From 992c238188a83befa0094a8c00bfead31aa302ed Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 28 Jul 2021 19:51:50 +0200 Subject: dma-buf: nuke seqno-fence MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Entirely unused. Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210729070330.41443-1-christian.koenig@amd.com --- include/linux/seqno-fence.h | 109 -------------------------------------------- 1 file changed, 109 deletions(-) delete mode 100644 include/linux/seqno-fence.h (limited to 'include/linux') diff --git a/include/linux/seqno-fence.h b/include/linux/seqno-fence.h deleted file mode 100644 index 3cca2b8fac43..000000000000 --- a/include/linux/seqno-fence.h +++ /dev/null @@ -1,109 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * seqno-fence, using a dma-buf to synchronize fencing - * - * Copyright (C) 2012 Texas Instruments - * Copyright (C) 2012 Canonical Ltd - * Authors: - * Rob Clark - * Maarten Lankhorst - */ - -#ifndef __LINUX_SEQNO_FENCE_H -#define __LINUX_SEQNO_FENCE_H - -#include -#include - -enum seqno_fence_condition { - SEQNO_FENCE_WAIT_GEQUAL, - SEQNO_FENCE_WAIT_NONZERO -}; - -struct seqno_fence { - struct dma_fence base; - - const struct dma_fence_ops *ops; - struct dma_buf *sync_buf; - uint32_t seqno_ofs; - enum seqno_fence_condition condition; -}; - -extern const struct dma_fence_ops seqno_fence_ops; - -/** - * to_seqno_fence - cast a fence to a seqno_fence - * @fence: fence to cast to a seqno_fence - * - * Returns NULL if the fence is not a seqno_fence, - * or the seqno_fence otherwise. - */ -static inline struct seqno_fence * -to_seqno_fence(struct dma_fence *fence) -{ - if (fence->ops != &seqno_fence_ops) - return NULL; - return container_of(fence, struct seqno_fence, base); -} - -/** - * seqno_fence_init - initialize a seqno fence - * @fence: seqno_fence to initialize - * @lock: pointer to spinlock to use for fence - * @sync_buf: buffer containing the memory location to signal on - * @context: the execution context this fence is a part of - * @seqno_ofs: the offset within @sync_buf - * @seqno: the sequence # to signal on - * @cond: fence wait condition - * @ops: the fence_ops for operations on this seqno fence - * - * This function initializes a struct seqno_fence with passed parameters, - * and takes a reference on sync_buf which is released on fence destruction. - * - * A seqno_fence is a dma_fence which can complete in software when - * enable_signaling is called, but it also completes when - * (s32)((sync_buf)[seqno_ofs] - seqno) >= 0 is true - * - * The seqno_fence will take a refcount on the sync_buf until it's - * destroyed, but actual lifetime of sync_buf may be longer if one of the - * callers take a reference to it. - * - * Certain hardware have instructions to insert this type of wait condition - * in the command stream, so no intervention from software would be needed. - * This type of fence can be destroyed before completed, however a reference - * on the sync_buf dma-buf can be taken. It is encouraged to re-use the same - * dma-buf for sync_buf, since mapping or unmapping the sync_buf to the - * device's vm can be expensive. - * - * It is recommended for creators of seqno_fence to call dma_fence_signal() - * before destruction. This will prevent possible issues from wraparound at - * time of issue vs time of check, since users can check dma_fence_is_signaled() - * before submitting instructions for the hardware to wait on the fence. - * However, when ops.enable_signaling is not called, it doesn't have to be - * done as soon as possible, just before there's any real danger of seqno - * wraparound. - */ -static inline void -seqno_fence_init(struct seqno_fence *fence, spinlock_t *lock, - struct dma_buf *sync_buf, uint32_t context, - uint32_t seqno_ofs, uint32_t seqno, - enum seqno_fence_condition cond, - const struct dma_fence_ops *ops) -{ - BUG_ON(!fence || !sync_buf || !ops); - BUG_ON(!ops->wait || !ops->enable_signaling || - !ops->get_driver_name || !ops->get_timeline_name); - - /* - * ops is used in dma_fence_init for get_driver_name, so needs to be - * initialized first - */ - fence->ops = ops; - dma_fence_init(&fence->base, &seqno_fence_ops, lock, context, seqno); - get_dma_buf(sync_buf); - fence->sync_buf = sync_buf; - fence->seqno_ofs = seqno_ofs; - fence->condition = cond; -} - -#endif /* __LINUX_SEQNO_FENCE_H */ -- cgit v1.2.3 From 880121be1179a0db3eb4fdb198108d9475b8be4c Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 15 Apr 2021 13:56:23 +0200 Subject: mm/vmscan: add sync_shrinkers function v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit While unplugging a device the TTM shrinker implementation needs a barrier to make sure that all concurrent shrink operations are done and no other CPU is referring to a device specific pool any more. Taking and releasing the shrinker semaphore on the write side after unmapping and freeing all pages from the device pool should make sure that no shrinker is running in paralell. This allows us to avoid the contented mutex in the TTM pool implementation for every alloc/free operation. v2: rework the commit message to make clear why we need this v3: rename the function and add more doc as suggested by Daniel Signed-off-by: Christian König Acked-by: Huang Rui Acked-by: Andrew Morton Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210820120528.81114-2-christian.koenig@amd.com --- include/linux/shrinker.h | 1 + mm/vmscan.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h index 9814fff58a69..76fbf92b04d9 100644 --- a/include/linux/shrinker.h +++ b/include/linux/shrinker.h @@ -93,4 +93,5 @@ extern void register_shrinker_prepared(struct shrinker *shrinker); extern int register_shrinker(struct shrinker *shrinker); extern void unregister_shrinker(struct shrinker *shrinker); extern void free_prealloced_shrinker(struct shrinker *shrinker); +extern void synchronize_shrinkers(void); #endif diff --git a/mm/vmscan.c b/mm/vmscan.c index 4620df62f0ff..5d22a63472f0 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -638,6 +638,21 @@ void unregister_shrinker(struct shrinker *shrinker) } EXPORT_SYMBOL(unregister_shrinker); +/** + * synchronize_shrinkers - Wait for all running shrinkers to complete. + * + * This is equivalent to calling unregister_shrink() and register_shrinker(), + * but atomically and with less overhead. This is useful to guarantee that all + * shrinker invocations have seen an update, before freeing memory, similar to + * rcu. + */ +void synchronize_shrinkers(void) +{ + down_write(&shrinker_rwsem); + up_write(&shrinker_rwsem); +} +EXPORT_SYMBOL(synchronize_shrinkers); + #define SHRINK_BATCH 128 static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, -- cgit v1.2.3 From d9edf92d496b61e5ac75b2b0aba5ea6c7f7ecdca Mon Sep 17 00:00:00 2001 From: Daniel Vetter Date: Thu, 5 Aug 2021 12:47:05 +0200 Subject: dma-resv: Give the docs a do-over MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Specifically document the new/clarified rules around how the shared fences do not have any ordering requirements against the exclusive fence. But also document all the things a bit better, given how central struct dma_resv to dynamic buffer management the docs have been very inadequat. - Lots more links to other pieces of the puzzle. Unfortunately ttm_buffer_object has no docs, so no links :-( - Explain/complain a bit about dma_resv_locking_ctx(). I still don't like that one, but fixing the ttm call chains is going to be horrible. Plus we want to plug in real slowpath locking when we do that anyway. - Main part of the patch is some actual docs for struct dma_resv. Overall I think we still have a lot of bad naming in this area (e.g. dma_resv.fence is singular, but contains the multiple shared fences), but I think that's more indicative of how the semantics and rules are just not great. Another thing that's real awkard is how chaining exclusive fences right now means direct dma_resv.exclusive_fence pointer access with an rcu_assign_pointer. Not so great either. v2: - Fix a pile of typos (Matt, Jason) - Hammer it in that breaking the rules leads to use-after-free issues around dma-buf sharing (Christian) Reviewed-by: Christian König Cc: Jason Ekstrand Cc: Matthew Auld Reviewed-by: Matthew Auld Signed-off-by: Daniel Vetter Cc: Sumit Semwal Cc: "Christian König" Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20210805104705.862416-21-daniel.vetter@ffwll.ch --- drivers/dma-buf/dma-resv.c | 24 ++++++++--- include/linux/dma-buf.h | 7 +++ include/linux/dma-resv.h | 104 ++++++++++++++++++++++++++++++++++++++++++--- 3 files changed, 124 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index e744fd87c63c..84fbe60629e3 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -48,6 +48,8 @@ * write operations) or N shared fences (read operations). The RCU * mechanism is used to protect read access to fences from locked * write-side updates. + * + * See struct dma_resv for more details. */ DEFINE_WD_CLASS(reservation_ww_class); @@ -137,7 +139,11 @@ EXPORT_SYMBOL(dma_resv_fini); * @num_fences: number of fences we want to add * * Should be called before dma_resv_add_shared_fence(). Must - * be called with obj->lock held. + * be called with @obj locked through dma_resv_lock(). + * + * Note that the preallocated slots need to be re-reserved if @obj is unlocked + * at any time before calling dma_resv_add_shared_fence(). This is validated + * when CONFIG_DEBUG_MUTEXES is enabled. * * RETURNS * Zero for success, or -errno @@ -234,8 +240,10 @@ EXPORT_SYMBOL(dma_resv_reset_shared_max); * @obj: the reservation object * @fence: the shared fence to add * - * Add a fence to a shared slot, obj->lock must be held, and + * Add a fence to a shared slot, @obj must be locked with dma_resv_lock(), and * dma_resv_reserve_shared() has been called. + * + * See also &dma_resv.fence for a discussion of the semantics. */ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence) { @@ -278,9 +286,11 @@ EXPORT_SYMBOL(dma_resv_add_shared_fence); /** * dma_resv_add_excl_fence - Add an exclusive fence. * @obj: the reservation object - * @fence: the shared fence to add + * @fence: the exclusive fence to add * - * Add a fence to the exclusive slot. The obj->lock must be held. + * Add a fence to the exclusive slot. @obj must be locked with dma_resv_lock(). + * Note that this function replaces all fences attached to @obj, see also + * &dma_resv.fence_excl for a discussion of the semantics. */ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) { @@ -609,9 +619,11 @@ static inline int dma_resv_test_signaled_single(struct dma_fence *passed_fence) * fence * * Callers are not required to hold specific locks, but maybe hold - * dma_resv_lock() already + * dma_resv_lock() already. + * * RETURNS - * true if all fences signaled, else false + * + * True if all fences signaled, else false. */ bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) { diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8b32b4bdd590..66470c37e471 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -420,6 +420,13 @@ struct dma_buf { * - Dynamic importers should set fences for any access that they can't * disable immediately from their &dma_buf_attach_ops.move_notify * callback. + * + * IMPORTANT: + * + * All drivers must obey the struct dma_resv rules, specifically the + * rules for updating fences, see &dma_resv.fence_excl and + * &dma_resv.fence. If these dependency rules are broken access tracking + * can be lost resulting in use after free issues. */ struct dma_resv *resv; diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e1ca2080a1ff..9100dd3dc21f 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -62,16 +62,90 @@ struct dma_resv_list { /** * struct dma_resv - a reservation object manages fences for a buffer - * @lock: update side lock - * @seq: sequence count for managing RCU read-side synchronization - * @fence_excl: the exclusive fence, if there is one currently - * @fence: list of current shared fences + * + * There are multiple uses for this, with sometimes slightly different rules in + * how the fence slots are used. + * + * One use is to synchronize cross-driver access to a struct dma_buf, either for + * dynamic buffer management or just to handle implicit synchronization between + * different users of the buffer in userspace. See &dma_buf.resv for a more + * in-depth discussion. + * + * The other major use is to manage access and locking within a driver in a + * buffer based memory manager. struct ttm_buffer_object is the canonical + * example here, since this is where reservation objects originated from. But + * use in drivers is spreading and some drivers also manage struct + * drm_gem_object with the same scheme. */ struct dma_resv { + /** + * @lock: + * + * Update side lock. Don't use directly, instead use the wrapper + * functions like dma_resv_lock() and dma_resv_unlock(). + * + * Drivers which use the reservation object to manage memory dynamically + * also use this lock to protect buffer object state like placement, + * allocation policies or throughout command submission. + */ struct ww_mutex lock; + + /** + * @seq: + * + * Sequence count for managing RCU read-side synchronization, allows + * read-only access to @fence_excl and @fence while ensuring we take a + * consistent snapshot. + */ seqcount_ww_mutex_t seq; + /** + * @fence_excl: + * + * The exclusive fence, if there is one currently. + * + * There are two ways to update this fence: + * + * - First by calling dma_resv_add_excl_fence(), which replaces all + * fences attached to the reservation object. To guarantee that no + * fences are lost, this new fence must signal only after all previous + * fences, both shared and exclusive, have signalled. In some cases it + * is convenient to achieve that by attaching a struct dma_fence_array + * with all the new and old fences. + * + * - Alternatively the fence can be set directly, which leaves the + * shared fences unchanged. To guarantee that no fences are lost, this + * new fence must signal only after the previous exclusive fence has + * signalled. Since the shared fences are staying intact, it is not + * necessary to maintain any ordering against those. If semantically + * only a new access is added without actually treating the previous + * one as a dependency the exclusive fences can be strung together + * using struct dma_fence_chain. + * + * Note that actual semantics of what an exclusive or shared fence mean + * is defined by the user, for reservation objects shared across drivers + * see &dma_buf.resv. + */ struct dma_fence __rcu *fence_excl; + + /** + * @fence: + * + * List of current shared fences. + * + * There are no ordering constraints of shared fences against the + * exclusive fence slot. If a waiter needs to wait for all access, it + * has to wait for both sets of fences to signal. + * + * A new fence is added by calling dma_resv_add_shared_fence(). Since + * this often needs to be done past the point of no return in command + * submission it cannot fail, and therefore sufficient slots need to be + * reserved by calling dma_resv_reserve_shared(). + * + * Note that actual semantics of what an exclusive or shared fence mean + * is defined by the user, for reservation objects shared across drivers + * see &dma_buf.resv. + */ struct dma_resv_list __rcu *fence; }; @@ -98,6 +172,13 @@ static inline void dma_resv_reset_shared_max(struct dma_resv *obj) {} * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation * object may be locked by itself by passing NULL as @ctx. + * + * When a die situation is indicated by returning -EDEADLK all locks held by + * @ctx must be unlocked and then dma_resv_lock_slow() called on @obj. + * + * Unlocked by calling dma_resv_unlock(). + * + * See also dma_resv_lock_interruptible() for the interruptible variant. */ static inline int dma_resv_lock(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -119,6 +200,12 @@ static inline int dma_resv_lock(struct dma_resv *obj, * undefined order, a #ww_acquire_ctx is passed to unwind if a cycle * is detected. See ww_mutex_lock() and ww_acquire_init(). A reservation * object may be locked by itself by passing NULL as @ctx. + * + * When a die situation is indicated by returning -EDEADLK all locks held by + * @ctx must be unlocked and then dma_resv_lock_slow_interruptible() called on + * @obj. + * + * Unlocked by calling dma_resv_unlock(). */ static inline int dma_resv_lock_interruptible(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -134,6 +221,8 @@ static inline int dma_resv_lock_interruptible(struct dma_resv *obj, * Acquires the reservation object after a die case. This function * will sleep until the lock becomes available. See dma_resv_lock() as * well. + * + * See also dma_resv_lock_slow_interruptible() for the interruptible variant. */ static inline void dma_resv_lock_slow(struct dma_resv *obj, struct ww_acquire_ctx *ctx) @@ -167,7 +256,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj, * if they overlap with a writer. * * Also note that since no context is provided, no deadlock protection is - * possible. + * possible, which is also not needed for a trylock. * * Returns true if the lock was acquired, false otherwise. */ @@ -193,6 +282,11 @@ static inline bool dma_resv_is_locked(struct dma_resv *obj) * * Returns the context used to lock a reservation object or NULL if no context * was used or the object is not locked at all. + * + * WARNING: This interface is pretty horrible, but TTM needs it because it + * doesn't pass the struct ww_acquire_ctx around in some very long callchains. + * Everyone else just uses it to check whether they're holding a reservation or + * not. */ static inline struct ww_acquire_ctx *dma_resv_locking_ctx(struct dma_resv *obj) { -- cgit v1.2.3 From d72277b6c37db66b457fd6b77aabd5e930d58687 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 29 Jul 2021 08:39:31 +0200 Subject: dma-buf: nuke DMA_FENCE_TRACE macros v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Only the DRM GPU scheduler, radeon and amdgpu where using them and they depend on a non existing config option to actually emit some code. v2: keep the signal path as is for now Signed-off-by: Christian König Acked-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210818105443.1578-1-christian.koenig@amd.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 10 +--------- drivers/gpu/drm/radeon/radeon_fence.c | 24 ++++-------------------- drivers/gpu/drm/scheduler/sched_fence.c | 18 ++---------------- include/linux/dma-fence.h | 22 ---------------------- 4 files changed, 7 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c index 0b1c48590c43..c65994e382bd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c @@ -246,7 +246,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) struct amdgpu_fence_driver *drv = &ring->fence_drv; struct amdgpu_device *adev = ring->adev; uint32_t seq, last_seq; - int r; do { last_seq = atomic_read(&ring->fence_drv.last_seq); @@ -278,12 +277,7 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring) if (!fence) continue; - r = dma_fence_signal(fence); - if (!r) - DMA_FENCE_TRACE(fence, "signaled from irq context\n"); - else - BUG(); - + dma_fence_signal(fence); dma_fence_put(fence); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -639,8 +633,6 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f) if (!timer_pending(&ring->fence_drv.fallback_timer)) amdgpu_fence_schedule_fallback(ring); - DMA_FENCE_TRACE(&fence->base, "armed on ring %i!\n", ring->idx); - return true; } diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c index 18f2c2e0dfb3..3f351d222cbb 100644 --- a/drivers/gpu/drm/radeon/radeon_fence.c +++ b/drivers/gpu/drm/radeon/radeon_fence.c @@ -176,18 +176,11 @@ static int radeon_fence_check_signaled(wait_queue_entry_t *wait, unsigned mode, */ seq = atomic64_read(&fence->rdev->fence_drv[fence->ring].last_seq); if (seq >= fence->seq) { - int ret = dma_fence_signal_locked(&fence->base); - - if (!ret) - DMA_FENCE_TRACE(&fence->base, "signaled from irq context\n"); - else - DMA_FENCE_TRACE(&fence->base, "was already signaled\n"); - + dma_fence_signal_locked(&fence->base); radeon_irq_kms_sw_irq_put(fence->rdev, fence->ring); __remove_wait_queue(&fence->rdev->fence_queue, &fence->fence_wake); dma_fence_put(&fence->base); - } else - DMA_FENCE_TRACE(&fence->base, "pending\n"); + } return 0; } @@ -422,8 +415,6 @@ static bool radeon_fence_enable_signaling(struct dma_fence *f) fence->fence_wake.func = radeon_fence_check_signaled; __add_wait_queue(&rdev->fence_queue, &fence->fence_wake); dma_fence_get(f); - - DMA_FENCE_TRACE(&fence->base, "armed on ring %i!\n", fence->ring); return true; } @@ -441,11 +432,7 @@ bool radeon_fence_signaled(struct radeon_fence *fence) return true; if (radeon_fence_seq_signaled(fence->rdev, fence->seq, fence->ring)) { - int ret; - - ret = dma_fence_signal(&fence->base); - if (!ret) - DMA_FENCE_TRACE(&fence->base, "signaled from radeon_fence_signaled\n"); + dma_fence_signal(&fence->base); return true; } return false; @@ -550,7 +537,6 @@ long radeon_fence_wait_timeout(struct radeon_fence *fence, bool intr, long timeo { uint64_t seq[RADEON_NUM_RINGS] = {}; long r; - int r_sig; /* * This function should not be called on !radeon fences. @@ -567,9 +553,7 @@ long radeon_fence_wait_timeout(struct radeon_fence *fence, bool intr, long timeo return r; } - r_sig = dma_fence_signal(&fence->base); - if (!r_sig) - DMA_FENCE_TRACE(&fence->base, "signaled from fence_wait\n"); + dma_fence_signal(&fence->base); return r; } diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index bcea035cf4c6..db3fd1303fc4 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -50,26 +50,12 @@ static void __exit drm_sched_fence_slab_fini(void) void drm_sched_fence_scheduled(struct drm_sched_fence *fence) { - int ret = dma_fence_signal(&fence->scheduled); - - if (!ret) - DMA_FENCE_TRACE(&fence->scheduled, - "signaled from irq context\n"); - else - DMA_FENCE_TRACE(&fence->scheduled, - "was already signaled\n"); + dma_fence_signal(&fence->scheduled); } void drm_sched_fence_finished(struct drm_sched_fence *fence) { - int ret = dma_fence_signal(&fence->finished); - - if (!ret) - DMA_FENCE_TRACE(&fence->finished, - "signaled from irq context\n"); - else - DMA_FENCE_TRACE(&fence->finished, - "was already signaled\n"); + dma_fence_signal(&fence->finished); } static const char *drm_sched_fence_get_driver_name(struct dma_fence *fence) diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 6ffb4b2c6371..4cc119ab272f 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -590,26 +590,4 @@ struct dma_fence *dma_fence_get_stub(void); struct dma_fence *dma_fence_allocate_private_stub(void); u64 dma_fence_context_alloc(unsigned num); -#define DMA_FENCE_TRACE(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - if (IS_ENABLED(CONFIG_DMA_FENCE_TRACE)) \ - pr_info("f %llu#%llu: " fmt, \ - __ff->context, __ff->seqno, ##args); \ - } while (0) - -#define DMA_FENCE_WARN(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_warn("f %llu#%llu: " fmt, __ff->context, __ff->seqno,\ - ##args); \ - } while (0) - -#define DMA_FENCE_ERR(f, fmt, args...) \ - do { \ - struct dma_fence *__ff = (f); \ - pr_err("f %llu#%llu: " fmt, __ff->context, __ff->seqno, \ - ##args); \ - } while (0) - #endif /* __LINUX_DMA_FENCE_H */ -- cgit v1.2.3 From b83dcd753dbe42d5e7467ab65124f3d0a6002dc3 Mon Sep 17 00:00:00 2001 From: Christian König Date: Wed, 21 Jul 2021 11:01:04 +0200 Subject: dma-buf: clarify dma_fence_ops->wait documentation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This callback is pretty much deprecated and should not be used by new implementations. Clarify that in the documentation as well. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210901120240.7339-2-christian.koenig@amd.com --- include/linux/dma-fence.h | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 4cc119ab272f..a706b7bf51d7 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -214,19 +214,15 @@ struct dma_fence_ops { * Custom wait implementation, defaults to dma_fence_default_wait() if * not set. * - * The dma_fence_default_wait implementation should work for any fence, as long - * as @enable_signaling works correctly. This hook allows drivers to - * have an optimized version for the case where a process context is - * already available, e.g. if @enable_signaling for the general case - * needs to set up a worker thread. + * Deprecated and should not be used by new implementations. Only used + * by existing implementations which need special handling for their + * hardware reset procedure. * * Must return -ERESTARTSYS if the wait is intr = true and the wait was * interrupted, and remaining jiffies if fence has signaled, or 0 if wait * timed out. Can also return other error values on custom implementations, * which should be treated as if the fence is signaled. For example a hardware * lockup could be reported like that. - * - * This callback is optional. */ signed long (*wait)(struct dma_fence *fence, bool intr, signed long timeout); -- cgit v1.2.3 From cb19c107979b8000825060cb5b84dfe9212f4f86 Mon Sep 17 00:00:00 2001 From: Yongqiang Niu Date: Mon, 2 Aug 2021 16:59:32 +0800 Subject: soc: mediatek: mmsys: add comp OVL_2L2/POSTMASK/RDMA4 This patch add some more ddp component OVL_2L2 is ovl which include 2 layers overlay POSTMASK control round corner for display frame RDMA4 read dma buffer Signed-off-by: Yongqiang Niu Reviewed-by: Chun-Kuang Hu Reviewed-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/1627894773-23872-2-git-send-email-yongqiang.niu@mediatek.com Signed-off-by: Matthias Brugger --- include/linux/soc/mediatek/mtk-mmsys.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk-mmsys.h b/include/linux/soc/mediatek/mtk-mmsys.h index 2228bf6133da..4bba275e235a 100644 --- a/include/linux/soc/mediatek/mtk-mmsys.h +++ b/include/linux/soc/mediatek/mtk-mmsys.h @@ -29,13 +29,16 @@ enum mtk_ddp_comp_id { DDP_COMPONENT_OVL0, DDP_COMPONENT_OVL_2L0, DDP_COMPONENT_OVL_2L1, + DDP_COMPONENT_OVL_2L2, DDP_COMPONENT_OVL1, + DDP_COMPONENT_POSTMASK0, DDP_COMPONENT_PWM0, DDP_COMPONENT_PWM1, DDP_COMPONENT_PWM2, DDP_COMPONENT_RDMA0, DDP_COMPONENT_RDMA1, DDP_COMPONENT_RDMA2, + DDP_COMPONENT_RDMA4, DDP_COMPONENT_UFOE, DDP_COMPONENT_WDMA0, DDP_COMPONENT_WDMA1, -- cgit v1.2.3 From f55e36d5ab76c3097ff36ecea60b91c6b0d80fc8 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Mon, 13 Sep 2021 10:50:24 +0300 Subject: qed: Improve the stack space of filter_config() As it was reported and discussed in: https://lore.kernel.org/lkml/CAHk-=whF9F89vsfH8E9TGc0tZA-yhzi2Di8wOtquNB5vRkFX5w@mail.gmail.com/ This patch improves the stack space of qede_config_rx_mode() by splitting filter_config() to 3 functions and removing the union qed_filter_type_params. Reported-by: Naresh Kamboju Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_l2.c | 23 ++----------- drivers/net/ethernet/qlogic/qede/qede_filter.c | 47 +++++++++++--------------- include/linux/qed/qed_eth_if.h | 21 +++++------- 3 files changed, 30 insertions(+), 61 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index dfaf10edfabf..ba8c7a31cce1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2763,25 +2763,6 @@ static int qed_configure_filter_mcast(struct qed_dev *cdev, return qed_filter_mcast_cmd(cdev, &mcast, QED_SPQ_MODE_CB, NULL); } -static int qed_configure_filter(struct qed_dev *cdev, - struct qed_filter_params *params) -{ - enum qed_filter_rx_mode_type accept_flags; - - switch (params->type) { - case QED_FILTER_TYPE_UCAST: - return qed_configure_filter_ucast(cdev, ¶ms->filter.ucast); - case QED_FILTER_TYPE_MCAST: - return qed_configure_filter_mcast(cdev, ¶ms->filter.mcast); - case QED_FILTER_TYPE_RX_MODE: - accept_flags = params->filter.accept_flags; - return qed_configure_filter_rx_mode(cdev, accept_flags); - default: - DP_NOTICE(cdev, "Unknown filter type %d\n", (int)params->type); - return -EINVAL; - } -} - static int qed_configure_arfs_searcher(struct qed_dev *cdev, enum qed_filter_config_mode mode) { @@ -2904,7 +2885,9 @@ static const struct qed_eth_ops qed_eth_ops_pass = { .q_rx_stop = &qed_stop_rxq, .q_tx_start = &qed_start_txq, .q_tx_stop = &qed_stop_txq, - .filter_config = &qed_configure_filter, + .filter_config_rx_mode = &qed_configure_filter_rx_mode, + .filter_config_ucast = &qed_configure_filter_ucast, + .filter_config_mcast = &qed_configure_filter_mcast, .fastpath_stop = &qed_fastpath_stop, .eth_cqe_completion = &qed_fp_cqe_completion, .get_vport_stats = &qed_get_vport_stats, diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index a2e4dfb5cb44..f99b085b56a5 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -619,30 +619,28 @@ static int qede_set_ucast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, unsigned char mac[ETH_ALEN]) { - struct qed_filter_params filter_cmd; + struct qed_filter_ucast_params ucast; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_UCAST; - filter_cmd.filter.ucast.type = opcode; - filter_cmd.filter.ucast.mac_valid = 1; - ether_addr_copy(filter_cmd.filter.ucast.mac, mac); + memset(&ucast, 0, sizeof(ucast)); + ucast.type = opcode; + ucast.mac_valid = 1; + ether_addr_copy(ucast.mac, mac); - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_ucast(edev->cdev, &ucast); } static int qede_set_ucast_rx_vlan(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, u16 vid) { - struct qed_filter_params filter_cmd; + struct qed_filter_ucast_params ucast; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_UCAST; - filter_cmd.filter.ucast.type = opcode; - filter_cmd.filter.ucast.vlan_valid = 1; - filter_cmd.filter.ucast.vlan = vid; + memset(&ucast, 0, sizeof(ucast)); + ucast.type = opcode; + ucast.vlan_valid = 1; + ucast.vlan = vid; - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_ucast(edev->cdev, &ucast); } static int qede_config_accept_any_vlan(struct qede_dev *edev, bool action) @@ -1057,18 +1055,17 @@ static int qede_set_mcast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, unsigned char *mac, int num_macs) { - struct qed_filter_params filter_cmd; + struct qed_filter_mcast_params mcast; int i; - memset(&filter_cmd, 0, sizeof(filter_cmd)); - filter_cmd.type = QED_FILTER_TYPE_MCAST; - filter_cmd.filter.mcast.type = opcode; - filter_cmd.filter.mcast.num = num_macs; + memset(&mcast, 0, sizeof(mcast)); + mcast.type = opcode; + mcast.num = num_macs; for (i = 0; i < num_macs; i++, mac += ETH_ALEN) - ether_addr_copy(filter_cmd.filter.mcast.mac[i], mac); + ether_addr_copy(mcast.mac[i], mac); - return edev->ops->filter_config(edev->cdev, &filter_cmd); + return edev->ops->filter_config_mcast(edev->cdev, &mcast); } int qede_set_mac_addr(struct net_device *ndev, void *p) @@ -1194,7 +1191,6 @@ void qede_config_rx_mode(struct net_device *ndev) { enum qed_filter_rx_mode_type accept_flags; struct qede_dev *edev = netdev_priv(ndev); - struct qed_filter_params rx_mode; unsigned char *uc_macs, *temp; struct netdev_hw_addr *ha; int rc, uc_count; @@ -1220,10 +1216,6 @@ void qede_config_rx_mode(struct net_device *ndev) netif_addr_unlock_bh(ndev); - /* Configure the struct for the Rx mode */ - memset(&rx_mode, 0, sizeof(struct qed_filter_params)); - rx_mode.type = QED_FILTER_TYPE_RX_MODE; - /* Remove all previous unicast secondary macs and multicast macs * (configure / leave the primary mac) */ @@ -1271,8 +1263,7 @@ void qede_config_rx_mode(struct net_device *ndev) qede_config_accept_any_vlan(edev, false); } - rx_mode.filter.accept_flags = accept_flags; - edev->ops->filter_config(edev->cdev, &rx_mode); + edev->ops->filter_config_rx_mode(edev->cdev, accept_flags); out: kfree(uc_macs); } diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 812a4d751163..4df0bf0a0864 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -145,12 +145,6 @@ struct qed_filter_mcast_params { unsigned char mac[64][ETH_ALEN]; }; -union qed_filter_type_params { - enum qed_filter_rx_mode_type accept_flags; - struct qed_filter_ucast_params ucast; - struct qed_filter_mcast_params mcast; -}; - enum qed_filter_type { QED_FILTER_TYPE_UCAST, QED_FILTER_TYPE_MCAST, @@ -158,11 +152,6 @@ enum qed_filter_type { QED_MAX_FILTER_TYPES, }; -struct qed_filter_params { - enum qed_filter_type type; - union qed_filter_type_params filter; -}; - struct qed_tunn_params { u16 vxlan_port; u8 update_vxlan_port; @@ -314,8 +303,14 @@ struct qed_eth_ops { int (*q_tx_stop)(struct qed_dev *cdev, u8 rss_id, void *handle); - int (*filter_config)(struct qed_dev *cdev, - struct qed_filter_params *params); + int (*filter_config_rx_mode)(struct qed_dev *cdev, + enum qed_filter_rx_mode_type type); + + int (*filter_config_ucast)(struct qed_dev *cdev, + struct qed_filter_ucast_params *params); + + int (*filter_config_mcast)(struct qed_dev *cdev, + struct qed_filter_mcast_params *params); int (*fastpath_stop)(struct qed_dev *cdev); -- cgit v1.2.3 From 537d3af1bee8ad1415fda9b622d1ea6d1ae76dfa Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Mon, 12 Jul 2021 14:39:12 +0200 Subject: rpmsg: Fix rpmsg_create_ept return when RPMSG config is not defined According to the description of the rpmsg_create_ept in rpmsg_core.c the function should return NULL on error. Fixes: 2c8a57088045 ("rpmsg: Provide function stubs for API") Signed-off-by: Arnaud Pouliquen Reviewed-by: Mathieu Poirier Link: https://lore.kernel.org/r/20210712123912.10672-1-arnaud.pouliquen@foss.st.com Signed-off-by: Bjorn Andersson --- include/linux/rpmsg.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index d97dcd049f18..a8dcf8a9ae88 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -231,7 +231,7 @@ static inline struct rpmsg_endpoint *rpmsg_create_ept(struct rpmsg_device *rpdev /* This shouldn't be possible */ WARN_ON(1); - return ERR_PTR(-ENXIO); + return NULL; } static inline int rpmsg_send(struct rpmsg_endpoint *ept, void *data, int len) -- cgit v1.2.3 From c22ac2a3d4bd83411ebf0b1726e9e5fc4f5e7ebf Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 10 Sep 2021 11:33:50 -0700 Subject: perf: Enable branch record for software events The typical way to access branch record (e.g. Intel LBR) is via hardware perf_event. For CPUs with FREEZE_LBRS_ON_PMI support, PMI could capture reliable LBR. On the other hand, LBR could also be useful in non-PMI scenario. For example, in kretprobe or bpf fexit program, LBR could provide a lot of information on what happened with the function. Add API to use branch record for software use. Note that, when the software event triggers, it is necessary to stop the branch record hardware asap. Therefore, static_call is used to remove some branch instructions in this process. Suggested-by: Peter Zijlstra Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Andrii Nakryiko Acked-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/bpf/20210910183352.3151445-2-songliubraving@fb.com --- arch/x86/events/intel/core.c | 67 ++++++++++++++++++++++++++++++++++++++++---- arch/x86/events/intel/ds.c | 2 +- arch/x86/events/intel/lbr.c | 20 ++++--------- arch/x86/events/perf_event.h | 19 +++++++++++++ include/linux/perf_event.h | 23 +++++++++++++++ kernel/events/core.c | 2 ++ 6 files changed, 111 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..1248fc1937f8 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2143,19 +2143,19 @@ static __initconst const u64 knl_hw_cache_extra_regs * However, there are some cases which may change PEBS status, e.g. PMI * throttle. The PEBS_ENABLE should be updated where the status changes. */ -static void __intel_pmu_disable_all(void) +static __always_inline void __intel_pmu_disable_all(bool bts) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0); - if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) + if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) intel_pmu_disable_bts(); } -static void intel_pmu_disable_all(void) +static __always_inline void intel_pmu_disable_all(void) { - __intel_pmu_disable_all(); + __intel_pmu_disable_all(true); intel_pmu_pebs_disable_all(); intel_pmu_lbr_disable_all(); } @@ -2186,6 +2186,49 @@ static void intel_pmu_enable_all(int added) __intel_pmu_enable_all(added, false); } +static noinline int +__intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, + unsigned int cnt, unsigned long flags) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + + intel_pmu_lbr_read(); + cnt = min_t(unsigned int, cnt, x86_pmu.lbr_nr); + + memcpy(entries, cpuc->lbr_entries, sizeof(struct perf_branch_entry) * cnt); + intel_pmu_enable_all(0); + local_irq_restore(flags); + return cnt; +} + +static int +intel_pmu_snapshot_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + unsigned long flags; + + /* must not have branches... */ + local_irq_save(flags); + __intel_pmu_disable_all(false); /* we don't care about BTS */ + __intel_pmu_pebs_disable_all(); + __intel_pmu_lbr_disable(); + /* ... until here */ + return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); +} + +static int +intel_pmu_snapshot_arch_branch_stack(struct perf_branch_entry *entries, unsigned int cnt) +{ + unsigned long flags; + + /* must not have branches... */ + local_irq_save(flags); + __intel_pmu_disable_all(false); /* we don't care about BTS */ + __intel_pmu_pebs_disable_all(); + __intel_pmu_arch_lbr_disable(); + /* ... until here */ + return __intel_pmu_snapshot_branch_stack(entries, cnt, flags); +} + /* * Workaround for: * Intel Errata AAK100 (model 26) @@ -2929,7 +2972,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) apic_write(APIC_LVTPC, APIC_DM_NMI); intel_bts_disable_local(); cpuc->enabled = 0; - __intel_pmu_disable_all(); + __intel_pmu_disable_all(true); handled = intel_pmu_drain_bts_buffer(); handled += intel_bts_interrupt(); status = intel_pmu_get_status(); @@ -6283,9 +6326,21 @@ __init int intel_pmu_init(void) x86_pmu.lbr_nr = 0; } - if (x86_pmu.lbr_nr) + if (x86_pmu.lbr_nr) { pr_cont("%d-deep LBR, ", x86_pmu.lbr_nr); + /* only support branch_stack snapshot for perfmon >= v2 */ + if (x86_pmu.disable_all == intel_pmu_disable_all) { + if (boot_cpu_has(X86_FEATURE_ARCH_LBR)) { + static_call_update(perf_snapshot_branch_stack, + intel_pmu_snapshot_arch_branch_stack); + } else { + static_call_update(perf_snapshot_branch_stack, + intel_pmu_snapshot_branch_stack); + } + } + } + intel_pmu_check_extra_regs(x86_pmu.extra_regs); /* Support full width counters using alternative MSR range */ diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8647713276a7..ac5991fea9ee 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1301,7 +1301,7 @@ void intel_pmu_pebs_disable_all(void) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); + __intel_pmu_pebs_disable_all(); } static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 9e6d6eaeb4cb..6b72e9b55c69 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -228,20 +228,6 @@ static void __intel_pmu_lbr_enable(bool pmi) wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN); } -static void __intel_pmu_lbr_disable(void) -{ - u64 debugctl; - - if (static_cpu_has(X86_FEATURE_ARCH_LBR)) { - wrmsrl(MSR_ARCH_LBR_CTL, 0); - return; - } - - rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); - debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); -} - void intel_pmu_lbr_reset_32(void) { int i; @@ -779,8 +765,12 @@ void intel_pmu_lbr_disable_all(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - if (cpuc->lbr_users && !vlbr_exclude_host()) + if (cpuc->lbr_users && !vlbr_exclude_host()) { + if (static_cpu_has(X86_FEATURE_ARCH_LBR)) + return __intel_pmu_arch_lbr_disable(); + __intel_pmu_lbr_disable(); + } } void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e3ac05c97b5e..0e3e596e33cd 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1240,6 +1240,25 @@ static inline bool intel_pmu_has_bts(struct perf_event *event) return intel_pmu_has_bts_period(event, hwc->sample_period); } +static __always_inline void __intel_pmu_pebs_disable_all(void) +{ + wrmsrl(MSR_IA32_PEBS_ENABLE, 0); +} + +static __always_inline void __intel_pmu_arch_lbr_disable(void) +{ + wrmsrl(MSR_ARCH_LBR_CTL, 0); +} + +static __always_inline void __intel_pmu_lbr_disable(void) +{ + u64 debugctl; + + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); + debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); +} + int intel_pmu_save_and_restart(struct perf_event *event); struct event_constraint * diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fe156a8170aa..0cbc5dfe1110 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -57,6 +57,7 @@ struct perf_guest_info_callbacks { #include #include #include +#include #include struct perf_callchain_entry { @@ -1612,4 +1613,26 @@ extern void __weak arch_perf_update_userpage(struct perf_event *event, extern __weak u64 arch_perf_get_page_size(struct mm_struct *mm, unsigned long addr); #endif +/* + * Snapshot branch stack on software events. + * + * Branch stack can be very useful in understanding software events. For + * example, when a long function, e.g. sys_perf_event_open, returns an + * errno, it is not obvious why the function failed. Branch stack could + * provide very helpful information in this type of scenarios. + * + * On software event, it is necessary to stop the hardware branch recorder + * fast. Otherwise, the hardware register/buffer will be flushed with + * entries of the triggering event. Therefore, static call is used to + * stop the hardware recorder. + */ + +/* + * cnt is the number of entries allocated for entries. + * Return number of entries copied to . + */ +typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, + unsigned int cnt); +DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); + #endif /* _LINUX_PERF_EVENT_H */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 744e8726c5b2..349f80aa9e7d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -13435,3 +13435,5 @@ struct cgroup_subsys perf_event_cgrp_subsys = { .threaded = true, }; #endif /* CONFIG_CGROUP_PERF */ + +DEFINE_STATIC_CALL_RET0(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); -- cgit v1.2.3 From efeff6b39b9de4480572c7b0c5eb77204795cb57 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 5 Aug 2021 13:28:24 -0700 Subject: rcutorture: Warn on individual rcu_torture_init() error conditions When running rcutorture as a module, any rcu_torture_init() issues will be reflected in the error code from modprobe or insmod, as the case may be. However, these error codes are not available when running rcutorture built-in, for example, when using the kvm.sh script. This commit therefore adds WARN_ON_ONCE() to allow distinguishing rcu_torture_init() errors when running rcutorture built-in. Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 8 ++++++++ kernel/rcu/rcutorture.c | 30 +++++++++++++++--------------- 2 files changed, 23 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 0910c5803f35..24f58e50a94b 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -47,6 +47,14 @@ do { \ } while (0) void verbose_torout_sleep(void); +#define torture_init_error(firsterr) \ +({ \ + int ___firsterr = (firsterr); \ + \ + WARN_ONCE(!IS_MODULE(CONFIG_RCU_TORTURE_TEST) && ___firsterr < 0, "Torture-test initialization failed with error code %d\n", ___firsterr); \ + ___firsterr < 0; \ +}) + /* Definitions for online/offline exerciser. */ #ifdef CONFIG_HOTPLUG_CPU int torture_num_online_cpus(void); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 59254fa15cc6..b90cd4d98a20 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -3037,7 +3037,7 @@ rcu_torture_init(void) rcu_torture_write_types(); firsterr = torture_create_kthread(rcu_torture_writer, NULL, writer_task); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; if (nfakewriters > 0) { fakewriter_tasks = kcalloc(nfakewriters, @@ -3052,7 +3052,7 @@ rcu_torture_init(void) for (i = 0; i < nfakewriters; i++) { firsterr = torture_create_kthread(rcu_torture_fakewriter, NULL, fakewriter_tasks[i]); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } reader_tasks = kcalloc(nrealreaders, sizeof(reader_tasks[0]), @@ -3068,7 +3068,7 @@ rcu_torture_init(void) rcu_torture_reader_mbchk[i].rtc_chkrdr = -1; firsterr = torture_create_kthread(rcu_torture_reader, (void *)i, reader_tasks[i]); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } nrealnocbers = nocbs_nthreads; @@ -3088,18 +3088,18 @@ rcu_torture_init(void) } for (i = 0; i < nrealnocbers; i++) { firsterr = torture_create_kthread(rcu_nocb_toggle, NULL, nocb_tasks[i]); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } if (stat_interval > 0) { firsterr = torture_create_kthread(rcu_torture_stats, NULL, stats_task); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } if (test_no_idle_hz && shuffle_interval > 0) { firsterr = torture_shuffle_init(shuffle_interval * HZ); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } if (stutter < 0) @@ -3109,7 +3109,7 @@ rcu_torture_init(void) t = cur_ops->stall_dur ? cur_ops->stall_dur() : stutter * HZ; firsterr = torture_stutter_init(stutter * HZ, t); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } if (fqs_duration < 0) @@ -3118,7 +3118,7 @@ rcu_torture_init(void) /* Create the fqs thread */ firsterr = torture_create_kthread(rcu_torture_fqs, NULL, fqs_task); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; } if (test_boost_interval < 1) @@ -3132,7 +3132,7 @@ rcu_torture_init(void) firsterr = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "RCU_TORTURE", rcutorture_booster_init, rcutorture_booster_cleanup); - if (firsterr < 0) + if (torture_init_error(firsterr)) goto unwind; rcutor_hp = firsterr; @@ -3153,23 +3153,23 @@ rcu_torture_init(void) } shutdown_jiffies = jiffies + shutdown_secs * HZ; firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval, rcutorture_sync); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; firsterr = rcu_torture_stall_init(); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; firsterr = rcu_torture_fwd_prog_init(); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; firsterr = rcu_torture_barrier_init(); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; firsterr = rcu_torture_read_exit_init(); - if (firsterr) + if (torture_init_error(firsterr)) goto unwind; if (object_debug) rcu_test_debug_objects(); -- cgit v1.2.3 From f4c87dbbef2638f6da6e29b5e998e3b1dcdb08ee Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Mon, 9 Aug 2021 13:25:13 +0200 Subject: kcsan: Save instruction pointer for scoped accesses Save the instruction pointer for scoped accesses, so that it becomes possible for the reporting code to construct more accurate stack traces that will show the start of the scope. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 3 +++ kernel/kcsan/core.c | 12 +++++++++--- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 9fd0ad80fef6..5f5965246877 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -100,9 +100,12 @@ void kcsan_set_access_mask(unsigned long mask); /* Scoped access information. */ struct kcsan_scoped_access { struct list_head list; + /* Access information. */ const volatile void *ptr; size_t size; int type; + /* Location where scoped access was set up. */ + unsigned long ip; }; /* * Automatically call kcsan_end_scoped_access() when kcsan_scoped_access goes diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index bffd1d95addb..8b20af541776 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -202,6 +202,9 @@ static __always_inline struct kcsan_ctx *get_ctx(void) return in_task() ? ¤t->kcsan_ctx : raw_cpu_ptr(&kcsan_cpu_ctx); } +static __always_inline void +check_access(const volatile void *ptr, size_t size, int type, unsigned long ip); + /* Check scoped accesses; never inline because this is a slow-path! */ static noinline void kcsan_check_scoped_accesses(void) { @@ -210,8 +213,10 @@ static noinline void kcsan_check_scoped_accesses(void) struct kcsan_scoped_access *scoped_access; ctx->scoped_accesses.prev = NULL; /* Avoid recursion. */ - list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) - __kcsan_check_access(scoped_access->ptr, scoped_access->size, scoped_access->type); + list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) { + check_access(scoped_access->ptr, scoped_access->size, + scoped_access->type, scoped_access->ip); + } ctx->scoped_accesses.prev = prev_save; } @@ -767,6 +772,7 @@ kcsan_begin_scoped_access(const volatile void *ptr, size_t size, int type, sa->ptr = ptr; sa->size = size; sa->type = type; + sa->ip = _RET_IP_; if (!ctx->scoped_accesses.prev) /* Lazy initialize list head. */ INIT_LIST_HEAD(&ctx->scoped_accesses); @@ -798,7 +804,7 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) ctx->disable_count--; - __kcsan_check_access(sa->ptr, sa->size, sa->type); + check_access(sa->ptr, sa->size, sa->type, sa->ip); } EXPORT_SYMBOL(kcsan_end_scoped_access); -- cgit v1.2.3 From 8988bacd6045adf39719e5057e43170f83bd1709 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Tue, 31 Aug 2021 17:30:44 +0800 Subject: kobject: unexport kobject_create() in kobject.h The function kobject_create() is only used by one caller, kobject_create_and_add(), no other driver uses it, nor is exported to other modules. However it's still exported in kobject.h, and can sometimes confuse users of kobject.h. Since all users should call kobject_create_and_add(), or if extra attributes are needed, should alloc the memory manually then call kobject_init_and_add(). Signed-off-by: Qu Wenruo Link: https://lore.kernel.org/r/20210831093044.110729-1-wqu@suse.com Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 1 - lib/kobject.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index ea30529fba08..efd56f990a46 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -101,7 +101,6 @@ int kobject_init_and_add(struct kobject *kobj, extern void kobject_del(struct kobject *kobj); -extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); diff --git a/lib/kobject.c b/lib/kobject.c index ea53b30cf483..4a56f519139d 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -777,7 +777,7 @@ static struct kobj_type dynamic_kobj_ktype = { * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ -struct kobject *kobject_create(void) +static struct kobject *kobject_create(void) { struct kobject *kobj; -- cgit v1.2.3 From 82bcb7fb649844a561ff1ac2e2ace4252bdff793 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 23 Aug 2021 14:22:01 +0300 Subject: iio: st_sensors: remove st_sensors_deallocate_trigger() function This change converts the st_sensors_allocate_trigger() to use device-managed functions. The parent device of the IIO device object is used. This is based on the assumption that all other devm_ calls in the ST sensors use this reference. That makes the st_sensors_deallocate_trigger() function un-needed, so it can be removed. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210823112204.243255-3-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 18 +-------- drivers/iio/common/st_sensors/st_sensors_trigger.c | 45 ++++++++-------------- drivers/iio/gyro/st_gyro_core.c | 18 +-------- drivers/iio/magnetometer/st_magn_core.c | 18 +-------- drivers/iio/pressure/st_pressure_core.c | 18 +-------- include/linux/iio/common/st_sensors.h | 5 --- 6 files changed, 19 insertions(+), 103 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index f1e6ec380667..a7be1633bff1 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1380,29 +1380,13 @@ int st_accel_common_probe(struct iio_dev *indio_dev) return err; } - err = iio_device_register(indio_dev); - if (err) - goto st_accel_device_register_error; - - dev_info(&indio_dev->dev, "registered accelerometer %s\n", - indio_dev->name); - - return 0; - -st_accel_device_register_error: - if (adata->irq > 0) - st_sensors_deallocate_trigger(indio_dev); - return err; + return iio_device_register(indio_dev); } EXPORT_SYMBOL(st_accel_common_probe); void st_accel_common_remove(struct iio_dev *indio_dev) { - struct st_sensor_data *adata = iio_priv(indio_dev); - iio_device_unregister(indio_dev); - if (adata->irq > 0) - st_sensors_deallocate_trigger(indio_dev); } EXPORT_SYMBOL(st_accel_common_remove); diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 64e0a748a855..d022157b66a2 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -119,11 +119,12 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops) { struct st_sensor_data *sdata = iio_priv(indio_dev); + struct device *parent = indio_dev->dev.parent; unsigned long irq_trig; int err; - sdata->trig = iio_trigger_alloc(sdata->dev, "%s-trigger", - indio_dev->name); + sdata->trig = devm_iio_trigger_alloc(parent, "%s-trigger", + indio_dev->name); if (sdata->trig == NULL) { dev_err(&indio_dev->dev, "failed to allocate iio trigger.\n"); return -ENOMEM; @@ -153,7 +154,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.addr_ihl, sdata->sensor_settings->drdy_irq.mask_ihl, 1); if (err < 0) - goto iio_trigger_free; + return err; dev_info(&indio_dev->dev, "interrupts on the falling edge or active low level\n"); } @@ -179,8 +180,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) { dev_err(&indio_dev->dev, "edge IRQ not supported w/o stat register.\n"); - err = -EOPNOTSUPP; - goto iio_trigger_free; + return -EOPNOTSUPP; } sdata->edge_irq = true; } else { @@ -205,44 +205,29 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.stat_drdy.addr) irq_trig |= IRQF_SHARED; - err = request_threaded_irq(sdata->irq, - st_sensors_irq_handler, - st_sensors_irq_thread, - irq_trig, - sdata->trig->name, - sdata->trig); + err = devm_request_threaded_irq(parent, + sdata->irq, + st_sensors_irq_handler, + st_sensors_irq_thread, + irq_trig, + sdata->trig->name, + sdata->trig); if (err) { dev_err(&indio_dev->dev, "failed to request trigger IRQ.\n"); - goto iio_trigger_free; + return err; } - err = iio_trigger_register(sdata->trig); + err = devm_iio_trigger_register(parent, sdata->trig); if (err < 0) { dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); - goto iio_trigger_register_error; + return err; } indio_dev->trig = iio_trigger_get(sdata->trig); return 0; - -iio_trigger_register_error: - free_irq(sdata->irq, sdata->trig); -iio_trigger_free: - iio_trigger_free(sdata->trig); - return err; } EXPORT_SYMBOL(st_sensors_allocate_trigger); -void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) -{ - struct st_sensor_data *sdata = iio_priv(indio_dev); - - iio_trigger_unregister(sdata->trig); - free_irq(sdata->irq, sdata->trig); - iio_trigger_free(sdata->trig); -} -EXPORT_SYMBOL(st_sensors_deallocate_trigger); - int st_sensors_validate_device(struct iio_trigger *trig, struct iio_dev *indio_dev) { diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index e8fc8af65143..cb539b47cdf4 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -515,29 +515,13 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) return err; } - err = iio_device_register(indio_dev); - if (err) - goto st_gyro_device_register_error; - - dev_info(&indio_dev->dev, "registered gyroscope %s\n", - indio_dev->name); - - return 0; - -st_gyro_device_register_error: - if (gdata->irq > 0) - st_sensors_deallocate_trigger(indio_dev); - return err; + return iio_device_register(indio_dev); } EXPORT_SYMBOL(st_gyro_common_probe); void st_gyro_common_remove(struct iio_dev *indio_dev) { - struct st_sensor_data *gdata = iio_priv(indio_dev); - iio_device_unregister(indio_dev); - if (gdata->irq > 0) - st_sensors_deallocate_trigger(indio_dev); } EXPORT_SYMBOL(st_gyro_common_remove); diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 9ffd50d796bf..5be85e2405a5 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -650,29 +650,13 @@ int st_magn_common_probe(struct iio_dev *indio_dev) return err; } - err = iio_device_register(indio_dev); - if (err) - goto st_magn_device_register_error; - - dev_info(&indio_dev->dev, "registered magnetometer %s\n", - indio_dev->name); - - return 0; - -st_magn_device_register_error: - if (mdata->irq > 0) - st_sensors_deallocate_trigger(indio_dev); - return err; + return iio_device_register(indio_dev); } EXPORT_SYMBOL(st_magn_common_probe); void st_magn_common_remove(struct iio_dev *indio_dev) { - struct st_sensor_data *mdata = iio_priv(indio_dev); - iio_device_unregister(indio_dev); - if (mdata->irq > 0) - st_sensors_deallocate_trigger(indio_dev); } EXPORT_SYMBOL(st_magn_common_remove); diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index ab1c17fac807..17ebb5171d4c 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -721,29 +721,13 @@ int st_press_common_probe(struct iio_dev *indio_dev) return err; } - err = iio_device_register(indio_dev); - if (err) - goto st_press_device_register_error; - - dev_info(&indio_dev->dev, "registered pressure sensor %s\n", - indio_dev->name); - - return err; - -st_press_device_register_error: - if (press_data->irq > 0) - st_sensors_deallocate_trigger(indio_dev); - return err; + return iio_device_register(indio_dev); } EXPORT_SYMBOL(st_press_common_probe); void st_press_common_remove(struct iio_dev *indio_dev) { - struct st_sensor_data *press_data = iio_priv(indio_dev); - iio_device_unregister(indio_dev); - if (press_data->irq > 0) - st_sensors_deallocate_trigger(indio_dev); } EXPORT_SYMBOL(st_press_common_remove); diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index 8bdbaf3f3796..e74b55244f35 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -273,7 +273,6 @@ irqreturn_t st_sensors_trigger_handler(int irq, void *p); int st_sensors_allocate_trigger(struct iio_dev *indio_dev, const struct iio_trigger_ops *trigger_ops); -void st_sensors_deallocate_trigger(struct iio_dev *indio_dev); int st_sensors_validate_device(struct iio_trigger *trig, struct iio_dev *indio_dev); #else @@ -282,10 +281,6 @@ static inline int st_sensors_allocate_trigger(struct iio_dev *indio_dev, { return 0; } -static inline void st_sensors_deallocate_trigger(struct iio_dev *indio_dev) -{ - return; -} #define st_sensors_validate_device NULL #endif -- cgit v1.2.3 From 5363c6c17b1014f696bf0b2984af4b694062ce8f Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 23 Aug 2021 14:22:02 +0300 Subject: iio: st_sensors: remove st_sensors_power_disable() function This change converts the st_sensors_power_enable() function to use devm_add_action_or_reset() handlers to register regulator_disable hooks for when the drivers get unloaded. The parent device of the IIO device object is used. This is based on the assumption that all other devm_ calls in the ST sensors use this reference. This makes the st_sensors_power_disable() un-needed. Removing this also changes unload order a bit, as all ST drivers would call st_sensors_power_disable() first and iio_device_unregister() after that. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210823112204.243255-4-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_i2c.c | 13 +--------- drivers/iio/accel/st_accel_spi.c | 13 +--------- drivers/iio/common/st_sensors/st_sensors_core.c | 34 +++++++++++-------------- drivers/iio/gyro/st_gyro_i2c.c | 13 +--------- drivers/iio/gyro/st_gyro_spi.c | 13 +--------- drivers/iio/magnetometer/st_magn_i2c.c | 13 +--------- drivers/iio/magnetometer/st_magn_spi.c | 13 +--------- drivers/iio/pressure/st_pressure_i2c.c | 13 +--------- drivers/iio/pressure/st_pressure_spi.c | 13 +--------- include/linux/iio/common/st_sensors.h | 2 -- 10 files changed, 23 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c index cba57459e90a..b377575efc41 100644 --- a/drivers/iio/accel/st_accel_i2c.c +++ b/drivers/iio/accel/st_accel_i2c.c @@ -177,16 +177,7 @@ static int st_accel_i2c_probe(struct i2c_client *client) if (ret) return ret; - ret = st_accel_common_probe(indio_dev); - if (ret < 0) - goto st_accel_power_off; - - return 0; - -st_accel_power_off: - st_sensors_power_disable(indio_dev); - - return ret; + return st_accel_common_probe(indio_dev); } static int st_accel_i2c_remove(struct i2c_client *client) @@ -195,8 +186,6 @@ static int st_accel_i2c_remove(struct i2c_client *client) st_accel_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/accel/st_accel_spi.c b/drivers/iio/accel/st_accel_spi.c index 5167fae1ee8e..4ca87e73bdb3 100644 --- a/drivers/iio/accel/st_accel_spi.c +++ b/drivers/iio/accel/st_accel_spi.c @@ -127,16 +127,7 @@ static int st_accel_spi_probe(struct spi_device *spi) if (err) return err; - err = st_accel_common_probe(indio_dev); - if (err < 0) - goto st_accel_power_off; - - return 0; - -st_accel_power_off: - st_sensors_power_disable(indio_dev); - - return err; + return st_accel_common_probe(indio_dev); } static int st_accel_spi_remove(struct spi_device *spi) @@ -145,8 +136,6 @@ static int st_accel_spi_remove(struct spi_device *spi) st_accel_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 0bbb090b108c..a5a140de9a23 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -215,13 +215,19 @@ int st_sensors_set_axis_enable(struct iio_dev *indio_dev, u8 axis_enable) } EXPORT_SYMBOL(st_sensors_set_axis_enable); +static void st_reg_disable(void *reg) +{ + regulator_disable(reg); +} + int st_sensors_power_enable(struct iio_dev *indio_dev) { struct st_sensor_data *pdata = iio_priv(indio_dev); + struct device *parent = indio_dev->dev.parent; int err; /* Regulators not mandatory, but if requested we should enable them. */ - pdata->vdd = devm_regulator_get(indio_dev->dev.parent, "vdd"); + pdata->vdd = devm_regulator_get(parent, "vdd"); if (IS_ERR(pdata->vdd)) { dev_err(&indio_dev->dev, "unable to get Vdd supply\n"); return PTR_ERR(pdata->vdd); @@ -233,36 +239,26 @@ int st_sensors_power_enable(struct iio_dev *indio_dev) return err; } - pdata->vdd_io = devm_regulator_get(indio_dev->dev.parent, "vddio"); + err = devm_add_action_or_reset(parent, st_reg_disable, pdata->vdd); + if (err) + return err; + + pdata->vdd_io = devm_regulator_get(parent, "vddio"); if (IS_ERR(pdata->vdd_io)) { dev_err(&indio_dev->dev, "unable to get Vdd_IO supply\n"); - err = PTR_ERR(pdata->vdd_io); - goto st_sensors_disable_vdd; + return PTR_ERR(pdata->vdd_io); } err = regulator_enable(pdata->vdd_io); if (err != 0) { dev_warn(&indio_dev->dev, "Failed to enable specified Vdd_IO supply\n"); - goto st_sensors_disable_vdd; + return err; } - return 0; - -st_sensors_disable_vdd: - regulator_disable(pdata->vdd); - return err; + return devm_add_action_or_reset(parent, st_reg_disable, pdata->vdd_io); } EXPORT_SYMBOL(st_sensors_power_enable); -void st_sensors_power_disable(struct iio_dev *indio_dev) -{ - struct st_sensor_data *pdata = iio_priv(indio_dev); - - regulator_disable(pdata->vdd); - regulator_disable(pdata->vdd_io); -} -EXPORT_SYMBOL(st_sensors_power_disable); - static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c index a8164fe48b85..0bd80dfd389f 100644 --- a/drivers/iio/gyro/st_gyro_i2c.c +++ b/drivers/iio/gyro/st_gyro_i2c.c @@ -90,16 +90,7 @@ static int st_gyro_i2c_probe(struct i2c_client *client, if (err) return err; - err = st_gyro_common_probe(indio_dev); - if (err < 0) - goto st_gyro_power_off; - - return 0; - -st_gyro_power_off: - st_sensors_power_disable(indio_dev); - - return err; + return st_gyro_common_probe(indio_dev); } static int st_gyro_i2c_remove(struct i2c_client *client) @@ -108,8 +99,6 @@ static int st_gyro_i2c_remove(struct i2c_client *client) st_gyro_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c index 9d8916871b4b..f74b09fa5cde 100644 --- a/drivers/iio/gyro/st_gyro_spi.c +++ b/drivers/iio/gyro/st_gyro_spi.c @@ -94,16 +94,7 @@ static int st_gyro_spi_probe(struct spi_device *spi) if (err) return err; - err = st_gyro_common_probe(indio_dev); - if (err < 0) - goto st_gyro_power_off; - - return 0; - -st_gyro_power_off: - st_sensors_power_disable(indio_dev); - - return err; + return st_gyro_common_probe(indio_dev); } static int st_gyro_spi_remove(struct spi_device *spi) @@ -112,8 +103,6 @@ static int st_gyro_spi_remove(struct spi_device *spi) st_gyro_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/magnetometer/st_magn_i2c.c b/drivers/iio/magnetometer/st_magn_i2c.c index fa78f0a3b53e..0a5117dffcf4 100644 --- a/drivers/iio/magnetometer/st_magn_i2c.c +++ b/drivers/iio/magnetometer/st_magn_i2c.c @@ -86,16 +86,7 @@ static int st_magn_i2c_probe(struct i2c_client *client, if (err) return err; - err = st_magn_common_probe(indio_dev); - if (err < 0) - goto st_magn_power_off; - - return 0; - -st_magn_power_off: - st_sensors_power_disable(indio_dev); - - return err; + return st_magn_common_probe(indio_dev); } static int st_magn_i2c_remove(struct i2c_client *client) @@ -104,8 +95,6 @@ static int st_magn_i2c_remove(struct i2c_client *client) st_magn_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/magnetometer/st_magn_spi.c b/drivers/iio/magnetometer/st_magn_spi.c index ff43cbf61b05..1f3bf02b24e0 100644 --- a/drivers/iio/magnetometer/st_magn_spi.c +++ b/drivers/iio/magnetometer/st_magn_spi.c @@ -80,16 +80,7 @@ static int st_magn_spi_probe(struct spi_device *spi) if (err) return err; - err = st_magn_common_probe(indio_dev); - if (err < 0) - goto st_magn_power_off; - - return 0; - -st_magn_power_off: - st_sensors_power_disable(indio_dev); - - return err; + return st_magn_common_probe(indio_dev); } static int st_magn_spi_remove(struct spi_device *spi) @@ -98,8 +89,6 @@ static int st_magn_spi_remove(struct spi_device *spi) st_magn_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/pressure/st_pressure_i2c.c b/drivers/iio/pressure/st_pressure_i2c.c index 6215de677017..afeeab485c0d 100644 --- a/drivers/iio/pressure/st_pressure_i2c.c +++ b/drivers/iio/pressure/st_pressure_i2c.c @@ -103,16 +103,7 @@ static int st_press_i2c_probe(struct i2c_client *client, if (ret) return ret; - ret = st_press_common_probe(indio_dev); - if (ret < 0) - goto st_press_power_off; - - return 0; - -st_press_power_off: - st_sensors_power_disable(indio_dev); - - return ret; + return st_press_common_probe(indio_dev); } static int st_press_i2c_remove(struct i2c_client *client) @@ -121,8 +112,6 @@ static int st_press_i2c_remove(struct i2c_client *client) st_press_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/drivers/iio/pressure/st_pressure_spi.c b/drivers/iio/pressure/st_pressure_spi.c index 5001aae8f00b..834ad6d40a70 100644 --- a/drivers/iio/pressure/st_pressure_spi.c +++ b/drivers/iio/pressure/st_pressure_spi.c @@ -86,16 +86,7 @@ static int st_press_spi_probe(struct spi_device *spi) if (err) return err; - err = st_press_common_probe(indio_dev); - if (err < 0) - goto st_press_power_off; - - return 0; - -st_press_power_off: - st_sensors_power_disable(indio_dev); - - return err; + return st_press_common_probe(indio_dev); } static int st_press_spi_remove(struct spi_device *spi) @@ -104,8 +95,6 @@ static int st_press_spi_remove(struct spi_device *spi) st_press_common_remove(indio_dev); - st_sensors_power_disable(indio_dev); - return 0; } diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index e74b55244f35..fc90c202d15e 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -293,8 +293,6 @@ int st_sensors_set_axis_enable(struct iio_dev *indio_dev, u8 axis_enable); int st_sensors_power_enable(struct iio_dev *indio_dev); -void st_sensors_power_disable(struct iio_dev *indio_dev); - int st_sensors_debugfs_reg_access(struct iio_dev *indio_dev, unsigned reg, unsigned writeval, unsigned *readval); -- cgit v1.2.3 From 6b658c31bb6bc033f6ae60141c676383fb78784c Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 23 Aug 2021 14:22:03 +0300 Subject: iio: st_sensors: remove all driver remove functions At this point all ST driver remove functions do iio_device_unregister(). This change removes them from them and replaces all iio_device_register() with devm_iio_device_register(). This can be done in a single change relatively easy, since all these remove functions are define in st_sensors.h. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210823112204.243255-5-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 9 ++------- drivers/iio/accel/st_accel_i2c.c | 10 ---------- drivers/iio/accel/st_accel_spi.c | 10 ---------- drivers/iio/gyro/st_gyro_core.c | 9 ++------- drivers/iio/gyro/st_gyro_i2c.c | 10 ---------- drivers/iio/gyro/st_gyro_spi.c | 10 ---------- drivers/iio/imu/st_lsm9ds0/st_lsm9ds0.h | 1 - drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c | 15 +-------------- drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_i2c.c | 6 ------ drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_spi.c | 6 ------ drivers/iio/magnetometer/st_magn_core.c | 9 ++------- drivers/iio/magnetometer/st_magn_i2c.c | 10 ---------- drivers/iio/magnetometer/st_magn_spi.c | 10 ---------- drivers/iio/pressure/st_pressure_core.c | 9 ++------- drivers/iio/pressure/st_pressure_i2c.c | 10 ---------- drivers/iio/pressure/st_pressure_spi.c | 10 ---------- include/linux/iio/common/st_sensors.h | 4 ---- 17 files changed, 9 insertions(+), 139 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index a7be1633bff1..01695abd9d2f 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1335,6 +1335,7 @@ int st_accel_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *adata = iio_priv(indio_dev); struct st_sensors_platform_data *pdata = dev_get_platdata(adata->dev); + struct device *parent = indio_dev->dev.parent; int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -1380,16 +1381,10 @@ int st_accel_common_probe(struct iio_dev *indio_dev) return err; } - return iio_device_register(indio_dev); + return devm_iio_device_register(parent, indio_dev); } EXPORT_SYMBOL(st_accel_common_probe); -void st_accel_common_remove(struct iio_dev *indio_dev) -{ - iio_device_unregister(indio_dev); -} -EXPORT_SYMBOL(st_accel_common_remove); - MODULE_AUTHOR("Denis Ciocca "); MODULE_DESCRIPTION("STMicroelectronics accelerometers driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/accel/st_accel_i2c.c b/drivers/iio/accel/st_accel_i2c.c index b377575efc41..c0ce78eebad9 100644 --- a/drivers/iio/accel/st_accel_i2c.c +++ b/drivers/iio/accel/st_accel_i2c.c @@ -180,15 +180,6 @@ static int st_accel_i2c_probe(struct i2c_client *client) return st_accel_common_probe(indio_dev); } -static int st_accel_i2c_remove(struct i2c_client *client) -{ - struct iio_dev *indio_dev = i2c_get_clientdata(client); - - st_accel_common_remove(indio_dev); - - return 0; -} - static struct i2c_driver st_accel_driver = { .driver = { .name = "st-accel-i2c", @@ -196,7 +187,6 @@ static struct i2c_driver st_accel_driver = { .acpi_match_table = ACPI_PTR(st_accel_acpi_match), }, .probe_new = st_accel_i2c_probe, - .remove = st_accel_i2c_remove, .id_table = st_accel_id_table, }; module_i2c_driver(st_accel_driver); diff --git a/drivers/iio/accel/st_accel_spi.c b/drivers/iio/accel/st_accel_spi.c index 4ca87e73bdb3..b74a1c6d03de 100644 --- a/drivers/iio/accel/st_accel_spi.c +++ b/drivers/iio/accel/st_accel_spi.c @@ -130,15 +130,6 @@ static int st_accel_spi_probe(struct spi_device *spi) return st_accel_common_probe(indio_dev); } -static int st_accel_spi_remove(struct spi_device *spi) -{ - struct iio_dev *indio_dev = spi_get_drvdata(spi); - - st_accel_common_remove(indio_dev); - - return 0; -} - static const struct spi_device_id st_accel_id_table[] = { { LIS3DH_ACCEL_DEV_NAME }, { LSM330D_ACCEL_DEV_NAME }, @@ -166,7 +157,6 @@ static struct spi_driver st_accel_driver = { .of_match_table = st_accel_of_match, }, .probe = st_accel_spi_probe, - .remove = st_accel_spi_remove, .id_table = st_accel_id_table, }; module_spi_driver(st_accel_driver); diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index cb539b47cdf4..3609082a6778 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -478,6 +478,7 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *gdata = iio_priv(indio_dev); struct st_sensors_platform_data *pdata; + struct device *parent = indio_dev->dev.parent; int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -515,16 +516,10 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) return err; } - return iio_device_register(indio_dev); + return devm_iio_device_register(parent, indio_dev); } EXPORT_SYMBOL(st_gyro_common_probe); -void st_gyro_common_remove(struct iio_dev *indio_dev) -{ - iio_device_unregister(indio_dev); -} -EXPORT_SYMBOL(st_gyro_common_remove); - MODULE_AUTHOR("Denis Ciocca "); MODULE_DESCRIPTION("STMicroelectronics gyroscopes driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/gyro/st_gyro_i2c.c b/drivers/iio/gyro/st_gyro_i2c.c index 0bd80dfd389f..163c7ba300c1 100644 --- a/drivers/iio/gyro/st_gyro_i2c.c +++ b/drivers/iio/gyro/st_gyro_i2c.c @@ -93,15 +93,6 @@ static int st_gyro_i2c_probe(struct i2c_client *client, return st_gyro_common_probe(indio_dev); } -static int st_gyro_i2c_remove(struct i2c_client *client) -{ - struct iio_dev *indio_dev = i2c_get_clientdata(client); - - st_gyro_common_remove(indio_dev); - - return 0; -} - static const struct i2c_device_id st_gyro_id_table[] = { { L3G4200D_GYRO_DEV_NAME }, { LSM330D_GYRO_DEV_NAME }, @@ -122,7 +113,6 @@ static struct i2c_driver st_gyro_driver = { .of_match_table = st_gyro_of_match, }, .probe = st_gyro_i2c_probe, - .remove = st_gyro_i2c_remove, .id_table = st_gyro_id_table, }; module_i2c_driver(st_gyro_driver); diff --git a/drivers/iio/gyro/st_gyro_spi.c b/drivers/iio/gyro/st_gyro_spi.c index f74b09fa5cde..b0023f9b9771 100644 --- a/drivers/iio/gyro/st_gyro_spi.c +++ b/drivers/iio/gyro/st_gyro_spi.c @@ -97,15 +97,6 @@ static int st_gyro_spi_probe(struct spi_device *spi) return st_gyro_common_probe(indio_dev); } -static int st_gyro_spi_remove(struct spi_device *spi) -{ - struct iio_dev *indio_dev = spi_get_drvdata(spi); - - st_gyro_common_remove(indio_dev); - - return 0; -} - static const struct spi_device_id st_gyro_id_table[] = { { L3G4200D_GYRO_DEV_NAME }, { LSM330D_GYRO_DEV_NAME }, @@ -126,7 +117,6 @@ static struct spi_driver st_gyro_driver = { .of_match_table = st_gyro_of_match, }, .probe = st_gyro_spi_probe, - .remove = st_gyro_spi_remove, .id_table = st_gyro_id_table, }; module_spi_driver(st_gyro_driver); diff --git a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0.h b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0.h index 146393afd9a7..76678cdefb07 100644 --- a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0.h +++ b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0.h @@ -18,6 +18,5 @@ struct st_lsm9ds0 { }; int st_lsm9ds0_probe(struct st_lsm9ds0 *lsm9ds0, struct regmap *regmap); -int st_lsm9ds0_remove(struct st_lsm9ds0 *lsm9ds0); #endif /* ST_LSM9DS0_H */ diff --git a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c index 5e6625140db7..d276f663fe57 100644 --- a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c +++ b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c @@ -142,23 +142,10 @@ int st_lsm9ds0_probe(struct st_lsm9ds0 *lsm9ds0, struct regmap *regmap) return ret; /* Setup magnetometer device */ - ret = st_lsm9ds0_probe_magn(lsm9ds0, regmap); - if (ret) - st_accel_common_remove(lsm9ds0->accel); - - return ret; + return st_lsm9ds0_probe_magn(lsm9ds0, regmap); } EXPORT_SYMBOL_GPL(st_lsm9ds0_probe); -int st_lsm9ds0_remove(struct st_lsm9ds0 *lsm9ds0) -{ - st_magn_common_remove(lsm9ds0->magn); - st_accel_common_remove(lsm9ds0->accel); - - return 0; -} -EXPORT_SYMBOL_GPL(st_lsm9ds0_remove); - MODULE_AUTHOR("Andy Shevchenko "); MODULE_DESCRIPTION("STMicroelectronics LSM9DS0 IMU core driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_i2c.c b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_i2c.c index 78bede358747..8f205c477e6f 100644 --- a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_i2c.c +++ b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_i2c.c @@ -64,18 +64,12 @@ static int st_lsm9ds0_i2c_probe(struct i2c_client *client) return st_lsm9ds0_probe(lsm9ds0, regmap); } -static int st_lsm9ds0_i2c_remove(struct i2c_client *client) -{ - return st_lsm9ds0_remove(i2c_get_clientdata(client)); -} - static struct i2c_driver st_lsm9ds0_driver = { .driver = { .name = "st-lsm9ds0-i2c", .of_match_table = st_lsm9ds0_of_match, }, .probe_new = st_lsm9ds0_i2c_probe, - .remove = st_lsm9ds0_i2c_remove, .id_table = st_lsm9ds0_id_table, }; module_i2c_driver(st_lsm9ds0_driver); diff --git a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_spi.c b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_spi.c index 180b54e66438..0ddfa53166af 100644 --- a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_spi.c +++ b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_spi.c @@ -63,18 +63,12 @@ static int st_lsm9ds0_spi_probe(struct spi_device *spi) return st_lsm9ds0_probe(lsm9ds0, regmap); } -static int st_lsm9ds0_spi_remove(struct spi_device *spi) -{ - return st_lsm9ds0_remove(spi_get_drvdata(spi)); -} - static struct spi_driver st_lsm9ds0_driver = { .driver = { .name = "st-lsm9ds0-spi", .of_match_table = st_lsm9ds0_of_match, }, .probe = st_lsm9ds0_spi_probe, - .remove = st_lsm9ds0_spi_remove, .id_table = st_lsm9ds0_id_table, }; module_spi_driver(st_lsm9ds0_driver); diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 5be85e2405a5..1458906a3765 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -612,6 +612,7 @@ int st_magn_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *mdata = iio_priv(indio_dev); struct st_sensors_platform_data *pdata = dev_get_platdata(mdata->dev); + struct device *parent = indio_dev->dev.parent; int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -650,16 +651,10 @@ int st_magn_common_probe(struct iio_dev *indio_dev) return err; } - return iio_device_register(indio_dev); + return devm_iio_device_register(parent, indio_dev); } EXPORT_SYMBOL(st_magn_common_probe); -void st_magn_common_remove(struct iio_dev *indio_dev) -{ - iio_device_unregister(indio_dev); -} -EXPORT_SYMBOL(st_magn_common_remove); - MODULE_AUTHOR("Denis Ciocca "); MODULE_DESCRIPTION("STMicroelectronics magnetometers driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/magnetometer/st_magn_i2c.c b/drivers/iio/magnetometer/st_magn_i2c.c index 0a5117dffcf4..7237711fc09b 100644 --- a/drivers/iio/magnetometer/st_magn_i2c.c +++ b/drivers/iio/magnetometer/st_magn_i2c.c @@ -89,15 +89,6 @@ static int st_magn_i2c_probe(struct i2c_client *client, return st_magn_common_probe(indio_dev); } -static int st_magn_i2c_remove(struct i2c_client *client) -{ - struct iio_dev *indio_dev = i2c_get_clientdata(client); - - st_magn_common_remove(indio_dev); - - return 0; -} - static const struct i2c_device_id st_magn_id_table[] = { { LSM303DLH_MAGN_DEV_NAME }, { LSM303DLHC_MAGN_DEV_NAME }, @@ -117,7 +108,6 @@ static struct i2c_driver st_magn_driver = { .of_match_table = st_magn_of_match, }, .probe = st_magn_i2c_probe, - .remove = st_magn_i2c_remove, .id_table = st_magn_id_table, }; module_i2c_driver(st_magn_driver); diff --git a/drivers/iio/magnetometer/st_magn_spi.c b/drivers/iio/magnetometer/st_magn_spi.c index 1f3bf02b24e0..489d4462862f 100644 --- a/drivers/iio/magnetometer/st_magn_spi.c +++ b/drivers/iio/magnetometer/st_magn_spi.c @@ -83,15 +83,6 @@ static int st_magn_spi_probe(struct spi_device *spi) return st_magn_common_probe(indio_dev); } -static int st_magn_spi_remove(struct spi_device *spi) -{ - struct iio_dev *indio_dev = spi_get_drvdata(spi); - - st_magn_common_remove(indio_dev); - - return 0; -} - static const struct spi_device_id st_magn_id_table[] = { { LIS3MDL_MAGN_DEV_NAME }, { LSM303AGR_MAGN_DEV_NAME }, @@ -108,7 +99,6 @@ static struct spi_driver st_magn_driver = { .of_match_table = st_magn_of_match, }, .probe = st_magn_spi_probe, - .remove = st_magn_spi_remove, .id_table = st_magn_id_table, }; module_spi_driver(st_magn_driver); diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index 17ebb5171d4c..cebcc1d93d0b 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -678,6 +678,7 @@ int st_press_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *press_data = iio_priv(indio_dev); struct st_sensors_platform_data *pdata = dev_get_platdata(press_data->dev); + struct device *parent = indio_dev->dev.parent; int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -721,16 +722,10 @@ int st_press_common_probe(struct iio_dev *indio_dev) return err; } - return iio_device_register(indio_dev); + return devm_iio_device_register(parent, indio_dev); } EXPORT_SYMBOL(st_press_common_probe); -void st_press_common_remove(struct iio_dev *indio_dev) -{ - iio_device_unregister(indio_dev); -} -EXPORT_SYMBOL(st_press_common_remove); - MODULE_AUTHOR("Denis Ciocca "); MODULE_DESCRIPTION("STMicroelectronics pressures driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/iio/pressure/st_pressure_i2c.c b/drivers/iio/pressure/st_pressure_i2c.c index afeeab485c0d..1939e999a427 100644 --- a/drivers/iio/pressure/st_pressure_i2c.c +++ b/drivers/iio/pressure/st_pressure_i2c.c @@ -106,15 +106,6 @@ static int st_press_i2c_probe(struct i2c_client *client, return st_press_common_probe(indio_dev); } -static int st_press_i2c_remove(struct i2c_client *client) -{ - struct iio_dev *indio_dev = i2c_get_clientdata(client); - - st_press_common_remove(indio_dev); - - return 0; -} - static struct i2c_driver st_press_driver = { .driver = { .name = "st-press-i2c", @@ -122,7 +113,6 @@ static struct i2c_driver st_press_driver = { .acpi_match_table = ACPI_PTR(st_press_acpi_match), }, .probe = st_press_i2c_probe, - .remove = st_press_i2c_remove, .id_table = st_press_id_table, }; module_i2c_driver(st_press_driver); diff --git a/drivers/iio/pressure/st_pressure_spi.c b/drivers/iio/pressure/st_pressure_spi.c index 834ad6d40a70..9b2523c5bc94 100644 --- a/drivers/iio/pressure/st_pressure_spi.c +++ b/drivers/iio/pressure/st_pressure_spi.c @@ -89,15 +89,6 @@ static int st_press_spi_probe(struct spi_device *spi) return st_press_common_probe(indio_dev); } -static int st_press_spi_remove(struct spi_device *spi) -{ - struct iio_dev *indio_dev = spi_get_drvdata(spi); - - st_press_common_remove(indio_dev); - - return 0; -} - static const struct spi_device_id st_press_id_table[] = { { LPS001WP_PRESS_DEV_NAME }, { LPS25H_PRESS_DEV_NAME }, @@ -116,7 +107,6 @@ static struct spi_driver st_press_driver = { .of_match_table = st_press_of_match, }, .probe = st_press_spi_probe, - .remove = st_press_spi_remove, .id_table = st_press_id_table, }; module_spi_driver(st_press_driver); diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index fc90c202d15e..d17ae1e5ca19 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -323,21 +323,17 @@ void st_sensors_dev_name_probe(struct device *dev, char *name, int len); /* Accelerometer */ const struct st_sensor_settings *st_accel_get_settings(const char *name); int st_accel_common_probe(struct iio_dev *indio_dev); -void st_accel_common_remove(struct iio_dev *indio_dev); /* Gyroscope */ const struct st_sensor_settings *st_gyro_get_settings(const char *name); int st_gyro_common_probe(struct iio_dev *indio_dev); -void st_gyro_common_remove(struct iio_dev *indio_dev); /* Magnetometer */ const struct st_sensor_settings *st_magn_get_settings(const char *name); int st_magn_common_probe(struct iio_dev *indio_dev); -void st_magn_common_remove(struct iio_dev *indio_dev); /* Pressure */ const struct st_sensor_settings *st_press_get_settings(const char *name); int st_press_common_probe(struct iio_dev *indio_dev); -void st_press_common_remove(struct iio_dev *indio_dev); #endif /* ST_SENSORS_H */ -- cgit v1.2.3 From e42696515414a15774c80f1d454194ce0cd9f145 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Mon, 23 Aug 2021 14:22:04 +0300 Subject: iio: st_sensors: remove reference to parent device object on st_sensor_data The idea behind it, is that all devm_ calls in ST sensors are bound to the parent device object. However, the reference to that object is kept on both the st_sensor_data struct and the IIO object parent (indio_dev->dev.parent). This change only adds a bit consistency and uses the reference stored on indio_dev->dev.parent, to enforce the assumption that all ST sensors' devm_ calls are bound to the same reference as the one store on st_sensor_data. Reviewed-by: Andy Shevchenko Signed-off-by: Alexandru Ardelean Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20210823112204.243255-6-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/st_accel_core.c | 6 +++--- drivers/iio/common/st_sensors/st_sensors_i2c.c | 1 - drivers/iio/common/st_sensors/st_sensors_spi.c | 1 - drivers/iio/common/st_sensors/st_sensors_trigger.c | 8 +++++--- drivers/iio/gyro/st_gyro_core.c | 2 +- drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c | 2 -- drivers/iio/magnetometer/st_magn_core.c | 4 ++-- drivers/iio/pressure/st_pressure_core.c | 2 +- include/linux/iio/common/st_sensors.h | 2 -- 9 files changed, 12 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 01695abd9d2f..31ea19d0ba71 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1210,7 +1210,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) }; - adev = ACPI_COMPANION(adata->dev); + adev = ACPI_COMPANION(indio_dev->dev.parent); if (!adev) return 0; @@ -1334,8 +1334,8 @@ EXPORT_SYMBOL(st_accel_get_settings); int st_accel_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *adata = iio_priv(indio_dev); - struct st_sensors_platform_data *pdata = dev_get_platdata(adata->dev); struct device *parent = indio_dev->dev.parent; + struct st_sensors_platform_data *pdata = dev_get_platdata(parent); int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -1355,7 +1355,7 @@ int st_accel_common_probe(struct iio_dev *indio_dev) */ err = apply_acpi_orientation(indio_dev); if (err) { - err = iio_read_mount_matrix(adata->dev, &adata->mount_matrix); + err = iio_read_mount_matrix(parent, &adata->mount_matrix); if (err) return err; } diff --git a/drivers/iio/common/st_sensors/st_sensors_i2c.c b/drivers/iio/common/st_sensors/st_sensors_i2c.c index b3ff88700866..18bd3c3d99bc 100644 --- a/drivers/iio/common/st_sensors/st_sensors_i2c.c +++ b/drivers/iio/common/st_sensors/st_sensors_i2c.c @@ -57,7 +57,6 @@ int st_sensors_i2c_configure(struct iio_dev *indio_dev, indio_dev->name = client->name; - sdata->dev = &client->dev; sdata->irq = client->irq; return 0; diff --git a/drivers/iio/common/st_sensors/st_sensors_spi.c b/drivers/iio/common/st_sensors/st_sensors_spi.c index 0d1d66c77cd8..7c60050e90dc 100644 --- a/drivers/iio/common/st_sensors/st_sensors_spi.c +++ b/drivers/iio/common/st_sensors/st_sensors_spi.c @@ -109,7 +109,6 @@ int st_sensors_spi_configure(struct iio_dev *indio_dev, indio_dev->name = spi->modalias; - sdata->dev = &spi->dev; sdata->irq = spi->irq; return 0; diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index d022157b66a2..392d74449886 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -42,7 +42,8 @@ static bool st_sensors_new_samples_available(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.stat_drdy.addr, &status); if (ret < 0) { - dev_err(sdata->dev, "error checking samples available\n"); + dev_err(indio_dev->dev.parent, + "error checking samples available\n"); return false; } @@ -87,7 +88,7 @@ static irqreturn_t st_sensors_irq_thread(int irq, void *p) st_sensors_new_samples_available(indio_dev, sdata)) { iio_trigger_poll_chained(p); } else { - dev_dbg(sdata->dev, "spurious IRQ\n"); + dev_dbg(indio_dev->dev.parent, "spurious IRQ\n"); return IRQ_NONE; } @@ -107,7 +108,8 @@ static irqreturn_t st_sensors_irq_thread(int irq, void *p) */ while (sdata->hw_irq_trigger && st_sensors_new_samples_available(indio_dev, sdata)) { - dev_dbg(sdata->dev, "more samples came in during polling\n"); + dev_dbg(indio_dev->dev.parent, + "more samples came in during polling\n"); sdata->hw_timestamp = iio_get_time_ns(indio_dev); iio_trigger_poll_chained(p); } diff --git a/drivers/iio/gyro/st_gyro_core.c b/drivers/iio/gyro/st_gyro_core.c index 3609082a6778..201050b76fe5 100644 --- a/drivers/iio/gyro/st_gyro_core.c +++ b/drivers/iio/gyro/st_gyro_core.c @@ -492,7 +492,7 @@ int st_gyro_common_probe(struct iio_dev *indio_dev) indio_dev->channels = gdata->sensor_settings->ch; indio_dev->num_channels = ST_SENSORS_NUMBER_ALL_CHANNELS; - err = iio_read_mount_matrix(gdata->dev, &gdata->mount_matrix); + err = iio_read_mount_matrix(parent, &gdata->mount_matrix); if (err) return err; diff --git a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c index d276f663fe57..b3a43a3b04ff 100644 --- a/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c +++ b/drivers/iio/imu/st_lsm9ds0/st_lsm9ds0_core.c @@ -90,7 +90,6 @@ static int st_lsm9ds0_probe_accel(struct st_lsm9ds0 *lsm9ds0, struct regmap *reg data = iio_priv(lsm9ds0->accel); data->sensor_settings = (struct st_sensor_settings *)settings; - data->dev = dev; data->irq = lsm9ds0->irq; data->regmap = regmap; data->vdd = lsm9ds0->vdd; @@ -119,7 +118,6 @@ static int st_lsm9ds0_probe_magn(struct st_lsm9ds0 *lsm9ds0, struct regmap *regm data = iio_priv(lsm9ds0->magn); data->sensor_settings = (struct st_sensor_settings *)settings; - data->dev = dev; data->irq = lsm9ds0->irq; data->regmap = regmap; data->vdd = lsm9ds0->vdd; diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 1458906a3765..0806a1e65ce4 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -611,8 +611,8 @@ EXPORT_SYMBOL(st_magn_get_settings); int st_magn_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *mdata = iio_priv(indio_dev); - struct st_sensors_platform_data *pdata = dev_get_platdata(mdata->dev); struct device *parent = indio_dev->dev.parent; + struct st_sensors_platform_data *pdata = dev_get_platdata(parent); int err; indio_dev->modes = INDIO_DIRECT_MODE; @@ -626,7 +626,7 @@ int st_magn_common_probe(struct iio_dev *indio_dev) indio_dev->channels = mdata->sensor_settings->ch; indio_dev->num_channels = ST_SENSORS_NUMBER_ALL_CHANNELS; - err = iio_read_mount_matrix(mdata->dev, &mdata->mount_matrix); + err = iio_read_mount_matrix(parent, &mdata->mount_matrix); if (err) return err; diff --git a/drivers/iio/pressure/st_pressure_core.c b/drivers/iio/pressure/st_pressure_core.c index cebcc1d93d0b..26a1ee43d56e 100644 --- a/drivers/iio/pressure/st_pressure_core.c +++ b/drivers/iio/pressure/st_pressure_core.c @@ -677,8 +677,8 @@ EXPORT_SYMBOL(st_press_get_settings); int st_press_common_probe(struct iio_dev *indio_dev) { struct st_sensor_data *press_data = iio_priv(indio_dev); - struct st_sensors_platform_data *pdata = dev_get_platdata(press_data->dev); struct device *parent = indio_dev->dev.parent; + struct st_sensors_platform_data *pdata = dev_get_platdata(parent); int err; indio_dev->modes = INDIO_DIRECT_MODE; diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h index d17ae1e5ca19..22f67845cdd3 100644 --- a/include/linux/iio/common/st_sensors.h +++ b/include/linux/iio/common/st_sensors.h @@ -220,7 +220,6 @@ struct st_sensor_settings { /** * struct st_sensor_data - ST sensor device status - * @dev: Pointer to instance of struct device (I2C or SPI). * @trig: The trigger in use by the core driver. * @mount_matrix: The mounting matrix of the sensor. * @sensor_settings: Pointer to the specific sensor settings in use. @@ -240,7 +239,6 @@ struct st_sensor_settings { * @buffer_data: Data used by buffer part. */ struct st_sensor_data { - struct device *dev; struct iio_trigger *trig; struct iio_mount_matrix mount_matrix; struct st_sensor_settings *sensor_settings; -- cgit v1.2.3 From 2935662449dfa4467d2e769a70801c608fd510c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 13 Sep 2021 07:41:10 +0200 Subject: kernfs: remove kernfs_create_file and kernfs_create_file_ns All callers actually use __kernfs_create_file. Acked-by: Christian Brauner Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210913054121.616001-3-hch@lst.de Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 24 ------------------------ 1 file changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 1093abf7c28c..cecfeedb7361 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -568,30 +568,6 @@ kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode, priv, NULL); } -static inline struct kernfs_node * -kernfs_create_file_ns(struct kernfs_node *parent, const char *name, - umode_t mode, kuid_t uid, kgid_t gid, - loff_t size, const struct kernfs_ops *ops, - void *priv, const void *ns) -{ - struct lock_class_key *key = NULL; - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - key = (struct lock_class_key *)&ops->lockdep_key; -#endif - return __kernfs_create_file(parent, name, mode, uid, gid, - size, ops, priv, ns, key); -} - -static inline struct kernfs_node * -kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, - loff_t size, const struct kernfs_ops *ops, void *priv) -{ - return kernfs_create_file_ns(parent, name, mode, - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, - size, ops, priv, NULL); -} - static inline int kernfs_remove_by_name(struct kernfs_node *parent, const char *name) { -- cgit v1.2.3 From eaf501e0d8af691e532b6b9aee511659cf5ee00c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 13 Sep 2021 07:41:11 +0200 Subject: kernfs: remove the unused lockdep_key field in struct kernfs_ops Not actually used anywhere. Acked-by: Christian Brauner Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210913054121.616001-4-hch@lst.de Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index cecfeedb7361..3ccce6f24548 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -269,10 +269,6 @@ struct kernfs_ops { struct poll_table_struct *pt); int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif }; /* -- cgit v1.2.3 From a2aec2c86ef0cad0fd6be718cfeb5cf5eefbfca9 Mon Sep 17 00:00:00 2001 From: "GONG, Ruiqi" Date: Mon, 30 Aug 2021 16:33:56 +0800 Subject: mtd: Remove obsolete macros only used by the old nand_ecclayout struct All uses of MTD_MAX_{OOBFREE,ECCPOS}_ENTRIES_LARGE have been removed as commit ef5eeea6e911 ("mtd: nand: brcm: switch to mtd_ooblayout_ops") and commit aab616e31d1c ("mtd: kill the nand_ecclayout struct") replaced struct nand_ecclayout by the new mtd_ooblayout_ops interface. Remove these two macros therefore. Reported-by: Yi Yang Signed-off-by: GONG, Ruiqi Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20210830083356.31702-1-gongruiqi1@huawei.com --- include/linux/mtd/mtd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 88227044fc86..f5e7dfc2e4e9 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -72,8 +72,6 @@ struct mtd_oob_ops { uint8_t *oobbuf; }; -#define MTD_MAX_OOBFREE_ENTRIES_LARGE 32 -#define MTD_MAX_ECCPOS_ENTRIES_LARGE 640 /** * struct mtd_oob_region - oob region definition * @offset: region offset -- cgit v1.2.3 From 67f1e027c27054e641584655020a417eaac9cb3a Mon Sep 17 00:00:00 2001 From: Lukas Prediger Date: Tue, 14 Sep 2021 00:09:42 +0100 Subject: drivers/cdrom: improved ioctl for media change detection The current implementation of the CDROM_MEDIA_CHANGED ioctl relies on global state, meaning that only one process can detect a disc change while the ioctl call will return 0 for other calling processes afterwards (see bug 213267). This introduces a new cdrom ioctl, CDROM_TIMED_MEDIA_CHANGE, that works by maintaining a timestamp of the last detected disc change instead of a boolean flag: Processes calling this ioctl command can provide a timestamp of the last disc change known to them and receive an indication whether the disc was changed since then and the updated timestamp. I considered fixing the buggy behavior in the original CDROM_MEDIA_CHANGED ioctl but that would require maintaining state for each calling process in the kernel, which seems like a worse solution than introducing this new ioctl. Signed-off-by: Lukas Prediger Link: https://lore.kernel.org/all/20210912191207.74449-1-lumip@lumip.de Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20210913230942.1188-1-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- Documentation/cdrom/cdrom-standard.rst | 11 ++++++ Documentation/userspace-api/ioctl/cdrom.rst | 3 ++ drivers/cdrom/cdrom.c | 59 +++++++++++++++++++++++++++-- include/linux/cdrom.h | 1 + include/uapi/linux/cdrom.h | 19 ++++++++++ 5 files changed, 89 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 5845960ca382..52ea7b6b2fe8 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -907,6 +907,17 @@ commands can be identified by the underscores in their names. specifies the slot for which the information is given. The special value *CDSL_CURRENT* requests that information about the currently selected slot be returned. +`CDROM_TIMED_MEDIA_CHANGE` + Checks whether the disc has been changed since a user supplied time + and returns the time of the last disc change. + + *arg* is a pointer to a *cdrom_timed_media_change_info* struct. + *arg->last_media_change* may be set by calling code to signal + the timestamp of the last known media change (by the caller). + Upon successful return, this ioctl call will set + *arg->last_media_change* to the latest media change timestamp (in ms) + known by the kernel/driver and set *arg->has_changed* to 1 if + that timestamp is more recent than the timestamp set by the caller. `CDROM_DRIVE_STATUS` Returns the status of the drive by a call to *drive_status()*. Return values are defined in cdrom_drive_status_. diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst index 3b4c0506de46..bac5bbf93ca0 100644 --- a/Documentation/userspace-api/ioctl/cdrom.rst +++ b/Documentation/userspace-api/ioctl/cdrom.rst @@ -54,6 +54,9 @@ are as follows: CDROM_SELECT_SPEED Set the CD-ROM speed CDROM_SELECT_DISC Select disc (for juke-boxes) CDROM_MEDIA_CHANGED Check is media changed + CDROM_TIMED_MEDIA_CHANGE Check if media changed + since given time + (struct cdrom_timed_media_change_info) CDROM_DRIVE_STATUS Get tray position, etc. CDROM_DISC_STATUS Get disc type, etc. CDROM_CHANGER_NSLOTS Get number of slots diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index bd2e5b1560f5..89a68457820a 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -344,6 +344,12 @@ static void cdrom_sysctl_register(void); static LIST_HEAD(cdrom_list); +static void signal_media_change(struct cdrom_device_info *cdi) +{ + cdi->mc_flags = 0x3; /* set media changed bits, on both queues */ + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); +} + int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi, struct packet_command *cgc) { @@ -616,6 +622,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) ENSURE(cdo, generic_packet, CDC_GENERIC_PACKET); cdi->mc_flags = 0; cdi->options = CDO_USE_FFLAGS; + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); if (autoclose == 1 && CDROM_CAN(CDC_CLOSE_TRAY)) cdi->options |= (int) CDO_AUTO_CLOSE; @@ -1421,8 +1428,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) cdi->ops->check_events(cdi, 0, slot); if (slot == CDSL_NONE) { - /* set media changed bits, on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); return cdrom_load_unload(cdi, -1); } @@ -1455,7 +1461,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) slot = curslot; /* set media changed bits on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); if ((ret = cdrom_load_unload(cdi, slot))) return ret; @@ -1521,7 +1527,7 @@ int media_changed(struct cdrom_device_info *cdi, int queue) cdi->ioctl_events = 0; if (changed) { - cdi->mc_flags = 0x3; /* set bit on both queues */ + signal_media_change(cdi); ret |= 1; cdi->media_written = 0; } @@ -2336,6 +2342,49 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, return ret; } +/* + * Media change detection with timing information. + * + * arg is a pointer to a cdrom_timed_media_change_info struct. + * arg->last_media_change may be set by calling code to signal + * the timestamp (in ms) of the last known media change (by the caller). + * Upon successful return, ioctl call will set arg->last_media_change + * to the latest media change timestamp known by the kernel/driver + * and set arg->has_changed to 1 if that timestamp is more recent + * than the timestamp set by the caller. + */ +static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi, + unsigned long arg) +{ + int ret; + struct cdrom_timed_media_change_info __user *info; + struct cdrom_timed_media_change_info tmp_info; + + if (!CDROM_CAN(CDC_MEDIA_CHANGED)) + return -ENOSYS; + + info = (struct cdrom_timed_media_change_info __user *)arg; + cd_dbg(CD_DO_IOCTL, "entering CDROM_TIMED_MEDIA_CHANGE\n"); + + ret = cdrom_ioctl_media_changed(cdi, CDSL_CURRENT); + if (ret < 0) + return ret; + + if (copy_from_user(&tmp_info, info, sizeof(tmp_info)) != 0) + return -EFAULT; + + tmp_info.media_flags = 0; + if (tmp_info.last_media_change - cdi->last_media_change_ms < 0) + tmp_info.media_flags |= MEDIA_CHANGED_FLAG; + + tmp_info.last_media_change = cdi->last_media_change_ms; + + if (copy_to_user(info, &tmp_info, sizeof(*info)) != 0) + return -EFAULT; + + return 0; +} + static int cdrom_ioctl_set_options(struct cdrom_device_info *cdi, unsigned long arg) { @@ -3313,6 +3362,8 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, return cdrom_ioctl_eject_sw(cdi, arg); case CDROM_MEDIA_CHANGED: return cdrom_ioctl_media_changed(cdi, arg); + case CDROM_TIMED_MEDIA_CHANGE: + return cdrom_ioctl_timed_media_change(cdi, arg); case CDROM_SET_OPTIONS: return cdrom_ioctl_set_options(cdi, arg); case CDROM_CLEAR_OPTIONS: diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index c4fef00abdf3..0a89f111e00e 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -64,6 +64,7 @@ struct cdrom_device_info { int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + __s64 last_media_change_ms; }; struct cdrom_device_ops { diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 6c34f6e2f1f7..804ff8d98f71 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -147,6 +147,8 @@ #define CDROM_NEXT_WRITABLE 0x5394 /* get next writable block */ #define CDROM_LAST_WRITTEN 0x5395 /* get last block written on disc */ +#define CDROM_TIMED_MEDIA_CHANGE 0x5396 /* get the timestamp of the last media change */ + /******************************************************* * CDROM IOCTL structures *******************************************************/ @@ -295,6 +297,23 @@ struct cdrom_generic_command }; }; +/* This struct is used by CDROM_TIMED_MEDIA_CHANGE */ +struct cdrom_timed_media_change_info { + __s64 last_media_change; /* Timestamp of the last detected media + * change in ms. May be set by caller, + * updated upon successful return of + * ioctl. + */ + __u64 media_flags; /* Flags returned by ioctl to indicate + * media status. + */ +}; +#define MEDIA_CHANGED_FLAG 0x1 /* Last detected media change was more + * recent than last_media_change set by + * caller. + */ +/* other bits of media_flags available for future use */ + /* * A CD-ROM physical sector size is 2048, 2052, 2056, 2324, 2332, 2336, * 2340, or 2352 bytes long. -- cgit v1.2.3 From e25b694bf1d9ef4a3f36c0b85348f8e780f22139 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 24 Jun 2021 11:41:05 +0200 Subject: x86: Always inline context_tracking_guest_enter() Yes, it really did out-of-line this.... vmlinux.o: warning: objtool: vmx_vcpu_enter_exit()+0x31: call to context_tracking_guest_enter() leaves .noinstr.text section 000000000019f660 : 19f660: e8 00 00 00 00 callq 19f665 19f661: R_X86_64_PLT32 __sanitizer_cov_trace_pc-0x4 19f665: 31 c0 xor %eax,%eax 19f667: c3 retq Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210624095148.003928226@infradead.org --- include/linux/context_tracking.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 4d7fced3a39f..7a14807c9d1a 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -105,7 +105,7 @@ static inline void user_exit_irqoff(void) { } static inline enum ctx_state exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; } -static inline bool context_tracking_guest_enter(void) { return false; } +static __always_inline bool context_tracking_guest_enter(void) { return false; } static inline void context_tracking_guest_exit(void) { } #endif /* !CONFIG_CONTEXT_TRACKING */ -- cgit v1.2.3 From a5c071ccfa1728508f31e61213ee795e4529d0d4 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 28 Jul 2021 12:28:27 -0700 Subject: rcu-tasks: Remove second argument of rcu_read_unlock_trace_special() The second argument of rcu_read_unlock_trace_special() is always zero. When called from exit_tasks_rcu_finish_trace(), it is the constant zero, and rcu_read_unlock_trace_special() doesn't get called from rcu_read_unlock_trace() unless the value of local variable "nesting" is zero because in that case the early return is taken instead. This commit therefore removes the "nesting" argument from the rcu_read_unlock_trace_special() function, substituting the constant zero within that function. This commit also adds a WARN_ON_ONCE() to rcu_read_lock_trace_held() in case non-zeroness some day appears. Signed-off-by: Paul E. McKenney --- include/linux/rcupdate_trace.h | 5 +++-- kernel/rcu/tasks.h | 6 +++--- 2 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate_trace.h b/include/linux/rcupdate_trace.h index 86c8f6c98412..6f9c35817398 100644 --- a/include/linux/rcupdate_trace.h +++ b/include/linux/rcupdate_trace.h @@ -31,7 +31,7 @@ static inline int rcu_read_lock_trace_held(void) #ifdef CONFIG_TASKS_TRACE_RCU -void rcu_read_unlock_trace_special(struct task_struct *t, int nesting); +void rcu_read_unlock_trace_special(struct task_struct *t); /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section @@ -80,7 +80,8 @@ static inline void rcu_read_unlock_trace(void) WRITE_ONCE(t->trc_reader_nesting, nesting); return; // We assume shallow reader nesting. } - rcu_read_unlock_trace_special(t, nesting); + WARN_ON_ONCE(nesting != 0); + rcu_read_unlock_trace_special(t); } void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 8387e70e6b00..a3f4f9bd8c67 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -848,7 +848,7 @@ static void rcu_read_unlock_iw(struct irq_work *iwp) static DEFINE_IRQ_WORK(rcu_tasks_trace_iw, rcu_read_unlock_iw); /* If we are the last reader, wake up the grace-period kthread. */ -void rcu_read_unlock_trace_special(struct task_struct *t, int nesting) +void rcu_read_unlock_trace_special(struct task_struct *t) { int nq = READ_ONCE(t->trc_reader_special.b.need_qs); @@ -858,7 +858,7 @@ void rcu_read_unlock_trace_special(struct task_struct *t, int nesting) // Update .need_qs before ->trc_reader_nesting for irq/NMI handlers. if (nq) WRITE_ONCE(t->trc_reader_special.b.need_qs, false); - WRITE_ONCE(t->trc_reader_nesting, nesting); + WRITE_ONCE(t->trc_reader_nesting, 0); if (nq && atomic_dec_and_test(&trc_n_readers_need_end)) irq_work_queue(&rcu_tasks_trace_iw); } @@ -1200,7 +1200,7 @@ static void exit_tasks_rcu_finish_trace(struct task_struct *t) WARN_ON_ONCE(READ_ONCE(t->trc_reader_nesting)); WRITE_ONCE(t->trc_reader_nesting, 0); if (WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs))) - rcu_read_unlock_trace_special(t, 0); + rcu_read_unlock_trace_special(t); } /** -- cgit v1.2.3 From 925da92ba5cb0c82d07cdd5049a07e40f54e9c44 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 26 Aug 2021 22:21:22 -0400 Subject: rcu: Avoid unneeded function call in rcu_read_unlock() Since commit aa40c138cc8f3 ("rcu: Report QS for outermost PREEMPT=n rcu_read_unlock() for strict GPs") the function rcu_read_unlock_strict() is invoked by the inlined rcu_read_unlock() function. However, rcu_read_unlock_strict() is an empty function in production kernels, which are built with CONFIG_RCU_STRICT_GRACE_PERIOD=n. There is a mention of rcu_read_unlock_strict() in the BPF verifier, but this is in a deny-list, meaning that BPF does not care whether rcu_read_unlock_strict() is ever called. This commit therefore provides a slight performance improvement by hoisting the check of CONFIG_RCU_STRICT_GRACE_PERIOD from rcu_read_unlock_strict() into rcu_read_unlock(), thus avoiding the pointless call to an empty function. Cc: Alexei Starovoitov Acked-by: Andrii Nakryiko Signed-off-by: Waiman Long Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 3 ++- kernel/rcu/tree_plugin.h | 3 +-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 434d12fe2d4f..5e0beb5c5659 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -71,7 +71,8 @@ static inline void __rcu_read_lock(void) static inline void __rcu_read_unlock(void) { preempt_enable(); - rcu_read_unlock_strict(); + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) + rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index d070059163d7..1a6fdb03d0a5 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -814,8 +814,7 @@ void rcu_read_unlock_strict(void) { struct rcu_data *rdp; - if (!IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD) || - irqs_disabled() || preempt_count() || !rcu_state.gp_kthread) + if (irqs_disabled() || preempt_count() || !rcu_state.gp_kthread) return; rdp = this_cpu_ptr(&rcu_data); rcu_report_qs_rdp(rdp); -- cgit v1.2.3 From 8dc84dcd7f74b50f81de3dbf6f6b5b146e3a8eea Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 16 Sep 2021 14:27:41 -0700 Subject: net: phy: broadcom: Enable 10BaseT DAC early wake Enable the DAC early wake when then link operates at 10BaseT allows power savings in the hundreds of milli Watts by shutting down the transmitter. A number of errata have been issued for various Gigabit PHYs and the recommendation is to enable both the early and forced DAC wake to be on the safe side. This needs to be done dynamically based upon the link state, which is why a link_change_notify callback is utilized. Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20210916212742.1653088-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/broadcom.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/brcmphy.h | 1 + 2 files changed, 48 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 83aea5c5cd03..add0c4e33425 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -702,6 +702,36 @@ static void bcm54xx_get_stats(struct phy_device *phydev, bcm_phy_get_stats(phydev, priv->stats, stats, data); } +static void bcm54xx_link_change_notify(struct phy_device *phydev) +{ + u16 mask = MII_BCM54XX_EXP_EXP08_EARLY_DAC_WAKE | + MII_BCM54XX_EXP_EXP08_FORCE_DAC_WAKE; + int ret; + + if (phydev->state != PHY_RUNNING) + return; + + /* Don't change the DAC wake settings if auto power down + * is not requested. + */ + if (!(phydev->dev_flags & PHY_BRCM_AUTO_PWRDWN_ENABLE)) + return; + + ret = bcm_phy_read_exp(phydev, MII_BCM54XX_EXP_EXP08); + if (ret < 0) + return; + + /* Enable/disable 10BaseT auto and forced early DAC wake depending + * on the negotiated speed, those settings should only be done + * for 10Mbits/sec. + */ + if (phydev->speed == SPEED_10) + ret |= mask; + else + ret &= ~mask; + bcm_phy_write_exp(phydev, MII_BCM54XX_EXP_EXP08, ret); +} + static struct phy_driver broadcom_drivers[] = { { .phy_id = PHY_ID_BCM5411, @@ -715,6 +745,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5421, .phy_id_mask = 0xfffffff0, @@ -727,6 +758,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54210E, .phy_id_mask = 0xfffffff0, @@ -739,6 +771,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, @@ -751,6 +784,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54612E, .phy_id_mask = 0xfffffff0, @@ -763,6 +797,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54616S, .phy_id_mask = 0xfffffff0, @@ -774,6 +809,7 @@ static struct phy_driver broadcom_drivers[] = { .handle_interrupt = bcm_phy_handle_interrupt, .read_status = bcm54616s_read_status, .probe = bcm54616s_probe, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5464, .phy_id_mask = 0xfffffff0, @@ -788,6 +824,7 @@ static struct phy_driver broadcom_drivers[] = { .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5481, .phy_id_mask = 0xfffffff0, @@ -801,6 +838,7 @@ static struct phy_driver broadcom_drivers[] = { .config_aneg = bcm5481_config_aneg, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54810, .phy_id_mask = 0xfffffff0, @@ -816,6 +854,7 @@ static struct phy_driver broadcom_drivers[] = { .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = bcm54xx_resume, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM54811, .phy_id_mask = 0xfffffff0, @@ -831,6 +870,7 @@ static struct phy_driver broadcom_drivers[] = { .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = bcm54xx_resume, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM5482, .phy_id_mask = 0xfffffff0, @@ -843,6 +883,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM50610, .phy_id_mask = 0xfffffff0, @@ -855,6 +896,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM50610M, .phy_id_mask = 0xfffffff0, @@ -867,6 +909,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM57780, .phy_id_mask = 0xfffffff0, @@ -879,6 +922,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCMAC131, .phy_id_mask = 0xfffffff0, @@ -905,6 +949,7 @@ static struct phy_driver broadcom_drivers[] = { .get_strings = bcm_phy_get_strings, .get_stats = bcm54xx_get_stats, .probe = bcm54xx_phy_probe, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM53125, .phy_id_mask = 0xfffffff0, @@ -918,6 +963,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, }, { .phy_id = PHY_ID_BCM89610, .phy_id_mask = 0xfffffff0, @@ -930,6 +976,7 @@ static struct phy_driver broadcom_drivers[] = { .config_init = bcm54xx_config_init, .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, + .link_change_notify = bcm54xx_link_change_notify, } }; module_phy_driver(broadcom_drivers); diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index c2c2147dfeb8..3308cebe1c19 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -233,6 +233,7 @@ #define MII_BCM54XX_EXP_EXP08 0x0F08 #define MII_BCM54XX_EXP_EXP08_RJCT_2MHZ 0x0001 #define MII_BCM54XX_EXP_EXP08_EARLY_DAC_WAKE 0x0200 +#define MII_BCM54XX_EXP_EXP08_FORCE_DAC_WAKE 0x0100 #define MII_BCM54XX_EXP_EXP75 0x0f75 #define MII_BCM54XX_EXP_EXP75_VDACCTRL 0x003c #define MII_BCM54XX_EXP_EXP75_CM_OSC 0x0001 -- cgit v1.2.3 From 12235da8c80a1f9909008e4ca6036d5772b81192 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Thu, 9 Sep 2021 11:32:18 +0200 Subject: kernel/locking: Add context to ww_mutex_trylock() i915 will soon gain an eviction path that trylock a whole lot of locks for eviction, getting dmesg failures like below: BUG: MAX_LOCK_DEPTH too low! turning off the locking correctness validator. depth: 48 max: 48! 48 locks held by i915_selftest/5776: #0: ffff888101a79240 (&dev->mutex){....}-{3:3}, at: __driver_attach+0x88/0x160 #1: ffffc900009778c0 (reservation_ww_class_acquire){+.+.}-{0:0}, at: i915_vma_pin.constprop.63+0x39/0x1b0 [i915] #2: ffff88800cf74de8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_vma_pin.constprop.63+0x5f/0x1b0 [i915] #3: ffff88810c7f9e38 (&vm->mutex/1){+.+.}-{3:3}, at: i915_vma_pin_ww+0x1c4/0x9d0 [i915] #4: ffff88810bad5768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] #5: ffff88810bad60e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] ... #46: ffff88811964d768 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] #47: ffff88811964e0e8 (reservation_ww_class_mutex){+.+.}-{3:3}, at: i915_gem_evict_something+0x110/0x860 [i915] INFO: lockdep is turned off. Fixing eviction to nest into ww_class_acquire is a high priority, but it requires a rework of the entire driver, which can only be done one step at a time. As an intermediate solution, add an acquire context to ww_mutex_trylock, which allows us to do proper nesting annotations on the trylocks, making the above lockdep splat disappear. This is also useful in regulator_lock_nested, which may avoid dropping regulator_nesting_mutex in the uncontended path, so use it there. TTM may be another user for this, where we could lock a buffer in a fastpath with list locks held, without dropping all locks we hold. [peterz: rework actual ww_mutex_trylock() implementations] Signed-off-by: Maarten Lankhorst Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/YUBGPdDDjKlxAuXJ@hirez.programming.kicks-ass.net --- drivers/gpu/drm/drm_modeset_lock.c | 2 +- drivers/regulator/core.c | 2 +- include/linux/dma-resv.h | 2 +- include/linux/ww_mutex.h | 15 +------ kernel/locking/mutex.c | 41 ++++++++++++++++++ kernel/locking/test-ww_mutex.c | 86 ++++++++++++++++++++++++++++---------- kernel/locking/ww_rt_mutex.c | 25 +++++++++++ lib/locking-selftest.c | 2 +- 8 files changed, 137 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index fcfe1a03c4a1..bf8a6e823a15 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -248,7 +248,7 @@ static inline int modeset_lock(struct drm_modeset_lock *lock, if (ctx->trylock_only) { lockdep_assert_held(&ctx->ww_ctx); - if (!ww_mutex_trylock(&lock->mutex)) + if (!ww_mutex_trylock(&lock->mutex, NULL)) return -EBUSY; else return 0; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index ca6caba8a191..f4d441b1a8bf 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -145,7 +145,7 @@ static inline int regulator_lock_nested(struct regulator_dev *rdev, mutex_lock(®ulator_nesting_mutex); - if (ww_ctx || !ww_mutex_trylock(&rdev->mutex)) { + if (!ww_mutex_trylock(&rdev->mutex, ww_ctx)) { if (rdev->mutex_owner == current) rdev->ref_cnt++; else diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index e1ca2080a1ff..39fefb86780b 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -173,7 +173,7 @@ static inline int dma_resv_lock_slow_interruptible(struct dma_resv *obj, */ static inline bool __must_check dma_resv_trylock(struct dma_resv *obj) { - return ww_mutex_trylock(&obj->lock); + return ww_mutex_trylock(&obj->lock, NULL); } /** diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 29db736af86d..bb763085479a 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -28,12 +28,10 @@ #ifndef CONFIG_PREEMPT_RT #define WW_MUTEX_BASE mutex #define ww_mutex_base_init(l,n,k) __mutex_init(l,n,k) -#define ww_mutex_base_trylock(l) mutex_trylock(l) #define ww_mutex_base_is_locked(b) mutex_is_locked((b)) #else #define WW_MUTEX_BASE rt_mutex #define ww_mutex_base_init(l,n,k) __rt_mutex_init(l,n,k) -#define ww_mutex_base_trylock(l) rt_mutex_trylock(l) #define ww_mutex_base_is_locked(b) rt_mutex_base_is_locked(&(b)->rtmutex) #endif @@ -339,17 +337,8 @@ ww_mutex_lock_slow_interruptible(struct ww_mutex *lock, extern void ww_mutex_unlock(struct ww_mutex *lock); -/** - * ww_mutex_trylock - tries to acquire the w/w mutex without acquire context - * @lock: mutex to lock - * - * Trylocks a mutex without acquire context, so no deadlock detection is - * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. - */ -static inline int __must_check ww_mutex_trylock(struct ww_mutex *lock) -{ - return ww_mutex_base_trylock(&lock->base); -} +extern int __must_check ww_mutex_trylock(struct ww_mutex *lock, + struct ww_acquire_ctx *ctx); /*** * ww_mutex_destroy - mark a w/w mutex unusable diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index d456579d0952..2fede72b6af5 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -94,6 +94,9 @@ static inline unsigned long __owner_flags(unsigned long owner) return owner & MUTEX_FLAGS; } +/* + * Returns: __mutex_owner(lock) on failure or NULL on success. + */ static inline struct task_struct *__mutex_trylock_common(struct mutex *lock, bool handoff) { unsigned long owner, curr = (unsigned long)current; @@ -736,6 +739,44 @@ __ww_mutex_lock(struct mutex *lock, unsigned int state, unsigned int subclass, return __mutex_lock_common(lock, state, subclass, NULL, ip, ww_ctx, true); } +/** + * ww_mutex_trylock - tries to acquire the w/w mutex with optional acquire context + * @ww: mutex to lock + * @ww_ctx: optional w/w acquire context + * + * Trylocks a mutex with the optional acquire context; no deadlock detection is + * possible. Returns 1 if the mutex has been acquired successfully, 0 otherwise. + * + * Unlike ww_mutex_lock, no deadlock handling is performed. However, if a @ctx is + * specified, -EALREADY handling may happen in calls to ww_mutex_trylock. + * + * A mutex acquired with this function must be released with ww_mutex_unlock. + */ +int ww_mutex_trylock(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) +{ + if (!ww_ctx) + return mutex_trylock(&ww->base); + + MUTEX_WARN_ON(ww->base.magic != &ww->base); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__mutex_trylock(&ww->base)) { + ww_mutex_set_context_fastpath(ww, ww_ctx); + mutex_acquire_nest(&ww->base.dep_map, 0, 1, &ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + #ifdef CONFIG_DEBUG_LOCK_ALLOC void __sched mutex_lock_nested(struct mutex *lock, unsigned int subclass) diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 3e82f449b4ff..d63ac411f367 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -16,6 +16,15 @@ static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; +#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH +#define ww_acquire_init_noinject(a, b) do { \ + ww_acquire_init((a), (b)); \ + (a)->deadlock_inject_countdown = ~0U; \ + } while (0) +#else +#define ww_acquire_init_noinject(a, b) ww_acquire_init((a), (b)) +#endif + struct test_mutex { struct work_struct work; struct ww_mutex mutex; @@ -36,7 +45,7 @@ static void test_mutex_work(struct work_struct *work) wait_for_completion(&mtx->go); if (mtx->flags & TEST_MTX_TRY) { - while (!ww_mutex_trylock(&mtx->mutex)) + while (!ww_mutex_trylock(&mtx->mutex, NULL)) cond_resched(); } else { ww_mutex_lock(&mtx->mutex, NULL); @@ -109,19 +118,38 @@ static int test_mutex(void) return 0; } -static int test_aa(void) +static int test_aa(bool trylock) { struct ww_mutex mutex; struct ww_acquire_ctx ctx; int ret; + const char *from = trylock ? "trylock" : "lock"; ww_mutex_init(&mutex, &ww_class); ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&mutex, &ctx); + if (!trylock) { + ret = ww_mutex_lock(&mutex, &ctx); + if (ret) { + pr_err("%s: initial lock failed!\n", __func__); + goto out; + } + } else { + if (!ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: initial trylock failed!\n", __func__); + goto out; + } + } - if (ww_mutex_trylock(&mutex)) { - pr_err("%s: trylocked itself!\n", __func__); + if (ww_mutex_trylock(&mutex, NULL)) { + pr_err("%s: trylocked itself without context from %s!\n", __func__, from); + ww_mutex_unlock(&mutex); + ret = -EINVAL; + goto out; + } + + if (ww_mutex_trylock(&mutex, &ctx)) { + pr_err("%s: trylocked itself with context from %s!\n", __func__, from); ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; @@ -129,17 +157,17 @@ static int test_aa(void) ret = ww_mutex_lock(&mutex, &ctx); if (ret != -EALREADY) { - pr_err("%s: missed deadlock for recursing, ret=%d\n", - __func__, ret); + pr_err("%s: missed deadlock for recursing, ret=%d from %s\n", + __func__, ret, from); if (!ret) ww_mutex_unlock(&mutex); ret = -EINVAL; goto out; } + ww_mutex_unlock(&mutex); ret = 0; out: - ww_mutex_unlock(&mutex); ww_acquire_fini(&ctx); return ret; } @@ -150,7 +178,7 @@ struct test_abba { struct ww_mutex b_mutex; struct completion a_ready; struct completion b_ready; - bool resolve; + bool resolve, trylock; int result; }; @@ -160,8 +188,13 @@ static void test_abba_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err; - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba->b_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!abba->trylock) + ww_mutex_lock(&abba->b_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba->b_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba->b_mutex.ctx) != &ctx); complete(&abba->b_ready); wait_for_completion(&abba->a_ready); @@ -181,7 +214,7 @@ static void test_abba_work(struct work_struct *work) abba->result = err; } -static int test_abba(bool resolve) +static int test_abba(bool trylock, bool resolve) { struct test_abba abba; struct ww_acquire_ctx ctx; @@ -192,12 +225,18 @@ static int test_abba(bool resolve) INIT_WORK_ONSTACK(&abba.work, test_abba_work); init_completion(&abba.a_ready); init_completion(&abba.b_ready); + abba.trylock = trylock; abba.resolve = resolve; schedule_work(&abba.work); - ww_acquire_init(&ctx, &ww_class); - ww_mutex_lock(&abba.a_mutex, &ctx); + ww_acquire_init_noinject(&ctx, &ww_class); + if (!trylock) + ww_mutex_lock(&abba.a_mutex, &ctx); + else + WARN_ON(!ww_mutex_trylock(&abba.a_mutex, &ctx)); + + WARN_ON(READ_ONCE(abba.a_mutex.ctx) != &ctx); complete(&abba.a_ready); wait_for_completion(&abba.b_ready); @@ -249,7 +288,7 @@ static void test_cycle_work(struct work_struct *work) struct ww_acquire_ctx ctx; int err, erra = 0; - ww_acquire_init(&ctx, &ww_class); + ww_acquire_init_noinject(&ctx, &ww_class); ww_mutex_lock(&cycle->a_mutex, &ctx); complete(cycle->a_signal); @@ -581,7 +620,9 @@ static int stress(int nlocks, int nthreads, unsigned int flags) static int __init test_ww_mutex_init(void) { int ncpus = num_online_cpus(); - int ret; + int ret, i; + + printk(KERN_INFO "Beginning ww mutex selftests\n"); wq = alloc_workqueue("test-ww_mutex", WQ_UNBOUND, 0); if (!wq) @@ -591,17 +632,19 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; - ret = test_aa(); + ret = test_aa(false); if (ret) return ret; - ret = test_abba(false); + ret = test_aa(true); if (ret) return ret; - ret = test_abba(true); - if (ret) - return ret; + for (i = 0; i < 4; i++) { + ret = test_abba(i & 1, i & 2); + if (ret) + return ret; + } ret = test_cycle(ncpus); if (ret) @@ -619,6 +662,7 @@ static int __init test_ww_mutex_init(void) if (ret) return ret; + printk(KERN_INFO "All ww mutex selftests passed\n"); return 0; } diff --git a/kernel/locking/ww_rt_mutex.c b/kernel/locking/ww_rt_mutex.c index 3f1fff7d2780..0e00205cf467 100644 --- a/kernel/locking/ww_rt_mutex.c +++ b/kernel/locking/ww_rt_mutex.c @@ -9,6 +9,31 @@ #define WW_RT #include "rtmutex.c" +int ww_mutex_trylock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + struct rt_mutex *rtm = &lock->base; + + if (!ww_ctx) + return rt_mutex_trylock(rtm); + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here, since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; + + if (__rt_mutex_trylock(&rtm->rtmutex)) { + ww_mutex_set_context_fastpath(lock, ww_ctx); + mutex_acquire_nest(&rtm->dep_map, 0, 1, ww_ctx->dep_map, _RET_IP_); + return 1; + } + + return 0; +} +EXPORT_SYMBOL(ww_mutex_trylock); + static int __sched __ww_rt_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx, unsigned int state, unsigned long ip) diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index 161108e5d2fe..71652e1c397c 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -258,7 +258,7 @@ static void init_shared_classes(void) #define WWAF(x) ww_acquire_fini(x) #define WWL(x, c) ww_mutex_lock(x, c) -#define WWT(x) ww_mutex_trylock(x) +#define WWT(x) ww_mutex_trylock(x, NULL) #define WWL1(x) ww_mutex_lock(x, NULL) #define WWU(x) ww_mutex_unlock(x) -- cgit v1.2.3 From a2e05ddda11b0bd529f443df9089ab498b2c2642 Mon Sep 17 00:00:00 2001 From: Zhouyi Zhou Date: Wed, 11 Aug 2021 10:59:20 +0800 Subject: lockdep: Improve comments in wait-type checks Comments in wait-type checks be improved by mentioning the PREEPT_RT kernel configure option. Signed-off-by: Zhouyi Zhou Signed-off-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Link: https://lkml.kernel.org/r/20210811025920.20751-1-zhouzhouyi@gmail.com --- include/linux/lockdep_types.h | 2 +- kernel/locking/lockdep.c | 2 +- kernel/rcu/update.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h index 3e726ace5c62..d22430840b53 100644 --- a/include/linux/lockdep_types.h +++ b/include/linux/lockdep_types.h @@ -21,7 +21,7 @@ enum lockdep_wait_type { LD_WAIT_SPIN, /* spin loops, raw_spinlock_t etc.. */ #ifdef CONFIG_PROVE_RAW_LOCK_NESTING - LD_WAIT_CONFIG, /* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */ + LD_WAIT_CONFIG, /* preemptible in PREEMPT_RT, spinlock_t etc.. */ #else LD_WAIT_CONFIG = LD_WAIT_SPIN, #endif diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index bfa0a347f27c..4e6312977ffb 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4671,7 +4671,7 @@ print_lock_invalid_wait_context(struct task_struct *curr, /* * Verify the wait_type context. * - * This check validates we takes locks in the right wait-type order; that is it + * This check validates we take locks in the right wait-type order; that is it * ensures that we do not take mutexes inside spinlocks and do not attempt to * acquire spinlocks inside raw_spinlocks and the sort. * diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index c21b38cc25e9..690b0cec7459 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -247,7 +247,7 @@ struct lockdep_map rcu_lock_map = { .name = "rcu_read_lock", .key = &rcu_lock_key, .wait_type_outer = LD_WAIT_FREE, - .wait_type_inner = LD_WAIT_CONFIG, /* XXX PREEMPT_RCU ? */ + .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_RT implies PREEMPT_RCU */ }; EXPORT_SYMBOL_GPL(rcu_lock_map); @@ -256,7 +256,7 @@ struct lockdep_map rcu_bh_lock_map = { .name = "rcu_read_lock_bh", .key = &rcu_bh_lock_key, .wait_type_outer = LD_WAIT_FREE, - .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_LOCK also makes BH preemptible */ + .wait_type_inner = LD_WAIT_CONFIG, /* PREEMPT_RT makes BH preemptible. */ }; EXPORT_SYMBOL_GPL(rcu_bh_lock_map); -- cgit v1.2.3 From f7427ba5ce9c5438ad392b6cbcc4ca8a0487d7e7 Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Wed, 25 Aug 2021 15:07:04 +0800 Subject: locking/lockdep: Cleanup the repeated declaration 'struct task_struct' has been decleared twice, so keep the top one and cleanup the repeated one. Signed-off-by: Shaokun Zhang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1629875224-32751-1-git-send-email-zhangshaokun@hisilicon.com --- include/linux/debug_locks.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h index 3f49e65169c6..dbb409d77d4f 100644 --- a/include/linux/debug_locks.h +++ b/include/linux/debug_locks.h @@ -47,8 +47,6 @@ extern int debug_locks_off(void); # define locking_selftest() do { } while (0) #endif -struct task_struct; - #ifdef CONFIG_LOCKDEP extern void debug_show_all_locks(void); extern void debug_show_held_locks(struct task_struct *task); -- cgit v1.2.3 From f68d08c437f98ee19a14142b9de2d7afe2032d5c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 17 Sep 2021 11:15:50 -0700 Subject: net: phy: bcm7xxx: Add EPHY entry for 72165 72165 is a 16nm process SoC with a 10/100 integrated Ethernet PHY, create a new macro and set of functions for this different process type. Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20210917181551.2836036-1-f.fainelli@gmail.com Signed-off-by: Jakub Kicinski --- drivers/net/phy/bcm7xxx.c | 201 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/brcmphy.h | 1 + 2 files changed, 202 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index e79297a4bae8..3a29a1493ff1 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -398,6 +398,190 @@ static int bcm7xxx_28nm_ephy_config_init(struct phy_device *phydev) return bcm7xxx_28nm_ephy_apd_enable(phydev); } +static int bcm7xxx_16nm_ephy_afe_config(struct phy_device *phydev) +{ + int tmp, rcalcode, rcalnewcodelp, rcalnewcode11, rcalnewcode11d2; + + /* Reset PHY */ + tmp = genphy_soft_reset(phydev); + if (tmp) + return tmp; + + /* Reset AFE and PLL */ + bcm_phy_write_exp_sel(phydev, 0x0003, 0x0006); + /* Clear reset */ + bcm_phy_write_exp_sel(phydev, 0x0003, 0x0000); + + /* Write PLL/AFE control register to select 54MHz crystal */ + bcm_phy_write_misc(phydev, 0x0030, 0x0001, 0x0000); + bcm_phy_write_misc(phydev, 0x0031, 0x0000, 0x044a); + + /* Change Ka,Kp,Ki to pdiv=1 */ + bcm_phy_write_misc(phydev, 0x0033, 0x0002, 0x71a1); + /* Configuration override */ + bcm_phy_write_misc(phydev, 0x0033, 0x0001, 0x8000); + + /* Change PLL_NDIV and PLL_NUDGE */ + bcm_phy_write_misc(phydev, 0x0031, 0x0001, 0x2f68); + bcm_phy_write_misc(phydev, 0x0031, 0x0002, 0x0000); + + /* Reference frequency is 54Mhz, config_mode[15:14] = 3 (low + * phase) + */ + bcm_phy_write_misc(phydev, 0x0030, 0x0003, 0xc036); + + /* Initialize bypass mode */ + bcm_phy_write_misc(phydev, 0x0032, 0x0003, 0x0000); + /* Bypass code, default: VCOCLK enabled */ + bcm_phy_write_misc(phydev, 0x0033, 0x0000, 0x0002); + /* LDOs at default setting */ + bcm_phy_write_misc(phydev, 0x0030, 0x0002, 0x01c0); + /* Release PLL reset */ + bcm_phy_write_misc(phydev, 0x0030, 0x0001, 0x0001); + + /* Bandgap curvature correction to correct default */ + bcm_phy_write_misc(phydev, 0x0038, 0x0000, 0x0010); + + /* Run RCAL */ + bcm_phy_write_misc(phydev, 0x0039, 0x0003, 0x0038); + bcm_phy_write_misc(phydev, 0x0039, 0x0003, 0x003b); + udelay(2); + bcm_phy_write_misc(phydev, 0x0039, 0x0003, 0x003f); + mdelay(5); + + /* AFE_CAL_CONFIG_0, Vref=1000, Target=10, averaging enabled */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x1c82); + /* AFE_CAL_CONFIG_0, no reset and analog powerup */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9e82); + udelay(2); + /* AFE_CAL_CONFIG_0, start calibration */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9f82); + udelay(100); + /* AFE_CAL_CONFIG_0, clear start calibration, set HiBW */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9e86); + udelay(2); + /* AFE_CAL_CONFIG_0, start calibration with hi BW mode set */ + bcm_phy_write_misc(phydev, 0x0039, 0x0001, 0x9f86); + udelay(100); + + /* Adjust 10BT amplitude additional +7% and 100BT +2% */ + bcm_phy_write_misc(phydev, 0x0038, 0x0001, 0xe7ea); + /* Adjust 1G mode amplitude and 1G testmode1 */ + bcm_phy_write_misc(phydev, 0x0038, 0x0002, 0xede0); + + /* Read CORE_EXPA9 */ + tmp = bcm_phy_read_exp(phydev, 0x00a9); + /* CORE_EXPA9[6:1] is rcalcode[5:0] */ + rcalcode = (tmp & 0x7e) / 2; + /* Correct RCAL code + 1 is -1% rprogr, LP: +16 */ + rcalnewcodelp = rcalcode + 16; + /* Correct RCAL code + 1 is -15 rprogr, 11: +10 */ + rcalnewcode11 = rcalcode + 10; + /* Saturate if necessary */ + if (rcalnewcodelp > 0x3f) + rcalnewcodelp = 0x3f; + if (rcalnewcode11 > 0x3f) + rcalnewcode11 = 0x3f; + /* REXT=1 BYP=1 RCAL_st1<5:0>=new rcal code */ + tmp = 0x00f8 + rcalnewcodelp * 256; + /* Program into AFE_CAL_CONFIG_2 */ + bcm_phy_write_misc(phydev, 0x0039, 0x0003, tmp); + /* AFE_BIAS_CONFIG_0 10BT bias code (Bias: E4) */ + bcm_phy_write_misc(phydev, 0x0038, 0x0001, 0xe7e4); + /* invert adc clock output and 'adc refp ldo current To correct + * default + */ + bcm_phy_write_misc(phydev, 0x003b, 0x0000, 0x8002); + /* 100BT stair case, high BW, 1G stair case, alternate encode */ + bcm_phy_write_misc(phydev, 0x003c, 0x0003, 0xf882); + /* 1000BT DAC transition method per Erol, bits[32], DAC Shuffle + * sequence 1 + 10BT imp adjust bits + */ + bcm_phy_write_misc(phydev, 0x003d, 0x0000, 0x3201); + /* Non-overlap fix */ + bcm_phy_write_misc(phydev, 0x003a, 0x0002, 0x0c00); + + /* pwdb override (rxconfig<5>) to turn on RX LDO indpendent of + * pwdb controls from DSP_TAP10 + */ + bcm_phy_write_misc(phydev, 0x003a, 0x0001, 0x0020); + + /* Remove references to channel 2 and 3 */ + bcm_phy_write_misc(phydev, 0x003b, 0x0002, 0x0000); + bcm_phy_write_misc(phydev, 0x003b, 0x0003, 0x0000); + + /* Set cal_bypassb bit rxconfig<43> */ + bcm_phy_write_misc(phydev, 0x003a, 0x0003, 0x0800); + udelay(2); + + /* Revert pwdb_override (rxconfig<5>) to 0 so that the RX pwr + * is controlled by DSP. + */ + bcm_phy_write_misc(phydev, 0x003a, 0x0001, 0x0000); + + /* Drop LSB */ + rcalnewcode11d2 = (rcalnewcode11 & 0xfffe) / 2; + tmp = bcm_phy_read_misc(phydev, 0x003d, 0x0001); + /* Clear bits [11:5] */ + tmp &= ~0xfe0; + /* set txcfg_ch0<5>=1 (enable + set local rcal) */ + tmp |= 0x0020 | (rcalnewcode11d2 * 64); + bcm_phy_write_misc(phydev, 0x003d, 0x0001, tmp); + bcm_phy_write_misc(phydev, 0x003d, 0x0002, tmp); + + tmp = bcm_phy_read_misc(phydev, 0x003d, 0x0000); + /* set txcfg<45:44>=11 (enable Rextra + invert fullscaledetect) + */ + tmp &= ~0x3000; + tmp |= 0x3000; + bcm_phy_write_misc(phydev, 0x003d, 0x0000, tmp); + + return 0; +} + +static int bcm7xxx_16nm_ephy_config_init(struct phy_device *phydev) +{ + int ret, val; + + ret = bcm7xxx_16nm_ephy_afe_config(phydev); + if (ret) + return ret; + + ret = bcm_phy_set_eee(phydev, true); + if (ret) + return ret; + + ret = bcm_phy_read_shadow(phydev, BCM54XX_SHD_SCR3); + if (ret < 0) + return ret; + + val = ret; + + /* Auto power down of DLL enabled, + * TXC/RXC disabled during auto power down. + */ + val &= ~BCM54XX_SHD_SCR3_DLLAPD_DIS; + val |= BIT(8); + + ret = bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val); + if (ret < 0) + return ret; + + return bcm_phy_enable_apd(phydev, true); +} + +static int bcm7xxx_16nm_ephy_resume(struct phy_device *phydev) +{ + int ret; + + /* Re-apply workarounds coming out suspend/resume */ + ret = bcm7xxx_16nm_ephy_config_init(phydev); + if (ret) + return ret; + + return genphy_config_aneg(phydev); +} + static int bcm7xxx_28nm_ephy_resume(struct phy_device *phydev) { int ret; @@ -610,9 +794,25 @@ static void bcm7xxx_28nm_remove(struct phy_device *phydev) .resume = bcm7xxx_config_init, \ } +#define BCM7XXX_16NM_EPHY(_oui, _name) \ +{ \ + .phy_id = (_oui), \ + .phy_id_mask = 0xfffffff0, \ + .name = _name, \ + /* PHY_BASIC_FEATURES */ \ + .flags = PHY_IS_INTERNAL, \ + .probe = bcm7xxx_28nm_probe, \ + .remove = bcm7xxx_28nm_remove, \ + .config_init = bcm7xxx_16nm_ephy_config_init, \ + .config_aneg = genphy_config_aneg, \ + .read_status = genphy_read_status, \ + .resume = bcm7xxx_16nm_ephy_resume, \ +} + static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_28NM_EPHY(PHY_ID_BCM72113, "Broadcom BCM72113"), BCM7XXX_28NM_EPHY(PHY_ID_BCM72116, "Broadcom BCM72116"), + BCM7XXX_16NM_EPHY(PHY_ID_BCM72165, "Broadcom BCM72165"), BCM7XXX_28NM_GPHY(PHY_ID_BCM7250, "Broadcom BCM7250"), BCM7XXX_28NM_EPHY(PHY_ID_BCM7255, "Broadcom BCM7255"), BCM7XXX_28NM_EPHY(PHY_ID_BCM7260, "Broadcom BCM7260"), @@ -635,6 +835,7 @@ static struct phy_driver bcm7xxx_driver[] = { static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM72113, 0xfffffff0 }, { PHY_ID_BCM72116, 0xfffffff0, }, + { PHY_ID_BCM72165, 0xfffffff0, }, { PHY_ID_BCM7250, 0xfffffff0, }, { PHY_ID_BCM7255, 0xfffffff0, }, { PHY_ID_BCM7260, 0xfffffff0, }, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 3308cebe1c19..07e1dfadbbdf 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -32,6 +32,7 @@ #define PHY_ID_BCM72113 0x35905310 #define PHY_ID_BCM72116 0x35905350 +#define PHY_ID_BCM72165 0x35905340 #define PHY_ID_BCM7250 0xae025280 #define PHY_ID_BCM7255 0xae025120 #define PHY_ID_BCM7260 0xae025190 -- cgit v1.2.3 From 335ff4990cf3bfa42d8846f9b3d8c09456f51801 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:03 -0700 Subject: bpf: Merge printk and seq_printf VARARG max macros MAX_SNPRINTF_VARARGS and MAX_SEQ_PRINTF_VARARGS are used by bpf helpers bpf_snprintf and bpf_seq_printf to limit their varargs. Both call into bpf_bprintf_prepare for print formatting logic and have convenience macros in libbpf (BPF_SNPRINTF, BPF_SEQ_PRINTF) which use the same helper macros to convert varargs to a byte array. Changing shared functionality to support more varargs for either bpf helper would affect the other as well, so let's combine the _VARARGS macros to make this more obvious. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-2-davemarchevsky@fb.com --- include/linux/bpf.h | 2 ++ kernel/bpf/helpers.c | 4 +--- kernel/trace/bpf_trace.c | 4 +--- 3 files changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f4c16f19f83e..be8d57e6e78a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2216,6 +2216,8 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); +#define MAX_BPRINTF_VARARGS 12 + int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 **bin_buf, u32 num_args); void bpf_bprintf_cleanup(void); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9aabf84afd4b..8f9f392c1322 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -979,15 +979,13 @@ out: return err; } -#define MAX_SNPRINTF_VARARGS 12 - BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt, const void *, data, u32, data_len) { int err, num_args; u32 *bin_args; - if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 || + if (data_len % 8 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !data)) return -EINVAL; num_args = data_len / 8; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 067e88c3d2ee..4ec779fa0c1d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -414,15 +414,13 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) return &bpf_trace_printk_proto; } -#define MAX_SEQ_PRINTF_VARARGS 12 - BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) { int err, num_args; u32 *bin_args; - if (data_len & 7 || data_len > MAX_SEQ_PRINTF_VARARGS * 8 || + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || (data_len && !data)) return -EINVAL; num_args = data_len / 8; -- cgit v1.2.3 From 10aceb629e198429c849d5e995c3bb1ba7a9aaa3 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:05 -0700 Subject: bpf: Add bpf_trace_vprintk helper This helper is meant to be "bpf_trace_printk, but with proper vararg support". Follow bpf_snprintf's example and take a u64 pseudo-vararg array. Write to /sys/kernel/debug/tracing/trace_pipe using the same mechanism as bpf_trace_printk. The functionality of this helper was requested in the libbpf issue tracker [0]. [0] Closes: https://github.com/libbpf/libbpf/issues/315 Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-4-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++ kernel/bpf/core.c | 5 ++++ kernel/bpf/helpers.c | 2 ++ kernel/trace/bpf_trace.c | 52 +++++++++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 11 +++++++++ 6 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be8d57e6e78a..b6c45a6cbbba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1088,6 +1088,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..6fddc13fe67f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2357,6 +2357,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8f9f392c1322..2c604ff8c7fb 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1435,6 +1435,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return NULL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4ec779fa0c1d..6b3153841a33 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -398,7 +398,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .arg2_type = ARG_CONST_SIZE, }; -const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +static void __set_printk_clr_event(void) { /* * This program might be calling bpf_trace_printk, @@ -410,10 +410,58 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); +} +const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +{ + __set_printk_clr_event(); return &bpf_trace_printk_proto; } +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, + u32, data_len) +{ + static char buf[BPF_TRACE_PRINTK_SIZE]; + unsigned long flags; + int ret, num_args; + u32 *bin_args; + + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || + (data_len && !data)) + return -EINVAL; + num_args = data_len / 8; + + ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + if (ret < 0) + return ret; + + raw_spin_lock_irqsave(&trace_printk_lock, flags); + ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + + trace_bpf_trace_printk(buf); + raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + + bpf_bprintf_cleanup(); + + return ret; +} + +static const struct bpf_func_proto bpf_trace_vprintk_proto = { + .func = bpf_trace_vprintk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) +{ + __set_printk_clr_event(); + return &bpf_trace_vprintk_proto; +} + BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) { @@ -1160,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 55c42fa7fa331f98062c32799456420930b8bf8c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:19 -0700 Subject: mptcp: add MPTCP_INFO getsockopt Its not compatible with multipath-tcp.org kernel one. 1. The out-of-tree implementation defines a different 'struct mptcp_info', with embedded __user addresses for additional data such as endpoint addresses. 2. Mat Martineau points out that embedded __user addresses doesn't work with BPF_CGROUP_RUN_PROG_GETSOCKOPT() which assumes that copying in optsize bytes from optval provides all data that got copied to userspace. This provides mptcp_info data for the given mptcp socket. Userspace sets optlen to the size of the structure it expects. The kernel updates it to contain the number of bytes that it copied. This allows to append more information to the structure later. Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/uapi/linux/mptcp.h | 3 +++ net/mptcp/sockopt.c | 40 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 041d6032a348..7612d760b6a9 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -364,6 +364,7 @@ struct ucred { #define SOL_KCM 281 #define SOL_TLS 282 #define SOL_XDP 283 +#define SOL_MPTCP 284 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index f66038b9551f..3e9caeddda7e 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -193,4 +193,7 @@ enum mptcp_event_attr { #define MPTCP_RST_EBADPERF 5 #define MPTCP_RST_EMIDDLEBOX 6 +/* MPTCP socket options */ +#define MPTCP_INFO 1 + #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 54f0d521a399..f7683c22911f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -673,10 +673,14 @@ out: void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) { struct sock *sk = &msk->sk.icsk_inet.sk; - bool slow = lock_sock_fast(sk); u32 flags = 0; + bool slow; u8 val; + memset(info, 0, sizeof(*info)); + + slow = lock_sock_fast(sk); + info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); @@ -702,6 +706,27 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); +static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen) +{ + struct mptcp_info m_info; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(struct mptcp_info)); + + mptcp_diag_fill_info(msk, &m_info); + + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &m_info, len)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -716,6 +741,17 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return -EOPNOTSUPP; } +static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, + char __user *optval, int __user *optlen) +{ + switch (optname) { + case MPTCP_INFO: + return mptcp_getsockopt_info(msk, optval, optlen); + } + + return -EOPNOTSUPP; +} + int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { @@ -738,6 +774,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, if (level == SOL_TCP) return mptcp_getsockopt_sol_tcp(msk, optname, optval, option); + if (level == SOL_MPTCP) + return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option); return -EOPNOTSUPP; } -- cgit v1.2.3 From 5bd2182d58e9d9c6279b7a8a2f9b41add0e7f9cb Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 16 Feb 2021 19:46:48 -0500 Subject: audit,io_uring,io-wq: add some basic audit support to io_uring This patch adds basic auditing to io_uring operations, regardless of their context. This is accomplished by allocating audit_context structures for the io-wq worker and io_uring SQPOLL kernel threads as well as explicitly auditing the io_uring operations in io_issue_sqe(). Individual io_uring operations can bypass auditing through the "audit_skip" field in the struct io_op_def definition for the operation; although great care must be taken so that security relevant io_uring operations do not bypass auditing; please contact the audit mailing list (see the MAINTAINERS file) with any questions. The io_uring operations are audited using a new AUDIT_URINGOP record, an example is shown below: type=UNKNOWN[1336] msg=audit(1631800225.981:37289): uring_op=19 success=yes exit=0 items=0 ppid=15454 pid=15681 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) Thanks to Richard Guy Briggs for review and feedback. Signed-off-by: Paul Moore --- fs/io-wq.c | 4 ++ fs/io_uring.c | 55 +++++++++++++-- include/linux/audit.h | 26 +++++++ include/uapi/linux/audit.h | 1 + kernel/audit.h | 2 + kernel/auditsc.c | 166 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 248 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/io-wq.c b/fs/io-wq.c index 6c55362c1f99..dac5c5961c9d 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "io-wq.h" @@ -562,6 +563,8 @@ static int io_wqe_worker(void *data) snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); + audit_alloc_kernel(current); + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { long ret; @@ -601,6 +604,7 @@ loop: io_worker_handle_work(worker); } + audit_free(current); io_worker_exit(worker); return 0; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 16fb7436043c..388754b24785 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -79,6 +79,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -917,6 +918,8 @@ struct io_op_def { unsigned needs_async_setup : 1; /* should block plug */ unsigned plug : 1; + /* skip auditing */ + unsigned audit_skip : 1; /* size of async data needed, if any */ unsigned short async_size; }; @@ -930,6 +933,7 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .needs_async_setup = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITEV] = { @@ -939,16 +943,19 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .needs_async_setup = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FSYNC] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE_FIXED] = { @@ -957,15 +964,20 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_POLL_ADD] = { .needs_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, + }, + [IORING_OP_POLL_REMOVE] = { + .audit_skip = 1, }, - [IORING_OP_POLL_REMOVE] = {}, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_SENDMSG] = { .needs_file = 1, @@ -983,18 +995,23 @@ static const struct io_op_def io_op_defs[] = { .async_size = sizeof(struct io_async_msghdr), }, [IORING_OP_TIMEOUT] = { + .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_TIMEOUT_REMOVE] = { /* used by timeout updates' prep() */ + .audit_skip = 1, }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, }, - [IORING_OP_ASYNC_CANCEL] = {}, + [IORING_OP_ASYNC_CANCEL] = { + .audit_skip = 1, + }, [IORING_OP_LINK_TIMEOUT] = { + .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_CONNECT] = { @@ -1009,14 +1026,19 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_OPENAT] = {}, [IORING_OP_CLOSE] = {}, - [IORING_OP_FILES_UPDATE] = {}, - [IORING_OP_STATX] = {}, + [IORING_OP_FILES_UPDATE] = { + .audit_skip = 1, + }, + [IORING_OP_STATX] = { + .audit_skip = 1, + }, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE] = { @@ -1025,39 +1047,50 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FADVISE] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_MADVISE] = {}, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .audit_skip = 1, }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, + .audit_skip = 1, }, [IORING_OP_OPENAT2] = { }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, + .audit_skip = 1, }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, + }, + [IORING_OP_PROVIDE_BUFFERS] = { + .audit_skip = 1, + }, + [IORING_OP_REMOVE_BUFFERS] = { + .audit_skip = 1, }, - [IORING_OP_PROVIDE_BUFFERS] = {}, - [IORING_OP_REMOVE_BUFFERS] = {}, [IORING_OP_TEE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, }, [IORING_OP_SHUTDOWN] = { .needs_file = 1, @@ -6591,6 +6624,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) creds = override_creds(req->creds); + if (!io_op_defs[req->opcode].audit_skip) + audit_uring_entry(req->opcode); + switch (req->opcode) { case IORING_OP_NOP: ret = io_nop(req, issue_flags); @@ -6706,6 +6742,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) break; } + if (!io_op_defs[req->opcode].audit_skip) + audit_uring_exit(!ret, ret); + if (creds) revert_creds(creds); if (ret) @@ -7360,6 +7399,8 @@ static int io_sq_thread(void *data) set_cpus_allowed_ptr(current, cpu_online_mask); current->flags |= PF_NO_SETAFFINITY; + audit_alloc_kernel(current); + mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; @@ -7425,6 +7466,8 @@ static int io_sq_thread(void *data) io_run_task_work(); mutex_unlock(&sqd->lock); + audit_free(current); + complete(&sqd->exited); do_exit(0); } diff --git a/include/linux/audit.h b/include/linux/audit.h index 82b7c1116a85..d656a06dd909 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -286,7 +286,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t) /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); +extern int audit_alloc_kernel(struct task_struct *task); extern void __audit_free(struct task_struct *task); +extern void __audit_uring_entry(u8 op); +extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); @@ -323,6 +326,21 @@ static inline void audit_free(struct task_struct *task) if (unlikely(task->audit_context)) __audit_free(task); } +static inline void audit_uring_entry(u8 op) +{ + /* + * We intentionally check audit_context() before audit_enabled as most + * Linux systems (as of ~2021) rely on systemd which forces audit to + * be enabled regardless of the user's audit configuration. + */ + if (unlikely(audit_context() && audit_enabled)) + __audit_uring_entry(op); +} +static inline void audit_uring_exit(int success, long code) +{ + if (unlikely(!audit_dummy_context())) + __audit_uring_exit(success, code); +} static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) @@ -554,8 +572,16 @@ static inline int audit_alloc(struct task_struct *task) { return 0; } +static inline int audit_alloc_kernel(struct task_struct *task) +{ + return 0; +} static inline void audit_free(struct task_struct *task) { } +static inline void audit_uring_entry(u8 op) +{ } +static inline void audit_uring_exit(int success, long code) +{ } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..a1997697c8b1 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,7 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_URINGOP 1336 /* io_uring operation */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.h b/kernel/audit.h index 13abc48de0bd..d1161e3b83e2 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -103,10 +103,12 @@ struct audit_context { enum { AUDIT_CTX_UNUSED, /* audit_context is currently unused */ AUDIT_CTX_SYSCALL, /* in use by syscall */ + AUDIT_CTX_URING, /* in use by io_uring */ } context; enum audit_state state, current_state; unsigned int serial; /* serial number for record */ int major; /* syscall number */ + int uring_op; /* uring operation */ struct timespec64 ctime; /* time of syscall entry */ unsigned long argv[4]; /* syscall arguments */ long return_code;/* syscall return code */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f3d309b05c2d..6dda448fb826 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -959,6 +959,7 @@ static void audit_reset_context(struct audit_context *ctx) ctx->current_state = ctx->state; ctx->serial = 0; ctx->major = 0; + ctx->uring_op = 0; ctx->ctime = (struct timespec64){ .tv_sec = 0, .tv_nsec = 0 }; memset(ctx->argv, 0, sizeof(ctx->argv)); ctx->return_code = 0; @@ -1044,6 +1045,31 @@ int audit_alloc(struct task_struct *tsk) return 0; } +/** + * audit_alloc_kernel - allocate an audit_context for a kernel task + * @tsk: the kernel task + * + * Similar to the audit_alloc() function, but intended for kernel private + * threads. Returns zero on success, negative values on failure. + */ +int audit_alloc_kernel(struct task_struct *tsk) +{ + /* + * At the moment we are just going to call into audit_alloc() to + * simplify the code, but there two things to keep in mind with this + * approach: + * + * 1. Filtering internal kernel tasks is a bit laughable in almost all + * cases, but there is at least one case where there is a benefit: + * the '-a task,never' case allows the admin to effectively disable + * task auditing at runtime. + * + * 2. The {set,clear}_task_syscall_work() ops likely have zero effect + * on these internal kernel tasks, but they probably don't hurt either. + */ + return audit_alloc(tsk); +} + static inline void audit_free_context(struct audit_context *context) { /* resetting is extra work, but it is likely just noise */ @@ -1546,6 +1572,44 @@ out: audit_log_end(ab); } +/** + * audit_log_uring - generate a AUDIT_URINGOP record + * @ctx: the audit context + */ +static void audit_log_uring(struct audit_context *ctx) +{ + struct audit_buffer *ab; + const struct cred *cred; + + ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_URINGOP); + if (!ab) + return; + cred = current_cred(); + audit_log_format(ab, "uring_op=%d", ctx->uring_op); + if (ctx->return_valid != AUDITSC_INVALID) + audit_log_format(ab, " success=%s exit=%ld", + (ctx->return_valid == AUDITSC_SUCCESS ? + "yes" : "no"), + ctx->return_code); + audit_log_format(ab, + " items=%d" + " ppid=%d pid=%d uid=%u gid=%u euid=%u suid=%u" + " fsuid=%u egid=%u sgid=%u fsgid=%u", + ctx->name_count, + task_ppid_nr(current), task_tgid_nr(current), + from_kuid(&init_user_ns, cred->uid), + from_kgid(&init_user_ns, cred->gid), + from_kuid(&init_user_ns, cred->euid), + from_kuid(&init_user_ns, cred->suid), + from_kuid(&init_user_ns, cred->fsuid), + from_kgid(&init_user_ns, cred->egid), + from_kgid(&init_user_ns, cred->sgid), + from_kgid(&init_user_ns, cred->fsgid)); + audit_log_task_context(ab); + audit_log_key(ab, ctx->filterkey); + audit_log_end(ab); +} + static void audit_log_exit(void) { int i, call_panic = 0; @@ -1581,6 +1645,9 @@ static void audit_log_exit(void) audit_log_key(ab, context->filterkey); audit_log_end(ab); break; + case AUDIT_CTX_URING: + audit_log_uring(context); + break; default: BUG(); break; @@ -1751,6 +1818,105 @@ static void audit_return_fixup(struct audit_context *ctx, ctx->return_valid = (success ? AUDITSC_SUCCESS : AUDITSC_FAILURE); } +/** + * __audit_uring_entry - prepare the kernel task's audit context for io_uring + * @op: the io_uring opcode + * + * This is similar to audit_syscall_entry() but is intended for use by io_uring + * operations. This function should only ever be called from + * audit_uring_entry() as we rely on the audit context checking present in that + * function. + */ +void __audit_uring_entry(u8 op) +{ + struct audit_context *ctx = audit_context(); + + if (ctx->state == AUDIT_STATE_DISABLED) + return; + + /* + * NOTE: It's possible that we can be called from the process' context + * before it returns to userspace, and before audit_syscall_exit() + * is called. In this case there is not much to do, just record + * the io_uring details and return. + */ + ctx->uring_op = op; + if (ctx->context == AUDIT_CTX_SYSCALL) + return; + + ctx->dummy = !audit_n_rules; + if (!ctx->dummy && ctx->state == AUDIT_STATE_BUILD) + ctx->prio = 0; + + ctx->context = AUDIT_CTX_URING; + ctx->current_state = ctx->state; + ktime_get_coarse_real_ts64(&ctx->ctime); +} + +/** + * __audit_uring_exit - wrap up the kernel task's audit context after io_uring + * @success: true/false value to indicate if the operation succeeded or not + * @code: operation return code + * + * This is similar to audit_syscall_exit() but is intended for use by io_uring + * operations. This function should only ever be called from + * audit_uring_exit() as we rely on the audit context checking present in that + * function. + */ +void __audit_uring_exit(int success, long code) +{ + struct audit_context *ctx = audit_context(); + + /* + * TODO: At some point we will likely want to filter on io_uring ops + * and other things similar to what we do for syscalls, but that + * is something for another day; just record what we can here. + */ + + if (ctx->context == AUDIT_CTX_SYSCALL) { + /* + * NOTE: See the note in __audit_uring_entry() about the case + * where we may be called from process context before we + * return to userspace via audit_syscall_exit(). In this + * case we simply emit a URINGOP record and bail, the + * normal syscall exit handling will take care of + * everything else. + * It is also worth mentioning that when we are called, + * the current process creds may differ from the creds + * used during the normal syscall processing; keep that + * in mind if/when we move the record generation code. + */ + + /* + * We need to filter on the syscall info here to decide if we + * should emit a URINGOP record. I know it seems odd but this + * solves the problem where users have a filter to block *all* + * syscall records in the "exit" filter; we want to preserve + * the behavior here. + */ + audit_filter_syscall(current, ctx); + audit_filter_inodes(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + return; + + audit_log_uring(ctx); + return; + } + + /* this may generate CONFIG_CHANGE records */ + if (!list_empty(&ctx->killed_trees)) + audit_kill_trees(ctx); + + audit_filter_inodes(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + goto out; + audit_return_fixup(ctx, success, code); + audit_log_exit(); + +out: + audit_reset_context(ctx); +} + /** * __audit_syscall_entry - fill in an audit record at syscall entry * @major: major syscall type (function) -- cgit v1.2.3 From 3a862cacf8670729b1ad8fc28e4f7e078f9c570c Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Mon, 1 Feb 2021 19:22:44 -0500 Subject: fs: add anon_inode_getfile_secure() similar to anon_inode_getfd_secure() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extending the secure anonymous inode support to other subsystems requires that we have a secure anon_inode_getfile() variant in addition to the existing secure anon_inode_getfd() variant. Thankfully we can reuse the existing __anon_inode_getfile() function and just wrap it with the proper arguments. Acked-by: Mickaël Salaün Signed-off-by: Paul Moore --- fs/anon_inodes.c | 29 +++++++++++++++++++++++++++++ include/linux/anon_inodes.h | 4 ++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index a280156138ed..e0c3e33c4177 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -148,6 +148,35 @@ struct file *anon_inode_getfile(const char *name, } EXPORT_SYMBOL_GPL(anon_inode_getfile); +/** + * anon_inode_getfile_secure - Like anon_inode_getfile(), but creates a new + * !S_PRIVATE anon inode rather than reuse the + * singleton anon inode and calls the + * inode_init_security_anon() LSM hook. This + * allows for both the inode to have its own + * security context and for the LSM to enforce + * policy on the inode's creation. + * + * @name: [in] name of the "class" of the new file + * @fops: [in] file operations for the new file + * @priv: [in] private data for the new file (will be file's private_data) + * @flags: [in] flags + * @context_inode: + * [in] the logical relationship with the new inode (optional) + * + * The LSM may use @context_inode in inode_init_security_anon(), but a + * reference to it is not held. Returns the newly created file* or an error + * pointer. See the anon_inode_getfile() documentation for more information. + */ +struct file *anon_inode_getfile_secure(const char *name, + const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode) +{ + return __anon_inode_getfile(name, fops, priv, flags, + context_inode, true); +} + static int __anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags, diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h index 71881a2b6f78..5deaddbd7927 100644 --- a/include/linux/anon_inodes.h +++ b/include/linux/anon_inodes.h @@ -15,6 +15,10 @@ struct inode; struct file *anon_inode_getfile(const char *name, const struct file_operations *fops, void *priv, int flags); +struct file *anon_inode_getfile_secure(const char *name, + const struct file_operations *fops, + void *priv, int flags, + const struct inode *context_inode); int anon_inode_getfd(const char *name, const struct file_operations *fops, void *priv, int flags); int anon_inode_getfd_secure(const char *name, -- cgit v1.2.3 From cdc1404a40461faba23c5a5ad40adcc7eecc1580 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Mon, 1 Feb 2021 19:56:49 -0500 Subject: lsm,io_uring: add LSM hooks to io_uring A full expalantion of io_uring is beyond the scope of this commit description, but in summary it is an asynchronous I/O mechanism which allows for I/O requests and the resulting data to be queued in memory mapped "rings" which are shared between the kernel and userspace. Optionally, io_uring offers the ability for applications to spawn kernel threads to dequeue I/O requests from the ring and submit the requests in the kernel, helping to minimize the syscall overhead. Rings are accessed in userspace by memory mapping a file descriptor provided by the io_uring_setup(2), and can be shared between applications as one might do with any open file descriptor. Finally, process credentials can be registered with a given ring and any process with access to that ring can submit I/O requests using any of the registered credentials. While the io_uring functionality is widely recognized as offering a vastly improved, and high performing asynchronous I/O mechanism, its ability to allow processes to submit I/O requests with credentials other than its own presents a challenge to LSMs. When a process creates a new io_uring ring the ring's credentials are inhertied from the calling process; if this ring is shared with another process operating with different credentials there is the potential to bypass the LSMs security policy. Similarly, registering credentials with a given ring allows any process with access to that ring to submit I/O requests with those credentials. In an effort to allow LSMs to apply security policy to io_uring I/O operations, this patch adds two new LSM hooks. These hooks, in conjunction with the LSM anonymous inode support previously submitted, allow an LSM to apply access control policy to the sharing of io_uring rings as well as any io_uring credential changes requested by a process. The new LSM hooks are described below: * int security_uring_override_creds(cred) Controls if the current task, executing an io_uring operation, is allowed to override it's credentials with @cred. In cases where the current task is a user application, the current credentials will be those of the user application. In cases where the current task is a kernel thread servicing io_uring requests the current credentials will be those of the io_uring ring (inherited from the process that created the ring). * int security_uring_sqpoll(void) Controls if the current task is allowed to create an io_uring polling thread (IORING_SETUP_SQPOLL). Without a SQPOLL thread in the kernel processes must submit I/O requests via io_uring_enter(2) which allows us to compare any requested credential changes against the application making the request. With a SQPOLL thread, we can no longer compare requested credential changes against the application making the request, the comparison is made against the ring's credentials. Signed-off-by: Paul Moore --- fs/io_uring.c | 10 ++++++++++ include/linux/lsm_hook_defs.h | 5 +++++ include/linux/lsm_hooks.h | 13 +++++++++++++ include/linux/security.h | 16 ++++++++++++++++ security/security.c | 12 ++++++++++++ 5 files changed, 56 insertions(+) (limited to 'include/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 56cc9aba0d01..f89d00af3a67 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -80,6 +80,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -7070,6 +7071,11 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (!req->creds) return -EINVAL; get_cred(req->creds); + ret = security_uring_override_creds(req->creds); + if (ret) { + put_cred(req->creds); + return ret; + } req->flags |= REQ_F_CREDS; } state = &ctx->submit_state; @@ -8566,6 +8572,10 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx, struct io_sq_data *sqd; bool attached; + ret = security_uring_sqpoll(); + if (ret) + return ret; + sqd = io_get_sq_data(p, &attached); if (IS_ERR(sqd)) { ret = PTR_ERR(sqd); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 2adeea44c0d5..b3c525353769 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -402,3 +402,8 @@ LSM_HOOK(void, LSM_RET_VOID, perf_event_free, struct perf_event *event) LSM_HOOK(int, 0, perf_event_read, struct perf_event *event) LSM_HOOK(int, 0, perf_event_write, struct perf_event *event) #endif /* CONFIG_PERF_EVENTS */ + +#ifdef CONFIG_IO_URING +LSM_HOOK(int, 0, uring_override_creds, const struct cred *new) +LSM_HOOK(int, 0, uring_sqpoll, void) +#endif /* CONFIG_IO_URING */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 5c4c5c0602cb..0eb0ae95c4c4 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1557,6 +1557,19 @@ * Read perf_event security info if allowed. * @perf_event_write: * Write perf_event security info if allowed. + * + * Security hooks for io_uring + * + * @uring_override_creds: + * Check if the current task, executing an io_uring operation, is allowed + * to override it's credentials with @new. + * + * @new: the new creds to use + * + * @uring_sqpoll: + * Check whether the current task is allowed to spawn a io_uring polling + * thread (IORING_SETUP_SQPOLL). + * */ union security_list_options { #define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__); diff --git a/include/linux/security.h b/include/linux/security.h index 5b7288521300..7979b9629a42 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2038,4 +2038,20 @@ static inline int security_perf_event_write(struct perf_event *event) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_PERF_EVENTS */ +#ifdef CONFIG_IO_URING +#ifdef CONFIG_SECURITY +extern int security_uring_override_creds(const struct cred *new); +extern int security_uring_sqpoll(void); +#else +static inline int security_uring_override_creds(const struct cred *new) +{ + return 0; +} +static inline int security_uring_sqpoll(void) +{ + return 0; +} +#endif /* CONFIG_SECURITY */ +#endif /* CONFIG_IO_URING */ + #endif /* ! __LINUX_SECURITY_H */ diff --git a/security/security.c b/security/security.c index 9ffa9e9c5c55..c49a2c0cc1c1 100644 --- a/security/security.c +++ b/security/security.c @@ -2625,3 +2625,15 @@ int security_perf_event_write(struct perf_event *event) return call_int_hook(perf_event_write, 0, event); } #endif /* CONFIG_PERF_EVENTS */ + +#ifdef CONFIG_IO_URING +int security_uring_override_creds(const struct cred *new) +{ + return call_int_hook(uring_override_creds, 0, new); +} + +int security_uring_sqpoll(void) +{ + return call_int_hook(uring_sqpoll, 0); +} +#endif /* CONFIG_IO_URING */ -- cgit v1.2.3 From f279294b329363eb6ada568e494d609ef78e3e8e Mon Sep 17 00:00:00 2001 From: Chunguang Xu Date: Fri, 17 Sep 2021 20:44:14 +0800 Subject: misc_cgroup: introduce misc.events to count failures MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce misc.events to make it easier for us to understand the pressure of resources. Currently only the 'max' event is implemented, which indicates the times the resource is about to exceeds the max limit. Signed-off-by: Chunguang Xu Reviewed-by: Vipin Sharma Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo --- include/linux/misc_cgroup.h | 5 +++++ kernel/cgroup/misc.c | 24 ++++++++++++++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index da2367e2ac1e..091f2d2a1aec 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -36,6 +36,7 @@ struct misc_cg; struct misc_res { unsigned long max; atomic_long_t usage; + atomic_long_t events; bool failed; }; @@ -46,6 +47,10 @@ struct misc_res { */ struct misc_cg { struct cgroup_subsys_state css; + + /* misc.events */ + struct cgroup_file events_file; + struct misc_res res[MISC_CG_RES_TYPES]; }; diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c index ec02d963cad1..4b2b49267384 100644 --- a/kernel/cgroup/misc.c +++ b/kernel/cgroup/misc.c @@ -171,6 +171,11 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, return 0; err_charge: + for (j = i; j; j = parent_misc(j)) { + atomic_long_inc(&j->res[type].events); + cgroup_file_notify(&j->events_file); + } + for (j = cg; j != i; j = parent_misc(j)) misc_cg_cancel_charge(type, j, amount); misc_cg_cancel_charge(type, i, amount); @@ -335,6 +340,19 @@ static int misc_cg_capacity_show(struct seq_file *sf, void *v) return 0; } +static int misc_events_show(struct seq_file *sf, void *v) +{ + struct misc_cg *cg = css_misc(seq_css(sf)); + unsigned long events, i; + + for (i = 0; i < MISC_CG_RES_TYPES; i++) { + events = atomic_long_read(&cg->res[i].events); + if (READ_ONCE(misc_res_capacity[i]) || events) + seq_printf(sf, "%s.max %lu\n", misc_res_name[i], events); + } + return 0; +} + /* Misc cgroup interface files */ static struct cftype misc_cg_files[] = { { @@ -353,6 +371,12 @@ static struct cftype misc_cg_files[] = { .seq_show = misc_cg_capacity_show, .flags = CFTYPE_ONLY_ON_ROOT, }, + { + .name = "events", + .flags = CFTYPE_NOT_ON_ROOT, + .file_offset = offsetof(struct misc_cg, events_file), + .seq_show = misc_events_show, + }, {} }; -- cgit v1.2.3 From b03357528fd9516600ff358ab5d4b887b8cb80e8 Mon Sep 17 00:00:00 2001 From: Chunguang Xu Date: Fri, 17 Sep 2021 20:44:15 +0800 Subject: misc_cgroup: remove error log to avoid log flood MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In scenarios where containers are frequently created and deleted, a large number of error logs maybe generated. The logs only show which node is about to go over the max limit, not the node which resource request failed. As misc.events has provided relevant information, maybe we can remove this log. Signed-off-by: Chunguang Xu Reviewed-by: Michal Koutný Signed-off-by: Tejun Heo --- include/linux/misc_cgroup.h | 1 - kernel/cgroup/misc.c | 7 ------- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index 091f2d2a1aec..c238207d1615 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -37,7 +37,6 @@ struct misc_res { unsigned long max; atomic_long_t usage; atomic_long_t events; - bool failed; }; /** diff --git a/kernel/cgroup/misc.c b/kernel/cgroup/misc.c index 4b2b49267384..fe3e8a0eb7ed 100644 --- a/kernel/cgroup/misc.c +++ b/kernel/cgroup/misc.c @@ -157,13 +157,6 @@ int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, new_usage = atomic_long_add_return(amount, &res->usage); if (new_usage > READ_ONCE(res->max) || new_usage > READ_ONCE(misc_res_capacity[type])) { - if (!res->failed) { - pr_info("cgroup: charge rejected by the misc controller for %s resource in ", - misc_res_name[type]); - pr_cont_cgroup_path(i->css.cgroup); - pr_cont("\n"); - res->failed = true; - } ret = -EBUSY; goto err_charge; } -- cgit v1.2.3 From 4373b3dc922038e8924f648506f6556f2afa7e77 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 9 Sep 2021 11:45:13 -0700 Subject: fscrypt: remove fscrypt_operations::max_namelen The max_namelen field is unnecessary, as it is set to 255 (NAME_MAX) on all filesystems that support fscrypt (or plan to support fscrypt). For simplicity, just use NAME_MAX directly instead. Link: https://lore.kernel.org/r/20210909184513.139281-1-ebiggers@kernel.org Signed-off-by: Eric Biggers --- fs/crypto/fname.c | 3 +-- fs/ext4/super.c | 1 - fs/f2fs/super.c | 1 - fs/ubifs/crypto.c | 1 - include/linux/fscrypt.h | 3 --- 5 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index eb538c28df94..a9be4bc74a94 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -429,8 +429,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, if (fscrypt_has_encryption_key(dir)) { if (!fscrypt_fname_encrypted_size(&dir->i_crypt_info->ci_policy, - iname->len, - dir->i_sb->s_cop->max_namelen, + iname->len, NAME_MAX, &fname->crypto_buf.len)) return -ENAMETOOLONG; fname->crypto_buf.name = kmalloc(fname->crypto_buf.len, diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0775950ee84e..f37e64f72b5d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1566,7 +1566,6 @@ static const struct fscrypt_operations ext4_cryptops = { .set_context = ext4_set_context, .get_dummy_policy = ext4_get_dummy_policy, .empty_dir = ext4_empty_dir, - .max_namelen = EXT4_NAME_LEN, .has_stable_inodes = ext4_has_stable_inodes, .get_ino_and_lblk_bits = ext4_get_ino_and_lblk_bits, }; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 78ebc306ee2b..cf049a042482 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -2976,7 +2976,6 @@ static const struct fscrypt_operations f2fs_cryptops = { .set_context = f2fs_set_context, .get_dummy_policy = f2fs_get_dummy_policy, .empty_dir = f2fs_empty_dir, - .max_namelen = F2FS_NAME_LEN, .has_stable_inodes = f2fs_has_stable_inodes, .get_ino_and_lblk_bits = f2fs_get_ino_and_lblk_bits, .get_num_devices = f2fs_get_num_devices, diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c index 22be7aeb96c4..c57b46a352d8 100644 --- a/fs/ubifs/crypto.c +++ b/fs/ubifs/crypto.c @@ -82,5 +82,4 @@ const struct fscrypt_operations ubifs_crypt_operations = { .get_context = ubifs_crypt_get_context, .set_context = ubifs_crypt_set_context, .empty_dir = ubifs_crypt_empty_dir, - .max_namelen = UBIFS_MAX_NLEN, }; diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h index e912ed9141d9..91ea9477e9bd 100644 --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -118,9 +118,6 @@ struct fscrypt_operations { */ bool (*empty_dir)(struct inode *inode); - /* The filesystem's maximum ciphertext filename length, in bytes */ - unsigned int max_namelen; - /* * Check whether the filesystem's inode numbers and UUID are stable, * meaning that they will never be changed even by offline operations -- cgit v1.2.3 From 9d881361206ebcf6285c2ec2ef275aff80875347 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 21 Sep 2021 12:42:25 +0300 Subject: bus: ti-sysc: Add quirk handling for reinit on context lost Some interconnect target modules such as otg and gpmc on am335x need a re-init after resume. As we also have PM runtime cases where the context may be lost, let's handle these all with cpu_pm. For the am335x resume path, we already have cpu_pm_resume() call cpu_pm_cluster_exit(). Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 108 ++++++++++++++++++++++++++++++++-- include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 103 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 9e958343a719..a73c707d14c3 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -52,11 +53,18 @@ struct sysc_address { struct list_head node; }; +struct sysc_module { + struct sysc *ddata; + struct list_head node; +}; + struct sysc_soc_info { unsigned long general_purpose:1; enum sysc_soc soc; - struct mutex list_lock; /* disabled modules list lock */ + struct mutex list_lock; /* disabled and restored modules list lock */ struct list_head disabled_modules; + struct list_head restored_modules; + struct notifier_block nb; }; enum sysc_clocks { @@ -2477,6 +2485,79 @@ static struct dev_pm_domain sysc_child_pm_domain = { } }; +/* Caller needs to take list_lock if ever used outside of cpu_pm */ +static void sysc_reinit_modules(struct sysc_soc_info *soc) +{ + struct sysc_module *module; + struct list_head *pos; + struct sysc *ddata; + int error = 0; + + list_for_each(pos, &sysc_soc->restored_modules) { + module = list_entry(pos, struct sysc_module, node); + ddata = module->ddata; + error = sysc_reinit_module(ddata, ddata->enabled); + } +} + +/** + * sysc_context_notifier - optionally reset and restore module after idle + * @nb: notifier block + * @cmd: unused + * @v: unused + * + * Some interconnect target modules need to be restored, or reset and restored + * on CPU_PM CPU_PM_CLUSTER_EXIT notifier. This is needed at least for am335x + * OTG and GPMC target modules even if the modules are unused. + */ +static int sysc_context_notifier(struct notifier_block *nb, unsigned long cmd, + void *v) +{ + struct sysc_soc_info *soc; + + soc = container_of(nb, struct sysc_soc_info, nb); + + switch (cmd) { + case CPU_CLUSTER_PM_ENTER: + break; + case CPU_CLUSTER_PM_ENTER_FAILED: /* No need to restore context */ + break; + case CPU_CLUSTER_PM_EXIT: + sysc_reinit_modules(soc); + break; + } + + return NOTIFY_OK; +} + +/** + * sysc_add_restored - optionally add reset and restore quirk hanlling + * @ddata: device data + */ +static void sysc_add_restored(struct sysc *ddata) +{ + struct sysc_module *restored_module; + + restored_module = kzalloc(sizeof(*restored_module), GFP_KERNEL); + if (!restored_module) + return; + + restored_module->ddata = ddata; + + mutex_lock(&sysc_soc->list_lock); + + list_add(&restored_module->node, &sysc_soc->restored_modules); + + if (sysc_soc->nb.notifier_call) + goto out_unlock; + + sysc_soc->nb.notifier_call = sysc_context_notifier; + cpu_pm_register_notifier(&sysc_soc->nb); + +out_unlock: + mutex_unlock(&sysc_soc->list_lock); +} + /** * sysc_legacy_idle_quirk - handle children in omap_device compatible way * @ddata: device driver data @@ -2976,12 +3057,14 @@ static int sysc_add_disabled(unsigned long base) } /* - * One time init to detect the booted SoC and disable unavailable features. + * One time init to detect the booted SoC, disable unavailable features + * and initialize list for optional cpu_pm notifier. + * * Note that we initialize static data shared across all ti-sysc instances * so ddata is only used for SoC type. This can be called from module_init * once we no longer need to rely on platform data. */ -static int sysc_init_soc(struct sysc *ddata) +static int sysc_init_static_data(struct sysc *ddata) { const struct soc_device_attribute *match; struct ti_sysc_platform_data *pdata; @@ -2997,6 +3080,7 @@ static int sysc_init_soc(struct sysc *ddata) mutex_init(&sysc_soc->list_lock); INIT_LIST_HEAD(&sysc_soc->disabled_modules); + INIT_LIST_HEAD(&sysc_soc->restored_modules); sysc_soc->general_purpose = true; pdata = dev_get_platdata(ddata->dev); @@ -3060,15 +3144,24 @@ static int sysc_init_soc(struct sysc *ddata) return 0; } -static void sysc_cleanup_soc(void) +static void sysc_cleanup_static_data(void) { + struct sysc_module *restored_module; struct sysc_address *disabled_module; struct list_head *pos, *tmp; if (!sysc_soc) return; + if (sysc_soc->nb.notifier_call) + cpu_pm_unregister_notifier(&sysc_soc->nb); + mutex_lock(&sysc_soc->list_lock); + list_for_each_safe(pos, tmp, &sysc_soc->restored_modules) { + restored_module = list_entry(pos, struct sysc_module, node); + list_del(pos); + kfree(restored_module); + } list_for_each_safe(pos, tmp, &sysc_soc->disabled_modules) { disabled_module = list_entry(pos, struct sysc_address, node); list_del(pos); @@ -3136,7 +3229,7 @@ static int sysc_probe(struct platform_device *pdev) ddata->dev = &pdev->dev; platform_set_drvdata(pdev, ddata); - error = sysc_init_soc(ddata); + error = sysc_init_static_data(ddata); if (error) return error; @@ -3234,6 +3327,9 @@ static int sysc_probe(struct platform_device *pdev) pm_runtime_put(&pdev->dev); } + if (ddata->cfg.quirks & SYSC_QUIRK_REINIT_ON_CTX_LOST) + sysc_add_restored(ddata); + return 0; err: @@ -3315,7 +3411,7 @@ static void __exit sysc_exit(void) { bus_unregister_notifier(&platform_bus_type, &sysc_nb); platform_driver_unregister(&sysc_driver); - sysc_cleanup_soc(); + sysc_cleanup_static_data(); } module_exit(sysc_exit); diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 9837fb011f2f..989aa30c598d 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_REINIT_ON_CTX_LOST BIT(28) #define SYSC_QUIRK_REINIT_ON_RESUME BIT(27) #define SYSC_QUIRK_GPMC_DEBUG BIT(26) #define SYSC_MODULE_QUIRK_ENA_RESETDONE BIT(25) -- cgit v1.2.3 From 6a52bc2b81fa06b7ab98472c7d80644e8e071af6 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 21 Sep 2021 12:42:25 +0300 Subject: bus: ti-sysc: Add quirk handling for reset on re-init At least am335x gpmc module needs a reset in addition to re-init on resume. Let's add a quirk handling for reset on re-init. Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 10 ++++++++++ include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index a73c707d14c3..cacdc4e301fb 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -157,6 +157,7 @@ struct sysc { static void sysc_parse_dts_quirks(struct sysc *ddata, struct device_node *np, bool is_child); +static int sysc_reset(struct sysc *ddata); static void sysc_write(struct sysc *ddata, int offset, u32 value) { @@ -1440,6 +1441,15 @@ static int sysc_reinit_module(struct sysc *ddata, bool leave_enabled) if (error) dev_warn(dev, "reinit resume failed: %i\n", error); + /* Some modules like am335x gpmc need reset and restore of sysconfig */ + if (ddata->cfg.quirks & SYSC_QUIRK_RESET_ON_CTX_LOST) { + error = sysc_reset(ddata); + if (error) + dev_warn(dev, "reinit reset failed: %i\n", error); + + sysc_write_sysconfig(ddata, ddata->sysconfig); + } + if (leave_enabled) return error; diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index 989aa30c598d..f11244f5c0b6 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_QUIRK_RESET_ON_CTX_LOST BIT(29) #define SYSC_QUIRK_REINIT_ON_CTX_LOST BIT(28) #define SYSC_QUIRK_REINIT_ON_RESUME BIT(27) #define SYSC_QUIRK_GPMC_DEBUG BIT(26) -- cgit v1.2.3 From 5c99fa737c693a50419606d8f8266974a3521b32 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Tue, 21 Sep 2021 12:42:25 +0300 Subject: bus: ti-sysc: Handle otg force idle quirk Let's add handling the otg force idle quirk for the old omap2430 glue layer used up to omap4 as the musb driver quirk only works if the driver is loaded. Unlike with the am335x glue layer, looks like we don't need the quirk handling for SYSC_QUIRK_REINIT_ON_CTX_LOST. Eventually when all the musb using SoCs are booting with device tree based configuration, we can just remove the related quirk handling from the musb driver. Signed-off-by: Tony Lindgren --- drivers/bus/ti-sysc.c | 24 +++++++++++++++++++++++- include/linux/platform_data/ti-sysc.h | 1 + 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index 88524faa61cc..fc6968dc7397 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -1610,7 +1610,8 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = { SYSC_QUIRK("usb_host_hs", 0, 0, 0x10, -ENODEV, 0x50700101, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), SYSC_QUIRK("usb_otg_hs", 0, 0x400, 0x404, 0x408, 0x00000050, - 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY), + 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY | + SYSC_MODULE_QUIRK_OTG), SYSC_QUIRK("usb_otg_hs", 0, 0, 0x10, -ENODEV, 0x4ea2080d, 0xffffffff, SYSC_QUIRK_SWSUP_SIDLE | SYSC_QUIRK_SWSUP_MSTANDBY | SYSC_QUIRK_REINIT_ON_CTX_LOST), @@ -1969,6 +1970,22 @@ static void sysc_module_lock_quirk_rtc(struct sysc *ddata) sysc_quirk_rtc(ddata, true); } +/* OTG omap2430 glue layer up to omap4 needs OTG_FORCESTDBY configured */ +static void sysc_module_enable_quirk_otg(struct sysc *ddata) +{ + int offset = 0x414; /* OTG_FORCESTDBY */ + + sysc_write(ddata, offset, 0); +} + +static void sysc_module_disable_quirk_otg(struct sysc *ddata) +{ + int offset = 0x414; /* OTG_FORCESTDBY */ + u32 val = BIT(0); /* ENABLEFORCE */ + + sysc_write(ddata, offset, val); +} + /* 36xx SGX needs a quirk for to bypass OCP IPG interrupt logic */ static void sysc_module_enable_quirk_sgx(struct sysc *ddata) { @@ -2051,6 +2068,11 @@ static void sysc_init_module_quirks(struct sysc *ddata) return; } + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_OTG) { + ddata->module_enable_quirk = sysc_module_enable_quirk_otg; + ddata->module_disable_quirk = sysc_module_disable_quirk_otg; + } + if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_SGX) ddata->module_enable_quirk = sysc_module_enable_quirk_sgx; diff --git a/include/linux/platform_data/ti-sysc.h b/include/linux/platform_data/ti-sysc.h index f11244f5c0b6..eb556f988d57 100644 --- a/include/linux/platform_data/ti-sysc.h +++ b/include/linux/platform_data/ti-sysc.h @@ -50,6 +50,7 @@ struct sysc_regbits { s8 emufree_shift; }; +#define SYSC_MODULE_QUIRK_OTG BIT(30) #define SYSC_QUIRK_RESET_ON_CTX_LOST BIT(29) #define SYSC_QUIRK_REINIT_ON_CTX_LOST BIT(28) #define SYSC_QUIRK_REINIT_ON_RESUME BIT(27) -- cgit v1.2.3 From d6da08ed1425180b8d54c828ec06d247fd915d60 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 20 Sep 2021 14:54:14 -0700 Subject: net: phy: broadcom: Add IDDQ-SR mode Add support for putting the PHY into IDDQ Soft Recovery mode by setting the TOP_MISC register bits accordingly. This requires us to implement a custom bcm54xx_suspend() routine which diverges from genphy_suspend() in order to configure the PHY to enter IDDQ with software recovery as well as avoid doing a read/modify/write on the BMCR register. Doing a read/modify/write on the BMCR register means that the auto-negotation bit may remain which interferes with the ability to put the PHY into IDDQ-SR mode. We do software reset upon suspend in order to put the PHY back into its state prior to suspend as recommended by the datasheet. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/broadcom.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/brcmphy.h | 8 ++++++++ 2 files changed, 59 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index add0c4e33425..f5868a0dee4b 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -392,10 +392,50 @@ static int bcm54xx_config_init(struct phy_device *phydev) return 0; } +static int bcm54xx_iddq_set(struct phy_device *phydev, bool enable) +{ + int ret = 0; + + if (!(phydev->dev_flags & PHY_BRCM_IDDQ_SUSPEND)) + return ret; + + ret = bcm_phy_read_exp(phydev, BCM54XX_TOP_MISC_IDDQ_CTRL); + if (ret < 0) + goto out; + + if (enable) + ret |= BCM54XX_TOP_MISC_IDDQ_SR | BCM54XX_TOP_MISC_IDDQ_LP; + else + ret &= ~(BCM54XX_TOP_MISC_IDDQ_SR | BCM54XX_TOP_MISC_IDDQ_LP); + + ret = bcm_phy_write_exp(phydev, BCM54XX_TOP_MISC_IDDQ_CTRL, ret); +out: + return ret; +} + +static int bcm54xx_suspend(struct phy_device *phydev) +{ + int ret; + + /* We cannot use a read/modify/write here otherwise the PHY gets into + * a bad state where its LEDs keep flashing, thus defeating the purpose + * of low power mode. + */ + ret = phy_write(phydev, MII_BMCR, BMCR_PDOWN); + if (ret < 0) + return ret; + + return bcm54xx_iddq_set(phydev, true); +} + static int bcm54xx_resume(struct phy_device *phydev) { int ret; + ret = bcm54xx_iddq_set(phydev, false); + if (ret < 0) + return ret; + /* Writes to register other than BMCR would be ignored * unless we clear the PDOWN bit first */ @@ -408,6 +448,15 @@ static int bcm54xx_resume(struct phy_device *phydev) */ fsleep(40); + /* Issue a soft reset after clearing the power down bit + * and before doing any other configuration. + */ + if (phydev->dev_flags & PHY_BRCM_IDDQ_SUSPEND) { + ret = genphy_soft_reset(phydev); + if (ret < 0) + return ret; + } + return bcm54xx_config_init(phydev); } @@ -772,6 +821,8 @@ static struct phy_driver broadcom_drivers[] = { .config_intr = bcm_phy_config_intr, .handle_interrupt = bcm_phy_handle_interrupt, .link_change_notify = bcm54xx_link_change_notify, + .suspend = bcm54xx_suspend, + .resume = bcm54xx_resume, }, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 07e1dfadbbdf..b119d6819d6c 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -67,6 +67,7 @@ #define PHY_BRCM_CLEAR_RGMII_MODE 0x00000004 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000008 #define PHY_BRCM_EN_MASTER_MODE 0x00000010 +#define PHY_BRCM_IDDQ_SUSPEND 0x000000220 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) @@ -84,6 +85,7 @@ #define MII_BCM54XX_EXP_DATA 0x15 /* Expansion register data */ #define MII_BCM54XX_EXP_SEL 0x17 /* Expansion register select */ +#define MII_BCM54XX_EXP_SEL_TOP 0x0d00 /* TOP_MISC expansion register select */ #define MII_BCM54XX_EXP_SEL_SSD 0x0e00 /* Secondary SerDes select */ #define MII_BCM54XX_EXP_SEL_ER 0x0f00 /* Expansion register select */ #define MII_BCM54XX_EXP_SEL_ETC 0x0d00 /* Expansion register spare + 2k mem */ @@ -243,6 +245,12 @@ #define MII_BCM54XX_EXP_EXP97 0x0f97 #define MII_BCM54XX_EXP_EXP97_MYST 0x0c0c +/* Top-MISC expansion registers */ +#define BCM54XX_TOP_MISC_IDDQ_CTRL (MII_BCM54XX_EXP_SEL_TOP + 0x06) +#define BCM54XX_TOP_MISC_IDDQ_LP (1 << 0) +#define BCM54XX_TOP_MISC_IDDQ_SD (1 << 2) +#define BCM54XX_TOP_MISC_IDDQ_SR (1 << 3) + /* * BCM5482: Secondary SerDes registers */ -- cgit v1.2.3 From 06dc660e6eb8817c4c379d2ca290ae0b3f77c69f Mon Sep 17 00:00:00 2001 From: Oliver O'Halloran Date: Tue, 14 Sep 2021 01:27:08 +1000 Subject: PCI: Rename pcibios_add_device() to pcibios_device_add() The general convention for pcibios_* hooks is that they're named after the corresponding pci_* function they provide a hook for. The exception is pcibios_add_device() which provides a hook for pci_device_add(). Rename pcibios_add_device() to pcibios_device_add() so it matches pci_device_add(). Also, remove the export of the microblaze version. The only caller must be compiled as a built-in so there's no reason for the export. Link: https://lore.kernel.org/r/20210913152709.48013-1-oohall@gmail.com Signed-off-by: Oliver O'Halloran Signed-off-by: Bjorn Helgaas Acked-by: Niklas Schnelle # s390 --- arch/microblaze/pci/pci-common.c | 3 +-- arch/powerpc/kernel/pci-common.c | 2 +- arch/powerpc/platforms/powernv/pci-sriov.c | 2 +- arch/s390/pci/pci.c | 2 +- arch/sparc/kernel/pci.c | 2 +- arch/x86/pci/common.c | 2 +- drivers/pci/pci.c | 4 ++-- drivers/pci/probe.c | 4 ++-- include/linux/pci.h | 2 +- 9 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index 557585f1be41..622a4867f9e9 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -587,13 +587,12 @@ static void pcibios_fixup_resources(struct pci_dev *dev) } DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pcibios_fixup_resources); -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { dev->irq = of_irq_parse_and_map_pci(dev, 0, 0); return 0; } -EXPORT_SYMBOL(pcibios_add_device); /* * Reparent resource children of pr that conflict with res diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index c3573430919d..6749905932f4 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1059,7 +1059,7 @@ void pcibios_bus_add_device(struct pci_dev *dev) ppc_md.pcibios_bus_add_device(dev); } -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct irq_domain *d; diff --git a/arch/powerpc/platforms/powernv/pci-sriov.c b/arch/powerpc/platforms/powernv/pci-sriov.c index 28aac933a439..486c2937b159 100644 --- a/arch/powerpc/platforms/powernv/pci-sriov.c +++ b/arch/powerpc/platforms/powernv/pci-sriov.c @@ -54,7 +54,7 @@ * to "new_size", calculated above. Implementing this is a convoluted process * which requires several hooks in the PCI core: * - * 1. In pcibios_add_device() we call pnv_pci_ioda_fixup_iov(). + * 1. In pcibios_device_add() we call pnv_pci_ioda_fixup_iov(). * * At this point the device has been probed and the device's BARs are sized, * but no resource allocations have been done. The SR-IOV BARs are sized diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e7e6788d75a8..ded3321b7208 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -561,7 +561,7 @@ static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) zdev->has_resources = 0; } -int pcibios_add_device(struct pci_dev *pdev) +int pcibios_device_add(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); struct resource *res; diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c index 9c2b720bfd20..31b0c1983286 100644 --- a/arch/sparc/kernel/pci.c +++ b/arch/sparc/kernel/pci.c @@ -1010,7 +1010,7 @@ void pcibios_set_master(struct pci_dev *dev) } #ifdef CONFIG_PCI_IOV -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct pci_dev *pdev; diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 3507f456fcd0..9e1e6b8d8876 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -632,7 +632,7 @@ static void set_dev_domain_options(struct pci_dev *pdev) pdev->hotplug_user_indicators = 1; } -int pcibios_add_device(struct pci_dev *dev) +int pcibios_device_add(struct pci_dev *dev) { struct pci_setup_rom *rom; struct irq_domain *msidom; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index ce2ab62b64cf..c63598c1cdd8 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2091,14 +2091,14 @@ void pcim_pin_device(struct pci_dev *pdev) EXPORT_SYMBOL(pcim_pin_device); /* - * pcibios_add_device - provide arch specific hooks when adding device dev + * pcibios_device_add - provide arch specific hooks when adding device dev * @dev: the PCI device being added * * Permits the platform to provide architecture specific functionality when * devices are added. This is the default implementation. Architecture * implementations can override this. */ -int __weak pcibios_add_device(struct pci_dev *dev) +int __weak pcibios_device_add(struct pci_dev *dev) { return 0; } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index d9fc02a71baa..2ba43b6adf31 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2450,7 +2450,7 @@ static struct irq_domain *pci_dev_msi_domain(struct pci_dev *dev) struct irq_domain *d; /* - * If a domain has been set through the pcibios_add_device() + * If a domain has been set through the pcibios_device_add() * callback, then this is the one (platform code knows best). */ d = dev_get_msi_domain(&dev->dev); @@ -2518,7 +2518,7 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) list_add_tail(&dev->bus_list, &bus->devices); up_write(&pci_bus_sem); - ret = pcibios_add_device(dev); + ret = pcibios_device_add(dev); WARN_ON(ret < 0); /* Set up MSI IRQ domain */ diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..7e0ce3a4d5a1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -2126,7 +2126,7 @@ void pcibios_disable_device(struct pci_dev *dev); void pcibios_set_master(struct pci_dev *dev); int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state); -int pcibios_add_device(struct pci_dev *dev); +int pcibios_device_add(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); #ifdef CONFIG_PCI void pcibios_penalize_isa_irq(int irq, int active); -- cgit v1.2.3 From d1c6e08e7503649e4a4f3f9e700e2c05300b6379 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 8 Sep 2021 22:11:37 -0700 Subject: libnvdimm/labels: Add uuid helpers In preparation for CXL labels that move the uuid to a different offset in the label, add nsl_{ref,get,validate}_uuid(). These helpers use the proper uuid_t type. That type definition predated the libnvdimm subsystem, so now is as a good a time as any to convert all the uuid handling in the subsystem to uuid_t to match the helpers. Note that the uuid fields in the label data and superblocks is not replaced per Andy's expectation that uuid_t is a kernel internal type not to appear in external ABI interfaces. So, in those case {import,export}_uuid() is used to go between the 2 types. Also note that this rework uncovered some unnecessary copies for label comparisons, those are cleaned up with nsl_uuid_equal(). As for the whitespace changes, all new code is clang-format compliant. Reported-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163116429748.2460985.15659993454313919977.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/nvdimm/btt.c | 11 ++--- drivers/nvdimm/btt_devs.c | 14 ++++--- drivers/nvdimm/core.c | 40 ++---------------- drivers/nvdimm/label.c | 34 +++++++--------- drivers/nvdimm/namespace_devs.c | 90 +++++++++++++++++++++++------------------ drivers/nvdimm/nd-core.h | 5 ++- drivers/nvdimm/nd.h | 40 ++++++++++++++++-- drivers/nvdimm/pfn_devs.c | 2 +- include/linux/nd.h | 4 +- 9 files changed, 124 insertions(+), 116 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 92dec4952297..52de60b7adee 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -973,7 +973,7 @@ static int btt_arena_write_layout(struct arena_info *arena) u64 sum; struct btt_sb *super; struct nd_btt *nd_btt = arena->nd_btt; - const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); + const uuid_t *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); ret = btt_map_init(arena); if (ret) @@ -988,8 +988,8 @@ static int btt_arena_write_layout(struct arena_info *arena) return -ENOMEM; strncpy(super->signature, BTT_SIG, BTT_SIG_LEN); - memcpy(super->uuid, nd_btt->uuid, 16); - memcpy(super->parent_uuid, parent_uuid, 16); + export_uuid(super->uuid, nd_btt->uuid); + export_uuid(super->parent_uuid, parent_uuid); super->flags = cpu_to_le32(arena->flags); super->version_major = cpu_to_le16(arena->version_major); super->version_minor = cpu_to_le16(arena->version_minor); @@ -1575,7 +1575,8 @@ static void btt_blk_cleanup(struct btt *btt) * Pointer to a new struct btt on success, NULL on failure. */ static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize, - u32 lbasize, u8 *uuid, struct nd_region *nd_region) + u32 lbasize, uuid_t *uuid, + struct nd_region *nd_region) { int ret; struct btt *btt; @@ -1694,7 +1695,7 @@ int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns) } nd_region = to_nd_region(nd_btt->dev.parent); btt = btt_init(nd_btt, rawsize, nd_btt->lbasize, nd_btt->uuid, - nd_region); + nd_region); if (!btt) return -ENOMEM; nd_btt->btt = btt; diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 05feb97e11ce..8b52e5144f08 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -180,8 +180,8 @@ bool is_nd_btt(struct device *dev) EXPORT_SYMBOL(is_nd_btt); static struct device *__nd_btt_create(struct nd_region *nd_region, - unsigned long lbasize, u8 *uuid, - struct nd_namespace_common *ndns) + unsigned long lbasize, uuid_t *uuid, + struct nd_namespace_common *ndns) { struct nd_btt *nd_btt; struct device *dev; @@ -244,14 +244,16 @@ struct device *nd_btt_create(struct nd_region *nd_region) */ bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super) { - const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); + const uuid_t *ns_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev); + uuid_t parent_uuid; u64 checksum; if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0) return false; - if (!guid_is_null((guid_t *)&super->parent_uuid)) - if (memcmp(super->parent_uuid, parent_uuid, 16) != 0) + import_uuid(&parent_uuid, super->parent_uuid); + if (!uuid_is_null(&parent_uuid)) + if (!uuid_equal(&parent_uuid, ns_uuid)) return false; checksum = le64_to_cpu(super->checksum); @@ -319,7 +321,7 @@ static int __nd_btt_probe(struct nd_btt *nd_btt, return rc; nd_btt->lbasize = le32_to_cpu(btt_sb->external_lbasize); - nd_btt->uuid = kmemdup(btt_sb->uuid, 16, GFP_KERNEL); + nd_btt->uuid = kmemdup(&btt_sb->uuid, sizeof(uuid_t), GFP_KERNEL); if (!nd_btt->uuid) return -ENOMEM; diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 7de592d7eff4..690152d62bf0 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -206,38 +206,6 @@ struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus) } EXPORT_SYMBOL_GPL(to_nvdimm_bus_dev); -static bool is_uuid_sep(char sep) -{ - if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0') - return true; - return false; -} - -static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, - size_t len) -{ - const char *str = buf; - u8 uuid[16]; - int i; - - for (i = 0; i < 16; i++) { - if (!isxdigit(str[0]) || !isxdigit(str[1])) { - dev_dbg(dev, "pos: %d buf[%zd]: %c buf[%zd]: %c\n", - i, str - buf, str[0], - str + 1 - buf, str[1]); - return -EINVAL; - } - - uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]); - str += 2; - if (is_uuid_sep(*str)) - str++; - } - - memcpy(uuid_out, uuid, sizeof(uuid)); - return 0; -} - /** * nd_uuid_store: common implementation for writing 'uuid' sysfs attributes * @dev: container device for the uuid property @@ -248,21 +216,21 @@ static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf, * (driver detached) * LOCKING: expects nd_device_lock() is held on entry */ -int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, +int nd_uuid_store(struct device *dev, uuid_t **uuid_out, const char *buf, size_t len) { - u8 uuid[16]; + uuid_t uuid; int rc; if (dev->driver) return -EBUSY; - rc = nd_uuid_parse(dev, uuid, buf, len); + rc = uuid_parse(buf, &uuid); if (rc) return rc; kfree(*uuid_out); - *uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL); + *uuid_out = kmemdup(&uuid, sizeof(uuid), GFP_KERNEL); if (!(*uuid_out)) return -ENOMEM; diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c index 7f473f9db300..e7fdb718ebf0 100644 --- a/drivers/nvdimm/label.c +++ b/drivers/nvdimm/label.c @@ -321,7 +321,8 @@ static bool preamble_index(struct nvdimm_drvdata *ndd, int idx, return true; } -char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags) +char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid, + u32 flags) { if (!label_id || !uuid) return NULL; @@ -400,9 +401,9 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) struct nvdimm *nvdimm = to_nvdimm(ndd->dev); struct nd_namespace_label *nd_label; struct nd_region *nd_region = NULL; - u8 label_uuid[NSLABEL_UUID_LEN]; struct nd_label_id label_id; struct resource *res; + uuid_t label_uuid; u32 flags; nd_label = to_label(ndd, slot); @@ -410,11 +411,11 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) if (!slot_valid(ndd, nd_label, slot)) continue; - memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); + nsl_get_uuid(ndd, nd_label, &label_uuid); flags = nsl_get_flags(ndd, nd_label); if (test_bit(NDD_NOBLK, &nvdimm->flags)) flags &= ~NSLABEL_FLAG_LOCAL; - nd_label_gen_id(&label_id, label_uuid, flags); + nd_label_gen_id(&label_id, &label_uuid, flags); res = nvdimm_allocate_dpa(ndd, &label_id, nsl_get_dpa(ndd, nd_label), nsl_get_rawsize(ndd, nd_label)); @@ -851,7 +852,7 @@ static int __pmem_label_update(struct nd_region *nd_region, nd_label = to_label(ndd, slot); memset(nd_label, 0, sizeof_namespace_label(ndd)); - memcpy(nd_label->uuid, nspm->uuid, NSLABEL_UUID_LEN); + nsl_set_uuid(ndd, nd_label, nspm->uuid); nsl_set_name(ndd, nd_label, nspm->alt_name); nsl_set_flags(ndd, nd_label, flags); nsl_set_nlabel(ndd, nd_label, nd_region->ndr_mappings); @@ -878,9 +879,8 @@ static int __pmem_label_update(struct nd_region *nd_region, list_for_each_entry(label_ent, &nd_mapping->labels, list) { if (!label_ent->label) continue; - if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags) - || memcmp(nspm->uuid, label_ent->label->uuid, - NSLABEL_UUID_LEN) == 0) + if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags) || + nsl_uuid_equal(ndd, label_ent->label, nspm->uuid)) reap_victim(nd_mapping, label_ent); } @@ -1005,7 +1005,6 @@ static int __blk_label_update(struct nd_region *nd_region, unsigned long *free, *victim_map = NULL; struct resource *res, **old_res_list; struct nd_label_id label_id; - u8 uuid[NSLABEL_UUID_LEN]; int min_dpa_idx = 0; LIST_HEAD(list); u32 nslot, slot; @@ -1043,8 +1042,7 @@ static int __blk_label_update(struct nd_region *nd_region, /* mark unused labels for garbage collection */ for_each_clear_bit_le(slot, free, nslot) { nd_label = to_label(ndd, slot); - memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) continue; res = to_resource(ndd, nd_label); if (res && is_old_resource(res, old_res_list, @@ -1113,7 +1111,7 @@ static int __blk_label_update(struct nd_region *nd_region, nd_label = to_label(ndd, slot); memset(nd_label, 0, sizeof_namespace_label(ndd)); - memcpy(nd_label->uuid, nsblk->uuid, NSLABEL_UUID_LEN); + nsl_set_uuid(ndd, nd_label, nsblk->uuid); nsl_set_name(ndd, nd_label, nsblk->alt_name); nsl_set_flags(ndd, nd_label, NSLABEL_FLAG_LOCAL); @@ -1161,8 +1159,7 @@ static int __blk_label_update(struct nd_region *nd_region, if (!nd_label) continue; nlabel++; - memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) continue; nlabel--; list_move(&label_ent->list, &list); @@ -1192,8 +1189,7 @@ static int __blk_label_update(struct nd_region *nd_region, } for_each_clear_bit_le(slot, free, nslot) { nd_label = to_label(ndd, slot); - memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, nsblk->uuid)) continue; res = to_resource(ndd, nd_label); res->flags &= ~DPA_RESOURCE_ADJUSTED; @@ -1273,12 +1269,11 @@ static int init_labels(struct nd_mapping *nd_mapping, int num_labels) return max(num_labels, old_num_labels); } -static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) +static int del_labels(struct nd_mapping *nd_mapping, uuid_t *uuid) { struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); struct nd_label_ent *label_ent, *e; struct nd_namespace_index *nsindex; - u8 label_uuid[NSLABEL_UUID_LEN]; unsigned long *free; LIST_HEAD(list); u32 nslot, slot; @@ -1298,8 +1293,7 @@ static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid) if (!nd_label) continue; active++; - memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN); - if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; active--; slot = to_slot(ndd, nd_label); diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 4cec171c934d..1415d543c3e3 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -51,7 +51,7 @@ static bool is_namespace_io(const struct device *dev); static int is_uuid_busy(struct device *dev, void *data) { - u8 *uuid1 = data, *uuid2 = NULL; + uuid_t *uuid1 = data, *uuid2 = NULL; if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -71,7 +71,7 @@ static int is_uuid_busy(struct device *dev, void *data) uuid2 = nd_pfn->uuid; } - if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0) + if (uuid2 && uuid_equal(uuid1, uuid2)) return -EBUSY; return 0; @@ -89,7 +89,7 @@ static int is_namespace_uuid_busy(struct device *dev, void *data) * @dev: any device on a nvdimm_bus * @uuid: uuid to check */ -bool nd_is_uuid_unique(struct device *dev, u8 *uuid) +bool nd_is_uuid_unique(struct device *dev, uuid_t *uuid) { struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev); @@ -192,12 +192,10 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns, } EXPORT_SYMBOL(nvdimm_namespace_disk_name); -const u8 *nd_dev_to_uuid(struct device *dev) +const uuid_t *nd_dev_to_uuid(struct device *dev) { - static const u8 null_uuid[16]; - if (!dev) - return null_uuid; + return &uuid_null; if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -208,7 +206,7 @@ const u8 *nd_dev_to_uuid(struct device *dev) return nsblk->uuid; } else - return null_uuid; + return &uuid_null; } EXPORT_SYMBOL(nd_dev_to_uuid); @@ -938,7 +936,8 @@ static void nd_namespace_pmem_set_resource(struct nd_region *nd_region, res->end = res->start + size - 1; } -static bool uuid_not_set(const u8 *uuid, struct device *dev, const char *where) +static bool uuid_not_set(const uuid_t *uuid, struct device *dev, + const char *where) { if (!uuid) { dev_dbg(dev, "%s: uuid not set\n", where); @@ -957,7 +956,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) struct nd_label_id label_id; u32 flags = 0, remainder; int rc, i, id = -1; - u8 *uuid = NULL; + uuid_t *uuid = NULL; if (dev->driver || ndns->claim) return -EBUSY; @@ -1050,7 +1049,7 @@ static ssize_t size_store(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev->parent); unsigned long long val; - u8 **uuid = NULL; + uuid_t **uuid = NULL; int rc; rc = kstrtoull(buf, 0, &val); @@ -1147,7 +1146,7 @@ static ssize_t size_show(struct device *dev, } static DEVICE_ATTR(size, 0444, size_show, size_store); -static u8 *namespace_to_uuid(struct device *dev) +static uuid_t *namespace_to_uuid(struct device *dev) { if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -1161,10 +1160,10 @@ static u8 *namespace_to_uuid(struct device *dev) return ERR_PTR(-ENXIO); } -static ssize_t uuid_show(struct device *dev, - struct device_attribute *attr, char *buf) +static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, + char *buf) { - u8 *uuid = namespace_to_uuid(dev); + uuid_t *uuid = namespace_to_uuid(dev); if (IS_ERR(uuid)) return PTR_ERR(uuid); @@ -1181,7 +1180,8 @@ static ssize_t uuid_show(struct device *dev, * @old_uuid: reference to the uuid storage location in the namespace object */ static int namespace_update_uuid(struct nd_region *nd_region, - struct device *dev, u8 *new_uuid, u8 **old_uuid) + struct device *dev, uuid_t *new_uuid, + uuid_t **old_uuid) { u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0; struct nd_label_id old_label_id; @@ -1231,10 +1231,12 @@ static int namespace_update_uuid(struct nd_region *nd_region, list_for_each_entry(label_ent, &nd_mapping->labels, list) { struct nd_namespace_label *nd_label = label_ent->label; struct nd_label_id label_id; + uuid_t uuid; if (!nd_label) continue; - nd_label_gen_id(&label_id, nd_label->uuid, + nsl_get_uuid(ndd, nd_label, &uuid); + nd_label_gen_id(&label_id, &uuid, nsl_get_flags(ndd, nd_label)); if (strcmp(old_label_id.id, label_id.id) == 0) set_bit(ND_LABEL_REAP, &label_ent->flags); @@ -1251,9 +1253,9 @@ static ssize_t uuid_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct nd_region *nd_region = to_nd_region(dev->parent); - u8 *uuid = NULL; + uuid_t *uuid = NULL; + uuid_t **ns_uuid; ssize_t rc = 0; - u8 **ns_uuid; if (is_namespace_pmem(dev)) { struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev); @@ -1378,8 +1380,8 @@ static ssize_t dpa_extents_show(struct device *dev, { struct nd_region *nd_region = to_nd_region(dev->parent); struct nd_label_id label_id; + uuid_t *uuid = NULL; int count = 0, i; - u8 *uuid = NULL; u32 flags = 0; nvdimm_bus_lock(dev); @@ -1831,8 +1833,8 @@ static struct device **create_namespace_io(struct nd_region *nd_region) return devs; } -static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, - u64 cookie, u16 pos) +static bool has_uuid_at_pos(struct nd_region *nd_region, const uuid_t *uuid, + u64 cookie, u16 pos) { struct nd_namespace_label *found = NULL; int i; @@ -1856,7 +1858,7 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, if (!nsl_validate_isetcookie(ndd, nd_label, cookie)) continue; - if (memcmp(nd_label->uuid, uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; if (!nsl_validate_type_guid(ndd, nd_label, @@ -1881,7 +1883,7 @@ static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid, return found != NULL; } -static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) +static int select_pmem_id(struct nd_region *nd_region, const uuid_t *pmem_id) { int i; @@ -1900,7 +1902,7 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) nd_label = label_ent->label; if (!nd_label) continue; - if (memcmp(nd_label->uuid, pmem_id, NSLABEL_UUID_LEN) == 0) + if (nsl_uuid_equal(ndd, nd_label, pmem_id)) break; nd_label = NULL; } @@ -1923,7 +1925,8 @@ static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id) /* pass */; else { dev_dbg(&nd_region->dev, "%s invalid label for %pUb\n", - dev_name(ndd->dev), nd_label->uuid); + dev_name(ndd->dev), + nsl_uuid_raw(ndd, nd_label)); return -EINVAL; } @@ -1953,6 +1956,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, resource_size_t size = 0; struct resource *res; struct device *dev; + uuid_t uuid; int rc = 0; u16 i; @@ -1963,12 +1967,12 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, if (!nsl_validate_isetcookie(ndd, nd_label, cookie)) { dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n", - nd_label->uuid); + nsl_uuid_raw(ndd, nd_label)); if (!nsl_validate_isetcookie(ndd, nd_label, altcookie)) return ERR_PTR(-EAGAIN); dev_dbg(&nd_region->dev, "valid altcookie in label: %pUb\n", - nd_label->uuid); + nsl_uuid_raw(ndd, nd_label)); } nspm = kzalloc(sizeof(*nspm), GFP_KERNEL); @@ -1984,9 +1988,12 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, res->flags = IORESOURCE_MEM; for (i = 0; i < nd_region->ndr_mappings; i++) { - if (has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i)) + uuid_t uuid; + + nsl_get_uuid(ndd, nd_label, &uuid); + if (has_uuid_at_pos(nd_region, &uuid, cookie, i)) continue; - if (has_uuid_at_pos(nd_region, nd_label->uuid, altcookie, i)) + if (has_uuid_at_pos(nd_region, &uuid, altcookie, i)) continue; break; } @@ -2000,7 +2007,7 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, * find a dimm with two instances of the same uuid. */ dev_err(&nd_region->dev, "%s missing label for %pUb\n", - nvdimm_name(nvdimm), nd_label->uuid); + nvdimm_name(nvdimm), nsl_uuid_raw(ndd, nd_label)); rc = -EINVAL; goto err; } @@ -2013,7 +2020,8 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, * the dimm being enabled (i.e. nd_label_reserve_dpa() * succeeded). */ - rc = select_pmem_id(nd_region, nd_label->uuid); + nsl_get_uuid(ndd, nd_label, &uuid); + rc = select_pmem_id(nd_region, &uuid); if (rc) goto err; @@ -2039,8 +2047,8 @@ static struct device *create_namespace_pmem(struct nd_region *nd_region, WARN_ON(nspm->alt_name || nspm->uuid); nspm->alt_name = kmemdup(nsl_ref_name(ndd, label0), NSLABEL_NAME_LEN, GFP_KERNEL); - nspm->uuid = kmemdup((void __force *) label0->uuid, - NSLABEL_UUID_LEN, GFP_KERNEL); + nsl_get_uuid(ndd, label0, &uuid); + nspm->uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL); nspm->lbasize = nsl_get_lbasize(ndd, label0); nspm->nsio.common.claim_class = nsl_get_claim_class(ndd, label0); @@ -2217,15 +2225,15 @@ static int add_namespace_resource(struct nd_region *nd_region, int i; for (i = 0; i < count; i++) { - u8 *uuid = namespace_to_uuid(devs[i]); + uuid_t *uuid = namespace_to_uuid(devs[i]); struct resource *res; - if (IS_ERR_OR_NULL(uuid)) { + if (IS_ERR(uuid)) { WARN_ON(1); continue; } - if (memcmp(uuid, nd_label->uuid, NSLABEL_UUID_LEN) != 0) + if (!nsl_uuid_equal(ndd, nd_label, uuid)) continue; if (is_namespace_blk(devs[i])) { res = nsblk_add_resource(nd_region, ndd, @@ -2236,8 +2244,8 @@ static int add_namespace_resource(struct nd_region *nd_region, nd_dbg_dpa(nd_region, ndd, res, "%d assign\n", count); } else { dev_err(&nd_region->dev, - "error: conflicting extents for uuid: %pUb\n", - nd_label->uuid); + "error: conflicting extents for uuid: %pUb\n", + uuid); return -ENXIO; } break; @@ -2257,6 +2265,7 @@ static struct device *create_namespace_blk(struct nd_region *nd_region, char name[NSLABEL_NAME_LEN]; struct device *dev = NULL; struct resource *res; + uuid_t uuid; if (!nsl_validate_type_guid(ndd, nd_label, &nd_set->type_guid)) return ERR_PTR(-EAGAIN); @@ -2271,7 +2280,8 @@ static struct device *create_namespace_blk(struct nd_region *nd_region, dev->parent = &nd_region->dev; nsblk->id = -1; nsblk->lbasize = nsl_get_lbasize(ndd, nd_label); - nsblk->uuid = kmemdup(nd_label->uuid, NSLABEL_UUID_LEN, GFP_KERNEL); + nsl_get_uuid(ndd, nd_label, &uuid); + nsblk->uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL); nsblk->common.claim_class = nsl_get_claim_class(ndd, nd_label); if (!nsblk->uuid) goto blk_err; diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 564faa36a3ca..a11850dd475d 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -126,8 +126,9 @@ void nvdimm_bus_destroy_ndctl(struct nvdimm_bus *nvdimm_bus); void nd_synchronize(void); void __nd_device_register(struct device *dev); struct nd_label_id; -char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags); -bool nd_is_uuid_unique(struct device *dev, u8 *uuid); +char *nd_label_gen_id(struct nd_label_id *label_id, const uuid_t *uuid, + u32 flags); +bool nd_is_uuid_unique(struct device *dev, uuid_t *uuid); struct nd_region; struct nvdimm_drvdata; struct nd_mapping; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 5467ebbb4a6b..ec3c9aad7f50 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -177,6 +177,38 @@ static inline void nsl_set_lbasize(struct nvdimm_drvdata *ndd, nd_label->lbasize = __cpu_to_le64(lbasize); } +static inline const uuid_t *nsl_get_uuid(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + uuid_t *uuid) +{ + import_uuid(uuid, nd_label->uuid); + return uuid; +} + +static inline const uuid_t *nsl_set_uuid(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + const uuid_t *uuid) +{ + export_uuid(nd_label->uuid, uuid); + return uuid; +} + +static inline bool nsl_uuid_equal(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label, + const uuid_t *uuid) +{ + uuid_t tmp; + + import_uuid(&tmp, nd_label->uuid); + return uuid_equal(&tmp, uuid); +} + +static inline const u8 *nsl_uuid_raw(struct nvdimm_drvdata *ndd, + struct nd_namespace_label *nd_label) +{ + return nd_label->uuid; +} + bool nsl_validate_blk_isetcookie(struct nvdimm_drvdata *ndd, struct nd_namespace_label *nd_label, u64 isetcookie); @@ -335,7 +367,7 @@ struct nd_btt { struct btt *btt; unsigned long lbasize; u64 size; - u8 *uuid; + uuid_t *uuid; int id; int initial_offset; u16 version_major; @@ -350,7 +382,7 @@ enum nd_pfn_mode { struct nd_pfn { int id; - u8 *uuid; + uuid_t *uuid; struct device dev; unsigned long align; unsigned long npfns; @@ -378,7 +410,7 @@ void wait_nvdimm_bus_probe_idle(struct device *dev); void nd_device_register(struct device *dev); void nd_device_unregister(struct device *dev, enum nd_async_mode mode); void nd_device_notify(struct device *dev, enum nvdimm_event event); -int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf, +int nd_uuid_store(struct device *dev, uuid_t **uuid_out, const char *buf, size_t len); ssize_t nd_size_select_show(unsigned long current_size, const unsigned long *supported, char *buf); @@ -561,6 +593,6 @@ static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector, return false; } resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk); -const u8 *nd_dev_to_uuid(struct device *dev); +const uuid_t *nd_dev_to_uuid(struct device *dev); bool pmem_should_map_pages(struct device *dev); #endif /* __ND_H__ */ diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index b499df630d4d..58eda16f5c53 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -452,7 +452,7 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) unsigned long align, start_pad; struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb; struct nd_namespace_common *ndns = nd_pfn->ndns; - const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev); + const uuid_t *parent_uuid = nd_dev_to_uuid(&ndns->dev); if (!pfn_sb || !ndns) return -ENODEV; diff --git a/include/linux/nd.h b/include/linux/nd.h index ee9ad76afbba..8a8c63edb1b2 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -88,7 +88,7 @@ struct nd_namespace_pmem { struct nd_namespace_io nsio; unsigned long lbasize; char *alt_name; - u8 *uuid; + uuid_t *uuid; int id; }; @@ -105,7 +105,7 @@ struct nd_namespace_pmem { struct nd_namespace_blk { struct nd_namespace_common common; char *alt_name; - u8 *uuid; + uuid_t *uuid; int id; unsigned long lbasize; resource_size_t size; -- cgit v1.2.3 From 8c75d585b931ac874fbe4ee5a8f1811d20c2817f Mon Sep 17 00:00:00 2001 From: Deepak Kumar Singh Date: Tue, 31 Aug 2021 20:00:27 +0530 Subject: soc: qcom: aoss: Expose send for generic usecase Not all upcoming usecases will have an interface to allow the aoss driver to hook onto. Expose the send api and create a get function to enable drivers to send their own messages to aoss. Signed-off-by: Chris Lew Signed-off-by: Deepak Kumar Singh Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1630420228-31075-2-git-send-email-deesin@codeaurora.org --- drivers/soc/qcom/qcom_aoss.c | 54 +++++++++++++++++++++++++++++++++++++- include/linux/soc/qcom/qcom_aoss.h | 38 +++++++++++++++++++++++++++ 2 files changed, 91 insertions(+), 1 deletion(-) create mode 100644 include/linux/soc/qcom/qcom_aoss.h (limited to 'include/linux') diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c index 536c3e4114fb..bb336cc8df6f 100644 --- a/drivers/soc/qcom/qcom_aoss.c +++ b/drivers/soc/qcom/qcom_aoss.c @@ -8,10 +8,12 @@ #include #include #include +#include #include #include #include #include +#include #define QMP_DESC_MAGIC 0x0 #define QMP_DESC_VERSION 0x4 @@ -223,11 +225,14 @@ static bool qmp_message_empty(struct qmp *qmp) * * Return: 0 on success, negative errno on failure */ -static int qmp_send(struct qmp *qmp, const void *data, size_t len) +int qmp_send(struct qmp *qmp, const void *data, size_t len) { long time_left; int ret; + if (WARN_ON(IS_ERR_OR_NULL(qmp) || !data)) + return -EINVAL; + if (WARN_ON(len + sizeof(u32) > qmp->size)) return -EINVAL; @@ -261,6 +266,7 @@ static int qmp_send(struct qmp *qmp, const void *data, size_t len) return ret; } +EXPORT_SYMBOL(qmp_send); static int qmp_qdss_clk_prepare(struct clk_hw *hw) { @@ -519,6 +525,51 @@ static void qmp_cooling_devices_remove(struct qmp *qmp) thermal_cooling_device_unregister(qmp->cooling_devs[i].cdev); } +/** + * qmp_get() - get a qmp handle from a device + * @dev: client device pointer + * + * Return: handle to qmp device on success, ERR_PTR() on failure + */ +struct qmp *qmp_get(struct device *dev) +{ + struct platform_device *pdev; + struct device_node *np; + struct qmp *qmp; + + if (!dev || !dev->of_node) + return ERR_PTR(-EINVAL); + + np = of_parse_phandle(dev->of_node, "qcom,qmp", 0); + if (!np) + return ERR_PTR(-ENODEV); + + pdev = of_find_device_by_node(np); + of_node_put(np); + if (!pdev) + return ERR_PTR(-EINVAL); + + qmp = platform_get_drvdata(pdev); + + return qmp ? qmp : ERR_PTR(-EPROBE_DEFER); +} +EXPORT_SYMBOL(qmp_get); + +/** + * qmp_put() - release a qmp handle + * @qmp: qmp handle obtained from qmp_get() + */ +void qmp_put(struct qmp *qmp) +{ + /* + * Match get_device() inside of_find_device_by_node() in + * qmp_get() + */ + if (!IS_ERR_OR_NULL(qmp)) + put_device(qmp->dev); +} +EXPORT_SYMBOL(qmp_put); + static int qmp_probe(struct platform_device *pdev) { struct resource *res; @@ -615,6 +666,7 @@ static struct platform_driver qmp_driver = { .driver = { .name = "qcom_aoss_qmp", .of_match_table = qmp_dt_match, + .suppress_bind_attrs = true, }, .probe = qmp_probe, .remove = qmp_remove, diff --git a/include/linux/soc/qcom/qcom_aoss.h b/include/linux/soc/qcom/qcom_aoss.h new file mode 100644 index 000000000000..3c2a82e606f8 --- /dev/null +++ b/include/linux/soc/qcom/qcom_aoss.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef __QCOM_AOSS_H__ +#define __QCOM_AOSS_H__ + +#include +#include + +struct qmp; + +#if IS_ENABLED(CONFIG_QCOM_AOSS_QMP) + +int qmp_send(struct qmp *qmp, const void *data, size_t len); +struct qmp *qmp_get(struct device *dev); +void qmp_put(struct qmp *qmp); + +#else + +static inline int qmp_send(struct qmp *qmp, const void *data, size_t len) +{ + return -ENODEV; +} + +static inline struct qmp *qmp_get(struct device *dev) +{ + return ERR_PTR(-ENODEV); +} + +static inline void qmp_put(struct qmp *qmp) +{ +} + +#endif + +#endif -- cgit v1.2.3 From b468e688240b58ece498c430c377bb81b78a41f1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 14 Sep 2021 11:11:20 +0200 Subject: tty: remove flags from struct tty_ldisc_ops The last user was apparently removed by commit a352def21a64 (tty: Ldisc revamp) in 2008. So remove the field completely, the only setter (n_tty_inherit_ops) and also its only possible value (LDISC_FLAG_DEFINED). Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210914091134.17426-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/tty/n_tty.c | 1 - include/linux/tty_ldisc.h | 3 --- 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 0ec93f1a61f5..797af5d46cbe 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2450,7 +2450,6 @@ void n_tty_inherit_ops(struct tty_ldisc_ops *ops) { *ops = n_tty_ops; ops->owner = NULL; - ops->flags = 0; } EXPORT_SYMBOL_GPL(n_tty_inherit_ops); diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index b1d812e902aa..1f37184eee63 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -180,7 +180,6 @@ extern int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, struct tty_ldisc_ops { char *name; int num; - int flags; /* * The following routines are called from above. @@ -220,8 +219,6 @@ struct tty_ldisc { struct tty_struct *tty; }; -#define LDISC_FLAG_DEFINED 0x00000001 - #define MODULE_ALIAS_LDISC(ldisc) \ MODULE_ALIAS("tty-ldisc-" __stringify(ldisc)) -- cgit v1.2.3 From 7894193436b65f304ba790abe2532a7a3bbeb7c8 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 14 Sep 2021 11:11:21 +0200 Subject: tty: remove extern from functions in tty headers After the recent headers cleanup, some function declarations still have extern before them. It is superfluous (for function declarations), so remove extern from those which still have it. This unifies them with the rest of the files. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210914091134.17426-3-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 139 ++++++++++++++++++++++----------------------- include/linux/tty_driver.h | 8 +-- include/linux/tty_flip.h | 20 +++---- include/linux/tty_ldisc.h | 22 +++---- 4 files changed, 94 insertions(+), 95 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 168e57e40bbb..15453b0c4081 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -252,20 +252,20 @@ static inline bool tty_throttled(struct tty_struct *tty) } #ifdef CONFIG_TTY -extern void tty_kref_put(struct tty_struct *tty); -extern struct pid *tty_get_pgrp(struct tty_struct *tty); -extern void tty_vhangup_self(void); -extern void disassociate_ctty(int priv); -extern dev_t tty_devnum(struct tty_struct *tty); -extern void proc_clear_tty(struct task_struct *p); -extern struct tty_struct *get_current_tty(void); +void tty_kref_put(struct tty_struct *tty); +struct pid *tty_get_pgrp(struct tty_struct *tty); +void tty_vhangup_self(void); +void disassociate_ctty(int priv); +dev_t tty_devnum(struct tty_struct *tty); +void proc_clear_tty(struct task_struct *p); +struct tty_struct *get_current_tty(void); /* tty_io.c */ -extern int __init tty_init(void); -extern const char *tty_name(const struct tty_struct *tty); -extern struct tty_struct *tty_kopen_exclusive(dev_t device); -extern struct tty_struct *tty_kopen_shared(dev_t device); -extern void tty_kclose(struct tty_struct *tty); -extern int tty_dev_name_to_number(const char *name, dev_t *number); +int __init tty_init(void); +const char *tty_name(const struct tty_struct *tty); +struct tty_struct *tty_kopen_exclusive(dev_t device); +struct tty_struct *tty_kopen_shared(dev_t device); +void tty_kclose(struct tty_struct *tty); +int tty_dev_name_to_number(const char *name, dev_t *number); #else static inline void tty_kref_put(struct tty_struct *tty) { } @@ -296,7 +296,7 @@ static inline int tty_dev_name_to_number(const char *name, dev_t *number) extern struct ktermios tty_std_termios; -extern int vcs_init(void); +int vcs_init(void); extern struct class *tty_class; @@ -316,34 +316,34 @@ static inline struct tty_struct *tty_kref_get(struct tty_struct *tty) return tty; } -extern const char *tty_driver_name(const struct tty_struct *tty); -extern void tty_wait_until_sent(struct tty_struct *tty, long timeout); -extern void stop_tty(struct tty_struct *tty); -extern void start_tty(struct tty_struct *tty); -extern void tty_write_message(struct tty_struct *tty, char *msg); -extern int tty_send_xchar(struct tty_struct *tty, char ch); -extern int tty_put_char(struct tty_struct *tty, unsigned char c); -extern unsigned int tty_chars_in_buffer(struct tty_struct *tty); -extern unsigned int tty_write_room(struct tty_struct *tty); -extern void tty_driver_flush_buffer(struct tty_struct *tty); -extern void tty_unthrottle(struct tty_struct *tty); -extern int tty_throttle_safe(struct tty_struct *tty); -extern int tty_unthrottle_safe(struct tty_struct *tty); -extern int tty_do_resize(struct tty_struct *tty, struct winsize *ws); -extern int tty_get_icount(struct tty_struct *tty, - struct serial_icounter_struct *icount); -extern int is_current_pgrp_orphaned(void); -extern void tty_hangup(struct tty_struct *tty); -extern void tty_vhangup(struct tty_struct *tty); -extern int tty_hung_up_p(struct file *filp); -extern void do_SAK(struct tty_struct *tty); -extern void __do_SAK(struct tty_struct *tty); -extern void no_tty(void); -extern speed_t tty_termios_baud_rate(struct ktermios *termios); -extern void tty_termios_encode_baud_rate(struct ktermios *termios, - speed_t ibaud, speed_t obaud); -extern void tty_encode_baud_rate(struct tty_struct *tty, - speed_t ibaud, speed_t obaud); +const char *tty_driver_name(const struct tty_struct *tty); +void tty_wait_until_sent(struct tty_struct *tty, long timeout); +void stop_tty(struct tty_struct *tty); +void start_tty(struct tty_struct *tty); +void tty_write_message(struct tty_struct *tty, char *msg); +int tty_send_xchar(struct tty_struct *tty, char ch); +int tty_put_char(struct tty_struct *tty, unsigned char c); +unsigned int tty_chars_in_buffer(struct tty_struct *tty); +unsigned int tty_write_room(struct tty_struct *tty); +void tty_driver_flush_buffer(struct tty_struct *tty); +void tty_unthrottle(struct tty_struct *tty); +int tty_throttle_safe(struct tty_struct *tty); +int tty_unthrottle_safe(struct tty_struct *tty); +int tty_do_resize(struct tty_struct *tty, struct winsize *ws); +int tty_get_icount(struct tty_struct *tty, + struct serial_icounter_struct *icount); +int is_current_pgrp_orphaned(void); +void tty_hangup(struct tty_struct *tty); +void tty_vhangup(struct tty_struct *tty); +int tty_hung_up_p(struct file *filp); +void do_SAK(struct tty_struct *tty); +void __do_SAK(struct tty_struct *tty); +void no_tty(void); +speed_t tty_termios_baud_rate(struct ktermios *termios); +void tty_termios_encode_baud_rate(struct ktermios *termios, speed_t ibaud, + speed_t obaud); +void tty_encode_baud_rate(struct tty_struct *tty, speed_t ibaud, + speed_t obaud); /** * tty_get_baud_rate - get tty bit rates @@ -363,37 +363,37 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) unsigned char tty_get_char_size(unsigned int cflag); unsigned char tty_get_frame_size(unsigned int cflag); -extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); -extern int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); -extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); +void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); +int tty_termios_hw_change(const struct ktermios *a, const struct ktermios *b); +int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); -extern void tty_wakeup(struct tty_struct *tty); +void tty_wakeup(struct tty_struct *tty); -extern int tty_mode_ioctl(struct tty_struct *tty, struct file *file, +int tty_mode_ioctl(struct tty_struct *tty, struct file *file, unsigned int cmd, unsigned long arg); -extern int tty_perform_flush(struct tty_struct *tty, unsigned long arg); -extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); -extern void tty_release_struct(struct tty_struct *tty, int idx); -extern void tty_init_termios(struct tty_struct *tty); -extern void tty_save_termios(struct tty_struct *tty); -extern int tty_standard_install(struct tty_driver *driver, +int tty_perform_flush(struct tty_struct *tty, unsigned long arg); +struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); +void tty_release_struct(struct tty_struct *tty, int idx); +void tty_init_termios(struct tty_struct *tty); +void tty_save_termios(struct tty_struct *tty); +int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty); extern struct mutex tty_mutex; /* n_tty.c */ -extern void n_tty_inherit_ops(struct tty_ldisc_ops *ops); +void n_tty_inherit_ops(struct tty_ldisc_ops *ops); #ifdef CONFIG_TTY -extern void __init n_tty_init(void); +void __init n_tty_init(void); #else static inline void n_tty_init(void) { } #endif /* tty_audit.c */ #ifdef CONFIG_AUDIT -extern void tty_audit_exit(void); -extern void tty_audit_fork(struct signal_struct *sig); -extern int tty_audit_push(void); +void tty_audit_exit(void); +void tty_audit_fork(struct signal_struct *sig); +int tty_audit_push(void); #else static inline void tty_audit_exit(void) { @@ -408,24 +408,23 @@ static inline int tty_audit_push(void) #endif /* tty_ioctl.c */ -extern int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); +int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, + unsigned int cmd, unsigned long arg); /* vt.c */ -extern int vt_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg); +int vt_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg); -extern long vt_compat_ioctl(struct tty_struct *tty, - unsigned int cmd, unsigned long arg); +long vt_compat_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); /* tty_mutex.c */ /* functions for preparation of BKL removal */ -extern void tty_lock(struct tty_struct *tty); -extern int tty_lock_interruptible(struct tty_struct *tty); -extern void tty_unlock(struct tty_struct *tty); -extern void tty_lock_slave(struct tty_struct *tty); -extern void tty_unlock_slave(struct tty_struct *tty); -extern void tty_set_lock_subclass(struct tty_struct *tty); +void tty_lock(struct tty_struct *tty); +int tty_lock_interruptible(struct tty_struct *tty); +void tty_unlock(struct tty_struct *tty); +void tty_lock_slave(struct tty_struct *tty); +void tty_unlock_slave(struct tty_struct *tty); +void tty_set_lock_subclass(struct tty_struct *tty); #endif diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index c20431d8def8..29e1cf178afb 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -327,11 +327,11 @@ struct tty_driver { extern struct list_head tty_drivers; -extern struct tty_driver *__tty_alloc_driver(unsigned int lines, - struct module *owner, unsigned long flags); -extern struct tty_driver *tty_find_polling_driver(char *name, int *line); +struct tty_driver *__tty_alloc_driver(unsigned int lines, struct module *owner, + unsigned long flags); +struct tty_driver *tty_find_polling_driver(char *name, int *line); -extern void tty_driver_kref_put(struct tty_driver *driver); +void tty_driver_kref_put(struct tty_driver *driver); /* Use TTY_DRIVER_* flags below */ #define tty_alloc_driver(lines, flags) \ diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 32284992b31a..9916acb5de49 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -7,16 +7,16 @@ struct tty_ldisc; -extern int tty_buffer_set_limit(struct tty_port *port, int limit); -extern unsigned int tty_buffer_space_avail(struct tty_port *port); -extern int tty_buffer_request_room(struct tty_port *port, size_t size); -extern int tty_insert_flip_string_flags(struct tty_port *port, +int tty_buffer_set_limit(struct tty_port *port, int limit); +unsigned int tty_buffer_space_avail(struct tty_port *port); +int tty_buffer_request_room(struct tty_port *port, size_t size); +int tty_insert_flip_string_flags(struct tty_port *port, const unsigned char *chars, const char *flags, size_t size); -extern int tty_insert_flip_string_fixed_flag(struct tty_port *port, +int tty_insert_flip_string_fixed_flag(struct tty_port *port, const unsigned char *chars, char flag, size_t size); -extern int tty_prepare_flip_string(struct tty_port *port, - unsigned char **chars, size_t size); -extern void tty_flip_buffer_push(struct tty_port *port); +int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, + size_t size); +void tty_flip_buffer_push(struct tty_port *port); void tty_schedule_flip(struct tty_port *port); int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); @@ -45,7 +45,7 @@ static inline int tty_insert_flip_string(struct tty_port *port, int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p, const char *f, int count); -extern void tty_buffer_lock_exclusive(struct tty_port *port); -extern void tty_buffer_unlock_exclusive(struct tty_port *port); +void tty_buffer_lock_exclusive(struct tty_port *port); +void tty_buffer_unlock_exclusive(struct tty_port *port); #endif /* _LINUX_TTY_FLIP_H */ diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 1f37184eee63..4d1c128afbfa 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -146,7 +146,7 @@ struct ld_semaphore { #endif }; -extern void __init_ldsem(struct ld_semaphore *sem, const char *name, +void __init_ldsem(struct ld_semaphore *sem, const char *name, struct lock_class_key *key); #define init_ldsem(sem) \ @@ -157,18 +157,18 @@ do { \ } while (0) -extern int ldsem_down_read(struct ld_semaphore *sem, long timeout); -extern int ldsem_down_read_trylock(struct ld_semaphore *sem); -extern int ldsem_down_write(struct ld_semaphore *sem, long timeout); -extern int ldsem_down_write_trylock(struct ld_semaphore *sem); -extern void ldsem_up_read(struct ld_semaphore *sem); -extern void ldsem_up_write(struct ld_semaphore *sem); +int ldsem_down_read(struct ld_semaphore *sem, long timeout); +int ldsem_down_read_trylock(struct ld_semaphore *sem); +int ldsem_down_write(struct ld_semaphore *sem, long timeout); +int ldsem_down_write_trylock(struct ld_semaphore *sem); +void ldsem_up_read(struct ld_semaphore *sem); +void ldsem_up_write(struct ld_semaphore *sem); #ifdef CONFIG_DEBUG_LOCK_ALLOC -extern int ldsem_down_read_nested(struct ld_semaphore *sem, int subclass, - long timeout); -extern int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, - long timeout); +int ldsem_down_read_nested(struct ld_semaphore *sem, int subclass, + long timeout); +int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, + long timeout); #else # define ldsem_down_read_nested(sem, subclass, timeout) \ ldsem_down_read(sem, timeout) -- cgit v1.2.3 From 28f194da4a2c4d431552025a4386edaffab181bd Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 14 Sep 2021 11:11:22 +0200 Subject: tty: make tty_ldisc_ops::hangup return void The documentation says that the return value of tty_ldisc_ops::hangup hook is ignored. And it really is, so there is no point for its return type to be int. Switch it to void and all the hooks too. Cc: Dmitry Torokhov Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Paul Mackerras Cc: Liam Girdwood Cc: Mark Brown Cc: Jaroslav Kysela Cc: Takashi Iwai Cc: Peter Ujfalusi Acked-by: Dmitry Torokhov Acked-by: Mark Brown Acked-by: Marc Kleine-Budde Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210914091134.17426-4-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/serial/tty.rst | 2 +- drivers/input/serio/serport.c | 3 +-- drivers/net/can/slcan.c | 3 +-- drivers/net/ppp/ppp_async.c | 3 +-- drivers/net/ppp/ppp_synctty.c | 3 +-- drivers/net/slip/slip.c | 3 +-- include/linux/tty_ldisc.h | 2 +- sound/soc/codecs/cx20442.c | 3 +-- sound/soc/ti/ams-delta.c | 3 +-- 9 files changed, 9 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/serial/tty.rst b/Documentation/driver-api/serial/tty.rst index dd972caacf3e..4b709f392713 100644 --- a/Documentation/driver-api/serial/tty.rst +++ b/Documentation/driver-api/serial/tty.rst @@ -58,7 +58,7 @@ close() This is called on a terminal when the line hangup() Called when the tty line is hung up. The line discipline should cease I/O to the tty. No further calls into the ldisc code will occur. - The return value is ignored. Can sleep. + Can sleep. read() (optional) A process requests reading data from the line. Multiple read calls may occur in parallel diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index 7fbbe00e3553..17eb8f2aa48d 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -244,7 +244,7 @@ static int serport_ldisc_compat_ioctl(struct tty_struct *tty, } #endif -static int serport_ldisc_hangup(struct tty_struct *tty) +static void serport_ldisc_hangup(struct tty_struct *tty) { struct serport *serport = (struct serport *) tty->disc_data; unsigned long flags; @@ -254,7 +254,6 @@ static int serport_ldisc_hangup(struct tty_struct *tty) spin_unlock_irqrestore(&serport->lock, flags); wake_up_interruptible(&serport->wait); - return 0; } static void serport_ldisc_write_wakeup(struct tty_struct * tty) diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index d42ec7d1bc14..012da4b8abe0 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -664,10 +664,9 @@ static void slcan_close(struct tty_struct *tty) /* This will complete via sl_free_netdev */ } -static int slcan_hangup(struct tty_struct *tty) +static void slcan_hangup(struct tty_struct *tty) { slcan_close(tty); - return 0; } /* Perform I/O control on an active SLCAN channel. */ diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 29a93d6bfe37..78ec1bcebc4f 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -247,10 +247,9 @@ ppp_asynctty_close(struct tty_struct *tty) * Wait for I/O to driver to complete and unregister PPP channel. * This is already done by the close routine, so just call that. */ -static int ppp_asynctty_hangup(struct tty_struct *tty) +static void ppp_asynctty_hangup(struct tty_struct *tty) { ppp_asynctty_close(tty); - return 0; } /* diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index af3e048695b6..c249db7c466a 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -245,10 +245,9 @@ ppp_sync_close(struct tty_struct *tty) * Wait for I/O to driver to complete and unregister PPP channel. * This is already done by the close routine, so just call that. */ -static int ppp_sync_hangup(struct tty_struct *tty) +static void ppp_sync_hangup(struct tty_struct *tty) { ppp_sync_close(tty); - return 0; } /* diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 5435b5689ce6..8be9d0c351b5 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -907,10 +907,9 @@ static void slip_close(struct tty_struct *tty) /* This will complete via sl_free_netdev */ } -static int slip_hangup(struct tty_struct *tty) +static void slip_hangup(struct tty_struct *tty) { slip_close(tty); - return 0; } /************************************************************************ * STANDARD SLIP ENCAPSULATION * diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 4d1c128afbfa..b85d84fb5f49 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -199,7 +199,7 @@ struct tty_ldisc_ops { void (*set_termios)(struct tty_struct *tty, struct ktermios *old); __poll_t (*poll)(struct tty_struct *, struct file *, struct poll_table_struct *); - int (*hangup)(struct tty_struct *tty); + void (*hangup)(struct tty_struct *tty); /* * The following routines are called from below. diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c index 13258f3ca9aa..1af0bf5f1e2f 100644 --- a/sound/soc/codecs/cx20442.c +++ b/sound/soc/codecs/cx20442.c @@ -252,10 +252,9 @@ static void v253_close(struct tty_struct *tty) } /* Line discipline .hangup() */ -static int v253_hangup(struct tty_struct *tty) +static void v253_hangup(struct tty_struct *tty) { v253_close(tty); - return 0; } /* Line discipline .receive_buf() */ diff --git a/sound/soc/ti/ams-delta.c b/sound/soc/ti/ams-delta.c index ecd24d412a9b..b1a32545babd 100644 --- a/sound/soc/ti/ams-delta.c +++ b/sound/soc/ti/ams-delta.c @@ -330,10 +330,9 @@ static void cx81801_close(struct tty_struct *tty) } /* Line discipline .hangup() */ -static int cx81801_hangup(struct tty_struct *tty) +static void cx81801_hangup(struct tty_struct *tty) { cx81801_close(tty); - return 0; } /* Line discipline .receive_buf() */ -- cgit v1.2.3 From dcc223e8b9bf3f987bcd3c327a6737022b39e35b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 14 Sep 2021 11:11:23 +0200 Subject: tty: remove file from tty_mode_ioctl The only user of 'file' parameter in tty_mode_ioctl is a BUG_ON check. Provided it never crashed for anyone, it's an overkill to pass the parameter to tty_mode_ioctl only for this check. If we wanted to check 'file' there, we should handle it in more graceful way anyway. Not by a BUG == crash. Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Andreas Koensgen Cc: Paul Mackerras Acked-by: Marc Kleine-Budde Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210914091134.17426-5-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/net/can/slcan.c | 2 +- drivers/net/hamradio/6pack.c | 2 +- drivers/net/ppp/ppp_async.c | 2 +- drivers/net/ppp/ppp_synctty.c | 2 +- drivers/net/slip/slip.c | 2 +- drivers/tty/tty_ioctl.c | 8 ++------ include/linux/tty.h | 3 +-- 7 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 012da4b8abe0..9a4ebda30510 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -691,7 +691,7 @@ static int slcan_ioctl(struct tty_struct *tty, struct file *file, return -EINVAL; default: - return tty_mode_ioctl(tty, file, cmd, arg); + return tty_mode_ioctl(tty, cmd, arg); } } diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 8fe8887d506a..05404f7a3204 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -732,7 +732,7 @@ static int sixpack_ioctl(struct tty_struct *tty, struct file *file, break; } default: - err = tty_mode_ioctl(tty, file, cmd, arg); + err = tty_mode_ioctl(tty, cmd, arg); } sp_put(sp); diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 78ec1bcebc4f..6492523fc234 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -322,7 +322,7 @@ ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file, default: /* Try the various mode ioctls */ - err = tty_mode_ioctl(tty, file, cmd, arg); + err = tty_mode_ioctl(tty, cmd, arg); } ap_put(ap); diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index c249db7c466a..ebbfea0e1140 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -314,7 +314,7 @@ ppp_synctty_ioctl(struct tty_struct *tty, struct file *file, break; default: - err = tty_mode_ioctl(tty, file, cmd, arg); + err = tty_mode_ioctl(tty, cmd, arg); break; } diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 8be9d0c351b5..9f3b4c1aa5ce 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -1173,7 +1173,7 @@ static int slip_ioctl(struct tty_struct *tty, struct file *file, /* VSV changes end */ #endif default: - return tty_mode_ioctl(tty, file, cmd, arg); + return tty_mode_ioctl(tty, cmd, arg); } } diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 507a25d692bb..99a29d72d294 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -675,7 +675,6 @@ static int tty_change_softcar(struct tty_struct *tty, int arg) /** * tty_mode_ioctl - mode related ioctls * @tty: tty for the ioctl - * @file: file pointer for the tty * @cmd: command * @arg: ioctl argument * @@ -684,16 +683,13 @@ static int tty_change_softcar(struct tty_struct *tty, int arg) * consistent mode setting. */ -int tty_mode_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct tty_struct *real_tty; void __user *p = (void __user *)arg; int ret = 0; struct ktermios kterm; - BUG_ON(file == NULL); - if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) real_tty = tty->link; @@ -904,7 +900,7 @@ int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, return __tty_perform_flush(tty, arg); default: /* Try the mode commands */ - return tty_mode_ioctl(tty, file, cmd, arg); + return tty_mode_ioctl(tty, cmd, arg); } } EXPORT_SYMBOL(n_tty_ioctl_helper); diff --git a/include/linux/tty.h b/include/linux/tty.h index 15453b0c4081..5e73f577c2b4 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -369,8 +369,7 @@ int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); void tty_wakeup(struct tty_struct *tty); -int tty_mode_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); +int tty_mode_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg); int tty_perform_flush(struct tty_struct *tty, unsigned long arg); struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx); void tty_release_struct(struct tty_struct *tty, int idx); -- cgit v1.2.3 From 7c783601a3bc22a54cce0fb650259a983c8cafba Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Tue, 14 Sep 2021 11:11:24 +0200 Subject: tty: remove file from n_tty_ioctl_helper After the previous patch, there are no users of 'file' in n_tty_ioctl_helper. So remove it also from there. Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Cc: Paul Mackerras Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Krzysztof Kozlowski Acked-by: Krzysztof Kozlowski Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20210914091134.17426-6-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_ldisc.c | 2 +- drivers/net/ppp/ppp_async.c | 2 +- drivers/net/ppp/ppp_synctty.c | 2 +- drivers/tty/n_gsm.c | 2 +- drivers/tty/n_hdlc.c | 2 +- drivers/tty/n_tty.c | 2 +- drivers/tty/tty_ioctl.c | 4 ++-- include/linux/tty.h | 4 ++-- net/nfc/nci/uart.c | 2 +- 9 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 5ed2cfa7da1d..824d1c7e3e53 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -790,7 +790,7 @@ static int hci_uart_tty_ioctl(struct tty_struct *tty, struct file *file, break; default: - err = n_tty_ioctl_helper(tty, file, cmd, arg); + err = n_tty_ioctl_helper(tty, cmd, arg); break; } diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index 6492523fc234..f4429b93a9c8 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -310,7 +310,7 @@ ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file, /* flush our buffers and the serial port's buffer */ if (arg == TCIOFLUSH || arg == TCOFLUSH) ppp_async_flush_output(ap); - err = n_tty_ioctl_helper(tty, file, cmd, arg); + err = n_tty_ioctl_helper(tty, cmd, arg); break; case FIONREAD: diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index ebbfea0e1140..b3a71b409a80 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -303,7 +303,7 @@ ppp_synctty_ioctl(struct tty_struct *tty, struct file *file, /* flush our buffers and the serial port's buffer */ if (arg == TCIOFLUSH || arg == TCOFLUSH) ppp_sync_flush_output(ap); - err = n_tty_ioctl_helper(tty, file, cmd, arg); + err = n_tty_ioctl_helper(tty, cmd, arg); break; case FIONREAD: diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 157b51ce9cc0..c98a04595084 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2712,7 +2712,7 @@ static int gsmld_ioctl(struct tty_struct *tty, struct file *file, base = mux_num_to_base(gsm); return put_user(base + 1, (__u32 __user *)arg); default: - return n_tty_ioctl_helper(tty, file, cmd, arg); + return n_tty_ioctl_helper(tty, cmd, arg); } } diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 580a37b3fe1b..7e0884ecc74f 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -630,7 +630,7 @@ static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, fallthrough; /* to default */ default: - error = n_tty_ioctl_helper(tty, file, cmd, arg); + error = n_tty_ioctl_helper(tty, cmd, arg); break; } return error; diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 797af5d46cbe..5be6d02dc690 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2418,7 +2418,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file, up_write(&tty->termios_rwsem); return put_user(retval, (unsigned int __user *) arg); default: - return n_tty_ioctl_helper(tty, file, cmd, arg); + return n_tty_ioctl_helper(tty, cmd, arg); } } diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 99a29d72d294..63181925ec1a 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -854,8 +854,8 @@ int tty_perform_flush(struct tty_struct *tty, unsigned long arg) } EXPORT_SYMBOL_GPL(tty_perform_flush); -int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +int n_tty_ioctl_helper(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { int retval; diff --git a/include/linux/tty.h b/include/linux/tty.h index 5e73f577c2b4..5dbd7c5afac7 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -407,8 +407,8 @@ static inline int tty_audit_push(void) #endif /* tty_ioctl.c */ -int n_tty_ioctl_helper(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); +int n_tty_ioctl_helper(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); /* vt.c */ diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 502e7a3f8948..9bdd9a7d187e 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -349,7 +349,7 @@ static int nci_uart_tty_ioctl(struct tty_struct *tty, struct file *file, return -EBUSY; break; default: - err = n_tty_ioctl_helper(tty, file, cmd, arg); + err = n_tty_ioctl_helper(tty, cmd, arg); break; } -- cgit v1.2.3 From 3229b906fb35b63515f0c703b917357c83e1ea22 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 16 Sep 2021 20:15:57 +0200 Subject: lib: devres: Add managed arch_phys_wc_add() Add devm_arch_phys_wc_add() as managed wrapper around arch_phys_wc_add(). Useful for several graphics drivers that set framebuffer memory to write combining. v2: * fix typo in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20210916181601.9146-2-tzimmermann@suse.de --- include/linux/io.h | 2 ++ lib/devres.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index 9595151d800d..fcd8ea79c5df 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -132,6 +132,8 @@ static inline int arch_phys_wc_index(int handle) #endif #endif +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size); + enum { /* See memremap() kernel-doc for usage description... */ MEMREMAP_WB = 1 << 0, diff --git a/lib/devres.c b/lib/devres.c index b0e1c6702c71..24d4d849ff67 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -528,3 +528,39 @@ void pcim_iounmap_regions(struct pci_dev *pdev, int mask) } EXPORT_SYMBOL(pcim_iounmap_regions); #endif /* CONFIG_PCI */ + +static void devm_arch_phys_ac_add_release(struct device *dev, void *res) +{ + arch_phys_wc_del(*((int *)res)); +} + +/** + * devm_arch_phys_wc_add - Managed arch_phys_wc_add() + * @dev: Managed device + * @base: Memory base address + * @size: Size of memory range + * + * Adds a WC MTRR using arch_phys_wc_add() and sets up a release callback. + * See arch_phys_wc_add() for more information. + */ +int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long size) +{ + int *mtrr; + int ret; + + mtrr = devres_alloc(devm_arch_phys_ac_add_release, sizeof(*mtrr), GFP_KERNEL); + if (!mtrr) + return -ENOMEM; + + ret = arch_phys_wc_add(base, size); + if (ret < 0) { + devres_free(mtrr); + return ret; + } + + *mtrr = ret; + devres_add(dev, mtrr); + + return ret; +} +EXPORT_SYMBOL(devm_arch_phys_wc_add); -- cgit v1.2.3 From c822310725ee41af663de2448094155d442ff871 Mon Sep 17 00:00:00 2001 From: Thomas Zimmermann Date: Thu, 16 Sep 2021 20:15:58 +0200 Subject: lib: devres: Add managed arch_io_reserve_memtype_wc() Add devm_arch_io_reserve_memtype_wc() as managed wrapper around arch_io_reserve_memtype_wc(). Useful for several graphics drivers that set framebuffer memory to write combining. v2: * fix typo in commit description Signed-off-by: Thomas Zimmermann Reviewed-by: Hans de Goede Link: https://patchwork.freedesktop.org/patch/msgid/20210916181601.9146-3-tzimmermann@suse.de --- include/linux/io.h | 3 +++ lib/devres.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+) (limited to 'include/linux') diff --git a/include/linux/io.h b/include/linux/io.h index fcd8ea79c5df..5fc800390fe4 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -168,4 +168,7 @@ static inline void arch_io_free_memtype_wc(resource_size_t base, } #endif +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size); + #endif /* _LINUX_IO_H */ diff --git a/lib/devres.c b/lib/devres.c index 24d4d849ff67..14664bbb4875 100644 --- a/lib/devres.c +++ b/lib/devres.c @@ -564,3 +564,49 @@ int devm_arch_phys_wc_add(struct device *dev, unsigned long base, unsigned long return ret; } EXPORT_SYMBOL(devm_arch_phys_wc_add); + +struct arch_io_reserve_memtype_wc_devres { + resource_size_t start; + resource_size_t size; +}; + +static void devm_arch_io_free_memtype_wc_release(struct device *dev, void *res) +{ + const struct arch_io_reserve_memtype_wc_devres *this = res; + + arch_io_free_memtype_wc(this->start, this->size); +} + +/** + * devm_arch_io_reserve_memtype_wc - Managed arch_io_reserve_memtype_wc() + * @dev: Managed device + * @start: Memory base address + * @size: Size of memory range + * + * Reserves a memory range with WC caching using arch_io_reserve_memtype_wc() + * and sets up a release callback See arch_io_reserve_memtype_wc() for more + * information. + */ +int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start, + resource_size_t size) +{ + struct arch_io_reserve_memtype_wc_devres *dr; + int ret; + + dr = devres_alloc(devm_arch_io_free_memtype_wc_release, sizeof(*dr), GFP_KERNEL); + if (!dr) + return -ENOMEM; + + ret = arch_io_reserve_memtype_wc(start, size); + if (ret < 0) { + devres_free(dr); + return ret; + } + + dr->start = start; + dr->size = size; + devres_add(dev, dr); + + return ret; +} +EXPORT_SYMBOL(devm_arch_io_reserve_memtype_wc); -- cgit v1.2.3 From 23c64d7618a7e76e46db99444d184ef75498fb71 Mon Sep 17 00:00:00 2001 From: Piyush Mehta Date: Wed, 22 Sep 2021 19:23:17 +0530 Subject: firmware: zynqmp: Add MMIO read and write support for PS_MODE pin Add Xilinx ZynqMP firmware MMIO APIs support to set and get PS_MODE pins value and status. These APIs create an interface path between mode pin controller driver and low-level API to access GPIO pins. Signed-off-by: Piyush Mehta Acked-by: Michal Simek Acked-by: Linus Walleij Signed-off-by: Bartosz Golaszewski --- drivers/firmware/xilinx/zynqmp.c | 46 ++++++++++++++++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 14 +++++++++++ 2 files changed, 60 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index a3cadbaf3cba..7feba125b883 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -28,6 +28,13 @@ /* Max HashMap Order for PM API feature check (1<<7 = 128) */ #define PM_API_FEATURE_CHECK_MAX_ORDER 7 +/* CRL registers and bitfields */ +#define CRL_APB_BASE 0xFF5E0000U +/* BOOT_PIN_CTRL- Used to control the mode pins after boot */ +#define CRL_APB_BOOT_PIN_CTRL (CRL_APB_BASE + (0x250U)) +/* BOOT_PIN_CTRL_MASK- out_val[11:8], out_en[3:0] */ +#define CRL_APB_BOOTPIN_CTRL_MASK 0xF0FU + static bool feature_check_enabled; static DEFINE_HASHTABLE(pm_api_features_map, PM_API_FEATURE_CHECK_MAX_ORDER); @@ -925,6 +932,45 @@ int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, } EXPORT_SYMBOL_GPL(zynqmp_pm_pinctrl_set_config); +/** + * zynqmp_pm_bootmode_read() - PM Config API for read bootpin status + * @ps_mode: Returned output value of ps_mode + * + * This API function is to be used for notify the power management controller + * to read bootpin status. + * + * Return: status, either success or error+reason + */ +unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode) +{ + unsigned int ret; + u32 ret_payload[PAYLOAD_ARG_CNT]; + + ret = zynqmp_pm_invoke_fn(PM_MMIO_READ, CRL_APB_BOOT_PIN_CTRL, 0, + 0, 0, ret_payload); + + *ps_mode = ret_payload[1]; + + return ret; +} +EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_read); + +/** + * zynqmp_pm_bootmode_write() - PM Config API for Configure bootpin + * @ps_mode: Value to be written to the bootpin ctrl register + * + * This API function is to be used for notify the power management controller + * to configure bootpin. + * + * Return: Returns status, either success or error+reason + */ +int zynqmp_pm_bootmode_write(u32 ps_mode) +{ + return zynqmp_pm_invoke_fn(PM_MMIO_WRITE, CRL_APB_BOOT_PIN_CTRL, + CRL_APB_BOOTPIN_CTRL_MASK, ps_mode, 0, NULL); +} +EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write); + /** * zynqmp_pm_init_finalize() - PM call to inform firmware that the caller * master has initialized its own power management diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 56b426fe020c..3917f89b2b3c 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -72,6 +72,8 @@ enum pm_api_id { PM_SET_REQUIREMENT = 15, PM_RESET_ASSERT = 17, PM_RESET_GET_STATUS = 18, + PM_MMIO_WRITE = 19, + PM_MMIO_READ = 20, PM_PM_INIT_FINALIZE = 21, PM_FPGA_LOAD = 22, PM_FPGA_GET_STATUS = 23, @@ -390,6 +392,8 @@ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); +unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode); +int zynqmp_pm_bootmode_write(u32 ps_mode); int zynqmp_pm_init_finalize(void); int zynqmp_pm_set_suspend_mode(u32 mode); int zynqmp_pm_request_node(const u32 node, const u32 capabilities, @@ -520,6 +524,16 @@ static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, return -ENODEV; } +static inline unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode) +{ + return -ENODEV; +} + +static inline int zynqmp_pm_bootmode_write(u32 ps_mode) +{ + return -ENODEV; +} + static inline int zynqmp_pm_init_finalize(void) { return -ENODEV; -- cgit v1.2.3 From 68a81bb2eebdeaabb04ae04c4d89c3bb5bec3b32 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 22 Sep 2021 16:57:03 +0300 Subject: net: dsa: sja1105: remove sp->dp It looks like this field was never used since its introduction in commit 227d07a07ef1 ("net: dsa: sja1105: Add support for traffic through standalone ports") remove it. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 1 - include/linux/dsa/sja1105.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 2f8cc6686c38..7ce69dc07800 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2965,7 +2965,6 @@ static int sja1105_setup_ports(struct sja1105_private *priv) continue; dp->priv = sp; - sp->dp = dp; sp->data = tagger_data; slave = dp->slave; kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 171106202fe5..71b69ec52108 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -65,7 +65,6 @@ struct sja1105_port { struct kthread_work xmit_work; struct sk_buff_head xmit_queue; struct sja1105_tagger_data *data; - struct dsa_port *dp; bool hwts_tx_en; }; -- cgit v1.2.3 From 6d709cadfde68dbd12bef12fcced6222226dcb06 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 22 Sep 2021 17:37:25 +0300 Subject: net: dsa: move sja1110_process_meta_tstamp inside the tagging protocol driver The problem is that DSA tagging protocols really must not depend on the switch driver, because this creates a circular dependency at insmod time, and the switch driver will effectively not load when the tagging protocol driver is missing. The code was structured in the way it was for a reason, though. The DSA driver-facing API for PTP timestamping relies on the assumption that two-step TX timestamps are provided by the hardware in an out-of-band manner, typically by raising an interrupt and making that timestamp available inside some sort of FIFO which is to be accessed over SPI/MDIO/etc. So the API puts .port_txtstamp into dsa_switch_ops, because it is expected that the switch driver needs to save some state (like put the skb into a queue until its TX timestamp arrives). On SJA1110, TX timestamps are provided by the switch as Ethernet packets, so this makes them be received and processed by the tagging protocol driver. This in itself is great, because the timestamps are full 64-bit and do not require reconstruction, and since Ethernet is the fastest I/O method available to/from the switch, PTP timestamps arrive very quickly, no matter how bottlenecked the SPI connection is, because SPI interaction is not needed at all. DSA's code structure and strict isolation between the tagging protocol driver and the switch driver break the natural code organization. When the tagging protocol driver receives a packet which is classified as a metadata packet containing timestamps, it passes those timestamps one by one to the switch driver, which then proceeds to compare them based on the recorded timestamp ID that was generated in .port_txtstamp. The communication between the tagging protocol and the switch driver is done through a method exported by the switch driver, sja1110_process_meta_tstamp. To satisfy build requirements, we force a dependency to build the tagging protocol driver as a module when the switch driver is a module. However, as explained in the first paragraph, that causes the circular dependency. To solve this, move the skb queue from struct sja1105_private :: struct sja1105_ptp_data to struct sja1105_private :: struct sja1105_tagger_data. The latter is a data structure for which hacks have already been put into place to be able to create persistent storage per switch that is accessible from the tagging protocol driver (see sja1105_setup_ports). With the skb queue directly accessible from the tagging protocol driver, we can now move sja1110_process_meta_tstamp into the tagging driver itself, and avoid exporting a symbol. Fixes: 566b18c8b752 ("net: dsa: sja1105: implement TX timestamping for SJA1110") Link: https://lore.kernel.org/netdev/20210908220834.d7gmtnwrorhharna@skbuf/ Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_ptp.c | 45 +++++------------------------------ drivers/net/dsa/sja1105/sja1105_ptp.h | 19 --------------- include/linux/dsa/sja1105.h | 29 +++++++++++----------- net/dsa/tag_sja1105.c | 43 +++++++++++++++++++++++++++++++++ 4 files changed, 63 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 691f6dd7e669..54396992a919 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -64,6 +64,7 @@ enum sja1105_ptp_clk_mode { static int sja1105_change_rxtstamping(struct sja1105_private *priv, bool on) { + struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; struct sja1105_general_params_entry *general_params; struct sja1105_table *table; @@ -79,7 +80,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, priv->tagger_data.stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&ptp_data->skb_txtstamp_queue); + skb_queue_purge(&tagger_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -452,40 +453,6 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return priv->info->rxtstamp(ds, port, skb); } -void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, - enum sja1110_meta_tstamp dir, u64 tstamp) -{ - struct sja1105_private *priv = ds->priv; - struct sja1105_ptp_data *ptp_data = &priv->ptp_data; - struct sk_buff *skb, *skb_tmp, *skb_match = NULL; - struct skb_shared_hwtstamps shwt = {0}; - - /* We don't care about RX timestamps on the CPU port */ - if (dir == SJA1110_META_TSTAMP_RX) - return; - - spin_lock(&ptp_data->skb_txtstamp_queue.lock); - - skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { - if (SJA1105_SKB_CB(skb)->ts_id != ts_id) - continue; - - __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); - skb_match = skb; - - break; - } - - spin_unlock(&ptp_data->skb_txtstamp_queue.lock); - - if (WARN_ON(!skb_match)) - return; - - shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); - skb_complete_tx_timestamp(skb_match, &shwt); -} -EXPORT_SYMBOL_GPL(sja1110_process_meta_tstamp); - /* In addition to cloning the skb which is done by the common * sja1105_port_txtstamp, we need to generate a timestamp ID and save the * packet to the TX timestamping queue. @@ -494,7 +461,6 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct sja1105_private *priv = ds->priv; - struct sja1105_ptp_data *ptp_data = &priv->ptp_data; struct sja1105_port *sp = &priv->ports[port]; u8 ts_id; @@ -510,7 +476,7 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) spin_unlock(&sp->data->meta_lock); - skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); + skb_queue_tail(&sp->data->skb_txtstamp_queue, clone); } /* Called from dsa_skb_tx_timestamp. This callback is just to clone @@ -953,7 +919,7 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); /* Only used on SJA1110 */ - skb_queue_head_init(&ptp_data->skb_txtstamp_queue); + skb_queue_head_init(&tagger_data->skb_txtstamp_queue); spin_lock_init(&tagger_data->meta_lock); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); @@ -971,6 +937,7 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) void sja1105_ptp_clock_unregister(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; + struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; if (IS_ERR_OR_NULL(ptp_data->clock)) @@ -978,7 +945,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&ptp_data->skb_txtstamp_queue); + skb_queue_purge(&tagger_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 3c874bb4c17b..3ae6b9fdd492 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -8,21 +8,6 @@ #if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) -/* Timestamps are in units of 8 ns clock ticks (equivalent to - * a fixed 125 MHz clock). - */ -#define SJA1105_TICK_NS 8 - -static inline s64 ns_to_sja1105_ticks(s64 ns) -{ - return ns / SJA1105_TICK_NS; -} - -static inline s64 sja1105_ticks_to_ns(s64 ticks) -{ - return ticks * SJA1105_TICK_NS; -} - /* Calculate the first base_time in the future that satisfies this * relationship: * @@ -77,10 +62,6 @@ struct sja1105_ptp_data { struct timer_list extts_timer; /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; - /* Used on SJA1110 where meta frames are generated only for - * 2-step TX timestamps - */ - struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 71b69ec52108..9d5a1053b276 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -48,6 +48,10 @@ struct sja1105_tagger_data { spinlock_t meta_lock; unsigned long state; u8 ts_id; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; }; struct sja1105_skb_cb { @@ -68,25 +72,20 @@ struct sja1105_port { bool hwts_tx_en; }; -enum sja1110_meta_tstamp { - SJA1110_META_TSTAMP_TX = 0, - SJA1110_META_TSTAMP_RX = 1, -}; - -#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) - -void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, - enum sja1110_meta_tstamp dir, u64 tstamp); - -#else +/* Timestamps are in units of 8 ns clock ticks (equivalent to + * a fixed 125 MHz clock). + */ +#define SJA1105_TICK_NS 8 -static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, - u8 ts_id, enum sja1110_meta_tstamp dir, - u64 tstamp) +static inline s64 ns_to_sja1105_ticks(s64 ns) { + return ns / SJA1105_TICK_NS; } -#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ +static inline s64 sja1105_ticks_to_ns(s64 ticks) +{ + return ticks * SJA1105_TICK_NS; +} #if IS_ENABLED(CONFIG_NET_DSA_SJA1105) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index c054f48541c8..2edede9ddac9 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include "dsa_priv.h" @@ -53,6 +54,11 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -520,6 +526,43 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct dsa_port *dp = dsa_to_port(ds, port); + struct skb_shared_hwtstamps shwt = {0}; + struct sja1105_port *sp = dp->priv; + + if (!dsa_port_is_sja1105(dp)) + return; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&sp->data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&sp->data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &sp->data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&sp->data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} + static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) { u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN; -- cgit v1.2.3 From f5aef4241592765a868611509e5170bbe8c89ae7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 22 Sep 2021 17:37:26 +0300 Subject: net: dsa: sja1105: break dependency between dsa_port_is_sja1105 and switch driver It's nice to be able to test a tagging protocol with dsa_loop, but not at the cost of losing the ability of building the tagging protocol and switch driver as modules, because as things stand, there is a circular dependency between the two. Tagging protocol drivers cannot depend on switch drivers, that is a hard fact. The reasoning behind the blamed patch was that accessing dp->priv should first make sure that the structure behind that pointer is what we really think it is. Currently the "sja1105" and "sja1110" tagging protocols only operate with the sja1105 switch driver, just like any other tagging protocol and switch combination. The only way to mix and match them is by modifying the code, and this applies to dsa_loop as well (by default that uses DSA_TAG_PROTO_NONE). So while in principle there is an issue, in practice there isn't one. Until we extend dsa_loop to allow user space configuration, treat the problem as a non-issue and just say that DSA ports found by tag_sja1105 are always sja1105 ports, which is in fact true. But keep the dsa_port_is_sja1105 function so that it's easy to patch it during testing, and rely on dead code elimination. Fixes: 994d2cbb08ca ("net: dsa: tag_sja1105: be dsa_loop-safe") Link: https://lore.kernel.org/netdev/20210908220834.d7gmtnwrorhharna@skbuf/ Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 3 +-- include/linux/dsa/sja1105.h | 15 +-------------- net/dsa/Kconfig | 1 - 3 files changed, 2 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 7ce69dc07800..d5f8166b73b1 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3116,7 +3116,7 @@ static void sja1105_teardown(struct dsa_switch *ds) sja1105_static_config_free(&priv->static_config); } -const struct dsa_switch_ops sja1105_switch_ops = { +static const struct dsa_switch_ops sja1105_switch_ops = { .get_tag_protocol = sja1105_get_tag_protocol, .setup = sja1105_setup, .teardown = sja1105_teardown, @@ -3165,7 +3165,6 @@ const struct dsa_switch_ops sja1105_switch_ops = { .port_bridge_tx_fwd_offload = dsa_tag_8021q_bridge_tx_fwd_offload, .port_bridge_tx_fwd_unoffload = dsa_tag_8021q_bridge_tx_fwd_unoffload, }; -EXPORT_SYMBOL_GPL(sja1105_switch_ops); static const struct of_device_id sja1105_dt_ids[]; diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 9d5a1053b276..e6c78be40bde 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -87,22 +87,9 @@ static inline s64 sja1105_ticks_to_ns(s64 ticks) return ticks * SJA1105_TICK_NS; } -#if IS_ENABLED(CONFIG_NET_DSA_SJA1105) - -extern const struct dsa_switch_ops sja1105_switch_ops; - -static inline bool dsa_port_is_sja1105(struct dsa_port *dp) -{ - return dp->ds->ops == &sja1105_switch_ops; -} - -#else - static inline bool dsa_port_is_sja1105(struct dsa_port *dp) { - return false; + return true; } -#endif - #endif /* _NET_DSA_SJA1105_H */ diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 548285539752..bca1b5d66df2 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -138,7 +138,6 @@ config NET_DSA_TAG_LAN9303 config NET_DSA_TAG_SJA1105 tristate "Tag driver for NXP SJA1105 switches" - depends on NET_DSA_SJA1105 || !NET_DSA_SJA1105 select PACKING help Say Y or M if you want to enable support for tagging frames with the -- cgit v1.2.3 From d50497c4a05e73e76874fd0d4942036375a7ec0f Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 15 Sep 2021 18:46:27 -0700 Subject: platform/chrome: cros_ec_proto: Fix check_features ret val The kerneldoc for cros_ec_check_features() states that it returns 1 or 0 depedending on whether a feature is supported or not, but it instead returns a negative error number in one case, and a non-1 bitmask in other cases. Since all call-sites only check for a 1 or 0 return value, update the function to return boolean values. Signed-off-by: Prashant Malani Reviewed-by: Guenter Roeck Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210916014632.2662612-1-pmalani@chromium.org --- drivers/platform/chrome/cros_ec_proto.c | 12 +++++++----- include/linux/platform_data/cros_ec_proto.h | 2 +- 2 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index a7404d69b2d3..a34cf58c5ef7 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -808,9 +808,9 @@ EXPORT_SYMBOL(cros_ec_get_host_event); * * Call this function to test whether the ChromeOS EC supports a feature. * - * Return: 1 if supported, 0 if not + * Return: true if supported, false if not (or if an error was encountered). */ -int cros_ec_check_features(struct cros_ec_dev *ec, int feature) +bool cros_ec_check_features(struct cros_ec_dev *ec, int feature) { struct cros_ec_command *msg; int ret; @@ -818,8 +818,10 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature) if (ec->features[0] == -1U && ec->features[1] == -1U) { /* features bitmap not read yet */ msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); - if (!msg) - return -ENOMEM; + if (!msg) { + dev_err(ec->dev, "failed to allocate memory to get EC features\n"); + return false; + } msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; msg->insize = sizeof(ec->features); @@ -839,7 +841,7 @@ int cros_ec_check_features(struct cros_ec_dev *ec, int feature) kfree(msg); } - return ec->features[feature / 32] & EC_FEATURE_MASK_0(feature); + return !!(ec->features[feature / 32] & EC_FEATURE_MASK_0(feature)); } EXPORT_SYMBOL_GPL(cros_ec_check_features); diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 02599687770c..55844ece0b32 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -227,7 +227,7 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev, u32 cros_ec_get_host_event(struct cros_ec_device *ec_dev); -int cros_ec_check_features(struct cros_ec_dev *ec, int feature); +bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -- cgit v1.2.3 From 3fd445a4d49fce594eecc90b9bbcf85cd223154d Mon Sep 17 00:00:00 2001 From: Len Baker Date: Sat, 4 Sep 2021 11:22:17 +0200 Subject: brcmfmac: Replace zero-length array with flexible array member There is a regular need in the kernel to provide a way to declare having a dynamically sized set of trailing elements in a structure. Kernel code should always use "flexible array members"[1] for these cases. The older style of one-element or zero-length arrays should no longer be used[2]. Also, make use of the struct_size() helper in devm_kzalloc(). [1] https://en.wikipedia.org/wiki/Flexible_array_member [2] https://www.kernel.org/doc/html/v5.14/process/deprecated.html#zero-length-and-one-element-arrays Signed-off-by: Len Baker Reviewed-by: Gustavo A. R. Silva Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210904092217.2848-1-len.baker@gmx.com --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c | 2 +- include/linux/platform_data/brcmfmac.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index 2f7bc3a70c65..513c7e6421b2 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -29,7 +29,7 @@ static int brcmf_of_get_country_codes(struct device *dev, return (count == -EINVAL) ? 0 : count; } - cc = devm_kzalloc(dev, sizeof(*cc) + count * sizeof(*cce), GFP_KERNEL); + cc = devm_kzalloc(dev, struct_size(cc, table, count), GFP_KERNEL); if (!cc) return -ENOMEM; diff --git a/include/linux/platform_data/brcmfmac.h b/include/linux/platform_data/brcmfmac.h index 1d30bf278231..2b5676ff35be 100644 --- a/include/linux/platform_data/brcmfmac.h +++ b/include/linux/platform_data/brcmfmac.h @@ -125,7 +125,7 @@ struct brcmfmac_pd_cc_entry { */ struct brcmfmac_pd_cc { int table_size; - struct brcmfmac_pd_cc_entry table[0]; + struct brcmfmac_pd_cc_entry table[]; }; /** -- cgit v1.2.3 From ae98f40d32cd0ee6fc222e765734ffa497a0a95e Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 23 Sep 2021 13:57:32 -0700 Subject: net: phy: broadcom: Fix PHY_BRCM_IDDQ_SUSPEND definition An extraneous number was added during the inclusion of that change, correct that such that we use a single bit as is expected by the PHY driver. Reported-by: Justin Chen Fixes: d6da08ed1425 ("net: phy: broadcom: Add IDDQ-SR mode") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- include/linux/brcmphy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index b119d6819d6c..27d9b6683f0e 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -67,7 +67,7 @@ #define PHY_BRCM_CLEAR_RGMII_MODE 0x00000004 #define PHY_BRCM_DIS_TXCRXC_NOENRGY 0x00000008 #define PHY_BRCM_EN_MASTER_MODE 0x00000010 -#define PHY_BRCM_IDDQ_SUSPEND 0x000000220 +#define PHY_BRCM_IDDQ_SUSPEND 0x00000020 /* Broadcom BCM7xxx specific workarounds */ #define PHY_BRCM_7XXX_REV(x) (((x) >> 8) & 0xff) -- cgit v1.2.3 From e7f18c22e6bea258ffd65185fdab66d1e63dd5bd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 19 Aug 2021 13:42:43 -0700 Subject: stddef: Fix kerndoc for sizeof_field() and offsetofend() Adjust the comment styles so these are correctly identified as valid kern-doc. Signed-off-by: Kees Cook --- include/linux/stddef.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 998a4ba28eba..8553b33143d1 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -20,7 +20,7 @@ enum { #endif /** - * sizeof_field(TYPE, MEMBER) + * sizeof_field() - Report the size of a struct field in bytes * * @TYPE: The structure containing the field of interest * @MEMBER: The field to return the size of @@ -28,7 +28,7 @@ enum { #define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) /** - * offsetofend(TYPE, MEMBER) + * offsetofend() - Report the offset of a struct field within the struct * * @TYPE: The type of the structure * @MEMBER: The member within the structure to get the end offset of -- cgit v1.2.3 From 50d7bd38c3aafc4749e05e8d7fcb616979143602 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 17 May 2021 20:01:15 -0700 Subject: stddef: Introduce struct_group() helper macro Kernel code has a regular need to describe groups of members within a structure usually when they need to be copied or initialized separately from the rest of the surrounding structure. The generally accepted design pattern in C is to use a named sub-struct: struct foo { int one; struct { int two; int three, four; } thing; int five; }; This would allow for traditional references and sizing: memcpy(&dst.thing, &src.thing, sizeof(dst.thing)); However, doing this would mean that referencing struct members enclosed by such named structs would always require including the sub-struct name in identifiers: do_something(dst.thing.three); This has tended to be quite inflexible, especially when such groupings need to be added to established code which causes huge naming churn. Three workarounds exist in the kernel for this problem, and each have other negative properties. To avoid the naming churn, there is a design pattern of adding macro aliases for the named struct: #define f_three thing.three This ends up polluting the global namespace, and makes it difficult to search for identifiers. Another common work-around in kernel code avoids the pollution by avoiding the named struct entirely, instead identifying the group's boundaries using either a pair of empty anonymous structs of a pair of zero-element arrays: struct foo { int one; struct { } start; int two; int three, four; struct { } finish; int five; }; struct foo { int one; int start[0]; int two; int three, four; int finish[0]; int five; }; This allows code to avoid needing to use a sub-struct named for member references within the surrounding structure, but loses the benefits of being able to actually use such a struct, making it rather fragile. Using these requires open-coded calculation of sizes and offsets. The efforts made to avoid common mistakes include lots of comments, or adding various BUILD_BUG_ON()s. Such code is left with no way for the compiler to reason about the boundaries (e.g. the "start" object looks like it's 0 bytes in length), making bounds checking depend on open-coded calculations: if (length > offsetof(struct foo, finish) - offsetof(struct foo, start)) return -EINVAL; memcpy(&dst.start, &src.start, offsetof(struct foo, finish) - offsetof(struct foo, start)); However, the vast majority of places in the kernel that operate on groups of members do so without any identification of the grouping, relying either on comments or implicit knowledge of the struct contents, which is even harder for the compiler to reason about, and results in even more fragile manual sizing, usually depending on member locations outside of the region (e.g. to copy "two" and "three", use the start of "four" to find the size): BUILD_BUG_ON((offsetof(struct foo, four) < offsetof(struct foo, two)) || (offsetof(struct foo, four) < offsetof(struct foo, three)); if (length > offsetof(struct foo, four) - offsetof(struct foo, two)) return -EINVAL; memcpy(&dst.two, &src.two, length); In order to have a regular programmatic way to describe a struct region that can be used for references and sizing, can be examined for bounds checking, avoids forcing the use of intermediate identifiers, and avoids polluting the global namespace, introduce the struct_group() macro. This macro wraps the member declarations to create an anonymous union of an anonymous struct (no intermediate name) and a named struct (for references and sizing): struct foo { int one; struct_group(thing, int two; int three, four; ); int five; }; if (length > sizeof(src.thing)) return -EINVAL; memcpy(&dst.thing, &src.thing, length); do_something(dst.three); There are some rare cases where the resulting struct_group() needs attributes added, so struct_group_attr() is also introduced to allow for specifying struct attributes (e.g. __align(x) or __packed). Additionally, there are places where such declarations would like to have the struct be tagged, so struct_group_tagged() is added. Given there is a need for a handful of UAPI uses too, the underlying __struct_group() macro has been defined in UAPI so it can be used there too. To avoid confusing scripts/kernel-doc, hide the macro from its struct parsing. Co-developed-by: Keith Packard Signed-off-by: Keith Packard Acked-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/20210728023217.GC35706@embeddedor Enhanced-by: Rasmus Villemoes Link: https://lore.kernel.org/lkml/41183a98-bdb9-4ad6-7eab-5a7292a6df84@rasmusvillemoes.dk Enhanced-by: Dan Williams Link: https://lore.kernel.org/lkml/1d9a2e6df2a9a35b2cdd50a9a68cac5991e7e5f0.camel@intel.com Enhanced-by: Daniel Vetter Link: https://lore.kernel.org/lkml/YQKa76A6XuFqgM03@phenom.ffwll.local Acked-by: Dan Williams Signed-off-by: Kees Cook --- include/linux/stddef.h | 48 +++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/stddef.h | 21 ++++++++++++++++++++ scripts/kernel-doc | 7 +++++++ 3 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 8553b33143d1..8b103a53b000 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -36,4 +36,52 @@ enum { #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +/** + * struct_group() - Wrap a set of declarations in a mirrored struct + * + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. + */ +#define struct_group(NAME, MEMBERS...) \ + __struct_group(/* no tag */, NAME, /* no attrs */, MEMBERS) + +/** + * struct_group_attr() - Create a struct_group() with trailing attributes + * + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes to apply + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes structure attributes argument. + */ +#define struct_group_attr(NAME, ATTRS, MEMBERS...) \ + __struct_group(/* no tag */, NAME, ATTRS, MEMBERS) + +/** + * struct_group_tagged() - Create a struct_group with a reusable tag + * + * @TAG: The tag name for the named sub-struct + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes struct tag argument for the named copy, + * so the specified layout can be reused later. + */ +#define struct_group_tagged(TAG, NAME, MEMBERS...) \ + __struct_group(TAG, NAME, /* no attrs */, MEMBERS) + #endif diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index ee8220f8dcf5..610204f7c275 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -4,3 +4,24 @@ #ifndef __always_inline #define __always_inline inline #endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse, as well + * as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct TAG { MEMBERS } ATTRS NAME; \ + } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index cfcb60737957..38aa799a776c 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1245,6 +1245,13 @@ sub dump_struct($$) { $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; $members =~ s/\s*____cacheline_aligned/ /gos; + # unwrap struct_group(): + # - first eat non-declaration parameters and rewrite for final match + # - then remove macro, outer parens, and trailing semicolon + $members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos; + $members =~ s/\bstruct_group_(attr|tagged)\s*\(([^,]*,){2}/STRUCT_GROUP(/gos; + $members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos; + $members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos; my $args = qr{([^,)]+)}; # replace DECLARE_BITMAP -- cgit v1.2.3 From c80d92fbb67b2c80b8eeb8759ee79d676eb33520 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 17 Jun 2021 22:48:05 -0700 Subject: compiler_types.h: Remove __compiletime_object_size() Since all compilers support __builtin_object_size(), and there is only one user of __compiletime_object_size, remove it to avoid the needless indirection. This lets Clang reason about check_copy_size() correctly. Link: https://github.com/ClangBuiltLinux/linux/issues/1179 Suggested-by: Nick Desaulniers Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Sedat Dilek Cc: Will Deacon Cc: Marco Elver Cc: Arvind Sankar Cc: Masahiro Yamada Cc: Luc Van Oostenryck Cc: Andrew Morton Cc: Sami Tolvanen Cc: Thomas Gleixner Cc: Gabriel Krisman Bertazi Cc: Andy Lutomirski Cc: Oleg Nesterov Reviewed-by: Miguel Ojeda Signed-off-by: Kees Cook --- include/linux/compiler-gcc.h | 2 -- include/linux/compiler_types.h | 5 ----- include/linux/thread_info.h | 2 +- 3 files changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index bd2b881c6b63..9957085b8148 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -41,8 +41,6 @@ #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) -#define __compiletime_object_size(obj) __builtin_object_size(obj, 0) - #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__) #define __latent_entropy __attribute__((latent_entropy)) #endif diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b6ff83a714ca..05ceb2e92b0e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -290,11 +290,6 @@ struct ftrace_likely_data { (sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \ sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long)) -/* Compile time object size, -1 for unknown */ -#ifndef __compiletime_object_size -# define __compiletime_object_size(obj) -1 -#endif - #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 0999f6317978..ad0c4e041030 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -203,7 +203,7 @@ static inline void copy_overflow(int size, unsigned long count) static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { - int sz = __compiletime_object_size(addr); + int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); -- cgit v1.2.3 From c430f60036af44079170ff71a461b9d7cf5ee431 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 14 Apr 2021 15:45:39 -0700 Subject: fortify: Move remaining fortify helpers into fortify-string.h When commit a28a6e860c6c ("string.h: move fortified functions definitions in a dedicated header.") moved the fortify-specific code, some helpers were left behind. Move the remaining fortify-specific helpers into fortify-string.h so they're together where they're used. This requires that any FORTIFY helper function prototypes be conditionally built to avoid "no prototype" warnings. Additionally removes unused helpers. Cc: Andrew Morton Cc: Daniel Axtens Cc: Vincenzo Frascino Cc: Andrey Konovalov Cc: Dan Williams Acked-by: Francis Laniel Reviewed-by: Nick Desaulniers Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 7 +++++++ include/linux/string.h | 9 --------- lib/string_helpers.c | 2 ++ 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index c1be37437e77..7e67d02764db 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -2,6 +2,13 @@ #ifndef _LINUX_FORTIFY_STRING_H_ #define _LINUX_FORTIFY_STRING_H_ +#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) +#define __RENAME(x) __asm__(#x) + +void fortify_panic(const char *name) __noreturn __cold; +void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)"); +void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); +void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); diff --git a/include/linux/string.h b/include/linux/string.h index 5e96d656be7a..ac1c769a5a80 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -249,15 +249,6 @@ static inline const char *kbasename(const char *path) return tail ? tail + 1 : path; } -#define __FORTIFY_INLINE extern __always_inline __attribute__((gnu_inline)) -#define __RENAME(x) __asm__(#x) - -void fortify_panic(const char *name) __noreturn __cold; -void __read_overflow(void) __compiletime_error("detected read beyond size of object passed as 1st parameter"); -void __read_overflow2(void) __compiletime_error("detected read beyond size of object passed as 2nd parameter"); -void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); -void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); - #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) #include #endif diff --git a/lib/string_helpers.c b/lib/string_helpers.c index bde13612c25d..faa9d8e4e2c5 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -883,9 +883,11 @@ char *strreplace(char *s, char old, char new) } EXPORT_SYMBOL(strreplace); +#ifdef CONFIG_FORTIFY_SOURCE void fortify_panic(const char *name) { pr_emerg("detected buffer overflow in %s\n", name); BUG(); } EXPORT_SYMBOL(fortify_panic); +#endif /* CONFIG_FORTIFY_SOURCE */ -- cgit v1.2.3 From 072af0c638dc8a5c7db2edc4dddbd6d44bee3bdb Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 2 Aug 2021 10:25:01 -0700 Subject: fortify: Fix dropped strcpy() compile-time write overflow check The implementation for intra-object overflow in str*-family functions accidentally dropped compile-time write overflow checking in strcpy(), leaving it entirely to run-time. Add back the intended check. Fixes: 6a39e62abbaf ("lib: string.h: detect intra-object overflow in fortified string functions") Cc: Daniel Axtens Cc: Francis Laniel Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers --- include/linux/fortify-string.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 7e67d02764db..68bc5978d916 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -287,7 +287,10 @@ __FORTIFY_INLINE char *strcpy(char *p, const char *q) if (p_size == (size_t)-1 && q_size == (size_t)-1) return __underlying_strcpy(p, q); size = strlen(q) + 1; - /* test here to use the more stringent object size */ + /* Compile-time check for const size overflow. */ + if (__builtin_constant_p(size) && p_size < size) + __write_overflow(); + /* Run-time check for dynamic size overflow. */ if (p_size < size) fortify_panic(__func__); memcpy(p, q, size); -- cgit v1.2.3 From 369cd2165d7beac1db144b40811baa2c6b7d8c54 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 4 Aug 2021 14:20:14 -0700 Subject: fortify: Prepare to improve strnlen() and strlen() warnings In order to have strlen() use fortified strnlen() internally, swap their positions in the source. Doing this as part of later changes makes review difficult, so reoroder it here; no code changes. Cc: Francis Laniel Signed-off-by: Kees Cook Reviewed-by: Nick Desaulniers --- include/linux/fortify-string.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 68bc5978d916..a3cb1d9aacce 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -56,6 +56,17 @@ __FORTIFY_INLINE char *strcat(char *p, const char *q) return p; } +extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); +__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) +{ + size_t p_size = __builtin_object_size(p, 1); + __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + + if (p_size <= ret && maxlen != ret) + fortify_panic(__func__); + return ret; +} + __FORTIFY_INLINE __kernel_size_t strlen(const char *p) { __kernel_size_t ret; @@ -71,17 +82,6 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) return ret; } -extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); -__FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) -{ - size_t p_size = __builtin_object_size(p, 1); - __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); - - if (p_size <= ret && maxlen != ret) - fortify_panic(__func__); - return ret; -} - /* defined after fortified strlen to reuse it */ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) -- cgit v1.2.3 From 3009f891bb9f328945ebd5b71e12df7e2467f3dd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 2 Aug 2021 22:51:31 -0700 Subject: fortify: Allow strlen() and strnlen() to pass compile-time known lengths Under CONFIG_FORTIFY_SOURCE, it is possible for the compiler to perform strlen() and strnlen() at compile-time when the string size is known. This is required to support compile-time overflow checking in strlcpy(). Signed-off-by: Kees Cook --- include/linux/fortify-string.h | 49 ++++++++++++++++++++++++++++++++---------- 1 file changed, 38 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index a3cb1d9aacce..fdb0a74c9ca2 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -10,6 +10,20 @@ void __read_overflow(void) __compiletime_error("detected read beyond size of obj void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); +#define __compiletime_strlen(p) \ +({ \ + unsigned char *__p = (unsigned char *)(p); \ + size_t ret = (size_t)-1; \ + size_t p_size = __builtin_object_size(p, 1); \ + if (p_size != (size_t)-1) { \ + size_t p_len = p_size - 1; \ + if (__builtin_constant_p(__p[p_len]) && \ + __p[p_len] == '\0') \ + ret = __builtin_strlen(__p); \ + } \ + ret; \ +}) + #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr); extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp); @@ -60,21 +74,31 @@ extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(st __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) { size_t p_size = __builtin_object_size(p, 1); - __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); + size_t p_len = __compiletime_strlen(p); + size_t ret; + + /* We can take compile-time actions when maxlen is const. */ + if (__builtin_constant_p(maxlen) && p_len != (size_t)-1) { + /* If p is const, we can use its compile-time-known len. */ + if (maxlen >= p_size) + return p_len; + } + /* Do not check characters beyond the end of p. */ + ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); if (p_size <= ret && maxlen != ret) fortify_panic(__func__); return ret; } +/* defined after fortified strnlen to reuse it. */ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) { __kernel_size_t ret; size_t p_size = __builtin_object_size(p, 1); - /* Work around gcc excess stack consumption issue */ - if (p_size == (size_t)-1 || - (__builtin_constant_p(p[p_size - 1]) && p[p_size - 1] == '\0')) + /* Give up if we don't know how large p is. */ + if (p_size == (size_t)-1) return __underlying_strlen(p); ret = strnlen(p, p_size); if (p_size <= ret) @@ -86,24 +110,27 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) { - size_t ret; size_t p_size = __builtin_object_size(p, 1); size_t q_size = __builtin_object_size(q, 1); + size_t q_len; /* Full count of source string length. */ + size_t len; /* Count of characters going into destination. */ if (p_size == (size_t)-1 && q_size == (size_t)-1) return __real_strlcpy(p, q, size); - ret = strlen(q); - if (size) { - size_t len = (ret >= size) ? size - 1 : ret; - - if (__builtin_constant_p(len) && len >= p_size) + q_len = strlen(q); + len = (q_len >= size) ? size - 1 : q_len; + if (__builtin_constant_p(size) && __builtin_constant_p(q_len) && size) { + /* Write size is always larger than destination. */ + if (len >= p_size) __write_overflow(); + } + if (size) { if (len >= p_size) fortify_panic(__func__); __underlying_memcpy(p, q, len); p[len] = '\0'; } - return ret; + return q_len; } /* defined after fortified strnlen to reuse it */ -- cgit v1.2.3 From 405fca8a946168e71c04b82cc80727c3ea686e08 Mon Sep 17 00:00:00 2001 From: Wen Gong Date: Fri, 24 Sep 2021 06:00:47 -0400 Subject: ieee80211: add power type definition for 6 GHz 6 GHz regulatory domains introduces different modes for 6 GHz AP operations: Low Power Indoor (LPI), Standard Power (SP) and Very Low Power (VLP). 6 GHz STAs could be operated as either Regular or Subordinate clients. Define the flags for power type of AP and STATION mode. Signed-off-by: Wen Gong Link: https://lore.kernel.org/r/20210924100052.32029-2-wgong@codeaurora.org Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 38 ++++++++++++++++++++++++++++++++++++++ include/net/mac80211.h | 2 ++ 2 files changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 694264503119..420dea9aa648 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1988,6 +1988,44 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss); +/** + * enum ieee80211_ap_reg_power - regulatory power for a Access Point + * + * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode + * @IEEE80211_REG_LPI: Indoor Access Point + * @IEEE80211_REG_SP: Standard power Access Point + * @IEEE80211_REG_VLP: Very low power Access Point + * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal + * @IEEE80211_REG_AP_POWER_MAX: maximum value + */ +enum ieee80211_ap_reg_power { + IEEE80211_REG_UNSET_AP, + IEEE80211_REG_LPI_AP, + IEEE80211_REG_SP_AP, + IEEE80211_REG_VLP_AP, + IEEE80211_REG_AP_POWER_AFTER_LAST, + IEEE80211_REG_AP_POWER_MAX = + IEEE80211_REG_AP_POWER_AFTER_LAST - 1, +}; + +/** + * enum ieee80211_client_reg_power - regulatory power for a client + * + * @IEEE80211_REG_UNSET_CLIENT: Client has no regulatory power mode + * @IEEE80211_REG_DEFAULT_CLIENT: Default Client + * @IEEE80211_REG_SUBORDINATE_CLIENT: Subordinate Client + * @IEEE80211_REG_CLIENT_POWER_AFTER_LAST: internal + * @IEEE80211_REG_CLIENT_POWER_MAX: maximum value + */ +enum ieee80211_client_reg_power { + IEEE80211_REG_UNSET_CLIENT, + IEEE80211_REG_DEFAULT_CLIENT, + IEEE80211_REG_SUBORDINATE_CLIENT, + IEEE80211_REG_CLIENT_POWER_AFTER_LAST, + IEEE80211_REG_CLIENT_POWER_MAX = + IEEE80211_REG_CLIENT_POWER_AFTER_LAST - 1, +}; + /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 #define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 diff --git a/include/net/mac80211.h b/include/net/mac80211.h index af0fc13cea34..8923a9fc4126 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -632,6 +632,7 @@ struct ieee80211_fils_discovery { * @s1g: BSS is S1G BSS (affects Association Request format). * @beacon_tx_rate: The configured beacon transmit rate that needs to be passed * to driver when rate control is offloaded to firmware. + * @power_type: power type of BSS for 6 GHz */ struct ieee80211_bss_conf { const u8 *bssid; @@ -702,6 +703,7 @@ struct ieee80211_bss_conf { u32 unsol_bcast_probe_resp_interval; bool s1g; struct cfg80211_bitrate_mask beacon_tx_rate; + enum ieee80211_ap_reg_power power_type; }; /** -- cgit v1.2.3 From 930dfa563155179861470b2aba880eac2ae30bfb Mon Sep 17 00:00:00 2001 From: Min Li Date: Fri, 24 Sep 2021 15:01:32 -0400 Subject: ptp: clockmatrix: use rsmu driver to access i2c/spi bus rsmu (Renesas Synchronization Management Unit ) driver is located in drivers/mfd and responsible for creating multiple devices including clockmatrix phc, which will then use the exposed regmap and mutex handle to access i2c/spi bus. Signed-off-by: Min Li Signed-off-by: David S. Miller --- drivers/ptp/idt8a340_reg.h | 783 --------------------------------------- drivers/ptp/ptp_clockmatrix.c | 772 ++++++++++++++++++++------------------ drivers/ptp/ptp_clockmatrix.h | 117 +----- include/linux/mfd/idt8a340_reg.h | 31 +- 4 files changed, 461 insertions(+), 1242 deletions(-) delete mode 100644 drivers/ptp/idt8a340_reg.h (limited to 'include/linux') diff --git a/drivers/ptp/idt8a340_reg.h b/drivers/ptp/idt8a340_reg.h deleted file mode 100644 index 1c5210187110..000000000000 --- a/drivers/ptp/idt8a340_reg.h +++ /dev/null @@ -1,783 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* idt8a340_reg.h - * - * Originally generated by regen.tcl on Thu Feb 14 19:23:44 PST 2019 - * https://github.com/richardcochran/regen - * - * Hand modified to include some HW registers. - * Based on 5.2.0, Family Programming Guide (Sept 30, 2020) - */ -#ifndef HAVE_IDT8A340_REG -#define HAVE_IDT8A340_REG - -#define PAGE_ADDR_BASE 0x0000 -#define PAGE_ADDR 0x00fc - -#define HW_REVISION 0x8180 -#define REV_ID 0x007a - -#define HW_DPLL_0 (0x8a00) -#define HW_DPLL_1 (0x8b00) -#define HW_DPLL_2 (0x8c00) -#define HW_DPLL_3 (0x8d00) -#define HW_DPLL_4 (0x8e00) -#define HW_DPLL_5 (0x8f00) -#define HW_DPLL_6 (0x9000) -#define HW_DPLL_7 (0x9100) - -#define HW_DPLL_TOD_SW_TRIG_ADDR__0 (0x080) -#define HW_DPLL_TOD_CTRL_1 (0x089) -#define HW_DPLL_TOD_CTRL_2 (0x08A) -#define HW_DPLL_TOD_OVR__0 (0x098) -#define HW_DPLL_TOD_OUT_0__0 (0x0B0) - -#define HW_Q0_Q1_CH_SYNC_CTRL_0 (0xa740) -#define HW_Q0_Q1_CH_SYNC_CTRL_1 (0xa741) -#define HW_Q2_Q3_CH_SYNC_CTRL_0 (0xa742) -#define HW_Q2_Q3_CH_SYNC_CTRL_1 (0xa743) -#define HW_Q4_Q5_CH_SYNC_CTRL_0 (0xa744) -#define HW_Q4_Q5_CH_SYNC_CTRL_1 (0xa745) -#define HW_Q6_Q7_CH_SYNC_CTRL_0 (0xa746) -#define HW_Q6_Q7_CH_SYNC_CTRL_1 (0xa747) -#define HW_Q8_CH_SYNC_CTRL_0 (0xa748) -#define HW_Q8_CH_SYNC_CTRL_1 (0xa749) -#define HW_Q9_CH_SYNC_CTRL_0 (0xa74a) -#define HW_Q9_CH_SYNC_CTRL_1 (0xa74b) -#define HW_Q10_CH_SYNC_CTRL_0 (0xa74c) -#define HW_Q10_CH_SYNC_CTRL_1 (0xa74d) -#define HW_Q11_CH_SYNC_CTRL_0 (0xa74e) -#define HW_Q11_CH_SYNC_CTRL_1 (0xa74f) - -#define SYNC_SOURCE_DPLL0_TOD_PPS 0x14 -#define SYNC_SOURCE_DPLL1_TOD_PPS 0x15 -#define SYNC_SOURCE_DPLL2_TOD_PPS 0x16 -#define SYNC_SOURCE_DPLL3_TOD_PPS 0x17 - -#define SYNCTRL1_MASTER_SYNC_RST BIT(7) -#define SYNCTRL1_MASTER_SYNC_TRIG BIT(5) -#define SYNCTRL1_TOD_SYNC_TRIG BIT(4) -#define SYNCTRL1_FBDIV_FRAME_SYNC_TRIG BIT(3) -#define SYNCTRL1_FBDIV_SYNC_TRIG BIT(2) -#define SYNCTRL1_Q1_DIV_SYNC_TRIG BIT(1) -#define SYNCTRL1_Q0_DIV_SYNC_TRIG BIT(0) - -#define HW_Q8_CTRL_SPARE (0xa7d4) -#define HW_Q11_CTRL_SPARE (0xa7ec) - -/** - * Select FOD5 as sync_trigger for Q8 divider. - * Transition from logic zero to one - * sets trigger to sync Q8 divider. - * - * Unused when FOD4 is driving Q8 divider (normal operation). - */ -#define Q9_TO_Q8_SYNC_TRIG BIT(1) - -/** - * Enable FOD5 as driver for clock and sync for Q8 divider. - * Enable fanout buffer for FOD5. - * - * Unused when FOD4 is driving Q8 divider (normal operation). - */ -#define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) - -/** - * Select FOD6 as sync_trigger for Q11 divider. - * Transition from logic zero to one - * sets trigger to sync Q11 divider. - * - * Unused when FOD7 is driving Q11 divider (normal operation). - */ -#define Q10_TO_Q11_SYNC_TRIG BIT(1) - -/** - * Enable FOD6 as driver for clock and sync for Q11 divider. - * Enable fanout buffer for FOD6. - * - * Unused when FOD7 is driving Q11 divider (normal operation). - */ -#define Q10_TO_Q11_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK (BIT(0) | BIT(2)) - -#define RESET_CTRL 0xc000 -#define SM_RESET 0x0012 -#define SM_RESET_V520 0x0013 -#define SM_RESET_CMD 0x5A - -#define GENERAL_STATUS 0xc014 -#define BOOT_STATUS 0x0000 -#define HW_REV_ID 0x000A -#define BOND_ID 0x000B -#define HW_CSR_ID 0x000C -#define HW_IRQ_ID 0x000E - -#define MAJ_REL 0x0010 -#define MIN_REL 0x0011 -#define HOTFIX_REL 0x0012 - -#define PIPELINE_ID 0x0014 -#define BUILD_ID 0x0018 - -#define JTAG_DEVICE_ID 0x001c -#define PRODUCT_ID 0x001e - -#define OTP_SCSR_CONFIG_SELECT 0x0022 - -#define STATUS 0xc03c -#define DPLL_SYS_STATUS 0x0020 -#define DPLL_SYS_APLL_STATUS 0x0021 -#define USER_GPIO0_TO_7_STATUS 0x008a -#define USER_GPIO8_TO_15_STATUS 0x008b - -#define GPIO_USER_CONTROL 0xc160 -#define GPIO0_TO_7_OUT 0x0000 -#define GPIO8_TO_15_OUT 0x0001 -#define GPIO0_TO_7_OUT_V520 0x0002 -#define GPIO8_TO_15_OUT_V520 0x0003 - -#define STICKY_STATUS_CLEAR 0xc164 - -#define GPIO_TOD_NOTIFICATION_CLEAR 0xc16c - -#define ALERT_CFG 0xc188 - -#define SYS_DPLL_XO 0xc194 - -#define SYS_APLL 0xc19c - -#define INPUT_0 0xc1b0 - -#define INPUT_1 0xc1c0 - -#define INPUT_2 0xc1d0 - -#define INPUT_3 0xc200 - -#define INPUT_4 0xc210 - -#define INPUT_5 0xc220 - -#define INPUT_6 0xc230 - -#define INPUT_7 0xc240 - -#define INPUT_8 0xc250 - -#define INPUT_9 0xc260 - -#define INPUT_10 0xc280 - -#define INPUT_11 0xc290 - -#define INPUT_12 0xc2a0 - -#define INPUT_13 0xc2b0 - -#define INPUT_14 0xc2c0 - -#define INPUT_15 0xc2d0 - -#define REF_MON_0 0xc2e0 - -#define REF_MON_1 0xc2ec - -#define REF_MON_2 0xc300 - -#define REF_MON_3 0xc30c - -#define REF_MON_4 0xc318 - -#define REF_MON_5 0xc324 - -#define REF_MON_6 0xc330 - -#define REF_MON_7 0xc33c - -#define REF_MON_8 0xc348 - -#define REF_MON_9 0xc354 - -#define REF_MON_10 0xc360 - -#define REF_MON_11 0xc36c - -#define REF_MON_12 0xc380 - -#define REF_MON_13 0xc38c - -#define REF_MON_14 0xc398 - -#define REF_MON_15 0xc3a4 - -#define DPLL_0 0xc3b0 -#define DPLL_CTRL_REG_0 0x0002 -#define DPLL_CTRL_REG_1 0x0003 -#define DPLL_CTRL_REG_2 0x0004 -#define DPLL_TOD_SYNC_CFG 0x0031 -#define DPLL_COMBO_SLAVE_CFG_0 0x0032 -#define DPLL_COMBO_SLAVE_CFG_1 0x0033 -#define DPLL_SLAVE_REF_CFG 0x0034 -#define DPLL_REF_MODE 0x0035 -#define DPLL_PHASE_MEASUREMENT_CFG 0x0036 -#define DPLL_MODE 0x0037 -#define DPLL_MODE_V520 0x003B - -#define DPLL_1 0xc400 - -#define DPLL_2 0xc438 -#define DPLL_2_V520 0xc43c - -#define DPLL_3 0xc480 - -#define DPLL_4 0xc4b8 -#define DPLL_4_V520 0xc4bc - -#define DPLL_5 0xc500 - -#define DPLL_6 0xc538 -#define DPLL_6_V520 0xc53c - -#define DPLL_7 0xc580 - -#define SYS_DPLL 0xc5b8 -#define SYS_DPLL_V520 0xc5bc - -#define DPLL_CTRL_0 0xc600 -#define DPLL_CTRL_DPLL_MANU_REF_CFG 0x0001 -#define DPLL_CTRL_COMBO_MASTER_CFG 0x003a - -#define DPLL_CTRL_1 0xc63c - -#define DPLL_CTRL_2 0xc680 - -#define DPLL_CTRL_3 0xc6bc - -#define DPLL_CTRL_4 0xc700 - -#define DPLL_CTRL_5 0xc73c - -#define DPLL_CTRL_6 0xc780 - -#define DPLL_CTRL_7 0xc7bc - -#define SYS_DPLL_CTRL 0xc800 - -#define DPLL_PHASE_0 0xc818 - -/* Signed 42-bit FFO in units of 2^(-53) */ -#define DPLL_WR_PHASE 0x0000 - -#define DPLL_PHASE_1 0xc81c - -#define DPLL_PHASE_2 0xc820 - -#define DPLL_PHASE_3 0xc824 - -#define DPLL_PHASE_4 0xc828 - -#define DPLL_PHASE_5 0xc82c - -#define DPLL_PHASE_6 0xc830 - -#define DPLL_PHASE_7 0xc834 - -#define DPLL_FREQ_0 0xc838 - -/* Signed 42-bit FFO in units of 2^(-53) */ -#define DPLL_WR_FREQ 0x0000 - -#define DPLL_FREQ_1 0xc840 - -#define DPLL_FREQ_2 0xc848 - -#define DPLL_FREQ_3 0xc850 - -#define DPLL_FREQ_4 0xc858 - -#define DPLL_FREQ_5 0xc860 - -#define DPLL_FREQ_6 0xc868 - -#define DPLL_FREQ_7 0xc870 - -#define DPLL_PHASE_PULL_IN_0 0xc880 -#define PULL_IN_OFFSET 0x0000 /* Signed 32 bit */ -#define PULL_IN_SLOPE_LIMIT 0x0004 /* Unsigned 24 bit */ -#define PULL_IN_CTRL 0x0007 - -#define DPLL_PHASE_PULL_IN_1 0xc888 - -#define DPLL_PHASE_PULL_IN_2 0xc890 - -#define DPLL_PHASE_PULL_IN_3 0xc898 - -#define DPLL_PHASE_PULL_IN_4 0xc8a0 - -#define DPLL_PHASE_PULL_IN_5 0xc8a8 - -#define DPLL_PHASE_PULL_IN_6 0xc8b0 - -#define DPLL_PHASE_PULL_IN_7 0xc8b8 - -#define GPIO_CFG 0xc8c0 -#define GPIO_CFG_GBL 0x0000 - -#define GPIO_0 0xc8c2 -#define GPIO_DCO_INC_DEC 0x0000 -#define GPIO_OUT_CTRL_0 0x0001 -#define GPIO_OUT_CTRL_1 0x0002 -#define GPIO_TOD_TRIG 0x0003 -#define GPIO_DPLL_INDICATOR 0x0004 -#define GPIO_LOS_INDICATOR 0x0005 -#define GPIO_REF_INPUT_DSQ_0 0x0006 -#define GPIO_REF_INPUT_DSQ_1 0x0007 -#define GPIO_REF_INPUT_DSQ_2 0x0008 -#define GPIO_REF_INPUT_DSQ_3 0x0009 -#define GPIO_MAN_CLK_SEL_0 0x000a -#define GPIO_MAN_CLK_SEL_1 0x000b -#define GPIO_MAN_CLK_SEL_2 0x000c -#define GPIO_SLAVE 0x000d -#define GPIO_ALERT_OUT_CFG 0x000e -#define GPIO_TOD_NOTIFICATION_CFG 0x000f -#define GPIO_CTRL 0x0010 -#define GPIO_CTRL_V520 0x0011 - -#define GPIO_1 0xc8d4 - -#define GPIO_2 0xc8e6 - -#define GPIO_3 0xc900 - -#define GPIO_4 0xc912 - -#define GPIO_5 0xc924 - -#define GPIO_6 0xc936 - -#define GPIO_7 0xc948 - -#define GPIO_8 0xc95a - -#define GPIO_9 0xc980 - -#define GPIO_10 0xc992 - -#define GPIO_11 0xc9a4 - -#define GPIO_12 0xc9b6 - -#define GPIO_13 0xc9c8 - -#define GPIO_14 0xc9da - -#define GPIO_15 0xca00 - -#define OUT_DIV_MUX 0xca12 - -#define OUTPUT_0 0xca14 -#define OUTPUT_0_V520 0xca20 -/* FOD frequency output divider value */ -#define OUT_DIV 0x0000 -#define OUT_DUTY_CYCLE_HIGH 0x0004 -#define OUT_CTRL_0 0x0008 -#define OUT_CTRL_1 0x0009 -/* Phase adjustment in FOD cycles */ -#define OUT_PHASE_ADJ 0x000c - -#define OUTPUT_1 0xca24 -#define OUTPUT_1_V520 0xca30 - -#define OUTPUT_2 0xca34 -#define OUTPUT_2_V520 0xca40 - -#define OUTPUT_3 0xca44 -#define OUTPUT_3_V520 0xca50 - -#define OUTPUT_4 0xca54 -#define OUTPUT_4_V520 0xca60 - -#define OUTPUT_5 0xca64 -#define OUTPUT_5_V520 0xca80 - -#define OUTPUT_6 0xca80 -#define OUTPUT_6_V520 0xca90 - -#define OUTPUT_7 0xca90 -#define OUTPUT_7_V520 0xcaa0 - -#define OUTPUT_8 0xcaa0 -#define OUTPUT_8_V520 0xcab0 - -#define OUTPUT_9 0xcab0 -#define OUTPUT_9_V520 0xcac0 - -#define OUTPUT_10 0xcac0 -#define OUTPUT_10_V520 0xcad0 - -#define OUTPUT_11 0xcad0 -#define OUTPUT_11_V520 0xcae0 - -#define SERIAL 0xcae0 -#define SERIAL_V520 0xcaf0 - -#define PWM_ENCODER_0 0xcb00 - -#define PWM_ENCODER_1 0xcb08 - -#define PWM_ENCODER_2 0xcb10 - -#define PWM_ENCODER_3 0xcb18 - -#define PWM_ENCODER_4 0xcb20 - -#define PWM_ENCODER_5 0xcb28 - -#define PWM_ENCODER_6 0xcb30 - -#define PWM_ENCODER_7 0xcb38 - -#define PWM_DECODER_0 0xcb40 - -#define PWM_DECODER_1 0xcb48 -#define PWM_DECODER_1_V520 0xcb4a - -#define PWM_DECODER_2 0xcb50 -#define PWM_DECODER_2_V520 0xcb54 - -#define PWM_DECODER_3 0xcb58 -#define PWM_DECODER_3_V520 0xcb5e - -#define PWM_DECODER_4 0xcb60 -#define PWM_DECODER_4_V520 0xcb68 - -#define PWM_DECODER_5 0xcb68 -#define PWM_DECODER_5_V520 0xcb80 - -#define PWM_DECODER_6 0xcb70 -#define PWM_DECODER_6_V520 0xcb8a - -#define PWM_DECODER_7 0xcb80 -#define PWM_DECODER_7_V520 0xcb94 - -#define PWM_DECODER_8 0xcb88 -#define PWM_DECODER_8_V520 0xcb9e - -#define PWM_DECODER_9 0xcb90 -#define PWM_DECODER_9_V520 0xcba8 - -#define PWM_DECODER_10 0xcb98 -#define PWM_DECODER_10_V520 0xcbb2 - -#define PWM_DECODER_11 0xcba0 -#define PWM_DECODER_11_V520 0xcbbc - -#define PWM_DECODER_12 0xcba8 -#define PWM_DECODER_12_V520 0xcbc6 - -#define PWM_DECODER_13 0xcbb0 -#define PWM_DECODER_13_V520 0xcbd0 - -#define PWM_DECODER_14 0xcbb8 -#define PWM_DECODER_14_V520 0xcbda - -#define PWM_DECODER_15 0xcbc0 -#define PWM_DECODER_15_V520 0xcbe4 - -#define PWM_USER_DATA 0xcbc8 -#define PWM_USER_DATA_V520 0xcbf0 - -#define TOD_0 0xcbcc -#define TOD_0_V520 0xcc00 - -/* Enable TOD counter, output channel sync and even-PPS mode */ -#define TOD_CFG 0x0000 -#define TOD_CFG_V520 0x0001 - -#define TOD_1 0xcbce -#define TOD_1_V520 0xcc02 - -#define TOD_2 0xcbd0 -#define TOD_2_V520 0xcc04 - -#define TOD_3 0xcbd2 -#define TOD_3_V520 0xcc06 - - -#define TOD_WRITE_0 0xcc00 -#define TOD_WRITE_0_V520 0xcc10 -/* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_WRITE 0x0000 -/* Counter increments after TOD write is completed */ -#define TOD_WRITE_COUNTER 0x000c -/* TOD write trigger configuration */ -#define TOD_WRITE_SELECT_CFG_0 0x000d -/* TOD write trigger selection */ -#define TOD_WRITE_CMD 0x000f - -#define TOD_WRITE_1 0xcc10 -#define TOD_WRITE_1_V520 0xcc20 - -#define TOD_WRITE_2 0xcc20 -#define TOD_WRITE_2_V520 0xcc30 - -#define TOD_WRITE_3 0xcc30 -#define TOD_WRITE_3_V520 0xcc40 - -#define TOD_READ_PRIMARY_0 0xcc40 -#define TOD_READ_PRIMARY_0_V520 0xcc50 -/* 8-bit subns, 32-bit ns, 48-bit seconds */ -#define TOD_READ_PRIMARY 0x0000 -/* Counter increments after TOD write is completed */ -#define TOD_READ_PRIMARY_COUNTER 0x000b -/* Read trigger configuration */ -#define TOD_READ_PRIMARY_SEL_CFG_0 0x000c -/* Read trigger selection */ -#define TOD_READ_PRIMARY_CMD 0x000e -#define TOD_READ_PRIMARY_CMD_V520 0x000f - -#define TOD_READ_PRIMARY_1 0xcc50 -#define TOD_READ_PRIMARY_1_V520 0xcc60 - -#define TOD_READ_PRIMARY_2 0xcc60 -#define TOD_READ_PRIMARY_2_V520 0xcc80 - -#define TOD_READ_PRIMARY_3 0xcc80 -#define TOD_READ_PRIMARY_3_V520 0xcc90 - -#define TOD_READ_SECONDARY_0 0xcc90 -#define TOD_READ_SECONDARY_0_V520 0xcca0 - -#define TOD_READ_SECONDARY_1 0xcca0 -#define TOD_READ_SECONDARY_1_V520 0xccb0 - -#define TOD_READ_SECONDARY_2 0xccb0 -#define TOD_READ_SECONDARY_2_V520 0xccc0 - -#define TOD_READ_SECONDARY_3 0xccc0 -#define TOD_READ_SECONDARY_3_V520 0xccd0 - -#define OUTPUT_TDC_CFG 0xccd0 -#define OUTPUT_TDC_CFG_V520 0xcce0 - -#define OUTPUT_TDC_0 0xcd00 - -#define OUTPUT_TDC_1 0xcd08 - -#define OUTPUT_TDC_2 0xcd10 - -#define OUTPUT_TDC_3 0xcd18 - -#define INPUT_TDC 0xcd20 - -#define SCRATCH 0xcf50 -#define SCRATCH_V520 0xcf4c - -#define EEPROM 0xcf68 -#define EEPROM_V520 0xcf64 - -#define OTP 0xcf70 - -#define BYTE 0xcf80 - -/* Bit definitions for the MAJ_REL register */ -#define MAJOR_SHIFT (1) -#define MAJOR_MASK (0x7f) -#define PR_BUILD BIT(0) - -/* Bit definitions for the USER_GPIO0_TO_7_STATUS register */ -#define GPIO0_LEVEL BIT(0) -#define GPIO1_LEVEL BIT(1) -#define GPIO2_LEVEL BIT(2) -#define GPIO3_LEVEL BIT(3) -#define GPIO4_LEVEL BIT(4) -#define GPIO5_LEVEL BIT(5) -#define GPIO6_LEVEL BIT(6) -#define GPIO7_LEVEL BIT(7) - -/* Bit definitions for the USER_GPIO8_TO_15_STATUS register */ -#define GPIO8_LEVEL BIT(0) -#define GPIO9_LEVEL BIT(1) -#define GPIO10_LEVEL BIT(2) -#define GPIO11_LEVEL BIT(3) -#define GPIO12_LEVEL BIT(4) -#define GPIO13_LEVEL BIT(5) -#define GPIO14_LEVEL BIT(6) -#define GPIO15_LEVEL BIT(7) - -/* Bit definitions for the GPIO0_TO_7_OUT register */ -#define GPIO0_DRIVE_LEVEL BIT(0) -#define GPIO1_DRIVE_LEVEL BIT(1) -#define GPIO2_DRIVE_LEVEL BIT(2) -#define GPIO3_DRIVE_LEVEL BIT(3) -#define GPIO4_DRIVE_LEVEL BIT(4) -#define GPIO5_DRIVE_LEVEL BIT(5) -#define GPIO6_DRIVE_LEVEL BIT(6) -#define GPIO7_DRIVE_LEVEL BIT(7) - -/* Bit definitions for the GPIO8_TO_15_OUT register */ -#define GPIO8_DRIVE_LEVEL BIT(0) -#define GPIO9_DRIVE_LEVEL BIT(1) -#define GPIO10_DRIVE_LEVEL BIT(2) -#define GPIO11_DRIVE_LEVEL BIT(3) -#define GPIO12_DRIVE_LEVEL BIT(4) -#define GPIO13_DRIVE_LEVEL BIT(5) -#define GPIO14_DRIVE_LEVEL BIT(6) -#define GPIO15_DRIVE_LEVEL BIT(7) - -/* Bit definitions for the DPLL_TOD_SYNC_CFG register */ -#define TOD_SYNC_SOURCE_SHIFT (1) -#define TOD_SYNC_SOURCE_MASK (0x3) -#define TOD_SYNC_EN BIT(0) - -/* Bit definitions for the DPLL_MODE register */ -#define WRITE_TIMER_MODE BIT(6) -#define PLL_MODE_SHIFT (3) -#define PLL_MODE_MASK (0x7) -#define STATE_MODE_SHIFT (0) -#define STATE_MODE_MASK (0x7) - -/* Bit definitions for the DPLL_MANU_REF_CFG register */ -#define MANUAL_REFERENCE_SHIFT (0) -#define MANUAL_REFERENCE_MASK (0x1f) - -/* Bit definitions for the GPIO_CFG_GBL register */ -#define SUPPLY_MODE_SHIFT (0) -#define SUPPLY_MODE_MASK (0x3) - -/* Bit definitions for the GPIO_DCO_INC_DEC register */ -#define INCDEC_DPLL_INDEX_SHIFT (0) -#define INCDEC_DPLL_INDEX_MASK (0x7) - -/* Bit definitions for the GPIO_OUT_CTRL_0 register */ -#define CTRL_OUT_0 BIT(0) -#define CTRL_OUT_1 BIT(1) -#define CTRL_OUT_2 BIT(2) -#define CTRL_OUT_3 BIT(3) -#define CTRL_OUT_4 BIT(4) -#define CTRL_OUT_5 BIT(5) -#define CTRL_OUT_6 BIT(6) -#define CTRL_OUT_7 BIT(7) - -/* Bit definitions for the GPIO_OUT_CTRL_1 register */ -#define CTRL_OUT_8 BIT(0) -#define CTRL_OUT_9 BIT(1) -#define CTRL_OUT_10 BIT(2) -#define CTRL_OUT_11 BIT(3) -#define CTRL_OUT_12 BIT(4) -#define CTRL_OUT_13 BIT(5) -#define CTRL_OUT_14 BIT(6) -#define CTRL_OUT_15 BIT(7) - -/* Bit definitions for the GPIO_TOD_TRIG register */ -#define TOD_TRIG_0 BIT(0) -#define TOD_TRIG_1 BIT(1) -#define TOD_TRIG_2 BIT(2) -#define TOD_TRIG_3 BIT(3) - -/* Bit definitions for the GPIO_DPLL_INDICATOR register */ -#define IND_DPLL_INDEX_SHIFT (0) -#define IND_DPLL_INDEX_MASK (0x7) - -/* Bit definitions for the GPIO_LOS_INDICATOR register */ -#define REFMON_INDEX_SHIFT (0) -#define REFMON_INDEX_MASK (0xf) -/* Active level of LOS indicator, 0=low 1=high */ -#define ACTIVE_LEVEL BIT(4) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_0 register */ -#define DSQ_INP_0 BIT(0) -#define DSQ_INP_1 BIT(1) -#define DSQ_INP_2 BIT(2) -#define DSQ_INP_3 BIT(3) -#define DSQ_INP_4 BIT(4) -#define DSQ_INP_5 BIT(5) -#define DSQ_INP_6 BIT(6) -#define DSQ_INP_7 BIT(7) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_1 register */ -#define DSQ_INP_8 BIT(0) -#define DSQ_INP_9 BIT(1) -#define DSQ_INP_10 BIT(2) -#define DSQ_INP_11 BIT(3) -#define DSQ_INP_12 BIT(4) -#define DSQ_INP_13 BIT(5) -#define DSQ_INP_14 BIT(6) -#define DSQ_INP_15 BIT(7) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_2 register */ -#define DSQ_DPLL_0 BIT(0) -#define DSQ_DPLL_1 BIT(1) -#define DSQ_DPLL_2 BIT(2) -#define DSQ_DPLL_3 BIT(3) -#define DSQ_DPLL_4 BIT(4) -#define DSQ_DPLL_5 BIT(5) -#define DSQ_DPLL_6 BIT(6) -#define DSQ_DPLL_7 BIT(7) - -/* Bit definitions for the GPIO_REF_INPUT_DSQ_3 register */ -#define DSQ_DPLL_SYS BIT(0) -#define GPIO_DSQ_LEVEL BIT(1) - -/* Bit definitions for the GPIO_TOD_NOTIFICATION_CFG register */ -#define DPLL_TOD_SHIFT (0) -#define DPLL_TOD_MASK (0x3) -#define TOD_READ_SECONDARY BIT(2) -#define GPIO_ASSERT_LEVEL BIT(3) - -/* Bit definitions for the GPIO_CTRL register */ -#define GPIO_FUNCTION_EN BIT(0) -#define GPIO_CMOS_OD_MODE BIT(1) -#define GPIO_CONTROL_DIR BIT(2) -#define GPIO_PU_PD_MODE BIT(3) -#define GPIO_FUNCTION_SHIFT (4) -#define GPIO_FUNCTION_MASK (0xf) - -/* Bit definitions for the OUT_CTRL_1 register */ -#define OUT_SYNC_DISABLE BIT(7) -#define SQUELCH_VALUE BIT(6) -#define SQUELCH_DISABLE BIT(5) -#define PAD_VDDO_SHIFT (2) -#define PAD_VDDO_MASK (0x7) -#define PAD_CMOSDRV_SHIFT (0) -#define PAD_CMOSDRV_MASK (0x3) - -/* Bit definitions for the TOD_CFG register */ -#define TOD_EVEN_PPS_MODE BIT(2) -#define TOD_OUT_SYNC_ENABLE BIT(1) -#define TOD_ENABLE BIT(0) - -/* Bit definitions for the TOD_WRITE_SELECT_CFG_0 register */ -#define WR_PWM_DECODER_INDEX_SHIFT (4) -#define WR_PWM_DECODER_INDEX_MASK (0xf) -#define WR_REF_INDEX_SHIFT (0) -#define WR_REF_INDEX_MASK (0xf) - -/* Bit definitions for the TOD_WRITE_CMD register */ -#define TOD_WRITE_SELECTION_SHIFT (0) -#define TOD_WRITE_SELECTION_MASK (0xf) -/* 4.8.7 */ -#define TOD_WRITE_TYPE_SHIFT (4) -#define TOD_WRITE_TYPE_MASK (0x3) - -/* Bit definitions for the TOD_READ_PRIMARY_SEL_CFG_0 register */ -#define RD_PWM_DECODER_INDEX_SHIFT (4) -#define RD_PWM_DECODER_INDEX_MASK (0xf) -#define RD_REF_INDEX_SHIFT (0) -#define RD_REF_INDEX_MASK (0xf) - -/* Bit definitions for the TOD_READ_PRIMARY_CMD register */ -#define TOD_READ_TRIGGER_MODE BIT(4) -#define TOD_READ_TRIGGER_SHIFT (0) -#define TOD_READ_TRIGGER_MASK (0xf) - -/* Bit definitions for the DPLL_CTRL_COMBO_MASTER_CFG register */ -#define COMBO_MASTER_HOLD BIT(0) - -/* Bit definitions for DPLL_SYS_STATUS register */ -#define DPLL_SYS_STATE_MASK (0xf) - -/* Bit definitions for SYS_APLL_STATUS register */ -#define SYS_APLL_LOSS_LOCK_LIVE_MASK BIT(0) -#define SYS_APLL_LOSS_LOCK_LIVE_LOCKED 0 -#define SYS_APLL_LOSS_LOCK_LIVE_UNLOCKED 1 - -#endif diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 1a2e3c2e4328..6bc5791a7ec5 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -6,7 +6,7 @@ * Copyright (C) 2019 Integrated Device Technology, Inc., a Renesas Company. */ #include -#include +#include #include #include #include @@ -14,6 +14,10 @@ #include #include #include +#include +#include +#include +#include #include "ptp_private.h" #include "ptp_clockmatrix.h" @@ -32,9 +36,28 @@ static char *firmware; module_param(firmware, charp, 0); #define SETTIME_CORRECTION (0) +#define EXTTS_PERIOD_MS (95) static int _idtcm_adjfine(struct idtcm_channel *channel, long scaled_ppm); +static inline int idtcm_read(struct idtcm *idtcm, + u16 module, + u16 regaddr, + u8 *buf, + u16 count) +{ + return regmap_bulk_read(idtcm->regmap, module + regaddr, buf, count); +} + +static inline int idtcm_write(struct idtcm *idtcm, + u16 module, + u16 regaddr, + u8 *buf, + u16 count) +{ + return regmap_bulk_write(idtcm->regmap, module + regaddr, buf, count); +} + static int contains_full_configuration(struct idtcm *idtcm, const struct firmware *fw) { @@ -173,134 +196,6 @@ static enum fw_version idtcm_fw_version(const char *version) return ver; } -static int idtcm_xfer_read(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count) -{ - struct i2c_client *client = idtcm->client; - struct i2c_msg msg[2]; - int cnt; - - msg[0].addr = client->addr; - msg[0].flags = 0; - msg[0].len = 1; - msg[0].buf = ®addr; - - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].len = count; - msg[1].buf = buf; - - cnt = i2c_transfer(client->adapter, msg, 2); - - if (cnt < 0) { - dev_err(&client->dev, - "i2c_transfer failed at %d in %s, at addr: %04x!", - __LINE__, __func__, regaddr); - return cnt; - } else if (cnt != 2) { - dev_err(&client->dev, - "i2c_transfer sent only %d of %d messages", cnt, 2); - return -EIO; - } - - return 0; -} - -static int idtcm_xfer_write(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count) -{ - struct i2c_client *client = idtcm->client; - /* we add 1 byte for device register */ - u8 msg[IDTCM_MAX_WRITE_COUNT + 1]; - int cnt; - - if (count > IDTCM_MAX_WRITE_COUNT) - return -EINVAL; - - msg[0] = regaddr; - memcpy(&msg[1], buf, count); - - cnt = i2c_master_send(client, msg, count + 1); - - if (cnt < 0) { - dev_err(&client->dev, - "i2c_master_send failed at %d in %s, at addr: %04x!", - __LINE__, __func__, regaddr); - return cnt; - } - - return 0; -} - -static int idtcm_page_offset(struct idtcm *idtcm, u8 val) -{ - u8 buf[4]; - int err; - - if (idtcm->page_offset == val) - return 0; - - buf[0] = 0x0; - buf[1] = val; - buf[2] = 0x10; - buf[3] = 0x20; - - err = idtcm_xfer_write(idtcm, PAGE_ADDR, buf, sizeof(buf)); - if (err) { - idtcm->page_offset = 0xff; - dev_err(&idtcm->client->dev, "failed to set page offset"); - } else { - idtcm->page_offset = val; - } - - return err; -} - -static int _idtcm_rdwr(struct idtcm *idtcm, - u16 regaddr, - u8 *buf, - u16 count, - bool write) -{ - u8 hi; - u8 lo; - int err; - - hi = (regaddr >> 8) & 0xff; - lo = regaddr & 0xff; - - err = idtcm_page_offset(idtcm, hi); - if (err) - return err; - - if (write) - return idtcm_xfer_write(idtcm, lo, buf, count); - - return idtcm_xfer_read(idtcm, lo, buf, count); -} - -static int idtcm_read(struct idtcm *idtcm, - u16 module, - u16 regaddr, - u8 *buf, - u16 count) -{ - return _idtcm_rdwr(idtcm, module + regaddr, buf, count, false); -} - -static int idtcm_write(struct idtcm *idtcm, - u16 module, - u16 regaddr, - u8 *buf, - u16 count) -{ - return _idtcm_rdwr(idtcm, module + regaddr, buf, count, true); -} - static int clear_boot_status(struct idtcm *idtcm) { u8 buf[4] = {0}; @@ -339,11 +234,82 @@ static int wait_for_boot_status_ready(struct idtcm *idtcm) } while (i); - dev_warn(&idtcm->client->dev, "%s timed out", __func__); + dev_warn(idtcm->dev, "%s timed out", __func__); return -EBUSY; } +static int _idtcm_set_scsr_read_trig(struct idtcm_channel *channel, + enum scsr_read_trig_sel trig, u8 ref) +{ + struct idtcm *idtcm = channel->idtcm; + u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_PRIMARY_CMD); + u8 val; + int err; + + if (trig == SCSR_TOD_READ_TRIG_SEL_REFCLK) { + err = idtcm_read(idtcm, channel->tod_read_primary, + TOD_READ_PRIMARY_SEL_CFG_0, &val, sizeof(val)); + if (err) + return err; + + val &= ~(WR_REF_INDEX_MASK << WR_REF_INDEX_SHIFT); + val |= (ref << WR_REF_INDEX_SHIFT); + + err = idtcm_write(idtcm, channel->tod_read_primary, + TOD_READ_PRIMARY_SEL_CFG_0, &val, sizeof(val)); + if (err) + return err; + } + + err = idtcm_read(idtcm, channel->tod_read_primary, + tod_read_cmd, &val, sizeof(val)); + if (err) + return err; + + val &= ~(TOD_READ_TRIGGER_MASK << TOD_READ_TRIGGER_SHIFT); + val |= (trig << TOD_READ_TRIGGER_SHIFT); + val &= ~TOD_READ_TRIGGER_MODE; /* single shot */ + + err = idtcm_write(idtcm, channel->tod_read_primary, + tod_read_cmd, &val, sizeof(val)); + return err; +} + +static int idtcm_enable_extts(struct idtcm_channel *channel, u8 todn, u8 ref, + bool enable) +{ + struct idtcm *idtcm = channel->idtcm; + u8 old_mask = idtcm->extts_mask; + u8 mask = 1 << todn; + int err = 0; + + if (todn >= MAX_TOD) + return -EINVAL; + + if (enable) { + if (ref > 0xF) /* E_REF_CLK15 */ + return -EINVAL; + if (idtcm->extts_mask & mask) + return 0; + err = _idtcm_set_scsr_read_trig(&idtcm->channel[todn], + SCSR_TOD_READ_TRIG_SEL_REFCLK, + ref); + if (err == 0) { + idtcm->extts_mask |= mask; + idtcm->event_channel[todn] = channel; + idtcm->channel[todn].refn = ref; + } + } else + idtcm->extts_mask &= ~mask; + + if (old_mask == 0 && idtcm->extts_mask) + schedule_delayed_work(&idtcm->extts_work, + msecs_to_jiffies(EXTTS_PERIOD_MS)); + + return err; +} + static int read_sys_apll_status(struct idtcm *idtcm, u8 *status) { return idtcm_read(idtcm, STATUS, DPLL_SYS_APLL_STATUS, status, @@ -380,7 +346,7 @@ static int wait_for_sys_apll_dpll_lock(struct idtcm *idtcm) } else if (dpll == DPLL_STATE_FREERUN || dpll == DPLL_STATE_HOLDOVER || dpll == DPLL_STATE_OPEN_LOOP) { - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "No wait state: DPLL_SYS_STATE %d", dpll); return -EPERM; } @@ -388,7 +354,7 @@ static int wait_for_sys_apll_dpll_lock(struct idtcm *idtcm) msleep(LOCK_POLL_INTERVAL_MS); } while (time_is_after_jiffies(timeout)); - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "%d ms lock timeout: SYS APLL Loss Lock %d SYS DPLL state %d", LOCK_TIMEOUT_MS, apll, dpll); @@ -398,39 +364,27 @@ static int wait_for_sys_apll_dpll_lock(struct idtcm *idtcm) static void wait_for_chip_ready(struct idtcm *idtcm) { if (wait_for_boot_status_ready(idtcm)) - dev_warn(&idtcm->client->dev, "BOOT_STATUS != 0xA0"); + dev_warn(idtcm->dev, "BOOT_STATUS != 0xA0"); if (wait_for_sys_apll_dpll_lock(idtcm)) - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "Continuing while SYS APLL/DPLL is not locked"); } static int _idtcm_gettime(struct idtcm_channel *channel, - struct timespec64 *ts) + struct timespec64 *ts, u8 timeout) { struct idtcm *idtcm = channel->idtcm; u16 tod_read_cmd = IDTCM_FW_REG(idtcm->fw_ver, V520, TOD_READ_PRIMARY_CMD); u8 buf[TOD_BYTE_COUNT]; - u8 timeout = 10; u8 trigger; int err; - err = idtcm_read(idtcm, channel->tod_read_primary, - tod_read_cmd, &trigger, sizeof(trigger)); - if (err) - return err; - - trigger &= ~(TOD_READ_TRIGGER_MASK << TOD_READ_TRIGGER_SHIFT); - trigger |= (1 << TOD_READ_TRIGGER_SHIFT); - trigger &= ~TOD_READ_TRIGGER_MODE; /* single shot */ - - err = idtcm_write(idtcm, channel->tod_read_primary, - tod_read_cmd, &trigger, sizeof(trigger)); - if (err) - return err; - /* wait trigger to be 0 */ - while (trigger & TOD_READ_TRIGGER_MASK) { + do { + if (timeout-- == 0) + return -EIO; + if (idtcm->calculate_overhead_flag) idtcm->start_time = ktime_get_raw(); @@ -439,10 +393,7 @@ static int _idtcm_gettime(struct idtcm_channel *channel, sizeof(trigger)); if (err) return err; - - if (--timeout == 0) - return -EIO; - } + } while (trigger & TOD_READ_TRIGGER_MASK); err = idtcm_read(idtcm, channel->tod_read_primary, TOD_READ_PRIMARY, buf, sizeof(buf)); @@ -454,6 +405,79 @@ static int _idtcm_gettime(struct idtcm_channel *channel, return err; } +static int idtcm_extts_check_channel(struct idtcm *idtcm, u8 todn) +{ + struct idtcm_channel *ptp_channel, *extts_channel; + struct ptp_clock_event event; + struct timespec64 ts; + u32 dco_delay = 0; + int err; + + extts_channel = &idtcm->channel[todn]; + ptp_channel = idtcm->event_channel[todn]; + if (extts_channel == ptp_channel) + dco_delay = ptp_channel->dco_delay; + + err = _idtcm_gettime(extts_channel, &ts, 1); + if (err == 0) { + event.type = PTP_CLOCK_EXTTS; + event.index = todn; + event.timestamp = timespec64_to_ns(&ts) - dco_delay; + ptp_clock_event(ptp_channel->ptp_clock, &event); + } + return err; +} + +static u8 idtcm_enable_extts_mask(struct idtcm_channel *channel, + u8 extts_mask, bool enable) +{ + struct idtcm *idtcm = channel->idtcm; + int i, err; + + for (i = 0; i < MAX_TOD; i++) { + u8 mask = 1 << i; + u8 refn = idtcm->channel[i].refn; + + if (extts_mask & mask) { + /* check extts before disabling it */ + if (enable == false) { + err = idtcm_extts_check_channel(idtcm, i); + /* trigger happened so we won't re-enable it */ + if (err == 0) + extts_mask &= ~mask; + } + (void)idtcm_enable_extts(channel, i, refn, enable); + } + } + + return extts_mask; +} + +static int _idtcm_gettime_immediate(struct idtcm_channel *channel, + struct timespec64 *ts) +{ + struct idtcm *idtcm = channel->idtcm; + u8 extts_mask = 0; + int err; + + /* Disable extts */ + if (idtcm->extts_mask) { + extts_mask = idtcm_enable_extts_mask(channel, idtcm->extts_mask, + false); + } + + err = _idtcm_set_scsr_read_trig(channel, + SCSR_TOD_READ_TRIG_SEL_IMMEDIATE, 0); + if (err == 0) + err = _idtcm_gettime(channel, ts, 10); + + /* Re-enable extts */ + if (extts_mask) + idtcm_enable_extts_mask(channel, extts_mask, true); + + return err; +} + static int _sync_pll_output(struct idtcm *idtcm, u8 pll, u8 sync_src, @@ -777,7 +801,7 @@ static int _idtcm_set_dpll_scsr_tod(struct idtcm_channel *channel, break; if (++count > 20) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Timed out waiting for the write counter"); return -EIO; } @@ -842,7 +866,7 @@ static int _idtcm_settime_deprecated(struct idtcm_channel *channel, err = _idtcm_set_dpll_hw_tod(channel, ts, HW_TOD_WR_TRIG_SEL_MSB); if (err) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "%s: Set HW ToD failed", __func__); return err; } @@ -1001,7 +1025,7 @@ static int _idtcm_adjtime_deprecated(struct idtcm_channel *channel, s64 delta) if (err) return err; - err = _idtcm_gettime(channel, &ts); + err = _idtcm_gettime_immediate(channel, &ts); if (err) return err; @@ -1035,14 +1059,14 @@ static int idtcm_state_machine_reset(struct idtcm *idtcm) read_boot_status(idtcm, &status); if (status == 0xA0) { - dev_dbg(&idtcm->client->dev, + dev_dbg(idtcm->dev, "SM_RESET completed in %d ms", i * 100); break; } } if (!status) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Timed out waiting for CM_RESET to complete"); } @@ -1139,12 +1163,12 @@ static int set_pll_output_mask(struct idtcm *idtcm, u16 addr, u8 val) static int set_tod_ptp_pll(struct idtcm *idtcm, u8 index, u8 pll) { if (index >= MAX_TOD) { - dev_err(&idtcm->client->dev, "ToD%d not supported", index); + dev_err(idtcm->dev, "ToD%d not supported", index); return -EINVAL; } if (pll >= MAX_PLL) { - dev_err(&idtcm->client->dev, "Pll%d not supported", pll); + dev_err(idtcm->dev, "Pll%d not supported", pll); return -EINVAL; } @@ -1162,7 +1186,7 @@ static int check_and_set_masks(struct idtcm *idtcm, switch (regaddr) { case TOD_MASK_ADDR: if ((val & 0xf0) || !(val & 0x0f)) { - dev_err(&idtcm->client->dev, "Invalid TOD mask 0x%02x", val); + dev_err(idtcm->dev, "Invalid TOD mask 0x%02x", val); err = -EINVAL; } else { idtcm->tod_mask = val; @@ -1193,13 +1217,13 @@ static void display_pll_and_masks(struct idtcm *idtcm) u8 i; u8 mask; - dev_dbg(&idtcm->client->dev, "tod_mask = 0x%02x", idtcm->tod_mask); + dev_dbg(idtcm->dev, "tod_mask = 0x%02x", idtcm->tod_mask); for (i = 0; i < MAX_TOD; i++) { mask = 1 << i; if (mask & idtcm->tod_mask) - dev_dbg(&idtcm->client->dev, + dev_dbg(idtcm->dev, "TOD%d pll = %d output_mask = 0x%04x", i, idtcm->channel[i].pll, idtcm->channel[i].output_mask); @@ -1222,16 +1246,16 @@ static int idtcm_load_firmware(struct idtcm *idtcm, if (firmware) /* module parameter */ snprintf(fname, sizeof(fname), "%s", firmware); - dev_info(&idtcm->client->dev, "firmware '%s'", fname); + dev_info(idtcm->dev, "requesting firmware '%s'", fname); err = request_firmware(&fw, fname, dev); if (err) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); return err; } - dev_dbg(&idtcm->client->dev, "firmware size %zu bytes", fw->size); + dev_dbg(idtcm->dev, "firmware size %zu bytes", fw->size); rec = (struct idtcm_fwrc *) fw->data; @@ -1240,7 +1264,7 @@ static int idtcm_load_firmware(struct idtcm *idtcm, for (len = fw->size; len > 0; len -= sizeof(*rec)) { if (rec->reserved) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "bad firmware, reserved field non-zero"); err = -EINVAL; } else { @@ -1291,7 +1315,7 @@ static int idtcm_output_enable(struct idtcm_channel *channel, base = get_output_base_addr(idtcm->fw_ver, outn); if (!(base > 0)) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "%s - Unsupported out%d", __func__, outn); return base; } @@ -1333,8 +1357,8 @@ static int idtcm_output_mask_enable(struct idtcm_channel *channel, } static int idtcm_perout_enable(struct idtcm_channel *channel, - bool enable, - struct ptp_perout_request *perout) + struct ptp_perout_request *perout, + bool enable) { struct idtcm *idtcm = channel->idtcm; unsigned int flags = perout->flags; @@ -1347,7 +1371,7 @@ static int idtcm_perout_enable(struct idtcm_channel *channel, err = idtcm_output_enable(channel, enable, perout->index); if (err) { - dev_err(&idtcm->client->dev, "Unable to set output enable"); + dev_err(idtcm->dev, "Unable to set output enable"); return err; } @@ -1448,7 +1472,7 @@ static int configure_dpll_mode_write_frequency(struct idtcm_channel *channel) err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_FREQUENCY); if (err) - dev_err(&idtcm->client->dev, "Failed to set pll mode to write frequency"); + dev_err(idtcm->dev, "Failed to set pll mode to write frequency"); else channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; @@ -1463,7 +1487,7 @@ static int configure_dpll_mode_write_phase(struct idtcm_channel *channel) err = idtcm_set_pll_mode(channel, PLL_MODE_WRITE_PHASE); if (err) - dev_err(&idtcm->client->dev, "Failed to set pll mode to write phase"); + dev_err(idtcm->dev, "Failed to set pll mode to write phase"); else channel->mode = PTP_PLL_MODE_WRITE_PHASE; @@ -1478,7 +1502,7 @@ static int configure_manual_reference_write_frequency(struct idtcm_channel *chan err = idtcm_set_manual_reference(channel, MANU_REF_WRITE_FREQUENCY); if (err) - dev_err(&idtcm->client->dev, "Failed to set manual reference to write frequency"); + dev_err(idtcm->dev, "Failed to set manual reference to write frequency"); else channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; @@ -1493,7 +1517,7 @@ static int configure_manual_reference_write_phase(struct idtcm_channel *channel) err = idtcm_set_manual_reference(channel, MANU_REF_WRITE_PHASE); if (err) - dev_err(&idtcm->client->dev, "Failed to set manual reference to write phase"); + dev_err(idtcm->dev, "Failed to set manual reference to write phase"); else channel->mode = PTP_PLL_MODE_WRITE_PHASE; @@ -1518,11 +1542,11 @@ static long idtcm_work_handler(struct ptp_clock_info *ptp) struct idtcm_channel *channel = container_of(ptp, struct idtcm_channel, caps); struct idtcm *idtcm = channel->idtcm; - mutex_lock(&idtcm->reg_lock); + mutex_lock(idtcm->lock); (void)idtcm_stop_phase_pull_in(channel); - mutex_unlock(&idtcm->reg_lock); + mutex_unlock(idtcm->lock); /* Return a negative value here to not reschedule */ return -1; @@ -1533,8 +1557,8 @@ static s32 phase_pull_in_scaled_ppm(s32 current_ppm, s32 phase_pull_in_ppb) /* ppb = scaled_ppm * 125 / 2^13 */ /* scaled_ppm = ppb * 2^13 / 125 */ - s64 max_scaled_ppm = (PHASE_PULL_IN_MAX_PPB << 13) / 125; - s64 scaled_ppm = (phase_pull_in_ppb << 13) / 125; + s64 max_scaled_ppm = div_s64((s64)PHASE_PULL_IN_MAX_PPB << 13, 125); + s64 scaled_ppm = div_s64((s64)phase_pull_in_ppb << 13, 125); current_ppm += scaled_ppm; @@ -1607,7 +1631,7 @@ static int initialize_operating_mode_with_manual_reference(struct idtcm_channel channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; break; default: - dev_warn(&idtcm->client->dev, + dev_warn(idtcm->dev, "Unsupported MANUAL_REFERENCE: 0x%02x", ref); } @@ -1633,7 +1657,7 @@ static int initialize_operating_mode_with_pll_mode(struct idtcm_channel *channel channel->mode = PTP_PLL_MODE_WRITE_FREQUENCY; break; default: - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Unsupported PLL_MODE: 0x%02x", mode); err = -EINVAL; } @@ -1652,14 +1676,14 @@ static int initialize_dco_operating_mode(struct idtcm_channel *channel) err = idtcm_get_pll_mode(channel, &mode); if (err) { - dev_err(&idtcm->client->dev, "Unable to read pll mode!"); + dev_err(idtcm->dev, "Unable to read pll mode!"); return err; } if (mode == PLL_MODE_PLL) { err = idtcm_get_manual_reference(channel, &ref); if (err) { - dev_err(&idtcm->client->dev, "Unable to read manual reference!"); + dev_err(idtcm->dev, "Unable to read manual reference!"); return err; } err = initialize_operating_mode_with_manual_reference(channel, ref); @@ -1775,15 +1799,14 @@ static int idtcm_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); + mutex_lock(idtcm->lock); + err = _idtcm_gettime_immediate(channel, ts); + mutex_unlock(idtcm->lock); - err = _idtcm_gettime(channel, ts); if (err) - dev_err(&idtcm->client->dev, "Failed at line %d in %s!", + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1794,15 +1817,14 @@ static int idtcm_settime_deprecated(struct ptp_clock_info *ptp, struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_settime_deprecated(channel, ts); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1813,15 +1835,14 @@ static int idtcm_settime(struct ptp_clock_info *ptp, struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_settime(channel, ts, SCSR_TOD_WR_TYPE_SEL_ABSOLUTE); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1831,15 +1852,14 @@ static int idtcm_adjtime_deprecated(struct ptp_clock_info *ptp, s64 delta) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_adjtime_deprecated(channel, delta); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1854,13 +1874,10 @@ static int idtcm_adjtime(struct ptp_clock_info *ptp, s64 delta) if (channel->phase_pull_in == true) return 0; - mutex_lock(&idtcm->reg_lock); + mutex_lock(idtcm->lock); if (abs(delta) < PHASE_PULL_IN_THRESHOLD_NS) { err = channel->do_phase_pull_in(channel, delta, 0); - if (err) - dev_err(&idtcm->client->dev, - "Failed at line %d in %s!", __LINE__, __func__); } else { if (delta >= 0) { ts = ns_to_timespec64(delta); @@ -1870,11 +1887,13 @@ static int idtcm_adjtime(struct ptp_clock_info *ptp, s64 delta) type = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS; } err = _idtcm_settime(channel, &ts, type); - if (err) - dev_err(&idtcm->client->dev, - "Failed at line %d in %s!", __LINE__, __func__); } - mutex_unlock(&idtcm->reg_lock); + + mutex_unlock(idtcm->lock); + + if (err) + dev_err(idtcm->dev, + "Failed at line %d in %s!", __LINE__, __func__); return err; } @@ -1885,15 +1904,14 @@ static int idtcm_adjphase(struct ptp_clock_info *ptp, s32 delta) struct idtcm *idtcm = channel->idtcm; int err; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_adjphase(channel, delta); + mutex_unlock(idtcm->lock); + if (err) - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); - mutex_unlock(&idtcm->reg_lock); - return err; } @@ -1909,13 +1927,14 @@ static int idtcm_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) if (scaled_ppm == channel->current_freq_scaled_ppm) return 0; - mutex_lock(&idtcm->reg_lock); - + mutex_lock(idtcm->lock); err = _idtcm_adjfine(channel, scaled_ppm); + mutex_unlock(idtcm->lock); - mutex_unlock(&idtcm->reg_lock); - - if (!err) + if (err) + dev_err(idtcm->dev, + "Failed at line %d in %s!", __LINE__, __func__); + else channel->current_freq_scaled_ppm = scaled_ppm; return err; @@ -1924,35 +1943,38 @@ static int idtcm_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) static int idtcm_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { - int err; struct idtcm_channel *channel = container_of(ptp, struct idtcm_channel, caps); + struct idtcm *idtcm = channel->idtcm; + int err = -EOPNOTSUPP; + + mutex_lock(idtcm->lock); switch (rq->type) { case PTP_CLK_REQ_PEROUT: - if (!on) { - err = idtcm_perout_enable(channel, false, &rq->perout); - if (err) - dev_err(&channel->idtcm->client->dev, - "Failed at line %d in %s!", - __LINE__, __func__); - return err; - } - + if (!on) + err = idtcm_perout_enable(channel, &rq->perout, false); /* Only accept a 1-PPS aligned to the second. */ - if (rq->perout.start.nsec || rq->perout.period.sec != 1 || - rq->perout.period.nsec) - return -ERANGE; - - err = idtcm_perout_enable(channel, true, &rq->perout); - if (err) - dev_err(&channel->idtcm->client->dev, - "Failed at line %d in %s!", __LINE__, __func__); - return err; + else if (rq->perout.start.nsec || rq->perout.period.sec != 1 || + rq->perout.period.nsec) + err = -ERANGE; + else + err = idtcm_perout_enable(channel, &rq->perout, true); + break; + case PTP_CLK_REQ_EXTTS: + err = idtcm_enable_extts(channel, rq->extts.index, + rq->extts.rsv[0], on); + break; default: break; } - return -EOPNOTSUPP; + mutex_unlock(idtcm->lock); + + if (err) + dev_err(channel->idtcm->dev, + "Failed in %s with err %d!", __func__, err); + + return err; } static int idtcm_enable_tod(struct idtcm_channel *channel) @@ -2013,7 +2035,7 @@ static void idtcm_set_version_info(struct idtcm *idtcm) idtcm->fw_ver = idtcm_fw_version(idtcm->version); - dev_info(&idtcm->client->dev, + dev_info(idtcm->dev, "%d.%d.%d, Id: 0x%04x HW Rev: %d OTP Config Select: %d", major, minor, hotfix, product_id, hw_rev_id, config_select); @@ -2023,6 +2045,7 @@ static const struct ptp_clock_info idtcm_caps = { .owner = THIS_MODULE, .max_adj = 244000, .n_per_out = 12, + .n_ext_ts = MAX_TOD, .adjphase = &idtcm_adjphase, .adjfine = &idtcm_adjfine, .adjtime = &idtcm_adjtime, @@ -2036,6 +2059,7 @@ static const struct ptp_clock_info idtcm_caps_deprecated = { .owner = THIS_MODULE, .max_adj = 244000, .n_per_out = 12, + .n_ext_ts = MAX_TOD, .adjphase = &idtcm_adjphase, .adjfine = &idtcm_adjfine, .adjtime = &idtcm_adjtime_deprecated, @@ -2122,24 +2146,46 @@ static int configure_channel_pll(struct idtcm_channel *channel) return err; } -static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) +/* + * Compensate for the PTP DCO input-to-output delay. + * This delay is 18 FOD cycles. + */ +static u32 idtcm_get_dco_delay(struct idtcm_channel *channel) { - enum fw_version fw_ver = idtcm->fw_ver; - struct idtcm_channel *channel; + struct idtcm *idtcm = channel->idtcm; + u8 mbuf[8] = {0}; + u8 nbuf[2] = {0}; + u32 fodFreq; int err; + u64 m; + u16 n; - if (!(index < MAX_TOD)) - return -EINVAL; + err = idtcm_read(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_FOD_FREQ, mbuf, 6); + if (err) + return 0; - channel = &idtcm->channel[index]; + err = idtcm_read(idtcm, channel->dpll_ctrl_n, + DPLL_CTRL_DPLL_FOD_FREQ + 6, nbuf, 2); + if (err) + return 0; - channel->idtcm = idtcm; - channel->current_freq_scaled_ppm = 0; + m = get_unaligned_le64(mbuf); + n = get_unaligned_le16(nbuf); - /* Set pll addresses */ - err = configure_channel_pll(channel); - if (err) - return err; + if (n == 0) + n = 1; + + fodFreq = (u32)div_u64(m, n); + if (fodFreq >= 500000000) + return 18 * (u32)div_u64(NSEC_PER_SEC, fodFreq); + + return 0; +} + +static int configure_channel_tod(struct idtcm_channel *channel, u32 index) +{ + enum fw_version fw_ver = channel->idtcm->fw_ver; /* Set tod addresses */ switch (index) { @@ -2171,6 +2217,32 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) return -EINVAL; } + return 0; +} + +static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) +{ + struct idtcm_channel *channel; + int err; + + if (!(index < MAX_TOD)) + return -EINVAL; + + channel = &idtcm->channel[index]; + + channel->idtcm = idtcm; + channel->current_freq_scaled_ppm = 0; + + /* Set pll addresses */ + err = configure_channel_pll(channel); + if (err) + return err; + + /* Set tod addresses */ + err = configure_channel_tod(channel, index); + if (err) + return err; + if (idtcm->fw_ver < V487) channel->caps = idtcm_caps_deprecated; else @@ -2185,11 +2257,13 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) err = idtcm_enable_tod(channel); if (err) { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "Failed at line %d in %s!", __LINE__, __func__); return err; } + channel->dco_delay = idtcm_get_dco_delay(channel); + channel->ptp_clock = ptp_clock_register(&channel->caps, NULL); if (IS_ERR(channel->ptp_clock)) { @@ -2201,12 +2275,59 @@ static int idtcm_enable_channel(struct idtcm *idtcm, u32 index) if (!channel->ptp_clock) return -ENOTSUPP; - dev_info(&idtcm->client->dev, "PLL%d registered as ptp%d", + dev_info(idtcm->dev, "PLL%d registered as ptp%d", index, channel->ptp_clock->index); return 0; } +static int idtcm_enable_extts_channel(struct idtcm *idtcm, u32 index) +{ + struct idtcm_channel *channel; + int err; + + if (!(index < MAX_TOD)) + return -EINVAL; + + channel = &idtcm->channel[index]; + channel->idtcm = idtcm; + + /* Set tod addresses */ + err = configure_channel_tod(channel, index); + if (err) + return err; + + channel->idtcm = idtcm; + + return 0; +} + +static void idtcm_extts_check(struct work_struct *work) +{ + struct idtcm *idtcm = container_of(work, struct idtcm, extts_work.work); + int err, i; + + if (idtcm->extts_mask == 0) + return; + + mutex_lock(idtcm->lock); + for (i = 0; i < MAX_TOD; i++) { + u8 mask = 1 << i; + + if (idtcm->extts_mask & mask) { + err = idtcm_extts_check_channel(idtcm, i); + /* trigger clears itself, so clear the mask */ + if (err == 0) + idtcm->extts_mask &= ~mask; + } + } + + if (idtcm->extts_mask) + schedule_delayed_work(&idtcm->extts_work, + msecs_to_jiffies(EXTTS_PERIOD_MS)); + mutex_unlock(idtcm->lock); +} + static void ptp_clock_unregister_all(struct idtcm *idtcm) { u8 i; @@ -2222,6 +2343,7 @@ static void ptp_clock_unregister_all(struct idtcm *idtcm) static void set_default_masks(struct idtcm *idtcm) { idtcm->tod_mask = DEFAULT_TOD_MASK; + idtcm->extts_mask = 0; idtcm->channel[0].pll = DEFAULT_TOD0_PTP_PLL; idtcm->channel[1].pll = DEFAULT_TOD1_PTP_PLL; @@ -2234,158 +2356,86 @@ static void set_default_masks(struct idtcm *idtcm) idtcm->channel[3].output_mask = DEFAULT_OUTPUT_MASK_PLL3; } -static int idtcm_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int idtcm_probe(struct platform_device *pdev) { + struct rsmu_ddata *ddata = dev_get_drvdata(pdev->dev.parent); struct idtcm *idtcm; int err; u8 i; - /* Unused for now */ - (void)id; - - idtcm = devm_kzalloc(&client->dev, sizeof(struct idtcm), GFP_KERNEL); + idtcm = devm_kzalloc(&pdev->dev, sizeof(struct idtcm), GFP_KERNEL); if (!idtcm) return -ENOMEM; - idtcm->client = client; - idtcm->page_offset = 0xff; + idtcm->dev = &pdev->dev; + idtcm->mfd = pdev->dev.parent; + idtcm->lock = &ddata->lock; + idtcm->regmap = ddata->regmap; idtcm->calculate_overhead_flag = 0; + INIT_DELAYED_WORK(&idtcm->extts_work, idtcm_extts_check); + set_default_masks(idtcm); - mutex_init(&idtcm->reg_lock); - mutex_lock(&idtcm->reg_lock); + mutex_lock(idtcm->lock); idtcm_set_version_info(idtcm); - err = idtcm_load_firmware(idtcm, &client->dev); + err = idtcm_load_firmware(idtcm, &pdev->dev); + if (err) - dev_warn(&idtcm->client->dev, "loading firmware failed with %d", err); + dev_warn(idtcm->dev, "loading firmware failed with %d", err); wait_for_chip_ready(idtcm); if (idtcm->tod_mask) { for (i = 0; i < MAX_TOD; i++) { - if (idtcm->tod_mask & (1 << i)) { + if (idtcm->tod_mask & (1 << i)) err = idtcm_enable_channel(idtcm, i); - if (err) { - dev_err(&idtcm->client->dev, - "idtcm_enable_channel %d failed!", i); - break; - } + else + err = idtcm_enable_extts_channel(idtcm, i); + if (err) { + dev_err(idtcm->dev, + "idtcm_enable_channel %d failed!", i); + break; } } } else { - dev_err(&idtcm->client->dev, + dev_err(idtcm->dev, "no PLLs flagged as PHCs, nothing to do"); err = -ENODEV; } - mutex_unlock(&idtcm->reg_lock); + mutex_unlock(idtcm->lock); if (err) { ptp_clock_unregister_all(idtcm); return err; } - i2c_set_clientdata(client, idtcm); + platform_set_drvdata(pdev, idtcm); return 0; } -static int idtcm_remove(struct i2c_client *client) +static int idtcm_remove(struct platform_device *pdev) { - struct idtcm *idtcm = i2c_get_clientdata(client); + struct idtcm *idtcm = platform_get_drvdata(pdev); ptp_clock_unregister_all(idtcm); - mutex_destroy(&idtcm->reg_lock); + cancel_delayed_work_sync(&idtcm->extts_work); return 0; } -#ifdef CONFIG_OF -static const struct of_device_id idtcm_dt_id[] = { - { .compatible = "idt,8a34000" }, - { .compatible = "idt,8a34001" }, - { .compatible = "idt,8a34002" }, - { .compatible = "idt,8a34003" }, - { .compatible = "idt,8a34004" }, - { .compatible = "idt,8a34005" }, - { .compatible = "idt,8a34006" }, - { .compatible = "idt,8a34007" }, - { .compatible = "idt,8a34008" }, - { .compatible = "idt,8a34009" }, - { .compatible = "idt,8a34010" }, - { .compatible = "idt,8a34011" }, - { .compatible = "idt,8a34012" }, - { .compatible = "idt,8a34013" }, - { .compatible = "idt,8a34014" }, - { .compatible = "idt,8a34015" }, - { .compatible = "idt,8a34016" }, - { .compatible = "idt,8a34017" }, - { .compatible = "idt,8a34018" }, - { .compatible = "idt,8a34019" }, - { .compatible = "idt,8a34040" }, - { .compatible = "idt,8a34041" }, - { .compatible = "idt,8a34042" }, - { .compatible = "idt,8a34043" }, - { .compatible = "idt,8a34044" }, - { .compatible = "idt,8a34045" }, - { .compatible = "idt,8a34046" }, - { .compatible = "idt,8a34047" }, - { .compatible = "idt,8a34048" }, - { .compatible = "idt,8a34049" }, - {}, -}; -MODULE_DEVICE_TABLE(of, idtcm_dt_id); -#endif - -static const struct i2c_device_id idtcm_i2c_id[] = { - { "8a34000" }, - { "8a34001" }, - { "8a34002" }, - { "8a34003" }, - { "8a34004" }, - { "8a34005" }, - { "8a34006" }, - { "8a34007" }, - { "8a34008" }, - { "8a34009" }, - { "8a34010" }, - { "8a34011" }, - { "8a34012" }, - { "8a34013" }, - { "8a34014" }, - { "8a34015" }, - { "8a34016" }, - { "8a34017" }, - { "8a34018" }, - { "8a34019" }, - { "8a34040" }, - { "8a34041" }, - { "8a34042" }, - { "8a34043" }, - { "8a34044" }, - { "8a34045" }, - { "8a34046" }, - { "8a34047" }, - { "8a34048" }, - { "8a34049" }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, idtcm_i2c_id); - -static struct i2c_driver idtcm_driver = { +static struct platform_driver idtcm_driver = { .driver = { - .of_match_table = of_match_ptr(idtcm_dt_id), - .name = "idtcm", + .name = "8a3400x-phc", }, - .probe = idtcm_probe, - .remove = idtcm_remove, - .id_table = idtcm_i2c_id, + .probe = idtcm_probe, + .remove = idtcm_remove, }; -module_i2c_driver(idtcm_driver); +module_platform_driver(idtcm_driver); diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h index 833e5907c351..0f3059ae1fff 100644 --- a/drivers/ptp/ptp_clockmatrix.h +++ b/drivers/ptp/ptp_clockmatrix.h @@ -9,8 +9,8 @@ #define PTP_IDTCLOCKMATRIX_H #include - -#include "idt8a340_reg.h" +#include +#include #define FW_FILENAME "idtcm.bin" #define MAX_TOD (4) @@ -44,7 +44,6 @@ #define DEFAULT_TOD2_PTP_PLL (2) #define DEFAULT_TOD3_PTP_PLL (3) -#define POST_SM_RESET_DELAY_MS (3000) #define PHASE_PULL_IN_THRESHOLD_NS_DEPRECATED (150000) #define PHASE_PULL_IN_THRESHOLD_NS (15000) #define TOD_WRITE_OVERHEAD_COUNT_MAX (2) @@ -64,6 +63,11 @@ * Return register address based on passed in firmware version */ #define IDTCM_FW_REG(FW, VER, REG) (((FW) < (VER)) ? (REG) : (REG##_##VER)) +enum fw_version { + V_DEFAULT = 0, + V487 = 1, + V520 = 2, +}; /* PTP PLL Mode */ enum ptp_pll_mode { @@ -74,94 +78,6 @@ enum ptp_pll_mode { PTP_PLL_MODE_MAX = PTP_PLL_MODE_UNSUPPORTED, }; -/* Values of DPLL_N.DPLL_MODE.PLL_MODE */ -enum pll_mode { - PLL_MODE_MIN = 0, - PLL_MODE_PLL = PLL_MODE_MIN, - PLL_MODE_WRITE_PHASE = 1, - PLL_MODE_WRITE_FREQUENCY = 2, - PLL_MODE_GPIO_INC_DEC = 3, - PLL_MODE_SYNTHESIS = 4, - PLL_MODE_PHASE_MEASUREMENT = 5, - PLL_MODE_DISABLED = 6, - PLL_MODE_MAX = PLL_MODE_DISABLED, -}; - -/* Values of DPLL_CTRL_n.DPLL_MANU_REF_CFG.MANUAL_REFERENCE */ -enum manual_reference { - MANU_REF_MIN = 0, - MANU_REF_CLK0 = MANU_REF_MIN, - MANU_REF_CLK1, - MANU_REF_CLK2, - MANU_REF_CLK3, - MANU_REF_CLK4, - MANU_REF_CLK5, - MANU_REF_CLK6, - MANU_REF_CLK7, - MANU_REF_CLK8, - MANU_REF_CLK9, - MANU_REF_CLK10, - MANU_REF_CLK11, - MANU_REF_CLK12, - MANU_REF_CLK13, - MANU_REF_CLK14, - MANU_REF_CLK15, - MANU_REF_WRITE_PHASE, - MANU_REF_WRITE_FREQUENCY, - MANU_REF_XO_DPLL, - MANU_REF_MAX = MANU_REF_XO_DPLL, -}; - -enum hw_tod_write_trig_sel { - HW_TOD_WR_TRIG_SEL_MIN = 0, - HW_TOD_WR_TRIG_SEL_MSB = HW_TOD_WR_TRIG_SEL_MIN, - HW_TOD_WR_TRIG_SEL_RESERVED = 1, - HW_TOD_WR_TRIG_SEL_TOD_PPS = 2, - HW_TOD_WR_TRIG_SEL_IRIGB_PPS = 3, - HW_TOD_WR_TRIG_SEL_PWM_PPS = 4, - HW_TOD_WR_TRIG_SEL_GPIO = 5, - HW_TOD_WR_TRIG_SEL_FOD_SYNC = 6, - WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_FOD_SYNC, -}; - -/* 4.8.7 only */ -enum scsr_tod_write_trig_sel { - SCSR_TOD_WR_TRIG_SEL_DISABLE = 0, - SCSR_TOD_WR_TRIG_SEL_IMMEDIATE = 1, - SCSR_TOD_WR_TRIG_SEL_REFCLK = 2, - SCSR_TOD_WR_TRIG_SEL_PWMPPS = 3, - SCSR_TOD_WR_TRIG_SEL_TODPPS = 4, - SCSR_TOD_WR_TRIG_SEL_SYNCFOD = 5, - SCSR_TOD_WR_TRIG_SEL_GPIO = 6, - SCSR_TOD_WR_TRIG_SEL_MAX = SCSR_TOD_WR_TRIG_SEL_GPIO, -}; - -/* 4.8.7 only */ -enum scsr_tod_write_type_sel { - SCSR_TOD_WR_TYPE_SEL_ABSOLUTE = 0, - SCSR_TOD_WR_TYPE_SEL_DELTA_PLUS = 1, - SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS = 2, - SCSR_TOD_WR_TYPE_SEL_MAX = SCSR_TOD_WR_TYPE_SEL_DELTA_MINUS, -}; - -/* Values STATUS.DPLL_SYS_STATUS.DPLL_SYS_STATE */ -enum dpll_state { - DPLL_STATE_MIN = 0, - DPLL_STATE_FREERUN = DPLL_STATE_MIN, - DPLL_STATE_LOCKACQ = 1, - DPLL_STATE_LOCKREC = 2, - DPLL_STATE_LOCKED = 3, - DPLL_STATE_HOLDOVER = 4, - DPLL_STATE_OPEN_LOOP = 5, - DPLL_STATE_MAX = DPLL_STATE_OPEN_LOOP, -}; - -enum fw_version { - V_DEFAULT = 0, - V487 = 1, - V520 = 2, -}; - struct idtcm; struct idtcm_channel { @@ -185,25 +101,32 @@ struct idtcm_channel { s32 offset_ns, u32 max_ffo_ppb); s32 current_freq_scaled_ppm; bool phase_pull_in; + u32 dco_delay; + /* last input trigger for extts */ + u8 refn; u8 pll; u16 output_mask; }; struct idtcm { struct idtcm_channel channel[MAX_TOD]; - struct i2c_client *client; - u8 page_offset; + struct device *dev; u8 tod_mask; char version[16]; enum fw_version fw_ver; - + /* Polls for external time stamps */ + u8 extts_mask; + struct delayed_work extts_work; + /* Remember the ptp channel to report extts */ + struct idtcm_channel *event_channel[MAX_TOD]; + /* Mutex to protect operations from being interrupted */ + struct mutex *lock; + struct device *mfd; + struct regmap *regmap; /* Overhead calculation for adjtime */ u8 calculate_overhead_flag; s64 tod_write_overhead_ns; ktime_t start_time; - - /* Protects I2C read/modify/write registers from concurrent access */ - struct mutex reg_lock; }; struct idtcm_fwrc { diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h index 92d763230bdf..a18c1539a152 100644 --- a/include/linux/mfd/idt8a340_reg.h +++ b/include/linux/mfd/idt8a340_reg.h @@ -506,6 +506,10 @@ #define STATE_MODE_SHIFT (0) #define STATE_MODE_MASK (0x7) +/* Bit definitions for the DPLL_MANU_REF_CFG register */ +#define MANUAL_REFERENCE_SHIFT (0) +#define MANUAL_REFERENCE_MASK (0x1f) + /* Bit definitions for the GPIO_CFG_GBL register */ #define SUPPLY_MODE_SHIFT (0) #define SUPPLY_MODE_MASK (0x3) @@ -654,7 +658,7 @@ /* Values of DPLL_N.DPLL_MODE.PLL_MODE */ enum pll_mode { PLL_MODE_MIN = 0, - PLL_MODE_NORMAL = PLL_MODE_MIN, + PLL_MODE_PLL = PLL_MODE_MIN, PLL_MODE_WRITE_PHASE = 1, PLL_MODE_WRITE_FREQUENCY = 2, PLL_MODE_GPIO_INC_DEC = 3, @@ -664,6 +668,31 @@ enum pll_mode { PLL_MODE_MAX = PLL_MODE_DISABLED, }; +/* Values of DPLL_CTRL_n.DPLL_MANU_REF_CFG.MANUAL_REFERENCE */ +enum manual_reference { + MANU_REF_MIN = 0, + MANU_REF_CLK0 = MANU_REF_MIN, + MANU_REF_CLK1, + MANU_REF_CLK2, + MANU_REF_CLK3, + MANU_REF_CLK4, + MANU_REF_CLK5, + MANU_REF_CLK6, + MANU_REF_CLK7, + MANU_REF_CLK8, + MANU_REF_CLK9, + MANU_REF_CLK10, + MANU_REF_CLK11, + MANU_REF_CLK12, + MANU_REF_CLK13, + MANU_REF_CLK14, + MANU_REF_CLK15, + MANU_REF_WRITE_PHASE, + MANU_REF_WRITE_FREQUENCY, + MANU_REF_XO_DPLL, + MANU_REF_MAX = MANU_REF_XO_DPLL, +}; + enum hw_tod_write_trig_sel { HW_TOD_WR_TRIG_SEL_MIN = 0, HW_TOD_WR_TRIG_SEL_MSB = HW_TOD_WR_TRIG_SEL_MIN, -- cgit v1.2.3 From f6bc909e7673c30abcbdb329e7d0aa2e83c103d7 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Mon, 13 Sep 2021 17:00:57 +0100 Subject: firmware: cs_dsp: add driver to support firmware loading on Cirrus Logic DSPs wm_adsp originally provided firmware loading on some audio DSP and was implemented as an ASoC codec driver. However, the firmware loading now covers a wider range of DSP cores and peripherals containing them, beyond just audio. So it needs to be available to non-audio drivers. All the core firmware loading support has been moved into a new driver cs_dsp, leaving only the ASoC-specific parts in wm_adsp. Signed-off-by: Simon Trimmer Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20210913160057.103842-17-simont@opensource.cirrus.com Signed-off-by: Mark Brown --- MAINTAINERS | 11 + drivers/firmware/Kconfig | 1 + drivers/firmware/Makefile | 1 + drivers/firmware/cirrus/Kconfig | 5 + drivers/firmware/cirrus/Makefile | 3 + drivers/firmware/cirrus/cs_dsp.c | 3109 ++++++++++++++++++++++++++++++++ include/linux/firmware/cirrus/cs_dsp.h | 242 +++ include/linux/firmware/cirrus/wmfw.h | 202 +++ sound/soc/codecs/Kconfig | 1 + sound/soc/codecs/wm_adsp.c | 3036 +------------------------------ sound/soc/codecs/wm_adsp.h | 132 +- sound/soc/codecs/wmfw.h | 202 --- 12 files changed, 3674 insertions(+), 3271 deletions(-) create mode 100644 drivers/firmware/cirrus/Kconfig create mode 100644 drivers/firmware/cirrus/Makefile create mode 100644 drivers/firmware/cirrus/cs_dsp.c create mode 100644 include/linux/firmware/cirrus/cs_dsp.h create mode 100644 include/linux/firmware/cirrus/wmfw.h delete mode 100644 sound/soc/codecs/wmfw.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index f555bfad3ca0..dd3ed0f809a3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4445,6 +4445,17 @@ L: patches@opensource.cirrus.com S: Maintained F: sound/soc/codecs/cs* +CIRRUS LOGIC DSP FIRMWARE DRIVER +M: Simon Trimmer +M: Charles Keepax +M: Richard Fitzgerald +L: patches@opensource.cirrus.com +S: Supported +W: https://github.com/CirrusLogic/linux-drivers/wiki +T: git https://github.com/CirrusLogic/linux-drivers.git +F: drivers/firmware/cirrus/* +F: include/linux/firmware/cirrus/* + CIRRUS LOGIC EP93XX ETHERNET DRIVER M: Hartley Sweeten L: netdev@vger.kernel.org diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 220a58cf0a44..fd2a5f68acab 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -298,6 +298,7 @@ config TURRIS_MOX_RWTM source "drivers/firmware/arm_ffa/Kconfig" source "drivers/firmware/broadcom/Kconfig" +source "drivers/firmware/cirrus/Kconfig" source "drivers/firmware/google/Kconfig" source "drivers/firmware/efi/Kconfig" source "drivers/firmware/imx/Kconfig" diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index 5ced0673d94b..4e58cb474a68 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_TURRIS_MOX_RWTM) += turris-mox-rwtm.o obj-y += arm_ffa/ obj-y += arm_scmi/ obj-y += broadcom/ +obj-y += cirrus/ obj-y += meson/ obj-$(CONFIG_GOOGLE_FIRMWARE) += google/ obj-$(CONFIG_EFI) += efi/ diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig new file mode 100644 index 000000000000..f9503cb481d2 --- /dev/null +++ b/drivers/firmware/cirrus/Kconfig @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config CS_DSP + tristate + default n diff --git a/drivers/firmware/cirrus/Makefile b/drivers/firmware/cirrus/Makefile new file mode 100644 index 000000000000..f074e2638c9c --- /dev/null +++ b/drivers/firmware/cirrus/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +# +obj-$(CONFIG_CS_DSP) += cs_dsp.o diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c new file mode 100644 index 000000000000..948dd8382686 --- /dev/null +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -0,0 +1,3109 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * cs_dsp.c -- Cirrus Logic DSP firmware support + * + * Based on sound/soc/codecs/wm_adsp.c + * + * Copyright 2012 Wolfson Microelectronics plc + * Copyright (C) 2015-2021 Cirrus Logic, Inc. and + * Cirrus Logic International Semiconductor Ltd. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define cs_dsp_err(_dsp, fmt, ...) \ + dev_err(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) +#define cs_dsp_warn(_dsp, fmt, ...) \ + dev_warn(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) +#define cs_dsp_info(_dsp, fmt, ...) \ + dev_info(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) +#define cs_dsp_dbg(_dsp, fmt, ...) \ + dev_dbg(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) + +#define ADSP1_CONTROL_1 0x00 +#define ADSP1_CONTROL_2 0x02 +#define ADSP1_CONTROL_3 0x03 +#define ADSP1_CONTROL_4 0x04 +#define ADSP1_CONTROL_5 0x06 +#define ADSP1_CONTROL_6 0x07 +#define ADSP1_CONTROL_7 0x08 +#define ADSP1_CONTROL_8 0x09 +#define ADSP1_CONTROL_9 0x0A +#define ADSP1_CONTROL_10 0x0B +#define ADSP1_CONTROL_11 0x0C +#define ADSP1_CONTROL_12 0x0D +#define ADSP1_CONTROL_13 0x0F +#define ADSP1_CONTROL_14 0x10 +#define ADSP1_CONTROL_15 0x11 +#define ADSP1_CONTROL_16 0x12 +#define ADSP1_CONTROL_17 0x13 +#define ADSP1_CONTROL_18 0x14 +#define ADSP1_CONTROL_19 0x16 +#define ADSP1_CONTROL_20 0x17 +#define ADSP1_CONTROL_21 0x18 +#define ADSP1_CONTROL_22 0x1A +#define ADSP1_CONTROL_23 0x1B +#define ADSP1_CONTROL_24 0x1C +#define ADSP1_CONTROL_25 0x1E +#define ADSP1_CONTROL_26 0x20 +#define ADSP1_CONTROL_27 0x21 +#define ADSP1_CONTROL_28 0x22 +#define ADSP1_CONTROL_29 0x23 +#define ADSP1_CONTROL_30 0x24 +#define ADSP1_CONTROL_31 0x26 + +/* + * ADSP1 Control 19 + */ +#define ADSP1_WDMA_BUFFER_LENGTH_MASK 0x00FF /* DSP1_WDMA_BUFFER_LENGTH - [7:0] */ +#define ADSP1_WDMA_BUFFER_LENGTH_SHIFT 0 /* DSP1_WDMA_BUFFER_LENGTH - [7:0] */ +#define ADSP1_WDMA_BUFFER_LENGTH_WIDTH 8 /* DSP1_WDMA_BUFFER_LENGTH - [7:0] */ + +/* + * ADSP1 Control 30 + */ +#define ADSP1_DBG_CLK_ENA 0x0008 /* DSP1_DBG_CLK_ENA */ +#define ADSP1_DBG_CLK_ENA_MASK 0x0008 /* DSP1_DBG_CLK_ENA */ +#define ADSP1_DBG_CLK_ENA_SHIFT 3 /* DSP1_DBG_CLK_ENA */ +#define ADSP1_DBG_CLK_ENA_WIDTH 1 /* DSP1_DBG_CLK_ENA */ +#define ADSP1_SYS_ENA 0x0004 /* DSP1_SYS_ENA */ +#define ADSP1_SYS_ENA_MASK 0x0004 /* DSP1_SYS_ENA */ +#define ADSP1_SYS_ENA_SHIFT 2 /* DSP1_SYS_ENA */ +#define ADSP1_SYS_ENA_WIDTH 1 /* DSP1_SYS_ENA */ +#define ADSP1_CORE_ENA 0x0002 /* DSP1_CORE_ENA */ +#define ADSP1_CORE_ENA_MASK 0x0002 /* DSP1_CORE_ENA */ +#define ADSP1_CORE_ENA_SHIFT 1 /* DSP1_CORE_ENA */ +#define ADSP1_CORE_ENA_WIDTH 1 /* DSP1_CORE_ENA */ +#define ADSP1_START 0x0001 /* DSP1_START */ +#define ADSP1_START_MASK 0x0001 /* DSP1_START */ +#define ADSP1_START_SHIFT 0 /* DSP1_START */ +#define ADSP1_START_WIDTH 1 /* DSP1_START */ + +/* + * ADSP1 Control 31 + */ +#define ADSP1_CLK_SEL_MASK 0x0007 /* CLK_SEL_ENA */ +#define ADSP1_CLK_SEL_SHIFT 0 /* CLK_SEL_ENA */ +#define ADSP1_CLK_SEL_WIDTH 3 /* CLK_SEL_ENA */ + +#define ADSP2_CONTROL 0x0 +#define ADSP2_CLOCKING 0x1 +#define ADSP2V2_CLOCKING 0x2 +#define ADSP2_STATUS1 0x4 +#define ADSP2_WDMA_CONFIG_1 0x30 +#define ADSP2_WDMA_CONFIG_2 0x31 +#define ADSP2V2_WDMA_CONFIG_2 0x32 +#define ADSP2_RDMA_CONFIG_1 0x34 + +#define ADSP2_SCRATCH0 0x40 +#define ADSP2_SCRATCH1 0x41 +#define ADSP2_SCRATCH2 0x42 +#define ADSP2_SCRATCH3 0x43 + +#define ADSP2V2_SCRATCH0_1 0x40 +#define ADSP2V2_SCRATCH2_3 0x42 + +/* + * ADSP2 Control + */ +#define ADSP2_MEM_ENA 0x0010 /* DSP1_MEM_ENA */ +#define ADSP2_MEM_ENA_MASK 0x0010 /* DSP1_MEM_ENA */ +#define ADSP2_MEM_ENA_SHIFT 4 /* DSP1_MEM_ENA */ +#define ADSP2_MEM_ENA_WIDTH 1 /* DSP1_MEM_ENA */ +#define ADSP2_SYS_ENA 0x0004 /* DSP1_SYS_ENA */ +#define ADSP2_SYS_ENA_MASK 0x0004 /* DSP1_SYS_ENA */ +#define ADSP2_SYS_ENA_SHIFT 2 /* DSP1_SYS_ENA */ +#define ADSP2_SYS_ENA_WIDTH 1 /* DSP1_SYS_ENA */ +#define ADSP2_CORE_ENA 0x0002 /* DSP1_CORE_ENA */ +#define ADSP2_CORE_ENA_MASK 0x0002 /* DSP1_CORE_ENA */ +#define ADSP2_CORE_ENA_SHIFT 1 /* DSP1_CORE_ENA */ +#define ADSP2_CORE_ENA_WIDTH 1 /* DSP1_CORE_ENA */ +#define ADSP2_START 0x0001 /* DSP1_START */ +#define ADSP2_START_MASK 0x0001 /* DSP1_START */ +#define ADSP2_START_SHIFT 0 /* DSP1_START */ +#define ADSP2_START_WIDTH 1 /* DSP1_START */ + +/* + * ADSP2 clocking + */ +#define ADSP2_CLK_SEL_MASK 0x0007 /* CLK_SEL_ENA */ +#define ADSP2_CLK_SEL_SHIFT 0 /* CLK_SEL_ENA */ +#define ADSP2_CLK_SEL_WIDTH 3 /* CLK_SEL_ENA */ + +/* + * ADSP2V2 clocking + */ +#define ADSP2V2_CLK_SEL_MASK 0x70000 /* CLK_SEL_ENA */ +#define ADSP2V2_CLK_SEL_SHIFT 16 /* CLK_SEL_ENA */ +#define ADSP2V2_CLK_SEL_WIDTH 3 /* CLK_SEL_ENA */ + +#define ADSP2V2_RATE_MASK 0x7800 /* DSP_RATE */ +#define ADSP2V2_RATE_SHIFT 11 /* DSP_RATE */ +#define ADSP2V2_RATE_WIDTH 4 /* DSP_RATE */ + +/* + * ADSP2 Status 1 + */ +#define ADSP2_RAM_RDY 0x0001 +#define ADSP2_RAM_RDY_MASK 0x0001 +#define ADSP2_RAM_RDY_SHIFT 0 +#define ADSP2_RAM_RDY_WIDTH 1 + +/* + * ADSP2 Lock support + */ +#define ADSP2_LOCK_CODE_0 0x5555 +#define ADSP2_LOCK_CODE_1 0xAAAA + +#define ADSP2_WATCHDOG 0x0A +#define ADSP2_BUS_ERR_ADDR 0x52 +#define ADSP2_REGION_LOCK_STATUS 0x64 +#define ADSP2_LOCK_REGION_1_LOCK_REGION_0 0x66 +#define ADSP2_LOCK_REGION_3_LOCK_REGION_2 0x68 +#define ADSP2_LOCK_REGION_5_LOCK_REGION_4 0x6A +#define ADSP2_LOCK_REGION_7_LOCK_REGION_6 0x6C +#define ADSP2_LOCK_REGION_9_LOCK_REGION_8 0x6E +#define ADSP2_LOCK_REGION_CTRL 0x7A +#define ADSP2_PMEM_ERR_ADDR_XMEM_ERR_ADDR 0x7C + +#define ADSP2_REGION_LOCK_ERR_MASK 0x8000 +#define ADSP2_ADDR_ERR_MASK 0x4000 +#define ADSP2_WDT_TIMEOUT_STS_MASK 0x2000 +#define ADSP2_CTRL_ERR_PAUSE_ENA 0x0002 +#define ADSP2_CTRL_ERR_EINT 0x0001 + +#define ADSP2_BUS_ERR_ADDR_MASK 0x00FFFFFF +#define ADSP2_XMEM_ERR_ADDR_MASK 0x0000FFFF +#define ADSP2_PMEM_ERR_ADDR_MASK 0x7FFF0000 +#define ADSP2_PMEM_ERR_ADDR_SHIFT 16 +#define ADSP2_WDT_ENA_MASK 0xFFFFFFFD + +#define ADSP2_LOCK_REGION_SHIFT 16 + +/* + * Event control messages + */ +#define CS_DSP_FW_EVENT_SHUTDOWN 0x000001 + +/* + * HALO system info + */ +#define HALO_AHBM_WINDOW_DEBUG_0 0x02040 +#define HALO_AHBM_WINDOW_DEBUG_1 0x02044 + +/* + * HALO core + */ +#define HALO_SCRATCH1 0x005c0 +#define HALO_SCRATCH2 0x005c8 +#define HALO_SCRATCH3 0x005d0 +#define HALO_SCRATCH4 0x005d8 +#define HALO_CCM_CORE_CONTROL 0x41000 +#define HALO_CORE_SOFT_RESET 0x00010 +#define HALO_WDT_CONTROL 0x47000 + +/* + * HALO MPU banks + */ +#define HALO_MPU_XMEM_ACCESS_0 0x43000 +#define HALO_MPU_YMEM_ACCESS_0 0x43004 +#define HALO_MPU_WINDOW_ACCESS_0 0x43008 +#define HALO_MPU_XREG_ACCESS_0 0x4300C +#define HALO_MPU_YREG_ACCESS_0 0x43014 +#define HALO_MPU_XMEM_ACCESS_1 0x43018 +#define HALO_MPU_YMEM_ACCESS_1 0x4301C +#define HALO_MPU_WINDOW_ACCESS_1 0x43020 +#define HALO_MPU_XREG_ACCESS_1 0x43024 +#define HALO_MPU_YREG_ACCESS_1 0x4302C +#define HALO_MPU_XMEM_ACCESS_2 0x43030 +#define HALO_MPU_YMEM_ACCESS_2 0x43034 +#define HALO_MPU_WINDOW_ACCESS_2 0x43038 +#define HALO_MPU_XREG_ACCESS_2 0x4303C +#define HALO_MPU_YREG_ACCESS_2 0x43044 +#define HALO_MPU_XMEM_ACCESS_3 0x43048 +#define HALO_MPU_YMEM_ACCESS_3 0x4304C +#define HALO_MPU_WINDOW_ACCESS_3 0x43050 +#define HALO_MPU_XREG_ACCESS_3 0x43054 +#define HALO_MPU_YREG_ACCESS_3 0x4305C +#define HALO_MPU_XM_VIO_ADDR 0x43100 +#define HALO_MPU_XM_VIO_STATUS 0x43104 +#define HALO_MPU_YM_VIO_ADDR 0x43108 +#define HALO_MPU_YM_VIO_STATUS 0x4310C +#define HALO_MPU_PM_VIO_ADDR 0x43110 +#define HALO_MPU_PM_VIO_STATUS 0x43114 +#define HALO_MPU_LOCK_CONFIG 0x43140 + +/* + * HALO_AHBM_WINDOW_DEBUG_1 + */ +#define HALO_AHBM_CORE_ERR_ADDR_MASK 0x0fffff00 +#define HALO_AHBM_CORE_ERR_ADDR_SHIFT 8 +#define HALO_AHBM_FLAGS_ERR_MASK 0x000000ff + +/* + * HALO_CCM_CORE_CONTROL + */ +#define HALO_CORE_RESET 0x00000200 +#define HALO_CORE_EN 0x00000001 + +/* + * HALO_CORE_SOFT_RESET + */ +#define HALO_CORE_SOFT_RESET_MASK 0x00000001 + +/* + * HALO_WDT_CONTROL + */ +#define HALO_WDT_EN_MASK 0x00000001 + +/* + * HALO_MPU_?M_VIO_STATUS + */ +#define HALO_MPU_VIO_STS_MASK 0x007e0000 +#define HALO_MPU_VIO_STS_SHIFT 17 +#define HALO_MPU_VIO_ERR_WR_MASK 0x00008000 +#define HALO_MPU_VIO_ERR_SRC_MASK 0x00007fff +#define HALO_MPU_VIO_ERR_SRC_SHIFT 0 + +struct cs_dsp_ops { + bool (*validate_version)(struct cs_dsp *dsp, unsigned int version); + unsigned int (*parse_sizes)(struct cs_dsp *dsp, + const char * const file, + unsigned int pos, + const struct firmware *firmware); + int (*setup_algs)(struct cs_dsp *dsp); + unsigned int (*region_to_reg)(struct cs_dsp_region const *mem, + unsigned int offset); + + void (*show_fw_status)(struct cs_dsp *dsp); + void (*stop_watchdog)(struct cs_dsp *dsp); + + int (*enable_memory)(struct cs_dsp *dsp); + void (*disable_memory)(struct cs_dsp *dsp); + int (*lock_memory)(struct cs_dsp *dsp, unsigned int lock_regions); + + int (*enable_core)(struct cs_dsp *dsp); + void (*disable_core)(struct cs_dsp *dsp); + + int (*start_core)(struct cs_dsp *dsp); + void (*stop_core)(struct cs_dsp *dsp); +}; + +static const struct cs_dsp_ops cs_dsp_adsp1_ops; +static const struct cs_dsp_ops cs_dsp_adsp2_ops[]; +static const struct cs_dsp_ops cs_dsp_halo_ops; + +struct cs_dsp_buf { + struct list_head list; + void *buf; +}; + +static struct cs_dsp_buf *cs_dsp_buf_alloc(const void *src, size_t len, + struct list_head *list) +{ + struct cs_dsp_buf *buf = kzalloc(sizeof(*buf), GFP_KERNEL); + + if (buf == NULL) + return NULL; + + buf->buf = vmalloc(len); + if (!buf->buf) { + kfree(buf); + return NULL; + } + memcpy(buf->buf, src, len); + + if (list) + list_add_tail(&buf->list, list); + + return buf; +} + +static void cs_dsp_buf_free(struct list_head *list) +{ + while (!list_empty(list)) { + struct cs_dsp_buf *buf = list_first_entry(list, + struct cs_dsp_buf, + list); + list_del(&buf->list); + vfree(buf->buf); + kfree(buf); + } +} + +/** + * cs_dsp_mem_region_name() - Return a name string for a memory type + * @type: the memory type to match + * + * Return: A const string identifying the memory region. + */ +const char *cs_dsp_mem_region_name(unsigned int type) +{ + switch (type) { + case WMFW_ADSP1_PM: + return "PM"; + case WMFW_HALO_PM_PACKED: + return "PM_PACKED"; + case WMFW_ADSP1_DM: + return "DM"; + case WMFW_ADSP2_XM: + return "XM"; + case WMFW_HALO_XM_PACKED: + return "XM_PACKED"; + case WMFW_ADSP2_YM: + return "YM"; + case WMFW_HALO_YM_PACKED: + return "YM_PACKED"; + case WMFW_ADSP1_ZM: + return "ZM"; + default: + return NULL; + } +} +EXPORT_SYMBOL_GPL(cs_dsp_mem_region_name); + +#ifdef CONFIG_DEBUG_FS +static void cs_dsp_debugfs_save_wmfwname(struct cs_dsp *dsp, const char *s) +{ + char *tmp = kasprintf(GFP_KERNEL, "%s\n", s); + + kfree(dsp->wmfw_file_name); + dsp->wmfw_file_name = tmp; +} + +static void cs_dsp_debugfs_save_binname(struct cs_dsp *dsp, const char *s) +{ + char *tmp = kasprintf(GFP_KERNEL, "%s\n", s); + + kfree(dsp->bin_file_name); + dsp->bin_file_name = tmp; +} + +static void cs_dsp_debugfs_clear(struct cs_dsp *dsp) +{ + kfree(dsp->wmfw_file_name); + kfree(dsp->bin_file_name); + dsp->wmfw_file_name = NULL; + dsp->bin_file_name = NULL; +} + +static ssize_t cs_dsp_debugfs_wmfw_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct cs_dsp *dsp = file->private_data; + ssize_t ret; + + mutex_lock(&dsp->pwr_lock); + + if (!dsp->wmfw_file_name || !dsp->booted) + ret = 0; + else + ret = simple_read_from_buffer(user_buf, count, ppos, + dsp->wmfw_file_name, + strlen(dsp->wmfw_file_name)); + + mutex_unlock(&dsp->pwr_lock); + return ret; +} + +static ssize_t cs_dsp_debugfs_bin_read(struct file *file, + char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct cs_dsp *dsp = file->private_data; + ssize_t ret; + + mutex_lock(&dsp->pwr_lock); + + if (!dsp->bin_file_name || !dsp->booted) + ret = 0; + else + ret = simple_read_from_buffer(user_buf, count, ppos, + dsp->bin_file_name, + strlen(dsp->bin_file_name)); + + mutex_unlock(&dsp->pwr_lock); + return ret; +} + +static const struct { + const char *name; + const struct file_operations fops; +} cs_dsp_debugfs_fops[] = { + { + .name = "wmfw_file_name", + .fops = { + .open = simple_open, + .read = cs_dsp_debugfs_wmfw_read, + }, + }, + { + .name = "bin_file_name", + .fops = { + .open = simple_open, + .read = cs_dsp_debugfs_bin_read, + }, + }, +}; + +/** + * cs_dsp_init_debugfs() - Create and populate DSP representation in debugfs + * @dsp: pointer to DSP structure + * @debugfs_root: pointer to debugfs directory in which to create this DSP + * representation + */ +void cs_dsp_init_debugfs(struct cs_dsp *dsp, struct dentry *debugfs_root) +{ + struct dentry *root = NULL; + int i; + + root = debugfs_create_dir(dsp->name, debugfs_root); + + debugfs_create_bool("booted", 0444, root, &dsp->booted); + debugfs_create_bool("running", 0444, root, &dsp->running); + debugfs_create_x32("fw_id", 0444, root, &dsp->fw_id); + debugfs_create_x32("fw_version", 0444, root, &dsp->fw_id_version); + + for (i = 0; i < ARRAY_SIZE(cs_dsp_debugfs_fops); ++i) + debugfs_create_file(cs_dsp_debugfs_fops[i].name, 0444, root, + dsp, &cs_dsp_debugfs_fops[i].fops); + + dsp->debugfs_root = root; +} +EXPORT_SYMBOL_GPL(cs_dsp_init_debugfs); + +/** + * cs_dsp_cleanup_debugfs() - Removes DSP representation from debugfs + * @dsp: pointer to DSP structure + */ +void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp) +{ + cs_dsp_debugfs_clear(dsp); + debugfs_remove_recursive(dsp->debugfs_root); + dsp->debugfs_root = NULL; +} +EXPORT_SYMBOL_GPL(cs_dsp_cleanup_debugfs); +#else +void cs_dsp_init_debugfs(struct cs_dsp *dsp, struct dentry *debugfs_root) +{ +} +EXPORT_SYMBOL_GPL(cs_dsp_init_debugfs); + +void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp) +{ +} +EXPORT_SYMBOL_GPL(cs_dsp_cleanup_debugfs); + +static inline void cs_dsp_debugfs_save_wmfwname(struct cs_dsp *dsp, + const char *s) +{ +} + +static inline void cs_dsp_debugfs_save_binname(struct cs_dsp *dsp, + const char *s) +{ +} + +static inline void cs_dsp_debugfs_clear(struct cs_dsp *dsp) +{ +} +#endif + +static const struct cs_dsp_region *cs_dsp_find_region(struct cs_dsp *dsp, + int type) +{ + int i; + + for (i = 0; i < dsp->num_mems; i++) + if (dsp->mem[i].type == type) + return &dsp->mem[i]; + + return NULL; +} + +static unsigned int cs_dsp_region_to_reg(struct cs_dsp_region const *mem, + unsigned int offset) +{ + switch (mem->type) { + case WMFW_ADSP1_PM: + return mem->base + (offset * 3); + case WMFW_ADSP1_DM: + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + case WMFW_ADSP1_ZM: + return mem->base + (offset * 2); + default: + WARN(1, "Unknown memory region type"); + return offset; + } +} + +static unsigned int cs_dsp_halo_region_to_reg(struct cs_dsp_region const *mem, + unsigned int offset) +{ + switch (mem->type) { + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + return mem->base + (offset * 4); + case WMFW_HALO_XM_PACKED: + case WMFW_HALO_YM_PACKED: + return (mem->base + (offset * 3)) & ~0x3; + case WMFW_HALO_PM_PACKED: + return mem->base + (offset * 5); + default: + WARN(1, "Unknown memory region type"); + return offset; + } +} + +static void cs_dsp_read_fw_status(struct cs_dsp *dsp, + int noffs, unsigned int *offs) +{ + unsigned int i; + int ret; + + for (i = 0; i < noffs; ++i) { + ret = regmap_read(dsp->regmap, dsp->base + offs[i], &offs[i]); + if (ret) { + cs_dsp_err(dsp, "Failed to read SCRATCH%u: %d\n", i, ret); + return; + } + } +} + +static void cs_dsp_adsp2_show_fw_status(struct cs_dsp *dsp) +{ + unsigned int offs[] = { + ADSP2_SCRATCH0, ADSP2_SCRATCH1, ADSP2_SCRATCH2, ADSP2_SCRATCH3, + }; + + cs_dsp_read_fw_status(dsp, ARRAY_SIZE(offs), offs); + + cs_dsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", + offs[0], offs[1], offs[2], offs[3]); +} + +static void cs_dsp_adsp2v2_show_fw_status(struct cs_dsp *dsp) +{ + unsigned int offs[] = { ADSP2V2_SCRATCH0_1, ADSP2V2_SCRATCH2_3 }; + + cs_dsp_read_fw_status(dsp, ARRAY_SIZE(offs), offs); + + cs_dsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", + offs[0] & 0xFFFF, offs[0] >> 16, + offs[1] & 0xFFFF, offs[1] >> 16); +} + +static void cs_dsp_halo_show_fw_status(struct cs_dsp *dsp) +{ + unsigned int offs[] = { + HALO_SCRATCH1, HALO_SCRATCH2, HALO_SCRATCH3, HALO_SCRATCH4, + }; + + cs_dsp_read_fw_status(dsp, ARRAY_SIZE(offs), offs); + + cs_dsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", + offs[0], offs[1], offs[2], offs[3]); +} + +static int cs_dsp_coeff_base_reg(struct cs_dsp_coeff_ctl *ctl, unsigned int *reg) +{ + const struct cs_dsp_alg_region *alg_region = &ctl->alg_region; + struct cs_dsp *dsp = ctl->dsp; + const struct cs_dsp_region *mem; + + mem = cs_dsp_find_region(dsp, alg_region->type); + if (!mem) { + cs_dsp_err(dsp, "No base for region %x\n", + alg_region->type); + return -EINVAL; + } + + *reg = dsp->ops->region_to_reg(mem, ctl->alg_region.base + ctl->offset); + + return 0; +} + +/** + * cs_dsp_coeff_write_acked_control() - Sends event_id to the acked control + * @ctl: pointer to acked coefficient control + * @event_id: the value to write to the given acked control + * + * Once the value has been written to the control the function shall block + * until the running firmware acknowledges the write or timeout is exceeded. + * + * Must be called with pwr_lock held. + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id) +{ + struct cs_dsp *dsp = ctl->dsp; + __be32 val = cpu_to_be32(event_id); + unsigned int reg; + int i, ret; + + if (!dsp->running) + return -EPERM; + + ret = cs_dsp_coeff_base_reg(ctl, ®); + if (ret) + return ret; + + cs_dsp_dbg(dsp, "Sending 0x%x to acked control alg 0x%x %s:0x%x\n", + event_id, ctl->alg_region.alg, + cs_dsp_mem_region_name(ctl->alg_region.type), ctl->offset); + + ret = regmap_raw_write(dsp->regmap, reg, &val, sizeof(val)); + if (ret) { + cs_dsp_err(dsp, "Failed to write %x: %d\n", reg, ret); + return ret; + } + + /* + * Poll for ack, we initially poll at ~1ms intervals for firmwares + * that respond quickly, then go to ~10ms polls. A firmware is unlikely + * to ack instantly so we do the first 1ms delay before reading the + * control to avoid a pointless bus transaction + */ + for (i = 0; i < CS_DSP_ACKED_CTL_TIMEOUT_MS;) { + switch (i) { + case 0 ... CS_DSP_ACKED_CTL_N_QUICKPOLLS - 1: + usleep_range(1000, 2000); + i++; + break; + default: + usleep_range(10000, 20000); + i += 10; + break; + } + + ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val)); + if (ret) { + cs_dsp_err(dsp, "Failed to read %x: %d\n", reg, ret); + return ret; + } + + if (val == 0) { + cs_dsp_dbg(dsp, "Acked control ACKED at poll %u\n", i); + return 0; + } + } + + cs_dsp_warn(dsp, "Acked control @0x%x alg:0x%x %s:0x%x timed out\n", + reg, ctl->alg_region.alg, + cs_dsp_mem_region_name(ctl->alg_region.type), + ctl->offset); + + return -ETIMEDOUT; +} +EXPORT_SYMBOL_GPL(cs_dsp_coeff_write_acked_control); + +static int cs_dsp_coeff_write_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, + const void *buf, size_t len) +{ + struct cs_dsp *dsp = ctl->dsp; + void *scratch; + int ret; + unsigned int reg; + + ret = cs_dsp_coeff_base_reg(ctl, ®); + if (ret) + return ret; + + scratch = kmemdup(buf, len, GFP_KERNEL | GFP_DMA); + if (!scratch) + return -ENOMEM; + + ret = regmap_raw_write(dsp->regmap, reg, scratch, + len); + if (ret) { + cs_dsp_err(dsp, "Failed to write %zu bytes to %x: %d\n", + len, reg, ret); + kfree(scratch); + return ret; + } + cs_dsp_dbg(dsp, "Wrote %zu bytes to %x\n", len, reg); + + kfree(scratch); + + return 0; +} + +/** + * cs_dsp_coeff_write_ctrl() - Writes the given buffer to the given coefficient control + * @ctl: pointer to coefficient control + * @buf: the buffer to write to the given control + * @len: the length of the buffer + * + * Must be called with pwr_lock held. + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_t len) +{ + int ret = 0; + + if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) + ret = -EPERM; + else if (buf != ctl->cache) + memcpy(ctl->cache, buf, len); + + ctl->set = 1; + if (ctl->enabled && ctl->dsp->running) + ret = cs_dsp_coeff_write_ctrl_raw(ctl, buf, len); + + return ret; +} +EXPORT_SYMBOL_GPL(cs_dsp_coeff_write_ctrl); + +static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len) +{ + struct cs_dsp *dsp = ctl->dsp; + void *scratch; + int ret; + unsigned int reg; + + ret = cs_dsp_coeff_base_reg(ctl, ®); + if (ret) + return ret; + + scratch = kmalloc(len, GFP_KERNEL | GFP_DMA); + if (!scratch) + return -ENOMEM; + + ret = regmap_raw_read(dsp->regmap, reg, scratch, len); + if (ret) { + cs_dsp_err(dsp, "Failed to read %zu bytes from %x: %d\n", + len, reg, ret); + kfree(scratch); + return ret; + } + cs_dsp_dbg(dsp, "Read %zu bytes from %x\n", len, reg); + + memcpy(buf, scratch, len); + kfree(scratch); + + return 0; +} + +/** + * cs_dsp_coeff_read_ctrl() - Reads the given coefficient control into the given buffer + * @ctl: pointer to coefficient control + * @buf: the buffer to store to the given control + * @len: the length of the buffer + * + * Must be called with pwr_lock held. + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len) +{ + int ret = 0; + + if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) { + if (ctl->enabled && ctl->dsp->running) + return cs_dsp_coeff_read_ctrl_raw(ctl, buf, len); + else + return -EPERM; + } else { + if (!ctl->flags && ctl->enabled && ctl->dsp->running) + ret = cs_dsp_coeff_read_ctrl_raw(ctl, ctl->cache, ctl->len); + + if (buf != ctl->cache) + memcpy(buf, ctl->cache, len); + } + + return ret; +} +EXPORT_SYMBOL_GPL(cs_dsp_coeff_read_ctrl); + +static int cs_dsp_coeff_init_control_caches(struct cs_dsp *dsp) +{ + struct cs_dsp_coeff_ctl *ctl; + int ret; + + list_for_each_entry(ctl, &dsp->ctl_list, list) { + if (!ctl->enabled || ctl->set) + continue; + if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) + continue; + + /* + * For readable controls populate the cache from the DSP memory. + * For non-readable controls the cache was zero-filled when + * created so we don't need to do anything. + */ + if (!ctl->flags || (ctl->flags & WMFW_CTL_FLAG_READABLE)) { + ret = cs_dsp_coeff_read_ctrl_raw(ctl, ctl->cache, ctl->len); + if (ret < 0) + return ret; + } + } + + return 0; +} + +static int cs_dsp_coeff_sync_controls(struct cs_dsp *dsp) +{ + struct cs_dsp_coeff_ctl *ctl; + int ret; + + list_for_each_entry(ctl, &dsp->ctl_list, list) { + if (!ctl->enabled) + continue; + if (ctl->set && !(ctl->flags & WMFW_CTL_FLAG_VOLATILE)) { + ret = cs_dsp_coeff_write_ctrl_raw(ctl, ctl->cache, + ctl->len); + if (ret < 0) + return ret; + } + } + + return 0; +} + +static void cs_dsp_signal_event_controls(struct cs_dsp *dsp, + unsigned int event) +{ + struct cs_dsp_coeff_ctl *ctl; + int ret; + + list_for_each_entry(ctl, &dsp->ctl_list, list) { + if (ctl->type != WMFW_CTL_TYPE_HOSTEVENT) + continue; + + if (!ctl->enabled) + continue; + + ret = cs_dsp_coeff_write_acked_control(ctl, event); + if (ret) + cs_dsp_warn(dsp, + "Failed to send 0x%x event to alg 0x%x (%d)\n", + event, ctl->alg_region.alg, ret); + } +} + +static void cs_dsp_free_ctl_blk(struct cs_dsp_coeff_ctl *ctl) +{ + kfree(ctl->cache); + kfree(ctl->subname); + kfree(ctl); +} + +static int cs_dsp_create_control(struct cs_dsp *dsp, + const struct cs_dsp_alg_region *alg_region, + unsigned int offset, unsigned int len, + const char *subname, unsigned int subname_len, + unsigned int flags, unsigned int type) +{ + struct cs_dsp_coeff_ctl *ctl; + int ret; + + list_for_each_entry(ctl, &dsp->ctl_list, list) { + if (ctl->fw_name == dsp->fw_name && + ctl->alg_region.alg == alg_region->alg && + ctl->alg_region.type == alg_region->type) { + if ((!subname && !ctl->subname) || + (subname && !strncmp(ctl->subname, subname, ctl->subname_len))) { + if (!ctl->enabled) + ctl->enabled = 1; + return 0; + } + } + } + + ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); + if (!ctl) + return -ENOMEM; + + ctl->fw_name = dsp->fw_name; + ctl->alg_region = *alg_region; + if (subname && dsp->fw_ver >= 2) { + ctl->subname_len = subname_len; + ctl->subname = kmemdup(subname, + strlen(subname) + 1, GFP_KERNEL); + if (!ctl->subname) { + ret = -ENOMEM; + goto err_ctl; + } + } + ctl->enabled = 1; + ctl->set = 0; + ctl->dsp = dsp; + + ctl->flags = flags; + ctl->type = type; + ctl->offset = offset; + ctl->len = len; + ctl->cache = kzalloc(ctl->len, GFP_KERNEL); + if (!ctl->cache) { + ret = -ENOMEM; + goto err_ctl_subname; + } + + list_add(&ctl->list, &dsp->ctl_list); + + if (dsp->client_ops->control_add) { + ret = dsp->client_ops->control_add(ctl); + if (ret) + goto err_list_del; + } + + return 0; + +err_list_del: + list_del(&ctl->list); + kfree(ctl->cache); +err_ctl_subname: + kfree(ctl->subname); +err_ctl: + kfree(ctl); + + return ret; +} + +struct cs_dsp_coeff_parsed_alg { + int id; + const u8 *name; + int name_len; + int ncoeff; +}; + +struct cs_dsp_coeff_parsed_coeff { + int offset; + int mem_type; + const u8 *name; + int name_len; + unsigned int ctl_type; + int flags; + int len; +}; + +static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, const u8 **str) +{ + int length; + + switch (bytes) { + case 1: + length = **pos; + break; + case 2: + length = le16_to_cpu(*((__le16 *)*pos)); + break; + default: + return 0; + } + + if (str) + *str = *pos + bytes; + + *pos += ((length + bytes) + 3) & ~0x03; + + return length; +} + +static int cs_dsp_coeff_parse_int(int bytes, const u8 **pos) +{ + int val = 0; + + switch (bytes) { + case 2: + val = le16_to_cpu(*((__le16 *)*pos)); + break; + case 4: + val = le32_to_cpu(*((__le32 *)*pos)); + break; + default: + break; + } + + *pos += bytes; + + return val; +} + +static inline void cs_dsp_coeff_parse_alg(struct cs_dsp *dsp, const u8 **data, + struct cs_dsp_coeff_parsed_alg *blk) +{ + const struct wmfw_adsp_alg_data *raw; + + switch (dsp->fw_ver) { + case 0: + case 1: + raw = (const struct wmfw_adsp_alg_data *)*data; + *data = raw->data; + + blk->id = le32_to_cpu(raw->id); + blk->name = raw->name; + blk->name_len = strlen(raw->name); + blk->ncoeff = le32_to_cpu(raw->ncoeff); + break; + default: + blk->id = cs_dsp_coeff_parse_int(sizeof(raw->id), data); + blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), data, + &blk->name); + cs_dsp_coeff_parse_string(sizeof(u16), data, NULL); + blk->ncoeff = cs_dsp_coeff_parse_int(sizeof(raw->ncoeff), data); + break; + } + + cs_dsp_dbg(dsp, "Algorithm ID: %#x\n", blk->id); + cs_dsp_dbg(dsp, "Algorithm name: %.*s\n", blk->name_len, blk->name); + cs_dsp_dbg(dsp, "# of coefficient descriptors: %#x\n", blk->ncoeff); +} + +static inline void cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, const u8 **data, + struct cs_dsp_coeff_parsed_coeff *blk) +{ + const struct wmfw_adsp_coeff_data *raw; + const u8 *tmp; + int length; + + switch (dsp->fw_ver) { + case 0: + case 1: + raw = (const struct wmfw_adsp_coeff_data *)*data; + *data = *data + sizeof(raw->hdr) + le32_to_cpu(raw->hdr.size); + + blk->offset = le16_to_cpu(raw->hdr.offset); + blk->mem_type = le16_to_cpu(raw->hdr.type); + blk->name = raw->name; + blk->name_len = strlen(raw->name); + blk->ctl_type = le16_to_cpu(raw->ctl_type); + blk->flags = le16_to_cpu(raw->flags); + blk->len = le32_to_cpu(raw->len); + break; + default: + tmp = *data; + blk->offset = cs_dsp_coeff_parse_int(sizeof(raw->hdr.offset), &tmp); + blk->mem_type = cs_dsp_coeff_parse_int(sizeof(raw->hdr.type), &tmp); + length = cs_dsp_coeff_parse_int(sizeof(raw->hdr.size), &tmp); + blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, + &blk->name); + cs_dsp_coeff_parse_string(sizeof(u8), &tmp, NULL); + cs_dsp_coeff_parse_string(sizeof(u16), &tmp, NULL); + blk->ctl_type = cs_dsp_coeff_parse_int(sizeof(raw->ctl_type), &tmp); + blk->flags = cs_dsp_coeff_parse_int(sizeof(raw->flags), &tmp); + blk->len = cs_dsp_coeff_parse_int(sizeof(raw->len), &tmp); + + *data = *data + sizeof(raw->hdr) + length; + break; + } + + cs_dsp_dbg(dsp, "\tCoefficient type: %#x\n", blk->mem_type); + cs_dsp_dbg(dsp, "\tCoefficient offset: %#x\n", blk->offset); + cs_dsp_dbg(dsp, "\tCoefficient name: %.*s\n", blk->name_len, blk->name); + cs_dsp_dbg(dsp, "\tCoefficient flags: %#x\n", blk->flags); + cs_dsp_dbg(dsp, "\tALSA control type: %#x\n", blk->ctl_type); + cs_dsp_dbg(dsp, "\tALSA control len: %#x\n", blk->len); +} + +static int cs_dsp_check_coeff_flags(struct cs_dsp *dsp, + const struct cs_dsp_coeff_parsed_coeff *coeff_blk, + unsigned int f_required, + unsigned int f_illegal) +{ + if ((coeff_blk->flags & f_illegal) || + ((coeff_blk->flags & f_required) != f_required)) { + cs_dsp_err(dsp, "Illegal flags 0x%x for control type 0x%x\n", + coeff_blk->flags, coeff_blk->ctl_type); + return -EINVAL; + } + + return 0; +} + +static int cs_dsp_parse_coeff(struct cs_dsp *dsp, + const struct wmfw_region *region) +{ + struct cs_dsp_alg_region alg_region = {}; + struct cs_dsp_coeff_parsed_alg alg_blk; + struct cs_dsp_coeff_parsed_coeff coeff_blk; + const u8 *data = region->data; + int i, ret; + + cs_dsp_coeff_parse_alg(dsp, &data, &alg_blk); + for (i = 0; i < alg_blk.ncoeff; i++) { + cs_dsp_coeff_parse_coeff(dsp, &data, &coeff_blk); + + switch (coeff_blk.ctl_type) { + case WMFW_CTL_TYPE_BYTES: + break; + case WMFW_CTL_TYPE_ACKED: + if (coeff_blk.flags & WMFW_CTL_FLAG_SYS) + continue; /* ignore */ + + ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, + WMFW_CTL_FLAG_VOLATILE | + WMFW_CTL_FLAG_WRITEABLE | + WMFW_CTL_FLAG_READABLE, + 0); + if (ret) + return -EINVAL; + break; + case WMFW_CTL_TYPE_HOSTEVENT: + ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, + WMFW_CTL_FLAG_SYS | + WMFW_CTL_FLAG_VOLATILE | + WMFW_CTL_FLAG_WRITEABLE | + WMFW_CTL_FLAG_READABLE, + 0); + if (ret) + return -EINVAL; + break; + case WMFW_CTL_TYPE_HOST_BUFFER: + ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, + WMFW_CTL_FLAG_SYS | + WMFW_CTL_FLAG_VOLATILE | + WMFW_CTL_FLAG_READABLE, + 0); + if (ret) + return -EINVAL; + break; + default: + cs_dsp_err(dsp, "Unknown control type: %d\n", + coeff_blk.ctl_type); + return -EINVAL; + } + + alg_region.type = coeff_blk.mem_type; + alg_region.alg = alg_blk.id; + + ret = cs_dsp_create_control(dsp, &alg_region, + coeff_blk.offset, + coeff_blk.len, + coeff_blk.name, + coeff_blk.name_len, + coeff_blk.flags, + coeff_blk.ctl_type); + if (ret < 0) + cs_dsp_err(dsp, "Failed to create control: %.*s, %d\n", + coeff_blk.name_len, coeff_blk.name, ret); + } + + return 0; +} + +static unsigned int cs_dsp_adsp1_parse_sizes(struct cs_dsp *dsp, + const char * const file, + unsigned int pos, + const struct firmware *firmware) +{ + const struct wmfw_adsp1_sizes *adsp1_sizes; + + adsp1_sizes = (void *)&firmware->data[pos]; + + cs_dsp_dbg(dsp, "%s: %d DM, %d PM, %d ZM\n", file, + le32_to_cpu(adsp1_sizes->dm), le32_to_cpu(adsp1_sizes->pm), + le32_to_cpu(adsp1_sizes->zm)); + + return pos + sizeof(*adsp1_sizes); +} + +static unsigned int cs_dsp_adsp2_parse_sizes(struct cs_dsp *dsp, + const char * const file, + unsigned int pos, + const struct firmware *firmware) +{ + const struct wmfw_adsp2_sizes *adsp2_sizes; + + adsp2_sizes = (void *)&firmware->data[pos]; + + cs_dsp_dbg(dsp, "%s: %d XM, %d YM %d PM, %d ZM\n", file, + le32_to_cpu(adsp2_sizes->xm), le32_to_cpu(adsp2_sizes->ym), + le32_to_cpu(adsp2_sizes->pm), le32_to_cpu(adsp2_sizes->zm)); + + return pos + sizeof(*adsp2_sizes); +} + +static bool cs_dsp_validate_version(struct cs_dsp *dsp, unsigned int version) +{ + switch (version) { + case 0: + cs_dsp_warn(dsp, "Deprecated file format %d\n", version); + return true; + case 1: + case 2: + return true; + default: + return false; + } +} + +static bool cs_dsp_halo_validate_version(struct cs_dsp *dsp, unsigned int version) +{ + switch (version) { + case 3: + return true; + default: + return false; + } +} + +static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, + const char *file) +{ + LIST_HEAD(buf_list); + struct regmap *regmap = dsp->regmap; + unsigned int pos = 0; + const struct wmfw_header *header; + const struct wmfw_adsp1_sizes *adsp1_sizes; + const struct wmfw_footer *footer; + const struct wmfw_region *region; + const struct cs_dsp_region *mem; + const char *region_name; + char *text = NULL; + struct cs_dsp_buf *buf; + unsigned int reg; + int regions = 0; + int ret, offset, type; + + ret = -EINVAL; + + pos = sizeof(*header) + sizeof(*adsp1_sizes) + sizeof(*footer); + if (pos >= firmware->size) { + cs_dsp_err(dsp, "%s: file too short, %zu bytes\n", + file, firmware->size); + goto out_fw; + } + + header = (void *)&firmware->data[0]; + + if (memcmp(&header->magic[0], "WMFW", 4) != 0) { + cs_dsp_err(dsp, "%s: invalid magic\n", file); + goto out_fw; + } + + if (!dsp->ops->validate_version(dsp, header->ver)) { + cs_dsp_err(dsp, "%s: unknown file format %d\n", + file, header->ver); + goto out_fw; + } + + cs_dsp_info(dsp, "Firmware version: %d\n", header->ver); + dsp->fw_ver = header->ver; + + if (header->core != dsp->type) { + cs_dsp_err(dsp, "%s: invalid core %d != %d\n", + file, header->core, dsp->type); + goto out_fw; + } + + pos = sizeof(*header); + pos = dsp->ops->parse_sizes(dsp, file, pos, firmware); + + footer = (void *)&firmware->data[pos]; + pos += sizeof(*footer); + + if (le32_to_cpu(header->len) != pos) { + cs_dsp_err(dsp, "%s: unexpected header length %d\n", + file, le32_to_cpu(header->len)); + goto out_fw; + } + + cs_dsp_dbg(dsp, "%s: timestamp %llu\n", file, + le64_to_cpu(footer->timestamp)); + + while (pos < firmware->size && + sizeof(*region) < firmware->size - pos) { + region = (void *)&(firmware->data[pos]); + region_name = "Unknown"; + reg = 0; + text = NULL; + offset = le32_to_cpu(region->offset) & 0xffffff; + type = be32_to_cpu(region->type) & 0xff; + + switch (type) { + case WMFW_NAME_TEXT: + region_name = "Firmware name"; + text = kzalloc(le32_to_cpu(region->len) + 1, + GFP_KERNEL); + break; + case WMFW_ALGORITHM_DATA: + region_name = "Algorithm"; + ret = cs_dsp_parse_coeff(dsp, region); + if (ret != 0) + goto out_fw; + break; + case WMFW_INFO_TEXT: + region_name = "Information"; + text = kzalloc(le32_to_cpu(region->len) + 1, + GFP_KERNEL); + break; + case WMFW_ABSOLUTE: + region_name = "Absolute"; + reg = offset; + break; + case WMFW_ADSP1_PM: + case WMFW_ADSP1_DM: + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + case WMFW_ADSP1_ZM: + case WMFW_HALO_PM_PACKED: + case WMFW_HALO_XM_PACKED: + case WMFW_HALO_YM_PACKED: + mem = cs_dsp_find_region(dsp, type); + if (!mem) { + cs_dsp_err(dsp, "No region of type: %x\n", type); + ret = -EINVAL; + goto out_fw; + } + + region_name = cs_dsp_mem_region_name(type); + reg = dsp->ops->region_to_reg(mem, offset); + break; + default: + cs_dsp_warn(dsp, + "%s.%d: Unknown region type %x at %d(%x)\n", + file, regions, type, pos, pos); + break; + } + + cs_dsp_dbg(dsp, "%s.%d: %d bytes at %d in %s\n", file, + regions, le32_to_cpu(region->len), offset, + region_name); + + if (le32_to_cpu(region->len) > + firmware->size - pos - sizeof(*region)) { + cs_dsp_err(dsp, + "%s.%d: %s region len %d bytes exceeds file length %zu\n", + file, regions, region_name, + le32_to_cpu(region->len), firmware->size); + ret = -EINVAL; + goto out_fw; + } + + if (text) { + memcpy(text, region->data, le32_to_cpu(region->len)); + cs_dsp_info(dsp, "%s: %s\n", file, text); + kfree(text); + text = NULL; + } + + if (reg) { + buf = cs_dsp_buf_alloc(region->data, + le32_to_cpu(region->len), + &buf_list); + if (!buf) { + cs_dsp_err(dsp, "Out of memory\n"); + ret = -ENOMEM; + goto out_fw; + } + + ret = regmap_raw_write_async(regmap, reg, buf->buf, + le32_to_cpu(region->len)); + if (ret != 0) { + cs_dsp_err(dsp, + "%s.%d: Failed to write %d bytes at %d in %s: %d\n", + file, regions, + le32_to_cpu(region->len), offset, + region_name, ret); + goto out_fw; + } + } + + pos += le32_to_cpu(region->len) + sizeof(*region); + regions++; + } + + ret = regmap_async_complete(regmap); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret); + goto out_fw; + } + + if (pos > firmware->size) + cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n", + file, regions, pos - firmware->size); + + cs_dsp_debugfs_save_wmfwname(dsp, file); + +out_fw: + regmap_async_complete(regmap); + cs_dsp_buf_free(&buf_list); + kfree(text); + + return ret; +} + +/** + * cs_dsp_get_ctl() - Finds a matching coefficient control + * @dsp: pointer to DSP structure + * @name: pointer to string to match with a control's subname + * @type: the algorithm type to match + * @alg: the algorithm id to match + * + * Find cs_dsp_coeff_ctl with input name as its subname + * + * Return: pointer to the control on success, NULL if not found + */ +struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, + unsigned int alg) +{ + struct cs_dsp_coeff_ctl *pos, *rslt = NULL; + + list_for_each_entry(pos, &dsp->ctl_list, list) { + if (!pos->subname) + continue; + if (strncmp(pos->subname, name, pos->subname_len) == 0 && + pos->fw_name == dsp->fw_name && + pos->alg_region.alg == alg && + pos->alg_region.type == type) { + rslt = pos; + break; + } + } + + return rslt; +} +EXPORT_SYMBOL_GPL(cs_dsp_get_ctl); + +static void cs_dsp_ctl_fixup_base(struct cs_dsp *dsp, + const struct cs_dsp_alg_region *alg_region) +{ + struct cs_dsp_coeff_ctl *ctl; + + list_for_each_entry(ctl, &dsp->ctl_list, list) { + if (ctl->fw_name == dsp->fw_name && + alg_region->alg == ctl->alg_region.alg && + alg_region->type == ctl->alg_region.type) { + ctl->alg_region.base = alg_region->base; + } + } +} + +static void *cs_dsp_read_algs(struct cs_dsp *dsp, size_t n_algs, + const struct cs_dsp_region *mem, + unsigned int pos, unsigned int len) +{ + void *alg; + unsigned int reg; + int ret; + __be32 val; + + if (n_algs == 0) { + cs_dsp_err(dsp, "No algorithms\n"); + return ERR_PTR(-EINVAL); + } + + if (n_algs > 1024) { + cs_dsp_err(dsp, "Algorithm count %zx excessive\n", n_algs); + return ERR_PTR(-EINVAL); + } + + /* Read the terminator first to validate the length */ + reg = dsp->ops->region_to_reg(mem, pos + len); + + ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val)); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to read algorithm list end: %d\n", + ret); + return ERR_PTR(ret); + } + + if (be32_to_cpu(val) != 0xbedead) + cs_dsp_warn(dsp, "Algorithm list end %x 0x%x != 0xbedead\n", + reg, be32_to_cpu(val)); + + /* Convert length from DSP words to bytes */ + len *= sizeof(u32); + + alg = kzalloc(len, GFP_KERNEL | GFP_DMA); + if (!alg) + return ERR_PTR(-ENOMEM); + + reg = dsp->ops->region_to_reg(mem, pos); + + ret = regmap_raw_read(dsp->regmap, reg, alg, len); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to read algorithm list: %d\n", ret); + kfree(alg); + return ERR_PTR(ret); + } + + return alg; +} + +/** + * cs_dsp_find_alg_region() - Finds a matching algorithm region + * @dsp: pointer to DSP structure + * @type: the algorithm type to match + * @id: the algorithm id to match + * + * Return: Pointer to matching algorithm region, or NULL if not found. + */ +struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp, + int type, unsigned int id) +{ + struct cs_dsp_alg_region *alg_region; + + list_for_each_entry(alg_region, &dsp->alg_regions, list) { + if (id == alg_region->alg && type == alg_region->type) + return alg_region; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(cs_dsp_find_alg_region); + +static struct cs_dsp_alg_region *cs_dsp_create_region(struct cs_dsp *dsp, + int type, __be32 id, + __be32 base) +{ + struct cs_dsp_alg_region *alg_region; + + alg_region = kzalloc(sizeof(*alg_region), GFP_KERNEL); + if (!alg_region) + return ERR_PTR(-ENOMEM); + + alg_region->type = type; + alg_region->alg = be32_to_cpu(id); + alg_region->base = be32_to_cpu(base); + + list_add_tail(&alg_region->list, &dsp->alg_regions); + + if (dsp->fw_ver > 0) + cs_dsp_ctl_fixup_base(dsp, alg_region); + + return alg_region; +} + +static void cs_dsp_free_alg_regions(struct cs_dsp *dsp) +{ + struct cs_dsp_alg_region *alg_region; + + while (!list_empty(&dsp->alg_regions)) { + alg_region = list_first_entry(&dsp->alg_regions, + struct cs_dsp_alg_region, + list); + list_del(&alg_region->list); + kfree(alg_region); + } +} + +static void cs_dsp_parse_wmfw_id_header(struct cs_dsp *dsp, + struct wmfw_id_hdr *fw, int nalgs) +{ + dsp->fw_id = be32_to_cpu(fw->id); + dsp->fw_id_version = be32_to_cpu(fw->ver); + + cs_dsp_info(dsp, "Firmware: %x v%d.%d.%d, %d algorithms\n", + dsp->fw_id, (dsp->fw_id_version & 0xff0000) >> 16, + (dsp->fw_id_version & 0xff00) >> 8, dsp->fw_id_version & 0xff, + nalgs); +} + +static void cs_dsp_parse_wmfw_v3_id_header(struct cs_dsp *dsp, + struct wmfw_v3_id_hdr *fw, int nalgs) +{ + dsp->fw_id = be32_to_cpu(fw->id); + dsp->fw_id_version = be32_to_cpu(fw->ver); + dsp->fw_vendor_id = be32_to_cpu(fw->vendor_id); + + cs_dsp_info(dsp, "Firmware: %x vendor: 0x%x v%d.%d.%d, %d algorithms\n", + dsp->fw_id, dsp->fw_vendor_id, + (dsp->fw_id_version & 0xff0000) >> 16, + (dsp->fw_id_version & 0xff00) >> 8, dsp->fw_id_version & 0xff, + nalgs); +} + +static int cs_dsp_create_regions(struct cs_dsp *dsp, __be32 id, int nregions, + const int *type, __be32 *base) +{ + struct cs_dsp_alg_region *alg_region; + int i; + + for (i = 0; i < nregions; i++) { + alg_region = cs_dsp_create_region(dsp, type[i], id, base[i]); + if (IS_ERR(alg_region)) + return PTR_ERR(alg_region); + } + + return 0; +} + +static int cs_dsp_adsp1_setup_algs(struct cs_dsp *dsp) +{ + struct wmfw_adsp1_id_hdr adsp1_id; + struct wmfw_adsp1_alg_hdr *adsp1_alg; + struct cs_dsp_alg_region *alg_region; + const struct cs_dsp_region *mem; + unsigned int pos, len; + size_t n_algs; + int i, ret; + + mem = cs_dsp_find_region(dsp, WMFW_ADSP1_DM); + if (WARN_ON(!mem)) + return -EINVAL; + + ret = regmap_raw_read(dsp->regmap, mem->base, &adsp1_id, + sizeof(adsp1_id)); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to read algorithm info: %d\n", + ret); + return ret; + } + + n_algs = be32_to_cpu(adsp1_id.n_algs); + + cs_dsp_parse_wmfw_id_header(dsp, &adsp1_id.fw, n_algs); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_ZM, + adsp1_id.fw.id, adsp1_id.zm); + if (IS_ERR(alg_region)) + return PTR_ERR(alg_region); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_DM, + adsp1_id.fw.id, adsp1_id.dm); + if (IS_ERR(alg_region)) + return PTR_ERR(alg_region); + + /* Calculate offset and length in DSP words */ + pos = sizeof(adsp1_id) / sizeof(u32); + len = (sizeof(*adsp1_alg) * n_algs) / sizeof(u32); + + adsp1_alg = cs_dsp_read_algs(dsp, n_algs, mem, pos, len); + if (IS_ERR(adsp1_alg)) + return PTR_ERR(adsp1_alg); + + for (i = 0; i < n_algs; i++) { + cs_dsp_info(dsp, "%d: ID %x v%d.%d.%d DM@%x ZM@%x\n", + i, be32_to_cpu(adsp1_alg[i].alg.id), + (be32_to_cpu(adsp1_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(adsp1_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(adsp1_alg[i].alg.ver) & 0xff, + be32_to_cpu(adsp1_alg[i].dm), + be32_to_cpu(adsp1_alg[i].zm)); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_DM, + adsp1_alg[i].alg.id, + adsp1_alg[i].dm); + if (IS_ERR(alg_region)) { + ret = PTR_ERR(alg_region); + goto out; + } + if (dsp->fw_ver == 0) { + if (i + 1 < n_algs) { + len = be32_to_cpu(adsp1_alg[i + 1].dm); + len -= be32_to_cpu(adsp1_alg[i].dm); + len *= 4; + cs_dsp_create_control(dsp, alg_region, 0, + len, NULL, 0, 0, + WMFW_CTL_TYPE_BYTES); + } else { + cs_dsp_warn(dsp, "Missing length info for region DM with ID %x\n", + be32_to_cpu(adsp1_alg[i].alg.id)); + } + } + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_ZM, + adsp1_alg[i].alg.id, + adsp1_alg[i].zm); + if (IS_ERR(alg_region)) { + ret = PTR_ERR(alg_region); + goto out; + } + if (dsp->fw_ver == 0) { + if (i + 1 < n_algs) { + len = be32_to_cpu(adsp1_alg[i + 1].zm); + len -= be32_to_cpu(adsp1_alg[i].zm); + len *= 4; + cs_dsp_create_control(dsp, alg_region, 0, + len, NULL, 0, 0, + WMFW_CTL_TYPE_BYTES); + } else { + cs_dsp_warn(dsp, "Missing length info for region ZM with ID %x\n", + be32_to_cpu(adsp1_alg[i].alg.id)); + } + } + } + +out: + kfree(adsp1_alg); + return ret; +} + +static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) +{ + struct wmfw_adsp2_id_hdr adsp2_id; + struct wmfw_adsp2_alg_hdr *adsp2_alg; + struct cs_dsp_alg_region *alg_region; + const struct cs_dsp_region *mem; + unsigned int pos, len; + size_t n_algs; + int i, ret; + + mem = cs_dsp_find_region(dsp, WMFW_ADSP2_XM); + if (WARN_ON(!mem)) + return -EINVAL; + + ret = regmap_raw_read(dsp->regmap, mem->base, &adsp2_id, + sizeof(adsp2_id)); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to read algorithm info: %d\n", + ret); + return ret; + } + + n_algs = be32_to_cpu(adsp2_id.n_algs); + + cs_dsp_parse_wmfw_id_header(dsp, &adsp2_id.fw, n_algs); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, + adsp2_id.fw.id, adsp2_id.xm); + if (IS_ERR(alg_region)) + return PTR_ERR(alg_region); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_YM, + adsp2_id.fw.id, adsp2_id.ym); + if (IS_ERR(alg_region)) + return PTR_ERR(alg_region); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_ZM, + adsp2_id.fw.id, adsp2_id.zm); + if (IS_ERR(alg_region)) + return PTR_ERR(alg_region); + + /* Calculate offset and length in DSP words */ + pos = sizeof(adsp2_id) / sizeof(u32); + len = (sizeof(*adsp2_alg) * n_algs) / sizeof(u32); + + adsp2_alg = cs_dsp_read_algs(dsp, n_algs, mem, pos, len); + if (IS_ERR(adsp2_alg)) + return PTR_ERR(adsp2_alg); + + for (i = 0; i < n_algs; i++) { + cs_dsp_info(dsp, + "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n", + i, be32_to_cpu(adsp2_alg[i].alg.id), + (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff, + be32_to_cpu(adsp2_alg[i].xm), + be32_to_cpu(adsp2_alg[i].ym), + be32_to_cpu(adsp2_alg[i].zm)); + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, + adsp2_alg[i].alg.id, + adsp2_alg[i].xm); + if (IS_ERR(alg_region)) { + ret = PTR_ERR(alg_region); + goto out; + } + if (dsp->fw_ver == 0) { + if (i + 1 < n_algs) { + len = be32_to_cpu(adsp2_alg[i + 1].xm); + len -= be32_to_cpu(adsp2_alg[i].xm); + len *= 4; + cs_dsp_create_control(dsp, alg_region, 0, + len, NULL, 0, 0, + WMFW_CTL_TYPE_BYTES); + } else { + cs_dsp_warn(dsp, "Missing length info for region XM with ID %x\n", + be32_to_cpu(adsp2_alg[i].alg.id)); + } + } + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_YM, + adsp2_alg[i].alg.id, + adsp2_alg[i].ym); + if (IS_ERR(alg_region)) { + ret = PTR_ERR(alg_region); + goto out; + } + if (dsp->fw_ver == 0) { + if (i + 1 < n_algs) { + len = be32_to_cpu(adsp2_alg[i + 1].ym); + len -= be32_to_cpu(adsp2_alg[i].ym); + len *= 4; + cs_dsp_create_control(dsp, alg_region, 0, + len, NULL, 0, 0, + WMFW_CTL_TYPE_BYTES); + } else { + cs_dsp_warn(dsp, "Missing length info for region YM with ID %x\n", + be32_to_cpu(adsp2_alg[i].alg.id)); + } + } + + alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_ZM, + adsp2_alg[i].alg.id, + adsp2_alg[i].zm); + if (IS_ERR(alg_region)) { + ret = PTR_ERR(alg_region); + goto out; + } + if (dsp->fw_ver == 0) { + if (i + 1 < n_algs) { + len = be32_to_cpu(adsp2_alg[i + 1].zm); + len -= be32_to_cpu(adsp2_alg[i].zm); + len *= 4; + cs_dsp_create_control(dsp, alg_region, 0, + len, NULL, 0, 0, + WMFW_CTL_TYPE_BYTES); + } else { + cs_dsp_warn(dsp, "Missing length info for region ZM with ID %x\n", + be32_to_cpu(adsp2_alg[i].alg.id)); + } + } + } + +out: + kfree(adsp2_alg); + return ret; +} + +static int cs_dsp_halo_create_regions(struct cs_dsp *dsp, __be32 id, + __be32 xm_base, __be32 ym_base) +{ + static const int types[] = { + WMFW_ADSP2_XM, WMFW_HALO_XM_PACKED, + WMFW_ADSP2_YM, WMFW_HALO_YM_PACKED + }; + __be32 bases[] = { xm_base, xm_base, ym_base, ym_base }; + + return cs_dsp_create_regions(dsp, id, ARRAY_SIZE(types), types, bases); +} + +static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) +{ + struct wmfw_halo_id_hdr halo_id; + struct wmfw_halo_alg_hdr *halo_alg; + const struct cs_dsp_region *mem; + unsigned int pos, len; + size_t n_algs; + int i, ret; + + mem = cs_dsp_find_region(dsp, WMFW_ADSP2_XM); + if (WARN_ON(!mem)) + return -EINVAL; + + ret = regmap_raw_read(dsp->regmap, mem->base, &halo_id, + sizeof(halo_id)); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to read algorithm info: %d\n", + ret); + return ret; + } + + n_algs = be32_to_cpu(halo_id.n_algs); + + cs_dsp_parse_wmfw_v3_id_header(dsp, &halo_id.fw, n_algs); + + ret = cs_dsp_halo_create_regions(dsp, halo_id.fw.id, + halo_id.xm_base, halo_id.ym_base); + if (ret) + return ret; + + /* Calculate offset and length in DSP words */ + pos = sizeof(halo_id) / sizeof(u32); + len = (sizeof(*halo_alg) * n_algs) / sizeof(u32); + + halo_alg = cs_dsp_read_algs(dsp, n_algs, mem, pos, len); + if (IS_ERR(halo_alg)) + return PTR_ERR(halo_alg); + + for (i = 0; i < n_algs; i++) { + cs_dsp_info(dsp, + "%d: ID %x v%d.%d.%d XM@%x YM@%x\n", + i, be32_to_cpu(halo_alg[i].alg.id), + (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16, + (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8, + be32_to_cpu(halo_alg[i].alg.ver) & 0xff, + be32_to_cpu(halo_alg[i].xm_base), + be32_to_cpu(halo_alg[i].ym_base)); + + ret = cs_dsp_halo_create_regions(dsp, halo_alg[i].alg.id, + halo_alg[i].xm_base, + halo_alg[i].ym_base); + if (ret) + goto out; + } + +out: + kfree(halo_alg); + return ret; +} + +static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware, + const char *file) +{ + LIST_HEAD(buf_list); + struct regmap *regmap = dsp->regmap; + struct wmfw_coeff_hdr *hdr; + struct wmfw_coeff_item *blk; + const struct cs_dsp_region *mem; + struct cs_dsp_alg_region *alg_region; + const char *region_name; + int ret, pos, blocks, type, offset, reg; + struct cs_dsp_buf *buf; + + if (!firmware) + return 0; + + ret = -EINVAL; + + if (sizeof(*hdr) >= firmware->size) { + cs_dsp_err(dsp, "%s: coefficient file too short, %zu bytes\n", + file, firmware->size); + goto out_fw; + } + + hdr = (void *)&firmware->data[0]; + if (memcmp(hdr->magic, "WMDR", 4) != 0) { + cs_dsp_err(dsp, "%s: invalid coefficient magic\n", file); + goto out_fw; + } + + switch (be32_to_cpu(hdr->rev) & 0xff) { + case 1: + break; + default: + cs_dsp_err(dsp, "%s: Unsupported coefficient file format %d\n", + file, be32_to_cpu(hdr->rev) & 0xff); + ret = -EINVAL; + goto out_fw; + } + + cs_dsp_dbg(dsp, "%s: v%d.%d.%d\n", file, + (le32_to_cpu(hdr->ver) >> 16) & 0xff, + (le32_to_cpu(hdr->ver) >> 8) & 0xff, + le32_to_cpu(hdr->ver) & 0xff); + + pos = le32_to_cpu(hdr->len); + + blocks = 0; + while (pos < firmware->size && + sizeof(*blk) < firmware->size - pos) { + blk = (void *)(&firmware->data[pos]); + + type = le16_to_cpu(blk->type); + offset = le16_to_cpu(blk->offset); + + cs_dsp_dbg(dsp, "%s.%d: %x v%d.%d.%d\n", + file, blocks, le32_to_cpu(blk->id), + (le32_to_cpu(blk->ver) >> 16) & 0xff, + (le32_to_cpu(blk->ver) >> 8) & 0xff, + le32_to_cpu(blk->ver) & 0xff); + cs_dsp_dbg(dsp, "%s.%d: %d bytes at 0x%x in %x\n", + file, blocks, le32_to_cpu(blk->len), offset, type); + + reg = 0; + region_name = "Unknown"; + switch (type) { + case (WMFW_NAME_TEXT << 8): + case (WMFW_INFO_TEXT << 8): + case (WMFW_METADATA << 8): + break; + case (WMFW_ABSOLUTE << 8): + /* + * Old files may use this for global + * coefficients. + */ + if (le32_to_cpu(blk->id) == dsp->fw_id && + offset == 0) { + region_name = "global coefficients"; + mem = cs_dsp_find_region(dsp, type); + if (!mem) { + cs_dsp_err(dsp, "No ZM\n"); + break; + } + reg = dsp->ops->region_to_reg(mem, 0); + + } else { + region_name = "register"; + reg = offset; + } + break; + + case WMFW_ADSP1_DM: + case WMFW_ADSP1_ZM: + case WMFW_ADSP2_XM: + case WMFW_ADSP2_YM: + case WMFW_HALO_XM_PACKED: + case WMFW_HALO_YM_PACKED: + case WMFW_HALO_PM_PACKED: + cs_dsp_dbg(dsp, "%s.%d: %d bytes in %x for %x\n", + file, blocks, le32_to_cpu(blk->len), + type, le32_to_cpu(blk->id)); + + mem = cs_dsp_find_region(dsp, type); + if (!mem) { + cs_dsp_err(dsp, "No base for region %x\n", type); + break; + } + + alg_region = cs_dsp_find_alg_region(dsp, type, + le32_to_cpu(blk->id)); + if (alg_region) { + reg = alg_region->base; + reg = dsp->ops->region_to_reg(mem, reg); + reg += offset; + } else { + cs_dsp_err(dsp, "No %x for algorithm %x\n", + type, le32_to_cpu(blk->id)); + } + break; + + default: + cs_dsp_err(dsp, "%s.%d: Unknown region type %x at %d\n", + file, blocks, type, pos); + break; + } + + if (reg) { + if (le32_to_cpu(blk->len) > + firmware->size - pos - sizeof(*blk)) { + cs_dsp_err(dsp, + "%s.%d: %s region len %d bytes exceeds file length %zu\n", + file, blocks, region_name, + le32_to_cpu(blk->len), + firmware->size); + ret = -EINVAL; + goto out_fw; + } + + buf = cs_dsp_buf_alloc(blk->data, + le32_to_cpu(blk->len), + &buf_list); + if (!buf) { + cs_dsp_err(dsp, "Out of memory\n"); + ret = -ENOMEM; + goto out_fw; + } + + cs_dsp_dbg(dsp, "%s.%d: Writing %d bytes at %x\n", + file, blocks, le32_to_cpu(blk->len), + reg); + ret = regmap_raw_write_async(regmap, reg, buf->buf, + le32_to_cpu(blk->len)); + if (ret != 0) { + cs_dsp_err(dsp, + "%s.%d: Failed to write to %x in %s: %d\n", + file, blocks, reg, region_name, ret); + } + } + + pos += (le32_to_cpu(blk->len) + sizeof(*blk) + 3) & ~0x03; + blocks++; + } + + ret = regmap_async_complete(regmap); + if (ret != 0) + cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret); + + if (pos > firmware->size) + cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n", + file, blocks, pos - firmware->size); + + cs_dsp_debugfs_save_binname(dsp, file); + +out_fw: + regmap_async_complete(regmap); + cs_dsp_buf_free(&buf_list); + return ret; +} + +static int cs_dsp_create_name(struct cs_dsp *dsp) +{ + if (!dsp->name) { + dsp->name = devm_kasprintf(dsp->dev, GFP_KERNEL, "DSP%d", + dsp->num); + if (!dsp->name) + return -ENOMEM; + } + + return 0; +} + +static int cs_dsp_common_init(struct cs_dsp *dsp) +{ + int ret; + + ret = cs_dsp_create_name(dsp); + if (ret) + return ret; + + INIT_LIST_HEAD(&dsp->alg_regions); + INIT_LIST_HEAD(&dsp->ctl_list); + + mutex_init(&dsp->pwr_lock); + + return 0; +} + +/** + * cs_dsp_adsp1_init() - Initialise a cs_dsp structure representing a ADSP1 device + * @dsp: pointer to DSP structure + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_adsp1_init(struct cs_dsp *dsp) +{ + dsp->ops = &cs_dsp_adsp1_ops; + + return cs_dsp_common_init(dsp); +} +EXPORT_SYMBOL_GPL(cs_dsp_adsp1_init); + +/** + * cs_dsp_adsp1_power_up() - Load and start the named firmware + * @dsp: pointer to DSP structure + * @wmfw_firmware: the firmware to be sent + * @wmfw_filename: file name of firmware to be sent + * @coeff_firmware: the coefficient data to be sent + * @coeff_filename: file name of coefficient to data be sent + * @fw_name: the user-friendly firmware name + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_adsp1_power_up(struct cs_dsp *dsp, + const struct firmware *wmfw_firmware, char *wmfw_filename, + const struct firmware *coeff_firmware, char *coeff_filename, + const char *fw_name) +{ + unsigned int val; + int ret; + + mutex_lock(&dsp->pwr_lock); + + dsp->fw_name = fw_name; + + regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, + ADSP1_SYS_ENA, ADSP1_SYS_ENA); + + /* + * For simplicity set the DSP clock rate to be the + * SYSCLK rate rather than making it configurable. + */ + if (dsp->sysclk_reg) { + ret = regmap_read(dsp->regmap, dsp->sysclk_reg, &val); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to read SYSCLK state: %d\n", ret); + goto err_mutex; + } + + val = (val & dsp->sysclk_mask) >> dsp->sysclk_shift; + + ret = regmap_update_bits(dsp->regmap, + dsp->base + ADSP1_CONTROL_31, + ADSP1_CLK_SEL_MASK, val); + if (ret != 0) { + cs_dsp_err(dsp, "Failed to set clock rate: %d\n", ret); + goto err_mutex; + } + } + + ret = cs_dsp_load(dsp, wmfw_firmware, wmfw_filename); + if (ret != 0) + goto err_ena; + + ret = cs_dsp_adsp1_setup_algs(dsp); + if (ret != 0) + goto err_ena; + + ret = cs_dsp_load_coeff(dsp, coeff_firmware, coeff_filename); + if (ret != 0) + goto err_ena; + + /* Initialize caches for enabled and unset controls */ + ret = cs_dsp_coeff_init_control_caches(dsp); + if (ret != 0) + goto err_ena; + + /* Sync set controls */ + ret = cs_dsp_coeff_sync_controls(dsp); + if (ret != 0) + goto err_ena; + + dsp->booted = true; + + /* Start the core running */ + regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, + ADSP1_CORE_ENA | ADSP1_START, + ADSP1_CORE_ENA | ADSP1_START); + + dsp->running = true; + + mutex_unlock(&dsp->pwr_lock); + + return 0; + +err_ena: + regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, + ADSP1_SYS_ENA, 0); +err_mutex: + mutex_unlock(&dsp->pwr_lock); + return ret; +} +EXPORT_SYMBOL_GPL(cs_dsp_adsp1_power_up); + +/** + * cs_dsp_adsp1_power_down() - Halts the DSP + * @dsp: pointer to DSP structure + */ +void cs_dsp_adsp1_power_down(struct cs_dsp *dsp) +{ + struct cs_dsp_coeff_ctl *ctl; + + mutex_lock(&dsp->pwr_lock); + + dsp->running = false; + dsp->booted = false; + + /* Halt the core */ + regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, + ADSP1_CORE_ENA | ADSP1_START, 0); + + regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_19, + ADSP1_WDMA_BUFFER_LENGTH_MASK, 0); + + regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, + ADSP1_SYS_ENA, 0); + + list_for_each_entry(ctl, &dsp->ctl_list, list) + ctl->enabled = 0; + + cs_dsp_free_alg_regions(dsp); + + mutex_unlock(&dsp->pwr_lock); +} +EXPORT_SYMBOL_GPL(cs_dsp_adsp1_power_down); + +static int cs_dsp_adsp2v2_enable_core(struct cs_dsp *dsp) +{ + unsigned int val; + int ret, count; + + /* Wait for the RAM to start, should be near instantaneous */ + for (count = 0; count < 10; ++count) { + ret = regmap_read(dsp->regmap, dsp->base + ADSP2_STATUS1, &val); + if (ret != 0) + return ret; + + if (val & ADSP2_RAM_RDY) + break; + + usleep_range(250, 500); + } + + if (!(val & ADSP2_RAM_RDY)) { + cs_dsp_err(dsp, "Failed to start DSP RAM\n"); + return -EBUSY; + } + + cs_dsp_dbg(dsp, "RAM ready after %d polls\n", count); + + return 0; +} + +static int cs_dsp_adsp2_enable_core(struct cs_dsp *dsp) +{ + int ret; + + ret = regmap_update_bits_async(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_SYS_ENA, ADSP2_SYS_ENA); + if (ret != 0) + return ret; + + return cs_dsp_adsp2v2_enable_core(dsp); +} + +static int cs_dsp_adsp2_lock(struct cs_dsp *dsp, unsigned int lock_regions) +{ + struct regmap *regmap = dsp->regmap; + unsigned int code0, code1, lock_reg; + + if (!(lock_regions & CS_ADSP2_REGION_ALL)) + return 0; + + lock_regions &= CS_ADSP2_REGION_ALL; + lock_reg = dsp->base + ADSP2_LOCK_REGION_1_LOCK_REGION_0; + + while (lock_regions) { + code0 = code1 = 0; + if (lock_regions & BIT(0)) { + code0 = ADSP2_LOCK_CODE_0; + code1 = ADSP2_LOCK_CODE_1; + } + if (lock_regions & BIT(1)) { + code0 |= ADSP2_LOCK_CODE_0 << ADSP2_LOCK_REGION_SHIFT; + code1 |= ADSP2_LOCK_CODE_1 << ADSP2_LOCK_REGION_SHIFT; + } + regmap_write(regmap, lock_reg, code0); + regmap_write(regmap, lock_reg, code1); + lock_regions >>= 2; + lock_reg += 2; + } + + return 0; +} + +static int cs_dsp_adsp2_enable_memory(struct cs_dsp *dsp) +{ + return regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_MEM_ENA, ADSP2_MEM_ENA); +} + +static void cs_dsp_adsp2_disable_memory(struct cs_dsp *dsp) +{ + regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_MEM_ENA, 0); +} + +static void cs_dsp_adsp2_disable_core(struct cs_dsp *dsp) +{ + regmap_write(dsp->regmap, dsp->base + ADSP2_RDMA_CONFIG_1, 0); + regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_1, 0); + regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_2, 0); + + regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_SYS_ENA, 0); +} + +static void cs_dsp_adsp2v2_disable_core(struct cs_dsp *dsp) +{ + regmap_write(dsp->regmap, dsp->base + ADSP2_RDMA_CONFIG_1, 0); + regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_1, 0); + regmap_write(dsp->regmap, dsp->base + ADSP2V2_WDMA_CONFIG_2, 0); +} + +static int cs_dsp_halo_configure_mpu(struct cs_dsp *dsp, unsigned int lock_regions) +{ + struct reg_sequence config[] = { + { dsp->base + HALO_MPU_LOCK_CONFIG, 0x5555 }, + { dsp->base + HALO_MPU_LOCK_CONFIG, 0xAAAA }, + { dsp->base + HALO_MPU_XMEM_ACCESS_0, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_YMEM_ACCESS_0, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_WINDOW_ACCESS_0, lock_regions }, + { dsp->base + HALO_MPU_XREG_ACCESS_0, lock_regions }, + { dsp->base + HALO_MPU_YREG_ACCESS_0, lock_regions }, + { dsp->base + HALO_MPU_XMEM_ACCESS_1, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_YMEM_ACCESS_1, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_WINDOW_ACCESS_1, lock_regions }, + { dsp->base + HALO_MPU_XREG_ACCESS_1, lock_regions }, + { dsp->base + HALO_MPU_YREG_ACCESS_1, lock_regions }, + { dsp->base + HALO_MPU_XMEM_ACCESS_2, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_YMEM_ACCESS_2, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_WINDOW_ACCESS_2, lock_regions }, + { dsp->base + HALO_MPU_XREG_ACCESS_2, lock_regions }, + { dsp->base + HALO_MPU_YREG_ACCESS_2, lock_regions }, + { dsp->base + HALO_MPU_XMEM_ACCESS_3, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_YMEM_ACCESS_3, 0xFFFFFFFF }, + { dsp->base + HALO_MPU_WINDOW_ACCESS_3, lock_regions }, + { dsp->base + HALO_MPU_XREG_ACCESS_3, lock_regions }, + { dsp->base + HALO_MPU_YREG_ACCESS_3, lock_regions }, + { dsp->base + HALO_MPU_LOCK_CONFIG, 0 }, + }; + + return regmap_multi_reg_write(dsp->regmap, config, ARRAY_SIZE(config)); +} + +/** + * cs_dsp_set_dspclk() - Applies the given frequency to the given cs_dsp + * @dsp: pointer to DSP structure + * @freq: clock rate to set + * + * This is only for use on ADSP2 cores. + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_set_dspclk(struct cs_dsp *dsp, unsigned int freq) +{ + int ret; + + ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CLOCKING, + ADSP2_CLK_SEL_MASK, + freq << ADSP2_CLK_SEL_SHIFT); + if (ret) + cs_dsp_err(dsp, "Failed to set clock rate: %d\n", ret); + + return ret; +} +EXPORT_SYMBOL_GPL(cs_dsp_set_dspclk); + +static void cs_dsp_stop_watchdog(struct cs_dsp *dsp) +{ + regmap_update_bits(dsp->regmap, dsp->base + ADSP2_WATCHDOG, + ADSP2_WDT_ENA_MASK, 0); +} + +static void cs_dsp_halo_stop_watchdog(struct cs_dsp *dsp) +{ + regmap_update_bits(dsp->regmap, dsp->base + HALO_WDT_CONTROL, + HALO_WDT_EN_MASK, 0); +} + +/** + * cs_dsp_power_up() - Downloads firmware to the DSP + * @dsp: pointer to DSP structure + * @wmfw_firmware: the firmware to be sent + * @wmfw_filename: file name of firmware to be sent + * @coeff_firmware: the coefficient data to be sent + * @coeff_filename: file name of coefficient to data be sent + * @fw_name: the user-friendly firmware name + * + * This function is used on ADSP2 and Halo DSP cores, it powers-up the DSP core + * and downloads the firmware but does not start the firmware running. The + * cs_dsp booted flag will be set once completed and if the core has a low-power + * memory retention mode it will be put into this state after the firmware is + * downloaded. + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_power_up(struct cs_dsp *dsp, + const struct firmware *wmfw_firmware, char *wmfw_filename, + const struct firmware *coeff_firmware, char *coeff_filename, + const char *fw_name) +{ + int ret; + + mutex_lock(&dsp->pwr_lock); + + dsp->fw_name = fw_name; + + if (dsp->ops->enable_memory) { + ret = dsp->ops->enable_memory(dsp); + if (ret != 0) + goto err_mutex; + } + + if (dsp->ops->enable_core) { + ret = dsp->ops->enable_core(dsp); + if (ret != 0) + goto err_mem; + } + + ret = cs_dsp_load(dsp, wmfw_firmware, wmfw_filename); + if (ret != 0) + goto err_ena; + + ret = dsp->ops->setup_algs(dsp); + if (ret != 0) + goto err_ena; + + ret = cs_dsp_load_coeff(dsp, coeff_firmware, coeff_filename); + if (ret != 0) + goto err_ena; + + /* Initialize caches for enabled and unset controls */ + ret = cs_dsp_coeff_init_control_caches(dsp); + if (ret != 0) + goto err_ena; + + if (dsp->ops->disable_core) + dsp->ops->disable_core(dsp); + + dsp->booted = true; + + mutex_unlock(&dsp->pwr_lock); + + return 0; +err_ena: + if (dsp->ops->disable_core) + dsp->ops->disable_core(dsp); +err_mem: + if (dsp->ops->disable_memory) + dsp->ops->disable_memory(dsp); +err_mutex: + mutex_unlock(&dsp->pwr_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cs_dsp_power_up); + +/** + * cs_dsp_power_down() - Powers-down the DSP + * @dsp: pointer to DSP structure + * + * cs_dsp_stop() must have been called before this function. The core will be + * fully powered down and so the memory will not be retained. + */ +void cs_dsp_power_down(struct cs_dsp *dsp) +{ + struct cs_dsp_coeff_ctl *ctl; + + mutex_lock(&dsp->pwr_lock); + + cs_dsp_debugfs_clear(dsp); + + dsp->fw_id = 0; + dsp->fw_id_version = 0; + + dsp->booted = false; + + if (dsp->ops->disable_memory) + dsp->ops->disable_memory(dsp); + + list_for_each_entry(ctl, &dsp->ctl_list, list) + ctl->enabled = 0; + + cs_dsp_free_alg_regions(dsp); + + mutex_unlock(&dsp->pwr_lock); + + cs_dsp_dbg(dsp, "Shutdown complete\n"); +} +EXPORT_SYMBOL_GPL(cs_dsp_power_down); + +static int cs_dsp_adsp2_start_core(struct cs_dsp *dsp) +{ + return regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_CORE_ENA | ADSP2_START, + ADSP2_CORE_ENA | ADSP2_START); +} + +static void cs_dsp_adsp2_stop_core(struct cs_dsp *dsp) +{ + regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_CORE_ENA | ADSP2_START, 0); +} + +/** + * cs_dsp_run() - Starts the firmware running + * @dsp: pointer to DSP structure + * + * cs_dsp_power_up() must have previously been called successfully. + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_run(struct cs_dsp *dsp) +{ + int ret; + + mutex_lock(&dsp->pwr_lock); + + if (!dsp->booted) { + ret = -EIO; + goto err; + } + + if (dsp->ops->enable_core) { + ret = dsp->ops->enable_core(dsp); + if (ret != 0) + goto err; + } + + /* Sync set controls */ + ret = cs_dsp_coeff_sync_controls(dsp); + if (ret != 0) + goto err; + + if (dsp->ops->lock_memory) { + ret = dsp->ops->lock_memory(dsp, dsp->lock_regions); + if (ret != 0) { + cs_dsp_err(dsp, "Error configuring MPU: %d\n", ret); + goto err; + } + } + + if (dsp->ops->start_core) { + ret = dsp->ops->start_core(dsp); + if (ret != 0) + goto err; + } + + dsp->running = true; + + if (dsp->client_ops->post_run) { + ret = dsp->client_ops->post_run(dsp); + if (ret) + goto err; + } + + mutex_unlock(&dsp->pwr_lock); + + return 0; + +err: + if (dsp->ops->stop_core) + dsp->ops->stop_core(dsp); + if (dsp->ops->disable_core) + dsp->ops->disable_core(dsp); + mutex_unlock(&dsp->pwr_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cs_dsp_run); + +/** + * cs_dsp_stop() - Stops the firmware + * @dsp: pointer to DSP structure + * + * Memory will not be disabled so firmware will remain loaded. + */ +void cs_dsp_stop(struct cs_dsp *dsp) +{ + /* Tell the firmware to cleanup */ + cs_dsp_signal_event_controls(dsp, CS_DSP_FW_EVENT_SHUTDOWN); + + if (dsp->ops->stop_watchdog) + dsp->ops->stop_watchdog(dsp); + + /* Log firmware state, it can be useful for analysis */ + if (dsp->ops->show_fw_status) + dsp->ops->show_fw_status(dsp); + + mutex_lock(&dsp->pwr_lock); + + dsp->running = false; + + if (dsp->ops->stop_core) + dsp->ops->stop_core(dsp); + if (dsp->ops->disable_core) + dsp->ops->disable_core(dsp); + + if (dsp->client_ops->post_stop) + dsp->client_ops->post_stop(dsp); + + mutex_unlock(&dsp->pwr_lock); + + cs_dsp_dbg(dsp, "Execution stopped\n"); +} +EXPORT_SYMBOL_GPL(cs_dsp_stop); + +static int cs_dsp_halo_start_core(struct cs_dsp *dsp) +{ + return regmap_update_bits(dsp->regmap, + dsp->base + HALO_CCM_CORE_CONTROL, + HALO_CORE_RESET | HALO_CORE_EN, + HALO_CORE_RESET | HALO_CORE_EN); +} + +static void cs_dsp_halo_stop_core(struct cs_dsp *dsp) +{ + regmap_update_bits(dsp->regmap, dsp->base + HALO_CCM_CORE_CONTROL, + HALO_CORE_EN, 0); + + /* reset halo core with CORE_SOFT_RESET */ + regmap_update_bits(dsp->regmap, dsp->base + HALO_CORE_SOFT_RESET, + HALO_CORE_SOFT_RESET_MASK, 1); +} + +/** + * cs_dsp_adsp2_init() - Initialise a cs_dsp structure representing a ADSP2 core + * @dsp: pointer to DSP structure + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_adsp2_init(struct cs_dsp *dsp) +{ + int ret; + + switch (dsp->rev) { + case 0: + /* + * Disable the DSP memory by default when in reset for a small + * power saving. + */ + ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, + ADSP2_MEM_ENA, 0); + if (ret) { + cs_dsp_err(dsp, + "Failed to clear memory retention: %d\n", ret); + return ret; + } + + dsp->ops = &cs_dsp_adsp2_ops[0]; + break; + case 1: + dsp->ops = &cs_dsp_adsp2_ops[1]; + break; + default: + dsp->ops = &cs_dsp_adsp2_ops[2]; + break; + } + + return cs_dsp_common_init(dsp); +} +EXPORT_SYMBOL_GPL(cs_dsp_adsp2_init); + +/** + * cs_dsp_halo_init() - Initialise a cs_dsp structure representing a HALO Core DSP + * @dsp: pointer to DSP structure + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_halo_init(struct cs_dsp *dsp) +{ + dsp->ops = &cs_dsp_halo_ops; + + return cs_dsp_common_init(dsp); +} +EXPORT_SYMBOL_GPL(cs_dsp_halo_init); + +/** + * cs_dsp_remove() - Clean a cs_dsp before deletion + * @dsp: pointer to DSP structure + */ +void cs_dsp_remove(struct cs_dsp *dsp) +{ + struct cs_dsp_coeff_ctl *ctl; + + while (!list_empty(&dsp->ctl_list)) { + ctl = list_first_entry(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); + + if (dsp->client_ops->control_remove) + dsp->client_ops->control_remove(ctl); + + list_del(&ctl->list); + cs_dsp_free_ctl_blk(ctl); + } +} +EXPORT_SYMBOL_GPL(cs_dsp_remove); + +/** + * cs_dsp_read_raw_data_block() - Reads a block of data from DSP memory + * @dsp: pointer to DSP structure + * @mem_type: the type of DSP memory containing the data to be read + * @mem_addr: the address of the data within the memory region + * @num_words: the length of the data to read + * @data: a buffer to store the fetched data + * + * If this is used to read unpacked 24-bit memory, each 24-bit DSP word will + * occupy 32-bits in data (MSbyte will be 0). This padding can be removed using + * cs_dsp_remove_padding() + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_read_raw_data_block(struct cs_dsp *dsp, int mem_type, unsigned int mem_addr, + unsigned int num_words, __be32 *data) +{ + struct cs_dsp_region const *mem = cs_dsp_find_region(dsp, mem_type); + unsigned int reg; + int ret; + + if (!mem) + return -EINVAL; + + reg = dsp->ops->region_to_reg(mem, mem_addr); + + ret = regmap_raw_read(dsp->regmap, reg, data, + sizeof(*data) * num_words); + if (ret < 0) + return ret; + + return 0; +} +EXPORT_SYMBOL_GPL(cs_dsp_read_raw_data_block); + +/** + * cs_dsp_read_data_word() - Reads a word from DSP memory + * @dsp: pointer to DSP structure + * @mem_type: the type of DSP memory containing the data to be read + * @mem_addr: the address of the data within the memory region + * @data: a buffer to store the fetched data + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_read_data_word(struct cs_dsp *dsp, int mem_type, unsigned int mem_addr, u32 *data) +{ + __be32 raw; + int ret; + + ret = cs_dsp_read_raw_data_block(dsp, mem_type, mem_addr, 1, &raw); + if (ret < 0) + return ret; + + *data = be32_to_cpu(raw) & 0x00ffffffu; + + return 0; +} +EXPORT_SYMBOL_GPL(cs_dsp_read_data_word); + +/** + * cs_dsp_write_data_word() - Writes a word to DSP memory + * @dsp: pointer to DSP structure + * @mem_type: the type of DSP memory containing the data to be written + * @mem_addr: the address of the data within the memory region + * @data: the data to be written + * + * Return: Zero for success, a negative number on error. + */ +int cs_dsp_write_data_word(struct cs_dsp *dsp, int mem_type, unsigned int mem_addr, u32 data) +{ + struct cs_dsp_region const *mem = cs_dsp_find_region(dsp, mem_type); + __be32 val = cpu_to_be32(data & 0x00ffffffu); + unsigned int reg; + + if (!mem) + return -EINVAL; + + reg = dsp->ops->region_to_reg(mem, mem_addr); + + return regmap_raw_write(dsp->regmap, reg, &val, sizeof(val)); +} +EXPORT_SYMBOL_GPL(cs_dsp_write_data_word); + +/** + * cs_dsp_remove_padding() - Convert unpacked words to packed bytes + * @buf: buffer containing DSP words read from DSP memory + * @nwords: number of words to convert + * + * DSP words from the register map have pad bytes and the data bytes + * are in swapped order. This swaps to the native endian order and + * strips the pad bytes. + */ +void cs_dsp_remove_padding(u32 *buf, int nwords) +{ + const __be32 *pack_in = (__be32 *)buf; + u8 *pack_out = (u8 *)buf; + int i; + + for (i = 0; i < nwords; i++) { + u32 word = be32_to_cpu(*pack_in++); + *pack_out++ = (u8)word; + *pack_out++ = (u8)(word >> 8); + *pack_out++ = (u8)(word >> 16); + } +} +EXPORT_SYMBOL_GPL(cs_dsp_remove_padding); + +/** + * cs_dsp_adsp2_bus_error() - Handle a DSP bus error interrupt + * @dsp: pointer to DSP structure + * + * The firmware and DSP state will be logged for future analysis. + */ +void cs_dsp_adsp2_bus_error(struct cs_dsp *dsp) +{ + unsigned int val; + struct regmap *regmap = dsp->regmap; + int ret = 0; + + mutex_lock(&dsp->pwr_lock); + + ret = regmap_read(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, &val); + if (ret) { + cs_dsp_err(dsp, + "Failed to read Region Lock Ctrl register: %d\n", ret); + goto error; + } + + if (val & ADSP2_WDT_TIMEOUT_STS_MASK) { + cs_dsp_err(dsp, "watchdog timeout error\n"); + dsp->ops->stop_watchdog(dsp); + if (dsp->client_ops->watchdog_expired) + dsp->client_ops->watchdog_expired(dsp); + } + + if (val & (ADSP2_ADDR_ERR_MASK | ADSP2_REGION_LOCK_ERR_MASK)) { + if (val & ADSP2_ADDR_ERR_MASK) + cs_dsp_err(dsp, "bus error: address error\n"); + else + cs_dsp_err(dsp, "bus error: region lock error\n"); + + ret = regmap_read(regmap, dsp->base + ADSP2_BUS_ERR_ADDR, &val); + if (ret) { + cs_dsp_err(dsp, + "Failed to read Bus Err Addr register: %d\n", + ret); + goto error; + } + + cs_dsp_err(dsp, "bus error address = 0x%x\n", + val & ADSP2_BUS_ERR_ADDR_MASK); + + ret = regmap_read(regmap, + dsp->base + ADSP2_PMEM_ERR_ADDR_XMEM_ERR_ADDR, + &val); + if (ret) { + cs_dsp_err(dsp, + "Failed to read Pmem Xmem Err Addr register: %d\n", + ret); + goto error; + } + + cs_dsp_err(dsp, "xmem error address = 0x%x\n", + val & ADSP2_XMEM_ERR_ADDR_MASK); + cs_dsp_err(dsp, "pmem error address = 0x%x\n", + (val & ADSP2_PMEM_ERR_ADDR_MASK) >> + ADSP2_PMEM_ERR_ADDR_SHIFT); + } + + regmap_update_bits(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, + ADSP2_CTRL_ERR_EINT, ADSP2_CTRL_ERR_EINT); + +error: + mutex_unlock(&dsp->pwr_lock); +} +EXPORT_SYMBOL_GPL(cs_dsp_adsp2_bus_error); + +/** + * cs_dsp_halo_bus_error() - Handle a DSP bus error interrupt + * @dsp: pointer to DSP structure + * + * The firmware and DSP state will be logged for future analysis. + */ +void cs_dsp_halo_bus_error(struct cs_dsp *dsp) +{ + struct regmap *regmap = dsp->regmap; + unsigned int fault[6]; + struct reg_sequence clear[] = { + { dsp->base + HALO_MPU_XM_VIO_STATUS, 0x0 }, + { dsp->base + HALO_MPU_YM_VIO_STATUS, 0x0 }, + { dsp->base + HALO_MPU_PM_VIO_STATUS, 0x0 }, + }; + int ret; + + mutex_lock(&dsp->pwr_lock); + + ret = regmap_read(regmap, dsp->base_sysinfo + HALO_AHBM_WINDOW_DEBUG_1, + fault); + if (ret) { + cs_dsp_warn(dsp, "Failed to read AHB DEBUG_1: %d\n", ret); + goto exit_unlock; + } + + cs_dsp_warn(dsp, "AHB: STATUS: 0x%x ADDR: 0x%x\n", + *fault & HALO_AHBM_FLAGS_ERR_MASK, + (*fault & HALO_AHBM_CORE_ERR_ADDR_MASK) >> + HALO_AHBM_CORE_ERR_ADDR_SHIFT); + + ret = regmap_read(regmap, dsp->base_sysinfo + HALO_AHBM_WINDOW_DEBUG_0, + fault); + if (ret) { + cs_dsp_warn(dsp, "Failed to read AHB DEBUG_0: %d\n", ret); + goto exit_unlock; + } + + cs_dsp_warn(dsp, "AHB: SYS_ADDR: 0x%x\n", *fault); + + ret = regmap_bulk_read(regmap, dsp->base + HALO_MPU_XM_VIO_ADDR, + fault, ARRAY_SIZE(fault)); + if (ret) { + cs_dsp_warn(dsp, "Failed to read MPU fault info: %d\n", ret); + goto exit_unlock; + } + + cs_dsp_warn(dsp, "XM: STATUS:0x%x ADDR:0x%x\n", fault[1], fault[0]); + cs_dsp_warn(dsp, "YM: STATUS:0x%x ADDR:0x%x\n", fault[3], fault[2]); + cs_dsp_warn(dsp, "PM: STATUS:0x%x ADDR:0x%x\n", fault[5], fault[4]); + + ret = regmap_multi_reg_write(dsp->regmap, clear, ARRAY_SIZE(clear)); + if (ret) + cs_dsp_warn(dsp, "Failed to clear MPU status: %d\n", ret); + +exit_unlock: + mutex_unlock(&dsp->pwr_lock); +} +EXPORT_SYMBOL_GPL(cs_dsp_halo_bus_error); + +/** + * cs_dsp_halo_wdt_expire() - Handle DSP watchdog expiry + * @dsp: pointer to DSP structure + * + * This is logged for future analysis. + */ +void cs_dsp_halo_wdt_expire(struct cs_dsp *dsp) +{ + mutex_lock(&dsp->pwr_lock); + + cs_dsp_warn(dsp, "WDT Expiry Fault\n"); + + dsp->ops->stop_watchdog(dsp); + if (dsp->client_ops->watchdog_expired) + dsp->client_ops->watchdog_expired(dsp); + + mutex_unlock(&dsp->pwr_lock); +} +EXPORT_SYMBOL_GPL(cs_dsp_halo_wdt_expire); + +static const struct cs_dsp_ops cs_dsp_adsp1_ops = { + .validate_version = cs_dsp_validate_version, + .parse_sizes = cs_dsp_adsp1_parse_sizes, + .region_to_reg = cs_dsp_region_to_reg, +}; + +static const struct cs_dsp_ops cs_dsp_adsp2_ops[] = { + { + .parse_sizes = cs_dsp_adsp2_parse_sizes, + .validate_version = cs_dsp_validate_version, + .setup_algs = cs_dsp_adsp2_setup_algs, + .region_to_reg = cs_dsp_region_to_reg, + + .show_fw_status = cs_dsp_adsp2_show_fw_status, + + .enable_memory = cs_dsp_adsp2_enable_memory, + .disable_memory = cs_dsp_adsp2_disable_memory, + + .enable_core = cs_dsp_adsp2_enable_core, + .disable_core = cs_dsp_adsp2_disable_core, + + .start_core = cs_dsp_adsp2_start_core, + .stop_core = cs_dsp_adsp2_stop_core, + + }, + { + .parse_sizes = cs_dsp_adsp2_parse_sizes, + .validate_version = cs_dsp_validate_version, + .setup_algs = cs_dsp_adsp2_setup_algs, + .region_to_reg = cs_dsp_region_to_reg, + + .show_fw_status = cs_dsp_adsp2v2_show_fw_status, + + .enable_memory = cs_dsp_adsp2_enable_memory, + .disable_memory = cs_dsp_adsp2_disable_memory, + .lock_memory = cs_dsp_adsp2_lock, + + .enable_core = cs_dsp_adsp2v2_enable_core, + .disable_core = cs_dsp_adsp2v2_disable_core, + + .start_core = cs_dsp_adsp2_start_core, + .stop_core = cs_dsp_adsp2_stop_core, + }, + { + .parse_sizes = cs_dsp_adsp2_parse_sizes, + .validate_version = cs_dsp_validate_version, + .setup_algs = cs_dsp_adsp2_setup_algs, + .region_to_reg = cs_dsp_region_to_reg, + + .show_fw_status = cs_dsp_adsp2v2_show_fw_status, + .stop_watchdog = cs_dsp_stop_watchdog, + + .enable_memory = cs_dsp_adsp2_enable_memory, + .disable_memory = cs_dsp_adsp2_disable_memory, + .lock_memory = cs_dsp_adsp2_lock, + + .enable_core = cs_dsp_adsp2v2_enable_core, + .disable_core = cs_dsp_adsp2v2_disable_core, + + .start_core = cs_dsp_adsp2_start_core, + .stop_core = cs_dsp_adsp2_stop_core, + }, +}; + +static const struct cs_dsp_ops cs_dsp_halo_ops = { + .parse_sizes = cs_dsp_adsp2_parse_sizes, + .validate_version = cs_dsp_halo_validate_version, + .setup_algs = cs_dsp_halo_setup_algs, + .region_to_reg = cs_dsp_halo_region_to_reg, + + .show_fw_status = cs_dsp_halo_show_fw_status, + .stop_watchdog = cs_dsp_halo_stop_watchdog, + + .lock_memory = cs_dsp_halo_configure_mpu, + + .start_core = cs_dsp_halo_start_core, + .stop_core = cs_dsp_halo_stop_core, +}; + +MODULE_DESCRIPTION("Cirrus Logic DSP Support"); +MODULE_AUTHOR("Simon Trimmer "); +MODULE_LICENSE("GPL v2"); diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h new file mode 100644 index 000000000000..9ad9eaaaa552 --- /dev/null +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -0,0 +1,242 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * cs_dsp.h -- Cirrus Logic DSP firmware support + * + * Based on sound/soc/codecs/wm_adsp.h + * + * Copyright 2012 Wolfson Microelectronics plc + * Copyright (C) 2015-2021 Cirrus Logic, Inc. and + * Cirrus Logic International Semiconductor Ltd. + */ +#ifndef __CS_DSP_H +#define __CS_DSP_H + +#define CS_ADSP2_REGION_0 BIT(0) +#define CS_ADSP2_REGION_1 BIT(1) +#define CS_ADSP2_REGION_2 BIT(2) +#define CS_ADSP2_REGION_3 BIT(3) +#define CS_ADSP2_REGION_4 BIT(4) +#define CS_ADSP2_REGION_5 BIT(5) +#define CS_ADSP2_REGION_6 BIT(6) +#define CS_ADSP2_REGION_7 BIT(7) +#define CS_ADSP2_REGION_8 BIT(8) +#define CS_ADSP2_REGION_9 BIT(9) +#define CS_ADSP2_REGION_1_9 (CS_ADSP2_REGION_1 | \ + CS_ADSP2_REGION_2 | CS_ADSP2_REGION_3 | \ + CS_ADSP2_REGION_4 | CS_ADSP2_REGION_5 | \ + CS_ADSP2_REGION_6 | CS_ADSP2_REGION_7 | \ + CS_ADSP2_REGION_8 | CS_ADSP2_REGION_9) +#define CS_ADSP2_REGION_ALL (CS_ADSP2_REGION_0 | CS_ADSP2_REGION_1_9) + +#define CS_DSP_DATA_WORD_SIZE 3 + +#define CS_DSP_ACKED_CTL_TIMEOUT_MS 100 +#define CS_DSP_ACKED_CTL_N_QUICKPOLLS 10 +#define CS_DSP_ACKED_CTL_MIN_VALUE 0 +#define CS_DSP_ACKED_CTL_MAX_VALUE 0xFFFFFF + +/** + * struct cs_dsp_region - Describes a logical memory region in DSP address space + * @type: Memory region type + * @base: Address of region + */ +struct cs_dsp_region { + int type; + unsigned int base; +}; + +/** + * struct cs_dsp_alg_region - Describes a logical algorithm region in DSP address space + * @list: List node for internal use + * @alg: Algorithm id + * @type: Memory region type + * @base: Address of region + */ +struct cs_dsp_alg_region { + struct list_head list; + unsigned int alg; + int type; + unsigned int base; +}; + +/** + * struct cs_dsp_coeff_ctl - Describes a coefficient control + * @fw_name: Name of the firmware + * @subname: Name of the control parsed from the WMFW + * @subname_len: Length of subname + * @alg_region: Logical region associated with this control + * @dsp: DSP instance associated with this control + * @enabled: Flag indicating whether control is enabled + * @list: List node for internal use + * @cache: Cached value of the control + * @offset: Offset of control within alg_region + * @len: Length of the cached value + * @set: Flag indicating the value has been written by the user + * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h + * @type: One of the WMFW_CTL_TYPE_ control types defined in wmfw.h + * @priv: For use by the client + */ +struct cs_dsp_coeff_ctl { + const char *fw_name; + /* Subname is needed to match with firmware */ + const char *subname; + unsigned int subname_len; + struct cs_dsp_alg_region alg_region; + struct cs_dsp *dsp; + unsigned int enabled:1; + struct list_head list; + void *cache; + unsigned int offset; + size_t len; + unsigned int set:1; + unsigned int flags; + unsigned int type; + + void *priv; +}; + +struct cs_dsp_ops; +struct cs_dsp_client_ops; + +/** + * struct cs_dsp - Configuration and state of a Cirrus Logic DSP + * @name: The name of the DSP instance + * @rev: Revision of the DSP + * @num: DSP instance number + * @type: Type of DSP + * @dev: Driver model representation of the device + * @regmap: Register map of the device + * @ops: Function pointers for internal callbacks + * @client_ops: Function pointers for client callbacks + * @base: Address of the DSP registers + * @base_sysinfo: Address of the sysinfo register (Halo only) + * @sysclk_reg: Address of the sysclk register (ADSP1 only) + * @sysclk_mask: Mask of frequency bits within sysclk register (ADSP1 only) + * @sysclk_shift: Shift of frequency bits within sysclk register (ADSP1 only) + * @alg_regions: List of currently loaded algorithm regions + * @fw_file_name: Filename of the current firmware + * @fw_name: Name of the current firmware + * @fw_id: ID of the current firmware, obtained from the wmfw + * @fw_id_version: Version of the firmware, obtained from the wmfw + * @fw_vendor_id: Vendor of the firmware, obtained from the wmfw + * @mem: DSP memory region descriptions + * @num_mems: Number of memory regions in this DSP + * @fw_ver: Version of the wmfw file format + * @booted: Flag indicating DSP has been configured + * @running: Flag indicating DSP is executing firmware + * @ctl_list: Controls defined within the loaded DSP firmware + * @lock_regions: Enable MPU traps on specified memory regions + * @pwr_lock: Lock used to serialize accesses + * @debugfs_root: Debugfs directory for this DSP instance + * @wmfw_file_name: Filename of the currently loaded firmware + * @bin_file_name: Filename of the currently loaded coefficients + */ +struct cs_dsp { + const char *name; + int rev; + int num; + int type; + struct device *dev; + struct regmap *regmap; + + const struct cs_dsp_ops *ops; + const struct cs_dsp_client_ops *client_ops; + + unsigned int base; + unsigned int base_sysinfo; + unsigned int sysclk_reg; + unsigned int sysclk_mask; + unsigned int sysclk_shift; + + struct list_head alg_regions; + + const char *fw_name; + unsigned int fw_id; + unsigned int fw_id_version; + unsigned int fw_vendor_id; + + const struct cs_dsp_region *mem; + int num_mems; + + int fw_ver; + + bool booted; + bool running; + + struct list_head ctl_list; + + struct mutex pwr_lock; + + unsigned int lock_regions; + +#ifdef CONFIG_DEBUG_FS + struct dentry *debugfs_root; + char *wmfw_file_name; + char *bin_file_name; +#endif +}; + +/** + * struct cs_dsp_client_ops - client callbacks + * @control_add: Called under the pwr_lock when a control is created + * @control_remove: Called under the pwr_lock when a control is destroyed + * @post_run: Called under the pwr_lock by cs_dsp_run() + * @post_stop: Called under the pwr_lock by cs_dsp_stop() + * @watchdog_expired: Called when a watchdog expiry is detected + * + * These callbacks give the cs_dsp client an opportunity to respond to events + * or to perform actions atomically. + */ +struct cs_dsp_client_ops { + int (*control_add)(struct cs_dsp_coeff_ctl *ctl); + void (*control_remove)(struct cs_dsp_coeff_ctl *ctl); + int (*post_run)(struct cs_dsp *dsp); + void (*post_stop)(struct cs_dsp *dsp); + void (*watchdog_expired)(struct cs_dsp *dsp); +}; + +int cs_dsp_adsp1_init(struct cs_dsp *dsp); +int cs_dsp_adsp2_init(struct cs_dsp *dsp); +int cs_dsp_halo_init(struct cs_dsp *dsp); + +int cs_dsp_adsp1_power_up(struct cs_dsp *dsp, + const struct firmware *wmfw_firmware, char *wmfw_filename, + const struct firmware *coeff_firmware, char *coeff_filename, + const char *fw_name); +void cs_dsp_adsp1_power_down(struct cs_dsp *dsp); +int cs_dsp_power_up(struct cs_dsp *dsp, + const struct firmware *wmfw_firmware, char *wmfw_filename, + const struct firmware *coeff_firmware, char *coeff_filename, + const char *fw_name); +void cs_dsp_power_down(struct cs_dsp *dsp); +int cs_dsp_run(struct cs_dsp *dsp); +void cs_dsp_stop(struct cs_dsp *dsp); + +void cs_dsp_remove(struct cs_dsp *dsp); + +int cs_dsp_set_dspclk(struct cs_dsp *dsp, unsigned int freq); +void cs_dsp_adsp2_bus_error(struct cs_dsp *dsp); +void cs_dsp_halo_bus_error(struct cs_dsp *dsp); +void cs_dsp_halo_wdt_expire(struct cs_dsp *dsp); + +void cs_dsp_init_debugfs(struct cs_dsp *dsp, struct dentry *debugfs_root); +void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); + +int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); +int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_t len); +int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len); +struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, + unsigned int alg); + +int cs_dsp_read_raw_data_block(struct cs_dsp *dsp, int mem_type, unsigned int mem_addr, + unsigned int num_words, __be32 *data); +int cs_dsp_read_data_word(struct cs_dsp *dsp, int mem_type, unsigned int mem_addr, u32 *data); +int cs_dsp_write_data_word(struct cs_dsp *dsp, int mem_type, unsigned int mem_addr, u32 data); +void cs_dsp_remove_padding(u32 *buf, int nwords); + +struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp, + int type, unsigned int id); + +const char *cs_dsp_mem_region_name(unsigned int type); + +#endif diff --git a/include/linux/firmware/cirrus/wmfw.h b/include/linux/firmware/cirrus/wmfw.h new file mode 100644 index 000000000000..a19bf7c6fc8b --- /dev/null +++ b/include/linux/firmware/cirrus/wmfw.h @@ -0,0 +1,202 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * wmfw.h - Wolfson firmware format information + * + * Copyright 2012 Wolfson Microelectronics plc + * + * Author: Mark Brown + */ + +#ifndef __WMFW_H +#define __WMFW_H + +#include + +#define WMFW_MAX_ALG_NAME 256 +#define WMFW_MAX_ALG_DESCR_NAME 256 + +#define WMFW_MAX_COEFF_NAME 256 +#define WMFW_MAX_COEFF_DESCR_NAME 256 + +#define WMFW_CTL_FLAG_SYS 0x8000 +#define WMFW_CTL_FLAG_VOLATILE 0x0004 +#define WMFW_CTL_FLAG_WRITEABLE 0x0002 +#define WMFW_CTL_FLAG_READABLE 0x0001 + +#define WMFW_CTL_TYPE_BYTES 0x0004 /* byte control */ + +/* Non-ALSA coefficient types start at 0x1000 */ +#define WMFW_CTL_TYPE_ACKED 0x1000 /* acked control */ +#define WMFW_CTL_TYPE_HOSTEVENT 0x1001 /* event control */ +#define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */ + +struct wmfw_header { + char magic[4]; + __le32 len; + __le16 rev; + u8 core; + u8 ver; +} __packed; + +struct wmfw_footer { + __le64 timestamp; + __le32 checksum; +} __packed; + +struct wmfw_adsp1_sizes { + __le32 dm; + __le32 pm; + __le32 zm; +} __packed; + +struct wmfw_adsp2_sizes { + __le32 xm; + __le32 ym; + __le32 pm; + __le32 zm; +} __packed; + +struct wmfw_region { + union { + __be32 type; + __le32 offset; + }; + __le32 len; + u8 data[]; +} __packed; + +struct wmfw_id_hdr { + __be32 core_id; + __be32 core_rev; + __be32 id; + __be32 ver; +} __packed; + +struct wmfw_v3_id_hdr { + __be32 core_id; + __be32 block_rev; + __be32 vendor_id; + __be32 id; + __be32 ver; +} __packed; + +struct wmfw_adsp1_id_hdr { + struct wmfw_id_hdr fw; + __be32 zm; + __be32 dm; + __be32 n_algs; +} __packed; + +struct wmfw_adsp2_id_hdr { + struct wmfw_id_hdr fw; + __be32 zm; + __be32 xm; + __be32 ym; + __be32 n_algs; +} __packed; + +struct wmfw_halo_id_hdr { + struct wmfw_v3_id_hdr fw; + __be32 xm_base; + __be32 xm_size; + __be32 ym_base; + __be32 ym_size; + __be32 n_algs; +} __packed; + +struct wmfw_alg_hdr { + __be32 id; + __be32 ver; +} __packed; + +struct wmfw_adsp1_alg_hdr { + struct wmfw_alg_hdr alg; + __be32 zm; + __be32 dm; +} __packed; + +struct wmfw_adsp2_alg_hdr { + struct wmfw_alg_hdr alg; + __be32 zm; + __be32 xm; + __be32 ym; +} __packed; + +struct wmfw_halo_alg_hdr { + struct wmfw_alg_hdr alg; + __be32 xm_base; + __be32 xm_size; + __be32 ym_base; + __be32 ym_size; +} __packed; + +struct wmfw_adsp_alg_data { + __le32 id; + u8 name[WMFW_MAX_ALG_NAME]; + u8 descr[WMFW_MAX_ALG_DESCR_NAME]; + __le32 ncoeff; + u8 data[]; +} __packed; + +struct wmfw_adsp_coeff_data { + struct { + __le16 offset; + __le16 type; + __le32 size; + } hdr; + u8 name[WMFW_MAX_COEFF_NAME]; + u8 descr[WMFW_MAX_COEFF_DESCR_NAME]; + __le16 ctl_type; + __le16 flags; + __le32 len; + u8 data[]; +} __packed; + +struct wmfw_coeff_hdr { + u8 magic[4]; + __le32 len; + union { + __be32 rev; + __le32 ver; + }; + union { + __be32 core; + __le32 core_ver; + }; + u8 data[]; +} __packed; + +struct wmfw_coeff_item { + __le16 offset; + __le16 type; + __le32 id; + __le32 ver; + __le32 sr; + __le32 len; + u8 data[]; +} __packed; + +#define WMFW_ADSP1 1 +#define WMFW_ADSP2 2 +#define WMFW_HALO 4 + +#define WMFW_ABSOLUTE 0xf0 +#define WMFW_ALGORITHM_DATA 0xf2 +#define WMFW_METADATA 0xfc +#define WMFW_NAME_TEXT 0xfe +#define WMFW_INFO_TEXT 0xff + +#define WMFW_ADSP1_PM 2 +#define WMFW_ADSP1_DM 3 +#define WMFW_ADSP1_ZM 4 + +#define WMFW_ADSP2_PM 2 +#define WMFW_ADSP2_ZM 4 +#define WMFW_ADSP2_XM 5 +#define WMFW_ADSP2_YM 6 + +#define WMFW_HALO_PM_PACKED 0x10 +#define WMFW_HALO_XM_PACKED 0x11 +#define WMFW_HALO_YM_PACKED 0x12 + +#endif diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index ab7ac5e0bd68..deda5ee02ebb 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -333,6 +333,7 @@ config SND_SOC_WM_HUBS config SND_SOC_WM_ADSP tristate + select CS_DSP select SND_SOC_COMPRESS default y if SND_SOC_MADERA=y default y if SND_SOC_CS47L24=y diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 6c5d55b3b311..f17c749c24c3 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include @@ -44,15 +43,6 @@ #define adsp_dbg(_dsp, fmt, ...) \ dev_dbg(_dsp->cs_dsp.dev, "%s: " fmt, _dsp->cs_dsp.name, ##__VA_ARGS__) -#define cs_dsp_err(_dsp, fmt, ...) \ - dev_err(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) -#define cs_dsp_warn(_dsp, fmt, ...) \ - dev_warn(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) -#define cs_dsp_info(_dsp, fmt, ...) \ - dev_info(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) -#define cs_dsp_dbg(_dsp, fmt, ...) \ - dev_dbg(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__) - #define compr_err(_obj, fmt, ...) \ adsp_err(_obj->dsp, "%s: " fmt, _obj->name ? _obj->name : "legacy", \ ##__VA_ARGS__) @@ -60,305 +50,11 @@ adsp_dbg(_obj->dsp, "%s: " fmt, _obj->name ? _obj->name : "legacy", \ ##__VA_ARGS__) -#define ADSP1_CONTROL_1 0x00 -#define ADSP1_CONTROL_2 0x02 -#define ADSP1_CONTROL_3 0x03 -#define ADSP1_CONTROL_4 0x04 -#define ADSP1_CONTROL_5 0x06 -#define ADSP1_CONTROL_6 0x07 -#define ADSP1_CONTROL_7 0x08 -#define ADSP1_CONTROL_8 0x09 -#define ADSP1_CONTROL_9 0x0A -#define ADSP1_CONTROL_10 0x0B -#define ADSP1_CONTROL_11 0x0C -#define ADSP1_CONTROL_12 0x0D -#define ADSP1_CONTROL_13 0x0F -#define ADSP1_CONTROL_14 0x10 -#define ADSP1_CONTROL_15 0x11 -#define ADSP1_CONTROL_16 0x12 -#define ADSP1_CONTROL_17 0x13 -#define ADSP1_CONTROL_18 0x14 -#define ADSP1_CONTROL_19 0x16 -#define ADSP1_CONTROL_20 0x17 -#define ADSP1_CONTROL_21 0x18 -#define ADSP1_CONTROL_22 0x1A -#define ADSP1_CONTROL_23 0x1B -#define ADSP1_CONTROL_24 0x1C -#define ADSP1_CONTROL_25 0x1E -#define ADSP1_CONTROL_26 0x20 -#define ADSP1_CONTROL_27 0x21 -#define ADSP1_CONTROL_28 0x22 -#define ADSP1_CONTROL_29 0x23 -#define ADSP1_CONTROL_30 0x24 -#define ADSP1_CONTROL_31 0x26 - -/* - * ADSP1 Control 19 - */ -#define ADSP1_WDMA_BUFFER_LENGTH_MASK 0x00FF /* DSP1_WDMA_BUFFER_LENGTH - [7:0] */ -#define ADSP1_WDMA_BUFFER_LENGTH_SHIFT 0 /* DSP1_WDMA_BUFFER_LENGTH - [7:0] */ -#define ADSP1_WDMA_BUFFER_LENGTH_WIDTH 8 /* DSP1_WDMA_BUFFER_LENGTH - [7:0] */ - - -/* - * ADSP1 Control 30 - */ -#define ADSP1_DBG_CLK_ENA 0x0008 /* DSP1_DBG_CLK_ENA */ -#define ADSP1_DBG_CLK_ENA_MASK 0x0008 /* DSP1_DBG_CLK_ENA */ -#define ADSP1_DBG_CLK_ENA_SHIFT 3 /* DSP1_DBG_CLK_ENA */ -#define ADSP1_DBG_CLK_ENA_WIDTH 1 /* DSP1_DBG_CLK_ENA */ -#define ADSP1_SYS_ENA 0x0004 /* DSP1_SYS_ENA */ -#define ADSP1_SYS_ENA_MASK 0x0004 /* DSP1_SYS_ENA */ -#define ADSP1_SYS_ENA_SHIFT 2 /* DSP1_SYS_ENA */ -#define ADSP1_SYS_ENA_WIDTH 1 /* DSP1_SYS_ENA */ -#define ADSP1_CORE_ENA 0x0002 /* DSP1_CORE_ENA */ -#define ADSP1_CORE_ENA_MASK 0x0002 /* DSP1_CORE_ENA */ -#define ADSP1_CORE_ENA_SHIFT 1 /* DSP1_CORE_ENA */ -#define ADSP1_CORE_ENA_WIDTH 1 /* DSP1_CORE_ENA */ -#define ADSP1_START 0x0001 /* DSP1_START */ -#define ADSP1_START_MASK 0x0001 /* DSP1_START */ -#define ADSP1_START_SHIFT 0 /* DSP1_START */ -#define ADSP1_START_WIDTH 1 /* DSP1_START */ - -/* - * ADSP1 Control 31 - */ -#define ADSP1_CLK_SEL_MASK 0x0007 /* CLK_SEL_ENA */ -#define ADSP1_CLK_SEL_SHIFT 0 /* CLK_SEL_ENA */ -#define ADSP1_CLK_SEL_WIDTH 3 /* CLK_SEL_ENA */ - -#define ADSP2_CONTROL 0x0 -#define ADSP2_CLOCKING 0x1 -#define ADSP2V2_CLOCKING 0x2 -#define ADSP2_STATUS1 0x4 -#define ADSP2_WDMA_CONFIG_1 0x30 -#define ADSP2_WDMA_CONFIG_2 0x31 -#define ADSP2V2_WDMA_CONFIG_2 0x32 -#define ADSP2_RDMA_CONFIG_1 0x34 - -#define ADSP2_SCRATCH0 0x40 -#define ADSP2_SCRATCH1 0x41 -#define ADSP2_SCRATCH2 0x42 -#define ADSP2_SCRATCH3 0x43 - -#define ADSP2V2_SCRATCH0_1 0x40 -#define ADSP2V2_SCRATCH2_3 0x42 - -/* - * ADSP2 Control - */ - -#define ADSP2_MEM_ENA 0x0010 /* DSP1_MEM_ENA */ -#define ADSP2_MEM_ENA_MASK 0x0010 /* DSP1_MEM_ENA */ -#define ADSP2_MEM_ENA_SHIFT 4 /* DSP1_MEM_ENA */ -#define ADSP2_MEM_ENA_WIDTH 1 /* DSP1_MEM_ENA */ -#define ADSP2_SYS_ENA 0x0004 /* DSP1_SYS_ENA */ -#define ADSP2_SYS_ENA_MASK 0x0004 /* DSP1_SYS_ENA */ -#define ADSP2_SYS_ENA_SHIFT 2 /* DSP1_SYS_ENA */ -#define ADSP2_SYS_ENA_WIDTH 1 /* DSP1_SYS_ENA */ -#define ADSP2_CORE_ENA 0x0002 /* DSP1_CORE_ENA */ -#define ADSP2_CORE_ENA_MASK 0x0002 /* DSP1_CORE_ENA */ -#define ADSP2_CORE_ENA_SHIFT 1 /* DSP1_CORE_ENA */ -#define ADSP2_CORE_ENA_WIDTH 1 /* DSP1_CORE_ENA */ -#define ADSP2_START 0x0001 /* DSP1_START */ -#define ADSP2_START_MASK 0x0001 /* DSP1_START */ -#define ADSP2_START_SHIFT 0 /* DSP1_START */ -#define ADSP2_START_WIDTH 1 /* DSP1_START */ - -/* - * ADSP2 clocking - */ -#define ADSP2_CLK_SEL_MASK 0x0007 /* CLK_SEL_ENA */ -#define ADSP2_CLK_SEL_SHIFT 0 /* CLK_SEL_ENA */ -#define ADSP2_CLK_SEL_WIDTH 3 /* CLK_SEL_ENA */ - -/* - * ADSP2V2 clocking - */ -#define ADSP2V2_CLK_SEL_MASK 0x70000 /* CLK_SEL_ENA */ -#define ADSP2V2_CLK_SEL_SHIFT 16 /* CLK_SEL_ENA */ -#define ADSP2V2_CLK_SEL_WIDTH 3 /* CLK_SEL_ENA */ - -#define ADSP2V2_RATE_MASK 0x7800 /* DSP_RATE */ -#define ADSP2V2_RATE_SHIFT 11 /* DSP_RATE */ -#define ADSP2V2_RATE_WIDTH 4 /* DSP_RATE */ - -/* - * ADSP2 Status 1 - */ -#define ADSP2_RAM_RDY 0x0001 -#define ADSP2_RAM_RDY_MASK 0x0001 -#define ADSP2_RAM_RDY_SHIFT 0 -#define ADSP2_RAM_RDY_WIDTH 1 - -/* - * ADSP2 Lock support - */ -#define ADSP2_LOCK_CODE_0 0x5555 -#define ADSP2_LOCK_CODE_1 0xAAAA - -#define ADSP2_WATCHDOG 0x0A -#define ADSP2_BUS_ERR_ADDR 0x52 -#define ADSP2_REGION_LOCK_STATUS 0x64 -#define ADSP2_LOCK_REGION_1_LOCK_REGION_0 0x66 -#define ADSP2_LOCK_REGION_3_LOCK_REGION_2 0x68 -#define ADSP2_LOCK_REGION_5_LOCK_REGION_4 0x6A -#define ADSP2_LOCK_REGION_7_LOCK_REGION_6 0x6C -#define ADSP2_LOCK_REGION_9_LOCK_REGION_8 0x6E -#define ADSP2_LOCK_REGION_CTRL 0x7A -#define ADSP2_PMEM_ERR_ADDR_XMEM_ERR_ADDR 0x7C - -#define ADSP2_REGION_LOCK_ERR_MASK 0x8000 -#define ADSP2_ADDR_ERR_MASK 0x4000 -#define ADSP2_WDT_TIMEOUT_STS_MASK 0x2000 -#define ADSP2_CTRL_ERR_PAUSE_ENA 0x0002 -#define ADSP2_CTRL_ERR_EINT 0x0001 - -#define ADSP2_BUS_ERR_ADDR_MASK 0x00FFFFFF -#define ADSP2_XMEM_ERR_ADDR_MASK 0x0000FFFF -#define ADSP2_PMEM_ERR_ADDR_MASK 0x7FFF0000 -#define ADSP2_PMEM_ERR_ADDR_SHIFT 16 -#define ADSP2_WDT_ENA_MASK 0xFFFFFFFD - -#define ADSP2_LOCK_REGION_SHIFT 16 - #define ADSP_MAX_STD_CTRL_SIZE 512 -#define CS_DSP_ACKED_CTL_TIMEOUT_MS 100 -#define CS_DSP_ACKED_CTL_N_QUICKPOLLS 10 -#define CS_DSP_ACKED_CTL_MIN_VALUE 0 -#define CS_DSP_ACKED_CTL_MAX_VALUE 0xFFFFFF - -/* - * Event control messages - */ -#define CS_DSP_FW_EVENT_SHUTDOWN 0x000001 - -/* - * HALO system info - */ -#define HALO_AHBM_WINDOW_DEBUG_0 0x02040 -#define HALO_AHBM_WINDOW_DEBUG_1 0x02044 - -/* - * HALO core - */ -#define HALO_SCRATCH1 0x005c0 -#define HALO_SCRATCH2 0x005c8 -#define HALO_SCRATCH3 0x005d0 -#define HALO_SCRATCH4 0x005d8 -#define HALO_CCM_CORE_CONTROL 0x41000 -#define HALO_CORE_SOFT_RESET 0x00010 -#define HALO_WDT_CONTROL 0x47000 - -/* - * HALO MPU banks - */ -#define HALO_MPU_XMEM_ACCESS_0 0x43000 -#define HALO_MPU_YMEM_ACCESS_0 0x43004 -#define HALO_MPU_WINDOW_ACCESS_0 0x43008 -#define HALO_MPU_XREG_ACCESS_0 0x4300C -#define HALO_MPU_YREG_ACCESS_0 0x43014 -#define HALO_MPU_XMEM_ACCESS_1 0x43018 -#define HALO_MPU_YMEM_ACCESS_1 0x4301C -#define HALO_MPU_WINDOW_ACCESS_1 0x43020 -#define HALO_MPU_XREG_ACCESS_1 0x43024 -#define HALO_MPU_YREG_ACCESS_1 0x4302C -#define HALO_MPU_XMEM_ACCESS_2 0x43030 -#define HALO_MPU_YMEM_ACCESS_2 0x43034 -#define HALO_MPU_WINDOW_ACCESS_2 0x43038 -#define HALO_MPU_XREG_ACCESS_2 0x4303C -#define HALO_MPU_YREG_ACCESS_2 0x43044 -#define HALO_MPU_XMEM_ACCESS_3 0x43048 -#define HALO_MPU_YMEM_ACCESS_3 0x4304C -#define HALO_MPU_WINDOW_ACCESS_3 0x43050 -#define HALO_MPU_XREG_ACCESS_3 0x43054 -#define HALO_MPU_YREG_ACCESS_3 0x4305C -#define HALO_MPU_XM_VIO_ADDR 0x43100 -#define HALO_MPU_XM_VIO_STATUS 0x43104 -#define HALO_MPU_YM_VIO_ADDR 0x43108 -#define HALO_MPU_YM_VIO_STATUS 0x4310C -#define HALO_MPU_PM_VIO_ADDR 0x43110 -#define HALO_MPU_PM_VIO_STATUS 0x43114 -#define HALO_MPU_LOCK_CONFIG 0x43140 - -/* - * HALO_AHBM_WINDOW_DEBUG_1 - */ -#define HALO_AHBM_CORE_ERR_ADDR_MASK 0x0fffff00 -#define HALO_AHBM_CORE_ERR_ADDR_SHIFT 8 -#define HALO_AHBM_FLAGS_ERR_MASK 0x000000ff - -/* - * HALO_CCM_CORE_CONTROL - */ -#define HALO_CORE_RESET 0x00000200 -#define HALO_CORE_EN 0x00000001 - -/* - * HALO_CORE_SOFT_RESET - */ -#define HALO_CORE_SOFT_RESET_MASK 0x00000001 - -/* - * HALO_WDT_CONTROL - */ -#define HALO_WDT_EN_MASK 0x00000001 - -/* - * HALO_MPU_?M_VIO_STATUS - */ -#define HALO_MPU_VIO_STS_MASK 0x007e0000 -#define HALO_MPU_VIO_STS_SHIFT 17 -#define HALO_MPU_VIO_ERR_WR_MASK 0x00008000 -#define HALO_MPU_VIO_ERR_SRC_MASK 0x00007fff -#define HALO_MPU_VIO_ERR_SRC_SHIFT 0 - -static const struct cs_dsp_ops cs_dsp_adsp1_ops; -static const struct cs_dsp_ops cs_dsp_adsp2_ops[]; -static const struct cs_dsp_ops cs_dsp_halo_ops; - static const struct cs_dsp_client_ops wm_adsp1_client_ops; static const struct cs_dsp_client_ops wm_adsp2_client_ops; -struct cs_dsp_buf { - struct list_head list; - void *buf; -}; - -static struct cs_dsp_buf *cs_dsp_buf_alloc(const void *src, size_t len, - struct list_head *list) -{ - struct cs_dsp_buf *buf = kzalloc(sizeof(*buf), GFP_KERNEL); - - if (buf == NULL) - return NULL; - - buf->buf = vmalloc(len); - if (!buf->buf) { - kfree(buf); - return NULL; - } - memcpy(buf->buf, src, len); - - if (list) - list_add_tail(&buf->list, list); - - return buf; -} - -static void cs_dsp_buf_free(struct list_head *list) -{ - while (!list_empty(list)) { - struct cs_dsp_buf *buf = list_first_entry(list, - struct cs_dsp_buf, - list); - list_del(&buf->list); - vfree(buf->buf); - kfree(buf); - } -} - #define WM_ADSP_FW_MBC_VSS 0 #define WM_ADSP_FW_HIFI 1 #define WM_ADSP_FW_TX 2 @@ -483,8 +179,6 @@ struct wm_adsp_compr { const char *name; }; -#define CS_DSP_DATA_WORD_SIZE 3 - #define WM_ADSP_MIN_FRAGMENTS 1 #define WM_ADSP_MAX_FRAGMENTS 256 #define WM_ADSP_MIN_FRAGMENT_SIZE (64 * CS_DSP_DATA_WORD_SIZE) @@ -616,166 +310,6 @@ struct wm_coeff_ctl { struct work_struct work; }; -static const char *cs_dsp_mem_region_name(unsigned int type) -{ - switch (type) { - case WMFW_ADSP1_PM: - return "PM"; - case WMFW_HALO_PM_PACKED: - return "PM_PACKED"; - case WMFW_ADSP1_DM: - return "DM"; - case WMFW_ADSP2_XM: - return "XM"; - case WMFW_HALO_XM_PACKED: - return "XM_PACKED"; - case WMFW_ADSP2_YM: - return "YM"; - case WMFW_HALO_YM_PACKED: - return "YM_PACKED"; - case WMFW_ADSP1_ZM: - return "ZM"; - default: - return NULL; - } -} - -#ifdef CONFIG_DEBUG_FS -static void cs_dsp_debugfs_save_wmfwname(struct cs_dsp *dsp, const char *s) -{ - char *tmp = kasprintf(GFP_KERNEL, "%s\n", s); - - kfree(dsp->wmfw_file_name); - dsp->wmfw_file_name = tmp; -} - -static void cs_dsp_debugfs_save_binname(struct cs_dsp *dsp, const char *s) -{ - char *tmp = kasprintf(GFP_KERNEL, "%s\n", s); - - kfree(dsp->bin_file_name); - dsp->bin_file_name = tmp; -} - -static void cs_dsp_debugfs_clear(struct cs_dsp *dsp) -{ - kfree(dsp->wmfw_file_name); - kfree(dsp->bin_file_name); - dsp->wmfw_file_name = NULL; - dsp->bin_file_name = NULL; -} - -static ssize_t cs_dsp_debugfs_wmfw_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct cs_dsp *dsp = file->private_data; - ssize_t ret; - - mutex_lock(&dsp->pwr_lock); - - if (!dsp->wmfw_file_name || !dsp->booted) - ret = 0; - else - ret = simple_read_from_buffer(user_buf, count, ppos, - dsp->wmfw_file_name, - strlen(dsp->wmfw_file_name)); - - mutex_unlock(&dsp->pwr_lock); - return ret; -} - -static ssize_t cs_dsp_debugfs_bin_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct cs_dsp *dsp = file->private_data; - ssize_t ret; - - mutex_lock(&dsp->pwr_lock); - - if (!dsp->bin_file_name || !dsp->booted) - ret = 0; - else - ret = simple_read_from_buffer(user_buf, count, ppos, - dsp->bin_file_name, - strlen(dsp->bin_file_name)); - - mutex_unlock(&dsp->pwr_lock); - return ret; -} - -static const struct { - const char *name; - const struct file_operations fops; -} cs_dsp_debugfs_fops[] = { - { - .name = "wmfw_file_name", - .fops = { - .open = simple_open, - .read = cs_dsp_debugfs_wmfw_read, - }, - }, - { - .name = "bin_file_name", - .fops = { - .open = simple_open, - .read = cs_dsp_debugfs_bin_read, - }, - }, -}; - -static void cs_dsp_init_debugfs(struct cs_dsp *dsp, - struct dentry *debugfs_root) -{ - struct dentry *root = NULL; - int i; - - root = debugfs_create_dir(dsp->name, debugfs_root); - - debugfs_create_bool("booted", 0444, root, &dsp->booted); - debugfs_create_bool("running", 0444, root, &dsp->running); - debugfs_create_x32("fw_id", 0444, root, &dsp->fw_id); - debugfs_create_x32("fw_version", 0444, root, &dsp->fw_id_version); - - for (i = 0; i < ARRAY_SIZE(cs_dsp_debugfs_fops); ++i) - debugfs_create_file(cs_dsp_debugfs_fops[i].name, 0444, root, - dsp, &cs_dsp_debugfs_fops[i].fops); - - dsp->debugfs_root = root; -} - -static void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp) -{ - cs_dsp_debugfs_clear(dsp); - debugfs_remove_recursive(dsp->debugfs_root); - dsp->debugfs_root = NULL; -} -#else -static inline void cs_dsp_init_debugfs(struct cs_dsp *dsp, - struct dentry *debugfs_root) -{ -} - -static inline void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp) -{ -} - -static inline void cs_dsp_debugfs_save_wmfwname(struct cs_dsp *dsp, - const char *s) -{ -} - -static inline void cs_dsp_debugfs_save_binname(struct cs_dsp *dsp, - const char *s) -{ -} - -static inline void cs_dsp_debugfs_clear(struct cs_dsp *dsp) -{ -} -#endif - int wm_adsp_fw_get(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { @@ -827,126 +361,11 @@ const struct soc_enum wm_adsp_fw_enum[] = { }; EXPORT_SYMBOL_GPL(wm_adsp_fw_enum); -static const struct cs_dsp_region *cs_dsp_find_region(struct cs_dsp *dsp, - int type) -{ - int i; - - for (i = 0; i < dsp->num_mems; i++) - if (dsp->mem[i].type == type) - return &dsp->mem[i]; - - return NULL; -} - -static unsigned int cs_dsp_region_to_reg(struct cs_dsp_region const *mem, - unsigned int offset) -{ - switch (mem->type) { - case WMFW_ADSP1_PM: - return mem->base + (offset * 3); - case WMFW_ADSP1_DM: - case WMFW_ADSP2_XM: - case WMFW_ADSP2_YM: - case WMFW_ADSP1_ZM: - return mem->base + (offset * 2); - default: - WARN(1, "Unknown memory region type"); - return offset; - } -} - -static unsigned int cs_dsp_halo_region_to_reg(struct cs_dsp_region const *mem, - unsigned int offset) -{ - switch (mem->type) { - case WMFW_ADSP2_XM: - case WMFW_ADSP2_YM: - return mem->base + (offset * 4); - case WMFW_HALO_XM_PACKED: - case WMFW_HALO_YM_PACKED: - return (mem->base + (offset * 3)) & ~0x3; - case WMFW_HALO_PM_PACKED: - return mem->base + (offset * 5); - default: - WARN(1, "Unknown memory region type"); - return offset; - } -} - -static void cs_dsp_read_fw_status(struct cs_dsp *dsp, - int noffs, unsigned int *offs) -{ - unsigned int i; - int ret; - - for (i = 0; i < noffs; ++i) { - ret = regmap_read(dsp->regmap, dsp->base + offs[i], &offs[i]); - if (ret) { - cs_dsp_err(dsp, "Failed to read SCRATCH%u: %d\n", i, ret); - return; - } - } -} - -static void cs_dsp_adsp2_show_fw_status(struct cs_dsp *dsp) -{ - unsigned int offs[] = { - ADSP2_SCRATCH0, ADSP2_SCRATCH1, ADSP2_SCRATCH2, ADSP2_SCRATCH3, - }; - - cs_dsp_read_fw_status(dsp, ARRAY_SIZE(offs), offs); - - cs_dsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", - offs[0], offs[1], offs[2], offs[3]); -} - -static void cs_dsp_adsp2v2_show_fw_status(struct cs_dsp *dsp) -{ - unsigned int offs[] = { ADSP2V2_SCRATCH0_1, ADSP2V2_SCRATCH2_3 }; - - cs_dsp_read_fw_status(dsp, ARRAY_SIZE(offs), offs); - - cs_dsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", - offs[0] & 0xFFFF, offs[0] >> 16, - offs[1] & 0xFFFF, offs[1] >> 16); -} - -static void cs_dsp_halo_show_fw_status(struct cs_dsp *dsp) -{ - unsigned int offs[] = { - HALO_SCRATCH1, HALO_SCRATCH2, HALO_SCRATCH3, HALO_SCRATCH4, - }; - - cs_dsp_read_fw_status(dsp, ARRAY_SIZE(offs), offs); - - cs_dsp_dbg(dsp, "FW SCRATCH 0:0x%x 1:0x%x 2:0x%x 3:0x%x\n", - offs[0], offs[1], offs[2], offs[3]); -} - static inline struct wm_coeff_ctl *bytes_ext_to_ctl(struct soc_bytes_ext *ext) { return container_of(ext, struct wm_coeff_ctl, bytes_ext); } -static int cs_dsp_coeff_base_reg(struct cs_dsp_coeff_ctl *ctl, unsigned int *reg) -{ - const struct cs_dsp_alg_region *alg_region = &ctl->alg_region; - struct cs_dsp *dsp = ctl->dsp; - const struct cs_dsp_region *mem; - - mem = cs_dsp_find_region(dsp, alg_region->type); - if (!mem) { - cs_dsp_err(dsp, "No base for region %x\n", - alg_region->type); - return -EINVAL; - } - - *reg = dsp->ops->region_to_reg(mem, ctl->alg_region.base + ctl->offset); - - return 0; -} - static int wm_coeff_info(struct snd_kcontrol *kctl, struct snd_ctl_elem_info *uinfo) { @@ -972,117 +391,6 @@ static int wm_coeff_info(struct snd_kcontrol *kctl, return 0; } -static int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, - unsigned int event_id) -{ - struct cs_dsp *dsp = ctl->dsp; - __be32 val = cpu_to_be32(event_id); - unsigned int reg; - int i, ret; - - if (!dsp->running) - return -EPERM; - - ret = cs_dsp_coeff_base_reg(ctl, ®); - if (ret) - return ret; - - cs_dsp_dbg(dsp, "Sending 0x%x to acked control alg 0x%x %s:0x%x\n", - event_id, ctl->alg_region.alg, - cs_dsp_mem_region_name(ctl->alg_region.type), ctl->offset); - - ret = regmap_raw_write(dsp->regmap, reg, &val, sizeof(val)); - if (ret) { - cs_dsp_err(dsp, "Failed to write %x: %d\n", reg, ret); - return ret; - } - - /* - * Poll for ack, we initially poll at ~1ms intervals for firmwares - * that respond quickly, then go to ~10ms polls. A firmware is unlikely - * to ack instantly so we do the first 1ms delay before reading the - * control to avoid a pointless bus transaction - */ - for (i = 0; i < CS_DSP_ACKED_CTL_TIMEOUT_MS;) { - switch (i) { - case 0 ... CS_DSP_ACKED_CTL_N_QUICKPOLLS - 1: - usleep_range(1000, 2000); - i++; - break; - default: - usleep_range(10000, 20000); - i += 10; - break; - } - - ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val)); - if (ret) { - cs_dsp_err(dsp, "Failed to read %x: %d\n", reg, ret); - return ret; - } - - if (val == 0) { - cs_dsp_dbg(dsp, "Acked control ACKED at poll %u\n", i); - return 0; - } - } - - cs_dsp_warn(dsp, "Acked control @0x%x alg:0x%x %s:0x%x timed out\n", - reg, ctl->alg_region.alg, - cs_dsp_mem_region_name(ctl->alg_region.type), - ctl->offset); - - return -ETIMEDOUT; -} - -static int cs_dsp_coeff_write_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, - const void *buf, size_t len) -{ - struct cs_dsp *dsp = ctl->dsp; - void *scratch; - int ret; - unsigned int reg; - - ret = cs_dsp_coeff_base_reg(ctl, ®); - if (ret) - return ret; - - scratch = kmemdup(buf, len, GFP_KERNEL | GFP_DMA); - if (!scratch) - return -ENOMEM; - - ret = regmap_raw_write(dsp->regmap, reg, scratch, - len); - if (ret) { - cs_dsp_err(dsp, "Failed to write %zu bytes to %x: %d\n", - len, reg, ret); - kfree(scratch); - return ret; - } - cs_dsp_dbg(dsp, "Wrote %zu bytes to %x\n", len, reg); - - kfree(scratch); - - return 0; -} - -static int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, - const void *buf, size_t len) -{ - int ret = 0; - - if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) - ret = -EPERM; - else if (buf != ctl->cache) - memcpy(ctl->cache, buf, len); - - ctl->set = 1; - if (ctl->enabled && ctl->dsp->running) - ret = cs_dsp_coeff_write_ctrl_raw(ctl, buf, len); - - return ret; -} - static int wm_coeff_put(struct snd_kcontrol *kctl, struct snd_ctl_elem_value *ucontrol) { @@ -1146,65 +454,14 @@ static int wm_coeff_put_acked(struct snd_kcontrol *kctl, return ret; } -static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, - void *buf, size_t len) +static int wm_coeff_get(struct snd_kcontrol *kctl, + struct snd_ctl_elem_value *ucontrol) { - struct cs_dsp *dsp = ctl->dsp; - void *scratch; - int ret; - unsigned int reg; - - ret = cs_dsp_coeff_base_reg(ctl, ®); - if (ret) - return ret; - - scratch = kmalloc(len, GFP_KERNEL | GFP_DMA); - if (!scratch) - return -ENOMEM; - - ret = regmap_raw_read(dsp->regmap, reg, scratch, len); - if (ret) { - cs_dsp_err(dsp, "Failed to read %zu bytes from %x: %d\n", - len, reg, ret); - kfree(scratch); - return ret; - } - cs_dsp_dbg(dsp, "Read %zu bytes from %x\n", len, reg); - - memcpy(buf, scratch, len); - kfree(scratch); - - return 0; -} - -static int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len) -{ - int ret = 0; - - if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) { - if (ctl->enabled && ctl->dsp->running) - return cs_dsp_coeff_read_ctrl_raw(ctl, buf, len); - else - return -EPERM; - } else { - if (!ctl->flags && ctl->enabled && ctl->dsp->running) - ret = cs_dsp_coeff_read_ctrl_raw(ctl, ctl->cache, ctl->len); - - if (buf != ctl->cache) - memcpy(buf, ctl->cache, len); - } - - return ret; -} - -static int wm_coeff_get(struct snd_kcontrol *kctl, - struct snd_ctl_elem_value *ucontrol) -{ - struct soc_bytes_ext *bytes_ext = - (struct soc_bytes_ext *)kctl->private_value; - struct wm_coeff_ctl *ctl = bytes_ext_to_ctl(bytes_ext); - struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; - char *p = ucontrol->value.bytes.data; + struct soc_bytes_ext *bytes_ext = + (struct soc_bytes_ext *)kctl->private_value; + struct wm_coeff_ctl *ctl = bytes_ext_to_ctl(bytes_ext); + struct cs_dsp_coeff_ctl *cs_ctl = ctl->cs_ctl; + char *p = ucontrol->value.bytes.data; int ret; mutex_lock(&cs_ctl->dsp->pwr_lock); @@ -1328,72 +585,6 @@ err_kcontrol: return ret; } -static int cs_dsp_coeff_init_control_caches(struct cs_dsp *dsp) -{ - struct cs_dsp_coeff_ctl *ctl; - int ret; - - list_for_each_entry(ctl, &dsp->ctl_list, list) { - if (!ctl->enabled || ctl->set) - continue; - if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) - continue; - - /* - * For readable controls populate the cache from the DSP memory. - * For non-readable controls the cache was zero-filled when - * created so we don't need to do anything. - */ - if (!ctl->flags || (ctl->flags & WMFW_CTL_FLAG_READABLE)) { - ret = cs_dsp_coeff_read_ctrl_raw(ctl, ctl->cache, ctl->len); - if (ret < 0) - return ret; - } - } - - return 0; -} - -static int cs_dsp_coeff_sync_controls(struct cs_dsp *dsp) -{ - struct cs_dsp_coeff_ctl *ctl; - int ret; - - list_for_each_entry(ctl, &dsp->ctl_list, list) { - if (!ctl->enabled) - continue; - if (ctl->set && !(ctl->flags & WMFW_CTL_FLAG_VOLATILE)) { - ret = cs_dsp_coeff_write_ctrl_raw(ctl, ctl->cache, - ctl->len); - if (ret < 0) - return ret; - } - } - - return 0; -} - -static void cs_dsp_signal_event_controls(struct cs_dsp *dsp, - unsigned int event) -{ - struct cs_dsp_coeff_ctl *ctl; - int ret; - - list_for_each_entry(ctl, &dsp->ctl_list, list) { - if (ctl->type != WMFW_CTL_TYPE_HOSTEVENT) - continue; - - if (!ctl->enabled) - continue; - - ret = cs_dsp_coeff_write_acked_control(ctl, event); - if (ret) - cs_dsp_warn(dsp, - "Failed to send 0x%x event to alg 0x%x (%d)\n", - event, ctl->alg_region.alg, ret); - } -} - static void wm_adsp_ctl_work(struct work_struct *work) { struct wm_coeff_ctl *ctl = container_of(work, @@ -1406,13 +597,6 @@ static void wm_adsp_ctl_work(struct work_struct *work) wmfw_add_ctl(dsp, ctl); } -static void cs_dsp_free_ctl_blk(struct cs_dsp_coeff_ctl *ctl) -{ - kfree(ctl->cache); - kfree(ctl->subname); - kfree(ctl); -} - static int wm_adsp_control_add(struct cs_dsp_coeff_ctl *cs_ctl) { struct wm_adsp *dsp = container_of(cs_ctl->dsp, struct wm_adsp, cs_dsp); @@ -1498,315 +682,66 @@ static void wm_adsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl) kfree(ctl); } -static int cs_dsp_create_control(struct cs_dsp *dsp, - const struct cs_dsp_alg_region *alg_region, - unsigned int offset, unsigned int len, - const char *subname, unsigned int subname_len, - unsigned int flags, unsigned int type) +int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, + unsigned int alg, void *buf, size_t len) { - struct cs_dsp_coeff_ctl *ctl; + struct cs_dsp_coeff_ctl *cs_ctl; + struct wm_coeff_ctl *ctl; + struct snd_kcontrol *kcontrol; + char ctl_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; int ret; - list_for_each_entry(ctl, &dsp->ctl_list, list) { - if (ctl->fw_name == dsp->fw_name && - ctl->alg_region.alg == alg_region->alg && - ctl->alg_region.type == alg_region->type) { - if ((!subname && !ctl->subname) || - (subname && !strncmp(ctl->subname, subname, ctl->subname_len))) { - if (!ctl->enabled) - ctl->enabled = 1; - return 0; - } - } - } - - ctl = kzalloc(sizeof(*ctl), GFP_KERNEL); - if (!ctl) - return -ENOMEM; - - ctl->fw_name = dsp->fw_name; - ctl->alg_region = *alg_region; - if (subname && dsp->fw_ver >= 2) { - ctl->subname_len = subname_len; - ctl->subname = kmemdup(subname, - strlen(subname) + 1, GFP_KERNEL); - if (!ctl->subname) { - ret = -ENOMEM; - goto err_ctl; - } - } - ctl->enabled = 1; - ctl->set = 0; - ctl->dsp = dsp; - - ctl->flags = flags; - ctl->type = type; - ctl->offset = offset; - ctl->len = len; - ctl->cache = kzalloc(ctl->len, GFP_KERNEL); - if (!ctl->cache) { - ret = -ENOMEM; - goto err_ctl_subname; - } - - list_add(&ctl->list, &dsp->ctl_list); - - if (dsp->client_ops->control_add) { - ret = dsp->client_ops->control_add(ctl); - if (ret) - goto err_list_del; - } - - return 0; - -err_list_del: - list_del(&ctl->list); - kfree(ctl->cache); -err_ctl_subname: - kfree(ctl->subname); -err_ctl: - kfree(ctl); - - return ret; -} + cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg); + if (!cs_ctl) + return -EINVAL; -struct cs_dsp_coeff_parsed_alg { - int id; - const u8 *name; - int name_len; - int ncoeff; -}; + ctl = cs_ctl->priv; -struct cs_dsp_coeff_parsed_coeff { - int offset; - int mem_type; - const u8 *name; - int name_len; - unsigned int ctl_type; - int flags; - int len; -}; + if (len > cs_ctl->len) + return -EINVAL; -static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, const u8 **str) -{ - int length; + ret = cs_dsp_coeff_write_ctrl(cs_ctl, buf, len); + if (ret) + return ret; - switch (bytes) { - case 1: - length = **pos; - break; - case 2: - length = le16_to_cpu(*((__le16 *)*pos)); - break; - default: + if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) return 0; - } - - if (str) - *str = *pos + bytes; - - *pos += ((length + bytes) + 3) & ~0x03; - - return length; -} - -static int cs_dsp_coeff_parse_int(int bytes, const u8 **pos) -{ - int val = 0; - - switch (bytes) { - case 2: - val = le16_to_cpu(*((__le16 *)*pos)); - break; - case 4: - val = le32_to_cpu(*((__le32 *)*pos)); - break; - default: - break; - } - - *pos += bytes; - - return val; -} - -static inline void cs_dsp_coeff_parse_alg(struct cs_dsp *dsp, const u8 **data, - struct cs_dsp_coeff_parsed_alg *blk) -{ - const struct wmfw_adsp_alg_data *raw; - - switch (dsp->fw_ver) { - case 0: - case 1: - raw = (const struct wmfw_adsp_alg_data *)*data; - *data = raw->data; - - blk->id = le32_to_cpu(raw->id); - blk->name = raw->name; - blk->name_len = strlen(raw->name); - blk->ncoeff = le32_to_cpu(raw->ncoeff); - break; - default: - blk->id = cs_dsp_coeff_parse_int(sizeof(raw->id), data); - blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), data, - &blk->name); - cs_dsp_coeff_parse_string(sizeof(u16), data, NULL); - blk->ncoeff = cs_dsp_coeff_parse_int(sizeof(raw->ncoeff), data); - break; - } - - cs_dsp_dbg(dsp, "Algorithm ID: %#x\n", blk->id); - cs_dsp_dbg(dsp, "Algorithm name: %.*s\n", blk->name_len, blk->name); - cs_dsp_dbg(dsp, "# of coefficient descriptors: %#x\n", blk->ncoeff); -} - -static inline void cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, const u8 **data, - struct cs_dsp_coeff_parsed_coeff *blk) -{ - const struct wmfw_adsp_coeff_data *raw; - const u8 *tmp; - int length; - - switch (dsp->fw_ver) { - case 0: - case 1: - raw = (const struct wmfw_adsp_coeff_data *)*data; - *data = *data + sizeof(raw->hdr) + le32_to_cpu(raw->hdr.size); - - blk->offset = le16_to_cpu(raw->hdr.offset); - blk->mem_type = le16_to_cpu(raw->hdr.type); - blk->name = raw->name; - blk->name_len = strlen(raw->name); - blk->ctl_type = le16_to_cpu(raw->ctl_type); - blk->flags = le16_to_cpu(raw->flags); - blk->len = le32_to_cpu(raw->len); - break; - default: - tmp = *data; - blk->offset = cs_dsp_coeff_parse_int(sizeof(raw->hdr.offset), &tmp); - blk->mem_type = cs_dsp_coeff_parse_int(sizeof(raw->hdr.type), &tmp); - length = cs_dsp_coeff_parse_int(sizeof(raw->hdr.size), &tmp); - blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, - &blk->name); - cs_dsp_coeff_parse_string(sizeof(u8), &tmp, NULL); - cs_dsp_coeff_parse_string(sizeof(u16), &tmp, NULL); - blk->ctl_type = cs_dsp_coeff_parse_int(sizeof(raw->ctl_type), &tmp); - blk->flags = cs_dsp_coeff_parse_int(sizeof(raw->flags), &tmp); - blk->len = cs_dsp_coeff_parse_int(sizeof(raw->len), &tmp); - - *data = *data + sizeof(raw->hdr) + length; - break; - } - cs_dsp_dbg(dsp, "\tCoefficient type: %#x\n", blk->mem_type); - cs_dsp_dbg(dsp, "\tCoefficient offset: %#x\n", blk->offset); - cs_dsp_dbg(dsp, "\tCoefficient name: %.*s\n", blk->name_len, blk->name); - cs_dsp_dbg(dsp, "\tCoefficient flags: %#x\n", blk->flags); - cs_dsp_dbg(dsp, "\tALSA control type: %#x\n", blk->ctl_type); - cs_dsp_dbg(dsp, "\tALSA control len: %#x\n", blk->len); -} + if (dsp->component->name_prefix) + snprintf(ctl_name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s", + dsp->component->name_prefix, ctl->name); + else + snprintf(ctl_name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", + ctl->name); -static int cs_dsp_check_coeff_flags(struct cs_dsp *dsp, - const struct cs_dsp_coeff_parsed_coeff *coeff_blk, - unsigned int f_required, - unsigned int f_illegal) -{ - if ((coeff_blk->flags & f_illegal) || - ((coeff_blk->flags & f_required) != f_required)) { - cs_dsp_err(dsp, "Illegal flags 0x%x for control type 0x%x\n", - coeff_blk->flags, coeff_blk->ctl_type); + kcontrol = snd_soc_card_get_kcontrol(dsp->component->card, ctl_name); + if (!kcontrol) { + adsp_err(dsp, "Can't find kcontrol %s\n", ctl_name); return -EINVAL; } - return 0; -} - -static int cs_dsp_parse_coeff(struct cs_dsp *dsp, - const struct wmfw_region *region) -{ - struct cs_dsp_alg_region alg_region = {}; - struct cs_dsp_coeff_parsed_alg alg_blk; - struct cs_dsp_coeff_parsed_coeff coeff_blk; - const u8 *data = region->data; - int i, ret; - - cs_dsp_coeff_parse_alg(dsp, &data, &alg_blk); - for (i = 0; i < alg_blk.ncoeff; i++) { - cs_dsp_coeff_parse_coeff(dsp, &data, &coeff_blk); - - switch (coeff_blk.ctl_type) { - case WMFW_CTL_TYPE_BYTES: - break; - case WMFW_CTL_TYPE_ACKED: - if (coeff_blk.flags & WMFW_CTL_FLAG_SYS) - continue; /* ignore */ - - ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, - WMFW_CTL_FLAG_VOLATILE | - WMFW_CTL_FLAG_WRITEABLE | - WMFW_CTL_FLAG_READABLE, - 0); - if (ret) - return -EINVAL; - break; - case WMFW_CTL_TYPE_HOSTEVENT: - ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, - WMFW_CTL_FLAG_SYS | - WMFW_CTL_FLAG_VOLATILE | - WMFW_CTL_FLAG_WRITEABLE | - WMFW_CTL_FLAG_READABLE, - 0); - if (ret) - return -EINVAL; - break; - case WMFW_CTL_TYPE_HOST_BUFFER: - ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, - WMFW_CTL_FLAG_SYS | - WMFW_CTL_FLAG_VOLATILE | - WMFW_CTL_FLAG_READABLE, - 0); - if (ret) - return -EINVAL; - break; - default: - cs_dsp_err(dsp, "Unknown control type: %d\n", - coeff_blk.ctl_type); - return -EINVAL; - } - - alg_region.type = coeff_blk.mem_type; - alg_region.alg = alg_blk.id; - - ret = cs_dsp_create_control(dsp, &alg_region, - coeff_blk.offset, - coeff_blk.len, - coeff_blk.name, - coeff_blk.name_len, - coeff_blk.flags, - coeff_blk.ctl_type); - if (ret < 0) - cs_dsp_err(dsp, "Failed to create control: %.*s, %d\n", - coeff_blk.name_len, coeff_blk.name, ret); - } + snd_ctl_notify(dsp->component->card->snd_card, + SNDRV_CTL_EVENT_MASK_VALUE, &kcontrol->id); return 0; } +EXPORT_SYMBOL_GPL(wm_adsp_write_ctl); -static unsigned int cs_dsp_adsp1_parse_sizes(struct cs_dsp *dsp, - const char * const file, - unsigned int pos, - const struct firmware *firmware) +int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name, int type, + unsigned int alg, void *buf, size_t len) { - const struct wmfw_adsp1_sizes *adsp1_sizes; + struct cs_dsp_coeff_ctl *cs_ctl; - adsp1_sizes = (void *)&firmware->data[pos]; + cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg); + if (!cs_ctl) + return -EINVAL; - cs_dsp_dbg(dsp, "%s: %d DM, %d PM, %d ZM\n", file, - le32_to_cpu(adsp1_sizes->dm), le32_to_cpu(adsp1_sizes->pm), - le32_to_cpu(adsp1_sizes->zm)); + if (len > cs_ctl->len) + return -EINVAL; - return pos + sizeof(*adsp1_sizes); + return cs_dsp_coeff_read_ctrl(cs_ctl, buf, len); } +EXPORT_SYMBOL_GPL(wm_adsp_read_ctl); static void wm_adsp_release_firmware_files(struct wm_adsp *dsp, const struct firmware *wmfw_firmware, @@ -1863,1314 +798,82 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp, return 0; } -static unsigned int cs_dsp_adsp2_parse_sizes(struct cs_dsp *dsp, - const char * const file, - unsigned int pos, - const struct firmware *firmware) +static int wm_adsp_common_init(struct wm_adsp *dsp) { - const struct wmfw_adsp2_sizes *adsp2_sizes; - - adsp2_sizes = (void *)&firmware->data[pos]; + char *p; - cs_dsp_dbg(dsp, "%s: %d XM, %d YM %d PM, %d ZM\n", file, - le32_to_cpu(adsp2_sizes->xm), le32_to_cpu(adsp2_sizes->ym), - le32_to_cpu(adsp2_sizes->pm), le32_to_cpu(adsp2_sizes->zm)); + INIT_LIST_HEAD(&dsp->compr_list); + INIT_LIST_HEAD(&dsp->buffer_list); - return pos + sizeof(*adsp2_sizes); -} + if (!dsp->fwf_name) { + p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL); + if (!p) + return -ENOMEM; -static bool cs_dsp_validate_version(struct cs_dsp *dsp, unsigned int version) -{ - switch (version) { - case 0: - cs_dsp_warn(dsp, "Deprecated file format %d\n", version); - return true; - case 1: - case 2: - return true; - default: - return false; + dsp->fwf_name = p; + for (; *p != 0; ++p) + *p = tolower(*p); } -} -static bool cs_dsp_halo_validate_version(struct cs_dsp *dsp, unsigned int version) -{ - switch (version) { - case 3: - return true; - default: - return false; - } + return 0; } -static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, - const char *file) +int wm_adsp1_init(struct wm_adsp *dsp) { - LIST_HEAD(buf_list); - struct regmap *regmap = dsp->regmap; - unsigned int pos = 0; - const struct wmfw_header *header; - const struct wmfw_adsp1_sizes *adsp1_sizes; - const struct wmfw_footer *footer; - const struct wmfw_region *region; - const struct cs_dsp_region *mem; - const char *region_name; - char *text = NULL; - struct cs_dsp_buf *buf; - unsigned int reg; - int regions = 0; - int ret, offset, type; - - ret = -EINVAL; - - pos = sizeof(*header) + sizeof(*adsp1_sizes) + sizeof(*footer); - if (pos >= firmware->size) { - cs_dsp_err(dsp, "%s: file too short, %zu bytes\n", - file, firmware->size); - goto out_fw; - } - - header = (void *)&firmware->data[0]; - - if (memcmp(&header->magic[0], "WMFW", 4) != 0) { - cs_dsp_err(dsp, "%s: invalid magic\n", file); - goto out_fw; - } - - if (!dsp->ops->validate_version(dsp, header->ver)) { - cs_dsp_err(dsp, "%s: unknown file format %d\n", - file, header->ver); - goto out_fw; - } - - cs_dsp_info(dsp, "Firmware version: %d\n", header->ver); - dsp->fw_ver = header->ver; + int ret; - if (header->core != dsp->type) { - cs_dsp_err(dsp, "%s: invalid core %d != %d\n", - file, header->core, dsp->type); - goto out_fw; - } + dsp->cs_dsp.client_ops = &wm_adsp1_client_ops; - pos = sizeof(*header); - pos = dsp->ops->parse_sizes(dsp, file, pos, firmware); + ret = cs_dsp_adsp1_init(&dsp->cs_dsp); + if (ret) + return ret; - footer = (void *)&firmware->data[pos]; - pos += sizeof(*footer); + return wm_adsp_common_init(dsp); +} +EXPORT_SYMBOL_GPL(wm_adsp1_init); - if (le32_to_cpu(header->len) != pos) { - cs_dsp_err(dsp, "%s: unexpected header length %d\n", - file, le32_to_cpu(header->len)); - goto out_fw; - } +int wm_adsp1_event(struct snd_soc_dapm_widget *w, + struct snd_kcontrol *kcontrol, + int event) +{ + struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct wm_adsp *dsps = snd_soc_component_get_drvdata(component); + struct wm_adsp *dsp = &dsps[w->shift]; + int ret = 0; + char *wmfw_filename = NULL; + const struct firmware *wmfw_firmware = NULL; + char *coeff_filename = NULL; + const struct firmware *coeff_firmware = NULL; - cs_dsp_dbg(dsp, "%s: timestamp %llu\n", file, - le64_to_cpu(footer->timestamp)); - - while (pos < firmware->size && - sizeof(*region) < firmware->size - pos) { - region = (void *)&(firmware->data[pos]); - region_name = "Unknown"; - reg = 0; - text = NULL; - offset = le32_to_cpu(region->offset) & 0xffffff; - type = be32_to_cpu(region->type) & 0xff; - - switch (type) { - case WMFW_NAME_TEXT: - region_name = "Firmware name"; - text = kzalloc(le32_to_cpu(region->len) + 1, - GFP_KERNEL); - break; - case WMFW_ALGORITHM_DATA: - region_name = "Algorithm"; - ret = cs_dsp_parse_coeff(dsp, region); - if (ret != 0) - goto out_fw; - break; - case WMFW_INFO_TEXT: - region_name = "Information"; - text = kzalloc(le32_to_cpu(region->len) + 1, - GFP_KERNEL); - break; - case WMFW_ABSOLUTE: - region_name = "Absolute"; - reg = offset; - break; - case WMFW_ADSP1_PM: - case WMFW_ADSP1_DM: - case WMFW_ADSP2_XM: - case WMFW_ADSP2_YM: - case WMFW_ADSP1_ZM: - case WMFW_HALO_PM_PACKED: - case WMFW_HALO_XM_PACKED: - case WMFW_HALO_YM_PACKED: - mem = cs_dsp_find_region(dsp, type); - if (!mem) { - cs_dsp_err(dsp, "No region of type: %x\n", type); - ret = -EINVAL; - goto out_fw; - } - - region_name = cs_dsp_mem_region_name(type); - reg = dsp->ops->region_to_reg(mem, offset); - break; - default: - cs_dsp_warn(dsp, - "%s.%d: Unknown region type %x at %d(%x)\n", - file, regions, type, pos, pos); - break; - } - - cs_dsp_dbg(dsp, "%s.%d: %d bytes at %d in %s\n", file, - regions, le32_to_cpu(region->len), offset, - region_name); - - if (le32_to_cpu(region->len) > - firmware->size - pos - sizeof(*region)) { - cs_dsp_err(dsp, - "%s.%d: %s region len %d bytes exceeds file length %zu\n", - file, regions, region_name, - le32_to_cpu(region->len), firmware->size); - ret = -EINVAL; - goto out_fw; - } - - if (text) { - memcpy(text, region->data, le32_to_cpu(region->len)); - cs_dsp_info(dsp, "%s: %s\n", file, text); - kfree(text); - text = NULL; - } - - if (reg) { - buf = cs_dsp_buf_alloc(region->data, - le32_to_cpu(region->len), - &buf_list); - if (!buf) { - cs_dsp_err(dsp, "Out of memory\n"); - ret = -ENOMEM; - goto out_fw; - } - - ret = regmap_raw_write_async(regmap, reg, buf->buf, - le32_to_cpu(region->len)); - if (ret != 0) { - cs_dsp_err(dsp, - "%s.%d: Failed to write %d bytes at %d in %s: %d\n", - file, regions, - le32_to_cpu(region->len), offset, - region_name, ret); - goto out_fw; - } - } - - pos += le32_to_cpu(region->len) + sizeof(*region); - regions++; - } - - ret = regmap_async_complete(regmap); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret); - goto out_fw; - } - - if (pos > firmware->size) - cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n", - file, regions, pos - firmware->size); - - cs_dsp_debugfs_save_wmfwname(dsp, file); - -out_fw: - regmap_async_complete(regmap); - cs_dsp_buf_free(&buf_list); - kfree(text); - - return ret; -} - -/* - * Find cs_dsp_coeff_ctl with input name as its subname - * If not found, return NULL - */ -static struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, - const char *name, int type, - unsigned int alg) -{ - struct cs_dsp_coeff_ctl *pos, *rslt = NULL; - - list_for_each_entry(pos, &dsp->ctl_list, list) { - if (!pos->subname) - continue; - if (strncmp(pos->subname, name, pos->subname_len) == 0 && - pos->fw_name == dsp->fw_name && - pos->alg_region.alg == alg && - pos->alg_region.type == type) { - rslt = pos; - break; - } - } - - return rslt; -} - -int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, - unsigned int alg, void *buf, size_t len) -{ - struct cs_dsp_coeff_ctl *cs_ctl; - struct wm_coeff_ctl *ctl; - struct snd_kcontrol *kcontrol; - char ctl_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - int ret; - - cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; - - ctl = cs_ctl->priv; - - if (len > cs_ctl->len) - return -EINVAL; - - ret = cs_dsp_coeff_write_ctrl(cs_ctl, buf, len); - if (ret) - return ret; - - if (cs_ctl->flags & WMFW_CTL_FLAG_SYS) - return 0; - - if (dsp->component->name_prefix) - snprintf(ctl_name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s", - dsp->component->name_prefix, ctl->name); - else - snprintf(ctl_name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s", - ctl->name); - - kcontrol = snd_soc_card_get_kcontrol(dsp->component->card, ctl_name); - if (!kcontrol) { - adsp_err(dsp, "Can't find kcontrol %s\n", ctl_name); - return -EINVAL; - } - - snd_ctl_notify(dsp->component->card->snd_card, - SNDRV_CTL_EVENT_MASK_VALUE, &kcontrol->id); - - return 0; -} -EXPORT_SYMBOL_GPL(wm_adsp_write_ctl); - -int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name, int type, - unsigned int alg, void *buf, size_t len) -{ - struct cs_dsp_coeff_ctl *cs_ctl; - - cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg); - if (!cs_ctl) - return -EINVAL; - - if (len > cs_ctl->len) - return -EINVAL; - - return cs_dsp_coeff_read_ctrl(cs_ctl, buf, len); -} -EXPORT_SYMBOL_GPL(wm_adsp_read_ctl); - -static void cs_dsp_ctl_fixup_base(struct cs_dsp *dsp, - const struct cs_dsp_alg_region *alg_region) -{ - struct cs_dsp_coeff_ctl *ctl; - - list_for_each_entry(ctl, &dsp->ctl_list, list) { - if (ctl->fw_name == dsp->fw_name && - alg_region->alg == ctl->alg_region.alg && - alg_region->type == ctl->alg_region.type) { - ctl->alg_region.base = alg_region->base; - } - } -} - -static void *cs_dsp_read_algs(struct cs_dsp *dsp, size_t n_algs, - const struct cs_dsp_region *mem, - unsigned int pos, unsigned int len) -{ - void *alg; - unsigned int reg; - int ret; - __be32 val; - - if (n_algs == 0) { - cs_dsp_err(dsp, "No algorithms\n"); - return ERR_PTR(-EINVAL); - } - - if (n_algs > 1024) { - cs_dsp_err(dsp, "Algorithm count %zx excessive\n", n_algs); - return ERR_PTR(-EINVAL); - } - - /* Read the terminator first to validate the length */ - reg = dsp->ops->region_to_reg(mem, pos + len); - - ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val)); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to read algorithm list end: %d\n", - ret); - return ERR_PTR(ret); - } - - if (be32_to_cpu(val) != 0xbedead) - cs_dsp_warn(dsp, "Algorithm list end %x 0x%x != 0xbedead\n", - reg, be32_to_cpu(val)); - - /* Convert length from DSP words to bytes */ - len *= sizeof(u32); - - alg = kzalloc(len, GFP_KERNEL | GFP_DMA); - if (!alg) - return ERR_PTR(-ENOMEM); - - reg = dsp->ops->region_to_reg(mem, pos); - - ret = regmap_raw_read(dsp->regmap, reg, alg, len); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to read algorithm list: %d\n", ret); - kfree(alg); - return ERR_PTR(ret); - } - - return alg; -} - -static struct cs_dsp_alg_region * - cs_dsp_find_alg_region(struct cs_dsp *dsp, int type, unsigned int id) -{ - struct cs_dsp_alg_region *alg_region; - - list_for_each_entry(alg_region, &dsp->alg_regions, list) { - if (id == alg_region->alg && type == alg_region->type) - return alg_region; - } - - return NULL; -} - -static struct cs_dsp_alg_region *cs_dsp_create_region(struct cs_dsp *dsp, - int type, __be32 id, - __be32 base) -{ - struct cs_dsp_alg_region *alg_region; - - alg_region = kzalloc(sizeof(*alg_region), GFP_KERNEL); - if (!alg_region) - return ERR_PTR(-ENOMEM); - - alg_region->type = type; - alg_region->alg = be32_to_cpu(id); - alg_region->base = be32_to_cpu(base); - - list_add_tail(&alg_region->list, &dsp->alg_regions); - - if (dsp->fw_ver > 0) - cs_dsp_ctl_fixup_base(dsp, alg_region); - - return alg_region; -} - -static void cs_dsp_free_alg_regions(struct cs_dsp *dsp) -{ - struct cs_dsp_alg_region *alg_region; - - while (!list_empty(&dsp->alg_regions)) { - alg_region = list_first_entry(&dsp->alg_regions, - struct cs_dsp_alg_region, - list); - list_del(&alg_region->list); - kfree(alg_region); - } -} - -static void cs_dsp_parse_wmfw_id_header(struct cs_dsp *dsp, - struct wmfw_id_hdr *fw, int nalgs) -{ - dsp->fw_id = be32_to_cpu(fw->id); - dsp->fw_id_version = be32_to_cpu(fw->ver); - - cs_dsp_info(dsp, "Firmware: %x v%d.%d.%d, %d algorithms\n", - dsp->fw_id, (dsp->fw_id_version & 0xff0000) >> 16, - (dsp->fw_id_version & 0xff00) >> 8, dsp->fw_id_version & 0xff, - nalgs); -} - -static void cs_dsp_parse_wmfw_v3_id_header(struct cs_dsp *dsp, - struct wmfw_v3_id_hdr *fw, int nalgs) -{ - dsp->fw_id = be32_to_cpu(fw->id); - dsp->fw_id_version = be32_to_cpu(fw->ver); - dsp->fw_vendor_id = be32_to_cpu(fw->vendor_id); - - cs_dsp_info(dsp, "Firmware: %x vendor: 0x%x v%d.%d.%d, %d algorithms\n", - dsp->fw_id, dsp->fw_vendor_id, - (dsp->fw_id_version & 0xff0000) >> 16, - (dsp->fw_id_version & 0xff00) >> 8, dsp->fw_id_version & 0xff, - nalgs); -} - -static int cs_dsp_create_regions(struct cs_dsp *dsp, __be32 id, int nregions, - const int *type, __be32 *base) -{ - struct cs_dsp_alg_region *alg_region; - int i; - - for (i = 0; i < nregions; i++) { - alg_region = cs_dsp_create_region(dsp, type[i], id, base[i]); - if (IS_ERR(alg_region)) - return PTR_ERR(alg_region); - } - - return 0; -} - -static int cs_dsp_adsp1_setup_algs(struct cs_dsp *dsp) -{ - struct wmfw_adsp1_id_hdr adsp1_id; - struct wmfw_adsp1_alg_hdr *adsp1_alg; - struct cs_dsp_alg_region *alg_region; - const struct cs_dsp_region *mem; - unsigned int pos, len; - size_t n_algs; - int i, ret; - - mem = cs_dsp_find_region(dsp, WMFW_ADSP1_DM); - if (WARN_ON(!mem)) - return -EINVAL; - - ret = regmap_raw_read(dsp->regmap, mem->base, &adsp1_id, - sizeof(adsp1_id)); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to read algorithm info: %d\n", - ret); - return ret; - } - - n_algs = be32_to_cpu(adsp1_id.n_algs); - - cs_dsp_parse_wmfw_id_header(dsp, &adsp1_id.fw, n_algs); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_ZM, - adsp1_id.fw.id, adsp1_id.zm); - if (IS_ERR(alg_region)) - return PTR_ERR(alg_region); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_DM, - adsp1_id.fw.id, adsp1_id.dm); - if (IS_ERR(alg_region)) - return PTR_ERR(alg_region); - - /* Calculate offset and length in DSP words */ - pos = sizeof(adsp1_id) / sizeof(u32); - len = (sizeof(*adsp1_alg) * n_algs) / sizeof(u32); - - adsp1_alg = cs_dsp_read_algs(dsp, n_algs, mem, pos, len); - if (IS_ERR(adsp1_alg)) - return PTR_ERR(adsp1_alg); - - for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, "%d: ID %x v%d.%d.%d DM@%x ZM@%x\n", - i, be32_to_cpu(adsp1_alg[i].alg.id), - (be32_to_cpu(adsp1_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(adsp1_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(adsp1_alg[i].alg.ver) & 0xff, - be32_to_cpu(adsp1_alg[i].dm), - be32_to_cpu(adsp1_alg[i].zm)); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_DM, - adsp1_alg[i].alg.id, - adsp1_alg[i].dm); - if (IS_ERR(alg_region)) { - ret = PTR_ERR(alg_region); - goto out; - } - if (dsp->fw_ver == 0) { - if (i + 1 < n_algs) { - len = be32_to_cpu(adsp1_alg[i + 1].dm); - len -= be32_to_cpu(adsp1_alg[i].dm); - len *= 4; - cs_dsp_create_control(dsp, alg_region, 0, - len, NULL, 0, 0, - WMFW_CTL_TYPE_BYTES); - } else { - cs_dsp_warn(dsp, "Missing length info for region DM with ID %x\n", - be32_to_cpu(adsp1_alg[i].alg.id)); - } - } - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_ZM, - adsp1_alg[i].alg.id, - adsp1_alg[i].zm); - if (IS_ERR(alg_region)) { - ret = PTR_ERR(alg_region); - goto out; - } - if (dsp->fw_ver == 0) { - if (i + 1 < n_algs) { - len = be32_to_cpu(adsp1_alg[i + 1].zm); - len -= be32_to_cpu(adsp1_alg[i].zm); - len *= 4; - cs_dsp_create_control(dsp, alg_region, 0, - len, NULL, 0, 0, - WMFW_CTL_TYPE_BYTES); - } else { - cs_dsp_warn(dsp, "Missing length info for region ZM with ID %x\n", - be32_to_cpu(adsp1_alg[i].alg.id)); - } - } - } - -out: - kfree(adsp1_alg); - return ret; -} - -static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) -{ - struct wmfw_adsp2_id_hdr adsp2_id; - struct wmfw_adsp2_alg_hdr *adsp2_alg; - struct cs_dsp_alg_region *alg_region; - const struct cs_dsp_region *mem; - unsigned int pos, len; - size_t n_algs; - int i, ret; - - mem = cs_dsp_find_region(dsp, WMFW_ADSP2_XM); - if (WARN_ON(!mem)) - return -EINVAL; - - ret = regmap_raw_read(dsp->regmap, mem->base, &adsp2_id, - sizeof(adsp2_id)); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to read algorithm info: %d\n", - ret); - return ret; - } - - n_algs = be32_to_cpu(adsp2_id.n_algs); - - cs_dsp_parse_wmfw_id_header(dsp, &adsp2_id.fw, n_algs); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, - adsp2_id.fw.id, adsp2_id.xm); - if (IS_ERR(alg_region)) - return PTR_ERR(alg_region); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_YM, - adsp2_id.fw.id, adsp2_id.ym); - if (IS_ERR(alg_region)) - return PTR_ERR(alg_region); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_ZM, - adsp2_id.fw.id, adsp2_id.zm); - if (IS_ERR(alg_region)) - return PTR_ERR(alg_region); - - /* Calculate offset and length in DSP words */ - pos = sizeof(adsp2_id) / sizeof(u32); - len = (sizeof(*adsp2_alg) * n_algs) / sizeof(u32); - - adsp2_alg = cs_dsp_read_algs(dsp, n_algs, mem, pos, len); - if (IS_ERR(adsp2_alg)) - return PTR_ERR(adsp2_alg); - - for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, - "%d: ID %x v%d.%d.%d XM@%x YM@%x ZM@%x\n", - i, be32_to_cpu(adsp2_alg[i].alg.id), - (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(adsp2_alg[i].alg.ver) & 0xff, - be32_to_cpu(adsp2_alg[i].xm), - be32_to_cpu(adsp2_alg[i].ym), - be32_to_cpu(adsp2_alg[i].zm)); - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, - adsp2_alg[i].alg.id, - adsp2_alg[i].xm); - if (IS_ERR(alg_region)) { - ret = PTR_ERR(alg_region); - goto out; - } - if (dsp->fw_ver == 0) { - if (i + 1 < n_algs) { - len = be32_to_cpu(adsp2_alg[i + 1].xm); - len -= be32_to_cpu(adsp2_alg[i].xm); - len *= 4; - cs_dsp_create_control(dsp, alg_region, 0, - len, NULL, 0, 0, - WMFW_CTL_TYPE_BYTES); - } else { - cs_dsp_warn(dsp, "Missing length info for region XM with ID %x\n", - be32_to_cpu(adsp2_alg[i].alg.id)); - } - } - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_YM, - adsp2_alg[i].alg.id, - adsp2_alg[i].ym); - if (IS_ERR(alg_region)) { - ret = PTR_ERR(alg_region); - goto out; - } - if (dsp->fw_ver == 0) { - if (i + 1 < n_algs) { - len = be32_to_cpu(adsp2_alg[i + 1].ym); - len -= be32_to_cpu(adsp2_alg[i].ym); - len *= 4; - cs_dsp_create_control(dsp, alg_region, 0, - len, NULL, 0, 0, - WMFW_CTL_TYPE_BYTES); - } else { - cs_dsp_warn(dsp, "Missing length info for region YM with ID %x\n", - be32_to_cpu(adsp2_alg[i].alg.id)); - } - } - - alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_ZM, - adsp2_alg[i].alg.id, - adsp2_alg[i].zm); - if (IS_ERR(alg_region)) { - ret = PTR_ERR(alg_region); - goto out; - } - if (dsp->fw_ver == 0) { - if (i + 1 < n_algs) { - len = be32_to_cpu(adsp2_alg[i + 1].zm); - len -= be32_to_cpu(adsp2_alg[i].zm); - len *= 4; - cs_dsp_create_control(dsp, alg_region, 0, - len, NULL, 0, 0, - WMFW_CTL_TYPE_BYTES); - } else { - cs_dsp_warn(dsp, "Missing length info for region ZM with ID %x\n", - be32_to_cpu(adsp2_alg[i].alg.id)); - } - } - } - -out: - kfree(adsp2_alg); - return ret; -} - -static int cs_dsp_halo_create_regions(struct cs_dsp *dsp, __be32 id, - __be32 xm_base, __be32 ym_base) -{ - static const int types[] = { - WMFW_ADSP2_XM, WMFW_HALO_XM_PACKED, - WMFW_ADSP2_YM, WMFW_HALO_YM_PACKED - }; - __be32 bases[] = { xm_base, xm_base, ym_base, ym_base }; - - return cs_dsp_create_regions(dsp, id, ARRAY_SIZE(types), types, bases); -} - -static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) -{ - struct wmfw_halo_id_hdr halo_id; - struct wmfw_halo_alg_hdr *halo_alg; - const struct cs_dsp_region *mem; - unsigned int pos, len; - size_t n_algs; - int i, ret; - - mem = cs_dsp_find_region(dsp, WMFW_ADSP2_XM); - if (WARN_ON(!mem)) - return -EINVAL; - - ret = regmap_raw_read(dsp->regmap, mem->base, &halo_id, - sizeof(halo_id)); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to read algorithm info: %d\n", - ret); - return ret; - } - - n_algs = be32_to_cpu(halo_id.n_algs); - - cs_dsp_parse_wmfw_v3_id_header(dsp, &halo_id.fw, n_algs); - - ret = cs_dsp_halo_create_regions(dsp, halo_id.fw.id, - halo_id.xm_base, halo_id.ym_base); - if (ret) - return ret; - - /* Calculate offset and length in DSP words */ - pos = sizeof(halo_id) / sizeof(u32); - len = (sizeof(*halo_alg) * n_algs) / sizeof(u32); - - halo_alg = cs_dsp_read_algs(dsp, n_algs, mem, pos, len); - if (IS_ERR(halo_alg)) - return PTR_ERR(halo_alg); - - for (i = 0; i < n_algs; i++) { - cs_dsp_info(dsp, - "%d: ID %x v%d.%d.%d XM@%x YM@%x\n", - i, be32_to_cpu(halo_alg[i].alg.id), - (be32_to_cpu(halo_alg[i].alg.ver) & 0xff0000) >> 16, - (be32_to_cpu(halo_alg[i].alg.ver) & 0xff00) >> 8, - be32_to_cpu(halo_alg[i].alg.ver) & 0xff, - be32_to_cpu(halo_alg[i].xm_base), - be32_to_cpu(halo_alg[i].ym_base)); - - ret = cs_dsp_halo_create_regions(dsp, halo_alg[i].alg.id, - halo_alg[i].xm_base, - halo_alg[i].ym_base); - if (ret) - goto out; - } - -out: - kfree(halo_alg); - return ret; -} - -static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware, - const char *file) -{ - LIST_HEAD(buf_list); - struct regmap *regmap = dsp->regmap; - struct wmfw_coeff_hdr *hdr; - struct wmfw_coeff_item *blk; - const struct cs_dsp_region *mem; - struct cs_dsp_alg_region *alg_region; - const char *region_name; - int ret, pos, blocks, type, offset, reg; - struct cs_dsp_buf *buf; - - if (!firmware) - return 0; - - ret = -EINVAL; - - if (sizeof(*hdr) >= firmware->size) { - cs_dsp_err(dsp, "%s: coefficient file too short, %zu bytes\n", - file, firmware->size); - goto out_fw; - } - - hdr = (void *)&firmware->data[0]; - if (memcmp(hdr->magic, "WMDR", 4) != 0) { - cs_dsp_err(dsp, "%s: invalid coefficient magic\n", file); - goto out_fw; - } - - switch (be32_to_cpu(hdr->rev) & 0xff) { - case 1: - break; - default: - cs_dsp_err(dsp, "%s: Unsupported coefficient file format %d\n", - file, be32_to_cpu(hdr->rev) & 0xff); - ret = -EINVAL; - goto out_fw; - } - - cs_dsp_dbg(dsp, "%s: v%d.%d.%d\n", file, - (le32_to_cpu(hdr->ver) >> 16) & 0xff, - (le32_to_cpu(hdr->ver) >> 8) & 0xff, - le32_to_cpu(hdr->ver) & 0xff); - - pos = le32_to_cpu(hdr->len); - - blocks = 0; - while (pos < firmware->size && - sizeof(*blk) < firmware->size - pos) { - blk = (void *)(&firmware->data[pos]); - - type = le16_to_cpu(blk->type); - offset = le16_to_cpu(blk->offset); - - cs_dsp_dbg(dsp, "%s.%d: %x v%d.%d.%d\n", - file, blocks, le32_to_cpu(blk->id), - (le32_to_cpu(blk->ver) >> 16) & 0xff, - (le32_to_cpu(blk->ver) >> 8) & 0xff, - le32_to_cpu(blk->ver) & 0xff); - cs_dsp_dbg(dsp, "%s.%d: %d bytes at 0x%x in %x\n", - file, blocks, le32_to_cpu(blk->len), offset, type); - - reg = 0; - region_name = "Unknown"; - switch (type) { - case (WMFW_NAME_TEXT << 8): - case (WMFW_INFO_TEXT << 8): - case (WMFW_METADATA << 8): - break; - case (WMFW_ABSOLUTE << 8): - /* - * Old files may use this for global - * coefficients. - */ - if (le32_to_cpu(blk->id) == dsp->fw_id && - offset == 0) { - region_name = "global coefficients"; - mem = cs_dsp_find_region(dsp, type); - if (!mem) { - cs_dsp_err(dsp, "No ZM\n"); - break; - } - reg = dsp->ops->region_to_reg(mem, 0); - - } else { - region_name = "register"; - reg = offset; - } - break; - - case WMFW_ADSP1_DM: - case WMFW_ADSP1_ZM: - case WMFW_ADSP2_XM: - case WMFW_ADSP2_YM: - case WMFW_HALO_XM_PACKED: - case WMFW_HALO_YM_PACKED: - case WMFW_HALO_PM_PACKED: - cs_dsp_dbg(dsp, "%s.%d: %d bytes in %x for %x\n", - file, blocks, le32_to_cpu(blk->len), - type, le32_to_cpu(blk->id)); - - mem = cs_dsp_find_region(dsp, type); - if (!mem) { - cs_dsp_err(dsp, "No base for region %x\n", type); - break; - } - - alg_region = cs_dsp_find_alg_region(dsp, type, - le32_to_cpu(blk->id)); - if (alg_region) { - reg = alg_region->base; - reg = dsp->ops->region_to_reg(mem, reg); - reg += offset; - } else { - cs_dsp_err(dsp, "No %x for algorithm %x\n", - type, le32_to_cpu(blk->id)); - } - break; - - default: - cs_dsp_err(dsp, "%s.%d: Unknown region type %x at %d\n", - file, blocks, type, pos); - break; - } - - if (reg) { - if (le32_to_cpu(blk->len) > - firmware->size - pos - sizeof(*blk)) { - cs_dsp_err(dsp, - "%s.%d: %s region len %d bytes exceeds file length %zu\n", - file, blocks, region_name, - le32_to_cpu(blk->len), - firmware->size); - ret = -EINVAL; - goto out_fw; - } - - buf = cs_dsp_buf_alloc(blk->data, - le32_to_cpu(blk->len), - &buf_list); - if (!buf) { - cs_dsp_err(dsp, "Out of memory\n"); - ret = -ENOMEM; - goto out_fw; - } - - cs_dsp_dbg(dsp, "%s.%d: Writing %d bytes at %x\n", - file, blocks, le32_to_cpu(blk->len), - reg); - ret = regmap_raw_write_async(regmap, reg, buf->buf, - le32_to_cpu(blk->len)); - if (ret != 0) { - cs_dsp_err(dsp, - "%s.%d: Failed to write to %x in %s: %d\n", - file, blocks, reg, region_name, ret); - } - } - - pos += (le32_to_cpu(blk->len) + sizeof(*blk) + 3) & ~0x03; - blocks++; - } - - ret = regmap_async_complete(regmap); - if (ret != 0) - cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret); - - if (pos > firmware->size) - cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n", - file, blocks, pos - firmware->size); - - cs_dsp_debugfs_save_binname(dsp, file); - -out_fw: - regmap_async_complete(regmap); - cs_dsp_buf_free(&buf_list); - return ret; -} - -static int cs_dsp_create_name(struct cs_dsp *dsp) -{ - if (!dsp->name) { - dsp->name = devm_kasprintf(dsp->dev, GFP_KERNEL, "DSP%d", - dsp->num); - if (!dsp->name) - return -ENOMEM; - } - - return 0; -} - -static int cs_dsp_common_init(struct cs_dsp *dsp) -{ - int ret; - - ret = cs_dsp_create_name(dsp); - if (ret) - return ret; - - INIT_LIST_HEAD(&dsp->alg_regions); - INIT_LIST_HEAD(&dsp->ctl_list); - - mutex_init(&dsp->pwr_lock); - - return 0; -} - -static int wm_adsp_common_init(struct wm_adsp *dsp) -{ - char *p; - - INIT_LIST_HEAD(&dsp->compr_list); - INIT_LIST_HEAD(&dsp->buffer_list); - - if (!dsp->fwf_name) { - p = devm_kstrdup(dsp->cs_dsp.dev, dsp->cs_dsp.name, GFP_KERNEL); - if (!p) - return -ENOMEM; - - dsp->fwf_name = p; - for (; *p != 0; ++p) - *p = tolower(*p); - } - - return 0; -} - -static int cs_dsp_adsp1_init(struct cs_dsp *dsp) -{ - dsp->ops = &cs_dsp_adsp1_ops; - - return cs_dsp_common_init(dsp); -} - -int wm_adsp1_init(struct wm_adsp *dsp) -{ - int ret; - - dsp->cs_dsp.client_ops = &wm_adsp1_client_ops; - - ret = cs_dsp_adsp1_init(&dsp->cs_dsp); - if (ret) - return ret; - - return wm_adsp_common_init(dsp); -} -EXPORT_SYMBOL_GPL(wm_adsp1_init); - -static int cs_dsp_adsp1_power_up(struct cs_dsp *dsp, - const struct firmware *wmfw_firmware, char *wmfw_filename, - const struct firmware *coeff_firmware, char *coeff_filename, - const char *fw_name) -{ - unsigned int val; - int ret; - - mutex_lock(&dsp->pwr_lock); - - dsp->fw_name = fw_name; - - regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, - ADSP1_SYS_ENA, ADSP1_SYS_ENA); - - /* - * For simplicity set the DSP clock rate to be the - * SYSCLK rate rather than making it configurable. - */ - if (dsp->sysclk_reg) { - ret = regmap_read(dsp->regmap, dsp->sysclk_reg, &val); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to read SYSCLK state: %d\n", ret); - goto err_mutex; - } - - val = (val & dsp->sysclk_mask) >> dsp->sysclk_shift; - - ret = regmap_update_bits(dsp->regmap, - dsp->base + ADSP1_CONTROL_31, - ADSP1_CLK_SEL_MASK, val); - if (ret != 0) { - cs_dsp_err(dsp, "Failed to set clock rate: %d\n", ret); - goto err_mutex; - } - } - - ret = cs_dsp_load(dsp, wmfw_firmware, wmfw_filename); - if (ret != 0) - goto err_ena; - - ret = cs_dsp_adsp1_setup_algs(dsp); - if (ret != 0) - goto err_ena; - - ret = cs_dsp_load_coeff(dsp, coeff_firmware, coeff_filename); - if (ret != 0) - goto err_ena; - - /* Initialize caches for enabled and unset controls */ - ret = cs_dsp_coeff_init_control_caches(dsp); - if (ret != 0) - goto err_ena; - - /* Sync set controls */ - ret = cs_dsp_coeff_sync_controls(dsp); - if (ret != 0) - goto err_ena; - - dsp->booted = true; - - /* Start the core running */ - regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, - ADSP1_CORE_ENA | ADSP1_START, - ADSP1_CORE_ENA | ADSP1_START); - - dsp->running = true; - - mutex_unlock(&dsp->pwr_lock); - - return 0; - -err_ena: - regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, - ADSP1_SYS_ENA, 0); -err_mutex: - mutex_unlock(&dsp->pwr_lock); - return ret; -} - -static void cs_dsp_adsp1_power_down(struct cs_dsp *dsp) -{ - struct cs_dsp_coeff_ctl *ctl; - - mutex_lock(&dsp->pwr_lock); - - dsp->running = false; - dsp->booted = false; - - /* Halt the core */ - regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, - ADSP1_CORE_ENA | ADSP1_START, 0); - - regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_19, - ADSP1_WDMA_BUFFER_LENGTH_MASK, 0); - - regmap_update_bits(dsp->regmap, dsp->base + ADSP1_CONTROL_30, - ADSP1_SYS_ENA, 0); - - list_for_each_entry(ctl, &dsp->ctl_list, list) - ctl->enabled = 0; - - cs_dsp_free_alg_regions(dsp); - - mutex_unlock(&dsp->pwr_lock); -} - -int wm_adsp1_event(struct snd_soc_dapm_widget *w, - struct snd_kcontrol *kcontrol, - int event) -{ - struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); - struct wm_adsp *dsps = snd_soc_component_get_drvdata(component); - struct wm_adsp *dsp = &dsps[w->shift]; - int ret = 0; - char *wmfw_filename = NULL; - const struct firmware *wmfw_firmware = NULL; - char *coeff_filename = NULL; - const struct firmware *coeff_firmware = NULL; - - dsp->component = component; + dsp->component = component; switch (event) { case SND_SOC_DAPM_POST_PMU: ret = wm_adsp_request_firmware_files(dsp, &wmfw_firmware, &wmfw_filename, &coeff_firmware, &coeff_filename); - if (ret) - break; - - ret = cs_dsp_adsp1_power_up(&dsp->cs_dsp, - wmfw_firmware, wmfw_filename, - coeff_firmware, coeff_filename, - wm_adsp_fw_text[dsp->fw]); - - wm_adsp_release_firmware_files(dsp, - wmfw_firmware, wmfw_filename, - coeff_firmware, coeff_filename); - break; - case SND_SOC_DAPM_PRE_PMD: - cs_dsp_adsp1_power_down(&dsp->cs_dsp); - break; - default: - break; - } - - return ret; -} -EXPORT_SYMBOL_GPL(wm_adsp1_event); - -static int cs_dsp_adsp2v2_enable_core(struct cs_dsp *dsp) -{ - unsigned int val; - int ret, count; - - /* Wait for the RAM to start, should be near instantaneous */ - for (count = 0; count < 10; ++count) { - ret = regmap_read(dsp->regmap, dsp->base + ADSP2_STATUS1, &val); - if (ret != 0) - return ret; - - if (val & ADSP2_RAM_RDY) - break; - - usleep_range(250, 500); - } - - if (!(val & ADSP2_RAM_RDY)) { - cs_dsp_err(dsp, "Failed to start DSP RAM\n"); - return -EBUSY; - } - - cs_dsp_dbg(dsp, "RAM ready after %d polls\n", count); - - return 0; -} - -static int cs_dsp_adsp2_enable_core(struct cs_dsp *dsp) -{ - int ret; - - ret = regmap_update_bits_async(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_SYS_ENA, ADSP2_SYS_ENA); - if (ret != 0) - return ret; - - return cs_dsp_adsp2v2_enable_core(dsp); -} - -static int cs_dsp_adsp2_lock(struct cs_dsp *dsp, unsigned int lock_regions) -{ - struct regmap *regmap = dsp->regmap; - unsigned int code0, code1, lock_reg; - - if (!(lock_regions & CS_ADSP2_REGION_ALL)) - return 0; - - lock_regions &= CS_ADSP2_REGION_ALL; - lock_reg = dsp->base + ADSP2_LOCK_REGION_1_LOCK_REGION_0; - - while (lock_regions) { - code0 = code1 = 0; - if (lock_regions & BIT(0)) { - code0 = ADSP2_LOCK_CODE_0; - code1 = ADSP2_LOCK_CODE_1; - } - if (lock_regions & BIT(1)) { - code0 |= ADSP2_LOCK_CODE_0 << ADSP2_LOCK_REGION_SHIFT; - code1 |= ADSP2_LOCK_CODE_1 << ADSP2_LOCK_REGION_SHIFT; - } - regmap_write(regmap, lock_reg, code0); - regmap_write(regmap, lock_reg, code1); - lock_regions >>= 2; - lock_reg += 2; - } - - return 0; -} - -static int cs_dsp_adsp2_enable_memory(struct cs_dsp *dsp) -{ - return regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_MEM_ENA, ADSP2_MEM_ENA); -} - -static void cs_dsp_adsp2_disable_memory(struct cs_dsp *dsp) -{ - regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_MEM_ENA, 0); -} - -static void cs_dsp_adsp2_disable_core(struct cs_dsp *dsp) -{ - regmap_write(dsp->regmap, dsp->base + ADSP2_RDMA_CONFIG_1, 0); - regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_1, 0); - regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_2, 0); - - regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_SYS_ENA, 0); -} - -static void cs_dsp_adsp2v2_disable_core(struct cs_dsp *dsp) -{ - regmap_write(dsp->regmap, dsp->base + ADSP2_RDMA_CONFIG_1, 0); - regmap_write(dsp->regmap, dsp->base + ADSP2_WDMA_CONFIG_1, 0); - regmap_write(dsp->regmap, dsp->base + ADSP2V2_WDMA_CONFIG_2, 0); -} - -static int cs_dsp_halo_configure_mpu(struct cs_dsp *dsp, unsigned int lock_regions) -{ - struct reg_sequence config[] = { - { dsp->base + HALO_MPU_LOCK_CONFIG, 0x5555 }, - { dsp->base + HALO_MPU_LOCK_CONFIG, 0xAAAA }, - { dsp->base + HALO_MPU_XMEM_ACCESS_0, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_YMEM_ACCESS_0, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_WINDOW_ACCESS_0, lock_regions }, - { dsp->base + HALO_MPU_XREG_ACCESS_0, lock_regions }, - { dsp->base + HALO_MPU_YREG_ACCESS_0, lock_regions }, - { dsp->base + HALO_MPU_XMEM_ACCESS_1, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_YMEM_ACCESS_1, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_WINDOW_ACCESS_1, lock_regions }, - { dsp->base + HALO_MPU_XREG_ACCESS_1, lock_regions }, - { dsp->base + HALO_MPU_YREG_ACCESS_1, lock_regions }, - { dsp->base + HALO_MPU_XMEM_ACCESS_2, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_YMEM_ACCESS_2, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_WINDOW_ACCESS_2, lock_regions }, - { dsp->base + HALO_MPU_XREG_ACCESS_2, lock_regions }, - { dsp->base + HALO_MPU_YREG_ACCESS_2, lock_regions }, - { dsp->base + HALO_MPU_XMEM_ACCESS_3, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_YMEM_ACCESS_3, 0xFFFFFFFF }, - { dsp->base + HALO_MPU_WINDOW_ACCESS_3, lock_regions }, - { dsp->base + HALO_MPU_XREG_ACCESS_3, lock_regions }, - { dsp->base + HALO_MPU_YREG_ACCESS_3, lock_regions }, - { dsp->base + HALO_MPU_LOCK_CONFIG, 0 }, - }; - - return regmap_multi_reg_write(dsp->regmap, config, ARRAY_SIZE(config)); -} + if (ret) + break; -static int cs_dsp_set_dspclk(struct cs_dsp *dsp, unsigned int freq) -{ - int ret; + ret = cs_dsp_adsp1_power_up(&dsp->cs_dsp, + wmfw_firmware, wmfw_filename, + coeff_firmware, coeff_filename, + wm_adsp_fw_text[dsp->fw]); - ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CLOCKING, - ADSP2_CLK_SEL_MASK, - freq << ADSP2_CLK_SEL_SHIFT); - if (ret) - cs_dsp_err(dsp, "Failed to set clock rate: %d\n", ret); + wm_adsp_release_firmware_files(dsp, + wmfw_firmware, wmfw_filename, + coeff_firmware, coeff_filename); + break; + case SND_SOC_DAPM_PRE_PMD: + cs_dsp_adsp1_power_down(&dsp->cs_dsp); + break; + default: + break; + } return ret; } +EXPORT_SYMBOL_GPL(wm_adsp1_event); int wm_adsp2_set_dspclk(struct snd_soc_dapm_widget *w, unsigned int freq) { @@ -3225,104 +928,6 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol, } EXPORT_SYMBOL_GPL(wm_adsp2_preloader_put); -static void cs_dsp_stop_watchdog(struct cs_dsp *dsp) -{ - regmap_update_bits(dsp->regmap, dsp->base + ADSP2_WATCHDOG, - ADSP2_WDT_ENA_MASK, 0); -} - -static void cs_dsp_halo_stop_watchdog(struct cs_dsp *dsp) -{ - regmap_update_bits(dsp->regmap, dsp->base + HALO_WDT_CONTROL, - HALO_WDT_EN_MASK, 0); -} - -static int cs_dsp_power_up(struct cs_dsp *dsp, - const struct firmware *wmfw_firmware, char *wmfw_filename, - const struct firmware *coeff_firmware, char *coeff_filename, - const char *fw_name) -{ - int ret; - - mutex_lock(&dsp->pwr_lock); - - dsp->fw_name = fw_name; - - if (dsp->ops->enable_memory) { - ret = dsp->ops->enable_memory(dsp); - if (ret != 0) - goto err_mutex; - } - - if (dsp->ops->enable_core) { - ret = dsp->ops->enable_core(dsp); - if (ret != 0) - goto err_mem; - } - - ret = cs_dsp_load(dsp, wmfw_firmware, wmfw_filename); - if (ret != 0) - goto err_ena; - - ret = dsp->ops->setup_algs(dsp); - if (ret != 0) - goto err_ena; - - ret = cs_dsp_load_coeff(dsp, coeff_firmware, coeff_filename); - if (ret != 0) - goto err_ena; - - /* Initialize caches for enabled and unset controls */ - ret = cs_dsp_coeff_init_control_caches(dsp); - if (ret != 0) - goto err_ena; - - if (dsp->ops->disable_core) - dsp->ops->disable_core(dsp); - - dsp->booted = true; - - mutex_unlock(&dsp->pwr_lock); - - return 0; -err_ena: - if (dsp->ops->disable_core) - dsp->ops->disable_core(dsp); -err_mem: - if (dsp->ops->disable_memory) - dsp->ops->disable_memory(dsp); -err_mutex: - mutex_unlock(&dsp->pwr_lock); - - return ret; -} - -static void cs_dsp_power_down(struct cs_dsp *dsp) -{ - struct cs_dsp_coeff_ctl *ctl; - - mutex_lock(&dsp->pwr_lock); - - cs_dsp_debugfs_clear(dsp); - - dsp->fw_id = 0; - dsp->fw_id_version = 0; - - dsp->booted = false; - - if (dsp->ops->disable_memory) - dsp->ops->disable_memory(dsp); - - list_for_each_entry(ctl, &dsp->ctl_list, list) - ctl->enabled = 0; - - cs_dsp_free_alg_regions(dsp); - - mutex_unlock(&dsp->pwr_lock); - - cs_dsp_dbg(dsp, "Shutdown complete\n"); -} - static void wm_adsp_boot_work(struct work_struct *work) { struct wm_adsp *dsp = container_of(work, @@ -3372,19 +977,6 @@ int wm_adsp_early_event(struct snd_soc_dapm_widget *w, } EXPORT_SYMBOL_GPL(wm_adsp_early_event); -static int cs_dsp_adsp2_start_core(struct cs_dsp *dsp) -{ - return regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_CORE_ENA | ADSP2_START, - ADSP2_CORE_ENA | ADSP2_START); -} - -static void cs_dsp_adsp2_stop_core(struct cs_dsp *dsp) -{ - regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_CORE_ENA | ADSP2_START, 0); -} - static int wm_adsp_event_post_run(struct cs_dsp *cs_dsp) { struct wm_adsp *dsp = container_of(cs_dsp, struct wm_adsp, cs_dsp); @@ -3405,93 +997,6 @@ static void wm_adsp_event_post_stop(struct cs_dsp *cs_dsp) dsp->fatal_error = false; } -static int cs_dsp_run(struct cs_dsp *dsp) -{ - int ret; - - mutex_lock(&dsp->pwr_lock); - - if (!dsp->booted) { - ret = -EIO; - goto err; - } - - if (dsp->ops->enable_core) { - ret = dsp->ops->enable_core(dsp); - if (ret != 0) - goto err; - } - - /* Sync set controls */ - ret = cs_dsp_coeff_sync_controls(dsp); - if (ret != 0) - goto err; - - if (dsp->ops->lock_memory) { - ret = dsp->ops->lock_memory(dsp, dsp->lock_regions); - if (ret != 0) { - cs_dsp_err(dsp, "Error configuring MPU: %d\n", ret); - goto err; - } - } - - if (dsp->ops->start_core) { - ret = dsp->ops->start_core(dsp); - if (ret != 0) - goto err; - } - - dsp->running = true; - - if (dsp->client_ops->post_run) { - ret = dsp->client_ops->post_run(dsp); - if (ret) - goto err; - } - - mutex_unlock(&dsp->pwr_lock); - - return 0; - -err: - if (dsp->ops->stop_core) - dsp->ops->stop_core(dsp); - if (dsp->ops->disable_core) - dsp->ops->disable_core(dsp); - mutex_unlock(&dsp->pwr_lock); - - return ret; -} - -static void cs_dsp_stop(struct cs_dsp *dsp) -{ - /* Tell the firmware to cleanup */ - cs_dsp_signal_event_controls(dsp, CS_DSP_FW_EVENT_SHUTDOWN); - - if (dsp->ops->stop_watchdog) - dsp->ops->stop_watchdog(dsp); - - /* Log firmware state, it can be useful for analysis */ - if (dsp->ops->show_fw_status) - dsp->ops->show_fw_status(dsp); - - mutex_lock(&dsp->pwr_lock); - - dsp->running = false; - - if (dsp->ops->stop_core) - dsp->ops->stop_core(dsp); - if (dsp->ops->disable_core) - dsp->ops->disable_core(dsp); - - if (dsp->client_ops->post_stop) - dsp->client_ops->post_stop(dsp); - - mutex_unlock(&dsp->pwr_lock); - - cs_dsp_dbg(dsp, "Execution stopped\n"); -} - int wm_adsp_event(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { @@ -3516,24 +1021,6 @@ int wm_adsp_event(struct snd_soc_dapm_widget *w, } EXPORT_SYMBOL_GPL(wm_adsp_event); -static int cs_dsp_halo_start_core(struct cs_dsp *dsp) -{ - return regmap_update_bits(dsp->regmap, - dsp->base + HALO_CCM_CORE_CONTROL, - HALO_CORE_RESET | HALO_CORE_EN, - HALO_CORE_RESET | HALO_CORE_EN); -} - -static void cs_dsp_halo_stop_core(struct cs_dsp *dsp) -{ - regmap_update_bits(dsp->regmap, dsp->base + HALO_CCM_CORE_CONTROL, - HALO_CORE_EN, 0); - - /* reset halo core with CORE_SOFT_RESET */ - regmap_update_bits(dsp->regmap, dsp->base + HALO_CORE_SOFT_RESET, - HALO_CORE_SOFT_RESET_MASK, 1); -} - int wm_adsp2_component_probe(struct wm_adsp *dsp, struct snd_soc_component *component) { char preload[32]; @@ -3557,37 +1044,6 @@ int wm_adsp2_component_remove(struct wm_adsp *dsp, struct snd_soc_component *com } EXPORT_SYMBOL_GPL(wm_adsp2_component_remove); -static int cs_dsp_adsp2_init(struct cs_dsp *dsp) -{ - int ret; - - switch (dsp->rev) { - case 0: - /* - * Disable the DSP memory by default when in reset for a small - * power saving. - */ - ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL, - ADSP2_MEM_ENA, 0); - if (ret) { - cs_dsp_err(dsp, - "Failed to clear memory retention: %d\n", ret); - return ret; - } - - dsp->ops = &cs_dsp_adsp2_ops[0]; - break; - case 1: - dsp->ops = &cs_dsp_adsp2_ops[1]; - break; - default: - dsp->ops = &cs_dsp_adsp2_ops[2]; - break; - } - - return cs_dsp_common_init(dsp); -} - int wm_adsp2_init(struct wm_adsp *dsp) { int ret; @@ -3605,13 +1061,6 @@ int wm_adsp2_init(struct wm_adsp *dsp) } EXPORT_SYMBOL_GPL(wm_adsp2_init); -static int cs_dsp_halo_init(struct cs_dsp *dsp) -{ - dsp->ops = &cs_dsp_halo_ops; - - return cs_dsp_common_init(dsp); -} - int wm_halo_init(struct wm_adsp *dsp) { int ret; @@ -3629,21 +1078,6 @@ int wm_halo_init(struct wm_adsp *dsp) } EXPORT_SYMBOL_GPL(wm_halo_init); -static void cs_dsp_remove(struct cs_dsp *dsp) -{ - struct cs_dsp_coeff_ctl *ctl; - - while (!list_empty(&dsp->ctl_list)) { - ctl = list_first_entry(&dsp->ctl_list, struct cs_dsp_coeff_ctl, list); - - if (dsp->client_ops->control_remove) - dsp->client_ops->control_remove(ctl); - - list_del(&ctl->list); - cs_dsp_free_ctl_blk(ctl); - } -} - void wm_adsp2_remove(struct wm_adsp *dsp) { cs_dsp_remove(&dsp->cs_dsp); @@ -3873,57 +1307,6 @@ int wm_adsp_compr_get_caps(struct snd_soc_component *component, } EXPORT_SYMBOL_GPL(wm_adsp_compr_get_caps); -static int cs_dsp_read_raw_data_block(struct cs_dsp *dsp, int mem_type, - unsigned int mem_addr, - unsigned int num_words, __be32 *data) -{ - struct cs_dsp_region const *mem = cs_dsp_find_region(dsp, mem_type); - unsigned int reg; - int ret; - - if (!mem) - return -EINVAL; - - reg = dsp->ops->region_to_reg(mem, mem_addr); - - ret = regmap_raw_read(dsp->regmap, reg, data, - sizeof(*data) * num_words); - if (ret < 0) - return ret; - - return 0; -} - -static int cs_dsp_read_data_word(struct cs_dsp *dsp, int mem_type, - unsigned int mem_addr, u32 *data) -{ - __be32 raw; - int ret; - - ret = cs_dsp_read_raw_data_block(dsp, mem_type, mem_addr, 1, &raw); - if (ret < 0) - return ret; - - *data = be32_to_cpu(raw) & 0x00ffffffu; - - return 0; -} - -static int cs_dsp_write_data_word(struct cs_dsp *dsp, int mem_type, - unsigned int mem_addr, u32 data) -{ - struct cs_dsp_region const *mem = cs_dsp_find_region(dsp, mem_type); - __be32 val = cpu_to_be32(data & 0x00ffffffu); - unsigned int reg; - - if (!mem) - return -EINVAL; - - reg = dsp->ops->region_to_reg(mem, mem_addr); - - return regmap_raw_write(dsp->regmap, reg, &val, sizeof(val)); -} - static inline int wm_adsp_buffer_read(struct wm_adsp_compr_buf *buf, unsigned int field_offset, u32 *data) { @@ -3939,25 +1322,6 @@ static inline int wm_adsp_buffer_write(struct wm_adsp_compr_buf *buf, data); } -static void cs_dsp_remove_padding(u32 *buf, int nwords) -{ - const __be32 *pack_in = (__be32 *)buf; - u8 *pack_out = (u8 *)buf; - int i; - - /* - * DSP words from the register map have pad bytes and the data bytes - * are in swapped order. This swaps back to the original little-endian - * order and strips the pad bytes. - */ - for (i = 0; i < nwords; i++) { - u32 word = be32_to_cpu(*pack_in++); - *pack_out++ = (u8)word; - *pack_out++ = (u8)(word >> 8); - *pack_out++ = (u8)(word >> 16); - } -} - static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf) { const struct wm_adsp_fw_caps *caps = wm_adsp_fw[buf->dsp->fw].caps; @@ -4568,69 +1932,6 @@ static void wm_adsp_fatal_error(struct cs_dsp *cs_dsp) } } -static void cs_dsp_adsp2_bus_error(struct cs_dsp *dsp) -{ - unsigned int val; - struct regmap *regmap = dsp->regmap; - int ret = 0; - - mutex_lock(&dsp->pwr_lock); - - ret = regmap_read(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, &val); - if (ret) { - cs_dsp_err(dsp, - "Failed to read Region Lock Ctrl register: %d\n", ret); - goto error; - } - - if (val & ADSP2_WDT_TIMEOUT_STS_MASK) { - cs_dsp_err(dsp, "watchdog timeout error\n"); - dsp->ops->stop_watchdog(dsp); - if (dsp->client_ops->watchdog_expired) - dsp->client_ops->watchdog_expired(dsp); - } - - if (val & (ADSP2_ADDR_ERR_MASK | ADSP2_REGION_LOCK_ERR_MASK)) { - if (val & ADSP2_ADDR_ERR_MASK) - cs_dsp_err(dsp, "bus error: address error\n"); - else - cs_dsp_err(dsp, "bus error: region lock error\n"); - - ret = regmap_read(regmap, dsp->base + ADSP2_BUS_ERR_ADDR, &val); - if (ret) { - cs_dsp_err(dsp, - "Failed to read Bus Err Addr register: %d\n", - ret); - goto error; - } - - cs_dsp_err(dsp, "bus error address = 0x%x\n", - val & ADSP2_BUS_ERR_ADDR_MASK); - - ret = regmap_read(regmap, - dsp->base + ADSP2_PMEM_ERR_ADDR_XMEM_ERR_ADDR, - &val); - if (ret) { - cs_dsp_err(dsp, - "Failed to read Pmem Xmem Err Addr register: %d\n", - ret); - goto error; - } - - cs_dsp_err(dsp, "xmem error address = 0x%x\n", - val & ADSP2_XMEM_ERR_ADDR_MASK); - cs_dsp_err(dsp, "pmem error address = 0x%x\n", - (val & ADSP2_PMEM_ERR_ADDR_MASK) >> - ADSP2_PMEM_ERR_ADDR_SHIFT); - } - - regmap_update_bits(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, - ADSP2_CTRL_ERR_EINT, ADSP2_CTRL_ERR_EINT); - -error: - mutex_unlock(&dsp->pwr_lock); -} - irqreturn_t wm_adsp2_bus_error(int irq, void *data) { struct wm_adsp *dsp = (struct wm_adsp *)data; @@ -4641,59 +1942,6 @@ irqreturn_t wm_adsp2_bus_error(int irq, void *data) } EXPORT_SYMBOL_GPL(wm_adsp2_bus_error); -static void cs_dsp_halo_bus_error(struct cs_dsp *dsp) -{ - struct regmap *regmap = dsp->regmap; - unsigned int fault[6]; - struct reg_sequence clear[] = { - { dsp->base + HALO_MPU_XM_VIO_STATUS, 0x0 }, - { dsp->base + HALO_MPU_YM_VIO_STATUS, 0x0 }, - { dsp->base + HALO_MPU_PM_VIO_STATUS, 0x0 }, - }; - int ret; - - mutex_lock(&dsp->pwr_lock); - - ret = regmap_read(regmap, dsp->base_sysinfo + HALO_AHBM_WINDOW_DEBUG_1, - fault); - if (ret) { - cs_dsp_warn(dsp, "Failed to read AHB DEBUG_1: %d\n", ret); - goto exit_unlock; - } - - cs_dsp_warn(dsp, "AHB: STATUS: 0x%x ADDR: 0x%x\n", - *fault & HALO_AHBM_FLAGS_ERR_MASK, - (*fault & HALO_AHBM_CORE_ERR_ADDR_MASK) >> - HALO_AHBM_CORE_ERR_ADDR_SHIFT); - - ret = regmap_read(regmap, dsp->base_sysinfo + HALO_AHBM_WINDOW_DEBUG_0, - fault); - if (ret) { - cs_dsp_warn(dsp, "Failed to read AHB DEBUG_0: %d\n", ret); - goto exit_unlock; - } - - cs_dsp_warn(dsp, "AHB: SYS_ADDR: 0x%x\n", *fault); - - ret = regmap_bulk_read(regmap, dsp->base + HALO_MPU_XM_VIO_ADDR, - fault, ARRAY_SIZE(fault)); - if (ret) { - cs_dsp_warn(dsp, "Failed to read MPU fault info: %d\n", ret); - goto exit_unlock; - } - - cs_dsp_warn(dsp, "XM: STATUS:0x%x ADDR:0x%x\n", fault[1], fault[0]); - cs_dsp_warn(dsp, "YM: STATUS:0x%x ADDR:0x%x\n", fault[3], fault[2]); - cs_dsp_warn(dsp, "PM: STATUS:0x%x ADDR:0x%x\n", fault[5], fault[4]); - - ret = regmap_multi_reg_write(dsp->regmap, clear, ARRAY_SIZE(clear)); - if (ret) - cs_dsp_warn(dsp, "Failed to clear MPU status: %d\n", ret); - -exit_unlock: - mutex_unlock(&dsp->pwr_lock); -} - irqreturn_t wm_halo_bus_error(int irq, void *data) { struct wm_adsp *dsp = (struct wm_adsp *)data; @@ -4704,19 +1952,6 @@ irqreturn_t wm_halo_bus_error(int irq, void *data) } EXPORT_SYMBOL_GPL(wm_halo_bus_error); -static void cs_dsp_halo_wdt_expire(struct cs_dsp *dsp) -{ - mutex_lock(&dsp->pwr_lock); - - cs_dsp_warn(dsp, "WDT Expiry Fault\n"); - - dsp->ops->stop_watchdog(dsp); - if (dsp->client_ops->watchdog_expired) - dsp->client_ops->watchdog_expired(dsp); - - mutex_unlock(&dsp->pwr_lock); -} - irqreturn_t wm_halo_wdt_expire(int irq, void *data) { struct wm_adsp *dsp = data; @@ -4727,90 +1962,11 @@ irqreturn_t wm_halo_wdt_expire(int irq, void *data) } EXPORT_SYMBOL_GPL(wm_halo_wdt_expire); -static const struct cs_dsp_ops cs_dsp_adsp1_ops = { - .validate_version = cs_dsp_validate_version, - .parse_sizes = cs_dsp_adsp1_parse_sizes, - .region_to_reg = cs_dsp_region_to_reg, -}; - static const struct cs_dsp_client_ops wm_adsp1_client_ops = { .control_add = wm_adsp_control_add, .control_remove = wm_adsp_control_remove, }; -static const struct cs_dsp_ops cs_dsp_adsp2_ops[] = { - { - .parse_sizes = cs_dsp_adsp2_parse_sizes, - .validate_version = cs_dsp_validate_version, - .setup_algs = cs_dsp_adsp2_setup_algs, - .region_to_reg = cs_dsp_region_to_reg, - - .show_fw_status = cs_dsp_adsp2_show_fw_status, - - .enable_memory = cs_dsp_adsp2_enable_memory, - .disable_memory = cs_dsp_adsp2_disable_memory, - - .enable_core = cs_dsp_adsp2_enable_core, - .disable_core = cs_dsp_adsp2_disable_core, - - .start_core = cs_dsp_adsp2_start_core, - .stop_core = cs_dsp_adsp2_stop_core, - - }, - { - .parse_sizes = cs_dsp_adsp2_parse_sizes, - .validate_version = cs_dsp_validate_version, - .setup_algs = cs_dsp_adsp2_setup_algs, - .region_to_reg = cs_dsp_region_to_reg, - - .show_fw_status = cs_dsp_adsp2v2_show_fw_status, - - .enable_memory = cs_dsp_adsp2_enable_memory, - .disable_memory = cs_dsp_adsp2_disable_memory, - .lock_memory = cs_dsp_adsp2_lock, - - .enable_core = cs_dsp_adsp2v2_enable_core, - .disable_core = cs_dsp_adsp2v2_disable_core, - - .start_core = cs_dsp_adsp2_start_core, - .stop_core = cs_dsp_adsp2_stop_core, - }, - { - .parse_sizes = cs_dsp_adsp2_parse_sizes, - .validate_version = cs_dsp_validate_version, - .setup_algs = cs_dsp_adsp2_setup_algs, - .region_to_reg = cs_dsp_region_to_reg, - - .show_fw_status = cs_dsp_adsp2v2_show_fw_status, - .stop_watchdog = cs_dsp_stop_watchdog, - - .enable_memory = cs_dsp_adsp2_enable_memory, - .disable_memory = cs_dsp_adsp2_disable_memory, - .lock_memory = cs_dsp_adsp2_lock, - - .enable_core = cs_dsp_adsp2v2_enable_core, - .disable_core = cs_dsp_adsp2v2_disable_core, - - .start_core = cs_dsp_adsp2_start_core, - .stop_core = cs_dsp_adsp2_stop_core, - }, -}; - -static const struct cs_dsp_ops cs_dsp_halo_ops = { - .parse_sizes = cs_dsp_adsp2_parse_sizes, - .validate_version = cs_dsp_halo_validate_version, - .setup_algs = cs_dsp_halo_setup_algs, - .region_to_reg = cs_dsp_halo_region_to_reg, - - .show_fw_status = cs_dsp_halo_show_fw_status, - .stop_watchdog = cs_dsp_halo_stop_watchdog, - - .lock_memory = cs_dsp_halo_configure_mpu, - - .start_core = cs_dsp_halo_start_core, - .stop_core = cs_dsp_halo_stop_core, -}; - static const struct cs_dsp_client_ops wm_adsp2_client_ops = { .control_add = wm_adsp_control_add, .control_remove = wm_adsp_control_remove, diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h index 25aaef74654c..0e2f113bd342 100644 --- a/sound/soc/codecs/wm_adsp.h +++ b/sound/soc/codecs/wm_adsp.h @@ -10,113 +10,19 @@ #ifndef __WM_ADSP_H #define __WM_ADSP_H +#include +#include + #include #include #include -#include "wmfw.h" - /* Return values for wm_adsp_compr_handle_irq */ #define WM_ADSP_COMPR_OK 0 #define WM_ADSP_COMPR_VOICE_TRIGGER 1 -#define CS_ADSP2_REGION_0 BIT(0) -#define CS_ADSP2_REGION_1 BIT(1) -#define CS_ADSP2_REGION_2 BIT(2) -#define CS_ADSP2_REGION_3 BIT(3) -#define CS_ADSP2_REGION_4 BIT(4) -#define CS_ADSP2_REGION_5 BIT(5) -#define CS_ADSP2_REGION_6 BIT(6) -#define CS_ADSP2_REGION_7 BIT(7) -#define CS_ADSP2_REGION_8 BIT(8) -#define CS_ADSP2_REGION_9 BIT(9) -#define CS_ADSP2_REGION_1_9 (CS_ADSP2_REGION_1 | \ - CS_ADSP2_REGION_2 | CS_ADSP2_REGION_3 | \ - CS_ADSP2_REGION_4 | CS_ADSP2_REGION_5 | \ - CS_ADSP2_REGION_6 | CS_ADSP2_REGION_7 | \ - CS_ADSP2_REGION_8 | CS_ADSP2_REGION_9) -#define CS_ADSP2_REGION_ALL (CS_ADSP2_REGION_0 | CS_ADSP2_REGION_1_9) - -struct cs_dsp_region { - int type; - unsigned int base; -}; - -struct cs_dsp_alg_region { - struct list_head list; - unsigned int alg; - int type; - unsigned int base; -}; - struct wm_adsp_compr; struct wm_adsp_compr_buf; -struct cs_dsp_ops; -struct cs_dsp_client_ops; - -struct cs_dsp_coeff_ctl { - const char *fw_name; - /* Subname is needed to match with firmware */ - const char *subname; - unsigned int subname_len; - struct cs_dsp_alg_region alg_region; - struct cs_dsp *dsp; - unsigned int enabled:1; - struct list_head list; - void *cache; - unsigned int offset; - size_t len; - unsigned int set:1; - unsigned int flags; - unsigned int type; - - void *priv; -}; - -struct cs_dsp { - const char *name; - int rev; - int num; - int type; - struct device *dev; - struct regmap *regmap; - - const struct cs_dsp_ops *ops; - const struct cs_dsp_client_ops *client_ops; - - unsigned int base; - unsigned int base_sysinfo; - unsigned int sysclk_reg; - unsigned int sysclk_mask; - unsigned int sysclk_shift; - - struct list_head alg_regions; - - const char *fw_name; - unsigned int fw_id; - unsigned int fw_id_version; - unsigned int fw_vendor_id; - - const struct cs_dsp_region *mem; - int num_mems; - - int fw_ver; - - bool booted; - bool running; - - struct list_head ctl_list; - - struct mutex pwr_lock; - - unsigned int lock_regions; - -#ifdef CONFIG_DEBUG_FS - struct dentry *debugfs_root; - char *wmfw_file_name; - char *bin_file_name; -#endif -}; struct wm_adsp { struct cs_dsp cs_dsp; @@ -137,30 +43,6 @@ struct wm_adsp { struct list_head buffer_list; }; -struct cs_dsp_ops { - bool (*validate_version)(struct cs_dsp *dsp, unsigned int version); - unsigned int (*parse_sizes)(struct cs_dsp *dsp, - const char * const file, - unsigned int pos, - const struct firmware *firmware); - int (*setup_algs)(struct cs_dsp *dsp); - unsigned int (*region_to_reg)(struct cs_dsp_region const *mem, - unsigned int offset); - - void (*show_fw_status)(struct cs_dsp *dsp); - void (*stop_watchdog)(struct cs_dsp *dsp); - - int (*enable_memory)(struct cs_dsp *dsp); - void (*disable_memory)(struct cs_dsp *dsp); - int (*lock_memory)(struct cs_dsp *dsp, unsigned int lock_regions); - - int (*enable_core)(struct cs_dsp *dsp); - void (*disable_core)(struct cs_dsp *dsp); - - int (*start_core)(struct cs_dsp *dsp); - void (*stop_core)(struct cs_dsp *dsp); -}; - #define WM_ADSP1(wname, num) \ SND_SOC_DAPM_PGA_E(wname, SND_SOC_NOPM, num, 0, NULL, 0, \ wm_adsp1_event, SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD) @@ -239,12 +121,4 @@ int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name, int type, unsigned int alg, void *buf, size_t len); -struct cs_dsp_client_ops { - int (*control_add)(struct cs_dsp_coeff_ctl *ctl); - void (*control_remove)(struct cs_dsp_coeff_ctl *ctl); - int (*post_run)(struct cs_dsp *dsp); - void (*post_stop)(struct cs_dsp *dsp); - void (*watchdog_expired)(struct cs_dsp *dsp); -}; - #endif diff --git a/sound/soc/codecs/wmfw.h b/sound/soc/codecs/wmfw.h deleted file mode 100644 index a19bf7c6fc8b..000000000000 --- a/sound/soc/codecs/wmfw.h +++ /dev/null @@ -1,202 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * wmfw.h - Wolfson firmware format information - * - * Copyright 2012 Wolfson Microelectronics plc - * - * Author: Mark Brown - */ - -#ifndef __WMFW_H -#define __WMFW_H - -#include - -#define WMFW_MAX_ALG_NAME 256 -#define WMFW_MAX_ALG_DESCR_NAME 256 - -#define WMFW_MAX_COEFF_NAME 256 -#define WMFW_MAX_COEFF_DESCR_NAME 256 - -#define WMFW_CTL_FLAG_SYS 0x8000 -#define WMFW_CTL_FLAG_VOLATILE 0x0004 -#define WMFW_CTL_FLAG_WRITEABLE 0x0002 -#define WMFW_CTL_FLAG_READABLE 0x0001 - -#define WMFW_CTL_TYPE_BYTES 0x0004 /* byte control */ - -/* Non-ALSA coefficient types start at 0x1000 */ -#define WMFW_CTL_TYPE_ACKED 0x1000 /* acked control */ -#define WMFW_CTL_TYPE_HOSTEVENT 0x1001 /* event control */ -#define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */ - -struct wmfw_header { - char magic[4]; - __le32 len; - __le16 rev; - u8 core; - u8 ver; -} __packed; - -struct wmfw_footer { - __le64 timestamp; - __le32 checksum; -} __packed; - -struct wmfw_adsp1_sizes { - __le32 dm; - __le32 pm; - __le32 zm; -} __packed; - -struct wmfw_adsp2_sizes { - __le32 xm; - __le32 ym; - __le32 pm; - __le32 zm; -} __packed; - -struct wmfw_region { - union { - __be32 type; - __le32 offset; - }; - __le32 len; - u8 data[]; -} __packed; - -struct wmfw_id_hdr { - __be32 core_id; - __be32 core_rev; - __be32 id; - __be32 ver; -} __packed; - -struct wmfw_v3_id_hdr { - __be32 core_id; - __be32 block_rev; - __be32 vendor_id; - __be32 id; - __be32 ver; -} __packed; - -struct wmfw_adsp1_id_hdr { - struct wmfw_id_hdr fw; - __be32 zm; - __be32 dm; - __be32 n_algs; -} __packed; - -struct wmfw_adsp2_id_hdr { - struct wmfw_id_hdr fw; - __be32 zm; - __be32 xm; - __be32 ym; - __be32 n_algs; -} __packed; - -struct wmfw_halo_id_hdr { - struct wmfw_v3_id_hdr fw; - __be32 xm_base; - __be32 xm_size; - __be32 ym_base; - __be32 ym_size; - __be32 n_algs; -} __packed; - -struct wmfw_alg_hdr { - __be32 id; - __be32 ver; -} __packed; - -struct wmfw_adsp1_alg_hdr { - struct wmfw_alg_hdr alg; - __be32 zm; - __be32 dm; -} __packed; - -struct wmfw_adsp2_alg_hdr { - struct wmfw_alg_hdr alg; - __be32 zm; - __be32 xm; - __be32 ym; -} __packed; - -struct wmfw_halo_alg_hdr { - struct wmfw_alg_hdr alg; - __be32 xm_base; - __be32 xm_size; - __be32 ym_base; - __be32 ym_size; -} __packed; - -struct wmfw_adsp_alg_data { - __le32 id; - u8 name[WMFW_MAX_ALG_NAME]; - u8 descr[WMFW_MAX_ALG_DESCR_NAME]; - __le32 ncoeff; - u8 data[]; -} __packed; - -struct wmfw_adsp_coeff_data { - struct { - __le16 offset; - __le16 type; - __le32 size; - } hdr; - u8 name[WMFW_MAX_COEFF_NAME]; - u8 descr[WMFW_MAX_COEFF_DESCR_NAME]; - __le16 ctl_type; - __le16 flags; - __le32 len; - u8 data[]; -} __packed; - -struct wmfw_coeff_hdr { - u8 magic[4]; - __le32 len; - union { - __be32 rev; - __le32 ver; - }; - union { - __be32 core; - __le32 core_ver; - }; - u8 data[]; -} __packed; - -struct wmfw_coeff_item { - __le16 offset; - __le16 type; - __le32 id; - __le32 ver; - __le32 sr; - __le32 len; - u8 data[]; -} __packed; - -#define WMFW_ADSP1 1 -#define WMFW_ADSP2 2 -#define WMFW_HALO 4 - -#define WMFW_ABSOLUTE 0xf0 -#define WMFW_ALGORITHM_DATA 0xf2 -#define WMFW_METADATA 0xfc -#define WMFW_NAME_TEXT 0xfe -#define WMFW_INFO_TEXT 0xff - -#define WMFW_ADSP1_PM 2 -#define WMFW_ADSP1_DM 3 -#define WMFW_ADSP1_ZM 4 - -#define WMFW_ADSP2_PM 2 -#define WMFW_ADSP2_ZM 4 -#define WMFW_ADSP2_XM 5 -#define WMFW_ADSP2_YM 6 - -#define WMFW_HALO_PM_PACKED 0x10 -#define WMFW_HALO_XM_PACKED 0x11 -#define WMFW_HALO_YM_PACKED 0x12 - -#endif -- cgit v1.2.3 From c25303281d79299e9f35d4b2e496a8bd134d5715 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 5 Jun 2021 23:20:17 -0400 Subject: mm: Convert get_page_unless_zero() to return bool atomic_add_unless() returns bool, so remove the widening casts to int in page_ref_add_unless() and get_page_unless_zero(). This causes gcc to produce slightly larger code in isolate_migratepages_block(), but it's not clear that it's worse code. Net +19 bytes of text. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Kirill A. Shutemov Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 2 +- include/linux/page_ref.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..1de8864a1e28 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -754,7 +754,7 @@ static inline int put_page_testzero(struct page *page) * This can be called when MMU is off so it must not access * any of the virtual mappings. */ -static inline int get_page_unless_zero(struct page *page) +static inline bool get_page_unless_zero(struct page *page) { return page_ref_add_unless(page, 1, 0); } diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 7ad46f45df39..3a799de8ad52 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -161,9 +161,9 @@ static inline int page_ref_dec_return(struct page *page) return ret; } -static inline int page_ref_add_unless(struct page *page, int nr, int u) +static inline bool page_ref_add_unless(struct page *page, int nr, int u) { - int ret = atomic_add_unless(&page->_refcount, nr, u); + bool ret = atomic_add_unless(&page->_refcount, nr, u); if (page_ref_tracepoint_active(page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); -- cgit v1.2.3 From 7b230db3b8d373219f88a3d25c8fbbf12cc7f233 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 6 Dec 2020 22:22:48 -0500 Subject: mm: Introduce struct folio A struct folio is a new abstraction to replace the venerable struct page. A function which takes a struct folio argument declares that it will operate on the entire (possibly compound) page, not just PAGE_SIZE bytes. In return, the caller guarantees that the pointer it is passing does not point to a tail page. No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Mike Rapoport --- Documentation/core-api/mm-api.rst | 1 + include/linux/mm.h | 75 +++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 60 +++++++++++++++++++++++++++++++ include/linux/page-flags.h | 28 +++++++++++++++ 4 files changed, 164 insertions(+) (limited to 'include/linux') diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index a42f9baddfbf..2a94e6164f80 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -95,6 +95,7 @@ More Memory Management Functions .. kernel-doc:: mm/mempolicy.c .. kernel-doc:: include/linux/mm_types.h :internal: +.. kernel-doc:: include/linux/page-flags.h .. kernel-doc:: include/linux/mm.h :internal: .. kernel-doc:: include/linux/mmzone.h diff --git a/include/linux/mm.h b/include/linux/mm.h index 1de8864a1e28..9057b8406acf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -950,6 +950,20 @@ static inline unsigned int compound_order(struct page *page) return page[1].compound_order; } +/** + * folio_order - The allocation order of a folio. + * @folio: The folio. + * + * A folio is composed of 2^order pages. See get_order() for the definition + * of order. + * + * Return: The order of the folio. + */ +static inline unsigned int folio_order(struct folio *folio) +{ + return compound_order(&folio->page); +} + static inline bool hpage_pincount_available(struct page *page) { /* @@ -1595,6 +1609,66 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } +/** + * folio_nr_pages - The number of pages in the folio. + * @folio: The folio. + * + * Return: A positive power of two. + */ +static inline long folio_nr_pages(struct folio *folio) +{ + return compound_nr(&folio->page); +} + +/** + * folio_next - Move to the next physical folio. + * @folio: The folio we're currently operating on. + * + * If you have physically contiguous memory which may span more than + * one folio (eg a &struct bio_vec), use this function to move from one + * folio to the next. Do not use it if the memory is only virtually + * contiguous as the folios are almost certainly not adjacent to each + * other. This is the folio equivalent to writing ``page++``. + * + * Context: We assume that the folios are refcounted and/or locked at a + * higher level and do not adjust the reference counts. + * Return: The next struct folio. + */ +static inline struct folio *folio_next(struct folio *folio) +{ + return (struct folio *)folio_page(folio, folio_nr_pages(folio)); +} + +/** + * folio_shift - The size of the memory described by this folio. + * @folio: The folio. + * + * A folio represents a number of bytes which is a power-of-two in size. + * This function tells you which power-of-two the folio is. See also + * folio_size() and folio_order(). + * + * Context: The caller should have a reference on the folio to prevent + * it from being split. It is not necessary for the folio to be locked. + * Return: The base-2 logarithm of the size of this folio. + */ +static inline unsigned int folio_shift(struct folio *folio) +{ + return PAGE_SHIFT + folio_order(folio); +} + +/** + * folio_size - The number of bytes in a folio. + * @folio: The folio. + * + * Context: The caller should have a reference on the folio to prevent + * it from being split. It is not necessary for the folio to be locked. + * Return: The number of bytes in this folio. + */ +static inline size_t folio_size(struct folio *folio) +{ + return PAGE_SIZE << folio_order(folio); +} + /* * Some inline functions in vmstat.h depend on page_zone() */ @@ -1700,6 +1774,7 @@ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) #define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1)) +#define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1)) /* * Flags passed to show_mem() and show_free_areas() to suppress output in diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..6908186629b4 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -239,6 +239,66 @@ struct page { #endif } _struct_page_alignment; +/** + * struct folio - Represents a contiguous set of bytes. + * @flags: Identical to the page flags. + * @lru: Least Recently Used list; tracks how recently this folio was used. + * @mapping: The file this page belongs to, or refers to the anon_vma for + * anonymous memory. + * @index: Offset within the file, in units of pages. For anonymous memory, + * this is the index from the beginning of the mmap. + * @private: Filesystem per-folio data (see folio_attach_private()). + * Used for swp_entry_t if folio_test_swapcache(). + * @_mapcount: Do not access this member directly. Use folio_mapcount() to + * find out how many times this folio is mapped by userspace. + * @_refcount: Do not access this member directly. Use folio_ref_count() + * to find how many references there are to this folio. + * @memcg_data: Memory Control Group data. + * + * A folio is a physically, virtually and logically contiguous set + * of bytes. It is a power-of-two in size, and it is aligned to that + * same power-of-two. It is at least as large as %PAGE_SIZE. If it is + * in the page cache, it is at a file offset which is a multiple of that + * power-of-two. It may be mapped into userspace at an address which is + * at an arbitrary page offset, but its kernel virtual address is aligned + * to its size. + */ +struct folio { + /* private: don't document the anon union */ + union { + struct { + /* public: */ + unsigned long flags; + struct list_head lru; + struct address_space *mapping; + pgoff_t index; + void *private; + atomic_t _mapcount; + atomic_t _refcount; +#ifdef CONFIG_MEMCG + unsigned long memcg_data; +#endif + /* private: the union with struct page is transitional */ + }; + struct page page; + }; +}; + +static_assert(sizeof(struct page) == sizeof(struct folio)); +#define FOLIO_MATCH(pg, fl) \ + static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) +FOLIO_MATCH(flags, flags); +FOLIO_MATCH(lru, lru); +FOLIO_MATCH(compound_head, lru); +FOLIO_MATCH(index, index); +FOLIO_MATCH(private, private); +FOLIO_MATCH(_mapcount, _mapcount); +FOLIO_MATCH(_refcount, _refcount); +#ifdef CONFIG_MEMCG +FOLIO_MATCH(memcg_data, memcg_data); +#endif +#undef FOLIO_MATCH + static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index a558d67ee86f..e9b0723a637d 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -193,6 +193,34 @@ static inline unsigned long _compound_head(const struct page *page) #define compound_head(page) ((typeof(page))_compound_head(page)) +/** + * page_folio - Converts from page to folio. + * @p: The page. + * + * Every page is part of a folio. This function cannot be called on a + * NULL pointer. + * + * Context: No reference, nor lock is required on @page. If the caller + * does not hold a reference, this call may race with a folio split, so + * it should re-check the folio still contains this page after gaining + * a reference on the folio. + * Return: The folio which contains this page. + */ +#define page_folio(p) (_Generic((p), \ + const struct page *: (const struct folio *)_compound_head(p), \ + struct page *: (struct folio *)_compound_head(p))) + +/** + * folio_page - Return a page from a folio. + * @folio: The folio. + * @n: The page number to return. + * + * @n is relative to the start of the folio. This function does not + * check that the page number lies within @folio; the caller is presumed + * to have a reference to the page. + */ +#define folio_page(folio, n) nth_page(&(folio)->page, n) + static __always_inline int PageTail(struct page *page) { return READ_ONCE(page->compound_head) & 1; -- cgit v1.2.3 From 32b8fc486524044f2643c5d3340fa436b761ba71 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 18 Jan 2021 07:40:36 -0500 Subject: mm: Add folio_pgdat(), folio_zone() and folio_zonenum() These are just convenience wrappers for callers with folios; pgdat and zone can be reached from tail pages as well as head pages. No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/mm.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 9057b8406acf..3fc524f8c2a2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1145,6 +1145,11 @@ static inline enum zone_type page_zonenum(const struct page *page) return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } +static inline enum zone_type folio_zonenum(const struct folio *folio) +{ + return page_zonenum(&folio->page); +} + #ifdef CONFIG_ZONE_DEVICE static inline bool is_zone_device_page(const struct page *page) { @@ -1560,6 +1565,16 @@ static inline pg_data_t *page_pgdat(const struct page *page) return NODE_DATA(page_to_nid(page)); } +static inline struct zone *folio_zone(const struct folio *folio) +{ + return page_zone(&folio->page); +} + +static inline pg_data_t *folio_pgdat(const struct folio *folio) +{ + return page_pgdat(&folio->page); +} + #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { -- cgit v1.2.3 From a53e17e4e97b4519882d640984a386c522e9fba3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 18 Jan 2021 08:14:00 -0500 Subject: mm/vmstat: Add functions to account folio statistics Allow page counters to be more readily modified by callers which have a folio. Name these wrappers with 'stat' instead of 'state' as requested by Linus here: https://lore.kernel.org/linux-mm/CAHk-=wj847SudR-kt+46fT3+xFFgiwpgThvm7DJWGdi4cVrbnQ@mail.gmail.com/ No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/vmstat.h | 107 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 107 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index d6a6cf53b127..241bd0f53fb9 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -415,6 +415,78 @@ static inline void drain_zonestat(struct zone *zone, struct per_cpu_zonestat *pzstats) { } #endif /* CONFIG_SMP */ +static inline void __zone_stat_mod_folio(struct folio *folio, + enum zone_stat_item item, long nr) +{ + __mod_zone_page_state(folio_zone(folio), item, nr); +} + +static inline void __zone_stat_add_folio(struct folio *folio, + enum zone_stat_item item) +{ + __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); +} + +static inline void __zone_stat_sub_folio(struct folio *folio, + enum zone_stat_item item) +{ + __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); +} + +static inline void zone_stat_mod_folio(struct folio *folio, + enum zone_stat_item item, long nr) +{ + mod_zone_page_state(folio_zone(folio), item, nr); +} + +static inline void zone_stat_add_folio(struct folio *folio, + enum zone_stat_item item) +{ + mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio)); +} + +static inline void zone_stat_sub_folio(struct folio *folio, + enum zone_stat_item item) +{ + mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio)); +} + +static inline void __node_stat_mod_folio(struct folio *folio, + enum node_stat_item item, long nr) +{ + __mod_node_page_state(folio_pgdat(folio), item, nr); +} + +static inline void __node_stat_add_folio(struct folio *folio, + enum node_stat_item item) +{ + __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); +} + +static inline void __node_stat_sub_folio(struct folio *folio, + enum node_stat_item item) +{ + __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); +} + +static inline void node_stat_mod_folio(struct folio *folio, + enum node_stat_item item, long nr) +{ + mod_node_page_state(folio_pgdat(folio), item, nr); +} + +static inline void node_stat_add_folio(struct folio *folio, + enum node_stat_item item) +{ + mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio)); +} + +static inline void node_stat_sub_folio(struct folio *folio, + enum node_stat_item item) +{ + mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio)); +} + static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { @@ -543,6 +615,24 @@ static inline void __dec_lruvec_page_state(struct page *page, __mod_lruvec_page_state(page, idx, -1); } +static inline void __lruvec_stat_mod_folio(struct folio *folio, + enum node_stat_item idx, int val) +{ + __mod_lruvec_page_state(&folio->page, idx, val); +} + +static inline void __lruvec_stat_add_folio(struct folio *folio, + enum node_stat_item idx) +{ + __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); +} + +static inline void __lruvec_stat_sub_folio(struct folio *folio, + enum node_stat_item idx) +{ + __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); +} + static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { @@ -555,4 +645,21 @@ static inline void dec_lruvec_page_state(struct page *page, mod_lruvec_page_state(page, idx, -1); } +static inline void lruvec_stat_mod_folio(struct folio *folio, + enum node_stat_item idx, int val) +{ + mod_lruvec_page_state(&folio->page, idx, val); +} + +static inline void lruvec_stat_add_folio(struct folio *folio, + enum node_stat_item idx) +{ + lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio)); +} + +static inline void lruvec_stat_sub_folio(struct folio *folio, + enum node_stat_item idx) +{ + lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio)); +} #endif /* _LINUX_VMSTAT_H */ -- cgit v1.2.3 From 9e9edb2094db7eb4c6da21e02ac885955350ecf9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 15 Jan 2021 10:52:37 -0500 Subject: mm/debug: Add VM_BUG_ON_FOLIO() and VM_WARN_ON_ONCE_FOLIO() These are the folio equivalents of VM_BUG_ON_PAGE and VM_WARN_ON_ONCE_PAGE. No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/mmdebug.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index 1935d4c72d10..d7285f8148a3 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -22,6 +22,13 @@ void dump_mm(const struct mm_struct *mm); BUG(); \ } \ } while (0) +#define VM_BUG_ON_FOLIO(cond, folio) \ + do { \ + if (unlikely(cond)) { \ + dump_page(&folio->page, "VM_BUG_ON_FOLIO(" __stringify(cond)")");\ + BUG(); \ + } \ + } while (0) #define VM_BUG_ON_VMA(cond, vma) \ do { \ if (unlikely(cond)) { \ @@ -47,6 +54,17 @@ void dump_mm(const struct mm_struct *mm); } \ unlikely(__ret_warn_once); \ }) +#define VM_WARN_ON_ONCE_FOLIO(cond, folio) ({ \ + static bool __section(".data.once") __warned; \ + int __ret_warn_once = !!(cond); \ + \ + if (unlikely(__ret_warn_once && !__warned)) { \ + dump_page(&folio->page, "VM_WARN_ON_ONCE_FOLIO(" __stringify(cond)")");\ + __warned = true; \ + WARN_ON(1); \ + } \ + unlikely(__ret_warn_once); \ +}) #define VM_WARN_ON(cond) (void)WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond) @@ -55,11 +73,13 @@ void dump_mm(const struct mm_struct *mm); #else #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond) +#define VM_BUG_ON_FOLIO(cond, folio) VM_BUG_ON(cond) #define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond) #define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond) #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif -- cgit v1.2.3 From c24016ac3a629655ea164b1129816660187943c0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 31 Mar 2021 10:39:55 -0400 Subject: mm: Add folio reference count functions These functions mirror their page reference counterparts. Also add the kernel-doc to the mm-api and correct the return type of page_ref_add_unless() to bool. No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- Documentation/core-api/mm-api.rst | 1 + include/linux/page_ref.h | 88 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 88 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index 2a94e6164f80..5c459ee2acce 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -98,4 +98,5 @@ More Memory Management Functions .. kernel-doc:: include/linux/page-flags.h .. kernel-doc:: include/linux/mm.h :internal: +.. kernel-doc:: include/linux/page_ref.h .. kernel-doc:: include/linux/mmzone.h diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 3a799de8ad52..717d53c9ddf1 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -67,9 +67,31 @@ static inline int page_ref_count(const struct page *page) return atomic_read(&page->_refcount); } +/** + * folio_ref_count - The reference count on this folio. + * @folio: The folio. + * + * The refcount is usually incremented by calls to folio_get() and + * decremented by calls to folio_put(). Some typical users of the + * folio refcount: + * + * - Each reference from a page table + * - The page cache + * - Filesystem private data + * - The LRU list + * - Pipes + * - Direct IO which references this page in the process address space + * + * Return: The number of references to this folio. + */ +static inline int folio_ref_count(const struct folio *folio) +{ + return page_ref_count(&folio->page); +} + static inline int page_count(const struct page *page) { - return atomic_read(&compound_head(page)->_refcount); + return folio_ref_count(page_folio(page)); } static inline void set_page_count(struct page *page, int v) @@ -79,6 +101,11 @@ static inline void set_page_count(struct page *page, int v) __page_ref_set(page, v); } +static inline void folio_set_count(struct folio *folio, int v) +{ + set_page_count(&folio->page, v); +} + /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) @@ -95,6 +122,11 @@ static inline void page_ref_add(struct page *page, int nr) __page_ref_mod(page, nr); } +static inline void folio_ref_add(struct folio *folio, int nr) +{ + page_ref_add(&folio->page, nr); +} + static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); @@ -102,6 +134,11 @@ static inline void page_ref_sub(struct page *page, int nr) __page_ref_mod(page, -nr); } +static inline void folio_ref_sub(struct folio *folio, int nr) +{ + page_ref_sub(&folio->page, nr); +} + static inline int page_ref_sub_return(struct page *page, int nr) { int ret = atomic_sub_return(nr, &page->_refcount); @@ -111,6 +148,11 @@ static inline int page_ref_sub_return(struct page *page, int nr) return ret; } +static inline int folio_ref_sub_return(struct folio *folio, int nr) +{ + return page_ref_sub_return(&folio->page, nr); +} + static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); @@ -118,6 +160,11 @@ static inline void page_ref_inc(struct page *page) __page_ref_mod(page, 1); } +static inline void folio_ref_inc(struct folio *folio) +{ + page_ref_inc(&folio->page); +} + static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); @@ -125,6 +172,11 @@ static inline void page_ref_dec(struct page *page) __page_ref_mod(page, -1); } +static inline void folio_ref_dec(struct folio *folio) +{ + page_ref_dec(&folio->page); +} + static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); @@ -134,6 +186,11 @@ static inline int page_ref_sub_and_test(struct page *page, int nr) return ret; } +static inline int folio_ref_sub_and_test(struct folio *folio, int nr) +{ + return page_ref_sub_and_test(&folio->page, nr); +} + static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); @@ -143,6 +200,11 @@ static inline int page_ref_inc_return(struct page *page) return ret; } +static inline int folio_ref_inc_return(struct folio *folio) +{ + return page_ref_inc_return(&folio->page); +} + static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); @@ -152,6 +214,11 @@ static inline int page_ref_dec_and_test(struct page *page) return ret; } +static inline int folio_ref_dec_and_test(struct folio *folio) +{ + return page_ref_dec_and_test(&folio->page); +} + static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); @@ -161,6 +228,11 @@ static inline int page_ref_dec_return(struct page *page) return ret; } +static inline int folio_ref_dec_return(struct folio *folio) +{ + return page_ref_dec_return(&folio->page); +} + static inline bool page_ref_add_unless(struct page *page, int nr, int u) { bool ret = atomic_add_unless(&page->_refcount, nr, u); @@ -170,6 +242,11 @@ static inline bool page_ref_add_unless(struct page *page, int nr, int u) return ret; } +static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) +{ + return page_ref_add_unless(&folio->page, nr, u); +} + static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); @@ -179,6 +256,11 @@ static inline int page_ref_freeze(struct page *page, int count) return ret; } +static inline int folio_ref_freeze(struct folio *folio, int count) +{ + return page_ref_freeze(&folio->page, count); +} + static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); @@ -189,4 +271,8 @@ static inline void page_ref_unfreeze(struct page *page, int count) __page_ref_unfreeze(page, count); } +static inline void folio_ref_unfreeze(struct folio *folio, int count) +{ + page_ref_unfreeze(&folio->page, count); +} #endif -- cgit v1.2.3 From b620f63358cd35c8e9084ee9fc460153f64714f6 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 6 Dec 2020 23:04:57 -0500 Subject: mm: Add folio_put() If we know we have a folio, we can call folio_put() instead of put_page() and save the overhead of calling compound_head(). Also skips the devmap checks. This commit looks like it should be a no-op, but actually saves 684 bytes of text with the distro-derived config that I'm testing. Some functions grow a little while others shrink. I presume the compiler is making different inlining decisions. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/mm.h | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3fc524f8c2a2..28a84d82247b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -748,6 +748,11 @@ static inline int put_page_testzero(struct page *page) return page_ref_dec_and_test(page); } +static inline int folio_put_testzero(struct folio *folio) +{ + return put_page_testzero(&folio->page); +} + /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. @@ -1247,9 +1252,28 @@ static inline __must_check bool try_get_page(struct page *page) return true; } +/** + * folio_put - Decrement the reference count on a folio. + * @folio: The folio. + * + * If the folio's reference count reaches zero, the memory will be + * released back to the page allocator and may be used by another + * allocation immediately. Do not access the memory or the struct folio + * after calling folio_put() unless you can be sure that it wasn't the + * last reference. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folio_put(struct folio *folio) +{ + if (folio_put_testzero(folio)) + __put_page(&folio->page); +} + static inline void put_page(struct page *page) { - page = compound_head(page); + struct folio *folio = page_folio(page); /* * For devmap managed pages we need to catch refcount transition from @@ -1257,13 +1281,12 @@ static inline void put_page(struct page *page) * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (page_is_devmap_managed(page)) { - put_devmap_managed_page(page); + if (page_is_devmap_managed(&folio->page)) { + put_devmap_managed_page(&folio->page); return; } - if (put_page_testzero(page)) - __put_page(page); + folio_put(folio); } /* -- cgit v1.2.3 From 86d234cb0499c6466ccfc45f6501bc0cd4621c60 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 6 Dec 2020 23:04:57 -0500 Subject: mm: Add folio_get() If we know we have a folio, we can call folio_get() instead of get_page() and save the overhead of calling compound_head(). No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/mm.h | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 28a84d82247b..63685d953ce0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1224,18 +1224,26 @@ static inline bool is_pci_p2pdma_page(const struct page *page) } /* 127: arbitrary random number, small enough to assemble well */ -#define page_ref_zero_or_close_to_overflow(page) \ - ((unsigned int) page_ref_count(page) + 127u <= 127u) +#define folio_ref_zero_or_close_to_overflow(folio) \ + ((unsigned int) folio_ref_count(folio) + 127u <= 127u) + +/** + * folio_get - Increment the reference count on a folio. + * @folio: The folio. + * + * Context: May be called in any context, as long as you know that + * you have a refcount on the folio. If you do not already have one, + * folio_try_get() may be the right interface for you to use. + */ +static inline void folio_get(struct folio *folio) +{ + VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio); + folio_ref_inc(folio); +} static inline void get_page(struct page *page) { - page = compound_head(page); - /* - * Getting a normal page or the head of a compound page - * requires to already have an elevated page->_refcount. - */ - VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); - page_ref_inc(page); + folio_get(page_folio(page)); } bool __must_check try_grab_page(struct page *page, unsigned int flags); -- cgit v1.2.3 From 020853b6f5ead2849b055e9873ff7267ce584256 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 10 May 2021 16:33:22 -0400 Subject: mm: Add folio_try_get_rcu() This is the equivalent of page_cache_get_speculative(). Also add folio_ref_try_add_rcu (the equivalent of page_cache_add_speculative) and folio_get_unless_zero() (the equivalent of get_page_unless_zero()). The new kernel-doc attempts to explain from the user's point of view when to use folio_try_get_rcu() and when to use folio_get_unless_zero(), because there seems to be some confusion currently between the users of page_cache_get_speculative() and get_page_unless_zero(). Reimplement page_cache_add_speculative() and page_cache_get_speculative() as wrappers around the folio equivalents, but leave get_page_unless_zero() alone for now. This commit reduces text size by 3 bytes due to slightly different register allocation & instruction selections. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Acked-by: Kirill A. Shutemov Acked-by: Mike Rapoport --- include/linux/page_ref.h | 66 +++++++++++++++++++++++++++++++++++++ include/linux/pagemap.h | 84 +++--------------------------------------------- mm/filemap.c | 20 ++++++++++++ 3 files changed, 90 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 717d53c9ddf1..2e677e6ad09f 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -247,6 +247,72 @@ static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u) return page_ref_add_unless(&folio->page, nr, u); } +/** + * folio_try_get - Attempt to increase the refcount on a folio. + * @folio: The folio. + * + * If you do not already have a reference to a folio, you can attempt to + * get one using this function. It may fail if, for example, the folio + * has been freed since you found a pointer to it, or it is frozen for + * the purposes of splitting or migration. + * + * Return: True if the reference count was successfully incremented. + */ +static inline bool folio_try_get(struct folio *folio) +{ + return folio_ref_add_unless(folio, 1, 0); +} + +static inline bool folio_ref_try_add_rcu(struct folio *folio, int count) +{ +#ifdef CONFIG_TINY_RCU + /* + * The caller guarantees the folio will not be freed from interrupt + * context, so (on !SMP) we only need preemption to be disabled + * and TINY_RCU does that for us. + */ +# ifdef CONFIG_PREEMPT_COUNT + VM_BUG_ON(!in_atomic() && !irqs_disabled()); +# endif + VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio); + folio_ref_add(folio, count); +#else + if (unlikely(!folio_ref_add_unless(folio, count, 0))) { + /* Either the folio has been freed, or will be freed. */ + return false; + } +#endif + return true; +} + +/** + * folio_try_get_rcu - Attempt to increase the refcount on a folio. + * @folio: The folio. + * + * This is a version of folio_try_get() optimised for non-SMP kernels. + * If you are still holding the rcu_read_lock() after looking up the + * page and know that the page cannot have its refcount decreased to + * zero in interrupt context, you can use this instead of folio_try_get(). + * + * Example users include get_user_pages_fast() (as pages are not unmapped + * from interrupt context) and the page cache lookups (as pages are not + * truncated from interrupt context). We also know that pages are not + * frozen in interrupt context for the purposes of splitting or migration. + * + * You can also use this function if you're holding a lock that prevents + * pages being frozen & removed; eg the i_pages lock for the page cache + * or the mmap_sem or page table lock for page tables. In this case, + * it will always succeed, and you could have used a plain folio_get(), + * but it's sometimes more convenient to have a common function called + * from both locked and RCU-protected contexts. + * + * Return: True if the reference count was successfully incremented. + */ +static inline bool folio_try_get_rcu(struct folio *folio) +{ + return folio_ref_try_add_rcu(folio, 1); +} + static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 62db6b0176b9..f3ec26551082 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -172,91 +172,15 @@ static inline struct address_space *page_mapping_file(struct page *page) return page_mapping(page); } -/* - * speculatively take a reference to a page. - * If the page is free (_refcount == 0), then _refcount is untouched, and 0 - * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned. - * - * This function must be called inside the same rcu_read_lock() section as has - * been used to lookup the page in the pagecache radix-tree (or page table): - * this allows allocators to use a synchronize_rcu() to stabilize _refcount. - * - * Unless an RCU grace period has passed, the count of all pages coming out - * of the allocator must be considered unstable. page_count may return higher - * than expected, and put_page must be able to do the right thing when the - * page has been finished with, no matter what it is subsequently allocated - * for (because put_page is what is used here to drop an invalid speculative - * reference). - * - * This is the interesting part of the lockless pagecache (and lockless - * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) - * has the following pattern: - * 1. find page in radix tree - * 2. conditionally increment refcount - * 3. check the page is still in pagecache (if no, goto 1) - * - * Remove-side that cares about stability of _refcount (eg. reclaim) has the - * following (with the i_pages lock held): - * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) - * B. remove page from pagecache - * C. free the page - * - * There are 2 critical interleavings that matter: - * - 2 runs before A: in this case, A sees elevated refcount and bails out - * - A runs before 2: in this case, 2 sees zero refcount and retries; - * subsequently, B will complete and 1 will find no page, causing the - * lookup to return NULL. - * - * It is possible that between 1 and 2, the page is removed then the exact same - * page is inserted into the same position in pagecache. That's OK: the - * old find_get_page using a lock could equally have run before or after - * such a re-insertion, depending on order that locks are granted. - * - * Lookups racing against pagecache insertion isn't a big problem: either 1 - * will find the page or it will not. Likewise, the old find_get_page could run - * either before the insertion or afterwards, depending on timing. - */ -static inline int __page_cache_add_speculative(struct page *page, int count) +static inline bool page_cache_add_speculative(struct page *page, int count) { -#ifdef CONFIG_TINY_RCU -# ifdef CONFIG_PREEMPT_COUNT - VM_BUG_ON(!in_atomic() && !irqs_disabled()); -# endif - /* - * Preempt must be disabled here - we rely on rcu_read_lock doing - * this for us. - * - * Pagecache won't be truncated from interrupt context, so if we have - * found a page in the radix tree here, we have pinned its refcount by - * disabling preempt, and hence no need for the "speculative get" that - * SMP requires. - */ - VM_BUG_ON_PAGE(page_count(page) == 0, page); - page_ref_add(page, count); - -#else - if (unlikely(!page_ref_add_unless(page, count, 0))) { - /* - * Either the page has been freed, or will be freed. - * In either case, retry here and the caller should - * do the right thing (see comments above). - */ - return 0; - } -#endif VM_BUG_ON_PAGE(PageTail(page), page); - - return 1; -} - -static inline int page_cache_get_speculative(struct page *page) -{ - return __page_cache_add_speculative(page, 1); + return folio_ref_try_add_rcu((struct folio *)page, count); } -static inline int page_cache_add_speculative(struct page *page, int count) +static inline bool page_cache_get_speculative(struct page *page) { - return __page_cache_add_speculative(page, count); + return page_cache_add_speculative(page, 1); } /** diff --git a/mm/filemap.c b/mm/filemap.c index dae481293b5d..9fcc3d94cfcd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1801,6 +1801,26 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, } EXPORT_SYMBOL(page_cache_prev_miss); +/* + * Lockless page cache protocol: + * On the lookup side: + * 1. Load the folio from i_pages + * 2. Increment the refcount if it's not zero + * 3. If the folio is not found by xas_reload(), put the refcount and retry + * + * On the removal side: + * A. Freeze the page (by zeroing the refcount if nobody else has a reference) + * B. Remove the page from i_pages + * C. Return the page to the page allocator + * + * This means that any page may have its reference count temporarily + * increased by a speculative page cache (or fast GUP) lookup as it can + * be allocated by another user before the RCU grace period expires. + * Because the refcount temporarily acquired here may end up being the + * last refcount on the page, any page allocation must be freeable by + * folio_put(). + */ + /* * mapping_get_entry - Get a page cache entry. * @mapping: the address_space to search -- cgit v1.2.3 From d389a4a8115518e2cc232649b012b72113fe8b67 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 7 Dec 2020 15:42:09 -0500 Subject: mm: Add folio flag manipulation functions These new functions are the folio analogues of the various PageFlags functions. If CONFIG_DEBUG_VM_PGFLAGS is enabled, we check the folio is not a tail page at every invocation. This will also catch the PagePoisoned case as a poisoned page has every bit set, which would include PageTail. This saves 1684 bytes of text with the distro-derived config that I'm testing due to removing a double call to compound_head() in PageSwapCache(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/page-flags.h | 219 ++++++++++++++++++++++++++++++++------------- 1 file changed, 156 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index e9b0723a637d..2491e84b8e52 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -143,6 +143,8 @@ enum pageflags { #endif __NR_PAGEFLAGS, + PG_readahead = PG_reclaim, + /* Filesystems */ PG_checked = PG_owner_priv_1, @@ -245,6 +247,15 @@ static inline void page_init_poison(struct page *page, size_t size) } #endif +static unsigned long *folio_flags(struct folio *folio, unsigned n) +{ + struct page *page = &folio->page; + + VM_BUG_ON_PGFLAGS(PageTail(page), page); + VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page); + return &page[n].flags; +} + /* * Page flags policies wrt compound pages * @@ -289,36 +300,64 @@ static inline void page_init_poison(struct page *page, size_t size) VM_BUG_ON_PGFLAGS(!PageHead(page), page); \ PF_POISONED_CHECK(&page[1]); }) +/* Which page is the flag stored in */ +#define FOLIO_PF_ANY 0 +#define FOLIO_PF_HEAD 0 +#define FOLIO_PF_ONLY_HEAD 0 +#define FOLIO_PF_NO_TAIL 0 +#define FOLIO_PF_NO_COMPOUND 0 +#define FOLIO_PF_SECOND 1 + /* * Macros to create function definitions for page flags */ #define TESTPAGEFLAG(uname, lname, policy) \ +static __always_inline bool folio_test_##lname(struct folio *folio) \ +{ return test_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline int Page##uname(struct page *page) \ - { return test_bit(PG_##lname, &policy(page, 0)->flags); } +{ return test_bit(PG_##lname, &policy(page, 0)->flags); } #define SETPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void folio_set_##lname(struct folio *folio) \ +{ set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void SetPage##uname(struct page *page) \ - { set_bit(PG_##lname, &policy(page, 1)->flags); } +{ set_bit(PG_##lname, &policy(page, 1)->flags); } #define CLEARPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void folio_clear_##lname(struct folio *folio) \ +{ clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void ClearPage##uname(struct page *page) \ - { clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ clear_bit(PG_##lname, &policy(page, 1)->flags); } #define __SETPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void __folio_set_##lname(struct folio *folio) \ +{ __set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void __SetPage##uname(struct page *page) \ - { __set_bit(PG_##lname, &policy(page, 1)->flags); } +{ __set_bit(PG_##lname, &policy(page, 1)->flags); } #define __CLEARPAGEFLAG(uname, lname, policy) \ +static __always_inline \ +void __folio_clear_##lname(struct folio *folio) \ +{ __clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline void __ClearPage##uname(struct page *page) \ - { __clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ __clear_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTSETFLAG(uname, lname, policy) \ +static __always_inline \ +bool folio_test_set_##lname(struct folio *folio) \ +{ return test_and_set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline int TestSetPage##uname(struct page *page) \ - { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } +{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); } #define TESTCLEARFLAG(uname, lname, policy) \ +static __always_inline \ +bool folio_test_clear_##lname(struct folio *folio) \ +{ return test_and_clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \ static __always_inline int TestClearPage##uname(struct page *page) \ - { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } +{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); } #define PAGEFLAG(uname, lname, policy) \ TESTPAGEFLAG(uname, lname, policy) \ @@ -334,29 +373,37 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTSETFLAG(uname, lname, policy) \ TESTCLEARFLAG(uname, lname, policy) -#define TESTPAGEFLAG_FALSE(uname) \ +#define TESTPAGEFLAG_FALSE(uname, lname) \ +static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \ static inline int Page##uname(const struct page *page) { return 0; } -#define SETPAGEFLAG_NOOP(uname) \ +#define SETPAGEFLAG_NOOP(uname, lname) \ +static inline void folio_set_##lname(struct folio *folio) { } \ static inline void SetPage##uname(struct page *page) { } -#define CLEARPAGEFLAG_NOOP(uname) \ +#define CLEARPAGEFLAG_NOOP(uname, lname) \ +static inline void folio_clear_##lname(struct folio *folio) { } \ static inline void ClearPage##uname(struct page *page) { } -#define __CLEARPAGEFLAG_NOOP(uname) \ +#define __CLEARPAGEFLAG_NOOP(uname, lname) \ +static inline void __folio_clear_##lname(struct folio *folio) { } \ static inline void __ClearPage##uname(struct page *page) { } -#define TESTSETFLAG_FALSE(uname) \ +#define TESTSETFLAG_FALSE(uname, lname) \ +static inline bool folio_test_set_##lname(struct folio *folio) \ +{ return 0; } \ static inline int TestSetPage##uname(struct page *page) { return 0; } -#define TESTCLEARFLAG_FALSE(uname) \ +#define TESTCLEARFLAG_FALSE(uname, lname) \ +static inline bool folio_test_clear_##lname(struct folio *folio) \ +{ return 0; } \ static inline int TestClearPage##uname(struct page *page) { return 0; } -#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ - SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) +#define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \ + SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname) -#define TESTSCFLAG_FALSE(uname) \ - TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) +#define TESTSCFLAG_FALSE(uname, lname) \ + TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname) __PAGEFLAG(Locked, locked, PF_NO_TAIL) PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) @@ -412,8 +459,8 @@ PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL) /* PG_readahead is only used for reads; PG_reclaim is only for writes */ PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL) TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL) -PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) - TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND) +PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND) + TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND) #ifdef CONFIG_HIGHMEM /* @@ -422,22 +469,25 @@ PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND) */ #define PageHighMem(__p) is_highmem_idx(page_zonenum(__p)) #else -PAGEFLAG_FALSE(HighMem) +PAGEFLAG_FALSE(HighMem, highmem) #endif #ifdef CONFIG_SWAP -static __always_inline int PageSwapCache(struct page *page) +static __always_inline bool folio_test_swapcache(struct folio *folio) { -#ifdef CONFIG_THP_SWAP - page = compound_head(page); -#endif - return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags); + return folio_test_swapbacked(folio) && + test_bit(PG_swapcache, folio_flags(folio, 0)); +} +static __always_inline bool PageSwapCache(struct page *page) +{ + return folio_test_swapcache(page_folio(page)); } + SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL) #else -PAGEFLAG_FALSE(SwapCache) +PAGEFLAG_FALSE(SwapCache, swapcache) #endif PAGEFLAG(Unevictable, unevictable, PF_HEAD) @@ -449,14 +499,14 @@ PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) __CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL) TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL) #else -PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) - TESTSCFLAG_FALSE(Mlocked) +PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked) + TESTSCFLAG_FALSE(Mlocked, mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND) #else -PAGEFLAG_FALSE(Uncached) +PAGEFLAG_FALSE(Uncached, uncached) #endif #ifdef CONFIG_MEMORY_FAILURE @@ -465,7 +515,7 @@ TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) extern bool take_page_off_buddy(struct page *page); #else -PAGEFLAG_FALSE(HWPoison) +PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 #endif @@ -479,7 +529,7 @@ PAGEFLAG(Idle, idle, PF_ANY) #ifdef CONFIG_KASAN_HW_TAGS PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD) #else -PAGEFLAG_FALSE(SkipKASanPoison) +PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison) #endif /* @@ -517,10 +567,14 @@ static __always_inline int PageMappingFlags(struct page *page) return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0; } -static __always_inline int PageAnon(struct page *page) +static __always_inline bool folio_test_anon(struct folio *folio) +{ + return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0; +} + +static __always_inline bool PageAnon(struct page *page) { - page = compound_head(page); - return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; + return folio_test_anon(page_folio(page)); } static __always_inline int __PageMovable(struct page *page) @@ -536,30 +590,32 @@ static __always_inline int __PageMovable(struct page *page) * is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any * anon_vma, but to that page's node of the stable tree. */ -static __always_inline int PageKsm(struct page *page) +static __always_inline bool folio_test_ksm(struct folio *folio) { - page = compound_head(page); - return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) == + return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_KSM; } + +static __always_inline bool PageKsm(struct page *page) +{ + return folio_test_ksm(page_folio(page)); +} #else -TESTPAGEFLAG_FALSE(Ksm) +TESTPAGEFLAG_FALSE(Ksm, ksm) #endif u64 stable_page_flags(struct page *page); -static inline int PageUptodate(struct page *page) +static inline bool folio_test_uptodate(struct folio *folio) { - int ret; - page = compound_head(page); - ret = test_bit(PG_uptodate, &(page)->flags); + bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); /* - * Must ensure that the data we read out of the page is loaded - * _after_ we've loaded page->flags to check for PageUptodate. - * We can skip the barrier if the page is not uptodate, because + * Must ensure that the data we read out of the folio is loaded + * _after_ we've loaded folio->flags to check the uptodate bit. + * We can skip the barrier if the folio is not uptodate, because * we wouldn't be reading anything from it. * - * See SetPageUptodate() for the other side of the story. + * See folio_mark_uptodate() for the other side of the story. */ if (ret) smp_rmb(); @@ -567,23 +623,36 @@ static inline int PageUptodate(struct page *page) return ret; } -static __always_inline void __SetPageUptodate(struct page *page) +static inline int PageUptodate(struct page *page) +{ + return folio_test_uptodate(page_folio(page)); +} + +static __always_inline void __folio_mark_uptodate(struct folio *folio) { - VM_BUG_ON_PAGE(PageTail(page), page); smp_wmb(); - __set_bit(PG_uptodate, &page->flags); + __set_bit(PG_uptodate, folio_flags(folio, 0)); } -static __always_inline void SetPageUptodate(struct page *page) +static __always_inline void folio_mark_uptodate(struct folio *folio) { - VM_BUG_ON_PAGE(PageTail(page), page); /* * Memory barrier must be issued before setting the PG_uptodate bit, - * so that all previous stores issued in order to bring the page - * uptodate are actually visible before PageUptodate becomes true. + * so that all previous stores issued in order to bring the folio + * uptodate are actually visible before folio_test_uptodate becomes true. */ smp_wmb(); - set_bit(PG_uptodate, &page->flags); + set_bit(PG_uptodate, folio_flags(folio, 0)); +} + +static __always_inline void __SetPageUptodate(struct page *page) +{ + __folio_mark_uptodate((struct folio *)page); +} + +static __always_inline void SetPageUptodate(struct page *page) +{ + folio_mark_uptodate((struct folio *)page); } CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) @@ -608,6 +677,17 @@ static inline void set_page_writeback_keepwrite(struct page *page) __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) +/* Whether there are one or multiple pages in a folio */ +static inline bool folio_test_single(struct folio *folio) +{ + return !folio_test_head(folio); +} + +static inline bool folio_test_multi(struct folio *folio) +{ + return folio_test_head(folio); +} + static __always_inline void set_compound_head(struct page *page, struct page *head) { WRITE_ONCE(page->compound_head, (unsigned long)head + 1); @@ -631,12 +711,15 @@ static inline void ClearPageCompound(struct page *page) #ifdef CONFIG_HUGETLB_PAGE int PageHuge(struct page *page); int PageHeadHuge(struct page *page); +static inline bool folio_test_hugetlb(struct folio *folio) +{ + return PageHeadHuge(&folio->page); +} #else -TESTPAGEFLAG_FALSE(Huge) -TESTPAGEFLAG_FALSE(HeadHuge) +TESTPAGEFLAG_FALSE(Huge, hugetlb) +TESTPAGEFLAG_FALSE(HeadHuge, headhuge) #endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * PageHuge() only returns true for hugetlbfs pages, but not for @@ -652,6 +735,11 @@ static inline int PageTransHuge(struct page *page) return PageHead(page); } +static inline bool folio_test_transhuge(struct folio *folio) +{ + return folio_test_head(folio); +} + /* * PageTransCompound returns true for both transparent huge pages * and hugetlbfs pages, so it should only be called when it's known @@ -688,12 +776,12 @@ static inline int PageTransTail(struct page *page) PAGEFLAG(DoubleMap, double_map, PF_SECOND) TESTSCFLAG(DoubleMap, double_map, PF_SECOND) #else -TESTPAGEFLAG_FALSE(TransHuge) -TESTPAGEFLAG_FALSE(TransCompound) -TESTPAGEFLAG_FALSE(TransCompoundMap) -TESTPAGEFLAG_FALSE(TransTail) -PAGEFLAG_FALSE(DoubleMap) - TESTSCFLAG_FALSE(DoubleMap) +TESTPAGEFLAG_FALSE(TransHuge, transhuge) +TESTPAGEFLAG_FALSE(TransCompound, transcompound) +TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap) +TESTPAGEFLAG_FALSE(TransTail, transtail) +PAGEFLAG_FALSE(DoubleMap, double_map) + TESTSCFLAG_FALSE(DoubleMap, double_map) #endif /* @@ -877,6 +965,11 @@ static inline int page_has_private(struct page *page) return !!(page->flags & PAGE_FLAGS_PRIVATE); } +static inline bool folio_has_private(struct folio *folio) +{ + return page_has_private(&folio->page); +} + #undef PF_ANY #undef PF_HEAD #undef PF_ONLY_HEAD -- cgit v1.2.3 From 889a3747b3b7661b089ba4eae081a3b6bb351a23 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 25 Feb 2021 09:47:41 -0500 Subject: mm/lru: Add folio LRU functions Handle arbitrary-order folios being added to the LRU. By definition, all pages being added to the LRU were already head or base pages, but call page_folio() on them anyway to get the type right and avoid the buried calls to compound_head(). Saves 783 bytes of kernel text; no functions grow. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Yu Zhao Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Kirill A. Shutemov Acked-by: Mike Rapoport Acked-by: Vlastimil Babka --- Documentation/core-api/mm-api.rst | 1 + include/linux/mm_inline.h | 103 +++++++++++++++++++++++++------------- include/trace/events/pagemap.h | 2 +- 3 files changed, 69 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index 5c459ee2acce..971149f5d241 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -95,6 +95,7 @@ More Memory Management Functions .. kernel-doc:: mm/mempolicy.c .. kernel-doc:: include/linux/mm_types.h :internal: +.. kernel-doc:: include/linux/mm_inline.h .. kernel-doc:: include/linux/page-flags.h .. kernel-doc:: include/linux/mm.h :internal: diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 355ea1ee32bd..e2ec68b0515c 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -6,27 +6,33 @@ #include /** - * page_is_file_lru - should the page be on a file LRU or anon LRU? - * @page: the page to test - * - * Returns 1 if @page is a regular filesystem backed page cache page or a lazily - * freed anonymous page (e.g. via MADV_FREE). Returns 0 if @page is a normal - * anonymous page, a tmpfs page or otherwise ram or swap backed page. Used by - * functions that manipulate the LRU lists, to sort a page onto the right LRU - * list. + * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? + * @folio: The folio to test. * * We would like to get this info without a page flag, but the state - * needs to survive until the page is last deleted from the LRU, which + * needs to survive until the folio is last deleted from the LRU, which * could be as far down as __page_cache_release. + * + * Return: An integer (not a boolean!) used to sort a folio onto the + * right LRU list and to account folios correctly. + * 1 if @folio is a regular filesystem backed page cache folio + * or a lazily freed anonymous folio (e.g. via MADV_FREE). + * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise + * ram or swap backed folio. */ +static inline int folio_is_file_lru(struct folio *folio) +{ + return !folio_test_swapbacked(folio); +} + static inline int page_is_file_lru(struct page *page) { - return !PageSwapBacked(page); + return folio_is_file_lru(page_folio(page)); } static __always_inline void update_lru_size(struct lruvec *lruvec, enum lru_list lru, enum zone_type zid, - int nr_pages) + long nr_pages) { struct pglist_data *pgdat = lruvec_pgdat(lruvec); @@ -39,69 +45,94 @@ static __always_inline void update_lru_size(struct lruvec *lruvec, } /** - * __clear_page_lru_flags - clear page lru flags before releasing a page - * @page: the page that was on lru and now has a zero reference + * __folio_clear_lru_flags - Clear page lru flags before releasing a page. + * @folio: The folio that was on lru and now has a zero reference. */ -static __always_inline void __clear_page_lru_flags(struct page *page) +static __always_inline void __folio_clear_lru_flags(struct folio *folio) { - VM_BUG_ON_PAGE(!PageLRU(page), page); + VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio); - __ClearPageLRU(page); + __folio_clear_lru(folio); /* this shouldn't happen, so leave the flags to bad_page() */ - if (PageActive(page) && PageUnevictable(page)) + if (folio_test_active(folio) && folio_test_unevictable(folio)) return; - __ClearPageActive(page); - __ClearPageUnevictable(page); + __folio_clear_active(folio); + __folio_clear_unevictable(folio); +} + +static __always_inline void __clear_page_lru_flags(struct page *page) +{ + __folio_clear_lru_flags(page_folio(page)); } /** - * page_lru - which LRU list should a page be on? - * @page: the page to test + * folio_lru_list - Which LRU list should a folio be on? + * @folio: The folio to test. * - * Returns the LRU list a page should be on, as an index + * Return: The LRU list a folio should be on, as an index * into the array of LRU lists. */ -static __always_inline enum lru_list page_lru(struct page *page) +static __always_inline enum lru_list folio_lru_list(struct folio *folio) { enum lru_list lru; - VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); + VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); - if (PageUnevictable(page)) + if (folio_test_unevictable(folio)) return LRU_UNEVICTABLE; - lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; - if (PageActive(page)) + lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON; + if (folio_test_active(folio)) lru += LRU_ACTIVE; return lru; } +static __always_inline +void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio) +{ + enum lru_list lru = folio_lru_list(folio); + + update_lru_size(lruvec, lru, folio_zonenum(folio), + folio_nr_pages(folio)); + list_add(&folio->lru, &lruvec->lists[lru]); +} + static __always_inline void add_page_to_lru_list(struct page *page, struct lruvec *lruvec) { - enum lru_list lru = page_lru(page); + lruvec_add_folio(lruvec, page_folio(page)); +} - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add(&page->lru, &lruvec->lists[lru]); +static __always_inline +void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio) +{ + enum lru_list lru = folio_lru_list(folio); + + update_lru_size(lruvec, lru, folio_zonenum(folio), + folio_nr_pages(folio)); + list_add_tail(&folio->lru, &lruvec->lists[lru]); } static __always_inline void add_page_to_lru_list_tail(struct page *page, struct lruvec *lruvec) { - enum lru_list lru = page_lru(page); + lruvec_add_folio_tail(lruvec, page_folio(page)); +} - update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page)); - list_add_tail(&page->lru, &lruvec->lists[lru]); +static __always_inline +void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio) +{ + list_del(&folio->lru); + update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio), + -folio_nr_pages(folio)); } static __always_inline void del_page_from_lru_list(struct page *page, struct lruvec *lruvec) { - list_del(&page->lru); - update_lru_size(lruvec, page_lru(page), page_zonenum(page), - -thp_nr_pages(page)); + lruvec_del_folio(lruvec, page_folio(page)); } #endif diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 1d28431e85bd..92ad176210ff 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -41,7 +41,7 @@ TRACE_EVENT(mm_lru_insertion, TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); - __entry->lru = page_lru(page); + __entry->lru = folio_lru_list(page_folio(page)); __entry->flags = trace_pagemap_flags(page); ), -- cgit v1.2.3 From 85d0a2ed3747da7f9aedacb72478bbedf06f9f2e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 11 Jan 2021 10:04:40 -0500 Subject: mm: Handle per-folio private data Add folio_get_private() which mirrors page_private() -- ie folio private data is the same as page private data. The only difference is that these return a void * instead of an unsigned long, which matches the majority of users. Turn attach_page_private() into folio_attach_private() and reimplement attach_page_private() as a wrapper. No filesystem which uses page private data currently supports compound pages, so we're free to define the rules. attach_page_private() may only be called on a head page; if you want to add private data to a tail page, you can call set_page_private() directly (and shouldn't increment the page refcount! That should be done when adding private data to the head page / folio). This saves 813 bytes of text with the distro-derived config that I'm testing due to removing the calls to compound_head() in get_page() & put_page(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/mm_types.h | 11 +++++++++++ include/linux/pagemap.h | 48 +++++++++++++++++++++++++++++------------------- 2 files changed, 40 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6908186629b4..5ebcb86ac934 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -317,6 +317,12 @@ static inline atomic_t *compound_pincount_ptr(struct page *page) #define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) #define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +/* + * page_private can be used on tail pages. However, PagePrivate is only + * checked by the VM on the head page. So page_private on the tail pages + * should be used for data that's ancillary to the head page (eg attaching + * buffer heads to tail pages after attaching buffer heads to the head page) + */ #define page_private(page) ((page)->private) static inline void set_page_private(struct page *page, unsigned long private) @@ -324,6 +330,11 @@ static inline void set_page_private(struct page *page, unsigned long private) page->private = private; } +static inline void *folio_get_private(struct folio *folio) +{ + return folio->private; +} + struct page_frag_cache { void * va; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index f3ec26551082..b0f5bf1cb540 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -184,42 +184,52 @@ static inline bool page_cache_get_speculative(struct page *page) } /** - * attach_page_private - Attach private data to a page. - * @page: Page to attach data to. - * @data: Data to attach to page. + * folio_attach_private - Attach private data to a folio. + * @folio: Folio to attach data to. + * @data: Data to attach to folio. * - * Attaching private data to a page increments the page's reference count. - * The data must be detached before the page will be freed. + * Attaching private data to a folio increments the page's reference count. + * The data must be detached before the folio will be freed. */ -static inline void attach_page_private(struct page *page, void *data) +static inline void folio_attach_private(struct folio *folio, void *data) { - get_page(page); - set_page_private(page, (unsigned long)data); - SetPagePrivate(page); + folio_get(folio); + folio->private = data; + folio_set_private(folio); } /** - * detach_page_private - Detach private data from a page. - * @page: Page to detach data from. + * folio_detach_private - Detach private data from a folio. + * @folio: Folio to detach data from. * - * Removes the data that was previously attached to the page and decrements + * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * - * Return: Data that was attached to the page. + * Return: Data that was attached to the folio. */ -static inline void *detach_page_private(struct page *page) +static inline void *folio_detach_private(struct folio *folio) { - void *data = (void *)page_private(page); + void *data = folio_get_private(folio); - if (!PagePrivate(page)) + if (!folio_test_private(folio)) return NULL; - ClearPagePrivate(page); - set_page_private(page, 0); - put_page(page); + folio_clear_private(folio); + folio->private = NULL; + folio_put(folio); return data; } +static inline void attach_page_private(struct page *page, void *data) +{ + folio_attach_private(page_folio(page), data); +} + +static inline void *detach_page_private(struct page *page) +{ + return folio_detach_private(page_folio(page)); +} + #ifdef CONFIG_NUMA extern struct page *__page_cache_alloc(gfp_t gfp); #else -- cgit v1.2.3 From 9257e15677384d1ccdfe0619c4455e34cb0342c7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 15 Jan 2021 23:39:21 -0500 Subject: mm/filemap: Add folio_index(), folio_file_page() and folio_contains() folio_index() is the equivalent of page_index() for folios. folio_file_page() is the equivalent of find_subpage(). folio_contains() is the equivalent of thp_contains(). No changes to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/pagemap.h | 56 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b0f5bf1cb540..e7b46223239a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -386,6 +386,62 @@ static inline bool thp_contains(struct page *head, pgoff_t index) return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); } +#define swapcache_index(folio) __page_file_index(&(folio)->page) + +/** + * folio_index - File index of a folio. + * @folio: The folio. + * + * For a folio which is either in the page cache or the swap cache, + * return its index within the address_space it belongs to. If you know + * the page is definitely in the page cache, you can look at the folio's + * index directly. + * + * Return: The index (offset in units of pages) of a folio in its file. + */ +static inline pgoff_t folio_index(struct folio *folio) +{ + if (unlikely(folio_test_swapcache(folio))) + return swapcache_index(folio); + return folio->index; +} + +/** + * folio_file_page - The page for a particular index. + * @folio: The folio which contains this index. + * @index: The index we want to look up. + * + * Sometimes after looking up a folio in the page cache, we need to + * obtain the specific page for an index (eg a page fault). + * + * Return: The page containing the file data for this index. + */ +static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) +{ + /* HugeTLBfs indexes the page cache in units of hpage_size */ + if (folio_test_hugetlb(folio)) + return &folio->page; + return folio_page(folio, index & (folio_nr_pages(folio) - 1)); +} + +/** + * folio_contains - Does this folio contain this index? + * @folio: The folio. + * @index: The page index within the file. + * + * Context: The caller should have the page locked in order to prevent + * (eg) shmem from moving the page between the page cache and swap cache + * and changing its index in the middle of the operation. + * Return: true or false. + */ +static inline bool folio_contains(struct folio *folio, pgoff_t index) +{ + /* HugeTLBfs indexes the page cache in units of hpage_size */ + if (folio_test_hugetlb(folio)) + return folio->index == index; + return index - folio_index(folio) < folio_nr_pages(folio); +} + /* * Given the page we found in the page cache, return the page corresponding * to this index in the file -- cgit v1.2.3 From f94b18f6653ab6d3aa503213c2e1e79b18f05a30 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 21 Mar 2021 16:24:31 -0400 Subject: mm/filemap: Add folio_next_index() This helper returns the page index of the next folio in the file (ie the end of this folio, plus one). No changes to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/pagemap.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e7b46223239a..95e83a9e73c7 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -406,6 +406,17 @@ static inline pgoff_t folio_index(struct folio *folio) return folio->index; } +/** + * folio_next_index - Get the index of the next folio. + * @folio: The current folio. + * + * Return: The index of the folio which follows this folio in the file. + */ +static inline pgoff_t folio_next_index(struct folio *folio) +{ + return folio->index + folio_nr_pages(folio); +} + /** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. -- cgit v1.2.3 From 352b47a6984470954e1e262126b1da5312c40b09 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 24 Dec 2020 07:25:19 -0500 Subject: mm/filemap: Add folio_pos() and folio_file_pos() These are just wrappers around page_offset() and page_file_offset() respectively. No change to generated code. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells --- include/linux/pagemap.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 95e83a9e73c7..3354117a1dae 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -561,6 +561,27 @@ static inline loff_t page_file_offset(struct page *page) return ((loff_t)page_index(page)) << PAGE_SHIFT; } +/** + * folio_pos - Returns the byte position of this folio in its file. + * @folio: The folio. + */ +static inline loff_t folio_pos(struct folio *folio) +{ + return page_offset(&folio->page); +} + +/** + * folio_file_pos - Returns the byte position of this folio in its file. + * @folio: The folio. + * + * This differs from folio_pos() for folios which belong to a swap file. + * NFS is the only filesystem today which needs to use folio_file_pos(). + */ +static inline loff_t folio_file_pos(struct folio *folio) +{ + return page_file_offset(&folio->page); +} + extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma, unsigned long address); -- cgit v1.2.3 From 2f52578f9c64d7d9a96ab81c243cc20804fabf2b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 10 Dec 2020 10:55:05 -0500 Subject: mm/util: Add folio_mapping() and folio_file_mapping() These are the folio equivalent of page_mapping() and page_file_mapping(). Add an out-of-line page_mapping() wrapper around folio_mapping() in order to prevent the page_folio() call from bloating every caller of page_mapping(). Adjust page_file_mapping() and page_mapping_file() to use folios internally. Rename __page_file_mapping() to swapcache_mapping() and change it to take a folio. This ends up saving 122 bytes of text overall. folio_mapping() is 45 bytes shorter than page_mapping() was, but the new page_mapping() wrapper is 30 bytes. The major reduction is a few bytes less in dozens of nfs functions (which call page_file_mapping()). Most of these appear to be a slight change in gcc's register allocation decisions, which allow: 48 8b 56 08 mov 0x8(%rsi),%rdx 48 8d 42 ff lea -0x1(%rdx),%rax 83 e2 01 and $0x1,%edx 48 0f 44 c6 cmove %rsi,%rax to become: 48 8b 46 08 mov 0x8(%rsi),%rax 48 8d 78 ff lea -0x1(%rax),%rdi a8 01 test $0x1,%al 48 0f 44 fe cmove %rsi,%rdi for a reduction of a single byte. Once the NFS client is converted to use folios, this entire sequence will disappear. Also add folio_mapping() documentation. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells --- Documentation/core-api/mm-api.rst | 2 ++ include/linux/mm.h | 14 -------------- include/linux/pagemap.h | 35 +++++++++++++++++++++++++++++++++-- include/linux/swap.h | 6 ++++++ mm/Makefile | 2 +- mm/folio-compat.c | 13 +++++++++++++ mm/swapfile.c | 8 ++++---- mm/util.c | 30 ++++++++++++++++++------------ 8 files changed, 77 insertions(+), 33 deletions(-) create mode 100644 mm/folio-compat.c (limited to 'include/linux') diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index 971149f5d241..395835f9289f 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -101,3 +101,5 @@ More Memory Management Functions :internal: .. kernel-doc:: include/linux/page_ref.h .. kernel-doc:: include/linux/mmzone.h +.. kernel-doc:: mm/util.c + :functions: folio_mapping diff --git a/include/linux/mm.h b/include/linux/mm.h index 63685d953ce0..bc5c38e1f780 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1755,19 +1755,6 @@ void page_address_init(void); extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); -extern struct address_space *page_mapping(struct page *page); - -extern struct address_space *__page_file_mapping(struct page *); - -static inline -struct address_space *page_file_mapping(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return __page_file_mapping(page); - - return page->mapping; -} - extern pgoff_t __page_file_index(struct page *page); /* @@ -1782,7 +1769,6 @@ static inline pgoff_t page_index(struct page *page) } bool page_mapped(struct page *page); -struct address_space *page_mapping(struct page *page); /* * Return true only if the page has been allocated with diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3354117a1dae..0ca96a40fabe 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -162,14 +162,45 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping) void release_pages(struct page **pages, int nr); +struct address_space *page_mapping(struct page *); +struct address_space *folio_mapping(struct folio *); +struct address_space *swapcache_mapping(struct folio *); + +/** + * folio_file_mapping - Find the mapping this folio belongs to. + * @folio: The folio. + * + * For folios which are in the page cache, return the mapping that this + * page belongs to. Folios in the swap cache return the mapping of the + * swap file or swap device where the data is stored. This is different + * from the mapping returned by folio_mapping(). The only reason to + * use it is if, like NFS, you return 0 from ->activate_swapfile. + * + * Do not call this for folios which aren't in the page cache or swap cache. + */ +static inline struct address_space *folio_file_mapping(struct folio *folio) +{ + if (unlikely(folio_test_swapcache(folio))) + return swapcache_mapping(folio); + + return folio->mapping; +} + +static inline struct address_space *page_file_mapping(struct page *page) +{ + return folio_file_mapping(page_folio(page)); +} + /* * For file cache pages, return the address_space, otherwise return NULL */ static inline struct address_space *page_mapping_file(struct page *page) { - if (unlikely(PageSwapCache(page))) + struct folio *folio = page_folio(page); + + if (unlikely(folio_test_swapcache(folio))) return NULL; - return page_mapping(page); + return folio_mapping(folio); } static inline bool page_cache_add_speculative(struct page *page, int count) diff --git a/include/linux/swap.h b/include/linux/swap.h index ba52f3a3478e..85607c6c0cba 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -320,6 +320,12 @@ struct vma_swap_readahead { #endif }; +static inline swp_entry_t folio_swap_entry(struct folio *folio) +{ + swp_entry_t entry = { .val = page_private(&folio->page) }; + return entry; +} + /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); diff --git a/mm/Makefile b/mm/Makefile index fc60a40ce954..d6c0042e3aa0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -46,7 +46,7 @@ mmu-$(CONFIG_MMU) += process_vm_access.o endif obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ - maccess.o page-writeback.o \ + maccess.o page-writeback.o folio-compat.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o percpu.o slab_common.o \ diff --git a/mm/folio-compat.c b/mm/folio-compat.c new file mode 100644 index 000000000000..5e107aa30a62 --- /dev/null +++ b/mm/folio-compat.c @@ -0,0 +1,13 @@ +/* + * Compatibility functions which bloat the callers too much to make inline. + * All of the callers of these functions should be converted to use folios + * eventually. + */ + +#include + +struct address_space *page_mapping(struct page *page) +{ + return folio_mapping(page_folio(page)); +} +EXPORT_SYMBOL(page_mapping); diff --git a/mm/swapfile.c b/mm/swapfile.c index 22d10f713848..e3dcaeecc50f 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -3534,13 +3534,13 @@ struct swap_info_struct *page_swap_info(struct page *page) } /* - * out-of-line __page_file_ methods to avoid include hell. + * out-of-line methods to avoid include hell. */ -struct address_space *__page_file_mapping(struct page *page) +struct address_space *swapcache_mapping(struct folio *folio) { - return page_swap_info(page)->swap_file->f_mapping; + return page_swap_info(&folio->page)->swap_file->f_mapping; } -EXPORT_SYMBOL_GPL(__page_file_mapping); +EXPORT_SYMBOL_GPL(swapcache_mapping); pgoff_t __page_file_index(struct page *page) { diff --git a/mm/util.c b/mm/util.c index bacabe446906..6c1fe9bee30a 100644 --- a/mm/util.c +++ b/mm/util.c @@ -705,30 +705,36 @@ struct anon_vma *page_anon_vma(struct page *page) return __page_rmapping(page); } -struct address_space *page_mapping(struct page *page) +/** + * folio_mapping - Find the mapping where this folio is stored. + * @folio: The folio. + * + * For folios which are in the page cache, return the mapping that this + * page belongs to. Folios in the swap cache return the swap mapping + * this page is stored in (which is different from the mapping for the + * swap file or swap device where the data is stored). + * + * You can call this for folios which aren't in the swap cache or page + * cache and it will return NULL. + */ +struct address_space *folio_mapping(struct folio *folio) { struct address_space *mapping; - page = compound_head(page); - /* This happens if someone calls flush_dcache_page on slab page */ - if (unlikely(PageSlab(page))) + if (unlikely(folio_test_slab(folio))) return NULL; - if (unlikely(PageSwapCache(page))) { - swp_entry_t entry; - - entry.val = page_private(page); - return swap_address_space(entry); - } + if (unlikely(folio_test_swapcache(folio))) + return swap_address_space(folio_swap_entry(folio)); - mapping = page->mapping; + mapping = folio->mapping; if ((unsigned long)mapping & PAGE_MAPPING_ANON) return NULL; return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); } -EXPORT_SYMBOL(page_mapping); +EXPORT_SYMBOL(folio_mapping); /* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) -- cgit v1.2.3 From 4e1364286d0a2dd384bceb6db6185b99c0e2c0bc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 7 Dec 2020 15:44:35 -0500 Subject: mm/filemap: Add folio_unlock() Convert unlock_page() to call folio_unlock(). By using a folio we avoid a call to compound_head(). This shortens the function from 39 bytes to 25 and removes 4 instructions on x86-64. Because we still have unlock_page(), it's a net increase of 16 bytes of text for the kernel as a whole, but any path that uses folio_unlock() will execute 4 fewer instructions. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 3 ++- mm/filemap.c | 29 ++++++++++++----------------- mm/folio-compat.c | 6 ++++++ 3 files changed, 20 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0ca96a40fabe..8087921641a3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -657,7 +657,8 @@ extern int __lock_page_killable(struct page *page); extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); -extern void unlock_page(struct page *page); +void unlock_page(struct page *page); +void folio_unlock(struct folio *folio); /* * Return true if the page was successfully locked diff --git a/mm/filemap.c b/mm/filemap.c index 9fcc3d94cfcd..191d7d39e838 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1490,29 +1490,24 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem #endif /** - * unlock_page - unlock a locked page - * @page: the page + * folio_unlock - Unlock a locked folio. + * @folio: The folio. * - * Unlocks the page and wakes up sleepers in wait_on_page_locked(). - * Also wakes sleepers in wait_on_page_writeback() because the wakeup - * mechanism between PageLocked pages and PageWriteback pages is shared. - * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep. + * Unlocks the folio and wakes up any thread sleeping on the page lock. * - * Note that this depends on PG_waiters being the sign bit in the byte - * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to - * clear the PG_locked bit and test PG_waiters at the same time fairly - * portably (architectures that do LL/SC can test any bit, while x86 can - * test the sign bit). + * Context: May be called from interrupt or process context. May not be + * called from NMI context. */ -void unlock_page(struct page *page) +void folio_unlock(struct folio *folio) { + /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); - page = compound_head(page); - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags)) - wake_up_page_bit(page, PG_locked); + BUILD_BUG_ON(PG_locked > 7); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0))) + wake_up_page_bit(&folio->page, PG_locked); } -EXPORT_SYMBOL(unlock_page); +EXPORT_SYMBOL(folio_unlock); /** * end_page_private_2 - Clear PG_private_2 and release any waiters diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 5e107aa30a62..91b3d00a92f7 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -11,3 +11,9 @@ struct address_space *page_mapping(struct page *page) return folio_mapping(page_folio(page)); } EXPORT_SYMBOL(page_mapping); + +void unlock_page(struct page *page) +{ + return folio_unlock(page_folio(page)); +} +EXPORT_SYMBOL(unlock_page); -- cgit v1.2.3 From 7c23c782d5d57df97509ed2fc17f9b9490f18f1b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 1 Mar 2021 19:38:25 -0500 Subject: mm/filemap: Add folio_lock() This is like lock_page() but for use by callers who know they have a folio. Convert __lock_page() to be __folio_lock(). This saves one call to compound_head() per contended call to lock_page(). Saves 455 bytes of text; mostly from improved register allocation and inlining decisions. __folio_lock is 59 bytes while __lock_page was 79. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/pagemap.h | 24 +++++++++++++++++++----- mm/filemap.c | 29 +++++++++++++++-------------- 2 files changed, 34 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8087921641a3..6481a431ea40 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -652,7 +652,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, return true; } -extern void __lock_page(struct page *page); +void __folio_lock(struct folio *folio); extern int __lock_page_killable(struct page *page); extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, @@ -660,13 +660,24 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, void unlock_page(struct page *page); void folio_unlock(struct folio *folio); +static inline bool folio_trylock(struct folio *folio) +{ + return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); +} + /* * Return true if the page was successfully locked */ static inline int trylock_page(struct page *page) { - page = compound_head(page); - return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); + return folio_trylock(page_folio(page)); +} + +static inline void folio_lock(struct folio *folio) +{ + might_sleep(); + if (!folio_trylock(folio)) + __folio_lock(folio); } /* @@ -674,9 +685,12 @@ static inline int trylock_page(struct page *page) */ static inline void lock_page(struct page *page) { + struct folio *folio; might_sleep(); - if (!trylock_page(page)) - __lock_page(page); + + folio = page_folio(page); + if (!folio_trylock(folio)) + __folio_lock(folio); } /* diff --git a/mm/filemap.c b/mm/filemap.c index 191d7d39e838..a1d3f67e1b49 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1242,7 +1242,7 @@ static void wake_up_page(struct page *page, int bit) */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like - * __lock_page() waiting on then setting PG_locked. + * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * wait_on_page_writeback() waiting on PG_writeback. @@ -1633,17 +1633,16 @@ void page_endio(struct page *page, bool is_write, int err) EXPORT_SYMBOL_GPL(page_endio); /** - * __lock_page - get a lock on the page, assuming we need to sleep to get it - * @__page: the page to lock + * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. + * @folio: The folio to lock */ -void __lock_page(struct page *__page) +void __folio_lock(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, + wait_queue_head_t *q = page_waitqueue(&folio->page); + wait_on_page_bit_common(q, &folio->page, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } -EXPORT_SYMBOL(__lock_page); +EXPORT_SYMBOL(__folio_lock); int __lock_page_killable(struct page *__page) { @@ -1718,10 +1717,10 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, return 0; } } else { - __lock_page(page); + __folio_lock(page_folio(page)); } - return 1; + return 1; } /** @@ -2915,7 +2914,9 @@ unlock: static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, struct file **fpin) { - if (trylock_page(page)) + struct folio *folio = page_folio(page); + + if (folio_trylock(folio)) return 1; /* @@ -2928,7 +2929,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { - if (__lock_page_killable(page)) { + if (__lock_page_killable(&folio->page)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals @@ -2940,11 +2941,11 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, return 0; } } else - __lock_page(page); + __folio_lock(folio); + return 1; } - /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have -- cgit v1.2.3 From af7f29d9e1a7bda1429923327421367b69aa2e70 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Dec 2020 00:07:31 -0500 Subject: mm/filemap: Add folio_lock_killable() This is like lock_page_killable() but for use by callers who know they have a folio. Convert __lock_page_killable() to be __folio_lock_killable(). This saves one call to compound_head() per contended call to lock_page_killable(). __folio_lock_killable() is 19 bytes smaller than __lock_page_killable() was. filemap_fault() shrinks by 74 bytes and __lock_page_or_retry() shrinks by 71 bytes. That's a total of 164 bytes of text saved. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Acked-by: Mike Rapoport Reviewed-by: David Howells --- include/linux/pagemap.h | 15 ++++++++++----- mm/filemap.c | 17 +++++++++-------- 2 files changed, 19 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6481a431ea40..cf0ebd8c9e86 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -653,7 +653,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, } void __folio_lock(struct folio *folio); -extern int __lock_page_killable(struct page *page); +int __folio_lock_killable(struct folio *folio); extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); @@ -693,6 +693,14 @@ static inline void lock_page(struct page *page) __folio_lock(folio); } +static inline int folio_lock_killable(struct folio *folio) +{ + might_sleep(); + if (!folio_trylock(folio)) + return __folio_lock_killable(folio); + return 0; +} + /* * lock_page_killable is like lock_page but can be interrupted by fatal * signals. It returns 0 if it locked the page and -EINTR if it was @@ -700,10 +708,7 @@ static inline void lock_page(struct page *page) */ static inline int lock_page_killable(struct page *page) { - might_sleep(); - if (!trylock_page(page)) - return __lock_page_killable(page); - return 0; + return folio_lock_killable(page_folio(page)); } /* diff --git a/mm/filemap.c b/mm/filemap.c index a1d3f67e1b49..17803f785a34 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1644,14 +1644,13 @@ void __folio_lock(struct folio *folio) } EXPORT_SYMBOL(__folio_lock); -int __lock_page_killable(struct page *__page) +int __folio_lock_killable(struct folio *folio) { - struct page *page = compound_head(__page); - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, + wait_queue_head_t *q = page_waitqueue(&folio->page); + return wait_on_page_bit_common(q, &folio->page, PG_locked, TASK_KILLABLE, EXCLUSIVE); } -EXPORT_SYMBOL_GPL(__lock_page_killable); +EXPORT_SYMBOL_GPL(__folio_lock_killable); int __lock_page_async(struct page *page, struct wait_page_queue *wait) { @@ -1693,6 +1692,8 @@ int __lock_page_async(struct page *page, struct wait_page_queue *wait) int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { + struct folio *folio = page_folio(page); + if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock is not released @@ -1711,13 +1712,13 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, if (flags & FAULT_FLAG_KILLABLE) { int ret; - ret = __lock_page_killable(page); + ret = __folio_lock_killable(folio); if (ret) { mmap_read_unlock(mm); return 0; } } else { - __folio_lock(page_folio(page)); + __folio_lock(folio); } return 1; @@ -2929,7 +2930,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page, *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { - if (__lock_page_killable(&folio->page)) { + if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the mmap_lock, * but all fault_handlers only check for fatal signals -- cgit v1.2.3 From ffdc8dabf20b1b894eda63e7ec9ca15ab0b7292c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 30 Dec 2020 17:58:40 -0500 Subject: mm/filemap: Add __folio_lock_async() There aren't any actual callers of lock_page_async(), so remove it. Convert filemap_update_page() to call __folio_lock_async(). __folio_lock_async() is 21 bytes smaller than __lock_page_async(), but the real savings come from using a folio in filemap_update_page(), shrinking it from 515 bytes to 404 bytes, saving 110 bytes. The text shrinks by 132 bytes in total. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- fs/io_uring.c | 2 +- include/linux/pagemap.h | 17 ----------------- mm/filemap.c | 27 ++++++++++++++------------- 3 files changed, 15 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 82f867983bb3..2c913698e428 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -3364,7 +3364,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) } /* - * This is our waitqueue callback handler, registered through lock_page_async() + * This is our waitqueue callback handler, registered through __folio_lock_async() * when we initially tried to do the IO with the iocb armed our waitqueue. * This gets called when the page is unlocked, and we generally expect that to * happen when the page IO is completed and the page is now uptodate. This will diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf0ebd8c9e86..5b5e8bd0b3fb 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -654,7 +654,6 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); -extern int __lock_page_async(struct page *page, struct wait_page_queue *wait); extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags); void unlock_page(struct page *page); @@ -711,22 +710,6 @@ static inline int lock_page_killable(struct page *page) return folio_lock_killable(page_folio(page)); } -/* - * lock_page_async - Lock the page, unless this would block. If the page - * is already locked, then queue a callback when the page becomes unlocked. - * This callback can then retry the operation. - * - * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page - * was already locked and the callback defined in 'wait' was queued. - */ -static inline int lock_page_async(struct page *page, - struct wait_page_queue *wait) -{ - if (!trylock_page(page)) - return __lock_page_async(page, wait); - return 0; -} - /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. diff --git a/mm/filemap.c b/mm/filemap.c index 17803f785a34..655145d27fff 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1652,18 +1652,18 @@ int __folio_lock_killable(struct folio *folio) } EXPORT_SYMBOL_GPL(__folio_lock_killable); -int __lock_page_async(struct page *page, struct wait_page_queue *wait) +static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { - struct wait_queue_head *q = page_waitqueue(page); + struct wait_queue_head *q = page_waitqueue(&folio->page); int ret = 0; - wait->page = page; + wait->page = &folio->page; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); - SetPageWaiters(page); - ret = !trylock_page(page); + folio_set_waiters(folio); + ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's @@ -2436,6 +2436,7 @@ static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, struct iov_iter *iter, struct page *page) { + struct folio *folio = page_folio(page); int error; if (iocb->ki_flags & IOCB_NOWAIT) { @@ -2445,40 +2446,40 @@ static int filemap_update_page(struct kiocb *iocb, filemap_invalidate_lock_shared(mapping); } - if (!trylock_page(page)) { + if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); - put_and_wait_on_page_locked(page, TASK_KILLABLE); + put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } - error = __lock_page_async(page, iocb->ki_waitq); + error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; - if (!page->mapping) + if (!folio->mapping) goto unlock; error = 0; - if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page)) + if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, &folio->page)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; - error = filemap_read_page(iocb->ki_filp, mapping, page); + error = filemap_read_page(iocb->ki_filp, mapping, &folio->page); goto unlock_mapping; unlock: - unlock_page(page); + folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) - put_page(page); + folio_put(folio); return error; } -- cgit v1.2.3 From 6baa8d602e84d97a7541ed94ccaeb6a3f9763111 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 4 Mar 2021 10:21:02 -0500 Subject: mm/filemap: Add folio_wait_locked() Also add folio_wait_locked_killable(). Turn wait_on_page_locked() and wait_on_page_locked_killable() into wrappers. This eliminates a call to compound_head() from each call-site, reducing text size by 193 bytes for me. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/pagemap.h | 26 ++++++++++++++++++-------- mm/filemap.c | 4 ++-- 2 files changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 5b5e8bd0b3fb..77dbb7f625af 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -732,23 +732,33 @@ extern void wait_on_page_bit(struct page *page, int bit_nr); extern int wait_on_page_bit_killable(struct page *page, int bit_nr); /* - * Wait for a page to be unlocked. + * Wait for a folio to be unlocked. * - * This must be called with the caller "holding" the page, - * ie with increased "page->count" so that the page won't + * This must be called with the caller "holding" the folio, + * ie with increased "page->count" so that the folio won't * go away during the wait.. */ +static inline void folio_wait_locked(struct folio *folio) +{ + if (folio_test_locked(folio)) + wait_on_page_bit(&folio->page, PG_locked); +} + +static inline int folio_wait_locked_killable(struct folio *folio) +{ + if (!folio_test_locked(folio)) + return 0; + return wait_on_page_bit_killable(&folio->page, PG_locked); +} + static inline void wait_on_page_locked(struct page *page) { - if (PageLocked(page)) - wait_on_page_bit(compound_head(page), PG_locked); + folio_wait_locked(page_folio(page)); } static inline int wait_on_page_locked_killable(struct page *page) { - if (!PageLocked(page)) - return 0; - return wait_on_page_bit_killable(compound_head(page), PG_locked); + return folio_wait_locked_killable(page_folio(page)); } int put_and_wait_on_page_locked(struct page *page, int state); diff --git a/mm/filemap.c b/mm/filemap.c index 655145d27fff..b17b58c29ed7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1704,9 +1704,9 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) - wait_on_page_locked_killable(page); + folio_wait_locked_killable(folio); else - wait_on_page_locked(page); + folio_wait_locked(folio); return 0; } if (flags & FAULT_FLAG_KILLABLE) { -- cgit v1.2.3 From 9138e47ed425246102317dbe452f7f0d4a54c4a2 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 18 Mar 2021 21:39:45 -0400 Subject: mm/filemap: Add __folio_lock_or_retry() Convert __lock_page_or_retry() to __folio_lock_or_retry(). This actually saves 4 bytes in the only caller of lock_page_or_retry() (due to better register allocation) and saves the 14 byte cost of calling page_folio() in __folio_lock_or_retry() for a total saving of 18 bytes. Also use a bool for the return type. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Reviewed-by: William Kucharski Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 11 +++++++---- mm/filemap.c | 22 ++++++++++------------ mm/memory.c | 8 ++++---- 3 files changed, 21 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 77dbb7f625af..7cf140f98910 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -654,7 +654,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page, void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); -extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm, +bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, unsigned int flags); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); @@ -715,13 +715,16 @@ static inline int lock_page_killable(struct page *page) * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see - * __lock_page_or_retry(). + * __folio_lock_or_retry(). */ -static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, +static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) { + struct folio *folio; might_sleep(); - return trylock_page(page) || __lock_page_or_retry(page, mm, flags); + + folio = page_folio(page); + return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags); } /* diff --git a/mm/filemap.c b/mm/filemap.c index b17b58c29ed7..706d121ca9cc 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1680,48 +1680,46 @@ static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) /* * Return values: - * 1 - page is locked; mmap_lock is still held. - * 0 - page is not locked. + * true - folio is locked; mmap_lock is still held. + * false - folio is not locked. * mmap_lock has been released (mmap_read_unlock(), unless flags had both * FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in * which case mmap_lock is still held. * - * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1 - * with the page locked and the mmap_lock unperturbed. + * If neither ALLOW_RETRY nor KILLABLE are set, will always return true + * with the folio locked and the mmap_lock unperturbed. */ -int __lock_page_or_retry(struct page *page, struct mm_struct *mm, +bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm, unsigned int flags) { - struct folio *folio = page_folio(page); - if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock is not released * even though return 0. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) - return 0; + return false; mmap_read_unlock(mm); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); - return 0; + return false; } if (flags & FAULT_FLAG_KILLABLE) { - int ret; + bool ret; ret = __folio_lock_killable(folio); if (ret) { mmap_read_unlock(mm); - return 0; + return false; } } else { __folio_lock(folio); } - return 1; + return true; } /** diff --git a/mm/memory.c b/mm/memory.c index adf9b9ef8277..269992ba3fa3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4258,7 +4258,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf) * We enter with non-exclusive mmap_lock (to exclude vma changes, * but allow concurrent faults). * The mmap_lock may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * return value. See filemap_fault() and __folio_lock_or_retry(). * If mmap_lock is released, vma may become invalid (for example * by other thread calling munmap()). */ @@ -4499,7 +4499,7 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud) * concurrent faults). * * The mmap_lock may have been released depending on flags and our return value. - * See filemap_fault() and __lock_page_or_retry(). + * See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) { @@ -4603,7 +4603,7 @@ unlock: * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * return value. See filemap_fault() and __folio_lock_or_retry(). */ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags) @@ -4759,7 +4759,7 @@ static inline void mm_account_fault(struct pt_regs *regs, * By the time we get here, we already hold the mm semaphore * * The mmap_lock may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). + * return value. See filemap_fault() and __folio_lock_or_retry(). */ vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct pt_regs *regs) -- cgit v1.2.3 From 575ced1c8b0d3b578b933a68ce67ddaff3df9506 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Dec 2020 01:25:39 -0500 Subject: mm/swap: Add folio_rotate_reclaimable() Convert rotate_reclaimable_page() to folio_rotate_reclaimable(). This eliminates all five of the calls to compound_head() in this function, saving 75 bytes at the cost of adding 15 bytes to its one caller, end_page_writeback(). We also save 36 bytes from pagevec_move_tail_fn() due to using folios there. Net 96 bytes savings. Also move its declaration to mm/internal.h as it's only used by filemap.c. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Acked-by: Kirill A. Shutemov Acked-by: Mike Rapoport Reviewed-by: David Howells --- include/linux/swap.h | 1 - mm/filemap.c | 3 ++- mm/internal.h | 1 + mm/page_io.c | 4 ++-- mm/swap.c | 30 ++++++++++++++++-------------- 5 files changed, 21 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 85607c6c0cba..c7ecd3ad8e2e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -371,7 +371,6 @@ extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); -extern void rotate_reclaimable_page(struct page *page); extern void deactivate_file_page(struct page *page); extern void deactivate_page(struct page *page); extern void mark_page_lazyfree(struct page *page); diff --git a/mm/filemap.c b/mm/filemap.c index 706d121ca9cc..6a5bdb4f7c73 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1584,8 +1584,9 @@ void end_page_writeback(struct page *page) * ever page writeback. */ if (PageReclaim(page)) { + struct folio *folio = page_folio(page); ClearPageReclaim(page); - rotate_reclaimable_page(page); + folio_rotate_reclaimable(folio); } /* diff --git a/mm/internal.h b/mm/internal.h index cf3cb933eba3..1a84484f8650 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -35,6 +35,7 @@ void page_writeback_init(void); vm_fault_t do_swap_page(struct vm_fault *vmf); +void folio_rotate_reclaimable(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); diff --git a/mm/page_io.c b/mm/page_io.c index c493ce9ebcf5..d597bc6e6e45 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -38,7 +38,7 @@ void end_swap_bio_write(struct bio *bio) * Also print a dire warning that things will go BAD (tm) * very quickly. * - * Also clear PG_reclaim to avoid rotate_reclaimable_page() + * Also clear PG_reclaim to avoid folio_rotate_reclaimable() */ set_page_dirty(page); pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n", @@ -317,7 +317,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, * temporary failure if the system has limited * memory for allocating transmit buffers. * Mark the page dirty and avoid - * rotate_reclaimable_page but rate-limit the + * folio_rotate_reclaimable but rate-limit the * messages but do not flag PageError like * the normal direct-to-bio case as it could * be temporary. diff --git a/mm/swap.c b/mm/swap.c index af3cad4e5378..0edbcb9c8876 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -206,11 +206,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec) { - if (!PageUnevictable(page)) { - del_page_from_lru_list(page, lruvec); - ClearPageActive(page); - add_page_to_lru_list_tail(page, lruvec); - __count_vm_events(PGROTATED, thp_nr_pages(page)); + struct folio *folio = page_folio(page); + + if (!folio_test_unevictable(folio)) { + lruvec_del_folio(lruvec, folio); + folio_clear_active(folio); + lruvec_add_folio_tail(lruvec, folio); + __count_vm_events(PGROTATED, folio_nr_pages(folio)); } } @@ -227,23 +229,23 @@ static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page) } /* - * Writeback is about to end against a page which has been marked for immediate - * reclaim. If it still appears to be reclaimable, move it to the tail of the - * inactive list. + * Writeback is about to end against a folio which has been marked for + * immediate reclaim. If it still appears to be reclaimable, move it + * to the tail of the inactive list. * - * rotate_reclaimable_page() must disable IRQs, to prevent nasty races. + * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races. */ -void rotate_reclaimable_page(struct page *page) +void folio_rotate_reclaimable(struct folio *folio) { - if (!PageLocked(page) && !PageDirty(page) && - !PageUnevictable(page) && PageLRU(page)) { + if (!folio_test_locked(folio) && !folio_test_dirty(folio) && + !folio_test_unevictable(folio) && folio_test_lru(folio)) { struct pagevec *pvec; unsigned long flags; - get_page(page); + folio_get(folio); local_lock_irqsave(&lru_rotate.lock, flags); pvec = this_cpu_ptr(&lru_rotate.pvec); - if (pagevec_add_and_need_flush(pvec, page)) + if (pagevec_add_and_need_flush(pvec, &folio->page)) pagevec_lru_move_fn(pvec, pagevec_move_tail_fn); local_unlock_irqrestore(&lru_rotate.lock, flags); } -- cgit v1.2.3 From 4268b48077e55a93959f368aa9d3103ede5d3f0f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 3 Mar 2021 15:21:55 -0500 Subject: mm/filemap: Add folio_end_writeback() Add an end_page_writeback() wrapper function for users that are not yet converted to folios. folio_end_writeback() is less than half the size of end_page_writeback() at just 105 bytes compared to 228 bytes, due to removing all the compound_head() calls. The 30 byte wrapper function makes this a net saving of 93 bytes. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/pagemap.h | 3 ++- mm/filemap.c | 43 +++++++++++++++++++++---------------------- mm/folio-compat.c | 6 ++++++ 3 files changed, 29 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7cf140f98910..d9dcd335cc18 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -767,7 +767,8 @@ static inline int wait_on_page_locked_killable(struct page *page) int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); int wait_on_page_writeback_killable(struct page *page); -extern void end_page_writeback(struct page *page); +void end_page_writeback(struct page *page); +void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void __set_page_dirty(struct page *, struct address_space *, int warn); diff --git a/mm/filemap.c b/mm/filemap.c index 6a5bdb4f7c73..4e41bfdb6555 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1230,11 +1230,11 @@ static void wake_up_page_bit(struct page *page, int bit_nr) spin_unlock_irqrestore(&q->lock, flags); } -static void wake_up_page(struct page *page, int bit) +static void folio_wake(struct folio *folio, int bit) { - if (!PageWaiters(page)) + if (!folio_test_waiters(folio)) return; - wake_up_page_bit(page, bit); + wake_up_page_bit(&folio->page, bit); } /* @@ -1571,39 +1571,38 @@ int wait_on_page_private_2_killable(struct page *page) EXPORT_SYMBOL(wait_on_page_private_2_killable); /** - * end_page_writeback - end writeback against a page - * @page: the page + * folio_end_writeback - End writeback against a folio. + * @folio: The folio. */ -void end_page_writeback(struct page *page) +void folio_end_writeback(struct folio *folio) { /* - * TestClearPageReclaim could be used here but it is an atomic - * operation and overkill in this particular case. Failing to - * shuffle a page marked for immediate reclaim is too mild to - * justify taking an atomic operation penalty at the end of - * ever page writeback. + * folio_test_clear_reclaim() could be used here but it is an + * atomic operation and overkill in this particular case. Failing + * to shuffle a folio marked for immediate reclaim is too mild + * a gain to justify taking an atomic operation penalty at the + * end of every folio writeback. */ - if (PageReclaim(page)) { - struct folio *folio = page_folio(page); - ClearPageReclaim(page); + if (folio_test_reclaim(folio)) { + folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } /* - * Writeback does not hold a page reference of its own, relying + * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. - * But here we must make sure that the page is not freed and - * reused before the wake_up_page(). + * But here we must make sure that the folio is not freed and + * reused before the folio_wake(). */ - get_page(page); - if (!test_clear_page_writeback(page)) + folio_get(folio); + if (!test_clear_page_writeback(&folio->page)) BUG(); smp_mb__after_atomic(); - wake_up_page(page, PG_writeback); - put_page(page); + folio_wake(folio, PG_writeback); + folio_put(folio); } -EXPORT_SYMBOL(end_page_writeback); +EXPORT_SYMBOL(folio_end_writeback); /* * After completing I/O on a page, call this routine to update the page diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 91b3d00a92f7..526843d03d58 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -17,3 +17,9 @@ void unlock_page(struct page *page) return folio_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page); + +void end_page_writeback(struct page *page) +{ + return folio_end_writeback(page_folio(page)); +} +EXPORT_SYMBOL(end_page_writeback); -- cgit v1.2.3 From 490e016f229a79dc7551e7f0e989d2304416c189 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 4 Mar 2021 11:09:17 -0500 Subject: mm/writeback: Add folio_wait_writeback() wait_on_page_writeback_killable() only has one caller, so convert it to call folio_wait_writeback_killable(). For the wait_on_page_writeback() callers, add a compatibility wrapper around folio_wait_writeback(). Turning PageWriteback() into folio_test_writeback() eliminates a call to compound_head() which saves 8 bytes and 15 bytes in the two functions. Unfortunately, that is more than offset by adding the wait_on_page_writeback compatibility wrapper for a net increase in text of 7 bytes. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Acked-by: Mike Rapoport Reviewed-by: David Howells --- fs/afs/write.c | 9 +++++---- include/linux/pagemap.h | 3 ++- mm/folio-compat.c | 6 ++++++ mm/page-writeback.c | 48 +++++++++++++++++++++++++++++++++--------------- 4 files changed, 46 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/afs/write.c b/fs/afs/write.c index 2dfe3b3a53d6..5103328e528d 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -861,7 +861,8 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) */ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { - struct page *page = thp_head(vmf->page); + struct folio *folio = page_folio(vmf->page); + struct page *page = &folio->page; struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); @@ -884,7 +885,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) goto out; #endif - if (wait_on_page_writeback_killable(page)) + if (folio_wait_writeback_killable(folio)) goto out; if (lock_page_killable(page) < 0) @@ -894,8 +895,8 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) * details the portion of the page we need to write back and we might * need to redirty the page if there's a problem. */ - if (wait_on_page_writeback_killable(page) < 0) { - unlock_page(page); + if (folio_wait_writeback_killable(folio) < 0) { + folio_unlock(folio); goto out; } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d9dcd335cc18..e6013c063986 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -766,7 +766,8 @@ static inline int wait_on_page_locked_killable(struct page *page) int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); -int wait_on_page_writeback_killable(struct page *page); +void folio_wait_writeback(struct folio *folio); +int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 526843d03d58..41275dac7a92 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -23,3 +23,9 @@ void end_page_writeback(struct page *page) return folio_end_writeback(page_folio(page)); } EXPORT_SYMBOL(end_page_writeback); + +void wait_on_page_writeback(struct page *page) +{ + return folio_wait_writeback(page_folio(page)); +} +EXPORT_SYMBOL_GPL(wait_on_page_writeback); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 4812a17b288c..c7f40c954217 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2873,33 +2873,51 @@ int __test_set_page_writeback(struct page *page, bool keep_write) } EXPORT_SYMBOL(__test_set_page_writeback); -/* - * Wait for a page to complete writeback +/** + * folio_wait_writeback - Wait for a folio to finish writeback. + * @folio: The folio to wait for. + * + * If the folio is currently being written back to storage, wait for the + * I/O to complete. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. */ -void wait_on_page_writeback(struct page *page) +void folio_wait_writeback(struct folio *folio) { - while (PageWriteback(page)) { - trace_wait_on_page_writeback(page, page_mapping(page)); - wait_on_page_bit(page, PG_writeback); + while (folio_test_writeback(folio)) { + trace_wait_on_page_writeback(&folio->page, folio_mapping(folio)); + wait_on_page_bit(&folio->page, PG_writeback); } } -EXPORT_SYMBOL_GPL(wait_on_page_writeback); +EXPORT_SYMBOL_GPL(folio_wait_writeback); -/* - * Wait for a page to complete writeback. Returns -EINTR if we get a - * fatal signal while waiting. +/** + * folio_wait_writeback_killable - Wait for a folio to finish writeback. + * @folio: The folio to wait for. + * + * If the folio is currently being written back to storage, wait for the + * I/O to complete or a fatal signal to arrive. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. + * Return: 0 on success, -EINTR if we get a fatal signal while waiting. */ -int wait_on_page_writeback_killable(struct page *page) +int folio_wait_writeback_killable(struct folio *folio) { - while (PageWriteback(page)) { - trace_wait_on_page_writeback(page, page_mapping(page)); - if (wait_on_page_bit_killable(page, PG_writeback)) + while (folio_test_writeback(folio)) { + trace_wait_on_page_writeback(&folio->page, folio_mapping(folio)); + if (wait_on_page_bit_killable(&folio->page, PG_writeback)) return -EINTR; } return 0; } -EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable); +EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** * wait_for_stable_page() - wait for writeback to finish, if necessary. -- cgit v1.2.3 From a49d0c507759214a7cfd26555382c314db486792 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 4 Mar 2021 11:25:25 -0500 Subject: mm/writeback: Add folio_wait_stable() Move wait_for_stable_page() into the folio compatibility file. folio_wait_stable() avoids a call to compound_head() and is 14 bytes smaller than wait_for_stable_page() was. The net text size grows by 16 bytes as a result of this patch. We can also remove thp_head() as this was the last user. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells --- include/linux/huge_mm.h | 15 --------------- include/linux/pagemap.h | 1 + mm/folio-compat.c | 6 ++++++ mm/page-writeback.c | 24 ++++++++++++++---------- 4 files changed, 21 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f123e15d966e..f280f33ff223 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -250,15 +250,6 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, return NULL; } -/** - * thp_head - Head page of a transparent huge page. - * @page: Any page (tail, head or regular) found in the page cache. - */ -static inline struct page *thp_head(struct page *page) -{ - return compound_head(page); -} - /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. @@ -336,12 +327,6 @@ static inline struct list_head *page_deferred_list(struct page *page) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) -static inline struct page *thp_head(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return page; -} - static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e6013c063986..ee39ad7b42f1 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -771,6 +771,7 @@ int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); +void folio_wait_stable(struct folio *folio); void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 41275dac7a92..3c83f03b80d7 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -29,3 +29,9 @@ void wait_on_page_writeback(struct page *page) return folio_wait_writeback(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_on_page_writeback); + +void wait_for_stable_page(struct page *page) +{ + return folio_wait_stable(page_folio(page)); +} +EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index c7f40c954217..0b0b7cd81a93 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2920,17 +2920,21 @@ int folio_wait_writeback_killable(struct folio *folio) EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); /** - * wait_for_stable_page() - wait for writeback to finish, if necessary. - * @page: The page to wait on. + * folio_wait_stable() - wait for writeback to finish, if necessary. + * @folio: The folio to wait on. * - * This function determines if the given page is related to a backing device - * that requires page contents to be held stable during writeback. If so, then - * it will wait for any pending writeback to complete. + * This function determines if the given folio is related to a backing + * device that requires folio contents to be held stable during writeback. + * If so, then it will wait for any pending writeback to complete. + * + * Context: Sleeps. Must be called in process context and with + * no spinlocks held. Caller should hold a reference on the folio. + * If the folio is not locked, writeback may start again after writeback + * has finished. */ -void wait_for_stable_page(struct page *page) +void folio_wait_stable(struct folio *folio) { - page = thp_head(page); - if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) - wait_on_page_writeback(page); + if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) + folio_wait_writeback(folio); } -EXPORT_SYMBOL_GPL(wait_for_stable_page); +EXPORT_SYMBOL_GPL(folio_wait_stable); -- cgit v1.2.3 From 101c0bf67f50ca0e8b9da97b26f8dc7cb232b4d3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 4 Mar 2021 12:02:54 -0500 Subject: mm/filemap: Add folio_wait_bit() Rename wait_on_page_bit() to folio_wait_bit(). We must always wait on the folio, otherwise we won't be woken up due to the tail page hashing to a different bucket from the head page. This commit shrinks the kernel by 770 bytes, mostly due to moving the page waitqueue lookup into folio_wait_bit_common(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells Acked-by: Mike Rapoport --- include/linux/pagemap.h | 10 +++---- mm/filemap.c | 77 +++++++++++++++++++++++-------------------------- mm/page-writeback.c | 4 +-- 3 files changed, 43 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee39ad7b42f1..2f481327dee8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -728,11 +728,11 @@ static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm, } /* - * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc., + * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */ -extern void wait_on_page_bit(struct page *page, int bit_nr); -extern int wait_on_page_bit_killable(struct page *page, int bit_nr); +void folio_wait_bit(struct folio *folio, int bit_nr); +int folio_wait_bit_killable(struct folio *folio, int bit_nr); /* * Wait for a folio to be unlocked. @@ -744,14 +744,14 @@ extern int wait_on_page_bit_killable(struct page *page, int bit_nr); static inline void folio_wait_locked(struct folio *folio) { if (folio_test_locked(folio)) - wait_on_page_bit(&folio->page, PG_locked); + folio_wait_bit(folio, PG_locked); } static inline int folio_wait_locked_killable(struct folio *folio) { if (!folio_test_locked(folio)) return 0; - return wait_on_page_bit_killable(&folio->page, PG_locked); + return folio_wait_bit_killable(folio, PG_locked); } static inline void wait_on_page_locked(struct page *page) diff --git a/mm/filemap.c b/mm/filemap.c index 4e41bfdb6555..13663f0cfd51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1157,7 +1157,7 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs - * with the load-acquire in wait_on_page_bit_common(). + * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); @@ -1238,7 +1238,7 @@ static void folio_wake(struct folio *folio, int bit) } /* - * A choice of three behaviors for wait_on_page_bit_common(): + * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like @@ -1253,16 +1253,16 @@ enum behavior { }; /* - * Attempt to check (or get) the page bit, and mark us done + * Attempt to check (or get) the folio flag, and mark us done * if successful. */ -static inline bool trylock_page_bit_common(struct page *page, int bit_nr, +static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { - if (test_and_set_bit(bit_nr, &page->flags)) + if (test_and_set_bit(bit_nr, &folio->flags)) return false; - } else if (test_bit(bit_nr, &page->flags)) + } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; @@ -1272,9 +1272,10 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr, /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; -static inline int wait_on_page_bit_common(wait_queue_head_t *q, - struct page *page, int bit_nr, int state, enum behavior behavior) +static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, + int state, enum behavior behavior) { + wait_queue_head_t *q = page_waitqueue(&folio->page); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; @@ -1283,8 +1284,8 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, unsigned long pflags; if (bit_nr == PG_locked && - !PageUptodate(page) && PageWorkingset(page)) { - if (!PageSwapBacked(page)) { + !folio_test_uptodate(folio) && folio_test_workingset(folio)) { + if (!folio_test_swapbacked(folio)) { delayacct_thrashing_start(); delayacct = true; } @@ -1294,7 +1295,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, init_wait(wait); wait->func = wake_page_function; - wait_page.page = page; + wait_page.page = &folio->page; wait_page.bit_nr = bit_nr; repeat: @@ -1309,7 +1310,7 @@ repeat: * Do one last check whether we can get the * page bit synchronously. * - * Do the SetPageWaiters() marking before that + * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the @@ -1320,8 +1321,8 @@ repeat: * lock to avoid races. */ spin_lock_irq(&q->lock); - SetPageWaiters(page); - if (!trylock_page_bit_common(page, bit_nr, wait)) + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); @@ -1331,10 +1332,10 @@ repeat: * see whether the page bit testing has already * been done by the wake function. * - * We can drop our reference to the page. + * We can drop our reference to the folio. */ if (behavior == DROP) - put_page(page); + folio_put(folio); /* * Note that until the "finish_wait()", or until @@ -1371,7 +1372,7 @@ repeat: * * And if that fails, we'll have to retry this all. */ - if (unlikely(test_and_set_bit(bit_nr, &page->flags))) + if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; @@ -1380,7 +1381,7 @@ repeat: /* * If a signal happened, this 'finish_wait()' may remove the last - * waiter from the wait-queues, but the PageWaiters bit will remain + * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ @@ -1411,19 +1412,17 @@ repeat: return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } -void wait_on_page_bit(struct page *page, int bit_nr) +void folio_wait_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); + folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit); +EXPORT_SYMBOL(folio_wait_bit); -int wait_on_page_bit_killable(struct page *page, int bit_nr) +int folio_wait_bit_killable(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED); + return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } -EXPORT_SYMBOL(wait_on_page_bit_killable); +EXPORT_SYMBOL(folio_wait_bit_killable); /** * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked @@ -1440,11 +1439,8 @@ EXPORT_SYMBOL(wait_on_page_bit_killable); */ int put_and_wait_on_page_locked(struct page *page, int state) { - wait_queue_head_t *q; - - page = compound_head(page); - q = page_waitqueue(page); - return wait_on_page_bit_common(q, page, PG_locked, state, DROP); + return folio_wait_bit_common(page_folio(page), PG_locked, state, + DROP); } /** @@ -1538,9 +1534,10 @@ EXPORT_SYMBOL(end_page_private_2); */ void wait_on_page_private_2(struct page *page) { - page = compound_head(page); - while (PagePrivate2(page)) - wait_on_page_bit(page, PG_private_2); + struct folio *folio = page_folio(page); + + while (folio_test_private_2(folio)) + folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(wait_on_page_private_2); @@ -1557,11 +1554,11 @@ EXPORT_SYMBOL(wait_on_page_private_2); */ int wait_on_page_private_2_killable(struct page *page) { + struct folio *folio = page_folio(page); int ret = 0; - page = compound_head(page); - while (PagePrivate2(page)) { - ret = wait_on_page_bit_killable(page, PG_private_2); + while (folio_test_private_2(folio)) { + ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } @@ -1638,16 +1635,14 @@ EXPORT_SYMBOL_GPL(page_endio); */ void __folio_lock(struct folio *folio) { - wait_queue_head_t *q = page_waitqueue(&folio->page); - wait_on_page_bit_common(q, &folio->page, PG_locked, TASK_UNINTERRUPTIBLE, + folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { - wait_queue_head_t *q = page_waitqueue(&folio->page); - return wait_on_page_bit_common(q, &folio->page, PG_locked, TASK_KILLABLE, + return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 0b0b7cd81a93..1d8f2ee2e065 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2889,7 +2889,7 @@ void folio_wait_writeback(struct folio *folio) { while (folio_test_writeback(folio)) { trace_wait_on_page_writeback(&folio->page, folio_mapping(folio)); - wait_on_page_bit(&folio->page, PG_writeback); + folio_wait_bit(folio, PG_writeback); } } EXPORT_SYMBOL_GPL(folio_wait_writeback); @@ -2911,7 +2911,7 @@ int folio_wait_writeback_killable(struct folio *folio) { while (folio_test_writeback(folio)) { trace_wait_on_page_writeback(&folio->page, folio_mapping(folio)); - if (wait_on_page_bit_killable(&folio->page, PG_writeback)) + if (folio_wait_bit_killable(folio, PG_writeback)) return -EINTR; } -- cgit v1.2.3 From df4d4f12739495332e0d1f916ef4270f7d25d207 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 16 Jan 2021 11:22:14 -0500 Subject: mm/filemap: Convert page wait queues to be folios Reinforce that page flags are actually in the head page by changing the type from page to folio. Increases the size of cachefiles by two bytes, but the kernel core is unchanged in size. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Jeff Layton Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: David Howells --- fs/cachefiles/rdwr.c | 16 ++++++++-------- include/linux/pagemap.h | 8 ++++---- mm/filemap.c | 38 +++++++++++++++++++------------------- 3 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 8ffc40e84a59..fcf4f3b72923 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -25,20 +25,20 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, struct cachefiles_object *object; struct fscache_retrieval *op = monitor->op; struct wait_page_key *key = _key; - struct page *page = wait->private; + struct folio *folio = wait->private; ASSERT(key); _enter("{%lu},%u,%d,{%p,%u}", monitor->netfs_page->index, mode, sync, - key->page, key->bit_nr); + key->folio, key->bit_nr); - if (key->page != page || key->bit_nr != PG_locked) + if (key->folio != folio || key->bit_nr != PG_locked) return 0; - _debug("--- monitor %p %lx ---", page, page->flags); + _debug("--- monitor %p %lx ---", folio, folio->flags); - if (!PageUptodate(page) && !PageError(page)) { + if (!folio_test_uptodate(folio) && !folio_test_error(folio)) { /* unlocked, not uptodate and not erronous? */ _debug("page probably truncated"); } @@ -107,7 +107,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object, put_page(backpage2); INIT_LIST_HEAD(&monitor->op_link); - add_page_wait_queue(backpage, &monitor->monitor); + folio_add_wait_queue(page_folio(backpage), &monitor->monitor); if (trylock_page(backpage)) { ret = -EIO; @@ -294,7 +294,7 @@ monitor_backing_page: get_page(backpage); monitor->back_page = backpage; monitor->monitor.private = backpage; - add_page_wait_queue(backpage, &monitor->monitor); + folio_add_wait_queue(page_folio(backpage), &monitor->monitor); monitor = NULL; /* but the page may have been read before the monitor was installed, so @@ -548,7 +548,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object, get_page(backpage); monitor->back_page = backpage; monitor->monitor.private = backpage; - add_page_wait_queue(backpage, &monitor->monitor); + folio_add_wait_queue(page_folio(backpage), &monitor->monitor); monitor = NULL; /* but the page may have been read before the monitor was diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 2f481327dee8..ebc62e9e453b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -628,13 +628,13 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, } struct wait_page_key { - struct page *page; + struct folio *folio; int bit_nr; int page_match; }; struct wait_page_queue { - struct page *page; + struct folio *folio; int bit_nr; wait_queue_entry_t wait; }; @@ -642,7 +642,7 @@ struct wait_page_queue { static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { - if (wait_page->page != key->page) + if (wait_page->folio != key->folio) return false; key->page_match = 1; @@ -802,7 +802,7 @@ int wait_on_page_private_2_killable(struct page *page); /* * Add an arbitrary waiter to a page's wait queue */ -extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); +void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter); /* * Fault everything in given userspace address range in. diff --git a/mm/filemap.c b/mm/filemap.c index a896348ff4de..1f8c00c2a4b7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1074,11 +1074,11 @@ EXPORT_SYMBOL(filemap_invalidate_unlock_two); */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) -static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; +static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; -static wait_queue_head_t *page_waitqueue(struct page *page) +static wait_queue_head_t *folio_waitqueue(struct folio *folio) { - return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)]; + return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) @@ -1086,7 +1086,7 @@ void __init pagecache_init(void) int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) - init_waitqueue_head(&page_wait_table[i]); + init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } @@ -1141,10 +1141,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { - if (test_bit(key->bit_nr, &key->page->flags)) + if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { - if (test_and_set_bit(key->bit_nr, &key->page->flags)) + if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } @@ -1178,12 +1178,12 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, static void folio_wake_bit(struct folio *folio, int bit_nr) { - wait_queue_head_t *q = page_waitqueue(&folio->page); + wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; wait_queue_entry_t bookmark; - key.page = &folio->page; + key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; @@ -1275,7 +1275,7 @@ int sysctl_page_lock_unfairness = 5; static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { - wait_queue_head_t *q = page_waitqueue(&folio->page); + wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; @@ -1295,7 +1295,7 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, init_wait(wait); wait->func = wake_page_function; - wait_page.page = &folio->page; + wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: @@ -1444,23 +1444,23 @@ int put_and_wait_on_page_locked(struct page *page, int state) } /** - * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue - * @page: Page defining the wait queue of interest + * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue + * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * - * Add an arbitrary @waiter to the wait queue for the nominated @page. + * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ -void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) +void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { - wait_queue_head_t *q = page_waitqueue(page); + wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); - SetPageWaiters(page); + folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } -EXPORT_SYMBOL_GPL(add_page_wait_queue); +EXPORT_SYMBOL_GPL(folio_add_wait_queue); #ifndef clear_bit_unlock_is_negative_byte @@ -1650,10 +1650,10 @@ EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { - struct wait_queue_head *q = page_waitqueue(&folio->page); + struct wait_queue_head *q = folio_waitqueue(folio); int ret = 0; - wait->page = &folio->page; + wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); -- cgit v1.2.3 From b47393f8448ade8bafe09ed302ce2a15093e9718 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 22 Apr 2021 22:58:32 -0400 Subject: mm/filemap: Add folio private_2 functions end_page_private_2() becomes folio_end_private_2(), wait_on_page_private_2() becomes folio_wait_private_2() and wait_on_page_private_2_killable() becomes folio_wait_private_2_killable(). Adjust the fscache equivalents to call page_folio() before calling these functions to avoid adding wrappers. Ends up costing 1 byte of text in ceph & netfs, but the core shrinks by three calls to page_folio(). Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Kirill A. Shutemov --- include/linux/netfs.h | 6 +++--- include/linux/pagemap.h | 6 +++--- mm/filemap.c | 41 ++++++++++++++++++----------------------- 3 files changed, 24 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5d6a4158a9a6..3d4cbf2f7dc4 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -55,7 +55,7 @@ static inline void set_page_fscache(struct page *page) */ static inline void end_page_fscache(struct page *page) { - end_page_private_2(page); + folio_end_private_2(page_folio(page)); } /** @@ -66,7 +66,7 @@ static inline void end_page_fscache(struct page *page) */ static inline void wait_on_page_fscache(struct page *page) { - wait_on_page_private_2(page); + folio_wait_private_2(page_folio(page)); } /** @@ -82,7 +82,7 @@ static inline void wait_on_page_fscache(struct page *page) */ static inline int wait_on_page_fscache_killable(struct page *page) { - return wait_on_page_private_2_killable(page); + return folio_wait_private_2_killable(page_folio(page)); } enum netfs_read_source { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ebc62e9e453b..05f91bfc048d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -795,9 +795,9 @@ static inline void set_page_private_2(struct page *page) SetPagePrivate2(page); } -void end_page_private_2(struct page *page); -void wait_on_page_private_2(struct page *page); -int wait_on_page_private_2_killable(struct page *page); +void folio_end_private_2(struct folio *folio); +void folio_wait_private_2(struct folio *folio); +int folio_wait_private_2_killable(struct folio *folio); /* * Add an arbitrary waiter to a page's wait queue diff --git a/mm/filemap.c b/mm/filemap.c index 1f8c00c2a4b7..d74be9fb3aa2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1506,56 +1506,51 @@ void folio_unlock(struct folio *folio) EXPORT_SYMBOL(folio_unlock); /** - * end_page_private_2 - Clear PG_private_2 and release any waiters - * @page: The page + * folio_end_private_2 - Clear PG_private_2 and wake any waiters. + * @folio: The folio. * - * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for - * this. The page ref held for PG_private_2 being set is released. + * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for + * it. The folio reference held for PG_private_2 being set is released. * - * This is, for example, used when a netfs page is being written to a local - * disk cache, thereby allowing writes to the cache for the same page to be + * This is, for example, used when a netfs folio is being written to a local + * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ -void end_page_private_2(struct page *page) +void folio_end_private_2(struct folio *folio) { - struct folio *folio = page_folio(page); - VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } -EXPORT_SYMBOL(end_page_private_2); +EXPORT_SYMBOL(folio_end_private_2); /** - * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page - * @page: The page to wait on + * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. + * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page. + * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio. */ -void wait_on_page_private_2(struct page *page) +void folio_wait_private_2(struct folio *folio) { - struct folio *folio = page_folio(page); - while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } -EXPORT_SYMBOL(wait_on_page_private_2); +EXPORT_SYMBOL(folio_wait_private_2); /** - * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page - * @page: The page to wait on + * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. + * @folio: The folio to wait on. * - * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a + * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a * fatal signal is received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ -int wait_on_page_private_2_killable(struct page *page) +int folio_wait_private_2_killable(struct folio *folio) { - struct folio *folio = page_folio(page); int ret = 0; while (folio_test_private_2(folio)) { @@ -1566,7 +1561,7 @@ int wait_on_page_private_2_killable(struct page *page) return ret; } -EXPORT_SYMBOL(wait_on_page_private_2_killable); +EXPORT_SYMBOL(folio_wait_private_2_killable); /** * folio_end_writeback - End writeback against a folio. -- cgit v1.2.3 From 6abbaa5b01730a1f0883d199cf5a90ae5c5dccea Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 27 Apr 2021 14:24:30 -0400 Subject: fs/netfs: Add folio fscache functions Match the page writeback functions by adding folio_start_fscache(), folio_end_fscache(), folio_wait_fscache() and folio_wait_fscache_killable(). Remove set_page_private_2(). Also rewrite the kernel-doc to describe when to use the function rather than what the function does, and include the kernel-doc in the appropriate rst file. Saves 31 bytes of text in netfs_rreq_unlock() due to set_page_fscache() calling page_folio() once instead of three times. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Acked-by: Kirill A. Shutemov Acked-by: Mike Rapoport Reviewed-by: David Howells --- Documentation/filesystems/netfs_library.rst | 2 + include/linux/netfs.h | 75 ++++++++++++++++++----------- include/linux/pagemap.h | 16 ------ 3 files changed, 50 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 57a641847818..bb68d39f03b7 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -524,3 +524,5 @@ Note that these methods are passed a pointer to the cache resource structure, not the read request structure as they could be used in other situations where there isn't a read request structure as well, such as writing dirty data to the cache. + +.. kernel-doc:: include/linux/netfs.h diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 3d4cbf2f7dc4..12c4177f7703 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -22,6 +22,7 @@ * Overload PG_private_2 to give us PG_fscache - this is used to indicate that * a page is currently backed by a local disk cache */ +#define folio_test_fscache(folio) folio_test_private_2(folio) #define PageFsCache(page) PagePrivate2((page)) #define SetPageFsCache(page) SetPagePrivate2((page)) #define ClearPageFsCache(page) ClearPagePrivate2((page)) @@ -29,57 +30,77 @@ #define TestClearPageFsCache(page) TestClearPagePrivate2((page)) /** - * set_page_fscache - Set PG_fscache on a page and take a ref - * @page: The page. + * folio_start_fscache - Start an fscache write on a folio. + * @folio: The folio. * - * Set the PG_fscache (PG_private_2) flag on a page and take the reference - * needed for the VM to handle its lifetime correctly. This sets the flag and - * takes the reference unconditionally, so care must be taken not to set the - * flag again if it's already set. + * Call this function before writing a folio to a local cache. Starting a + * second write before the first one finishes is not allowed. */ -static inline void set_page_fscache(struct page *page) +static inline void folio_start_fscache(struct folio *folio) { - set_page_private_2(page); + VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio); + folio_get(folio); + folio_set_private_2(folio); } /** - * end_page_fscache - Clear PG_fscache and release any waiters - * @page: The page - * - * Clear the PG_fscache (PG_private_2) bit on a page and wake up any sleepers - * waiting for this. The page ref held for PG_private_2 being set is released. + * folio_end_fscache - End an fscache write on a folio. + * @folio: The folio. * - * This is, for example, used when a netfs page is being written to a local - * disk cache, thereby allowing writes to the cache for the same page to be - * serialised. + * Call this function after the folio has been written to the local cache. + * This will wake any sleepers waiting on this folio. */ -static inline void end_page_fscache(struct page *page) +static inline void folio_end_fscache(struct folio *folio) { - folio_end_private_2(page_folio(page)); + folio_end_private_2(folio); } /** - * wait_on_page_fscache - Wait for PG_fscache to be cleared on a page - * @page: The page to wait on + * folio_wait_fscache - Wait for an fscache write on this folio to end. + * @folio: The folio. * - * Wait for PG_fscache (aka PG_private_2) to be cleared on a page. + * If this folio is currently being written to a local cache, wait for + * the write to finish. Another write may start after this one finishes, + * unless the caller holds the folio lock. */ -static inline void wait_on_page_fscache(struct page *page) +static inline void folio_wait_fscache(struct folio *folio) { - folio_wait_private_2(page_folio(page)); + folio_wait_private_2(folio); } /** - * wait_on_page_fscache_killable - Wait for PG_fscache to be cleared on a page - * @page: The page to wait on + * folio_wait_fscache_killable - Wait for an fscache write on this folio to end. + * @folio: The folio. * - * Wait for PG_fscache (aka PG_private_2) to be cleared on a page or until a - * fatal signal is received by the calling task. + * If this folio is currently being written to a local cache, wait + * for the write to finish or for a fatal signal to be received. + * Another write may start after this one finishes, unless the caller + * holds the folio lock. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ +static inline int folio_wait_fscache_killable(struct folio *folio) +{ + return folio_wait_private_2_killable(folio); +} + +static inline void set_page_fscache(struct page *page) +{ + folio_start_fscache(page_folio(page)); +} + +static inline void end_page_fscache(struct page *page) +{ + folio_end_private_2(page_folio(page)); +} + +static inline void wait_on_page_fscache(struct page *page) +{ + folio_wait_private_2(page_folio(page)); +} + static inline int wait_on_page_fscache_killable(struct page *page) { return folio_wait_private_2_killable(page_folio(page)); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 05f91bfc048d..bdbd7be67812 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -779,22 +779,6 @@ int __set_page_dirty_no_writeback(struct page *page); void page_endio(struct page *page, bool is_write, int err); -/** - * set_page_private_2 - Set PG_private_2 on a page and take a ref - * @page: The page. - * - * Set the PG_private_2 flag on a page and take the reference needed for the VM - * to handle its lifetime correctly. This sets the flag and takes the - * reference unconditionally, so care must be taken not to set the flag again - * if it's already set. - */ -static inline void set_page_private_2(struct page *page) -{ - page = compound_head(page); - get_page(page); - SetPagePrivate2(page); -} - void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); -- cgit v1.2.3 From dd10ab049beb479dc83bb14a7b5cd68c363983ce Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 12 Apr 2021 16:45:17 -0400 Subject: mm: Add folio_mapped() This function is the equivalent of page_mapped(). It is slightly shorter as we do not need to handle the PageTail() case. Reimplement page_mapped() as a wrapper around folio_mapped(). folio_mapped() is 13 bytes smaller than page_mapped(), but the page_mapped() wrapper is 30 bytes, for a net increase of 17 bytes of text. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Kirill A. Shutemov Acked-by: Mike Rapoport --- include/linux/mm.h | 1 + include/linux/mm_types.h | 6 ++++++ mm/folio-compat.c | 6 ++++++ mm/util.c | 29 ++++++++++++++++------------- 4 files changed, 29 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index bc5c38e1f780..95e36d0475ac 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1769,6 +1769,7 @@ static inline pgoff_t page_index(struct page *page) } bool page_mapped(struct page *page); +bool folio_mapped(struct folio *folio); /* * Return true only if the page has been allocated with diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5ebcb86ac934..82dab23205c3 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -299,6 +299,12 @@ FOLIO_MATCH(memcg_data, memcg_data); #endif #undef FOLIO_MATCH +static inline atomic_t *folio_mapcount_ptr(struct folio *folio) +{ + struct page *tail = &folio->page + 1; + return &tail->compound_mapcount; +} + static inline atomic_t *compound_mapcount_ptr(struct page *page) { return &page[1].compound_mapcount; diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 3c83f03b80d7..7044fcc8a8aa 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -35,3 +35,9 @@ void wait_for_stable_page(struct page *page) return folio_wait_stable(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_for_stable_page); + +bool page_mapped(struct page *page) +{ + return folio_mapped(page_folio(page)); +} +EXPORT_SYMBOL(page_mapped); diff --git a/mm/util.c b/mm/util.c index 6c1fe9bee30a..e322a42090e5 100644 --- a/mm/util.c +++ b/mm/util.c @@ -671,28 +671,31 @@ void *page_rmapping(struct page *page) return __page_rmapping(page); } -/* - * Return true if this page is mapped into pagetables. - * For compound page it returns true if any subpage of compound page is mapped. +/** + * folio_mapped - Is this folio mapped into userspace? + * @folio: The folio. + * + * Return: True if any page in this folio is referenced by user page tables. */ -bool page_mapped(struct page *page) +bool folio_mapped(struct folio *folio) { - int i; + long i, nr; - if (likely(!PageCompound(page))) - return atomic_read(&page->_mapcount) >= 0; - page = compound_head(page); - if (atomic_read(compound_mapcount_ptr(page)) >= 0) + if (folio_test_single(folio)) + return atomic_read(&folio->_mapcount) >= 0; + if (atomic_read(folio_mapcount_ptr(folio)) >= 0) return true; - if (PageHuge(page)) + if (folio_test_hugetlb(folio)) return false; - for (i = 0; i < compound_nr(page); i++) { - if (atomic_read(&page[i]._mapcount) >= 0) + + nr = folio_nr_pages(folio); + for (i = 0; i < nr; i++) { + if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0) return true; } return false; } -EXPORT_SYMBOL(page_mapped); +EXPORT_SYMBOL(folio_mapped); struct anon_vma *page_anon_vma(struct page *page) { -- cgit v1.2.3 From 874fd90cafdca9d678bceb88f91322af8c9a9d2d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 25 Jun 2021 09:27:29 -0400 Subject: mm: Add folio_nid() This is the folio equivalent of page_to_nid(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 95e36d0475ac..04e41d4d85ea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1429,6 +1429,11 @@ static inline int page_to_nid(const struct page *page) } #endif +static inline int folio_nid(const struct folio *folio) +{ + return page_to_nid(&folio->page); +} + #ifdef CONFIG_NUMA_BALANCING static inline int cpu_pid_to_cpupid(int cpu, int pid) { -- cgit v1.2.3 From 1b7e4464d43a488e383843bf96ec62d12393bff1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 14:59:26 -0400 Subject: mm/memcg: Add folio_memcg() and related functions memcg information is only stored in the head page, so the memcg subsystem needs to assure that all accesses are to the head page. The first step is converting page_memcg() to folio_memcg(). The callers of page_memcg() and PageMemcgKmem() are not yet ready to be converted to use folios, so retain them as wrappers around folio_memcg() and folio_memcg_kmem(). They will be converted in a later patch set. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 110 ++++++++++++++++++++++++++------------------- mm/memcontrol.c | 21 +++++---- 2 files changed, 77 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3096c9a0ee01..06659670db32 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -369,7 +369,7 @@ enum page_memcg_data_flags { #define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) -static inline bool PageMemcgKmem(struct page *page); +static inline bool folio_memcg_kmem(struct folio *folio); /* * After the initialization objcg->memcg is always pointing at @@ -384,73 +384,77 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) } /* - * __page_memcg - get the memory cgroup associated with a non-kmem page - * @page: a pointer to the page struct + * __folio_memcg - Get the memory cgroup associated with a non-kmem folio + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages or - * kmem pages. + * against some type of folios, e.g. slab folios or ex-slab folios or + * kmem folios. */ -static inline struct mem_cgroup *__page_memcg(struct page *page) +static inline struct mem_cgroup *__folio_memcg(struct folio *folio) { - unsigned long memcg_data = page->memcg_data; + unsigned long memcg_data = folio->memcg_data; - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio); return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* - * __page_objcg - get the object cgroup associated with a kmem page - * @page: a pointer to the page struct + * __folio_objcg - get the object cgroup associated with a kmem folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the object cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the object cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages or - * LRU pages. + * against some type of folios, e.g. slab folios or ex-slab folios or + * LRU folios. */ -static inline struct obj_cgroup *__page_objcg(struct page *page) +static inline struct obj_cgroup *__folio_objcg(struct folio *folio) { - unsigned long memcg_data = page->memcg_data; + unsigned long memcg_data = folio->memcg_data; - VM_BUG_ON_PAGE(PageSlab(page), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); - VM_BUG_ON_PAGE(!(memcg_data & MEMCG_DATA_KMEM), page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); + VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio); + VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio); return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } /* - * page_memcg - get the memory cgroup associated with a page - * @page: a pointer to the page struct + * folio_memcg - Get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * Returns a pointer to the memory cgroup associated with the folio, + * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages. + * against some type of folios, e.g. slab folios or ex-slab folios. * - * For a non-kmem page any of the following ensures page and memcg binding + * For a non-kmem folio any of the following ensures folio and memcg binding * stability: * - * - the page lock + * - the folio lock * - LRU isolation * - lock_page_memcg() * - exclusive reference * - * For a kmem page a caller should hold an rcu read lock to protect memcg - * associated with a kmem page from being released. + * For a kmem folio a caller should hold an rcu read lock to protect memcg + * associated with a kmem folio from being released. */ +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + if (folio_memcg_kmem(folio)) + return obj_cgroup_memcg(__folio_objcg(folio)); + return __folio_memcg(folio); +} + static inline struct mem_cgroup *page_memcg(struct page *page) { - if (PageMemcgKmem(page)) - return obj_cgroup_memcg(__page_objcg(page)); - else - return __page_memcg(page); + return folio_memcg(page_folio(page)); } /* @@ -523,17 +527,18 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) #ifdef CONFIG_MEMCG_KMEM /* - * PageMemcgKmem - check if the page has MemcgKmem flag set - * @page: a pointer to the page struct + * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. + * @folio: Pointer to the folio. * - * Checks if the page has MemcgKmem flag set. The caller must ensure that - * the page has an associated memory cgroup. It's not safe to call this function - * against some types of pages, e.g. slab pages. + * Checks if the folio has MemcgKmem flag set. The caller must ensure + * that the folio has an associated memory cgroup. It's not safe to call + * this function against some types of folios, e.g. slab folios. */ -static inline bool PageMemcgKmem(struct page *page) +static inline bool folio_memcg_kmem(struct folio *folio) { - VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page); - return page->memcg_data & MEMCG_DATA_KMEM; + VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); + VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio); + return folio->memcg_data & MEMCG_DATA_KMEM; } /* @@ -577,7 +582,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #else -static inline bool PageMemcgKmem(struct page *page) +static inline bool folio_memcg_kmem(struct folio *folio) { return false; } @@ -593,6 +598,11 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page) } #endif +static inline bool PageMemcgKmem(struct page *page) +{ + return folio_memcg_kmem(page_folio(page)); +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -1115,6 +1125,11 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 +static inline struct mem_cgroup *folio_memcg(struct folio *folio) +{ + return NULL; +} + static inline struct mem_cgroup *page_memcg(struct page *page) { return NULL; @@ -1131,6 +1146,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return NULL; } +static inline bool folio_memcg_kmem(struct folio *folio) +{ + return false; +} + static inline bool PageMemcgKmem(struct page *page) { return false; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a064a85d51da..1385ac6f688e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2992,15 +2992,16 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) */ void __memcg_kmem_uncharge_page(struct page *page, int order) { + struct folio *folio = page_folio(page); struct obj_cgroup *objcg; unsigned int nr_pages = 1 << order; - if (!PageMemcgKmem(page)) + if (!folio_memcg_kmem(folio)) return; - objcg = __page_objcg(page); + objcg = __folio_objcg(folio); obj_cgroup_uncharge_pages(objcg, nr_pages); - page->memcg_data = 0; + folio->memcg_data = 0; obj_cgroup_put(objcg); } @@ -3234,17 +3235,18 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) */ void split_page_memcg(struct page *head, unsigned int nr) { - struct mem_cgroup *memcg = page_memcg(head); + struct folio *folio = page_folio(head); + struct mem_cgroup *memcg = folio_memcg(folio); int i; if (mem_cgroup_disabled() || !memcg) return; for (i = 1; i < nr; i++) - head[i].memcg_data = head->memcg_data; + folio_page(folio, i)->memcg_data = folio->memcg_data; - if (PageMemcgKmem(head)) - obj_cgroup_get_many(__page_objcg(head), nr - 1); + if (folio_memcg_kmem(folio)) + obj_cgroup_get_many(__folio_objcg(folio), nr - 1); else css_get_many(&memcg->css, nr - 1); } @@ -6811,6 +6813,7 @@ static void uncharge_batch(const struct uncharge_gather *ug) static void uncharge_page(struct page *page, struct uncharge_gather *ug) { + struct folio *folio = page_folio(page); unsigned long nr_pages; struct mem_cgroup *memcg; struct obj_cgroup *objcg; @@ -6824,14 +6827,14 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) * exclusive access to the page. */ if (use_objcg) { - objcg = __page_objcg(page); + objcg = __folio_objcg(folio); /* * This get matches the put at the end of the function and * kmem pages do not hold memcg references anymore. */ memcg = get_mem_cgroup_from_objcg(objcg); } else { - memcg = __page_memcg(page); + memcg = __folio_memcg(folio); } if (!memcg) -- cgit v1.2.3 From 8f425e4ed0eb3ef0b2d85a9efccf947ca6aa9b1c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 25 Jun 2021 09:27:04 -0400 Subject: mm/memcg: Convert mem_cgroup_charge() to take a folio Convert all callers of mem_cgroup_charge() to call page_folio() on the page they're currently passing in. Many of them will be converted to use folios themselves soon. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 28 +++++++++++++++++++++------- kernel/events/uprobes.c | 3 ++- mm/filemap.c | 2 +- mm/huge_memory.c | 2 +- mm/khugepaged.c | 4 ++-- mm/ksm.c | 3 ++- mm/memcontrol.c | 28 +++++++--------------------- mm/memory.c | 9 +++++---- mm/migrate.c | 2 +- mm/shmem.c | 2 +- mm/userfaultfd.c | 2 +- 11 files changed, 44 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 06659670db32..19a51729e00c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -694,14 +694,28 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) page_counter_read(&memcg->memory); } -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask); -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); + +/** + * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. + * @folio: Folio to charge. + * @mm: mm context of the allocating task. + * @gfp: Reclaim mode. + * + * Try to charge @folio to the memcg that @mm belongs to, reclaiming + * pages according to @gfp if necessary. If @mm is NULL, try to + * charge to the active memcg. + * + * Do not use this for folios allocated for swapin. + * + * Return: 0 on success. Otherwise, an error code is returned. + */ +static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, + gfp_t gfp) { if (mem_cgroup_disabled()) return 0; - return __mem_cgroup_charge(page, mm, gfp_mask); + return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, @@ -1199,8 +1213,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg) return false; } -static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +static inline int mem_cgroup_charge(struct folio *folio, + struct mm_struct *mm, gfp_t gfp) { return 0; } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index af24dc3febbe..6357c3580d07 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -167,7 +167,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, addr + PAGE_SIZE); if (new_page) { - err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL); + err = mem_cgroup_charge(page_folio(new_page), vma->vm_mm, + GFP_KERNEL); if (err) return err; } diff --git a/mm/filemap.c b/mm/filemap.c index d74be9fb3aa2..816af226f49d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -889,7 +889,7 @@ noinline int __add_to_page_cache_locked(struct page *page, page->index = offset; if (!huge) { - error = mem_cgroup_charge(page, NULL, gfp); + error = mem_cgroup_charge(page_folio(page), NULL, gfp); if (error) goto error; charged = true; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 5e9ef0fc261e..d49986a10d83 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -603,7 +603,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, VM_BUG_ON_PAGE(!PageCompound(page), page); - if (mem_cgroup_charge(page, vma->vm_mm, gfp)) { + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) { put_page(page); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 045cc579f724..8480a3b05bcc 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1087,7 +1087,7 @@ static void collapse_huge_page(struct mm_struct *mm, goto out_nolock; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out_nolock; } @@ -1658,7 +1658,7 @@ static void collapse_file(struct mm_struct *mm, goto out; } - if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) { + if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) { result = SCAN_CGROUP_CHARGE_FAIL; goto out; } diff --git a/mm/ksm.c b/mm/ksm.c index a5716fdec1aa..c246a0b0ac75 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -2578,7 +2578,8 @@ struct page *ksm_might_need_to_copy(struct page *page, return page; /* let do_swap_page report the error */ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); - if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) { + if (new_page && + mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) { put_page(new_page); new_page = NULL; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e352225970d2..dbca7bf92737 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6660,9 +6660,9 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root, atomic_long_read(&parent->memory.children_low_usage))); } -static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) +static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg, + gfp_t gfp) { - struct folio *folio = page_folio(page); long nr_pages = folio_nr_pages(folio); int ret; @@ -6675,34 +6675,19 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp) local_irq_disable(); mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, page_to_nid(page)); + memcg_check_events(memcg, folio_nid(folio)); local_irq_enable(); out: return ret; } -/** - * __mem_cgroup_charge - charge a newly allocated page to a cgroup - * @page: page to charge - * @mm: mm context of the victim - * @gfp_mask: reclaim mode - * - * Try to charge @page to the memcg that @mm belongs to, reclaiming - * pages according to @gfp_mask if necessary. if @mm is NULL, try to - * charge to the active memcg. - * - * Do not use this for pages allocated for swapin. - * - * Returns 0 on success. Otherwise, an error code is returned. - */ -int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, - gfp_t gfp_mask) +int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { struct mem_cgroup *memcg; int ret; memcg = get_mem_cgroup_from_mm(mm); - ret = charge_memcg(page, memcg, gfp_mask); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; @@ -6723,6 +6708,7 @@ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm, int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry) { + struct folio *folio = page_folio(page); struct mem_cgroup *memcg; unsigned short id; int ret; @@ -6737,7 +6723,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, memcg = get_mem_cgroup_from_mm(mm); rcu_read_unlock(); - ret = charge_memcg(page, memcg, gfp); + ret = charge_memcg(folio, memcg, gfp); css_put(&memcg->css); return ret; diff --git a/mm/memory.c b/mm/memory.c index 269992ba3fa3..b67d80526bee 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -990,7 +990,7 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, if (!new_page) return NULL; - if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) { put_page(new_page); return NULL; } @@ -3019,7 +3019,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) } } - if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL)) goto oom_free_new; cgroup_throttle_swaprate(new_page, GFP_KERNEL); @@ -3769,7 +3769,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf) if (!page) goto oom; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto oom_free_page; cgroup_throttle_swaprate(page, GFP_KERNEL); @@ -4193,7 +4193,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf) if (!vmf->cow_page) return VM_FAULT_OOM; - if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) { + if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm, + GFP_KERNEL)) { put_page(vmf->cow_page); return VM_FAULT_OOM; } diff --git a/mm/migrate.c b/mm/migrate.c index a6a7743ee98f..da55d2a8638d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2846,7 +2846,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (unlikely(anon_vma_prepare(vma))) goto abort; - if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL)) goto abort; /* diff --git a/mm/shmem.c b/mm/shmem.c index b5860f4a2738..a2e653aeb536 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -710,7 +710,7 @@ static int shmem_add_to_page_cache(struct page *page, page->index = index; if (!PageSwapCache(page)) { - error = mem_cgroup_charge(page, charge_mm, gfp); + error = mem_cgroup_charge(page_folio(page), charge_mm, gfp); if (error) { if (PageTransHuge(page)) { count_vm_event(THP_FILE_FALLBACK); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 7a9008415534..36e5f6ab976f 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -164,7 +164,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, __SetPageUptodate(page); ret = -ENOMEM; - if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL)) + if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL)) goto out_release; ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr, -- cgit v1.2.3 From bbc6b703b21963e909f633cf7718903ed5094319 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 1 May 2021 20:42:23 -0400 Subject: mm/memcg: Convert mem_cgroup_uncharge() to take a folio Convert all the callers to call page_folio(). Most of them were already using a head page, but a few of them I can't prove were, so this may actually fix a bug. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 15 +++++++++++---- mm/filemap.c | 2 +- mm/khugepaged.c | 4 ++-- mm/memcontrol.c | 14 ++++---------- mm/memory-failure.c | 2 +- mm/memremap.c | 2 +- mm/page_alloc.c | 2 +- mm/swap.c | 2 +- 8 files changed, 22 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 19a51729e00c..b4bc052db32b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -722,12 +722,19 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm, gfp_t gfp, swp_entry_t entry); void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry); -void __mem_cgroup_uncharge(struct page *page); -static inline void mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio); + +/** + * mem_cgroup_uncharge - Uncharge a folio. + * @folio: Folio to uncharge. + * + * Uncharge a folio previously charged with mem_cgroup_charge(). + */ +static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; - __mem_cgroup_uncharge(page); + __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_list(struct list_head *page_list); @@ -1229,7 +1236,7 @@ static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry) { } -static inline void mem_cgroup_uncharge(struct page *page) +static inline void mem_cgroup_uncharge(struct folio *folio) { } diff --git a/mm/filemap.c b/mm/filemap.c index 816af226f49d..44fcd9d1dd65 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -940,7 +940,7 @@ unlock: if (xas_error(&xas)) { error = xas_error(&xas); if (charged) - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); goto error; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 8480a3b05bcc..6d56e7abd2b8 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1211,7 +1211,7 @@ out_up_write: mmap_write_unlock(mm); out_nolock: if (!IS_ERR_OR_NULL(*hpage)) - mem_cgroup_uncharge(*hpage); + mem_cgroup_uncharge(page_folio(*hpage)); trace_mm_collapse_huge_page(mm, isolated, result); return; } @@ -1975,7 +1975,7 @@ xa_unlocked: out: VM_BUG_ON(!list_empty(&pagelist)); if (!IS_ERR_OR_NULL(*hpage)) - mem_cgroup_uncharge(*hpage); + mem_cgroup_uncharge(page_folio(*hpage)); /* TODO: tracepoints */ } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 64eac157db79..6321ed6d6e5a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6858,22 +6858,16 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) css_put(&memcg->css); } -/** - * __mem_cgroup_uncharge - uncharge a page - * @page: page to uncharge - * - * Uncharge a page previously charged with __mem_cgroup_charge(). - */ -void __mem_cgroup_uncharge(struct page *page) +void __mem_cgroup_uncharge(struct folio *folio) { struct uncharge_gather ug; - /* Don't touch page->lru of any random page, pre-check: */ - if (!page_memcg(page)) + /* Don't touch folio->lru of any random page, pre-check: */ + if (!folio_memcg(folio)) return; uncharge_gather_clear(&ug); - uncharge_folio(page_folio(page), &ug); + uncharge_folio(folio, &ug); uncharge_batch(&ug); } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3e6449f2102a..fffe4afaff43 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -762,7 +762,7 @@ static int delete_from_lru_cache(struct page *p) * Poisoned page might never drop its ref count to 0 so we have * to uncharge it manually from its memcg. */ - mem_cgroup_uncharge(p); + mem_cgroup_uncharge(page_folio(p)); /* * drop the page count elevated by isolate_lru_page() diff --git a/mm/memremap.c b/mm/memremap.c index ed593bf87109..5a66a71ab591 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -505,7 +505,7 @@ void free_devmap_managed_page(struct page *page) __ClearPageWaiters(page); - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); /* * When a device_private page is freed, the page->mapping field diff --git a/mm/page_alloc.c b/mm/page_alloc.c index b37435c274cf..869d0b06e1ef 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -724,7 +724,7 @@ static inline void free_the_page(struct page *page, unsigned int order) void free_compound_page(struct page *page) { - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); free_the_page(page, compound_order(page)); } diff --git a/mm/swap.c b/mm/swap.c index 0edbcb9c8876..5679ce5bc362 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -94,7 +94,7 @@ static void __page_cache_release(struct page *page) static void __put_single_page(struct page *page) { __page_cache_release(page); - mem_cgroup_uncharge(page); + mem_cgroup_uncharge(page_folio(page)); free_unref_page(page, 0); } -- cgit v1.2.3 From d21bba2b7d0ae19dd1279e10aee61c37a17aba74 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 6 May 2021 18:14:59 -0400 Subject: mm/memcg: Convert mem_cgroup_migrate() to take folios Convert all callers of mem_cgroup_migrate() to call page_folio() first. They all look like they're using head pages already, but this proves it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 4 ++-- mm/filemap.c | 4 +++- mm/memcontrol.c | 35 +++++++++++++++++------------------ mm/migrate.c | 4 +++- mm/shmem.c | 5 ++++- 5 files changed, 29 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b4bc052db32b..07eda24ec581 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -745,7 +745,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) __mem_cgroup_uncharge_list(page_list); } -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); +void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node @@ -1244,7 +1244,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } -static inline void mem_cgroup_migrate(struct page *old, struct page *new) +static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } diff --git a/mm/filemap.c b/mm/filemap.c index 44fcd9d1dd65..5368a4dcc35e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -835,6 +835,8 @@ EXPORT_SYMBOL(file_write_and_wait_range); */ void replace_page_cache_page(struct page *old, struct page *new) { + struct folio *fold = page_folio(old); + struct folio *fnew = page_folio(new); struct address_space *mapping = old->mapping; void (*freepage)(struct page *) = mapping->a_ops->freepage; pgoff_t offset = old->index; @@ -848,7 +850,7 @@ void replace_page_cache_page(struct page *old, struct page *new) new->mapping = mapping; new->index = offset; - mem_cgroup_migrate(old, new); + mem_cgroup_migrate(fold, fnew); xas_lock_irq(&xas); xas_store(&xas, new); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6321ed6d6e5a..c83d2f862f8a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6891,36 +6891,35 @@ void __mem_cgroup_uncharge_list(struct list_head *page_list) } /** - * mem_cgroup_migrate - charge a page's replacement - * @oldpage: currently circulating page - * @newpage: replacement page + * mem_cgroup_migrate - Charge a folio's replacement. + * @old: Currently circulating folio. + * @new: Replacement folio. * - * Charge @newpage as a replacement page for @oldpage. @oldpage will + * Charge @new as a replacement folio for @old. @old will * be uncharged upon free. * - * Both pages must be locked, @newpage->mapping must be set up. + * Both folios must be locked, @new->mapping must be set up. */ -void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) +void mem_cgroup_migrate(struct folio *old, struct folio *new) { - struct folio *newfolio = page_folio(newpage); struct mem_cgroup *memcg; - long nr_pages = folio_nr_pages(newfolio); + long nr_pages = folio_nr_pages(new); unsigned long flags; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); - VM_BUG_ON_FOLIO(PageAnon(oldpage) != folio_test_anon(newfolio), newfolio); - VM_BUG_ON_FOLIO(compound_nr(oldpage) != nr_pages, newfolio); + VM_BUG_ON_FOLIO(!folio_test_locked(old), old); + VM_BUG_ON_FOLIO(!folio_test_locked(new), new); + VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new); + VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new); if (mem_cgroup_disabled()) return; - /* Page cache replacement: new page already charged? */ - if (folio_memcg(newfolio)) + /* Page cache replacement: new folio already charged? */ + if (folio_memcg(new)) return; - memcg = page_memcg(oldpage); - VM_WARN_ON_ONCE_PAGE(!memcg, oldpage); + memcg = folio_memcg(old); + VM_WARN_ON_ONCE_FOLIO(!memcg, old); if (!memcg) return; @@ -6932,11 +6931,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) } css_get(&memcg->css); - commit_charge(newfolio, memcg); + commit_charge(new, memcg); local_irq_save(flags); mem_cgroup_charge_statistics(memcg, nr_pages); - memcg_check_events(memcg, page_to_nid(newpage)); + memcg_check_events(memcg, folio_nid(new)); local_irq_restore(flags); } diff --git a/mm/migrate.c b/mm/migrate.c index da55d2a8638d..bfb8ba490479 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -542,6 +542,8 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, */ void migrate_page_states(struct page *newpage, struct page *page) { + struct folio *folio = page_folio(page); + struct folio *newfolio = page_folio(newpage); int cpupid; if (PageError(page)) @@ -609,7 +611,7 @@ void migrate_page_states(struct page *newpage, struct page *page) copy_page_owner(page, newpage); if (!PageHuge(page)) - mem_cgroup_migrate(page, newpage); + mem_cgroup_migrate(folio, newfolio); } EXPORT_SYMBOL(migrate_page_states); diff --git a/mm/shmem.c b/mm/shmem.c index a2e653aeb536..1588f33d009a 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1637,6 +1637,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct page *oldpage, *newpage; + struct folio *old, *new; struct address_space *swap_mapping; swp_entry_t entry; pgoff_t swap_index; @@ -1673,7 +1674,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, xa_lock_irq(&swap_mapping->i_pages); error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { - mem_cgroup_migrate(oldpage, newpage); + old = page_folio(oldpage); + new = page_folio(newpage); + mem_cgroup_migrate(old, new); __inc_lruvec_page_state(newpage, NR_FILE_PAGES); __dec_lruvec_page_state(oldpage, NR_FILE_PAGES); } -- cgit v1.2.3 From 9d8053fc7a21ee2b3a540165d09418955258d9e8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 4 May 2021 11:43:01 -0400 Subject: mm/memcg: Convert mem_cgroup_track_foreign_dirty_slowpath() to folio The page was only being used for the memcg and to gather trace information, so this is a simple conversion. The only caller of mem_cgroup_track_foreign_dirty() will be converted to folios in a later patch, so doing this now makes that patch simpler. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 7 ++++--- include/trace/events/writeback.h | 8 ++++---- mm/memcontrol.c | 6 +++--- 3 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 07eda24ec581..1c2776c3a223 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1599,17 +1599,18 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { + struct folio *folio = page_folio(page); if (mem_cgroup_disabled()) return; - if (unlikely(&page_memcg(page)->css != wb->memcg_css)) - mem_cgroup_track_foreign_dirty_slowpath(page, wb); + if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 840d1ba84cf5..297871ca0004 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -236,9 +236,9 @@ TRACE_EVENT(inode_switch_wbs, TRACE_EVENT(track_foreign_dirty, - TP_PROTO(struct page *page, struct bdi_writeback *wb), + TP_PROTO(struct folio *folio, struct bdi_writeback *wb), - TP_ARGS(page, wb), + TP_ARGS(folio, wb), TP_STRUCT__entry( __array(char, name, 32) @@ -250,7 +250,7 @@ TRACE_EVENT(track_foreign_dirty, ), TP_fast_assign( - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); struct inode *inode = mapping ? mapping->host : NULL; strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32); @@ -258,7 +258,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup); + __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c83d2f862f8a..4a04bddefdbc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4516,17 +4516,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, * As being wrong occasionally doesn't matter, updates and accesses to the * records are lockless and racy. */ -void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, +void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb) { - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); struct memcg_cgwb_frn *frn; u64 now = get_jiffies_64(); u64 oldest_at = now; int oldest = -1; int i; - trace_track_foreign_dirty(page, wb); + trace_track_foreign_dirty(folio, wb); /* * Pick the slot to use. If there is already a slot for @wb, keep -- cgit v1.2.3 From f70ad448741580bf61cdfbeb02229c581409760a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 17:26:00 -0400 Subject: mm/memcg: Add folio_memcg_lock() and folio_memcg_unlock() These are the folio equivalents of lock_page_memcg() and unlock_page_memcg(). lock_page_memcg() and unlock_page_memcg() have too many callers to be easily replaced in a single patch, so reimplement them as wrappers for now to be cleaned up later when enough callers have been converted to use folios. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 10 ++++++++++ mm/memcontrol.c | 45 +++++++++++++++++++++++++++++---------------- 2 files changed, 39 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1c2776c3a223..be85450f066f 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -978,6 +978,8 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); extern bool cgroup_memory_noswap; #endif +void folio_memcg_lock(struct folio *folio); +void folio_memcg_unlock(struct folio *folio); void lock_page_memcg(struct page *page); void unlock_page_memcg(struct page *page); @@ -1397,6 +1399,14 @@ static inline void unlock_page_memcg(struct page *page) { } +static inline void folio_memcg_lock(struct folio *folio) +{ +} + +static inline void folio_memcg_unlock(struct folio *folio) +{ +} + static inline void mem_cgroup_handle_over_high(void) { } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4a04bddefdbc..23fe124fe78d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1933,18 +1933,17 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } /** - * lock_page_memcg - lock a page and memcg binding - * @page: the page + * folio_memcg_lock - Bind a folio to its memcg. + * @folio: The folio. * - * This function protects unlocked LRU pages from being moved to + * This function prevents unlocked LRU folios from being moved to * another cgroup. * - * It ensures lifetime of the locked memcg. Caller is responsible - * for the lifetime of the page. + * It ensures lifetime of the bound memcg. The caller is responsible + * for the lifetime of the folio. */ -void lock_page_memcg(struct page *page) +void folio_memcg_lock(struct folio *folio) { - struct page *head = compound_head(page); /* rmap on tail pages */ struct mem_cgroup *memcg; unsigned long flags; @@ -1958,7 +1957,7 @@ void lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return; again: - memcg = page_memcg(head); + memcg = folio_memcg(folio); if (unlikely(!memcg)) return; @@ -1972,7 +1971,7 @@ again: return; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != page_memcg(head)) { + if (memcg != folio_memcg(folio)) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -1986,9 +1985,15 @@ again: memcg->move_lock_task = current; memcg->move_lock_flags = flags; } +EXPORT_SYMBOL(folio_memcg_lock); + +void lock_page_memcg(struct page *page) +{ + folio_memcg_lock(page_folio(page)); +} EXPORT_SYMBOL(lock_page_memcg); -static void __unlock_page_memcg(struct mem_cgroup *memcg) +static void __folio_memcg_unlock(struct mem_cgroup *memcg) { if (memcg && memcg->move_lock_task == current) { unsigned long flags = memcg->move_lock_flags; @@ -2003,14 +2008,22 @@ static void __unlock_page_memcg(struct mem_cgroup *memcg) } /** - * unlock_page_memcg - unlock a page and memcg binding - * @page: the page + * folio_memcg_unlock - Release the binding between a folio and its memcg. + * @folio: The folio. + * + * This releases the binding created by folio_memcg_lock(). This does + * not change the accounting of this folio to its memcg, but it does + * permit others to change it. */ -void unlock_page_memcg(struct page *page) +void folio_memcg_unlock(struct folio *folio) { - struct page *head = compound_head(page); + __folio_memcg_unlock(folio_memcg(folio)); +} +EXPORT_SYMBOL(folio_memcg_unlock); - __unlock_page_memcg(page_memcg(head)); +void unlock_page_memcg(struct page *page) +{ + folio_memcg_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page_memcg); @@ -5643,7 +5656,7 @@ static int mem_cgroup_move_account(struct page *page, page->memcg_data = (unsigned long)to; - __unlock_page_memcg(from); + __folio_memcg_unlock(from); ret = 0; nid = page_to_nid(page); -- cgit v1.2.3 From b1baabd995ab8e830dbf647fe731b51e12b8cedd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 20:00:28 -0400 Subject: mm/memcg: Add folio_lruvec() This replaces mem_cgroup_page_lruvec(). All callers converted. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 20 +++++++++----------- mm/compaction.c | 2 +- mm/memcontrol.c | 9 ++++++--- mm/swap.c | 3 ++- mm/workingset.c | 3 ++- 5 files changed, 20 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index be85450f066f..35577caf27d9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -784,18 +784,17 @@ out: } /** - * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page - * @page: the page + * folio_lruvec - return lruvec for isolating/putting an LRU folio + * @folio: Pointer to the folio. * - * This function relies on page->mem_cgroup being stable. + * This function relies on folio->mem_cgroup being stable. */ -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec(struct folio *folio) { - pg_data_t *pgdat = page_pgdat(page); - struct mem_cgroup *memcg = page_memcg(page); + struct mem_cgroup *memcg = folio_memcg(folio); - VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page); - return mem_cgroup_lruvec(memcg, pgdat); + VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); + return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); @@ -1256,10 +1255,9 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, return &pgdat->__lruvec; } -static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec(struct folio *folio) { - pg_data_t *pgdat = page_pgdat(page); - + struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } diff --git a/mm/compaction.c b/mm/compaction.c index bfc93da1c2c7..37dfdf2b2287 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1022,7 +1022,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (!TestClearPageLRU(page)) goto isolate_fail_put; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(page_folio(page)); /* If we already hold the lock, we can skip some rechecking */ if (lruvec != locked) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c17681defeec..ea4f879d2771 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1154,9 +1154,10 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) */ struct lruvec *lock_page_lruvec(struct page *page) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); spin_lock(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1166,9 +1167,10 @@ struct lruvec *lock_page_lruvec(struct page *page) struct lruvec *lock_page_lruvec_irq(struct page *page) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); spin_lock_irq(&lruvec->lru_lock); lruvec_memcg_debug(lruvec, page); @@ -1178,9 +1180,10 @@ struct lruvec *lock_page_lruvec_irq(struct page *page) struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); spin_lock_irqsave(&lruvec->lru_lock, *flags); lruvec_memcg_debug(lruvec, page); diff --git a/mm/swap.c b/mm/swap.c index 5679ce5bc362..65a74c89e7cf 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -293,7 +293,8 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) void lru_note_cost_page(struct page *page) { - lru_note_cost(mem_cgroup_page_lruvec(page), + struct folio *folio = page_folio(page); + lru_note_cost(folio_lruvec(folio), page_is_file_lru(page), thp_nr_pages(page)); } diff --git a/mm/workingset.c b/mm/workingset.c index d5b81e4f4cbe..3deb408a240d 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -397,6 +397,7 @@ out: */ void workingset_activation(struct page *page) { + struct folio *folio = page_folio(page); struct mem_cgroup *memcg; struct lruvec *lruvec; @@ -411,7 +412,7 @@ void workingset_activation(struct page *page) memcg = page_memcg_rcu(page); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = mem_cgroup_page_lruvec(page); + lruvec = folio_lruvec(folio); workingset_age_nonresident(lruvec, thp_nr_pages(page)); out: rcu_read_unlock(); -- cgit v1.2.3 From e809c3fedeeb806993349e7bf797b4c2b728be7d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 28 Jun 2021 21:59:47 -0400 Subject: mm/memcg: Add folio_lruvec_lock() and similar functions These are the folio equivalents of lock_page_lruvec() and similar functions. Also convert lruvec_memcg_debug() to take a folio. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 32 ++++++++++--------- mm/compaction.c | 2 +- mm/huge_memory.c | 5 +-- mm/memcontrol.c | 77 +++++++++++++++++++++++++++++----------------- mm/rmap.c | 2 +- mm/swap.c | 8 +++-- mm/vmscan.c | 3 +- 7 files changed, 79 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 35577caf27d9..30d2cd7b5c9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -801,15 +801,16 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); -struct lruvec *lock_page_lruvec(struct page *page); -struct lruvec *lock_page_lruvec_irq(struct page *page); -struct lruvec *lock_page_lruvec_irqsave(struct page *page, +struct lruvec *folio_lruvec_lock(struct folio *folio); +struct lruvec *folio_lruvec_lock_irq(struct folio *folio); +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); #ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page); +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio); #else -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } #endif @@ -1261,7 +1262,8 @@ static inline struct lruvec *folio_lruvec(struct folio *folio) return &pgdat->__lruvec; } -static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +static inline +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { } @@ -1291,26 +1293,26 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } -static inline struct lruvec *lock_page_lruvec(struct page *page) +static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } -static inline struct lruvec *lock_page_lruvec_irq(struct page *page) +static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } -static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page, +static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { - struct pglist_data *pgdat = page_pgdat(page); + struct pglist_data *pgdat = folio_pgdat(folio); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; @@ -1576,6 +1578,7 @@ static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec) static inline struct lruvec *relock_page_lruvec_irq(struct page *page, struct lruvec *locked_lruvec) { + struct folio *folio = page_folio(page); if (locked_lruvec) { if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; @@ -1583,13 +1586,14 @@ static inline struct lruvec *relock_page_lruvec_irq(struct page *page, unlock_page_lruvec_irq(locked_lruvec); } - return lock_page_lruvec_irq(page); + return folio_lruvec_lock_irq(folio); } /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, struct lruvec *locked_lruvec, unsigned long *flags) { + struct folio *folio = page_folio(page); if (locked_lruvec) { if (page_matches_lruvec(page, locked_lruvec)) return locked_lruvec; @@ -1597,7 +1601,7 @@ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, unlock_page_lruvec_irqrestore(locked_lruvec, *flags); } - return lock_page_lruvec_irqsave(page, flags); + return folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK diff --git a/mm/compaction.c b/mm/compaction.c index 37dfdf2b2287..fbc60f964c38 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1032,7 +1032,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, compact_lock_irqsave(&lruvec->lru_lock, &flags, cc); locked = lruvec; - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, page_folio(page)); /* Try get exclusive access under lock */ if (!skip_updated) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d49986a10d83..e5ea5f775d5c 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2405,7 +2405,8 @@ static void __split_huge_page_tail(struct page *head, int tail, static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end) { - struct page *head = compound_head(page); + struct folio *folio = page_folio(page); + struct page *head = &folio->page; struct lruvec *lruvec; struct address_space *swap_cache = NULL; unsigned long offset = 0; @@ -2424,7 +2425,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, } /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ - lruvec = lock_page_lruvec(head); + lruvec = folio_lruvec_lock(folio); for (i = nr - 1; i >= 1; i--) { __split_huge_page_tail(head, i, lruvec, list); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ea4f879d2771..8dab23a71fc4 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1126,67 +1126,88 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, } #ifdef CONFIG_DEBUG_VM -void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page) +void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; - memcg = page_memcg(page); + memcg = folio_memcg(folio); if (!memcg) - VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page); + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio); else - VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page); + VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio); } #endif /** - * lock_page_lruvec - lock and return lruvec for a given page. - * @page: the page + * folio_lruvec_lock - Lock the lruvec for a folio. + * @folio: Pointer to the folio. * * These functions are safe to use under any of the following conditions: - * - page locked - * - PageLRU cleared - * - lock_page_memcg() - * - page->_refcount is zero + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held. */ -struct lruvec *lock_page_lruvec(struct page *page) +struct lruvec *folio_lruvec_lock(struct folio *folio) { - struct folio *folio = page_folio(page); - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = folio_lruvec(folio); spin_lock(&lruvec->lru_lock); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } -struct lruvec *lock_page_lruvec_irq(struct page *page) +/** + * folio_lruvec_lock_irq - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { - struct folio *folio = page_folio(page); - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = folio_lruvec(folio); spin_lock_irq(&lruvec->lru_lock); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } -struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags) +/** + * folio_lruvec_lock_irqsave - Lock the lruvec for a folio. + * @folio: Pointer to the folio. + * @flags: Pointer to irqsave flags. + * + * These functions are safe to use under any of the following conditions: + * - folio locked + * - folio_test_lru false + * - folio_memcg_lock() + * - folio frozen (refcount of 0) + * + * Return: The lruvec this folio is on with its lock held and interrupts + * disabled. + */ +struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, + unsigned long *flags) { - struct folio *folio = page_folio(page); - struct lruvec *lruvec; + struct lruvec *lruvec = folio_lruvec(folio); - lruvec = folio_lruvec(folio); spin_lock_irqsave(&lruvec->lru_lock, *flags); - - lruvec_memcg_debug(lruvec, page); + lruvec_memcg_debug(lruvec, folio); return lruvec; } diff --git a/mm/rmap.c b/mm/rmap.c index 6aebd1747251..059556dbefec 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -34,7 +34,7 @@ * mapping->private_lock (in __set_page_dirty_buffers) * lock_page_memcg move_lock (in __set_page_dirty_buffers) * i_pages lock (widely used) - * lruvec->lru_lock (in lock_page_lruvec_irq) + * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) diff --git a/mm/swap.c b/mm/swap.c index 65a74c89e7cf..d1fc964def12 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -80,10 +80,11 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = { static void __page_cache_release(struct page *page) { if (PageLRU(page)) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; unsigned long flags; - lruvec = lock_page_lruvec_irqsave(page, &flags); + lruvec = folio_lruvec_lock_irqsave(folio, &flags); del_page_from_lru_list(page, lruvec); __clear_page_lru_flags(page); unlock_page_lruvec_irqrestore(lruvec, flags); @@ -350,11 +351,12 @@ static inline void activate_page_drain(int cpu) static void activate_page(struct page *page) { + struct folio *folio = page_folio(page); struct lruvec *lruvec; - page = compound_head(page); + page = &folio->page; if (TestClearPageLRU(page)) { - lruvec = lock_page_lruvec_irq(page); + lruvec = folio_lruvec_lock_irq(folio); __activate_page(page, lruvec); unlock_page_lruvec_irq(lruvec); SetPageLRU(page); diff --git a/mm/vmscan.c b/mm/vmscan.c index 74296c2d1fed..8694e1549bcd 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2090,6 +2090,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, */ int isolate_lru_page(struct page *page) { + struct folio *folio = page_folio(page); int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); @@ -2099,7 +2100,7 @@ int isolate_lru_page(struct page *page) struct lruvec *lruvec; get_page(page); - lruvec = lock_page_lruvec_irq(page); + lruvec = folio_lruvec_lock_irq(folio); del_page_from_lru_list(page, lruvec); unlock_page_lruvec_irq(lruvec); ret = 0; -- cgit v1.2.3 From 0de340cbed3359423e38ed49242ac9d6986b5cfd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 29 Jun 2021 22:27:31 -0400 Subject: mm/memcg: Add folio_lruvec_relock_irq() and folio_lruvec_relock_irqsave() These are the folio equivalents of relock_page_lruvec_irq() and folio_lruvec_relock_irqsave(). Also convert page_matches_lruvec() to folio_matches_lruvec(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 17 ++++++++--------- mm/mlock.c | 3 ++- mm/swap.c | 13 ++++++++----- mm/vmscan.c | 5 +++-- 4 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 30d2cd7b5c9e..05094eaf1d61 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1568,19 +1568,19 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec, } /* Test requires a stable page->memcg binding, see page_memcg() */ -static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec) +static inline bool folio_matches_lruvec(struct folio *folio, + struct lruvec *lruvec) { - return lruvec_pgdat(lruvec) == page_pgdat(page) && - lruvec_memcg(lruvec) == page_memcg(page); + return lruvec_pgdat(lruvec) == folio_pgdat(folio) && + lruvec_memcg(lruvec) == folio_memcg(folio); } /* Don't lock again iff page's lruvec locked */ -static inline struct lruvec *relock_page_lruvec_irq(struct page *page, +static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, struct lruvec *locked_lruvec) { - struct folio *folio = page_folio(page); if (locked_lruvec) { - if (page_matches_lruvec(page, locked_lruvec)) + if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irq(locked_lruvec); @@ -1590,12 +1590,11 @@ static inline struct lruvec *relock_page_lruvec_irq(struct page *page, } /* Don't lock again iff page's lruvec locked */ -static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page, +static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio, struct lruvec *locked_lruvec, unsigned long *flags) { - struct folio *folio = page_folio(page); if (locked_lruvec) { - if (page_matches_lruvec(page, locked_lruvec)) + if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; unlock_page_lruvec_irqrestore(locked_lruvec, *flags); diff --git a/mm/mlock.c b/mm/mlock.c index 16d2ee160d43..e263d62ae2d0 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -271,6 +271,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) /* Phase 1: page isolation */ for (i = 0; i < nr; i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); if (TestClearPageMlocked(page)) { /* @@ -278,7 +279,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone) * so we can spare the get_page() here. */ if (TestClearPageLRU(page)) { - lruvec = relock_page_lruvec_irq(page, lruvec); + lruvec = folio_lruvec_relock_irq(folio, lruvec); del_page_from_lru_list(page, lruvec); continue; } else diff --git a/mm/swap.c b/mm/swap.c index d1fc964def12..57791ae80f2e 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -189,12 +189,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec, for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); /* block memcg migration during page moving between lru */ if (!TestClearPageLRU(page)) continue; - lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); + lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); (*move_fn)(page, lruvec); SetPageLRU(page); @@ -893,11 +894,12 @@ void release_pages(struct page **pages, int nr) int i; LIST_HEAD(pages_to_free); struct lruvec *lruvec = NULL; - unsigned long flags; + unsigned long flags = 0; unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; + struct folio *folio = page_folio(page); /* * Make sure the IRQ-safe lock-holding time does not get @@ -909,7 +911,7 @@ void release_pages(struct page **pages, int nr) lruvec = NULL; } - page = compound_head(page); + page = &folio->page; if (is_huge_zero_page(page)) continue; @@ -948,7 +950,7 @@ void release_pages(struct page **pages, int nr) if (PageLRU(page)) { struct lruvec *prev_lruvec = lruvec; - lruvec = relock_page_lruvec_irqsave(page, lruvec, + lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); if (prev_lruvec != lruvec) lock_batch = 0; @@ -1052,8 +1054,9 @@ void __pagevec_lru_add(struct pagevec *pvec) for (i = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); - lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags); + lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags); __pagevec_lru_add_fn(page, lruvec); } if (lruvec) diff --git a/mm/vmscan.c b/mm/vmscan.c index 8694e1549bcd..306229c4313f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2200,7 +2200,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec, * All pages were isolated from the same lruvec (and isolation * inhibits memcg migration). */ - VM_BUG_ON_PAGE(!page_matches_lruvec(page, lruvec), page); + VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page); add_page_to_lru_list(page, lruvec); nr_pages = thp_nr_pages(page); nr_moved += nr_pages; @@ -4666,6 +4666,7 @@ void check_move_unevictable_pages(struct pagevec *pvec) for (i = 0; i < pvec->nr; i++) { struct page *page = pvec->pages[i]; + struct folio *folio = page_folio(page); int nr_pages; if (PageTransTail(page)) @@ -4678,7 +4679,7 @@ void check_move_unevictable_pages(struct pagevec *pvec) if (!TestClearPageLRU(page)) continue; - lruvec = relock_page_lruvec_irq(page, lruvec); + lruvec = folio_lruvec_relock_irq(folio, lruvec); if (page_evictable(page) && PageUnevictable(page)) { del_page_from_lru_list(page, lruvec); ClearPageUnevictable(page); -- cgit v1.2.3 From c5ce619a77ce00d537ef512e7a823c99ce890a40 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 4 May 2021 17:19:13 -0400 Subject: mm/workingset: Convert workingset_activation to take a folio This function already assumed it was being passed a head page. No real change here, except that thp_nr_pages() compiles away on kernels with THP compiled out while folio_nr_pages() is always present. Also convert page_memcg_rcu() to folio_memcg_rcu(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 22 ++++++++++++---------- include/linux/swap.h | 2 +- mm/swap.c | 2 +- mm/workingset.c | 11 ++++------- 4 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 05094eaf1d61..7bd78c13d1fa 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -457,20 +457,22 @@ static inline struct mem_cgroup *page_memcg(struct page *page) return folio_memcg(page_folio(page)); } -/* - * page_memcg_rcu - locklessly get the memory cgroup associated with a page - * @page: a pointer to the page struct +/** + * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio. + * @folio: Pointer to the folio. * - * Returns a pointer to the memory cgroup associated with the page, - * or NULL. This function assumes that the page is known to have a + * This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function - * against some type of pages, e.g. slab pages or ex-slab pages. + * against some type of folios, e.g. slab folios or ex-slab folios. + * + * Return: A pointer to the memory cgroup associated with the folio, + * or NULL. */ -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { - unsigned long memcg_data = READ_ONCE(page->memcg_data); + unsigned long memcg_data = READ_ONCE(folio->memcg_data); - VM_BUG_ON_PAGE(PageSlab(page), page); + VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); WARN_ON_ONCE(!rcu_read_lock_held()); if (memcg_data & MEMCG_DATA_KMEM) { @@ -1158,7 +1160,7 @@ static inline struct mem_cgroup *page_memcg(struct page *page) return NULL; } -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio) { WARN_ON_ONCE(!rcu_read_lock_held()); return NULL; diff --git a/include/linux/swap.h b/include/linux/swap.h index c7ecd3ad8e2e..0fc84797623f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -330,7 +330,7 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); void workingset_refault(struct page *page, void *shadow); -void workingset_activation(struct page *page); +void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ void workingset_update_node(struct xa_node *node); diff --git a/mm/swap.c b/mm/swap.c index 57791ae80f2e..5c688897c013 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -429,7 +429,7 @@ void mark_page_accessed(struct page *page) else __lru_cache_activate_page(page); ClearPageReferenced(page); - workingset_activation(page); + workingset_activation(page_folio(page)); } if (page_is_idle(page)) clear_page_idle(page); diff --git a/mm/workingset.c b/mm/workingset.c index 3deb408a240d..1c96ed525a0e 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -393,13 +393,11 @@ out: /** * workingset_activation - note a page activation - * @page: page that is being activated + * @folio: Folio that is being activated. */ -void workingset_activation(struct page *page) +void workingset_activation(struct folio *folio) { - struct folio *folio = page_folio(page); struct mem_cgroup *memcg; - struct lruvec *lruvec; rcu_read_lock(); /* @@ -409,11 +407,10 @@ void workingset_activation(struct page *page) * XXX: See workingset_refault() - this should return * root_mem_cgroup even for !CONFIG_MEMCG. */ - memcg = page_memcg_rcu(page); + memcg = folio_memcg_rcu(folio); if (!mem_cgroup_disabled() && !memcg) goto out; - lruvec = folio_lruvec(folio); - workingset_age_nonresident(lruvec, thp_nr_pages(page)); + workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio)); out: rcu_read_unlock(); } -- cgit v1.2.3 From bf6bd276b374d44f6e7146d52aa6097eb91384a3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 7 May 2021 10:55:27 -0400 Subject: mm: Add folio_pfn() This is the folio equivalent of page_to_pfn(). Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Mike Rapoport Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 04e41d4d85ea..47143f3e7f0a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1624,6 +1624,20 @@ static inline unsigned long page_to_section(const struct page *page) } #endif +/** + * folio_pfn - Return the Page Frame Number of a folio. + * @folio: The folio. + * + * A folio may contain multiple pages. The pages have consecutive + * Page Frame Numbers. + * + * Return: The Page Frame Number of the first page in the folio. + */ +static inline unsigned long folio_pfn(struct folio *folio) +{ + return page_to_pfn(&folio->page); +} + /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */ #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3 From 2a5a8fa8b23144d14567d6f8293dd6fbeecee393 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 15 Sep 2021 18:16:01 +0200 Subject: leds: trigger: use RCU to protect the led_cdevs list Even with the previous commit 27af8e2c90fb ("leds: trigger: fix potential deadlock with libata") to this file, we still get lockdep unhappy, and Boqun explained the report here: https://lore.kernel.org/r/YNA+d1X4UkoQ7g8a@boqun-archlinux Effectively, this means that the read_lock_irqsave() isn't enough here because another CPU might be trying to do a write lock, and thus block the readers. This is all pretty messy, but it doesn't seem right that the LEDs framework imposes some locking requirements on users, in particular we'd have to make the spinlock in the iwlwifi driver always disable IRQs, even if we don't need that for any other reason, just to avoid this deadlock. Since writes to the led_cdevs list are rare (and are done by userspace), just switch the list to RCU. This costs a synchronize_rcu() at removal time so we can ensure things are correct, but that seems like a small price to pay for getting lock-free iterations and no deadlocks (nor any locking requirements imposed on users.) Signed-off-by: Johannes Berg Signed-off-by: Pavel Machek --- drivers/leds/led-triggers.c | 41 +++++++++++++++++++++-------------------- include/linux/leds.h | 2 +- 2 files changed, 22 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c index 4e7b78a84149..072491d3e17b 100644 --- a/drivers/leds/led-triggers.c +++ b/drivers/leds/led-triggers.c @@ -157,7 +157,6 @@ EXPORT_SYMBOL_GPL(led_trigger_read); /* Caller must ensure led_cdev->trigger_lock held */ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) { - unsigned long flags; char *event = NULL; char *envp[2]; const char *name; @@ -171,10 +170,13 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) /* Remove any existing trigger */ if (led_cdev->trigger) { - write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags); - list_del(&led_cdev->trig_list); - write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, - flags); + spin_lock(&led_cdev->trigger->leddev_list_lock); + list_del_rcu(&led_cdev->trig_list); + spin_unlock(&led_cdev->trigger->leddev_list_lock); + + /* ensure it's no longer visible on the led_cdevs list */ + synchronize_rcu(); + cancel_work_sync(&led_cdev->set_brightness_work); led_stop_software_blink(led_cdev); if (led_cdev->trigger->deactivate) @@ -186,9 +188,9 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig) led_set_brightness(led_cdev, LED_OFF); } if (trig) { - write_lock_irqsave(&trig->leddev_list_lock, flags); - list_add_tail(&led_cdev->trig_list, &trig->led_cdevs); - write_unlock_irqrestore(&trig->leddev_list_lock, flags); + spin_lock(&trig->leddev_list_lock); + list_add_tail_rcu(&led_cdev->trig_list, &trig->led_cdevs); + spin_unlock(&trig->leddev_list_lock); led_cdev->trigger = trig; if (trig->activate) @@ -223,9 +225,10 @@ err_add_groups: trig->deactivate(led_cdev); err_activate: - write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags); - list_del(&led_cdev->trig_list); - write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags); + spin_lock(&led_cdev->trigger->leddev_list_lock); + list_del_rcu(&led_cdev->trig_list); + spin_unlock(&led_cdev->trigger->leddev_list_lock); + synchronize_rcu(); led_cdev->trigger = NULL; led_cdev->trigger_data = NULL; led_set_brightness(led_cdev, LED_OFF); @@ -285,7 +288,7 @@ int led_trigger_register(struct led_trigger *trig) struct led_classdev *led_cdev; struct led_trigger *_trig; - rwlock_init(&trig->leddev_list_lock); + spin_lock_init(&trig->leddev_list_lock); INIT_LIST_HEAD(&trig->led_cdevs); down_write(&triggers_list_lock); @@ -378,15 +381,14 @@ void led_trigger_event(struct led_trigger *trig, enum led_brightness brightness) { struct led_classdev *led_cdev; - unsigned long flags; if (!trig) return; - read_lock_irqsave(&trig->leddev_list_lock, flags); - list_for_each_entry(led_cdev, &trig->led_cdevs, trig_list) + rcu_read_lock(); + list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) led_set_brightness(led_cdev, brightness); - read_unlock_irqrestore(&trig->leddev_list_lock, flags); + rcu_read_unlock(); } EXPORT_SYMBOL_GPL(led_trigger_event); @@ -397,20 +399,19 @@ static void led_trigger_blink_setup(struct led_trigger *trig, int invert) { struct led_classdev *led_cdev; - unsigned long flags; if (!trig) return; - read_lock_irqsave(&trig->leddev_list_lock, flags); - list_for_each_entry(led_cdev, &trig->led_cdevs, trig_list) { + rcu_read_lock(); + list_for_each_entry_rcu(led_cdev, &trig->led_cdevs, trig_list) { if (oneshot) led_blink_set_oneshot(led_cdev, delay_on, delay_off, invert); else led_blink_set(led_cdev, delay_on, delay_off); } - read_unlock_irqrestore(&trig->leddev_list_lock, flags); + rcu_read_unlock(); } void led_trigger_blink(struct led_trigger *trig, diff --git a/include/linux/leds.h b/include/linux/leds.h index a0b730be40ad..ba4861ec73d3 100644 --- a/include/linux/leds.h +++ b/include/linux/leds.h @@ -360,7 +360,7 @@ struct led_trigger { struct led_hw_trigger_type *trigger_type; /* LEDs under control by this trigger (for simple triggers) */ - rwlock_t leddev_list_lock; + spinlock_t leddev_list_lock; struct list_head led_cdevs; /* Link to next registered trigger */ -- cgit v1.2.3 From 4795448117824cc4900d696f17d1516c56371045 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 18 Sep 2021 14:53:44 +0200 Subject: PCI: ACPI: Drop acpi_pci_bus The acpi_pci_bus structure was used primarily for running acpi_pci_find_companion() during PCI device objects registration, but after commit 375553a93201 ("PCI: Setup ACPI fwnode early and at the same time with OF") that function is called by pci_setup_device() via pci_set_acpi_fwnode(), which happens before calling pci_device_add() on the new PCI device object, so its ACPI companion has been set already when acpi_device_notify() runs and it will never call ->find_companion() from acpi_pci_bus. For this reason, modify acpi_device_notify() and acpi_device_notify_remove() to call pci_acpi_setup() and pci_acpi_cleanup(), respectively, directly on PCI device objects and drop acpi_pci_bus altogether. While at it, notice that pci_acpi_setup() and pci_acpi_cleanup() can obtain the ACPI companion pointer, which is guaranteed to not be NULL, from their callers and modify them to work that way so as to reduce the number of redundant checks somewhat. Signed-off-by: Rafael J. Wysocki Tested-by: Ferry Toth --- drivers/acpi/glue.c | 34 ++++++++++++++++++++++------------ drivers/pci/pci-acpi.c | 31 +++---------------------------- include/linux/pci-acpi.h | 8 ++++++++ 3 files changed, 33 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 7a33a6d985f8..68768d6c8a47 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -17,6 +17,8 @@ #include #include #include +#include +#include #include #include "internal.h" @@ -307,13 +309,17 @@ void acpi_device_notify(struct device *dev) } adev = ACPI_COMPANION(dev); - if (dev_is_platform(dev)) - acpi_configure_pmsi_domain(dev); + if (dev_is_pci(dev)) { + pci_acpi_setup(dev, adev); + } else { + if (dev_is_platform(dev)) + acpi_configure_pmsi_domain(dev); - if (type && type->setup) - type->setup(dev); - else if (adev->handler && adev->handler->bind) - adev->handler->bind(dev); + if (type && type->setup) + type->setup(dev); + else if (adev->handler && adev->handler->bind) + adev->handler->bind(dev); + } acpi_handle_debug(ACPI_HANDLE(dev), "Bound to device %s\n", dev_name(dev)); @@ -327,16 +333,20 @@ err: void acpi_device_notify_remove(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); - struct acpi_bus_type *type; if (!adev) return; - type = acpi_get_bus_type(dev); - if (type && type->cleanup) - type->cleanup(dev); - else if (adev->handler && adev->handler->unbind) - adev->handler->unbind(dev); + if (dev_is_pci(dev)) { + pci_acpi_cleanup(dev, adev); + } else { + struct acpi_bus_type *type = acpi_get_bus_type(dev); + + if (type && type->cleanup) + type->cleanup(dev); + else if (adev->handler && adev->handler->unbind) + adev->handler->unbind(dev); + } acpi_unbind_one(dev); } diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 0f40943a9a18..d6720ebb252d 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -1353,13 +1353,9 @@ static void pci_acpi_set_external_facing(struct pci_dev *dev) dev->external_facing = 1; } -static void pci_acpi_setup(struct device *dev) +void pci_acpi_setup(struct device *dev, struct acpi_device *adev) { struct pci_dev *pci_dev = to_pci_dev(dev); - struct acpi_device *adev = ACPI_COMPANION(dev); - - if (!adev) - return; pci_acpi_optimize_delay(pci_dev, adev->handle); pci_acpi_set_external_facing(pci_dev); @@ -1383,14 +1379,10 @@ static void pci_acpi_setup(struct device *dev) acpi_device_power_add_dependent(adev, dev); } -static void pci_acpi_cleanup(struct device *dev) +void pci_acpi_cleanup(struct device *dev, struct acpi_device *adev) { - struct acpi_device *adev = ACPI_COMPANION(dev); struct pci_dev *pci_dev = to_pci_dev(dev); - if (!adev) - return; - pci_acpi_remove_edr_notifier(pci_dev); pci_acpi_remove_pm_notifier(adev); if (adev->wakeup.flags.valid) { @@ -1402,20 +1394,6 @@ static void pci_acpi_cleanup(struct device *dev) } } -static bool pci_acpi_bus_match(struct device *dev) -{ - return dev_is_pci(dev); -} - -static struct acpi_bus_type acpi_pci_bus = { - .name = "PCI", - .match = pci_acpi_bus_match, - .find_companion = acpi_pci_find_companion, - .setup = pci_acpi_setup, - .cleanup = pci_acpi_cleanup, -}; - - static struct fwnode_handle *(*pci_msi_get_fwnode_cb)(struct device *dev); /** @@ -1457,8 +1435,6 @@ struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus) static int __init acpi_pci_init(void) { - int ret; - if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_MSI) { pr_info("ACPI FADT declares the system doesn't support MSI, so disable it\n"); pci_no_msi(); @@ -1469,8 +1445,7 @@ static int __init acpi_pci_init(void) pcie_no_aspm(); } - ret = register_acpi_bus_type(&acpi_pci_bus); - if (ret) + if (acpi_pci_disabled) return 0; pci_set_platform_pm(&acpi_pci_platform_pm); diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h index f16de399d2de..078225b514d4 100644 --- a/include/linux/pci-acpi.h +++ b/include/linux/pci-acpi.h @@ -84,6 +84,14 @@ extern struct pci_bus *acpi_pci_root_create(struct acpi_pci_root *root, void acpi_pci_add_bus(struct pci_bus *bus); void acpi_pci_remove_bus(struct pci_bus *bus); +#ifdef CONFIG_PCI +void pci_acpi_setup(struct device *dev, struct acpi_device *adev); +void pci_acpi_cleanup(struct device *dev, struct acpi_device *adev); +#else +static inline void pci_acpi_setup(struct device *dev, struct acpi_device *adev) {} +static inline void pci_acpi_cleanup(struct device *dev, struct acpi_device *adev) {} +#endif + #ifdef CONFIG_ACPI_PCI_SLOT void acpi_pci_slot_init(void); void acpi_pci_slot_enumerate(struct pci_bus *bus); -- cgit v1.2.3 From e765f13ed126fe7e41d1a6e3c60d754cd6c2af93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 22 Sep 2021 19:34:30 +0200 Subject: nvdimm/pmem: move dax_attribute_group from dax to pmem dax_attribute_group is only used by the pmem driver, and can avoid the completely pointless lookup by the disk name if moved there. This leaves just a single caller of dax_get_by_host, so move dax_get_by_host into the same ifdef block as that caller. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20210922173431.2454024-3-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 100 +++++++++----------------------------------------- drivers/nvdimm/pmem.c | 43 ++++++++++++++++++++++ include/linux/dax.h | 2 - 3 files changed, 61 insertions(+), 84 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index fc89e91beea7..b882cf8106ea 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -63,6 +63,24 @@ static int dax_host_hash(const char *host) return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; } +#ifdef CONFIG_BLOCK +#include + +int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, + pgoff_t *pgoff) +{ + sector_t start_sect = bdev ? get_start_sect(bdev) : 0; + phys_addr_t phys_off = (start_sect + sector) * 512; + + if (pgoff) + *pgoff = PHYS_PFN(phys_off); + if (phys_off % PAGE_SIZE || size % PAGE_SIZE) + return -EINVAL; + return 0; +} +EXPORT_SYMBOL(bdev_dax_pgoff); + +#if IS_ENABLED(CONFIG_FS_DAX) /** * dax_get_by_host() - temporary lookup mechanism for filesystem-dax * @host: alternate name for the device registered by a dax driver @@ -94,24 +112,6 @@ static struct dax_device *dax_get_by_host(const char *host) return found; } -#ifdef CONFIG_BLOCK -#include - -int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, - pgoff_t *pgoff) -{ - sector_t start_sect = bdev ? get_start_sect(bdev) : 0; - phys_addr_t phys_off = (start_sect + sector) * 512; - - if (pgoff) - *pgoff = PHYS_PFN(phys_off); - if (phys_off % PAGE_SIZE || size % PAGE_SIZE) - return -EINVAL; - return 0; -} -EXPORT_SYMBOL(bdev_dax_pgoff); - -#if IS_ENABLED(CONFIG_FS_DAX) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { if (!blk_queue_dax(bdev->bd_disk->queue)) @@ -231,70 +231,6 @@ enum dax_device_flags { DAXDEV_SYNC, }; -static ssize_t write_cache_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct dax_device *dax_dev = dax_get_by_host(dev_name(dev)); - ssize_t rc; - - WARN_ON_ONCE(!dax_dev); - if (!dax_dev) - return -ENXIO; - - rc = sprintf(buf, "%d\n", !!dax_write_cache_enabled(dax_dev)); - put_dax(dax_dev); - return rc; -} - -static ssize_t write_cache_store(struct device *dev, - struct device_attribute *attr, const char *buf, size_t len) -{ - bool write_cache; - int rc = strtobool(buf, &write_cache); - struct dax_device *dax_dev = dax_get_by_host(dev_name(dev)); - - WARN_ON_ONCE(!dax_dev); - if (!dax_dev) - return -ENXIO; - - if (rc) - len = rc; - else - dax_write_cache(dax_dev, write_cache); - - put_dax(dax_dev); - return len; -} -static DEVICE_ATTR_RW(write_cache); - -static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n) -{ - struct device *dev = container_of(kobj, typeof(*dev), kobj); - struct dax_device *dax_dev = dax_get_by_host(dev_name(dev)); - - WARN_ON_ONCE(!dax_dev); - if (!dax_dev) - return 0; - -#ifndef CONFIG_ARCH_HAS_PMEM_API - if (a == &dev_attr_write_cache.attr) - return 0; -#endif - return a->mode; -} - -static struct attribute *dax_attributes[] = { - &dev_attr_write_cache.attr, - NULL, -}; - -struct attribute_group dax_attribute_group = { - .name = "dax", - .attrs = dax_attributes, - .is_visible = dax_visible, -}; -EXPORT_SYMBOL_GPL(dax_attribute_group); - /** * dax_direct_access() - translate a device pgoff to an absolute pfn * @dax_dev: a dax_device instance representing the logical memory range diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 72de88ff0d30..bccbc95f6d70 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -328,6 +328,49 @@ static const struct dax_operations pmem_dax_ops = { .zero_page_range = pmem_dax_zero_page_range, }; +static ssize_t write_cache_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pmem_device *pmem = dev_to_disk(dev)->private_data; + + return sprintf(buf, "%d\n", !!dax_write_cache_enabled(pmem->dax_dev)); +} + +static ssize_t write_cache_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct pmem_device *pmem = dev_to_disk(dev)->private_data; + bool write_cache; + int rc; + + rc = strtobool(buf, &write_cache); + if (rc) + return rc; + dax_write_cache(pmem->dax_dev, write_cache); + return len; +} +static DEVICE_ATTR_RW(write_cache); + +static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n) +{ +#ifndef CONFIG_ARCH_HAS_PMEM_API + if (a == &dev_attr_write_cache.attr) + return 0; +#endif + return a->mode; +} + +static struct attribute *dax_attributes[] = { + &dev_attr_write_cache.attr, + NULL, +}; + +static const struct attribute_group dax_attribute_group = { + .name = "dax", + .attrs = dax_attributes, + .is_visible = dax_visible, +}; + static const struct attribute_group *pmem_attribute_groups[] = { &dax_attribute_group, NULL, diff --git a/include/linux/dax.h b/include/linux/dax.h index 2619d94c308d..8623caa67388 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -38,8 +38,6 @@ struct dax_operations { int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; -extern struct attribute_group dax_attribute_group; - #if IS_ENABLED(CONFIG_DAX) struct dax_device *alloc_dax(void *private, const char *host, const struct dax_operations *ops, unsigned long flags); -- cgit v1.2.3 From 7b4d7894c65bd1e83b2f021d7944a46bdd64836a Mon Sep 17 00:00:00 2001 From: Deepak Kumar Singh Date: Tue, 31 Aug 2021 20:00:27 +0530 Subject: soc: qcom: aoss: Expose send for generic usecase Not all upcoming usecases will have an interface to allow the aoss driver to hook onto. Expose the send api and create a get function to enable drivers to send their own messages to aoss. Signed-off-by: Chris Lew Signed-off-by: Deepak Kumar Singh Reviewed-by: Stephen Boyd Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/1630420228-31075-2-git-send-email-deesin@codeaurora.org --- drivers/soc/qcom/qcom_aoss.c | 54 +++++++++++++++++++++++++++++++++++++- include/linux/soc/qcom/qcom_aoss.h | 38 +++++++++++++++++++++++++++ 2 files changed, 91 insertions(+), 1 deletion(-) create mode 100644 include/linux/soc/qcom/qcom_aoss.h (limited to 'include/linux') diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c index 536c3e4114fb..bb336cc8df6f 100644 --- a/drivers/soc/qcom/qcom_aoss.c +++ b/drivers/soc/qcom/qcom_aoss.c @@ -8,10 +8,12 @@ #include #include #include +#include #include #include #include #include +#include #define QMP_DESC_MAGIC 0x0 #define QMP_DESC_VERSION 0x4 @@ -223,11 +225,14 @@ static bool qmp_message_empty(struct qmp *qmp) * * Return: 0 on success, negative errno on failure */ -static int qmp_send(struct qmp *qmp, const void *data, size_t len) +int qmp_send(struct qmp *qmp, const void *data, size_t len) { long time_left; int ret; + if (WARN_ON(IS_ERR_OR_NULL(qmp) || !data)) + return -EINVAL; + if (WARN_ON(len + sizeof(u32) > qmp->size)) return -EINVAL; @@ -261,6 +266,7 @@ static int qmp_send(struct qmp *qmp, const void *data, size_t len) return ret; } +EXPORT_SYMBOL(qmp_send); static int qmp_qdss_clk_prepare(struct clk_hw *hw) { @@ -519,6 +525,51 @@ static void qmp_cooling_devices_remove(struct qmp *qmp) thermal_cooling_device_unregister(qmp->cooling_devs[i].cdev); } +/** + * qmp_get() - get a qmp handle from a device + * @dev: client device pointer + * + * Return: handle to qmp device on success, ERR_PTR() on failure + */ +struct qmp *qmp_get(struct device *dev) +{ + struct platform_device *pdev; + struct device_node *np; + struct qmp *qmp; + + if (!dev || !dev->of_node) + return ERR_PTR(-EINVAL); + + np = of_parse_phandle(dev->of_node, "qcom,qmp", 0); + if (!np) + return ERR_PTR(-ENODEV); + + pdev = of_find_device_by_node(np); + of_node_put(np); + if (!pdev) + return ERR_PTR(-EINVAL); + + qmp = platform_get_drvdata(pdev); + + return qmp ? qmp : ERR_PTR(-EPROBE_DEFER); +} +EXPORT_SYMBOL(qmp_get); + +/** + * qmp_put() - release a qmp handle + * @qmp: qmp handle obtained from qmp_get() + */ +void qmp_put(struct qmp *qmp) +{ + /* + * Match get_device() inside of_find_device_by_node() in + * qmp_get() + */ + if (!IS_ERR_OR_NULL(qmp)) + put_device(qmp->dev); +} +EXPORT_SYMBOL(qmp_put); + static int qmp_probe(struct platform_device *pdev) { struct resource *res; @@ -615,6 +666,7 @@ static struct platform_driver qmp_driver = { .driver = { .name = "qcom_aoss_qmp", .of_match_table = qmp_dt_match, + .suppress_bind_attrs = true, }, .probe = qmp_probe, .remove = qmp_remove, diff --git a/include/linux/soc/qcom/qcom_aoss.h b/include/linux/soc/qcom/qcom_aoss.h new file mode 100644 index 000000000000..3c2a82e606f8 --- /dev/null +++ b/include/linux/soc/qcom/qcom_aoss.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021, The Linux Foundation. All rights reserved. + */ + +#ifndef __QCOM_AOSS_H__ +#define __QCOM_AOSS_H__ + +#include +#include + +struct qmp; + +#if IS_ENABLED(CONFIG_QCOM_AOSS_QMP) + +int qmp_send(struct qmp *qmp, const void *data, size_t len); +struct qmp *qmp_get(struct device *dev); +void qmp_put(struct qmp *qmp); + +#else + +static inline int qmp_send(struct qmp *qmp, const void *data, size_t len) +{ + return -ENODEV; +} + +static inline struct qmp *qmp_get(struct device *dev) +{ + return ERR_PTR(-ENODEV); +} + +static inline void qmp_put(struct qmp *qmp) +{ +} + +#endif + +#endif -- cgit v1.2.3 From 99139b80c1b3d73026ed8be2de42c52e2976ab64 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Mon, 27 Sep 2021 14:55:40 +0100 Subject: soc: qcom: apr: make code more reuseable APR and other packet routers like GPR are pretty much same and interact with other drivers in similar way. Ex: GPR ports can be considered as APR services, only difference is they are allocated dynamically. Other difference is packet layout, which should not matter with the apis abstracted. Apart from this the rest of the functionality is pretty much identical across APR and GPR. Make the apr code more reusable by abstracting it service level, rather than device level so that we do not need to write new drivers for other new packet routers like GPR. This patch is in preparation to add GPR support to this driver. Signed-off-by: Srinivas Kandagatla Reviewed-by: Pierre-Louis Bossart Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210927135559.738-4-srinivas.kandagatla@linaro.org --- drivers/soc/qcom/apr.c | 129 ++++++++++++++++++++++++++----------------- include/linux/soc/qcom/apr.h | 12 +++- 2 files changed, 90 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index 475a57b435b2..bfad71e540ad 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -15,13 +15,18 @@ #include #include -struct apr { +enum { + PR_TYPE_APR = 0, +}; + +struct packet_router { struct rpmsg_endpoint *ch; struct device *dev; spinlock_t svcs_lock; spinlock_t rx_lock; struct idr svcs_idr; int dest_domain_id; + int type; struct pdr_handle *pdr; struct workqueue_struct *rxwq; struct work_struct rx_work; @@ -44,21 +49,21 @@ struct apr_rx_buf { */ int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt) { - struct apr *apr = dev_get_drvdata(adev->dev.parent); + struct packet_router *apr = dev_get_drvdata(adev->dev.parent); struct apr_hdr *hdr; unsigned long flags; int ret; - spin_lock_irqsave(&adev->lock, flags); + spin_lock_irqsave(&adev->svc.lock, flags); hdr = &pkt->hdr; hdr->src_domain = APR_DOMAIN_APPS; - hdr->src_svc = adev->svc_id; + hdr->src_svc = adev->svc.id; hdr->dest_domain = adev->domain_id; - hdr->dest_svc = adev->svc_id; + hdr->dest_svc = adev->svc.id; ret = rpmsg_trysend(apr->ch, pkt, hdr->pkt_size); - spin_unlock_irqrestore(&adev->lock, flags); + spin_unlock_irqrestore(&adev->svc.lock, flags); return ret ? ret : hdr->pkt_size; } @@ -74,7 +79,7 @@ static void apr_dev_release(struct device *dev) static int apr_callback(struct rpmsg_device *rpdev, void *buf, int len, void *priv, u32 addr) { - struct apr *apr = dev_get_drvdata(&rpdev->dev); + struct packet_router *apr = dev_get_drvdata(&rpdev->dev); struct apr_rx_buf *abuf; unsigned long flags; @@ -100,11 +105,11 @@ static int apr_callback(struct rpmsg_device *rpdev, void *buf, return 0; } - -static int apr_do_rx_callback(struct apr *apr, struct apr_rx_buf *abuf) +static int apr_do_rx_callback(struct packet_router *apr, struct apr_rx_buf *abuf) { uint16_t hdr_size, msg_type, ver, svc_id; - struct apr_device *svc = NULL; + struct pkt_router_svc *svc; + struct apr_device *adev; struct apr_driver *adrv = NULL; struct apr_resp_pkt resp; struct apr_hdr *hdr; @@ -145,12 +150,15 @@ static int apr_do_rx_callback(struct apr *apr, struct apr_rx_buf *abuf) svc_id = hdr->dest_svc; spin_lock_irqsave(&apr->svcs_lock, flags); svc = idr_find(&apr->svcs_idr, svc_id); - if (svc && svc->dev.driver) - adrv = to_apr_driver(svc->dev.driver); + if (svc && svc->dev->driver) { + adev = svc_to_apr_device(svc); + adrv = to_apr_driver(adev->dev.driver); + } spin_unlock_irqrestore(&apr->svcs_lock, flags); - if (!adrv) { - dev_err(apr->dev, "APR: service is not registered\n"); + if (!adrv || !adev) { + dev_err(apr->dev, "APR: service is not registered (%d)\n", + svc_id); return -EINVAL; } @@ -164,20 +172,26 @@ static int apr_do_rx_callback(struct apr *apr, struct apr_rx_buf *abuf) if (resp.payload_size > 0) resp.payload = buf + hdr_size; - adrv->callback(svc, &resp); + adrv->callback(adev, &resp); return 0; } static void apr_rxwq(struct work_struct *work) { - struct apr *apr = container_of(work, struct apr, rx_work); + struct packet_router *apr = container_of(work, struct packet_router, rx_work); struct apr_rx_buf *abuf, *b; unsigned long flags; if (!list_empty(&apr->rx_list)) { list_for_each_entry_safe(abuf, b, &apr->rx_list, node) { - apr_do_rx_callback(apr, abuf); + switch (apr->type) { + case PR_TYPE_APR: + apr_do_rx_callback(apr, abuf); + break; + default: + break; + } spin_lock_irqsave(&apr->rx_lock, flags); list_del(&abuf->node); spin_unlock_irqrestore(&apr->rx_lock, flags); @@ -201,7 +215,7 @@ static int apr_device_match(struct device *dev, struct device_driver *drv) while (id->domain_id != 0 || id->svc_id != 0) { if (id->domain_id == adev->domain_id && - id->svc_id == adev->svc_id) + id->svc_id == adev->svc.id) return 1; id++; } @@ -221,14 +235,14 @@ static void apr_device_remove(struct device *dev) { struct apr_device *adev = to_apr_device(dev); struct apr_driver *adrv; - struct apr *apr = dev_get_drvdata(adev->dev.parent); + struct packet_router *apr = dev_get_drvdata(adev->dev.parent); if (dev->driver) { adrv = to_apr_driver(dev->driver); if (adrv->remove) adrv->remove(adev); spin_lock(&apr->svcs_lock); - idr_remove(&apr->svcs_idr, adev->svc_id); + idr_remove(&apr->svcs_idr, adev->svc.id); spin_unlock(&apr->svcs_lock); } } @@ -255,28 +269,39 @@ struct bus_type aprbus = { EXPORT_SYMBOL_GPL(aprbus); static int apr_add_device(struct device *dev, struct device_node *np, - const struct apr_device_id *id) + u32 svc_id, u32 domain_id) { - struct apr *apr = dev_get_drvdata(dev); + struct packet_router *apr = dev_get_drvdata(dev); struct apr_device *adev = NULL; + struct pkt_router_svc *svc; int ret; adev = kzalloc(sizeof(*adev), GFP_KERNEL); if (!adev) return -ENOMEM; - spin_lock_init(&adev->lock); + adev->svc_id = svc_id; + svc = &adev->svc; + + svc->id = svc_id; + svc->pr = apr; + svc->priv = adev; + svc->dev = dev; + spin_lock_init(&svc->lock); + + adev->domain_id = domain_id; - adev->svc_id = id->svc_id; - adev->domain_id = id->domain_id; - adev->version = id->svc_version; if (np) snprintf(adev->name, APR_NAME_SIZE, "%pOFn", np); - else - strscpy(adev->name, id->name, APR_NAME_SIZE); - dev_set_name(&adev->dev, "aprsvc:%s:%x:%x", adev->name, - id->domain_id, id->svc_id); + switch (apr->type) { + case PR_TYPE_APR: + dev_set_name(&adev->dev, "aprsvc:%s:%x:%x", adev->name, + domain_id, svc_id); + break; + default: + break; + } adev->dev.bus = &aprbus; adev->dev.parent = dev; @@ -285,8 +310,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, adev->dev.driver = NULL; spin_lock(&apr->svcs_lock); - idr_alloc(&apr->svcs_idr, adev, id->svc_id, - id->svc_id + 1, GFP_ATOMIC); + idr_alloc(&apr->svcs_idr, svc, svc_id, svc_id + 1, GFP_ATOMIC); spin_unlock(&apr->svcs_lock); of_property_read_string_index(np, "qcom,protection-domain", @@ -306,7 +330,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, static int of_apr_add_pd_lookups(struct device *dev) { const char *service_name, *service_path; - struct apr *apr = dev_get_drvdata(dev); + struct packet_router *apr = dev_get_drvdata(dev); struct device_node *node; struct pdr_service *pds; int ret; @@ -336,13 +360,14 @@ static int of_apr_add_pd_lookups(struct device *dev) static void of_register_apr_devices(struct device *dev, const char *svc_path) { - struct apr *apr = dev_get_drvdata(dev); + struct packet_router *apr = dev_get_drvdata(dev); struct device_node *node; const char *service_path; int ret; for_each_child_of_node(dev->of_node, node) { - struct apr_device_id id = { {0} }; + u32 svc_id; + u32 domain_id; /* * This function is called with svc_path NULL during @@ -372,13 +397,13 @@ static void of_register_apr_devices(struct device *dev, const char *svc_path) continue; } - if (of_property_read_u32(node, "reg", &id.svc_id)) + if (of_property_read_u32(node, "reg", &svc_id)) continue; - id.domain_id = apr->dest_domain_id; + domain_id = apr->dest_domain_id; - if (apr_add_device(dev, node, &id)) - dev_err(dev, "Failed to add apr %d svc\n", id.svc_id); + if (apr_add_device(dev, node, svc_id, domain_id)) + dev_err(dev, "Failed to add apr %d svc\n", svc_id); } } @@ -398,7 +423,7 @@ static int apr_remove_device(struct device *dev, void *svc_path) static void apr_pd_status(int state, char *svc_path, void *priv) { - struct apr *apr = (struct apr *)priv; + struct packet_router *apr = (struct packet_router *)priv; switch (state) { case SERVREG_SERVICE_STATE_UP: @@ -413,16 +438,20 @@ static void apr_pd_status(int state, char *svc_path, void *priv) static int apr_probe(struct rpmsg_device *rpdev) { struct device *dev = &rpdev->dev; - struct apr *apr; + struct packet_router *apr; int ret; apr = devm_kzalloc(dev, sizeof(*apr), GFP_KERNEL); if (!apr) return -ENOMEM; - ret = of_property_read_u32(dev->of_node, "qcom,apr-domain", &apr->dest_domain_id); + ret = of_property_read_u32(dev->of_node, "qcom,domain", &apr->dest_domain_id); + if (ret) /* try deprecated apr-domain property */ + ret = of_property_read_u32(dev->of_node, "qcom,apr-domain", + &apr->dest_domain_id); + apr->type = PR_TYPE_APR; if (ret) { - dev_err(dev, "APR Domain ID not specified in DT\n"); + dev_err(dev, "Domain ID not specified in DT\n"); return ret; } @@ -465,7 +494,7 @@ destroy_wq: static void apr_remove(struct rpmsg_device *rpdev) { - struct apr *apr = dev_get_drvdata(&rpdev->dev); + struct packet_router *apr = dev_get_drvdata(&rpdev->dev); pdr_handle_release(apr->pdr); device_for_each_child(&rpdev->dev, NULL, apr_remove_device); @@ -502,20 +531,20 @@ void apr_driver_unregister(struct apr_driver *drv) } EXPORT_SYMBOL_GPL(apr_driver_unregister); -static const struct of_device_id apr_of_match[] = { +static const struct of_device_id pkt_router_of_match[] = { { .compatible = "qcom,apr"}, { .compatible = "qcom,apr-v2"}, {} }; -MODULE_DEVICE_TABLE(of, apr_of_match); +MODULE_DEVICE_TABLE(of, pkt_router_of_match); -static struct rpmsg_driver apr_driver = { +static struct rpmsg_driver packet_router_driver = { .probe = apr_probe, .remove = apr_remove, .callback = apr_callback, .drv = { .name = "qcom,apr", - .of_match_table = apr_of_match, + .of_match_table = pkt_router_of_match, }, }; @@ -525,7 +554,7 @@ static int __init apr_init(void) ret = bus_register(&aprbus); if (!ret) - ret = register_rpmsg_driver(&apr_driver); + ret = register_rpmsg_driver(&packet_router_driver); else bus_unregister(&aprbus); @@ -535,7 +564,7 @@ static int __init apr_init(void) static void __exit apr_exit(void) { bus_unregister(&aprbus); - unregister_rpmsg_driver(&apr_driver); + unregister_rpmsg_driver(&packet_router_driver); } subsys_initcall(apr_init); diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h index 137f9f2ac4c3..7bca213a3f83 100644 --- a/include/linux/soc/qcom/apr.h +++ b/include/linux/soc/qcom/apr.h @@ -79,6 +79,15 @@ struct apr_resp_pkt { #define APR_SVC_MAJOR_VERSION(v) ((v >> 16) & 0xFF) #define APR_SVC_MINOR_VERSION(v) (v & 0xFF) +struct packet_router; +struct pkt_router_svc { + struct device *dev; + struct packet_router *pr; + spinlock_t lock; + int id; + void *priv; +}; + struct apr_device { struct device dev; uint16_t svc_id; @@ -86,11 +95,12 @@ struct apr_device { uint32_t version; char name[APR_NAME_SIZE]; const char *service_path; - spinlock_t lock; + struct pkt_router_svc svc; struct list_head node; }; #define to_apr_device(d) container_of(d, struct apr_device, dev) +#define svc_to_apr_device(d) container_of(d, struct apr_device, svc) struct apr_driver { int (*probe)(struct apr_device *sl); -- cgit v1.2.3 From ec1471a898cca38af6b8956a83ebc1297214546f Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Mon, 27 Sep 2021 14:55:42 +0100 Subject: soc: qcom: apr: Add GPR support Qualcomm Generic Packet router aka GPR is the IPC mechanism found in AudioReach next generation signal processing framework to perform command and response messages between various processors. GPR has concepts of static and dynamic port, all static services like APM (Audio Processing Manager), PRM (Proxy resource manager) have fixed port numbers where as dynamic services like graphs have dynamic port numbers which are allocated at runtime. All GPR packet messages will have source and destination domain and port along with opcode and payload. Signed-off-by: Srinivas Kandagatla Reviewed-by: Pierre-Louis Bossart Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20210927135559.738-6-srinivas.kandagatla@linaro.org --- drivers/soc/qcom/Kconfig | 2 +- drivers/soc/qcom/apr.c | 166 +++++++++++++++++++++++++++++++++++++++++-- include/linux/soc/qcom/apr.h | 58 +++++++++++++++ 3 files changed, 219 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig index 79b568f82a1c..bfa2ab5772cf 100644 --- a/drivers/soc/qcom/Kconfig +++ b/drivers/soc/qcom/Kconfig @@ -199,7 +199,7 @@ config QCOM_WCNSS_CTRL firmware to a newly booted WCNSS chip. config QCOM_APR - tristate "Qualcomm APR Bus (Asynchronous Packet Router)" + tristate "Qualcomm APR/GPR Bus (Asynchronous/Generic Packet Router)" depends on ARCH_QCOM || COMPILE_TEST depends on RPMSG depends on NET diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index bfad71e540ad..8a9bfbcd4bb9 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -17,8 +17,13 @@ enum { PR_TYPE_APR = 0, + PR_TYPE_GPR, }; +/* Some random values tbh which does not collide with static modules */ +#define GPR_DYNAMIC_PORT_START 0x10000000 +#define GPR_DYNAMIC_PORT_END 0x20000000 + struct packet_router { struct rpmsg_endpoint *ch; struct device *dev; @@ -69,6 +74,83 @@ int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt) } EXPORT_SYMBOL_GPL(apr_send_pkt); +void gpr_free_port(gpr_port_t *port) +{ + struct packet_router *gpr = port->pr; + unsigned long flags; + + spin_lock_irqsave(&gpr->svcs_lock, flags); + idr_remove(&gpr->svcs_idr, port->id); + spin_unlock_irqrestore(&gpr->svcs_lock, flags); + + kfree(port); +} +EXPORT_SYMBOL_GPL(gpr_free_port); + +gpr_port_t *gpr_alloc_port(struct apr_device *gdev, struct device *dev, + gpr_port_cb cb, void *priv) +{ + struct packet_router *pr = dev_get_drvdata(gdev->dev.parent); + gpr_port_t *port; + struct pkt_router_svc *svc; + int id; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return ERR_PTR(-ENOMEM); + + svc = port; + svc->callback = cb; + svc->pr = pr; + svc->priv = priv; + svc->dev = dev; + spin_lock_init(&svc->lock); + + spin_lock(&pr->svcs_lock); + id = idr_alloc_cyclic(&pr->svcs_idr, svc, GPR_DYNAMIC_PORT_START, + GPR_DYNAMIC_PORT_END, GFP_ATOMIC); + if (id < 0) { + dev_err(dev, "Unable to allocate dynamic GPR src port\n"); + kfree(port); + spin_unlock(&pr->svcs_lock); + return ERR_PTR(id); + } + + svc->id = id; + spin_unlock(&pr->svcs_lock); + + return port; +} +EXPORT_SYMBOL_GPL(gpr_alloc_port); + +static int pkt_router_send_svc_pkt(struct pkt_router_svc *svc, struct gpr_pkt *pkt) +{ + struct packet_router *pr = svc->pr; + struct gpr_hdr *hdr; + unsigned long flags; + int ret; + + hdr = &pkt->hdr; + + spin_lock_irqsave(&svc->lock, flags); + ret = rpmsg_trysend(pr->ch, pkt, hdr->pkt_size); + spin_unlock_irqrestore(&svc->lock, flags); + + return ret ? ret : hdr->pkt_size; +} + +int gpr_send_pkt(struct apr_device *gdev, struct gpr_pkt *pkt) +{ + return pkt_router_send_svc_pkt(&gdev->svc, pkt); +} +EXPORT_SYMBOL_GPL(gpr_send_pkt); + +int gpr_send_port_pkt(gpr_port_t *port, struct gpr_pkt *pkt) +{ + return pkt_router_send_svc_pkt(port, pkt); +} +EXPORT_SYMBOL_GPL(gpr_send_port_pkt); + static void apr_dev_release(struct device *dev) { struct apr_device *adev = to_apr_device(dev); @@ -177,6 +259,59 @@ static int apr_do_rx_callback(struct packet_router *apr, struct apr_rx_buf *abuf return 0; } +static int gpr_do_rx_callback(struct packet_router *gpr, struct apr_rx_buf *abuf) +{ + uint16_t hdr_size, ver; + struct pkt_router_svc *svc = NULL; + struct gpr_resp_pkt resp; + struct gpr_hdr *hdr; + unsigned long flags; + void *buf = abuf->buf; + int len = abuf->len; + + hdr = buf; + ver = hdr->version; + if (ver > GPR_PKT_VER + 1) + return -EINVAL; + + hdr_size = hdr->hdr_size; + if (hdr_size < GPR_PKT_HEADER_WORD_SIZE) { + dev_err(gpr->dev, "GPR: Wrong hdr size:%d\n", hdr_size); + return -EINVAL; + } + + if (hdr->pkt_size < GPR_PKT_HEADER_BYTE_SIZE || hdr->pkt_size != len) { + dev_err(gpr->dev, "GPR: Wrong packet size\n"); + return -EINVAL; + } + + resp.hdr = *hdr; + resp.payload_size = hdr->pkt_size - (hdr_size * 4); + + /* + * NOTE: hdr_size is not same as GPR_HDR_SIZE as remote can include + * optional headers in to gpr_hdr which should be ignored + */ + if (resp.payload_size > 0) + resp.payload = buf + (hdr_size * 4); + + + spin_lock_irqsave(&gpr->svcs_lock, flags); + svc = idr_find(&gpr->svcs_idr, hdr->dest_port); + spin_unlock_irqrestore(&gpr->svcs_lock, flags); + + if (!svc) { + dev_err(gpr->dev, "GPR: Port(%x) is not registered\n", + hdr->dest_port); + return -EINVAL; + } + + if (svc->callback) + svc->callback(&resp, svc->priv, 0); + + return 0; +} + static void apr_rxwq(struct work_struct *work) { struct packet_router *apr = container_of(work, struct packet_router, rx_work); @@ -189,6 +324,9 @@ static void apr_rxwq(struct work_struct *work) case PR_TYPE_APR: apr_do_rx_callback(apr, abuf); break; + case PR_TYPE_GPR: + gpr_do_rx_callback(apr, abuf); + break; default: break; } @@ -227,8 +365,13 @@ static int apr_device_probe(struct device *dev) { struct apr_device *adev = to_apr_device(dev); struct apr_driver *adrv = to_apr_driver(dev->driver); + int ret; - return adrv->probe(adev); + ret = adrv->probe(adev); + if (!ret) + adev->svc.callback = adrv->gpr_callback; + + return ret; } static void apr_device_remove(struct device *dev) @@ -299,6 +442,10 @@ static int apr_add_device(struct device *dev, struct device_node *np, dev_set_name(&adev->dev, "aprsvc:%s:%x:%x", adev->name, domain_id, svc_id); break; + case PR_TYPE_GPR: + dev_set_name(&adev->dev, "gprsvc:%s:%x:%x", adev->name, + domain_id, svc_id); + break; default: break; } @@ -316,7 +463,7 @@ static int apr_add_device(struct device *dev, struct device_node *np, of_property_read_string_index(np, "qcom,protection-domain", 1, &adev->service_path); - dev_info(dev, "Adding APR dev: %s\n", dev_name(&adev->dev)); + dev_info(dev, "Adding APR/GPR dev: %s\n", dev_name(&adev->dev)); ret = device_register(&adev->dev); if (ret) { @@ -446,10 +593,16 @@ static int apr_probe(struct rpmsg_device *rpdev) return -ENOMEM; ret = of_property_read_u32(dev->of_node, "qcom,domain", &apr->dest_domain_id); - if (ret) /* try deprecated apr-domain property */ - ret = of_property_read_u32(dev->of_node, "qcom,apr-domain", - &apr->dest_domain_id); - apr->type = PR_TYPE_APR; + + if (of_device_is_compatible(dev->of_node, "qcom,gpr")) { + apr->type = PR_TYPE_GPR; + } else { + if (ret) /* try deprecated apr-domain property */ + ret = of_property_read_u32(dev->of_node, "qcom,apr-domain", + &apr->dest_domain_id); + apr->type = PR_TYPE_APR; + } + if (ret) { dev_err(dev, "Domain ID not specified in DT\n"); return ret; @@ -534,6 +687,7 @@ EXPORT_SYMBOL_GPL(apr_driver_unregister); static const struct of_device_id pkt_router_of_match[] = { { .compatible = "qcom,apr"}, { .compatible = "qcom,apr-v2"}, + { .compatible = "qcom,gpr"}, {} }; MODULE_DEVICE_TABLE(of, pkt_router_of_match); diff --git a/include/linux/soc/qcom/apr.h b/include/linux/soc/qcom/apr.h index 7bca213a3f83..23c5b30f3511 100644 --- a/include/linux/soc/qcom/apr.h +++ b/include/linux/soc/qcom/apr.h @@ -7,6 +7,7 @@ #include #include #include +#include extern struct bus_type aprbus; @@ -75,19 +76,65 @@ struct apr_resp_pkt { int payload_size; }; +struct gpr_hdr { + uint32_t version:4; + uint32_t hdr_size:4; + uint32_t pkt_size:24; + uint32_t dest_domain:8; + uint32_t src_domain:8; + uint32_t reserved:16; + uint32_t src_port; + uint32_t dest_port; + uint32_t token; + uint32_t opcode; +} __packed; + +struct gpr_pkt { + struct gpr_hdr hdr; + uint32_t payload[]; +}; + +struct gpr_resp_pkt { + struct gpr_hdr hdr; + void *payload; + int payload_size; +}; + +#define GPR_HDR_SIZE sizeof(struct gpr_hdr) +#define GPR_PKT_VER 0x0 +#define GPR_PKT_HEADER_WORD_SIZE ((sizeof(struct gpr_pkt) + 3) >> 2) +#define GPR_PKT_HEADER_BYTE_SIZE (GPR_PKT_HEADER_WORD_SIZE << 2) + +#define GPR_BASIC_RSP_RESULT 0x02001005 + +struct gpr_ibasic_rsp_result_t { + uint32_t opcode; + uint32_t status; +}; + +#define GPR_BASIC_EVT_ACCEPTED 0x02001006 + +struct gpr_ibasic_rsp_accepted_t { + uint32_t opcode; +}; + /* Bits 0 to 15 -- Minor version, Bits 16 to 31 -- Major version */ #define APR_SVC_MAJOR_VERSION(v) ((v >> 16) & 0xFF) #define APR_SVC_MINOR_VERSION(v) (v & 0xFF) +typedef int (*gpr_port_cb) (struct gpr_resp_pkt *d, void *priv, int op); struct packet_router; struct pkt_router_svc { struct device *dev; + gpr_port_cb callback; struct packet_router *pr; spinlock_t lock; int id; void *priv; }; +typedef struct pkt_router_svc gpr_port_t; + struct apr_device { struct device dev; uint16_t svc_id; @@ -99,6 +146,8 @@ struct apr_device { struct list_head node; }; +typedef struct apr_device gpr_device_t; + #define to_apr_device(d) container_of(d, struct apr_device, dev) #define svc_to_apr_device(d) container_of(d, struct apr_device, svc) @@ -107,10 +156,12 @@ struct apr_driver { int (*remove)(struct apr_device *sl); int (*callback)(struct apr_device *a, struct apr_resp_pkt *d); + int (*gpr_callback)(struct gpr_resp_pkt *d, void *data, int op); struct device_driver driver; const struct apr_device_id *id_table; }; +typedef struct apr_driver gpr_driver_t; #define to_apr_driver(d) container_of(d, struct apr_driver, driver) /* @@ -133,7 +184,14 @@ void apr_driver_unregister(struct apr_driver *drv); #define module_apr_driver(__apr_driver) \ module_driver(__apr_driver, apr_driver_register, \ apr_driver_unregister) +#define module_gpr_driver(__gpr_driver) module_apr_driver(__gpr_driver) int apr_send_pkt(struct apr_device *adev, struct apr_pkt *pkt); +gpr_port_t *gpr_alloc_port(gpr_device_t *gdev, struct device *dev, + gpr_port_cb cb, void *priv); +void gpr_free_port(gpr_port_t *port); +int gpr_send_port_pkt(gpr_port_t *port, struct gpr_pkt *pkt); +int gpr_send_pkt(gpr_device_t *gdev, struct gpr_pkt *pkt); + #endif /* __QCOM_APR_H_ */ -- cgit v1.2.3 From af3826db74d184bc9c2c9d3ff34548e5f317a6f3 Mon Sep 17 00:00:00 2001 From: Geetha sowjanya Date: Tue, 28 Sep 2021 11:25:26 +0530 Subject: octeontx2-pf: Use hardware register for CQE count Current driver uses software CQ head pointer to poll on CQE header in memory to determine if CQE is valid. Software needs to make sure, that the reads of the CQE do not get re-ordered so much that it ends up with an inconsistent view of the CQE. To ensure that DMB barrier after read to first CQE cacheline and before reading of the rest of the CQE is needed. But having barrier for every CQE read will impact the performance, instead use hardware CQ head and tail pointers to find the valid number of CQEs. Signed-off-by: Geetha sowjanya Signed-off-by: Sunil Kovvuri Goutham Signed-off-by: David S. Miller --- .../ethernet/marvell/octeontx2/nic/otx2_common.c | 3 + .../ethernet/marvell/octeontx2/nic/otx2_common.h | 1 + .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 69 +++++++++++++++++++--- .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.h | 5 ++ include/linux/soc/marvell/octeontx2/asm.h | 14 +++++ 5 files changed, 85 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 78df173e6df2..4c3dbade8cfb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1006,6 +1006,9 @@ int otx2_config_nix_queues(struct otx2_nic *pfvf) return err; } + pfvf->cq_op_addr = (__force u64 *)otx2_get_regaddr(pfvf, + NIX_LF_CQ_OP_STATUS); + /* Initialize work queue for receive buffer refill */ pfvf->refill_wrk = devm_kcalloc(pfvf->dev, pfvf->qset.cq_cnt, sizeof(struct refill_work), GFP_KERNEL); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 0a792fce55f1..069d1b925102 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -343,6 +343,7 @@ struct otx2_nic { #define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13) #define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14) u64 flags; + u64 *cq_op_addr; struct otx2_qset qset; struct otx2_hw hw; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index f42b1d4e0c67..3f3ec8ffc4dd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -18,6 +18,31 @@ #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx))) +static int otx2_nix_cq_op_status(struct otx2_nic *pfvf, + struct otx2_cq_queue *cq) +{ + u64 incr = (u64)(cq->cq_idx) << 32; + u64 status; + + status = otx2_atomic64_fetch_add(incr, pfvf->cq_op_addr); + + if (unlikely(status & BIT_ULL(CQ_OP_STAT_OP_ERR) || + status & BIT_ULL(CQ_OP_STAT_CQ_ERR))) { + dev_err(pfvf->dev, "CQ stopped due to error"); + return -EINVAL; + } + + cq->cq_tail = status & 0xFFFFF; + cq->cq_head = (status >> 20) & 0xFFFFF; + if (cq->cq_tail < cq->cq_head) + cq->pend_cqe = (cq->cqe_cnt - cq->cq_head) + + cq->cq_tail; + else + cq->pend_cqe = cq->cq_tail - cq->cq_head; + + return 0; +} + static struct nix_cqe_hdr_s *otx2_get_next_cqe(struct otx2_cq_queue *cq) { struct nix_cqe_hdr_s *cqe_hdr; @@ -318,7 +343,14 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, struct nix_cqe_rx_s *cqe; int processed_cqe = 0; - while (likely(processed_cqe < budget)) { + if (cq->pend_cqe >= budget) + goto process_cqe; + + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return 0; + +process_cqe: + while (likely(processed_cqe < budget) && cq->pend_cqe) { cqe = (struct nix_cqe_rx_s *)CQE_ADDR(cq, cq->cq_head); if (cqe->hdr.cqe_type == NIX_XQE_TYPE_INVALID || !cqe->sg.seg_addr) { @@ -334,6 +366,7 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf, cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; cqe->sg.seg_addr = 0x00; processed_cqe++; + cq->pend_cqe--; } /* Free CQEs to HW */ @@ -368,7 +401,14 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, struct nix_cqe_tx_s *cqe; int processed_cqe = 0; - while (likely(processed_cqe < budget)) { + if (cq->pend_cqe >= budget) + goto process_cqe; + + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return 0; + +process_cqe: + while (likely(processed_cqe < budget) && cq->pend_cqe) { cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq); if (unlikely(!cqe)) { if (!processed_cqe) @@ -380,6 +420,7 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf, cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID; processed_cqe++; + cq->pend_cqe--; } /* Free CQEs to HW */ @@ -936,10 +977,16 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) int processed_cqe = 0; u64 iova, pa; - while ((cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq))) { - if (!cqe->sg.subdc) - continue; + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return; + + while (cq->pend_cqe) { + cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq); processed_cqe++; + cq->pend_cqe--; + + if (!cqe) + continue; if (cqe->sg.segs > 1) { otx2_free_rcv_seg(pfvf, cqe, cq->cq_idx); continue; @@ -965,7 +1012,16 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) sq = &pfvf->qset.sq[cq->cint_idx]; - while ((cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq))) { + if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) + return; + + while (cq->pend_cqe) { + cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq); + processed_cqe++; + cq->pend_cqe--; + + if (!cqe) + continue; sg = &sq->sg[cqe->comp.sqe_id]; skb = (struct sk_buff *)sg->skb; if (skb) { @@ -973,7 +1029,6 @@ void otx2_cleanup_tx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq) dev_kfree_skb_any(skb); sg->skb = (u64)NULL; } - processed_cqe++; } /* Free CQEs to HW */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h index 3ff1ad79c001..6a97631ff226 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h @@ -56,6 +56,9 @@ */ #define CQ_QCOUNT_DEFAULT 1 +#define CQ_OP_STAT_OP_ERR 63 +#define CQ_OP_STAT_CQ_ERR 46 + struct queue_stats { u64 bytes; u64 pkts; @@ -122,6 +125,8 @@ struct otx2_cq_queue { u16 pool_ptrs; u32 cqe_cnt; u32 cq_head; + u32 cq_tail; + u32 pend_cqe; void *cqe_base; struct qmem *cqe; struct otx2_pool *rbpool; diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index fa1d6af0164e..0f79fd7f81a1 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -34,9 +34,23 @@ : [rf] "+r"(val) \ : [rs] "r"(addr)); \ }) + +static inline u64 otx2_atomic64_fetch_add(u64 incr, u64 *ptr) +{ + u64 result; + + asm volatile (".cpu generic+lse\n" + "ldadda %x[i], %x[r], [%[b]]" + : [r] "=r" (result), "+m" (*ptr) + : [i] "r" (incr), [b] "r" (ptr) + : "memory"); + return result; +} + #else #define otx2_lmt_flush(ioaddr) ({ 0; }) #define cn10k_lmt_flush(val, addr) ({ addr = val; }) +#define otx2_atomic64_fetch_add(incr, ptr) ({ incr; }) #endif #endif /* __SOC_OTX2_ASM_H */ -- cgit v1.2.3 From 62b8963cd84df1fc04986cd9b27586acce758f36 Mon Sep 17 00:00:00 2001 From: Pradeep Kumar Chitrapu Date: Tue, 28 Sep 2021 14:00:45 +0300 Subject: ieee80211: Add new A-MPDU factor macro for HE 6 GHz peer caps Add IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR as per IEEE Std 802.11ax-2021, 9.4.2.263 to use for peer max A-MPDU factor in 6 GHz band. Signed-off-by: Pradeep Kumar Chitrapu Signed-off-by: Jouni Malinen Acked-by: Johannes Berg Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20210913175510.193005-1-jouni@codeaurora.org --- include/linux/ieee80211.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 694264503119..a1a7eda35cb5 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2084,6 +2084,7 @@ int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, #define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 #define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 +#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR 13 /* 802.11ax HE PHY capabilities */ #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 -- cgit v1.2.3 From 8de1e9b01b03d2805f58aa490ea5bf0df003bc80 Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Wed, 22 Sep 2021 11:28:50 +0300 Subject: net/mlx5: Add uid field to UAR allocation structures Add uid field to mlx5_ifc_alloc_uar_in_bits and mlx5_ifc_dealloc_uar_out_bits structs. This field will be used by FW to manage UAR according to uid. Signed-off-by: Meir Lichtinger Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f3638d09ba77..96f5fb2af811 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -7569,7 +7569,7 @@ struct mlx5_ifc_dealloc_uar_out_bits { struct mlx5_ifc_dealloc_uar_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; @@ -8416,7 +8416,7 @@ struct mlx5_ifc_alloc_uar_out_bits { struct mlx5_ifc_alloc_uar_in_bits { u8 opcode[0x10]; - u8 reserved_at_10[0x10]; + u8 uid[0x10]; u8 reserved_at_20[0x10]; u8 op_mod[0x10]; -- cgit v1.2.3 From d2c8a1554c10d5e0443b1f97f480d7dacd55cf55 Mon Sep 17 00:00:00 2001 From: Meir Lichtinger Date: Wed, 22 Sep 2021 11:28:51 +0300 Subject: IB/mlx5: Enable UAR to have DevX UID UID field was added to alloc_uar and dealloc_uar PRM command, to specify DevX UID for UAR. This change enables firmware validating user access to its own UAR resources. For the kernel allocated UARs the UID will stay 0 as of today. Signed-off-by: Meir Lichtinger Reviewed-by: Yishai Hadas Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/cmd.c | 26 +++++++++++++ drivers/infiniband/hw/mlx5/cmd.h | 2 + drivers/infiniband/hw/mlx5/main.c | 55 +++++++++++++++------------ drivers/net/ethernet/mellanox/mlx5/core/uar.c | 14 +++---- include/linux/mlx5/driver.h | 2 - 5 files changed, 66 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index a8db8a051170..ff3742b0460a 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -206,3 +206,29 @@ out: kfree(in); return err; } + +int mlx5_cmd_uar_alloc(struct mlx5_core_dev *dev, u32 *uarn, u16 uid) +{ + u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {}; + u32 in[MLX5_ST_SZ_DW(alloc_uar_in)] = {}; + int err; + + MLX5_SET(alloc_uar_in, in, opcode, MLX5_CMD_OP_ALLOC_UAR); + MLX5_SET(alloc_uar_in, in, uid, uid); + err = mlx5_cmd_exec_inout(dev, alloc_uar, in, out); + if (err) + return err; + + *uarn = MLX5_GET(alloc_uar_out, out, uar); + return 0; +} + +int mlx5_cmd_uar_dealloc(struct mlx5_core_dev *dev, u32 uarn, u16 uid) +{ + u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)] = {}; + + MLX5_SET(dealloc_uar_in, in, opcode, MLX5_CMD_OP_DEALLOC_UAR); + MLX5_SET(dealloc_uar_in, in, uar, uarn); + MLX5_SET(dealloc_uar_in, in, uid, uid); + return mlx5_cmd_exec_in(dev, dealloc_uar, in); +} diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index 66c96292ed43..ee46638db5de 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -57,4 +57,6 @@ int mlx5_cmd_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn, u16 uid); int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid); int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, u16 opmod, u8 port); +int mlx5_cmd_uar_alloc(struct mlx5_core_dev *dev, u32 *uarn, u16 uid); +int mlx5_cmd_uar_dealloc(struct mlx5_core_dev *dev, u32 uarn, u16 uid); #endif /* MLX5_IB_CMD_H */ diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 8664bcf6d3f5..5ec8bd2f0b2f 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1643,7 +1643,8 @@ static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *conte bfregi = &context->bfregi; for (i = 0; i < bfregi->num_static_sys_pages; i++) { - err = mlx5_cmd_alloc_uar(dev->mdev, &bfregi->sys_pages[i]); + err = mlx5_cmd_uar_alloc(dev->mdev, &bfregi->sys_pages[i], + context->devx_uid); if (err) goto error; @@ -1657,7 +1658,8 @@ static int allocate_uars(struct mlx5_ib_dev *dev, struct mlx5_ib_ucontext *conte error: for (--i; i >= 0; i--) - if (mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i])) + if (mlx5_cmd_uar_dealloc(dev->mdev, bfregi->sys_pages[i], + context->devx_uid)) mlx5_ib_warn(dev, "failed to free uar %d\n", i); return err; @@ -1673,7 +1675,8 @@ static void deallocate_uars(struct mlx5_ib_dev *dev, for (i = 0; i < bfregi->num_sys_pages; i++) if (i < bfregi->num_static_sys_pages || bfregi->sys_pages[i] != MLX5_IB_INVALID_UAR_INDEX) - mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]); + mlx5_cmd_uar_dealloc(dev->mdev, bfregi->sys_pages[i], + context->devx_uid); } int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp) @@ -1891,6 +1894,13 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx, if (req.num_low_latency_bfregs > req.total_num_bfregs - 1) return -EINVAL; + if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) { + err = mlx5_ib_devx_create(dev, true); + if (err < 0) + goto out_ctx; + context->devx_uid = err; + } + lib_uar_4k = req.lib_caps & MLX5_LIB_CAP_4K_UAR; lib_uar_dyn = req.lib_caps & MLX5_LIB_CAP_DYN_UAR; bfregi = &context->bfregi; @@ -1903,7 +1913,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx, /* updates req->total_num_bfregs */ err = calc_total_bfregs(dev, lib_uar_4k, &req, bfregi); if (err) - goto out_ctx; + goto out_devx; mutex_init(&bfregi->lock); bfregi->lib_uar_4k = lib_uar_4k; @@ -1911,7 +1921,7 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx, GFP_KERNEL); if (!bfregi->count) { err = -ENOMEM; - goto out_ctx; + goto out_devx; } bfregi->sys_pages = kcalloc(bfregi->num_sys_pages, @@ -1927,17 +1937,10 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx, goto out_sys_pages; uar_done: - if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) { - err = mlx5_ib_devx_create(dev, true); - if (err < 0) - goto out_uars; - context->devx_uid = err; - } - err = mlx5_ib_alloc_transport_domain(dev, &context->tdn, context->devx_uid); if (err) - goto out_devx; + goto out_uars; INIT_LIST_HEAD(&context->db_page_list); mutex_init(&context->db_page_mutex); @@ -1972,9 +1975,6 @@ uar_done: out_mdev: mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid); -out_devx: - if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) - mlx5_ib_devx_destroy(dev, context->devx_uid); out_uars: deallocate_uars(dev, context); @@ -1985,6 +1985,10 @@ out_sys_pages: out_count: kfree(bfregi->count); +out_devx: + if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) + mlx5_ib_devx_destroy(dev, context->devx_uid); + out_ctx: return err; } @@ -2021,12 +2025,12 @@ static void mlx5_ib_dealloc_ucontext(struct ib_ucontext *ibcontext) bfregi = &context->bfregi; mlx5_ib_dealloc_transport_domain(dev, context->tdn, context->devx_uid); - if (context->devx_uid) - mlx5_ib_devx_destroy(dev, context->devx_uid); - deallocate_uars(dev, context); kfree(bfregi->sys_pages); kfree(bfregi->count); + + if (context->devx_uid) + mlx5_ib_devx_destroy(dev, context->devx_uid); } static phys_addr_t uar_index2pfn(struct mlx5_ib_dev *dev, @@ -2119,6 +2123,7 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry) struct mlx5_user_mmap_entry *mentry = to_mmmap(entry); struct mlx5_ib_dev *dev = to_mdev(entry->ucontext->device); struct mlx5_var_table *var_table = &dev->var_table; + struct mlx5_ib_ucontext *context = to_mucontext(entry->ucontext); switch (mentry->mmap_flag) { case MLX5_IB_MMAP_TYPE_MEMIC: @@ -2133,7 +2138,8 @@ static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry) break; case MLX5_IB_MMAP_TYPE_UAR_WC: case MLX5_IB_MMAP_TYPE_UAR_NC: - mlx5_cmd_free_uar(dev->mdev, mentry->page_idx); + mlx5_cmd_uar_dealloc(dev->mdev, mentry->page_idx, + context->devx_uid); kfree(mentry); break; default: @@ -2211,7 +2217,8 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd, bfregi->count[bfreg_dyn_idx]++; mutex_unlock(&bfregi->lock); - err = mlx5_cmd_alloc_uar(dev->mdev, &uar_index); + err = mlx5_cmd_uar_alloc(dev->mdev, &uar_index, + context->devx_uid); if (err) { mlx5_ib_warn(dev, "UAR alloc failed\n"); goto free_bfreg; @@ -2240,7 +2247,7 @@ err: if (!dyn_uar) return err; - mlx5_cmd_free_uar(dev->mdev, idx); + mlx5_cmd_uar_dealloc(dev->mdev, idx, context->devx_uid); free_bfreg: mlx5_ib_free_bfreg(dev, bfregi, bfreg_dyn_idx); @@ -3489,7 +3496,7 @@ alloc_uar_entry(struct mlx5_ib_ucontext *c, return ERR_PTR(-ENOMEM); dev = to_mdev(c->ibucontext.device); - err = mlx5_cmd_alloc_uar(dev->mdev, &uar_index); + err = mlx5_cmd_uar_alloc(dev->mdev, &uar_index, c->devx_uid); if (err) goto end; @@ -3507,7 +3514,7 @@ alloc_uar_entry(struct mlx5_ib_ucontext *c, return entry; err_insert: - mlx5_cmd_free_uar(dev->mdev, uar_index); + mlx5_cmd_uar_dealloc(dev->mdev, uar_index, c->devx_uid); end: kfree(entry); return ERR_PTR(err); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c index da481a7c12f4..01e9c412977c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c @@ -36,7 +36,7 @@ #include #include "mlx5_core.h" -int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn) +static int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn) { u32 out[MLX5_ST_SZ_DW(alloc_uar_out)] = {}; u32 in[MLX5_ST_SZ_DW(alloc_uar_in)] = {}; @@ -44,13 +44,14 @@ int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn) MLX5_SET(alloc_uar_in, in, opcode, MLX5_CMD_OP_ALLOC_UAR); err = mlx5_cmd_exec_inout(dev, alloc_uar, in, out); - if (!err) - *uarn = MLX5_GET(alloc_uar_out, out, uar); - return err; + if (err) + return err; + + *uarn = MLX5_GET(alloc_uar_out, out, uar); + return 0; } -EXPORT_SYMBOL(mlx5_cmd_alloc_uar); -int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn) +static int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn) { u32 in[MLX5_ST_SZ_DW(dealloc_uar_in)] = {}; @@ -58,7 +59,6 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn) MLX5_SET(dealloc_uar_in, in, uar, uarn); return mlx5_cmd_exec_in(dev, dealloc_uar, in); } -EXPORT_SYMBOL(mlx5_cmd_free_uar); static int uars_per_sys_page(struct mlx5_core_dev *mdev) { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e23417424373..1b8bae246b28 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1005,8 +1005,6 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); -int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); -int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_flush(struct mlx5_core_dev *dev); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From af9d82626c8f8547910e3e22c76ced3f5d5f5286 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Tue, 24 Aug 2021 14:20:51 +0200 Subject: PCI/ACPI: Remove OSC_PCI_SUPPORT_MASKS and OSC_PCI_CONTROL_MASKS These masks are only used internally in the PCI Host Bridge _OSC negotiation code, which already makes sure nothing outside of these masks is set. Remove the masks and simplify the code. Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20210824122054.29481-2-joro@8bytes.org Signed-off-by: Joerg Roedel Signed-off-by: Bjorn Helgaas Reviewed-by: Rafael J. Wysocki --- drivers/acpi/pci_root.c | 9 +++------ include/linux/acpi.h | 2 -- 2 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c index d7deedf3548e..0c3030a58219 100644 --- a/drivers/acpi/pci_root.c +++ b/drivers/acpi/pci_root.c @@ -199,18 +199,15 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, acpi_status status; u32 result, capbuf[3]; - support &= OSC_PCI_SUPPORT_MASKS; support |= root->osc_support_set; capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE; capbuf[OSC_SUPPORT_DWORD] = support; - if (control) { - *control &= OSC_PCI_CONTROL_MASKS; + if (control) capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set; - } else { + else /* Run _OSC query only with existing controls. */ capbuf[OSC_CONTROL_DWORD] = root->osc_control_set; - } status = acpi_pci_run_osc(root->device->handle, capbuf, &result); if (ACPI_SUCCESS(status)) { @@ -357,7 +354,7 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 r if (!mask) return AE_BAD_PARAMETER; - ctrl = *mask & OSC_PCI_CONTROL_MASKS; + ctrl = *mask; if ((ctrl & req) != req) return AE_TYPE; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 974d497a897d..eb59fd3052c0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -577,7 +577,6 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 -#define OSC_PCI_SUPPORT_MASKS 0x0000019f /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 @@ -587,7 +586,6 @@ extern u32 osc_sb_native_usb4_control; #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 -#define OSC_PCI_CONTROL_MASKS 0x000000bf #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 -- cgit v1.2.3 From fec2432c9a7370788faab416b38589ac9f4350e5 Mon Sep 17 00:00:00 2001 From: Diana Craciun Date: Wed, 22 Sep 2021 14:05:29 +0300 Subject: bus/fsl-mc: Add generic implementation for open/reset/close commands The open/reset/close commands format is similar for all objects. Currently there are multiple implementations for these commands scattered through various drivers. The code is cavsi-identical. Create a generic implementation for the open/reset/close commands. One of the consumer will be the VFIO driver which needs to be able to reset a device. Signed-off-by: Diana Craciun Reviewed-by: Laurentiu Tudor Link: https://lore.kernel.org/r/20210922110530.24736-1-diana.craciun@oss.nxp.com Signed-off-by: Alex Williamson --- drivers/bus/fsl-mc/Makefile | 3 +- drivers/bus/fsl-mc/fsl-mc-private.h | 39 ++++++++++++-- drivers/bus/fsl-mc/obj-api.c | 103 ++++++++++++++++++++++++++++++++++++ include/linux/fsl/mc.h | 14 +++++ 4 files changed, 154 insertions(+), 5 deletions(-) create mode 100644 drivers/bus/fsl-mc/obj-api.c (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/Makefile b/drivers/bus/fsl-mc/Makefile index 4ae292a30e53..892946245527 100644 --- a/drivers/bus/fsl-mc/Makefile +++ b/drivers/bus/fsl-mc/Makefile @@ -15,7 +15,8 @@ mc-bus-driver-objs := fsl-mc-bus.o \ dprc-driver.o \ fsl-mc-allocator.o \ fsl-mc-msi.o \ - dpmcp.o + dpmcp.o \ + obj-api.o # MC userspace support obj-$(CONFIG_FSL_MC_UAPI_SUPPORT) += fsl-mc-uapi.o diff --git a/drivers/bus/fsl-mc/fsl-mc-private.h b/drivers/bus/fsl-mc/fsl-mc-private.h index 1958fa065360..b3520ea1b9f4 100644 --- a/drivers/bus/fsl-mc/fsl-mc-private.h +++ b/drivers/bus/fsl-mc/fsl-mc-private.h @@ -48,7 +48,6 @@ struct dpmng_rsp_get_version { /* DPMCP command IDs */ #define DPMCP_CMDID_CLOSE DPMCP_CMD(0x800) -#define DPMCP_CMDID_OPEN DPMCP_CMD(0x80b) #define DPMCP_CMDID_RESET DPMCP_CMD(0x005) struct dpmcp_cmd_open { @@ -91,7 +90,6 @@ int dpmcp_reset(struct fsl_mc_io *mc_io, /* DPRC command IDs */ #define DPRC_CMDID_CLOSE DPRC_CMD(0x800) -#define DPRC_CMDID_OPEN DPRC_CMD(0x805) #define DPRC_CMDID_GET_API_VERSION DPRC_CMD(0xa05) #define DPRC_CMDID_GET_ATTR DPRC_CMD(0x004) @@ -453,7 +451,6 @@ int dprc_get_connection(struct fsl_mc_io *mc_io, /* Command IDs */ #define DPBP_CMDID_CLOSE DPBP_CMD(0x800) -#define DPBP_CMDID_OPEN DPBP_CMD(0x804) #define DPBP_CMDID_ENABLE DPBP_CMD(0x002) #define DPBP_CMDID_DISABLE DPBP_CMD(0x003) @@ -492,7 +489,6 @@ struct dpbp_rsp_get_attributes { /* Command IDs */ #define DPCON_CMDID_CLOSE DPCON_CMD(0x800) -#define DPCON_CMDID_OPEN DPCON_CMD(0x808) #define DPCON_CMDID_ENABLE DPCON_CMD(0x002) #define DPCON_CMDID_DISABLE DPCON_CMD(0x003) @@ -524,6 +520,41 @@ struct dpcon_cmd_set_notification { __le64 user_ctx; }; +/* + * Generic FSL MC API + */ + +/* generic command versioning */ +#define OBJ_CMD_BASE_VERSION 1 +#define OBJ_CMD_ID_OFFSET 4 + +#define OBJ_CMD(id) (((id) << OBJ_CMD_ID_OFFSET) | OBJ_CMD_BASE_VERSION) + +/* open command codes */ +#define DPRTC_CMDID_OPEN OBJ_CMD(0x810) +#define DPNI_CMDID_OPEN OBJ_CMD(0x801) +#define DPSW_CMDID_OPEN OBJ_CMD(0x802) +#define DPIO_CMDID_OPEN OBJ_CMD(0x803) +#define DPBP_CMDID_OPEN OBJ_CMD(0x804) +#define DPRC_CMDID_OPEN OBJ_CMD(0x805) +#define DPDMUX_CMDID_OPEN OBJ_CMD(0x806) +#define DPCI_CMDID_OPEN OBJ_CMD(0x807) +#define DPCON_CMDID_OPEN OBJ_CMD(0x808) +#define DPSECI_CMDID_OPEN OBJ_CMD(0x809) +#define DPAIOP_CMDID_OPEN OBJ_CMD(0x80a) +#define DPMCP_CMDID_OPEN OBJ_CMD(0x80b) +#define DPMAC_CMDID_OPEN OBJ_CMD(0x80c) +#define DPDCEI_CMDID_OPEN OBJ_CMD(0x80d) +#define DPDMAI_CMDID_OPEN OBJ_CMD(0x80e) +#define DPDBG_CMDID_OPEN OBJ_CMD(0x80f) + +/* Generic object command IDs */ +#define OBJ_CMDID_CLOSE OBJ_CMD(0x800) +#define OBJ_CMDID_RESET OBJ_CMD(0x005) + +struct fsl_mc_obj_cmd_open { + __le32 obj_id; +}; /** * struct fsl_mc_resource_pool - Pool of MC resources of a given diff --git a/drivers/bus/fsl-mc/obj-api.c b/drivers/bus/fsl-mc/obj-api.c new file mode 100644 index 000000000000..06c1dd84e38d --- /dev/null +++ b/drivers/bus/fsl-mc/obj-api.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* + * Copyright 2021 NXP + * + */ +#include +#include + +#include "fsl-mc-private.h" + +static int fsl_mc_get_open_cmd_id(const char *type) +{ + static const struct { + int cmd_id; + const char *type; + } dev_ids[] = { + { DPRTC_CMDID_OPEN, "dprtc" }, + { DPRC_CMDID_OPEN, "dprc" }, + { DPNI_CMDID_OPEN, "dpni" }, + { DPIO_CMDID_OPEN, "dpio" }, + { DPSW_CMDID_OPEN, "dpsw" }, + { DPBP_CMDID_OPEN, "dpbp" }, + { DPCON_CMDID_OPEN, "dpcon" }, + { DPMCP_CMDID_OPEN, "dpmcp" }, + { DPMAC_CMDID_OPEN, "dpmac" }, + { DPSECI_CMDID_OPEN, "dpseci" }, + { DPDMUX_CMDID_OPEN, "dpdmux" }, + { DPDCEI_CMDID_OPEN, "dpdcei" }, + { DPAIOP_CMDID_OPEN, "dpaiop" }, + { DPCI_CMDID_OPEN, "dpci" }, + { DPDMAI_CMDID_OPEN, "dpdmai" }, + { DPDBG_CMDID_OPEN, "dpdbg" }, + { 0, NULL } + }; + int i; + + for (i = 0; dev_ids[i].type; i++) + if (!strcmp(dev_ids[i].type, type)) + return dev_ids[i].cmd_id; + + return -1; +} + +int fsl_mc_obj_open(struct fsl_mc_io *mc_io, + u32 cmd_flags, + int obj_id, + char *obj_type, + u16 *token) +{ + struct fsl_mc_command cmd = { 0 }; + struct fsl_mc_obj_cmd_open *cmd_params; + int err = 0; + int cmd_id = fsl_mc_get_open_cmd_id(obj_type); + + if (cmd_id == -1) + return -ENODEV; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(cmd_id, cmd_flags, 0); + cmd_params = (struct fsl_mc_obj_cmd_open *)cmd.params; + cmd_params->obj_id = cpu_to_le32(obj_id); + + /* send command to mc*/ + err = mc_send_command(mc_io, &cmd); + if (err) + return err; + + /* retrieve response parameters */ + *token = mc_cmd_hdr_read_token(&cmd); + + return err; +} +EXPORT_SYMBOL_GPL(fsl_mc_obj_open); + +int fsl_mc_obj_close(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token) +{ + struct fsl_mc_command cmd = { 0 }; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(OBJ_CMDID_CLOSE, cmd_flags, + token); + + /* send command to mc*/ + return mc_send_command(mc_io, &cmd); +} +EXPORT_SYMBOL_GPL(fsl_mc_obj_close); + +int fsl_mc_obj_reset(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token) +{ + struct fsl_mc_command cmd = { 0 }; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(OBJ_CMDID_RESET, cmd_flags, + token); + + /* send command to mc*/ + return mc_send_command(mc_io, &cmd); +} +EXPORT_SYMBOL_GPL(fsl_mc_obj_reset); diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index 30ece3ae6df7..e026f6c48b49 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -620,6 +620,20 @@ int dpcon_reset(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token); +int fsl_mc_obj_open(struct fsl_mc_io *mc_io, + u32 cmd_flags, + int obj_id, + char *obj_type, + u16 *token); + +int fsl_mc_obj_close(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token); + +int fsl_mc_obj_reset(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token); + /** * struct dpcon_attr - Structure representing DPCON attributes * @id: DPCON object ID -- cgit v1.2.3 From 3d717fad5081b8e3bda76d86907fad95398cbde8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 28 Sep 2021 16:09:45 -0700 Subject: bpf: Replace "want address" users of BPF_CAST_CALL with BPF_CALL_IMM In order to keep ahead of cases in the kernel where Control Flow Integrity (CFI) may trip over function call casts, enabling -Wcast-function-type is helpful. To that end, BPF_CAST_CALL causes various warnings and is one of the last places in the kernel triggering this warning. Most places using BPF_CAST_CALL actually just want a void * to perform math on. It's not actually performing a call, so just use a different helper to get the void *, by way of the new BPF_CALL_IMM() helper, which can clean up a common copy/paste idiom as well. This change results in no object code difference. Signed-off-by: Kees Cook Signed-off-by: Alexei Starovoitov Reviewed-by: Gustavo A. R. Silva Acked-by: Andrii Nakryiko Link: https://github.com/KSPP/linux/issues/20 Link: https://lore.kernel.org/lkml/CAEf4Bzb46=-J5Fxc3mMZ8JQPtK1uoE0q6+g6WPz53Cvx=CBEhw@mail.gmail.com Link: https://lore.kernel.org/bpf/20210928230946.4062144-2-keescook@chromium.org --- include/linux/filter.h | 6 +++++- kernel/bpf/hashtab.c | 6 +++--- kernel/bpf/verifier.c | 26 +++++++++----------------- lib/test_bpf.c | 2 +- 4 files changed, 18 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 4a93c12543ee..6c247663d4ce 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -365,13 +365,17 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) #define BPF_CAST_CALL(x) \ ((u64 (*)(u64, u64, u64, u64, u64))(x)) +/* Convert function address to BPF immediate */ + +#define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) + #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ - .imm = ((FUNC) - __bpf_call_base) }) + .imm = BPF_CALL_IMM(FUNC) }) /* Raw code statement block */ diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 32471ba02708..3d8f9d6997d5 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -668,7 +668,7 @@ static int htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + @@ -709,7 +709,7 @@ static int htab_lru_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + @@ -2397,7 +2397,7 @@ static int htab_of_map_gen_lookup(struct bpf_map *map, BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); - *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); + *insn++ = BPF_EMIT_CALL(__htab_map_lookup_elem); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 7a8351604f67..1433752db740 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1744,7 +1744,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; - desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base; + desc->imm = BPF_CALL_IMM(addr); err = btf_distill_func_proto(&env->log, btf_vmlinux, func_proto, func_name, &desc->func_model); @@ -12514,8 +12514,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) if (!bpf_pseudo_call(insn)) continue; subprog = insn->off; - insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func); } /* we use the aux data to keep a list of the start addresses @@ -12995,32 +12994,25 @@ static int do_misc_fixups(struct bpf_verifier_env *env) patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: - insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); continue; case BPF_FUNC_map_update_elem: - insn->imm = BPF_CAST_CALL(ops->map_update_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_update_elem); continue; case BPF_FUNC_map_delete_elem: - insn->imm = BPF_CAST_CALL(ops->map_delete_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_delete_elem); continue; case BPF_FUNC_map_push_elem: - insn->imm = BPF_CAST_CALL(ops->map_push_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_push_elem); continue; case BPF_FUNC_map_pop_elem: - insn->imm = BPF_CAST_CALL(ops->map_pop_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_pop_elem); continue; case BPF_FUNC_map_peek_elem: - insn->imm = BPF_CAST_CALL(ops->map_peek_elem) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_peek_elem); continue; case BPF_FUNC_redirect_map: - insn->imm = BPF_CAST_CALL(ops->map_redirect) - - __bpf_call_base; + insn->imm = BPF_CALL_IMM(ops->map_redirect); continue; } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 08f438e6fe9e..21ea1ab253a1 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -12439,7 +12439,7 @@ static __init int prepare_tail_call_tests(struct bpf_array **pprogs) err = -EFAULT; goto out_err; } - *insn = BPF_EMIT_CALL(BPF_CAST_CALL(addr)); + *insn = BPF_EMIT_CALL(addr); if ((long)__bpf_call_base + insn->imm != addr) *insn = BPF_JMP_A(0); /* Skip: NOP */ break; -- cgit v1.2.3 From 102acbacfd9a96d101abd96d1a7a5bf92b7c3e8e Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 28 Sep 2021 16:09:46 -0700 Subject: bpf: Replace callers of BPF_CAST_CALL with proper function typedef In order to keep ahead of cases in the kernel where Control Flow Integrity (CFI) may trip over function call casts, enabling -Wcast-function-type is helpful. To that end, BPF_CAST_CALL causes various warnings and is one of the last places in the kernel triggering this warning. For actual function calls, replace BPF_CAST_CALL() with a typedef, which captures the same details about the given function pointers. This change results in no object code difference. Signed-off-by: Kees Cook Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Gustavo A. R. Silva Link: https://github.com/KSPP/linux/issues/20 Link: https://lore.kernel.org/lkml/CAEf4Bzb46=-J5Fxc3mMZ8JQPtK1uoE0q6+g6WPz53Cvx=CBEhw@mail.gmail.com Link: https://lore.kernel.org/bpf/20210928230946.4062144-3-keescook@chromium.org --- include/linux/bpf.h | 4 +++- include/linux/filter.h | 5 ----- kernel/bpf/arraymap.c | 7 +++---- kernel/bpf/hashtab.c | 7 +++---- kernel/bpf/helpers.c | 5 ++--- 5 files changed, 11 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b6c45a6cbbba..19735d59230a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -48,6 +48,7 @@ extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; +typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); @@ -142,7 +143,8 @@ struct bpf_map_ops { int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); - int (*map_for_each_callback)(struct bpf_map *map, void *callback_fn, + int (*map_for_each_callback)(struct bpf_map *map, + bpf_callback_t callback_fn, void *callback_ctx, u64 flags); /* BTF name and id of struct allocated by map_alloc */ diff --git a/include/linux/filter.h b/include/linux/filter.h index 6c247663d4ce..47f80adbe744 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -360,11 +360,6 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = 0, \ .imm = TGT }) -/* Function call */ - -#define BPF_CAST_CALL(x) \ - ((u64 (*)(u64, u64, u64, u64, u64))(x)) - /* Convert function address to BPF immediate */ #define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index cebd4fb06d19..5e1ccfae916b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -645,7 +645,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_array_map_info), }; -static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn, +static int bpf_for_each_array_elem(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags) { u32 i, key, num_elems = 0; @@ -668,9 +668,8 @@ static int bpf_for_each_array_elem(struct bpf_map *map, void *callback_fn, val = array->value + array->elem_size * i; num_elems++; key = i; - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)&key, (u64)(long)val, - (u64)(long)callback_ctx, 0); + ret = callback_fn((u64)(long)map, (u64)(long)&key, + (u64)(long)val, (u64)(long)callback_ctx, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) break; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3d8f9d6997d5..d29af9988f37 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -2049,7 +2049,7 @@ static const struct bpf_iter_seq_info iter_seq_info = { .seq_priv_size = sizeof(struct bpf_iter_seq_hash_map_info), }; -static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn, +static int bpf_for_each_hash_elem(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); @@ -2089,9 +2089,8 @@ static int bpf_for_each_hash_elem(struct bpf_map *map, void *callback_fn, val = elem->key + roundup_key_size; } num_elems++; - ret = BPF_CAST_CALL(callback_fn)((u64)(long)map, - (u64)(long)key, (u64)(long)val, - (u64)(long)callback_ctx, 0); + ret = callback_fn((u64)(long)map, (u64)(long)key, + (u64)(long)val, (u64)(long)callback_ctx, 0); /* return value: 0 - continue, 1 - stop and return */ if (ret) { rcu_read_unlock(); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 2c604ff8c7fb..1ffd469c217f 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1056,7 +1056,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) struct bpf_hrtimer *t = container_of(hrtimer, struct bpf_hrtimer, timer); struct bpf_map *map = t->map; void *value = t->value; - void *callback_fn; + bpf_callback_t callback_fn; void *key; u32 idx; @@ -1081,8 +1081,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) key = value - round_up(map->key_size, 8); } - BPF_CAST_CALL(callback_fn)((u64)(long)map, (u64)(long)key, - (u64)(long)value, 0, 0); + callback_fn((u64)(long)map, (u64)(long)key, (u64)(long)value, 0, 0); /* The verifier checked that return value is zero. */ this_cpu_write(hrtimer_running, NULL); -- cgit v1.2.3 From 7c2dcfa295b149a58010632c7eb7e73bd0626a7a Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Tue, 28 Sep 2021 20:45:19 +0200 Subject: net: phy: micrel: Add support for LAN8804 PHY The LAN8804 PHY has same features as that of LAN8814 PHY except that it doesn't support 1588, SyncE or Q-USGMII. This PHY is found inside the LAN966X switches. Reviewed-by: Andrew Lunn Signed-off-by: Horatiu Vultur Signed-off-by: David S. Miller --- drivers/net/phy/micrel.c | 74 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/micrel_phy.h | 1 + 2 files changed, 75 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 5c928f827173..c330a5a9f665 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1537,6 +1537,65 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, return ret; } +#define LAN_EXT_PAGE_ACCESS_CONTROL 0x16 +#define LAN_EXT_PAGE_ACCESS_ADDRESS_DATA 0x17 +#define LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC 0x4000 + +#define LAN8804_ALIGN_SWAP 0x4a +#define LAN8804_ALIGN_TX_A_B_SWAP 0x1 +#define LAN8804_ALIGN_TX_A_B_SWAP_MASK GENMASK(2, 0) +#define LAN8814_CLOCK_MANAGEMENT 0xd +#define LAN8814_LINK_QUALITY 0x8e + +static int lanphy_read_page_reg(struct phy_device *phydev, int page, u32 addr) +{ + u32 data; + + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, page); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA, addr); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, + (page | LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC)); + data = phy_read(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA); + + return data; +} + +static int lanphy_write_page_reg(struct phy_device *phydev, int page, u16 addr, + u16 val) +{ + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, page); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA, addr); + phy_write(phydev, LAN_EXT_PAGE_ACCESS_CONTROL, + (page | LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC)); + + val = phy_write(phydev, LAN_EXT_PAGE_ACCESS_ADDRESS_DATA, val); + if (val) { + phydev_err(phydev, "Error: phy_write has returned error %d\n", + val); + return val; + } + return 0; +} + +static int lan8804_config_init(struct phy_device *phydev) +{ + int val; + + /* MDI-X setting for swap A,B transmit */ + val = lanphy_read_page_reg(phydev, 2, LAN8804_ALIGN_SWAP); + val &= ~LAN8804_ALIGN_TX_A_B_SWAP_MASK; + val |= LAN8804_ALIGN_TX_A_B_SWAP; + lanphy_write_page_reg(phydev, 2, LAN8804_ALIGN_SWAP, val); + + /* Make sure that the PHY will not stop generating the clock when the + * link partner goes down + */ + lanphy_write_page_reg(phydev, 31, LAN8814_CLOCK_MANAGEMENT, 0x27e); + lanphy_read_page_reg(phydev, 1, LAN8814_LINK_QUALITY); + + return 0; +} + static struct phy_driver ksphy_driver[] = { { .phy_id = PHY_ID_KS8737, @@ -1718,6 +1777,20 @@ static struct phy_driver ksphy_driver[] = { .get_stats = kszphy_get_stats, .suspend = genphy_suspend, .resume = kszphy_resume, +}, { + .phy_id = PHY_ID_LAN8804, + .phy_id_mask = MICREL_PHY_ID_MASK, + .name = "Microchip LAN966X Gigabit PHY", + .config_init = lan8804_config_init, + .driver_data = &ksz9021_type, + .probe = kszphy_probe, + .soft_reset = genphy_soft_reset, + .read_status = ksz9031_read_status, + .get_sset_count = kszphy_get_sset_count, + .get_strings = kszphy_get_strings, + .get_stats = kszphy_get_stats, + .suspend = genphy_suspend, + .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ9131, .phy_id_mask = MICREL_PHY_ID_MASK, @@ -1794,6 +1867,7 @@ static struct mdio_device_id __maybe_unused micrel_tbl[] = { { PHY_ID_KSZ8873MLL, MICREL_PHY_ID_MASK }, { PHY_ID_KSZ886X, MICREL_PHY_ID_MASK }, { PHY_ID_LAN8814, MICREL_PHY_ID_MASK }, + { PHY_ID_LAN8804, MICREL_PHY_ID_MASK }, { } }; diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 3d43c60b49fa..1f7c33b2f5a3 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -28,6 +28,7 @@ #define PHY_ID_KSZ9031 0x00221620 #define PHY_ID_KSZ9131 0x00221640 #define PHY_ID_LAN8814 0x00221660 +#define PHY_ID_LAN8804 0x00221670 #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -- cgit v1.2.3 From e81e99bacc9f9347bda7808a949c1ce9fcc2bbf4 Mon Sep 17 00:00:00 2001 From: David Stevens Date: Wed, 29 Sep 2021 11:32:59 +0900 Subject: swiotlb: Support aligned swiotlb buffers Add an argument to swiotlb_tbl_map_single that specifies the desired alignment of the allocated buffer. This is used by dma-iommu to ensure the buffer is aligned to the iova granule size when using swiotlb with untrusted sub-granule mappings. This addresses an issue where adjacent slots could be exposed to the untrusted device if IO_TLB_SIZE < iova granule < PAGE_SIZE. Signed-off-by: David Stevens Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210929023300.335969-7-stevensd@google.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 4 ++-- drivers/xen/swiotlb-xen.c | 2 +- include/linux/swiotlb.h | 3 ++- kernel/dma/swiotlb.c | 13 ++++++++----- 4 files changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 85a005b268f6..289c49ead01a 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -818,8 +818,8 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, size_t padding_size; aligned_size = iova_align(iovad, size); - phys = swiotlb_tbl_map_single(dev, phys, size, - aligned_size, dir, attrs); + phys = swiotlb_tbl_map_single(dev, phys, size, aligned_size, + iova_mask(iovad), dir, attrs); if (phys == DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index e56a5faac395..cbdff8979980 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -380,7 +380,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, */ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force); - map = swiotlb_tbl_map_single(dev, phys, size, size, dir, attrs); + map = swiotlb_tbl_map_single(dev, phys, size, size, 0, dir, attrs); if (map == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index b0cb2a9973f4..569272871375 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -45,7 +45,8 @@ extern void __init swiotlb_update_mem_attributes(void); phys_addr_t swiotlb_tbl_map_single(struct device *hwdev, phys_addr_t phys, size_t mapping_size, size_t alloc_size, - enum dma_data_direction dir, unsigned long attrs); + unsigned int alloc_aligned_mask, enum dma_data_direction dir, + unsigned long attrs); extern void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 87c40517e822..019672b3da1d 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -459,7 +459,7 @@ static unsigned int wrap_index(struct io_tlb_mem *mem, unsigned int index) * allocate a buffer from that IO TLB pool. */ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, - size_t alloc_size) + size_t alloc_size, unsigned int alloc_align_mask) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned long boundary_mask = dma_get_seg_boundary(dev); @@ -483,6 +483,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, stride = (iotlb_align_mask >> IO_TLB_SHIFT) + 1; if (alloc_size >= PAGE_SIZE) stride = max(stride, stride << (PAGE_SHIFT - IO_TLB_SHIFT)); + stride = max(stride, (alloc_align_mask >> IO_TLB_SHIFT) + 1); spin_lock_irqsave(&mem->lock, flags); if (unlikely(nslots > mem->nslabs - mem->used)) @@ -541,7 +542,8 @@ found: phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, size_t alloc_size, - enum dma_data_direction dir, unsigned long attrs) + unsigned int alloc_align_mask, enum dma_data_direction dir, + unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset = swiotlb_align_offset(dev, orig_addr); @@ -561,7 +563,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, return (phys_addr_t)DMA_MAPPING_ERROR; } - index = swiotlb_find_slots(dev, orig_addr, alloc_size + offset); + index = swiotlb_find_slots(dev, orig_addr, + alloc_size + offset, alloc_align_mask); if (index == -1) { if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, @@ -675,7 +678,7 @@ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size, swiotlb_force); - swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, dir, + swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, size, 0, dir, attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; @@ -759,7 +762,7 @@ struct page *swiotlb_alloc(struct device *dev, size_t size) if (!mem) return NULL; - index = swiotlb_find_slots(dev, 0, size); + index = swiotlb_find_slots(dev, 0, size, 0); if (index == -1) return NULL; -- cgit v1.2.3 From e5af50a5df571c1d0268b02f924de49b742c990f Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Thu, 23 Sep 2021 18:06:55 -0700 Subject: arm64: kasan: mte: move GCR_EL1 switch to task switch when KASAN disabled It is not necessary to write to GCR_EL1 on every kernel entry and exit when HW tag-based KASAN is disabled because the kernel will not execute any IRG instructions in that mode. Since accessing GCR_EL1 can be expensive on some microarchitectures, avoid doing so by moving the access to task switch when HW tag-based KASAN is disabled. Signed-off-by: Peter Collingbourne Acked-by: Andrey Konovalov Link: https://linux-review.googlesource.com/id/I78e90d60612a94c24344526f476ac4ff216e10d2 Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20210924010655.2886918-1-pcc@google.com Signed-off-by: Will Deacon --- arch/arm64/kernel/entry.S | 10 +++++----- arch/arm64/kernel/mte.c | 26 ++++++++++++++++++++++++++ include/linux/kasan.h | 9 +++++++-- 3 files changed, 38 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index bc6d5a970a13..2f69ae43941d 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -168,9 +168,9 @@ alternative_else_nop_endif .macro mte_set_kernel_gcr, tmp, tmp2 #ifdef CONFIG_KASAN_HW_TAGS -alternative_if_not ARM64_MTE +alternative_cb kasan_hw_tags_enable b 1f -alternative_else_nop_endif +alternative_cb_end mov \tmp, KERNEL_GCR_EL1 msr_s SYS_GCR_EL1, \tmp 1: @@ -178,10 +178,10 @@ alternative_else_nop_endif .endm .macro mte_set_user_gcr, tsk, tmp, tmp2 -#ifdef CONFIG_ARM64_MTE -alternative_if_not ARM64_MTE +#ifdef CONFIG_KASAN_HW_TAGS +alternative_cb kasan_hw_tags_enable b 1f -alternative_else_nop_endif +alternative_cb_end ldr \tmp, [\tsk, #THREAD_MTE_CTRL] mte_set_gcr \tmp, \tmp2 diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index e5e801bc5312..0cdae086966e 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -179,6 +179,30 @@ static void mte_update_sctlr_user(struct task_struct *task) task->thread.sctlr_user = sctlr; } +static void mte_update_gcr_excl(struct task_struct *task) +{ + /* + * SYS_GCR_EL1 will be set to current->thread.mte_ctrl value by + * mte_set_user_gcr() in kernel_exit, but only if KASAN is enabled. + */ + if (kasan_hw_tags_enabled()) + return; + + write_sysreg_s( + ((task->thread.mte_ctrl >> MTE_CTRL_GCR_USER_EXCL_SHIFT) & + SYS_GCR_EL1_EXCL_MASK) | SYS_GCR_EL1_RRND, + SYS_GCR_EL1); +} + +void __init kasan_hw_tags_enable(struct alt_instr *alt, __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); /* Branch -> NOP */ + + if (kasan_hw_tags_enabled()) + *updptr = cpu_to_le32(aarch64_insn_gen_nop()); +} + void mte_thread_init_user(void) { if (!system_supports_mte()) @@ -198,6 +222,7 @@ void mte_thread_switch(struct task_struct *next) return; mte_update_sctlr_user(next); + mte_update_gcr_excl(next); /* * Check if an async tag exception occurred at EL1. @@ -243,6 +268,7 @@ long set_mte_ctrl(struct task_struct *task, unsigned long arg) if (task == current) { preempt_disable(); mte_update_sctlr_user(task); + mte_update_gcr_excl(task); update_sctlr_el1(task->thread.sctlr_user); preempt_enable(); } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index dd874a1ee862..de5f5913374d 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -89,7 +89,7 @@ static __always_inline bool kasan_enabled(void) return static_branch_likely(&kasan_flag_enabled); } -static inline bool kasan_has_integrated_init(void) +static inline bool kasan_hw_tags_enabled(void) { return kasan_enabled(); } @@ -104,7 +104,7 @@ static inline bool kasan_enabled(void) return IS_ENABLED(CONFIG_KASAN); } -static inline bool kasan_has_integrated_init(void) +static inline bool kasan_hw_tags_enabled(void) { return false; } @@ -125,6 +125,11 @@ static __always_inline void kasan_free_pages(struct page *page, #endif /* CONFIG_KASAN_HW_TAGS */ +static inline bool kasan_has_integrated_init(void) +{ + return kasan_hw_tags_enabled(); +} + #ifdef CONFIG_KASAN struct kasan_cache { -- cgit v1.2.3 From 7101c83950e629b83f9d827f288063e52074a6ea Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 29 Sep 2021 19:23:50 -0700 Subject: platform/chrome: cros_usbpd_notify: Move ec_command() cros_ec_command() can be used by other modules too. So, move it to a common location and export it. This patch does not introduce any functional changes. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210930022403.3358070-3-pmalani@chromium.org --- drivers/platform/chrome/cros_ec_proto.c | 45 +++++++++++++++++++++++++++++ drivers/platform/chrome/cros_usbpd_notify.c | 44 ---------------------------- include/linux/platform_data/cros_ec_proto.h | 3 ++ 3 files changed, 48 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index a34cf58c5ef7..67009b604630 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -910,3 +910,48 @@ int cros_ec_get_sensor_count(struct cros_ec_dev *ec) return sensor_count; } EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); + +/** + * cros_ec_command - Send a command to the EC. + * + * @ec_dev: EC device + * @command: EC command + * @outdata: EC command output data + * @outsize: Size of outdata + * @indata: EC command input data + * @insize: Size of indata + * + * Return: >= 0 on success, negative error number on failure. + */ +int cros_ec_command(struct cros_ec_device *ec_dev, + int command, + uint8_t *outdata, + int outsize, + uint8_t *indata, + int insize) +{ + struct cros_ec_command *msg; + int ret; + + msg = kzalloc(sizeof(*msg) + max(insize, outsize), GFP_KERNEL); + if (!msg) + return -ENOMEM; + + msg->command = command; + msg->outsize = outsize; + msg->insize = insize; + + if (outsize) + memcpy(msg->data, outdata, outsize); + + ret = cros_ec_cmd_xfer_status(ec_dev, msg); + if (ret < 0) + goto error; + + if (insize) + memcpy(indata, msg->data, insize); +error: + kfree(msg); + return ret; +} +EXPORT_SYMBOL_GPL(cros_ec_command); diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c index e718055f4313..39afdad897ce 100644 --- a/drivers/platform/chrome/cros_usbpd_notify.c +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -53,50 +53,6 @@ void cros_usbpd_unregister_notify(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(cros_usbpd_unregister_notify); -/** - * cros_ec_command - Send a command to the EC. - * - * @ec_dev: EC device - * @command: EC command - * @outdata: EC command output data - * @outsize: Size of outdata - * @indata: EC command input data - * @insize: Size of indata - * - * Return: >= 0 on success, negative error number on failure. - */ -static int cros_ec_command(struct cros_ec_device *ec_dev, - int command, - uint8_t *outdata, - int outsize, - uint8_t *indata, - int insize) -{ - struct cros_ec_command *msg; - int ret; - - msg = kzalloc(sizeof(*msg) + max(insize, outsize), GFP_KERNEL); - if (!msg) - return -ENOMEM; - - msg->command = command; - msg->outsize = outsize; - msg->insize = insize; - - if (outsize) - memcpy(msg->data, outdata, outsize); - - ret = cros_ec_cmd_xfer_status(ec_dev, msg); - if (ret < 0) - goto error; - - if (insize) - memcpy(indata, msg->data, insize); -error: - kfree(msg); - return ret; -} - static void cros_usbpd_get_event_and_notify(struct device *dev, struct cros_ec_device *ec_dev) { diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 55844ece0b32..20b17c43caeb 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -231,6 +231,9 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); +int cros_ec_command(struct cros_ec_device *ec_dev, int command, uint8_t *outdata, int outsize, + uint8_t *indata, int insize); + /** * cros_ec_get_time_ns() - Return time in ns. * -- cgit v1.2.3 From 5d122256f4e5900f7f8de5d8787af570314f6701 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 29 Sep 2021 19:23:52 -0700 Subject: platform/chrome: cros_ec_proto: Make data pointers void Convert the input and output data pointers for cros_ec_command() to void pointers so that the callers don't have to cast their custom structs to uint8_t *. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210930022403.3358070-4-pmalani@chromium.org --- drivers/platform/chrome/cros_ec_proto.c | 4 ++-- drivers/platform/chrome/cros_usbpd_notify.c | 2 +- include/linux/platform_data/cros_ec_proto.h | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index 67009b604630..fd114b57bca2 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -925,9 +925,9 @@ EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); */ int cros_ec_command(struct cros_ec_device *ec_dev, int command, - uint8_t *outdata, + void *outdata, int outsize, - uint8_t *indata, + void *indata, int insize) { struct cros_ec_command *msg; diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c index 39afdad897ce..860509474f05 100644 --- a/drivers/platform/chrome/cros_usbpd_notify.c +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -72,7 +72,7 @@ static void cros_usbpd_get_event_and_notify(struct device *dev, /* Check for PD host events on EC. */ ret = cros_ec_command(ec_dev, EC_CMD_PD_HOST_EVENT_STATUS, - NULL, 0, (uint8_t *)&host_event_status, sizeof(host_event_status)); + NULL, 0, &host_event_status, sizeof(host_event_status)); if (ret < 0) { dev_warn(dev, "Can't get host event status (err: %d)\n", ret); goto send_notify; diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 20b17c43caeb..f833473c5f44 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -231,8 +231,8 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -int cros_ec_command(struct cros_ec_device *ec_dev, int command, uint8_t *outdata, int outsize, - uint8_t *indata, int insize); +int cros_ec_command(struct cros_ec_device *ec_dev, int command, void *outdata, int outsize, + void *indata, int insize); /** * cros_ec_get_time_ns() - Return time in ns. -- cgit v1.2.3 From 4f1406396ed4d97518b8112327bdaf14fc9d4090 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Wed, 29 Sep 2021 19:23:54 -0700 Subject: platform/chrome: cros_ec_proto: Add version for ec_command Add a version parameter to cros_ec_command() for callers that may want to specify which version of the host command they would like to use. Signed-off-by: Prashant Malani Signed-off-by: Enric Balletbo i Serra Link: https://lore.kernel.org/r/20210930022403.3358070-5-pmalani@chromium.org --- drivers/platform/chrome/cros_ec_proto.c | 3 +++ drivers/platform/chrome/cros_usbpd_notify.c | 2 +- include/linux/platform_data/cros_ec_proto.h | 4 ++-- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index fd114b57bca2..a9f1867e5d8f 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -915,6 +915,7 @@ EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); * cros_ec_command - Send a command to the EC. * * @ec_dev: EC device + * @version: EC command version * @command: EC command * @outdata: EC command output data * @outsize: Size of outdata @@ -924,6 +925,7 @@ EXPORT_SYMBOL_GPL(cros_ec_get_sensor_count); * Return: >= 0 on success, negative error number on failure. */ int cros_ec_command(struct cros_ec_device *ec_dev, + unsigned int version, int command, void *outdata, int outsize, @@ -937,6 +939,7 @@ int cros_ec_command(struct cros_ec_device *ec_dev, if (!msg) return -ENOMEM; + msg->version = version; msg->command = command; msg->outsize = outsize; msg->insize = insize; diff --git a/drivers/platform/chrome/cros_usbpd_notify.c b/drivers/platform/chrome/cros_usbpd_notify.c index 860509474f05..91ce6be91aac 100644 --- a/drivers/platform/chrome/cros_usbpd_notify.c +++ b/drivers/platform/chrome/cros_usbpd_notify.c @@ -71,7 +71,7 @@ static void cros_usbpd_get_event_and_notify(struct device *dev, } /* Check for PD host events on EC. */ - ret = cros_ec_command(ec_dev, EC_CMD_PD_HOST_EVENT_STATUS, + ret = cros_ec_command(ec_dev, 0, EC_CMD_PD_HOST_EVENT_STATUS, NULL, 0, &host_event_status, sizeof(host_event_status)); if (ret < 0) { dev_warn(dev, "Can't get host event status (err: %d)\n", ret); diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index f833473c5f44..9d370816a419 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -231,8 +231,8 @@ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature); int cros_ec_get_sensor_count(struct cros_ec_dev *ec); -int cros_ec_command(struct cros_ec_device *ec_dev, int command, void *outdata, int outsize, - void *indata, int insize); +int cros_ec_command(struct cros_ec_device *ec_dev, unsigned int version, int command, void *outdata, + int outsize, void *indata, int insize); /** * cros_ec_get_time_ns() - Return time in ns. -- cgit v1.2.3 From 381cecc5d7b777ada7cdf12f5b0bf4caf43bf7aa Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 3 Sep 2021 09:51:38 +0200 Subject: KVM: Drop 'except' parameter from kvm_make_vcpus_request_mask() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Both remaining callers of kvm_make_vcpus_request_mask() pass 'NULL' for 'except' parameter so it can just be dropped. No functional change intended ©. Suggested-by: Sean Christopherson Reviewed-by: Sean Christopherson Signed-off-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini Message-Id: <20210903075141.403071-6-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/hyperv.c | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 1 - virt/kvm/kvm_main.c | 3 +-- 4 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 192062f65c97..b4b432a164ae 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1849,7 +1849,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool vp_bitmap, vcpu_bitmap); kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, - NULL, vcpu_mask, &hv_vcpu->tlb_flush); + vcpu_mask, &hv_vcpu->tlb_flush); } ret_success: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index aabd3a2ec1bc..7212ba654ba2 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9247,7 +9247,7 @@ void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, zalloc_cpumask_var(&cpus, GFP_ATOMIC); kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, - NULL, vcpu_bitmap, cpus); + vcpu_bitmap, cpus); free_cpumask_var(cpus); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 0f18df7fe874..89e1a0069833 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -160,7 +160,6 @@ static inline bool is_error_page(struct page *page) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 61101e7932f7..bcadbc0a70f2 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -288,7 +288,6 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu, } bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp) { struct kvm_vcpu *vcpu; @@ -299,7 +298,7 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { vcpu = kvm_get_vcpu(kvm, i); - if (!vcpu || vcpu == except) + if (!vcpu) continue; kvm_make_vcpu_request(kvm, vcpu, req, tmp, me); } -- cgit v1.2.3 From 620b2438abf98f09e19802cbc3bc2e98179cdbe2 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 3 Sep 2021 09:51:41 +0200 Subject: KVM: Make kvm_make_vcpus_request_mask() use pre-allocated cpu_kick_mask kvm_make_vcpus_request_mask() already disables preemption so just like kvm_make_all_cpus_request_except() it can be switched to using pre-allocated per-cpu cpumasks. This allows for improvements for both users of the function: in Hyper-V emulation code 'tlb_flush' can now be dropped from 'struct kvm_vcpu_hv' and kvm_make_scan_ioapic_request_mask() gets rid of dynamic allocation. cpumask_available() checks in kvm_make_vcpu_request() and kvm_kick_many_cpus() can now be dropped as they checks for an impossible condition: kvm_init() makes sure per-cpu masks are allocated. Signed-off-by: Vitaly Kuznetsov Reviewed-by: Sean Christopherson Signed-off-by: Paolo Bonzini Message-Id: <20210903075141.403071-9-vkuznets@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/hyperv.c | 5 +---- arch/x86/kvm/x86.c | 9 +-------- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 29 +++++++++-------------------- 5 files changed, 12 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f8f48a7ec577..120ac07e4094 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -581,7 +581,6 @@ struct kvm_vcpu_hv { struct kvm_hyperv_exit exit; struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); - cpumask_t tlb_flush; bool enforce_cpuid; struct { u32 features_eax; /* HYPERV_CPUID_FEATURES.EAX */ diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index b4b432a164ae..6f11cda2bfa4 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1754,7 +1754,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool int i; gpa_t gpa; struct kvm *kvm = vcpu->kvm; - struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; u64 vp_bitmap[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; @@ -1836,8 +1835,6 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool } } - cpumask_clear(&hv_vcpu->tlb_flush); - /* * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. @@ -1849,7 +1846,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool vp_bitmap, vcpu_bitmap); kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, - vcpu_mask, &hv_vcpu->tlb_flush); + vcpu_mask); } ret_success: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 7212ba654ba2..03568cbbe8bd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9242,14 +9242,7 @@ static void process_smi(struct kvm_vcpu *vcpu) void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { - cpumask_var_t cpus; - - zalloc_cpumask_var(&cpus, GFP_ATOMIC); - - kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, - vcpu_bitmap, cpus); - - free_cpumask_var(cpus); + kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, vcpu_bitmap); } void kvm_make_scan_ioapic_request(struct kvm *kvm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 89e1a0069833..f1b96a2ebaa7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -160,7 +160,7 @@ static inline bool is_error_page(struct page *page) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap, cpumask_var_t tmp); + unsigned long *vcpu_bitmap); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 9cb0fd1723e6..18d245fe2118 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -237,15 +237,8 @@ static void ack_flush(void *_completed) { } -static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait) +static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) { - const struct cpumask *cpus; - - if (likely(cpumask_available(tmp))) - cpus = tmp; - else - cpus = cpu_online_mask; - if (cpumask_empty(cpus)) return false; @@ -254,7 +247,7 @@ static inline bool kvm_kick_many_cpus(cpumask_var_t tmp, bool wait) } static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu, - unsigned int req, cpumask_var_t tmp, + unsigned int req, struct cpumask *tmp, int current_cpu) { int cpu; @@ -264,14 +257,6 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu, if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) return; - /* - * tmp can be "unavailable" if cpumasks are allocated off stack as - * allocation of the mask is deliberately not fatal and is handled by - * falling back to kicking all online CPUs. - */ - if (!cpumask_available(tmp)) - return; - /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_request_needs_ipi(), which could result in sending an IPI @@ -290,22 +275,26 @@ static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu, } bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - unsigned long *vcpu_bitmap, cpumask_var_t tmp) + unsigned long *vcpu_bitmap) { struct kvm_vcpu *vcpu; + struct cpumask *cpus; int i, me; bool called; me = get_cpu(); + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); + for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { vcpu = kvm_get_vcpu(kvm, i); if (!vcpu) continue; - kvm_make_vcpu_request(kvm, vcpu, req, tmp, me); + kvm_make_vcpu_request(kvm, vcpu, req, cpus, me); } - called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; -- cgit v1.2.3 From a1c42ddedf35dbf5f25ea0982ed6e226eef7a78c Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 13 Sep 2021 15:57:44 +0200 Subject: kvm: rename KVM_MAX_VCPU_ID to KVM_MAX_VCPU_IDS KVM_MAX_VCPU_ID is not specifying the highest allowed vcpu-id, but the number of allowed vcpu-ids. This has already led to confusion, so rename KVM_MAX_VCPU_ID to KVM_MAX_VCPU_IDS to make its semantics more clear Suggested-by: Eduardo Habkost Signed-off-by: Juergen Gross Signed-off-by: Paolo Bonzini Message-Id: <20210913135745.13944-3-jgross@suse.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/devices/xics.rst | 2 +- Documentation/virt/kvm/devices/xive.rst | 2 +- arch/mips/kvm/mips.c | 2 +- arch/powerpc/include/asm/kvm_book3s.h | 2 +- arch/powerpc/include/asm/kvm_host.h | 4 ++-- arch/powerpc/kvm/book3s_xive.c | 2 +- arch/powerpc/kvm/powerpc.c | 2 +- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/ioapic.c | 2 +- arch/x86/kvm/ioapic.h | 4 ++-- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 4 ++-- tools/testing/selftests/kvm/kvm_create_max_vcpus.c | 2 +- virt/kvm/kvm_main.c | 2 +- 14 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/devices/xics.rst b/Documentation/virt/kvm/devices/xics.rst index 2d6927e0b776..bf32c77174ab 100644 --- a/Documentation/virt/kvm/devices/xics.rst +++ b/Documentation/virt/kvm/devices/xics.rst @@ -22,7 +22,7 @@ Groups: Errors: ======= ========================================== - -EINVAL Value greater than KVM_MAX_VCPU_ID. + -EINVAL Value greater than KVM_MAX_VCPU_IDS. -EFAULT Invalid user pointer for attr->addr. -EBUSY A vcpu is already connected to the device. ======= ========================================== diff --git a/Documentation/virt/kvm/devices/xive.rst b/Documentation/virt/kvm/devices/xive.rst index 8bdf3dc38f01..8b5e7b40bdf8 100644 --- a/Documentation/virt/kvm/devices/xive.rst +++ b/Documentation/virt/kvm/devices/xive.rst @@ -91,7 +91,7 @@ the legacy interrupt mode, referred as XICS (POWER7/8). Errors: ======= ========================================== - -EINVAL Value greater than KVM_MAX_VCPU_ID. + -EINVAL Value greater than KVM_MAX_VCPU_IDS. -EFAULT Invalid user pointer for attr->addr. -EBUSY A vCPU is already connected to the device. ======= ========================================== diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 75c6f264c626..562aa878b266 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1073,7 +1073,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID: - r = KVM_MAX_VCPU_ID; + r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_MIPS_FPU: /* We don't handle systems with inconsistent cpu_has_fpu */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index caaa0f592d8e..3d31f2c59e43 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -434,7 +434,7 @@ extern int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu); #define SPLIT_HACK_OFFS 0xfb000000 /* - * This packs a VCPU ID from the [0..KVM_MAX_VCPU_ID) space down to the + * This packs a VCPU ID from the [0..KVM_MAX_VCPU_IDS) space down to the * [0..KVM_MAX_VCPUS) space, using knowledge of the guest's core stride * (but not its actual threading mode, which is not available) to avoid * collisions. diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 080a7feb7731..59cb38b04ede 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -33,11 +33,11 @@ #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE #include /* for MAX_SMT_THREADS */ -#define KVM_MAX_VCPU_ID (MAX_SMT_THREADS * KVM_MAX_VCORES) +#define KVM_MAX_VCPU_IDS (MAX_SMT_THREADS * KVM_MAX_VCORES) #define KVM_MAX_NESTED_GUESTS KVMPPC_NR_LPIDS #else -#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */ #define __KVM_HAVE_ARCH_INTC_INITIALIZED diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index a18db9e16ea4..225008882958 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -1928,7 +1928,7 @@ int kvmppc_xive_set_nr_servers(struct kvmppc_xive *xive, u64 addr) pr_devel("%s nr_servers=%u\n", __func__, nr_servers); - if (!nr_servers || nr_servers > KVM_MAX_VCPU_ID) + if (!nr_servers || nr_servers > KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&xive->lock); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index b4e6f70b97b9..8ab90ce8738f 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -649,7 +649,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID: - r = KVM_MAX_VCPU_ID; + r = KVM_MAX_VCPU_IDS; break; #ifdef CONFIG_PPC_BOOK3S_64 case KVM_CAP_PPC_GET_SMMU_INFO: diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 120ac07e4094..09c18e54e0a1 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -50,7 +50,7 @@ * so ratio of 4 should be enough. */ #define KVM_VCPU_ID_RATIO 4 -#define KVM_MAX_VCPU_ID (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) +#define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) /* memory slots that are not exposed to userspace */ #define KVM_PRIVATE_MEM_SLOTS 3 diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 4e0f52660842..816a82515dcd 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_IDS); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 27e61ff3ac3e..e66e620c3bed 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -39,13 +39,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); + DECLARE_BITMAP(map, KVM_MAX_VCPU_IDS); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID]; + u8 vectors[KVM_MAX_VCPU_IDS]; }; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 03568cbbe8bd..6ad2f55c78a5 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4077,7 +4077,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_MAX_VCPUS; break; case KVM_CAP_MAX_VCPU_ID: - r = KVM_MAX_VCPU_ID; + r = KVM_MAX_VCPU_IDS; break; case KVM_CAP_PV_MMU: /* obsolete */ r = 0; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f1b96a2ebaa7..1f9e80ce4723 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -39,8 +39,8 @@ #include #include -#ifndef KVM_MAX_VCPU_ID -#define KVM_MAX_VCPU_ID KVM_MAX_VCPUS +#ifndef KVM_MAX_VCPU_IDS +#define KVM_MAX_VCPU_IDS KVM_MAX_VCPUS #endif /* diff --git a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c index 0299cd81b8ba..f968dfd4ee88 100644 --- a/tools/testing/selftests/kvm/kvm_create_max_vcpus.c +++ b/tools/testing/selftests/kvm/kvm_create_max_vcpus.c @@ -53,7 +53,7 @@ int main(int argc, char *argv[]) kvm_max_vcpu_id = kvm_max_vcpus; TEST_ASSERT(kvm_max_vcpu_id >= kvm_max_vcpus, - "KVM_MAX_VCPU_ID (%d) must be at least as large as KVM_MAX_VCPUS (%d).", + "KVM_MAX_VCPU_IDS (%d) must be at least as large as KVM_MAX_VCPUS (%d).", kvm_max_vcpu_id, kvm_max_vcpus); test_vcpu_creation(0, kvm_max_vcpus); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 18d245fe2118..3f6d450355f0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3595,7 +3595,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) struct kvm_vcpu *vcpu; struct page *page; - if (id >= KVM_MAX_VCPU_ID) + if (id >= KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&kvm->lock); -- cgit v1.2.3 From 515a0c79e7963cc4556ca61516cc09d39e592712 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Fri, 27 Aug 2021 16:00:03 +0800 Subject: kvm: irqfd: avoid update unmodified entries of the routing All of the irqfds would to be updated when update the irq routing, it's too expensive if there're too many irqfds. However we can reduce the cost by avoid some unnecessary updates. For irqs of MSI type on X86, the update can be saved if the msi values are not change. The vfio migration could receives benefit from this optimi- zaiton. The test VM has 128 vcpus and 8 VF (with 65 vectors enabled), so the VM has more than 520 irqfds. We mesure the cost of the vfio_msix_enable (in QEMU, it would set routing for each irqfd) for each VF, and we can see the total cost can be significantly reduced. Origin Apply this Patch 1st 8 4 2nd 15 5 3rd 22 6 4th 24 6 5th 36 7 6th 44 7 7th 51 8 8th 58 8 Total 258ms 51ms We're also tring to optimize the QEMU part [1], but it's still worth to optimize the KVM to gain more benefits. [1] https://lists.gnu.org/archive/html/qemu-devel/2021-08/msg04215.html Signed-off-by: Longpeng(Mike) Message-Id: <20210827080003.2689-1-longpeng2@huawei.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 9 +++++++++ include/linux/kvm_host.h | 2 ++ virt/kvm/eventfd.c | 15 ++++++++++++++- 3 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 25bfc12c0d08..ee1b9e168d46 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12062,6 +12062,15 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, return static_call(kvm_x86_update_pi_irte)(kvm, host_irq, guest_irq, set); } +bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) +{ + if (new->type != KVM_IRQ_ROUTING_MSI) + return true; + + return !!memcmp(&old->msi, &new->msi, sizeof(new->msi)); +} + bool kvm_vector_hashing_enabled(void) { return vector_hashing; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1f9e80ce4723..3f87d6ad20bf 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1764,6 +1764,8 @@ void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *); void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *); int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); +bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *, + struct kvm_kernel_irq_routing_entry *); #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */ #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index e996989cd580..2ad013b8bde9 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -281,6 +281,13 @@ int __attribute__((weak)) kvm_arch_update_irqfd_routing( { return 0; } + +bool __attribute__((weak)) kvm_arch_irqfd_route_changed( + struct kvm_kernel_irq_routing_entry *old, + struct kvm_kernel_irq_routing_entry *new) +{ + return true; +} #endif static int @@ -615,10 +622,16 @@ void kvm_irq_routing_update(struct kvm *kvm) spin_lock_irq(&kvm->irqfds.lock); list_for_each_entry(irqfd, &kvm->irqfds.items, list) { +#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS + /* Under irqfds.lock, so can read irq_entry safely */ + struct kvm_kernel_irq_routing_entry old = irqfd->irq_entry; +#endif + irqfd_update(kvm, irqfd); #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS - if (irqfd->producer) { + if (irqfd->producer && + kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) { int ret = kvm_arch_update_irqfd_routing( irqfd->kvm, irqfd->producer->irq, irqfd->gsi, 1); -- cgit v1.2.3 From bcf9033e5449bdcaa9bed46467a7141a8049dadb Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Tue, 14 Sep 2021 14:10:33 +0200 Subject: sched: move CPU field back into thread_info if THREAD_INFO_IN_TASK=y THREAD_INFO_IN_TASK moved the CPU field out of thread_info, but this causes some issues on architectures that define raw_smp_processor_id() in terms of this field, due to the fact that #include'ing linux/sched.h to get at struct task_struct is problematic in terms of circular dependencies. Given that thread_info and task_struct are the same data structure anyway when THREAD_INFO_IN_TASK=y, let's move it back so that having access to the type definition of struct thread_info is sufficient to reference the CPU number of the current task. Note that this requires THREAD_INFO_IN_TASK's definition of the task_thread_info() helper to be updated, as task_cpu() takes a pointer-to-const, whereas task_thread_info() (which is used to generate lvalues as well), needs a non-const pointer. So make it a macro instead. Signed-off-by: Ard Biesheuvel Acked-by: Catalin Marinas Acked-by: Mark Rutland Acked-by: Michael Ellerman --- arch/arm64/kernel/asm-offsets.c | 1 - arch/arm64/kernel/head.S | 2 +- arch/powerpc/kernel/asm-offsets.c | 2 +- arch/powerpc/kernel/smp.c | 2 +- include/linux/sched.h | 13 +------------ kernel/sched/sched.h | 4 ---- 6 files changed, 4 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index cee9f3e9f906..0bfc048221af 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -27,7 +27,6 @@ int main(void) { DEFINE(TSK_ACTIVE_MM, offsetof(struct task_struct, active_mm)); - DEFINE(TSK_CPU, offsetof(struct task_struct, cpu)); BLANK(); DEFINE(TSK_TI_CPU, offsetof(struct task_struct, thread_info.cpu)); DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 17962452e31d..6a98f1a38c29 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -412,7 +412,7 @@ SYM_FUNC_END(__create_page_tables) scs_load \tsk adr_l \tmp1, __per_cpu_offset - ldr w\tmp2, [\tsk, #TSK_CPU] + ldr w\tmp2, [\tsk, #TSK_TI_CPU] ldr \tmp1, [\tmp1, \tmp2, lsl #3] set_this_cpu_offset \tmp1 .endm diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index e563d3222d69..e37e4546034e 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -93,7 +93,7 @@ int main(void) #endif /* CONFIG_PPC64 */ OFFSET(TASK_STACK, task_struct, stack); #ifdef CONFIG_SMP - OFFSET(TASK_CPU, task_struct, cpu); + OFFSET(TASK_CPU, task_struct, thread_info.cpu); #endif #ifdef CONFIG_LIVEPATCH diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index 9cc7d3dbf439..512d875b45e0 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -1223,7 +1223,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle) paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) + THREAD_SIZE - STACK_FRAME_OVERHEAD; #endif - idle->cpu = cpu; + task_thread_info(idle)->cpu = cpu; secondary_current = current_set[cpu] = idle; } diff --git a/include/linux/sched.h b/include/linux/sched.h index 39039ce8ac4c..8699594e3f99 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -750,10 +750,6 @@ struct task_struct { #ifdef CONFIG_SMP int on_cpu; struct __call_single_node wake_entry; -#ifdef CONFIG_THREAD_INFO_IN_TASK - /* Current CPU: */ - unsigned int cpu; -#endif unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -1886,10 +1882,7 @@ extern struct thread_info init_thread_info; extern unsigned long init_stack[THREAD_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_THREAD_INFO_IN_TASK -static inline struct thread_info *task_thread_info(struct task_struct *task) -{ - return &task->thread_info; -} +# define task_thread_info(task) (&(task)->thread_info) #elif !defined(__HAVE_THREAD_FUNCTIONS) # define task_thread_info(task) ((struct thread_info *)(task)->stack) #endif @@ -2114,11 +2107,7 @@ static __always_inline bool need_resched(void) static inline unsigned int task_cpu(const struct task_struct *p) { -#ifdef CONFIG_THREAD_INFO_IN_TASK - return READ_ONCE(p->cpu); -#else return READ_ONCE(task_thread_info(p)->cpu); -#endif } extern void set_task_cpu(struct task_struct *p, unsigned int cpu); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3d3e5793e117..79fcbad11450 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1926,11 +1926,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) * per-task data have been completed by this moment. */ smp_wmb(); -#ifdef CONFIG_THREAD_INFO_IN_TASK - WRITE_ONCE(p->cpu, cpu); -#else WRITE_ONCE(task_thread_info(p)->cpu, cpu); -#endif p->wake_cpu = cpu; #endif } -- cgit v1.2.3 From 38a68934aa72459217986cf6b461d87f7602648a Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Fri, 24 Sep 2021 17:56:51 +0200 Subject: vfio: Move vfio_iommu_group_get() to vfio_register_group_dev() We don't need to hold a reference to the group in the driver as well as obtain a reference to the same group as the first thing vfio_register_group_dev() does. Since the drivers never use the group move this all into the core code. Signed-off-by: Jason Gunthorpe Signed-off-by: Christoph Hellwig Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20210924155705.4258-2-hch@lst.de Signed-off-by: Alex Williamson --- drivers/vfio/fsl-mc/vfio_fsl_mc.c | 17 ++----------- drivers/vfio/pci/vfio_pci_core.c | 13 ++-------- drivers/vfio/platform/vfio_platform_common.c | 13 +--------- drivers/vfio/vfio.c | 36 +++++++++++----------------- include/linux/vfio.h | 3 --- 5 files changed, 19 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c index 0ead91bfa838..9e838fed5603 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c @@ -505,22 +505,13 @@ static void vfio_fsl_uninit_device(struct vfio_fsl_mc_device *vdev) static int vfio_fsl_mc_probe(struct fsl_mc_device *mc_dev) { - struct iommu_group *group; struct vfio_fsl_mc_device *vdev; struct device *dev = &mc_dev->dev; int ret; - group = vfio_iommu_group_get(dev); - if (!group) { - dev_err(dev, "VFIO_FSL_MC: No IOMMU group\n"); - return -EINVAL; - } - vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); - if (!vdev) { - ret = -ENOMEM; - goto out_group_put; - } + if (!vdev) + return -ENOMEM; vfio_init_group_dev(&vdev->vdev, dev, &vfio_fsl_mc_ops); vdev->mc_dev = mc_dev; @@ -556,8 +547,6 @@ out_device: out_uninit: vfio_uninit_group_dev(&vdev->vdev); kfree(vdev); -out_group_put: - vfio_iommu_group_put(group, dev); return ret; } @@ -574,8 +563,6 @@ static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev) vfio_uninit_group_dev(&vdev->vdev); kfree(vdev); - vfio_iommu_group_put(mc_dev->dev.iommu_group, dev); - return 0; } diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 68198e0f2a63..43bab0ca3e68 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -1806,7 +1806,6 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_uninit_device); int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) { struct pci_dev *pdev = vdev->pdev; - struct iommu_group *group; int ret; if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) @@ -1825,10 +1824,6 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) return -EBUSY; } - group = vfio_iommu_group_get(&pdev->dev); - if (!group) - return -EINVAL; - if (pci_is_root_bus(pdev->bus)) { ret = vfio_assign_device_set(&vdev->vdev, vdev); } else if (!pci_probe_reset_slot(pdev->slot)) { @@ -1842,10 +1837,10 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) } if (ret) - goto out_group_put; + return ret; ret = vfio_pci_vf_init(vdev); if (ret) - goto out_group_put; + return ret; ret = vfio_pci_vga_init(vdev); if (ret) goto out_vf; @@ -1876,8 +1871,6 @@ out_power: vfio_pci_set_power_state(vdev, PCI_D0); out_vf: vfio_pci_vf_uninit(vdev); -out_group_put: - vfio_iommu_group_put(group, &pdev->dev); return ret; } EXPORT_SYMBOL_GPL(vfio_pci_core_register_device); @@ -1893,8 +1886,6 @@ void vfio_pci_core_unregister_device(struct vfio_pci_core_device *vdev) vfio_pci_vf_uninit(vdev); vfio_pci_vga_uninit(vdev); - vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); - if (!disable_idle_d3) vfio_pci_set_power_state(vdev, PCI_D0); } diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c index 6af7ce7d619c..256f55b84e70 100644 --- a/drivers/vfio/platform/vfio_platform_common.c +++ b/drivers/vfio/platform/vfio_platform_common.c @@ -642,7 +642,6 @@ static int vfio_platform_of_probe(struct vfio_platform_device *vdev, int vfio_platform_probe_common(struct vfio_platform_device *vdev, struct device *dev) { - struct iommu_group *group; int ret; vfio_init_group_dev(&vdev->vdev, dev, &vfio_platform_ops); @@ -663,24 +662,15 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev, goto out_uninit; } - group = vfio_iommu_group_get(dev); - if (!group) { - dev_err(dev, "No IOMMU group for device %s\n", vdev->name); - ret = -EINVAL; - goto put_reset; - } - ret = vfio_register_group_dev(&vdev->vdev); if (ret) - goto put_iommu; + goto put_reset; mutex_init(&vdev->igate); pm_runtime_enable(dev); return 0; -put_iommu: - vfio_iommu_group_put(group, dev); put_reset: vfio_platform_put_reset(vdev); out_uninit: @@ -696,7 +686,6 @@ void vfio_platform_remove_common(struct vfio_platform_device *vdev) pm_runtime_disable(vdev->device); vfio_platform_put_reset(vdev); vfio_uninit_group_dev(&vdev->vdev); - vfio_iommu_group_put(vdev->vdev.dev->iommu_group, vdev->vdev.dev); } EXPORT_SYMBOL_GPL(vfio_platform_remove_common); diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 3c034fe14ccb..b483b61b7c22 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -169,15 +169,7 @@ static void vfio_release_device_set(struct vfio_device *device) xa_unlock(&vfio_device_set_xa); } -/* - * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe - * and remove functions, any use cases other than acquiring the first - * reference for the purpose of calling vfio_register_group_dev() or removing - * that symmetric reference after vfio_unregister_group_dev() should use the raw - * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() - * removes the device from the dummy group and cannot be nested. - */ -struct iommu_group *vfio_iommu_group_get(struct device *dev) +static struct iommu_group *vfio_iommu_group_get(struct device *dev) { struct iommu_group *group; int __maybe_unused ret; @@ -220,18 +212,6 @@ struct iommu_group *vfio_iommu_group_get(struct device *dev) return group; } -EXPORT_SYMBOL_GPL(vfio_iommu_group_get); - -void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) -{ -#ifdef CONFIG_VFIO_NOIOMMU - if (iommu_group_get_iommudata(group) == &noiommu) - iommu_group_remove_device(dev); -#endif - - iommu_group_put(group); -} -EXPORT_SYMBOL_GPL(vfio_iommu_group_put); #ifdef CONFIG_VFIO_NOIOMMU static void *vfio_noiommu_open(unsigned long arg) @@ -841,7 +821,7 @@ int vfio_register_group_dev(struct vfio_device *device) if (!device->dev_set) vfio_assign_device_set(device, device); - iommu_group = iommu_group_get(device->dev); + iommu_group = vfio_iommu_group_get(device->dev); if (!iommu_group) return -EINVAL; @@ -849,6 +829,10 @@ int vfio_register_group_dev(struct vfio_device *device) if (!group) { group = vfio_create_group(iommu_group); if (IS_ERR(group)) { +#ifdef CONFIG_VFIO_NOIOMMU + if (iommu_group_get_iommudata(iommu_group) == &noiommu) + iommu_group_remove_device(device->dev); +#endif iommu_group_put(iommu_group); return PTR_ERR(group); } @@ -865,6 +849,10 @@ int vfio_register_group_dev(struct vfio_device *device) dev_WARN(device->dev, "Device already exists on group %d\n", iommu_group_id(iommu_group)); vfio_device_put(existing_device); +#ifdef CONFIG_VFIO_NOIOMMU + if (iommu_group_get_iommudata(iommu_group) == &noiommu) + iommu_group_remove_device(device->dev); +#endif vfio_group_put(group); return -EBUSY; } @@ -1010,6 +998,10 @@ void vfio_unregister_group_dev(struct vfio_device *device) if (list_empty(&group->device_list)) wait_event(group->container_q, !group->container); +#ifdef CONFIG_VFIO_NOIOMMU + if (iommu_group_get_iommudata(group->iommu_group) == &noiommu) + iommu_group_remove_device(device->dev); +#endif /* Matches the get in vfio_register_group_dev() */ vfio_group_put(group); } diff --git a/include/linux/vfio.h b/include/linux/vfio.h index b53a9557884a..f7083c2fd0d0 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -71,9 +71,6 @@ struct vfio_device_ops { int (*match)(struct vfio_device *vdev, char *buf); }; -extern struct iommu_group *vfio_iommu_group_get(struct device *dev); -extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); - void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_uninit_group_dev(struct vfio_device *device); -- cgit v1.2.3 From c68ea0d00ad82428154aed890ec9f793e460fa1c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Sep 2021 17:56:57 +0200 Subject: vfio: simplify iommu group allocation for mediated devices Reuse the logic in vfio_noiommu_group_alloc to allocate a fake single-device iommu group for mediated devices by factoring out a common function, and replacing the noiommu boolean field in struct vfio_group with an enum to distinguish the three different kinds of groups. Signed-off-by: Christoph Hellwig Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20210924155705.4258-8-hch@lst.de Signed-off-by: Alex Williamson --- drivers/s390/crypto/vfio_ap_ops.c | 2 +- drivers/vfio/mdev/mdev_driver.c | 45 ++----------------- drivers/vfio/mdev/vfio_mdev.c | 2 +- drivers/vfio/vfio.c | 92 ++++++++++++++++++++++++++++----------- include/linux/vfio.h | 1 + samples/vfio-mdev/mbochs.c | 2 +- samples/vfio-mdev/mdpy.c | 2 +- samples/vfio-mdev/mtty.c | 2 +- 8 files changed, 76 insertions(+), 72 deletions(-) (limited to 'include/linux') diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 118939a7729a..24755d1aedd5 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -351,7 +351,7 @@ static int vfio_ap_mdev_probe(struct mdev_device *mdev) list_add(&matrix_mdev->node, &matrix_dev->mdev_list); mutex_unlock(&matrix_dev->lock); - ret = vfio_register_group_dev(&matrix_mdev->vdev); + ret = vfio_register_emulated_iommu_dev(&matrix_mdev->vdev); if (ret) goto err_list; dev_set_drvdata(&mdev->dev, matrix_mdev); diff --git a/drivers/vfio/mdev/mdev_driver.c b/drivers/vfio/mdev/mdev_driver.c index e2cb1ff56f6c..7927ed4f1711 100644 --- a/drivers/vfio/mdev/mdev_driver.c +++ b/drivers/vfio/mdev/mdev_driver.c @@ -13,60 +13,23 @@ #include "mdev_private.h" -static int mdev_attach_iommu(struct mdev_device *mdev) -{ - int ret; - struct iommu_group *group; - - group = iommu_group_alloc(); - if (IS_ERR(group)) - return PTR_ERR(group); - - ret = iommu_group_add_device(group, &mdev->dev); - if (!ret) - dev_info(&mdev->dev, "MDEV: group_id = %d\n", - iommu_group_id(group)); - - iommu_group_put(group); - return ret; -} - -static void mdev_detach_iommu(struct mdev_device *mdev) -{ - iommu_group_remove_device(&mdev->dev); - dev_info(&mdev->dev, "MDEV: detaching iommu\n"); -} - static int mdev_probe(struct device *dev) { struct mdev_driver *drv = container_of(dev->driver, struct mdev_driver, driver); - struct mdev_device *mdev = to_mdev_device(dev); - int ret; - ret = mdev_attach_iommu(mdev); - if (ret) - return ret; - - if (drv->probe) { - ret = drv->probe(mdev); - if (ret) - mdev_detach_iommu(mdev); - } - - return ret; + if (!drv->probe) + return 0; + return drv->probe(to_mdev_device(dev)); } static void mdev_remove(struct device *dev) { struct mdev_driver *drv = container_of(dev->driver, struct mdev_driver, driver); - struct mdev_device *mdev = to_mdev_device(dev); if (drv->remove) - drv->remove(mdev); - - mdev_detach_iommu(mdev); + drv->remove(to_mdev_device(dev)); } static int mdev_match(struct device *dev, struct device_driver *drv) diff --git a/drivers/vfio/mdev/vfio_mdev.c b/drivers/vfio/mdev/vfio_mdev.c index 7a9883048216..a90e24b0c851 100644 --- a/drivers/vfio/mdev/vfio_mdev.c +++ b/drivers/vfio/mdev/vfio_mdev.c @@ -119,7 +119,7 @@ static int vfio_mdev_probe(struct mdev_device *mdev) return -ENOMEM; vfio_init_group_dev(vdev, &mdev->dev, &vfio_mdev_dev_ops); - ret = vfio_register_group_dev(vdev); + ret = vfio_register_emulated_iommu_dev(vdev); if (ret) goto out_uninit; diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 23eaebd2e28c..2508c8c39840 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -67,6 +67,30 @@ struct vfio_unbound_dev { struct list_head unbound_next; }; +enum vfio_group_type { + /* + * Physical device with IOMMU backing. + */ + VFIO_IOMMU, + + /* + * Virtual device without IOMMU backing. The VFIO core fakes up an + * iommu_group as the iommu_group sysfs interface is part of the + * userspace ABI. The user of these devices must not be able to + * directly trigger unmediated DMA. + */ + VFIO_EMULATED_IOMMU, + + /* + * Physical device without IOMMU backing. The VFIO core fakes up an + * iommu_group as the iommu_group sysfs interface is part of the + * userspace ABI. Users can trigger unmediated DMA by the device, + * usage is highly dangerous, requires an explicit opt-in and will + * taint the kernel. + */ + VFIO_NO_IOMMU, +}; + struct vfio_group { struct kref kref; int minor; @@ -83,7 +107,7 @@ struct vfio_group { struct mutex unbound_lock; atomic_t opened; wait_queue_head_t container_q; - bool noiommu; + enum vfio_group_type type; unsigned int dev_counter; struct kvm *kvm; struct blocking_notifier_head notifier; @@ -336,7 +360,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) * Group objects - create, release, get, put, search */ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, - bool noiommu) + enum vfio_group_type type) { struct vfio_group *group, *tmp; struct device *dev; @@ -355,7 +379,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, atomic_set(&group->opened, 0); init_waitqueue_head(&group->container_q); group->iommu_group = iommu_group; - group->noiommu = noiommu; + group->type = type; BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); group->nb.notifier_call = vfio_iommu_group_notifier; @@ -391,8 +415,8 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, } dev = device_create(vfio.class, NULL, - MKDEV(MAJOR(vfio.group_devt), minor), - group, "%s%d", group->noiommu ? "noiommu-" : "", + MKDEV(MAJOR(vfio.group_devt), minor), group, "%s%d", + group->type == VFIO_NO_IOMMU ? "noiommu-" : "", iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); @@ -778,8 +802,8 @@ void vfio_uninit_group_dev(struct vfio_device *device) } EXPORT_SYMBOL_GPL(vfio_uninit_group_dev); -#ifdef CONFIG_VFIO_NOIOMMU -static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev) +static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev, + enum vfio_group_type type) { struct iommu_group *iommu_group; struct vfio_group *group; @@ -794,7 +818,7 @@ static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev) if (ret) goto out_put_group; - group = vfio_create_group(iommu_group, true); + group = vfio_create_group(iommu_group, type); if (IS_ERR(group)) { ret = PTR_ERR(group); goto out_remove_device; @@ -808,7 +832,6 @@ out_put_group: iommu_group_put(iommu_group); return ERR_PTR(ret); } -#endif static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) { @@ -824,7 +847,7 @@ static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) * bus. Taint the kernel because we're about to give a DMA * capable device to a user without IOMMU protection. */ - group = vfio_noiommu_group_alloc(dev); + group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU); if (!IS_ERR(group)) { add_taint(TAINT_USER, LOCKDEP_STILL_OK); dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); @@ -841,7 +864,7 @@ static struct vfio_group *vfio_group_find_or_alloc(struct device *dev) goto out_put; /* a newly created vfio_group keeps the reference. */ - group = vfio_create_group(iommu_group, false); + group = vfio_create_group(iommu_group, VFIO_IOMMU); if (IS_ERR(group)) goto out_put; return group; @@ -851,10 +874,13 @@ out_put: return group; } -int vfio_register_group_dev(struct vfio_device *device) +static int __vfio_register_dev(struct vfio_device *device, + struct vfio_group *group) { struct vfio_device *existing_device; - struct vfio_group *group; + + if (IS_ERR(group)) + return PTR_ERR(group); /* * If the driver doesn't specify a set then the device is added to a @@ -863,16 +889,13 @@ int vfio_register_group_dev(struct vfio_device *device) if (!device->dev_set) vfio_assign_device_set(device, device); - group = vfio_group_find_or_alloc(device->dev); - if (IS_ERR(group)) - return PTR_ERR(group); - existing_device = vfio_group_get_device(group, device->dev); if (existing_device) { dev_WARN(device->dev, "Device already exists on group %d\n", iommu_group_id(group->iommu_group)); vfio_device_put(existing_device); - if (group->noiommu) + if (group->type == VFIO_NO_IOMMU || + group->type == VFIO_EMULATED_IOMMU) iommu_group_remove_device(device->dev); vfio_group_put(group); return -EBUSY; @@ -891,8 +914,25 @@ int vfio_register_group_dev(struct vfio_device *device) return 0; } + +int vfio_register_group_dev(struct vfio_device *device) +{ + return __vfio_register_dev(device, + vfio_group_find_or_alloc(device->dev)); +} EXPORT_SYMBOL_GPL(vfio_register_group_dev); +/* + * Register a virtual device without IOMMU backing. The user of this + * device must not be able to directly trigger unmediated DMA. + */ +int vfio_register_emulated_iommu_dev(struct vfio_device *device) +{ + return __vfio_register_dev(device, + vfio_noiommu_group_alloc(device->dev, VFIO_EMULATED_IOMMU)); +} +EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev); + /** * Get a reference to the vfio_device for a device. Even if the * caller thinks they own the device, they could be racing with a @@ -1019,7 +1059,7 @@ void vfio_unregister_group_dev(struct vfio_device *device) if (list_empty(&group->device_list)) wait_event(group->container_q, !group->container); - if (group->noiommu) + if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU) iommu_group_remove_device(device->dev); /* Matches the get in vfio_register_group_dev() */ @@ -1368,7 +1408,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) + if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) return -EPERM; f = fdget(container_fd); @@ -1388,7 +1428,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) /* Real groups and fake groups cannot mix */ if (!list_empty(&container->group_list) && - container->noiommu != group->noiommu) { + container->noiommu != (group->type == VFIO_NO_IOMMU)) { ret = -EPERM; goto unlock_out; } @@ -1402,7 +1442,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; - container->noiommu = group->noiommu; + container->noiommu = (group->type == VFIO_NO_IOMMU); list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1426,7 +1466,7 @@ static int vfio_group_add_container_user(struct vfio_group *group) if (!atomic_inc_not_zero(&group->container_users)) return -EINVAL; - if (group->noiommu) { + if (group->type == VFIO_NO_IOMMU) { atomic_dec(&group->container_users); return -EPERM; } @@ -1451,7 +1491,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) + if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) return -EPERM; device = vfio_device_get_from_name(group, buf); @@ -1498,7 +1538,7 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(fdno, filep); - if (group->noiommu) + if (group->type == VFIO_NO_IOMMU) dev_warn(device->dev, "vfio-noiommu device opened by user " "(%s:%d)\n", current->comm, task_pid_nr(current)); return fdno; @@ -1594,7 +1634,7 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) { + if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) { vfio_group_put(group); return -EPERM; } diff --git a/include/linux/vfio.h b/include/linux/vfio.h index f7083c2fd0d0..bbe293008626 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -75,6 +75,7 @@ void vfio_init_group_dev(struct vfio_device *device, struct device *dev, const struct vfio_device_ops *ops); void vfio_uninit_group_dev(struct vfio_device *device); int vfio_register_group_dev(struct vfio_device *device); +int vfio_register_emulated_iommu_dev(struct vfio_device *device); void vfio_unregister_group_dev(struct vfio_device *device); extern struct vfio_device *vfio_device_get_from_dev(struct device *dev); extern void vfio_device_put(struct vfio_device *device); diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c index c313ab4d1f4e..cd41bec5fdeb 100644 --- a/samples/vfio-mdev/mbochs.c +++ b/samples/vfio-mdev/mbochs.c @@ -553,7 +553,7 @@ static int mbochs_probe(struct mdev_device *mdev) mbochs_create_config_space(mdev_state); mbochs_reset(mdev_state); - ret = vfio_register_group_dev(&mdev_state->vdev); + ret = vfio_register_emulated_iommu_dev(&mdev_state->vdev); if (ret) goto err_mem; dev_set_drvdata(&mdev->dev, mdev_state); diff --git a/samples/vfio-mdev/mdpy.c b/samples/vfio-mdev/mdpy.c index 8d1a80a0722a..fe5d43e797b6 100644 --- a/samples/vfio-mdev/mdpy.c +++ b/samples/vfio-mdev/mdpy.c @@ -258,7 +258,7 @@ static int mdpy_probe(struct mdev_device *mdev) mdpy_count++; - ret = vfio_register_group_dev(&mdev_state->vdev); + ret = vfio_register_emulated_iommu_dev(&mdev_state->vdev); if (ret) goto err_mem; dev_set_drvdata(&mdev->dev, mdev_state); diff --git a/samples/vfio-mdev/mtty.c b/samples/vfio-mdev/mtty.c index 5983cdb16e3d..a0e1a469bd47 100644 --- a/samples/vfio-mdev/mtty.c +++ b/samples/vfio-mdev/mtty.c @@ -741,7 +741,7 @@ static int mtty_probe(struct mdev_device *mdev) mtty_create_config_space(mdev_state); - ret = vfio_register_group_dev(&mdev_state->vdev); + ret = vfio_register_emulated_iommu_dev(&mdev_state->vdev); if (ret) goto err_vconfig; dev_set_drvdata(&mdev->dev, mdev_state); -- cgit v1.2.3 From 67462037872d5ca57dc4674cccff191947b9b43e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Sep 2021 17:56:58 +0200 Subject: vfio: remove unused method from vfio_iommu_driver_ops The read, write and mmap methods are never implemented, so remove them. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20210924155705.4258-9-hch@lst.de Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 50 -------------------------------------------------- include/linux/vfio.h | 5 ----- 2 files changed, 55 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 2508c8c39840..2c1c7316aa19 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1276,62 +1276,12 @@ static int vfio_fops_release(struct inode *inode, struct file *filep) return 0; } -/* - * Once an iommu driver is set, we optionally pass read/write/mmap - * on to the driver, allowing management interfaces beyond ioctl. - */ -static ssize_t vfio_fops_read(struct file *filep, char __user *buf, - size_t count, loff_t *ppos) -{ - struct vfio_container *container = filep->private_data; - struct vfio_iommu_driver *driver; - ssize_t ret = -EINVAL; - - driver = container->iommu_driver; - if (likely(driver && driver->ops->read)) - ret = driver->ops->read(container->iommu_data, - buf, count, ppos); - - return ret; -} - -static ssize_t vfio_fops_write(struct file *filep, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct vfio_container *container = filep->private_data; - struct vfio_iommu_driver *driver; - ssize_t ret = -EINVAL; - - driver = container->iommu_driver; - if (likely(driver && driver->ops->write)) - ret = driver->ops->write(container->iommu_data, - buf, count, ppos); - - return ret; -} - -static int vfio_fops_mmap(struct file *filep, struct vm_area_struct *vma) -{ - struct vfio_container *container = filep->private_data; - struct vfio_iommu_driver *driver; - int ret = -EINVAL; - - driver = container->iommu_driver; - if (likely(driver && driver->ops->mmap)) - ret = driver->ops->mmap(container->iommu_data, vma); - - return ret; -} - static const struct file_operations vfio_fops = { .owner = THIS_MODULE, .open = vfio_fops_open, .release = vfio_fops_release, - .read = vfio_fops_read, - .write = vfio_fops_write, .unlocked_ioctl = vfio_fops_unl_ioctl, .compat_ioctl = compat_ptr_ioctl, - .mmap = vfio_fops_mmap, }; /** diff --git a/include/linux/vfio.h b/include/linux/vfio.h index bbe293008626..7a57a0077f96 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -95,13 +95,8 @@ struct vfio_iommu_driver_ops { struct module *owner; void *(*open)(unsigned long arg); void (*release)(void *iommu_data); - ssize_t (*read)(void *iommu_data, char __user *buf, - size_t count, loff_t *ppos); - ssize_t (*write)(void *iommu_data, const char __user *buf, - size_t count, loff_t *size); long (*ioctl)(void *iommu_data, unsigned int cmd, unsigned long arg); - int (*mmap)(void *iommu_data, struct vm_area_struct *vma); int (*attach_group)(void *iommu_data, struct iommu_group *group); void (*detach_group)(void *iommu_data, -- cgit v1.2.3 From 8cc02d22d7e1596ed687c4ff967c32056c2bef3e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Sep 2021 17:56:59 +0200 Subject: vfio: move the vfio_iommu_driver_ops interface out of Create a new private drivers/vfio/vfio.h header for the interface between the VFIO core and the iommu drivers. Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20210924155705.4258-10-hch@lst.de Signed-off-by: Alex Williamson --- drivers/vfio/vfio.c | 1 + drivers/vfio/vfio.h | 47 +++++++++++++++++++++++++++++++++++++ drivers/vfio/vfio_iommu_spapr_tce.c | 1 + drivers/vfio/vfio_iommu_type1.c | 1 + include/linux/vfio.h | 44 ---------------------------------- 5 files changed, 50 insertions(+), 44 deletions(-) create mode 100644 drivers/vfio/vfio.h (limited to 'include/linux') diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 2c1c7316aa19..6589e296ef34 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -32,6 +32,7 @@ #include #include #include +#include "vfio.h" #define DRIVER_VERSION "0.3" #define DRIVER_AUTHOR "Alex Williamson " diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h new file mode 100644 index 000000000000..a78de649eb2f --- /dev/null +++ b/drivers/vfio/vfio.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson + */ + +/* events for the backend driver notify callback */ +enum vfio_iommu_notify_type { + VFIO_IOMMU_CONTAINER_CLOSE = 0, +}; + +/** + * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks + */ +struct vfio_iommu_driver_ops { + char *name; + struct module *owner; + void *(*open)(unsigned long arg); + void (*release)(void *iommu_data); + long (*ioctl)(void *iommu_data, unsigned int cmd, + unsigned long arg); + int (*attach_group)(void *iommu_data, + struct iommu_group *group); + void (*detach_group)(void *iommu_data, + struct iommu_group *group); + int (*pin_pages)(void *iommu_data, + struct iommu_group *group, + unsigned long *user_pfn, + int npage, int prot, + unsigned long *phys_pfn); + int (*unpin_pages)(void *iommu_data, + unsigned long *user_pfn, int npage); + int (*register_notifier)(void *iommu_data, + unsigned long *events, + struct notifier_block *nb); + int (*unregister_notifier)(void *iommu_data, + struct notifier_block *nb); + int (*dma_rw)(void *iommu_data, dma_addr_t user_iova, + void *data, size_t count, bool write); + struct iommu_domain *(*group_iommu_domain)(void *iommu_data, + struct iommu_group *group); + void (*notify)(void *iommu_data, + enum vfio_iommu_notify_type event); +}; + +int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); +void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops); diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index fe888b5dcc00..3efd09faeca4 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -20,6 +20,7 @@ #include #include #include +#include "vfio.h" #include #include diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 0e9217687f5c..2e51e4390c15 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -40,6 +40,7 @@ #include #include #include +#include "vfio.h" #define DRIVER_VERSION "0.2" #define DRIVER_AUTHOR "Alex Williamson " diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 7a57a0077f96..76191d7abed1 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -82,50 +82,6 @@ extern void vfio_device_put(struct vfio_device *device); int vfio_assign_device_set(struct vfio_device *device, void *set_id); -/* events for the backend driver notify callback */ -enum vfio_iommu_notify_type { - VFIO_IOMMU_CONTAINER_CLOSE = 0, -}; - -/** - * struct vfio_iommu_driver_ops - VFIO IOMMU driver callbacks - */ -struct vfio_iommu_driver_ops { - char *name; - struct module *owner; - void *(*open)(unsigned long arg); - void (*release)(void *iommu_data); - long (*ioctl)(void *iommu_data, unsigned int cmd, - unsigned long arg); - int (*attach_group)(void *iommu_data, - struct iommu_group *group); - void (*detach_group)(void *iommu_data, - struct iommu_group *group); - int (*pin_pages)(void *iommu_data, - struct iommu_group *group, - unsigned long *user_pfn, - int npage, int prot, - unsigned long *phys_pfn); - int (*unpin_pages)(void *iommu_data, - unsigned long *user_pfn, int npage); - int (*register_notifier)(void *iommu_data, - unsigned long *events, - struct notifier_block *nb); - int (*unregister_notifier)(void *iommu_data, - struct notifier_block *nb); - int (*dma_rw)(void *iommu_data, dma_addr_t user_iova, - void *data, size_t count, bool write); - struct iommu_domain *(*group_iommu_domain)(void *iommu_data, - struct iommu_group *group); - void (*notify)(void *iommu_data, - enum vfio_iommu_notify_type event); -}; - -extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); - -extern void vfio_unregister_iommu_driver( - const struct vfio_iommu_driver_ops *ops); - /* * External user API */ -- cgit v1.2.3 From fda49d97f2c4faf0b42e8796d3e6c868d992f3af Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 24 Sep 2021 17:57:00 +0200 Subject: vfio: remove the unused mdev iommu hook The iommu_device field in struct mdev_device has never been used since it was added more than 2 years ago. This is a manual revert of commit 7bd50f0cd2 ("vfio/type1: Add domain at(de)taching group helpers"). Signed-off-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20210924155705.4258-11-hch@lst.de Signed-off-by: Alex Williamson --- drivers/vfio/vfio_iommu_type1.c | 133 ++++++++-------------------------------- include/linux/mdev.h | 20 ------ 2 files changed, 26 insertions(+), 127 deletions(-) (limited to 'include/linux') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 2e51e4390c15..42a6be1fb726 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -114,7 +114,6 @@ struct vfio_batch { struct vfio_iommu_group { struct iommu_group *iommu_group; struct list_head next; - bool mdev_group; /* An mdev group */ bool pinned_page_dirty_scope; }; @@ -1935,61 +1934,6 @@ static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions, return ret; } -static int vfio_mdev_attach_domain(struct device *dev, void *data) -{ - struct mdev_device *mdev = to_mdev_device(dev); - struct iommu_domain *domain = data; - struct device *iommu_device; - - iommu_device = mdev_get_iommu_device(mdev); - if (iommu_device) { - if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX)) - return iommu_aux_attach_device(domain, iommu_device); - else - return iommu_attach_device(domain, iommu_device); - } - - return -EINVAL; -} - -static int vfio_mdev_detach_domain(struct device *dev, void *data) -{ - struct mdev_device *mdev = to_mdev_device(dev); - struct iommu_domain *domain = data; - struct device *iommu_device; - - iommu_device = mdev_get_iommu_device(mdev); - if (iommu_device) { - if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX)) - iommu_aux_detach_device(domain, iommu_device); - else - iommu_detach_device(domain, iommu_device); - } - - return 0; -} - -static int vfio_iommu_attach_group(struct vfio_domain *domain, - struct vfio_iommu_group *group) -{ - if (group->mdev_group) - return iommu_group_for_each_dev(group->iommu_group, - domain->domain, - vfio_mdev_attach_domain); - else - return iommu_attach_group(domain->domain, group->iommu_group); -} - -static void vfio_iommu_detach_group(struct vfio_domain *domain, - struct vfio_iommu_group *group) -{ - if (group->mdev_group) - iommu_group_for_each_dev(group->iommu_group, domain->domain, - vfio_mdev_detach_domain); - else - iommu_detach_group(domain->domain, group->iommu_group); -} - static bool vfio_bus_is_mdev(struct bus_type *bus) { struct bus_type *mdev_bus; @@ -2004,20 +1948,6 @@ static bool vfio_bus_is_mdev(struct bus_type *bus) return ret; } -static int vfio_mdev_iommu_device(struct device *dev, void *data) -{ - struct mdev_device *mdev = to_mdev_device(dev); - struct device **old = data, *new; - - new = mdev_get_iommu_device(mdev); - if (!new || (*old && *old != new)) - return -EINVAL; - - *old = new; - - return 0; -} - /* * This is a helper function to insert an address range to iova list. * The list is initially created with a single entry corresponding to @@ -2278,38 +2208,25 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, goto out_free; if (vfio_bus_is_mdev(bus)) { - struct device *iommu_device = NULL; - - group->mdev_group = true; - - /* Determine the isolation type */ - ret = iommu_group_for_each_dev(iommu_group, &iommu_device, - vfio_mdev_iommu_device); - if (ret || !iommu_device) { - if (!iommu->external_domain) { - INIT_LIST_HEAD(&domain->group_list); - iommu->external_domain = domain; - vfio_update_pgsize_bitmap(iommu); - } else { - kfree(domain); - } - - list_add(&group->next, - &iommu->external_domain->group_list); - /* - * Non-iommu backed group cannot dirty memory directly, - * it can only use interfaces that provide dirty - * tracking. - * The iommu scope can only be promoted with the - * addition of a dirty tracking group. - */ - group->pinned_page_dirty_scope = true; - mutex_unlock(&iommu->lock); - - return 0; + if (!iommu->external_domain) { + INIT_LIST_HEAD(&domain->group_list); + iommu->external_domain = domain; + vfio_update_pgsize_bitmap(iommu); + } else { + kfree(domain); } - bus = iommu_device->bus; + list_add(&group->next, &iommu->external_domain->group_list); + /* + * Non-iommu backed group cannot dirty memory directly, it can + * only use interfaces that provide dirty tracking. + * The iommu scope can only be promoted with the addition of a + * dirty tracking group. + */ + group->pinned_page_dirty_scope = true; + mutex_unlock(&iommu->lock); + + return 0; } domain->domain = iommu_domain_alloc(bus); @@ -2324,7 +2241,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, goto out_domain; } - ret = vfio_iommu_attach_group(domain, group); + ret = iommu_attach_group(domain->domain, group->iommu_group); if (ret) goto out_domain; @@ -2391,15 +2308,17 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, list_for_each_entry(d, &iommu->domain_list, next) { if (d->domain->ops == domain->domain->ops && d->prot == domain->prot) { - vfio_iommu_detach_group(domain, group); - if (!vfio_iommu_attach_group(d, group)) { + iommu_detach_group(domain->domain, group->iommu_group); + if (!iommu_attach_group(d->domain, + group->iommu_group)) { list_add(&group->next, &d->group_list); iommu_domain_free(domain->domain); kfree(domain); goto done; } - ret = vfio_iommu_attach_group(domain, group); + ret = iommu_attach_group(domain->domain, + group->iommu_group); if (ret) goto out_domain; } @@ -2436,7 +2355,7 @@ done: return 0; out_detach: - vfio_iommu_detach_group(domain, group); + iommu_detach_group(domain->domain, group->iommu_group); out_domain: iommu_domain_free(domain->domain); vfio_iommu_iova_free(&iova_copy); @@ -2601,7 +2520,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data, if (!group) continue; - vfio_iommu_detach_group(domain, group); + iommu_detach_group(domain->domain, group->iommu_group); update_dirty_scope = !group->pinned_page_dirty_scope; list_del(&group->next); kfree(group); @@ -2689,7 +2608,7 @@ static void vfio_release_domain(struct vfio_domain *domain, bool external) list_for_each_entry_safe(group, group_tmp, &domain->group_list, next) { if (!external) - vfio_iommu_detach_group(domain, group); + iommu_detach_group(domain->domain, group->iommu_group); list_del(&group->next); kfree(group); } diff --git a/include/linux/mdev.h b/include/linux/mdev.h index 68427e8fadeb..15d03f6532d0 100644 --- a/include/linux/mdev.h +++ b/include/linux/mdev.h @@ -18,7 +18,6 @@ struct mdev_device { void *driver_data; struct list_head next; struct mdev_type *type; - struct device *iommu_device; bool active; }; @@ -27,25 +26,6 @@ static inline struct mdev_device *to_mdev_device(struct device *dev) return container_of(dev, struct mdev_device, dev); } -/* - * Called by the parent device driver to set the device which represents - * this mdev in iommu protection scope. By default, the iommu device is - * NULL, that indicates using vendor defined isolation. - * - * @dev: the mediated device that iommu will isolate. - * @iommu_device: a pci device which represents the iommu for @dev. - */ -static inline void mdev_set_iommu_device(struct mdev_device *mdev, - struct device *iommu_device) -{ - mdev->iommu_device = iommu_device; -} - -static inline struct device *mdev_get_iommu_device(struct mdev_device *mdev) -{ - return mdev->iommu_device; -} - unsigned int mdev_get_type_group_id(struct mdev_device *mdev); unsigned int mtype_get_type_group_id(struct mdev_type *mtype); struct device *mtype_get_parent_dev(struct mdev_type *mtype); -- cgit v1.2.3 From 02afb8d6048d6526619e6e2dcdc95ce9c2bdb52f Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 14 Sep 2021 23:38:57 +0900 Subject: kprobe: Simplify prepare_kprobe() by dropping redundant version The function prepare_kprobe() is called during kprobe registration and is responsible for ensuring any architecture related preparation for the kprobe is done before returning. One of two versions of prepare_kprobe() is chosen depending on the availability of KPROBE_ON_FTRACE in the kernel configuration. Simplify the code by dropping the version when KPROBE_ON_FTRACE is not selected - instead relying on kprobe_ftrace() to return false when KPROBE_ON_FTRACE is not set. No functional change. Link: https://lkml.kernel.org/r/163163033696.489837.9264661820279300788.stgit@devnote2 Signed-off-by: Punit Agrawal Acked-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 5 +++++ kernel/kprobes.c | 23 +++++++++-------------- 2 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e4f3bfe08757..0b75549b2815 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -354,6 +354,11 @@ static inline void wait_for_kprobe_optimizer(void) { } extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs); extern int arch_prepare_kprobe_ftrace(struct kprobe *p); +#else +static inline int arch_prepare_kprobe_ftrace(struct kprobe *p) +{ + return -EINVAL; +} #endif int arch_check_ftrace_location(struct kprobe *p); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 26fc9904c3b1..cfa9d3c263eb 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1033,15 +1033,6 @@ static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; -/* Must ensure p->addr is really on ftrace */ -static int prepare_kprobe(struct kprobe *p) -{ - if (!kprobe_ftrace(p)) - return arch_prepare_kprobe(p); - - return arch_prepare_kprobe_ftrace(p); -} - /* Caller must lock kprobe_mutex */ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) @@ -1113,11 +1104,6 @@ static int disarm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } #else /* !CONFIG_KPROBES_ON_FTRACE */ -static inline int prepare_kprobe(struct kprobe *p) -{ - return arch_prepare_kprobe(p); -} - static inline int arm_kprobe_ftrace(struct kprobe *p) { return -ENODEV; @@ -1129,6 +1115,15 @@ static inline int disarm_kprobe_ftrace(struct kprobe *p) } #endif +static int prepare_kprobe(struct kprobe *p) +{ + /* Must ensure p->addr is really on ftrace */ + if (kprobe_ftrace(p)) + return arch_prepare_kprobe_ftrace(p); + + return arch_prepare_kprobe(p); +} + /* Arm a kprobe with text_mutex */ static int arm_kprobe(struct kprobe *kp) { -- cgit v1.2.3 From 4402deae8993fb0e25a19bb999b38df13e25a7e0 Mon Sep 17 00:00:00 2001 From: Punit Agrawal Date: Tue, 14 Sep 2021 23:39:16 +0900 Subject: kprobes: Make arch_check_ftrace_location static arch_check_ftrace_location() was introduced as a weak function in commit f7f242ff004499 ("kprobes: introduce weak arch_check_ftrace_location() helper function") to allow architectures to handle kprobes call site on their own. Recently, the only architecture (csky) to implement arch_check_ftrace_location() was migrated to using the common version. As a result, further cleanup the code to drop the weak attribute and rename the function to remove the architecture specific implementation. Link: https://lkml.kernel.org/r/163163035673.489837.2367816318195254104.stgit@devnote2 Signed-off-by: Punit Agrawal Acked-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 2 -- kernel/kprobes.c | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0b75549b2815..8a9412bb0d5e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -361,8 +361,6 @@ static inline int arch_prepare_kprobe_ftrace(struct kprobe *p) } #endif -int arch_check_ftrace_location(struct kprobe *p); - /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index cfa9d3c263eb..30199bfcc74a 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1524,7 +1524,7 @@ static inline int warn_kprobe_rereg(struct kprobe *p) return ret; } -int __weak arch_check_ftrace_location(struct kprobe *p) +static int check_ftrace_location(struct kprobe *p) { unsigned long ftrace_addr; @@ -1547,7 +1547,7 @@ static int check_kprobe_address_safe(struct kprobe *p, { int ret; - ret = arch_check_ftrace_location(p); + ret = check_ftrace_location(p); if (ret) return ret; jump_label_lock(); -- cgit v1.2.3 From 223a76b268c9cfa265d454879ae09e2c9c808f87 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:39:34 +0900 Subject: kprobes: Fix coding style issues Fix coding style issues reported by checkpatch.pl and update comments to quote variable names and add "()" to function name. One TODO comment in __disarm_kprobe() is removed because it has been done by following commit. Link: https://lkml.kernel.org/r/163163037468.489837.4282347782492003960.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 40 ++++---- kernel/kprobes.c | 236 +++++++++++++++++++++++++----------------------- 2 files changed, 145 insertions(+), 131 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8a9412bb0d5e..756d3d23ce37 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -3,7 +3,6 @@ #define _LINUX_KPROBES_H /* * Kernel Probes (KProbes) - * include/linux/kprobes.h * * Copyright (C) IBM Corporation, 2002, 2004 * @@ -39,7 +38,7 @@ #define KPROBE_REENTER 0x00000004 #define KPROBE_HIT_SSDONE 0x00000008 -#else /* CONFIG_KPROBES */ +#else /* !CONFIG_KPROBES */ #include typedef int kprobe_opcode_t; struct arch_specific_insn { @@ -228,7 +227,7 @@ static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance return READ_ONCE(ri->rph->rp); } -#else /* CONFIG_KRETPROBES */ +#else /* !CONFIG_KRETPROBES */ static inline void arch_prepare_kretprobe(struct kretprobe *rp, struct pt_regs *regs) { @@ -239,11 +238,15 @@ static inline int arch_trampoline_kprobe(struct kprobe *p) } #endif /* CONFIG_KRETPROBES */ +/* Markers of '_kprobe_blacklist' section */ +extern unsigned long __start_kprobe_blacklist[]; +extern unsigned long __stop_kprobe_blacklist[]; + extern struct kretprobe_blackpoint kretprobe_blacklist[]; #ifdef CONFIG_KPROBES_SANITY_TEST extern int init_test_probes(void); -#else +#else /* !CONFIG_KPROBES_SANITY_TEST */ static inline int init_test_probes(void) { return 0; @@ -303,7 +306,7 @@ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ #define KPROBE_OPTINSN_PAGE_SYM "kprobe_optinsn_page" int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, unsigned long *value, char *type, char *sym); -#else /* __ARCH_WANT_KPROBES_INSN_SLOT */ +#else /* !__ARCH_WANT_KPROBES_INSN_SLOT */ #define DEFINE_INSN_CACHE_OPS(__name) \ static inline bool is_kprobe_##__name##_slot(unsigned long addr) \ { \ @@ -345,11 +348,12 @@ extern int sysctl_kprobes_optimization; extern int proc_kprobes_optimization_handler(struct ctl_table *table, int write, void *buffer, size_t *length, loff_t *ppos); -#endif +#endif /* CONFIG_SYSCTL */ extern void wait_for_kprobe_optimizer(void); -#else +#else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } #endif /* CONFIG_OPTPROBES */ + #ifdef CONFIG_KPROBES_ON_FTRACE extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs); @@ -359,7 +363,7 @@ static inline int arch_prepare_kprobe_ftrace(struct kprobe *p) { return -EINVAL; } -#endif +#endif /* CONFIG_KPROBES_ON_FTRACE */ /* Get the kprobe at this addr (if any) - called with preemption disabled */ struct kprobe *get_kprobe(void *addr); @@ -367,7 +371,7 @@ struct kprobe *get_kprobe(void *addr); /* kprobe_running() will just return the current_kprobe on this CPU */ static inline struct kprobe *kprobe_running(void) { - return (__this_cpu_read(current_kprobe)); + return __this_cpu_read(current_kprobe); } static inline void reset_current_kprobe(void) @@ -431,11 +435,11 @@ static inline struct kprobe *kprobe_running(void) } static inline int register_kprobe(struct kprobe *p) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int register_kprobes(struct kprobe **kps, int num) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline void unregister_kprobe(struct kprobe *p) { @@ -445,11 +449,11 @@ static inline void unregister_kprobes(struct kprobe **kps, int num) } static inline int register_kretprobe(struct kretprobe *rp) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int register_kretprobes(struct kretprobe **rps, int num) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline void unregister_kretprobe(struct kretprobe *rp) { @@ -465,11 +469,11 @@ static inline void kprobe_free_init_mem(void) } static inline int disable_kprobe(struct kprobe *kp) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline int enable_kprobe(struct kprobe *kp) { - return -ENOSYS; + return -EOPNOTSUPP; } static inline bool within_kprobe_blacklist(unsigned long addr) @@ -482,6 +486,7 @@ static inline int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, return -ERANGE; } #endif /* CONFIG_KPROBES */ + static inline int disable_kretprobe(struct kretprobe *rp) { return disable_kprobe(&rp->kp); @@ -496,13 +501,14 @@ static inline bool is_kprobe_insn_slot(unsigned long addr) { return false; } -#endif +#endif /* !CONFIG_KPROBES */ + #ifndef CONFIG_OPTPROBES static inline bool is_kprobe_optinsn_slot(unsigned long addr) { return false; } -#endif +#endif /* !CONFIG_OPTPROBES */ /* Returns true if kprobes handled the fault */ static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 7663c8a51889..ad39eeaa4371 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* * Kernel Probes (KProbes) - * kernel/kprobes.c * * Copyright (C) IBM Corporation, 2002, 2004 * @@ -52,18 +51,18 @@ static int kprobes_initialized; /* kprobe_table can be accessed by - * - Normal hlist traversal and RCU add/del under kprobe_mutex is held. + * - Normal hlist traversal and RCU add/del under 'kprobe_mutex' is held. * Or * - RCU hlist traversal under disabling preempt (breakpoint handlers) */ static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE]; -/* NOTE: change this value only with kprobe_mutex held */ +/* NOTE: change this value only with 'kprobe_mutex' held */ static bool kprobes_all_disarmed; -/* This protects kprobe_table and optimizing_list */ +/* This protects 'kprobe_table' and 'optimizing_list' */ static DEFINE_MUTEX(kprobe_mutex); -static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; +static DEFINE_PER_CPU(struct kprobe *, kprobe_instance); kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, unsigned int __unused) @@ -71,12 +70,15 @@ kprobe_opcode_t * __weak kprobe_lookup_name(const char *name, return ((kprobe_opcode_t *)(kallsyms_lookup_name(name))); } -/* Blacklist -- list of struct kprobe_blacklist_entry */ +/* + * Blacklist -- list of 'struct kprobe_blacklist_entry' to store info where + * kprobes can not probe. + */ static LIST_HEAD(kprobe_blacklist); #ifdef __ARCH_WANT_KPROBES_INSN_SLOT /* - * kprobe->ainsn.insn points to the copy of the instruction to be + * 'kprobe::ainsn.insn' points to the copy of the instruction to be * single-stepped. x86_64, POWER4 and above have no-exec support and * stepping on the instruction on a vmalloced/kmalloced/data page * is a recipe for disaster @@ -107,6 +109,12 @@ enum kprobe_slot_state { void __weak *alloc_insn_page(void) { + /* + * Use module_alloc() so this page is within +/- 2GB of where the + * kernel image and loaded module images reside. This is required + * for most of the architectures. + * (e.g. x86-64 needs this to handle the %rip-relative fixups.) + */ return module_alloc(PAGE_SIZE); } @@ -142,6 +150,7 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) list_for_each_entry_rcu(kip, &c->pages, list) { if (kip->nused < slots_per_page(c)) { int i; + for (i = 0; i < slots_per_page(c); i++) { if (kip->slot_used[i] == SLOT_CLEAN) { kip->slot_used[i] = SLOT_USED; @@ -167,11 +176,6 @@ kprobe_opcode_t *__get_insn_slot(struct kprobe_insn_cache *c) if (!kip) goto out; - /* - * Use module_alloc so this page is within +/- 2GB of where the - * kernel image and loaded module images reside. This is required - * so x86_64 can correctly handle the %rip-relative fixups. - */ kip->insns = c->alloc(); if (!kip->insns) { kfree(kip); @@ -233,6 +237,7 @@ static int collect_garbage_slots(struct kprobe_insn_cache *c) list_for_each_entry_safe(kip, next, &c->pages, list) { int i; + if (kip->ngarbage == 0) continue; kip->ngarbage = 0; /* we will collect all garbages */ @@ -313,7 +318,7 @@ int kprobe_cache_get_kallsym(struct kprobe_insn_cache *c, unsigned int *symnum, list_for_each_entry_rcu(kip, &c->pages, list) { if ((*symnum)--) continue; - strlcpy(sym, c->sym, KSYM_NAME_LEN); + strscpy(sym, c->sym, KSYM_NAME_LEN); *type = 't'; *value = (unsigned long)kip->insns; ret = 0; @@ -361,9 +366,9 @@ static inline void reset_kprobe_instance(void) /* * This routine is called either: - * - under the kprobe_mutex - during kprobe_[un]register() - * OR - * - with preemption disabled - from arch/xxx/kernel/kprobes.c + * - under the 'kprobe_mutex' - during kprobe_[un]register(). + * OR + * - with preemption disabled - from architecture specific code. */ struct kprobe *get_kprobe(void *addr) { @@ -383,22 +388,20 @@ NOKPROBE_SYMBOL(get_kprobe); static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); -/* Return true if the kprobe is an aggregator */ +/* Return true if 'p' is an aggregator */ static inline int kprobe_aggrprobe(struct kprobe *p) { return p->pre_handler == aggr_pre_handler; } -/* Return true(!0) if the kprobe is unused */ +/* Return true if 'p' is unused */ static inline int kprobe_unused(struct kprobe *p) { return kprobe_aggrprobe(p) && kprobe_disabled(p) && list_empty(&p->list); } -/* - * Keep all fields in the kprobe consistent - */ +/* Keep all fields in the kprobe consistent. */ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) { memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t)); @@ -406,11 +409,11 @@ static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p) } #ifdef CONFIG_OPTPROBES -/* NOTE: change this value only with kprobe_mutex held */ +/* NOTE: This is protected by 'kprobe_mutex'. */ static bool kprobes_allow_optimization; /* - * Call all pre_handler on the list, but ignores its return value. + * Call all 'kprobe::pre_handler' on the list, but ignores its return value. * This must be called from arch-dep optimized caller. */ void opt_pre_handler(struct kprobe *p, struct pt_regs *regs) @@ -438,7 +441,7 @@ static void free_aggr_kprobe(struct kprobe *p) kfree(op); } -/* Return true(!0) if the kprobe is ready for optimization. */ +/* Return true if the kprobe is ready for optimization. */ static inline int kprobe_optready(struct kprobe *p) { struct optimized_kprobe *op; @@ -451,7 +454,7 @@ static inline int kprobe_optready(struct kprobe *p) return 0; } -/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */ +/* Return true if the kprobe is disarmed. Note: p must be on hash list */ static inline int kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; @@ -465,7 +468,7 @@ static inline int kprobe_disarmed(struct kprobe *p) return kprobe_disabled(p) && list_empty(&op->list); } -/* Return true(!0) if the probe is queued on (un)optimizing lists */ +/* Return true if the probe is queued on (un)optimizing lists */ static int kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; @@ -480,7 +483,7 @@ static int kprobe_queued(struct kprobe *p) /* * Return an optimized kprobe whose optimizing code replaces - * instructions including addr (exclude breakpoint). + * instructions including 'addr' (exclude breakpoint). */ static struct kprobe *get_optimized_kprobe(unsigned long addr) { @@ -501,7 +504,7 @@ static struct kprobe *get_optimized_kprobe(unsigned long addr) return NULL; } -/* Optimization staging list, protected by kprobe_mutex */ +/* Optimization staging list, protected by 'kprobe_mutex' */ static LIST_HEAD(optimizing_list); static LIST_HEAD(unoptimizing_list); static LIST_HEAD(freeing_list); @@ -512,20 +515,20 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); /* * Optimize (replace a breakpoint with a jump) kprobes listed on - * optimizing_list. + * 'optimizing_list'. */ static void do_optimize_kprobes(void) { lockdep_assert_held(&text_mutex); /* - * The optimization/unoptimization refers online_cpus via - * stop_machine() and cpu-hotplug modifies online_cpus. - * And same time, text_mutex will be held in cpu-hotplug and here. - * This combination can cause a deadlock (cpu-hotplug try to lock - * text_mutex but stop_machine can not be done because online_cpus - * has been changed) - * To avoid this deadlock, caller must have locked cpu hotplug - * for preventing cpu-hotplug outside of text_mutex locking. + * The optimization/unoptimization refers 'online_cpus' via + * stop_machine() and cpu-hotplug modifies the 'online_cpus'. + * And same time, 'text_mutex' will be held in cpu-hotplug and here. + * This combination can cause a deadlock (cpu-hotplug tries to lock + * 'text_mutex' but stop_machine() can not be done because + * the 'online_cpus' has been changed) + * To avoid this deadlock, caller must have locked cpu-hotplug + * for preventing cpu-hotplug outside of 'text_mutex' locking. */ lockdep_assert_cpus_held(); @@ -539,7 +542,7 @@ static void do_optimize_kprobes(void) /* * Unoptimize (replace a jump with a breakpoint and remove the breakpoint - * if need) kprobes listed on unoptimizing_list. + * if need) kprobes listed on 'unoptimizing_list'. */ static void do_unoptimize_kprobes(void) { @@ -554,7 +557,7 @@ static void do_unoptimize_kprobes(void) return; arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); - /* Loop free_list for disarming */ + /* Loop on 'freeing_list' for disarming */ list_for_each_entry_safe(op, tmp, &freeing_list, list) { /* Switching from detour code to origin */ op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; @@ -565,7 +568,7 @@ static void do_unoptimize_kprobes(void) /* * Remove unused probes from hash list. After waiting * for synchronization, these probes are reclaimed. - * (reclaiming is done by do_free_cleaned_kprobes.) + * (reclaiming is done by do_free_cleaned_kprobes().) */ hlist_del_rcu(&op->kp.hlist); } else @@ -573,7 +576,7 @@ static void do_unoptimize_kprobes(void) } } -/* Reclaim all kprobes on the free_list */ +/* Reclaim all kprobes on the 'freeing_list' */ static void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; @@ -645,9 +648,9 @@ void wait_for_kprobe_optimizer(void) while (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) { mutex_unlock(&kprobe_mutex); - /* this will also make optimizing_work execute immmediately */ + /* This will also make 'optimizing_work' execute immmediately */ flush_delayed_work(&optimizing_work); - /* @optimizing_work might not have been queued yet, relax */ + /* 'optimizing_work' might not have been queued yet, relax */ cpu_relax(); mutex_lock(&kprobe_mutex); @@ -678,7 +681,7 @@ static void optimize_kprobe(struct kprobe *p) (kprobe_disabled(p) || kprobes_all_disarmed)) return; - /* kprobes with post_handler can not be optimized */ + /* kprobes with 'post_handler' can not be optimized */ if (p->post_handler) return; @@ -698,7 +701,10 @@ static void optimize_kprobe(struct kprobe *p) } op->kp.flags |= KPROBE_FLAG_OPTIMIZED; - /* On unoptimizing/optimizing_list, op must have OPTIMIZED flag */ + /* + * On the 'unoptimizing_list' and 'optimizing_list', + * 'op' must have OPTIMIZED flag + */ if (WARN_ON_ONCE(!list_empty(&op->list))) return; @@ -768,7 +774,7 @@ static int reuse_unused_kprobe(struct kprobe *ap) WARN_ON_ONCE(list_empty(&op->list)); /* Enable the probe again */ ap->flags &= ~KPROBE_FLAG_DISABLED; - /* Optimize it again (remove from op->list) */ + /* Optimize it again. (remove from 'op->list') */ if (!kprobe_optready(ap)) return -EINVAL; @@ -818,7 +824,7 @@ static void prepare_optimized_kprobe(struct kprobe *p) __prepare_optimized_kprobe(op, p); } -/* Allocate new optimized_kprobe and try to prepare optimized instructions */ +/* Allocate new optimized_kprobe and try to prepare optimized instructions. */ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) { struct optimized_kprobe *op; @@ -837,19 +843,19 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p) static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p); /* - * Prepare an optimized_kprobe and optimize it - * NOTE: p must be a normal registered kprobe + * Prepare an optimized_kprobe and optimize it. + * NOTE: 'p' must be a normal registered kprobe. */ static void try_to_optimize_kprobe(struct kprobe *p) { struct kprobe *ap; struct optimized_kprobe *op; - /* Impossible to optimize ftrace-based kprobe */ + /* Impossible to optimize ftrace-based kprobe. */ if (kprobe_ftrace(p)) return; - /* For preparing optimization, jump_label_text_reserved() is called */ + /* For preparing optimization, jump_label_text_reserved() is called. */ cpus_read_lock(); jump_label_lock(); mutex_lock(&text_mutex); @@ -860,14 +866,14 @@ static void try_to_optimize_kprobe(struct kprobe *p) op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { - /* If failed to setup optimizing, fallback to kprobe */ + /* If failed to setup optimizing, fallback to kprobe. */ arch_remove_optimized_kprobe(op); kfree(op); goto out; } init_aggr_kprobe(ap, p); - optimize_kprobe(ap); /* This just kicks optimizer thread */ + optimize_kprobe(ap); /* This just kicks optimizer thread. */ out: mutex_unlock(&text_mutex); @@ -882,7 +888,7 @@ static void optimize_all_kprobes(void) unsigned int i; mutex_lock(&kprobe_mutex); - /* If optimization is already allowed, just return */ + /* If optimization is already allowed, just return. */ if (kprobes_allow_optimization) goto out; @@ -908,7 +914,7 @@ static void unoptimize_all_kprobes(void) unsigned int i; mutex_lock(&kprobe_mutex); - /* If optimization is already prohibited, just return */ + /* If optimization is already prohibited, just return. */ if (!kprobes_allow_optimization) { mutex_unlock(&kprobe_mutex); return; @@ -926,7 +932,7 @@ static void unoptimize_all_kprobes(void) cpus_read_unlock(); mutex_unlock(&kprobe_mutex); - /* Wait for unoptimizing completion */ + /* Wait for unoptimizing completion. */ wait_for_kprobe_optimizer(); pr_info("kprobe jump-optimization is disabled. All kprobes are based on software breakpoint.\n"); } @@ -953,12 +959,12 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, } #endif /* CONFIG_SYSCTL */ -/* Put a breakpoint for a probe. Must be called with text_mutex locked */ +/* Put a breakpoint for a probe. Must be called with 'text_mutex' locked. */ static void __arm_kprobe(struct kprobe *p) { struct kprobe *_p; - /* Check collision with other optimized kprobes */ + /* Find the overlapping optimized kprobes. */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p)) /* Fallback to unoptimized kprobe */ @@ -968,7 +974,7 @@ static void __arm_kprobe(struct kprobe *p) optimize_kprobe(p); /* Try to optimize (add kprobe to a list) */ } -/* Remove the breakpoint of a probe. Must be called with text_mutex locked */ +/* Remove the breakpoint of a probe. Must be called with 'text_mutex' locked. */ static void __disarm_kprobe(struct kprobe *p, bool reopt) { struct kprobe *_p; @@ -978,12 +984,17 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) if (!kprobe_queued(p)) { arch_disarm_kprobe(p); - /* If another kprobe was blocked, optimize it. */ + /* If another kprobe was blocked, re-optimize it. */ _p = get_optimized_kprobe((unsigned long)p->addr); if (unlikely(_p) && reopt) optimize_kprobe(_p); } - /* TODO: reoptimize others after unoptimized this probe */ + /* + * TODO: Since unoptimization and real disarming will be done by + * the worker thread, we can not check whether another probe are + * unoptimized because of this probe here. It should be re-optimized + * by the worker thread. + */ } #else /* !CONFIG_OPTPROBES */ @@ -1036,7 +1047,7 @@ static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = { static int kprobe_ipmodify_enabled; static int kprobe_ftrace_enabled; -/* Caller must lock kprobe_mutex */ +/* Caller must lock 'kprobe_mutex' */ static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { @@ -1073,7 +1084,7 @@ static int arm_kprobe_ftrace(struct kprobe *p) ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled); } -/* Caller must lock kprobe_mutex */ +/* Caller must lock 'kprobe_mutex'. */ static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops, int *cnt) { @@ -1122,7 +1133,7 @@ static int prepare_kprobe(struct kprobe *p) return arch_prepare_kprobe(p); } -/* Arm a kprobe with text_mutex */ +/* Arm a kprobe with 'text_mutex'. */ static int arm_kprobe(struct kprobe *kp) { if (unlikely(kprobe_ftrace(kp))) @@ -1137,7 +1148,7 @@ static int arm_kprobe(struct kprobe *kp) return 0; } -/* Disarm a kprobe with text_mutex */ +/* Disarm a kprobe with 'text_mutex'. */ static int disarm_kprobe(struct kprobe *kp, bool reopt) { if (unlikely(kprobe_ftrace(kp))) @@ -1187,17 +1198,17 @@ static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs, } NOKPROBE_SYMBOL(aggr_post_handler); -/* Walks the list and increments nmissed count for multiprobe case */ +/* Walks the list and increments 'nmissed' if 'p' has child probes. */ void kprobes_inc_nmissed_count(struct kprobe *p) { struct kprobe *kp; + if (!kprobe_aggrprobe(p)) { p->nmissed++; } else { list_for_each_entry_rcu(kp, &p->list, list) kp->nmissed++; } - return; } NOKPROBE_SYMBOL(kprobes_inc_nmissed_count); @@ -1215,9 +1226,9 @@ static void recycle_rp_inst(struct kretprobe_instance *ri) { struct kretprobe *rp = get_kretprobe(ri); - if (likely(rp)) { + if (likely(rp)) freelist_add(&ri->freelist, &rp->freelist); - } else + else call_rcu(&ri->rcu, free_rp_inst_rcu); } NOKPROBE_SYMBOL(recycle_rp_inst); @@ -1243,8 +1254,8 @@ void kprobe_busy_end(void) } /* - * This function is called from finish_task_switch when task tk becomes dead, - * so that we can recycle any function-return probe instances associated + * This function is called from finish_task_switch() when task 'tk' becomes + * dead, so that we can recycle any kretprobe instances associated * with this task. These left over instances represent probed functions * that have been called but will never return. */ @@ -1292,7 +1303,7 @@ static inline void free_rp_inst(struct kretprobe *rp) } } -/* Add the new probe to ap->list */ +/* Add the new probe to 'ap->list'. */ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) { if (p->post_handler) @@ -1306,12 +1317,12 @@ static int add_new_kprobe(struct kprobe *ap, struct kprobe *p) } /* - * Fill in the required fields of the "manager kprobe". Replace the - * earlier kprobe in the hlist with the manager kprobe + * Fill in the required fields of the aggregator kprobe. Replace the + * earlier kprobe in the hlist with the aggregator kprobe. */ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) { - /* Copy p's insn slot to ap */ + /* Copy the insn slot of 'p' to 'ap'. */ copy_kprobe(p, ap); flush_insn_slot(ap); ap->addr = p->addr; @@ -1329,8 +1340,7 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p) } /* - * This is the second or subsequent kprobe at the address - handle - * the intricacies + * This registers the second or subsequent kprobe at the same address. */ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) { @@ -1344,7 +1354,7 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) mutex_lock(&text_mutex); if (!kprobe_aggrprobe(orig_p)) { - /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ + /* If 'orig_p' is not an 'aggr_kprobe', create new one. */ ap = alloc_aggr_kprobe(orig_p); if (!ap) { ret = -ENOMEM; @@ -1369,8 +1379,8 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) if (ret) /* * Even if fail to allocate new slot, don't need to - * free aggr_probe. It will be used next time, or - * freed by unregister_kprobe. + * free the 'ap'. It will be used next time, or + * freed by unregister_kprobe(). */ goto out; @@ -1385,7 +1395,7 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p) | KPROBE_FLAG_DISABLED; } - /* Copy ap's insn slot to p */ + /* Copy the insn slot of 'p' to 'ap'. */ copy_kprobe(ap, p); ret = add_new_kprobe(ap, p); @@ -1411,7 +1421,7 @@ out: bool __weak arch_within_kprobe_blacklist(unsigned long addr) { - /* The __kprobes marked functions and entry code must not be probed */ + /* The '__kprobes' functions and entry code must not be probed. */ return addr >= (unsigned long)__kprobes_text_start && addr < (unsigned long)__kprobes_text_end; } @@ -1423,8 +1433,8 @@ static bool __within_kprobe_blacklist(unsigned long addr) if (arch_within_kprobe_blacklist(addr)) return true; /* - * If there exists a kprobe_blacklist, verify and - * fail any probe registration in the prohibited area + * If 'kprobe_blacklist' is defined, check the address and + * reject any probe registration in the prohibited area. */ list_for_each_entry(ent, &kprobe_blacklist, list) { if (addr >= ent->start_addr && addr < ent->end_addr) @@ -1454,7 +1464,7 @@ bool within_kprobe_blacklist(unsigned long addr) } /* - * If we have a symbol_name argument, look it up and add the offset field + * If 'symbol_name' is specified, look it up and add the 'offset' * to it. This way, we can specify a relative address to a symbol. * This returns encoded errors if it fails to look up symbol or invalid * combination of parameters. @@ -1484,7 +1494,10 @@ static kprobe_opcode_t *kprobe_addr(struct kprobe *p) return _kprobe_addr(p->addr, p->symbol_name, p->offset); } -/* Check passed kprobe is valid and return kprobe in kprobe_table. */ +/* + * Check the 'p' is valid and return the aggregator kprobe + * at the same address. + */ static struct kprobe *__get_valid_kprobe(struct kprobe *p) { struct kprobe *ap, *list_p; @@ -1561,7 +1574,7 @@ static int check_kprobe_address_safe(struct kprobe *p, goto out; } - /* Check if are we probing a module */ + /* Check if 'p' is probing a module. */ *probed_mod = __module_text_address((unsigned long) p->addr); if (*probed_mod) { /* @@ -1574,7 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p, } /* - * If the module freed .init.text, we couldn't insert + * If the module freed '.init.text', we couldn't insert * kprobes in there. */ if (within_module_init((unsigned long)p->addr, *probed_mod) && @@ -1621,7 +1634,7 @@ int register_kprobe(struct kprobe *p) old_p = get_kprobe(p->addr); if (old_p) { - /* Since this may unoptimize old_p, locking text_mutex. */ + /* Since this may unoptimize 'old_p', locking 'text_mutex'. */ ret = register_aggr_kprobe(old_p, p); goto out; } @@ -1660,7 +1673,7 @@ out: } EXPORT_SYMBOL_GPL(register_kprobe); -/* Check if all probes on the aggrprobe are disabled */ +/* Check if all probes on the 'ap' are disabled. */ static int aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; @@ -1670,15 +1683,15 @@ static int aggr_kprobe_disabled(struct kprobe *ap) list_for_each_entry(kp, &ap->list, list) if (!kprobe_disabled(kp)) /* - * There is an active probe on the list. - * We can't disable this ap. + * Since there is an active probe on the list, + * we can't disable this 'ap'. */ return 0; return 1; } -/* Disable one kprobe: Make sure called under kprobe_mutex is locked */ +/* Disable one kprobe: Make sure called under 'kprobe_mutex' is locked. */ static struct kprobe *__disable_kprobe(struct kprobe *p) { struct kprobe *orig_p; @@ -1697,7 +1710,7 @@ static struct kprobe *__disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { /* - * If kprobes_all_disarmed is set, orig_p + * If 'kprobes_all_disarmed' is set, 'orig_p' * should have already been disarmed, so * skip unneed disarming process. */ @@ -1984,7 +1997,7 @@ int register_kretprobe(struct kretprobe *rp) if (ret) return ret; - /* If only rp->kp.addr is specified, check reregistering kprobes */ + /* If only 'rp->kp.addr' is specified, check reregistering kprobes */ if (rp->kp.addr && warn_kprobe_rereg(&rp->kp)) return -EINVAL; @@ -2089,13 +2102,13 @@ EXPORT_SYMBOL_GPL(unregister_kretprobes); #else /* CONFIG_KRETPROBES */ int register_kretprobe(struct kretprobe *rp) { - return -ENOSYS; + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(register_kretprobe); int register_kretprobes(struct kretprobe **rps, int num) { - return -ENOSYS; + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(register_kretprobes); @@ -2144,7 +2157,7 @@ static void kill_kprobe(struct kprobe *p) /* * The module is going away. We should disarm the kprobe which * is using ftrace, because ftrace framework is still available at - * MODULE_STATE_GOING notification. + * 'MODULE_STATE_GOING' notification. */ if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); @@ -2317,13 +2330,13 @@ static int __init populate_kprobe_blacklist(unsigned long *start, return ret; } - /* Symbols in __kprobes_text are blacklisted */ + /* Symbols in '__kprobes_text' are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__kprobes_text_start, (unsigned long)__kprobes_text_end); if (ret) return ret; - /* Symbols in noinstr section are blacklisted */ + /* Symbols in 'noinstr' section are blacklisted */ ret = kprobe_add_area_blacklist((unsigned long)__noinstr_text_start, (unsigned long)__noinstr_text_end); @@ -2395,9 +2408,9 @@ static int kprobes_module_callback(struct notifier_block *nb, return NOTIFY_DONE; /* - * When MODULE_STATE_GOING was notified, both of module .text and - * .init.text sections would be freed. When MODULE_STATE_LIVE was - * notified, only .init.text section would be freed. We need to + * When 'MODULE_STATE_GOING' was notified, both of module '.text' and + * '.init.text' sections would be freed. When 'MODULE_STATE_LIVE' was + * notified, only '.init.text' section would be freed. We need to * disable kprobes which have been inserted in the sections. */ mutex_lock(&kprobe_mutex); @@ -2414,9 +2427,9 @@ static int kprobes_module_callback(struct notifier_block *nb, * * Note, this will also move any optimized probes * that are pending to be removed from their - * corresponding lists to the freeing_list and + * corresponding lists to the 'freeing_list' and * will not be touched by the delayed - * kprobe_optimizer work handler. + * kprobe_optimizer() work handler. */ kill_kprobe(p); } @@ -2432,10 +2445,6 @@ static struct notifier_block kprobe_module_nb = { .priority = 0 }; -/* Markers of _kprobe_blacklist section */ -extern unsigned long __start_kprobe_blacklist[]; -extern unsigned long __stop_kprobe_blacklist[]; - void kprobe_free_init_mem(void) { void *start = (void *)(&__init_begin); @@ -2446,7 +2455,7 @@ void kprobe_free_init_mem(void) mutex_lock(&kprobe_mutex); - /* Kill all kprobes on initmem */ + /* Kill all kprobes on initmem because the target code has been freed. */ for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry(p, head, hlist) { @@ -2469,9 +2478,8 @@ static int __init init_kprobes(void) err = populate_kprobe_blacklist(__start_kprobe_blacklist, __stop_kprobe_blacklist); - if (err) { + if (err) pr_err("Failed to populate blacklist (error %d), kprobes not restricted, be careful using them!\n", err); - } if (kretprobe_blacklist_size) { /* lookup the function address from its name */ @@ -2488,7 +2496,7 @@ static int __init init_kprobes(void) kprobes_all_disarmed = false; #if defined(CONFIG_OPTPROBES) && defined(__ARCH_WANT_KPROBES_INSN_SLOT) - /* Init kprobe_optinsn_slots for allocation */ + /* Init 'kprobe_optinsn_slots' for allocation */ kprobe_optinsn_slots.insn_size = MAX_OPTINSN_SIZE; #endif @@ -2622,7 +2630,7 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v) list_entry(v, struct kprobe_blacklist_entry, list); /* - * If /proc/kallsyms is not showing kernel address, we won't + * If '/proc/kallsyms' is not showing kernel address, we won't * show them here either. */ if (!kallsyms_show_value(m->file->f_cred)) -- cgit v1.2.3 From dfc05b55c3c6b15dbd889e9901ecb3fb695421bd Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:39:46 +0900 Subject: kprobes: Use IS_ENABLED() instead of kprobes_built_in() Use IS_ENABLED(CONFIG_KPROBES) instead of kprobes_built_in(). This inline function is introduced only for avoiding #ifdef. But since now we have IS_ENABLED(), it is no longer needed. Link: https://lkml.kernel.org/r/163163038581.489837.2805250706507372658.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 756d3d23ce37..9c28fbb18e74 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -180,14 +180,6 @@ struct kprobe_blacklist_entry { DECLARE_PER_CPU(struct kprobe *, current_kprobe); DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); -/* - * For #ifdef avoidance: - */ -static inline int kprobes_built_in(void) -{ - return 1; -} - extern void kprobe_busy_begin(void); extern void kprobe_busy_end(void); @@ -417,10 +409,6 @@ int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value, char *type, char *sym); #else /* !CONFIG_KPROBES: */ -static inline int kprobes_built_in(void) -{ - return 0; -} static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { return 0; @@ -514,7 +502,7 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs, unsigned int trap) { - if (!kprobes_built_in()) + if (!IS_ENABLED(CONFIG_KPROBES)) return false; if (user_mode(regs)) return false; -- cgit v1.2.3 From c42421e205fc2570a4d019184ea7d6c382c93f4c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:40:07 +0900 Subject: kprobes: treewide: Use 'kprobe_opcode_t *' for the code address in get_optimized_kprobe() Since get_optimized_kprobe() is only used inside kprobes, it doesn't need to use 'unsigned long' type for 'addr' parameter. Make it use 'kprobe_opcode_t *' for the 'addr' parameter and subsequent call of arch_within_optimized_kprobe() also should use 'kprobe_opcode_t *'. Note that MAX_OPTIMIZED_LENGTH and RELATIVEJUMP_SIZE are defined by byte-size, but the size of 'kprobe_opcode_t' depends on the architecture. Therefore, we must be careful when calculating addresses using those macros. Link: https://lkml.kernel.org/r/163163040680.489837.12133032364499833736.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- arch/arm/probes/kprobes/opt-arm.c | 7 ++++--- arch/powerpc/kernel/optprobes.c | 6 +++--- arch/x86/kernel/kprobes/opt.c | 6 +++--- include/linux/kprobes.h | 2 +- kernel/kprobes.c | 10 +++++----- 5 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index c78180172120..dbef34ed933f 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -347,10 +347,11 @@ void arch_unoptimize_kprobes(struct list_head *oplist, } int arch_within_optimized_kprobe(struct optimized_kprobe *op, - unsigned long addr) + kprobe_opcode_t *addr) { - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + RELATIVEJUMP_SIZE > addr); + return (op->kp.addr <= addr && + op->kp.addr + (RELATIVEJUMP_SIZE / sizeof(kprobe_opcode_t)) > addr); + } void arch_remove_optimized_kprobe(struct optimized_kprobe *op) diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index c79899abcec8..325ba544883c 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -301,8 +301,8 @@ void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_li } } -int arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +int arch_within_optimized_kprobe(struct optimized_kprobe *op, kprobe_opcode_t *addr) { - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + RELATIVEJUMP_SIZE > addr); + return (op->kp.addr <= addr && + op->kp.addr + (RELATIVEJUMP_SIZE / sizeof(kprobe_opcode_t)) > addr); } diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 71425ebba98a..b4a54a52aa59 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -367,10 +367,10 @@ int arch_check_optimized_kprobe(struct optimized_kprobe *op) /* Check the addr is within the optimized instructions. */ int arch_within_optimized_kprobe(struct optimized_kprobe *op, - unsigned long addr) + kprobe_opcode_t *addr) { - return ((unsigned long)op->kp.addr <= addr && - (unsigned long)op->kp.addr + op->optinsn.size > addr); + return (op->kp.addr <= addr && + op->kp.addr + op->optinsn.size > addr); } /* Free optimized instruction slot */ diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9c28fbb18e74..6a5995f334a0 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -329,7 +329,7 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list); extern void arch_unoptimize_kprobe(struct optimized_kprobe *op); extern int arch_within_optimized_kprobe(struct optimized_kprobe *op, - unsigned long addr); + kprobe_opcode_t *addr); extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ec3d97fd8c6b..b6f1dcf4bff3 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -485,15 +485,15 @@ static int kprobe_queued(struct kprobe *p) * Return an optimized kprobe whose optimizing code replaces * instructions including 'addr' (exclude breakpoint). */ -static struct kprobe *get_optimized_kprobe(unsigned long addr) +static struct kprobe *get_optimized_kprobe(kprobe_opcode_t *addr) { int i; struct kprobe *p = NULL; struct optimized_kprobe *op; /* Don't check i == 0, since that is a breakpoint case. */ - for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH; i++) - p = get_kprobe((void *)(addr - i)); + for (i = 1; !p && i < MAX_OPTIMIZED_LENGTH / sizeof(kprobe_opcode_t); i++) + p = get_kprobe(addr - i); if (p && kprobe_optready(p)) { op = container_of(p, struct optimized_kprobe, kp); @@ -967,7 +967,7 @@ static void __arm_kprobe(struct kprobe *p) lockdep_assert_held(&text_mutex); /* Find the overlapping optimized kprobes. */ - _p = get_optimized_kprobe((unsigned long)p->addr); + _p = get_optimized_kprobe(p->addr); if (unlikely(_p)) /* Fallback to unoptimized kprobe */ unoptimize_kprobe(_p, true); @@ -989,7 +989,7 @@ static void __disarm_kprobe(struct kprobe *p, bool reopt) if (!kprobe_queued(p)) { arch_disarm_kprobe(p); /* If another kprobe was blocked, re-optimize it. */ - _p = get_optimized_kprobe((unsigned long)p->addr); + _p = get_optimized_kprobe(p->addr); if (unlikely(_p) && reopt) optimize_kprobe(_p); } -- cgit v1.2.3 From 29e8077ae2beea6a85ad2d0bae9c550bd5d05ed9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:40:16 +0900 Subject: kprobes: Use bool type for functions which returns boolean value Use the 'bool' type instead of 'int' for the functions which returns a boolean value, because this makes clear that those functions don't return any error code. Link: https://lkml.kernel.org/r/163163041649.489837.17311187321419747536.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 8 ++++---- kernel/kprobes.c | 26 +++++++++++++------------- kernel/trace/trace_kprobe.c | 2 +- 3 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 6a5995f334a0..0ba3f9e316d4 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -104,25 +104,25 @@ struct kprobe { #define KPROBE_FLAG_FTRACE 8 /* probe is using ftrace */ /* Has this kprobe gone ? */ -static inline int kprobe_gone(struct kprobe *p) +static inline bool kprobe_gone(struct kprobe *p) { return p->flags & KPROBE_FLAG_GONE; } /* Is this kprobe disabled ? */ -static inline int kprobe_disabled(struct kprobe *p) +static inline bool kprobe_disabled(struct kprobe *p) { return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE); } /* Is this kprobe really running optimized path ? */ -static inline int kprobe_optimized(struct kprobe *p) +static inline bool kprobe_optimized(struct kprobe *p) { return p->flags & KPROBE_FLAG_OPTIMIZED; } /* Is this kprobe uses ftrace ? */ -static inline int kprobe_ftrace(struct kprobe *p) +static inline bool kprobe_ftrace(struct kprobe *p) { return p->flags & KPROBE_FLAG_FTRACE; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index b6f1dcf4bff3..8021bccb7770 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -198,8 +198,8 @@ out: return slot; } -/* Return 1 if all garbages are collected, otherwise 0. */ -static int collect_one_slot(struct kprobe_insn_page *kip, int idx) +/* Return true if all garbages are collected, otherwise false. */ +static bool collect_one_slot(struct kprobe_insn_page *kip, int idx) { kip->slot_used[idx] = SLOT_CLEAN; kip->nused--; @@ -223,9 +223,9 @@ static int collect_one_slot(struct kprobe_insn_page *kip, int idx) kip->cache->free(kip->insns); kfree(kip); } - return 1; + return true; } - return 0; + return false; } static int collect_garbage_slots(struct kprobe_insn_cache *c) @@ -389,13 +389,13 @@ NOKPROBE_SYMBOL(get_kprobe); static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs); /* Return true if 'p' is an aggregator */ -static inline int kprobe_aggrprobe(struct kprobe *p) +static inline bool kprobe_aggrprobe(struct kprobe *p) { return p->pre_handler == aggr_pre_handler; } /* Return true if 'p' is unused */ -static inline int kprobe_unused(struct kprobe *p) +static inline bool kprobe_unused(struct kprobe *p) { return kprobe_aggrprobe(p) && kprobe_disabled(p) && list_empty(&p->list); @@ -455,7 +455,7 @@ static inline int kprobe_optready(struct kprobe *p) } /* Return true if the kprobe is disarmed. Note: p must be on hash list */ -static inline int kprobe_disarmed(struct kprobe *p) +static inline bool kprobe_disarmed(struct kprobe *p) { struct optimized_kprobe *op; @@ -469,16 +469,16 @@ static inline int kprobe_disarmed(struct kprobe *p) } /* Return true if the probe is queued on (un)optimizing lists */ -static int kprobe_queued(struct kprobe *p) +static bool kprobe_queued(struct kprobe *p) { struct optimized_kprobe *op; if (kprobe_aggrprobe(p)) { op = container_of(p, struct optimized_kprobe, kp); if (!list_empty(&op->list)) - return 1; + return true; } - return 0; + return false; } /* @@ -1678,7 +1678,7 @@ out: EXPORT_SYMBOL_GPL(register_kprobe); /* Check if all probes on the 'ap' are disabled. */ -static int aggr_kprobe_disabled(struct kprobe *ap) +static bool aggr_kprobe_disabled(struct kprobe *ap) { struct kprobe *kp; @@ -1690,9 +1690,9 @@ static int aggr_kprobe_disabled(struct kprobe *ap) * Since there is an active probe on the list, * we can't disable this 'ap'. */ - return 0; + return false; - return 1; + return true; } static struct kprobe *__disable_kprobe(struct kprobe *p) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 3a64ba4bbad6..0e1e7ce5f7ed 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -97,7 +97,7 @@ static nokprobe_inline unsigned long trace_kprobe_offset(struct trace_kprobe *tk static nokprobe_inline bool trace_kprobe_has_gone(struct trace_kprobe *tk) { - return !!(kprobe_gone(&tk->rp.kp)); + return kprobe_gone(&tk->rp.kp); } static nokprobe_inline bool trace_kprobe_within_module(struct trace_kprobe *tk, -- cgit v1.2.3 From f2ec8d9a3b8c0f22cd6a2b4f5a2d9aee5206e3b7 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:40:36 +0900 Subject: kprobes: treewide: Replace arch_deref_entry_point() with dereference_symbol_descriptor() ~15 years ago kprobes grew the 'arch_deref_entry_point()' __weak function: 3d7e33825d87: ("jprobes: make jprobes a little safer for users") But this is just open-coded dereference_symbol_descriptor() in essence, and its obscure nature was causing bugs. Just use the real thing and remove arch_deref_entry_point(). Link: https://lkml.kernel.org/r/163163043630.489837.7924988885652708696.stgit@devnote2 Signed-off-by: Masami Hiramatsu Tested-by: Andrii Nakryiko Signed-off-by: Steven Rostedt (VMware) --- arch/ia64/kernel/kprobes.c | 5 ----- arch/powerpc/kernel/kprobes.c | 11 ----------- include/linux/kprobes.h | 1 - kernel/kprobes.c | 7 +------ lib/error-inject.c | 3 ++- 5 files changed, 3 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index d4048518a1d7..0f8573bbf520 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -891,11 +891,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, return ret; } -unsigned long arch_deref_entry_point(void *entry) -{ - return ((struct fnptr *)entry)->ip; -} - static struct kprobe trampoline_p = { .pre_handler = trampoline_probe_handler }; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 7a7cd6bda53e..d422e297978b 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -542,17 +542,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) } NOKPROBE_SYMBOL(kprobe_fault_handler); -unsigned long arch_deref_entry_point(void *entry) -{ -#ifdef PPC64_ELF_ABI_v1 - if (!kernel_text_address((unsigned long)entry)) - return ppc_global_function_entry(entry); - else -#endif - return (unsigned long)entry; -} -NOKPROBE_SYMBOL(arch_deref_entry_point); - static struct kprobe trampoline_p = { .addr = (kprobe_opcode_t *) &kretprobe_trampoline, .pre_handler = trampoline_probe_handler diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 0ba3f9e316d4..2ed61fcbc89c 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -381,7 +381,6 @@ int register_kprobe(struct kprobe *p); void unregister_kprobe(struct kprobe *p); int register_kprobes(struct kprobe **kps, int num); void unregister_kprobes(struct kprobe **kps, int num); -unsigned long arch_deref_entry_point(void *); int register_kretprobe(struct kretprobe *rp); void unregister_kretprobe(struct kretprobe *rp); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 8021bccb7770..550042d9a6ef 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1861,11 +1861,6 @@ static struct notifier_block kprobe_exceptions_nb = { .priority = 0x7fffffff /* we need to be notified first */ }; -unsigned long __weak arch_deref_entry_point(void *entry) -{ - return (unsigned long)entry; -} - #ifdef CONFIG_KRETPROBES unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, @@ -2327,7 +2322,7 @@ static int __init populate_kprobe_blacklist(unsigned long *start, int ret; for (iter = start; iter < end; iter++) { - entry = arch_deref_entry_point((void *)*iter); + entry = (unsigned long)dereference_symbol_descriptor((void *)*iter); ret = kprobe_add_ksym_blacklist(entry); if (ret == -EINVAL) continue; diff --git a/lib/error-inject.c b/lib/error-inject.c index c73651b15b76..2ff5ef689d72 100644 --- a/lib/error-inject.c +++ b/lib/error-inject.c @@ -8,6 +8,7 @@ #include #include #include +#include /* Whitelist of symbols that can be overridden for error injection. */ static LIST_HEAD(error_injection_list); @@ -64,7 +65,7 @@ static void populate_error_injection_list(struct error_injection_entry *start, mutex_lock(&ei_mutex); for (iter = start; iter < end; iter++) { - entry = arch_deref_entry_point((void *)iter->addr); + entry = (unsigned long)dereference_symbol_descriptor((void *)iter->addr); if (!kernel_text_address(entry) || !kallsyms_lookup_size_offset(entry, &size, &offset)) { -- cgit v1.2.3 From 96fed8ac2bb64ab45497fdd8e3d390165b7a9be8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:40:45 +0900 Subject: kprobes: treewide: Remove trampoline_address from kretprobe_trampoline_handler() The __kretprobe_trampoline_handler() callback, called from low level arch kprobes methods, has the 'trampoline_address' parameter, which is entirely superfluous as it basically just replicates: dereference_kernel_function_descriptor(kretprobe_trampoline) In fact we had bugs in arch code where it wasn't replicated correctly. So remove this superfluous parameter and use kretprobe_trampoline_addr() instead. Link: https://lkml.kernel.org/r/163163044546.489837.13505751885476015002.stgit@devnote2 Signed-off-by: Masami Hiramatsu Tested-by: Andrii Nakryiko Signed-off-by: Steven Rostedt (VMware) --- arch/arc/kernel/kprobes.c | 2 +- arch/arm/probes/kprobes/core.c | 3 +-- arch/arm64/kernel/probes/kprobes.c | 3 +-- arch/csky/kernel/probes/kprobes.c | 2 +- arch/ia64/kernel/kprobes.c | 5 ++--- arch/mips/kernel/kprobes.c | 3 +-- arch/parisc/kernel/kprobes.c | 4 ++-- arch/powerpc/kernel/kprobes.c | 2 +- arch/riscv/kernel/probes/kprobes.c | 2 +- arch/s390/kernel/kprobes.c | 2 +- arch/sh/kernel/kprobes.c | 2 +- arch/sparc/kernel/kprobes.c | 2 +- arch/x86/include/asm/kprobes.h | 1 - arch/x86/kernel/kprobes/core.c | 2 +- include/linux/kprobes.h | 18 +++++++++++++----- kernel/kprobes.c | 3 +-- 16 files changed, 29 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 5f0415fc7328..3cee75c87f97 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -381,7 +381,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, static int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - regs->ret = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + regs->ret = __kretprobe_trampoline_handler(regs, NULL); /* By returning a non zero value, we are telling the kprobe handler * that we don't want the post_handler to run diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index a59e38de4a03..08098ed6f035 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -392,8 +392,7 @@ void __naked __kprobes kretprobe_trampoline(void) /* Called from kretprobe_trampoline */ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) { - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, - (void *)regs->ARM_fp); + return (void *)kretprobe_trampoline_handler(regs, (void *)regs->ARM_fp); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index ce429cbacd35..f627a12984a8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -401,8 +401,7 @@ int __init arch_populate_kprobe_blacklist(void) void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) { - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, - (void *)kernel_stack_pointer(regs)); + return (void *)kretprobe_trampoline_handler(regs, (void *)kernel_stack_pointer(regs)); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c index 632407bf45d5..784c5aba7f66 100644 --- a/arch/csky/kernel/probes/kprobes.c +++ b/arch/csky/kernel/probes/kprobes.c @@ -386,7 +386,7 @@ int __init arch_populate_kprobe_blacklist(void) void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) { - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + return (void *)kretprobe_trampoline_handler(regs, NULL); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 0f8573bbf520..44c84c20b626 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -392,14 +392,13 @@ static void __kprobes set_current_kprobe(struct kprobe *p, __this_cpu_write(current_kprobe, p); } -static void kretprobe_trampoline(void) +void kretprobe_trampoline(void) { } int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - regs->cr_iip = __kretprobe_trampoline_handler(regs, - dereference_function_descriptor(kretprobe_trampoline), NULL); + regs->cr_iip = __kretprobe_trampoline_handler(regs, NULL); /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index b0934a0d7aed..b33bd2498651 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -485,8 +485,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, static int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - instruction_pointer(regs) = __kretprobe_trampoline_handler(regs, - kretprobe_trampoline, NULL); + instruction_pointer(regs) = __kretprobe_trampoline_handler(regs, NULL); /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 6d21a515eea5..4a35ac6e2ca2 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -175,7 +175,7 @@ int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs) return 1; } -static inline void kretprobe_trampoline(void) +void kretprobe_trampoline(void) { asm volatile("nop"); asm volatile("nop"); @@ -193,7 +193,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { unsigned long orig_ret_address; - orig_ret_address = __kretprobe_trampoline_handler(regs, trampoline_p.addr, NULL); + orig_ret_address = __kretprobe_trampoline_handler(regs, NULL); instruction_pointer_set(regs, orig_ret_address); return 1; diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index d422e297978b..43c77142a262 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -417,7 +417,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { unsigned long orig_ret_address; - orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + orig_ret_address = __kretprobe_trampoline_handler(regs, NULL); /* * We get here through one of two paths: * 1. by taking a trap -> kprobe_handler() -> here diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index cab6f874358e..62d477cf11da 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -347,7 +347,7 @@ int __init arch_populate_kprobe_blacklist(void) void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) { - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + return (void *)kretprobe_trampoline_handler(regs, NULL); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 952d44b0610b..5fa86e54f129 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -343,7 +343,7 @@ static void __used kretprobe_trampoline_holder(void) */ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - regs->psw.addr = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + regs->psw.addr = __kretprobe_trampoline_handler(regs, NULL); /* * By returning a non-zero value, we are telling * kprobe_handler() that we don't want the post_handler diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 1c7f358ef0be..8e76a35e6e33 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -303,7 +303,7 @@ static void __used kretprobe_trampoline_holder(void) */ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { - regs->pc = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + regs->pc = __kretprobe_trampoline_handler(regs, NULL); return 1; } diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index 4c05a4ee6a0e..401534236c2e 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -451,7 +451,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, { unsigned long orig_ret_address = 0; - orig_ret_address = __kretprobe_trampoline_handler(regs, &kretprobe_trampoline, NULL); + orig_ret_address = __kretprobe_trampoline_handler(regs, NULL); regs->tpc = orig_ret_address; regs->tnpc = orig_ret_address + 4; diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index bd7f5886a789..71ea2eab43d5 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -49,7 +49,6 @@ extern __visible kprobe_opcode_t optprobe_template_end[]; extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); -asmlinkage void kretprobe_trampoline(void); extern void arch_kprobe_override_function(struct pt_regs *regs); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index b6e046e4b289..0c59ef5971de 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1064,7 +1064,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) regs->ip = (unsigned long)&kretprobe_trampoline; regs->orig_ax = ~0UL; - return (void *)kretprobe_trampoline_handler(regs, &kretprobe_trampoline, ®s->sp); + return (void *)kretprobe_trampoline_handler(regs, ®s->sp); } NOKPROBE_SYMBOL(trampoline_handler); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 2ed61fcbc89c..96f5df93e36e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -188,15 +188,23 @@ extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); extern int arch_trampoline_kprobe(struct kprobe *p); +void kretprobe_trampoline(void); +/* + * Since some architecture uses structured function pointer, + * use dereference_function_descriptor() to get real function address. + */ +static nokprobe_inline void *kretprobe_trampoline_addr(void) +{ + return dereference_kernel_function_descriptor(kretprobe_trampoline); +} + /* If the trampoline handler called from a kprobe, use this version */ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, - void *trampoline_address, - void *frame_pointer); + void *frame_pointer); static nokprobe_inline unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, - void *trampoline_address, - void *frame_pointer) + void *frame_pointer) { unsigned long ret; /* @@ -205,7 +213,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs, * be running at this point. */ kprobe_busy_begin(); - ret = __kretprobe_trampoline_handler(regs, trampoline_address, frame_pointer); + ret = __kretprobe_trampoline_handler(regs, frame_pointer); kprobe_busy_end(); return ret; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 550042d9a6ef..6ed755111eea 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1864,7 +1864,6 @@ static struct notifier_block kprobe_exceptions_nb = { #ifdef CONFIG_KRETPROBES unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, - void *trampoline_address, void *frame_pointer) { kprobe_opcode_t *correct_ret_addr = NULL; @@ -1879,7 +1878,7 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, BUG_ON(ri->fp != frame_pointer); - if (ri->ret_addr != trampoline_address) { + if (ri->ret_addr != kretprobe_trampoline_addr()) { correct_ret_addr = ri->ret_addr; /* * This is the real return address. Any other -- cgit v1.2.3 From adf8a61a940c49fea6fab9c3865f2b69b8ceef28 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:40:54 +0900 Subject: kprobes: treewide: Make it harder to refer kretprobe_trampoline directly Since now there is kretprobe_trampoline_addr() for referring the address of kretprobe trampoline code, we don't need to access kretprobe_trampoline directly. Make it harder to refer by renaming it to __kretprobe_trampoline(). Link: https://lkml.kernel.org/r/163163045446.489837.14510577516938803097.stgit@devnote2 Suggested-by: Ingo Molnar Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- arch/arc/include/asm/kprobes.h | 2 +- arch/arc/kernel/kprobes.c | 11 ++++++----- arch/arm/probes/kprobes/core.c | 6 +++--- arch/arm64/include/asm/kprobes.h | 2 +- arch/arm64/kernel/probes/kprobes.c | 2 +- arch/arm64/kernel/probes/kprobes_trampoline.S | 4 ++-- arch/csky/include/asm/kprobes.h | 2 +- arch/csky/kernel/probes/kprobes.c | 2 +- arch/csky/kernel/probes/kprobes_trampoline.S | 4 ++-- arch/ia64/kernel/kprobes.c | 8 ++++---- arch/mips/kernel/kprobes.c | 12 ++++++------ arch/parisc/kernel/kprobes.c | 4 ++-- arch/powerpc/include/asm/kprobes.h | 2 +- arch/powerpc/kernel/kprobes.c | 16 ++++++++-------- arch/powerpc/kernel/optprobes.c | 2 +- arch/powerpc/kernel/stacktrace.c | 2 +- arch/riscv/include/asm/kprobes.h | 2 +- arch/riscv/kernel/probes/kprobes.c | 2 +- arch/riscv/kernel/probes/kprobes_trampoline.S | 4 ++-- arch/s390/include/asm/kprobes.h | 2 +- arch/s390/kernel/kprobes.c | 10 +++++----- arch/s390/kernel/stacktrace.c | 2 +- arch/sh/include/asm/kprobes.h | 2 +- arch/sh/kernel/kprobes.c | 10 +++++----- arch/sparc/include/asm/kprobes.h | 2 +- arch/sparc/kernel/kprobes.c | 10 +++++----- arch/x86/kernel/kprobes/core.c | 18 +++++++++--------- include/linux/kprobes.h | 4 ++-- kernel/trace/trace_output.c | 2 +- 29 files changed, 76 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h index 2134721dce44..de1566e32cb8 100644 --- a/arch/arc/include/asm/kprobes.h +++ b/arch/arc/include/asm/kprobes.h @@ -46,7 +46,7 @@ struct kprobe_ctlblk { }; int kprobe_fault_handler(struct pt_regs *regs, unsigned long cause); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); void trap_is_kprobe(unsigned long address, struct pt_regs *regs); #else #define trap_is_kprobe(address, regs) diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c index 3cee75c87f97..e71d64119d71 100644 --- a/arch/arc/kernel/kprobes.c +++ b/arch/arc/kernel/kprobes.c @@ -363,8 +363,9 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, static void __used kretprobe_trampoline_holder(void) { - __asm__ __volatile__(".global kretprobe_trampoline\n" - "kretprobe_trampoline:\n" "nop\n"); + __asm__ __volatile__(".global __kretprobe_trampoline\n" + "__kretprobe_trampoline:\n" + "nop\n"); } void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, @@ -375,7 +376,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->blink = (unsigned long)&kretprobe_trampoline; + regs->blink = (unsigned long)&__kretprobe_trampoline; } static int __kprobes trampoline_probe_handler(struct kprobe *p, @@ -390,7 +391,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, } static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -402,7 +403,7 @@ int __init arch_init_kprobes(void) int __kprobes arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *) &kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *) &__kretprobe_trampoline) return 1; return 0; diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c index 08098ed6f035..67ce7eb8f285 100644 --- a/arch/arm/probes/kprobes/core.c +++ b/arch/arm/probes/kprobes/core.c @@ -373,7 +373,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, * for kretprobe handlers which should normally be interested in r0 only * anyway. */ -void __naked __kprobes kretprobe_trampoline(void) +void __naked __kprobes __kretprobe_trampoline(void) { __asm__ __volatile__ ( "stmdb sp!, {r0 - r11} \n\t" @@ -389,7 +389,7 @@ void __naked __kprobes kretprobe_trampoline(void) : : : "memory"); } -/* Called from kretprobe_trampoline */ +/* Called from __kretprobe_trampoline */ static __used __kprobes void *trampoline_handler(struct pt_regs *regs) { return (void *)kretprobe_trampoline_handler(regs, (void *)regs->ARM_fp); @@ -402,7 +402,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, ri->fp = (void *)regs->ARM_fp; /* Replace the return addr with trampoline addr. */ - regs->ARM_lr = (unsigned long)&kretprobe_trampoline; + regs->ARM_lr = (unsigned long)&__kretprobe_trampoline; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 5d38ff4a4806..05cd82eeca13 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -39,7 +39,7 @@ void arch_remove_kprobe(struct kprobe *); int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr); int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); void __kprobes *trampoline_probe_handler(struct pt_regs *regs); #endif /* CONFIG_KPROBES */ diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index f627a12984a8..e7ad6da980e8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -411,7 +411,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, ri->fp = (void *)kernel_stack_pointer(regs); /* replace return addr (x30) with trampoline */ - regs->regs[30] = (long)&kretprobe_trampoline; + regs->regs[30] = (long)&__kretprobe_trampoline; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 288a84e253cc..520ee8711db1 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -61,7 +61,7 @@ ldp x28, x29, [sp, #S_X28] .endm -SYM_CODE_START(kretprobe_trampoline) +SYM_CODE_START(__kretprobe_trampoline) sub sp, sp, #PT_REGS_SIZE save_all_base_regs @@ -79,4 +79,4 @@ SYM_CODE_START(kretprobe_trampoline) add sp, sp, #PT_REGS_SIZE ret -SYM_CODE_END(kretprobe_trampoline) +SYM_CODE_END(__kretprobe_trampoline) diff --git a/arch/csky/include/asm/kprobes.h b/arch/csky/include/asm/kprobes.h index b647bbde4d6d..55267cbf5204 100644 --- a/arch/csky/include/asm/kprobes.h +++ b/arch/csky/include/asm/kprobes.h @@ -41,7 +41,7 @@ void arch_remove_kprobe(struct kprobe *p); int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr); int kprobe_breakpoint_handler(struct pt_regs *regs); int kprobe_single_step_handler(struct pt_regs *regs); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); void __kprobes *trampoline_probe_handler(struct pt_regs *regs); #endif /* CONFIG_KPROBES */ diff --git a/arch/csky/kernel/probes/kprobes.c b/arch/csky/kernel/probes/kprobes.c index 784c5aba7f66..42920f25e73c 100644 --- a/arch/csky/kernel/probes/kprobes.c +++ b/arch/csky/kernel/probes/kprobes.c @@ -394,7 +394,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, { ri->ret_addr = (kprobe_opcode_t *)regs->lr; ri->fp = NULL; - regs->lr = (unsigned long) &kretprobe_trampoline; + regs->lr = (unsigned long) &__kretprobe_trampoline; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/csky/kernel/probes/kprobes_trampoline.S b/arch/csky/kernel/probes/kprobes_trampoline.S index b1fe3af24f03..ba48ad04a847 100644 --- a/arch/csky/kernel/probes/kprobes_trampoline.S +++ b/arch/csky/kernel/probes/kprobes_trampoline.S @@ -4,7 +4,7 @@ #include -ENTRY(kretprobe_trampoline) +ENTRY(__kretprobe_trampoline) SAVE_REGS_FTRACE mov a0, sp /* pt_regs */ @@ -16,4 +16,4 @@ ENTRY(kretprobe_trampoline) RESTORE_REGS_FTRACE rts -ENDPROC(kretprobe_trampoline) +ENDPROC(__kretprobe_trampoline) diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c index 44c84c20b626..1a7bab1c5d7c 100644 --- a/arch/ia64/kernel/kprobes.c +++ b/arch/ia64/kernel/kprobes.c @@ -392,7 +392,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, __this_cpu_write(current_kprobe, p); } -void kretprobe_trampoline(void) +void __kretprobe_trampoline(void) { } @@ -414,7 +414,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->b0 = (unsigned long)dereference_function_descriptor(kretprobe_trampoline); + regs->b0 = (unsigned long)dereference_function_descriptor(__kretprobe_trampoline); } /* Check the instruction in the slot is break */ @@ -897,14 +897,14 @@ static struct kprobe trampoline_p = { int __init arch_init_kprobes(void) { trampoline_p.addr = - dereference_function_descriptor(kretprobe_trampoline); + dereference_function_descriptor(__kretprobe_trampoline); return register_kprobe(&trampoline_p); } int __kprobes arch_trampoline_kprobe(struct kprobe *p) { if (p->addr == - dereference_function_descriptor(kretprobe_trampoline)) + dereference_function_descriptor(__kretprobe_trampoline)) return 1; return 0; diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c index b33bd2498651..6c7f3b143fdc 100644 --- a/arch/mips/kernel/kprobes.c +++ b/arch/mips/kernel/kprobes.c @@ -460,14 +460,14 @@ static void __used kretprobe_trampoline_holder(void) /* Keep the assembler from reordering and placing JR here. */ ".set noreorder\n\t" "nop\n\t" - ".global kretprobe_trampoline\n" - "kretprobe_trampoline:\n\t" + ".global __kretprobe_trampoline\n" + "__kretprobe_trampoline:\n\t" "nop\n\t" ".set pop" : : : "memory"); } -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) @@ -476,7 +476,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->regs[31] = (unsigned long)kretprobe_trampoline; + regs->regs[31] = (unsigned long)__kretprobe_trampoline; } /* @@ -496,14 +496,14 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, int __kprobes arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *)kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)__kretprobe_trampoline) return 1; return 0; } static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *)kretprobe_trampoline, + .addr = (kprobe_opcode_t *)__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; diff --git a/arch/parisc/kernel/kprobes.c b/arch/parisc/kernel/kprobes.c index 4a35ac6e2ca2..e2bdb5a5f93e 100644 --- a/arch/parisc/kernel/kprobes.c +++ b/arch/parisc/kernel/kprobes.c @@ -175,7 +175,7 @@ int __kprobes parisc_kprobe_ss_handler(struct pt_regs *regs) return 1; } -void kretprobe_trampoline(void) +void __kretprobe_trampoline(void) { asm volatile("nop"); asm volatile("nop"); @@ -217,6 +217,6 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p) int __init arch_init_kprobes(void) { trampoline_p.addr = (kprobe_opcode_t *) - dereference_function_descriptor(kretprobe_trampoline); + dereference_function_descriptor(__kretprobe_trampoline); return register_kprobe(&trampoline_p); } diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h index 4fc0e15e23a5..bab364152b29 100644 --- a/arch/powerpc/include/asm/kprobes.h +++ b/arch/powerpc/include/asm/kprobes.h @@ -51,7 +51,7 @@ extern kprobe_opcode_t optprobe_template_end[]; #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); extern void arch_remove_kprobe(struct kprobe *p); /* Architecture specific copy of original instruction */ diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c index 43c77142a262..86d77ff056a6 100644 --- a/arch/powerpc/kernel/kprobes.c +++ b/arch/powerpc/kernel/kprobes.c @@ -237,7 +237,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->link = (unsigned long)kretprobe_trampoline; + regs->link = (unsigned long)__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -403,12 +403,12 @@ NOKPROBE_SYMBOL(kprobe_handler); * - When the probed function returns, this probe * causes the handlers to fire */ -asm(".global kretprobe_trampoline\n" - ".type kretprobe_trampoline, @function\n" - "kretprobe_trampoline:\n" +asm(".global __kretprobe_trampoline\n" + ".type __kretprobe_trampoline, @function\n" + "__kretprobe_trampoline:\n" "nop\n" "blr\n" - ".size kretprobe_trampoline, .-kretprobe_trampoline\n"); + ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n"); /* * Called when the probe at kretprobe trampoline is hit @@ -427,7 +427,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) * as it is used to determine the return address from the trap. * For (2), since nip is not honoured with optprobes, we instead setup * the link register properly so that the subsequent 'blr' in - * kretprobe_trampoline jumps back to the right instruction. + * __kretprobe_trampoline jumps back to the right instruction. * * For nip, we should set the address to the previous instruction since * we end up emulating it in kprobe_handler(), which increments the nip @@ -543,7 +543,7 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr) NOKPROBE_SYMBOL(kprobe_fault_handler); static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -554,7 +554,7 @@ int __init arch_init_kprobes(void) int arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) return 1; return 0; diff --git a/arch/powerpc/kernel/optprobes.c b/arch/powerpc/kernel/optprobes.c index 325ba544883c..ce1903064031 100644 --- a/arch/powerpc/kernel/optprobes.c +++ b/arch/powerpc/kernel/optprobes.c @@ -56,7 +56,7 @@ static unsigned long can_optimize(struct kprobe *p) * has a 'nop' instruction, which can be emulated. * So further checks can be skipped. */ - if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) return addr + sizeof(kprobe_opcode_t); /* diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c index 9e4a4a7af380..a2443d61728e 100644 --- a/arch/powerpc/kernel/stacktrace.c +++ b/arch/powerpc/kernel/stacktrace.c @@ -155,7 +155,7 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum * Mark stacktraces with kretprobed functions on them * as unreliable. */ - if (ip == (unsigned long)kretprobe_trampoline) + if (ip == (unsigned long)__kretprobe_trampoline) return -EINVAL; #endif diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h index 9ea9b5ec3113..217ef89f22b9 100644 --- a/arch/riscv/include/asm/kprobes.h +++ b/arch/riscv/include/asm/kprobes.h @@ -40,7 +40,7 @@ void arch_remove_kprobe(struct kprobe *p); int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr); bool kprobe_breakpoint_handler(struct pt_regs *regs); bool kprobe_single_step_handler(struct pt_regs *regs); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); void __kprobes *trampoline_probe_handler(struct pt_regs *regs); #endif /* CONFIG_KPROBES */ diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 62d477cf11da..e6e950b7cf32 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -355,7 +355,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, { ri->ret_addr = (kprobe_opcode_t *)regs->ra; ri->fp = NULL; - regs->ra = (unsigned long) &kretprobe_trampoline; + regs->ra = (unsigned long) &__kretprobe_trampoline; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/riscv/kernel/probes/kprobes_trampoline.S b/arch/riscv/kernel/probes/kprobes_trampoline.S index 6e85d021e2a2..7bdb09ded39b 100644 --- a/arch/riscv/kernel/probes/kprobes_trampoline.S +++ b/arch/riscv/kernel/probes/kprobes_trampoline.S @@ -75,7 +75,7 @@ REG_L x31, PT_T6(sp) .endm -ENTRY(kretprobe_trampoline) +ENTRY(__kretprobe_trampoline) addi sp, sp, -(PT_SIZE_ON_STACK) save_all_base_regs @@ -90,4 +90,4 @@ ENTRY(kretprobe_trampoline) addi sp, sp, PT_SIZE_ON_STACK ret -ENDPROC(kretprobe_trampoline) +ENDPROC(__kretprobe_trampoline) diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h index 09cdb632a490..5eb722c984e4 100644 --- a/arch/s390/include/asm/kprobes.h +++ b/arch/s390/include/asm/kprobes.h @@ -70,7 +70,7 @@ struct kprobe_ctlblk { }; void arch_remove_kprobe(struct kprobe *p); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); int kprobe_fault_handler(struct pt_regs *regs, int trapnr); int kprobe_exceptions_notify(struct notifier_block *self, diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 5fa86e54f129..c505c0ee5f47 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -242,7 +242,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->gprs[14] = (unsigned long) &kretprobe_trampoline; + regs->gprs[14] = (unsigned long) &__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -334,8 +334,8 @@ NOKPROBE_SYMBOL(kprobe_handler); */ static void __used kretprobe_trampoline_holder(void) { - asm volatile(".global kretprobe_trampoline\n" - "kretprobe_trampoline: bcr 0,0\n"); + asm volatile(".global __kretprobe_trampoline\n" + "__kretprobe_trampoline: bcr 0,0\n"); } /* @@ -509,7 +509,7 @@ int kprobe_exceptions_notify(struct notifier_block *self, NOKPROBE_SYMBOL(kprobe_exceptions_notify); static struct kprobe trampoline = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -520,6 +520,6 @@ int __init arch_init_kprobes(void) int arch_trampoline_kprobe(struct kprobe *p) { - return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline; + return p->addr == (kprobe_opcode_t *) &__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_trampoline_kprobe); diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 101477b3e263..b7bb1981e9ee 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -46,7 +46,7 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, * Mark stacktraces with kretprobed functions on them * as unreliable. */ - if (state.ip == (unsigned long)kretprobe_trampoline) + if (state.ip == (unsigned long)__kretprobe_trampoline) return -EINVAL; #endif diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h index 6171682f7798..eeba83e0a7d2 100644 --- a/arch/sh/include/asm/kprobes.h +++ b/arch/sh/include/asm/kprobes.h @@ -26,7 +26,7 @@ typedef insn_size_t kprobe_opcode_t; struct kprobe; void arch_remove_kprobe(struct kprobe *); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c index 8e76a35e6e33..aed1ea8e2c2f 100644 --- a/arch/sh/kernel/kprobes.c +++ b/arch/sh/kernel/kprobes.c @@ -207,7 +207,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, ri->fp = NULL; /* Replace the return addr with trampoline addr */ - regs->pr = (unsigned long)kretprobe_trampoline; + regs->pr = (unsigned long)__kretprobe_trampoline; } static int __kprobes kprobe_handler(struct pt_regs *regs) @@ -293,13 +293,13 @@ no_kprobe: */ static void __used kretprobe_trampoline_holder(void) { - asm volatile (".globl kretprobe_trampoline\n" - "kretprobe_trampoline:\n\t" + asm volatile (".globl __kretprobe_trampoline\n" + "__kretprobe_trampoline:\n\t" "nop\n"); } /* - * Called when we hit the probe point at kretprobe_trampoline + * Called when we hit the probe point at __kretprobe_trampoline */ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs) { @@ -442,7 +442,7 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self, } static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *)&kretprobe_trampoline, + .addr = (kprobe_opcode_t *)&__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h index bfcaa6326c20..06c2bc767ef7 100644 --- a/arch/sparc/include/asm/kprobes.h +++ b/arch/sparc/include/asm/kprobes.h @@ -24,7 +24,7 @@ do { flushi(&(p)->ainsn.insn[0]); \ flushi(&(p)->ainsn.insn[1]); \ } while (0) -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c index 401534236c2e..535c7b35cb59 100644 --- a/arch/sparc/kernel/kprobes.c +++ b/arch/sparc/kernel/kprobes.c @@ -440,7 +440,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, /* Replace the return addr with trampoline addr */ regs->u_regs[UREG_RETPC] = - ((unsigned long)kretprobe_trampoline) - 8; + ((unsigned long)__kretprobe_trampoline) - 8; } /* @@ -465,13 +465,13 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p, static void __used kretprobe_trampoline_holder(void) { - asm volatile(".global kretprobe_trampoline\n" - "kretprobe_trampoline:\n" + asm volatile(".global __kretprobe_trampoline\n" + "__kretprobe_trampoline:\n" "\tnop\n" "\tnop\n"); } static struct kprobe trampoline_p = { - .addr = (kprobe_opcode_t *) &kretprobe_trampoline, + .addr = (kprobe_opcode_t *) &__kretprobe_trampoline, .pre_handler = trampoline_probe_handler }; @@ -482,7 +482,7 @@ int __init arch_init_kprobes(void) int __kprobes arch_trampoline_kprobe(struct kprobe *p) { - if (p->addr == (kprobe_opcode_t *)&kretprobe_trampoline) + if (p->addr == (kprobe_opcode_t *)&__kretprobe_trampoline) return 1; return 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 0c59ef5971de..79cd23dba5b5 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -809,7 +809,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) ri->fp = sara; /* Replace the return addr with trampoline addr */ - *sara = (unsigned long) &kretprobe_trampoline; + *sara = (unsigned long) &__kretprobe_trampoline; } NOKPROBE_SYMBOL(arch_prepare_kretprobe); @@ -1019,9 +1019,9 @@ NOKPROBE_SYMBOL(kprobe_int3_handler); */ asm( ".text\n" - ".global kretprobe_trampoline\n" - ".type kretprobe_trampoline, @function\n" - "kretprobe_trampoline:\n" + ".global __kretprobe_trampoline\n" + ".type __kretprobe_trampoline, @function\n" + "__kretprobe_trampoline:\n" /* We don't bother saving the ss register */ #ifdef CONFIG_X86_64 " pushq %rsp\n" @@ -1045,14 +1045,14 @@ asm( " popfl\n" #endif " ret\n" - ".size kretprobe_trampoline, .-kretprobe_trampoline\n" + ".size __kretprobe_trampoline, .-__kretprobe_trampoline\n" ); -NOKPROBE_SYMBOL(kretprobe_trampoline); -STACK_FRAME_NON_STANDARD(kretprobe_trampoline); +NOKPROBE_SYMBOL(__kretprobe_trampoline); +STACK_FRAME_NON_STANDARD(__kretprobe_trampoline); /* - * Called from kretprobe_trampoline + * Called from __kretprobe_trampoline */ __used __visible void *trampoline_handler(struct pt_regs *regs) { @@ -1061,7 +1061,7 @@ __used __visible void *trampoline_handler(struct pt_regs *regs) #ifdef CONFIG_X86_32 regs->gs = 0; #endif - regs->ip = (unsigned long)&kretprobe_trampoline; + regs->ip = (unsigned long)&__kretprobe_trampoline; regs->orig_ax = ~0UL; return (void *)kretprobe_trampoline_handler(regs, ®s->sp); diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 96f5df93e36e..b6b2370f4a4c 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -188,14 +188,14 @@ extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); extern int arch_trampoline_kprobe(struct kprobe *p); -void kretprobe_trampoline(void); +void __kretprobe_trampoline(void); /* * Since some architecture uses structured function pointer, * use dereference_function_descriptor() to get real function address. */ static nokprobe_inline void *kretprobe_trampoline_addr(void) { - return dereference_kernel_function_descriptor(kretprobe_trampoline); + return dereference_kernel_function_descriptor(__kretprobe_trampoline); } /* If the trampoline handler called from a kprobe, use this version */ diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index c2ca40e8595b..5a5949c659d0 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -349,7 +349,7 @@ EXPORT_SYMBOL_GPL(trace_output_call); #ifdef CONFIG_KRETPROBES static inline const char *kretprobed(const char *name) { - static const char tramp_name[] = "kretprobe_trampoline"; + static const char tramp_name[] = "__kretprobe_trampoline"; int size = sizeof(tramp_name); if (strncmp(tramp_name, name, size) == 0) -- cgit v1.2.3 From 03bac0df2886882c43e6d0bfff9dee84a184fc7e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:41:04 +0900 Subject: kprobes: Add kretprobe_find_ret_addr() for searching return address Introduce kretprobe_find_ret_addr() and is_kretprobe_trampoline(). These APIs will be used by the ORC stack unwinder and ftrace, so that they can check whether the given address points kretprobe trampoline code and query the correct return address in that case. Link: https://lkml.kernel.org/r/163163046461.489837.1044778356430293962.stgit@devnote2 Signed-off-by: Masami Hiramatsu Tested-by: Andrii Nakryiko Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 22 ++++++++++ kernel/kprobes.c | 109 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 105 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index b6b2370f4a4c..6d47a9da1e0a 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -505,6 +505,28 @@ static inline bool is_kprobe_optinsn_slot(unsigned long addr) } #endif /* !CONFIG_OPTPROBES */ +#ifdef CONFIG_KRETPROBES +static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) +{ + return (void *)addr == kretprobe_trampoline_addr(); +} + +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur); +#else +static nokprobe_inline bool is_kretprobe_trampoline(unsigned long addr) +{ + return false; +} + +static nokprobe_inline +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur) +{ + return 0; +} +#endif + /* Returns true if kprobes handled the fault */ static nokprobe_inline bool kprobe_page_fault(struct pt_regs *regs, unsigned int trap) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 6ed755111eea..833f07f33115 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1863,45 +1863,87 @@ static struct notifier_block kprobe_exceptions_nb = { #ifdef CONFIG_KRETPROBES -unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, - void *frame_pointer) +/* This assumes the 'tsk' is the current task or the is not running. */ +static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk, + struct llist_node **cur) { - kprobe_opcode_t *correct_ret_addr = NULL; struct kretprobe_instance *ri = NULL; - struct llist_node *first, *node; - struct kretprobe *rp; + struct llist_node *node = *cur; + + if (!node) + node = tsk->kretprobe_instances.first; + else + node = node->next; - /* Find all nodes for this frame. */ - first = node = current->kretprobe_instances.first; while (node) { ri = container_of(node, struct kretprobe_instance, llist); - - BUG_ON(ri->fp != frame_pointer); - if (ri->ret_addr != kretprobe_trampoline_addr()) { - correct_ret_addr = ri->ret_addr; - /* - * This is the real return address. Any other - * instances associated with this task are for - * other calls deeper on the call stack - */ - goto found; + *cur = node; + return ri->ret_addr; } - node = node->next; } - pr_err("kretprobe: Return address not found, not execute handler. Maybe there is a bug in the kernel.\n"); - BUG_ON(1); + return NULL; +} +NOKPROBE_SYMBOL(__kretprobe_find_ret_addr); -found: - /* Unlink all nodes for this frame. */ - current->kretprobe_instances.first = node->next; - node->next = NULL; +/** + * kretprobe_find_ret_addr -- Find correct return address modified by kretprobe + * @tsk: Target task + * @fp: A frame pointer + * @cur: a storage of the loop cursor llist_node pointer for next call + * + * Find the correct return address modified by a kretprobe on @tsk in unsigned + * long type. If it finds the return address, this returns that address value, + * or this returns 0. + * The @tsk must be 'current' or a task which is not running. @fp is a hint + * to get the currect return address - which is compared with the + * kretprobe_instance::fp field. The @cur is a loop cursor for searching the + * kretprobe return addresses on the @tsk. The '*@cur' should be NULL at the + * first call, but '@cur' itself must NOT NULL. + */ +unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, + struct llist_node **cur) +{ + struct kretprobe_instance *ri = NULL; + kprobe_opcode_t *ret; + + if (WARN_ON_ONCE(!cur)) + return 0; + + do { + ret = __kretprobe_find_ret_addr(tsk, cur); + if (!ret) + break; + ri = container_of(*cur, struct kretprobe_instance, llist); + } while (ri->fp != fp); - /* Run them.. */ + return (unsigned long)ret; +} +NOKPROBE_SYMBOL(kretprobe_find_ret_addr); + +unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, + void *frame_pointer) +{ + kprobe_opcode_t *correct_ret_addr = NULL; + struct kretprobe_instance *ri = NULL; + struct llist_node *first, *node = NULL; + struct kretprobe *rp; + + /* Find correct address and all nodes for this frame. */ + correct_ret_addr = __kretprobe_find_ret_addr(current, &node); + if (!correct_ret_addr) { + pr_err("kretprobe: Return address not found, not execute handler. Maybe there is a bug in the kernel.\n"); + BUG_ON(1); + } + + /* Run the user handler of the nodes. */ + first = current->kretprobe_instances.first; while (first) { ri = container_of(first, struct kretprobe_instance, llist); - first = first->next; + + if (WARN_ON_ONCE(ri->fp != frame_pointer)) + break; rp = get_kretprobe(ri); if (rp && rp->handler) { @@ -1912,6 +1954,21 @@ found: rp->handler(ri, regs); __this_cpu_write(current_kprobe, prev); } + if (first == node) + break; + + first = first->next; + } + + /* Unlink all nodes for this frame. */ + first = current->kretprobe_instances.first; + current->kretprobe_instances.first = node->next; + node->next = NULL; + + /* Recycle free instances. */ + while (first) { + ri = container_of(first, struct kretprobe_instance, llist); + first = first->next; recycle_rp_inst(ri); } -- cgit v1.2.3 From e028c4f7ac7ca8c96126fe46c54ab3d56ffe6a66 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 14 Sep 2021 23:41:13 +0900 Subject: objtool: Add frame-pointer-specific function ignore Add a CONFIG_FRAME_POINTER-specific version of STACK_FRAME_NON_STANDARD() for the case where a function is intentionally missing frame pointer setup, but otherwise needs objtool/ORC coverage when frame pointers are disabled. Link: https://lkml.kernel.org/r/163163047364.489837.17377799909553689661.stgit@devnote2 Signed-off-by: Josh Poimboeuf Reviewed-by: Masami Hiramatsu Tested-by: Masami Hiramatsu Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/objtool.h | 12 ++++++++++++ tools/include/linux/objtool.h | 12 ++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 7e72d975cb76..aca52db2f3f3 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -66,6 +66,17 @@ struct unwind_hint { static void __used __section(".discard.func_stack_frame_non_standard") \ *__func_stack_frame_non_standard_##func = func +/* + * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore + * for the case where a function is intentionally missing frame pointer setup, + * but otherwise needs objtool/ORC coverage when frame pointers are disabled. + */ +#ifdef CONFIG_FRAME_POINTER +#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func) +#else +#define STACK_FRAME_NON_STANDARD_FP(func) +#endif + #else /* __ASSEMBLY__ */ /* @@ -127,6 +138,7 @@ struct unwind_hint { #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "\n\t" #define STACK_FRAME_NON_STANDARD(func) +#define STACK_FRAME_NON_STANDARD_FP(func) #else #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h index 7e72d975cb76..aca52db2f3f3 100644 --- a/tools/include/linux/objtool.h +++ b/tools/include/linux/objtool.h @@ -66,6 +66,17 @@ struct unwind_hint { static void __used __section(".discard.func_stack_frame_non_standard") \ *__func_stack_frame_non_standard_##func = func +/* + * STACK_FRAME_NON_STANDARD_FP() is a frame-pointer-specific function ignore + * for the case where a function is intentionally missing frame pointer setup, + * but otherwise needs objtool/ORC coverage when frame pointers are disabled. + */ +#ifdef CONFIG_FRAME_POINTER +#define STACK_FRAME_NON_STANDARD_FP(func) STACK_FRAME_NON_STANDARD(func) +#else +#define STACK_FRAME_NON_STANDARD_FP(func) +#endif + #else /* __ASSEMBLY__ */ /* @@ -127,6 +138,7 @@ struct unwind_hint { #define UNWIND_HINT(sp_reg, sp_offset, type, end) \ "\n\t" #define STACK_FRAME_NON_STANDARD(func) +#define STACK_FRAME_NON_STANDARD_FP(func) #else #define ANNOTATE_INTRA_FUNCTION_CALL .macro UNWIND_HINT sp_reg:req sp_offset=0 type:req end=0 -- cgit v1.2.3 From bf094cffea2a6503ce84062f9f0243bef77c58f9 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Tue, 14 Sep 2021 23:42:51 +0900 Subject: x86/kprobes: Fixup return address in generic trampoline handler In x86, the fake return address on the stack saved by __kretprobe_trampoline() will be replaced with the real return address after returning from trampoline_handler(). Before fixing the return address, the real return address can be found in the 'current->kretprobe_instances'. However, since there is a window between updating the 'current->kretprobe_instances' and fixing the address on the stack, if an interrupt happens at that timing and the interrupt handler does stacktrace, it may fail to unwind because it can not get the correct return address from 'current->kretprobe_instances'. This will eliminate that window by fixing the return address right before updating 'current->kretprobe_instances'. Link: https://lkml.kernel.org/r/163163057094.489837.9044470370440745866.stgit@devnote2 Signed-off-by: Masami Hiramatsu Tested-by: Andrii Nakryiko Signed-off-by: Steven Rostedt (VMware) --- arch/x86/kernel/kprobes/core.c | 18 ++++++++++++++++-- include/linux/kprobes.h | 3 +++ kernel/kprobes.c | 11 +++++++++++ 3 files changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 7e1111c19605..fce99e249d61 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -1065,6 +1065,16 @@ NOKPROBE_SYMBOL(__kretprobe_trampoline); */ STACK_FRAME_NON_STANDARD_FP(__kretprobe_trampoline); +/* This is called from kretprobe_trampoline_handler(). */ +void arch_kretprobe_fixup_return(struct pt_regs *regs, + kprobe_opcode_t *correct_ret_addr) +{ + unsigned long *frame_pointer = ®s->sp + 1; + + /* Replace fake return address with real one. */ + *frame_pointer = (unsigned long)correct_ret_addr; +} + /* * Called from __kretprobe_trampoline */ @@ -1082,8 +1092,12 @@ __used __visible void trampoline_handler(struct pt_regs *regs) regs->sp += sizeof(long); frame_pointer = ®s->sp + 1; - /* Replace fake return address with real one. */ - *frame_pointer = kretprobe_trampoline_handler(regs, frame_pointer); + /* + * The return address at 'frame_pointer' is recovered by the + * arch_kretprobe_fixup_return() which called from the + * kretprobe_trampoline_handler(). + */ + kretprobe_trampoline_handler(regs, frame_pointer); /* * Copy FLAGS to 'pt_regs::sp' so that __kretprobe_trapmoline() diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 6d47a9da1e0a..e974caf39d3e 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -188,6 +188,9 @@ extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs); extern int arch_trampoline_kprobe(struct kprobe *p); +void arch_kretprobe_fixup_return(struct pt_regs *regs, + kprobe_opcode_t *correct_ret_addr); + void __kretprobe_trampoline(void); /* * Since some architecture uses structured function pointer, diff --git a/kernel/kprobes.c b/kernel/kprobes.c index ebc587b9a346..b62af9fc3607 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1922,6 +1922,15 @@ unsigned long kretprobe_find_ret_addr(struct task_struct *tsk, void *fp, } NOKPROBE_SYMBOL(kretprobe_find_ret_addr); +void __weak arch_kretprobe_fixup_return(struct pt_regs *regs, + kprobe_opcode_t *correct_ret_addr) +{ + /* + * Do nothing by default. Please fill this to update the fake return + * address on the stack with the correct one on each arch if possible. + */ +} + unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, void *frame_pointer) { @@ -1967,6 +1976,8 @@ unsigned long __kretprobe_trampoline_handler(struct pt_regs *regs, first = first->next; } + arch_kretprobe_fixup_return(regs, correct_ret_addr); + /* Unlink all nodes for this frame. */ first = current->kretprobe_instances.first; current->kretprobe_instances.first = node->next; -- cgit v1.2.3 From 6b51b02a3a0ac49dfe302818d0746a799545e4e9 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 15 Jun 2021 13:12:33 +0200 Subject: dma-buf: fix and rework dma_buf_poll v7 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Daniel pointed me towards this function and there are multiple obvious problems in the implementation. First of all the retry loop is not working as intended. In general the retry makes only sense if you grab the reference first and then check the sequence values. Then we should always also wait for the exclusive fence. It's also good practice to keep the reference around when installing callbacks to fences you don't own. And last the whole implementation was unnecessary complex and rather hard to understand which could lead to probably unexpected behavior of the IOCTL. Fix all this by reworking the implementation from scratch. Dropping the whole RCU approach and taking the lock instead. Only mildly tested and needs a thoughtful review of the code. Pushing through drm-misc-next to avoid merge conflicts and give the code another round of testing. v2: fix the reference counting as well v3: keep the excl fence handling as is for stable v4: back to testing all fences, drop RCU v5: handle in and out separately v6: add missing clear of events v7: change coding style as suggested by Michel, drop unused variables Signed-off-by: Christian König Reviewed-by: Daniel Vetter Tested-by: Michel Dänzer CC: stable@vger.kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20210720131110.88512-1-christian.koenig@amd.com --- drivers/dma-buf/dma-buf.c | 152 +++++++++++++++++++++------------------------- include/linux/dma-buf.h | 2 +- 2 files changed, 71 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 474de2d988ca..61e20ae7b08b 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -74,7 +74,7 @@ static void dma_buf_release(struct dentry *dentry) * If you hit this BUG() it means someone dropped their ref to the * dma-buf while still having pending operation to the buffer. */ - BUG_ON(dmabuf->cb_shared.active || dmabuf->cb_excl.active); + BUG_ON(dmabuf->cb_in.active || dmabuf->cb_out.active); dma_buf_stats_teardown(dmabuf); dmabuf->ops->release(dmabuf); @@ -206,16 +206,55 @@ static void dma_buf_poll_cb(struct dma_fence *fence, struct dma_fence_cb *cb) wake_up_locked_poll(dcb->poll, dcb->active); dcb->active = 0; spin_unlock_irqrestore(&dcb->poll->lock, flags); + dma_fence_put(fence); +} + +static bool dma_buf_poll_shared(struct dma_resv *resv, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_resv_list *fobj = dma_resv_shared_list(resv); + struct dma_fence *fence; + int i, r; + + if (!fobj) + return false; + + for (i = 0; i < fobj->shared_count; ++i) { + fence = rcu_dereference_protected(fobj->shared[i], + dma_resv_held(resv)); + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + } + + return false; +} + +static bool dma_buf_poll_excl(struct dma_resv *resv, + struct dma_buf_poll_cb_t *dcb) +{ + struct dma_fence *fence = dma_resv_excl_fence(resv); + int r; + + if (!fence) + return false; + + dma_fence_get(fence); + r = dma_fence_add_callback(fence, &dcb->cb, dma_buf_poll_cb); + if (!r) + return true; + dma_fence_put(fence); + + return false; } static __poll_t dma_buf_poll(struct file *file, poll_table *poll) { struct dma_buf *dmabuf; struct dma_resv *resv; - struct dma_resv_list *fobj; - struct dma_fence *fence_excl; __poll_t events; - unsigned shared_count, seq; dmabuf = file->private_data; if (!dmabuf || !dmabuf->resv) @@ -229,101 +268,50 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll) if (!events) return 0; -retry: - seq = read_seqcount_begin(&resv->seq); - rcu_read_lock(); - - fobj = rcu_dereference(resv->fence); - if (fobj) - shared_count = fobj->shared_count; - else - shared_count = 0; - fence_excl = dma_resv_excl_fence(resv); - if (read_seqcount_retry(&resv->seq, seq)) { - rcu_read_unlock(); - goto retry; - } - - if (fence_excl && (!(events & EPOLLOUT) || shared_count == 0)) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_excl; - __poll_t pevents = EPOLLIN; + dma_resv_lock(resv, NULL); - if (shared_count == 0) - pevents |= EPOLLOUT; + if (events & EPOLLOUT) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_out; + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); - if (dcb->active) { - dcb->active |= pevents; - events &= ~pevents; - } else - dcb->active = pevents; + if (dcb->active) + events &= ~EPOLLOUT; + else + dcb->active = EPOLLOUT; spin_unlock_irq(&dmabuf->poll.lock); - if (events & pevents) { - if (!dma_fence_get_rcu(fence_excl)) { - /* force a recheck */ - events &= ~pevents; - dma_buf_poll_cb(NULL, &dcb->cb); - } else if (!dma_fence_add_callback(fence_excl, &dcb->cb, - dma_buf_poll_cb)) { - events &= ~pevents; - dma_fence_put(fence_excl); - } else { - /* - * No callback queued, wake up any additional - * waiters. - */ - dma_fence_put(fence_excl); + if (events & EPOLLOUT) { + if (!dma_buf_poll_shared(resv, dcb) && + !dma_buf_poll_excl(resv, dcb)) + /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); - } + else + events &= ~EPOLLOUT; } } - if ((events & EPOLLOUT) && shared_count > 0) { - struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_shared; - int i; + if (events & EPOLLIN) { + struct dma_buf_poll_cb_t *dcb = &dmabuf->cb_in; - /* Only queue a new callback if no event has fired yet */ + /* Check that callback isn't busy */ spin_lock_irq(&dmabuf->poll.lock); if (dcb->active) - events &= ~EPOLLOUT; + events &= ~EPOLLIN; else - dcb->active = EPOLLOUT; + dcb->active = EPOLLIN; spin_unlock_irq(&dmabuf->poll.lock); - if (!(events & EPOLLOUT)) - goto out; - - for (i = 0; i < shared_count; ++i) { - struct dma_fence *fence = rcu_dereference(fobj->shared[i]); - - if (!dma_fence_get_rcu(fence)) { - /* - * fence refcount dropped to zero, this means - * that fobj has been freed - * - * call dma_buf_poll_cb and force a recheck! - */ - events &= ~EPOLLOUT; + if (events & EPOLLIN) { + if (!dma_buf_poll_excl(resv, dcb)) + /* No callback queued, wake up any other waiters */ dma_buf_poll_cb(NULL, &dcb->cb); - break; - } - if (!dma_fence_add_callback(fence, &dcb->cb, - dma_buf_poll_cb)) { - dma_fence_put(fence); - events &= ~EPOLLOUT; - break; - } - dma_fence_put(fence); + else + events &= ~EPOLLIN; } - - /* No callback queued, wake up any additional waiters. */ - if (i == shared_count) - dma_buf_poll_cb(NULL, &dcb->cb); } -out: - rcu_read_unlock(); + dma_resv_unlock(resv); return events; } @@ -566,8 +554,8 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info) dmabuf->owner = exp_info->owner; spin_lock_init(&dmabuf->name_lock); init_waitqueue_head(&dmabuf->poll); - dmabuf->cb_excl.poll = dmabuf->cb_shared.poll = &dmabuf->poll; - dmabuf->cb_excl.active = dmabuf->cb_shared.active = 0; + dmabuf->cb_in.poll = dmabuf->cb_out.poll = &dmabuf->poll; + dmabuf->cb_in.active = dmabuf->cb_out.active = 0; if (!resv) { resv = (struct dma_resv *)&dmabuf[1]; diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 66470c37e471..02c2eb874da6 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -440,7 +440,7 @@ struct dma_buf { wait_queue_head_t *poll; __poll_t active; - } cb_excl, cb_shared; + } cb_in, cb_out; #ifdef CONFIG_DMABUF_SYSFS_STATS /** * @sysfs_entry: -- cgit v1.2.3 From 78b497f2e62d8c7514de5f83c80837bbb120e93e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 3 Sep 2021 15:08:05 +0200 Subject: kvm: use kvfree() in kvm_arch_free_vm() By switching from kfree() to kvfree() in kvm_arch_free_vm() Arm64 can use the common variant. This can be accomplished by adding another macro __KVM_HAVE_ARCH_VM_FREE, which will be used only by x86 for now. Further simplification can be achieved by adding __kvm_arch_free_vm() doing the common part. Suggested-by: Paolo Bonzini Signed-off-by: Juergen Gross Message-Id: <20210903130808.30142-5-jgross@suse.com> Signed-off-by: Paolo Bonzini --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/kvm/arm.c | 8 -------- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 9 ++++++++- 5 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f8be56d5342b..369c30e28301 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -771,7 +771,6 @@ int kvm_set_ipa_limit(void); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); -void kvm_arch_free_vm(struct kvm *kvm); int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fe102cd2e518..7838e9fb693e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -297,14 +297,6 @@ struct kvm *kvm_arch_alloc_vm(void) return vzalloc(sizeof(struct kvm)); } -void kvm_arch_free_vm(struct kvm *kvm) -{ - if (!has_vhe()) - kfree(kvm); - else - vfree(kvm); -} - int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 8470d4673068..1b280292bdff 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1540,6 +1540,8 @@ static inline struct kvm *kvm_arch_alloc_vm(void) { return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); } + +#define __KVM_HAVE_ARCH_VM_FREE void kvm_arch_free_vm(struct kvm *kvm); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 79535fe83a04..03091a2e0822 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11130,7 +11130,7 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_free_vm(struct kvm *kvm) { kfree(to_kvm_hv(kvm)->hv_pa_pg); - vfree(kvm); + __kvm_arch_free_vm(kvm); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3f87d6ad20bf..60a35d9fe259 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1081,10 +1081,17 @@ static inline struct kvm *kvm_arch_alloc_vm(void) { return kzalloc(sizeof(struct kvm), GFP_KERNEL); } +#endif + +static inline void __kvm_arch_free_vm(struct kvm *kvm) +{ + kvfree(kvm); +} +#ifndef __KVM_HAVE_ARCH_VM_FREE static inline void kvm_arch_free_vm(struct kvm *kvm) { - kfree(kvm); + __kvm_arch_free_vm(kvm); } #endif -- cgit v1.2.3 From 874f670e6088d3bff3972ecd44c1cb00610f9183 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:35 +0200 Subject: sched: Clean up the might_sleep() underscore zoo __might_sleep() vs. ___might_sleep() is hard to distinguish. Aside of that the three underscore variant is exposed to provide a checkpoint for rescheduling points which are distinct from blocking points. They are semantically a preemption point which means that scheduling is state preserving. A real blocking operation, e.g. mutex_lock(), wait*(), which cannot preserve a task state which is not equal to RUNNING. While technically blocking on a "sleeping" spinlock in RT enabled kernels falls into the voluntary scheduling category because it has to wait until the contended spin/rw lock becomes available, the RT lock substitution code can semantically be mapped to a voluntary preemption because the RT lock substitution code and the scheduler are providing mechanisms to preserve the task state and to take regular non-lock related wakeups into account. Rename ___might_sleep() to __might_resched() to make the distinction of these functions clear. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165357.928693482@linutronix.de --- include/linux/kernel.h | 6 +++--- include/linux/sched.h | 8 ++++---- kernel/locking/spinlock_rt.c | 6 +++--- kernel/sched/core.c | 6 +++--- 4 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..5e4ae54da73e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -111,7 +111,7 @@ static __always_inline void might_resched(void) #endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -extern void ___might_sleep(const char *file, int line, int preempt_offset); +extern void __might_resched(const char *file, int line, int preempt_offset); extern void __might_sleep(const char *file, int line, int preempt_offset); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); @@ -168,8 +168,8 @@ extern void __cant_migrate(const char *file, int line); */ # define non_block_end() WARN_ON(current->non_block_count-- == 0) #else - static inline void ___might_sleep(const char *file, int line, - int preempt_offset) { } + static inline void __might_resched(const char *file, int line, + int preempt_offset) { } static inline void __might_sleep(const char *file, int line, int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index e12b524426b0..b38f002334d5 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2038,7 +2038,7 @@ static inline int _cond_resched(void) { return 0; } #endif /* !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) */ #define cond_resched() ({ \ - ___might_sleep(__FILE__, __LINE__, 0); \ + __might_resched(__FILE__, __LINE__, 0); \ _cond_resched(); \ }) @@ -2046,9 +2046,9 @@ extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); -#define cond_resched_lock(lock) ({ \ - ___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\ - __cond_resched_lock(lock); \ +#define cond_resched_lock(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_lock(lock); \ }) #define cond_resched_rwlock_read(lock) ({ \ diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index d2912e44d61f..c5289240cfb4 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -32,7 +32,7 @@ static __always_inline void rtlock_lock(struct rt_mutex_base *rtm) static __always_inline void __rt_spin_lock(spinlock_t *lock) { - ___might_sleep(__FILE__, __LINE__, 0); + __might_resched(__FILE__, __LINE__, 0); rtlock_lock(&lock->lock); rcu_read_lock(); migrate_disable(); @@ -210,7 +210,7 @@ EXPORT_SYMBOL(rt_write_trylock); void __sched rt_read_lock(rwlock_t *rwlock) { - ___might_sleep(__FILE__, __LINE__, 0); + __might_resched(__FILE__, __LINE__, 0); rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); rwbase_read_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); rcu_read_lock(); @@ -220,7 +220,7 @@ EXPORT_SYMBOL(rt_read_lock); void __sched rt_write_lock(rwlock_t *rwlock) { - ___might_sleep(__FILE__, __LINE__, 0); + __might_resched(__FILE__, __LINE__, 0); rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); rcu_read_lock(); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1bba4128a3e6..c3943aa2f60c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9489,11 +9489,11 @@ void __might_sleep(const char *file, int line, int preempt_offset) (void *)current->task_state_change, (void *)current->task_state_change); - ___might_sleep(file, line, preempt_offset); + __might_resched(file, line, preempt_offset); } EXPORT_SYMBOL(__might_sleep); -void ___might_sleep(const char *file, int line, int preempt_offset) +void __might_resched(const char *file, int line, int preempt_offset) { /* Ratelimiting timestamp: */ static unsigned long prev_jiffy; @@ -9538,7 +9538,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset) dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } -EXPORT_SYMBOL(___might_sleep); +EXPORT_SYMBOL(__might_resched); void __cant_sleep(const char *file, int line, int preempt_offset) { -- cgit v1.2.3 From 7b5ff4bb9adc53cfbf7ac9ba7820ccf0cd7c070a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:37 +0200 Subject: sched: Make cond_resched_*lock() variants consistent vs. might_sleep() Commit 3427445afd26 ("sched: Exclude cond_resched() from nested sleep test") removed the task state check of __might_sleep() for cond_resched_lock() because cond_resched_lock() is not a voluntary scheduling point which blocks. It's a preemption point which requires the lock holder to release the spin lock. The same rationale applies to cond_resched_rwlock_read/write(), but those were not touched. Make it consistent and use the non-state checking __might_resched() there as well. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165357.991262778@linutronix.de --- include/linux/sched.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index b38f002334d5..7a989f2487f8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2051,14 +2051,14 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); __cond_resched_lock(lock); \ }) -#define cond_resched_rwlock_read(lock) ({ \ - __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_rwlock_read(lock); \ +#define cond_resched_rwlock_read(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_rwlock_read(lock); \ }) -#define cond_resched_rwlock_write(lock) ({ \ - __might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_rwlock_write(lock); \ +#define cond_resched_rwlock_write(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ + __cond_resched_rwlock_write(lock); \ }) static inline void cond_resched_rcu(void) -- cgit v1.2.3 From 42a387566c567603bafa1ec0c5b71c35cba83e86 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:38 +0200 Subject: sched: Remove preempt_offset argument from __might_sleep() All callers hand in 0 and never will hand in anything else. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165358.054321586@linutronix.de --- include/linux/kernel.h | 7 +++---- kernel/sched/core.c | 4 ++-- mm/memory.c | 2 +- 3 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 5e4ae54da73e..f95ee786e4ef 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -112,7 +112,7 @@ static __always_inline void might_resched(void) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP extern void __might_resched(const char *file, int line, int preempt_offset); -extern void __might_sleep(const char *file, int line, int preempt_offset); +extern void __might_sleep(const char *file, int line); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); @@ -129,7 +129,7 @@ extern void __cant_migrate(const char *file, int line); * supposed to. */ # define might_sleep() \ - do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + do { __might_sleep(__FILE__, __LINE__); might_resched(); } while (0) /** * cant_sleep - annotation for functions that cannot sleep * @@ -170,8 +170,7 @@ extern void __cant_migrate(const char *file, int line); #else static inline void __might_resched(const char *file, int line, int preempt_offset) { } - static inline void __might_sleep(const char *file, int line, - int preempt_offset) { } +static inline void __might_sleep(const char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) # define cant_migrate() do { } while (0) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index c3943aa2f60c..2d790df62ec9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9475,7 +9475,7 @@ static inline int preempt_count_equals(int preempt_offset) return (nested == preempt_offset); } -void __might_sleep(const char *file, int line, int preempt_offset) +void __might_sleep(const char *file, int line) { unsigned int state = get_current_state(); /* @@ -9489,7 +9489,7 @@ void __might_sleep(const char *file, int line, int preempt_offset) (void *)current->task_state_change, (void *)current->task_state_change); - __might_resched(file, line, preempt_offset); + __might_resched(file, line, 0); } EXPORT_SYMBOL(__might_sleep); diff --git a/mm/memory.c b/mm/memory.c index 25fc46e87214..1cd1792c00f2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -5255,7 +5255,7 @@ void __might_fault(const char *file, int line) return; if (pagefault_disabled()) return; - __might_sleep(file, line, 0); + __might_sleep(file, line); #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) if (current->mm) might_lock_read(¤t->mm->mmap_lock); -- cgit v1.2.3 From 50e081b96e35e43b65591f40f7376204decd1cb5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:43 +0200 Subject: sched: Make RCU nest depth distinct in __might_resched() For !RT kernels RCU nest depth in __might_resched() is always expected to be 0, but on RT kernels it can be non zero while the preempt count is expected to be always 0. Instead of playing magic games in interpreting the 'preempt_offset' argument, rename it to 'offsets' and use the lower 8 bits for the expected preempt count, allow to hand in the expected RCU nest depth in the upper bits and adopt the __might_resched() code and related checks and printks. The affected call sites are updated in subsequent steps. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165358.243232823@linutronix.de --- include/linux/kernel.h | 4 ++-- include/linux/sched.h | 3 +++ kernel/sched/core.c | 28 ++++++++++++++++------------ 3 files changed, 21 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index f95ee786e4ef..e8696e4a45aa 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -111,7 +111,7 @@ static __always_inline void might_resched(void) #endif /* CONFIG_PREEMPT_* */ #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -extern void __might_resched(const char *file, int line, int preempt_offset); +extern void __might_resched(const char *file, int line, unsigned int offsets); extern void __might_sleep(const char *file, int line); extern void __cant_sleep(const char *file, int line, int preempt_offset); extern void __cant_migrate(const char *file, int line); @@ -169,7 +169,7 @@ extern void __cant_migrate(const char *file, int line); # define non_block_end() WARN_ON(current->non_block_count-- == 0) #else static inline void __might_resched(const char *file, int line, - int preempt_offset) { } + unsigned int offsets) { } static inline void __might_sleep(const char *file, int line) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) diff --git a/include/linux/sched.h b/include/linux/sched.h index 7a989f2487f8..b448c7460577 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2046,6 +2046,9 @@ extern int __cond_resched_lock(spinlock_t *lock); extern int __cond_resched_rwlock_read(rwlock_t *lock); extern int __cond_resched_rwlock_write(rwlock_t *lock); +#define MIGHT_RESCHED_RCU_SHIFT 8 +#define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) + #define cond_resched_lock(lock) ({ \ __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ __cond_resched_lock(lock); \ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0a27cb8f72a9..8d3fa0768e5b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9468,12 +9468,6 @@ void __init sched_init(void) } #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -static inline int preempt_count_equals(int preempt_offset) -{ - int nested = preempt_count() + rcu_preempt_depth(); - - return (nested == preempt_offset); -} void __might_sleep(const char *file, int line) { @@ -9505,7 +9499,16 @@ static void print_preempt_disable_ip(int preempt_offset, unsigned long ip) print_ip_sym(KERN_ERR, ip); } -void __might_resched(const char *file, int line, int preempt_offset) +static inline bool resched_offsets_ok(unsigned int offsets) +{ + unsigned int nested = preempt_count(); + + nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT; + + return nested == offsets; +} + +void __might_resched(const char *file, int line, unsigned int offsets) { /* Ratelimiting timestamp: */ static unsigned long prev_jiffy; @@ -9515,7 +9518,7 @@ void __might_resched(const char *file, int line, int preempt_offset) /* WARN_ON_ONCE() by default, no rate limit required: */ rcu_sleep_check(); - if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + if ((resched_offsets_ok(offsets) && !irqs_disabled() && !is_idle_task(current) && !current->non_block_count) || system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || oops_in_progress) @@ -9534,11 +9537,11 @@ void __might_resched(const char *file, int line, int preempt_offset) in_atomic(), irqs_disabled(), current->non_block_count, current->pid, current->comm); pr_err("preempt_count: %x, expected: %x\n", preempt_count(), - preempt_offset); + offsets & MIGHT_RESCHED_PREEMPT_MASK); if (IS_ENABLED(CONFIG_PREEMPT_RCU)) { - pr_err("RCU nest depth: %d, expected: 0\n", - rcu_preempt_depth()); + pr_err("RCU nest depth: %d, expected: %u\n", + rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT); } if (task_stack_end_corrupted(current)) @@ -9548,7 +9551,8 @@ void __might_resched(const char *file, int line, int preempt_offset) if (irqs_disabled()) print_irqtrace_events(current); - print_preempt_disable_ip(preempt_offset, preempt_disable_ip); + print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK, + preempt_disable_ip); dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); -- cgit v1.2.3 From 3e9cc688e56cc2abb9b6067f57c8397f6c96d42c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 23 Sep 2021 18:54:44 +0200 Subject: sched: Make cond_resched_lock() variants RT aware The __might_resched() checks in the cond_resched_lock() variants use PREEMPT_LOCK_OFFSET for preempt count offset checking which takes the preemption disable by the spin_lock() which is still held at that point into account. On PREEMPT_RT enabled kernels spin/rw_lock held sections stay preemptible which means PREEMPT_LOCK_OFFSET is 0, but that still triggers the __might_resched() check because that takes RCU read side nesting into account. On RT enabled kernels spin/read/write_lock() issue rcu_read_lock() to resemble the !RT semantics, which means in cond_resched_lock() the might resched check will see preempt_count() == 0 and rcu_preempt_depth() == 1. Introduce PREEMPT_LOCK_SCHED_OFFSET for those might resched checks and map them depending on CONFIG_PREEMPT_RT. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210923165358.305969211@linutronix.de --- include/linux/preempt.h | 5 +++-- include/linux/sched.h | 34 +++++++++++++++++++++++++--------- 2 files changed, 28 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 4d244e295e85..031898b38d06 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -122,9 +122,10 @@ * The preempt_count offset after spin_lock() */ #if !defined(CONFIG_PREEMPT_RT) -#define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET +#define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET #else -#define PREEMPT_LOCK_OFFSET 0 +/* Locks on RT do not disable preemption */ +#define PREEMPT_LOCK_OFFSET 0 #endif /* diff --git a/include/linux/sched.h b/include/linux/sched.h index b448c7460577..21b7cd00bf1d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2049,19 +2049,35 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock); #define MIGHT_RESCHED_RCU_SHIFT 8 #define MIGHT_RESCHED_PREEMPT_MASK ((1U << MIGHT_RESCHED_RCU_SHIFT) - 1) -#define cond_resched_lock(lock) ({ \ - __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_lock(lock); \ +#ifndef CONFIG_PREEMPT_RT +/* + * Non RT kernels have an elevated preempt count due to the held lock, + * but are not allowed to be inside a RCU read side critical section + */ +# define PREEMPT_LOCK_RESCHED_OFFSETS PREEMPT_LOCK_OFFSET +#else +/* + * spin/rw_lock() on RT implies rcu_read_lock(). The might_sleep() check in + * cond_resched*lock() has to take that into account because it checks for + * preempt_count() and rcu_preempt_depth(). + */ +# define PREEMPT_LOCK_RESCHED_OFFSETS \ + (PREEMPT_LOCK_OFFSET + (1U << MIGHT_RESCHED_RCU_SHIFT)) +#endif + +#define cond_resched_lock(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ + __cond_resched_lock(lock); \ }) -#define cond_resched_rwlock_read(lock) ({ \ - __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_rwlock_read(lock); \ +#define cond_resched_rwlock_read(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ + __cond_resched_rwlock_read(lock); \ }) -#define cond_resched_rwlock_write(lock) ({ \ - __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET); \ - __cond_resched_rwlock_write(lock); \ +#define cond_resched_rwlock_write(lock) ({ \ + __might_resched(__FILE__, __LINE__, PREEMPT_LOCK_RESCHED_OFFSETS); \ + __cond_resched_rwlock_write(lock); \ }) static inline void cond_resched_rcu(void) -- cgit v1.2.3 From 74e78adc6ccf6c3b53939788cf0c49f54db70731 Mon Sep 17 00:00:00 2001 From: Sai Krishna Potthuri Date: Fri, 24 Sep 2021 15:37:08 +0530 Subject: firmware: xilinx: Add OSPI Mux selection support Add OSPI Mux selection API support to select the AXI interface to OSPI. Signed-off-by: Sai Krishna Potthuri Link: https://lore.kernel.org/r/1632478031-12242-2-git-send-email-lakshmi.sai.krishna.potthuri@xilinx.com Signed-off-by: Mark Brown --- drivers/firmware/xilinx/zynqmp.c | 17 +++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 12 ++++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index a3cadbaf3cba..1436e03ff4f7 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -647,6 +647,23 @@ int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) } EXPORT_SYMBOL_GPL(zynqmp_pm_sd_dll_reset); +/** + * zynqmp_pm_ospi_mux_select() - OSPI Mux selection + * + * @dev_id: Device Id of the OSPI device. + * @select: OSPI Mux select value. + * + * This function select the OSPI Mux. + * + * Return: Returns status, either success or error+reason + */ +int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select) +{ + return zynqmp_pm_invoke_fn(PM_IOCTL, dev_id, IOCTL_OSPI_MUX_SELECT, + select, 0, NULL); +} +EXPORT_SYMBOL_GPL(zynqmp_pm_ospi_mux_select); + /** * zynqmp_pm_write_ggs() - PM API for writing global general storage (ggs) * @index: GGS register index diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 56b426fe020c..4c70a6e2141e 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -123,6 +123,7 @@ enum pm_ioctl_id { IOCTL_READ_PGGS = 15, /* Set healthy bit value */ IOCTL_SET_BOOT_HEALTH_STATUS = 17, + IOCTL_OSPI_MUX_SELECT = 21, }; enum pm_query_id { @@ -351,6 +352,11 @@ enum zynqmp_pm_shutdown_subtype { ZYNQMP_PM_SHUTDOWN_SUBTYPE_SYSTEM = 2, }; +enum ospi_mux_select_type { + PM_OSPI_MUX_SEL_DMA = 0, + PM_OSPI_MUX_SEL_LINEAR = 1, +}; + /** * struct zynqmp_pm_query_data - PM query data * @qid: query ID @@ -387,6 +393,7 @@ int zynqmp_pm_set_pll_frac_data(u32 clk_id, u32 data); int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data); int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value); int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type); +int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select); int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag); int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status); @@ -508,6 +515,11 @@ static inline int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type) return -ENODEV; } +static inline int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select) +{ + return -ENODEV; +} + static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset, const enum zynqmp_pm_reset_action assert_flag) { -- cgit v1.2.3 From 42f355ef59a2f98fa4affb4265d3ba3e2d86baf1 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 19 May 2021 16:00:20 -0400 Subject: audit: replace magic audit syscall class numbers with macros Replace audit syscall class magic numbers with macros. This required putting the macros into new header file include/linux/audit_arch.h since the syscall macros were included for both 64 bit and 32 bit in any compat code, causing redefinition warnings. Link: https://lore.kernel.org/r/2300b1083a32aade7ae7efb95826e8f3f260b1df.1621363275.git.rgb@redhat.com Signed-off-by: Richard Guy Briggs Acked-by: Christian Brauner [PM: renamed header to audit_arch.h after consulting with Richard] Signed-off-by: Paul Moore --- MAINTAINERS | 1 + arch/alpha/kernel/audit.c | 8 ++++---- arch/ia64/kernel/audit.c | 8 ++++---- arch/parisc/kernel/audit.c | 8 ++++---- arch/parisc/kernel/compat_audit.c | 9 +++++---- arch/powerpc/kernel/audit.c | 10 +++++----- arch/powerpc/kernel/compat_audit.c | 11 ++++++----- arch/s390/kernel/audit.c | 10 +++++----- arch/s390/kernel/compat_audit.c | 11 ++++++----- arch/sparc/kernel/audit.c | 10 +++++----- arch/sparc/kernel/compat_audit.c | 11 ++++++----- arch/x86/ia32/audit.c | 11 ++++++----- arch/x86/kernel/audit_64.c | 8 ++++---- include/linux/audit.h | 1 + include/linux/audit_arch.h | 23 +++++++++++++++++++++++ kernel/auditsc.c | 12 ++++++------ lib/audit.c | 10 +++++----- lib/compat_audit.c | 11 ++++++----- 18 files changed, 102 insertions(+), 71 deletions(-) create mode 100644 include/linux/audit_arch.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..94c88bc0502f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3113,6 +3113,7 @@ W: https://github.com/linux-audit T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git F: include/asm-generic/audit_*.h F: include/linux/audit.h +F: include/linux/audit_arch.h F: include/uapi/linux/audit.h F: kernel/audit* F: lib/*audit.c diff --git a/arch/alpha/kernel/audit.c b/arch/alpha/kernel/audit.c index 96a9d18ff4c4..81cbd804e375 100644 --- a/arch/alpha/kernel/audit.c +++ b/arch/alpha/kernel/audit.c @@ -37,13 +37,13 @@ int audit_classify_syscall(int abi, unsigned syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/ia64/kernel/audit.c b/arch/ia64/kernel/audit.c index 5192ca899fe6..dba6a74c9ab3 100644 --- a/arch/ia64/kernel/audit.c +++ b/arch/ia64/kernel/audit.c @@ -38,13 +38,13 @@ int audit_classify_syscall(int abi, unsigned syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/parisc/kernel/audit.c b/arch/parisc/kernel/audit.c index 9eb47b2225d2..14244e83db75 100644 --- a/arch/parisc/kernel/audit.c +++ b/arch/parisc/kernel/audit.c @@ -47,13 +47,13 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch (syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/parisc/kernel/compat_audit.c b/arch/parisc/kernel/compat_audit.c index 20c39c9d86a9..1991b99f92ba 100644 --- a/arch/parisc/kernel/compat_audit.c +++ b/arch/parisc/kernel/compat_audit.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include unsigned int parisc32_dir_class[] = { @@ -30,12 +31,12 @@ int parisc32_classify_syscall(unsigned syscall) { switch (syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c index a2dddd7f3d09..6eb18ef77dff 100644 --- a/arch/powerpc/kernel/audit.c +++ b/arch/powerpc/kernel/audit.c @@ -47,15 +47,15 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c index 55c6ccda0a85..216a54f85a12 100644 --- a/arch/powerpc/kernel/compat_audit.c +++ b/arch/powerpc/kernel/compat_audit.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #undef __powerpc64__ +#include #include unsigned ppc32_dir_class[] = { @@ -31,14 +32,14 @@ int ppc32_classify_syscall(unsigned syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/s390/kernel/audit.c b/arch/s390/kernel/audit.c index d395c6c9944c..7e331e1831d4 100644 --- a/arch/s390/kernel/audit.c +++ b/arch/s390/kernel/audit.c @@ -47,15 +47,15 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/s390/kernel/compat_audit.c b/arch/s390/kernel/compat_audit.c index 444fb1f66944..acacc96c57cb 100644 --- a/arch/s390/kernel/compat_audit.c +++ b/arch/s390/kernel/compat_audit.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #undef __s390x__ +#include #include #include "audit.h" @@ -32,14 +33,14 @@ int s390_classify_syscall(unsigned syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/sparc/kernel/audit.c b/arch/sparc/kernel/audit.c index a6e91bf34d48..50fab35bdaba 100644 --- a/arch/sparc/kernel/audit.c +++ b/arch/sparc/kernel/audit.c @@ -48,15 +48,15 @@ int audit_classify_syscall(int abi, unsigned int syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/arch/sparc/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c index 10eeb4f15b20..12515bd655c3 100644 --- a/arch/sparc/kernel/compat_audit.c +++ b/arch/sparc/kernel/compat_audit.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #define __32bit_syscall_numbers__ +#include #include #include "kernel.h" @@ -32,14 +33,14 @@ int sparc32_classify_syscall(unsigned int syscall) { switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c index 6efe6cb3768a..a5fc3b1385e0 100644 --- a/arch/x86/ia32/audit.c +++ b/arch/x86/ia32/audit.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include @@ -31,15 +32,15 @@ int ia32_classify_syscall(unsigned syscall) { switch (syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; case __NR_execve: case __NR_execveat: - return 5; + return AUDITSC_EXECVE; default: - return 1; + return AUDITSC_COMPAT; } } diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index 83d9cad4e68b..2a6cc9c9c881 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -47,14 +47,14 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif switch(syscall) { case __NR_open: - return 2; + return AUDITSC_OPEN; case __NR_openat: - return 3; + return AUDITSC_OPENAT; case __NR_execve: case __NR_execveat: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/include/linux/audit.h b/include/linux/audit.h index 82b7c1116a85..5fbeeeb6b726 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -11,6 +11,7 @@ #include #include +#include #include #include diff --git a/include/linux/audit_arch.h b/include/linux/audit_arch.h new file mode 100644 index 000000000000..d4a506faabb0 --- /dev/null +++ b/include/linux/audit_arch.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* audit_arch.h -- Arch layer specific support for audit + * + * Copyright 2021 Red Hat Inc., Durham, North Carolina. + * All Rights Reserved. + * + * Author: Richard Guy Briggs + */ +#ifndef _LINUX_AUDIT_ARCH_H_ +#define _LINUX_AUDIT_ARCH_H_ + +enum auditsc_class_t { + AUDITSC_NATIVE = 0, + AUDITSC_COMPAT, + AUDITSC_OPEN, + AUDITSC_OPENAT, + AUDITSC_SOCKETCALL, + AUDITSC_EXECVE, + + AUDITSC_NVALS /* count */ +}; + +#endif diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 1af4e7d0c16e..3f9108101598 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -153,7 +153,7 @@ static int audit_match_perm(struct audit_context *ctx, int mask) n = ctx->major; switch (audit_classify_syscall(ctx->arch, n)) { - case 0: /* native */ + case AUDITSC_NATIVE: if ((mask & AUDIT_PERM_WRITE) && audit_match_class(AUDIT_CLASS_WRITE, n)) return 1; @@ -164,7 +164,7 @@ static int audit_match_perm(struct audit_context *ctx, int mask) audit_match_class(AUDIT_CLASS_CHATTR, n)) return 1; return 0; - case 1: /* 32bit on biarch */ + case AUDITSC_COMPAT: /* 32bit on biarch */ if ((mask & AUDIT_PERM_WRITE) && audit_match_class(AUDIT_CLASS_WRITE_32, n)) return 1; @@ -175,13 +175,13 @@ static int audit_match_perm(struct audit_context *ctx, int mask) audit_match_class(AUDIT_CLASS_CHATTR_32, n)) return 1; return 0; - case 2: /* open */ + case AUDITSC_OPEN: return mask & ACC_MODE(ctx->argv[1]); - case 3: /* openat */ + case AUDITSC_OPENAT: return mask & ACC_MODE(ctx->argv[2]); - case 4: /* socketcall */ + case AUDITSC_SOCKETCALL: return ((mask & AUDIT_PERM_WRITE) && ctx->argv[0] == SYS_BIND); - case 5: /* execve */ + case AUDITSC_EXECVE: return mask & AUDIT_PERM_EXEC; default: return 0; diff --git a/lib/audit.c b/lib/audit.c index 5004bff928a7..3ec1a94d8d64 100644 --- a/lib/audit.c +++ b/lib/audit.c @@ -45,23 +45,23 @@ int audit_classify_syscall(int abi, unsigned syscall) switch(syscall) { #ifdef __NR_open case __NR_open: - return 2; + return AUDITSC_OPEN; #endif #ifdef __NR_openat case __NR_openat: - return 3; + return AUDITSC_OPENAT; #endif #ifdef __NR_socketcall case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; #endif #ifdef __NR_execveat case __NR_execveat: #endif case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 0; + return AUDITSC_NATIVE; } } diff --git a/lib/compat_audit.c b/lib/compat_audit.c index 77eabad69b4a..d6567d9e8b99 100644 --- a/lib/compat_audit.c +++ b/lib/compat_audit.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include unsigned compat_dir_class[] = { @@ -33,19 +34,19 @@ int audit_classify_compat_syscall(int abi, unsigned syscall) switch (syscall) { #ifdef __NR_open case __NR_open: - return 2; + return AUDITSC_OPEN; #endif #ifdef __NR_openat case __NR_openat: - return 3; + return AUDITSC_OPENAT; #endif #ifdef __NR_socketcall case __NR_socketcall: - return 4; + return AUDITSC_SOCKETCALL; #endif case __NR_execve: - return 5; + return AUDITSC_EXECVE; default: - return 1; + return AUDITSC_COMPAT; } } -- cgit v1.2.3 From 1c30e3af8a79260cdba833a719209b01e6b92300 Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 19 May 2021 16:00:21 -0400 Subject: audit: add support for the openat2 syscall The openat2(2) syscall was added in kernel v5.6 with commit fddb5d430ad9 ("open: introduce openat2(2) syscall"). Add the openat2(2) syscall to the audit syscall classifier. Link: https://github.com/linux-audit/audit-kernel/issues/67 Link: https://lore.kernel.org/r/f5f1a4d8699613f8c02ce762807228c841c2e26f.1621363275.git.rgb@redhat.com Signed-off-by: Richard Guy Briggs Acked-by: Christian Brauner [PM: merge fuzz due to previous header rename, commit line wraps] Signed-off-by: Paul Moore --- arch/alpha/kernel/audit.c | 2 ++ arch/ia64/kernel/audit.c | 2 ++ arch/parisc/kernel/audit.c | 2 ++ arch/parisc/kernel/compat_audit.c | 2 ++ arch/powerpc/kernel/audit.c | 2 ++ arch/powerpc/kernel/compat_audit.c | 2 ++ arch/s390/kernel/audit.c | 2 ++ arch/s390/kernel/compat_audit.c | 2 ++ arch/sparc/kernel/audit.c | 2 ++ arch/sparc/kernel/compat_audit.c | 2 ++ arch/x86/ia32/audit.c | 2 ++ arch/x86/kernel/audit_64.c | 2 ++ include/linux/audit_arch.h | 1 + kernel/auditsc.c | 3 +++ lib/audit.c | 4 ++++ lib/compat_audit.c | 4 ++++ 16 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/arch/alpha/kernel/audit.c b/arch/alpha/kernel/audit.c index 81cbd804e375..3ab04709784a 100644 --- a/arch/alpha/kernel/audit.c +++ b/arch/alpha/kernel/audit.c @@ -42,6 +42,8 @@ int audit_classify_syscall(int abi, unsigned syscall) return AUDITSC_OPENAT; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/arch/ia64/kernel/audit.c b/arch/ia64/kernel/audit.c index dba6a74c9ab3..ec61f20ca61f 100644 --- a/arch/ia64/kernel/audit.c +++ b/arch/ia64/kernel/audit.c @@ -43,6 +43,8 @@ int audit_classify_syscall(int abi, unsigned syscall) return AUDITSC_OPENAT; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/arch/parisc/kernel/audit.c b/arch/parisc/kernel/audit.c index 14244e83db75..f420b5552140 100644 --- a/arch/parisc/kernel/audit.c +++ b/arch/parisc/kernel/audit.c @@ -52,6 +52,8 @@ int audit_classify_syscall(int abi, unsigned syscall) return AUDITSC_OPENAT; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/arch/parisc/kernel/compat_audit.c b/arch/parisc/kernel/compat_audit.c index 1991b99f92ba..539b16891bdf 100644 --- a/arch/parisc/kernel/compat_audit.c +++ b/arch/parisc/kernel/compat_audit.c @@ -36,6 +36,8 @@ int parisc32_classify_syscall(unsigned syscall) return AUDITSC_OPENAT; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_COMPAT; } diff --git a/arch/powerpc/kernel/audit.c b/arch/powerpc/kernel/audit.c index 6eb18ef77dff..1bcfca5fdf67 100644 --- a/arch/powerpc/kernel/audit.c +++ b/arch/powerpc/kernel/audit.c @@ -54,6 +54,8 @@ int audit_classify_syscall(int abi, unsigned syscall) return AUDITSC_SOCKETCALL; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/arch/powerpc/kernel/compat_audit.c b/arch/powerpc/kernel/compat_audit.c index 216a54f85a12..d92ffe4e5dc1 100644 --- a/arch/powerpc/kernel/compat_audit.c +++ b/arch/powerpc/kernel/compat_audit.c @@ -39,6 +39,8 @@ int ppc32_classify_syscall(unsigned syscall) return AUDITSC_SOCKETCALL; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_COMPAT; } diff --git a/arch/s390/kernel/audit.c b/arch/s390/kernel/audit.c index 7e331e1831d4..02051a596b87 100644 --- a/arch/s390/kernel/audit.c +++ b/arch/s390/kernel/audit.c @@ -54,6 +54,8 @@ int audit_classify_syscall(int abi, unsigned syscall) return AUDITSC_SOCKETCALL; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/arch/s390/kernel/compat_audit.c b/arch/s390/kernel/compat_audit.c index acacc96c57cb..a7c46e8310f0 100644 --- a/arch/s390/kernel/compat_audit.c +++ b/arch/s390/kernel/compat_audit.c @@ -40,6 +40,8 @@ int s390_classify_syscall(unsigned syscall) return AUDITSC_SOCKETCALL; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_COMPAT; } diff --git a/arch/sparc/kernel/audit.c b/arch/sparc/kernel/audit.c index 50fab35bdaba..b092274eca79 100644 --- a/arch/sparc/kernel/audit.c +++ b/arch/sparc/kernel/audit.c @@ -55,6 +55,8 @@ int audit_classify_syscall(int abi, unsigned int syscall) return AUDITSC_SOCKETCALL; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/arch/sparc/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c index 12515bd655c3..f1ea0005a729 100644 --- a/arch/sparc/kernel/compat_audit.c +++ b/arch/sparc/kernel/compat_audit.c @@ -40,6 +40,8 @@ int sparc32_classify_syscall(unsigned int syscall) return AUDITSC_SOCKETCALL; case __NR_execve: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_COMPAT; } diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c index a5fc3b1385e0..59e19549e759 100644 --- a/arch/x86/ia32/audit.c +++ b/arch/x86/ia32/audit.c @@ -40,6 +40,8 @@ int ia32_classify_syscall(unsigned syscall) case __NR_execve: case __NR_execveat: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_COMPAT; } diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c index 2a6cc9c9c881..44c3601cfdc4 100644 --- a/arch/x86/kernel/audit_64.c +++ b/arch/x86/kernel/audit_64.c @@ -53,6 +53,8 @@ int audit_classify_syscall(int abi, unsigned syscall) case __NR_execve: case __NR_execveat: return AUDITSC_EXECVE; + case __NR_openat2: + return AUDITSC_OPENAT2; default: return AUDITSC_NATIVE; } diff --git a/include/linux/audit_arch.h b/include/linux/audit_arch.h index d4a506faabb0..8fdb1afe251a 100644 --- a/include/linux/audit_arch.h +++ b/include/linux/audit_arch.h @@ -16,6 +16,7 @@ enum auditsc_class_t { AUDITSC_OPENAT, AUDITSC_SOCKETCALL, AUDITSC_EXECVE, + AUDITSC_OPENAT2, AUDITSC_NVALS /* count */ }; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 3f9108101598..8c4335a35274 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -63,6 +63,7 @@ #include #include #include +#include #include "audit.h" @@ -183,6 +184,8 @@ static int audit_match_perm(struct audit_context *ctx, int mask) return ((mask & AUDIT_PERM_WRITE) && ctx->argv[0] == SYS_BIND); case AUDITSC_EXECVE: return mask & AUDIT_PERM_EXEC; + case AUDITSC_OPENAT2: + return mask & ACC_MODE((u32)((struct open_how *)ctx->argv[2])->flags); default: return 0; } diff --git a/lib/audit.c b/lib/audit.c index 3ec1a94d8d64..738bda22dd39 100644 --- a/lib/audit.c +++ b/lib/audit.c @@ -60,6 +60,10 @@ int audit_classify_syscall(int abi, unsigned syscall) #endif case __NR_execve: return AUDITSC_EXECVE; +#ifdef __NR_openat2 + case __NR_openat2: + return AUDITSC_OPENAT2; +#endif default: return AUDITSC_NATIVE; } diff --git a/lib/compat_audit.c b/lib/compat_audit.c index d6567d9e8b99..3d6b8996f027 100644 --- a/lib/compat_audit.c +++ b/lib/compat_audit.c @@ -46,6 +46,10 @@ int audit_classify_compat_syscall(int abi, unsigned syscall) #endif case __NR_execve: return AUDITSC_EXECVE; +#ifdef __NR_openat2 + case __NR_openat2: + return AUDITSC_OPENAT2; +#endif default: return AUDITSC_COMPAT; } -- cgit v1.2.3 From e8c0722927e8fc112d78cc0435d336fcd7e3507c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 1 Oct 2021 18:15:27 +0300 Subject: net: mscc: ocelot: write full VLAN TCI in the injection header The VLAN TCI contains more than the VLAN ID, it also has the VLAN PCP and Drop Eligibility Indicator. If the ocelot driver is going to write the VLAN header inside the DSA tag, it could just as well write the entire TCI. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/ethernet/mscc/ocelot.c | 2 +- include/linux/dsa/ocelot.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 559177e6ded4..05c456dbdd72 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -916,7 +916,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, ocelot_ifh_set_bypass(ifh, 1); ocelot_ifh_set_dest(ifh, BIT_ULL(port)); ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C); - ocelot_ifh_set_vid(ifh, skb_vlan_tag_get(skb)); + ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb)); ocelot_ifh_set_rew_op(ifh, rew_op); for (i = 0; i < OCELOT_TAG_LEN / 4; i++) diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 435777a0073c..0fe101e8e190 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -210,9 +210,9 @@ static inline void ocelot_ifh_set_tag_type(void *injection, u64 tag_type) packing(injection, &tag_type, 16, 16, OCELOT_TAG_LEN, PACK, 0); } -static inline void ocelot_ifh_set_vid(void *injection, u64 vid) +static inline void ocelot_ifh_set_vlan_tci(void *injection, u64 vlan_tci) { - packing(injection, &vid, 11, 0, OCELOT_TAG_LEN, PACK, 0); + packing(injection, &vlan_tci, 15, 0, OCELOT_TAG_LEN, PACK, 0); } #endif -- cgit v1.2.3 From f3956ebb3bf06ab2266ad5ee2214aed46405810c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 1 Oct 2021 14:32:23 -0700 Subject: ethernet: use eth_hw_addr_set() instead of ether_addr_copy() Convert Ethernet from ether_addr_copy() to eth_hw_addr_set(): @@ expression dev, np; @@ - ether_addr_copy(dev->dev_addr, np) + eth_hw_addr_set(dev, np) Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/agere/et131x.c | 4 ++-- drivers/net/ethernet/alacritech/slicoss.c | 2 +- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/aquantia/atlantic/aq_nic.c | 2 +- drivers/net/ethernet/broadcom/bgmac-bcma.c | 2 +- drivers/net/ethernet/broadcom/bgmac.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 2 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++-- drivers/net/ethernet/brocade/bna/bnad.c | 4 ++-- drivers/net/ethernet/cavium/liquidio/lio_core.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 3 +-- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- drivers/net/ethernet/ethoc.c | 2 +- drivers/net/ethernet/ezchip/nps_enet.c | 2 +- drivers/net/ethernet/faraday/ftgmac100.c | 4 ++-- drivers/net/ethernet/google/gve/gve_adminq.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 ++-- drivers/net/ethernet/ibm/ibmveth.c | 2 +- drivers/net/ethernet/ibm/ibmvnic.c | 5 ++--- drivers/net/ethernet/intel/fm10k/fm10k_netdev.c | 2 +- drivers/net/ethernet/intel/fm10k/fm10k_pci.c | 4 ++-- drivers/net/ethernet/intel/i40e/i40e_main.c | 4 ++-- drivers/net/ethernet/intel/iavf/iavf_main.c | 2 +- drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 4 ++-- drivers/net/ethernet/intel/ice/ice_main.c | 4 ++-- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 6 +++--- drivers/net/ethernet/korina.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++-- drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 2 +- drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 2 +- drivers/net/ethernet/marvell/prestera/prestera_main.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c | 2 +- drivers/net/ethernet/microchip/enc28j60.c | 4 ++-- drivers/net/ethernet/microchip/lan743x_main.c | 4 ++-- drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c | 2 +- drivers/net/ethernet/microsoft/mana/mana_en.c | 2 +- drivers/net/ethernet/mscc/ocelot_net.c | 2 +- drivers/net/ethernet/netronome/nfp/abm/main.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_net_main.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c | 2 +- drivers/net/ethernet/ni/nixge.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_filter.c | 4 ++-- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/net/ethernet/qualcomm/emac/emac.c | 2 +- drivers/net/ethernet/sfc/ef10_sriov.c | 2 +- drivers/net/ethernet/sfc/efx.c | 2 +- drivers/net/ethernet/sfc/efx_common.c | 4 ++-- drivers/net/ethernet/sfc/falcon/efx.c | 6 +++--- drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 4 ++-- drivers/net/ethernet/ti/davinci_emac.c | 2 +- drivers/net/ethernet/ti/netcp_core.c | 2 +- include/linux/etherdevice.h | 2 +- 57 files changed, 77 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 920633161174..f4edc616388c 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3863,7 +3863,7 @@ static int et131x_change_mtu(struct net_device *netdev, int new_mtu) et131x_init_send(adapter); et131x_hwaddr_init(adapter); - ether_addr_copy(netdev->dev_addr, adapter->addr); + eth_hw_addr_set(netdev, adapter->addr); /* Init the device with the new settings */ et131x_adapter_setup(adapter); @@ -3966,7 +3966,7 @@ static int et131x_pci_setup(struct pci_dev *pdev, netif_napi_add(netdev, &adapter->napi, et131x_poll, 64); - ether_addr_copy(netdev->dev_addr, adapter->addr); + eth_hw_addr_set(netdev, adapter->addr); rc = -ENOMEM; diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 696517eae77f..82f4f2608102 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -1660,7 +1660,7 @@ static int slic_read_eeprom(struct slic_device *sdev) goto free_eeprom; } /* set mac address */ - ether_addr_copy(sdev->netdev->dev_addr, mac[devfn]); + eth_hw_addr_set(sdev->netdev, mac[devfn]); free_eeprom: dma_free_coherent(&sdev->pdev->dev, SLIC_EEPROM_SIZE, eeprom, paddr); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 0e43000614ab..7d5d885d85d5 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -4073,7 +4073,7 @@ static void ena_set_conf_feat_params(struct ena_adapter *adapter, ether_addr_copy(adapter->mac_addr, netdev->dev_addr); } else { ether_addr_copy(adapter->mac_addr, feat->dev_attr.mac_addr); - ether_addr_copy(netdev->dev_addr, adapter->mac_addr); + eth_hw_addr_set(netdev, adapter->mac_addr); } /* Set offload features */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 6c049864dac0..694aa70bcafe 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -332,7 +332,7 @@ int aq_nic_ndev_register(struct aq_nic_s *self) { static u8 mac_addr_permanent[] = AQ_CFG_MAC_ADDR_PERMANENT; - ether_addr_copy(self->ndev->dev_addr, mac_addr_permanent); + eth_hw_addr_set(self->ndev, mac_addr_permanent); } #endif diff --git a/drivers/net/ethernet/broadcom/bgmac-bcma.c b/drivers/net/ethernet/broadcom/bgmac-bcma.c index 9513cfb5ba58..28759062d68d 100644 --- a/drivers/net/ethernet/broadcom/bgmac-bcma.c +++ b/drivers/net/ethernet/broadcom/bgmac-bcma.c @@ -150,7 +150,7 @@ static int bgmac_probe(struct bcma_device *core) err = -ENOTSUPP; goto err; } - ether_addr_copy(bgmac->net_dev->dev_addr, mac); + eth_hw_addr_set(bgmac->net_dev, mac); } /* On BCM4706 we need common core to access PHY */ diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index fe4d99abd548..d2c7834850cc 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1241,7 +1241,7 @@ static int bgmac_set_mac_address(struct net_device *net_dev, void *addr) if (ret < 0) return ret; - ether_addr_copy(net_dev->dev_addr, sa->sa_data); + eth_hw_addr_set(net_dev, sa->sa_data); bgmac_write_mac_address(bgmac, net_dev->dev_addr); eth_commit_mac_addr_change(net_dev, addr); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index 9401936b74fa..8eb28e088582 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -475,7 +475,7 @@ static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep, dev->features |= pf_dev->features; bnxt_vf_rep_eth_addr_gen(bp->pf.mac_addr, vf_rep->vf_idx, dev->perm_addr); - ether_addr_copy(dev->dev_addr, dev->perm_addr); + eth_hw_addr_set(dev, dev->perm_addr); /* Set VF-Rep's max-mtu to the corresponding VF's max-mtu */ if (!bnxt_hwrm_vfr_qcfg(bp, vf_rep, &max_mtu)) dev->max_mtu = max_mtu; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 6a8234bc9428..02fe98cbabb0 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3633,7 +3633,7 @@ static int bcmgenet_set_mac_addr(struct net_device *dev, void *p) if (netif_running(dev)) return -EBUSY; - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); return 0; } @@ -4082,7 +4082,7 @@ static int bcmgenet_probe(struct platform_device *pdev) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); if (pd && !IS_ERR_OR_NULL(pd->mac_address)) - ether_addr_copy(dev->dev_addr, pd->mac_address); + eth_hw_addr_set(dev, pd->mac_address); else if (!device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) if (has_acpi_companion(&pdev->dev)) diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index ba47777d9cff..b1947fd9a07c 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -875,7 +875,7 @@ bnad_set_netdev_perm_addr(struct bnad *bnad) ether_addr_copy(netdev->perm_addr, bnad->perm_addr); if (is_zero_ether_addr(netdev->dev_addr)) - ether_addr_copy(netdev->dev_addr, bnad->perm_addr); + eth_hw_addr_set(netdev, bnad->perm_addr); } /* Control Path Handlers */ @@ -3249,7 +3249,7 @@ bnad_set_mac_address(struct net_device *netdev, void *addr) err = bnad_mac_addr_set_locked(bnad, sa->sa_data); if (!err) - ether_addr_copy(netdev->dev_addr, sa->sa_data); + eth_hw_addr_set(netdev, sa->sa_data); spin_unlock_irqrestore(&bnad->bna_lock, flags); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 2a0d64e5797c..ec7928b54e4a 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -411,7 +411,7 @@ void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac) if (!ether_addr_equal(netdev->dev_addr, mac)) { macaddr_changed = true; - ether_addr_copy(netdev->dev_addr, mac); + eth_hw_addr_set(netdev, mac); ether_addr_copy(((u8 *)&lio->linfo.hw_addr) + 2, mac); call_netdevice_notifiers(NETDEV_CHANGEADDR, netdev); } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index dafc79bd34f4..5d865ba7aed4 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -3634,7 +3634,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) /* Copy MAC Address to OS network device structure */ - ether_addr_copy(netdev->dev_addr, mac); + eth_hw_addr_set(netdev, mac); /* By default all interfaces on a single Octeon uses the same * tx and rx queues diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index f6396ac64006..8a969a9d4b63 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -2148,7 +2148,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) mac[j] = *((u8 *)(((u8 *)&lio->linfo.hw_addr) + 2 + j)); /* Copy MAC Address to OS network device structure */ - ether_addr_copy(netdev->dev_addr, mac); + eth_hw_addr_set(netdev, mac); if (liquidio_setup_io_queues(octeon_dev, i, lio->linfo.num_txpciq, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 2b87565781a0..5ef704c8d839 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -221,8 +221,7 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) nic->tns_mode = mbx.nic_cfg.tns_mode & 0x7F; nic->node = mbx.nic_cfg.node_id; if (!nic->set_mac_pending) - ether_addr_copy(nic->netdev->dev_addr, - mbx.nic_cfg.mac_addr); + eth_hw_addr_set(nic->netdev, mbx.nic_cfg.mac_addr); nic->sqs_mode = mbx.nic_cfg.sqs_mode; nic->loopback_supported = mbx.nic_cfg.loopback_supported; nic->link_up = false; diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 0fb36d50c42b..ef60e2da05a4 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -369,7 +369,7 @@ static int be_mac_addr_set(struct net_device *netdev, void *p) /* Remember currently programmed MAC */ ether_addr_copy(adapter->dev_mac, addr->sa_data); done: - ether_addr_copy(netdev->dev_addr, addr->sa_data); + eth_hw_addr_set(netdev, addr->sa_data); dev_info(dev, "MAC address changed to %pM\n", addr->sa_data); return 0; err: diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index c5bd27db708a..7eb7d28a489d 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -1144,7 +1144,7 @@ static int ethoc_probe(struct platform_device *pdev) /* Allow the platform setup code to pass in a MAC address. */ if (pdata) { - ether_addr_copy(netdev->dev_addr, pdata->hwaddr); + eth_hw_addr_set(netdev, pdata->hwaddr); priv->phy_id = pdata->phy_id; } else { of_get_mac_address(pdev->dev.of_node, netdev->dev_addr); diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index f9a288a6ec8c..f5935eb5a791 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -421,7 +421,7 @@ static s32 nps_enet_set_mac_address(struct net_device *ndev, void *p) res = eth_mac_addr(ndev, p); if (!res) { - ether_addr_copy(ndev->dev_addr, addr->sa_data); + eth_hw_addr_set(ndev, addr->sa_data); nps_enet_set_hw_mac_address(ndev); } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index ff76e401a014..ab9267225573 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -186,7 +186,7 @@ static void ftgmac100_initial_mac(struct ftgmac100 *priv) addr = device_get_mac_address(priv->dev, mac, ETH_ALEN); if (addr) { - ether_addr_copy(priv->netdev->dev_addr, mac); + eth_hw_addr_set(priv->netdev, mac); dev_info(priv->dev, "Read MAC address %pM from device tree\n", mac); return; @@ -203,7 +203,7 @@ static void ftgmac100_initial_mac(struct ftgmac100 *priv) mac[5] = l & 0xff; if (is_valid_ether_addr(mac)) { - ether_addr_copy(priv->netdev->dev_addr, mac); + eth_hw_addr_set(priv->netdev, mac); dev_info(priv->dev, "Read MAC address %pM from chip\n", mac); } else { eth_hw_addr_random(priv->netdev); diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index f089d33dd48e..af2c1d1535f5 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -733,7 +733,7 @@ int gve_adminq_describe_device(struct gve_priv *priv) } priv->dev->max_mtu = mtu; priv->num_event_counters = be16_to_cpu(descriptor->counters); - ether_addr_copy(priv->dev->dev_addr, descriptor->mac); + eth_hw_addr_set(priv->dev, descriptor->mac); mac = descriptor->mac; dev_info(&priv->pdev->dev, "MAC addr: %pM\n", mac); priv->tx_pages_per_qpl = be16_to_cpu(descriptor->tx_pages_per_qpl); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 468b8f07bf47..fea1be4c02ed 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2287,7 +2287,7 @@ static int hns3_nic_net_set_mac_address(struct net_device *netdev, void *p) return ret; } - ether_addr_copy(netdev->dev_addr, mac_addr->sa_data); + eth_hw_addr_set(netdev, mac_addr->sa_data); return 0; } @@ -4933,7 +4933,7 @@ static int hns3_init_mac_addr(struct net_device *netdev) dev_warn(priv->dev, "using random MAC address %pM\n", netdev->dev_addr); } else if (!ether_addr_equal(netdev->dev_addr, mac_addr_temp)) { - ether_addr_copy(netdev->dev_addr, mac_addr_temp); + eth_hw_addr_set(netdev, mac_addr_temp); ether_addr_copy(netdev->perm_addr, mac_addr_temp); } else { return 0; diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 42d374cef664..836617fb3f40 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -1613,7 +1613,7 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p) return rc; } - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); return 0; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 21efd76dd427..9d61167ba767 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -4766,8 +4766,7 @@ static int handle_change_mac_rsp(union ibmvnic_crq *crq, /* crq->change_mac_addr.mac_addr is the requested one * crq->change_mac_addr_rsp.mac_addr is the returned valid one. */ - ether_addr_copy(netdev->dev_addr, - &crq->change_mac_addr_rsp.mac_addr[0]); + eth_hw_addr_set(netdev, &crq->change_mac_addr_rsp.mac_addr[0]); ether_addr_copy(adapter->mac_addr, &crq->change_mac_addr_rsp.mac_addr[0]); out: @@ -5723,7 +5722,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) bitmap_set(adapter->map_ids, 0, 1); ether_addr_copy(adapter->mac_addr, mac_addr_p); - ether_addr_copy(netdev->dev_addr, adapter->mac_addr); + eth_hw_addr_set(netdev, adapter->mac_addr); netdev->irq = dev->irq; netdev->netdev_ops = &ibmvnic_netdev_ops; netdev->ethtool_ops = &ibmvnic_ethtool_ops; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 2fb52bd6fc0e..2cca9e84e31e 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -990,7 +990,7 @@ static int fm10k_set_mac(struct net_device *dev, void *p) } if (!err) { - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); ether_addr_copy(hw->mac.addr, addr->sa_data); dev->addr_assign_type &= ~NET_ADDR_RANDOM; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index adfa2768f024..b473cb7d7c57 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -300,7 +300,7 @@ static int fm10k_handle_reset(struct fm10k_intfc *interface) if (is_valid_ether_addr(hw->mac.perm_addr)) { ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); ether_addr_copy(netdev->perm_addr, hw->mac.perm_addr); - ether_addr_copy(netdev->dev_addr, hw->mac.perm_addr); + eth_hw_addr_set(netdev, hw->mac.perm_addr); netdev->addr_assign_type &= ~NET_ADDR_RANDOM; } @@ -2045,7 +2045,7 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, netdev->addr_assign_type |= NET_ADDR_RANDOM; } - ether_addr_copy(netdev->dev_addr, hw->mac.addr); + eth_hw_addr_set(netdev, hw->mac.addr); ether_addr_copy(netdev->perm_addr, hw->mac.addr); if (!is_valid_ether_addr(netdev->perm_addr)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2f20980dd9a5..f3a1d72538fb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1587,7 +1587,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p) */ spin_lock_bh(&vsi->mac_filter_hash_lock); i40e_del_mac_filter(vsi, netdev->dev_addr); - ether_addr_copy(netdev->dev_addr, addr->sa_data); + eth_hw_addr_set(netdev, addr->sa_data); i40e_add_mac_filter(vsi, netdev->dev_addr); spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -13424,7 +13424,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) i40e_add_mac_filter(vsi, broadcast); spin_unlock_bh(&vsi->mac_filter_hash_lock); - ether_addr_copy(netdev->dev_addr, mac_addr); + eth_hw_addr_set(netdev, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); /* i40iw_net_event() reads 16 bytes from neigh->primary_key */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 23762a7ef740..7f812abe5abe 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1847,7 +1847,7 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) eth_hw_addr_random(netdev); ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); } else { - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + eth_hw_addr_set(netdev, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 3c735968e1b8..8eb8d4663a81 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1685,7 +1685,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (!v_retval) iavf_mac_add_ok(adapter); if (!ether_addr_equal(netdev->dev_addr, adapter->hw.mac.addr)) - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + eth_hw_addr_set(netdev, adapter->hw.mac.addr); break; case VIRTCHNL_OP_GET_STATS: { struct iavf_eth_stats *stats = @@ -1716,7 +1716,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); } else { /* refresh current mac address if changed */ - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + eth_hw_addr_set(netdev, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 909e5cd98054..57e24aeffbc5 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3143,7 +3143,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_PF) { SET_NETDEV_DEV(netdev, ice_pf_to_dev(vsi->back)); ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); - ether_addr_copy(netdev->dev_addr, mac_addr); + eth_hw_addr_set(netdev, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); } @@ -5172,7 +5172,7 @@ err_update_filters: netdev_err(netdev, "can't set MAC %pM. filter update failed\n", mac); netif_addr_lock_bh(netdev); - ether_addr_copy(netdev->dev_addr, old_mac); + eth_hw_addr_set(netdev, old_mac); netif_addr_unlock_bh(netdev); return err; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index c714e1ecd308..d81811ab4ec4 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2540,7 +2540,7 @@ void ixgbevf_reset(struct ixgbevf_adapter *adapter) } if (is_valid_ether_addr(adapter->hw.mac.addr)) { - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + eth_hw_addr_set(netdev, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } @@ -3054,7 +3054,7 @@ static int ixgbevf_sw_init(struct ixgbevf_adapter *adapter) else if (is_zero_ether_addr(adapter->hw.mac.addr)) dev_info(&pdev->dev, "MAC address not assigned by administrator.\n"); - ether_addr_copy(netdev->dev_addr, hw->mac.addr); + eth_hw_addr_set(netdev, hw->mac.addr); } if (!is_valid_ether_addr(netdev->dev_addr)) { @@ -4231,7 +4231,7 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) ether_addr_copy(hw->mac.addr, addr->sa_data); ether_addr_copy(hw->mac.perm_addr, addr->sa_data); - ether_addr_copy(netdev->dev_addr, addr->sa_data); + eth_hw_addr_set(netdev, addr->sa_data); return 0; } diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c index 3e9f324f1061..097516af4325 100644 --- a/drivers/net/ethernet/korina.c +++ b/drivers/net/ethernet/korina.c @@ -1297,7 +1297,7 @@ static int korina_probe(struct platform_device *pdev) lp = netdev_priv(dev); if (mac_addr) - ether_addr_copy(dev->dev_addr, mac_addr); + eth_hw_addr_set(dev, mac_addr); else if (of_get_mac_address(pdev->dev.of_node, dev->dev_addr) < 0) eth_hw_addr_random(dev); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index d5c92e43f89e..94ea6dd91b74 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6083,7 +6083,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, if (fwnode_get_mac_address(fwnode, fw_mac_addr, ETH_ALEN)) { *mac_from = "firmware node"; - ether_addr_copy(dev->dev_addr, fw_mac_addr); + eth_hw_addr_set(dev, fw_mac_addr); return; } @@ -6091,7 +6091,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, mvpp21_get_mac_address(port, hw_mac_addr); if (is_valid_ether_addr(hw_mac_addr)) { *mac_from = "hardware"; - ether_addr_copy(dev->dev_addr, hw_mac_addr); + eth_hw_addr_set(dev, hw_mac_addr); return; } } diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c index 93575800ca92..75ba57bd1d46 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c @@ -2347,7 +2347,7 @@ int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da) return err; /* Set addr in the device */ - ether_addr_copy(dev->dev_addr, da); + eth_hw_addr_set(dev, da); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 0aa88cea1676..9826a9012737 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -188,7 +188,7 @@ static int otx2_hw_get_mac_addr(struct otx2_nic *pfvf, return PTR_ERR(msghdr); } rsp = (struct nix_get_mac_addr_rsp *)msghdr; - ether_addr_copy(netdev->dev_addr, rsp->mac_addr); + eth_hw_addr_set(netdev, rsp->mac_addr); mutex_unlock(&pfvf->mbox.lock); return 0; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index 78a7a00bce22..b667f560b931 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -137,7 +137,7 @@ static int prestera_port_set_mac_address(struct net_device *dev, void *p) if (err) return err; - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 40fc7eb8b2b9..005eb3c92506 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3228,7 +3228,7 @@ static int mlx5e_set_mac(struct net_device *netdev, void *addr) return -EADDRNOTAVAIL; netif_addr_lock_bh(netdev); - ether_addr_copy(netdev->dev_addr, saddr->sa_data); + eth_hw_addr_set(netdev, saddr->sa_data); netif_addr_unlock_bh(netdev); mlx5e_nic_set_rx_mode(priv); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c index 6704f5c1aa32..b990782c1eb1 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c @@ -75,7 +75,7 @@ static void mlxbf_gige_initial_mac(struct mlxbf_gige *priv) u64_to_ether_addr(local_mac, mac); if (is_valid_ether_addr(mac)) { - ether_addr_copy(priv->netdev->dev_addr, mac); + eth_hw_addr_set(priv->netdev, mac); } else { /* Provide a random MAC if for some reason the device has * not been configured with a valid MAC address already. diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c index 09cdc2f2e7ff..bf77e8adffbf 100644 --- a/drivers/net/ethernet/microchip/enc28j60.c +++ b/drivers/net/ethernet/microchip/enc28j60.c @@ -517,7 +517,7 @@ static int enc28j60_set_mac_address(struct net_device *dev, void *addr) if (!is_valid_ether_addr(address->sa_data)) return -EADDRNOTAVAIL; - ether_addr_copy(dev->dev_addr, address->sa_data); + eth_hw_addr_set(dev, address->sa_data); return enc28j60_set_hw_macaddr(dev); } @@ -1573,7 +1573,7 @@ static int enc28j60_probe(struct spi_device *spi) } if (device_get_mac_address(&spi->dev, macaddr, sizeof(macaddr))) - ether_addr_copy(dev->dev_addr, macaddr); + eth_hw_addr_set(dev, macaddr); else eth_hw_addr_random(dev); enc28j60_set_hw_macaddr(dev); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 9e8561cdc32a..03d02403c19e 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -816,7 +816,7 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter) eth_random_addr(adapter->mac_address); } lan743x_mac_set_address(adapter, adapter->mac_address); - ether_addr_copy(netdev->dev_addr, adapter->mac_address); + eth_hw_addr_set(netdev, adapter->mac_address); return 0; } @@ -2645,7 +2645,7 @@ static int lan743x_netdev_set_mac_address(struct net_device *netdev, ret = eth_prepare_mac_addr_change(netdev, sock_addr); if (ret) return ret; - ether_addr_copy(netdev->dev_addr, sock_addr->sa_data); + eth_hw_addr_set(netdev, sock_addr->sa_data); lan743x_mac_set_address(adapter, sock_addr->sa_data); lan743x_rfe_update_mac_address(adapter); return 0; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c index cb68eaaac881..b21ebaa32d7e 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_netdev.c @@ -162,7 +162,7 @@ static int sparx5_set_mac_address(struct net_device *dev, void *p) sparx5_mact_learn(sparx5, PGID_CPU, addr->sa_data, port->pvid); /* Record the address */ - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 1b21030308e5..9a871192ca96 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1608,7 +1608,7 @@ static int mana_init_port(struct net_device *ndev) if (apc->num_queues > apc->max_queues) apc->num_queues = apc->max_queues; - ether_addr_copy(ndev->dev_addr, apc->mac_addr); + eth_hw_addr_set(ndev, apc->mac_addr); return 0; diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 8ef3868d7d68..2f2312715439 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -605,7 +605,7 @@ static int ocelot_port_set_mac_address(struct net_device *dev, void *p) /* Then forget the previous one. */ ocelot_mact_forget(ocelot, dev->dev_addr, ocelot_port->pvid_vlan.vid); - ether_addr_copy(dev->dev_addr, addr->sa_data); + eth_hw_addr_set(dev, addr->sa_data); return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 605a1617b195..5d3df28c648f 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -305,7 +305,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, return; } - ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); + eth_hw_addr_set(nn->dp.netdev, mac_addr); ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 5fbb7c613ff1..751f76cd4f79 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -55,7 +55,7 @@ nfp_net_get_mac_addr(struct nfp_pf *pf, struct net_device *netdev, return; } - ether_addr_copy(netdev->dev_addr, eth_port->mac_addr); + eth_hw_addr_set(netdev, eth_port->mac_addr); ether_addr_copy(netdev->perm_addr, eth_port->mac_addr); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c index c0e2f4394aef..87f2268b16d6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c @@ -58,7 +58,7 @@ static void nfp_netvf_get_mac_addr(struct nfp_net *nn) return; } - ether_addr_copy(nn->dp.netdev->dev_addr, mac_addr); + eth_hw_addr_set(nn->dp.netdev, mac_addr); ether_addr_copy(nn->dp.netdev->perm_addr, mac_addr); } diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 346145d3180e..cfeb7620ae20 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -1283,7 +1283,7 @@ static int nixge_probe(struct platform_device *pdev) mac_addr = nixge_get_nvmem_address(&pdev->dev); if (mac_addr && is_valid_ether_addr(mac_addr)) { - ether_addr_copy(ndev->dev_addr, mac_addr); + eth_hw_addr_set(ndev, mac_addr); kfree(mac_addr); } else { eth_hw_addr_random(ndev); diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index f99b085b56a5..03c51dd37e1f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -557,7 +557,7 @@ void qede_force_mac(void *dev, u8 *mac, bool forced) return; } - ether_addr_copy(edev->ndev->dev_addr, mac); + eth_hw_addr_set(edev->ndev, mac); __qede_unlock(edev); } @@ -1101,7 +1101,7 @@ int qede_set_mac_addr(struct net_device *ndev, void *p) goto out; } - ether_addr_copy(ndev->dev_addr, addr->sa_data); + eth_hw_addr_set(ndev, addr->sa_data); DP_INFO(edev, "Setting device MAC to %pM\n", addr->sa_data); if (edev->state != QEDE_STATE_OPEN) { diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index ee4c3bd28a93..75adb71adf18 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -836,7 +836,7 @@ static void qede_init_ndev(struct qede_dev *edev) ndev->max_mtu = QEDE_MAX_JUMBO_PACKET_SIZE; /* Set network device HW mac */ - ether_addr_copy(edev->ndev->dev_addr, edev->dev_info.common.hw_mac); + eth_hw_addr_set(edev->ndev, edev->dev_info.common.hw_mac); ndev->mtu = edev->dev_info.common.mtu; } diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 9015a38eaced..fbfabfc5cc51 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -550,7 +550,7 @@ static int emac_probe_resources(struct platform_device *pdev, /* get mac address */ if (device_get_mac_address(&pdev->dev, maddr, ETH_ALEN)) - ether_addr_copy(netdev->dev_addr, maddr); + eth_hw_addr_set(netdev, maddr); else eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 752d6406f07e..06d23c708a5f 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -523,7 +523,7 @@ int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) goto fail; if (vf->efx) - ether_addr_copy(vf->efx->net_dev->dev_addr, mac); + eth_hw_addr_set(vf->efx->net_dev, mac); } ether_addr_copy(vf->mac, mac); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 43ef4f529028..6960a2fe2b53 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -136,7 +136,7 @@ static int efx_probe_port(struct efx_nic *efx) return rc; /* Initialise MAC address to permanent address */ - ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr); + eth_hw_addr_set(efx->net_dev, efx->net_dev->perm_addr); return 0; } diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index 896b59253197..f187631b2c5c 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -181,11 +181,11 @@ int efx_set_mac_address(struct net_device *net_dev, void *data) /* save old address */ ether_addr_copy(old_addr, net_dev->dev_addr); - ether_addr_copy(net_dev->dev_addr, new_addr); + eth_hw_addr_set(net_dev, new_addr); if (efx->type->set_mac_address) { rc = efx->type->set_mac_address(efx); if (rc) { - ether_addr_copy(net_dev->dev_addr, old_addr); + eth_hw_addr_set(net_dev, old_addr); return rc; } } diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 423bdf81200f..c68837a951f4 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -1044,7 +1044,7 @@ static int ef4_probe_port(struct ef4_nic *efx) return rc; /* Initialise MAC address to permanent address */ - ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr); + eth_hw_addr_set(efx->net_dev, efx->net_dev->perm_addr); return 0; } @@ -2162,11 +2162,11 @@ static int ef4_set_mac_address(struct net_device *net_dev, void *data) /* save old address */ ether_addr_copy(old_addr, net_dev->dev_addr); - ether_addr_copy(net_dev->dev_addr, new_addr); + eth_hw_addr_set(net_dev, new_addr); if (efx->type->set_mac_address) { rc = efx->type->set_mac_address(efx); if (rc) { - ether_addr_copy(net_dev->dev_addr, old_addr); + eth_hw_addr_set(net_dev, old_addr); return rc; } } diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index f80a2aef9972..c7e56dc0a494 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -2036,7 +2036,7 @@ static int netsec_probe(struct platform_device *pdev) mac = device_get_mac_address(&pdev->dev, macbuf, sizeof(macbuf)); if (mac) - ether_addr_copy(ndev->dev_addr, mac); + eth_hw_addr_set(ndev, mac); if (priv->eeprom_base && (!mac || !is_valid_ether_addr(ndev->dev_addr))) { diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 0de5f4a4fe08..6904bfaa5777 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1970,7 +1970,7 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) ndev_priv->msg_enable = AM65_CPSW_DEBUG; SET_NETDEV_DEV(port->ndev, dev); - ether_addr_copy(port->ndev->dev_addr, port->slave.mac_addr); + eth_hw_addr_set(port->ndev, port->slave.mac_addr); port->ndev->min_mtu = AM65_CPSW_MIN_PACKET_SIZE; port->ndev->max_mtu = AM65_CPSW_MAX_PACKET_SIZE; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 1530532748a8..279e261e4720 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1000,7 +1000,7 @@ static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) flags, vid); ether_addr_copy(priv->mac_addr, addr->sa_data); - ether_addr_copy(ndev->dev_addr, priv->mac_addr); + eth_hw_addr_set(ndev, priv->mac_addr); cpsw_set_slave_mac(&cpsw->slaves[slave_no], priv); pm_runtime_put(cpsw->dev); @@ -1401,7 +1401,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw) dev_info(cpsw->dev, "Random MACID = %pM\n", priv->mac_addr); } - ether_addr_copy(ndev->dev_addr, slave_data->mac_addr); + eth_hw_addr_set(ndev, slave_data->mac_addr); ether_addr_copy(priv->mac_addr, slave_data->mac_addr); cpsw->slaves[i].ndev = ndev; diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index e8291d848839..e4b4624be2ae 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1899,7 +1899,7 @@ static int davinci_emac_probe(struct platform_device *pdev) rc = davinci_emac_try_get_mac(pdev, res_ctrl ? 0 : 1, priv->mac_addr); if (!rc) - ether_addr_copy(ndev->dev_addr, priv->mac_addr); + eth_hw_addr_set(ndev, priv->mac_addr); if (!is_valid_ether_addr(priv->mac_addr)) { /* Use random MAC if still none obtained. */ diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index eda2961c0fe2..a4cd44a39e3d 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -2028,7 +2028,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device, emac_arch_get_mac_addr(efuse_mac_addr, efuse, efuse_mac); if (is_valid_ether_addr(efuse_mac_addr)) - ether_addr_copy(ndev->dev_addr, efuse_mac_addr); + eth_hw_addr_set(ndev, efuse_mac_addr); else eth_random_addr(ndev->dev_addr); diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 928c411bd509..e7b2e5fd8d24 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -323,7 +323,7 @@ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; - ether_addr_copy(dst->dev_addr, src->dev_addr); + eth_hw_addr_set(dst, src->dev_addr); } /** -- cgit v1.2.3 From d0c27c9211fef3ce8083cc3ad2ca3067d211edc9 Mon Sep 17 00:00:00 2001 From: Henrik Grimler Date: Wed, 29 Sep 2021 20:14:18 +0200 Subject: power: supply: max17042_battery: fix typo in MAX17042_IAvg_empty Datasheet gives the name IAvg_empty, not LAvg_empty. Signed-off-by: Henrik Grimler Reviewed-by: Hans de Goede Reviewed-by: Krzysztof Kozlowski Signed-off-by: Sebastian Reichel --- drivers/power/supply/max17042_battery.c | 2 +- include/linux/power/max17042_battery.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c index 5809ba997093..32f331480487 100644 --- a/drivers/power/supply/max17042_battery.c +++ b/drivers/power/supply/max17042_battery.c @@ -786,7 +786,7 @@ static inline void max17042_override_por_values(struct max17042_chip *chip) if ((chip->chip_type == MAXIM_DEVICE_TYPE_MAX17042) || (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17047) || (chip->chip_type == MAXIM_DEVICE_TYPE_MAX17050)) { - max17042_override_por(map, MAX17042_LAvg_empty, config->lavg_empty); + max17042_override_por(map, MAX17042_IAvg_empty, config->iavg_empty); max17042_override_por(map, MAX17042_TempNom, config->temp_nom); max17042_override_por(map, MAX17042_TempLim, config->temp_lim); max17042_override_por(map, MAX17042_FCTC, config->fctc); diff --git a/include/linux/power/max17042_battery.h b/include/linux/power/max17042_battery.h index dd24756a8af7..c417abd2ab70 100644 --- a/include/linux/power/max17042_battery.h +++ b/include/linux/power/max17042_battery.h @@ -78,7 +78,7 @@ enum max17042_register { MAX17042_T_empty = 0x34, MAX17042_FullCAP0 = 0x35, - MAX17042_LAvg_empty = 0x36, + MAX17042_IAvg_empty = 0x36, MAX17042_FCTC = 0x37, MAX17042_RCOMP0 = 0x38, MAX17042_TempCo = 0x39, @@ -221,7 +221,7 @@ struct max17042_config_data { u16 fullcap; /* 0x10 */ u16 fullcapnom; /* 0x23 */ u16 socempty; /* 0x33 */ - u16 lavg_empty; /* 0x36 */ + u16 iavg_empty; /* 0x36 */ u16 dqacc; /* 0x45 */ u16 dpacc; /* 0x46 */ u16 qrtbl00; /* 0x12 */ -- cgit v1.2.3 From dae9a6cab8009e526570e7477ce858dcdfeb256e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 30 Sep 2021 17:06:21 -0400 Subject: NFSD: Have legacy NFSD WRITE decoders use xdr_stream_subsegment() Refactor. Now that the NFSv2 and NFSv3 XDR decoders have been converted to use xdr_streams, the WRITE decoder functions can use xdr_stream_subsegment() to extract the WRITE payload into its own xdr_buf, just as the NFSv4 WRITE XDR decoder currently does. That makes it possible to pass the first kvec, pages array + length, page_base, and total payload length via a single function parameter. The payload's page_base is not yet assigned or used, but will be in subsequent patches. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/nfsd/nfs3proc.c | 3 +-- fs/nfsd/nfs3xdr.c | 12 ++---------- fs/nfsd/nfs4proc.c | 3 +-- fs/nfsd/nfsproc.c | 3 +-- fs/nfsd/nfsxdr.c | 9 +-------- fs/nfsd/xdr.h | 2 +- fs/nfsd/xdr3.h | 2 +- include/linux/sunrpc/svc.h | 3 +-- net/sunrpc/svc.c | 11 ++++++----- 9 files changed, 15 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 17715a6c7a40..4418517f6f12 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -201,8 +201,7 @@ nfsd3_proc_write(struct svc_rqst *rqstp) fh_copy(&resp->fh, &argp->fh); resp->committed = argp->stable; - nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages, - &argp->first, cnt); + nvecs = svc_fill_write_vector(rqstp, &argp->payload); if (!nvecs) { resp->status = nfserr_io; goto out; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 3d37923afb06..267e56f218af 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -621,9 +621,6 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_writeargs *args = rqstp->rq_argp; u32 max_blocksize = svc_max_payload(rqstp); - struct kvec *head = rqstp->rq_arg.head; - struct kvec *tail = rqstp->rq_arg.tail; - size_t remaining; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) return 0; @@ -641,17 +638,12 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) /* request sanity */ if (args->count != args->len) return 0; - remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; - remaining -= xdr_stream_pos(xdr); - if (remaining < xdr_align_size(args->len)) - return 0; if (args->count > max_blocksize) { args->count = max_blocksize; args->len = max_blocksize; } - - args->first.iov_base = xdr->p; - args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); + if (!xdr_stream_subsegment(xdr, &args->payload, args->count)) + return 0; return 1; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index 3dc40c1d32bc..5895bbeba373 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1033,8 +1033,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, write->wr_how_written = write->wr_stable_how; - nvecs = svc_fill_write_vector(rqstp, write->wr_payload.pages, - write->wr_payload.head, write->wr_buflen); + nvecs = svc_fill_write_vector(rqstp, &write->wr_payload); WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec)); status = nfsd_vfs_write(rqstp, &cstate->current_fh, nf, diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 90fcd6178823..eea5b59b6a6c 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -234,8 +234,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) SVCFH_fmt(&argp->fh), argp->len, argp->offset); - nvecs = svc_fill_write_vector(rqstp, rqstp->rq_arg.pages, - &argp->first, cnt); + nvecs = svc_fill_write_vector(rqstp, &argp->payload); if (!nvecs) { resp->status = nfserr_io; goto out; diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 082449c7d0db..ddcc18adfeb1 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -325,10 +325,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_writeargs *args = rqstp->rq_argp; - struct kvec *head = rqstp->rq_arg.head; - struct kvec *tail = rqstp->rq_arg.tail; u32 beginoffset, totalcount; - size_t remaining; if (!svcxdr_decode_fhandle(xdr, &args->fh)) return 0; @@ -346,12 +343,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) return 0; if (args->len > NFSSVC_MAXBLKSIZE_V2) return 0; - remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; - remaining -= xdr_stream_pos(xdr); - if (remaining < xdr_align_size(args->len)) + if (!xdr_stream_subsegment(xdr, &args->payload, args->len)) return 0; - args->first.iov_base = xdr->p; - args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); return 1; } diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index f45b4bc93f52..80fd6d7f3404 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -33,7 +33,7 @@ struct nfsd_writeargs { svc_fh fh; __u32 offset; int len; - struct kvec first; + struct xdr_buf payload; }; struct nfsd_createargs { diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 933008382bbe..712c117300cb 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -40,7 +40,7 @@ struct nfsd3_writeargs { __u32 count; int stable; __u32 len; - struct kvec first; + struct xdr_buf payload; }; struct nfsd3_createargs { diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 064c96157d1f..6263410c948a 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -532,8 +532,7 @@ int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset, unsigned int length); unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, - struct page **pages, - struct kvec *first, size_t total); + struct xdr_buf *payload); char *svc_fill_symlink_pathname(struct svc_rqst *rqstp, struct kvec *first, void *p, size_t total); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index a3bbe5ce4570..08ca797bb8a4 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1676,16 +1676,17 @@ EXPORT_SYMBOL_GPL(svc_encode_result_payload); /** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on - * @pages: list of pages containing data payload - * @first: buffer containing first section of write payload - * @total: total number of bytes of write payload + * @payload: xdr_buf containing only the write data payload * * Fills in rqstp::rq_vec, and returns the number of elements. */ -unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, struct page **pages, - struct kvec *first, size_t total) +unsigned int svc_fill_write_vector(struct svc_rqst *rqstp, + struct xdr_buf *payload) { + struct page **pages = payload->pages; + struct kvec *first = payload->head; struct kvec *vec = rqstp->rq_vec; + size_t total = payload->len; unsigned int i; /* Some types of transport can present the write payload -- cgit v1.2.3 From ca05cbae2a0468e5d78e9b4605936a8bf5da328b Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Sat, 10 Jul 2021 18:07:14 -0400 Subject: NFS: Fix up nfs_ctx_key_to_expire() If the cached credential exists but doesn't have any expiration callback then exit early. Fix up atomicity issues when replacing the credential with a new one since the existing code could lead to refcount leaks. Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 4 ++-- fs/nfs/write.c | 41 ++++++++++++++++++++++++++++------------- include/linux/nfs_fs.h | 2 +- 3 files changed, 31 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 853213b3a209..4f45281c47cf 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1024,7 +1024,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, ctx->cred = get_cred(filp->f_cred); else ctx->cred = get_current_cred(); - ctx->ll_cred = NULL; + rcu_assign_pointer(ctx->ll_cred, NULL); ctx->state = NULL; ctx->mode = f_mode; ctx->flags = 0; @@ -1063,7 +1063,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) put_cred(ctx->cred); dput(ctx->dentry); nfs_sb_deactive(sb); - put_rpccred(ctx->ll_cred); + put_rpccred(rcu_dereference_protected(ctx->ll_cred, 1)); kfree(ctx->mdsthreshold); kfree_rcu(ctx, rcu_head); } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index eae9bf114041..773ea2c8504d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1246,7 +1246,7 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode) struct nfs_open_context *ctx = nfs_file_open_context(filp); if (nfs_ctx_key_to_expire(ctx, inode) && - !ctx->ll_cred) + !rcu_access_pointer(ctx->ll_cred)) /* Already expired! */ return -EACCES; return 0; @@ -1258,23 +1258,38 @@ nfs_key_timeout_notify(struct file *filp, struct inode *inode) bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode) { struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; - struct rpc_cred *cred = ctx->ll_cred; + struct rpc_cred *cred, *new, *old = NULL; struct auth_cred acred = { .cred = ctx->cred, }; + bool ret = false; - if (cred && !cred->cr_ops->crmatch(&acred, cred, 0)) { - put_rpccred(cred); - ctx->ll_cred = NULL; - cred = NULL; - } - if (!cred) - cred = auth->au_ops->lookup_cred(auth, &acred, 0); - if (!cred || IS_ERR(cred)) + rcu_read_lock(); + cred = rcu_dereference(ctx->ll_cred); + if (cred && !(cred->cr_ops->crkey_timeout && + cred->cr_ops->crkey_timeout(cred))) + goto out; + rcu_read_unlock(); + + new = auth->au_ops->lookup_cred(auth, &acred, 0); + if (new == cred) { + put_rpccred(new); return true; - ctx->ll_cred = cred; - return !!(cred->cr_ops->crkey_timeout && - cred->cr_ops->crkey_timeout(cred)); + } + if (IS_ERR_OR_NULL(new)) { + new = NULL; + ret = true; + } else if (new->cr_ops->crkey_timeout && + new->cr_ops->crkey_timeout(new)) + ret = true; + + rcu_read_lock(); + old = rcu_dereference_protected(xchg(&ctx->ll_cred, + RCU_INITIALIZER(new)), 1); +out: + rcu_read_unlock(); + put_rpccred(old); + return ret; } /* diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index b9a8b925db43..9b75448ce0df 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -81,7 +81,7 @@ struct nfs_open_context { fl_owner_t flock_owner; struct dentry *dentry; const struct cred *cred; - struct rpc_cred *ll_cred; /* low-level cred - use to check for expiry */ + struct rpc_cred __rcu *ll_cred; /* low-level cred - use to check for expiry */ struct nfs4_state *state; fmode_t mode; -- cgit v1.2.3 From b9f8713f42af11ae6d7f63075334ba5298436be6 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 12 Jul 2021 12:24:15 -0400 Subject: SUNRPC: Remove unnecessary memory barriers The only check for RPC_TASK_RUNNING is the one in rpc_make_runnable(), which happens under the same spin lock held when we call rpc_clear_running(). Ditto, the last check for RPC_TASK_QUEUED in rpc_execute() is performed under the same lock as the one held when we call rpc_clear_queued(). Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 16 ++-------------- 1 file changed, 2 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index a237b8dbf608..db964bb63912 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -150,25 +150,13 @@ struct rpc_task_setup { #define RPC_TASK_MSG_PIN_WAIT 5 #define RPC_TASK_SIGNALLED 6 -#define RPC_IS_RUNNING(t) test_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -#define rpc_set_running(t) set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define rpc_test_and_set_running(t) \ test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) -#define rpc_clear_running(t) \ - do { \ - smp_mb__before_atomic(); \ - clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate); \ - smp_mb__after_atomic(); \ - } while (0) +#define rpc_clear_running(t) clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate) #define RPC_IS_QUEUED(t) test_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) #define rpc_set_queued(t) set_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) -#define rpc_clear_queued(t) \ - do { \ - smp_mb__before_atomic(); \ - clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate); \ - smp_mb__after_atomic(); \ - } while (0) +#define rpc_clear_queued(t) clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate) #define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate) -- cgit v1.2.3 From ff81dfb5d721fff87bd516c558847f6effb70031 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Sep 2021 14:33:44 -0400 Subject: NFS: Further optimisations for 'ls -l' If a user is doing 'ls -l', we have a heuristic in GETATTR that tells the readdir code to try to use READDIRPLUS in order to refresh the inode attributes. In certain cirumstances, we also try to invalidate the remaining directory entries in order to ensure this refresh. If there are multiple readers of the directory, we probably should avoid invalidating the page cache, since the heuristic breaks down in that situation anyway. Signed-off-by: Trond Myklebust Tested-by: Benjamin Coddington Reviewed-by: Benjamin Coddington --- fs/nfs/dir.c | 16 +++++++++++----- include/linux/nfs_fs.h | 5 ++--- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index fa4d33687d2b..33cfff8ea551 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -78,6 +78,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir ctx->attr_gencount = nfsi->attr_gencount; ctx->dir_cookie = 0; ctx->dup_cookie = 0; + ctx->page_index = 0; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) @@ -85,6 +86,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir NFS_INO_INVALID_DATA | NFS_INO_REVAL_FORCED); list_add(&ctx->list, &nfsi->open_files); + clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); spin_unlock(&dir->i_lock); return ctx; } @@ -627,8 +629,7 @@ void nfs_force_use_readdirplus(struct inode *dir) if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) && !list_empty(&nfsi->open_files)) { set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags); - invalidate_mapping_pages(dir->i_mapping, - nfsi->page_index + 1, -1); + set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags); } } @@ -938,10 +939,8 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc) sizeof(nfsi->cookieverf)); } res = nfs_readdir_search_array(desc); - if (res == 0) { - nfsi->page_index = desc->page_index; + if (res == 0) return 0; - } nfs_readdir_page_unlock_and_put_cached(desc); return res; } @@ -1080,6 +1079,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_dir_context *dir_ctx = file->private_data; struct nfs_readdir_descriptor *desc; + pgoff_t page_index; int res; dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n", @@ -1110,10 +1110,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->dir_cookie = dir_ctx->dir_cookie; desc->dup_cookie = dir_ctx->dup_cookie; desc->duped = dir_ctx->duped; + page_index = dir_ctx->page_index; desc->attr_gencount = dir_ctx->attr_gencount; memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); spin_unlock(&file->f_lock); + if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && + list_is_singular(&nfsi->open_files)) + invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); + do { res = readdir_search_pagecache(desc); @@ -1150,6 +1155,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) dir_ctx->dup_cookie = desc->dup_cookie; dir_ctx->duped = desc->duped; dir_ctx->attr_gencount = desc->attr_gencount; + dir_ctx->page_index = desc->page_index; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 9b75448ce0df..ca547cc5458c 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -103,6 +103,7 @@ struct nfs_open_dir_context { __be32 verf[NFS_DIR_VERIFIER_SIZE]; __u64 dir_cookie; __u64 dup_cookie; + pgoff_t page_index; signed char duped; }; @@ -181,9 +182,6 @@ struct nfs_inode { struct rw_semaphore rmdir_sem; struct mutex commit_mutex; - /* track last access to cached pages */ - unsigned long page_index; - #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ @@ -272,6 +270,7 @@ struct nfs4_copy_state { #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ #define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ +#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ #define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */ -- cgit v1.2.3 From 3734b9f2cee01d9dde2fbbda742ba6dd6ba10a29 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 27 Sep 2021 01:40:24 +0300 Subject: opp: Change type of dev_pm_opp_attach_genpd(names) argument Elements of the 'names' array are not changed by the code, constify them for consistency. Signed-off-by: Dmitry Osipenko Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 6 +++--- include/linux/pm_opp.h | 8 ++++---- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 04b4691a8aac..3057beabd370 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -2348,12 +2348,12 @@ static void _opp_detach_genpd(struct opp_table *opp_table) * "required-opps" are added in DT. */ struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, - const char **names, struct device ***virt_devs) + const char * const *names, struct device ***virt_devs) { struct opp_table *opp_table; struct device *virt_dev; int index = 0, ret = -EINVAL; - const char **name = names; + const char * const *name = names; opp_table = _add_opp_table(dev, false); if (IS_ERR(opp_table)) @@ -2457,7 +2457,7 @@ static void devm_pm_opp_detach_genpd(void *data) * * Return: 0 on success and errorno otherwise. */ -int devm_pm_opp_attach_genpd(struct device *dev, const char **names, +int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs) { struct opp_table *opp_table; diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 84150a22fd7c..7f1f066fc377 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -156,9 +156,9 @@ int devm_pm_opp_set_clkname(struct device *dev, const char *name); struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table); int devm_pm_opp_register_set_opp_helper(struct device *dev, int (*set_opp)(struct dev_pm_set_opp_data *data)); -struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); void dev_pm_opp_detach_genpd(struct opp_table *opp_table); -int devm_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs); +int devm_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs); struct dev_pm_opp *dev_pm_opp_xlate_required_opp(struct opp_table *src_table, struct opp_table *dst_table, struct dev_pm_opp *src_opp); int dev_pm_opp_xlate_performance_state(struct opp_table *src_table, struct opp_table *dst_table, unsigned int pstate); int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq); @@ -376,7 +376,7 @@ static inline int devm_pm_opp_set_clkname(struct device *dev, const char *name) return -EOPNOTSUPP; } -static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char **names, struct device ***virt_devs) +static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, const char * const *names, struct device ***virt_devs) { return ERR_PTR(-EOPNOTSUPP); } @@ -384,7 +384,7 @@ static inline struct opp_table *dev_pm_opp_attach_genpd(struct device *dev, cons static inline void dev_pm_opp_detach_genpd(struct opp_table *opp_table) {} static inline int devm_pm_opp_attach_genpd(struct device *dev, - const char **names, + const char * const *names, struct device ***virt_devs) { return -EOPNOTSUPP; -- cgit v1.2.3 From 46b49b12f3fc5e1347dba37d4639e2165f447871 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Wed, 8 Sep 2021 17:58:33 -0500 Subject: arch/cc: Introduce a function to check for confidential computing features In preparation for other confidential computing technologies, introduce a generic helper function, cc_platform_has(), that can be used to check for specific active confidential computing attributes, like memory encryption. This is intended to eliminate having to add multiple technology-specific checks to the code (e.g. if (sev_active() || tdx_active() || ... ). [ bp: s/_CC_PLATFORM_H/_LINUX_CC_PLATFORM_H/g ] Co-developed-by: Andi Kleen Signed-off-by: Andi Kleen Co-developed-by: Kuppuswamy Sathyanarayanan Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210928191009.32551-3-bp@alien8.de --- arch/Kconfig | 3 ++ include/linux/cc_platform.h | 88 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 91 insertions(+) create mode 100644 include/linux/cc_platform.h (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 8df1c7102643..d1e69d6e8498 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1234,6 +1234,9 @@ config RELR config ARCH_HAS_MEM_ENCRYPT bool +config ARCH_HAS_CC_PLATFORM + bool + config HAVE_SPARSE_SYSCALL_NR bool help diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h new file mode 100644 index 000000000000..a075b70b9a70 --- /dev/null +++ b/include/linux/cc_platform.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Confidential Computing Platform Capability checks + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky + */ + +#ifndef _LINUX_CC_PLATFORM_H +#define _LINUX_CC_PLATFORM_H + +#include +#include + +/** + * enum cc_attr - Confidential computing attributes + * + * These attributes represent confidential computing features that are + * currently active. + */ +enum cc_attr { + /** + * @CC_ATTR_MEM_ENCRYPT: Memory encryption is active + * + * The platform/OS is running with active memory encryption. This + * includes running either as a bare-metal system or a hypervisor + * and actively using memory encryption or as a guest/virtual machine + * and actively using memory encryption. + * + * Examples include SME, SEV and SEV-ES. + */ + CC_ATTR_MEM_ENCRYPT, + + /** + * @CC_ATTR_HOST_MEM_ENCRYPT: Host memory encryption is active + * + * The platform/OS is running as a bare-metal system or a hypervisor + * and actively using memory encryption. + * + * Examples include SME. + */ + CC_ATTR_HOST_MEM_ENCRYPT, + + /** + * @CC_ATTR_GUEST_MEM_ENCRYPT: Guest memory encryption is active + * + * The platform/OS is running as a guest/virtual machine and actively + * using memory encryption. + * + * Examples include SEV and SEV-ES. + */ + CC_ATTR_GUEST_MEM_ENCRYPT, + + /** + * @CC_ATTR_GUEST_STATE_ENCRYPT: Guest state encryption is active + * + * The platform/OS is running as a guest/virtual machine and actively + * using memory encryption and register state encryption. + * + * Examples include SEV-ES. + */ + CC_ATTR_GUEST_STATE_ENCRYPT, +}; + +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM + +/** + * cc_platform_has() - Checks if the specified cc_attr attribute is active + * @attr: Confidential computing attribute to check + * + * The cc_platform_has() function will return an indicator as to whether the + * specified Confidential Computing attribute is currently active. + * + * Context: Any context + * Return: + * * TRUE - Specified Confidential Computing attribute is active + * * FALSE - Specified Confidential Computing attribute is not active + */ +bool cc_platform_has(enum cc_attr attr); + +#else /* !CONFIG_ARCH_HAS_CC_PLATFORM */ + +static inline bool cc_platform_has(enum cc_attr attr) { return false; } + +#endif /* CONFIG_ARCH_HAS_CC_PLATFORM */ + +#endif /* _LINUX_CC_PLATFORM_H */ -- cgit v1.2.3 From e9d1d2bb75b2d5d4b426769c5aae0ce8cef3558f Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Wed, 8 Sep 2021 17:58:39 -0500 Subject: treewide: Replace the use of mem_encrypt_active() with cc_platform_has() Replace uses of mem_encrypt_active() with calls to cc_platform_has() with the CC_ATTR_MEM_ENCRYPT attribute. Remove the implementation of mem_encrypt_active() across all arches. For s390, since the default implementation of the cc_platform_has() matches the s390 implementation of mem_encrypt_active(), cc_platform_has() does not need to be implemented in s390 (the config option ARCH_HAS_CC_PLATFORM is not set). Signed-off-by: Tom Lendacky Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20210928191009.32551-9-bp@alien8.de --- arch/powerpc/include/asm/mem_encrypt.h | 5 ----- arch/powerpc/platforms/pseries/svm.c | 5 +++-- arch/s390/include/asm/mem_encrypt.h | 2 -- arch/x86/include/asm/mem_encrypt.h | 5 ----- arch/x86/kernel/head64.c | 9 +++++++-- arch/x86/mm/ioremap.c | 4 ++-- arch/x86/mm/mem_encrypt.c | 2 +- arch/x86/mm/pat/set_memory.c | 3 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 +++- drivers/gpu/drm/drm_cache.c | 4 ++-- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 4 ++-- drivers/gpu/drm/vmwgfx/vmwgfx_msg.c | 6 +++--- drivers/iommu/amd/iommu.c | 3 ++- drivers/iommu/amd/iommu_v2.c | 3 ++- drivers/iommu/iommu.c | 3 ++- fs/proc/vmcore.c | 6 +++--- include/linux/mem_encrypt.h | 4 ---- kernel/dma/swiotlb.c | 4 ++-- 18 files changed, 36 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/mem_encrypt.h b/arch/powerpc/include/asm/mem_encrypt.h index ba9dab07c1be..2f26b8fc8d29 100644 --- a/arch/powerpc/include/asm/mem_encrypt.h +++ b/arch/powerpc/include/asm/mem_encrypt.h @@ -10,11 +10,6 @@ #include -static inline bool mem_encrypt_active(void) -{ - return is_secure_guest(); -} - static inline bool force_dma_unencrypted(struct device *dev) { return is_secure_guest(); diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 87f001b4c4e4..c083ecbbae4d 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -63,7 +64,7 @@ void __init svm_swiotlb_init(void) int set_memory_encrypted(unsigned long addr, int numpages) { - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return 0; if (!PAGE_ALIGNED(addr)) @@ -76,7 +77,7 @@ int set_memory_encrypted(unsigned long addr, int numpages) int set_memory_decrypted(unsigned long addr, int numpages) { - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return 0; if (!PAGE_ALIGNED(addr)) diff --git a/arch/s390/include/asm/mem_encrypt.h b/arch/s390/include/asm/mem_encrypt.h index 2542cbf7e2d1..08a8b96606d7 100644 --- a/arch/s390/include/asm/mem_encrypt.h +++ b/arch/s390/include/asm/mem_encrypt.h @@ -4,8 +4,6 @@ #ifndef __ASSEMBLY__ -static inline bool mem_encrypt_active(void) { return false; } - int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index da14ede311aa..2d4f5c17d79c 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -96,11 +96,6 @@ static inline void mem_encrypt_free_decrypted_mem(void) { } extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline bool mem_encrypt_active(void) -{ - return sme_me_mask; -} - static inline u64 sme_get_me_mask(void) { return sme_me_mask; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index de01903c3735..fc5371a7e9d1 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include @@ -284,8 +284,13 @@ unsigned long __head __startup_64(unsigned long physaddr, * The bss section will be memset to zero later in the initialization so * there is no need to zero it after changing the memory encryption * attribute. + * + * This is early code, use an open coded check for SME instead of + * using cc_platform_has(). This eliminates worries about removing + * instrumentation or checking boot_cpu_data in the cc_platform_has() + * function. */ - if (mem_encrypt_active()) { + if (sme_get_me_mask()) { vaddr = (unsigned long)__start_bss_decrypted; vaddr_end = (unsigned long)__end_bss_decrypted; for (; vaddr < vaddr_end; vaddr += PMD_SIZE) { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b59a5cbc6bc5..026031b3b782 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -694,7 +694,7 @@ static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, unsigned long flags) { - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return true; if (flags & MEMREMAP_ENC) @@ -724,7 +724,7 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, { bool encrypted_prot; - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return prot; encrypted_prot = true; diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 2d04c39bea1d..23d54b810f08 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -400,7 +400,7 @@ void __init mem_encrypt_free_decrypted_mem(void) * The unused memory range was mapped decrypted, change the encryption * attribute from decrypted to encrypted before freeing it. */ - if (mem_encrypt_active()) { + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { r = set_memory_encrypted(vaddr, npages); if (r) { pr_warn("failed to free unused decrypted pages\n"); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index ad8a5c586a35..527957586f3c 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -1986,7 +1987,7 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) int ret; /* Nothing to do if memory encryption is not active */ - if (!mem_encrypt_active()) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return 0; /* Should not be working on unaligned addresses */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index f18240f87387..7741195eb85e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -38,6 +38,7 @@ #include #include #include +#include #include "amdgpu.h" #include "amdgpu_irq.h" @@ -1269,7 +1270,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, * however, SME requires an indirect IOMMU mapping because the encryption * bit is beyond the DMA mask of the chip. */ - if (mem_encrypt_active() && ((flags & AMD_ASIC_MASK) == CHIP_RAVEN)) { + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT) && + ((flags & AMD_ASIC_MASK) == CHIP_RAVEN)) { dev_info(&pdev->dev, "SME is not compatible with RAVEN\n"); return -ENOTSUPP; diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c index 30cc59fe6ef7..f19d9acbe959 100644 --- a/drivers/gpu/drm/drm_cache.c +++ b/drivers/gpu/drm/drm_cache.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include #include #include @@ -204,7 +204,7 @@ bool drm_need_swiotlb(int dma_bits) * Enforce dma_alloc_coherent when memory encryption is active as well * for the same reasons as for Xen paravirtual hosts. */ - if (mem_encrypt_active()) + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return true; for (tmp = iomem_resource.child; tmp; tmp = tmp->sibling) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index ab9a1750e1df..bfd71c86faa5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -29,7 +29,7 @@ #include #include #include -#include +#include #include #include @@ -666,7 +666,7 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_map_bind] = "Giving up DMA mappings early."}; /* TTM currently doesn't fully support SEV encryption. */ - if (mem_encrypt_active()) + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return -EINVAL; if (vmw_force_coherent) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c index e50fb82a3030..2aceac7856e2 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include @@ -160,7 +160,7 @@ static unsigned long vmw_port_hb_out(struct rpc_channel *channel, unsigned long msg_len = strlen(msg); /* HB port can't access encrypted memory. */ - if (hb && !mem_encrypt_active()) { + if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { unsigned long bp = channel->cookie_high; u32 channel_id = (channel->channel_id << 16); @@ -216,7 +216,7 @@ static unsigned long vmw_port_hb_in(struct rpc_channel *channel, char *reply, unsigned long si, di, eax, ebx, ecx, edx; /* HB port can't access encrypted memory */ - if (hb && !mem_encrypt_active()) { + if (hb && !cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { unsigned long bp = channel->cookie_low; u32 channel_id = (channel->channel_id << 16); diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 1722bb161841..9e5da037d949 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -2238,7 +2239,7 @@ static int amd_iommu_def_domain_type(struct device *dev) * active, because some of those devices (AMD GPUs) don't have the * encryption bit in their DMA-mask and require remapping. */ - if (!mem_encrypt_active() && dev_data->iommu_v2) + if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT) && dev_data->iommu_v2) return IOMMU_DOMAIN_IDENTITY; return 0; diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c index a9e568276c99..13cbeb997cc1 100644 --- a/drivers/iommu/amd/iommu_v2.c +++ b/drivers/iommu/amd/iommu_v2.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "amd_iommu.h" @@ -742,7 +743,7 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids) * When memory encryption is active the device is likely not in a * direct-mapped domain. Forbid using IOMMUv2 functionality for now. */ - if (mem_encrypt_active()) + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) return -ENODEV; if (!amd_iommu_v2_supported()) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 3303d707bab4..e80261d17a49 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -25,6 +25,7 @@ #include #include #include +#include #include static struct kset *iommu_group_kset; @@ -130,7 +131,7 @@ static int __init iommu_subsys_init(void) else iommu_set_default_translated(false); - if (iommu_default_passthrough() && mem_encrypt_active()) { + if (iommu_default_passthrough() && cc_platform_has(CC_ATTR_MEM_ENCRYPT)) { pr_info("Memory encryption detected - Disabling default IOMMU Passthrough\n"); iommu_set_default_translated(false); } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 9a15334da208..cdbbf819d2d6 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include "internal.h" @@ -177,7 +177,7 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos) */ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos) { - return read_from_oldmem(buf, count, ppos, 0, mem_encrypt_active()); + return read_from_oldmem(buf, count, ppos, 0, cc_platform_has(CC_ATTR_MEM_ENCRYPT)); } /* @@ -378,7 +378,7 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos, buflen); start = m->paddr + *fpos - m->offset; tmp = read_from_oldmem(buffer, tsz, &start, - userbuf, mem_encrypt_active()); + userbuf, cc_platform_has(CC_ATTR_MEM_ENCRYPT)); if (tmp < 0) return tmp; buflen -= tsz; diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h index 5c4a18a91f89..ae4526389261 100644 --- a/include/linux/mem_encrypt.h +++ b/include/linux/mem_encrypt.h @@ -16,10 +16,6 @@ #include -#else /* !CONFIG_ARCH_HAS_MEM_ENCRYPT */ - -static inline bool mem_encrypt_active(void) { return false; } - #endif /* CONFIG_ARCH_HAS_MEM_ENCRYPT */ #ifdef CONFIG_AMD_MEM_ENCRYPT diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 87c40517e822..c4ca040fdb05 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #ifdef CONFIG_DEBUG_FS #include @@ -552,7 +552,7 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, if (!mem) panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); - if (mem_encrypt_active()) + if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); if (mapping_size > alloc_size) { -- cgit v1.2.3 From e69709f6861aaba80b4eaab6825e8c522a2afb5c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Mon, 20 Sep 2021 20:22:46 +0300 Subject: opp: Add more resource-managed variants of dev_pm_opp_of_add_table() Add resource-managed variants of dev_pm_opp_of_add_table_indexed() and dev_pm_opp_of_add_table_noclk(), allowing drivers to remove boilerplate code. Signed-off-by: Dmitry Osipenko [ Viresh: Added underscore to devm_of_add_table_indexed() ] Signed-off-by: Viresh Kumar --- drivers/opp/of.c | 46 +++++++++++++++++++++++++++++++++++++++------- include/linux/pm_opp.h | 12 ++++++++++++ 2 files changed, 51 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/opp/of.c b/drivers/opp/of.c index 5437085fb380..fe218af735b0 100644 --- a/drivers/opp/of.c +++ b/drivers/opp/of.c @@ -1081,6 +1081,17 @@ static void devm_pm_opp_of_table_release(void *data) dev_pm_opp_of_remove_table(data); } +static int _devm_of_add_table_indexed(struct device *dev, int index, bool getclk) +{ + int ret; + + ret = _of_add_table_indexed(dev, index, getclk); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, devm_pm_opp_of_table_release, dev); +} + /** * devm_pm_opp_of_add_table() - Initialize opp table from device tree * @dev: device pointer used to lookup OPP table. @@ -1102,13 +1113,7 @@ static void devm_pm_opp_of_table_release(void *data) */ int devm_pm_opp_of_add_table(struct device *dev) { - int ret; - - ret = dev_pm_opp_of_add_table(dev); - if (ret) - return ret; - - return devm_add_action_or_reset(dev, devm_pm_opp_of_table_release, dev); + return _devm_of_add_table_indexed(dev, 0, true); } EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table); @@ -1151,6 +1156,19 @@ int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) } EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed); +/** + * devm_pm_opp_of_add_table_indexed() - Initialize indexed opp table from device tree + * @dev: device pointer used to lookup OPP table. + * @index: Index number. + * + * This is a resource-managed variant of dev_pm_opp_of_add_table_indexed(). + */ +int devm_pm_opp_of_add_table_indexed(struct device *dev, int index) +{ + return _devm_of_add_table_indexed(dev, index, true); +} +EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table_indexed); + /** * dev_pm_opp_of_add_table_noclk() - Initialize indexed opp table from device * tree without getting clk for device. @@ -1169,6 +1187,20 @@ int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) } EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_noclk); +/** + * devm_pm_opp_of_add_table_noclk() - Initialize indexed opp table from device + * tree without getting clk for device. + * @dev: device pointer used to lookup OPP table. + * @index: Index number. + * + * This is a resource-managed variant of dev_pm_opp_of_add_table_noclk(). + */ +int devm_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return _devm_of_add_table_indexed(dev, index, false); +} +EXPORT_SYMBOL_GPL(devm_pm_opp_of_add_table_noclk); + /* CPU device specific helpers */ /** diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 7f1f066fc377..879c138c7b8e 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -439,7 +439,9 @@ static inline int dev_pm_opp_sync_regulators(struct device *dev) #if defined(CONFIG_PM_OPP) && defined(CONFIG_OF) int dev_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_add_table_indexed(struct device *dev, int index); +int devm_pm_opp_of_add_table_indexed(struct device *dev, int index); int dev_pm_opp_of_add_table_noclk(struct device *dev, int index); +int devm_pm_opp_of_add_table_noclk(struct device *dev, int index); void dev_pm_opp_of_remove_table(struct device *dev); int devm_pm_opp_of_add_table(struct device *dev); int dev_pm_opp_of_cpumask_add_table(const struct cpumask *cpumask); @@ -465,11 +467,21 @@ static inline int dev_pm_opp_of_add_table_indexed(struct device *dev, int index) return -EOPNOTSUPP; } +static inline int devm_pm_opp_of_add_table_indexed(struct device *dev, int index) +{ + return -EOPNOTSUPP; +} + static inline int dev_pm_opp_of_add_table_noclk(struct device *dev, int index) { return -EOPNOTSUPP; } +static inline int devm_pm_opp_of_add_table_noclk(struct device *dev, int index) +{ + return -EOPNOTSUPP; +} + static inline void dev_pm_opp_of_remove_table(struct device *dev) { } -- cgit v1.2.3 From 19198e4ec97dc9d173b458a75ace3c3ca55c2d85 Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Mon, 4 Oct 2021 09:58:39 +0300 Subject: qed: Fix kernel-doc warnings This patch fixes all the qed and qede kernel-doc warnings according to the guidelines that are described in Documentation/doc-guide/kernel-doc.rst. Signed-off-by: Ariel Elior Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed.h | 9 +- drivers/net/ethernet/qlogic/qed/qed_cxt.h | 138 ++-- drivers/net/ethernet/qlogic/qed/qed_dev_api.h | 343 +++++---- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 956 +++++++++++++------------ drivers/net/ethernet/qlogic/qed/qed_hw.h | 222 +++--- drivers/net/ethernet/qlogic/qed/qed_init_ops.h | 58 +- drivers/net/ethernet/qlogic/qed/qed_int.h | 284 ++++---- drivers/net/ethernet/qlogic/qed/qed_iscsi.h | 9 +- drivers/net/ethernet/qlogic/qed/qed_l2.h | 134 ++-- drivers/net/ethernet/qlogic/qed/qed_ll2.h | 130 ++-- drivers/net/ethernet/qlogic/qed/qed_mcp.h | 757 +++++++++++--------- drivers/net/ethernet/qlogic/qed/qed_selftest.h | 30 +- drivers/net/ethernet/qlogic/qed/qed_sp.h | 215 +++--- drivers/net/ethernet/qlogic/qed/qed_sriov.h | 99 +-- drivers/net/ethernet/qlogic/qed/qed_vf.h | 301 ++++---- drivers/net/ethernet/qlogic/qede/qede_main.c | 5 +- include/linux/qed/qed_chain.h | 97 +-- include/linux/qed/qed_if.h | 255 ++++--- include/linux/qed/qed_iscsi_if.h | 2 +- include/linux/qed/qed_ll2_if.h | 42 +- include/linux/qed/qed_nvmetcp_if.h | 17 + 21 files changed, 2186 insertions(+), 1917 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index d58e021614cd..b656408b9d70 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -877,12 +877,13 @@ u32 qed_get_hsi_def_val(struct qed_dev *cdev, enum qed_hsi_def_type type); /** - * @brief qed_concrete_to_sw_fid - get the sw function id from - * the concrete value. + * qed_concrete_to_sw_fid(): Get the sw function id from + * the concrete value. * - * @param concrete_fid + * @cdev: Qed dev pointer. + * @concrete_fid: Concrete fid. * - * @return inline u8 + * Return: inline u8. */ static inline u8 qed_concrete_to_sw_fid(struct qed_dev *cdev, u32 concrete_fid) diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.h b/drivers/net/ethernet/qlogic/qed/qed_cxt.h index 8adb7ed0c12d..d31196db7bdd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.h +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.h @@ -28,24 +28,23 @@ struct qed_tid_mem { }; /** - * @brief qedo_cid_get_cxt_info - Returns the context info for a specific cid + * qed_cxt_get_cid_info(): Returns the context info for a specific cidi. * + * @p_hwfn: HW device data. + * @p_info: In/out. * - * @param p_hwfn - * @param p_info in/out - * - * @return int + * Return: Int. */ int qed_cxt_get_cid_info(struct qed_hwfn *p_hwfn, struct qed_cxt_info *p_info); /** - * @brief qed_cxt_get_tid_mem_info + * qed_cxt_get_tid_mem_info(): Returns the tid mem info. * - * @param p_hwfn - * @param p_info + * @p_hwfn: HW device data. + * @p_info: in/out. * - * @return int + * Return: int. */ int qed_cxt_get_tid_mem_info(struct qed_hwfn *p_hwfn, struct qed_tid_mem *p_info); @@ -64,142 +63,155 @@ u32 qed_cxt_get_proto_cid_count(struct qed_hwfn *p_hwfn, enum protocol_type type, u32 *vf_cid); /** - * @brief qed_cxt_set_pf_params - Set the PF params for cxt init + * qed_cxt_set_pf_params(): Set the PF params for cxt init. + * + * @p_hwfn: HW device data. + * @rdma_tasks: Requested maximum. * - * @param p_hwfn - * @param rdma_tasks - requested maximum - * @return int + * Return: int. */ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks); /** - * @brief qed_cxt_cfg_ilt_compute - compute ILT init parameters + * qed_cxt_cfg_ilt_compute(): Compute ILT init parameters. * - * @param p_hwfn - * @param last_line + * @p_hwfn: HW device data. + * @last_line: Last_line. * - * @return int + * Return: Int */ int qed_cxt_cfg_ilt_compute(struct qed_hwfn *p_hwfn, u32 *last_line); /** - * @brief qed_cxt_cfg_ilt_compute_excess - how many lines can be decreased + * qed_cxt_cfg_ilt_compute_excess(): How many lines can be decreased. + * + * @p_hwfn: HW device data. + * @used_lines: Used lines. * - * @param p_hwfn - * @param used_lines + * Return: Int. */ u32 qed_cxt_cfg_ilt_compute_excess(struct qed_hwfn *p_hwfn, u32 used_lines); /** - * @brief qed_cxt_mngr_alloc - Allocate and init the context manager struct + * qed_cxt_mngr_alloc(): Allocate and init the context manager struct. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_cxt_mngr_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_cxt_mngr_free + * qed_cxt_mngr_free() - Context manager free. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_cxt_mngr_free(struct qed_hwfn *p_hwfn); /** - * @brief qed_cxt_tables_alloc - Allocate ILT shadow, Searcher T2, acquired map + * qed_cxt_tables_alloc(): Allocate ILT shadow, Searcher T2, acquired map. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_cxt_tables_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_cxt_mngr_setup - Reset the acquired CIDs + * qed_cxt_mngr_setup(): Reset the acquired CIDs. * - * @param p_hwfn + * @p_hwfn: HW device data. */ void qed_cxt_mngr_setup(struct qed_hwfn *p_hwfn); /** - * @brief qed_cxt_hw_init_common - Initailze ILT and DQ, common phase, per path. - * + * qed_cxt_hw_init_common(): Initailze ILT and DQ, common phase, per path. * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_cxt_hw_init_common(struct qed_hwfn *p_hwfn); /** - * @brief qed_cxt_hw_init_pf - Initailze ILT and DQ, PF phase, per path. + * qed_cxt_hw_init_pf(): Initailze ILT and DQ, PF phase, per path. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Void. */ void qed_cxt_hw_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief qed_qm_init_pf - Initailze the QM PF phase, per path + * qed_qm_init_pf(): Initailze the QM PF phase, per path. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @is_pf_loading: Is pf pending. * - * @param p_hwfn - * @param p_ptt - * @param is_pf_loading + * Return: Void. */ void qed_qm_init_pf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool is_pf_loading); /** - * @brief Reconfigures QM pf on the fly + * qed_qm_reconf(): Reconfigures QM pf on the fly. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int + * Return: Int. */ int qed_qm_reconf(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); #define QED_CXT_PF_CID (0xff) /** - * @brief qed_cxt_release - Release a cid + * qed_cxt_release_cid(): Release a cid. * - * @param p_hwfn - * @param cid + * @p_hwfn: HW device data. + * @cid: Cid. + * + * Return: Void. */ void qed_cxt_release_cid(struct qed_hwfn *p_hwfn, u32 cid); /** - * @brief qed_cxt_release - Release a cid belonging to a vf-queue + * _qed_cxt_release_cid(): Release a cid belonging to a vf-queue. + * + * @p_hwfn: HW device data. + * @cid: Cid. + * @vfid: Engine relative index. QED_CXT_PF_CID if belongs to PF. * - * @param p_hwfn - * @param cid - * @param vfid - engine relative index. QED_CXT_PF_CID if belongs to PF + * Return: Void. */ void _qed_cxt_release_cid(struct qed_hwfn *p_hwfn, u32 cid, u8 vfid); /** - * @brief qed_cxt_acquire - Acquire a new cid of a specific protocol type + * qed_cxt_acquire_cid(): Acquire a new cid of a specific protocol type. * - * @param p_hwfn - * @param type - * @param p_cid + * @p_hwfn: HW device data. + * @type: Type. + * @p_cid: Pointer cid. * - * @return int + * Return: Int. */ int qed_cxt_acquire_cid(struct qed_hwfn *p_hwfn, enum protocol_type type, u32 *p_cid); /** - * @brief _qed_cxt_acquire - Acquire a new cid of a specific protocol type - * for a vf-queue + * _qed_cxt_acquire_cid(): Acquire a new cid of a specific protocol type + * for a vf-queue. * - * @param p_hwfn - * @param type - * @param p_cid - * @param vfid - engine relative index. QED_CXT_PF_CID if belongs to PF + * @p_hwfn: HW device data. + * @type: Type. + * @p_cid: Pointer cid. + * @vfid: Engine relative index. QED_CXT_PF_CID if belongs to PF. * - * @return int + * Return: Int. */ int _qed_cxt_acquire_cid(struct qed_hwfn *p_hwfn, enum protocol_type type, u32 *p_cid, u8 vfid); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index d3c1f3879be8..f0a825b985a4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -15,44 +15,52 @@ #include "qed_int.h" /** - * @brief qed_init_dp - initialize the debug level + * qed_init_dp(): Initialize the debug level. * - * @param cdev - * @param dp_module - * @param dp_level + * @cdev: Qed dev pointer. + * @dp_module: Module debug parameter. + * @dp_level: Module debug level. + * + * Return: Void. */ void qed_init_dp(struct qed_dev *cdev, u32 dp_module, u8 dp_level); /** - * @brief qed_init_struct - initialize the device structure to - * its defaults + * qed_init_struct(): Initialize the device structure to + * its defaults. + * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: Void. */ void qed_init_struct(struct qed_dev *cdev); /** - * @brief qed_resc_free - + * qed_resc_free: Free device resources. + * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: Void. */ void qed_resc_free(struct qed_dev *cdev); /** - * @brief qed_resc_alloc - + * qed_resc_alloc(): Alloc device resources. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_resc_alloc(struct qed_dev *cdev); /** - * @brief qed_resc_setup - + * qed_resc_setup(): Setup device resources. * - * @param cdev + * @cdev: Qed dev pointer. + * + * Return: Void. */ void qed_resc_setup(struct qed_dev *cdev); @@ -105,94 +113,97 @@ struct qed_hw_init_params { }; /** - * @brief qed_hw_init - + * qed_hw_init(): Init Qed hardware. * - * @param cdev - * @param p_params + * @cdev: Qed dev pointer. + * @p_params: Pointers to params. * - * @return int + * Return: Int. */ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params); /** - * @brief qed_hw_timers_stop_all - stop the timers HW block + * qed_hw_timers_stop_all(): Stop the timers HW block. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return void + * Return: void. */ void qed_hw_timers_stop_all(struct qed_dev *cdev); /** - * @brief qed_hw_stop - + * qed_hw_stop(): Stop Qed hardware. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: int. */ int qed_hw_stop(struct qed_dev *cdev); /** - * @brief qed_hw_stop_fastpath -should be called incase - * slowpath is still required for the device, - * but fastpath is not. + * qed_hw_stop_fastpath(): Should be called incase + * slowpath is still required for the device, + * but fastpath is not. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_hw_stop_fastpath(struct qed_dev *cdev); /** - * @brief qed_hw_start_fastpath -restart fastpath traffic, - * only if hw_stop_fastpath was called + * qed_hw_start_fastpath(): Restart fastpath traffic, + * only if hw_stop_fastpath was called. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_hw_start_fastpath(struct qed_hwfn *p_hwfn); /** - * @brief qed_hw_prepare - + * qed_hw_prepare(): Prepare Qed hardware. * - * @param cdev - * @param personality - personality to initialize + * @cdev: Qed dev pointer. + * @personality: Personality to initialize. * - * @return int + * Return: Int. */ int qed_hw_prepare(struct qed_dev *cdev, int personality); /** - * @brief qed_hw_remove - + * qed_hw_remove(): Remove Qed hardware. + * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: Void. */ void qed_hw_remove(struct qed_dev *cdev); /** - * @brief qed_ptt_acquire - Allocate a PTT window + * qed_ptt_acquire(): Allocate a PTT window. * - * Should be called at the entry point to the driver (at the beginning of an - * exported function) + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: struct qed_ptt. * - * @return struct qed_ptt + * Should be called at the entry point to the driver (at the beginning of an + * exported function). */ struct qed_ptt *qed_ptt_acquire(struct qed_hwfn *p_hwfn); /** - * @brief qed_ptt_release - Release PTT Window + * qed_ptt_release(): Release PTT Window. * - * Should be called at the end of a flow - at the end of the function that - * acquired the PTT. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * + * Return: Void. * - * @param p_hwfn - * @param p_ptt + * Should be called at the end of a flow - at the end of the function that + * acquired the PTT. */ void qed_ptt_release(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); @@ -205,15 +216,17 @@ enum qed_dmae_address_type_t { }; /** - * @brief qed_dmae_host2grc - copy data from source addr to - * dmae registers using the given ptt + * qed_dmae_host2grc(): Copy data from source addr to + * dmae registers using the given ptt. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @source_addr: Source address. + * @grc_addr: GRC address (dmae_data_offset). + * @size_in_dwords: Size. + * @p_params: (default parameters will be used in case of NULL). * - * @param p_hwfn - * @param p_ptt - * @param source_addr - * @param grc_addr (dmae_data_offset) - * @param size_in_dwords - * @param p_params (default parameters will be used in case of NULL) + * Return: Int. */ int qed_dmae_host2grc(struct qed_hwfn *p_hwfn, @@ -224,29 +237,34 @@ qed_dmae_host2grc(struct qed_hwfn *p_hwfn, struct qed_dmae_params *p_params); /** - * @brief qed_dmae_grc2host - Read data from dmae data offset - * to source address using the given ptt + * qed_dmae_grc2host(): Read data from dmae data offset + * to source address using the given ptt. + * + * @p_ptt: P_ptt. + * @grc_addr: GRC address (dmae_data_offset). + * @dest_addr: Destination Address. + * @size_in_dwords: Size. + * @p_params: (default parameters will be used in case of NULL). * - * @param p_ptt - * @param grc_addr (dmae_data_offset) - * @param dest_addr - * @param size_in_dwords - * @param p_params (default parameters will be used in case of NULL) + * Return: Int. */ int qed_dmae_grc2host(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 grc_addr, dma_addr_t dest_addr, u32 size_in_dwords, struct qed_dmae_params *p_params); /** - * @brief qed_dmae_host2host - copy data from to source address - * to a destination adress (for SRIOV) using the given ptt + * qed_dmae_host2host(): Copy data from to source address + * to a destination adrress (for SRIOV) using the given + * ptt. * - * @param p_hwfn - * @param p_ptt - * @param source_addr - * @param dest_addr - * @param size_in_dwords - * @param p_params (default parameters will be used in case of NULL) + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @source_addr: Source address. + * @dest_addr: Destination address. + * @size_in_dwords: size. + * @p_params: (default parameters will be used in case of NULL). + * + * Return: Int. */ int qed_dmae_host2host(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -259,51 +277,51 @@ int qed_chain_alloc(struct qed_dev *cdev, struct qed_chain *chain, void qed_chain_free(struct qed_dev *cdev, struct qed_chain *chain); /** - * @@brief qed_fw_l2_queue - Get absolute L2 queue ID + * qed_fw_l2_queue(): Get absolute L2 queue ID. * - * @param p_hwfn - * @param src_id - relative to p_hwfn - * @param dst_id - absolute per engine + * @p_hwfn: HW device data. + * @src_id: Relative to p_hwfn. + * @dst_id: Absolute per engine. * - * @return int + * Return: Int. */ int qed_fw_l2_queue(struct qed_hwfn *p_hwfn, u16 src_id, u16 *dst_id); /** - * @@brief qed_fw_vport - Get absolute vport ID + * qed_fw_vport(): Get absolute vport ID. * - * @param p_hwfn - * @param src_id - relative to p_hwfn - * @param dst_id - absolute per engine + * @p_hwfn: HW device data. + * @src_id: Relative to p_hwfn. + * @dst_id: Absolute per engine. * - * @return int + * Return: Int. */ int qed_fw_vport(struct qed_hwfn *p_hwfn, u8 src_id, u8 *dst_id); /** - * @@brief qed_fw_rss_eng - Get absolute RSS engine ID + * qed_fw_rss_eng(): Get absolute RSS engine ID. * - * @param p_hwfn - * @param src_id - relative to p_hwfn - * @param dst_id - absolute per engine + * @p_hwfn: HW device data. + * @src_id: Relative to p_hwfn. + * @dst_id: Absolute per engine. * - * @return int + * Return: Int. */ int qed_fw_rss_eng(struct qed_hwfn *p_hwfn, u8 src_id, u8 *dst_id); /** - * @brief qed_llh_get_num_ppfid - Return the allocated number of LLH filter - * banks that are allocated to the PF. + * qed_llh_get_num_ppfid(): Return the allocated number of LLH filter + * banks that are allocated to the PF. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return u8 - Number of LLH filter banks + * Return: u8 Number of LLH filter banks. */ u8 qed_llh_get_num_ppfid(struct qed_dev *cdev); @@ -314,45 +332,50 @@ enum qed_eng { }; /** - * @brief qed_llh_set_ppfid_affinity - Set the engine affinity for the given - * LLH filter bank. + * qed_llh_set_ppfid_affinity(): Set the engine affinity for the given + * LLH filter bank. * - * @param cdev - * @param ppfid - relative within the allocated ppfids ('0' is the default one). - * @param eng + * @cdev: Qed dev pointer. + * @ppfid: Relative within the allocated ppfids ('0' is the default one). + * @eng: Engine. * - * @return int + * Return: Int. */ int qed_llh_set_ppfid_affinity(struct qed_dev *cdev, u8 ppfid, enum qed_eng eng); /** - * @brief qed_llh_set_roce_affinity - Set the RoCE engine affinity + * qed_llh_set_roce_affinity(): Set the RoCE engine affinity. * - * @param cdev - * @param eng + * @cdev: Qed dev pointer. + * @eng: Engine. * - * @return int + * Return: Int. */ int qed_llh_set_roce_affinity(struct qed_dev *cdev, enum qed_eng eng); /** - * @brief qed_llh_add_mac_filter - Add a LLH MAC filter into the given filter - * bank. + * qed_llh_add_mac_filter(): Add a LLH MAC filter into the given filter + * bank. + * + * @cdev: Qed dev pointer. + * @ppfid: Relative within the allocated ppfids ('0' is the default one). + * @mac_addr: MAC to add. * - * @param cdev - * @param ppfid - relative within the allocated ppfids ('0' is the default one). - * @param mac_addr - MAC to add + * Return: Int. */ int qed_llh_add_mac_filter(struct qed_dev *cdev, u8 ppfid, u8 mac_addr[ETH_ALEN]); /** - * @brief qed_llh_remove_mac_filter - Remove a LLH MAC filter from the given - * filter bank. + * qed_llh_remove_mac_filter(): Remove a LLH MAC filter from the given + * filter bank. * - * @param p_ptt - * @param p_filter - MAC to remove + * @cdev: Qed dev pointer. + * @ppfid: Ppfid. + * @mac_addr: MAC to remove + * + * Return: Void. */ void qed_llh_remove_mac_filter(struct qed_dev *cdev, u8 ppfid, u8 mac_addr[ETH_ALEN]); @@ -368,15 +391,16 @@ enum qed_llh_prot_filter_type_t { }; /** - * @brief qed_llh_add_protocol_filter - Add a LLH protocol filter into the - * given filter bank. + * qed_llh_add_protocol_filter(): Add a LLH protocol filter into the + * given filter bank. + * + * @cdev: Qed dev pointer. + * @ppfid: Relative within the allocated ppfids ('0' is the default one). + * @type: Type of filters and comparing. + * @source_port_or_eth_type: Source port or ethertype to add. + * @dest_port: Destination port to add. * - * @param cdev - * @param ppfid - relative within the allocated ppfids ('0' is the default one). - * @param type - type of filters and comparing - * @param source_port_or_eth_type - source port or ethertype to add - * @param dest_port - destination port to add - * @param type - type of filters and comparing + * Return: Int. */ int qed_llh_add_protocol_filter(struct qed_dev *cdev, @@ -385,14 +409,14 @@ qed_llh_add_protocol_filter(struct qed_dev *cdev, u16 source_port_or_eth_type, u16 dest_port); /** - * @brief qed_llh_remove_protocol_filter - Remove a LLH protocol filter from - * the given filter bank. + * qed_llh_remove_protocol_filter(): Remove a LLH protocol filter from + * the given filter bank. * - * @param cdev - * @param ppfid - relative within the allocated ppfids ('0' is the default one). - * @param type - type of filters and comparing - * @param source_port_or_eth_type - source port or ethertype to add - * @param dest_port - destination port to add + * @cdev: Qed dev pointer. + * @ppfid: Relative within the allocated ppfids ('0' is the default one). + * @type: Type of filters and comparing. + * @source_port_or_eth_type: Source port or ethertype to add. + * @dest_port: Destination port to add. */ void qed_llh_remove_protocol_filter(struct qed_dev *cdev, @@ -401,31 +425,31 @@ qed_llh_remove_protocol_filter(struct qed_dev *cdev, u16 source_port_or_eth_type, u16 dest_port); /** - * *@brief Cleanup of previous driver remains prior to load + * qed_final_cleanup(): Cleanup of previous driver remains prior to load. * - * @param p_hwfn - * @param p_ptt - * @param id - For PF, engine-relative. For VF, PF-relative. - * @param is_vf - true iff cleanup is made for a VF. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @id: For PF, engine-relative. For VF, PF-relative. + * @is_vf: True iff cleanup is made for a VF. * - * @return int + * Return: Int. */ int qed_final_cleanup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 id, bool is_vf); /** - * @brief qed_get_queue_coalesce - Retrieve coalesce value for a given queue. + * qed_get_queue_coalesce(): Retrieve coalesce value for a given queue. * - * @param p_hwfn - * @param p_coal - store coalesce value read from the hardware. - * @param p_handle + * @p_hwfn: HW device data. + * @coal: Store coalesce value read from the hardware. + * @handle: P_handle. * - * @return int + * Return: Int. **/ int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle); /** - * @brief qed_set_queue_coalesce - Configure coalesce parameters for Rx and + * qed_set_queue_coalesce(): Configure coalesce parameters for Rx and * Tx queue. The fact that we can configure coalescing to up to 511, but on * varying accuracy [the bigger the value the less accurate] up to a mistake * of 3usec for the highest values. @@ -433,37 +457,38 @@ int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle); * should be in same range [i.e., either 0-0x7f, 0x80-0xff or 0x100-0x1ff] * otherwise configuration would break. * + * @rx_coal: Rx Coalesce value in micro seconds. + * @tx_coal: TX Coalesce value in micro seconds. + * @p_handle: P_handle. * - * @param rx_coal - Rx Coalesce value in micro seconds. - * @param tx_coal - TX Coalesce value in micro seconds. - * @param p_handle - * - * @return int + * Return: Int. **/ int qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle); /** - * @brief qed_pglueb_set_pfid_enable - Enable or disable PCI BUS MASTER + * qed_pglueb_set_pfid_enable(): Enable or disable PCI BUS MASTER. * - * @param p_hwfn - * @param p_ptt - * @param b_enable - true/false + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @b_enable: True/False. * - * @return int + * Return: Int. */ int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_enable); /** - * @brief db_recovery_add - add doorbell information to the doorbell - * recovery mechanism. + * qed_db_recovery_add(): add doorbell information to the doorbell + * recovery mechanism. * - * @param cdev - * @param db_addr - doorbell address - * @param db_data - address of where db_data is stored - * @param db_width - doorbell is 32b pr 64b - * @param db_space - doorbell recovery addresses are user or kernel space + * @cdev: Qed dev pointer. + * @db_addr: Doorbell address. + * @db_data: Address of where db_data is stored. + * @db_width: Doorbell is 32b pr 64b. + * @db_space: Doorbell recovery addresses are user or kernel space. + * + * Return: Int. */ int qed_db_recovery_add(struct qed_dev *cdev, void __iomem *db_addr, @@ -472,13 +497,15 @@ int qed_db_recovery_add(struct qed_dev *cdev, enum qed_db_rec_space db_space); /** - * @brief db_recovery_del - remove doorbell information from the doorbell + * qed_db_recovery_del() - remove doorbell information from the doorbell * recovery mechanism. db_data serves as key (db_addr is not unique). * - * @param cdev - * @param db_addr - doorbell address - * @param db_data - address where db_data is stored. Serves as key for the + * @cdev: Qed dev pointer. + * @db_addr: doorbell address. + * @db_data: address where db_data is stored. Serves as key for the * entry to delete. + * + * Return: Int. */ int qed_db_recovery_del(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index fb1baa2da2d0..744c82a10875 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -3012,96 +3012,102 @@ struct iro { /***************************** Public Functions *******************************/ /** - * @brief qed_dbg_set_bin_ptr - Sets a pointer to the binary data with debug - * arrays. + * qed_dbg_set_bin_ptr(): Sets a pointer to the binary data with debug + * arrays. * - * @param p_hwfn - HW device data - * @param bin_ptr - a pointer to the binary data with debug arrays. + * @p_hwfn: HW device data. + * @bin_ptr: A pointer to the binary data with debug arrays. + * + * Return: enum dbg status. */ enum dbg_status qed_dbg_set_bin_ptr(struct qed_hwfn *p_hwfn, const u8 * const bin_ptr); /** - * @brief qed_read_regs - Reads registers into a buffer (using GRC). + * qed_read_regs(): Reads registers into a buffer (using GRC). + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf: Destination buffer. + * @addr: Source GRC address in dwords. + * @len: Number of registers to read. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf - Destination buffer. - * @param addr - Source GRC address in dwords. - * @param len - Number of registers to read. + * Return: Void. */ void qed_read_regs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf, u32 addr, u32 len); /** - * @brief qed_read_fw_info - Reads FW info from the chip. + * qed_read_fw_info(): Reads FW info from the chip. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @fw_info: (Out) a pointer to write the FW info into. + * + * Return: True if the FW info was read successfully from one of the Storms, + * or false if all Storms are in reset. * * The FW info contains FW-related information, such as the FW version, * FW image (main/L2B/kuku), FW timestamp, etc. * The FW info is read from the internal RAM of the first Storm that is not in * reset. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param fw_info - Out: a pointer to write the FW info into. - * - * @return true if the FW info was read successfully from one of the Storms, - * or false if all Storms are in reset. */ bool qed_read_fw_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct fw_info *fw_info); /** - * @brief qed_dbg_grc_config - Sets the value of a GRC parameter. + * qed_dbg_grc_config(): Sets the value of a GRC parameter. * - * @param p_hwfn - HW device data - * @param grc_param - GRC parameter - * @param val - Value to set. + * @p_hwfn: HW device data. + * @grc_param: GRC parameter. + * @val: Value to set. * - * @return error if one of the following holds: - * - the version wasn't set - * - grc_param is invalid - * - val is outside the allowed boundaries + * Return: Error if one of the following holds: + * - The version wasn't set. + * - Grc_param is invalid. + * - Val is outside the allowed boundaries. */ enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, enum dbg_grc_params grc_param, u32 val); /** - * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their - * default value. + * qed_dbg_grc_set_params_default(): Reverts all GRC parameters to their + * default value. + * + * @p_hwfn: HW device data. * - * @param p_hwfn - HW device data + * Return: Void. */ void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn); /** - * @brief qed_dbg_grc_get_dump_buf_size - Returns the required buffer size for - * GRC Dump. + * qed_dbg_grc_get_dump_buf_size(): Returns the required buffer size for + * GRC Dump. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for the GRC Dump - * data. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) required buffer size (in dwords) for the GRC Dump + * data. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set + * Otherwise, returns ok. */ enum dbg_status qed_dbg_grc_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_grc_dump - Dumps GRC data into the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the collected GRC data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified dump buffer is too small - * Otherwise, returns ok. + * qed_dbg_grc_dump(): Dumps GRC data into the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the collected GRC data into. + * @buf_size_in_dwords:Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * Return: Error if one of the following holds: + * - The version wasn't set. + * - The specified dump buffer is too small. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3110,36 +3116,36 @@ enum dbg_status qed_dbg_grc_dump(struct qed_hwfn *p_hwfn, u32 *num_dumped_dwords); /** - * @brief qed_dbg_idle_chk_get_dump_buf_size - Returns the required buffer size - * for idle check results. + * qed_dbg_idle_chk_get_dump_buf_size(): Returns the required buffer size + * for idle check results. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for the idle check - * data. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) required buffer size (in dwords) for the idle check + * data. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * return: Error if one of the following holds: + * - The version wasn't set. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_idle_chk_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_idle_chk_dump - Performs idle check and writes the results - * into the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the idle check data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified buffer is too small - * Otherwise, returns ok. + * qed_dbg_idle_chk_dump: Performs idle check and writes the results + * into the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the idle check data into. + * @buf_size_in_dwords: Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * Return: Error if one of the following holds: + * - The version wasn't set. + * - The specified buffer is too small. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3148,42 +3154,42 @@ enum dbg_status qed_dbg_idle_chk_dump(struct qed_hwfn *p_hwfn, u32 *num_dumped_dwords); /** - * @brief qed_dbg_mcp_trace_get_dump_buf_size - Returns the required buffer size - * for mcp trace results. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for mcp trace data. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the trace data in MCP scratchpad contain an invalid signature - * - the bundle ID in NVRAM is invalid - * - the trace meta data cannot be found (in NVRAM or image file) - * Otherwise, returns ok. + * qed_dbg_mcp_trace_get_dump_buf_size(): Returns the required buffer size + * for mcp trace results. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) Required buffer size (in dwords) for mcp trace data. + * + * Return: Error if one of the following holds: + * - The version wasn't set. + * - The trace data in MCP scratchpad contain an invalid signature. + * - The bundle ID in NVRAM is invalid. + * - The trace meta data cannot be found (in NVRAM or image file). + * Otherwise, returns ok. */ enum dbg_status qed_dbg_mcp_trace_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_mcp_trace_dump - Performs mcp trace and writes the results - * into the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the mcp trace data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified buffer is too small - * - the trace data in MCP scratchpad contain an invalid signature - * - the bundle ID in NVRAM is invalid - * - the trace meta data cannot be found (in NVRAM or image file) - * - the trace meta data cannot be read (from NVRAM or image file) - * Otherwise, returns ok. + * qed_dbg_mcp_trace_dump(): Performs mcp trace and writes the results + * into the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the mcp trace data into. + * @buf_size_in_dwords: Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * Return: Error if one of the following holds: + * - The version wasn't set. + * - The specified buffer is too small. + * - The trace data in MCP scratchpad contain an invalid signature. + * - The bundle ID in NVRAM is invalid. + * - The trace meta data cannot be found (in NVRAM or image file). + * - The trace meta data cannot be read (from NVRAM or image file). + * Otherwise, returns ok. */ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3192,36 +3198,36 @@ enum dbg_status qed_dbg_mcp_trace_dump(struct qed_hwfn *p_hwfn, u32 *num_dumped_dwords); /** - * @brief qed_dbg_reg_fifo_get_dump_buf_size - Returns the required buffer size - * for grc trace fifo results. + * qed_dbg_reg_fifo_get_dump_buf_size(): Returns the required buffer size + * for grc trace fifo results. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for reg fifo data. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) Required buffer size (in dwords) for reg fifo data. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set + * Otherwise, returns ok. */ enum dbg_status qed_dbg_reg_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_reg_fifo_dump - Reads the reg fifo and writes the results into - * the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the reg fifo data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified buffer is too small - * - DMAE transaction failed - * Otherwise, returns ok. + * qed_dbg_reg_fifo_dump(): Reads the reg fifo and writes the results into + * the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the reg fifo data into. + * @buf_size_in_dwords: Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * Return: Error if one of the following holds: + * - The version wasn't set. + * - The specified buffer is too small. + * - DMAE transaction failed. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3230,37 +3236,37 @@ enum dbg_status qed_dbg_reg_fifo_dump(struct qed_hwfn *p_hwfn, u32 *num_dumped_dwords); /** - * @brief qed_dbg_igu_fifo_get_dump_buf_size - Returns the required buffer size - * for the IGU fifo results. + * qed_dbg_igu_fifo_get_dump_buf_size(): Returns the required buffer size + * for the IGU fifo results. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for the IGU fifo - * data. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) Required buffer size (in dwords) for the IGU fifo + * data. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_igu_fifo_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_igu_fifo_dump - Reads the IGU fifo and writes the results into - * the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the IGU fifo data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified buffer is too small - * - DMAE transaction failed - * Otherwise, returns ok. + * qed_dbg_igu_fifo_dump(): Reads the IGU fifo and writes the results into + * the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the IGU fifo data into. + * @buf_size_in_dwords: Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * Return: Error if one of the following holds: + * - The version wasn't set + * - The specified buffer is too small + * - DMAE transaction failed + * Otherwise, returns ok. */ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3269,37 +3275,37 @@ enum dbg_status qed_dbg_igu_fifo_dump(struct qed_hwfn *p_hwfn, u32 *num_dumped_dwords); /** - * @brief qed_dbg_protection_override_get_dump_buf_size - Returns the required - * buffer size for protection override window results. + * qed_dbg_protection_override_get_dump_buf_size(): Returns the required + * buffer size for protection override window results. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for protection - * override data. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) Required buffer size (in dwords) for protection + * override data. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set + * Otherwise, returns ok. */ enum dbg_status qed_dbg_protection_override_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_protection_override_dump - Reads protection override window - * entries and writes the results into the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the protection override data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified buffer is too small - * - DMAE transaction failed - * Otherwise, returns ok. + * qed_dbg_protection_override_dump(): Reads protection override window + * entries and writes the results into the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the protection override data into. + * @buf_size_in_dwords: Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * @return: Error if one of the following holds: + * - The version wasn't set. + * - The specified buffer is too small. + * - DMAE transaction failed. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3307,34 +3313,34 @@ enum dbg_status qed_dbg_protection_override_dump(struct qed_hwfn *p_hwfn, u32 buf_size_in_dwords, u32 *num_dumped_dwords); /** - * @brief qed_dbg_fw_asserts_get_dump_buf_size - Returns the required buffer - * size for FW Asserts results. + * qed_dbg_fw_asserts_get_dump_buf_size(): Returns the required buffer + * size for FW Asserts results. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param buf_size - OUT: required buffer size (in dwords) for FW Asserts data. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @buf_size: (OUT) Required buffer size (in dwords) for FW Asserts data. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_fw_asserts_get_dump_buf_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *buf_size); /** - * @brief qed_dbg_fw_asserts_dump - Reads the FW Asserts and writes the results - * into the specified buffer. - * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param dump_buf - Pointer to write the FW Asserts data into. - * @param buf_size_in_dwords - Size of the specified buffer in dwords. - * @param num_dumped_dwords - OUT: number of dumped dwords. - * - * @return error if one of the following holds: - * - the version wasn't set - * - the specified buffer is too small - * Otherwise, returns ok. + * qed_dbg_fw_asserts_dump(): Reads the FW Asserts and writes the results + * into the specified buffer. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dump_buf: Pointer to write the FW Asserts data into. + * @buf_size_in_dwords: Size of the specified buffer in dwords. + * @num_dumped_dwords: (OUT) number of dumped dwords. + * + * Return: Error if one of the following holds: + * - The version wasn't set. + * - The specified buffer is too small. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_fw_asserts_dump(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3343,19 +3349,19 @@ enum dbg_status qed_dbg_fw_asserts_dump(struct qed_hwfn *p_hwfn, u32 *num_dumped_dwords); /** - * @brief qed_dbg_read_attn - Reads the attention registers of the specified + * qed_dbg_read_attn(): Reads the attention registers of the specified * block and type, and writes the results into the specified buffer. * - * @param p_hwfn - HW device data - * @param p_ptt - Ptt window used for writing the registers. - * @param block - Block ID. - * @param attn_type - Attention type. - * @param clear_status - Indicates if the attention status should be cleared. - * @param results - OUT: Pointer to write the read results into + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @block: Block ID. + * @attn_type: Attention type. + * @clear_status: Indicates if the attention status should be cleared. + * @results: (OUT) Pointer to write the read results into. * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set + * Otherwise, returns ok. */ enum dbg_status qed_dbg_read_attn(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3365,15 +3371,15 @@ enum dbg_status qed_dbg_read_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); /** - * @brief qed_dbg_print_attn - Prints attention registers values in the - * specified results struct. + * qed_dbg_print_attn(): Prints attention registers values in the + * specified results struct. * - * @param p_hwfn - * @param results - Pointer to the attention read results + * @p_hwfn: HW device data. + * @results: Pointer to the attention read results * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set + * Otherwise, returns ok. */ enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); @@ -3420,60 +3426,64 @@ struct dbg_tools_user_data { /***************************** Public Functions *******************************/ /** - * @brief qed_dbg_user_set_bin_ptr - Sets a pointer to the binary data with - * debug arrays. + * qed_dbg_user_set_bin_ptr(): Sets a pointer to the binary data with + * debug arrays. * - * @param p_hwfn - HW device data - * @param bin_ptr - a pointer to the binary data with debug arrays. + * @p_hwfn: HW device data. + * @bin_ptr: a pointer to the binary data with debug arrays. + * + * Return: dbg_status. */ enum dbg_status qed_dbg_user_set_bin_ptr(struct qed_hwfn *p_hwfn, const u8 * const bin_ptr); /** - * @brief qed_dbg_alloc_user_data - Allocates user debug data. + * qed_dbg_alloc_user_data(): Allocates user debug data. + * + * @p_hwfn: HW device data. + * @user_data_ptr: (OUT) a pointer to the allocated memory. * - * @param p_hwfn - HW device data - * @param user_data_ptr - OUT: a pointer to the allocated memory. + * Return: dbg_status. */ enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn, void **user_data_ptr); /** - * @brief qed_dbg_get_status_str - Returns a string for the specified status. + * qed_dbg_get_status_str(): Returns a string for the specified status. * - * @param status - a debug status code. + * @status: A debug status code. * - * @return a string for the specified status + * Return: A string for the specified status. */ const char *qed_dbg_get_status_str(enum dbg_status status); /** - * @brief qed_get_idle_chk_results_buf_size - Returns the required buffer size - * for idle check results (in bytes). + * qed_get_idle_chk_results_buf_size(): Returns the required buffer size + * for idle check results (in bytes). * - * @param p_hwfn - HW device data - * @param dump_buf - idle check dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed - * results. + * @p_hwfn: HW device data. + * @dump_buf: idle check dump buffer. + * @num_dumped_dwords: number of dwords that were dumped. + * @results_buf_size: (OUT) required buffer size (in bytes) for the parsed + * results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_get_idle_chk_results_buf_size(struct qed_hwfn *p_hwfn, u32 *dump_buf, u32 num_dumped_dwords, u32 *results_buf_size); /** - * @brief qed_print_idle_chk_results - Prints idle check results + * qed_print_idle_chk_results(): Prints idle check results * - * @param p_hwfn - HW device data - * @param dump_buf - idle check dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf - buffer for printing the idle check results. - * @param num_errors - OUT: number of errors found in idle check. - * @param num_warnings - OUT: number of warnings found in idle check. + * @p_hwfn: HW device data. + * @dump_buf: idle check dump buffer. + * @num_dumped_dwords: number of dwords that were dumped. + * @results_buf: buffer for printing the idle check results. + * @num_errors: (OUT) number of errors found in idle check. + * @num_warnings: (OUT) number of warnings found in idle check. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3483,28 +3493,30 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, u32 *num_warnings); /** - * @brief qed_dbg_mcp_trace_set_meta_data - Sets the MCP Trace meta data. + * qed_dbg_mcp_trace_set_meta_data(): Sets the MCP Trace meta data. + * + * @p_hwfn: HW device data. + * @meta_buf: Meta buffer. + * + * Return: Void. * * Needed in case the MCP Trace dump doesn't contain the meta data (e.g. due to * no NVRAM access). - * - * @param data - pointer to MCP Trace meta data - * @param size - size of MCP Trace meta data in dwords */ void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, const u32 *meta_buf); /** - * @brief qed_get_mcp_trace_results_buf_size - Returns the required buffer size - * for MCP Trace results (in bytes). + * qed_get_mcp_trace_results_buf_size(): Returns the required buffer size + * for MCP Trace results (in bytes). * - * @param p_hwfn - HW device data - * @param dump_buf - MCP Trace dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed - * results. + * @p_hwfn: HW device data. + * @dump_buf: MCP Trace dump buffer. + * @num_dumped_dwords: number of dwords that were dumped. + * @results_buf_size: (OUT) required buffer size (in bytes) for the parsed + * results. * - * @return error if the parsing fails, ok otherwise. + * Return: Rrror if the parsing fails, ok otherwise. */ enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3512,14 +3524,14 @@ enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size); /** - * @brief qed_print_mcp_trace_results - Prints MCP Trace results + * qed_print_mcp_trace_results(): Prints MCP Trace results * - * @param p_hwfn - HW device data - * @param dump_buf - mcp trace dump buffer, starting from the header. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf - buffer for printing the mcp trace results. + * @p_hwfn: HW device data. + * @dump_buf: MCP trace dump buffer, starting from the header. + * @num_dumped_dwords: Member of dwords that were dumped. + * @results_buf: Buffer for printing the mcp trace results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3527,30 +3539,30 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, char *results_buf); /** - * @brief qed_print_mcp_trace_results_cont - Prints MCP Trace results, and + * qed_print_mcp_trace_results_cont(): Prints MCP Trace results, and * keeps the MCP trace meta data allocated, to support continuous MCP Trace * parsing. After the continuous parsing ends, mcp_trace_free_meta_data should * be called to free the meta data. * - * @param p_hwfn - HW device data - * @param dump_buf - mcp trace dump buffer, starting from the header. - * @param results_buf - buffer for printing the mcp trace results. + * @p_hwfn: HW device data. + * @dump_buf: MVP trace dump buffer, starting from the header. + * @results_buf: Buffer for printing the mcp trace results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, u32 *dump_buf, char *results_buf); /** - * @brief print_mcp_trace_line - Prints MCP Trace results for a single line + * qed_print_mcp_trace_line(): Prints MCP Trace results for a single line * - * @param p_hwfn - HW device data - * @param dump_buf - mcp trace dump buffer, starting from the header. - * @param num_dumped_bytes - number of bytes that were dumped. - * @param results_buf - buffer for printing the mcp trace results. + * @p_hwfn: HW device data. + * @dump_buf: MCP trace dump buffer, starting from the header. + * @num_dumped_bytes: Number of bytes that were dumped. + * @results_buf: Buffer for printing the mcp trace results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, u8 *dump_buf, @@ -3558,24 +3570,26 @@ enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, char *results_buf); /** - * @brief mcp_trace_free_meta_data - Frees the MCP Trace meta data. + * qed_mcp_trace_free_meta_data(): Frees the MCP Trace meta data. * Should be called after continuous MCP Trace parsing. * - * @param p_hwfn - HW device data + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn); /** - * @brief qed_get_reg_fifo_results_buf_size - Returns the required buffer size - * for reg_fifo results (in bytes). + * qed_get_reg_fifo_results_buf_size(): Returns the required buffer size + * for reg_fifo results (in bytes). * - * @param p_hwfn - HW device data - * @param dump_buf - reg fifo dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed - * results. + * @p_hwfn: HW device data. + * @dump_buf: Reg fifo dump buffer. + * @num_dumped_dwords: Number of dwords that were dumped. + * @results_buf_size: (OUT) required buffer size (in bytes) for the parsed + * results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3583,14 +3597,14 @@ enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size); /** - * @brief qed_print_reg_fifo_results - Prints reg fifo results + * qed_print_reg_fifo_results(): Prints reg fifo results. * - * @param p_hwfn - HW device data - * @param dump_buf - reg fifo dump buffer, starting from the header. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf - buffer for printing the reg fifo results. + * @p_hwfn: HW device data. + * @dump_buf: Reg fifo dump buffer, starting from the header. + * @num_dumped_dwords: Number of dwords that were dumped. + * @results_buf: Buffer for printing the reg fifo results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_reg_fifo_results(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3598,16 +3612,16 @@ enum dbg_status qed_print_reg_fifo_results(struct qed_hwfn *p_hwfn, char *results_buf); /** - * @brief qed_get_igu_fifo_results_buf_size - Returns the required buffer size - * for igu_fifo results (in bytes). + * qed_get_igu_fifo_results_buf_size(): Returns the required buffer size + * for igu_fifo results (in bytes). * - * @param p_hwfn - HW device data - * @param dump_buf - IGU fifo dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed - * results. + * @p_hwfn: HW device data. + * @dump_buf: IGU fifo dump buffer. + * @num_dumped_dwords: number of dwords that were dumped. + * @results_buf_size: (OUT) required buffer size (in bytes) for the parsed + * results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_get_igu_fifo_results_buf_size(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3615,14 +3629,14 @@ enum dbg_status qed_get_igu_fifo_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size); /** - * @brief qed_print_igu_fifo_results - Prints IGU fifo results + * qed_print_igu_fifo_results(): Prints IGU fifo results * - * @param p_hwfn - HW device data - * @param dump_buf - IGU fifo dump buffer, starting from the header. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf - buffer for printing the IGU fifo results. + * @p_hwfn: HW device data. + * @dump_buf: IGU fifo dump buffer, starting from the header. + * @num_dumped_dwords: Number of dwords that were dumped. + * @results_buf: Buffer for printing the IGU fifo results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_igu_fifo_results(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3630,16 +3644,16 @@ enum dbg_status qed_print_igu_fifo_results(struct qed_hwfn *p_hwfn, char *results_buf); /** - * @brief qed_get_protection_override_results_buf_size - Returns the required - * buffer size for protection override results (in bytes). + * qed_get_protection_override_results_buf_size(): Returns the required + * buffer size for protection override results (in bytes). * - * @param p_hwfn - HW device data - * @param dump_buf - protection override dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed - * results. + * @p_hwfn: HW device data. + * @dump_buf: Protection override dump buffer. + * @num_dumped_dwords: Number of dwords that were dumped. + * @results_buf_size: (OUT) required buffer size (in bytes) for the parsed + * results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_get_protection_override_results_buf_size(struct qed_hwfn *p_hwfn, @@ -3648,15 +3662,15 @@ qed_get_protection_override_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size); /** - * @brief qed_print_protection_override_results - Prints protection override - * results. + * qed_print_protection_override_results(): Prints protection override + * results. * - * @param p_hwfn - HW device data - * @param dump_buf - protection override dump buffer, starting from the header. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf - buffer for printing the reg fifo results. + * @p_hwfn: HW device data. + * @dump_buf: Protection override dump buffer, starting from the header. + * @num_dumped_dwords: Number of dwords that were dumped. + * @results_buf: Buffer for printing the reg fifo results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_protection_override_results(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3664,16 +3678,16 @@ enum dbg_status qed_print_protection_override_results(struct qed_hwfn *p_hwfn, char *results_buf); /** - * @brief qed_get_fw_asserts_results_buf_size - Returns the required buffer size - * for FW Asserts results (in bytes). + * qed_get_fw_asserts_results_buf_size(): Returns the required buffer size + * for FW Asserts results (in bytes). * - * @param p_hwfn - HW device data - * @param dump_buf - FW Asserts dump buffer. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf_size - OUT: required buffer size (in bytes) for the parsed - * results. + * @p_hwfn: HW device data. + * @dump_buf: FW Asserts dump buffer. + * @num_dumped_dwords: number of dwords that were dumped. + * @results_buf_size: (OUT) required buffer size (in bytes) for the parsed + * results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_get_fw_asserts_results_buf_size(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3681,14 +3695,14 @@ enum dbg_status qed_get_fw_asserts_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size); /** - * @brief qed_print_fw_asserts_results - Prints FW Asserts results + * qed_print_fw_asserts_results(): Prints FW Asserts results. * - * @param p_hwfn - HW device data - * @param dump_buf - FW Asserts dump buffer, starting from the header. - * @param num_dumped_dwords - number of dwords that were dumped. - * @param results_buf - buffer for printing the FW Asserts results. + * @p_hwfn: HW device data. + * @dump_buf: FW Asserts dump buffer, starting from the header. + * @num_dumped_dwords: number of dwords that were dumped. + * @results_buf: buffer for printing the FW Asserts results. * - * @return error if the parsing fails, ok otherwise. + * Return: Error if the parsing fails, ok otherwise. */ enum dbg_status qed_print_fw_asserts_results(struct qed_hwfn *p_hwfn, u32 *dump_buf, @@ -3696,15 +3710,15 @@ enum dbg_status qed_print_fw_asserts_results(struct qed_hwfn *p_hwfn, char *results_buf); /** - * @brief qed_dbg_parse_attn - Parses and prints attention registers values in - * the specified results struct. + * qed_dbg_parse_attn(): Parses and prints attention registers values in + * the specified results struct. * - * @param p_hwfn - HW device data - * @param results - Pointer to the attention read results + * @p_hwfn: HW device data. + * @results: Pointer to the attention read results * - * @return error if one of the following holds: - * - the version wasn't set - * Otherwise, returns ok. + * Return: Error if one of the following holds: + * - The version wasn't set. + * Otherwise, returns ok. */ enum dbg_status qed_dbg_parse_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); @@ -3746,18 +3760,18 @@ enum dbg_status qed_dbg_parse_attn(struct qed_hwfn *p_hwfn, #define GTT_BAR0_MAP_REG_PSDM_RAM 0x01a000UL /** - * @brief qed_qm_pf_mem_size - prepare QM ILT sizes + * qed_qm_pf_mem_size(): Prepare QM ILT sizes. * - * Returns the required host memory size in 4KB units. - * Must be called before all QM init HSI functions. + * @num_pf_cids: Number of connections used by this PF. + * @num_vf_cids: Number of connections used by VFs of this PF. + * @num_tids: Number of tasks used by this PF. + * @num_pf_pqs: Number of PQs used by this PF. + * @num_vf_pqs: Number of PQs used by VFs of this PF. * - * @param num_pf_cids - number of connections used by this PF - * @param num_vf_cids - number of connections used by VFs of this PF - * @param num_tids - number of tasks used by this PF - * @param num_pf_pqs - number of PQs used by this PF - * @param num_vf_pqs - number of PQs used by VFs of this PF + * Return: The required host memory size in 4KB units. * - * @return The required host memory size in 4KB units. + * Returns the required host memory size in 4KB units. + * Must be called before all QM init HSI functions. */ u32 qed_qm_pf_mem_size(u32 num_pf_cids, u32 num_vf_cids, @@ -3800,74 +3814,74 @@ int qed_qm_pf_rt_init(struct qed_hwfn *p_hwfn, struct qed_qm_pf_rt_init_params *p_params); /** - * @brief qed_init_pf_wfq - Initializes the WFQ weight of the specified PF + * qed_init_pf_wfq(): Initializes the WFQ weight of the specified PF. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers - * @param pf_id - PF ID - * @param pf_wfq - WFQ weight. Must be non-zero. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers + * @pf_id: PF ID + * @pf_wfq: WFQ weight. Must be non-zero. * - * @return 0 on success, -1 on error. + * Return: 0 on success, -1 on error. */ int qed_init_pf_wfq(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 pf_id, u16 pf_wfq); /** - * @brief qed_init_pf_rl - Initializes the rate limit of the specified PF + * qed_init_pf_rl(): Initializes the rate limit of the specified PF * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers - * @param pf_id - PF ID - * @param pf_rl - rate limit in Mb/sec units + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @pf_id: PF ID. + * @pf_rl: rate limit in Mb/sec units * - * @return 0 on success, -1 on error. + * Return: 0 on success, -1 on error. */ int qed_init_pf_rl(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 pf_id, u32 pf_rl); /** - * @brief qed_init_vport_wfq Initializes the WFQ weight of the specified VPORT + * qed_init_vport_wfq(): Initializes the WFQ weight of the specified VPORT * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers - * @param first_tx_pq_id- An array containing the first Tx PQ ID associated - * with the VPORT for each TC. This array is filled by - * qed_qm_pf_rt_init - * @param vport_wfq - WFQ weight. Must be non-zero. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers + * @first_tx_pq_id: An array containing the first Tx PQ ID associated + * with the VPORT for each TC. This array is filled by + * qed_qm_pf_rt_init + * @wfq: WFQ weight. Must be non-zero. * - * @return 0 on success, -1 on error. + * Return: 0 on success, -1 on error. */ int qed_init_vport_wfq(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 first_tx_pq_id[NUM_OF_TCS], u16 wfq); /** - * @brief qed_init_global_rl - Initializes the rate limit of the specified - * rate limiter + * qed_init_global_rl(): Initializes the rate limit of the specified + * rate limiter. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers - * @param rl_id - RL ID - * @param rate_limit - rate limit in Mb/sec units + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @rl_id: RL ID. + * @rate_limit: Rate limit in Mb/sec units * - * @return 0 on success, -1 on error. + * Return: 0 on success, -1 on error. */ int qed_init_global_rl(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 rl_id, u32 rate_limit); /** - * @brief qed_send_qm_stop_cmd Sends a stop command to the QM + * qed_send_qm_stop_cmd(): Sends a stop command to the QM. * - * @param p_hwfn - * @param p_ptt - * @param is_release_cmd - true for release, false for stop. - * @param is_tx_pq - true for Tx PQs, false for Other PQs. - * @param start_pq - first PQ ID to stop - * @param num_pqs - Number of PQs to stop, starting from start_pq. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @is_release_cmd: true for release, false for stop. + * @is_tx_pq: true for Tx PQs, false for Other PQs. + * @start_pq: first PQ ID to stop + * @num_pqs: Number of PQs to stop, starting from start_pq. * - * @return bool, true if successful, false if timeout occurred while waiting for - * QM command done. + * Return: Bool, true if successful, false if timeout occurred while waiting + * for QM command done. */ bool qed_send_qm_stop_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3875,53 +3889,64 @@ bool qed_send_qm_stop_cmd(struct qed_hwfn *p_hwfn, bool is_tx_pq, u16 start_pq, u16 num_pqs); /** - * @brief qed_set_vxlan_dest_port - initializes vxlan tunnel destination udp port + * qed_set_vxlan_dest_port(): Initializes vxlan tunnel destination udp port. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers. - * @param dest_port - vxlan destination udp port. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dest_port: vxlan destination udp port. + * + * Return: Void. */ void qed_set_vxlan_dest_port(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 dest_port); /** - * @brief qed_set_vxlan_enable - enable or disable VXLAN tunnel in HW + * qed_set_vxlan_enable(): Enable or disable VXLAN tunnel in HW. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @vxlan_enable: vxlan enable flag. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers. - * @param vxlan_enable - vxlan enable flag. + * Return: Void. */ void qed_set_vxlan_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool vxlan_enable); /** - * @brief qed_set_gre_enable - enable or disable GRE tunnel in HW + * qed_set_gre_enable(): Enable or disable GRE tunnel in HW. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @eth_gre_enable: Eth GRE enable flag. + * @ip_gre_enable: IP GRE enable flag. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers. - * @param eth_gre_enable - eth GRE enable enable flag. - * @param ip_gre_enable - IP GRE enable enable flag. + * Return: Void. */ void qed_set_gre_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool eth_gre_enable, bool ip_gre_enable); /** - * @brief qed_set_geneve_dest_port - initializes geneve tunnel destination udp port + * qed_set_geneve_dest_port(): Initializes geneve tunnel destination udp port * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers. - * @param dest_port - geneve destination udp port. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @dest_port: Geneve destination udp port. + * + * Retur: Void. */ void qed_set_geneve_dest_port(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 dest_port); /** - * @brief qed_set_gre_enable - enable or disable GRE tunnel in HW + * qed_set_geneve_enable(): Enable or disable GRE tunnel in HW. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @eth_geneve_enable: Eth GENEVE enable flag. + * @ip_geneve_enable: IP GENEVE enable flag. * - * @param p_ptt - ptt window used for writing the registers. - * @param eth_geneve_enable - eth GENEVE enable enable flag. - * @param ip_geneve_enable - IP GENEVE enable enable flag. + * Return: Void. */ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3931,25 +3956,29 @@ void qed_set_vxlan_no_l2_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool enable); /** - * @brief qed_gft_disable - Disable GFT + * qed_gft_disable(): Disable GFT. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @pf_id: PF on which to disable GFT. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers. - * @param pf_id - pf on which to disable GFT. + * Return: Void. */ void qed_gft_disable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 pf_id); /** - * @brief qed_gft_config - Enable and configure HW for GFT - * - * @param p_hwfn - HW device data - * @param p_ptt - ptt window used for writing the registers. - * @param pf_id - pf on which to enable GFT. - * @param tcp - set profile tcp packets. - * @param udp - set profile udp packet. - * @param ipv4 - set profile ipv4 packet. - * @param ipv6 - set profile ipv6 packet. - * @param profile_type - define packet same fields. Use enum gft_profile_type. + * qed_gft_config(): Enable and configure HW for GFT. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @pf_id: PF on which to enable GFT. + * @tcp: Set profile tcp packets. + * @udp: Set profile udp packet. + * @ipv4: Set profile ipv4 packet. + * @ipv6: Set profile ipv6 packet. + * @profile_type: Define packet same fields. Use enum gft_profile_type. + * + * Return: Void. */ void qed_gft_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -3959,107 +3988,120 @@ void qed_gft_config(struct qed_hwfn *p_hwfn, bool ipv4, bool ipv6, enum gft_profile_type profile_type); /** - * @brief qed_enable_context_validation - Enable and configure context - * validation. + * qed_enable_context_validation(): Enable and configure context + * validation. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. * - * @param p_hwfn - * @param p_ptt - ptt window used for writing the registers. + * Return: Void. */ void qed_enable_context_validation(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief qed_calc_session_ctx_validation - Calcualte validation byte for - * session context. + * qed_calc_session_ctx_validation(): Calcualte validation byte for + * session context. * - * @param p_ctx_mem - pointer to context memory. - * @param ctx_size - context size. - * @param ctx_type - context type. - * @param cid - context cid. + * @p_ctx_mem: Pointer to context memory. + * @ctx_size: Context size. + * @ctx_type: Context type. + * @cid: Context cid. + * + * Return: Void. */ void qed_calc_session_ctx_validation(void *p_ctx_mem, u16 ctx_size, u8 ctx_type, u32 cid); /** - * @brief qed_calc_task_ctx_validation - Calcualte validation byte for task - * context. + * qed_calc_task_ctx_validation(): Calcualte validation byte for task + * context. + * + * @p_ctx_mem: Pointer to context memory. + * @ctx_size: Context size. + * @ctx_type: Context type. + * @tid: Context tid. * - * @param p_ctx_mem - pointer to context memory. - * @param ctx_size - context size. - * @param ctx_type - context type. - * @param tid - context tid. + * Return: Void. */ void qed_calc_task_ctx_validation(void *p_ctx_mem, u16 ctx_size, u8 ctx_type, u32 tid); /** - * @brief qed_memset_session_ctx - Memset session context to 0 while - * preserving validation bytes. + * qed_memset_session_ctx(): Memset session context to 0 while + * preserving validation bytes. + * + * @p_ctx_mem: Pointer to context memory. + * @ctx_size: Size to initialzie. + * @ctx_type: Context type. * - * @param p_hwfn - - * @param p_ctx_mem - pointer to context memory. - * @param ctx_size - size to initialzie. - * @param ctx_type - context type. + * Return: Void. */ void qed_memset_session_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type); /** - * @brief qed_memset_task_ctx - Memset task context to 0 while preserving - * validation bytes. + * qed_memset_task_ctx(): Memset task context to 0 while preserving + * validation bytes. * - * @param p_ctx_mem - pointer to context memory. - * @param ctx_size - size to initialzie. - * @param ctx_type - context type. + * @p_ctx_mem: Pointer to context memory. + * @ctx_size: size to initialzie. + * @ctx_type: context type. + * + * Return: Void. */ void qed_memset_task_ctx(void *p_ctx_mem, u32 ctx_size, u8 ctx_type); #define NUM_STORMS 6 /** - * @brief qed_set_rdma_error_level - Sets the RDMA assert level. - * If the severity of the error will be - * above the level, the FW will assert. - * @param p_hwfn - HW device data - * @param p_ptt - ptt window used for writing the registers - * @param assert_level - An array of assert levels for each storm. + * qed_set_rdma_error_level(): Sets the RDMA assert level. + * If the severity of the error will be + * above the level, the FW will assert. + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @assert_level: An array of assert levels for each storm. * + * Return: Void. */ void qed_set_rdma_error_level(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 assert_level[NUM_STORMS]); /** - * @brief qed_fw_overlay_mem_alloc - Allocates and fills the FW overlay memory. + * qed_fw_overlay_mem_alloc(): Allocates and fills the FW overlay memory. * - * @param p_hwfn - HW device data - * @param fw_overlay_in_buf - the input FW overlay buffer. - * @param buf_size - the size of the input FW overlay buffer in bytes. - * must be aligned to dwords. - * @param fw_overlay_out_mem - OUT: a pointer to the allocated overlays memory. + * @p_hwfn: HW device data. + * @fw_overlay_in_buf: The input FW overlay buffer. + * @buf_size_in_bytes: The size of the input FW overlay buffer in bytes. + * must be aligned to dwords. * - * @return a pointer to the allocated overlays memory, + * Return: A pointer to the allocated overlays memory, * or NULL in case of failures. */ struct phys_mem_desc * qed_fw_overlay_mem_alloc(struct qed_hwfn *p_hwfn, - const u32 * const fw_overlay_in_buf, + const u32 *const fw_overlay_in_buf, u32 buf_size_in_bytes); /** - * @brief qed_fw_overlay_init_ram - Initializes the FW overlay RAM. + * qed_fw_overlay_init_ram(): Initializes the FW overlay RAM. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @fw_overlay_mem: the allocated FW overlay memory. * - * @param p_hwfn - HW device data. - * @param p_ptt - ptt window used for writing the registers. - * @param fw_overlay_mem - the allocated FW overlay memory. + * Return: Void. */ void qed_fw_overlay_init_ram(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct phys_mem_desc *fw_overlay_mem); /** - * @brief qed_fw_overlay_mem_free - Frees the FW overlay memory. + * qed_fw_overlay_mem_free(): Frees the FW overlay memory. + * + * @p_hwfn: HW device data. + * @fw_overlay_mem: The allocated FW overlay memory to free. * - * @param p_hwfn - HW device data. - * @param fw_overlay_mem - the allocated FW overlay memory to free. + * Return: Void. */ void qed_fw_overlay_mem_free(struct qed_hwfn *p_hwfn, struct phys_mem_desc *fw_overlay_mem); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.h b/drivers/net/ethernet/qlogic/qed/qed_hw.h index 2734f49956f7..e535983ce21b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hw.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hw.h @@ -53,85 +53,94 @@ enum _dmae_cmd_crc_mask { #define DMAE_MAX_CLIENTS 32 /** - * @brief qed_gtt_init - Initialize GTT windows + * qed_gtt_init(): Initialize GTT windows. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_gtt_init(struct qed_hwfn *p_hwfn); /** - * @brief qed_ptt_invalidate - Forces all ptt entries to be re-configured + * qed_ptt_invalidate(): Forces all ptt entries to be re-configured + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_ptt_invalidate(struct qed_hwfn *p_hwfn); /** - * @brief qed_ptt_pool_alloc - Allocate and initialize PTT pool + * qed_ptt_pool_alloc(): Allocate and initialize PTT pool. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return struct _qed_status - success (0), negative - error. + * Return: struct _qed_status - success (0), negative - error. */ int qed_ptt_pool_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_ptt_pool_free - + * qed_ptt_pool_free(): Free PTT pool. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_ptt_pool_free(struct qed_hwfn *p_hwfn); /** - * @brief qed_ptt_get_hw_addr - Get PTT's GRC/HW address + * qed_ptt_get_hw_addr(): Get PTT's GRC/HW address. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt * - * @return u32 + * Return: u32. */ u32 qed_ptt_get_hw_addr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief qed_ptt_get_bar_addr - Get PPT's external BAR address + * qed_ptt_get_bar_addr(): Get PPT's external BAR address. * - * @param p_hwfn - * @param p_ptt + * @p_ptt: P_ptt * - * @return u32 + * Return: u32. */ u32 qed_ptt_get_bar_addr(struct qed_ptt *p_ptt); /** - * @brief qed_ptt_set_win - Set PTT Window's GRC BAR address + * qed_ptt_set_win(): Set PTT Window's GRC BAR address * - * @param p_hwfn - * @param new_hw_addr - * @param p_ptt + * @p_hwfn: HW device data. + * @new_hw_addr: New HW address. + * @p_ptt: P_Ptt + * + * Return: Void. */ void qed_ptt_set_win(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 new_hw_addr); /** - * @brief qed_get_reserved_ptt - Get a specific reserved PTT + * qed_get_reserved_ptt(): Get a specific reserved PTT. * - * @param p_hwfn - * @param ptt_idx + * @p_hwfn: HW device data. + * @ptt_idx: Ptt Index. * - * @return struct qed_ptt * + * Return: struct qed_ptt *. */ struct qed_ptt *qed_get_reserved_ptt(struct qed_hwfn *p_hwfn, enum reserved_ptts ptt_idx); /** - * @brief qed_wr - Write value to BAR using the given ptt + * qed_wr(): Write value to BAR using the given ptt. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @val: Val. + * @hw_addr: HW address * - * @param p_hwfn - * @param p_ptt - * @param val - * @param hw_addr + * Return: Void. */ void qed_wr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -139,26 +148,28 @@ void qed_wr(struct qed_hwfn *p_hwfn, u32 val); /** - * @brief qed_rd - Read value from BAR using the given ptt + * qed_rd(): Read value from BAR using the given ptt. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @hw_addr: HW address * - * @param p_hwfn - * @param p_ptt - * @param val - * @param hw_addr + * Return: Void. */ u32 qed_rd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 hw_addr); /** - * @brief qed_memcpy_from - copy n bytes from BAR using the given - * ptt - * - * @param p_hwfn - * @param p_ptt - * @param dest - * @param hw_addr - * @param n + * qed_memcpy_from(): Copy n bytes from BAR using the given ptt. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @dest: Destination. + * @hw_addr: HW address. + * @n: N + * + * Return: Void. */ void qed_memcpy_from(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -167,14 +178,15 @@ void qed_memcpy_from(struct qed_hwfn *p_hwfn, size_t n); /** - * @brief qed_memcpy_to - copy n bytes to BAR using the given - * ptt - * - * @param p_hwfn - * @param p_ptt - * @param hw_addr - * @param src - * @param n + * qed_memcpy_to(): Copy n bytes to BAR using the given ptt + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @hw_addr: HW address. + * @src: Source. + * @n: N + * + * Return: Void. */ void qed_memcpy_to(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -182,83 +194,97 @@ void qed_memcpy_to(struct qed_hwfn *p_hwfn, void *src, size_t n); /** - * @brief qed_fid_pretend - pretend to another function when - * accessing the ptt window. There is no way to unpretend - * a function. The only way to cancel a pretend is to - * pretend back to the original function. - * - * @param p_hwfn - * @param p_ptt - * @param fid - fid field of pxp_pretend structure. Can contain - * either pf / vf, port/path fields are don't care. + * qed_fid_pretend(): pretend to another function when + * accessing the ptt window. There is no way to unpretend + * a function. The only way to cancel a pretend is to + * pretend back to the original function. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @fid: fid field of pxp_pretend structure. Can contain + * either pf / vf, port/path fields are don't care. + * + * Return: Void. */ void qed_fid_pretend(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 fid); /** - * @brief qed_port_pretend - pretend to another port when - * accessing the ptt window + * qed_port_pretend(): Pretend to another port when accessing the ptt window * - * @param p_hwfn - * @param p_ptt - * @param port_id - the port to pretend to + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @port_id: The port to pretend to + * + * Return: Void. */ void qed_port_pretend(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 port_id); /** - * @brief qed_port_unpretend - cancel any previously set port - * pretend + * qed_port_unpretend(): Cancel any previously set port pretend + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param p_hwfn - * @param p_ptt + * Return: Void. */ void qed_port_unpretend(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief qed_port_fid_pretend - pretend to another port and another function - * when accessing the ptt window + * qed_port_fid_pretend(): Pretend to another port and another function + * when accessing the ptt window + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @port_id: The port to pretend to + * @fid: fid field of pxp_pretend structure. Can contain either pf / vf. * - * @param p_hwfn - * @param p_ptt - * @param port_id - the port to pretend to - * @param fid - fid field of pxp_pretend structure. Can contain either pf / vf. + * Return: Void. */ void qed_port_fid_pretend(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 port_id, u16 fid); /** - * @brief qed_vfid_to_concrete - build a concrete FID for a - * given VF ID + * qed_vfid_to_concrete(): Build a concrete FID for a given VF ID * - * @param p_hwfn - * @param p_ptt - * @param vfid + * @p_hwfn: HW device data. + * @vfid: VFID. + * + * Return: Void. */ u32 qed_vfid_to_concrete(struct qed_hwfn *p_hwfn, u8 vfid); /** - * @brief qed_dmae_idx_to_go_cmd - map the idx to dmae cmd - * this is declared here since other files will require it. - * @param idx + * qed_dmae_idx_to_go_cmd(): Map the idx to dmae cmd + * this is declared here since other files will require it. + * + * @idx: Index + * + * Return: Void. */ u32 qed_dmae_idx_to_go_cmd(u8 idx); /** - * @brief qed_dmae_info_alloc - Init the dmae_info structure - * which is part of p_hwfn. - * @param p_hwfn + * qed_dmae_info_alloc(): Init the dmae_info structure + * which is part of p_hwfn. + * + * @p_hwfn: HW device data. + * + * Return: Int. */ int qed_dmae_info_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_dmae_info_free - Free the dmae_info structure - * which is part of p_hwfn + * qed_dmae_info_free(): Free the dmae_info structure + * which is part of p_hwfn. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_dmae_info_free(struct qed_hwfn *p_hwfn); @@ -292,14 +318,16 @@ int qed_dmae_sanity(struct qed_hwfn *p_hwfn, #define QED_HW_ERR_MAX_STR_SIZE 256 /** - * @brief qed_hw_err_notify - Notify upper layer driver and management FW - * about a HW error. - * - * @param p_hwfn - * @param p_ptt - * @param err_type - * @param fmt - debug data buffer to send to the MFW - * @param ... - buffer format args + * qed_hw_err_notify(): Notify upper layer driver and management FW + * about a HW error. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @err_type: Err Type. + * @fmt: Debug data buffer to send to the MFW + * @...: buffer format args + * + * Return void. */ void __printf(4, 5) __cold qed_hw_err_notify(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.h b/drivers/net/ethernet/qlogic/qed/qed_init_ops.h index a573c8921982..1dbc460c9eec 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.h +++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.h @@ -12,23 +12,24 @@ #include "qed.h" /** - * @brief qed_init_iro_array - init iro_arr. + * qed_init_iro_array(): init iro_arr. * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: Void. */ void qed_init_iro_array(struct qed_dev *cdev); /** - * @brief qed_init_run - Run the init-sequence. + * qed_init_run(): Run the init-sequence. * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @phase: Phase. + * @phase_id: Phase ID. + * @modes: Mode. * - * @param p_hwfn - * @param p_ptt - * @param phase - * @param phase_id - * @param modes - * @return _qed_status_t + * Return: _qed_status_t */ int qed_init_run(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -37,30 +38,31 @@ int qed_init_run(struct qed_hwfn *p_hwfn, int modes); /** - * @brief qed_init_hwfn_allocate - Allocate RT array, Store 'values' ptrs. + * qed_init_alloc(): Allocate RT array, Store 'values' ptrs. * + * @p_hwfn: HW device data. * - * @param p_hwfn - * - * @return _qed_status_t + * Return: _qed_status_t. */ int qed_init_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_init_hwfn_deallocate + * qed_init_free(): Init HW function deallocate. * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_init_free(struct qed_hwfn *p_hwfn); /** - * @brief qed_init_store_rt_reg - Store a configuration value in the RT array. + * qed_init_store_rt_reg(): Store a configuration value in the RT array. * + * @p_hwfn: HW device data. + * @rt_offset: RT offset. + * @val: Val. * - * @param p_hwfn - * @param rt_offset - * @param val + * Return: Void. */ void qed_init_store_rt_reg(struct qed_hwfn *p_hwfn, u32 rt_offset, @@ -72,15 +74,6 @@ void qed_init_store_rt_reg(struct qed_hwfn *p_hwfn, #define OVERWRITE_RT_REG(hwfn, offset, val) \ qed_init_store_rt_reg(hwfn, offset, val) -/** - * @brief - * - * - * @param p_hwfn - * @param rt_offset - * @param val - * @param size - */ void qed_init_store_rt_agg(struct qed_hwfn *p_hwfn, u32 rt_offset, u32 *val, @@ -90,11 +83,12 @@ void qed_init_store_rt_agg(struct qed_hwfn *p_hwfn, qed_init_store_rt_agg(hwfn, offset, (u32 *)&val, sizeof(val)) /** - * @brief - * Initialize GTT global windows and set admin window - * related params of GTT/PTT to default values. + * qed_gtt_init(): Initialize GTT global windows and set admin window + * related params of GTT/PTT to default values. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return Void. */ void qed_gtt_init(struct qed_hwfn *p_hwfn); #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index c5550e96bbe1..eb8e0f4242d7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -53,51 +53,54 @@ enum qed_coalescing_fsm { }; /** - * @brief qed_int_igu_enable_int - enable device interrupts + * qed_int_igu_enable_int(): Enable device interrupts. * - * @param p_hwfn - * @param p_ptt - * @param int_mode - interrupt mode to use + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @int_mode: Interrupt mode to use. + * + * Return: Void. */ void qed_int_igu_enable_int(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_int_mode int_mode); /** - * @brief qed_int_igu_disable_int - disable device interrupts + * qed_int_igu_disable_int(): Disable device interrupts. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param p_hwfn - * @param p_ptt + * Return: Void. */ void qed_int_igu_disable_int(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief qed_int_igu_read_sisr_reg - Reads the single isr multiple dpc - * register from igu. + * qed_int_igu_read_sisr_reg(): Reads the single isr multiple dpc + * register from igu. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return u64 + * Return: u64. */ u64 qed_int_igu_read_sisr_reg(struct qed_hwfn *p_hwfn); #define QED_SP_SB_ID 0xffff /** - * @brief qed_int_sb_init - Initializes the sb_info structure. + * qed_int_sb_init(): Initializes the sb_info structure. * - * once the structure is initialized it can be passed to sb related functions. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @sb_info: points to an uninitialized (but allocated) sb_info structure + * @sb_virt_addr: SB Virtual address. + * @sb_phy_addr: SB Physial address. + * @sb_id: the sb_id to be used (zero based in driver) + * should use QED_SP_SB_ID for SP Status block * - * @param p_hwfn - * @param p_ptt - * @param sb_info points to an uninitialized (but - * allocated) sb_info structure - * @param sb_virt_addr - * @param sb_phy_addr - * @param sb_id the sb_id to be used (zero based in driver) - * should use QED_SP_SB_ID for SP Status block + * Return: int. * - * @return int + * Once the structure is initialized it can be passed to sb related functions. */ int qed_int_sb_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -106,82 +109,91 @@ int qed_int_sb_init(struct qed_hwfn *p_hwfn, dma_addr_t sb_phy_addr, u16 sb_id); /** - * @brief qed_int_sb_setup - Setup the sb. + * qed_int_sb_setup(): Setup the sb. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @sb_info: Initialized sb_info structure. * - * @param p_hwfn - * @param p_ptt - * @param sb_info initialized sb_info structure + * Return: Void. */ void qed_int_sb_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_sb_info *sb_info); /** - * @brief qed_int_sb_release - releases the sb_info structure. + * qed_int_sb_release(): Releases the sb_info structure. * - * once the structure is released, it's memory can be freed + * @p_hwfn: HW device data. + * @sb_info: Points to an allocated sb_info structure. + * @sb_id: The sb_id to be used (zero based in driver) + * should never be equal to QED_SP_SB_ID + * (SP Status block). * - * @param p_hwfn - * @param sb_info points to an allocated sb_info structure - * @param sb_id the sb_id to be used (zero based in driver) - * should never be equal to QED_SP_SB_ID - * (SP Status block) + * Return: int. * - * @return int + * Once the structure is released, it's memory can be freed. */ int qed_int_sb_release(struct qed_hwfn *p_hwfn, struct qed_sb_info *sb_info, u16 sb_id); /** - * @brief qed_int_sp_dpc - To be called when an interrupt is received on the - * default status block. + * qed_int_sp_dpc(): To be called when an interrupt is received on the + * default status block. * - * @param p_hwfn - pointer to hwfn + * @t: Tasklet. + * + * Return: Void. * */ void qed_int_sp_dpc(struct tasklet_struct *t); /** - * @brief qed_int_get_num_sbs - get the number of status - * blocks configured for this funciton in the igu. + * qed_int_get_num_sbs(): Get the number of status blocks configured + * for this funciton in the igu. * - * @param p_hwfn - * @param p_sb_cnt_info + * @p_hwfn: HW device data. + * @p_sb_cnt_info: Pointer to SB count info. * - * @return int - number of status blocks configured + * Return: Void. */ void qed_int_get_num_sbs(struct qed_hwfn *p_hwfn, struct qed_sb_cnt_info *p_sb_cnt_info); /** - * @brief qed_int_disable_post_isr_release - performs the cleanup post ISR + * qed_int_disable_post_isr_release(): Performs the cleanup post ISR * release. The API need to be called after releasing all slowpath IRQs * of the device. * - * @param cdev + * @cdev: Qed dev pointer. * + * Return: Void. */ void qed_int_disable_post_isr_release(struct qed_dev *cdev); /** - * @brief qed_int_attn_clr_enable - sets whether the general behavior is + * qed_int_attn_clr_enable: Sets whether the general behavior is * preventing attentions from being reasserted, or following the * attributes of the specific attention. * - * @param cdev - * @param clr_enable + * @cdev: Qed dev pointer. + * @clr_enable: Clear enable + * + * Return: Void. * */ void qed_int_attn_clr_enable(struct qed_dev *cdev, bool clr_enable); /** - * @brief - Doorbell Recovery handler. + * qed_db_rec_handler(): Doorbell Recovery handler. * Run doorbell recovery in case of PF overflow (and flush DORQ if * needed). * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Int. */ int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); @@ -223,30 +235,34 @@ struct qed_igu_info { }; /** - * @brief - Make sure the IGU CAM reflects the resources provided by MFW + * qed_int_igu_reset_cam(): Make sure the IGU CAM reflects the resources + * provided by MFW. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param p_hwfn - * @param p_ptt + * Return: Void. */ int qed_int_igu_reset_cam(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Translate the weakly-defined client sb-id into an IGU sb-id + * qed_get_igu_sb_id(): Translate the weakly-defined client sb-id into + * an IGU sb-id * - * @param p_hwfn - * @param sb_id - user provided sb_id + * @p_hwfn: HW device data. + * @sb_id: user provided sb_id. * - * @return an index inside IGU CAM where the SB resides + * Return: An index inside IGU CAM where the SB resides. */ u16 qed_get_igu_sb_id(struct qed_hwfn *p_hwfn, u16 sb_id); /** - * @brief return a pointer to an unused valid SB + * qed_get_igu_free_sb(): Return a pointer to an unused valid SB * - * @param p_hwfn - * @param b_is_pf - true iff we want a SB belonging to a PF + * @p_hwfn: HW device data. + * @b_is_pf: True iff we want a SB belonging to a PF. * - * @return point to an igu_block, NULL if none is available + * Return: Point to an igu_block, NULL if none is available. */ struct qed_igu_block *qed_get_igu_free_sb(struct qed_hwfn *p_hwfn, bool b_is_pf); @@ -259,15 +275,15 @@ void qed_int_igu_init_pure_rt(struct qed_hwfn *p_hwfn, void qed_int_igu_init_rt(struct qed_hwfn *p_hwfn); /** - * @brief qed_int_igu_read_cam - Reads the IGU CAM. + * qed_int_igu_read_cam(): Reads the IGU CAM. * This function needs to be called during hardware * prepare. It reads the info from igu cam to know which * status block is the default / base status block etc. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int + * Return: Int. */ int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); @@ -275,24 +291,22 @@ int qed_int_igu_read_cam(struct qed_hwfn *p_hwfn, typedef int (*qed_int_comp_cb_t)(struct qed_hwfn *p_hwfn, void *cookie); /** - * @brief qed_int_register_cb - Register callback func for - * slowhwfn statusblock. - * - * Every protocol that uses the slowhwfn status block - * should register a callback function that will be called - * once there is an update of the sp status block. - * - * @param p_hwfn - * @param comp_cb - function to be called when there is an - * interrupt on the sp sb - * - * @param cookie - passed to the callback function - * @param sb_idx - OUT parameter which gives the chosen index - * for this protocol. - * @param p_fw_cons - pointer to the actual address of the - * consumer for this protocol. - * - * @return int + * qed_int_register_cb(): Register callback func for slowhwfn statusblock. + * + * @p_hwfn: HW device data. + * @comp_cb: Function to be called when there is an + * interrupt on the sp sb + * @cookie: Passed to the callback function + * @sb_idx: (OUT) parameter which gives the chosen index + * for this protocol. + * @p_fw_cons: Pointer to the actual address of the + * consumer for this protocol. + * + * Return: Int. + * + * Every protocol that uses the slowhwfn status block + * should register a callback function that will be called + * once there is an update of the sp status block. */ int qed_int_register_cb(struct qed_hwfn *p_hwfn, qed_int_comp_cb_t comp_cb, @@ -301,37 +315,40 @@ int qed_int_register_cb(struct qed_hwfn *p_hwfn, __le16 **p_fw_cons); /** - * @brief qed_int_unregister_cb - Unregisters callback - * function from sp sb. - * Partner of qed_int_register_cb -> should be called - * when no longer required. + * qed_int_unregister_cb(): Unregisters callback function from sp sb. + * + * @p_hwfn: HW device data. + * @pi: Producer Index. * - * @param p_hwfn - * @param pi + * Return: Int. * - * @return int + * Partner of qed_int_register_cb -> should be called + * when no longer required. */ int qed_int_unregister_cb(struct qed_hwfn *p_hwfn, u8 pi); /** - * @brief qed_int_get_sp_sb_id - Get the slowhwfn sb id. + * qed_int_get_sp_sb_id(): Get the slowhwfn sb id. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return u16 + * Return: u16. */ u16 qed_int_get_sp_sb_id(struct qed_hwfn *p_hwfn); /** - * @brief Status block cleanup. Should be called for each status - * block that will be used -> both PF / VF - * - * @param p_hwfn - * @param p_ptt - * @param igu_sb_id - igu status block id - * @param opaque - opaque fid of the sb owner. - * @param b_set - set(1) / clear(0) + * qed_int_igu_init_pure_rt_single(): Status block cleanup. + * Should be called for each status + * block that will be used -> both PF / VF. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @igu_sb_id: IGU status block id. + * @opaque: Opaque fid of the sb owner. + * @b_set: Set(1) / Clear(0). + * + * Return: Void. */ void qed_int_igu_init_pure_rt_single(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -340,15 +357,16 @@ void qed_int_igu_init_pure_rt_single(struct qed_hwfn *p_hwfn, bool b_set); /** - * @brief qed_int_cau_conf - configure cau for a given status - * block - * - * @param p_hwfn - * @param ptt - * @param sb_phys - * @param igu_sb_id - * @param vf_number - * @param vf_valid + * qed_int_cau_conf_sb(): Configure cau for a given status block. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @sb_phys: SB Physical. + * @igu_sb_id: IGU status block id. + * @vf_number: VF number + * @vf_valid: VF valid or not. + * + * Return: Void. */ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -358,52 +376,58 @@ void qed_int_cau_conf_sb(struct qed_hwfn *p_hwfn, u8 vf_valid); /** - * @brief qed_int_alloc + * qed_int_alloc(): QED interrupt alloc. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int + * Return: Int. */ int qed_int_alloc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief qed_int_free + * qed_int_free(): QED interrupt free. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_int_free(struct qed_hwfn *p_hwfn); /** - * @brief qed_int_setup + * qed_int_setup(): QED interrupt setup. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Void. */ void qed_int_setup(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief - Enable Interrupt & Attention for hw function + * qed_int_igu_enable(): Enable Interrupt & Attention for hw function. * - * @param p_hwfn - * @param p_ptt - * @param int_mode + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @int_mode: Interrut mode * - * @return int + * Return: Int. */ int qed_int_igu_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_int_mode int_mode); /** - * @brief - Initialize CAU status block entry + * qed_init_cau_sb_entry(): Initialize CAU status block entry. + * + * @p_hwfn: HW device data. + * @p_sb_entry: Pointer SB entry. + * @pf_id: PF number + * @vf_number: VF number + * @vf_valid: VF valid or not. * - * @param p_hwfn - * @param p_sb_entry - * @param pf_id - * @param vf_number - * @param vf_valid + * Return: Void. */ void qed_init_cau_sb_entry(struct qed_hwfn *p_hwfn, struct cau_sb_entry *p_sb_entry, diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h index dab7a5d09f87..dec2b00259d4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.h @@ -34,10 +34,13 @@ void qed_iscsi_setup(struct qed_hwfn *p_hwfn); void qed_iscsi_free(struct qed_hwfn *p_hwfn); /** - * @brief - Fills provided statistics struct with statistics. + * qed_get_protocol_stats_iscsi(): Fills provided statistics + * struct with statistics. * - * @param cdev - * @param stats - points to struct that will be filled with statistics. + * @cdev: Qed dev pointer. + * @stats: Points to struct that will be filled with statistics. + * + * Return: Void. */ void qed_get_protocol_stats_iscsi(struct qed_dev *cdev, struct qed_mcp_iscsi_stats *stats); diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 8eceeebb1a7b..2ab7f3f0cf6c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -92,18 +92,18 @@ struct qed_filter_mcast { }; /** - * @brief qed_eth_rx_queue_stop - This ramrod closes an Rx queue + * qed_eth_rx_queue_stop(): This ramrod closes an Rx queue. * - * @param p_hwfn - * @param p_rxq Handler of queue to close - * @param eq_completion_only If True completion will be on - * EQe, if False completion will be - * on EQe if p_hwfn opaque - * different from the RXQ opaque - * otherwise on CQe. - * @param cqe_completion If True completion will be - * receive on CQe. - * @return int + * @p_hwfn: HW device data. + * @p_rxq: Handler of queue to close + * @eq_completion_only: If True completion will be on + * EQe, if False completion will be + * on EQe if p_hwfn opaque + * different from the RXQ opaque + * otherwise on CQe. + * @cqe_completion: If True completion will be receive on CQe. + * + * Return: Int. */ int qed_eth_rx_queue_stop(struct qed_hwfn *p_hwfn, @@ -111,12 +111,12 @@ qed_eth_rx_queue_stop(struct qed_hwfn *p_hwfn, bool eq_completion_only, bool cqe_completion); /** - * @brief qed_eth_tx_queue_stop - closes a Tx queue + * qed_eth_tx_queue_stop(): Closes a Tx queue. * - * @param p_hwfn - * @param p_txq - handle to Tx queue needed to be closed + * @p_hwfn: HW device data. + * @p_txq: handle to Tx queue needed to be closed. * - * @return int + * Return: Int. */ int qed_eth_tx_queue_stop(struct qed_hwfn *p_hwfn, void *p_txq); @@ -205,16 +205,15 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, struct qed_spq_comp_cb *p_comp_data); /** - * @brief qed_sp_vport_stop - - * - * This ramrod closes a VPort after all its RX and TX queues are terminated. - * An Assert is generated if any queues are left open. + * qed_sp_vport_stop: This ramrod closes a VPort after all its + * RX and TX queues are terminated. + * An Assert is generated if any queues are left open. * - * @param p_hwfn - * @param opaque_fid - * @param vport_id VPort ID + * @p_hwfn: HW device data. + * @opaque_fid: Opaque FID + * @vport_id: VPort ID. * - * @return int + * Return: Int. */ int qed_sp_vport_stop(struct qed_hwfn *p_hwfn, u16 opaque_fid, u8 vport_id); @@ -225,22 +224,21 @@ int qed_sp_eth_filter_ucast(struct qed_hwfn *p_hwfn, struct qed_spq_comp_cb *p_comp_data); /** - * @brief qed_sp_rx_eth_queues_update - - * - * This ramrod updates an RX queue. It is used for setting the active state - * of the queue and updating the TPA and SGE parameters. + * qed_sp_eth_rx_queues_update(): This ramrod updates an RX queue. + * It is used for setting the active state + * of the queue and updating the TPA and + * SGE parameters. + * @p_hwfn: HW device data. + * @pp_rxq_handlers: An array of queue handlers to be updated. + * @num_rxqs: number of queues to update. + * @complete_cqe_flg: Post completion to the CQE Ring if set. + * @complete_event_flg: Post completion to the Event Ring if set. + * @comp_mode: Comp mode. + * @p_comp_data: Pointer Comp data. * - * @note At the moment - only used by non-linux VFs. + * Return: Int. * - * @param p_hwfn - * @param pp_rxq_handlers An array of queue handlers to be updated. - * @param num_rxqs number of queues to update. - * @param complete_cqe_flg Post completion to the CQE Ring if set - * @param complete_event_flg Post completion to the Event Ring if set - * @param comp_mode - * @param p_comp_data - * - * @return int + * Note At the moment - only used by non-linux VFs. */ int @@ -257,30 +255,32 @@ void qed_get_vport_stats(struct qed_dev *cdev, struct qed_eth_stats *stats); void qed_reset_vport_stats(struct qed_dev *cdev); /** - * *@brief qed_arfs_mode_configure - - * - **Enable or disable rfs mode. It must accept atleast one of tcp or udp true - **and atleast one of ipv4 or ipv6 true to enable rfs mode. + * qed_arfs_mode_configure(): Enable or disable rfs mode. + * It must accept at least one of tcp or udp true + * and at least one of ipv4 or ipv6 true to enable + * rfs mode. * - **@param p_hwfn - **@param p_ptt - **@param p_cfg_params - arfs mode configuration parameters. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_cfg_params: arfs mode configuration parameters. * + * Return. Void. */ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_arfs_config_params *p_cfg_params); /** - * @brief - qed_configure_rfs_ntuple_filter + * qed_configure_rfs_ntuple_filter(): This ramrod should be used to add + * or remove arfs hw filter * - * This ramrod should be used to add or remove arfs hw filter + * @p_hwfn: HW device data. + * @p_cb: Used for QED_SPQ_MODE_CB,where client would initialize + * it with cookie and callback function address, if not + * using this mode then client must pass NULL. + * @p_params: Pointer to params. * - * @params p_hwfn - * @params p_cb - Used for QED_SPQ_MODE_CB,where client would initialize - * it with cookie and callback function address, if not - * using this mode then client must pass NULL. - * @params p_params + * Return: Void. */ int qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, @@ -374,16 +374,17 @@ qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn, struct qed_sp_vport_start_params *p_params); /** - * @brief - Starts an Rx queue, when queue_cid is already prepared + * qed_eth_rxq_start_ramrod(): Starts an Rx queue, when queue_cid is + * already prepared * - * @param p_hwfn - * @param p_cid - * @param bd_max_bytes - * @param bd_chain_phys_addr - * @param cqe_pbl_addr - * @param cqe_pbl_size + * @p_hwfn: HW device data. + * @p_cid: Pointer CID. + * @bd_max_bytes: Max bytes. + * @bd_chain_phys_addr: Chain physcial address. + * @cqe_pbl_addr: PBL address. + * @cqe_pbl_size: PBL size. * - * @return int + * Return: Int. */ int qed_eth_rxq_start_ramrod(struct qed_hwfn *p_hwfn, @@ -393,15 +394,16 @@ qed_eth_rxq_start_ramrod(struct qed_hwfn *p_hwfn, dma_addr_t cqe_pbl_addr, u16 cqe_pbl_size); /** - * @brief - Starts a Tx queue, where queue_cid is already prepared + * qed_eth_txq_start_ramrod(): Starts a Tx queue, where queue_cid is + * already prepared * - * @param p_hwfn - * @param p_cid - * @param pbl_addr - * @param pbl_size - * @param p_pq_params - parameters for choosing the PQ for this Tx queue + * @p_hwfn: HW device data. + * @p_cid: Pointer CID. + * @pbl_addr: PBL address. + * @pbl_size: PBL size. + * @pq_id: Parameters for choosing the PQ for this Tx queue. * - * @return int + * Return: Int. */ int qed_eth_txq_start_ramrod(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h index df88d00053a2..f80f7739ff8d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h @@ -119,41 +119,41 @@ struct qed_ll2_info { extern const struct qed_ll2_ops qed_ll2_ops_pass; /** - * @brief qed_ll2_acquire_connection - allocate resources, - * starts rx & tx (if relevant) queues pair. Provides - * connecion handler as output parameter. + * qed_ll2_acquire_connection(): Allocate resources, + * starts rx & tx (if relevant) queues pair. + * Provides connecion handler as output + * parameter. * + * @cxt: Pointer to the hw-function [opaque to some]. + * @data: Describes connection parameters. * - * @param cxt - pointer to the hw-function [opaque to some] - * @param data - describes connection parameters - * @return int + * Return: Int. */ int qed_ll2_acquire_connection(void *cxt, struct qed_ll2_acquire_data *data); /** - * @brief qed_ll2_establish_connection - start previously - * allocated LL2 queues pair + * qed_ll2_establish_connection(): start previously allocated LL2 queues pair * - * @param cxt - pointer to the hw-function [opaque to some] - * @param p_ptt - * @param connection_handle LL2 connection's handle obtained from - * qed_ll2_require_connection + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: LL2 connection's handle obtained from + * qed_ll2_require_connection. * - * @return 0 on success, failure otherwise + * Return: 0 on success, failure otherwise. */ int qed_ll2_establish_connection(void *cxt, u8 connection_handle); /** - * @brief qed_ll2_post_rx_buffers - submit buffers to LL2 Rx queue. + * qed_ll2_post_rx_buffer(): Submit buffers to LL2 Rx queue. * - * @param cxt - pointer to the hw-function [opaque to some] - * @param connection_handle LL2 connection's handle obtained from - * qed_ll2_require_connection - * @param addr rx (physical address) buffers to submit - * @param cookie - * @param notify_fw produce corresponding Rx BD immediately + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: LL2 connection's handle obtained from + * qed_ll2_require_connection. + * @addr: RX (physical address) buffers to submit. + * @buf_len: Buffer Len. + * @cookie: Cookie. + * @notify_fw: Produce corresponding Rx BD immediately. * - * @return 0 on success, failure otherwise + * Return: 0 on success, failure otherwise. */ int qed_ll2_post_rx_buffer(void *cxt, u8 connection_handle, @@ -161,15 +161,15 @@ int qed_ll2_post_rx_buffer(void *cxt, u16 buf_len, void *cookie, u8 notify_fw); /** - * @brief qed_ll2_prepare_tx_packet - request for start Tx BD - * to prepare Tx packet submission to FW. + * qed_ll2_prepare_tx_packet(): Request for start Tx BD + * to prepare Tx packet submission to FW. * - * @param cxt - pointer to the hw-function [opaque to some] - * @param connection_handle - * @param pkt - info regarding the tx packet - * @param notify_fw - issue doorbell to fw for this packet + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: Connection handle. + * @pkt: Info regarding the tx packet. + * @notify_fw: Issue doorbell to fw for this packet. * - * @return 0 on success, failure otherwise + * Return: 0 on success, failure otherwise. */ int qed_ll2_prepare_tx_packet(void *cxt, u8 connection_handle, @@ -177,81 +177,83 @@ int qed_ll2_prepare_tx_packet(void *cxt, bool notify_fw); /** - * @brief qed_ll2_release_connection - releases resources - * allocated for LL2 connection + * qed_ll2_release_connection(): Releases resources allocated for LL2 + * connection. * - * @param cxt - pointer to the hw-function [opaque to some] - * @param connection_handle LL2 connection's handle obtained from - * qed_ll2_require_connection + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: LL2 connection's handle obtained from + * qed_ll2_require_connection. + * + * Return: Void. */ void qed_ll2_release_connection(void *cxt, u8 connection_handle); /** - * @brief qed_ll2_set_fragment_of_tx_packet - provides fragments to fill - * Tx BD of BDs requested by - * qed_ll2_prepare_tx_packet + * qed_ll2_set_fragment_of_tx_packet(): Provides fragments to fill + * Tx BD of BDs requested by + * qed_ll2_prepare_tx_packet * - * @param cxt - pointer to the hw-function [opaque to some] - * @param connection_handle LL2 connection's handle - * obtained from - * qed_ll2_require_connection - * @param addr - * @param nbytes + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: LL2 connection's handle obtained from + * qed_ll2_require_connection. + * @addr: Address. + * @nbytes: Number of bytes. * - * @return 0 on success, failure otherwise + * Return: 0 on success, failure otherwise. */ int qed_ll2_set_fragment_of_tx_packet(void *cxt, u8 connection_handle, dma_addr_t addr, u16 nbytes); /** - * @brief qed_ll2_terminate_connection - stops Tx/Rx queues - * + * qed_ll2_terminate_connection(): Stops Tx/Rx queues * - * @param cxt - pointer to the hw-function [opaque to some] - * @param connection_handle LL2 connection's handle - * obtained from - * qed_ll2_require_connection + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: LL2 connection's handle obtained from + * qed_ll2_require_connection. * - * @return 0 on success, failure otherwise + * Return: 0 on success, failure otherwise. */ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle); /** - * @brief qed_ll2_get_stats - get LL2 queue's statistics - * + * qed_ll2_get_stats(): Get LL2 queue's statistics * - * @param cxt - pointer to the hw-function [opaque to some] - * @param connection_handle LL2 connection's handle obtained from - * qed_ll2_require_connection - * @param p_stats + * @cxt: Pointer to the hw-function [opaque to some]. + * @connection_handle: LL2 connection's handle obtained from + * qed_ll2_require_connection. + * @p_stats: Pointer Status. * - * @return 0 on success, failure otherwise + * Return: 0 on success, failure otherwise. */ int qed_ll2_get_stats(void *cxt, u8 connection_handle, struct qed_ll2_stats *p_stats); /** - * @brief qed_ll2_alloc - Allocates LL2 connections set + * qed_ll2_alloc(): Allocates LL2 connections set. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_ll2_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_ll2_setup - Inits LL2 connections set + * qed_ll2_setup(): Inits LL2 connections set. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. * */ void qed_ll2_setup(struct qed_hwfn *p_hwfn); /** - * @brief qed_ll2_free - Releases LL2 connections set + * qed_ll2_free(): Releases LL2 connections set + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. * */ void qed_ll2_free(struct qed_hwfn *p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 8edb450d0abf..352b757183e8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -266,97 +266,97 @@ union qed_mfw_tlv_data { #define QED_NVM_CFG_OPTION_ENTITY_SEL BIT(4) /** - * @brief - returns the link params of the hw function + * qed_mcp_get_link_params(): Returns the link params of the hw function. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @returns pointer to link params + * Returns: Pointer to link params. */ -struct qed_mcp_link_params *qed_mcp_get_link_params(struct qed_hwfn *); +struct qed_mcp_link_params *qed_mcp_get_link_params(struct qed_hwfn *p_hwfn); /** - * @brief - return the link state of the hw function + * qed_mcp_get_link_state(): Return the link state of the hw function. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @returns pointer to link state + * Returns: Pointer to link state. */ -struct qed_mcp_link_state *qed_mcp_get_link_state(struct qed_hwfn *); +struct qed_mcp_link_state *qed_mcp_get_link_state(struct qed_hwfn *p_hwfn); /** - * @brief - return the link capabilities of the hw function + * qed_mcp_get_link_capabilities(): Return the link capabilities of the + * hw function. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @returns pointer to link capabilities + * Returns: Pointer to link capabilities. */ struct qed_mcp_link_capabilities *qed_mcp_get_link_capabilities(struct qed_hwfn *p_hwfn); /** - * @brief Request the MFW to set the the link according to 'link_input'. + * qed_mcp_set_link(): Request the MFW to set the link according + * to 'link_input'. * - * @param p_hwfn - * @param p_ptt - * @param b_up - raise link if `true'. Reset link if `false'. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @b_up: Raise link if `true'. Reset link if `false'. * - * @return int + * Return: Int. */ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up); /** - * @brief Get the management firmware version value + * qed_mcp_get_mfw_ver(): Get the management firmware version value. * - * @param p_hwfn - * @param p_ptt - * @param p_mfw_ver - mfw version value - * @param p_running_bundle_id - image id in nvram; Optional. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_mfw_ver: MFW version value. + * @p_running_bundle_id: Image id in nvram; Optional. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - operation was successful. */ int qed_mcp_get_mfw_ver(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_mfw_ver, u32 *p_running_bundle_id); /** - * @brief Get the MBI version value + * qed_mcp_get_mbi_ver(): Get the MBI version value. * - * @param p_hwfn - * @param p_ptt - * @param p_mbi_ver - A pointer to a variable to be filled with the MBI version. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_mbi_ver: A pointer to a variable to be filled with the MBI version. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - operation was successful. */ int qed_mcp_get_mbi_ver(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_mbi_ver); /** - * @brief Get media type value of the port. + * qed_mcp_get_media_type(): Get media type value of the port. * - * @param cdev - qed dev pointer - * @param p_ptt - * @param mfw_ver - media type value + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @media_type: Media type value * - * @return int - - * 0 - Operation was successul. - * -EBUSY - Operation failed + * Return: Int - 0 - Operation was successul. + * -EBUSY - Operation failed */ int qed_mcp_get_media_type(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *media_type); /** - * @brief Get transceiver data of the port. + * qed_mcp_get_transceiver_data(): Get transceiver data of the port. * - * @param cdev - qed dev pointer - * @param p_ptt - * @param p_transceiver_state - transceiver state. - * @param p_transceiver_type - media type value + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_transceiver_state: Transceiver state. + * @p_tranceiver_type: Media type value. * - * @return int - - * 0 - Operation was successful. - * -EBUSY - Operation failed + * Return: Int - 0 - Operation was successul. + * -EBUSY - Operation failed */ int qed_mcp_get_transceiver_data(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -364,50 +364,48 @@ int qed_mcp_get_transceiver_data(struct qed_hwfn *p_hwfn, u32 *p_tranceiver_type); /** - * @brief Get transceiver supported speed mask. + * qed_mcp_trans_speed_mask(): Get transceiver supported speed mask. * - * @param cdev - qed dev pointer - * @param p_ptt - * @param p_speed_mask - Bit mask of all supported speeds. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_speed_mask: Bit mask of all supported speeds. * - * @return int - - * 0 - Operation was successful. - * -EBUSY - Operation failed + * Return: Int - 0 - Operation was successul. + * -EBUSY - Operation failed */ int qed_mcp_trans_speed_mask(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_speed_mask); /** - * @brief Get board configuration. + * qed_mcp_get_board_config(): Get board configuration. * - * @param cdev - qed dev pointer - * @param p_ptt - * @param p_board_config - Board config. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_board_config: Board config. * - * @return int - - * 0 - Operation was successful. - * -EBUSY - Operation failed + * Return: Int - 0 - Operation was successul. + * -EBUSY - Operation failed */ int qed_mcp_get_board_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_board_config); /** - * @brief General function for sending commands to the MCP - * mailbox. It acquire mutex lock for the entire - * operation, from sending the request until the MCP - * response. Waiting for MCP response will be checked up - * to 5 seconds every 5ms. + * qed_mcp_cmd(): General function for sending commands to the MCP + * mailbox. It acquire mutex lock for the entire + * operation, from sending the request until the MCP + * response. Waiting for MCP response will be checked up + * to 5 seconds every 5ms. * - * @param p_hwfn - hw function - * @param p_ptt - PTT required for register access - * @param cmd - command to be sent to the MCP. - * @param param - Optional param - * @param o_mcp_resp - The MCP response code (exclude sequence). - * @param o_mcp_param- Optional parameter provided by the MCP + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @cmd: command to be sent to the MCP. + * @param: Optional param + * @o_mcp_resp: The MCP response code (exclude sequence). + * @o_mcp_param: Optional parameter provided by the MCP * response - * @return int - 0 - operation - * was successul. + * + * Return: Int - 0 - Operation was successul. */ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -417,37 +415,39 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn, u32 *o_mcp_param); /** - * @brief - drains the nig, allowing completion to pass in case of pauses. - * (Should be called only from sleepable context) + * qed_mcp_drain(): drains the nig, allowing completion to pass in + * case of pauses. + * (Should be called only from sleepable context) * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * + * Return: Int. */ int qed_mcp_drain(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Get the flash size value + * qed_mcp_get_flash_size(): Get the flash size value. * - * @param p_hwfn - * @param p_ptt - * @param p_flash_size - flash size in bytes to be filled. + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @p_flash_size: Flash size in bytes to be filled. * - * @return int - 0 - operation was successul. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_get_flash_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_flash_size); /** - * @brief Send driver version to MFW + * qed_mcp_send_drv_version(): Send driver version to MFW. * - * @param p_hwfn - * @param p_ptt - * @param version - Version value - * @param name - Protocol driver name + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @p_ver: Version value. * - * @return int - 0 - operation was successul. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn, @@ -455,146 +455,148 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn, struct qed_mcp_drv_version *p_ver); /** - * @brief Read the MFW process kill counter + * qed_get_process_kill_counter(): Read the MFW process kill counter. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. * - * @return u32 + * Return: u32. */ u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Trigger a recovery process + * qed_start_recovery_process(): Trigger a recovery process. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. * - * @return int + * Return: Int. */ int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief A recovery handler must call this function as its first step. - * It is assumed that the handler is not run from an interrupt context. + * qed_recovery_prolog(): A recovery handler must call this function + * as its first step. + * It is assumed that the handler is not run from + * an interrupt context. * - * @param cdev - * @param p_ptt + * @cdev: Qed dev pointer. * - * @return int + * Return: int. */ int qed_recovery_prolog(struct qed_dev *cdev); /** - * @brief Notify MFW about the change in base device properties + * qed_mcp_ov_update_current_config(): Notify MFW about the change in base + * device properties * - * @param p_hwfn - * @param p_ptt - * @param client - qed client type + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @client: Qed client type. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_current_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_ov_client client); /** - * @brief Notify MFW about the driver state + * qed_mcp_ov_update_driver_state(): Notify MFW about the driver state. * - * @param p_hwfn - * @param p_ptt - * @param drv_state - Driver state + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @drv_state: Driver state. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_driver_state(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_ov_driver_state drv_state); /** - * @brief Send MTU size to MFW + * qed_mcp_ov_update_mtu(): Send MTU size to MFW. * - * @param p_hwfn - * @param p_ptt - * @param mtu - MTU size + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @mtu: MTU size. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 mtu); /** - * @brief Send MAC address to MFW + * qed_mcp_ov_update_mac(): Send MAC address to MFW. * - * @param p_hwfn - * @param p_ptt - * @param mac - MAC address + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @mac: MAC address. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 *mac); /** - * @brief Send WOL mode to MFW + * qed_mcp_ov_update_wol(): Send WOL mode to MFW. * - * @param p_hwfn - * @param p_ptt - * @param wol - WOL mode + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @wol: WOL mode. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_wol(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_ov_wol wol); /** - * @brief Set LED status + * qed_mcp_set_led(): Set LED status. * - * @param p_hwfn - * @param p_ptt - * @param mode - LED mode + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @mode: LED mode. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_set_led(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, enum qed_led_mode mode); /** - * @brief Read from nvm + * qed_mcp_nvm_read(): Read from NVM. * - * @param cdev - * @param addr - nvm offset - * @param p_buf - nvm read buffer - * @param len - buffer len + * @cdev: Qed dev pointer. + * @addr: NVM offset. + * @p_buf: NVM read buffer. + * @len: Buffer len. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_nvm_read(struct qed_dev *cdev, u32 addr, u8 *p_buf, u32 len); /** - * @brief Write to nvm + * qed_mcp_nvm_write(): Write to NVM. * - * @param cdev - * @param addr - nvm offset - * @param cmd - nvm command - * @param p_buf - nvm write buffer - * @param len - buffer len + * @cdev: Qed dev pointer. + * @addr: NVM offset. + * @cmd: NVM command. + * @p_buf: NVM write buffer. + * @len: Buffer len. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_nvm_write(struct qed_dev *cdev, u32 cmd, u32 addr, u8 *p_buf, u32 len); /** - * @brief Check latest response + * qed_mcp_nvm_resp(): Check latest response. * - * @param cdev - * @param p_buf - nvm write buffer + * @cdev: Qed dev pointer. + * @p_buf: NVM write buffer. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_nvm_resp(struct qed_dev *cdev, u8 *p_buf); @@ -604,13 +606,13 @@ struct qed_nvm_image_att { }; /** - * @brief Allows reading a whole nvram image + * qed_mcp_get_nvm_image_att(): Allows reading a whole nvram image. * - * @param p_hwfn - * @param image_id - image to get attributes for - * @param p_image_att - image attributes structure into which to fill data + * @p_hwfn: HW device data. + * @image_id: Image to get attributes for. + * @p_image_att: Image attributes structure into which to fill data. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, @@ -618,64 +620,65 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, struct qed_nvm_image_att *p_image_att); /** - * @brief Allows reading a whole nvram image + * qed_mcp_get_nvm_image(): Allows reading a whole nvram image. * - * @param p_hwfn - * @param image_id - image requested for reading - * @param p_buffer - allocated buffer into which to fill data - * @param buffer_len - length of the allocated buffer. + * @p_hwfn: HW device data. + * @image_id: image requested for reading. + * @p_buffer: allocated buffer into which to fill data. + * @buffer_len: length of the allocated buffer. * - * @return 0 iff p_buffer now contains the nvram image. + * Return: 0 if p_buffer now contains the nvram image. */ int qed_mcp_get_nvm_image(struct qed_hwfn *p_hwfn, enum qed_nvm_images image_id, u8 *p_buffer, u32 buffer_len); /** - * @brief Bist register test + * qed_mcp_bist_register_test(): Bist register test. * - * @param p_hwfn - hw function - * @param p_ptt - PTT required for register access + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_bist_register_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Bist clock test + * qed_mcp_bist_clock_test(): Bist clock test. * - * @param p_hwfn - hw function - * @param p_ptt - PTT required for register access + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_bist_clock_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Bist nvm test - get number of images + * qed_mcp_bist_nvm_get_num_images(): Bist nvm test - get number of images. * - * @param p_hwfn - hw function - * @param p_ptt - PTT required for register access - * @param num_images - number of images if operation was + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @num_images: number of images if operation was * successful. 0 if not. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_bist_nvm_get_num_images(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *num_images); /** - * @brief Bist nvm test - get image attributes by index + * qed_mcp_bist_nvm_get_image_att(): Bist nvm test - get image attributes + * by index. * - * @param p_hwfn - hw function - * @param p_ptt - PTT required for register access - * @param p_image_att - Attributes of image - * @param image_index - Index of image to get information for + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @p_image_att: Attributes of image. + * @image_index: Index of image to get information for. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -683,23 +686,26 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn, u32 image_index); /** - * @brief - Processes the TLV request from MFW i.e., get the required TLV info - * from the qed client and send it to the MFW. + * qed_mfw_process_tlv_req(): Processes the TLV request from MFW i.e., + * get the required TLV info + * from the qed client and send it to the MFW. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param return 0 upon success. + * Return: 0 upon success. */ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Send raw debug data to the MFW + * qed_mcp_send_raw_debug_data(): Send raw debug data to the MFW + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_buf: raw debug data buffer. + * @size: Buffer size. * - * @param p_hwfn - * @param p_ptt - * @param p_buf - raw debug data buffer - * @param size - buffer size + * Return : Int. */ int qed_mcp_send_raw_debug_data(struct qed_hwfn *p_hwfn, @@ -796,47 +802,49 @@ qed_mcp_is_ext_speed_supported(const struct qed_hwfn *p_hwfn) } /** - * @brief Initialize the interface with the MCP + * qed_mcp_cmd_init(): Initialize the interface with the MCP. * - * @param p_hwfn - HW func - * @param p_ptt - PTT required for register access + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. * - * @return int + * Return: Int. */ int qed_mcp_cmd_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Initialize the port interface with the MCP + * qed_mcp_cmd_port_init(): Initialize the port interface with the MCP + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Void. * - * @param p_hwfn - * @param p_ptt * Can only be called after `num_ports_in_engines' is set */ void qed_mcp_cmd_port_init(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Releases resources allocated during the init process. + * qed_mcp_free(): Releases resources allocated during the init process. * - * @param p_hwfn - HW func - * @param p_ptt - PTT required for register access + * @p_hwfn: HW function. * - * @return int + * Return: Int. */ int qed_mcp_free(struct qed_hwfn *p_hwfn); /** - * @brief This function is called from the DPC context. After - * pointing PTT to the mfw mb, check for events sent by the MCP - * to the driver and ack them. In case a critical event - * detected, it will be handled here, otherwise the work will be - * queued to a sleepable work-queue. + * qed_mcp_handle_events(): This function is called from the DPC context. + * After pointing PTT to the mfw mb, check for events sent by + * the MCP to the driver and ack them. In case a critical event + * detected, it will be handled here, otherwise the work will be + * queued to a sleepable work-queue. + * + * @p_hwfn: HW function. + * @p_ptt: PTT required for register access. * - * @param p_hwfn - HW function - * @param p_ptt - PTT required for register access - * @return int - 0 - operation - * was successul. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); @@ -858,106 +866,111 @@ struct qed_load_req_params { }; /** - * @brief Sends a LOAD_REQ to the MFW, and in case the operation succeeds, - * returns whether this PF is the first on the engine/port or function. + * qed_mcp_load_req(): Sends a LOAD_REQ to the MFW, and in case the + * operation succeeds, returns whether this PF is + * the first on the engine/port or function. * - * @param p_hwfn - * @param p_ptt - * @param p_params + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_params: Params. * - * @return int - 0 - Operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_load_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_load_req_params *p_params); /** - * @brief Sends a LOAD_DONE message to the MFW + * qed_mcp_load_done(): Sends a LOAD_DONE message to the MFW. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int - 0 - Operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Sends a UNLOAD_REQ message to the MFW + * qed_mcp_unload_req(): Sends a UNLOAD_REQ message to the MFW. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int - 0 - Operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Sends a UNLOAD_DONE message to the MFW + * qed_mcp_unload_done(): Sends a UNLOAD_DONE message to the MFW * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int - 0 - Operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Read the MFW mailbox into Current buffer. + * qed_mcp_read_mb(): Read the MFW mailbox into Current buffer. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Void. */ void qed_mcp_read_mb(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Ack to mfw that driver finished FLR process for VFs + * qed_mcp_ack_vf_flr(): Ack to mfw that driver finished FLR process for VFs * - * @param p_hwfn - * @param p_ptt - * @param vfs_to_ack - bit mask of all engine VFs for which the PF acks. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @vfs_to_ack: bit mask of all engine VFs for which the PF acks. * - * @param return int - 0 upon success. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ack_vf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *vfs_to_ack); /** - * @brief - calls during init to read shmem of all function-related info. + * qed_mcp_fill_shmem_func_info(): Calls during init to read shmem of + * all function-related info. * - * @param p_hwfn + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param return 0 upon success. + * Return: 0 upon success. */ int qed_mcp_fill_shmem_func_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief - Reset the MCP using mailbox command. + * qed_mcp_reset(): Reset the MCP using mailbox command. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param return 0 upon success. + * Return: 0 upon success. */ int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief - Sends an NVM read command request to the MFW to get - * a buffer. + * qed_mcp_nvm_rd_cmd(): Sends an NVM read command request to the MFW to get + * a buffer. * - * @param p_hwfn - * @param p_ptt - * @param cmd - Command: DRV_MSG_CODE_NVM_GET_FILE_DATA or - * DRV_MSG_CODE_NVM_READ_NVRAM commands - * @param param - [0:23] - Offset [24:31] - Size - * @param o_mcp_resp - MCP response - * @param o_mcp_param - MCP response param - * @param o_txn_size - Buffer size output - * @param o_buf - Pointer to the buffer returned by the MFW. + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @cmd: (Command) DRV_MSG_CODE_NVM_GET_FILE_DATA or + * DRV_MSG_CODE_NVM_READ_NVRAM commands. + * @param: [0:23] - Offset [24:31] - Size. + * @o_mcp_resp: MCP response. + * @o_mcp_param: MCP response param. + * @o_txn_size: Buffer size output. + * @o_buf: Pointer to the buffer returned by the MFW. * - * @param return 0 upon success. + * Return: 0 upon success. */ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -967,60 +980,61 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn, u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf); /** - * @brief Read from sfp + * qed_mcp_phy_sfp_read(): Read from sfp. * - * @param p_hwfn - hw function - * @param p_ptt - PTT required for register access - * @param port - transceiver port - * @param addr - I2C address - * @param offset - offset in sfp - * @param len - buffer length - * @param p_buf - buffer to read into + * @p_hwfn: HW device data. + * @p_ptt: PTT required for register access. + * @port: transceiver port. + * @addr: I2C address. + * @offset: offset in sfp. + * @len: buffer length. + * @p_buf: buffer to read into. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf); /** - * @brief indicates whether the MFW objects [under mcp_info] are accessible + * qed_mcp_is_init(): indicates whether the MFW objects [under mcp_info] + * are accessible * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return true iff MFW is running and mcp_info is initialized + * Return: true if MFW is running and mcp_info is initialized. */ bool qed_mcp_is_init(struct qed_hwfn *p_hwfn); /** - * @brief request MFW to configure MSI-X for a VF + * qed_mcp_config_vf_msix(): Request MFW to configure MSI-X for a VF. * - * @param p_hwfn - * @param p_ptt - * @param vf_id - absolute inside engine - * @param num_sbs - number of entries to request + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @vf_id: absolute inside engine. + * @num: number of entries to request. * - * @return int + * Return: Int. */ int qed_mcp_config_vf_msix(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u8 vf_id, u8 num); /** - * @brief - Halt the MCP. + * qed_mcp_halt(): Halt the MCP. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param return 0 upon success. + * Return: 0 upon success. */ int qed_mcp_halt(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief - Wake up the MCP. + * qed_mcp_resume: Wake up the MCP. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param return 0 upon success. + * Return: 0 upon success. */ int qed_mcp_resume(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); @@ -1038,13 +1052,13 @@ int __qed_configure_pf_min_bandwidth(struct qed_hwfn *p_hwfn, int qed_mcp_mask_parities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 mask_parities); -/* @brief - Gets the mdump retained data from the MFW. +/* qed_mcp_mdump_get_retain(): Gets the mdump retained data from the MFW. * - * @param p_hwfn - * @param p_ptt - * @param p_mdump_retain + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_mdump_retain: mdump retain. * - * @param return 0 upon success. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn, @@ -1052,15 +1066,15 @@ qed_mcp_mdump_get_retain(struct qed_hwfn *p_hwfn, struct mdump_retain_data_stc *p_mdump_retain); /** - * @brief - Sets the MFW's max value for the given resource + * qed_mcp_set_resc_max_val(): Sets the MFW's max value for the given resource. * - * @param p_hwfn - * @param p_ptt - * @param res_id - * @param resc_max_val - * @param p_mcp_resp + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @res_id: RES ID. + * @resc_max_val: Resec max val. + * @p_mcp_resp: MCP Resp * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn, @@ -1069,16 +1083,17 @@ qed_mcp_set_resc_max_val(struct qed_hwfn *p_hwfn, u32 resc_max_val, u32 *p_mcp_resp); /** - * @brief - Gets the MFW allocation info for the given resource + * qed_mcp_get_resc_info(): Gets the MFW allocation info for the given + * resource. * - * @param p_hwfn - * @param p_ptt - * @param res_id - * @param p_mcp_resp - * @param p_resc_num - * @param p_resc_start + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @res_id: Res ID. + * @p_mcp_resp: MCP resp. + * @p_resc_num: Resc num. + * @p_resc_start: Resc start. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn, @@ -1087,13 +1102,13 @@ qed_mcp_get_resc_info(struct qed_hwfn *p_hwfn, u32 *p_mcp_resp, u32 *p_resc_num, u32 *p_resc_start); /** - * @brief Send eswitch mode to MFW + * qed_mcp_ov_update_eswitch(): Send eswitch mode to MFW. * - * @param p_hwfn - * @param p_ptt - * @param eswitch - eswitch mode + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @eswitch: eswitch mode. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_eswitch(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -1113,12 +1128,12 @@ enum qed_resc_lock { }; /** - * @brief - Initiates PF FLR + * qed_mcp_initiate_pf_flr(): Initiates PF FLR. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_initiate_pf_flr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); struct qed_resc_lock_params { @@ -1151,13 +1166,13 @@ struct qed_resc_lock_params { }; /** - * @brief Acquires MFW generic resource lock + * qed_mcp_resc_lock(): Acquires MFW generic resource lock. * - * @param p_hwfn - * @param p_ptt - * @param p_params + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_params: Params. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_resc_lock(struct qed_hwfn *p_hwfn, @@ -1175,13 +1190,13 @@ struct qed_resc_unlock_params { }; /** - * @brief Releases MFW generic resource lock + * qed_mcp_resc_unlock(): Releases MFW generic resource lock. * - * @param p_hwfn - * @param p_ptt - * @param p_params + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_params: Params. * - * @return int - 0 - operation was successful. + * Return: Int - 0 - Operation was successul. */ int qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn, @@ -1189,12 +1204,15 @@ qed_mcp_resc_unlock(struct qed_hwfn *p_hwfn, struct qed_resc_unlock_params *p_params); /** - * @brief - default initialization for lock/unlock resource structs + * qed_mcp_resc_lock_default_init(): Default initialization for + * lock/unlock resource structs. * - * @param p_lock - lock params struct to be initialized; Can be NULL - * @param p_unlock - unlock params struct to be initialized; Can be NULL - * @param resource - the requested resource - * @paral b_is_permanent - disable retries & aging when set + * @p_lock: lock params struct to be initialized; Can be NULL. + * @p_unlock: unlock params struct to be initialized; Can be NULL. + * @resource: the requested resource. + * @b_is_permanent: disable retries & aging when set. + * + * Return: Void. */ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, struct qed_resc_unlock_params *p_unlock, @@ -1202,94 +1220,117 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, resource, bool b_is_permanent); /** - * @brief - Return whether management firmware support smart AN + * qed_mcp_is_smart_an_supported(): Return whether management firmware + * support smart AN * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return bool - true if feature is supported. + * Return: bool true if feature is supported. */ bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn); /** - * @brief Learn of supported MFW features; To be done during early init + * qed_mcp_get_capabilities(): Learn of supported MFW features; + * To be done during early init. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Int. */ int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Inform MFW of set of features supported by driver. Should be done - * inside the content of the LOAD_REQ. + * qed_mcp_set_capabilities(): Inform MFW of set of features supported + * by driver. Should be done inside the content + * of the LOAD_REQ. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param p_hwfn - * @param p_ptt + * Return: Int. */ int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Read ufp config from the shared memory. + * qed_mcp_read_ufp_config(): Read ufp config from the shared memory. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. * - * @param p_hwfn - * @param p_ptt + * Return: Void. */ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Populate the nvm info shadow in the given hardware function + * qed_mcp_nvm_info_populate(): Populate the nvm info shadow in the given + * hardware function. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Int. */ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn); /** - * @brief Delete nvm info shadow in the given hardware function + * qed_mcp_nvm_info_free(): Delete nvm info shadow in the given + * hardware function. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_mcp_nvm_info_free(struct qed_hwfn *p_hwfn); /** - * @brief Get the engine affinity configuration. + * qed_mcp_get_engine_config(): Get the engine affinity configuration. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Int. */ int qed_mcp_get_engine_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Get the PPFID bitmap. + * qed_mcp_get_ppfid_bitmap(): Get the PPFID bitmap. * - * @param p_hwfn - * @param p_ptt + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * + * Return: Int. */ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** - * @brief Get NVM config attribute value. + * qed_mcp_nvm_get_cfg(): Get NVM config attribute value. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @option_id: Option ID. + * @entity_id: Entity ID. + * @flags: Flags. + * @p_buf: Buf. + * @p_len: Len. * - * @param p_hwfn - * @param p_ptt - * @param option_id - * @param entity_id - * @param flags - * @param p_buf - * @param p_len + * Return: Int. */ int qed_mcp_nvm_get_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, u32 *p_len); /** - * @brief Set NVM config attribute value. + * qed_mcp_nvm_set_cfg(): Set NVM config attribute value. * - * @param p_hwfn - * @param p_ptt - * @param option_id - * @param entity_id - * @param flags - * @param p_buf - * @param len + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @option_id: Option ID. + * @entity_id: Entity ID. + * @flags: Flags. + * @p_buf: Buf. + * @len: Len. + * + * Return: Int. */ int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, diff --git a/drivers/net/ethernet/qlogic/qed/qed_selftest.h b/drivers/net/ethernet/qlogic/qed/qed_selftest.h index e27dd9a4547e..7a3bd749e1e4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_selftest.h +++ b/drivers/net/ethernet/qlogic/qed/qed_selftest.h @@ -6,47 +6,47 @@ #include /** - * @brief qed_selftest_memory - Perform memory test + * qed_selftest_memory(): Perform memory test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_selftest_memory(struct qed_dev *cdev); /** - * @brief qed_selftest_interrupt - Perform interrupt test + * qed_selftest_interrupt(): Perform interrupt test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_selftest_interrupt(struct qed_dev *cdev); /** - * @brief qed_selftest_register - Perform register test + * qed_selftest_register(): Perform register test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_selftest_register(struct qed_dev *cdev); /** - * @brief qed_selftest_clock - Perform clock test + * qed_selftest_clock(): Perform clock test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_selftest_clock(struct qed_dev *cdev); /** - * @brief qed_selftest_nvram - Perform nvram test + * qed_selftest_nvram(): Perform nvram test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return int + * Return: Int. */ int qed_selftest_nvram(struct qed_dev *cdev); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 60ff3222bf55..c5a38f3c92b0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -31,23 +31,18 @@ struct qed_spq_comp_cb { }; /** - * @brief qed_eth_cqe_completion - handles the completion of a - * ramrod on the cqe ring + * qed_eth_cqe_completion(): handles the completion of a + * ramrod on the cqe ring. * - * @param p_hwfn - * @param cqe + * @p_hwfn: HW device data. + * @cqe: CQE. * - * @return int + * Return: Int. */ int qed_eth_cqe_completion(struct qed_hwfn *p_hwfn, struct eth_slow_path_rx_cqe *cqe); -/** - * @file - * - * QED Slow-hwfn queue interface - */ - + /* QED Slow-hwfn queue interface */ union ramrod_data { struct pf_start_ramrod_data pf_start; struct pf_update_ramrod_data pf_update; @@ -207,117 +202,128 @@ struct qed_spq { }; /** - * @brief qed_spq_post - Posts a Slow hwfn request to FW, or lacking that - * Pends it to the future list. + * qed_spq_post(): Posts a Slow hwfn request to FW, or lacking that + * Pends it to the future list. * - * @param p_hwfn - * @param p_req + * @p_hwfn: HW device data. + * @p_ent: Ent. + * @fw_return_code: Return code from firmware. * - * @return int + * Return: Int. */ int qed_spq_post(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent, u8 *fw_return_code); /** - * @brief qed_spq_allocate - Alloocates & initializes the SPQ and EQ. + * qed_spq_alloc(): Alloocates & initializes the SPQ and EQ. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_spq_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_spq_setup - Reset the SPQ to its start state. + * qed_spq_setup(): Reset the SPQ to its start state. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_spq_setup(struct qed_hwfn *p_hwfn); /** - * @brief qed_spq_deallocate - Deallocates the given SPQ struct. + * qed_spq_free(): Deallocates the given SPQ struct. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_spq_free(struct qed_hwfn *p_hwfn); /** - * @brief qed_spq_get_entry - Obtain an entrry from the spq - * free pool list. - * - * + * qed_spq_get_entry(): Obtain an entrry from the spq + * free pool list. * - * @param p_hwfn - * @param pp_ent + * @p_hwfn: HW device data. + * @pp_ent: PP ENT. * - * @return int + * Return: Int. */ int qed_spq_get_entry(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent); /** - * @brief qed_spq_return_entry - Return an entry to spq free - * pool list + * qed_spq_return_entry(): Return an entry to spq free pool list. * - * @param p_hwfn - * @param p_ent + * @p_hwfn: HW device data. + * @p_ent: P ENT. + * + * Return: Void. */ void qed_spq_return_entry(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent); /** - * @brief qed_eq_allocate - Allocates & initializes an EQ struct + * qed_eq_alloc(): Allocates & initializes an EQ struct. * - * @param p_hwfn - * @param num_elem number of elements in the eq + * @p_hwfn: HW device data. + * @num_elem: number of elements in the eq. * - * @return int + * Return: Int. */ int qed_eq_alloc(struct qed_hwfn *p_hwfn, u16 num_elem); /** - * @brief qed_eq_setup - Reset the EQ to its start state. + * qed_eq_setup(): Reset the EQ to its start state. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_eq_setup(struct qed_hwfn *p_hwfn); /** - * @brief qed_eq_free - deallocates the given EQ struct. + * qed_eq_free(): deallocates the given EQ struct. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_eq_free(struct qed_hwfn *p_hwfn); /** - * @brief qed_eq_prod_update - update the FW with default EQ producer + * qed_eq_prod_update(): update the FW with default EQ producer. + * + * @p_hwfn: HW device data. + * @prod: Prod. * - * @param p_hwfn - * @param prod + * Return: Void. */ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod); /** - * @brief qed_eq_completion - Completes currently pending EQ elements + * qed_eq_completion(): Completes currently pending EQ elements. * - * @param p_hwfn - * @param cookie + * @p_hwfn: HW device data. + * @cookie: Cookie. * - * @return int + * Return: Int. */ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie); /** - * @brief qed_spq_completion - Completes a single event + * qed_spq_completion(): Completes a single event. * - * @param p_hwfn - * @param echo - echo value from cookie (used for determining completion) - * @param p_data - data from cookie (used in callback function if applicable) + * @p_hwfn: HW device data. + * @echo: echo value from cookie (used for determining completion). + * @fw_return_code: FW return code. + * @p_data: data from cookie (used in callback function if applicable). * - * @return int + * Return: Int. */ int qed_spq_completion(struct qed_hwfn *p_hwfn, __le16 echo, @@ -325,44 +331,43 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, union event_ring_data *p_data); /** - * @brief qed_spq_get_cid - Given p_hwfn, return cid for the hwfn's SPQ + * qed_spq_get_cid(): Given p_hwfn, return cid for the hwfn's SPQ. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return u32 - SPQ CID + * Return: u32 - SPQ CID. */ u32 qed_spq_get_cid(struct qed_hwfn *p_hwfn); /** - * @brief qed_consq_alloc - Allocates & initializes an ConsQ - * struct + * qed_consq_alloc(): Allocates & initializes an ConsQ struct. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_consq_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_consq_setup - Reset the ConsQ to its start state. + * qed_consq_setup(): Reset the ConsQ to its start state. * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return Void. */ void qed_consq_setup(struct qed_hwfn *p_hwfn); /** - * @brief qed_consq_free - deallocates the given ConsQ struct. + * qed_consq_free(): deallocates the given ConsQ struct. + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return Void. */ void qed_consq_free(struct qed_hwfn *p_hwfn); int qed_spq_pend_post(struct qed_hwfn *p_hwfn); -/** - * @file - * - * @brief Slow-hwfn low-level commands (Ramrods) function definitions. - */ +/* Slow-hwfn low-level commands (Ramrods) function definitions. */ #define QED_SP_EQ_COMPLETION 0x01 #define QED_SP_CQE_COMPLETION 0x02 @@ -377,12 +382,15 @@ struct qed_sp_init_data { }; /** - * @brief Returns a SPQ entry to the pool / frees the entry if allocated. - * Should be called on in error flows after initializing the SPQ entry - * and before posting it. + * qed_sp_destroy_request(): Returns a SPQ entry to the pool / frees the + * entry if allocated. Should be called on in error + * flows after initializing the SPQ entry + * and before posting it. + * + * @p_hwfn: HW device data. + * @p_ent: Ent. * - * @param p_hwfn - * @param p_ent + * Return: Void. */ void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent); @@ -394,7 +402,14 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_sp_init_data *p_data); /** - * @brief qed_sp_pf_start - PF Function Start Ramrod + * qed_sp_pf_start(): PF Function Start Ramrod. + * + * @p_hwfn: HW device data. + * @p_ptt: P_ptt. + * @p_tunn: P_tunn. + * @allow_npar_tx_switch: Allow NPAR TX Switch. + * + * Return: Int. * * This ramrod is sent to initialize a physical function (PF). It will * configure the function related parameters and write its completion to the @@ -404,12 +419,6 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, * allocated by the driver on host memory and its parameters are written * to the internal RAM of the UStorm by the Function Start Ramrod. * - * @param p_hwfn - * @param p_ptt - * @param p_tunn - * @param allow_npar_tx_switch - * - * @return int */ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, @@ -418,47 +427,33 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, bool allow_npar_tx_switch); /** - * @brief qed_sp_pf_update - PF Function Update Ramrod + * qed_sp_pf_update(): PF Function Update Ramrod. * - * This ramrod updates function-related parameters. Every parameter can be - * updated independently, according to configuration flags. + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Int. * - * @return int + * This ramrod updates function-related parameters. Every parameter can be + * updated independently, according to configuration flags. */ int qed_sp_pf_update(struct qed_hwfn *p_hwfn); /** - * @brief qed_sp_pf_update_stag - Update firmware of new outer tag + * qed_sp_pf_update_stag(): Update firmware of new outer tag. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn); /** - * @brief qed_sp_pf_stop - PF Function Stop Ramrod - * - * This ramrod is sent to close a Physical Function (PF). It is the last ramrod - * sent and the last completion written to the PFs Event Ring. This ramrod also - * deletes the context for the Slowhwfn connection on this PF. - * - * @note Not required for first packet. - * - * @param p_hwfn - * - * @return int - */ - -/** - * @brief qed_sp_pf_update_ufp - PF ufp update Ramrod + * qed_sp_pf_update_ufp(): PF ufp update Ramrod. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_sp_pf_update_ufp(struct qed_hwfn *p_hwfn); @@ -470,11 +465,11 @@ int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn, enum spq_mode comp_mode, struct qed_spq_comp_cb *p_comp_data); /** - * @brief qed_sp_heartbeat_ramrod - Send empty Ramrod + * qed_sp_heartbeat_ramrod(): Send empty Ramrod. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_sp_heartbeat_ramrod(struct qed_hwfn *p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h index eacd6457f195..9f81295c6f45 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h @@ -250,29 +250,31 @@ extern const struct qed_iov_hv_ops qed_iov_ops_pass; #ifdef CONFIG_QED_SRIOV /** - * @brief Check if given VF ID @vfid is valid - * w.r.t. @b_enabled_only value - * if b_enabled_only = true - only enabled VF id is valid - * else any VF id less than max_vfs is valid + * qed_iov_is_valid_vfid(): Check if given VF ID @vfid is valid + * w.r.t. @b_enabled_only value + * if b_enabled_only = true - only enabled + * VF id is valid. + * else any VF id less than max_vfs is valid. * - * @param p_hwfn - * @param rel_vf_id - Relative VF ID - * @param b_enabled_only - consider only enabled VF - * @param b_non_malicious - true iff we want to validate vf isn't malicious. + * @p_hwfn: HW device data. + * @rel_vf_id: Relative VF ID. + * @b_enabled_only: consider only enabled VF. + * @b_non_malicious: true iff we want to validate vf isn't malicious. * - * @return bool - true for valid VF ID + * Return: bool - true for valid VF ID */ bool qed_iov_is_valid_vfid(struct qed_hwfn *p_hwfn, int rel_vf_id, bool b_enabled_only, bool b_non_malicious); /** - * @brief - Given a VF index, return index of next [including that] active VF. + * qed_iov_get_next_active_vf(): Given a VF index, return index of + * next [including that] active VF. * - * @param p_hwfn - * @param rel_vf_id + * @p_hwfn: HW device data. + * @rel_vf_id: VF ID. * - * @return MAX_NUM_VFS in case no further active VFs, otherwise index. + * Return: MAX_NUM_VFS in case no further active VFs, otherwise index. */ u16 qed_iov_get_next_active_vf(struct qed_hwfn *p_hwfn, u16 rel_vf_id); @@ -280,83 +282,92 @@ void qed_iov_bulletin_set_udp_ports(struct qed_hwfn *p_hwfn, int vfid, u16 vxlan_port, u16 geneve_port); /** - * @brief Read sriov related information and allocated resources - * reads from configuration space, shmem, etc. + * qed_iov_hw_info(): Read sriov related information and allocated resources + * reads from configuration space, shmem, etc. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_iov_hw_info(struct qed_hwfn *p_hwfn); /** - * @brief qed_add_tlv - place a given tlv on the tlv buffer at next offset + * qed_add_tlv(): place a given tlv on the tlv buffer at next offset * - * @param p_hwfn - * @param p_iov - * @param type - * @param length + * @p_hwfn: HW device data. + * @offset: offset. + * @type: Type + * @length: Length. * - * @return pointer to the newly placed tlv + * Return: pointer to the newly placed tlv */ void *qed_add_tlv(struct qed_hwfn *p_hwfn, u8 **offset, u16 type, u16 length); /** - * @brief list the types and lengths of the tlvs on the buffer + * qed_dp_tlv_list(): list the types and lengths of the tlvs on the buffer * - * @param p_hwfn - * @param tlvs_list + * @p_hwfn: HW device data. + * @tlvs_list: Tlvs_list. + * + * Return: Void. */ void qed_dp_tlv_list(struct qed_hwfn *p_hwfn, void *tlvs_list); /** - * @brief qed_iov_alloc - allocate sriov related resources + * qed_iov_alloc(): allocate sriov related resources * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_iov_alloc(struct qed_hwfn *p_hwfn); /** - * @brief qed_iov_setup - setup sriov related resources + * qed_iov_setup(): setup sriov related resources + * + * @p_hwfn: HW device data. * - * @param p_hwfn + * Return: Void. */ void qed_iov_setup(struct qed_hwfn *p_hwfn); /** - * @brief qed_iov_free - free sriov related resources + * qed_iov_free(): free sriov related resources * - * @param p_hwfn + * @p_hwfn: HW device data. + * + * Return: Void. */ void qed_iov_free(struct qed_hwfn *p_hwfn); /** - * @brief free sriov related memory that was allocated during hw_prepare + * qed_iov_free_hw_info(): free sriov related memory that was + * allocated during hw_prepare + * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: Void. */ void qed_iov_free_hw_info(struct qed_dev *cdev); /** - * @brief Mark structs of vfs that have been FLR-ed. + * qed_iov_mark_vf_flr(): Mark structs of vfs that have been FLR-ed. * - * @param p_hwfn - * @param disabled_vfs - bitmask of all VFs on path that were FLRed + * @p_hwfn: HW device data. + * @disabled_vfs: bitmask of all VFs on path that were FLRed * - * @return true iff one of the PF's vfs got FLRed. false otherwise. + * Return: true iff one of the PF's vfs got FLRed. false otherwise. */ bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *disabled_vfs); /** - * @brief Search extended TLVs in request/reply buffer. + * qed_iov_search_list_tlvs(): Search extended TLVs in request/reply buffer. * - * @param p_hwfn - * @param p_tlvs_list - Pointer to tlvs list - * @param req_type - Type of TLV + * @p_hwfn: HW device data. + * @p_tlvs_list: Pointer to tlvs list + * @req_type: Type of TLV * - * @return pointer to tlv type if found, otherwise returns NULL. + * Return: pointer to tlv type if found, otherwise returns NULL. */ void *qed_iov_search_list_tlvs(struct qed_hwfn *p_hwfn, void *p_tlvs_list, u16 req_type); diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 60d2bb64e65f..976201fc7d4a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -688,13 +688,16 @@ struct qed_vf_iov { }; /** - * @brief VF - Set Rx/Tx coalesce per VF's relative queue. - * Coalesce value '0' will omit the configuration. + * qed_vf_pf_set_coalesce(): VF - Set Rx/Tx coalesce per VF's relative queue. + * Coalesce value '0' will omit the + * configuration. * - * @param p_hwfn - * @param rx_coal - coalesce value in micro second for rx queue - * @param tx_coal - coalesce value in micro second for tx queue - * @param p_cid - queue cid + * @p_hwfn: HW device data. + * @rx_coal: coalesce value in micro second for rx queue. + * @tx_coal: coalesce value in micro second for tx queue. + * @p_cid: queue cid. + * + * Return: Int. * **/ int qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, @@ -702,148 +705,172 @@ int qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, u16 tx_coal, struct qed_queue_cid *p_cid); /** - * @brief VF - Get coalesce per VF's relative queue. + * qed_vf_pf_get_coalesce(): VF - Get coalesce per VF's relative queue. * - * @param p_hwfn - * @param p_coal - coalesce value in micro second for VF queues. - * @param p_cid - queue cid + * @p_hwfn: HW device data. + * @p_coal: coalesce value in micro second for VF queues. + * @p_cid: queue cid. * + * Return: Int. **/ int qed_vf_pf_get_coalesce(struct qed_hwfn *p_hwfn, u16 *p_coal, struct qed_queue_cid *p_cid); #ifdef CONFIG_QED_SRIOV /** - * @brief Read the VF bulletin and act on it if needed + * qed_vf_read_bulletin(): Read the VF bulletin and act on it if needed. * - * @param p_hwfn - * @param p_change - qed fills 1 iff bulletin board has changed, 0 otherwise. + * @p_hwfn: HW device data. + * @p_change: qed fills 1 iff bulletin board has changed, 0 otherwise. * - * @return enum _qed_status + * Return: enum _qed_status. */ int qed_vf_read_bulletin(struct qed_hwfn *p_hwfn, u8 *p_change); /** - * @brief Get link paramters for VF from qed + * qed_vf_get_link_params(): Get link parameters for VF from qed + * + * @p_hwfn: HW device data. + * @params: the link params structure to be filled for the VF. * - * @param p_hwfn - * @param params - the link params structure to be filled for the VF + * Return: Void. */ void qed_vf_get_link_params(struct qed_hwfn *p_hwfn, struct qed_mcp_link_params *params); /** - * @brief Get link state for VF from qed + * qed_vf_get_link_state(): Get link state for VF from qed. + * + * @p_hwfn: HW device data. + * @link: the link state structure to be filled for the VF * - * @param p_hwfn - * @param link - the link state structure to be filled for the VF + * Return: Void. */ void qed_vf_get_link_state(struct qed_hwfn *p_hwfn, struct qed_mcp_link_state *link); /** - * @brief Get link capabilities for VF from qed + * qed_vf_get_link_caps(): Get link capabilities for VF from qed. * - * @param p_hwfn - * @param p_link_caps - the link capabilities structure to be filled for the VF + * @p_hwfn: HW device data. + * @p_link_caps: the link capabilities structure to be filled for the VF + * + * Return: Void. */ void qed_vf_get_link_caps(struct qed_hwfn *p_hwfn, struct qed_mcp_link_capabilities *p_link_caps); /** - * @brief Get number of Rx queues allocated for VF by qed + * qed_vf_get_num_rxqs(): Get number of Rx queues allocated for VF by qed + * + * @p_hwfn: HW device data. + * @num_rxqs: allocated RX queues * - * @param p_hwfn - * @param num_rxqs - allocated RX queues + * Return: Void. */ void qed_vf_get_num_rxqs(struct qed_hwfn *p_hwfn, u8 *num_rxqs); /** - * @brief Get number of Rx queues allocated for VF by qed + * qed_vf_get_num_txqs(): Get number of Rx queues allocated for VF by qed * - * @param p_hwfn - * @param num_txqs - allocated RX queues + * @p_hwfn: HW device data. + * @num_txqs: allocated RX queues + * + * Return: Void. */ void qed_vf_get_num_txqs(struct qed_hwfn *p_hwfn, u8 *num_txqs); /** - * @brief Get number of available connections [both Rx and Tx] for VF + * qed_vf_get_num_cids(): Get number of available connections + * [both Rx and Tx] for VF + * + * @p_hwfn: HW device data. + * @num_cids: allocated number of connections * - * @param p_hwfn - * @param num_cids - allocated number of connections + * Return: Void. */ void qed_vf_get_num_cids(struct qed_hwfn *p_hwfn, u8 *num_cids); /** - * @brief Get port mac address for VF + * qed_vf_get_port_mac(): Get port mac address for VF. * - * @param p_hwfn - * @param port_mac - destination location for port mac + * @p_hwfn: HW device data. + * @port_mac: destination location for port mac + * + * Return: Void. */ void qed_vf_get_port_mac(struct qed_hwfn *p_hwfn, u8 *port_mac); /** - * @brief Get number of VLAN filters allocated for VF by qed + * qed_vf_get_num_vlan_filters(): Get number of VLAN filters allocated + * for VF by qed. + * + * @p_hwfn: HW device data. + * @num_vlan_filters: allocated VLAN filters * - * @param p_hwfn - * @param num_rxqs - allocated VLAN filters + * Return: Void. */ void qed_vf_get_num_vlan_filters(struct qed_hwfn *p_hwfn, u8 *num_vlan_filters); /** - * @brief Get number of MAC filters allocated for VF by qed + * qed_vf_get_num_mac_filters(): Get number of MAC filters allocated + * for VF by qed * - * @param p_hwfn - * @param num_rxqs - allocated MAC filters + * @p_hwfn: HW device data. + * @num_mac_filters: allocated MAC filters + * + * Return: Void. */ void qed_vf_get_num_mac_filters(struct qed_hwfn *p_hwfn, u8 *num_mac_filters); /** - * @brief Check if VF can set a MAC address + * qed_vf_check_mac(): Check if VF can set a MAC address * - * @param p_hwfn - * @param mac + * @p_hwfn: HW device data. + * @mac: Mac. * - * @return bool + * Return: bool. */ bool qed_vf_check_mac(struct qed_hwfn *p_hwfn, u8 *mac); /** - * @brief Set firmware version information in dev_info from VFs acquire response tlv + * qed_vf_get_fw_version(): Set firmware version information + * in dev_info from VFs acquire response tlv + * + * @p_hwfn: HW device data. + * @fw_major: FW major. + * @fw_minor: FW minor. + * @fw_rev: FW rev. + * @fw_eng: FW eng. * - * @param p_hwfn - * @param fw_major - * @param fw_minor - * @param fw_rev - * @param fw_eng + * Return: Void. */ void qed_vf_get_fw_version(struct qed_hwfn *p_hwfn, u16 *fw_major, u16 *fw_minor, u16 *fw_rev, u16 *fw_eng); /** - * @brief hw preparation for VF - * sends ACQUIRE message + * qed_vf_hw_prepare(): hw preparation for VF sends ACQUIRE message * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return int + * Return: Int. */ int qed_vf_hw_prepare(struct qed_hwfn *p_hwfn); /** - * @brief VF - start the RX Queue by sending a message to the PF - * @param p_hwfn - * @param p_cid - Only relative fields are relevant - * @param bd_max_bytes - maximum number of bytes per bd - * @param bd_chain_phys_addr - physical address of bd chain - * @param cqe_pbl_addr - physical address of pbl - * @param cqe_pbl_size - pbl size - * @param pp_prod - pointer to the producer to be - * used in fastpath + * qed_vf_pf_rxq_start(): start the RX Queue by sending a message to the PF + * + * @p_hwfn: HW device data. + * @p_cid: Only relative fields are relevant + * @bd_max_bytes: maximum number of bytes per bd + * @bd_chain_phys_addr: physical address of bd chain + * @cqe_pbl_addr: physical address of pbl + * @cqe_pbl_size: pbl size + * @pp_prod: pointer to the producer to be used in fastpath * - * @return int + * Return: Int. */ int qed_vf_pf_rxq_start(struct qed_hwfn *p_hwfn, struct qed_queue_cid *p_cid, @@ -853,18 +880,16 @@ int qed_vf_pf_rxq_start(struct qed_hwfn *p_hwfn, u16 cqe_pbl_size, void __iomem **pp_prod); /** - * @brief VF - start the TX queue by sending a message to the - * PF. + * qed_vf_pf_txq_start(): VF - start the TX queue by sending a message to the + * PF. * - * @param p_hwfn - * @param tx_queue_id - zero based within the VF - * @param sb - status block for this queue - * @param sb_index - index within the status block - * @param bd_chain_phys_addr - physical address of tx chain - * @param pp_doorbell - pointer to address to which to - * write the doorbell too.. + * @p_hwfn: HW device data. + * @p_cid: CID. + * @pbl_addr: PBL address. + * @pbl_size: PBL Size. + * @pp_doorbell: pointer to address to which to write the doorbell too. * - * @return int + * Return: Int. */ int qed_vf_pf_txq_start(struct qed_hwfn *p_hwfn, @@ -873,90 +898,91 @@ qed_vf_pf_txq_start(struct qed_hwfn *p_hwfn, u16 pbl_size, void __iomem **pp_doorbell); /** - * @brief VF - stop the RX queue by sending a message to the PF + * qed_vf_pf_rxq_stop(): VF - stop the RX queue by sending a message to the PF. * - * @param p_hwfn - * @param p_cid - * @param cqe_completion + * @p_hwfn: HW device data. + * @p_cid: CID. + * @cqe_completion: CQE Completion. * - * @return int + * Return: Int. */ int qed_vf_pf_rxq_stop(struct qed_hwfn *p_hwfn, struct qed_queue_cid *p_cid, bool cqe_completion); /** - * @brief VF - stop the TX queue by sending a message to the PF + * qed_vf_pf_txq_stop(): VF - stop the TX queue by sending a message to the PF. * - * @param p_hwfn - * @param tx_qid + * @p_hwfn: HW device data. + * @p_cid: CID. * - * @return int + * Return: Int. */ int qed_vf_pf_txq_stop(struct qed_hwfn *p_hwfn, struct qed_queue_cid *p_cid); /** - * @brief VF - send a vport update command + * qed_vf_pf_vport_update(): VF - send a vport update command. * - * @param p_hwfn - * @param params + * @p_hwfn: HW device data. + * @p_params: Params * - * @return int + * Return: Int. */ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn, struct qed_sp_vport_update_params *p_params); /** + * qed_vf_pf_reset(): VF - send a close message to PF. * - * @brief VF - send a close message to PF + * @p_hwfn: HW device data. * - * @param p_hwfn - * - * @return enum _qed_status + * Return: enum _qed_status */ int qed_vf_pf_reset(struct qed_hwfn *p_hwfn); /** - * @brief VF - free vf`s memories + * qed_vf_pf_release(): VF - free vf`s memories. * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return enum _qed_status + * Return: enum _qed_status */ int qed_vf_pf_release(struct qed_hwfn *p_hwfn); /** - * @brief qed_vf_get_igu_sb_id - Get the IGU SB ID for a given + * qed_vf_get_igu_sb_id(): Get the IGU SB ID for a given * sb_id. For VFs igu sbs don't have to be contiguous * - * @param p_hwfn - * @param sb_id + * @p_hwfn: HW device data. + * @sb_id: SB ID. * - * @return INLINE u16 + * Return: INLINE u16 */ u16 qed_vf_get_igu_sb_id(struct qed_hwfn *p_hwfn, u16 sb_id); /** - * @brief Stores [or removes] a configured sb_info. + * qed_vf_set_sb_info(): Stores [or removes] a configured sb_info. + * + * @p_hwfn: HW device data. + * @sb_id: zero-based SB index [for fastpath] + * @p_sb: may be NULL [during removal]. * - * @param p_hwfn - * @param sb_id - zero-based SB index [for fastpath] - * @param sb_info - may be NULL [during removal]. + * Return: Void. */ void qed_vf_set_sb_info(struct qed_hwfn *p_hwfn, u16 sb_id, struct qed_sb_info *p_sb); /** - * @brief qed_vf_pf_vport_start - perform vport start for VF. + * qed_vf_pf_vport_start(): perform vport start for VF. * - * @param p_hwfn - * @param vport_id - * @param mtu - * @param inner_vlan_removal - * @param tpa_mode - * @param max_buffers_per_cqe, - * @param only_untagged - default behavior regarding vlan acceptance + * @p_hwfn: HW device data. + * @vport_id: Vport ID. + * @mtu: MTU. + * @inner_vlan_removal: Innter VLAN removal. + * @tpa_mode: TPA mode + * @max_buffers_per_cqe: Max buffer pre CQE. + * @only_untagged: default behavior regarding vlan acceptance * - * @return enum _qed_status + * Return: enum _qed_status */ int qed_vf_pf_vport_start(struct qed_hwfn *p_hwfn, u8 vport_id, @@ -966,11 +992,11 @@ int qed_vf_pf_vport_start(struct qed_hwfn *p_hwfn, u8 max_buffers_per_cqe, u8 only_untagged); /** - * @brief qed_vf_pf_vport_stop - stop the VF's vport + * qed_vf_pf_vport_stop(): stop the VF's vport * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return enum _qed_status + * Return: enum _qed_status */ int qed_vf_pf_vport_stop(struct qed_hwfn *p_hwfn); @@ -981,42 +1007,49 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn, struct qed_filter_mcast *p_filter_cmd); /** - * @brief qed_vf_pf_int_cleanup - clean the SB of the VF + * qed_vf_pf_int_cleanup(): clean the SB of the VF * - * @param p_hwfn + * @p_hwfn: HW device data. * - * @return enum _qed_status + * Return: enum _qed_status */ int qed_vf_pf_int_cleanup(struct qed_hwfn *p_hwfn); /** - * @brief - return the link params in a given bulletin board + * __qed_vf_get_link_params(): return the link params in a given bulletin board * - * @param p_hwfn - * @param p_params - pointer to a struct to fill with link params - * @param p_bulletin + * @p_hwfn: HW device data. + * @p_params: pointer to a struct to fill with link params + * @p_bulletin: Bulletin. + * + * Return: Void. */ void __qed_vf_get_link_params(struct qed_hwfn *p_hwfn, struct qed_mcp_link_params *p_params, struct qed_bulletin_content *p_bulletin); /** - * @brief - return the link state in a given bulletin board + * __qed_vf_get_link_state(): return the link state in a given bulletin board + * + * @p_hwfn: HW device data. + * @p_link: pointer to a struct to fill with link state + * @p_bulletin: Bulletin. * - * @param p_hwfn - * @param p_link - pointer to a struct to fill with link state - * @param p_bulletin + * Return: Void. */ void __qed_vf_get_link_state(struct qed_hwfn *p_hwfn, struct qed_mcp_link_state *p_link, struct qed_bulletin_content *p_bulletin); /** - * @brief - return the link capabilities in a given bulletin board + * __qed_vf_get_link_caps(): return the link capabilities in a given + * bulletin board * - * @param p_hwfn - * @param p_link - pointer to a struct to fill with link capabilities - * @param p_bulletin + * @p_hwfn: HW device data. + * @p_link_caps: pointer to a struct to fill with link capabilities + * @p_bulletin: Bulletin. + * + * Return: Void. */ void __qed_vf_get_link_caps(struct qed_hwfn *p_hwfn, struct qed_mcp_link_capabilities *p_link_caps, @@ -1029,9 +1062,13 @@ int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, u32 qed_vf_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id); /** - * @brief - Ask PF to update the MAC address in it's bulletin board + * qed_vf_pf_bulletin_update_mac(): Ask PF to update the MAC address in + * it's bulletin board + * + * @p_hwfn: HW device data. + * @p_mac: mac address to be updated in bulletin board * - * @param p_mac - mac address to be updated in bulletin board + * Return: Int. */ int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, u8 *p_mac); diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 75adb71adf18..be33bde0f731 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -2800,10 +2800,13 @@ static void qede_get_eth_tlv_data(void *dev, void *data) } /** - * qede_io_error_detected - called when PCI error is detected + * qede_io_error_detected(): Called when PCI error is detected + * * @pdev: Pointer to PCI device * @state: The current pci connection state * + *Return: pci_ers_result_t. + * * This function is called after a PCI bus error affecting * this device has been detected. */ diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index f34dbd0db795..a84063492c71 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -268,14 +268,15 @@ static inline dma_addr_t qed_chain_get_pbl_phys(const struct qed_chain *chain) } /** - * @brief qed_chain_advance_page - + * qed_chain_advance_page(): Advance the next element across pages for a + * linked chain. * - * Advance the next element across pages for a linked chain + * @p_chain: P_chain. + * @p_next_elem: P_next_elem. + * @idx_to_inc: Idx_to_inc. + * @page_to_inc: page_to_inc. * - * @param p_chain - * @param p_next_elem - * @param idx_to_inc - * @param page_to_inc + * Return: Void. */ static inline void qed_chain_advance_page(struct qed_chain *p_chain, @@ -336,12 +337,14 @@ qed_chain_advance_page(struct qed_chain *p_chain, } while (0) /** - * @brief qed_chain_return_produced - + * qed_chain_return_produced(): A chain in which the driver "Produces" + * elements should use this API + * to indicate previous produced elements + * are now consumed. * - * A chain in which the driver "Produces" elements should use this API - * to indicate previous produced elements are now consumed. + * @p_chain: Chain. * - * @param p_chain + * Return: Void. */ static inline void qed_chain_return_produced(struct qed_chain *p_chain) { @@ -353,15 +356,15 @@ static inline void qed_chain_return_produced(struct qed_chain *p_chain) } /** - * @brief qed_chain_produce - + * qed_chain_produce(): A chain in which the driver "Produces" + * elements should use this to get a pointer to + * the next element which can be "Produced". It's driver + * responsibility to validate that the chain has room for + * new element. * - * A chain in which the driver "Produces" elements should use this to get - * a pointer to the next element which can be "Produced". It's driver - * responsibility to validate that the chain has room for new element. + * @p_chain: Chain. * - * @param p_chain - * - * @return void*, a pointer to next element + * Return: void*, a pointer to next element. */ static inline void *qed_chain_produce(struct qed_chain *p_chain) { @@ -395,14 +398,11 @@ static inline void *qed_chain_produce(struct qed_chain *p_chain) } /** - * @brief qed_chain_get_capacity - - * - * Get the maximum number of BDs in chain + * qed_chain_get_capacity(): Get the maximum number of BDs in chain * - * @param p_chain - * @param num + * @p_chain: Chain. * - * @return number of unusable BDs + * Return: number of unusable BDs. */ static inline u32 qed_chain_get_capacity(struct qed_chain *p_chain) { @@ -410,12 +410,14 @@ static inline u32 qed_chain_get_capacity(struct qed_chain *p_chain) } /** - * @brief qed_chain_recycle_consumed - + * qed_chain_recycle_consumed(): Returns an element which was + * previously consumed; + * Increments producers so they could + * be written to FW. * - * Returns an element which was previously consumed; - * Increments producers so they could be written to FW. + * @p_chain: Chain. * - * @param p_chain + * Return: Void. */ static inline void qed_chain_recycle_consumed(struct qed_chain *p_chain) { @@ -427,14 +429,13 @@ static inline void qed_chain_recycle_consumed(struct qed_chain *p_chain) } /** - * @brief qed_chain_consume - + * qed_chain_consume(): A Chain in which the driver utilizes data written + * by a different source (i.e., FW) should use this to + * access passed buffers. * - * A Chain in which the driver utilizes data written by a different source - * (i.e., FW) should use this to access passed buffers. + * @p_chain: Chain. * - * @param p_chain - * - * @return void*, a pointer to the next buffer written + * Return: void*, a pointer to the next buffer written. */ static inline void *qed_chain_consume(struct qed_chain *p_chain) { @@ -468,9 +469,11 @@ static inline void *qed_chain_consume(struct qed_chain *p_chain) } /** - * @brief qed_chain_reset - Resets the chain to its start state + * qed_chain_reset(): Resets the chain to its start state. + * + * @p_chain: pointer to a previously allocated chain. * - * @param p_chain pointer to a previously allocated chain + * Return Void. */ static inline void qed_chain_reset(struct qed_chain *p_chain) { @@ -519,13 +522,12 @@ static inline void qed_chain_reset(struct qed_chain *p_chain) } /** - * @brief qed_chain_get_last_elem - + * qed_chain_get_last_elem(): Returns a pointer to the last element of the + * chain. * - * Returns a pointer to the last element of the chain + * @p_chain: Chain. * - * @param p_chain - * - * @return void* + * Return: void*. */ static inline void *qed_chain_get_last_elem(struct qed_chain *p_chain) { @@ -563,10 +565,13 @@ out: } /** - * @brief qed_chain_set_prod - sets the prod to the given value + * qed_chain_set_prod(): sets the prod to the given value. + * + * @p_chain: Chain. + * @prod_idx: Prod Idx. + * @p_prod_elem: Prod elem. * - * @param prod_idx - * @param p_prod_elem + * Return Void. */ static inline void qed_chain_set_prod(struct qed_chain *p_chain, u32 prod_idx, void *p_prod_elem) @@ -610,9 +615,11 @@ static inline void qed_chain_set_prod(struct qed_chain *p_chain, } /** - * @brief qed_chain_pbl_zero_mem - set chain memory to 0 + * qed_chain_pbl_zero_mem(): set chain memory to 0. + * + * @p_chain: Chain. * - * @param p_chain + * Return: Void. */ static inline void qed_chain_pbl_zero_mem(struct qed_chain *p_chain) { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 850b98991670..f39451aaaeec 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -819,47 +819,47 @@ struct qed_common_cb_ops { struct qed_selftest_ops { /** - * @brief selftest_interrupt - Perform interrupt test + * selftest_interrupt(): Perform interrupt test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*selftest_interrupt)(struct qed_dev *cdev); /** - * @brief selftest_memory - Perform memory test + * selftest_memory(): Perform memory test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*selftest_memory)(struct qed_dev *cdev); /** - * @brief selftest_register - Perform register test + * selftest_register(): Perform register test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*selftest_register)(struct qed_dev *cdev); /** - * @brief selftest_clock - Perform clock test + * selftest_clock(): Perform clock test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*selftest_clock)(struct qed_dev *cdev); /** - * @brief selftest_nvram - Perform nvram test + * selftest_nvram(): Perform nvram test. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*selftest_nvram) (struct qed_dev *cdev); }; @@ -927,47 +927,53 @@ struct qed_common_ops { enum qed_hw_err_type err_type); /** - * @brief can_link_change - can the instance change the link or not + * can_link_change(): can the instance change the link or not. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return true if link-change is allowed, false otherwise. + * Return: true if link-change is allowed, false otherwise. */ bool (*can_link_change)(struct qed_dev *cdev); /** - * @brief set_link - set links according to params + * set_link(): set links according to params. * - * @param cdev - * @param params - values used to override the default link configuration + * @cdev: Qed dev pointer. + * @params: values used to override the default link configuration. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*set_link)(struct qed_dev *cdev, struct qed_link_params *params); /** - * @brief get_link - returns the current link state. + * get_link(): returns the current link state. * - * @param cdev - * @param if_link - structure to be filled with current link configuration. + * @cdev: Qed dev pointer. + * @if_link: structure to be filled with current link configuration. + * + * Return: Void. */ void (*get_link)(struct qed_dev *cdev, struct qed_link_output *if_link); /** - * @brief - drains chip in case Tx completions fail to arrive due to pause. + * drain(): drains chip in case Tx completions fail to arrive due to pause. + * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: Int. */ int (*drain)(struct qed_dev *cdev); /** - * @brief update_msglvl - update module debug level + * update_msglvl(): update module debug level. * - * @param cdev - * @param dp_module - * @param dp_level + * @cdev: Qed dev pointer. + * @dp_module: Debug module. + * @dp_level: Debug level. + * + * Return: Void. */ void (*update_msglvl)(struct qed_dev *cdev, u32 dp_module, @@ -981,70 +987,73 @@ struct qed_common_ops { struct qed_chain *p_chain); /** - * @brief nvm_flash - Flash nvm data. + * nvm_flash(): Flash nvm data. * - * @param cdev - * @param name - file containing the data + * @cdev: Qed dev pointer. + * @name: file containing the data. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*nvm_flash)(struct qed_dev *cdev, const char *name); /** - * @brief nvm_get_image - reads an entire image from nvram + * nvm_get_image(): reads an entire image from nvram. * - * @param cdev - * @param type - type of the request nvram image - * @param buf - preallocated buffer to fill with the image - * @param len - length of the allocated buffer + * @cdev: Qed dev pointer. + * @type: type of the request nvram image. + * @buf: preallocated buffer to fill with the image. + * @len: length of the allocated buffer. * - * @return 0 on success, error otherwise + * Return: 0 on success, error otherwise. */ int (*nvm_get_image)(struct qed_dev *cdev, enum qed_nvm_images type, u8 *buf, u16 len); /** - * @brief set_coalesce - Configure Rx coalesce value in usec + * set_coalesce(): Configure Rx coalesce value in usec. * - * @param cdev - * @param rx_coal - Rx coalesce value in usec - * @param tx_coal - Tx coalesce value in usec - * @param qid - Queue index - * @param sb_id - Status Block Id + * @cdev: Qed dev pointer. + * @rx_coal: Rx coalesce value in usec. + * @tx_coal: Tx coalesce value in usec. + * @handle: Handle. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*set_coalesce)(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, void *handle); /** - * @brief set_led - Configure LED mode + * set_led() - Configure LED mode. * - * @param cdev - * @param mode - LED mode + * @cdev: Qed dev pointer. + * @mode: LED mode. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*set_led)(struct qed_dev *cdev, enum qed_led_mode mode); /** - * @brief attn_clr_enable - Prevent attentions from being reasserted + * attn_clr_enable(): Prevent attentions from being reasserted. + * + * @cdev: Qed dev pointer. + * @clr_enable: Clear enable. * - * @param cdev - * @param clr_enable + * Return: Void. */ void (*attn_clr_enable)(struct qed_dev *cdev, bool clr_enable); /** - * @brief db_recovery_add - add doorbell information to the doorbell - * recovery mechanism. + * db_recovery_add(): add doorbell information to the doorbell + * recovery mechanism. * - * @param cdev - * @param db_addr - doorbell address - * @param db_data - address of where db_data is stored - * @param db_is_32b - doorbell is 32b pr 64b - * @param db_is_user - doorbell recovery addresses are user or kernel space + * @cdev: Qed dev pointer. + * @db_addr: Doorbell address. + * @db_data: Dddress of where db_data is stored. + * @db_width: Doorbell is 32b or 64b. + * @db_space: Doorbell recovery addresses are user or kernel space. + * + * Return: Int. */ int (*db_recovery_add)(struct qed_dev *cdev, void __iomem *db_addr, @@ -1053,114 +1062,130 @@ struct qed_common_ops { enum qed_db_rec_space db_space); /** - * @brief db_recovery_del - remove doorbell information from the doorbell + * db_recovery_del(): remove doorbell information from the doorbell * recovery mechanism. db_data serves as key (db_addr is not unique). * - * @param cdev - * @param db_addr - doorbell address - * @param db_data - address where db_data is stored. Serves as key for the - * entry to delete. + * @cdev: Qed dev pointer. + * @db_addr: Doorbell address. + * @db_data: Address where db_data is stored. Serves as key for the + * entry to delete. + * + * Return: Int. */ int (*db_recovery_del)(struct qed_dev *cdev, void __iomem *db_addr, void *db_data); /** - * @brief recovery_process - Trigger a recovery process + * recovery_process(): Trigger a recovery process. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*recovery_process)(struct qed_dev *cdev); /** - * @brief recovery_prolog - Execute the prolog operations of a recovery process + * recovery_prolog(): Execute the prolog operations of a recovery process. * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*recovery_prolog)(struct qed_dev *cdev); /** - * @brief update_drv_state - API to inform the change in the driver state. + * update_drv_state(): API to inform the change in the driver state. * - * @param cdev - * @param active + * @cdev: Qed dev pointer. + * @active: Active * + * Return: Int. */ int (*update_drv_state)(struct qed_dev *cdev, bool active); /** - * @brief update_mac - API to inform the change in the mac address + * update_mac(): API to inform the change in the mac address. * - * @param cdev - * @param mac + * @cdev: Qed dev pointer. + * @mac: MAC. * + * Return: Int. */ int (*update_mac)(struct qed_dev *cdev, u8 *mac); /** - * @brief update_mtu - API to inform the change in the mtu + * update_mtu(): API to inform the change in the mtu. * - * @param cdev - * @param mtu + * @cdev: Qed dev pointer. + * @mtu: MTU. * + * Return: Int. */ int (*update_mtu)(struct qed_dev *cdev, u16 mtu); /** - * @brief update_wol - update of changes in the WoL configuration + * update_wol(): Update of changes in the WoL configuration. + * + * @cdev: Qed dev pointer. + * @enabled: true iff WoL should be enabled. * - * @param cdev - * @param enabled - true iff WoL should be enabled. + * Return: Int. */ int (*update_wol) (struct qed_dev *cdev, bool enabled); /** - * @brief read_module_eeprom + * read_module_eeprom(): Read EEPROM. * - * @param cdev - * @param buf - buffer - * @param dev_addr - PHY device memory region - * @param offset - offset into eeprom contents to be read - * @param len - buffer length, i.e., max bytes to be read + * @cdev: Qed dev pointer. + * @buf: buffer. + * @dev_addr: PHY device memory region. + * @offset: offset into eeprom contents to be read. + * @len: buffer length, i.e., max bytes to be read. + * + * Return: Int. */ int (*read_module_eeprom)(struct qed_dev *cdev, char *buf, u8 dev_addr, u32 offset, u32 len); /** - * @brief get_affin_hwfn_idx + * get_affin_hwfn_idx(): Get affine HW function. + * + * @cdev: Qed dev pointer. * - * @param cdev + * Return: u8. */ u8 (*get_affin_hwfn_idx)(struct qed_dev *cdev); /** - * @brief read_nvm_cfg - Read NVM config attribute value. - * @param cdev - * @param buf - buffer - * @param cmd - NVM CFG command id - * @param entity_id - Entity id + * read_nvm_cfg(): Read NVM config attribute value. + * + * @cdev: Qed dev pointer. + * @buf: Buffer. + * @cmd: NVM CFG command id. + * @entity_id: Entity id. * + * Return: Int. */ int (*read_nvm_cfg)(struct qed_dev *cdev, u8 **buf, u32 cmd, u32 entity_id); /** - * @brief read_nvm_cfg - Read NVM config attribute value. - * @param cdev - * @param cmd - NVM CFG command id + * read_nvm_cfg_len(): Read NVM config attribute value. * - * @return config id length, 0 on error. + * @cdev: Qed dev pointer. + * @cmd: NVM CFG command id. + * + * Return: config id length, 0 on error. */ int (*read_nvm_cfg_len)(struct qed_dev *cdev, u32 cmd); /** - * @brief set_grc_config - Configure value for grc config id. - * @param cdev - * @param cfg_id - grc config id - * @param val - grc config value + * set_grc_config(): Configure value for grc config id. + * + * @cdev: Qed dev pointer. + * @cfg_id: grc config id + * @val: grc config value * + * Return: Int. */ int (*set_grc_config)(struct qed_dev *cdev, u32 cfg_id, u32 val); @@ -1397,18 +1422,16 @@ static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) } /** + * qed_sb_ack(): This function creates an update command for interrupts + * that is written to the IGU. * - * @brief This function creates an update command for interrupts that is - * written to the IGU. - * - * @param sb_info - This is the structure allocated and - * initialized per status block. Assumption is - * that it was initialized using qed_sb_init - * @param int_cmd - Enable/Disable/Nop - * @param upd_flg - whether igu consumer should be - * updated. + * @sb_info: This is the structure allocated and + * initialized per status block. Assumption is + * that it was initialized using qed_sb_init + * @int_cmd: Enable/Disable/Nop + * @upd_flg: Whether igu consumer should be updated. * - * @return inline void + * Return: inline void. */ static inline void qed_sb_ack(struct qed_sb_info *sb_info, enum igu_int_cmd int_cmd, diff --git a/include/linux/qed/qed_iscsi_if.h b/include/linux/qed/qed_iscsi_if.h index 04180d9af560..494cdc3cd840 100644 --- a/include/linux/qed/qed_iscsi_if.h +++ b/include/linux/qed/qed_iscsi_if.h @@ -182,7 +182,7 @@ struct qed_iscsi_cb_ops { * @param stats - pointer to struck that would be filled * we stats * @return 0 on success, error otherwise. - * @change_mac Change MAC of interface + * @change_mac: Change MAC of interface * @param cdev * @param handle - the connection handle. * @param mac - new MAC to configure. diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index ff808d248883..5b67cd03276e 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -208,57 +208,57 @@ enum qed_ll2_xmit_flags { struct qed_ll2_ops { /** - * @brief start - initializes ll2 + * start(): Initializes ll2. * - * @param cdev - * @param params - protocol driver configuration for the ll2. + * @cdev: Qed dev pointer. + * @params: Protocol driver configuration for the ll2. * - * @return 0 on success, otherwise error value. + * Return: 0 on success, otherwise error value. */ int (*start)(struct qed_dev *cdev, struct qed_ll2_params *params); /** - * @brief stop - stops the ll2 + * stop(): Stops the ll2 * - * @param cdev + * @cdev: Qed dev pointer. * - * @return 0 on success, otherwise error value. + * Return: 0 on success, otherwise error value. */ int (*stop)(struct qed_dev *cdev); /** - * @brief start_xmit - transmits an skb over the ll2 interface + * start_xmit(): Transmits an skb over the ll2 interface * - * @param cdev - * @param skb - * @param xmit_flags - Transmit options defined by the enum qed_ll2_xmit_flags. + * @cdev: Qed dev pointer. + * @skb: SKB. + * @xmit_flags: Transmit options defined by the enum qed_ll2_xmit_flags. * - * @return 0 on success, otherwise error value. + * Return: 0 on success, otherwise error value. */ int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb, unsigned long xmit_flags); /** - * @brief register_cb_ops - protocol driver register the callback for Rx/Tx + * register_cb_ops(): Protocol driver register the callback for Rx/Tx * packets. Should be called before `start'. * - * @param cdev - * @param cookie - to be passed to the callback functions. - * @param ops - the callback functions to register for Rx / Tx. + * @cdev: Qed dev pointer. + * @cookie: to be passed to the callback functions. + * @ops: the callback functions to register for Rx / Tx. * - * @return 0 on success, otherwise error value. + * Return: 0 on success, otherwise error value. */ void (*register_cb_ops)(struct qed_dev *cdev, const struct qed_ll2_cb_ops *ops, void *cookie); /** - * @brief get LL2 related statistics + * get_stats(): Get LL2 related statistics. * - * @param cdev - * @param stats - pointer to struct that would be filled with stats + * @cdev: Qed dev pointer. + * @stats: Pointer to struct that would be filled with stats. * - * @return 0 on success, error otherwise. + * Return: 0 on success, error otherwise. */ int (*get_stats)(struct qed_dev *cdev, struct qed_ll2_stats *stats); }; diff --git a/include/linux/qed/qed_nvmetcp_if.h b/include/linux/qed/qed_nvmetcp_if.h index 14671bc19ed1..1d51df347560 100644 --- a/include/linux/qed/qed_nvmetcp_if.h +++ b/include/linux/qed/qed_nvmetcp_if.h @@ -171,6 +171,23 @@ struct nvmetcp_task_params { * @param dest_port * @clear_all_filters: Clear all filters. * @param cdev + * @init_read_io: Init read IO. + * @task_params + * @cmd_pdu_header + * @nvme_cmd + * @sgl_task_params + * @init_write_io: Init write IO. + * @task_params + * @cmd_pdu_header + * @nvme_cmd + * @sgl_task_params + * @init_icreq_exchange: Exchange ICReq. + * @task_params + * @init_conn_req_pdu_hdr + * @tx_sgl_task_params + * @rx_sgl_task_params + * @init_task_cleanup: Init task cleanup. + * @task_params */ struct qed_nvmetcp_ops { const struct qed_common_ops *common; -- cgit v1.2.3 From fb09a1ed5c6e507499a9da54bfd34f71a2673961 Mon Sep 17 00:00:00 2001 From: Shai Malin Date: Mon, 4 Oct 2021 09:58:40 +0300 Subject: qed: Remove e4_ and _e4 from FW HSI The existing qed/qede/qedr/qedi/qedf code uses chip-specific naming in structures, functions, variables and defines in FW HSI (Hardware Software Interface). The new FW version introduced a generic naming convention in HSI in-which the same code will be used across different versions for simpler maintainability. It also eases in providing support for new features. With this patch every "_e4" or "e4_" prefix or suffix is not needed anymore and it will be removed. Reviewed-by: Manish Rangankar Reviewed-by: Javed Hasan Signed-off-by: Ariel Elior Signed-off-by: Omkar Kulkarni Signed-off-by: Shai Malin Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/infiniband/hw/qedr/main.c | 2 +- drivers/net/ethernet/qlogic/qed/qed.h | 4 +- drivers/net/ethernet/qlogic/qed/qed_cxt.c | 16 +- drivers/net/ethernet/qlogic/qed/qed_debug.c | 8 +- drivers/net/ethernet/qlogic/qed/qed_fcoe.c | 10 +- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 6794 ++++++++++---------- .../net/ethernet/qlogic/qed/qed_init_fw_funcs.c | 29 +- drivers/net/ethernet/qlogic/qed/qed_int.c | 4 +- drivers/net/ethernet/qlogic/qed/qed_int.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_ll2.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 4 - drivers/net/ethernet/qlogic/qed/qed_reg_addr.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_spq.c | 8 +- drivers/net/ethernet/qlogic/qed/qed_sriov.c | 10 +- drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +- drivers/scsi/qedf/drv_fcoe_fw_funcs.c | 8 +- drivers/scsi/qedf/drv_fcoe_fw_funcs.h | 2 +- drivers/scsi/qedf/qedf.h | 4 +- drivers/scsi/qedf/qedf_els.c | 2 +- drivers/scsi/qedf/qedf_io.c | 12 +- drivers/scsi/qedf/qedf_main.c | 8 +- drivers/scsi/qedi/qedi_debugfs.c | 4 +- drivers/scsi/qedi/qedi_fw.c | 40 +- drivers/scsi/qedi/qedi_fw_api.c | 22 +- drivers/scsi/qedi/qedi_fw_iscsi.h | 2 +- drivers/scsi/qedi/qedi_iscsi.h | 2 +- drivers/scsi/qedi/qedi_main.c | 8 +- include/linux/qed/common_hsi.h | 28 +- include/linux/qed/fcoe_common.h | 362 +- include/linux/qed/iscsi_common.h | 360 +- include/linux/qed/nvmetcp_common.h | 18 +- include/linux/qed/qed_if.h | 5 +- 32 files changed, 3888 insertions(+), 3896 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 755930be01b8..dc203f3d0f25 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -272,7 +272,7 @@ static int qedr_register_device(struct qedr_dev *dev) static int qedr_alloc_mem_sb(struct qedr_dev *dev, struct qed_sb_info *sb_info, u16 sb_id) { - struct status_block_e4 *sb_virt; + struct status_block *sb_virt; dma_addr_t sb_phys; int rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index b656408b9d70..cd1537bf5392 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -703,8 +703,6 @@ struct qed_dev { #define QED_IS_BB_B0(dev) (QED_IS_BB(dev) && CHIP_REV_IS_B0(dev)) #define QED_IS_AH(dev) ((dev)->type == QED_DEV_TYPE_AH) #define QED_IS_K2(dev) QED_IS_AH(dev) -#define QED_IS_E4(dev) (QED_IS_BB(dev) || QED_IS_AH(dev)) -#define QED_IS_E5(dev) ((dev)->type == QED_DEV_TYPE_E5) u16 vendor_id; @@ -903,7 +901,7 @@ static inline u8 qed_concrete_to_sw_fid(struct qed_dev *cdev, } #define PKT_LB_TC 9 -#define MAX_NUM_VOQS_E4 20 +#define MAX_NUM_VOQS 20 int qed_configure_vport_wfq(struct qed_dev *cdev, u16 vp_id, u32 rate); void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index cb0f2a3a1ac9..452494f8c298 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -54,22 +54,22 @@ /* connection context union */ union conn_context { - struct e4_core_conn_context core_ctx; - struct e4_eth_conn_context eth_ctx; - struct e4_iscsi_conn_context iscsi_ctx; - struct e4_fcoe_conn_context fcoe_ctx; - struct e4_roce_conn_context roce_ctx; + struct core_conn_context core_ctx; + struct eth_conn_context eth_ctx; + struct iscsi_conn_context iscsi_ctx; + struct fcoe_conn_context fcoe_ctx; + struct roce_conn_context roce_ctx; }; /* TYPE-0 task context - iSCSI, FCOE */ union type0_task_context { - struct e4_iscsi_task_context iscsi_ctx; - struct e4_fcoe_task_context fcoe_ctx; + struct iscsi_task_context iscsi_ctx; + struct fcoe_task_context fcoe_ctx; }; /* TYPE-1 task context - ROCE */ union type1_task_context { - struct e4_rdma_task_context roce_ctx; + struct rdma_task_context roce_ctx; }; struct src_ent { diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 6ab3e60d4928..380cf4963cbb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -4744,9 +4744,9 @@ static u32 qed_ilt_dump(struct qed_hwfn *p_hwfn, offset += qed_dump_section_hdr(dump_buf + offset, dump, "num_pf_cids_per_conn_type", 1); offset += qed_dump_num_param(dump_buf + offset, - dump, "size", NUM_OF_CONNECTION_TYPES_E4); + dump, "size", NUM_OF_CONNECTION_TYPES); for (conn_type = 0, valid_conn_pf_cids = 0; - conn_type < NUM_OF_CONNECTION_TYPES_E4; conn_type++, offset++) { + conn_type < NUM_OF_CONNECTION_TYPES; conn_type++, offset++) { u32 num_pf_cids = p_hwfn->p_cxt_mngr->conn_cfg[conn_type].cid_count; @@ -4759,9 +4759,9 @@ static u32 qed_ilt_dump(struct qed_hwfn *p_hwfn, offset += qed_dump_section_hdr(dump_buf + offset, dump, "num_vf_cids_per_conn_type", 1); offset += qed_dump_num_param(dump_buf + offset, - dump, "size", NUM_OF_CONNECTION_TYPES_E4); + dump, "size", NUM_OF_CONNECTION_TYPES); for (conn_type = 0, valid_conn_vf_cids = 0; - conn_type < NUM_OF_CONNECTION_TYPES_E4; conn_type++, offset++) { + conn_type < NUM_OF_CONNECTION_TYPES; conn_type++, offset++) { u32 num_vf_cids = p_hwfn->p_cxt_mngr->conn_cfg[conn_type].cids_per_vf; diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index b768f0698170..ba246d90344a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -89,7 +89,7 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, struct qed_fcoe_pf_params *fcoe_pf_params = NULL; struct fcoe_init_ramrod_params *p_ramrod = NULL; struct fcoe_init_func_ramrod_data *p_data; - struct e4_fcoe_conn_context *p_cxt = NULL; + struct fcoe_conn_context *p_cxt = NULL; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; struct qed_cxt_info cxt_info; @@ -144,7 +144,7 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, memset(p_cxt, 0, sizeof(*p_cxt)); SET_FIELD(p_cxt->tstorm_ag_context.flags3, - E4_TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_EN, 1); + TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_EN, 1); fcoe_pf_params->dummy_icid = (u16)dummy_cid; @@ -549,7 +549,7 @@ int qed_fcoe_alloc(struct qed_hwfn *p_hwfn) void qed_fcoe_setup(struct qed_hwfn *p_hwfn) { - struct e4_fcoe_task_context *p_task_ctx = NULL; + struct fcoe_task_context *p_task_ctx = NULL; u32 i, lc; int rc; @@ -561,7 +561,7 @@ void qed_fcoe_setup(struct qed_hwfn *p_hwfn) if (rc) continue; - memset(p_task_ctx, 0, sizeof(struct e4_fcoe_task_context)); + memset(p_task_ctx, 0, sizeof(struct fcoe_task_context)); lc = 0; SET_FIELD(lc, TIMERS_CONTEXT_VALIDLC0, 1); @@ -572,7 +572,7 @@ void qed_fcoe_setup(struct qed_hwfn *p_hwfn) p_task_ctx->timer_context.logical_client_1 = cpu_to_le32(lc); SET_FIELD(p_task_ctx->tstorm_ag_context.flags0, - E4_TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, 1); + TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE, 1); } } diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 744c82a10875..a17baa98baa4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -394,216 +394,216 @@ struct xstorm_core_conn_st_ctx { __le32 reserved0[55]; }; -struct e4_xstorm_core_conn_ag_ctx { +struct xstorm_core_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED6_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED6_SHIFT 7 u8 flags1; -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED9_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED9_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT12_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT12_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT13_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT13_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED9_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED9_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 u8 flags2; -#define E4_XSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF7_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF7_SHIFT 6 u8 flags4; -#define E4_XSTORM_CORE_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_CORE_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_DQ_CF_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 u8 flags7; -#define E4_XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED10_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED10_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED10_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED10_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF7EN_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_CORE_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED11_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED11_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF23EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF23EN_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED12_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED12_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED13_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED13_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED11_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED11_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_CF23EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_CF23EN_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED12_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED12_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED13_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED13_SHIFT 7 u8 flags11; -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED14_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED14_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED15_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RESERVED15_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED14_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED14_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED15_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RESERVED15_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE10EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE10EN_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_CORE_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT16_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT16_SHIFT 0 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT18_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT18_SHIFT 2 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT19_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT19_SHIFT 3 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT20_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT20_SHIFT 4 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT21_MASK 0x1 -#define E4_XSTORM_CORE_CONN_AG_CTX_BIT21_SHIFT 5 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF23_MASK 0x3 -#define E4_XSTORM_CORE_CONN_AG_CTX_CF23_SHIFT 6 +#define XSTORM_CORE_CONN_AG_CTX_BIT16_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT16_SHIFT 0 +#define XSTORM_CORE_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_CORE_CONN_AG_CTX_BIT18_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT18_SHIFT 2 +#define XSTORM_CORE_CONN_AG_CTX_BIT19_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT19_SHIFT 3 +#define XSTORM_CORE_CONN_AG_CTX_BIT20_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT20_SHIFT 4 +#define XSTORM_CORE_CONN_AG_CTX_BIT21_MASK 0x1 +#define XSTORM_CORE_CONN_AG_CTX_BIT21_SHIFT 5 +#define XSTORM_CORE_CONN_AG_CTX_CF23_MASK 0x3 +#define XSTORM_CORE_CONN_AG_CTX_CF23_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 consolid_prod; @@ -657,89 +657,89 @@ struct e4_xstorm_core_conn_ag_ctx { __le16 word15; }; -struct e4_tstorm_core_conn_ag_ctx { +struct tstorm_core_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_CORE_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_CORE_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_TSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 0 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 2 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF3_SHIFT 4 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF4_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF3_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF4_SHIFT 6 u8 flags2; -#define E4_TSTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF5_SHIFT 0 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_CORE_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF9_SHIFT 0 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF10_SHIFT 2 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 4 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 5 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 6 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 7 +#define TSTORM_CORE_CONN_AG_CTX_CF9_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF10_MASK 0x3 +#define TSTORM_CORE_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 0 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF9EN_SHIFT 5 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_CF10EN_SHIFT 6 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_CORE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define TSTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 reg0; __le32 reg1; __le32 reg2; @@ -761,63 +761,63 @@ struct e4_tstorm_core_conn_ag_ctx { __le32 reg10; }; -struct e4_ustorm_core_conn_ag_ctx { +struct ustorm_core_conn_ag_ctx { u8 reserved; u8 byte1; u8 flags0; -#define E4_USTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_USTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_USTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF4_SHIFT 2 -#define E4_USTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF5_SHIFT 4 -#define E4_USTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_CORE_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_CF4_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF4_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_CF5_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF5_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_CORE_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 4 -#define E4_USTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 5 -#define E4_USTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define USTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_CORE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF4EN_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF5EN_SHIFT 5 +#define USTORM_CORE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags3; -#define E4_USTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_CORE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_CORE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_CORE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_CORE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_CORE_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -846,15 +846,15 @@ struct tstorm_core_conn_st_ctx { }; /* core connection context */ -struct e4_core_conn_context { +struct core_conn_context { struct ystorm_core_conn_st_ctx ystorm_st_context; struct regpair ystorm_st_padding[2]; struct pstorm_core_conn_st_ctx pstorm_st_context; struct regpair pstorm_st_padding[2]; struct xstorm_core_conn_st_ctx xstorm_st_context; - struct e4_xstorm_core_conn_ag_ctx xstorm_ag_context; - struct e4_tstorm_core_conn_ag_ctx tstorm_ag_context; - struct e4_ustorm_core_conn_ag_ctx ustorm_ag_context; + struct xstorm_core_conn_ag_ctx xstorm_ag_context; + struct tstorm_core_conn_ag_ctx tstorm_ag_context; + struct ustorm_core_conn_ag_ctx ustorm_ag_context; struct mstorm_core_conn_st_ctx mstorm_st_context; struct ustorm_core_conn_st_ctx ustorm_st_context; struct regpair ustorm_st_padding[2]; @@ -1525,74 +1525,74 @@ enum dmae_cmd_src_enum { MAX_DMAE_CMD_SRC_ENUM }; -struct e4_mstorm_core_conn_ag_ctx { +struct mstorm_core_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_MSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_MSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; __le32 reg1; }; -struct e4_ystorm_core_conn_ag_ctx { +struct ystorm_core_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_CORE_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_CORE_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_CORE_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_CORE_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_CORE_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_CORE_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_CORE_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_CORE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_CORE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_CORE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_CORE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_CORE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_CORE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_CORE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_CORE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_CORE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_CORE_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -1778,22 +1778,22 @@ struct qm_rf_opportunistic_mask { }; /* QM hardware structure of QM map memory */ -struct qm_rf_pq_map_e4 { +struct qm_rf_pq_map { __le32 reg; -#define QM_RF_PQ_MAP_E4_PQ_VALID_MASK 0x1 -#define QM_RF_PQ_MAP_E4_PQ_VALID_SHIFT 0 -#define QM_RF_PQ_MAP_E4_RL_ID_MASK 0xFF -#define QM_RF_PQ_MAP_E4_RL_ID_SHIFT 1 -#define QM_RF_PQ_MAP_E4_VP_PQ_ID_MASK 0x1FF -#define QM_RF_PQ_MAP_E4_VP_PQ_ID_SHIFT 9 -#define QM_RF_PQ_MAP_E4_VOQ_MASK 0x1F -#define QM_RF_PQ_MAP_E4_VOQ_SHIFT 18 -#define QM_RF_PQ_MAP_E4_WRR_WEIGHT_GROUP_MASK 0x3 -#define QM_RF_PQ_MAP_E4_WRR_WEIGHT_GROUP_SHIFT 23 -#define QM_RF_PQ_MAP_E4_RL_VALID_MASK 0x1 -#define QM_RF_PQ_MAP_E4_RL_VALID_SHIFT 25 -#define QM_RF_PQ_MAP_E4_RESERVED_MASK 0x3F -#define QM_RF_PQ_MAP_E4_RESERVED_SHIFT 26 +#define QM_RF_PQ_MAP_PQ_VALID_MASK 0x1 +#define QM_RF_PQ_MAP_PQ_VALID_SHIFT 0 +#define QM_RF_PQ_MAP_RL_ID_MASK 0xFF +#define QM_RF_PQ_MAP_RL_ID_SHIFT 1 +#define QM_RF_PQ_MAP_VP_PQ_ID_MASK 0x1FF +#define QM_RF_PQ_MAP_VP_PQ_ID_SHIFT 9 +#define QM_RF_PQ_MAP_VOQ_MASK 0x1F +#define QM_RF_PQ_MAP_VOQ_SHIFT 18 +#define QM_RF_PQ_MAP_WRR_WEIGHT_GROUP_MASK 0x3 +#define QM_RF_PQ_MAP_WRR_WEIGHT_GROUP_SHIFT 23 +#define QM_RF_PQ_MAP_RL_VALID_MASK 0x1 +#define QM_RF_PQ_MAP_RL_VALID_SHIFT 25 +#define QM_RF_PQ_MAP_RESERVED_MASK 0x3F +#define QM_RF_PQ_MAP_RESERVED_SHIFT 26 }; /* Completion params for aggregated interrupt completion */ @@ -4892,216 +4892,216 @@ struct xstorm_eth_conn_st_ctx { __le32 reserved[60]; }; -struct e4_xstorm_eth_conn_ag_ctx { +struct xstorm_eth_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED6_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED6_SHIFT 7 u8 flags1; -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED9_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED9_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_E5_RESERVED2_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_E5_RESERVED2_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_E5_RESERVED3_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_E5_RESERVED3_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED9_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED9_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_E5_RESERVED2_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_E5_RESERVED2_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_E5_RESERVED3_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_E5_RESERVED3_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 u8 flags2; -#define E4_XSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_ETH_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF7_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF7_SHIFT 6 u8 flags4; -#define E4_XSTORM_ETH_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_ETH_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_DQ_CF_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_DQ_CF_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_DQ_CF_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 u8 flags7; -#define E4_XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED10_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED10_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED10_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED10_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF7EN_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_ETH_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_ETH_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED11_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED11_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED12_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED12_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED13_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED13_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED11_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED11_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED12_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED12_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED13_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED13_SHIFT 7 u8 flags11; -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED14_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED14_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED15_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RESERVED15_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED14_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED14_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED15_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RESERVED15_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE10EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE10EN_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_ETH_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 -#define E4_XSTORM_ETH_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 -#define E4_XSTORM_ETH_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 -#define E4_XSTORM_ETH_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 -#define E4_XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 -#define E4_XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 +#define XSTORM_ETH_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 +#define XSTORM_ETH_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 +#define XSTORM_ETH_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 u8 edpm_event_id; __le16 physical_q0; __le16 e5_reserved1; @@ -5160,37 +5160,37 @@ struct ystorm_eth_conn_st_ctx { __le32 reserved[8]; }; -struct e4_ystorm_eth_conn_ag_ctx { +struct ystorm_eth_conn_ag_ctx { u8 byte0; u8 state; u8 flags0; -#define E4_YSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 -#define E4_YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 2 -#define E4_YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_MASK 0x3 -#define E4_YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_SHIFT 4 -#define E4_YSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 2 +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_MASK 0x3 +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_SHIFT 4 +#define YSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 0 -#define E4_YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_EN_SHIFT 1 -#define E4_YSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 0 +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_PMD_TERMINATE_CF_EN_SHIFT 1 +#define YSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 tx_q0_int_coallecing_timeset; u8 byte3; __le16 word0; @@ -5204,89 +5204,89 @@ struct e4_ystorm_eth_conn_ag_ctx { __le32 reg3; }; -struct e4_tstorm_eth_conn_ag_ctx { +struct tstorm_eth_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_ETH_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_ETH_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_TSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 0 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 2 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF3_SHIFT 4 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF4_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF3_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF4_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF4_SHIFT 6 u8 flags2; -#define E4_TSTORM_ETH_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF5_SHIFT 0 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_ETH_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF9_SHIFT 0 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF10_SHIFT 2 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 4 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 5 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 6 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 7 +#define TSTORM_ETH_CONN_AG_CTX_CF9_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF10_MASK 0x3 +#define TSTORM_ETH_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_ETH_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF4EN_SHIFT 0 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF5EN_SHIFT 1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF9EN_SHIFT 5 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_CF10EN_SHIFT 6 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_ETH_CONN_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_ETH_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_ETH_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_CF9EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_CF10EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_SHIFT 5 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RX_BD_EN_SHIFT 5 +#define TSTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 reg0; __le32 reg1; __le32 reg2; @@ -5308,63 +5308,63 @@ struct e4_tstorm_eth_conn_ag_ctx { __le32 reg10; }; -struct e4_ustorm_eth_conn_ag_ctx { +struct ustorm_eth_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_USTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_USTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_SHIFT 2 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_SHIFT 4 -#define E4_USTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_ETH_CONN_AG_CTX_BIT0_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_SHIFT 2 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_SHIFT 4 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 6 +#define USTORM_ETH_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_MASK 0x3 +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_SHIFT 6 u8 flags2; -#define E4_USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_EN_SHIFT 0 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_EN_SHIFT 1 -#define E4_USTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_SHIFT 4 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_SHIFT 5 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 6 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_TX_PMD_TERMINATE_CF_EN_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RX_PMD_TERMINATE_CF_EN_SHIFT 1 +#define USTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_TX_ARM_CF_EN_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RX_ARM_CF_EN_SHIFT 5 +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_TX_BD_CONS_UPD_CF_EN_SHIFT 6 +#define USTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags3; -#define E4_USTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_ETH_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_ETH_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_ETH_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_ETH_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_ETH_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -5388,16 +5388,16 @@ struct mstorm_eth_conn_st_ctx { }; /* eth connection context */ -struct e4_eth_conn_context { +struct eth_conn_context { struct tstorm_eth_conn_st_ctx tstorm_st_context; struct regpair tstorm_st_padding[2]; struct pstorm_eth_conn_st_ctx pstorm_st_context; struct xstorm_eth_conn_st_ctx xstorm_st_context; - struct e4_xstorm_eth_conn_ag_ctx xstorm_ag_context; - struct e4_tstorm_eth_conn_ag_ctx tstorm_ag_context; + struct xstorm_eth_conn_ag_ctx xstorm_ag_context; + struct tstorm_eth_conn_ag_ctx tstorm_ag_context; struct ystorm_eth_conn_st_ctx ystorm_st_context; - struct e4_ystorm_eth_conn_ag_ctx ystorm_ag_context; - struct e4_ustorm_eth_conn_ag_ctx ustorm_ag_context; + struct ystorm_eth_conn_ag_ctx ystorm_ag_context; + struct ustorm_eth_conn_ag_ctx ustorm_ag_context; struct ustorm_eth_conn_st_ctx ustorm_st_context; struct mstorm_eth_conn_st_ctx mstorm_st_context; }; @@ -6006,7 +6006,7 @@ struct vport_update_ramrod_data { struct eth_vport_rss_config rss_config; }; -struct e4_xstorm_eth_conn_ag_ctx_dq_ext_ldpart { +struct xstorm_eth_conn_ag_ctx_dq_ext_ldpart { u8 reserved0; u8 state; u8 flags0; @@ -6235,253 +6235,253 @@ struct e4_xstorm_eth_conn_ag_ctx_dq_ext_ldpart { __le32 reg4; }; -struct e4_mstorm_eth_conn_ag_ctx { +struct mstorm_eth_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_MSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define MSTORM_ETH_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ETH_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ETH_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ETH_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ETH_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_ETH_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ETH_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ETH_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ETH_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; __le32 reg1; }; -struct e4_xstorm_eth_hw_conn_ag_ctx { +struct xstorm_eth_hw_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED6_SHIFT 7 u8 flags1; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED2_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED2_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED3_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED3_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED9_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED2_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_E5_RESERVED3_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_RULE_ACTIVE_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_ACTIVE_SHIFT 7 u8 flags2; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7_SHIFT 6 u8 flags4; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_SHIFT 6 u8 flags7; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED10_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_GO_TO_BD_CONS_CF_EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_MULTI_UNICAST_CF_EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_DQ_CF_EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TERMINATE_CF_EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED11_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_EN_RESERVED_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED12_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED13_SHIFT 7 u8 flags11; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED14_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RESERVED15_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_TX_DEC_RULE_EN_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 -#define E4_XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_USE_EXT_HDR_SHIFT 0 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_RAW_L3L4_SHIFT 1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_INBAND_PROP_HDR_SHIFT 2 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_EDPM_SEND_EXT_TUNNEL_SHIFT 3 +#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_L2_EDPM_ENABLE_SHIFT 4 +#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ETH_HW_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_MASK 0x3 +#define XSTORM_ETH_HW_CONN_AG_CTX_TPH_ENABLE_SHIFT 6 u8 edpm_event_id; __le16 physical_q0; __le16 e5_reserved1; @@ -6682,49 +6682,49 @@ struct ystorm_rdma_task_st_ctx { struct regpair temp[4]; }; -struct e4_ystorm_rdma_task_ag_ctx { +struct ystorm_rdma_task_ag_ctx { u8 reserved; u8 byte1; __le16 msem_ctx_upd_seq; u8 flags0; -#define E4_YSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_YSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_YSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_YSTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_YSTORM_RDMA_TASK_AG_CTX_VALID_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_VALID_SHIFT 6 -#define E4_YSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_SHIFT 7 +#define YSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define YSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define YSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define YSTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 +#define YSTORM_RDMA_TASK_AG_CTX_VALID_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_VALID_SHIFT 6 +#define YSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_SHIFT 7 u8 flags1; -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF0_SHIFT 0 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF1_SHIFT 2 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF0EN_SHIFT 6 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_CF1EN_SHIFT 7 +#define YSTORM_RDMA_TASK_AG_CTX_CF0_MASK 0x3 +#define YSTORM_RDMA_TASK_AG_CTX_CF0_SHIFT 0 +#define YSTORM_RDMA_TASK_AG_CTX_CF1_MASK 0x3 +#define YSTORM_RDMA_TASK_AG_CTX_CF1_SHIFT 2 +#define YSTORM_RDMA_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 +#define YSTORM_RDMA_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 +#define YSTORM_RDMA_TASK_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_CF0EN_SHIFT 6 +#define YSTORM_RDMA_TASK_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_CF1EN_SHIFT 7 u8 flags2; -#define E4_YSTORM_RDMA_TASK_AG_CTX_BIT4_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_BIT4_SHIFT 0 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 2 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 3 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE3EN_SHIFT 4 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 5 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE5EN_SHIFT 6 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_YSTORM_RDMA_TASK_AG_CTX_RULE6EN_SHIFT 7 +#define YSTORM_RDMA_TASK_AG_CTX_BIT4_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_BIT4_SHIFT 0 +#define YSTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define YSTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define YSTORM_RDMA_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define YSTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define YSTORM_RDMA_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define YSTORM_RDMA_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define YSTORM_RDMA_TASK_AG_CTX_RULE6EN_SHIFT 7 u8 key; __le32 mw_cnt_or_qp_id; u8 ref_cnt_seq; @@ -6738,49 +6738,49 @@ struct e4_ystorm_rdma_task_ag_ctx { __le32 fbo_hi; }; -struct e4_mstorm_rdma_task_ag_ctx { +struct mstorm_rdma_task_ag_ctx { u8 reserved; u8 byte1; __le16 icid; u8 flags0; -#define E4_MSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_MSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_MSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_MSTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_MSTORM_RDMA_TASK_AG_CTX_BIT2_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_BIT2_SHIFT 6 -#define E4_MSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_SHIFT 7 +#define MSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define MSTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define MSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define MSTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 +#define MSTORM_RDMA_TASK_AG_CTX_BIT2_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_BIT2_SHIFT 6 +#define MSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_DIF_FIRST_IO_SHIFT 7 u8 flags1; -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF0_SHIFT 0 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF1_SHIFT 2 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF2_SHIFT 4 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF0EN_SHIFT 6 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF1EN_SHIFT 7 +#define MSTORM_RDMA_TASK_AG_CTX_CF0_MASK 0x3 +#define MSTORM_RDMA_TASK_AG_CTX_CF0_SHIFT 0 +#define MSTORM_RDMA_TASK_AG_CTX_CF1_MASK 0x3 +#define MSTORM_RDMA_TASK_AG_CTX_CF1_SHIFT 2 +#define MSTORM_RDMA_TASK_AG_CTX_CF2_MASK 0x3 +#define MSTORM_RDMA_TASK_AG_CTX_CF2_SHIFT 4 +#define MSTORM_RDMA_TASK_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_CF0EN_SHIFT 6 +#define MSTORM_RDMA_TASK_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_CF1EN_SHIFT 7 u8 flags2; -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_CF2EN_SHIFT 0 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 2 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 3 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE3EN_SHIFT 4 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 5 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE5EN_SHIFT 6 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_MSTORM_RDMA_TASK_AG_CTX_RULE6EN_SHIFT 7 +#define MSTORM_RDMA_TASK_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_CF2EN_SHIFT 0 +#define MSTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define MSTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define MSTORM_RDMA_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define MSTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define MSTORM_RDMA_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define MSTORM_RDMA_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define MSTORM_RDMA_TASK_AG_CTX_RULE6EN_SHIFT 7 u8 key; __le32 mw_cnt_or_qp_id; u8 ref_cnt_seq; @@ -6804,56 +6804,56 @@ struct ustorm_rdma_task_st_ctx { struct regpair temp[6]; }; -struct e4_ustorm_rdma_task_ag_ctx { +struct ustorm_rdma_task_ag_ctx { u8 reserved; u8 state; __le16 icid; u8 flags0; -#define E4_USTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_USTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_USTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_USTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_MASK 0x3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_SHIFT 6 +#define USTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define USTORM_RDMA_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define USTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define USTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 +#define USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_MASK 0x3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_SHIFT 6 u8 flags1; -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_RESULT_TOGGLE_BIT_MASK 0x3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_RESULT_TOGGLE_BIT_SHIFT 0 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_TX_IO_FLG_MASK 0x3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_TX_IO_FLG_SHIFT 2 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_BLOCK_SIZE_MASK 0x3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_BLOCK_SIZE_SHIFT 4 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 +#define USTORM_RDMA_TASK_AG_CTX_DIF_RESULT_TOGGLE_BIT_MASK 0x3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_RESULT_TOGGLE_BIT_SHIFT 0 +#define USTORM_RDMA_TASK_AG_CTX_DIF_TX_IO_FLG_MASK 0x3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_TX_IO_FLG_SHIFT 2 +#define USTORM_RDMA_TASK_AG_CTX_DIF_BLOCK_SIZE_MASK 0x3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_BLOCK_SIZE_SHIFT 4 +#define USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 u8 flags2; -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_EN_SHIFT 0 -#define E4_USTORM_RDMA_TASK_AG_CTX_RESERVED2_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RESERVED2_SHIFT 1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RESERVED3_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RESERVED3_SHIFT 2 -#define E4_USTORM_RDMA_TASK_AG_CTX_RESERVED4_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RESERVED4_SHIFT 3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 5 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 6 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 7 +#define USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_RESULT_CF_EN_SHIFT 0 +#define USTORM_RDMA_TASK_AG_CTX_RESERVED2_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RESERVED2_SHIFT 1 +#define USTORM_RDMA_TASK_AG_CTX_RESERVED3_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RESERVED3_SHIFT 2 +#define USTORM_RDMA_TASK_AG_CTX_RESERVED4_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RESERVED4_SHIFT 3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define USTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 5 +#define USTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define USTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 7 u8 flags3; -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_RXMIT_PROD_CONS_EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_RXMIT_PROD_CONS_EN_SHIFT 0 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 1 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_PROD_CONS_EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_PROD_CONS_EN_SHIFT 2 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_RDMA_TASK_AG_CTX_RULE6EN_SHIFT 3 -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF -#define E4_USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 +#define USTORM_RDMA_TASK_AG_CTX_DIF_RXMIT_PROD_CONS_EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_DIF_RXMIT_PROD_CONS_EN_SHIFT 0 +#define USTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 1 +#define USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_PROD_CONS_EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_DIF_WRITE_PROD_CONS_EN_SHIFT 2 +#define USTORM_RDMA_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_RDMA_TASK_AG_CTX_RULE6EN_SHIFT 3 +#define USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define USTORM_RDMA_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 __le32 dif_err_intervals; __le32 dif_error_1st_interval; __le32 dif_rxmit_cons; @@ -6870,16 +6870,16 @@ struct e4_ustorm_rdma_task_ag_ctx { }; /* RDMA task context */ -struct e4_rdma_task_context { +struct rdma_task_context { struct ystorm_rdma_task_st_ctx ystorm_st_context; - struct e4_ystorm_rdma_task_ag_ctx ystorm_ag_context; + struct ystorm_rdma_task_ag_ctx ystorm_ag_context; struct tdif_task_context tdif_context; - struct e4_mstorm_rdma_task_ag_ctx mstorm_ag_context; + struct mstorm_rdma_task_ag_ctx mstorm_ag_context; struct mstorm_rdma_task_st_ctx mstorm_st_context; struct rdif_task_context rdif_context; struct ustorm_rdma_task_st_ctx ustorm_st_context; struct regpair ustorm_st_padding[2]; - struct e4_ustorm_rdma_task_ag_ctx ustorm_ag_context; + struct ustorm_rdma_task_ag_ctx ustorm_ag_context; }; /* rdma function init ramrod data */ @@ -7135,73 +7135,73 @@ struct rdma_xrc_srq_context { struct regpair temp[9]; }; -struct e4_tstorm_rdma_task_ag_ctx { +struct tstorm_rdma_task_ag_ctx { u8 byte0; u8 byte1; __le16 word0; u8 flags0; -#define E4_TSTORM_RDMA_TASK_AG_CTX_NIBBLE0_MASK 0xF -#define E4_TSTORM_RDMA_TASK_AG_CTX_NIBBLE0_SHIFT 0 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT0_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT0_SHIFT 4 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT2_SHIFT 6 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT3_SHIFT 7 +#define TSTORM_RDMA_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define TSTORM_RDMA_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define TSTORM_RDMA_TASK_AG_CTX_BIT0_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_BIT0_SHIFT 4 +#define TSTORM_RDMA_TASK_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_BIT1_SHIFT 5 +#define TSTORM_RDMA_TASK_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_BIT2_SHIFT 6 +#define TSTORM_RDMA_TASK_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_BIT3_SHIFT 7 u8 flags1; -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT4_SHIFT 0 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_BIT5_SHIFT 1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF0_SHIFT 2 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF1_SHIFT 4 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF2_SHIFT 6 +#define TSTORM_RDMA_TASK_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_BIT4_SHIFT 0 +#define TSTORM_RDMA_TASK_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_BIT5_SHIFT 1 +#define TSTORM_RDMA_TASK_AG_CTX_CF0_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF0_SHIFT 2 +#define TSTORM_RDMA_TASK_AG_CTX_CF1_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF1_SHIFT 4 +#define TSTORM_RDMA_TASK_AG_CTX_CF2_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF2_SHIFT 6 u8 flags2; -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF3_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF3_SHIFT 0 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF4_SHIFT 2 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF5_SHIFT 4 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF6_SHIFT 6 +#define TSTORM_RDMA_TASK_AG_CTX_CF3_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF3_SHIFT 0 +#define TSTORM_RDMA_TASK_AG_CTX_CF4_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF4_SHIFT 2 +#define TSTORM_RDMA_TASK_AG_CTX_CF5_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF5_SHIFT 4 +#define TSTORM_RDMA_TASK_AG_CTX_CF6_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF6_SHIFT 6 u8 flags3; -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF7_SHIFT 0 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF0EN_SHIFT 2 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF1EN_SHIFT 3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF2EN_SHIFT 4 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF3EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF3EN_SHIFT 5 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF4EN_SHIFT 6 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF5EN_SHIFT 7 +#define TSTORM_RDMA_TASK_AG_CTX_CF7_MASK 0x3 +#define TSTORM_RDMA_TASK_AG_CTX_CF7_SHIFT 0 +#define TSTORM_RDMA_TASK_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF0EN_SHIFT 2 +#define TSTORM_RDMA_TASK_AG_CTX_CF1EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF1EN_SHIFT 3 +#define TSTORM_RDMA_TASK_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF2EN_SHIFT 4 +#define TSTORM_RDMA_TASK_AG_CTX_CF3EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF3EN_SHIFT 5 +#define TSTORM_RDMA_TASK_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF4EN_SHIFT 6 +#define TSTORM_RDMA_TASK_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF5EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF6EN_SHIFT 0 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_CF7EN_SHIFT 1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 2 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 3 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 4 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE3EN_SHIFT 5 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 6 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_RDMA_TASK_AG_CTX_RULE5EN_SHIFT 7 +#define TSTORM_RDMA_TASK_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF6EN_SHIFT 0 +#define TSTORM_RDMA_TASK_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_CF7EN_SHIFT 1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE0EN_SHIFT 2 +#define TSTORM_RDMA_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE1EN_SHIFT 3 +#define TSTORM_RDMA_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE2EN_SHIFT 4 +#define TSTORM_RDMA_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE3EN_SHIFT 5 +#define TSTORM_RDMA_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE4EN_SHIFT 6 +#define TSTORM_RDMA_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_RDMA_TASK_AG_CTX_RULE5EN_SHIFT 7 u8 byte2; __le16 word1; __le32 reg0; @@ -7214,63 +7214,63 @@ struct e4_tstorm_rdma_task_ag_ctx { __le32 reg2; }; -struct e4_ustorm_rdma_conn_ag_ctx { +struct ustorm_rdma_conn_ag_ctx { u8 reserved; u8 byte1; u8 flags0; -#define E4_USTORM_RDMA_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_USTORM_RDMA_CONN_AG_CTX_DIF_ERROR_REPORTED_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_DIF_ERROR_REPORTED_SHIFT 1 -#define E4_USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 2 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_RDMA_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define USTORM_RDMA_CONN_AG_CTX_DIF_ERROR_REPORTED_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_DIF_ERROR_REPORTED_SHIFT 1 +#define USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 2 +#define USTORM_RDMA_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_RDMA_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_RDMA_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_SHIFT 2 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_SHIFT 4 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_RDMA_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_SHIFT 2 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_SHIFT 4 +#define USTORM_RDMA_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_RDMA_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_EN_SHIFT 4 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_EN_SHIFT 5 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_SE_EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_SE_EN_SHIFT 7 +#define USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 +#define USTORM_RDMA_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_RDMA_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_RDMA_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_SE_CF_EN_SHIFT 4 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CQ_ARM_CF_EN_SHIFT 5 +#define USTORM_RDMA_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_RDMA_CONN_AG_CTX_CQ_SE_EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CQ_SE_EN_SHIFT 7 u8 flags3; -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_CQ_EN_SHIFT 0 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_RDMA_CONN_AG_CTX_CQ_EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_CQ_EN_SHIFT 0 +#define USTORM_RDMA_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_RDMA_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_RDMA_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_RDMA_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_RDMA_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_RDMA_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_RDMA_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_RDMA_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 nvmf_only; __le16 conn_dpi; @@ -7283,214 +7283,214 @@ struct e4_ustorm_rdma_conn_ag_ctx { __le16 word3; }; -struct e4_xstorm_roce_conn_ag_ctx { +struct xstorm_roce_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT6_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT6_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT7_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT7_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT2_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT2_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_BIT4_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT4_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_BIT5_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT5_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_BIT6_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT6_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_BIT7_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT7_SHIFT 7 u8 flags1; -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT8_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT8_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT9_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT9_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT10_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT10_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_MSDM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_MSDM_FLUSH_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_MSEM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_MSEM_FLUSH_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT14_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT14_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_YSTORM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_YSTORM_FLUSH_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_BIT8_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT8_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_BIT9_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT9_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT10_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT10_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_MSDM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_MSDM_FLUSH_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_MSEM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_MSEM_FLUSH_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_BIT14_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT14_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_YSTORM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_YSTORM_FLUSH_SHIFT 7 u8 flags2; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 u8 flags4; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF16_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF16_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF18_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF18_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF19_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF19_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF16_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF16_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF19_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF19_SHIFT 6 u8 flags7; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF20_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF20_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF21_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF21_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_CF20_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF20_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF21_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF21_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF16EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF16EN_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_CF16EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF16EN_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF18EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF18EN_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF19EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF19EN_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF20EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF20EN_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF21EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF21EN_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF23EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF23EN_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_CF19EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF19EN_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_CF20EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF20EN_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_CF21EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF21EN_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_CF23EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_CF23EN_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 7 u8 flags11; -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE10EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE10EN_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_ROCE_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_ROCE_CONN_AG_CTX_MIGRATION_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_MIGRATION_SHIFT 0 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_DPM_PORT_NUM_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_DPM_PORT_NUM_SHIFT 2 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RESERVED_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_RESERVED_SHIFT 4 -#define E4_XSTORM_ROCE_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 -#define E4_XSTORM_ROCE_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF23_MASK 0x3 -#define E4_XSTORM_ROCE_CONN_AG_CTX_CF23_SHIFT 6 +#define XSTORM_ROCE_CONN_AG_CTX_MIGRATION_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_MIGRATION_SHIFT 0 +#define XSTORM_ROCE_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_ROCE_CONN_AG_CTX_DPM_PORT_NUM_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_DPM_PORT_NUM_SHIFT 2 +#define XSTORM_ROCE_CONN_AG_CTX_RESERVED_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_RESERVED_SHIFT 4 +#define XSTORM_ROCE_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ROCE_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORM_ROCE_CONN_AG_CTX_CF23_MASK 0x3 +#define XSTORM_ROCE_CONN_AG_CTX_CF23_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 word1; @@ -7512,89 +7512,89 @@ struct e4_xstorm_roce_conn_ag_ctx { __le32 reg6; }; -struct e4_tstorm_roce_conn_ag_ctx { +struct tstorm_roce_conn_ag_ctx { u8 reserved0; u8 byte1; u8 flags0; -#define E4_TSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 6 +#define TSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_ROCE_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_ROCE_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_ROCE_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_ROCE_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_SHIFT 0 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 2 -#define E4_TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_SHIFT 4 -#define E4_TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 +#define TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_SHIFT 0 +#define TSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_SHIFT 4 +#define TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 u8 flags2; -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF5_SHIFT 0 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_ROCE_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_ROCE_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_ROCE_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_ROCE_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF9_SHIFT 0 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF10_SHIFT 2 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 4 -#define E4_TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_SHIFT 5 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 6 -#define E4_TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_SHIFT 7 +#define TSTORM_ROCE_CONN_AG_CTX_CF9_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_ROCE_CONN_AG_CTX_CF10_MASK 0x3 +#define TSTORM_ROCE_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_SHIFT 5 +#define TSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF5EN_SHIFT 1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF9EN_SHIFT 5 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_CF10EN_SHIFT 6 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 +#define TSTORM_ROCE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_ROCE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_ROCE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_ROCE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_ROCE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_ROCE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_ROCE_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_ROCE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_ROCE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define TSTORM_ROCE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_ROCE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_ROCE_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 reg0; __le32 reg1; __le32 reg2; @@ -7647,15 +7647,15 @@ struct ustorm_roce_conn_st_ctx { }; /* roce connection context */ -struct e4_roce_conn_context { +struct roce_conn_context { struct ystorm_roce_conn_st_ctx ystorm_st_context; struct regpair ystorm_st_padding[2]; struct pstorm_roce_conn_st_ctx pstorm_st_context; struct xstorm_roce_conn_st_ctx xstorm_st_context; - struct e4_xstorm_roce_conn_ag_ctx xstorm_ag_context; - struct e4_tstorm_roce_conn_ag_ctx tstorm_ag_context; + struct xstorm_roce_conn_ag_ctx xstorm_ag_context; + struct tstorm_roce_conn_ag_ctx tstorm_ag_context; struct timers_context timer_context; - struct e4_ustorm_rdma_conn_ag_ctx ustorm_ag_context; + struct ustorm_rdma_conn_ag_ctx ustorm_ag_context; struct tstorm_roce_conn_st_ctx tstorm_st_context; struct regpair tstorm_st_padding[2]; struct mstorm_roce_conn_st_ctx mstorm_st_context; @@ -8037,7 +8037,7 @@ struct roce_update_func_params { __le32 cnp_send_timeout; }; -struct e4_xstorm_roce_conn_ag_ctx_dq_ext_ld_part { +struct xstorm_roce_conn_ag_ctx_dq_ext_ld_part { u8 reserved0; u8 state; u8 flags0; @@ -8264,200 +8264,200 @@ struct e4_xstorm_roce_conn_ag_ctx_dq_ext_ld_part { __le32 reg4; }; -struct e4_mstorm_roce_conn_ag_ctx { +struct mstorm_roce_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_MSTORM_ROCE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_MSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_ROCE_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ROCE_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ROCE_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ROCE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; __le32 reg1; }; -struct e4_mstorm_roce_req_conn_ag_ctx { +struct mstorm_roce_req_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; __le32 reg1; }; -struct e4_mstorm_roce_resp_conn_ag_ctx { +struct mstorm_roce_resp_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; __le32 reg1; }; -struct e4_tstorm_roce_req_conn_ag_ctx { +struct tstorm_roce_req_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_OCCURRED_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_OCCURRED_SHIFT 1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TX_CQE_ERROR_OCCURRED_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TX_CQE_ERROR_OCCURRED_SHIFT 2 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_SHIFT 4 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_CACHED_ORQ_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_CACHED_ORQ_SHIFT 5 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_SHIFT 6 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_OCCURRED_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_OCCURRED_SHIFT 1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TX_CQE_ERROR_OCCURRED_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TX_CQE_ERROR_OCCURRED_SHIFT 2 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_SHIFT 4 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_CACHED_ORQ_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_CACHED_ORQ_SHIFT 5 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_SHIFT 6 u8 flags1; -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_SHIFT 0 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_SHIFT 2 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_SHIFT 4 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_SHIFT 0 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_SHIFT 2 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_SHIFT 4 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 u8 flags2; -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_SHIFT 0 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_SHIFT 2 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_SHIFT 4 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_SHIFT 6 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_SHIFT 0 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_SHIFT 2 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_SHIFT 4 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_SHIFT 6 u8 flags3; -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_SHIFT 0 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_MASK 0x3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_SHIFT 2 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_EN_SHIFT 4 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_SHIFT 5 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_EN_SHIFT 6 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_SHIFT 7 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_SHIFT 0 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_MASK 0x3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_SHIFT 2 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_CF_EN_SHIFT 4 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_SHIFT 5 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_SQ_CF_EN_SHIFT 6 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_EN_SHIFT 1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_EN_SHIFT 2 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_EN_SHIFT 3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_EN_SHIFT 4 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_EN_SHIFT 5 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_EN_SHIFT 6 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_FORCE_COMP_CF_EN_SHIFT 1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SET_TIMER_CF_EN_SHIFT 2 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_TX_ASYNC_ERROR_CF_EN_SHIFT 3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RXMIT_DONE_CF_EN_SHIFT 4 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_SCAN_COMPLETED_CF_EN_SHIFT 5 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SQ_DRAIN_COMPLETED_CF_EN_SHIFT 6 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_DIF_CNT_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_DIF_CNT_EN_SHIFT 1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SND_SQ_CONS_EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_SND_SQ_CONS_EN_SHIFT 5 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_DIF_CNT_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_DIF_CNT_EN_SHIFT 1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SND_SQ_CONS_EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_SND_SQ_CONS_EN_SHIFT 5 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 dif_rxmit_cnt; __le32 snd_nxt_psn; __le32 snd_max_psn; @@ -8479,89 +8479,89 @@ struct e4_tstorm_roce_req_conn_ag_ctx { __le32 reg10; }; -struct e4_tstorm_roce_resp_conn_ag_ctx { +struct tstorm_roce_resp_conn_ag_ctx { u8 byte0; u8 state; u8 flags0; -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_NOTIFY_REQUESTER_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_NOTIFY_REQUESTER_SHIFT 1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_SHIFT 4 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 6 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_NOTIFY_REQUESTER_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_NOTIFY_REQUESTER_SHIFT 1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_SHIFT 4 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_SHIFT 0 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_SHIFT 2 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF3_SHIFT 4 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_SHIFT 0 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_SHIFT 2 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF3_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF3_SHIFT 4 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 u8 flags2; -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_SHIFT 0 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_SHIFT 0 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF9_SHIFT 0 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF10_SHIFT 2 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 4 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_SHIFT 5 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_EN_SHIFT 6 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_SHIFT 7 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF9_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF10_MASK 0x3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_MSTORM_FLUSH_CF_EN_SHIFT 5 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_TX_ERROR_CF_EN_SHIFT 6 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_SHIFT 1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_SHIFT 5 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_SHIFT 6 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 0 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_SHIFT 1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RQ_RULE_EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RQ_RULE_EN_SHIFT 5 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RQ_RULE_EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RQ_RULE_EN_SHIFT 5 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 psn_and_rxmit_id_echo; __le32 reg1; __le32 reg2; @@ -8583,63 +8583,63 @@ struct e4_tstorm_roce_resp_conn_ag_ctx { __le32 reg10; }; -struct e4_ustorm_roce_req_conn_ag_ctx { +struct ustorm_roce_req_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_ROCE_REQ_CONN_AG_CTX_BIT0_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_ROCE_REQ_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF4_SHIFT 2 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF5_SHIFT 4 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF4_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF4_SHIFT 2 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF5_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF5_SHIFT 4 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF4EN_SHIFT 4 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF5EN_SHIFT 5 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF4EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF4EN_SHIFT 4 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF5EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF5EN_SHIFT 5 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags3; -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_ROCE_REQ_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -8652,63 +8652,63 @@ struct e4_ustorm_roce_req_conn_ag_ctx { __le16 word3; }; -struct e4_ustorm_roce_resp_conn_ag_ctx { +struct ustorm_roce_resp_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_ROCE_RESP_CONN_AG_CTX_BIT0_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_ROCE_RESP_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF4_SHIFT 2 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF5_SHIFT 4 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF4_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF4_SHIFT 2 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF5_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF5_SHIFT 4 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF4EN_SHIFT 4 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF5EN_SHIFT 5 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF4EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF4EN_SHIFT 4 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF5EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF5EN_SHIFT 5 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags3; -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_ROCE_RESP_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -8721,214 +8721,214 @@ struct e4_ustorm_roce_resp_conn_ag_ctx { __le16 word3; }; -struct e4_xstorm_roce_req_conn_ag_ctx { +struct xstorm_roce_req_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED6_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED6_SHIFT 7 u8 flags1; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_BIT10_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_BIT10_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MSDM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MSDM_FLUSH_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MSEM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MSEM_FLUSH_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_STATE_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_STATE_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_YSTORM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_YSTORM_FLUSH_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_BIT10_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_BIT10_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MSDM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MSDM_FLUSH_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MSEM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MSEM_FLUSH_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_STATE_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_ERROR_STATE_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_YSTORM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_YSTORM_FLUSH_SHIFT 7 u8 flags2; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 u8 flags4; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FMR_ENDED_CF_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FMR_ENDED_CF_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FMR_ENDED_CF_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FMR_ENDED_CF_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF16_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF16_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF18_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF18_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF19_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF19_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF16_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF16_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF19_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF19_SHIFT 6 u8 flags7; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF20_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF20_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF21_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF21_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF20_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF20_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF21_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF21_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_EN_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_EN_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_EN_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_EN_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_EN_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_FLUSH_CF_EN_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RX_ERROR_CF_EN_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SND_RXMIT_CF_EN_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_DIF_ERROR_CF_EN_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SCAN_SQ_FOR_COMP_CF_EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FME_ENDED_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_FME_ENDED_CF_EN_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF16EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF16EN_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FME_ENDED_CF_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_FME_ENDED_CF_EN_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF16EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF16EN_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF18EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF18EN_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF19EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF19EN_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF20EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF20EN_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF21EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF21EN_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF23EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF23EN_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF19EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF19EN_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF20EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF20EN_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF21EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF21EN_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF23EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF23EN_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 7 u8 flags11; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_E2E_CREDIT_RULE_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_E2E_CREDIT_RULE_EN_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_E2E_CREDIT_RULE_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_E2E_CREDIT_RULE_EN_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_PROD_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_PROD_EN_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_INV_FENCE_RULE_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_INV_FENCE_RULE_EN_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_ORQ_FENCE_RULE_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_ORQ_FENCE_RULE_EN_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MAX_ORD_RULE_EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MAX_ORD_RULE_EN_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_PROD_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_SQ_PROD_EN_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_INV_FENCE_RULE_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_INV_FENCE_RULE_EN_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_ORQ_FENCE_RULE_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_ORQ_FENCE_RULE_EN_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MAX_ORD_RULE_EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MAX_ORD_RULE_EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MIGRATION_FLAG_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_MIGRATION_FLAG_SHIFT 0 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_DPM_PORT_NUM_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_DPM_PORT_NUM_SHIFT 2 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED_SHIFT 4 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF23_MASK 0x3 -#define E4_XSTORM_ROCE_REQ_CONN_AG_CTX_CF23_SHIFT 6 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MIGRATION_FLAG_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_MIGRATION_FLAG_SHIFT 0 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_DPM_PORT_NUM_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_DPM_PORT_NUM_SHIFT 2 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_RESERVED_SHIFT 4 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_ROCE_EDPM_ENABLE_MASK 0x1 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_ROCE_EDPM_ENABLE_SHIFT 5 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF23_MASK 0x3 +#define XSTORM_ROCE_REQ_CONN_AG_CTX_CF23_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 word1; @@ -8950,216 +8950,216 @@ struct e4_xstorm_roce_req_conn_ag_ctx { __le32 orq_cons; }; -struct e4_xstorm_roce_resp_conn_ag_ctx { +struct xstorm_roce_resp_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED6_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED6_SHIFT 7 u8 flags1; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT10_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT10_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_MSDM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_MSDM_FLUSH_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_MSEM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_MSEM_FLUSH_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_ERROR_STATE_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_ERROR_STATE_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_YSTORM_FLUSH_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_YSTORM_FLUSH_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT10_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT10_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_MSDM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_MSDM_FLUSH_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_MSEM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_MSEM_FLUSH_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_ERROR_STATE_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_ERROR_STATE_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_YSTORM_FLUSH_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_YSTORM_FLUSH_SHIFT 7 u8 flags2; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 6 u8 flags4; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF16_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF16_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF18_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF18_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF19_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF19_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF16_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF16_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF19_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF19_SHIFT 6 u8 flags7; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF20_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF20_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF21_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF21_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF20_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF20_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF21_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF21_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_EN_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_EN_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RXMIT_CF_EN_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RX_ERROR_CF_EN_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FORCE_ACK_CF_EN_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF16EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF16EN_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF16EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF16EN_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF18EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF18EN_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF19EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF19EN_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF20EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF20EN_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF21EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF21EN_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF23EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF23EN_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF19EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF19EN_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF20EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF20EN_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF21EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF21EN_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF23EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF23EN_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 7 u8 flags11; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_IRQ_PROD_RULE_EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_IRQ_PROD_RULE_EN_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_IRQ_PROD_RULE_EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_IRQ_PROD_RULE_EN_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE18EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE18EN_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT16_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT16_SHIFT 0 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT18_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT18_SHIFT 2 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT19_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT19_SHIFT 3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT20_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT20_SHIFT 4 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT21_MASK 0x1 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_BIT21_SHIFT 5 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF23_MASK 0x3 -#define E4_XSTORM_ROCE_RESP_CONN_AG_CTX_CF23_SHIFT 6 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT16_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT16_SHIFT 0 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT18_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT18_SHIFT 2 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT19_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT19_SHIFT 3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT20_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT20_SHIFT 4 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT21_MASK 0x1 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_BIT21_SHIFT 5 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF23_MASK 0x3 +#define XSTORM_ROCE_RESP_CONN_AG_CTX_CF23_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 irq_prod_shadow; @@ -9181,37 +9181,37 @@ struct e4_xstorm_roce_resp_conn_ag_ctx { __le32 msn_and_syndrome; }; -struct e4_ystorm_roce_conn_ag_ctx { +struct ystorm_roce_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_ROCE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_ROCE_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_ROCE_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_ROCE_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_ROCE_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_ROCE_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_ROCE_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_ROCE_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_ROCE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_ROCE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_ROCE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_ROCE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_ROCE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_ROCE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_ROCE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_ROCE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_ROCE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ROCE_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -9225,37 +9225,37 @@ struct e4_ystorm_roce_conn_ag_ctx { __le32 reg3; }; -struct e4_ystorm_roce_req_conn_ag_ctx { +struct ystorm_roce_req_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ROCE_REQ_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -9269,37 +9269,37 @@ struct e4_ystorm_roce_req_conn_ag_ctx { __le32 reg3; }; -struct e4_ystorm_roce_resp_conn_ag_ctx { +struct ystorm_roce_resp_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ROCE_RESP_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -9336,216 +9336,216 @@ struct xstorm_iwarp_conn_st_ctx { __le32 reserved[48]; }; -struct e4_xstorm_iwarp_conn_ag_ctx { +struct xstorm_iwarp_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM1_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM1_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM2_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM2_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RESERVED2_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT6_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT6_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT7_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT7_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM1_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM1_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM2_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM2_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_BIT4_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT4_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RESERVED2_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_BIT6_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT6_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_BIT7_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT7_SHIFT 7 u8 flags1; -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT8_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT8_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT9_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT9_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT10_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT10_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT12_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT12_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT13_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT13_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT14_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT14_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_YSTORM_FLUSH_OR_REWIND_SND_MAX_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_YSTORM_FLUSH_OR_REWIND_SND_MAX_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_BIT8_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT8_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_BIT9_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT9_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT10_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT10_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_BIT14_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT14_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_YSTORM_FLUSH_OR_REWIND_SND_MAX_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_YSTORM_FLUSH_OR_REWIND_SND_MAX_SHIFT 7 u8 flags2; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 6 u8 flags3; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF7_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF7_SHIFT 6 u8 flags4; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF18_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF18_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 u8 flags7; -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF7EN_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_EN_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_EN_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_FLUSH_CF_EN_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_MPA_OR_ERROR_WAKEUP_TRIGGER_CF_EN_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF18EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_CF18EN_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_EN_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_MORE_TO_SEND_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_MORE_TO_SEND_RULE_EN_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_EN_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_MORE_TO_SEND_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_MORE_TO_SEND_RULE_EN_SHIFT 7 u8 flags11; -#define E4_XSTORM_IWARP_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RESERVED3_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RESERVED3_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_NOT_EMPTY_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_NOT_EMPTY_RULE_EN_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_FENCE_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SQ_FENCE_RULE_EN_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_NOT_EMPTY_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_NOT_EMPTY_RULE_EN_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_FENCE_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_SQ_FENCE_RULE_EN_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_IWARP_CONN_AG_CTX_IRQ_NOT_EMPTY_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_IRQ_NOT_EMPTY_RULE_EN_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_HQ_NOT_FULL_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_HQ_NOT_FULL_RULE_EN_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_ORQ_RD_FENCE_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_ORQ_RD_FENCE_RULE_EN_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE21EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_RULE21EN_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_ORQ_NOT_FULL_RULE_EN_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_ORQ_NOT_FULL_RULE_EN_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_IWARP_CONN_AG_CTX_IRQ_NOT_EMPTY_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_IRQ_NOT_EMPTY_RULE_EN_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_HQ_NOT_FULL_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_HQ_NOT_FULL_RULE_EN_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_ORQ_RD_FENCE_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_ORQ_RD_FENCE_RULE_EN_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_RULE21EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_RULE21EN_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_ORQ_NOT_FULL_RULE_EN_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_ORQ_NOT_FULL_RULE_EN_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT16_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT16_SHIFT 0 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT18_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_BIT18_SHIFT 2 -#define E4_XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED1_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED1_SHIFT 3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED2_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED2_SHIFT 4 -#define E4_XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED3_MASK 0x1 -#define E4_XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED3_SHIFT 5 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_MASK 0x3 -#define E4_XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_SHIFT 6 +#define XSTORM_IWARP_CONN_AG_CTX_BIT16_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT16_SHIFT 0 +#define XSTORM_IWARP_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT18_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_BIT18_SHIFT 2 +#define XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED1_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED1_SHIFT 3 +#define XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED2_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED2_SHIFT 4 +#define XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED3_MASK 0x1 +#define XSTORM_IWARP_CONN_AG_CTX_E5_RESERVED3_SHIFT 5 +#define XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_MASK 0x3 +#define XSTORM_IWARP_CONN_AG_CTX_SEND_TERMINATE_CF_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 physical_q1; @@ -9593,89 +9593,89 @@ struct e4_xstorm_iwarp_conn_ag_ctx { __le32 reg17; }; -struct e4_tstorm_iwarp_conn_ag_ctx { +struct tstorm_iwarp_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_TSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_TSTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_IWARP_CONN_AG_CTX_MSTORM_FLUSH_OR_TERMINATE_SENT_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_MSTORM_FLUSH_OR_TERMINATE_SENT_SHIFT 3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CACHED_ORQ_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CACHED_ORQ_SHIFT 5 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 6 +#define TSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_IWARP_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_IWARP_CONN_AG_CTX_MSTORM_FLUSH_OR_TERMINATE_SENT_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_MSTORM_FLUSH_OR_TERMINATE_SENT_SHIFT 3 +#define TSTORM_IWARP_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_IWARP_CONN_AG_CTX_CACHED_ORQ_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CACHED_ORQ_SHIFT 5 +#define TSTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_SHIFT 0 -#define E4_TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_SHIFT 2 -#define E4_TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF4_SHIFT 6 +#define TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_SHIFT 0 +#define TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_SHIFT 2 +#define TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 +#define TSTORM_IWARP_CONN_AG_CTX_CF4_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_CF4_SHIFT 6 u8 flags2; -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF5_SHIFT 0 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_IWARP_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_IWARP_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_IWARP_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_IWARP_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPLETE_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPLETE_SHIFT 0 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_MASK 0x3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_SHIFT 2 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 4 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_EN_SHIFT 5 -#define E4_TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_EN_SHIFT 6 -#define E4_TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPLETE_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPLETE_SHIFT 0 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_MASK 0x3 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_SHIFT 2 +#define TSTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RQ_POST_CF_EN_SHIFT 5 +#define TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_MPA_TIMEOUT_CF_EN_SHIFT 6 +#define TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF4EN_SHIFT 0 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF5EN_SHIFT 1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPL_EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPL_EN_SHIFT 5 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_EN_SHIFT 6 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_IWARP_CONN_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_IWARP_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_IWARP_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_IWARP_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_IWARP_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPL_EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_Q0_AND_TCP_HANDSHAKE_COMPL_EN_SHIFT 5 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_FLUSH_OR_ERROR_DETECTED_EN_SHIFT 6 +#define TSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_IWARP_CONN_AG_CTX_SND_SQ_CONS_RULE_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_SND_SQ_CONS_RULE_SHIFT 5 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_IWARP_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_IWARP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_IWARP_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_IWARP_CONN_AG_CTX_SND_SQ_CONS_RULE_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_SND_SQ_CONS_RULE_SHIFT 5 +#define TSTORM_IWARP_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_IWARP_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_IWARP_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 reg0; __le32 reg1; __le32 unaligned_nxt_seq; @@ -9713,16 +9713,16 @@ struct ustorm_iwarp_conn_st_ctx { }; /* iwarp connection context */ -struct e4_iwarp_conn_context { +struct iwarp_conn_context { struct ystorm_iwarp_conn_st_ctx ystorm_st_context; struct regpair ystorm_st_padding[2]; struct pstorm_iwarp_conn_st_ctx pstorm_st_context; struct regpair pstorm_st_padding[2]; struct xstorm_iwarp_conn_st_ctx xstorm_st_context; - struct e4_xstorm_iwarp_conn_ag_ctx xstorm_ag_context; - struct e4_tstorm_iwarp_conn_ag_ctx tstorm_ag_context; + struct xstorm_iwarp_conn_ag_ctx xstorm_ag_context; + struct tstorm_iwarp_conn_ag_ctx tstorm_ag_context; struct timers_context timer_context; - struct e4_ustorm_rdma_conn_ag_ctx ustorm_ag_context; + struct ustorm_rdma_conn_ag_ctx ustorm_ag_context; struct tstorm_iwarp_conn_st_ctx tstorm_st_context; struct regpair tstorm_st_padding[2]; struct mstorm_iwarp_conn_st_ctx mstorm_st_context; @@ -10013,100 +10013,100 @@ struct unaligned_opaque_data { __le32 cid; }; -struct e4_mstorm_iwarp_conn_ag_ctx { +struct mstorm_iwarp_conn_ag_ctx { u8 reserved; u8 state; u8 flags0; -#define E4_MSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_MSTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_MASK 0x3 -#define E4_MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_SHIFT 2 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define MSTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_MASK 0x3 +#define MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_SHIFT 2 +#define MSTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_EN_SHIFT 0 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RCQ_CONS_EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RCQ_CONS_EN_SHIFT 6 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_INV_STAG_DONE_CF_EN_SHIFT 0 +#define MSTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_IWARP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_IWARP_CONN_AG_CTX_RCQ_CONS_EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_RCQ_CONS_EN_SHIFT 6 +#define MSTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 rcq_cons; __le16 rcq_cons_th; __le32 reg0; __le32 reg1; }; -struct e4_ustorm_iwarp_conn_ag_ctx { +struct ustorm_iwarp_conn_ag_ctx { u8 reserved; u8 byte1; u8 flags0; -#define E4_USTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_USTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define USTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_IWARP_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_SHIFT 2 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_SHIFT 4 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_IWARP_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_SHIFT 2 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_SHIFT 4 +#define USTORM_IWARP_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_IWARP_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_EN_SHIFT 4 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_EN_SHIFT 5 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_SE_EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_SE_EN_SHIFT 7 +#define USTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_IWARP_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_SE_CF_EN_SHIFT 4 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CQ_ARM_CF_EN_SHIFT 5 +#define USTORM_IWARP_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_IWARP_CONN_AG_CTX_CQ_SE_EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CQ_SE_EN_SHIFT 7 u8 flags3; -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_CQ_EN_SHIFT 0 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_IWARP_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_IWARP_CONN_AG_CTX_CQ_EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_CQ_EN_SHIFT 0 +#define USTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_IWARP_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_IWARP_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_IWARP_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_IWARP_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_IWARP_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -10119,37 +10119,37 @@ struct e4_ustorm_iwarp_conn_ag_ctx { __le16 word3; }; -struct e4_ystorm_iwarp_conn_ag_ctx { +struct ystorm_iwarp_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_IWARP_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_IWARP_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_IWARP_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_IWARP_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_IWARP_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_IWARP_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_IWARP_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_IWARP_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_IWARP_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_IWARP_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_IWARP_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_IWARP_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_IWARP_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_IWARP_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_IWARP_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_IWARP_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_IWARP_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_IWARP_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -10339,216 +10339,216 @@ struct xstorm_fcoe_conn_st_ctx { struct fcoe_wqe cached_wqes[16]; }; -struct e4_xstorm_fcoe_conn_ag_ctx { +struct xstorm_fcoe_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED1_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED2_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED3_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED4_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED4_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED5_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED5_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED6_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED6_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED1_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED2_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED3_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED4_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED4_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED5_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED5_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED6_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED6_SHIFT 7 u8 flags1; -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED7_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED7_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED8_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED8_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED9_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED9_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT12_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT12_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT13_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT13_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT14_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT14_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT15_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT15_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED7_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED7_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED8_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED8_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED9_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED9_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_BIT14_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT14_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_BIT15_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT15_SHIFT 7 u8 flags2; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF3_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF3_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF3_SHIFT 6 u8 flags3; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF7_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF7_SHIFT 6 u8 flags4; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF15_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF15_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF15_SHIFT 6 u8 flags6; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF16_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF16_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF18_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF18_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_DQ_CF_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_DQ_CF_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF16_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF16_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_DQ_CF_SHIFT 6 u8 flags7; -#define E4_XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED10_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED10_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED10_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED10_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF3EN_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF7EN_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF3EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF3EN_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF15EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF15EN_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF16EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF16EN_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_CF16EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF16EN_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF18EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF18EN_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_DQ_CF_EN_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED11_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED11_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF23EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF23EN_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED12_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED12_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED13_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED13_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_DQ_CF_EN_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED11_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED11_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_CF23EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_CF23EN_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED12_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED12_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED13_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED13_SHIFT 7 u8 flags11; -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED14_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED14_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED15_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED15_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED16_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESERVED16_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_XFERQ_DECISION_EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_XFERQ_DECISION_EN_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED14_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED14_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED15_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED15_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED16_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESERVED16_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_XFERQ_DECISION_EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_XFERQ_DECISION_EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_FCOE_CONN_AG_CTX_SQ_DECISION_EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_SQ_DECISION_EN_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_SQ_DECISION_EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_SQ_DECISION_EN_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESPQ_DECISION_EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RESPQ_DECISION_EN_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE19EN_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_RULE19EN_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_FCOE_CONN_AG_CTX_RESPQ_DECISION_EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RESPQ_DECISION_EN_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT16_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT16_SHIFT 0 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT18_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT18_SHIFT 2 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT19_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT19_SHIFT 3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT20_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT20_SHIFT 4 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT21_MASK 0x1 -#define E4_XSTORM_FCOE_CONN_AG_CTX_BIT21_SHIFT 5 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF23_MASK 0x3 -#define E4_XSTORM_FCOE_CONN_AG_CTX_CF23_SHIFT 6 +#define XSTORM_FCOE_CONN_AG_CTX_BIT16_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT16_SHIFT 0 +#define XSTORM_FCOE_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT18_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT18_SHIFT 2 +#define XSTORM_FCOE_CONN_AG_CTX_BIT19_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT19_SHIFT 3 +#define XSTORM_FCOE_CONN_AG_CTX_BIT20_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT20_SHIFT 4 +#define XSTORM_FCOE_CONN_AG_CTX_BIT21_MASK 0x1 +#define XSTORM_FCOE_CONN_AG_CTX_BIT21_SHIFT 5 +#define XSTORM_FCOE_CONN_AG_CTX_CF23_MASK 0x3 +#define XSTORM_FCOE_CONN_AG_CTX_CF23_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 word1; @@ -10586,150 +10586,150 @@ struct ustorm_fcoe_conn_st_ctx { u8 reserved[2]; }; -struct e4_tstorm_fcoe_conn_ag_ctx { +struct tstorm_fcoe_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_TSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_SHIFT 6 +#define TSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_FCOE_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_FCOE_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_FCOE_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_FCOE_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_SHIFT 6 u8 flags1; -#define E4_TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 0 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 2 -#define E4_TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_SHIFT 4 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF4_SHIFT 6 +#define TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_SHIFT 0 +#define TSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_SHIFT 4 +#define TSTORM_FCOE_CONN_AG_CTX_CF4_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF4_SHIFT 6 u8 flags2; -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF5_SHIFT 0 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_FCOE_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_FCOE_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_FCOE_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_FCOE_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF9_SHIFT 0 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF10_SHIFT 2 -#define E4_TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_EN_SHIFT 4 -#define E4_TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 6 -#define E4_TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_SHIFT 7 +#define TSTORM_FCOE_CONN_AG_CTX_CF9_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF9_SHIFT 0 +#define TSTORM_FCOE_CONN_AG_CTX_CF10_MASK 0x3 +#define TSTORM_FCOE_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_DUMMY_TIMER_CF_EN_SHIFT 4 +#define TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_FLUSH_Q0_CF_EN_SHIFT 5 +#define TSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_TIMER_STOP_ALL_CF_EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF4EN_SHIFT 0 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF5EN_SHIFT 1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF9EN_SHIFT 5 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_CF10EN_SHIFT 6 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_FCOE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_FCOE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_FCOE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_FCOE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_FCOE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_FCOE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF9EN_SHIFT 5 +#define TSTORM_FCOE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_FCOE_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_FCOE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_FCOE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define TSTORM_FCOE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_FCOE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_FCOE_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 reg0; __le32 reg1; }; -struct e4_ustorm_fcoe_conn_ag_ctx { +struct ustorm_fcoe_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_USTORM_FCOE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_USTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_FCOE_CONN_AG_CTX_BIT0_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_FCOE_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF4_SHIFT 2 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF5_SHIFT 4 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_FCOE_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_FCOE_CONN_AG_CTX_CF4_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF4_SHIFT 2 +#define USTORM_FCOE_CONN_AG_CTX_CF5_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF5_SHIFT 4 +#define USTORM_FCOE_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_FCOE_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF4EN_SHIFT 4 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF5EN_SHIFT 5 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define USTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_FCOE_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_FCOE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF4EN_SHIFT 4 +#define USTORM_FCOE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF5EN_SHIFT 5 +#define USTORM_FCOE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags3; -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_FCOE_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_FCOE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_FCOE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_FCOE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_FCOE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_FCOE_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -10770,37 +10770,37 @@ struct tstorm_fcoe_conn_st_ctx { u8 reserved0[4]; }; -struct e4_mstorm_fcoe_conn_ag_ctx { +struct mstorm_fcoe_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_MSTORM_FCOE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_MSTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_FCOE_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; @@ -10846,21 +10846,21 @@ struct mstorm_fcoe_conn_st_ctx { }; /* fcoe connection context */ -struct e4_fcoe_conn_context { +struct fcoe_conn_context { struct ystorm_fcoe_conn_st_ctx ystorm_st_context; struct pstorm_fcoe_conn_st_ctx pstorm_st_context; struct regpair pstorm_st_padding[2]; struct xstorm_fcoe_conn_st_ctx xstorm_st_context; - struct e4_xstorm_fcoe_conn_ag_ctx xstorm_ag_context; + struct xstorm_fcoe_conn_ag_ctx xstorm_ag_context; struct regpair xstorm_ag_padding[6]; struct ustorm_fcoe_conn_st_ctx ustorm_st_context; struct regpair ustorm_st_padding[2]; - struct e4_tstorm_fcoe_conn_ag_ctx tstorm_ag_context; + struct tstorm_fcoe_conn_ag_ctx tstorm_ag_context; struct regpair tstorm_ag_padding[2]; struct timers_context timer_context; - struct e4_ustorm_fcoe_conn_ag_ctx ustorm_ag_context; + struct ustorm_fcoe_conn_ag_ctx ustorm_ag_context; struct tstorm_fcoe_conn_st_ctx tstorm_st_context; - struct e4_mstorm_fcoe_conn_ag_ctx mstorm_ag_context; + struct mstorm_fcoe_conn_ag_ctx mstorm_ag_context; struct mstorm_fcoe_conn_st_ctx mstorm_st_context; }; @@ -10911,37 +10911,37 @@ struct fcoe_stat_ramrod_params { struct fcoe_stat_ramrod_data stat_ramrod_data; }; -struct e4_ystorm_fcoe_conn_ag_ctx { +struct ystorm_fcoe_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_FCOE_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_FCOE_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_FCOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_FCOE_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_FCOE_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_FCOE_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_FCOE_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_FCOE_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_FCOE_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_FCOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_FCOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_FCOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_FCOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_FCOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_FCOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_FCOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_FCOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_FCOE_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -10972,216 +10972,216 @@ struct xstorm_iscsi_tcp_conn_st_ctx { __le32 reserved_iscsi[44]; }; -struct e4_xstorm_iscsi_conn_ag_ctx { +struct xstorm_iscsi_conn_ag_ctx { u8 cdu_validation; u8 state; u8 flags0; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM1_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM1_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RESERVED1_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RESERVED1_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RESERVED2_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RESERVED2_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT6_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT6_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT7_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT7_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM1_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM1_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED1_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT4_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT4_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED2_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT6_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT6_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT7_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT7_SHIFT 7 u8 flags1; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT8_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT8_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT9_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT9_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT10_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT10_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT11_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT11_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT12_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT12_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT13_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT13_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT14_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT14_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TX_TRUNCATE_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TX_TRUNCATE_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT8_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT8_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT9_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT9_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT10_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT10_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT14_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT14_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_TRUNCATE_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_TRUNCATE_SHIFT 7 u8 flags2; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 6 u8 flags3; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF4_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF5_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF6_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF7_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF7_SHIFT 6 u8 flags4; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF8_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF9_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF9_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF10_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF11_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF11_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF11_SHIFT 6 u8 flags5; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF12_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF12_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF13_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF13_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF14_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF14_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_SHIFT 6 u8 flags6; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF16_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF16_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF17_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF17_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF18_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF18_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF16_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF16_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 u8 flags7; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 7 u8 flags8; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF4EN_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF5EN_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF6EN_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF7EN_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF8EN_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF9EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF9EN_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF9EN_SHIFT 7 u8 flags9; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF10EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF10EN_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF11EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF11EN_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF12EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF12EN_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF13EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF13EN_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF14EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF14EN_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_EN_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF16EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF16EN_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF17EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF17EN_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_UPDATE_STATE_TO_BASE_CF_EN_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_CF16EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF16EN_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF17EN_SHIFT 7 u8 flags10; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF18EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_MST_XCM_Q0_FLUSH_CF_EN_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_UST_XCM_Q1_FLUSH_CF_EN_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_EN_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_MORE_TO_SEND_DEC_RULE_EN_SHIFT 7 u8 flags11; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE5EN_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE6EN_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE7EN_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE9EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE9EN_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RESERVED3_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE9EN_SHIFT 7 u8 flags12; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_SQ_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_SQ_DEC_RULE_EN_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE11EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE11EN_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE14EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE14EN_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE15EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE15EN_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE16EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE16EN_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE17EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_RULE17EN_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_SQ_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_SQ_DEC_RULE_EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_RULE17EN_SHIFT 7 u8 flags13; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_R2TQ_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_R2TQ_DEC_RULE_EN_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_HQ_DEC_RULE_EN_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_HQ_DEC_RULE_EN_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 +#define XSTORM_ISCSI_CONN_AG_CTX_R2TQ_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_R2TQ_DEC_RULE_EN_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_HQ_DEC_RULE_EN_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_HQ_DEC_RULE_EN_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 u8 flags14; -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT16_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT16_SHIFT 0 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT17_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT17_SHIFT 1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT18_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT18_SHIFT 2 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT19_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT19_SHIFT 3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT20_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_BIT20_SHIFT 4 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_DUMMY_READ_DONE_MASK 0x1 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_DUMMY_READ_DONE_SHIFT 5 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_MASK 0x3 -#define E4_XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_SHIFT 6 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT16_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT16_SHIFT 0 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT18_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT18_SHIFT 2 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT19_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT19_SHIFT 3 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT20_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_BIT20_SHIFT 4 +#define XSTORM_ISCSI_CONN_AG_CTX_DUMMY_READ_DONE_MASK 0x1 +#define XSTORM_ISCSI_CONN_AG_CTX_DUMMY_READ_DONE_SHIFT 5 +#define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_MASK 0x3 +#define XSTORM_ISCSI_CONN_AG_CTX_PROC_ONLY_CLEANUP_SHIFT 6 u8 byte2; __le16 physical_q0; __le16 physical_q1; @@ -11229,89 +11229,89 @@ struct e4_xstorm_iscsi_conn_ag_ctx { __le32 reg17; }; -struct e4_tstorm_iscsi_conn_ag_ctx { +struct tstorm_iscsi_conn_ag_ctx { u8 reserved0; u8 state; u8 flags0; -#define E4_TSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT2_SHIFT 2 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT3_SHIFT 3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT4_SHIFT 4 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_BIT5_SHIFT 5 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT 0 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT 2 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF4_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 +#define TSTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF4_SHIFT 6 u8 flags2; -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF5_SHIFT 0 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF6_SHIFT 2 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF7_SHIFT 4 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF8_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF8_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_ISCSI_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF8_SHIFT 6 u8 flags3; -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_MASK 0x3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_SHIFT 2 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 4 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT 5 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT 6 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_MASK 0x3 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 4 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_P2T_FLUSH_CF_EN_SHIFT 5 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_M2T_FLUSH_CF_EN_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF4EN_SHIFT 0 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF5EN_SHIFT 1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF6EN_SHIFT 2 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF7EN_SHIFT 3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF8EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_CF8EN_SHIFT 4 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 5 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_EN_SHIFT 6 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define TSTORM_ISCSI_CONN_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_ISCSI_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 5 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_FLUSH_OOO_ISLES_CF_EN_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags5; -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_TSTORM_ISCSI_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_ISCSI_CONN_AG_CTX_RULE8EN_SHIFT 7 __le32 reg0; __le32 reg1; __le32 rx_tcp_checksum_err_cnt; @@ -11326,63 +11326,63 @@ struct e4_tstorm_iscsi_conn_ag_ctx { __le16 word0; }; -struct e4_ustorm_iscsi_conn_ag_ctx { +struct ustorm_iscsi_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_USTORM_ISCSI_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_USTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 6 +#define USTORM_ISCSI_CONN_AG_CTX_BIT0_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_BIT0_SHIFT 0 +#define USTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF3_SHIFT 0 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF4_SHIFT 2 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF5_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF5_SHIFT 4 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF6_MASK 0x3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF6_SHIFT 6 +#define USTORM_ISCSI_CONN_AG_CTX_CF3_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF3_SHIFT 0 +#define USTORM_ISCSI_CONN_AG_CTX_CF4_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF4_SHIFT 2 +#define USTORM_ISCSI_CONN_AG_CTX_CF5_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF5_SHIFT 4 +#define USTORM_ISCSI_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_ISCSI_CONN_AG_CTX_CF6_SHIFT 6 u8 flags2; -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF4EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF4EN_SHIFT 4 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF5EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF5EN_SHIFT 5 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF6EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_CF6EN_SHIFT 6 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 7 +#define USTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_ISCSI_CONN_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ISCSI_CONN_AG_CTX_CF4EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF4EN_SHIFT 4 +#define USTORM_ISCSI_CONN_AG_CTX_CF5EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF5EN_SHIFT 5 +#define USTORM_ISCSI_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 7 u8 flags3; -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 0 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 2 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 3 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE5EN_SHIFT 4 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE6EN_SHIFT 5 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE7EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE7EN_SHIFT 6 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE8EN_MASK 0x1 -#define E4_USTORM_ISCSI_CONN_AG_CTX_RULE8EN_SHIFT 7 +#define USTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_ISCSI_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_ISCSI_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_ISCSI_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_ISCSI_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_ISCSI_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; @@ -11400,37 +11400,37 @@ struct tstorm_iscsi_conn_st_ctx { __le32 reserved[44]; }; -struct e4_mstorm_iscsi_conn_ag_ctx { +struct mstorm_iscsi_conn_ag_ctx { u8 reserved; u8 state; u8 flags0; -#define E4_MSTORM_ISCSI_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 6 +#define MSTORM_ISCSI_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define MSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 7 __le16 word0; __le16 word1; __le32 reg0; @@ -11449,22 +11449,22 @@ struct ustorm_iscsi_conn_st_ctx { }; /* iscsi connection context */ -struct e4_iscsi_conn_context { +struct iscsi_conn_context { struct ystorm_iscsi_conn_st_ctx ystorm_st_context; struct pstorm_iscsi_tcp_conn_st_ctx pstorm_st_context; struct regpair pstorm_st_padding[2]; struct pb_context xpb2_context; struct xstorm_iscsi_tcp_conn_st_ctx xstorm_st_context; struct regpair xstorm_st_padding[2]; - struct e4_xstorm_iscsi_conn_ag_ctx xstorm_ag_context; - struct e4_tstorm_iscsi_conn_ag_ctx tstorm_ag_context; + struct xstorm_iscsi_conn_ag_ctx xstorm_ag_context; + struct tstorm_iscsi_conn_ag_ctx tstorm_ag_context; struct regpair tstorm_ag_padding[2]; struct timers_context timer_context; - struct e4_ustorm_iscsi_conn_ag_ctx ustorm_ag_context; + struct ustorm_iscsi_conn_ag_ctx ustorm_ag_context; struct pb_context upb_context; struct tstorm_iscsi_conn_st_ctx tstorm_st_context; struct regpair tstorm_st_padding[2]; - struct e4_mstorm_iscsi_conn_ag_ctx mstorm_ag_context; + struct mstorm_iscsi_conn_ag_ctx mstorm_ag_context; struct mstorm_iscsi_tcp_conn_st_ctx mstorm_st_context; struct ustorm_iscsi_conn_st_ctx ustorm_st_context; }; @@ -11475,37 +11475,37 @@ struct iscsi_init_ramrod_params { struct tcp_init_params tcp_init; }; -struct e4_ystorm_iscsi_conn_ag_ctx { +struct ystorm_iscsi_conn_ag_ctx { u8 byte0; u8 byte1; u8 flags0; -#define E4_YSTORM_ISCSI_CONN_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_BIT0_SHIFT 0 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 2 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 4 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 6 +#define YSTORM_ISCSI_CONN_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_BIT0_SHIFT 0 +#define YSTORM_ISCSI_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_ISCSI_CONN_AG_CTX_CF0_MASK 0x3 +#define YSTORM_ISCSI_CONN_AG_CTX_CF0_SHIFT 2 +#define YSTORM_ISCSI_CONN_AG_CTX_CF1_MASK 0x3 +#define YSTORM_ISCSI_CONN_AG_CTX_CF1_SHIFT 4 +#define YSTORM_ISCSI_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_ISCSI_CONN_AG_CTX_CF2_SHIFT 6 u8 flags1; -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 0 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 2 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 3 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 4 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 5 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 6 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 7 +#define YSTORM_ISCSI_CONN_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_CF0EN_SHIFT 0 +#define YSTORM_ISCSI_CONN_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_CF1EN_SHIFT 1 +#define YSTORM_ISCSI_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ISCSI_CONN_AG_CTX_RULE4EN_SHIFT 7 u8 byte2; u8 byte3; __le16 word0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index ea888a2c6ddb..30c0b5502670 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -17,13 +17,13 @@ #define CDU_VALIDATION_DEFAULT_CFG 61 -static u16 con_region_offsets[3][NUM_OF_CONNECTION_TYPES_E4] = { +static u16 con_region_offsets[3][NUM_OF_CONNECTION_TYPES] = { {400, 336, 352, 368, 304, 384, 416, 352}, /* region 3 offsets */ {528, 496, 416, 512, 448, 512, 544, 480}, /* region 4 offsets */ {608, 544, 496, 576, 576, 592, 624, 560} /* region 5 offsets */ }; -static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES_E4] = { +static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES] = { {240, 240, 112, 0, 0, 0, 0, 96} /* region 1 offsets */ }; @@ -54,7 +54,7 @@ static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES_E4] = { #define QM_WFQ_VP_PQ_VOQ_SHIFT 0 /* Bit of PF in WFQ VP PQ map */ -#define QM_WFQ_VP_PQ_PF_E4_SHIFT 5 +#define QM_WFQ_VP_PQ_PF_SHIFT 5 /* 0x9000 = 4*9*1024 */ #define QM_WFQ_INC_VAL(weight) ((weight) * 0x9000) @@ -156,20 +156,20 @@ static u16 task_region_offsets[1][NUM_OF_CONNECTION_TYPES_E4] = { cmd ## _ ## field, \ value) -#define QM_INIT_TX_PQ_MAP(p_hwfn, map, chip, pq_id, vp_pq_id, rl_valid, \ +#define QM_INIT_TX_PQ_MAP(p_hwfn, map, pq_id, vp_pq_id, rl_valid, \ rl_id, ext_voq, wrr) \ do { \ u32 __reg = 0; \ \ BUILD_BUG_ON(sizeof((map).reg) != sizeof(__reg)); \ \ - SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_PQ_VALID, 1); \ - SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_RL_VALID, \ + SET_FIELD(__reg, QM_RF_PQ_MAP_PQ_VALID, 1); \ + SET_FIELD(__reg, QM_RF_PQ_MAP_RL_VALID, \ !!(rl_valid)); \ - SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_VP_PQ_ID, (vp_pq_id)); \ - SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_RL_ID, (rl_id)); \ - SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_VOQ, (ext_voq)); \ - SET_FIELD(__reg, QM_RF_PQ_MAP_##chip##_WRR_WEIGHT_GROUP, \ + SET_FIELD(__reg, QM_RF_PQ_MAP_VP_PQ_ID, (vp_pq_id)); \ + SET_FIELD(__reg, QM_RF_PQ_MAP_RL_ID, (rl_id)); \ + SET_FIELD(__reg, QM_RF_PQ_MAP_VOQ, (ext_voq)); \ + SET_FIELD(__reg, QM_RF_PQ_MAP_WRR_WEIGHT_GROUP, \ (wrr)); \ \ STORE_RT_REG((p_hwfn), QM_REG_TXPQMAP_RT_OFFSET + (pq_id), \ @@ -204,7 +204,7 @@ static void qed_enable_pf_rl(struct qed_hwfn *p_hwfn, bool pf_rl_en) { STORE_RT_REG(p_hwfn, QM_REG_RLPFENABLE_RT_OFFSET, pf_rl_en ? 1 : 0); if (pf_rl_en) { - u8 num_ext_voqs = MAX_NUM_VOQS_E4; + u8 num_ext_voqs = MAX_NUM_VOQS; u64 voq_bit_mask = ((u64)1 << num_ext_voqs) - 1; /* Enable RLs for all VOQs */ @@ -298,7 +298,7 @@ static void qed_cmdq_lines_rt_init( struct init_qm_port_params port_params[MAX_NUM_PORTS]) { u8 tc, ext_voq, port_id, num_tcs_in_port; - u8 num_ext_voqs = MAX_NUM_VOQS_E4; + u8 num_ext_voqs = MAX_NUM_VOQS; /* Clear PBF lines of all VOQs */ for (ext_voq = 0; ext_voq < num_ext_voqs; ext_voq++) @@ -487,7 +487,7 @@ static void qed_tx_pq_map_rt_init(struct qed_hwfn *p_hwfn, /* Go over all Tx PQs */ for (i = 0, pq_id = p_params->start_pq; i < num_pqs; i++, pq_id++) { u16 *p_first_tx_pq_id, vport_id_in_pf; - struct qm_rf_pq_map_e4 tx_pq_map; + struct qm_rf_pq_map tx_pq_map; u8 tc_id = pq_params[i].tc_id; bool is_vf_pq; u8 ext_voq; @@ -505,7 +505,7 @@ static void qed_tx_pq_map_rt_init(struct qed_hwfn *p_hwfn, if (*p_first_tx_pq_id == QM_INVALID_PQ_ID) { u32 map_val = (ext_voq << QM_WFQ_VP_PQ_VOQ_SHIFT) | - (p_params->pf_id << QM_WFQ_VP_PQ_PF_E4_SHIFT); + (p_params->pf_id << QM_WFQ_VP_PQ_PF_SHIFT); /* Create new VP PQ */ *p_first_tx_pq_id = pq_id; @@ -520,7 +520,6 @@ static void qed_tx_pq_map_rt_init(struct qed_hwfn *p_hwfn, /* Prepare PQ map entry */ QM_INIT_TX_PQ_MAP(p_hwfn, tx_pq_map, - E4, pq_id, *p_first_tx_pq_id, pq_params[i].rl_valid, diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index f78e6055f654..a97f691839e0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -36,7 +36,7 @@ struct qed_sb_sp_info { struct qed_sb_info sb_info; /* per protocol index data */ - struct qed_pi_info pi_info_arr[PIS_PER_SB_E4]; + struct qed_pi_info pi_info_arr[PIS_PER_SB]; }; enum qed_attention_type { @@ -1507,7 +1507,7 @@ static void qed_int_cau_conf_pi(struct qed_hwfn *p_hwfn, else SET_FIELD(prod, CAU_PI_ENTRY_FSM_SEL, 1); - sb_offset = igu_sb_id * PIS_PER_SB_E4; + sb_offset = igu_sb_id * PIS_PER_SB; pi_offset = sb_offset + pi_index; if (p_hwfn->hw_init_done) diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index eb8e0f4242d7..84c17e97f569 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -204,7 +204,7 @@ int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); #define QED_SB_EVENT_MASK 0x0003 #define SB_ALIGNED_SIZE(p_hwfn) \ - ALIGNED_TYPE_SIZE(struct status_block_e4, p_hwfn) + ALIGNED_TYPE_SIZE(struct status_block, p_hwfn) #define QED_SB_INVALID_IDX 0xffff diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index c46a7f756ed5..bf48a66704bd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -1533,7 +1533,7 @@ static inline u8 qed_ll2_handle_to_queue_id(struct qed_hwfn *p_hwfn, int qed_ll2_establish_connection(void *cxt, u8 connection_handle) { - struct e4_core_conn_context *p_cxt; + struct core_conn_context *p_cxt; struct qed_ll2_tx_packet *p_pkt; struct qed_ll2_info *p_ll2_conn; struct qed_hwfn *p_hwfn = cxt; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 24cd41567775..2b39fa294d32 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3905,10 +3905,6 @@ int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK | DRV_MB_PARAM_FEATURE_SUPPORT_PORT_FEC_CONTROL; - if (QED_IS_E5(p_hwfn->cdev)) - features |= - DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EXT_SPEED_FEC_CONTROL; - return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_FEATURE_SUPPORT, features, &mcp_resp, &mcp_param); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index da1b7fdcbda7..fd338a8dbedc 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -1531,7 +1531,7 @@ 0x1940000UL #define SEM_FAST_REG_DBG_MODE23_SRC_DISABLE \ 0x000748UL -#define SEM_FAST_REG_DBG_MODE4_SRC_DISABLE \ +#define SEM_FAST_REG_DBG_MODSRC_DISABLE \ 0x00074cUL #define SEM_FAST_REG_DBG_MODE6_SRC_DISABLE \ 0x000750UL diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 0bc1a0aeb56e..fa8385178538 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -189,7 +189,7 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn, static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq) { - struct e4_core_conn_context *p_cxt; + struct core_conn_context *p_cxt; struct qed_cxt_info cxt_info; u16 physical_q; int rc; @@ -207,11 +207,11 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, p_cxt = cxt_info.p_cxt; SET_FIELD(p_cxt->xstorm_ag_context.flags10, - E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_EN, 1); + XSTORM_CORE_CONN_AG_CTX_DQ_CF_EN, 1); SET_FIELD(p_cxt->xstorm_ag_context.flags1, - E4_XSTORM_CORE_CONN_AG_CTX_DQ_CF_ACTIVE, 1); + XSTORM_CORE_CONN_AG_CTX_DQ_CF_ACTIVE, 1); SET_FIELD(p_cxt->xstorm_ag_context.flags9, - E4_XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN, 1); + XSTORM_CORE_CONN_AG_CTX_CONSOLID_PROD_CF_EN, 1); /* QM physical queue */ physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index ed2b6fe5a78d..08d92711c7a2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -1603,7 +1603,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn, /* fill in pfdev info */ pfdev_info->chip_num = p_hwfn->cdev->chip_num; pfdev_info->db_size = 0; - pfdev_info->indices_per_sb = PIS_PER_SB_E4; + pfdev_info->indices_per_sb = PIS_PER_SB; pfdev_info->capabilities = PFVF_ACQUIRE_CAP_DEFAULT_UNTAGGED | PFVF_ACQUIRE_CAP_POST_FW_OVERRIDE; @@ -3581,11 +3581,11 @@ static int qed_iov_vf_flr_poll_pbf(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf, struct qed_ptt *p_ptt) { - u32 cons[MAX_NUM_VOQS_E4], distance[MAX_NUM_VOQS_E4]; + u32 cons[MAX_NUM_VOQS], distance[MAX_NUM_VOQS]; int i, cnt; /* Read initial consumers & producers */ - for (i = 0; i < MAX_NUM_VOQS_E4; i++) { + for (i = 0; i < MAX_NUM_VOQS; i++) { u32 prod; cons[i] = qed_rd(p_hwfn, p_ptt, @@ -3600,7 +3600,7 @@ qed_iov_vf_flr_poll_pbf(struct qed_hwfn *p_hwfn, /* Wait for consumers to pass the producers */ i = 0; for (cnt = 0; cnt < 50; cnt++) { - for (; i < MAX_NUM_VOQS_E4; i++) { + for (; i < MAX_NUM_VOQS; i++) { u32 tmp; tmp = qed_rd(p_hwfn, p_ptt, @@ -3610,7 +3610,7 @@ qed_iov_vf_flr_poll_pbf(struct qed_hwfn *p_hwfn, break; } - if (i == MAX_NUM_VOQS_E4) + if (i == MAX_NUM_VOQS) break; msleep(20); diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index be33bde0f731..06c6a5813606 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1395,7 +1395,7 @@ static void qede_free_mem_sb(struct qede_dev *edev, struct qed_sb_info *sb_info, static int qede_alloc_mem_sb(struct qede_dev *edev, struct qed_sb_info *sb_info, u16 sb_id) { - struct status_block_e4 *sb_virt; + struct status_block *sb_virt; dma_addr_t sb_phys; int rc; diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c index 747af96dd15c..e8bc8d9e4583 100644 --- a/drivers/scsi/qedf/drv_fcoe_fw_funcs.c +++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.c @@ -22,9 +22,9 @@ int init_initiator_rw_fcoe_task(struct fcoe_task_params *task_params, u32 task_retry_id, u8 fcp_cmd_payload[32]) { - struct e4_fcoe_task_context *ctx = task_params->context; + struct fcoe_task_context *ctx = task_params->context; const u8 val_byte = ctx->ystorm_ag_context.byte0; - struct e4_ustorm_fcoe_task_ag_ctx *u_ag_ctx; + struct ustorm_fcoe_task_ag_ctx *u_ag_ctx; struct ystorm_fcoe_task_st_ctx *y_st_ctx; struct tstorm_fcoe_task_st_ctx *t_st_ctx; struct mstorm_fcoe_task_st_ctx *m_st_ctx; @@ -115,9 +115,9 @@ int init_initiator_midpath_unsolicited_fcoe_task( struct scsi_sgl_task_params *rx_sgl_task_params, u8 fw_to_place_fc_header) { - struct e4_fcoe_task_context *ctx = task_params->context; + struct fcoe_task_context *ctx = task_params->context; const u8 val_byte = ctx->ystorm_ag_context.byte0; - struct e4_ustorm_fcoe_task_ag_ctx *u_ag_ctx; + struct ustorm_fcoe_task_ag_ctx *u_ag_ctx; struct ystorm_fcoe_task_st_ctx *y_st_ctx; struct tstorm_fcoe_task_st_ctx *t_st_ctx; struct mstorm_fcoe_task_st_ctx *m_st_ctx; diff --git a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h index 1ee31a5f063b..7125e484bf93 100644 --- a/drivers/scsi/qedf/drv_fcoe_fw_funcs.h +++ b/drivers/scsi/qedf/drv_fcoe_fw_funcs.h @@ -10,7 +10,7 @@ struct fcoe_task_params { /* Output parameter [set/filled by the HSI function] */ - struct e4_fcoe_task_context *context; + struct fcoe_task_context *context; /* Output parameter [set/filled by the HSI function] */ struct fcoe_wqe *sqe; diff --git a/drivers/scsi/qedf/qedf.h b/drivers/scsi/qedf/qedf.h index ba94413fe2ea..631a15969d21 100644 --- a/drivers/scsi/qedf/qedf.h +++ b/drivers/scsi/qedf/qedf.h @@ -141,7 +141,7 @@ struct qedf_ioreq { struct completion tm_done; struct completion abts_done; struct completion cleanup_done; - struct e4_fcoe_task_context *task; + struct fcoe_task_context *task; struct fcoe_task_params *task_params; struct scsi_sgl_task_params *sgl_task_params; int idx; @@ -503,7 +503,7 @@ extern void qedf_cmd_timer_set(struct qedf_ctx *qedf, struct qedf_ioreq *io_req, unsigned int timer_msec); extern int qedf_init_mp_req(struct qedf_ioreq *io_req); extern void qedf_init_mp_task(struct qedf_ioreq *io_req, - struct e4_fcoe_task_context *task_ctx, struct fcoe_wqe *sqe); + struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe); extern u16 qedf_get_sqe_idx(struct qedf_rport *fcport); extern void qedf_ring_doorbell(struct qedf_rport *fcport); extern void qedf_process_els_compl(struct qedf_ctx *qedf, struct fcoe_cqe *cqe, diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c index 625e58ccb8c8..1ff5bc314fc0 100644 --- a/drivers/scsi/qedf/qedf_els.c +++ b/drivers/scsi/qedf/qedf_els.c @@ -16,7 +16,7 @@ static int qedf_initiate_els(struct qedf_rport *fcport, unsigned int op, struct qedf_ioreq *els_req; struct qedf_mp_req *mp_req; struct fc_frame_header *fc_hdr; - struct e4_fcoe_task_context *task; + struct fcoe_task_context *task; int rc = 0; uint32_t did, sid; uint16_t xid; diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index 3404782988d5..b649f835d436 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -584,7 +584,7 @@ static void qedf_build_fcp_cmnd(struct qedf_ioreq *io_req, } static void qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport, - struct qedf_ioreq *io_req, struct e4_fcoe_task_context *task_ctx, + struct qedf_ioreq *io_req, struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe) { enum fcoe_task_type task_type; @@ -602,7 +602,7 @@ static void qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport, /* Note init_initiator_rw_fcoe_task memsets the task context */ io_req->task = task_ctx; - memset(task_ctx, 0, sizeof(struct e4_fcoe_task_context)); + memset(task_ctx, 0, sizeof(struct fcoe_task_context)); memset(io_req->task_params, 0, sizeof(struct fcoe_task_params)); memset(io_req->sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); @@ -674,7 +674,7 @@ static void qedf_init_task(struct qedf_rport *fcport, struct fc_lport *lport, } void qedf_init_mp_task(struct qedf_ioreq *io_req, - struct e4_fcoe_task_context *task_ctx, struct fcoe_wqe *sqe) + struct fcoe_task_context *task_ctx, struct fcoe_wqe *sqe) { struct qedf_mp_req *mp_req = &(io_req->mp_req); struct qedf_rport *fcport = io_req->fcport; @@ -692,7 +692,7 @@ void qedf_init_mp_task(struct qedf_ioreq *io_req, memset(&tx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); memset(&rx_sgl_task_params, 0, sizeof(struct scsi_sgl_task_params)); - memset(task_ctx, 0, sizeof(struct e4_fcoe_task_context)); + memset(task_ctx, 0, sizeof(struct fcoe_task_context)); memset(&task_fc_hdr, 0, sizeof(struct fcoe_tx_mid_path_params)); /* Setup the task from io_req for easy reference */ @@ -850,7 +850,7 @@ int qedf_post_io_req(struct qedf_rport *fcport, struct qedf_ioreq *io_req) struct Scsi_Host *host = sc_cmd->device->host; struct fc_lport *lport = shost_priv(host); struct qedf_ctx *qedf = lport_priv(lport); - struct e4_fcoe_task_context *task_ctx; + struct fcoe_task_context *task_ctx; u16 xid; struct fcoe_wqe *sqe; u16 sqe_idx; @@ -2293,7 +2293,7 @@ static int qedf_execute_tmf(struct qedf_rport *fcport, struct scsi_cmnd *sc_cmd, uint8_t tm_flags) { struct qedf_ioreq *io_req; - struct e4_fcoe_task_context *task; + struct fcoe_task_context *task; struct qedf_ctx *qedf = fcport->qedf; struct fc_lport *lport = qedf->lport; int rc = 0; diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 94ee08fab46a..0da32fd3302e 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -2170,7 +2170,7 @@ static bool qedf_fp_has_work(struct qedf_fastpath *fp) struct qedf_ctx *qedf = fp->qedf; struct global_queue *que; struct qed_sb_info *sb_info = fp->sb_info; - struct status_block_e4 *sb = sb_info->sb_virt; + struct status_block *sb = sb_info->sb_virt; u16 prod_idx; /* Get the pointer to the global CQ this completion is on */ @@ -2197,7 +2197,7 @@ static bool qedf_process_completions(struct qedf_fastpath *fp) { struct qedf_ctx *qedf = fp->qedf; struct qed_sb_info *sb_info = fp->sb_info; - struct status_block_e4 *sb = sb_info->sb_virt; + struct status_block *sb = sb_info->sb_virt; struct global_queue *que; u16 prod_idx; struct fcoe_cqe *cqe; @@ -2688,12 +2688,12 @@ void qedf_fp_io_handler(struct work_struct *work) static int qedf_alloc_and_init_sb(struct qedf_ctx *qedf, struct qed_sb_info *sb_info, u16 sb_id) { - struct status_block_e4 *sb_virt; + struct status_block *sb_virt; dma_addr_t sb_phys; int ret; sb_virt = dma_alloc_coherent(&qedf->pdev->dev, - sizeof(struct status_block_e4), &sb_phys, GFP_KERNEL); + sizeof(struct status_block), &sb_phys, GFP_KERNEL); if (!sb_virt) { QEDF_ERR(&qedf->dbg_ctx, diff --git a/drivers/scsi/qedi/qedi_debugfs.c b/drivers/scsi/qedi/qedi_debugfs.c index 42f5afb60055..8deb2001dc2f 100644 --- a/drivers/scsi/qedi/qedi_debugfs.c +++ b/drivers/scsi/qedi/qedi_debugfs.c @@ -136,7 +136,7 @@ qedi_gbl_ctx_show(struct seq_file *s, void *unused) { struct qedi_fastpath *fp = NULL; struct qed_sb_info *sb_info = NULL; - struct status_block_e4 *sb = NULL; + struct status_block *sb = NULL; struct global_queue *que = NULL; int id; u16 prod_idx; @@ -152,7 +152,7 @@ qedi_gbl_ctx_show(struct seq_file *s, void *unused) sb_info = fp->sb_info; sb = sb_info->sb_virt; prod_idx = (sb->pi_array[QEDI_PROTO_CQ_PROD_IDX] & - STATUS_BLOCK_E4_PROD_INDEX_MASK); + STATUS_BLOCK_PROD_INDEX_MASK); seq_printf(s, "SB PROD IDX: %d\n", prod_idx); que = qedi->global_queues[fp->sb_id]; seq_printf(s, "DRV CONS IDX: %d\n", que->cq_cons_idx); diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index d01cd829ef97..84a4204a2cb4 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -85,7 +85,7 @@ static void qedi_process_text_resp(struct qedi_ctx *qedi, { struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data; struct iscsi_session *session = conn->session; - struct e4_iscsi_task_context *task_ctx; + struct iscsi_task_context *task_ctx; struct iscsi_text_rsp *resp_hdr_ptr; struct iscsi_text_response_hdr *cqe_text_response; struct qedi_cmd *cmd; @@ -261,7 +261,7 @@ static void qedi_process_login_resp(struct qedi_ctx *qedi, { struct iscsi_conn *conn = qedi_conn->cls_conn->dd_data; struct iscsi_session *session = conn->session; - struct e4_iscsi_task_context *task_ctx; + struct iscsi_task_context *task_ctx; struct iscsi_login_rsp *resp_hdr_ptr; struct iscsi_login_response_hdr *cqe_login_response; struct qedi_cmd *cmd; @@ -970,7 +970,7 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, struct scsi_sgl_task_params tx_sgl_task_params; struct scsi_sgl_task_params rx_sgl_task_params; struct iscsi_task_params task_params; - struct e4_iscsi_task_context *fw_task_ctx; + struct iscsi_task_context *fw_task_ctx; struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_login_req *login_hdr; struct scsi_sge *resp_sge = NULL; @@ -990,9 +990,9 @@ int qedi_send_iscsi_login(struct qedi_conn *qedi_conn, return -ENOMEM; fw_task_ctx = - (struct e4_iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); - memset(fw_task_ctx, 0, sizeof(struct e4_iscsi_task_context)); + memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; @@ -1073,7 +1073,7 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn, struct scsi_sgl_task_params tx_sgl_task_params; struct scsi_sgl_task_params rx_sgl_task_params; struct iscsi_task_params task_params; - struct e4_iscsi_task_context *fw_task_ctx; + struct iscsi_task_context *fw_task_ctx; struct iscsi_logout *logout_hdr = NULL; struct qedi_ctx *qedi = qedi_conn->qedi; struct qedi_cmd *qedi_cmd; @@ -1091,9 +1091,9 @@ int qedi_send_iscsi_logout(struct qedi_conn *qedi_conn, return -ENOMEM; fw_task_ctx = - (struct e4_iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); - memset(fw_task_ctx, 0, sizeof(struct e4_iscsi_task_context)); + memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; @@ -1434,7 +1434,7 @@ static int send_iscsi_tmf(struct qedi_conn *qedi_conn, struct iscsi_task *mtask, struct iscsi_tmf_request_hdr tmf_pdu_header; struct iscsi_task_params task_params; struct qedi_ctx *qedi = qedi_conn->qedi; - struct e4_iscsi_task_context *fw_task_ctx; + struct iscsi_task_context *fw_task_ctx; struct iscsi_tm *tmf_hdr; struct qedi_cmd *qedi_cmd; struct qedi_cmd *cmd; @@ -1454,9 +1454,9 @@ static int send_iscsi_tmf(struct qedi_conn *qedi_conn, struct iscsi_task *mtask, return -ENOMEM; fw_task_ctx = - (struct e4_iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); - memset(fw_task_ctx, 0, sizeof(struct e4_iscsi_task_context)); + memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; @@ -1548,7 +1548,7 @@ int qedi_send_iscsi_text(struct qedi_conn *qedi_conn, struct scsi_sgl_task_params tx_sgl_task_params; struct scsi_sgl_task_params rx_sgl_task_params; struct iscsi_task_params task_params; - struct e4_iscsi_task_context *fw_task_ctx; + struct iscsi_task_context *fw_task_ctx; struct qedi_ctx *qedi = qedi_conn->qedi; struct iscsi_text *text_hdr; struct scsi_sge *req_sge = NULL; @@ -1570,9 +1570,9 @@ int qedi_send_iscsi_text(struct qedi_conn *qedi_conn, return -ENOMEM; fw_task_ctx = - (struct e4_iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); - memset(fw_task_ctx, 0, sizeof(struct e4_iscsi_task_context)); + memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; @@ -1649,7 +1649,7 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, struct scsi_sgl_task_params rx_sgl_task_params; struct iscsi_task_params task_params; struct qedi_ctx *qedi = qedi_conn->qedi; - struct e4_iscsi_task_context *fw_task_ctx; + struct iscsi_task_context *fw_task_ctx; struct iscsi_nopout *nopout_hdr; struct scsi_sge *resp_sge = NULL; struct qedi_cmd *qedi_cmd; @@ -1669,9 +1669,9 @@ int qedi_send_iscsi_nopout(struct qedi_conn *qedi_conn, return -ENOMEM; fw_task_ctx = - (struct e4_iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); - memset(fw_task_ctx, 0, sizeof(struct e4_iscsi_task_context)); + memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); qedi_cmd->task_id = tid; @@ -1991,7 +1991,7 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task) struct iscsi_task_params task_params; struct iscsi_conn_params conn_params; struct scsi_initiator_cmd_params cmd_params; - struct e4_iscsi_task_context *fw_task_ctx; + struct iscsi_task_context *fw_task_ctx; struct iscsi_cls_conn *cls_conn; struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)task->hdr; enum iscsi_task_type task_type = MAX_ISCSI_TASK_TYPE; @@ -2014,9 +2014,9 @@ int qedi_iscsi_send_ioreq(struct iscsi_task *task) return -ENOMEM; fw_task_ctx = - (struct e4_iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, + (struct iscsi_task_context *)qedi_get_task_mem(&qedi->tasks, tid); - memset(fw_task_ctx, 0, sizeof(struct e4_iscsi_task_context)); + memset(fw_task_ctx, 0, sizeof(struct iscsi_task_context)); cmd->task_id = tid; diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c index 52772904ef5d..642556a1ce1c 100644 --- a/drivers/scsi/qedi/qedi_fw_api.c +++ b/drivers/scsi/qedi/qedi_fw_api.c @@ -202,7 +202,7 @@ static void init_default_iscsi_task(struct iscsi_task_params *task_params, struct data_hdr *pdu_header, enum iscsi_task_type task_type) { - struct e4_iscsi_task_context *context; + struct iscsi_task_context *context; u32 val; u16 index; u8 val_byte; @@ -224,7 +224,7 @@ static void init_default_iscsi_task(struct iscsi_task_params *task_params, cpu_to_le16(task_params->conn_icid); SET_FIELD(context->ustorm_ag_context.flags1, - E4_USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); + USTORM_ISCSI_TASK_AG_CTX_R2T2RECV, 1); context->ustorm_st_context.task_type = task_type; context->ustorm_st_context.cq_rss_number = task_params->cq_rss_number; @@ -254,7 +254,7 @@ void init_initiator_rw_cdb_ystorm_context(struct ystorm_iscsi_task_st_ctx *ystc, static void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt, - struct e4_ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt, + struct ustorm_iscsi_task_ag_ctx *ustorm_ag_cxt, u32 remaining_recv_len, u32 expected_data_transfer_len, u8 num_sges, bool tx_dif_conn_err_en) { @@ -266,12 +266,12 @@ void init_ustorm_task_contexts(struct ustorm_iscsi_task_st_ctx *ustorm_st_cxt, ustorm_st_cxt->exp_data_transfer_len = val; SET_FIELD(ustorm_st_cxt->reg1.reg1_map, ISCSI_REG1_NUM_SGES, num_sges); SET_FIELD(ustorm_ag_cxt->flags2, - E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN, + USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN, tx_dif_conn_err_en ? 1 : 0); } static -void set_rw_exp_data_acked_and_cont_len(struct e4_iscsi_task_context *context, +void set_rw_exp_data_acked_and_cont_len(struct iscsi_task_context *context, struct iscsi_conn_params *conn_params, enum iscsi_task_type task_type, u32 task_size, @@ -470,7 +470,7 @@ void init_rtdif_task_context(struct rdif_task_context *rdif_context, } } -static void set_local_completion_context(struct e4_iscsi_task_context *context) +static void set_local_completion_context(struct iscsi_task_context *context) { SET_FIELD(context->ystorm_st_context.state.flags, YSTORM_ISCSI_TASK_STATE_LOCAL_COMP, 1); @@ -487,7 +487,7 @@ static int init_rw_iscsi_task(struct iscsi_task_params *task_params, struct scsi_dif_task_params *dif_task_params) { u32 exp_data_transfer_len = conn_params->max_burst_length; - struct e4_iscsi_task_context *cxt; + struct iscsi_task_context *cxt; bool slow_io = false; u32 task_size, val; u8 num_sges = 0; @@ -615,7 +615,7 @@ int init_initiator_login_request_task(struct iscsi_task_params *task_params, struct scsi_sgl_task_params *tx_params, struct scsi_sgl_task_params *rx_params) { - struct e4_iscsi_task_context *cxt; + struct iscsi_task_context *cxt; cxt = task_params->context; @@ -657,7 +657,7 @@ int init_initiator_nop_out_task(struct iscsi_task_params *task_params, struct scsi_sgl_task_params *tx_sgl_task_params, struct scsi_sgl_task_params *rx_sgl_task_params) { - struct e4_iscsi_task_context *cxt; + struct iscsi_task_context *cxt; cxt = task_params->context; @@ -703,7 +703,7 @@ int init_initiator_logout_request_task(struct iscsi_task_params *task_params, struct scsi_sgl_task_params *tx_params, struct scsi_sgl_task_params *rx_params) { - struct e4_iscsi_task_context *cxt; + struct iscsi_task_context *cxt; cxt = task_params->context; @@ -758,7 +758,7 @@ int init_initiator_text_request_task(struct iscsi_task_params *task_params, struct scsi_sgl_task_params *tx_params, struct scsi_sgl_task_params *rx_params) { - struct e4_iscsi_task_context *cxt; + struct iscsi_task_context *cxt; cxt = task_params->context; diff --git a/drivers/scsi/qedi/qedi_fw_iscsi.h b/drivers/scsi/qedi/qedi_fw_iscsi.h index 10f19f0af0a3..df2d471a7b51 100644 --- a/drivers/scsi/qedi/qedi_fw_iscsi.h +++ b/drivers/scsi/qedi/qedi_fw_iscsi.h @@ -10,7 +10,7 @@ #include "qedi_fw_scsi.h" struct iscsi_task_params { - struct e4_iscsi_task_context *context; + struct iscsi_task_context *context; struct iscsi_wqe *sqe; u32 tx_io_size; u32 rx_io_size; diff --git a/drivers/scsi/qedi/qedi_iscsi.h b/drivers/scsi/qedi/qedi_iscsi.h index a31c5de74754..a282860da0aa 100644 --- a/drivers/scsi/qedi/qedi_iscsi.h +++ b/drivers/scsi/qedi/qedi_iscsi.h @@ -182,7 +182,7 @@ struct qedi_cmd { struct scsi_cmnd *scsi_cmd; struct scatterlist *sg; struct qedi_io_bdt io_tbl; - struct e4_iscsi_task_context request; + struct iscsi_task_context request; unsigned char *sense_buffer; dma_addr_t sense_buffer_dma; u16 task_id; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index e6dc0b495a82..fe36ddb82aef 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -351,12 +351,12 @@ static int qedi_init_uio(struct qedi_ctx *qedi) static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi, struct qed_sb_info *sb_info, u16 sb_id) { - struct status_block_e4 *sb_virt; + struct status_block *sb_virt; dma_addr_t sb_phys; int ret; sb_virt = dma_alloc_coherent(&qedi->pdev->dev, - sizeof(struct status_block_e4), &sb_phys, + sizeof(struct status_block), &sb_phys, GFP_KERNEL); if (!sb_virt) { QEDI_ERR(&qedi->dbg_ctx, @@ -1259,7 +1259,7 @@ static bool qedi_process_completions(struct qedi_fastpath *fp) { struct qedi_ctx *qedi = fp->qedi; struct qed_sb_info *sb_info = fp->sb_info; - struct status_block_e4 *sb = sb_info->sb_virt; + struct status_block *sb = sb_info->sb_virt; struct qedi_percpu_s *p = NULL; struct global_queue *que; u16 prod_idx; @@ -1315,7 +1315,7 @@ static bool qedi_fp_has_work(struct qedi_fastpath *fp) struct qedi_ctx *qedi = fp->qedi; struct global_queue *que; struct qed_sb_info *sb_info = fp->sb_info; - struct status_block_e4 *sb = sb_info->sb_virt; + struct status_block *sb = sb_info->sb_virt; u16 prod_idx; barrier(); diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 0a3807e927c5..3742d1f7d1f7 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -133,7 +133,7 @@ #define NUM_OF_TCS (NUM_OF_PHYS_TCS + 1) /* CIDs */ -#define NUM_OF_CONNECTION_TYPES_E4 (8) +#define NUM_OF_CONNECTION_TYPES (8) #define NUM_OF_LCIDS (320) #define NUM_OF_LTIDS (320) @@ -379,7 +379,7 @@ #define CAU_FSM_ETH_TX 1 /* Number of Protocol Indices per Status Block */ -#define PIS_PER_SB_E4 12 +#define PIS_PER_SB 12 #define MAX_PIS_PER_SB PIS_PER_SB #define CAU_HC_STOPPED_STATE 3 @@ -1221,20 +1221,20 @@ struct rdif_task_context { }; /* Status block structure */ -struct status_block_e4 { - __le16 pi_array[PIS_PER_SB_E4]; +struct status_block { + __le16 pi_array[PIS_PER_SB]; __le32 sb_num; -#define STATUS_BLOCK_E4_SB_NUM_MASK 0x1FF -#define STATUS_BLOCK_E4_SB_NUM_SHIFT 0 -#define STATUS_BLOCK_E4_ZERO_PAD_MASK 0x7F -#define STATUS_BLOCK_E4_ZERO_PAD_SHIFT 9 -#define STATUS_BLOCK_E4_ZERO_PAD2_MASK 0xFFFF -#define STATUS_BLOCK_E4_ZERO_PAD2_SHIFT 16 +#define STATUS_BLOCK_SB_NUM_MASK 0x1FF +#define STATUS_BLOCK_SB_NUM_SHIFT 0 +#define STATUS_BLOCK_ZERO_PAD_MASK 0x7F +#define STATUS_BLOCK_ZERO_PAD_SHIFT 9 +#define STATUS_BLOCK_ZERO_PAD2_MASK 0xFFFF +#define STATUS_BLOCK_ZERO_PAD2_SHIFT 16 __le32 prod_index; -#define STATUS_BLOCK_E4_PROD_INDEX_MASK 0xFFFFFF -#define STATUS_BLOCK_E4_PROD_INDEX_SHIFT 0 -#define STATUS_BLOCK_E4_ZERO_PAD3_MASK 0xFF -#define STATUS_BLOCK_E4_ZERO_PAD3_SHIFT 24 +#define STATUS_BLOCK_PROD_INDEX_MASK 0xFFFFFF +#define STATUS_BLOCK_PROD_INDEX_SHIFT 0 +#define STATUS_BLOCK_ZERO_PAD3_MASK 0xFF +#define STATUS_BLOCK_ZERO_PAD3_SHIFT 24 }; /* Tdif context */ diff --git a/include/linux/qed/fcoe_common.h b/include/linux/qed/fcoe_common.h index 68eda1c21cde..7ba0abc867f1 100644 --- a/include/linux/qed/fcoe_common.h +++ b/include/linux/qed/fcoe_common.h @@ -150,49 +150,49 @@ struct ystorm_fcoe_task_st_ctx { u8 reserved2[8]; }; -struct e4_ystorm_fcoe_task_ag_ctx { +struct ystorm_fcoe_task_ag_ctx { u8 byte0; u8 byte1; __le16 word0; u8 flags0; -#define E4_YSTORM_FCOE_TASK_AG_CTX_NIBBLE0_MASK 0xF -#define E4_YSTORM_FCOE_TASK_AG_CTX_NIBBLE0_SHIFT 0 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT0_SHIFT 4 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT2_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT2_SHIFT 6 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT3_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT3_SHIFT 7 +#define YSTORM_FCOE_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define YSTORM_FCOE_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define YSTORM_FCOE_TASK_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT0_SHIFT 4 +#define YSTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 +#define YSTORM_FCOE_TASK_AG_CTX_BIT2_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT2_SHIFT 6 +#define YSTORM_FCOE_TASK_AG_CTX_BIT3_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT3_SHIFT 7 u8 flags1; -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF0_SHIFT 0 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 2 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF0EN_SHIFT 6 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 7 +#define YSTORM_FCOE_TASK_AG_CTX_CF0_MASK 0x3 +#define YSTORM_FCOE_TASK_AG_CTX_CF0_SHIFT 0 +#define YSTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 +#define YSTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 2 +#define YSTORM_FCOE_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 +#define YSTORM_FCOE_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 +#define YSTORM_FCOE_TASK_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_CF0EN_SHIFT 6 +#define YSTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 7 u8 flags2; -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT4_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_BIT4_SHIFT 0 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 2 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 3 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 4 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 5 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 6 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_YSTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 7 +#define YSTORM_FCOE_TASK_AG_CTX_BIT4_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_BIT4_SHIFT 0 +#define YSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define YSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define YSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define YSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define YSTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define YSTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define YSTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 7 u8 byte2; __le32 reg0; u8 byte3; @@ -206,73 +206,73 @@ struct e4_ystorm_fcoe_task_ag_ctx { __le32 reg2; }; -struct e4_tstorm_fcoe_task_ag_ctx { +struct tstorm_fcoe_task_ag_ctx { u8 reserved; u8 byte1; __le16 icid; u8 flags0; -#define E4_TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_TSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_TSTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_TSTORM_FCOE_TASK_AG_CTX_WAIT_ABTS_RSP_F_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_WAIT_ABTS_RSP_F_SHIFT 6 -#define E4_TSTORM_FCOE_TASK_AG_CTX_VALID_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_VALID_SHIFT 7 +#define TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define TSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 +#define TSTORM_FCOE_TASK_AG_CTX_WAIT_ABTS_RSP_F_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_WAIT_ABTS_RSP_F_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_VALID_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_VALID_SHIFT 7 u8 flags1; -#define E4_TSTORM_FCOE_TASK_AG_CTX_FALSE_RR_TOV_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_FALSE_RR_TOV_SHIFT 0 -#define E4_TSTORM_FCOE_TASK_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_BIT5_SHIFT 1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_SHIFT 2 -#define E4_TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_SHIFT 4 -#define E4_TSTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_FALSE_RR_TOV_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_FALSE_RR_TOV_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_BIT5_SHIFT 1 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 6 u8 flags2; -#define E4_TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_SHIFT 0 -#define E4_TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_SHIFT 2 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_SHIFT 4 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_SHIFT 6 u8 flags3; -#define E4_TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_MASK 0x3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_SHIFT 0 -#define E4_TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_EN_SHIFT 2 -#define E4_TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_EN_SHIFT 3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 4 -#define E4_TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 5 -#define E4_TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_SHIFT 6 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_EN_SHIFT 7 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_MASK 0x3 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_REC_RR_TOV_CF_EN_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_ED_TOV_CF_EN_SHIFT 3 +#define TSTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 5 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_INIT_CF_EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_EN_SHIFT 0 -#define E4_TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_EN_SHIFT 1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 2 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 3 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 4 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 5 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 6 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 7 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_SEQ_RECOVERY_CF_EN_SHIFT 0 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_UNSOL_COMP_CF_EN_SHIFT 1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 2 +#define TSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 3 +#define TSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 4 +#define TSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 5 +#define TSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 6 +#define TSTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 7 u8 cleanup_state; __le16 last_sent_tid; __le32 rec_rr_tov_exp_timeout; @@ -352,49 +352,49 @@ struct tstorm_fcoe_task_st_ctx { struct fcoe_tstorm_fcoe_task_st_ctx_read_only read_only; }; -struct e4_mstorm_fcoe_task_ag_ctx { +struct mstorm_fcoe_task_ag_ctx { u8 byte0; u8 byte1; __le16 icid; u8 flags0; -#define E4_MSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_MSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_MSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CQE_PLACED_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CQE_PLACED_SHIFT 5 -#define E4_MSTORM_FCOE_TASK_AG_CTX_BIT2_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_BIT2_SHIFT 6 -#define E4_MSTORM_FCOE_TASK_AG_CTX_BIT3_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_BIT3_SHIFT 7 +#define MSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define MSTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define MSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define MSTORM_FCOE_TASK_AG_CTX_CQE_PLACED_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_CQE_PLACED_SHIFT 5 +#define MSTORM_FCOE_TASK_AG_CTX_BIT2_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_BIT2_SHIFT 6 +#define MSTORM_FCOE_TASK_AG_CTX_BIT3_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_BIT3_SHIFT 7 u8 flags1; -#define E4_MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_MASK 0x3 -#define E4_MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_SHIFT 0 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 2 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 4 -#define E4_MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_SHIFT 6 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 7 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_MASK 0x3 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_SHIFT 0 +#define MSTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 +#define MSTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 2 +#define MSTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 +#define MSTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 4 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_EX_CLEANUP_CF_EN_SHIFT 6 +#define MSTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 7 u8 flags2; -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 0 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 2 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 3 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 4 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 5 -#define E4_MSTORM_FCOE_TASK_AG_CTX_XFER_PLACEMENT_EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_XFER_PLACEMENT_EN_SHIFT 6 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_MSTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 7 +#define MSTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 0 +#define MSTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define MSTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define MSTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define MSTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define MSTORM_FCOE_TASK_AG_CTX_XFER_PLACEMENT_EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_XFER_PLACEMENT_EN_SHIFT 6 +#define MSTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define MSTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 7 u8 cleanup_state; __le32 received_bytes; u8 byte3; @@ -440,56 +440,56 @@ struct mstorm_fcoe_task_st_ctx { struct scsi_cached_sges data_desc; }; -struct e4_ustorm_fcoe_task_ag_ctx { +struct ustorm_fcoe_task_ag_ctx { u8 reserved; u8 byte1; __le16 icid; u8 flags0; -#define E4_USTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_USTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_USTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_USTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF0_SHIFT 6 +#define USTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define USTORM_FCOE_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_BIT1_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_BIT1_SHIFT 5 +#define USTORM_FCOE_TASK_AG_CTX_CF0_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF0_SHIFT 6 u8 flags1; -#define E4_USTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 0 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 2 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF3_SHIFT 4 -#define E4_USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 -#define E4_USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 +#define USTORM_FCOE_TASK_AG_CTX_CF1_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF1_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_CF2_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF2_SHIFT 2 +#define USTORM_FCOE_TASK_AG_CTX_CF3_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_CF3_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 u8 flags2; -#define E4_USTORM_FCOE_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF0EN_SHIFT 0 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 1 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 2 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 5 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 6 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 7 +#define USTORM_FCOE_TASK_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_FCOE_TASK_AG_CTX_CF2EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF2EN_SHIFT 2 +#define USTORM_FCOE_TASK_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE0EN_SHIFT 5 +#define USTORM_FCOE_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define USTORM_FCOE_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE2EN_SHIFT 7 u8 flags3; -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 0 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 2 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 3 -#define E4_USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF -#define E4_USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 +#define USTORM_FCOE_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE3EN_SHIFT 0 +#define USTORM_FCOE_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE4EN_SHIFT 1 +#define USTORM_FCOE_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE5EN_SHIFT 2 +#define USTORM_FCOE_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_FCOE_TASK_AG_CTX_RULE6EN_SHIFT 3 +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define USTORM_FCOE_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 __le32 dif_err_intervals; __le32 dif_error_1st_interval; __le32 global_cq_num; @@ -499,18 +499,18 @@ struct e4_ustorm_fcoe_task_ag_ctx { }; /* FCoE task context */ -struct e4_fcoe_task_context { +struct fcoe_task_context { struct ystorm_fcoe_task_st_ctx ystorm_st_context; struct regpair ystorm_st_padding[2]; struct tdif_task_context tdif_context; - struct e4_ystorm_fcoe_task_ag_ctx ystorm_ag_context; - struct e4_tstorm_fcoe_task_ag_ctx tstorm_ag_context; + struct ystorm_fcoe_task_ag_ctx ystorm_ag_context; + struct tstorm_fcoe_task_ag_ctx tstorm_ag_context; struct timers_context timer_context; struct tstorm_fcoe_task_st_ctx tstorm_st_context; struct regpair tstorm_st_padding[2]; - struct e4_mstorm_fcoe_task_ag_ctx mstorm_ag_context; + struct mstorm_fcoe_task_ag_ctx mstorm_ag_context; struct mstorm_fcoe_task_st_ctx mstorm_st_context; - struct e4_ustorm_fcoe_task_ag_ctx ustorm_ag_context; + struct ustorm_fcoe_task_ag_ctx ustorm_ag_context; struct rdif_task_context rdif_context; }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index 157019f716f1..1a60285a01e3 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -714,49 +714,49 @@ struct ystorm_iscsi_task_st_ctx { union iscsi_task_hdr pdu_hdr; }; -struct e4_ystorm_iscsi_task_ag_ctx { +struct ystorm_iscsi_task_ag_ctx { u8 reserved; u8 byte1; __le16 word0; u8 flags0; -#define E4_YSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_MASK 0xF -#define E4_YSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_SHIFT 0 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_BIT0_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_BIT0_SHIFT 4 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_TTT_VALID_MASK 0x1 /* bit3 */ -#define E4_YSTORM_ISCSI_TASK_AG_CTX_TTT_VALID_SHIFT 7 +#define YSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define YSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT0_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT0_SHIFT 4 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define YSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 +#define YSTORM_ISCSI_TASK_AG_CTX_TTT_VALID_MASK 0x1 /* bit3 */ +#define YSTORM_ISCSI_TASK_AG_CTX_TTT_VALID_SHIFT 7 u8 flags1; -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF0_SHIFT 0 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 2 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF0EN_SHIFT 6 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 7 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0_MASK 0x3 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0_SHIFT 0 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 2 +#define YSTORM_ISCSI_TASK_AG_CTX_CF2SPECIAL_MASK 0x3 +#define YSTORM_ISCSI_TASK_AG_CTX_CF2SPECIAL_SHIFT 4 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_CF0EN_SHIFT 6 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 7 u8 flags2; -#define E4_YSTORM_ISCSI_TASK_AG_CTX_BIT4_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_BIT4_SHIFT 0 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 2 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 3 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 4 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 5 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 6 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_YSTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 7 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT4_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_BIT4_SHIFT 0 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define YSTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 7 u8 byte2; __le32 TTT; u8 byte3; @@ -764,49 +764,49 @@ struct e4_ystorm_iscsi_task_ag_ctx { __le16 word1; }; -struct e4_mstorm_iscsi_task_ag_ctx { +struct mstorm_iscsi_task_ag_ctx { u8 cdu_validation; u8 byte1; __le16 task_cid; u8 flags0; -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 +#define MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define MSTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define MSTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define MSTORM_ISCSI_TASK_AG_CTX_VALID_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_VALID_SHIFT 6 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_FLAG_SHIFT 7 u8 flags1; -#define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 2 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF2_SHIFT 4 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 7 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_MASK 0x3 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_SHIFT 0 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 2 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2_MASK 0x3 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2_SHIFT 4 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_TASK_CLEANUP_CF_EN_SHIFT 6 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 7 u8 flags2; -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_CF2EN_SHIFT 0 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 2 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 3 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 4 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 5 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 6 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_MSTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 7 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_CF2EN_SHIFT 0 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 2 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 3 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 4 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 5 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 6 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define MSTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 7 u8 byte2; __le32 reg0; u8 byte3; @@ -814,56 +814,56 @@ struct e4_mstorm_iscsi_task_ag_ctx { __le16 word1; }; -struct e4_ustorm_iscsi_task_ag_ctx { +struct ustorm_iscsi_task_ag_ctx { u8 reserved; u8 state; __le16 icid; u8 flags0; -#define E4_USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF -#define E4_USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 -#define E4_USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 -#define E4_USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 +#define USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_MASK 0xF +#define USTORM_ISCSI_TASK_AG_CTX_CONNECTION_TYPE_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_EXIST_IN_QM0_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CONN_CLEAR_SQ_FLAG_SHIFT 5 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_SHIFT 6 u8 flags1; -#define E4_USTORM_ISCSI_TASK_AG_CTX_RESERVED1_MASK 0x3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RESERVED1_SHIFT 0 -#define E4_USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_MASK 0x3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_SHIFT 2 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CF3_MASK 0x3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CF3_SHIFT 4 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 +#define USTORM_ISCSI_TASK_AG_CTX_RESERVED1_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_RESERVED1_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_SHIFT 2 +#define USTORM_ISCSI_TASK_AG_CTX_CF3_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_CF3_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_MASK 0x3 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_SHIFT 6 u8 flags2; -#define E4_USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CF3EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CF3EN_SHIFT 3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 6 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_HQ_SCANNED_CF_EN_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_DISABLE_DATA_ACKED_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_DISABLE_DATA_ACKED_SHIFT 1 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_R2T2RECV_EN_SHIFT 2 +#define USTORM_ISCSI_TASK_AG_CTX_CF3EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CF3EN_SHIFT 3 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_CF_EN_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_DATA_TOTAL_EXP_EN_SHIFT 5 +#define USTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 6 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 u8 flags3; -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 0 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 2 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 -#define E4_USTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 3 -#define E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF -#define E4_USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 +#define USTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 0 +#define USTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 2 +#define USTORM_ISCSI_TASK_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_ISCSI_TASK_AG_CTX_RULE6EN_SHIFT 3 +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF +#define USTORM_ISCSI_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 __le32 dif_err_intervals; __le32 dif_error_1st_interval; __le32 rcv_cont_len; @@ -952,14 +952,14 @@ struct ustorm_iscsi_task_st_ctx { }; /* iscsi task context */ -struct e4_iscsi_task_context { +struct iscsi_task_context { struct ystorm_iscsi_task_st_ctx ystorm_st_context; - struct e4_ystorm_iscsi_task_ag_ctx ystorm_ag_context; + struct ystorm_iscsi_task_ag_ctx ystorm_ag_context; struct regpair ystorm_ag_padding[2]; struct tdif_task_context tdif_context; - struct e4_mstorm_iscsi_task_ag_ctx mstorm_ag_context; + struct mstorm_iscsi_task_ag_ctx mstorm_ag_context; struct regpair mstorm_ag_padding[2]; - struct e4_ustorm_iscsi_task_ag_ctx ustorm_ag_context; + struct ustorm_iscsi_task_ag_ctx ustorm_ag_context; struct mstorm_iscsi_task_st_ctx mstorm_st_context; struct ustorm_iscsi_task_st_ctx ustorm_st_context; struct rdif_task_context rdif_context; @@ -1431,73 +1431,73 @@ struct ystorm_iscsi_stats_drv { struct regpair iscsi_tx_tcp_pkt_cnt; }; -struct e4_tstorm_iscsi_task_ag_ctx { +struct tstorm_iscsi_task_ag_ctx { u8 byte0; u8 byte1; __le16 word0; u8 flags0; -#define E4_TSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_MASK 0xF -#define E4_TSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_SHIFT 0 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT0_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT0_SHIFT 4 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT2_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT2_SHIFT 6 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT3_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT3_SHIFT 7 +#define TSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_MASK 0xF +#define TSTORM_ISCSI_TASK_AG_CTX_NIBBLE0_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT0_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT0_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT1_SHIFT 5 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT2_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT3_SHIFT 7 u8 flags1; -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT4_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT4_SHIFT 0 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT5_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_BIT5_SHIFT 1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF0_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF0_SHIFT 2 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 4 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF2_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF2_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT4_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_BIT5_SHIFT 1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2_SHIFT 6 u8 flags2; -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF3_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF3_SHIFT 0 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF4_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF4_SHIFT 2 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF5_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF5_SHIFT 4 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF6_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF6_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6_SHIFT 6 u8 flags3; -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF7_MASK 0x3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF7_SHIFT 0 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF0EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF0EN_SHIFT 2 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF2EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF2EN_SHIFT 4 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF3EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF3EN_SHIFT 5 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF4EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF4EN_SHIFT 6 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF5EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF5EN_SHIFT 7 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7_MASK 0x3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF0EN_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF1EN_SHIFT 3 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF2EN_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF3EN_SHIFT 5 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF4EN_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF5EN_SHIFT 7 u8 flags4; -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF6EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF6EN_SHIFT 0 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF7EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_CF7EN_SHIFT 1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 2 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 3 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 4 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 5 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 6 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 -#define E4_TSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 7 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF6EN_SHIFT 0 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_CF7EN_SHIFT 1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE0EN_SHIFT 2 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE1EN_SHIFT 3 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE2EN_SHIFT 4 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE3EN_SHIFT 5 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE4EN_SHIFT 6 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_ISCSI_TASK_AG_CTX_RULE5EN_SHIFT 7 u8 byte2; __le16 word1; __le32 reg0; diff --git a/include/linux/qed/nvmetcp_common.h b/include/linux/qed/nvmetcp_common.h index 5a2ab0606308..cc7c7481a0e0 100644 --- a/include/linux/qed/nvmetcp_common.h +++ b/include/linux/qed/nvmetcp_common.h @@ -410,7 +410,7 @@ struct e5_ystorm_nvmetcp_task_ag_ctx { u8 byte2; u8 byte3; u8 byte4; - u8 e4_reserved7; + u8 reserved7; }; struct e5_mstorm_nvmetcp_task_ag_ctx { @@ -445,7 +445,7 @@ struct e5_mstorm_nvmetcp_task_ag_ctx { u8 byte2; u8 byte3; u8 byte4; - u8 e4_reserved7; + u8 reserved7; }; struct e5_ustorm_nvmetcp_task_ag_ctx { @@ -489,17 +489,17 @@ struct e5_ustorm_nvmetcp_task_ag_ctx { #define E5_USTORM_NVMETCP_TASK_AG_CTX_CMP_CONT_RCV_EXP_EN_SHIFT 7 u8 flags3; u8 flags4; -#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_MASK 0x3 -#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED5_SHIFT 0 -#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_MASK 0x1 -#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED6_SHIFT 2 -#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_MASK 0x1 -#define E5_USTORM_NVMETCP_TASK_AG_CTX_E4_RESERVED7_SHIFT 3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED5_MASK 0x3 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED5_SHIFT 0 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED6_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED6_SHIFT 2 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED7_MASK 0x1 +#define E5_USTORM_NVMETCP_TASK_AG_CTX_RESERVED7_SHIFT 3 #define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_MASK 0xF #define E5_USTORM_NVMETCP_TASK_AG_CTX_DIF_ERROR_TYPE_SHIFT 4 u8 byte2; u8 byte3; - u8 e4_reserved8; + u8 reserved8; __le32 dif_err_intervals; __le32 dif_error_1st_interval; __le32 rcv_cont_len; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f39451aaaeec..4dcd0d37a521 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -588,7 +588,7 @@ enum qed_int_mode { }; struct qed_sb_info { - struct status_block_e4 *sb_virt; + struct status_block *sb_virt; dma_addr_t sb_phys; u32 sb_ack; /* Last given ack */ u16 igu_sb_id; @@ -613,7 +613,6 @@ enum qed_hw_err_type { enum qed_dev_type { QED_DEV_TYPE_BB, QED_DEV_TYPE_AH, - QED_DEV_TYPE_E5, }; struct qed_dev_info { @@ -1411,7 +1410,7 @@ static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) u16 rc = 0; prod = le32_to_cpu(sb_info->sb_virt->prod_index) & - STATUS_BLOCK_E4_PROD_INDEX_MASK; + STATUS_BLOCK_PROD_INDEX_MASK; if (sb_info->sb_ack != prod) { sb_info->sb_ack = prod; rc |= QED_SB_IDX; -- cgit v1.2.3 From 484563e230a8c68ab342080b41b5a5e2ce9621ef Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Mon, 4 Oct 2021 09:58:42 +0300 Subject: qed: Update common_hsi for FW ver 8.59.1.0 The common_hsi.h has been updated for FW version 8.59.1.0 with below changes. - FW and Tools version. - New structures related to search table, packet duplication. - Structure for doorbell address for legacy mode without DEM. - Enhanced union rdma_eqe_data for RoCE Suspend Event Data. - New defines. This patch also fixes the existing checkpatch warnings and few important checks. Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: Omkar Kulkarni Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 2 +- include/linux/qed/common_hsi.h | 113 +++++++++++++++++++++++++++--- 2 files changed, 106 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 987b086811b7..68eaef8ab6e8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -1093,7 +1093,7 @@ enum malicious_vf_error_id { /* Mstorm non-triggering VF zone */ struct mstorm_non_trigger_vf_zone { struct eth_mstorm_per_queue_stat eth_queue_stat; - struct eth_rx_prod_data eth_rx_queue_producers[ETH_MAX_NUM_RX_QUEUES_PER_VF_QUAD]; + struct eth_rx_prod_data eth_rx_queue_producers[ETH_MAX_RXQ_VF_QUAD]; }; /* Mstorm VF zone */ diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 3742d1f7d1f7..827624840ee2 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2016 QLogic Corporation - * Copyright (c) 2019-2020 Marvell International Ltd. + * Copyright (c) 2019-2021 Marvell International Ltd. */ #ifndef _COMMON_HSI_H @@ -47,10 +47,10 @@ #define ISCSI_CDU_TASK_SEG_TYPE 0 #define FCOE_CDU_TASK_SEG_TYPE 0 #define RDMA_CDU_TASK_SEG_TYPE 1 +#define ETH_CDU_TASK_SEG_TYPE 2 #define FW_ASSERT_GENERAL_ATTN_IDX 32 - /* Queue Zone sizes in bytes */ #define TSTORM_QZONE_SIZE 8 #define MSTORM_QZONE_SIZE 16 @@ -60,9 +60,12 @@ #define PSTORM_QZONE_SIZE 0 #define MSTORM_VF_ZONE_DEFAULT_SIZE_LOG 7 -#define ETH_MAX_NUM_RX_QUEUES_PER_VF_DEFAULT 16 -#define ETH_MAX_NUM_RX_QUEUES_PER_VF_DOUBLE 48 -#define ETH_MAX_NUM_RX_QUEUES_PER_VF_QUAD 112 +#define ETH_MAX_RXQ_VF_DEFAULT 16 +#define ETH_MAX_RXQ_VF_DOUBLE 48 +#define ETH_MAX_RXQ_VF_QUAD 112 + +#define ETH_RGSRC_CTX_SIZE 6 +#define ETH_TGSRC_CTX_SIZE 6 /********************************/ /* CORE (LIGHT L2) FW CONSTANTS */ @@ -89,8 +92,8 @@ #define MAX_NUM_LL2_TX_STATS_COUNTERS 48 #define FW_MAJOR_VERSION 8 -#define FW_MINOR_VERSION 42 -#define FW_REVISION_VERSION 2 +#define FW_MINOR_VERSION 59 +#define FW_REVISION_VERSION 1 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -112,6 +115,7 @@ #define MAX_NUM_VFS (MAX_NUM_VFS_K2) #define MAX_NUM_FUNCTIONS_BB (MAX_NUM_PFS_BB + MAX_NUM_VFS_BB) +#define MAX_NUM_FUNCTIONS_K2 (MAX_NUM_PFS_K2 + MAX_NUM_VFS_K2) #define MAX_FUNCTION_NUMBER_BB (MAX_NUM_PFS + MAX_NUM_VFS_BB) #define MAX_FUNCTION_NUMBER_K2 (MAX_NUM_PFS + MAX_NUM_VFS_K2) @@ -144,7 +148,7 @@ #define GTT_DWORD_SIZE BIT(GTT_DWORD_SIZE_BITS) /* Tools Version */ -#define TOOLS_VERSION 10 +#define TOOLS_VERSION 11 /*****************/ /* CDU CONSTANTS */ @@ -162,6 +166,7 @@ #define CDU_CONTEXT_VALIDATION_CFG_USE_REGION (3) #define CDU_CONTEXT_VALIDATION_CFG_USE_CID (4) #define CDU_CONTEXT_VALIDATION_CFG_USE_ACTIVE (5) +#define CDU_CONTEXT_VALIDATION_DEFAULT_CFG (0x3d) /*****************/ /* DQ CONSTANTS */ @@ -302,6 +307,9 @@ /* PWM address mapping */ #define DQ_PWM_OFFSET_DPM_BASE 0x0 #define DQ_PWM_OFFSET_DPM_END 0x27 +#define DQ_PWM_OFFSET_XCM32_24ICID_BASE 0x28 +#define DQ_PWM_OFFSET_UCM32_24ICID_BASE 0x30 +#define DQ_PWM_OFFSET_TCM32_24ICID_BASE 0x38 #define DQ_PWM_OFFSET_XCM16_BASE 0x40 #define DQ_PWM_OFFSET_XCM32_BASE 0x44 #define DQ_PWM_OFFSET_UCM16_BASE 0x48 @@ -325,6 +333,13 @@ #define DQ_PWM_OFFSET_TCM_LL2_PROD_UPDATE \ (DQ_PWM_OFFSET_TCM32_BASE + DQ_TCM_AGG_VAL_SEL_REG9 - 4) +#define DQ_PWM_OFFSET_XCM_RDMA_24B_ICID_SQ_PROD \ + (DQ_PWM_OFFSET_XCM32_24ICID_BASE + 2) +#define DQ_PWM_OFFSET_UCM_RDMA_24B_ICID_CQ_CONS_32BIT \ + (DQ_PWM_OFFSET_UCM32_24ICID_BASE + 4) +#define DQ_PWM_OFFSET_TCM_ROCE_24B_ICID_RQ_PROD \ + (DQ_PWM_OFFSET_TCM32_24ICID_BASE + 1) + #define DQ_REGION_SHIFT (12) /* DPM */ @@ -360,6 +375,7 @@ /* Number of global Vport/QCN rate limiters */ #define MAX_QM_GLOBAL_RLS 256 +#define COMMON_MAX_QM_GLOBAL_RLS MAX_QM_GLOBAL_RLS /* QM registers data */ #define QM_LINE_CRD_REG_WIDTH 16 @@ -700,6 +716,13 @@ enum mf_mode { MAX_MF_MODE }; +/* Per protocol packet duplication enable bit vector. If set, duplicate + * offloaded traffic to LL2 debug queueu. + */ +struct offload_pkt_dup_enable { + __le16 enable_vector; +}; + /* Per-protocol connection types */ enum protocol_type { PROTOCOLID_TCP_ULP, @@ -717,6 +740,12 @@ enum protocol_type { MAX_PROTOCOL_TYPE }; +/* Pstorm packet duplication config */ +struct pstorm_pkt_dup_cfg { + struct offload_pkt_dup_enable enable; + __le16 reserved[3]; +}; + struct regpair { __le32 lo; __le32 hi; @@ -728,10 +757,24 @@ struct rdma_eqe_destroy_qp { u8 reserved[4]; }; +/* RoCE Suspend Event Data */ +struct rdma_eqe_suspend_qp { + __le32 cid; + u8 reserved[4]; +}; + /* RDMA Event Data Union */ union rdma_eqe_data { struct regpair async_handle; struct rdma_eqe_destroy_qp rdma_destroy_qp_data; + struct rdma_eqe_suspend_qp rdma_suspend_qp_data; +}; + +/* Tstorm packet duplication config */ +struct tstorm_pkt_dup_cfg { + struct offload_pkt_dup_enable enable; + __le16 reserved; + __le32 cid; }; struct tstorm_queue_zone { @@ -891,6 +934,15 @@ struct db_legacy_addr { #define DB_LEGACY_ADDR_ICID_SHIFT 5 }; +/* Structure for doorbell address, in legacy mode, without DEMS */ +struct db_legacy_wo_dems_addr { + __le32 addr; +#define DB_LEGACY_WO_DEMS_ADDR_RESERVED0_MASK 0x3 +#define DB_LEGACY_WO_DEMS_ADDR_RESERVED0_SHIFT 0 +#define DB_LEGACY_WO_DEMS_ADDR_ICID_MASK 0x3FFFFFFF +#define DB_LEGACY_WO_DEMS_ADDR_ICID_SHIFT 2 +}; + /* Structure for doorbell address, in PWM mode */ struct db_pwm_addr { __le32 addr; @@ -906,6 +958,31 @@ struct db_pwm_addr { #define DB_PWM_ADDR_RESERVED1_SHIFT 28 }; +/* Parameters to RDMA firmware, passed in EDPM doorbell */ +struct db_rdma_24b_icid_dpm_params { + __le32 params; +#define DB_RDMA_24B_ICID_DPM_PARAMS_SIZE_MASK 0x3F +#define DB_RDMA_24B_ICID_DPM_PARAMS_SIZE_SHIFT 0 +#define DB_RDMA_24B_ICID_DPM_PARAMS_DPM_TYPE_MASK 0x3 +#define DB_RDMA_24B_ICID_DPM_PARAMS_DPM_TYPE_SHIFT 6 +#define DB_RDMA_24B_ICID_DPM_PARAMS_OPCODE_MASK 0xFF +#define DB_RDMA_24B_ICID_DPM_PARAMS_OPCODE_SHIFT 8 +#define DB_RDMA_24B_ICID_DPM_PARAMS_ICID_EXT_MASK 0xFF +#define DB_RDMA_24B_ICID_DPM_PARAMS_ICID_EXT_SHIFT 16 +#define DB_RDMA_24B_ICID_DPM_PARAMS_INV_BYTE_CNT_MASK 0x7 +#define DB_RDMA_24B_ICID_DPM_PARAMS_INV_BYTE_CNT_SHIFT 24 +#define DB_RDMA_24B_ICID_DPM_PARAMS_EXT_ICID_MODE_EN_MASK 0x1 +#define DB_RDMA_24B_ICID_DPM_PARAMS_EXT_ICID_MODE_EN_SHIFT 27 +#define DB_RDMA_24B_ICID_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_24B_ICID_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_24B_ICID_DPM_PARAMS_S_FLG_MASK 0x1 +#define DB_RDMA_24B_ICID_DPM_PARAMS_S_FLG_SHIFT 29 +#define DB_RDMA_24B_ICID_DPM_PARAMS_RESERVED1_MASK 0x1 +#define DB_RDMA_24B_ICID_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_24B_ICID_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 +#define DB_RDMA_24B_ICID_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 +}; + /* Parameters to RDMA firmware, passed in EDPM doorbell */ struct db_rdma_dpm_params { __le32 params; @@ -1220,6 +1297,26 @@ struct rdif_task_context { __le32 reserved2; }; +/* Searcher Table struct */ +struct src_entry_header { + __le32 flags; +#define SRC_ENTRY_HEADER_NEXT_PTR_TYPE_MASK 0x1 +#define SRC_ENTRY_HEADER_NEXT_PTR_TYPE_SHIFT 0 +#define SRC_ENTRY_HEADER_EMPTY_MASK 0x1 +#define SRC_ENTRY_HEADER_EMPTY_SHIFT 1 +#define SRC_ENTRY_HEADER_RESERVED_MASK 0x3FFFFFFF +#define SRC_ENTRY_HEADER_RESERVED_SHIFT 2 + __le32 magic_number; + struct regpair next_ptr; +}; + +/* Enumeration for address type */ +enum src_header_next_ptr_type_enum { + e_physical_addr, + e_logical_addr, + MAX_SRC_HEADER_NEXT_PTR_TYPE_ENUM +}; + /* Status block structure */ struct status_block { __le16 pi_array[PIS_PER_SB]; -- cgit v1.2.3 From fe40a830dcded26f012739fd6dac0da9c805bc38 Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Mon, 4 Oct 2021 09:58:44 +0300 Subject: qed: Update qed_hsi.h for fw 8.59.1.0 The qed_hsi.h has been updated to support new FW version 8.59.1.0 with changes. - Updates FW HSI (Hardware Software interface) structures. - Addition/update in function declaration and defines as per HSI. - Add generic infrastructure for FW error reporting as part of common event queue handling. - Move malicious VF error reporting to FW error reporting infrastructure. - Move consolidation queue initialization from FW context to ramrod message. qed_hsi.h header file changes lead to change in many files to ensure compilation. This patch also fixes the existing checkpatch warnings and few important checks. Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: Omkar Kulkarni Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dev.c | 112 +- drivers/net/ethernet/qlogic/qed/qed_hsi.h | 1556 +++++++++++++++++--- .../net/ethernet/qlogic/qed/qed_init_fw_funcs.c | 14 +- drivers/net/ethernet/qlogic/qed/qed_l2.c | 6 +- drivers/net/ethernet/qlogic/qed/qed_l2.h | 1 - drivers/net/ethernet/qlogic/qed/qed_sp.h | 8 +- drivers/net/ethernet/qlogic/qed/qed_sp_commands.c | 10 +- drivers/net/ethernet/qlogic/qed/qed_spq.c | 50 +- drivers/net/ethernet/qlogic/qed/qed_sriov.c | 112 +- drivers/net/ethernet/qlogic/qed/qed_sriov.h | 27 +- include/linux/qed/eth_common.h | 1 + include/linux/qed/rdma_common.h | 1 + 12 files changed, 1590 insertions(+), 308 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 3db1a5512b9b..dad5cd219b0e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1397,12 +1397,13 @@ void qed_resc_free(struct qed_dev *cdev) qed_rdma_info_free(p_hwfn); } + qed_spq_unregister_async_cb(p_hwfn, PROTOCOLID_COMMON); qed_iov_free(p_hwfn); qed_l2_free(p_hwfn); qed_dmae_info_free(p_hwfn); qed_dcbx_info_free(p_hwfn); qed_dbg_user_data_free(p_hwfn); - qed_fw_overlay_mem_free(p_hwfn, p_hwfn->fw_overlay_mem); + qed_fw_overlay_mem_free(p_hwfn, &p_hwfn->fw_overlay_mem); /* Destroy doorbell recovery mechanism */ qed_db_recovery_teardown(p_hwfn); @@ -1484,8 +1485,8 @@ static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn) u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn); /* num RLs can't exceed resource amount of rls or vports */ - num_pf_rls = (u16) min_t(u32, RESC_NUM(p_hwfn, QED_RL), - RESC_NUM(p_hwfn, QED_VPORT)); + num_pf_rls = (u16)min_t(u32, RESC_NUM(p_hwfn, QED_RL), + RESC_NUM(p_hwfn, QED_VPORT)); /* Make sure after we reserve there's something left */ if (num_pf_rls < num_vfs + NUM_DEFAULT_RLS) @@ -1533,8 +1534,8 @@ static void qed_init_qm_params(struct qed_hwfn *p_hwfn) bool four_port; /* pq and vport bases for this PF */ - qm_info->start_pq = (u16) RESC_START(p_hwfn, QED_PQ); - qm_info->start_vport = (u8) RESC_START(p_hwfn, QED_VPORT); + qm_info->start_pq = (u16)RESC_START(p_hwfn, QED_PQ); + qm_info->start_vport = (u8)RESC_START(p_hwfn, QED_VPORT); /* rate limiting and weighted fair queueing are always enabled */ qm_info->vport_rl_en = true; @@ -1629,9 +1630,9 @@ static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn) */ /* flags for pq init */ -#define PQ_INIT_SHARE_VPORT (1 << 0) -#define PQ_INIT_PF_RL (1 << 1) -#define PQ_INIT_VF_RL (1 << 2) +#define PQ_INIT_SHARE_VPORT BIT(0) +#define PQ_INIT_PF_RL BIT(1) +#define PQ_INIT_VF_RL BIT(2) /* defines for pq init */ #define PQ_INIT_DEFAULT_WRR_GROUP 1 @@ -2291,7 +2292,7 @@ int qed_resc_alloc(struct qed_dev *cdev) goto alloc_no_mem; } - rc = qed_eq_alloc(p_hwfn, (u16) n_eqes); + rc = qed_eq_alloc(p_hwfn, (u16)n_eqes); if (rc) goto alloc_err; @@ -2376,6 +2377,49 @@ alloc_err: return rc; } +static int qed_fw_err_handler(struct qed_hwfn *p_hwfn, + u8 opcode, + u16 echo, + union event_ring_data *data, u8 fw_return_code) +{ + if (fw_return_code != COMMON_ERR_CODE_ERROR) + goto eqe_unexpected; + + if (data->err_data.recovery_scope == ERR_SCOPE_FUNC && + le16_to_cpu(data->err_data.entity_id) >= MAX_NUM_PFS) { + qed_sriov_vfpf_malicious(p_hwfn, &data->err_data); + return 0; + } + +eqe_unexpected: + DP_ERR(p_hwfn, + "Skipping unexpected eqe 0x%02x, FW return code 0x%x, echo 0x%x\n", + opcode, fw_return_code, echo); + return -EINVAL; +} + +static int qed_common_eqe_event(struct qed_hwfn *p_hwfn, + u8 opcode, + __le16 echo, + union event_ring_data *data, + u8 fw_return_code) +{ + switch (opcode) { + case COMMON_EVENT_VF_PF_CHANNEL: + case COMMON_EVENT_VF_FLR: + return qed_sriov_eqe_event(p_hwfn, opcode, echo, data, + fw_return_code); + case COMMON_EVENT_FW_ERROR: + return qed_fw_err_handler(p_hwfn, opcode, + le16_to_cpu(echo), data, + fw_return_code); + default: + DP_INFO(p_hwfn->cdev, "Unknown eqe event 0x%02x, echo 0x%x\n", + opcode, echo); + return -EINVAL; + } +} + void qed_resc_setup(struct qed_dev *cdev) { int i; @@ -2404,6 +2448,8 @@ void qed_resc_setup(struct qed_dev *cdev) qed_l2_setup(p_hwfn); qed_iov_setup(p_hwfn); + qed_spq_register_async_cb(p_hwfn, PROTOCOLID_COMMON, + qed_common_eqe_event); #ifdef CONFIG_QED_LL2 if (p_hwfn->using_ll2) qed_ll2_setup(p_hwfn); @@ -2593,7 +2639,7 @@ static void qed_init_cache_line_size(struct qed_hwfn *p_hwfn, cache_line_size); } - if (L1_CACHE_BYTES > wr_mbs) + if (wr_mbs < L1_CACHE_BYTES) DP_INFO(p_hwfn, "The cache line size for padding is suboptimal for performance [OS cache line size 0x%x, wr mbs 0x%x]\n", L1_CACHE_BYTES, wr_mbs); @@ -2609,13 +2655,21 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, int hw_mode) { struct qed_qm_info *qm_info = &p_hwfn->qm_info; - struct qed_qm_common_rt_init_params params; + struct qed_qm_common_rt_init_params *params; struct qed_dev *cdev = p_hwfn->cdev; u8 vf_id, max_num_vfs; u16 num_pfs, pf_id; u32 concrete_fid; int rc = 0; + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) { + DP_NOTICE(p_hwfn->cdev, + "Failed to allocate common init params\n"); + + return -ENOMEM; + } + qed_init_cau_rt_data(cdev); /* Program GTT windows */ @@ -2628,16 +2682,15 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, qm_info->pf_wfq_en = true; } - memset(¶ms, 0, sizeof(params)); - params.max_ports_per_engine = p_hwfn->cdev->num_ports_in_engine; - params.max_phys_tcs_per_port = qm_info->max_phys_tcs_per_port; - params.pf_rl_en = qm_info->pf_rl_en; - params.pf_wfq_en = qm_info->pf_wfq_en; - params.global_rl_en = qm_info->vport_rl_en; - params.vport_wfq_en = qm_info->vport_wfq_en; - params.port_params = qm_info->qm_port_params; + params->max_ports_per_engine = p_hwfn->cdev->num_ports_in_engine; + params->max_phys_tcs_per_port = qm_info->max_phys_tcs_per_port; + params->pf_rl_en = qm_info->pf_rl_en; + params->pf_wfq_en = qm_info->pf_wfq_en; + params->global_rl_en = qm_info->vport_rl_en; + params->vport_wfq_en = qm_info->vport_wfq_en; + params->port_params = qm_info->qm_port_params; - qed_qm_common_rt_init(p_hwfn, ¶ms); + qed_qm_common_rt_init(p_hwfn, params); qed_cxt_hw_init_common(p_hwfn); @@ -2645,7 +2698,7 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, rc = qed_init_run(p_hwfn, p_ptt, PHASE_ENGINE, ANY_PHASE_ID, hw_mode); if (rc) - return rc; + goto out; qed_wr(p_hwfn, p_ptt, PSWRQ2_REG_L2P_VALIDATE_VFID, 0); qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_USE_CLIENTID_IN_TAG, 1); @@ -2664,7 +2717,7 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, max_num_vfs = QED_IS_AH(cdev) ? MAX_NUM_VFS_K2 : MAX_NUM_VFS_BB; for (vf_id = 0; vf_id < max_num_vfs; vf_id++) { concrete_fid = qed_vfid_to_concrete(p_hwfn, vf_id); - qed_fid_pretend(p_hwfn, p_ptt, (u16) concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)concrete_fid); qed_wr(p_hwfn, p_ptt, CCFC_REG_STRONG_ENABLE_VF, 0x1); qed_wr(p_hwfn, p_ptt, CCFC_REG_WEAK_ENABLE_VF, 0x0); qed_wr(p_hwfn, p_ptt, TCFC_REG_STRONG_ENABLE_VF, 0x1); @@ -2673,6 +2726,9 @@ static int qed_hw_init_common(struct qed_hwfn *p_hwfn, /* pretend to original PF */ qed_fid_pretend(p_hwfn, p_ptt, p_hwfn->rel_pf_id); +out: + kfree(params); + return rc; } @@ -2785,7 +2841,7 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) qed_rdma_dpm_bar(p_hwfn, p_ptt); } - p_hwfn->wid_count = (u16) n_cpus; + p_hwfn->wid_count = (u16)n_cpus; DP_INFO(p_hwfn, "doorbell bar: normal_region_size=%d, pwm_region_size=%d, dpi_size=%d, dpi_count=%d, roce_edpm=%s, page_size=%lu\n", @@ -3504,8 +3560,8 @@ static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn) static void get_function_id(struct qed_hwfn *p_hwfn) { /* ME Register */ - p_hwfn->hw_info.opaque_fid = (u16) REG_RD(p_hwfn, - PXP_PF_ME_OPAQUE_ADDR); + p_hwfn->hw_info.opaque_fid = (u16)REG_RD(p_hwfn, + PXP_PF_ME_OPAQUE_ADDR); p_hwfn->hw_info.concrete_fid = REG_RD(p_hwfn, PXP_PF_ME_CONCRETE_ADDR); @@ -3671,12 +3727,14 @@ u32 qed_get_hsi_def_val(struct qed_dev *cdev, enum qed_hsi_def_type type) return qed_hsi_def_val[type][chip_id]; } + static int qed_hw_set_soft_resc_size(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u32 resc_max_val, mcp_resp; u8 res_id; int rc; + for (res_id = 0; res_id < QED_MAX_RESC; res_id++) { switch (res_id) { case QED_LL2_RAM_QUEUE: @@ -3922,7 +3980,7 @@ static int qed_hw_get_resc(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) * resources allocation queries should be atomic. Since several PFs can * run in parallel - a resource lock is needed. * If either the resource lock or resource set value commands are not - * supported - skip the the max values setting, release the lock if + * supported - skip the max values setting, release the lock if * needed, and proceed to the queries. Other failures, including a * failure to acquire the lock, will cause this function to fail. */ @@ -4776,7 +4834,7 @@ int qed_fw_l2_queue(struct qed_hwfn *p_hwfn, u16 src_id, u16 *dst_id) if (src_id >= RESC_NUM(p_hwfn, QED_L2_QUEUE)) { u16 min, max; - min = (u16) RESC_START(p_hwfn, QED_L2_QUEUE); + min = (u16)RESC_START(p_hwfn, QED_L2_QUEUE); max = min + RESC_NUM(p_hwfn, QED_L2_QUEUE); DP_NOTICE(p_hwfn, "l2_queue id [%d] is not valid, available indices [%d - %d]\n", diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 68eaef8ab6e8..f2cedbd9489c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: (GPL-2.0-only OR BSD-3-Clause) */ /* QLogic qed NIC Driver * Copyright (c) 2015-2017 QLogic Corporation - * Copyright (c) 2019-2020 Marvell International Ltd. + * Copyright (c) 2019-2021 Marvell International Ltd. */ #ifndef _QED_HSI_H @@ -38,7 +38,7 @@ enum common_event_opcode { COMMON_EVENT_VF_PF_CHANNEL, COMMON_EVENT_VF_FLR, COMMON_EVENT_PF_UPDATE, - COMMON_EVENT_MALICIOUS_VF, + COMMON_EVENT_FW_ERROR, COMMON_EVENT_RL_UPDATE, COMMON_EVENT_EMPTY, MAX_COMMON_EVENT_OPCODE @@ -84,6 +84,13 @@ enum core_l4_pseudo_checksum_mode { MAX_CORE_L4_PSEUDO_CHECKSUM_MODE }; +/* LL2 SP error code */ +enum core_ll2_error_code { + LL2_OK = 0, + LL2_ERROR, + MAX_CORE_LL2_ERROR_CODE +}; + /* Light-L2 RX Producers in Tstorm RAM */ struct core_ll2_port_stats { struct regpair gsi_invalid_hdr; @@ -123,6 +130,15 @@ struct core_ll2_ustorm_per_queue_stat { struct regpair rcv_bcast_pkts; }; +struct core_ll2_rx_per_queue_stat { + struct core_ll2_tstorm_per_queue_stat tstorm_stat; + struct core_ll2_ustorm_per_queue_stat ustorm_stat; +}; + +struct core_ll2_tx_per_queue_stat { + struct core_ll2_pstorm_per_queue_stat pstorm_stat; +}; + /* Structure for doorbell data, in PWM mode, for RX producers update. */ struct core_pwm_prod_update_data { __le16 icid; /* internal CID */ @@ -135,6 +151,15 @@ struct core_pwm_prod_update_data { struct core_ll2_rx_prod prod; /* Producers */ }; +/* Ramrod data for rx/tx queue statistics query ramrod */ +struct core_queue_stats_query_ramrod_data { + u8 rx_stat; + u8 tx_stat; + __le16 reserved[3]; + struct regpair rx_stat_addr; + struct regpair tx_stat_addr; +}; + /* Core Ramrod Command IDs (light L2) */ enum core_ramrod_cmd_id { CORE_RAMROD_UNUSED, @@ -210,7 +235,8 @@ struct core_rx_fast_path_cqe { __le16 vlan; struct core_rx_cqe_opaque_data opaque_data; struct parsing_err_flags err_flags; - __le16 reserved0; + u8 packet_source; + u8 reserved0; __le32 reserved1[3]; }; @@ -226,7 +252,8 @@ struct core_rx_gsi_offload_cqe { __le16 qp_id; __le32 src_qp; struct core_rx_cqe_opaque_data opaque_data; - __le32 reserved; + u8 packet_source; + u8 reserved[3]; }; /* Core RX CQE for Light L2 */ @@ -245,6 +272,15 @@ union core_rx_cqe_union { struct core_rx_slow_path_cqe rx_cqe_sp; }; +/* RX packet source. */ +enum core_rx_pkt_source { + CORE_RX_PKT_SOURCE_NETWORK = 0, + CORE_RX_PKT_SOURCE_LB, + CORE_RX_PKT_SOURCE_TX, + CORE_RX_PKT_SOURCE_LL2_TX, + MAX_CORE_RX_PKT_SOURCE +}; + /* Ramrod data for rx queue start ramrod */ struct core_rx_start_ramrod_data { struct regpair bd_base; @@ -362,7 +398,7 @@ struct core_tx_update_ramrod_data { u8 update_qm_pq_id_flg; u8 reserved0; __le16 qm_pq_id; - __le32 reserved1; + __le32 reserved1[1]; }; /* Enum flag for what type of dcb data to update */ @@ -386,12 +422,10 @@ struct pstorm_core_conn_st_ctx { /* Core Slowpath Connection storm context of Xstorm */ struct xstorm_core_conn_st_ctx { - __le32 spq_base_lo; - __le32 spq_base_hi; - struct regpair consolid_base_addr; + struct regpair spq_base_addr; + __le32 reserved0[2]; __le16 spq_cons; - __le16 consolid_cons; - __le32 reserved0[55]; + __le16 reserved1[111]; }; struct xstorm_core_conn_ag_ctx { @@ -930,12 +964,12 @@ struct eth_rx_rate_limit { /* Update RSS indirection table entry command */ struct eth_tstorm_rss_update_data { - u8 valid; u8 vport_id; u8 ind_table_index; - u8 reserved; __le16 ind_table_value; __le16 reserved1; + u8 reserved; + u8 valid; }; struct eth_ustorm_per_pf_stat { @@ -967,19 +1001,20 @@ struct vf_pf_channel_eqe_data { struct regpair msg_addr; }; -/* Event Ring malicious VF data */ -struct malicious_vf_eqe_data { - u8 vf_id; - u8 err_id; - __le16 reserved[3]; -}; - /* Event Ring initial cleanup data */ struct initial_cleanup_eqe_data { u8 vf_id; u8 reserved[7]; }; +/* FW error data */ +struct fw_err_data { + u8 recovery_scope; + u8 err_id; + __le16 entity_id; + u8 reserved[4]; +}; + /* Event Data Union */ union event_ring_data { u8 bytes[8]; @@ -987,8 +1022,8 @@ union event_ring_data { struct iscsi_eqe_data iscsi_info; struct iscsi_connect_done_results iscsi_conn_done_info; union rdma_eqe_data rdma_data; - struct malicious_vf_eqe_data malicious_vf; struct initial_cleanup_eqe_data vf_init_cleanup; + struct fw_err_data err_data; }; /* Event Ring Entry */ @@ -1042,6 +1077,15 @@ struct hsi_fp_ver_struct { u8 major_ver_arr[2]; }; +/* Integration Phase */ +enum integ_phase { + INTEG_PHASE_BB_A0_LATEST = 3, + INTEG_PHASE_BB_B0_NO_MCP = 10, + INTEG_PHASE_BB_B0_WITH_MCP = 11, + MAX_INTEG_PHASE +}; + +/* Ports mode */ enum iwarp_ll2_tx_queues { IWARP_LL2_IN_ORDER_TX_QUEUE = 1, IWARP_LL2_ALIGNED_TX_QUEUE, @@ -1050,9 +1094,9 @@ enum iwarp_ll2_tx_queues { MAX_IWARP_LL2_TX_QUEUES }; -/* Malicious VF error ID */ -enum malicious_vf_error_id { - MALICIOUS_VF_NO_ERROR, +/* Function error ID */ +enum func_err_id { + FUNC_NO_ERROR, VF_PF_CHANNEL_NOT_READY, VF_ZONE_MSG_NOT_VALID, VF_ZONE_FUNC_NOT_ENABLED, @@ -1087,7 +1131,27 @@ enum malicious_vf_error_id { CORE_PACKET_SIZE_TOO_LARGE, CORE_ILLEGAL_BD_FLAGS, CORE_GSI_PACKET_VIOLATION, - MAX_MALICIOUS_VF_ERROR_ID, + MAX_FUNC_ERR_ID +}; + +/* FW error handling mode */ +enum fw_err_mode { + FW_ERR_FATAL_ASSERT, + FW_ERR_DRV_REPORT, + MAX_FW_ERR_MODE +}; + +/* FW error recovery scope */ +enum fw_err_recovery_scope { + ERR_SCOPE_INVALID, + ERR_SCOPE_TX_Q, + ERR_SCOPE_RX_Q, + ERR_SCOPE_QP, + ERR_SCOPE_VPORT, + ERR_SCOPE_FUNC, + ERR_SCOPE_PORT, + ERR_SCOPE_ENGINE, + MAX_FW_ERR_RECOVERY_SCOPE }; /* Mstorm non-triggering VF zone */ @@ -1148,7 +1212,7 @@ struct pf_start_tunnel_config { /* Ramrod data for PF start ramrod */ struct pf_start_ramrod_data { struct regpair event_ring_pbl_addr; - struct regpair consolid_q_pbl_addr; + struct regpair consolid_q_pbl_base_addr; struct pf_start_tunnel_config tunnel_config; __le16 event_ring_sb_id; u8 base_vf_id; @@ -1166,6 +1230,9 @@ struct pf_start_ramrod_data { u8 reserved0; struct hsi_fp_ver_struct hsi_fp_ver; struct outer_tag_config_struct outer_tag_config; + u8 pf_fp_err_mode; + u8 consolid_q_num_pages; + u8 reserved[6]; }; /* Data for port update ramrod */ @@ -1230,6 +1297,13 @@ enum ports_mode { MAX_PORTS_MODE }; +/* Protocol-common error code */ +enum protocol_common_error_code { + COMMON_ERR_CODE_OK = 0, + COMMON_ERR_CODE_ERROR, + MAX_PROTOCOL_COMMON_ERROR_CODE +}; + /* use to index in hsi_fp_[major|minor]_ver_arr per protocol */ enum protocol_version_array_key { ETH_VER_KEY = 0, @@ -1704,6 +1778,7 @@ struct igu_msix_vector { #define IGU_MSIX_VECTOR_RESERVED1_MASK 0xFF #define IGU_MSIX_VECTOR_RESERVED1_SHIFT 24 }; + /* per encapsulation type enabling flags */ struct prs_reg_encapsulation_type_en { u8 flags; @@ -1881,6 +1956,9 @@ struct init_nig_pri_tc_map_req { /* QM per global RL init parameters */ struct init_qm_global_rl_params { + u8 type; + u8 reserved0; + u16 reserved1; u32 rate_limit; }; @@ -1895,18 +1973,33 @@ struct init_qm_port_params { /* QM per-PQ init parameters */ struct init_qm_pq_params { - u8 vport_id; + u16 vport_id; + u16 rl_id; + u8 rl_valid; u8 tc_id; u8 wrr_group; - u8 rl_valid; - u16 rl_id; u8 port_id; - u8 reserved; +}; + +/* QM per RL init parameters */ +struct init_qm_rl_params { + u32 vport_rl; + u8 vport_rl_type; + u8 reserved[3]; +}; + +/* QM Rate Limiter types */ +enum init_qm_rl_type { + QM_RL_TYPE_NORMAL, + QM_RL_TYPE_QCN, + MAX_INIT_QM_RL_TYPE }; /* QM per-vport init parameters */ struct init_qm_vport_params { u16 wfq; + u16 reserved; + u16 tc_wfq[NUM_OF_TCS]; u16 first_tx_pq_id[NUM_OF_TCS]; }; @@ -1965,14 +2058,14 @@ struct fw_info_location { }; enum init_modes { - MODE_RESERVED, + MODE_BB_A0_DEPRECATED, MODE_BB, MODE_K2, MODE_ASIC, - MODE_RESERVED2, - MODE_RESERVED3, - MODE_RESERVED4, - MODE_RESERVED5, + MODE_EMUL_REDUCED, + MODE_EMUL_FULL, + MODE_FPGA, + MODE_CHIPSIM, MODE_SF, MODE_MF_SD, MODE_MF_SI, @@ -1980,8 +2073,8 @@ enum init_modes { MODE_PORTS_PER_ENG_2, MODE_PORTS_PER_ENG_4, MODE_100G, - MODE_RESERVED6, - MODE_RESERVED7, + MODE_SKIP_PRAM_INIT, + MODE_EMUL_MAC, MAX_INIT_MODES }; @@ -2282,6 +2375,15 @@ struct iro { /* Win 13 */ #define GTT_BAR0_MAP_REG_PSDM_RAM 0x01a000UL +/* Returns the VOQ based on port and TC */ +#define VOQ(port, tc, max_phys_tcs_per_port) ((tc) == \ + PURE_LB_TC ? NUM_OF_PHYS_TCS *\ + MAX_NUM_PORTS_BB + \ + (port) : (port) * \ + (max_phys_tcs_per_port) + (tc)) + +struct init_qm_pq_params; + /** * qed_qm_pf_mem_size(): Prepare QM ILT sizes. * @@ -2308,8 +2410,19 @@ struct qed_qm_common_rt_init_params { bool global_rl_en; bool vport_wfq_en; struct init_qm_port_params *port_params; + struct init_qm_global_rl_params + global_rl_params[COMMON_MAX_QM_GLOBAL_RLS]; }; +/** + * qed_qm_common_rt_init(): Prepare QM runtime init values for the + * engine phase. + * + * @p_hwfn: HW device data. + * @p_params: Parameters. + * + * Return: 0 on success, -1 on error. + */ int qed_qm_common_rt_init(struct qed_hwfn *p_hwfn, struct qed_qm_common_rt_init_params *p_params); @@ -2326,15 +2439,28 @@ struct qed_qm_pf_rt_init_params { u16 num_vf_pqs; u16 start_vport; u16 num_vports; + u16 start_rl; + u16 num_rls; u16 pf_wfq; u32 pf_rl; + u32 link_speed; struct init_qm_pq_params *pq_params; struct init_qm_vport_params *vport_params; + struct init_qm_rl_params *rl_params; }; +/** + * qed_qm_pf_rt_init(): Prepare QM runtime init values for the PF phase. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers + * @p_params: Parameters. + * + * Return: 0 on success, -1 on error. + */ int qed_qm_pf_rt_init(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_qm_pf_rt_init_params *p_params); + struct qed_ptt *p_ptt, + struct qed_qm_pf_rt_init_params *p_params); /** * qed_init_pf_wfq(): Initializes the WFQ weight of the specified PF. @@ -2378,6 +2504,22 @@ int qed_init_vport_wfq(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 first_tx_pq_id[NUM_OF_TCS], u16 wfq); +/** + * qed_init_vport_tc_wfq(): Initializes the WFQ weight of the specified + * VPORT and TC. + * + * @p_hwfn: HW device data. + * @p_ptt: Ptt window used for writing the registers. + * @first_tx_pq_id: The first Tx PQ ID associated with the VPORT and TC. + * (filled by qed_qm_pf_rt_init). + * @weight: VPORT+TC WFQ weight. + * + * Return: 0 on success, -1 on error. + */ +int qed_init_vport_tc_wfq(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + u16 first_tx_pq_id, u16 weight); + /** * qed_init_global_rl(): Initializes the rate limit of the specified * rate limiter. @@ -2386,12 +2528,14 @@ int qed_init_vport_wfq(struct qed_hwfn *p_hwfn, * @p_ptt: Ptt window used for writing the registers. * @rl_id: RL ID. * @rate_limit: Rate limit in Mb/sec units + * @vport_rl_type: Vport RL type. * * Return: 0 on success, -1 on error. */ int qed_init_global_rl(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, - u16 rl_id, u32 rate_limit); + u16 rl_id, u32 rate_limit, + enum init_qm_rl_type vport_rl_type); /** * qed_send_qm_stop_cmd(): Sends a stop command to the QM. @@ -2627,7 +2771,19 @@ void qed_fw_overlay_init_ram(struct qed_hwfn *p_hwfn, * Return: Void. */ void qed_fw_overlay_mem_free(struct qed_hwfn *p_hwfn, - struct phys_mem_desc *fw_overlay_mem); + struct phys_mem_desc **fw_overlay_mem); + +#define PCICFG_OFFSET 0x2000 +#define GRC_CONFIG_REG_PF_INIT_VF 0x624 + +/* First VF_NUM for PF is encoded in this register. + * The number of VFs assigned to a PF is assumed to be a multiple of 8. + * Software should program these bits based on Total Number of VFs programmed + * for each PF. + * Since registers from 0x000-0x7ff are spilt across functions, each PF will + * have the same location for the same 4 bits + */ +#define GRC_CR_PF_INIT_VF_PF_FIRST_VF_NUM_MASK 0xff /* Runtime array offsets */ #define DORQ_REG_PF_MAX_ICID_0_RT_OFFSET 0 @@ -2958,116 +3114,118 @@ void qed_fw_overlay_mem_free(struct qed_hwfn *p_hwfn, #define QM_REG_TXPQMAP_RT_SIZE 512 #define QM_REG_WFQVPWEIGHT_RT_OFFSET 31556 #define QM_REG_WFQVPWEIGHT_RT_SIZE 512 -#define QM_REG_WFQVPCRD_RT_OFFSET 32068 +#define QM_REG_WFQVPUPPERBOUND_RT_OFFSET 32068 +#define QM_REG_WFQVPUPPERBOUND_RT_SIZE 512 +#define QM_REG_WFQVPCRD_RT_OFFSET 32580 #define QM_REG_WFQVPCRD_RT_SIZE 512 -#define QM_REG_WFQVPMAP_RT_OFFSET 32580 +#define QM_REG_WFQVPMAP_RT_OFFSET 33092 #define QM_REG_WFQVPMAP_RT_SIZE 512 -#define QM_REG_PTRTBLTX_RT_OFFSET 33092 +#define QM_REG_PTRTBLTX_RT_OFFSET 33604 #define QM_REG_PTRTBLTX_RT_SIZE 1024 -#define QM_REG_WFQPFCRD_MSB_RT_OFFSET 34116 +#define QM_REG_WFQPFCRD_MSB_RT_OFFSET 34628 #define QM_REG_WFQPFCRD_MSB_RT_SIZE 160 -#define NIG_REG_TAG_ETHERTYPE_0_RT_OFFSET 34276 -#define NIG_REG_BRB_GATE_DNTFWD_PORT_RT_OFFSET 34277 -#define NIG_REG_OUTER_TAG_VALUE_LIST0_RT_OFFSET 34278 -#define NIG_REG_OUTER_TAG_VALUE_LIST1_RT_OFFSET 34279 -#define NIG_REG_OUTER_TAG_VALUE_LIST2_RT_OFFSET 34280 -#define NIG_REG_OUTER_TAG_VALUE_LIST3_RT_OFFSET 34281 -#define NIG_REG_LLH_FUNC_TAGMAC_CLS_TYPE_RT_OFFSET 34282 -#define NIG_REG_LLH_FUNC_TAG_EN_RT_OFFSET 34283 +#define NIG_REG_TAG_ETHERTYPE_0_RT_OFFSET 34788 +#define NIG_REG_BRB_GATE_DNTFWD_PORT_RT_OFFSET 34789 +#define NIG_REG_OUTER_TAG_VALUE_LIST0_RT_OFFSET 34790 +#define NIG_REG_OUTER_TAG_VALUE_LIST1_RT_OFFSET 34791 +#define NIG_REG_OUTER_TAG_VALUE_LIST2_RT_OFFSET 34792 +#define NIG_REG_OUTER_TAG_VALUE_LIST3_RT_OFFSET 34793 +#define NIG_REG_LLH_FUNC_TAGMAC_CLS_TYPE_RT_OFFSET 34794 +#define NIG_REG_LLH_FUNC_TAG_EN_RT_OFFSET 34795 #define NIG_REG_LLH_FUNC_TAG_EN_RT_SIZE 4 -#define NIG_REG_LLH_FUNC_TAG_VALUE_RT_OFFSET 34287 +#define NIG_REG_LLH_FUNC_TAG_VALUE_RT_OFFSET 34799 #define NIG_REG_LLH_FUNC_TAG_VALUE_RT_SIZE 4 -#define NIG_REG_LLH_FUNC_FILTER_VALUE_RT_OFFSET 34291 +#define NIG_REG_LLH_FUNC_FILTER_VALUE_RT_OFFSET 34803 #define NIG_REG_LLH_FUNC_FILTER_VALUE_RT_SIZE 32 -#define NIG_REG_LLH_FUNC_FILTER_EN_RT_OFFSET 34323 +#define NIG_REG_LLH_FUNC_FILTER_EN_RT_OFFSET 34835 #define NIG_REG_LLH_FUNC_FILTER_EN_RT_SIZE 16 -#define NIG_REG_LLH_FUNC_FILTER_MODE_RT_OFFSET 34339 +#define NIG_REG_LLH_FUNC_FILTER_MODE_RT_OFFSET 34851 #define NIG_REG_LLH_FUNC_FILTER_MODE_RT_SIZE 16 -#define NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE_RT_OFFSET 34355 +#define NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE_RT_OFFSET 34867 #define NIG_REG_LLH_FUNC_FILTER_PROTOCOL_TYPE_RT_SIZE 16 -#define NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_OFFSET 34371 +#define NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_OFFSET 34883 #define NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_SIZE 16 -#define NIG_REG_TX_EDPM_CTRL_RT_OFFSET 34387 -#define NIG_REG_PPF_TO_ENGINE_SEL_RT_OFFSET 34388 +#define NIG_REG_TX_EDPM_CTRL_RT_OFFSET 34899 +#define NIG_REG_PPF_TO_ENGINE_SEL_RT_OFFSET 34900 #define NIG_REG_PPF_TO_ENGINE_SEL_RT_SIZE 8 -#define CDU_REG_CID_ADDR_PARAMS_RT_OFFSET 34396 -#define CDU_REG_SEGMENT0_PARAMS_RT_OFFSET 34397 -#define CDU_REG_SEGMENT1_PARAMS_RT_OFFSET 34398 -#define CDU_REG_PF_SEG0_TYPE_OFFSET_RT_OFFSET 34399 -#define CDU_REG_PF_SEG1_TYPE_OFFSET_RT_OFFSET 34400 -#define CDU_REG_PF_SEG2_TYPE_OFFSET_RT_OFFSET 34401 -#define CDU_REG_PF_SEG3_TYPE_OFFSET_RT_OFFSET 34402 -#define CDU_REG_PF_FL_SEG0_TYPE_OFFSET_RT_OFFSET 34403 -#define CDU_REG_PF_FL_SEG1_TYPE_OFFSET_RT_OFFSET 34404 -#define CDU_REG_PF_FL_SEG2_TYPE_OFFSET_RT_OFFSET 34405 -#define CDU_REG_PF_FL_SEG3_TYPE_OFFSET_RT_OFFSET 34406 -#define CDU_REG_VF_SEG_TYPE_OFFSET_RT_OFFSET 34407 -#define CDU_REG_VF_FL_SEG_TYPE_OFFSET_RT_OFFSET 34408 -#define PBF_REG_TAG_ETHERTYPE_0_RT_OFFSET 34409 -#define PBF_REG_BTB_SHARED_AREA_SIZE_RT_OFFSET 34410 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ0_RT_OFFSET 34411 -#define PBF_REG_BTB_GUARANTEED_VOQ0_RT_OFFSET 34412 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ0_RT_OFFSET 34413 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ1_RT_OFFSET 34414 -#define PBF_REG_BTB_GUARANTEED_VOQ1_RT_OFFSET 34415 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ1_RT_OFFSET 34416 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ2_RT_OFFSET 34417 -#define PBF_REG_BTB_GUARANTEED_VOQ2_RT_OFFSET 34418 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ2_RT_OFFSET 34419 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ3_RT_OFFSET 34420 -#define PBF_REG_BTB_GUARANTEED_VOQ3_RT_OFFSET 34421 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ3_RT_OFFSET 34422 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ4_RT_OFFSET 34423 -#define PBF_REG_BTB_GUARANTEED_VOQ4_RT_OFFSET 34424 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ4_RT_OFFSET 34425 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ5_RT_OFFSET 34426 -#define PBF_REG_BTB_GUARANTEED_VOQ5_RT_OFFSET 34427 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ5_RT_OFFSET 34428 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ6_RT_OFFSET 34429 -#define PBF_REG_BTB_GUARANTEED_VOQ6_RT_OFFSET 34430 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ6_RT_OFFSET 34431 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ7_RT_OFFSET 34432 -#define PBF_REG_BTB_GUARANTEED_VOQ7_RT_OFFSET 34433 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ7_RT_OFFSET 34434 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ8_RT_OFFSET 34435 -#define PBF_REG_BTB_GUARANTEED_VOQ8_RT_OFFSET 34436 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ8_RT_OFFSET 34437 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ9_RT_OFFSET 34438 -#define PBF_REG_BTB_GUARANTEED_VOQ9_RT_OFFSET 34439 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ9_RT_OFFSET 34440 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ10_RT_OFFSET 34441 -#define PBF_REG_BTB_GUARANTEED_VOQ10_RT_OFFSET 34442 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ10_RT_OFFSET 34443 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ11_RT_OFFSET 34444 -#define PBF_REG_BTB_GUARANTEED_VOQ11_RT_OFFSET 34445 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ11_RT_OFFSET 34446 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ12_RT_OFFSET 34447 -#define PBF_REG_BTB_GUARANTEED_VOQ12_RT_OFFSET 34448 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ12_RT_OFFSET 34449 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ13_RT_OFFSET 34450 -#define PBF_REG_BTB_GUARANTEED_VOQ13_RT_OFFSET 34451 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ13_RT_OFFSET 34452 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ14_RT_OFFSET 34453 -#define PBF_REG_BTB_GUARANTEED_VOQ14_RT_OFFSET 34454 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ14_RT_OFFSET 34455 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ15_RT_OFFSET 34456 -#define PBF_REG_BTB_GUARANTEED_VOQ15_RT_OFFSET 34457 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ15_RT_OFFSET 34458 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ16_RT_OFFSET 34459 -#define PBF_REG_BTB_GUARANTEED_VOQ16_RT_OFFSET 34460 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ16_RT_OFFSET 34461 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ17_RT_OFFSET 34462 -#define PBF_REG_BTB_GUARANTEED_VOQ17_RT_OFFSET 34463 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ17_RT_OFFSET 34464 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ18_RT_OFFSET 34465 -#define PBF_REG_BTB_GUARANTEED_VOQ18_RT_OFFSET 34466 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ18_RT_OFFSET 34467 -#define PBF_REG_YCMD_QS_NUM_LINES_VOQ19_RT_OFFSET 34468 -#define PBF_REG_BTB_GUARANTEED_VOQ19_RT_OFFSET 34469 -#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ19_RT_OFFSET 34470 -#define XCM_REG_CON_PHY_Q3_RT_OFFSET 34471 - -#define RUNTIME_ARRAY_SIZE 34472 +#define CDU_REG_CID_ADDR_PARAMS_RT_OFFSET 34908 +#define CDU_REG_SEGMENT0_PARAMS_RT_OFFSET 34909 +#define CDU_REG_SEGMENT1_PARAMS_RT_OFFSET 34910 +#define CDU_REG_PF_SEG0_TYPE_OFFSET_RT_OFFSET 34911 +#define CDU_REG_PF_SEG1_TYPE_OFFSET_RT_OFFSET 34912 +#define CDU_REG_PF_SEG2_TYPE_OFFSET_RT_OFFSET 34913 +#define CDU_REG_PF_SEG3_TYPE_OFFSET_RT_OFFSET 34914 +#define CDU_REG_PF_FL_SEG0_TYPE_OFFSET_RT_OFFSET 34915 +#define CDU_REG_PF_FL_SEG1_TYPE_OFFSET_RT_OFFSET 34916 +#define CDU_REG_PF_FL_SEG2_TYPE_OFFSET_RT_OFFSET 34917 +#define CDU_REG_PF_FL_SEG3_TYPE_OFFSET_RT_OFFSET 34918 +#define CDU_REG_VF_SEG_TYPE_OFFSET_RT_OFFSET 34919 +#define CDU_REG_VF_FL_SEG_TYPE_OFFSET_RT_OFFSET 34920 +#define PBF_REG_TAG_ETHERTYPE_0_RT_OFFSET 34921 +#define PBF_REG_BTB_SHARED_AREA_SIZE_RT_OFFSET 34922 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ0_RT_OFFSET 34923 +#define PBF_REG_BTB_GUARANTEED_VOQ0_RT_OFFSET 34924 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ0_RT_OFFSET 34925 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ1_RT_OFFSET 34926 +#define PBF_REG_BTB_GUARANTEED_VOQ1_RT_OFFSET 34927 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ1_RT_OFFSET 34928 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ2_RT_OFFSET 34929 +#define PBF_REG_BTB_GUARANTEED_VOQ2_RT_OFFSET 34930 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ2_RT_OFFSET 34931 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ3_RT_OFFSET 34932 +#define PBF_REG_BTB_GUARANTEED_VOQ3_RT_OFFSET 34933 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ3_RT_OFFSET 34934 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ4_RT_OFFSET 34935 +#define PBF_REG_BTB_GUARANTEED_VOQ4_RT_OFFSET 34936 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ4_RT_OFFSET 34937 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ5_RT_OFFSET 34938 +#define PBF_REG_BTB_GUARANTEED_VOQ5_RT_OFFSET 34939 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ5_RT_OFFSET 34940 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ6_RT_OFFSET 34941 +#define PBF_REG_BTB_GUARANTEED_VOQ6_RT_OFFSET 34942 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ6_RT_OFFSET 34943 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ7_RT_OFFSET 34944 +#define PBF_REG_BTB_GUARANTEED_VOQ7_RT_OFFSET 34945 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ7_RT_OFFSET 34946 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ8_RT_OFFSET 34947 +#define PBF_REG_BTB_GUARANTEED_VOQ8_RT_OFFSET 34948 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ8_RT_OFFSET 34949 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ9_RT_OFFSET 34950 +#define PBF_REG_BTB_GUARANTEED_VOQ9_RT_OFFSET 34951 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ9_RT_OFFSET 34952 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ10_RT_OFFSET 34953 +#define PBF_REG_BTB_GUARANTEED_VOQ10_RT_OFFSET 34954 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ10_RT_OFFSET 34955 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ11_RT_OFFSET 34956 +#define PBF_REG_BTB_GUARANTEED_VOQ11_RT_OFFSET 34957 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ11_RT_OFFSET 34958 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ12_RT_OFFSET 34959 +#define PBF_REG_BTB_GUARANTEED_VOQ12_RT_OFFSET 34960 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ12_RT_OFFSET 34961 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ13_RT_OFFSET 34962 +#define PBF_REG_BTB_GUARANTEED_VOQ13_RT_OFFSET 34963 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ13_RT_OFFSET 34964 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ14_RT_OFFSET 34965 +#define PBF_REG_BTB_GUARANTEED_VOQ14_RT_OFFSET 34966 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ14_RT_OFFSET 34967 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ15_RT_OFFSET 34968 +#define PBF_REG_BTB_GUARANTEED_VOQ15_RT_OFFSET 34969 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ15_RT_OFFSET 34970 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ16_RT_OFFSET 34971 +#define PBF_REG_BTB_GUARANTEED_VOQ16_RT_OFFSET 34972 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ16_RT_OFFSET 34973 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ17_RT_OFFSET 34974 +#define PBF_REG_BTB_GUARANTEED_VOQ17_RT_OFFSET 34975 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ17_RT_OFFSET 34976 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ18_RT_OFFSET 34977 +#define PBF_REG_BTB_GUARANTEED_VOQ18_RT_OFFSET 34978 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ18_RT_OFFSET 34979 +#define PBF_REG_YCMD_QS_NUM_LINES_VOQ19_RT_OFFSET 34980 +#define PBF_REG_BTB_GUARANTEED_VOQ19_RT_OFFSET 34981 +#define PBF_REG_BTB_SHARED_AREA_SETUP_VOQ19_RT_OFFSET 34982 +#define XCM_REG_CON_PHY_Q3_RT_OFFSET 34983 + +#define RUNTIME_ARRAY_SIZE 34984 /* Init Callbacks */ #define DMAE_READY_CB 0 @@ -3749,7 +3907,7 @@ enum eth_ramrod_cmd_id { ETH_RAMROD_RX_ADD_UDP_FILTER, ETH_RAMROD_RX_DELETE_UDP_FILTER, ETH_RAMROD_RX_CREATE_GFT_ACTION, - ETH_RAMROD_GFT_UPDATE_FILTER, + ETH_RAMROD_RX_UPDATE_GFT_FILTER, ETH_RAMROD_TX_QUEUE_UPDATE, ETH_RAMROD_RGFS_FILTER_ADD, ETH_RAMROD_RGFS_FILTER_DEL, @@ -3833,10 +3991,12 @@ struct eth_vport_rss_config { u8 update_rss_ind_table; u8 update_rss_capabilities; u8 tbl_size; - __le32 reserved2[2]; + u8 ind_table_mask_valid; + u8 reserved2[3]; __le16 indirection_table[ETH_RSS_IND_TABLE_ENTRIES_NUM]; + __le32 ind_table_mask[ETH_RSS_IND_TABLE_MASK_SIZE_REGS]; __le32 rss_key[ETH_RSS_KEY_SIZE_REGS]; - __le32 reserved3[2]; + __le32 reserved3; }; /* eth vport RSS mode */ @@ -3911,8 +4071,20 @@ enum gft_filter_update_action { MAX_GFT_FILTER_UPDATE_ACTION }; +/* Ramrod data for rx create gft action */ +struct rx_create_gft_action_ramrod_data { + u8 vport_id; + u8 reserved[7]; +}; + +/* Ramrod data for rx create openflow action */ +struct rx_create_openflow_action_ramrod_data { + u8 vport_id; + u8 reserved[7]; +}; + /* Ramrod data for rx add openflow filter */ -struct rx_add_openflow_filter_data { +struct rx_openflow_filter_ramrod_data { __le16 action_icid; u8 priority; u8 reserved0; @@ -3935,18 +4107,6 @@ struct rx_add_openflow_filter_data { __le16 l4_src_port; }; -/* Ramrod data for rx create gft action */ -struct rx_create_gft_action_data { - u8 vport_id; - u8 reserved[7]; -}; - -/* Ramrod data for rx create openflow action */ -struct rx_create_openflow_action_data { - u8 vport_id; - u8 reserved[7]; -}; - /* Ramrod data for rx queue start ramrod */ struct rx_queue_start_ramrod_data { __le16 rx_queue_id; @@ -4005,7 +4165,7 @@ struct rx_queue_update_ramrod_data { }; /* Ramrod data for rx Add UDP Filter */ -struct rx_udp_filter_data { +struct rx_udp_filter_ramrod_data { __le16 action_icid; __le16 vlan_id; u8 ip_type; @@ -4021,7 +4181,7 @@ struct rx_udp_filter_data { /* Add or delete GFT filter - filter is packet header of type of packet wished * to pass certain FW flow. */ -struct rx_update_gft_filter_data { +struct rx_update_gft_filter_ramrod_data { struct regpair pkt_hdr_addr; __le16 pkt_hdr_length; __le16 action_icid; @@ -4061,7 +4221,8 @@ struct tx_queue_start_ramrod_data { u8 pxp_tph_valid_bd; u8 pxp_tph_valid_pkt; __le16 pxp_st_index; - __le16 comp_agg_size; + u8 comp_agg_size; + u8 reserved3; __le16 queue_zone_id; __le16 reserved2; __le16 pbl_size; @@ -4182,7 +4343,12 @@ struct vport_update_ramrod_data_cmn { u8 ctl_frame_ethtype_check_en; u8 update_in_to_in_pri_map_mode; u8 in_to_in_pri_map[8]; - u8 reserved[6]; + u8 update_tx_dst_port_mode_flg; + u8 tx_dst_port_mode_config; + u8 dst_vport_id; + u8 tx_dst_port_mode; + u8 dst_vport_id_valid; + u8 reserved[1]; }; struct vport_update_ramrod_mcast { @@ -4716,7 +4882,6 @@ struct gft_cam_line_mapped { #define GFT_CAM_LINE_MAPPED_RESERVED1_SHIFT 29 }; - /* Used in gft_profile_key: Indication for ip version */ enum gft_profile_ip_version { GFT_PROFILE_IPV4 = 0, @@ -5077,6 +5242,843 @@ struct rdma_task_context { struct ustorm_rdma_task_ag_ctx ustorm_ag_context; }; +#define TOE_MAX_RAMROD_PER_PF 8 +#define TOE_TX_PAGE_SIZE_BYTES 4096 +#define TOE_GRQ_PAGE_SIZE_BYTES 4096 +#define TOE_RX_CQ_PAGE_SIZE_BYTES 4096 + +#define TOE_RX_MAX_RSS_CHAINS 64 +#define TOE_TX_MAX_TSS_CHAINS 64 +#define TOE_RSS_INDIRECTION_TABLE_SIZE 128 + +/* The toe storm context of Mstorm */ +struct mstorm_toe_conn_st_ctx { + __le32 reserved[24]; +}; + +/* The toe storm context of Pstorm */ +struct pstorm_toe_conn_st_ctx { + __le32 reserved[36]; +}; + +/* The toe storm context of Ystorm */ +struct ystorm_toe_conn_st_ctx { + __le32 reserved[8]; +}; + +/* The toe storm context of Xstorm */ +struct xstorm_toe_conn_st_ctx { + __le32 reserved[44]; +}; + +struct ystorm_toe_conn_ag_ctx { + u8 byte0; + u8 byte1; + u8 flags0; +#define YSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define YSTORM_TOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define YSTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_MASK 0x3 +#define YSTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_SHIFT 2 +#define YSTORM_TOE_CONN_AG_CTX_RESET_RECEIVED_CF_MASK 0x3 +#define YSTORM_TOE_CONN_AG_CTX_RESET_RECEIVED_CF_SHIFT 4 +#define YSTORM_TOE_CONN_AG_CTX_CF2_MASK 0x3 +#define YSTORM_TOE_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define YSTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_EN_SHIFT 0 +#define YSTORM_TOE_CONN_AG_CTX_RESET_RECEIVED_CF_EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_RESET_RECEIVED_CF_EN_SHIFT 1 +#define YSTORM_TOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define YSTORM_TOE_CONN_AG_CTX_REL_SEQ_EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_REL_SEQ_EN_SHIFT 3 +#define YSTORM_TOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define YSTORM_TOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define YSTORM_TOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define YSTORM_TOE_CONN_AG_CTX_CONS_PROD_EN_MASK 0x1 +#define YSTORM_TOE_CONN_AG_CTX_CONS_PROD_EN_SHIFT 7 + u8 completion_opcode; + u8 byte3; + __le16 word0; + __le32 rel_seq; + __le32 rel_seq_threshold; + __le16 app_prod; + __le16 app_cons; + __le16 word3; + __le16 word4; + __le32 reg2; + __le32 reg3; +}; + +struct xstorm_toe_conn_ag_ctx { + u8 reserved0; + u8 state; + u8 flags0; +#define XSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM1_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM1_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_RESERVED1_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RESERVED1_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM3_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM3_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_TX_DEC_RULE_RES_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_TX_DEC_RULE_RES_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_RESERVED2_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RESERVED2_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_BIT6_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT6_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_BIT7_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT7_SHIFT 7 + u8 flags1; +#define XSTORM_TOE_CONN_AG_CTX_BIT8_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT8_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_BIT9_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT9_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_BIT10_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT10_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_BIT11_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT11_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_BIT12_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT12_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_BIT13_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT13_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_BIT14_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT14_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_BIT15_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT15_SHIFT 7 + u8 flags2; +#define XSTORM_TOE_CONN_AG_CTX_CF0_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF0_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_CF1_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF1_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF2_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF2_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 6 + u8 flags3; +#define XSTORM_TOE_CONN_AG_CTX_CF4_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF4_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_CF5_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF5_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF6_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF6_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF7_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF7_SHIFT 6 + u8 flags4; +#define XSTORM_TOE_CONN_AG_CTX_CF8_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF8_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_CF9_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF9_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF10_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF10_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF11_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF11_SHIFT 6 + u8 flags5; +#define XSTORM_TOE_CONN_AG_CTX_CF12_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF12_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_CF13_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF13_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF14_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF14_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF15_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF15_SHIFT 6 + u8 flags6; +#define XSTORM_TOE_CONN_AG_CTX_CF16_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF16_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_CF17_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF17_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF18_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF18_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_DQ_FLUSH_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_DQ_FLUSH_SHIFT 6 + u8 flags7; +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q1_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q1_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_SLOW_PATH_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_SLOW_PATH_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF0EN_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF1EN_SHIFT 7 + u8 flags8; +#define XSTORM_TOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF2EN_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF4EN_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF5EN_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF6EN_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF7EN_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF8EN_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_CF9EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF9EN_SHIFT 7 + u8 flags9; +#define XSTORM_TOE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF10EN_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_CF11EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF11EN_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_CF12EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF12EN_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_CF13EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF13EN_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_CF14EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF14EN_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF15EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF15EN_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_CF16EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF16EN_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_CF17EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF17EN_SHIFT 7 + u8 flags10; +#define XSTORM_TOE_CONN_AG_CTX_CF18EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF18EN_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_DQ_FLUSH_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_DQ_FLUSH_EN_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q1_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_FLUSH_Q1_EN_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_SLOW_PATH_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_SLOW_PATH_EN_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_CF23EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_CF23EN_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE0EN_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_MORE_TO_SEND_RULE_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_MORE_TO_SEND_RULE_EN_SHIFT 7 + u8 flags11; +#define XSTORM_TOE_CONN_AG_CTX_TX_BLOCKED_EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_TX_BLOCKED_EN_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE3EN_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_RESERVED3_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RESERVED3_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE5EN_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE6EN_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE7EN_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED1_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED1_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_RULE9EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE9EN_SHIFT 7 + u8 flags12; +#define XSTORM_TOE_CONN_AG_CTX_RULE10EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE10EN_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_RULE11EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE11EN_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED2_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED2_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED3_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED3_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_RULE14EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE14EN_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_RULE15EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE15EN_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_RULE16EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE16EN_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_RULE17EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE17EN_SHIFT 7 + u8 flags13; +#define XSTORM_TOE_CONN_AG_CTX_RULE18EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE18EN_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_RULE19EN_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_RULE19EN_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED4_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED4_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED5_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED5_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED6_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED6_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED7_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED7_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED8_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED8_SHIFT 6 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED9_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_A0_RESERVED9_SHIFT 7 + u8 flags14; +#define XSTORM_TOE_CONN_AG_CTX_BIT16_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT16_SHIFT 0 +#define XSTORM_TOE_CONN_AG_CTX_BIT17_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT17_SHIFT 1 +#define XSTORM_TOE_CONN_AG_CTX_BIT18_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT18_SHIFT 2 +#define XSTORM_TOE_CONN_AG_CTX_BIT19_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT19_SHIFT 3 +#define XSTORM_TOE_CONN_AG_CTX_BIT20_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT20_SHIFT 4 +#define XSTORM_TOE_CONN_AG_CTX_BIT21_MASK 0x1 +#define XSTORM_TOE_CONN_AG_CTX_BIT21_SHIFT 5 +#define XSTORM_TOE_CONN_AG_CTX_CF23_MASK 0x3 +#define XSTORM_TOE_CONN_AG_CTX_CF23_SHIFT 6 + u8 byte2; + __le16 physical_q0; + __le16 physical_q1; + __le16 word2; + __le16 word3; + __le16 bd_prod; + __le16 word5; + __le16 word6; + u8 byte3; + u8 byte4; + u8 byte5; + u8 byte6; + __le32 reg0; + __le32 reg1; + __le32 reg2; + __le32 more_to_send_seq; + __le32 local_adv_wnd_seq; + __le32 reg5; + __le32 reg6; + __le16 word7; + __le16 word8; + __le16 word9; + __le16 word10; + __le32 reg7; + __le32 reg8; + __le32 reg9; + u8 byte7; + u8 byte8; + u8 byte9; + u8 byte10; + u8 byte11; + u8 byte12; + u8 byte13; + u8 byte14; + u8 byte15; + u8 e5_reserved; + __le16 word11; + __le32 reg10; + __le32 reg11; + __le32 reg12; + __le32 reg13; + __le32 reg14; + __le32 reg15; + __le32 reg16; + __le32 reg17; +}; + +struct tstorm_toe_conn_ag_ctx { + u8 reserved0; + u8 byte1; + u8 flags0; +#define TSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define TSTORM_TOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define TSTORM_TOE_CONN_AG_CTX_BIT2_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_BIT2_SHIFT 2 +#define TSTORM_TOE_CONN_AG_CTX_BIT3_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_BIT3_SHIFT 3 +#define TSTORM_TOE_CONN_AG_CTX_BIT4_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_BIT4_SHIFT 4 +#define TSTORM_TOE_CONN_AG_CTX_BIT5_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_BIT5_SHIFT 5 +#define TSTORM_TOE_CONN_AG_CTX_TIMEOUT_CF_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_TIMEOUT_CF_SHIFT 6 + u8 flags1; +#define TSTORM_TOE_CONN_AG_CTX_CF1_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF1_SHIFT 0 +#define TSTORM_TOE_CONN_AG_CTX_CF2_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF2_SHIFT 2 +#define TSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 4 +#define TSTORM_TOE_CONN_AG_CTX_CF4_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF4_SHIFT 6 + u8 flags2; +#define TSTORM_TOE_CONN_AG_CTX_CF5_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF5_SHIFT 0 +#define TSTORM_TOE_CONN_AG_CTX_CF6_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF6_SHIFT 2 +#define TSTORM_TOE_CONN_AG_CTX_CF7_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF7_SHIFT 4 +#define TSTORM_TOE_CONN_AG_CTX_CF8_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF8_SHIFT 6 + u8 flags3; +#define TSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_SHIFT 0 +#define TSTORM_TOE_CONN_AG_CTX_CF10_MASK 0x3 +#define TSTORM_TOE_CONN_AG_CTX_CF10_SHIFT 2 +#define TSTORM_TOE_CONN_AG_CTX_TIMEOUT_CF_EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_TIMEOUT_CF_EN_SHIFT 4 +#define TSTORM_TOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF1EN_SHIFT 5 +#define TSTORM_TOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF2EN_SHIFT 6 +#define TSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 7 + u8 flags4; +#define TSTORM_TOE_CONN_AG_CTX_CF4EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF4EN_SHIFT 0 +#define TSTORM_TOE_CONN_AG_CTX_CF5EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF5EN_SHIFT 1 +#define TSTORM_TOE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF6EN_SHIFT 2 +#define TSTORM_TOE_CONN_AG_CTX_CF7EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF7EN_SHIFT 3 +#define TSTORM_TOE_CONN_AG_CTX_CF8EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF8EN_SHIFT 4 +#define TSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_FLUSH_Q0_EN_SHIFT 5 +#define TSTORM_TOE_CONN_AG_CTX_CF10EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_CF10EN_SHIFT 6 +#define TSTORM_TOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE0EN_SHIFT 7 + u8 flags5; +#define TSTORM_TOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define TSTORM_TOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define TSTORM_TOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define TSTORM_TOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define TSTORM_TOE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define TSTORM_TOE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define TSTORM_TOE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define TSTORM_TOE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define TSTORM_TOE_CONN_AG_CTX_RULE8EN_SHIFT 7 + __le32 reg0; + __le32 reg1; + __le32 reg2; + __le32 reg3; + __le32 reg4; + __le32 reg5; + __le32 reg6; + __le32 reg7; + __le32 reg8; + u8 byte2; + u8 byte3; + __le16 word0; +}; + +struct ustorm_toe_conn_ag_ctx { + u8 reserved; + u8 byte1; + u8 flags0; +#define USTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_EXIST_IN_QM0_SHIFT 0 +#define USTORM_TOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define USTORM_TOE_CONN_AG_CTX_CF0_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_CF0_SHIFT 2 +#define USTORM_TOE_CONN_AG_CTX_CF1_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_CF1_SHIFT 4 +#define USTORM_TOE_CONN_AG_CTX_PUSH_TIMER_CF_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_PUSH_TIMER_CF_SHIFT 6 + u8 flags1; +#define USTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_SHIFT 0 +#define USTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_SHIFT 2 +#define USTORM_TOE_CONN_AG_CTX_DQ_CF_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_DQ_CF_SHIFT 4 +#define USTORM_TOE_CONN_AG_CTX_CF6_MASK 0x3 +#define USTORM_TOE_CONN_AG_CTX_CF6_SHIFT 6 + u8 flags2; +#define USTORM_TOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define USTORM_TOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define USTORM_TOE_CONN_AG_CTX_PUSH_TIMER_CF_EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_PUSH_TIMER_CF_EN_SHIFT 2 +#define USTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_TIMER_STOP_ALL_EN_SHIFT 3 +#define USTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_SLOW_PATH_CF_EN_SHIFT 4 +#define USTORM_TOE_CONN_AG_CTX_DQ_CF_EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_DQ_CF_EN_SHIFT 5 +#define USTORM_TOE_CONN_AG_CTX_CF6EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_CF6EN_SHIFT 6 +#define USTORM_TOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE0EN_SHIFT 7 + u8 flags3; +#define USTORM_TOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE1EN_SHIFT 0 +#define USTORM_TOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE2EN_SHIFT 1 +#define USTORM_TOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE3EN_SHIFT 2 +#define USTORM_TOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE4EN_SHIFT 3 +#define USTORM_TOE_CONN_AG_CTX_RULE5EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE5EN_SHIFT 4 +#define USTORM_TOE_CONN_AG_CTX_RULE6EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE6EN_SHIFT 5 +#define USTORM_TOE_CONN_AG_CTX_RULE7EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE7EN_SHIFT 6 +#define USTORM_TOE_CONN_AG_CTX_RULE8EN_MASK 0x1 +#define USTORM_TOE_CONN_AG_CTX_RULE8EN_SHIFT 7 + u8 byte2; + u8 byte3; + __le16 word0; + __le16 word1; + __le32 reg0; + __le32 reg1; + __le32 reg2; + __le32 reg3; + __le16 word2; + __le16 word3; +}; + +/* The toe storm context of Tstorm */ +struct tstorm_toe_conn_st_ctx { + __le32 reserved[16]; +}; + +/* The toe storm context of Ustorm */ +struct ustorm_toe_conn_st_ctx { + __le32 reserved[52]; +}; + +/* toe connection context */ +struct toe_conn_context { + struct ystorm_toe_conn_st_ctx ystorm_st_context; + struct pstorm_toe_conn_st_ctx pstorm_st_context; + struct regpair pstorm_st_padding[2]; + struct xstorm_toe_conn_st_ctx xstorm_st_context; + struct regpair xstorm_st_padding[2]; + struct ystorm_toe_conn_ag_ctx ystorm_ag_context; + struct xstorm_toe_conn_ag_ctx xstorm_ag_context; + struct tstorm_toe_conn_ag_ctx tstorm_ag_context; + struct regpair tstorm_ag_padding[2]; + struct timers_context timer_context; + struct ustorm_toe_conn_ag_ctx ustorm_ag_context; + struct tstorm_toe_conn_st_ctx tstorm_st_context; + struct mstorm_toe_conn_st_ctx mstorm_st_context; + struct ustorm_toe_conn_st_ctx ustorm_st_context; +}; + +/* toe init ramrod header */ +struct toe_init_ramrod_header { + u8 first_rss; + u8 num_rss; + u8 reserved[6]; +}; + +/* toe pf init parameters */ +struct toe_pf_init_params { + __le32 push_timeout; + __le16 grq_buffer_size; + __le16 grq_sb_id; + u8 grq_sb_index; + u8 max_seg_retransmit; + u8 doubt_reachability; + u8 ll2_rx_queue_id; + __le16 grq_fetch_threshold; + u8 reserved1[2]; + struct regpair grq_page_addr; +}; + +/* toe tss parameters */ +struct toe_tss_params { + struct regpair curr_page_addr; + struct regpair next_page_addr; + u8 reserved0; + u8 status_block_index; + __le16 status_block_id; + __le16 reserved1[2]; +}; + +/* toe rss parameters */ +struct toe_rss_params { + struct regpair curr_page_addr; + struct regpair next_page_addr; + u8 reserved0; + u8 status_block_index; + __le16 status_block_id; + __le16 reserved1[2]; +}; + +/* toe init ramrod data */ +struct toe_init_ramrod_data { + struct toe_init_ramrod_header hdr; + struct tcp_init_params tcp_params; + struct toe_pf_init_params pf_params; + struct toe_tss_params tss_params[TOE_TX_MAX_TSS_CHAINS]; + struct toe_rss_params rss_params[TOE_RX_MAX_RSS_CHAINS]; +}; + +/* toe offload parameters */ +struct toe_offload_params { + struct regpair tx_bd_page_addr; + struct regpair tx_app_page_addr; + __le32 more_to_send_seq; + __le16 rcv_indication_size; + u8 rss_tss_id; + u8 ignore_grq_push; + struct regpair rx_db_data_ptr; +}; + +/* TOE offload ramrod data - DMAed by firmware */ +struct toe_offload_ramrod_data { + struct tcp_offload_params tcp_ofld_params; + struct toe_offload_params toe_ofld_params; +}; + +/* TOE ramrod command IDs */ +enum toe_ramrod_cmd_id { + TOE_RAMROD_UNUSED, + TOE_RAMROD_FUNC_INIT, + TOE_RAMROD_INITATE_OFFLOAD, + TOE_RAMROD_FUNC_CLOSE, + TOE_RAMROD_SEARCHER_DELETE, + TOE_RAMROD_TERMINATE, + TOE_RAMROD_QUERY, + TOE_RAMROD_UPDATE, + TOE_RAMROD_EMPTY, + TOE_RAMROD_RESET_SEND, + TOE_RAMROD_INVALIDATE, + MAX_TOE_RAMROD_CMD_ID +}; + +/* Toe RQ buffer descriptor */ +struct toe_rx_bd { + struct regpair addr; + __le16 size; + __le16 flags; +#define TOE_RX_BD_START_MASK 0x1 +#define TOE_RX_BD_START_SHIFT 0 +#define TOE_RX_BD_END_MASK 0x1 +#define TOE_RX_BD_END_SHIFT 1 +#define TOE_RX_BD_NO_PUSH_MASK 0x1 +#define TOE_RX_BD_NO_PUSH_SHIFT 2 +#define TOE_RX_BD_SPLIT_MASK 0x1 +#define TOE_RX_BD_SPLIT_SHIFT 3 +#define TOE_RX_BD_RESERVED0_MASK 0xFFF +#define TOE_RX_BD_RESERVED0_SHIFT 4 + __le32 reserved1; +}; + +/* TOE RX completion queue opcodes (opcode 0 is illegal) */ +enum toe_rx_cmp_opcode { + TOE_RX_CMP_OPCODE_GA = 1, + TOE_RX_CMP_OPCODE_GR = 2, + TOE_RX_CMP_OPCODE_GNI = 3, + TOE_RX_CMP_OPCODE_GAIR = 4, + TOE_RX_CMP_OPCODE_GAIL = 5, + TOE_RX_CMP_OPCODE_GRI = 6, + TOE_RX_CMP_OPCODE_GJ = 7, + TOE_RX_CMP_OPCODE_DGI = 8, + TOE_RX_CMP_OPCODE_CMP = 9, + TOE_RX_CMP_OPCODE_REL = 10, + TOE_RX_CMP_OPCODE_SKP = 11, + TOE_RX_CMP_OPCODE_URG = 12, + TOE_RX_CMP_OPCODE_RT_TO = 13, + TOE_RX_CMP_OPCODE_KA_TO = 14, + TOE_RX_CMP_OPCODE_MAX_RT = 15, + TOE_RX_CMP_OPCODE_DBT_RE = 16, + TOE_RX_CMP_OPCODE_SYN = 17, + TOE_RX_CMP_OPCODE_OPT_ERR = 18, + TOE_RX_CMP_OPCODE_FW2_TO = 19, + TOE_RX_CMP_OPCODE_2WY_CLS = 20, + TOE_RX_CMP_OPCODE_RST_RCV = 21, + TOE_RX_CMP_OPCODE_FIN_RCV = 22, + TOE_RX_CMP_OPCODE_FIN_UPL = 23, + TOE_RX_CMP_OPCODE_INIT = 32, + TOE_RX_CMP_OPCODE_RSS_UPDATE = 33, + TOE_RX_CMP_OPCODE_CLOSE = 34, + TOE_RX_CMP_OPCODE_INITIATE_OFFLOAD = 80, + TOE_RX_CMP_OPCODE_SEARCHER_DELETE = 81, + TOE_RX_CMP_OPCODE_TERMINATE = 82, + TOE_RX_CMP_OPCODE_QUERY = 83, + TOE_RX_CMP_OPCODE_RESET_SEND = 84, + TOE_RX_CMP_OPCODE_INVALIDATE = 85, + TOE_RX_CMP_OPCODE_EMPTY = 86, + TOE_RX_CMP_OPCODE_UPDATE = 87, + MAX_TOE_RX_CMP_OPCODE +}; + +/* TOE rx ooo completion data */ +struct toe_rx_cqe_ooo_params { + __le32 nbytes; + __le16 grq_buff_id; + u8 isle_num; + u8 reserved0; +}; + +/* TOE rx in order completion data */ +struct toe_rx_cqe_in_order_params { + __le32 nbytes; + __le16 grq_buff_id; + __le16 reserved1; +}; + +/* Union for TOE rx completion data */ +union toe_rx_cqe_data_union { + struct toe_rx_cqe_ooo_params ooo_params; + struct toe_rx_cqe_in_order_params in_order_params; + struct regpair raw_data; +}; + +/* TOE rx completion element */ +struct toe_rx_cqe { + __le16 icid; + u8 completion_opcode; + u8 reserved0; + __le32 reserved1; + union toe_rx_cqe_data_union data; +}; + +/* toe RX doorbel data */ +struct toe_rx_db_data { + __le32 local_adv_wnd_seq; + __le32 reserved[3]; +}; + +/* Toe GRQ buffer descriptor */ +struct toe_rx_grq_bd { + struct regpair addr; + __le16 buff_id; + __le16 reserved0; + __le32 reserved1; +}; + +/* Toe transmission application buffer descriptor */ +struct toe_tx_app_buff_desc { + __le32 next_buffer_start_seq; + __le32 reserved; +}; + +/* Toe transmission application buffer descriptor page pointer */ +struct toe_tx_app_buff_page_pointer { + struct regpair next_page_addr; +}; + +/* Toe transmission buffer descriptor */ +struct toe_tx_bd { + struct regpair addr; + __le16 size; + __le16 flags; +#define TOE_TX_BD_PUSH_MASK 0x1 +#define TOE_TX_BD_PUSH_SHIFT 0 +#define TOE_TX_BD_NOTIFY_MASK 0x1 +#define TOE_TX_BD_NOTIFY_SHIFT 1 +#define TOE_TX_BD_LARGE_IO_MASK 0x1 +#define TOE_TX_BD_LARGE_IO_SHIFT 2 +#define TOE_TX_BD_BD_CONS_MASK 0x1FFF +#define TOE_TX_BD_BD_CONS_SHIFT 3 + __le32 next_bd_start_seq; +}; + +/* TOE completion opcodes */ +enum toe_tx_cmp_opcode { + TOE_TX_CMP_OPCODE_DATA, + TOE_TX_CMP_OPCODE_TERMINATE, + TOE_TX_CMP_OPCODE_EMPTY, + TOE_TX_CMP_OPCODE_RESET_SEND, + TOE_TX_CMP_OPCODE_INVALIDATE, + TOE_TX_CMP_OPCODE_RST_RCV, + MAX_TOE_TX_CMP_OPCODE +}; + +/* Toe transmission completion element */ +struct toe_tx_cqe { + __le16 icid; + u8 opcode; + u8 reserved; + __le32 size; +}; + +/* Toe transmission page pointer bd */ +struct toe_tx_page_pointer_bd { + struct regpair next_page_addr; + struct regpair prev_page_addr; +}; + +/* Toe transmission completion element page pointer */ +struct toe_tx_page_pointer_cqe { + struct regpair next_page_addr; +}; + +/* toe update parameters */ +struct toe_update_params { + __le16 flags; +#define TOE_UPDATE_PARAMS_RCV_INDICATION_SIZE_CHANGED_MASK 0x1 +#define TOE_UPDATE_PARAMS_RCV_INDICATION_SIZE_CHANGED_SHIFT 0 +#define TOE_UPDATE_PARAMS_RESERVED_MASK 0x7FFF +#define TOE_UPDATE_PARAMS_RESERVED_SHIFT 1 + __le16 rcv_indication_size; + __le16 reserved1[2]; +}; + +/* TOE update ramrod data - DMAed by firmware */ +struct toe_update_ramrod_data { + struct tcp_update_params tcp_upd_params; + struct toe_update_params toe_upd_params; +}; + +struct mstorm_toe_conn_ag_ctx { + u8 byte0; + u8 byte1; + u8 flags0; +#define MSTORM_TOE_CONN_AG_CTX_BIT0_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_BIT0_SHIFT 0 +#define MSTORM_TOE_CONN_AG_CTX_BIT1_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_BIT1_SHIFT 1 +#define MSTORM_TOE_CONN_AG_CTX_CF0_MASK 0x3 +#define MSTORM_TOE_CONN_AG_CTX_CF0_SHIFT 2 +#define MSTORM_TOE_CONN_AG_CTX_CF1_MASK 0x3 +#define MSTORM_TOE_CONN_AG_CTX_CF1_SHIFT 4 +#define MSTORM_TOE_CONN_AG_CTX_CF2_MASK 0x3 +#define MSTORM_TOE_CONN_AG_CTX_CF2_SHIFT 6 + u8 flags1; +#define MSTORM_TOE_CONN_AG_CTX_CF0EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_CF0EN_SHIFT 0 +#define MSTORM_TOE_CONN_AG_CTX_CF1EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_CF1EN_SHIFT 1 +#define MSTORM_TOE_CONN_AG_CTX_CF2EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_CF2EN_SHIFT 2 +#define MSTORM_TOE_CONN_AG_CTX_RULE0EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_RULE0EN_SHIFT 3 +#define MSTORM_TOE_CONN_AG_CTX_RULE1EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_RULE1EN_SHIFT 4 +#define MSTORM_TOE_CONN_AG_CTX_RULE2EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_RULE2EN_SHIFT 5 +#define MSTORM_TOE_CONN_AG_CTX_RULE3EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_RULE3EN_SHIFT 6 +#define MSTORM_TOE_CONN_AG_CTX_RULE4EN_MASK 0x1 +#define MSTORM_TOE_CONN_AG_CTX_RULE4EN_SHIFT 7 + __le16 word0; + __le16 word1; + __le32 reg0; + __le32 reg1; +}; + +/* TOE doorbell data */ +struct toe_db_data { + u8 params; +#define TOE_DB_DATA_DEST_MASK 0x3 +#define TOE_DB_DATA_DEST_SHIFT 0 +#define TOE_DB_DATA_AGG_CMD_MASK 0x3 +#define TOE_DB_DATA_AGG_CMD_SHIFT 2 +#define TOE_DB_DATA_BYPASS_EN_MASK 0x1 +#define TOE_DB_DATA_BYPASS_EN_SHIFT 4 +#define TOE_DB_DATA_RESERVED_MASK 0x1 +#define TOE_DB_DATA_RESERVED_SHIFT 5 +#define TOE_DB_DATA_AGG_VAL_SEL_MASK 0x3 +#define TOE_DB_DATA_AGG_VAL_SEL_SHIFT 6 + u8 agg_flags; + __le16 bd_prod; +}; + /* rdma function init ramrod data */ struct rdma_close_func_ramrod_data { u8 cnq_start_offset; @@ -5148,6 +6150,8 @@ enum rdma_event_opcode { RDMA_EVENT_CREATE_SRQ, RDMA_EVENT_MODIFY_SRQ, RDMA_EVENT_DESTROY_SRQ, + RDMA_EVENT_START_NAMESPACE_TRACKING, + RDMA_EVENT_STOP_NAMESPACE_TRACKING, MAX_RDMA_EVENT_OPCODE }; @@ -5172,18 +6176,33 @@ struct rdma_init_func_hdr { u8 relaxed_ordering; __le16 first_reg_srq_id; __le32 reg_srq_base_addr; - u8 searcher_mode; - u8 pvrdma_mode; + u8 flags; +#define RDMA_INIT_FUNC_HDR_SEARCHER_MODE_MASK 0x1 +#define RDMA_INIT_FUNC_HDR_SEARCHER_MODE_SHIFT 0 +#define RDMA_INIT_FUNC_HDR_PVRDMA_MODE_MASK 0x1 +#define RDMA_INIT_FUNC_HDR_PVRDMA_MODE_SHIFT 1 +#define RDMA_INIT_FUNC_HDR_DPT_MODE_MASK 0x1 +#define RDMA_INIT_FUNC_HDR_DPT_MODE_SHIFT 2 +#define RDMA_INIT_FUNC_HDR_RESERVED0_MASK 0x1F +#define RDMA_INIT_FUNC_HDR_RESERVED0_SHIFT 3 + u8 dpt_byte_threshold_log; + u8 dpt_common_queue_id; u8 max_num_ns_log; - u8 reserved; }; /* rdma function init ramrod data */ struct rdma_init_func_ramrod_data { struct rdma_init_func_hdr params_header; + struct rdma_cnq_params dptq_params; struct rdma_cnq_params cnq_params[NUM_OF_GLOBAL_QUEUES]; }; +/* rdma namespace tracking ramrod data */ +struct rdma_namespace_tracking_ramrod_data { + u8 name_space; + u8 reserved[7]; +}; + /* RDMA ramrod command IDs */ enum rdma_ramrod_cmd_id { RDMA_RAMROD_UNUSED, @@ -5197,6 +6216,8 @@ enum rdma_ramrod_cmd_id { RDMA_RAMROD_CREATE_SRQ, RDMA_RAMROD_MODIFY_SRQ, RDMA_RAMROD_DESTROY_SRQ, + RDMA_RAMROD_START_NS_TRACKING, + RDMA_RAMROD_STOP_NS_TRACKING, MAX_RDMA_RAMROD_CMD_ID }; @@ -5918,8 +6939,10 @@ struct roce_create_qp_req_ramrod_data { #define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_SHIFT 0 #define ROCE_CREATE_QP_REQ_RAMROD_DATA_VF_ID_VALID_MASK 0x1 #define ROCE_CREATE_QP_REQ_RAMROD_DATA_VF_ID_VALID_SHIFT 1 -#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_MASK 0x3F -#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_SHIFT 2 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_FORCE_LB_MASK 0x1 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_FORCE_LB_SHIFT 2 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_MASK 0x1F +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_SHIFT 3 u8 name_space; u8 reserved3[3]; __le16 regular_latency_phy_queue; @@ -5951,8 +6974,10 @@ struct roce_create_qp_resp_ramrod_data { #define ROCE_CREATE_QP_RESP_RAMROD_DATA_XRC_FLAG_SHIFT 16 #define ROCE_CREATE_QP_RESP_RAMROD_DATA_VF_ID_VALID_MASK 0x1 #define ROCE_CREATE_QP_RESP_RAMROD_DATA_VF_ID_VALID_SHIFT 17 -#define ROCE_CREATE_QP_RESP_RAMROD_DATA_RESERVED_MASK 0x3FFF -#define ROCE_CREATE_QP_RESP_RAMROD_DATA_RESERVED_SHIFT 18 +#define ROCE_CREATE_QP_RESP_RAMROD_DATA_FORCE_LB_MASK 0x1 +#define ROCE_CREATE_QP_RESP_RAMROD_DATA_FORCE_LB_SHIFT 18 +#define ROCE_CREATE_QP_RESP_RAMROD_DATA_RESERVED_MASK 0x1FFF +#define ROCE_CREATE_QP_RESP_RAMROD_DATA_RESERVED_SHIFT 19 __le16 xrc_domain; u8 max_ird; u8 traffic_class; @@ -5989,10 +7014,85 @@ struct roce_create_qp_resp_ramrod_data { u8 reserved3[3]; }; +/* RoCE Create Suspended qp requester runtime ramrod data */ +struct roce_create_suspended_qp_req_runtime_ramrod_data { + __le32 flags; +#define ROCE_CREATE_SUSPENDED_QP_REQ_RUNTIME_RAMROD_DATA_ERR_FLG_MASK 0x1 +#define ROCE_CREATE_SUSPENDED_QP_REQ_RUNTIME_RAMROD_DATA_ERR_FLG_SHIFT 0 +#define ROCE_CREATE_SUSPENDED_QP_REQ_RUNTIME_RAMROD_DATA_RESERVED0_MASK \ + 0x7FFFFFFF +#define ROCE_CREATE_SUSPENDED_QP_REQ_RUNTIME_RAMROD_DATA_RESERVED0_SHIFT 1 + __le32 send_msg_psn; + __le32 inflight_sends; + __le32 ssn; +}; + +/* RoCE Create Suspended QP requester ramrod data */ +struct roce_create_suspended_qp_req_ramrod_data { + struct roce_create_qp_req_ramrod_data qp_params; + struct roce_create_suspended_qp_req_runtime_ramrod_data + qp_runtime_params; +}; + +/* RoCE Create Suspended QP responder runtime params */ +struct roce_create_suspended_qp_resp_runtime_params { + __le32 flags; +#define ROCE_CREATE_SUSPENDED_QP_RESP_RUNTIME_PARAMS_ERR_FLG_MASK 0x1 +#define ROCE_CREATE_SUSPENDED_QP_RESP_RUNTIME_PARAMS_ERR_FLG_SHIFT 0 +#define ROCE_CREATE_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RDMA_ACTIVE_MASK 0x1 +#define ROCE_CREATE_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RDMA_ACTIVE_SHIFT 1 +#define ROCE_CREATE_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RESERVED0_MASK 0x3FFFFFFF +#define ROCE_CREATE_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RESERVED0_SHIFT 2 + __le32 receive_msg_psn; + __le32 inflight_receives; + __le32 rmsn; + __le32 rdma_key; + struct regpair rdma_va; + __le32 rdma_length; + __le32 num_rdb_entries; + __le32 resreved; +}; + +/* RoCE RDB array entry */ +struct roce_resp_qp_rdb_entry { + struct regpair atomic_data; + struct regpair va; + __le32 psn; + __le32 rkey; + __le32 byte_count; + u8 op_type; + u8 reserved[3]; +}; + +/* RoCE Create Suspended QP responder runtime ramrod data */ +struct roce_create_suspended_qp_resp_runtime_ramrod_data { + struct roce_create_suspended_qp_resp_runtime_params params; + struct roce_resp_qp_rdb_entry + rdb_array_entries[RDMA_MAX_IRQ_ELEMS_IN_PAGE]; +}; + +/* RoCE Create Suspended QP responder ramrod data */ +struct roce_create_suspended_qp_resp_ramrod_data { + struct roce_create_qp_resp_ramrod_data + qp_params; + struct roce_create_suspended_qp_resp_runtime_ramrod_data + qp_runtime_params; +}; + +/* RoCE create ud qp ramrod data */ +struct roce_create_ud_qp_ramrod_data { + __le16 local_mac_addr[3]; + __le16 vlan_id; + __le32 src_qp_id; + u8 name_space; + u8 reserved[3]; +}; + /* roce DCQCN received statistics */ struct roce_dcqcn_received_stats { struct regpair ecn_pkt_rcv; struct regpair cnp_pkt_rcv; + struct regpair cnp_pkt_reject; }; /* roce DCQCN sent statistics */ @@ -6024,6 +7124,12 @@ struct roce_destroy_qp_resp_ramrod_data { __le32 reserved; }; +/* RoCE destroy ud qp ramrod data */ +struct roce_destroy_ud_qp_ramrod_data { + __le32 src_qp_id; + __le32 reserved; +}; + /* roce error statistics */ struct roce_error_stats { __le32 resp_remote_access_errors; @@ -6046,13 +7152,21 @@ struct roce_events_stats { /* roce slow path EQ cmd IDs */ enum roce_event_opcode { - ROCE_EVENT_CREATE_QP = 11, + ROCE_EVENT_CREATE_QP = 13, ROCE_EVENT_MODIFY_QP, ROCE_EVENT_QUERY_QP, ROCE_EVENT_DESTROY_QP, ROCE_EVENT_CREATE_UD_QP, ROCE_EVENT_DESTROY_UD_QP, ROCE_EVENT_FUNC_UPDATE, + ROCE_EVENT_SUSPEND_QP, + ROCE_EVENT_QUERY_SUSPENDED_QP, + ROCE_EVENT_CREATE_SUSPENDED_QP, + ROCE_EVENT_RESUME_QP, + ROCE_EVENT_SUSPEND_UD_QP, + ROCE_EVENT_RESUME_UD_QP, + ROCE_EVENT_CREATE_SUSPENDED_UD_QP, + ROCE_EVENT_FLUSH_DPT_QP, MAX_ROCE_EVENT_OPCODE }; @@ -6080,6 +7194,18 @@ struct roce_init_func_ramrod_data { struct roce_init_func_params roce; }; +/* roce_ll2_cqe_data */ +struct roce_ll2_cqe_data { + u8 name_space; + u8 flags; +#define ROCE_LL2_CQE_DATA_QP_SUSPENDED_MASK 0x1 +#define ROCE_LL2_CQE_DATA_QP_SUSPENDED_SHIFT 0 +#define ROCE_LL2_CQE_DATA_RESERVED0_MASK 0x7F +#define ROCE_LL2_CQE_DATA_RESERVED0_SHIFT 1 + u8 reserved1[2]; + __le32 cid; +}; + /* roce modify qp requester ramrod data */ struct roce_modify_qp_req_ramrod_data { __le16 flags; @@ -6107,8 +7233,10 @@ struct roce_modify_qp_req_ramrod_data { #define ROCE_MODIFY_QP_REQ_RAMROD_DATA_PRI_SHIFT 10 #define ROCE_MODIFY_QP_REQ_RAMROD_DATA_PHYSICAL_QUEUE_FLG_MASK 0x1 #define ROCE_MODIFY_QP_REQ_RAMROD_DATA_PHYSICAL_QUEUE_FLG_SHIFT 13 -#define ROCE_MODIFY_QP_REQ_RAMROD_DATA_RESERVED1_MASK 0x3 -#define ROCE_MODIFY_QP_REQ_RAMROD_DATA_RESERVED1_SHIFT 14 +#define ROCE_MODIFY_QP_REQ_RAMROD_DATA_FORCE_LB_MASK 0x1 +#define ROCE_MODIFY_QP_REQ_RAMROD_DATA_FORCE_LB_SHIFT 14 +#define ROCE_MODIFY_QP_REQ_RAMROD_DATA_RESERVED1_MASK 0x1 +#define ROCE_MODIFY_QP_REQ_RAMROD_DATA_RESERVED1_SHIFT 15 u8 fields; #define ROCE_MODIFY_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT_MASK 0xF #define ROCE_MODIFY_QP_REQ_RAMROD_DATA_ERR_RETRY_CNT_SHIFT 0 @@ -6154,8 +7282,10 @@ struct roce_modify_qp_resp_ramrod_data { #define ROCE_MODIFY_QP_RESP_RAMROD_DATA_RDMA_OPS_EN_FLG_SHIFT 9 #define ROCE_MODIFY_QP_RESP_RAMROD_DATA_PHYSICAL_QUEUE_FLG_MASK 0x1 #define ROCE_MODIFY_QP_RESP_RAMROD_DATA_PHYSICAL_QUEUE_FLG_SHIFT 10 -#define ROCE_MODIFY_QP_RESP_RAMROD_DATA_RESERVED1_MASK 0x1F -#define ROCE_MODIFY_QP_RESP_RAMROD_DATA_RESERVED1_SHIFT 11 +#define ROCE_MODIFY_QP_RESP_RAMROD_DATA_FORCE_LB_MASK 0x1 +#define ROCE_MODIFY_QP_RESP_RAMROD_DATA_FORCE_LB_SHIFT 11 +#define ROCE_MODIFY_QP_RESP_RAMROD_DATA_RESERVED1_MASK 0xF +#define ROCE_MODIFY_QP_RESP_RAMROD_DATA_RESERVED1_SHIFT 12 u8 fields; #define ROCE_MODIFY_QP_RESP_RAMROD_DATA_PRI_MASK 0x7 #define ROCE_MODIFY_QP_RESP_RAMROD_DATA_PRI_SHIFT 0 @@ -6206,18 +7336,84 @@ struct roce_query_qp_resp_ramrod_data { struct regpair output_params_addr; }; +/* RoCE Query Suspended QP requester output params */ +struct roce_query_suspended_qp_req_output_params { + __le32 psn; + __le32 flags; +#define ROCE_QUERY_SUSPENDED_QP_REQ_OUTPUT_PARAMS_ERR_FLG_MASK 0x1 +#define ROCE_QUERY_SUSPENDED_QP_REQ_OUTPUT_PARAMS_ERR_FLG_SHIFT 0 +#define ROCE_QUERY_SUSPENDED_QP_REQ_OUTPUT_PARAMS_RESERVED0_MASK 0x7FFFFFFF +#define ROCE_QUERY_SUSPENDED_QP_REQ_OUTPUT_PARAMS_RESERVED0_SHIFT 1 + __le32 send_msg_psn; + __le32 inflight_sends; + __le32 ssn; + __le32 reserved; +}; + +/* RoCE Query Suspended QP requester ramrod data */ +struct roce_query_suspended_qp_req_ramrod_data { + struct regpair output_params_addr; +}; + +/* RoCE Query Suspended QP responder runtime params */ +struct roce_query_suspended_qp_resp_runtime_params { + __le32 psn; + __le32 flags; +#define ROCE_QUERY_SUSPENDED_QP_RESP_RUNTIME_PARAMS_ERR_FLG_MASK 0x1 +#define ROCE_QUERY_SUSPENDED_QP_RESP_RUNTIME_PARAMS_ERR_FLG_SHIFT 0 +#define ROCE_QUERY_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RDMA_ACTIVE_MASK 0x1 +#define ROCE_QUERY_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RDMA_ACTIVE_SHIFT 1 +#define ROCE_QUERY_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RESERVED0_MASK 0x3FFFFFFF +#define ROCE_QUERY_SUSPENDED_QP_RESP_RUNTIME_PARAMS_RESERVED0_SHIFT 2 + __le32 receive_msg_psn; + __le32 inflight_receives; + __le32 rmsn; + __le32 rdma_key; + struct regpair rdma_va; + __le32 rdma_length; + __le32 num_rdb_entries; +}; + +/* RoCE Query Suspended QP responder output params */ +struct roce_query_suspended_qp_resp_output_params { + struct roce_query_suspended_qp_resp_runtime_params runtime_params; + struct roce_resp_qp_rdb_entry + rdb_array_entries[RDMA_MAX_IRQ_ELEMS_IN_PAGE]; +}; + +/* RoCE Query Suspended QP responder ramrod data */ +struct roce_query_suspended_qp_resp_ramrod_data { + struct regpair output_params_addr; +}; + /* ROCE ramrod command IDs */ enum roce_ramrod_cmd_id { - ROCE_RAMROD_CREATE_QP = 11, + ROCE_RAMROD_CREATE_QP = 13, ROCE_RAMROD_MODIFY_QP, ROCE_RAMROD_QUERY_QP, ROCE_RAMROD_DESTROY_QP, ROCE_RAMROD_CREATE_UD_QP, ROCE_RAMROD_DESTROY_UD_QP, ROCE_RAMROD_FUNC_UPDATE, + ROCE_RAMROD_SUSPEND_QP, + ROCE_RAMROD_QUERY_SUSPENDED_QP, + ROCE_RAMROD_CREATE_SUSPENDED_QP, + ROCE_RAMROD_RESUME_QP, + ROCE_RAMROD_SUSPEND_UD_QP, + ROCE_RAMROD_RESUME_UD_QP, + ROCE_RAMROD_CREATE_SUSPENDED_UD_QP, + ROCE_RAMROD_FLUSH_DPT_QP, MAX_ROCE_RAMROD_CMD_ID }; +/* ROCE RDB array entry type */ +enum roce_resp_qp_rdb_entry_type { + ROCE_QP_RDB_ENTRY_RDMA_RESPONSE = 0, + ROCE_QP_RDB_ENTRY_ATOMIC_RESPONSE = 1, + ROCE_QP_RDB_ENTRY_INVALID = 2, + MAX_ROCE_RESP_QP_RDB_ENTRY_TYPE +}; + /* RoCE func init ramrod data */ struct roce_update_func_params { u8 cnp_vlan_priority; @@ -7968,8 +9164,8 @@ enum iwarp_eqe_async_opcode { IWARP_EVENT_TYPE_ASYNC_EXCEPTION_DETECTED, IWARP_EVENT_TYPE_ASYNC_QP_IN_ERROR_STATE, IWARP_EVENT_TYPE_ASYNC_CQ_OVERFLOW, - IWARP_EVENT_TYPE_ASYNC_SRQ_EMPTY, IWARP_EVENT_TYPE_ASYNC_SRQ_LIMIT, + IWARP_EVENT_TYPE_ASYNC_SRQ_EMPTY, MAX_IWARP_EQE_ASYNC_OPCODE }; @@ -7987,8 +9183,7 @@ struct iwarp_eqe_data_tcp_async_completion { /* iWARP completion queue types */ enum iwarp_eqe_sync_opcode { - IWARP_EVENT_TYPE_TCP_OFFLOAD = - 11, + IWARP_EVENT_TYPE_TCP_OFFLOAD = 13, IWARP_EVENT_TYPE_MPA_OFFLOAD, IWARP_EVENT_TYPE_MPA_OFFLOAD_SEND_RTR, IWARP_EVENT_TYPE_CREATE_QP, @@ -8020,8 +9215,6 @@ enum iwarp_fw_return_code { IWARP_EXCEPTION_DETECTED_LLP_RESET, IWARP_EXCEPTION_DETECTED_IRQ_FULL, IWARP_EXCEPTION_DETECTED_RQ_EMPTY, - IWARP_EXCEPTION_DETECTED_SRQ_EMPTY, - IWARP_EXCEPTION_DETECTED_SRQ_LIMIT, IWARP_EXCEPTION_DETECTED_LLP_TIMEOUT, IWARP_EXCEPTION_DETECTED_REMOTE_PROTECTION_ERROR, IWARP_EXCEPTION_DETECTED_CQ_OVERFLOW, @@ -8115,9 +9308,10 @@ struct iwarp_mpa_offload_ramrod_data { struct regpair async_eqe_output_buf; struct regpair handle_for_async; struct regpair shared_queue_addr; + __le32 additional_setup_time; __le16 rcv_wnd; u8 stats_counter_id; - u8 reserved3[13]; + u8 reserved3[9]; }; /* iWARP TCP connection offload params passed by driver to FW */ @@ -8125,11 +9319,13 @@ struct iwarp_offload_params { struct mpa_ulp_buffer incoming_ulp_buffer; struct regpair async_eqe_output_buf; struct regpair handle_for_async; + __le32 additional_setup_time; __le16 physical_q0; __le16 physical_q1; u8 stats_counter_id; u8 mpa_mode; - u8 reserved[10]; + u8 src_vport_id; + u8 reserved[5]; }; /* iWARP query QP output params */ @@ -8149,7 +9345,7 @@ struct iwarp_query_qp_ramrod_data { /* iWARP Ramrod Command IDs */ enum iwarp_ramrod_cmd_id { - IWARP_RAMROD_CMD_ID_TCP_OFFLOAD = 11, + IWARP_RAMROD_CMD_ID_TCP_OFFLOAD = 13, IWARP_RAMROD_CMD_ID_MPA_OFFLOAD, IWARP_RAMROD_CMD_ID_MPA_OFFLOAD_SEND_RTR, IWARP_RAMROD_CMD_ID_CREATE_QP, diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c index 7dad91049cc0..fb90ad4a9d1f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c @@ -920,7 +920,8 @@ int qed_init_vport_wfq(struct qed_hwfn *p_hwfn, } int qed_init_global_rl(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u16 rl_id, u32 rate_limit) + struct qed_ptt *p_ptt, u16 rl_id, u32 rate_limit, + enum init_qm_rl_type vport_rl_type) { u32 inc_val; @@ -1645,7 +1646,7 @@ struct phys_mem_desc *qed_fw_overlay_mem_alloc(struct qed_hwfn *p_hwfn, /* If memory allocation has failed, free all allocated memory */ if (buf_offset < buf_size) { - qed_fw_overlay_mem_free(p_hwfn, allocated_mem); + qed_fw_overlay_mem_free(p_hwfn, &allocated_mem); return NULL; } @@ -1679,16 +1680,16 @@ void qed_fw_overlay_init_ram(struct qed_hwfn *p_hwfn, } void qed_fw_overlay_mem_free(struct qed_hwfn *p_hwfn, - struct phys_mem_desc *fw_overlay_mem) + struct phys_mem_desc **fw_overlay_mem) { u8 storm_id; - if (!fw_overlay_mem) + if (!fw_overlay_mem || !(*fw_overlay_mem)) return; for (storm_id = 0; storm_id < NUM_STORMS; storm_id++) { struct phys_mem_desc *storm_mem_desc = - (struct phys_mem_desc *)fw_overlay_mem + storm_id; + (struct phys_mem_desc *)*fw_overlay_mem + storm_id; /* Free Storm's physical memory */ if (storm_mem_desc->virt_addr) @@ -1699,5 +1700,6 @@ void qed_fw_overlay_mem_free(struct qed_hwfn *p_hwfn, } /* Free allocated virtual memory */ - kfree(fw_overlay_mem); + kfree(*fw_overlay_mem); + *fw_overlay_mem = NULL; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 991bf4313da6..9b3850712797 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -38,7 +38,6 @@ #include "qed_sp.h" #include "qed_sriov.h" - #define QED_MAX_SGES_NUM 16 #define CRC32_POLY 0x1edc6f41 @@ -1112,7 +1111,6 @@ qed_eth_pf_tx_queue_start(struct qed_hwfn *p_hwfn, { int rc; - rc = qed_eth_txq_start_ramrod(p_hwfn, p_cid, pbl_addr, pbl_size, qed_get_cm_pq_idx_mcos(p_hwfn, tc)); @@ -2011,7 +2009,7 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, struct qed_spq_comp_cb *p_cb, struct qed_ntuple_filter_params *p_params) { - struct rx_update_gft_filter_data *p_ramrod = NULL; + struct rx_update_gft_filter_ramrod_data *p_ramrod = NULL; struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; u16 abs_rx_q_id = 0; @@ -2032,7 +2030,7 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, } rc = qed_sp_init_request(p_hwfn, &p_ent, - ETH_RAMROD_GFT_UPDATE_FILTER, + ETH_RAMROD_RX_UPDATE_GFT_FILTER, PROTOCOLID_ETH, &init_data); if (rc) return rc; diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 2ab7f3f0cf6c..a538cf478c14 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -146,7 +146,6 @@ struct qed_sp_vport_start_params { int qed_sp_eth_vport_start(struct qed_hwfn *p_hwfn, struct qed_sp_vport_start_params *p_params); - struct qed_filter_accept_flags { u8 update_rx_mode_config; u8 update_tx_mode_config; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index c5a38f3c92b0..4fb02a5579ee 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -23,9 +23,9 @@ enum spq_mode { }; struct qed_spq_comp_cb { - void (*function)(struct qed_hwfn *, - void *, - union event_ring_data *, + void (*function)(struct qed_hwfn *p_hwfn, + void *cookie, + union event_ring_data *data, u8 fw_return_code); void *cookie; }; @@ -53,7 +53,7 @@ union ramrod_data { struct tx_queue_stop_ramrod_data tx_queue_stop; struct vport_start_ramrod_data vport_start; struct vport_stop_ramrod_data vport_stop; - struct rx_update_gft_filter_data rx_update_gft; + struct rx_update_gft_filter_ramrod_data rx_update_gft; struct vport_update_ramrod_data vport_update; struct core_rx_start_ramrod_data core_rx_queue_start; struct core_rx_stop_ramrod_data core_rx_queue_stop; diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index b4ed54ffef9b..648176dfb871 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -369,8 +369,12 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, qed_chain_get_pbl_phys(&p_hwfn->p_eq->chain)); page_cnt = (u8)qed_chain_get_page_cnt(&p_hwfn->p_eq->chain); p_ramrod->event_ring_num_pages = page_cnt; - DMA_REGPAIR_LE(p_ramrod->consolid_q_pbl_addr, + + /* Place consolidation queue address in ramrod */ + DMA_REGPAIR_LE(p_ramrod->consolid_q_pbl_base_addr, qed_chain_get_pbl_phys(&p_hwfn->p_consq->chain)); + page_cnt = (u8)qed_chain_get_page_cnt(&p_hwfn->p_consq->chain); + p_ramrod->consolid_q_num_pages = page_cnt; qed_tunn_set_pf_start_params(p_hwfn, p_tunn, &p_ramrod->tunnel_config); @@ -401,8 +405,8 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, if (p_hwfn->cdev->p_iov_info) { struct qed_hw_sriov_info *p_iov = p_hwfn->cdev->p_iov_info; - p_ramrod->base_vf_id = (u8) p_iov->first_vf_in_pf; - p_ramrod->num_vfs = (u8) p_iov->total_vfs; + p_ramrod->base_vf_id = (u8)p_iov->first_vf_in_pf; + p_ramrod->num_vfs = (u8)p_iov->total_vfs; } p_ramrod->hsi_fp_ver.major_ver_arr[ETH_VER_KEY] = ETH_HSI_VER_MAJOR; p_ramrod->hsi_fp_ver.minor_ver_arr[ETH_VER_KEY] = ETH_HSI_VER_MINOR; diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 8bef53ca7597..65dbc08196b7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -32,8 +32,8 @@ #include "qed_rdma.h" /*************************************************************************** -* Structures & Definitions -***************************************************************************/ + * Structures & Definitions + ***************************************************************************/ #define SPQ_HIGH_PRI_RESERVE_DEFAULT (1) @@ -43,8 +43,8 @@ #define SPQ_BLOCK_SLEEP_MS (5) /*************************************************************************** -* Blocking Imp. (BLOCK/EBLOCK mode) -***************************************************************************/ + * Blocking Imp. (BLOCK/EBLOCK mode) + ***************************************************************************/ static void qed_spq_blocking_cb(struct qed_hwfn *p_hwfn, void *cookie, union event_ring_data *data, u8 fw_return_code) @@ -150,8 +150,8 @@ err: } /*************************************************************************** -* SPQ entries inner API -***************************************************************************/ + * SPQ entries inner API + ***************************************************************************/ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent) { @@ -185,8 +185,8 @@ static int qed_spq_fill_entry(struct qed_hwfn *p_hwfn, } /*************************************************************************** -* HSI access -***************************************************************************/ + * HSI access + ***************************************************************************/ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq) { @@ -218,13 +218,10 @@ static void qed_spq_hw_initialize(struct qed_hwfn *p_hwfn, physical_q = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LB); p_cxt->xstorm_ag_context.physical_q0 = cpu_to_le16(physical_q); - p_cxt->xstorm_st_context.spq_base_lo = + p_cxt->xstorm_st_context.spq_base_addr.lo = DMA_LO_LE(p_spq->chain.p_phys_addr); - p_cxt->xstorm_st_context.spq_base_hi = + p_cxt->xstorm_st_context.spq_base_addr.hi = DMA_HI_LE(p_spq->chain.p_phys_addr); - - DMA_REGPAIR_LE(p_cxt->xstorm_st_context.consolid_base_addr, - p_hwfn->p_consq->chain.p_phys_addr); } static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, @@ -266,8 +263,8 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn, } /*************************************************************************** -* Asynchronous events -***************************************************************************/ + * Asynchronous events + ***************************************************************************/ static int qed_async_event_completion(struct qed_hwfn *p_hwfn, struct event_ring_entry *p_eqe) @@ -312,8 +309,8 @@ qed_spq_unregister_async_cb(struct qed_hwfn *p_hwfn, } /*************************************************************************** -* EQ API -***************************************************************************/ + * EQ API + ***************************************************************************/ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod) { u32 addr = GTT_BAR0_MAP_REG_USDM_RAM + @@ -434,8 +431,8 @@ void qed_eq_free(struct qed_hwfn *p_hwfn) } /*************************************************************************** -* CQE API - manipulate EQ functionality -***************************************************************************/ + * CQE API - manipulate EQ functionality + ***************************************************************************/ static int qed_cqe_completion(struct qed_hwfn *p_hwfn, struct eth_slow_path_rx_cqe *cqe, enum protocol_type protocol) @@ -465,8 +462,8 @@ int qed_eth_cqe_completion(struct qed_hwfn *p_hwfn, } /*************************************************************************** -* Slow hwfn Queue (spq) -***************************************************************************/ + * Slow hwfn Queue (spq) + ***************************************************************************/ void qed_spq_setup(struct qed_hwfn *p_hwfn) { struct qed_spq *p_spq = p_hwfn->p_spq; @@ -549,7 +546,7 @@ int qed_spq_alloc(struct qed_hwfn *p_hwfn) int ret; /* SPQ struct */ - p_spq = kzalloc(sizeof(struct qed_spq), GFP_KERNEL); + p_spq = kzalloc(sizeof(*p_spq), GFP_KERNEL); if (!p_spq) return -ENOMEM; @@ -677,7 +674,6 @@ static int qed_spq_add_entry(struct qed_hwfn *p_hwfn, struct qed_spq *p_spq = p_hwfn->p_spq; if (p_ent->queue == &p_spq->unlimited_pending) { - if (list_empty(&p_spq->free_pool)) { list_add_tail(&p_ent->list, &p_spq->unlimited_pending); p_spq->unlimited_pending_count++; @@ -726,8 +722,8 @@ static int qed_spq_add_entry(struct qed_hwfn *p_hwfn, } /*************************************************************************** -* Accessor -***************************************************************************/ + * Accessor + ***************************************************************************/ u32 qed_spq_get_cid(struct qed_hwfn *p_hwfn) { if (!p_hwfn->p_spq) @@ -736,8 +732,8 @@ u32 qed_spq_get_cid(struct qed_hwfn *p_hwfn) } /*************************************************************************** -* Posting new Ramrods -***************************************************************************/ + * Posting new Ramrods + ***************************************************************************/ static int qed_spq_post_list(struct qed_hwfn *p_hwfn, struct list_head *head, u32 keep_reserve) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 2a67b1308fe0..9556a2c4d3a6 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -20,12 +20,13 @@ #include "qed_sp.h" #include "qed_sriov.h" #include "qed_vf.h" -static int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, - u8 opcode, - __le16 echo, - union event_ring_data *data, u8 fw_return_code); static int qed_iov_bulletin_set_mac(struct qed_hwfn *p_hwfn, u8 *mac, int vfid); +static u16 qed_vf_from_entity_id(__le16 entity_id) +{ + return le16_to_cpu(entity_id) - MAX_NUM_PFS; +} + static u8 qed_vf_calculate_legacy(struct qed_vf_info *p_vf) { u8 legacy = 0; @@ -170,8 +171,8 @@ static struct qed_vf_info *qed_iov_get_vf_info(struct qed_hwfn *p_hwfn, b_enabled_only, false)) vf = &p_hwfn->pf_iov_info->vfs_array[relative_vf_id]; else - DP_ERR(p_hwfn, "qed_iov_get_vf_info: VF[%d] is not enabled\n", - relative_vf_id); + DP_ERR(p_hwfn, "%s: VF[%d] is not enabled\n", + __func__, relative_vf_id); return vf; } @@ -309,7 +310,7 @@ static int qed_iov_post_vf_bulletin(struct qed_hwfn *p_hwfn, struct qed_dmae_params params; struct qed_vf_info *p_vf; - p_vf = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + p_vf = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!p_vf) return -EINVAL; @@ -421,7 +422,7 @@ static void qed_iov_setup_vfdb(struct qed_hwfn *p_hwfn) bulletin_p = p_iov_info->bulletins_phys; if (!p_req_virt_addr || !p_reply_virt_addr || !p_bulletin_virt) { DP_ERR(p_hwfn, - "qed_iov_setup_vfdb called without allocating mem first\n"); + "%s called without allocating mem first\n", __func__); return; } @@ -465,7 +466,7 @@ static int qed_iov_allocate_vfdb(struct qed_hwfn *p_hwfn) num_vfs = p_hwfn->cdev->p_iov_info->total_vfs; DP_VERBOSE(p_hwfn, QED_MSG_IOV, - "qed_iov_allocate_vfdb for %d VFs\n", num_vfs); + "%s for %d VFs\n", __func__, num_vfs); /* Allocate PF Mailbox buffer (per-VF) */ p_iov_info->mbx_msg_size = sizeof(union vfpf_tlvs) * num_vfs; @@ -501,10 +502,10 @@ static int qed_iov_allocate_vfdb(struct qed_hwfn *p_hwfn) QED_MSG_IOV, "PF's Requests mailbox [%p virt 0x%llx phys], Response mailbox [%p virt 0x%llx phys] Bulletins [%p virt 0x%llx phys]\n", p_iov_info->mbx_msg_virt_addr, - (u64) p_iov_info->mbx_msg_phys_addr, + (u64)p_iov_info->mbx_msg_phys_addr, p_iov_info->mbx_reply_virt_addr, - (u64) p_iov_info->mbx_reply_phys_addr, - p_iov_info->p_bulletins, (u64) p_iov_info->bulletins_phys); + (u64)p_iov_info->mbx_reply_phys_addr, + p_iov_info->p_bulletins, (u64)p_iov_info->bulletins_phys); return 0; } @@ -609,7 +610,7 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn) if (rc) return rc; - /* We want PF IOV to be synonemous with the existance of p_iov_info; + /* We want PF IOV to be synonemous with the existence of p_iov_info; * In case the capability is published but there are no VFs, simply * de-allocate the struct. */ @@ -715,12 +716,12 @@ static void qed_iov_vf_igu_reset(struct qed_hwfn *p_hwfn, int i; /* Set VF masks and configuration - pretend */ - qed_fid_pretend(p_hwfn, p_ptt, (u16) vf->concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)vf->concrete_fid); qed_wr(p_hwfn, p_ptt, IGU_REG_STATISTIC_NUM_VF_MSG_SENT, 0); /* unpretend */ - qed_fid_pretend(p_hwfn, p_ptt, (u16) p_hwfn->hw_info.concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)p_hwfn->hw_info.concrete_fid); /* iterate over all queues, clear sb consumer */ for (i = 0; i < vf->num_sbs; i++) @@ -735,7 +736,7 @@ static void qed_iov_vf_igu_set_int(struct qed_hwfn *p_hwfn, { u32 igu_vf_conf; - qed_fid_pretend(p_hwfn, p_ptt, (u16) vf->concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)vf->concrete_fid); igu_vf_conf = qed_rd(p_hwfn, p_ptt, IGU_REG_VF_CONFIGURATION); @@ -747,7 +748,7 @@ static void qed_iov_vf_igu_set_int(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, IGU_REG_VF_CONFIGURATION, igu_vf_conf); /* unpretend */ - qed_fid_pretend(p_hwfn, p_ptt, (u16) p_hwfn->hw_info.concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)p_hwfn->hw_info.concrete_fid); } static int @@ -808,7 +809,7 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn, if (rc) return rc; - qed_fid_pretend(p_hwfn, p_ptt, (u16) vf->concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)vf->concrete_fid); SET_FIELD(igu_vf_conf, IGU_VF_CONF_PARENT, p_hwfn->rel_pf_id); STORE_RT_REG(p_hwfn, IGU_REG_VF_CONFIGURATION_RT_OFFSET, igu_vf_conf); @@ -817,7 +818,7 @@ static int qed_iov_enable_vf_access(struct qed_hwfn *p_hwfn, p_hwfn->hw_info.hw_mode); /* unpretend */ - qed_fid_pretend(p_hwfn, p_ptt, (u16) p_hwfn->hw_info.concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)p_hwfn->hw_info.concrete_fid); vf->state = VF_FREE; @@ -905,7 +906,7 @@ static u8 qed_iov_alloc_vf_igu_sbs(struct qed_hwfn *p_hwfn, p_block->igu_sb_id * sizeof(u64), 2, NULL); } - vf->num_sbs = (u8) num_rx_queues; + vf->num_sbs = (u8)num_rx_queues; return vf->num_sbs; } @@ -989,7 +990,7 @@ static int qed_iov_init_hw_for_vf(struct qed_hwfn *p_hwfn, vf = qed_iov_get_vf_info(p_hwfn, p_params->rel_vf_id, false); if (!vf) { - DP_ERR(p_hwfn, "qed_iov_init_hw_for_vf : vf is NULL\n"); + DP_ERR(p_hwfn, "%s : vf is NULL\n", __func__); return -EINVAL; } @@ -1093,7 +1094,7 @@ static int qed_iov_release_hw_for_vf(struct qed_hwfn *p_hwfn, vf = qed_iov_get_vf_info(p_hwfn, rel_vf_id, true); if (!vf) { - DP_ERR(p_hwfn, "qed_iov_release_hw_for_vf : vf is NULL\n"); + DP_ERR(p_hwfn, "%s : vf is NULL\n", __func__); return -EINVAL; } @@ -1546,7 +1547,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn, memset(resp, 0, sizeof(*resp)); /* Write the PF version so that VF would know which version - * is supported - might be later overriden. This guarantees that + * is supported - might be later overridden. This guarantees that * VF could recognize legacy PF based on lack of versions in reply. */ pfdev_info->major_fp_hsi = ETH_HSI_VER_MAJOR; @@ -1898,7 +1899,7 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn, int sb_id; int rc; - vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vf->relative_vf_id, true); + vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vf->relative_vf_id, true); if (!vf_info) { DP_NOTICE(p_hwfn->cdev, "Failed to get VF info, invalid vfid [%d]\n", @@ -1958,7 +1959,7 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn, rc = qed_sp_eth_vport_start(p_hwfn, ¶ms); if (rc) { DP_ERR(p_hwfn, - "qed_iov_vf_mbx_start_vport returned error %d\n", rc); + "%s returned error %d\n", __func__, rc); status = PFVF_STATUS_FAILURE; } else { vf->vport_instance++; @@ -1994,8 +1995,8 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn, rc = qed_sp_vport_stop(p_hwfn, vf->opaque_fid, vf->vport_id); if (rc) { - DP_ERR(p_hwfn, "qed_iov_vf_mbx_stop_vport returned error %d\n", - rc); + DP_ERR(p_hwfn, "%s returned error %d\n", + __func__, rc); status = PFVF_STATUS_FAILURE; } @@ -3031,7 +3032,7 @@ static void qed_iov_vf_mbx_vport_update(struct qed_hwfn *p_hwfn, goto out; } p_rss_params = vzalloc(sizeof(*p_rss_params)); - if (p_rss_params == NULL) { + if (!p_rss_params) { status = PFVF_STATUS_FAILURE; goto out; } @@ -3551,6 +3552,7 @@ out: qed_iov_prepare_resp(p_hwfn, p_ptt, vf, CHANNEL_TLV_COALESCE_UPDATE, sizeof(struct pfvf_def_resp_tlv), status); } + static int qed_iov_vf_flr_poll_dorq(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf, struct qed_ptt *p_ptt) @@ -3558,7 +3560,7 @@ qed_iov_vf_flr_poll_dorq(struct qed_hwfn *p_hwfn, int cnt; u32 val; - qed_fid_pretend(p_hwfn, p_ptt, (u16) p_vf->concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)p_vf->concrete_fid); for (cnt = 0; cnt < 50; cnt++) { val = qed_rd(p_hwfn, p_ptt, DORQ_REG_VF_USAGE_CNT); @@ -3566,7 +3568,7 @@ qed_iov_vf_flr_poll_dorq(struct qed_hwfn *p_hwfn, break; msleep(20); } - qed_fid_pretend(p_hwfn, p_ptt, (u16) p_hwfn->hw_info.concrete_fid); + qed_fid_pretend(p_hwfn, p_ptt, (u16)p_hwfn->hw_info.concrete_fid); if (cnt == 50) { DP_ERR(p_hwfn, @@ -3843,7 +3845,7 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn, struct qed_iov_vf_mbx *mbx; struct qed_vf_info *p_vf; - p_vf = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + p_vf = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!p_vf) return; @@ -3980,7 +3982,7 @@ static void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events) static struct qed_vf_info *qed_sriov_get_vf_from_absid(struct qed_hwfn *p_hwfn, u16 abs_vfid) { - u8 min = (u8) p_hwfn->cdev->p_iov_info->first_vf_in_pf; + u8 min = (u8)p_hwfn->cdev->p_iov_info->first_vf_in_pf; if (!_qed_iov_pf_sanity_check(p_hwfn, (int)abs_vfid - min, false)) { DP_VERBOSE(p_hwfn, @@ -3990,7 +3992,7 @@ static struct qed_vf_info *qed_sriov_get_vf_from_absid(struct qed_hwfn *p_hwfn, return NULL; } - return &p_hwfn->pf_iov_info->vfs_array[(u8) abs_vfid - min]; + return &p_hwfn->pf_iov_info->vfs_array[(u8)abs_vfid - min]; } static int qed_sriov_vfpf_msg(struct qed_hwfn *p_hwfn, @@ -4014,13 +4016,13 @@ static int qed_sriov_vfpf_msg(struct qed_hwfn *p_hwfn, return 0; } -static void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn, - struct malicious_vf_eqe_data *p_data) +void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn, + struct fw_err_data *p_data) { struct qed_vf_info *p_vf; - p_vf = qed_sriov_get_vf_from_absid(p_hwfn, p_data->vf_id); - + p_vf = qed_sriov_get_vf_from_absid(p_hwfn, qed_vf_from_entity_id + (p_data->entity_id)); if (!p_vf) return; @@ -4037,16 +4039,13 @@ static void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn, } } -static int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, __le16 echo, - union event_ring_data *data, u8 fw_return_code) +int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, __le16 echo, + union event_ring_data *data, u8 fw_return_code) { switch (opcode) { case COMMON_EVENT_VF_PF_CHANNEL: return qed_sriov_vfpf_msg(p_hwfn, le16_to_cpu(echo), &data->vf_pf_channel.msg_addr); - case COMMON_EVENT_MALICIOUS_VF: - qed_sriov_vfpf_malicious(p_hwfn, &data->malicious_vf); - return 0; default: DP_INFO(p_hwfn->cdev, "Unknown sriov eqe event 0x%02x\n", opcode); @@ -4076,7 +4075,7 @@ static int qed_iov_copy_vf_msg(struct qed_hwfn *p_hwfn, struct qed_ptt *ptt, struct qed_dmae_params params; struct qed_vf_info *vf_info; - vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!vf_info) return -EINVAL; @@ -4177,7 +4176,7 @@ static void qed_iov_bulletin_set_forced_vlan(struct qed_hwfn *p_hwfn, struct qed_vf_info *vf_info; u64 feature; - vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!vf_info) { DP_NOTICE(p_hwfn->cdev, "Can not set forced MAC, invalid vfid [%d]\n", vfid); @@ -4227,7 +4226,7 @@ static bool qed_iov_vf_has_vport_instance(struct qed_hwfn *p_hwfn, int vfid) { struct qed_vf_info *p_vf_info; - p_vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + p_vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!p_vf_info) return false; @@ -4238,7 +4237,7 @@ static bool qed_iov_is_vf_stopped(struct qed_hwfn *p_hwfn, int vfid) { struct qed_vf_info *p_vf_info; - p_vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + p_vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!p_vf_info) return true; @@ -4249,7 +4248,7 @@ static bool qed_iov_spoofchk_get(struct qed_hwfn *p_hwfn, int vfid) { struct qed_vf_info *vf_info; - vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!vf_info) return false; @@ -4267,7 +4266,7 @@ static int qed_iov_spoofchk_set(struct qed_hwfn *p_hwfn, int vfid, bool val) goto out; } - vf = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + vf = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!vf) goto out; @@ -4346,7 +4345,8 @@ static int qed_iov_configure_tx_rate(struct qed_hwfn *p_hwfn, return rc; rl_id = abs_vp_id; /* The "rl_id" is set as the "vport_id" */ - return qed_init_global_rl(p_hwfn, p_ptt, rl_id, (u32)val); + return qed_init_global_rl(p_hwfn, p_ptt, rl_id, (u32)val, + QM_RL_TYPE_NORMAL); } static int @@ -4377,7 +4377,7 @@ static int qed_iov_get_vf_min_rate(struct qed_hwfn *p_hwfn, int vfid) struct qed_wfq_data *vf_vp_wfq; struct qed_vf_info *vf_info; - vf_info = qed_iov_get_vf_info(p_hwfn, (u16) vfid, true); + vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); if (!vf_info) return 0; @@ -4396,8 +4396,10 @@ static int qed_iov_get_vf_min_rate(struct qed_hwfn *p_hwfn, int vfid) */ void qed_schedule_iov(struct qed_hwfn *hwfn, enum qed_iov_wq_flag flag) { + /* Memory barrier for setting atomic bit */ smp_mb__before_atomic(); set_bit(flag, &hwfn->iov_task_flags); + /* Memory barrier after setting atomic bit */ smp_mb__after_atomic(); DP_VERBOSE(hwfn, QED_MSG_IOV, "Scheduling iov task [Flag: %d]\n", flag); queue_delayed_work(hwfn->iov_wq, &hwfn->iov_task, 0); @@ -4408,8 +4410,8 @@ void qed_vf_start_iov_wq(struct qed_dev *cdev) int i; for_each_hwfn(cdev, i) - queue_delayed_work(cdev->hwfns[i].iov_wq, - &cdev->hwfns[i].iov_task, 0); + queue_delayed_work(cdev->hwfns[i].iov_wq, + &cdev->hwfns[i].iov_task, 0); } int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled) @@ -4417,8 +4419,8 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled) int i, j; for_each_hwfn(cdev, i) - if (cdev->hwfns[i].iov_wq) - flush_workqueue(cdev->hwfns[i].iov_wq); + if (cdev->hwfns[i].iov_wq) + flush_workqueue(cdev->hwfns[i].iov_wq); /* Mark VFs for disablement */ qed_iov_set_vfs_to_disable(cdev, true); @@ -5011,7 +5013,7 @@ static void qed_handle_bulletin_post(struct qed_hwfn *hwfn) } qed_for_each_vf(hwfn, i) - qed_iov_post_vf_bulletin(hwfn, i, ptt); + qed_iov_post_vf_bulletin(hwfn, i, ptt); qed_ptt_release(hwfn, ptt); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.h b/drivers/net/ethernet/qlogic/qed/qed_sriov.h index 9f81295c6f45..1edf9c44dc67 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.h @@ -142,7 +142,7 @@ struct qed_vf_queue { enum vf_state { VF_FREE = 0, /* VF ready to be acquired holds no resc */ - VF_ACQUIRED, /* VF, acquired, but not initalized */ + VF_ACQUIRED, /* VF, acquired, but not initialized */ VF_ENABLED, /* VF, Enabled */ VF_RESET, /* VF, FLR'd, pending cleanup */ VF_STOPPED /* VF, Stopped */ @@ -313,6 +313,31 @@ void *qed_add_tlv(struct qed_hwfn *p_hwfn, u8 **offset, u16 type, u16 length); */ void qed_dp_tlv_list(struct qed_hwfn *p_hwfn, void *tlvs_list); +/** + * qed_sriov_vfpf_malicious(): Handle malicious VF/PF. + * + * @p_hwfn: HW device data. + * @p_data: Pointer to data. + * + * Return: Void. + */ +void qed_sriov_vfpf_malicious(struct qed_hwfn *p_hwfn, + struct fw_err_data *p_data); + +/** + * qed_sriov_eqe_event(): Callback for SRIOV events. + * + * @p_hwfn: HW device data. + * @opcode: Opcode. + * @echo: Echo. + * @data: data + * @fw_return_code: FW return code. + * + * Return: Int. + */ +int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, __le16 echo, + union event_ring_data *data, u8 fw_return_code); + /** * qed_iov_alloc(): allocate sriov related resources * diff --git a/include/linux/qed/eth_common.h b/include/linux/qed/eth_common.h index cd1207ad4ada..c84e08bc6802 100644 --- a/include/linux/qed/eth_common.h +++ b/include/linux/qed/eth_common.h @@ -67,6 +67,7 @@ /* Ethernet vport update constants */ #define ETH_FILTER_RULES_COUNT 10 #define ETH_RSS_IND_TABLE_ENTRIES_NUM 128 +#define ETH_RSS_IND_TABLE_MASK_SIZE_REGS (ETH_RSS_IND_TABLE_ENTRIES_NUM / 32) #define ETH_RSS_KEY_SIZE_REGS 10 #define ETH_RSS_ENGINE_NUM_K2 207 #define ETH_RSS_ENGINE_NUM_BB 127 diff --git a/include/linux/qed/rdma_common.h b/include/linux/qed/rdma_common.h index bab078b25834..6dfed163ab6c 100644 --- a/include/linux/qed/rdma_common.h +++ b/include/linux/qed/rdma_common.h @@ -27,6 +27,7 @@ #define RDMA_MAX_PDS (64 * 1024) #define RDMA_MAX_XRC_SRQS (1024) #define RDMA_MAX_SRQS (32 * 1024) +#define RDMA_MAX_IRQ_ELEMS_IN_PAGE (128) #define RDMA_NUM_STATISTIC_COUNTERS MAX_NUM_VPORTS #define RDMA_NUM_STATISTIC_COUNTERS_K2 MAX_NUM_VPORTS_K2 -- cgit v1.2.3 From 3a6f5d0cbda37f24f60ca778bd1675125b7d594f Mon Sep 17 00:00:00 2001 From: Nikolay Assa Date: Mon, 4 Oct 2021 09:58:49 +0300 Subject: qed: Update TCP silly-window-syndrome timeout for iwarp, scsi Update TCP silly-window-syndrome timeout, for the cases where initiator's small TCP window size prevents FW from transmitting packets on the connection. Timeout causes FW to retransmit window probes if needed, preventing I/O stall if initiator ignores first window probe. Reviewed-by: Manish Rangankar Signed-off-by: Nikolay Assa Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: Omkar Kulkarni Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 1 + drivers/scsi/qedi/qedi_main.c | 1 + include/linux/qed/qed_if.h | 2 ++ 3 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index 186d0048a9d1..b2c0e522e51f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -114,6 +114,7 @@ qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn, RESC_START(p_hwfn, QED_LL2_RAM_QUEUE) + p_hwfn->p_rdma_info->iwarp.ll2_ooo_handle; + p_ramrod->tcp.tx_sws_timer = cpu_to_le16(QED_TX_SWS_TIMER_DFLT); p_ramrod->tcp.max_fin_rt = QED_IWARP_MAX_FIN_RT_DEFAULT; return; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index fe36ddb82aef..8c2f32655424 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -866,6 +866,7 @@ static int qedi_set_iscsi_pf_param(struct qedi_ctx *qedi) qedi->pf_params.iscsi_pf_params.num_queues = qedi->num_queues; qedi->pf_params.iscsi_pf_params.debug_mode = qedi_fw_debug; qedi->pf_params.iscsi_pf_params.two_msl_timer = 4000; + qedi->pf_params.iscsi_pf_params.tx_sws_timer = QED_TX_SWS_TIMER_DFLT; qedi->pf_params.iscsi_pf_params.max_fin_rt = 2; for (log_page_size = 0 ; log_page_size < 32 ; log_page_size++) { diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 4dcd0d37a521..07f8d19421ab 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -24,6 +24,8 @@ #include #include +#define QED_TX_SWS_TIMER_DFLT 500 + enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, DCBX_PROTOCOL_FCOE, -- cgit v1.2.3 From a64aa0a8b991e3cae61ee8322cf936c00068a5c1 Mon Sep 17 00:00:00 2001 From: Prabhakar Kushwaha Date: Mon, 4 Oct 2021 09:58:50 +0300 Subject: qed: Update the TCP active termination 2 MSL timer ("TIME_WAIT") Initialize 2 MSL timeout value used for the TCP TIME_WAIT state to non-zero default. This patch also removes magic number from qedi/qedi_main.c. Reviewed-by: Manish Rangankar Signed-off-by: Nikolay Assa Signed-off-by: Ariel Elior Signed-off-by: Shai Malin Signed-off-by: Omkar Kulkarni Signed-off-by: Prabhakar Kushwaha Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 1 + drivers/scsi/qedi/qedi_main.c | 2 +- include/linux/qed/qed_if.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index b2c0e522e51f..1d1d4caad680 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -115,6 +115,7 @@ qed_iwarp_init_fw_ramrod(struct qed_hwfn *p_hwfn, p_hwfn->p_rdma_info->iwarp.ll2_ooo_handle; p_ramrod->tcp.tx_sws_timer = cpu_to_le16(QED_TX_SWS_TIMER_DFLT); + p_ramrod->tcp.two_msl_timer = cpu_to_le32(QED_TWO_MSL_TIMER_DFLT); p_ramrod->tcp.max_fin_rt = QED_IWARP_MAX_FIN_RT_DEFAULT; return; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 8c2f32655424..1dec814d8788 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -865,7 +865,7 @@ static int qedi_set_iscsi_pf_param(struct qedi_ctx *qedi) qedi->pf_params.iscsi_pf_params.num_uhq_pages_in_ring = num_sq_pages; qedi->pf_params.iscsi_pf_params.num_queues = qedi->num_queues; qedi->pf_params.iscsi_pf_params.debug_mode = qedi_fw_debug; - qedi->pf_params.iscsi_pf_params.two_msl_timer = 4000; + qedi->pf_params.iscsi_pf_params.two_msl_timer = QED_TWO_MSL_TIMER_DFLT; qedi->pf_params.iscsi_pf_params.tx_sws_timer = QED_TX_SWS_TIMER_DFLT; qedi->pf_params.iscsi_pf_params.max_fin_rt = 2; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 07f8d19421ab..ad220d5da18f 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -25,6 +25,7 @@ #include #define QED_TX_SWS_TIMER_DFLT 500 +#define QED_TWO_MSL_TIMER_DFLT 4000 enum dcbx_protocol_type { DCBX_PROTOCOL_ISCSI, -- cgit v1.2.3 From a2c27a61b4335344c1bacaade61e9b2dc6e12a76 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 4 Oct 2021 12:03:28 +0100 Subject: net: phylink: add phylink_set_10g_modes() helper Add a helper for setting 10Gigabit modes, so we have one central place that sets all appropriate 10G modes for a driver. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 11 +++++++++++ include/linux/phylink.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 5a58c77d0002..b32774fd65f8 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -132,6 +132,17 @@ void phylink_set_port_modes(unsigned long *mask) } EXPORT_SYMBOL_GPL(phylink_set_port_modes); +void phylink_set_10g_modes(unsigned long *mask) +{ + phylink_set(mask, 10000baseT_Full); + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseER_Full); +} +EXPORT_SYMBOL_GPL(phylink_set_10g_modes); + static int phylink_is_empty_linkmode(const unsigned long *linkmode) { __ETHTOOL_DECLARE_LINK_MODE_MASK(tmp) = { 0, }; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 237291196ce2..f7b5ed06a815 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -484,6 +484,7 @@ int phylink_speed_up(struct phylink *pl); #define phylink_test(bm, mode) __phylink_do_bit(test_bit, bm, mode) void phylink_set_port_modes(unsigned long *bits); +void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, -- cgit v1.2.3 From 571e5c0efcb29c5dac8cf2949d3eed84ec43056c Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 19 May 2021 16:00:22 -0400 Subject: audit: add OPENAT2 record to list "how" info Since the openat2(2) syscall uses a struct open_how pointer to communicate its parameters they are not usefully recorded by the audit SYSCALL record's four existing arguments. Add a new audit record type OPENAT2 that reports the parameters in its third argument, struct open_how with fields oflag, mode and resolve. The new record in the context of an event would look like: time->Wed Mar 17 16:28:53 2021 type=PROCTITLE msg=audit(1616012933.531:184): proctitle= 73797363616C6C735F66696C652F6F70656E617432002F746D702F61756469742D 7465737473756974652D737641440066696C652D6F70656E617432 type=PATH msg=audit(1616012933.531:184): item=1 name="file-openat2" inode=29 dev=00:1f mode=0100600 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=CREATE cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 cap_frootid=0 type=PATH msg=audit(1616012933.531:184): item=0 name="/root/rgb/git/audit-testsuite/tests" inode=25 dev=00:1f mode=040700 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=PARENT cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 cap_frootid=0 type=CWD msg=audit(1616012933.531:184): cwd="/root/rgb/git/audit-testsuite/tests" type=OPENAT2 msg=audit(1616012933.531:184): oflag=0100302 mode=0600 resolve=0xa type=SYSCALL msg=audit(1616012933.531:184): arch=c000003e syscall=437 success=yes exit=4 a0=3 a1=7ffe315f1c53 a2=7ffe315f1550 a3=18 items=2 ppid=528 pid=540 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=ttyS0 ses=1 comm="openat2" exe="/root/rgb/git/audit-testsuite/tests/syscalls_file/openat2" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key="testsuite-1616012933-bjAUcEPO" Link: https://lore.kernel.org/r/d23fbb89186754487850367224b060e26f9b7181.1621363275.git.rgb@redhat.com Signed-off-by: Richard Guy Briggs Acked-by: Christian Brauner [PM: tweak subject, wrap example, move AUDIT_OPENAT2 to 1337] Signed-off-by: Paul Moore --- fs/open.c | 2 ++ include/linux/audit.h | 10 ++++++++++ include/uapi/linux/audit.h | 1 + kernel/audit.h | 2 ++ kernel/auditsc.c | 18 +++++++++++++++++- 5 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/open.c b/fs/open.c index daa324606a41..a7f6cab81267 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1248,6 +1248,8 @@ SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, if (err) return err; + audit_openat2_how(&tmp); + /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; diff --git a/include/linux/audit.h b/include/linux/audit.h index 5fbeeeb6b726..0e0eb4c0fa10 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -399,6 +399,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); +extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); @@ -495,6 +496,12 @@ static inline void audit_mmap_fd(int fd, int flags) __audit_mmap_fd(fd, flags); } +static inline void audit_openat2_how(struct open_how *how) +{ + if (unlikely(!audit_dummy_context())) + __audit_openat2_how(how); +} + static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) @@ -646,6 +653,9 @@ static inline void audit_log_capset(const struct cred *new, static inline void audit_mmap_fd(int fd, int flags) { } +static inline void audit_openat2_how(struct open_how *how) +{ } + static inline void audit_log_kern_module(char *name) { } diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..afa2472ad5d6 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,7 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_OPENAT2 1337 /* Record showing openat2 how args */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.h b/kernel/audit.h index d6a2c899a8db..3b64a97f6091 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -14,6 +14,7 @@ #include #include #include +#include // struct open_how /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). If we get more names we will allocate @@ -188,6 +189,7 @@ struct audit_context { int fd; int flags; } mmap; + struct open_how openat2; struct { int argc; } execve; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8c4335a35274..a4ba53f5354e 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -63,7 +63,7 @@ #include #include #include -#include +#include // struct open_how #include "audit.h" @@ -1306,6 +1306,12 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd, context->mmap.flags); break; + case AUDIT_OPENAT2: + audit_log_format(ab, "oflag=0%llo mode=0%llo resolve=0x%llx", + context->openat2.flags, + context->openat2.mode, + context->openat2.resolve); + break; case AUDIT_EXECVE: audit_log_execve_info(context, &ab); break; @@ -2536,6 +2542,16 @@ void __audit_mmap_fd(int fd, int flags) context->type = AUDIT_MMAP; } +void __audit_openat2_how(struct open_how *how) +{ + struct audit_context *context = audit_context(); + + context->openat2.flags = how->flags; + context->openat2.mode = how->mode; + context->openat2.resolve = how->resolve; + context->type = AUDIT_OPENAT2; +} + void __audit_log_kern_module(char *name) { struct audit_context *context = audit_context(); -- cgit v1.2.3 From 5249001d69a223811ad654884c6115d55158fd51 Mon Sep 17 00:00:00 2001 From: Vlad Buslov Date: Wed, 1 Sep 2021 19:05:02 +0300 Subject: net/mlx5: Bridge, mark reg_c1 when pushing VLAN On ingress VLAN push also assign value 0x7FE to reg_c1 tunnel id+opts bits (tunnel id 0, which is not a valid tunnel id, and option 0x7FE which was reserved by one of previous patches in the series). In following patch the reg value is matched on egress miss to restore the packet to its original state by removing the VLAN before passing it to the software data path. Signed-off-by: Vlad Buslov Reviewed-by: Paul Blakey Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/esw/bridge.c | 40 +++++++++++++++++++++- .../ethernet/mellanox/mlx5/core/esw/bridge_priv.h | 1 + include/linux/mlx5/eswitch.h | 9 +++++ 3 files changed, 49 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index 8361dfc0bf1a..439b67b4380f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -465,8 +465,10 @@ mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num)); if (vlan && vlan->pkt_reformat_push) { - flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; flow_act.pkt_reformat = vlan->pkt_reformat_push; + flow_act.modify_hdr = vlan->pkt_mod_hdr_push_mark; } else if (vlan) { MLX5_SET_TO_ONES(fte_match_param, rule_spec->match_criteria, outer_headers.cvlan_tag); @@ -845,6 +847,33 @@ mlx5_esw_bridge_vlan_pop_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_ vlan->pkt_reformat_pop = NULL; } +static int +mlx5_esw_bridge_vlan_push_mark_create(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; + struct mlx5_modify_hdr *pkt_mod_hdr; + + MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET); + MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_1); + MLX5_SET(set_action_in, action, offset, 8); + MLX5_SET(set_action_in, action, length, ESW_TUN_OPTS_BITS + ESW_TUN_ID_BITS); + MLX5_SET(set_action_in, action, data, ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN); + + pkt_mod_hdr = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_FDB, 1, action); + if (IS_ERR(pkt_mod_hdr)) + return PTR_ERR(pkt_mod_hdr); + + vlan->pkt_mod_hdr_push_mark = pkt_mod_hdr; + return 0; +} + +static void +mlx5_esw_bridge_vlan_push_mark_cleanup(struct mlx5_esw_bridge_vlan *vlan, struct mlx5_eswitch *esw) +{ + mlx5_modify_header_dealloc(esw->dev, vlan->pkt_mod_hdr_push_mark); + vlan->pkt_mod_hdr_push_mark = NULL; +} + static struct mlx5_esw_bridge_vlan * mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *port, struct mlx5_eswitch *esw) @@ -864,6 +893,10 @@ mlx5_esw_bridge_vlan_create(u16 vid, u16 flags, struct mlx5_esw_bridge_port *por err = mlx5_esw_bridge_vlan_push_create(vlan, esw); if (err) goto err_vlan_push; + + err = mlx5_esw_bridge_vlan_push_mark_create(vlan, esw); + if (err) + goto err_vlan_push_mark; } if (flags & BRIDGE_VLAN_INFO_UNTAGGED) { err = mlx5_esw_bridge_vlan_pop_create(vlan, esw); @@ -882,6 +915,9 @@ err_xa_insert: if (vlan->pkt_reformat_pop) mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); err_vlan_pop: + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); +err_vlan_push_mark: if (vlan->pkt_reformat_push) mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); err_vlan_push: @@ -908,6 +944,8 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan, if (vlan->pkt_reformat_pop) mlx5_esw_bridge_vlan_pop_cleanup(vlan, esw); + if (vlan->pkt_mod_hdr_push_mark) + mlx5_esw_bridge_vlan_push_mark_cleanup(vlan, esw); if (vlan->pkt_reformat_push) mlx5_esw_bridge_vlan_push_cleanup(vlan, esw); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h index 52964a82d6a6..878311fe950a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -49,6 +49,7 @@ struct mlx5_esw_bridge_vlan { struct list_head fdb_list; struct mlx5_pkt_reformat *pkt_reformat_push; struct mlx5_pkt_reformat *pkt_reformat_pop; + struct mlx5_modify_hdr *pkt_mod_hdr_push_mark; }; struct mlx5_esw_bridge_port { diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 4ab5c1fc1270..97afcea39a7b 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -130,11 +130,20 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, #define ESW_TUN_OPTS_MASK GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, ESW_TUN_OPTS_OFFSET) #define ESW_TUN_MASK GENMASK(31 - ESW_RESERVED_BITS, ESW_TUN_OFFSET) #define ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT 0 /* 0 is not a valid tunnel id */ +#define ESW_TUN_ID_BRIDGE_INGRESS_PUSH_VLAN ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT /* 0x7FF is a reserved mapping */ #define ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT GENMASK(ESW_TUN_OPTS_BITS - 1, 0) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT ((ESW_TUN_ID_SLOW_TABLE_GOTO_VPORT << ESW_TUN_OPTS_BITS) | \ ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT) #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK +/* 0x7FE is a reserved mapping for bridge ingress push vlan mark */ +#define ESW_TUN_OPTS_BRIDGE_INGRESS_PUSH_VLAN (ESW_TUN_OPTS_SLOW_TABLE_GOTO_VPORT - 1) +#define ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN ((ESW_TUN_ID_BRIDGE_INGRESS_PUSH_VLAN << \ + ESW_TUN_OPTS_BITS) | \ + ESW_TUN_OPTS_BRIDGE_INGRESS_PUSH_VLAN) +#define ESW_TUN_BRIDGE_INGRESS_PUSH_VLAN_MARK \ + GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ + ESW_TUN_OPTS_OFFSET + 1) u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); -- cgit v1.2.3 From 3663ad34bc707fc85492f4d83a313f5df84718d4 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 19 Aug 2021 16:18:57 +0300 Subject: net/mlx5: Shift control IRQ to the last index Control IRQ is the first IRQ vector. This complicates handling of completion irqs as we need to offset them by one. in the next patch, there are scenarios where completion and control EQs will share the same irq. for example: functions with single IRQ. To ease such scenarios, we shift control IRQ to the end of the irq array. Signed-off-by: Shay Drory Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/odp.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/eq.c | 9 +++++---- drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h | 2 -- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 10 +++++----- include/linux/mlx5/driver.h | 2 ++ 5 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index d0d98e584ebc..81147d774dd2 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1559,6 +1559,7 @@ int mlx5r_odp_create_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq) eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int; param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = MLX5_IB_NUM_PF_EQE, }; param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 605c8ecc3610..792e0d6aa861 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -632,6 +632,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_eq_notifier_register(dev, &table->cq_err_nb); param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = MLX5_NUM_CMD_EQE, .mask[0] = 1ull << MLX5_EVENT_TYPE_CMD, }; @@ -644,6 +645,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = MLX5_NUM_ASYNC_EQE, }; @@ -653,6 +655,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) goto err2; param = (struct mlx5_eq_param) { + .irq_index = MLX5_IRQ_EQ_CTRL, .nent = /* TODO: sriov max_vf + */ 1, .mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST, }; @@ -806,8 +809,8 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) ncomp_eqs = table->num_comp_eqs; nent = MLX5_COMP_EQ_SIZE; for (i = 0; i < ncomp_eqs; i++) { - int vecidx = i + MLX5_IRQ_VEC_COMP_BASE; struct mlx5_eq_param param = {}; + int vecidx = i; eq = kzalloc(sizeof(*eq), GFP_KERNEL); if (!eq) { @@ -953,9 +956,7 @@ static int set_rmap(struct mlx5_core_dev *mdev) goto err_out; } - vecidx = MLX5_IRQ_VEC_COMP_BASE; - for (; vecidx < eq_table->num_comp_eqs + MLX5_IRQ_VEC_COMP_BASE; - vecidx++) { + for (vecidx = 0; vecidx < eq_table->num_comp_eqs; vecidx++) { err = irq_cpu_rmap_add(eq_table->rmap, pci_irq_vector(mdev->pdev, vecidx)); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index abd024173c42..8116815663a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -8,8 +8,6 @@ #define MLX5_COMP_EQS_PER_SF 8 -#define MLX5_IRQ_EQ_CTRL (0) - struct mlx5_irq; int mlx5_irq_table_init(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 763c83a02380..a66144b54fc8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -194,15 +194,14 @@ static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) snprintf(name, MLX5_MAX_IRQ_NAME, "%s%d", pool->name, vecidx); } -static void irq_set_name(char *name, int vecidx) +static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) { - if (vecidx == 0) { + if (vecidx == pool->xa_num_irqs.max) { snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx); return; } - snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", - vecidx - MLX5_IRQ_VEC_COMP_BASE); + snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx); } static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) @@ -217,7 +216,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) return ERR_PTR(-ENOMEM); irq->irqn = pci_irq_vector(dev->pdev, i); if (!pool->name[0]) - irq_set_name(name, i); + irq_set_name(pool, name, i); else irq_sf_set_name(pool, name, i); ATOMIC_INIT_NOTIFIER_HEAD(&irq->nh); @@ -440,6 +439,7 @@ struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx, } pf_irq: pool = irq_table->pf_pool; + vecidx = (vecidx == MLX5_IRQ_EQ_CTRL) ? pool->xa_num_irqs.max : vecidx; irq = irq_pool_request_vector(pool, vecidx, affinity); out: if (IS_ERR(irq)) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e23417424373..0ca719c00824 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -59,6 +59,8 @@ #define MLX5_ADEV_NAME "mlx5_core" +#define MLX5_IRQ_EQ_CTRL (U8_MAX) + enum { MLX5_BOARD_ID_LEN = 64, }; -- cgit v1.2.3 From f891b7cdbdcda116fd26bbd706f91bd58567aa17 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sun, 1 Aug 2021 12:08:49 +0300 Subject: net/mlx5: Enable single IRQ for PCI Function Prior to this patch the driver requires two IRQs to function properly, one required IRQ for control and at least one required IRQ for IO. This requirement can be relaxed to one as the driver now allows sharing of IRQs, so control and IO EQs can share the same irq. This is needed for high scale amount of VFs. Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 26 +++++++++++++++++------ include/linux/mlx5/eq.h | 1 - 2 files changed, 19 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index a66144b54fc8..830444f927d4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -196,6 +196,12 @@ static void irq_sf_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) { + if (!pool->xa_num_irqs.max) { + /* in case we only have a single irq for the device */ + snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_combined%d", vecidx); + return; + } + if (vecidx == pool->xa_num_irqs.max) { snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_async%d", vecidx); return; @@ -204,6 +210,11 @@ static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx) snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx); } +static bool irq_pool_is_sf_pool(struct mlx5_irq_pool *pool) +{ + return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf")); +} + static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) { struct mlx5_core_dev *dev = pool->dev; @@ -215,7 +226,7 @@ static struct mlx5_irq *irq_request(struct mlx5_irq_pool *pool, int i) if (!irq) return ERR_PTR(-ENOMEM); irq->irqn = pci_irq_vector(dev->pdev, i); - if (!pool->name[0]) + if (!irq_pool_is_sf_pool(pool)) irq_set_name(pool, name, i); else irq_sf_set_name(pool, name, i); @@ -385,6 +396,9 @@ irq_pool_request_vector(struct mlx5_irq_pool *pool, int vecidx, if (IS_ERR(irq) || !affinity) goto unlock; cpumask_copy(irq->mask, affinity); + if (!irq_pool_is_sf_pool(pool) && !pool->xa_num_irqs.max && + cpumask_empty(irq->mask)) + cpumask_set_cpu(0, irq->mask); irq_set_affinity_hint(irq->irqn, irq->mask); unlock: mutex_unlock(&pool->lock); @@ -577,6 +591,8 @@ void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev) int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table) { + if (!table->pf_pool->xa_num_irqs.max) + return 1; return table->pf_pool->xa_num_irqs.max - table->pf_pool->xa_num_irqs.min; } @@ -592,19 +608,15 @@ int mlx5_irq_table_create(struct mlx5_core_dev *dev) if (mlx5_core_is_sf(dev)) return 0; - pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + - MLX5_IRQ_VEC_COMP_BASE; + pf_vec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() + 1; pf_vec = min_t(int, pf_vec, num_eqs); - if (pf_vec <= MLX5_IRQ_VEC_COMP_BASE) - return -ENOMEM; total_vec = pf_vec; if (mlx5_sf_max_functions(dev)) total_vec += MLX5_IRQ_CTRL_SF_MAX + MLX5_COMP_EQS_PER_SF * mlx5_sf_max_functions(dev); - total_vec = pci_alloc_irq_vectors(dev->pdev, MLX5_IRQ_VEC_COMP_BASE + 1, - total_vec, PCI_IRQ_MSIX); + total_vec = pci_alloc_irq_vectors(dev->pdev, 1, total_vec, PCI_IRQ_MSIX); if (total_vec < 0) return total_vec; pf_vec = min(pf_vec, total_vec); diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index cea6ecb4b73e..ea3ff5a8ced3 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -4,7 +4,6 @@ #ifndef MLX5_CORE_EQ_H #define MLX5_CORE_EQ_H -#define MLX5_IRQ_VEC_COMP_BASE 1 #define MLX5_NUM_CMD_EQE (32) #define MLX5_NUM_ASYNC_EQE (0x1000) #define MLX5_NUM_SPARE_EQE (0x80) -- cgit v1.2.3 From e68ce0faf29c7c268666e11e95bf27dca97d28b0 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 2 Sep 2021 14:47:48 +0200 Subject: mfd: hi6421-spmi-pmic: Cleanup drvdata to only include regmap There are lots of fields in struct hi6421_spmi_pmic that aren't used. As a matter of fact, only regmap is needed. So, drop the struct as a whole, and set regmap as the drvdata. Signed-off-by: Mauro Carvalho Chehab Acked-by: Mark Brown Acked-by: Greg Kroah-Hartman Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/1828cb783b1ebca0b98bf0b3077d8701adb228f7.1630586862.git.mchehab+huawei@kernel.org --- drivers/mfd/hi6421-spmi-pmic.c | 16 +++++----------- drivers/misc/hi6421v600-irq.c | 9 ++++----- drivers/regulator/hi6421v600-regulator.c | 10 +++++----- include/linux/mfd/hi6421-spmi-pmic.h | 25 ------------------------- 4 files changed, 14 insertions(+), 46 deletions(-) delete mode 100644 include/linux/mfd/hi6421-spmi-pmic.h (limited to 'include/linux') diff --git a/drivers/mfd/hi6421-spmi-pmic.c b/drivers/mfd/hi6421-spmi-pmic.c index 4f136826681b..c9c0c3d7011f 100644 --- a/drivers/mfd/hi6421-spmi-pmic.c +++ b/drivers/mfd/hi6421-spmi-pmic.c @@ -8,7 +8,6 @@ */ #include -#include #include #include #include @@ -30,19 +29,14 @@ static const struct regmap_config regmap_config = { static int hi6421_spmi_pmic_probe(struct spmi_device *sdev) { struct device *dev = &sdev->dev; + struct regmap *regmap; int ret; - struct hi6421_spmi_pmic *ddata; - ddata = devm_kzalloc(dev, sizeof(*ddata), GFP_KERNEL); - if (!ddata) - return -ENOMEM; - ddata->regmap = devm_regmap_init_spmi_ext(sdev, ®map_config); - if (IS_ERR(ddata->regmap)) - return PTR_ERR(ddata->regmap); + regmap = devm_regmap_init_spmi_ext(sdev, ®map_config); + if (IS_ERR(regmap)) + return PTR_ERR(regmap); - ddata->dev = dev; - - dev_set_drvdata(&sdev->dev, ddata); + dev_set_drvdata(&sdev->dev, regmap); ret = devm_mfd_add_devices(&sdev->dev, PLATFORM_DEVID_NONE, hi6421v600_devs, ARRAY_SIZE(hi6421v600_devs), diff --git a/drivers/misc/hi6421v600-irq.c b/drivers/misc/hi6421v600-irq.c index 08535e97ff43..1c763796cf1f 100644 --- a/drivers/misc/hi6421v600-irq.c +++ b/drivers/misc/hi6421v600-irq.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include @@ -220,7 +219,7 @@ static int hi6421v600_irq_probe(struct platform_device *pdev) struct platform_device *pmic_pdev; struct device *dev = &pdev->dev; struct hi6421v600_irq *priv; - struct hi6421_spmi_pmic *pmic; + struct regmap *regmap; unsigned int virq; int i, ret; @@ -229,8 +228,8 @@ static int hi6421v600_irq_probe(struct platform_device *pdev) * which should first set drvdata. If this doesn't happen, hit * a warn on and return. */ - pmic = dev_get_drvdata(pmic_dev); - if (WARN_ON(!pmic)) + regmap = dev_get_drvdata(pmic_dev); + if (WARN_ON(!regmap)) return -ENODEV; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -238,7 +237,7 @@ static int hi6421v600_irq_probe(struct platform_device *pdev) return -ENOMEM; priv->dev = dev; - priv->regmap = pmic->regmap; + priv->regmap = regmap; spin_lock_init(&priv->lock); diff --git a/drivers/regulator/hi6421v600-regulator.c b/drivers/regulator/hi6421v600-regulator.c index 662d87ae61cb..4671678f6b19 100644 --- a/drivers/regulator/hi6421v600-regulator.c +++ b/drivers/regulator/hi6421v600-regulator.c @@ -9,8 +9,8 @@ // Guodong Xu #include -#include #include +#include #include #include #include @@ -237,7 +237,7 @@ static int hi6421_spmi_regulator_probe(struct platform_device *pdev) struct hi6421_spmi_reg_priv *priv; struct hi6421_spmi_reg_info *info; struct device *dev = &pdev->dev; - struct hi6421_spmi_pmic *pmic; + struct regmap *regmap; struct regulator_dev *rdev; int i; @@ -246,8 +246,8 @@ static int hi6421_spmi_regulator_probe(struct platform_device *pdev) * which should first set drvdata. If this doesn't happen, hit * a warn on and return. */ - pmic = dev_get_drvdata(pmic_dev); - if (WARN_ON(!pmic)) + regmap = dev_get_drvdata(pmic_dev); + if (WARN_ON(!regmap)) return -ENODEV; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -261,7 +261,7 @@ static int hi6421_spmi_regulator_probe(struct platform_device *pdev) config.dev = pdev->dev.parent; config.driver_data = priv; - config.regmap = pmic->regmap; + config.regmap = regmap; rdev = devm_regulator_register(dev, &info->desc, &config); if (IS_ERR(rdev)) { diff --git a/include/linux/mfd/hi6421-spmi-pmic.h b/include/linux/mfd/hi6421-spmi-pmic.h deleted file mode 100644 index e5b8dbf828b6..000000000000 --- a/include/linux/mfd/hi6421-spmi-pmic.h +++ /dev/null @@ -1,25 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Header file for device driver Hi6421 PMIC - * - * Copyright (c) 2013 Linaro Ltd. - * Copyright (C) 2011 Hisilicon. - * Copyright (c) 2020-2021 Huawei Technologies Co., Ltd - * - * Guodong Xu - */ - -#ifndef __HISI_PMIC_H -#define __HISI_PMIC_H - -#include -#include - -struct hi6421_spmi_pmic { - struct resource *res; - struct device *dev; - void __iomem *regs; - struct regmap *regmap; -}; - -#endif /* __HISI_PMIC_H */ -- cgit v1.2.3 From c1baf6c591e6901d3422d7a0d0d32ccf29883edf Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Sun, 12 Sep 2021 21:17:15 +0300 Subject: usb: phy: tegra: Support OTG mode programming Support programming USB PHY into OTG mode. Signed-off-by: Dmitry Osipenko Acked-by: Thierry Reding Link: https://lore.kernel.org/r/20210912181718.1328-5-digetx@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/phy/phy-tegra-usb.c | 198 +++++++++++++++++++++++++++++++++++++- include/linux/usb/tegra_usb_phy.h | 5 + 2 files changed, 198 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c index c0f432d509aa..68cd4b68e3a2 100644 --- a/drivers/usb/phy/phy-tegra-usb.c +++ b/drivers/usb/phy/phy-tegra-usb.c @@ -63,6 +63,10 @@ #define A_VBUS_VLD_WAKEUP_EN BIT(30) #define USB_PHY_VBUS_WAKEUP_ID 0x408 +#define ID_INT_EN BIT(0) +#define ID_CHG_DET BIT(1) +#define VBUS_WAKEUP_INT_EN BIT(8) +#define VBUS_WAKEUP_CHG_DET BIT(9) #define VBUS_WAKEUP_STS BIT(10) #define VBUS_WAKEUP_WAKEUP_EN BIT(30) @@ -158,6 +162,10 @@ #define USB_USBMODE_HOST (3 << 0) #define USB_USBMODE_DEVICE (2 << 0) +#define PMC_USB_AO 0xf0 +#define VBUS_WAKEUP_PD_P0 BIT(2) +#define ID_PD_P0 BIT(3) + static DEFINE_SPINLOCK(utmip_pad_lock); static unsigned int utmip_pad_count; @@ -533,13 +541,14 @@ static int utmi_phy_power_on(struct tegra_usb_phy *phy) val &= ~USB_WAKE_ON_RESUME_EN; writel_relaxed(val, base + USB_SUSP_CTRL); - if (phy->mode == USB_DR_MODE_PERIPHERAL) { + if (phy->mode != USB_DR_MODE_HOST) { val = readl_relaxed(base + USB_SUSP_CTRL); val &= ~(USB_WAKE_ON_CNNT_EN_DEV | USB_WAKE_ON_DISCON_EN_DEV); writel_relaxed(val, base + USB_SUSP_CTRL); val = readl_relaxed(base + USB_PHY_VBUS_WAKEUP_ID); val &= ~VBUS_WAKEUP_WAKEUP_EN; + val &= ~(ID_CHG_DET | VBUS_WAKEUP_CHG_DET); writel_relaxed(val, base + USB_PHY_VBUS_WAKEUP_ID); val = readl_relaxed(base + USB_PHY_VBUS_SENSORS); @@ -687,9 +696,10 @@ static int utmi_phy_power_off(struct tegra_usb_phy *phy) * Ask VBUS sensor to generate wake event once cable is * connected. */ - if (phy->mode == USB_DR_MODE_PERIPHERAL) { + if (phy->mode != USB_DR_MODE_HOST) { val = readl_relaxed(base + USB_PHY_VBUS_WAKEUP_ID); val |= VBUS_WAKEUP_WAKEUP_EN; + val &= ~(ID_CHG_DET | VBUS_WAKEUP_CHG_DET); writel_relaxed(val, base + USB_PHY_VBUS_WAKEUP_ID); val = readl_relaxed(base + USB_PHY_VBUS_SENSORS); @@ -893,6 +903,7 @@ static void tegra_usb_phy_shutdown(struct usb_phy *u_phy) if (WARN_ON(!phy->freq)) return; + usb_phy_set_wakeup(u_phy, false); tegra_usb_phy_power_off(phy); if (!phy->is_ulpi_phy) @@ -904,26 +915,146 @@ static void tegra_usb_phy_shutdown(struct usb_phy *u_phy) phy->freq = NULL; } +static irqreturn_t tegra_usb_phy_isr(int irq, void *data) +{ + u32 val, int_mask = ID_CHG_DET | VBUS_WAKEUP_CHG_DET; + struct tegra_usb_phy *phy = data; + void __iomem *base = phy->regs; + + /* + * The PHY interrupt also wakes the USB controller driver since + * interrupt is shared. We don't do anything in the PHY driver, + * so just clear the interrupt. + */ + val = readl_relaxed(base + USB_PHY_VBUS_WAKEUP_ID); + writel_relaxed(val, base + USB_PHY_VBUS_WAKEUP_ID); + + return val & int_mask ? IRQ_HANDLED : IRQ_NONE; +} + static int tegra_usb_phy_set_wakeup(struct usb_phy *u_phy, bool enable) { struct tegra_usb_phy *phy = to_tegra_usb_phy(u_phy); + void __iomem *base = phy->regs; + int ret = 0; + u32 val; + + if (phy->wakeup_enabled && phy->mode != USB_DR_MODE_HOST && + phy->irq > 0) { + disable_irq(phy->irq); + + val = readl_relaxed(base + USB_PHY_VBUS_WAKEUP_ID); + val &= ~(ID_INT_EN | VBUS_WAKEUP_INT_EN); + writel_relaxed(val, base + USB_PHY_VBUS_WAKEUP_ID); + + enable_irq(phy->irq); + + free_irq(phy->irq, phy); + + phy->wakeup_enabled = false; + } + + if (enable && phy->mode != USB_DR_MODE_HOST && phy->irq > 0) { + ret = request_irq(phy->irq, tegra_usb_phy_isr, IRQF_SHARED, + dev_name(phy->u_phy.dev), phy); + if (!ret) { + disable_irq(phy->irq); + + /* + * USB clock will be resumed once wake event will be + * generated. The ID-change event requires to have + * interrupts enabled, otherwise it won't be generated. + */ + val = readl_relaxed(base + USB_PHY_VBUS_WAKEUP_ID); + val |= ID_INT_EN | VBUS_WAKEUP_INT_EN; + writel_relaxed(val, base + USB_PHY_VBUS_WAKEUP_ID); + + enable_irq(phy->irq); + } else { + dev_err(phy->u_phy.dev, + "Failed to request interrupt: %d", ret); + enable = false; + } + } phy->wakeup_enabled = enable; - return 0; + return ret; } static int tegra_usb_phy_set_suspend(struct usb_phy *u_phy, int suspend) { struct tegra_usb_phy *phy = to_tegra_usb_phy(u_phy); + int ret; if (WARN_ON(!phy->freq)) return -EINVAL; + /* + * PHY is sharing IRQ with the CI driver, hence here we either + * disable interrupt for both PHY and CI or for CI only. The + * interrupt needs to be disabled while hardware is reprogrammed + * because interrupt touches the programmed registers, and thus, + * there could be a race condition. + */ + if (phy->irq > 0) + disable_irq(phy->irq); + if (suspend) - return tegra_usb_phy_power_off(phy); + ret = tegra_usb_phy_power_off(phy); else - return tegra_usb_phy_power_on(phy); + ret = tegra_usb_phy_power_on(phy); + + if (phy->irq > 0) + enable_irq(phy->irq); + + return ret; +} + +static int tegra_usb_phy_configure_pmc(struct tegra_usb_phy *phy) +{ + int err, val = 0; + + /* older device-trees don't have PMC regmap */ + if (!phy->pmc_regmap) + return 0; + + /* + * Tegra20 has a different layout of PMC USB register bits and AO is + * enabled by default after system reset on Tegra20, so assume nothing + * to do on Tegra20. + */ + if (!phy->soc_config->requires_pmc_ao_power_up) + return 0; + + /* enable VBUS wake-up detector */ + if (phy->mode != USB_DR_MODE_HOST) + val |= VBUS_WAKEUP_PD_P0 << phy->instance * 4; + + /* enable ID-pin ACC detector for OTG mode switching */ + if (phy->mode == USB_DR_MODE_OTG) + val |= ID_PD_P0 << phy->instance * 4; + + /* disable detectors to reset them */ + err = regmap_set_bits(phy->pmc_regmap, PMC_USB_AO, val); + if (err) { + dev_err(phy->u_phy.dev, "Failed to disable PMC AO: %d\n", err); + return err; + } + + usleep_range(10, 100); + + /* enable detectors */ + err = regmap_clear_bits(phy->pmc_regmap, PMC_USB_AO, val); + if (err) { + dev_err(phy->u_phy.dev, "Failed to enable PMC AO: %d\n", err); + return err; + } + + /* detectors starts to work after 10ms */ + usleep_range(10000, 15000); + + return 0; } static int tegra_usb_phy_init(struct usb_phy *u_phy) @@ -967,6 +1098,10 @@ static int tegra_usb_phy_init(struct usb_phy *u_phy) goto disable_vbus; } + err = tegra_usb_phy_configure_pmc(phy); + if (err) + goto close_phy; + err = tegra_usb_phy_power_on(phy); if (err) goto close_phy; @@ -1135,11 +1270,56 @@ static int utmi_phy_probe(struct tegra_usb_phy *tegra_phy, return 0; } +static void tegra_usb_phy_put_pmc_device(void *dev) +{ + put_device(dev); +} + +static int tegra_usb_phy_parse_pmc(struct device *dev, + struct tegra_usb_phy *phy) +{ + struct platform_device *pmc_pdev; + struct of_phandle_args args; + int err; + + err = of_parse_phandle_with_fixed_args(dev->of_node, "nvidia,pmc", + 1, 0, &args); + if (err) { + if (err != -ENOENT) + return err; + + dev_warn_once(dev, "nvidia,pmc is missing, please update your device-tree\n"); + return 0; + } + + pmc_pdev = of_find_device_by_node(args.np); + of_node_put(args.np); + if (!pmc_pdev) + return -ENODEV; + + err = devm_add_action_or_reset(dev, tegra_usb_phy_put_pmc_device, + &pmc_pdev->dev); + if (err) + return err; + + if (!platform_get_drvdata(pmc_pdev)) + return -EPROBE_DEFER; + + phy->pmc_regmap = dev_get_regmap(&pmc_pdev->dev, "usb_sleepwalk"); + if (!phy->pmc_regmap) + return -EINVAL; + + phy->instance = args.args[0]; + + return 0; +} + static const struct tegra_phy_soc_config tegra20_soc_config = { .utmi_pll_config_in_car_module = false, .has_hostpc = false, .requires_usbmode_setup = false, .requires_extra_tuning_parameters = false, + .requires_pmc_ao_power_up = false, }; static const struct tegra_phy_soc_config tegra30_soc_config = { @@ -1147,6 +1327,7 @@ static const struct tegra_phy_soc_config tegra30_soc_config = { .has_hostpc = true, .requires_usbmode_setup = true, .requires_extra_tuning_parameters = true, + .requires_pmc_ao_power_up = true, }; static const struct of_device_id tegra_usb_phy_id_table[] = { @@ -1172,6 +1353,7 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return -ENOMEM; tegra_phy->soc_config = of_device_get_match_data(&pdev->dev); + tegra_phy->irq = platform_get_irq_optional(pdev, 0); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!res) { @@ -1215,6 +1397,12 @@ static int tegra_usb_phy_probe(struct platform_device *pdev) return err; } + err = tegra_usb_phy_parse_pmc(&pdev->dev, tegra_phy); + if (err) { + dev_err_probe(&pdev->dev, err, "Failed to get PMC regmap\n"); + return err; + } + phy_type = of_usb_get_phy_mode(np); switch (phy_type) { case USBPHY_INTERFACE_MODE_UTMI: diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h index fd1c9f6a4e37..d3e65eb9e16f 100644 --- a/include/linux/usb/tegra_usb_phy.h +++ b/include/linux/usb/tegra_usb_phy.h @@ -18,6 +18,7 @@ #include #include +#include #include #include @@ -30,6 +31,7 @@ * enter host mode * requires_extra_tuning_parameters: true if xcvr_hsslew, hssquelch_level * and hsdiscon_level should be set for adequate signal quality + * requires_pmc_ao_power_up: true if USB AO is powered down by default */ struct tegra_phy_soc_config { @@ -37,6 +39,7 @@ struct tegra_phy_soc_config { bool has_hostpc; bool requires_usbmode_setup; bool requires_extra_tuning_parameters; + bool requires_pmc_ao_power_up; }; struct tegra_utmip_config { @@ -62,6 +65,7 @@ enum tegra_usb_phy_port_speed { struct tegra_xtal_freq; struct tegra_usb_phy { + int irq; int instance; const struct tegra_xtal_freq *freq; void __iomem *regs; @@ -70,6 +74,7 @@ struct tegra_usb_phy { struct clk *pll_u; struct clk *pad_clk; struct regulator *vbus; + struct regmap *pmc_regmap; enum usb_dr_mode mode; void *config; const struct tegra_phy_soc_config *soc_config; -- cgit v1.2.3 From 1e4071f6282b3323435b02b1719bcfbfe1b57150 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 24 Sep 2021 07:12:42 -0500 Subject: ipmi: Export ipmb_checksum() It will be needed by the upcoming ipmb direct addressing. Signed-off-by: Corey Minyard Tested-by: Andrew Manley Reviewed-by: Andrew Manley --- drivers/char/ipmi/ipmi_msghandler.c | 3 ++- include/linux/ipmi.h | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 13988f88f1b0..ad1a8fc379b9 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -1710,7 +1710,7 @@ int ipmi_unregister_for_cmd(struct ipmi_user *user, } EXPORT_SYMBOL(ipmi_unregister_for_cmd); -static unsigned char +unsigned char ipmb_checksum(unsigned char *data, int size) { unsigned char csum = 0; @@ -1720,6 +1720,7 @@ ipmb_checksum(unsigned char *data, int size) return -csum; } +EXPORT_SYMBOL(ipmb_checksum); static inline void format_ipmb_msg(struct ipmi_smi_msg *smi_msg, struct kernel_ipmi_msg *msg, diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h index 52850a02a3d0..163831a087ef 100644 --- a/include/linux/ipmi.h +++ b/include/linux/ipmi.h @@ -335,4 +335,7 @@ extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data); #define GET_DEVICE_ID_MAX_RETRY 5 +/* Helper function for computing the IPMB checksum of some data. */ +unsigned char ipmb_checksum(unsigned char *data, int size); + #endif /* __LINUX_IPMI_H */ -- cgit v1.2.3 From 059747c245f0e9af5e109eece7d3414dbe08d513 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 24 Sep 2021 11:42:56 -0500 Subject: ipmi: Add support for IPMB direct messages An application has come up that has a device sitting right on the IPMB that would like to communicate with the BMC on the IPMB using normal IPMI commands. Sending these commands and handling the responses is easy enough, no modifications are needed to the IPMI infrastructure. But if this is an application that also needs to receive IPMB commands and respond, some way is needed to handle these incoming commands and send the responses. Currently, the IPMI message handler only sends commands to the interface and only receives responses from interface. This change extends the interface to receive commands/responses and send commands/responses. These are formatted differently in support of receiving/sending IPMB messages directly. Signed-off-by: Corey Minyard Tested-by: Andrew Manley Reviewed-by: Andrew Manley --- drivers/char/ipmi/ipmi_msghandler.c | 288 +++++++++++++++++++++++++++++++----- include/linux/ipmi_smi.h | 59 ++++++++ include/uapi/linux/ipmi.h | 14 ++ 3 files changed, 328 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index ad1a8fc379b9..a60201d3f735 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -653,6 +653,11 @@ static int is_ipmb_bcast_addr(struct ipmi_addr *addr) return addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE; } +static int is_ipmb_direct_addr(struct ipmi_addr *addr) +{ + return addr->addr_type == IPMI_IPMB_DIRECT_ADDR_TYPE; +} + static void free_recv_msg_list(struct list_head *q) { struct ipmi_recv_msg *msg, *msg2; @@ -805,6 +810,17 @@ ipmi_addr_equal(struct ipmi_addr *addr1, struct ipmi_addr *addr2) && (ipmb_addr1->lun == ipmb_addr2->lun)); } + if (is_ipmb_direct_addr(addr1)) { + struct ipmi_ipmb_direct_addr *daddr1 + = (struct ipmi_ipmb_direct_addr *) addr1; + struct ipmi_ipmb_direct_addr *daddr2 + = (struct ipmi_ipmb_direct_addr *) addr2; + + return daddr1->slave_addr == daddr2->slave_addr && + daddr1->rq_lun == daddr2->rq_lun && + daddr1->rs_lun == daddr2->rs_lun; + } + if (is_lan_addr(addr1)) { struct ipmi_lan_addr *lan_addr1 = (struct ipmi_lan_addr *) addr1; @@ -843,6 +859,23 @@ int ipmi_validate_addr(struct ipmi_addr *addr, int len) return 0; } + if (is_ipmb_direct_addr(addr)) { + struct ipmi_ipmb_direct_addr *daddr = (void *) addr; + + if (addr->channel != 0) + return -EINVAL; + if (len < sizeof(struct ipmi_ipmb_direct_addr)) + return -EINVAL; + + if (daddr->slave_addr & 0x01) + return -EINVAL; + if (daddr->rq_lun >= 4) + return -EINVAL; + if (daddr->rs_lun >= 4) + return -EINVAL; + return 0; + } + if (is_lan_addr(addr)) { if (len < sizeof(struct ipmi_lan_addr)) return -EINVAL; @@ -862,6 +895,9 @@ unsigned int ipmi_addr_length(int addr_type) || (addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)) return sizeof(struct ipmi_ipmb_addr); + if (addr_type == IPMI_IPMB_DIRECT_ADDR_TYPE) + return sizeof(struct ipmi_ipmb_direct_addr); + if (addr_type == IPMI_LAN_ADDR_TYPE) return sizeof(struct ipmi_lan_addr); @@ -2052,6 +2088,58 @@ out_err: return rv; } +static int i_ipmi_req_ipmb_direct(struct ipmi_smi *intf, + struct ipmi_addr *addr, + long msgid, + struct kernel_ipmi_msg *msg, + struct ipmi_smi_msg *smi_msg, + struct ipmi_recv_msg *recv_msg, + unsigned char source_lun) +{ + struct ipmi_ipmb_direct_addr *daddr; + bool is_cmd = !(recv_msg->msg.netfn & 0x1); + + if (!(intf->handlers->flags & IPMI_SMI_CAN_HANDLE_IPMB_DIRECT)) + return -EAFNOSUPPORT; + + /* Responses must have a completion code. */ + if (!is_cmd && msg->data_len < 1) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EINVAL; + } + + if ((msg->data_len + 4) > IPMI_MAX_MSG_LENGTH) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EMSGSIZE; + } + + daddr = (struct ipmi_ipmb_direct_addr *) addr; + if (daddr->rq_lun > 3 || daddr->rs_lun > 3) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EINVAL; + } + + smi_msg->type = IPMI_SMI_MSG_TYPE_IPMB_DIRECT; + smi_msg->msgid = msgid; + + if (is_cmd) { + smi_msg->data[0] = msg->netfn << 2 | daddr->rs_lun; + smi_msg->data[2] = recv_msg->msgid << 2 | daddr->rq_lun; + } else { + smi_msg->data[0] = msg->netfn << 2 | daddr->rq_lun; + smi_msg->data[2] = recv_msg->msgid << 2 | daddr->rs_lun; + } + smi_msg->data[1] = daddr->slave_addr; + smi_msg->data[3] = msg->cmd; + + memcpy(smi_msg->data + 4, msg->data, msg->data_len); + smi_msg->data_size = msg->data_len + 4; + + smi_msg->user_data = recv_msg; + + return 0; +} + static int i_ipmi_req_lan(struct ipmi_smi *intf, struct ipmi_addr *addr, long msgid, @@ -2241,6 +2329,9 @@ static int i_ipmi_request(struct ipmi_user *user, rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg, source_address, source_lun, retries, retry_time_ms); + } else if (is_ipmb_direct_addr(addr)) { + rv = i_ipmi_req_ipmb_direct(intf, addr, msgid, msg, smi_msg, + recv_msg, source_lun); } else if (is_lan_addr(addr)) { rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg, source_lun, retries, retry_time_ms); @@ -3802,6 +3893,123 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf, return rv; } +static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf, + struct ipmi_smi_msg *msg) +{ + struct cmd_rcvr *rcvr; + int rv = 0; + struct ipmi_user *user = NULL; + struct ipmi_ipmb_direct_addr *daddr; + struct ipmi_recv_msg *recv_msg; + unsigned char netfn = msg->rsp[0] >> 2; + unsigned char cmd = msg->rsp[3]; + + rcu_read_lock(); + /* We always use channel 0 for direct messages. */ + rcvr = find_cmd_rcvr(intf, netfn, cmd, 0); + if (rcvr) { + user = rcvr->user; + kref_get(&user->refcount); + } else + user = NULL; + rcu_read_unlock(); + + if (user == NULL) { + /* We didn't find a user, deliver an error response. */ + ipmi_inc_stat(intf, unhandled_commands); + + msg->data[0] = ((netfn + 1) << 2) | (msg->rsp[4] & 0x3); + msg->data[1] = msg->rsp[2]; + msg->data[2] = msg->rsp[4] & ~0x3; + msg->data[3] = cmd; + msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE; + msg->data_size = 5; + + rcu_read_lock(); + if (!intf->in_shutdown) { + smi_send(intf, intf->handlers, msg, 0); + /* + * We used the message, so return the value + * that causes it to not be freed or + * queued. + */ + rv = -1; + } + rcu_read_unlock(); + } else { + recv_msg = ipmi_alloc_recv_msg(); + if (!recv_msg) { + /* + * We couldn't allocate memory for the + * message, so requeue it for handling + * later. + */ + rv = 1; + kref_put(&user->refcount, free_user); + } else { + /* Extract the source address from the data. */ + daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr; + daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE; + daddr->channel = 0; + daddr->slave_addr = msg->rsp[1]; + daddr->rs_lun = msg->rsp[0] & 3; + daddr->rq_lun = msg->rsp[2] & 3; + + /* + * Extract the rest of the message information + * from the IPMB header. + */ + recv_msg->user = user; + recv_msg->recv_type = IPMI_CMD_RECV_TYPE; + recv_msg->msgid = (msg->rsp[2] >> 2); + recv_msg->msg.netfn = msg->rsp[0] >> 2; + recv_msg->msg.cmd = msg->rsp[3]; + recv_msg->msg.data = recv_msg->msg_data; + + recv_msg->msg.data_len = msg->rsp_size - 4; + memcpy(recv_msg->msg_data, msg->rsp + 4, + msg->rsp_size - 4); + if (deliver_response(intf, recv_msg)) + ipmi_inc_stat(intf, unhandled_commands); + else + ipmi_inc_stat(intf, handled_commands); + } + } + + return rv; +} + +static int handle_ipmb_direct_rcv_rsp(struct ipmi_smi *intf, + struct ipmi_smi_msg *msg) +{ + struct ipmi_recv_msg *recv_msg; + struct ipmi_ipmb_direct_addr *daddr; + + recv_msg = (struct ipmi_recv_msg *) msg->user_data; + if (recv_msg == NULL) { + dev_warn(intf->si_dev, + "IPMI message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); + return 0; + } + + recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE; + recv_msg->msgid = msg->msgid; + daddr = (struct ipmi_ipmb_direct_addr *) &recv_msg->addr; + daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE; + daddr->channel = 0; + daddr->slave_addr = msg->rsp[1]; + daddr->rq_lun = msg->rsp[0] & 3; + daddr->rs_lun = msg->rsp[2] & 3; + recv_msg->msg.netfn = msg->rsp[0] >> 2; + recv_msg->msg.cmd = msg->rsp[3]; + memcpy(recv_msg->msg_data, &msg->rsp[4], msg->rsp_size - 4); + recv_msg->msg.data = recv_msg->msg_data; + recv_msg->msg.data_len = msg->rsp_size - 4; + deliver_local_response(intf, recv_msg); + + return 0; +} + static int handle_lan_get_msg_rsp(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { @@ -4227,18 +4435,40 @@ static int handle_bmc_rsp(struct ipmi_smi *intf, static int handle_one_recv_msg(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { - int requeue; + int requeue = 0; int chan; + unsigned char cc; + bool is_cmd = !((msg->rsp[0] >> 2) & 1); pr_debug("Recv: %*ph\n", msg->rsp_size, msg->rsp); - if ((msg->data_size >= 2) + if (msg->rsp_size < 2) { + /* Message is too small to be correct. */ + dev_warn(intf->si_dev, + "BMC returned too small a message for netfn %x cmd %x, got %d bytes\n", + (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp_size); + +return_unspecified: + /* Generate an error response for the message. */ + msg->rsp[0] = msg->data[0] | (1 << 2); + msg->rsp[1] = msg->data[1]; + msg->rsp[2] = IPMI_ERR_UNSPECIFIED; + msg->rsp_size = 3; + } else if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { + /* commands must have at least 3 bytes, responses 4. */ + if (is_cmd && (msg->rsp_size < 3)) { + ipmi_inc_stat(intf, invalid_commands); + goto out; + } + if (!is_cmd && (msg->rsp_size < 4)) + goto return_unspecified; + } else if ((msg->data_size >= 2) && (msg->data[0] == (IPMI_NETFN_APP_REQUEST << 2)) && (msg->data[1] == IPMI_SEND_MSG_CMD) && (msg->user_data == NULL)) { if (intf->in_shutdown) - goto free_msg; + goto out; /* * This is the local response to a command send, start @@ -4273,21 +4503,6 @@ static int handle_one_recv_msg(struct ipmi_smi *intf, } else /* The message was sent, start the timer. */ intf_start_seq_timer(intf, msg->msgid); -free_msg: - requeue = 0; - goto out; - - } else if (msg->rsp_size < 2) { - /* Message is too small to be correct. */ - dev_warn(intf->si_dev, - "BMC returned too small a message for netfn %x cmd %x, got %d bytes\n", - (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp_size); - - /* Generate an error response for the message. */ - msg->rsp[0] = msg->data[0] | (1 << 2); - msg->rsp[1] = msg->data[1]; - msg->rsp[2] = IPMI_ERR_UNSPECIFIED; - msg->rsp_size = 3; } else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1)) || (msg->rsp[1] != msg->data[1])) { /* @@ -4299,39 +4514,46 @@ free_msg: (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp[0] >> 2, msg->rsp[1]); - /* Generate an error response for the message. */ - msg->rsp[0] = msg->data[0] | (1 << 2); - msg->rsp[1] = msg->data[1]; - msg->rsp[2] = IPMI_ERR_UNSPECIFIED; - msg->rsp_size = 3; + goto return_unspecified; } - if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) - && (msg->rsp[1] == IPMI_SEND_MSG_CMD) - && (msg->user_data != NULL)) { + if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { + if ((msg->data[0] >> 2) & 1) { + /* It's a response to a sent response. */ + chan = 0; + cc = msg->rsp[4]; + goto process_response_response; + } + if (is_cmd) + requeue = handle_ipmb_direct_rcv_cmd(intf, msg); + else + requeue = handle_ipmb_direct_rcv_rsp(intf, msg); + } else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) + && (msg->rsp[1] == IPMI_SEND_MSG_CMD) + && (msg->user_data != NULL)) { /* * It's a response to a response we sent. For this we * deliver a send message response to the user. */ - struct ipmi_recv_msg *recv_msg = msg->user_data; - - requeue = 0; - if (msg->rsp_size < 2) - /* Message is too small to be correct. */ - goto out; + struct ipmi_recv_msg *recv_msg; chan = msg->data[2] & 0x0f; if (chan >= IPMI_MAX_CHANNELS) /* Invalid channel number */ goto out; + cc = msg->rsp[2]; +process_response_response: + recv_msg = msg->user_data; + + requeue = 0; if (!recv_msg) goto out; recv_msg->recv_type = IPMI_RESPONSE_RESPONSE_TYPE; recv_msg->msg.data = recv_msg->msg_data; + recv_msg->msg_data[0] = cc; recv_msg->msg.data_len = 1; - recv_msg->msg_data[0] = msg->rsp[2]; deliver_local_response(intf, recv_msg); } else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) && (msg->rsp[1] == IPMI_GET_MSG_CMD)) { diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index deec18b8944a..9277d21c2690 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -38,6 +38,59 @@ struct ipmi_smi; #define IPMI_WATCH_MASK_CHECK_WATCHDOG (1 << 1) #define IPMI_WATCH_MASK_CHECK_COMMANDS (1 << 2) +/* + * SMI messages + * + * When communicating with an SMI, messages come in two formats: + * + * * Normal (to a BMC over a BMC interface) + * + * * IPMB (over a IPMB to another MC) + * + * When normal, commands are sent using the format defined by a + * standard message over KCS (NetFn must be even): + * + * +-----------+-----+------+ + * | NetFn/LUN | Cmd | Data | + * +-----------+-----+------+ + * + * And responses, similarly, with an completion code added (NetFn must + * be odd): + * + * +-----------+-----+------+------+ + * | NetFn/LUN | Cmd | CC | Data | + * +-----------+-----+------+------+ + * + * With normal messages, only commands are sent and only responses are + * received. + * + * In IPMB mode, we are acting as an IPMB device. Commands will be in + * the following format (NetFn must be even): + * + * +-------------+------+-------------+-----+------+ + * | NetFn/rsLUN | Addr | rqSeq/rqLUN | Cmd | Data | + * +-------------+------+-------------+-----+------+ + * + * Responses will using the following format: + * + * +-------------+------+-------------+-----+------+------+ + * | NetFn/rqLUN | Addr | rqSeq/rsLUN | Cmd | CC | Data | + * +-------------+------+-------------+-----+------+------+ + * + * This is similar to the format defined in the IPMB manual section + * 2.11.1 with the checksums and the first address removed. Also, the + * address is always the remote address. + * + * IPMB messages can be commands and responses in both directions. + * Received commands are handled as received commands from the message + * queue. + */ + +enum ipmi_smi_msg_type { + IPMI_SMI_MSG_TYPE_NORMAL = 0, + IPMI_SMI_MSG_TYPE_IPMB_DIRECT +}; + /* * Messages to/from the lower layer. The smi interface will take one * of these to send. After the send has occurred and a response has @@ -54,6 +107,8 @@ struct ipmi_smi; struct ipmi_smi_msg { struct list_head link; + enum ipmi_smi_msg_type type; + long msgid; void *user_data; @@ -73,6 +128,10 @@ struct ipmi_smi_msg { struct ipmi_smi_handlers { struct module *owner; + /* Capabilities of the SMI. */ +#define IPMI_SMI_CAN_HANDLE_IPMB_DIRECT (1 << 0) + unsigned int flags; + /* * The low-level interface cannot start sending messages to * the upper layer until this function is called. This may diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index 007e65f9243b..966c3070959b 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -80,6 +80,20 @@ struct ipmi_ipmb_addr { unsigned char lun; }; +/* + * Used for messages received directly from an IPMB that have not gone + * through a MC. This is for systems that sit right on an IPMB so + * they can receive commands and respond to them. + */ +#define IPMI_IPMB_DIRECT_ADDR_TYPE 0x81 +struct ipmi_ipmb_direct_addr { + int addr_type; + short channel; + unsigned char slave_addr; + unsigned char rs_lun; + unsigned char rq_lun; +}; + /* * A LAN Address. This is an address to/from a LAN interface bridged * by the BMC, not an address actually out on the LAN. -- cgit v1.2.3 From 549017aa1bb7ec19a1e24e7f65480a1c2e76b90e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 5 Oct 2021 13:52:42 +0200 Subject: netlink: remove netlink_broadcast_filtered No users in tree since commit a3498436b3a0 ("netns: restrict uevents"), so remove this functionality. Cc: Christian Brauner Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netlink.h | 4 ---- net/netlink/af_netlink.c | 23 ++--------------------- 2 files changed, 2 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 61b1c7fcc401..1ec631838af9 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -156,10 +156,6 @@ bool netlink_strict_get_check(struct sk_buff *skb); int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); -int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, - __u32 portid, __u32 group, gfp_t allocation, - int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), - void *filter_data); int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); int netlink_register_notifier(struct notifier_block *nb); int netlink_unregister_notifier(struct notifier_block *nb); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 24b7cf447bc5..4f5f93fd6802 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1407,8 +1407,6 @@ struct netlink_broadcast_data { int delivered; gfp_t allocation; struct sk_buff *skb, *skb2; - int (*tx_filter)(struct sock *dsk, struct sk_buff *skb, void *data); - void *tx_data; }; static void do_one_broadcast(struct sock *sk, @@ -1462,11 +1460,6 @@ static void do_one_broadcast(struct sock *sk, p->delivery_failure = 1; goto out; } - if (p->tx_filter && p->tx_filter(sk, p->skb2, p->tx_data)) { - kfree_skb(p->skb2); - p->skb2 = NULL; - goto out; - } if (sk_filter(sk, p->skb2)) { kfree_skb(p->skb2); p->skb2 = NULL; @@ -1489,10 +1482,8 @@ out: sock_put(sk); } -int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, - u32 group, gfp_t allocation, - int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), - void *filter_data) +int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, + u32 group, gfp_t allocation) { struct net *net = sock_net(ssk); struct netlink_broadcast_data info; @@ -1511,8 +1502,6 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid info.allocation = allocation; info.skb = skb; info.skb2 = NULL; - info.tx_filter = filter; - info.tx_data = filter_data; /* While we sleep in clone, do not allow to change socket list */ @@ -1538,14 +1527,6 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid } return -ESRCH; } -EXPORT_SYMBOL(netlink_broadcast_filtered); - -int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, - u32 group, gfp_t allocation) -{ - return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, - NULL, NULL); -} EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { -- cgit v1.2.3 From ded6e16b37e4c8c86cda98604ecd78818d6ca36a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 4 Oct 2021 12:14:43 -0700 Subject: mlx4: replace mlx4_mac_to_u64() with ether_addr_to_u64() mlx4_mac_to_u64() predates and opencodes ether_addr_to_u64(). It doesn't make the argument constant so it'll be problematic when dev->dev_addr becomes a const. Convert to the generic helper. Signed-off-by: Jakub Kicinski Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/main.c | 2 +- drivers/infiniband/hw/mlx4/qp.c | 2 +- drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 16 ++++++++-------- drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +- include/linux/mlx4/driver.h | 12 ------------ 6 files changed, 12 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index f367f4a4abff..f3fa2fe6a88a 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -2275,7 +2275,7 @@ static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev, u64 release_mac = MLX4_IB_INVALID_MAC; struct mlx4_ib_qp *qp; - new_smac = mlx4_mac_to_u64(dev->dev_addr); + new_smac = ether_addr_to_u64(dev->dev_addr); atomic64_set(&ibdev->iboe.mac[port - 1], new_smac); /* no need for update QP1 and mac registration in non-SRIOV */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 8662f462e2a5..aea4182f33a4 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1853,7 +1853,7 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp, u16 vlan_id, u8 *smac) { return _mlx4_set_path(dev, &qp->ah_attr, - mlx4_mac_to_u64(smac), + ether_addr_to_u64(smac), vlan_id, path, &mqp->pri, port); } diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 8d751383530b..9fadedfca41c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -3009,7 +3009,7 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u8 *mac) return -EPERM; } - s_info->mac = mlx4_mac_to_u64(mac); + s_info->mac = ether_addr_to_u64(mac); mlx4_info(dev, "default mac on vf %d port %d to %llX will take effect only after vf restart\n", vf, port, s_info->mac); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index ac480dc79bc1..76c8fe8e0125 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -644,7 +644,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv) int index = 0; int err = 0; int *qpn = &priv->base_qpn; - u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr); + u64 mac = ether_addr_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for adding\n", priv->dev->dev_addr); @@ -683,7 +683,7 @@ static void mlx4_en_put_qp(struct mlx4_en_priv *priv) int qpn = priv->base_qpn; if (dev->caps.steering_mode == MLX4_STEERING_MODE_A0) { - u64 mac = mlx4_mac_to_u64(priv->dev->dev_addr); + u64 mac = ether_addr_to_u64(priv->dev->dev_addr); en_dbg(DRV, priv, "Registering MAC: %pM for deleting\n", priv->dev->dev_addr); mlx4_unregister_mac(dev, priv->port, mac); @@ -701,14 +701,14 @@ static int mlx4_en_replace_mac(struct mlx4_en_priv *priv, int qpn, struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; int err = 0; - u64 new_mac_u64 = mlx4_mac_to_u64(new_mac); + u64 new_mac_u64 = ether_addr_to_u64(new_mac); if (dev->caps.steering_mode != MLX4_STEERING_MODE_A0) { struct hlist_head *bucket; unsigned int mac_hash; struct mlx4_mac_entry *entry; struct hlist_node *tmp; - u64 prev_mac_u64 = mlx4_mac_to_u64(prev_mac); + u64 prev_mac_u64 = ether_addr_to_u64(prev_mac); bucket = &priv->mac_hash[prev_mac[MLX4_EN_MAC_HASH_IDX]]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { @@ -1076,7 +1076,7 @@ static void mlx4_en_do_multicast(struct mlx4_en_priv *priv, mlx4_en_cache_mclist(dev); netif_addr_unlock_bh(dev); list_for_each_entry(mclist, &priv->mc_list, list) { - mcast_addr = mlx4_mac_to_u64(mclist->addr); + mcast_addr = ether_addr_to_u64(mclist->addr); mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, mcast_addr, 0, MLX4_MCAST_CONFIG); } @@ -1169,7 +1169,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, found = true; if (!found) { - mac = mlx4_mac_to_u64(entry->mac); + mac = ether_addr_to_u64(entry->mac); mlx4_en_uc_steer_release(priv, entry->mac, priv->base_qpn, entry->reg_id); @@ -1212,7 +1212,7 @@ static void mlx4_en_do_uc_filter(struct mlx4_en_priv *priv, priv->flags |= MLX4_EN_FLAG_FORCE_PROMISC; break; } - mac = mlx4_mac_to_u64(ha->addr); + mac = ether_addr_to_u64(ha->addr); memcpy(entry->mac, ha->addr, ETH_ALEN); err = mlx4_register_mac(mdev->dev, priv->port, mac); if (err < 0) { @@ -1348,7 +1348,7 @@ static void mlx4_en_delete_rss_steer_rules(struct mlx4_en_priv *priv) for (i = 0; i < MLX4_EN_MAC_HASH_SIZE; ++i) { bucket = &priv->mac_hash[i]; hlist_for_each_entry_safe(entry, tmp, bucket, hlist) { - mac = mlx4_mac_to_u64(entry->mac); + mac = ether_addr_to_u64(entry->mac); en_dbg(DRV, priv, "Registering MAC:%pM for deleting\n", entry->mac); mlx4_en_uc_steer_release(priv, entry->mac, diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index dc4ac1a2b6b6..42c96c9d7fb1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -3105,7 +3105,7 @@ void mlx4_replace_zero_macs(struct mlx4_dev *dev) dev->caps.port_type[i] == MLX4_PORT_TYPE_ETH) { eth_random_addr(mac_addr); dev->port_random_macs |= 1 << i; - dev->caps.def_mac[i] = mlx4_mac_to_u64(mac_addr); + dev->caps.def_mac[i] = ether_addr_to_u64(mac_addr); } } EXPORT_SYMBOL_GPL(mlx4_replace_zero_macs); diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index a858bcb6220b..b26b71f62fb4 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -92,18 +92,6 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); -static inline u64 mlx4_mac_to_u64(u8 *addr) -{ - u64 mac = 0; - int i; - - for (i = 0; i < ETH_ALEN; i++) { - mac <<= 8; - mac |= addr[i]; - } - return mac; -} - static inline void mlx4_u64_to_mac(u8 *addr, u64 mac) { int i; -- cgit v1.2.3 From 1bb96a07f9a8f2fe9725f6689605e32b75d20508 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 4 Oct 2021 12:14:44 -0700 Subject: mlx4: replace mlx4_u64_to_mac() with u64_to_ether_addr() mlx4_u64_to_mac() predates the common helper but doesn't make the argument constant. Signed-off-by: Jakub Kicinski Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 2 +- include/linux/mlx4/driver.h | 10 ---------- 2 files changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 9fadedfca41c..94ead263081f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -3195,7 +3195,7 @@ int mlx4_set_vf_spoofchk(struct mlx4_dev *dev, int port, int vf, bool setting) port = mlx4_slaves_closest_port(dev, slave, port); s_info = &priv->mfunc.master.vf_admin[slave].vport[port]; - mlx4_u64_to_mac(mac, s_info->mac); + u64_to_ether_addr(s_info->mac, mac); if (setting && !is_valid_ether_addr(mac)) { mlx4_info(dev, "Illegal MAC with spoofchk\n"); return -EPERM; diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h index b26b71f62fb4..1834c8fad12e 100644 --- a/include/linux/mlx4/driver.h +++ b/include/linux/mlx4/driver.h @@ -92,14 +92,4 @@ void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port); -static inline void mlx4_u64_to_mac(u8 *addr, u64 mac) -{ - int i; - - for (i = ETH_ALEN; i > 0; i--) { - addr[i - 1] = mac & 0xFF; - mac >>= 8; - } -} - #endif /* MLX4_DRIVER_H */ -- cgit v1.2.3 From ebb1fdb589bd6d0ee647d4fa285bc934ba369cde Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 4 Oct 2021 12:14:46 -0700 Subject: mlx4: constify args for const dev_addr netdev->dev_addr will become const soon. Make sure all functions which pass it around mark appropriate args as const. Signed-off-by: Jakub Kicinski Reviewed-by: Tariq Toukan Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 8 +++++--- drivers/net/ethernet/mellanox/mlx4/mcg.c | 2 +- include/linux/mlx4/device.h | 2 +- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index dce228170b14..3f6d5c384637 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -536,7 +536,8 @@ static void mlx4_en_u64_to_mac(struct net_device *dev, u64 src_mac) } -static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *addr, +static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, + const unsigned char *addr, int qpn, u64 *reg_id) { int err; @@ -557,7 +558,7 @@ static int mlx4_en_tunnel_steer_add(struct mlx4_en_priv *priv, unsigned char *ad static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv, - unsigned char *mac, int *qpn, u64 *reg_id) + const unsigned char *mac, int *qpn, u64 *reg_id) { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; @@ -609,7 +610,8 @@ static int mlx4_en_uc_steer_add(struct mlx4_en_priv *priv, } static void mlx4_en_uc_steer_release(struct mlx4_en_priv *priv, - unsigned char *mac, int qpn, u64 reg_id) + const unsigned char *mac, + int qpn, u64 reg_id) { struct mlx4_en_dev *mdev = priv->mdev; struct mlx4_dev *dev = mdev->dev; diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index f1b4ad9c66d2..f1716a83a4d3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1046,7 +1046,7 @@ int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id) } EXPORT_SYMBOL_GPL(mlx4_flow_detach); -int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr, +int mlx4_tunnel_steer_add(struct mlx4_dev *dev, const unsigned char *addr, int port, int qpn, u16 prio, u64 *reg_id) { int err; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 30bb59fe970c..6646634a0b9d 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -1436,7 +1436,7 @@ int mlx4_map_sw_to_hw_steering_id(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); int mlx4_hw_rule_sz(struct mlx4_dev *dev, enum mlx4_net_trans_rule_id id); -int mlx4_tunnel_steer_add(struct mlx4_dev *dev, unsigned char *addr, +int mlx4_tunnel_steer_add(struct mlx4_dev *dev, const unsigned char *addr, int port, int qpn, u16 prio, u64 *reg_id); void mlx4_sync_pkey_table(struct mlx4_dev *dev, int slave, int port, -- cgit v1.2.3 From 027b57170bf8bb6999a28e4a5f3d78bf1db0f90c Mon Sep 17 00:00:00 2001 From: Pali Rohár Date: Sat, 2 Oct 2021 15:09:00 +0200 Subject: serial: core: Fix initializing and restoring termios speed MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit edc6afc54968 ("tty: switch to ktermios and new framework") termios speed is no longer stored only in c_cflag member but also in new additional c_ispeed and c_ospeed members. If BOTHER flag is set in c_cflag then termios speed is stored only in these new members. Therefore to correctly restore termios speed it is required to store also ispeed and ospeed members, not only cflag member. In case only cflag member with BOTHER flag is restored then functions tty_termios_baud_rate() and tty_termios_input_baud_rate() returns baudrate stored in c_ospeed / c_ispeed member, which is zero as it was not restored too. If reported baudrate is invalid (e.g. zero) then serial core functions report fallback baudrate value 9600. So it means that in this case original baudrate is lost and kernel changes it to value 9600. Simple reproducer of this issue is to boot kernel with following command line argument: "console=ttyXXX,86400" (where ttyXXX is the device name). For speed 86400 there is no Bnnn constant and therefore kernel has to represent this speed via BOTHER c_cflag. Which means that speed is stored only in c_ospeed and c_ispeed members, not in c_cflag anymore. If bootloader correctly configures serial device to speed 86400 then kernel prints boot log to early console at speed speed 86400 without any issue. But after kernel starts initializing real console device ttyXXX then speed is changed to fallback value 9600 because information about speed was lost. This patch fixes above issue by storing and restoring also ispeed and ospeed members, which are required for BOTHER flag. Fixes: edc6afc54968 ("[PATCH] tty: switch to ktermios and new framework") Cc: stable@vger.kernel.org Signed-off-by: Pali Rohár Link: https://lore.kernel.org/r/20211002130900.9518-1-pali@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/serial_core.c | 16 ++++++++++++++-- include/linux/console.h | 2 ++ 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 0e2e35ab64c7..1e738f265eea 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -222,7 +222,11 @@ static int uart_port_startup(struct tty_struct *tty, struct uart_state *state, if (retval == 0) { if (uart_console(uport) && uport->cons->cflag) { tty->termios.c_cflag = uport->cons->cflag; + tty->termios.c_ispeed = uport->cons->ispeed; + tty->termios.c_ospeed = uport->cons->ospeed; uport->cons->cflag = 0; + uport->cons->ispeed = 0; + uport->cons->ospeed = 0; } /* * Initialise the hardware port settings. @@ -290,8 +294,11 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) /* * Turn off DTR and RTS early. */ - if (uport && uart_console(uport) && tty) + if (uport && uart_console(uport) && tty) { uport->cons->cflag = tty->termios.c_cflag; + uport->cons->ispeed = tty->termios.c_ispeed; + uport->cons->ospeed = tty->termios.c_ospeed; + } if (!tty || C_HUPCL(tty)) uart_port_dtr_rts(uport, 0); @@ -2094,8 +2101,11 @@ uart_set_options(struct uart_port *port, struct console *co, * Allow the setting of the UART parameters with a NULL console * too: */ - if (co) + if (co) { co->cflag = termios.c_cflag; + co->ispeed = termios.c_ispeed; + co->ospeed = termios.c_ospeed; + } return 0; } @@ -2229,6 +2239,8 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) */ memset(&termios, 0, sizeof(struct ktermios)); termios.c_cflag = uport->cons->cflag; + termios.c_ispeed = uport->cons->ispeed; + termios.c_ospeed = uport->cons->ospeed; /* * If that's unset, use the tty termios setting. diff --git a/include/linux/console.h b/include/linux/console.h index 20874db50bc8..a97f277cfdfa 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -149,6 +149,8 @@ struct console { short flags; short index; int cflag; + uint ispeed; + uint ospeed; void *data; struct console *next; }; -- cgit v1.2.3 From a130e8fbc7de796eb6e680724d87f4737a26d0ac Mon Sep 17 00:00:00 2001 From: Josh Don Date: Fri, 27 Aug 2021 09:54:38 -0700 Subject: fs/proc/uptime.c: Fix idle time reporting in /proc/uptime /proc/uptime reports idle time by reading the CPUTIME_IDLE field from the per-cpu kcpustats. However, on NO_HZ systems, idle time is not continually updated on idle cpus, leading this value to appear incorrectly small. /proc/stat performs an accounting update when reading idle time; we can use the same approach for uptime. With this patch, /proc/stat and /proc/uptime now agree on idle time. Additionally, the following shows idle time tick up consistently on an idle machine: (while true; do cat /proc/uptime; sleep 1; done) | awk '{print $2-prev; prev=$2}' Reported-by: Luigi Rizzo Signed-off-by: Josh Don Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Eric Dumazet Link: https://lkml.kernel.org/r/20210827165438.3280779-1-joshdon@google.com --- fs/proc/stat.c | 4 ++-- fs/proc/uptime.c | 14 +++++++++----- include/linux/kernel_stat.h | 1 + 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 6561a06ef905..4fb8729a68d4 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -24,7 +24,7 @@ #ifdef arch_idle_time -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) +u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle; @@ -46,7 +46,7 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu) #else -static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) +u64 get_idle_time(struct kernel_cpustat *kcs, int cpu) { u64 idle, idle_usecs = -1ULL; diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 5a1b228964fb..deb99bc9b7e6 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -12,18 +12,22 @@ static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec64 uptime; struct timespec64 idle; - u64 nsec; + u64 idle_nsec; u32 rem; int i; - nsec = 0; - for_each_possible_cpu(i) - nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE]; + idle_nsec = 0; + for_each_possible_cpu(i) { + struct kernel_cpustat kcs; + + kcpustat_cpu_fetch(&kcs, i); + idle_nsec += get_idle_time(&kcs, i); + } ktime_get_boottime_ts64(&uptime); timens_add_boottime(&uptime); - idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem); + idle.tv_sec = div_u64_rem(idle_nsec, NSEC_PER_SEC, &rem); idle.tv_nsec = rem; seq_printf(m, "%lu.%02lu %lu.%02lu\n", (unsigned long) uptime.tv_sec, diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 44ae1a7eb9e3..69ae6b278464 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -102,6 +102,7 @@ extern void account_system_index_time(struct task_struct *, u64, enum cpu_usage_stat); extern void account_steal_time(u64); extern void account_idle_time(u64); +extern u64 get_idle_time(struct kernel_cpustat *kcs, int cpu); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE static inline void account_process_tick(struct task_struct *tsk, int user) -- cgit v1.2.3 From ceeadb83aea28372e54857bf88ab7e17af48ab7b Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 5 Sep 2021 14:35:41 +0000 Subject: sched: Make struct sched_statistics independent of fair sched class If we want to use the schedstats facility to trace other sched classes, we should make it independent of fair sched class. The struct sched_statistics is the schedular statistics of a task_struct or a task_group. So we can move it into struct task_struct and struct task_group to achieve the goal. After the patch, schestats are orgnized as follows, struct task_struct { ... struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; ... struct sched_statistics stats; ... }; Regarding the task group, schedstats is only supported for fair group sched, and a new struct sched_entity_stats is introduced, suggested by Peter - struct sched_entity_stats { struct sched_entity se; struct sched_statistics stats; } __no_randomize_layout; Then with the se in a task_group, we can easily get the stats. The sched_statistics members may be frequently modified when schedstats is enabled, in order to avoid impacting on random data which may in the same cacheline with them, the struct sched_statistics is defined as cacheline aligned. As this patch changes the core struct of scheduler, so I verified the performance it may impact on the scheduler with 'perf bench sched pipe', suggested by Mel. Below is the result, in which all the values are in usecs/op. Before After kernel.sched_schedstats=0 5.2~5.4 5.2~5.4 kernel.sched_schedstats=1 5.3~5.5 5.3~5.5 [These data is a little difference with the earlier version, that is because my old test machine is destroyed so I have to use a new different test machine.] Almost no impact on the sched performance. No functional change. [lkp@intel.com: reported build failure in earlier version] Signed-off-by: Yafang Shao Signed-off-by: Peter Zijlstra (Intel) Acked-by: Mel Gorman Link: https://lore.kernel.org/r/20210905143547.4668-3-laoar.shao@gmail.com --- include/linux/sched.h | 6 ++-- kernel/sched/core.c | 25 +++++++------ kernel/sched/deadline.c | 4 +-- kernel/sched/debug.c | 92 +++++++++++++++++++++++++----------------------- kernel/sched/fair.c | 89 +++++++++++++++++++++++++++------------------- kernel/sched/rt.c | 4 +-- kernel/sched/stats.h | 19 ++++++++++ kernel/sched/stop_task.c | 4 +-- 8 files changed, 143 insertions(+), 100 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c1a927ddec64..2bc4c72fec2d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -522,7 +522,7 @@ struct sched_statistics { u64 nr_wakeups_passive; u64 nr_wakeups_idle; #endif -}; +} ____cacheline_aligned; struct sched_entity { /* For load-balancing: */ @@ -538,8 +538,6 @@ struct sched_entity { u64 nr_migrations; - struct sched_statistics statistics; - #ifdef CONFIG_FAIR_GROUP_SCHED int depth; struct sched_entity *parent; @@ -803,6 +801,8 @@ struct task_struct { struct uclamp_se uclamp[UCLAMP_CNT]; #endif + struct sched_statistics stats; + #ifdef CONFIG_PREEMPT_NOTIFIERS /* List of struct preempt_notifier: */ struct hlist_head preempt_notifiers; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ccb604a1bd22..a1741e004eaa 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3489,11 +3489,11 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) #ifdef CONFIG_SMP if (cpu == rq->cpu) { __schedstat_inc(rq->ttwu_local); - __schedstat_inc(p->se.statistics.nr_wakeups_local); + __schedstat_inc(p->stats.nr_wakeups_local); } else { struct sched_domain *sd; - __schedstat_inc(p->se.statistics.nr_wakeups_remote); + __schedstat_inc(p->stats.nr_wakeups_remote); rcu_read_lock(); for_each_domain(rq->cpu, sd) { if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { @@ -3505,14 +3505,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } if (wake_flags & WF_MIGRATED) - __schedstat_inc(p->se.statistics.nr_wakeups_migrate); + __schedstat_inc(p->stats.nr_wakeups_migrate); #endif /* CONFIG_SMP */ __schedstat_inc(rq->ttwu_count); - __schedstat_inc(p->se.statistics.nr_wakeups); + __schedstat_inc(p->stats.nr_wakeups); if (wake_flags & WF_SYNC) - __schedstat_inc(p->se.statistics.nr_wakeups_sync); + __schedstat_inc(p->stats.nr_wakeups_sync); } /* @@ -4196,7 +4196,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #ifdef CONFIG_SCHEDSTATS /* Even if schedstat is disabled, there should not be garbage */ - memset(&p->se.statistics, 0, sizeof(p->se.statistics)); + memset(&p->stats, 0, sizeof(p->stats)); #endif RB_CLEAR_NODE(&p->dl.rb_node); @@ -9553,9 +9553,9 @@ void normalize_rt_tasks(void) continue; p->se.exec_start = 0; - schedstat_set(p->se.statistics.wait_start, 0); - schedstat_set(p->se.statistics.sleep_start, 0); - schedstat_set(p->se.statistics.block_start, 0); + schedstat_set(p->stats.wait_start, 0); + schedstat_set(p->stats.sleep_start, 0); + schedstat_set(p->stats.block_start, 0); if (!dl_task(p) && !rt_task(p)) { /* @@ -10397,11 +10397,14 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); if (schedstat_enabled() && tg != &root_task_group) { + struct sched_statistics *stats; u64 ws = 0; int i; - for_each_possible_cpu(i) - ws += schedstat_val(tg->se[i]->statistics.wait_sum); + for_each_possible_cpu(i) { + stats = __schedstats_from_se(tg->se[i]); + ws += schedstat_val(stats->wait_sum); + } seq_printf(sf, "wait_sum %llu\n", ws); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index e94314633b39..51dd30990042 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1265,8 +1265,8 @@ static void update_curr_dl(struct rq *rq) return; } - schedstat_set(curr->se.statistics.exec_max, - max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->stats.exec_max, + max(curr->stats.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 34913a7f775a..76fd38ea844c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -449,9 +449,11 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group struct sched_entity *se = tg->se[cpu]; #define P(F) SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)F) -#define P_SCHEDSTAT(F) SEQ_printf(m, " .%-30s: %lld\n", #F, (long long)schedstat_val(F)) +#define P_SCHEDSTAT(F) SEQ_printf(m, " .%-30s: %lld\n", \ + #F, (long long)schedstat_val(stats->F)) #define PN(F) SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F)) -#define PN_SCHEDSTAT(F) SEQ_printf(m, " .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)schedstat_val(F))) +#define PN_SCHEDSTAT(F) SEQ_printf(m, " .%-30s: %lld.%06ld\n", \ + #F, SPLIT_NS((long long)schedstat_val(stats->F))) if (!se) return; @@ -461,16 +463,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group PN(se->sum_exec_runtime); if (schedstat_enabled()) { - PN_SCHEDSTAT(se->statistics.wait_start); - PN_SCHEDSTAT(se->statistics.sleep_start); - PN_SCHEDSTAT(se->statistics.block_start); - PN_SCHEDSTAT(se->statistics.sleep_max); - PN_SCHEDSTAT(se->statistics.block_max); - PN_SCHEDSTAT(se->statistics.exec_max); - PN_SCHEDSTAT(se->statistics.slice_max); - PN_SCHEDSTAT(se->statistics.wait_max); - PN_SCHEDSTAT(se->statistics.wait_sum); - P_SCHEDSTAT(se->statistics.wait_count); + struct sched_statistics *stats = __schedstats_from_se(se); + + PN_SCHEDSTAT(wait_start); + PN_SCHEDSTAT(sleep_start); + PN_SCHEDSTAT(block_start); + PN_SCHEDSTAT(sleep_max); + PN_SCHEDSTAT(block_max); + PN_SCHEDSTAT(exec_max); + PN_SCHEDSTAT(slice_max); + PN_SCHEDSTAT(wait_max); + PN_SCHEDSTAT(wait_sum); + P_SCHEDSTAT(wait_count); } P(se->load.weight); @@ -537,9 +541,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) p->prio); SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(schedstat_val_or_zero(p->se.statistics.wait_sum)), + SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)), SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(schedstat_val_or_zero(p->se.statistics.sum_sleep_runtime))); + SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime))); #ifdef CONFIG_NUMA_BALANCING SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); @@ -958,8 +962,8 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, "---------------------------------------------------------" "----------\n"); -#define P_SCHEDSTAT(F) __PS(#F, schedstat_val(p->F)) -#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->F)) +#define P_SCHEDSTAT(F) __PS(#F, schedstat_val(p->stats.F)) +#define PN_SCHEDSTAT(F) __PSN(#F, schedstat_val(p->stats.F)) PN(se.exec_start); PN(se.vruntime); @@ -972,33 +976,33 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, if (schedstat_enabled()) { u64 avg_atom, avg_per_cpu; - PN_SCHEDSTAT(se.statistics.sum_sleep_runtime); - PN_SCHEDSTAT(se.statistics.wait_start); - PN_SCHEDSTAT(se.statistics.sleep_start); - PN_SCHEDSTAT(se.statistics.block_start); - PN_SCHEDSTAT(se.statistics.sleep_max); - PN_SCHEDSTAT(se.statistics.block_max); - PN_SCHEDSTAT(se.statistics.exec_max); - PN_SCHEDSTAT(se.statistics.slice_max); - PN_SCHEDSTAT(se.statistics.wait_max); - PN_SCHEDSTAT(se.statistics.wait_sum); - P_SCHEDSTAT(se.statistics.wait_count); - PN_SCHEDSTAT(se.statistics.iowait_sum); - P_SCHEDSTAT(se.statistics.iowait_count); - P_SCHEDSTAT(se.statistics.nr_migrations_cold); - P_SCHEDSTAT(se.statistics.nr_failed_migrations_affine); - P_SCHEDSTAT(se.statistics.nr_failed_migrations_running); - P_SCHEDSTAT(se.statistics.nr_failed_migrations_hot); - P_SCHEDSTAT(se.statistics.nr_forced_migrations); - P_SCHEDSTAT(se.statistics.nr_wakeups); - P_SCHEDSTAT(se.statistics.nr_wakeups_sync); - P_SCHEDSTAT(se.statistics.nr_wakeups_migrate); - P_SCHEDSTAT(se.statistics.nr_wakeups_local); - P_SCHEDSTAT(se.statistics.nr_wakeups_remote); - P_SCHEDSTAT(se.statistics.nr_wakeups_affine); - P_SCHEDSTAT(se.statistics.nr_wakeups_affine_attempts); - P_SCHEDSTAT(se.statistics.nr_wakeups_passive); - P_SCHEDSTAT(se.statistics.nr_wakeups_idle); + PN_SCHEDSTAT(sum_sleep_runtime); + PN_SCHEDSTAT(wait_start); + PN_SCHEDSTAT(sleep_start); + PN_SCHEDSTAT(block_start); + PN_SCHEDSTAT(sleep_max); + PN_SCHEDSTAT(block_max); + PN_SCHEDSTAT(exec_max); + PN_SCHEDSTAT(slice_max); + PN_SCHEDSTAT(wait_max); + PN_SCHEDSTAT(wait_sum); + P_SCHEDSTAT(wait_count); + PN_SCHEDSTAT(iowait_sum); + P_SCHEDSTAT(iowait_count); + P_SCHEDSTAT(nr_migrations_cold); + P_SCHEDSTAT(nr_failed_migrations_affine); + P_SCHEDSTAT(nr_failed_migrations_running); + P_SCHEDSTAT(nr_failed_migrations_hot); + P_SCHEDSTAT(nr_forced_migrations); + P_SCHEDSTAT(nr_wakeups); + P_SCHEDSTAT(nr_wakeups_sync); + P_SCHEDSTAT(nr_wakeups_migrate); + P_SCHEDSTAT(nr_wakeups_local); + P_SCHEDSTAT(nr_wakeups_remote); + P_SCHEDSTAT(nr_wakeups_affine); + P_SCHEDSTAT(nr_wakeups_affine_attempts); + P_SCHEDSTAT(nr_wakeups_passive); + P_SCHEDSTAT(nr_wakeups_idle); avg_atom = p->se.sum_exec_runtime; if (nr_switches) @@ -1064,7 +1068,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, void proc_sched_set_task(struct task_struct *p) { #ifdef CONFIG_SCHEDSTATS - memset(&p->se.statistics, 0, sizeof(p->se.statistics)); + memset(&p->stats, 0, sizeof(p->stats)); #endif } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 61d3e3b97fe5..97c6ecb03bb2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -856,8 +856,13 @@ static void update_curr(struct cfs_rq *cfs_rq) curr->exec_start = now; - schedstat_set(curr->statistics.exec_max, - max(delta_exec, curr->statistics.exec_max)); + if (schedstat_enabled()) { + struct sched_statistics *stats; + + stats = __schedstats_from_se(curr); + __schedstat_set(stats->exec_max, + max(delta_exec, stats->exec_max)); + } curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq->exec_clock, delta_exec); @@ -885,39 +890,45 @@ static inline void update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) { u64 wait_start, prev_wait_start; + struct sched_statistics *stats; if (!schedstat_enabled()) return; + stats = __schedstats_from_se(se); + wait_start = rq_clock(rq_of(cfs_rq)); - prev_wait_start = schedstat_val(se->statistics.wait_start); + prev_wait_start = schedstat_val(stats->wait_start); if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) && likely(wait_start > prev_wait_start)) wait_start -= prev_wait_start; - __schedstat_set(se->statistics.wait_start, wait_start); + __schedstat_set(stats->wait_start, wait_start); } static inline void update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { - struct task_struct *p; + struct sched_statistics *stats; + struct task_struct *p = NULL; u64 delta; if (!schedstat_enabled()) return; + stats = __schedstats_from_se(se); + /* * When the sched_schedstat changes from 0 to 1, some sched se * maybe already in the runqueue, the se->statistics.wait_start * will be 0.So it will let the delta wrong. We need to avoid this * scenario. */ - if (unlikely(!schedstat_val(se->statistics.wait_start))) + if (unlikely(!schedstat_val(stats->wait_start))) return; - delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start); + delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(stats->wait_start); if (entity_is_task(se)) { p = task_of(se); @@ -927,30 +938,33 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) * time stamp can be adjusted to accumulate wait time * prior to migration. */ - __schedstat_set(se->statistics.wait_start, delta); + __schedstat_set(stats->wait_start, delta); return; } trace_sched_stat_wait(p, delta); } - __schedstat_set(se->statistics.wait_max, - max(schedstat_val(se->statistics.wait_max), delta)); - __schedstat_inc(se->statistics.wait_count); - __schedstat_add(se->statistics.wait_sum, delta); - __schedstat_set(se->statistics.wait_start, 0); + __schedstat_set(stats->wait_max, + max(schedstat_val(stats->wait_max), delta)); + __schedstat_inc(stats->wait_count); + __schedstat_add(stats->wait_sum, delta); + __schedstat_set(stats->wait_start, 0); } static inline void update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { + struct sched_statistics *stats; struct task_struct *tsk = NULL; u64 sleep_start, block_start; if (!schedstat_enabled()) return; - sleep_start = schedstat_val(se->statistics.sleep_start); - block_start = schedstat_val(se->statistics.block_start); + stats = __schedstats_from_se(se); + + sleep_start = schedstat_val(stats->sleep_start); + block_start = schedstat_val(stats->block_start); if (entity_is_task(se)) tsk = task_of(se); @@ -961,11 +975,11 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) if ((s64)delta < 0) delta = 0; - if (unlikely(delta > schedstat_val(se->statistics.sleep_max))) - __schedstat_set(se->statistics.sleep_max, delta); + if (unlikely(delta > schedstat_val(stats->sleep_max))) + __schedstat_set(stats->sleep_max, delta); - __schedstat_set(se->statistics.sleep_start, 0); - __schedstat_add(se->statistics.sum_sleep_runtime, delta); + __schedstat_set(stats->sleep_start, 0); + __schedstat_add(stats->sum_sleep_runtime, delta); if (tsk) { account_scheduler_latency(tsk, delta >> 10, 1); @@ -978,16 +992,16 @@ update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) if ((s64)delta < 0) delta = 0; - if (unlikely(delta > schedstat_val(se->statistics.block_max))) - __schedstat_set(se->statistics.block_max, delta); + if (unlikely(delta > schedstat_val(stats->block_max))) + __schedstat_set(stats->block_max, delta); - __schedstat_set(se->statistics.block_start, 0); - __schedstat_add(se->statistics.sum_sleep_runtime, delta); + __schedstat_set(stats->block_start, 0); + __schedstat_add(stats->sum_sleep_runtime, delta); if (tsk) { if (tsk->in_iowait) { - __schedstat_add(se->statistics.iowait_sum, delta); - __schedstat_inc(se->statistics.iowait_count); + __schedstat_add(stats->iowait_sum, delta); + __schedstat_inc(stats->iowait_count); trace_sched_stat_iowait(tsk, delta); } @@ -1049,10 +1063,10 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* XXX racy against TTWU */ state = READ_ONCE(tsk->__state); if (state & TASK_INTERRUPTIBLE) - __schedstat_set(se->statistics.sleep_start, + __schedstat_set(tsk->stats.sleep_start, rq_clock(rq_of(cfs_rq))); if (state & TASK_UNINTERRUPTIBLE) - __schedstat_set(se->statistics.block_start, + __schedstat_set(tsk->stats.block_start, rq_clock(rq_of(cfs_rq))); } } @@ -4530,8 +4544,11 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ if (schedstat_enabled() && rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) { - __schedstat_set(se->statistics.slice_max, - max((u64)se->statistics.slice_max, + struct sched_statistics *stats; + + stats = __schedstats_from_se(se); + __schedstat_set(stats->slice_max, + max((u64)stats->slice_max, se->sum_exec_runtime - se->prev_sum_exec_runtime)); } @@ -6046,12 +6063,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits) target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); - schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); + schedstat_inc(p->stats.nr_wakeups_affine_attempts); if (target == nr_cpumask_bits) return prev_cpu; schedstat_inc(sd->ttwu_move_affine); - schedstat_inc(p->se.statistics.nr_wakeups_affine); + schedstat_inc(p->stats.nr_wakeups_affine); return target; } @@ -7855,7 +7872,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { int cpu; - schedstat_inc(p->se.statistics.nr_failed_migrations_affine); + schedstat_inc(p->stats.nr_failed_migrations_affine); env->flags |= LBF_SOME_PINNED; @@ -7889,7 +7906,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) env->flags &= ~LBF_ALL_PINNED; if (task_running(env->src_rq, p)) { - schedstat_inc(p->se.statistics.nr_failed_migrations_running); + schedstat_inc(p->stats.nr_failed_migrations_running); return 0; } @@ -7911,12 +7928,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) env->sd->nr_balance_failed > env->sd->cache_nice_tries) { if (tsk_cache_hot == 1) { schedstat_inc(env->sd->lb_hot_gained[env->idle]); - schedstat_inc(p->se.statistics.nr_forced_migrations); + schedstat_inc(p->stats.nr_forced_migrations); } return 1; } - schedstat_inc(p->se.statistics.nr_failed_migrations_hot); + schedstat_inc(p->stats.nr_failed_migrations_hot); return 0; } @@ -11457,7 +11474,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) if (!cfs_rq) goto err; - se = kzalloc_node(sizeof(struct sched_entity), + se = kzalloc_node(sizeof(struct sched_entity_stats), GFP_KERNEL, cpu_to_node(i)); if (!se) goto err_free_rq; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 3daf42a0f462..95a7c3ad2dc3 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1009,8 +1009,8 @@ static void update_curr_rt(struct rq *rq) if (unlikely((s64)delta_exec <= 0)) return; - schedstat_set(curr->se.statistics.exec_max, - max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->stats.exec_max, + max(curr->stats.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index d8f8eb0c655b..fb6022e860af 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -41,6 +41,7 @@ rq_sched_info_dequeue(struct rq *rq, unsigned long long delta) #define schedstat_val_or_zero(var) ((schedstat_enabled()) ? (var) : 0) #else /* !CONFIG_SCHEDSTATS: */ + static inline void rq_sched_info_arrive (struct rq *rq, unsigned long long delta) { } static inline void rq_sched_info_dequeue(struct rq *rq, unsigned long long delta) { } static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delta) { } @@ -53,8 +54,26 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt # define schedstat_set(var, val) do { } while (0) # define schedstat_val(var) 0 # define schedstat_val_or_zero(var) 0 + #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_FAIR_GROUP_SCHED +struct sched_entity_stats { + struct sched_entity se; + struct sched_statistics stats; +} __no_randomize_layout; +#endif + +static inline struct sched_statistics * +__schedstats_from_se(struct sched_entity *se) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + if (!entity_is_task(se)) + return &container_of(se, struct sched_entity_stats, se)->stats; +#endif + return &task_of(se)->stats; +} + #ifdef CONFIG_PSI /* * PSI tracks state that persists across sleeps, such as iowaits and diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index f988ebe3febb..0b165a25f22f 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -78,8 +78,8 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) if (unlikely((s64)delta_exec < 0)) delta_exec = 0; - schedstat_set(curr->se.statistics.exec_max, - max(curr->se.statistics.exec_max, delta_exec)); + schedstat_set(curr->stats.exec_max, + max(curr->stats.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; account_group_exec_runtime(curr, delta_exec); -- cgit v1.2.3 From 847fc0cd0664fcb2a08ac66df6b85935361ec454 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Sun, 5 Sep 2021 14:35:43 +0000 Subject: sched: Introduce task block time in schedstats Currently in schedstats we have sum_sleep_runtime and iowait_sum, but there's no metric to show how long the task is in D state. Once a task in D state, it means the task is blocked in the kernel, for example the task may be waiting for a mutex. The D state is more frequent than iowait, and it is more critital than S state. So it is worth to add a metric to measure it. Signed-off-by: Yafang Shao Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210905143547.4668-5-laoar.shao@gmail.com --- include/linux/sched.h | 2 ++ kernel/sched/debug.c | 6 ++++-- kernel/sched/stats.c | 1 + 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2bc4c72fec2d..193e16e2d0e4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -503,6 +503,8 @@ struct sched_statistics { u64 block_start; u64 block_max; + s64 sum_block_runtime; + u64 exec_max; u64 slice_max; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 76fd38ea844c..26fac5e28bc0 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -540,10 +540,11 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) (long long)(p->nvcsw + p->nivcsw), p->prio); - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + SEQ_printf(m, "%9lld.%06ld %9lld.%06ld %9lld.%06ld %9lld.%06ld", SPLIT_NS(schedstat_val_or_zero(p->stats.wait_sum)), SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime))); + SPLIT_NS(schedstat_val_or_zero(p->stats.sum_sleep_runtime)), + SPLIT_NS(schedstat_val_or_zero(p->stats.sum_block_runtime))); #ifdef CONFIG_NUMA_BALANCING SEQ_printf(m, " %d %d", task_node(p), task_numa_group_id(p)); @@ -977,6 +978,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, u64 avg_atom, avg_per_cpu; PN_SCHEDSTAT(sum_sleep_runtime); + PN_SCHEDSTAT(sum_block_runtime); PN_SCHEDSTAT(wait_start); PN_SCHEDSTAT(sleep_start); PN_SCHEDSTAT(block_start); diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index fad781ca7791..07dde2928c79 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -82,6 +82,7 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p, __schedstat_set(stats->block_start, 0); __schedstat_add(stats->sum_sleep_runtime, delta); + __schedstat_add(stats->sum_block_runtime, delta); if (p) { if (p->in_iowait) { -- cgit v1.2.3 From 8d491de6edc27138806cae6e8eca455beb325b62 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 28 Sep 2021 14:24:32 +0200 Subject: sched: Move mmdrop to RCU on RT mmdrop() is invoked from finish_task_switch() by the incoming task to drop the mm which was handed over by the previous task. mmdrop() can be quite expensive which prevents an incoming real-time task from getting useful work done. Provide mmdrop_sched() which maps to mmdrop() on !RT kernels. On RT kernels it delagates the eventually required invocation of __mmdrop() to RCU. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210928122411.648582026@linutronix.de --- include/linux/mm_types.h | 4 ++++ include/linux/sched/mm.h | 29 +++++++++++++++++++++++++++++ kernel/sched/core.c | 2 +- 3 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..e9672de22cf2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -572,6 +573,9 @@ struct mm_struct { bool tlb_flush_batched; #endif struct uprobes_state uprobes_state; +#ifdef CONFIG_PREEMPT_RT + struct rcu_head delayed_drop; +#endif #ifdef CONFIG_HUGETLB_PAGE atomic_long_t hugetlb_usage; #endif diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 5561486fddef..aca874d33fe6 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,35 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +#ifdef CONFIG_PREEMPT_RT +/* + * RCU callback for delayed mm drop. Not strictly RCU, but call_rcu() is + * by far the least expensive way to do that. + */ +static inline void __mmdrop_delayed(struct rcu_head *rhp) +{ + struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); + + __mmdrop(mm); +} + +/* + * Invoked from finish_task_switch(). Delegates the heavy lifting on RT + * kernels via RCU. + */ +static inline void mmdrop_sched(struct mm_struct *mm) +{ + /* Provides a full memory barrier. See mmdrop() */ + if (atomic_dec_and_test(&mm->mm_count)) + call_rcu(&mm->delayed_drop, __mmdrop_delayed); +} +#else +static inline void mmdrop_sched(struct mm_struct *mm) +{ + mmdrop(mm); +} +#endif + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 95f4e16f98a2..9eaeba671001 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4836,7 +4836,7 @@ static struct rq *finish_task_switch(struct task_struct *prev) */ if (mm) { membarrier_mm_sync_core_before_usermode(mm); - mmdrop(mm); + mmdrop_sched(mm); } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) -- cgit v1.2.3 From c8ed99533dbc0fcc1142671ec80acb33045d2999 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Sep 2021 15:05:23 +0100 Subject: PM: EM: Mark inefficient states Some SoCs, such as the sd855 have OPPs within the same performance domain, whose cost is higher than others with a higher frequency. Even though those OPPs are interesting from a cooling perspective, it makes no sense to use them when the device can run at full capacity. Those OPPs handicap the performance domain, when choosing the most energy-efficient CPU and are wasting energy. They are inefficient. Hence, add support for such OPPs to the Energy Model. The table can now be read skipping inefficient performance states (and by extension, inefficient OPPs). Signed-off-by: Vincent Donnefort Reviewed-by: Matthias Kaehlcke Reviewed-by: Lukasz Luba Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 12 ++++++++++++ kernel/power/energy_model.c | 4 +++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 39dcadd492b5..3641ca4acf04 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -17,13 +17,25 @@ * device). It can be a total power: static and dynamic. * @cost: The cost coefficient associated with this level, used during * energy calculation. Equal to: power * max_frequency / frequency + * @flags: see "em_perf_state flags" description below. */ struct em_perf_state { unsigned long frequency; unsigned long power; unsigned long cost; + unsigned long flags; }; +/* + * em_perf_state flags: + * + * EM_PERF_STATE_INEFFICIENT: The performance state is inefficient. There is + * in this em_perf_domain, another performance state with a higher frequency + * but a lower or equal power cost. Such inefficient states are ignored when + * using em_pd_get_efficient_*() functions. + */ +#define EM_PERF_STATE_INEFFICIENT BIT(0) + /** * struct em_perf_domain - Performance domain * @table: List of performance states, in ascending order diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 97e62469a6b3..6d8438347535 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -2,7 +2,7 @@ /* * Energy Model of devices * - * Copyright (c) 2018-2020, Arm ltd. + * Copyright (c) 2018-2021, Arm ltd. * Written by: Quentin Perret, Arm ltd. * Improvements provided by: Lukasz Luba, Arm ltd. */ @@ -42,6 +42,7 @@ static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd) debugfs_create_ulong("frequency", 0444, d, &ps->frequency); debugfs_create_ulong("power", 0444, d, &ps->power); debugfs_create_ulong("cost", 0444, d, &ps->cost); + debugfs_create_ulong("inefficient", 0444, d, &ps->flags); } static int em_debug_cpus_show(struct seq_file *s, void *unused) @@ -162,6 +163,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, table[i].cost = div64_u64(fmax * power_res, table[i].frequency); if (table[i].cost >= prev_cost) { + table[i].flags = EM_PERF_STATE_INEFFICIENT; dev_dbg(dev, "EM: OPP:%lu is inefficient\n", table[i].frequency); } else { -- cgit v1.2.3 From 88f7a89560f6d0fc7803a8933637488f14e0a098 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Sep 2021 15:05:24 +0100 Subject: PM: EM: Extend em_perf_domain with a flag field Merge the current "milliwatts" option into a "flag" field. This intends to prepare the extension of this structure for inefficient states support in the Energy Model. Signed-off-by: Vincent Donnefort Reviewed-by: Lukasz Luba Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 13 ++++++++++--- kernel/power/energy_model.c | 6 ++++-- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 3641ca4acf04..671440371a95 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -40,8 +40,7 @@ struct em_perf_state { * struct em_perf_domain - Performance domain * @table: List of performance states, in ascending order * @nr_perf_states: Number of performance states - * @milliwatts: Flag indicating the power values are in milli-Watts - * or some other scale. + * @flags: See "em_perf_domain flags" * @cpus: Cpumask covering the CPUs of the domain. It's here * for performance reasons to avoid potential cache * misses during energy calculations in the scheduler @@ -56,10 +55,18 @@ struct em_perf_state { struct em_perf_domain { struct em_perf_state *table; int nr_perf_states; - int milliwatts; + unsigned long flags; unsigned long cpus[]; }; +/* + * em_perf_domain flags: + * + * EM_PERF_DOMAIN_MILLIWATTS: The power values are in milli-Watts or some + * other scale. + */ +#define EM_PERF_DOMAIN_MILLIWATTS BIT(0) + #define em_span_cpus(em) (to_cpumask((em)->cpus)) #ifdef CONFIG_ENERGY_MODEL diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 6d8438347535..3a7d1573b214 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -56,7 +56,8 @@ DEFINE_SHOW_ATTRIBUTE(em_debug_cpus); static int em_debug_units_show(struct seq_file *s, void *unused) { struct em_perf_domain *pd = s->private; - char *units = pd->milliwatts ? "milliWatts" : "bogoWatts"; + char *units = (pd->flags & EM_PERF_DOMAIN_MILLIWATTS) ? + "milliWatts" : "bogoWatts"; seq_printf(s, "%s\n", units); @@ -330,7 +331,8 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, if (ret) goto unlock; - dev->em_pd->milliwatts = milliwatts; + if (milliwatts) + dev->em_pd->flags |= EM_PERF_DOMAIN_MILLIWATTS; em_debug_create_pd(dev); dev_info(dev, "EM: created perf domain\n"); -- cgit v1.2.3 From 8354eb9eb3ddb4a8d0857648a470beffcc9d8639 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Sep 2021 15:05:25 +0100 Subject: PM: EM: Allow skipping inefficient states The new performance domain flag EM_PERF_DOMAIN_SKIP_INEFFICIENCIES allows to not take into account inefficient states when estimating energy consumption. This intends to let the Energy Model know that CPUFreq itself will skip inefficiencies and such states don't need to be part of the estimation anymore. Signed-off-by: Vincent Donnefort Reviewed-by: Lukasz Luba Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/energy_model.h | 43 +++++++++++++++++++++++++++++++++++++------ kernel/power/energy_model.c | 13 +++++++++++++ 2 files changed, 50 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 671440371a95..6377adc3b78d 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -64,8 +64,12 @@ struct em_perf_domain { * * EM_PERF_DOMAIN_MILLIWATTS: The power values are in milli-Watts or some * other scale. + * + * EM_PERF_DOMAIN_SKIP_INEFFICIENCIES: Skip inefficient states when estimating + * energy consumption. */ #define EM_PERF_DOMAIN_MILLIWATTS BIT(0) +#define EM_PERF_DOMAIN_SKIP_INEFFICIENCIES BIT(1) #define em_span_cpus(em) (to_cpumask((em)->cpus)) @@ -120,6 +124,37 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, bool milliwatts); void em_dev_unregister_perf_domain(struct device *dev); +/** + * em_pd_get_efficient_state() - Get an efficient performance state from the EM + * @pd : Performance domain for which we want an efficient frequency + * @freq : Frequency to map with the EM + * + * It is called from the scheduler code quite frequently and as a consequence + * doesn't implement any check. + * + * Return: An efficient performance state, high enough to meet @freq + * requirement. + */ +static inline +struct em_perf_state *em_pd_get_efficient_state(struct em_perf_domain *pd, + unsigned long freq) +{ + struct em_perf_state *ps; + int i; + + for (i = 0; i < pd->nr_perf_states; i++) { + ps = &pd->table[i]; + if (ps->frequency >= freq) { + if (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES && + ps->flags & EM_PERF_STATE_INEFFICIENT) + continue; + break; + } + } + + return ps; +} + /** * em_cpu_energy() - Estimates the energy consumed by the CPUs of a * performance domain @@ -142,7 +177,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, { unsigned long freq, scale_cpu; struct em_perf_state *ps; - int i, cpu; + int cpu; if (!sum_util) return 0; @@ -167,11 +202,7 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd, * Find the lowest performance state of the Energy Model above the * requested frequency. */ - for (i = 0; i < pd->nr_perf_states; i++) { - ps = &pd->table[i]; - if (ps->frequency >= freq) - break; - } + ps = em_pd_get_efficient_state(pd, freq); /* * The capacity of a CPU in the domain at the performance state (ps) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 3a7d1573b214..d353ef29e37f 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -65,6 +65,17 @@ static int em_debug_units_show(struct seq_file *s, void *unused) } DEFINE_SHOW_ATTRIBUTE(em_debug_units); +static int em_debug_skip_inefficiencies_show(struct seq_file *s, void *unused) +{ + struct em_perf_domain *pd = s->private; + int enabled = (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES) ? 1 : 0; + + seq_printf(s, "%d\n", enabled); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(em_debug_skip_inefficiencies); + static void em_debug_create_pd(struct device *dev) { struct dentry *d; @@ -78,6 +89,8 @@ static void em_debug_create_pd(struct device *dev) &em_debug_cpus_fops); debugfs_create_file("units", 0444, d, dev->em_pd, &em_debug_units_fops); + debugfs_create_file("skip-inefficiencies", 0444, d, dev->em_pd, + &em_debug_skip_inefficiencies_fops); /* Create a sub-directory for each performance state */ for (i = 0; i < dev->em_pd->nr_perf_states; i++) -- cgit v1.2.3 From 442d24a5c49a8ed1008dcb9c06dc463d12421e7f Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Sep 2021 15:05:27 +0100 Subject: cpufreq: Add an interface to mark inefficient frequencies Some SoCs such as the sd855 have OPPs within the same policy whose cost is higher than others with a higher frequency. Those OPPs are inefficients and it might be interesting for a governor to not use them. cpufreq_table_set_inefficient() allows the caller to identify a specified frequency as being inefficient. Inefficient frequencies are only supported on sorted tables. Signed-off-by: Vincent Donnefort Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 44 +++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 41 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ff88bb3e44fc..16997e1ff3fe 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -660,10 +660,11 @@ struct governor_attr { *********************************************************************/ /* Special Values of .frequency field */ -#define CPUFREQ_ENTRY_INVALID ~0u -#define CPUFREQ_TABLE_END ~1u +#define CPUFREQ_ENTRY_INVALID ~0u +#define CPUFREQ_TABLE_END ~1u /* Special Values of .flags field */ -#define CPUFREQ_BOOST_FREQ (1 << 0) +#define CPUFREQ_BOOST_FREQ (1 << 0) +#define CPUFREQ_INEFFICIENT_FREQ (1 << 1) struct cpufreq_frequency_table { unsigned int flags; @@ -1003,6 +1004,36 @@ static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy return count; } +/** + * cpufreq_table_set_inefficient() - Mark a frequency as inefficient + * @policy: the &struct cpufreq_policy containing the inefficient frequency + * @frequency: the inefficient frequency + * + * The &struct cpufreq_policy must use a sorted frequency table + * + * Return: %0 on success or a negative errno code + */ + +static inline int +cpufreq_table_set_inefficient(struct cpufreq_policy *policy, + unsigned int frequency) +{ + struct cpufreq_frequency_table *pos; + + /* Not supported */ + if (policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED) + return -EINVAL; + + cpufreq_for_each_valid_entry(pos, policy->freq_table) { + if (pos->frequency == frequency) { + pos->flags |= CPUFREQ_INEFFICIENT_FREQ; + return 0; + } + } + + return -EINVAL; +} + static inline int parse_perf_domain(int cpu, const char *list_name, const char *cell_name) { @@ -1071,6 +1102,13 @@ static inline bool policy_has_boost_freq(struct cpufreq_policy *policy) return false; } +static inline int +cpufreq_table_set_inefficient(struct cpufreq_policy *policy, + unsigned int frequency) +{ + return -EINVAL; +} + static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_name, const char *cell_name, struct cpumask *cpumask) { -- cgit v1.2.3 From 1f39fa0dccff71d4788089b5e617229b19166867 Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Sep 2021 15:05:28 +0100 Subject: cpufreq: Introducing CPUFREQ_RELATION_E This newly introduced flag can be applied by a governor to a CPUFreq relation, when looking for a frequency within the policy table. The resolution would then only walk through efficient frequencies. Even with the flag set, the policy max limit will still be honoured. If no efficient frequencies can be found within the limits of the policy, an inefficient one would be returned. Signed-off-by: Vincent Donnefort Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/acpi-cpufreq.c | 3 +- drivers/cpufreq/amd_freq_sensitivity.c | 3 +- drivers/cpufreq/cpufreq.c | 10 ++- drivers/cpufreq/cpufreq_ondemand.c | 6 +- drivers/cpufreq/powernv-cpufreq.c | 4 +- drivers/cpufreq/s5pv210-cpufreq.c | 2 +- include/linux/cpufreq.h | 111 +++++++++++++++++++++++++-------- 7 files changed, 106 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c index 28467d83c745..3d514b82d055 100644 --- a/drivers/cpufreq/acpi-cpufreq.c +++ b/drivers/cpufreq/acpi-cpufreq.c @@ -470,7 +470,8 @@ static unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy, if (policy->cached_target_freq == target_freq) index = policy->cached_resolved_idx; else - index = cpufreq_table_find_index_dl(policy, target_freq); + index = cpufreq_table_find_index_dl(policy, target_freq, + false); entry = &policy->freq_table[index]; next_freq = entry->frequency; diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c index d0b10baf039a..6448e03bcf48 100644 --- a/drivers/cpufreq/amd_freq_sensitivity.c +++ b/drivers/cpufreq/amd_freq_sensitivity.c @@ -91,7 +91,8 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy, unsigned int index; index = cpufreq_table_find_index_h(policy, - policy->cur - 1); + policy->cur - 1, + relation & CPUFREQ_RELATION_E); freq_next = policy->freq_table[index].frequency; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 284e940084c6..8069a7bac9ef 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2260,8 +2260,16 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy, !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS)) return 0; - if (cpufreq_driver->target) + if (cpufreq_driver->target) { + /* + * If the driver hasn't setup a single inefficient frequency, + * it's unlikely it knows how to decode CPUFREQ_RELATION_E. + */ + if (!policy->efficiencies_available) + relation &= ~CPUFREQ_RELATION_E; + return cpufreq_driver->target(policy, target_freq, relation); + } if (!cpufreq_driver->target_index) return -EINVAL; diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index eb4320b619c9..f68cad9abd11 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -83,9 +83,11 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy, freq_avg = freq_req - freq_reduc; /* Find freq bounds for freq_avg in freq_table */ - index = cpufreq_table_find_index_h(policy, freq_avg); + index = cpufreq_table_find_index_h(policy, freq_avg, + relation & CPUFREQ_RELATION_E); freq_lo = freq_table[index].frequency; - index = cpufreq_table_find_index_l(policy, freq_avg); + index = cpufreq_table_find_index_l(policy, freq_avg, + relation & CPUFREQ_RELATION_E); freq_hi = freq_table[index].frequency; /* Find out how long we have to be in hi and lo freqs */ diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 5a2cf5f91ccb..fddbd1ea1635 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -934,7 +934,7 @@ static void powernv_cpufreq_work_fn(struct work_struct *work) policy = cpufreq_cpu_get(cpu); if (!policy) continue; - index = cpufreq_table_find_index_c(policy, policy->cur); + index = cpufreq_table_find_index_c(policy, policy->cur, false); powernv_cpufreq_target_index(policy, index); cpumask_andnot(&mask, &mask, policy->cpus); cpufreq_cpu_put(policy); @@ -1022,7 +1022,7 @@ static unsigned int powernv_fast_switch(struct cpufreq_policy *policy, int index; struct powernv_smp_call_data freq_data; - index = cpufreq_table_find_index_dl(policy, target_freq); + index = cpufreq_table_find_index_dl(policy, target_freq, false); freq_data.pstate_id = powernv_freqs[index].driver_data; freq_data.gpstate_id = powernv_freqs[index].driver_data; set_pstate(&freq_data); diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c index ad7d4f272ddc..76c888ed8d16 100644 --- a/drivers/cpufreq/s5pv210-cpufreq.c +++ b/drivers/cpufreq/s5pv210-cpufreq.c @@ -243,7 +243,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index) new_freq = s5pv210_freq_table[index].frequency; /* Finding current running level index */ - priv_index = cpufreq_table_find_index_h(policy, old_freq); + priv_index = cpufreq_table_find_index_h(policy, old_freq, false); arm_volt = dvs_conf[index].arm_volt; int_volt = dvs_conf[index].int_volt; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 16997e1ff3fe..6d96bd452d55 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -118,6 +118,13 @@ struct cpufreq_policy { */ bool strict_target; + /* + * Set if inefficient frequencies were found in the frequency table. + * This indicates if the relation flag CPUFREQ_RELATION_E can be + * honored. + */ + bool efficiencies_available; + /* * Preferred average time interval between consecutive invocations of * the driver to set the frequency for this policy. To be set by the @@ -273,6 +280,8 @@ static inline void cpufreq_stats_record_transition(struct cpufreq_policy *policy #define CPUFREQ_RELATION_L 0 /* lowest frequency at or above target */ #define CPUFREQ_RELATION_H 1 /* highest frequency below or at target */ #define CPUFREQ_RELATION_C 2 /* closest frequency to target */ +/* relation flags */ +#define CPUFREQ_RELATION_E BIT(2) /* Get if possible an efficient frequency */ struct freq_attr { struct attribute attr; @@ -741,6 +750,22 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev, continue; \ else +/** + * cpufreq_for_each_efficient_entry_idx - iterate with index over a cpufreq + * frequency_table excluding CPUFREQ_ENTRY_INVALID and + * CPUFREQ_INEFFICIENT_FREQ frequencies. + * @pos: the &struct cpufreq_frequency_table to use as a loop cursor. + * @table: the &struct cpufreq_frequency_table to iterate over. + * @idx: the table entry currently being processed. + * @efficiencies: set to true to only iterate over efficient frequencies. + */ + +#define cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) \ + cpufreq_for_each_valid_entry_idx(pos, table, idx) \ + if (efficiencies && (pos->flags & CPUFREQ_INEFFICIENT_FREQ)) \ + continue; \ + else + int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table); @@ -765,14 +790,15 @@ bool policy_has_boost_freq(struct cpufreq_policy *policy); /* Find lowest freq at or above target in a table in ascending order */ static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { struct cpufreq_frequency_table *table = policy->freq_table; struct cpufreq_frequency_table *pos; unsigned int freq; int idx, best = -1; - cpufreq_for_each_valid_entry_idx(pos, table, idx) { + cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) { freq = pos->frequency; if (freq >= target_freq) @@ -786,14 +812,15 @@ static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy, /* Find lowest freq at or above target in a table in descending order */ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { struct cpufreq_frequency_table *table = policy->freq_table; struct cpufreq_frequency_table *pos; unsigned int freq; int idx, best = -1; - cpufreq_for_each_valid_entry_idx(pos, table, idx) { + cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) { freq = pos->frequency; if (freq == target_freq) @@ -816,26 +843,30 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy, /* Works only on sorted freq-tables */ static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { target_freq = clamp_val(target_freq, policy->min, policy->max); if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING) - return cpufreq_table_find_index_al(policy, target_freq); + return cpufreq_table_find_index_al(policy, target_freq, + efficiencies); else - return cpufreq_table_find_index_dl(policy, target_freq); + return cpufreq_table_find_index_dl(policy, target_freq, + efficiencies); } /* Find highest freq at or below target in a table in ascending order */ static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { struct cpufreq_frequency_table *table = policy->freq_table; struct cpufreq_frequency_table *pos; unsigned int freq; int idx, best = -1; - cpufreq_for_each_valid_entry_idx(pos, table, idx) { + cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) { freq = pos->frequency; if (freq == target_freq) @@ -858,14 +889,15 @@ static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy, /* Find highest freq at or below target in a table in descending order */ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { struct cpufreq_frequency_table *table = policy->freq_table; struct cpufreq_frequency_table *pos; unsigned int freq; int idx, best = -1; - cpufreq_for_each_valid_entry_idx(pos, table, idx) { + cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) { freq = pos->frequency; if (freq <= target_freq) @@ -879,26 +911,30 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy, /* Works only on sorted freq-tables */ static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { target_freq = clamp_val(target_freq, policy->min, policy->max); if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING) - return cpufreq_table_find_index_ah(policy, target_freq); + return cpufreq_table_find_index_ah(policy, target_freq, + efficiencies); else - return cpufreq_table_find_index_dh(policy, target_freq); + return cpufreq_table_find_index_dh(policy, target_freq, + efficiencies); } /* Find closest freq to target in a table in ascending order */ static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { struct cpufreq_frequency_table *table = policy->freq_table; struct cpufreq_frequency_table *pos; unsigned int freq; int idx, best = -1; - cpufreq_for_each_valid_entry_idx(pos, table, idx) { + cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) { freq = pos->frequency; if (freq == target_freq) @@ -925,14 +961,15 @@ static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy, /* Find closest freq to target in a table in descending order */ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { struct cpufreq_frequency_table *table = policy->freq_table; struct cpufreq_frequency_table *pos; unsigned int freq; int idx, best = -1; - cpufreq_for_each_valid_entry_idx(pos, table, idx) { + cpufreq_for_each_efficient_entry_idx(pos, table, idx, efficiencies) { freq = pos->frequency; if (freq == target_freq) @@ -959,35 +996,58 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy, /* Works only on sorted freq-tables */ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy, - unsigned int target_freq) + unsigned int target_freq, + bool efficiencies) { target_freq = clamp_val(target_freq, policy->min, policy->max); if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING) - return cpufreq_table_find_index_ac(policy, target_freq); + return cpufreq_table_find_index_ac(policy, target_freq, + efficiencies); else - return cpufreq_table_find_index_dc(policy, target_freq); + return cpufreq_table_find_index_dc(policy, target_freq, + efficiencies); } static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) { + bool efficiencies = policy->efficiencies_available && + (relation & CPUFREQ_RELATION_E); + int idx; + + /* cpufreq_table_index_unsorted() has no use for this flag anyway */ + relation &= ~CPUFREQ_RELATION_E; + if (unlikely(policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED)) return cpufreq_table_index_unsorted(policy, target_freq, relation); - +retry: switch (relation) { case CPUFREQ_RELATION_L: - return cpufreq_table_find_index_l(policy, target_freq); + idx = cpufreq_table_find_index_l(policy, target_freq, + efficiencies); + break; case CPUFREQ_RELATION_H: - return cpufreq_table_find_index_h(policy, target_freq); + idx = cpufreq_table_find_index_h(policy, target_freq, + efficiencies); + break; case CPUFREQ_RELATION_C: - return cpufreq_table_find_index_c(policy, target_freq); + idx = cpufreq_table_find_index_c(policy, target_freq, + efficiencies); + break; default: WARN_ON_ONCE(1); return 0; } + + if (idx < 0 && efficiencies) { + efficiencies = false; + goto retry; + } + + return idx; } static inline int cpufreq_table_count_valid_entries(const struct cpufreq_policy *policy) @@ -1027,6 +1087,7 @@ cpufreq_table_set_inefficient(struct cpufreq_policy *policy, cpufreq_for_each_valid_entry(pos, policy->freq_table) { if (pos->frequency == frequency) { pos->flags |= CPUFREQ_INEFFICIENT_FREQ; + policy->efficiencies_available = true; return 0; } } -- cgit v1.2.3 From b894d20e6867f04827c7817fbc155460ff108f6f Mon Sep 17 00:00:00 2001 From: Vincent Donnefort Date: Wed, 8 Sep 2021 15:05:29 +0100 Subject: cpufreq: Use CPUFREQ_RELATION_E in DVFS governors Let the governors schedutil, conservative and ondemand to work, if possible on efficient frequencies only. Signed-off-by: Vincent Donnefort Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/cpufreq/cpufreq.c | 2 +- drivers/cpufreq/cpufreq_conservative.c | 6 ++++-- drivers/cpufreq/cpufreq_ondemand.c | 10 +++++----- include/linux/cpufreq.h | 10 ++++++++-- 4 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 8069a7bac9ef..e338d2f010fe 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -554,7 +554,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy, unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy, unsigned int target_freq) { - return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_L); + return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_LE); } EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq); diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c index aa39ff31ec9f..0879ec3c170c 100644 --- a/drivers/cpufreq/cpufreq_conservative.c +++ b/drivers/cpufreq/cpufreq_conservative.c @@ -111,7 +111,8 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy) if (requested_freq > policy->max) requested_freq = policy->max; - __cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_H); + __cpufreq_driver_target(policy, requested_freq, + CPUFREQ_RELATION_HE); dbs_info->requested_freq = requested_freq; goto out; } @@ -134,7 +135,8 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy) else requested_freq = policy->min; - __cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_L); + __cpufreq_driver_target(policy, requested_freq, + CPUFREQ_RELATION_LE); dbs_info->requested_freq = requested_freq; } diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c index f68cad9abd11..3b8f924771b4 100644 --- a/drivers/cpufreq/cpufreq_ondemand.c +++ b/drivers/cpufreq/cpufreq_ondemand.c @@ -120,12 +120,12 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq) if (od_tuners->powersave_bias) freq = od_ops.powersave_bias_target(policy, freq, - CPUFREQ_RELATION_H); + CPUFREQ_RELATION_HE); else if (policy->cur == policy->max) return; __cpufreq_driver_target(policy, freq, od_tuners->powersave_bias ? - CPUFREQ_RELATION_L : CPUFREQ_RELATION_H); + CPUFREQ_RELATION_LE : CPUFREQ_RELATION_HE); } /* @@ -163,9 +163,9 @@ static void od_update(struct cpufreq_policy *policy) if (od_tuners->powersave_bias) freq_next = od_ops.powersave_bias_target(policy, freq_next, - CPUFREQ_RELATION_L); + CPUFREQ_RELATION_LE); - __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_C); + __cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_CE); } } @@ -184,7 +184,7 @@ static unsigned int od_dbs_update(struct cpufreq_policy *policy) */ if (sample_type == OD_SUB_SAMPLE && policy_dbs->sample_delay_ns > 0) { __cpufreq_driver_target(policy, dbs_info->freq_lo, - CPUFREQ_RELATION_H); + CPUFREQ_RELATION_HE); return dbs_info->freq_lo_delay_us; } diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 6d96bd452d55..7ce71c7371fb 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -283,6 +283,10 @@ static inline void cpufreq_stats_record_transition(struct cpufreq_policy *policy /* relation flags */ #define CPUFREQ_RELATION_E BIT(2) /* Get if possible an efficient frequency */ +#define CPUFREQ_RELATION_LE (CPUFREQ_RELATION_L | CPUFREQ_RELATION_E) +#define CPUFREQ_RELATION_HE (CPUFREQ_RELATION_H | CPUFREQ_RELATION_E) +#define CPUFREQ_RELATION_CE (CPUFREQ_RELATION_C | CPUFREQ_RELATION_E) + struct freq_attr { struct attribute attr; ssize_t (*show)(struct cpufreq_policy *, char *); @@ -636,9 +640,11 @@ struct cpufreq_governor *cpufreq_fallback_governor(void); static inline void cpufreq_policy_apply_limits(struct cpufreq_policy *policy) { if (policy->max < policy->cur) - __cpufreq_driver_target(policy, policy->max, CPUFREQ_RELATION_H); + __cpufreq_driver_target(policy, policy->max, + CPUFREQ_RELATION_HE); else if (policy->min > policy->cur) - __cpufreq_driver_target(policy, policy->min, CPUFREQ_RELATION_L); + __cpufreq_driver_target(policy, policy->min, + CPUFREQ_RELATION_LE); } /* Governor attribute set */ -- cgit v1.2.3 From 4ad81f6ef89b62434f1d2ed26e9bec9d0e3d9dfe Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Mon, 4 Oct 2021 22:06:41 +0200 Subject: clk: tegra: Add stubs needed for compile testing These stubs are needed to allow the tegra-cpuidle driver to be compile-tested. Signed-off-by: Thierry Reding --- include/linux/clk/tegra.h | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk/tegra.h b/include/linux/clk/tegra.h index d128ad1570aa..3650e926e93f 100644 --- a/include/linux/clk/tegra.h +++ b/include/linux/clk/tegra.h @@ -42,6 +42,7 @@ struct tegra_cpu_car_ops { #endif }; +#ifdef CONFIG_ARCH_TEGRA extern struct tegra_cpu_car_ops *tegra_cpu_car_ops; static inline void tegra_wait_cpu_in_reset(u32 cpu) @@ -83,8 +84,29 @@ static inline void tegra_disable_cpu_clock(u32 cpu) tegra_cpu_car_ops->disable_clock(cpu); } +#else +static inline void tegra_wait_cpu_in_reset(u32 cpu) +{ +} -#ifdef CONFIG_PM_SLEEP +static inline void tegra_put_cpu_in_reset(u32 cpu) +{ +} + +static inline void tegra_cpu_out_of_reset(u32 cpu) +{ +} + +static inline void tegra_enable_cpu_clock(u32 cpu) +{ +} + +static inline void tegra_disable_cpu_clock(u32 cpu) +{ +} +#endif + +#if defined(CONFIG_ARCH_TEGRA) && defined(CONFIG_PM_SLEEP) static inline bool tegra_cpu_rail_off_ready(void) { if (WARN_ON(!tegra_cpu_car_ops->rail_off_ready)) -- cgit v1.2.3 From 2357672c54c3f748f675446f8eba8b0432b1e7e2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:49 +0530 Subject: bpf: Introduce BPF support for kernel module function calls This change adds support on the kernel side to allow for BPF programs to call kernel module functions. Userspace will prepare an array of module BTF fds that is passed in during BPF_PROG_LOAD using fd_array parameter. In the kernel, the module BTFs are placed in the auxilliary struct for bpf_prog, and loaded as needed. The verifier then uses insn->off to index into the fd_array. insn->off 0 is reserved for vmlinux BTF (for backwards compat), so userspace must use an fd_array index > 0 for module kfunc support. kfunc_btf_tab is sorted based on offset in an array, and each offset corresponds to one descriptor, with a max limit up to 256 such module BTFs. We also change existing kfunc_tab to distinguish each element based on imm, off pair as each such call will now be distinct. Another change is to check_kfunc_call callback, which now include a struct module * pointer, this is to be used in later patch such that the kfunc_id and module pointer are matched for dynamically registered BTF sets from loadable modules, so that same kfunc_id in two modules doesn't lead to check_kfunc_call succeeding. For the duration of the check_kfunc_call, the reference to struct module exists, as it returns the pointer stored in kfunc_btf_tab. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-2-memxor@gmail.com --- include/linux/bpf.h | 8 +- include/linux/bpf_verifier.h | 2 + kernel/bpf/core.c | 4 + kernel/bpf/verifier.c | 202 +++++++++++++++++++++++++++++++++++++------ net/bpf/test_run.c | 2 +- net/ipv4/bpf_tcp_ca.c | 2 +- 6 files changed, 188 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 1c7fd7c4c6d3..d604c8251d88 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -513,7 +513,7 @@ struct bpf_verifier_ops { const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); - bool (*check_kfunc_call)(u32 kfunc_btf_id); + bool (*check_kfunc_call)(u32 kfunc_btf_id, struct module *owner); }; struct bpf_prog_offload_ops { @@ -877,6 +877,7 @@ struct bpf_prog_aux { void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; + struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; struct bpf_ksym ksym; const struct bpf_prog_ops *ops; @@ -1639,7 +1640,7 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id); +bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); @@ -1860,7 +1861,8 @@ static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, return -ENOTSUPP; } -static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) +static inline bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, + struct module *owner) { return false; } diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 5424124dbe36..c8a78e830fca 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -527,5 +527,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, const struct bpf_prog *tgt_prog, u32 btf_id, struct bpf_attach_target_info *tgt_info); +void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); + #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ea8a468dbded..b6c72af64d5d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -2255,6 +2256,9 @@ static void bpf_prog_free_deferred(struct work_struct *work) int i; aux = container_of(work, struct bpf_prog_aux, work); +#ifdef CONFIG_BPF_SYSCALL + bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab); +#endif bpf_free_used_maps(aux); bpf_free_used_btfs(aux); if (bpf_prog_is_dev_bound(aux)) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1433752db740..1d6d10265cab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1640,52 +1640,173 @@ static int add_subprog(struct bpf_verifier_env *env, int off) return env->subprog_cnt - 1; } +#define MAX_KFUNC_DESCS 256 +#define MAX_KFUNC_BTFS 256 + struct bpf_kfunc_desc { struct btf_func_model func_model; u32 func_id; s32 imm; + u16 offset; +}; + +struct bpf_kfunc_btf { + struct btf *btf; + struct module *module; + u16 offset; }; -#define MAX_KFUNC_DESCS 256 struct bpf_kfunc_desc_tab { struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS]; u32 nr_descs; }; -static int kfunc_desc_cmp_by_id(const void *a, const void *b) +struct bpf_kfunc_btf_tab { + struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS]; + u32 nr_descs; +}; + +static int kfunc_desc_cmp_by_id_off(const void *a, const void *b) { const struct bpf_kfunc_desc *d0 = a; const struct bpf_kfunc_desc *d1 = b; /* func_id is not greater than BTF_MAX_TYPE */ - return d0->func_id - d1->func_id; + return d0->func_id - d1->func_id ?: d0->offset - d1->offset; +} + +static int kfunc_btf_cmp_by_off(const void *a, const void *b) +{ + const struct bpf_kfunc_btf *d0 = a; + const struct bpf_kfunc_btf *d1 = b; + + return d0->offset - d1->offset; } static const struct bpf_kfunc_desc * -find_kfunc_desc(const struct bpf_prog *prog, u32 func_id) +find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset) { struct bpf_kfunc_desc desc = { .func_id = func_id, + .offset = offset, }; struct bpf_kfunc_desc_tab *tab; tab = prog->aux->kfunc_tab; return bsearch(&desc, tab->descs, tab->nr_descs, - sizeof(tab->descs[0]), kfunc_desc_cmp_by_id); + sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off); +} + +static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env, + s16 offset, struct module **btf_modp) +{ + struct bpf_kfunc_btf kf_btf = { .offset = offset }; + struct bpf_kfunc_btf_tab *tab; + struct bpf_kfunc_btf *b; + struct module *mod; + struct btf *btf; + int btf_fd; + + tab = env->prog->aux->kfunc_btf_tab; + b = bsearch(&kf_btf, tab->descs, tab->nr_descs, + sizeof(tab->descs[0]), kfunc_btf_cmp_by_off); + if (!b) { + if (tab->nr_descs == MAX_KFUNC_BTFS) { + verbose(env, "too many different module BTFs\n"); + return ERR_PTR(-E2BIG); + } + + if (bpfptr_is_null(env->fd_array)) { + verbose(env, "kfunc offset > 0 without fd_array is invalid\n"); + return ERR_PTR(-EPROTO); + } + + if (copy_from_bpfptr_offset(&btf_fd, env->fd_array, + offset * sizeof(btf_fd), + sizeof(btf_fd))) + return ERR_PTR(-EFAULT); + + btf = btf_get_by_fd(btf_fd); + if (IS_ERR(btf)) + return btf; + + if (!btf_is_module(btf)) { + verbose(env, "BTF fd for kfunc is not a module BTF\n"); + btf_put(btf); + return ERR_PTR(-EINVAL); + } + + mod = btf_try_get_module(btf); + if (!mod) { + btf_put(btf); + return ERR_PTR(-ENXIO); + } + + b = &tab->descs[tab->nr_descs++]; + b->btf = btf; + b->module = mod; + b->offset = offset; + + sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), + kfunc_btf_cmp_by_off, NULL); + } + if (btf_modp) + *btf_modp = b->module; + return b->btf; } -static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) +void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab) +{ + if (!tab) + return; + + while (tab->nr_descs--) { + module_put(tab->descs[tab->nr_descs].module); + btf_put(tab->descs[tab->nr_descs].btf); + } + kfree(tab); +} + +static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, + u32 func_id, s16 offset, + struct module **btf_modp) +{ + struct btf *kfunc_btf; + + if (offset) { + if (offset < 0) { + /* In the future, this can be allowed to increase limit + * of fd index into fd_array, interpreted as u16. + */ + verbose(env, "negative offset disallowed for kernel module function call\n"); + return ERR_PTR(-EINVAL); + } + + kfunc_btf = __find_kfunc_desc_btf(env, offset, btf_modp); + if (IS_ERR_OR_NULL(kfunc_btf)) { + verbose(env, "cannot find module BTF for func_id %u\n", func_id); + return kfunc_btf ?: ERR_PTR(-ENOENT); + } + return kfunc_btf; + } + return btf_vmlinux ?: ERR_PTR(-ENOENT); +} + +static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset) { const struct btf_type *func, *func_proto; + struct bpf_kfunc_btf_tab *btf_tab; struct bpf_kfunc_desc_tab *tab; struct bpf_prog_aux *prog_aux; struct bpf_kfunc_desc *desc; const char *func_name; + struct btf *desc_btf; unsigned long addr; int err; prog_aux = env->prog->aux; tab = prog_aux->kfunc_tab; + btf_tab = prog_aux->kfunc_btf_tab; if (!tab) { if (!btf_vmlinux) { verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n"); @@ -1713,7 +1834,20 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) prog_aux->kfunc_tab = tab; } - if (find_kfunc_desc(env->prog, func_id)) + if (!btf_tab && offset) { + btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL); + if (!btf_tab) + return -ENOMEM; + prog_aux->kfunc_btf_tab = btf_tab; + } + + desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL); + if (IS_ERR(desc_btf)) { + verbose(env, "failed to find BTF for kernel function\n"); + return PTR_ERR(desc_btf); + } + + if (find_kfunc_desc(env->prog, func_id, offset)) return 0; if (tab->nr_descs == MAX_KFUNC_DESCS) { @@ -1721,20 +1855,20 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) return -E2BIG; } - func = btf_type_by_id(btf_vmlinux, func_id); + func = btf_type_by_id(desc_btf, func_id); if (!func || !btf_type_is_func(func)) { verbose(env, "kernel btf_id %u is not a function\n", func_id); return -EINVAL; } - func_proto = btf_type_by_id(btf_vmlinux, func->type); + func_proto = btf_type_by_id(desc_btf, func->type); if (!func_proto || !btf_type_is_func_proto(func_proto)) { verbose(env, "kernel function btf_id %u does not have a valid func_proto\n", func_id); return -EINVAL; } - func_name = btf_name_by_offset(btf_vmlinux, func->name_off); + func_name = btf_name_by_offset(desc_btf, func->name_off); addr = kallsyms_lookup_name(func_name); if (!addr) { verbose(env, "cannot find address for kernel function %s\n", @@ -1745,12 +1879,13 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id) desc = &tab->descs[tab->nr_descs++]; desc->func_id = func_id; desc->imm = BPF_CALL_IMM(addr); - err = btf_distill_func_proto(&env->log, btf_vmlinux, + desc->offset = offset; + err = btf_distill_func_proto(&env->log, desc_btf, func_proto, func_name, &desc->func_model); if (!err) sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]), - kfunc_desc_cmp_by_id, NULL); + kfunc_desc_cmp_by_id_off, NULL); return err; } @@ -1829,7 +1964,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) } else if (bpf_pseudo_call(insn)) { ret = add_subprog(env, i + insn->imm + 1); } else { - ret = add_kfunc_call(env, insn->imm); + ret = add_kfunc_call(env, insn->imm, insn->off); } if (ret < 0) @@ -2166,12 +2301,17 @@ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i, static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn) { const struct btf_type *func; + struct btf *desc_btf; if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL) return NULL; - func = btf_type_by_id(btf_vmlinux, insn->imm); - return btf_name_by_offset(btf_vmlinux, func->name_off); + desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL); + if (IS_ERR(desc_btf)) + return ""; + + func = btf_type_by_id(desc_btf, insn->imm); + return btf_name_by_offset(desc_btf, func->name_off); } /* For given verifier state backtrack_insn() is called from the last insn to @@ -6530,23 +6670,29 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) struct bpf_reg_state *regs = cur_regs(env); const char *func_name, *ptr_type_name; u32 i, nargs, func_id, ptr_type_id; + struct module *btf_mod = NULL; const struct btf_param *args; + struct btf *desc_btf; int err; + desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod); + if (IS_ERR(desc_btf)) + return PTR_ERR(desc_btf); + func_id = insn->imm; - func = btf_type_by_id(btf_vmlinux, func_id); - func_name = btf_name_by_offset(btf_vmlinux, func->name_off); - func_proto = btf_type_by_id(btf_vmlinux, func->type); + func = btf_type_by_id(desc_btf, func_id); + func_name = btf_name_by_offset(desc_btf, func->name_off); + func_proto = btf_type_by_id(desc_btf, func->type); if (!env->ops->check_kfunc_call || - !env->ops->check_kfunc_call(func_id)) { + !env->ops->check_kfunc_call(func_id, btf_mod)) { verbose(env, "calling kernel function %s is not allowed\n", func_name); return -EACCES; } /* Check the arguments */ - err = btf_check_kfunc_arg_match(env, btf_vmlinux, func_id, regs); + err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs); if (err) return err; @@ -6554,15 +6700,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) mark_reg_not_init(env, regs, caller_saved[i]); /* Check return type */ - t = btf_type_skip_modifiers(btf_vmlinux, func_proto->type, NULL); + t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL); if (btf_type_is_scalar(t)) { mark_reg_unknown(env, regs, BPF_REG_0); mark_btf_func_reg_size(env, BPF_REG_0, t->size); } else if (btf_type_is_ptr(t)) { - ptr_type = btf_type_skip_modifiers(btf_vmlinux, t->type, + ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id); if (!btf_type_is_struct(ptr_type)) { - ptr_type_name = btf_name_by_offset(btf_vmlinux, + ptr_type_name = btf_name_by_offset(desc_btf, ptr_type->name_off); verbose(env, "kernel function %s returns pointer type %s %s is not supported\n", func_name, btf_type_str(ptr_type), @@ -6570,7 +6716,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].btf = btf_vmlinux; + regs[BPF_REG_0].btf = desc_btf; regs[BPF_REG_0].type = PTR_TO_BTF_ID; regs[BPF_REG_0].btf_id = ptr_type_id; mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *)); @@ -6581,7 +6727,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn) for (i = 0; i < nargs; i++) { u32 regno = i + 1; - t = btf_type_skip_modifiers(btf_vmlinux, args[i].type, NULL); + t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL); if (btf_type_is_ptr(t)) mark_btf_func_reg_size(env, regno, sizeof(void *)); else @@ -11121,7 +11267,8 @@ static int do_check(struct bpf_verifier_env *env) env->jmps_processed++; if (opcode == BPF_CALL) { if (BPF_SRC(insn->code) != BPF_K || - insn->off != 0 || + (insn->src_reg != BPF_PSEUDO_KFUNC_CALL + && insn->off != 0) || (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL && insn->src_reg != BPF_PSEUDO_KFUNC_CALL) || @@ -12477,6 +12624,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i]->aux->kfunc_tab = prog->aux->kfunc_tab; + func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab; func[i]->aux->linfo = prog->aux->linfo; func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; @@ -12665,7 +12813,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, /* insn->imm has the btf func_id. Replace it with * an address (relative to __bpf_base_call). */ - desc = find_kfunc_desc(env->prog, insn->imm); + desc = find_kfunc_desc(env->prog, insn->imm, insn->off); if (!desc) { verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n", insn->imm); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 072f0c16c779..b1f6f5237de6 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -241,7 +241,7 @@ BTF_ID(func, bpf_kfunc_call_test2) BTF_ID(func, bpf_kfunc_call_test3) BTF_SET_END(test_sk_kfunc_ids) -bool bpf_prog_test_check_kfunc_call(u32 kfunc_id) +bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner) { return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id); } diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 0dcee9df1326..b3afd3361f34 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -255,7 +255,7 @@ BTF_ID(func, bbr_set_state) #endif /* CONFIG_X86 */ BTF_SET_END(bpf_tcp_ca_kfunc_ids) -static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id) +static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id, struct module *owner) { return btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id); } -- cgit v1.2.3 From 14f267d95fe4b08831a022c8e15a2eb8991edbf6 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:51 +0530 Subject: bpf: btf: Introduce helpers for dynamic BTF set registration This adds helpers for registering btf_id_set from modules and the bpf_check_mod_kfunc_call callback that can be used to look them up. With in kernel sets, the way this is supposed to work is, in kernel callback looks up within the in-kernel kfunc whitelist, and then defers to the dynamic BTF set lookup if it doesn't find the BTF id. If there is no in-kernel BTF id set, this callback can be used directly. Also fix includes for btf.h and bpfptr.h so that they can included in isolation. This is in preparation for their usage in tcp_bbr, tcp_cubic and tcp_dctcp modules in the next patch. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-4-memxor@gmail.com --- include/linux/bpfptr.h | 1 + include/linux/btf.h | 36 ++++++++++++++++++++++++++++++++++ kernel/bpf/btf.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 89 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h index 546e27fc6d46..46e1757d06a3 100644 --- a/include/linux/bpfptr.h +++ b/include/linux/bpfptr.h @@ -3,6 +3,7 @@ #ifndef _LINUX_BPFPTR_H #define _LINUX_BPFPTR_H +#include #include typedef sockptr_t bpfptr_t; diff --git a/include/linux/btf.h b/include/linux/btf.h index 214fde93214b..6c4c61d821d7 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -5,6 +5,7 @@ #define _LINUX_BTF_H 1 #include +#include #include #include @@ -238,4 +239,39 @@ static inline const char *btf_name_by_offset(const struct btf *btf, } #endif +struct kfunc_btf_id_set { + struct list_head list; + struct btf_id_set *set; + struct module *owner; +}; + +struct kfunc_btf_id_list; + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES +void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s); +void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s); +bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, + struct module *owner); +#else +static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ +} +static inline void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ +} +static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, + u32 kfunc_id, struct module *owner) +{ + return false; +} +#endif + +#define DEFINE_KFUNC_BTF_ID_SET(set, name) \ + struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ + THIS_MODULE } + #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index c3d605b22473..62cbeb4951eb 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6343,3 +6343,55 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { }; BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) + +/* BTF ID set registration API for modules */ + +struct kfunc_btf_id_list { + struct list_head list; + struct mutex mutex; +}; + +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + +void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ + mutex_lock(&l->mutex); + list_add(&s->list, &l->list); + mutex_unlock(&l->mutex); +} +EXPORT_SYMBOL_GPL(register_kfunc_btf_id_set); + +void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, + struct kfunc_btf_id_set *s) +{ + mutex_lock(&l->mutex); + list_del_init(&s->list); + mutex_unlock(&l->mutex); +} +EXPORT_SYMBOL_GPL(unregister_kfunc_btf_id_set); + +bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, + struct module *owner) +{ + struct kfunc_btf_id_set *s; + + if (!owner) + return false; + mutex_lock(&klist->mutex); + list_for_each_entry(s, &klist->list, list) { + if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { + mutex_unlock(&klist->mutex); + return true; + } + } + mutex_unlock(&klist->mutex); + return false; +} + +#endif + +#define DEFINE_KFUNC_BTF_ID_LIST(name) \ + struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ + __MUTEX_INITIALIZER(name.mutex) }; \ + EXPORT_SYMBOL_GPL(name) -- cgit v1.2.3 From 0e32dfc80bae53b05e9eda7eaf259f30ab9ba43a Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:53 +0530 Subject: bpf: Enable TCP congestion control kfunc from modules This commit moves BTF ID lookup into the newly added registration helper, in a way that the bbr, cubic, and dctcp implementation set up their sets in the bpf_tcp_ca kfunc_btf_set list, while the ones not dependent on modules are looked up from the wrapper function. This lifts the restriction for them to be compiled as built in objects, and can be loaded as modules if required. Also modify Makefile.modfinal to call resolve_btfids for each module. Note that since kernel kfunc_ids never overlap with module kfunc_ids, we only match the owner for module btf id sets. See following commits for background on use of: CONFIG_X86 ifdef: 569c484f9995 (bpf: Limit static tcp-cc functions in the .BTF_ids list to x86) CONFIG_DYNAMIC_FTRACE ifdef: 7aae231ac93b (bpf: tcp: Limit calling some tcp cc functions to CONFIG_DYNAMIC_FTRACE) Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-6-memxor@gmail.com --- include/linux/btf.h | 2 ++ kernel/bpf/btf.c | 2 ++ net/ipv4/bpf_tcp_ca.c | 34 +++------------------------------- net/ipv4/tcp_bbr.c | 28 +++++++++++++++++++++++++++- net/ipv4/tcp_cubic.c | 26 +++++++++++++++++++++++++- net/ipv4/tcp_dctcp.c | 26 +++++++++++++++++++++++++- scripts/Makefile.modfinal | 1 + 7 files changed, 85 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 6c4c61d821d7..1d56cd2bb362 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -274,4 +274,6 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ THIS_MODULE } +extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; + #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 62cbeb4951eb..1460dff3c154 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6395,3 +6395,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ EXPORT_SYMBOL_GPL(name) + +DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index b3afd3361f34..57709ac09fb2 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -223,41 +223,13 @@ BTF_ID(func, tcp_reno_cong_avoid) BTF_ID(func, tcp_reno_undo_cwnd) BTF_ID(func, tcp_slow_start) BTF_ID(func, tcp_cong_avoid_ai) -#ifdef CONFIG_X86 -#ifdef CONFIG_DYNAMIC_FTRACE -#if IS_BUILTIN(CONFIG_TCP_CONG_CUBIC) -BTF_ID(func, cubictcp_init) -BTF_ID(func, cubictcp_recalc_ssthresh) -BTF_ID(func, cubictcp_cong_avoid) -BTF_ID(func, cubictcp_state) -BTF_ID(func, cubictcp_cwnd_event) -BTF_ID(func, cubictcp_acked) -#endif -#if IS_BUILTIN(CONFIG_TCP_CONG_DCTCP) -BTF_ID(func, dctcp_init) -BTF_ID(func, dctcp_update_alpha) -BTF_ID(func, dctcp_cwnd_event) -BTF_ID(func, dctcp_ssthresh) -BTF_ID(func, dctcp_cwnd_undo) -BTF_ID(func, dctcp_state) -#endif -#if IS_BUILTIN(CONFIG_TCP_CONG_BBR) -BTF_ID(func, bbr_init) -BTF_ID(func, bbr_main) -BTF_ID(func, bbr_sndbuf_expand) -BTF_ID(func, bbr_undo_cwnd) -BTF_ID(func, bbr_cwnd_event) -BTF_ID(func, bbr_ssthresh) -BTF_ID(func, bbr_min_tso_segs) -BTF_ID(func, bbr_set_state) -#endif -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_X86 */ BTF_SET_END(bpf_tcp_ca_kfunc_ids) static bool bpf_tcp_ca_check_kfunc_call(u32 kfunc_btf_id, struct module *owner) { - return btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id); + if (btf_id_set_contains(&bpf_tcp_ca_kfunc_ids, kfunc_btf_id)) + return true; + return bpf_check_mod_kfunc_call(&bpf_tcp_ca_kfunc_list, kfunc_btf_id, owner); } static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 6274462b86b4..ec5550089b4d 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -56,6 +56,8 @@ * otherwise TCP stack falls back to an internal pacing using one high * resolution timer per TCP socket and may use more resources. */ +#include +#include #include #include #include @@ -1152,14 +1154,38 @@ static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = { .set_state = bbr_set_state, }; +BTF_SET_START(tcp_bbr_kfunc_ids) +#ifdef CONFIG_X86 +#ifdef CONFIG_DYNAMIC_FTRACE +BTF_ID(func, bbr_init) +BTF_ID(func, bbr_main) +BTF_ID(func, bbr_sndbuf_expand) +BTF_ID(func, bbr_undo_cwnd) +BTF_ID(func, bbr_cwnd_event) +BTF_ID(func, bbr_ssthresh) +BTF_ID(func, bbr_min_tso_segs) +BTF_ID(func, bbr_set_state) +#endif +#endif +BTF_SET_END(tcp_bbr_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&tcp_bbr_kfunc_ids, tcp_bbr_kfunc_btf_set); + static int __init bbr_register(void) { + int ret; + BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE); - return tcp_register_congestion_control(&tcp_bbr_cong_ops); + ret = tcp_register_congestion_control(&tcp_bbr_cong_ops); + if (ret) + return ret; + register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); + return 0; } static void __exit bbr_unregister(void) { + unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_bbr_kfunc_btf_set); tcp_unregister_congestion_control(&tcp_bbr_cong_ops); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 4a30deaa9a37..5e9d9c51164c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -25,6 +25,8 @@ */ #include +#include +#include #include #include #include @@ -482,8 +484,25 @@ static struct tcp_congestion_ops cubictcp __read_mostly = { .name = "cubic", }; +BTF_SET_START(tcp_cubic_kfunc_ids) +#ifdef CONFIG_X86 +#ifdef CONFIG_DYNAMIC_FTRACE +BTF_ID(func, cubictcp_init) +BTF_ID(func, cubictcp_recalc_ssthresh) +BTF_ID(func, cubictcp_cong_avoid) +BTF_ID(func, cubictcp_state) +BTF_ID(func, cubictcp_cwnd_event) +BTF_ID(func, cubictcp_acked) +#endif +#endif +BTF_SET_END(tcp_cubic_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&tcp_cubic_kfunc_ids, tcp_cubic_kfunc_btf_set); + static int __init cubictcp_register(void) { + int ret; + BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); /* Precompute a bunch of the scaling factors that are used per-packet @@ -514,11 +533,16 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); - return tcp_register_congestion_control(&cubictcp); + ret = tcp_register_congestion_control(&cubictcp); + if (ret) + return ret; + register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); + return 0; } static void __exit cubictcp_unregister(void) { + unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_cubic_kfunc_btf_set); tcp_unregister_congestion_control(&cubictcp); } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 79f705450c16..0d7ab3cc7b61 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -36,6 +36,8 @@ * Glenn Judd */ +#include +#include #include #include #include @@ -236,14 +238,36 @@ static struct tcp_congestion_ops dctcp_reno __read_mostly = { .name = "dctcp-reno", }; +BTF_SET_START(tcp_dctcp_kfunc_ids) +#ifdef CONFIG_X86 +#ifdef CONFIG_DYNAMIC_FTRACE +BTF_ID(func, dctcp_init) +BTF_ID(func, dctcp_update_alpha) +BTF_ID(func, dctcp_cwnd_event) +BTF_ID(func, dctcp_ssthresh) +BTF_ID(func, dctcp_cwnd_undo) +BTF_ID(func, dctcp_state) +#endif +#endif +BTF_SET_END(tcp_dctcp_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&tcp_dctcp_kfunc_ids, tcp_dctcp_kfunc_btf_set); + static int __init dctcp_register(void) { + int ret; + BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE); - return tcp_register_congestion_control(&dctcp); + ret = tcp_register_congestion_control(&dctcp); + if (ret) + return ret; + register_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); + return 0; } static void __exit dctcp_unregister(void) { + unregister_kfunc_btf_id_set(&bpf_tcp_ca_kfunc_list, &tcp_dctcp_kfunc_btf_set); tcp_unregister_congestion_control(&dctcp); } diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index ff805777431c..1fb45b011e4b 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -41,6 +41,7 @@ quiet_cmd_btf_ko = BTF [M] $@ cmd_btf_ko = \ if [ -f vmlinux ]; then \ LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J --btf_base vmlinux $@; \ + $(RESOLVE_BTFIDS) -b vmlinux $@; \ else \ printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ fi; -- cgit v1.2.3 From c48e51c8b07aba8a18125221cb67a40cb1256bf2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 2 Oct 2021 06:47:57 +0530 Subject: bpf: selftests: Add selftests for module kfunc support This adds selftests that tests the success and failure path for modules kfuncs (in presence of invalid kfunc calls) for both libbpf and gen_loader. It also adds a prog_test kfunc_btf_id_list so that we can add module BTF ID set from bpf_testmod. This also introduces a couple of test cases to verifier selftests for validating whether we get an error or not depending on if invalid kfunc call remains after elimination of unreachable instructions. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211002011757.311265-10-memxor@gmail.com --- include/linux/btf.h | 1 + kernel/bpf/btf.c | 1 + net/bpf/test_run.c | 5 ++- tools/testing/selftests/bpf/Makefile | 7 ++-- .../selftests/bpf/bpf_testmod/bpf_testmod.c | 23 ++++++++++- .../selftests/bpf/prog_tests/ksyms_module.c | 29 +++++++------- .../selftests/bpf/prog_tests/ksyms_module_libbpf.c | 28 +++++++++++++ .../selftests/bpf/progs/test_ksyms_module.c | 46 ++++++++++++++++------ tools/testing/selftests/bpf/verifier/calls.c | 23 +++++++++++ 9 files changed, 132 insertions(+), 31 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 1d56cd2bb362..203eef993d76 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -275,5 +275,6 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, THIS_MODULE } extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; +extern struct kfunc_btf_id_list prog_test_kfunc_list; #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1460dff3c154..2ebffb9f57eb 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6397,3 +6397,4 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, EXPORT_SYMBOL_GPL(name) DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); +DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index b1f6f5237de6..529608784aa8 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017 Facebook */ #include +#include #include #include #include @@ -243,7 +244,9 @@ BTF_SET_END(test_sk_kfunc_ids) bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner) { - return btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id); + if (btf_id_set_contains(&test_sk_kfunc_ids, kfunc_id)) + return true; + return bpf_check_mod_kfunc_call(&prog_test_kfunc_list, kfunc_id, owner); } static void *bpf_test_init(const union bpf_attr *kattr, u32 size, diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 5a94d0900d1b..c5c9a9f50d8d 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -315,8 +315,9 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h \ linked_vars.skel.h linked_maps.skel.h LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \ - test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \ - trace_vprintk.c + test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c +# Generate both light skeleton and libbpf skeleton for these +LSKELS_EXTRA := test_ksyms_module.c SKEL_BLACKLIST += $$(LSKELS) test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o @@ -346,7 +347,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS) TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h, \ $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\ $$(TRUNNER_BPF_SRCS))) -TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS)) +TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS) $$(LSKELS_EXTRA)) TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS)) TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS) diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c index 50fc5561110a..b892948dc134 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020 Facebook */ +#include +#include #include #include #include @@ -13,6 +15,12 @@ DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123; +noinline void +bpf_testmod_test_mod_kfunc(int i) +{ + *(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i; +} + noinline int bpf_testmod_loop_test(int n) { int i, sum = 0; @@ -71,13 +79,26 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { .write = bpf_testmod_test_write, }; +BTF_SET_START(bpf_testmod_kfunc_ids) +BTF_ID(func, bpf_testmod_test_mod_kfunc) +BTF_SET_END(bpf_testmod_kfunc_ids) + +static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set); + static int bpf_testmod_init(void) { - return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); + int ret; + + ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); + if (ret) + return ret; + register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); + return 0; } static void bpf_testmod_exit(void) { + unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set); return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); } diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c index 2cd5cded543f..831447878d7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c @@ -2,30 +2,29 @@ /* Copyright (c) 2021 Facebook */ #include -#include -#include +#include #include "test_ksyms_module.lskel.h" -static int duration; - void test_ksyms_module(void) { - struct test_ksyms_module* skel; + struct test_ksyms_module *skel; + int retval; int err; - skel = test_ksyms_module__open_and_load(); - if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + if (!env.has_testmod) { + test__skip(); return; + } - err = test_ksyms_module__attach(skel); - if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + skel = test_ksyms_module__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open_and_load")) + return; + err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) goto cleanup; - - usleep(1); - - ASSERT_EQ(skel->bss->triggered, true, "triggered"); - ASSERT_EQ(skel->bss->out_mod_ksym_global, 123, "global_ksym_val"); - + ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); cleanup: test_ksyms_module__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c new file mode 100644 index 000000000000..e6343ef63af9 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include "test_ksyms_module.skel.h" + +void test_ksyms_module_libbpf(void) +{ + struct test_ksyms_module *skel; + int retval, err; + + if (!env.has_testmod) { + test__skip(); + return; + } + + skel = test_ksyms_module__open_and_load(); + if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open")) + return; + err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4, + sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL); + if (!ASSERT_OK(err, "bpf_prog_test_run")) + goto cleanup; + ASSERT_EQ(retval, 0, "retval"); + ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym"); +cleanup: + test_ksyms_module__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_module.c b/tools/testing/selftests/bpf/progs/test_ksyms_module.c index d6a0b3086b90..0650d918c096 100644 --- a/tools/testing/selftests/bpf/progs/test_ksyms_module.c +++ b/tools/testing/selftests/bpf/progs/test_ksyms_module.c @@ -2,24 +2,48 @@ /* Copyright (c) 2021 Facebook */ #include "vmlinux.h" - #include +#define X_0(x) +#define X_1(x) x X_0(x) +#define X_2(x) x X_1(x) +#define X_3(x) x X_2(x) +#define X_4(x) x X_3(x) +#define X_5(x) x X_4(x) +#define X_6(x) x X_5(x) +#define X_7(x) x X_6(x) +#define X_8(x) x X_7(x) +#define X_9(x) x X_8(x) +#define X_10(x) x X_9(x) +#define REPEAT_256(Y) X_2(X_10(X_10(Y))) X_5(X_10(Y)) X_6(Y) + extern const int bpf_testmod_ksym_percpu __ksym; +extern void bpf_testmod_test_mod_kfunc(int i) __ksym; +extern void bpf_testmod_invalid_mod_kfunc(void) __ksym __weak; -int out_mod_ksym_global = 0; -bool triggered = false; +int out_bpf_testmod_ksym = 0; +const volatile int x = 0; -SEC("raw_tp/sys_enter") -int handler(const void *ctx) +SEC("tc") +int load(struct __sk_buff *skb) { - int *val; - __u32 cpu; - - val = (int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); - out_mod_ksym_global = *val; - triggered = true; + /* This will be kept by clang, but removed by verifier. Since it is + * marked as __weak, libbpf and gen_loader don't error out if BTF ID + * is not found for it, instead imm and off is set to 0 for it. + */ + if (x) + bpf_testmod_invalid_mod_kfunc(); + bpf_testmod_test_mod_kfunc(42); + out_bpf_testmod_ksym = *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu); + return 0; +} +SEC("tc") +int load_256(struct __sk_buff *skb) +{ + /* this will fail if kfunc doesn't reuse its own btf fd index */ + REPEAT_256(bpf_testmod_test_mod_kfunc(42);); + bpf_testmod_test_mod_kfunc(42); return 0; } diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 336a749673d1..d7b74eb28333 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -1,3 +1,26 @@ +{ + "calls: invalid kfunc call not eliminated", + .insns = { + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = REJECT, + .errstr = "invalid kernel function call not eliminated in verifier pass", +}, +{ + "calls: invalid kfunc call unreachable", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 0, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .result = ACCEPT, +}, { "calls: basic sanity", .insns = { -- cgit v1.2.3 From c921ff373b469ad7907cde219fa700909f59cac4 Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 15 Jun 2021 15:10:03 +0200 Subject: dma-buf: add dma_resv_for_each_fence_unlocked v8 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Abstract the complexity of iterating over all the fences in a dma_resv object. The new loop handles the whole RCU and retry dance and returns only fences where we can be sure we grabbed the right one. v2: fix accessing the shared fences while they might be freed, improve kerneldoc, rename _cursor to _iter, add dma_resv_iter_is_exclusive, add dma_resv_iter_begin/end v3: restructor the code, move rcu_read_lock()/unlock() into the iterator, add dma_resv_iter_is_restarted() v4: fix NULL deref when no explicit fence exists, drop superflous rcu_read_lock()/unlock() calls. v5: fix typos in the documentation v6: fix coding error when excl fence is NULL v7: one more logic fix v8: fix index check in dma_resv_iter_is_exclusive() Signed-off-by: Christian König Reviewed-by: Tvrtko Ursulin (v7) Link: https://patchwork.freedesktop.org/patch/msgid/20211005113742.1101-2-christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 100 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/dma-resv.h | 95 ++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 195 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 84fbe60629e3..3cbcf66a137e 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -323,6 +323,106 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence) } EXPORT_SYMBOL(dma_resv_add_excl_fence); +/** + * dma_resv_iter_restart_unlocked - restart the unlocked iterator + * @cursor: The dma_resv_iter object to restart + * + * Restart the unlocked iteration by initializing the cursor object. + */ +static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) +{ + cursor->seq = read_seqcount_begin(&cursor->obj->seq); + cursor->index = -1; + if (cursor->all_fences) + cursor->fences = dma_resv_shared_list(cursor->obj); + else + cursor->fences = NULL; + cursor->is_restarted = true; +} + +/** + * dma_resv_iter_walk_unlocked - walk over fences in a dma_resv obj + * @cursor: cursor to record the current position + * + * Return all the fences in the dma_resv object which are not yet signaled. + * The returned fence has an extra local reference so will stay alive. + * If a concurrent modify is detected the whole iteration is started over again. + */ +static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) +{ + struct dma_resv *obj = cursor->obj; + + do { + /* Drop the reference from the previous round */ + dma_fence_put(cursor->fence); + + if (cursor->index == -1) { + cursor->fence = dma_resv_excl_fence(obj); + cursor->index++; + if (!cursor->fence) + continue; + + } else if (!cursor->fences || + cursor->index >= cursor->fences->shared_count) { + cursor->fence = NULL; + break; + + } else { + struct dma_resv_list *fences = cursor->fences; + unsigned int idx = cursor->index++; + + cursor->fence = rcu_dereference(fences->shared[idx]); + } + cursor->fence = dma_fence_get_rcu(cursor->fence); + if (!cursor->fence || !dma_fence_is_signaled(cursor->fence)) + break; + } while (true); +} + +/** + * dma_resv_iter_first_unlocked - first fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Returns the first fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor) +{ + rcu_read_lock(); + do { + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_first_unlocked); + +/** + * dma_resv_iter_next_unlocked - next fence in an unlocked dma_resv obj. + * @cursor: the cursor with the current position + * + * Returns the next fence from an unlocked dma_resv obj. + */ +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) +{ + bool restart; + + rcu_read_lock(); + cursor->is_restarted = false; + restart = read_seqcount_retry(&cursor->obj->seq, cursor->seq); + do { + if (restart) + dma_resv_iter_restart_unlocked(cursor); + dma_resv_iter_walk_unlocked(cursor); + restart = true; + } while (read_seqcount_retry(&cursor->obj->seq, cursor->seq)); + rcu_read_unlock(); + + return cursor->fence; +} +EXPORT_SYMBOL(dma_resv_iter_next_unlocked); + /** * dma_resv_copy_fences - Copy all fences from src to dst. * @dst: the destination reservation object diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 9100dd3dc21f..764138ad8583 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -149,6 +149,101 @@ struct dma_resv { struct dma_resv_list __rcu *fence; }; +/** + * struct dma_resv_iter - current position into the dma_resv fences + * + * Don't touch this directly in the driver, use the accessor function instead. + */ +struct dma_resv_iter { + /** @obj: The dma_resv object we iterate over */ + struct dma_resv *obj; + + /** @all_fences: If all fences should be returned */ + bool all_fences; + + /** @fence: the currently handled fence */ + struct dma_fence *fence; + + /** @seq: sequence number to check for modifications */ + unsigned int seq; + + /** @index: index into the shared fences */ + unsigned int index; + + /** @fences: the shared fences */ + struct dma_resv_list *fences; + + /** @is_restarted: true if this is the first returned fence */ + bool is_restarted; +}; + +struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); + +/** + * dma_resv_iter_begin - initialize a dma_resv_iter object + * @cursor: The dma_resv_iter object to initialize + * @obj: The dma_resv object which we want to iterate over + * @all_fences: If all fences should be returned or just the exclusive one + */ +static inline void dma_resv_iter_begin(struct dma_resv_iter *cursor, + struct dma_resv *obj, + bool all_fences) +{ + cursor->obj = obj; + cursor->all_fences = all_fences; + cursor->fence = NULL; +} + +/** + * dma_resv_iter_end - cleanup a dma_resv_iter object + * @cursor: the dma_resv_iter object which should be cleaned up + * + * Make sure that the reference to the fence in the cursor is properly + * dropped. + */ +static inline void dma_resv_iter_end(struct dma_resv_iter *cursor) +{ + dma_fence_put(cursor->fence); +} + +/** + * dma_resv_iter_is_exclusive - test if the current fence is the exclusive one + * @cursor: the cursor of the current position + * + * Returns true if the currently returned fence is the exclusive one. + */ +static inline bool dma_resv_iter_is_exclusive(struct dma_resv_iter *cursor) +{ + return cursor->index == 0; +} + +/** + * dma_resv_iter_is_restarted - test if this is the first fence after a restart + * @cursor: the cursor with the current position + * + * Return true if this is the first fence in an iteration after a restart. + */ +static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) +{ + return cursor->is_restarted; +} + +/** + * dma_resv_for_each_fence_unlocked - unlocked fence iterator + * @cursor: a struct dma_resv_iter pointer + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object without holding the + * &dma_resv.lock and using RCU instead. The cursor needs to be initialized + * with dma_resv_iter_begin() and cleaned up with dma_resv_iter_end(). Inside + * the iterator a reference to the dma_fence is held and the RCU lock dropped. + * When the dma_resv is modified the iteration starts over again. + */ +#define dma_resv_for_each_fence_unlocked(cursor, fence) \ + for (fence = dma_resv_iter_first_unlocked(cursor); \ + fence; fence = dma_resv_iter_next_unlocked(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -- cgit v1.2.3 From 4f627af8e6068892cafe031df6c14e8a0aaaa426 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Sep 2021 16:10:11 -0500 Subject: ptrace: Remove the unnecessary arguments from arch_ptrace_stop Both arch_ptrace_stop_needed and arch_ptrace_stop are called with an exit_code and a siginfo structure. Neither argument is used by any of the implementations so just remove the unneeded arguments. The two arechitectures that implement arch_ptrace_stop are ia64 and sparc. Both architectures flush their register stacks before a ptrace_stack so that all of the register information can be accessed by debuggers. As the question of if a register stack needs to be flushed is independent of why ptrace is stopping not needing arguments make sense. Cc: David Miller Cc: sparclinux@vger.kernel.org Link: https://lkml.kernel.org/r/87lf3mx290.fsf@disp2133 Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- arch/ia64/include/asm/ptrace.h | 4 ++-- arch/sparc/include/asm/ptrace.h | 8 ++++---- include/linux/ptrace.h | 22 +++++++++------------- kernel/signal.c | 4 ++-- 4 files changed, 17 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/ptrace.h b/arch/ia64/include/asm/ptrace.h index 08179135905c..f15504f75f10 100644 --- a/arch/ia64/include/asm/ptrace.h +++ b/arch/ia64/include/asm/ptrace.h @@ -129,9 +129,9 @@ static inline long regs_return_value(struct pt_regs *regs) extern void ia64_decrement_ip (struct pt_regs *pt); extern void ia64_ptrace_stop(void); - #define arch_ptrace_stop(code, info) \ + #define arch_ptrace_stop() \ ia64_ptrace_stop() - #define arch_ptrace_stop_needed(code, info) \ + #define arch_ptrace_stop_needed() \ (!test_thread_flag(TIF_RESTORE_RSE)) extern void ptrace_attach_sync_user_rbs (struct task_struct *); diff --git a/arch/sparc/include/asm/ptrace.h b/arch/sparc/include/asm/ptrace.h index 71dd82b43cc5..d1419e669027 100644 --- a/arch/sparc/include/asm/ptrace.h +++ b/arch/sparc/include/asm/ptrace.h @@ -26,12 +26,12 @@ static inline bool pt_regs_clear_syscall(struct pt_regs *regs) return (regs->tstate &= ~TSTATE_SYSCALL); } -#define arch_ptrace_stop_needed(exit_code, info) \ +#define arch_ptrace_stop_needed() \ ({ flush_user_windows(); \ get_thread_wsaved() != 0; \ }) -#define arch_ptrace_stop(exit_code, info) \ +#define arch_ptrace_stop() \ synchronize_user_stack() #define current_pt_regs() \ @@ -129,12 +129,12 @@ static inline bool pt_regs_clear_syscall(struct pt_regs *regs) return (regs->psr &= ~PSR_SYSCALL); } -#define arch_ptrace_stop_needed(exit_code, info) \ +#define arch_ptrace_stop_needed() \ ({ flush_user_windows(); \ current_thread_info()->w_saved != 0; \ }) -#define arch_ptrace_stop(exit_code, info) \ +#define arch_ptrace_stop() \ synchronize_user_stack() #define current_pt_regs() \ diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index b5ebf6c01292..8aee2945ff08 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -362,29 +362,25 @@ static inline void user_single_step_report(struct pt_regs *regs) #ifndef arch_ptrace_stop_needed /** * arch_ptrace_stop_needed - Decide whether arch_ptrace_stop() should be called - * @code: current->exit_code value ptrace will stop with - * @info: siginfo_t pointer (or %NULL) for signal ptrace will stop with * * This is called with the siglock held, to decide whether or not it's - * necessary to release the siglock and call arch_ptrace_stop() with the - * same @code and @info arguments. It can be defined to a constant if - * arch_ptrace_stop() is never required, or always is. On machines where - * this makes sense, it should be defined to a quick test to optimize out - * calling arch_ptrace_stop() when it would be superfluous. For example, - * if the thread has not been back to user mode since the last stop, the - * thread state might indicate that nothing needs to be done. + * necessary to release the siglock and call arch_ptrace_stop(). It can be + * defined to a constant if arch_ptrace_stop() is never required, or always + * is. On machines where this makes sense, it should be defined to a quick + * test to optimize out calling arch_ptrace_stop() when it would be + * superfluous. For example, if the thread has not been back to user mode + * since the last stop, the thread state might indicate that nothing needs + * to be done. * * This is guaranteed to be invoked once before a task stops for ptrace and * may include arch-specific operations necessary prior to a ptrace stop. */ -#define arch_ptrace_stop_needed(code, info) (0) +#define arch_ptrace_stop_needed() (0) #endif #ifndef arch_ptrace_stop /** * arch_ptrace_stop - Do machine-specific work before stopping for ptrace - * @code: current->exit_code value ptrace will stop with - * @info: siginfo_t pointer (or %NULL) for signal ptrace will stop with * * This is called with no locks held when arch_ptrace_stop_needed() has * just returned nonzero. It is allowed to block, e.g. for user memory @@ -394,7 +390,7 @@ static inline void user_single_step_report(struct pt_regs *regs) * we only do it when the arch requires it for this particular stop, as * indicated by arch_ptrace_stop_needed(). */ -#define arch_ptrace_stop(code, info) do { } while (0) +#define arch_ptrace_stop() do { } while (0) #endif #ifndef current_pt_regs diff --git a/kernel/signal.c b/kernel/signal.c index 9f2dc9cf3208..c9759ff2cb43 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2200,7 +2200,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t { bool gstop_done = false; - if (arch_ptrace_stop_needed(exit_code, info)) { + if (arch_ptrace_stop_needed()) { /* * The arch code has something special to do before a * ptrace stop. This is allowed to block, e.g. for faults @@ -2210,7 +2210,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t * any signal bookkeeping like checking group_stop_count. */ spin_unlock_irq(¤t->sighand->siglock); - arch_ptrace_stop(exit_code, info); + arch_ptrace_stop(); spin_lock_irq(¤t->sighand->siglock); } -- cgit v1.2.3 From 92307383082daff5df884a25df9e283efb7ef261 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 1 Sep 2021 11:33:50 -0500 Subject: coredump: Don't perform any cleanups before dumping core Rename coredump_exit_mm to coredump_task_exit and call it from do_exit before PTRACE_EVENT_EXIT, and before any cleanup work for a task happens. This ensures that an accurate copy of the process can be captured in the coredump as no cleanup for the process happens before the coredump completes. This also ensures that PTRACE_EVENT_EXIT will not be visited by any thread until the coredump is complete. Add a new flag PF_POSTCOREDUMP so that tasks that have passed through coredump_task_exit can be recognized and ignored in zap_process. Now that all of the coredumping happens before exit_mm remove code to test for a coredump in progress from mm_release. Replace "may_ptrace_stop()" with a simple test of "current->ptrace". The other tests in may_ptrace_stop all concern avoiding stopping during a coredump. These tests are no longer necessary as it is now guaranteed that fatal_signal_pending will be set if the code enters ptrace_stop during a coredump. The code in ptrace_stop is guaranteed not to stop if fatal_signal_pending returns true. Until this change "ptrace_event(PTRACE_EVENT_EXIT)" could call ptrace_stop without fatal_signal_pending being true, as signals are dequeued in get_signal before calling do_exit. This is no longer an issue as "ptrace_event(PTRACE_EVENT_EXIT)" is no longer reached until after the coredump completes. Link: https://lkml.kernel.org/r/874kaax26c.fsf@disp2133 Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- fs/coredump.c | 8 ++++---- include/linux/sched.h | 1 + kernel/exit.c | 19 ++++++++++++------- kernel/fork.c | 3 +-- kernel/signal.c | 27 +-------------------------- mm/oom_kill.c | 2 +- 6 files changed, 20 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/fs/coredump.c b/fs/coredump.c index 5e0e08a7fb9b..d576287fb88b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -359,7 +359,7 @@ static int zap_process(struct task_struct *start, int exit_code, int flags) for_each_thread(start, t) { task_clear_jobctl_pending(t, JOBCTL_PENDING_MASK); - if (t != current && t->mm) { + if (t != current && !(t->flags & PF_POSTCOREDUMP)) { sigaddset(&t->pending.signal, SIGKILL); signal_wake_up(t, 1); nr++; @@ -404,8 +404,8 @@ static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, * * do_exit: * The caller holds mm->mmap_lock. This means that the task which - * uses this mm can't pass coredump_exit_mm(), so it can't exit or - * clear its ->mm. + * uses this mm can't pass coredump_task_exit(), so it can't exit + * or clear its ->mm. * * de_thread: * It does list_replace_rcu(&leader->tasks, ¤t->tasks), @@ -500,7 +500,7 @@ static void coredump_finish(struct mm_struct *mm, bool core_dumped) next = curr->next; task = curr->task; /* - * see coredump_exit_mm(), curr->task must not see + * see coredump_task_exit(), curr->task must not see * ->task == NULL before we read ->next. */ smp_mb(); diff --git a/include/linux/sched.h b/include/linux/sched.h index e12b524426b0..f3741f23935e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1664,6 +1664,7 @@ extern struct pid *cad_pid; #define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ +#define PF_POSTCOREDUMP 0x00000008 /* Coredumps should ignore this task */ #define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ diff --git a/kernel/exit.c b/kernel/exit.c index cb1619d8fd64..774e6b5061b8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -339,23 +339,29 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) } } -static void coredump_exit_mm(struct mm_struct *mm) +static void coredump_task_exit(struct task_struct *tsk) { struct core_state *core_state; + struct mm_struct *mm; + + mm = tsk->mm; + if (!mm) + return; /* * Serialize with any possible pending coredump. * We must hold mmap_lock around checking core_state - * and clearing tsk->mm. The core-inducing thread + * and setting PF_POSTCOREDUMP. The core-inducing thread * will increment ->nr_threads for each thread in the - * group with ->mm != NULL. + * group without PF_POSTCOREDUMP set. */ + mmap_read_lock(mm); + tsk->flags |= PF_POSTCOREDUMP; core_state = mm->core_state; + mmap_read_unlock(mm); if (core_state) { struct core_thread self; - mmap_read_unlock(mm); - self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); @@ -375,7 +381,6 @@ static void coredump_exit_mm(struct mm_struct *mm) freezable_schedule(); } __set_current_state(TASK_RUNNING); - mmap_read_lock(mm); } } @@ -480,7 +485,6 @@ static void exit_mm(void) return; sync_mm_rss(mm); mmap_read_lock(mm); - coredump_exit_mm(mm); mmgrab(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ @@ -768,6 +772,7 @@ void __noreturn do_exit(long code) profile_task_exit(tsk); kcov_task_exit(tsk); + coredump_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); validate_creds_for_do_exit(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index 38681ad44c76..9bd9f2da9e41 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1392,8 +1392,7 @@ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) * purposes. */ if (tsk->clear_child_tid) { - if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) && - atomic_read(&mm->mm_users) > 1) { + if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. diff --git a/kernel/signal.c b/kernel/signal.c index c9759ff2cb43..b0db80acc6ef 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2158,31 +2158,6 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, spin_unlock_irqrestore(&sighand->siglock, flags); } -static inline bool may_ptrace_stop(void) -{ - if (!likely(current->ptrace)) - return false; - /* - * Are we in the middle of do_coredump? - * If so and our tracer is also part of the coredump stopping - * is a deadlock situation, and pointless because our tracer - * is dead so don't allow us to stop. - * If SIGKILL was already sent before the caller unlocked - * ->siglock we must see ->core_state != NULL. Otherwise it - * is safe to enter schedule(). - * - * This is almost outdated, a task with the pending SIGKILL can't - * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported - * after SIGKILL was already dequeued. - */ - if (unlikely(current->mm->core_state) && - unlikely(current->mm == current->parent->mm)) - return false; - - return true; -} - - /* * This must be called with current->sighand->siglock held. * @@ -2263,7 +2238,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, kernel_siginfo_t spin_unlock_irq(¤t->sighand->siglock); read_lock(&tasklist_lock); - if (may_ptrace_stop()) { + if (likely(current->ptrace)) { /* * Notify parents of the stop. * diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 295c8bdfd6c8..7877c755ab37 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -788,7 +788,7 @@ static inline bool __task_will_free_mem(struct task_struct *task) /* * A coredumping process may sleep for an extended period in - * coredump_exit_mm(), so the oom killer cannot assume that + * coredump_task_exit(), so the oom killer cannot assume that * the process will promptly exit and release memory. */ if (sig->flags & SIGNAL_GROUP_COREDUMP) -- cgit v1.2.3 From 353407d917b2d87cd8104a0453d012439c6ca4be Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Oct 2021 13:46:42 +0300 Subject: ethtool: Add ability to control transceiver modules' power mode Add a pair of new ethtool messages, 'ETHTOOL_MSG_MODULE_SET' and 'ETHTOOL_MSG_MODULE_GET', that can be used to control transceiver modules parameters and retrieve their status. The first parameter to control is the power mode of the module. It is only relevant for paged memory modules, as flat memory modules always operate in low power mode. When a paged memory module is in low power mode, its power consumption is reduced to the minimum, the management interface towards the host is available and the data path is deactivated. User space can choose to put modules that are not currently in use in low power mode and transition them to high power mode before putting the associated ports administratively up. This is useful for user space that favors reduced power consumption and lower temperatures over reduced link up times. In QSFP-DD modules the transition from low power mode to high power mode can take a few seconds and this transition is only expected to get longer with future / more complex modules. User space can control the power mode of the module via the power mode policy attribute ('ETHTOOL_A_MODULE_POWER_MODE_POLICY'). Possible values: * high: Module is always in high power mode. * auto: Module is transitioned by the host to high power mode when the first port using it is put administratively up and to low power mode when the last port using it is put administratively down. The operational power mode of the module is available to user space via the 'ETHTOOL_A_MODULE_POWER_MODE' attribute. The attribute is not reported to user space when a module is not plugged-in. The user API is designed to be generic enough so that it could be used for modules with different memory maps (e.g., SFF-8636, CMIS). The only implementation of the device driver API in this series is for a MAC driver (mlxsw) where the module is controlled by the device's firmware, but it is designed to be generic enough so that it could also be used by implementations where the module is controlled by the CPU. CMIS testing ============ # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x03 (ModuleReady) LowPwrAllowRequestHW : Off LowPwrRequestSW : Off The module is not in low power mode, as it is not forced by hardware (LowPwrAllowRequestHW is off) or by software (LowPwrRequestSW is off). The power mode can be queried from the kernel. In case LowPwrAllowRequestHW was on, the kernel would need to take into account the state of the LowPwrRequestHW signal, which is not visible to user space. $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy high power-mode high Change the power mode policy to 'auto': # ethtool --set-module swp11 power-mode-policy auto Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x01 (ModuleLowPwr) LowPwrAllowRequestHW : Off LowPwrRequestSW : On Put the associated port administratively up which will instruct the host to transition the module to high power mode: # ip link set dev swp11 up Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode high Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x03 (ModuleReady) LowPwrAllowRequestHW : Off LowPwrRequestSW : Off Put the associated port administratively down which will instruct the host to transition the module to low power mode: # ip link set dev swp11 down Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x01 (ModuleLowPwr) LowPwrAllowRequestHW : Off LowPwrRequestSW : On SFF-8636 testing ================ # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) enabled Power set : Off Power override : On ... Transmit avg optical power (Channel 1) : 0.7733 mW / -1.12 dBm Transmit avg optical power (Channel 2) : 0.7649 mW / -1.16 dBm Transmit avg optical power (Channel 3) : 0.7790 mW / -1.08 dBm Transmit avg optical power (Channel 4) : 0.7837 mW / -1.06 dBm Rcvr signal avg optical power(Channel 1) : 0.9302 mW / -0.31 dBm Rcvr signal avg optical power(Channel 2) : 0.9079 mW / -0.42 dBm Rcvr signal avg optical power(Channel 3) : 0.8993 mW / -0.46 dBm Rcvr signal avg optical power(Channel 4) : 0.8778 mW / -0.57 dBm The module is not in low power mode, as it is not forced by hardware (Power override is on) or by software (Power set is off). The power mode can be queried from the kernel. In case Power override was off, the kernel would need to take into account the state of the LPMode signal, which is not visible to user space. $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy high power-mode high Change the power mode policy to 'auto': # ethtool --set-module swp13 power-mode-policy auto Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) not enabled Power set : On Power override : On ... Transmit avg optical power (Channel 1) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 2) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 3) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 4) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 1) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 2) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 3) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 4) : 0.0000 mW / -inf dBm Put the associated port administratively up which will instruct the host to transition the module to high power mode: # ip link set dev swp13 up Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode high Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) enabled Power set : Off Power override : On ... Transmit avg optical power (Channel 1) : 0.7934 mW / -1.01 dBm Transmit avg optical power (Channel 2) : 0.7859 mW / -1.05 dBm Transmit avg optical power (Channel 3) : 0.7885 mW / -1.03 dBm Transmit avg optical power (Channel 4) : 0.7985 mW / -0.98 dBm Rcvr signal avg optical power(Channel 1) : 0.9325 mW / -0.30 dBm Rcvr signal avg optical power(Channel 2) : 0.9034 mW / -0.44 dBm Rcvr signal avg optical power(Channel 3) : 0.9086 mW / -0.42 dBm Rcvr signal avg optical power(Channel 4) : 0.8885 mW / -0.51 dBm Put the associated port administratively down which will instruct the host to transition the module to low power mode: # ip link set dev swp13 down Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) not enabled Power set : On Power override : On ... Transmit avg optical power (Channel 1) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 2) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 3) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 4) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 1) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 2) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 3) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 4) : 0.0000 mW / -inf dBm Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 71 ++++++++++- include/linux/ethtool.h | 22 ++++ include/uapi/linux/ethtool.h | 23 ++++ include/uapi/linux/ethtool_netlink.h | 17 +++ net/ethtool/Makefile | 2 +- net/ethtool/module.c | 180 +++++++++++++++++++++++++++ net/ethtool/netlink.c | 19 +++ net/ethtool/netlink.h | 4 + 8 files changed, 335 insertions(+), 3 deletions(-) create mode 100644 net/ethtool/module.c (limited to 'include/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d9b55b7a1a4d..d6fd4b2e243c 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -41,6 +41,11 @@ In the message structure descriptions below, if an attribute name is suffixed with "+", parent nest can contain multiple attributes of the same type. This implements an array of entries. +Attributes that need to be filled-in by device drivers and that are dumped to +user space based on whether they are valid or not should not use zero as a +valid value. This avoids the need to explicitly signal the validity of the +attribute in the device driver API. + Request header ============== @@ -179,7 +184,7 @@ according to message purpose: Userspace to kernel: - ===================================== ================================ + ===================================== ================================= ``ETHTOOL_MSG_STRSET_GET`` get string set ``ETHTOOL_MSG_LINKINFO_GET`` get link settings ``ETHTOOL_MSG_LINKINFO_SET`` set link settings @@ -213,7 +218,9 @@ Userspace to kernel: ``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET`` get standard statistics ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info - ===================================== ================================ + ``ETHTOOL_MSG_MODULE_SET`` set transceiver module parameters + ``ETHTOOL_MSG_MODULE_GET`` get transceiver module parameters + ===================================== ================================= Kernel to userspace: @@ -252,6 +259,7 @@ Kernel to userspace: ``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info + ``ETHTOOL_MSG_MODULE_GET_REPLY`` transceiver module parameters ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1521,6 +1529,63 @@ Kernel response contents: ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array ==================================== ====== ========================== +MODULE_GET +========== + +Gets transceiver module parameters. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested reply header + ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` u8 power mode policy + ``ETHTOOL_A_MODULE_POWER_MODE`` u8 operational power mode + ====================================== ====== ========================== + +The optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute encodes the +transceiver module power mode policy enforced by the host. The default policy +is driver-dependent, but "auto" is the recommended default and it should be +implemented by new drivers and drivers where conformance to a legacy behavior +is not critical. + +The optional ``ETHTHOOL_A_MODULE_POWER_MODE`` attribute encodes the operational +power mode policy of the transceiver module. It is only reported when a module +is plugged-in. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_power_mode + +MODULE_SET +========== + +Sets transceiver module parameters. + +Request contents: + + ====================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested request header + ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` u8 power mode policy + ====================================== ====== ========================== + +When set, the optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute is used +to set the transceiver module power policy enforced by the host. Possible +values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_power_mode_policy + +For SFF-8636 modules, low power mode is forced by the host according to table +6-10 in revision 2.10a of the specification. + +For CMIS modules, low power mode is forced by the host according to table 6-12 +in revision 5.0 of the specification. + Request translation =================== @@ -1620,4 +1685,6 @@ are netlink only. n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` + n/a ``ETHTOOL_MSG_MODULE_GET`` + n/a ``ETHTOOL_MSG_MODULE_SET`` =================================== ===================================== diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 849524b55d89..9adf8d2c3144 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -415,6 +415,17 @@ struct ethtool_module_eeprom { u8 *data; }; +/** + * struct ethtool_module_power_mode_params - module power mode parameters + * @policy: The power mode policy enforced by the host for the plug-in module. + * @mode: The operational power mode of the plug-in module. Should be filled by + * device drivers on get operations. + */ +struct ethtool_module_power_mode_params { + enum ethtool_module_power_mode_policy policy; + enum ethtool_module_power_mode mode; +}; + /** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes @@ -580,6 +591,11 @@ struct ethtool_module_eeprom { * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics. * @get_rmon_stats: Query some of the RMON (RFC 2819) statistics. * Set %ranges to a pointer to zero-terminated array of byte ranges. + * @get_module_power_mode: Get the power mode policy for the plug-in module + * used by the network device and its operational power mode, if + * plugged-in. + * @set_module_power_mode: Set the power mode policy for the plug-in module + * used by the network device. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -705,6 +721,12 @@ struct ethtool_ops { void (*get_rmon_stats)(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); + int (*get_module_power_mode)(struct net_device *dev, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); + int (*set_module_power_mode)(struct net_device *dev, + const struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); }; int ethtool_check_ops(const struct ethtool_ops *ops); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index b6db6590baf0..6de61d53ca5d 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -706,6 +706,29 @@ enum ethtool_stringset { ETH_SS_COUNT }; +/** + * enum ethtool_module_power_mode_policy - plug-in module power mode policy + * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. + * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host + * to high power mode when the first port using it is put administratively + * up and to low power mode when the last port using it is put + * administratively down. + */ +enum ethtool_module_power_mode_policy { + ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO, +}; + +/** + * enum ethtool_module_power_mode - plug-in module power mode + * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode. + * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode. + */ +enum ethtool_module_power_mode { + ETHTOOL_MODULE_POWER_MODE_LOW = 1, + ETHTOOL_MODULE_POWER_MODE_HIGH, +}; + /** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5545f1ca9237..ca5fbb59fa42 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -47,6 +47,8 @@ enum { ETHTOOL_MSG_MODULE_EEPROM_GET, ETHTOOL_MSG_STATS_GET, ETHTOOL_MSG_PHC_VCLOCKS_GET, + ETHTOOL_MSG_MODULE_GET, + ETHTOOL_MSG_MODULE_SET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -90,6 +92,8 @@ enum { ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, ETHTOOL_MSG_STATS_GET_REPLY, ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + ETHTOOL_MSG_MODULE_GET_REPLY, + ETHTOOL_MSG_MODULE_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -833,6 +837,19 @@ enum { ETHTOOL_A_STATS_RMON_MAX = (__ETHTOOL_A_STATS_RMON_CNT - 1) }; +/* MODULE */ + +enum { + ETHTOOL_A_MODULE_UNSPEC, + ETHTOOL_A_MODULE_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_MODULE_POWER_MODE_POLICY, /* u8 */ + ETHTOOL_A_MODULE_POWER_MODE, /* u8 */ + + /* add new constants above here */ + __ETHTOOL_A_MODULE_CNT, + ETHTOOL_A_MODULE_MAX = (__ETHTOOL_A_MODULE_CNT - 1) +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 0a19470efbfb..b76432e70e6b 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ - tunnels.o fec.o eeprom.o stats.o phc_vclocks.o + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o diff --git a/net/ethtool/module.c b/net/ethtool/module.c new file mode 100644 index 000000000000..bc2cef11bbda --- /dev/null +++ b/net/ethtool/module.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct module_req_info { + struct ethnl_req_info base; +}; + +struct module_reply_data { + struct ethnl_reply_data base; + struct ethtool_module_power_mode_params power; +}; + +#define MODULE_REPDATA(__reply_base) \ + container_of(__reply_base, struct module_reply_data, base) + +/* MODULE_GET */ + +const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1] = { + [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int module_get_power_mode(struct net_device *dev, + struct module_reply_data *data, + struct netlink_ext_ack *extack) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_power_mode) + return 0; + + return ops->get_module_power_mode(dev, &data->power, extack); +} + +static int module_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct module_reply_data *data = MODULE_REPDATA(reply_base); + struct netlink_ext_ack *extack = info ? info->extack : NULL; + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = module_get_power_mode(dev, data, extack); + if (ret < 0) + goto out_complete; + +out_complete: + ethnl_ops_complete(dev); + return ret; +} + +static int module_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct module_reply_data *data = MODULE_REPDATA(reply_base); + int len = 0; + + if (data->power.policy) + len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE_POLICY */ + + if (data->power.mode) + len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE */ + + return len; +} + +static int module_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct module_reply_data *data = MODULE_REPDATA(reply_base); + + if (data->power.policy && + nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE_POLICY, + data->power.policy)) + return -EMSGSIZE; + + if (data->power.mode && + nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE, data->power.mode)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_module_request_ops = { + .request_cmd = ETHTOOL_MSG_MODULE_GET, + .reply_cmd = ETHTOOL_MSG_MODULE_GET_REPLY, + .hdr_attr = ETHTOOL_A_MODULE_HEADER, + .req_info_size = sizeof(struct module_req_info), + .reply_data_size = sizeof(struct module_reply_data), + + .prepare_data = module_prepare_data, + .reply_size = module_reply_size, + .fill_reply = module_fill_reply, +}; + +/* MODULE_SET */ + +const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1] = { + [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_MODULE_POWER_MODE_POLICY] = + NLA_POLICY_RANGE(NLA_U8, ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO), +}; + +static int module_set_power_mode(struct net_device *dev, struct nlattr **tb, + bool *p_mod, struct netlink_ext_ack *extack) +{ + struct ethtool_module_power_mode_params power = {}; + struct ethtool_module_power_mode_params power_new; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + + if (!tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]) + return 0; + + if (!ops->get_module_power_mode || !ops->set_module_power_mode) { + NL_SET_ERR_MSG_ATTR(extack, + tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY], + "Setting power mode policy is not supported by this device"); + return -EOPNOTSUPP; + } + + power_new.policy = nla_get_u8(tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]); + ret = ops->get_module_power_mode(dev, &power, extack); + if (ret < 0) + return ret; + + if (power_new.policy == power.policy) + return 0; + *p_mod = true; + + return ops->set_module_power_mode(dev, &power_new, extack); +} + +int ethnl_set_module(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct net_device *dev; + bool mod = false; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MODULE_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = module_set_power_mode(dev, tb, &mod, info->extack); + if (ret < 0) + goto out_ops; + + if (!mod) + goto out_ops; + + ethtool_notify(dev, ETHTOOL_MSG_MODULE_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1797a0a90019..38b44c0291b1 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -282,6 +282,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, + [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -593,6 +594,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, + [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, }; /* default notification handler */ @@ -686,6 +688,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -999,6 +1002,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_phc_vclocks_get_policy, .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_MODULE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_module_get_policy, + .maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_MODULE_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_module, + .policy = ethnl_module_set_policy, + .maxattr = ARRAY_SIZE(ethnl_module_set_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index e8987e28036f..836ee7157848 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -337,6 +337,7 @@ extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; extern const struct ethnl_request_ops ethnl_stats_request_ops; extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; +extern const struct ethnl_request_ops ethnl_module_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -373,6 +374,8 @@ extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; +extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1]; +extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); @@ -391,6 +394,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_set_fec(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_module(struct sk_buff *skb, struct genl_info *info); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; -- cgit v1.2.3 From 3dfb51126064b594470b9c0b278188fbc9194709 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Oct 2021 13:46:46 +0300 Subject: ethtool: Add transceiver module extended state Add an extended state and sub-state to describe link issues related to transceiver modules. The 'ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY' extended sub-state tells user space that port is unable to gain a carrier because the CMIS Module State Machine did not reach the ModuleReady (Fully Operational) state. For example, if the module is stuck at ModuleLowPwr or ModuleFault state. In case of the latter, user space can read the fault reason from the module's EEPROM and potentially reset it. Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 10 ++++++++++ include/linux/ethtool.h | 1 + include/uapi/linux/ethtool.h | 6 ++++++ 3 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d6fd4b2e243c..7b598c7e3912 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -528,6 +528,8 @@ Link extended states: power required from cable or module ``ETHTOOL_LINK_EXT_STATE_OVERHEAT`` The module is overheated + + ``ETHTOOL_LINK_EXT_STATE_MODULE`` Transceiver module issue ================================================ ============================================ Link extended substates: @@ -621,6 +623,14 @@ Link extended substates: ``ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE`` Cable test failure =================================================== ============================================ + Transceiver module issue substates: + + =================================================== ============================================ + ``ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY`` The CMIS Module State Machine did not reach + the ModuleReady state. For example, if the + module is stuck at ModuleFault state + =================================================== ============================================ + DEBUG_GET ========= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9adf8d2c3144..845a0ffc16ee 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -94,6 +94,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch; enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; + enum ethtool_link_ext_substate_module module; u8 __link_ext_substate; }; }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 6de61d53ca5d..a2223b685451 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -603,6 +603,7 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, ETHTOOL_LINK_EXT_STATE_OVERHEAT, + ETHTOOL_LINK_EXT_STATE_MODULE, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ @@ -649,6 +650,11 @@ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, }; +/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */ +enum ethtool_link_ext_substate_module { + ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1, +}; + #define ETH_GSTRING_LEN 32 /** -- cgit v1.2.3 From 79365f36d1de87286bb4fc0abcb2a01678ef4bef Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 6 Oct 2021 13:19:20 +0100 Subject: net: mdio: add mdiobus_modify_changed() Add mdiobus_modify_changed() helper to reflect the phylib and similar equivalents. This will avoid this functionality being open-coded, as has already happened in phylink, and it looks like other users will be appearing soon. Reviewed-by: Andrew Lunn Signed-off-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- drivers/net/phy/mdio_bus.c | 22 ++++++++++++++++++++++ include/linux/mdio.h | 2 ++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 6f4b4e5df639..d8b68145f6b4 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -926,6 +926,28 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set) } EXPORT_SYMBOL_GPL(mdiobus_modify); +/** + * mdiobus_modify_changed - Convenience function for modifying a given mdio + * device register and returning if it changed + * @bus: the mii_bus struct + * @addr: the phy address + * @regnum: register number to write + * @mask: bit mask of bits to clear + * @set: bit mask of bits to set + */ +int mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, + u16 mask, u16 set) +{ + int err; + + mutex_lock(&bus->mdio_lock); + err = __mdiobus_modify_changed(bus, addr, regnum, mask, set); + mutex_unlock(&bus->mdio_lock); + + return err; +} +EXPORT_SYMBOL_GPL(mdiobus_modify_changed); + /** * mdio_bus_match - determine if given MDIO driver supports the given * MDIO device diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 5e6dc38f418e..f622888a4ba8 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -349,6 +349,8 @@ int mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); int mdiobus_write_nested(struct mii_bus *bus, int addr, u32 regnum, u16 val); int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); +int mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, + u16 mask, u16 set); static inline u32 mdiobus_c45_addr(int devad, u16 regnum) { -- cgit v1.2.3 From af8cc9600bbf2251b04c56139f7c83f87c3f878a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Sep 2021 14:10:51 -0300 Subject: futex: Split out syscalls MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Put the syscalls in their own little file. Signed-off-by: Peter Zijlstra (Intel) Suggested-by: Thomas Gleixner Signed-off-by: André Almeida Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: André Almeida Link: https://lore.kernel.org/r/20210923171111.300673-3-andrealmeid@collabora.com --- include/linux/syscalls.h | 2 +- kernel/futex/Makefile | 2 +- kernel/futex/core.c | 532 ++++++++++------------------------------------- kernel/futex/futex.h | 58 ++++++ kernel/futex/syscalls.c | 279 +++++++++++++++++++++++++ kernel/sys_ni.c | 2 +- 6 files changed, 455 insertions(+), 420 deletions(-) create mode 100644 kernel/futex/futex.h create mode 100644 kernel/futex/syscalls.c (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 252243c7783d..25979682ade5 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -610,7 +610,7 @@ asmlinkage long sys_waitid(int which, pid_t pid, asmlinkage long sys_set_tid_address(int __user *tidptr); asmlinkage long sys_unshare(unsigned long unshare_flags); -/* kernel/futex.c */ +/* kernel/futex/syscalls.c */ asmlinkage long sys_futex(u32 __user *uaddr, int op, u32 val, const struct __kernel_timespec __user *utime, u32 __user *uaddr2, u32 val3); diff --git a/kernel/futex/Makefile b/kernel/futex/Makefile index b89ba3fba343..ff9a9605a8d6 100644 --- a/kernel/futex/Makefile +++ b/kernel/futex/Makefile @@ -1,3 +1,3 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += core.o +obj-y += core.o syscalls.o diff --git a/kernel/futex/core.c b/kernel/futex/core.c index f9bc9aa0ce1e..69d98929f2f5 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -34,14 +34,12 @@ #include #include #include -#include #include #include #include -#include - -#include +#include +#include "futex.h" #include "../locking/rtmutex_common.h" /* @@ -144,27 +142,10 @@ * double_lock_hb() and double_unlock_hb(), respectively. */ -#ifdef CONFIG_HAVE_FUTEX_CMPXCHG -#define futex_cmpxchg_enabled 1 -#else -static int __read_mostly futex_cmpxchg_enabled; +#ifndef CONFIG_HAVE_FUTEX_CMPXCHG +int __read_mostly futex_cmpxchg_enabled; #endif -/* - * Futex flags used to encode options to functions and preserve them across - * restarts. - */ -#ifdef CONFIG_MMU -# define FLAGS_SHARED 0x01 -#else -/* - * NOMMU does not have per process address space. Let the compiler optimize - * code away. - */ -# define FLAGS_SHARED 0x00 -#endif -#define FLAGS_CLOCKRT 0x02 -#define FLAGS_HAS_TIMEOUT 0x04 /* * Priority Inheritance state: @@ -329,7 +310,7 @@ static int __init setup_fail_futex(char *str) } __setup("fail_futex=", setup_fail_futex); -static bool should_fail_futex(bool fshared) +bool should_fail_futex(bool fshared) { if (fail_futex.ignore_private && !fshared) return false; @@ -358,17 +339,8 @@ late_initcall(fail_futex_debugfs); #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ -#else -static inline bool should_fail_futex(bool fshared) -{ - return false; -} #endif /* CONFIG_FAIL_FUTEX */ -#ifdef CONFIG_COMPAT -static void compat_exit_robust_list(struct task_struct *curr); -#endif - /* * Reflects a new waiter being added to the waitqueue. */ @@ -1647,8 +1619,7 @@ double_unlock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2) /* * Wake up waiters matching bitset queued on this futex (uaddr). */ -static int -futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) +int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset) { struct futex_hash_bucket *hb; struct futex_q *this, *next; @@ -1743,9 +1714,8 @@ static int futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr) * Wake up all waiters hashed on the physical page that is mapped * to this virtual address: */ -static int -futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, - int nr_wake, int nr_wake2, int op) +int futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, + int nr_wake, int nr_wake2, int op) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; struct futex_hash_bucket *hb1, *hb2; @@ -2124,9 +2094,8 @@ futex_proxy_trylock_atomic(u32 __user *pifutex, struct futex_hash_bucket *hb1, * - >=0 - on success, the number of tasks requeued or woken; * - <0 - on error */ -static int futex_requeue(u32 __user *uaddr1, unsigned int flags, - u32 __user *uaddr2, int nr_wake, int nr_requeue, - u32 *cmpval, int requeue_pi) +int futex_requeue(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2, + int nr_wake, int nr_requeue, u32 *cmpval, int requeue_pi) { union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT; int task_count = 0, ret; @@ -2926,8 +2895,7 @@ retry_private: return ret; } -static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, - ktime_t *abs_time, u32 bitset) +int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset) { struct hrtimer_sleeper timeout, *to; struct restart_block *restart; @@ -3015,8 +2983,7 @@ static long futex_wait_restart(struct restart_block *restart) * * Also serves as futex trylock_pi()'ing, and due semantics. */ -static int futex_lock_pi(u32 __user *uaddr, unsigned int flags, - ktime_t *time, int trylock) +int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock) { struct hrtimer_sleeper timeout, *to; struct task_struct *exiting = NULL; @@ -3186,7 +3153,7 @@ uaddr_faulted: * This is the in-kernel slowpath: we look up the PI state (if any), * and do the rt-mutex unlock. */ -static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) +int futex_unlock_pi(u32 __user *uaddr, unsigned int flags) { u32 curval, uval, vpid = task_pid_vnr(current); union futex_key key = FUTEX_KEY_INIT; @@ -3403,9 +3370,9 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, * - 0 - On success; * - <0 - On error */ -static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, - u32 val, ktime_t *abs_time, u32 bitset, - u32 __user *uaddr2) +int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, + u32 val, ktime_t *abs_time, u32 bitset, + u32 __user *uaddr2) { struct hrtimer_sleeper timeout, *to; struct rt_mutex_waiter rt_waiter; @@ -3539,87 +3506,6 @@ out: return ret; } -/* - * Support for robust futexes: the kernel cleans up held futexes at - * thread exit time. - * - * Implementation: user-space maintains a per-thread list of locks it - * is holding. Upon do_exit(), the kernel carefully walks this list, - * and marks all locks that are owned by this thread with the - * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is - * always manipulated with the lock held, so the list is private and - * per-thread. Userspace also maintains a per-thread 'list_op_pending' - * field, to allow the kernel to clean up if the thread dies after - * acquiring the lock, but just before it could have added itself to - * the list. There can only be one such pending lock. - */ - -/** - * sys_set_robust_list() - Set the robust-futex list head of a task - * @head: pointer to the list-head - * @len: length of the list-head, as userspace expects - */ -SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, - size_t, len) -{ - if (!futex_cmpxchg_enabled) - return -ENOSYS; - /* - * The kernel knows only one size for now: - */ - if (unlikely(len != sizeof(*head))) - return -EINVAL; - - current->robust_list = head; - - return 0; -} - -/** - * sys_get_robust_list() - Get the robust-futex list head of a task - * @pid: pid of the process [zero for current task] - * @head_ptr: pointer to a list-head pointer, the kernel fills it in - * @len_ptr: pointer to a length field, the kernel fills in the header size - */ -SYSCALL_DEFINE3(get_robust_list, int, pid, - struct robust_list_head __user * __user *, head_ptr, - size_t __user *, len_ptr) -{ - struct robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; - - head = p->robust_list; - rcu_read_unlock(); - - if (put_user(sizeof(*head), len_ptr)) - return -EFAULT; - return put_user(head, head_ptr); - -err_unlock: - rcu_read_unlock(); - - return ret; -} - /* Constants for the pending_op argument of handle_futex_death */ #define HANDLE_DEATH_PENDING true #define HANDLE_DEATH_LIST false @@ -3821,227 +3707,16 @@ static void exit_robust_list(struct task_struct *curr) } } -static void futex_cleanup(struct task_struct *tsk) -{ - if (unlikely(tsk->robust_list)) { - exit_robust_list(tsk); - tsk->robust_list = NULL; - } - #ifdef CONFIG_COMPAT - if (unlikely(tsk->compat_robust_list)) { - compat_exit_robust_list(tsk); - tsk->compat_robust_list = NULL; - } -#endif - - if (unlikely(!list_empty(&tsk->pi_state_list))) - exit_pi_state_list(tsk); -} - -/** - * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD - * @tsk: task to set the state on - * - * Set the futex exit state of the task lockless. The futex waiter code - * observes that state when a task is exiting and loops until the task has - * actually finished the futex cleanup. The worst case for this is that the - * waiter runs through the wait loop until the state becomes visible. - * - * This is called from the recursive fault handling path in do_exit(). - * - * This is best effort. Either the futex exit code has run already or - * not. If the OWNER_DIED bit has been set on the futex then the waiter can - * take it over. If not, the problem is pushed back to user space. If the - * futex exit code did not run yet, then an already queued waiter might - * block forever, but there is nothing which can be done about that. - */ -void futex_exit_recursive(struct task_struct *tsk) -{ - /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ - if (tsk->futex_state == FUTEX_STATE_EXITING) - mutex_unlock(&tsk->futex_exit_mutex); - tsk->futex_state = FUTEX_STATE_DEAD; -} - -static void futex_cleanup_begin(struct task_struct *tsk) -{ - /* - * Prevent various race issues against a concurrent incoming waiter - * including live locks by forcing the waiter to block on - * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in - * attach_to_pi_owner(). - */ - mutex_lock(&tsk->futex_exit_mutex); - - /* - * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. - * - * This ensures that all subsequent checks of tsk->futex_state in - * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with - * tsk->pi_lock held. - * - * It guarantees also that a pi_state which was queued right before - * the state change under tsk->pi_lock by a concurrent waiter must - * be observed in exit_pi_state_list(). - */ - raw_spin_lock_irq(&tsk->pi_lock); - tsk->futex_state = FUTEX_STATE_EXITING; - raw_spin_unlock_irq(&tsk->pi_lock); -} - -static void futex_cleanup_end(struct task_struct *tsk, int state) -{ - /* - * Lockless store. The only side effect is that an observer might - * take another loop until it becomes visible. - */ - tsk->futex_state = state; - /* - * Drop the exit protection. This unblocks waiters which observed - * FUTEX_STATE_EXITING to reevaluate the state. - */ - mutex_unlock(&tsk->futex_exit_mutex); -} - -void futex_exec_release(struct task_struct *tsk) -{ - /* - * The state handling is done for consistency, but in the case of - * exec() there is no way to prevent further damage as the PID stays - * the same. But for the unlikely and arguably buggy case that a - * futex is held on exec(), this provides at least as much state - * consistency protection which is possible. - */ - futex_cleanup_begin(tsk); - futex_cleanup(tsk); - /* - * Reset the state to FUTEX_STATE_OK. The task is alive and about - * exec a new binary. - */ - futex_cleanup_end(tsk, FUTEX_STATE_OK); -} - -void futex_exit_release(struct task_struct *tsk) -{ - futex_cleanup_begin(tsk); - futex_cleanup(tsk); - futex_cleanup_end(tsk, FUTEX_STATE_DEAD); -} - -long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, - u32 __user *uaddr2, u32 val2, u32 val3) -{ - int cmd = op & FUTEX_CMD_MASK; - unsigned int flags = 0; - - if (!(op & FUTEX_PRIVATE_FLAG)) - flags |= FLAGS_SHARED; - - if (op & FUTEX_CLOCK_REALTIME) { - flags |= FLAGS_CLOCKRT; - if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && - cmd != FUTEX_LOCK_PI2) - return -ENOSYS; - } - - switch (cmd) { - case FUTEX_LOCK_PI: - case FUTEX_LOCK_PI2: - case FUTEX_UNLOCK_PI: - case FUTEX_TRYLOCK_PI: - case FUTEX_WAIT_REQUEUE_PI: - case FUTEX_CMP_REQUEUE_PI: - if (!futex_cmpxchg_enabled) - return -ENOSYS; - } - - switch (cmd) { - case FUTEX_WAIT: - val3 = FUTEX_BITSET_MATCH_ANY; - fallthrough; - case FUTEX_WAIT_BITSET: - return futex_wait(uaddr, flags, val, timeout, val3); - case FUTEX_WAKE: - val3 = FUTEX_BITSET_MATCH_ANY; - fallthrough; - case FUTEX_WAKE_BITSET: - return futex_wake(uaddr, flags, val, val3); - case FUTEX_REQUEUE: - return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); - case FUTEX_CMP_REQUEUE: - return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); - case FUTEX_WAKE_OP: - return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); - case FUTEX_LOCK_PI: - flags |= FLAGS_CLOCKRT; - fallthrough; - case FUTEX_LOCK_PI2: - return futex_lock_pi(uaddr, flags, timeout, 0); - case FUTEX_UNLOCK_PI: - return futex_unlock_pi(uaddr, flags); - case FUTEX_TRYLOCK_PI: - return futex_lock_pi(uaddr, flags, NULL, 1); - case FUTEX_WAIT_REQUEUE_PI: - val3 = FUTEX_BITSET_MATCH_ANY; - return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, - uaddr2); - case FUTEX_CMP_REQUEUE_PI: - return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); - } - return -ENOSYS; -} - -static __always_inline bool futex_cmd_has_timeout(u32 cmd) -{ - switch (cmd) { - case FUTEX_WAIT: - case FUTEX_LOCK_PI: - case FUTEX_LOCK_PI2: - case FUTEX_WAIT_BITSET: - case FUTEX_WAIT_REQUEUE_PI: - return true; - } - return false; -} - -static __always_inline int -futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) -{ - if (!timespec64_valid(ts)) - return -EINVAL; - - *t = timespec64_to_ktime(*ts); - if (cmd == FUTEX_WAIT) - *t = ktime_add_safe(ktime_get(), *t); - else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) - *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); - return 0; -} - -SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, - const struct __kernel_timespec __user *, utime, - u32 __user *, uaddr2, u32, val3) +static void __user *futex_uaddr(struct robust_list __user *entry, + compat_long_t futex_offset) { - int ret, cmd = op & FUTEX_CMD_MASK; - ktime_t t, *tp = NULL; - struct timespec64 ts; - - if (utime && futex_cmd_has_timeout(cmd)) { - if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) - return -EFAULT; - if (get_timespec64(&ts, utime)) - return -EFAULT; - ret = futex_init_timeout(cmd, op, &ts, &t); - if (ret) - return ret; - tp = &t; - } + compat_uptr_t base = ptr_to_compat(entry); + void __user *uaddr = compat_ptr(base + futex_offset); - return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); + return uaddr; } -#ifdef CONFIG_COMPAT /* * Fetch a robust-list pointer. Bit 0 signals PI futexes: */ @@ -4058,15 +3733,6 @@ compat_fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **ent return 0; } -static void __user *futex_uaddr(struct robust_list __user *entry, - compat_long_t futex_offset) -{ - compat_uptr_t base = ptr_to_compat(entry); - void __user *uaddr = compat_ptr(base + futex_offset); - - return uaddr; -} - /* * Walk curr->robust_list (very carefully, it's a userspace list!) * and mark any locks found there dead, and notify any waiters. @@ -4143,83 +3809,115 @@ static void compat_exit_robust_list(struct task_struct *curr) handle_futex_death(uaddr, curr, pip, HANDLE_DEATH_PENDING); } } +#endif -COMPAT_SYSCALL_DEFINE2(set_robust_list, - struct compat_robust_list_head __user *, head, - compat_size_t, len) +static void futex_cleanup(struct task_struct *tsk) { - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - if (unlikely(len != sizeof(*head))) - return -EINVAL; + if (unlikely(tsk->robust_list)) { + exit_robust_list(tsk); + tsk->robust_list = NULL; + } - current->compat_robust_list = head; +#ifdef CONFIG_COMPAT + if (unlikely(tsk->compat_robust_list)) { + compat_exit_robust_list(tsk); + tsk->compat_robust_list = NULL; + } +#endif - return 0; + if (unlikely(!list_empty(&tsk->pi_state_list))) + exit_pi_state_list(tsk); } -COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, - compat_uptr_t __user *, head_ptr, - compat_size_t __user *, len_ptr) +/** + * futex_exit_recursive - Set the tasks futex state to FUTEX_STATE_DEAD + * @tsk: task to set the state on + * + * Set the futex exit state of the task lockless. The futex waiter code + * observes that state when a task is exiting and loops until the task has + * actually finished the futex cleanup. The worst case for this is that the + * waiter runs through the wait loop until the state becomes visible. + * + * This is called from the recursive fault handling path in do_exit(). + * + * This is best effort. Either the futex exit code has run already or + * not. If the OWNER_DIED bit has been set on the futex then the waiter can + * take it over. If not, the problem is pushed back to user space. If the + * futex exit code did not run yet, then an already queued waiter might + * block forever, but there is nothing which can be done about that. + */ +void futex_exit_recursive(struct task_struct *tsk) { - struct compat_robust_list_head __user *head; - unsigned long ret; - struct task_struct *p; - - if (!futex_cmpxchg_enabled) - return -ENOSYS; - - rcu_read_lock(); - - ret = -ESRCH; - if (!pid) - p = current; - else { - p = find_task_by_vpid(pid); - if (!p) - goto err_unlock; - } - - ret = -EPERM; - if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) - goto err_unlock; - - head = p->compat_robust_list; - rcu_read_unlock(); - - if (put_user(sizeof(*head), len_ptr)) - return -EFAULT; - return put_user(ptr_to_compat(head), head_ptr); + /* If the state is FUTEX_STATE_EXITING then futex_exit_mutex is held */ + if (tsk->futex_state == FUTEX_STATE_EXITING) + mutex_unlock(&tsk->futex_exit_mutex); + tsk->futex_state = FUTEX_STATE_DEAD; +} -err_unlock: - rcu_read_unlock(); +static void futex_cleanup_begin(struct task_struct *tsk) +{ + /* + * Prevent various race issues against a concurrent incoming waiter + * including live locks by forcing the waiter to block on + * tsk->futex_exit_mutex when it observes FUTEX_STATE_EXITING in + * attach_to_pi_owner(). + */ + mutex_lock(&tsk->futex_exit_mutex); - return ret; + /* + * Switch the state to FUTEX_STATE_EXITING under tsk->pi_lock. + * + * This ensures that all subsequent checks of tsk->futex_state in + * attach_to_pi_owner() must observe FUTEX_STATE_EXITING with + * tsk->pi_lock held. + * + * It guarantees also that a pi_state which was queued right before + * the state change under tsk->pi_lock by a concurrent waiter must + * be observed in exit_pi_state_list(). + */ + raw_spin_lock_irq(&tsk->pi_lock); + tsk->futex_state = FUTEX_STATE_EXITING; + raw_spin_unlock_irq(&tsk->pi_lock); } -#endif /* CONFIG_COMPAT */ -#ifdef CONFIG_COMPAT_32BIT_TIME -SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, - const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, - u32, val3) +static void futex_cleanup_end(struct task_struct *tsk, int state) { - int ret, cmd = op & FUTEX_CMD_MASK; - ktime_t t, *tp = NULL; - struct timespec64 ts; + /* + * Lockless store. The only side effect is that an observer might + * take another loop until it becomes visible. + */ + tsk->futex_state = state; + /* + * Drop the exit protection. This unblocks waiters which observed + * FUTEX_STATE_EXITING to reevaluate the state. + */ + mutex_unlock(&tsk->futex_exit_mutex); +} - if (utime && futex_cmd_has_timeout(cmd)) { - if (get_old_timespec32(&ts, utime)) - return -EFAULT; - ret = futex_init_timeout(cmd, op, &ts, &t); - if (ret) - return ret; - tp = &t; - } +void futex_exec_release(struct task_struct *tsk) +{ + /* + * The state handling is done for consistency, but in the case of + * exec() there is no way to prevent further damage as the PID stays + * the same. But for the unlikely and arguably buggy case that a + * futex is held on exec(), this provides at least as much state + * consistency protection which is possible. + */ + futex_cleanup_begin(tsk); + futex_cleanup(tsk); + /* + * Reset the state to FUTEX_STATE_OK. The task is alive and about + * exec a new binary. + */ + futex_cleanup_end(tsk, FUTEX_STATE_OK); +} - return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); +void futex_exit_release(struct task_struct *tsk) +{ + futex_cleanup_begin(tsk); + futex_cleanup(tsk); + futex_cleanup_end(tsk, FUTEX_STATE_DEAD); } -#endif /* CONFIG_COMPAT_32BIT_TIME */ static void __init futex_detect_cmpxchg(void) { diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h new file mode 100644 index 000000000000..7bb4ca8bf32f --- /dev/null +++ b/kernel/futex/futex.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _FUTEX_H +#define _FUTEX_H + +#include + +/* + * Futex flags used to encode options to functions and preserve them across + * restarts. + */ +#ifdef CONFIG_MMU +# define FLAGS_SHARED 0x01 +#else +/* + * NOMMU does not have per process address space. Let the compiler optimize + * code away. + */ +# define FLAGS_SHARED 0x00 +#endif +#define FLAGS_CLOCKRT 0x02 +#define FLAGS_HAS_TIMEOUT 0x04 + +#ifdef CONFIG_HAVE_FUTEX_CMPXCHG +#define futex_cmpxchg_enabled 1 +#else +extern int __read_mostly futex_cmpxchg_enabled; +#endif + +#ifdef CONFIG_FAIL_FUTEX +extern bool should_fail_futex(bool fshared); +#else +static inline bool should_fail_futex(bool fshared) +{ + return false; +} +#endif + +extern int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags, u32 + val, ktime_t *abs_time, u32 bitset, u32 __user + *uaddr2); + +extern int futex_requeue(u32 __user *uaddr1, unsigned int flags, + u32 __user *uaddr2, int nr_wake, int nr_requeue, + u32 *cmpval, int requeue_pi); + +extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, + ktime_t *abs_time, u32 bitset); + +extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); + +extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, + u32 __user *uaddr2, int nr_wake, int nr_wake2, int op); + +extern int futex_unlock_pi(u32 __user *uaddr, unsigned int flags); + +extern int futex_lock_pi(u32 __user *uaddr, unsigned int flags, ktime_t *time, int trylock); + +#endif /* _FUTEX_H */ diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c new file mode 100644 index 000000000000..6e7e36c640a1 --- /dev/null +++ b/kernel/futex/syscalls.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include + +#include "futex.h" + +/* + * Support for robust futexes: the kernel cleans up held futexes at + * thread exit time. + * + * Implementation: user-space maintains a per-thread list of locks it + * is holding. Upon do_exit(), the kernel carefully walks this list, + * and marks all locks that are owned by this thread with the + * FUTEX_OWNER_DIED bit, and wakes up a waiter (if any). The list is + * always manipulated with the lock held, so the list is private and + * per-thread. Userspace also maintains a per-thread 'list_op_pending' + * field, to allow the kernel to clean up if the thread dies after + * acquiring the lock, but just before it could have added itself to + * the list. There can only be one such pending lock. + */ + +/** + * sys_set_robust_list() - Set the robust-futex list head of a task + * @head: pointer to the list-head + * @len: length of the list-head, as userspace expects + */ +SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, + size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + /* + * The kernel knows only one size for now: + */ + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->robust_list = head; + + return 0; +} + +/** + * sys_get_robust_list() - Get the robust-futex list head of a task + * @pid: pid of the process [zero for current task] + * @head_ptr: pointer to a list-head pointer, the kernel fills it in + * @len_ptr: pointer to a length field, the kernel fills in the header size + */ +SYSCALL_DEFINE3(get_robust_list, int, pid, + struct robust_list_head __user * __user *, head_ptr, + size_t __user *, len_ptr) +{ + struct robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) + goto err_unlock; + + head = p->robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(head, head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} + +long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout, + u32 __user *uaddr2, u32 val2, u32 val3) +{ + int cmd = op & FUTEX_CMD_MASK; + unsigned int flags = 0; + + if (!(op & FUTEX_PRIVATE_FLAG)) + flags |= FLAGS_SHARED; + + if (op & FUTEX_CLOCK_REALTIME) { + flags |= FLAGS_CLOCKRT; + if (cmd != FUTEX_WAIT_BITSET && cmd != FUTEX_WAIT_REQUEUE_PI && + cmd != FUTEX_LOCK_PI2) + return -ENOSYS; + } + + switch (cmd) { + case FUTEX_LOCK_PI: + case FUTEX_LOCK_PI2: + case FUTEX_UNLOCK_PI: + case FUTEX_TRYLOCK_PI: + case FUTEX_WAIT_REQUEUE_PI: + case FUTEX_CMP_REQUEUE_PI: + if (!futex_cmpxchg_enabled) + return -ENOSYS; + } + + switch (cmd) { + case FUTEX_WAIT: + val3 = FUTEX_BITSET_MATCH_ANY; + fallthrough; + case FUTEX_WAIT_BITSET: + return futex_wait(uaddr, flags, val, timeout, val3); + case FUTEX_WAKE: + val3 = FUTEX_BITSET_MATCH_ANY; + fallthrough; + case FUTEX_WAKE_BITSET: + return futex_wake(uaddr, flags, val, val3); + case FUTEX_REQUEUE: + return futex_requeue(uaddr, flags, uaddr2, val, val2, NULL, 0); + case FUTEX_CMP_REQUEUE: + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 0); + case FUTEX_WAKE_OP: + return futex_wake_op(uaddr, flags, uaddr2, val, val2, val3); + case FUTEX_LOCK_PI: + flags |= FLAGS_CLOCKRT; + fallthrough; + case FUTEX_LOCK_PI2: + return futex_lock_pi(uaddr, flags, timeout, 0); + case FUTEX_UNLOCK_PI: + return futex_unlock_pi(uaddr, flags); + case FUTEX_TRYLOCK_PI: + return futex_lock_pi(uaddr, flags, NULL, 1); + case FUTEX_WAIT_REQUEUE_PI: + val3 = FUTEX_BITSET_MATCH_ANY; + return futex_wait_requeue_pi(uaddr, flags, val, timeout, val3, + uaddr2); + case FUTEX_CMP_REQUEUE_PI: + return futex_requeue(uaddr, flags, uaddr2, val, val2, &val3, 1); + } + return -ENOSYS; +} + +static __always_inline bool futex_cmd_has_timeout(u32 cmd) +{ + switch (cmd) { + case FUTEX_WAIT: + case FUTEX_LOCK_PI: + case FUTEX_LOCK_PI2: + case FUTEX_WAIT_BITSET: + case FUTEX_WAIT_REQUEUE_PI: + return true; + } + return false; +} + +static __always_inline int +futex_init_timeout(u32 cmd, u32 op, struct timespec64 *ts, ktime_t *t) +{ + if (!timespec64_valid(ts)) + return -EINVAL; + + *t = timespec64_to_ktime(*ts); + if (cmd == FUTEX_WAIT) + *t = ktime_add_safe(ktime_get(), *t); + else if (cmd != FUTEX_LOCK_PI && !(op & FUTEX_CLOCK_REALTIME)) + *t = timens_ktime_to_host(CLOCK_MONOTONIC, *t); + return 0; +} + +SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, + const struct __kernel_timespec __user *, utime, + u32 __user *, uaddr2, u32, val3) +{ + int ret, cmd = op & FUTEX_CMD_MASK; + ktime_t t, *tp = NULL; + struct timespec64 ts; + + if (utime && futex_cmd_has_timeout(cmd)) { + if (unlikely(should_fail_futex(!(op & FUTEX_PRIVATE_FLAG)))) + return -EFAULT; + if (get_timespec64(&ts, utime)) + return -EFAULT; + ret = futex_init_timeout(cmd, op, &ts, &t); + if (ret) + return ret; + tp = &t; + } + + return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(set_robust_list, + struct compat_robust_list_head __user *, head, + compat_size_t, len) +{ + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + if (unlikely(len != sizeof(*head))) + return -EINVAL; + + current->compat_robust_list = head; + + return 0; +} + +COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid, + compat_uptr_t __user *, head_ptr, + compat_size_t __user *, len_ptr) +{ + struct compat_robust_list_head __user *head; + unsigned long ret; + struct task_struct *p; + + if (!futex_cmpxchg_enabled) + return -ENOSYS; + + rcu_read_lock(); + + ret = -ESRCH; + if (!pid) + p = current; + else { + p = find_task_by_vpid(pid); + if (!p) + goto err_unlock; + } + + ret = -EPERM; + if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS)) + goto err_unlock; + + head = p->compat_robust_list; + rcu_read_unlock(); + + if (put_user(sizeof(*head), len_ptr)) + return -EFAULT; + return put_user(ptr_to_compat(head), head_ptr); + +err_unlock: + rcu_read_unlock(); + + return ret; +} +#endif /* CONFIG_COMPAT */ + +#ifdef CONFIG_COMPAT_32BIT_TIME +SYSCALL_DEFINE6(futex_time32, u32 __user *, uaddr, int, op, u32, val, + const struct old_timespec32 __user *, utime, u32 __user *, uaddr2, + u32, val3) +{ + int ret, cmd = op & FUTEX_CMD_MASK; + ktime_t t, *tp = NULL; + struct timespec64 ts; + + if (utime && futex_cmd_has_timeout(cmd)) { + if (get_old_timespec32(&ts, utime)) + return -EFAULT; + ret = futex_init_timeout(cmd, op, &ts, &t); + if (ret) + return ret; + tp = &t; + } + + return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); +} +#endif /* CONFIG_COMPAT_32BIT_TIME */ + diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index f43d89d92860..13ee8334ab6e 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -143,7 +143,7 @@ COND_SYSCALL(capset); /* __ARCH_WANT_SYS_CLONE3 */ COND_SYSCALL(clone3); -/* kernel/futex.c */ +/* kernel/futex/syscalls.c */ COND_SYSCALL(futex); COND_SYSCALL(futex_time32); COND_SYSCALL(set_robust_list); -- cgit v1.2.3 From bf69bad38cf63d980e8a603f8d1bd1f85b5ed3d9 Mon Sep 17 00:00:00 2001 From: André Almeida Date: Thu, 23 Sep 2021 14:11:05 -0300 Subject: futex: Implement sys_futex_waitv() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support to wait on multiple futexes. This is the interface implemented by this syscall: futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes, unsigned int flags, struct timespec *timeout, clockid_t clockid) struct futex_waitv { __u64 val; __u64 uaddr; __u32 flags; __u32 __reserved; }; Given an array of struct futex_waitv, wait on each uaddr. The thread wakes if a futex_wake() is performed at any uaddr. The syscall returns immediately if any waiter has *uaddr != val. *timeout is an optional absolute timeout value for the operation. This syscall supports only 64bit sized timeout structs. The flags argument of the syscall should be empty, but it can be used for future extensions. Flags for shared futexes, sizes, etc. should be used on the individual flags of each waiter. __reserved is used for explicit padding and should be 0, but it might be used for future extensions. If the userspace uses 32-bit pointers, it should make sure to explicitly cast it when assigning to waitv::uaddr. Returns the array index of one of the woken futexes. There’s no given information of how many were woken, or any particular attribute of it (if it’s the first woken, if it is of the smaller index...). Signed-off-by: André Almeida Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210923171111.300673-17-andrealmeid@collabora.com --- MAINTAINERS | 1 + include/linux/syscalls.h | 5 + include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/futex.h | 25 +++++ kernel/futex/futex.h | 15 +++ kernel/futex/syscalls.c | 119 ++++++++++++++++++++++ kernel/futex/waitwake.c | 201 ++++++++++++++++++++++++++++++++++++++ kernel/sys_ni.c | 1 + 8 files changed, 371 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index b3094cb1afdd..310fb018acf9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7718,6 +7718,7 @@ M: Ingo Molnar R: Peter Zijlstra R: Darren Hart R: Davidlohr Bueso +R: André Almeida L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 25979682ade5..528a478dbda8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -58,6 +58,7 @@ struct mq_attr; struct compat_stat; struct old_timeval32; struct robust_list_head; +struct futex_waitv; struct getcpu_cache; struct old_linux_dirent; struct perf_event_attr; @@ -623,6 +624,10 @@ asmlinkage long sys_get_robust_list(int pid, asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); +asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, + unsigned int nr_futexes, unsigned int flags, + struct __kernel_timespec __user *timeout, clockid_t clockid); + /* kernel/hrtimer.c */ asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 1c5fb86d455a..4557a8b6086f 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #define __NR_process_mrelease 448 __SYSCALL(__NR_process_mrelease, sys_process_mrelease) +#define __NR_futex_waitv 449 +__SYSCALL(__NR_futex_waitv, sys_futex_waitv) + #undef __NR_syscalls -#define __NR_syscalls 449 +#define __NR_syscalls 450 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 235e5b2facaa..71a5df8d2689 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -43,6 +43,31 @@ #define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \ FUTEX_PRIVATE_FLAG) +/* + * Flags to specify the bit length of the futex word for futex2 syscalls. + * Currently, only 32 is supported. + */ +#define FUTEX_32 2 + +/* + * Max numbers of elements in a futex_waitv array + */ +#define FUTEX_WAITV_MAX 128 + +/** + * struct futex_waitv - A waiter for vectorized wait + * @val: Expected value at uaddr + * @uaddr: User address to wait on + * @flags: Flags for this waiter + * @__reserved: Reserved member to preserve data alignment. Should be 0. + */ +struct futex_waitv { + __u64 val; + __u64 uaddr; + __u32 flags; + __u32 __reserved; +}; + /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 465f7bd5caef..948fcf317681 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -268,6 +268,21 @@ extern int futex_requeue(u32 __user *uaddr1, unsigned int flags, extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); +/** + * struct futex_vector - Auxiliary struct for futex_waitv() + * @w: Userspace provided data + * @q: Kernel side data + * + * Struct used to build an array with all data need for futex_waitv() + */ +struct futex_vector { + struct futex_waitv w; + struct futex_q q; +}; + +extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to); + extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 6e7e36c640a1..6f91a07a6a83 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -199,6 +199,125 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } +/* Mask of available flags for each futex in futex_waitv list */ +#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG) + +/** + * futex_parse_waitv - Parse a waitv array from userspace + * @futexv: Kernel side list of waiters to be filled + * @uwaitv: Userspace list to be parsed + * @nr_futexes: Length of futexv + * + * Return: Error code on failure, 0 on success + */ +static int futex_parse_waitv(struct futex_vector *futexv, + struct futex_waitv __user *uwaitv, + unsigned int nr_futexes) +{ + struct futex_waitv aux; + unsigned int i; + + for (i = 0; i < nr_futexes; i++) { + if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) + return -EFAULT; + + if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved) + return -EINVAL; + + if (!(aux.flags & FUTEX_32)) + return -EINVAL; + + futexv[i].w.flags = aux.flags; + futexv[i].w.val = aux.val; + futexv[i].w.uaddr = aux.uaddr; + futexv[i].q = futex_q_init; + } + + return 0; +} + +/** + * sys_futex_waitv - Wait on a list of futexes + * @waiters: List of futexes to wait on + * @nr_futexes: Length of futexv + * @flags: Flag for timeout (monotonic/realtime) + * @timeout: Optional absolute timeout. + * @clockid: Clock to be used for the timeout, realtime or monotonic. + * + * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes + * if a futex_wake() is performed at any uaddr. The syscall returns immediately + * if any waiter has *uaddr != val. *timeout is an optional timeout value for + * the operation. Each waiter has individual flags. The `flags` argument for + * the syscall should be used solely for specifying the timeout as realtime, if + * needed. Flags for private futexes, sizes, etc. should be used on the + * individual flags of each waiter. + * + * Returns the array index of one of the woken futexes. No further information + * is provided: any number of other futexes may also have been woken by the + * same event, and if more than one futex was woken, the retrned index may + * refer to any one of them. (It is not necessaryily the futex with the + * smallest index, nor the one most recently woken, nor...) + */ + +SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, + unsigned int, nr_futexes, unsigned int, flags, + struct __kernel_timespec __user *, timeout, clockid_t, clockid) +{ + struct hrtimer_sleeper to; + struct futex_vector *futexv; + struct timespec64 ts; + ktime_t time; + int ret; + + /* This syscall supports no flags for now */ + if (flags) + return -EINVAL; + + if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) + return -EINVAL; + + if (timeout) { + int flag_clkid = 0, flag_init = 0; + + if (clockid == CLOCK_REALTIME) { + flag_clkid = FLAGS_CLOCKRT; + flag_init = FUTEX_CLOCK_REALTIME; + } + + if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) + return -EINVAL; + + if (get_timespec64(&ts, timeout)) + return -EFAULT; + + /* + * Since there's no opcode for futex_waitv, use + * FUTEX_WAIT_BITSET that uses absolute timeout as well + */ + ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); + if (ret) + return ret; + + futex_setup_timer(&time, &to, flag_clkid, 0); + } + + futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); + if (!futexv) + return -ENOMEM; + + ret = futex_parse_waitv(futexv, waiters, nr_futexes); + if (!ret) + ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); + + if (timeout) { + hrtimer_cancel(&to.timer); + destroy_hrtimer_on_stack(&to.timer); + } + + kfree(futexv); + return ret; +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index 36880784aa11..4ce0923f1ce3 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -357,6 +357,207 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, __set_current_state(TASK_RUNNING); } +/** + * unqueue_multiple - Remove various futexes from their hash bucket + * @v: The list of futexes to unqueue + * @count: Number of futexes in the list + * + * Helper to unqueue a list of futexes. This can't fail. + * + * Return: + * - >=0 - Index of the last futex that was awoken; + * - -1 - No futex was awoken + */ +static int unqueue_multiple(struct futex_vector *v, int count) +{ + int ret = -1, i; + + for (i = 0; i < count; i++) { + if (!futex_unqueue(&v[i].q)) + ret = i; + } + + return ret; +} + +/** + * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes + * @vs: The futex list to wait on + * @count: The size of the list + * @woken: Index of the last woken futex, if any. Used to notify the + * caller that it can return this index to userspace (return parameter) + * + * Prepare multiple futexes in a single step and enqueue them. This may fail if + * the futex list is invalid or if any futex was already awoken. On success the + * task is ready to interruptible sleep. + * + * Return: + * - 1 - One of the futexes was woken by another thread + * - 0 - Success + * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL + */ +static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) +{ + struct futex_hash_bucket *hb; + bool retry = false; + int ret, i; + u32 uval; + + /* + * Enqueuing multiple futexes is tricky, because we need to enqueue + * each futex on the list before dealing with the next one to avoid + * deadlocking on the hash bucket. But, before enqueuing, we need to + * make sure that current->state is TASK_INTERRUPTIBLE, so we don't + * lose any wake events, which cannot be done before the get_futex_key + * of the next key, because it calls get_user_pages, which can sleep. + * Thus, we fetch the list of futexes keys in two steps, by first + * pinning all the memory keys in the futex key, and only then we read + * each key and queue the corresponding futex. + * + * Private futexes doesn't need to recalculate hash in retry, so skip + * get_futex_key() when retrying. + */ +retry: + for (i = 0; i < count; i++) { + if ((vs[i].w.flags & FUTEX_PRIVATE_FLAG) && retry) + continue; + + ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), + !(vs[i].w.flags & FUTEX_PRIVATE_FLAG), + &vs[i].q.key, FUTEX_READ); + + if (unlikely(ret)) + return ret; + } + + set_current_state(TASK_INTERRUPTIBLE); + + for (i = 0; i < count; i++) { + u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; + struct futex_q *q = &vs[i].q; + u32 val = (u32)vs[i].w.val; + + hb = futex_q_lock(q); + ret = futex_get_value_locked(&uval, uaddr); + + if (!ret && uval == val) { + /* + * The bucket lock can't be held while dealing with the + * next futex. Queue each futex at this moment so hb can + * be unlocked. + */ + futex_queue(q, hb); + continue; + } + + futex_q_unlock(hb); + __set_current_state(TASK_RUNNING); + + /* + * Even if something went wrong, if we find out that a futex + * was woken, we don't return error and return this index to + * userspace + */ + *woken = unqueue_multiple(vs, i); + if (*woken >= 0) + return 1; + + if (ret) { + /* + * If we need to handle a page fault, we need to do so + * without any lock and any enqueued futex (otherwise + * we could lose some wakeup). So we do it here, after + * undoing all the work done so far. In success, we + * retry all the work. + */ + if (get_user(uval, uaddr)) + return -EFAULT; + + retry = true; + goto retry; + } + + if (uval != val) + return -EWOULDBLOCK; + } + + return 0; +} + +/** + * futex_sleep_multiple - Check sleeping conditions and sleep + * @vs: List of futexes to wait for + * @count: Length of vs + * @to: Timeout + * + * Sleep if and only if the timeout hasn't expired and no futex on the list has + * been woken up. + */ +static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to) +{ + if (to && !to->task) + return; + + for (; count; count--, vs++) { + if (!READ_ONCE(vs->q.lock_ptr)) + return; + } + + freezable_schedule(); +} + +/** + * futex_wait_multiple - Prepare to wait on and enqueue several futexes + * @vs: The list of futexes to wait on + * @count: The number of objects + * @to: Timeout before giving up and returning to userspace + * + * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function + * sleeps on a group of futexes and returns on the first futex that is + * wake, or after the timeout has elapsed. + * + * Return: + * - >=0 - Hint to the futex that was awoken + * - <0 - On error + */ +int futex_wait_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to) +{ + int ret, hint = 0; + + if (to) + hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); + + while (1) { + ret = futex_wait_multiple_setup(vs, count, &hint); + if (ret) { + if (ret > 0) { + /* A futex was woken during setup */ + ret = hint; + } + return ret; + } + + futex_sleep_multiple(vs, count, to); + + __set_current_state(TASK_RUNNING); + + ret = unqueue_multiple(vs, count); + if (ret >= 0) + return ret; + + if (to && !to->task) + return -ETIMEDOUT; + else if (signal_pending(current)) + return -ERESTARTSYS; + /* + * The final case is a spurious wakeup, for + * which just retry. + */ + } +} + /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 13ee8334ab6e..d1944258cfc0 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -150,6 +150,7 @@ COND_SYSCALL(set_robust_list); COND_SYSCALL_COMPAT(set_robust_list); COND_SYSCALL(get_robust_list); COND_SYSCALL_COMPAT(get_robust_list); +COND_SYSCALL(futex_waitv); /* kernel/hrtimer.c */ -- cgit v1.2.3 From 9b3c4ab3045e953670c7de9c1165fae5358a7237 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 21 Sep 2021 21:54:32 +0200 Subject: sched,rcu: Rework try_invoke_on_locked_down_task() Give try_invoke_on_locked_down_task() a saner name and have it return an int so that the caller might distinguish between different reasons of failure. Signed-off-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Acked-by: Vasily Gorbik Tested-by: Vasily Gorbik # on s390 Link: https://lkml.kernel.org/r/20210929152428.649944917@infradead.org --- include/linux/wait.h | 3 ++- kernel/rcu/tasks.h | 12 ++++++------ kernel/rcu/tree_stall.h | 8 ++++---- kernel/sched/core.c | 6 +++--- 4 files changed, 15 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 93dab0e9580f..2d0df57c9902 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -1160,6 +1160,7 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i (wait)->flags = 0; \ } while (0) -bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg); +typedef int (*task_call_f)(struct task_struct *p, void *arg); +extern int task_call_func(struct task_struct *p, task_call_f func, void *arg); #endif /* _LINUX_WAIT_H */ diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 806160c44b17..171bc848e8e3 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -928,7 +928,7 @@ reset_ipi: } /* Callback function for scheduler to check locked-down task. */ -static bool trc_inspect_reader(struct task_struct *t, void *arg) +static int trc_inspect_reader(struct task_struct *t, void *arg) { int cpu = task_cpu(t); bool in_qs = false; @@ -939,7 +939,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) // If no chance of heavyweight readers, do it the hard way. if (!ofl && !IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) - return false; + return -EINVAL; // If heavyweight readers are enabled on the remote task, // we can inspect its state despite its currently running. @@ -947,7 +947,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) n_heavy_reader_attempts++; if (!ofl && // Check for "running" idle tasks on offline CPUs. !rcu_dynticks_zero_in_eqs(cpu, &t->trc_reader_nesting)) - return false; // No quiescent state, do it the hard way. + return -EINVAL; // No quiescent state, do it the hard way. n_heavy_reader_updates++; if (ofl) n_heavy_reader_ofl_updates++; @@ -962,7 +962,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) t->trc_reader_checked = true; if (in_qs) - return true; // Already in quiescent state, done!!! + return 0; // Already in quiescent state, done!!! // The task is in a read-side critical section, so set up its // state so that it will awaken the grace-period kthread upon exit @@ -970,7 +970,7 @@ static bool trc_inspect_reader(struct task_struct *t, void *arg) atomic_inc(&trc_n_readers_need_end); // One more to wait on. WARN_ON_ONCE(READ_ONCE(t->trc_reader_special.b.need_qs)); WRITE_ONCE(t->trc_reader_special.b.need_qs, true); - return true; + return 0; } /* Attempt to extract the state for the specified task. */ @@ -992,7 +992,7 @@ static void trc_wait_for_one_reader(struct task_struct *t, // Attempt to nail down the task for inspection. get_task_struct(t); - if (try_invoke_on_locked_down_task(t, trc_inspect_reader, NULL)) { + if (!task_call_func(t, trc_inspect_reader, NULL)) { put_task_struct(t); return; } diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 677ee3d8671b..5e2fa6fd97f1 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -240,16 +240,16 @@ struct rcu_stall_chk_rdr { * Report out the state of a not-running task that is stalling the * current RCU grace period. */ -static bool check_slow_task(struct task_struct *t, void *arg) +static int check_slow_task(struct task_struct *t, void *arg) { struct rcu_stall_chk_rdr *rscrp = arg; if (task_curr(t)) - return false; // It is running, so decline to inspect it. + return -EBUSY; // It is running, so decline to inspect it. rscrp->nesting = t->rcu_read_lock_nesting; rscrp->rs = t->rcu_read_unlock_special; rscrp->on_blkd_list = !list_empty(&t->rcu_node_entry); - return true; + return 0; } /* @@ -283,7 +283,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) raw_spin_unlock_irqrestore_rcu_node(rnp, flags); while (i) { t = ts[--i]; - if (!try_invoke_on_locked_down_task(t, check_slow_task, &rscr)) + if (task_call_func(t, check_slow_task, &rscr)) pr_cont(" P%d", t->pid); else pr_cont(" P%d/%d:%c%c%c%c", diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8a9aeac3469f..74db3c3afa6d 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4110,7 +4110,7 @@ out: } /** - * try_invoke_on_locked_down_task - Invoke a function on task in fixed state + * task_call_func - Invoke a function on task in fixed state * @p: Process for which the function is to be invoked, can be @current. * @func: Function to invoke. * @arg: Argument to function. @@ -4123,12 +4123,12 @@ out: * Returns: * Whatever @func returns */ -bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg) +int task_call_func(struct task_struct *p, task_call_f func, void *arg) { struct rq *rq = NULL; unsigned int state; struct rq_flags rf; - bool ret = false; + int ret; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); -- cgit v1.2.3 From e330fb14590c5c80f7195c3d8c9b4bcf79e1a5cd Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Oct 2021 18:06:54 -0700 Subject: of: net: move of_net under net/ Rob suggests to move of_net.c from under drivers/of/ somewhere to the networking code. Suggested-by: Rob Herring Signed-off-by: Jakub Kicinski Reviewed-by: Rob Herring Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/Kconfig | 2 +- drivers/net/ethernet/arc/Kconfig | 4 +- drivers/net/ethernet/ezchip/Kconfig | 2 +- drivers/net/ethernet/litex/Kconfig | 2 +- drivers/net/ethernet/mscc/Kconfig | 2 +- drivers/of/Kconfig | 4 - drivers/of/Makefile | 1 - drivers/of/of_net.c | 145 ------------------------------------ include/linux/of_net.h | 2 +- net/core/Makefile | 1 + net/core/net-sysfs.c | 2 +- net/core/of_net.c | 145 ++++++++++++++++++++++++++++++++++++ 12 files changed, 154 insertions(+), 158 deletions(-) delete mode 100644 drivers/of/of_net.c create mode 100644 net/core/of_net.c (limited to 'include/linux') diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index 4786f0504691..899c8a2a34b6 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -168,7 +168,7 @@ config SUNLANCE config AMD_XGBE tristate "AMD 10GbE Ethernet driver" - depends on ((OF_NET && OF_ADDRESS) || ACPI || PCI) && HAS_IOMEM + depends on (OF_ADDRESS || ACPI || PCI) && HAS_IOMEM depends on X86 || ARM64 || COMPILE_TEST depends on PTP_1588_CLOCK_OPTIONAL select BITREVERSE diff --git a/drivers/net/ethernet/arc/Kconfig b/drivers/net/ethernet/arc/Kconfig index 37a41773dd43..840a9ce7ba1c 100644 --- a/drivers/net/ethernet/arc/Kconfig +++ b/drivers/net/ethernet/arc/Kconfig @@ -25,7 +25,7 @@ config ARC_EMAC_CORE config ARC_EMAC tristate "ARC EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ && OF_NET + depends on OF_IRQ depends on ARC || COMPILE_TEST help On some legacy ARC (Synopsys) FPGA boards such as ARCAngel4/ML50x @@ -35,7 +35,7 @@ config ARC_EMAC config EMAC_ROCKCHIP tristate "Rockchip EMAC support" select ARC_EMAC_CORE - depends on OF_IRQ && OF_NET && REGULATOR + depends on OF_IRQ && REGULATOR depends on ARCH_ROCKCHIP || COMPILE_TEST help Support for Rockchip RK3036/RK3066/RK3188 EMAC ethernet controllers. diff --git a/drivers/net/ethernet/ezchip/Kconfig b/drivers/net/ethernet/ezchip/Kconfig index 38aa824efb25..9241b9b1c7a3 100644 --- a/drivers/net/ethernet/ezchip/Kconfig +++ b/drivers/net/ethernet/ezchip/Kconfig @@ -18,7 +18,7 @@ if NET_VENDOR_EZCHIP config EZCHIP_NPS_MANAGEMENT_ENET tristate "EZchip NPS management enet support" - depends on OF_IRQ && OF_NET + depends on OF_IRQ depends on HAS_IOMEM help Simple LAN device for debug or management purposes. diff --git a/drivers/net/ethernet/litex/Kconfig b/drivers/net/ethernet/litex/Kconfig index 63bf01d28f0c..f99adbf26ab4 100644 --- a/drivers/net/ethernet/litex/Kconfig +++ b/drivers/net/ethernet/litex/Kconfig @@ -17,7 +17,7 @@ if NET_VENDOR_LITEX config LITEX_LITEETH tristate "LiteX Ethernet support" - depends on OF_NET + depends on OF help If you wish to compile a kernel for hardware with a LiteX LiteEth device then you should answer Y to this. diff --git a/drivers/net/ethernet/mscc/Kconfig b/drivers/net/ethernet/mscc/Kconfig index b6a73d151dec..8dd8c7f425d2 100644 --- a/drivers/net/ethernet/mscc/Kconfig +++ b/drivers/net/ethernet/mscc/Kconfig @@ -28,7 +28,7 @@ config MSCC_OCELOT_SWITCH depends on BRIDGE || BRIDGE=n depends on NET_SWITCHDEV depends on HAS_IOMEM - depends on OF_NET + depends on OF select MSCC_OCELOT_SWITCH_LIB select GENERIC_PHY help diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig index 3dfeae8912df..80b5fd44ab1c 100644 --- a/drivers/of/Kconfig +++ b/drivers/of/Kconfig @@ -70,10 +70,6 @@ config OF_IRQ def_bool y depends on !SPARC && IRQ_DOMAIN -config OF_NET - depends on NETDEVICES - def_bool y - config OF_RESERVED_MEM def_bool OF_EARLY_FLATTREE diff --git a/drivers/of/Makefile b/drivers/of/Makefile index c13b982084a3..e0360a44306e 100644 --- a/drivers/of/Makefile +++ b/drivers/of/Makefile @@ -7,7 +7,6 @@ obj-$(CONFIG_OF_EARLY_FLATTREE) += fdt_address.o obj-$(CONFIG_OF_PROMTREE) += pdt.o obj-$(CONFIG_OF_ADDRESS) += address.o obj-$(CONFIG_OF_IRQ) += irq.o -obj-$(CONFIG_OF_NET) += of_net.o obj-$(CONFIG_OF_UNITTEST) += unittest.o obj-$(CONFIG_OF_RESERVED_MEM) += of_reserved_mem.o obj-$(CONFIG_OF_RESOLVE) += resolver.o diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c deleted file mode 100644 index dbac3a172a11..000000000000 --- a/drivers/of/of_net.c +++ /dev/null @@ -1,145 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * OF helpers for network devices. - * - * Initially copied out of arch/powerpc/kernel/prom_parse.c - */ -#include -#include -#include -#include -#include -#include -#include -#include - -/** - * of_get_phy_mode - Get phy mode for given device_node - * @np: Pointer to the given device_node - * @interface: Pointer to the result - * - * The function gets phy interface string from property 'phy-mode' or - * 'phy-connection-type'. The index in phy_modes table is set in - * interface and 0 returned. In case of error interface is set to - * PHY_INTERFACE_MODE_NA and an errno is returned, e.g. -ENODEV. - */ -int of_get_phy_mode(struct device_node *np, phy_interface_t *interface) -{ - const char *pm; - int err, i; - - *interface = PHY_INTERFACE_MODE_NA; - - err = of_property_read_string(np, "phy-mode", &pm); - if (err < 0) - err = of_property_read_string(np, "phy-connection-type", &pm); - if (err < 0) - return err; - - for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) - if (!strcasecmp(pm, phy_modes(i))) { - *interface = i; - return 0; - } - - return -ENODEV; -} -EXPORT_SYMBOL_GPL(of_get_phy_mode); - -static int of_get_mac_addr(struct device_node *np, const char *name, u8 *addr) -{ - struct property *pp = of_find_property(np, name, NULL); - - if (pp && pp->length == ETH_ALEN && is_valid_ether_addr(pp->value)) { - memcpy(addr, pp->value, ETH_ALEN); - return 0; - } - return -ENODEV; -} - -static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) -{ - struct platform_device *pdev = of_find_device_by_node(np); - struct nvmem_cell *cell; - const void *mac; - size_t len; - int ret; - - /* Try lookup by device first, there might be a nvmem_cell_lookup - * associated with a given device. - */ - if (pdev) { - ret = nvmem_get_mac_address(&pdev->dev, addr); - put_device(&pdev->dev); - return ret; - } - - cell = of_nvmem_cell_get(np, "mac-address"); - if (IS_ERR(cell)) - return PTR_ERR(cell); - - mac = nvmem_cell_read(cell, &len); - nvmem_cell_put(cell); - - if (IS_ERR(mac)) - return PTR_ERR(mac); - - if (len != ETH_ALEN || !is_valid_ether_addr(mac)) { - kfree(mac); - return -EINVAL; - } - - memcpy(addr, mac, ETH_ALEN); - kfree(mac); - - return 0; -} - -/** - * of_get_mac_address() - * @np: Caller's Device Node - * @addr: Pointer to a six-byte array for the result - * - * Search the device tree for the best MAC address to use. 'mac-address' is - * checked first, because that is supposed to contain to "most recent" MAC - * address. If that isn't set, then 'local-mac-address' is checked next, - * because that is the default address. If that isn't set, then the obsolete - * 'address' is checked, just in case we're using an old device tree. If any - * of the above isn't set, then try to get MAC address from nvmem cell named - * 'mac-address'. - * - * Note that the 'address' property is supposed to contain a virtual address of - * the register set, but some DTS files have redefined that property to be the - * MAC address. - * - * All-zero MAC addresses are rejected, because those could be properties that - * exist in the device tree, but were not set by U-Boot. For example, the - * DTS could define 'mac-address' and 'local-mac-address', with zero MAC - * addresses. Some older U-Boots only initialized 'local-mac-address'. In - * this case, the real MAC is in 'local-mac-address', and 'mac-address' exists - * but is all zeros. - * - * Return: 0 on success and errno in case of error. -*/ -int of_get_mac_address(struct device_node *np, u8 *addr) -{ - int ret; - - if (!np) - return -ENODEV; - - ret = of_get_mac_addr(np, "mac-address", addr); - if (!ret) - return 0; - - ret = of_get_mac_addr(np, "local-mac-address", addr); - if (!ret) - return 0; - - ret = of_get_mac_addr(np, "address", addr); - if (!ret) - return 0; - - return of_get_mac_addr_nvmem(np, addr); -} -EXPORT_SYMBOL(of_get_mac_address); diff --git a/include/linux/of_net.h b/include/linux/of_net.h index daef3b0d9270..cf31188329b5 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -8,7 +8,7 @@ #include -#ifdef CONFIG_OF_NET +#ifdef CONFIG_OF #include struct net_device; diff --git a/net/core/Makefile b/net/core/Makefile index 35ced6201814..4268846f2f47 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -36,3 +36,4 @@ obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o +obj-$(CONFIG_OF) += of_net.o diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f6197774048b..ae001c2ca2af 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1869,7 +1869,7 @@ static struct class net_class __ro_after_init = { .get_ownership = net_get_ownership, }; -#ifdef CONFIG_OF_NET +#ifdef CONFIG_OF static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { diff --git a/net/core/of_net.c b/net/core/of_net.c new file mode 100644 index 000000000000..dbac3a172a11 --- /dev/null +++ b/net/core/of_net.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * OF helpers for network devices. + * + * Initially copied out of arch/powerpc/kernel/prom_parse.c + */ +#include +#include +#include +#include +#include +#include +#include +#include + +/** + * of_get_phy_mode - Get phy mode for given device_node + * @np: Pointer to the given device_node + * @interface: Pointer to the result + * + * The function gets phy interface string from property 'phy-mode' or + * 'phy-connection-type'. The index in phy_modes table is set in + * interface and 0 returned. In case of error interface is set to + * PHY_INTERFACE_MODE_NA and an errno is returned, e.g. -ENODEV. + */ +int of_get_phy_mode(struct device_node *np, phy_interface_t *interface) +{ + const char *pm; + int err, i; + + *interface = PHY_INTERFACE_MODE_NA; + + err = of_property_read_string(np, "phy-mode", &pm); + if (err < 0) + err = of_property_read_string(np, "phy-connection-type", &pm); + if (err < 0) + return err; + + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) + if (!strcasecmp(pm, phy_modes(i))) { + *interface = i; + return 0; + } + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(of_get_phy_mode); + +static int of_get_mac_addr(struct device_node *np, const char *name, u8 *addr) +{ + struct property *pp = of_find_property(np, name, NULL); + + if (pp && pp->length == ETH_ALEN && is_valid_ether_addr(pp->value)) { + memcpy(addr, pp->value, ETH_ALEN); + return 0; + } + return -ENODEV; +} + +static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) +{ + struct platform_device *pdev = of_find_device_by_node(np); + struct nvmem_cell *cell; + const void *mac; + size_t len; + int ret; + + /* Try lookup by device first, there might be a nvmem_cell_lookup + * associated with a given device. + */ + if (pdev) { + ret = nvmem_get_mac_address(&pdev->dev, addr); + put_device(&pdev->dev); + return ret; + } + + cell = of_nvmem_cell_get(np, "mac-address"); + if (IS_ERR(cell)) + return PTR_ERR(cell); + + mac = nvmem_cell_read(cell, &len); + nvmem_cell_put(cell); + + if (IS_ERR(mac)) + return PTR_ERR(mac); + + if (len != ETH_ALEN || !is_valid_ether_addr(mac)) { + kfree(mac); + return -EINVAL; + } + + memcpy(addr, mac, ETH_ALEN); + kfree(mac); + + return 0; +} + +/** + * of_get_mac_address() + * @np: Caller's Device Node + * @addr: Pointer to a six-byte array for the result + * + * Search the device tree for the best MAC address to use. 'mac-address' is + * checked first, because that is supposed to contain to "most recent" MAC + * address. If that isn't set, then 'local-mac-address' is checked next, + * because that is the default address. If that isn't set, then the obsolete + * 'address' is checked, just in case we're using an old device tree. If any + * of the above isn't set, then try to get MAC address from nvmem cell named + * 'mac-address'. + * + * Note that the 'address' property is supposed to contain a virtual address of + * the register set, but some DTS files have redefined that property to be the + * MAC address. + * + * All-zero MAC addresses are rejected, because those could be properties that + * exist in the device tree, but were not set by U-Boot. For example, the + * DTS could define 'mac-address' and 'local-mac-address', with zero MAC + * addresses. Some older U-Boots only initialized 'local-mac-address'. In + * this case, the real MAC is in 'local-mac-address', and 'mac-address' exists + * but is all zeros. + * + * Return: 0 on success and errno in case of error. +*/ +int of_get_mac_address(struct device_node *np, u8 *addr) +{ + int ret; + + if (!np) + return -ENODEV; + + ret = of_get_mac_addr(np, "mac-address", addr); + if (!ret) + return 0; + + ret = of_get_mac_addr(np, "local-mac-address", addr); + if (!ret) + return 0; + + ret = of_get_mac_addr(np, "address", addr); + if (!ret) + return 0; + + return of_get_mac_addr_nvmem(np, addr); +} +EXPORT_SYMBOL(of_get_mac_address); -- cgit v1.2.3 From d466effe282ddbab6acb6c3120c1de0ee1b86d57 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Oct 2021 18:06:55 -0700 Subject: of: net: add a helper for loading netdev->dev_addr Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. To maintain netdev->dev_addr in this tree we need to make all the writes to it got through appropriate helpers. There are roughly 40 places where netdev->dev_addr is passed as the destination to a of_get_mac_address() call. Add a helper which takes a dev pointer instead, so it can call an appropriate helper. Note that of_get_mac_address() already assumes the address is 6 bytes long (ETH_ALEN) so use eth_hw_addr_set(). Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/of_net.h | 6 ++++++ net/core/of_net.c | 25 +++++++++++++++++++++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index cf31188329b5..0797e2edb8c2 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -14,6 +14,7 @@ struct net_device; extern int of_get_phy_mode(struct device_node *np, phy_interface_t *interface); extern int of_get_mac_address(struct device_node *np, u8 *mac); +int of_get_ethdev_address(struct device_node *np, struct net_device *dev); extern struct net_device *of_find_net_device_by_node(struct device_node *np); #else static inline int of_get_phy_mode(struct device_node *np, @@ -27,6 +28,11 @@ static inline int of_get_mac_address(struct device_node *np, u8 *mac) return -ENODEV; } +static inline int of_get_ethdev_address(struct device_node *np, struct net_device *dev) +{ + return -ENODEV; +} + static inline struct net_device *of_find_net_device_by_node(struct device_node *np) { return NULL; diff --git a/net/core/of_net.c b/net/core/of_net.c index dbac3a172a11..f1a9bf7578e7 100644 --- a/net/core/of_net.c +++ b/net/core/of_net.c @@ -143,3 +143,28 @@ int of_get_mac_address(struct device_node *np, u8 *addr) return of_get_mac_addr_nvmem(np, addr); } EXPORT_SYMBOL(of_get_mac_address); + +/** + * of_get_ethdev_address() + * @np: Caller's Device Node + * @dev: Pointer to netdevice which address will be updated + * + * Search the device tree for the best MAC address to use. + * If found set @dev->dev_addr to that address. + * + * See documentation of of_get_mac_address() for more information on how + * the best address is determined. + * + * Return: 0 on success and errno in case of error. + */ +int of_get_ethdev_address(struct device_node *np, struct net_device *dev) +{ + u8 addr[ETH_ALEN]; + int ret; + + ret = of_get_mac_address(np, addr); + if (!ret) + eth_hw_addr_set(dev, addr); + return ret; +} +EXPORT_SYMBOL(of_get_ethdev_address); -- cgit v1.2.3 From 433baf0719d6a81d0587ea27545a120a3880abf6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Oct 2021 18:06:57 -0700 Subject: device property: move mac addr helpers to eth.c Move the mac address helpers out, eth.c already contains a bunch of similar helpers. Suggested-by: Heikki Krogerus Acked-by: Greg Kroah-Hartman Signed-off-by: Jakub Kicinski Reviewed-by: Heikki Krogerus Signed-off-by: David S. Miller --- drivers/base/property.c | 63 --------------------------------------------- include/linux/etherdevice.h | 6 +++++ include/linux/property.h | 4 --- net/ethernet/eth.c | 63 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 69 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index 453918eb7390..f1f35b48ab8b 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -15,7 +15,6 @@ #include #include #include -#include #include struct fwnode_handle *dev_fwnode(struct device *dev) @@ -935,68 +934,6 @@ int device_get_phy_mode(struct device *dev) } EXPORT_SYMBOL_GPL(device_get_phy_mode); -static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode, - const char *name, char *addr, - int alen) -{ - int ret = fwnode_property_read_u8_array(fwnode, name, addr, alen); - - if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr)) - return addr; - return NULL; -} - -/** - * fwnode_get_mac_address - Get the MAC from the firmware node - * @fwnode: Pointer to the firmware node - * @addr: Address of buffer to store the MAC in - * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN - * - * Search the firmware node for the best MAC address to use. 'mac-address' is - * checked first, because that is supposed to contain to "most recent" MAC - * address. If that isn't set, then 'local-mac-address' is checked next, - * because that is the default address. If that isn't set, then the obsolete - * 'address' is checked, just in case we're using an old device tree. - * - * Note that the 'address' property is supposed to contain a virtual address of - * the register set, but some DTS files have redefined that property to be the - * MAC address. - * - * All-zero MAC addresses are rejected, because those could be properties that - * exist in the firmware tables, but were not updated by the firmware. For - * example, the DTS could define 'mac-address' and 'local-mac-address', with - * zero MAC addresses. Some older U-Boots only initialized 'local-mac-address'. - * In this case, the real MAC is in 'local-mac-address', and 'mac-address' - * exists but is all zeros. -*/ -void *fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen) -{ - char *res; - - res = fwnode_get_mac_addr(fwnode, "mac-address", addr, alen); - if (res) - return res; - - res = fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen); - if (res) - return res; - - return fwnode_get_mac_addr(fwnode, "address", addr, alen); -} -EXPORT_SYMBOL(fwnode_get_mac_address); - -/** - * device_get_mac_address - Get the MAC for a given device - * @dev: Pointer to the device - * @addr: Address of buffer to store the MAC in - * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN - */ -void *device_get_mac_address(struct device *dev, char *addr, int alen) -{ - return fwnode_get_mac_address(dev_fwnode(dev), addr, alen); -} -EXPORT_SYMBOL(device_get_mac_address); - /** * fwnode_irq_get - Get IRQ directly from a fwnode * @fwnode: Pointer to the firmware node diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e7b2e5fd8d24..39f0758274ae 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -26,9 +26,15 @@ #ifdef __KERNEL__ struct device; +struct fwnode_handle; + int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); +void *device_get_mac_address(struct device *dev, char *addr, int alen); +void *fwnode_get_mac_address(struct fwnode_handle *fwnode, + char *addr, int alen); + u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; diff --git a/include/linux/property.h b/include/linux/property.h index 357513a977e5..4fb081684255 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -389,11 +389,7 @@ const void *device_get_match_data(struct device *dev); int device_get_phy_mode(struct device *dev); -void *device_get_mac_address(struct device *dev, char *addr, int alen); - int fwnode_get_phy_mode(struct fwnode_handle *fwnode); -void *fwnode_get_mac_address(struct fwnode_handle *fwnode, - char *addr, int alen); struct fwnode_handle *fwnode_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev); struct fwnode_handle * diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index b57530c231a6..9ea45aae04ee 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include @@ -558,3 +559,65 @@ int nvmem_get_mac_address(struct device *dev, void *addrbuf) return 0; } EXPORT_SYMBOL(nvmem_get_mac_address); + +static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode, + const char *name, char *addr, + int alen) +{ + int ret = fwnode_property_read_u8_array(fwnode, name, addr, alen); + + if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr)) + return addr; + return NULL; +} + +/** + * fwnode_get_mac_address - Get the MAC from the firmware node + * @fwnode: Pointer to the firmware node + * @addr: Address of buffer to store the MAC in + * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN + * + * Search the firmware node for the best MAC address to use. 'mac-address' is + * checked first, because that is supposed to contain to "most recent" MAC + * address. If that isn't set, then 'local-mac-address' is checked next, + * because that is the default address. If that isn't set, then the obsolete + * 'address' is checked, just in case we're using an old device tree. + * + * Note that the 'address' property is supposed to contain a virtual address of + * the register set, but some DTS files have redefined that property to be the + * MAC address. + * + * All-zero MAC addresses are rejected, because those could be properties that + * exist in the firmware tables, but were not updated by the firmware. For + * example, the DTS could define 'mac-address' and 'local-mac-address', with + * zero MAC addresses. Some older U-Boots only initialized 'local-mac-address'. + * In this case, the real MAC is in 'local-mac-address', and 'mac-address' + * exists but is all zeros. + */ +void *fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen) +{ + char *res; + + res = fwnode_get_mac_addr(fwnode, "mac-address", addr, alen); + if (res) + return res; + + res = fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen); + if (res) + return res; + + return fwnode_get_mac_addr(fwnode, "address", addr, alen); +} +EXPORT_SYMBOL(fwnode_get_mac_address); + +/** + * device_get_mac_address - Get the MAC for a given device + * @dev: Pointer to the device + * @addr: Address of buffer to store the MAC in + * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN + */ +void *device_get_mac_address(struct device *dev, char *addr, int alen) +{ + return fwnode_get_mac_address(dev_fwnode(dev), addr, alen); +} +EXPORT_SYMBOL(device_get_mac_address); -- cgit v1.2.3 From 8017c4d8173cfe086420dc5710d631cabd03ef67 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Oct 2021 18:06:58 -0700 Subject: eth: fwnode: change the return type of mac address helpers fwnode_get_mac_address() and device_get_mac_address() return a pointer to the buffer that was passed to them on success or NULL on failure. None of the callers care about the actual value, only if it's NULL or not. These semantics differ from of_get_mac_address() which returns an int so to avoid confusion make the device helpers return an errno. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene-v2/main.c | 2 +- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 2 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 6 ++-- drivers/net/ethernet/faraday/ftgmac100.c | 4 +-- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- drivers/net/ethernet/microchip/enc28j60.c | 2 +- drivers/net/ethernet/qualcomm/emac/emac.c | 2 +- drivers/net/ethernet/socionext/netsec.c | 10 +++--- include/linux/etherdevice.h | 5 ++- net/ethernet/eth.c | 39 ++++++++++++----------- 12 files changed, 38 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index 80399c8980bd..c7253ecc0fa5 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -36,7 +36,7 @@ static int xge_get_resources(struct xge_pdata *pdata) return -ENOMEM; } - if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) + if (device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) eth_hw_addr_random(ndev); memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 5f1fc6582d74..268e099aa5e1 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1731,7 +1731,7 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_get_port_id_acpi(dev, pdata); #endif - if (!device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) + if (device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) eth_hw_addr_random(ndev); memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 02fe98cbabb0..30c5dcaea802 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -4084,7 +4084,7 @@ static int bcmgenet_probe(struct platform_device *pdev) if (pd && !IS_ERR_OR_NULL(pd->mac_address)) eth_hw_addr_set(dev, pd->mac_address); else - if (!device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) + if (device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) if (has_acpi_companion(&pdev->dev)) bcmgenet_get_hw_addr(priv, dev->dev_addr); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index db66d4beb28a..77ce81633cdc 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1387,10 +1387,10 @@ static int acpi_get_mac_address(struct device *dev, struct acpi_device *adev, u8 *dst) { u8 mac[ETH_ALEN]; - u8 *addr; + int ret; - addr = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac, ETH_ALEN); - if (!addr) { + ret = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac, ETH_ALEN); + if (ret) { dev_err(dev, "MAC address invalid: %pM\n", mac); return -EINVAL; } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index ab9267225573..8de9c99a18fb 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -182,10 +182,8 @@ static void ftgmac100_initial_mac(struct ftgmac100 *priv) u8 mac[ETH_ALEN]; unsigned int m; unsigned int l; - void *addr; - addr = device_get_mac_address(priv->dev, mac, ETH_ALEN); - if (addr) { + if (!device_get_mac_address(priv->dev, mac, ETH_ALEN)) { eth_hw_addr_set(priv->netdev, mac); dev_info(priv->dev, "Read MAC address %pM from device tree\n", mac); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 2c4801e49aa1..12b916399ba7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1212,7 +1212,7 @@ static void hns_init_mac_addr(struct net_device *ndev) { struct hns_nic_priv *priv = netdev_priv(ndev); - if (!device_get_mac_address(priv->dev, ndev->dev_addr, ETH_ALEN)) { + if (device_get_mac_address(priv->dev, ndev->dev_addr, ETH_ALEN)) { eth_hw_addr_random(ndev); dev_warn(priv->dev, "No valid mac, use random mac %pM", ndev->dev_addr); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 3197526455d9..b84f8b6fe9f4 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6081,7 +6081,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, char hw_mac_addr[ETH_ALEN] = {0}; char fw_mac_addr[ETH_ALEN]; - if (fwnode_get_mac_address(fwnode, fw_mac_addr, ETH_ALEN)) { + if (!fwnode_get_mac_address(fwnode, fw_mac_addr, ETH_ALEN)) { *mac_from = "firmware node"; eth_hw_addr_set(dev, fw_mac_addr); return; diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c index bf77e8adffbf..fa62311d326a 100644 --- a/drivers/net/ethernet/microchip/enc28j60.c +++ b/drivers/net/ethernet/microchip/enc28j60.c @@ -1572,7 +1572,7 @@ static int enc28j60_probe(struct spi_device *spi) goto error_irq; } - if (device_get_mac_address(&spi->dev, macaddr, sizeof(macaddr))) + if (!device_get_mac_address(&spi->dev, macaddr, sizeof(macaddr))) eth_hw_addr_set(dev, macaddr); else eth_hw_addr_random(dev); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index fbfabfc5cc51..2e913508fbeb 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -549,7 +549,7 @@ static int emac_probe_resources(struct platform_device *pdev, int ret = 0; /* get mac address */ - if (device_get_mac_address(&pdev->dev, maddr, ETH_ALEN)) + if (!device_get_mac_address(&pdev->dev, maddr, ETH_ALEN)) eth_hw_addr_set(netdev, maddr); else eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index c7e56dc0a494..f8dd7fa5f632 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1978,10 +1978,10 @@ static int netsec_register_mdio(struct netsec_priv *priv, u32 phy_addr) static int netsec_probe(struct platform_device *pdev) { struct resource *mmio_res, *eeprom_res, *irq_res; - u8 *mac, macbuf[ETH_ALEN]; struct netsec_priv *priv; u32 hw_ver, phy_addr = 0; struct net_device *ndev; + u8 macbuf[ETH_ALEN]; int ret; mmio_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -2034,12 +2034,12 @@ static int netsec_probe(struct platform_device *pdev) goto free_ndev; } - mac = device_get_mac_address(&pdev->dev, macbuf, sizeof(macbuf)); - if (mac) - eth_hw_addr_set(ndev, mac); + ret = device_get_mac_address(&pdev->dev, macbuf, sizeof(macbuf)); + if (!ret) + eth_hw_addr_set(ndev, macbuf); if (priv->eeprom_base && - (!mac || !is_valid_ether_addr(ndev->dev_addr))) { + (ret || !is_valid_ether_addr(ndev->dev_addr))) { void __iomem *macp = priv->eeprom_base + NETSEC_EEPROM_MAC_ADDRESS; diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 39f0758274ae..8299f1cd9175 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -31,9 +31,8 @@ struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); -void *device_get_mac_address(struct device *dev, char *addr, int alen); -void *fwnode_get_mac_address(struct fwnode_handle *fwnode, - char *addr, int alen); +int device_get_mac_address(struct device *dev, char *addr, int alen); +int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 9ea45aae04ee..70692f5b514c 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -560,15 +560,21 @@ int nvmem_get_mac_address(struct device *dev, void *addrbuf) } EXPORT_SYMBOL(nvmem_get_mac_address); -static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode, - const char *name, char *addr, - int alen) +static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, + const char *name, char *addr, int alen) { - int ret = fwnode_property_read_u8_array(fwnode, name, addr, alen); + int ret; - if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr)) - return addr; - return NULL; + if (alen != ETH_ALEN) + return -EINVAL; + + ret = fwnode_property_read_u8_array(fwnode, name, addr, alen); + if (ret) + return ret; + + if (!is_valid_ether_addr(addr)) + return -EINVAL; + return 0; } /** @@ -594,19 +600,14 @@ static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode, * In this case, the real MAC is in 'local-mac-address', and 'mac-address' * exists but is all zeros. */ -void *fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen) +int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen) { - char *res; - - res = fwnode_get_mac_addr(fwnode, "mac-address", addr, alen); - if (res) - return res; - - res = fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen); - if (res) - return res; + if (!fwnode_get_mac_addr(fwnode, "mac-address", addr, alen) || + !fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen) || + !fwnode_get_mac_addr(fwnode, "address", addr, alen)) + return 0; - return fwnode_get_mac_addr(fwnode, "address", addr, alen); + return -ENOENT; } EXPORT_SYMBOL(fwnode_get_mac_address); @@ -616,7 +617,7 @@ EXPORT_SYMBOL(fwnode_get_mac_address); * @addr: Address of buffer to store the MAC in * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN */ -void *device_get_mac_address(struct device *dev, char *addr, int alen) +int device_get_mac_address(struct device *dev, char *addr, int alen) { return fwnode_get_mac_address(dev_fwnode(dev), addr, alen); } -- cgit v1.2.3 From 0a14501ed818ff51eed237bbe5009d0d784e4450 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Oct 2021 18:06:59 -0700 Subject: eth: fwnode: remove the addr len from mac helpers All callers pass in ETH_ALEN and the function itself will return -EINVAL for any other address length. Just assume it's ETH_ALEN like all other mac address helpers (nvm, of, platform). Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene-v2/main.c | 2 +- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 2 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +- drivers/net/ethernet/cavium/thunder/thunder_bgx.c | 2 +- drivers/net/ethernet/faraday/ftgmac100.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_enet.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- drivers/net/ethernet/microchip/enc28j60.c | 2 +- drivers/net/ethernet/qualcomm/emac/emac.c | 2 +- drivers/net/ethernet/smsc/smsc911x.c | 2 +- drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/wireless/ath/ath10k/core.c | 2 +- include/linux/etherdevice.h | 4 ++-- net/ethernet/eth.c | 21 ++++++++------------- 14 files changed, 22 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index c7253ecc0fa5..d1ebd153b7a8 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -36,7 +36,7 @@ static int xge_get_resources(struct xge_pdata *pdata) return -ENOMEM; } - if (device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) + if (device_get_mac_address(dev, ndev->dev_addr)) eth_hw_addr_random(ndev); memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 268e099aa5e1..4a5bf13ffae2 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1731,7 +1731,7 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) xgene_get_port_id_acpi(dev, pdata); #endif - if (device_get_mac_address(dev, ndev->dev_addr, ETH_ALEN)) + if (device_get_mac_address(dev, ndev->dev_addr)) eth_hw_addr_random(ndev); memcpy(ndev->perm_addr, ndev->dev_addr, ndev->addr_len); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 30c5dcaea802..e61b687d33ba 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -4084,7 +4084,7 @@ static int bcmgenet_probe(struct platform_device *pdev) if (pd && !IS_ERR_OR_NULL(pd->mac_address)) eth_hw_addr_set(dev, pd->mac_address); else - if (device_get_mac_address(&pdev->dev, dev->dev_addr, ETH_ALEN)) + if (device_get_mac_address(&pdev->dev, dev->dev_addr)) if (has_acpi_companion(&pdev->dev)) bcmgenet_get_hw_addr(priv, dev->dev_addr); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 77ce81633cdc..574a32f23f96 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1389,7 +1389,7 @@ static int acpi_get_mac_address(struct device *dev, struct acpi_device *adev, u8 mac[ETH_ALEN]; int ret; - ret = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac, ETH_ALEN); + ret = fwnode_get_mac_address(acpi_fwnode_handle(adev), mac); if (ret) { dev_err(dev, "MAC address invalid: %pM\n", mac); return -EINVAL; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 8de9c99a18fb..86c2986395de 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -183,7 +183,7 @@ static void ftgmac100_initial_mac(struct ftgmac100 *priv) unsigned int m; unsigned int l; - if (!device_get_mac_address(priv->dev, mac, ETH_ALEN)) { + if (!device_get_mac_address(priv->dev, mac)) { eth_hw_addr_set(priv->netdev, mac); dev_info(priv->dev, "Read MAC address %pM from device tree\n", mac); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 12b916399ba7..1195f64fb161 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -1212,7 +1212,7 @@ static void hns_init_mac_addr(struct net_device *ndev) { struct hns_nic_priv *priv = netdev_priv(ndev); - if (device_get_mac_address(priv->dev, ndev->dev_addr, ETH_ALEN)) { + if (device_get_mac_address(priv->dev, ndev->dev_addr)) { eth_hw_addr_random(ndev); dev_warn(priv->dev, "No valid mac, use random mac %pM", ndev->dev_addr); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index b84f8b6fe9f4..ad3be55cce68 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6081,7 +6081,7 @@ static void mvpp2_port_copy_mac_addr(struct net_device *dev, struct mvpp2 *priv, char hw_mac_addr[ETH_ALEN] = {0}; char fw_mac_addr[ETH_ALEN]; - if (!fwnode_get_mac_address(fwnode, fw_mac_addr, ETH_ALEN)) { + if (!fwnode_get_mac_address(fwnode, fw_mac_addr)) { *mac_from = "firmware node"; eth_hw_addr_set(dev, fw_mac_addr); return; diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c index fa62311d326a..cca8aa70cfc9 100644 --- a/drivers/net/ethernet/microchip/enc28j60.c +++ b/drivers/net/ethernet/microchip/enc28j60.c @@ -1572,7 +1572,7 @@ static int enc28j60_probe(struct spi_device *spi) goto error_irq; } - if (!device_get_mac_address(&spi->dev, macaddr, sizeof(macaddr))) + if (!device_get_mac_address(&spi->dev, macaddr)) eth_hw_addr_set(dev, macaddr); else eth_hw_addr_random(dev); diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 2e913508fbeb..b1b324f45fe7 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -549,7 +549,7 @@ static int emac_probe_resources(struct platform_device *pdev, int ret = 0; /* get mac address */ - if (!device_get_mac_address(&pdev->dev, maddr, ETH_ALEN)) + if (!device_get_mac_address(&pdev->dev, maddr)) eth_hw_addr_set(netdev, maddr); else eth_hw_addr_random(netdev); diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index d47308ace075..fa387510c189 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -2375,7 +2375,7 @@ static int smsc911x_probe_config(struct smsc911x_platform_config *config, phy_interface = PHY_INTERFACE_MODE_NA; config->phy_interface = phy_interface; - device_get_mac_address(dev, config->mac, ETH_ALEN); + device_get_mac_address(dev, config->mac); err = device_property_read_u32(dev, "reg-io-width", &width); if (err == -ENXIO) diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index f8dd7fa5f632..7e3dd07ac94e 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -2034,7 +2034,7 @@ static int netsec_probe(struct platform_device *pdev) goto free_ndev; } - ret = device_get_mac_address(&pdev->dev, macbuf, sizeof(macbuf)); + ret = device_get_mac_address(&pdev->dev, macbuf); if (!ret) eth_hw_addr_set(ndev, macbuf); diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 2f9be182fbfb..c21e05549f61 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -3224,7 +3224,7 @@ static int ath10k_core_probe_fw(struct ath10k *ar) ath10k_debug_print_board_info(ar); } - device_get_mac_address(ar->dev, ar->mac_addr, sizeof(ar->mac_addr)); + device_get_mac_address(ar->dev, ar->mac_addr); ret = ath10k_core_init_firmware_features(ar); if (ret) { diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 8299f1cd9175..bb612c7382e3 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -31,8 +31,8 @@ struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); -int device_get_mac_address(struct device *dev, char *addr, int alen); -int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen); +int device_get_mac_address(struct device *dev, char *addr); +int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 70692f5b514c..29447a61d3ec 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -561,14 +561,11 @@ int nvmem_get_mac_address(struct device *dev, void *addrbuf) EXPORT_SYMBOL(nvmem_get_mac_address); static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, - const char *name, char *addr, int alen) + const char *name, char *addr) { int ret; - if (alen != ETH_ALEN) - return -EINVAL; - - ret = fwnode_property_read_u8_array(fwnode, name, addr, alen); + ret = fwnode_property_read_u8_array(fwnode, name, addr, ETH_ALEN); if (ret) return ret; @@ -581,7 +578,6 @@ static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, * fwnode_get_mac_address - Get the MAC from the firmware node * @fwnode: Pointer to the firmware node * @addr: Address of buffer to store the MAC in - * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN * * Search the firmware node for the best MAC address to use. 'mac-address' is * checked first, because that is supposed to contain to "most recent" MAC @@ -600,11 +596,11 @@ static int fwnode_get_mac_addr(struct fwnode_handle *fwnode, * In this case, the real MAC is in 'local-mac-address', and 'mac-address' * exists but is all zeros. */ -int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen) +int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr) { - if (!fwnode_get_mac_addr(fwnode, "mac-address", addr, alen) || - !fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen) || - !fwnode_get_mac_addr(fwnode, "address", addr, alen)) + if (!fwnode_get_mac_addr(fwnode, "mac-address", addr) || + !fwnode_get_mac_addr(fwnode, "local-mac-address", addr) || + !fwnode_get_mac_addr(fwnode, "address", addr)) return 0; return -ENOENT; @@ -615,10 +611,9 @@ EXPORT_SYMBOL(fwnode_get_mac_address); * device_get_mac_address - Get the MAC for a given device * @dev: Pointer to the device * @addr: Address of buffer to store the MAC in - * @alen: Length of the buffer pointed to by addr, should be ETH_ALEN */ -int device_get_mac_address(struct device *dev, char *addr, int alen) +int device_get_mac_address(struct device *dev, char *addr) { - return fwnode_get_mac_address(dev_fwnode(dev), addr, alen); + return fwnode_get_mac_address(dev_fwnode(dev), addr); } EXPORT_SYMBOL(device_get_mac_address); -- cgit v1.2.3 From d9eb44904e87c8ad1da0240849dbab638bacb799 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 6 Oct 2021 18:07:00 -0700 Subject: eth: fwnode: add a helper for loading netdev->dev_addr Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. To maintain netdev->dev_addr in this tree we need to make all the writes to it got through appropriate helpers. There is a handful of drivers which pass netdev->dev_addr as the destination buffer to device_get_mac_address(). Add a helper which takes a dev pointer instead, so it can call an appropriate helper. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 1 + include/linux/property.h | 1 + net/ethernet/eth.c | 20 ++++++++++++++++++++ 3 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index bb612c7382e3..a8bb64cf4079 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -32,6 +32,7 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); +int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); diff --git a/include/linux/property.h b/include/linux/property.h index 4fb081684255..88fa726a76df 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -15,6 +15,7 @@ #include struct device; +struct net_device; enum dev_prop_type { DEV_PROP_U8, diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 29447a61d3ec..d7b8fa10fabb 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -617,3 +617,23 @@ int device_get_mac_address(struct device *dev, char *addr) return fwnode_get_mac_address(dev_fwnode(dev), addr); } EXPORT_SYMBOL(device_get_mac_address); + +/** + * device_get_ethdev_address - Set netdev's MAC address from a given device + * @dev: Pointer to the device + * @netdev: Pointer to netdev to write the address to + * + * Wrapper around device_get_mac_address() which writes the address + * directly to netdev->dev_addr. + */ +int device_get_ethdev_address(struct device *dev, struct net_device *netdev) +{ + u8 addr[ETH_ALEN]; + int ret; + + ret = device_get_mac_address(dev, addr); + if (!ret) + eth_hw_addr_set(netdev, addr); + return ret; +} +EXPORT_SYMBOL(device_get_ethdev_address); -- cgit v1.2.3 From 5baaac3184ab896d74993825858f1b1a46c460ce Mon Sep 17 00:00:00 2001 From: Christian König Date: Tue, 15 Jun 2021 15:10:03 +0200 Subject: dma-buf: add dma_resv_for_each_fence v3 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A simpler version of the iterator to be used when the dma_resv object is locked. v2: fix index check here as well v3: minor coding improvement, some documentation cleanup Signed-off-by: Christian König Reviewed-by: Tvrtko Ursulin Link: https://patchwork.freedesktop.org/patch/msgid/20211006123609.2026-1-christian.koenig@amd.com --- drivers/dma-buf/dma-resv.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/dma-resv.h | 20 ++++++++++++++++++ 2 files changed, 71 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index a480af9581bd..2f98caa68ae5 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -423,6 +423,57 @@ struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor) } EXPORT_SYMBOL(dma_resv_iter_next_unlocked); +/** + * dma_resv_iter_first - first fence from a locked dma_resv object + * @cursor: cursor to record the current position + * + * Return the first fence in the dma_resv object while holding the + * &dma_resv.lock. + */ +struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor) +{ + struct dma_fence *fence; + + dma_resv_assert_held(cursor->obj); + + cursor->index = 0; + if (cursor->all_fences) + cursor->fences = dma_resv_shared_list(cursor->obj); + else + cursor->fences = NULL; + + fence = dma_resv_excl_fence(cursor->obj); + if (!fence) + fence = dma_resv_iter_next(cursor); + + cursor->is_restarted = true; + return fence; +} +EXPORT_SYMBOL_GPL(dma_resv_iter_first); + +/** + * dma_resv_iter_next - next fence from a locked dma_resv object + * @cursor: cursor to record the current position + * + * Return the next fences from the dma_resv object while holding the + * &dma_resv.lock. + */ +struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor) +{ + unsigned int idx; + + dma_resv_assert_held(cursor->obj); + + cursor->is_restarted = false; + if (!cursor->fences || cursor->index >= cursor->fences->shared_count) + return NULL; + + idx = cursor->index++; + return rcu_dereference_protected(cursor->fences->shared[idx], + dma_resv_held(cursor->obj)); +} +EXPORT_SYMBOL_GPL(dma_resv_iter_next); + /** * dma_resv_copy_fences - Copy all fences from src to dst. * @dst: the destination reservation object diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 764138ad8583..491359cea54c 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -179,6 +179,8 @@ struct dma_resv_iter { struct dma_fence *dma_resv_iter_first_unlocked(struct dma_resv_iter *cursor); struct dma_fence *dma_resv_iter_next_unlocked(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_first(struct dma_resv_iter *cursor); +struct dma_fence *dma_resv_iter_next(struct dma_resv_iter *cursor); /** * dma_resv_iter_begin - initialize a dma_resv_iter object @@ -244,6 +246,24 @@ static inline bool dma_resv_iter_is_restarted(struct dma_resv_iter *cursor) for (fence = dma_resv_iter_first_unlocked(cursor); \ fence; fence = dma_resv_iter_next_unlocked(cursor)) +/** + * dma_resv_for_each_fence - fence iterator + * @cursor: a struct dma_resv_iter pointer + * @obj: a dma_resv object pointer + * @all_fences: true if all fences should be returned + * @fence: the current fence + * + * Iterate over the fences in a struct dma_resv object while holding the + * &dma_resv.lock. @all_fences controls if the shared fences are returned as + * well. The cursor initialisation is part of the iterator and the fence stays + * valid as long as the lock is held and so no extra reference to the fence is + * taken. + */ +#define dma_resv_for_each_fence(cursor, obj, all_fences, fence) \ + for (dma_resv_iter_begin(cursor, obj, all_fences), \ + fence = dma_resv_iter_first(cursor); fence; \ + fence = dma_resv_iter_next(cursor)) + #define dma_resv_held(obj) lockdep_is_held(&(obj)->lock.base) #define dma_resv_assert_held(obj) lockdep_assert_held(&(obj)->lock.base) -- cgit v1.2.3 From bdc7ca008e1f5539e891187032cb2cbbc3decb5e Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 7 Oct 2021 14:14:13 +0200 Subject: spi: Remove unused function spi_busnum_to_master() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The last user is gone since commit 2962db71c703 ("staging/fbtft: Remove fbtft_device") in 2019. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20211007121415.2401638-3-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- Documentation/spi/spi-summary.rst | 8 -------- drivers/spi/spi.c | 35 ----------------------------------- include/linux/spi/spi.h | 2 -- 3 files changed, 45 deletions(-) (limited to 'include/linux') diff --git a/Documentation/spi/spi-summary.rst b/Documentation/spi/spi-summary.rst index d4239025461d..aab5d07cb3d7 100644 --- a/Documentation/spi/spi-summary.rst +++ b/Documentation/spi/spi-summary.rst @@ -336,14 +336,6 @@ certainly includes SPI devices hooked up through the card connectors! Non-static Configurations ^^^^^^^^^^^^^^^^^^^^^^^^^ -Developer boards often play by different rules than product boards, and one -example is the potential need to hotplug SPI devices and/or controllers. - -For those cases you might need to use spi_busnum_to_master() to look -up the spi bus master, and will likely need spi_new_device() to provide the -board info based on the board that was hotplugged. Of course, you'd later -call at least spi_unregister_device() when that board is removed. - When Linux includes support for MMC/SD/SDIO/DataFlash cards through SPI, those configurations will also be dynamic. Fortunately, such devices all support basic device identification probes, so they should hotplug normally. diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ff4254dc64af..cc4ac42aa93d 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -3033,41 +3033,6 @@ int spi_controller_resume(struct spi_controller *ctlr) } EXPORT_SYMBOL_GPL(spi_controller_resume); -static int __spi_controller_match(struct device *dev, const void *data) -{ - struct spi_controller *ctlr; - const u16 *bus_num = data; - - ctlr = container_of(dev, struct spi_controller, dev); - return ctlr->bus_num == *bus_num; -} - -/** - * spi_busnum_to_master - look up master associated with bus_num - * @bus_num: the master's bus number - * Context: can sleep - * - * This call may be used with devices that are registered after - * arch init time. It returns a refcounted pointer to the relevant - * spi_controller (which the caller must release), or NULL if there is - * no such master registered. - * - * Return: the SPI master structure on success, else NULL. - */ -struct spi_controller *spi_busnum_to_master(u16 bus_num) -{ - struct device *dev; - struct spi_controller *ctlr = NULL; - - dev = class_find_device(&spi_master_class, NULL, &bus_num, - __spi_controller_match); - if (dev) - ctlr = container_of(dev, struct spi_controller, dev); - /* reference got in class_find_device */ - return ctlr; -} -EXPORT_SYMBOL_GPL(spi_busnum_to_master); - /*-------------------------------------------------------------------------*/ /* Core methods for SPI resource management */ diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 8371bca13729..f8e322a46616 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -760,8 +760,6 @@ extern int devm_spi_register_controller(struct device *dev, struct spi_controller *ctlr); extern void spi_unregister_controller(struct spi_controller *ctlr); -extern struct spi_controller *spi_busnum_to_master(u16 busnum); - /* * SPI resource management while processing a SPI message */ -- cgit v1.2.3 From da21fde0fdb393c2fbe0ae0735cc826cd55fd46f Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 7 Oct 2021 14:14:15 +0200 Subject: spi: Make several public functions private to spi.c MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All these functions have no callers apart from drivers/spi/spi.c. So drop their declarations in include/linux/spi/spi.h and don't export them. Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20211007121415.2401638-5-u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown --- drivers/spi/spi.c | 41 +++++++++++++------------------------- include/linux/spi/spi.h | 53 ------------------------------------------------- 2 files changed, 14 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 397643104576..50591de16e0f 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -285,9 +285,9 @@ static const struct attribute_group *spi_master_groups[] = { NULL, }; -void spi_statistics_add_transfer_stats(struct spi_statistics *stats, - struct spi_transfer *xfer, - struct spi_controller *ctlr) +static void spi_statistics_add_transfer_stats(struct spi_statistics *stats, + struct spi_transfer *xfer, + struct spi_controller *ctlr) { unsigned long flags; int l2len = min(fls(xfer->len), SPI_STATISTICS_HISTO_SIZE) - 1; @@ -310,7 +310,6 @@ void spi_statistics_add_transfer_stats(struct spi_statistics *stats, spin_unlock_irqrestore(&stats->lock, flags); } -EXPORT_SYMBOL_GPL(spi_statistics_add_transfer_stats); /* modalias support makes "modprobe $MODALIAS" new-style hotplug work, * and the sysfs version makes coldplug work too. @@ -501,7 +500,7 @@ static DEFINE_MUTEX(spi_add_lock); * * Return: a pointer to the new device, or NULL. */ -struct spi_device *spi_alloc_device(struct spi_controller *ctlr) +static struct spi_device *spi_alloc_device(struct spi_controller *ctlr) { struct spi_device *spi; @@ -526,7 +525,6 @@ struct spi_device *spi_alloc_device(struct spi_controller *ctlr) device_initialize(&spi->dev); return spi; } -EXPORT_SYMBOL_GPL(spi_alloc_device); static void spi_dev_set_name(struct spi_device *spi) { @@ -621,7 +619,7 @@ static int __spi_add_device(struct spi_device *spi) * * Return: 0 on success; negative errno on failure */ -int spi_add_device(struct spi_device *spi) +static int spi_add_device(struct spi_device *spi) { struct spi_controller *ctlr = spi->controller; struct device *dev = ctlr->dev.parent; @@ -642,7 +640,6 @@ int spi_add_device(struct spi_device *spi) mutex_unlock(&spi_add_lock); return status; } -EXPORT_SYMBOL_GPL(spi_add_device); static int spi_add_device_locked(struct spi_device *spi) { @@ -833,9 +830,8 @@ int spi_register_board_info(struct spi_board_info const *info, unsigned n) * This may get enhanced in the future to allocate from a memory pool * of the @spi_device or @spi_controller to avoid repeated allocations. */ -void *spi_res_alloc(struct spi_device *spi, - spi_res_release_t release, - size_t size, gfp_t gfp) +static void *spi_res_alloc(struct spi_device *spi, spi_res_release_t release, + size_t size, gfp_t gfp) { struct spi_res *sres; @@ -848,14 +844,13 @@ void *spi_res_alloc(struct spi_device *spi, return sres->data; } -EXPORT_SYMBOL_GPL(spi_res_alloc); /** * spi_res_free - free an spi resource * @res: pointer to the custom data of a resource * */ -void spi_res_free(void *res) +static void spi_res_free(void *res) { struct spi_res *sres = container_of(res, struct spi_res, data); @@ -865,28 +860,26 @@ void spi_res_free(void *res) WARN_ON(!list_empty(&sres->entry)); kfree(sres); } -EXPORT_SYMBOL_GPL(spi_res_free); /** * spi_res_add - add a spi_res to the spi_message * @message: the spi message * @res: the spi_resource */ -void spi_res_add(struct spi_message *message, void *res) +static void spi_res_add(struct spi_message *message, void *res) { struct spi_res *sres = container_of(res, struct spi_res, data); WARN_ON(!list_empty(&sres->entry)); list_add_tail(&sres->entry, &message->resources); } -EXPORT_SYMBOL_GPL(spi_res_add); /** * spi_res_release - release all spi resources for this message * @ctlr: the @spi_controller * @message: the @spi_message */ -void spi_res_release(struct spi_controller *ctlr, struct spi_message *message) +static void spi_res_release(struct spi_controller *ctlr, struct spi_message *message) { struct spi_res *res, *tmp; @@ -899,7 +892,6 @@ void spi_res_release(struct spi_controller *ctlr, struct spi_message *message) kfree(res); } } -EXPORT_SYMBOL_GPL(spi_res_release); /*-------------------------------------------------------------------------*/ @@ -3157,7 +3149,7 @@ static void __spi_replace_transfers_release(struct spi_controller *ctlr, * Returns: pointer to @spi_replaced_transfers, * PTR_ERR(...) in case of errors. */ -struct spi_replaced_transfers *spi_replace_transfers( +static struct spi_replaced_transfers *spi_replace_transfers( struct spi_message *msg, struct spi_transfer *xfer_first, size_t remove, @@ -3249,7 +3241,6 @@ struct spi_replaced_transfers *spi_replace_transfers( return rxfer; } -EXPORT_SYMBOL_GPL(spi_replace_transfers); static int __spi_split_transfer_maxsize(struct spi_controller *ctlr, struct spi_message *msg, @@ -3799,7 +3790,7 @@ EXPORT_SYMBOL_GPL(spi_async); * * Return: zero on success, else a negative error code. */ -int spi_async_locked(struct spi_device *spi, struct spi_message *message) +static int spi_async_locked(struct spi_device *spi, struct spi_message *message) { struct spi_controller *ctlr = spi->controller; int ret; @@ -3818,7 +3809,6 @@ int spi_async_locked(struct spi_device *spi, struct spi_message *message) return ret; } -EXPORT_SYMBOL_GPL(spi_async_locked); /*-------------------------------------------------------------------------*/ @@ -4076,18 +4066,15 @@ EXPORT_SYMBOL_GPL(spi_write_then_read); /*-------------------------------------------------------------------------*/ -#if IS_ENABLED(CONFIG_OF) +#if IS_ENABLED(CONFIG_OF_DYNAMIC) /* must call put_device() when done with returned spi_device device */ -struct spi_device *of_find_spi_device_by_node(struct device_node *node) +static struct spi_device *of_find_spi_device_by_node(struct device_node *node) { struct device *dev = bus_find_device_by_of_node(&spi_bus_type, node); return dev ? to_spi_device(dev) : NULL; } -EXPORT_SYMBOL_GPL(of_find_spi_device_by_node); -#endif /* IS_ENABLED(CONFIG_OF) */ -#if IS_ENABLED(CONFIG_OF_DYNAMIC) /* the spi controllers are not using spi_bus, so we find it with another way */ static struct spi_controller *of_find_spi_controller_by_node(struct device_node *node) { diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index f8e322a46616..29e21d49aafc 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -78,10 +78,6 @@ struct spi_statistics { unsigned long transfers_split_maxsize; }; -void spi_statistics_add_transfer_stats(struct spi_statistics *stats, - struct spi_transfer *xfer, - struct spi_controller *ctlr); - #define SPI_STATISTICS_ADD_TO_FIELD(stats, field, count) \ do { \ unsigned long flags; \ @@ -783,15 +779,6 @@ struct spi_res { unsigned long long data[]; /* guarantee ull alignment */ }; -extern void *spi_res_alloc(struct spi_device *spi, - spi_res_release_t release, - size_t size, gfp_t gfp); -extern void spi_res_add(struct spi_message *message, void *res); -extern void spi_res_free(void *res); - -extern void spi_res_release(struct spi_controller *ctlr, - struct spi_message *message); - /*---------------------------------------------------------------------------*/ /* @@ -1109,8 +1096,6 @@ static inline void spi_message_free(struct spi_message *m) extern int spi_setup(struct spi_device *spi); extern int spi_async(struct spi_device *spi, struct spi_message *message); -extern int spi_async_locked(struct spi_device *spi, - struct spi_message *message); extern int spi_slave_abort(struct spi_device *spi); static inline size_t @@ -1193,15 +1178,6 @@ struct spi_replaced_transfers { struct spi_transfer inserted_transfers[]; }; -extern struct spi_replaced_transfers *spi_replace_transfers( - struct spi_message *msg, - struct spi_transfer *xfer_first, - size_t remove, - size_t insert, - spi_replaced_release_t release, - size_t extradatasize, - gfp_t gfp); - /*---------------------------------------------------------------------------*/ /* SPI transfer transformation methods */ @@ -1473,19 +1449,7 @@ spi_register_board_info(struct spi_board_info const *info, unsigned n) * use spi_new_device() to describe each device. You can also call * spi_unregister_device() to start making that device vanish, but * normally that would be handled by spi_unregister_controller(). - * - * You can also use spi_alloc_device() and spi_add_device() to use a two - * stage registration sequence for each spi_device. This gives the caller - * some more control over the spi_device structure before it is registered, - * but requires that caller to initialize fields that would otherwise - * be defined using the board info. */ -extern struct spi_device * -spi_alloc_device(struct spi_controller *ctlr); - -extern int -spi_add_device(struct spi_device *spi); - extern struct spi_device * spi_new_device(struct spi_controller *, struct spi_board_info *); @@ -1500,23 +1464,6 @@ spi_transfer_is_last(struct spi_controller *ctlr, struct spi_transfer *xfer) return list_is_last(&xfer->transfer_list, &ctlr->cur_msg->transfers); } -/* OF support code */ -#if IS_ENABLED(CONFIG_OF) - -/* must call put_device() when done with returned spi_device device */ -extern struct spi_device * -of_find_spi_device_by_node(struct device_node *node); - -#else - -static inline struct spi_device * -of_find_spi_device_by_node(struct device_node *node) -{ - return NULL; -} - -#endif /* IS_ENABLED(CONFIG_OF) */ - /* Compatibility layer */ #define spi_master spi_controller -- cgit v1.2.3 From ba882580f211dbe4fee7f010c9d38dd879db83a6 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 7 Oct 2021 11:18:46 -0700 Subject: eth: platform: add a helper for loading netdev->dev_addr Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. To maintain netdev->dev_addr in this tree we need to make all the writes to it got through appropriate helpers. There is a handful of drivers which pass netdev->dev_addr as the destination buffer to eth_platform_get_mac_address(). Add a helper which takes a dev pointer instead, so it can call an appropriate helper. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 1 + net/ethernet/eth.c | 20 ++++++++++++++++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e75116f48cd1..3cf546d2ffd1 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -29,6 +29,7 @@ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); +int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 182de70ac258..c7d9e08107cb 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -523,6 +523,26 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr) } EXPORT_SYMBOL(eth_platform_get_mac_address); +/** + * platform_get_ethdev_address - Set netdev's MAC address from a given device + * @dev: Pointer to the device + * @netdev: Pointer to netdev to write the address to + * + * Wrapper around eth_platform_get_mac_address() which writes the address + * directly to netdev->dev_addr. + */ +int platform_get_ethdev_address(struct device *dev, struct net_device *netdev) +{ + u8 addr[ETH_ALEN] __aligned(2); + int ret; + + ret = eth_platform_get_mac_address(dev, addr); + if (!ret) + eth_hw_addr_set(netdev, addr); + return ret; +} +EXPORT_SYMBOL(platform_get_ethdev_address); + /** * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named * 'mac-address' associated with given device. -- cgit v1.2.3 From 75ea27d0d62281c31ee259c872dfdeb072cf5e39 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Thu, 7 Oct 2021 18:16:50 +0200 Subject: net: introduce a function to check if a netdev name is in use __dev_get_by_name is currently used to either retrieve a net device reference using its name or to check if a name is already used by a registered net device (per ns). In the later case there is no need to return a reference to a net device. Introduce a new helper, netdev_name_in_use, to check if a name is currently used by a registered net device without leaking a reference the corresponding net device. This helper uses netdev_name_node_lookup instead of __dev_get_by_name as we don't need the extra logic retrieving a reference to the corresponding net device. Signed-off-by: Antoine Tenart Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/dev.c | 14 ++++++++++---- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d79163208dfd..15f4a658e436 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2955,6 +2955,7 @@ struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); +bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); diff --git a/net/core/dev.c b/net/core/dev.c index 16ab09b6a7f8..1594cd2955ba 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -303,6 +303,12 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +bool netdev_name_in_use(struct net *net, const char *name) +{ + return netdev_name_node_lookup(net, name); +} +EXPORT_SYMBOL(netdev_name_in_use); + int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; @@ -1133,7 +1139,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } snprintf(buf, IFNAMSIZ, name, i); - if (!__dev_get_by_name(net, buf)) + if (!netdev_name_in_use(net, buf)) return i; /* It is possible to run out of possible slots @@ -1187,7 +1193,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, if (strchr(name, '%')) return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) + else if (netdev_name_in_use(net, name)) return -EEXIST; else if (dev->name != name) strlcpy(dev->name, name, IFNAMSIZ); @@ -11153,7 +11159,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * we can use it in the destination network namespace. */ err = -EEXIST; - if (__dev_get_by_name(net, dev->name)) { + if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; @@ -11506,7 +11512,7 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); - if (__dev_get_by_name(&init_net, fb_name)) + if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { -- cgit v1.2.3 From 0258b5fd7c7124b87e185a1a9322d2c66b1876b7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 22 Sep 2021 11:24:02 -0500 Subject: coredump: Limit coredumps to a single thread group Today when a signal is delivered with a handler of SIG_DFL whose default behavior is to generate a core dump not only that process but every process that shares the mm is killed. In the case of vfork this looks like a real world problem. Consider the following well defined sequence. if (vfork() == 0) { execve(...); _exit(EXIT_FAILURE); } If a signal that generates a core dump is received after vfork but before the execve changes the mm the process that called vfork will also be killed (as the mm is shared). Similarly if the execve fails after the point of no return the kernel delivers SIGSEGV which will kill both the exec'ing process and because the mm is shared the process that called vfork as well. As far as I can tell this behavior is a violation of people's reasonable expectations, POSIX, and is unnecessarily fragile when the system is low on memory. Solve this by making a userspace visible change to only kill a single process/thread group. This is possible because Jann Horn recently modified[1] the coredump code so that the mm can safely be modified while the coredump is happening. With LinuxThreads long gone I don't expect anyone to have a notice this behavior change in practice. To accomplish this move the core_state pointer from mm_struct to signal_struct, which allows different thread groups to coredump simultatenously. In zap_threads remove the work to kill anything except for the current thread group. v2: Remove core_state from the VM_BUG_ON_MM print to fix compile failure when CONFIG_DEBUG_VM is enabled. Reported-by: Stephen Rothwell [1] a07279c9a8cd ("binfmt_elf, binfmt_elf_fdpic: use a VMA list snapshot") Fixes: d89f3847def4 ("[PATCH] thread-aware coredumps, 2.5.43-C3") History-tree: git://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.git Link: https://lkml.kernel.org/r/87y27mvnke.fsf@disp2133 Link: https://lkml.kernel.org/r/20211007144701.67592574@canb.auug.org.au Reviewed-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- fs/binfmt_elf.c | 4 +-- fs/binfmt_elf_fdpic.c | 2 +- fs/coredump.c | 84 +++++--------------------------------------- fs/proc/array.c | 6 ++-- include/linux/mm_types.h | 13 ------- include/linux/sched/signal.h | 13 +++++++ kernel/exit.c | 13 +++---- kernel/fork.c | 1 - mm/debug.c | 4 +-- 9 files changed, 34 insertions(+), 106 deletions(-) (limited to 'include/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 69d900a8473d..796e5327ee7d 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1834,7 +1834,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, /* * Allocate a structure for each thread. */ - for (ct = &dump_task->mm->core_state->dumper; ct; ct = ct->next) { + for (ct = &dump_task->signal->core_state->dumper; ct; ct = ct->next) { t = kzalloc(offsetof(struct elf_thread_core_info, notes[info->thread_notes]), GFP_KERNEL); @@ -2024,7 +2024,7 @@ static int fill_note_info(struct elfhdr *elf, int phdrs, if (!elf_note_info_init(info)) return 0; - for (ct = current->mm->core_state->dumper.next; + for (ct = current->signal->core_state->dumper.next; ct; ct = ct->next) { ets = kzalloc(sizeof(*ets), GFP_KERNEL); if (!ets) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 6d8fd6030cbb..c6f588dc4a9d 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1494,7 +1494,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) if (dump_vma_snapshot(cprm, &vma_count, &vma_meta, &vma_data_size)) goto end_coredump; - for (ct = current->mm->core_state->dumper.next; + for (ct = current->signal->core_state->dumper.next; ct; ct = ct->next) { tmp = elf_dump_thread_status(cprm->siginfo->si_signo, ct->task, &thread_status_size); diff --git a/fs/coredump.c b/fs/coredump.c index d576287fb88b..a6b3c196cdef 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -369,99 +369,34 @@ static int zap_process(struct task_struct *start, int exit_code, int flags) return nr; } -static int zap_threads(struct task_struct *tsk, struct mm_struct *mm, +static int zap_threads(struct task_struct *tsk, struct core_state *core_state, int exit_code) { - struct task_struct *g, *p; - unsigned long flags; int nr = -EAGAIN; spin_lock_irq(&tsk->sighand->siglock); if (!signal_group_exit(tsk->signal)) { - mm->core_state = core_state; + tsk->signal->core_state = core_state; tsk->signal->group_exit_task = tsk; nr = zap_process(tsk, exit_code, 0); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); + tsk->flags |= PF_DUMPCORE; + atomic_set(&core_state->nr_threads, nr); } spin_unlock_irq(&tsk->sighand->siglock); - if (unlikely(nr < 0)) - return nr; - - tsk->flags |= PF_DUMPCORE; - if (atomic_read(&mm->mm_users) == nr + 1) - goto done; - /* - * We should find and kill all tasks which use this mm, and we should - * count them correctly into ->nr_threads. We don't take tasklist - * lock, but this is safe wrt: - * - * fork: - * None of sub-threads can fork after zap_process(leader). All - * processes which were created before this point should be - * visible to zap_threads() because copy_process() adds the new - * process to the tail of init_task.tasks list, and lock/unlock - * of ->siglock provides a memory barrier. - * - * do_exit: - * The caller holds mm->mmap_lock. This means that the task which - * uses this mm can't pass coredump_task_exit(), so it can't exit - * or clear its ->mm. - * - * de_thread: - * It does list_replace_rcu(&leader->tasks, ¤t->tasks), - * we must see either old or new leader, this does not matter. - * However, it can change p->sighand, so lock_task_sighand(p) - * must be used. Since p->mm != NULL and we hold ->mmap_lock - * it can't fail. - * - * Note also that "g" can be the old leader with ->mm == NULL - * and already unhashed and thus removed from ->thread_group. - * This is OK, __unhash_process()->list_del_rcu() does not - * clear the ->next pointer, we will find the new leader via - * next_thread(). - */ - rcu_read_lock(); - for_each_process(g) { - if (g == tsk->group_leader) - continue; - if (g->flags & PF_KTHREAD) - continue; - - for_each_thread(g, p) { - if (unlikely(!p->mm)) - continue; - if (unlikely(p->mm == mm)) { - lock_task_sighand(p, &flags); - nr += zap_process(p, exit_code, - SIGNAL_GROUP_EXIT); - unlock_task_sighand(p, &flags); - } - break; - } - } - rcu_read_unlock(); -done: - atomic_set(&core_state->nr_threads, nr); return nr; } static int coredump_wait(int exit_code, struct core_state *core_state) { struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; int core_waiters = -EBUSY; init_completion(&core_state->startup); core_state->dumper.task = tsk; core_state->dumper.next = NULL; - if (mmap_write_lock_killable(mm)) - return -EINTR; - - if (!mm->core_state) - core_waiters = zap_threads(tsk, mm, core_state, exit_code); - mmap_write_unlock(mm); - + core_waiters = zap_threads(tsk, core_state, exit_code); if (core_waiters > 0) { struct core_thread *ptr; @@ -483,7 +418,7 @@ static int coredump_wait(int exit_code, struct core_state *core_state) return core_waiters; } -static void coredump_finish(struct mm_struct *mm, bool core_dumped) +static void coredump_finish(bool core_dumped) { struct core_thread *curr, *next; struct task_struct *task; @@ -493,9 +428,10 @@ static void coredump_finish(struct mm_struct *mm, bool core_dumped) current->signal->group_exit_code |= 0x80; current->signal->group_exit_task = NULL; current->signal->flags = SIGNAL_GROUP_EXIT; + next = current->signal->core_state->dumper.next; + current->signal->core_state = NULL; spin_unlock_irq(¤t->sighand->siglock); - next = mm->core_state->dumper.next; while ((curr = next) != NULL) { next = curr->next; task = curr->task; @@ -507,8 +443,6 @@ static void coredump_finish(struct mm_struct *mm, bool core_dumped) curr->task = NULL; wake_up_process(task); } - - mm->core_state = NULL; } static bool dump_interrupted(void) @@ -839,7 +773,7 @@ fail_dropcount: fail_unlock: kfree(argv); kfree(cn.corename); - coredump_finish(mm, core_dumped); + coredump_finish(core_dumped); revert_creds(old_cred); fail_creds: put_cred(cred); diff --git a/fs/proc/array.c b/fs/proc/array.c index 49be8c8ef555..520c51be1e57 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -408,9 +408,9 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) cpumask_pr_args(&task->cpus_mask)); } -static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) +static inline void task_core_dumping(struct seq_file *m, struct task_struct *task) { - seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state); + seq_put_decimal_ull(m, "CoreDumping:\t", !!task->signal->core_state); seq_putc(m, '\n'); } @@ -436,7 +436,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns, if (mm) { task_mem(m, mm); - task_core_dumping(m, mm); + task_core_dumping(m, task); task_thp_status(m, mm); mmput(mm); } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..1039f6ae922c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -387,17 +387,6 @@ struct vm_area_struct { struct vm_userfaultfd_ctx vm_userfaultfd_ctx; } __randomize_layout; -struct core_thread { - struct task_struct *task; - struct core_thread *next; -}; - -struct core_state { - atomic_t nr_threads; - struct core_thread dumper; - struct completion startup; -}; - struct kioctx_table; struct mm_struct { struct { @@ -518,8 +507,6 @@ struct mm_struct { unsigned long flags; /* Must use atomic bitops to access */ - struct core_state *core_state; /* coredumping support */ - #ifdef CONFIG_AIO spinlock_t ioctx_lock; struct kioctx_table __rcu *ioctx_table; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e5f4ce622ee6..a8fe2a593a3a 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -72,6 +72,17 @@ struct multiprocess_signals { struct hlist_node node; }; +struct core_thread { + struct task_struct *task; + struct core_thread *next; +}; + +struct core_state { + atomic_t nr_threads; + struct core_thread dumper; + struct completion startup; +}; + /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always @@ -110,6 +121,8 @@ struct signal_struct { int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ + struct core_state *core_state; /* coredumping support */ + /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes diff --git a/kernel/exit.c b/kernel/exit.c index 774e6b5061b8..2b355e926c13 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -342,23 +342,18 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) static void coredump_task_exit(struct task_struct *tsk) { struct core_state *core_state; - struct mm_struct *mm; - - mm = tsk->mm; - if (!mm) - return; /* * Serialize with any possible pending coredump. - * We must hold mmap_lock around checking core_state + * We must hold siglock around checking core_state * and setting PF_POSTCOREDUMP. The core-inducing thread * will increment ->nr_threads for each thread in the * group without PF_POSTCOREDUMP set. */ - mmap_read_lock(mm); + spin_lock_irq(&tsk->sighand->siglock); tsk->flags |= PF_POSTCOREDUMP; - core_state = mm->core_state; - mmap_read_unlock(mm); + core_state = tsk->signal->core_state; + spin_unlock_irq(&tsk->sighand->siglock); if (core_state) { struct core_thread self; diff --git a/kernel/fork.c b/kernel/fork.c index 9bd9f2da9e41..c8adb76982f7 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1044,7 +1044,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); - mm->core_state = NULL; mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; diff --git a/mm/debug.c b/mm/debug.c index e73fe0a8ec3d..aa5fe4d5c4b4 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -214,7 +214,7 @@ void dump_mm(const struct mm_struct *mm) "start_code %lx end_code %lx start_data %lx end_data %lx\n" "start_brk %lx brk %lx start_stack %lx\n" "arg_start %lx arg_end %lx env_start %lx env_end %lx\n" - "binfmt %px flags %lx core_state %px\n" + "binfmt %px flags %lx\n" #ifdef CONFIG_AIO "ioctx_table %px\n" #endif @@ -246,7 +246,7 @@ void dump_mm(const struct mm_struct *mm) mm->start_code, mm->end_code, mm->start_data, mm->end_data, mm->start_brk, mm->brk, mm->start_stack, mm->arg_start, mm->arg_end, mm->env_start, mm->env_end, - mm->binfmt, mm->flags, mm->core_state, + mm->binfmt, mm->flags, #ifdef CONFIG_AIO mm->ioctx_table, #endif -- cgit v1.2.3 From 8208461d3912e3e97e31bcbd4ce716e4a251a5dd Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Fri, 8 Oct 2021 15:24:27 +0300 Subject: net/mlx5: Add ifc bits to support optional counters Adding bth_opcode field and the relevant bits. This field will be used to capture and count congestion notification packets (CNP). Adding source_vhca_port support bit. This field will be used to check the capability to use the source_vhca_port as a match criteria in cases of dual port. Signed-off-by: Aharon Landau Reviewed-by: Maor Gottlieb Signed-off-by: Mark Zhang Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 96f5fb2af811..34254dbe7117 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -342,7 +342,7 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_geneve_oam[0x1]; u8 outer_geneve_protocol_type[0x1]; u8 outer_geneve_opt_len[0x1]; - u8 reserved_at_1e[0x1]; + u8 source_vhca_port[0x1]; u8 source_eswitch_port[0x1]; u8 inner_dmac[0x1]; @@ -393,6 +393,14 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 metadata_reg_c_0[0x1]; }; +struct mlx5_ifc_flow_table_fields_supported_2_bits { + u8 reserved_at_0[0xe]; + u8 bth_opcode[0x1]; + u8 reserved_at_f[0x11]; + + u8 reserved_at_20[0x60]; +}; + struct mlx5_ifc_flow_table_prop_layout_bits { u8 ft_support[0x1]; u8 reserved_at_1[0x1]; @@ -539,7 +547,7 @@ struct mlx5_ifc_fte_match_set_misc_bits { union mlx5_ifc_gre_key_bits gre_key; u8 vxlan_vni[0x18]; - u8 reserved_at_b8[0x8]; + u8 bth_opcode[0x8]; u8 geneve_vni[0x18]; u8 reserved_at_d8[0x7]; @@ -756,7 +764,15 @@ struct mlx5_ifc_flow_table_nic_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_at_e00[0x1200]; + u8 reserved_at_e00[0x700]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma; + + u8 reserved_at_1580[0x280]; + + struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_transmit_rdma; + + u8 reserved_at_1880[0x780]; u8 sw_steering_nic_rx_action_drop_icm_address[0x40]; -- cgit v1.2.3 From b8dfed636fc6239396c3a2ae5f812505906cf215 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Fri, 8 Oct 2021 15:24:28 +0300 Subject: net/mlx5: Add priorities for counters in RDMA namespaces Add additional flow steering priorities in the RDMA namespace. This allows adding flow counters to count filtered RDMA traffic and then continue processing in the regular RDMA steering flow. Signed-off-by: Aharon Landau Reviewed-by: Maor Gottlieb Signed-off-by: Mark Zhang Signed-off-by: Leon Romanovsky --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 54 +++++++++++++++++++---- include/linux/mlx5/device.h | 2 + include/linux/mlx5/fs.h | 2 + 3 files changed, 50 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fe501ba88bea..71a08f84d49d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -99,6 +99,9 @@ #define LEFTOVERS_NUM_LEVELS 1 #define LEFTOVERS_NUM_PRIOS 1 +#define RDMA_RX_COUNTERS_PRIO_NUM_LEVELS 1 +#define RDMA_TX_COUNTERS_PRIO_NUM_LEVELS 1 + #define BY_PASS_PRIO_NUM_LEVELS 1 #define BY_PASS_MIN_LEVEL (ETHTOOL_MIN_LEVEL + MLX5_BY_PASS_NUM_PRIOS +\ LEFTOVERS_NUM_PRIOS) @@ -206,34 +209,63 @@ static struct init_tree_node egress_root_fs = { } }; -#define RDMA_RX_BYPASS_PRIO 0 -#define RDMA_RX_KERNEL_PRIO 1 +enum { + RDMA_RX_COUNTERS_PRIO, + RDMA_RX_BYPASS_PRIO, + RDMA_RX_KERNEL_PRIO, +}; + +#define RDMA_RX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_REGULAR_PRIOS +#define RDMA_RX_KERNEL_MIN_LEVEL (RDMA_RX_BYPASS_MIN_LEVEL + 1) +#define RDMA_RX_COUNTERS_MIN_LEVEL (RDMA_RX_KERNEL_MIN_LEVEL + 2) + static struct init_tree_node rdma_rx_root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 2, + .ar_size = 3, .children = (struct init_tree_node[]) { + [RDMA_RX_COUNTERS_PRIO] = + ADD_PRIO(0, RDMA_RX_COUNTERS_MIN_LEVEL, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_RDMA_RX_NUM_COUNTERS_PRIOS, + RDMA_RX_COUNTERS_PRIO_NUM_LEVELS))), [RDMA_RX_BYPASS_PRIO] = - ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS, 0, + ADD_PRIO(0, RDMA_RX_BYPASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_REGULAR_PRIOS, BY_PASS_PRIO_NUM_LEVELS))), [RDMA_RX_KERNEL_PRIO] = - ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS + 1, 0, + ADD_PRIO(0, RDMA_RX_KERNEL_MIN_LEVEL, 0, FS_CHAINING_CAPS, ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN, ADD_MULTIPLE_PRIO(1, 1))), } }; +enum { + RDMA_TX_COUNTERS_PRIO, + RDMA_TX_BYPASS_PRIO, +}; + +#define RDMA_TX_BYPASS_MIN_LEVEL MLX5_BY_PASS_NUM_PRIOS +#define RDMA_TX_COUNTERS_MIN_LEVEL (RDMA_TX_BYPASS_MIN_LEVEL + 1) + static struct init_tree_node rdma_tx_root_fs = { .type = FS_TYPE_NAMESPACE, - .ar_size = 1, + .ar_size = 2, .children = (struct init_tree_node[]) { - ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0, + [RDMA_TX_COUNTERS_PRIO] = + ADD_PRIO(0, RDMA_TX_COUNTERS_MIN_LEVEL, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_RDMA_TX_NUM_COUNTERS_PRIOS, + RDMA_TX_COUNTERS_PRIO_NUM_LEVELS))), + [RDMA_TX_BYPASS_PRIO] = + ADD_PRIO(0, RDMA_TX_BYPASS_MIN_LEVEL, 0, FS_CHAINING_CAPS_RDMA_TX, ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, - ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + ADD_MULTIPLE_PRIO(RDMA_TX_BYPASS_MIN_LEVEL, BY_PASS_PRIO_NUM_LEVELS))), } }; @@ -2215,6 +2247,12 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, prio = RDMA_RX_KERNEL_PRIO; } else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX) { root_ns = steering->rdma_tx_root_ns; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_COUNTERS_PRIO; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS) { + root_ns = steering->rdma_tx_root_ns; + prio = RDMA_TX_COUNTERS_PRIO; } else { /* Must be NIC RX */ root_ns = steering->root_ns; prio = type; diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 66eaf0aa7f69..ed0230ff9422 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1456,6 +1456,8 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz) return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz; } +#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 2 +#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 1 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1 diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0106c67e8ccb..f2c3da2006d9 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -83,6 +83,8 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_RX, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_TX, + MLX5_FLOW_NAMESPACE_RDMA_RX_COUNTERS, + MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS, }; enum { -- cgit v1.2.3 From 0392dd51f9c78d46109a408f27dc820300dcd8bd Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 4 Oct 2021 10:10:10 -0400 Subject: SUNRPC: Per-rpc_clnt task PIDs The current range of RPC task PIDs is 0..65535. That's not adequate for distinguishing tasks across multiple rpc_clnts running high throughput workloads. To help relieve this situation and to reduce the bottleneck of having a single atomic for assigning all RPC task PIDs, assign task PIDs per rpc_clnt. Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- include/linux/sunrpc/clnt.h | 1 + net/sunrpc/sched.c | 12 ++++++++++-- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index a4661646adc9..267b7aeaf1a6 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -40,6 +40,7 @@ struct rpc_clnt { unsigned int cl_clid; /* client id */ struct list_head cl_clients; /* Global list of clients */ struct list_head cl_tasks; /* List of tasks */ + atomic_t cl_pid; /* task PID counter */ spinlock_t cl_lock; /* spinlock */ struct rpc_xprt __rcu * cl_xprt; /* transport */ const struct rpc_procinfo *cl_procinfo; /* procedure info */ diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index b21457cec8a5..f4f311ea7a66 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -277,9 +277,17 @@ static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) || IS_ENABLED(CONFIG_TRACEPOINTS) static void rpc_task_set_debuginfo(struct rpc_task *task) { - static atomic_t rpc_pid; + struct rpc_clnt *clnt = task->tk_client; - task->tk_pid = atomic_inc_return(&rpc_pid); + /* Might be a task carrying a reverse-direction operation */ + if (!clnt) { + static atomic_t rpc_pid; + + task->tk_pid = atomic_inc_return(&rpc_pid); + return; + } + + task->tk_pid = atomic_inc_return(&clnt->cl_pid); } #else static inline void rpc_task_set_debuginfo(struct rpc_task *task) -- cgit v1.2.3 From 0199215216978b612d4e8be11e878b87bc643033 Mon Sep 17 00:00:00 2001 From: Juhee Kang Date: Sun, 10 Oct 2021 13:03:29 +0900 Subject: mlxsw: spectrum: use netif_is_macsec() instead of open code Open code which is dev->priv_flags & IFF_MACSEC has already defined as netif_is_macsec(). So use netif_is_macsec() instead of open code. This patch doesn't change logic. Signed-off-by: Juhee Kang Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 15f4a658e436..0723c1314ea2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5237,7 +5237,7 @@ static inline void netif_keep_dst(struct net_device *dev) static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ - return dev->priv_flags & IFF_MACSEC; + return netif_is_macsec(dev); } extern struct pernet_operations __net_initdata loopback_net_ops; -- cgit v1.2.3 From bdac5c2b243f68ec15f8203c3348ae79fee8e8d8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 16 Sep 2021 15:23:20 +0900 Subject: bootconfig: Allocate xbc_data inside xbc_init() Allocate 'xbc_data' in the xbc_init() so that it does not need to care about the ownership of the copied data. Link: https://lkml.kernel.org/r/163177339986.682366.898762699429769117.stgit@devnote2 Suggested-by: Steven Rostedt Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 2 +- init/main.c | 13 ++----------- lib/bootconfig.c | 33 +++++++++++++++++++++------------ tools/bootconfig/main.c | 6 +++--- 4 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 537e1b991f11..62e09b788172 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -271,7 +271,7 @@ static inline int __init xbc_node_compose_key(struct xbc_node *node, } /* XBC node initializer */ -int __init xbc_init(char *buf, const char **emsg, int *epos); +int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); /* XBC cleanup data structures */ diff --git a/init/main.c b/init/main.c index 81a79a77db46..d894989d86bc 100644 --- a/init/main.c +++ b/init/main.c @@ -409,7 +409,7 @@ static void __init setup_boot_config(void) const char *msg; int pos; u32 size, csum; - char *data, *copy, *err; + char *data, *err; int ret; /* Cut out the bootconfig data even if we have no bootconfig option */ @@ -442,16 +442,7 @@ static void __init setup_boot_config(void) return; } - copy = memblock_alloc(size + 1, SMP_CACHE_BYTES); - if (!copy) { - pr_err("Failed to allocate memory for bootconfig\n"); - return; - } - - memcpy(copy, data, size); - copy[size] = '\0'; - - ret = xbc_init(copy, &msg, &pos); + ret = xbc_init(data, size, &msg, &pos); if (ret < 0) { if (pos < 0) pr_err("Failed to init bootconfig: %s.\n", msg); diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 5ae248b29373..66b02fddfea8 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -789,6 +789,7 @@ static int __init xbc_verify_tree(void) */ void __init xbc_destroy_all(void) { + memblock_free_ptr(xbc_data, xbc_data_size); xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; @@ -799,19 +800,20 @@ void __init xbc_destroy_all(void) /** * xbc_init() - Parse given XBC file and build XBC internal tree - * @buf: boot config text + * @data: The boot config text original data + * @size: The size of @data * @emsg: A pointer of const char * to store the error message * @epos: A pointer of int to store the error position * - * This parses the boot config text in @buf. @buf must be a - * null terminated string and smaller than XBC_DATA_MAX. + * This parses the boot config text in @data. @size must be smaller + * than XBC_DATA_MAX. * Return the number of stored nodes (>0) if succeeded, or -errno * if there is any error. * In error cases, @emsg will be updated with an error message and * @epos will be updated with the error position which is the byte offset * of @buf. If the error is not a parser error, @epos will be -1. */ -int __init xbc_init(char *buf, const char **emsg, int *epos) +int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) { char *p, *q; int ret, c; @@ -824,28 +826,35 @@ int __init xbc_init(char *buf, const char **emsg, int *epos) *emsg = "Bootconfig is already initialized"; return -EBUSY; } - - ret = strlen(buf); - if (ret > XBC_DATA_MAX - 1 || ret == 0) { + if (size > XBC_DATA_MAX || size == 0) { if (emsg) - *emsg = ret ? "Config data is too big" : + *emsg = size ? "Config data is too big" : "Config data is empty"; return -ERANGE; } + xbc_data = memblock_alloc(size + 1, SMP_CACHE_BYTES); + if (!xbc_data) { + if (emsg) + *emsg = "Failed to allocate bootconfig data"; + return -ENOMEM; + } + memcpy(xbc_data, data, size); + xbc_data[size] = '\0'; + xbc_data_size = size + 1; + xbc_nodes = memblock_alloc(sizeof(struct xbc_node) * XBC_NODE_MAX, SMP_CACHE_BYTES); if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; + xbc_destroy_all(); return -ENOMEM; } memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); - xbc_data = buf; - xbc_data_size = ret + 1; - last_parent = NULL; - p = buf; + last_parent = NULL; + p = xbc_data; do { q = strpbrk(p, "{}=+;:\n#"); if (!q) { diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index fd67496a947f..7269c9e35335 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -229,7 +229,7 @@ static int load_xbc_from_initrd(int fd, char **buf) return -EINVAL; } - ret = xbc_init(*buf, &msg, NULL); + ret = xbc_init(*buf, size, &msg, NULL); /* Wrong data */ if (ret < 0) { pr_err("parse error: %s.\n", msg); @@ -269,7 +269,7 @@ static int init_xbc_with_error(char *buf, int len) if (!copy) return -ENOMEM; - ret = xbc_init(buf, &msg, &pos); + ret = xbc_init(buf, len, &msg, &pos); if (ret < 0) show_xbc_error(copy, msg, pos); free(copy); @@ -382,7 +382,7 @@ static int apply_xbc(const char *path, const char *xbc_path) memcpy(data, buf, size); /* Check the data format */ - ret = xbc_init(buf, &msg, &pos); + ret = xbc_init(buf, size, &msg, &pos); if (ret < 0) { show_xbc_error(data, msg, pos); free(data); -- cgit v1.2.3 From e306220cb7b7c2948f191414ab06851e143b54c1 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Thu, 16 Sep 2021 15:23:29 +0900 Subject: bootconfig: Add xbc_get_info() for the node information Add xbc_get_info() API which allows user to get the number of used xbc_nodes and the size of bootconfig data. This is also useful for checking the bootconfig is initialized or not. Link: https://lkml.kernel.org/r/163177340877.682366.4360676589783197627.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 2 ++ init/main.c | 1 + lib/bootconfig.c | 21 +++++++++++++++++++++ tools/bootconfig/main.c | 1 + 4 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 62e09b788172..f955bb7eabbb 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -273,6 +273,8 @@ static inline int __init xbc_node_compose_key(struct xbc_node *node, /* XBC node initializer */ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); +/* XBC node and size information */ +int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ void __init xbc_destroy_all(void); diff --git a/init/main.c b/init/main.c index d894989d86bc..afaed805de19 100644 --- a/init/main.c +++ b/init/main.c @@ -450,6 +450,7 @@ static void __init setup_boot_config(void) pr_err("Failed to parse bootconfig: %s at %d.\n", msg, pos); } else { + xbc_get_info(&ret, NULL); pr_info("Load bootconfig: %d bytes %d nodes\n", size, ret); /* keys starting with "kernel." are passed via cmdline */ extra_command_line = xbc_make_cmdline("kernel"); diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 66b02fddfea8..b088fe5c0001 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -34,6 +34,27 @@ static int xbc_err_pos __initdata; static int open_brace[XBC_DEPTH_MAX] __initdata; static int brace_index __initdata; +/** + * xbc_get_info() - Get the information of loaded boot config + * node_size: A pointer to store the number of nodes. + * data_size: A pointer to store the size of bootconfig data. + * + * Get the number of used nodes in @node_size if it is not NULL, + * and the size of bootconfig data in @data_size if it is not NULL. + * Return 0 if the boot config is initialized, or return -ENODEV. + */ +int __init xbc_get_info(int *node_size, size_t *data_size) +{ + if (!xbc_data) + return -ENODEV; + + if (node_size) + *node_size = xbc_node_num; + if (data_size) + *data_size = xbc_data_size; + return 0; +} + static int __init xbc_parse_error(const char *msg, const char *p) { xbc_err_msg = msg; diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 7269c9e35335..4f2a8d884745 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -391,6 +391,7 @@ static int apply_xbc(const char *path, const char *xbc_path) return ret; } printf("Apply %s to %s\n", xbc_path, path); + xbc_get_info(&ret, NULL); printf("\tNumber of nodes: %d\n", ret); printf("\tSize: %u bytes\n", (unsigned int)size); printf("\tChecksum: %d\n", (unsigned int)csum); -- cgit v1.2.3 From 115d4d08aeb942133d025a425dd611092893d774 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 17 Sep 2021 19:02:39 +0900 Subject: bootconfig: Rename xbc_destroy_all() to xbc_exit() Avoid using this noisy name and use more calm one. This is just a name change. No functional change. Link: https://lkml.kernel.org/r/163187295918.2366983.5231840238429996027.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 2 +- init/main.c | 2 +- lib/bootconfig.c | 8 ++++---- tools/bootconfig/main.c | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index f955bb7eabbb..7eb7a7f8ade7 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -277,7 +277,7 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos); int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ -void __init xbc_destroy_all(void); +void __init xbc_exit(void); /* Debug dump functions */ void __init xbc_debug_dump(void); diff --git a/init/main.c b/init/main.c index afaed805de19..f1428234e1e4 100644 --- a/init/main.c +++ b/init/main.c @@ -462,7 +462,7 @@ static void __init setup_boot_config(void) static void __init exit_boot_config(void) { - xbc_destroy_all(); + xbc_exit(); } #else /* !CONFIG_BOOT_CONFIG */ diff --git a/lib/bootconfig.c b/lib/bootconfig.c index b088fe5c0001..a3ce5a0c3ca4 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -802,13 +802,13 @@ static int __init xbc_verify_tree(void) } /** - * xbc_destroy_all() - Clean up all parsed bootconfig + * xbc_exit() - Clean up all parsed bootconfig * * This clears all data structures of parsed bootconfig on memory. * If you need to reuse xbc_init() with new boot config, you can * use this. */ -void __init xbc_destroy_all(void) +void __init xbc_exit(void) { memblock_free_ptr(xbc_data, xbc_data_size); xbc_data = NULL; @@ -869,7 +869,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; - xbc_destroy_all(); + xbc_exit(); return -ENOMEM; } memset(xbc_nodes, 0, sizeof(struct xbc_node) * XBC_NODE_MAX); @@ -925,7 +925,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) *epos = xbc_err_pos; if (emsg) *emsg = xbc_err_msg; - xbc_destroy_all(); + xbc_exit(); } else ret = xbc_node_num; diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 4f2a8d884745..4252c23bd35d 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -397,7 +397,7 @@ static int apply_xbc(const char *path, const char *xbc_path) printf("\tChecksum: %d\n", (unsigned int)csum); /* TODO: Check the options by schema */ - xbc_destroy_all(); + xbc_exit(); free(buf); /* Remove old boot config if exists */ -- cgit v1.2.3 From 9b81c9bfff4651abb28bfa6d83c8b879e467963b Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 17 Sep 2021 19:02:53 +0900 Subject: bootconfig: Remove unused debug function Remove unused xbc_debug_dump() from bootconfig for clean up the code. Link: https://lkml.kernel.org/r/163187297371.2366983.12943349701785875450.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 3 --- lib/bootconfig.c | 21 --------------------- 2 files changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 7eb7a7f8ade7..85cdfd381877 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -279,7 +279,4 @@ int __init xbc_get_info(int *node_size, size_t *data_size); /* XBC cleanup data structures */ void __init xbc_exit(void); -/* Debug dump functions */ -void __init xbc_debug_dump(void); - #endif diff --git a/lib/bootconfig.c b/lib/bootconfig.c index b7e5a32b30d3..953789171858 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -4,15 +4,12 @@ * Masami Hiramatsu */ -#define pr_fmt(fmt) "bootconfig: " fmt - #include #include #include #include #include #include -#include #include /* @@ -940,21 +937,3 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) return ret; } - -/** - * xbc_debug_dump() - Dump current XBC node list - * - * Dump the current XBC node list on printk buffer for debug. - */ -void __init xbc_debug_dump(void) -{ - int i; - - for (i = 0; i < xbc_node_num; i++) { - pr_debug("[%d] %s (%s) .next=%d, .child=%d .parent=%d\n", i, - xbc_node_get_data(xbc_nodes + i), - xbc_node_is_value(xbc_nodes + i) ? "value" : "key", - xbc_nodes[i].next, xbc_nodes[i].child, - xbc_nodes[i].parent); - } -} -- cgit v1.2.3 From 4f292c4886bfdfc2a7191ef4ff3f7aac69d1cc3f Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 17 Sep 2021 19:03:08 +0900 Subject: bootconfig: Replace u16 and u32 with uint16_t and uint32_t Replace u16 and u32 with uint16_t and uint32_t so that the tools/bootconfig only needs . Link: https://lkml.kernel.org/r/163187298835.2366983.9838262576854319669.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 12 ++++++------ lib/bootconfig.c | 16 ++++++++-------- tools/bootconfig/include/linux/kernel.h | 4 +--- tools/bootconfig/main.c | 20 ++++++++++---------- 4 files changed, 25 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index 85cdfd381877..a6f8dc51f168 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -25,10 +25,10 @@ * The checksum will be used with the BOOTCONFIG_MAGIC and the size for * embedding the bootconfig in the initrd image. */ -static inline __init u32 xbc_calc_checksum(void *data, u32 size) +static inline __init uint32_t xbc_calc_checksum(void *data, uint32_t size) { unsigned char *p = data; - u32 ret = 0; + uint32_t ret = 0; while (size--) ret += *p++; @@ -38,10 +38,10 @@ static inline __init u32 xbc_calc_checksum(void *data, u32 size) /* XBC tree node */ struct xbc_node { - u16 next; - u16 child; - u16 parent; - u16 data; + uint16_t next; + uint16_t child; + uint16_t parent; + uint16_t data; } __attribute__ ((__packed__)); #define XBC_KEY 0 diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 953789171858..a2f5f582181d 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -244,7 +244,7 @@ int __init xbc_node_compose_key_after(struct xbc_node *root, struct xbc_node *node, char *buf, size_t size) { - u16 keys[XBC_DEPTH_MAX]; + uint16_t keys[XBC_DEPTH_MAX]; int depth = 0, ret = 0, total = 0; if (!node || node == root) @@ -359,21 +359,21 @@ const char * __init xbc_node_find_next_key_value(struct xbc_node *root, /* XBC parse and tree build */ -static int __init xbc_init_node(struct xbc_node *node, char *data, u32 flag) +static int __init xbc_init_node(struct xbc_node *node, char *data, uint32_t flag) { unsigned long offset = data - xbc_data; if (WARN_ON(offset >= XBC_DATA_MAX)) return -EINVAL; - node->data = (u16)offset | flag; + node->data = (uint16_t)offset | flag; node->child = 0; node->next = 0; return 0; } -static struct xbc_node * __init xbc_add_node(char *data, u32 flag) +static struct xbc_node * __init xbc_add_node(char *data, uint32_t flag) { struct xbc_node *node; @@ -403,7 +403,7 @@ static inline __init struct xbc_node *xbc_last_child(struct xbc_node *node) return node; } -static struct xbc_node * __init __xbc_add_sibling(char *data, u32 flag, bool head) +static struct xbc_node * __init __xbc_add_sibling(char *data, uint32_t flag, bool head) { struct xbc_node *sib, *node = xbc_add_node(data, flag); @@ -430,17 +430,17 @@ static struct xbc_node * __init __xbc_add_sibling(char *data, u32 flag, bool hea return node; } -static inline struct xbc_node * __init xbc_add_sibling(char *data, u32 flag) +static inline struct xbc_node * __init xbc_add_sibling(char *data, uint32_t flag) { return __xbc_add_sibling(data, flag, false); } -static inline struct xbc_node * __init xbc_add_head_sibling(char *data, u32 flag) +static inline struct xbc_node * __init xbc_add_head_sibling(char *data, uint32_t flag) { return __xbc_add_sibling(data, flag, true); } -static inline __init struct xbc_node *xbc_add_child(char *data, u32 flag) +static inline __init struct xbc_node *xbc_add_child(char *data, uint32_t flag) { struct xbc_node *node = xbc_add_sibling(data, flag); diff --git a/tools/bootconfig/include/linux/kernel.h b/tools/bootconfig/include/linux/kernel.h index c4854b8e7023..39f306c18dd0 100644 --- a/tools/bootconfig/include/linux/kernel.h +++ b/tools/bootconfig/include/linux/kernel.h @@ -3,11 +3,9 @@ #define _SKC_LINUX_KERNEL_H #include +#include #include -typedef unsigned short u16; -typedef unsigned int u32; - #define unlikely(cond) (cond) #define __init diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index adc6c6e73fa9..fb7c9fb953d7 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -178,7 +178,7 @@ static int load_xbc_from_initrd(int fd, char **buf) { struct stat stat; int ret; - u32 size = 0, csum = 0, rcsum; + uint32_t size = 0, csum = 0, rcsum; char magic[BOOTCONFIG_MAGIC_LEN]; const char *msg; @@ -202,11 +202,11 @@ static int load_xbc_from_initrd(int fd, char **buf) if (lseek(fd, -(8 + BOOTCONFIG_MAGIC_LEN), SEEK_END) < 0) return pr_errno("Failed to lseek for size", -errno); - if (read(fd, &size, sizeof(u32)) < 0) + if (read(fd, &size, sizeof(uint32_t)) < 0) return pr_errno("Failed to read size", -errno); size = le32toh(size); - if (read(fd, &csum, sizeof(u32)) < 0) + if (read(fd, &csum, sizeof(uint32_t)) < 0) return pr_errno("Failed to read checksum", -errno); csum = le32toh(csum); @@ -364,7 +364,7 @@ static int apply_xbc(const char *path, const char *xbc_path) size_t total_size; struct stat stat; const char *msg; - u32 size, csum; + uint32_t size, csum; int pos, pad; int ret, fd; @@ -378,7 +378,7 @@ static int apply_xbc(const char *path, const char *xbc_path) /* Backup the bootconfig data */ data = calloc(size + BOOTCONFIG_ALIGN + - sizeof(u32) + sizeof(u32) + BOOTCONFIG_MAGIC_LEN, 1); + sizeof(uint32_t) + sizeof(uint32_t) + BOOTCONFIG_MAGIC_LEN, 1); if (!data) return -ENOMEM; memcpy(data, buf, size); @@ -426,17 +426,17 @@ static int apply_xbc(const char *path, const char *xbc_path) } /* To align up the total size to BOOTCONFIG_ALIGN, get padding size */ - total_size = stat.st_size + size + sizeof(u32) * 2 + BOOTCONFIG_MAGIC_LEN; + total_size = stat.st_size + size + sizeof(uint32_t) * 2 + BOOTCONFIG_MAGIC_LEN; pad = ((total_size + BOOTCONFIG_ALIGN - 1) & (~BOOTCONFIG_ALIGN_MASK)) - total_size; size += pad; /* Add a footer */ p = data + size; - *(u32 *)p = htole32(size); - p += sizeof(u32); + *(uint32_t *)p = htole32(size); + p += sizeof(uint32_t); - *(u32 *)p = htole32(csum); - p += sizeof(u32); + *(uint32_t *)p = htole32(csum); + p += sizeof(uint32_t); memcpy(p, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); p += BOOTCONFIG_MAGIC_LEN; -- cgit v1.2.3 From 4ee1b4cac236650979a5d9b745bb0a83efde3a46 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Fri, 17 Sep 2021 19:03:16 +0900 Subject: bootconfig: Cleanup dummy headers in tools/bootconfig Cleanup dummy headers in tools/bootconfig/include except for tools/bootconfig/include/linux/bootconfig.h. For this change, I use __KERNEL__ macro to split kernel header #include and introduce xbc_alloc_mem() and xbc_free_mem(). Link: https://lkml.kernel.org/r/163187299574.2366983.18371329724128746091.stgit@devnote2 Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/bootconfig.h | 10 +++++++ lib/bootconfig.c | 43 +++++++++++++++++++++++---- tools/bootconfig/Makefile | 2 +- tools/bootconfig/include/linux/bootconfig.h | 45 ++++++++++++++++++++++++++++- tools/bootconfig/include/linux/bug.h | 12 -------- tools/bootconfig/include/linux/ctype.h | 7 ----- tools/bootconfig/include/linux/errno.h | 7 ----- tools/bootconfig/include/linux/kernel.h | 14 --------- tools/bootconfig/include/linux/memblock.h | 11 ------- tools/bootconfig/include/linux/string.h | 32 -------------------- tools/bootconfig/main.c | 1 - 11 files changed, 93 insertions(+), 91 deletions(-) delete mode 100644 tools/bootconfig/include/linux/bug.h delete mode 100644 tools/bootconfig/include/linux/ctype.h delete mode 100644 tools/bootconfig/include/linux/errno.h delete mode 100644 tools/bootconfig/include/linux/kernel.h delete mode 100644 tools/bootconfig/include/linux/memblock.h delete mode 100644 tools/bootconfig/include/linux/string.h (limited to 'include/linux') diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h index a6f8dc51f168..a4665c7ab07c 100644 --- a/include/linux/bootconfig.h +++ b/include/linux/bootconfig.h @@ -7,8 +7,18 @@ * Author: Masami Hiramatsu */ +#ifdef __KERNEL__ #include #include +#else /* !__KERNEL__ */ +/* + * NOTE: This is only for tools/bootconfig, because tools/bootconfig will + * run the parser sanity test. + * This does NOT mean linux/bootconfig.h is available in the user space. + * However, if you change this file, please make sure the tools/bootconfig + * has no issue on building and running. + */ +#endif #define BOOTCONFIG_MAGIC "#BOOTCONFIG\n" #define BOOTCONFIG_MAGIC_LEN 12 diff --git a/lib/bootconfig.c b/lib/bootconfig.c index a2f5f582181d..a056ae137750 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -4,6 +4,7 @@ * Masami Hiramatsu */ +#ifdef __KERNEL__ #include #include #include @@ -11,6 +12,16 @@ #include #include #include +#else /* !__KERNEL__ */ +/* + * NOTE: This is only for tools/bootconfig, because tools/bootconfig will + * run the parser sanity test. + * This does NOT mean lib/bootconfig.c is available in the user space. + * However, if you change this file, please make sure the tools/bootconfig + * has no issue on building and running. + */ +#include +#endif /* * Extra Boot Config (XBC) is given as tree-structured ascii text of @@ -31,6 +42,29 @@ static int xbc_err_pos __initdata; static int open_brace[XBC_DEPTH_MAX] __initdata; static int brace_index __initdata; +#ifdef __KERNEL__ +static inline void *xbc_alloc_mem(size_t size) +{ + return memblock_alloc(size, SMP_CACHE_BYTES); +} + +static inline void xbc_free_mem(void *addr, size_t size) +{ + memblock_free_ptr(addr, size); +} + +#else /* !__KERNEL__ */ + +static inline void *xbc_alloc_mem(size_t size) +{ + return malloc(size); +} + +static inline void xbc_free_mem(void *addr, size_t size) +{ + free(addr); +} +#endif /** * xbc_get_info() - Get the information of loaded boot config * node_size: A pointer to store the number of nodes. @@ -859,11 +893,11 @@ static int __init xbc_parse_tree(void) */ void __init xbc_exit(void) { - memblock_free_ptr(xbc_data, xbc_data_size); + xbc_free_mem(xbc_data, xbc_data_size); xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + xbc_free_mem(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } @@ -902,7 +936,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) return -ERANGE; } - xbc_data = memblock_alloc(size + 1, SMP_CACHE_BYTES); + xbc_data = xbc_alloc_mem(size + 1); if (!xbc_data) { if (emsg) *emsg = "Failed to allocate bootconfig data"; @@ -912,8 +946,7 @@ int __init xbc_init(const char *data, size_t size, const char **emsg, int *epos) xbc_data[size] = '\0'; xbc_data_size = size + 1; - xbc_nodes = memblock_alloc(sizeof(struct xbc_node) * XBC_NODE_MAX, - SMP_CACHE_BYTES); + xbc_nodes = xbc_alloc_mem(sizeof(struct xbc_node) * XBC_NODE_MAX); if (!xbc_nodes) { if (emsg) *emsg = "Failed to allocate bootconfig nodes"; diff --git a/tools/bootconfig/Makefile b/tools/bootconfig/Makefile index f1eec3ccbe18..566c3e0ee561 100644 --- a/tools/bootconfig/Makefile +++ b/tools/bootconfig/Makefile @@ -17,7 +17,7 @@ ALL_PROGRAMS := $(patsubst %,$(OUTPUT)%,$(ALL_TARGETS)) all: $(ALL_PROGRAMS) test -$(OUTPUT)bootconfig: main.c $(LIBSRC) +$(OUTPUT)bootconfig: main.c include/linux/bootconfig.h $(LIBSRC) $(CC) $(filter %.c,$^) $(CFLAGS) -o $@ test: $(ALL_PROGRAMS) test-bootconfig.sh diff --git a/tools/bootconfig/include/linux/bootconfig.h b/tools/bootconfig/include/linux/bootconfig.h index de7f30f99af3..6784296a0692 100644 --- a/tools/bootconfig/include/linux/bootconfig.h +++ b/tools/bootconfig/include/linux/bootconfig.h @@ -2,10 +2,53 @@ #ifndef _BOOTCONFIG_LINUX_BOOTCONFIG_H #define _BOOTCONFIG_LINUX_BOOTCONFIG_H -#include "../../../../include/linux/bootconfig.h" +#include +#include +#include +#include +#include +#include +#include + #ifndef fallthrough # define fallthrough #endif +#define WARN_ON(cond) \ + ((cond) ? printf("Internal warning(%s:%d, %s): %s\n", \ + __FILE__, __LINE__, __func__, #cond) : 0) + +#define unlikely(cond) (cond) + +/* Copied from lib/string.c */ +static inline char *skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} + +static inline char *strim(char *s) +{ + size_t size; + char *end; + + size = strlen(s); + if (!size) + return s; + + end = s + size - 1; + while (end >= s && isspace(*end)) + end--; + *(end + 1) = '\0'; + + return skip_spaces(s); +} + +#define __init +#define __initdata + +#include "../../../../include/linux/bootconfig.h" + #endif diff --git a/tools/bootconfig/include/linux/bug.h b/tools/bootconfig/include/linux/bug.h deleted file mode 100644 index 7b65a389c0dd..000000000000 --- a/tools/bootconfig/include/linux/bug.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SKC_LINUX_BUG_H -#define _SKC_LINUX_BUG_H - -#include -#include - -#define WARN_ON(cond) \ - ((cond) ? printf("Internal warning(%s:%d, %s): %s\n", \ - __FILE__, __LINE__, __func__, #cond) : 0) - -#endif diff --git a/tools/bootconfig/include/linux/ctype.h b/tools/bootconfig/include/linux/ctype.h deleted file mode 100644 index c56ecc136448..000000000000 --- a/tools/bootconfig/include/linux/ctype.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SKC_LINUX_CTYPE_H -#define _SKC_LINUX_CTYPE_H - -#include - -#endif diff --git a/tools/bootconfig/include/linux/errno.h b/tools/bootconfig/include/linux/errno.h deleted file mode 100644 index 5d9f91ec2fda..000000000000 --- a/tools/bootconfig/include/linux/errno.h +++ /dev/null @@ -1,7 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SKC_LINUX_ERRNO_H -#define _SKC_LINUX_ERRNO_H - -#include - -#endif diff --git a/tools/bootconfig/include/linux/kernel.h b/tools/bootconfig/include/linux/kernel.h deleted file mode 100644 index 39f306c18dd0..000000000000 --- a/tools/bootconfig/include/linux/kernel.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SKC_LINUX_KERNEL_H -#define _SKC_LINUX_KERNEL_H - -#include -#include -#include - -#define unlikely(cond) (cond) - -#define __init -#define __initdata - -#endif diff --git a/tools/bootconfig/include/linux/memblock.h b/tools/bootconfig/include/linux/memblock.h deleted file mode 100644 index f2e506f7d57f..000000000000 --- a/tools/bootconfig/include/linux/memblock.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _XBC_LINUX_MEMBLOCK_H -#define _XBC_LINUX_MEMBLOCK_H - -#include - -#define SMP_CACHE_BYTES 0 -#define memblock_alloc(size, align) malloc(size) -#define memblock_free_ptr(paddr, size) free(paddr) - -#endif diff --git a/tools/bootconfig/include/linux/string.h b/tools/bootconfig/include/linux/string.h deleted file mode 100644 index 8267af75153a..000000000000 --- a/tools/bootconfig/include/linux/string.h +++ /dev/null @@ -1,32 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _SKC_LINUX_STRING_H -#define _SKC_LINUX_STRING_H - -#include - -/* Copied from lib/string.c */ -static inline char *skip_spaces(const char *str) -{ - while (isspace(*str)) - ++str; - return (char *)str; -} - -static inline char *strim(char *s) -{ - size_t size; - char *end; - - size = strlen(s); - if (!size) - return s; - - end = s + size - 1; - while (end >= s && isspace(*end)) - end--; - *(end + 1) = '\0'; - - return skip_spaces(s); -} - -#endif diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index fb7c9fb953d7..156b62a163c5 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -12,7 +12,6 @@ #include #include -#include #include #define pr_err(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__) -- cgit v1.2.3 From 5e51cc0005c6ed1b793c228632f36269615f7c31 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Fri, 8 Oct 2021 10:50:07 +0100 Subject: dma-resv: Fix dma_resv_get_fences and dma_resv_copy_fences after conversion MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cache the count of shared fences in the iterator to avoid dereferencing the dma_resv_object outside the RCU protection. Otherwise iterator and its users can observe an incosistent state which makes it impossible to use safely. Such as: <6> [187.517041] [IGT] gem_sync: executing <7> [187.536343] i915 0000:00:02.0: [drm:i915_gem_context_create_ioctl [i915]] HW context 1 created <7> [187.536793] i915 0000:00:02.0: [drm:i915_gem_context_create_ioctl [i915]] HW context 1 created <6> [187.551235] [IGT] gem_sync: starting subtest basic-many-each <1> [188.935462] BUG: kernel NULL pointer dereference, address: 0000000000000010 <1> [188.935485] #PF: supervisor write access in kernel mode <1> [188.935495] #PF: error_code(0x0002) - not-present page <6> [188.935504] PGD 0 P4D 0 <4> [188.935512] Oops: 0002 [#1] PREEMPT SMP NOPTI <4> [188.935521] CPU: 2 PID: 1467 Comm: gem_sync Not tainted 5.15.0-rc4-CI-Patchwork_21264+ #1 <4> [188.935535] Hardware name: /NUC6CAYB, BIOS AYAPLCEL.86A.0049.2018.0508.1356 05/08/2018 <4> [188.935546] RIP: 0010:dma_resv_get_fences+0x116/0x2d0 <4> [188.935560] Code: 10 85 c0 7f c9 be 03 00 00 00 e8 15 8b df ff eb bd e8 8e c6 ff ff eb b6 41 8b 04 24 49 8b 55 00 48 89 e7 8d 48 01 41 89 0c 24 <4c> 89 34 c2 e8 41 f2 ff ff 49 89 c6 48 85 c0 75 8c 48 8b 44 24 10 <4> [188.935583] RSP: 0018:ffffc900011dbcc8 EFLAGS: 00010202 <4> [188.935593] RAX: 0000000000000000 RBX: 00000000ffffffff RCX: 0000000000000001 <4> [188.935603] RDX: 0000000000000010 RSI: ffffffff822e343c RDI: ffffc900011dbcc8 <4> [188.935613] RBP: ffffc900011dbd48 R08: ffff88812d255bb8 R09: 00000000fffffffe <4> [188.935623] R10: 0000000000000001 R11: 0000000000000000 R12: ffffc900011dbd44 <4> [188.935633] R13: ffffc900011dbd50 R14: ffff888113d29cc0 R15: 0000000000000000 <4> [188.935643] FS: 00007f68d17e9700(0000) GS:ffff888277900000(0000) knlGS:0000000000000000 <4> [188.935655] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [188.935665] CR2: 0000000000000010 CR3: 000000012d0a4000 CR4: 00000000003506e0 <4> [188.935676] Call Trace: <4> [188.935685] i915_gem_object_wait+0x1ff/0x410 [i915] <4> [188.935988] i915_gem_wait_ioctl+0xf2/0x2a0 [i915] <4> [188.936272] ? i915_gem_object_wait+0x410/0x410 [i915] <4> [188.936533] drm_ioctl_kernel+0xae/0x140 <4> [188.936546] drm_ioctl+0x201/0x3d0 <4> [188.936555] ? i915_gem_object_wait+0x410/0x410 [i915] <4> [188.936820] ? __fget_files+0xc2/0x1c0 <4> [188.936830] ? __fget_files+0xda/0x1c0 <4> [188.936839] __x64_sys_ioctl+0x6d/0xa0 <4> [188.936848] do_syscall_64+0x3a/0xb0 <4> [188.936859] entry_SYSCALL_64_after_hwframe+0x44/0xae If the shared object has changed during the RCU unlocked period callers will correctly handle the restart on the next iteration. Signed-off-by: Tvrtko Ursulin Fixes: 96601e8a4755 ("dma-buf: use new iterator in dma_resv_copy_fences") Fixes: d3c80698c9f5 ("dma-buf: use new iterator in dma_resv_get_fences v3") Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/4274 Cc: Christian König Cc: Daniel Vetter Cc: Sumit Semwal Cc: linux-media@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: linaro-mm-sig@lists.linaro.org Link: https://patchwork.freedesktop.org/patch/msgid/20211008095007.972693-1-tvrtko.ursulin@linux.intel.com Reviewed-by: Christian König Signed-off-by: Christian König --- drivers/dma-buf/dma-resv.c | 18 ++++++++++-------- include/linux/dma-resv.h | 5 ++++- 2 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 2f98caa68ae5..9eb2baa387d4 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -333,10 +333,14 @@ static void dma_resv_iter_restart_unlocked(struct dma_resv_iter *cursor) { cursor->seq = read_seqcount_begin(&cursor->obj->seq); cursor->index = -1; - if (cursor->all_fences) + cursor->shared_count = 0; + if (cursor->all_fences) { cursor->fences = dma_resv_shared_list(cursor->obj); - else + if (cursor->fences) + cursor->shared_count = cursor->fences->shared_count; + } else { cursor->fences = NULL; + } cursor->is_restarted = true; } @@ -363,7 +367,7 @@ static void dma_resv_iter_walk_unlocked(struct dma_resv_iter *cursor) continue; } else if (!cursor->fences || - cursor->index >= cursor->fences->shared_count) { + cursor->index >= cursor->shared_count) { cursor->fence = NULL; break; @@ -499,10 +503,8 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src) dma_resv_list_free(list); dma_fence_put(excl); - if (cursor.fences) { - unsigned int cnt = cursor.fences->shared_count; - - list = dma_resv_list_alloc(cnt); + if (cursor.shared_count) { + list = dma_resv_list_alloc(cursor.shared_count); if (!list) { dma_resv_iter_end(&cursor); return -ENOMEM; @@ -573,7 +575,7 @@ int dma_resv_get_fences(struct dma_resv *obj, struct dma_fence **fence_excl, if (fence_excl) dma_fence_put(*fence_excl); - count = cursor.fences ? cursor.fences->shared_count : 0; + count = cursor.shared_count; count += fence_excl ? 0 : 1; /* Eventually re-allocate the array */ diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 491359cea54c..45f1d4812a37 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -170,9 +170,12 @@ struct dma_resv_iter { /** @index: index into the shared fences */ unsigned int index; - /** @fences: the shared fences */ + /** @fences: the shared fences; private, *MUST* not dereference */ struct dma_resv_list *fences; + /** @shared_count: number of shared fences */ + unsigned int shared_count; + /** @is_restarted: true if this is the first returned fence */ bool is_restarted; }; -- cgit v1.2.3 From a440943e68cd1b5a853a6f60865967b7cc2539eb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Sep 2021 08:59:58 +0200 Subject: unicode: remove the charset field from struct unicode_map It is hardcoded and only used for a f2fs sysfs file where it can be hardcoded just as easily. Signed-off-by: Christoph Hellwig Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Gabriel Krisman Bertazi --- fs/f2fs/sysfs.c | 3 +-- fs/unicode/utf8-core.c | 3 --- include/linux/unicode.h | 1 - 3 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index a32fe31c33b8..650e84398f74 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -196,8 +196,7 @@ static ssize_t encoding_show(struct f2fs_attr *a, struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) - return snprintf(buf, PAGE_SIZE, "%s (%d.%d.%d)\n", - sb->s_encoding->charset, + return snprintf(buf, PAGE_SIZE, "UTF-8 (%d.%d.%d)\n", (sb->s_encoding->version >> 16) & 0xff, (sb->s_encoding->version >> 8) & 0xff, sb->s_encoding->version & 0xff); diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index dc25823bfed9..86f42a078d99 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -219,10 +219,7 @@ struct unicode_map *utf8_load(const char *version) um = kzalloc(sizeof(struct unicode_map), GFP_KERNEL); if (!um) return ERR_PTR(-ENOMEM); - - um->charset = "UTF-8"; um->version = unicode_version; - return um; } EXPORT_SYMBOL(utf8_load); diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 74484d44c755..6a392cd9f076 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -6,7 +6,6 @@ #include struct unicode_map { - const char *charset; int version; }; -- cgit v1.2.3 From f3a9c82396006a5664f6e398d6928799d29de76e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Sep 2021 08:59:59 +0200 Subject: unicode: mark the version field in struct unicode_map unsigned unicode version tripplets are always unsigned. Signed-off-by: Christoph Hellwig Reviewed-by: Gabriel Krisman Bertazi Signed-off-by: Gabriel Krisman Bertazi --- include/linux/unicode.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 6a392cd9f076..0744f81c4b5f 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -6,7 +6,7 @@ #include struct unicode_map { - int version; + unsigned int version; }; int utf8_validate(const struct unicode_map *um, const struct qstr *str); -- cgit v1.2.3 From 49bd03cc7e95cb78420305ca2f5ef67497b6fa80 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Sep 2021 09:00:00 +0200 Subject: unicode: pass a UNICODE_AGE() tripple to utf8_load Don't bother with pointless string parsing when the caller can just pass the version in the format that the core expects. Also remove the fallback to the latest version that none of the callers actually uses. Signed-off-by: Christoph Hellwig Signed-off-by: Gabriel Krisman Bertazi --- fs/ext4/super.c | 18 +++++++++++------ fs/f2fs/super.c | 18 +++++++++++------ fs/unicode/utf8-core.c | 50 +++++----------------------------------------- fs/unicode/utf8-norm.c | 11 ++-------- fs/unicode/utf8-selftest.c | 15 +++++++------- fs/unicode/utf8n.h | 14 ++----------- include/linux/unicode.h | 25 ++++++++++++++++++++++- 7 files changed, 65 insertions(+), 86 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 26c0e6fc5bce..85e73093c61a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2018,9 +2018,9 @@ static const struct mount_opts { static const struct ext4_sb_encodings { __u16 magic; char *name; - char *version; + unsigned int version; } ext4_sb_encoding_map[] = { - {EXT4_ENC_UTF8_12_1, "utf8", "12.1.0"}, + {EXT4_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct ext4_sb_encodings * @@ -4166,15 +4166,21 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { ext4_msg(sb, KERN_ERR, - "can't mount with superblock charset: %s-%s " + "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", - encoding_info->name, encoding_info->version, + encoding_info->name, + unicode_major(encoding_info->version), + unicode_minor(encoding_info->version), + unicode_rev(encoding_info->version), encoding_flags); goto failed_mount; } ext4_msg(sb, KERN_INFO,"Using encoding defined by superblock: " - "%s-%s with flags 0x%hx", encoding_info->name, - encoding_info->version?:"\b", encoding_flags); + "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, + unicode_major(encoding_info->version), + unicode_minor(encoding_info->version), + unicode_rev(encoding_info->version), + encoding_flags); sb->s_encoding = encoding; sb->s_encoding_flags = encoding_flags; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 4c457100f18e..3029f71bf2b7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -259,9 +259,9 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) static const struct f2fs_sb_encodings { __u16 magic; char *name; - char *version; + unsigned int version; } f2fs_sb_encoding_map[] = { - {F2FS_ENC_UTF8_12_1, "utf8", "12.1.0"}, + {F2FS_ENC_UTF8_12_1, "utf8", UNICODE_AGE(12, 1, 0)}, }; static const struct f2fs_sb_encodings * @@ -3847,15 +3847,21 @@ static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) encoding = utf8_load(encoding_info->version); if (IS_ERR(encoding)) { f2fs_err(sbi, - "can't mount with superblock charset: %s-%s " + "can't mount with superblock charset: %s-%u.%u.%u " "not supported by the kernel. flags: 0x%x.", - encoding_info->name, encoding_info->version, + encoding_info->name, + unicode_major(encoding_info->version), + unicode_minor(encoding_info->version), + unicode_rev(encoding_info->version), encoding_flags); return PTR_ERR(encoding); } f2fs_info(sbi, "Using encoding defined by superblock: " - "%s-%s with flags 0x%hx", encoding_info->name, - encoding_info->version?:"\b", encoding_flags); + "%s-%u.%u.%u with flags 0x%hx", encoding_info->name, + unicode_major(encoding_info->version), + unicode_minor(encoding_info->version), + unicode_rev(encoding_info->version), + encoding_flags); sbi->sb->s_encoding = encoding; sbi->sb->s_encoding_flags = encoding_flags; diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index 86f42a078d99..dca2865c3bee 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -167,59 +167,19 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str, } return -EINVAL; } - EXPORT_SYMBOL(utf8_normalize); -static int utf8_parse_version(const char *version, unsigned int *maj, - unsigned int *min, unsigned int *rev) +struct unicode_map *utf8_load(unsigned int version) { - substring_t args[3]; - char version_string[12]; - static const struct match_token token[] = { - {1, "%d.%d.%d"}, - {0, NULL} - }; - - strncpy(version_string, version, sizeof(version_string)); - - if (match_token(version_string, token, args) != 1) - return -EINVAL; - - if (match_int(&args[0], maj) || match_int(&args[1], min) || - match_int(&args[2], rev)) - return -EINVAL; + struct unicode_map *um; - return 0; -} - -struct unicode_map *utf8_load(const char *version) -{ - struct unicode_map *um = NULL; - int unicode_version; - - if (version) { - unsigned int maj, min, rev; - - if (utf8_parse_version(version, &maj, &min, &rev) < 0) - return ERR_PTR(-EINVAL); - - if (!utf8version_is_supported(maj, min, rev)) - return ERR_PTR(-EINVAL); - - unicode_version = UNICODE_AGE(maj, min, rev); - } else { - unicode_version = utf8version_latest(); - printk(KERN_WARNING"UTF-8 version not specified. " - "Assuming latest supported version (%d.%d.%d).", - (unicode_version >> 16) & 0xff, - (unicode_version >> 8) & 0xff, - (unicode_version & 0xff)); - } + if (!utf8version_is_supported(version)) + return ERR_PTR(-EINVAL); um = kzalloc(sizeof(struct unicode_map), GFP_KERNEL); if (!um) return ERR_PTR(-ENOMEM); - um->version = unicode_version; + um->version = version; return um; } EXPORT_SYMBOL(utf8_load); diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c index 1d2d2e5b906a..12abf89ae6ec 100644 --- a/fs/unicode/utf8-norm.c +++ b/fs/unicode/utf8-norm.c @@ -15,13 +15,12 @@ struct utf8data { #include "utf8data.h" #undef __INCLUDED_FROM_UTF8NORM_C__ -int utf8version_is_supported(u8 maj, u8 min, u8 rev) +int utf8version_is_supported(unsigned int version) { int i = ARRAY_SIZE(utf8agetab) - 1; - unsigned int sb_utf8version = UNICODE_AGE(maj, min, rev); while (i >= 0 && utf8agetab[i] != 0) { - if (sb_utf8version == utf8agetab[i]) + if (version == utf8agetab[i]) return 1; i--; } @@ -29,12 +28,6 @@ int utf8version_is_supported(u8 maj, u8 min, u8 rev) } EXPORT_SYMBOL(utf8version_is_supported); -int utf8version_latest(void) -{ - return utf8vers; -} -EXPORT_SYMBOL(utf8version_latest); - /* * UTF-8 valid ranges. * diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c index 6fe8af7edccb..37f33890e012 100644 --- a/fs/unicode/utf8-selftest.c +++ b/fs/unicode/utf8-selftest.c @@ -235,7 +235,7 @@ static void check_utf8_nfdicf(void) static void check_utf8_comparisons(void) { int i; - struct unicode_map *table = utf8_load("12.1.0"); + struct unicode_map *table = utf8_load(UNICODE_AGE(12, 1, 0)); if (IS_ERR(table)) { pr_err("%s: Unable to load utf8 %d.%d.%d. Skipping.\n", @@ -269,18 +269,19 @@ static void check_utf8_comparisons(void) static void check_supported_versions(void) { /* Unicode 7.0.0 should be supported. */ - test(utf8version_is_supported(7, 0, 0)); + test(utf8version_is_supported(UNICODE_AGE(7, 0, 0))); /* Unicode 9.0.0 should be supported. */ - test(utf8version_is_supported(9, 0, 0)); + test(utf8version_is_supported(UNICODE_AGE(9, 0, 0))); /* Unicode 1x.0.0 (the latest version) should be supported. */ - test(utf8version_is_supported(latest_maj, latest_min, latest_rev)); + test(utf8version_is_supported( + UNICODE_AGE(latest_maj, latest_min, latest_rev))); /* Next versions don't exist. */ - test(!utf8version_is_supported(13, 0, 0)); - test(!utf8version_is_supported(0, 0, 0)); - test(!utf8version_is_supported(-1, -1, -1)); + test(!utf8version_is_supported(UNICODE_AGE(13, 0, 0))); + test(!utf8version_is_supported(UNICODE_AGE(0, 0, 0))); + test(!utf8version_is_supported(UNICODE_AGE(-1, -1, -1))); } static int __init init_test_ucd(void) diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h index 0acd530c2c79..85a7bebf6927 100644 --- a/fs/unicode/utf8n.h +++ b/fs/unicode/utf8n.h @@ -11,19 +11,9 @@ #include #include #include +#include -/* Encoding a unicode version number as a single unsigned int. */ -#define UNICODE_MAJ_SHIFT (16) -#define UNICODE_MIN_SHIFT (8) - -#define UNICODE_AGE(MAJ, MIN, REV) \ - (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \ - ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ - ((unsigned int)(REV))) - -/* Highest unicode version supported by the data tables. */ -extern int utf8version_is_supported(u8 maj, u8 min, u8 rev); -extern int utf8version_latest(void); +int utf8version_is_supported(unsigned int version); /* * Look for the correct const struct utf8data for a unicode version. diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 0744f81c4b5f..77bb915fd1f0 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -5,6 +5,29 @@ #include #include +#define UNICODE_MAJ_SHIFT 16 +#define UNICODE_MIN_SHIFT 8 + +#define UNICODE_AGE(MAJ, MIN, REV) \ + (((unsigned int)(MAJ) << UNICODE_MAJ_SHIFT) | \ + ((unsigned int)(MIN) << UNICODE_MIN_SHIFT) | \ + ((unsigned int)(REV))) + +static inline u8 unicode_major(unsigned int age) +{ + return (age >> UNICODE_MAJ_SHIFT) & 0xff; +} + +static inline u8 unicode_minor(unsigned int age) +{ + return (age >> UNICODE_MIN_SHIFT) & 0xff; +} + +static inline u8 unicode_rev(unsigned int age) +{ + return age & 0xff; +} + struct unicode_map { unsigned int version; }; @@ -29,7 +52,7 @@ int utf8_casefold(const struct unicode_map *um, const struct qstr *str, int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct qstr *str); -struct unicode_map *utf8_load(const char *version); +struct unicode_map *utf8_load(unsigned int version); void utf8_unload(struct unicode_map *um); #endif /* _LINUX_UNICODE_H */ -- cgit v1.2.3 From 6ca99ce756c27852d1ea1e555045de1c920f30ed Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Sep 2021 09:00:04 +0200 Subject: unicode: cache the normalization tables in struct unicode_map Instead of repeatedly looking up the version add pointers to the NFD and NFD+CF tables to struct unicode_map, and pass a unicode_map plus index to the functions using the normalization tables. Signed-off-by: Christoph Hellwig Signed-off-by: Gabriel Krisman Bertazi --- fs/unicode/utf8-core.c | 37 ++++++++++----------- fs/unicode/utf8-norm.c | 45 ++++++++++++-------------- fs/unicode/utf8-selftest.c | 80 +++++++++++++++++++--------------------------- fs/unicode/utf8n.h | 10 +++--- include/linux/unicode.h | 19 +++++++++++ 5 files changed, 97 insertions(+), 94 deletions(-) (limited to 'include/linux') diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index dca2865c3bee..d9f713d38c0a 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -5,16 +5,13 @@ #include #include #include -#include #include #include "utf8n.h" int utf8_validate(const struct unicode_map *um, const struct qstr *str) { - const struct utf8data *data = utf8nfdi(um->version); - - if (utf8nlen(data, str->name, str->len) < 0) + if (utf8nlen(um, UTF8_NFDI, str->name, str->len) < 0) return -1; return 0; } @@ -23,14 +20,13 @@ EXPORT_SYMBOL(utf8_validate); int utf8_strncmp(const struct unicode_map *um, const struct qstr *s1, const struct qstr *s2) { - const struct utf8data *data = utf8nfdi(um->version); struct utf8cursor cur1, cur2; int c1, c2; - if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0) + if (utf8ncursor(&cur1, um, UTF8_NFDI, s1->name, s1->len) < 0) return -EINVAL; - if (utf8ncursor(&cur2, data, s2->name, s2->len) < 0) + if (utf8ncursor(&cur2, um, UTF8_NFDI, s2->name, s2->len) < 0) return -EINVAL; do { @@ -50,14 +46,13 @@ EXPORT_SYMBOL(utf8_strncmp); int utf8_strncasecmp(const struct unicode_map *um, const struct qstr *s1, const struct qstr *s2) { - const struct utf8data *data = utf8nfdicf(um->version); struct utf8cursor cur1, cur2; int c1, c2; - if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0) + if (utf8ncursor(&cur1, um, UTF8_NFDICF, s1->name, s1->len) < 0) return -EINVAL; - if (utf8ncursor(&cur2, data, s2->name, s2->len) < 0) + if (utf8ncursor(&cur2, um, UTF8_NFDICF, s2->name, s2->len) < 0) return -EINVAL; do { @@ -81,12 +76,11 @@ int utf8_strncasecmp_folded(const struct unicode_map *um, const struct qstr *cf, const struct qstr *s1) { - const struct utf8data *data = utf8nfdicf(um->version); struct utf8cursor cur1; int c1, c2; int i = 0; - if (utf8ncursor(&cur1, data, s1->name, s1->len) < 0) + if (utf8ncursor(&cur1, um, UTF8_NFDICF, s1->name, s1->len) < 0) return -EINVAL; do { @@ -105,11 +99,10 @@ EXPORT_SYMBOL(utf8_strncasecmp_folded); int utf8_casefold(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen) { - const struct utf8data *data = utf8nfdicf(um->version); struct utf8cursor cur; size_t nlen = 0; - if (utf8ncursor(&cur, data, str->name, str->len) < 0) + if (utf8ncursor(&cur, um, UTF8_NFDICF, str->name, str->len) < 0) return -EINVAL; for (nlen = 0; nlen < dlen; nlen++) { @@ -128,12 +121,11 @@ EXPORT_SYMBOL(utf8_casefold); int utf8_casefold_hash(const struct unicode_map *um, const void *salt, struct qstr *str) { - const struct utf8data *data = utf8nfdicf(um->version); struct utf8cursor cur; int c; unsigned long hash = init_name_hash(salt); - if (utf8ncursor(&cur, data, str->name, str->len) < 0) + if (utf8ncursor(&cur, um, UTF8_NFDICF, str->name, str->len) < 0) return -EINVAL; while ((c = utf8byte(&cur))) { @@ -149,11 +141,10 @@ EXPORT_SYMBOL(utf8_casefold_hash); int utf8_normalize(const struct unicode_map *um, const struct qstr *str, unsigned char *dest, size_t dlen) { - const struct utf8data *data = utf8nfdi(um->version); struct utf8cursor cur; ssize_t nlen = 0; - if (utf8ncursor(&cur, data, str->name, str->len) < 0) + if (utf8ncursor(&cur, um, UTF8_NFDI, str->name, str->len) < 0) return -EINVAL; for (nlen = 0; nlen < dlen; nlen++) { @@ -180,7 +171,17 @@ struct unicode_map *utf8_load(unsigned int version) if (!um) return ERR_PTR(-ENOMEM); um->version = version; + um->ntab[UTF8_NFDI] = utf8nfdi(version); + if (!um->ntab[UTF8_NFDI]) + goto out_free_um; + um->ntab[UTF8_NFDICF] = utf8nfdicf(version); + if (!um->ntab[UTF8_NFDICF]) + goto out_free_um; return um; + +out_free_um: + kfree(um); + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL(utf8_load); diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c index 1ac90fa00070..7c1f28ab31a8 100644 --- a/fs/unicode/utf8-norm.c +++ b/fs/unicode/utf8-norm.c @@ -309,21 +309,19 @@ utf8hangul(const char *str, unsigned char *hangul) * is well-formed and corresponds to a known unicode code point. The * shorthand for this will be "is valid UTF-8 unicode". */ -static utf8leaf_t *utf8nlookup(const struct utf8data *data, - unsigned char *hangul, const char *s, size_t len) +static utf8leaf_t *utf8nlookup(const struct unicode_map *um, + enum utf8_normalization n, unsigned char *hangul, const char *s, + size_t len) { - utf8trie_t *trie = NULL; + utf8trie_t *trie = utf8data + um->ntab[n]->offset; int offlen; int offset; int mask; int node; - if (!data) - return NULL; if (len == 0) return NULL; - trie = utf8data + data->offset; node = 1; while (node) { offlen = (*trie & OFFLEN) >> OFFLEN_SHIFT; @@ -385,29 +383,28 @@ static utf8leaf_t *utf8nlookup(const struct utf8data *data, * * Forwards to utf8nlookup(). */ -static utf8leaf_t *utf8lookup(const struct utf8data *data, - unsigned char *hangul, const char *s) +static utf8leaf_t *utf8lookup(const struct unicode_map *um, + enum utf8_normalization n, unsigned char *hangul, const char *s) { - return utf8nlookup(data, hangul, s, (size_t)-1); + return utf8nlookup(um, n, hangul, s, (size_t)-1); } /* * Length of the normalization of s, touch at most len bytes. * Return -1 if s is not valid UTF-8 unicode. */ -ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len) +ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n, + const char *s, size_t len) { utf8leaf_t *leaf; size_t ret = 0; unsigned char hangul[UTF8HANGULLEAF]; - if (!data) - return -1; while (len && *s) { - leaf = utf8nlookup(data, hangul, s, len); + leaf = utf8nlookup(um, n, hangul, s, len); if (!leaf) return -1; - if (utf8agetab[LEAF_GEN(leaf)] > data->maxage) + if (utf8agetab[LEAF_GEN(leaf)] > um->ntab[n]->maxage) ret += utf8clen(s); else if (LEAF_CCC(leaf) == DECOMPOSE) ret += strlen(LEAF_STR(leaf)); @@ -430,14 +427,13 @@ EXPORT_SYMBOL(utf8nlen); * * Returns -1 on error, 0 on success. */ -int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data, - const char *s, size_t len) +int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um, + enum utf8_normalization n, const char *s, size_t len) { - if (!data) - return -1; if (!s) return -1; - u8c->data = data; + u8c->um = um; + u8c->n = n; u8c->s = s; u8c->p = NULL; u8c->ss = NULL; @@ -512,9 +508,9 @@ int utf8byte(struct utf8cursor *u8c) /* Look up the data for the current character. */ if (u8c->p) { - leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s); + leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s); } else { - leaf = utf8nlookup(u8c->data, u8c->hangul, + leaf = utf8nlookup(u8c->um, u8c->n, u8c->hangul, u8c->s, u8c->len); } @@ -524,7 +520,8 @@ int utf8byte(struct utf8cursor *u8c) ccc = LEAF_CCC(leaf); /* Characters that are too new have CCC 0. */ - if (utf8agetab[LEAF_GEN(leaf)] > u8c->data->maxage) { + if (utf8agetab[LEAF_GEN(leaf)] > + u8c->um->ntab[u8c->n]->maxage) { ccc = STOPPER; } else if (ccc == DECOMPOSE) { u8c->len -= utf8clen(u8c->s); @@ -538,7 +535,7 @@ int utf8byte(struct utf8cursor *u8c) goto ccc_mismatch; } - leaf = utf8lookup(u8c->data, u8c->hangul, u8c->s); + leaf = utf8lookup(u8c->um, u8c->n, u8c->hangul, u8c->s); if (!leaf) return -1; ccc = LEAF_CCC(leaf); @@ -611,7 +608,6 @@ const struct utf8data *utf8nfdi(unsigned int maxage) return NULL; return &utf8nfdidata[i]; } -EXPORT_SYMBOL(utf8nfdi); const struct utf8data *utf8nfdicf(unsigned int maxage) { @@ -623,4 +619,3 @@ const struct utf8data *utf8nfdicf(unsigned int maxage) return NULL; return &utf8nfdicfdata[i]; } -EXPORT_SYMBOL(utf8nfdicf); diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c index 04628b50351d..cfa3832b75f4 100644 --- a/fs/unicode/utf8-selftest.c +++ b/fs/unicode/utf8-selftest.c @@ -18,9 +18,7 @@ unsigned int failed_tests; unsigned int total_tests; /* Tests will be based on this version. */ -#define latest_maj 12 -#define latest_min 1 -#define latest_rev 0 +#define UTF8_LATEST UNICODE_AGE(12, 1, 0) #define _test(cond, func, line, fmt, ...) do { \ total_tests++; \ @@ -160,29 +158,22 @@ static const struct { } }; -static ssize_t utf8len(const struct utf8data *data, const char *s) +static ssize_t utf8len(const struct unicode_map *um, enum utf8_normalization n, + const char *s) { - return utf8nlen(data, s, (size_t)-1); + return utf8nlen(um, n, s, (size_t)-1); } -static int utf8cursor(struct utf8cursor *u8c, const struct utf8data *data, - const char *s) +static int utf8cursor(struct utf8cursor *u8c, const struct unicode_map *um, + enum utf8_normalization n, const char *s) { - return utf8ncursor(u8c, data, s, (unsigned int)-1); + return utf8ncursor(u8c, um, n, s, (unsigned int)-1); } -static void check_utf8_nfdi(void) +static void check_utf8_nfdi(struct unicode_map *um) { int i; struct utf8cursor u8c; - const struct utf8data *data; - - data = utf8nfdi(UNICODE_AGE(latest_maj, latest_min, latest_rev)); - if (!data) { - pr_err("%s: Unable to load utf8-%d.%d.%d. Skipping.\n", - __func__, latest_maj, latest_min, latest_rev); - return; - } for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) { int len = strlen(nfdi_test_data[i].str); @@ -190,10 +181,11 @@ static void check_utf8_nfdi(void) int j = 0; unsigned char c; - test((utf8len(data, nfdi_test_data[i].str) == nlen)); - test((utf8nlen(data, nfdi_test_data[i].str, len) == nlen)); + test((utf8len(um, UTF8_NFDI, nfdi_test_data[i].str) == nlen)); + test((utf8nlen(um, UTF8_NFDI, nfdi_test_data[i].str, len) == + nlen)); - if (utf8cursor(&u8c, data, nfdi_test_data[i].str) < 0) + if (utf8cursor(&u8c, um, UTF8_NFDI, nfdi_test_data[i].str) < 0) pr_err("can't create cursor\n"); while ((c = utf8byte(&u8c)) > 0) { @@ -207,18 +199,10 @@ static void check_utf8_nfdi(void) } } -static void check_utf8_nfdicf(void) +static void check_utf8_nfdicf(struct unicode_map *um) { int i; struct utf8cursor u8c; - const struct utf8data *data; - - data = utf8nfdicf(UNICODE_AGE(latest_maj, latest_min, latest_rev)); - if (!data) { - pr_err("%s: Unable to load utf8-%d.%d.%d. Skipping.\n", - __func__, latest_maj, latest_min, latest_rev); - return; - } for (i = 0; i < ARRAY_SIZE(nfdicf_test_data); i++) { int len = strlen(nfdicf_test_data[i].str); @@ -226,10 +210,13 @@ static void check_utf8_nfdicf(void) int j = 0; unsigned char c; - test((utf8len(data, nfdicf_test_data[i].str) == nlen)); - test((utf8nlen(data, nfdicf_test_data[i].str, len) == nlen)); + test((utf8len(um, UTF8_NFDICF, nfdicf_test_data[i].str) == + nlen)); + test((utf8nlen(um, UTF8_NFDICF, nfdicf_test_data[i].str, len) == + nlen)); - if (utf8cursor(&u8c, data, nfdicf_test_data[i].str) < 0) + if (utf8cursor(&u8c, um, UTF8_NFDICF, + nfdicf_test_data[i].str) < 0) pr_err("can't create cursor\n"); while ((c = utf8byte(&u8c)) > 0) { @@ -243,16 +230,9 @@ static void check_utf8_nfdicf(void) } } -static void check_utf8_comparisons(void) +static void check_utf8_comparisons(struct unicode_map *table) { int i; - struct unicode_map *table = utf8_load(UNICODE_AGE(12, 1, 0)); - - if (IS_ERR(table)) { - pr_err("%s: Unable to load utf8 %d.%d.%d. Skipping.\n", - __func__, latest_maj, latest_min, latest_rev); - return; - } for (i = 0; i < ARRAY_SIZE(nfdi_test_data); i++) { const struct qstr s1 = {.name = nfdi_test_data[i].str, @@ -273,8 +253,6 @@ static void check_utf8_comparisons(void) test_f(!utf8_strncasecmp(table, &s1, &s2), "%s %s comparison mismatch\n", s1.name, s2.name); } - - utf8_unload(table); } static void check_supported_versions(void) @@ -286,8 +264,7 @@ static void check_supported_versions(void) test(utf8version_is_supported(UNICODE_AGE(9, 0, 0))); /* Unicode 1x.0.0 (the latest version) should be supported. */ - test(utf8version_is_supported( - UNICODE_AGE(latest_maj, latest_min, latest_rev))); + test(utf8version_is_supported(UTF8_LATEST)); /* Next versions don't exist. */ test(!utf8version_is_supported(UNICODE_AGE(13, 0, 0))); @@ -297,19 +274,28 @@ static void check_supported_versions(void) static int __init init_test_ucd(void) { + struct unicode_map *um; + failed_tests = 0; total_tests = 0; + um = utf8_load(UTF8_LATEST); + if (IS_ERR(um)) { + pr_err("%s: Unable to load utf8 table.\n", __func__); + return PTR_ERR(um); + } + check_supported_versions(); - check_utf8_nfdi(); - check_utf8_nfdicf(); - check_utf8_comparisons(); + check_utf8_nfdi(um); + check_utf8_nfdicf(um); + check_utf8_comparisons(um); if (!failed_tests) pr_info("All %u tests passed\n", total_tests); else pr_err("%u out of %u tests failed\n", failed_tests, total_tests); + utf8_unload(um); return 0; } diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h index 736b6460a38c..206c89f0dbf7 100644 --- a/fs/unicode/utf8n.h +++ b/fs/unicode/utf8n.h @@ -39,7 +39,8 @@ extern const struct utf8data *utf8nfdicf(unsigned int maxage); * Returns 0 if only ignorable code points are present. * Returns -1 if the input is not valid UTF-8. */ -extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len); +ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n, + const char *s, size_t len); /* Needed in struct utf8cursor below. */ #define UTF8HANGULLEAF (12) @@ -48,7 +49,8 @@ extern ssize_t utf8nlen(const struct utf8data *data, const char *s, size_t len); * Cursor structure used by the normalizer. */ struct utf8cursor { - const struct utf8data *data; + const struct unicode_map *um; + enum utf8_normalization n; const char *s; const char *p; const char *ss; @@ -65,8 +67,8 @@ struct utf8cursor { * Returns 0 on success. * Returns -1 on failure. */ -extern int utf8ncursor(struct utf8cursor *u8c, const struct utf8data *data, - const char *s, size_t len); +int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um, + enum utf8_normalization n, const char *s, size_t len); /* * Get the next byte in the normalization. diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 77bb915fd1f0..526ca8b8391a 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -5,6 +5,8 @@ #include #include +struct utf8data; + #define UNICODE_MAJ_SHIFT 16 #define UNICODE_MIN_SHIFT 8 @@ -28,8 +30,25 @@ static inline u8 unicode_rev(unsigned int age) return age & 0xff; } +/* + * Two normalization forms are supported: + * 1) NFDI + * - Apply unicode normalization form NFD. + * - Remove any Default_Ignorable_Code_Point. + * 2) NFDICF + * - Apply unicode normalization form NFD. + * - Remove any Default_Ignorable_Code_Point. + * - Apply a full casefold (C + F). + */ +enum utf8_normalization { + UTF8_NFDI = 0, + UTF8_NFDICF, + UTF8_NMAX, +}; + struct unicode_map { unsigned int version; + const struct utf8data *ntab[UTF8_NMAX]; }; int utf8_validate(const struct unicode_map *um, const struct qstr *str); -- cgit v1.2.3 From bf2928c7a284e31f9f91a004b5dca09c522157c0 Mon Sep 17 00:00:00 2001 From: Heiner Kallweit Date: Fri, 10 Sep 2021 08:22:06 +0200 Subject: PCI/VPD: Add pci_read/write_vpd_any() In certain cases we need a variant of pci_read_vpd()/pci_write_vpd() that does not check against dev->vpd.len. Such cases are: - Reading VPD if dev->vpd.len isn't set yet (in pci_vpd_size()) - Devices that map non-VPD information to arbitrary places in VPD address space (example: Chelsio T3 EEPROM write-protect flag) Therefore add pci_read_vpd_any() and pci_write_vpd_any() that check against PCI_VPD_MAX_SIZE only. Link: https://lore.kernel.org/r/93ecce28-a158-f02a-d134-8afcaced8efe@gmail.com Signed-off-by: Heiner Kallweit Signed-off-by: Bjorn Helgaas Acked-by: Jakub Kicinski --- drivers/pci/vpd.c | 72 +++++++++++++++++++++++++++++++++++++---------------- include/linux/pci.h | 2 ++ 2 files changed, 52 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 4be24890132e..0a804715d98e 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -156,9 +156,10 @@ static int pci_vpd_wait(struct pci_dev *dev, bool set) } static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, - void *arg) + void *arg, bool check_size) { struct pci_vpd *vpd = &dev->vpd; + unsigned int max_len = check_size ? vpd->len : PCI_VPD_MAX_SIZE; int ret = 0; loff_t end = pos + count; u8 *buf = arg; @@ -169,11 +170,11 @@ static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, if (pos < 0) return -EINVAL; - if (pos > vpd->len) + if (pos >= max_len) return 0; - if (end > vpd->len) { - end = vpd->len; + if (end > max_len) { + end = max_len; count = end - pos; } @@ -217,9 +218,10 @@ static ssize_t pci_vpd_read(struct pci_dev *dev, loff_t pos, size_t count, } static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, - const void *arg) + const void *arg, bool check_size) { struct pci_vpd *vpd = &dev->vpd; + unsigned int max_len = check_size ? vpd->len : PCI_VPD_MAX_SIZE; const u8 *buf = arg; loff_t end = pos + count; int ret = 0; @@ -230,7 +232,7 @@ static ssize_t pci_vpd_write(struct pci_dev *dev, loff_t pos, size_t count, if (pos < 0 || (pos & 3) || (count & 3)) return -EINVAL; - if (end > vpd->len) + if (end > max_len) return -EINVAL; if (mutex_lock_killable(&vpd->lock)) @@ -381,6 +383,24 @@ static int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, return -ENOENT; } +static ssize_t __pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf, + bool check_size) +{ + ssize_t ret; + + if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) { + dev = pci_get_func0_dev(dev); + if (!dev) + return -ENODEV; + + ret = pci_vpd_read(dev, pos, count, buf, check_size); + pci_dev_put(dev); + return ret; + } + + return pci_vpd_read(dev, pos, count, buf, check_size); +} + /** * pci_read_vpd - Read one entry from Vital Product Data * @dev: PCI device struct @@ -389,6 +409,20 @@ static int pci_vpd_find_info_keyword(const u8 *buf, unsigned int off, * @buf: pointer to where to store result */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf) +{ + return __pci_read_vpd(dev, pos, count, buf, true); +} +EXPORT_SYMBOL(pci_read_vpd); + +/* Same, but allow to access any address */ +ssize_t pci_read_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, void *buf) +{ + return __pci_read_vpd(dev, pos, count, buf, false); +} +EXPORT_SYMBOL(pci_read_vpd_any); + +static ssize_t __pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, + const void *buf, bool check_size) { ssize_t ret; @@ -397,14 +431,13 @@ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf) if (!dev) return -ENODEV; - ret = pci_vpd_read(dev, pos, count, buf); + ret = pci_vpd_write(dev, pos, count, buf, check_size); pci_dev_put(dev); return ret; } - return pci_vpd_read(dev, pos, count, buf); + return pci_vpd_write(dev, pos, count, buf, check_size); } -EXPORT_SYMBOL(pci_read_vpd); /** * pci_write_vpd - Write entry to Vital Product Data @@ -415,22 +448,17 @@ EXPORT_SYMBOL(pci_read_vpd); */ ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf) { - ssize_t ret; - - if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) { - dev = pci_get_func0_dev(dev); - if (!dev) - return -ENODEV; - - ret = pci_vpd_write(dev, pos, count, buf); - pci_dev_put(dev); - return ret; - } - - return pci_vpd_write(dev, pos, count, buf); + return __pci_write_vpd(dev, pos, count, buf, true); } EXPORT_SYMBOL(pci_write_vpd); +/* Same, but allow to access any address */ +ssize_t pci_write_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, const void *buf) +{ + return __pci_write_vpd(dev, pos, count, buf, false); +} +EXPORT_SYMBOL(pci_write_vpd_any); + int pci_vpd_find_ro_info_keyword(const void *buf, unsigned int len, const char *kw, unsigned int *size) { diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..9649bd9e468d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1350,6 +1350,8 @@ void pci_unlock_rescan_remove(void); /* Vital Product Data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); +ssize_t pci_read_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, void *buf); +ssize_t pci_write_vpd_any(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); /* Helper functions for low-level code (drivers/pci/setup-[bus,res].c) */ resource_size_t pcibios_retrieve_fw_addr(struct pci_dev *dev, int idx); -- cgit v1.2.3 From f614fb60a1983819e83796198de2b607fba75e99 Mon Sep 17 00:00:00 2001 From: Wenbin Mei Date: Fri, 17 Sep 2021 20:48:02 +0800 Subject: mmc: core: Add host specific tuning support for eMMC HS400 mode This adds a ->execute_hs400_tuning() host callback to enable optional support for host specific tuning for eMMC HS400 mode. Additionally, share mmc_get_ext_csd() through the public host headerfile, to allow it to be used by the host drivers, which is needed to support the HS400 tuning. Signed-off-by: Wenbin Mei Link: https://lore.kernel.org/r/20210917124803.22871-3-wenbin.mei@mediatek.com Signed-off-by: Ulf Hansson --- drivers/mmc/core/mmc.c | 8 ++++++++ drivers/mmc/core/mmc_ops.h | 1 - include/linux/mmc/host.h | 4 ++++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 29e58ffae379..b1c1716dacf0 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1224,6 +1224,14 @@ static int mmc_select_hs400(struct mmc_card *card) mmc_set_timing(host, MMC_TIMING_MMC_HS400); mmc_set_bus_speed(card); + if (host->ops->execute_hs400_tuning) { + mmc_retune_disable(host); + err = host->ops->execute_hs400_tuning(host, card); + mmc_retune_enable(host); + if (err) + goto out_err; + } + if (host->ops->hs400_complete) host->ops->hs400_complete(host); diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h index ae25ffc2e870..e5e94567a9a9 100644 --- a/drivers/mmc/core/mmc_ops.h +++ b/drivers/mmc/core/mmc_ops.h @@ -38,7 +38,6 @@ int mmc_spi_read_ocr(struct mmc_host *host, int highcap, u32 *ocrp); int mmc_spi_set_crc(struct mmc_host *host, int use_crc); int mmc_bus_test(struct mmc_card *card, u8 bus_width); int mmc_can_ext_csd(struct mmc_card *card); -int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); int mmc_switch_status(struct mmc_card *card, bool crc_err_fatal); bool mmc_prepare_busy_cmd(struct mmc_host *host, struct mmc_command *cmd, unsigned int timeout_ms); diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0c0c9a0fdf57..b6c082e2664c 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -162,6 +162,9 @@ struct mmc_host_ops { /* Prepare HS400 target operating frequency depending host driver */ int (*prepare_hs400_tuning)(struct mmc_host *host, struct mmc_ios *ios); + /* Execute HS400 tuning depending host driver */ + int (*execute_hs400_tuning)(struct mmc_host *host, struct mmc_card *card); + /* Prepare switch to DDR during the HS400 init sequence */ int (*hs400_prepare_ddr)(struct mmc_host *host); @@ -634,5 +637,6 @@ static inline enum dma_data_direction mmc_get_dma_dir(struct mmc_data *data) int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error); int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode); +int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd); #endif /* LINUX_MMC_HOST_H */ -- cgit v1.2.3 From 0ae93b99beb283438aa571a6add4eab0c077d576 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Thu, 7 Oct 2021 16:17:24 -0400 Subject: SUNRPC: Simplify the SVC dispatch code path Micro-optimization: The last user of the generic SVC dispatch code path has been removed, so svc_process_common() can be simplified. This declutters the hot path so that the by-far most common case (a dispatch function exists) is made the /only/ path. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- include/linux/sunrpc/svc.h | 5 +---- net/sunrpc/svc.c | 51 ++-------------------------------------------- 2 files changed, 3 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6263410c948a..4205a6ef4770 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -443,10 +443,7 @@ struct svc_version { /* Need xprt with congestion control */ bool vs_need_cong_ctrl; - /* Override dispatch function (e.g. when caching replies). - * A return value of 0 means drop the request. - * vs_dispatch == NULL means use default dispatcher. - */ + /* Dispatch function */ int (*vs_dispatch)(struct svc_rqst *, __be32 *); }; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 08ca797bb8a4..e0dd6e6a4602 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1186,45 +1186,6 @@ void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) static __printf(2,3) void svc_printk(struct svc_rqst *rqstp, const char *fmt, ...) {} #endif -static int -svc_generic_dispatch(struct svc_rqst *rqstp, __be32 *statp) -{ - struct kvec *argv = &rqstp->rq_arg.head[0]; - struct kvec *resv = &rqstp->rq_res.head[0]; - const struct svc_procedure *procp = rqstp->rq_procinfo; - - /* - * Decode arguments - * XXX: why do we ignore the return value? - */ - if (procp->pc_decode && - !procp->pc_decode(rqstp, argv->iov_base)) { - *statp = rpc_garbage_args; - return 1; - } - - *statp = procp->pc_func(rqstp); - - if (*statp == rpc_drop_reply || - test_bit(RQ_DROPME, &rqstp->rq_flags)) - return 0; - - if (rqstp->rq_auth_stat != rpc_auth_ok) - return 1; - - if (*statp != rpc_success) - return 1; - - /* Encode reply */ - if (procp->pc_encode && - !procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) { - dprintk("svc: failed to encode reply\n"); - /* serv->sv_stats->rpcsystemerr++; */ - *statp = rpc_system_err; - } - return 1; -} - __be32 svc_generic_init_request(struct svc_rqst *rqstp, const struct svc_program *progp, @@ -1392,16 +1353,8 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) svc_reserve_auth(rqstp, procp->pc_xdrressize<<2); /* Call the function that processes the request. */ - if (!process.dispatch) { - if (!svc_generic_dispatch(rqstp, statp)) - goto release_dropit; - if (*statp == rpc_garbage_args) - goto err_garbage; - } else { - dprintk("svc: calling dispatcher\n"); - if (!process.dispatch(rqstp, statp)) - goto release_dropit; /* Release reply info */ - } + if (!process.dispatch(rqstp, statp)) + goto release_dropit; if (rqstp->rq_auth_stat != rpc_auth_ok) goto err_release_bad_auth; -- cgit v1.2.3 From 2b3d047870120bcd46d7cc257d19ff49328fd585 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Sep 2021 09:00:05 +0200 Subject: unicode: Add utf8-data module utf8data.h contains a large database table which is an auto-generated decodification trie for the unicode normalization functions. Allow building it into a separate module. Based on a patch from Shreeya Patel . Signed-off-by: Christoph Hellwig Signed-off-by: Gabriel Krisman Bertazi --- fs/unicode/Kconfig | 13 +- fs/unicode/Makefile | 13 +- fs/unicode/mkutf8data.c | 24 +- fs/unicode/utf8-core.c | 39 +- fs/unicode/utf8-norm.c | 48 +- fs/unicode/utf8-selftest.c | 16 +- fs/unicode/utf8data.c_shipped | 4123 +++++++++++++++++++++++++++++++++++++++++ fs/unicode/utf8data.h_shipped | 4109 ---------------------------------------- fs/unicode/utf8n.h | 40 +- include/linux/unicode.h | 2 + 10 files changed, 4231 insertions(+), 4196 deletions(-) create mode 100644 fs/unicode/utf8data.c_shipped delete mode 100644 fs/unicode/utf8data.h_shipped (limited to 'include/linux') diff --git a/fs/unicode/Kconfig b/fs/unicode/Kconfig index 2c27b9a5cd6c..610d7bc05d6e 100644 --- a/fs/unicode/Kconfig +++ b/fs/unicode/Kconfig @@ -8,7 +8,16 @@ config UNICODE Say Y here to enable UTF-8 NFD normalization and NFD+CF casefolding support. +config UNICODE_UTF8_DATA + tristate "UTF-8 normalization and casefolding tables" + depends on UNICODE + default UNICODE + help + This contains a large table of case foldings, which can be loaded as + a separate module if you say M here. To be on the safe side stick + to the default of Y. Saying N here makes no sense, if you do not want + utf8 casefolding support, disable CONFIG_UNICODE instead. + config UNICODE_NORMALIZATION_SELFTEST tristate "Test UTF-8 normalization support" - depends on UNICODE - default n + depends on UNICODE_UTF8_DATA diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index b88aecc86550..2f9d9188852b 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -2,14 +2,15 @@ obj-$(CONFIG_UNICODE) += unicode.o obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o +obj-$(CONFIG_UNICODE_UTF8_DATA) += utf8data.o unicode-y := utf8-norm.o utf8-core.o -$(obj)/utf8-norm.o: $(obj)/utf8data.h +$(obj)/utf8-data.o: $(obj)/utf8data.c -# In the normal build, the checked-in utf8data.h is just shipped. +# In the normal build, the checked-in utf8data.c is just shipped. # -# To generate utf8data.h from UCD, put *.txt files in this directory +# To generate utf8data.c from UCD, put *.txt files in this directory # and pass REGENERATE_UTF8DATA=1 from the command line. ifdef REGENERATE_UTF8DATA @@ -24,15 +25,15 @@ quiet_cmd_utf8data = GEN $@ -t $(srctree)/$(src)/NormalizationTest.txt \ -o $@ -$(obj)/utf8data.h: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE +$(obj)/utf8data.c: $(obj)/mkutf8data $(filter %.txt, $(cmd_utf8data)) FORCE $(call if_changed,utf8data) else -$(obj)/utf8data.h: $(src)/utf8data.h_shipped FORCE +$(obj)/utf8data.c: $(src)/utf8data.c_shipped FORCE $(call if_changed,shipped) endif -targets += utf8data.h +targets += utf8data.c hostprogs += mkutf8data diff --git a/fs/unicode/mkutf8data.c b/fs/unicode/mkutf8data.c index ff2025ac5a32..bc1a7c8b5c8d 100644 --- a/fs/unicode/mkutf8data.c +++ b/fs/unicode/mkutf8data.c @@ -3287,12 +3287,10 @@ static void write_file(void) open_fail(utf8_name, errno); fprintf(file, "/* This file is generated code, do not edit. */\n"); - fprintf(file, "#ifndef __INCLUDED_FROM_UTF8NORM_C__\n"); - fprintf(file, "#error Only nls_utf8-norm.c should include this file.\n"); - fprintf(file, "#endif\n"); fprintf(file, "\n"); - fprintf(file, "static const unsigned int utf8vers = %#x;\n", - unicode_maxage); + fprintf(file, "#include \n"); + fprintf(file, "#include \n"); + fprintf(file, "#include \"utf8n.h\"\n"); fprintf(file, "\n"); fprintf(file, "static const unsigned int utf8agetab[] = {\n"); for (i = 0; i != ages_count; i++) @@ -3339,6 +3337,22 @@ static void write_file(void) fprintf(file, "\n"); } fprintf(file, "};\n"); + fprintf(file, "\n"); + fprintf(file, "struct utf8data_table utf8_data_table = {\n"); + fprintf(file, "\t.utf8agetab = utf8agetab,\n"); + fprintf(file, "\t.utf8agetab_size = ARRAY_SIZE(utf8agetab),\n"); + fprintf(file, "\n"); + fprintf(file, "\t.utf8nfdicfdata = utf8nfdicfdata,\n"); + fprintf(file, "\t.utf8nfdicfdata_size = ARRAY_SIZE(utf8nfdicfdata),\n"); + fprintf(file, "\n"); + fprintf(file, "\t.utf8nfdidata = utf8nfdidata,\n"); + fprintf(file, "\t.utf8nfdidata_size = ARRAY_SIZE(utf8nfdidata),\n"); + fprintf(file, "\n"); + fprintf(file, "\t.utf8data = utf8data,\n"); + fprintf(file, "};\n"); + fprintf(file, "EXPORT_SYMBOL_GPL(utf8_data_table);"); + fprintf(file, "\n"); + fprintf(file, "MODULE_LICENSE(\"GPL v2\");\n"); fclose(file); } diff --git a/fs/unicode/utf8-core.c b/fs/unicode/utf8-core.c index d9f713d38c0a..67aaadc3ab07 100644 --- a/fs/unicode/utf8-core.c +++ b/fs/unicode/utf8-core.c @@ -160,25 +160,45 @@ int utf8_normalize(const struct unicode_map *um, const struct qstr *str, } EXPORT_SYMBOL(utf8_normalize); +static const struct utf8data *find_table_version(const struct utf8data *table, + size_t nr_entries, unsigned int version) +{ + size_t i = nr_entries - 1; + + while (version < table[i].maxage) + i--; + if (version > table[i].maxage) + return NULL; + return &table[i]; +} + struct unicode_map *utf8_load(unsigned int version) { struct unicode_map *um; - if (!utf8version_is_supported(version)) - return ERR_PTR(-EINVAL); - um = kzalloc(sizeof(struct unicode_map), GFP_KERNEL); if (!um) return ERR_PTR(-ENOMEM); um->version = version; - um->ntab[UTF8_NFDI] = utf8nfdi(version); - if (!um->ntab[UTF8_NFDI]) + + um->tables = symbol_request(utf8_data_table); + if (!um->tables) goto out_free_um; - um->ntab[UTF8_NFDICF] = utf8nfdicf(version); + + if (!utf8version_is_supported(um, version)) + goto out_symbol_put; + um->ntab[UTF8_NFDI] = find_table_version(um->tables->utf8nfdidata, + um->tables->utf8nfdidata_size, um->version); + if (!um->ntab[UTF8_NFDI]) + goto out_symbol_put; + um->ntab[UTF8_NFDICF] = find_table_version(um->tables->utf8nfdicfdata, + um->tables->utf8nfdicfdata_size, um->version); if (!um->ntab[UTF8_NFDICF]) - goto out_free_um; + goto out_symbol_put; return um; +out_symbol_put: + symbol_put(um->tables); out_free_um: kfree(um); return ERR_PTR(-EINVAL); @@ -187,7 +207,10 @@ EXPORT_SYMBOL(utf8_load); void utf8_unload(struct unicode_map *um) { - kfree(um); + if (um) { + symbol_put(utf8_data_table); + kfree(um); + } } EXPORT_SYMBOL(utf8_unload); diff --git a/fs/unicode/utf8-norm.c b/fs/unicode/utf8-norm.c index 7c1f28ab31a8..829c7e2ad764 100644 --- a/fs/unicode/utf8-norm.c +++ b/fs/unicode/utf8-norm.c @@ -6,21 +6,12 @@ #include "utf8n.h" -struct utf8data { - unsigned int maxage; - unsigned int offset; -}; - -#define __INCLUDED_FROM_UTF8NORM_C__ -#include "utf8data.h" -#undef __INCLUDED_FROM_UTF8NORM_C__ - -int utf8version_is_supported(unsigned int version) +int utf8version_is_supported(const struct unicode_map *um, unsigned int version) { - int i = ARRAY_SIZE(utf8agetab) - 1; + int i = um->tables->utf8agetab_size - 1; - while (i >= 0 && utf8agetab[i] != 0) { - if (version == utf8agetab[i]) + while (i >= 0 && um->tables->utf8agetab[i] != 0) { + if (version == um->tables->utf8agetab[i]) return 1; i--; } @@ -161,7 +152,7 @@ typedef const unsigned char utf8trie_t; * underlying datatype: unsigned char. * * leaf[0]: The unicode version, stored as a generation number that is - * an index into utf8agetab[]. With this we can filter code + * an index into ->utf8agetab[]. With this we can filter code * points based on the unicode version in which they were * defined. The CCC of a non-defined code point is 0. * leaf[1]: Canonical Combining Class. During normalization, we need @@ -313,7 +304,7 @@ static utf8leaf_t *utf8nlookup(const struct unicode_map *um, enum utf8_normalization n, unsigned char *hangul, const char *s, size_t len) { - utf8trie_t *trie = utf8data + um->ntab[n]->offset; + utf8trie_t *trie = um->tables->utf8data + um->ntab[n]->offset; int offlen; int offset; int mask; @@ -404,7 +395,8 @@ ssize_t utf8nlen(const struct unicode_map *um, enum utf8_normalization n, leaf = utf8nlookup(um, n, hangul, s, len); if (!leaf) return -1; - if (utf8agetab[LEAF_GEN(leaf)] > um->ntab[n]->maxage) + if (um->tables->utf8agetab[LEAF_GEN(leaf)] > + um->ntab[n]->maxage) ret += utf8clen(s); else if (LEAF_CCC(leaf) == DECOMPOSE) ret += strlen(LEAF_STR(leaf)); @@ -520,7 +512,7 @@ int utf8byte(struct utf8cursor *u8c) ccc = LEAF_CCC(leaf); /* Characters that are too new have CCC 0. */ - if (utf8agetab[LEAF_GEN(leaf)] > + if (u8c->um->tables->utf8agetab[LEAF_GEN(leaf)] > u8c->um->ntab[u8c->n]->maxage) { ccc = STOPPER; } else if (ccc == DECOMPOSE) { @@ -597,25 +589,3 @@ ccc_mismatch: } } EXPORT_SYMBOL(utf8byte); - -const struct utf8data *utf8nfdi(unsigned int maxage) -{ - int i = ARRAY_SIZE(utf8nfdidata) - 1; - - while (maxage < utf8nfdidata[i].maxage) - i--; - if (maxage > utf8nfdidata[i].maxage) - return NULL; - return &utf8nfdidata[i]; -} - -const struct utf8data *utf8nfdicf(unsigned int maxage) -{ - int i = ARRAY_SIZE(utf8nfdicfdata) - 1; - - while (maxage < utf8nfdicfdata[i].maxage) - i--; - if (maxage > utf8nfdicfdata[i].maxage) - return NULL; - return &utf8nfdicfdata[i]; -} diff --git a/fs/unicode/utf8-selftest.c b/fs/unicode/utf8-selftest.c index cfa3832b75f4..eb2bbdd688d7 100644 --- a/fs/unicode/utf8-selftest.c +++ b/fs/unicode/utf8-selftest.c @@ -255,21 +255,21 @@ static void check_utf8_comparisons(struct unicode_map *table) } } -static void check_supported_versions(void) +static void check_supported_versions(struct unicode_map *um) { /* Unicode 7.0.0 should be supported. */ - test(utf8version_is_supported(UNICODE_AGE(7, 0, 0))); + test(utf8version_is_supported(um, UNICODE_AGE(7, 0, 0))); /* Unicode 9.0.0 should be supported. */ - test(utf8version_is_supported(UNICODE_AGE(9, 0, 0))); + test(utf8version_is_supported(um, UNICODE_AGE(9, 0, 0))); /* Unicode 1x.0.0 (the latest version) should be supported. */ - test(utf8version_is_supported(UTF8_LATEST)); + test(utf8version_is_supported(um, UTF8_LATEST)); /* Next versions don't exist. */ - test(!utf8version_is_supported(UNICODE_AGE(13, 0, 0))); - test(!utf8version_is_supported(UNICODE_AGE(0, 0, 0))); - test(!utf8version_is_supported(UNICODE_AGE(-1, -1, -1))); + test(!utf8version_is_supported(um, UNICODE_AGE(13, 0, 0))); + test(!utf8version_is_supported(um, UNICODE_AGE(0, 0, 0))); + test(!utf8version_is_supported(um, UNICODE_AGE(-1, -1, -1))); } static int __init init_test_ucd(void) @@ -285,7 +285,7 @@ static int __init init_test_ucd(void) return PTR_ERR(um); } - check_supported_versions(); + check_supported_versions(um); check_utf8_nfdi(um); check_utf8_nfdicf(um); check_utf8_comparisons(um); diff --git a/fs/unicode/utf8data.c_shipped b/fs/unicode/utf8data.c_shipped new file mode 100644 index 000000000000..d9b62901aa96 --- /dev/null +++ b/fs/unicode/utf8data.c_shipped @@ -0,0 +1,4123 @@ +/* This file is generated code, do not edit. */ + +#include +#include +#include "utf8n.h" + +static const unsigned int utf8agetab[] = { + 0, + 0x10100, + 0x20000, + 0x20100, + 0x30000, + 0x30100, + 0x30200, + 0x40000, + 0x40100, + 0x50000, + 0x50100, + 0x50200, + 0x60000, + 0x60100, + 0x60200, + 0x60300, + 0x70000, + 0x80000, + 0x90000, + 0xa0000, + 0xb0000, + 0xc0000, + 0xc0100 +}; + +static const struct utf8data utf8nfdicfdata[] = { + { 0, 0 }, + { 0x10100, 0 }, + { 0x20000, 0 }, + { 0x20100, 0 }, + { 0x30000, 0 }, + { 0x30100, 0 }, + { 0x30200, 1792 }, + { 0x40000, 3200 }, + { 0x40100, 3200 }, + { 0x50000, 3200 }, + { 0x50100, 3200 }, + { 0x50200, 3200 }, + { 0x60000, 3200 }, + { 0x60100, 3200 }, + { 0x60200, 3200 }, + { 0x60300, 3200 }, + { 0x70000, 3200 }, + { 0x80000, 3200 }, + { 0x90000, 3200 }, + { 0xa0000, 3200 }, + { 0xb0000, 3200 }, + { 0xc0000, 3200 }, + { 0xc0100, 3200 } +}; + +static const struct utf8data utf8nfdidata[] = { + { 0, 896 }, + { 0x10100, 896 }, + { 0x20000, 896 }, + { 0x20100, 896 }, + { 0x30000, 896 }, + { 0x30100, 896 }, + { 0x30200, 2496 }, + { 0x40000, 20736 }, + { 0x40100, 20736 }, + { 0x50000, 20736 }, + { 0x50100, 20736 }, + { 0x50200, 20736 }, + { 0x60000, 20736 }, + { 0x60100, 20736 }, + { 0x60200, 20736 }, + { 0x60300, 20736 }, + { 0x70000, 20736 }, + { 0x80000, 20736 }, + { 0x90000, 20736 }, + { 0xa0000, 20736 }, + { 0xb0000, 20736 }, + { 0xc0000, 20736 }, + { 0xc0100, 20736 } +}; + +static const unsigned char utf8data[64256] = { + /* nfdicf_30100 */ + 0xd7,0x07,0x66,0x84,0x0c,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x99,0x1a,0xe3,0x63,0x15, + 0xe2,0x4c,0x0e,0xc1,0xe0,0x4e,0x0d,0xcf,0x86,0x65,0x2d,0x0d,0x01,0x00,0xd4,0xb8, + 0xd3,0x27,0xe2,0x89,0xa3,0xe1,0xce,0x35,0xe0,0x2c,0x22,0xcf,0x86,0xc5,0xe4,0x15, + 0x6d,0xe3,0x60,0x68,0xe2,0xf6,0x65,0xe1,0x29,0x65,0xe0,0xee,0x64,0xcf,0x86,0xe5, + 0xb3,0x64,0x64,0x96,0x64,0x0b,0x00,0xd2,0x0e,0xe1,0xb5,0x3c,0xe0,0xba,0xa3,0xcf, + 0x86,0xcf,0x06,0x01,0x00,0xd1,0x0c,0xe0,0x1e,0xa9,0xcf,0x86,0xcf,0x06,0x02,0xff, + 0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01, + 0x00,0xe4,0xe1,0x45,0xe3,0x3b,0x45,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x87,0xad, + 0xd0,0x21,0xcf,0x86,0xe5,0x81,0xaa,0xe4,0x00,0xaa,0xe3,0xbf,0xa9,0xe2,0x9e,0xa9, + 0xe1,0x8d,0xa9,0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4, + 0x00,0xcf,0x86,0xe5,0x63,0xac,0xd4,0x19,0xe3,0xa2,0xab,0xe2,0x81,0xab,0xe1,0x70, + 0xab,0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3, + 0x09,0xac,0xe2,0xe8,0xab,0xe1,0xd7,0xab,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00, + 0x01,0xff,0xe9,0x9b,0xbb,0x00,0x83,0xe2,0x19,0xfa,0xe1,0xf2,0xf6,0xe0,0x6f,0xf5, + 0xcf,0x86,0xd5,0x31,0xc4,0xe3,0x54,0x4e,0xe2,0xf5,0x4c,0xe1,0xa4,0xcc,0xe0,0x9c, + 0x4b,0xcf,0x86,0xe5,0x8e,0x49,0xe4,0xaf,0x46,0xe3,0x11,0xbd,0xe2,0x68,0xbc,0xe1, + 0x43,0xbc,0xe0,0x1c,0xbc,0xcf,0x86,0xe5,0xe9,0xbb,0x94,0x07,0x63,0xd4,0xbb,0x07, + 0x00,0x07,0x00,0xe4,0xdb,0xf4,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b, + 0xe1,0xea,0xe1,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xd9,0xe2,0xcf,0x86, + 0xe5,0x9e,0xe2,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xd9,0xe2,0xcf,0x06, + 0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x74,0xf4,0xe3,0x5d,0xf3, + 0xd2,0xa0,0xe1,0x13,0xe7,0xd0,0x21,0xcf,0x86,0xe5,0x14,0xe4,0xe4,0x90,0xe3,0xe3, + 0x4e,0xe3,0xe2,0x2d,0xe3,0xe1,0x1b,0xe3,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00, + 0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x70,0xe5,0xe3,0x2f,0xe5, + 0xe2,0x0e,0xe5,0xe1,0xfd,0xe4,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff, + 0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xf7,0xe5,0xe1,0xe6,0xe5,0x10,0x09, + 0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x17, + 0xe6,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac, + 0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x5d,0xe6,0xd2,0x14,0xe1,0x2c,0xe6, + 0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1, + 0x38,0xe6,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00, + 0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x8d,0xeb,0xd4,0x19,0xe3,0xc6,0xea,0xe2,0xa4, + 0xea,0xe1,0x93,0xea,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5, + 0xb7,0x00,0xd3,0x18,0xe2,0x10,0xeb,0xe1,0xff,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3, + 0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x28,0xeb,0x10, + 0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10, + 0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08, + 0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0x2a, + 0xed,0xd4,0x1a,0xe3,0x62,0xec,0xe2,0x48,0xec,0xe1,0x35,0xec,0x10,0x08,0x05,0xff, + 0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0xaa,0xec, + 0xe1,0x98,0xec,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3, + 0x00,0xd2,0x13,0xe1,0xc6,0xec,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff, + 0xe7,0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05, + 0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05, + 0xff,0xe7,0xaa,0xae,0x00,0xe0,0xdc,0xef,0xcf,0x86,0xd5,0x1d,0xe4,0x51,0xee,0xe3, + 0x0d,0xee,0xe2,0xeb,0xed,0xe1,0xda,0xed,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f, + 0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xf8,0xee,0xe2,0xd4,0xee,0xe1, + 0xc3,0xee,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00, + 0xd3,0x18,0xe2,0x43,0xef,0xe1,0x32,0xef,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1, + 0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x5b,0xef,0x10,0x08,0x05, + 0xff,0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05, + 0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8, + 0x9e,0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + /* nfdi_30100 */ + 0x57,0x04,0x01,0x00,0xc6,0xd5,0x16,0xe4,0xc2,0x59,0xe3,0xfb,0x54,0xe2,0x74,0x4f, + 0xc1,0xe0,0xa0,0x4d,0xcf,0x86,0x65,0x84,0x4d,0x01,0x00,0xd4,0xb8,0xd3,0x27,0xe2, + 0x0c,0xa0,0xe1,0xdf,0x8d,0xe0,0x39,0x71,0xcf,0x86,0xc5,0xe4,0x98,0x69,0xe3,0xe3, + 0x64,0xe2,0x79,0x62,0xe1,0xac,0x61,0xe0,0x71,0x61,0xcf,0x86,0xe5,0x36,0x61,0x64, + 0x19,0x61,0x0b,0x00,0xd2,0x0e,0xe1,0xc2,0xa0,0xe0,0x3d,0xa0,0xcf,0x86,0xcf,0x06, + 0x01,0x00,0xd1,0x0c,0xe0,0xa1,0xa5,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd0,0x08, + 0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xe4,0x9e, + 0xb6,0xe3,0x18,0xae,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x0a,0xaa,0xd0,0x21,0xcf, + 0x86,0xe5,0x04,0xa7,0xe4,0x83,0xa6,0xe3,0x42,0xa6,0xe2,0x21,0xa6,0xe1,0x10,0xa6, + 0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0xcf,0x86, + 0xe5,0xe6,0xa8,0xd4,0x19,0xe3,0x25,0xa8,0xe2,0x04,0xa8,0xe1,0xf3,0xa7,0x10,0x08, + 0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3,0x8c,0xa8,0xe2, + 0x6b,0xa8,0xe1,0x5a,0xa8,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9, + 0x9b,0xbb,0x00,0x83,0xe2,0x9c,0xf6,0xe1,0x75,0xf3,0xe0,0xf2,0xf1,0xcf,0x86,0xd5, + 0x31,0xc4,0xe3,0x6d,0xcc,0xe2,0x46,0xca,0xe1,0x27,0xc9,0xe0,0xb7,0xbf,0xcf,0x86, + 0xe5,0xaa,0xbb,0xe4,0xa3,0xba,0xe3,0x94,0xb9,0xe2,0xeb,0xb8,0xe1,0xc6,0xb8,0xe0, + 0x9f,0xb8,0xcf,0x86,0xe5,0x6c,0xb8,0x94,0x07,0x63,0x57,0xb8,0x07,0x00,0x07,0x00, + 0xe4,0x5e,0xf1,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1,0x6d,0xde, + 0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x5c,0xdf,0xcf,0x86,0xe5,0x21,0xdf, + 0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x5c,0xdf,0xcf,0x06,0x13,0x00,0xcf, + 0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0xf7,0xf0,0xe3,0xe0,0xef,0xd2,0xa0,0xe1, + 0x96,0xe3,0xd0,0x21,0xcf,0x86,0xe5,0x97,0xe0,0xe4,0x13,0xe0,0xe3,0xd1,0xdf,0xe2, + 0xb0,0xdf,0xe1,0x9e,0xdf,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4, + 0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xf3,0xe1,0xe3,0xb2,0xe1,0xe2,0x91,0xe1, + 0xe1,0x80,0xe1,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6, + 0x00,0xd4,0x34,0xd3,0x18,0xe2,0x7a,0xe2,0xe1,0x69,0xe2,0x10,0x09,0x05,0xff,0xf0, + 0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x9a,0xe2,0x91,0x11, + 0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05, + 0xff,0xe5,0xac,0xbe,0x00,0xe3,0xe0,0xe2,0xd2,0x14,0xe1,0xaf,0xe2,0x10,0x08,0x05, + 0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0xbb,0xe2,0x10, + 0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1,0xd5,0xd0, + 0x6a,0xcf,0x86,0xe5,0x10,0xe8,0xd4,0x19,0xe3,0x49,0xe7,0xe2,0x27,0xe7,0xe1,0x16, + 0xe7,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7,0x00,0xd3, + 0x18,0xe2,0x93,0xe7,0xe1,0x82,0xe7,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00, + 0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xab,0xe7,0x10,0x08,0x05,0xff, + 0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08,0x05,0xff, + 0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7, + 0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0xad,0xe9,0xd4,0x1a, + 0xe3,0xe5,0xe8,0xe2,0xcb,0xe8,0xe1,0xb8,0xe8,0x10,0x08,0x05,0xff,0xe7,0x9b,0xb4, + 0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x2d,0xe9,0xe1,0x1b,0xe9, + 0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0xd2,0x13, + 0xe1,0x49,0xe9,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80, + 0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff,0xf0,0xa5, + 0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff,0xe7,0xaa, + 0xae,0x00,0xe0,0x5f,0xec,0xcf,0x86,0xd5,0x1d,0xe4,0xd4,0xea,0xe3,0x90,0xea,0xe2, + 0x6e,0xea,0xe1,0x5d,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff, + 0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x7b,0xeb,0xe2,0x57,0xeb,0xe1,0x46,0xeb,0x10, + 0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3,0x18,0xe2, + 0xc6,0xeb,0xe1,0xb5,0xeb,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00,0x05,0xff, + 0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xde,0xeb,0x10,0x08,0x05,0xff,0xe8,0x9a, + 0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c, + 0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00, + 0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + /* nfdicf_30200 */ + 0xd7,0x07,0x66,0x84,0x05,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x99,0x13,0xe3,0x63,0x0e, + 0xe2,0x4c,0x07,0xc1,0xe0,0x4e,0x06,0xcf,0x86,0x65,0x2d,0x06,0x01,0x00,0xd4,0x2a, + 0xe3,0xd0,0x35,0xe2,0x88,0x9c,0xe1,0xcd,0x2e,0xe0,0x2b,0x1b,0xcf,0x86,0xc5,0xe4, + 0x14,0x66,0xe3,0x5f,0x61,0xe2,0xf5,0x5e,0xe1,0x28,0x5e,0xe0,0xed,0x5d,0xcf,0x86, + 0xe5,0xb2,0x5d,0x64,0x95,0x5d,0x0b,0x00,0x83,0xe2,0xa7,0xf3,0xe1,0x80,0xf0,0xe0, + 0xfd,0xee,0xcf,0x86,0xd5,0x31,0xc4,0xe3,0xe2,0x47,0xe2,0x83,0x46,0xe1,0x32,0xc6, + 0xe0,0x2a,0x45,0xcf,0x86,0xe5,0x1c,0x43,0xe4,0x3d,0x40,0xe3,0x9f,0xb6,0xe2,0xf6, + 0xb5,0xe1,0xd1,0xb5,0xe0,0xaa,0xb5,0xcf,0x86,0xe5,0x77,0xb5,0x94,0x07,0x63,0x62, + 0xb5,0x07,0x00,0x07,0x00,0xe4,0x69,0xee,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00, + 0xd2,0x0b,0xe1,0x78,0xdb,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x67,0xdc, + 0xcf,0x86,0xe5,0x2c,0xdc,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x67,0xdc, + 0xcf,0x06,0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x02,0xee,0xe3, + 0xeb,0xec,0xd2,0xa0,0xe1,0xa1,0xe0,0xd0,0x21,0xcf,0x86,0xe5,0xa2,0xdd,0xe4,0x1e, + 0xdd,0xe3,0xdc,0xdc,0xe2,0xbb,0xdc,0xe1,0xa9,0xdc,0x10,0x08,0x05,0xff,0xe4,0xb8, + 0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xfe,0xde,0xe3, + 0xbd,0xde,0xe2,0x9c,0xde,0xe1,0x8b,0xde,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00, + 0x05,0xff,0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0x85,0xdf,0xe1,0x74,0xdf, + 0x10,0x09,0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00, + 0xe2,0xa5,0xdf,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff, + 0xe5,0xac,0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0xeb,0xdf,0xd2,0x14,0xe1, + 0xba,0xdf,0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98, + 0x00,0xe1,0xc6,0xdf,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0, + 0xa2,0x00,0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x1b,0xe5,0xd4,0x19,0xe3,0x54,0xe4, + 0xe2,0x32,0xe4,0xe1,0x21,0xe4,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff, + 0xe6,0xb5,0xb7,0x00,0xd3,0x18,0xe2,0x9e,0xe4,0xe1,0x8d,0xe4,0x10,0x09,0x05,0xff, + 0xf0,0xa3,0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xb6, + 0xe4,0x10,0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1, + 0x11,0x10,0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00, + 0x10,0x08,0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86, + 0xe5,0xb8,0xe6,0xd4,0x1a,0xe3,0xf0,0xe5,0xe2,0xd6,0xe5,0xe1,0xc3,0xe5,0x10,0x08, + 0x05,0xff,0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2, + 0x38,0xe6,0xe1,0x26,0xe6,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4, + 0x83,0xa3,0x00,0xd2,0x13,0xe1,0x54,0xe6,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00, + 0x05,0xff,0xe7,0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc, + 0x00,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7, + 0x00,0x05,0xff,0xe7,0xaa,0xae,0x00,0xe0,0x6a,0xe9,0xcf,0x86,0xd5,0x1d,0xe4,0xdf, + 0xe7,0xe3,0x9b,0xe7,0xe2,0x79,0xe7,0xe1,0x68,0xe7,0x10,0x09,0x05,0xff,0xf0,0xa3, + 0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x86,0xe8,0xe2,0x62, + 0xe8,0xe1,0x51,0xe8,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f, + 0x8a,0x00,0xd3,0x18,0xe2,0xd1,0xe8,0xe1,0xc0,0xe8,0x10,0x09,0x05,0xff,0xf0,0xa6, + 0xbe,0xb1,0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xe9,0xe8,0x10, + 0x08,0x05,0xff,0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10, + 0x08,0x05,0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05, + 0xff,0xe8,0x9e,0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00, + /* nfdi_30200 */ + 0x57,0x04,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x82,0x53,0xe3,0xbb,0x4e,0xe2,0x34,0x49, + 0xc1,0xe0,0x60,0x47,0xcf,0x86,0x65,0x44,0x47,0x01,0x00,0xd4,0x2a,0xe3,0x1c,0x9a, + 0xe2,0xcb,0x99,0xe1,0x9e,0x87,0xe0,0xf8,0x6a,0xcf,0x86,0xc5,0xe4,0x57,0x63,0xe3, + 0xa2,0x5e,0xe2,0x38,0x5c,0xe1,0x6b,0x5b,0xe0,0x30,0x5b,0xcf,0x86,0xe5,0xf5,0x5a, + 0x64,0xd8,0x5a,0x0b,0x00,0x83,0xe2,0xea,0xf0,0xe1,0xc3,0xed,0xe0,0x40,0xec,0xcf, + 0x86,0xd5,0x31,0xc4,0xe3,0xbb,0xc6,0xe2,0x94,0xc4,0xe1,0x75,0xc3,0xe0,0x05,0xba, + 0xcf,0x86,0xe5,0xf8,0xb5,0xe4,0xf1,0xb4,0xe3,0xe2,0xb3,0xe2,0x39,0xb3,0xe1,0x14, + 0xb3,0xe0,0xed,0xb2,0xcf,0x86,0xe5,0xba,0xb2,0x94,0x07,0x63,0xa5,0xb2,0x07,0x00, + 0x07,0x00,0xe4,0xac,0xeb,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1, + 0xbb,0xd8,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xaa,0xd9,0xcf,0x86,0xe5, + 0x6f,0xd9,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xaa,0xd9,0xcf,0x06,0x13, + 0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x45,0xeb,0xe3,0x2e,0xea,0xd2, + 0xa0,0xe1,0xe4,0xdd,0xd0,0x21,0xcf,0x86,0xe5,0xe5,0xda,0xe4,0x61,0xda,0xe3,0x1f, + 0xda,0xe2,0xfe,0xd9,0xe1,0xec,0xd9,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05, + 0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x41,0xdc,0xe3,0x00,0xdc,0xe2, + 0xdf,0xdb,0xe1,0xce,0xdb,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5, + 0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xc8,0xdc,0xe1,0xb7,0xdc,0x10,0x09,0x05, + 0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0xe8,0xdc, + 0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88, + 0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x2e,0xdd,0xd2,0x14,0xe1,0xfd,0xdc,0x10, + 0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0x09, + 0xdd,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1, + 0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x5e,0xe2,0xd4,0x19,0xe3,0x97,0xe1,0xe2,0x75,0xe1, + 0xe1,0x64,0xe1,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7, + 0x00,0xd3,0x18,0xe2,0xe1,0xe1,0xe1,0xd0,0xe1,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd, + 0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xf9,0xe1,0x10,0x08, + 0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08, + 0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05, + 0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0xfb,0xe3, + 0xd4,0x1a,0xe3,0x33,0xe3,0xe2,0x19,0xe3,0xe1,0x06,0xe3,0x10,0x08,0x05,0xff,0xe7, + 0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x7b,0xe3,0xe1, + 0x69,0xe3,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00, + 0xd2,0x13,0xe1,0x97,0xe3,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7, + 0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff, + 0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff, + 0xe7,0xaa,0xae,0x00,0xe0,0xad,0xe6,0xcf,0x86,0xd5,0x1d,0xe4,0x22,0xe5,0xe3,0xde, + 0xe4,0xe2,0xbc,0xe4,0xe1,0xab,0xe4,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00, + 0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xc9,0xe5,0xe2,0xa5,0xe5,0xe1,0x94, + 0xe5,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3, + 0x18,0xe2,0x14,0xe6,0xe1,0x03,0xe6,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00, + 0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x2c,0xe6,0x10,0x08,0x05,0xff, + 0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, + 0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e, + 0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + /* nfdicf_c0100 */ + 0xd7,0xb0,0x56,0x04,0x01,0x00,0x95,0xa8,0xd4,0x5e,0xd3,0x2e,0xd2,0x16,0xd1,0x0a, + 0x10,0x04,0x01,0x00,0x01,0xff,0x61,0x00,0x10,0x06,0x01,0xff,0x62,0x00,0x01,0xff, + 0x63,0x00,0xd1,0x0c,0x10,0x06,0x01,0xff,0x64,0x00,0x01,0xff,0x65,0x00,0x10,0x06, + 0x01,0xff,0x66,0x00,0x01,0xff,0x67,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x06,0x01,0xff, + 0x68,0x00,0x01,0xff,0x69,0x00,0x10,0x06,0x01,0xff,0x6a,0x00,0x01,0xff,0x6b,0x00, + 0xd1,0x0c,0x10,0x06,0x01,0xff,0x6c,0x00,0x01,0xff,0x6d,0x00,0x10,0x06,0x01,0xff, + 0x6e,0x00,0x01,0xff,0x6f,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x06,0x01,0xff, + 0x70,0x00,0x01,0xff,0x71,0x00,0x10,0x06,0x01,0xff,0x72,0x00,0x01,0xff,0x73,0x00, + 0xd1,0x0c,0x10,0x06,0x01,0xff,0x74,0x00,0x01,0xff,0x75,0x00,0x10,0x06,0x01,0xff, + 0x76,0x00,0x01,0xff,0x77,0x00,0x92,0x16,0xd1,0x0c,0x10,0x06,0x01,0xff,0x78,0x00, + 0x01,0xff,0x79,0x00,0x10,0x06,0x01,0xff,0x7a,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0xc6,0xe5,0xf9,0x14,0xe4,0x6f,0x0d,0xe3,0x39,0x08,0xe2,0x22,0x01,0xc1,0xd0,0x24, + 0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x07,0x63,0xd8,0x43,0x01,0x00,0x93,0x13,0x52, + 0x04,0x01,0x00,0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xce,0xbc,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xe5,0xb3,0x44,0xd4,0x7f,0xd3,0x3f,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x07,0x01,0xff,0xc3, + 0xa6,0x00,0x01,0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x65,0xcc,0x80,0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, + 0x82,0x00,0x01,0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc, + 0x80,0x00,0x01,0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00, + 0x01,0xff,0x69,0xcc,0x88,0x00,0xd3,0x3b,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff, + 0xc3,0xb0,0x00,0x01,0xff,0x6e,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80, + 0x00,0x01,0xff,0x6f,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82, + 0x00,0x01,0xff,0x6f,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01, + 0x00,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff,0xc3,0xb8,0x00,0x01,0xff,0x75,0xcc, + 0x80,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x82,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x88,0x00,0x01,0xff,0x79,0xcc,0x81,0x00, + 0x10,0x07,0x01,0xff,0xc3,0xbe,0x00,0x01,0xff,0x73,0x73,0x00,0xe1,0xd4,0x03,0xe0, + 0xeb,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x61,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84,0x00,0x10,0x08,0x01,0xff, + 0x61,0xcc,0x86,0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x61,0xcc,0xa8,0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x63,0xcc, + 0x81,0x00,0x01,0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x63,0xcc,0x82,0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x63,0xcc, + 0x87,0x00,0x01,0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x63,0xcc, + 0x8c,0x00,0x01,0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x8c,0x00, + 0x01,0xff,0x64,0xcc,0x8c,0x00,0xd3,0x3b,0xd2,0x1b,0xd1,0x0b,0x10,0x07,0x01,0xff, + 0xc4,0x91,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x84,0x00,0x01,0xff,0x65, + 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x86,0x00,0x01,0xff,0x65, + 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0xa8,0x00,0x01,0xff,0x65, + 0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82, + 0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4, + 0x7b,0xd3,0x3b,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x87,0x00,0x01, + 0xff,0x67,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0xa7,0x00,0x01,0xff,0x67, + 0xcc,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x68,0xcc,0x82,0x00,0x01,0xff,0x68, + 0xcc,0x82,0x00,0x10,0x07,0x01,0xff,0xc4,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x69,0xcc,0x83,0x00,0x01,0xff,0x69,0xcc,0x83,0x00,0x10,0x08, + 0x01,0xff,0x69,0xcc,0x84,0x00,0x01,0xff,0x69,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x69,0xcc,0x86,0x00,0x01,0xff,0x69,0xcc,0x86,0x00,0x10,0x08,0x01,0xff, + 0x69,0xcc,0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8,0x00,0xd3,0x37,0xd2,0x17,0xd1,0x0c, + 0x10,0x08,0x01,0xff,0x69,0xcc,0x87,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc4,0xb3, + 0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6a,0xcc,0x82,0x00,0x01,0xff,0x6a, + 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x6b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7, + 0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6c,0xcc,0x81,0x00,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff,0x6c,0xcc,0xa7,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff,0x6c,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x6c,0xcc,0x8c,0x00,0x01,0xff,0xc5,0x80,0x00,0xcf,0x86,0xd5,0xed,0xd4,0x72, + 0xd3,0x37,0xd2,0x17,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc5,0x82,0x00,0x10, + 0x04,0x01,0x00,0x01,0xff,0x6e,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0x81,0x00,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa7, + 0x00,0x01,0xff,0x6e,0xcc,0x8c,0x00,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0x8c,0x00,0x01,0xff,0xca,0xbc,0x6e,0x00,0x10,0x07,0x01,0xff,0xc5,0x8b,0x00, + 0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc, + 0x84,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00, + 0xd3,0x3b,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01,0xff, + 0x6f,0xcc,0x8b,0x00,0x10,0x07,0x01,0xff,0xc5,0x93,0x00,0x01,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x72,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81,0x00,0x10,0x08,0x01, + 0xff,0x72,0xcc,0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x72,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x73,0xcc,0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x73,0xcc,0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x73, + 0xcc,0xa7,0x00,0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x7b,0xd3,0x3b,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x73,0xcc,0x8c,0x00,0x01,0xff,0x73,0xcc,0x8c,0x00,0x10, + 0x08,0x01,0xff,0x74,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x74,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c,0x00,0x10,0x07,0x01, + 0xff,0xc5,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc, + 0x83,0x00,0x01,0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x84,0x00, + 0x01,0xff,0x75,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x86,0x00, + 0x01,0xff,0x75,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x8a,0x00,0x01,0xff, + 0x75,0xcc,0x8a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc, + 0x8b,0x00,0x01,0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa8,0x00, + 0x01,0xff,0x75,0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x82,0x00, + 0x01,0xff,0x77,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x82,0x00,0x01,0xff, + 0x79,0xcc,0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x79,0xcc,0x88,0x00, + 0x01,0xff,0x7a,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff, + 0x7a,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff, + 0x7a,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0xff,0x73,0x00, + 0xe0,0x65,0x01,0xcf,0x86,0xd5,0xb4,0xd4,0x5a,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10, + 0x04,0x01,0x00,0x01,0xff,0xc9,0x93,0x00,0x10,0x07,0x01,0xff,0xc6,0x83,0x00,0x01, + 0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff, + 0xc9,0x94,0x00,0x01,0xff,0xc6,0x88,0x00,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x01,0x00, + 0x01,0xff,0xc9,0x96,0x00,0x10,0x07,0x01,0xff,0xc9,0x97,0x00,0x01,0xff,0xc6,0x8c, + 0x00,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xc7,0x9d,0x00,0x01,0xff,0xc9,0x99, + 0x00,0xd3,0x32,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0x9b,0x00,0x01,0xff, + 0xc6,0x92,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xa0,0x00,0xd1,0x0b,0x10,0x07, + 0x01,0xff,0xc9,0xa3,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc9,0xa9,0x00,0x01,0xff, + 0xc9,0xa8,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0x99,0x00,0x01,0x00, + 0x01,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0xaf,0x00,0x01,0xff,0xc9,0xb2,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xb5,0x00,0xd4,0x5d,0xd3,0x34,0xd2,0x1b,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x10, + 0x07,0x01,0xff,0xc6,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0xa5, + 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x80,0x00,0x01,0xff,0xc6,0xa8,0x00,0xd2, + 0x0f,0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x83,0x00,0x01,0x00,0xd1,0x0b, + 0x10,0x07,0x01,0xff,0xc6,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x88,0x00, + 0x01,0xff,0x75,0xcc,0x9b,0x00,0xd3,0x33,0xd2,0x1d,0xd1,0x0f,0x10,0x08,0x01,0xff, + 0x75,0xcc,0x9b,0x00,0x01,0xff,0xca,0x8a,0x00,0x10,0x07,0x01,0xff,0xca,0x8b,0x00, + 0x01,0xff,0xc6,0xb4,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc6,0xb6,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x92,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01, + 0xff,0xc6,0xb9,0x00,0x01,0x00,0x01,0x00,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0xbd, + 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x44,0xd3,0x16,0x52,0x04,0x01, + 0x00,0x51,0x07,0x01,0xff,0xc7,0x86,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc7,0x89, + 0x00,0xd2,0x12,0x91,0x0b,0x10,0x07,0x01,0xff,0xc7,0x89,0x00,0x01,0x00,0x01,0xff, + 0xc7,0x8c,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x61,0xcc,0x8c,0x00,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff,0x69,0xcc,0x8c,0x00,0xd3,0x46,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x6f,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x8c,0x00,0xd1, + 0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84, + 0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x75,0xcc,0x88, + 0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81, + 0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88, + 0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01, + 0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x88, + 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x87,0xd3,0x41,0xd2, + 0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61, + 0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x84,0x00,0x01,0xff, + 0xc3,0xa6,0xcc,0x84,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc7,0xa5,0x00,0x01,0x00, + 0x10,0x08,0x01,0xff,0x67,0xcc,0x8c,0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00, + 0x10,0x08,0x01,0xff,0x6f,0xcc,0xa8,0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14, + 0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc, + 0x84,0x00,0x10,0x09,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc, + 0x8c,0x00,0xd3,0x38,0xd2,0x1a,0xd1,0x0f,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00, + 0x01,0xff,0xc7,0xb3,0x00,0x10,0x07,0x01,0xff,0xc7,0xb3,0x00,0x01,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x67,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x10,0x07, + 0x04,0xff,0xc6,0x95,0x00,0x04,0xff,0xc6,0xbf,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08, + 0x04,0xff,0x6e,0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff, + 0x61,0xcc,0x8a,0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a,0xcc,0x81,0x00,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00, + 0x10,0x09,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00, + 0xe2,0x31,0x02,0xe1,0xc3,0x44,0xe0,0xc8,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0x8f,0x00,0x01,0xff,0x61, + 0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x91,0x00,0x01,0xff,0x61,0xcc,0x91, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x8f,0x00,0x01,0xff,0x65,0xcc,0x8f, + 0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x91,0x00,0x01,0xff,0x65,0xcc,0x91,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8f,0x00,0x01,0xff,0x69,0xcc,0x8f, + 0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x91,0x00,0x01,0xff,0x69,0xcc,0x91,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x10, + 0x08,0x01,0xff,0x6f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc,0x91,0x00,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x8f,0x00,0x01,0xff,0x72,0xcc,0x8f, + 0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0x91,0x00,0x01,0xff,0x72,0xcc,0x91,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x8f,0x00,0x01,0xff,0x75,0xcc,0x8f,0x00,0x10, + 0x08,0x01,0xff,0x75,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc,0x91,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x04,0xff,0x73,0xcc,0xa6,0x00,0x04,0xff,0x73,0xcc,0xa6,0x00,0x10, + 0x08,0x04,0xff,0x74,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc,0xa6,0x00,0xd1,0x0b,0x10, + 0x07,0x04,0xff,0xc8,0x9d,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x68,0xcc,0x8c,0x00, + 0x04,0xff,0x68,0xcc,0x8c,0x00,0xd4,0x79,0xd3,0x31,0xd2,0x16,0xd1,0x0b,0x10,0x07, + 0x06,0xff,0xc6,0x9e,0x00,0x07,0x00,0x10,0x07,0x04,0xff,0xc8,0xa3,0x00,0x04,0x00, + 0xd1,0x0b,0x10,0x07,0x04,0xff,0xc8,0xa5,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x61, + 0xcc,0x87,0x00,0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04, + 0xff,0x65,0xcc,0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x6f, + 0xcc,0x88,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10, + 0x0a,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84, + 0x00,0x10,0x08,0x04,0xff,0x6f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0xd3, + 0x27,0xe2,0x21,0x43,0xd1,0x14,0x10,0x0a,0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00, + 0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x79,0xcc,0x84,0x00, + 0x04,0xff,0x79,0xcc,0x84,0x00,0xd2,0x13,0x51,0x04,0x08,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0xa5,0x00,0x08,0xff,0xc8,0xbc,0x00,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08, + 0xff,0xc6,0x9a,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0xa6,0x00,0x08,0x00,0xcf,0x86, + 0x95,0x5f,0x94,0x5b,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08,0xff, + 0xc9,0x82,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xc6,0x80,0x00,0xd1,0x0e,0x10,0x07, + 0x09,0xff,0xca,0x89,0x00,0x09,0xff,0xca,0x8c,0x00,0x10,0x07,0x09,0xff,0xc9,0x87, + 0x00,0x09,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9,0x89,0x00,0x09,0x00, + 0x10,0x07,0x09,0xff,0xc9,0x8b,0x00,0x09,0x00,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9, + 0x8d,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xc9,0x8f,0x00,0x09,0x00,0x01,0x00,0x01, + 0x00,0xd1,0x8b,0xd0,0x0c,0xcf,0x86,0xe5,0x10,0x43,0x64,0xef,0x42,0x01,0xe6,0xcf, + 0x86,0xd5,0x2a,0xe4,0x99,0x43,0xe3,0x7f,0x43,0xd2,0x11,0xe1,0x5e,0x43,0x10,0x07, + 0x01,0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0xe1,0x65,0x43,0x10,0x09,0x01, + 0xff,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0x00,0xd4,0x0f,0x93,0x0b,0x92, + 0x07,0x61,0xab,0x43,0x01,0xea,0x06,0xe6,0x06,0xe6,0xd3,0x2c,0xd2,0x16,0xd1,0x0b, + 0x10,0x07,0x0a,0xff,0xcd,0xb1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xcd,0xb3,0x00, + 0x0a,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x10,0x07,0x0a, + 0xff,0xcd,0xb7,0x00,0x0a,0x00,0xd2,0x07,0x61,0x97,0x43,0x00,0x00,0x51,0x04,0x09, + 0x00,0x10,0x06,0x01,0xff,0x3b,0x00,0x10,0xff,0xcf,0xb3,0x00,0xe0,0x31,0x01,0xcf, + 0x86,0xd5,0xd3,0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x01, + 0x00,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x81, + 0x00,0x01,0xff,0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5, + 0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9, + 0xcc,0x81,0x00,0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00, + 0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x81,0x00,0xd3,0x3c,0xd2,0x20,0xd1,0x12,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x88, + 0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0x00,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01, + 0xff,0xce,0xb3,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb4,0x00,0x01,0xff,0xce, + 0xb5,0x00,0x10,0x07,0x01,0xff,0xce,0xb6,0x00,0x01,0xff,0xce,0xb7,0x00,0xd2,0x1c, + 0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb8,0x00,0x01,0xff,0xce,0xb9,0x00,0x10,0x07, + 0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xce,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff, + 0xce,0xbc,0x00,0x01,0xff,0xce,0xbd,0x00,0x10,0x07,0x01,0xff,0xce,0xbe,0x00,0x01, + 0xff,0xce,0xbf,0x00,0xe4,0x85,0x43,0xd3,0x35,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01, + 0xff,0xcf,0x80,0x00,0x01,0xff,0xcf,0x81,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf, + 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xcf,0x84,0x00,0x01,0xff,0xcf,0x85,0x00, + 0x10,0x07,0x01,0xff,0xcf,0x86,0x00,0x01,0xff,0xcf,0x87,0x00,0xe2,0x2b,0x43,0xd1, + 0x0e,0x10,0x07,0x01,0xff,0xcf,0x88,0x00,0x01,0xff,0xcf,0x89,0x00,0x10,0x09,0x01, + 0xff,0xce,0xb9,0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc,0x88,0x00,0xcf,0x86,0xd5, + 0x94,0xd4,0x3c,0xd3,0x13,0x92,0x0f,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xcf, + 0x83,0x00,0x01,0x00,0x01,0x00,0xd2,0x07,0x61,0x3a,0x43,0x01,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x10, + 0x09,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x0a,0xff,0xcf,0x97,0x00,0xd3,0x2c,0xd2, + 0x11,0xe1,0x46,0x43,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01,0xff,0xce,0xb8,0x00, + 0xd1,0x10,0x10,0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0xff,0xcf,0x86,0x00, + 0x10,0x07,0x01,0xff,0xcf,0x80,0x00,0x04,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06, + 0xff,0xcf,0x99,0x00,0x06,0x00,0x10,0x07,0x01,0xff,0xcf,0x9b,0x00,0x04,0x00,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xcf,0x9d,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0x9f, + 0x00,0x04,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf, + 0xa1,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10, + 0x07,0x01,0xff,0xcf,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xa7,0x00,0x01, + 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xa9,0x00,0x01,0x00,0x10,0x07, + 0x01,0xff,0xcf,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xad,0x00, + 0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xaf,0x00,0x01,0x00,0xd3,0x2b,0xd2,0x12,0x91, + 0x0e,0x10,0x07,0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xcf,0x81,0x00,0x01,0x00,0xd1, + 0x0e,0x10,0x07,0x05,0xff,0xce,0xb8,0x00,0x05,0xff,0xce,0xb5,0x00,0x10,0x04,0x06, + 0x00,0x07,0xff,0xcf,0xb8,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x07,0x00,0x07,0xff, + 0xcf,0xb2,0x00,0x10,0x07,0x07,0xff,0xcf,0xbb,0x00,0x07,0x00,0xd1,0x0b,0x10,0x04, + 0x08,0x00,0x08,0xff,0xcd,0xbb,0x00,0x10,0x07,0x08,0xff,0xcd,0xbc,0x00,0x08,0xff, + 0xcd,0xbd,0x00,0xe3,0xed,0x46,0xe2,0x3d,0x05,0xe1,0x27,0x02,0xe0,0x66,0x01,0xcf, + 0x86,0xd5,0xf0,0xd4,0x7e,0xd3,0x40,0xd2,0x22,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0, + 0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x07,0x01,0xff,0xd1, + 0x92,0x00,0x01,0xff,0xd0,0xb3,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1, + 0x94,0x00,0x01,0xff,0xd1,0x95,0x00,0x10,0x07,0x01,0xff,0xd1,0x96,0x00,0x01,0xff, + 0xd1,0x96,0xcc,0x88,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x98,0x00, + 0x01,0xff,0xd1,0x99,0x00,0x10,0x07,0x01,0xff,0xd1,0x9a,0x00,0x01,0xff,0xd1,0x9b, + 0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8, + 0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x86,0x00,0x01,0xff,0xd1,0x9f, + 0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xb0,0x00,0x01,0xff, + 0xd0,0xb1,0x00,0x10,0x07,0x01,0xff,0xd0,0xb2,0x00,0x01,0xff,0xd0,0xb3,0x00,0xd1, + 0x0e,0x10,0x07,0x01,0xff,0xd0,0xb4,0x00,0x01,0xff,0xd0,0xb5,0x00,0x10,0x07,0x01, + 0xff,0xd0,0xb6,0x00,0x01,0xff,0xd0,0xb7,0x00,0xd2,0x1e,0xd1,0x10,0x10,0x07,0x01, + 0xff,0xd0,0xb8,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x10,0x07,0x01,0xff,0xd0, + 0xba,0x00,0x01,0xff,0xd0,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xbc,0x00, + 0x01,0xff,0xd0,0xbd,0x00,0x10,0x07,0x01,0xff,0xd0,0xbe,0x00,0x01,0xff,0xd0,0xbf, + 0x00,0xe4,0x25,0x42,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x80, + 0x00,0x01,0xff,0xd1,0x81,0x00,0x10,0x07,0x01,0xff,0xd1,0x82,0x00,0x01,0xff,0xd1, + 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x84,0x00,0x01,0xff,0xd1,0x85,0x00, + 0x10,0x07,0x01,0xff,0xd1,0x86,0x00,0x01,0xff,0xd1,0x87,0x00,0xd2,0x1c,0xd1,0x0e, + 0x10,0x07,0x01,0xff,0xd1,0x88,0x00,0x01,0xff,0xd1,0x89,0x00,0x10,0x07,0x01,0xff, + 0xd1,0x8a,0x00,0x01,0xff,0xd1,0x8b,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x8c, + 0x00,0x01,0xff,0xd1,0x8d,0x00,0x10,0x07,0x01,0xff,0xd1,0x8e,0x00,0x01,0xff,0xd1, + 0x8f,0x00,0xcf,0x86,0xd5,0x07,0x64,0xcf,0x41,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2, + 0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff, + 0xd1,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa5,0x00,0x01,0x00, + 0x10,0x07,0x01,0xff,0xd1,0xa7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01, + 0xff,0xd1,0xa9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xab,0x00,0x01,0x00,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xd1,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xaf, + 0x00,0x01,0x00,0xd3,0x33,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb1,0x00, + 0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xb3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01, + 0xff,0xd1,0xb5,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb5,0xcc,0x8f,0x00,0x01, + 0xff,0xd1,0xb5,0xcc,0x8f,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb9, + 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07, + 0x01,0xff,0xd1,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbf,0x00,0x01,0x00, + 0xe0,0x41,0x01,0xcf,0x86,0xd5,0x8e,0xd4,0x36,0xd3,0x11,0xe2,0x91,0x41,0xe1,0x88, + 0x41,0x10,0x07,0x01,0xff,0xd2,0x81,0x00,0x01,0x00,0xd2,0x0f,0x51,0x04,0x04,0x00, + 0x10,0x07,0x06,0xff,0xd2,0x8b,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x04,0xff,0xd2, + 0x8d,0x00,0x04,0x00,0x10,0x07,0x04,0xff,0xd2,0x8f,0x00,0x04,0x00,0xd3,0x2c,0xd2, + 0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x91,0x00,0x01,0x00,0x10,0x07,0x01,0xff, + 0xd2,0x93,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x95,0x00,0x01,0x00, + 0x10,0x07,0x01,0xff,0xd2,0x97,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01, + 0xff,0xd2,0x99,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9b,0x00,0x01,0x00,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xd2,0x9d,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9f, + 0x00,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2, + 0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10, + 0x07,0x01,0xff,0xd2,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa7,0x00,0x01, + 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xa9,0x00,0x01,0x00,0x10,0x07, + 0x01,0xff,0xd2,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xad,0x00, + 0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xaf,0x00,0x01,0x00,0xd3,0x2c,0xd2,0x16,0xd1, + 0x0b,0x10,0x07,0x01,0xff,0xd2,0xb1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xb3, + 0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xb5,0x00,0x01,0x00,0x10,0x07, + 0x01,0xff,0xd2,0xb7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2, + 0xb9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10, + 0x07,0x01,0xff,0xd2,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbf,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0xdc,0xd4,0x5a,0xd3,0x36,0xd2,0x20,0xd1,0x10,0x10,0x07,0x01, + 0xff,0xd3,0x8f,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0, + 0xb6,0xcc,0x86,0x00,0x01,0xff,0xd3,0x84,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x06, + 0xff,0xd3,0x86,0x00,0x10,0x04,0x06,0x00,0x01,0xff,0xd3,0x88,0x00,0xd2,0x16,0xd1, + 0x0b,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8a,0x00,0x10,0x04,0x06,0x00,0x01,0xff, + 0xd3,0x8c,0x00,0xe1,0x69,0x40,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8e,0x00,0xd3, + 0x41,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x01,0xff, + 0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x01,0xff, + 0xd0,0xb0,0xcc,0x88,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x95,0x00,0x01,0x00, + 0x10,0x09,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00, + 0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x99,0x00,0x01,0x00,0x10,0x09,0x01, + 0xff,0xd3,0x99,0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc,0x88,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x10, + 0x09,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0xd4, + 0x82,0xd3,0x41,0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa1,0x00,0x01,0x00, + 0x10,0x09,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc, + 0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc, + 0x88,0x00,0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa9,0x00,0x01,0x00,0x10, + 0x09,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1, + 0x12,0x10,0x09,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88, + 0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0x01,0xff,0xd1,0x83,0xcc,0x84, + 0x00,0xd3,0x41,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00, + 0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00, + 0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x87,0xcc, + 0x88,0x00,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00,0x10,0x07,0x08,0xff,0xd3,0xb7,0x00, + 0x08,0x00,0xd2,0x1d,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x8b,0xcc,0x88,0x00,0x01, + 0xff,0xd1,0x8b,0xcc,0x88,0x00,0x10,0x07,0x09,0xff,0xd3,0xbb,0x00,0x09,0x00,0xd1, + 0x0b,0x10,0x07,0x09,0xff,0xd3,0xbd,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd3,0xbf, + 0x00,0x09,0x00,0xe1,0x26,0x02,0xe0,0x78,0x01,0xcf,0x86,0xd5,0xb0,0xd4,0x58,0xd3, + 0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x81,0x00,0x06,0x00,0x10,0x07, + 0x06,0xff,0xd4,0x83,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x85,0x00, + 0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x87,0x00,0x06,0x00,0xd2,0x16,0xd1,0x0b,0x10, + 0x07,0x06,0xff,0xd4,0x89,0x00,0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x8b,0x00,0x06, + 0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x8d,0x00,0x06,0x00,0x10,0x07,0x06,0xff, + 0xd4,0x8f,0x00,0x06,0x00,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xd4, + 0x91,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd4,0x93,0x00,0x09,0x00,0xd1,0x0b,0x10, + 0x07,0x0a,0xff,0xd4,0x95,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x97,0x00,0x0a, + 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x99,0x00,0x0a,0x00,0x10,0x07, + 0x0a,0xff,0xd4,0x9b,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x9d,0x00, + 0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x9f,0x00,0x0a,0x00,0xd4,0x58,0xd3,0x2c,0xd2, + 0x16,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0xa1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff, + 0xd4,0xa3,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xd4,0xa5,0x00,0x0b,0x00, + 0x10,0x07,0x0c,0xff,0xd4,0xa7,0x00,0x0c,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x10, + 0xff,0xd4,0xa9,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xab,0x00,0x10,0x00,0xd1, + 0x0b,0x10,0x07,0x10,0xff,0xd4,0xad,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xaf, + 0x00,0x10,0x00,0xd3,0x35,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x00,0x00,0x01,0xff,0xd5, + 0xa1,0x00,0x10,0x07,0x01,0xff,0xd5,0xa2,0x00,0x01,0xff,0xd5,0xa3,0x00,0xd1,0x0e, + 0x10,0x07,0x01,0xff,0xd5,0xa4,0x00,0x01,0xff,0xd5,0xa5,0x00,0x10,0x07,0x01,0xff, + 0xd5,0xa6,0x00,0x01,0xff,0xd5,0xa7,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff, + 0xd5,0xa8,0x00,0x01,0xff,0xd5,0xa9,0x00,0x10,0x07,0x01,0xff,0xd5,0xaa,0x00,0x01, + 0xff,0xd5,0xab,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xac,0x00,0x01,0xff,0xd5, + 0xad,0x00,0x10,0x07,0x01,0xff,0xd5,0xae,0x00,0x01,0xff,0xd5,0xaf,0x00,0xcf,0x86, + 0xe5,0x08,0x3f,0xd4,0x70,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5, + 0xb0,0x00,0x01,0xff,0xd5,0xb1,0x00,0x10,0x07,0x01,0xff,0xd5,0xb2,0x00,0x01,0xff, + 0xd5,0xb3,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xb4,0x00,0x01,0xff,0xd5,0xb5, + 0x00,0x10,0x07,0x01,0xff,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb7,0x00,0xd2,0x1c,0xd1, + 0x0e,0x10,0x07,0x01,0xff,0xd5,0xb8,0x00,0x01,0xff,0xd5,0xb9,0x00,0x10,0x07,0x01, + 0xff,0xd5,0xba,0x00,0x01,0xff,0xd5,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5, + 0xbc,0x00,0x01,0xff,0xd5,0xbd,0x00,0x10,0x07,0x01,0xff,0xd5,0xbe,0x00,0x01,0xff, + 0xd5,0xbf,0x00,0xe3,0x87,0x3e,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x80, + 0x00,0x01,0xff,0xd6,0x81,0x00,0x10,0x07,0x01,0xff,0xd6,0x82,0x00,0x01,0xff,0xd6, + 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x84,0x00,0x01,0xff,0xd6,0x85,0x00, + 0x10,0x07,0x01,0xff,0xd6,0x86,0x00,0x00,0x00,0xe0,0x2f,0x3f,0xcf,0x86,0xe5,0xc0, + 0x3e,0xe4,0x97,0x3e,0xe3,0x76,0x3e,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x01,0xff,0xd5,0xa5,0xd6,0x82,0x00,0xe4,0x3e,0x25,0xe3,0xc3,0x1a, + 0xe2,0x7b,0x81,0xe1,0xc0,0x13,0xd0,0x1e,0xcf,0x86,0xc5,0xe4,0x08,0x4b,0xe3,0x53, + 0x46,0xe2,0xe9,0x43,0xe1,0x1c,0x43,0xe0,0xe1,0x42,0xcf,0x86,0xe5,0xa6,0x42,0x64, + 0x89,0x42,0x0b,0x00,0xcf,0x86,0xe5,0xfa,0x01,0xe4,0x03,0x56,0xe3,0x76,0x01,0xe2, + 0x8e,0x53,0xd1,0x0c,0xe0,0xef,0x52,0xcf,0x86,0x65,0x8d,0x52,0x04,0x00,0xe0,0x0d, + 0x01,0xcf,0x86,0xd5,0x0a,0xe4,0x10,0x53,0x63,0xff,0x52,0x0a,0x00,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x80,0x00,0x01,0xff,0xe2, + 0xb4,0x81,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x82,0x00,0x01,0xff,0xe2,0xb4,0x83, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x84,0x00,0x01,0xff,0xe2,0xb4,0x85, + 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x86,0x00,0x01,0xff,0xe2,0xb4,0x87,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x88,0x00,0x01,0xff,0xe2,0xb4,0x89, + 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x8a,0x00,0x01,0xff,0xe2,0xb4,0x8b,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x8c,0x00,0x01,0xff,0xe2,0xb4,0x8d,0x00,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x8e,0x00,0x01,0xff,0xe2,0xb4,0x8f,0x00,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x90,0x00,0x01,0xff,0xe2,0xb4,0x91, + 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x92,0x00,0x01,0xff,0xe2,0xb4,0x93,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x94,0x00,0x01,0xff,0xe2,0xb4,0x95,0x00,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x96,0x00,0x01,0xff,0xe2,0xb4,0x97,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x98,0x00,0x01,0xff,0xe2,0xb4,0x99,0x00,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x9a,0x00,0x01,0xff,0xe2,0xb4,0x9b,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe2,0xb4,0x9c,0x00,0x01,0xff,0xe2,0xb4,0x9d,0x00,0x10,0x08,0x01, + 0xff,0xe2,0xb4,0x9e,0x00,0x01,0xff,0xe2,0xb4,0x9f,0x00,0xcf,0x86,0xe5,0x42,0x52, + 0x94,0x50,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa0,0x00, + 0x01,0xff,0xe2,0xb4,0xa1,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa2,0x00,0x01,0xff, + 0xe2,0xb4,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa4,0x00,0x01,0xff, + 0xe2,0xb4,0xa5,0x00,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xa7,0x00,0x52,0x04, + 0x00,0x00,0x91,0x0c,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xad,0x00,0x00,0x00, + 0x01,0x00,0xd2,0x1b,0xe1,0xfc,0x52,0xe0,0xad,0x52,0xcf,0x86,0x95,0x0f,0x94,0x0b, + 0x93,0x07,0x62,0x92,0x52,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xd1,0x13,0xe0, + 0xd3,0x53,0xcf,0x86,0x95,0x0a,0xe4,0xa8,0x53,0x63,0x97,0x53,0x04,0x00,0x04,0x00, + 0xd0,0x0d,0xcf,0x86,0x95,0x07,0x64,0x22,0x54,0x08,0x00,0x04,0x00,0xcf,0x86,0x55, + 0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x07,0x62,0x2f,0x54,0x04,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0xb0,0x00,0x11,0xff,0xe1,0x8f,0xb1,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0xb2,0x00,0x11,0xff,0xe1,0x8f,0xb3,0x00,0x91,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0xb4,0x00,0x11,0xff,0xe1,0x8f,0xb5,0x00,0x00,0x00, + 0xd4,0x1c,0xe3,0xe0,0x56,0xe2,0x17,0x56,0xe1,0xda,0x55,0xe0,0xbb,0x55,0xcf,0x86, + 0x95,0x0a,0xe4,0xa4,0x55,0x63,0x88,0x55,0x04,0x00,0x04,0x00,0xe3,0xd2,0x01,0xe2, + 0x2b,0x5a,0xd1,0x0c,0xe0,0x4c,0x59,0xcf,0x86,0x65,0x25,0x59,0x0a,0x00,0xe0,0x9c, + 0x59,0xcf,0x86,0xd5,0xc5,0xd4,0x45,0xd3,0x31,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x12, + 0xff,0xd0,0xb2,0x00,0x12,0xff,0xd0,0xb4,0x00,0x10,0x07,0x12,0xff,0xd0,0xbe,0x00, + 0x12,0xff,0xd1,0x81,0x00,0x51,0x07,0x12,0xff,0xd1,0x82,0x00,0x10,0x07,0x12,0xff, + 0xd1,0x8a,0x00,0x12,0xff,0xd1,0xa3,0x00,0x92,0x10,0x91,0x0c,0x10,0x08,0x12,0xff, + 0xea,0x99,0x8b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x14,0xff,0xe1,0x83,0x90,0x00,0x14,0xff,0xe1,0x83,0x91,0x00,0x10,0x08, + 0x14,0xff,0xe1,0x83,0x92,0x00,0x14,0xff,0xe1,0x83,0x93,0x00,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0x94,0x00,0x14,0xff,0xe1,0x83,0x95,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0x96,0x00,0x14,0xff,0xe1,0x83,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0x98,0x00,0x14,0xff,0xe1,0x83,0x99,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0x9a,0x00,0x14,0xff,0xe1,0x83,0x9b,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0x9c,0x00,0x14,0xff,0xe1,0x83,0x9d,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0x9e,0x00,0x14,0xff,0xe1,0x83,0x9f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x14,0xff,0xe1,0x83,0xa0,0x00,0x14,0xff,0xe1,0x83,0xa1,0x00,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xa2,0x00,0x14,0xff,0xe1,0x83,0xa3,0x00,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xa4,0x00,0x14,0xff,0xe1,0x83,0xa5,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xa6,0x00,0x14,0xff,0xe1,0x83,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xa8,0x00,0x14,0xff,0xe1,0x83,0xa9,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xaa,0x00,0x14,0xff,0xe1,0x83,0xab,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xac,0x00,0x14,0xff,0xe1,0x83,0xad,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0xae,0x00,0x14,0xff,0xe1,0x83,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x14,0xff,0xe1,0x83,0xb0,0x00,0x14,0xff,0xe1,0x83,0xb1,0x00,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xb2,0x00,0x14,0xff,0xe1,0x83,0xb3,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xb4,0x00,0x14,0xff,0xe1,0x83,0xb5,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0xb6,0x00,0x14,0xff,0xe1,0x83,0xb7,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x14,0xff, + 0xe1,0x83,0xb8,0x00,0x14,0xff,0xe1,0x83,0xb9,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, + 0xba,0x00,0x00,0x00,0xd1,0x0c,0x10,0x04,0x00,0x00,0x14,0xff,0xe1,0x83,0xbd,0x00, + 0x10,0x08,0x14,0xff,0xe1,0x83,0xbe,0x00,0x14,0xff,0xe1,0x83,0xbf,0x00,0xe2,0x9d, + 0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa5,0x00,0x01,0xff,0x61,0xcc, + 0xa5,0x00,0x10,0x08,0x01,0xff,0x62,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc,0x87,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x62,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc,0xa3,0x00, + 0x10,0x08,0x01,0xff,0x62,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00,0xd2,0x24, + 0xd1,0x14,0x10,0x0a,0x01,0xff,0x63,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc, + 0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x87,0x00,0x01,0xff,0x64,0xcc, + 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa3,0x00,0x01,0xff,0x64,0xcc, + 0xa3,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc,0xb1,0x00, + 0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa7,0x00,0x01,0xff, + 0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xad,0x00,0x01,0xff,0x64,0xcc, + 0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff, + 0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00, + 0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x65,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, + 0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc, + 0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08,0x01,0xff, + 0x66,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc,0x84,0x00, + 0x10,0x08,0x01,0xff,0x68,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x68,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00,0x10,0x08, + 0x01,0xff,0x68,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x68,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00,0x10,0x08, + 0x01,0xff,0x68,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x69,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a,0x01,0xff, + 0x69,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x81,0x00,0x01,0xff,0x6b,0xcc, + 0x81,0x00,0x10,0x08,0x01,0xff,0x6b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc,0xa3,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc,0xb1,0x00, + 0x10,0x08,0x01,0xff,0x6c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00,0xd2,0x24, + 0xd1,0x14,0x10,0x0a,0x01,0xff,0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff,0x6c,0xcc, + 0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x6c,0xcc,0xb1,0x00,0x01,0xff,0x6c,0xcc, + 0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6c,0xcc,0xad,0x00,0x01,0xff,0x6c,0xcc, + 0xad,0x00,0x10,0x08,0x01,0xff,0x6d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc,0x81,0x00, + 0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x6d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6d, + 0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa3, + 0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, + 0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xad, + 0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x83, + 0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f, + 0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3,0x48,0xd2, + 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff,0x6f, + 0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0x01, + 0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x70,0xcc,0x81, + 0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x70,0xcc,0x87,0x00,0x01, + 0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x87, + 0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xa3,0x00,0x01, + 0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84, + 0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xb1, + 0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x73,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10,0x08,0x01, + 0xff,0x73,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01, + 0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x10, + 0x0a,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87, + 0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x01, + 0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0x87,0x00,0x01, + 0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xa3,0x00,0x01, + 0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0xb1,0x00,0x01,0xff,0x74, + 0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xad, + 0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa4,0x00,0x01, + 0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0xb0,0x00,0x01, + 0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xad,0x00,0x01,0xff,0x75, + 0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81, + 0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x84, + 0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x76,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x76, + 0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x11,0x02,0xcf,0x86,0xd5,0xe2, + 0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x80,0x00, + 0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x81,0x00,0x01,0xff, + 0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x88,0x00,0x01,0xff, + 0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x87,0x00,0x01,0xff,0x77,0xcc, + 0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0xa3,0x00,0x01,0xff, + 0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x78,0xcc,0x87,0x00,0x01,0xff,0x78,0xcc, + 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x78,0xcc,0x88,0x00,0x01,0xff,0x78,0xcc, + 0x88,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc,0x87,0x00, + 0xd3,0x33,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x82,0x00,0x01,0xff, + 0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0xa3,0x00,0x01,0xff,0x7a,0xcc, + 0xa3,0x00,0xe1,0x12,0x59,0x10,0x08,0x01,0xff,0x7a,0xcc,0xb1,0x00,0x01,0xff,0x7a, + 0xcc,0xb1,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01, + 0xff,0x79,0xcc,0x8a,0x00,0x10,0x08,0x01,0xff,0x61,0xca,0xbe,0x00,0x02,0xff,0x73, + 0xcc,0x87,0x00,0x51,0x04,0x0a,0x00,0x10,0x07,0x0a,0xff,0x73,0x73,0x00,0x0a,0x00, + 0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa3,0x00, + 0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x89,0x00,0x01,0xff, + 0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00, + 0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc, + 0x80,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a, + 0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00, + 0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc, + 0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, + 0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00, + 0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a, + 0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00, + 0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc, + 0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x01,0xff, + 0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00, + 0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x65,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, + 0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc, + 0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc, + 0x81,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01,0xd4, + 0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80, + 0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82, + 0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01, + 0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x10, + 0x0a,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x89,0x00,0x01,0xff,0x69, + 0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc,0xa3, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc,0xa3, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00,0xd3, + 0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x01, + 0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80, + 0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f, + 0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a,0x01, + 0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0xd2, + 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x6f, + 0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0x01, + 0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b, + 0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f, + 0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98,0xd3, + 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x01, + 0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3, + 0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75, + 0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x89, + 0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75, + 0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a,0x01, + 0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0xd1, + 0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc,0x9b, + 0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff,0x75, + 0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75, + 0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08,0x01, + 0xff,0x79,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x79,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x79, + 0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x79,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x10,0x08,0x0a,0xff,0xe1, + 0xbb,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbd,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbf,0x00,0x0a,0x00,0xe1,0xbf,0x02,0xe0,0xa1, + 0x01,0xcf,0x86,0xd5,0xc6,0xd4,0x6c,0xd3,0x18,0xe2,0x0e,0x59,0xe1,0xf7,0x58,0x10, + 0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0x00,0xd2, + 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1, + 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, + 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82, + 0x00,0xd3,0x18,0xe2,0x4a,0x59,0xe1,0x33,0x59,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc, + 0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xce,0xb5,0xcc,0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb5,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80, + 0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff, + 0xce,0xb5,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd4,0x6c,0xd3,0x18,0xe2,0x74,0x59, + 0xe1,0x5d,0x59,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7, + 0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00, + 0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc, + 0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01, + 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81, + 0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7, + 0xcc,0x94,0xcd,0x82,0x00,0xd3,0x18,0xe2,0xb0,0x59,0xe1,0x99,0x59,0x10,0x09,0x01, + 0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0x00,0xd2,0x28,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94, + 0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9, + 0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce, + 0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82,0x00,0xcf, + 0x86,0xd5,0xac,0xd4,0x5a,0xd3,0x18,0xe2,0xed,0x59,0xe1,0xd6,0x59,0x10,0x09,0x01, + 0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00,0xd2,0x28,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94, + 0x00,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf, + 0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x18,0xe2, + 0x17,0x5a,0xe1,0x00,0x5a,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff, + 0xcf,0x85,0xcc,0x94,0x00,0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xcf, + 0x85,0xcc,0x94,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x80, + 0x00,0xd1,0x0f,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00, + 0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00,0xe4,0xd3,0x5a, + 0xd3,0x18,0xe2,0x52,0x5a,0xe1,0x3b,0x5a,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0x00, + 0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xcf, + 0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xe0,0xd9,0x02,0xcf,0x86,0xe5, + 0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1, + 0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d, + 0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc, + 0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93, + 0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00, + 0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb1,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff, + 0xce,0xb1,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00, + 0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb1,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1, + 0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce, + 0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01, + 0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x64,0xd2,0x30,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc, + 0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0xce,0xb9, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d, + 0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc, + 0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82, + 0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30, + 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb7,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80, + 0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a, + 0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce, + 0xb7,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93, + 0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00, + 0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93, + 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc, + 0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81, + 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d, + 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89, + 0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d, + 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93, + 0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00, + 0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf, + 0x89,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x49,0xd2,0x26,0xd1,0x12,0x10,0x09, + 0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce,0xb1,0xcc,0x84,0x00,0x10,0x0b, + 0x01,0xff,0xce,0xb1,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xce,0xb9,0x00, + 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10, + 0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcd,0x82,0xce,0xb9, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x81,0x00,0xe1,0xf3,0x5a,0x10,0x09,0x01,0xff,0xce,0xb1,0xce,0xb9, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0xbd,0xd4,0x7e,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10, + 0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7, + 0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0xd1,0x0f,0x10,0x0b, + 0x01,0xff,0xce,0xb7,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce, + 0xb7,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81, + 0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81, + 0x00,0xe1,0x02,0x5b,0x10,0x09,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0x01,0xff,0xe1, + 0xbe,0xbf,0xcc,0x80,0x00,0xd3,0x18,0xe2,0x28,0x5b,0xe1,0x11,0x5b,0x10,0x09,0x01, + 0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0xe2,0x4c,0x5b, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc, + 0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc, + 0x81,0x00,0xd4,0x51,0xd3,0x18,0xe2,0x6f,0x5b,0xe1,0x58,0x5b,0x10,0x09,0x01,0xff, + 0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00,0xd2,0x24,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00, + 0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00, + 0xe1,0x8f,0x5b,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8, + 0xcc,0x80,0x00,0xd3,0x3b,0xd2,0x18,0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf, + 0x89,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0xd1,0x0f,0x10, + 0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff, + 0xcf,0x89,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc, + 0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x81,0x00,0xe1,0x99,0x5b,0x10,0x09,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0x01,0xff, + 0xc2,0xb4,0x00,0xe0,0x0c,0x68,0xcf,0x86,0xe5,0x23,0x02,0xe4,0x25,0x01,0xe3,0x85, + 0x5e,0xd2,0x2a,0xe1,0x5f,0x5c,0xe0,0xdd,0x5b,0xcf,0x86,0xe5,0xbb,0x5b,0x94,0x1b, + 0xe3,0xa4,0x5b,0x92,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01, + 0xff,0xe2,0x80,0x83,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd1,0xd6,0xd0,0x46,0xcf, + 0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04,0x01, + 0x00,0x10,0x07,0x01,0xff,0xcf,0x89,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01,0x00, + 0x10,0x06,0x01,0xff,0x6b,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x01,0x00,0xe3,0x25, + 0x5d,0x92,0x10,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0x8e,0x00,0x01, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x0a,0xe4,0x42,0x5d,0x63,0x2d,0x5d,0x06,0x00,0x94, + 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb0,0x00,0x01, + 0xff,0xe2,0x85,0xb1,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb2,0x00,0x01,0xff,0xe2, + 0x85,0xb3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb4,0x00,0x01,0xff,0xe2, + 0x85,0xb5,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb6,0x00,0x01,0xff,0xe2,0x85,0xb7, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb8,0x00,0x01,0xff,0xe2, + 0x85,0xb9,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xba,0x00,0x01,0xff,0xe2,0x85,0xbb, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xbc,0x00,0x01,0xff,0xe2,0x85,0xbd, + 0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xbe,0x00,0x01,0xff,0xe2,0x85,0xbf,0x00,0x01, + 0x00,0xe0,0x34,0x5d,0xcf,0x86,0xe5,0x13,0x5d,0xe4,0xf2,0x5c,0xe3,0xe1,0x5c,0xe2, + 0xd4,0x5c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0xff,0xe2,0x86,0x84,0x00, + 0xe3,0x23,0x61,0xe2,0xf0,0x60,0xd1,0x0c,0xe0,0x9d,0x60,0xcf,0x86,0x65,0x7e,0x60, + 0x01,0x00,0xd0,0x62,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x18, + 0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x90,0x00, + 0x01,0xff,0xe2,0x93,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93, + 0x92,0x00,0x01,0xff,0xe2,0x93,0x93,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x94,0x00, + 0x01,0xff,0xe2,0x93,0x95,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x96,0x00, + 0x01,0xff,0xe2,0x93,0x97,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x98,0x00,0x01,0xff, + 0xe2,0x93,0x99,0x00,0xcf,0x86,0xe5,0x57,0x60,0x94,0x80,0xd3,0x40,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x9a,0x00,0x01,0xff,0xe2,0x93,0x9b,0x00,0x10, + 0x08,0x01,0xff,0xe2,0x93,0x9c,0x00,0x01,0xff,0xe2,0x93,0x9d,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe2,0x93,0x9e,0x00,0x01,0xff,0xe2,0x93,0x9f,0x00,0x10,0x08,0x01, + 0xff,0xe2,0x93,0xa0,0x00,0x01,0xff,0xe2,0x93,0xa1,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe2,0x93,0xa2,0x00,0x01,0xff,0xe2,0x93,0xa3,0x00,0x10,0x08,0x01, + 0xff,0xe2,0x93,0xa4,0x00,0x01,0xff,0xe2,0x93,0xa5,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe2,0x93,0xa6,0x00,0x01,0xff,0xe2,0x93,0xa7,0x00,0x10,0x08,0x01,0xff,0xe2, + 0x93,0xa8,0x00,0x01,0xff,0xe2,0x93,0xa9,0x00,0x01,0x00,0xd4,0x0c,0xe3,0x33,0x62, + 0xe2,0x2c,0x62,0xcf,0x06,0x04,0x00,0xe3,0x0c,0x65,0xe2,0xff,0x63,0xe1,0x2e,0x02, + 0xe0,0x84,0x01,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x08,0xff,0xe2,0xb0,0xb0,0x00,0x08,0xff,0xe2,0xb0,0xb1,0x00,0x10,0x08, + 0x08,0xff,0xe2,0xb0,0xb2,0x00,0x08,0xff,0xe2,0xb0,0xb3,0x00,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb0,0xb4,0x00,0x08,0xff,0xe2,0xb0,0xb5,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb0,0xb6,0x00,0x08,0xff,0xe2,0xb0,0xb7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb0,0xb8,0x00,0x08,0xff,0xe2,0xb0,0xb9,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb0,0xba,0x00,0x08,0xff,0xe2,0xb0,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb0,0xbc,0x00,0x08,0xff,0xe2,0xb0,0xbd,0x00,0x10,0x08,0x08,0xff,0xe2,0xb0, + 0xbe,0x00,0x08,0xff,0xe2,0xb0,0xbf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb1,0x80,0x00,0x08,0xff,0xe2,0xb1,0x81,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x82,0x00,0x08,0xff,0xe2,0xb1,0x83,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x84,0x00,0x08,0xff,0xe2,0xb1,0x85,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x86,0x00,0x08,0xff,0xe2,0xb1,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x88,0x00,0x08,0xff,0xe2,0xb1,0x89,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x8a,0x00,0x08,0xff,0xe2,0xb1,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x8c,0x00,0x08,0xff,0xe2,0xb1,0x8d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x8e,0x00, + 0x08,0xff,0xe2,0xb1,0x8f,0x00,0x94,0x7c,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe2,0xb1,0x90,0x00,0x08,0xff,0xe2,0xb1,0x91,0x00,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x92,0x00,0x08,0xff,0xe2,0xb1,0x93,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x94,0x00,0x08,0xff,0xe2,0xb1,0x95,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x96,0x00,0x08,0xff,0xe2,0xb1,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe2,0xb1,0x98,0x00,0x08,0xff,0xe2,0xb1,0x99,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x9a,0x00,0x08,0xff,0xe2,0xb1,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, + 0x9c,0x00,0x08,0xff,0xe2,0xb1,0x9d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x9e,0x00, + 0x00,0x00,0x08,0x00,0xcf,0x86,0xd5,0x07,0x64,0xef,0x61,0x08,0x00,0xd4,0x63,0xd3, + 0x32,0xd2,0x1b,0xd1,0x0c,0x10,0x08,0x09,0xff,0xe2,0xb1,0xa1,0x00,0x09,0x00,0x10, + 0x07,0x09,0xff,0xc9,0xab,0x00,0x09,0xff,0xe1,0xb5,0xbd,0x00,0xd1,0x0b,0x10,0x07, + 0x09,0xff,0xc9,0xbd,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xa8, + 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xaa,0x00,0x10, + 0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xac,0x00,0xd1,0x0b,0x10,0x04,0x09,0x00,0x0a, + 0xff,0xc9,0x91,0x00,0x10,0x07,0x0a,0xff,0xc9,0xb1,0x00,0x0a,0xff,0xc9,0x90,0x00, + 0xd3,0x27,0xd2,0x17,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xc9,0x92,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xe2,0xb1,0xb3,0x00,0x0a,0x00,0x91,0x0c,0x10,0x04,0x09,0x00,0x09, + 0xff,0xe2,0xb1,0xb6,0x00,0x09,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10, + 0x07,0x0b,0xff,0xc8,0xbf,0x00,0x0b,0xff,0xc9,0x80,0x00,0xe0,0x83,0x01,0xcf,0x86, + 0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, + 0x81,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x83,0x00,0x08,0x00,0xd1,0x0c, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2, + 0x87,0x00,0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x89,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8f,0x00, + 0x08,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x91,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x97,0x00, + 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x99,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb2,0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x9f,0x00,0x08,0x00, + 0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa1,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0xa5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa7,0x00, + 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa9,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0xab,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb2,0xad,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xaf,0x00,0x08,0x00, + 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb1,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb2,0xb3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb2,0xb5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb7,0x00,0x08,0x00, + 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb9,0x00,0x08,0x00,0x10,0x08, + 0x08,0xff,0xe2,0xb2,0xbb,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, + 0xbd,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xbf,0x00,0x08,0x00,0xcf,0x86, + 0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3, + 0x81,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x83,0x00,0x08,0x00,0xd1,0x0c, + 0x10,0x08,0x08,0xff,0xe2,0xb3,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3, + 0x87,0x00,0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x89,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb3,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8f,0x00, + 0x08,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x91,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, + 0x08,0xff,0xe2,0xb3,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x97,0x00, + 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x99,0x00,0x08,0x00, + 0x10,0x08,0x08,0xff,0xe2,0xb3,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, + 0xe2,0xb3,0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x9f,0x00,0x08,0x00, + 0xd4,0x3b,0xd3,0x1c,0x92,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa1,0x00, + 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa3,0x00,0x08,0x00,0x08,0x00,0xd2,0x10, + 0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x0b,0xff,0xe2,0xb3,0xac,0x00,0xe1,0x3b, + 0x5f,0x10,0x04,0x0b,0x00,0x0b,0xff,0xe2,0xb3,0xae,0x00,0xe3,0x40,0x5f,0x92,0x10, + 0x51,0x04,0x0b,0xe6,0x10,0x08,0x0d,0xff,0xe2,0xb3,0xb3,0x00,0x0d,0x00,0x00,0x00, + 0xe2,0x98,0x08,0xd1,0x0b,0xe0,0x11,0x67,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe0,0x65, + 0x6c,0xcf,0x86,0xe5,0xa7,0x05,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x0c,0xe2,0xf8, + 0x67,0xe1,0x8f,0x67,0xcf,0x06,0x04,0x00,0xe2,0xdb,0x01,0xe1,0x26,0x01,0xd0,0x09, + 0xcf,0x86,0x65,0xf4,0x67,0x0a,0x00,0xcf,0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2, + 0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a, + 0xff,0xea,0x99,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x85, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1, + 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x99,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x8d,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1, + 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x99,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x95,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x97,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x99,0x99,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x9b, + 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x9d,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xea,0x99,0x9f,0x00,0x0a,0x00,0xe4,0x5d,0x67,0xd3,0x30,0xd2,0x18, + 0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x99,0xa1,0x00,0x0c,0x00,0x10,0x08,0x0a,0xff, + 0xea,0x99,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0xa5,0x00, + 0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x0a,0xff,0xea,0x99,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99, + 0xab,0x00,0x0a,0x00,0xe1,0x0c,0x67,0x10,0x08,0x0a,0xff,0xea,0x99,0xad,0x00,0x0a, + 0x00,0xe0,0x35,0x67,0xcf,0x86,0x95,0xab,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x0a,0xff,0xea,0x9a,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a, + 0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x85,0x00,0x0a,0x00, + 0x10,0x08,0x0a,0xff,0xea,0x9a,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8b,0x00, + 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8d,0x00,0x0a,0x00,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x93,0x00, + 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x95,0x00,0x0a,0x00,0x10,0x08, + 0x0a,0xff,0xea,0x9a,0x97,0x00,0x0a,0x00,0xe2,0x92,0x66,0xd1,0x0c,0x10,0x08,0x10, + 0xff,0xea,0x9a,0x99,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9a,0x9b,0x00,0x10, + 0x00,0x0b,0x00,0xe1,0x10,0x02,0xd0,0xb9,0xcf,0x86,0xd5,0x07,0x64,0x9e,0x66,0x08, + 0x00,0xd4,0x58,0xd3,0x28,0xd2,0x10,0x51,0x04,0x09,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x9c,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa5,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9c,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xab, + 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xad,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xea,0x9c,0xaf,0x00,0x0a,0x00,0xd3,0x28,0xd2,0x10,0x51,0x04,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, + 0xff,0xea,0x9c,0xb5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb7,0x00,0x0a, + 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb9,0x00,0x0a,0x00,0x10, + 0x08,0x0a,0xff,0xea,0x9c,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, + 0x9c,0xbd,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xbf,0x00,0x0a,0x00,0xcf, + 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, + 0x9d,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x83,0x00,0x0a,0x00,0xd1, + 0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x85,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, + 0x9d,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x89, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9d,0x8d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8f, + 0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x91, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9d,0x95,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x97, + 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x99,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, + 0xff,0xea,0x9d,0x9d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9f,0x00,0x0a, + 0x00,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa1, + 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10, + 0x08,0x0a,0xff,0xea,0x9d,0xa5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa7, + 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa9,0x00,0x0a, + 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xab,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, + 0xff,0xea,0x9d,0xad,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xaf,0x00,0x0a, + 0x00,0x53,0x04,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea, + 0x9d,0xba,0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9d,0xbc,0x00,0xd1,0x0c,0x10, + 0x04,0x0a,0x00,0x0a,0xff,0xe1,0xb5,0xb9,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xbf, + 0x00,0x0a,0x00,0xe0,0x71,0x01,0xcf,0x86,0xd5,0xa6,0xd4,0x4e,0xd3,0x30,0xd2,0x18, + 0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff, + 0xea,0x9e,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x85,0x00, + 0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9e,0x87,0x00,0x0a,0x00,0xd2,0x10,0x51,0x04, + 0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9e,0x8c,0x00,0xe1,0x9a,0x64,0x10, + 0x04,0x0a,0x00,0x0c,0xff,0xc9,0xa5,0x00,0xd3,0x28,0xd2,0x18,0xd1,0x0c,0x10,0x08, + 0x0c,0xff,0xea,0x9e,0x91,0x00,0x0c,0x00,0x10,0x08,0x0d,0xff,0xea,0x9e,0x93,0x00, + 0x0d,0x00,0x51,0x04,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x97,0x00,0x10,0x00, + 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e,0x99,0x00,0x10,0x00,0x10,0x08, + 0x10,0xff,0xea,0x9e,0x9b,0x00,0x10,0x00,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e, + 0x9d,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x9f,0x00,0x10,0x00,0xd4,0x63, + 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa1,0x00,0x0c,0x00, + 0x10,0x08,0x0c,0xff,0xea,0x9e,0xa3,0x00,0x0c,0x00,0xd1,0x0c,0x10,0x08,0x0c,0xff, + 0xea,0x9e,0xa5,0x00,0x0c,0x00,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa7,0x00,0x0c,0x00, + 0xd2,0x1a,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa9,0x00,0x0c,0x00,0x10,0x07, + 0x0d,0xff,0xc9,0xa6,0x00,0x10,0xff,0xc9,0x9c,0x00,0xd1,0x0e,0x10,0x07,0x10,0xff, + 0xc9,0xa1,0x00,0x10,0xff,0xc9,0xac,0x00,0x10,0x07,0x12,0xff,0xc9,0xaa,0x00,0x14, + 0x00,0xd3,0x35,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x10,0xff,0xca,0x9e,0x00,0x10,0xff, + 0xca,0x87,0x00,0x10,0x07,0x11,0xff,0xca,0x9d,0x00,0x11,0xff,0xea,0xad,0x93,0x00, + 0xd1,0x0c,0x10,0x08,0x11,0xff,0xea,0x9e,0xb5,0x00,0x11,0x00,0x10,0x08,0x11,0xff, + 0xea,0x9e,0xb7,0x00,0x11,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x14,0xff,0xea,0x9e, + 0xb9,0x00,0x14,0x00,0x10,0x08,0x15,0xff,0xea,0x9e,0xbb,0x00,0x15,0x00,0xd1,0x0c, + 0x10,0x08,0x15,0xff,0xea,0x9e,0xbd,0x00,0x15,0x00,0x10,0x08,0x15,0xff,0xea,0x9e, + 0xbf,0x00,0x15,0x00,0xcf,0x86,0xe5,0xd4,0x63,0x94,0x2f,0x93,0x2b,0xd2,0x10,0x51, + 0x04,0x00,0x00,0x10,0x08,0x15,0xff,0xea,0x9f,0x83,0x00,0x15,0x00,0xd1,0x0f,0x10, + 0x08,0x15,0xff,0xea,0x9e,0x94,0x00,0x15,0xff,0xca,0x82,0x00,0x10,0x08,0x15,0xff, + 0xe1,0xb6,0x8e,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe4,0xb4,0x66,0xd3,0x1d,0xe2, + 0x5b,0x64,0xe1,0x0a,0x64,0xe0,0xf7,0x63,0xcf,0x86,0xe5,0xd8,0x63,0x94,0x0b,0x93, + 0x07,0x62,0xc3,0x63,0x08,0x00,0x08,0x00,0x08,0x00,0xd2,0x0f,0xe1,0x5a,0x65,0xe0, + 0x27,0x65,0xcf,0x86,0x65,0x0c,0x65,0x0a,0x00,0xd1,0xab,0xd0,0x1a,0xcf,0x86,0xe5, + 0x17,0x66,0xe4,0xfa,0x65,0xe3,0xe1,0x65,0xe2,0xd4,0x65,0x91,0x08,0x10,0x04,0x00, + 0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x0b,0x93,0x07,0x62, + 0x27,0x66,0x11,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff, + 0xe1,0x8e,0xa0,0x00,0x11,0xff,0xe1,0x8e,0xa1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e, + 0xa2,0x00,0x11,0xff,0xe1,0x8e,0xa3,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, + 0xa4,0x00,0x11,0xff,0xe1,0x8e,0xa5,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa6,0x00, + 0x11,0xff,0xe1,0x8e,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, + 0xa8,0x00,0x11,0xff,0xe1,0x8e,0xa9,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xaa,0x00, + 0x11,0xff,0xe1,0x8e,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xac,0x00, + 0x11,0xff,0xe1,0x8e,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xae,0x00,0x11,0xff, + 0xe1,0x8e,0xaf,0x00,0xe0,0xb2,0x65,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb0,0x00,0x11,0xff,0xe1,0x8e, + 0xb1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb2,0x00,0x11,0xff,0xe1,0x8e,0xb3,0x00, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb4,0x00,0x11,0xff,0xe1,0x8e,0xb5,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8e,0xb6,0x00,0x11,0xff,0xe1,0x8e,0xb7,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb8,0x00,0x11,0xff,0xe1,0x8e,0xb9,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8e,0xba,0x00,0x11,0xff,0xe1,0x8e,0xbb,0x00,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8e,0xbc,0x00,0x11,0xff,0xe1,0x8e,0xbd,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8e,0xbe,0x00,0x11,0xff,0xe1,0x8e,0xbf,0x00,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0x80,0x00,0x11,0xff,0xe1,0x8f,0x81,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x82,0x00,0x11,0xff,0xe1,0x8f,0x83,0x00,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x84,0x00,0x11,0xff,0xe1,0x8f,0x85,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x86,0x00,0x11,0xff,0xe1,0x8f,0x87,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x88,0x00,0x11,0xff,0xe1,0x8f,0x89,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x8a,0x00,0x11,0xff,0xe1,0x8f,0x8b,0x00,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x8c,0x00,0x11,0xff,0xe1,0x8f,0x8d,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0x8e,0x00,0x11,0xff,0xe1,0x8f,0x8f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0x90,0x00,0x11,0xff,0xe1,0x8f,0x91,0x00, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x92,0x00,0x11,0xff,0xe1,0x8f,0x93,0x00,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x94,0x00,0x11,0xff,0xe1,0x8f,0x95,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x96,0x00,0x11,0xff,0xe1,0x8f,0x97,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0x98,0x00,0x11,0xff,0xe1,0x8f,0x99,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x9a,0x00,0x11,0xff,0xe1,0x8f,0x9b,0x00,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0x9c,0x00,0x11,0xff,0xe1,0x8f,0x9d,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0x9e,0x00,0x11,0xff,0xe1,0x8f,0x9f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x11,0xff,0xe1,0x8f,0xa0,0x00,0x11,0xff,0xe1,0x8f,0xa1,0x00,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0xa2,0x00,0x11,0xff,0xe1,0x8f,0xa3,0x00,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0xa4,0x00,0x11,0xff,0xe1,0x8f,0xa5,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0xa6,0x00,0x11,0xff,0xe1,0x8f,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x11,0xff,0xe1,0x8f,0xa8,0x00,0x11,0xff,0xe1,0x8f,0xa9,0x00,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0xaa,0x00,0x11,0xff,0xe1,0x8f,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff, + 0xe1,0x8f,0xac,0x00,0x11,0xff,0xe1,0x8f,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, + 0xae,0x00,0x11,0xff,0xe1,0x8f,0xaf,0x00,0xd1,0x0c,0xe0,0xeb,0x63,0xcf,0x86,0xcf, + 0x06,0x02,0xff,0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06, + 0xcf,0x06,0x01,0x00,0xd4,0xae,0xd3,0x09,0xe2,0x54,0x64,0xcf,0x06,0x01,0x00,0xd2, + 0x27,0xe1,0x1f,0x70,0xe0,0x26,0x6e,0xcf,0x86,0xe5,0x3f,0x6d,0xe4,0xce,0x6c,0xe3, + 0x99,0x6c,0xe2,0x78,0x6c,0xe1,0x67,0x6c,0x10,0x08,0x01,0xff,0xe5,0x88,0x87,0x00, + 0x01,0xff,0xe5,0xba,0xa6,0x00,0xe1,0x74,0x74,0xe0,0xe8,0x73,0xcf,0x86,0xe5,0x22, + 0x73,0xd4,0x3b,0x93,0x37,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x01,0xff,0x66,0x66,0x00, + 0x01,0xff,0x66,0x69,0x00,0x10,0x07,0x01,0xff,0x66,0x6c,0x00,0x01,0xff,0x66,0x66, + 0x69,0x00,0xd1,0x0f,0x10,0x08,0x01,0xff,0x66,0x66,0x6c,0x00,0x01,0xff,0x73,0x74, + 0x00,0x10,0x07,0x01,0xff,0x73,0x74,0x00,0x00,0x00,0x00,0x00,0xe3,0xc8,0x72,0xd2, + 0x11,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xd5,0xb4,0xd5,0xb6,0x00, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xd5,0xb4,0xd5,0xa5,0x00,0x01,0xff,0xd5,0xb4,0xd5, + 0xab,0x00,0x10,0x09,0x01,0xff,0xd5,0xbe,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb4,0xd5, + 0xad,0x00,0xd3,0x09,0xe2,0x40,0x74,0xcf,0x06,0x01,0x00,0xd2,0x13,0xe1,0x30,0x75, + 0xe0,0xc1,0x74,0xcf,0x86,0xe5,0x9e,0x74,0x64,0x8d,0x74,0x06,0xff,0x00,0xe1,0x96, + 0x75,0xe0,0x63,0x75,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x7c, + 0xd3,0x3c,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xef,0xbd,0x81,0x00, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x82,0x00,0x01,0xff,0xef,0xbd,0x83,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x84,0x00,0x01,0xff,0xef,0xbd,0x85,0x00,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x86,0x00,0x01,0xff,0xef,0xbd,0x87,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x88,0x00,0x01,0xff,0xef,0xbd,0x89,0x00,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x8a,0x00,0x01,0xff,0xef,0xbd,0x8b,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x8c,0x00,0x01,0xff,0xef,0xbd,0x8d,0x00,0x10,0x08,0x01,0xff, + 0xef,0xbd,0x8e,0x00,0x01,0xff,0xef,0xbd,0x8f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xef,0xbd,0x90,0x00,0x01,0xff,0xef,0xbd,0x91,0x00,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x92,0x00,0x01,0xff,0xef,0xbd,0x93,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x94,0x00,0x01,0xff,0xef,0xbd,0x95,0x00,0x10,0x08,0x01,0xff, + 0xef,0xbd,0x96,0x00,0x01,0xff,0xef,0xbd,0x97,0x00,0x92,0x1c,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xef,0xbd,0x98,0x00,0x01,0xff,0xef,0xbd,0x99,0x00,0x10,0x08,0x01,0xff, + 0xef,0xbd,0x9a,0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0x87,0xb3,0xe1,0x60,0xb0,0xe0, + 0xdd,0xae,0xcf,0x86,0xe5,0x81,0x9b,0xc4,0xe3,0xc1,0x07,0xe2,0x62,0x06,0xe1,0x11, + 0x86,0xe0,0x09,0x05,0xcf,0x86,0xe5,0xfb,0x02,0xd4,0x1c,0xe3,0x7f,0x76,0xe2,0xd6, + 0x75,0xe1,0xb1,0x75,0xe0,0x8a,0x75,0xcf,0x86,0xe5,0x57,0x75,0x94,0x07,0x63,0x42, + 0x75,0x07,0x00,0x07,0x00,0xe3,0x2b,0x78,0xe2,0xf0,0x77,0xe1,0x77,0x01,0xe0,0x88, + 0x77,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xa8,0x00,0x05,0xff,0xf0,0x90,0x90,0xa9,0x00,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xaa,0x00,0x05,0xff,0xf0,0x90,0x90,0xab,0x00,0xd1,0x12, + 0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xac,0x00,0x05,0xff,0xf0,0x90,0x90,0xad,0x00, + 0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xae,0x00,0x05,0xff,0xf0,0x90,0x90,0xaf,0x00, + 0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb0,0x00,0x05,0xff,0xf0, + 0x90,0x90,0xb1,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb2,0x00,0x05,0xff,0xf0, + 0x90,0x90,0xb3,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb4,0x00,0x05, + 0xff,0xf0,0x90,0x90,0xb5,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb6,0x00,0x05, + 0xff,0xf0,0x90,0x90,0xb7,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x90,0xb8,0x00,0x05,0xff,0xf0,0x90,0x90,0xb9,0x00,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x90,0xba,0x00,0x05,0xff,0xf0,0x90,0x90,0xbb,0x00,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xbc,0x00,0x05,0xff,0xf0,0x90,0x90,0xbd,0x00,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x90,0xbe,0x00,0x05,0xff,0xf0,0x90,0x90,0xbf,0x00,0xd2,0x24, + 0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x80,0x00,0x05,0xff,0xf0,0x90,0x91, + 0x81,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x82,0x00,0x05,0xff,0xf0,0x90,0x91, + 0x83,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x84,0x00,0x05,0xff,0xf0, + 0x90,0x91,0x85,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x86,0x00,0x05,0xff,0xf0, + 0x90,0x91,0x87,0x00,0x94,0x4c,0x93,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x91,0x88,0x00,0x05,0xff,0xf0,0x90,0x91,0x89,0x00,0x10,0x09,0x05,0xff, + 0xf0,0x90,0x91,0x8a,0x00,0x05,0xff,0xf0,0x90,0x91,0x8b,0x00,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0x90,0x91,0x8c,0x00,0x05,0xff,0xf0,0x90,0x91,0x8d,0x00,0x10,0x09, + 0x07,0xff,0xf0,0x90,0x91,0x8e,0x00,0x07,0xff,0xf0,0x90,0x91,0x8f,0x00,0x05,0x00, + 0x05,0x00,0xd0,0xa0,0xcf,0x86,0xd5,0x07,0x64,0x30,0x76,0x07,0x00,0xd4,0x07,0x63, + 0x3d,0x76,0x07,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90, + 0x93,0x98,0x00,0x12,0xff,0xf0,0x90,0x93,0x99,0x00,0x10,0x09,0x12,0xff,0xf0,0x90, + 0x93,0x9a,0x00,0x12,0xff,0xf0,0x90,0x93,0x9b,0x00,0xd1,0x12,0x10,0x09,0x12,0xff, + 0xf0,0x90,0x93,0x9c,0x00,0x12,0xff,0xf0,0x90,0x93,0x9d,0x00,0x10,0x09,0x12,0xff, + 0xf0,0x90,0x93,0x9e,0x00,0x12,0xff,0xf0,0x90,0x93,0x9f,0x00,0xd2,0x24,0xd1,0x12, + 0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa0,0x00,0x12,0xff,0xf0,0x90,0x93,0xa1,0x00, + 0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa2,0x00,0x12,0xff,0xf0,0x90,0x93,0xa3,0x00, + 0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa4,0x00,0x12,0xff,0xf0,0x90,0x93, + 0xa5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa6,0x00,0x12,0xff,0xf0,0x90,0x93, + 0xa7,0x00,0xcf,0x86,0xe5,0xc6,0x75,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x12,0xff,0xf0,0x90,0x93,0xa8,0x00,0x12,0xff,0xf0,0x90,0x93,0xa9,0x00,0x10, + 0x09,0x12,0xff,0xf0,0x90,0x93,0xaa,0x00,0x12,0xff,0xf0,0x90,0x93,0xab,0x00,0xd1, + 0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xac,0x00,0x12,0xff,0xf0,0x90,0x93,0xad, + 0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xae,0x00,0x12,0xff,0xf0,0x90,0x93,0xaf, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb0,0x00,0x12,0xff, + 0xf0,0x90,0x93,0xb1,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb2,0x00,0x12,0xff, + 0xf0,0x90,0x93,0xb3,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb4,0x00, + 0x12,0xff,0xf0,0x90,0x93,0xb5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb6,0x00, + 0x12,0xff,0xf0,0x90,0x93,0xb7,0x00,0x93,0x28,0x92,0x24,0xd1,0x12,0x10,0x09,0x12, + 0xff,0xf0,0x90,0x93,0xb8,0x00,0x12,0xff,0xf0,0x90,0x93,0xb9,0x00,0x10,0x09,0x12, + 0xff,0xf0,0x90,0x93,0xba,0x00,0x12,0xff,0xf0,0x90,0x93,0xbb,0x00,0x00,0x00,0x12, + 0x00,0xd4,0x1f,0xe3,0xdf,0x76,0xe2,0x6a,0x76,0xe1,0x09,0x76,0xe0,0xea,0x75,0xcf, + 0x86,0xe5,0xb7,0x75,0x94,0x0a,0xe3,0xa2,0x75,0x62,0x99,0x75,0x07,0x00,0x07,0x00, + 0xe3,0xde,0x78,0xe2,0xaf,0x78,0xd1,0x09,0xe0,0x4c,0x78,0xcf,0x06,0x0b,0x00,0xe0, + 0x7f,0x78,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x80,0x00,0x11,0xff,0xf0,0x90,0xb3,0x81,0x00,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x82,0x00,0x11,0xff,0xf0,0x90,0xb3,0x83,0x00,0xd1, + 0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x84,0x00,0x11,0xff,0xf0,0x90,0xb3,0x85, + 0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x86,0x00,0x11,0xff,0xf0,0x90,0xb3,0x87, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x88,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x89,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8a,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x8b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8c,0x00, + 0x11,0xff,0xf0,0x90,0xb3,0x8d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8e,0x00, + 0x11,0xff,0xf0,0x90,0xb3,0x8f,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0x90,0x00,0x11,0xff,0xf0,0x90,0xb3,0x91,0x00,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0x92,0x00,0x11,0xff,0xf0,0x90,0xb3,0x93,0x00,0xd1,0x12,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x94,0x00,0x11,0xff,0xf0,0x90,0xb3,0x95,0x00,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0x96,0x00,0x11,0xff,0xf0,0x90,0xb3,0x97,0x00,0xd2, + 0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x98,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0x99,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9a,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9c,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x9d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9e,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0x9f,0x00,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0xa0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa1,0x00,0x10,0x09,0x11, + 0xff,0xf0,0x90,0xb3,0xa2,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa3,0x00,0xd1,0x12,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0xa4,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa5,0x00,0x10, + 0x09,0x11,0xff,0xf0,0x90,0xb3,0xa6,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa7,0x00,0xd2, + 0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xa8,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0xa9,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xaa,0x00,0x11,0xff,0xf0,0x90, + 0xb3,0xab,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xac,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0xad,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xae,0x00,0x11,0xff, + 0xf0,0x90,0xb3,0xaf,0x00,0x93,0x23,0x92,0x1f,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0, + 0x90,0xb3,0xb0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xb1,0x00,0x10,0x09,0x11,0xff,0xf0, + 0x90,0xb3,0xb2,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x15,0xe4,0x91, + 0x7b,0xe3,0x9b,0x79,0xe2,0x94,0x78,0xe1,0xe4,0x77,0xe0,0x9d,0x77,0xcf,0x06,0x0c, + 0x00,0xe4,0xeb,0x7e,0xe3,0x44,0x7e,0xe2,0xed,0x7d,0xd1,0x0c,0xe0,0xb2,0x7d,0xcf, + 0x86,0x65,0x93,0x7d,0x14,0x00,0xe0,0xb6,0x7d,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4, + 0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x80,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x81,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x82,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x83,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3, + 0x84,0x00,0x10,0xff,0xf0,0x91,0xa3,0x85,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3, + 0x86,0x00,0x10,0xff,0xf0,0x91,0xa3,0x87,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x88,0x00,0x10,0xff,0xf0,0x91,0xa3,0x89,0x00,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x8a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8b,0x00,0xd1,0x12,0x10, + 0x09,0x10,0xff,0xf0,0x91,0xa3,0x8c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8d,0x00,0x10, + 0x09,0x10,0xff,0xf0,0x91,0xa3,0x8e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8f,0x00,0xd3, + 0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x90,0x00,0x10,0xff, + 0xf0,0x91,0xa3,0x91,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x92,0x00,0x10,0xff, + 0xf0,0x91,0xa3,0x93,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x94,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x95,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x96,0x00, + 0x10,0xff,0xf0,0x91,0xa3,0x97,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0, + 0x91,0xa3,0x98,0x00,0x10,0xff,0xf0,0x91,0xa3,0x99,0x00,0x10,0x09,0x10,0xff,0xf0, + 0x91,0xa3,0x9a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x9c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9d,0x00,0x10,0x09,0x10, + 0xff,0xf0,0x91,0xa3,0x9e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9f,0x00,0xd1,0x11,0xe0, + 0x12,0x81,0xcf,0x86,0xe5,0x09,0x81,0xe4,0xd2,0x80,0xcf,0x06,0x00,0x00,0xe0,0xdb, + 0x82,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x09,0xe3,0x10,0x81,0xcf,0x06, + 0x0c,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xe2,0x3b,0x82,0xe1,0x16,0x82,0xd0,0x06, + 0xcf,0x06,0x00,0x00,0xcf,0x86,0xa5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1, + 0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa1, + 0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa3, + 0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa4,0x00,0x14,0xff,0xf0,0x96, + 0xb9,0xa5,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa6,0x00,0x14,0xff,0xf0,0x96, + 0xb9,0xa7,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa8,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xa9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xaa,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xab,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9, + 0xac,0x00,0x14,0xff,0xf0,0x96,0xb9,0xad,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9, + 0xae,0x00,0x14,0xff,0xf0,0x96,0xb9,0xaf,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x14,0xff,0xf0,0x96,0xb9,0xb0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb1,0x00,0x10, + 0x09,0x14,0xff,0xf0,0x96,0xb9,0xb2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb3,0x00,0xd1, + 0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb4,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb5, + 0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb6,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb7, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb8,0x00,0x14,0xff, + 0xf0,0x96,0xb9,0xb9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xba,0x00,0x14,0xff, + 0xf0,0x96,0xb9,0xbb,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbc,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xbd,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbe,0x00, + 0x14,0xff,0xf0,0x96,0xb9,0xbf,0x00,0x14,0x00,0xd2,0x14,0xe1,0x25,0x82,0xe0,0x1c, + 0x82,0xcf,0x86,0xe5,0xdd,0x81,0xe4,0x9a,0x81,0xcf,0x06,0x12,0x00,0xd1,0x0b,0xe0, + 0x51,0x83,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0x95,0x8b,0xcf,0x86,0xd5,0x22,0xe4, + 0xd0,0x88,0xe3,0x93,0x88,0xe2,0x38,0x88,0xe1,0x31,0x88,0xe0,0x2a,0x88,0xcf,0x86, + 0xe5,0xfb,0x87,0xe4,0xe2,0x87,0x93,0x07,0x62,0xd1,0x87,0x12,0xe6,0x12,0xe6,0xe4, + 0x36,0x89,0xe3,0x2f,0x89,0xd2,0x09,0xe1,0xb8,0x88,0xcf,0x06,0x10,0x00,0xe1,0x1f, + 0x89,0xe0,0xec,0x88,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1, + 0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa3, + 0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa5, + 0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa6,0x00,0x12,0xff,0xf0,0x9e, + 0xa4,0xa7,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa8,0x00,0x12,0xff,0xf0,0x9e, + 0xa4,0xa9,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xaa,0x00, + 0x12,0xff,0xf0,0x9e,0xa4,0xab,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xac,0x00, + 0x12,0xff,0xf0,0x9e,0xa4,0xad,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4, + 0xae,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xaf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4, + 0xb0,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb1,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, + 0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb3,0x00,0x10, + 0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb5,0x00,0xd1, + 0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb6,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb7, + 0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb8,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb9, + 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xba,0x00,0x12,0xff, + 0xf0,0x9e,0xa4,0xbb,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbc,0x00,0x12,0xff, + 0xf0,0x9e,0xa4,0xbd,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbe,0x00, + 0x12,0xff,0xf0,0x9e,0xa4,0xbf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa5,0x80,0x00, + 0x12,0xff,0xf0,0x9e,0xa5,0x81,0x00,0x94,0x1e,0x93,0x1a,0x92,0x16,0x91,0x12,0x10, + 0x09,0x12,0xff,0xf0,0x9e,0xa5,0x82,0x00,0x12,0xff,0xf0,0x9e,0xa5,0x83,0x00,0x12, + 0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + /* nfdi_c0100 */ + 0x57,0x04,0x01,0x00,0xc6,0xe5,0xac,0x13,0xe4,0x41,0x0c,0xe3,0x7a,0x07,0xe2,0xf3, + 0x01,0xc1,0xd0,0x1f,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x53,0x04,0x01,0x00, + 0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x04,0x01,0x00,0x01,0xff,0x00,0x01,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0xe4,0xd4,0x7c,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x41,0xcc,0x80,0x00,0x01,0xff,0x41,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x41, + 0xcc,0x82,0x00,0x01,0xff,0x41,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x41, + 0xcc,0x88,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x43, + 0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x80,0x00,0x01, + 0xff,0x45,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x82,0x00,0x01,0xff,0x45, + 0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x80,0x00,0x01,0xff,0x49, + 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x82,0x00,0x01,0xff,0x49,0xcc,0x88, + 0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x4e,0xcc,0x83, + 0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x80,0x00,0x01,0xff,0x4f,0xcc,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x82,0x00,0x01,0xff,0x4f,0xcc,0x83,0x00,0x10, + 0x08,0x01,0xff,0x4f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01, + 0x00,0x01,0xff,0x55,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x81,0x00,0x01, + 0xff,0x55,0xcc,0x82,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x88,0x00,0x01, + 0xff,0x59,0xcc,0x81,0x00,0x01,0x00,0xd4,0x7c,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x80, + 0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x82,0x00,0x01, + 0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x80,0x00,0x01, + 0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00,0x01,0xff,0x69, + 0xcc,0x88,0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6e, + 0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x81, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82,0x00,0x01,0xff,0x6f,0xcc,0x83, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10, + 0x04,0x01,0x00,0x01,0xff,0x75,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x81, + 0x00,0x01,0xff,0x75,0xcc,0x82,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x88, + 0x00,0x01,0xff,0x79,0xcc,0x81,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x79,0xcc,0x88, + 0x00,0xe1,0x9a,0x03,0xe0,0xd3,0x01,0xcf,0x86,0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84, + 0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x86,0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa8,0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10, + 0x08,0x01,0xff,0x43,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x43,0xcc,0x82,0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10, + 0x08,0x01,0xff,0x43,0xcc,0x87,0x00,0x01,0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x43,0xcc,0x8c,0x00,0x01,0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x44,0xcc,0x8c,0x00,0x01,0xff,0x64,0xcc,0x8c,0x00,0xd3,0x34,0xd2,0x14,0x51, + 0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x84,0x00,0x01,0xff,0x65,0xcc,0x84, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0x86, + 0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0xa8,0x00,0x01,0xff,0x65,0xcc,0xa8, + 0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82,0x00,0x10, + 0x08,0x01,0xff,0x47,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4,0x74,0xd3, + 0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x87,0x00,0x01,0xff,0x67, + 0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0xa7,0x00,0x01,0xff,0x67,0xcc,0xa7, + 0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0x82,0x00,0x01,0xff,0x68,0xcc,0x82, + 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x83,0x00,0x01, + 0xff,0x69,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x84,0x00,0x01,0xff,0x69, + 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x86,0x00,0x01,0xff,0x69, + 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8, + 0x00,0xd3,0x30,0xd2,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x49,0xcc,0x87,0x00,0x01, + 0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4a,0xcc,0x82,0x00,0x01,0xff,0x6a, + 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7, + 0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x4c,0xcc,0x81,0x00,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff,0x4c,0xcc,0xa7,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff,0x4c,0xcc,0x8c,0x00,0x10,0x08,0x01, + 0xff,0x6c,0xcc,0x8c,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x60,0xd3,0x30,0xd2, + 0x10,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x4e,0xcc,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x81,0x00,0x01,0xff,0x4e,0xcc,0xa7,0x00,0x10, + 0x08,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x01,0xff,0x4e,0xcc,0x8c,0x00,0xd2,0x10,0x91, + 0x0c,0x10,0x08,0x01,0xff,0x6e,0xcc,0x8c,0x00,0x01,0x00,0x01,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x4f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0x84,0x00,0x10,0x08,0x01, + 0xff,0x4f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00,0xd3,0x34,0xd2,0x14,0x91, + 0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8b,0x00,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81, + 0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x53,0xcc,0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10, + 0x08,0x01,0xff,0x53,0xcc,0xa7,0x00,0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x74,0xd3, + 0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x8c,0x00,0x01,0xff,0x73, + 0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7, + 0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c, + 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x83,0x00,0x01, + 0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x84,0x00,0x01,0xff,0x75, + 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x86,0x00,0x01,0xff,0x75, + 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x8a,0x00,0x01,0xff,0x75,0xcc,0x8a, + 0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x8b,0x00,0x01, + 0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa8,0x00,0x01,0xff,0x75, + 0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x82,0x00,0x01,0xff,0x77, + 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x82,0x00,0x01,0xff,0x79,0xcc,0x82, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x59,0xcc,0x88,0x00,0x01,0xff,0x5a, + 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff,0x5a,0xcc,0x87, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff,0x5a,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0x00,0xd0,0x4a,0xcf,0x86,0x55, + 0x04,0x01,0x00,0xd4,0x2c,0xd3,0x18,0x92,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0x4f, + 0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01, + 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x55,0xcc,0x9b,0x00,0x93, + 0x14,0x92,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x75,0xcc,0x9b,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xb4,0xd4,0x24,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x41,0xcc,0x8c,0x00,0x10, + 0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff,0x49,0xcc,0x8c,0x00,0xd3,0x46,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x4f,0xcc,0x8c, + 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x8c,0x00,0xd1, + 0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x84, + 0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x55,0xcc,0x88, + 0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81, + 0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88, + 0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01, + 0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x88, + 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x80,0xd3,0x3a,0xd2, + 0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61, + 0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0x86,0xcc,0x84,0x00,0x01,0xff, + 0xc3,0xa6,0xcc,0x84,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0x8c, + 0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b, + 0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa8, + 0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa8, + 0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc6, + 0xb7,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0xd3,0x24,0xd2,0x10,0x91, + 0x0c,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00,0x01,0x00,0x01,0x00,0x91,0x10,0x10, + 0x08,0x01,0xff,0x47,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x04,0x00,0xd2, + 0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x4e,0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80, + 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x8a,0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a, + 0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xc3,0x86,0xcc,0x81,0x00,0x01,0xff, + 0xc3,0xa6,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xc3,0x98,0xcc,0x81,0x00,0x01,0xff, + 0xc3,0xb8,0xcc,0x81,0x00,0xe2,0x07,0x02,0xe1,0xae,0x01,0xe0,0x93,0x01,0xcf,0x86, + 0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc, + 0x8f,0x00,0x01,0xff,0x61,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x91,0x00, + 0x01,0xff,0x61,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x8f,0x00, + 0x01,0xff,0x65,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x91,0x00,0x01,0xff, + 0x65,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x8f,0x00, + 0x01,0xff,0x69,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x91,0x00,0x01,0xff, + 0x69,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8f,0x00,0x01,0xff, + 0x6f,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc, + 0x91,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x8f,0x00, + 0x01,0xff,0x72,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0x91,0x00,0x01,0xff, + 0x72,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x8f,0x00,0x01,0xff, + 0x75,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc, + 0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x04,0xff,0x53,0xcc,0xa6,0x00,0x04,0xff, + 0x73,0xcc,0xa6,0x00,0x10,0x08,0x04,0xff,0x54,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc, + 0xa6,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04,0xff,0x48,0xcc,0x8c,0x00,0x04,0xff, + 0x68,0xcc,0x8c,0x00,0xd4,0x68,0xd3,0x20,0xd2,0x0c,0x91,0x08,0x10,0x04,0x06,0x00, + 0x07,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04,0xff,0x41,0xcc,0x87,0x00, + 0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x45,0xcc, + 0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x88,0xcc, + 0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10,0x0a,0x04,0xff, + 0x4f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x10,0x08, + 0x04,0xff,0x4f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0x93,0x30,0xd2,0x24, + 0xd1,0x14,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x87,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc, + 0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x59,0xcc,0x84,0x00,0x04,0xff,0x79,0xcc, + 0x84,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0xcf,0x86, + 0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x08,0x00,0x09,0x00,0x09,0x00, + 0x09,0x00,0x01,0x00,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18, + 0x53,0x04,0x01,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00, + 0x11,0x04,0x04,0x00,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01,0x00, + 0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x04,0x00,0x94,0x18,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00,0x07,0x00,0xe1,0x35,0x01,0xd0, + 0x72,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0xe6,0xd3,0x10,0x52,0x04,0x01,0xe6,0x91, + 0x08,0x10,0x04,0x01,0xe6,0x01,0xe8,0x01,0xdc,0x92,0x0c,0x51,0x04,0x01,0xdc,0x10, + 0x04,0x01,0xe8,0x01,0xd8,0x01,0xdc,0xd4,0x2c,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10, + 0x04,0x01,0xdc,0x01,0xca,0x10,0x04,0x01,0xca,0x01,0xdc,0x51,0x04,0x01,0xdc,0x10, + 0x04,0x01,0xdc,0x01,0xca,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0xca,0x01,0xdc,0x01, + 0xdc,0x01,0xdc,0xd3,0x08,0x12,0x04,0x01,0xdc,0x01,0x01,0xd2,0x0c,0x91,0x08,0x10, + 0x04,0x01,0x01,0x01,0xdc,0x01,0xdc,0x91,0x08,0x10,0x04,0x01,0xdc,0x01,0xe6,0x01, + 0xe6,0xcf,0x86,0xd5,0x7f,0xd4,0x47,0xd3,0x2e,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01, + 0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0x10,0x04,0x01,0xe6,0x01,0xff,0xcc, + 0x93,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcc,0x88,0xcc,0x81,0x00,0x01,0xf0,0x10, + 0x04,0x04,0xe6,0x04,0xdc,0xd2,0x08,0x11,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10, + 0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x04,0xdc,0x06,0xff,0x00,0xd3,0x18,0xd2,0x0c, + 0x51,0x04,0x07,0xe6,0x10,0x04,0x07,0xe6,0x07,0xdc,0x51,0x04,0x07,0xdc,0x10,0x04, + 0x07,0xdc,0x07,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe8,0x08,0xdc,0x10,0x04, + 0x08,0xdc,0x08,0xe6,0xd1,0x08,0x10,0x04,0x08,0xe9,0x07,0xea,0x10,0x04,0x07,0xea, + 0x07,0xe9,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0xea,0x10,0x04,0x04,0xe9, + 0x06,0xe6,0x06,0xe6,0x06,0xe6,0xd3,0x13,0x52,0x04,0x0a,0x00,0x91,0x0b,0x10,0x07, + 0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10, + 0x04,0x01,0x00,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x06,0x01,0xff,0x3b,0x00,0x10, + 0x00,0xd0,0xe1,0xcf,0x86,0xd5,0x7a,0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1, + 0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, + 0xce,0x91,0xcc,0x81,0x00,0x01,0xff,0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09, + 0x01,0xff,0xce,0x95,0xcc,0x81,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00,0x10,0x09, + 0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce, + 0x9f,0xcc,0x81,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0x01, + 0xff,0xce,0xa9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff, + 0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4, + 0x4a,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01, + 0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x88,0x00, + 0x01,0xff,0xce,0xa5,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc, + 0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13,0x91,0x0f,0x10, + 0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x39,0x53,0x04,0x01,0x00,0xd2,0x16,0x51,0x04, + 0x01,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc, + 0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf, + 0x85,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x0a,0x00,0xd3, + 0x26,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xcf,0x92,0xcc, + 0x81,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0x00,0x10, + 0x04,0x01,0x00,0x04,0x00,0xd2,0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x01,0x00,0x04, + 0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0xd4, + 0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x06, + 0x00,0x07,0x00,0x12,0x04,0x07,0x00,0x08,0x00,0xe3,0x47,0x04,0xe2,0xbe,0x02,0xe1, + 0x07,0x01,0xd0,0x8b,0xcf,0x86,0xd5,0x6c,0xd4,0x53,0xd3,0x30,0xd2,0x1f,0xd1,0x12, + 0x10,0x09,0x04,0xff,0xd0,0x95,0xcc,0x80,0x00,0x01,0xff,0xd0,0x95,0xcc,0x88,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x93,0xcc,0x81,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x01,0xff,0xd0,0x86,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xd0,0x9a,0xcc,0x81,0x00,0x04,0xff,0xd0,0x98,0xcc,0x80,0x00, + 0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x86,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0x92, + 0x11,0x91,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x98,0xcc,0x86,0x00,0x01,0x00, + 0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x11,0x91,0x0d,0x10,0x04, + 0x01,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5, + 0x57,0x54,0x04,0x01,0x00,0xd3,0x30,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0, + 0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0xd0,0xb3,0xcc,0x81,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, + 0xd1,0x96,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0, + 0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8,0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd1, + 0x83,0xcc,0x86,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x1a,0x52,0x04,0x01,0x00, + 0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb4,0xcc,0x8f,0x00,0x01,0xff,0xd1, + 0xb5,0xcc,0x8f,0x00,0x01,0x00,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x94,0x24,0xd3,0x18, + 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0x51,0x04,0x01,0xe6, + 0x10,0x04,0x01,0xe6,0x0a,0xe6,0x92,0x08,0x11,0x04,0x04,0x00,0x06,0x00,0x04,0x00, + 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xbe,0xd4,0x4a,0xd3,0x2a,0xd2,0x1a,0xd1,0x0d, + 0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x96,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0, + 0xb6,0xcc,0x86,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, + 0x06,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, + 0x06,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00, + 0x09,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x90,0xcc,0x86, + 0x00,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0x90,0xcc,0x88, + 0x00,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, + 0xd0,0x95,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0xd2,0x16,0x51,0x04, + 0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0x98,0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc, + 0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x96,0xcc,0x88,0x00,0x01,0xff,0xd0, + 0xb6,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0x97,0xcc,0x88,0x00,0x01,0xff,0xd0, + 0xb7,0xcc,0x88,0x00,0xd4,0x74,0xd3,0x3a,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09, + 0x01,0xff,0xd0,0x98,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xd0,0x98,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00, + 0x10,0x09,0x01,0xff,0xd0,0x9e,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00, + 0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0xa8,0xcc,0x88,0x00,0x01, + 0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0,0xad,0xcc,0x88, + 0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x84, + 0x00,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09, + 0x01,0xff,0xd0,0xa3,0xcc,0x88,0x00,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x10,0x09, + 0x01,0xff,0xd0,0xa3,0xcc,0x8b,0x00,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0x91,0x12, + 0x10,0x09,0x01,0xff,0xd0,0xa7,0xcc,0x88,0x00,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00, + 0x08,0x00,0x92,0x16,0x91,0x12,0x10,0x09,0x01,0xff,0xd0,0xab,0xcc,0x88,0x00,0x01, + 0xff,0xd1,0x8b,0xcc,0x88,0x00,0x09,0x00,0x09,0x00,0xd1,0x74,0xd0,0x36,0xcf,0x86, + 0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, + 0xd4,0x10,0x93,0x0c,0x52,0x04,0x0a,0x00,0x11,0x04,0x0b,0x00,0x0c,0x00,0x10,0x00, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00, + 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0xba, + 0xcf,0x86,0xd5,0x4c,0xd4,0x24,0x53,0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x14,0x00,0x01,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x10,0x00,0x10,0x04,0x10,0x00,0x0d,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x00,0x00,0x02,0xdc,0x02,0xe6,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc,0x02,0xe6, + 0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xde,0x02,0xdc,0x02,0xe6,0xd4,0x2c, + 0xd3,0x10,0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x08,0xdc,0x02,0xdc,0x02,0xdc, + 0xd2,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc,0x02,0xe6,0xd1,0x08,0x10,0x04, + 0x02,0xe6,0x02,0xde,0x10,0x04,0x02,0xe4,0x02,0xe6,0xd3,0x20,0xd2,0x10,0xd1,0x08, + 0x10,0x04,0x01,0x0a,0x01,0x0b,0x10,0x04,0x01,0x0c,0x01,0x0d,0xd1,0x08,0x10,0x04, + 0x01,0x0e,0x01,0x0f,0x10,0x04,0x01,0x10,0x01,0x11,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x01,0x12,0x01,0x13,0x10,0x04,0x09,0x13,0x01,0x14,0xd1,0x08,0x10,0x04,0x01,0x15, + 0x01,0x16,0x10,0x04,0x01,0x00,0x01,0x17,0xcf,0x86,0xd5,0x28,0x94,0x24,0x93,0x20, + 0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x18,0x10,0x04,0x01,0x19,0x01,0x00, + 0xd1,0x08,0x10,0x04,0x02,0xe6,0x08,0xdc,0x10,0x04,0x08,0x00,0x08,0x12,0x00,0x00, + 0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, + 0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x93,0x10, + 0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xe2,0xfb,0x01,0xe1,0x2b,0x01,0xd0,0xa8,0xcf,0x86,0xd5,0x55,0xd4,0x28,0xd3,0x10, + 0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x10,0x00,0x0a,0x00,0xd2,0x0c, + 0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x08,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x07,0x00,0x07,0x00,0xd3,0x0c,0x52,0x04,0x07,0xe6,0x11,0x04,0x07,0xe6,0x0a,0xe6, + 0xd2,0x10,0xd1,0x08,0x10,0x04,0x0a,0x1e,0x0a,0x1f,0x10,0x04,0x0a,0x20,0x01,0x00, + 0xd1,0x09,0x10,0x05,0x0f,0xff,0x00,0x00,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0xd4, + 0x3d,0x93,0x39,0xd2,0x1a,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x09,0x01, + 0xff,0xd8,0xa7,0xd9,0x93,0x00,0x01,0xff,0xd8,0xa7,0xd9,0x94,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xd9,0x88,0xd9,0x94,0x00,0x01,0xff,0xd8,0xa7,0xd9,0x95,0x00,0x10, + 0x09,0x01,0xff,0xd9,0x8a,0xd9,0x94,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00, + 0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x86, + 0xd5,0x5c,0xd4,0x20,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, + 0x01,0x00,0x01,0x1b,0xd1,0x08,0x10,0x04,0x01,0x1c,0x01,0x1d,0x10,0x04,0x01,0x1e, + 0x01,0x1f,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x20,0x01,0x21,0x10,0x04, + 0x01,0x22,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x07,0xdc, + 0x07,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x07,0xe6,0x08,0xe6,0x08,0xe6,0xd1,0x08, + 0x10,0x04,0x08,0xdc,0x08,0xe6,0x10,0x04,0x08,0xe6,0x0c,0xdc,0xd4,0x10,0x53,0x04, + 0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06,0x00,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x01,0x23,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x22, + 0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x08, + 0x11,0x04,0x04,0x00,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00, + 0xcf,0x86,0xd5,0x5b,0xd4,0x2e,0xd3,0x1e,0x92,0x1a,0xd1,0x0d,0x10,0x09,0x01,0xff, + 0xdb,0x95,0xd9,0x94,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xdb,0x81,0xd9,0x94,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x04,0x00,0xd3,0x19,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, + 0xdb,0x92,0xd9,0x94,0x00,0x11,0x04,0x01,0x00,0x01,0xe6,0x52,0x04,0x01,0xe6,0xd1, + 0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0xd4,0x38,0xd3, + 0x1c,0xd2,0x0c,0x51,0x04,0x01,0xe6,0x10,0x04,0x01,0xe6,0x01,0xdc,0xd1,0x08,0x10, + 0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0xd2,0x10,0xd1,0x08,0x10, + 0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0xdc,0x01,0xe6,0x91,0x08,0x10,0x04,0x01, + 0xe6,0x01,0xdc,0x07,0x00,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x04, + 0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00,0xd1,0xc8,0xd0,0x76,0xcf, + 0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04, + 0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04, + 0x00,0x04,0x24,0x04,0x00,0x04,0x00,0x04,0x00,0xd4,0x14,0x53,0x04,0x04,0x00,0x52, + 0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x07,0x00,0x07,0x00,0xd3,0x1c,0xd2, + 0x0c,0x91,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04, + 0xdc,0x04,0xe6,0x10,0x04,0x04,0xe6,0x04,0xdc,0xd2,0x0c,0x51,0x04,0x04,0xdc,0x10, + 0x04,0x04,0xe6,0x04,0xdc,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10,0x04,0x04, + 0xdc,0x04,0xe6,0xcf,0x86,0xd5,0x3c,0x94,0x38,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x04, + 0xe6,0x10,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10, + 0x04,0x04,0xdc,0x04,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10, + 0x04,0x04,0xe6,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x08, + 0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0a, + 0x00,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93, + 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x14,0x53,0x04,0x09,0x00,0x92,0x0c,0x51, + 0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xe6,0x09,0xe6,0xd3,0x10,0x92,0x0c,0x51, + 0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09, + 0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x14,0xdc,0x14, + 0x00,0xe4,0xf8,0x57,0xe3,0x45,0x3f,0xe2,0xf4,0x3e,0xe1,0xc7,0x2c,0xe0,0x21,0x10, + 0xcf,0x86,0xc5,0xe4,0x80,0x08,0xe3,0xcb,0x03,0xe2,0x61,0x01,0xd1,0x94,0xd0,0x5a, + 0xcf,0x86,0xd5,0x20,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52,0x04,0x0b,0x00,0x11,0x04, + 0x0b,0x00,0x0b,0xe6,0x92,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04,0x0b,0x00,0x0b,0xe6, + 0x0b,0xe6,0xd4,0x24,0xd3,0x10,0x52,0x04,0x0b,0xe6,0x91,0x08,0x10,0x04,0x0b,0x00, + 0x0b,0xe6,0x0b,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6,0x0b,0xe6, + 0x11,0x04,0x0b,0xe6,0x00,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04, + 0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xcf,0x86,0xd5,0x20,0x54,0x04,0x0c,0x00, + 0x53,0x04,0x0c,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0c,0xdc,0x0c,0xdc, + 0x51,0x04,0x00,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x13,0x00, + 0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd0,0x4a,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4,0x20,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0d,0x00,0x10,0x00,0x0d,0x00,0x0d,0x00,0x52,0x04,0x0d,0x00,0x91,0x08, + 0x10,0x04,0x0d,0x00,0x10,0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00, + 0x10,0x04,0x10,0x00,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x12,0x00, + 0x52,0x04,0x12,0x00,0x11,0x04,0x12,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04, + 0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x14,0xdc, + 0x12,0xe6,0x12,0xe6,0xd4,0x30,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x12,0xe6,0x10,0x04, + 0x12,0x00,0x11,0xdc,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xdc,0x0d,0xe6,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x0d,0xe6,0x91,0x08,0x10,0x04,0x0d,0xe6, + 0x0d,0xdc,0x0d,0xdc,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0x1b,0x0d,0x1c, + 0x10,0x04,0x0d,0x1d,0x0d,0xe6,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xdc,0x0d,0xe6, + 0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x10,0x04,0x0d,0xdc,0x0d,0xe6, + 0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x10,0xe6,0xe1,0x3a,0x01,0xd0,0x77,0xcf, + 0x86,0xd5,0x20,0x94,0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x01, + 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0xd4,0x1b,0x53,0x04,0x01,0x00,0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe0,0xa4,0xa8,0xe0,0xa4,0xbc,0x00,0x01,0x00,0x01,0x00,0xd3,0x26,0xd2,0x13, + 0x91,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa4,0xb0,0xe0,0xa4,0xbc,0x00,0x01, + 0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xa4,0xb3,0xe0,0xa4,0xbc,0x00,0x01,0x00, + 0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x91,0x08,0x10,0x04,0x01,0x07, + 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x8c,0xd4,0x18,0x53,0x04,0x01,0x00,0x52,0x04, + 0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x10,0x04,0x0b,0x00,0x0c,0x00, + 0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x10,0x04,0x01,0xdc, + 0x01,0xe6,0x91,0x08,0x10,0x04,0x01,0xe6,0x0b,0x00,0x0c,0x00,0xd2,0x2c,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xe0,0xa4,0x95,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0x96, + 0xe0,0xa4,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa4,0x97,0xe0,0xa4,0xbc,0x00,0x01, + 0xff,0xe0,0xa4,0x9c,0xe0,0xa4,0xbc,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa4, + 0xa1,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xa2,0xe0,0xa4,0xbc,0x00,0x10,0x0b, + 0x01,0xff,0xe0,0xa4,0xab,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xaf,0xe0,0xa4, + 0xbc,0x00,0x54,0x04,0x01,0x00,0xd3,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, + 0x0a,0x00,0x10,0x04,0x0a,0x00,0x0c,0x00,0x0c,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x10,0x00,0x0b,0x00,0x10,0x04,0x0b,0x00,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00, + 0x08,0x00,0x09,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00, + 0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, + 0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, + 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, + 0xd3,0x18,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00, + 0x91,0x08,0x10,0x04,0x01,0x07,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x42, + 0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04, + 0x00,0x00,0x01,0x00,0xd2,0x17,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04, + 0x00,0x00,0x01,0xff,0xe0,0xa7,0x87,0xe0,0xa6,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01, + 0xff,0xe0,0xa7,0x87,0xe0,0xa7,0x97,0x00,0x01,0x09,0x10,0x04,0x08,0x00,0x00,0x00, + 0xd3,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, + 0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa6,0xa1,0xe0,0xa6,0xbc, + 0x00,0x01,0xff,0xe0,0xa6,0xa2,0xe0,0xa6,0xbc,0x00,0x10,0x04,0x00,0x00,0x01,0xff, + 0xe0,0xa6,0xaf,0xe0,0xa6,0xbc,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x01,0x00,0x11, + 0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x14,0xe6,0x00, + 0x00,0xe2,0x48,0x02,0xe1,0x4f,0x01,0xd0,0xa4,0xcf,0x86,0xd5,0x4c,0xd4,0x34,0xd3, + 0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x10,0x04,0x01,0x00,0x07, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01, + 0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x2e,0xd2,0x17,0xd1, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa8,0xb2, + 0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x0b,0x01,0xff, + 0xe0,0xa8,0xb8,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00, + 0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x00,0x00,0x01,0x00,0xcf,0x86,0xd5,0x80,0xd4, + 0x34,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51, + 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01, + 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x01, + 0x09,0x00,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x00, + 0x00,0x00,0x00,0xd2,0x25,0xd1,0x0f,0x10,0x04,0x00,0x00,0x01,0xff,0xe0,0xa8,0x96, + 0xe0,0xa8,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa8,0x97,0xe0,0xa8,0xbc,0x00,0x01, + 0xff,0xe0,0xa8,0x9c,0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00, + 0x10,0x0b,0x01,0xff,0xe0,0xa8,0xab,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd4,0x10,0x93, + 0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x14,0x52, + 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04,0x14,0x00,0x00, + 0x00,0x00,0x00,0xd0,0x82,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, + 0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x10, + 0x04,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, + 0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01, + 0x07,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x10,0x52,0x04,0x01, + 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x00, + 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x07, + 0x00,0x07,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x0d,0x00,0x07,0x00,0x00,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x11,0x00,0x13,0x00,0x13,0x00,0xe1,0x24,0x01,0xd0,0x86,0xcf,0x86, + 0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00, + 0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14, + 0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x73,0xd4,0x45,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08, + 0x10,0x04,0x0a,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x0f, + 0x10,0x0b,0x01,0xff,0xe0,0xad,0x87,0xe0,0xad,0x96,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x01,0xff,0xe0,0xad,0x87,0xe0,0xac,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff, + 0xe0,0xad,0x87,0xe0,0xad,0x97,0x00,0x01,0x09,0x00,0x00,0xd3,0x0c,0x52,0x04,0x00, + 0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01, + 0xff,0xe0,0xac,0xa1,0xe0,0xac,0xbc,0x00,0x01,0xff,0xe0,0xac,0xa2,0xe0,0xac,0xbc, + 0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01, + 0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x0c,0x00,0x0c,0x00,0x00,0x00,0xd0,0xb1,0xcf, + 0x86,0xd5,0x63,0xd4,0x28,0xd3,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x91, + 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd3,0x1f,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0, + 0xae,0x92,0xe0,0xaf,0x97,0x00,0x01,0x00,0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x00,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x00,0x00,0x01,0x00,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04, + 0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c, + 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00, + 0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x08,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xcf,0x86, + 0xd5,0x61,0xd4,0x45,0xd3,0x14,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08,0x10,0x04,0x01,0x00, + 0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0,0xae,0xbe,0x00,0x01,0xff,0xe0, + 0xaf,0x87,0xe0,0xae,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0, + 0xaf,0x97,0x00,0x01,0x09,0x00,0x00,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0a, + 0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x00, + 0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x08, + 0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x07,0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00, + 0x00,0x00,0x00,0xe3,0x1c,0x04,0xe2,0x1a,0x02,0xd1,0xf3,0xd0,0x76,0xcf,0x86,0xd5, + 0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01, + 0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91, + 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01, + 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3, + 0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0xd2, + 0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0x53,0xd4,0x2f,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10, + 0x04,0x01,0x00,0x00,0x00,0x01,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0, + 0xb1,0x86,0xe0,0xb1,0x96,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x01,0x54,0x10,0x04,0x01,0x5b,0x00,0x00,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04, + 0x11,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01,0x00, + 0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x52,0x04,0x00,0x00, + 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0a,0x00,0xd0,0x76,0xcf,0x86, + 0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x10,0x00, + 0x01,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00, + 0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, + 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, + 0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x07,0x07,0x07,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x82,0xd4,0x5e,0xd3,0x2a,0xd2,0x13,0x91,0x0f,0x10,0x0b, + 0x01,0xff,0xe0,0xb2,0xbf,0xe0,0xb3,0x95,0x00,0x01,0x00,0x01,0x00,0xd1,0x08,0x10, + 0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3, + 0x95,0x00,0xd2,0x28,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x96, + 0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x82,0x00,0x01,0xff, + 0xe0,0xb3,0x86,0xe0,0xb3,0x82,0xe0,0xb3,0x95,0x00,0x91,0x08,0x10,0x04,0x01,0x00, + 0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00, + 0x10,0x04,0x01,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01,0x00, + 0x09,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08, + 0x10,0x04,0x00,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xe1,0x06,0x01,0xd0,0x6e,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91, + 0x08,0x10,0x04,0x13,0x00,0x10,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, + 0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01, + 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, + 0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x0c,0x00,0x13,0x09,0x91,0x08,0x10,0x04,0x13,0x09,0x0a,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0x65,0xd4,0x45,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10, + 0x04,0x0a,0x00,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08,0x10,0x04,0x01,0x00,0x00, + 0x00,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb4,0xbe,0x00,0x01,0xff,0xe0,0xb5, + 0x87,0xe0,0xb4,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb5, + 0x97,0x00,0x01,0x09,0x10,0x04,0x0c,0x00,0x12,0x00,0xd3,0x10,0x52,0x04,0x00,0x00, + 0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x01,0x00,0x52,0x04,0x12,0x00,0x51,0x04, + 0x12,0x00,0x10,0x04,0x12,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04, + 0x01,0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x0c,0x52,0x04, + 0x0a,0x00,0x11,0x04,0x0a,0x00,0x12,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00, + 0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x5a,0xcf,0x86,0xd5,0x34,0xd4,0x18,0x93,0x14, + 0xd2,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x04,0x00, + 0x04,0x00,0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04, + 0x04,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x54,0x04, + 0x04,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x00,0x00,0x04,0x00, + 0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x04,0x00,0x00,0x00, + 0xcf,0x86,0xd5,0x77,0xd4,0x28,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00, + 0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x04,0x09, + 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x04,0x00,0xd3,0x14,0x52,0x04, + 0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x10,0x04,0x04,0x00,0x00,0x00, + 0xd2,0x13,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8a, + 0x00,0x04,0x00,0xd1,0x19,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0x00, + 0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0xe0,0xb7,0x8a,0x00,0x10,0x0b,0x04,0xff, + 0xe0,0xb7,0x99,0xe0,0xb7,0x9f,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x00, + 0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x14,0xd2,0x08,0x11,0x04,0x00, + 0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe2, + 0x31,0x01,0xd1,0x58,0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x67,0x10,0x04, + 0x01,0x09,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xcf,0x86, + 0x95,0x18,0xd4,0x0c,0x53,0x04,0x01,0x00,0x12,0x04,0x01,0x6b,0x01,0x00,0x53,0x04, + 0x01,0x00,0x12,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd0,0x9e,0xcf,0x86,0xd5,0x54, + 0xd4,0x3c,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04, + 0x01,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x15,0x00, + 0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x15,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x15,0x00,0xd3,0x08,0x12,0x04, + 0x15,0x00,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00, + 0x01,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x15,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00, + 0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x76,0x10,0x04,0x15,0x09, + 0x01,0x00,0x11,0x04,0x01,0x00,0x00,0x00,0xcf,0x86,0x95,0x34,0xd4,0x20,0xd3,0x14, + 0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x52,0x04,0x01,0x7a,0x11,0x04,0x01,0x00,0x00,0x00,0x53,0x04,0x01,0x00, + 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x01,0x00,0x0d,0x00,0x00,0x00, + 0xe1,0x2b,0x01,0xd0,0x3e,0xcf,0x86,0xd5,0x14,0x54,0x04,0x02,0x00,0x53,0x04,0x02, + 0x00,0x92,0x08,0x11,0x04,0x02,0xdc,0x02,0x00,0x02,0x00,0x54,0x04,0x02,0x00,0xd3, + 0x14,0x52,0x04,0x02,0x00,0xd1,0x08,0x10,0x04,0x02,0x00,0x02,0xdc,0x10,0x04,0x02, + 0x00,0x02,0xdc,0x92,0x0c,0x91,0x08,0x10,0x04,0x02,0x00,0x02,0xd8,0x02,0x00,0x02, + 0x00,0xcf,0x86,0xd5,0x73,0xd4,0x36,0xd3,0x17,0x92,0x13,0x51,0x04,0x02,0x00,0x10, + 0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x82,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x00,0x00,0x02,0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00, + 0x02,0xff,0xe0,0xbd,0x8c,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd3,0x26,0xd2,0x13,0x51, + 0x04,0x02,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x91,0xe0,0xbe,0xb7,0x00,0x02,0x00, + 0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x96,0xe0,0xbe,0xb7, + 0x00,0x52,0x04,0x02,0x00,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x9b,0xe0,0xbe, + 0xb7,0x00,0x02,0x00,0x02,0x00,0xd4,0x27,0x53,0x04,0x02,0x00,0xd2,0x17,0xd1,0x0f, + 0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x80,0xe0,0xbe,0xb5,0x00,0x10,0x04,0x04, + 0x00,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0xd3,0x35,0xd2, + 0x17,0xd1,0x08,0x10,0x04,0x00,0x00,0x02,0x81,0x10,0x04,0x02,0x82,0x02,0xff,0xe0, + 0xbd,0xb1,0xe0,0xbd,0xb2,0x00,0xd1,0x0f,0x10,0x04,0x02,0x84,0x02,0xff,0xe0,0xbd, + 0xb1,0xe0,0xbd,0xb4,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xb2,0xe0,0xbe,0x80,0x00, + 0x02,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xb3,0xe0,0xbe,0x80, + 0x00,0x02,0x00,0x02,0x82,0x11,0x04,0x02,0x82,0x02,0x00,0xd0,0xd3,0xcf,0x86,0xd5, + 0x65,0xd4,0x27,0xd3,0x1f,0xd2,0x13,0x91,0x0f,0x10,0x04,0x02,0x82,0x02,0xff,0xe0, + 0xbd,0xb1,0xe0,0xbe,0x80,0x00,0x02,0xe6,0x91,0x08,0x10,0x04,0x02,0x09,0x02,0x00, + 0x02,0xe6,0x12,0x04,0x02,0x00,0x0c,0x00,0xd3,0x1f,0xd2,0x13,0x51,0x04,0x02,0x00, + 0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x92,0xe0,0xbe,0xb7,0x00,0x51,0x04,0x02, + 0x00,0x10,0x04,0x04,0x00,0x02,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x02, + 0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x9c,0xe0,0xbe, + 0xb7,0x00,0x02,0x00,0xd4,0x3d,0xd3,0x26,0xd2,0x13,0x51,0x04,0x02,0x00,0x10,0x0b, + 0x02,0xff,0xe0,0xbe,0xa1,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x51,0x04,0x02,0x00,0x10, + 0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0xa6,0xe0,0xbe,0xb7,0x00,0x52,0x04,0x02,0x00, + 0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xab,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x04, + 0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x02,0x00,0x02,0x00,0x02, + 0x00,0xd2,0x13,0x91,0x0f,0x10,0x04,0x04,0x00,0x02,0xff,0xe0,0xbe,0x90,0xe0,0xbe, + 0xb5,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xcf,0x86, + 0x95,0x4c,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04, + 0x04,0xdc,0x04,0x00,0x52,0x04,0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00, + 0x10,0x04,0x0a,0x00,0x04,0x00,0xd3,0x14,0xd2,0x08,0x11,0x04,0x08,0x00,0x0a,0x00, + 0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04, + 0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, + 0xe5,0xf7,0x04,0xe4,0x79,0x03,0xe3,0x7b,0x01,0xe2,0x04,0x01,0xd1,0x7f,0xd0,0x65, + 0xcf,0x86,0x55,0x04,0x04,0x00,0xd4,0x33,0xd3,0x1f,0xd2,0x0c,0x51,0x04,0x04,0x00, + 0x10,0x04,0x0a,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe1,0x80, + 0xa5,0xe1,0x80,0xae,0x00,0x04,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0a,0x00,0x04, + 0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x04,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x04, + 0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x04,0x00,0x04, + 0x07,0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0x09,0x10,0x04,0x0a,0x09,0x0a, + 0x00,0x0a,0x00,0xcf,0x86,0x95,0x14,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92, + 0x08,0x11,0x04,0x04,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x2e,0xcf,0x86,0x95, + 0x28,0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a, + 0x00,0x0a,0xdc,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00,0x0b, + 0x00,0x11,0x04,0x0b,0x00,0x0a,0x00,0x01,0x00,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3, + 0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x52, + 0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x00,0x00,0x01,0x00,0x54, + 0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x06,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x06,0x00,0x08,0x00,0x10,0x04,0x08, + 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0d,0x00,0x0d,0x00,0xd1,0x3e,0xd0, + 0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x1d,0x54,0x04,0x01,0x00,0x53,0x04,0x01, + 0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, + 0x00,0x01,0xff,0x00,0x94,0x15,0x93,0x11,0x92,0x0d,0x91,0x09,0x10,0x05,0x01,0xff, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55, + 0x04,0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x0b,0x00,0x0b,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54, + 0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x0b, + 0x00,0xe2,0x21,0x01,0xd1,0x6c,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10, + 0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00, + 0x04,0x00,0x04,0x00,0xcf,0x86,0x95,0x48,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0xd3,0x10,0x52,0x04, + 0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08, + 0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00, + 0xd0,0x62,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04, + 0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00, + 0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xd4,0x14,0x53,0x04, + 0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, + 0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04, + 0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00, + 0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x93,0x10,0x52,0x04,0x04,0x00, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x94,0x14,0x53,0x04, + 0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, + 0x04,0x00,0xd1,0x9c,0xd0,0x3e,0xcf,0x86,0x95,0x38,0xd4,0x14,0x53,0x04,0x04,0x00, + 0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd3,0x14, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00, + 0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, + 0x04,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04, + 0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00,0x53,0x04,0x04,0x00,0xd2,0x0c, + 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, + 0x0c,0xe6,0x10,0x04,0x0c,0xe6,0x08,0xe6,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x08,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x53,0x04,0x04,0x00, + 0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a, + 0xcf,0x86,0x95,0x14,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04, + 0x08,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04, + 0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x11,0x00, + 0x00,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0xd3,0x30,0xd2,0x2a, + 0xd1,0x24,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0b,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00, + 0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd2,0x6c,0xd1,0x24, + 0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00, + 0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x0b,0x00, + 0x0b,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00, + 0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00, + 0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x04,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x46,0xcf,0x86,0xd5,0x28, + 0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x00, + 0x00,0x00,0x06,0x00,0x93,0x10,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x09, + 0x00,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x06,0x00,0x93,0x14,0x52,0x04,0x06,0x00, + 0xd1,0x08,0x10,0x04,0x06,0x09,0x06,0x00,0x10,0x04,0x06,0x00,0x00,0x00,0x00,0x00, + 0xcf,0x86,0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x06,0x00,0x00,0x00, + 0x00,0x00,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04, + 0x06,0x00,0x00,0x00,0x06,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00, + 0x00,0x00,0x06,0x00,0x00,0x00,0x00,0x00,0xd0,0x1b,0xcf,0x86,0x55,0x04,0x04,0x00, + 0x54,0x04,0x04,0x00,0x93,0x0d,0x52,0x04,0x04,0x00,0x11,0x05,0x04,0xff,0x00,0x04, + 0x00,0x04,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x51, + 0x04,0x04,0x00,0x10,0x04,0x04,0x09,0x04,0x00,0x04,0x00,0x52,0x04,0x04,0x00,0x91, + 0x08,0x10,0x04,0x04,0x00,0x07,0xe6,0x00,0x00,0xd4,0x10,0x53,0x04,0x04,0x00,0x92, + 0x08,0x11,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x08,0x11, + 0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xe4,0xb7,0x03,0xe3,0x58,0x01,0xd2,0x8f,0xd1, + 0x53,0xd0,0x35,0xcf,0x86,0x95,0x2f,0xd4,0x1f,0x53,0x04,0x04,0x00,0xd2,0x0d,0x51, + 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x04,0xff,0x00,0x51,0x05,0x04,0xff,0x00,0x10, + 0x05,0x04,0xff,0x00,0x00,0x00,0x53,0x04,0x04,0x00,0x92,0x08,0x11,0x04,0x04,0x00, + 0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00, + 0x53,0x04,0x04,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x04,0x00,0x94,0x18,0x53,0x04,0x04,0x00, + 0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0xe4,0x10,0x04,0x0a,0x00,0x00,0x00, + 0x00,0x00,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x0c, + 0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x42, + 0xcf,0x86,0xd5,0x1c,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00, + 0xd1,0x08,0x10,0x04,0x07,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0xd4,0x0c, + 0x53,0x04,0x07,0x00,0x12,0x04,0x07,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x10, + 0xd1,0x08,0x10,0x04,0x07,0x00,0x07,0xde,0x10,0x04,0x07,0xe6,0x07,0xdc,0x00,0x00, + 0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00, + 0x00,0x00,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd4,0x10,0x53,0x04,0x07,0x00, + 0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x07,0x00, + 0x91,0x08,0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a,0xcf,0x86, + 0x55,0x04,0x08,0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00, + 0x0b,0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x95,0x28,0xd4,0x10,0x53,0x04,0x08,0x00, + 0x92,0x08,0x11,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0xd2,0x0c, + 0x51,0x04,0x08,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x08,0x00, + 0x07,0x00,0xd2,0xe4,0xd1,0x80,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x54,0x04,0x08,0x00, + 0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x08,0xe6, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x08,0xdc,0x08,0x00,0x08,0x00,0x11,0x04,0x00,0x00, + 0x08,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00, + 0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xd4,0x14, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00, + 0x0b,0x00,0xd3,0x10,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6, + 0x0b,0xe6,0x52,0x04,0x0b,0xe6,0xd1,0x08,0x10,0x04,0x0b,0xe6,0x00,0x00,0x10,0x04, + 0x00,0x00,0x0b,0xdc,0xd0,0x5e,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0b,0x00, + 0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0b,0x00,0x92,0x08, + 0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd4,0x10,0x53,0x04,0x0b,0x00,0x52,0x04, + 0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x10,0xe6,0x91,0x08, + 0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0xdc,0xd2,0x0c,0x51,0x04,0x10,0xdc,0x10,0x04, + 0x10,0xdc,0x10,0xe6,0xd1,0x08,0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0x04,0x10,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xe1,0x1e,0x01,0xd0,0xaa,0xcf,0x86,0xd5,0x6e,0xd4, + 0x53,0xd3,0x17,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1, + 0xac,0x85,0xe1,0xac,0xb5,0x00,0x09,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x09,0xff, + 0xe1,0xac,0x87,0xe1,0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x89, + 0xe1,0xac,0xb5,0x00,0x09,0x00,0xd1,0x0f,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8b,0xe1, + 0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8d,0xe1,0xac,0xb5,0x00, + 0x09,0x00,0x93,0x17,0x92,0x13,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac, + 0x91,0xe1,0xac,0xb5,0x00,0x09,0x00,0x09,0x00,0x09,0x00,0x54,0x04,0x09,0x00,0xd3, + 0x10,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x07,0x09,0x00,0x09,0x00,0xd2, + 0x13,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xba,0xe1,0xac, + 0xb5,0x00,0x91,0x0f,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xbc,0xe1,0xac,0xb5, + 0x00,0x09,0x00,0xcf,0x86,0xd5,0x3d,0x94,0x39,0xd3,0x31,0xd2,0x25,0xd1,0x16,0x10, + 0x0b,0x09,0xff,0xe1,0xac,0xbe,0xe1,0xac,0xb5,0x00,0x09,0xff,0xe1,0xac,0xbf,0xe1, + 0xac,0xb5,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xad,0x82,0xe1,0xac,0xb5,0x00, + 0x91,0x08,0x10,0x04,0x09,0x09,0x09,0x00,0x09,0x00,0x12,0x04,0x09,0x00,0x00,0x00, + 0x09,0x00,0xd4,0x1c,0x53,0x04,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09,0x00,0x10,0x04, + 0x09,0x00,0x09,0xe6,0x91,0x08,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0xe6,0xd3,0x08, + 0x12,0x04,0x09,0xe6,0x09,0x00,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00, + 0x00,0x00,0x00,0x00,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x18,0x53,0x04, + 0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x09,0x0d,0x09,0x11,0x04, + 0x0d,0x00,0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x0d,0x00, + 0x0d,0x00,0xcf,0x86,0x55,0x04,0x0c,0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x0c,0x00, + 0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x07,0x0c,0x00,0x0c,0x00,0xd3,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x0c,0x09,0x00,0x00,0x12,0x04,0x00,0x00,0x0c,0x00,0xe3,0xb2, + 0x01,0xe2,0x09,0x01,0xd1,0x4c,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x0a,0x00,0x54,0x04, + 0x0a,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00, + 0x0a,0x07,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00, + 0xcf,0x86,0x95,0x1c,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00, + 0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00, + 0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x14,0x00,0x54,0x04,0x14,0x00, + 0x53,0x04,0x14,0x00,0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00, + 0x91,0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x14,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x08, + 0x13,0x04,0x0d,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04, + 0x0b,0xe6,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x01,0x0b,0xdc,0x0b,0xdc,0x92,0x08, + 0x11,0x04,0x0b,0xdc,0x0b,0xe6,0x0b,0xdc,0xd4,0x28,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x01,0x0b,0x01,0xd2,0x0c,0x91,0x08,0x10,0x04, + 0x0b,0x01,0x0b,0x00,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xdc,0x0b,0x00, + 0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0d,0x00,0xd1,0x08, + 0x10,0x04,0x0d,0xe6,0x0d,0x00,0x10,0x04,0x0d,0x00,0x13,0x00,0x92,0x0c,0x51,0x04, + 0x10,0xe6,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06, + 0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x94,0x0c,0x53,0x04,0x07,0x00,0x12,0x04, + 0x07,0x00,0x08,0x00,0x08,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0xd5,0x40, + 0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x51,0x04,0x08,0xe6,0x10,0x04,0x08,0xdc,0x08,0xe6, + 0x09,0xe6,0xd2,0x0c,0x51,0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x0a,0xe6,0xd1,0x08, + 0x10,0x04,0x0a,0xe6,0x0a,0xea,0x10,0x04,0x0a,0xd6,0x0a,0xdc,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x0a,0xca,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0xd4,0x14, + 0x93,0x10,0x52,0x04,0x0a,0xe6,0x51,0x04,0x0a,0xe6,0x10,0x04,0x0a,0xe6,0x10,0xe6, + 0x10,0xe6,0xd3,0x10,0x52,0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x13,0xe8, + 0x13,0xe4,0xd2,0x10,0xd1,0x08,0x10,0x04,0x13,0xe4,0x13,0xdc,0x10,0x04,0x00,0x00, + 0x12,0xe6,0xd1,0x08,0x10,0x04,0x0c,0xe9,0x0b,0xdc,0x10,0x04,0x09,0xe6,0x09,0xdc, + 0xe2,0x80,0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84, + 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa5,0x00,0x01,0xff, + 0x61,0xcc,0xa5,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc, + 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x42,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc, + 0xa3,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00, + 0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x43,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff, + 0x63,0xcc,0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0x87,0x00,0x01,0xff, + 0x64,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa3,0x00,0x01,0xff, + 0x64,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc, + 0xb1,0x00,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa7,0x00, + 0x01,0xff,0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xad,0x00,0x01,0xff, + 0x64,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc,0x80,0x00, + 0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc, + 0x81,0x00,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x45,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff, + 0x45,0xcc,0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x45,0xcc,0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08, + 0x01,0xff,0x46,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc, + 0x84,0x00,0x10,0x08,0x01,0xff,0x48,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00, + 0x10,0x08,0x01,0xff,0x48,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00, + 0x10,0x08,0x01,0xff,0x48,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0x49,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a, + 0x01,0xff,0x49,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00, + 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0x81,0x00,0x01,0xff, + 0x6b,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc, + 0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc, + 0xb1,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00, + 0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff, + 0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xb1,0x00,0x01,0xff, + 0x6c,0xcc,0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4c,0xcc,0xad,0x00,0x01,0xff, + 0x6c,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x4d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc, + 0x81,0x00,0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x4d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01, + 0xff,0x4d,0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x4e,0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x4e, + 0xcc,0xa3,0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x4e,0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x4e, + 0xcc,0xad,0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f, + 0xcc,0x83,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01, + 0xff,0x4f,0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3, + 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x80,0x00,0x01, + 0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x81, + 0x00,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x50, + 0xcc,0x81,0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x50,0xcc,0x87, + 0x00,0x01,0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52, + 0xcc,0x87,0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa3, + 0x00,0x01,0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x52,0xcc,0xa3, + 0xcc,0x84,0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x52, + 0xcc,0xb1,0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10, + 0x08,0x01,0xff,0x53,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10, + 0x0a,0x01,0xff,0x53,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87, + 0x00,0x10,0x0a,0x01,0xff,0x53,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c, + 0xcc,0x87,0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x53,0xcc,0xa3,0xcc,0x87, + 0x00,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0x87, + 0x00,0x01,0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0xa3, + 0x00,0x01,0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xb1,0x00,0x01, + 0xff,0x74,0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x54, + 0xcc,0xad,0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa4, + 0x00,0x01,0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0xb0, + 0x00,0x01,0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xad,0x00,0x01, + 0xff,0x75,0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x83, + 0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x55, + 0xcc,0x84,0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0x56,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01, + 0xff,0x56,0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x10,0x02,0xcf,0x86, + 0xd5,0xe1,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc, + 0x80,0x00,0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x81,0x00, + 0x01,0xff,0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x88,0x00, + 0x01,0xff,0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x87,0x00,0x01,0xff, + 0x77,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0xa3,0x00, + 0x01,0xff,0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x58,0xcc,0x87,0x00,0x01,0xff, + 0x78,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x58,0xcc,0x88,0x00,0x01,0xff, + 0x78,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc, + 0x87,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0x82,0x00, + 0x01,0xff,0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x5a,0xcc,0xa3,0x00,0x01,0xff, + 0x7a,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0xb1,0x00,0x01,0xff, + 0x7a,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x68,0xcc,0xb1,0x00,0x01,0xff,0x74,0xcc, + 0x88,0x00,0x92,0x1d,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01,0xff, + 0x79,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x02,0xff,0xc5,0xbf,0xcc,0x87,0x00,0x0a, + 0x00,0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa3, + 0x00,0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x89,0x00,0x01, + 0xff,0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x81, + 0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82, + 0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10, + 0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89, + 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82, + 0xcc,0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x82,0x00,0x01, + 0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x81, + 0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10, + 0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80, + 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86, + 0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x83,0x00,0x01, + 0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x86, + 0x00,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0x45,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x45, + 0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45, + 0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82, + 0xcc,0x81,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01, + 0xd4,0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82,0xcc, + 0x80,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc, + 0x82,0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a, + 0x01,0xff,0x45,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00, + 0x10,0x0a,0x01,0xff,0x45,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc, + 0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x89,0x00,0x01,0xff, + 0x69,0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc, + 0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc, + 0xa3,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00, + 0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc,0x81,0x00, + 0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc, + 0x80,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x4f,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a, + 0x01,0xff,0x4f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00, + 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, + 0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x81,0x00, + 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc, + 0x9b,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff, + 0x4f,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98, + 0xd3,0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x83,0x00, + 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc, + 0xa3,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0x55,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x55,0xcc, + 0x89,0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x55,0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a, + 0x01,0xff,0x55,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00, + 0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc, + 0x9b,0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff, + 0x75,0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff, + 0x55,0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08, + 0x01,0xff,0x59,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0x59,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff, + 0x59,0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0x92,0x14,0x91,0x10,0x10,0x08, + 0x01,0xff,0x59,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x0a,0x00,0x0a,0x00, + 0xe1,0xc0,0x04,0xe0,0x80,0x02,0xcf,0x86,0xe5,0x2d,0x01,0xd4,0xa8,0xd3,0x54,0xd2, + 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1, + 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, + 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82, + 0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x91,0xcc,0x93,0x00,0x01,0xff, + 0xce,0x91,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80,0x00, + 0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce, + 0x91,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x81,0x00,0x10, + 0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x91,0xcc,0x94, + 0xcd,0x82,0x00,0xd3,0x42,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc, + 0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc, + 0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10, + 0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94, + 0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x95,0xcc, + 0x93,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x95,0xcc, + 0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10, + 0x0b,0x01,0xff,0xce,0x95,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x95,0xcc,0x94, + 0xcc,0x81,0x00,0x00,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80, + 0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff, + 0xce,0xb7,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd, + 0x82,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xce,0x97,0xcc,0x93,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0x00,0x10, + 0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x94, + 0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81,0x00, + 0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc, + 0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x82,0x00,0xd3,0x54,0xd2, + 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9, + 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, + 0xce,0xb9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc, + 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, + 0xff,0xce,0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82, + 0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x93,0x00,0x01,0xff, + 0xce,0x99,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcc,0x80,0x00, + 0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce, + 0x99,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x81,0x00,0x10, + 0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x99,0xcc,0x94, + 0xcd,0x82,0x00,0xcf,0x86,0xe5,0x13,0x01,0xd4,0x84,0xd3,0x42,0xd2,0x28,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00, + 0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc, + 0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x81, + 0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xce,0x9f,0xcc,0x93,0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0x00, + 0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc, + 0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x81, + 0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x54,0xd2,0x28, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff,0xcf,0x85,0xcc, + 0x94,0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf, + 0x85,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93, + 0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, + 0xcf,0x85,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00, + 0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0x00,0x10, + 0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x0f,0x10,0x04, + 0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x81,0x00,0x10,0x04,0x00,0x00,0x01, + 0xff,0xce,0xa5,0xcc,0x94,0xcd,0x82,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00, + 0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc, + 0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89, + 0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28, + 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xa9,0xcc,0x93,0x00,0x01,0xff,0xce,0xa9,0xcc, + 0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce, + 0xa9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93, + 0xcc,0x81,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, + 0xce,0xa9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0x00, + 0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01, + 0xff,0xce,0xb1,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01, + 0xff,0xce,0xb5,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80, + 0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff, + 0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, + 0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x91,0x12,0x10,0x09, + 0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x00,0x00, + 0xe0,0xe1,0x02,0xcf,0x86,0xe5,0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc, + 0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d, + 0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc, + 0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82, + 0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30, + 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce, + 0x91,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80, + 0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a, + 0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce, + 0x91,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93, + 0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00, + 0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7, + 0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xcd, + 0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff, + 0xce,0xb7,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd, + 0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93, + 0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff, + 0xce,0x97,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc, + 0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81, + 0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d, + 0x01,0xff,0xce,0x97,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc, + 0x94,0xcd,0x82,0xcd,0x85,0x00,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b, + 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd, + 0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01, + 0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff, + 0xcf,0x89,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc, + 0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xcd,0x85, + 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16, + 0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc, + 0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0xcd,0x85, + 0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d, + 0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc, + 0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x82, + 0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd3,0x49, + 0xd2,0x26,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce, + 0xb1,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x80,0xcd,0x85,0x00,0x01, + 0xff,0xce,0xb1,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81, + 0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff, + 0xce,0xb1,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, + 0x91,0xcc,0x86,0x00,0x01,0xff,0xce,0x91,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce, + 0x91,0xcc,0x80,0x00,0x01,0xff,0xce,0x91,0xcc,0x81,0x00,0xd1,0x0d,0x10,0x09,0x01, + 0xff,0xce,0x91,0xcd,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xb9,0x00,0x01, + 0x00,0xcf,0x86,0xe5,0x16,0x01,0xd4,0x8f,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10,0x04, + 0x01,0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc, + 0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01, + 0xff,0xce,0xb7,0xcc,0x81,0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb7, + 0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12, + 0x10,0x09,0x01,0xff,0xce,0x95,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x81,0x00, + 0x10,0x09,0x01,0xff,0xce,0x97,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00, + 0xd1,0x13,0x10,0x09,0x01,0xff,0xce,0x97,0xcd,0x85,0x00,0x01,0xff,0xe1,0xbe,0xbf, + 0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbe,0xbf,0xcc,0x81,0x00,0x01,0xff,0xe1, + 0xbe,0xbf,0xcd,0x82,0x00,0xd3,0x40,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, + 0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce, + 0xb9,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x51, + 0x04,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9, + 0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc, + 0x86,0x00,0x01,0xff,0xce,0x99,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc, + 0x80,0x00,0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x04,0x00,0x00,0x01, + 0xff,0xe1,0xbf,0xbe,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbf,0xbe,0xcc,0x81, + 0x00,0x01,0xff,0xe1,0xbf,0xbe,0xcd,0x82,0x00,0xd4,0x93,0xd3,0x4e,0xd2,0x28,0xd1, + 0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84, + 0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85, + 0xcc,0x88,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x93,0x00, + 0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcd,0x82,0x00, + 0x01,0xff,0xcf,0x85,0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xce,0xa5,0xcc,0x86,0x00,0x01,0xff,0xce,0xa5,0xcc,0x84,0x00,0x10,0x09,0x01, + 0xff,0xce,0xa5,0xcc,0x80,0x00,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0xd1,0x12,0x10, + 0x09,0x01,0xff,0xce,0xa1,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x80,0x00,0x10, + 0x09,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x01,0xff,0x60,0x00,0xd3,0x3b,0xd2,0x18, + 0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x80,0xcd,0x85,0x00,0x01, + 0xff,0xcf,0x89,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81, + 0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcd,0x82,0x00,0x01,0xff, + 0xcf,0x89,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, + 0x9f,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce, + 0xa9,0xcc,0x80,0x00,0x01,0xff,0xce,0xa9,0xcc,0x81,0x00,0xd1,0x10,0x10,0x09,0x01, + 0xff,0xce,0xa9,0xcd,0x85,0x00,0x01,0xff,0xc2,0xb4,0x00,0x10,0x04,0x01,0x00,0x00, + 0x00,0xe0,0x7e,0x0c,0xcf,0x86,0xe5,0xbb,0x08,0xe4,0x14,0x06,0xe3,0xf7,0x02,0xe2, + 0xbd,0x01,0xd1,0xd0,0xd0,0x4f,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0xd3,0x18,0x92,0x14, + 0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01,0xff,0xe2,0x80,0x83,0x00, + 0x01,0x00,0x01,0x00,0x92,0x0d,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, + 0x00,0x01,0xff,0x00,0x01,0x00,0x94,0x1b,0x53,0x04,0x01,0x00,0xd2,0x09,0x11,0x04, + 0x01,0x00,0x01,0xff,0x00,0x51,0x05,0x01,0xff,0x00,0x10,0x05,0x01,0xff,0x00,0x04, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x48,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x01,0x00,0x51, + 0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x52,0x04,0x04,0x00,0x11,0x04,0x04, + 0x00,0x06,0x00,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x06,0x00,0x07, + 0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0x52, + 0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0xd4,0x23,0xd3, + 0x14,0x52,0x05,0x06,0xff,0x00,0x91,0x0a,0x10,0x05,0x0a,0xff,0x00,0x00,0xff,0x00, + 0x0f,0xff,0x00,0x92,0x0a,0x11,0x05,0x0f,0xff,0x00,0x01,0xff,0x00,0x01,0xff,0x00, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x00,0x00,0x01,0x00, + 0x01,0x00,0xd0,0x7e,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x53,0x04,0x01,0x00,0x52,0x04, + 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xd3,0x10,0x52,0x04, + 0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0c,0x00,0x0c,0x00,0x52,0x04,0x0c,0x00, + 0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00, + 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x02,0x00,0x91,0x08,0x10,0x04, + 0x03,0x00,0x04,0x00,0x04,0x00,0xd3,0x10,0xd2,0x08,0x11,0x04,0x06,0x00,0x08,0x00, + 0x11,0x04,0x08,0x00,0x0b,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00, + 0x10,0x04,0x0e,0x00,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x11,0x00,0x13,0x00, + 0xcf,0x86,0xd5,0x28,0x54,0x04,0x00,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x01,0xe6, + 0x01,0x01,0x01,0xe6,0xd2,0x0c,0x51,0x04,0x01,0x01,0x10,0x04,0x01,0x01,0x01,0xe6, + 0x91,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x04,0x00,0xd1,0x08,0x10,0x04,0x06,0x00, + 0x06,0x01,0x10,0x04,0x06,0x01,0x06,0xe6,0x92,0x10,0xd1,0x08,0x10,0x04,0x06,0xdc, + 0x06,0xe6,0x10,0x04,0x06,0x01,0x08,0x01,0x09,0xdc,0x93,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0a,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x81,0xd0,0x4f, + 0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04, + 0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xa9,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01, + 0x00,0x10,0x06,0x01,0xff,0x4b,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00,0x01,0x00,0x53, + 0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x04, + 0x00,0x07,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0x95, + 0x2c,0xd4,0x18,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0xd1,0x08,0x10,0x04,0x08, + 0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b, + 0x00,0x10,0x04,0x0b,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x68,0xcf, + 0x86,0xd5,0x48,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x11,0x00,0x00,0x00,0x53,0x04,0x01,0x00,0x92, + 0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x90,0xcc,0xb8,0x00,0x01, + 0xff,0xe2,0x86,0x92,0xcc,0xb8,0x00,0x01,0x00,0x94,0x1a,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x94,0xcc,0xb8, + 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x87,0x90,0xcc,0xb8, + 0x00,0x10,0x0a,0x01,0xff,0xe2,0x87,0x94,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x87,0x92, + 0xcc,0xb8,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x06, + 0x00,0x06,0x00,0xe2,0x38,0x02,0xe1,0x3f,0x01,0xd0,0x68,0xcf,0x86,0xd5,0x3e,0x94, + 0x3a,0xd3,0x16,0x52,0x04,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0x83, + 0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0xd2,0x12,0x91,0x0e,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe2,0x88,0x88,0xcc,0xb8,0x00,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff,0xe2, + 0x88,0x8b,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x24,0x93,0x20,0x52, + 0x04,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa3,0xcc,0xb8,0x00,0x01, + 0x00,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa5,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0xcf,0x86,0xd5,0x48,0x94,0x44,0xd3,0x2e,0xd2,0x12,0x91,0x0e,0x10,0x04,0x01, + 0x00,0x01,0xff,0xe2,0x88,0xbc,0xcc,0xb8,0x00,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01, + 0xff,0xe2,0x89,0x83,0xcc,0xb8,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe2, + 0x89,0x85,0xcc,0xb8,0x00,0x92,0x12,0x91,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2, + 0x89,0x88,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x40,0xd3,0x1e,0x92, + 0x1a,0xd1,0x0c,0x10,0x08,0x01,0xff,0x3d,0xcc,0xb8,0x00,0x01,0x00,0x10,0x0a,0x01, + 0xff,0xe2,0x89,0xa1,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1, + 0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x89,0x8d,0xcc,0xb8,0x00,0x10,0x08,0x01, + 0xff,0x3c,0xcc,0xb8,0x00,0x01,0xff,0x3e,0xcc,0xb8,0x00,0xd3,0x30,0xd2,0x18,0x91, + 0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xa4,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xa5, + 0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xb2,0xcc,0xb8, + 0x00,0x01,0xff,0xe2,0x89,0xb3,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18,0x91,0x14,0x10, + 0x0a,0x01,0xff,0xe2,0x89,0xb6,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xb7,0xcc,0xb8, + 0x00,0x01,0x00,0x01,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x50,0x94,0x4c,0xd3,0x30,0xd2, + 0x18,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xba,0xcc,0xb8,0x00,0x01,0xff,0xe2, + 0x89,0xbb,0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x82, + 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x83,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18,0x91, + 0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x86,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x87, + 0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x30,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa2,0xcc,0xb8,0x00,0x01, + 0xff,0xe2,0x8a,0xa8,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa9,0xcc,0xb8, + 0x00,0x01,0xff,0xe2,0x8a,0xab,0xcc,0xb8,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01, + 0x00,0xd4,0x5c,0xd3,0x2c,0x92,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xbc, + 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xbd,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2, + 0x8a,0x91,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x92,0xcc,0xb8,0x00,0x01,0x00,0xd2, + 0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb2,0xcc,0xb8,0x00,0x01, + 0xff,0xe2,0x8a,0xb3,0xcc,0xb8,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb4, + 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0xb5,0xcc,0xb8,0x00,0x01,0x00,0x93,0x0c,0x92, + 0x08,0x11,0x04,0x01,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xd1,0x64,0xd0,0x3e,0xcf, + 0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x20,0x53,0x04,0x01,0x00,0x92, + 0x18,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x80,0x88,0x00,0x10,0x08,0x01, + 0xff,0xe3,0x80,0x89,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01, + 0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00,0x04,0x00,0xd0, + 0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51, + 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5, + 0x2c,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00,0x10, + 0x04,0x06,0x00,0x07,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x08, + 0x00,0x08,0x00,0x08,0x00,0x12,0x04,0x08,0x00,0x09,0x00,0xd4,0x14,0x53,0x04,0x09, + 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xd3, + 0x08,0x12,0x04,0x0c,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10, + 0x00,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0xd3,0xa6,0xd2, + 0x74,0xd1,0x40,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18,0x93,0x14,0x52, + 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x04,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x92, + 0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01, + 0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x14,0x53, + 0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x06, + 0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x06, + 0x00,0x07,0x00,0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54, + 0x04,0x01,0x00,0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06,0x00,0x06, + 0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x13,0x04,0x04, + 0x00,0x06,0x00,0xd2,0xdc,0xd1,0x48,0xd0,0x26,0xcf,0x86,0x95,0x20,0x54,0x04,0x01, + 0x00,0xd3,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x07,0x00,0x06,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x08,0x00,0x04,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55, + 0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x04,0x00,0x06, + 0x00,0x06,0x00,0x52,0x04,0x06,0x00,0x11,0x04,0x06,0x00,0x08,0x00,0xd0,0x5e,0xcf, + 0x86,0xd5,0x2c,0xd4,0x10,0x53,0x04,0x06,0x00,0x92,0x08,0x11,0x04,0x06,0x00,0x07, + 0x00,0x07,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x52, + 0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0a,0x00,0x0b,0x00,0xd4,0x10,0x93, + 0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd3,0x10,0x92, + 0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x52,0x04,0x0a, + 0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x1c,0x94, + 0x18,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b, + 0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0b,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51, + 0x04,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0c,0x00,0x0b,0x00,0x0b,0x00,0xd1, + 0xa8,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10, + 0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x01, + 0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x53, + 0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x18,0x53,0x04,0x01,0x00,0x52,0x04,0x01, + 0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x04,0x0c,0x00,0x01,0x00,0xd3, + 0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0c,0x00,0x51,0x04,0x0c, + 0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x0c,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x06,0x00,0x93,0x0c,0x52,0x04,0x06,0x00,0x11, + 0x04,0x06,0x00,0x01,0x00,0x01,0x00,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01, + 0x00,0x93,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x0c, + 0x00,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, + 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, + 0x04,0x01,0x00,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0x94,0x28,0xd3,0x10,0x52,0x04,0x08, + 0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09, + 0x00,0x10,0x04,0x09,0x00,0x0d,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0d,0x00,0x0c, + 0x00,0x06,0x00,0x94,0x0c,0x53,0x04,0x06,0x00,0x12,0x04,0x06,0x00,0x0a,0x00,0x06, + 0x00,0xe4,0x39,0x01,0xd3,0x0c,0xd2,0x06,0xcf,0x06,0x04,0x00,0xcf,0x06,0x06,0x00, + 0xd2,0x30,0xd1,0x06,0xcf,0x06,0x06,0x00,0xd0,0x06,0xcf,0x06,0x06,0x00,0xcf,0x86, + 0x95,0x1e,0x54,0x04,0x06,0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x0e, + 0x10,0x0a,0x06,0xff,0xe2,0xab,0x9d,0xcc,0xb8,0x00,0x06,0x00,0x06,0x00,0x06,0x00, + 0xd1,0x80,0xd0,0x3a,0xcf,0x86,0xd5,0x28,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04, + 0x07,0x00,0x11,0x04,0x07,0x00,0x08,0x00,0xd3,0x08,0x12,0x04,0x08,0x00,0x09,0x00, + 0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x94,0x0c, + 0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x30, + 0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, + 0x10,0x00,0x10,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, + 0x0b,0x00,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x10,0x00,0x10,0x00,0x54,0x04, + 0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00, + 0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00, + 0x11,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, + 0xd2,0x08,0x11,0x04,0x10,0x00,0x14,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x10,0x00, + 0x10,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x10,0x00,0x15,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, + 0x10,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd4,0x0c,0x53,0x04, + 0x14,0x00,0x12,0x04,0x14,0x00,0x11,0x00,0x53,0x04,0x14,0x00,0x52,0x04,0x14,0x00, + 0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0xe3,0xb9,0x01,0xd2,0xac,0xd1, + 0x68,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x08,0x00,0x94,0x14,0x53,0x04,0x08,0x00,0x52, + 0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x08,0x00,0xcf, + 0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00,0x51, + 0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x09,0x00,0x52, + 0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0xd3,0x10,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0a,0x00,0x0a,0x00,0x09,0x00,0x52,0x04,0x0a, + 0x00,0x11,0x04,0x0a,0x00,0x0b,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0x55, + 0x04,0x08,0x00,0xd4,0x1c,0x53,0x04,0x08,0x00,0xd2,0x0c,0x51,0x04,0x08,0x00,0x10, + 0x04,0x08,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd3, + 0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0d,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd1,0x6c,0xd0,0x2a,0xcf,0x86,0x55, + 0x04,0x08,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10, + 0x04,0x00,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d, + 0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x55,0x04,0x08,0x00,0xd4,0x1c,0xd3,0x0c,0x52, + 0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00, + 0x00,0x10,0x04,0x00,0x00,0x08,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10, + 0x04,0x00,0x00,0x0c,0x09,0xd0,0x5a,0xcf,0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x93, + 0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x00, + 0x00,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, + 0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, + 0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, + 0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xcf, + 0x86,0x95,0x40,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10, + 0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, + 0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, + 0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, + 0x00,0x0a,0xe6,0xd2,0x9c,0xd1,0x68,0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x08, + 0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x0a,0x00,0x11,0x04,0x08,0x00,0x0a,0x00,0x54, + 0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0d, + 0x00,0x0d,0x00,0x12,0x04,0x0d,0x00,0x10,0x00,0xcf,0x86,0x95,0x30,0x94,0x2c,0xd3, + 0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x12,0x00,0x91,0x08,0x10, + 0x04,0x12,0x00,0x13,0x00,0x13,0x00,0xd2,0x08,0x11,0x04,0x13,0x00,0x14,0x00,0x51, + 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf, + 0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51,0x04,0x04, + 0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04, + 0x00,0x54,0x04,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x06,0xcf,0x06,0x04,0x00,0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0xd5,0x14,0x54, + 0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x00, + 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x04,0x00,0x12,0x04,0x04,0x00,0x00,0x00,0xcf, + 0x86,0xe5,0xa6,0x05,0xe4,0x9f,0x05,0xe3,0x96,0x04,0xe2,0xe4,0x03,0xe1,0xc0,0x01, + 0xd0,0x3e,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c, + 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0xda,0x01,0xe4,0x91,0x08,0x10,0x04,0x01,0xe8, + 0x01,0xde,0x01,0xe0,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x04,0x00,0x10,0x04, + 0x04,0x00,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x04,0x00,0x01,0x00,0xcf,0x86, + 0xd5,0xaa,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81, + 0x8b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x8d,0xe3,0x82, + 0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81, + 0x8f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x91,0xe3,0x82, + 0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x93,0xe3,0x82,0x99, + 0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x95,0xe3,0x82,0x99,0x00,0x01,0x00, + 0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x97,0xe3,0x82,0x99,0x00,0x01, + 0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x99,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f, + 0x10,0x0b,0x01,0xff,0xe3,0x81,0x9b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01, + 0xff,0xe3,0x81,0x9d,0xe3,0x82,0x99,0x00,0x01,0x00,0xd4,0x53,0xd3,0x3c,0xd2,0x1e, + 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x9f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10, + 0x0b,0x01,0xff,0xe3,0x81,0xa1,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x04, + 0x01,0x00,0x01,0xff,0xe3,0x81,0xa4,0xe3,0x82,0x99,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe3,0x81,0xa6,0xe3,0x82,0x99,0x00,0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00, + 0x01,0xff,0xe3,0x81,0xa8,0xe3,0x82,0x99,0x00,0x01,0x00,0x01,0x00,0xd3,0x4a,0xd2, + 0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xaf,0xe3,0x82,0x99,0x00,0x01,0xff, + 0xe3,0x81,0xaf,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x81,0xb2, + 0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb2,0xe3,0x82,0x9a, + 0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb5,0xe3,0x82,0x99,0x00,0x01,0xff, + 0xe3,0x81,0xb5,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe3,0x81,0xb8,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb8,0xe3, + 0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82, + 0x99,0x00,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82,0x9a,0x00,0x01,0x00,0xd0,0xee,0xcf, + 0x86,0xd5,0x42,0x54,0x04,0x01,0x00,0xd3,0x1b,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10, + 0x0b,0x01,0xff,0xe3,0x81,0x86,0xe3,0x82,0x99,0x00,0x06,0x00,0x10,0x04,0x06,0x00, + 0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x08,0x10,0x04,0x01,0x08, + 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0x9d,0xe3,0x82,0x99, + 0x00,0x06,0x00,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x01, + 0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, + 0x82,0xab,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xad,0xe3, + 0x82,0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, + 0x82,0xaf,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb1,0xe3, + 0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb3,0xe3,0x82, + 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb5,0xe3,0x82,0x99,0x00,0x01, + 0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb7,0xe3,0x82,0x99,0x00, + 0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb9,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1, + 0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbb,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b, + 0x01,0xff,0xe3,0x82,0xbd,0xe3,0x82,0x99,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd5,0xd4, + 0x53,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbf,0xe3,0x82, + 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x81,0xe3,0x82,0x99,0x00,0x01, + 0x00,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x84,0xe3,0x82,0x99,0x00, + 0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x86,0xe3,0x82,0x99,0x00,0x92,0x13,0x91, + 0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x88,0xe3,0x82,0x99,0x00,0x01,0x00, + 0x01,0x00,0xd3,0x4a,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x83,0x8f,0xe3, + 0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x8f,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00, + 0x01,0xff,0xe3,0x83,0x92,0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, + 0x83,0x92,0xe3,0x82,0x9a,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x95,0xe3, + 0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x95,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f, + 0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x98,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01, + 0xff,0xe3,0x83,0x98,0xe3,0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff, + 0xe3,0x83,0x9b,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x9b,0xe3,0x82,0x9a,0x00, + 0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x22,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b, + 0x01,0xff,0xe3,0x82,0xa6,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x01, + 0xff,0xe3,0x83,0xaf,0xe3,0x82,0x99,0x00,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff, + 0xe3,0x83,0xb0,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0xb1,0xe3,0x82,0x99,0x00, + 0x10,0x0b,0x01,0xff,0xe3,0x83,0xb2,0xe3,0x82,0x99,0x00,0x01,0x00,0x51,0x04,0x01, + 0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0xbd,0xe3,0x82,0x99,0x00,0x06,0x00,0xd1,0x65, + 0xd0,0x46,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x91,0x08, + 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x18,0x53,0x04, + 0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04, + 0x13,0x00,0x14,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x93,0x11, + 0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x05,0x01,0xff,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0x01,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x54, + 0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x08,0x00,0x0a,0x00,0x94, + 0x0c,0x93,0x08,0x12,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x06,0x00,0xd2,0xa4,0xd1, + 0x5c,0xd0,0x22,0xcf,0x86,0x95,0x1c,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52, + 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x10,0x04,0x07,0x00,0x00, + 0x00,0x01,0x00,0xcf,0x86,0xd5,0x20,0xd4,0x0c,0x93,0x08,0x12,0x04,0x01,0x00,0x0b, + 0x00,0x0b,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x06,0x00,0x06, + 0x00,0x06,0x00,0x06,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01, + 0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55, + 0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, + 0x00,0x06,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5,0x10,0x94,0x0c,0x53, + 0x04,0x01,0x00,0x12,0x04,0x01,0x00,0x07,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53, + 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x16, + 0x00,0xd1,0x30,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54, + 0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x01,0x00,0x01, + 0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x01,0x00,0x53, + 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x07,0x00,0x54,0x04,0x01, + 0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x07,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd1,0x48,0xd0,0x40,0xcf, + 0x86,0xd5,0x06,0xcf,0x06,0x04,0x00,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x2c,0xd2, + 0x06,0xcf,0x06,0x04,0x00,0xd1,0x06,0xcf,0x06,0x04,0x00,0xd0,0x1a,0xcf,0x86,0x55, + 0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x07,0x00,0xcf,0x06,0x01,0x00,0xcf,0x86,0xcf, + 0x06,0x01,0x00,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe2,0x71,0x05,0xd1,0x8c,0xd0,0x08, + 0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xd4,0x06, + 0xcf,0x06,0x01,0x00,0xd3,0x06,0xcf,0x06,0x01,0x00,0xd2,0x06,0xcf,0x06,0x01,0x00, + 0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x10, + 0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x08,0x00,0x08,0x00,0x53,0x04, + 0x08,0x00,0x12,0x04,0x08,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0xd3,0x08, + 0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0d,0x00, + 0x11,0x00,0x11,0x00,0x93,0x0c,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x13,0x00, + 0x13,0x00,0x94,0x14,0x53,0x04,0x13,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04, + 0x13,0x00,0x14,0x00,0x14,0x00,0x00,0x00,0xe0,0xdb,0x04,0xcf,0x86,0xe5,0xdf,0x01, + 0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x74,0xd2,0x6e,0xd1,0x06,0xcf,0x06,0x04,0x00, + 0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00, + 0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c, + 0x92,0x08,0x11,0x04,0x04,0x00,0x06,0x00,0x04,0x00,0x04,0x00,0x93,0x10,0x52,0x04, + 0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86, + 0x95,0x24,0x94,0x20,0x93,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00, + 0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x10,0x04,0x04,0x00,0x00,0x00, + 0x00,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x06,0x0a,0x00,0xd2,0x84,0xd1,0x4c,0xd0,0x16, + 0xcf,0x86,0x55,0x04,0x0a,0x00,0x94,0x0c,0x53,0x04,0x0a,0x00,0x12,0x04,0x0a,0x00, + 0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x1c,0xd3,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x0a,0x00,0x0a,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00, + 0x10,0x04,0x0a,0x00,0x0a,0xe6,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0d,0xe6,0x52,0x04, + 0x0d,0xe6,0x11,0x04,0x0a,0xe6,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x0a,0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, + 0x11,0xe6,0x0d,0xe6,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00, + 0x93,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x00,0x00,0xd1,0x40, + 0xd0,0x3a,0xcf,0x86,0xd5,0x24,0x54,0x04,0x08,0x00,0xd3,0x10,0x52,0x04,0x08,0x00, + 0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0x92,0x0c,0x51,0x04,0x09,0x00, + 0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04, + 0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x06,0x0a,0x00,0xd0,0x5e, + 0xcf,0x86,0xd5,0x28,0xd4,0x18,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0xd1,0x08, + 0x10,0x04,0x0a,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x11,0x00,0x93,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x0d,0x00,0x10,0x00,0x10,0x00,0xd4,0x1c,0x53,0x04,0x0c,0x00, + 0xd2,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0d,0x00,0x10,0x00,0x51,0x04,0x10,0x00, + 0x10,0x04,0x12,0x00,0x14,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00, + 0x11,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x1c, + 0x94,0x18,0x93,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x51,0x04,0x15,0x00, + 0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x00,0x00,0xd3,0x10, + 0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x92,0x0c, + 0x51,0x04,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0a,0x00,0x0a,0x00,0xe4,0xf2,0x02,0xe3, + 0x65,0x01,0xd2,0x98,0xd1,0x48,0xd0,0x36,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10, + 0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x09,0x08,0x00,0x08,0x00, + 0x08,0x00,0xd4,0x0c,0x53,0x04,0x08,0x00,0x12,0x04,0x08,0x00,0x00,0x00,0x53,0x04, + 0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04, + 0x09,0x00,0x54,0x04,0x09,0x00,0x13,0x04,0x09,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06, + 0x0a,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08, + 0x10,0x04,0x0a,0x09,0x12,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00, + 0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x00,0x00,0x00,0x00, + 0x54,0x04,0x0b,0xe6,0xd3,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00, + 0x52,0x04,0x0b,0x00,0x11,0x04,0x11,0x00,0x14,0x00,0xd1,0x60,0xd0,0x22,0xcf,0x86, + 0x55,0x04,0x0a,0x00,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00, + 0x10,0x04,0x0a,0x00,0x0a,0xdc,0x11,0x04,0x0a,0xdc,0x0a,0x00,0x0a,0x00,0xcf,0x86, + 0xd5,0x24,0x54,0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04, + 0x0a,0x00,0x0a,0x09,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, + 0x00,0x00,0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00, + 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04, + 0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04, + 0x0b,0x00,0x0b,0x07,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x20,0xd3,0x10, + 0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00,0x52,0x04, + 0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x53,0x04,0x0b,0x00, + 0xd2,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x0b,0x00,0x54,0x04, + 0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x00,0x00,0xd2,0xd0,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0a,0x00, + 0x54,0x04,0x0a,0x00,0x93,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04, + 0x0a,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0a,0x00, + 0x52,0x04,0x0a,0x00,0x11,0x04,0x0a,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x92,0x08, + 0x11,0x04,0x0a,0x00,0x00,0x00,0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00, + 0x12,0x04,0x0b,0x00,0x10,0x00,0xd0,0x3a,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04, + 0x0b,0x00,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0xe6, + 0xd1,0x08,0x10,0x04,0x0b,0xdc,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x11,0x04,0x0b,0x00,0x0b,0xe6, + 0xcf,0x86,0xd5,0x2c,0xd4,0x18,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00, + 0x0b,0xe6,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x00,0x00, + 0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00,0x54,0x04, + 0x0d,0x00,0x93,0x10,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x09, + 0x00,0x00,0x00,0x00,0xd1,0x8c,0xd0,0x72,0xcf,0x86,0xd5,0x4c,0xd4,0x30,0xd3,0x18, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00, + 0x10,0x04,0x0c,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00, + 0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x93,0x18,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04, + 0x0c,0x00,0x00,0x00,0x00,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04, + 0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00, + 0x10,0x04,0x0c,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x94,0x10, + 0x93,0x0c,0x52,0x04,0x11,0x00,0x11,0x04,0x10,0x00,0x15,0x00,0x00,0x00,0x11,0x00, + 0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0xd4,0x14,0x53,0x04, + 0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x00,0x00, + 0x53,0x04,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x06, + 0x02,0xff,0xff,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd1,0x76,0xd0,0x09,0xcf,0x86, + 0xcf,0x06,0x02,0xff,0xff,0xcf,0x86,0x85,0xd4,0x07,0xcf,0x06,0x02,0xff,0xff,0xd3, + 0x07,0xcf,0x06,0x02,0xff,0xff,0xd2,0x07,0xcf,0x06,0x02,0xff,0xff,0xd1,0x07,0xcf, + 0x06,0x02,0xff,0xff,0xd0,0x18,0xcf,0x86,0x55,0x05,0x02,0xff,0xff,0x94,0x0d,0x93, + 0x09,0x12,0x05,0x02,0xff,0xff,0x00,0x00,0x00,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x24, + 0x94,0x20,0xd3,0x10,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, + 0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00, + 0x0b,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x12,0x04,0x0b,0x00,0x00,0x00, + 0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00, + 0xe4,0x9c,0x10,0xe3,0x16,0x08,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x08,0x04,0xe0, + 0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0x10,0x08,0x01, + 0xff,0xe8,0xbb,0x8a,0x00,0x01,0xff,0xe8,0xb3,0x88,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe6,0xbb,0x91,0x00,0x01,0xff,0xe4,0xb8,0xb2,0x00,0x10,0x08,0x01,0xff,0xe5, + 0x8f,0xa5,0x00,0x01,0xff,0xe9,0xbe,0x9c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe9,0xbe,0x9c,0x00,0x01,0xff,0xe5,0xa5,0x91,0x00,0x10,0x08,0x01,0xff,0xe9, + 0x87,0x91,0x00,0x01,0xff,0xe5,0x96,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, + 0xa5,0x88,0x00,0x01,0xff,0xe6,0x87,0xb6,0x00,0x10,0x08,0x01,0xff,0xe7,0x99,0xa9, + 0x00,0x01,0xff,0xe7,0xbe,0x85,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe8,0x98,0xbf,0x00,0x01,0xff,0xe8,0x9e,0xba,0x00,0x10,0x08,0x01,0xff,0xe8, + 0xa3,0xb8,0x00,0x01,0xff,0xe9,0x82,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6, + 0xa8,0x82,0x00,0x01,0xff,0xe6,0xb4,0x9b,0x00,0x10,0x08,0x01,0xff,0xe7,0x83,0x99, + 0x00,0x01,0xff,0xe7,0x8f,0x9e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, + 0x90,0xbd,0x00,0x01,0xff,0xe9,0x85,0xaa,0x00,0x10,0x08,0x01,0xff,0xe9,0xa7,0xb1, + 0x00,0x01,0xff,0xe4,0xba,0x82,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x8d,0xb5, + 0x00,0x01,0xff,0xe6,0xac,0x84,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x9b,0x00,0x01, + 0xff,0xe8,0x98,0xad,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe9,0xb8,0x9e,0x00,0x01,0xff,0xe5,0xb5,0x90,0x00,0x10,0x08,0x01,0xff,0xe6, + 0xbf,0xab,0x00,0x01,0xff,0xe8,0x97,0x8d,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, + 0xa5,0xa4,0x00,0x01,0xff,0xe6,0x8b,0x89,0x00,0x10,0x08,0x01,0xff,0xe8,0x87,0x98, + 0x00,0x01,0xff,0xe8,0xa0,0x9f,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, + 0xbb,0x8a,0x00,0x01,0xff,0xe6,0x9c,0x97,0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0xaa, + 0x00,0x01,0xff,0xe7,0x8b,0xbc,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x83,0x8e, + 0x00,0x01,0xff,0xe4,0xbe,0x86,0x00,0x10,0x08,0x01,0xff,0xe5,0x86,0xb7,0x00,0x01, + 0xff,0xe5,0x8b,0x9e,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6, + 0x93,0x84,0x00,0x01,0xff,0xe6,0xab,0x93,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x90, + 0x00,0x01,0xff,0xe7,0x9b,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x80,0x81, + 0x00,0x01,0xff,0xe8,0x98,0x86,0x00,0x10,0x08,0x01,0xff,0xe8,0x99,0x9c,0x00,0x01, + 0xff,0xe8,0xb7,0xaf,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9c,0xb2, + 0x00,0x01,0xff,0xe9,0xad,0xaf,0x00,0x10,0x08,0x01,0xff,0xe9,0xb7,0xba,0x00,0x01, + 0xff,0xe7,0xa2,0x8c,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa5,0xbf,0x00,0x01, + 0xff,0xe7,0xb6,0xa0,0x00,0x10,0x08,0x01,0xff,0xe8,0x8f,0x89,0x00,0x01,0xff,0xe9, + 0x8c,0x84,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0x10,0x08, + 0x01,0xff,0xe5,0xa3,0x9f,0x00,0x01,0xff,0xe5,0xbc,0x84,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe7,0xb1,0xa0,0x00,0x01,0xff,0xe8,0x81,0xbe,0x00,0x10,0x08,0x01,0xff, + 0xe7,0x89,0xa2,0x00,0x01,0xff,0xe7,0xa3,0x8a,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe8,0xb3,0x82,0x00,0x01,0xff,0xe9,0x9b,0xb7,0x00,0x10,0x08,0x01,0xff, + 0xe5,0xa3,0x98,0x00,0x01,0xff,0xe5,0xb1,0xa2,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe6,0xa8,0x93,0x00,0x01,0xff,0xe6,0xb7,0x9a,0x00,0x10,0x08,0x01,0xff,0xe6,0xbc, + 0x8f,0x00,0x01,0xff,0xe7,0xb4,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9,0x99,0x8b,0x00,0x10,0x08,0x01,0xff, + 0xe5,0x8b,0x92,0x00,0x01,0xff,0xe8,0x82,0x8b,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe5,0x87,0x9c,0x00,0x01,0xff,0xe5,0x87,0x8c,0x00,0x10,0x08,0x01,0xff,0xe7,0xa8, + 0x9c,0x00,0x01,0xff,0xe7,0xb6,0xbe,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe8,0x8f,0xb1,0x00,0x01,0xff,0xe9,0x99,0xb5,0x00,0x10,0x08,0x01,0xff,0xe8,0xae, + 0x80,0x00,0x01,0xff,0xe6,0x8b,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xa8, + 0x82,0x00,0x01,0xff,0xe8,0xab,0xbe,0x00,0x10,0x08,0x01,0xff,0xe4,0xb8,0xb9,0x00, + 0x01,0xff,0xe5,0xaf,0xa7,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe6,0x80,0x92,0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0x10,0x08,0x01,0xff, + 0xe7,0x95,0xb0,0x00,0x01,0xff,0xe5,0x8c,0x97,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe7,0xa3,0xbb,0x00,0x01,0xff,0xe4,0xbe,0xbf,0x00,0x10,0x08,0x01,0xff,0xe5,0xbe, + 0xa9,0x00,0x01,0xff,0xe4,0xb8,0x8d,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe6,0xb3,0x8c,0x00,0x01,0xff,0xe6,0x95,0xb8,0x00,0x10,0x08,0x01,0xff,0xe7,0xb4, + 0xa2,0x00,0x01,0xff,0xe5,0x8f,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xa1, + 0x9e,0x00,0x01,0xff,0xe7,0x9c,0x81,0x00,0x10,0x08,0x01,0xff,0xe8,0x91,0x89,0x00, + 0x01,0xff,0xe8,0xaa,0xaa,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe6,0xae,0xba,0x00,0x01,0xff,0xe8,0xbe,0xb0,0x00,0x10,0x08,0x01,0xff,0xe6,0xb2, + 0x88,0x00,0x01,0xff,0xe6,0x8b,0xbe,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x8b, + 0xa5,0x00,0x01,0xff,0xe6,0x8e,0xa0,0x00,0x10,0x08,0x01,0xff,0xe7,0x95,0xa5,0x00, + 0x01,0xff,0xe4,0xba,0xae,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x85, + 0xa9,0x00,0x01,0xff,0xe5,0x87,0x89,0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0x81,0x00, + 0x01,0xff,0xe7,0xb3,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x89,0xaf,0x00, + 0x01,0xff,0xe8,0xab,0x92,0x00,0x10,0x08,0x01,0xff,0xe9,0x87,0x8f,0x00,0x01,0xff, + 0xe5,0x8b,0xb5,0x00,0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x91,0x82,0x00,0x01,0xff,0xe5,0xa5, + 0xb3,0x00,0x10,0x08,0x01,0xff,0xe5,0xbb,0xac,0x00,0x01,0xff,0xe6,0x97,0x85,0x00, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xbf,0xbe,0x00,0x01,0xff,0xe7,0xa4,0xaa,0x00, + 0x10,0x08,0x01,0xff,0xe9,0x96,0xad,0x00,0x01,0xff,0xe9,0xa9,0xaa,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xba,0x97,0x00,0x01,0xff,0xe9,0xbb,0x8e,0x00, + 0x10,0x08,0x01,0xff,0xe5,0x8a,0x9b,0x00,0x01,0xff,0xe6,0x9b,0x86,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe6,0xad,0xb7,0x00,0x01,0xff,0xe8,0xbd,0xa2,0x00,0x10,0x08, + 0x01,0xff,0xe5,0xb9,0xb4,0x00,0x01,0xff,0xe6,0x86,0x90,0x00,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x88,0x80,0x00,0x01,0xff,0xe6,0x92,0x9a,0x00, + 0x10,0x08,0x01,0xff,0xe6,0xbc,0xa3,0x00,0x01,0xff,0xe7,0x85,0x89,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe7,0x92,0x89,0x00,0x01,0xff,0xe7,0xa7,0x8a,0x00,0x10,0x08, + 0x01,0xff,0xe7,0xb7,0xb4,0x00,0x01,0xff,0xe8,0x81,0xaf,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe8,0xbc,0xa6,0x00,0x01,0xff,0xe8,0x93,0xae,0x00,0x10,0x08, + 0x01,0xff,0xe9,0x80,0xa3,0x00,0x01,0xff,0xe9,0x8d,0x8a,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe5,0x88,0x97,0x00,0x01,0xff,0xe5,0x8a,0xa3,0x00,0x10,0x08,0x01,0xff, + 0xe5,0x92,0xbd,0x00,0x01,0xff,0xe7,0x83,0x88,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xa3,0x82,0x00,0x01,0xff,0xe8,0xaa,0xaa,0x00, + 0x10,0x08,0x01,0xff,0xe5,0xbb,0x89,0x00,0x01,0xff,0xe5,0xbf,0xb5,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe6,0x8d,0xbb,0x00,0x01,0xff,0xe6,0xae,0xae,0x00,0x10,0x08, + 0x01,0xff,0xe7,0xb0,0xbe,0x00,0x01,0xff,0xe7,0x8d,0xb5,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe4,0xbb,0xa4,0x00,0x01,0xff,0xe5,0x9b,0xb9,0x00,0x10,0x08, + 0x01,0xff,0xe5,0xaf,0xa7,0x00,0x01,0xff,0xe5,0xb6,0xba,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe6,0x80,0x9c,0x00,0x01,0xff,0xe7,0x8e,0xb2,0x00,0x10,0x08,0x01,0xff, + 0xe7,0x91,0xa9,0x00,0x01,0xff,0xe7,0xbe,0x9a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe8,0x81,0x86,0x00,0x01,0xff,0xe9,0x88,0xb4,0x00,0x10,0x08, + 0x01,0xff,0xe9,0x9b,0xb6,0x00,0x01,0xff,0xe9,0x9d,0x88,0x00,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe9,0xa0,0x98,0x00,0x01,0xff,0xe4,0xbe,0x8b,0x00,0x10,0x08,0x01,0xff, + 0xe7,0xa6,0xae,0x00,0x01,0xff,0xe9,0x86,0xb4,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe9,0x9a,0xb8,0x00,0x01,0xff,0xe6,0x83,0xa1,0x00,0x10,0x08,0x01,0xff, + 0xe4,0xba,0x86,0x00,0x01,0xff,0xe5,0x83,0x9a,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe5,0xaf,0xae,0x00,0x01,0xff,0xe5,0xb0,0xbf,0x00,0x10,0x08,0x01,0xff,0xe6,0x96, + 0x99,0x00,0x01,0xff,0xe6,0xa8,0x82,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0x87,0x8e,0x00,0x01,0xff,0xe7, + 0x99,0x82,0x00,0x10,0x08,0x01,0xff,0xe8,0x93,0xbc,0x00,0x01,0xff,0xe9,0x81,0xbc, + 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xbe,0x8d,0x00,0x01,0xff,0xe6,0x9a,0x88, + 0x00,0x10,0x08,0x01,0xff,0xe9,0x98,0xae,0x00,0x01,0xff,0xe5,0x8a,0x89,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x9d,0xbb,0x00,0x01,0xff,0xe6,0x9f,0xb3, + 0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0x81,0x00,0x01,0xff,0xe6,0xba,0x9c,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe7,0x90,0x89,0x00,0x01,0xff,0xe7,0x95,0x99,0x00,0x10, + 0x08,0x01,0xff,0xe7,0xa1,0xab,0x00,0x01,0xff,0xe7,0xb4,0x90,0x00,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xa1,0x9e,0x00,0x01,0xff,0xe5,0x85,0xad, + 0x00,0x10,0x08,0x01,0xff,0xe6,0x88,0xae,0x00,0x01,0xff,0xe9,0x99,0xb8,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe5,0x80,0xab,0x00,0x01,0xff,0xe5,0xb4,0x99,0x00,0x10, + 0x08,0x01,0xff,0xe6,0xb7,0xaa,0x00,0x01,0xff,0xe8,0xbc,0xaa,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe5,0xbe,0x8b,0x00,0x01,0xff,0xe6,0x85,0x84,0x00,0x10, + 0x08,0x01,0xff,0xe6,0xa0,0x97,0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe9,0x9a,0x86,0x00,0x01,0xff,0xe5,0x88,0xa9,0x00,0x10,0x08,0x01, + 0xff,0xe5,0x90,0x8f,0x00,0x01,0xff,0xe5,0xb1,0xa5,0x00,0xd4,0x80,0xd3,0x40,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x98,0x93,0x00,0x01,0xff,0xe6,0x9d,0x8e, + 0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0xa8,0x00,0x01,0xff,0xe6,0xb3,0xa5,0x00,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe7,0x90,0x86,0x00,0x01,0xff,0xe7,0x97,0xa2,0x00,0x10, + 0x08,0x01,0xff,0xe7,0xbd,0xb9,0x00,0x01,0xff,0xe8,0xa3,0x8f,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe8,0xa3,0xa1,0x00,0x01,0xff,0xe9,0x87,0x8c,0x00,0x10, + 0x08,0x01,0xff,0xe9,0x9b,0xa2,0x00,0x01,0xff,0xe5,0x8c,0xbf,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe6,0xba,0xba,0x00,0x01,0xff,0xe5,0x90,0x9d,0x00,0x10,0x08,0x01, + 0xff,0xe7,0x87,0x90,0x00,0x01,0xff,0xe7,0x92,0x98,0x00,0xd3,0x40,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x01,0xff,0xe8,0x97,0xba,0x00,0x01,0xff,0xe9,0x9a,0xa3,0x00,0x10, + 0x08,0x01,0xff,0xe9,0xb1,0x97,0x00,0x01,0xff,0xe9,0xba,0x9f,0x00,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe6,0x9e,0x97,0x00,0x01,0xff,0xe6,0xb7,0x8b,0x00,0x10,0x08,0x01, + 0xff,0xe8,0x87,0xa8,0x00,0x01,0xff,0xe7,0xab,0x8b,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x01,0xff,0xe7,0xac,0xa0,0x00,0x01,0xff,0xe7,0xb2,0x92,0x00,0x10,0x08,0x01, + 0xff,0xe7,0x8b,0x80,0x00,0x01,0xff,0xe7,0x82,0x99,0x00,0xd1,0x10,0x10,0x08,0x01, + 0xff,0xe8,0xad,0x98,0x00,0x01,0xff,0xe4,0xbb,0x80,0x00,0x10,0x08,0x01,0xff,0xe8, + 0x8c,0xb6,0x00,0x01,0xff,0xe5,0x88,0xba,0x00,0xe2,0xad,0x06,0xe1,0xc4,0x03,0xe0, + 0xcb,0x01,0xcf,0x86,0xd5,0xe4,0xd4,0x74,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x01,0xff,0xe5,0x88,0x87,0x00,0x01,0xff,0xe5,0xba,0xa6,0x00,0x10,0x08,0x01,0xff, + 0xe6,0x8b,0x93,0x00,0x01,0xff,0xe7,0xb3,0x96,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe5,0xae,0x85,0x00,0x01,0xff,0xe6,0xb4,0x9e,0x00,0x10,0x08,0x01,0xff,0xe6,0x9a, + 0xb4,0x00,0x01,0xff,0xe8,0xbc,0xbb,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, + 0xe8,0xa1,0x8c,0x00,0x01,0xff,0xe9,0x99,0x8d,0x00,0x10,0x08,0x01,0xff,0xe8,0xa6, + 0x8b,0x00,0x01,0xff,0xe5,0xbb,0x93,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0xe5,0x85, + 0x80,0x00,0x01,0xff,0xe5,0x97,0x80,0x00,0x01,0x00,0xd3,0x34,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x01,0xff,0xe5,0xa1,0x9a,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe6,0x99, + 0xb4,0x00,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe5,0x87,0x9e,0x00, + 0x10,0x08,0x01,0xff,0xe7,0x8c,0xaa,0x00,0x01,0xff,0xe7,0x9b,0x8a,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa4,0xbc,0x00,0x01,0xff,0xe7,0xa5,0x9e,0x00, + 0x10,0x08,0x01,0xff,0xe7,0xa5,0xa5,0x00,0x01,0xff,0xe7,0xa6,0x8f,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe9,0x9d,0x96,0x00,0x01,0xff,0xe7,0xb2,0xbe,0x00,0x10,0x08, + 0x01,0xff,0xe7,0xbe,0xbd,0x00,0x01,0x00,0xd4,0x64,0xd3,0x30,0xd2,0x18,0xd1,0x0c, + 0x10,0x08,0x01,0xff,0xe8,0x98,0x92,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe8,0xab, + 0xb8,0x00,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe9,0x80,0xb8,0x00, + 0x10,0x08,0x01,0xff,0xe9,0x83,0xbd,0x00,0x01,0x00,0xd2,0x14,0x51,0x04,0x01,0x00, + 0x10,0x08,0x01,0xff,0xe9,0xa3,0xaf,0x00,0x01,0xff,0xe9,0xa3,0xbc,0x00,0xd1,0x10, + 0x10,0x08,0x01,0xff,0xe9,0xa4,0xa8,0x00,0x01,0xff,0xe9,0xb6,0xb4,0x00,0x10,0x08, + 0x0d,0xff,0xe9,0x83,0x9e,0x00,0x0d,0xff,0xe9,0x9a,0xb7,0x00,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x06,0xff,0xe4,0xbe,0xae,0x00,0x06,0xff,0xe5,0x83,0xa7,0x00, + 0x10,0x08,0x06,0xff,0xe5,0x85,0x8d,0x00,0x06,0xff,0xe5,0x8b,0x89,0x00,0xd1,0x10, + 0x10,0x08,0x06,0xff,0xe5,0x8b,0xa4,0x00,0x06,0xff,0xe5,0x8d,0x91,0x00,0x10,0x08, + 0x06,0xff,0xe5,0x96,0x9d,0x00,0x06,0xff,0xe5,0x98,0x86,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x06,0xff,0xe5,0x99,0xa8,0x00,0x06,0xff,0xe5,0xa1,0x80,0x00,0x10,0x08, + 0x06,0xff,0xe5,0xa2,0xa8,0x00,0x06,0xff,0xe5,0xb1,0xa4,0x00,0xd1,0x10,0x10,0x08, + 0x06,0xff,0xe5,0xb1,0xae,0x00,0x06,0xff,0xe6,0x82,0x94,0x00,0x10,0x08,0x06,0xff, + 0xe6,0x85,0xa8,0x00,0x06,0xff,0xe6,0x86,0x8e,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4, + 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe6,0x87,0xb2,0x00,0x06, + 0xff,0xe6,0x95,0x8f,0x00,0x10,0x08,0x06,0xff,0xe6,0x97,0xa2,0x00,0x06,0xff,0xe6, + 0x9a,0x91,0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe6,0xa2,0x85,0x00,0x06,0xff,0xe6, + 0xb5,0xb7,0x00,0x10,0x08,0x06,0xff,0xe6,0xb8,0x9a,0x00,0x06,0xff,0xe6,0xbc,0xa2, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0x85,0xae,0x00,0x06,0xff,0xe7, + 0x88,0xab,0x00,0x10,0x08,0x06,0xff,0xe7,0x90,0xa2,0x00,0x06,0xff,0xe7,0xa2,0x91, + 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa4,0xbe,0x00,0x06,0xff,0xe7,0xa5,0x89, + 0x00,0x10,0x08,0x06,0xff,0xe7,0xa5,0x88,0x00,0x06,0xff,0xe7,0xa5,0x90,0x00,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa5,0x96,0x00,0x06,0xff,0xe7, + 0xa5,0x9d,0x00,0x10,0x08,0x06,0xff,0xe7,0xa6,0x8d,0x00,0x06,0xff,0xe7,0xa6,0x8e, + 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa9,0x80,0x00,0x06,0xff,0xe7,0xaa,0x81, + 0x00,0x10,0x08,0x06,0xff,0xe7,0xaf,0x80,0x00,0x06,0xff,0xe7,0xb7,0xb4,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xb8,0x89,0x00,0x06,0xff,0xe7,0xb9,0x81, + 0x00,0x10,0x08,0x06,0xff,0xe7,0xbd,0xb2,0x00,0x06,0xff,0xe8,0x80,0x85,0x00,0xd1, + 0x10,0x10,0x08,0x06,0xff,0xe8,0x87,0xad,0x00,0x06,0xff,0xe8,0x89,0xb9,0x00,0x10, + 0x08,0x06,0xff,0xe8,0x89,0xb9,0x00,0x06,0xff,0xe8,0x91,0x97,0x00,0xd4,0x75,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8,0xa4,0x90,0x00,0x06,0xff,0xe8, + 0xa6,0x96,0x00,0x10,0x08,0x06,0xff,0xe8,0xac,0x81,0x00,0x06,0xff,0xe8,0xac,0xb9, + 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8,0xb3,0x93,0x00,0x06,0xff,0xe8,0xb4,0x88, + 0x00,0x10,0x08,0x06,0xff,0xe8,0xbe,0xb6,0x00,0x06,0xff,0xe9,0x80,0xb8,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe9,0x9b,0xa3,0x00,0x06,0xff,0xe9,0x9f,0xbf, + 0x00,0x10,0x08,0x06,0xff,0xe9,0xa0,0xbb,0x00,0x0b,0xff,0xe6,0x81,0xb5,0x00,0x91, + 0x11,0x10,0x09,0x0b,0xff,0xf0,0xa4,0x8b,0xae,0x00,0x0b,0xff,0xe8,0x88,0x98,0x00, + 0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe4,0xb8,0xa6,0x00, + 0x08,0xff,0xe5,0x86,0xb5,0x00,0x10,0x08,0x08,0xff,0xe5,0x85,0xa8,0x00,0x08,0xff, + 0xe4,0xbe,0x80,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0x85,0x85,0x00,0x08,0xff, + 0xe5,0x86,0x80,0x00,0x10,0x08,0x08,0xff,0xe5,0x8b,0x87,0x00,0x08,0xff,0xe5,0x8b, + 0xba,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0x96,0x9d,0x00,0x08,0xff, + 0xe5,0x95,0x95,0x00,0x10,0x08,0x08,0xff,0xe5,0x96,0x99,0x00,0x08,0xff,0xe5,0x97, + 0xa2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0xa1,0x9a,0x00,0x08,0xff,0xe5,0xa2, + 0xb3,0x00,0x10,0x08,0x08,0xff,0xe5,0xa5,0x84,0x00,0x08,0xff,0xe5,0xa5,0x94,0x00, + 0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x08,0xff,0xe5,0xa9,0xa2,0x00,0x08,0xff,0xe5,0xac,0xa8,0x00,0x10,0x08, + 0x08,0xff,0xe5,0xbb,0x92,0x00,0x08,0xff,0xe5,0xbb,0x99,0x00,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe5,0xbd,0xa9,0x00,0x08,0xff,0xe5,0xbe,0xad,0x00,0x10,0x08,0x08,0xff, + 0xe6,0x83,0x98,0x00,0x08,0xff,0xe6,0x85,0x8e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe6,0x84,0x88,0x00,0x08,0xff,0xe6,0x86,0x8e,0x00,0x10,0x08,0x08,0xff, + 0xe6,0x85,0xa0,0x00,0x08,0xff,0xe6,0x87,0xb2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe6,0x88,0xb4,0x00,0x08,0xff,0xe6,0x8f,0x84,0x00,0x10,0x08,0x08,0xff,0xe6,0x90, + 0x9c,0x00,0x08,0xff,0xe6,0x91,0x92,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe6,0x95,0x96,0x00,0x08,0xff,0xe6,0x99,0xb4,0x00,0x10,0x08,0x08,0xff, + 0xe6,0x9c,0x97,0x00,0x08,0xff,0xe6,0x9c,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe6,0x9d,0x96,0x00,0x08,0xff,0xe6,0xad,0xb9,0x00,0x10,0x08,0x08,0xff,0xe6,0xae, + 0xba,0x00,0x08,0xff,0xe6,0xb5,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe6,0xbb,0x9b,0x00,0x08,0xff,0xe6,0xbb,0x8b,0x00,0x10,0x08,0x08,0xff,0xe6,0xbc, + 0xa2,0x00,0x08,0xff,0xe7,0x80,0x9e,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x85, + 0xae,0x00,0x08,0xff,0xe7,0x9e,0xa7,0x00,0x10,0x08,0x08,0xff,0xe7,0x88,0xb5,0x00, + 0x08,0xff,0xe7,0x8a,0xaf,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe7,0x8c,0xaa,0x00,0x08,0xff,0xe7,0x91,0xb1,0x00,0x10,0x08,0x08,0xff, + 0xe7,0x94,0x86,0x00,0x08,0xff,0xe7,0x94,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe7,0x98,0x9d,0x00,0x08,0xff,0xe7,0x98,0x9f,0x00,0x10,0x08,0x08,0xff,0xe7,0x9b, + 0x8a,0x00,0x08,0xff,0xe7,0x9b,0x9b,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe7,0x9b,0xb4,0x00,0x08,0xff,0xe7,0x9d,0x8a,0x00,0x10,0x08,0x08,0xff,0xe7,0x9d, + 0x80,0x00,0x08,0xff,0xe7,0xa3,0x8c,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0xaa, + 0xb1,0x00,0x08,0xff,0xe7,0xaf,0x80,0x00,0x10,0x08,0x08,0xff,0xe7,0xb1,0xbb,0x00, + 0x08,0xff,0xe7,0xb5,0x9b,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe7,0xb7,0xb4,0x00,0x08,0xff,0xe7,0xbc,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0x80, + 0x85,0x00,0x08,0xff,0xe8,0x8d,0x92,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0x8f, + 0xaf,0x00,0x08,0xff,0xe8,0x9d,0xb9,0x00,0x10,0x08,0x08,0xff,0xe8,0xa5,0x81,0x00, + 0x08,0xff,0xe8,0xa6,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xa6, + 0x96,0x00,0x08,0xff,0xe8,0xaa,0xbf,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xb8,0x00, + 0x08,0xff,0xe8,0xab,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xac,0x81,0x00, + 0x08,0xff,0xe8,0xab,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xad,0x00,0x08,0xff, + 0xe8,0xac,0xb9,0x00,0xcf,0x86,0x95,0xde,0xd4,0x81,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x08,0xff,0xe8,0xae,0x8a,0x00,0x08,0xff,0xe8,0xb4,0x88,0x00,0x10,0x08, + 0x08,0xff,0xe8,0xbc,0xb8,0x00,0x08,0xff,0xe9,0x81,0xb2,0x00,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe9,0x86,0x99,0x00,0x08,0xff,0xe9,0x89,0xb6,0x00,0x10,0x08,0x08,0xff, + 0xe9,0x99,0xbc,0x00,0x08,0xff,0xe9,0x9b,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x08,0xff,0xe9,0x9d,0x96,0x00,0x08,0xff,0xe9,0x9f,0x9b,0x00,0x10,0x08,0x08,0xff, + 0xe9,0x9f,0xbf,0x00,0x08,0xff,0xe9,0xa0,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, + 0xe9,0xa0,0xbb,0x00,0x08,0xff,0xe9,0xac,0x92,0x00,0x10,0x08,0x08,0xff,0xe9,0xbe, + 0x9c,0x00,0x08,0xff,0xf0,0xa2,0xa1,0x8a,0x00,0xd3,0x45,0xd2,0x22,0xd1,0x12,0x10, + 0x09,0x08,0xff,0xf0,0xa2,0xa1,0x84,0x00,0x08,0xff,0xf0,0xa3,0x8f,0x95,0x00,0x10, + 0x08,0x08,0xff,0xe3,0xae,0x9d,0x00,0x08,0xff,0xe4,0x80,0x98,0x00,0xd1,0x11,0x10, + 0x08,0x08,0xff,0xe4,0x80,0xb9,0x00,0x08,0xff,0xf0,0xa5,0x89,0x89,0x00,0x10,0x09, + 0x08,0xff,0xf0,0xa5,0xb3,0x90,0x00,0x08,0xff,0xf0,0xa7,0xbb,0x93,0x00,0x92,0x14, + 0x91,0x10,0x10,0x08,0x08,0xff,0xe9,0xbd,0x83,0x00,0x08,0xff,0xe9,0xbe,0x8e,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0xe1,0x94,0x01,0xe0,0x08,0x01,0xcf,0x86,0xd5,0x42, + 0xd4,0x14,0x93,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, + 0x00,0x00,0x00,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00, + 0x01,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x00,0x00,0x04,0xff, + 0xd7,0x99,0xd6,0xb4,0x00,0x10,0x04,0x01,0x1a,0x01,0xff,0xd7,0xb2,0xd6,0xb7,0x00, + 0xd4,0x42,0x53,0x04,0x01,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, + 0xd7,0xa9,0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd7,0x82,0x00,0xd1,0x16,0x10,0x0b, + 0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7, + 0x82,0x00,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xb7,0x00,0x01,0xff,0xd7,0x90,0xd6, + 0xb8,0x00,0xd3,0x43,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xbc, + 0x00,0x01,0xff,0xd7,0x91,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x92,0xd6,0xbc, + 0x00,0x01,0xff,0xd7,0x93,0xd6,0xbc,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x94, + 0xd6,0xbc,0x00,0x01,0xff,0xd7,0x95,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x96, + 0xd6,0xbc,0x00,0x00,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x98,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0x99,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x9a,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0x9b,0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7, + 0x9c,0xd6,0xbc,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xd7,0x9e,0xd6,0xbc,0x00,0x00, + 0x00,0xcf,0x86,0x95,0x85,0x94,0x81,0xd3,0x3e,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01, + 0xff,0xd7,0xa0,0xd6,0xbc,0x00,0x01,0xff,0xd7,0xa1,0xd6,0xbc,0x00,0x10,0x04,0x00, + 0x00,0x01,0xff,0xd7,0xa3,0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7,0xa4, + 0xd6,0xbc,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xd7,0xa6,0xd6,0xbc,0x00,0x01,0xff, + 0xd7,0xa7,0xd6,0xbc,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0xa8,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0xaa,0xd6, + 0xbc,0x00,0x01,0xff,0xd7,0x95,0xd6,0xb9,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7, + 0x91,0xd6,0xbf,0x00,0x01,0xff,0xd7,0x9b,0xd6,0xbf,0x00,0x10,0x09,0x01,0xff,0xd7, + 0xa4,0xd6,0xbf,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04, + 0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00, + 0x0c,0x00,0x0c,0x00,0xcf,0x86,0x95,0x24,0xd4,0x10,0x93,0x0c,0x92,0x08,0x11,0x04, + 0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00, + 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd3,0x5a,0xd2,0x06, + 0xcf,0x06,0x01,0x00,0xd1,0x14,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x95,0x08, + 0x14,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54,0x04, + 0x01,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0xcf,0x86,0xd5,0x0c,0x94,0x08,0x13,0x04,0x01,0x00,0x00,0x00,0x05,0x00, + 0x54,0x04,0x05,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04, + 0x06,0x00,0x07,0x00,0x00,0x00,0xd2,0xce,0xd1,0xa5,0xd0,0x37,0xcf,0x86,0xd5,0x15, + 0x54,0x05,0x06,0xff,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00,0x00, + 0x00,0x00,0x00,0x94,0x1c,0xd3,0x10,0x52,0x04,0x01,0xe6,0x51,0x04,0x0a,0xe6,0x10, + 0x04,0x0a,0xe6,0x10,0xdc,0x52,0x04,0x10,0xdc,0x11,0x04,0x10,0xdc,0x11,0xe6,0x01, + 0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10, + 0x04,0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00,0x07,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x07,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01, + 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd4,0x18,0xd3,0x10,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x12,0x04,0x01, + 0x00,0x00,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06, + 0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x06,0xcf, + 0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01, + 0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x01,0xff,0x00,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10, + 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00, + 0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x94,0x14, + 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x01,0x00,0x01,0x00,0x01,0x00, + 0x01,0x00,0x01,0x00,0xd0,0x2f,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x15,0x93,0x11, + 0x92,0x0d,0x91,0x09,0x10,0x05,0x01,0xff,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01, + 0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, + 0x00,0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x18,0xd3,0x0c,0x92,0x08,0x11,0x04,0x00, + 0x00,0x01,0x00,0x01,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3, + 0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x00, + 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd4,0x20,0xd3, + 0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52, + 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x53,0x05,0x00, + 0xff,0x00,0xd2,0x0d,0x91,0x09,0x10,0x05,0x00,0xff,0x00,0x04,0x00,0x04,0x00,0x91, + 0x08,0x10,0x04,0x03,0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0x46,0x3e,0xe1,0x1f,0x3b, + 0xe0,0x9c,0x39,0xcf,0x86,0xe5,0x40,0x26,0xc4,0xe3,0x16,0x14,0xe2,0xef,0x11,0xe1, + 0xd0,0x10,0xe0,0x60,0x07,0xcf,0x86,0xe5,0x53,0x03,0xe4,0x4c,0x02,0xe3,0x3d,0x01, + 0xd2,0x94,0xd1,0x70,0xd0,0x4a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x07,0x00, + 0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00, + 0xd4,0x14,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00, + 0x00,0x00,0x07,0x00,0x53,0x04,0x07,0x00,0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04, + 0x07,0x00,0x00,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86, + 0x95,0x20,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00, + 0x00,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00, + 0x00,0x00,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x54,0x04, + 0x07,0x00,0x53,0x04,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00, + 0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x94,0x1c,0x93,0x18, + 0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x51,0x04,0x00,0x00, + 0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07,0x00,0x93,0x10, + 0x52,0x04,0x07,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00, + 0xcf,0x06,0x08,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4,0x20,0x53,0x04,0x08,0x00, + 0xd2,0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x10,0x00,0xd1,0x08,0x10,0x04, + 0x10,0x00,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x12,0x04, + 0x0a,0x00,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04, + 0x00,0x00,0x0a,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00, + 0x91,0x08,0x10,0x04,0x0a,0x00,0x0a,0xdc,0x00,0x00,0xd2,0x5e,0xd1,0x06,0xcf,0x06, + 0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00, + 0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x0a,0x00, + 0xcf,0x86,0xd5,0x18,0x54,0x04,0x0a,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x0a,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x10,0xdc,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04, + 0x10,0x00,0x12,0x04,0x10,0x00,0x00,0x00,0xd1,0x70,0xd0,0x36,0xcf,0x86,0xd5,0x18, + 0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x51,0x04,0x05,0x00, + 0x10,0x04,0x05,0x00,0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x05,0x00,0x00,0x00, + 0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x05,0x00, + 0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x05,0x00,0x92,0x0c,0x51,0x04,0x05,0x00, + 0x10,0x04,0x05,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x0c, + 0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x10,0xe6,0x92,0x0c,0x51,0x04,0x10,0xe6, + 0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04, + 0x00,0x00,0x07,0x00,0x08,0x00,0xcf,0x86,0x95,0x1c,0xd4,0x0c,0x93,0x08,0x12,0x04, + 0x08,0x00,0x00,0x00,0x08,0x00,0x93,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0xba,0xd2,0x80,0xd1,0x34,0xd0,0x1a,0xcf,0x86, + 0x55,0x04,0x05,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00, + 0x07,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x53,0x04,0x05,0x00, + 0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd0,0x2a, + 0xcf,0x86,0xd5,0x14,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00, + 0x11,0x04,0x07,0x00,0x00,0x00,0x94,0x10,0x53,0x04,0x07,0x00,0x92,0x08,0x11,0x04, + 0x07,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xcf,0x86,0xd5,0x10,0x54,0x04,0x12,0x00, + 0x93,0x08,0x12,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x54,0x04,0x12,0x00,0x53,0x04, + 0x12,0x00,0x12,0x04,0x12,0x00,0x00,0x00,0xd1,0x34,0xd0,0x12,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x10,0x00,0x00,0x00,0x52,0x04,0x00,0x00, + 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00, + 0xd2,0x06,0xcf,0x06,0x10,0x00,0xd1,0x40,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00, + 0x54,0x04,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c, + 0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x08,0x13,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe4,0xce,0x02,0xe3,0x45,0x01, + 0xd2,0xd0,0xd1,0x70,0xd0,0x52,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3,0x0c,0x52,0x04, + 0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00, + 0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07,0x00,0xd3,0x10,0x52,0x04, + 0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xd2,0x0c,0x91,0x08, + 0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x00,0x00, + 0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86,0x95,0x18,0x54,0x04,0x0b,0x00,0x93,0x10, + 0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00, + 0x10,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, + 0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14, + 0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00, + 0x10,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x11,0x00,0xd3,0x14, + 0xd2,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x04,0x11,0x00, + 0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00, + 0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x1c,0x54,0x04,0x09,0x00,0x53,0x04,0x09,0x00, + 0xd2,0x08,0x11,0x04,0x09,0x00,0x0b,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00, + 0x09,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00, + 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0xcf,0x06,0x00,0x00, + 0xd0,0x1a,0xcf,0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0x53,0x04,0x0d,0x00, + 0x52,0x04,0x00,0x00,0x11,0x04,0x11,0x00,0x0d,0x00,0xcf,0x86,0x95,0x14,0x54,0x04, + 0x11,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x11,0x00, + 0x11,0x00,0xd2,0xec,0xd1,0xa4,0xd0,0x76,0xcf,0x86,0xd5,0x48,0xd4,0x28,0xd3,0x14, + 0x52,0x04,0x08,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x10,0x04,0x08,0x00, + 0x00,0x00,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x08,0x00,0x08,0xdc,0x10,0x04, + 0x08,0x00,0x08,0xe6,0xd3,0x10,0x52,0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x00,0x00, + 0x08,0x00,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x08,0x00, + 0x08,0x00,0x54,0x04,0x08,0x00,0xd3,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x14,0x00, + 0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe6,0x08,0x01,0x10,0x04,0x08,0xdc, + 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x08,0x09,0xcf,0x86,0x95,0x28, + 0xd4,0x14,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x08,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x10,0x00, + 0x00,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x24,0xd3,0x14,0x52,0x04,0x10,0x00, + 0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0xe6,0x10,0x04,0x10,0xdc,0x00,0x00,0x92,0x0c, + 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x52,0x04, + 0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd1,0x54, + 0xd0,0x26,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52,0x04, + 0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, + 0x0b,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x0b,0x00,0x93,0x0c, + 0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x0b,0x00,0x54,0x04,0x0b,0x00, + 0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00, + 0x0b,0x00,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x54,0x04,0x10,0x00,0xd3,0x0c,0x92,0x08, + 0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, + 0x10,0x00,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14, + 0x53,0x04,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00, + 0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x96,0xd2,0x68,0xd1,0x24,0xd0,0x06, + 0xcf,0x06,0x0b,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x0b,0x00,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd0,0x1e,0xcf,0x86,0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0x93,0x10,0x92,0x0c, + 0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, + 0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x11,0x00, + 0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x11,0x00, + 0x11,0x00,0xd1,0x28,0xd0,0x22,0xcf,0x86,0x55,0x04,0x14,0x00,0xd4,0x0c,0x93,0x08, + 0x12,0x04,0x14,0x00,0x14,0xe6,0x00,0x00,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04, + 0x14,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a, + 0xd1,0x24,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04, + 0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04, + 0x0b,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x58,0xd0,0x12,0xcf,0x86,0x55,0x04, + 0x14,0x00,0x94,0x08,0x13,0x04,0x14,0x00,0x00,0x00,0x14,0x00,0xcf,0x86,0x95,0x40, + 0xd4,0x24,0xd3,0x0c,0x52,0x04,0x14,0x00,0x11,0x04,0x14,0x00,0x14,0xdc,0xd2,0x0c, + 0x51,0x04,0x14,0xe6,0x10,0x04,0x14,0xe6,0x14,0xdc,0x91,0x08,0x10,0x04,0x14,0xe6, + 0x14,0xdc,0x14,0xdc,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0xdc,0x14,0x00, + 0x14,0x00,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x15,0x00, + 0x93,0x10,0x52,0x04,0x15,0x00,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00, + 0x00,0x00,0xcf,0x86,0xe5,0x0f,0x06,0xe4,0xf8,0x03,0xe3,0x02,0x02,0xd2,0xfb,0xd1, + 0x4c,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x1c,0xd3,0x10,0x52, + 0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x09,0x0c,0x00,0x52,0x04,0x0c, + 0x00,0x11,0x04,0x0c,0x00,0x00,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x0c, + 0x00,0x0c,0x00,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00, + 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x09,0xd0,0x69,0xcf,0x86,0xd5, + 0x32,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0xd2,0x15,0x51,0x04,0x0b,0x00,0x10, + 0x0d,0x0b,0xff,0xf0,0x91,0x82,0x99,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x91,0x11, + 0x10,0x0d,0x0b,0xff,0xf0,0x91,0x82,0x9b,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x0b, + 0x00,0xd4,0x1d,0x53,0x04,0x0b,0x00,0x92,0x15,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, + 0x00,0x0b,0xff,0xf0,0x91,0x82,0xa5,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x53,0x04, + 0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x10,0x04,0x0b,0x07, + 0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3,0x0c,0x92,0x08,0x11,0x04, + 0x0b,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00, + 0x14,0x00,0x00,0x00,0x0d,0x00,0xd4,0x14,0x53,0x04,0x0d,0x00,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x08, + 0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0xd1,0x96,0xd0,0x5c,0xcf,0x86,0xd5,0x18, + 0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x0d,0x00, + 0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd4,0x26,0x53,0x04,0x0d,0x00,0x52,0x04,0x0d,0x00, + 0x51,0x04,0x0d,0x00,0x10,0x0d,0x0d,0xff,0xf0,0x91,0x84,0xb1,0xf0,0x91,0x84,0xa7, + 0x00,0x0d,0xff,0xf0,0x91,0x84,0xb2,0xf0,0x91,0x84,0xa7,0x00,0x93,0x18,0xd2,0x0c, + 0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x0d,0x09,0x91,0x08,0x10,0x04,0x0d,0x09, + 0x00,0x00,0x0d,0x00,0x0d,0x00,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04, + 0x0d,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x10,0x00, + 0x54,0x04,0x10,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00, + 0x10,0x07,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0,0x06, + 0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x91,0x08, + 0x10,0x04,0x0d,0x09,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, + 0x0d,0x00,0x11,0x00,0x10,0x04,0x11,0x07,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00, + 0x10,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04, + 0x10,0x00,0x11,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00, + 0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xc8,0xd1,0x48, + 0xd0,0x42,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, + 0x10,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x54,0x04,0x10,0x00, + 0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0x09,0x10,0x04, + 0x10,0x07,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x12,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xd0,0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x10, + 0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04, + 0x00,0x00,0x11,0x00,0x53,0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00, + 0x10,0x04,0x00,0x00,0x11,0x00,0x94,0x10,0x53,0x04,0x11,0x00,0x92,0x08,0x11,0x04, + 0x11,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x18, + 0x53,0x04,0x10,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0x07,0x10,0x04, + 0x10,0x09,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00, + 0x00,0x00,0x00,0x00,0xe1,0x27,0x01,0xd0,0x8a,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3, + 0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x10,0x00,0x10,0x00,0x91,0x08,0x10, + 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10, + 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0xd4, + 0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10, + 0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10, + 0x00,0x10,0x04,0x00,0x00,0x14,0x07,0x91,0x08,0x10,0x04,0x10,0x07,0x10,0x00,0x10, + 0x00,0xcf,0x86,0xd5,0x6a,0xd4,0x42,0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0xd2,0x19,0xd1,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0xff,0xf0,0x91,0x8d,0x87,0xf0, + 0x91,0x8c,0xbe,0x00,0x91,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x8d,0x87,0xf0,0x91, + 0x8d,0x97,0x00,0x10,0x09,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11, + 0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x52, + 0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd4,0x1c,0xd3, + 0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0xe6,0x52,0x04,0x10,0xe6,0x91, + 0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x10,0xe6,0x91, + 0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3, + 0x30,0x01,0xd2,0xb7,0xd1,0x48,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x95,0x3c, + 0xd4,0x1c,0x93,0x18,0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x09,0x12,0x00, + 0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x07,0x12,0x00,0x12,0x00,0x53,0x04,0x12,0x00, + 0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x00,0x00,0x12,0x00,0xd1,0x08,0x10,0x04, + 0x00,0x00,0x12,0x00,0x10,0x04,0x14,0xe6,0x15,0x00,0x00,0x00,0xd0,0x45,0xcf,0x86, + 0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0xd2,0x15,0x51,0x04, + 0x10,0x00,0x10,0x04,0x10,0x00,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xba, + 0x00,0xd1,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xb0,0x00, + 0x10,0x00,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xbd,0x00,0x10, + 0x00,0xcf,0x86,0x95,0x24,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10, + 0x04,0x10,0x09,0x10,0x07,0x10,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11, + 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0, + 0x40,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x0c,0x52,0x04,0x10, + 0x00,0x11,0x04,0x10,0x00,0x00,0x00,0xd2,0x1e,0x51,0x04,0x10,0x00,0x10,0x0d,0x10, + 0xff,0xf0,0x91,0x96,0xb8,0xf0,0x91,0x96,0xaf,0x00,0x10,0xff,0xf0,0x91,0x96,0xb9, + 0xf0,0x91,0x96,0xaf,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10,0x09,0xcf, + 0x86,0x95,0x2c,0xd4,0x1c,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x07,0x10, + 0x00,0x10,0x00,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0x53, + 0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0xd2, + 0xa0,0xd1,0x5c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53, + 0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10, + 0x09,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x93,0x10,0x52,0x04,0x10,0x00,0x91,0x08,0x10, + 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11, + 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12, + 0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x2a,0xcf, + 0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0xd3,0x10,0x52,0x04,0x0d,0x00,0x51, + 0x04,0x0d,0x00,0x10,0x04,0x0d,0x09,0x0d,0x07,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x53,0x04,0x0d, + 0x00,0x92,0x08,0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x54,0x04,0x11,0x00,0x53,0x04,0x11,0x00,0xd2, + 0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00, + 0x00,0x11,0x00,0x11,0x00,0x94,0x14,0x53,0x04,0x11,0x00,0x92,0x0c,0x51,0x04,0x11, + 0x00,0x10,0x04,0x11,0x00,0x11,0x09,0x00,0x00,0x11,0x00,0xcf,0x06,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xe4,0x59,0x01,0xd3,0xb2,0xd2,0x5c,0xd1,0x28,0xd0,0x22,0xcf,0x86, + 0x55,0x04,0x14,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14,0x00,0x92,0x10,0xd1,0x08, + 0x10,0x04,0x14,0x00,0x14,0x09,0x10,0x04,0x14,0x07,0x14,0x00,0x00,0x00,0xcf,0x06, + 0x00,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, + 0x00,0x00,0x10,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04, + 0x00,0x00,0x94,0x10,0x53,0x04,0x15,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00, + 0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x15,0x00,0x53,0x04,0x15,0x00, + 0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x94,0x1c,0x93,0x18,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x15,0x09,0x15,0x00,0x15,0x00,0x91,0x08,0x10,0x04,0x15,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xa0,0xd1,0x3c,0xd0,0x1e,0xcf,0x86, + 0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x93,0x10,0x52,0x04,0x13,0x00,0x91,0x08, + 0x10,0x04,0x13,0x09,0x13,0x00,0x13,0x00,0x13,0x00,0xcf,0x86,0x95,0x18,0x94,0x14, + 0x93,0x10,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x13,0x09, + 0x00,0x00,0x13,0x00,0x13,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4,0x10,0x93,0x0c, + 0x52,0x04,0x13,0x00,0x11,0x04,0x15,0x00,0x13,0x00,0x13,0x00,0x53,0x04,0x13,0x00, + 0xd2,0x0c,0x91,0x08,0x10,0x04,0x13,0x00,0x13,0x09,0x13,0x00,0x91,0x08,0x10,0x04, + 0x13,0x00,0x14,0x00,0x13,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x13,0x00, + 0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04, + 0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3,0xa9,0x01,0xd2, + 0xb0,0xd1,0x6c,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x54, + 0x04,0x12,0x00,0xd3,0x10,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12, + 0x00,0x00,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x12, + 0x09,0xcf,0x86,0xd5,0x14,0x94,0x10,0x93,0x0c,0x52,0x04,0x12,0x00,0x11,0x04,0x12, + 0x00,0x00,0x00,0x00,0x00,0x12,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12, + 0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xd0,0x3e,0xcf, + 0x86,0xd5,0x14,0x54,0x04,0x12,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x12, + 0x00,0x12,0x00,0x12,0x00,0xd4,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x93,0x10,0x52,0x04,0x12,0x00,0x51, + 0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1, + 0xa0,0xd0,0x52,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3,0x10,0x52,0x04,0x13,0x00,0x51, + 0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10, + 0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x54,0x04,0x13,0x00,0xd3,0x10,0x52, + 0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0xd2,0x0c,0x51, + 0x04,0x00,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x00, + 0x00,0x13,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x51,0x04,0x13, + 0x00,0x10,0x04,0x13,0x07,0x13,0x00,0x11,0x04,0x13,0x09,0x13,0x00,0x00,0x00,0x53, + 0x04,0x13,0x00,0x92,0x08,0x11,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x94,0x20,0xd3, + 0x10,0x52,0x04,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd0, + 0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x14,0x53,0x04,0x14,0x00,0x52,0x04,0x14,0x00,0x51, + 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x14, + 0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x14, + 0x09,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94, + 0x10,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14, + 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x15, + 0x00,0x54,0x04,0x15,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x15,0x00,0x00,0x00,0x00, + 0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0xd0, + 0xca,0xcf,0x86,0xd5,0xc2,0xd4,0x54,0xd3,0x06,0xcf,0x06,0x09,0x00,0xd2,0x06,0xcf, + 0x06,0x09,0x00,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09, + 0x00,0x94,0x14,0x53,0x04,0x09,0x00,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10, + 0x04,0x09,0x00,0x10,0x00,0x10,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x10, + 0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x11,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x68,0xd2,0x46,0xd1,0x40,0xd0, + 0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x20,0xd3,0x10,0x92, + 0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10, + 0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x09, + 0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x11, + 0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x95,0x10,0x94,0x0c,0x93, + 0x08,0x12,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x4c,0xd4,0x06,0xcf, + 0x06,0x0b,0x00,0xd3,0x40,0xd2,0x3a,0xd1,0x34,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0b, + 0x00,0xd4,0x14,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10, + 0x04,0x0b,0x00,0x00,0x00,0x53,0x04,0x15,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x4c,0xd0,0x44,0xcf, + 0x86,0xd5,0x3c,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2, + 0x2a,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x93, + 0x10,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0xd2,0x01,0xcf,0x86,0xd5,0x06,0xcf,0x06, + 0x00,0x00,0xe4,0x0b,0x01,0xd3,0x06,0xcf,0x06,0x0c,0x00,0xd2,0x84,0xd1,0x50,0xd0, + 0x1e,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x92, + 0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5, + 0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10, + 0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x10,0x00,0xd2,0x08,0x11, + 0x04,0x10,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x00,0x00,0xd0,0x06,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x00,0x00,0x10,0x00,0xd4,0x10,0x53, + 0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x93,0x10,0x52, + 0x04,0x10,0x01,0x91,0x08,0x10,0x04,0x10,0x01,0x10,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x6c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x93,0x10,0x52, + 0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x10,0xe6,0x10,0x00,0x10,0x00,0xcf, + 0x86,0xd5,0x24,0xd4,0x10,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00, + 0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x00, + 0x00,0x10,0x00,0x10,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10, + 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x00, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd0,0x0e,0xcf,0x86,0x95, + 0x08,0x14,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf, + 0x06,0x00,0x00,0xd2,0x30,0xd1,0x0c,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x06,0x14, + 0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x14,0x00,0x53,0x04,0x14,0x00,0x92, + 0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xd1,0x4c,0xd0,0x06,0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x2c,0x94, + 0x28,0xd3,0x10,0x52,0x04,0x0d,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x15,0x00,0x15, + 0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x51,0x04,0x00, + 0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0d,0x00,0x54,0x04,0x0d,0x00,0x53,0x04,0x0d, + 0x00,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x15,0x00,0xd0, + 0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x15,0x00,0x52,0x04,0x00,0x00,0x51, + 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x00,0x00,0xcf,0x86,0x55, + 0x04,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x13, + 0x00,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xcf,0x06,0x12,0x00,0xe2, + 0xc6,0x01,0xd1,0x8e,0xd0,0x86,0xcf,0x86,0xd5,0x48,0xd4,0x06,0xcf,0x06,0x12,0x00, + 0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x06,0xcf,0x06,0x12,0x00,0xd1,0x06,0xcf,0x06, + 0x12,0x00,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12,0x00,0xd4,0x14, + 0x53,0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x14,0x00, + 0x14,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0x00,0x00, + 0xd4,0x36,0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06,0x12,0x00, + 0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12,0x00,0x54,0x04,0x12,0x00, + 0x93,0x10,0x92,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0xa2,0xd4,0x9c,0xd3,0x74, + 0xd2,0x26,0xd1,0x20,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0xcf,0x06, + 0x13,0x00,0xcf,0x06,0x13,0x00,0xd1,0x48,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x13,0x00,0x53,0x04,0x13,0x00,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04, + 0x13,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x00,0x00,0x93,0x10, + 0x92,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0x94,0x0c,0x93,0x08,0x12,0x04,0x00,0x00,0x15,0x00,0x00,0x00,0x13,0x00,0xcf,0x06, + 0x13,0x00,0xd2,0x22,0xd1,0x06,0xcf,0x06,0x13,0x00,0xd0,0x06,0xcf,0x06,0x13,0x00, + 0xcf,0x86,0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x53,0x04,0x13,0x00,0x12,0x04, + 0x13,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06, + 0x00,0x00,0xd3,0x7f,0xd2,0x79,0xd1,0x34,0xd0,0x06,0xcf,0x06,0x10,0x00,0xcf,0x86, + 0x55,0x04,0x10,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00, + 0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00, + 0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0,0x3f,0xcf,0x86,0xd5,0x2c, + 0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0xd2,0x08,0x11,0x04,0x10,0x00,0x00,0x00, + 0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x01,0x10,0x00,0x94,0x0d,0x93,0x09,0x12,0x05, + 0x10,0xff,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xe1,0x96,0x04,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xcf,0x86,0xe5,0x33,0x04,0xe4,0x83,0x02,0xe3,0xf8,0x01,0xd2,0x26,0xd1,0x06,0xcf, + 0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x55,0x04,0x05,0x00,0x54, + 0x04,0x05,0x00,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x00,0x00,0x00, + 0x00,0xd1,0xef,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94,0x20,0xd3,0x10,0x52, + 0x04,0x05,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0xd5, + 0x2a,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x51,0x04,0x05, + 0x00,0x10,0x0d,0x05,0xff,0xf0,0x9d,0x85,0x97,0xf0,0x9d,0x85,0xa5,0x00,0x05,0xff, + 0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0x00,0xd4,0x75,0xd3,0x61,0xd2,0x44,0xd1, + 0x22,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85, + 0xae,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xaf, + 0x00,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85, + 0xb0,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xb1, + 0x00,0xd1,0x15,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0, + 0x9d,0x85,0xb2,0x00,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0x01,0xd2,0x08,0x11,0x04, + 0x05,0x01,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe2,0x05,0xd8,0xd3,0x12, + 0x92,0x0d,0x51,0x04,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0xff,0x00,0x05,0xff,0x00, + 0x92,0x0e,0x51,0x05,0x05,0xff,0x00,0x10,0x05,0x05,0xff,0x00,0x05,0xdc,0x05,0xdc, + 0xd0,0x97,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x05,0xdc, + 0x10,0x04,0x05,0xdc,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe6,0x05,0xe6, + 0x92,0x08,0x11,0x04,0x05,0xe6,0x05,0xdc,0x05,0x00,0x05,0x00,0xd4,0x14,0x53,0x04, + 0x05,0x00,0xd2,0x08,0x11,0x04,0x05,0x00,0x05,0xe6,0x11,0x04,0x05,0xe6,0x05,0x00, + 0x53,0x04,0x05,0x00,0xd2,0x15,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x05,0xff, + 0xf0,0x9d,0x86,0xb9,0xf0,0x9d,0x85,0xa5,0x00,0xd1,0x1e,0x10,0x0d,0x05,0xff,0xf0, + 0x9d,0x86,0xba,0xf0,0x9d,0x85,0xa5,0x00,0x05,0xff,0xf0,0x9d,0x86,0xb9,0xf0,0x9d, + 0x85,0xa5,0xf0,0x9d,0x85,0xae,0x00,0x10,0x11,0x05,0xff,0xf0,0x9d,0x86,0xba,0xf0, + 0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xae,0x00,0x05,0xff,0xf0,0x9d,0x86,0xb9,0xf0,0x9d, + 0x85,0xa5,0xf0,0x9d,0x85,0xaf,0x00,0xcf,0x86,0xd5,0x31,0xd4,0x21,0x93,0x1d,0x92, + 0x19,0x91,0x15,0x10,0x11,0x05,0xff,0xf0,0x9d,0x86,0xba,0xf0,0x9d,0x85,0xa5,0xf0, + 0x9d,0x85,0xaf,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x53,0x04,0x05,0x00, + 0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x11,0x00,0x94,0x14,0x53,0x04,0x11,0x00, + 0x92,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, + 0xd2,0x44,0xd1,0x28,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0x95,0x1c,0x94,0x18, + 0x93,0x14,0xd2,0x08,0x11,0x04,0x08,0x00,0x08,0xe6,0x91,0x08,0x10,0x04,0x08,0xe6, + 0x08,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00, + 0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x14,0x00,0x93,0x08,0x12,0x04,0x14,0x00, + 0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0xd5,0x18, + 0x54,0x04,0x07,0x00,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04, + 0x07,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x09,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04, + 0x09,0x00,0x14,0x00,0x14,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3,0x5f,0x01,0xd2,0xb4,0xd1,0x24,0xd0, + 0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x95,0x18,0x54,0x04,0x05,0x00,0x93,0x10,0x52, + 0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x05,0x00,0x05, + 0x00,0xd0,0x6a,0xcf,0x86,0xd5,0x18,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52, + 0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0xd4,0x34,0xd3, + 0x1c,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0xd1,0x08,0x10, + 0x04,0x00,0x00,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x05,0x00,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05, + 0x00,0x53,0x04,0x05,0x00,0xd2,0x0c,0x51,0x04,0x05,0x00,0x10,0x04,0x00,0x00,0x05, + 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0x95,0x20,0x94, + 0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x05,0x00,0x07,0x00,0x05,0x00,0x91, + 0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0xd1, + 0xa4,0xd0,0x6a,0xcf,0x86,0xd5,0x48,0xd4,0x28,0xd3,0x10,0x52,0x04,0x05,0x00,0x51, + 0x04,0x05,0x00,0x10,0x04,0x00,0x00,0x05,0x00,0xd2,0x0c,0x51,0x04,0x05,0x00,0x10, + 0x04,0x05,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0xd3, + 0x10,0x52,0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x52, + 0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x54,0x04,0x05, + 0x00,0x53,0x04,0x05,0x00,0xd2,0x0c,0x51,0x04,0x05,0x00,0x10,0x04,0x00,0x00,0x05, + 0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0xcf,0x86,0x95,0x34,0xd4, + 0x20,0xd3,0x14,0x52,0x04,0x05,0x00,0xd1,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x10, + 0x04,0x05,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0x93, + 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x05,0x00,0x05, + 0x00,0x05,0x00,0xcf,0x06,0x05,0x00,0xd2,0x26,0xd1,0x06,0xcf,0x06,0x05,0x00,0xd0, + 0x1a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x05,0x00,0x11, + 0x04,0x08,0x00,0x00,0x00,0x05,0x00,0x05,0x00,0xcf,0x06,0x05,0x00,0xd1,0x06,0xcf, + 0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53, + 0x04,0x05,0x00,0xd2,0x08,0x11,0x04,0x05,0x00,0x09,0x00,0x11,0x04,0x00,0x00,0x05, + 0x00,0x05,0x00,0x05,0x00,0xd4,0x52,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2,0x46,0xd1, + 0x06,0xcf,0x06,0x11,0x00,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0xd4,0x0c,0x53,0x04,0x11, + 0x00,0x12,0x04,0x11,0x00,0x00,0x00,0x53,0x04,0x00,0x00,0x92,0x0c,0x51,0x04,0x00, + 0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x11,0x00,0x11,0x00,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xe0,0xc2,0x03,0xcf,0x86, + 0xe5,0x03,0x01,0xd4,0xfc,0xd3,0xc0,0xd2,0x66,0xd1,0x60,0xd0,0x5a,0xcf,0x86,0xd5, + 0x2c,0xd4,0x14,0x93,0x10,0x52,0x04,0x12,0xe6,0x51,0x04,0x12,0xe6,0x10,0x04,0x12, + 0xe6,0x00,0x00,0x12,0xe6,0x53,0x04,0x12,0xe6,0x92,0x10,0xd1,0x08,0x10,0x04,0x12, + 0xe6,0x00,0x00,0x10,0x04,0x00,0x00,0x12,0xe6,0x12,0xe6,0x94,0x28,0xd3,0x18,0xd2, + 0x0c,0x51,0x04,0x12,0xe6,0x10,0x04,0x00,0x00,0x12,0xe6,0x91,0x08,0x10,0x04,0x12, + 0xe6,0x00,0x00,0x12,0xe6,0x92,0x0c,0x51,0x04,0x12,0xe6,0x10,0x04,0x12,0xe6,0x00, + 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x54,0xd0, + 0x36,0xcf,0x86,0x55,0x04,0x15,0x00,0xd4,0x14,0x53,0x04,0x15,0x00,0x52,0x04,0x15, + 0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x15, + 0xe6,0x51,0x04,0x15,0xe6,0x10,0x04,0x15,0xe6,0x15,0x00,0x52,0x04,0x15,0x00,0x11, + 0x04,0x15,0x00,0x00,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x15,0x00,0xd2, + 0x08,0x11,0x04,0x15,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x15,0x00,0x00,0x00,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xd2,0x36,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x15,0x00,0xd4,0x0c,0x53,0x04,0x15,0x00,0x12, + 0x04,0x15,0x00,0x15,0xe6,0x53,0x04,0x15,0x00,0xd2,0x08,0x11,0x04,0x15,0x00,0x00, + 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0xcf,0x06,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xd4,0x82,0xd3,0x7c,0xd2,0x3e,0xd1,0x06,0xcf,0x06,0x10,0x00,0xd0, + 0x06,0xcf,0x06,0x10,0x00,0xcf,0x86,0x95,0x2c,0xd4,0x18,0x93,0x14,0x52,0x04,0x10, + 0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10, + 0x00,0x93,0x10,0x52,0x04,0x10,0xdc,0x51,0x04,0x10,0xdc,0x10,0x04,0x10,0xdc,0x00, + 0x00,0x00,0x00,0x00,0x00,0xd1,0x38,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x95, + 0x2c,0xd4,0x18,0xd3,0x08,0x12,0x04,0x12,0x00,0x12,0xe6,0x92,0x0c,0x51,0x04,0x12, + 0xe6,0x10,0x04,0x12,0x07,0x15,0x00,0x00,0x00,0x53,0x04,0x12,0x00,0xd2,0x08,0x11, + 0x04,0x12,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x12,0x00,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xd3,0x82,0xd2,0x48,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x00, + 0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x93,0x10,0x92,0x0c,0x91, + 0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd0,0x1e,0xcf, + 0x86,0x55,0x04,0x14,0x00,0x54,0x04,0x14,0x00,0x93,0x10,0x52,0x04,0x14,0x00,0x91, + 0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1, + 0x34,0xd0,0x2e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0x54,0x04,0x15, + 0x00,0x53,0x04,0x15,0x00,0x52,0x04,0x15,0x00,0x11,0x04,0x15,0x00,0x00,0x00,0xcf, + 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xe2,0xb2,0x01,0xe1,0x41,0x01,0xd0,0x6e,0xcf, + 0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x0d,0x00,0x91,0x08,0x10,0x04,0x00, + 0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd4,0x30,0xd3,0x20,0xd2,0x10,0xd1, + 0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0xd1,0x08,0x10, + 0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x92,0x0c,0x91,0x08,0x10, + 0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0d, + 0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x0d,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x00, + 0x00,0x0d,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x00,0x00,0xcf,0x86,0xd5,0x74,0xd4, + 0x34,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x51, + 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00, + 0x00,0x0d,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d, + 0x00,0x0d,0x00,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10, + 0x04,0x0d,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10,0x04,0x00, + 0x00,0x0d,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10,0x04,0x00,0x00,0x0d, + 0x00,0xd4,0x30,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10, + 0x04,0x0d,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x00, + 0x00,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x0d, + 0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x0d, + 0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0xd1,0x08,0x10, + 0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0xd0,0x56,0xcf,0x86,0xd5, + 0x20,0xd4,0x14,0x53,0x04,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x00, + 0x00,0x0d,0x00,0x0d,0x00,0x53,0x04,0x0d,0x00,0x12,0x04,0x0d,0x00,0x00,0x00,0xd4, + 0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x91, + 0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10, + 0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x53,0x04,0x0d,0x00,0x12,0x04,0x0d,0x00,0x00, + 0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x93,0x0c,0x92,0x08,0x11, + 0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xe5, + 0x96,0x05,0xe4,0x28,0x03,0xe3,0xed,0x01,0xd2,0xa0,0xd1,0x1c,0xd0,0x16,0xcf,0x86, + 0x55,0x04,0x0a,0x00,0x94,0x0c,0x53,0x04,0x0a,0x00,0x12,0x04,0x0a,0x00,0x00,0x00, + 0x0a,0x00,0xcf,0x06,0x0a,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x10,0x54,0x04,0x0a,0x00, + 0x93,0x08,0x12,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x0c,0x00, + 0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0xd3,0x10, + 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x52,0x04, + 0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x10,0x00,0xcf,0x86,0xd5,0x28, + 0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00, + 0x0c,0x00,0x0c,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00, + 0x0c,0x00,0x0c,0x00,0x0c,0x00,0x54,0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00, + 0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd1,0xe4,0xd0,0x5a,0xcf,0x86,0xd5,0x20, + 0x94,0x1c,0x53,0x04,0x0b,0x00,0xd2,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, + 0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd4,0x14, + 0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, + 0x14,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0c,0x00, + 0x0c,0x00,0x52,0x04,0x0c,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x0b,0x00,0x10,0x04, + 0x0c,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x4c,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04, + 0x0c,0x00,0x10,0x04,0x0b,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0b,0x00, + 0x0c,0x00,0xd2,0x08,0x11,0x04,0x0c,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04, + 0x0b,0x00,0x0c,0x00,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04, + 0x0c,0x00,0x0b,0x00,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, + 0x0b,0x00,0xd4,0x18,0x53,0x04,0x0c,0x00,0xd2,0x08,0x11,0x04,0x0c,0x00,0x0d,0x00, + 0x91,0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0c,0x00,0xd2,0x10, + 0xd1,0x08,0x10,0x04,0x0c,0x00,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0xd1,0x08, + 0x10,0x04,0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0xd0,0x4e,0xcf,0x86, + 0xd5,0x34,0xd4,0x14,0x53,0x04,0x0c,0x00,0xd2,0x08,0x11,0x04,0x0c,0x00,0x0b,0x00, + 0x11,0x04,0x0b,0x00,0x0c,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00, + 0x0c,0x00,0x0c,0x00,0x0c,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, + 0x12,0x00,0x12,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08, + 0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00, + 0x94,0x10,0x93,0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00, + 0x0c,0x00,0xd2,0x7e,0xd1,0x78,0xd0,0x3e,0xcf,0x86,0xd5,0x1c,0x94,0x18,0x93,0x14, + 0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0x0b,0x00,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04, + 0x0b,0x00,0x0c,0x00,0x0c,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, + 0x12,0x00,0x00,0x00,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x53,0x04,0x0b,0x00,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x0c,0x92,0x08, + 0x11,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94,0x10,0x93,0x0c,0x52,0x04, + 0x13,0x00,0x11,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00, + 0xd1,0x58,0xd0,0x3a,0xcf,0x86,0x55,0x04,0x0c,0x00,0xd4,0x20,0xd3,0x10,0x92,0x0c, + 0x91,0x08,0x10,0x04,0x0c,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10,0x00, + 0x91,0x08,0x10,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0x93,0x10,0x52,0x04,0x0c,0x00, + 0x51,0x04,0x0c,0x00,0x10,0x04,0x10,0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x55,0x04, + 0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x52,0x04,0x0c,0x00,0x91,0x08, + 0x10,0x04,0x0c,0x00,0x10,0x00,0x11,0x00,0xd0,0x16,0xcf,0x86,0x95,0x10,0x54,0x04, + 0x0c,0x00,0x93,0x08,0x12,0x04,0x0c,0x00,0x10,0x00,0x10,0x00,0x0c,0x00,0xcf,0x86, + 0xd5,0x34,0xd4,0x28,0xd3,0x10,0x52,0x04,0x0c,0x00,0x91,0x08,0x10,0x04,0x0c,0x00, + 0x10,0x00,0x0c,0x00,0xd2,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x10,0x00, + 0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0x93,0x08,0x12,0x04,0x11,0x00, + 0x10,0x00,0x10,0x00,0x54,0x04,0x0c,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, + 0x0c,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x11,0x00,0xd3,0xfc,0xd2,0x6c,0xd1,0x3c, + 0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00, + 0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x10,0x00,0xcf,0x86, + 0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x10,0x00, + 0x0c,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xd0,0x06,0xcf,0x06,0x0c,0x00, + 0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0xd2,0x0c, + 0x91,0x08,0x10,0x04,0x10,0x00,0x0c,0x00,0x0c,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00, + 0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0xd1,0x54,0xd0,0x1a,0xcf,0x86,0x55,0x04, + 0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x52,0x04,0x0c,0x00,0x11,0x04, + 0x0c,0x00,0x10,0x00,0xcf,0x86,0xd5,0x1c,0x94,0x18,0xd3,0x08,0x12,0x04,0x0d,0x00, + 0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0x11,0x00, + 0x0c,0x00,0xd4,0x08,0x13,0x04,0x0c,0x00,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c, + 0x51,0x04,0x10,0x00,0x10,0x04,0x12,0x00,0x10,0x00,0x10,0x00,0xd0,0x1e,0xcf,0x86, + 0x55,0x04,0x10,0x00,0x94,0x14,0x93,0x10,0x52,0x04,0x10,0x00,0x91,0x08,0x10,0x04, + 0x12,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00, + 0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04, + 0x10,0x00,0x0c,0x00,0x0c,0x00,0xe2,0x19,0x01,0xd1,0xa8,0xd0,0x7e,0xcf,0x86,0xd5, + 0x4c,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0d,0x00,0x0c,0x00,0x0c, + 0x00,0x0c,0x00,0x0c,0x00,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0d, + 0x00,0x0c,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0d, + 0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0c,0x00,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0d, + 0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x0d,0x00,0xd4,0x1c,0xd3,0x0c,0x52, + 0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x0d,0x00,0x52,0x04,0x0c,0x00,0x91,0x08,0x10, + 0x04,0x0d,0x00,0x0c,0x00,0x0d,0x00,0x93,0x10,0x52,0x04,0x0c,0x00,0x91,0x08,0x10, + 0x04,0x0d,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x95,0x24,0x94,0x20,0x93, + 0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0c,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x11, + 0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x10,0x00,0x10, + 0x00,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0xd5,0x30,0xd4,0x10,0x93,0x0c,0x52, + 0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x10,0x00,0x10,0x00,0x93,0x1c,0xd2,0x10,0xd1, + 0x08,0x10,0x04,0x11,0x00,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0x91,0x08,0x10, + 0x04,0x13,0x00,0x15,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x52, + 0x04,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd3,0x10,0x52, + 0x04,0x10,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0x92,0x10,0xd1, + 0x08,0x10,0x04,0x13,0x00,0x14,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd1, + 0x1c,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c, + 0x00,0x93,0x08,0x12,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x10, + 0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x10,0x00,0xd3,0x10,0x52,0x04,0x10,0x00,0x91, + 0x08,0x10,0x04,0x10,0x00,0x14,0x00,0x14,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94,0x0c,0x53,0x04,0x15,0x00,0x12,0x04,0x15, + 0x00,0x00,0x00,0x00,0x00,0xe4,0x40,0x02,0xe3,0xc9,0x01,0xd2,0x5c,0xd1,0x34,0xd0, + 0x16,0xcf,0x86,0x95,0x10,0x94,0x0c,0x53,0x04,0x10,0x00,0x12,0x04,0x10,0x00,0x00, + 0x00,0x10,0x00,0x10,0x00,0xcf,0x86,0x95,0x18,0xd4,0x08,0x13,0x04,0x10,0x00,0x00, + 0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x10, + 0x00,0xd0,0x22,0xcf,0x86,0xd5,0x0c,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x10, + 0x00,0x94,0x10,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00, + 0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0xc0,0xd0,0x5e,0xcf,0x86,0xd5,0x30,0xd4, + 0x14,0x53,0x04,0x13,0x00,0x52,0x04,0x13,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x15, + 0x00,0x15,0x00,0x53,0x04,0x11,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x12, + 0x00,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0xd4,0x08,0x13, + 0x04,0x12,0x00,0x13,0x00,0xd3,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x12,0x00,0x13, + 0x00,0x10,0x04,0x13,0x00,0x12,0x00,0x12,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12, + 0x00,0x10,0x04,0x12,0x00,0x15,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x12, + 0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x53, + 0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13, + 0x00,0xd4,0x0c,0x53,0x04,0x13,0x00,0x12,0x04,0x13,0x00,0x14,0x00,0xd3,0x1c,0xd2, + 0x10,0xd1,0x08,0x10,0x04,0x14,0x00,0x15,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x51, + 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10, + 0x04,0x14,0x00,0x15,0x00,0x14,0x00,0xd0,0x62,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x93, + 0x10,0x52,0x04,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x12,0x00,0x12,0x00,0x12, + 0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x12,0x00,0x13,0x00,0x13,0x00,0x14,0x00,0xd4, + 0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x91, + 0x08,0x10,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10, + 0x04,0x15,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x15,0x00,0x53,0x04,0x14,0x00,0x92, + 0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x30,0x94,0x2c,0xd3, + 0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x11,0x00,0x14,0x00,0x10,0x04,0x14,0x00,0x15, + 0x00,0x15,0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x91, + 0x08,0x10,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x13,0x00,0x94,0x14,0x93,0x10,0x52, + 0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x14, + 0x00,0xd2,0x70,0xd1,0x40,0xd0,0x06,0xcf,0x06,0x15,0x00,0xcf,0x86,0xd5,0x10,0x54, + 0x04,0x15,0x00,0x93,0x08,0x12,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd4,0x10,0x53, + 0x04,0x14,0x00,0x52,0x04,0x14,0x00,0x11,0x04,0x14,0x00,0x00,0x00,0xd3,0x08,0x12, + 0x04,0x15,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00, + 0x00,0x00,0x00,0xd0,0x2a,0xcf,0x86,0x95,0x24,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51, + 0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x0c,0x52, + 0x04,0x15,0x00,0x11,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, + 0x00,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00, + 0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55, + 0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11, + 0x04,0x00,0x00,0x02,0x00,0xe4,0xf9,0x12,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00, + 0xd2,0xc2,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd0,0x44,0xcf,0x86,0xd5,0x3c, + 0xd4,0x06,0xcf,0x06,0x05,0x00,0xd3,0x06,0xcf,0x06,0x05,0x00,0xd2,0x2a,0xd1,0x06, + 0xcf,0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x95,0x18,0x54,0x04, + 0x05,0x00,0x93,0x10,0x52,0x04,0x05,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x0b,0x00,0xcf,0x06,0x0b,0x00,0xcf,0x86, + 0xd5,0x3c,0xd4,0x06,0xcf,0x06,0x0b,0x00,0xd3,0x06,0xcf,0x06,0x0b,0x00,0xd2,0x06, + 0xcf,0x06,0x0b,0x00,0xd1,0x24,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04, + 0x0b,0x00,0x93,0x10,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00, + 0x00,0x00,0x00,0x00,0xcf,0x06,0x0c,0x00,0xcf,0x06,0x0c,0x00,0xd4,0x32,0xd3,0x2c, + 0xd2,0x26,0xd1,0x20,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54,0x04,0x0c,0x00,0x53,0x04, + 0x0c,0x00,0x52,0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x00,0x00,0x11,0x00,0xcf,0x06, + 0x11,0x00,0xcf,0x06,0x11,0x00,0xcf,0x06,0x11,0x00,0xcf,0x06,0x11,0x00,0xcf,0x06, + 0x11,0x00,0xd1,0x48,0xd0,0x40,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x11,0x00,0xd4,0x06, + 0xcf,0x06,0x11,0x00,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2,0x26,0xd1,0x06,0xcf,0x06, + 0x11,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04,0x11,0x00,0x94,0x10,0x93,0x0c,0x92,0x08, + 0x11,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x13,0x00,0xcf,0x06,0x13,0x00, + 0xcf,0x06,0x13,0x00,0xcf,0x86,0xcf,0x06,0x13,0x00,0xd0,0x44,0xcf,0x86,0xd5,0x06, + 0xcf,0x06,0x13,0x00,0xd4,0x36,0xd3,0x06,0xcf,0x06,0x13,0x00,0xd2,0x06,0xcf,0x06, + 0x13,0x00,0xd1,0x06,0xcf,0x06,0x13,0x00,0xd0,0x06,0xcf,0x06,0x13,0x00,0xcf,0x86, + 0x55,0x04,0x13,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x13,0x00, + 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86, + 0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x68,0x11,0xe3,0x51,0x10,0xe2,0x17,0x08,0xe1, + 0x06,0x04,0xe0,0x03,0x02,0xcf,0x86,0xe5,0x06,0x01,0xd4,0x82,0xd3,0x41,0xd2,0x21, + 0xd1,0x10,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00, + 0x10,0x08,0x05,0xff,0xe4,0xb9,0x81,0x00,0x05,0xff,0xf0,0xa0,0x84,0xa2,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe4,0xbd,0xa0,0x00,0x05,0xff,0xe4,0xbe,0xae,0x00,0x10, + 0x08,0x05,0xff,0xe4,0xbe,0xbb,0x00,0x05,0xff,0xe5,0x80,0x82,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe5,0x81,0xba,0x00,0x05,0xff,0xe5,0x82,0x99,0x00,0x10, + 0x08,0x05,0xff,0xe5,0x83,0xa7,0x00,0x05,0xff,0xe5,0x83,0x8f,0x00,0xd1,0x11,0x10, + 0x08,0x05,0xff,0xe3,0x92,0x9e,0x00,0x05,0xff,0xf0,0xa0,0x98,0xba,0x00,0x10,0x08, + 0x05,0xff,0xe5,0x85,0x8d,0x00,0x05,0xff,0xe5,0x85,0x94,0x00,0xd3,0x42,0xd2,0x21, + 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x85,0xa4,0x00,0x05,0xff,0xe5,0x85,0xb7,0x00, + 0x10,0x09,0x05,0xff,0xf0,0xa0,0x94,0x9c,0x00,0x05,0xff,0xe3,0x92,0xb9,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe5,0x85,0xa7,0x00,0x05,0xff,0xe5,0x86,0x8d,0x00,0x10, + 0x09,0x05,0xff,0xf0,0xa0,0x95,0x8b,0x00,0x05,0xff,0xe5,0x86,0x97,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x86,0xa4,0x00,0x05,0xff,0xe4,0xbb,0x8c,0x00, + 0x10,0x08,0x05,0xff,0xe5,0x86,0xac,0x00,0x05,0xff,0xe5,0x86,0xb5,0x00,0xd1,0x11, + 0x10,0x09,0x05,0xff,0xf0,0xa9,0x87,0x9f,0x00,0x05,0xff,0xe5,0x87,0xb5,0x00,0x10, + 0x08,0x05,0xff,0xe5,0x88,0x83,0x00,0x05,0xff,0xe3,0x93,0x9f,0x00,0xd4,0x80,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x88,0xbb,0x00,0x05,0xff,0xe5, + 0x89,0x86,0x00,0x10,0x08,0x05,0xff,0xe5,0x89,0xb2,0x00,0x05,0xff,0xe5,0x89,0xb7, + 0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe3,0x94,0x95,0x00,0x05,0xff,0xe5,0x8b,0x87, + 0x00,0x10,0x08,0x05,0xff,0xe5,0x8b,0x89,0x00,0x05,0xff,0xe5,0x8b,0xa4,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x8b,0xba,0x00,0x05,0xff,0xe5,0x8c,0x85, + 0x00,0x10,0x08,0x05,0xff,0xe5,0x8c,0x86,0x00,0x05,0xff,0xe5,0x8c,0x97,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe5,0x8d,0x89,0x00,0x05,0xff,0xe5,0x8d,0x91,0x00,0x10, + 0x08,0x05,0xff,0xe5,0x8d,0x9a,0x00,0x05,0xff,0xe5,0x8d,0xb3,0x00,0xd3,0x39,0xd2, + 0x18,0x91,0x10,0x10,0x08,0x05,0xff,0xe5,0x8d,0xbd,0x00,0x05,0xff,0xe5,0x8d,0xbf, + 0x00,0x05,0xff,0xe5,0x8d,0xbf,0x00,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa0,0xa8, + 0xac,0x00,0x05,0xff,0xe7,0x81,0xb0,0x00,0x10,0x08,0x05,0xff,0xe5,0x8f,0x8a,0x00, + 0x05,0xff,0xe5,0x8f,0x9f,0x00,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa0, + 0xad,0xa3,0x00,0x05,0xff,0xe5,0x8f,0xab,0x00,0x10,0x08,0x05,0xff,0xe5,0x8f,0xb1, + 0x00,0x05,0xff,0xe5,0x90,0x86,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x92,0x9e, + 0x00,0x05,0xff,0xe5,0x90,0xb8,0x00,0x10,0x08,0x05,0xff,0xe5,0x91,0x88,0x00,0x05, + 0xff,0xe5,0x91,0xa8,0x00,0xcf,0x86,0xe5,0x02,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6,0x00, + 0x10,0x08,0x05,0xff,0xe5,0x94,0x90,0x00,0x05,0xff,0xe5,0x95,0x93,0x00,0xd1,0x10, + 0x10,0x08,0x05,0xff,0xe5,0x95,0xa3,0x00,0x05,0xff,0xe5,0x96,0x84,0x00,0x10,0x08, + 0x05,0xff,0xe5,0x96,0x84,0x00,0x05,0xff,0xe5,0x96,0x99,0x00,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x05,0xff,0xe5,0x96,0xab,0x00,0x05,0xff,0xe5,0x96,0xb3,0x00,0x10,0x08, + 0x05,0xff,0xe5,0x97,0x82,0x00,0x05,0xff,0xe5,0x9c,0x96,0x00,0xd1,0x10,0x10,0x08, + 0x05,0xff,0xe5,0x98,0x86,0x00,0x05,0xff,0xe5,0x9c,0x97,0x00,0x10,0x08,0x05,0xff, + 0xe5,0x99,0x91,0x00,0x05,0xff,0xe5,0x99,0xb4,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x05,0xff,0xe5,0x88,0x87,0x00,0x05,0xff,0xe5,0xa3,0xae,0x00,0x10,0x08, + 0x05,0xff,0xe5,0x9f,0x8e,0x00,0x05,0xff,0xe5,0x9f,0xb4,0x00,0xd1,0x10,0x10,0x08, + 0x05,0xff,0xe5,0xa0,0x8d,0x00,0x05,0xff,0xe5,0x9e,0x8b,0x00,0x10,0x08,0x05,0xff, + 0xe5,0xa0,0xb2,0x00,0x05,0xff,0xe5,0xa0,0xb1,0x00,0xd2,0x21,0xd1,0x11,0x10,0x08, + 0x05,0xff,0xe5,0xa2,0xac,0x00,0x05,0xff,0xf0,0xa1,0x93,0xa4,0x00,0x10,0x08,0x05, + 0xff,0xe5,0xa3,0xb2,0x00,0x05,0xff,0xe5,0xa3,0xb7,0x00,0xd1,0x10,0x10,0x08,0x05, + 0xff,0xe5,0xa4,0x86,0x00,0x05,0xff,0xe5,0xa4,0x9a,0x00,0x10,0x08,0x05,0xff,0xe5, + 0xa4,0xa2,0x00,0x05,0xff,0xe5,0xa5,0xa2,0x00,0xd4,0x7b,0xd3,0x42,0xd2,0x22,0xd1, + 0x12,0x10,0x09,0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa, + 0x00,0x10,0x08,0x05,0xff,0xe5,0xa7,0xac,0x00,0x05,0xff,0xe5,0xa8,0x9b,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe5,0xa8,0xa7,0x00,0x05,0xff,0xe5,0xa7,0x98,0x00,0x10, + 0x08,0x05,0xff,0xe5,0xa9,0xa6,0x00,0x05,0xff,0xe3,0x9b,0xae,0x00,0xd2,0x18,0x91, + 0x10,0x10,0x08,0x05,0xff,0xe3,0x9b,0xbc,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05, + 0xff,0xe5,0xac,0xbe,0x00,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0xa7,0x88,0x00, + 0x05,0xff,0xe5,0xaf,0x83,0x00,0x10,0x08,0x05,0xff,0xe5,0xaf,0x98,0x00,0x05,0xff, + 0xe5,0xaf,0xa7,0x00,0xd3,0x41,0xd2,0x21,0xd1,0x11,0x10,0x08,0x05,0xff,0xe5,0xaf, + 0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0x10,0x08,0x05,0xff,0xe5,0xaf,0xbf, + 0x00,0x05,0xff,0xe5,0xb0,0x86,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xbd,0x93, + 0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0x10,0x08,0x05,0xff,0xe3,0x9e,0x81,0x00,0x05, + 0xff,0xe5,0xb1,0xa0,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb1,0xae, + 0x00,0x05,0xff,0xe5,0xb3,0x80,0x00,0x10,0x08,0x05,0xff,0xe5,0xb2,0x8d,0x00,0x05, + 0xff,0xf0,0xa1,0xb7,0xa4,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe5,0xb5,0x83,0x00, + 0x05,0xff,0xf0,0xa1,0xb7,0xa6,0x00,0x10,0x08,0x05,0xff,0xe5,0xb5,0xae,0x00,0x05, + 0xff,0xe5,0xb5,0xab,0x00,0xe0,0x04,0x02,0xcf,0x86,0xd5,0xfe,0xd4,0x82,0xd3,0x40, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb5,0xbc,0x00,0x05,0xff,0xe5,0xb7, + 0xa1,0x00,0x10,0x08,0x05,0xff,0xe5,0xb7,0xa2,0x00,0x05,0xff,0xe3,0xa0,0xaf,0x00, + 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb7,0xbd,0x00,0x05,0xff,0xe5,0xb8,0xa8,0x00, + 0x10,0x08,0x05,0xff,0xe5,0xb8,0xbd,0x00,0x05,0xff,0xe5,0xb9,0xa9,0x00,0xd2,0x21, + 0xd1,0x11,0x10,0x08,0x05,0xff,0xe3,0xa1,0xa2,0x00,0x05,0xff,0xf0,0xa2,0x86,0x83, + 0x00,0x10,0x08,0x05,0xff,0xe3,0xa1,0xbc,0x00,0x05,0xff,0xe5,0xba,0xb0,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe5,0xba,0xb3,0x00,0x05,0xff,0xe5,0xba,0xb6,0x00,0x10, + 0x08,0x05,0xff,0xe5,0xbb,0x8a,0x00,0x05,0xff,0xf0,0xaa,0x8e,0x92,0x00,0xd3,0x3b, + 0xd2,0x22,0xd1,0x11,0x10,0x08,0x05,0xff,0xe5,0xbb,0xbe,0x00,0x05,0xff,0xf0,0xa2, + 0x8c,0xb1,0x00,0x10,0x09,0x05,0xff,0xf0,0xa2,0x8c,0xb1,0x00,0x05,0xff,0xe8,0x88, + 0x81,0x00,0x51,0x08,0x05,0xff,0xe5,0xbc,0xa2,0x00,0x10,0x08,0x05,0xff,0xe3,0xa3, + 0x87,0x00,0x05,0xff,0xf0,0xa3,0x8a,0xb8,0x00,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05, + 0xff,0xf0,0xa6,0x87,0x9a,0x00,0x05,0xff,0xe5,0xbd,0xa2,0x00,0x10,0x08,0x05,0xff, + 0xe5,0xbd,0xab,0x00,0x05,0xff,0xe3,0xa3,0xa3,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, + 0xe5,0xbe,0x9a,0x00,0x05,0xff,0xe5,0xbf,0x8d,0x00,0x10,0x08,0x05,0xff,0xe5,0xbf, + 0x97,0x00,0x05,0xff,0xe5,0xbf,0xb9,0x00,0xd4,0x81,0xd3,0x41,0xd2,0x20,0xd1,0x10, + 0x10,0x08,0x05,0xff,0xe6,0x82,0x81,0x00,0x05,0xff,0xe3,0xa4,0xba,0x00,0x10,0x08, + 0x05,0xff,0xe3,0xa4,0x9c,0x00,0x05,0xff,0xe6,0x82,0x94,0x00,0xd1,0x11,0x10,0x09, + 0x05,0xff,0xf0,0xa2,0x9b,0x94,0x00,0x05,0xff,0xe6,0x83,0x87,0x00,0x10,0x08,0x05, + 0xff,0xe6,0x85,0x88,0x00,0x05,0xff,0xe6,0x85,0x8c,0x00,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x05,0xff,0xe6,0x85,0x8e,0x00,0x05,0xff,0xe6,0x85,0x8c,0x00,0x10,0x08,0x05, + 0xff,0xe6,0x85,0xba,0x00,0x05,0xff,0xe6,0x86,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05, + 0xff,0xe6,0x86,0xb2,0x00,0x05,0xff,0xe6,0x86,0xa4,0x00,0x10,0x08,0x05,0xff,0xe6, + 0x86,0xaf,0x00,0x05,0xff,0xe6,0x87,0x9e,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, + 0x08,0x05,0xff,0xe6,0x87,0xb2,0x00,0x05,0xff,0xe6,0x87,0xb6,0x00,0x10,0x08,0x05, + 0xff,0xe6,0x88,0x90,0x00,0x05,0xff,0xe6,0x88,0x9b,0x00,0xd1,0x10,0x10,0x08,0x05, + 0xff,0xe6,0x89,0x9d,0x00,0x05,0xff,0xe6,0x8a,0xb1,0x00,0x10,0x08,0x05,0xff,0xe6, + 0x8b,0x94,0x00,0x05,0xff,0xe6,0x8d,0x90,0x00,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05, + 0xff,0xf0,0xa2,0xac,0x8c,0x00,0x05,0xff,0xe6,0x8c,0xbd,0x00,0x10,0x08,0x05,0xff, + 0xe6,0x8b,0xbc,0x00,0x05,0xff,0xe6,0x8d,0xa8,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, + 0xe6,0x8e,0x83,0x00,0x05,0xff,0xe6,0x8f,0xa4,0x00,0x10,0x09,0x05,0xff,0xf0,0xa2, + 0xaf,0xb1,0x00,0x05,0xff,0xe6,0x90,0xa2,0x00,0xcf,0x86,0xe5,0x03,0x01,0xd4,0x81, + 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x8f,0x85,0x00,0x05,0xff, + 0xe6,0x8e,0xa9,0x00,0x10,0x08,0x05,0xff,0xe3,0xa8,0xae,0x00,0x05,0xff,0xe6,0x91, + 0xa9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x91,0xbe,0x00,0x05,0xff,0xe6,0x92, + 0x9d,0x00,0x10,0x08,0x05,0xff,0xe6,0x91,0xb7,0x00,0x05,0xff,0xe3,0xa9,0xac,0x00, + 0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x95,0x8f,0x00,0x05,0xff,0xe6,0x95, + 0xac,0x00,0x10,0x09,0x05,0xff,0xf0,0xa3,0x80,0x8a,0x00,0x05,0xff,0xe6,0x97,0xa3, + 0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9b,0xb8,0x00,0x05,0xff,0xe6,0x99,0x89, + 0x00,0x10,0x08,0x05,0xff,0xe3,0xac,0x99,0x00,0x05,0xff,0xe6,0x9a,0x91,0x00,0xd3, + 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe3,0xac,0x88,0x00,0x05,0xff,0xe3, + 0xab,0xa4,0x00,0x10,0x08,0x05,0xff,0xe5,0x86,0x92,0x00,0x05,0xff,0xe5,0x86,0x95, + 0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9c,0x80,0x00,0x05,0xff,0xe6,0x9a,0x9c, + 0x00,0x10,0x08,0x05,0xff,0xe8,0x82,0xad,0x00,0x05,0xff,0xe4,0x8f,0x99,0x00,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9c,0x97,0x00,0x05,0xff,0xe6,0x9c,0x9b, + 0x00,0x10,0x08,0x05,0xff,0xe6,0x9c,0xa1,0x00,0x05,0xff,0xe6,0x9d,0x9e,0x00,0xd1, + 0x11,0x10,0x08,0x05,0xff,0xe6,0x9d,0x93,0x00,0x05,0xff,0xf0,0xa3,0x8f,0x83,0x00, + 0x10,0x08,0x05,0xff,0xe3,0xad,0x89,0x00,0x05,0xff,0xe6,0x9f,0xba,0x00,0xd4,0x82, + 0xd3,0x41,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9e,0x85,0x00,0x05,0xff, + 0xe6,0xa1,0x92,0x00,0x10,0x08,0x05,0xff,0xe6,0xa2,0x85,0x00,0x05,0xff,0xf0,0xa3, + 0x91,0xad,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xa2,0x8e,0x00,0x05,0xff,0xe6, + 0xa0,0x9f,0x00,0x10,0x08,0x05,0xff,0xe6,0xa4,0x94,0x00,0x05,0xff,0xe3,0xae,0x9d, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xa5,0x82,0x00,0x05,0xff,0xe6, + 0xa6,0xa3,0x00,0x10,0x08,0x05,0xff,0xe6,0xa7,0xaa,0x00,0x05,0xff,0xe6,0xaa,0xa8, + 0x00,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa3,0x9a,0xa3,0x00,0x05,0xff,0xe6,0xab, + 0x9b,0x00,0x10,0x08,0x05,0xff,0xe3,0xb0,0x98,0x00,0x05,0xff,0xe6,0xac,0xa1,0x00, + 0xd3,0x42,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa3,0xa2,0xa7,0x00,0x05, + 0xff,0xe6,0xad,0x94,0x00,0x10,0x08,0x05,0xff,0xe3,0xb1,0x8e,0x00,0x05,0xff,0xe6, + 0xad,0xb2,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xae,0x9f,0x00,0x05,0xff,0xe6, + 0xae,0xba,0x00,0x10,0x08,0x05,0xff,0xe6,0xae,0xbb,0x00,0x05,0xff,0xf0,0xa3,0xaa, + 0x8d,0x00,0xd2,0x23,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa1,0xb4,0x8b,0x00,0x05, + 0xff,0xf0,0xa3,0xab,0xba,0x00,0x10,0x08,0x05,0xff,0xe6,0xb1,0x8e,0x00,0x05,0xff, + 0xf0,0xa3,0xb2,0xbc,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb2,0xbf,0x00,0x05, + 0xff,0xe6,0xb3,0x8d,0x00,0x10,0x08,0x05,0xff,0xe6,0xb1,0xa7,0x00,0x05,0xff,0xe6, + 0xb4,0x96,0x00,0xe1,0x1d,0x04,0xe0,0x0c,0x02,0xcf,0x86,0xe5,0x08,0x01,0xd4,0x82, + 0xd3,0x41,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff, + 0xe6,0xb5,0xb7,0x00,0x10,0x08,0x05,0xff,0xe6,0xb5,0x81,0x00,0x05,0xff,0xe6,0xb5, + 0xa9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb5,0xb8,0x00,0x05,0xff,0xe6,0xb6, + 0x85,0x00,0x10,0x09,0x05,0xff,0xf0,0xa3,0xb4,0x9e,0x00,0x05,0xff,0xe6,0xb4,0xb4, + 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb8,0xaf,0x00,0x05,0xff,0xe6, + 0xb9,0xae,0x00,0x10,0x08,0x05,0xff,0xe3,0xb4,0xb3,0x00,0x05,0xff,0xe6,0xbb,0x8b, + 0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe6,0xbb,0x87,0x00,0x05,0xff,0xf0,0xa3,0xbb, + 0x91,0x00,0x10,0x08,0x05,0xff,0xe6,0xb7,0xb9,0x00,0x05,0xff,0xe6,0xbd,0xae,0x00, + 0xd3,0x42,0xd2,0x22,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00,0x05, + 0xff,0xf0,0xa3,0xbe,0x8e,0x00,0x10,0x08,0x05,0xff,0xe6,0xbf,0x86,0x00,0x05,0xff, + 0xe7,0x80,0xb9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x80,0x9e,0x00,0x05,0xff, + 0xe7,0x80,0x9b,0x00,0x10,0x08,0x05,0xff,0xe3,0xb6,0x96,0x00,0x05,0xff,0xe7,0x81, + 0x8a,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff, + 0xe7,0x81,0xb7,0x00,0x10,0x08,0x05,0xff,0xe7,0x82,0xad,0x00,0x05,0xff,0xf0,0xa0, + 0x94,0xa5,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0, + 0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xf0,0xa4, + 0x8e,0xab,0x00,0xd4,0x7b,0xd3,0x43,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7, + 0x88,0xa8,0x00,0x05,0xff,0xe7,0x88,0xb5,0x00,0x10,0x08,0x05,0xff,0xe7,0x89,0x90, + 0x00,0x05,0xff,0xf0,0xa4,0x98,0x88,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x8a, + 0x80,0x00,0x05,0xff,0xe7,0x8a,0x95,0x00,0x10,0x09,0x05,0xff,0xf0,0xa4,0x9c,0xb5, + 0x00,0x05,0xff,0xf0,0xa4,0xa0,0x94,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff, + 0xe7,0x8d,0xba,0x00,0x05,0xff,0xe7,0x8e,0x8b,0x00,0x10,0x08,0x05,0xff,0xe3,0xba, + 0xac,0x00,0x05,0xff,0xe7,0x8e,0xa5,0x00,0x51,0x08,0x05,0xff,0xe3,0xba,0xb8,0x00, + 0x10,0x08,0x05,0xff,0xe7,0x91,0x87,0x00,0x05,0xff,0xe7,0x91,0x9c,0x00,0xd3,0x42, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x91,0xb1,0x00,0x05,0xff,0xe7,0x92, + 0x85,0x00,0x10,0x08,0x05,0xff,0xe7,0x93,0x8a,0x00,0x05,0xff,0xe3,0xbc,0x9b,0x00, + 0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x94,0xa4,0x00,0x05,0xff,0xf0,0xa4,0xb0,0xb6, + 0x00,0x10,0x08,0x05,0xff,0xe7,0x94,0xbe,0x00,0x05,0xff,0xf0,0xa4,0xb2,0x92,0x00, + 0xd2,0x22,0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x95,0xb0,0x00,0x05,0xff,0xf0,0xa2, + 0x86,0x9f,0x00,0x10,0x08,0x05,0xff,0xe7,0x98,0x90,0x00,0x05,0xff,0xf0,0xa4,0xbe, + 0xa1,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa4,0xbe,0xb8,0x00,0x05,0xff,0xf0, + 0xa5,0x81,0x84,0x00,0x10,0x08,0x05,0xff,0xe3,0xbf,0xbc,0x00,0x05,0xff,0xe4,0x80, + 0x88,0x00,0xcf,0x86,0xe5,0x04,0x01,0xd4,0x7d,0xd3,0x3c,0xd2,0x23,0xd1,0x11,0x10, + 0x08,0x05,0xff,0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0x10,0x09, + 0x05,0xff,0xf0,0xa5,0x83,0xb2,0x00,0x05,0xff,0xf0,0xa5,0x84,0x99,0x00,0x91,0x11, + 0x10,0x09,0x05,0xff,0xf0,0xa5,0x84,0xb3,0x00,0x05,0xff,0xe7,0x9c,0x9e,0x00,0x05, + 0xff,0xe7,0x9c,0x9f,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x9d,0x8a, + 0x00,0x05,0xff,0xe4,0x80,0xb9,0x00,0x10,0x08,0x05,0xff,0xe7,0x9e,0x8b,0x00,0x05, + 0xff,0xe4,0x81,0x86,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe4,0x82,0x96,0x00,0x05, + 0xff,0xf0,0xa5,0x90,0x9d,0x00,0x10,0x08,0x05,0xff,0xe7,0xa1,0x8e,0x00,0x05,0xff, + 0xe7,0xa2,0x8c,0x00,0xd3,0x43,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0xa3, + 0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0x98,0xa6, + 0x00,0x05,0xff,0xe7,0xa5,0x96,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0x9a, + 0x9a,0x00,0x05,0xff,0xf0,0xa5,0x9b,0x85,0x00,0x10,0x08,0x05,0xff,0xe7,0xa6,0x8f, + 0x00,0x05,0xff,0xe7,0xa7,0xab,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe4, + 0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80,0x00,0x10,0x08,0x05,0xff,0xe7,0xa9,0x8a, + 0x00,0x05,0xff,0xe7,0xa9,0x8f,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5, + 0xbc,0x00,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa, + 0xa7,0x00,0x05,0xff,0xe7,0xab,0xae,0x00,0xd4,0x83,0xd3,0x42,0xd2,0x21,0xd1,0x11, + 0x10,0x08,0x05,0xff,0xe4,0x88,0x82,0x00,0x05,0xff,0xf0,0xa5,0xae,0xab,0x00,0x10, + 0x08,0x05,0xff,0xe7,0xaf,0x86,0x00,0x05,0xff,0xe7,0xaf,0x89,0x00,0xd1,0x11,0x10, + 0x08,0x05,0xff,0xe4,0x88,0xa7,0x00,0x05,0xff,0xf0,0xa5,0xb2,0x80,0x00,0x10,0x08, + 0x05,0xff,0xe7,0xb3,0x92,0x00,0x05,0xff,0xe4,0x8a,0xa0,0x00,0xd2,0x21,0xd1,0x10, + 0x10,0x08,0x05,0xff,0xe7,0xb3,0xa8,0x00,0x05,0xff,0xe7,0xb3,0xa3,0x00,0x10,0x08, + 0x05,0xff,0xe7,0xb4,0x80,0x00,0x05,0xff,0xf0,0xa5,0xbe,0x86,0x00,0xd1,0x10,0x10, + 0x08,0x05,0xff,0xe7,0xb5,0xa3,0x00,0x05,0xff,0xe4,0x8c,0x81,0x00,0x10,0x08,0x05, + 0xff,0xe7,0xb7,0x87,0x00,0x05,0xff,0xe7,0xb8,0x82,0x00,0xd3,0x44,0xd2,0x22,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe7,0xb9,0x85,0x00,0x05,0xff,0xe4,0x8c,0xb4,0x00,0x10, + 0x09,0x05,0xff,0xf0,0xa6,0x88,0xa8,0x00,0x05,0xff,0xf0,0xa6,0x89,0x87,0x00,0xd1, + 0x11,0x10,0x08,0x05,0xff,0xe4,0x8d,0x99,0x00,0x05,0xff,0xf0,0xa6,0x8b,0x99,0x00, + 0x10,0x08,0x05,0xff,0xe7,0xbd,0xba,0x00,0x05,0xff,0xf0,0xa6,0x8c,0xbe,0x00,0xd2, + 0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0xbe,0x95,0x00,0x05,0xff,0xe7,0xbf,0xba, + 0x00,0x10,0x08,0x05,0xff,0xe8,0x80,0x85,0x00,0x05,0xff,0xf0,0xa6,0x93,0x9a,0x00, + 0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa6,0x94,0xa3,0x00,0x05,0xff,0xe8,0x81,0xa0, + 0x00,0x10,0x09,0x05,0xff,0xf0,0xa6,0x96,0xa8,0x00,0x05,0xff,0xe8,0x81,0xb0,0x00, + 0xe0,0x11,0x02,0xcf,0x86,0xe5,0x07,0x01,0xd4,0x85,0xd3,0x42,0xd2,0x21,0xd1,0x11, + 0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0x10, + 0x08,0x05,0xff,0xe8,0x82,0xb2,0x00,0x05,0xff,0xe8,0x84,0x83,0x00,0xd1,0x10,0x10, + 0x08,0x05,0xff,0xe4,0x90,0x8b,0x00,0x05,0xff,0xe8,0x84,0xbe,0x00,0x10,0x08,0x05, + 0xff,0xe5,0xaa,0xb5,0x00,0x05,0xff,0xf0,0xa6,0x9e,0xa7,0x00,0xd2,0x23,0xd1,0x12, + 0x10,0x09,0x05,0xff,0xf0,0xa6,0x9e,0xb5,0x00,0x05,0xff,0xf0,0xa3,0x8e,0x93,0x00, + 0x10,0x09,0x05,0xff,0xf0,0xa3,0x8e,0x9c,0x00,0x05,0xff,0xe8,0x88,0x81,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe8,0x88,0x84,0x00,0x05,0xff,0xe8,0xbe,0x9e,0x00,0x10, + 0x08,0x05,0xff,0xe4,0x91,0xab,0x00,0x05,0xff,0xe8,0x8a,0x91,0x00,0xd3,0x41,0xd2, + 0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x8a,0x8b,0x00,0x05,0xff,0xe8,0x8a,0x9d, + 0x00,0x10,0x08,0x05,0xff,0xe5,0x8a,0xb3,0x00,0x05,0xff,0xe8,0x8a,0xb1,0x00,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe8,0x8a,0xb3,0x00,0x05,0xff,0xe8,0x8a,0xbd,0x00,0x10, + 0x08,0x05,0xff,0xe8,0x8b,0xa6,0x00,0x05,0xff,0xf0,0xa6,0xac,0xbc,0x00,0xd2,0x20, + 0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x8b,0xa5,0x00,0x05,0xff,0xe8,0x8c,0x9d,0x00, + 0x10,0x08,0x05,0xff,0xe8,0x8d,0xa3,0x00,0x05,0xff,0xe8,0x8e,0xad,0x00,0xd1,0x10, + 0x10,0x08,0x05,0xff,0xe8,0x8c,0xa3,0x00,0x05,0xff,0xe8,0x8e,0xbd,0x00,0x10,0x08, + 0x05,0xff,0xe8,0x8f,0xa7,0x00,0x05,0xff,0xe8,0x91,0x97,0x00,0xd4,0x85,0xd3,0x43, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f, + 0x8a,0x00,0x10,0x08,0x05,0xff,0xe8,0x8f,0x8c,0x00,0x05,0xff,0xe8,0x8f,0x9c,0x00, + 0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa6,0xb0,0xb6,0x00,0x05,0xff,0xf0,0xa6,0xb5, + 0xab,0x00,0x10,0x09,0x05,0xff,0xf0,0xa6,0xb3,0x95,0x00,0x05,0xff,0xe4,0x94,0xab, + 0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x93,0xb1,0x00,0x05,0xff,0xe8, + 0x93,0xb3,0x00,0x10,0x08,0x05,0xff,0xe8,0x94,0x96,0x00,0x05,0xff,0xf0,0xa7,0x8f, + 0x8a,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe8,0x95,0xa4,0x00,0x05,0xff,0xf0,0xa6, + 0xbc,0xac,0x00,0x10,0x08,0x05,0xff,0xe4,0x95,0x9d,0x00,0x05,0xff,0xe4,0x95,0xa1, + 0x00,0xd3,0x42,0xd2,0x22,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00, + 0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0x10,0x08,0x05,0xff,0xe4,0x95,0xab,0x00,0x05, + 0xff,0xe8,0x99,0x90,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x99,0x9c,0x00,0x05, + 0xff,0xe8,0x99,0xa7,0x00,0x10,0x08,0x05,0xff,0xe8,0x99,0xa9,0x00,0x05,0xff,0xe8, + 0x9a,0xa9,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9a,0x88,0x00,0x05, + 0xff,0xe8,0x9c,0x8e,0x00,0x10,0x08,0x05,0xff,0xe8,0x9b,0xa2,0x00,0x05,0xff,0xe8, + 0x9d,0xb9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8, + 0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00,0x05,0xff,0xe4,0x97,0x97, + 0x00,0xcf,0x86,0xe5,0x08,0x01,0xd4,0x83,0xd3,0x41,0xd2,0x20,0xd1,0x10,0x10,0x08, + 0x05,0xff,0xe8,0x9f,0xa1,0x00,0x05,0xff,0xe8,0xa0,0x81,0x00,0x10,0x08,0x05,0xff, + 0xe4,0x97,0xb9,0x00,0x05,0xff,0xe8,0xa1,0xa0,0x00,0xd1,0x11,0x10,0x08,0x05,0xff, + 0xe8,0xa1,0xa3,0x00,0x05,0xff,0xf0,0xa7,0x99,0xa7,0x00,0x10,0x08,0x05,0xff,0xe8, + 0xa3,0x97,0x00,0x05,0xff,0xe8,0xa3,0x9e,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05, + 0xff,0xe4,0x98,0xb5,0x00,0x05,0xff,0xe8,0xa3,0xba,0x00,0x10,0x08,0x05,0xff,0xe3, + 0x92,0xbb,0x00,0x05,0xff,0xf0,0xa7,0xa2,0xae,0x00,0xd1,0x11,0x10,0x09,0x05,0xff, + 0xf0,0xa7,0xa5,0xa6,0x00,0x05,0xff,0xe4,0x9a,0xbe,0x00,0x10,0x08,0x05,0xff,0xe4, + 0x9b,0x87,0x00,0x05,0xff,0xe8,0xaa,0xa0,0x00,0xd3,0x41,0xd2,0x21,0xd1,0x10,0x10, + 0x08,0x05,0xff,0xe8,0xab,0xad,0x00,0x05,0xff,0xe8,0xae,0x8a,0x00,0x10,0x08,0x05, + 0xff,0xe8,0xb1,0x95,0x00,0x05,0xff,0xf0,0xa7,0xb2,0xa8,0x00,0xd1,0x10,0x10,0x08, + 0x05,0xff,0xe8,0xb2,0xab,0x00,0x05,0xff,0xe8,0xb3,0x81,0x00,0x10,0x08,0x05,0xff, + 0xe8,0xb4,0x9b,0x00,0x05,0xff,0xe8,0xb5,0xb7,0x00,0xd2,0x22,0xd1,0x12,0x10,0x09, + 0x05,0xff,0xf0,0xa7,0xbc,0xaf,0x00,0x05,0xff,0xf0,0xa0,0xa0,0x84,0x00,0x10,0x08, + 0x05,0xff,0xe8,0xb7,0x8b,0x00,0x05,0xff,0xe8,0xb6,0xbc,0x00,0xd1,0x11,0x10,0x08, + 0x05,0xff,0xe8,0xb7,0xb0,0x00,0x05,0xff,0xf0,0xa0,0xa3,0x9e,0x00,0x10,0x08,0x05, + 0xff,0xe8,0xbb,0x94,0x00,0x05,0xff,0xe8,0xbc,0xb8,0x00,0xd4,0x84,0xd3,0x43,0xd2, + 0x22,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa8,0x97,0x92,0x00,0x05,0xff,0xf0,0xa8, + 0x97,0xad,0x00,0x10,0x08,0x05,0xff,0xe9,0x82,0x94,0x00,0x05,0xff,0xe9,0x83,0xb1, + 0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe9,0x84,0x91,0x00,0x05,0xff,0xf0,0xa8,0x9c, + 0xae,0x00,0x10,0x08,0x05,0xff,0xe9,0x84,0x9b,0x00,0x05,0xff,0xe9,0x88,0xb8,0x00, + 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe9,0x8b,0x97,0x00,0x05,0xff,0xe9,0x8b, + 0x98,0x00,0x10,0x08,0x05,0xff,0xe9,0x89,0xbc,0x00,0x05,0xff,0xe9,0x8f,0xb9,0x00, + 0xd1,0x11,0x10,0x08,0x05,0xff,0xe9,0x90,0x95,0x00,0x05,0xff,0xf0,0xa8,0xaf,0xba, + 0x00,0x10,0x08,0x05,0xff,0xe9,0x96,0x8b,0x00,0x05,0xff,0xe4,0xa6,0x95,0x00,0xd3, + 0x43,0xd2,0x21,0xd1,0x11,0x10,0x08,0x05,0xff,0xe9,0x96,0xb7,0x00,0x05,0xff,0xf0, + 0xa8,0xb5,0xb7,0x00,0x10,0x08,0x05,0xff,0xe4,0xa7,0xa6,0x00,0x05,0xff,0xe9,0x9b, + 0x83,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb6,0xb2,0x00,0x05,0xff,0xe9,0x9c, + 0xa3,0x00,0x10,0x09,0x05,0xff,0xf0,0xa9,0x85,0x85,0x00,0x05,0xff,0xf0,0xa9,0x88, + 0x9a,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe4,0xa9,0xae,0x00,0x05,0xff, + 0xe4,0xa9,0xb6,0x00,0x10,0x08,0x05,0xff,0xe9,0x9f,0xa0,0x00,0x05,0xff,0xf0,0xa9, + 0x90,0x8a,0x00,0x91,0x11,0x10,0x08,0x05,0xff,0xe4,0xaa,0xb2,0x00,0x05,0xff,0xf0, + 0xa9,0x92,0x96,0x00,0x05,0xff,0xe9,0xa0,0x8b,0x00,0xe2,0x10,0x01,0xe1,0x09,0x01, + 0xe0,0x02,0x01,0xcf,0x86,0x95,0xfb,0xd4,0x82,0xd3,0x41,0xd2,0x21,0xd1,0x11,0x10, + 0x08,0x05,0xff,0xe9,0xa0,0xa9,0x00,0x05,0xff,0xf0,0xa9,0x96,0xb6,0x00,0x10,0x08, + 0x05,0xff,0xe9,0xa3,0xa2,0x00,0x05,0xff,0xe4,0xac,0xb3,0x00,0xd1,0x10,0x10,0x08, + 0x05,0xff,0xe9,0xa4,0xa9,0x00,0x05,0xff,0xe9,0xa6,0xa7,0x00,0x10,0x08,0x05,0xff, + 0xe9,0xa7,0x82,0x00,0x05,0xff,0xe9,0xa7,0xbe,0x00,0xd2,0x21,0xd1,0x11,0x10,0x08, + 0x05,0xff,0xe4,0xaf,0x8e,0x00,0x05,0xff,0xf0,0xa9,0xac,0xb0,0x00,0x10,0x08,0x05, + 0xff,0xe9,0xac,0x92,0x00,0x05,0xff,0xe9,0xb1,0x80,0x00,0xd1,0x10,0x10,0x08,0x05, + 0xff,0xe9,0xb3,0xbd,0x00,0x05,0xff,0xe4,0xb3,0x8e,0x00,0x10,0x08,0x05,0xff,0xe4, + 0xb3,0xad,0x00,0x05,0xff,0xe9,0xb5,0xa7,0x00,0xd3,0x44,0xd2,0x23,0xd1,0x11,0x10, + 0x09,0x05,0xff,0xf0,0xaa,0x83,0x8e,0x00,0x05,0xff,0xe4,0xb3,0xb8,0x00,0x10,0x09, + 0x05,0xff,0xf0,0xaa,0x84,0x85,0x00,0x05,0xff,0xf0,0xaa,0x88,0x8e,0x00,0xd1,0x11, + 0x10,0x09,0x05,0xff,0xf0,0xaa,0x8a,0x91,0x00,0x05,0xff,0xe9,0xba,0xbb,0x00,0x10, + 0x08,0x05,0xff,0xe4,0xb5,0x96,0x00,0x05,0xff,0xe9,0xbb,0xb9,0x00,0xd2,0x20,0xd1, + 0x10,0x10,0x08,0x05,0xff,0xe9,0xbb,0xbe,0x00,0x05,0xff,0xe9,0xbc,0x85,0x00,0x10, + 0x08,0x05,0xff,0xe9,0xbc,0x8f,0x00,0x05,0xff,0xe9,0xbc,0x96,0x00,0x91,0x11,0x10, + 0x08,0x05,0xff,0xe9,0xbc,0xbb,0x00,0x05,0xff,0xf0,0xaa,0x98,0x80,0x00,0x00,0x00, + 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x06, + 0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00, + 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00, + 0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xd3,0x08, + 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08, + 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, + 0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06, + 0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06, + 0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04, + 0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xd5,0xc0, + 0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06, + 0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06, + 0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00, + 0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06, + 0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04, + 0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00, + 0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06, + 0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00, + 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00, + 0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xd4,0x60, + 0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, + 0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06, + 0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00, + 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00, + 0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xd3,0x08, + 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08, + 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, + 0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06, + 0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06, + 0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04, + 0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xe0,0x83,0x01,0xcf, + 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf, + 0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf, + 0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf, + 0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1, + 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00, + 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00, + 0x00,0x02,0x00,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf, + 0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00, + 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, + 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, + 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, + 0x00,0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf, + 0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00, + 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, + 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, + 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, + 0x00,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00, + 0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00, + 0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3, + 0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00, + 0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00, + 0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf, + 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf, + 0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf, + 0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf, + 0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1, + 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00, + 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00, + 0x00,0x02,0x00,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf, + 0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf, + 0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00, + 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, + 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, + 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, + 0x00,0xd4,0xd9,0xd3,0x81,0xd2,0x79,0xd1,0x71,0xd0,0x69,0xcf,0x86,0xd5,0x60,0xd4, + 0x59,0xd3,0x52,0xd2,0x33,0xd1,0x2c,0xd0,0x25,0xcf,0x86,0x95,0x1e,0x94,0x19,0x93, + 0x14,0x92,0x0f,0x91,0x0a,0x10,0x05,0x00,0xff,0x00,0x05,0xff,0x00,0x00,0xff,0x00, + 0x00,0xff,0x00,0x00,0xff,0x00,0x00,0xff,0x00,0x05,0xff,0x00,0xcf,0x06,0x05,0xff, + 0x00,0xcf,0x06,0x00,0xff,0x00,0xd1,0x07,0xcf,0x06,0x07,0xff,0x00,0xd0,0x07,0xcf, + 0x06,0x07,0xff,0x00,0xcf,0x86,0x55,0x05,0x07,0xff,0x00,0x14,0x05,0x07,0xff,0x00, + 0x00,0xff,0x00,0xcf,0x06,0x00,0xff,0x00,0xcf,0x06,0x00,0xff,0x00,0xcf,0x06,0x00, + 0xff,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, + 0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86, + 0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06, + 0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00, + 0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06, + 0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00, + 0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xcf,0x06,0x02,0x00, + 0x81,0x80,0xcf,0x86,0x85,0x84,0xcf,0x86,0xcf,0x06,0x02,0x00,0x00,0x00,0x00,0x00 +}; + +struct utf8data_table utf8_data_table = { + .utf8agetab = utf8agetab, + .utf8agetab_size = ARRAY_SIZE(utf8agetab), + + .utf8nfdicfdata = utf8nfdicfdata, + .utf8nfdicfdata_size = ARRAY_SIZE(utf8nfdicfdata), + + .utf8nfdidata = utf8nfdidata, + .utf8nfdidata_size = ARRAY_SIZE(utf8nfdidata), + + .utf8data = utf8data, +}; +EXPORT_SYMBOL_GPL(utf8_data_table); +MODULE_LICENSE("GPL v2"); diff --git a/fs/unicode/utf8data.h_shipped b/fs/unicode/utf8data.h_shipped deleted file mode 100644 index 76e4f0e1b089..000000000000 --- a/fs/unicode/utf8data.h_shipped +++ /dev/null @@ -1,4109 +0,0 @@ -/* This file is generated code, do not edit. */ -#ifndef __INCLUDED_FROM_UTF8NORM_C__ -#error Only nls_utf8-norm.c should include this file. -#endif - -static const unsigned int utf8vers = 0xc0100; - -static const unsigned int utf8agetab[] = { - 0, - 0x10100, - 0x20000, - 0x20100, - 0x30000, - 0x30100, - 0x30200, - 0x40000, - 0x40100, - 0x50000, - 0x50100, - 0x50200, - 0x60000, - 0x60100, - 0x60200, - 0x60300, - 0x70000, - 0x80000, - 0x90000, - 0xa0000, - 0xb0000, - 0xc0000, - 0xc0100 -}; - -static const struct utf8data utf8nfdicfdata[] = { - { 0, 0 }, - { 0x10100, 0 }, - { 0x20000, 0 }, - { 0x20100, 0 }, - { 0x30000, 0 }, - { 0x30100, 0 }, - { 0x30200, 1792 }, - { 0x40000, 3200 }, - { 0x40100, 3200 }, - { 0x50000, 3200 }, - { 0x50100, 3200 }, - { 0x50200, 3200 }, - { 0x60000, 3200 }, - { 0x60100, 3200 }, - { 0x60200, 3200 }, - { 0x60300, 3200 }, - { 0x70000, 3200 }, - { 0x80000, 3200 }, - { 0x90000, 3200 }, - { 0xa0000, 3200 }, - { 0xb0000, 3200 }, - { 0xc0000, 3200 }, - { 0xc0100, 3200 } -}; - -static const struct utf8data utf8nfdidata[] = { - { 0, 896 }, - { 0x10100, 896 }, - { 0x20000, 896 }, - { 0x20100, 896 }, - { 0x30000, 896 }, - { 0x30100, 896 }, - { 0x30200, 2496 }, - { 0x40000, 20736 }, - { 0x40100, 20736 }, - { 0x50000, 20736 }, - { 0x50100, 20736 }, - { 0x50200, 20736 }, - { 0x60000, 20736 }, - { 0x60100, 20736 }, - { 0x60200, 20736 }, - { 0x60300, 20736 }, - { 0x70000, 20736 }, - { 0x80000, 20736 }, - { 0x90000, 20736 }, - { 0xa0000, 20736 }, - { 0xb0000, 20736 }, - { 0xc0000, 20736 }, - { 0xc0100, 20736 } -}; - -static const unsigned char utf8data[64256] = { - /* nfdicf_30100 */ - 0xd7,0x07,0x66,0x84,0x0c,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x99,0x1a,0xe3,0x63,0x15, - 0xe2,0x4c,0x0e,0xc1,0xe0,0x4e,0x0d,0xcf,0x86,0x65,0x2d,0x0d,0x01,0x00,0xd4,0xb8, - 0xd3,0x27,0xe2,0x89,0xa3,0xe1,0xce,0x35,0xe0,0x2c,0x22,0xcf,0x86,0xc5,0xe4,0x15, - 0x6d,0xe3,0x60,0x68,0xe2,0xf6,0x65,0xe1,0x29,0x65,0xe0,0xee,0x64,0xcf,0x86,0xe5, - 0xb3,0x64,0x64,0x96,0x64,0x0b,0x00,0xd2,0x0e,0xe1,0xb5,0x3c,0xe0,0xba,0xa3,0xcf, - 0x86,0xcf,0x06,0x01,0x00,0xd1,0x0c,0xe0,0x1e,0xa9,0xcf,0x86,0xcf,0x06,0x02,0xff, - 0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01, - 0x00,0xe4,0xe1,0x45,0xe3,0x3b,0x45,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x87,0xad, - 0xd0,0x21,0xcf,0x86,0xe5,0x81,0xaa,0xe4,0x00,0xaa,0xe3,0xbf,0xa9,0xe2,0x9e,0xa9, - 0xe1,0x8d,0xa9,0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4, - 0x00,0xcf,0x86,0xe5,0x63,0xac,0xd4,0x19,0xe3,0xa2,0xab,0xe2,0x81,0xab,0xe1,0x70, - 0xab,0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3, - 0x09,0xac,0xe2,0xe8,0xab,0xe1,0xd7,0xab,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00, - 0x01,0xff,0xe9,0x9b,0xbb,0x00,0x83,0xe2,0x19,0xfa,0xe1,0xf2,0xf6,0xe0,0x6f,0xf5, - 0xcf,0x86,0xd5,0x31,0xc4,0xe3,0x54,0x4e,0xe2,0xf5,0x4c,0xe1,0xa4,0xcc,0xe0,0x9c, - 0x4b,0xcf,0x86,0xe5,0x8e,0x49,0xe4,0xaf,0x46,0xe3,0x11,0xbd,0xe2,0x68,0xbc,0xe1, - 0x43,0xbc,0xe0,0x1c,0xbc,0xcf,0x86,0xe5,0xe9,0xbb,0x94,0x07,0x63,0xd4,0xbb,0x07, - 0x00,0x07,0x00,0xe4,0xdb,0xf4,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b, - 0xe1,0xea,0xe1,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xd9,0xe2,0xcf,0x86, - 0xe5,0x9e,0xe2,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xd9,0xe2,0xcf,0x06, - 0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x74,0xf4,0xe3,0x5d,0xf3, - 0xd2,0xa0,0xe1,0x13,0xe7,0xd0,0x21,0xcf,0x86,0xe5,0x14,0xe4,0xe4,0x90,0xe3,0xe3, - 0x4e,0xe3,0xe2,0x2d,0xe3,0xe1,0x1b,0xe3,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00, - 0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x70,0xe5,0xe3,0x2f,0xe5, - 0xe2,0x0e,0xe5,0xe1,0xfd,0xe4,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff, - 0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xf7,0xe5,0xe1,0xe6,0xe5,0x10,0x09, - 0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x17, - 0xe6,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac, - 0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x5d,0xe6,0xd2,0x14,0xe1,0x2c,0xe6, - 0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1, - 0x38,0xe6,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00, - 0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x8d,0xeb,0xd4,0x19,0xe3,0xc6,0xea,0xe2,0xa4, - 0xea,0xe1,0x93,0xea,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5, - 0xb7,0x00,0xd3,0x18,0xe2,0x10,0xeb,0xe1,0xff,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3, - 0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0x28,0xeb,0x10, - 0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10, - 0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08, - 0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0x2a, - 0xed,0xd4,0x1a,0xe3,0x62,0xec,0xe2,0x48,0xec,0xe1,0x35,0xec,0x10,0x08,0x05,0xff, - 0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0xaa,0xec, - 0xe1,0x98,0xec,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3, - 0x00,0xd2,0x13,0xe1,0xc6,0xec,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff, - 0xe7,0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05, - 0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05, - 0xff,0xe7,0xaa,0xae,0x00,0xe0,0xdc,0xef,0xcf,0x86,0xd5,0x1d,0xe4,0x51,0xee,0xe3, - 0x0d,0xee,0xe2,0xeb,0xed,0xe1,0xda,0xed,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f, - 0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xf8,0xee,0xe2,0xd4,0xee,0xe1, - 0xc3,0xee,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00, - 0xd3,0x18,0xe2,0x43,0xef,0xe1,0x32,0xef,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1, - 0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x5b,0xef,0x10,0x08,0x05, - 0xff,0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05, - 0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8, - 0x9e,0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - /* nfdi_30100 */ - 0x57,0x04,0x01,0x00,0xc6,0xd5,0x16,0xe4,0xc2,0x59,0xe3,0xfb,0x54,0xe2,0x74,0x4f, - 0xc1,0xe0,0xa0,0x4d,0xcf,0x86,0x65,0x84,0x4d,0x01,0x00,0xd4,0xb8,0xd3,0x27,0xe2, - 0x0c,0xa0,0xe1,0xdf,0x8d,0xe0,0x39,0x71,0xcf,0x86,0xc5,0xe4,0x98,0x69,0xe3,0xe3, - 0x64,0xe2,0x79,0x62,0xe1,0xac,0x61,0xe0,0x71,0x61,0xcf,0x86,0xe5,0x36,0x61,0x64, - 0x19,0x61,0x0b,0x00,0xd2,0x0e,0xe1,0xc2,0xa0,0xe0,0x3d,0xa0,0xcf,0x86,0xcf,0x06, - 0x01,0x00,0xd1,0x0c,0xe0,0xa1,0xa5,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd0,0x08, - 0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xe4,0x9e, - 0xb6,0xe3,0x18,0xae,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x0a,0xaa,0xd0,0x21,0xcf, - 0x86,0xe5,0x04,0xa7,0xe4,0x83,0xa6,0xe3,0x42,0xa6,0xe2,0x21,0xa6,0xe1,0x10,0xa6, - 0x10,0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0xcf,0x86, - 0xe5,0xe6,0xa8,0xd4,0x19,0xe3,0x25,0xa8,0xe2,0x04,0xa8,0xe1,0xf3,0xa7,0x10,0x08, - 0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0xe3,0x8c,0xa8,0xe2, - 0x6b,0xa8,0xe1,0x5a,0xa8,0x10,0x08,0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9, - 0x9b,0xbb,0x00,0x83,0xe2,0x9c,0xf6,0xe1,0x75,0xf3,0xe0,0xf2,0xf1,0xcf,0x86,0xd5, - 0x31,0xc4,0xe3,0x6d,0xcc,0xe2,0x46,0xca,0xe1,0x27,0xc9,0xe0,0xb7,0xbf,0xcf,0x86, - 0xe5,0xaa,0xbb,0xe4,0xa3,0xba,0xe3,0x94,0xb9,0xe2,0xeb,0xb8,0xe1,0xc6,0xb8,0xe0, - 0x9f,0xb8,0xcf,0x86,0xe5,0x6c,0xb8,0x94,0x07,0x63,0x57,0xb8,0x07,0x00,0x07,0x00, - 0xe4,0x5e,0xf1,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1,0x6d,0xde, - 0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x5c,0xdf,0xcf,0x86,0xe5,0x21,0xdf, - 0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x5c,0xdf,0xcf,0x06,0x13,0x00,0xcf, - 0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0xf7,0xf0,0xe3,0xe0,0xef,0xd2,0xa0,0xe1, - 0x96,0xe3,0xd0,0x21,0xcf,0x86,0xe5,0x97,0xe0,0xe4,0x13,0xe0,0xe3,0xd1,0xdf,0xe2, - 0xb0,0xdf,0xe1,0x9e,0xdf,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4, - 0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xf3,0xe1,0xe3,0xb2,0xe1,0xe2,0x91,0xe1, - 0xe1,0x80,0xe1,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6, - 0x00,0xd4,0x34,0xd3,0x18,0xe2,0x7a,0xe2,0xe1,0x69,0xe2,0x10,0x09,0x05,0xff,0xf0, - 0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0x9a,0xe2,0x91,0x11, - 0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05, - 0xff,0xe5,0xac,0xbe,0x00,0xe3,0xe0,0xe2,0xd2,0x14,0xe1,0xaf,0xe2,0x10,0x08,0x05, - 0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0xbb,0xe2,0x10, - 0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1,0xd5,0xd0, - 0x6a,0xcf,0x86,0xe5,0x10,0xe8,0xd4,0x19,0xe3,0x49,0xe7,0xe2,0x27,0xe7,0xe1,0x16, - 0xe7,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7,0x00,0xd3, - 0x18,0xe2,0x93,0xe7,0xe1,0x82,0xe7,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00, - 0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xab,0xe7,0x10,0x08,0x05,0xff, - 0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08,0x05,0xff, - 0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7, - 0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0xad,0xe9,0xd4,0x1a, - 0xe3,0xe5,0xe8,0xe2,0xcb,0xe8,0xe1,0xb8,0xe8,0x10,0x08,0x05,0xff,0xe7,0x9b,0xb4, - 0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x2d,0xe9,0xe1,0x1b,0xe9, - 0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0xd2,0x13, - 0xe1,0x49,0xe9,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80, - 0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff,0xf0,0xa5, - 0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff,0xe7,0xaa, - 0xae,0x00,0xe0,0x5f,0xec,0xcf,0x86,0xd5,0x1d,0xe4,0xd4,0xea,0xe3,0x90,0xea,0xe2, - 0x6e,0xea,0xe1,0x5d,0xea,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff, - 0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x7b,0xeb,0xe2,0x57,0xeb,0xe1,0x46,0xeb,0x10, - 0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3,0x18,0xe2, - 0xc6,0xeb,0xe1,0xb5,0xeb,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00,0x05,0xff, - 0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xde,0xeb,0x10,0x08,0x05,0xff,0xe8,0x9a, - 0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c, - 0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00, - 0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - /* nfdicf_30200 */ - 0xd7,0x07,0x66,0x84,0x05,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x99,0x13,0xe3,0x63,0x0e, - 0xe2,0x4c,0x07,0xc1,0xe0,0x4e,0x06,0xcf,0x86,0x65,0x2d,0x06,0x01,0x00,0xd4,0x2a, - 0xe3,0xd0,0x35,0xe2,0x88,0x9c,0xe1,0xcd,0x2e,0xe0,0x2b,0x1b,0xcf,0x86,0xc5,0xe4, - 0x14,0x66,0xe3,0x5f,0x61,0xe2,0xf5,0x5e,0xe1,0x28,0x5e,0xe0,0xed,0x5d,0xcf,0x86, - 0xe5,0xb2,0x5d,0x64,0x95,0x5d,0x0b,0x00,0x83,0xe2,0xa7,0xf3,0xe1,0x80,0xf0,0xe0, - 0xfd,0xee,0xcf,0x86,0xd5,0x31,0xc4,0xe3,0xe2,0x47,0xe2,0x83,0x46,0xe1,0x32,0xc6, - 0xe0,0x2a,0x45,0xcf,0x86,0xe5,0x1c,0x43,0xe4,0x3d,0x40,0xe3,0x9f,0xb6,0xe2,0xf6, - 0xb5,0xe1,0xd1,0xb5,0xe0,0xaa,0xb5,0xcf,0x86,0xe5,0x77,0xb5,0x94,0x07,0x63,0x62, - 0xb5,0x07,0x00,0x07,0x00,0xe4,0x69,0xee,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00, - 0xd2,0x0b,0xe1,0x78,0xdb,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0x67,0xdc, - 0xcf,0x86,0xe5,0x2c,0xdc,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0x67,0xdc, - 0xcf,0x06,0x13,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x02,0xee,0xe3, - 0xeb,0xec,0xd2,0xa0,0xe1,0xa1,0xe0,0xd0,0x21,0xcf,0x86,0xe5,0xa2,0xdd,0xe4,0x1e, - 0xdd,0xe3,0xdc,0xdc,0xe2,0xbb,0xdc,0xe1,0xa9,0xdc,0x10,0x08,0x05,0xff,0xe4,0xb8, - 0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0xfe,0xde,0xe3, - 0xbd,0xde,0xe2,0x9c,0xde,0xe1,0x8b,0xde,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00, - 0x05,0xff,0xe5,0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0x85,0xdf,0xe1,0x74,0xdf, - 0x10,0x09,0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00, - 0xe2,0xa5,0xdf,0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff, - 0xe5,0xac,0x88,0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0xeb,0xdf,0xd2,0x14,0xe1, - 0xba,0xdf,0x10,0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98, - 0x00,0xe1,0xc6,0xdf,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0, - 0xa2,0x00,0xd1,0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x1b,0xe5,0xd4,0x19,0xe3,0x54,0xe4, - 0xe2,0x32,0xe4,0xe1,0x21,0xe4,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff, - 0xe6,0xb5,0xb7,0x00,0xd3,0x18,0xe2,0x9e,0xe4,0xe1,0x8d,0xe4,0x10,0x09,0x05,0xff, - 0xf0,0xa3,0xbd,0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xb6, - 0xe4,0x10,0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1, - 0x11,0x10,0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00, - 0x10,0x08,0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86, - 0xe5,0xb8,0xe6,0xd4,0x1a,0xe3,0xf0,0xe5,0xe2,0xd6,0xe5,0xe1,0xc3,0xe5,0x10,0x08, - 0x05,0xff,0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2, - 0x38,0xe6,0xe1,0x26,0xe6,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4, - 0x83,0xa3,0x00,0xd2,0x13,0xe1,0x54,0xe6,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00, - 0x05,0xff,0xe7,0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc, - 0x00,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7, - 0x00,0x05,0xff,0xe7,0xaa,0xae,0x00,0xe0,0x6a,0xe9,0xcf,0x86,0xd5,0x1d,0xe4,0xdf, - 0xe7,0xe3,0x9b,0xe7,0xe2,0x79,0xe7,0xe1,0x68,0xe7,0x10,0x09,0x05,0xff,0xf0,0xa3, - 0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0x86,0xe8,0xe2,0x62, - 0xe8,0xe1,0x51,0xe8,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f, - 0x8a,0x00,0xd3,0x18,0xe2,0xd1,0xe8,0xe1,0xc0,0xe8,0x10,0x09,0x05,0xff,0xf0,0xa6, - 0xbe,0xb1,0x00,0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0xe9,0xe8,0x10, - 0x08,0x05,0xff,0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10, - 0x08,0x05,0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05, - 0xff,0xe8,0x9e,0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00, - /* nfdi_30200 */ - 0x57,0x04,0x01,0x00,0xc6,0xd5,0x16,0xe4,0x82,0x53,0xe3,0xbb,0x4e,0xe2,0x34,0x49, - 0xc1,0xe0,0x60,0x47,0xcf,0x86,0x65,0x44,0x47,0x01,0x00,0xd4,0x2a,0xe3,0x1c,0x9a, - 0xe2,0xcb,0x99,0xe1,0x9e,0x87,0xe0,0xf8,0x6a,0xcf,0x86,0xc5,0xe4,0x57,0x63,0xe3, - 0xa2,0x5e,0xe2,0x38,0x5c,0xe1,0x6b,0x5b,0xe0,0x30,0x5b,0xcf,0x86,0xe5,0xf5,0x5a, - 0x64,0xd8,0x5a,0x0b,0x00,0x83,0xe2,0xea,0xf0,0xe1,0xc3,0xed,0xe0,0x40,0xec,0xcf, - 0x86,0xd5,0x31,0xc4,0xe3,0xbb,0xc6,0xe2,0x94,0xc4,0xe1,0x75,0xc3,0xe0,0x05,0xba, - 0xcf,0x86,0xe5,0xf8,0xb5,0xe4,0xf1,0xb4,0xe3,0xe2,0xb3,0xe2,0x39,0xb3,0xe1,0x14, - 0xb3,0xe0,0xed,0xb2,0xcf,0x86,0xe5,0xba,0xb2,0x94,0x07,0x63,0xa5,0xb2,0x07,0x00, - 0x07,0x00,0xe4,0xac,0xeb,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd2,0x0b,0xe1, - 0xbb,0xd8,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd1,0x0e,0xe0,0xaa,0xd9,0xcf,0x86,0xe5, - 0x6f,0xd9,0xcf,0x06,0x11,0x00,0xd0,0x0b,0xcf,0x86,0xe5,0xaa,0xd9,0xcf,0x06,0x13, - 0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x45,0xeb,0xe3,0x2e,0xea,0xd2, - 0xa0,0xe1,0xe4,0xdd,0xd0,0x21,0xcf,0x86,0xe5,0xe5,0xda,0xe4,0x61,0xda,0xe3,0x1f, - 0xda,0xe2,0xfe,0xd9,0xe1,0xec,0xd9,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05, - 0xff,0xe4,0xb8,0xb8,0x00,0xcf,0x86,0xd5,0x1c,0xe4,0x41,0xdc,0xe3,0x00,0xdc,0xe2, - 0xdf,0xdb,0xe1,0xce,0xdb,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5, - 0x93,0xb6,0x00,0xd4,0x34,0xd3,0x18,0xe2,0xc8,0xdc,0xe1,0xb7,0xdc,0x10,0x09,0x05, - 0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa,0x00,0xe2,0xe8,0xdc, - 0x91,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0x8d,0xaa,0x00,0x05,0xff,0xe5,0xac,0x88, - 0x00,0x05,0xff,0xe5,0xac,0xbe,0x00,0xe3,0x2e,0xdd,0xd2,0x14,0xe1,0xfd,0xdc,0x10, - 0x08,0x05,0xff,0xe5,0xaf,0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0xe1,0x09, - 0xdd,0x10,0x08,0x05,0xff,0xe5,0xbc,0xb3,0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0xd1, - 0xd5,0xd0,0x6a,0xcf,0x86,0xe5,0x5e,0xe2,0xd4,0x19,0xe3,0x97,0xe1,0xe2,0x75,0xe1, - 0xe1,0x64,0xe1,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff,0xe6,0xb5,0xb7, - 0x00,0xd3,0x18,0xe2,0xe1,0xe1,0xe1,0xd0,0xe1,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd, - 0x9e,0x00,0x05,0xff,0xf0,0xa3,0xbe,0x8e,0x00,0xd2,0x13,0xe1,0xf9,0xe1,0x10,0x08, - 0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff,0xe7,0x81,0xb7,0x00,0xd1,0x11,0x10,0x08, - 0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0,0xa4,0x89,0xa3,0x00,0x10,0x08,0x05, - 0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xe4,0x8e,0xab,0x00,0xcf,0x86,0xe5,0xfb,0xe3, - 0xd4,0x1a,0xe3,0x33,0xe3,0xe2,0x19,0xe3,0xe1,0x06,0xe3,0x10,0x08,0x05,0xff,0xe7, - 0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0xd3,0x16,0xe2,0x7b,0xe3,0xe1, - 0x69,0xe3,0x10,0x08,0x05,0xff,0xe7,0xa3,0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00, - 0xd2,0x13,0xe1,0x97,0xe3,0x10,0x08,0x05,0xff,0xe4,0x84,0xaf,0x00,0x05,0xff,0xe7, - 0xa9,0x80,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5,0xbc,0x00,0x05,0xff, - 0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x05,0xff, - 0xe7,0xaa,0xae,0x00,0xe0,0xad,0xe6,0xcf,0x86,0xd5,0x1d,0xe4,0x22,0xe5,0xe3,0xde, - 0xe4,0xe2,0xbc,0xe4,0xe1,0xab,0xe4,0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00, - 0x05,0xff,0xe4,0x8f,0x95,0x00,0xd4,0x19,0xe3,0xc9,0xe5,0xe2,0xa5,0xe5,0xe1,0x94, - 0xe5,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f,0x8a,0x00,0xd3, - 0x18,0xe2,0x14,0xe6,0xe1,0x03,0xe6,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00, - 0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0xd2,0x13,0xe1,0x2c,0xe6,0x10,0x08,0x05,0xff, - 0xe8,0x9a,0x88,0x00,0x05,0xff,0xe8,0x9c,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, - 0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8,0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e, - 0x86,0x00,0x05,0xff,0xe4,0xb5,0x97,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - /* nfdicf_c0100 */ - 0xd7,0xb0,0x56,0x04,0x01,0x00,0x95,0xa8,0xd4,0x5e,0xd3,0x2e,0xd2,0x16,0xd1,0x0a, - 0x10,0x04,0x01,0x00,0x01,0xff,0x61,0x00,0x10,0x06,0x01,0xff,0x62,0x00,0x01,0xff, - 0x63,0x00,0xd1,0x0c,0x10,0x06,0x01,0xff,0x64,0x00,0x01,0xff,0x65,0x00,0x10,0x06, - 0x01,0xff,0x66,0x00,0x01,0xff,0x67,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x06,0x01,0xff, - 0x68,0x00,0x01,0xff,0x69,0x00,0x10,0x06,0x01,0xff,0x6a,0x00,0x01,0xff,0x6b,0x00, - 0xd1,0x0c,0x10,0x06,0x01,0xff,0x6c,0x00,0x01,0xff,0x6d,0x00,0x10,0x06,0x01,0xff, - 0x6e,0x00,0x01,0xff,0x6f,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x06,0x01,0xff, - 0x70,0x00,0x01,0xff,0x71,0x00,0x10,0x06,0x01,0xff,0x72,0x00,0x01,0xff,0x73,0x00, - 0xd1,0x0c,0x10,0x06,0x01,0xff,0x74,0x00,0x01,0xff,0x75,0x00,0x10,0x06,0x01,0xff, - 0x76,0x00,0x01,0xff,0x77,0x00,0x92,0x16,0xd1,0x0c,0x10,0x06,0x01,0xff,0x78,0x00, - 0x01,0xff,0x79,0x00,0x10,0x06,0x01,0xff,0x7a,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0xc6,0xe5,0xf9,0x14,0xe4,0x6f,0x0d,0xe3,0x39,0x08,0xe2,0x22,0x01,0xc1,0xd0,0x24, - 0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x07,0x63,0xd8,0x43,0x01,0x00,0x93,0x13,0x52, - 0x04,0x01,0x00,0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xce,0xbc,0x00,0x01,0x00, - 0x01,0x00,0xcf,0x86,0xe5,0xb3,0x44,0xd4,0x7f,0xd3,0x3f,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01, - 0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x07,0x01,0xff,0xc3, - 0xa6,0x00,0x01,0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x65,0xcc,0x80,0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, - 0x82,0x00,0x01,0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc, - 0x80,0x00,0x01,0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00, - 0x01,0xff,0x69,0xcc,0x88,0x00,0xd3,0x3b,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff, - 0xc3,0xb0,0x00,0x01,0xff,0x6e,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80, - 0x00,0x01,0xff,0x6f,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82, - 0x00,0x01,0xff,0x6f,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01, - 0x00,0xd2,0x1f,0xd1,0x0f,0x10,0x07,0x01,0xff,0xc3,0xb8,0x00,0x01,0xff,0x75,0xcc, - 0x80,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x82,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x88,0x00,0x01,0xff,0x79,0xcc,0x81,0x00, - 0x10,0x07,0x01,0xff,0xc3,0xbe,0x00,0x01,0xff,0x73,0x73,0x00,0xe1,0xd4,0x03,0xe0, - 0xeb,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x61,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84,0x00,0x10,0x08,0x01,0xff, - 0x61,0xcc,0x86,0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x61,0xcc,0xa8,0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x63,0xcc, - 0x81,0x00,0x01,0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x63,0xcc,0x82,0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x63,0xcc, - 0x87,0x00,0x01,0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x63,0xcc, - 0x8c,0x00,0x01,0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x8c,0x00, - 0x01,0xff,0x64,0xcc,0x8c,0x00,0xd3,0x3b,0xd2,0x1b,0xd1,0x0b,0x10,0x07,0x01,0xff, - 0xc4,0x91,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x84,0x00,0x01,0xff,0x65, - 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x86,0x00,0x01,0xff,0x65, - 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0xa8,0x00,0x01,0xff,0x65, - 0xcc,0xa8,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82, - 0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4, - 0x7b,0xd3,0x3b,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x87,0x00,0x01, - 0xff,0x67,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x67,0xcc,0xa7,0x00,0x01,0xff,0x67, - 0xcc,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x68,0xcc,0x82,0x00,0x01,0xff,0x68, - 0xcc,0x82,0x00,0x10,0x07,0x01,0xff,0xc4,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x69,0xcc,0x83,0x00,0x01,0xff,0x69,0xcc,0x83,0x00,0x10,0x08, - 0x01,0xff,0x69,0xcc,0x84,0x00,0x01,0xff,0x69,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x69,0xcc,0x86,0x00,0x01,0xff,0x69,0xcc,0x86,0x00,0x10,0x08,0x01,0xff, - 0x69,0xcc,0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8,0x00,0xd3,0x37,0xd2,0x17,0xd1,0x0c, - 0x10,0x08,0x01,0xff,0x69,0xcc,0x87,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc4,0xb3, - 0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6a,0xcc,0x82,0x00,0x01,0xff,0x6a, - 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x6b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7, - 0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6c,0xcc,0x81,0x00,0x10, - 0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff,0x6c,0xcc,0xa7,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff,0x6c,0xcc,0x8c,0x00,0x10,0x08,0x01, - 0xff,0x6c,0xcc,0x8c,0x00,0x01,0xff,0xc5,0x80,0x00,0xcf,0x86,0xd5,0xed,0xd4,0x72, - 0xd3,0x37,0xd2,0x17,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc5,0x82,0x00,0x10, - 0x04,0x01,0x00,0x01,0xff,0x6e,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, - 0xcc,0x81,0x00,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa7, - 0x00,0x01,0xff,0x6e,0xcc,0x8c,0x00,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, - 0xcc,0x8c,0x00,0x01,0xff,0xca,0xbc,0x6e,0x00,0x10,0x07,0x01,0xff,0xc5,0x8b,0x00, - 0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc, - 0x84,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00, - 0xd3,0x3b,0xd2,0x1b,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01,0xff, - 0x6f,0xcc,0x8b,0x00,0x10,0x07,0x01,0xff,0xc5,0x93,0x00,0x01,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x72,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81,0x00,0x10,0x08,0x01, - 0xff,0x72,0xcc,0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x72,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c,0x00,0x10,0x08,0x01, - 0xff,0x73,0xcc,0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x73,0xcc,0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x73, - 0xcc,0xa7,0x00,0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x7b,0xd3,0x3b,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x73,0xcc,0x8c,0x00,0x01,0xff,0x73,0xcc,0x8c,0x00,0x10, - 0x08,0x01,0xff,0x74,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x74,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c,0x00,0x10,0x07,0x01, - 0xff,0xc5,0xa7,0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc, - 0x83,0x00,0x01,0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x84,0x00, - 0x01,0xff,0x75,0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x86,0x00, - 0x01,0xff,0x75,0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x8a,0x00,0x01,0xff, - 0x75,0xcc,0x8a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc, - 0x8b,0x00,0x01,0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa8,0x00, - 0x01,0xff,0x75,0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x82,0x00, - 0x01,0xff,0x77,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x82,0x00,0x01,0xff, - 0x79,0xcc,0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x79,0xcc,0x88,0x00, - 0x01,0xff,0x7a,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff, - 0x7a,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff, - 0x7a,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0xff,0x73,0x00, - 0xe0,0x65,0x01,0xcf,0x86,0xd5,0xb4,0xd4,0x5a,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10, - 0x04,0x01,0x00,0x01,0xff,0xc9,0x93,0x00,0x10,0x07,0x01,0xff,0xc6,0x83,0x00,0x01, - 0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff, - 0xc9,0x94,0x00,0x01,0xff,0xc6,0x88,0x00,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x01,0x00, - 0x01,0xff,0xc9,0x96,0x00,0x10,0x07,0x01,0xff,0xc9,0x97,0x00,0x01,0xff,0xc6,0x8c, - 0x00,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xc7,0x9d,0x00,0x01,0xff,0xc9,0x99, - 0x00,0xd3,0x32,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0x9b,0x00,0x01,0xff, - 0xc6,0x92,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xa0,0x00,0xd1,0x0b,0x10,0x07, - 0x01,0xff,0xc9,0xa3,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xc9,0xa9,0x00,0x01,0xff, - 0xc9,0xa8,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0x99,0x00,0x01,0x00, - 0x01,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xc9,0xaf,0x00,0x01,0xff,0xc9,0xb2,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0xc9,0xb5,0x00,0xd4,0x5d,0xd3,0x34,0xd2,0x1b,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x10, - 0x07,0x01,0xff,0xc6,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc6,0xa5, - 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x80,0x00,0x01,0xff,0xc6,0xa8,0x00,0xd2, - 0x0f,0x91,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x83,0x00,0x01,0x00,0xd1,0x0b, - 0x10,0x07,0x01,0xff,0xc6,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xca,0x88,0x00, - 0x01,0xff,0x75,0xcc,0x9b,0x00,0xd3,0x33,0xd2,0x1d,0xd1,0x0f,0x10,0x08,0x01,0xff, - 0x75,0xcc,0x9b,0x00,0x01,0xff,0xca,0x8a,0x00,0x10,0x07,0x01,0xff,0xca,0x8b,0x00, - 0x01,0xff,0xc6,0xb4,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x01,0xff,0xc6,0xb6,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0xca,0x92,0x00,0xd2,0x0f,0x91,0x0b,0x10,0x07,0x01, - 0xff,0xc6,0xb9,0x00,0x01,0x00,0x01,0x00,0x91,0x0b,0x10,0x07,0x01,0xff,0xc6,0xbd, - 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x44,0xd3,0x16,0x52,0x04,0x01, - 0x00,0x51,0x07,0x01,0xff,0xc7,0x86,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xc7,0x89, - 0x00,0xd2,0x12,0x91,0x0b,0x10,0x07,0x01,0xff,0xc7,0x89,0x00,0x01,0x00,0x01,0xff, - 0xc7,0x8c,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x61,0xcc,0x8c,0x00,0x10, - 0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff,0x69,0xcc,0x8c,0x00,0xd3,0x46,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x6f,0xcc,0x8c, - 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x8c,0x00,0xd1, - 0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84, - 0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x75,0xcc,0x88, - 0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81, - 0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88, - 0xcc,0x8c,0x00,0x01,0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01, - 0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x88, - 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x87,0xd3,0x41,0xd2, - 0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61, - 0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x84,0x00,0x01,0xff, - 0xc3,0xa6,0xcc,0x84,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xc7,0xa5,0x00,0x01,0x00, - 0x10,0x08,0x01,0xff,0x67,0xcc,0x8c,0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00, - 0x10,0x08,0x01,0xff,0x6f,0xcc,0xa8,0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14, - 0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc, - 0x84,0x00,0x10,0x09,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc, - 0x8c,0x00,0xd3,0x38,0xd2,0x1a,0xd1,0x0f,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00, - 0x01,0xff,0xc7,0xb3,0x00,0x10,0x07,0x01,0xff,0xc7,0xb3,0x00,0x01,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x67,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x10,0x07, - 0x04,0xff,0xc6,0x95,0x00,0x04,0xff,0xc6,0xbf,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08, - 0x04,0xff,0x6e,0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff, - 0x61,0xcc,0x8a,0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a,0xcc,0x81,0x00,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00,0x01,0xff,0xc3,0xa6,0xcc,0x81,0x00, - 0x10,0x09,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00,0x01,0xff,0xc3,0xb8,0xcc,0x81,0x00, - 0xe2,0x31,0x02,0xe1,0xc3,0x44,0xe0,0xc8,0x01,0xcf,0x86,0xd5,0xfb,0xd4,0x80,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0x8f,0x00,0x01,0xff,0x61, - 0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x91,0x00,0x01,0xff,0x61,0xcc,0x91, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x8f,0x00,0x01,0xff,0x65,0xcc,0x8f, - 0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x91,0x00,0x01,0xff,0x65,0xcc,0x91,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8f,0x00,0x01,0xff,0x69,0xcc,0x8f, - 0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x91,0x00,0x01,0xff,0x69,0xcc,0x91,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x01,0xff,0x6f,0xcc,0x8f,0x00,0x10, - 0x08,0x01,0xff,0x6f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc,0x91,0x00,0xd3,0x40,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x8f,0x00,0x01,0xff,0x72,0xcc,0x8f, - 0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0x91,0x00,0x01,0xff,0x72,0xcc,0x91,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x8f,0x00,0x01,0xff,0x75,0xcc,0x8f,0x00,0x10, - 0x08,0x01,0xff,0x75,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc,0x91,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x04,0xff,0x73,0xcc,0xa6,0x00,0x04,0xff,0x73,0xcc,0xa6,0x00,0x10, - 0x08,0x04,0xff,0x74,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc,0xa6,0x00,0xd1,0x0b,0x10, - 0x07,0x04,0xff,0xc8,0x9d,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x68,0xcc,0x8c,0x00, - 0x04,0xff,0x68,0xcc,0x8c,0x00,0xd4,0x79,0xd3,0x31,0xd2,0x16,0xd1,0x0b,0x10,0x07, - 0x06,0xff,0xc6,0x9e,0x00,0x07,0x00,0x10,0x07,0x04,0xff,0xc8,0xa3,0x00,0x04,0x00, - 0xd1,0x0b,0x10,0x07,0x04,0xff,0xc8,0xa5,0x00,0x04,0x00,0x10,0x08,0x04,0xff,0x61, - 0xcc,0x87,0x00,0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04, - 0xff,0x65,0xcc,0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x6f, - 0xcc,0x88,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10, - 0x0a,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84, - 0x00,0x10,0x08,0x04,0xff,0x6f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0xd3, - 0x27,0xe2,0x21,0x43,0xd1,0x14,0x10,0x0a,0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00, - 0x04,0xff,0x6f,0xcc,0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x79,0xcc,0x84,0x00, - 0x04,0xff,0x79,0xcc,0x84,0x00,0xd2,0x13,0x51,0x04,0x08,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0xa5,0x00,0x08,0xff,0xc8,0xbc,0x00,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08, - 0xff,0xc6,0x9a,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0xa6,0x00,0x08,0x00,0xcf,0x86, - 0x95,0x5f,0x94,0x5b,0xd3,0x2f,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x08,0x00,0x08,0xff, - 0xc9,0x82,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xc6,0x80,0x00,0xd1,0x0e,0x10,0x07, - 0x09,0xff,0xca,0x89,0x00,0x09,0xff,0xca,0x8c,0x00,0x10,0x07,0x09,0xff,0xc9,0x87, - 0x00,0x09,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9,0x89,0x00,0x09,0x00, - 0x10,0x07,0x09,0xff,0xc9,0x8b,0x00,0x09,0x00,0xd1,0x0b,0x10,0x07,0x09,0xff,0xc9, - 0x8d,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xc9,0x8f,0x00,0x09,0x00,0x01,0x00,0x01, - 0x00,0xd1,0x8b,0xd0,0x0c,0xcf,0x86,0xe5,0x10,0x43,0x64,0xef,0x42,0x01,0xe6,0xcf, - 0x86,0xd5,0x2a,0xe4,0x99,0x43,0xe3,0x7f,0x43,0xd2,0x11,0xe1,0x5e,0x43,0x10,0x07, - 0x01,0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0xe1,0x65,0x43,0x10,0x09,0x01, - 0xff,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0x00,0xd4,0x0f,0x93,0x0b,0x92, - 0x07,0x61,0xab,0x43,0x01,0xea,0x06,0xe6,0x06,0xe6,0xd3,0x2c,0xd2,0x16,0xd1,0x0b, - 0x10,0x07,0x0a,0xff,0xcd,0xb1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xcd,0xb3,0x00, - 0x0a,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x10,0x07,0x0a, - 0xff,0xcd,0xb7,0x00,0x0a,0x00,0xd2,0x07,0x61,0x97,0x43,0x00,0x00,0x51,0x04,0x09, - 0x00,0x10,0x06,0x01,0xff,0x3b,0x00,0x10,0xff,0xcf,0xb3,0x00,0xe0,0x31,0x01,0xcf, - 0x86,0xd5,0xd3,0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x01, - 0x00,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x81, - 0x00,0x01,0xff,0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5, - 0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9, - 0xcc,0x81,0x00,0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00, - 0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x01,0xff,0xcf,0x89,0xcc, - 0x81,0x00,0xd3,0x3c,0xd2,0x20,0xd1,0x12,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x88, - 0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0x00,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01, - 0xff,0xce,0xb3,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb4,0x00,0x01,0xff,0xce, - 0xb5,0x00,0x10,0x07,0x01,0xff,0xce,0xb6,0x00,0x01,0xff,0xce,0xb7,0x00,0xd2,0x1c, - 0xd1,0x0e,0x10,0x07,0x01,0xff,0xce,0xb8,0x00,0x01,0xff,0xce,0xb9,0x00,0x10,0x07, - 0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xce,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff, - 0xce,0xbc,0x00,0x01,0xff,0xce,0xbd,0x00,0x10,0x07,0x01,0xff,0xce,0xbe,0x00,0x01, - 0xff,0xce,0xbf,0x00,0xe4,0x85,0x43,0xd3,0x35,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01, - 0xff,0xcf,0x80,0x00,0x01,0xff,0xcf,0x81,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf, - 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xcf,0x84,0x00,0x01,0xff,0xcf,0x85,0x00, - 0x10,0x07,0x01,0xff,0xcf,0x86,0x00,0x01,0xff,0xcf,0x87,0x00,0xe2,0x2b,0x43,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xcf,0x88,0x00,0x01,0xff,0xcf,0x89,0x00,0x10,0x09,0x01, - 0xff,0xce,0xb9,0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc,0x88,0x00,0xcf,0x86,0xd5, - 0x94,0xd4,0x3c,0xd3,0x13,0x92,0x0f,0x51,0x04,0x01,0x00,0x10,0x07,0x01,0xff,0xcf, - 0x83,0x00,0x01,0x00,0x01,0x00,0xd2,0x07,0x61,0x3a,0x43,0x01,0x00,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x10, - 0x09,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x0a,0xff,0xcf,0x97,0x00,0xd3,0x2c,0xd2, - 0x11,0xe1,0x46,0x43,0x10,0x07,0x01,0xff,0xce,0xb2,0x00,0x01,0xff,0xce,0xb8,0x00, - 0xd1,0x10,0x10,0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0xff,0xcf,0x86,0x00, - 0x10,0x07,0x01,0xff,0xcf,0x80,0x00,0x04,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06, - 0xff,0xcf,0x99,0x00,0x06,0x00,0x10,0x07,0x01,0xff,0xcf,0x9b,0x00,0x04,0x00,0xd1, - 0x0b,0x10,0x07,0x01,0xff,0xcf,0x9d,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0x9f, - 0x00,0x04,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf, - 0xa1,0x00,0x04,0x00,0x10,0x07,0x01,0xff,0xcf,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10, - 0x07,0x01,0xff,0xcf,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xa7,0x00,0x01, - 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xa9,0x00,0x01,0x00,0x10,0x07, - 0x01,0xff,0xcf,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xcf,0xad,0x00, - 0x01,0x00,0x10,0x07,0x01,0xff,0xcf,0xaf,0x00,0x01,0x00,0xd3,0x2b,0xd2,0x12,0x91, - 0x0e,0x10,0x07,0x01,0xff,0xce,0xba,0x00,0x01,0xff,0xcf,0x81,0x00,0x01,0x00,0xd1, - 0x0e,0x10,0x07,0x05,0xff,0xce,0xb8,0x00,0x05,0xff,0xce,0xb5,0x00,0x10,0x04,0x06, - 0x00,0x07,0xff,0xcf,0xb8,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x04,0x07,0x00,0x07,0xff, - 0xcf,0xb2,0x00,0x10,0x07,0x07,0xff,0xcf,0xbb,0x00,0x07,0x00,0xd1,0x0b,0x10,0x04, - 0x08,0x00,0x08,0xff,0xcd,0xbb,0x00,0x10,0x07,0x08,0xff,0xcd,0xbc,0x00,0x08,0xff, - 0xcd,0xbd,0x00,0xe3,0xed,0x46,0xe2,0x3d,0x05,0xe1,0x27,0x02,0xe0,0x66,0x01,0xcf, - 0x86,0xd5,0xf0,0xd4,0x7e,0xd3,0x40,0xd2,0x22,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0, - 0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x07,0x01,0xff,0xd1, - 0x92,0x00,0x01,0xff,0xd0,0xb3,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1, - 0x94,0x00,0x01,0xff,0xd1,0x95,0x00,0x10,0x07,0x01,0xff,0xd1,0x96,0x00,0x01,0xff, - 0xd1,0x96,0xcc,0x88,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x98,0x00, - 0x01,0xff,0xd1,0x99,0x00,0x10,0x07,0x01,0xff,0xd1,0x9a,0x00,0x01,0xff,0xd1,0x9b, - 0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8, - 0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x86,0x00,0x01,0xff,0xd1,0x9f, - 0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xb0,0x00,0x01,0xff, - 0xd0,0xb1,0x00,0x10,0x07,0x01,0xff,0xd0,0xb2,0x00,0x01,0xff,0xd0,0xb3,0x00,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xd0,0xb4,0x00,0x01,0xff,0xd0,0xb5,0x00,0x10,0x07,0x01, - 0xff,0xd0,0xb6,0x00,0x01,0xff,0xd0,0xb7,0x00,0xd2,0x1e,0xd1,0x10,0x10,0x07,0x01, - 0xff,0xd0,0xb8,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x10,0x07,0x01,0xff,0xd0, - 0xba,0x00,0x01,0xff,0xd0,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd0,0xbc,0x00, - 0x01,0xff,0xd0,0xbd,0x00,0x10,0x07,0x01,0xff,0xd0,0xbe,0x00,0x01,0xff,0xd0,0xbf, - 0x00,0xe4,0x25,0x42,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x80, - 0x00,0x01,0xff,0xd1,0x81,0x00,0x10,0x07,0x01,0xff,0xd1,0x82,0x00,0x01,0xff,0xd1, - 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x84,0x00,0x01,0xff,0xd1,0x85,0x00, - 0x10,0x07,0x01,0xff,0xd1,0x86,0x00,0x01,0xff,0xd1,0x87,0x00,0xd2,0x1c,0xd1,0x0e, - 0x10,0x07,0x01,0xff,0xd1,0x88,0x00,0x01,0xff,0xd1,0x89,0x00,0x10,0x07,0x01,0xff, - 0xd1,0x8a,0x00,0x01,0xff,0xd1,0x8b,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd1,0x8c, - 0x00,0x01,0xff,0xd1,0x8d,0x00,0x10,0x07,0x01,0xff,0xd1,0x8e,0x00,0x01,0xff,0xd1, - 0x8f,0x00,0xcf,0x86,0xd5,0x07,0x64,0xcf,0x41,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2, - 0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff, - 0xd1,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xa5,0x00,0x01,0x00, - 0x10,0x07,0x01,0xff,0xd1,0xa7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01, - 0xff,0xd1,0xa9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xab,0x00,0x01,0x00,0xd1, - 0x0b,0x10,0x07,0x01,0xff,0xd1,0xad,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xaf, - 0x00,0x01,0x00,0xd3,0x33,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb1,0x00, - 0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xb3,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01, - 0xff,0xd1,0xb5,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb5,0xcc,0x8f,0x00,0x01, - 0xff,0xd1,0xb5,0xcc,0x8f,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd1,0xb9, - 0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07, - 0x01,0xff,0xd1,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd1,0xbf,0x00,0x01,0x00, - 0xe0,0x41,0x01,0xcf,0x86,0xd5,0x8e,0xd4,0x36,0xd3,0x11,0xe2,0x91,0x41,0xe1,0x88, - 0x41,0x10,0x07,0x01,0xff,0xd2,0x81,0x00,0x01,0x00,0xd2,0x0f,0x51,0x04,0x04,0x00, - 0x10,0x07,0x06,0xff,0xd2,0x8b,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x04,0xff,0xd2, - 0x8d,0x00,0x04,0x00,0x10,0x07,0x04,0xff,0xd2,0x8f,0x00,0x04,0x00,0xd3,0x2c,0xd2, - 0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x91,0x00,0x01,0x00,0x10,0x07,0x01,0xff, - 0xd2,0x93,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0x95,0x00,0x01,0x00, - 0x10,0x07,0x01,0xff,0xd2,0x97,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01, - 0xff,0xd2,0x99,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9b,0x00,0x01,0x00,0xd1, - 0x0b,0x10,0x07,0x01,0xff,0xd2,0x9d,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0x9f, - 0x00,0x01,0x00,0xd4,0x58,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2, - 0xa1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa3,0x00,0x01,0x00,0xd1,0x0b,0x10, - 0x07,0x01,0xff,0xd2,0xa5,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xa7,0x00,0x01, - 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xa9,0x00,0x01,0x00,0x10,0x07, - 0x01,0xff,0xd2,0xab,0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xad,0x00, - 0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xaf,0x00,0x01,0x00,0xd3,0x2c,0xd2,0x16,0xd1, - 0x0b,0x10,0x07,0x01,0xff,0xd2,0xb1,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xb3, - 0x00,0x01,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2,0xb5,0x00,0x01,0x00,0x10,0x07, - 0x01,0xff,0xd2,0xb7,0x00,0x01,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd2, - 0xb9,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbb,0x00,0x01,0x00,0xd1,0x0b,0x10, - 0x07,0x01,0xff,0xd2,0xbd,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xd2,0xbf,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0xdc,0xd4,0x5a,0xd3,0x36,0xd2,0x20,0xd1,0x10,0x10,0x07,0x01, - 0xff,0xd3,0x8f,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0, - 0xb6,0xcc,0x86,0x00,0x01,0xff,0xd3,0x84,0x00,0xd1,0x0b,0x10,0x04,0x01,0x00,0x06, - 0xff,0xd3,0x86,0x00,0x10,0x04,0x06,0x00,0x01,0xff,0xd3,0x88,0x00,0xd2,0x16,0xd1, - 0x0b,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8a,0x00,0x10,0x04,0x06,0x00,0x01,0xff, - 0xd3,0x8c,0x00,0xe1,0x69,0x40,0x10,0x04,0x01,0x00,0x06,0xff,0xd3,0x8e,0x00,0xd3, - 0x41,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x01,0xff, - 0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x01,0xff, - 0xd0,0xb0,0xcc,0x88,0x00,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x95,0x00,0x01,0x00, - 0x10,0x09,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00, - 0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0x99,0x00,0x01,0x00,0x10,0x09,0x01, - 0xff,0xd3,0x99,0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc,0x88,0x00,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb6,0xcc,0x88,0x00,0x10, - 0x09,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb7,0xcc,0x88,0x00,0xd4, - 0x82,0xd3,0x41,0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa1,0x00,0x01,0x00, - 0x10,0x09,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc, - 0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc, - 0x88,0x00,0xd2,0x1d,0xd1,0x0b,0x10,0x07,0x01,0xff,0xd3,0xa9,0x00,0x01,0x00,0x10, - 0x09,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0x01,0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1, - 0x12,0x10,0x09,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88, - 0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0x01,0xff,0xd1,0x83,0xcc,0x84, - 0x00,0xd3,0x41,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00, - 0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00, - 0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x87,0xcc, - 0x88,0x00,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00,0x10,0x07,0x08,0xff,0xd3,0xb7,0x00, - 0x08,0x00,0xd2,0x1d,0xd1,0x12,0x10,0x09,0x01,0xff,0xd1,0x8b,0xcc,0x88,0x00,0x01, - 0xff,0xd1,0x8b,0xcc,0x88,0x00,0x10,0x07,0x09,0xff,0xd3,0xbb,0x00,0x09,0x00,0xd1, - 0x0b,0x10,0x07,0x09,0xff,0xd3,0xbd,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd3,0xbf, - 0x00,0x09,0x00,0xe1,0x26,0x02,0xe0,0x78,0x01,0xcf,0x86,0xd5,0xb0,0xd4,0x58,0xd3, - 0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x81,0x00,0x06,0x00,0x10,0x07, - 0x06,0xff,0xd4,0x83,0x00,0x06,0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x85,0x00, - 0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x87,0x00,0x06,0x00,0xd2,0x16,0xd1,0x0b,0x10, - 0x07,0x06,0xff,0xd4,0x89,0x00,0x06,0x00,0x10,0x07,0x06,0xff,0xd4,0x8b,0x00,0x06, - 0x00,0xd1,0x0b,0x10,0x07,0x06,0xff,0xd4,0x8d,0x00,0x06,0x00,0x10,0x07,0x06,0xff, - 0xd4,0x8f,0x00,0x06,0x00,0xd3,0x2c,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x09,0xff,0xd4, - 0x91,0x00,0x09,0x00,0x10,0x07,0x09,0xff,0xd4,0x93,0x00,0x09,0x00,0xd1,0x0b,0x10, - 0x07,0x0a,0xff,0xd4,0x95,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x97,0x00,0x0a, - 0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x99,0x00,0x0a,0x00,0x10,0x07, - 0x0a,0xff,0xd4,0x9b,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0x9d,0x00, - 0x0a,0x00,0x10,0x07,0x0a,0xff,0xd4,0x9f,0x00,0x0a,0x00,0xd4,0x58,0xd3,0x2c,0xd2, - 0x16,0xd1,0x0b,0x10,0x07,0x0a,0xff,0xd4,0xa1,0x00,0x0a,0x00,0x10,0x07,0x0a,0xff, - 0xd4,0xa3,0x00,0x0a,0x00,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xd4,0xa5,0x00,0x0b,0x00, - 0x10,0x07,0x0c,0xff,0xd4,0xa7,0x00,0x0c,0x00,0xd2,0x16,0xd1,0x0b,0x10,0x07,0x10, - 0xff,0xd4,0xa9,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xab,0x00,0x10,0x00,0xd1, - 0x0b,0x10,0x07,0x10,0xff,0xd4,0xad,0x00,0x10,0x00,0x10,0x07,0x10,0xff,0xd4,0xaf, - 0x00,0x10,0x00,0xd3,0x35,0xd2,0x19,0xd1,0x0b,0x10,0x04,0x00,0x00,0x01,0xff,0xd5, - 0xa1,0x00,0x10,0x07,0x01,0xff,0xd5,0xa2,0x00,0x01,0xff,0xd5,0xa3,0x00,0xd1,0x0e, - 0x10,0x07,0x01,0xff,0xd5,0xa4,0x00,0x01,0xff,0xd5,0xa5,0x00,0x10,0x07,0x01,0xff, - 0xd5,0xa6,0x00,0x01,0xff,0xd5,0xa7,0x00,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff, - 0xd5,0xa8,0x00,0x01,0xff,0xd5,0xa9,0x00,0x10,0x07,0x01,0xff,0xd5,0xaa,0x00,0x01, - 0xff,0xd5,0xab,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xac,0x00,0x01,0xff,0xd5, - 0xad,0x00,0x10,0x07,0x01,0xff,0xd5,0xae,0x00,0x01,0xff,0xd5,0xaf,0x00,0xcf,0x86, - 0xe5,0x08,0x3f,0xd4,0x70,0xd3,0x38,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5, - 0xb0,0x00,0x01,0xff,0xd5,0xb1,0x00,0x10,0x07,0x01,0xff,0xd5,0xb2,0x00,0x01,0xff, - 0xd5,0xb3,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5,0xb4,0x00,0x01,0xff,0xd5,0xb5, - 0x00,0x10,0x07,0x01,0xff,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb7,0x00,0xd2,0x1c,0xd1, - 0x0e,0x10,0x07,0x01,0xff,0xd5,0xb8,0x00,0x01,0xff,0xd5,0xb9,0x00,0x10,0x07,0x01, - 0xff,0xd5,0xba,0x00,0x01,0xff,0xd5,0xbb,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd5, - 0xbc,0x00,0x01,0xff,0xd5,0xbd,0x00,0x10,0x07,0x01,0xff,0xd5,0xbe,0x00,0x01,0xff, - 0xd5,0xbf,0x00,0xe3,0x87,0x3e,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x80, - 0x00,0x01,0xff,0xd6,0x81,0x00,0x10,0x07,0x01,0xff,0xd6,0x82,0x00,0x01,0xff,0xd6, - 0x83,0x00,0xd1,0x0e,0x10,0x07,0x01,0xff,0xd6,0x84,0x00,0x01,0xff,0xd6,0x85,0x00, - 0x10,0x07,0x01,0xff,0xd6,0x86,0x00,0x00,0x00,0xe0,0x2f,0x3f,0xcf,0x86,0xe5,0xc0, - 0x3e,0xe4,0x97,0x3e,0xe3,0x76,0x3e,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x01,0xff,0xd5,0xa5,0xd6,0x82,0x00,0xe4,0x3e,0x25,0xe3,0xc3,0x1a, - 0xe2,0x7b,0x81,0xe1,0xc0,0x13,0xd0,0x1e,0xcf,0x86,0xc5,0xe4,0x08,0x4b,0xe3,0x53, - 0x46,0xe2,0xe9,0x43,0xe1,0x1c,0x43,0xe0,0xe1,0x42,0xcf,0x86,0xe5,0xa6,0x42,0x64, - 0x89,0x42,0x0b,0x00,0xcf,0x86,0xe5,0xfa,0x01,0xe4,0x03,0x56,0xe3,0x76,0x01,0xe2, - 0x8e,0x53,0xd1,0x0c,0xe0,0xef,0x52,0xcf,0x86,0x65,0x8d,0x52,0x04,0x00,0xe0,0x0d, - 0x01,0xcf,0x86,0xd5,0x0a,0xe4,0x10,0x53,0x63,0xff,0x52,0x0a,0x00,0xd4,0x80,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x80,0x00,0x01,0xff,0xe2, - 0xb4,0x81,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x82,0x00,0x01,0xff,0xe2,0xb4,0x83, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x84,0x00,0x01,0xff,0xe2,0xb4,0x85, - 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x86,0x00,0x01,0xff,0xe2,0xb4,0x87,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x88,0x00,0x01,0xff,0xe2,0xb4,0x89, - 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x8a,0x00,0x01,0xff,0xe2,0xb4,0x8b,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x8c,0x00,0x01,0xff,0xe2,0xb4,0x8d,0x00,0x10, - 0x08,0x01,0xff,0xe2,0xb4,0x8e,0x00,0x01,0xff,0xe2,0xb4,0x8f,0x00,0xd3,0x40,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x90,0x00,0x01,0xff,0xe2,0xb4,0x91, - 0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0x92,0x00,0x01,0xff,0xe2,0xb4,0x93,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x94,0x00,0x01,0xff,0xe2,0xb4,0x95,0x00,0x10, - 0x08,0x01,0xff,0xe2,0xb4,0x96,0x00,0x01,0xff,0xe2,0xb4,0x97,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0x98,0x00,0x01,0xff,0xe2,0xb4,0x99,0x00,0x10, - 0x08,0x01,0xff,0xe2,0xb4,0x9a,0x00,0x01,0xff,0xe2,0xb4,0x9b,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe2,0xb4,0x9c,0x00,0x01,0xff,0xe2,0xb4,0x9d,0x00,0x10,0x08,0x01, - 0xff,0xe2,0xb4,0x9e,0x00,0x01,0xff,0xe2,0xb4,0x9f,0x00,0xcf,0x86,0xe5,0x42,0x52, - 0x94,0x50,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa0,0x00, - 0x01,0xff,0xe2,0xb4,0xa1,0x00,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa2,0x00,0x01,0xff, - 0xe2,0xb4,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0xb4,0xa4,0x00,0x01,0xff, - 0xe2,0xb4,0xa5,0x00,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xa7,0x00,0x52,0x04, - 0x00,0x00,0x91,0x0c,0x10,0x04,0x00,0x00,0x0d,0xff,0xe2,0xb4,0xad,0x00,0x00,0x00, - 0x01,0x00,0xd2,0x1b,0xe1,0xfc,0x52,0xe0,0xad,0x52,0xcf,0x86,0x95,0x0f,0x94,0x0b, - 0x93,0x07,0x62,0x92,0x52,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xd1,0x13,0xe0, - 0xd3,0x53,0xcf,0x86,0x95,0x0a,0xe4,0xa8,0x53,0x63,0x97,0x53,0x04,0x00,0x04,0x00, - 0xd0,0x0d,0xcf,0x86,0x95,0x07,0x64,0x22,0x54,0x08,0x00,0x04,0x00,0xcf,0x86,0x55, - 0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x07,0x62,0x2f,0x54,0x04,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0xb0,0x00,0x11,0xff,0xe1,0x8f,0xb1,0x00, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0xb2,0x00,0x11,0xff,0xe1,0x8f,0xb3,0x00,0x91,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0xb4,0x00,0x11,0xff,0xe1,0x8f,0xb5,0x00,0x00,0x00, - 0xd4,0x1c,0xe3,0xe0,0x56,0xe2,0x17,0x56,0xe1,0xda,0x55,0xe0,0xbb,0x55,0xcf,0x86, - 0x95,0x0a,0xe4,0xa4,0x55,0x63,0x88,0x55,0x04,0x00,0x04,0x00,0xe3,0xd2,0x01,0xe2, - 0x2b,0x5a,0xd1,0x0c,0xe0,0x4c,0x59,0xcf,0x86,0x65,0x25,0x59,0x0a,0x00,0xe0,0x9c, - 0x59,0xcf,0x86,0xd5,0xc5,0xd4,0x45,0xd3,0x31,0xd2,0x1c,0xd1,0x0e,0x10,0x07,0x12, - 0xff,0xd0,0xb2,0x00,0x12,0xff,0xd0,0xb4,0x00,0x10,0x07,0x12,0xff,0xd0,0xbe,0x00, - 0x12,0xff,0xd1,0x81,0x00,0x51,0x07,0x12,0xff,0xd1,0x82,0x00,0x10,0x07,0x12,0xff, - 0xd1,0x8a,0x00,0x12,0xff,0xd1,0xa3,0x00,0x92,0x10,0x91,0x0c,0x10,0x08,0x12,0xff, - 0xea,0x99,0x8b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x14,0xff,0xe1,0x83,0x90,0x00,0x14,0xff,0xe1,0x83,0x91,0x00,0x10,0x08, - 0x14,0xff,0xe1,0x83,0x92,0x00,0x14,0xff,0xe1,0x83,0x93,0x00,0xd1,0x10,0x10,0x08, - 0x14,0xff,0xe1,0x83,0x94,0x00,0x14,0xff,0xe1,0x83,0x95,0x00,0x10,0x08,0x14,0xff, - 0xe1,0x83,0x96,0x00,0x14,0xff,0xe1,0x83,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x14,0xff,0xe1,0x83,0x98,0x00,0x14,0xff,0xe1,0x83,0x99,0x00,0x10,0x08,0x14,0xff, - 0xe1,0x83,0x9a,0x00,0x14,0xff,0xe1,0x83,0x9b,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, - 0xe1,0x83,0x9c,0x00,0x14,0xff,0xe1,0x83,0x9d,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, - 0x9e,0x00,0x14,0xff,0xe1,0x83,0x9f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x14,0xff,0xe1,0x83,0xa0,0x00,0x14,0xff,0xe1,0x83,0xa1,0x00,0x10,0x08, - 0x14,0xff,0xe1,0x83,0xa2,0x00,0x14,0xff,0xe1,0x83,0xa3,0x00,0xd1,0x10,0x10,0x08, - 0x14,0xff,0xe1,0x83,0xa4,0x00,0x14,0xff,0xe1,0x83,0xa5,0x00,0x10,0x08,0x14,0xff, - 0xe1,0x83,0xa6,0x00,0x14,0xff,0xe1,0x83,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x14,0xff,0xe1,0x83,0xa8,0x00,0x14,0xff,0xe1,0x83,0xa9,0x00,0x10,0x08,0x14,0xff, - 0xe1,0x83,0xaa,0x00,0x14,0xff,0xe1,0x83,0xab,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, - 0xe1,0x83,0xac,0x00,0x14,0xff,0xe1,0x83,0xad,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, - 0xae,0x00,0x14,0xff,0xe1,0x83,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x14,0xff,0xe1,0x83,0xb0,0x00,0x14,0xff,0xe1,0x83,0xb1,0x00,0x10,0x08,0x14,0xff, - 0xe1,0x83,0xb2,0x00,0x14,0xff,0xe1,0x83,0xb3,0x00,0xd1,0x10,0x10,0x08,0x14,0xff, - 0xe1,0x83,0xb4,0x00,0x14,0xff,0xe1,0x83,0xb5,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, - 0xb6,0x00,0x14,0xff,0xe1,0x83,0xb7,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x14,0xff, - 0xe1,0x83,0xb8,0x00,0x14,0xff,0xe1,0x83,0xb9,0x00,0x10,0x08,0x14,0xff,0xe1,0x83, - 0xba,0x00,0x00,0x00,0xd1,0x0c,0x10,0x04,0x00,0x00,0x14,0xff,0xe1,0x83,0xbd,0x00, - 0x10,0x08,0x14,0xff,0xe1,0x83,0xbe,0x00,0x14,0xff,0xe1,0x83,0xbf,0x00,0xe2,0x9d, - 0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84,0xd3,0x40, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa5,0x00,0x01,0xff,0x61,0xcc, - 0xa5,0x00,0x10,0x08,0x01,0xff,0x62,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc,0x87,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x62,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc,0xa3,0x00, - 0x10,0x08,0x01,0xff,0x62,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00,0xd2,0x24, - 0xd1,0x14,0x10,0x0a,0x01,0xff,0x63,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc, - 0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0x87,0x00,0x01,0xff,0x64,0xcc, - 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa3,0x00,0x01,0xff,0x64,0xcc, - 0xa3,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc,0xb1,0x00, - 0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x64,0xcc,0xa7,0x00,0x01,0xff, - 0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x64,0xcc,0xad,0x00,0x01,0xff,0x64,0xcc, - 0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff, - 0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00, - 0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x65,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, - 0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc, - 0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08,0x01,0xff, - 0x66,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x67,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc,0x84,0x00, - 0x10,0x08,0x01,0xff,0x68,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x68,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00,0x10,0x08, - 0x01,0xff,0x68,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x68,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00,0x10,0x08, - 0x01,0xff,0x68,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x69,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a,0x01,0xff, - 0x69,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00,0xd3,0x40, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0x81,0x00,0x01,0xff,0x6b,0xcc, - 0x81,0x00,0x10,0x08,0x01,0xff,0x6b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc,0xa3,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x6b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc,0xb1,0x00, - 0x10,0x08,0x01,0xff,0x6c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00,0xd2,0x24, - 0xd1,0x14,0x10,0x0a,0x01,0xff,0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff,0x6c,0xcc, - 0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x6c,0xcc,0xb1,0x00,0x01,0xff,0x6c,0xcc, - 0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6c,0xcc,0xad,0x00,0x01,0xff,0x6c,0xcc, - 0xad,0x00,0x10,0x08,0x01,0xff,0x6d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc,0x81,0x00, - 0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x6d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6d, - 0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, - 0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xa3, - 0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x6e, - 0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x6e,0xcc,0xad, - 0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x83, - 0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f, - 0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3,0x48,0xd2, - 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x01,0xff,0x6f, - 0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0x01, - 0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x70,0xcc,0x81, - 0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x70,0xcc,0x87,0x00,0x01, - 0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x72,0xcc,0x87, - 0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xa3,0x00,0x01, - 0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84, - 0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x72,0xcc,0xb1, - 0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x73,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10,0x08,0x01, - 0xff,0x73,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01, - 0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87,0x00,0x10, - 0x0a,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c,0xcc,0x87, - 0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x01, - 0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0x87,0x00,0x01, - 0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xa3,0x00,0x01, - 0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x74,0xcc,0xb1,0x00,0x01,0xff,0x74, - 0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x74,0xcc,0xad, - 0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xa4,0x00,0x01, - 0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0xb0,0x00,0x01, - 0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0xad,0x00,0x01,0xff,0x75, - 0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81, - 0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x84, - 0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x76,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x76, - 0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x11,0x02,0xcf,0x86,0xd5,0xe2, - 0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x80,0x00, - 0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x81,0x00,0x01,0xff, - 0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x88,0x00,0x01,0xff, - 0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x77,0xcc,0x87,0x00,0x01,0xff,0x77,0xcc, - 0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0xa3,0x00,0x01,0xff, - 0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x78,0xcc,0x87,0x00,0x01,0xff,0x78,0xcc, - 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x78,0xcc,0x88,0x00,0x01,0xff,0x78,0xcc, - 0x88,0x00,0x10,0x08,0x01,0xff,0x79,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc,0x87,0x00, - 0xd3,0x33,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x82,0x00,0x01,0xff, - 0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0xa3,0x00,0x01,0xff,0x7a,0xcc, - 0xa3,0x00,0xe1,0x12,0x59,0x10,0x08,0x01,0xff,0x7a,0xcc,0xb1,0x00,0x01,0xff,0x7a, - 0xcc,0xb1,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01, - 0xff,0x79,0xcc,0x8a,0x00,0x10,0x08,0x01,0xff,0x61,0xca,0xbe,0x00,0x02,0xff,0x73, - 0xcc,0x87,0x00,0x51,0x04,0x0a,0x00,0x10,0x07,0x0a,0xff,0x73,0x73,0x00,0x0a,0x00, - 0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x61,0xcc,0xa3,0x00, - 0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x61,0xcc,0x89,0x00,0x01,0xff, - 0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00, - 0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc, - 0x80,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89,0x00, - 0x10,0x0a,0x01,0xff,0x61,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc, - 0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, - 0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00, - 0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80,0x00, - 0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc, - 0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x01,0xff, - 0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00, - 0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x65,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x65,0xcc, - 0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc, - 0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc, - 0x81,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01,0xd4, - 0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80, - 0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x65,0xcc,0x82, - 0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01, - 0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00,0x10, - 0x0a,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc,0x82, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x89,0x00,0x01,0xff,0x69, - 0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc,0xa3, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc,0xa3, - 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00,0xd3, - 0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x01, - 0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80, - 0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f, - 0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a,0x01, - 0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00,0xd2, - 0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x6f, - 0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0x01, - 0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b, - 0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x6f, - 0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98,0xd3, - 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x01, - 0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3, - 0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75, - 0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x89, - 0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75, - 0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a,0x01, - 0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00,0xd1, - 0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc,0x9b, - 0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff,0x75, - 0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75, - 0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08,0x01, - 0xff,0x79,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x79,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x79, - 0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0xd2,0x1c,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x79,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x10,0x08,0x0a,0xff,0xe1, - 0xbb,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbd,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xe1,0xbb,0xbf,0x00,0x0a,0x00,0xe1,0xbf,0x02,0xe0,0xa1, - 0x01,0xcf,0x86,0xd5,0xc6,0xd4,0x6c,0xd3,0x18,0xe2,0x0e,0x59,0xe1,0xf7,0x58,0x10, - 0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0x00,0xd2, - 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1, - 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, - 0xce,0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, - 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, - 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82, - 0x00,0xd3,0x18,0xe2,0x4a,0x59,0xe1,0x33,0x59,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc, - 0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01, - 0xff,0xce,0xb5,0xcc,0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01, - 0xff,0xce,0xb5,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80, - 0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff, - 0xce,0xb5,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd4,0x6c,0xd3,0x18,0xe2,0x74,0x59, - 0xe1,0x5d,0x59,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7, - 0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x93,0x00, - 0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc, - 0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01, - 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81, - 0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7, - 0xcc,0x94,0xcd,0x82,0x00,0xd3,0x18,0xe2,0xb0,0x59,0xe1,0x99,0x59,0x10,0x09,0x01, - 0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0x00,0xd2,0x28,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94, - 0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9, - 0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc, - 0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce, - 0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82,0x00,0xcf, - 0x86,0xd5,0xac,0xd4,0x5a,0xd3,0x18,0xe2,0xed,0x59,0xe1,0xd6,0x59,0x10,0x09,0x01, - 0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00,0xd2,0x28,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94, - 0x00,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf, - 0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc, - 0x81,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x18,0xe2, - 0x17,0x5a,0xe1,0x00,0x5a,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff, - 0xcf,0x85,0xcc,0x94,0x00,0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xcf, - 0x85,0xcc,0x94,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x80, - 0x00,0xd1,0x0f,0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00, - 0x10,0x04,0x00,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00,0xe4,0xd3,0x5a, - 0xd3,0x18,0xe2,0x52,0x5a,0xe1,0x3b,0x5a,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93, - 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff, - 0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0x00, - 0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xcf, - 0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82, - 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xe0,0xd9,0x02,0xcf,0x86,0xe5, - 0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1, - 0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d, - 0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93, - 0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00, - 0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce, - 0xb1,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff, - 0xce,0xb1,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xce,0xb9,0x00, - 0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce, - 0xb1,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb1, - 0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0xce, - 0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01, - 0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x64,0xd2,0x30,0xd1,0x16, - 0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc, - 0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0xce,0xb9, - 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d, - 0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc, - 0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x82, - 0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30, - 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xce, - 0xb7,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80, - 0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a, - 0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xce, - 0xb7,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93, - 0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00, - 0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93, - 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d,0x01,0xff, - 0xcf,0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc, - 0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81, - 0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00,0x10,0x0d, - 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc, - 0x94,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89, - 0xcc,0x93,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xce,0xb9,0x00,0x10,0x0d, - 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc, - 0x94,0xcc,0x80,0xce,0xb9,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93, - 0xcc,0x81,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0xce,0xb9,0x00, - 0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xce,0xb9,0x00,0x01,0xff,0xcf, - 0x89,0xcc,0x94,0xcd,0x82,0xce,0xb9,0x00,0xd3,0x49,0xd2,0x26,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce,0xb1,0xcc,0x84,0x00,0x10,0x0b, - 0x01,0xff,0xce,0xb1,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb1,0xce,0xb9,0x00, - 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10, - 0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcd,0x82,0xce,0xb9, - 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff, - 0xce,0xb1,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01,0xff, - 0xce,0xb1,0xcc,0x81,0x00,0xe1,0xf3,0x5a,0x10,0x09,0x01,0xff,0xce,0xb1,0xce,0xb9, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0xbd,0xd4,0x7e,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10, - 0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7, - 0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0xd1,0x0f,0x10,0x0b, - 0x01,0xff,0xce,0xb7,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce, - 0xb7,0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81, - 0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x81, - 0x00,0xe1,0x02,0x5b,0x10,0x09,0x01,0xff,0xce,0xb7,0xce,0xb9,0x00,0x01,0xff,0xe1, - 0xbe,0xbf,0xcc,0x80,0x00,0xd3,0x18,0xe2,0x28,0x5b,0xe1,0x11,0x5b,0x10,0x09,0x01, - 0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0xe2,0x4c,0x5b, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc, - 0x84,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc, - 0x81,0x00,0xd4,0x51,0xd3,0x18,0xe2,0x6f,0x5b,0xe1,0x58,0x5b,0x10,0x09,0x01,0xff, - 0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00,0xd2,0x24,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84,0x00, - 0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00, - 0xe1,0x8f,0x5b,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8, - 0xcc,0x80,0x00,0xd3,0x3b,0xd2,0x18,0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf, - 0x89,0xcc,0x80,0xce,0xb9,0x00,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0xd1,0x0f,0x10, - 0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81,0xce,0xb9,0x00,0x00,0x00,0x10,0x09,0x01,0xff, - 0xcf,0x89,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcd,0x82,0xce,0xb9,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc, - 0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc, - 0x81,0x00,0xe1,0x99,0x5b,0x10,0x09,0x01,0xff,0xcf,0x89,0xce,0xb9,0x00,0x01,0xff, - 0xc2,0xb4,0x00,0xe0,0x0c,0x68,0xcf,0x86,0xe5,0x23,0x02,0xe4,0x25,0x01,0xe3,0x85, - 0x5e,0xd2,0x2a,0xe1,0x5f,0x5c,0xe0,0xdd,0x5b,0xcf,0x86,0xe5,0xbb,0x5b,0x94,0x1b, - 0xe3,0xa4,0x5b,0x92,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01, - 0xff,0xe2,0x80,0x83,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd1,0xd6,0xd0,0x46,0xcf, - 0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04,0x01, - 0x00,0x10,0x07,0x01,0xff,0xcf,0x89,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01,0x00, - 0x10,0x06,0x01,0xff,0x6b,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x01,0x00,0xe3,0x25, - 0x5d,0x92,0x10,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0x8e,0x00,0x01, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0x0a,0xe4,0x42,0x5d,0x63,0x2d,0x5d,0x06,0x00,0x94, - 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb0,0x00,0x01, - 0xff,0xe2,0x85,0xb1,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb2,0x00,0x01,0xff,0xe2, - 0x85,0xb3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb4,0x00,0x01,0xff,0xe2, - 0x85,0xb5,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xb6,0x00,0x01,0xff,0xe2,0x85,0xb7, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xb8,0x00,0x01,0xff,0xe2, - 0x85,0xb9,0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xba,0x00,0x01,0xff,0xe2,0x85,0xbb, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x85,0xbc,0x00,0x01,0xff,0xe2,0x85,0xbd, - 0x00,0x10,0x08,0x01,0xff,0xe2,0x85,0xbe,0x00,0x01,0xff,0xe2,0x85,0xbf,0x00,0x01, - 0x00,0xe0,0x34,0x5d,0xcf,0x86,0xe5,0x13,0x5d,0xe4,0xf2,0x5c,0xe3,0xe1,0x5c,0xe2, - 0xd4,0x5c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0xff,0xe2,0x86,0x84,0x00, - 0xe3,0x23,0x61,0xe2,0xf0,0x60,0xd1,0x0c,0xe0,0x9d,0x60,0xcf,0x86,0x65,0x7e,0x60, - 0x01,0x00,0xd0,0x62,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x18, - 0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x90,0x00, - 0x01,0xff,0xe2,0x93,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93, - 0x92,0x00,0x01,0xff,0xe2,0x93,0x93,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x94,0x00, - 0x01,0xff,0xe2,0x93,0x95,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x96,0x00, - 0x01,0xff,0xe2,0x93,0x97,0x00,0x10,0x08,0x01,0xff,0xe2,0x93,0x98,0x00,0x01,0xff, - 0xe2,0x93,0x99,0x00,0xcf,0x86,0xe5,0x57,0x60,0x94,0x80,0xd3,0x40,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe2,0x93,0x9a,0x00,0x01,0xff,0xe2,0x93,0x9b,0x00,0x10, - 0x08,0x01,0xff,0xe2,0x93,0x9c,0x00,0x01,0xff,0xe2,0x93,0x9d,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe2,0x93,0x9e,0x00,0x01,0xff,0xe2,0x93,0x9f,0x00,0x10,0x08,0x01, - 0xff,0xe2,0x93,0xa0,0x00,0x01,0xff,0xe2,0x93,0xa1,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe2,0x93,0xa2,0x00,0x01,0xff,0xe2,0x93,0xa3,0x00,0x10,0x08,0x01, - 0xff,0xe2,0x93,0xa4,0x00,0x01,0xff,0xe2,0x93,0xa5,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe2,0x93,0xa6,0x00,0x01,0xff,0xe2,0x93,0xa7,0x00,0x10,0x08,0x01,0xff,0xe2, - 0x93,0xa8,0x00,0x01,0xff,0xe2,0x93,0xa9,0x00,0x01,0x00,0xd4,0x0c,0xe3,0x33,0x62, - 0xe2,0x2c,0x62,0xcf,0x06,0x04,0x00,0xe3,0x0c,0x65,0xe2,0xff,0x63,0xe1,0x2e,0x02, - 0xe0,0x84,0x01,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x08,0xff,0xe2,0xb0,0xb0,0x00,0x08,0xff,0xe2,0xb0,0xb1,0x00,0x10,0x08, - 0x08,0xff,0xe2,0xb0,0xb2,0x00,0x08,0xff,0xe2,0xb0,0xb3,0x00,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe2,0xb0,0xb4,0x00,0x08,0xff,0xe2,0xb0,0xb5,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb0,0xb6,0x00,0x08,0xff,0xe2,0xb0,0xb7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe2,0xb0,0xb8,0x00,0x08,0xff,0xe2,0xb0,0xb9,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb0,0xba,0x00,0x08,0xff,0xe2,0xb0,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb0,0xbc,0x00,0x08,0xff,0xe2,0xb0,0xbd,0x00,0x10,0x08,0x08,0xff,0xe2,0xb0, - 0xbe,0x00,0x08,0xff,0xe2,0xb0,0xbf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe2,0xb1,0x80,0x00,0x08,0xff,0xe2,0xb1,0x81,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x82,0x00,0x08,0xff,0xe2,0xb1,0x83,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x84,0x00,0x08,0xff,0xe2,0xb1,0x85,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x86,0x00,0x08,0xff,0xe2,0xb1,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x88,0x00,0x08,0xff,0xe2,0xb1,0x89,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x8a,0x00,0x08,0xff,0xe2,0xb1,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x8c,0x00,0x08,0xff,0xe2,0xb1,0x8d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x8e,0x00, - 0x08,0xff,0xe2,0xb1,0x8f,0x00,0x94,0x7c,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe2,0xb1,0x90,0x00,0x08,0xff,0xe2,0xb1,0x91,0x00,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x92,0x00,0x08,0xff,0xe2,0xb1,0x93,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x94,0x00,0x08,0xff,0xe2,0xb1,0x95,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x96,0x00,0x08,0xff,0xe2,0xb1,0x97,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe2,0xb1,0x98,0x00,0x08,0xff,0xe2,0xb1,0x99,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x9a,0x00,0x08,0xff,0xe2,0xb1,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe2,0xb1, - 0x9c,0x00,0x08,0xff,0xe2,0xb1,0x9d,0x00,0x10,0x08,0x08,0xff,0xe2,0xb1,0x9e,0x00, - 0x00,0x00,0x08,0x00,0xcf,0x86,0xd5,0x07,0x64,0xef,0x61,0x08,0x00,0xd4,0x63,0xd3, - 0x32,0xd2,0x1b,0xd1,0x0c,0x10,0x08,0x09,0xff,0xe2,0xb1,0xa1,0x00,0x09,0x00,0x10, - 0x07,0x09,0xff,0xc9,0xab,0x00,0x09,0xff,0xe1,0xb5,0xbd,0x00,0xd1,0x0b,0x10,0x07, - 0x09,0xff,0xc9,0xbd,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xa8, - 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xaa,0x00,0x10, - 0x04,0x09,0x00,0x09,0xff,0xe2,0xb1,0xac,0x00,0xd1,0x0b,0x10,0x04,0x09,0x00,0x0a, - 0xff,0xc9,0x91,0x00,0x10,0x07,0x0a,0xff,0xc9,0xb1,0x00,0x0a,0xff,0xc9,0x90,0x00, - 0xd3,0x27,0xd2,0x17,0xd1,0x0b,0x10,0x07,0x0b,0xff,0xc9,0x92,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xe2,0xb1,0xb3,0x00,0x0a,0x00,0x91,0x0c,0x10,0x04,0x09,0x00,0x09, - 0xff,0xe2,0xb1,0xb6,0x00,0x09,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10, - 0x07,0x0b,0xff,0xc8,0xbf,0x00,0x0b,0xff,0xc9,0x80,0x00,0xe0,0x83,0x01,0xcf,0x86, - 0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, - 0x81,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x83,0x00,0x08,0x00,0xd1,0x0c, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2, - 0x87,0x00,0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x89,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x8f,0x00, - 0x08,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x91,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x97,0x00, - 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0x99,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0x9f,0x00,0x08,0x00, - 0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa1,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0xa5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa7,0x00, - 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xa9,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0xab,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0xad,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xaf,0x00,0x08,0x00, - 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb1,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb2,0xb3,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb2,0xb5,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb7,0x00,0x08,0x00, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2,0xb9,0x00,0x08,0x00,0x10,0x08, - 0x08,0xff,0xe2,0xb2,0xbb,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb2, - 0xbd,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb2,0xbf,0x00,0x08,0x00,0xcf,0x86, - 0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3, - 0x81,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x83,0x00,0x08,0x00,0xd1,0x0c, - 0x10,0x08,0x08,0xff,0xe2,0xb3,0x85,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3, - 0x87,0x00,0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x89,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb3,0x8d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x8f,0x00, - 0x08,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x91,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x93,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08, - 0x08,0xff,0xe2,0xb3,0x95,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x97,0x00, - 0x08,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0x99,0x00,0x08,0x00, - 0x10,0x08,0x08,0xff,0xe2,0xb3,0x9b,0x00,0x08,0x00,0xd1,0x0c,0x10,0x08,0x08,0xff, - 0xe2,0xb3,0x9d,0x00,0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0x9f,0x00,0x08,0x00, - 0xd4,0x3b,0xd3,0x1c,0x92,0x18,0xd1,0x0c,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa1,0x00, - 0x08,0x00,0x10,0x08,0x08,0xff,0xe2,0xb3,0xa3,0x00,0x08,0x00,0x08,0x00,0xd2,0x10, - 0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x0b,0xff,0xe2,0xb3,0xac,0x00,0xe1,0x3b, - 0x5f,0x10,0x04,0x0b,0x00,0x0b,0xff,0xe2,0xb3,0xae,0x00,0xe3,0x40,0x5f,0x92,0x10, - 0x51,0x04,0x0b,0xe6,0x10,0x08,0x0d,0xff,0xe2,0xb3,0xb3,0x00,0x0d,0x00,0x00,0x00, - 0xe2,0x98,0x08,0xd1,0x0b,0xe0,0x11,0x67,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe0,0x65, - 0x6c,0xcf,0x86,0xe5,0xa7,0x05,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x0c,0xe2,0xf8, - 0x67,0xe1,0x8f,0x67,0xcf,0x06,0x04,0x00,0xe2,0xdb,0x01,0xe1,0x26,0x01,0xd0,0x09, - 0xcf,0x86,0x65,0xf4,0x67,0x0a,0x00,0xcf,0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2, - 0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a, - 0xff,0xea,0x99,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x85, - 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1, - 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, - 0x99,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x8d,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1, - 0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, - 0x99,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x95,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x97,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x99,0x99,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0x9b, - 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0x9d,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x99,0x9f,0x00,0x0a,0x00,0xe4,0x5d,0x67,0xd3,0x30,0xd2,0x18, - 0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x99,0xa1,0x00,0x0c,0x00,0x10,0x08,0x0a,0xff, - 0xea,0x99,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x99,0xa5,0x00, - 0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c, - 0x10,0x08,0x0a,0xff,0xea,0x99,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x99, - 0xab,0x00,0x0a,0x00,0xe1,0x0c,0x67,0x10,0x08,0x0a,0xff,0xea,0x99,0xad,0x00,0x0a, - 0x00,0xe0,0x35,0x67,0xcf,0x86,0x95,0xab,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c, - 0x10,0x08,0x0a,0xff,0xea,0x9a,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a, - 0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x85,0x00,0x0a,0x00, - 0x10,0x08,0x0a,0xff,0xea,0x9a,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08, - 0x0a,0xff,0xea,0x9a,0x89,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8b,0x00, - 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x8d,0x00,0x0a,0x00,0x10,0x08, - 0x0a,0xff,0xea,0x9a,0x8f,0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08, - 0x0a,0xff,0xea,0x9a,0x91,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9a,0x93,0x00, - 0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9a,0x95,0x00,0x0a,0x00,0x10,0x08, - 0x0a,0xff,0xea,0x9a,0x97,0x00,0x0a,0x00,0xe2,0x92,0x66,0xd1,0x0c,0x10,0x08,0x10, - 0xff,0xea,0x9a,0x99,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9a,0x9b,0x00,0x10, - 0x00,0x0b,0x00,0xe1,0x10,0x02,0xd0,0xb9,0xcf,0x86,0xd5,0x07,0x64,0x9e,0x66,0x08, - 0x00,0xd4,0x58,0xd3,0x28,0xd2,0x10,0x51,0x04,0x09,0x00,0x10,0x08,0x0a,0xff,0xea, - 0x9c,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa5,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xa7,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x9c,0xa9,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xab, - 0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xad,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x9c,0xaf,0x00,0x0a,0x00,0xd3,0x28,0xd2,0x10,0x51,0x04,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb3,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9c,0xb5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb7,0x00,0x0a, - 0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9c,0xb9,0x00,0x0a,0x00,0x10, - 0x08,0x0a,0xff,0xea,0x9c,0xbb,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, - 0x9c,0xbd,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9c,0xbf,0x00,0x0a,0x00,0xcf, - 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea, - 0x9d,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x83,0x00,0x0a,0x00,0xd1, - 0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x85,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea, - 0x9d,0x87,0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x89, - 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8b,0x00,0x0a,0x00,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x9d,0x8d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x8f, - 0x00,0x0a,0x00,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x91, - 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x93,0x00,0x0a,0x00,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x9d,0x95,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x97, - 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0x99,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9b,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9d,0x9d,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0x9f,0x00,0x0a, - 0x00,0xd4,0x60,0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa1, - 0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa3,0x00,0x0a,0x00,0xd1,0x0c,0x10, - 0x08,0x0a,0xff,0xea,0x9d,0xa5,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa7, - 0x00,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9d,0xa9,0x00,0x0a, - 0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xab,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a, - 0xff,0xea,0x9d,0xad,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xaf,0x00,0x0a, - 0x00,0x53,0x04,0x0a,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea, - 0x9d,0xba,0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9d,0xbc,0x00,0xd1,0x0c,0x10, - 0x04,0x0a,0x00,0x0a,0xff,0xe1,0xb5,0xb9,0x00,0x10,0x08,0x0a,0xff,0xea,0x9d,0xbf, - 0x00,0x0a,0x00,0xe0,0x71,0x01,0xcf,0x86,0xd5,0xa6,0xd4,0x4e,0xd3,0x30,0xd2,0x18, - 0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x81,0x00,0x0a,0x00,0x10,0x08,0x0a,0xff, - 0xea,0x9e,0x83,0x00,0x0a,0x00,0xd1,0x0c,0x10,0x08,0x0a,0xff,0xea,0x9e,0x85,0x00, - 0x0a,0x00,0x10,0x08,0x0a,0xff,0xea,0x9e,0x87,0x00,0x0a,0x00,0xd2,0x10,0x51,0x04, - 0x0a,0x00,0x10,0x04,0x0a,0x00,0x0a,0xff,0xea,0x9e,0x8c,0x00,0xe1,0x9a,0x64,0x10, - 0x04,0x0a,0x00,0x0c,0xff,0xc9,0xa5,0x00,0xd3,0x28,0xd2,0x18,0xd1,0x0c,0x10,0x08, - 0x0c,0xff,0xea,0x9e,0x91,0x00,0x0c,0x00,0x10,0x08,0x0d,0xff,0xea,0x9e,0x93,0x00, - 0x0d,0x00,0x51,0x04,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x97,0x00,0x10,0x00, - 0xd2,0x18,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e,0x99,0x00,0x10,0x00,0x10,0x08, - 0x10,0xff,0xea,0x9e,0x9b,0x00,0x10,0x00,0xd1,0x0c,0x10,0x08,0x10,0xff,0xea,0x9e, - 0x9d,0x00,0x10,0x00,0x10,0x08,0x10,0xff,0xea,0x9e,0x9f,0x00,0x10,0x00,0xd4,0x63, - 0xd3,0x30,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa1,0x00,0x0c,0x00, - 0x10,0x08,0x0c,0xff,0xea,0x9e,0xa3,0x00,0x0c,0x00,0xd1,0x0c,0x10,0x08,0x0c,0xff, - 0xea,0x9e,0xa5,0x00,0x0c,0x00,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa7,0x00,0x0c,0x00, - 0xd2,0x1a,0xd1,0x0c,0x10,0x08,0x0c,0xff,0xea,0x9e,0xa9,0x00,0x0c,0x00,0x10,0x07, - 0x0d,0xff,0xc9,0xa6,0x00,0x10,0xff,0xc9,0x9c,0x00,0xd1,0x0e,0x10,0x07,0x10,0xff, - 0xc9,0xa1,0x00,0x10,0xff,0xc9,0xac,0x00,0x10,0x07,0x12,0xff,0xc9,0xaa,0x00,0x14, - 0x00,0xd3,0x35,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x10,0xff,0xca,0x9e,0x00,0x10,0xff, - 0xca,0x87,0x00,0x10,0x07,0x11,0xff,0xca,0x9d,0x00,0x11,0xff,0xea,0xad,0x93,0x00, - 0xd1,0x0c,0x10,0x08,0x11,0xff,0xea,0x9e,0xb5,0x00,0x11,0x00,0x10,0x08,0x11,0xff, - 0xea,0x9e,0xb7,0x00,0x11,0x00,0xd2,0x18,0xd1,0x0c,0x10,0x08,0x14,0xff,0xea,0x9e, - 0xb9,0x00,0x14,0x00,0x10,0x08,0x15,0xff,0xea,0x9e,0xbb,0x00,0x15,0x00,0xd1,0x0c, - 0x10,0x08,0x15,0xff,0xea,0x9e,0xbd,0x00,0x15,0x00,0x10,0x08,0x15,0xff,0xea,0x9e, - 0xbf,0x00,0x15,0x00,0xcf,0x86,0xe5,0xd4,0x63,0x94,0x2f,0x93,0x2b,0xd2,0x10,0x51, - 0x04,0x00,0x00,0x10,0x08,0x15,0xff,0xea,0x9f,0x83,0x00,0x15,0x00,0xd1,0x0f,0x10, - 0x08,0x15,0xff,0xea,0x9e,0x94,0x00,0x15,0xff,0xca,0x82,0x00,0x10,0x08,0x15,0xff, - 0xe1,0xb6,0x8e,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe4,0xb4,0x66,0xd3,0x1d,0xe2, - 0x5b,0x64,0xe1,0x0a,0x64,0xe0,0xf7,0x63,0xcf,0x86,0xe5,0xd8,0x63,0x94,0x0b,0x93, - 0x07,0x62,0xc3,0x63,0x08,0x00,0x08,0x00,0x08,0x00,0xd2,0x0f,0xe1,0x5a,0x65,0xe0, - 0x27,0x65,0xcf,0x86,0x65,0x0c,0x65,0x0a,0x00,0xd1,0xab,0xd0,0x1a,0xcf,0x86,0xe5, - 0x17,0x66,0xe4,0xfa,0x65,0xe3,0xe1,0x65,0xe2,0xd4,0x65,0x91,0x08,0x10,0x04,0x00, - 0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x0b,0x93,0x07,0x62, - 0x27,0x66,0x11,0x00,0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff, - 0xe1,0x8e,0xa0,0x00,0x11,0xff,0xe1,0x8e,0xa1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e, - 0xa2,0x00,0x11,0xff,0xe1,0x8e,0xa3,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, - 0xa4,0x00,0x11,0xff,0xe1,0x8e,0xa5,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xa6,0x00, - 0x11,0xff,0xe1,0x8e,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e, - 0xa8,0x00,0x11,0xff,0xe1,0x8e,0xa9,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xaa,0x00, - 0x11,0xff,0xe1,0x8e,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xac,0x00, - 0x11,0xff,0xe1,0x8e,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xae,0x00,0x11,0xff, - 0xe1,0x8e,0xaf,0x00,0xe0,0xb2,0x65,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb0,0x00,0x11,0xff,0xe1,0x8e, - 0xb1,0x00,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb2,0x00,0x11,0xff,0xe1,0x8e,0xb3,0x00, - 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb4,0x00,0x11,0xff,0xe1,0x8e,0xb5,0x00, - 0x10,0x08,0x11,0xff,0xe1,0x8e,0xb6,0x00,0x11,0xff,0xe1,0x8e,0xb7,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8e,0xb8,0x00,0x11,0xff,0xe1,0x8e,0xb9,0x00, - 0x10,0x08,0x11,0xff,0xe1,0x8e,0xba,0x00,0x11,0xff,0xe1,0x8e,0xbb,0x00,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8e,0xbc,0x00,0x11,0xff,0xe1,0x8e,0xbd,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8e,0xbe,0x00,0x11,0xff,0xe1,0x8e,0xbf,0x00,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0x80,0x00,0x11,0xff,0xe1,0x8f,0x81,0x00, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x82,0x00,0x11,0xff,0xe1,0x8f,0x83,0x00,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x84,0x00,0x11,0xff,0xe1,0x8f,0x85,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x86,0x00,0x11,0xff,0xe1,0x8f,0x87,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x88,0x00,0x11,0xff,0xe1,0x8f,0x89,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x8a,0x00,0x11,0xff,0xe1,0x8f,0x8b,0x00,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x8c,0x00,0x11,0xff,0xe1,0x8f,0x8d,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x8e,0x00,0x11,0xff,0xe1,0x8f,0x8f,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x11,0xff,0xe1,0x8f,0x90,0x00,0x11,0xff,0xe1,0x8f,0x91,0x00, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x92,0x00,0x11,0xff,0xe1,0x8f,0x93,0x00,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x94,0x00,0x11,0xff,0xe1,0x8f,0x95,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x96,0x00,0x11,0xff,0xe1,0x8f,0x97,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0x98,0x00,0x11,0xff,0xe1,0x8f,0x99,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x9a,0x00,0x11,0xff,0xe1,0x8f,0x9b,0x00,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0x9c,0x00,0x11,0xff,0xe1,0x8f,0x9d,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0x9e,0x00,0x11,0xff,0xe1,0x8f,0x9f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x11,0xff,0xe1,0x8f,0xa0,0x00,0x11,0xff,0xe1,0x8f,0xa1,0x00,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0xa2,0x00,0x11,0xff,0xe1,0x8f,0xa3,0x00,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0xa4,0x00,0x11,0xff,0xe1,0x8f,0xa5,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0xa6,0x00,0x11,0xff,0xe1,0x8f,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x11,0xff,0xe1,0x8f,0xa8,0x00,0x11,0xff,0xe1,0x8f,0xa9,0x00,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0xaa,0x00,0x11,0xff,0xe1,0x8f,0xab,0x00,0xd1,0x10,0x10,0x08,0x11,0xff, - 0xe1,0x8f,0xac,0x00,0x11,0xff,0xe1,0x8f,0xad,0x00,0x10,0x08,0x11,0xff,0xe1,0x8f, - 0xae,0x00,0x11,0xff,0xe1,0x8f,0xaf,0x00,0xd1,0x0c,0xe0,0xeb,0x63,0xcf,0x86,0xcf, - 0x06,0x02,0xff,0xff,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06, - 0xcf,0x06,0x01,0x00,0xd4,0xae,0xd3,0x09,0xe2,0x54,0x64,0xcf,0x06,0x01,0x00,0xd2, - 0x27,0xe1,0x1f,0x70,0xe0,0x26,0x6e,0xcf,0x86,0xe5,0x3f,0x6d,0xe4,0xce,0x6c,0xe3, - 0x99,0x6c,0xe2,0x78,0x6c,0xe1,0x67,0x6c,0x10,0x08,0x01,0xff,0xe5,0x88,0x87,0x00, - 0x01,0xff,0xe5,0xba,0xa6,0x00,0xe1,0x74,0x74,0xe0,0xe8,0x73,0xcf,0x86,0xe5,0x22, - 0x73,0xd4,0x3b,0x93,0x37,0xd2,0x1d,0xd1,0x0e,0x10,0x07,0x01,0xff,0x66,0x66,0x00, - 0x01,0xff,0x66,0x69,0x00,0x10,0x07,0x01,0xff,0x66,0x6c,0x00,0x01,0xff,0x66,0x66, - 0x69,0x00,0xd1,0x0f,0x10,0x08,0x01,0xff,0x66,0x66,0x6c,0x00,0x01,0xff,0x73,0x74, - 0x00,0x10,0x07,0x01,0xff,0x73,0x74,0x00,0x00,0x00,0x00,0x00,0xe3,0xc8,0x72,0xd2, - 0x11,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0xff,0xd5,0xb4,0xd5,0xb6,0x00, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xd5,0xb4,0xd5,0xa5,0x00,0x01,0xff,0xd5,0xb4,0xd5, - 0xab,0x00,0x10,0x09,0x01,0xff,0xd5,0xbe,0xd5,0xb6,0x00,0x01,0xff,0xd5,0xb4,0xd5, - 0xad,0x00,0xd3,0x09,0xe2,0x40,0x74,0xcf,0x06,0x01,0x00,0xd2,0x13,0xe1,0x30,0x75, - 0xe0,0xc1,0x74,0xcf,0x86,0xe5,0x9e,0x74,0x64,0x8d,0x74,0x06,0xff,0x00,0xe1,0x96, - 0x75,0xe0,0x63,0x75,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x7c, - 0xd3,0x3c,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xef,0xbd,0x81,0x00, - 0x10,0x08,0x01,0xff,0xef,0xbd,0x82,0x00,0x01,0xff,0xef,0xbd,0x83,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xef,0xbd,0x84,0x00,0x01,0xff,0xef,0xbd,0x85,0x00,0x10,0x08, - 0x01,0xff,0xef,0xbd,0x86,0x00,0x01,0xff,0xef,0xbd,0x87,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xef,0xbd,0x88,0x00,0x01,0xff,0xef,0xbd,0x89,0x00,0x10,0x08, - 0x01,0xff,0xef,0xbd,0x8a,0x00,0x01,0xff,0xef,0xbd,0x8b,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xef,0xbd,0x8c,0x00,0x01,0xff,0xef,0xbd,0x8d,0x00,0x10,0x08,0x01,0xff, - 0xef,0xbd,0x8e,0x00,0x01,0xff,0xef,0xbd,0x8f,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xef,0xbd,0x90,0x00,0x01,0xff,0xef,0xbd,0x91,0x00,0x10,0x08, - 0x01,0xff,0xef,0xbd,0x92,0x00,0x01,0xff,0xef,0xbd,0x93,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xef,0xbd,0x94,0x00,0x01,0xff,0xef,0xbd,0x95,0x00,0x10,0x08,0x01,0xff, - 0xef,0xbd,0x96,0x00,0x01,0xff,0xef,0xbd,0x97,0x00,0x92,0x1c,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xef,0xbd,0x98,0x00,0x01,0xff,0xef,0xbd,0x99,0x00,0x10,0x08,0x01,0xff, - 0xef,0xbd,0x9a,0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0x87,0xb3,0xe1,0x60,0xb0,0xe0, - 0xdd,0xae,0xcf,0x86,0xe5,0x81,0x9b,0xc4,0xe3,0xc1,0x07,0xe2,0x62,0x06,0xe1,0x11, - 0x86,0xe0,0x09,0x05,0xcf,0x86,0xe5,0xfb,0x02,0xd4,0x1c,0xe3,0x7f,0x76,0xe2,0xd6, - 0x75,0xe1,0xb1,0x75,0xe0,0x8a,0x75,0xcf,0x86,0xe5,0x57,0x75,0x94,0x07,0x63,0x42, - 0x75,0x07,0x00,0x07,0x00,0xe3,0x2b,0x78,0xe2,0xf0,0x77,0xe1,0x77,0x01,0xe0,0x88, - 0x77,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09, - 0x05,0xff,0xf0,0x90,0x90,0xa8,0x00,0x05,0xff,0xf0,0x90,0x90,0xa9,0x00,0x10,0x09, - 0x05,0xff,0xf0,0x90,0x90,0xaa,0x00,0x05,0xff,0xf0,0x90,0x90,0xab,0x00,0xd1,0x12, - 0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xac,0x00,0x05,0xff,0xf0,0x90,0x90,0xad,0x00, - 0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xae,0x00,0x05,0xff,0xf0,0x90,0x90,0xaf,0x00, - 0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb0,0x00,0x05,0xff,0xf0, - 0x90,0x90,0xb1,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb2,0x00,0x05,0xff,0xf0, - 0x90,0x90,0xb3,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb4,0x00,0x05, - 0xff,0xf0,0x90,0x90,0xb5,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x90,0xb6,0x00,0x05, - 0xff,0xf0,0x90,0x90,0xb7,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff, - 0xf0,0x90,0x90,0xb8,0x00,0x05,0xff,0xf0,0x90,0x90,0xb9,0x00,0x10,0x09,0x05,0xff, - 0xf0,0x90,0x90,0xba,0x00,0x05,0xff,0xf0,0x90,0x90,0xbb,0x00,0xd1,0x12,0x10,0x09, - 0x05,0xff,0xf0,0x90,0x90,0xbc,0x00,0x05,0xff,0xf0,0x90,0x90,0xbd,0x00,0x10,0x09, - 0x05,0xff,0xf0,0x90,0x90,0xbe,0x00,0x05,0xff,0xf0,0x90,0x90,0xbf,0x00,0xd2,0x24, - 0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x80,0x00,0x05,0xff,0xf0,0x90,0x91, - 0x81,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x82,0x00,0x05,0xff,0xf0,0x90,0x91, - 0x83,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x84,0x00,0x05,0xff,0xf0, - 0x90,0x91,0x85,0x00,0x10,0x09,0x05,0xff,0xf0,0x90,0x91,0x86,0x00,0x05,0xff,0xf0, - 0x90,0x91,0x87,0x00,0x94,0x4c,0x93,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x05,0xff, - 0xf0,0x90,0x91,0x88,0x00,0x05,0xff,0xf0,0x90,0x91,0x89,0x00,0x10,0x09,0x05,0xff, - 0xf0,0x90,0x91,0x8a,0x00,0x05,0xff,0xf0,0x90,0x91,0x8b,0x00,0xd1,0x12,0x10,0x09, - 0x05,0xff,0xf0,0x90,0x91,0x8c,0x00,0x05,0xff,0xf0,0x90,0x91,0x8d,0x00,0x10,0x09, - 0x07,0xff,0xf0,0x90,0x91,0x8e,0x00,0x07,0xff,0xf0,0x90,0x91,0x8f,0x00,0x05,0x00, - 0x05,0x00,0xd0,0xa0,0xcf,0x86,0xd5,0x07,0x64,0x30,0x76,0x07,0x00,0xd4,0x07,0x63, - 0x3d,0x76,0x07,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90, - 0x93,0x98,0x00,0x12,0xff,0xf0,0x90,0x93,0x99,0x00,0x10,0x09,0x12,0xff,0xf0,0x90, - 0x93,0x9a,0x00,0x12,0xff,0xf0,0x90,0x93,0x9b,0x00,0xd1,0x12,0x10,0x09,0x12,0xff, - 0xf0,0x90,0x93,0x9c,0x00,0x12,0xff,0xf0,0x90,0x93,0x9d,0x00,0x10,0x09,0x12,0xff, - 0xf0,0x90,0x93,0x9e,0x00,0x12,0xff,0xf0,0x90,0x93,0x9f,0x00,0xd2,0x24,0xd1,0x12, - 0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa0,0x00,0x12,0xff,0xf0,0x90,0x93,0xa1,0x00, - 0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa2,0x00,0x12,0xff,0xf0,0x90,0x93,0xa3,0x00, - 0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa4,0x00,0x12,0xff,0xf0,0x90,0x93, - 0xa5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xa6,0x00,0x12,0xff,0xf0,0x90,0x93, - 0xa7,0x00,0xcf,0x86,0xe5,0xc6,0x75,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x12,0xff,0xf0,0x90,0x93,0xa8,0x00,0x12,0xff,0xf0,0x90,0x93,0xa9,0x00,0x10, - 0x09,0x12,0xff,0xf0,0x90,0x93,0xaa,0x00,0x12,0xff,0xf0,0x90,0x93,0xab,0x00,0xd1, - 0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xac,0x00,0x12,0xff,0xf0,0x90,0x93,0xad, - 0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xae,0x00,0x12,0xff,0xf0,0x90,0x93,0xaf, - 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb0,0x00,0x12,0xff, - 0xf0,0x90,0x93,0xb1,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb2,0x00,0x12,0xff, - 0xf0,0x90,0x93,0xb3,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb4,0x00, - 0x12,0xff,0xf0,0x90,0x93,0xb5,0x00,0x10,0x09,0x12,0xff,0xf0,0x90,0x93,0xb6,0x00, - 0x12,0xff,0xf0,0x90,0x93,0xb7,0x00,0x93,0x28,0x92,0x24,0xd1,0x12,0x10,0x09,0x12, - 0xff,0xf0,0x90,0x93,0xb8,0x00,0x12,0xff,0xf0,0x90,0x93,0xb9,0x00,0x10,0x09,0x12, - 0xff,0xf0,0x90,0x93,0xba,0x00,0x12,0xff,0xf0,0x90,0x93,0xbb,0x00,0x00,0x00,0x12, - 0x00,0xd4,0x1f,0xe3,0xdf,0x76,0xe2,0x6a,0x76,0xe1,0x09,0x76,0xe0,0xea,0x75,0xcf, - 0x86,0xe5,0xb7,0x75,0x94,0x0a,0xe3,0xa2,0x75,0x62,0x99,0x75,0x07,0x00,0x07,0x00, - 0xe3,0xde,0x78,0xe2,0xaf,0x78,0xd1,0x09,0xe0,0x4c,0x78,0xcf,0x06,0x0b,0x00,0xe0, - 0x7f,0x78,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x11,0xff,0xf0,0x90,0xb3,0x80,0x00,0x11,0xff,0xf0,0x90,0xb3,0x81,0x00,0x10, - 0x09,0x11,0xff,0xf0,0x90,0xb3,0x82,0x00,0x11,0xff,0xf0,0x90,0xb3,0x83,0x00,0xd1, - 0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x84,0x00,0x11,0xff,0xf0,0x90,0xb3,0x85, - 0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x86,0x00,0x11,0xff,0xf0,0x90,0xb3,0x87, - 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x88,0x00,0x11,0xff, - 0xf0,0x90,0xb3,0x89,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8a,0x00,0x11,0xff, - 0xf0,0x90,0xb3,0x8b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8c,0x00, - 0x11,0xff,0xf0,0x90,0xb3,0x8d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x8e,0x00, - 0x11,0xff,0xf0,0x90,0xb3,0x8f,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11, - 0xff,0xf0,0x90,0xb3,0x90,0x00,0x11,0xff,0xf0,0x90,0xb3,0x91,0x00,0x10,0x09,0x11, - 0xff,0xf0,0x90,0xb3,0x92,0x00,0x11,0xff,0xf0,0x90,0xb3,0x93,0x00,0xd1,0x12,0x10, - 0x09,0x11,0xff,0xf0,0x90,0xb3,0x94,0x00,0x11,0xff,0xf0,0x90,0xb3,0x95,0x00,0x10, - 0x09,0x11,0xff,0xf0,0x90,0xb3,0x96,0x00,0x11,0xff,0xf0,0x90,0xb3,0x97,0x00,0xd2, - 0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x98,0x00,0x11,0xff,0xf0,0x90, - 0xb3,0x99,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9a,0x00,0x11,0xff,0xf0,0x90, - 0xb3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9c,0x00,0x11,0xff, - 0xf0,0x90,0xb3,0x9d,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0x9e,0x00,0x11,0xff, - 0xf0,0x90,0xb3,0x9f,0x00,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x11, - 0xff,0xf0,0x90,0xb3,0xa0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa1,0x00,0x10,0x09,0x11, - 0xff,0xf0,0x90,0xb3,0xa2,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa3,0x00,0xd1,0x12,0x10, - 0x09,0x11,0xff,0xf0,0x90,0xb3,0xa4,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa5,0x00,0x10, - 0x09,0x11,0xff,0xf0,0x90,0xb3,0xa6,0x00,0x11,0xff,0xf0,0x90,0xb3,0xa7,0x00,0xd2, - 0x24,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xa8,0x00,0x11,0xff,0xf0,0x90, - 0xb3,0xa9,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xaa,0x00,0x11,0xff,0xf0,0x90, - 0xb3,0xab,0x00,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xac,0x00,0x11,0xff, - 0xf0,0x90,0xb3,0xad,0x00,0x10,0x09,0x11,0xff,0xf0,0x90,0xb3,0xae,0x00,0x11,0xff, - 0xf0,0x90,0xb3,0xaf,0x00,0x93,0x23,0x92,0x1f,0xd1,0x12,0x10,0x09,0x11,0xff,0xf0, - 0x90,0xb3,0xb0,0x00,0x11,0xff,0xf0,0x90,0xb3,0xb1,0x00,0x10,0x09,0x11,0xff,0xf0, - 0x90,0xb3,0xb2,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x15,0xe4,0x91, - 0x7b,0xe3,0x9b,0x79,0xe2,0x94,0x78,0xe1,0xe4,0x77,0xe0,0x9d,0x77,0xcf,0x06,0x0c, - 0x00,0xe4,0xeb,0x7e,0xe3,0x44,0x7e,0xe2,0xed,0x7d,0xd1,0x0c,0xe0,0xb2,0x7d,0xcf, - 0x86,0x65,0x93,0x7d,0x14,0x00,0xe0,0xb6,0x7d,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4, - 0x90,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x80,0x00, - 0x10,0xff,0xf0,0x91,0xa3,0x81,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x82,0x00, - 0x10,0xff,0xf0,0x91,0xa3,0x83,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3, - 0x84,0x00,0x10,0xff,0xf0,0x91,0xa3,0x85,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3, - 0x86,0x00,0x10,0xff,0xf0,0x91,0xa3,0x87,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10, - 0xff,0xf0,0x91,0xa3,0x88,0x00,0x10,0xff,0xf0,0x91,0xa3,0x89,0x00,0x10,0x09,0x10, - 0xff,0xf0,0x91,0xa3,0x8a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8b,0x00,0xd1,0x12,0x10, - 0x09,0x10,0xff,0xf0,0x91,0xa3,0x8c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8d,0x00,0x10, - 0x09,0x10,0xff,0xf0,0x91,0xa3,0x8e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x8f,0x00,0xd3, - 0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x90,0x00,0x10,0xff, - 0xf0,0x91,0xa3,0x91,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x92,0x00,0x10,0xff, - 0xf0,0x91,0xa3,0x93,0x00,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x94,0x00, - 0x10,0xff,0xf0,0x91,0xa3,0x95,0x00,0x10,0x09,0x10,0xff,0xf0,0x91,0xa3,0x96,0x00, - 0x10,0xff,0xf0,0x91,0xa3,0x97,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x10,0xff,0xf0, - 0x91,0xa3,0x98,0x00,0x10,0xff,0xf0,0x91,0xa3,0x99,0x00,0x10,0x09,0x10,0xff,0xf0, - 0x91,0xa3,0x9a,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9b,0x00,0xd1,0x12,0x10,0x09,0x10, - 0xff,0xf0,0x91,0xa3,0x9c,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9d,0x00,0x10,0x09,0x10, - 0xff,0xf0,0x91,0xa3,0x9e,0x00,0x10,0xff,0xf0,0x91,0xa3,0x9f,0x00,0xd1,0x11,0xe0, - 0x12,0x81,0xcf,0x86,0xe5,0x09,0x81,0xe4,0xd2,0x80,0xcf,0x06,0x00,0x00,0xe0,0xdb, - 0x82,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x09,0xe3,0x10,0x81,0xcf,0x06, - 0x0c,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xe2,0x3b,0x82,0xe1,0x16,0x82,0xd0,0x06, - 0xcf,0x06,0x00,0x00,0xcf,0x86,0xa5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1, - 0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa1, - 0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xa3, - 0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa4,0x00,0x14,0xff,0xf0,0x96, - 0xb9,0xa5,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa6,0x00,0x14,0xff,0xf0,0x96, - 0xb9,0xa7,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xa8,0x00, - 0x14,0xff,0xf0,0x96,0xb9,0xa9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xaa,0x00, - 0x14,0xff,0xf0,0x96,0xb9,0xab,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9, - 0xac,0x00,0x14,0xff,0xf0,0x96,0xb9,0xad,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9, - 0xae,0x00,0x14,0xff,0xf0,0x96,0xb9,0xaf,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x14,0xff,0xf0,0x96,0xb9,0xb0,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb1,0x00,0x10, - 0x09,0x14,0xff,0xf0,0x96,0xb9,0xb2,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb3,0x00,0xd1, - 0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb4,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb5, - 0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb6,0x00,0x14,0xff,0xf0,0x96,0xb9,0xb7, - 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xb8,0x00,0x14,0xff, - 0xf0,0x96,0xb9,0xb9,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xba,0x00,0x14,0xff, - 0xf0,0x96,0xb9,0xbb,0x00,0xd1,0x12,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbc,0x00, - 0x14,0xff,0xf0,0x96,0xb9,0xbd,0x00,0x10,0x09,0x14,0xff,0xf0,0x96,0xb9,0xbe,0x00, - 0x14,0xff,0xf0,0x96,0xb9,0xbf,0x00,0x14,0x00,0xd2,0x14,0xe1,0x25,0x82,0xe0,0x1c, - 0x82,0xcf,0x86,0xe5,0xdd,0x81,0xe4,0x9a,0x81,0xcf,0x06,0x12,0x00,0xd1,0x0b,0xe0, - 0x51,0x83,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0x95,0x8b,0xcf,0x86,0xd5,0x22,0xe4, - 0xd0,0x88,0xe3,0x93,0x88,0xe2,0x38,0x88,0xe1,0x31,0x88,0xe0,0x2a,0x88,0xcf,0x86, - 0xe5,0xfb,0x87,0xe4,0xe2,0x87,0x93,0x07,0x62,0xd1,0x87,0x12,0xe6,0x12,0xe6,0xe4, - 0x36,0x89,0xe3,0x2f,0x89,0xd2,0x09,0xe1,0xb8,0x88,0xcf,0x06,0x10,0x00,0xe1,0x1f, - 0x89,0xe0,0xec,0x88,0xcf,0x86,0xe5,0x21,0x01,0xd4,0x90,0xd3,0x48,0xd2,0x24,0xd1, - 0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa3, - 0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xa5, - 0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa6,0x00,0x12,0xff,0xf0,0x9e, - 0xa4,0xa7,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xa8,0x00,0x12,0xff,0xf0,0x9e, - 0xa4,0xa9,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xaa,0x00, - 0x12,0xff,0xf0,0x9e,0xa4,0xab,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xac,0x00, - 0x12,0xff,0xf0,0x9e,0xa4,0xad,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4, - 0xae,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xaf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4, - 0xb0,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb1,0x00,0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10, - 0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb2,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb3,0x00,0x10, - 0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb4,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb5,0x00,0xd1, - 0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb6,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb7, - 0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xb8,0x00,0x12,0xff,0xf0,0x9e,0xa4,0xb9, - 0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xba,0x00,0x12,0xff, - 0xf0,0x9e,0xa4,0xbb,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbc,0x00,0x12,0xff, - 0xf0,0x9e,0xa4,0xbd,0x00,0xd1,0x12,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa4,0xbe,0x00, - 0x12,0xff,0xf0,0x9e,0xa4,0xbf,0x00,0x10,0x09,0x12,0xff,0xf0,0x9e,0xa5,0x80,0x00, - 0x12,0xff,0xf0,0x9e,0xa5,0x81,0x00,0x94,0x1e,0x93,0x1a,0x92,0x16,0x91,0x12,0x10, - 0x09,0x12,0xff,0xf0,0x9e,0xa5,0x82,0x00,0x12,0xff,0xf0,0x9e,0xa5,0x83,0x00,0x12, - 0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - /* nfdi_c0100 */ - 0x57,0x04,0x01,0x00,0xc6,0xe5,0xac,0x13,0xe4,0x41,0x0c,0xe3,0x7a,0x07,0xe2,0xf3, - 0x01,0xc1,0xd0,0x1f,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x53,0x04,0x01,0x00, - 0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x04,0x01,0x00,0x01,0xff,0x00,0x01,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0xe4,0xd4,0x7c,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x41,0xcc,0x80,0x00,0x01,0xff,0x41,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x41, - 0xcc,0x82,0x00,0x01,0xff,0x41,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x41, - 0xcc,0x88,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x43, - 0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x80,0x00,0x01, - 0xff,0x45,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x82,0x00,0x01,0xff,0x45, - 0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x80,0x00,0x01,0xff,0x49, - 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x82,0x00,0x01,0xff,0x49,0xcc,0x88, - 0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x4e,0xcc,0x83, - 0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x80,0x00,0x01,0xff,0x4f,0xcc,0x81,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x82,0x00,0x01,0xff,0x4f,0xcc,0x83,0x00,0x10, - 0x08,0x01,0xff,0x4f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01, - 0x00,0x01,0xff,0x55,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x81,0x00,0x01, - 0xff,0x55,0xcc,0x82,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x88,0x00,0x01, - 0xff,0x59,0xcc,0x81,0x00,0x01,0x00,0xd4,0x7c,0xd3,0x3c,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x61,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x81,0x00,0x10,0x08,0x01, - 0xff,0x61,0xcc,0x82,0x00,0x01,0xff,0x61,0xcc,0x83,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x61,0xcc,0x88,0x00,0x01,0xff,0x61,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x01, - 0xff,0x63,0xcc,0xa7,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x65,0xcc,0x80, - 0x00,0x01,0xff,0x65,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x65,0xcc,0x82,0x00,0x01, - 0xff,0x65,0xcc,0x88,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x80,0x00,0x01, - 0xff,0x69,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x69,0xcc,0x82,0x00,0x01,0xff,0x69, - 0xcc,0x88,0x00,0xd3,0x38,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x6e, - 0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x81, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x6f,0xcc,0x82,0x00,0x01,0xff,0x6f,0xcc,0x83, - 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x88,0x00,0x01,0x00,0xd2,0x1c,0xd1,0x0c,0x10, - 0x04,0x01,0x00,0x01,0xff,0x75,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x75,0xcc,0x81, - 0x00,0x01,0xff,0x75,0xcc,0x82,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x75,0xcc,0x88, - 0x00,0x01,0xff,0x79,0xcc,0x81,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x79,0xcc,0x88, - 0x00,0xe1,0x9a,0x03,0xe0,0xd3,0x01,0xcf,0x86,0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x84, - 0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x86,0x00,0x01,0xff,0x61,0xcc,0x86,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa8,0x00,0x01,0xff,0x61,0xcc,0xa8,0x00,0x10, - 0x08,0x01,0xff,0x43,0xcc,0x81,0x00,0x01,0xff,0x63,0xcc,0x81,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x43,0xcc,0x82,0x00,0x01,0xff,0x63,0xcc,0x82,0x00,0x10, - 0x08,0x01,0xff,0x43,0xcc,0x87,0x00,0x01,0xff,0x63,0xcc,0x87,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x43,0xcc,0x8c,0x00,0x01,0xff,0x63,0xcc,0x8c,0x00,0x10,0x08,0x01, - 0xff,0x44,0xcc,0x8c,0x00,0x01,0xff,0x64,0xcc,0x8c,0x00,0xd3,0x34,0xd2,0x14,0x51, - 0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x84,0x00,0x01,0xff,0x65,0xcc,0x84, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0x86, - 0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x87,0x00,0x01,0xff,0x65,0xcc,0x87,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0xa8,0x00,0x01,0xff,0x65,0xcc,0xa8, - 0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x8c,0x00,0x01,0xff,0x65,0xcc,0x8c,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x82,0x00,0x01,0xff,0x67,0xcc,0x82,0x00,0x10, - 0x08,0x01,0xff,0x47,0xcc,0x86,0x00,0x01,0xff,0x67,0xcc,0x86,0x00,0xd4,0x74,0xd3, - 0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x87,0x00,0x01,0xff,0x67, - 0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0xa7,0x00,0x01,0xff,0x67,0xcc,0xa7, - 0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0x82,0x00,0x01,0xff,0x68,0xcc,0x82, - 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x83,0x00,0x01, - 0xff,0x69,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x84,0x00,0x01,0xff,0x69, - 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x86,0x00,0x01,0xff,0x69, - 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa8,0x00,0x01,0xff,0x69,0xcc,0xa8, - 0x00,0xd3,0x30,0xd2,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x49,0xcc,0x87,0x00,0x01, - 0x00,0x01,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4a,0xcc,0x82,0x00,0x01,0xff,0x6a, - 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa7,0x00,0x01,0xff,0x6b,0xcc,0xa7, - 0x00,0xd2,0x1c,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x4c,0xcc,0x81,0x00,0x10, - 0x08,0x01,0xff,0x6c,0xcc,0x81,0x00,0x01,0xff,0x4c,0xcc,0xa7,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x6c,0xcc,0xa7,0x00,0x01,0xff,0x4c,0xcc,0x8c,0x00,0x10,0x08,0x01, - 0xff,0x6c,0xcc,0x8c,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd4,0xd4,0x60,0xd3,0x30,0xd2, - 0x10,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x4e,0xcc,0x81,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x6e,0xcc,0x81,0x00,0x01,0xff,0x4e,0xcc,0xa7,0x00,0x10, - 0x08,0x01,0xff,0x6e,0xcc,0xa7,0x00,0x01,0xff,0x4e,0xcc,0x8c,0x00,0xd2,0x10,0x91, - 0x0c,0x10,0x08,0x01,0xff,0x6e,0xcc,0x8c,0x00,0x01,0x00,0x01,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x4f,0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0x84,0x00,0x10,0x08,0x01, - 0xff,0x4f,0xcc,0x86,0x00,0x01,0xff,0x6f,0xcc,0x86,0x00,0xd3,0x34,0xd2,0x14,0x91, - 0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8b,0x00,0x01,0xff,0x6f,0xcc,0x8b,0x00,0x01, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x81,0x00,0x01,0xff,0x72,0xcc,0x81, - 0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa7,0x00,0x01,0xff,0x72,0xcc,0xa7,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x8c,0x00,0x01,0xff,0x72,0xcc,0x8c, - 0x00,0x10,0x08,0x01,0xff,0x53,0xcc,0x81,0x00,0x01,0xff,0x73,0xcc,0x81,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x82,0x00,0x01,0xff,0x73,0xcc,0x82,0x00,0x10, - 0x08,0x01,0xff,0x53,0xcc,0xa7,0x00,0x01,0xff,0x73,0xcc,0xa7,0x00,0xd4,0x74,0xd3, - 0x34,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x8c,0x00,0x01,0xff,0x73, - 0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xa7,0x00,0x01,0xff,0x74,0xcc,0xa7, - 0x00,0x91,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0x8c,0x00,0x01,0xff,0x74,0xcc,0x8c, - 0x00,0x01,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x83,0x00,0x01, - 0xff,0x75,0xcc,0x83,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x84,0x00,0x01,0xff,0x75, - 0xcc,0x84,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x86,0x00,0x01,0xff,0x75, - 0xcc,0x86,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x8a,0x00,0x01,0xff,0x75,0xcc,0x8a, - 0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x8b,0x00,0x01, - 0xff,0x75,0xcc,0x8b,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa8,0x00,0x01,0xff,0x75, - 0xcc,0xa8,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x82,0x00,0x01,0xff,0x77, - 0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x82,0x00,0x01,0xff,0x79,0xcc,0x82, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x59,0xcc,0x88,0x00,0x01,0xff,0x5a, - 0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x81,0x00,0x01,0xff,0x5a,0xcc,0x87, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x7a,0xcc,0x87,0x00,0x01,0xff,0x5a,0xcc,0x8c, - 0x00,0x10,0x08,0x01,0xff,0x7a,0xcc,0x8c,0x00,0x01,0x00,0xd0,0x4a,0xcf,0x86,0x55, - 0x04,0x01,0x00,0xd4,0x2c,0xd3,0x18,0x92,0x14,0x91,0x10,0x10,0x08,0x01,0xff,0x4f, - 0xcc,0x9b,0x00,0x01,0xff,0x6f,0xcc,0x9b,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01, - 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0x55,0xcc,0x9b,0x00,0x93, - 0x14,0x92,0x10,0x91,0x0c,0x10,0x08,0x01,0xff,0x75,0xcc,0x9b,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xb4,0xd4,0x24,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0x41,0xcc,0x8c,0x00,0x10, - 0x08,0x01,0xff,0x61,0xcc,0x8c,0x00,0x01,0xff,0x49,0xcc,0x8c,0x00,0xd3,0x46,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x69,0xcc,0x8c,0x00,0x01,0xff,0x4f,0xcc,0x8c, - 0x00,0x10,0x08,0x01,0xff,0x6f,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x8c,0x00,0xd1, - 0x12,0x10,0x08,0x01,0xff,0x75,0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x84, - 0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x84,0x00,0x01,0xff,0x55,0xcc,0x88, - 0xcc,0x81,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88,0xcc,0x81, - 0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x8c,0x00,0x10,0x0a,0x01,0xff,0x75,0xcc,0x88, - 0xcc,0x8c,0x00,0x01,0xff,0x55,0xcc,0x88,0xcc,0x80,0x00,0xd1,0x0e,0x10,0x0a,0x01, - 0xff,0x75,0xcc,0x88,0xcc,0x80,0x00,0x01,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x88, - 0xcc,0x84,0x00,0x01,0xff,0x61,0xcc,0x88,0xcc,0x84,0x00,0xd4,0x80,0xd3,0x3a,0xd2, - 0x26,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x87,0xcc,0x84,0x00,0x01,0xff,0x61, - 0xcc,0x87,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc3,0x86,0xcc,0x84,0x00,0x01,0xff, - 0xc3,0xa6,0xcc,0x84,0x00,0x51,0x04,0x01,0x00,0x10,0x08,0x01,0xff,0x47,0xcc,0x8c, - 0x00,0x01,0xff,0x67,0xcc,0x8c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b, - 0xcc,0x8c,0x00,0x01,0xff,0x6b,0xcc,0x8c,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa8, - 0x00,0x01,0xff,0x6f,0xcc,0xa8,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa8, - 0xcc,0x84,0x00,0x01,0xff,0x6f,0xcc,0xa8,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xc6, - 0xb7,0xcc,0x8c,0x00,0x01,0xff,0xca,0x92,0xcc,0x8c,0x00,0xd3,0x24,0xd2,0x10,0x91, - 0x0c,0x10,0x08,0x01,0xff,0x6a,0xcc,0x8c,0x00,0x01,0x00,0x01,0x00,0x91,0x10,0x10, - 0x08,0x01,0xff,0x47,0xcc,0x81,0x00,0x01,0xff,0x67,0xcc,0x81,0x00,0x04,0x00,0xd2, - 0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x4e,0xcc,0x80,0x00,0x04,0xff,0x6e,0xcc,0x80, - 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x8a,0xcc,0x81,0x00,0x01,0xff,0x61,0xcc,0x8a, - 0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xc3,0x86,0xcc,0x81,0x00,0x01,0xff, - 0xc3,0xa6,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xc3,0x98,0xcc,0x81,0x00,0x01,0xff, - 0xc3,0xb8,0xcc,0x81,0x00,0xe2,0x07,0x02,0xe1,0xae,0x01,0xe0,0x93,0x01,0xcf,0x86, - 0xd5,0xf4,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc, - 0x8f,0x00,0x01,0xff,0x61,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x91,0x00, - 0x01,0xff,0x61,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45,0xcc,0x8f,0x00, - 0x01,0xff,0x65,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x45,0xcc,0x91,0x00,0x01,0xff, - 0x65,0xcc,0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x8f,0x00, - 0x01,0xff,0x69,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0x91,0x00,0x01,0xff, - 0x69,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0x8f,0x00,0x01,0xff, - 0x6f,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x91,0x00,0x01,0xff,0x6f,0xcc, - 0x91,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52,0xcc,0x8f,0x00, - 0x01,0xff,0x72,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0x91,0x00,0x01,0xff, - 0x72,0xcc,0x91,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0x8f,0x00,0x01,0xff, - 0x75,0xcc,0x8f,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0x91,0x00,0x01,0xff,0x75,0xcc, - 0x91,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x04,0xff,0x53,0xcc,0xa6,0x00,0x04,0xff, - 0x73,0xcc,0xa6,0x00,0x10,0x08,0x04,0xff,0x54,0xcc,0xa6,0x00,0x04,0xff,0x74,0xcc, - 0xa6,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04,0xff,0x48,0xcc,0x8c,0x00,0x04,0xff, - 0x68,0xcc,0x8c,0x00,0xd4,0x68,0xd3,0x20,0xd2,0x0c,0x91,0x08,0x10,0x04,0x06,0x00, - 0x07,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x08,0x04,0xff,0x41,0xcc,0x87,0x00, - 0x04,0xff,0x61,0xcc,0x87,0x00,0xd2,0x24,0xd1,0x10,0x10,0x08,0x04,0xff,0x45,0xcc, - 0xa7,0x00,0x04,0xff,0x65,0xcc,0xa7,0x00,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x88,0xcc, - 0x84,0x00,0x04,0xff,0x6f,0xcc,0x88,0xcc,0x84,0x00,0xd1,0x14,0x10,0x0a,0x04,0xff, - 0x4f,0xcc,0x83,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc,0x83,0xcc,0x84,0x00,0x10,0x08, - 0x04,0xff,0x4f,0xcc,0x87,0x00,0x04,0xff,0x6f,0xcc,0x87,0x00,0x93,0x30,0xd2,0x24, - 0xd1,0x14,0x10,0x0a,0x04,0xff,0x4f,0xcc,0x87,0xcc,0x84,0x00,0x04,0xff,0x6f,0xcc, - 0x87,0xcc,0x84,0x00,0x10,0x08,0x04,0xff,0x59,0xcc,0x84,0x00,0x04,0xff,0x79,0xcc, - 0x84,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0xcf,0x86, - 0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04,0x08,0x00,0x09,0x00,0x09,0x00, - 0x09,0x00,0x01,0x00,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18, - 0x53,0x04,0x01,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00, - 0x11,0x04,0x04,0x00,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01,0x00, - 0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x04,0x00,0x94,0x18,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x04,0x00, - 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00,0x07,0x00,0xe1,0x35,0x01,0xd0, - 0x72,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0xe6,0xd3,0x10,0x52,0x04,0x01,0xe6,0x91, - 0x08,0x10,0x04,0x01,0xe6,0x01,0xe8,0x01,0xdc,0x92,0x0c,0x51,0x04,0x01,0xdc,0x10, - 0x04,0x01,0xe8,0x01,0xd8,0x01,0xdc,0xd4,0x2c,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10, - 0x04,0x01,0xdc,0x01,0xca,0x10,0x04,0x01,0xca,0x01,0xdc,0x51,0x04,0x01,0xdc,0x10, - 0x04,0x01,0xdc,0x01,0xca,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0xca,0x01,0xdc,0x01, - 0xdc,0x01,0xdc,0xd3,0x08,0x12,0x04,0x01,0xdc,0x01,0x01,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x01,0x01,0x01,0xdc,0x01,0xdc,0x91,0x08,0x10,0x04,0x01,0xdc,0x01,0xe6,0x01, - 0xe6,0xcf,0x86,0xd5,0x7f,0xd4,0x47,0xd3,0x2e,0xd2,0x19,0xd1,0x0e,0x10,0x07,0x01, - 0xff,0xcc,0x80,0x00,0x01,0xff,0xcc,0x81,0x00,0x10,0x04,0x01,0xe6,0x01,0xff,0xcc, - 0x93,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcc,0x88,0xcc,0x81,0x00,0x01,0xf0,0x10, - 0x04,0x04,0xe6,0x04,0xdc,0xd2,0x08,0x11,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10, - 0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x04,0xdc,0x06,0xff,0x00,0xd3,0x18,0xd2,0x0c, - 0x51,0x04,0x07,0xe6,0x10,0x04,0x07,0xe6,0x07,0xdc,0x51,0x04,0x07,0xdc,0x10,0x04, - 0x07,0xdc,0x07,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe8,0x08,0xdc,0x10,0x04, - 0x08,0xdc,0x08,0xe6,0xd1,0x08,0x10,0x04,0x08,0xe9,0x07,0xea,0x10,0x04,0x07,0xea, - 0x07,0xe9,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0xea,0x10,0x04,0x04,0xe9, - 0x06,0xe6,0x06,0xe6,0x06,0xe6,0xd3,0x13,0x52,0x04,0x0a,0x00,0x91,0x0b,0x10,0x07, - 0x01,0xff,0xca,0xb9,0x00,0x01,0x00,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10, - 0x04,0x01,0x00,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x06,0x01,0xff,0x3b,0x00,0x10, - 0x00,0xd0,0xe1,0xcf,0x86,0xd5,0x7a,0xd4,0x5f,0xd3,0x21,0x52,0x04,0x00,0x00,0xd1, - 0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, - 0xce,0x91,0xcc,0x81,0x00,0x01,0xff,0xc2,0xb7,0x00,0xd2,0x1f,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xce,0x95,0xcc,0x81,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00,0x10,0x09, - 0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0x00,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xce, - 0x9f,0xcc,0x81,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0x01, - 0xff,0xce,0xa9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff, - 0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4, - 0x4a,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01, - 0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x88,0x00, - 0x01,0xff,0xce,0xa5,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc, - 0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc, - 0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0x93,0x17,0x92,0x13,0x91,0x0f,0x10, - 0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x81,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x39,0x53,0x04,0x01,0x00,0xd2,0x16,0x51,0x04, - 0x01,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x88,0x00,0x01,0xff,0xcf,0x85,0xcc, - 0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x01,0xff,0xcf, - 0x85,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x0a,0x00,0xd3, - 0x26,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xcf,0x92,0xcc, - 0x81,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xcf,0x92,0xcc,0x88,0x00,0x01,0x00,0x10, - 0x04,0x01,0x00,0x04,0x00,0xd2,0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x01,0x00,0x04, - 0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x01,0x00,0x04,0x00,0xd4, - 0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x06, - 0x00,0x07,0x00,0x12,0x04,0x07,0x00,0x08,0x00,0xe3,0x47,0x04,0xe2,0xbe,0x02,0xe1, - 0x07,0x01,0xd0,0x8b,0xcf,0x86,0xd5,0x6c,0xd4,0x53,0xd3,0x30,0xd2,0x1f,0xd1,0x12, - 0x10,0x09,0x04,0xff,0xd0,0x95,0xcc,0x80,0x00,0x01,0xff,0xd0,0x95,0xcc,0x88,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x93,0xcc,0x81,0x00,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x01,0xff,0xd0,0x86,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xd0,0x9a,0xcc,0x81,0x00,0x04,0xff,0xd0,0x98,0xcc,0x80,0x00, - 0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x86,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0x92, - 0x11,0x91,0x0d,0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x98,0xcc,0x86,0x00,0x01,0x00, - 0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x11,0x91,0x0d,0x10,0x04, - 0x01,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x86,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5, - 0x57,0x54,0x04,0x01,0x00,0xd3,0x30,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0, - 0xb5,0xcc,0x80,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x88,0x00,0x10,0x04,0x01,0x00,0x01, - 0xff,0xd0,0xb3,0xcc,0x81,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, - 0xd1,0x96,0xcc,0x88,0x00,0x52,0x04,0x01,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0, - 0xba,0xcc,0x81,0x00,0x04,0xff,0xd0,0xb8,0xcc,0x80,0x00,0x10,0x09,0x01,0xff,0xd1, - 0x83,0xcc,0x86,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x1a,0x52,0x04,0x01,0x00, - 0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd1,0xb4,0xcc,0x8f,0x00,0x01,0xff,0xd1, - 0xb5,0xcc,0x8f,0x00,0x01,0x00,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x94,0x24,0xd3,0x18, - 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0x51,0x04,0x01,0xe6, - 0x10,0x04,0x01,0xe6,0x0a,0xe6,0x92,0x08,0x11,0x04,0x04,0x00,0x06,0x00,0x04,0x00, - 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0xbe,0xd4,0x4a,0xd3,0x2a,0xd2,0x1a,0xd1,0x0d, - 0x10,0x04,0x01,0x00,0x01,0xff,0xd0,0x96,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0, - 0xb6,0xcc,0x86,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, - 0x06,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04, - 0x06,0x00,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00, - 0x09,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x90,0xcc,0x86, - 0x00,0x01,0xff,0xd0,0xb0,0xcc,0x86,0x00,0x10,0x09,0x01,0xff,0xd0,0x90,0xcc,0x88, - 0x00,0x01,0xff,0xd0,0xb0,0xcc,0x88,0x00,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, - 0xd0,0x95,0xcc,0x86,0x00,0x01,0xff,0xd0,0xb5,0xcc,0x86,0x00,0xd2,0x16,0x51,0x04, - 0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0x98,0xcc,0x88,0x00,0x01,0xff,0xd3,0x99,0xcc, - 0x88,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd0,0x96,0xcc,0x88,0x00,0x01,0xff,0xd0, - 0xb6,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0x97,0xcc,0x88,0x00,0x01,0xff,0xd0, - 0xb7,0xcc,0x88,0x00,0xd4,0x74,0xd3,0x3a,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09, - 0x01,0xff,0xd0,0x98,0xcc,0x84,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x84,0x00,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xd0,0x98,0xcc,0x88,0x00,0x01,0xff,0xd0,0xb8,0xcc,0x88,0x00, - 0x10,0x09,0x01,0xff,0xd0,0x9e,0xcc,0x88,0x00,0x01,0xff,0xd0,0xbe,0xcc,0x88,0x00, - 0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff,0xd3,0xa8,0xcc,0x88,0x00,0x01, - 0xff,0xd3,0xa9,0xcc,0x88,0x00,0xd1,0x12,0x10,0x09,0x04,0xff,0xd0,0xad,0xcc,0x88, - 0x00,0x04,0xff,0xd1,0x8d,0xcc,0x88,0x00,0x10,0x09,0x01,0xff,0xd0,0xa3,0xcc,0x84, - 0x00,0x01,0xff,0xd1,0x83,0xcc,0x84,0x00,0xd3,0x3a,0xd2,0x24,0xd1,0x12,0x10,0x09, - 0x01,0xff,0xd0,0xa3,0xcc,0x88,0x00,0x01,0xff,0xd1,0x83,0xcc,0x88,0x00,0x10,0x09, - 0x01,0xff,0xd0,0xa3,0xcc,0x8b,0x00,0x01,0xff,0xd1,0x83,0xcc,0x8b,0x00,0x91,0x12, - 0x10,0x09,0x01,0xff,0xd0,0xa7,0xcc,0x88,0x00,0x01,0xff,0xd1,0x87,0xcc,0x88,0x00, - 0x08,0x00,0x92,0x16,0x91,0x12,0x10,0x09,0x01,0xff,0xd0,0xab,0xcc,0x88,0x00,0x01, - 0xff,0xd1,0x8b,0xcc,0x88,0x00,0x09,0x00,0x09,0x00,0xd1,0x74,0xd0,0x36,0xcf,0x86, - 0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00, - 0xd4,0x10,0x93,0x0c,0x52,0x04,0x0a,0x00,0x11,0x04,0x0b,0x00,0x0c,0x00,0x10,0x00, - 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0xba, - 0xcf,0x86,0xd5,0x4c,0xd4,0x24,0x53,0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x14,0x00,0x01,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, - 0x10,0x00,0x10,0x04,0x10,0x00,0x0d,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x00,0x00,0x02,0xdc,0x02,0xe6,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc,0x02,0xe6, - 0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xde,0x02,0xdc,0x02,0xe6,0xd4,0x2c, - 0xd3,0x10,0x92,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x08,0xdc,0x02,0xdc,0x02,0xdc, - 0xd2,0x0c,0x51,0x04,0x02,0xe6,0x10,0x04,0x02,0xdc,0x02,0xe6,0xd1,0x08,0x10,0x04, - 0x02,0xe6,0x02,0xde,0x10,0x04,0x02,0xe4,0x02,0xe6,0xd3,0x20,0xd2,0x10,0xd1,0x08, - 0x10,0x04,0x01,0x0a,0x01,0x0b,0x10,0x04,0x01,0x0c,0x01,0x0d,0xd1,0x08,0x10,0x04, - 0x01,0x0e,0x01,0x0f,0x10,0x04,0x01,0x10,0x01,0x11,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x01,0x12,0x01,0x13,0x10,0x04,0x09,0x13,0x01,0x14,0xd1,0x08,0x10,0x04,0x01,0x15, - 0x01,0x16,0x10,0x04,0x01,0x00,0x01,0x17,0xcf,0x86,0xd5,0x28,0x94,0x24,0x93,0x20, - 0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x18,0x10,0x04,0x01,0x19,0x01,0x00, - 0xd1,0x08,0x10,0x04,0x02,0xe6,0x08,0xdc,0x10,0x04,0x08,0x00,0x08,0x12,0x00,0x00, - 0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, - 0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x93,0x10, - 0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xe2,0xfb,0x01,0xe1,0x2b,0x01,0xd0,0xa8,0xcf,0x86,0xd5,0x55,0xd4,0x28,0xd3,0x10, - 0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x10,0x00,0x0a,0x00,0xd2,0x0c, - 0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00,0x08,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x07,0x00,0x07,0x00,0xd3,0x0c,0x52,0x04,0x07,0xe6,0x11,0x04,0x07,0xe6,0x0a,0xe6, - 0xd2,0x10,0xd1,0x08,0x10,0x04,0x0a,0x1e,0x0a,0x1f,0x10,0x04,0x0a,0x20,0x01,0x00, - 0xd1,0x09,0x10,0x05,0x0f,0xff,0x00,0x00,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0xd4, - 0x3d,0x93,0x39,0xd2,0x1a,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x09,0x01, - 0xff,0xd8,0xa7,0xd9,0x93,0x00,0x01,0xff,0xd8,0xa7,0xd9,0x94,0x00,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xd9,0x88,0xd9,0x94,0x00,0x01,0xff,0xd8,0xa7,0xd9,0x95,0x00,0x10, - 0x09,0x01,0xff,0xd9,0x8a,0xd9,0x94,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00, - 0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x86, - 0xd5,0x5c,0xd4,0x20,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04, - 0x01,0x00,0x01,0x1b,0xd1,0x08,0x10,0x04,0x01,0x1c,0x01,0x1d,0x10,0x04,0x01,0x1e, - 0x01,0x1f,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x20,0x01,0x21,0x10,0x04, - 0x01,0x22,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x10,0x04,0x07,0xdc, - 0x07,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x07,0xe6,0x08,0xe6,0x08,0xe6,0xd1,0x08, - 0x10,0x04,0x08,0xdc,0x08,0xe6,0x10,0x04,0x08,0xe6,0x0c,0xdc,0xd4,0x10,0x53,0x04, - 0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06,0x00,0x93,0x10,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x01,0x23,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x22, - 0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x08, - 0x11,0x04,0x04,0x00,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x04,0x00, - 0xcf,0x86,0xd5,0x5b,0xd4,0x2e,0xd3,0x1e,0x92,0x1a,0xd1,0x0d,0x10,0x09,0x01,0xff, - 0xdb,0x95,0xd9,0x94,0x00,0x01,0x00,0x10,0x09,0x01,0xff,0xdb,0x81,0xd9,0x94,0x00, - 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x04,0x00,0xd3,0x19,0xd2,0x11,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, - 0xdb,0x92,0xd9,0x94,0x00,0x11,0x04,0x01,0x00,0x01,0xe6,0x52,0x04,0x01,0xe6,0xd1, - 0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0xd4,0x38,0xd3, - 0x1c,0xd2,0x0c,0x51,0x04,0x01,0xe6,0x10,0x04,0x01,0xe6,0x01,0xdc,0xd1,0x08,0x10, - 0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xe6,0xd2,0x10,0xd1,0x08,0x10, - 0x04,0x01,0xe6,0x01,0x00,0x10,0x04,0x01,0xdc,0x01,0xe6,0x91,0x08,0x10,0x04,0x01, - 0xe6,0x01,0xdc,0x07,0x00,0x53,0x04,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x04, - 0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x07,0x00,0xd1,0xc8,0xd0,0x76,0xcf, - 0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04, - 0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04, - 0x00,0x04,0x24,0x04,0x00,0x04,0x00,0x04,0x00,0xd4,0x14,0x53,0x04,0x04,0x00,0x52, - 0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x07,0x00,0x07,0x00,0xd3,0x1c,0xd2, - 0x0c,0x91,0x08,0x10,0x04,0x04,0xe6,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04, - 0xdc,0x04,0xe6,0x10,0x04,0x04,0xe6,0x04,0xdc,0xd2,0x0c,0x51,0x04,0x04,0xdc,0x10, - 0x04,0x04,0xe6,0x04,0xdc,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10,0x04,0x04, - 0xdc,0x04,0xe6,0xcf,0x86,0xd5,0x3c,0x94,0x38,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x04, - 0xe6,0x10,0x04,0x04,0xdc,0x04,0xe6,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10, - 0x04,0x04,0xdc,0x04,0xe6,0xd2,0x10,0xd1,0x08,0x10,0x04,0x04,0xdc,0x04,0xe6,0x10, - 0x04,0x04,0xe6,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x08, - 0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0a, - 0x00,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x14,0x53,0x04,0x09,0x00,0x92,0x0c,0x51, - 0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xe6,0x09,0xe6,0xd3,0x10,0x92,0x0c,0x51, - 0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09, - 0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x14,0xdc,0x14, - 0x00,0xe4,0xf8,0x57,0xe3,0x45,0x3f,0xe2,0xf4,0x3e,0xe1,0xc7,0x2c,0xe0,0x21,0x10, - 0xcf,0x86,0xc5,0xe4,0x80,0x08,0xe3,0xcb,0x03,0xe2,0x61,0x01,0xd1,0x94,0xd0,0x5a, - 0xcf,0x86,0xd5,0x20,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52,0x04,0x0b,0x00,0x11,0x04, - 0x0b,0x00,0x0b,0xe6,0x92,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04,0x0b,0x00,0x0b,0xe6, - 0x0b,0xe6,0xd4,0x24,0xd3,0x10,0x52,0x04,0x0b,0xe6,0x91,0x08,0x10,0x04,0x0b,0x00, - 0x0b,0xe6,0x0b,0xe6,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6,0x0b,0xe6, - 0x11,0x04,0x0b,0xe6,0x00,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04, - 0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xcf,0x86,0xd5,0x20,0x54,0x04,0x0c,0x00, - 0x53,0x04,0x0c,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0c,0xdc,0x0c,0xdc, - 0x51,0x04,0x00,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x13,0x00, - 0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xd0,0x4a,0xcf,0x86,0x55,0x04,0x00,0x00,0xd4,0x20,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0d,0x00,0x10,0x00,0x0d,0x00,0x0d,0x00,0x52,0x04,0x0d,0x00,0x91,0x08, - 0x10,0x04,0x0d,0x00,0x10,0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00, - 0x10,0x04,0x10,0x00,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x12,0x00, - 0x52,0x04,0x12,0x00,0x11,0x04,0x12,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04, - 0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x14,0xdc, - 0x12,0xe6,0x12,0xe6,0xd4,0x30,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x12,0xe6,0x10,0x04, - 0x12,0x00,0x11,0xdc,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xdc,0x0d,0xe6,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x0d,0xe6,0x91,0x08,0x10,0x04,0x0d,0xe6, - 0x0d,0xdc,0x0d,0xdc,0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0x1b,0x0d,0x1c, - 0x10,0x04,0x0d,0x1d,0x0d,0xe6,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xdc,0x0d,0xe6, - 0xd2,0x10,0xd1,0x08,0x10,0x04,0x0d,0xe6,0x0d,0xdc,0x10,0x04,0x0d,0xdc,0x0d,0xe6, - 0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x10,0xe6,0xe1,0x3a,0x01,0xd0,0x77,0xcf, - 0x86,0xd5,0x20,0x94,0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x01, - 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0xd4,0x1b,0x53,0x04,0x01,0x00,0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00,0x01, - 0xff,0xe0,0xa4,0xa8,0xe0,0xa4,0xbc,0x00,0x01,0x00,0x01,0x00,0xd3,0x26,0xd2,0x13, - 0x91,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa4,0xb0,0xe0,0xa4,0xbc,0x00,0x01, - 0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xa4,0xb3,0xe0,0xa4,0xbc,0x00,0x01,0x00, - 0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x91,0x08,0x10,0x04,0x01,0x07, - 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x8c,0xd4,0x18,0x53,0x04,0x01,0x00,0x52,0x04, - 0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x10,0x04,0x0b,0x00,0x0c,0x00, - 0xd3,0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x10,0x04,0x01,0xdc, - 0x01,0xe6,0x91,0x08,0x10,0x04,0x01,0xe6,0x0b,0x00,0x0c,0x00,0xd2,0x2c,0xd1,0x16, - 0x10,0x0b,0x01,0xff,0xe0,0xa4,0x95,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0x96, - 0xe0,0xa4,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa4,0x97,0xe0,0xa4,0xbc,0x00,0x01, - 0xff,0xe0,0xa4,0x9c,0xe0,0xa4,0xbc,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa4, - 0xa1,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xa2,0xe0,0xa4,0xbc,0x00,0x10,0x0b, - 0x01,0xff,0xe0,0xa4,0xab,0xe0,0xa4,0xbc,0x00,0x01,0xff,0xe0,0xa4,0xaf,0xe0,0xa4, - 0xbc,0x00,0x54,0x04,0x01,0x00,0xd3,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, - 0x0a,0x00,0x10,0x04,0x0a,0x00,0x0c,0x00,0x0c,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x10,0x00,0x0b,0x00,0x10,0x04,0x0b,0x00,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00, - 0x08,0x00,0x09,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00, - 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00, - 0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, - 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd3,0x18,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, - 0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00, - 0x91,0x08,0x10,0x04,0x01,0x07,0x07,0x00,0x01,0x00,0xcf,0x86,0xd5,0x7b,0xd4,0x42, - 0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04, - 0x00,0x00,0x01,0x00,0xd2,0x17,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04, - 0x00,0x00,0x01,0xff,0xe0,0xa7,0x87,0xe0,0xa6,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01, - 0xff,0xe0,0xa7,0x87,0xe0,0xa7,0x97,0x00,0x01,0x09,0x10,0x04,0x08,0x00,0x00,0x00, - 0xd3,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, - 0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe0,0xa6,0xa1,0xe0,0xa6,0xbc, - 0x00,0x01,0xff,0xe0,0xa6,0xa2,0xe0,0xa6,0xbc,0x00,0x10,0x04,0x00,0x00,0x01,0xff, - 0xe0,0xa6,0xaf,0xe0,0xa6,0xbc,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x01,0x00,0x11, - 0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x14,0xe6,0x00, - 0x00,0xe2,0x48,0x02,0xe1,0x4f,0x01,0xd0,0xa4,0xcf,0x86,0xd5,0x4c,0xd4,0x34,0xd3, - 0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x10,0x04,0x01,0x00,0x07, - 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01, - 0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x2e,0xd2,0x17,0xd1, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xa8,0xb2, - 0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x0b,0x01,0xff, - 0xe0,0xa8,0xb8,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00, - 0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x00,0x00,0x01,0x00,0xcf,0x86,0xd5,0x80,0xd4, - 0x34,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x51, - 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01, - 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x01, - 0x09,0x00,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x00, - 0x00,0x00,0x00,0xd2,0x25,0xd1,0x0f,0x10,0x04,0x00,0x00,0x01,0xff,0xe0,0xa8,0x96, - 0xe0,0xa8,0xbc,0x00,0x10,0x0b,0x01,0xff,0xe0,0xa8,0x97,0xe0,0xa8,0xbc,0x00,0x01, - 0xff,0xe0,0xa8,0x9c,0xe0,0xa8,0xbc,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00, - 0x10,0x0b,0x01,0xff,0xe0,0xa8,0xab,0xe0,0xa8,0xbc,0x00,0x00,0x00,0xd4,0x10,0x93, - 0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x14,0x52, - 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04,0x14,0x00,0x00, - 0x00,0x00,0x00,0xd0,0x82,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91, - 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, - 0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x01,0x00,0x10, - 0x04,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x0c,0x91, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, - 0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01, - 0x07,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x10,0x52,0x04,0x01, - 0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x01,0x09,0x00, - 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x07, - 0x00,0x07,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x0d,0x00,0x07,0x00,0x00,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x11,0x00,0x13,0x00,0x13,0x00,0xe1,0x24,0x01,0xd0,0x86,0xcf,0x86, - 0xd5,0x44,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00, - 0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x93,0x14, - 0x92,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x01,0x00, - 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x07,0x01,0x00, - 0x01,0x00,0xcf,0x86,0xd5,0x73,0xd4,0x45,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08, - 0x10,0x04,0x0a,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x0f, - 0x10,0x0b,0x01,0xff,0xe0,0xad,0x87,0xe0,0xad,0x96,0x00,0x00,0x00,0x10,0x04,0x00, - 0x00,0x01,0xff,0xe0,0xad,0x87,0xe0,0xac,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff, - 0xe0,0xad,0x87,0xe0,0xad,0x97,0x00,0x01,0x09,0x00,0x00,0xd3,0x0c,0x52,0x04,0x00, - 0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x16,0x10,0x0b,0x01, - 0xff,0xe0,0xac,0xa1,0xe0,0xac,0xbc,0x00,0x01,0xff,0xe0,0xac,0xa2,0xe0,0xac,0xbc, - 0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01, - 0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x0c,0x00,0x0c,0x00,0x00,0x00,0xd0,0xb1,0xcf, - 0x86,0xd5,0x63,0xd4,0x28,0xd3,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd3,0x1f,0xd2,0x0c,0x91, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0, - 0xae,0x92,0xe0,0xaf,0x97,0x00,0x01,0x00,0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x00,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x01,0x00,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00, - 0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x08,0x00,0x01,0x00, - 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xcf,0x86, - 0xd5,0x61,0xd4,0x45,0xd3,0x14,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x00,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08,0x10,0x04,0x01,0x00, - 0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0,0xae,0xbe,0x00,0x01,0xff,0xe0, - 0xaf,0x87,0xe0,0xae,0xbe,0x00,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xaf,0x86,0xe0, - 0xaf,0x97,0x00,0x01,0x09,0x00,0x00,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0a, - 0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0x00, - 0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x08, - 0x00,0x01,0x00,0x01,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x07,0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00, - 0x00,0x00,0x00,0xe3,0x1c,0x04,0xe2,0x1a,0x02,0xd1,0xf3,0xd0,0x76,0xcf,0x86,0xd5, - 0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01, - 0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91, - 0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01, - 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd3, - 0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x01,0x00,0x01,0x00,0xd2, - 0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0x53,0xd4,0x2f,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10, - 0x04,0x01,0x00,0x00,0x00,0x01,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x01,0xff,0xe0, - 0xb1,0x86,0xe0,0xb1,0x96,0x00,0x00,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, - 0x01,0x54,0x10,0x04,0x01,0x5b,0x00,0x00,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04, - 0x11,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01,0x00, - 0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x52,0x04,0x00,0x00, - 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0a,0x00,0xd0,0x76,0xcf,0x86, - 0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x10,0x00, - 0x01,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00, - 0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x14,0x53,0x04, - 0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00, - 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x07,0x07,0x07,0x00, - 0x01,0x00,0xcf,0x86,0xd5,0x82,0xd4,0x5e,0xd3,0x2a,0xd2,0x13,0x91,0x0f,0x10,0x0b, - 0x01,0xff,0xe0,0xb2,0xbf,0xe0,0xb3,0x95,0x00,0x01,0x00,0x01,0x00,0xd1,0x08,0x10, - 0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3, - 0x95,0x00,0xd2,0x28,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x96, - 0x00,0x00,0x00,0x10,0x0b,0x01,0xff,0xe0,0xb3,0x86,0xe0,0xb3,0x82,0x00,0x01,0xff, - 0xe0,0xb3,0x86,0xe0,0xb3,0x82,0xe0,0xb3,0x95,0x00,0x91,0x08,0x10,0x04,0x01,0x00, - 0x01,0x09,0x00,0x00,0xd3,0x14,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, - 0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00, - 0x10,0x04,0x01,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04,0x01,0x00, - 0x09,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x93,0x14,0x92,0x10,0xd1,0x08, - 0x10,0x04,0x00,0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xe1,0x06,0x01,0xd0,0x6e,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x91, - 0x08,0x10,0x04,0x13,0x00,0x10,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x01, - 0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01, - 0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, - 0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x0c,0x00,0x13,0x09,0x91,0x08,0x10,0x04,0x13,0x09,0x0a,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0x65,0xd4,0x45,0xd3,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10, - 0x04,0x0a,0x00,0x00,0x00,0x01,0x00,0xd2,0x1e,0xd1,0x08,0x10,0x04,0x01,0x00,0x00, - 0x00,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb4,0xbe,0x00,0x01,0xff,0xe0,0xb5, - 0x87,0xe0,0xb4,0xbe,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe0,0xb5,0x86,0xe0,0xb5, - 0x97,0x00,0x01,0x09,0x10,0x04,0x0c,0x00,0x12,0x00,0xd3,0x10,0x52,0x04,0x00,0x00, - 0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x01,0x00,0x52,0x04,0x12,0x00,0x51,0x04, - 0x12,0x00,0x10,0x04,0x12,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0xd2,0x08,0x11,0x04, - 0x01,0x00,0x0a,0x00,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3,0x0c,0x52,0x04, - 0x0a,0x00,0x11,0x04,0x0a,0x00,0x12,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00, - 0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x5a,0xcf,0x86,0xd5,0x34,0xd4,0x18,0x93,0x14, - 0xd2,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x04,0x00, - 0x04,0x00,0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04, - 0x04,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x54,0x04, - 0x04,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x04,0x00,0x10,0x04,0x00,0x00,0x04,0x00, - 0x04,0x00,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x04,0x00,0x00,0x00, - 0xcf,0x86,0xd5,0x77,0xd4,0x28,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00, - 0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x04,0x09, - 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x04,0x00,0xd3,0x14,0x52,0x04, - 0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x10,0x04,0x04,0x00,0x00,0x00, - 0xd2,0x13,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8a, - 0x00,0x04,0x00,0xd1,0x19,0x10,0x0b,0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0x00, - 0x04,0xff,0xe0,0xb7,0x99,0xe0,0xb7,0x8f,0xe0,0xb7,0x8a,0x00,0x10,0x0b,0x04,0xff, - 0xe0,0xb7,0x99,0xe0,0xb7,0x9f,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c,0x52,0x04,0x00, - 0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x14,0xd2,0x08,0x11,0x04,0x00, - 0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xe2, - 0x31,0x01,0xd1,0x58,0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x67,0x10,0x04, - 0x01,0x09,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x01,0x00,0xcf,0x86, - 0x95,0x18,0xd4,0x0c,0x53,0x04,0x01,0x00,0x12,0x04,0x01,0x6b,0x01,0x00,0x53,0x04, - 0x01,0x00,0x12,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd0,0x9e,0xcf,0x86,0xd5,0x54, - 0xd4,0x3c,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04, - 0x01,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x15,0x00, - 0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x15,0x00,0x10,0x04,0x01,0x00, - 0x00,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x15,0x00,0xd3,0x08,0x12,0x04, - 0x15,0x00,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00, - 0x01,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x10,0x04,0x00,0x00,0x01,0x00, - 0xd2,0x08,0x11,0x04,0x15,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x01,0x00, - 0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x76,0x10,0x04,0x15,0x09, - 0x01,0x00,0x11,0x04,0x01,0x00,0x00,0x00,0xcf,0x86,0x95,0x34,0xd4,0x20,0xd3,0x14, - 0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x01,0x00, - 0x00,0x00,0x52,0x04,0x01,0x7a,0x11,0x04,0x01,0x00,0x00,0x00,0x53,0x04,0x01,0x00, - 0xd2,0x08,0x11,0x04,0x01,0x00,0x00,0x00,0x11,0x04,0x01,0x00,0x0d,0x00,0x00,0x00, - 0xe1,0x2b,0x01,0xd0,0x3e,0xcf,0x86,0xd5,0x14,0x54,0x04,0x02,0x00,0x53,0x04,0x02, - 0x00,0x92,0x08,0x11,0x04,0x02,0xdc,0x02,0x00,0x02,0x00,0x54,0x04,0x02,0x00,0xd3, - 0x14,0x52,0x04,0x02,0x00,0xd1,0x08,0x10,0x04,0x02,0x00,0x02,0xdc,0x10,0x04,0x02, - 0x00,0x02,0xdc,0x92,0x0c,0x91,0x08,0x10,0x04,0x02,0x00,0x02,0xd8,0x02,0x00,0x02, - 0x00,0xcf,0x86,0xd5,0x73,0xd4,0x36,0xd3,0x17,0x92,0x13,0x51,0x04,0x02,0x00,0x10, - 0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x82,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x00,0x00,0x02,0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00, - 0x02,0xff,0xe0,0xbd,0x8c,0xe0,0xbe,0xb7,0x00,0x02,0x00,0xd3,0x26,0xd2,0x13,0x51, - 0x04,0x02,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x91,0xe0,0xbe,0xb7,0x00,0x02,0x00, - 0x51,0x04,0x02,0x00,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x96,0xe0,0xbe,0xb7, - 0x00,0x52,0x04,0x02,0x00,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbd,0x9b,0xe0,0xbe, - 0xb7,0x00,0x02,0x00,0x02,0x00,0xd4,0x27,0x53,0x04,0x02,0x00,0xd2,0x17,0xd1,0x0f, - 0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbd,0x80,0xe0,0xbe,0xb5,0x00,0x10,0x04,0x04, - 0x00,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0xd3,0x35,0xd2, - 0x17,0xd1,0x08,0x10,0x04,0x00,0x00,0x02,0x81,0x10,0x04,0x02,0x82,0x02,0xff,0xe0, - 0xbd,0xb1,0xe0,0xbd,0xb2,0x00,0xd1,0x0f,0x10,0x04,0x02,0x84,0x02,0xff,0xe0,0xbd, - 0xb1,0xe0,0xbd,0xb4,0x00,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xb2,0xe0,0xbe,0x80,0x00, - 0x02,0x00,0xd2,0x13,0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xb3,0xe0,0xbe,0x80, - 0x00,0x02,0x00,0x02,0x82,0x11,0x04,0x02,0x82,0x02,0x00,0xd0,0xd3,0xcf,0x86,0xd5, - 0x65,0xd4,0x27,0xd3,0x1f,0xd2,0x13,0x91,0x0f,0x10,0x04,0x02,0x82,0x02,0xff,0xe0, - 0xbd,0xb1,0xe0,0xbe,0x80,0x00,0x02,0xe6,0x91,0x08,0x10,0x04,0x02,0x09,0x02,0x00, - 0x02,0xe6,0x12,0x04,0x02,0x00,0x0c,0x00,0xd3,0x1f,0xd2,0x13,0x51,0x04,0x02,0x00, - 0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x92,0xe0,0xbe,0xb7,0x00,0x51,0x04,0x02, - 0x00,0x10,0x04,0x04,0x00,0x02,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x02, - 0x00,0x02,0x00,0x91,0x0f,0x10,0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0x9c,0xe0,0xbe, - 0xb7,0x00,0x02,0x00,0xd4,0x3d,0xd3,0x26,0xd2,0x13,0x51,0x04,0x02,0x00,0x10,0x0b, - 0x02,0xff,0xe0,0xbe,0xa1,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x51,0x04,0x02,0x00,0x10, - 0x04,0x02,0x00,0x02,0xff,0xe0,0xbe,0xa6,0xe0,0xbe,0xb7,0x00,0x52,0x04,0x02,0x00, - 0x91,0x0f,0x10,0x0b,0x02,0xff,0xe0,0xbe,0xab,0xe0,0xbe,0xb7,0x00,0x02,0x00,0x04, - 0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x02,0x00,0x02,0x00,0x02, - 0x00,0xd2,0x13,0x91,0x0f,0x10,0x04,0x04,0x00,0x02,0xff,0xe0,0xbe,0x90,0xe0,0xbe, - 0xb5,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xcf,0x86, - 0x95,0x4c,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04, - 0x04,0xdc,0x04,0x00,0x52,0x04,0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x00,0x00, - 0x10,0x04,0x0a,0x00,0x04,0x00,0xd3,0x14,0xd2,0x08,0x11,0x04,0x08,0x00,0x0a,0x00, - 0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04, - 0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, - 0xe5,0xf7,0x04,0xe4,0x79,0x03,0xe3,0x7b,0x01,0xe2,0x04,0x01,0xd1,0x7f,0xd0,0x65, - 0xcf,0x86,0x55,0x04,0x04,0x00,0xd4,0x33,0xd3,0x1f,0xd2,0x0c,0x51,0x04,0x04,0x00, - 0x10,0x04,0x0a,0x00,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x0b,0x04,0xff,0xe1,0x80, - 0xa5,0xe1,0x80,0xae,0x00,0x04,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0a,0x00,0x04, - 0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x04,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x04, - 0x00,0x10,0x04,0x04,0x00,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x04,0x00,0x04, - 0x07,0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0x09,0x10,0x04,0x0a,0x09,0x0a, - 0x00,0x0a,0x00,0xcf,0x86,0x95,0x14,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92, - 0x08,0x11,0x04,0x04,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xd0,0x2e,0xcf,0x86,0x95, - 0x28,0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a, - 0x00,0x0a,0xdc,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00,0x0b, - 0x00,0x11,0x04,0x0b,0x00,0x0a,0x00,0x01,0x00,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3, - 0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x52, - 0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x00,0x00,0x01,0x00,0x54, - 0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x06,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x06,0x00,0x08,0x00,0x10,0x04,0x08, - 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0d,0x00,0x0d,0x00,0xd1,0x3e,0xd0, - 0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x1d,0x54,0x04,0x01,0x00,0x53,0x04,0x01, - 0x00,0xd2,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, - 0x00,0x01,0xff,0x00,0x94,0x15,0x93,0x11,0x92,0x0d,0x91,0x09,0x10,0x05,0x01,0xff, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55, - 0x04,0x01,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x0b,0x00,0x0b,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54, - 0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0b,0x00,0x0b, - 0x00,0xe2,0x21,0x01,0xd1,0x6c,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10, - 0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00, - 0x04,0x00,0x04,0x00,0xcf,0x86,0x95,0x48,0xd4,0x24,0xd3,0x10,0x52,0x04,0x04,0x00, - 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0xd3,0x10,0x52,0x04, - 0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08, - 0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00, - 0xd0,0x62,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x10,0x52,0x04,0x04,0x00,0x51,0x04, - 0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00, - 0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0xd4,0x14,0x53,0x04, - 0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, - 0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04, - 0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00, - 0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x52,0x04,0x04,0x00, - 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x93,0x10,0x52,0x04,0x04,0x00, - 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x94,0x14,0x53,0x04, - 0x04,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, - 0x04,0x00,0xd1,0x9c,0xd0,0x3e,0xcf,0x86,0x95,0x38,0xd4,0x14,0x53,0x04,0x04,0x00, - 0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0xd3,0x14, - 0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x04,0x00,0x11,0x04,0x04,0x00, - 0x00,0x00,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00, - 0x04,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04, - 0x04,0x00,0x10,0x04,0x04,0x00,0x08,0x00,0x04,0x00,0x53,0x04,0x04,0x00,0xd2,0x0c, - 0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x00,0x00, - 0x0c,0xe6,0x10,0x04,0x0c,0xe6,0x08,0xe6,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x08,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x53,0x04,0x04,0x00, - 0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a, - 0xcf,0x86,0x95,0x14,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04, - 0x08,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04, - 0x04,0x00,0xd3,0x10,0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x11,0x00, - 0x00,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0xd3,0x30,0xd2,0x2a, - 0xd1,0x24,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0b,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0x04,0x00, - 0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd2,0x6c,0xd1,0x24, - 0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00, - 0x93,0x10,0x52,0x04,0x04,0x00,0x51,0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x0b,0x00, - 0x0b,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00, - 0x52,0x04,0x04,0x00,0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00, - 0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x04,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x46,0xcf,0x86,0xd5,0x28, - 0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x00, - 0x00,0x00,0x06,0x00,0x93,0x10,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04,0x06,0x09, - 0x00,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x06,0x00,0x93,0x14,0x52,0x04,0x06,0x00, - 0xd1,0x08,0x10,0x04,0x06,0x09,0x06,0x00,0x10,0x04,0x06,0x00,0x00,0x00,0x00,0x00, - 0xcf,0x86,0xd5,0x10,0x54,0x04,0x06,0x00,0x93,0x08,0x12,0x04,0x06,0x00,0x00,0x00, - 0x00,0x00,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x08,0x10,0x04, - 0x06,0x00,0x00,0x00,0x06,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00, - 0x00,0x00,0x06,0x00,0x00,0x00,0x00,0x00,0xd0,0x1b,0xcf,0x86,0x55,0x04,0x04,0x00, - 0x54,0x04,0x04,0x00,0x93,0x0d,0x52,0x04,0x04,0x00,0x11,0x05,0x04,0xff,0x00,0x04, - 0x00,0x04,0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x04,0x00,0xd3,0x10,0x92,0x0c,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x09,0x04,0x00,0x04,0x00,0x52,0x04,0x04,0x00,0x91, - 0x08,0x10,0x04,0x04,0x00,0x07,0xe6,0x00,0x00,0xd4,0x10,0x53,0x04,0x04,0x00,0x92, - 0x08,0x11,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x08,0x11, - 0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xe4,0xb7,0x03,0xe3,0x58,0x01,0xd2,0x8f,0xd1, - 0x53,0xd0,0x35,0xcf,0x86,0x95,0x2f,0xd4,0x1f,0x53,0x04,0x04,0x00,0xd2,0x0d,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x04,0xff,0x00,0x51,0x05,0x04,0xff,0x00,0x10, - 0x05,0x04,0xff,0x00,0x00,0x00,0x53,0x04,0x04,0x00,0x92,0x08,0x11,0x04,0x04,0x00, - 0x00,0x00,0x00,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04,0x00,0x54,0x04,0x04,0x00, - 0x53,0x04,0x04,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x04,0x00,0x94,0x18,0x53,0x04,0x04,0x00, - 0x92,0x10,0xd1,0x08,0x10,0x04,0x04,0x00,0x04,0xe4,0x10,0x04,0x0a,0x00,0x00,0x00, - 0x00,0x00,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x0c, - 0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd1,0x80,0xd0,0x42, - 0xcf,0x86,0xd5,0x1c,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00, - 0xd1,0x08,0x10,0x04,0x07,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0xd4,0x0c, - 0x53,0x04,0x07,0x00,0x12,0x04,0x07,0x00,0x00,0x00,0x53,0x04,0x07,0x00,0x92,0x10, - 0xd1,0x08,0x10,0x04,0x07,0x00,0x07,0xde,0x10,0x04,0x07,0xe6,0x07,0xdc,0x00,0x00, - 0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00, - 0x00,0x00,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd4,0x10,0x53,0x04,0x07,0x00, - 0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x07,0x00, - 0x91,0x08,0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x1a,0xcf,0x86, - 0x55,0x04,0x08,0x00,0x94,0x10,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00, - 0x0b,0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x95,0x28,0xd4,0x10,0x53,0x04,0x08,0x00, - 0x92,0x08,0x11,0x04,0x08,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0xd2,0x0c, - 0x51,0x04,0x08,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x08,0x00, - 0x07,0x00,0xd2,0xe4,0xd1,0x80,0xd0,0x2e,0xcf,0x86,0x95,0x28,0x54,0x04,0x08,0x00, - 0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x08,0xe6, - 0xd2,0x0c,0x91,0x08,0x10,0x04,0x08,0xdc,0x08,0x00,0x08,0x00,0x11,0x04,0x00,0x00, - 0x08,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00, - 0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0xd4,0x14, - 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00, - 0x0b,0x00,0xd3,0x10,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xe6, - 0x0b,0xe6,0x52,0x04,0x0b,0xe6,0xd1,0x08,0x10,0x04,0x0b,0xe6,0x00,0x00,0x10,0x04, - 0x00,0x00,0x0b,0xdc,0xd0,0x5e,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0b,0x00, - 0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0b,0x00,0x92,0x08, - 0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd4,0x10,0x53,0x04,0x0b,0x00,0x52,0x04, - 0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x10,0xe6,0x91,0x08, - 0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0xdc,0xd2,0x0c,0x51,0x04,0x10,0xdc,0x10,0x04, - 0x10,0xdc,0x10,0xe6,0xd1,0x08,0x10,0x04,0x10,0xe6,0x10,0xdc,0x10,0x04,0x10,0x00, - 0x00,0x00,0xcf,0x06,0x00,0x00,0xe1,0x1e,0x01,0xd0,0xaa,0xcf,0x86,0xd5,0x6e,0xd4, - 0x53,0xd3,0x17,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1, - 0xac,0x85,0xe1,0xac,0xb5,0x00,0x09,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x09,0xff, - 0xe1,0xac,0x87,0xe1,0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x89, - 0xe1,0xac,0xb5,0x00,0x09,0x00,0xd1,0x0f,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8b,0xe1, - 0xac,0xb5,0x00,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac,0x8d,0xe1,0xac,0xb5,0x00, - 0x09,0x00,0x93,0x17,0x92,0x13,0x51,0x04,0x09,0x00,0x10,0x0b,0x09,0xff,0xe1,0xac, - 0x91,0xe1,0xac,0xb5,0x00,0x09,0x00,0x09,0x00,0x09,0x00,0x54,0x04,0x09,0x00,0xd3, - 0x10,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x07,0x09,0x00,0x09,0x00,0xd2, - 0x13,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xba,0xe1,0xac, - 0xb5,0x00,0x91,0x0f,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xac,0xbc,0xe1,0xac,0xb5, - 0x00,0x09,0x00,0xcf,0x86,0xd5,0x3d,0x94,0x39,0xd3,0x31,0xd2,0x25,0xd1,0x16,0x10, - 0x0b,0x09,0xff,0xe1,0xac,0xbe,0xe1,0xac,0xb5,0x00,0x09,0xff,0xe1,0xac,0xbf,0xe1, - 0xac,0xb5,0x00,0x10,0x04,0x09,0x00,0x09,0xff,0xe1,0xad,0x82,0xe1,0xac,0xb5,0x00, - 0x91,0x08,0x10,0x04,0x09,0x09,0x09,0x00,0x09,0x00,0x12,0x04,0x09,0x00,0x00,0x00, - 0x09,0x00,0xd4,0x1c,0x53,0x04,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09,0x00,0x10,0x04, - 0x09,0x00,0x09,0xe6,0x91,0x08,0x10,0x04,0x09,0xdc,0x09,0xe6,0x09,0xe6,0xd3,0x08, - 0x12,0x04,0x09,0xe6,0x09,0x00,0x52,0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00, - 0x00,0x00,0x00,0x00,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x18,0x53,0x04, - 0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x09,0x0d,0x09,0x11,0x04, - 0x0d,0x00,0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x0d,0x00, - 0x0d,0x00,0xcf,0x86,0x55,0x04,0x0c,0x00,0xd4,0x14,0x93,0x10,0x52,0x04,0x0c,0x00, - 0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x07,0x0c,0x00,0x0c,0x00,0xd3,0x0c,0x92,0x08, - 0x11,0x04,0x0c,0x00,0x0c,0x09,0x00,0x00,0x12,0x04,0x00,0x00,0x0c,0x00,0xe3,0xb2, - 0x01,0xe2,0x09,0x01,0xd1,0x4c,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x0a,0x00,0x54,0x04, - 0x0a,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04,0x0a,0x00, - 0x0a,0x07,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00, - 0xcf,0x86,0x95,0x1c,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00, - 0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00, - 0xd0,0x3a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x14,0x00,0x54,0x04,0x14,0x00, - 0x53,0x04,0x14,0x00,0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00, - 0x91,0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x14,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x08, - 0x13,0x04,0x0d,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x0b,0xe6,0x10,0x04, - 0x0b,0xe6,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x01,0x0b,0xdc,0x0b,0xdc,0x92,0x08, - 0x11,0x04,0x0b,0xdc,0x0b,0xe6,0x0b,0xdc,0xd4,0x28,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x01,0x0b,0x01,0xd2,0x0c,0x91,0x08,0x10,0x04, - 0x0b,0x01,0x0b,0x00,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0xdc,0x0b,0x00, - 0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0d,0x00,0xd1,0x08, - 0x10,0x04,0x0d,0xe6,0x0d,0x00,0x10,0x04,0x0d,0x00,0x13,0x00,0x92,0x0c,0x51,0x04, - 0x10,0xe6,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06, - 0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x94,0x0c,0x53,0x04,0x07,0x00,0x12,0x04, - 0x07,0x00,0x08,0x00,0x08,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0xd5,0x40, - 0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x51,0x04,0x08,0xe6,0x10,0x04,0x08,0xdc,0x08,0xe6, - 0x09,0xe6,0xd2,0x0c,0x51,0x04,0x09,0xe6,0x10,0x04,0x09,0xdc,0x0a,0xe6,0xd1,0x08, - 0x10,0x04,0x0a,0xe6,0x0a,0xea,0x10,0x04,0x0a,0xd6,0x0a,0xdc,0x93,0x10,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x0a,0xca,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0x0a,0xe6,0xd4,0x14, - 0x93,0x10,0x52,0x04,0x0a,0xe6,0x51,0x04,0x0a,0xe6,0x10,0x04,0x0a,0xe6,0x10,0xe6, - 0x10,0xe6,0xd3,0x10,0x52,0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x13,0xe8, - 0x13,0xe4,0xd2,0x10,0xd1,0x08,0x10,0x04,0x13,0xe4,0x13,0xdc,0x10,0x04,0x00,0x00, - 0x12,0xe6,0xd1,0x08,0x10,0x04,0x0c,0xe9,0x0b,0xdc,0x10,0x04,0x09,0xe6,0x09,0xdc, - 0xe2,0x80,0x08,0xe1,0x48,0x04,0xe0,0x1c,0x02,0xcf,0x86,0xe5,0x11,0x01,0xd4,0x84, - 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa5,0x00,0x01,0xff, - 0x61,0xcc,0xa5,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0x87,0x00,0x01,0xff,0x62,0xcc, - 0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x42,0xcc,0xa3,0x00,0x01,0xff,0x62,0xcc, - 0xa3,0x00,0x10,0x08,0x01,0xff,0x42,0xcc,0xb1,0x00,0x01,0xff,0x62,0xcc,0xb1,0x00, - 0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x43,0xcc,0xa7,0xcc,0x81,0x00,0x01,0xff, - 0x63,0xcc,0xa7,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0x87,0x00,0x01,0xff, - 0x64,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa3,0x00,0x01,0xff, - 0x64,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xb1,0x00,0x01,0xff,0x64,0xcc, - 0xb1,0x00,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x44,0xcc,0xa7,0x00, - 0x01,0xff,0x64,0xcc,0xa7,0x00,0x10,0x08,0x01,0xff,0x44,0xcc,0xad,0x00,0x01,0xff, - 0x64,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc,0x80,0x00, - 0x01,0xff,0x65,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x84,0xcc, - 0x81,0x00,0x01,0xff,0x65,0xcc,0x84,0xcc,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x45,0xcc,0xad,0x00,0x01,0xff,0x65,0xcc,0xad,0x00,0x10,0x08,0x01,0xff, - 0x45,0xcc,0xb0,0x00,0x01,0xff,0x65,0xcc,0xb0,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff, - 0x45,0xcc,0xa7,0xcc,0x86,0x00,0x01,0xff,0x65,0xcc,0xa7,0xcc,0x86,0x00,0x10,0x08, - 0x01,0xff,0x46,0xcc,0x87,0x00,0x01,0xff,0x66,0xcc,0x87,0x00,0xd4,0x84,0xd3,0x40, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x47,0xcc,0x84,0x00,0x01,0xff,0x67,0xcc, - 0x84,0x00,0x10,0x08,0x01,0xff,0x48,0xcc,0x87,0x00,0x01,0xff,0x68,0xcc,0x87,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa3,0x00,0x01,0xff,0x68,0xcc,0xa3,0x00, - 0x10,0x08,0x01,0xff,0x48,0xcc,0x88,0x00,0x01,0xff,0x68,0xcc,0x88,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0x48,0xcc,0xa7,0x00,0x01,0xff,0x68,0xcc,0xa7,0x00, - 0x10,0x08,0x01,0xff,0x48,0xcc,0xae,0x00,0x01,0xff,0x68,0xcc,0xae,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0x49,0xcc,0xb0,0x00,0x01,0xff,0x69,0xcc,0xb0,0x00,0x10,0x0a, - 0x01,0xff,0x49,0xcc,0x88,0xcc,0x81,0x00,0x01,0xff,0x69,0xcc,0x88,0xcc,0x81,0x00, - 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0x81,0x00,0x01,0xff, - 0x6b,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x4b,0xcc,0xa3,0x00,0x01,0xff,0x6b,0xcc, - 0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4b,0xcc,0xb1,0x00,0x01,0xff,0x6b,0xcc, - 0xb1,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xa3,0x00,0x01,0xff,0x6c,0xcc,0xa3,0x00, - 0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4c,0xcc,0xa3,0xcc,0x84,0x00,0x01,0xff, - 0x6c,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x4c,0xcc,0xb1,0x00,0x01,0xff, - 0x6c,0xcc,0xb1,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4c,0xcc,0xad,0x00,0x01,0xff, - 0x6c,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x4d,0xcc,0x81,0x00,0x01,0xff,0x6d,0xcc, - 0x81,0x00,0xcf,0x86,0xe5,0x15,0x01,0xd4,0x88,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x4d,0xcc,0x87,0x00,0x01,0xff,0x6d,0xcc,0x87,0x00,0x10,0x08,0x01, - 0xff,0x4d,0xcc,0xa3,0x00,0x01,0xff,0x6d,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x4e,0xcc,0x87,0x00,0x01,0xff,0x6e,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x4e, - 0xcc,0xa3,0x00,0x01,0xff,0x6e,0xcc,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x4e,0xcc,0xb1,0x00,0x01,0xff,0x6e,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x4e, - 0xcc,0xad,0x00,0x01,0xff,0x6e,0xcc,0xad,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f, - 0xcc,0x83,0xcc,0x81,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01, - 0xff,0x4f,0xcc,0x83,0xcc,0x88,0x00,0x01,0xff,0x6f,0xcc,0x83,0xcc,0x88,0x00,0xd3, - 0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x80,0x00,0x01, - 0xff,0x6f,0xcc,0x84,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x84,0xcc,0x81, - 0x00,0x01,0xff,0x6f,0xcc,0x84,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x50, - 0xcc,0x81,0x00,0x01,0xff,0x70,0xcc,0x81,0x00,0x10,0x08,0x01,0xff,0x50,0xcc,0x87, - 0x00,0x01,0xff,0x70,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x52, - 0xcc,0x87,0x00,0x01,0xff,0x72,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x52,0xcc,0xa3, - 0x00,0x01,0xff,0x72,0xcc,0xa3,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x52,0xcc,0xa3, - 0xcc,0x84,0x00,0x01,0xff,0x72,0xcc,0xa3,0xcc,0x84,0x00,0x10,0x08,0x01,0xff,0x52, - 0xcc,0xb1,0x00,0x01,0xff,0x72,0xcc,0xb1,0x00,0xd4,0x8c,0xd3,0x48,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0x53,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x87,0x00,0x10, - 0x08,0x01,0xff,0x53,0xcc,0xa3,0x00,0x01,0xff,0x73,0xcc,0xa3,0x00,0xd1,0x14,0x10, - 0x0a,0x01,0xff,0x53,0xcc,0x81,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x81,0xcc,0x87, - 0x00,0x10,0x0a,0x01,0xff,0x53,0xcc,0x8c,0xcc,0x87,0x00,0x01,0xff,0x73,0xcc,0x8c, - 0xcc,0x87,0x00,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff,0x53,0xcc,0xa3,0xcc,0x87, - 0x00,0x01,0xff,0x73,0xcc,0xa3,0xcc,0x87,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0x87, - 0x00,0x01,0xff,0x74,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x54,0xcc,0xa3, - 0x00,0x01,0xff,0x74,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x54,0xcc,0xb1,0x00,0x01, - 0xff,0x74,0xcc,0xb1,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x54, - 0xcc,0xad,0x00,0x01,0xff,0x74,0xcc,0xad,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xa4, - 0x00,0x01,0xff,0x75,0xcc,0xa4,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x55,0xcc,0xb0, - 0x00,0x01,0xff,0x75,0xcc,0xb0,0x00,0x10,0x08,0x01,0xff,0x55,0xcc,0xad,0x00,0x01, - 0xff,0x75,0xcc,0xad,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x83, - 0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x83,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x55, - 0xcc,0x84,0xcc,0x88,0x00,0x01,0xff,0x75,0xcc,0x84,0xcc,0x88,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0x56,0xcc,0x83,0x00,0x01,0xff,0x76,0xcc,0x83,0x00,0x10,0x08,0x01, - 0xff,0x56,0xcc,0xa3,0x00,0x01,0xff,0x76,0xcc,0xa3,0x00,0xe0,0x10,0x02,0xcf,0x86, - 0xd5,0xe1,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc, - 0x80,0x00,0x01,0xff,0x77,0xcc,0x80,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x81,0x00, - 0x01,0xff,0x77,0xcc,0x81,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0x88,0x00, - 0x01,0xff,0x77,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x57,0xcc,0x87,0x00,0x01,0xff, - 0x77,0xcc,0x87,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x57,0xcc,0xa3,0x00, - 0x01,0xff,0x77,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x58,0xcc,0x87,0x00,0x01,0xff, - 0x78,0xcc,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x58,0xcc,0x88,0x00,0x01,0xff, - 0x78,0xcc,0x88,0x00,0x10,0x08,0x01,0xff,0x59,0xcc,0x87,0x00,0x01,0xff,0x79,0xcc, - 0x87,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0x82,0x00, - 0x01,0xff,0x7a,0xcc,0x82,0x00,0x10,0x08,0x01,0xff,0x5a,0xcc,0xa3,0x00,0x01,0xff, - 0x7a,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x5a,0xcc,0xb1,0x00,0x01,0xff, - 0x7a,0xcc,0xb1,0x00,0x10,0x08,0x01,0xff,0x68,0xcc,0xb1,0x00,0x01,0xff,0x74,0xcc, - 0x88,0x00,0x92,0x1d,0xd1,0x10,0x10,0x08,0x01,0xff,0x77,0xcc,0x8a,0x00,0x01,0xff, - 0x79,0xcc,0x8a,0x00,0x10,0x04,0x01,0x00,0x02,0xff,0xc5,0xbf,0xcc,0x87,0x00,0x0a, - 0x00,0xd4,0x98,0xd3,0x48,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x41,0xcc,0xa3, - 0x00,0x01,0xff,0x61,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x41,0xcc,0x89,0x00,0x01, - 0xff,0x61,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x81, - 0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82, - 0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x80,0x00,0xd2,0x28,0xd1,0x14,0x10, - 0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x82,0xcc,0x89, - 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x61,0xcc,0x82, - 0xcc,0x83,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x82,0x00,0x01, - 0xff,0x61,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x81, - 0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x81,0x00,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10, - 0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x80,0x00,0x01,0xff,0x61,0xcc,0x86,0xcc,0x80, - 0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x89,0x00,0x01,0xff,0x61,0xcc,0x86, - 0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x41,0xcc,0x86,0xcc,0x83,0x00,0x01, - 0xff,0x61,0xcc,0x86,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x41,0xcc,0xa3,0xcc,0x86, - 0x00,0x01,0xff,0x61,0xcc,0xa3,0xcc,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0x45,0xcc,0xa3,0x00,0x01,0xff,0x65,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x45, - 0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x89,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x45, - 0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82, - 0xcc,0x81,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x81,0x00,0xcf,0x86,0xe5,0x31,0x01, - 0xd4,0x90,0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x45,0xcc,0x82,0xcc, - 0x80,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0x45,0xcc, - 0x82,0xcc,0x89,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x89,0x00,0xd1,0x14,0x10,0x0a, - 0x01,0xff,0x45,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x65,0xcc,0x82,0xcc,0x83,0x00, - 0x10,0x0a,0x01,0xff,0x45,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff,0x65,0xcc,0xa3,0xcc, - 0x82,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0x49,0xcc,0x89,0x00,0x01,0xff, - 0x69,0xcc,0x89,0x00,0x10,0x08,0x01,0xff,0x49,0xcc,0xa3,0x00,0x01,0xff,0x69,0xcc, - 0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0x4f,0xcc,0xa3,0x00,0x01,0xff,0x6f,0xcc, - 0xa3,0x00,0x10,0x08,0x01,0xff,0x4f,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x89,0x00, - 0xd3,0x50,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc,0x81,0x00, - 0x01,0xff,0x6f,0xcc,0x82,0xcc,0x81,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x82,0xcc, - 0x80,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x80,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff, - 0x4f,0xcc,0x82,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x89,0x00,0x10,0x0a, - 0x01,0xff,0x4f,0xcc,0x82,0xcc,0x83,0x00,0x01,0xff,0x6f,0xcc,0x82,0xcc,0x83,0x00, - 0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0xa3,0xcc,0x82,0x00,0x01,0xff, - 0x6f,0xcc,0xa3,0xcc,0x82,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x81,0x00, - 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x81,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc, - 0x9b,0xcc,0x80,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff, - 0x4f,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x89,0x00,0xd4,0x98, - 0xd3,0x48,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc,0x83,0x00, - 0x01,0xff,0x6f,0xcc,0x9b,0xcc,0x83,0x00,0x10,0x0a,0x01,0xff,0x4f,0xcc,0x9b,0xcc, - 0xa3,0x00,0x01,0xff,0x6f,0xcc,0x9b,0xcc,0xa3,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0x55,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff,0x55,0xcc, - 0x89,0x00,0x01,0xff,0x75,0xcc,0x89,0x00,0xd2,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff, - 0x55,0xcc,0x9b,0xcc,0x81,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x81,0x00,0x10,0x0a, - 0x01,0xff,0x55,0xcc,0x9b,0xcc,0x80,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0x80,0x00, - 0xd1,0x14,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x89,0x00,0x01,0xff,0x75,0xcc, - 0x9b,0xcc,0x89,0x00,0x10,0x0a,0x01,0xff,0x55,0xcc,0x9b,0xcc,0x83,0x00,0x01,0xff, - 0x75,0xcc,0x9b,0xcc,0x83,0x00,0xd3,0x44,0xd2,0x24,0xd1,0x14,0x10,0x0a,0x01,0xff, - 0x55,0xcc,0x9b,0xcc,0xa3,0x00,0x01,0xff,0x75,0xcc,0x9b,0xcc,0xa3,0x00,0x10,0x08, - 0x01,0xff,0x59,0xcc,0x80,0x00,0x01,0xff,0x79,0xcc,0x80,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0x59,0xcc,0xa3,0x00,0x01,0xff,0x79,0xcc,0xa3,0x00,0x10,0x08,0x01,0xff, - 0x59,0xcc,0x89,0x00,0x01,0xff,0x79,0xcc,0x89,0x00,0x92,0x14,0x91,0x10,0x10,0x08, - 0x01,0xff,0x59,0xcc,0x83,0x00,0x01,0xff,0x79,0xcc,0x83,0x00,0x0a,0x00,0x0a,0x00, - 0xe1,0xc0,0x04,0xe0,0x80,0x02,0xcf,0x86,0xe5,0x2d,0x01,0xd4,0xa8,0xd3,0x54,0xd2, - 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x93,0x00,0x01,0xff,0xce,0xb1, - 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, - 0xce,0xb1,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc, - 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, - 0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82, - 0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x91,0xcc,0x93,0x00,0x01,0xff, - 0xce,0x91,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80,0x00, - 0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce, - 0x91,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x81,0x00,0x10, - 0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x91,0xcc,0x94, - 0xcd,0x82,0x00,0xd3,0x42,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc, - 0x93,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb5,0xcc, - 0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10, - 0x0b,0x01,0xff,0xce,0xb5,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb5,0xcc,0x94, - 0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x95,0xcc, - 0x93,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x95,0xcc, - 0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x94,0xcc,0x80,0x00,0x91,0x16,0x10, - 0x0b,0x01,0xff,0xce,0x95,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x95,0xcc,0x94, - 0xcc,0x81,0x00,0x00,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01, - 0xff,0xce,0xb7,0xcc,0x93,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0x00,0x10,0x0b,0x01, - 0xff,0xce,0xb7,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80, - 0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff, - 0xce,0xb7,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd, - 0x82,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0x97,0xcc,0x93,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0x00,0x10, - 0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x94, - 0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81,0x00, - 0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc, - 0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x82,0x00,0xd3,0x54,0xd2, - 0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x93,0x00,0x01,0xff,0xce,0xb9, - 0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff, - 0xce,0xb9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb9,0xcc, - 0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01, - 0xff,0xce,0xb9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9,0xcc,0x94,0xcd,0x82, - 0x00,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc,0x93,0x00,0x01,0xff, - 0xce,0x99,0xcc,0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcc,0x80,0x00, - 0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce, - 0x99,0xcc,0x93,0xcc,0x81,0x00,0x01,0xff,0xce,0x99,0xcc,0x94,0xcc,0x81,0x00,0x10, - 0x0b,0x01,0xff,0xce,0x99,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0x99,0xcc,0x94, - 0xcd,0x82,0x00,0xcf,0x86,0xe5,0x13,0x01,0xd4,0x84,0xd3,0x42,0xd2,0x28,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xce,0xbf,0xcc,0x93,0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0x00, - 0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc, - 0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0xbf,0xcc,0x93,0xcc,0x81, - 0x00,0x01,0xff,0xce,0xbf,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd2,0x28,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xce,0x9f,0xcc,0x93,0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0x00, - 0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc, - 0x94,0xcc,0x80,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xce,0x9f,0xcc,0x93,0xcc,0x81, - 0x00,0x01,0xff,0xce,0x9f,0xcc,0x94,0xcc,0x81,0x00,0x00,0x00,0xd3,0x54,0xd2,0x28, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x93,0x00,0x01,0xff,0xcf,0x85,0xcc, - 0x94,0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf, - 0x85,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x93, - 0xcc,0x81,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, - 0xcf,0x85,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x85,0xcc,0x94,0xcd,0x82,0x00, - 0xd2,0x1c,0xd1,0x0d,0x10,0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0x00,0x10, - 0x04,0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x0f,0x10,0x04, - 0x00,0x00,0x01,0xff,0xce,0xa5,0xcc,0x94,0xcc,0x81,0x00,0x10,0x04,0x00,0x00,0x01, - 0xff,0xce,0xa5,0xcc,0x94,0xcd,0x82,0x00,0xd4,0xa8,0xd3,0x54,0xd2,0x28,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xcf,0x89,0xcc,0x93,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0x00, - 0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc, - 0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x81, - 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89, - 0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0x00,0xd2,0x28, - 0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xa9,0xcc,0x93,0x00,0x01,0xff,0xce,0xa9,0xcc, - 0x94,0x00,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0x00,0x01,0xff,0xce, - 0xa9,0xcc,0x94,0xcc,0x80,0x00,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93, - 0xcc,0x81,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x81,0x00,0x10,0x0b,0x01,0xff, - 0xce,0xa9,0xcc,0x93,0xcd,0x82,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0x00, - 0xd3,0x48,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x80,0x00,0x01, - 0xff,0xce,0xb1,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb5,0xcc,0x80,0x00,0x01, - 0xff,0xce,0xb5,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb7,0xcc,0x80, - 0x00,0x01,0xff,0xce,0xb7,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcc,0x80, - 0x00,0x01,0xff,0xce,0xb9,0xcc,0x81,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff, - 0xce,0xbf,0xcc,0x80,0x00,0x01,0xff,0xce,0xbf,0xcc,0x81,0x00,0x10,0x09,0x01,0xff, - 0xcf,0x85,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85,0xcc,0x81,0x00,0x91,0x12,0x10,0x09, - 0x01,0xff,0xcf,0x89,0xcc,0x80,0x00,0x01,0xff,0xcf,0x89,0xcc,0x81,0x00,0x00,0x00, - 0xe0,0xe1,0x02,0xcf,0x86,0xe5,0x91,0x01,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16, - 0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x80,0xcd,0x85, - 0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d, - 0x01,0xff,0xce,0xb1,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc, - 0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb1,0xcc,0x93,0xcd,0x82, - 0xcd,0x85,0x00,0x01,0xff,0xce,0xb1,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30, - 0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x91,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce, - 0x91,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x80, - 0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a, - 0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce, - 0x91,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0x91,0xcc,0x93, - 0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x91,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00, - 0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcd,0x85, - 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xb7, - 0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x80,0xcd, - 0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0xb7,0xcc,0x93,0xcc,0x81,0xcd,0x85, - 0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff, - 0xce,0xb7,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcc,0x94,0xcd, - 0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16,0x10,0x0b,0x01,0xff,0xce,0x97,0xcc,0x93, - 0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff, - 0xce,0x97,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc, - 0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff,0xce,0x97,0xcc,0x93,0xcc,0x81, - 0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc,0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d, - 0x01,0xff,0xce,0x97,0xcc,0x93,0xcd,0x82,0xcd,0x85,0x00,0x01,0xff,0xce,0x97,0xcc, - 0x94,0xcd,0x82,0xcd,0x85,0x00,0xd4,0xc8,0xd3,0x64,0xd2,0x30,0xd1,0x16,0x10,0x0b, - 0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd, - 0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcc,0x80,0xcd,0x85,0x00,0x01, - 0xff,0xcf,0x89,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d,0x01,0xff, - 0xcf,0x89,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcc, - 0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xcf,0x89,0xcc,0x93,0xcd,0x82,0xcd,0x85, - 0x00,0x01,0xff,0xcf,0x89,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x30,0xd1,0x16, - 0x10,0x0b,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc, - 0x94,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x80,0xcd,0x85, - 0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcc,0x80,0xcd,0x85,0x00,0xd1,0x1a,0x10,0x0d, - 0x01,0xff,0xce,0xa9,0xcc,0x93,0xcc,0x81,0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc, - 0x94,0xcc,0x81,0xcd,0x85,0x00,0x10,0x0d,0x01,0xff,0xce,0xa9,0xcc,0x93,0xcd,0x82, - 0xcd,0x85,0x00,0x01,0xff,0xce,0xa9,0xcc,0x94,0xcd,0x82,0xcd,0x85,0x00,0xd3,0x49, - 0xd2,0x26,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0xb1,0xcc,0x86,0x00,0x01,0xff,0xce, - 0xb1,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x80,0xcd,0x85,0x00,0x01, - 0xff,0xce,0xb1,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xce,0xb1,0xcc,0x81, - 0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb1,0xcd,0x82,0x00,0x01,0xff, - 0xce,0xb1,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, - 0x91,0xcc,0x86,0x00,0x01,0xff,0xce,0x91,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce, - 0x91,0xcc,0x80,0x00,0x01,0xff,0xce,0x91,0xcc,0x81,0x00,0xd1,0x0d,0x10,0x09,0x01, - 0xff,0xce,0x91,0xcd,0x85,0x00,0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xb9,0x00,0x01, - 0x00,0xcf,0x86,0xe5,0x16,0x01,0xd4,0x8f,0xd3,0x44,0xd2,0x21,0xd1,0x0d,0x10,0x04, - 0x01,0x00,0x01,0xff,0xc2,0xa8,0xcd,0x82,0x00,0x10,0x0b,0x01,0xff,0xce,0xb7,0xcc, - 0x80,0xcd,0x85,0x00,0x01,0xff,0xce,0xb7,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01, - 0xff,0xce,0xb7,0xcc,0x81,0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb7, - 0xcd,0x82,0x00,0x01,0xff,0xce,0xb7,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12, - 0x10,0x09,0x01,0xff,0xce,0x95,0xcc,0x80,0x00,0x01,0xff,0xce,0x95,0xcc,0x81,0x00, - 0x10,0x09,0x01,0xff,0xce,0x97,0xcc,0x80,0x00,0x01,0xff,0xce,0x97,0xcc,0x81,0x00, - 0xd1,0x13,0x10,0x09,0x01,0xff,0xce,0x97,0xcd,0x85,0x00,0x01,0xff,0xe1,0xbe,0xbf, - 0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbe,0xbf,0xcc,0x81,0x00,0x01,0xff,0xe1, - 0xbe,0xbf,0xcd,0x82,0x00,0xd3,0x40,0xd2,0x28,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, - 0xb9,0xcc,0x86,0x00,0x01,0xff,0xce,0xb9,0xcc,0x84,0x00,0x10,0x0b,0x01,0xff,0xce, - 0xb9,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xce,0xb9,0xcc,0x88,0xcc,0x81,0x00,0x51, - 0x04,0x00,0x00,0x10,0x09,0x01,0xff,0xce,0xb9,0xcd,0x82,0x00,0x01,0xff,0xce,0xb9, - 0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce,0x99,0xcc, - 0x86,0x00,0x01,0xff,0xce,0x99,0xcc,0x84,0x00,0x10,0x09,0x01,0xff,0xce,0x99,0xcc, - 0x80,0x00,0x01,0xff,0xce,0x99,0xcc,0x81,0x00,0xd1,0x0e,0x10,0x04,0x00,0x00,0x01, - 0xff,0xe1,0xbf,0xbe,0xcc,0x80,0x00,0x10,0x0a,0x01,0xff,0xe1,0xbf,0xbe,0xcc,0x81, - 0x00,0x01,0xff,0xe1,0xbf,0xbe,0xcd,0x82,0x00,0xd4,0x93,0xd3,0x4e,0xd2,0x28,0xd1, - 0x12,0x10,0x09,0x01,0xff,0xcf,0x85,0xcc,0x86,0x00,0x01,0xff,0xcf,0x85,0xcc,0x84, - 0x00,0x10,0x0b,0x01,0xff,0xcf,0x85,0xcc,0x88,0xcc,0x80,0x00,0x01,0xff,0xcf,0x85, - 0xcc,0x88,0xcc,0x81,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xcf,0x81,0xcc,0x93,0x00, - 0x01,0xff,0xcf,0x81,0xcc,0x94,0x00,0x10,0x09,0x01,0xff,0xcf,0x85,0xcd,0x82,0x00, - 0x01,0xff,0xcf,0x85,0xcc,0x88,0xcd,0x82,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01, - 0xff,0xce,0xa5,0xcc,0x86,0x00,0x01,0xff,0xce,0xa5,0xcc,0x84,0x00,0x10,0x09,0x01, - 0xff,0xce,0xa5,0xcc,0x80,0x00,0x01,0xff,0xce,0xa5,0xcc,0x81,0x00,0xd1,0x12,0x10, - 0x09,0x01,0xff,0xce,0xa1,0xcc,0x94,0x00,0x01,0xff,0xc2,0xa8,0xcc,0x80,0x00,0x10, - 0x09,0x01,0xff,0xc2,0xa8,0xcc,0x81,0x00,0x01,0xff,0x60,0x00,0xd3,0x3b,0xd2,0x18, - 0x51,0x04,0x00,0x00,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x80,0xcd,0x85,0x00,0x01, - 0xff,0xcf,0x89,0xcd,0x85,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xcf,0x89,0xcc,0x81, - 0xcd,0x85,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xcf,0x89,0xcd,0x82,0x00,0x01,0xff, - 0xcf,0x89,0xcd,0x82,0xcd,0x85,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xce, - 0x9f,0xcc,0x80,0x00,0x01,0xff,0xce,0x9f,0xcc,0x81,0x00,0x10,0x09,0x01,0xff,0xce, - 0xa9,0xcc,0x80,0x00,0x01,0xff,0xce,0xa9,0xcc,0x81,0x00,0xd1,0x10,0x10,0x09,0x01, - 0xff,0xce,0xa9,0xcd,0x85,0x00,0x01,0xff,0xc2,0xb4,0x00,0x10,0x04,0x01,0x00,0x00, - 0x00,0xe0,0x7e,0x0c,0xcf,0x86,0xe5,0xbb,0x08,0xe4,0x14,0x06,0xe3,0xf7,0x02,0xe2, - 0xbd,0x01,0xd1,0xd0,0xd0,0x4f,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0xd3,0x18,0x92,0x14, - 0x91,0x10,0x10,0x08,0x01,0xff,0xe2,0x80,0x82,0x00,0x01,0xff,0xe2,0x80,0x83,0x00, - 0x01,0x00,0x01,0x00,0x92,0x0d,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff, - 0x00,0x01,0xff,0x00,0x01,0x00,0x94,0x1b,0x53,0x04,0x01,0x00,0xd2,0x09,0x11,0x04, - 0x01,0x00,0x01,0xff,0x00,0x51,0x05,0x01,0xff,0x00,0x10,0x05,0x01,0xff,0x00,0x04, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0x48,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x01,0x00,0x51, - 0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x52,0x04,0x04,0x00,0x11,0x04,0x04, - 0x00,0x06,0x00,0xd3,0x1c,0xd2,0x0c,0x51,0x04,0x06,0x00,0x10,0x04,0x06,0x00,0x07, - 0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0x52, - 0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x06,0x00,0xd4,0x23,0xd3, - 0x14,0x52,0x05,0x06,0xff,0x00,0x91,0x0a,0x10,0x05,0x0a,0xff,0x00,0x00,0xff,0x00, - 0x0f,0xff,0x00,0x92,0x0a,0x11,0x05,0x0f,0xff,0x00,0x01,0xff,0x00,0x01,0xff,0x00, - 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x06,0x00,0x00,0x00,0x01,0x00, - 0x01,0x00,0xd0,0x7e,0xcf,0x86,0xd5,0x34,0xd4,0x14,0x53,0x04,0x01,0x00,0x52,0x04, - 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0xd3,0x10,0x52,0x04, - 0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0c,0x00,0x0c,0x00,0x52,0x04,0x0c,0x00, - 0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00, - 0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x02,0x00,0x91,0x08,0x10,0x04, - 0x03,0x00,0x04,0x00,0x04,0x00,0xd3,0x10,0xd2,0x08,0x11,0x04,0x06,0x00,0x08,0x00, - 0x11,0x04,0x08,0x00,0x0b,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00, - 0x10,0x04,0x0e,0x00,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x11,0x00,0x13,0x00, - 0xcf,0x86,0xd5,0x28,0x54,0x04,0x00,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x01,0xe6, - 0x01,0x01,0x01,0xe6,0xd2,0x0c,0x51,0x04,0x01,0x01,0x10,0x04,0x01,0x01,0x01,0xe6, - 0x91,0x08,0x10,0x04,0x01,0xe6,0x01,0x00,0x01,0x00,0xd4,0x30,0xd3,0x1c,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x01,0x00,0x01,0xe6,0x04,0x00,0xd1,0x08,0x10,0x04,0x06,0x00, - 0x06,0x01,0x10,0x04,0x06,0x01,0x06,0xe6,0x92,0x10,0xd1,0x08,0x10,0x04,0x06,0xdc, - 0x06,0xe6,0x10,0x04,0x06,0x01,0x08,0x01,0x09,0xdc,0x93,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0a,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x81,0xd0,0x4f, - 0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x29,0xd3,0x13,0x52,0x04,0x01,0x00,0x51,0x04, - 0x01,0x00,0x10,0x07,0x01,0xff,0xce,0xa9,0x00,0x01,0x00,0x92,0x12,0x51,0x04,0x01, - 0x00,0x10,0x06,0x01,0xff,0x4b,0x00,0x01,0xff,0x41,0xcc,0x8a,0x00,0x01,0x00,0x53, - 0x04,0x01,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x04, - 0x00,0x07,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0x95, - 0x2c,0xd4,0x18,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0xd1,0x08,0x10,0x04,0x08, - 0x00,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b, - 0x00,0x10,0x04,0x0b,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x68,0xcf, - 0x86,0xd5,0x48,0xd4,0x28,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x11,0x00,0x00,0x00,0x53,0x04,0x01,0x00,0x92, - 0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x90,0xcc,0xb8,0x00,0x01, - 0xff,0xe2,0x86,0x92,0xcc,0xb8,0x00,0x01,0x00,0x94,0x1a,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x86,0x94,0xcc,0xb8, - 0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x2e,0x94,0x2a,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0xd1,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x87,0x90,0xcc,0xb8, - 0x00,0x10,0x0a,0x01,0xff,0xe2,0x87,0x94,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x87,0x92, - 0xcc,0xb8,0x00,0x01,0x00,0xd4,0x14,0x53,0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x04,0x00,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x06, - 0x00,0x06,0x00,0xe2,0x38,0x02,0xe1,0x3f,0x01,0xd0,0x68,0xcf,0x86,0xd5,0x3e,0x94, - 0x3a,0xd3,0x16,0x52,0x04,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0x83, - 0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0xd2,0x12,0x91,0x0e,0x10,0x04,0x01,0x00,0x01, - 0xff,0xe2,0x88,0x88,0xcc,0xb8,0x00,0x01,0x00,0x91,0x0e,0x10,0x0a,0x01,0xff,0xe2, - 0x88,0x8b,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x24,0x93,0x20,0x52, - 0x04,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa3,0xcc,0xb8,0x00,0x01, - 0x00,0x10,0x0a,0x01,0xff,0xe2,0x88,0xa5,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0xcf,0x86,0xd5,0x48,0x94,0x44,0xd3,0x2e,0xd2,0x12,0x91,0x0e,0x10,0x04,0x01, - 0x00,0x01,0xff,0xe2,0x88,0xbc,0xcc,0xb8,0x00,0x01,0x00,0xd1,0x0e,0x10,0x0a,0x01, - 0xff,0xe2,0x89,0x83,0xcc,0xb8,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe2, - 0x89,0x85,0xcc,0xb8,0x00,0x92,0x12,0x91,0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2, - 0x89,0x88,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x40,0xd3,0x1e,0x92, - 0x1a,0xd1,0x0c,0x10,0x08,0x01,0xff,0x3d,0xcc,0xb8,0x00,0x01,0x00,0x10,0x0a,0x01, - 0xff,0xe2,0x89,0xa1,0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1, - 0x0e,0x10,0x04,0x01,0x00,0x01,0xff,0xe2,0x89,0x8d,0xcc,0xb8,0x00,0x10,0x08,0x01, - 0xff,0x3c,0xcc,0xb8,0x00,0x01,0xff,0x3e,0xcc,0xb8,0x00,0xd3,0x30,0xd2,0x18,0x91, - 0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xa4,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xa5, - 0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xb2,0xcc,0xb8, - 0x00,0x01,0xff,0xe2,0x89,0xb3,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18,0x91,0x14,0x10, - 0x0a,0x01,0xff,0xe2,0x89,0xb6,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xb7,0xcc,0xb8, - 0x00,0x01,0x00,0x01,0x00,0xd0,0x86,0xcf,0x86,0xd5,0x50,0x94,0x4c,0xd3,0x30,0xd2, - 0x18,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xba,0xcc,0xb8,0x00,0x01,0xff,0xe2, - 0x89,0xbb,0xcc,0xb8,0x00,0x01,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x82, - 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x83,0xcc,0xb8,0x00,0x01,0x00,0x92,0x18,0x91, - 0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0x86,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x87, - 0xcc,0xb8,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x30,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa2,0xcc,0xb8,0x00,0x01, - 0xff,0xe2,0x8a,0xa8,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xa9,0xcc,0xb8, - 0x00,0x01,0xff,0xe2,0x8a,0xab,0xcc,0xb8,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01, - 0x00,0xd4,0x5c,0xd3,0x2c,0x92,0x28,0xd1,0x14,0x10,0x0a,0x01,0xff,0xe2,0x89,0xbc, - 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x89,0xbd,0xcc,0xb8,0x00,0x10,0x0a,0x01,0xff,0xe2, - 0x8a,0x91,0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0x92,0xcc,0xb8,0x00,0x01,0x00,0xd2, - 0x18,0x51,0x04,0x01,0x00,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb2,0xcc,0xb8,0x00,0x01, - 0xff,0xe2,0x8a,0xb3,0xcc,0xb8,0x00,0x91,0x14,0x10,0x0a,0x01,0xff,0xe2,0x8a,0xb4, - 0xcc,0xb8,0x00,0x01,0xff,0xe2,0x8a,0xb5,0xcc,0xb8,0x00,0x01,0x00,0x93,0x0c,0x92, - 0x08,0x11,0x04,0x01,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xd1,0x64,0xd0,0x3e,0xcf, - 0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01,0x00,0x04, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x94,0x20,0x53,0x04,0x01,0x00,0x92, - 0x18,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x80,0x88,0x00,0x10,0x08,0x01, - 0xff,0xe3,0x80,0x89,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01, - 0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00,0x04,0x00,0xd0, - 0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51, - 0x04,0x04,0x00,0x10,0x04,0x04,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5, - 0x2c,0xd4,0x14,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00,0x10, - 0x04,0x06,0x00,0x07,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x08, - 0x00,0x08,0x00,0x08,0x00,0x12,0x04,0x08,0x00,0x09,0x00,0xd4,0x14,0x53,0x04,0x09, - 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xd3, - 0x08,0x12,0x04,0x0c,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10, - 0x00,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0xd3,0xa6,0xd2, - 0x74,0xd1,0x40,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x18,0x93,0x14,0x52, - 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x04,0x00,0x10,0x04,0x04,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x92, - 0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01, - 0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x14,0x53, - 0x04,0x01,0x00,0x92,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x06, - 0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x06, - 0x00,0x07,0x00,0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54, - 0x04,0x01,0x00,0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x06,0x00,0x06, - 0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x13,0x04,0x04, - 0x00,0x06,0x00,0xd2,0xdc,0xd1,0x48,0xd0,0x26,0xcf,0x86,0x95,0x20,0x54,0x04,0x01, - 0x00,0xd3,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x07,0x00,0x06,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x08,0x00,0x04,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55, - 0x04,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x04,0x00,0x06, - 0x00,0x06,0x00,0x52,0x04,0x06,0x00,0x11,0x04,0x06,0x00,0x08,0x00,0xd0,0x5e,0xcf, - 0x86,0xd5,0x2c,0xd4,0x10,0x53,0x04,0x06,0x00,0x92,0x08,0x11,0x04,0x06,0x00,0x07, - 0x00,0x07,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x52, - 0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x08,0x00,0x0a,0x00,0x0b,0x00,0xd4,0x10,0x93, - 0x0c,0x92,0x08,0x11,0x04,0x07,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd3,0x10,0x92, - 0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x52,0x04,0x0a, - 0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x1c,0x94, - 0x18,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b, - 0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0b,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51, - 0x04,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0c,0x00,0x0b,0x00,0x0b,0x00,0xd1, - 0xa8,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x10,0x00,0x01,0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x01, - 0x00,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00,0x01,0x00,0x01,0x00,0x94,0x14,0x53, - 0x04,0x01,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x18,0x53,0x04,0x01,0x00,0x52,0x04,0x01, - 0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x01,0x00,0x10,0x04,0x0c,0x00,0x01,0x00,0xd3, - 0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x0c,0x00,0x51,0x04,0x0c, - 0x00,0x10,0x04,0x01,0x00,0x0b,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x0c,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x06,0x00,0x93,0x0c,0x52,0x04,0x06,0x00,0x11, - 0x04,0x06,0x00,0x01,0x00,0x01,0x00,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01, - 0x00,0x93,0x10,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x0c,0x00,0x0c, - 0x00,0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, - 0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10, - 0x04,0x01,0x00,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0x94,0x28,0xd3,0x10,0x52,0x04,0x08, - 0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0xd2,0x0c,0x51,0x04,0x09, - 0x00,0x10,0x04,0x09,0x00,0x0d,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x0d,0x00,0x0c, - 0x00,0x06,0x00,0x94,0x0c,0x53,0x04,0x06,0x00,0x12,0x04,0x06,0x00,0x0a,0x00,0x06, - 0x00,0xe4,0x39,0x01,0xd3,0x0c,0xd2,0x06,0xcf,0x06,0x04,0x00,0xcf,0x06,0x06,0x00, - 0xd2,0x30,0xd1,0x06,0xcf,0x06,0x06,0x00,0xd0,0x06,0xcf,0x06,0x06,0x00,0xcf,0x86, - 0x95,0x1e,0x54,0x04,0x06,0x00,0x53,0x04,0x06,0x00,0x52,0x04,0x06,0x00,0x91,0x0e, - 0x10,0x0a,0x06,0xff,0xe2,0xab,0x9d,0xcc,0xb8,0x00,0x06,0x00,0x06,0x00,0x06,0x00, - 0xd1,0x80,0xd0,0x3a,0xcf,0x86,0xd5,0x28,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04, - 0x07,0x00,0x11,0x04,0x07,0x00,0x08,0x00,0xd3,0x08,0x12,0x04,0x08,0x00,0x09,0x00, - 0x92,0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x94,0x0c, - 0x93,0x08,0x12,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x30, - 0xd4,0x14,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, - 0x10,0x00,0x10,0x00,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00, - 0x0b,0x00,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x10,0x00,0x10,0x00,0x54,0x04, - 0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x10,0x00, - 0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00, - 0x11,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, - 0xd2,0x08,0x11,0x04,0x10,0x00,0x14,0x00,0x91,0x08,0x10,0x04,0x14,0x00,0x10,0x00, - 0x10,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x10,0x00,0x15,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, - 0x10,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd4,0x0c,0x53,0x04, - 0x14,0x00,0x12,0x04,0x14,0x00,0x11,0x00,0x53,0x04,0x14,0x00,0x52,0x04,0x14,0x00, - 0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0xe3,0xb9,0x01,0xd2,0xac,0xd1, - 0x68,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x08,0x00,0x94,0x14,0x53,0x04,0x08,0x00,0x52, - 0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x08,0x00,0xcf, - 0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x08,0x00,0x51, - 0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x09,0x00,0x52, - 0x04,0x09,0x00,0x91,0x08,0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0xd3,0x10,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x0b,0x00,0x0a,0x00,0x0a,0x00,0x09,0x00,0x52,0x04,0x0a, - 0x00,0x11,0x04,0x0a,0x00,0x0b,0x00,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0x55, - 0x04,0x08,0x00,0xd4,0x1c,0x53,0x04,0x08,0x00,0xd2,0x0c,0x51,0x04,0x08,0x00,0x10, - 0x04,0x08,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd3, - 0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0d,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x08,0x00,0x08,0x00,0x08,0x00,0xd1,0x6c,0xd0,0x2a,0xcf,0x86,0x55, - 0x04,0x08,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10, - 0x04,0x00,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d, - 0x00,0x00,0x00,0x08,0x00,0xcf,0x86,0x55,0x04,0x08,0x00,0xd4,0x1c,0xd3,0x0c,0x52, - 0x04,0x08,0x00,0x11,0x04,0x08,0x00,0x0d,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00, - 0x00,0x10,0x04,0x00,0x00,0x08,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10, - 0x04,0x00,0x00,0x0c,0x09,0xd0,0x5a,0xcf,0x86,0xd5,0x18,0x54,0x04,0x08,0x00,0x93, - 0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0x00, - 0x00,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, - 0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, - 0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, - 0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00,0x00,0xcf, - 0x86,0x95,0x40,0xd4,0x20,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10, - 0x04,0x08,0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, - 0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08, - 0x00,0x00,0x00,0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x00, - 0x00,0x0a,0xe6,0xd2,0x9c,0xd1,0x68,0xd0,0x32,0xcf,0x86,0xd5,0x14,0x54,0x04,0x08, - 0x00,0x53,0x04,0x08,0x00,0x52,0x04,0x0a,0x00,0x11,0x04,0x08,0x00,0x0a,0x00,0x54, - 0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0a,0x00,0x0b,0x00,0x0d, - 0x00,0x0d,0x00,0x12,0x04,0x0d,0x00,0x10,0x00,0xcf,0x86,0x95,0x30,0x94,0x2c,0xd3, - 0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x12,0x00,0x91,0x08,0x10, - 0x04,0x12,0x00,0x13,0x00,0x13,0x00,0xd2,0x08,0x11,0x04,0x13,0x00,0x14,0x00,0x51, - 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x15,0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf, - 0x86,0x95,0x18,0x54,0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51,0x04,0x04, - 0x00,0x10,0x04,0x00,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86,0x55,0x04,0x04, - 0x00,0x54,0x04,0x04,0x00,0x93,0x08,0x12,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0xd1, - 0x06,0xcf,0x06,0x04,0x00,0xd0,0x06,0xcf,0x06,0x04,0x00,0xcf,0x86,0xd5,0x14,0x54, - 0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04,0x00,0x00,0x00,0x00, - 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x04,0x00,0x12,0x04,0x04,0x00,0x00,0x00,0xcf, - 0x86,0xe5,0xa6,0x05,0xe4,0x9f,0x05,0xe3,0x96,0x04,0xe2,0xe4,0x03,0xe1,0xc0,0x01, - 0xd0,0x3e,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x1c,0x53,0x04,0x01,0x00,0xd2,0x0c, - 0x51,0x04,0x01,0x00,0x10,0x04,0x01,0xda,0x01,0xe4,0x91,0x08,0x10,0x04,0x01,0xe8, - 0x01,0xde,0x01,0xe0,0x53,0x04,0x01,0x00,0xd2,0x0c,0x51,0x04,0x04,0x00,0x10,0x04, - 0x04,0x00,0x06,0x00,0x51,0x04,0x06,0x00,0x10,0x04,0x04,0x00,0x01,0x00,0xcf,0x86, - 0xd5,0xaa,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81, - 0x8b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x8d,0xe3,0x82, - 0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81, - 0x8f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x91,0xe3,0x82, - 0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x93,0xe3,0x82,0x99, - 0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x95,0xe3,0x82,0x99,0x00,0x01,0x00, - 0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x97,0xe3,0x82,0x99,0x00,0x01, - 0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0x99,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f, - 0x10,0x0b,0x01,0xff,0xe3,0x81,0x9b,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01, - 0xff,0xe3,0x81,0x9d,0xe3,0x82,0x99,0x00,0x01,0x00,0xd4,0x53,0xd3,0x3c,0xd2,0x1e, - 0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0x9f,0xe3,0x82,0x99,0x00,0x01,0x00,0x10, - 0x0b,0x01,0xff,0xe3,0x81,0xa1,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x04, - 0x01,0x00,0x01,0xff,0xe3,0x81,0xa4,0xe3,0x82,0x99,0x00,0x10,0x04,0x01,0x00,0x01, - 0xff,0xe3,0x81,0xa6,0xe3,0x82,0x99,0x00,0x92,0x13,0x91,0x0f,0x10,0x04,0x01,0x00, - 0x01,0xff,0xe3,0x81,0xa8,0xe3,0x82,0x99,0x00,0x01,0x00,0x01,0x00,0xd3,0x4a,0xd2, - 0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xaf,0xe3,0x82,0x99,0x00,0x01,0xff, - 0xe3,0x81,0xaf,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x81,0xb2, - 0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb2,0xe3,0x82,0x9a, - 0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb5,0xe3,0x82,0x99,0x00,0x01,0xff, - 0xe3,0x81,0xb5,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01, - 0xff,0xe3,0x81,0xb8,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01,0xff,0xe3,0x81,0xb8,0xe3, - 0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82, - 0x99,0x00,0x01,0xff,0xe3,0x81,0xbb,0xe3,0x82,0x9a,0x00,0x01,0x00,0xd0,0xee,0xcf, - 0x86,0xd5,0x42,0x54,0x04,0x01,0x00,0xd3,0x1b,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10, - 0x0b,0x01,0xff,0xe3,0x81,0x86,0xe3,0x82,0x99,0x00,0x06,0x00,0x10,0x04,0x06,0x00, - 0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x01,0x08,0x10,0x04,0x01,0x08, - 0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0x9d,0xe3,0x82,0x99, - 0x00,0x06,0x00,0xd4,0x32,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x01, - 0x00,0x01,0x00,0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, - 0x82,0xab,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xad,0xe3, - 0x82,0x99,0x00,0x01,0x00,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, - 0x82,0xaf,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb1,0xe3, - 0x82,0x99,0x00,0x01,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb3,0xe3,0x82, - 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb5,0xe3,0x82,0x99,0x00,0x01, - 0x00,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb7,0xe3,0x82,0x99,0x00, - 0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x82,0xb9,0xe3,0x82,0x99,0x00,0x01,0x00,0xd1, - 0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbb,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x0b, - 0x01,0xff,0xe3,0x82,0xbd,0xe3,0x82,0x99,0x00,0x01,0x00,0xcf,0x86,0xd5,0xd5,0xd4, - 0x53,0xd3,0x3c,0xd2,0x1e,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3,0x82,0xbf,0xe3,0x82, - 0x99,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x81,0xe3,0x82,0x99,0x00,0x01, - 0x00,0xd1,0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x84,0xe3,0x82,0x99,0x00, - 0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x86,0xe3,0x82,0x99,0x00,0x92,0x13,0x91, - 0x0f,0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x88,0xe3,0x82,0x99,0x00,0x01,0x00, - 0x01,0x00,0xd3,0x4a,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff,0xe3,0x83,0x8f,0xe3, - 0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x8f,0xe3,0x82,0x9a,0x00,0x10,0x04,0x01,0x00, - 0x01,0xff,0xe3,0x83,0x92,0xe3,0x82,0x99,0x00,0xd1,0x0f,0x10,0x0b,0x01,0xff,0xe3, - 0x83,0x92,0xe3,0x82,0x9a,0x00,0x01,0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0x95,0xe3, - 0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x95,0xe3,0x82,0x9a,0x00,0xd2,0x1e,0xd1,0x0f, - 0x10,0x04,0x01,0x00,0x01,0xff,0xe3,0x83,0x98,0xe3,0x82,0x99,0x00,0x10,0x0b,0x01, - 0xff,0xe3,0x83,0x98,0xe3,0x82,0x9a,0x00,0x01,0x00,0x91,0x16,0x10,0x0b,0x01,0xff, - 0xe3,0x83,0x9b,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0x9b,0xe3,0x82,0x9a,0x00, - 0x01,0x00,0x54,0x04,0x01,0x00,0xd3,0x22,0x52,0x04,0x01,0x00,0xd1,0x0f,0x10,0x0b, - 0x01,0xff,0xe3,0x82,0xa6,0xe3,0x82,0x99,0x00,0x01,0x00,0x10,0x04,0x01,0x00,0x01, - 0xff,0xe3,0x83,0xaf,0xe3,0x82,0x99,0x00,0xd2,0x25,0xd1,0x16,0x10,0x0b,0x01,0xff, - 0xe3,0x83,0xb0,0xe3,0x82,0x99,0x00,0x01,0xff,0xe3,0x83,0xb1,0xe3,0x82,0x99,0x00, - 0x10,0x0b,0x01,0xff,0xe3,0x83,0xb2,0xe3,0x82,0x99,0x00,0x01,0x00,0x51,0x04,0x01, - 0x00,0x10,0x0b,0x01,0xff,0xe3,0x83,0xbd,0xe3,0x82,0x99,0x00,0x06,0x00,0xd1,0x65, - 0xd0,0x46,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x00,0x00,0x91,0x08, - 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd4,0x18,0x53,0x04, - 0x01,0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x0a,0x00,0x10,0x04, - 0x13,0x00,0x14,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x94,0x15,0x93,0x11, - 0x52,0x04,0x01,0x00,0x91,0x09,0x10,0x05,0x01,0xff,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0x01,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x54, - 0x04,0x04,0x00,0x53,0x04,0x04,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c, - 0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x08,0x00,0x0a,0x00,0x94, - 0x0c,0x93,0x08,0x12,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x06,0x00,0xd2,0xa4,0xd1, - 0x5c,0xd0,0x22,0xcf,0x86,0x95,0x1c,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52, - 0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x07,0x00,0x10,0x04,0x07,0x00,0x00, - 0x00,0x01,0x00,0xcf,0x86,0xd5,0x20,0xd4,0x0c,0x93,0x08,0x12,0x04,0x01,0x00,0x0b, - 0x00,0x0b,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00,0x06,0x00,0x06, - 0x00,0x06,0x00,0x06,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01, - 0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x08,0x00,0x01,0x00,0xd0,0x1e,0xcf,0x86,0x55, - 0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x01, - 0x00,0x06,0x00,0x06,0x00,0x06,0x00,0x06,0x00,0xcf,0x86,0xd5,0x10,0x94,0x0c,0x53, - 0x04,0x01,0x00,0x12,0x04,0x01,0x00,0x07,0x00,0x01,0x00,0x54,0x04,0x01,0x00,0x53, - 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x16, - 0x00,0xd1,0x30,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54, - 0x04,0x01,0x00,0xd3,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x01,0x00,0x01, - 0x00,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x01,0x00,0x53, - 0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x07,0x00,0x54,0x04,0x01, - 0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x07,0x00,0xcf,0x06,0x04,0x00,0xcf,0x06,0x04,0x00,0xd1,0x48,0xd0,0x40,0xcf, - 0x86,0xd5,0x06,0xcf,0x06,0x04,0x00,0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x2c,0xd2, - 0x06,0xcf,0x06,0x04,0x00,0xd1,0x06,0xcf,0x06,0x04,0x00,0xd0,0x1a,0xcf,0x86,0x55, - 0x04,0x04,0x00,0x54,0x04,0x04,0x00,0x93,0x0c,0x52,0x04,0x04,0x00,0x11,0x04,0x04, - 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x07,0x00,0xcf,0x06,0x01,0x00,0xcf,0x86,0xcf, - 0x06,0x01,0x00,0xcf,0x86,0xcf,0x06,0x01,0x00,0xe2,0x71,0x05,0xd1,0x8c,0xd0,0x08, - 0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00,0xd4,0x06, - 0xcf,0x06,0x01,0x00,0xd3,0x06,0xcf,0x06,0x01,0x00,0xd2,0x06,0xcf,0x06,0x01,0x00, - 0xd1,0x06,0xcf,0x06,0x01,0x00,0xd0,0x22,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x10, - 0x93,0x0c,0x52,0x04,0x01,0x00,0x11,0x04,0x01,0x00,0x08,0x00,0x08,0x00,0x53,0x04, - 0x08,0x00,0x12,0x04,0x08,0x00,0x0a,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0xd3,0x08, - 0x12,0x04,0x0a,0x00,0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0d,0x00, - 0x11,0x00,0x11,0x00,0x93,0x0c,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x13,0x00, - 0x13,0x00,0x94,0x14,0x53,0x04,0x13,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10,0x04, - 0x13,0x00,0x14,0x00,0x14,0x00,0x00,0x00,0xe0,0xdb,0x04,0xcf,0x86,0xe5,0xdf,0x01, - 0xd4,0x06,0xcf,0x06,0x04,0x00,0xd3,0x74,0xd2,0x6e,0xd1,0x06,0xcf,0x06,0x04,0x00, - 0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x04,0x00,0x52,0x04,0x04,0x00, - 0x91,0x08,0x10,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0xd4,0x10,0x93,0x0c, - 0x92,0x08,0x11,0x04,0x04,0x00,0x06,0x00,0x04,0x00,0x04,0x00,0x93,0x10,0x52,0x04, - 0x04,0x00,0x91,0x08,0x10,0x04,0x06,0x00,0x04,0x00,0x04,0x00,0x04,0x00,0xcf,0x86, - 0x95,0x24,0x94,0x20,0x93,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x04,0x00,0x06,0x00, - 0x04,0x00,0xd1,0x08,0x10,0x04,0x04,0x00,0x06,0x00,0x10,0x04,0x04,0x00,0x00,0x00, - 0x00,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x06,0x0a,0x00,0xd2,0x84,0xd1,0x4c,0xd0,0x16, - 0xcf,0x86,0x55,0x04,0x0a,0x00,0x94,0x0c,0x53,0x04,0x0a,0x00,0x12,0x04,0x0a,0x00, - 0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x0a,0x00,0xd4,0x1c,0xd3,0x0c,0x92,0x08, - 0x11,0x04,0x0c,0x00,0x0a,0x00,0x0a,0x00,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00, - 0x10,0x04,0x0a,0x00,0x0a,0xe6,0xd3,0x08,0x12,0x04,0x0a,0x00,0x0d,0xe6,0x52,0x04, - 0x0d,0xe6,0x11,0x04,0x0a,0xe6,0x0a,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, - 0x0a,0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, - 0x11,0xe6,0x0d,0xe6,0x0b,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00, - 0x93,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x00,0x00,0xd1,0x40, - 0xd0,0x3a,0xcf,0x86,0xd5,0x24,0x54,0x04,0x08,0x00,0xd3,0x10,0x52,0x04,0x08,0x00, - 0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x09,0x00,0x92,0x0c,0x51,0x04,0x09,0x00, - 0x10,0x04,0x09,0x00,0x0a,0x00,0x0a,0x00,0x94,0x10,0x93,0x0c,0x92,0x08,0x11,0x04, - 0x09,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0x0a,0x00,0xcf,0x06,0x0a,0x00,0xd0,0x5e, - 0xcf,0x86,0xd5,0x28,0xd4,0x18,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00,0xd1,0x08, - 0x10,0x04,0x0a,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x11,0x00,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x0c,0x00,0x0d,0x00,0x10,0x00,0x10,0x00,0xd4,0x1c,0x53,0x04,0x0c,0x00, - 0xd2,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0d,0x00,0x10,0x00,0x51,0x04,0x10,0x00, - 0x10,0x04,0x12,0x00,0x14,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00, - 0x11,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x1c, - 0x94,0x18,0x93,0x14,0xd2,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x51,0x04,0x15,0x00, - 0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x00,0x00,0xd3,0x10, - 0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x92,0x0c, - 0x51,0x04,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0a,0x00,0x0a,0x00,0xe4,0xf2,0x02,0xe3, - 0x65,0x01,0xd2,0x98,0xd1,0x48,0xd0,0x36,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10, - 0x52,0x04,0x08,0x00,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x09,0x08,0x00,0x08,0x00, - 0x08,0x00,0xd4,0x0c,0x53,0x04,0x08,0x00,0x12,0x04,0x08,0x00,0x00,0x00,0x53,0x04, - 0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04, - 0x09,0x00,0x54,0x04,0x09,0x00,0x13,0x04,0x09,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06, - 0x0a,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x1c,0xd3,0x10,0x52,0x04,0x0a,0x00,0x91,0x08, - 0x10,0x04,0x0a,0x09,0x12,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00, - 0x0a,0x00,0x53,0x04,0x0a,0x00,0x92,0x08,0x11,0x04,0x0a,0x00,0x00,0x00,0x00,0x00, - 0x54,0x04,0x0b,0xe6,0xd3,0x0c,0x92,0x08,0x11,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00, - 0x52,0x04,0x0b,0x00,0x11,0x04,0x11,0x00,0x14,0x00,0xd1,0x60,0xd0,0x22,0xcf,0x86, - 0x55,0x04,0x0a,0x00,0x94,0x18,0x53,0x04,0x0a,0x00,0xd2,0x0c,0x51,0x04,0x0a,0x00, - 0x10,0x04,0x0a,0x00,0x0a,0xdc,0x11,0x04,0x0a,0xdc,0x0a,0x00,0x0a,0x00,0xcf,0x86, - 0xd5,0x24,0x54,0x04,0x0a,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0a,0x00,0x10,0x04, - 0x0a,0x00,0x0a,0x09,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00, - 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x55,0x04, - 0x0b,0x00,0x54,0x04,0x0b,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04, - 0x0b,0x00,0x0b,0x07,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x34,0xd4,0x20,0xd3,0x10, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x09,0x0b,0x00,0x0b,0x00,0x0b,0x00,0x52,0x04, - 0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x53,0x04,0x0b,0x00, - 0xd2,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x0b,0x00,0x54,0x04, - 0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, - 0x10,0x00,0x00,0x00,0xd2,0xd0,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0a,0x00, - 0x54,0x04,0x0a,0x00,0x93,0x10,0x52,0x04,0x0a,0x00,0x51,0x04,0x0a,0x00,0x10,0x04, - 0x0a,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x20,0xd4,0x10,0x53,0x04,0x0a,0x00, - 0x52,0x04,0x0a,0x00,0x11,0x04,0x0a,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x92,0x08, - 0x11,0x04,0x0a,0x00,0x00,0x00,0x0a,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00, - 0x12,0x04,0x0b,0x00,0x10,0x00,0xd0,0x3a,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04, - 0x0b,0x00,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0xe6, - 0xd1,0x08,0x10,0x04,0x0b,0xdc,0x0b,0x00,0x10,0x04,0x0b,0x00,0x0b,0xe6,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x0b,0xe6,0x0b,0x00,0x0b,0x00,0x11,0x04,0x0b,0x00,0x0b,0xe6, - 0xcf,0x86,0xd5,0x2c,0xd4,0x18,0x93,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00, - 0x0b,0xe6,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x00,0x00, - 0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00,0x54,0x04, - 0x0d,0x00,0x93,0x10,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x09, - 0x00,0x00,0x00,0x00,0xd1,0x8c,0xd0,0x72,0xcf,0x86,0xd5,0x4c,0xd4,0x30,0xd3,0x18, - 0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00, - 0x10,0x04,0x0c,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00, - 0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x93,0x18,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04, - 0x0c,0x00,0x00,0x00,0x00,0x00,0x94,0x20,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04, - 0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00, - 0x10,0x04,0x0c,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0x94,0x10, - 0x93,0x0c,0x52,0x04,0x11,0x00,0x11,0x04,0x10,0x00,0x15,0x00,0x00,0x00,0x11,0x00, - 0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x55,0x04,0x0b,0x00,0xd4,0x14,0x53,0x04, - 0x0b,0x00,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x00,0x00, - 0x53,0x04,0x0b,0x00,0x92,0x08,0x11,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0xcf,0x06, - 0x02,0xff,0xff,0xcf,0x86,0xcf,0x06,0x02,0xff,0xff,0xd1,0x76,0xd0,0x09,0xcf,0x86, - 0xcf,0x06,0x02,0xff,0xff,0xcf,0x86,0x85,0xd4,0x07,0xcf,0x06,0x02,0xff,0xff,0xd3, - 0x07,0xcf,0x06,0x02,0xff,0xff,0xd2,0x07,0xcf,0x06,0x02,0xff,0xff,0xd1,0x07,0xcf, - 0x06,0x02,0xff,0xff,0xd0,0x18,0xcf,0x86,0x55,0x05,0x02,0xff,0xff,0x94,0x0d,0x93, - 0x09,0x12,0x05,0x02,0xff,0xff,0x00,0x00,0x00,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x24, - 0x94,0x20,0xd3,0x10,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, - 0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00, - 0x0b,0x00,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0x12,0x04,0x0b,0x00,0x00,0x00, - 0xd0,0x08,0xcf,0x86,0xcf,0x06,0x01,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x01,0x00, - 0xe4,0x9c,0x10,0xe3,0x16,0x08,0xd2,0x06,0xcf,0x06,0x01,0x00,0xe1,0x08,0x04,0xe0, - 0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe8,0xb1,0x88,0x00,0x01,0xff,0xe6,0x9b,0xb4,0x00,0x10,0x08,0x01, - 0xff,0xe8,0xbb,0x8a,0x00,0x01,0xff,0xe8,0xb3,0x88,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe6,0xbb,0x91,0x00,0x01,0xff,0xe4,0xb8,0xb2,0x00,0x10,0x08,0x01,0xff,0xe5, - 0x8f,0xa5,0x00,0x01,0xff,0xe9,0xbe,0x9c,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe9,0xbe,0x9c,0x00,0x01,0xff,0xe5,0xa5,0x91,0x00,0x10,0x08,0x01,0xff,0xe9, - 0x87,0x91,0x00,0x01,0xff,0xe5,0x96,0x87,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, - 0xa5,0x88,0x00,0x01,0xff,0xe6,0x87,0xb6,0x00,0x10,0x08,0x01,0xff,0xe7,0x99,0xa9, - 0x00,0x01,0xff,0xe7,0xbe,0x85,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe8,0x98,0xbf,0x00,0x01,0xff,0xe8,0x9e,0xba,0x00,0x10,0x08,0x01,0xff,0xe8, - 0xa3,0xb8,0x00,0x01,0xff,0xe9,0x82,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6, - 0xa8,0x82,0x00,0x01,0xff,0xe6,0xb4,0x9b,0x00,0x10,0x08,0x01,0xff,0xe7,0x83,0x99, - 0x00,0x01,0xff,0xe7,0x8f,0x9e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, - 0x90,0xbd,0x00,0x01,0xff,0xe9,0x85,0xaa,0x00,0x10,0x08,0x01,0xff,0xe9,0xa7,0xb1, - 0x00,0x01,0xff,0xe4,0xba,0x82,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x8d,0xb5, - 0x00,0x01,0xff,0xe6,0xac,0x84,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x9b,0x00,0x01, - 0xff,0xe8,0x98,0xad,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe9,0xb8,0x9e,0x00,0x01,0xff,0xe5,0xb5,0x90,0x00,0x10,0x08,0x01,0xff,0xe6, - 0xbf,0xab,0x00,0x01,0xff,0xe8,0x97,0x8d,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8, - 0xa5,0xa4,0x00,0x01,0xff,0xe6,0x8b,0x89,0x00,0x10,0x08,0x01,0xff,0xe8,0x87,0x98, - 0x00,0x01,0xff,0xe8,0xa0,0x9f,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5, - 0xbb,0x8a,0x00,0x01,0xff,0xe6,0x9c,0x97,0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0xaa, - 0x00,0x01,0xff,0xe7,0x8b,0xbc,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x83,0x8e, - 0x00,0x01,0xff,0xe4,0xbe,0x86,0x00,0x10,0x08,0x01,0xff,0xe5,0x86,0xb7,0x00,0x01, - 0xff,0xe5,0x8b,0x9e,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6, - 0x93,0x84,0x00,0x01,0xff,0xe6,0xab,0x93,0x00,0x10,0x08,0x01,0xff,0xe7,0x88,0x90, - 0x00,0x01,0xff,0xe7,0x9b,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x80,0x81, - 0x00,0x01,0xff,0xe8,0x98,0x86,0x00,0x10,0x08,0x01,0xff,0xe8,0x99,0x9c,0x00,0x01, - 0xff,0xe8,0xb7,0xaf,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0x9c,0xb2, - 0x00,0x01,0xff,0xe9,0xad,0xaf,0x00,0x10,0x08,0x01,0xff,0xe9,0xb7,0xba,0x00,0x01, - 0xff,0xe7,0xa2,0x8c,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa5,0xbf,0x00,0x01, - 0xff,0xe7,0xb6,0xa0,0x00,0x10,0x08,0x01,0xff,0xe8,0x8f,0x89,0x00,0x01,0xff,0xe9, - 0x8c,0x84,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe9,0xb9,0xbf,0x00,0x01,0xff,0xe8,0xab,0x96,0x00,0x10,0x08, - 0x01,0xff,0xe5,0xa3,0x9f,0x00,0x01,0xff,0xe5,0xbc,0x84,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe7,0xb1,0xa0,0x00,0x01,0xff,0xe8,0x81,0xbe,0x00,0x10,0x08,0x01,0xff, - 0xe7,0x89,0xa2,0x00,0x01,0xff,0xe7,0xa3,0x8a,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe8,0xb3,0x82,0x00,0x01,0xff,0xe9,0x9b,0xb7,0x00,0x10,0x08,0x01,0xff, - 0xe5,0xa3,0x98,0x00,0x01,0xff,0xe5,0xb1,0xa2,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe6,0xa8,0x93,0x00,0x01,0xff,0xe6,0xb7,0x9a,0x00,0x10,0x08,0x01,0xff,0xe6,0xbc, - 0x8f,0x00,0x01,0xff,0xe7,0xb4,0xaf,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe7,0xb8,0xb7,0x00,0x01,0xff,0xe9,0x99,0x8b,0x00,0x10,0x08,0x01,0xff, - 0xe5,0x8b,0x92,0x00,0x01,0xff,0xe8,0x82,0x8b,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe5,0x87,0x9c,0x00,0x01,0xff,0xe5,0x87,0x8c,0x00,0x10,0x08,0x01,0xff,0xe7,0xa8, - 0x9c,0x00,0x01,0xff,0xe7,0xb6,0xbe,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe8,0x8f,0xb1,0x00,0x01,0xff,0xe9,0x99,0xb5,0x00,0x10,0x08,0x01,0xff,0xe8,0xae, - 0x80,0x00,0x01,0xff,0xe6,0x8b,0x8f,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xa8, - 0x82,0x00,0x01,0xff,0xe8,0xab,0xbe,0x00,0x10,0x08,0x01,0xff,0xe4,0xb8,0xb9,0x00, - 0x01,0xff,0xe5,0xaf,0xa7,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe6,0x80,0x92,0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0x10,0x08,0x01,0xff, - 0xe7,0x95,0xb0,0x00,0x01,0xff,0xe5,0x8c,0x97,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe7,0xa3,0xbb,0x00,0x01,0xff,0xe4,0xbe,0xbf,0x00,0x10,0x08,0x01,0xff,0xe5,0xbe, - 0xa9,0x00,0x01,0xff,0xe4,0xb8,0x8d,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe6,0xb3,0x8c,0x00,0x01,0xff,0xe6,0x95,0xb8,0x00,0x10,0x08,0x01,0xff,0xe7,0xb4, - 0xa2,0x00,0x01,0xff,0xe5,0x8f,0x83,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0xa1, - 0x9e,0x00,0x01,0xff,0xe7,0x9c,0x81,0x00,0x10,0x08,0x01,0xff,0xe8,0x91,0x89,0x00, - 0x01,0xff,0xe8,0xaa,0xaa,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe6,0xae,0xba,0x00,0x01,0xff,0xe8,0xbe,0xb0,0x00,0x10,0x08,0x01,0xff,0xe6,0xb2, - 0x88,0x00,0x01,0xff,0xe6,0x8b,0xbe,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x8b, - 0xa5,0x00,0x01,0xff,0xe6,0x8e,0xa0,0x00,0x10,0x08,0x01,0xff,0xe7,0x95,0xa5,0x00, - 0x01,0xff,0xe4,0xba,0xae,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x85, - 0xa9,0x00,0x01,0xff,0xe5,0x87,0x89,0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0x81,0x00, - 0x01,0xff,0xe7,0xb3,0xa7,0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0x89,0xaf,0x00, - 0x01,0xff,0xe8,0xab,0x92,0x00,0x10,0x08,0x01,0xff,0xe9,0x87,0x8f,0x00,0x01,0xff, - 0xe5,0x8b,0xb5,0x00,0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe5,0x91,0x82,0x00,0x01,0xff,0xe5,0xa5, - 0xb3,0x00,0x10,0x08,0x01,0xff,0xe5,0xbb,0xac,0x00,0x01,0xff,0xe6,0x97,0x85,0x00, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0xbf,0xbe,0x00,0x01,0xff,0xe7,0xa4,0xaa,0x00, - 0x10,0x08,0x01,0xff,0xe9,0x96,0xad,0x00,0x01,0xff,0xe9,0xa9,0xaa,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xba,0x97,0x00,0x01,0xff,0xe9,0xbb,0x8e,0x00, - 0x10,0x08,0x01,0xff,0xe5,0x8a,0x9b,0x00,0x01,0xff,0xe6,0x9b,0x86,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe6,0xad,0xb7,0x00,0x01,0xff,0xe8,0xbd,0xa2,0x00,0x10,0x08, - 0x01,0xff,0xe5,0xb9,0xb4,0x00,0x01,0xff,0xe6,0x86,0x90,0x00,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x88,0x80,0x00,0x01,0xff,0xe6,0x92,0x9a,0x00, - 0x10,0x08,0x01,0xff,0xe6,0xbc,0xa3,0x00,0x01,0xff,0xe7,0x85,0x89,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe7,0x92,0x89,0x00,0x01,0xff,0xe7,0xa7,0x8a,0x00,0x10,0x08, - 0x01,0xff,0xe7,0xb7,0xb4,0x00,0x01,0xff,0xe8,0x81,0xaf,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe8,0xbc,0xa6,0x00,0x01,0xff,0xe8,0x93,0xae,0x00,0x10,0x08, - 0x01,0xff,0xe9,0x80,0xa3,0x00,0x01,0xff,0xe9,0x8d,0x8a,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe5,0x88,0x97,0x00,0x01,0xff,0xe5,0x8a,0xa3,0x00,0x10,0x08,0x01,0xff, - 0xe5,0x92,0xbd,0x00,0x01,0xff,0xe7,0x83,0x88,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe8,0xa3,0x82,0x00,0x01,0xff,0xe8,0xaa,0xaa,0x00, - 0x10,0x08,0x01,0xff,0xe5,0xbb,0x89,0x00,0x01,0xff,0xe5,0xbf,0xb5,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe6,0x8d,0xbb,0x00,0x01,0xff,0xe6,0xae,0xae,0x00,0x10,0x08, - 0x01,0xff,0xe7,0xb0,0xbe,0x00,0x01,0xff,0xe7,0x8d,0xb5,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe4,0xbb,0xa4,0x00,0x01,0xff,0xe5,0x9b,0xb9,0x00,0x10,0x08, - 0x01,0xff,0xe5,0xaf,0xa7,0x00,0x01,0xff,0xe5,0xb6,0xba,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe6,0x80,0x9c,0x00,0x01,0xff,0xe7,0x8e,0xb2,0x00,0x10,0x08,0x01,0xff, - 0xe7,0x91,0xa9,0x00,0x01,0xff,0xe7,0xbe,0x9a,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe8,0x81,0x86,0x00,0x01,0xff,0xe9,0x88,0xb4,0x00,0x10,0x08, - 0x01,0xff,0xe9,0x9b,0xb6,0x00,0x01,0xff,0xe9,0x9d,0x88,0x00,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe9,0xa0,0x98,0x00,0x01,0xff,0xe4,0xbe,0x8b,0x00,0x10,0x08,0x01,0xff, - 0xe7,0xa6,0xae,0x00,0x01,0xff,0xe9,0x86,0xb4,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe9,0x9a,0xb8,0x00,0x01,0xff,0xe6,0x83,0xa1,0x00,0x10,0x08,0x01,0xff, - 0xe4,0xba,0x86,0x00,0x01,0xff,0xe5,0x83,0x9a,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe5,0xaf,0xae,0x00,0x01,0xff,0xe5,0xb0,0xbf,0x00,0x10,0x08,0x01,0xff,0xe6,0x96, - 0x99,0x00,0x01,0xff,0xe6,0xa8,0x82,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0x87,0x8e,0x00,0x01,0xff,0xe7, - 0x99,0x82,0x00,0x10,0x08,0x01,0xff,0xe8,0x93,0xbc,0x00,0x01,0xff,0xe9,0x81,0xbc, - 0x00,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xbe,0x8d,0x00,0x01,0xff,0xe6,0x9a,0x88, - 0x00,0x10,0x08,0x01,0xff,0xe9,0x98,0xae,0x00,0x01,0xff,0xe5,0x8a,0x89,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x9d,0xbb,0x00,0x01,0xff,0xe6,0x9f,0xb3, - 0x00,0x10,0x08,0x01,0xff,0xe6,0xb5,0x81,0x00,0x01,0xff,0xe6,0xba,0x9c,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe7,0x90,0x89,0x00,0x01,0xff,0xe7,0x95,0x99,0x00,0x10, - 0x08,0x01,0xff,0xe7,0xa1,0xab,0x00,0x01,0xff,0xe7,0xb4,0x90,0x00,0xd3,0x40,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe9,0xa1,0x9e,0x00,0x01,0xff,0xe5,0x85,0xad, - 0x00,0x10,0x08,0x01,0xff,0xe6,0x88,0xae,0x00,0x01,0xff,0xe9,0x99,0xb8,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe5,0x80,0xab,0x00,0x01,0xff,0xe5,0xb4,0x99,0x00,0x10, - 0x08,0x01,0xff,0xe6,0xb7,0xaa,0x00,0x01,0xff,0xe8,0xbc,0xaa,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe5,0xbe,0x8b,0x00,0x01,0xff,0xe6,0x85,0x84,0x00,0x10, - 0x08,0x01,0xff,0xe6,0xa0,0x97,0x00,0x01,0xff,0xe7,0x8e,0x87,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe9,0x9a,0x86,0x00,0x01,0xff,0xe5,0x88,0xa9,0x00,0x10,0x08,0x01, - 0xff,0xe5,0x90,0x8f,0x00,0x01,0xff,0xe5,0xb1,0xa5,0x00,0xd4,0x80,0xd3,0x40,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x01,0xff,0xe6,0x98,0x93,0x00,0x01,0xff,0xe6,0x9d,0x8e, - 0x00,0x10,0x08,0x01,0xff,0xe6,0xa2,0xa8,0x00,0x01,0xff,0xe6,0xb3,0xa5,0x00,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe7,0x90,0x86,0x00,0x01,0xff,0xe7,0x97,0xa2,0x00,0x10, - 0x08,0x01,0xff,0xe7,0xbd,0xb9,0x00,0x01,0xff,0xe8,0xa3,0x8f,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe8,0xa3,0xa1,0x00,0x01,0xff,0xe9,0x87,0x8c,0x00,0x10, - 0x08,0x01,0xff,0xe9,0x9b,0xa2,0x00,0x01,0xff,0xe5,0x8c,0xbf,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe6,0xba,0xba,0x00,0x01,0xff,0xe5,0x90,0x9d,0x00,0x10,0x08,0x01, - 0xff,0xe7,0x87,0x90,0x00,0x01,0xff,0xe7,0x92,0x98,0x00,0xd3,0x40,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x01,0xff,0xe8,0x97,0xba,0x00,0x01,0xff,0xe9,0x9a,0xa3,0x00,0x10, - 0x08,0x01,0xff,0xe9,0xb1,0x97,0x00,0x01,0xff,0xe9,0xba,0x9f,0x00,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe6,0x9e,0x97,0x00,0x01,0xff,0xe6,0xb7,0x8b,0x00,0x10,0x08,0x01, - 0xff,0xe8,0x87,0xa8,0x00,0x01,0xff,0xe7,0xab,0x8b,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x01,0xff,0xe7,0xac,0xa0,0x00,0x01,0xff,0xe7,0xb2,0x92,0x00,0x10,0x08,0x01, - 0xff,0xe7,0x8b,0x80,0x00,0x01,0xff,0xe7,0x82,0x99,0x00,0xd1,0x10,0x10,0x08,0x01, - 0xff,0xe8,0xad,0x98,0x00,0x01,0xff,0xe4,0xbb,0x80,0x00,0x10,0x08,0x01,0xff,0xe8, - 0x8c,0xb6,0x00,0x01,0xff,0xe5,0x88,0xba,0x00,0xe2,0xad,0x06,0xe1,0xc4,0x03,0xe0, - 0xcb,0x01,0xcf,0x86,0xd5,0xe4,0xd4,0x74,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x01,0xff,0xe5,0x88,0x87,0x00,0x01,0xff,0xe5,0xba,0xa6,0x00,0x10,0x08,0x01,0xff, - 0xe6,0x8b,0x93,0x00,0x01,0xff,0xe7,0xb3,0x96,0x00,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe5,0xae,0x85,0x00,0x01,0xff,0xe6,0xb4,0x9e,0x00,0x10,0x08,0x01,0xff,0xe6,0x9a, - 0xb4,0x00,0x01,0xff,0xe8,0xbc,0xbb,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x01,0xff, - 0xe8,0xa1,0x8c,0x00,0x01,0xff,0xe9,0x99,0x8d,0x00,0x10,0x08,0x01,0xff,0xe8,0xa6, - 0x8b,0x00,0x01,0xff,0xe5,0xbb,0x93,0x00,0x91,0x10,0x10,0x08,0x01,0xff,0xe5,0x85, - 0x80,0x00,0x01,0xff,0xe5,0x97,0x80,0x00,0x01,0x00,0xd3,0x34,0xd2,0x18,0xd1,0x0c, - 0x10,0x08,0x01,0xff,0xe5,0xa1,0x9a,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe6,0x99, - 0xb4,0x00,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe5,0x87,0x9e,0x00, - 0x10,0x08,0x01,0xff,0xe7,0x8c,0xaa,0x00,0x01,0xff,0xe7,0x9b,0x8a,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x01,0xff,0xe7,0xa4,0xbc,0x00,0x01,0xff,0xe7,0xa5,0x9e,0x00, - 0x10,0x08,0x01,0xff,0xe7,0xa5,0xa5,0x00,0x01,0xff,0xe7,0xa6,0x8f,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe9,0x9d,0x96,0x00,0x01,0xff,0xe7,0xb2,0xbe,0x00,0x10,0x08, - 0x01,0xff,0xe7,0xbe,0xbd,0x00,0x01,0x00,0xd4,0x64,0xd3,0x30,0xd2,0x18,0xd1,0x0c, - 0x10,0x08,0x01,0xff,0xe8,0x98,0x92,0x00,0x01,0x00,0x10,0x08,0x01,0xff,0xe8,0xab, - 0xb8,0x00,0x01,0x00,0xd1,0x0c,0x10,0x04,0x01,0x00,0x01,0xff,0xe9,0x80,0xb8,0x00, - 0x10,0x08,0x01,0xff,0xe9,0x83,0xbd,0x00,0x01,0x00,0xd2,0x14,0x51,0x04,0x01,0x00, - 0x10,0x08,0x01,0xff,0xe9,0xa3,0xaf,0x00,0x01,0xff,0xe9,0xa3,0xbc,0x00,0xd1,0x10, - 0x10,0x08,0x01,0xff,0xe9,0xa4,0xa8,0x00,0x01,0xff,0xe9,0xb6,0xb4,0x00,0x10,0x08, - 0x0d,0xff,0xe9,0x83,0x9e,0x00,0x0d,0xff,0xe9,0x9a,0xb7,0x00,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x06,0xff,0xe4,0xbe,0xae,0x00,0x06,0xff,0xe5,0x83,0xa7,0x00, - 0x10,0x08,0x06,0xff,0xe5,0x85,0x8d,0x00,0x06,0xff,0xe5,0x8b,0x89,0x00,0xd1,0x10, - 0x10,0x08,0x06,0xff,0xe5,0x8b,0xa4,0x00,0x06,0xff,0xe5,0x8d,0x91,0x00,0x10,0x08, - 0x06,0xff,0xe5,0x96,0x9d,0x00,0x06,0xff,0xe5,0x98,0x86,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x06,0xff,0xe5,0x99,0xa8,0x00,0x06,0xff,0xe5,0xa1,0x80,0x00,0x10,0x08, - 0x06,0xff,0xe5,0xa2,0xa8,0x00,0x06,0xff,0xe5,0xb1,0xa4,0x00,0xd1,0x10,0x10,0x08, - 0x06,0xff,0xe5,0xb1,0xae,0x00,0x06,0xff,0xe6,0x82,0x94,0x00,0x10,0x08,0x06,0xff, - 0xe6,0x85,0xa8,0x00,0x06,0xff,0xe6,0x86,0x8e,0x00,0xcf,0x86,0xe5,0x01,0x01,0xd4, - 0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe6,0x87,0xb2,0x00,0x06, - 0xff,0xe6,0x95,0x8f,0x00,0x10,0x08,0x06,0xff,0xe6,0x97,0xa2,0x00,0x06,0xff,0xe6, - 0x9a,0x91,0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe6,0xa2,0x85,0x00,0x06,0xff,0xe6, - 0xb5,0xb7,0x00,0x10,0x08,0x06,0xff,0xe6,0xb8,0x9a,0x00,0x06,0xff,0xe6,0xbc,0xa2, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0x85,0xae,0x00,0x06,0xff,0xe7, - 0x88,0xab,0x00,0x10,0x08,0x06,0xff,0xe7,0x90,0xa2,0x00,0x06,0xff,0xe7,0xa2,0x91, - 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa4,0xbe,0x00,0x06,0xff,0xe7,0xa5,0x89, - 0x00,0x10,0x08,0x06,0xff,0xe7,0xa5,0x88,0x00,0x06,0xff,0xe7,0xa5,0x90,0x00,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa5,0x96,0x00,0x06,0xff,0xe7, - 0xa5,0x9d,0x00,0x10,0x08,0x06,0xff,0xe7,0xa6,0x8d,0x00,0x06,0xff,0xe7,0xa6,0x8e, - 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xa9,0x80,0x00,0x06,0xff,0xe7,0xaa,0x81, - 0x00,0x10,0x08,0x06,0xff,0xe7,0xaf,0x80,0x00,0x06,0xff,0xe7,0xb7,0xb4,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe7,0xb8,0x89,0x00,0x06,0xff,0xe7,0xb9,0x81, - 0x00,0x10,0x08,0x06,0xff,0xe7,0xbd,0xb2,0x00,0x06,0xff,0xe8,0x80,0x85,0x00,0xd1, - 0x10,0x10,0x08,0x06,0xff,0xe8,0x87,0xad,0x00,0x06,0xff,0xe8,0x89,0xb9,0x00,0x10, - 0x08,0x06,0xff,0xe8,0x89,0xb9,0x00,0x06,0xff,0xe8,0x91,0x97,0x00,0xd4,0x75,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8,0xa4,0x90,0x00,0x06,0xff,0xe8, - 0xa6,0x96,0x00,0x10,0x08,0x06,0xff,0xe8,0xac,0x81,0x00,0x06,0xff,0xe8,0xac,0xb9, - 0x00,0xd1,0x10,0x10,0x08,0x06,0xff,0xe8,0xb3,0x93,0x00,0x06,0xff,0xe8,0xb4,0x88, - 0x00,0x10,0x08,0x06,0xff,0xe8,0xbe,0xb6,0x00,0x06,0xff,0xe9,0x80,0xb8,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x06,0xff,0xe9,0x9b,0xa3,0x00,0x06,0xff,0xe9,0x9f,0xbf, - 0x00,0x10,0x08,0x06,0xff,0xe9,0xa0,0xbb,0x00,0x0b,0xff,0xe6,0x81,0xb5,0x00,0x91, - 0x11,0x10,0x09,0x0b,0xff,0xf0,0xa4,0x8b,0xae,0x00,0x0b,0xff,0xe8,0x88,0x98,0x00, - 0x00,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe4,0xb8,0xa6,0x00, - 0x08,0xff,0xe5,0x86,0xb5,0x00,0x10,0x08,0x08,0xff,0xe5,0x85,0xa8,0x00,0x08,0xff, - 0xe4,0xbe,0x80,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0x85,0x85,0x00,0x08,0xff, - 0xe5,0x86,0x80,0x00,0x10,0x08,0x08,0xff,0xe5,0x8b,0x87,0x00,0x08,0xff,0xe5,0x8b, - 0xba,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0x96,0x9d,0x00,0x08,0xff, - 0xe5,0x95,0x95,0x00,0x10,0x08,0x08,0xff,0xe5,0x96,0x99,0x00,0x08,0xff,0xe5,0x97, - 0xa2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe5,0xa1,0x9a,0x00,0x08,0xff,0xe5,0xa2, - 0xb3,0x00,0x10,0x08,0x08,0xff,0xe5,0xa5,0x84,0x00,0x08,0xff,0xe5,0xa5,0x94,0x00, - 0xe0,0x04,0x02,0xcf,0x86,0xe5,0x01,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x08,0xff,0xe5,0xa9,0xa2,0x00,0x08,0xff,0xe5,0xac,0xa8,0x00,0x10,0x08, - 0x08,0xff,0xe5,0xbb,0x92,0x00,0x08,0xff,0xe5,0xbb,0x99,0x00,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe5,0xbd,0xa9,0x00,0x08,0xff,0xe5,0xbe,0xad,0x00,0x10,0x08,0x08,0xff, - 0xe6,0x83,0x98,0x00,0x08,0xff,0xe6,0x85,0x8e,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe6,0x84,0x88,0x00,0x08,0xff,0xe6,0x86,0x8e,0x00,0x10,0x08,0x08,0xff, - 0xe6,0x85,0xa0,0x00,0x08,0xff,0xe6,0x87,0xb2,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe6,0x88,0xb4,0x00,0x08,0xff,0xe6,0x8f,0x84,0x00,0x10,0x08,0x08,0xff,0xe6,0x90, - 0x9c,0x00,0x08,0xff,0xe6,0x91,0x92,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe6,0x95,0x96,0x00,0x08,0xff,0xe6,0x99,0xb4,0x00,0x10,0x08,0x08,0xff, - 0xe6,0x9c,0x97,0x00,0x08,0xff,0xe6,0x9c,0x9b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe6,0x9d,0x96,0x00,0x08,0xff,0xe6,0xad,0xb9,0x00,0x10,0x08,0x08,0xff,0xe6,0xae, - 0xba,0x00,0x08,0xff,0xe6,0xb5,0x81,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe6,0xbb,0x9b,0x00,0x08,0xff,0xe6,0xbb,0x8b,0x00,0x10,0x08,0x08,0xff,0xe6,0xbc, - 0xa2,0x00,0x08,0xff,0xe7,0x80,0x9e,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0x85, - 0xae,0x00,0x08,0xff,0xe7,0x9e,0xa7,0x00,0x10,0x08,0x08,0xff,0xe7,0x88,0xb5,0x00, - 0x08,0xff,0xe7,0x8a,0xaf,0x00,0xd4,0x80,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe7,0x8c,0xaa,0x00,0x08,0xff,0xe7,0x91,0xb1,0x00,0x10,0x08,0x08,0xff, - 0xe7,0x94,0x86,0x00,0x08,0xff,0xe7,0x94,0xbb,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe7,0x98,0x9d,0x00,0x08,0xff,0xe7,0x98,0x9f,0x00,0x10,0x08,0x08,0xff,0xe7,0x9b, - 0x8a,0x00,0x08,0xff,0xe7,0x9b,0x9b,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe7,0x9b,0xb4,0x00,0x08,0xff,0xe7,0x9d,0x8a,0x00,0x10,0x08,0x08,0xff,0xe7,0x9d, - 0x80,0x00,0x08,0xff,0xe7,0xa3,0x8c,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe7,0xaa, - 0xb1,0x00,0x08,0xff,0xe7,0xaf,0x80,0x00,0x10,0x08,0x08,0xff,0xe7,0xb1,0xbb,0x00, - 0x08,0xff,0xe7,0xb5,0x9b,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe7,0xb7,0xb4,0x00,0x08,0xff,0xe7,0xbc,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0x80, - 0x85,0x00,0x08,0xff,0xe8,0x8d,0x92,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0x8f, - 0xaf,0x00,0x08,0xff,0xe8,0x9d,0xb9,0x00,0x10,0x08,0x08,0xff,0xe8,0xa5,0x81,0x00, - 0x08,0xff,0xe8,0xa6,0x86,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xa6, - 0x96,0x00,0x08,0xff,0xe8,0xaa,0xbf,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xb8,0x00, - 0x08,0xff,0xe8,0xab,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff,0xe8,0xac,0x81,0x00, - 0x08,0xff,0xe8,0xab,0xbe,0x00,0x10,0x08,0x08,0xff,0xe8,0xab,0xad,0x00,0x08,0xff, - 0xe8,0xac,0xb9,0x00,0xcf,0x86,0x95,0xde,0xd4,0x81,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x08,0xff,0xe8,0xae,0x8a,0x00,0x08,0xff,0xe8,0xb4,0x88,0x00,0x10,0x08, - 0x08,0xff,0xe8,0xbc,0xb8,0x00,0x08,0xff,0xe9,0x81,0xb2,0x00,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe9,0x86,0x99,0x00,0x08,0xff,0xe9,0x89,0xb6,0x00,0x10,0x08,0x08,0xff, - 0xe9,0x99,0xbc,0x00,0x08,0xff,0xe9,0x9b,0xa3,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x08,0xff,0xe9,0x9d,0x96,0x00,0x08,0xff,0xe9,0x9f,0x9b,0x00,0x10,0x08,0x08,0xff, - 0xe9,0x9f,0xbf,0x00,0x08,0xff,0xe9,0xa0,0x8b,0x00,0xd1,0x10,0x10,0x08,0x08,0xff, - 0xe9,0xa0,0xbb,0x00,0x08,0xff,0xe9,0xac,0x92,0x00,0x10,0x08,0x08,0xff,0xe9,0xbe, - 0x9c,0x00,0x08,0xff,0xf0,0xa2,0xa1,0x8a,0x00,0xd3,0x45,0xd2,0x22,0xd1,0x12,0x10, - 0x09,0x08,0xff,0xf0,0xa2,0xa1,0x84,0x00,0x08,0xff,0xf0,0xa3,0x8f,0x95,0x00,0x10, - 0x08,0x08,0xff,0xe3,0xae,0x9d,0x00,0x08,0xff,0xe4,0x80,0x98,0x00,0xd1,0x11,0x10, - 0x08,0x08,0xff,0xe4,0x80,0xb9,0x00,0x08,0xff,0xf0,0xa5,0x89,0x89,0x00,0x10,0x09, - 0x08,0xff,0xf0,0xa5,0xb3,0x90,0x00,0x08,0xff,0xf0,0xa7,0xbb,0x93,0x00,0x92,0x14, - 0x91,0x10,0x10,0x08,0x08,0xff,0xe9,0xbd,0x83,0x00,0x08,0xff,0xe9,0xbe,0x8e,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0xe1,0x94,0x01,0xe0,0x08,0x01,0xcf,0x86,0xd5,0x42, - 0xd4,0x14,0x93,0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00, - 0x00,0x00,0x00,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00, - 0x01,0x00,0x01,0x00,0x52,0x04,0x00,0x00,0xd1,0x0d,0x10,0x04,0x00,0x00,0x04,0xff, - 0xd7,0x99,0xd6,0xb4,0x00,0x10,0x04,0x01,0x1a,0x01,0xff,0xd7,0xb2,0xd6,0xb7,0x00, - 0xd4,0x42,0x53,0x04,0x01,0x00,0xd2,0x16,0x51,0x04,0x01,0x00,0x10,0x09,0x01,0xff, - 0xd7,0xa9,0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd7,0x82,0x00,0xd1,0x16,0x10,0x0b, - 0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7,0x81,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0xd7, - 0x82,0x00,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xb7,0x00,0x01,0xff,0xd7,0x90,0xd6, - 0xb8,0x00,0xd3,0x43,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x90,0xd6,0xbc, - 0x00,0x01,0xff,0xd7,0x91,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x92,0xd6,0xbc, - 0x00,0x01,0xff,0xd7,0x93,0xd6,0xbc,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x94, - 0xd6,0xbc,0x00,0x01,0xff,0xd7,0x95,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x96, - 0xd6,0xbc,0x00,0x00,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0x98,0xd6, - 0xbc,0x00,0x01,0xff,0xd7,0x99,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0x9a,0xd6, - 0xbc,0x00,0x01,0xff,0xd7,0x9b,0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7, - 0x9c,0xd6,0xbc,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xd7,0x9e,0xd6,0xbc,0x00,0x00, - 0x00,0xcf,0x86,0x95,0x85,0x94,0x81,0xd3,0x3e,0xd2,0x1f,0xd1,0x12,0x10,0x09,0x01, - 0xff,0xd7,0xa0,0xd6,0xbc,0x00,0x01,0xff,0xd7,0xa1,0xd6,0xbc,0x00,0x10,0x04,0x00, - 0x00,0x01,0xff,0xd7,0xa3,0xd6,0xbc,0x00,0xd1,0x0d,0x10,0x09,0x01,0xff,0xd7,0xa4, - 0xd6,0xbc,0x00,0x00,0x00,0x10,0x09,0x01,0xff,0xd7,0xa6,0xd6,0xbc,0x00,0x01,0xff, - 0xd7,0xa7,0xd6,0xbc,0x00,0xd2,0x24,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7,0xa8,0xd6, - 0xbc,0x00,0x01,0xff,0xd7,0xa9,0xd6,0xbc,0x00,0x10,0x09,0x01,0xff,0xd7,0xaa,0xd6, - 0xbc,0x00,0x01,0xff,0xd7,0x95,0xd6,0xb9,0x00,0xd1,0x12,0x10,0x09,0x01,0xff,0xd7, - 0x91,0xd6,0xbf,0x00,0x01,0xff,0xd7,0x9b,0xd6,0xbf,0x00,0x10,0x09,0x01,0xff,0xd7, - 0xa4,0xd6,0xbf,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04, - 0x01,0x00,0x54,0x04,0x01,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x01,0x00,0x0c,0x00, - 0x0c,0x00,0x0c,0x00,0xcf,0x86,0x95,0x24,0xd4,0x10,0x93,0x0c,0x92,0x08,0x11,0x04, - 0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x00,0x00, - 0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0xd3,0x5a,0xd2,0x06, - 0xcf,0x06,0x01,0x00,0xd1,0x14,0xd0,0x06,0xcf,0x06,0x01,0x00,0xcf,0x86,0x95,0x08, - 0x14,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54,0x04, - 0x01,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0xcf,0x86,0xd5,0x0c,0x94,0x08,0x13,0x04,0x01,0x00,0x00,0x00,0x05,0x00, - 0x54,0x04,0x05,0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x91,0x08,0x10,0x04, - 0x06,0x00,0x07,0x00,0x00,0x00,0xd2,0xce,0xd1,0xa5,0xd0,0x37,0xcf,0x86,0xd5,0x15, - 0x54,0x05,0x06,0xff,0x00,0x53,0x04,0x08,0x00,0x92,0x08,0x11,0x04,0x08,0x00,0x00, - 0x00,0x00,0x00,0x94,0x1c,0xd3,0x10,0x52,0x04,0x01,0xe6,0x51,0x04,0x0a,0xe6,0x10, - 0x04,0x0a,0xe6,0x10,0xdc,0x52,0x04,0x10,0xdc,0x11,0x04,0x10,0xdc,0x11,0xe6,0x01, - 0x00,0xcf,0x86,0xd5,0x38,0xd4,0x24,0xd3,0x14,0x52,0x04,0x01,0x00,0xd1,0x08,0x10, - 0x04,0x01,0x00,0x06,0x00,0x10,0x04,0x06,0x00,0x07,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x07,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x93,0x10,0x92,0x0c,0x51,0x04,0x01, - 0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd4,0x18,0xd3,0x10,0x52, - 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x12,0x04,0x01, - 0x00,0x00,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06, - 0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0xd0,0x06,0xcf, - 0x06,0x01,0x00,0xcf,0x86,0x55,0x04,0x01,0x00,0x54,0x04,0x01,0x00,0x53,0x04,0x01, - 0x00,0x52,0x04,0x01,0x00,0xd1,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x10,0x04,0x00, - 0x00,0x01,0xff,0x00,0xd1,0x50,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x93,0x10, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x01,0x00,0x53,0x04,0x01,0x00, - 0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x06,0x00,0x94,0x14, - 0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x06,0x00,0x01,0x00,0x01,0x00,0x01,0x00, - 0x01,0x00,0x01,0x00,0xd0,0x2f,0xcf,0x86,0x55,0x04,0x01,0x00,0xd4,0x15,0x93,0x11, - 0x92,0x0d,0x91,0x09,0x10,0x05,0x01,0xff,0x00,0x01,0x00,0x01,0x00,0x01,0x00,0x01, - 0x00,0x53,0x04,0x01,0x00,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01, - 0x00,0x00,0x00,0xcf,0x86,0xd5,0x38,0xd4,0x18,0xd3,0x0c,0x92,0x08,0x11,0x04,0x00, - 0x00,0x01,0x00,0x01,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd3, - 0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x01,0x00,0x01,0x00,0xd2,0x08,0x11,0x04,0x00, - 0x00,0x01,0x00,0x91,0x08,0x10,0x04,0x01,0x00,0x00,0x00,0x00,0x00,0xd4,0x20,0xd3, - 0x10,0x52,0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x52, - 0x04,0x01,0x00,0x51,0x04,0x01,0x00,0x10,0x04,0x01,0x00,0x00,0x00,0x53,0x05,0x00, - 0xff,0x00,0xd2,0x0d,0x91,0x09,0x10,0x05,0x00,0xff,0x00,0x04,0x00,0x04,0x00,0x91, - 0x08,0x10,0x04,0x03,0x00,0x01,0x00,0x01,0x00,0x83,0xe2,0x46,0x3e,0xe1,0x1f,0x3b, - 0xe0,0x9c,0x39,0xcf,0x86,0xe5,0x40,0x26,0xc4,0xe3,0x16,0x14,0xe2,0xef,0x11,0xe1, - 0xd0,0x10,0xe0,0x60,0x07,0xcf,0x86,0xe5,0x53,0x03,0xe4,0x4c,0x02,0xe3,0x3d,0x01, - 0xd2,0x94,0xd1,0x70,0xd0,0x4a,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x07,0x00, - 0x52,0x04,0x07,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00, - 0xd4,0x14,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00, - 0x00,0x00,0x07,0x00,0x53,0x04,0x07,0x00,0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04, - 0x07,0x00,0x00,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86, - 0x95,0x20,0xd4,0x10,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00, - 0x00,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00, - 0x00,0x00,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0x55,0x04,0x07,0x00,0x54,0x04, - 0x07,0x00,0x53,0x04,0x07,0x00,0x92,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00, - 0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x94,0x1c,0x93,0x18, - 0xd2,0x0c,0x51,0x04,0x07,0x00,0x10,0x04,0x07,0x00,0x00,0x00,0x51,0x04,0x00,0x00, - 0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07,0x00,0x93,0x10, - 0x52,0x04,0x07,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0x07,0x00, - 0xcf,0x06,0x08,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4,0x20,0x53,0x04,0x08,0x00, - 0xd2,0x0c,0x51,0x04,0x08,0x00,0x10,0x04,0x08,0x00,0x10,0x00,0xd1,0x08,0x10,0x04, - 0x10,0x00,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x53,0x04,0x0a,0x00,0x12,0x04, - 0x0a,0x00,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04, - 0x00,0x00,0x0a,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0x52,0x04,0x0a,0x00, - 0x91,0x08,0x10,0x04,0x0a,0x00,0x0a,0xdc,0x00,0x00,0xd2,0x5e,0xd1,0x06,0xcf,0x06, - 0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00, - 0x52,0x04,0x0a,0x00,0x91,0x08,0x10,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0x0a,0x00, - 0xcf,0x86,0xd5,0x18,0x54,0x04,0x0a,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x0a,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x10,0xdc,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04, - 0x10,0x00,0x12,0x04,0x10,0x00,0x00,0x00,0xd1,0x70,0xd0,0x36,0xcf,0x86,0xd5,0x18, - 0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x51,0x04,0x05,0x00, - 0x10,0x04,0x05,0x00,0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x05,0x00,0x00,0x00, - 0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x05,0x00, - 0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x05,0x00,0x92,0x0c,0x51,0x04,0x05,0x00, - 0x10,0x04,0x05,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x0c, - 0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x10,0xe6,0x92,0x0c,0x51,0x04,0x10,0xe6, - 0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, - 0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04, - 0x00,0x00,0x07,0x00,0x08,0x00,0xcf,0x86,0x95,0x1c,0xd4,0x0c,0x93,0x08,0x12,0x04, - 0x08,0x00,0x00,0x00,0x08,0x00,0x93,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x08,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0xd3,0xba,0xd2,0x80,0xd1,0x34,0xd0,0x1a,0xcf,0x86, - 0x55,0x04,0x05,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00, - 0x07,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x53,0x04,0x05,0x00, - 0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0xd0,0x2a, - 0xcf,0x86,0xd5,0x14,0x54,0x04,0x07,0x00,0x53,0x04,0x07,0x00,0x52,0x04,0x07,0x00, - 0x11,0x04,0x07,0x00,0x00,0x00,0x94,0x10,0x53,0x04,0x07,0x00,0x92,0x08,0x11,0x04, - 0x07,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xcf,0x86,0xd5,0x10,0x54,0x04,0x12,0x00, - 0x93,0x08,0x12,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x54,0x04,0x12,0x00,0x53,0x04, - 0x12,0x00,0x12,0x04,0x12,0x00,0x00,0x00,0xd1,0x34,0xd0,0x12,0xcf,0x86,0x55,0x04, - 0x10,0x00,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04, - 0x10,0x00,0x94,0x18,0xd3,0x08,0x12,0x04,0x10,0x00,0x00,0x00,0x52,0x04,0x00,0x00, - 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00, - 0xd2,0x06,0xcf,0x06,0x10,0x00,0xd1,0x40,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00, - 0x54,0x04,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04, - 0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x10,0x00,0x93,0x0c, - 0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x08,0x13,0x04, - 0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe4,0xce,0x02,0xe3,0x45,0x01, - 0xd2,0xd0,0xd1,0x70,0xd0,0x52,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3,0x0c,0x52,0x04, - 0x07,0x00,0x11,0x04,0x07,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x07,0x00, - 0x00,0x00,0x07,0x00,0x07,0x00,0x07,0x00,0x54,0x04,0x07,0x00,0xd3,0x10,0x52,0x04, - 0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04,0x00,0x00,0x07,0x00,0xd2,0x0c,0x91,0x08, - 0x10,0x04,0x07,0x00,0x00,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x07,0x00,0x00,0x00, - 0x10,0x04,0x00,0x00,0x07,0x00,0xcf,0x86,0x95,0x18,0x54,0x04,0x0b,0x00,0x93,0x10, - 0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x00,0x00,0x0b,0x00,0x0b,0x00, - 0x10,0x00,0xd0,0x32,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00, - 0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14, - 0x93,0x10,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00, - 0x10,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x11,0x00,0xd3,0x14, - 0xd2,0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x04,0x11,0x00, - 0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00, - 0xd1,0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x1c,0x54,0x04,0x09,0x00,0x53,0x04,0x09,0x00, - 0xd2,0x08,0x11,0x04,0x09,0x00,0x0b,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00, - 0x09,0x00,0x54,0x04,0x0a,0x00,0x53,0x04,0x0a,0x00,0xd2,0x08,0x11,0x04,0x0a,0x00, - 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0a,0x00,0xcf,0x06,0x00,0x00, - 0xd0,0x1a,0xcf,0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0x53,0x04,0x0d,0x00, - 0x52,0x04,0x00,0x00,0x11,0x04,0x11,0x00,0x0d,0x00,0xcf,0x86,0x95,0x14,0x54,0x04, - 0x11,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x11,0x00, - 0x11,0x00,0xd2,0xec,0xd1,0xa4,0xd0,0x76,0xcf,0x86,0xd5,0x48,0xd4,0x28,0xd3,0x14, - 0x52,0x04,0x08,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x10,0x04,0x08,0x00, - 0x00,0x00,0x52,0x04,0x00,0x00,0xd1,0x08,0x10,0x04,0x08,0x00,0x08,0xdc,0x10,0x04, - 0x08,0x00,0x08,0xe6,0xd3,0x10,0x52,0x04,0x08,0x00,0x91,0x08,0x10,0x04,0x00,0x00, - 0x08,0x00,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x08,0x00,0x08,0x00, - 0x08,0x00,0x54,0x04,0x08,0x00,0xd3,0x0c,0x52,0x04,0x08,0x00,0x11,0x04,0x14,0x00, - 0x00,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x08,0xe6,0x08,0x01,0x10,0x04,0x08,0xdc, - 0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x08,0x09,0xcf,0x86,0x95,0x28, - 0xd4,0x14,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x53,0x04,0x08,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x08,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x10,0x00, - 0x00,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x24,0xd3,0x14,0x52,0x04,0x10,0x00, - 0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0xe6,0x10,0x04,0x10,0xdc,0x00,0x00,0x92,0x0c, - 0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x52,0x04, - 0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd1,0x54, - 0xd0,0x26,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x52,0x04, - 0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, - 0x0b,0x00,0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x0b,0x00,0x93,0x0c, - 0x52,0x04,0x0b,0x00,0x11,0x04,0x0b,0x00,0x00,0x00,0x0b,0x00,0x54,0x04,0x0b,0x00, - 0x93,0x10,0x92,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00, - 0x0b,0x00,0xd0,0x42,0xcf,0x86,0xd5,0x28,0x54,0x04,0x10,0x00,0xd3,0x0c,0x92,0x08, - 0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00, - 0x10,0x00,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14, - 0x53,0x04,0x00,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00, - 0x10,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x96,0xd2,0x68,0xd1,0x24,0xd0,0x06, - 0xcf,0x06,0x0b,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x0b,0x00,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xd0,0x1e,0xcf,0x86,0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0x93,0x10,0x92,0x0c, - 0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86, - 0x55,0x04,0x11,0x00,0x54,0x04,0x11,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x11,0x00, - 0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x11,0x00, - 0x11,0x00,0xd1,0x28,0xd0,0x22,0xcf,0x86,0x55,0x04,0x14,0x00,0xd4,0x0c,0x93,0x08, - 0x12,0x04,0x14,0x00,0x14,0xe6,0x00,0x00,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04, - 0x14,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a, - 0xd1,0x24,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04, - 0x0b,0x00,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04, - 0x0b,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x58,0xd0,0x12,0xcf,0x86,0x55,0x04, - 0x14,0x00,0x94,0x08,0x13,0x04,0x14,0x00,0x00,0x00,0x14,0x00,0xcf,0x86,0x95,0x40, - 0xd4,0x24,0xd3,0x0c,0x52,0x04,0x14,0x00,0x11,0x04,0x14,0x00,0x14,0xdc,0xd2,0x0c, - 0x51,0x04,0x14,0xe6,0x10,0x04,0x14,0xe6,0x14,0xdc,0x91,0x08,0x10,0x04,0x14,0xe6, - 0x14,0xdc,0x14,0xdc,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0xdc,0x14,0x00, - 0x14,0x00,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x15,0x00, - 0x93,0x10,0x52,0x04,0x15,0x00,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00, - 0x00,0x00,0xcf,0x86,0xe5,0x0f,0x06,0xe4,0xf8,0x03,0xe3,0x02,0x02,0xd2,0xfb,0xd1, - 0x4c,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0xd5,0x2c,0xd4,0x1c,0xd3,0x10,0x52, - 0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x09,0x0c,0x00,0x52,0x04,0x0c, - 0x00,0x11,0x04,0x0c,0x00,0x00,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x0c, - 0x00,0x0c,0x00,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00, - 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x09,0xd0,0x69,0xcf,0x86,0xd5, - 0x32,0x54,0x04,0x0b,0x00,0x53,0x04,0x0b,0x00,0xd2,0x15,0x51,0x04,0x0b,0x00,0x10, - 0x0d,0x0b,0xff,0xf0,0x91,0x82,0x99,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x91,0x11, - 0x10,0x0d,0x0b,0xff,0xf0,0x91,0x82,0x9b,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x0b, - 0x00,0xd4,0x1d,0x53,0x04,0x0b,0x00,0x92,0x15,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b, - 0x00,0x0b,0xff,0xf0,0x91,0x82,0xa5,0xf0,0x91,0x82,0xba,0x00,0x0b,0x00,0x53,0x04, - 0x0b,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0b,0x09,0x10,0x04,0x0b,0x07, - 0x0b,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x20,0x94,0x1c,0xd3,0x0c,0x92,0x08,0x11,0x04, - 0x0b,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00, - 0x14,0x00,0x00,0x00,0x0d,0x00,0xd4,0x14,0x53,0x04,0x0d,0x00,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x08, - 0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0xd1,0x96,0xd0,0x5c,0xcf,0x86,0xd5,0x18, - 0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x0d,0xe6,0x10,0x04,0x0d,0xe6,0x0d,0x00, - 0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd4,0x26,0x53,0x04,0x0d,0x00,0x52,0x04,0x0d,0x00, - 0x51,0x04,0x0d,0x00,0x10,0x0d,0x0d,0xff,0xf0,0x91,0x84,0xb1,0xf0,0x91,0x84,0xa7, - 0x00,0x0d,0xff,0xf0,0x91,0x84,0xb2,0xf0,0x91,0x84,0xa7,0x00,0x93,0x18,0xd2,0x0c, - 0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x0d,0x09,0x91,0x08,0x10,0x04,0x0d,0x09, - 0x00,0x00,0x0d,0x00,0x0d,0x00,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04, - 0x0d,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x10,0x00, - 0x54,0x04,0x10,0x00,0x93,0x18,0xd2,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00, - 0x10,0x07,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0,0x06, - 0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x40,0xd4,0x2c,0xd3,0x10,0x92,0x0c,0x91,0x08, - 0x10,0x04,0x0d,0x09,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04, - 0x0d,0x00,0x11,0x00,0x10,0x04,0x11,0x07,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00, - 0x10,0x00,0x00,0x00,0x53,0x04,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04, - 0x10,0x00,0x11,0x00,0x11,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x93,0x10,0x52,0x04,0x10,0x00, - 0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xc8,0xd1,0x48, - 0xd0,0x42,0xcf,0x86,0xd5,0x18,0x54,0x04,0x10,0x00,0x93,0x10,0x92,0x0c,0x51,0x04, - 0x10,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x54,0x04,0x10,0x00, - 0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0x09,0x10,0x04, - 0x10,0x07,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x12,0x00, - 0x00,0x00,0xcf,0x06,0x00,0x00,0xd0,0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x28,0xd3,0x10, - 0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04, - 0x00,0x00,0x11,0x00,0x53,0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00, - 0x10,0x04,0x00,0x00,0x11,0x00,0x94,0x10,0x53,0x04,0x11,0x00,0x92,0x08,0x11,0x04, - 0x11,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00,0xd4,0x18, - 0x53,0x04,0x10,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x10,0x00,0x10,0x07,0x10,0x04, - 0x10,0x09,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00, - 0x00,0x00,0x00,0x00,0xe1,0x27,0x01,0xd0,0x8a,0xcf,0x86,0xd5,0x44,0xd4,0x2c,0xd3, - 0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x10,0x00,0x10,0x00,0x91,0x08,0x10, - 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10,0x00,0xd1,0x08,0x10,0x04,0x10, - 0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x93,0x14,0x92,0x10,0xd1,0x08,0x10, - 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0xd4, - 0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10, - 0x00,0x10,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10, - 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd2,0x0c,0x51,0x04,0x10, - 0x00,0x10,0x04,0x00,0x00,0x14,0x07,0x91,0x08,0x10,0x04,0x10,0x07,0x10,0x00,0x10, - 0x00,0xcf,0x86,0xd5,0x6a,0xd4,0x42,0xd3,0x14,0x52,0x04,0x10,0x00,0xd1,0x08,0x10, - 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0xd2,0x19,0xd1,0x08,0x10, - 0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0xff,0xf0,0x91,0x8d,0x87,0xf0, - 0x91,0x8c,0xbe,0x00,0x91,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x8d,0x87,0xf0,0x91, - 0x8d,0x97,0x00,0x10,0x09,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11, - 0x00,0x00,0x00,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x52, - 0x04,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd4,0x1c,0xd3, - 0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x00,0x00,0x10,0xe6,0x52,0x04,0x10,0xe6,0x91, - 0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x10,0xe6,0x91, - 0x08,0x10,0x04,0x10,0xe6,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3, - 0x30,0x01,0xd2,0xb7,0xd1,0x48,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x95,0x3c, - 0xd4,0x1c,0x93,0x18,0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x09,0x12,0x00, - 0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x07,0x12,0x00,0x12,0x00,0x53,0x04,0x12,0x00, - 0xd2,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x00,0x00,0x12,0x00,0xd1,0x08,0x10,0x04, - 0x00,0x00,0x12,0x00,0x10,0x04,0x14,0xe6,0x15,0x00,0x00,0x00,0xd0,0x45,0xcf,0x86, - 0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0xd2,0x15,0x51,0x04, - 0x10,0x00,0x10,0x04,0x10,0x00,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xba, - 0x00,0xd1,0x11,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xb0,0x00, - 0x10,0x00,0x10,0x0d,0x10,0xff,0xf0,0x91,0x92,0xb9,0xf0,0x91,0x92,0xbd,0x00,0x10, - 0x00,0xcf,0x86,0x95,0x24,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10, - 0x04,0x10,0x09,0x10,0x07,0x10,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11, - 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0, - 0x40,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x0c,0x52,0x04,0x10, - 0x00,0x11,0x04,0x10,0x00,0x00,0x00,0xd2,0x1e,0x51,0x04,0x10,0x00,0x10,0x0d,0x10, - 0xff,0xf0,0x91,0x96,0xb8,0xf0,0x91,0x96,0xaf,0x00,0x10,0xff,0xf0,0x91,0x96,0xb9, - 0xf0,0x91,0x96,0xaf,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10,0x09,0xcf, - 0x86,0x95,0x2c,0xd4,0x1c,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x07,0x10, - 0x00,0x10,0x00,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0x53, - 0x04,0x11,0x00,0x52,0x04,0x11,0x00,0x11,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0xd2, - 0xa0,0xd1,0x5c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x53, - 0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x10, - 0x09,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x93,0x10,0x52,0x04,0x10,0x00,0x91,0x08,0x10, - 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11, - 0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12, - 0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x2a,0xcf, - 0x86,0x55,0x04,0x0d,0x00,0x54,0x04,0x0d,0x00,0xd3,0x10,0x52,0x04,0x0d,0x00,0x51, - 0x04,0x0d,0x00,0x10,0x04,0x0d,0x09,0x0d,0x07,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x95,0x14,0x94,0x10,0x53,0x04,0x0d, - 0x00,0x92,0x08,0x11,0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, - 0x40,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0x54,0x04,0x11,0x00,0x53,0x04,0x11,0x00,0xd2, - 0x0c,0x51,0x04,0x11,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00, - 0x00,0x11,0x00,0x11,0x00,0x94,0x14,0x53,0x04,0x11,0x00,0x92,0x0c,0x51,0x04,0x11, - 0x00,0x10,0x04,0x11,0x00,0x11,0x09,0x00,0x00,0x11,0x00,0xcf,0x06,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xe4,0x59,0x01,0xd3,0xb2,0xd2,0x5c,0xd1,0x28,0xd0,0x22,0xcf,0x86, - 0x55,0x04,0x14,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14,0x00,0x92,0x10,0xd1,0x08, - 0x10,0x04,0x14,0x00,0x14,0x09,0x10,0x04,0x14,0x07,0x14,0x00,0x00,0x00,0xcf,0x06, - 0x00,0x00,0xd0,0x0a,0xcf,0x86,0x15,0x04,0x00,0x00,0x10,0x00,0xcf,0x86,0x55,0x04, - 0x10,0x00,0x54,0x04,0x10,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04, - 0x10,0x00,0x00,0x00,0x00,0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04, - 0x00,0x00,0x10,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04, - 0x00,0x00,0x94,0x10,0x53,0x04,0x15,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00, - 0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x14,0x54,0x04,0x15,0x00,0x53,0x04,0x15,0x00, - 0x92,0x08,0x11,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x94,0x1c,0x93,0x18,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x15,0x09,0x15,0x00,0x15,0x00,0x91,0x08,0x10,0x04,0x15,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd2,0xa0,0xd1,0x3c,0xd0,0x1e,0xcf,0x86, - 0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x93,0x10,0x52,0x04,0x13,0x00,0x91,0x08, - 0x10,0x04,0x13,0x09,0x13,0x00,0x13,0x00,0x13,0x00,0xcf,0x86,0x95,0x18,0x94,0x14, - 0x93,0x10,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x13,0x09, - 0x00,0x00,0x13,0x00,0x13,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x2c,0xd4,0x10,0x93,0x0c, - 0x52,0x04,0x13,0x00,0x11,0x04,0x15,0x00,0x13,0x00,0x13,0x00,0x53,0x04,0x13,0x00, - 0xd2,0x0c,0x91,0x08,0x10,0x04,0x13,0x00,0x13,0x09,0x13,0x00,0x91,0x08,0x10,0x04, - 0x13,0x00,0x14,0x00,0x13,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x13,0x00, - 0x10,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04, - 0x10,0x00,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3,0xa9,0x01,0xd2, - 0xb0,0xd1,0x6c,0xd0,0x3e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x53,0x04,0x12,0x00,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x54, - 0x04,0x12,0x00,0xd3,0x10,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12, - 0x00,0x00,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x12, - 0x09,0xcf,0x86,0xd5,0x14,0x94,0x10,0x93,0x0c,0x52,0x04,0x12,0x00,0x11,0x04,0x12, - 0x00,0x00,0x00,0x00,0x00,0x12,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12, - 0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x12,0x00,0xd0,0x3e,0xcf, - 0x86,0xd5,0x14,0x54,0x04,0x12,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x00,0x00,0x12, - 0x00,0x12,0x00,0x12,0x00,0xd4,0x14,0x53,0x04,0x12,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x12,0x00,0x12,0x00,0x12,0x00,0x93,0x10,0x52,0x04,0x12,0x00,0x51, - 0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1, - 0xa0,0xd0,0x52,0xcf,0x86,0xd5,0x24,0x94,0x20,0xd3,0x10,0x52,0x04,0x13,0x00,0x51, - 0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x13,0x00,0x10, - 0x04,0x00,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x54,0x04,0x13,0x00,0xd3,0x10,0x52, - 0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0xd2,0x0c,0x51, - 0x04,0x00,0x00,0x10,0x04,0x13,0x00,0x00,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x00, - 0x00,0x13,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x18,0x93,0x14,0xd2,0x0c,0x51,0x04,0x13, - 0x00,0x10,0x04,0x13,0x07,0x13,0x00,0x11,0x04,0x13,0x09,0x13,0x00,0x00,0x00,0x53, - 0x04,0x13,0x00,0x92,0x08,0x11,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x94,0x20,0xd3, - 0x10,0x52,0x04,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd0, - 0x52,0xcf,0x86,0xd5,0x3c,0xd4,0x14,0x53,0x04,0x14,0x00,0x52,0x04,0x14,0x00,0x51, - 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x14, - 0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x14, - 0x09,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94, - 0x10,0x53,0x04,0x14,0x00,0x92,0x08,0x11,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf, - 0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x14,0x00,0x53,0x04,0x14, - 0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd1, - 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x15, - 0x00,0x54,0x04,0x15,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04,0x15,0x00,0x00,0x00,0x00, - 0x00,0x52,0x04,0x00,0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0xd0, - 0xca,0xcf,0x86,0xd5,0xc2,0xd4,0x54,0xd3,0x06,0xcf,0x06,0x09,0x00,0xd2,0x06,0xcf, - 0x06,0x09,0x00,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09, - 0x00,0x94,0x14,0x53,0x04,0x09,0x00,0x52,0x04,0x09,0x00,0x51,0x04,0x09,0x00,0x10, - 0x04,0x09,0x00,0x10,0x00,0x10,0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x10, - 0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x11,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x68,0xd2,0x46,0xd1,0x40,0xd0, - 0x06,0xcf,0x06,0x09,0x00,0xcf,0x86,0x55,0x04,0x09,0x00,0xd4,0x20,0xd3,0x10,0x92, - 0x0c,0x51,0x04,0x09,0x00,0x10,0x04,0x09,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10, - 0x00,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x93,0x10,0x52,0x04,0x09, - 0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x11, - 0x00,0xd1,0x1c,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x95,0x10,0x94,0x0c,0x93, - 0x08,0x12,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x4c,0xd4,0x06,0xcf, - 0x06,0x0b,0x00,0xd3,0x40,0xd2,0x3a,0xd1,0x34,0xd0,0x2e,0xcf,0x86,0x55,0x04,0x0b, - 0x00,0xd4,0x14,0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10, - 0x04,0x0b,0x00,0x00,0x00,0x53,0x04,0x15,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x15, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x4c,0xd0,0x44,0xcf, - 0x86,0xd5,0x3c,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2, - 0x2a,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x11,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x93, - 0x10,0x52,0x04,0x11,0x00,0x51,0x04,0x11,0x00,0x10,0x04,0x11,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xe0,0xd2,0x01,0xcf,0x86,0xd5,0x06,0xcf,0x06, - 0x00,0x00,0xe4,0x0b,0x01,0xd3,0x06,0xcf,0x06,0x0c,0x00,0xd2,0x84,0xd1,0x50,0xd0, - 0x1e,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x92, - 0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5, - 0x18,0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x51,0x04,0x10, - 0x00,0x10,0x04,0x10,0x00,0x00,0x00,0x94,0x14,0x53,0x04,0x10,0x00,0xd2,0x08,0x11, - 0x04,0x10,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x10,0x00,0x00,0x00,0xd0,0x06,0xcf, - 0x06,0x00,0x00,0xcf,0x86,0xd5,0x08,0x14,0x04,0x00,0x00,0x10,0x00,0xd4,0x10,0x53, - 0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00,0x00,0x93,0x10,0x52, - 0x04,0x10,0x01,0x91,0x08,0x10,0x04,0x10,0x01,0x10,0x00,0x00,0x00,0x00,0x00,0xd1, - 0x6c,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x10,0x00,0x54,0x04,0x10,0x00,0x93,0x10,0x52, - 0x04,0x10,0xe6,0x51,0x04,0x10,0xe6,0x10,0x04,0x10,0xe6,0x10,0x00,0x10,0x00,0xcf, - 0x86,0xd5,0x24,0xd4,0x10,0x93,0x0c,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00, - 0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x00, - 0x00,0x10,0x00,0x10,0x00,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51,0x04,0x10,0x00,0x10, - 0x04,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x00, - 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x10,0x00,0x10,0x00,0xd0,0x0e,0xcf,0x86,0x95, - 0x08,0x14,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf, - 0x06,0x00,0x00,0xd2,0x30,0xd1,0x0c,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x06,0x14, - 0x00,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04,0x14,0x00,0x53,0x04,0x14,0x00,0x92, - 0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xd1,0x4c,0xd0,0x06,0xcf,0x06,0x0d,0x00,0xcf,0x86,0xd5,0x2c,0x94, - 0x28,0xd3,0x10,0x52,0x04,0x0d,0x00,0x91,0x08,0x10,0x04,0x0d,0x00,0x15,0x00,0x15, - 0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x51,0x04,0x00, - 0x00,0x10,0x04,0x00,0x00,0x15,0x00,0x0d,0x00,0x54,0x04,0x0d,0x00,0x53,0x04,0x0d, - 0x00,0x52,0x04,0x0d,0x00,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x15,0x00,0xd0, - 0x1e,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x15,0x00,0x52,0x04,0x00,0x00,0x51, - 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x00,0x00,0xcf,0x86,0x55, - 0x04,0x00,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x12,0x00,0x13, - 0x00,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xcf,0x06,0x12,0x00,0xe2, - 0xc6,0x01,0xd1,0x8e,0xd0,0x86,0xcf,0x86,0xd5,0x48,0xd4,0x06,0xcf,0x06,0x12,0x00, - 0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x06,0xcf,0x06,0x12,0x00,0xd1,0x06,0xcf,0x06, - 0x12,0x00,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12,0x00,0xd4,0x14, - 0x53,0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x12,0x00,0x14,0x00, - 0x14,0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0x00,0x00, - 0xd4,0x36,0xd3,0x06,0xcf,0x06,0x12,0x00,0xd2,0x2a,0xd1,0x06,0xcf,0x06,0x12,0x00, - 0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x55,0x04,0x12,0x00,0x54,0x04,0x12,0x00, - 0x93,0x10,0x92,0x0c,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00, - 0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0xa2,0xd4,0x9c,0xd3,0x74, - 0xd2,0x26,0xd1,0x20,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x94,0x10,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x0c,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0x13,0x00,0xcf,0x06, - 0x13,0x00,0xcf,0x06,0x13,0x00,0xd1,0x48,0xd0,0x1e,0xcf,0x86,0x95,0x18,0x54,0x04, - 0x13,0x00,0x53,0x04,0x13,0x00,0x52,0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04, - 0x13,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0xd5,0x18,0x54,0x04,0x00,0x00,0x93,0x10, - 0x92,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x94,0x0c,0x93,0x08,0x12,0x04,0x00,0x00,0x15,0x00,0x00,0x00,0x13,0x00,0xcf,0x06, - 0x13,0x00,0xd2,0x22,0xd1,0x06,0xcf,0x06,0x13,0x00,0xd0,0x06,0xcf,0x06,0x13,0x00, - 0xcf,0x86,0x55,0x04,0x13,0x00,0x54,0x04,0x13,0x00,0x53,0x04,0x13,0x00,0x12,0x04, - 0x13,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06, - 0x00,0x00,0xd3,0x7f,0xd2,0x79,0xd1,0x34,0xd0,0x06,0xcf,0x06,0x10,0x00,0xcf,0x86, - 0x55,0x04,0x10,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00, - 0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00, - 0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd0,0x3f,0xcf,0x86,0xd5,0x2c, - 0xd4,0x14,0x53,0x04,0x10,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x53,0x04,0x10,0x00,0xd2,0x08,0x11,0x04,0x10,0x00,0x00,0x00, - 0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x01,0x10,0x00,0x94,0x0d,0x93,0x09,0x12,0x05, - 0x10,0xff,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xe1,0x96,0x04,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, - 0xcf,0x86,0xe5,0x33,0x04,0xe4,0x83,0x02,0xe3,0xf8,0x01,0xd2,0x26,0xd1,0x06,0xcf, - 0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x55,0x04,0x05,0x00,0x54, - 0x04,0x05,0x00,0x93,0x0c,0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x00,0x00,0x00, - 0x00,0xd1,0xef,0xd0,0x2a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94,0x20,0xd3,0x10,0x52, - 0x04,0x05,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x00,0x00,0x0a,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0xd5, - 0x2a,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52,0x04,0x05,0x00,0x51,0x04,0x05, - 0x00,0x10,0x0d,0x05,0xff,0xf0,0x9d,0x85,0x97,0xf0,0x9d,0x85,0xa5,0x00,0x05,0xff, - 0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0x00,0xd4,0x75,0xd3,0x61,0xd2,0x44,0xd1, - 0x22,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85, - 0xae,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xaf, - 0x00,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85, - 0xb0,0x00,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xb1, - 0x00,0xd1,0x15,0x10,0x11,0x05,0xff,0xf0,0x9d,0x85,0x98,0xf0,0x9d,0x85,0xa5,0xf0, - 0x9d,0x85,0xb2,0x00,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0x01,0xd2,0x08,0x11,0x04, - 0x05,0x01,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe2,0x05,0xd8,0xd3,0x12, - 0x92,0x0d,0x51,0x04,0x05,0xd8,0x10,0x04,0x05,0xd8,0x05,0xff,0x00,0x05,0xff,0x00, - 0x92,0x0e,0x51,0x05,0x05,0xff,0x00,0x10,0x05,0x05,0xff,0x00,0x05,0xdc,0x05,0xdc, - 0xd0,0x97,0xcf,0x86,0xd5,0x28,0x94,0x24,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x05,0xdc, - 0x10,0x04,0x05,0xdc,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x05,0xe6,0x05,0xe6, - 0x92,0x08,0x11,0x04,0x05,0xe6,0x05,0xdc,0x05,0x00,0x05,0x00,0xd4,0x14,0x53,0x04, - 0x05,0x00,0xd2,0x08,0x11,0x04,0x05,0x00,0x05,0xe6,0x11,0x04,0x05,0xe6,0x05,0x00, - 0x53,0x04,0x05,0x00,0xd2,0x15,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x05,0xff, - 0xf0,0x9d,0x86,0xb9,0xf0,0x9d,0x85,0xa5,0x00,0xd1,0x1e,0x10,0x0d,0x05,0xff,0xf0, - 0x9d,0x86,0xba,0xf0,0x9d,0x85,0xa5,0x00,0x05,0xff,0xf0,0x9d,0x86,0xb9,0xf0,0x9d, - 0x85,0xa5,0xf0,0x9d,0x85,0xae,0x00,0x10,0x11,0x05,0xff,0xf0,0x9d,0x86,0xba,0xf0, - 0x9d,0x85,0xa5,0xf0,0x9d,0x85,0xae,0x00,0x05,0xff,0xf0,0x9d,0x86,0xb9,0xf0,0x9d, - 0x85,0xa5,0xf0,0x9d,0x85,0xaf,0x00,0xcf,0x86,0xd5,0x31,0xd4,0x21,0x93,0x1d,0x92, - 0x19,0x91,0x15,0x10,0x11,0x05,0xff,0xf0,0x9d,0x86,0xba,0xf0,0x9d,0x85,0xa5,0xf0, - 0x9d,0x85,0xaf,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x53,0x04,0x05,0x00, - 0x52,0x04,0x05,0x00,0x11,0x04,0x05,0x00,0x11,0x00,0x94,0x14,0x53,0x04,0x11,0x00, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xd2,0x44,0xd1,0x28,0xd0,0x06,0xcf,0x06,0x08,0x00,0xcf,0x86,0x95,0x1c,0x94,0x18, - 0x93,0x14,0xd2,0x08,0x11,0x04,0x08,0x00,0x08,0xe6,0x91,0x08,0x10,0x04,0x08,0xe6, - 0x08,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00, - 0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x14,0x00,0x93,0x08,0x12,0x04,0x14,0x00, - 0x00,0x00,0x00,0x00,0xd1,0x40,0xd0,0x06,0xcf,0x06,0x07,0x00,0xcf,0x86,0xd5,0x18, - 0x54,0x04,0x07,0x00,0x93,0x10,0x52,0x04,0x07,0x00,0x51,0x04,0x07,0x00,0x10,0x04, - 0x07,0x00,0x00,0x00,0x00,0x00,0x54,0x04,0x09,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04, - 0x09,0x00,0x14,0x00,0x14,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xe3,0x5f,0x01,0xd2,0xb4,0xd1,0x24,0xd0, - 0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x95,0x18,0x54,0x04,0x05,0x00,0x93,0x10,0x52, - 0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x05,0x00,0x05, - 0x00,0xd0,0x6a,0xcf,0x86,0xd5,0x18,0x54,0x04,0x05,0x00,0x53,0x04,0x05,0x00,0x52, - 0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0xd4,0x34,0xd3, - 0x1c,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0xd1,0x08,0x10, - 0x04,0x00,0x00,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0xd2,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x05,0x00,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05, - 0x00,0x53,0x04,0x05,0x00,0xd2,0x0c,0x51,0x04,0x05,0x00,0x10,0x04,0x00,0x00,0x05, - 0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0xcf,0x86,0x95,0x20,0x94, - 0x1c,0x93,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x05,0x00,0x07,0x00,0x05,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0x05,0x00,0xd1, - 0xa4,0xd0,0x6a,0xcf,0x86,0xd5,0x48,0xd4,0x28,0xd3,0x10,0x52,0x04,0x05,0x00,0x51, - 0x04,0x05,0x00,0x10,0x04,0x00,0x00,0x05,0x00,0xd2,0x0c,0x51,0x04,0x05,0x00,0x10, - 0x04,0x05,0x00,0x00,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0xd3, - 0x10,0x52,0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x52, - 0x04,0x05,0x00,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x54,0x04,0x05, - 0x00,0x53,0x04,0x05,0x00,0xd2,0x0c,0x51,0x04,0x05,0x00,0x10,0x04,0x00,0x00,0x05, - 0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00,0x00,0x00,0xcf,0x86,0x95,0x34,0xd4, - 0x20,0xd3,0x14,0x52,0x04,0x05,0x00,0xd1,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x10, - 0x04,0x05,0x00,0x00,0x00,0x92,0x08,0x11,0x04,0x00,0x00,0x05,0x00,0x05,0x00,0x93, - 0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x05,0x00,0x00,0x00,0x05,0x00,0x05,0x00,0x05, - 0x00,0x05,0x00,0xcf,0x06,0x05,0x00,0xd2,0x26,0xd1,0x06,0xcf,0x06,0x05,0x00,0xd0, - 0x1a,0xcf,0x86,0x55,0x04,0x05,0x00,0x94,0x10,0x93,0x0c,0x52,0x04,0x05,0x00,0x11, - 0x04,0x08,0x00,0x00,0x00,0x05,0x00,0x05,0x00,0xcf,0x06,0x05,0x00,0xd1,0x06,0xcf, - 0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53, - 0x04,0x05,0x00,0xd2,0x08,0x11,0x04,0x05,0x00,0x09,0x00,0x11,0x04,0x00,0x00,0x05, - 0x00,0x05,0x00,0x05,0x00,0xd4,0x52,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2,0x46,0xd1, - 0x06,0xcf,0x06,0x11,0x00,0xd0,0x3a,0xcf,0x86,0xd5,0x20,0xd4,0x0c,0x53,0x04,0x11, - 0x00,0x12,0x04,0x11,0x00,0x00,0x00,0x53,0x04,0x00,0x00,0x92,0x0c,0x51,0x04,0x00, - 0x00,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x00,0x00,0x11,0x00,0x11,0x00,0x11,0x00,0x11,0x00,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xe0,0xc2,0x03,0xcf,0x86, - 0xe5,0x03,0x01,0xd4,0xfc,0xd3,0xc0,0xd2,0x66,0xd1,0x60,0xd0,0x5a,0xcf,0x86,0xd5, - 0x2c,0xd4,0x14,0x93,0x10,0x52,0x04,0x12,0xe6,0x51,0x04,0x12,0xe6,0x10,0x04,0x12, - 0xe6,0x00,0x00,0x12,0xe6,0x53,0x04,0x12,0xe6,0x92,0x10,0xd1,0x08,0x10,0x04,0x12, - 0xe6,0x00,0x00,0x10,0x04,0x00,0x00,0x12,0xe6,0x12,0xe6,0x94,0x28,0xd3,0x18,0xd2, - 0x0c,0x51,0x04,0x12,0xe6,0x10,0x04,0x00,0x00,0x12,0xe6,0x91,0x08,0x10,0x04,0x12, - 0xe6,0x00,0x00,0x12,0xe6,0x92,0x0c,0x51,0x04,0x12,0xe6,0x10,0x04,0x12,0xe6,0x00, - 0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0x54,0xd0, - 0x36,0xcf,0x86,0x55,0x04,0x15,0x00,0xd4,0x14,0x53,0x04,0x15,0x00,0x52,0x04,0x15, - 0x00,0x91,0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd3,0x10,0x52,0x04,0x15, - 0xe6,0x51,0x04,0x15,0xe6,0x10,0x04,0x15,0xe6,0x15,0x00,0x52,0x04,0x15,0x00,0x11, - 0x04,0x15,0x00,0x00,0x00,0xcf,0x86,0x95,0x18,0x94,0x14,0x53,0x04,0x15,0x00,0xd2, - 0x08,0x11,0x04,0x15,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x15,0x00,0x00,0x00,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xd2,0x36,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf, - 0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x15,0x00,0xd4,0x0c,0x53,0x04,0x15,0x00,0x12, - 0x04,0x15,0x00,0x15,0xe6,0x53,0x04,0x15,0x00,0xd2,0x08,0x11,0x04,0x15,0x00,0x00, - 0x00,0x51,0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x15,0x00,0xcf,0x06,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xd4,0x82,0xd3,0x7c,0xd2,0x3e,0xd1,0x06,0xcf,0x06,0x10,0x00,0xd0, - 0x06,0xcf,0x06,0x10,0x00,0xcf,0x86,0x95,0x2c,0xd4,0x18,0x93,0x14,0x52,0x04,0x10, - 0x00,0xd1,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x10,0x00,0x10, - 0x00,0x93,0x10,0x52,0x04,0x10,0xdc,0x51,0x04,0x10,0xdc,0x10,0x04,0x10,0xdc,0x00, - 0x00,0x00,0x00,0x00,0x00,0xd1,0x38,0xd0,0x06,0xcf,0x06,0x12,0x00,0xcf,0x86,0x95, - 0x2c,0xd4,0x18,0xd3,0x08,0x12,0x04,0x12,0x00,0x12,0xe6,0x92,0x0c,0x51,0x04,0x12, - 0xe6,0x10,0x04,0x12,0x07,0x15,0x00,0x00,0x00,0x53,0x04,0x12,0x00,0xd2,0x08,0x11, - 0x04,0x12,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x12,0x00,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xd3,0x82,0xd2,0x48,0xd1,0x24,0xd0,0x06,0xcf,0x06,0x00, - 0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x93,0x10,0x92,0x0c,0x91, - 0x08,0x10,0x04,0x00,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0x14,0x00,0xd0,0x1e,0xcf, - 0x86,0x55,0x04,0x14,0x00,0x54,0x04,0x14,0x00,0x93,0x10,0x52,0x04,0x14,0x00,0x91, - 0x08,0x10,0x04,0x14,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1, - 0x34,0xd0,0x2e,0xcf,0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0x15,0x00,0x54,0x04,0x15, - 0x00,0x53,0x04,0x15,0x00,0x52,0x04,0x15,0x00,0x11,0x04,0x15,0x00,0x00,0x00,0xcf, - 0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xe2,0xb2,0x01,0xe1,0x41,0x01,0xd0,0x6e,0xcf, - 0x86,0xd5,0x18,0x94,0x14,0x93,0x10,0x52,0x04,0x0d,0x00,0x91,0x08,0x10,0x04,0x00, - 0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd4,0x30,0xd3,0x20,0xd2,0x10,0xd1, - 0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0xd1,0x08,0x10, - 0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x92,0x0c,0x91,0x08,0x10, - 0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x0d,0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0d, - 0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x0d,0x00,0x92,0x10,0xd1,0x08,0x10,0x04,0x00, - 0x00,0x0d,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x00,0x00,0xcf,0x86,0xd5,0x74,0xd4, - 0x34,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x00,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x51, - 0x04,0x00,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00, - 0x00,0x0d,0x00,0x10,0x04,0x00,0x00,0x0d,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x0d, - 0x00,0x0d,0x00,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10, - 0x04,0x0d,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x00, - 0x00,0x0d,0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10,0x04,0x00, - 0x00,0x0d,0x00,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10,0x04,0x00,0x00,0x0d, - 0x00,0xd4,0x30,0xd3,0x20,0xd2,0x10,0xd1,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x10, - 0x04,0x0d,0x00,0x00,0x00,0xd1,0x08,0x10,0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x00, - 0x00,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x0d, - 0x00,0xd3,0x10,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0x0d, - 0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0xd1,0x08,0x10, - 0x04,0x0d,0x00,0x00,0x00,0x10,0x04,0x0d,0x00,0x00,0x00,0xd0,0x56,0xcf,0x86,0xd5, - 0x20,0xd4,0x14,0x53,0x04,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10,0x04,0x00, - 0x00,0x0d,0x00,0x0d,0x00,0x53,0x04,0x0d,0x00,0x12,0x04,0x0d,0x00,0x00,0x00,0xd4, - 0x28,0xd3,0x18,0xd2,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x92,0x0c,0x51,0x04,0x0d,0x00,0x10, - 0x04,0x00,0x00,0x0d,0x00,0x0d,0x00,0x53,0x04,0x0d,0x00,0x12,0x04,0x0d,0x00,0x00, - 0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x93,0x0c,0x92,0x08,0x11, - 0x04,0x0d,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86,0xe5, - 0x96,0x05,0xe4,0x28,0x03,0xe3,0xed,0x01,0xd2,0xa0,0xd1,0x1c,0xd0,0x16,0xcf,0x86, - 0x55,0x04,0x0a,0x00,0x94,0x0c,0x53,0x04,0x0a,0x00,0x12,0x04,0x0a,0x00,0x00,0x00, - 0x0a,0x00,0xcf,0x06,0x0a,0x00,0xd0,0x46,0xcf,0x86,0xd5,0x10,0x54,0x04,0x0a,0x00, - 0x93,0x08,0x12,0x04,0x0a,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x0c,0x00, - 0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00,0xd3,0x10, - 0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x52,0x04, - 0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x10,0x00,0xcf,0x86,0xd5,0x28, - 0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00, - 0x0c,0x00,0x0c,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x00,0x00,0x0c,0x00, - 0x0c,0x00,0x0c,0x00,0x0c,0x00,0x54,0x04,0x10,0x00,0x93,0x0c,0x52,0x04,0x10,0x00, - 0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd1,0xe4,0xd0,0x5a,0xcf,0x86,0xd5,0x20, - 0x94,0x1c,0x53,0x04,0x0b,0x00,0xd2,0x0c,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, - 0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x0b,0x00,0xd4,0x14, - 0x53,0x04,0x0b,0x00,0x52,0x04,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04,0x0b,0x00, - 0x14,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0b,0x00,0x0c,0x00, - 0x0c,0x00,0x52,0x04,0x0c,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x0b,0x00,0x10,0x04, - 0x0c,0x00,0x0b,0x00,0xcf,0x86,0xd5,0x4c,0xd4,0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04, - 0x0c,0x00,0x10,0x04,0x0b,0x00,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0b,0x00, - 0x0c,0x00,0xd2,0x08,0x11,0x04,0x0c,0x00,0x0b,0x00,0x51,0x04,0x0b,0x00,0x10,0x04, - 0x0b,0x00,0x0c,0x00,0xd3,0x10,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04, - 0x0c,0x00,0x0b,0x00,0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, - 0x0b,0x00,0xd4,0x18,0x53,0x04,0x0c,0x00,0xd2,0x08,0x11,0x04,0x0c,0x00,0x0d,0x00, - 0x91,0x08,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x53,0x04,0x0c,0x00,0xd2,0x10, - 0xd1,0x08,0x10,0x04,0x0c,0x00,0x0b,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0xd1,0x08, - 0x10,0x04,0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x0b,0x00,0xd0,0x4e,0xcf,0x86, - 0xd5,0x34,0xd4,0x14,0x53,0x04,0x0c,0x00,0xd2,0x08,0x11,0x04,0x0c,0x00,0x0b,0x00, - 0x11,0x04,0x0b,0x00,0x0c,0x00,0xd3,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0b,0x00, - 0x0c,0x00,0x0c,0x00,0x0c,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, - 0x12,0x00,0x12,0x00,0x94,0x14,0x53,0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x91,0x08, - 0x10,0x04,0x12,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00, - 0x94,0x10,0x93,0x0c,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x0c,0x00,0x0c,0x00, - 0x0c,0x00,0xd2,0x7e,0xd1,0x78,0xd0,0x3e,0xcf,0x86,0xd5,0x1c,0x94,0x18,0x93,0x14, - 0x92,0x10,0xd1,0x08,0x10,0x04,0x0b,0x00,0x0c,0x00,0x10,0x04,0x0c,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x0b,0x00,0x54,0x04,0x0b,0x00,0xd3,0x0c,0x92,0x08,0x11,0x04, - 0x0b,0x00,0x0c,0x00,0x0c,0x00,0x92,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00, - 0x12,0x00,0x00,0x00,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x53,0x04,0x0b,0x00,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94,0x10,0x93,0x0c,0x52,0x04, - 0x13,0x00,0x11,0x04,0x13,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00, - 0xd1,0x58,0xd0,0x3a,0xcf,0x86,0x55,0x04,0x0c,0x00,0xd4,0x20,0xd3,0x10,0x92,0x0c, - 0x91,0x08,0x10,0x04,0x0c,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x52,0x04,0x10,0x00, - 0x91,0x08,0x10,0x04,0x10,0x00,0x11,0x00,0x11,0x00,0x93,0x10,0x52,0x04,0x0c,0x00, - 0x51,0x04,0x0c,0x00,0x10,0x04,0x10,0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x55,0x04, - 0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x52,0x04,0x0c,0x00,0x91,0x08, - 0x10,0x04,0x0c,0x00,0x10,0x00,0x11,0x00,0xd0,0x16,0xcf,0x86,0x95,0x10,0x54,0x04, - 0x0c,0x00,0x93,0x08,0x12,0x04,0x0c,0x00,0x10,0x00,0x10,0x00,0x0c,0x00,0xcf,0x86, - 0xd5,0x34,0xd4,0x28,0xd3,0x10,0x52,0x04,0x0c,0x00,0x91,0x08,0x10,0x04,0x0c,0x00, - 0x10,0x00,0x0c,0x00,0xd2,0x0c,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x10,0x00, - 0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0x93,0x08,0x12,0x04,0x11,0x00, - 0x10,0x00,0x10,0x00,0x54,0x04,0x0c,0x00,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04, - 0x0c,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x11,0x00,0xd3,0xfc,0xd2,0x6c,0xd1,0x3c, - 0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00, - 0x52,0x04,0x0c,0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x10,0x00,0xcf,0x86, - 0x95,0x18,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x10,0x00, - 0x0c,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xd0,0x06,0xcf,0x06,0x0c,0x00, - 0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0xd2,0x0c, - 0x91,0x08,0x10,0x04,0x10,0x00,0x0c,0x00,0x0c,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00, - 0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0xd1,0x54,0xd0,0x1a,0xcf,0x86,0x55,0x04, - 0x0c,0x00,0x54,0x04,0x0c,0x00,0x53,0x04,0x0c,0x00,0x52,0x04,0x0c,0x00,0x11,0x04, - 0x0c,0x00,0x10,0x00,0xcf,0x86,0xd5,0x1c,0x94,0x18,0xd3,0x08,0x12,0x04,0x0d,0x00, - 0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04,0x10,0x00,0x11,0x00,0x11,0x00, - 0x0c,0x00,0xd4,0x08,0x13,0x04,0x0c,0x00,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c, - 0x51,0x04,0x10,0x00,0x10,0x04,0x12,0x00,0x10,0x00,0x10,0x00,0xd0,0x1e,0xcf,0x86, - 0x55,0x04,0x10,0x00,0x94,0x14,0x93,0x10,0x52,0x04,0x10,0x00,0x91,0x08,0x10,0x04, - 0x12,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0x10,0x00,0xcf,0x86,0x55,0x04,0x10,0x00, - 0x54,0x04,0x10,0x00,0x53,0x04,0x10,0x00,0x92,0x0c,0x51,0x04,0x10,0x00,0x10,0x04, - 0x10,0x00,0x0c,0x00,0x0c,0x00,0xe2,0x19,0x01,0xd1,0xa8,0xd0,0x7e,0xcf,0x86,0xd5, - 0x4c,0xd4,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x0d,0x00,0x0c,0x00,0x0c, - 0x00,0x0c,0x00,0x0c,0x00,0xd3,0x1c,0xd2,0x0c,0x91,0x08,0x10,0x04,0x0c,0x00,0x0d, - 0x00,0x0c,0x00,0xd1,0x08,0x10,0x04,0x0c,0x00,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0d, - 0x00,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0c,0x00,0x0d,0x00,0x10,0x04,0x0c,0x00,0x0d, - 0x00,0x51,0x04,0x0c,0x00,0x10,0x04,0x0c,0x00,0x0d,0x00,0xd4,0x1c,0xd3,0x0c,0x52, - 0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x0d,0x00,0x52,0x04,0x0c,0x00,0x91,0x08,0x10, - 0x04,0x0d,0x00,0x0c,0x00,0x0d,0x00,0x93,0x10,0x52,0x04,0x0c,0x00,0x91,0x08,0x10, - 0x04,0x0d,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0xcf,0x86,0x95,0x24,0x94,0x20,0x93, - 0x1c,0xd2,0x10,0xd1,0x08,0x10,0x04,0x0c,0x00,0x10,0x00,0x10,0x04,0x10,0x00,0x11, - 0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x0c,0x00,0x0c,0x00,0x0c,0x00,0x10,0x00,0x10, - 0x00,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0xd5,0x30,0xd4,0x10,0x93,0x0c,0x52, - 0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x10,0x00,0x10,0x00,0x93,0x1c,0xd2,0x10,0xd1, - 0x08,0x10,0x04,0x11,0x00,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0x91,0x08,0x10, - 0x04,0x13,0x00,0x15,0x00,0x00,0x00,0x00,0x00,0xd4,0x14,0x53,0x04,0x10,0x00,0x52, - 0x04,0x10,0x00,0x91,0x08,0x10,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0xd3,0x10,0x52, - 0x04,0x10,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0x92,0x10,0xd1, - 0x08,0x10,0x04,0x13,0x00,0x14,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd1, - 0x1c,0xd0,0x06,0xcf,0x06,0x0c,0x00,0xcf,0x86,0x55,0x04,0x0c,0x00,0x54,0x04,0x0c, - 0x00,0x93,0x08,0x12,0x04,0x0c,0x00,0x00,0x00,0x00,0x00,0xd0,0x06,0xcf,0x06,0x10, - 0x00,0xcf,0x86,0xd5,0x24,0x54,0x04,0x10,0x00,0xd3,0x10,0x52,0x04,0x10,0x00,0x91, - 0x08,0x10,0x04,0x10,0x00,0x14,0x00,0x14,0x00,0x92,0x0c,0x91,0x08,0x10,0x04,0x14, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x94,0x0c,0x53,0x04,0x15,0x00,0x12,0x04,0x15, - 0x00,0x00,0x00,0x00,0x00,0xe4,0x40,0x02,0xe3,0xc9,0x01,0xd2,0x5c,0xd1,0x34,0xd0, - 0x16,0xcf,0x86,0x95,0x10,0x94,0x0c,0x53,0x04,0x10,0x00,0x12,0x04,0x10,0x00,0x00, - 0x00,0x10,0x00,0x10,0x00,0xcf,0x86,0x95,0x18,0xd4,0x08,0x13,0x04,0x10,0x00,0x00, - 0x00,0x53,0x04,0x10,0x00,0x92,0x08,0x11,0x04,0x10,0x00,0x00,0x00,0x00,0x00,0x10, - 0x00,0xd0,0x22,0xcf,0x86,0xd5,0x0c,0x94,0x08,0x13,0x04,0x10,0x00,0x00,0x00,0x10, - 0x00,0x94,0x10,0x53,0x04,0x10,0x00,0x52,0x04,0x10,0x00,0x11,0x04,0x10,0x00,0x00, - 0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xd1,0xc0,0xd0,0x5e,0xcf,0x86,0xd5,0x30,0xd4, - 0x14,0x53,0x04,0x13,0x00,0x52,0x04,0x13,0x00,0x91,0x08,0x10,0x04,0x00,0x00,0x15, - 0x00,0x15,0x00,0x53,0x04,0x11,0x00,0xd2,0x0c,0x91,0x08,0x10,0x04,0x11,0x00,0x12, - 0x00,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13,0x00,0xd4,0x08,0x13, - 0x04,0x12,0x00,0x13,0x00,0xd3,0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x12,0x00,0x13, - 0x00,0x10,0x04,0x13,0x00,0x12,0x00,0x12,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12, - 0x00,0x10,0x04,0x12,0x00,0x15,0x00,0xcf,0x86,0xd5,0x28,0xd4,0x14,0x53,0x04,0x12, - 0x00,0x52,0x04,0x12,0x00,0x91,0x08,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x53, - 0x04,0x12,0x00,0x52,0x04,0x12,0x00,0x51,0x04,0x12,0x00,0x10,0x04,0x12,0x00,0x13, - 0x00,0xd4,0x0c,0x53,0x04,0x13,0x00,0x12,0x04,0x13,0x00,0x14,0x00,0xd3,0x1c,0xd2, - 0x10,0xd1,0x08,0x10,0x04,0x14,0x00,0x15,0x00,0x10,0x04,0x00,0x00,0x14,0x00,0x51, - 0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x00,0x00,0x10, - 0x04,0x14,0x00,0x15,0x00,0x14,0x00,0xd0,0x62,0xcf,0x86,0xd5,0x24,0xd4,0x14,0x93, - 0x10,0x52,0x04,0x11,0x00,0x91,0x08,0x10,0x04,0x11,0x00,0x12,0x00,0x12,0x00,0x12, - 0x00,0x93,0x0c,0x92,0x08,0x11,0x04,0x12,0x00,0x13,0x00,0x13,0x00,0x14,0x00,0xd4, - 0x2c,0xd3,0x18,0xd2,0x0c,0x51,0x04,0x14,0x00,0x10,0x04,0x14,0x00,0x00,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10, - 0x04,0x15,0x00,0x00,0x00,0x11,0x04,0x00,0x00,0x15,0x00,0x53,0x04,0x14,0x00,0x92, - 0x08,0x11,0x04,0x14,0x00,0x15,0x00,0x15,0x00,0xcf,0x86,0xd5,0x30,0x94,0x2c,0xd3, - 0x14,0x92,0x10,0xd1,0x08,0x10,0x04,0x11,0x00,0x14,0x00,0x10,0x04,0x14,0x00,0x15, - 0x00,0x15,0x00,0xd2,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x91, - 0x08,0x10,0x04,0x00,0x00,0x15,0x00,0x15,0x00,0x13,0x00,0x94,0x14,0x93,0x10,0x52, - 0x04,0x13,0x00,0x51,0x04,0x13,0x00,0x10,0x04,0x13,0x00,0x14,0x00,0x14,0x00,0x14, - 0x00,0xd2,0x70,0xd1,0x40,0xd0,0x06,0xcf,0x06,0x15,0x00,0xcf,0x86,0xd5,0x10,0x54, - 0x04,0x15,0x00,0x93,0x08,0x12,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0xd4,0x10,0x53, - 0x04,0x14,0x00,0x52,0x04,0x14,0x00,0x11,0x04,0x14,0x00,0x00,0x00,0xd3,0x08,0x12, - 0x04,0x15,0x00,0x00,0x00,0x92,0x0c,0x51,0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00, - 0x00,0x00,0x00,0xd0,0x2a,0xcf,0x86,0x95,0x24,0xd4,0x14,0x93,0x10,0x92,0x0c,0x51, - 0x04,0x15,0x00,0x10,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x93,0x0c,0x52, - 0x04,0x15,0x00,0x11,0x04,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00, - 0x00,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00, - 0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55, - 0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11, - 0x04,0x00,0x00,0x02,0x00,0xe4,0xf9,0x12,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00, - 0xd2,0xc2,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x05,0x00,0xd0,0x44,0xcf,0x86,0xd5,0x3c, - 0xd4,0x06,0xcf,0x06,0x05,0x00,0xd3,0x06,0xcf,0x06,0x05,0x00,0xd2,0x2a,0xd1,0x06, - 0xcf,0x06,0x05,0x00,0xd0,0x06,0xcf,0x06,0x05,0x00,0xcf,0x86,0x95,0x18,0x54,0x04, - 0x05,0x00,0x93,0x10,0x52,0x04,0x05,0x00,0x51,0x04,0x05,0x00,0x10,0x04,0x05,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x0b,0x00,0xcf,0x06,0x0b,0x00,0xcf,0x86, - 0xd5,0x3c,0xd4,0x06,0xcf,0x06,0x0b,0x00,0xd3,0x06,0xcf,0x06,0x0b,0x00,0xd2,0x06, - 0xcf,0x06,0x0b,0x00,0xd1,0x24,0xd0,0x1e,0xcf,0x86,0x55,0x04,0x0b,0x00,0x54,0x04, - 0x0b,0x00,0x93,0x10,0x52,0x04,0x0b,0x00,0x91,0x08,0x10,0x04,0x0b,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xcf,0x06,0x0c,0x00,0xcf,0x06,0x0c,0x00,0xd4,0x32,0xd3,0x2c, - 0xd2,0x26,0xd1,0x20,0xd0,0x1a,0xcf,0x86,0x95,0x14,0x54,0x04,0x0c,0x00,0x53,0x04, - 0x0c,0x00,0x52,0x04,0x0c,0x00,0x11,0x04,0x0c,0x00,0x00,0x00,0x11,0x00,0xcf,0x06, - 0x11,0x00,0xcf,0x06,0x11,0x00,0xcf,0x06,0x11,0x00,0xcf,0x06,0x11,0x00,0xcf,0x06, - 0x11,0x00,0xd1,0x48,0xd0,0x40,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x11,0x00,0xd4,0x06, - 0xcf,0x06,0x11,0x00,0xd3,0x06,0xcf,0x06,0x11,0x00,0xd2,0x26,0xd1,0x06,0xcf,0x06, - 0x11,0x00,0xd0,0x1a,0xcf,0x86,0x55,0x04,0x11,0x00,0x94,0x10,0x93,0x0c,0x92,0x08, - 0x11,0x04,0x11,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x13,0x00,0xcf,0x06,0x13,0x00, - 0xcf,0x06,0x13,0x00,0xcf,0x86,0xcf,0x06,0x13,0x00,0xd0,0x44,0xcf,0x86,0xd5,0x06, - 0xcf,0x06,0x13,0x00,0xd4,0x36,0xd3,0x06,0xcf,0x06,0x13,0x00,0xd2,0x06,0xcf,0x06, - 0x13,0x00,0xd1,0x06,0xcf,0x06,0x13,0x00,0xd0,0x06,0xcf,0x06,0x13,0x00,0xcf,0x86, - 0x55,0x04,0x13,0x00,0x94,0x14,0x93,0x10,0x92,0x0c,0x91,0x08,0x10,0x04,0x13,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x86, - 0xd5,0x06,0xcf,0x06,0x00,0x00,0xe4,0x68,0x11,0xe3,0x51,0x10,0xe2,0x17,0x08,0xe1, - 0x06,0x04,0xe0,0x03,0x02,0xcf,0x86,0xe5,0x06,0x01,0xd4,0x82,0xd3,0x41,0xd2,0x21, - 0xd1,0x10,0x10,0x08,0x05,0xff,0xe4,0xb8,0xbd,0x00,0x05,0xff,0xe4,0xb8,0xb8,0x00, - 0x10,0x08,0x05,0xff,0xe4,0xb9,0x81,0x00,0x05,0xff,0xf0,0xa0,0x84,0xa2,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe4,0xbd,0xa0,0x00,0x05,0xff,0xe4,0xbe,0xae,0x00,0x10, - 0x08,0x05,0xff,0xe4,0xbe,0xbb,0x00,0x05,0xff,0xe5,0x80,0x82,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe5,0x81,0xba,0x00,0x05,0xff,0xe5,0x82,0x99,0x00,0x10, - 0x08,0x05,0xff,0xe5,0x83,0xa7,0x00,0x05,0xff,0xe5,0x83,0x8f,0x00,0xd1,0x11,0x10, - 0x08,0x05,0xff,0xe3,0x92,0x9e,0x00,0x05,0xff,0xf0,0xa0,0x98,0xba,0x00,0x10,0x08, - 0x05,0xff,0xe5,0x85,0x8d,0x00,0x05,0xff,0xe5,0x85,0x94,0x00,0xd3,0x42,0xd2,0x21, - 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x85,0xa4,0x00,0x05,0xff,0xe5,0x85,0xb7,0x00, - 0x10,0x09,0x05,0xff,0xf0,0xa0,0x94,0x9c,0x00,0x05,0xff,0xe3,0x92,0xb9,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe5,0x85,0xa7,0x00,0x05,0xff,0xe5,0x86,0x8d,0x00,0x10, - 0x09,0x05,0xff,0xf0,0xa0,0x95,0x8b,0x00,0x05,0xff,0xe5,0x86,0x97,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x86,0xa4,0x00,0x05,0xff,0xe4,0xbb,0x8c,0x00, - 0x10,0x08,0x05,0xff,0xe5,0x86,0xac,0x00,0x05,0xff,0xe5,0x86,0xb5,0x00,0xd1,0x11, - 0x10,0x09,0x05,0xff,0xf0,0xa9,0x87,0x9f,0x00,0x05,0xff,0xe5,0x87,0xb5,0x00,0x10, - 0x08,0x05,0xff,0xe5,0x88,0x83,0x00,0x05,0xff,0xe3,0x93,0x9f,0x00,0xd4,0x80,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x88,0xbb,0x00,0x05,0xff,0xe5, - 0x89,0x86,0x00,0x10,0x08,0x05,0xff,0xe5,0x89,0xb2,0x00,0x05,0xff,0xe5,0x89,0xb7, - 0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe3,0x94,0x95,0x00,0x05,0xff,0xe5,0x8b,0x87, - 0x00,0x10,0x08,0x05,0xff,0xe5,0x8b,0x89,0x00,0x05,0xff,0xe5,0x8b,0xa4,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x8b,0xba,0x00,0x05,0xff,0xe5,0x8c,0x85, - 0x00,0x10,0x08,0x05,0xff,0xe5,0x8c,0x86,0x00,0x05,0xff,0xe5,0x8c,0x97,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe5,0x8d,0x89,0x00,0x05,0xff,0xe5,0x8d,0x91,0x00,0x10, - 0x08,0x05,0xff,0xe5,0x8d,0x9a,0x00,0x05,0xff,0xe5,0x8d,0xb3,0x00,0xd3,0x39,0xd2, - 0x18,0x91,0x10,0x10,0x08,0x05,0xff,0xe5,0x8d,0xbd,0x00,0x05,0xff,0xe5,0x8d,0xbf, - 0x00,0x05,0xff,0xe5,0x8d,0xbf,0x00,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa0,0xa8, - 0xac,0x00,0x05,0xff,0xe7,0x81,0xb0,0x00,0x10,0x08,0x05,0xff,0xe5,0x8f,0x8a,0x00, - 0x05,0xff,0xe5,0x8f,0x9f,0x00,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa0, - 0xad,0xa3,0x00,0x05,0xff,0xe5,0x8f,0xab,0x00,0x10,0x08,0x05,0xff,0xe5,0x8f,0xb1, - 0x00,0x05,0xff,0xe5,0x90,0x86,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x92,0x9e, - 0x00,0x05,0xff,0xe5,0x90,0xb8,0x00,0x10,0x08,0x05,0xff,0xe5,0x91,0x88,0x00,0x05, - 0xff,0xe5,0x91,0xa8,0x00,0xcf,0x86,0xe5,0x02,0x01,0xd4,0x80,0xd3,0x40,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0x92,0xa2,0x00,0x05,0xff,0xe5,0x93,0xb6,0x00, - 0x10,0x08,0x05,0xff,0xe5,0x94,0x90,0x00,0x05,0xff,0xe5,0x95,0x93,0x00,0xd1,0x10, - 0x10,0x08,0x05,0xff,0xe5,0x95,0xa3,0x00,0x05,0xff,0xe5,0x96,0x84,0x00,0x10,0x08, - 0x05,0xff,0xe5,0x96,0x84,0x00,0x05,0xff,0xe5,0x96,0x99,0x00,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x05,0xff,0xe5,0x96,0xab,0x00,0x05,0xff,0xe5,0x96,0xb3,0x00,0x10,0x08, - 0x05,0xff,0xe5,0x97,0x82,0x00,0x05,0xff,0xe5,0x9c,0x96,0x00,0xd1,0x10,0x10,0x08, - 0x05,0xff,0xe5,0x98,0x86,0x00,0x05,0xff,0xe5,0x9c,0x97,0x00,0x10,0x08,0x05,0xff, - 0xe5,0x99,0x91,0x00,0x05,0xff,0xe5,0x99,0xb4,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x05,0xff,0xe5,0x88,0x87,0x00,0x05,0xff,0xe5,0xa3,0xae,0x00,0x10,0x08, - 0x05,0xff,0xe5,0x9f,0x8e,0x00,0x05,0xff,0xe5,0x9f,0xb4,0x00,0xd1,0x10,0x10,0x08, - 0x05,0xff,0xe5,0xa0,0x8d,0x00,0x05,0xff,0xe5,0x9e,0x8b,0x00,0x10,0x08,0x05,0xff, - 0xe5,0xa0,0xb2,0x00,0x05,0xff,0xe5,0xa0,0xb1,0x00,0xd2,0x21,0xd1,0x11,0x10,0x08, - 0x05,0xff,0xe5,0xa2,0xac,0x00,0x05,0xff,0xf0,0xa1,0x93,0xa4,0x00,0x10,0x08,0x05, - 0xff,0xe5,0xa3,0xb2,0x00,0x05,0xff,0xe5,0xa3,0xb7,0x00,0xd1,0x10,0x10,0x08,0x05, - 0xff,0xe5,0xa4,0x86,0x00,0x05,0xff,0xe5,0xa4,0x9a,0x00,0x10,0x08,0x05,0xff,0xe5, - 0xa4,0xa2,0x00,0x05,0xff,0xe5,0xa5,0xa2,0x00,0xd4,0x7b,0xd3,0x42,0xd2,0x22,0xd1, - 0x12,0x10,0x09,0x05,0xff,0xf0,0xa1,0x9a,0xa8,0x00,0x05,0xff,0xf0,0xa1,0x9b,0xaa, - 0x00,0x10,0x08,0x05,0xff,0xe5,0xa7,0xac,0x00,0x05,0xff,0xe5,0xa8,0x9b,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe5,0xa8,0xa7,0x00,0x05,0xff,0xe5,0xa7,0x98,0x00,0x10, - 0x08,0x05,0xff,0xe5,0xa9,0xa6,0x00,0x05,0xff,0xe3,0x9b,0xae,0x00,0xd2,0x18,0x91, - 0x10,0x10,0x08,0x05,0xff,0xe3,0x9b,0xbc,0x00,0x05,0xff,0xe5,0xac,0x88,0x00,0x05, - 0xff,0xe5,0xac,0xbe,0x00,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa1,0xa7,0x88,0x00, - 0x05,0xff,0xe5,0xaf,0x83,0x00,0x10,0x08,0x05,0xff,0xe5,0xaf,0x98,0x00,0x05,0xff, - 0xe5,0xaf,0xa7,0x00,0xd3,0x41,0xd2,0x21,0xd1,0x11,0x10,0x08,0x05,0xff,0xe5,0xaf, - 0xb3,0x00,0x05,0xff,0xf0,0xa1,0xac,0x98,0x00,0x10,0x08,0x05,0xff,0xe5,0xaf,0xbf, - 0x00,0x05,0xff,0xe5,0xb0,0x86,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xbd,0x93, - 0x00,0x05,0xff,0xe5,0xb0,0xa2,0x00,0x10,0x08,0x05,0xff,0xe3,0x9e,0x81,0x00,0x05, - 0xff,0xe5,0xb1,0xa0,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb1,0xae, - 0x00,0x05,0xff,0xe5,0xb3,0x80,0x00,0x10,0x08,0x05,0xff,0xe5,0xb2,0x8d,0x00,0x05, - 0xff,0xf0,0xa1,0xb7,0xa4,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe5,0xb5,0x83,0x00, - 0x05,0xff,0xf0,0xa1,0xb7,0xa6,0x00,0x10,0x08,0x05,0xff,0xe5,0xb5,0xae,0x00,0x05, - 0xff,0xe5,0xb5,0xab,0x00,0xe0,0x04,0x02,0xcf,0x86,0xd5,0xfe,0xd4,0x82,0xd3,0x40, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb5,0xbc,0x00,0x05,0xff,0xe5,0xb7, - 0xa1,0x00,0x10,0x08,0x05,0xff,0xe5,0xb7,0xa2,0x00,0x05,0xff,0xe3,0xa0,0xaf,0x00, - 0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb7,0xbd,0x00,0x05,0xff,0xe5,0xb8,0xa8,0x00, - 0x10,0x08,0x05,0xff,0xe5,0xb8,0xbd,0x00,0x05,0xff,0xe5,0xb9,0xa9,0x00,0xd2,0x21, - 0xd1,0x11,0x10,0x08,0x05,0xff,0xe3,0xa1,0xa2,0x00,0x05,0xff,0xf0,0xa2,0x86,0x83, - 0x00,0x10,0x08,0x05,0xff,0xe3,0xa1,0xbc,0x00,0x05,0xff,0xe5,0xba,0xb0,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe5,0xba,0xb3,0x00,0x05,0xff,0xe5,0xba,0xb6,0x00,0x10, - 0x08,0x05,0xff,0xe5,0xbb,0x8a,0x00,0x05,0xff,0xf0,0xaa,0x8e,0x92,0x00,0xd3,0x3b, - 0xd2,0x22,0xd1,0x11,0x10,0x08,0x05,0xff,0xe5,0xbb,0xbe,0x00,0x05,0xff,0xf0,0xa2, - 0x8c,0xb1,0x00,0x10,0x09,0x05,0xff,0xf0,0xa2,0x8c,0xb1,0x00,0x05,0xff,0xe8,0x88, - 0x81,0x00,0x51,0x08,0x05,0xff,0xe5,0xbc,0xa2,0x00,0x10,0x08,0x05,0xff,0xe3,0xa3, - 0x87,0x00,0x05,0xff,0xf0,0xa3,0x8a,0xb8,0x00,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05, - 0xff,0xf0,0xa6,0x87,0x9a,0x00,0x05,0xff,0xe5,0xbd,0xa2,0x00,0x10,0x08,0x05,0xff, - 0xe5,0xbd,0xab,0x00,0x05,0xff,0xe3,0xa3,0xa3,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, - 0xe5,0xbe,0x9a,0x00,0x05,0xff,0xe5,0xbf,0x8d,0x00,0x10,0x08,0x05,0xff,0xe5,0xbf, - 0x97,0x00,0x05,0xff,0xe5,0xbf,0xb9,0x00,0xd4,0x81,0xd3,0x41,0xd2,0x20,0xd1,0x10, - 0x10,0x08,0x05,0xff,0xe6,0x82,0x81,0x00,0x05,0xff,0xe3,0xa4,0xba,0x00,0x10,0x08, - 0x05,0xff,0xe3,0xa4,0x9c,0x00,0x05,0xff,0xe6,0x82,0x94,0x00,0xd1,0x11,0x10,0x09, - 0x05,0xff,0xf0,0xa2,0x9b,0x94,0x00,0x05,0xff,0xe6,0x83,0x87,0x00,0x10,0x08,0x05, - 0xff,0xe6,0x85,0x88,0x00,0x05,0xff,0xe6,0x85,0x8c,0x00,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x05,0xff,0xe6,0x85,0x8e,0x00,0x05,0xff,0xe6,0x85,0x8c,0x00,0x10,0x08,0x05, - 0xff,0xe6,0x85,0xba,0x00,0x05,0xff,0xe6,0x86,0x8e,0x00,0xd1,0x10,0x10,0x08,0x05, - 0xff,0xe6,0x86,0xb2,0x00,0x05,0xff,0xe6,0x86,0xa4,0x00,0x10,0x08,0x05,0xff,0xe6, - 0x86,0xaf,0x00,0x05,0xff,0xe6,0x87,0x9e,0x00,0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10, - 0x08,0x05,0xff,0xe6,0x87,0xb2,0x00,0x05,0xff,0xe6,0x87,0xb6,0x00,0x10,0x08,0x05, - 0xff,0xe6,0x88,0x90,0x00,0x05,0xff,0xe6,0x88,0x9b,0x00,0xd1,0x10,0x10,0x08,0x05, - 0xff,0xe6,0x89,0x9d,0x00,0x05,0xff,0xe6,0x8a,0xb1,0x00,0x10,0x08,0x05,0xff,0xe6, - 0x8b,0x94,0x00,0x05,0xff,0xe6,0x8d,0x90,0x00,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05, - 0xff,0xf0,0xa2,0xac,0x8c,0x00,0x05,0xff,0xe6,0x8c,0xbd,0x00,0x10,0x08,0x05,0xff, - 0xe6,0x8b,0xbc,0x00,0x05,0xff,0xe6,0x8d,0xa8,0x00,0xd1,0x10,0x10,0x08,0x05,0xff, - 0xe6,0x8e,0x83,0x00,0x05,0xff,0xe6,0x8f,0xa4,0x00,0x10,0x09,0x05,0xff,0xf0,0xa2, - 0xaf,0xb1,0x00,0x05,0xff,0xe6,0x90,0xa2,0x00,0xcf,0x86,0xe5,0x03,0x01,0xd4,0x81, - 0xd3,0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x8f,0x85,0x00,0x05,0xff, - 0xe6,0x8e,0xa9,0x00,0x10,0x08,0x05,0xff,0xe3,0xa8,0xae,0x00,0x05,0xff,0xe6,0x91, - 0xa9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x91,0xbe,0x00,0x05,0xff,0xe6,0x92, - 0x9d,0x00,0x10,0x08,0x05,0xff,0xe6,0x91,0xb7,0x00,0x05,0xff,0xe3,0xa9,0xac,0x00, - 0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x95,0x8f,0x00,0x05,0xff,0xe6,0x95, - 0xac,0x00,0x10,0x09,0x05,0xff,0xf0,0xa3,0x80,0x8a,0x00,0x05,0xff,0xe6,0x97,0xa3, - 0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9b,0xb8,0x00,0x05,0xff,0xe6,0x99,0x89, - 0x00,0x10,0x08,0x05,0xff,0xe3,0xac,0x99,0x00,0x05,0xff,0xe6,0x9a,0x91,0x00,0xd3, - 0x40,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe3,0xac,0x88,0x00,0x05,0xff,0xe3, - 0xab,0xa4,0x00,0x10,0x08,0x05,0xff,0xe5,0x86,0x92,0x00,0x05,0xff,0xe5,0x86,0x95, - 0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9c,0x80,0x00,0x05,0xff,0xe6,0x9a,0x9c, - 0x00,0x10,0x08,0x05,0xff,0xe8,0x82,0xad,0x00,0x05,0xff,0xe4,0x8f,0x99,0x00,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9c,0x97,0x00,0x05,0xff,0xe6,0x9c,0x9b, - 0x00,0x10,0x08,0x05,0xff,0xe6,0x9c,0xa1,0x00,0x05,0xff,0xe6,0x9d,0x9e,0x00,0xd1, - 0x11,0x10,0x08,0x05,0xff,0xe6,0x9d,0x93,0x00,0x05,0xff,0xf0,0xa3,0x8f,0x83,0x00, - 0x10,0x08,0x05,0xff,0xe3,0xad,0x89,0x00,0x05,0xff,0xe6,0x9f,0xba,0x00,0xd4,0x82, - 0xd3,0x41,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0x9e,0x85,0x00,0x05,0xff, - 0xe6,0xa1,0x92,0x00,0x10,0x08,0x05,0xff,0xe6,0xa2,0x85,0x00,0x05,0xff,0xf0,0xa3, - 0x91,0xad,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xa2,0x8e,0x00,0x05,0xff,0xe6, - 0xa0,0x9f,0x00,0x10,0x08,0x05,0xff,0xe6,0xa4,0x94,0x00,0x05,0xff,0xe3,0xae,0x9d, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xa5,0x82,0x00,0x05,0xff,0xe6, - 0xa6,0xa3,0x00,0x10,0x08,0x05,0xff,0xe6,0xa7,0xaa,0x00,0x05,0xff,0xe6,0xaa,0xa8, - 0x00,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa3,0x9a,0xa3,0x00,0x05,0xff,0xe6,0xab, - 0x9b,0x00,0x10,0x08,0x05,0xff,0xe3,0xb0,0x98,0x00,0x05,0xff,0xe6,0xac,0xa1,0x00, - 0xd3,0x42,0xd2,0x21,0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa3,0xa2,0xa7,0x00,0x05, - 0xff,0xe6,0xad,0x94,0x00,0x10,0x08,0x05,0xff,0xe3,0xb1,0x8e,0x00,0x05,0xff,0xe6, - 0xad,0xb2,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xae,0x9f,0x00,0x05,0xff,0xe6, - 0xae,0xba,0x00,0x10,0x08,0x05,0xff,0xe6,0xae,0xbb,0x00,0x05,0xff,0xf0,0xa3,0xaa, - 0x8d,0x00,0xd2,0x23,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa1,0xb4,0x8b,0x00,0x05, - 0xff,0xf0,0xa3,0xab,0xba,0x00,0x10,0x08,0x05,0xff,0xe6,0xb1,0x8e,0x00,0x05,0xff, - 0xf0,0xa3,0xb2,0xbc,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb2,0xbf,0x00,0x05, - 0xff,0xe6,0xb3,0x8d,0x00,0x10,0x08,0x05,0xff,0xe6,0xb1,0xa7,0x00,0x05,0xff,0xe6, - 0xb4,0x96,0x00,0xe1,0x1d,0x04,0xe0,0x0c,0x02,0xcf,0x86,0xe5,0x08,0x01,0xd4,0x82, - 0xd3,0x41,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb4,0xbe,0x00,0x05,0xff, - 0xe6,0xb5,0xb7,0x00,0x10,0x08,0x05,0xff,0xe6,0xb5,0x81,0x00,0x05,0xff,0xe6,0xb5, - 0xa9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb5,0xb8,0x00,0x05,0xff,0xe6,0xb6, - 0x85,0x00,0x10,0x09,0x05,0xff,0xf0,0xa3,0xb4,0x9e,0x00,0x05,0xff,0xe6,0xb4,0xb4, - 0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe6,0xb8,0xaf,0x00,0x05,0xff,0xe6, - 0xb9,0xae,0x00,0x10,0x08,0x05,0xff,0xe3,0xb4,0xb3,0x00,0x05,0xff,0xe6,0xbb,0x8b, - 0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe6,0xbb,0x87,0x00,0x05,0xff,0xf0,0xa3,0xbb, - 0x91,0x00,0x10,0x08,0x05,0xff,0xe6,0xb7,0xb9,0x00,0x05,0xff,0xe6,0xbd,0xae,0x00, - 0xd3,0x42,0xd2,0x22,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa3,0xbd,0x9e,0x00,0x05, - 0xff,0xf0,0xa3,0xbe,0x8e,0x00,0x10,0x08,0x05,0xff,0xe6,0xbf,0x86,0x00,0x05,0xff, - 0xe7,0x80,0xb9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x80,0x9e,0x00,0x05,0xff, - 0xe7,0x80,0x9b,0x00,0x10,0x08,0x05,0xff,0xe3,0xb6,0x96,0x00,0x05,0xff,0xe7,0x81, - 0x8a,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x81,0xbd,0x00,0x05,0xff, - 0xe7,0x81,0xb7,0x00,0x10,0x08,0x05,0xff,0xe7,0x82,0xad,0x00,0x05,0xff,0xf0,0xa0, - 0x94,0xa5,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x85,0x85,0x00,0x05,0xff,0xf0, - 0xa4,0x89,0xa3,0x00,0x10,0x08,0x05,0xff,0xe7,0x86,0x9c,0x00,0x05,0xff,0xf0,0xa4, - 0x8e,0xab,0x00,0xd4,0x7b,0xd3,0x43,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7, - 0x88,0xa8,0x00,0x05,0xff,0xe7,0x88,0xb5,0x00,0x10,0x08,0x05,0xff,0xe7,0x89,0x90, - 0x00,0x05,0xff,0xf0,0xa4,0x98,0x88,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x8a, - 0x80,0x00,0x05,0xff,0xe7,0x8a,0x95,0x00,0x10,0x09,0x05,0xff,0xf0,0xa4,0x9c,0xb5, - 0x00,0x05,0xff,0xf0,0xa4,0xa0,0x94,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff, - 0xe7,0x8d,0xba,0x00,0x05,0xff,0xe7,0x8e,0x8b,0x00,0x10,0x08,0x05,0xff,0xe3,0xba, - 0xac,0x00,0x05,0xff,0xe7,0x8e,0xa5,0x00,0x51,0x08,0x05,0xff,0xe3,0xba,0xb8,0x00, - 0x10,0x08,0x05,0xff,0xe7,0x91,0x87,0x00,0x05,0xff,0xe7,0x91,0x9c,0x00,0xd3,0x42, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x91,0xb1,0x00,0x05,0xff,0xe7,0x92, - 0x85,0x00,0x10,0x08,0x05,0xff,0xe7,0x93,0x8a,0x00,0x05,0xff,0xe3,0xbc,0x9b,0x00, - 0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x94,0xa4,0x00,0x05,0xff,0xf0,0xa4,0xb0,0xb6, - 0x00,0x10,0x08,0x05,0xff,0xe7,0x94,0xbe,0x00,0x05,0xff,0xf0,0xa4,0xb2,0x92,0x00, - 0xd2,0x22,0xd1,0x11,0x10,0x08,0x05,0xff,0xe7,0x95,0xb0,0x00,0x05,0xff,0xf0,0xa2, - 0x86,0x9f,0x00,0x10,0x08,0x05,0xff,0xe7,0x98,0x90,0x00,0x05,0xff,0xf0,0xa4,0xbe, - 0xa1,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa4,0xbe,0xb8,0x00,0x05,0xff,0xf0, - 0xa5,0x81,0x84,0x00,0x10,0x08,0x05,0xff,0xe3,0xbf,0xbc,0x00,0x05,0xff,0xe4,0x80, - 0x88,0x00,0xcf,0x86,0xe5,0x04,0x01,0xd4,0x7d,0xd3,0x3c,0xd2,0x23,0xd1,0x11,0x10, - 0x08,0x05,0xff,0xe7,0x9b,0xb4,0x00,0x05,0xff,0xf0,0xa5,0x83,0xb3,0x00,0x10,0x09, - 0x05,0xff,0xf0,0xa5,0x83,0xb2,0x00,0x05,0xff,0xf0,0xa5,0x84,0x99,0x00,0x91,0x11, - 0x10,0x09,0x05,0xff,0xf0,0xa5,0x84,0xb3,0x00,0x05,0xff,0xe7,0x9c,0x9e,0x00,0x05, - 0xff,0xe7,0x9c,0x9f,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0x9d,0x8a, - 0x00,0x05,0xff,0xe4,0x80,0xb9,0x00,0x10,0x08,0x05,0xff,0xe7,0x9e,0x8b,0x00,0x05, - 0xff,0xe4,0x81,0x86,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe4,0x82,0x96,0x00,0x05, - 0xff,0xf0,0xa5,0x90,0x9d,0x00,0x10,0x08,0x05,0xff,0xe7,0xa1,0x8e,0x00,0x05,0xff, - 0xe7,0xa2,0x8c,0x00,0xd3,0x43,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0xa3, - 0x8c,0x00,0x05,0xff,0xe4,0x83,0xa3,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0x98,0xa6, - 0x00,0x05,0xff,0xe7,0xa5,0x96,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0x9a, - 0x9a,0x00,0x05,0xff,0xf0,0xa5,0x9b,0x85,0x00,0x10,0x08,0x05,0xff,0xe7,0xa6,0x8f, - 0x00,0x05,0xff,0xe7,0xa7,0xab,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe4, - 0x84,0xaf,0x00,0x05,0xff,0xe7,0xa9,0x80,0x00,0x10,0x08,0x05,0xff,0xe7,0xa9,0x8a, - 0x00,0x05,0xff,0xe7,0xa9,0x8f,0x00,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa5,0xa5, - 0xbc,0x00,0x05,0xff,0xf0,0xa5,0xaa,0xa7,0x00,0x10,0x09,0x05,0xff,0xf0,0xa5,0xaa, - 0xa7,0x00,0x05,0xff,0xe7,0xab,0xae,0x00,0xd4,0x83,0xd3,0x42,0xd2,0x21,0xd1,0x11, - 0x10,0x08,0x05,0xff,0xe4,0x88,0x82,0x00,0x05,0xff,0xf0,0xa5,0xae,0xab,0x00,0x10, - 0x08,0x05,0xff,0xe7,0xaf,0x86,0x00,0x05,0xff,0xe7,0xaf,0x89,0x00,0xd1,0x11,0x10, - 0x08,0x05,0xff,0xe4,0x88,0xa7,0x00,0x05,0xff,0xf0,0xa5,0xb2,0x80,0x00,0x10,0x08, - 0x05,0xff,0xe7,0xb3,0x92,0x00,0x05,0xff,0xe4,0x8a,0xa0,0x00,0xd2,0x21,0xd1,0x10, - 0x10,0x08,0x05,0xff,0xe7,0xb3,0xa8,0x00,0x05,0xff,0xe7,0xb3,0xa3,0x00,0x10,0x08, - 0x05,0xff,0xe7,0xb4,0x80,0x00,0x05,0xff,0xf0,0xa5,0xbe,0x86,0x00,0xd1,0x10,0x10, - 0x08,0x05,0xff,0xe7,0xb5,0xa3,0x00,0x05,0xff,0xe4,0x8c,0x81,0x00,0x10,0x08,0x05, - 0xff,0xe7,0xb7,0x87,0x00,0x05,0xff,0xe7,0xb8,0x82,0x00,0xd3,0x44,0xd2,0x22,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe7,0xb9,0x85,0x00,0x05,0xff,0xe4,0x8c,0xb4,0x00,0x10, - 0x09,0x05,0xff,0xf0,0xa6,0x88,0xa8,0x00,0x05,0xff,0xf0,0xa6,0x89,0x87,0x00,0xd1, - 0x11,0x10,0x08,0x05,0xff,0xe4,0x8d,0x99,0x00,0x05,0xff,0xf0,0xa6,0x8b,0x99,0x00, - 0x10,0x08,0x05,0xff,0xe7,0xbd,0xba,0x00,0x05,0xff,0xf0,0xa6,0x8c,0xbe,0x00,0xd2, - 0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe7,0xbe,0x95,0x00,0x05,0xff,0xe7,0xbf,0xba, - 0x00,0x10,0x08,0x05,0xff,0xe8,0x80,0x85,0x00,0x05,0xff,0xf0,0xa6,0x93,0x9a,0x00, - 0xd1,0x11,0x10,0x09,0x05,0xff,0xf0,0xa6,0x94,0xa3,0x00,0x05,0xff,0xe8,0x81,0xa0, - 0x00,0x10,0x09,0x05,0xff,0xf0,0xa6,0x96,0xa8,0x00,0x05,0xff,0xe8,0x81,0xb0,0x00, - 0xe0,0x11,0x02,0xcf,0x86,0xe5,0x07,0x01,0xd4,0x85,0xd3,0x42,0xd2,0x21,0xd1,0x11, - 0x10,0x09,0x05,0xff,0xf0,0xa3,0x8d,0x9f,0x00,0x05,0xff,0xe4,0x8f,0x95,0x00,0x10, - 0x08,0x05,0xff,0xe8,0x82,0xb2,0x00,0x05,0xff,0xe8,0x84,0x83,0x00,0xd1,0x10,0x10, - 0x08,0x05,0xff,0xe4,0x90,0x8b,0x00,0x05,0xff,0xe8,0x84,0xbe,0x00,0x10,0x08,0x05, - 0xff,0xe5,0xaa,0xb5,0x00,0x05,0xff,0xf0,0xa6,0x9e,0xa7,0x00,0xd2,0x23,0xd1,0x12, - 0x10,0x09,0x05,0xff,0xf0,0xa6,0x9e,0xb5,0x00,0x05,0xff,0xf0,0xa3,0x8e,0x93,0x00, - 0x10,0x09,0x05,0xff,0xf0,0xa3,0x8e,0x9c,0x00,0x05,0xff,0xe8,0x88,0x81,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe8,0x88,0x84,0x00,0x05,0xff,0xe8,0xbe,0x9e,0x00,0x10, - 0x08,0x05,0xff,0xe4,0x91,0xab,0x00,0x05,0xff,0xe8,0x8a,0x91,0x00,0xd3,0x41,0xd2, - 0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x8a,0x8b,0x00,0x05,0xff,0xe8,0x8a,0x9d, - 0x00,0x10,0x08,0x05,0xff,0xe5,0x8a,0xb3,0x00,0x05,0xff,0xe8,0x8a,0xb1,0x00,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe8,0x8a,0xb3,0x00,0x05,0xff,0xe8,0x8a,0xbd,0x00,0x10, - 0x08,0x05,0xff,0xe8,0x8b,0xa6,0x00,0x05,0xff,0xf0,0xa6,0xac,0xbc,0x00,0xd2,0x20, - 0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x8b,0xa5,0x00,0x05,0xff,0xe8,0x8c,0x9d,0x00, - 0x10,0x08,0x05,0xff,0xe8,0x8d,0xa3,0x00,0x05,0xff,0xe8,0x8e,0xad,0x00,0xd1,0x10, - 0x10,0x08,0x05,0xff,0xe8,0x8c,0xa3,0x00,0x05,0xff,0xe8,0x8e,0xbd,0x00,0x10,0x08, - 0x05,0xff,0xe8,0x8f,0xa7,0x00,0x05,0xff,0xe8,0x91,0x97,0x00,0xd4,0x85,0xd3,0x43, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x8d,0x93,0x00,0x05,0xff,0xe8,0x8f, - 0x8a,0x00,0x10,0x08,0x05,0xff,0xe8,0x8f,0x8c,0x00,0x05,0xff,0xe8,0x8f,0x9c,0x00, - 0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa6,0xb0,0xb6,0x00,0x05,0xff,0xf0,0xa6,0xb5, - 0xab,0x00,0x10,0x09,0x05,0xff,0xf0,0xa6,0xb3,0x95,0x00,0x05,0xff,0xe4,0x94,0xab, - 0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x93,0xb1,0x00,0x05,0xff,0xe8, - 0x93,0xb3,0x00,0x10,0x08,0x05,0xff,0xe8,0x94,0x96,0x00,0x05,0xff,0xf0,0xa7,0x8f, - 0x8a,0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe8,0x95,0xa4,0x00,0x05,0xff,0xf0,0xa6, - 0xbc,0xac,0x00,0x10,0x08,0x05,0xff,0xe4,0x95,0x9d,0x00,0x05,0xff,0xe4,0x95,0xa1, - 0x00,0xd3,0x42,0xd2,0x22,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa6,0xbe,0xb1,0x00, - 0x05,0xff,0xf0,0xa7,0x83,0x92,0x00,0x10,0x08,0x05,0xff,0xe4,0x95,0xab,0x00,0x05, - 0xff,0xe8,0x99,0x90,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x99,0x9c,0x00,0x05, - 0xff,0xe8,0x99,0xa7,0x00,0x10,0x08,0x05,0xff,0xe8,0x99,0xa9,0x00,0x05,0xff,0xe8, - 0x9a,0xa9,0x00,0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9a,0x88,0x00,0x05, - 0xff,0xe8,0x9c,0x8e,0x00,0x10,0x08,0x05,0xff,0xe8,0x9b,0xa2,0x00,0x05,0xff,0xe8, - 0x9d,0xb9,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe8,0x9c,0xa8,0x00,0x05,0xff,0xe8, - 0x9d,0xab,0x00,0x10,0x08,0x05,0xff,0xe8,0x9e,0x86,0x00,0x05,0xff,0xe4,0x97,0x97, - 0x00,0xcf,0x86,0xe5,0x08,0x01,0xd4,0x83,0xd3,0x41,0xd2,0x20,0xd1,0x10,0x10,0x08, - 0x05,0xff,0xe8,0x9f,0xa1,0x00,0x05,0xff,0xe8,0xa0,0x81,0x00,0x10,0x08,0x05,0xff, - 0xe4,0x97,0xb9,0x00,0x05,0xff,0xe8,0xa1,0xa0,0x00,0xd1,0x11,0x10,0x08,0x05,0xff, - 0xe8,0xa1,0xa3,0x00,0x05,0xff,0xf0,0xa7,0x99,0xa7,0x00,0x10,0x08,0x05,0xff,0xe8, - 0xa3,0x97,0x00,0x05,0xff,0xe8,0xa3,0x9e,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05, - 0xff,0xe4,0x98,0xb5,0x00,0x05,0xff,0xe8,0xa3,0xba,0x00,0x10,0x08,0x05,0xff,0xe3, - 0x92,0xbb,0x00,0x05,0xff,0xf0,0xa7,0xa2,0xae,0x00,0xd1,0x11,0x10,0x09,0x05,0xff, - 0xf0,0xa7,0xa5,0xa6,0x00,0x05,0xff,0xe4,0x9a,0xbe,0x00,0x10,0x08,0x05,0xff,0xe4, - 0x9b,0x87,0x00,0x05,0xff,0xe8,0xaa,0xa0,0x00,0xd3,0x41,0xd2,0x21,0xd1,0x10,0x10, - 0x08,0x05,0xff,0xe8,0xab,0xad,0x00,0x05,0xff,0xe8,0xae,0x8a,0x00,0x10,0x08,0x05, - 0xff,0xe8,0xb1,0x95,0x00,0x05,0xff,0xf0,0xa7,0xb2,0xa8,0x00,0xd1,0x10,0x10,0x08, - 0x05,0xff,0xe8,0xb2,0xab,0x00,0x05,0xff,0xe8,0xb3,0x81,0x00,0x10,0x08,0x05,0xff, - 0xe8,0xb4,0x9b,0x00,0x05,0xff,0xe8,0xb5,0xb7,0x00,0xd2,0x22,0xd1,0x12,0x10,0x09, - 0x05,0xff,0xf0,0xa7,0xbc,0xaf,0x00,0x05,0xff,0xf0,0xa0,0xa0,0x84,0x00,0x10,0x08, - 0x05,0xff,0xe8,0xb7,0x8b,0x00,0x05,0xff,0xe8,0xb6,0xbc,0x00,0xd1,0x11,0x10,0x08, - 0x05,0xff,0xe8,0xb7,0xb0,0x00,0x05,0xff,0xf0,0xa0,0xa3,0x9e,0x00,0x10,0x08,0x05, - 0xff,0xe8,0xbb,0x94,0x00,0x05,0xff,0xe8,0xbc,0xb8,0x00,0xd4,0x84,0xd3,0x43,0xd2, - 0x22,0xd1,0x12,0x10,0x09,0x05,0xff,0xf0,0xa8,0x97,0x92,0x00,0x05,0xff,0xf0,0xa8, - 0x97,0xad,0x00,0x10,0x08,0x05,0xff,0xe9,0x82,0x94,0x00,0x05,0xff,0xe9,0x83,0xb1, - 0x00,0xd1,0x11,0x10,0x08,0x05,0xff,0xe9,0x84,0x91,0x00,0x05,0xff,0xf0,0xa8,0x9c, - 0xae,0x00,0x10,0x08,0x05,0xff,0xe9,0x84,0x9b,0x00,0x05,0xff,0xe9,0x88,0xb8,0x00, - 0xd2,0x20,0xd1,0x10,0x10,0x08,0x05,0xff,0xe9,0x8b,0x97,0x00,0x05,0xff,0xe9,0x8b, - 0x98,0x00,0x10,0x08,0x05,0xff,0xe9,0x89,0xbc,0x00,0x05,0xff,0xe9,0x8f,0xb9,0x00, - 0xd1,0x11,0x10,0x08,0x05,0xff,0xe9,0x90,0x95,0x00,0x05,0xff,0xf0,0xa8,0xaf,0xba, - 0x00,0x10,0x08,0x05,0xff,0xe9,0x96,0x8b,0x00,0x05,0xff,0xe4,0xa6,0x95,0x00,0xd3, - 0x43,0xd2,0x21,0xd1,0x11,0x10,0x08,0x05,0xff,0xe9,0x96,0xb7,0x00,0x05,0xff,0xf0, - 0xa8,0xb5,0xb7,0x00,0x10,0x08,0x05,0xff,0xe4,0xa7,0xa6,0x00,0x05,0xff,0xe9,0x9b, - 0x83,0x00,0xd1,0x10,0x10,0x08,0x05,0xff,0xe5,0xb6,0xb2,0x00,0x05,0xff,0xe9,0x9c, - 0xa3,0x00,0x10,0x09,0x05,0xff,0xf0,0xa9,0x85,0x85,0x00,0x05,0xff,0xf0,0xa9,0x88, - 0x9a,0x00,0xd2,0x21,0xd1,0x10,0x10,0x08,0x05,0xff,0xe4,0xa9,0xae,0x00,0x05,0xff, - 0xe4,0xa9,0xb6,0x00,0x10,0x08,0x05,0xff,0xe9,0x9f,0xa0,0x00,0x05,0xff,0xf0,0xa9, - 0x90,0x8a,0x00,0x91,0x11,0x10,0x08,0x05,0xff,0xe4,0xaa,0xb2,0x00,0x05,0xff,0xf0, - 0xa9,0x92,0x96,0x00,0x05,0xff,0xe9,0xa0,0x8b,0x00,0xe2,0x10,0x01,0xe1,0x09,0x01, - 0xe0,0x02,0x01,0xcf,0x86,0x95,0xfb,0xd4,0x82,0xd3,0x41,0xd2,0x21,0xd1,0x11,0x10, - 0x08,0x05,0xff,0xe9,0xa0,0xa9,0x00,0x05,0xff,0xf0,0xa9,0x96,0xb6,0x00,0x10,0x08, - 0x05,0xff,0xe9,0xa3,0xa2,0x00,0x05,0xff,0xe4,0xac,0xb3,0x00,0xd1,0x10,0x10,0x08, - 0x05,0xff,0xe9,0xa4,0xa9,0x00,0x05,0xff,0xe9,0xa6,0xa7,0x00,0x10,0x08,0x05,0xff, - 0xe9,0xa7,0x82,0x00,0x05,0xff,0xe9,0xa7,0xbe,0x00,0xd2,0x21,0xd1,0x11,0x10,0x08, - 0x05,0xff,0xe4,0xaf,0x8e,0x00,0x05,0xff,0xf0,0xa9,0xac,0xb0,0x00,0x10,0x08,0x05, - 0xff,0xe9,0xac,0x92,0x00,0x05,0xff,0xe9,0xb1,0x80,0x00,0xd1,0x10,0x10,0x08,0x05, - 0xff,0xe9,0xb3,0xbd,0x00,0x05,0xff,0xe4,0xb3,0x8e,0x00,0x10,0x08,0x05,0xff,0xe4, - 0xb3,0xad,0x00,0x05,0xff,0xe9,0xb5,0xa7,0x00,0xd3,0x44,0xd2,0x23,0xd1,0x11,0x10, - 0x09,0x05,0xff,0xf0,0xaa,0x83,0x8e,0x00,0x05,0xff,0xe4,0xb3,0xb8,0x00,0x10,0x09, - 0x05,0xff,0xf0,0xaa,0x84,0x85,0x00,0x05,0xff,0xf0,0xaa,0x88,0x8e,0x00,0xd1,0x11, - 0x10,0x09,0x05,0xff,0xf0,0xaa,0x8a,0x91,0x00,0x05,0xff,0xe9,0xba,0xbb,0x00,0x10, - 0x08,0x05,0xff,0xe4,0xb5,0x96,0x00,0x05,0xff,0xe9,0xbb,0xb9,0x00,0xd2,0x20,0xd1, - 0x10,0x10,0x08,0x05,0xff,0xe9,0xbb,0xbe,0x00,0x05,0xff,0xe9,0xbc,0x85,0x00,0x10, - 0x08,0x05,0xff,0xe9,0xbc,0x8f,0x00,0x05,0xff,0xe9,0xbc,0x96,0x00,0x91,0x11,0x10, - 0x08,0x05,0xff,0xe9,0xbc,0xbb,0x00,0x05,0xff,0xf0,0xaa,0x98,0x80,0x00,0x00,0x00, - 0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xcf,0x06,0x00,0x00,0xd3,0x06, - 0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00, - 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00, - 0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xd3,0x08, - 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08, - 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, - 0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06, - 0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06, - 0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04, - 0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xd5,0xc0, - 0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06, - 0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06, - 0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00, - 0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06, - 0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04, - 0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00, - 0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, - 0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, - 0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06, - 0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00, - 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00, - 0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xd4,0x60, - 0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, - 0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00, - 0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06, - 0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00, - 0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00, - 0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xd3,0x08, - 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08, - 0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, - 0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06, - 0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06, - 0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04, - 0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xe0,0x83,0x01,0xcf, - 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf, - 0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf, - 0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf, - 0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1, - 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00, - 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00, - 0x00,0x02,0x00,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00, - 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, - 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, - 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, - 0x00,0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00, - 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, - 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, - 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, - 0x00,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00, - 0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00, - 0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3, - 0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00, - 0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00, - 0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf, - 0x86,0xd5,0xc0,0xd4,0x60,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf, - 0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf, - 0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf, - 0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1, - 0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00, - 0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00, - 0x00,0x02,0x00,0xd3,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xd1,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf, - 0x06,0x00,0x00,0xcf,0x86,0xd5,0x06,0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00, - 0x00,0xd3,0x06,0xcf,0x06,0x00,0x00,0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf, - 0x06,0x00,0x00,0xd0,0x06,0xcf,0x06,0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54, - 0x04,0x00,0x00,0x53,0x04,0x00,0x00,0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02, - 0x00,0xd4,0xd9,0xd3,0x81,0xd2,0x79,0xd1,0x71,0xd0,0x69,0xcf,0x86,0xd5,0x60,0xd4, - 0x59,0xd3,0x52,0xd2,0x33,0xd1,0x2c,0xd0,0x25,0xcf,0x86,0x95,0x1e,0x94,0x19,0x93, - 0x14,0x92,0x0f,0x91,0x0a,0x10,0x05,0x00,0xff,0x00,0x05,0xff,0x00,0x00,0xff,0x00, - 0x00,0xff,0x00,0x00,0xff,0x00,0x00,0xff,0x00,0x05,0xff,0x00,0xcf,0x06,0x05,0xff, - 0x00,0xcf,0x06,0x00,0xff,0x00,0xd1,0x07,0xcf,0x06,0x07,0xff,0x00,0xd0,0x07,0xcf, - 0x06,0x07,0xff,0x00,0xcf,0x86,0x55,0x05,0x07,0xff,0x00,0x14,0x05,0x07,0xff,0x00, - 0x00,0xff,0x00,0xcf,0x06,0x00,0xff,0x00,0xcf,0x06,0x00,0xff,0x00,0xcf,0x06,0x00, - 0xff,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86, - 0xcf,0x06,0x00,0x00,0xd2,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xd1,0x08,0xcf,0x86, - 0xcf,0x06,0x00,0x00,0xd0,0x08,0xcf,0x86,0xcf,0x06,0x00,0x00,0xcf,0x86,0xd5,0x06, - 0xcf,0x06,0x00,0x00,0xd4,0x06,0xcf,0x06,0x00,0x00,0xd3,0x06,0xcf,0x06,0x00,0x00, - 0xd2,0x06,0xcf,0x06,0x00,0x00,0xd1,0x06,0xcf,0x06,0x00,0x00,0xd0,0x06,0xcf,0x06, - 0x00,0x00,0xcf,0x86,0x55,0x04,0x00,0x00,0x54,0x04,0x00,0x00,0x53,0x04,0x00,0x00, - 0x52,0x04,0x00,0x00,0x11,0x04,0x00,0x00,0x02,0x00,0xcf,0x86,0xcf,0x06,0x02,0x00, - 0x81,0x80,0xcf,0x86,0x85,0x84,0xcf,0x86,0xcf,0x06,0x02,0x00,0x00,0x00,0x00,0x00 -}; diff --git a/fs/unicode/utf8n.h b/fs/unicode/utf8n.h index 206c89f0dbf7..bd00d587747a 100644 --- a/fs/unicode/utf8n.h +++ b/fs/unicode/utf8n.h @@ -13,25 +13,7 @@ #include #include -int utf8version_is_supported(unsigned int version); - -/* - * Look for the correct const struct utf8data for a unicode version. - * Returns NULL if the version requested is too new. - * - * Two normalization forms are supported: nfdi and nfdicf. - * - * nfdi: - * - Apply unicode normalization form NFD. - * - Remove any Default_Ignorable_Code_Point. - * - * nfdicf: - * - Apply unicode normalization form NFD. - * - Remove any Default_Ignorable_Code_Point. - * - Apply a full casefold (C + F). - */ -extern const struct utf8data *utf8nfdi(unsigned int maxage); -extern const struct utf8data *utf8nfdicf(unsigned int maxage); +int utf8version_is_supported(const struct unicode_map *um, unsigned int version); /* * Determine the length of the normalized from of the string, @@ -78,4 +60,24 @@ int utf8ncursor(struct utf8cursor *u8c, const struct unicode_map *um, */ extern int utf8byte(struct utf8cursor *u8c); +struct utf8data { + unsigned int maxage; + unsigned int offset; +}; + +struct utf8data_table { + const unsigned int *utf8agetab; + int utf8agetab_size; + + const struct utf8data *utf8nfdicfdata; + int utf8nfdicfdata_size; + + const struct utf8data *utf8nfdidata; + int utf8nfdidata_size; + + const unsigned char *utf8data; +}; + +extern struct utf8data_table utf8_data_table; + #endif /* UTF8NORM_H */ diff --git a/include/linux/unicode.h b/include/linux/unicode.h index 526ca8b8391a..4d39e6e11a95 100644 --- a/include/linux/unicode.h +++ b/include/linux/unicode.h @@ -6,6 +6,7 @@ #include struct utf8data; +struct utf8data_table; #define UNICODE_MAJ_SHIFT 16 #define UNICODE_MIN_SHIFT 8 @@ -49,6 +50,7 @@ enum utf8_normalization { struct unicode_map { unsigned int version; const struct utf8data *ntab[UTF8_NMAX]; + const struct utf8data_table *tables; }; int utf8_validate(const struct unicode_map *um, const struct qstr *str); -- cgit v1.2.3 From 8e9028b3790ddb02c407e1a4da0ab7cf82790e7e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 12 Oct 2021 15:42:59 -0500 Subject: PCI: Return NULL for to_pci_driver(NULL) to_pci_driver() takes a pointer to a struct device_driver and uses container_of() to find the struct pci_driver that contains it. If given a NULL pointer to a struct device_driver, return a NULL pci_driver pointer instead of applying container_of() to NULL. This simplifies callers that would otherwise have to check for a NULL pointer first. Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..a2d62165a7f7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -900,7 +900,10 @@ struct pci_driver { struct pci_dynids dynids; }; -#define to_pci_driver(drv) container_of(drv, struct pci_driver, driver) +static inline struct pci_driver *to_pci_driver(struct device_driver *drv) +{ + return drv ? container_of(drv, struct pci_driver, driver) : NULL; +} /** * PCI_DEVICE - macro used to describe a specific PCI device -- cgit v1.2.3 From b3ec8cdf457e5e63d396fe1346cc788cf7c1b578 Mon Sep 17 00:00:00 2001 From: Claudio Suarez Date: Thu, 30 Sep 2021 17:10:26 +0200 Subject: fbdev: Garbage collect fbdev scrolling acceleration, part 1 (from TODO list) Scroll acceleration is disabled in fbcon by hard-wiring p->scrollmode = SCROLL_REDRAW. Remove the obsolete code in fbcon.c and fbdev/core/ Signed-off-by: Claudio Suarez Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/YVXTYqszZix9TxjJ@gineta.localdomain --- Documentation/gpu/todo.rst | 13 +- drivers/video/fbdev/core/bitblit.c | 16 - drivers/video/fbdev/core/fbcon.c | 509 ++------------------------------ drivers/video/fbdev/core/fbcon.h | 59 ---- drivers/video/fbdev/core/fbcon_ccw.c | 28 +- drivers/video/fbdev/core/fbcon_cw.c | 28 +- drivers/video/fbdev/core/fbcon_rotate.h | 9 - drivers/video/fbdev/core/fbcon_ud.c | 37 +-- drivers/video/fbdev/core/tileblit.c | 16 - drivers/video/fbdev/skeletonfb.c | 12 +- include/linux/fb.h | 2 +- 11 files changed, 51 insertions(+), 678 deletions(-) (limited to 'include/linux') diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index 6613543955e9..60d1d7ee0719 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -314,16 +314,19 @@ Level: Advanced Garbage collect fbdev scrolling acceleration -------------------------------------------- -Scroll acceleration is disabled in fbcon by hard-wiring p->scrollmode = -SCROLL_REDRAW. There's a ton of code this will allow us to remove: +Scroll acceleration has been disabled in fbcon. Now it works as the old +SCROLL_REDRAW mode. A ton of code was removed in fbcon.c and the hook bmove was +removed from fbcon_ops. +Remaining tasks: -- lots of code in fbcon.c - -- a bunch of the hooks in fbcon_ops, maybe the remaining hooks could be called +- a bunch of the hooks in fbcon_ops could be removed or simplified by calling directly instead of the function table (with a switch on p->rotate) - fb_copyarea is unused after this, and can be deleted from all drivers +- after that, fb_copyarea can be deleted from fb_ops in include/linux/fb.h as + well as cfb_copyarea + Note that not all acceleration code can be deleted, since clearing and cursor support is still accelerated, which might be good candidates for further deletion projects. diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index f98e8f298bc1..01fae2c96965 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -43,21 +43,6 @@ static void update_attr(u8 *dst, u8 *src, int attribute, } } -static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fb_copyarea area; - - area.sx = sx * vc->vc_font.width; - area.sy = sy * vc->vc_font.height; - area.dx = dx * vc->vc_font.width; - area.dy = dy * vc->vc_font.height; - area.height = height * vc->vc_font.height; - area.width = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -393,7 +378,6 @@ static int bit_update_start(struct fb_info *info) void fbcon_set_bitops(struct fbcon_ops *ops) { - ops->bmove = bit_bmove; ops->clear = bit_clear; ops->putcs = bit_putcs; ops->clear_margins = bit_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 22bb3892f6bd..99ecd9a6d844 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -173,8 +173,6 @@ static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, int count, int ypos, int xpos); static void fbcon_clear_margins(struct vc_data *vc, int bottom_only); static void fbcon_cursor(struct vc_data *vc, int mode); -static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, - int height, int width); static int fbcon_switch(struct vc_data *vc); static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); @@ -182,16 +180,8 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines */ -static __inline__ void ywrap_up(struct vc_data *vc, int count); -static __inline__ void ywrap_down(struct vc_data *vc, int count); -static __inline__ void ypan_up(struct vc_data *vc, int count); -static __inline__ void ypan_down(struct vc_data *vc, int count); -static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, - int dy, int dx, int height, int width, u_int y_break); static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit); -static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, - int line, int count, int dy); static void fbcon_modechanged(struct fb_info *info); static void fbcon_set_all_vcs(struct fb_info *info); static void fbcon_start(void); @@ -1135,14 +1125,6 @@ static void fbcon_init(struct vc_data *vc, int init) ops->graphics = 0; - /* - * No more hw acceleration for fbcon. - * - * FIXME: Garbage collect all the now dead code after sufficient time - * has passed. - */ - p->scrollmode = SCROLL_REDRAW; - /* * ++guenther: console.c:vc_allocate() relies on initializing * vc_{cols,rows}, but we must not set those if we are only @@ -1229,14 +1211,13 @@ finished: * This system is now divided into two levels because of complications * caused by hardware scrolling. Top level functions: * - * fbcon_bmove(), fbcon_clear(), fbcon_putc(), fbcon_clear_margins() + * fbcon_clear(), fbcon_putc(), fbcon_clear_margins() * * handles y values in range [0, scr_height-1] that correspond to real * screen positions. y_wrap shift means that first line of bitmap may be * anywhere on this display. These functions convert lineoffsets to * bitmap offsets and deal with the wrap-around case by splitting blits. * - * fbcon_bmove_physical_8() -- These functions fast implementations * fbcon_clear_physical_8() -- of original fbcon_XXX fns. * fbcon_putc_physical_8() -- (font width != 8) may be added later * @@ -1409,224 +1390,6 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, } } -static __inline__ void ywrap_up(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll += count; - if (p->yscroll >= p->vrows) /* Deal with wrap */ - p->yscroll -= p->vrows; - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode |= FB_VMODE_YWRAP; - ops->update_start(info); - scrollback_max += count; - if (scrollback_max > scrollback_phys_max) - scrollback_max = scrollback_phys_max; - scrollback_current = 0; -} - -static __inline__ void ywrap_down(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll -= count; - if (p->yscroll < 0) /* Deal with wrap */ - p->yscroll += p->vrows; - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode |= FB_VMODE_YWRAP; - ops->update_start(info); - scrollback_max -= count; - if (scrollback_max < 0) - scrollback_max = 0; - scrollback_current = 0; -} - -static __inline__ void ypan_up(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; - - p->yscroll += count; - if (p->yscroll > p->vrows - vc->vc_rows) { - ops->bmove(vc, info, p->vrows - vc->vc_rows, - 0, 0, 0, vc->vc_rows, vc->vc_cols); - p->yscroll -= p->vrows - vc->vc_rows; - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max += count; - if (scrollback_max > scrollback_phys_max) - scrollback_max = scrollback_phys_max; - scrollback_current = 0; -} - -static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll += count; - - if (p->yscroll > p->vrows - vc->vc_rows) { - p->yscroll -= p->vrows - vc->vc_rows; - fbcon_redraw_move(vc, p, t + count, vc->vc_rows - count, t); - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max += count; - if (scrollback_max > scrollback_phys_max) - scrollback_max = scrollback_phys_max; - scrollback_current = 0; -} - -static __inline__ void ypan_down(struct vc_data *vc, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - struct fbcon_ops *ops = info->fbcon_par; - - p->yscroll -= count; - if (p->yscroll < 0) { - ops->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, - 0, vc->vc_rows, vc->vc_cols); - p->yscroll += p->vrows - vc->vc_rows; - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max -= count; - if (scrollback_max < 0) - scrollback_max = 0; - scrollback_current = 0; -} - -static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - p->yscroll -= count; - - if (p->yscroll < 0) { - p->yscroll += p->vrows - vc->vc_rows; - fbcon_redraw_move(vc, p, t, vc->vc_rows - count, t + count); - } - - ops->var.xoffset = 0; - ops->var.yoffset = p->yscroll * vc->vc_font.height; - ops->var.vmode &= ~FB_VMODE_YWRAP; - ops->update_start(info); - fbcon_clear_margins(vc, 1); - scrollback_max -= count; - if (scrollback_max < 0) - scrollback_max = 0; - scrollback_current = 0; -} - -static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, - int line, int count, int dy) -{ - unsigned short *s = (unsigned short *) - (vc->vc_origin + vc->vc_size_row * line); - - while (count--) { - unsigned short *start = s; - unsigned short *le = advance_row(s, 1); - unsigned short c; - int x = 0; - unsigned short attr = 1; - - do { - c = scr_readw(s); - if (attr != (c & 0xff00)) { - attr = c & 0xff00; - if (s > start) { - fbcon_putcs(vc, start, s - start, - dy, x); - x += s - start; - start = s; - } - } - console_conditional_schedule(); - s++; - } while (s < le); - if (s > start) - fbcon_putcs(vc, start, s - start, dy, x); - console_conditional_schedule(); - dy++; - } -} - -static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, - struct fbcon_display *p, int line, int count, int ycount) -{ - int offset = ycount * vc->vc_cols; - unsigned short *d = (unsigned short *) - (vc->vc_origin + vc->vc_size_row * line); - unsigned short *s = d + offset; - struct fbcon_ops *ops = info->fbcon_par; - - while (count--) { - unsigned short *start = s; - unsigned short *le = advance_row(s, 1); - unsigned short c; - int x = 0; - - do { - c = scr_readw(s); - - if (c == scr_readw(d)) { - if (s > start) { - ops->bmove(vc, info, line + ycount, x, - line, x, 1, s-start); - x += s - start + 1; - start = s + 1; - } else { - x++; - start++; - } - } - - scr_writew(c, d); - console_conditional_schedule(); - s++; - d++; - } while (s < le); - if (s > start) - ops->bmove(vc, info, line + ycount, x, line, x, 1, - s-start); - console_conditional_schedule(); - if (ycount > 0) - line++; - else { - line--; - /* NOTE: We subtract two lines from these pointers */ - s -= vc->vc_size_row; - d -= vc->vc_size_row; - } - } -} - static void fbcon_redraw(struct vc_data *vc, struct fbcon_display *p, int line, int count, int offset) { @@ -1687,7 +1450,6 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; struct fbcon_display *p = &fb_display[vc->vc_num]; - int scroll_partial = info->flags & FBINFO_PARTIAL_PAN_OK; if (fbcon_is_inactive(vc, info)) return true; @@ -1704,249 +1466,32 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, case SM_UP: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - if (logo_shown >= 0) - goto redraw_up; - switch (p->scrollmode) { - case SCROLL_MOVE: - fbcon_redraw_blit(vc, info, p, t, b - t - count, - count); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - (b - count)), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - - case SCROLL_WRAP_MOVE: - if (b - t - count > 3 * vc->vc_rows >> 2) { - if (t > 0) - fbcon_bmove(vc, 0, 0, count, 0, t, - vc->vc_cols); - ywrap_up(vc, count); - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b - count, 0, b, 0, - vc->vc_rows - b, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t + count, 0, t, 0, - b - t - count, vc->vc_cols); - else - goto redraw_up; - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_REDRAW: - if ((p->yscroll + count <= - 2 * (p->vrows - vc->vc_rows)) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (t > 0) - fbcon_redraw_move(vc, p, 0, t, count); - ypan_up_redraw(vc, t, count); - if (vc->vc_rows - b > 0) - fbcon_redraw_move(vc, p, b, - vc->vc_rows - b, b); - } else - fbcon_redraw_move(vc, p, t + count, b - t - count, t); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_MOVE: - if ((p->yscroll + count <= - 2 * (p->vrows - vc->vc_rows)) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (t > 0) - fbcon_bmove(vc, 0, 0, count, 0, t, - vc->vc_cols); - ypan_up(vc, count); - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b - count, 0, b, 0, - vc->vc_rows - b, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t + count, 0, t, 0, - b - t - count, vc->vc_cols); - else - goto redraw_up; - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - break; - - case SCROLL_REDRAW: - redraw_up: - fbcon_redraw(vc, p, t, b - t - count, - count * vc->vc_cols); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - (b - count)), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - } - break; + fbcon_redraw(vc, p, t, b - t - count, + count * vc->vc_cols); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + (b - count)), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; case SM_DOWN: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - if (logo_shown >= 0) - goto redraw_down; - switch (p->scrollmode) { - case SCROLL_MOVE: - fbcon_redraw_blit(vc, info, p, b - 1, b - t - count, - -count); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - t), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - - case SCROLL_WRAP_MOVE: - if (b - t - count > 3 * vc->vc_rows >> 2) { - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b, 0, b - count, 0, - vc->vc_rows - b, - vc->vc_cols); - ywrap_down(vc, count); - if (t > 0) - fbcon_bmove(vc, count, 0, 0, 0, t, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t, 0, t + count, 0, - b - t - count, vc->vc_cols); - else - goto redraw_down; - fbcon_clear(vc, t, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_MOVE: - if ((count - p->yscroll <= p->vrows - vc->vc_rows) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (vc->vc_rows - b > 0) - fbcon_bmove(vc, b, 0, b - count, 0, - vc->vc_rows - b, - vc->vc_cols); - ypan_down(vc, count); - if (t > 0) - fbcon_bmove(vc, count, 0, 0, 0, t, - vc->vc_cols); - } else if (info->flags & FBINFO_READS_FAST) - fbcon_bmove(vc, t, 0, t + count, 0, - b - t - count, vc->vc_cols); - else - goto redraw_down; - fbcon_clear(vc, t, 0, count, vc->vc_cols); - break; - - case SCROLL_PAN_REDRAW: - if ((count - p->yscroll <= p->vrows - vc->vc_rows) - && ((!scroll_partial && (b - t == vc->vc_rows)) - || (scroll_partial - && (b - t - count > - 3 * vc->vc_rows >> 2)))) { - if (vc->vc_rows - b > 0) - fbcon_redraw_move(vc, p, b, vc->vc_rows - b, - b - count); - ypan_down_redraw(vc, t, count); - if (t > 0) - fbcon_redraw_move(vc, p, count, t, 0); - } else - fbcon_redraw_move(vc, p, t, b - t - count, t + count); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - break; - - case SCROLL_REDRAW: - redraw_down: - fbcon_redraw(vc, p, b - 1, b - t - count, - -count * vc->vc_cols); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - t), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; - } + fbcon_redraw(vc, p, b - 1, b - t - count, + -count * vc->vc_cols); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + t), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; } return false; } - -static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, - int height, int width) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_display *p = &fb_display[vc->vc_num]; - - if (fbcon_is_inactive(vc, info)) - return; - - if (!width || !height) - return; - - /* Split blits that cross physical y_wrap case. - * Pathological case involves 4 blits, better to use recursive - * code rather than unrolled case - * - * Recursive invocations don't need to erase the cursor over and - * over again, so we use fbcon_bmove_rec() - */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, - p->vrows - p->yscroll); -} - -static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, - int dy, int dx, int height, int width, u_int y_break) -{ - struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; - struct fbcon_ops *ops = info->fbcon_par; - u_int b; - - if (sy < y_break && sy + height > y_break) { - b = y_break - sy; - if (dy < sy) { /* Avoid trashing self */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - } else { - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - } - return; - } - - if (dy < y_break && dy + height > y_break) { - b = y_break - dy; - if (dy < sy) { /* Avoid trashing self */ - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - } else { - fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, - height - b, width, y_break); - fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, - y_break); - } - return; - } - ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, - height, width); -} - static void updatescrollmode(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) @@ -2119,21 +1664,7 @@ static int fbcon_switch(struct vc_data *vc) updatescrollmode(p, info, vc); - switch (p->scrollmode) { - case SCROLL_WRAP_MOVE: - scrollback_phys_max = p->vrows - vc->vc_rows; - break; - case SCROLL_PAN_MOVE: - case SCROLL_PAN_REDRAW: - scrollback_phys_max = p->vrows - 2 * vc->vc_rows; - if (scrollback_phys_max < 0) - scrollback_phys_max = 0; - break; - default: - scrollback_phys_max = 0; - break; - } - + scrollback_phys_max = 0; scrollback_max = 0; scrollback_current = 0; diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 9315b360c898..a00603b4451a 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -29,7 +29,6 @@ struct fbcon_display { /* Filled in by the low-level console driver */ const u_char *fontdata; int userfont; /* != 0 if fontdata kmalloc()ed */ - u_short scrollmode; /* Scroll Method */ u_short inverse; /* != 0 text black on white as default */ short yscroll; /* Hardware scrolling */ int vrows; /* number of virtual rows */ @@ -52,8 +51,6 @@ struct fbcon_display { }; struct fbcon_ops { - void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width); void (*clear)(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width); void (*putcs)(struct vc_data *vc, struct fb_info *info, @@ -152,62 +149,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) - /* - * Scroll Method - */ - -/* There are several methods fbcon can use to move text around the screen: - * - * Operation Pan Wrap - *--------------------------------------------- - * SCROLL_MOVE copyarea No No - * SCROLL_PAN_MOVE copyarea Yes No - * SCROLL_WRAP_MOVE copyarea No Yes - * SCROLL_REDRAW imageblit No No - * SCROLL_PAN_REDRAW imageblit Yes No - * SCROLL_WRAP_REDRAW imageblit No Yes - * - * (SCROLL_WRAP_REDRAW is not implemented yet) - * - * In general, fbcon will choose the best scrolling - * method based on the rule below: - * - * Pan/Wrap > accel imageblit > accel copyarea > - * soft imageblit > (soft copyarea) - * - * Exception to the rule: Pan + accel copyarea is - * preferred over Pan + accel imageblit. - * - * The above is typical for PCI/AGP cards. Unless - * overridden, fbcon will never use soft copyarea. - * - * If you need to override the above rule, set the - * appropriate flags in fb_info->flags. For example, - * to prefer copyarea over imageblit, set - * FBINFO_READS_FAST. - * - * Other notes: - * + use the hardware engine to move the text - * (hw-accelerated copyarea() and fillrect()) - * + use hardware-supported panning on a large virtual screen - * + amifb can not only pan, but also wrap the display by N lines - * (i.e. visible line i = physical line (i+N) % yres). - * + read what's already rendered on the screen and - * write it in a different place (this is cfb_copyarea()) - * + re-render the text to the screen - * - * Whether to use wrapping or panning can only be figured out at - * runtime (when we know whether our font height is a multiple - * of the pan/wrap step) - * - */ - -#define SCROLL_MOVE 0x001 -#define SCROLL_PAN_MOVE 0x002 -#define SCROLL_WRAP_MOVE 0x003 -#define SCROLL_REDRAW 0x004 -#define SCROLL_PAN_REDRAW 0x005 - #ifdef CONFIG_FB_TILEBLITTING extern void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info); #endif diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index 9cd2c4b05c32..ffa78936eaab 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -59,31 +59,12 @@ static void ccw_update_attr(u8 *dst, u8 *src, int attribute, } } - -static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fbcon_ops *ops = info->fbcon_par; - struct fb_copyarea area; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - - area.sx = sy * vc->vc_font.height; - area.sy = vyres - ((sx + width) * vc->vc_font.width); - area.dx = dy * vc->vc_font.height; - area.dy = vyres - ((dx + width) * vc->vc_font.width); - area.width = height * vc->vc_font.height; - area.height = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = sy * vc->vc_font.height; @@ -140,7 +121,7 @@ static void ccw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; if (!ops->fontbuffer) return; @@ -229,7 +210,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; if (!ops->fontbuffer) return; @@ -387,7 +368,7 @@ static int ccw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; u32 yoffset; - u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; int err; yoffset = (vyres - info->var.yres) - ops->var.xoffset; @@ -402,7 +383,6 @@ static int ccw_update_start(struct fb_info *info) void fbcon_rotate_ccw(struct fbcon_ops *ops) { - ops->bmove = ccw_bmove; ops->clear = ccw_clear; ops->putcs = ccw_putcs; ops->clear_margins = ccw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index 88d89fad3f05..92e5b7fb51ee 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -44,31 +44,12 @@ static void cw_update_attr(u8 *dst, u8 *src, int attribute, } } - -static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fbcon_ops *ops = info->fbcon_par; - struct fb_copyarea area; - u32 vxres = GETVXRES(ops->p->scrollmode, info); - - area.sx = vxres - ((sy + height) * vc->vc_font.height); - area.sy = sx * vc->vc_font.width; - area.dx = vxres - ((dy + height) * vc->vc_font.height); - area.dy = dx * vc->vc_font.width; - area.width = height * vc->vc_font.height; - area.height = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = vxres - ((sy + height) * vc->vc_font.height); @@ -125,7 +106,7 @@ static void cw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -212,7 +193,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -369,7 +350,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, static int cw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vxres = info->var.xres; u32 xoffset; int err; @@ -385,7 +366,6 @@ static int cw_update_start(struct fb_info *info) void fbcon_rotate_cw(struct fbcon_ops *ops) { - ops->bmove = cw_bmove; ops->clear = cw_clear; ops->putcs = cw_putcs; ops->clear_margins = cw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_rotate.h b/drivers/video/fbdev/core/fbcon_rotate.h index e233444cda66..b528b2e54283 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.h +++ b/drivers/video/fbdev/core/fbcon_rotate.h @@ -11,15 +11,6 @@ #ifndef _FBCON_ROTATE_H #define _FBCON_ROTATE_H -#define GETVYRES(s,i) ({ \ - (s == SCROLL_REDRAW || s == SCROLL_MOVE) ? \ - (i)->var.yres : (i)->var.yres_virtual; }) - -#define GETVXRES(s,i) ({ \ - (s == SCROLL_REDRAW || s == SCROLL_MOVE || !(i)->fix.xpanstep) ? \ - (i)->var.xres : (i)->var.xres_virtual; }) - - static inline int pattern_test_bit(u32 x, u32 y, u32 pitch, const char *pat) { u32 tmp = (y * pitch) + x, index = tmp / 8, bit = tmp % 8; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 8d5e66b1bdfb..09619bd8e021 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -44,33 +44,13 @@ static void ud_update_attr(u8 *dst, u8 *src, int attribute, } } - -static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fbcon_ops *ops = info->fbcon_par; - struct fb_copyarea area; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); - - area.sy = vyres - ((sy + height) * vc->vc_font.height); - area.sx = vxres - ((sx + width) * vc->vc_font.width); - area.dy = vyres - ((dy + height) * vc->vc_font.height); - area.dx = vxres - ((dx + width) * vc->vc_font.width); - area.height = height * vc->vc_font.height; - area.width = width * vc->vc_font.width; - - info->fbops->fb_copyarea(info, &area); -} - static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { - struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; region.color = attr_bgcol_ec(bgshift,vc,info); region.dy = vyres - ((sy + height) * vc->vc_font.height); @@ -162,8 +142,8 @@ static void ud_putcs(struct vc_data *vc, struct fb_info *info, u32 mod = vc->vc_font.width % 8, cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -259,8 +239,8 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; if (!ops->fontbuffer) return; @@ -410,8 +390,8 @@ static int ud_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; int xoffset, yoffset; - u32 vyres = GETVYRES(ops->p->scrollmode, info); - u32 vxres = GETVXRES(ops->p->scrollmode, info); + u32 vyres = info->var.yres; + u32 vxres = info->var.xres; int err; xoffset = vxres - info->var.xres - ops->var.xoffset; @@ -429,7 +409,6 @@ static int ud_update_start(struct fb_info *info) void fbcon_rotate_ud(struct fbcon_ops *ops) { - ops->bmove = ud_bmove; ops->clear = ud_clear; ops->putcs = ud_putcs; ops->clear_margins = ud_clear_margins; diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 2768eff247ba..72af95053bcb 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -16,21 +16,6 @@ #include #include "fbcon.h" -static void tile_bmove(struct vc_data *vc, struct fb_info *info, int sy, - int sx, int dy, int dx, int height, int width) -{ - struct fb_tilearea area; - - area.sx = sx; - area.sy = sy; - area.dx = dx; - area.dy = dy; - area.height = height; - area.width = width; - - info->tileops->fb_tilecopy(info, &area); -} - static void tile_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -133,7 +118,6 @@ void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info) struct fb_tilemap map; struct fbcon_ops *ops = info->fbcon_par; - ops->bmove = tile_bmove; ops->clear = tile_clear; ops->putcs = tile_putcs; ops->clear_margins = tile_clear_margins; diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c index bcacfb6934fa..0fe922f726e9 100644 --- a/drivers/video/fbdev/skeletonfb.c +++ b/drivers/video/fbdev/skeletonfb.c @@ -505,15 +505,15 @@ void xxxfb_fillrect(struct fb_info *p, const struct fb_fillrect *region) } /** - * xxxfb_copyarea - REQUIRED function. Can use generic routines if - * non acclerated hardware and packed pixel based. + * xxxfb_copyarea - OBSOLETE function. * Copies one area of the screen to another area. + * Will be deleted in a future version * * @info: frame buffer structure that represents a single frame buffer * @area: Structure providing the data to copy the framebuffer contents * from one region to another. * - * This drawing operation copies a rectangular area from one area of the + * This drawing operation copied a rectangular area from one area of the * screen to another area. */ void xxxfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) @@ -645,9 +645,9 @@ static const struct fb_ops xxxfb_ops = { .fb_setcolreg = xxxfb_setcolreg, .fb_blank = xxxfb_blank, .fb_pan_display = xxxfb_pan_display, - .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ - .fb_copyarea = xxxfb_copyarea, /* Needed !!! */ - .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ + .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ + .fb_copyarea = xxxfb_copyarea, /* Obsolete */ + .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ .fb_cursor = xxxfb_cursor, /* Optional !!! */ .fb_sync = xxxfb_sync, .fb_ioctl = xxxfb_ioctl, diff --git a/include/linux/fb.h b/include/linux/fb.h index 5950f8f5dc74..6f3db99ab990 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -262,7 +262,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another */ + /* Copy data from area to another. Obsolete. */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); -- cgit v1.2.3 From 5008062f1c3f5af3acf86164aa6fcc77b0c7bdce Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Wed, 13 Oct 2021 14:19:56 +0100 Subject: nvmem: core: add nvmem cell post processing callback Some NVMEM providers have certain nvmem cells encoded, which requires post processing before actually using it. For example mac-address is stored in either in ascii or delimited or reverse-order. Having a post-process callback hook to provider drivers would enable them to do this vendor specific post processing before nvmem consumers see it. Tested-by: Joakim Zhang Signed-off-by: Srinivas Kandagatla Link: https://lore.kernel.org/r/20211013131957.30271-3-srinivas.kandagatla@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 9 +++++++++ include/linux/nvmem-provider.h | 5 +++++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index f37d7838d2e3..d7013c9b0fae 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -38,6 +38,7 @@ struct nvmem_device { unsigned int nkeepout; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; + nvmem_cell_post_process_t cell_post_process; struct gpio_desc *wp_gpio; void *priv; }; @@ -796,6 +797,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->type = config->type; nvmem->reg_read = config->reg_read; nvmem->reg_write = config->reg_write; + nvmem->cell_post_process = config->cell_post_process; nvmem->keepout = config->keepout; nvmem->nkeepout = config->nkeepout; if (config->of_node) @@ -1440,6 +1442,13 @@ static int __nvmem_cell_read(struct nvmem_device *nvmem, if (cell->bit_offset || cell->nbits) nvmem_shift_read_buffer_in_place(cell, buf); + if (nvmem->cell_post_process) { + rc = nvmem->cell_post_process(nvmem->priv, id, + cell->offset, buf, cell->bytes); + if (rc) + return rc; + } + if (len) *len = cell->bytes; diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 104505e9028f..98efb7b5660d 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -19,6 +19,9 @@ typedef int (*nvmem_reg_read_t)(void *priv, unsigned int offset, void *val, size_t bytes); typedef int (*nvmem_reg_write_t)(void *priv, unsigned int offset, void *val, size_t bytes); +/* used for vendor specific post processing of cell data */ +typedef int (*nvmem_cell_post_process_t)(void *priv, const char *id, unsigned int offset, + void *buf, size_t bytes); enum nvmem_type { NVMEM_TYPE_UNKNOWN = 0, @@ -62,6 +65,7 @@ struct nvmem_keepout { * @no_of_node: Device should not use the parent's of_node even if it's !NULL. * @reg_read: Callback to read data. * @reg_write: Callback to write data. + * @cell_post_process: Callback for vendor specific post processing of cell data * @size: Device size. * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. @@ -92,6 +96,7 @@ struct nvmem_config { bool no_of_node; nvmem_reg_read_t reg_read; nvmem_reg_write_t reg_write; + nvmem_cell_post_process_t cell_post_process; int size; int word_size; int stride; -- cgit v1.2.3 From 16c663642c7ec03cd4cee5fec520bb69e97babe4 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 12 Oct 2021 11:57:22 -0400 Subject: SUNRPC: Replace the "__be32 *p" parameter to .pc_decode The passed-in value of the "__be32 *p" parameter is now unused in every server-side XDR decoder, and can be removed. Note also that there is a line in each decoder that sets up a local pointer to a struct xdr_stream. Passing that pointer from the dispatcher instead saves one line per decoder function. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/lockd/svc.c | 3 +-- fs/lockd/xdr.c | 27 ++++++++++----------------- fs/lockd/xdr4.c | 27 ++++++++++----------------- fs/nfsd/nfs2acl.c | 12 ++++++------ fs/nfsd/nfs3acl.c | 8 ++++---- fs/nfsd/nfs3xdr.c | 45 +++++++++++++++------------------------------ fs/nfsd/nfs4xdr.c | 4 ++-- fs/nfsd/nfsd.h | 3 ++- fs/nfsd/nfssvc.c | 7 +++---- fs/nfsd/nfsxdr.c | 30 ++++++++++-------------------- fs/nfsd/xdr.h | 21 +++++++++++---------- fs/nfsd/xdr3.h | 31 ++++++++++++++++--------------- fs/nfsd/xdr4.h | 2 +- include/linux/lockd/xdr.h | 19 ++++++++++--------- include/linux/lockd/xdr4.h | 19 +++++++++---------- include/linux/sunrpc/svc.h | 3 ++- 16 files changed, 112 insertions(+), 149 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index b632be3ad57b..9a82471bda07 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -780,11 +780,10 @@ module_exit(exit_nlm); static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *procp = rqstp->rq_procinfo; - struct kvec *argv = rqstp->rq_arg.head; struct kvec *resv = rqstp->rq_res.head; svcxdr_init_decode(rqstp); - if (!procp->pc_decode(rqstp, argv->iov_base)) + if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; *statp = procp->pc_func(rqstp); diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 9235e60b1769..895f15222104 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -146,15 +146,14 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) */ int -nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } int -nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; @@ -171,9 +170,8 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; @@ -197,9 +195,8 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; @@ -218,9 +215,8 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) @@ -233,9 +229,8 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) @@ -247,10 +242,10 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_reboot *argp = rqstp->rq_argp; + __be32 *p; u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) @@ -273,9 +268,8 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; @@ -301,9 +295,8 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 98e957e4566c..573c7d580a5e 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -145,15 +145,14 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) */ int -nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } int -nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; @@ -170,9 +169,8 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; @@ -196,9 +194,8 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; @@ -216,9 +213,8 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) @@ -231,9 +227,8 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) @@ -245,10 +240,10 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_reboot *argp = rqstp->rq_argp; + __be32 *p; u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) @@ -271,9 +266,8 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; @@ -299,9 +293,8 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 4b43929c1f25..0069c0fdb94f 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -188,9 +188,9 @@ out: * XDR decode functions */ -static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) +static int +nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) @@ -201,9 +201,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) return 1; } -static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) +static int +nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) @@ -222,9 +222,9 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) return 1; } -static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) +static int +nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 5dfe7644a517..b1e352ed2436 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -127,9 +127,9 @@ out: * XDR decode functions */ -static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) +static int +nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_getaclargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) @@ -140,9 +140,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p) return 1; } -static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p) +static int +nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh)) diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 267e56f218af..5f744f03cda7 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -557,18 +557,16 @@ void fill_post_wcc(struct svc_fh *fhp) */ int -nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->fh); } int -nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_sattrargs *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->fh) && @@ -577,18 +575,16 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_diropargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len); } int -nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) @@ -600,9 +596,8 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) @@ -616,9 +611,8 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_writeargs *args = rqstp->rq_argp; u32 max_blocksize = svc_max_payload(rqstp); @@ -649,9 +643,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) @@ -674,9 +667,8 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_createargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->fh, @@ -685,9 +677,8 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; struct kvec *tail = rqstp->rq_arg.tail; @@ -713,9 +704,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_mknodargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) @@ -742,9 +732,8 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_renameargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs3(xdr, &args->ffh, @@ -754,9 +743,8 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_linkargs *args = rqstp->rq_argp; return svcxdr_decode_nfs_fh3(xdr, &args->ffh) && @@ -765,9 +753,8 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) @@ -784,9 +771,8 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_readdirargs *args = rqstp->rq_argp; u32 dircount; @@ -807,9 +793,8 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p) } int -nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd3_commitargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index a54b2845473b..fc0f154f1172 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -5412,14 +5412,14 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) } int -nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p) +nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundargs *args = rqstp->rq_argp; /* svcxdr_tmp_alloc */ args->to_free = NULL; - args->xdr = &rqstp->rq_arg_stream; + args->xdr = xdr; args->ops = args->iops; args->rqstp = rqstp; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 9664303afdaf..6e8ad5f9757c 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -78,7 +78,8 @@ extern const struct seq_operations nfs_exports_op; */ struct nfsd_voidargs { }; struct nfsd_voidres { }; -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p); +int nfssvc_decode_voidarg(struct svc_rqst *rqstp, + struct xdr_stream *xdr); int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p); /* diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ccb59e91011b..7cd13e9474ff 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1004,7 +1004,6 @@ out: int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *proc = rqstp->rq_procinfo; - struct kvec *argv = &rqstp->rq_arg.head[0]; struct kvec *resv = &rqstp->rq_res.head[0]; __be32 *p; @@ -1015,7 +1014,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) rqstp->rq_cachetype = proc->pc_cachetype; svcxdr_init_decode(rqstp); - if (!proc->pc_decode(rqstp, argv->iov_base)) + if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; switch (nfsd_cache_lookup(rqstp)) { @@ -1065,13 +1064,13 @@ out_encode_err: /** * nfssvc_decode_voidarg - Decode void arguments * @rqstp: Server RPC transaction context - * @p: buffer containing arguments to decode + * @xdr: XDR stream positioned at arguments to decode * * Return values: * %0: Arguments were not valid * %1: Decoding was successful */ -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, __be32 *p) +int nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index ddcc18adfeb1..08e899180ee4 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -273,18 +273,16 @@ svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, */ int -nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_fhandle *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->fh); } int -nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_sattrargs *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->fh) && @@ -292,18 +290,16 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_diropargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len); } int -nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readargs *args = rqstp->rq_argp; u32 totalcount; @@ -321,9 +317,8 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_writeargs *args = rqstp->rq_argp; u32 beginoffset, totalcount; @@ -350,9 +345,8 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_createargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->fh, @@ -361,9 +355,8 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_renameargs *args = rqstp->rq_argp; return svcxdr_decode_diropargs(xdr, &args->ffh, @@ -373,9 +366,8 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_linkargs *args = rqstp->rq_argp; return svcxdr_decode_fhandle(xdr, &args->ffh) && @@ -384,9 +376,8 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; @@ -405,9 +396,8 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p) +nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct nfsd_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 80fd6d7f3404..804f9af94d6d 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -141,16 +141,17 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_fhandleargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_createargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *); -int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *); +int nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); + int nfssvc_encode_statres(struct svc_rqst *, __be32 *); int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *); int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 712c117300cb..60a8909205e5 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -265,21 +265,22 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandleargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *); -int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *); +int nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); + int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *); int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 3e4052e3bd50..1d1b8771bdcf 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -756,7 +756,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *); +int nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index a98309c0121c..170ad6f5596a 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,18 +96,19 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_testargs(struct svc_rqst *, __be32 *); +int nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); + int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlmsvc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_res(struct svc_rqst *, __be32 *); -int nlmsvc_decode_res(struct svc_rqst *, __be32 *); int nlmsvc_encode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_void(struct svc_rqst *, __be32 *); -int nlmsvc_decode_shareargs(struct svc_rqst *, __be32 *); int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); -int nlmsvc_decode_notify(struct svc_rqst *, __be32 *); -int nlmsvc_decode_reboot(struct svc_rqst *, __be32 *); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 5ae766f26e04..68e14e0f2b1f 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,21 +22,20 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) +int nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); - -int nlm4svc_decode_testargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_lockargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_cancargs(struct svc_rqst *, __be32 *); -int nlm4svc_decode_unlockargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_res(struct svc_rqst *, __be32 *); -int nlm4svc_decode_res(struct svc_rqst *, __be32 *); int nlm4svc_encode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_void(struct svc_rqst *, __be32 *); -int nlm4svc_decode_shareargs(struct svc_rqst *, __be32 *); int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); -int nlm4svc_decode_notify(struct svc_rqst *, __be32 *); -int nlm4svc_decode_reboot(struct svc_rqst *, __be32 *); extern const struct rpc_version nlm_version4; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 4205a6ef4770..da3c5bc43d85 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -454,7 +454,8 @@ struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ - int (*pc_decode)(struct svc_rqst *, __be32 *data); + int (*pc_decode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR encode result: */ int (*pc_encode)(struct svc_rqst *, __be32 *data); /* XDR free result: */ -- cgit v1.2.3 From c44b31c263798ec34614dd394c31ef1a2e7e716e Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 12 Oct 2021 11:57:28 -0400 Subject: SUNRPC: Change return value type of .pc_decode Returning an undecorated integer is an age-old trope, but it's not clear (even to previous experts in this code) that the only valid return values are 1 and 0. These functions do not return a negative errno, rpc_stat value, or a positive length. Document there are only two valid return values by having .pc_decode return only true or false. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/lockd/xdr.c | 96 ++++++++++++++++++------------------ fs/lockd/xdr4.c | 97 +++++++++++++++++++------------------ fs/nfsd/nfs2acl.c | 30 ++++++------ fs/nfsd/nfs3acl.c | 22 ++++----- fs/nfsd/nfs3xdr.c | 118 ++++++++++++++++++++++----------------------- fs/nfsd/nfs4xdr.c | 24 ++++----- fs/nfsd/nfsd.h | 2 +- fs/nfsd/nfssvc.c | 6 +-- fs/nfsd/nfsxdr.c | 62 ++++++++++++------------ fs/nfsd/xdr.h | 20 ++++---- fs/nfsd/xdr3.h | 30 ++++++------ fs/nfsd/xdr4.h | 2 +- include/linux/lockd/xdr.h | 18 +++---- include/linux/lockd/xdr4.h | 18 +++---- include/linux/sunrpc/svc.h | 2 +- 15 files changed, 274 insertions(+), 273 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 895f15222104..622c2ca37dbf 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -145,103 +145,103 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) * Decode Call arguments */ -int +bool nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int +bool nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int +bool nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; argp->monitor = 1; /* monitor client by default */ - return 1; + return true; } -int +bool nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int +bool nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; argp->lock.fl.fl_type = F_UNLCK; - return 1; + return true; } -int +bool nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_decode_stats(xdr, &resp->status)) - return 0; + return false; - return 1; + return true; } -int +bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_reboot *argp = rqstp->rq_argp; @@ -249,25 +249,25 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) - return 0; + return false; if (len > SM_MAXSTRLEN) - return 0; + return false; p = xdr_inline_decode(xdr, len); if (!p) - return 0; + return false; argp->len = len; argp->mon = (char *)p; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; p = xdr_inline_decode(xdr, SM_PRIV_SIZE); if (!p) - return 0; + return false; memcpy(&argp->priv.data, p, sizeof(argp->priv.data)); - return 1; + return true; } -int +bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; @@ -278,34 +278,34 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) lock->svid = ~(u32)0; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (!svcxdr_decode_fhandle(xdr, &lock->fh)) - return 0; + return false; if (!svcxdr_decode_owner(xdr, &lock->oh)) - return 0; + return false; /* XXX: Range checks are missing in the original code */ if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 573c7d580a5e..45551dee26b4 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -144,102 +144,103 @@ svcxdr_encode_testrply(struct xdr_stream *xdr, const struct nlm_res *resp) * Decode Call arguments */ -int +bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int +bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + return true; } -int +bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; if (xdr_stream_decode_bool(xdr, &argp->reclaim) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; argp->monitor = 1; /* monitor client by default */ - return 1; + return true; } -int +bool nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; u32 exclusive; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &argp->block) < 0) - return 0; + return false; if (xdr_stream_decode_bool(xdr, &exclusive) < 0) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; if (exclusive) argp->lock.fl.fl_type = F_WRLCK; - return 1; + + return true; } -int +bool nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_lock(xdr, &argp->lock)) - return 0; + return false; argp->lock.fl.fl_type = F_UNLCK; - return 1; + return true; } -int +bool nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_argp; if (!svcxdr_decode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_decode_stats(xdr, &resp->status)) - return 0; + return false; - return 1; + return true; } -int +bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_reboot *argp = rqstp->rq_argp; @@ -247,25 +248,25 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr) u32 len; if (xdr_stream_decode_u32(xdr, &len) < 0) - return 0; + return false; if (len > SM_MAXSTRLEN) - return 0; + return false; p = xdr_inline_decode(xdr, len); if (!p) - return 0; + return false; argp->len = len; argp->mon = (char *)p; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; p = xdr_inline_decode(xdr, SM_PRIV_SIZE); if (!p) - return 0; + return false; memcpy(&argp->priv.data, p, sizeof(argp->priv.data)); - return 1; + return true; } -int +bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; @@ -276,34 +277,34 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) lock->svid = ~(u32)0; if (!svcxdr_decode_cookie(xdr, &argp->cookie)) - return 0; + return false; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (!svcxdr_decode_fhandle(xdr, &lock->fh)) - return 0; + return false; if (!svcxdr_decode_owner(xdr, &lock->oh)) - return 0; + return false; /* XXX: Range checks are missing in the original code */ if (xdr_stream_decode_u32(xdr, &argp->fsm_mode) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->fsm_access) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_args *argp = rqstp->rq_argp; struct nlm_lock *lock = &argp->lock; if (!svcxdr_decode_string(xdr, &lock->caller, &lock->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->state) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 0069c0fdb94f..cf6ba5e7937e 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -188,51 +188,51 @@ out: * XDR decode functions */ -static int +static bool nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_getaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; - return 1; + return true; } -static int +static bool nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; if (argp->mask & ~NFS_ACL_MASK) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? &argp->acl_access : NULL)) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? &argp->acl_default : NULL)) - return 0; + return false; - return 1; + return true; } -static int +static bool nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->access) < 0) - return 0; + return false; - return 1; + return true; } /* diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index b1e352ed2436..9e9f6afb2e00 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -127,38 +127,38 @@ out: * XDR decode functions */ -static int +static bool nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_getaclargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->mask) < 0) - return 0; + return false; - return 1; + return true; } -static int +static bool nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_setaclargs *argp = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &argp->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &argp->mask) < 0) - return 0; + return false; if (argp->mask & ~NFS_ACL_MASK) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_ACL) ? &argp->acl_access : NULL)) - return 0; + return false; if (!nfs_stream_decode_acl(xdr, NULL, (argp->mask & NFS_DFACL) ? &argp->acl_default : NULL)) - return 0; + return false; - return 1; + return true; } /* diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 5f744f03cda7..1f3de46d24d4 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -556,7 +556,7 @@ void fill_post_wcc(struct svc_fh *fhp) * XDR decode functions */ -int +bool nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_fhandle *args = rqstp->rq_argp; @@ -564,7 +564,7 @@ nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) return svcxdr_decode_nfs_fh3(xdr, &args->fh); } -int +bool nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_sattrargs *args = rqstp->rq_argp; @@ -574,7 +574,7 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_decode_sattrguard3(xdr, args); } -int +bool nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_diropargs *args = rqstp->rq_argp; @@ -582,75 +582,75 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) return svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len); } -int +bool nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_accessargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->access) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_readargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_writeargs *args = rqstp->rq_argp; u32 max_blocksize = svc_max_payload(rqstp); if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->stable) < 0) - return 0; + return false; /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) - return 0; + return false; /* request sanity */ if (args->count != args->len) - return 0; + return false; if (args->count > max_blocksize) { args->count = max_blocksize; args->len = max_blocksize; } if (!xdr_stream_subsegment(xdr, &args->payload, args->count)) - return 0; + return false; - return 1; + return true; } -int +bool nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_createargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->createmode) < 0) - return 0; + return false; switch (args->createmode) { case NFS3_CREATE_UNCHECKED: case NFS3_CREATE_GUARDED: @@ -658,15 +658,15 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) case NFS3_CREATE_EXCLUSIVE: args->verf = xdr_inline_decode(xdr, NFS3_CREATEVERFSIZE); if (!args->verf) - return 0; + return false; break; default: - return 0; + return false; } - return 1; + return true; } -int +bool nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_createargs *args = rqstp->rq_argp; @@ -676,7 +676,7 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_decode_sattr3(rqstp, xdr, &args->attrs); } -int +bool nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_symlinkargs *args = rqstp->rq_argp; @@ -685,33 +685,33 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) size_t remaining; if (!svcxdr_decode_diropargs3(xdr, &args->ffh, &args->fname, &args->flen)) - return 0; + return false; if (!svcxdr_decode_sattr3(rqstp, xdr, &args->attrs)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) - return 0; + return false; /* request sanity */ remaining = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len; remaining -= xdr_stream_pos(xdr); if (remaining < xdr_align_size(args->tlen)) - return 0; + return false; args->first.iov_base = xdr->p; args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); - return 1; + return true; } -int +bool nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_mknodargs *args = rqstp->rq_argp; if (!svcxdr_decode_diropargs3(xdr, &args->fh, &args->name, &args->len)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->ftype) < 0) - return 0; + return false; switch (args->ftype) { case NF3CHR: case NF3BLK: @@ -725,13 +725,13 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) /* Valid XDR but illegal file types */ break; default: - return 0; + return false; } - return 1; + return true; } -int +bool nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_renameargs *args = rqstp->rq_argp; @@ -742,7 +742,7 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) &args->tname, &args->tlen); } -int +bool nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_linkargs *args = rqstp->rq_argp; @@ -752,59 +752,59 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) &args->tname, &args->tlen); } -int +bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) - return 0; + return false; args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); if (!args->verf) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_readdirargs *args = rqstp->rq_argp; u32 dircount; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->cookie) < 0) - return 0; + return false; args->verf = xdr_inline_decode(xdr, NFS3_COOKIEVERFSIZE); if (!args->verf) - return 0; + return false; /* dircount is ignored */ if (xdr_stream_decode_u32(xdr, &dircount) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_commitargs *args = rqstp->rq_argp; if (!svcxdr_decode_nfs_fh3(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u64(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } /* diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fc0f154f1172..dd1ee9ada7dd 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2322,7 +2322,7 @@ nfsd4_opnum_in_range(struct nfsd4_compoundargs *argp, struct nfsd4_op *op) return true; } -static int +static bool nfsd4_decode_compound(struct nfsd4_compoundargs *argp) { struct nfsd4_op *op; @@ -2335,25 +2335,25 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) int i; if (xdr_stream_decode_u32(argp->xdr, &argp->taglen) < 0) - return 0; + return false; max_reply += XDR_UNIT; argp->tag = NULL; if (unlikely(argp->taglen)) { if (argp->taglen > NFSD4_MAX_TAGLEN) - return 0; + return false; p = xdr_inline_decode(argp->xdr, argp->taglen); if (!p) - return 0; + return false; argp->tag = svcxdr_savemem(argp, p, argp->taglen); if (!argp->tag) - return 0; + return false; max_reply += xdr_align_size(argp->taglen); } if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) - return 0; + return false; if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0) - return 0; + return false; /* * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS @@ -2361,14 +2361,14 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) * nfsd4_proc can handle this is an NFS-level error. */ if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND) - return 1; + return true; if (argp->opcnt > ARRAY_SIZE(argp->iops)) { argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL); if (!argp->ops) { argp->ops = argp->iops; dprintk("nfsd: couldn't allocate room for COMPOUND\n"); - return 0; + return false; } } @@ -2380,7 +2380,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->replay = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) - return 0; + return false; if (nfsd4_opnum_in_range(argp, op)) { op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); if (op->status != nfs_ok) @@ -2427,7 +2427,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); - return 1; + return true; } static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode, @@ -5411,7 +5411,7 @@ void nfsd4_release_compoundargs(struct svc_rqst *rqstp) } } -int +bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundargs *args = rqstp->rq_argp; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 6e8ad5f9757c..bfcddd4c7534 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -78,7 +78,7 @@ extern const struct seq_operations nfs_exports_op; */ struct nfsd_voidargs { }; struct nfsd_voidres { }; -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, +bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 7cd13e9474ff..beb564e8a3db 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1067,10 +1067,10 @@ out_encode_err: * @xdr: XDR stream positioned at arguments to decode * * Return values: - * %0: Arguments were not valid - * %1: Decoding was successful + * %false: Arguments were not valid + * %true: Decoding was successful */ -int nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) +bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 08e899180ee4..b5817a41b3de 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -272,7 +272,7 @@ svcxdr_encode_fattr(struct svc_rqst *rqstp, struct xdr_stream *xdr, * XDR decode functions */ -int +bool nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_fhandle *args = rqstp->rq_argp; @@ -280,7 +280,7 @@ nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) return svcxdr_decode_fhandle(xdr, &args->fh); } -int +bool nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_sattrargs *args = rqstp->rq_argp; @@ -289,7 +289,7 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int +bool nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_diropargs *args = rqstp->rq_argp; @@ -297,54 +297,54 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) return svcxdr_decode_diropargs(xdr, &args->fh, &args->name, &args->len); } -int +bool nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_readargs *args = rqstp->rq_argp; u32 totalcount; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->offset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; /* totalcount is ignored */ if (xdr_stream_decode_u32(xdr, &totalcount) < 0) - return 0; + return false; - return 1; + return true; } -int +bool nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_writeargs *args = rqstp->rq_argp; u32 beginoffset, totalcount; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; /* beginoffset is ignored */ if (xdr_stream_decode_u32(xdr, &beginoffset) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->offset) < 0) - return 0; + return false; /* totalcount is ignored */ if (xdr_stream_decode_u32(xdr, &totalcount) < 0) - return 0; + return false; /* opaque data */ if (xdr_stream_decode_u32(xdr, &args->len) < 0) - return 0; + return false; if (args->len > NFSSVC_MAXBLKSIZE_V2) - return 0; + return false; if (!xdr_stream_subsegment(xdr, &args->payload, args->len)) - return 0; + return false; - return 1; + return true; } -int +bool nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_createargs *args = rqstp->rq_argp; @@ -354,7 +354,7 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int +bool nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_renameargs *args = rqstp->rq_argp; @@ -365,7 +365,7 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) &args->tname, &args->tlen); } -int +bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_linkargs *args = rqstp->rq_argp; @@ -375,39 +375,39 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) &args->tname, &args->tlen); } -int +bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_symlinkargs *args = rqstp->rq_argp; struct kvec *head = rqstp->rq_arg.head; if (!svcxdr_decode_diropargs(xdr, &args->ffh, &args->fname, &args->flen)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->tlen) < 0) - return 0; + return false; if (args->tlen == 0) - return 0; + return false; args->first.iov_len = head->iov_len - xdr_stream_pos(xdr); args->first.iov_base = xdr_inline_decode(xdr, args->tlen); if (!args->first.iov_base) - return 0; + return false; return svcxdr_decode_sattr(rqstp, xdr, &args->attrs); } -int +bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_readdirargs *args = rqstp->rq_argp; if (!svcxdr_decode_fhandle(xdr, &args->fh)) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->cookie) < 0) - return 0; + return false; if (xdr_stream_decode_u32(xdr, &args->count) < 0) - return 0; + return false; - return 1; + return true; } /* diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 804f9af94d6d..31be7d30e64e 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -141,16 +141,16 @@ union nfsd_xdrstore { #define NFS2_SVC_XDRSIZE sizeof(union nfsd_xdrstore) -int nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nfssvc_encode_statres(struct svc_rqst *, __be32 *); int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *); diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index 60a8909205e5..ef72bc4868da 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -265,21 +265,21 @@ union nfsd3_xdrstore { #define NFS3_SVC_XDRSIZE sizeof(union nfsd3_xdrstore) -int nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_fhandleargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_diropargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_writeargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_createargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_renameargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *); int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 1d1b8771bdcf..8812256cd520 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -756,7 +756,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); -int nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index 170ad6f5596a..e1362244f909 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -96,15 +96,15 @@ struct nlm_reboot { */ #define NLMSVC_XDRSIZE sizeof(struct nlm_args) -int nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); int nlmsvc_encode_res(struct svc_rqst *, __be32 *); diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 68e14e0f2b1f..376b8f6a3763 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,15 +22,15 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) -int nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_cancargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); int nlm4svc_encode_res(struct svc_rqst *, __be32 *); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index da3c5bc43d85..d6109fa7a57b 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -454,7 +454,7 @@ struct svc_procedure { /* process the request: */ __be32 (*pc_func)(struct svc_rqst *); /* XDR decode args: */ - int (*pc_decode)(struct svc_rqst *rqstp, + bool (*pc_decode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR encode result: */ int (*pc_encode)(struct svc_rqst *, __be32 *data); -- cgit v1.2.3 From fda494411485aff91768842c532f90fb8eb54943 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 13 Oct 2021 10:41:06 -0400 Subject: SUNRPC: Replace the "__be32 *p" parameter to .pc_encode The passed-in value of the "__be32 *p" parameter is now unused in every server-side XDR encoder, and can be removed. Note also that there is a line in each encoder that sets up a local pointer to a struct xdr_stream. Passing that pointer from the dispatcher instead saves one line per encoder function. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/lockd/svc.c | 3 +-- fs/lockd/xdr.c | 11 ++++------- fs/lockd/xdr4.c | 11 ++++------- fs/nfs/callback_xdr.c | 4 ++-- fs/nfsd/nfs2acl.c | 8 ++++---- fs/nfsd/nfs3acl.c | 8 ++++---- fs/nfsd/nfs3xdr.c | 46 ++++++++++++++++------------------------------ fs/nfsd/nfs4xdr.c | 7 ++++--- fs/nfsd/nfsd.h | 3 ++- fs/nfsd/nfssvc.c | 9 +++------ fs/nfsd/nfsxdr.c | 22 ++++++++-------------- fs/nfsd/xdr.h | 14 +++++++------- fs/nfsd/xdr3.h | 30 +++++++++++++++--------------- fs/nfsd/xdr4.h | 2 +- include/linux/lockd/xdr.h | 8 ++++---- include/linux/lockd/xdr4.h | 8 ++++---- include/linux/sunrpc/svc.h | 3 ++- 17 files changed, 85 insertions(+), 112 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 9a82471bda07..b220e1b91726 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -780,7 +780,6 @@ module_exit(exit_nlm); static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *procp = rqstp->rq_procinfo; - struct kvec *resv = rqstp->rq_res.head; svcxdr_init_decode(rqstp); if (!procp->pc_decode(rqstp, &rqstp->rq_arg_stream)) @@ -793,7 +792,7 @@ static int nlmsvc_dispatch(struct svc_rqst *rqstp, __be32 *statp) return 1; svcxdr_init_encode(rqstp); - if (!procp->pc_encode(rqstp, resv->iov_base + resv->iov_len)) + if (!procp->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; return 1; diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 622c2ca37dbf..2595b4d14cd4 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -314,15 +314,14 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ int -nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } int -nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && @@ -330,9 +329,8 @@ nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && @@ -340,9 +338,8 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p) } int -nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) +nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 45551dee26b4..32231c21c22d 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -313,15 +313,14 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ int -nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } int -nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && @@ -329,9 +328,8 @@ nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; return svcxdr_encode_cookie(xdr, &resp->cookie) && @@ -339,9 +337,8 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p) } int -nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p) +nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 4c48d85f6517..286d330488a7 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -67,9 +67,9 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp) * svc_process_common() looks for an XDR encoder to know when * not to drop a Reply. */ -static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p) +static int nfs4_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return xdr_ressize_check(rqstp, p); + return 1; } static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index cf6ba5e7937e..25592ba1ed50 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -240,9 +240,9 @@ nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ /* GETACL */ -static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) +static int +nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct inode *inode; @@ -280,9 +280,9 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) } /* ACCESS */ -static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) +static int +nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 9e9f6afb2e00..e186467b63ec 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -166,9 +166,9 @@ nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ /* GETACL */ -static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) +static int +nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_getaclres *resp = rqstp->rq_resp; struct dentry *dentry = resp->fh.fh_dentry; struct kvec *head = rqstp->rq_res.head; @@ -218,9 +218,9 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p) } /* SETACL */ -static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p) +static int +nfs3svc_encode_setaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 1f3de46d24d4..63f0be4e44f7 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -813,9 +813,8 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) /* GETATTR */ int -nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -833,9 +832,8 @@ nfs3svc_encode_getattrres(struct svc_rqst *rqstp, __be32 *p) /* SETATTR, REMOVE, RMDIR */ int -nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_attrstat *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -843,9 +841,9 @@ nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p) } /* LOOKUP */ -int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p) +int +nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -869,9 +867,8 @@ int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, __be32 *p) /* ACCESS */ int -nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -893,9 +890,8 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p) /* READLINK */ int -nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; @@ -921,9 +917,8 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) /* READ */ int -nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; @@ -954,9 +949,8 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p) /* WRITE */ int -nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_writeres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -982,9 +976,8 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p) /* CREATE, MKDIR, SYMLINK, MKNOD */ int -nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -1008,9 +1001,8 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p) /* RENAME */ int -nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_renameres *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -1020,9 +1012,8 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p) /* LINK */ int -nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_linkres *resp = rqstp->rq_resp; return svcxdr_encode_nfsstat3(xdr, resp->status) && @@ -1032,9 +1023,8 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p) /* READDIR */ int -nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; @@ -1286,9 +1276,8 @@ svcxdr_encode_fsstat3resok(struct xdr_stream *xdr, /* FSSTAT */ int -nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_fsstatres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -1333,9 +1322,8 @@ svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr, /* FSINFO */ int -nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_fsinfores *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -1376,9 +1364,8 @@ svcxdr_encode_pathconf3resok(struct xdr_stream *xdr, /* PATHCONF */ int -nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_pathconfres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) @@ -1400,9 +1387,8 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p) /* COMMIT */ int -nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p) +nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd3_commitres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c6623080ad98..fc77db35f2e7 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -5427,10 +5427,11 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) } int -nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) +nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundres *resp = rqstp->rq_resp; - struct xdr_buf *buf = resp->xdr->buf; + struct xdr_buf *buf = xdr->buf; + __be32 *p; WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len + buf->tail[0].iov_len); @@ -5443,7 +5444,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p) *p++ = resp->cstate.status; - rqstp->rq_next_page = resp->xdr->page_ptr + 1; + rqstp->rq_next_page = xdr->page_ptr + 1; *p++ = htonl(resp->taglen); memcpy(p, resp->tag, resp->taglen); diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index bfcddd4c7534..345f8247d5da 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -80,7 +80,8 @@ struct nfsd_voidargs { }; struct nfsd_voidres { }; bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p); +int nfssvc_encode_voidres(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* * Function prototypes. diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index beb564e8a3db..ed6a28ecf278 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1004,8 +1004,6 @@ out: int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) { const struct svc_procedure *proc = rqstp->rq_procinfo; - struct kvec *resv = &rqstp->rq_res.head[0]; - __be32 *p; /* * Give the xdr decoder a chance to change this if it wants @@ -1030,14 +1028,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) * Need to grab the location to store the status, as * NFSv4 does some encoding while processing */ - p = resv->iov_base + resv->iov_len; svcxdr_init_encode(rqstp); *statp = proc->pc_func(rqstp); if (*statp == rpc_drop_reply || test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; - if (!proc->pc_encode(rqstp, p)) + if (!proc->pc_encode(rqstp, &rqstp->rq_res_stream)) goto out_encode_err; nfsd_cache_update(rqstp, rqstp->rq_cachetype, statp + 1); @@ -1078,13 +1075,13 @@ bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) /** * nfssvc_encode_voidres - Encode void results * @rqstp: Server RPC transaction context - * @p: buffer in which to encode results + * @xdr: XDR stream into which to encode results * * Return values: * %0: Local error while encoding * %1: Encoding was successful */ -int nfssvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p) +int nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { return 1; } diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index b5817a41b3de..6aa8138ae2f7 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -415,18 +415,16 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ int -nfssvc_encode_statres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_stat *resp = rqstp->rq_resp; return svcxdr_encode_stat(xdr, resp->status); } int -nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) @@ -442,9 +440,8 @@ nfssvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) @@ -462,9 +459,8 @@ nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; @@ -484,9 +480,8 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; @@ -509,9 +504,8 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; @@ -532,11 +526,11 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p) } int -nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p) +nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_stream *xdr = &rqstp->rq_res_stream; struct nfsd_statfsres *resp = rqstp->rq_resp; struct kstatfs *stat = &resp->stats; + __be32 *p; if (!svcxdr_encode_stat(xdr, resp->status)) return 0; diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 31be7d30e64e..1133fb3bf328 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -152,13 +152,13 @@ bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_statres(struct svc_rqst *, __be32 *); -int nfssvc_encode_attrstatres(struct svc_rqst *, __be32 *); -int nfssvc_encode_diropres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readres(struct svc_rqst *, __be32 *); -int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *); -int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *); +int nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset); int nfssvc_encode_entry(void *data, const char *name, int namlen, diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index ef72bc4868da..bb017fc7cba1 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -281,21 +281,21 @@ bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_getattrres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *); -int nfs3svc_encode_lookupres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_createres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *); -int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *); -int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *); +int nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfs3svc_release_fhandle(struct svc_rqst *); void nfs3svc_release_fhandle2(struct svc_rqst *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 6aeb6755278f..3bd553925c35 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -758,7 +758,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *); +int nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index e1362244f909..d8bd26a5525e 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -106,9 +106,9 @@ bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_testres(struct svc_rqst *, __be32 *); -int nlmsvc_encode_res(struct svc_rqst *, __be32 *); -int nlmsvc_encode_void(struct svc_rqst *, __be32 *); -int nlmsvc_encode_shareres(struct svc_rqst *, __be32 *); +int nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 376b8f6a3763..50677be3557d 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -32,10 +32,10 @@ bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_testres(struct svc_rqst *, __be32 *); -int nlm4svc_encode_res(struct svc_rqst *, __be32 *); -int nlm4svc_encode_void(struct svc_rqst *, __be32 *); -int nlm4svc_encode_shareres(struct svc_rqst *, __be32 *); +int nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +int nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); extern const struct rpc_version nlm_version4; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d6109fa7a57b..85694cd0db66 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -457,7 +457,8 @@ struct svc_procedure { bool (*pc_decode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR encode result: */ - int (*pc_encode)(struct svc_rqst *, __be32 *data); + int (*pc_encode)(struct svc_rqst *rqstp, + struct xdr_stream *xdr); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); unsigned int pc_argsize; /* argument struct size */ -- cgit v1.2.3 From 130e2054d4a652a2bd79fb1557ddcd19c053cb37 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Wed, 13 Oct 2021 10:41:13 -0400 Subject: SUNRPC: Change return value type of .pc_encode Returning an undecorated integer is an age-old trope, but it's not clear (even to previous experts in this code) that the only valid return values are 1 and 0. These functions do not return a negative errno, rpc_stat value, or a positive length. Document there are only two valid return values by having .pc_encode return only true or false. Signed-off-by: Chuck Lever Signed-off-by: J. Bruce Fields --- fs/lockd/xdr.c | 18 ++--- fs/lockd/xdr4.c | 18 ++--- fs/nfs/callback_xdr.c | 4 +- fs/nfsd/nfs2acl.c | 4 +- fs/nfsd/nfs3acl.c | 18 ++--- fs/nfsd/nfs3xdr.c | 166 ++++++++++++++++++++++----------------------- fs/nfsd/nfs4xdr.c | 4 +- fs/nfsd/nfsd.h | 2 +- fs/nfsd/nfssvc.c | 8 +-- fs/nfsd/nfsxdr.c | 60 ++++++++-------- fs/nfsd/xdr.h | 14 ++-- fs/nfsd/xdr3.h | 30 ++++---- fs/nfsd/xdr4.h | 2 +- include/linux/lockd/xdr.h | 8 +-- include/linux/lockd/xdr4.h | 8 +-- include/linux/sunrpc/svc.h | 2 +- 16 files changed, 183 insertions(+), 183 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c index 2595b4d14cd4..2fb5748dae0c 100644 --- a/fs/lockd/xdr.c +++ b/fs/lockd/xdr.c @@ -313,13 +313,13 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) * Encode Reply results */ -int +bool nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int +bool nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_resp; @@ -328,7 +328,7 @@ nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_encode_testrply(xdr, resp); } -int +bool nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_resp; @@ -337,18 +337,18 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_encode_stats(xdr, resp->status); } -int +bool nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_encode_stats(xdr, resp->status)) - return 0; + return false; /* sequence */ if (xdr_stream_encode_u32(xdr, 0) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 32231c21c22d..856267c0864b 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -312,13 +312,13 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr) * Encode Reply results */ -int +bool nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } -int +bool nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_resp; @@ -327,7 +327,7 @@ nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_encode_testrply(xdr, resp); } -int +bool nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_resp; @@ -336,18 +336,18 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr) svcxdr_encode_stats(xdr, resp->status); } -int +bool nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nlm_res *resp = rqstp->rq_resp; if (!svcxdr_encode_cookie(xdr, &resp->cookie)) - return 0; + return false; if (!svcxdr_encode_stats(xdr, resp->status)) - return 0; + return false; /* sequence */ if (xdr_stream_encode_u32(xdr, 0) < 0) - return 0; + return false; - return 1; + return true; } diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 286d330488a7..a67c41ec545f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -67,9 +67,9 @@ static __be32 nfs4_callback_null(struct svc_rqst *rqstp) * svc_process_common() looks for an XDR encoder to know when * not to drop a Reply. */ -static int nfs4_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) +static bool nfs4_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len, diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 25592ba1ed50..367551bddfc6 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -240,7 +240,7 @@ nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ /* GETACL */ -static int +static bool nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_getaclres *resp = rqstp->rq_resp; @@ -280,7 +280,7 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) } /* ACCESS */ -static int +static bool nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_accessres *resp = rqstp->rq_resp; diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index e186467b63ec..35b2ebda14da 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -166,7 +166,7 @@ nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ /* GETACL */ -static int +static bool nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_getaclres *resp = rqstp->rq_resp; @@ -178,14 +178,14 @@ nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) int w; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: inode = d_inode(dentry); if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; base = (char *)xdr->p - (char *)head->iov_base; @@ -194,7 +194,7 @@ nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 0; + return false; w -= PAGE_SIZE; } @@ -207,18 +207,18 @@ nfs3svc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) resp->mask & NFS_DFACL, NFS_ACL_DEFAULT); if (n <= 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* SETACL */ -static int +static bool nfs3svc_encode_setaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_attrstat *resp = rqstp->rq_resp; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 63f0be4e44f7..c3ac1b6aa3aa 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -812,26 +812,26 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) */ /* GETATTR */ -int +bool nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: lease_get_mtime(d_inode(resp->fh.fh_dentry), &resp->stat.mtime); if (!svcxdr_encode_fattr3(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } /* SETATTR, REMOVE, RMDIR */ -int +bool nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_attrstat *resp = rqstp->rq_resp; @@ -841,166 +841,166 @@ nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr) } /* LOOKUP */ -int +bool nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_nfs_fh3(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->dirfh)) - return 0; + return false; } - return 1; + return true; } /* ACCESS */ -int +bool nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* READLINK */ -int +bool nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->len) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, 0, resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* READ */ -int +bool nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->eof) < 0) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* WRITE */ -int +bool nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_writeres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->committed) < 0) - return 0; + return false; if (!svcxdr_encode_writeverf3(xdr, resp->verf)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* CREATE, MKDIR, SYMLINK, MKNOD */ -int +bool nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_fh3(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->dirfh)) - return 0; + return false; } - return 1; + return true; } /* RENAME */ -int +bool nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_renameres *resp = rqstp->rq_resp; @@ -1011,7 +1011,7 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr) } /* LINK */ -int +bool nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_linkres *resp = rqstp->rq_resp; @@ -1022,33 +1022,33 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) } /* READDIR */ -int +bool nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_cookieverf3(xdr, resp->verf)) - return 0; + return false; xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } static __be32 @@ -1275,26 +1275,26 @@ svcxdr_encode_fsstat3resok(struct xdr_stream *xdr, } /* FSSTAT */ -int +bool nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_fsstatres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_fsstat3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } static bool @@ -1321,26 +1321,26 @@ svcxdr_encode_fsinfo3resok(struct xdr_stream *xdr, } /* FSINFO */ -int +bool nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_fsinfores *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_fsinfo3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } static bool @@ -1363,49 +1363,49 @@ svcxdr_encode_pathconf3resok(struct xdr_stream *xdr, } /* PATHCONF */ -int +bool nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_pathconfres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; if (!svcxdr_encode_pathconf3resok(xdr, resp)) - return 0; + return false; break; default: if (!svcxdr_encode_post_op_attr(rqstp, xdr, &nfs3svc_null_fh)) - return 0; + return false; } - return 1; + return true; } /* COMMIT */ -int +bool nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd3_commitres *resp = rqstp->rq_resp; if (!svcxdr_encode_nfsstat3(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_writeverf3(xdr, resp->verf)) - return 0; + return false; break; default: if (!svcxdr_encode_wcc_data(rqstp, xdr, &resp->fh)) - return 0; + return false; } - return 1; + return true; } /* diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fc77db35f2e7..9b609aac47e1 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -5426,7 +5426,7 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) return nfsd4_decode_compound(args); } -int +bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd4_compoundres *resp = rqstp->rq_resp; @@ -5452,5 +5452,5 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr) *p++ = htonl(resp->opcnt); nfsd4_sequence_done(resp); - return 1; + return true; } diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 345f8247d5da..498e5a489826 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -80,7 +80,7 @@ struct nfsd_voidargs { }; struct nfsd_voidres { }; bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_voidres(struct svc_rqst *rqstp, +bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index ed6a28ecf278..362e819ff06a 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -1078,12 +1078,12 @@ bool nfssvc_decode_voidarg(struct svc_rqst *rqstp, struct xdr_stream *xdr) * @xdr: XDR stream into which to encode results * * Return values: - * %0: Local error while encoding - * %1: Encoding was successful + * %false: Local error while encoding + * %true: Encoding was successful */ -int nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) +bool nfssvc_encode_voidres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { - return 1; + return true; } int nfsd_pool_stats_open(struct inode *inode, struct file *file) diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index 6aa8138ae2f7..aba8520b4b8b 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -414,7 +414,7 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr) * XDR encode functions */ -int +bool nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_stat *resp = rqstp->rq_resp; @@ -422,110 +422,110 @@ nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr) return svcxdr_encode_stat(xdr, resp->status); } -int +bool nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_attrstat *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } -int +bool nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_diropres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fhandle(xdr, &resp->fh)) - return 0; + return false; if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; break; } - return 1; + return true; } -int +bool nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_readlinkres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (xdr_stream_encode_u32(xdr, resp->len) < 0) - return 0; + return false; xdr_write_pages(xdr, &resp->page, 0, resp->len); if (svc_encode_result_payload(rqstp, head->iov_len, resp->len) < 0) - return 0; + return false; break; } - return 1; + return true; } -int +bool nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_readres *resp = rqstp->rq_resp; struct kvec *head = rqstp->rq_res.head; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->count) < 0) - return 0; + return false; xdr_write_pages(xdr, resp->pages, rqstp->rq_res.page_base, resp->count); if (svc_encode_result_payload(rqstp, head->iov_len, resp->count) < 0) - return 0; + return false; break; } - return 1; + return true; } -int +bool nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_readdirres *resp = rqstp->rq_resp; struct xdr_buf *dirlist = &resp->dirlist; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: xdr_write_pages(xdr, dirlist->pages, 0, dirlist->len); /* no more entries */ if (xdr_stream_encode_item_absent(xdr) < 0) - return 0; + return false; if (xdr_stream_encode_bool(xdr, resp->common.err == nfserr_eof) < 0) - return 0; + return false; break; } - return 1; + return true; } -int +bool nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) { struct nfsd_statfsres *resp = rqstp->rq_resp; @@ -533,12 +533,12 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) __be32 *p; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: p = xdr_reserve_space(xdr, XDR_UNIT * 5); if (!p) - return 0; + return false; *p++ = cpu_to_be32(NFSSVC_MAXBLKSIZE_V2); *p++ = cpu_to_be32(stat->f_bsize); *p++ = cpu_to_be32(stat->f_blocks); @@ -547,7 +547,7 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr) break; } - return 1; + return true; } /** diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h index 1133fb3bf328..528fb299430e 100644 --- a/fs/nfsd/xdr.h +++ b/fs/nfsd/xdr.h @@ -152,13 +152,13 @@ bool nfssvc_decode_linkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfssvc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_statres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_attrstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_diropres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_statfsres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfssvc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfssvc_encode_nfscookie(struct nfsd_readdirres *resp, u32 offset); int nfssvc_encode_entry(void *data, const char *name, int namlen, diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h index bb017fc7cba1..03fe4e21306c 100644 --- a/fs/nfsd/xdr3.h +++ b/fs/nfsd/xdr3.h @@ -281,21 +281,21 @@ bool nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nfs3svc_decode_commitargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_getattrres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_wccstat(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_lookupres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_writeres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_createres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_renameres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_linkres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_readdirres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs3svc_encode_commitres(struct svc_rqst *rqstp, struct xdr_stream *xdr); void nfs3svc_release_fhandle(struct svc_rqst *); void nfs3svc_release_fhandle2(struct svc_rqst *); diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 3bd553925c35..846ab6df9d48 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -758,7 +758,7 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp) bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp); bool nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nfs4svc_encode_compoundres(struct svc_rqst *rqstp, struct xdr_stream *xdr); __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32); void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *); void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op); diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h index d8bd26a5525e..398f70093cd3 100644 --- a/include/linux/lockd/xdr.h +++ b/include/linux/lockd/xdr.h @@ -106,9 +106,9 @@ bool nlmsvc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlmsvc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlmsvc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); #endif /* LOCKD_XDR_H */ diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 50677be3557d..9a6b55da8fd6 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -32,10 +32,10 @@ bool nlm4svc_decode_reboot(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_shareargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_notify(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); -int nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_testres(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_res(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); +bool nlm4svc_encode_shareres(struct svc_rqst *rqstp, struct xdr_stream *xdr); extern const struct rpc_version nlm_version4; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 85694cd0db66..0ae28ae6caf2 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -457,7 +457,7 @@ struct svc_procedure { bool (*pc_decode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR encode result: */ - int (*pc_encode)(struct svc_rqst *rqstp, + bool (*pc_encode)(struct svc_rqst *rqstp, struct xdr_stream *xdr); /* XDR free result: */ void (*pc_release)(struct svc_rqst *); -- cgit v1.2.3 From 40af35fdf79c77e19c597e47cc8fe9a8e200de30 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 12 Oct 2021 09:06:32 -0700 Subject: netdevice: demote the type of some dev_addr_set() helpers __dev_addr_set() and dev_addr_mod() and pretty low level, let the arguments be void, there's no chance for confusion in callers converted to use them. Keep u8 in dev_addr_set() because some of the callers are converted from a loop and we want to make sure assignments are not from an array of a different type. Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0723c1314ea2..f33af341bfb2 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4643,7 +4643,7 @@ void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ static inline void -__dev_addr_set(struct net_device *dev, const u8 *addr, size_t len) +__dev_addr_set(struct net_device *dev, const void *addr, size_t len) { memcpy(dev->dev_addr, addr, len); } @@ -4655,7 +4655,7 @@ static inline void dev_addr_set(struct net_device *dev, const u8 *addr) static inline void dev_addr_mod(struct net_device *dev, unsigned int offset, - const u8 *addr, size_t len) + const void *addr, size_t len) { memcpy(&dev->dev_addr[offset], addr, len); } -- cgit v1.2.3 From 06de2cd788bfa3b51137e9bd471d68029ab68103 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Tue, 12 Oct 2021 17:39:27 +0200 Subject: gpio: max730x: Make __max730x_remove() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An spi or i2c remove callback is only called for devices that probed successfully. In this case this implies that __max730x_probe() set a non-NULL driver data. So the check ts == NULL is never true. With this check dropped, __max730x_remove() returns zero unconditionally. Make it return void instead which makes it easier to see in the callers that there is no error to handle. Also the return value of i2c and spi remove callbacks is ignored anyway. Signed-off-by: Uwe Kleine-König Signed-off-by: Bartosz Golaszewski --- drivers/gpio/gpio-max7300.c | 4 +++- drivers/gpio/gpio-max7301.c | 4 +++- drivers/gpio/gpio-max730x.c | 6 +----- include/linux/spi/max7301.h | 2 +- 4 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-max7300.c b/drivers/gpio/gpio-max7300.c index 19cc2ed6a3f5..b2b547dd6e84 100644 --- a/drivers/gpio/gpio-max7300.c +++ b/drivers/gpio/gpio-max7300.c @@ -50,7 +50,9 @@ static int max7300_probe(struct i2c_client *client, static int max7300_remove(struct i2c_client *client) { - return __max730x_remove(&client->dev); + __max730x_remove(&client->dev); + + return 0; } static const struct i2c_device_id max7300_id[] = { diff --git a/drivers/gpio/gpio-max7301.c b/drivers/gpio/gpio-max7301.c index 1307c243b4e9..5862d73bf325 100644 --- a/drivers/gpio/gpio-max7301.c +++ b/drivers/gpio/gpio-max7301.c @@ -66,7 +66,9 @@ static int max7301_probe(struct spi_device *spi) static int max7301_remove(struct spi_device *spi) { - return __max730x_remove(&spi->dev); + __max730x_remove(&spi->dev); + + return 0; } static const struct spi_device_id max7301_id[] = { diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index b8c1fe20f49a..bb5cf14ae4c8 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -220,18 +220,14 @@ exit_destroy: } EXPORT_SYMBOL_GPL(__max730x_probe); -int __max730x_remove(struct device *dev) +void __max730x_remove(struct device *dev) { struct max7301 *ts = dev_get_drvdata(dev); - if (ts == NULL) - return -ENODEV; - /* Power down the chip and disable IRQ output */ ts->write(dev, 0x04, 0x00); gpiochip_remove(&ts->chip); mutex_destroy(&ts->lock); - return 0; } EXPORT_SYMBOL_GPL(__max730x_remove); diff --git a/include/linux/spi/max7301.h b/include/linux/spi/max7301.h index 21449067aedb..e392c53758bc 100644 --- a/include/linux/spi/max7301.h +++ b/include/linux/spi/max7301.h @@ -31,6 +31,6 @@ struct max7301_platform_data { u32 input_pullup_active; }; -extern int __max730x_remove(struct device *dev); +extern void __max730x_remove(struct device *dev); extern int __max730x_probe(struct max7301 *ts); #endif -- cgit v1.2.3 From 6312d52838b21f5c4a5afa1269a00df4364fd354 Mon Sep 17 00:00:00 2001 From: Anders Roxell Date: Wed, 13 Oct 2021 15:57:43 +0200 Subject: marvell: octeontx2: build error: unknown type name 'u64' Building an allmodconfig kernel arm64 kernel, the following build error shows up: In file included from drivers/crypto/marvell/octeontx2/cn10k_cpt.c:4: include/linux/soc/marvell/octeontx2/asm.h:38:15: error: unknown type name 'u64' 38 | static inline u64 otx2_atomic64_fetch_add(u64 incr, u64 *ptr) | ^~~ Include linux/types.h in asm.h so the compiler knows what the type 'u64' are. Fixes: af3826db74d1 ("octeontx2-pf: Use hardware register for CQE count") Signed-off-by: Anders Roxell Link: https://lore.kernel.org/r/20211013135743.3826594-1-anders.roxell@linaro.org Signed-off-by: Jakub Kicinski --- include/linux/soc/marvell/octeontx2/asm.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/soc/marvell/octeontx2/asm.h b/include/linux/soc/marvell/octeontx2/asm.h index 0f79fd7f81a1..d683251a0b40 100644 --- a/include/linux/soc/marvell/octeontx2/asm.h +++ b/include/linux/soc/marvell/octeontx2/asm.h @@ -5,6 +5,7 @@ #ifndef __SOC_OTX2_ASM_H #define __SOC_OTX2_ASM_H +#include #if defined(CONFIG_ARM64) /* * otx2_lmt_flush is used for LMT store operation. -- cgit v1.2.3 From 78b727d0281507fabf954573420790b21e34aefe Mon Sep 17 00:00:00 2001 From: Shawn Guo Date: Fri, 17 Sep 2021 11:04:34 +0800 Subject: clk: qcom: smd-rpm: Add QCM2290 RPM clock support Add support for RPM-managed clocks on the QCM2290 platform. Signed-off-by: Shawn Guo Link: https://lore.kernel.org/r/20210917030434.19859-4-shawn.guo@linaro.org Reviewed-by: Bjorn Andersson Signed-off-by: Stephen Boyd --- drivers/clk/qcom/clk-smd-rpm.c | 59 ++++++++++++++++++++++++++++++++++ include/dt-bindings/clock/qcom,rpmcc.h | 6 ++++ include/linux/soc/qcom/smd-rpm.h | 2 ++ 3 files changed, 67 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/qcom/clk-smd-rpm.c b/drivers/clk/qcom/clk-smd-rpm.c index 27fce64c2003..5776d85a1e5c 100644 --- a/drivers/clk/qcom/clk-smd-rpm.c +++ b/drivers/clk/qcom/clk-smd-rpm.c @@ -1077,6 +1077,64 @@ static const struct rpm_smd_clk_desc rpm_clk_sm6115 = { .num_clks = ARRAY_SIZE(sm6115_clks), }; +/* QCM2290 */ +DEFINE_CLK_SMD_RPM_XO_BUFFER(qcm2290, ln_bb_clk2, ln_bb_clk2_a, 0x2, 19200000); +DEFINE_CLK_SMD_RPM_XO_BUFFER(qcm2290, rf_clk3, rf_clk3_a, 6, 38400000); + +DEFINE_CLK_SMD_RPM(qcm2290, qpic_clk, qpic_a_clk, QCOM_SMD_RPM_QPIC_CLK, 0); +DEFINE_CLK_SMD_RPM(qcm2290, hwkm_clk, hwkm_a_clk, QCOM_SMD_RPM_HWKM_CLK, 0); +DEFINE_CLK_SMD_RPM(qcm2290, pka_clk, pka_a_clk, QCOM_SMD_RPM_PKA_CLK, 0); +DEFINE_CLK_SMD_RPM(qcm2290, cpuss_gnoc_clk, cpuss_gnoc_a_clk, + QCOM_SMD_RPM_MEM_CLK, 1); +DEFINE_CLK_SMD_RPM(qcm2290, bimc_gpu_clk, bimc_gpu_a_clk, + QCOM_SMD_RPM_MEM_CLK, 2); + +static struct clk_smd_rpm *qcm2290_clks[] = { + [RPM_SMD_XO_CLK_SRC] = &sdm660_bi_tcxo, + [RPM_SMD_XO_A_CLK_SRC] = &sdm660_bi_tcxo_a, + [RPM_SMD_SNOC_CLK] = &sm6125_snoc_clk, + [RPM_SMD_SNOC_A_CLK] = &sm6125_snoc_a_clk, + [RPM_SMD_BIMC_CLK] = &msm8916_bimc_clk, + [RPM_SMD_BIMC_A_CLK] = &msm8916_bimc_a_clk, + [RPM_SMD_QDSS_CLK] = &sm6125_qdss_clk, + [RPM_SMD_QDSS_A_CLK] = &sm6125_qdss_a_clk, + [RPM_SMD_LN_BB_CLK2] = &qcm2290_ln_bb_clk2, + [RPM_SMD_LN_BB_CLK2_A] = &qcm2290_ln_bb_clk2_a, + [RPM_SMD_RF_CLK3] = &qcm2290_rf_clk3, + [RPM_SMD_RF_CLK3_A] = &qcm2290_rf_clk3_a, + [RPM_SMD_CNOC_CLK] = &sm6125_cnoc_clk, + [RPM_SMD_CNOC_A_CLK] = &sm6125_cnoc_a_clk, + [RPM_SMD_IPA_CLK] = &msm8976_ipa_clk, + [RPM_SMD_IPA_A_CLK] = &msm8976_ipa_a_clk, + [RPM_SMD_QUP_CLK] = &sm6125_qup_clk, + [RPM_SMD_QUP_A_CLK] = &sm6125_qup_a_clk, + [RPM_SMD_MMRT_CLK] = &sm6125_mmrt_clk, + [RPM_SMD_MMRT_A_CLK] = &sm6125_mmrt_a_clk, + [RPM_SMD_MMNRT_CLK] = &sm6125_mmnrt_clk, + [RPM_SMD_MMNRT_A_CLK] = &sm6125_mmnrt_a_clk, + [RPM_SMD_SNOC_PERIPH_CLK] = &sm6125_snoc_periph_clk, + [RPM_SMD_SNOC_PERIPH_A_CLK] = &sm6125_snoc_periph_a_clk, + [RPM_SMD_SNOC_LPASS_CLK] = &sm6125_snoc_lpass_clk, + [RPM_SMD_SNOC_LPASS_A_CLK] = &sm6125_snoc_lpass_a_clk, + [RPM_SMD_CE1_CLK] = &msm8992_ce1_clk, + [RPM_SMD_CE1_A_CLK] = &msm8992_ce1_a_clk, + [RPM_SMD_QPIC_CLK] = &qcm2290_qpic_clk, + [RPM_SMD_QPIC_CLK_A] = &qcm2290_qpic_a_clk, + [RPM_SMD_HWKM_CLK] = &qcm2290_hwkm_clk, + [RPM_SMD_HWKM_A_CLK] = &qcm2290_hwkm_a_clk, + [RPM_SMD_PKA_CLK] = &qcm2290_pka_clk, + [RPM_SMD_PKA_A_CLK] = &qcm2290_pka_a_clk, + [RPM_SMD_BIMC_GPU_CLK] = &qcm2290_bimc_gpu_clk, + [RPM_SMD_BIMC_GPU_A_CLK] = &qcm2290_bimc_gpu_a_clk, + [RPM_SMD_CPUSS_GNOC_CLK] = &qcm2290_cpuss_gnoc_clk, + [RPM_SMD_CPUSS_GNOC_A_CLK] = &qcm2290_cpuss_gnoc_a_clk, +}; + +static const struct rpm_smd_clk_desc rpm_clk_qcm2290 = { + .clks = qcm2290_clks, + .num_clks = ARRAY_SIZE(qcm2290_clks), +}; + static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-mdm9607", .data = &rpm_clk_mdm9607 }, { .compatible = "qcom,rpmcc-msm8226", .data = &rpm_clk_msm8974 }, @@ -1089,6 +1147,7 @@ static const struct of_device_id rpm_smd_clk_match_table[] = { { .compatible = "qcom,rpmcc-msm8994", .data = &rpm_clk_msm8994 }, { .compatible = "qcom,rpmcc-msm8996", .data = &rpm_clk_msm8996 }, { .compatible = "qcom,rpmcc-msm8998", .data = &rpm_clk_msm8998 }, + { .compatible = "qcom,rpmcc-qcm2290", .data = &rpm_clk_qcm2290 }, { .compatible = "qcom,rpmcc-qcs404", .data = &rpm_clk_qcs404 }, { .compatible = "qcom,rpmcc-sdm660", .data = &rpm_clk_sdm660 }, { .compatible = "qcom,rpmcc-sm6115", .data = &rpm_clk_sm6115 }, diff --git a/include/dt-bindings/clock/qcom,rpmcc.h b/include/dt-bindings/clock/qcom,rpmcc.h index aa834d516234..fb624ff39273 100644 --- a/include/dt-bindings/clock/qcom,rpmcc.h +++ b/include/dt-bindings/clock/qcom,rpmcc.h @@ -159,5 +159,11 @@ #define RPM_SMD_SNOC_PERIPH_A_CLK 113 #define RPM_SMD_SNOC_LPASS_CLK 114 #define RPM_SMD_SNOC_LPASS_A_CLK 115 +#define RPM_SMD_HWKM_CLK 116 +#define RPM_SMD_HWKM_A_CLK 117 +#define RPM_SMD_PKA_CLK 118 +#define RPM_SMD_PKA_A_CLK 119 +#define RPM_SMD_CPUSS_GNOC_CLK 120 +#define RPM_SMD_CPUSS_GNOC_A_CLK 121 #endif diff --git a/include/linux/soc/qcom/smd-rpm.h b/include/linux/soc/qcom/smd-rpm.h index 60e66fc9b6bf..860dd8cdf9f3 100644 --- a/include/linux/soc/qcom/smd-rpm.h +++ b/include/linux/soc/qcom/smd-rpm.h @@ -38,6 +38,8 @@ struct qcom_smd_rpm; #define QCOM_SMD_RPM_IPA_CLK 0x617069 #define QCOM_SMD_RPM_CE_CLK 0x6563 #define QCOM_SMD_RPM_AGGR_CLK 0x72676761 +#define QCOM_SMD_RPM_HWKM_CLK 0x6d6b7768 +#define QCOM_SMD_RPM_PKA_CLK 0x616b70 int qcom_rpm_smd_write(struct qcom_smd_rpm *rpm, int state, -- cgit v1.2.3 From 9974cb5c879048f5144d0660c4932d98176213c4 Mon Sep 17 00:00:00 2001 From: Chen Wandun Date: Wed, 13 Oct 2021 17:47:02 +0800 Subject: net: delete redundant function declaration The implement of function netdev_all_upper_get_next_dev_rcu has been removed in: commit f1170fd462c6 ("net: Remove all_adj_list and its references") so delete redundant declaration in header file. Fixes: f1170fd462c6 ("net: Remove all_adj_list and its references") Signed-off-by: Chen Wandun Link: https://lore.kernel.org/r/20211013094702.3931071-1-chenwandun@huawei.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f33af341bfb2..173984414f38 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4801,8 +4801,6 @@ struct netdev_nested_priv { bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, - struct list_head **iter); #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); -- cgit v1.2.3 From f0ada6da3a0d69682e21f1783d02676e0fbf1bc1 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 13 Oct 2021 17:37:07 +0300 Subject: device property: Add missed header in fwnode.h When adding some stuff to the header file we must not rely on implicit dependencies that are happen by luck or bugs in other headers. Hence fwnode.h needs to use bits.h directly. Fixes: c2c724c868c4 ("driver core: Add fw_devlink_parse_fwtree()") Cc: Saravana Kannan Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211013143707.80222-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/fwnode.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 9f4ad719bfe3..3a532ba66f6c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -11,6 +11,7 @@ #include #include +#include #include struct fwnode_operations; -- cgit v1.2.3 From 5de62ea84abd732ded7c5569426fd71c0420f83e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 21 Sep 2021 22:16:02 +0200 Subject: sched,livepatch: Use wake_up_if_idle() Make sure to prod idle CPUs so they call klp_update_patch_state(). Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Petr Mladek Acked-by: Miroslav Benes Acked-by: Vasily Gorbik Tested-by: Petr Mladek Tested-by: Vasily Gorbik # on s390 Link: https://lkml.kernel.org/r/20210929151723.162004989@infradead.org --- include/linux/sched/idle.h | 4 ++++ kernel/livepatch/transition.c | 5 ++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h index 22873d276be6..d73d314d59c6 100644 --- a/include/linux/sched/idle.h +++ b/include/linux/sched/idle.h @@ -11,7 +11,11 @@ enum cpu_idle_type { CPU_MAX_IDLE_TYPES }; +#ifdef CONFIG_SMP extern void wake_up_if_idle(int cpu); +#else +static inline void wake_up_if_idle(int cpu) { } +#endif /* * Idle thread specific functions to determine the need_resched diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c index 75251e9dbc3c..5683ac0d2566 100644 --- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -413,8 +413,11 @@ void klp_try_complete_transition(void) for_each_possible_cpu(cpu) { task = idle_task(cpu); if (cpu_online(cpu)) { - if (!klp_try_switch_task(task)) + if (!klp_try_switch_task(task)) { complete = false; + /* Make idle task go through the main loop. */ + wake_up_if_idle(cpu); + } } else if (task->patch_state != klp_target_state) { /* offline idle tasks can be switched immediately */ clear_tsk_thread_flag(task, TIF_PATCH_PENDING); -- cgit v1.2.3 From 4ef0c5c6b5ba1f38f0ea1cedad0cad722f00c14a Mon Sep 17 00:00:00 2001 From: Zhang Qiao Date: Wed, 15 Sep 2021 14:40:30 +0800 Subject: kernel/sched: Fix sched_fork() access an invalid sched_task_group There is a small race between copy_process() and sched_fork() where child->sched_task_group point to an already freed pointer. parent doing fork() | someone moving the parent | to another cgroup -------------------------------+------------------------------- copy_process() + dup_task_struct()<1> parent move to another cgroup, and free the old cgroup. <2> + sched_fork() + __set_task_cpu()<3> + task_fork_fair() + sched_slice()<4> In the worst case, this bug can lead to "use-after-free" and cause panic as shown above: (1) parent copy its sched_task_group to child at <1>; (2) someone move the parent to another cgroup and free the old cgroup at <2>; (3) the sched_task_group and cfs_rq that belong to the old cgroup will be accessed at <3> and <4>, which cause a panic: [] BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 [] PGD 8000001fa0a86067 P4D 8000001fa0a86067 PUD 2029955067 PMD 0 [] Oops: 0000 [#1] SMP PTI [] CPU: 7 PID: 648398 Comm: ebizzy Kdump: loaded Tainted: G OE --------- - - 4.18.0.x86_64+ #1 [] RIP: 0010:sched_slice+0x84/0xc0 [] Call Trace: [] task_fork_fair+0x81/0x120 [] sched_fork+0x132/0x240 [] copy_process.part.5+0x675/0x20e0 [] ? __handle_mm_fault+0x63f/0x690 [] _do_fork+0xcd/0x3b0 [] do_syscall_64+0x5d/0x1d0 [] entry_SYSCALL_64_after_hwframe+0x65/0xca [] RIP: 0033:0x7f04418cd7e1 Between cgroup_can_fork() and cgroup_post_fork(), the cgroup membership and thus sched_task_group can't change. So update child's sched_task_group at sched_post_fork() and move task_fork() and __set_task_cpu() (where accees the sched_task_group) from sched_fork() to sched_post_fork(). Fixes: 8323f26ce342 ("sched: Fix race in task_group") Signed-off-by: Zhang Qiao Signed-off-by: Peter Zijlstra (Intel) Acked-by: Tejun Heo Link: https://lkml.kernel.org/r/20210915064030.2231-1-zhangqiao22@huawei.com --- include/linux/sched/task.h | 3 ++- kernel/fork.c | 2 +- kernel/sched/core.c | 43 ++++++++++++++++++++++--------------------- 3 files changed, 25 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ef02be869cf2..ba88a6987400 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -54,7 +54,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); -extern void sched_post_fork(struct task_struct *p); +extern void sched_post_fork(struct task_struct *p, + struct kernel_clone_args *kargs); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); diff --git a/kernel/fork.c b/kernel/fork.c index 38681ad44c76..0e4251dc5436 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2405,7 +2405,7 @@ static __latent_entropy struct task_struct *copy_process( write_unlock_irq(&tasklist_lock); proc_fork_connector(p); - sched_post_fork(p); + sched_post_fork(p, args); cgroup_post_fork(p, args); perf_event_fork(p); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3b55ef99c03f..935c2da00339 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4343,8 +4343,6 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, */ int sched_fork(unsigned long clone_flags, struct task_struct *p) { - unsigned long flags; - __sched_fork(clone_flags, p); /* * We mark the process as NEW here. This guarantees that @@ -4390,24 +4388,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) init_entity_runnable_average(&p->se); - /* - * The child is not yet in the pid-hash so no cgroup attach races, - * and the cgroup is pinned to this child due to cgroup_fork() - * is ran before sched_fork(). - * - * Silence PROVE_RCU. - */ - raw_spin_lock_irqsave(&p->pi_lock, flags); - rseq_migrate(p); - /* - * We're setting the CPU for the first time, we don't migrate, - * so use __set_task_cpu(). - */ - __set_task_cpu(p, smp_processor_id()); - if (p->sched_class->task_fork) - p->sched_class->task_fork(p); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); - #ifdef CONFIG_SCHED_INFO if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); @@ -4423,8 +4403,29 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) return 0; } -void sched_post_fork(struct task_struct *p) +void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs) { + unsigned long flags; +#ifdef CONFIG_CGROUP_SCHED + struct task_group *tg; +#endif + + raw_spin_lock_irqsave(&p->pi_lock, flags); +#ifdef CONFIG_CGROUP_SCHED + tg = container_of(kargs->cset->subsys[cpu_cgrp_id], + struct task_group, css); + p->sched_task_group = autogroup_task_group(p, tg); +#endif + rseq_migrate(p); + /* + * We're setting the CPU for the first time, we don't migrate, + * so use __set_task_cpu(). + */ + __set_task_cpu(p, smp_processor_id()); + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + uclamp_post_fork(p); } -- cgit v1.2.3 From 804bccba71a57e7e5deb507a4c8ebbab730909c0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Thu, 23 Sep 2021 19:54:50 -0700 Subject: sched: Fill unconditional hole induced by sched_entity With struct sched_entity before the other sched entities, its alignment won't induce a struct hole. This saves 64 bytes in defconfig task_struct: Before: ... unsigned int rt_priority; /* 120 4 */ /* XXX 4 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ const struct sched_class * sched_class; /* 128 8 */ /* XXX 56 bytes hole, try to pack */ /* --- cacheline 3 boundary (192 bytes) --- */ struct sched_entity se __attribute__((__aligned__(64))); /* 192 448 */ /* --- cacheline 10 boundary (640 bytes) --- */ struct sched_rt_entity rt; /* 640 48 */ struct sched_dl_entity dl __attribute__((__aligned__(8))); /* 688 224 */ /* --- cacheline 14 boundary (896 bytes) was 16 bytes ago --- */ After: ... unsigned int rt_priority; /* 120 4 */ /* XXX 4 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ struct sched_entity se __attribute__((__aligned__(64))); /* 128 448 */ /* --- cacheline 9 boundary (576 bytes) --- */ struct sched_rt_entity rt; /* 576 48 */ struct sched_dl_entity dl __attribute__((__aligned__(8))); /* 624 224 */ /* --- cacheline 13 boundary (832 bytes) was 16 bytes ago --- */ Summary diff: - /* size: 7040, cachelines: 110, members: 188 */ + /* size: 6976, cachelines: 109, members: 188 */ Signed-off-by: Kees Cook Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210924025450.4138503-1-keescook@chromium.org --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 193e16e2d0e4..343603f77f8b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -775,10 +775,10 @@ struct task_struct { int normal_prio; unsigned int rt_priority; - const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; struct sched_dl_entity dl; + const struct sched_class *sched_class; #ifdef CONFIG_SCHED_CORE struct rb_node core_node; -- cgit v1.2.3 From e9bdcdbf6936dd1fbf419e00222dc9038b7812c2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 11 Oct 2021 15:32:44 +0200 Subject: pid: add pidfd_get_task() helper The number of system calls making use of pidfds is constantly increasing. Some of those new system calls duplicate the code to turn a pidfd into task_struct it refers to. Give them a simple helper for this. Link: https://lore.kernel.org/r/20211004125050.1153693-2-christian.brauner@ubuntu.com Link: https://lore.kernel.org/r/20211011133245.1703103-2-brauner@kernel.org Cc: Vlastimil Babka Cc: Suren Baghdasaryan Cc: Matthew Bobrowski Cc: Alexander Duyck Cc: David Hildenbrand Cc: Jan Kara Cc: Minchan Kim Reviewed-by: Matthew Bobrowski Acked-by: David Hildenbrand Signed-off-by: Christian Brauner --- include/linux/pid.h | 1 + kernel/pid.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid.h b/include/linux/pid.h index af308e15f174..343abf22092e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -78,6 +78,7 @@ struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); +struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_create(struct pid *pid, unsigned int flags); static inline struct pid *get_pid(struct pid *pid) diff --git a/kernel/pid.c b/kernel/pid.c index efe87db44683..2fc0a16ec77b 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -539,6 +539,42 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) return pid; } +/** + * pidfd_get_task() - Get the task associated with a pidfd + * + * @pidfd: pidfd for which to get the task + * @flags: flags associated with this pidfd + * + * Return the task associated with @pidfd. The function takes a reference on + * the returned task. The caller is responsible for releasing that reference. + * + * Currently, the process identified by @pidfd is always a thread-group leader. + * This restriction currently exists for all aspects of pidfds including pidfd + * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling + * (only supports thread group leaders). + * + * Return: On success, the task_struct associated with the pidfd. + * On error, a negative errno number will be returned. + */ +struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) +{ + unsigned int f_flags; + struct pid *pid; + struct task_struct *task; + + pid = pidfd_get_pid(pidfd, &f_flags); + if (IS_ERR(pid)) + return ERR_CAST(pid); + + task = get_pid_task(pid, PIDTYPE_TGID); + put_pid(pid); + if (!task) + return ERR_PTR(-ESRCH); + + *flags = f_flags; + return task; +} + /** * pidfd_create() - Create a new pid file descriptor. * -- cgit v1.2.3 From 9f37ab0412eba537377c38b1dde1a04fbd7b5264 Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Thu, 14 Oct 2021 14:18:59 +0000 Subject: PCI/switchtec: Add check of event support Not all events are supported by every gen/variant of the Switchtec firmware. To solve this, since Gen4, a new bit in each event header is introduced to indicate if an event is supported by the firmware. Link: https://lore.kernel.org/r/20211014141859.11444-6-kelvin.cao@microchip.com Signed-off-by: Logan Gunthorpe Signed-off-by: Kelvin Cao Signed-off-by: Bjorn Helgaas --- drivers/pci/switch/switchtec.c | 8 +++++++- include/linux/switchtec.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 236cb40cc7c5..38c2b036fb8e 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -1024,6 +1024,9 @@ static int event_ctl(struct switchtec_dev *stdev, return PTR_ERR(reg); hdr = ioread32(reg); + if (hdr & SWITCHTEC_EVENT_NOT_SUPP) + return -EOPNOTSUPP; + for (i = 0; i < ARRAY_SIZE(ctl->data); i++) ctl->data[i] = ioread32(®[i + 1]); @@ -1096,7 +1099,7 @@ static int ioctl_event_ctl(struct switchtec_dev *stdev, for (ctl.index = 0; ctl.index < nr_idxs; ctl.index++) { ctl.flags = event_flags; ret = event_ctl(stdev, &ctl); - if (ret < 0) + if (ret < 0 && ret != -EOPNOTSUPP) return ret; } } else { @@ -1403,6 +1406,9 @@ static int mask_event(struct switchtec_dev *stdev, int eid, int idx) hdr_reg = event_regs[eid].map_reg(stdev, off, idx); hdr = ioread32(hdr_reg); + if (hdr & SWITCHTEC_EVENT_NOT_SUPP) + return 0; + if (!(hdr & SWITCHTEC_EVENT_OCCURRED && hdr & SWITCHTEC_EVENT_EN_IRQ)) return 0; diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index 082f1d51957a..be24056ac00f 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -19,6 +19,7 @@ #define SWITCHTEC_EVENT_EN_CLI BIT(2) #define SWITCHTEC_EVENT_EN_IRQ BIT(3) #define SWITCHTEC_EVENT_FATAL BIT(4) +#define SWITCHTEC_EVENT_NOT_SUPP BIT(31) #define SWITCHTEC_DMA_MRPC_EN BIT(0) -- cgit v1.2.3 From 766607570becbd26cab6d66a544dd8d0d964df5a Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 14 Oct 2021 07:24:31 -0700 Subject: ethernet: constify references to netdev->dev_addr in drivers This big patch sprinkles const on local variables and function arguments which may refer to netdev->dev_addr. Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. To maintain netdev->dev_addr in this tree we need to make all the writes to it got through appropriate helpers. Some of the changes here are not strictly required - const is sometimes cast off but pointer is not used for writing. It seems like it's still better to add the const in case the code changes later or relevant -W flags get enabled for the build. No functional changes. Link: https://lore.kernel.org/r/20211014142432.449314-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/actions/owl-emac.c | 2 +- drivers/net/ethernet/adaptec/starfire.c | 10 +++++----- drivers/net/ethernet/alacritech/slicoss.c | 2 +- drivers/net/ethernet/alteon/acenic.c | 4 ++-- drivers/net/ethernet/altera/altera_tse_main.c | 2 +- drivers/net/ethernet/amd/nmclan_cs.c | 3 ++- drivers/net/ethernet/amd/xgbe/xgbe-dev.c | 2 +- drivers/net/ethernet/amd/xgbe/xgbe.h | 2 +- drivers/net/ethernet/apm/xgene-v2/mac.c | 2 +- drivers/net/ethernet/apm/xgene/xgene_enet_hw.c | 2 +- drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c | 2 +- drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c | 2 +- drivers/net/ethernet/apple/bmac.c | 8 ++++---- drivers/net/ethernet/aquantia/atlantic/aq_hw.h | 6 +++--- drivers/net/ethernet/aquantia/atlantic/aq_macsec.c | 2 +- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c | 4 ++-- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c | 4 ++-- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h | 2 +- drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 4 ++-- .../ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c | 4 ++-- drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c | 2 +- drivers/net/ethernet/broadcom/b44.c | 6 ++++-- drivers/net/ethernet/broadcom/bcmsysport.c | 2 +- drivers/net/ethernet/broadcom/bgmac.c | 2 +- drivers/net/ethernet/broadcom/bnx2.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 4 ++-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h | 3 ++- drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 4 ++-- drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h | 2 +- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 ++-- drivers/net/ethernet/calxeda/xgmac.c | 2 +- drivers/net/ethernet/chelsio/cxgb/gmac.h | 2 +- drivers/net/ethernet/chelsio/cxgb/pm3393.c | 2 +- drivers/net/ethernet/chelsio/cxgb/vsc7326.c | 2 +- drivers/net/ethernet/chelsio/cxgb3/common.h | 2 +- drivers/net/ethernet/chelsio/cxgb3/xgmac.c | 2 +- drivers/net/ethernet/cisco/enic/enic_pp.c | 2 +- drivers/net/ethernet/dlink/dl2k.c | 2 +- drivers/net/ethernet/dnet.c | 6 +++--- drivers/net/ethernet/emulex/benet/be_cmds.c | 2 +- drivers/net/ethernet/emulex/benet/be_cmds.h | 2 +- drivers/net/ethernet/emulex/benet/be_main.c | 2 +- drivers/net/ethernet/ethoc.c | 2 +- drivers/net/ethernet/fealnx.c | 2 +- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 ++-- drivers/net/ethernet/freescale/fman/fman_dtsec.c | 8 ++++---- drivers/net/ethernet/freescale/fman/fman_dtsec.h | 2 +- drivers/net/ethernet/freescale/fman/fman_memac.c | 8 ++++---- drivers/net/ethernet/freescale/fman/fman_memac.h | 2 +- drivers/net/ethernet/freescale/fman/fman_tgec.c | 8 ++++---- drivers/net/ethernet/freescale/fman/fman_tgec.h | 2 +- drivers/net/ethernet/freescale/fman/mac.h | 2 +- drivers/net/ethernet/hisilicon/hisi_femac.c | 2 +- drivers/net/ethernet/hisilicon/hix5hd2_gmac.c | 2 +- drivers/net/ethernet/hisilicon/hns/hnae.h | 2 +- drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 2 +- drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h | 5 +++-- drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hnae3.h | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +- drivers/net/ethernet/i825xx/sun3_82586.c | 2 +- drivers/net/ethernet/intel/i40e/i40e.h | 2 +- drivers/net/ethernet/intel/ixgb/ixgb_hw.c | 2 +- drivers/net/ethernet/intel/ixgb/ixgb_hw.h | 2 +- drivers/net/ethernet/marvell/mv643xx_eth.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 4 ++-- drivers/net/ethernet/marvell/pxa168_eth.c | 6 +++--- drivers/net/ethernet/mediatek/mtk_star_emac.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_fs.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 2 +- drivers/net/ethernet/micrel/ks8842.c | 2 +- drivers/net/ethernet/micrel/ksz884x.c | 4 ++-- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 3 ++- drivers/net/ethernet/neterion/s2io.c | 2 +- drivers/net/ethernet/neterion/s2io.h | 2 +- drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c | 6 +++--- drivers/net/ethernet/nxp/lpc_eth.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_dev.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_dev_api.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_l2.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_main.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_mcp.h | 2 +- drivers/net/ethernet/qlogic/qed/qed_rdma.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_vf.c | 2 +- drivers/net/ethernet/qlogic/qed/qed_vf.h | 4 ++-- drivers/net/ethernet/qlogic/qede/qede_filter.c | 2 +- drivers/net/ethernet/qualcomm/emac/emac-mac.c | 2 +- drivers/net/ethernet/rdc/r6040.c | 12 ++++++------ drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h | 2 +- drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c | 3 ++- drivers/net/ethernet/sfc/ef10.c | 4 ++-- drivers/net/ethernet/sfc/ef10_sriov.c | 2 +- drivers/net/ethernet/sfc/ef10_sriov.h | 6 +++--- drivers/net/ethernet/sfc/net_driver.h | 2 +- drivers/net/ethernet/sfc/siena_sriov.c | 2 +- drivers/net/ethernet/sfc/siena_sriov.h | 2 +- drivers/net/ethernet/sis/sis900.c | 2 +- drivers/net/ethernet/smsc/smsc911x.c | 2 +- drivers/net/ethernet/smsc/smsc9420.c | 2 +- drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++-- drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c | 3 ++- drivers/net/ethernet/stmicro/stmmac/hwif.h | 3 ++- drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c | 4 ++-- drivers/net/ethernet/sun/sunbmac.c | 2 +- drivers/net/ethernet/sun/sunqe.c | 2 +- drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c | 2 +- drivers/net/ethernet/synopsys/dwc-xlgmac.h | 2 +- drivers/net/ethernet/ti/tlan.c | 4 ++-- drivers/net/ethernet/toshiba/tc35815.c | 3 ++- drivers/net/ethernet/xilinx/xilinx_emaclite.c | 7 ++++--- drivers/net/ethernet/xircom/xirc2ps_cs.c | 2 +- drivers/net/phy/mscc/mscc_main.c | 2 +- drivers/net/usb/aqc111.c | 2 +- drivers/net/usb/ax88179_178a.c | 8 ++++---- drivers/net/usb/catc.c | 2 +- drivers/net/usb/dm9601.c | 3 ++- drivers/net/usb/mcs7830.c | 3 ++- drivers/net/usb/sr9700.c | 3 ++- include/linux/qed/qed_eth_if.h | 2 +- include/linux/qed/qed_if.h | 2 +- include/linux/qed/qed_rdma_if.h | 3 ++- 134 files changed, 204 insertions(+), 189 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c index dce93acd1644..1cfdd01b4c2e 100644 --- a/drivers/net/ethernet/actions/owl-emac.c +++ b/drivers/net/ethernet/actions/owl-emac.c @@ -342,7 +342,7 @@ static u32 owl_emac_dma_cmd_stop(struct owl_emac_priv *priv) static void owl_emac_set_hw_mac_addr(struct net_device *netdev) { struct owl_emac_priv *priv = netdev_priv(netdev); - u8 *mac_addr = netdev->dev_addr; + const u8 *mac_addr = netdev->dev_addr; u32 addr_high, addr_low; addr_high = mac_addr[0] << 8 | mac_addr[1]; diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index e0f6cc910bd2..16b6b83f670b 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -955,7 +955,7 @@ static int netdev_open(struct net_device *dev) writew(0, ioaddr + PerfFilterTable + 4); writew(0, ioaddr + PerfFilterTable + 8); for (i = 1; i < 16; i++) { - __be16 *eaddrs = (__be16 *)dev->dev_addr; + const __be16 *eaddrs = (const __be16 *)dev->dev_addr; void __iomem *setup_frm = ioaddr + PerfFilterTable + i * 16; writew(be16_to_cpu(eaddrs[2]), setup_frm); setup_frm += 4; writew(be16_to_cpu(eaddrs[1]), setup_frm); setup_frm += 4; @@ -1787,14 +1787,14 @@ static void set_rx_mode(struct net_device *dev) } else if (netdev_mc_count(dev) <= 14) { /* Use the 16 element perfect filter, skip first two entries. */ void __iomem *filter_addr = ioaddr + PerfFilterTable + 2 * 16; - __be16 *eaddrs; + const __be16 *eaddrs; netdev_for_each_mc_addr(ha, dev) { eaddrs = (__be16 *) ha->addr; writew(be16_to_cpu(eaddrs[2]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 8; } - eaddrs = (__be16 *)dev->dev_addr; + eaddrs = (const __be16 *)dev->dev_addr; i = netdev_mc_count(dev) + 2; while (i++ < 16) { writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 4; @@ -1805,7 +1805,7 @@ static void set_rx_mode(struct net_device *dev) } else { /* Must use a multicast hash table. */ void __iomem *filter_addr; - __be16 *eaddrs; + const __be16 *eaddrs; __le16 mc_filter[32] __attribute__ ((aligned(sizeof(long)))); /* Multicast hash filter */ memset(mc_filter, 0, sizeof(mc_filter)); @@ -1819,7 +1819,7 @@ static void set_rx_mode(struct net_device *dev) } /* Clear the perfect filter list, skip first two entries. */ filter_addr = ioaddr + PerfFilterTable + 2 * 16; - eaddrs = (__be16 *)dev->dev_addr; + eaddrs = (const __be16 *)dev->dev_addr; for (i = 2; i < 16; i++) { writew(be16_to_cpu(eaddrs[0]), filter_addr); filter_addr += 4; writew(be16_to_cpu(eaddrs[1]), filter_addr); filter_addr += 4; diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 82f4f2608102..1fc9a1cd3ef8 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -1008,7 +1008,7 @@ static void slic_set_link_autoneg(struct slic_device *sdev) static void slic_set_mac_address(struct slic_device *sdev) { - u8 *addr = sdev->netdev->dev_addr; + const u8 *addr = sdev->netdev->dev_addr; u32 val; val = addr[5] | addr[4] << 8 | addr[3] << 16 | addr[2] << 24; diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 7aaef593b031..eeb86bd851f9 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -2712,7 +2712,7 @@ static int ace_set_mac_addr(struct net_device *dev, void *p) struct ace_private *ap = netdev_priv(dev); struct ace_regs __iomem *regs = ap->regs; struct sockaddr *addr=p; - u8 *da; + const u8 *da; struct cmd cmd; if(netif_running(dev)) @@ -2720,7 +2720,7 @@ static int ace_set_mac_addr(struct net_device *dev, void *p) eth_hw_addr_set(dev, addr->sa_data); - da = (u8 *)dev->dev_addr; + da = (const u8 *)dev->dev_addr; writel(da[0] << 8 | da[1], ®s->MacAddrHi); writel((da[2] << 24) | (da[3] << 16) | (da[4] << 8) | da[5], diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 7b75b0cd7ac9..d75d95a97dd9 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -849,7 +849,7 @@ static int init_phy(struct net_device *dev) return 0; } -static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr) +static void tse_update_mac_addr(struct altera_tse_private *priv, const u8 *addr) { u32 msb; u32 lsb; diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c index 2c07d15c8dfe..30ee5329bd7c 100644 --- a/drivers/net/ethernet/amd/nmclan_cs.c +++ b/drivers/net/ethernet/amd/nmclan_cs.c @@ -529,7 +529,8 @@ static void mace_write(mace_private *lp, unsigned int ioaddr, int reg, mace_init Resets the MACE chip. ---------------------------------------------------------------------------- */ -static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr) +static int mace_init(mace_private *lp, unsigned int ioaddr, + const char *enet_addr) { int i; int ct = 0; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index d5fd49dd25f3..3936543a74d8 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -1080,7 +1080,7 @@ static int xgbe_add_mac_addresses(struct xgbe_prv_data *pdata) return 0; } -static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, u8 *addr) +static int xgbe_set_mac_address(struct xgbe_prv_data *pdata, const u8 *addr) { unsigned int mac_addr_hi, mac_addr_lo; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 3305979a9f7c..607a2c90513b 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -729,7 +729,7 @@ struct xgbe_ext_stats { struct xgbe_hw_if { int (*tx_complete)(struct xgbe_ring_desc *); - int (*set_mac_address)(struct xgbe_prv_data *, u8 *addr); + int (*set_mac_address)(struct xgbe_prv_data *, const u8 *addr); int (*config_rx_mode)(struct xgbe_prv_data *); int (*enable_rx_csum)(struct xgbe_prv_data *); diff --git a/drivers/net/ethernet/apm/xgene-v2/mac.c b/drivers/net/ethernet/apm/xgene-v2/mac.c index 2da979e4fad1..6423e22e05b2 100644 --- a/drivers/net/ethernet/apm/xgene-v2/mac.c +++ b/drivers/net/ethernet/apm/xgene-v2/mac.c @@ -65,7 +65,7 @@ void xge_mac_set_speed(struct xge_pdata *pdata) void xge_mac_set_station_addr(struct xge_pdata *pdata) { - u8 *dev_addr = pdata->ndev->dev_addr; + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 5f657879134e..e641dbbea1e2 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -378,8 +378,8 @@ u32 xgene_enet_rd_stat(struct xgene_enet_pdata *pdata, u32 rd_addr) static void xgene_gmac_set_mac_addr(struct xgene_enet_pdata *pdata) { + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = pdata->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index f482ced2cadd..72b5e8eb0ec7 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -165,8 +165,8 @@ static void xgene_sgmac_reset(struct xgene_enet_pdata *p) static void xgene_sgmac_set_mac_addr(struct xgene_enet_pdata *p) { + const u8 *dev_addr = p->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = p->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index 304b5d43f236..86607b79c09f 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -207,8 +207,8 @@ static void xgene_pcs_reset(struct xgene_enet_pdata *pdata) static void xgene_xgmac_set_mac_addr(struct xgene_enet_pdata *pdata) { + const u8 *dev_addr = pdata->ndev->dev_addr; u32 addr0, addr1; - u8 *dev_addr = pdata->ndev->dev_addr; addr0 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index a989d2df59ad..a63ec2005af3 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -308,7 +308,7 @@ bmac_init_registers(struct net_device *dev) { struct bmac_data *bp = netdev_priv(dev); volatile unsigned short regValue; - unsigned short *pWord16; + const unsigned short *pWord16; int i; /* XXDEBUG(("bmac: enter init_registers\n")); */ @@ -371,7 +371,7 @@ bmac_init_registers(struct net_device *dev) bmwrite(dev, BHASH1, bp->hash_table_mask[2]); /* bits 47 - 32 */ bmwrite(dev, BHASH0, bp->hash_table_mask[3]); /* bits 63 - 48 */ - pWord16 = (unsigned short *)dev->dev_addr; + pWord16 = (const unsigned short *)dev->dev_addr; bmwrite(dev, MADD0, *pWord16++); bmwrite(dev, MADD1, *pWord16++); bmwrite(dev, MADD2, *pWord16); @@ -522,7 +522,7 @@ static int bmac_set_address(struct net_device *dev, void *addr) { struct bmac_data *bp = netdev_priv(dev); unsigned char *p = addr; - unsigned short *pWord16; + const unsigned short *pWord16; unsigned long flags; int i; @@ -533,7 +533,7 @@ static int bmac_set_address(struct net_device *dev, void *addr) dev->dev_addr[i] = p[i]; } /* load up the hardware address */ - pWord16 = (unsigned short *)dev->dev_addr; + pWord16 = (const unsigned short *)dev->dev_addr; bmwrite(dev, MADD0, *pWord16++); bmwrite(dev, MADD1, *pWord16++); bmwrite(dev, MADD2, *pWord16); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index bed481816ea3..062a300a566a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -217,7 +217,7 @@ struct aq_hw_ops { int (*hw_ring_tx_head_update)(struct aq_hw_s *self, struct aq_ring_s *aq_ring); - int (*hw_set_mac_address)(struct aq_hw_s *self, u8 *mac_addr); + int (*hw_set_mac_address)(struct aq_hw_s *self, const u8 *mac_addr); int (*hw_soft_reset)(struct aq_hw_s *self); @@ -226,7 +226,7 @@ struct aq_hw_ops { int (*hw_reset)(struct aq_hw_s *self); - int (*hw_init)(struct aq_hw_s *self, u8 *mac_addr); + int (*hw_init)(struct aq_hw_s *self, const u8 *mac_addr); int (*hw_start)(struct aq_hw_s *self); @@ -373,7 +373,7 @@ struct aq_fw_ops { int (*set_phyloopback)(struct aq_hw_s *self, u32 mode, bool enable); int (*set_power)(struct aq_hw_s *self, unsigned int power_state, - u8 *mac); + const u8 *mac); int (*send_fw_request)(struct aq_hw_s *self, const struct hw_fw_request_iface *fw_req, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c index 4a6dfac857ca..02058fe79f52 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c @@ -35,7 +35,7 @@ static int aq_apply_macsec_cfg(struct aq_nic_s *nic); static int aq_apply_secy_cfg(struct aq_nic_s *nic, const struct macsec_secy *secy); -static void aq_ether_addr_to_mac(u32 mac[2], unsigned char *emac) +static void aq_ether_addr_to_mac(u32 mac[2], const unsigned char *emac) { u32 tmp[2] = { 0 }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 611875ef2cd1..4625ccb79499 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -322,7 +322,7 @@ static int hw_atl_a0_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr) { unsigned int h = 0U; unsigned int l = 0U; @@ -348,7 +348,7 @@ err_exit: return err; } -static int hw_atl_a0_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_a0_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 9f1b15077e7d..d875ce3ec759 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -533,7 +533,7 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) +int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr) { unsigned int h = 0U; unsigned int l = 0U; @@ -558,7 +558,7 @@ err_exit: return err; } -static int hw_atl_b0_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl_b0_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h index d8db972113ec..5298846dd9f7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.h @@ -58,7 +58,7 @@ int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, struct aq_ring_s *ring); void hw_atl_b0_hw_init_rx_rss_ctrl1(struct aq_hw_s *self); -int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr); +int hw_atl_b0_hw_mac_addr_set(struct aq_hw_s *self, const u8 *mac_addr); int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc); int hw_atl_b0_set_loopback(struct aq_hw_s *self, u32 mode, bool enable); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 404cbf60d3f2..fc0e66006644 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -944,7 +944,7 @@ u32 hw_atl_utils_get_fw_version(struct aq_hw_s *self) } static int aq_fw1x_set_wake_magic(struct aq_hw_s *self, bool wol_enabled, - u8 *mac) + const u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; @@ -987,7 +987,7 @@ err_exit: } static int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) + const u8 *mac) { struct hw_atl_utils_fw_rpc *prpc = NULL; unsigned int rpc_size = 0U; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index ee0c22d04935..eac631c45c56 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -358,7 +358,7 @@ static int aq_fw2x_get_phy_temp(struct aq_hw_s *self, int *temp) return 0; } -static int aq_fw2x_set_wol(struct aq_hw_s *self, u8 *mac) +static int aq_fw2x_set_wol(struct aq_hw_s *self, const u8 *mac) { struct hw_atl_utils_fw_rpc *rpc = NULL; struct offload_info *info = NULL; @@ -404,7 +404,7 @@ err_exit: } static int aq_fw2x_set_power(struct aq_hw_s *self, unsigned int power_state, - u8 *mac) + const u8 *mac) { int err = 0; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c index 92f64048bf69..c98708bb044c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl2/hw_atl2.c @@ -516,7 +516,7 @@ static int hw_atl2_hw_init_rx_path(struct aq_hw_s *self) return aq_hw_err_from_flags(self); } -static int hw_atl2_hw_init(struct aq_hw_s *self, u8 *mac_addr) +static int hw_atl2_hw_init(struct aq_hw_s *self, const u8 *mac_addr) { static u32 aq_hw_atl2_igcr_table_[4][2] = { [AQ_HW_IRQ_INVALID] = { 0x20000000U, 0x20000000U }, diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 55c9e6fcb471..969591bbc066 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -218,7 +218,8 @@ static inline void __b44_cam_read(struct b44 *bp, unsigned char *data, int index data[1] = (val >> 0) & 0xFF; } -static inline void __b44_cam_write(struct b44 *bp, unsigned char *data, int index) +static inline void __b44_cam_write(struct b44 *bp, + const unsigned char *data, int index) { u32 val; @@ -1507,7 +1508,8 @@ static void bwfilter_table(struct b44 *bp, u8 *pp, u32 bytes, u32 table_offset) } } -static int b44_magic_pattern(u8 *macaddr, u8 *ppattern, u8 *pmask, int offset) +static int b44_magic_pattern(const u8 *macaddr, u8 *ppattern, u8 *pmask, + int offset) { int magicsync = 6; int k, j, len = offset; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index b813745e8de3..40933bf5a710 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1818,7 +1818,7 @@ static inline void umac_reset(struct bcm_sysport_priv *priv) } static void umac_set_hw_addr(struct bcm_sysport_priv *priv, - unsigned char *addr) + const unsigned char *addr) { u32 mac0 = (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]; diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index d2c7834850cc..7b525c65bacb 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -768,7 +768,7 @@ static void bgmac_umac_cmd_maskset(struct bgmac *bgmac, u32 mask, u32 set, udelay(2); } -static void bgmac_write_mac_address(struct bgmac *bgmac, u8 *addr) +static void bgmac_write_mac_address(struct bgmac *bgmac, const u8 *addr) { u32 tmp; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index 248b81249cb0..babc955ba64e 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -2704,7 +2704,7 @@ bnx2_alloc_bad_rbuf(struct bnx2 *bp) } static void -bnx2_set_mac_addr(struct bnx2 *bp, u8 *mac_addr, u32 pos) +bnx2_set_mac_addr(struct bnx2 *bp, const u8 *mac_addr, u32 pos) { u32 val; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index e789430f407c..2b06d78baa08 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1994,7 +1994,7 @@ int bnx2x_idle_chk(struct bnx2x *bp); * operation has been successfully scheduled and a negative - if a requested * operations has failed. */ -int bnx2x_set_mac_one(struct bnx2x *bp, u8 *mac, +int bnx2x_set_mac_one(struct bnx2x *bp, const u8 *mac, struct bnx2x_vlan_mac_obj *obj, bool set, int mac_type, unsigned long *ramrod_flags); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index ef49e38ae027..27e712178f95 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -8417,7 +8417,7 @@ alloc_mem_err: * Init service functions */ -int bnx2x_set_mac_one(struct bnx2x *bp, u8 *mac, +int bnx2x_set_mac_one(struct bnx2x *bp, const u8 *mac, struct bnx2x_vlan_mac_obj *obj, bool set, int mac_type, unsigned long *ramrod_flags) { @@ -9146,7 +9146,7 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode) else if (bp->wol) { u32 emac_base = port ? GRCBASE_EMAC1 : GRCBASE_EMAC0; - u8 *mac_addr = bp->dev->dev_addr; + const u8 *mac_addr = bp->dev->dev_addr; struct pci_dev *pdev = bp->pdev; u32 val; u16 pmc; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index 966d5722c5e2..8c2cf5519787 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -508,7 +508,8 @@ int bnx2x_vfpf_init(struct bnx2x *bp); void bnx2x_vfpf_close_vf(struct bnx2x *bp); int bnx2x_vfpf_setup_q(struct bnx2x *bp, struct bnx2x_fastpath *fp, bool is_leading); -int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set); +int bnx2x_vfpf_config_mac(struct bnx2x *bp, const u8 *addr, u8 vf_qid, + bool set); int bnx2x_vfpf_config_rss(struct bnx2x *bp, struct bnx2x_config_rss_params *params); int bnx2x_vfpf_set_mcast(struct net_device *dev); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 7c96f943c6f3..c9129b9ba446 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -721,7 +721,7 @@ out: } /* request pf to add a mac for the vf */ -int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set) +int bnx2x_vfpf_config_mac(struct bnx2x *bp, const u8 *addr, u8 vf_qid, bool set) { struct vfpf_set_q_filters_tlv *req = &bp->vf2pf_mbox->req.set_q_filters; struct pfvf_general_resp_tlv *resp = &bp->vf2pf_mbox->resp.general_resp; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 800020f4d79d..66263aa0d96b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4869,7 +4869,7 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp, #endif static int bnxt_hwrm_set_vnic_filter(struct bnxt *bp, u16 vnic_id, u16 idx, - u8 *mac_addr) + const u8 *mac_addr) { struct hwrm_cfa_l2_filter_alloc_output *resp; struct hwrm_cfa_l2_filter_alloc_input *req; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index d4ebc5d710ba..1d177fed44a6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -1151,7 +1151,7 @@ void bnxt_hwrm_exec_fwd_req(struct bnxt *bp) } } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) +int bnxt_approve_mac(struct bnxt *bp, const u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input *req; int rc = 0; @@ -1246,7 +1246,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) +int bnxt_approve_mac(struct bnxt *bp, const u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 995535e4c11b..9a4bacba477b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -41,5 +41,5 @@ int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *, bool); +int bnxt_approve_mac(struct bnxt *, const u8 *, bool); #endif diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 83c55e7b099f..ed53859b6f7d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -3266,7 +3266,7 @@ static void bcmgenet_umac_reset(struct bcmgenet_priv *priv) } static void bcmgenet_set_hw_addr(struct bcmgenet_priv *priv, - unsigned char *addr) + const unsigned char *addr) { bcmgenet_umac_writel(priv, get_unaligned_be32(&addr[0]), UMAC_MAC0); bcmgenet_umac_writel(priv, get_unaligned_be16(&addr[4]), UMAC_MAC1); @@ -3560,7 +3560,7 @@ static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue) #define MAX_MDF_FILTER 17 static inline void bcmgenet_set_mdf_addr(struct bcmgenet_priv *priv, - unsigned char *addr, + const unsigned char *addr, int *i) { bcmgenet_umac_writel(priv, addr[0] << 8 | addr[1], diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index dc51f36fdf2a..9ad89a53c3e6 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -607,7 +607,7 @@ static inline void xgmac_mac_disable(void __iomem *ioaddr) writel(value, ioaddr + XGMAC_CONTROL); } -static void xgmac_set_mac_addr(void __iomem *ioaddr, unsigned char *addr, +static void xgmac_set_mac_addr(void __iomem *ioaddr, const unsigned char *addr, int num) { u32 data; diff --git a/drivers/net/ethernet/chelsio/cxgb/gmac.h b/drivers/net/ethernet/chelsio/cxgb/gmac.h index dfa77491a910..5913eaf442b5 100644 --- a/drivers/net/ethernet/chelsio/cxgb/gmac.h +++ b/drivers/net/ethernet/chelsio/cxgb/gmac.h @@ -117,7 +117,7 @@ struct cmac_ops { const struct cmac_statistics *(*statistics_update)(struct cmac *, int); int (*macaddress_get)(struct cmac *, u8 mac_addr[6]); - int (*macaddress_set)(struct cmac *, u8 mac_addr[6]); + int (*macaddress_set)(struct cmac *, const u8 mac_addr[6]); }; typedef struct _cmac_instance cmac_instance; diff --git a/drivers/net/ethernet/chelsio/cxgb/pm3393.c b/drivers/net/ethernet/chelsio/cxgb/pm3393.c index c27908e66f5e..0bb37e4680c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb/pm3393.c +++ b/drivers/net/ethernet/chelsio/cxgb/pm3393.c @@ -496,7 +496,7 @@ static int pm3393_macaddress_get(struct cmac *cmac, u8 mac_addr[6]) return 0; } -static int pm3393_macaddress_set(struct cmac *cmac, u8 ma[6]) +static int pm3393_macaddress_set(struct cmac *cmac, const u8 ma[6]) { u32 val, lo, mid, hi, enabled = cmac->instance->enabled; diff --git a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c index a19284bdb80e..2ad3efb550c2 100644 --- a/drivers/net/ethernet/chelsio/cxgb/vsc7326.c +++ b/drivers/net/ethernet/chelsio/cxgb/vsc7326.c @@ -379,7 +379,7 @@ static int mac_intr_clear(struct cmac *mac) } /* Expect MAC address to be in network byte order. */ -static int mac_set_address(struct cmac* mac, u8 addr[6]) +static int mac_set_address(struct cmac* mac, const u8 addr[6]) { u32 val; int port = mac->instance->index; diff --git a/drivers/net/ethernet/chelsio/cxgb3/common.h b/drivers/net/ethernet/chelsio/cxgb3/common.h index b706f2fbe4f4..a309016f7f8c 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/common.h +++ b/drivers/net/ethernet/chelsio/cxgb3/common.h @@ -710,7 +710,7 @@ int t3_mac_enable(struct cmac *mac, int which); int t3_mac_disable(struct cmac *mac, int which); int t3_mac_set_mtu(struct cmac *mac, unsigned int mtu); int t3_mac_set_rx_mode(struct cmac *mac, struct net_device *dev); -int t3_mac_set_address(struct cmac *mac, unsigned int idx, u8 addr[6]); +int t3_mac_set_address(struct cmac *mac, unsigned int idx, const u8 addr[6]); int t3_mac_set_num_ucast(struct cmac *mac, int n); const struct mac_stats *t3_mac_update_stats(struct cmac *mac); int t3_mac_set_speed_duplex_fc(struct cmac *mac, int speed, int duplex, int fc); diff --git a/drivers/net/ethernet/chelsio/cxgb3/xgmac.c b/drivers/net/ethernet/chelsio/cxgb3/xgmac.c index 3af19a550372..1bdc6cad1e49 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/xgmac.c +++ b/drivers/net/ethernet/chelsio/cxgb3/xgmac.c @@ -240,7 +240,7 @@ static void set_addr_filter(struct cmac *mac, int idx, const u8 * addr) } /* Set one of the station's unicast MAC addresses. */ -int t3_mac_set_address(struct cmac *mac, unsigned int idx, u8 addr[6]) +int t3_mac_set_address(struct cmac *mac, unsigned int idx, const u8 addr[6]) { if (idx >= mac->nucast) return -EINVAL; diff --git a/drivers/net/ethernet/cisco/enic/enic_pp.c b/drivers/net/ethernet/cisco/enic/enic_pp.c index e6a83198c3dd..80f46dbd5117 100644 --- a/drivers/net/ethernet/cisco/enic/enic_pp.c +++ b/drivers/net/ethernet/cisco/enic/enic_pp.c @@ -73,9 +73,9 @@ static int enic_set_port_profile(struct enic *enic, int vf) struct vic_provinfo *vp; const u8 oui[3] = VIC_PROVINFO_CISCO_OUI; const __be16 os_type = htons(VIC_GENERIC_PROV_OS_TYPE_LINUX); + const u8 *client_mac; char uuid_str[38]; char client_mac_str[18]; - u8 *client_mac; int err; ENIC_PP_BY_INDEX(enic, vf, pp, &err); diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index 202ecb132053..993bba0ffb16 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -567,7 +567,7 @@ static void rio_hw_init(struct net_device *dev) */ for (i = 0; i < 3; i++) dw16(StationAddr0 + 2 * i, - cpu_to_le16(((u16 *)dev->dev_addr)[i])); + cpu_to_le16(((const u16 *)dev->dev_addr)[i])); set_multicast (dev); if (np->coalesce) { diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 6c51cf991dad..3ed21ba4eb99 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -60,11 +60,11 @@ static void __dnet_set_hwaddr(struct dnet *bp) { u16 tmp; - tmp = be16_to_cpup((__be16 *)bp->dev->dev_addr); + tmp = be16_to_cpup((const __be16 *)bp->dev->dev_addr); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_0_REG, tmp); - tmp = be16_to_cpup((__be16 *)(bp->dev->dev_addr + 2)); + tmp = be16_to_cpup((const __be16 *)(bp->dev->dev_addr + 2)); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_1_REG, tmp); - tmp = be16_to_cpup((__be16 *)(bp->dev->dev_addr + 4)); + tmp = be16_to_cpup((const __be16 *)(bp->dev->dev_addr + 4)); dnet_writew_mac(bp, DNET_INTERNAL_MAC_ADDR_2_REG, tmp); } diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 649c5c429bd7..528eb0f223b1 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1080,7 +1080,7 @@ err: } /* Uses synchronous MCCQ */ -int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, +int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain) { struct be_mcc_wrb *wrb; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index c30d6d6f0f3a..db1f3b908582 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -2385,7 +2385,7 @@ int be_pci_fnum_get(struct be_adapter *adapter); int be_fw_wait_ready(struct be_adapter *adapter); int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr, bool permanent, u32 if_handle, u32 pmac_id); -int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr, u32 if_id, +int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr, u32 if_id, u32 *pmac_id, u32 domain); int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 domain); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 736a6ea86eb1..d51f24c9e1b8 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -272,7 +272,7 @@ void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped) iowrite32(val, adapter->db + DB_CQ_OFFSET); } -static int be_dev_mac_add(struct be_adapter *adapter, u8 *mac) +static int be_dev_mac_add(struct be_adapter *adapter, const u8 *mac) { int i; diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index cd3a3b8f23b6..ed2ef167cdb2 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -802,8 +802,8 @@ static int ethoc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void ethoc_do_set_mac_address(struct net_device *dev) { + const unsigned char *mac = dev->dev_addr; struct ethoc *priv = netdev_priv(dev); - unsigned char *mac = dev->dev_addr; ethoc_write(priv, MAC_ADDR0, (mac[2] << 24) | (mac[3] << 16) | (mac[4] << 8) | (mac[5] << 0)); diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index 25c91b3c5fd3..63c935e7b625 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -827,7 +827,7 @@ static int netdev_open(struct net_device *dev) return -EAGAIN; for (i = 0; i < 3; i++) - iowrite16(((unsigned short*)dev->dev_addr)[i], + iowrite16(((const unsigned short *)dev->dev_addr)[i], ioaddr + PAR0 + i*2); init_ring(dev); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index cd8a7d94f60c..6b2927d863e2 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -272,7 +272,7 @@ static int dpaa_netdev_init(struct net_device *net_dev, } else { eth_hw_addr_random(net_dev); err = priv->mac_dev->change_addr(priv->mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err) { dev_err(dev, "Failed to set random MAC address\n"); return -EINVAL; @@ -452,7 +452,7 @@ static int dpaa_set_mac_address(struct net_device *net_dev, void *addr) mac_dev = priv->mac_dev; err = mac_dev->change_addr(mac_dev->fman_mac, - (enet_addr_t *)net_dev->dev_addr); + (const enet_addr_t *)net_dev->dev_addr); if (err < 0) { netif_err(priv, drv, net_dev, "mac_dev->change_addr() = %d\n", err); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c index bce3c9398887..1950a8936bc0 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c @@ -366,7 +366,7 @@ static void set_dflts(struct dtsec_cfg *cfg) cfg->maximum_frame = DEFAULT_MAXIMUM_FRAME; } -static void set_mac_address(struct dtsec_regs __iomem *regs, u8 *adr) +static void set_mac_address(struct dtsec_regs __iomem *regs, const u8 *adr) { u32 tmp; @@ -516,7 +516,7 @@ static int init(struct dtsec_regs __iomem *regs, struct dtsec_cfg *cfg, if (addr) { MAKE_ENET_ADDR_FROM_UINT64(addr, eth_addr); - set_mac_address(regs, (u8 *)eth_addr); + set_mac_address(regs, (const u8 *)eth_addr); } /* HASH */ @@ -1022,7 +1022,7 @@ int dtsec_accept_rx_pause_frames(struct fman_mac *dtsec, bool en) return 0; } -int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) +int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr) { struct dtsec_regs __iomem *regs = dtsec->regs; enum comm_mode mode = COMM_MODE_NONE; @@ -1041,7 +1041,7 @@ int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr) * Station address have to be swapped (big endian to little endian */ dtsec->addr = ENET_ADDR_TO_UINT64(*enet_addr); - set_mac_address(dtsec->regs, (u8 *)(*enet_addr)); + set_mac_address(dtsec->regs, (const u8 *)(*enet_addr)); graceful_start(dtsec, mode); diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h index 5149d96ec2c1..68512c3bd6e5 100644 --- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h +++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h @@ -37,7 +37,7 @@ struct fman_mac *dtsec_config(struct fman_mac_params *params); int dtsec_set_promiscuous(struct fman_mac *dtsec, bool new_val); -int dtsec_modify_mac_address(struct fman_mac *dtsec, enet_addr_t *enet_addr); +int dtsec_modify_mac_address(struct fman_mac *dtsec, const enet_addr_t *enet_addr); int dtsec_adjust_link(struct fman_mac *dtsec, u16 speed); int dtsec_restart_autoneg(struct fman_mac *dtsec); diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 62f42921933d..2216b7f51d26 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -354,7 +354,7 @@ struct fman_mac { bool allmulti_enabled; }; -static void add_addr_in_paddr(struct memac_regs __iomem *regs, u8 *adr, +static void add_addr_in_paddr(struct memac_regs __iomem *regs, const u8 *adr, u8 paddr_num) { u32 tmp0, tmp1; @@ -897,12 +897,12 @@ int memac_accept_rx_pause_frames(struct fman_mac *memac, bool en) return 0; } -int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr) +int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr) { if (!is_init_done(memac->memac_drv_param)) return -EINVAL; - add_addr_in_paddr(memac->regs, (u8 *)(*enet_addr), 0); + add_addr_in_paddr(memac->regs, (const u8 *)(*enet_addr), 0); return 0; } @@ -1058,7 +1058,7 @@ int memac_init(struct fman_mac *memac) /* MAC Address */ if (memac->addr != 0) { MAKE_ENET_ADDR_FROM_UINT64(memac->addr, eth_addr); - add_addr_in_paddr(memac->regs, (u8 *)eth_addr, 0); + add_addr_in_paddr(memac->regs, (const u8 *)eth_addr, 0); } fixed_link = memac_drv_param->fixed_link; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h index b2c671ec0ce7..3820f7a22983 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.h +++ b/drivers/net/ethernet/freescale/fman/fman_memac.h @@ -40,7 +40,7 @@ struct fman_mac *memac_config(struct fman_mac_params *params); int memac_set_promiscuous(struct fman_mac *memac, bool new_val); -int memac_modify_mac_address(struct fman_mac *memac, enet_addr_t *enet_addr); +int memac_modify_mac_address(struct fman_mac *memac, const enet_addr_t *enet_addr); int memac_adjust_link(struct fman_mac *memac, u16 speed); int memac_cfg_max_frame_len(struct fman_mac *memac, u16 new_val); int memac_cfg_reset_on_init(struct fman_mac *memac, bool enable); diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c index 41946b16f6c7..311c1906e044 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.c +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c @@ -221,7 +221,7 @@ struct fman_mac { bool allmulti_enabled; }; -static void set_mac_address(struct tgec_regs __iomem *regs, u8 *adr) +static void set_mac_address(struct tgec_regs __iomem *regs, const u8 *adr) { u32 tmp0, tmp1; @@ -514,13 +514,13 @@ int tgec_accept_rx_pause_frames(struct fman_mac *tgec, bool en) return 0; } -int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *p_enet_addr) +int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *p_enet_addr) { if (!is_init_done(tgec->cfg)) return -EINVAL; tgec->addr = ENET_ADDR_TO_UINT64(*p_enet_addr); - set_mac_address(tgec->regs, (u8 *)(*p_enet_addr)); + set_mac_address(tgec->regs, (const u8 *)(*p_enet_addr)); return 0; } @@ -704,7 +704,7 @@ int tgec_init(struct fman_mac *tgec) if (tgec->addr) { MAKE_ENET_ADDR_FROM_UINT64(tgec->addr, eth_addr); - set_mac_address(tgec->regs, (u8 *)eth_addr); + set_mac_address(tgec->regs, (const u8 *)eth_addr); } /* interrupts */ diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h index 3bfd1062b386..b28b20b26148 100644 --- a/drivers/net/ethernet/freescale/fman/fman_tgec.h +++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h @@ -37,7 +37,7 @@ struct fman_mac *tgec_config(struct fman_mac_params *params); int tgec_set_promiscuous(struct fman_mac *tgec, bool new_val); -int tgec_modify_mac_address(struct fman_mac *tgec, enet_addr_t *enet_addr); +int tgec_modify_mac_address(struct fman_mac *tgec, const enet_addr_t *enet_addr); int tgec_cfg_max_frame_len(struct fman_mac *tgec, u16 new_val); int tgec_enable(struct fman_mac *tgec, enum comm_mode mode); int tgec_disable(struct fman_mac *tgec, enum comm_mode mode); diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h index 824a81a9f350..daa285a9b8b2 100644 --- a/drivers/net/ethernet/freescale/fman/mac.h +++ b/drivers/net/ethernet/freescale/fman/mac.h @@ -66,7 +66,7 @@ struct mac_device { int (*stop)(struct mac_device *mac_dev); void (*adjust_link)(struct mac_device *mac_dev); int (*set_promisc)(struct fman_mac *mac_dev, bool enable); - int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr); + int (*change_addr)(struct fman_mac *mac_dev, const enet_addr_t *enet_addr); int (*set_allmulti)(struct fman_mac *mac_dev, bool enable); int (*set_tstamp)(struct fman_mac *mac_dev, bool enable); int (*set_multi)(struct net_device *net_dev, diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 29190eb890c8..a6c18b6527f9 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -427,7 +427,7 @@ static void hisi_femac_free_skb_rings(struct hisi_femac_priv *priv) } static int hisi_femac_set_hw_mac_addr(struct hisi_femac_priv *priv, - unsigned char *mac) + const unsigned char *mac) { u32 reg; diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index 5f7ccdc834b7..d7e62eca050f 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -429,7 +429,7 @@ static void hix5hd2_port_disable(struct hix5hd2_priv *priv) static void hix5hd2_hw_set_mac_addr(struct net_device *dev) { struct hix5hd2_priv *priv = netdev_priv(dev); - unsigned char *mac = dev->dev_addr; + const unsigned char *mac = dev->dev_addr; u32 val; val = mac[1] | (mac[0] << 8); diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index d46e8f999019..d72657444ef3 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -499,7 +499,7 @@ struct hnae_ae_ops { u32 *tx_usecs_high, u32 *rx_usecs_high); void (*set_promisc_mode)(struct hnae_handle *handle, u32 en); int (*get_mac_addr)(struct hnae_handle *handle, void **p); - int (*set_mac_addr)(struct hnae_handle *handle, void *p); + int (*set_mac_addr)(struct hnae_handle *handle, const void *p); int (*add_uc_addr)(struct hnae_handle *handle, const unsigned char *addr); int (*rm_uc_addr)(struct hnae_handle *handle, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index e81116ad9bdf..bc3e406f0139 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -206,7 +206,7 @@ static void hns_ae_fini_queue(struct hnae_queue *q) hns_rcb_reset_ring_hw(q); } -static int hns_ae_set_mac_address(struct hnae_handle *handle, void *p) +static int hns_ae_set_mac_address(struct hnae_handle *handle, const void *p) { int ret; struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index f387a859a201..8f391e2adcc0 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -450,7 +450,7 @@ static void hns_gmac_update_stats(void *mac_drv) += dsaf_read_dev(drv, GMAC_TX_PAUSE_FRAMES_REG); } -static void hns_gmac_set_mac_addr(void *mac_drv, char *mac_addr) +static void hns_gmac_set_mac_addr(void *mac_drv, const char *mac_addr) { struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index f41379de2186..7edf8569514c 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -240,7 +240,7 @@ int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, u8 vmid, u8 *port_num) *@addr:mac address */ int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, - u32 vmid, char *addr) + u32 vmid, const char *addr) { int ret; struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index 8943ffab4418..e3bb05959ba9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -348,7 +348,7 @@ struct mac_driver { /*disable mac when disable nic or dsaf*/ void (*mac_disable)(void *mac_drv, enum mac_commom_mode mode); /* config mac address*/ - void (*set_mac_addr)(void *mac_drv, char *mac_addr); + void (*set_mac_addr)(void *mac_drv, const char *mac_addr); /*adjust mac mode of port,include speed and duplex*/ int (*adjust_link)(void *mac_drv, enum mac_speed speed, u32 full_duplex); @@ -425,7 +425,8 @@ int hns_mac_init(struct dsaf_device *dsaf_dev); void mac_adjust_link(struct net_device *net_dev); bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status); -int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, char *addr); +int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, + const char *addr); int hns_mac_set_multi(struct hns_mac_cb *mac_cb, u32 port_num, char *addr, bool enable); int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, bool enable); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c index 401fef5f1d07..fc26ffaae620 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -255,7 +255,7 @@ static void hns_xgmac_pausefrm_cfg(void *mac_drv, u32 rx_en, u32 tx_en) dsaf_write_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG, origin); } -static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, char *mac_addr) +static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, const char *mac_addr) { struct mac_driver *drv = (struct mac_driver *)mac_drv; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 5d188573c433..98d63e804903 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -595,7 +595,7 @@ struct hnae3_ae_ops { u32 *tx_usecs_high, u32 *rx_usecs_high); void (*get_mac_addr)(struct hnae3_handle *handle, u8 *p); - int (*set_mac_addr)(struct hnae3_handle *handle, void *p, + int (*set_mac_addr)(struct hnae3_handle *handle, const void *p, bool is_first); int (*do_ioctl)(struct hnae3_handle *handle, struct ifreq *ifr, int cmd); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index cd981b33d4ff..7bb34af3981e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9442,7 +9442,7 @@ int hclge_update_mac_node_for_dev_addr(struct hclge_vport *vport, return 0; } -static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, +static int hclge_set_mac_addr(struct hnae3_handle *handle, const void *p, bool is_first) { const unsigned char *new_addr = (const unsigned char *)p; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 5fdac8685f95..2e6dcf75fba6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1349,7 +1349,7 @@ static void hclgevf_get_mac_addr(struct hnae3_handle *handle, u8 *p) ether_addr_copy(p, hdev->hw.mac.mac_addr); } -static int hclgevf_set_mac_addr(struct hnae3_handle *handle, void *p, +static int hclgevf_set_mac_addr(struct hnae3_handle *handle, const void *p, bool is_first) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); diff --git a/drivers/net/ethernet/i825xx/sun3_82586.c b/drivers/net/ethernet/i825xx/sun3_82586.c index 0696f723228a..18d32302c3c7 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.c +++ b/drivers/net/ethernet/i825xx/sun3_82586.c @@ -461,7 +461,7 @@ static int init586(struct net_device *dev) ias_cmd->cmd_cmd = swab16(CMD_IASETUP | CMD_LAST); ias_cmd->cmd_link = 0xffff; - memcpy((char *)&ias_cmd->iaddr,(char *) dev->dev_addr,ETH_ALEN); + memcpy((char *)&ias_cmd->iaddr,(const char *) dev->dev_addr,ETH_ALEN); p->scb->cbl_offset = make16(ias_cmd); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 39fb3d57c057..3d528fba754b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -435,7 +435,7 @@ static inline bool i40e_is_channel_macvlan(struct i40e_channel *ch) return !!ch->fwd; } -static inline u8 *i40e_channel_mac(struct i40e_channel *ch) +static inline const u8 *i40e_channel_mac(struct i40e_channel *ch) { if (i40e_is_channel_macvlan(ch)) return ch->fwd->netdev->dev_addr; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c index a430871d1c27..c8d1e815ec6b 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c @@ -549,7 +549,7 @@ ixgb_mta_set(struct ixgb_hw *hw, *****************************************************************************/ void ixgb_rar_set(struct ixgb_hw *hw, - u8 *addr, + const u8 *addr, u32 index) { u32 rar_low, rar_high; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h index 6064583095da..70bcff5fb3db 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h @@ -740,7 +740,7 @@ bool ixgb_adapter_start(struct ixgb_hw *hw); void ixgb_check_for_link(struct ixgb_hw *hw); bool ixgb_check_for_bad_link(struct ixgb_hw *hw); -void ixgb_rar_set(struct ixgb_hw *hw, u8 *addr, u32 index); +void ixgb_rar_set(struct ixgb_hw *hw, const u8 *addr, u32 index); /* Filters (multicast, vlan, receive) */ void ixgb_mc_addr_list_update(struct ixgb_hw *hw, u8 *mc_addr_list, diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 654ec25e6705..a63d9a5c8059 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1770,7 +1770,7 @@ static void uc_addr_get(struct mv643xx_eth_private *mp, unsigned char *addr) addr[5] = mac_l & 0xff; } -static void uc_addr_set(struct mv643xx_eth_private *mp, unsigned char *addr) +static void uc_addr_set(struct mv643xx_eth_private *mp, const u8 *addr) { wrlp(mp, MAC_ADDR_HIGH, (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 761155af25d8..e2ce84ecb7a6 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1623,8 +1623,8 @@ static void mvneta_set_ucast_addr(struct mvneta_port *pp, u8 last_nibble, } /* Set mac address */ -static void mvneta_mac_addr_set(struct mvneta_port *pp, unsigned char *addr, - int queue) +static void mvneta_mac_addr_set(struct mvneta_port *pp, + const unsigned char *addr, int queue) { unsigned int mac_h; unsigned int mac_l; diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 898b513f74e0..bb5341020803 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -389,7 +389,7 @@ static void inverse_every_nibble(unsigned char *mac_addr) * Outputs * return the calculated entry. */ -static u32 hash_function(unsigned char *mac_addr_orig) +static u32 hash_function(const unsigned char *mac_addr_orig) { u32 hash_result; u32 addr0; @@ -434,7 +434,7 @@ static u32 hash_function(unsigned char *mac_addr_orig) * -ENOSPC if table full */ static int add_del_hash_entry(struct pxa168_eth_private *pep, - unsigned char *mac_addr, + const unsigned char *mac_addr, u32 rd, u32 skip, int del) { struct addr_table_entry *entry, *start; @@ -521,7 +521,7 @@ static int add_del_hash_entry(struct pxa168_eth_private *pep, */ static void update_hash_table_mac_address(struct pxa168_eth_private *pep, unsigned char *oaddr, - unsigned char *addr) + const unsigned char *addr) { /* Delete old entry */ if (oaddr) diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c index e2ebfd8115a0..89ca7960b225 100644 --- a/drivers/net/ethernet/mediatek/mtk_star_emac.c +++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c @@ -523,7 +523,7 @@ static void mtk_star_dma_resume_tx(struct mtk_star_priv *priv) static void mtk_star_set_mac_addr(struct net_device *ndev) { struct mtk_star_priv *priv = netdev_priv(ndev); - u8 *mac_addr = ndev->dev_addr; + const u8 *mac_addr = ndev->dev_addr; unsigned int high, low; high = mac_addr[0] << 8 | mac_addr[1] << 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index c06b4b938ae7..73a377c8a2da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -71,12 +71,12 @@ struct mlx5e_l2_hash_node { bool mpfs; }; -static inline int mlx5e_hash_l2(u8 *addr) +static inline int mlx5e_hash_l2(const u8 *addr) { return addr[5]; } -static void mlx5e_add_l2_to_hash(struct hlist_head *hash, u8 *addr) +static void mlx5e_add_l2_to_hash(struct hlist_head *hash, const u8 *addr) { struct mlx5e_l2_hash_node *hn; int ix = mlx5e_hash_l2(addr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 269ebb53eda6..f7ebc1f9283f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -219,7 +219,7 @@ void mlx5i_uninit_underlay_qp(struct mlx5e_priv *priv) int mlx5i_create_underlay_qp(struct mlx5e_priv *priv) { - unsigned char *dev_addr = priv->netdev->dev_addr; + const unsigned char *dev_addr = priv->netdev->dev_addr; u32 out[MLX5_ST_SZ_DW(create_qp_out)] = {}; u32 in[MLX5_ST_SZ_DW(create_qp_in)] = {}; struct mlx5i_priv *ipriv = priv->ppriv; diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c index 37ccf8c570b5..0f2cdcd4a4c0 100644 --- a/drivers/net/ethernet/micrel/ks8842.c +++ b/drivers/net/ethernet/micrel/ks8842.c @@ -380,7 +380,7 @@ static void ks8842_read_mac_addr(struct ks8842_adapter *adapter, u8 *dest) } } -static void ks8842_write_mac_addr(struct ks8842_adapter *adapter, u8 *mac) +static void ks8842_write_mac_addr(struct ks8842_adapter *adapter, const u8 *mac) { unsigned long flags; unsigned i; diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index a1f7f45b9d08..03ad8bdc1f0d 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -4033,7 +4033,7 @@ static void hw_set_add_addr(struct ksz_hw *hw) } } -static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr) +static int hw_add_addr(struct ksz_hw *hw, const u8 *mac_addr) { int i; int j = ADDITIONAL_ENTRIES; @@ -4054,7 +4054,7 @@ static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr) return -1; } -static int hw_del_addr(struct ksz_hw *hw, u8 *mac_addr) +static int hw_del_addr(struct ksz_hw *hw, const u8 *mac_addr) { int i; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 32760f87bf8a..5ae59b1e5b48 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -796,7 +796,8 @@ static int myri10ge_load_firmware(struct myri10ge_priv *mgp, int adopt) return status; } -static int myri10ge_update_mac_address(struct myri10ge_priv *mgp, u8 * addr) +static int myri10ge_update_mac_address(struct myri10ge_priv *mgp, + const u8 * addr) { struct myri10ge_cmd cmd; int status; diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 5454c1c2f8ad..ea0b2f3fd9c6 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5217,7 +5217,7 @@ static int s2io_set_mac_addr(struct net_device *dev, void *p) * as defined in errno.h file on failure. */ -static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr) +static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr) { struct s2io_nic *sp = netdev_priv(dev); register u64 mac_addr = 0, perm_addr = 0; diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 5a6032212c19..a4266d1544ab 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1073,7 +1073,7 @@ static void s2io_reset(struct s2io_nic * sp); static int s2io_poll_msix(struct napi_struct *napi, int budget); static int s2io_poll_inta(struct napi_struct *napi, int budget); static void s2io_init_pci(struct s2io_nic * sp); -static int do_s2io_prog_unicast(struct net_device *dev, u8 *addr); +static int do_s2io_prog_unicast(struct net_device *dev, const u8 *addr); static void s2io_alarm_handle(struct timer_list *t); static irqreturn_t s2io_msix_ring_handle(int irq, void *dev_id); diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index ab70179728f6..dfb4468fe287 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -837,7 +837,7 @@ nfp_tunnel_put_ipv6_off(struct nfp_app *app, struct nfp_ipv6_addr_entry *entry) } static int -__nfp_tunnel_offload_mac(struct nfp_app *app, u8 *mac, u16 idx, bool del) +__nfp_tunnel_offload_mac(struct nfp_app *app, const u8 *mac, u16 idx, bool del) { struct nfp_tun_mac_addr_offload payload; @@ -886,7 +886,7 @@ static bool nfp_tunnel_is_mac_idx_global(u16 nfp_mac_idx) } static struct nfp_tun_offloaded_mac * -nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, u8 *mac) +nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, const u8 *mac) { struct nfp_flower_priv *priv = app->priv; @@ -1005,7 +1005,7 @@ err_free_ida: static int nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, - u8 *mac, bool mod) + const u8 *mac, bool mod) { struct nfp_flower_priv *priv = app->priv; struct nfp_flower_repr_priv *repr_priv; diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 43fd569aa5f1..fbfbf94e0377 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -419,7 +419,7 @@ struct netdata_local { /* * MAC support functions */ -static void __lpc_set_mac(struct netdata_local *pldat, u8 *mac) +static void __lpc_set_mac(struct netdata_local *pldat, const u8 *mac) { u32 tmp; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 6823016ab5a3..18f3bf7c4dfe 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -952,7 +952,7 @@ qed_llh_remove_filter(struct qed_hwfn *p_hwfn, } int qed_llh_add_mac_filter(struct qed_dev *cdev, - u8 ppfid, u8 mac_addr[ETH_ALEN]) + u8 ppfid, const u8 mac_addr[ETH_ALEN]) { struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *p_ptt = qed_ptt_acquire(p_hwfn); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h index 6582bfc1b4a9..f8682356d0cf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h +++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h @@ -364,7 +364,7 @@ int qed_llh_set_roce_affinity(struct qed_dev *cdev, enum qed_eng eng); * Return: Int. */ int qed_llh_add_mac_filter(struct qed_dev *cdev, - u8 ppfid, u8 mac_addr[ETH_ALEN]); + u8 ppfid, const u8 mac_addr[ETH_ALEN]); /** * qed_llh_remove_mac_filter(): Remove a LLH MAC filter from the given diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index a116fbc59725..2edd6bf64a3c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2848,7 +2848,7 @@ static int qed_fp_cqe_completion(struct qed_dev *dev, cqe); } -static int qed_req_bulletin_update_mac(struct qed_dev *cdev, u8 *mac) +static int qed_req_bulletin_update_mac(struct qed_dev *cdev, const u8 *mac) { int i, ret; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 5e7242304ee2..29f9711bf438 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -2887,7 +2887,7 @@ static int qed_update_drv_state(struct qed_dev *cdev, bool active) return status; } -static int qed_update_mac(struct qed_dev *cdev, u8 *mac) +static int qed_update_mac(struct qed_dev *cdev, const u8 *mac) { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); struct qed_ptt *ptt; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 11a52a4a673b..64678a256f3b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -2851,7 +2851,7 @@ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, } int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u8 *mac) + struct qed_ptt *p_ptt, const u8 *mac) { struct qed_mcp_mb_params mb_params; u32 mfw_mac[2]; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 9e1de1191bd4..564723800d15 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -536,7 +536,7 @@ int qed_mcp_ov_update_mtu(struct qed_hwfn *p_hwfn, * Return: Int - 0 - Operation was successul. */ int qed_mcp_ov_update_mac(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, u8 *mac); + struct qed_ptt *p_ptt, const u8 *mac); /** * qed_mcp_ov_update_wol(): Send WOL mode to MFW. diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index fe0bb11d0e43..7f3e84b8622d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1965,7 +1965,7 @@ static void qed_rdma_remove_user(void *rdma_cxt, u16 dpi) static int qed_roce_ll2_set_mac_filter(struct qed_dev *cdev, u8 *old_mac_address, - u8 *new_mac_address) + const u8 *new_mac_address) { int rc = 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 220a95fa96e1..597cd9cd57b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1373,7 +1373,7 @@ exit: int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, - u8 *p_mac) + const u8 *p_mac) { struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; struct vfpf_bulletin_update_mac_tlv *p_req; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 8718760443be..306b5f4bc632 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -1070,7 +1070,7 @@ u32 qed_vf_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id); * * Return: Int. */ -int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, u8 *p_mac); +int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, const u8 *p_mac); #else static inline void qed_vf_get_link_params(struct qed_hwfn *p_hwfn, @@ -1259,7 +1259,7 @@ static inline int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, } static inline int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, - u8 *p_mac) + const u8 *p_mac) { return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 03c51dd37e1f..3010833ddde3 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -617,7 +617,7 @@ void qede_fill_rss_params(struct qede_dev *edev, static int qede_set_ucast_rx_mac(struct qede_dev *edev, enum qed_filter_xcast_params_type opcode, - unsigned char mac[ETH_ALEN]) + const unsigned char mac[ETH_ALEN]) { struct qed_filter_ucast_params ucast; diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 87b8c032195d..06104d2ff5b3 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -420,7 +420,7 @@ static void emac_mac_dma_config(struct emac_adapter *adpt) } /* set MAC address */ -static void emac_set_mac_address(struct emac_adapter *adpt, u8 *addr) +static void emac_set_mac_address(struct emac_adapter *adpt, const u8 *addr) { u32 sta; diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index 01ef5efd7bc2..a8f282c43a78 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -453,7 +453,7 @@ static void r6040_down(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; + const u16 *adrp; /* Stop MAC */ iowrite16(MSK_INT, ioaddr + MIER); /* Mask Off Interrupt */ @@ -462,7 +462,7 @@ static void r6040_down(struct net_device *dev) r6040_reset_mac(lp); /* Restore MAC Address to MIDx */ - adrp = (u16 *) dev->dev_addr; + adrp = (const u16 *) dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -731,13 +731,13 @@ static void r6040_mac_address(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; + const u16 *adrp; /* Reset MAC */ r6040_reset_mac(lp); /* Restore MAC Address */ - adrp = (u16 *) dev->dev_addr; + adrp = (const u16 *) dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); @@ -849,13 +849,13 @@ static void r6040_multicast_list(struct net_device *dev) unsigned long flags; struct netdev_hw_addr *ha; int i; - u16 *adrp; + const u16 *adrp; u16 hash_table[4] = { 0 }; spin_lock_irqsave(&lp->lock, flags); /* Keep our MAC Address */ - adrp = (u16 *)dev->dev_addr; + adrp = (const u16 *)dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h index 049dc6cf4611..0f45107db8dd 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_common.h @@ -329,7 +329,7 @@ struct sxgbe_core_ops { /* Set power management mode (e.g. magic frame) */ void (*pmt)(void __iomem *ioaddr, unsigned long mode); /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(void __iomem *ioaddr, unsigned char *addr, + void (*set_umac_addr)(void __iomem *ioaddr, const unsigned char *addr, unsigned int reg_n); void (*get_umac_addr)(void __iomem *ioaddr, unsigned char *addr, unsigned int reg_n); diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c index e96e2bd295ef..7d9f257de92a 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_core.c @@ -85,7 +85,8 @@ static void sxgbe_core_pmt(void __iomem *ioaddr, unsigned long mode) } /* Set/Get Unicast MAC addresses */ -static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, unsigned char *addr, +static void sxgbe_core_set_umac_addr(void __iomem *ioaddr, + const unsigned char *addr, unsigned int reg_n) { u32 high_word, low_word; diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index e7e2223aebbf..cf366ed2557c 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -1038,7 +1038,7 @@ int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id) } int efx_ef10_vport_add_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac) + unsigned int port_id, const u8 *mac) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN); @@ -1050,7 +1050,7 @@ int efx_ef10_vport_add_mac(struct efx_nic *efx, } int efx_ef10_vport_del_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac) + unsigned int port_id, const u8 *mac) { MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN); diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c index 06d23c708a5f..7f5aa4a8c451 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.c +++ b/drivers/net/ethernet/sfc/ef10_sriov.c @@ -480,7 +480,7 @@ static int efx_ef10_vport_del_vf_mac(struct efx_nic *efx, unsigned int port_id, return rc; } -int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) +int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, const u8 *mac) { struct efx_ef10_nic_data *nic_data = efx->nic_data; struct ef10_vf *vf; diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h index cfe556d17313..3c703ca878b0 100644 --- a/drivers/net/ethernet/sfc/ef10_sriov.h +++ b/drivers/net/ethernet/sfc/ef10_sriov.h @@ -39,7 +39,7 @@ static inline void efx_ef10_sriov_reset(struct efx_nic *efx) {} void efx_ef10_sriov_fini(struct efx_nic *efx); static inline void efx_ef10_sriov_flr(struct efx_nic *efx, unsigned vf_i) {} -int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac); +int efx_ef10_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac); int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan, u8 qos); @@ -60,9 +60,9 @@ int efx_ef10_vswitching_restore_vf(struct efx_nic *efx); void efx_ef10_vswitching_remove_pf(struct efx_nic *efx); void efx_ef10_vswitching_remove_vf(struct efx_nic *efx); int efx_ef10_vport_add_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac); + unsigned int port_id, const u8 *mac); int efx_ef10_vport_del_mac(struct efx_nic *efx, - unsigned int port_id, u8 *mac); + unsigned int port_id, const u8 *mac); int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id); int efx_ef10_vadaptor_query(struct efx_nic *efx, unsigned int port_id, u32 *port_flags, u32 *vadaptor_flags, diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index f6981810039d..cc15ee8812d9 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1440,7 +1440,7 @@ struct efx_nic_type { bool (*sriov_wanted)(struct efx_nic *efx); void (*sriov_reset)(struct efx_nic *efx); void (*sriov_flr)(struct efx_nic *efx, unsigned vf_i); - int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, u8 *mac); + int (*sriov_set_vf_mac)(struct efx_nic *efx, int vf_i, const u8 *mac); int (*sriov_set_vf_vlan)(struct efx_nic *efx, int vf_i, u16 vlan, u8 qos); int (*sriov_set_vf_spoofchk)(struct efx_nic *efx, int vf_i, diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 83dcfcae3d4b..e9095cf06368 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1591,7 +1591,7 @@ void efx_fini_sriov(void) destroy_workqueue(vfdi_workqueue); } -int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, u8 *mac) +int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf_i, const u8 *mac) { struct siena_nic_data *nic_data = efx->nic_data; struct siena_vf *vf; diff --git a/drivers/net/ethernet/sfc/siena_sriov.h b/drivers/net/ethernet/sfc/siena_sriov.h index e441c89c25ce..e548c4daf189 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.h +++ b/drivers/net/ethernet/sfc/siena_sriov.h @@ -46,7 +46,7 @@ bool efx_siena_sriov_wanted(struct efx_nic *efx); void efx_siena_sriov_reset(struct efx_nic *efx); void efx_siena_sriov_flr(struct efx_nic *efx, unsigned flr); -int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, u8 *mac); +int efx_siena_sriov_set_vf_mac(struct efx_nic *efx, int vf, const u8 *mac); int efx_siena_sriov_set_vf_vlan(struct efx_nic *efx, int vf, u16 vlan, u8 qos); int efx_siena_sriov_set_vf_spoofchk(struct efx_nic *efx, int vf, diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 60a0c0e9ded2..d105779ba3b2 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -1098,7 +1098,7 @@ sis900_init_rxfilter (struct net_device * net_dev) /* load MAC addr to filter data register */ for (i = 0 ; i < 3 ; i++) { - u32 w = (u32) *((u16 *)(net_dev->dev_addr)+i); + u32 w = (u32) *((const u16 *)(net_dev->dev_addr)+i); sw32(rfcr, i << RFADDR_shift); sw32(rfdr, w); diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index fa387510c189..73bcc6f2bb6e 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1503,7 +1503,7 @@ static int smsc911x_soft_reset(struct smsc911x_data *pdata) /* Sets the device MAC address to dev_addr, called with mac_lock held */ static void -smsc911x_set_hw_mac_address(struct smsc911x_data *pdata, u8 dev_addr[6]) +smsc911x_set_hw_mac_address(struct smsc911x_data *pdata, const u8 dev_addr[6]) { u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 3d1176588f7d..d207c0b463ab 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -404,7 +404,7 @@ static const struct ethtool_ops smsc9420_ethtool_ops = { static void smsc9420_set_mac_address(struct net_device *dev) { struct smsc9420_pdata *pd = netdev_priv(dev); - u8 *dev_addr = dev->dev_addr; + const u8 *dev_addr = dev->dev_addr; u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | (dev_addr[1] << 8) | dev_addr[0]; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b6d945ea903d..9160f9ed363a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -546,13 +546,13 @@ int dwmac4_setup(struct stmmac_priv *priv); int dwxgmac2_setup(struct stmmac_priv *priv); int dwxlgmac2_setup(struct stmmac_priv *priv); -void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low); void stmmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, unsigned int high, unsigned int low); void stmmac_set_mac(void __iomem *ioaddr, bool enable); -void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low); void stmmac_dwmac4_get_mac_addr(void __iomem *ioaddr, unsigned char *addr, unsigned int high, unsigned int low); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 4422baeed3d8..617d0e4c6495 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -634,7 +634,7 @@ static void sun8i_dwmac_set_mac(void __iomem *ioaddr, bool enable) * If addr is NULL, clear the slot */ static void sun8i_dwmac_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index fc8759f146c7..76edb9b72675 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -104,7 +104,7 @@ static void dwmac1000_dump_regs(struct mac_device_info *hw, u32 *reg_space) } static void dwmac1000_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index ebcad8dd99db..75071a7d551a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -68,7 +68,7 @@ static int dwmac100_irq_status(struct mac_device_info *hw, } static void dwmac100_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index b21745368983..fd41db65fe1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -322,7 +322,7 @@ static void dwmac4_pmt(struct mac_device_info *hw, unsigned long mode) } static void dwmac4_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, unsigned int reg_n) + const unsigned char *addr, unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c index 9292a1fab7d3..d1c605777985 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c @@ -187,7 +187,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr, return ret; } -void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_dwmac4_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { unsigned long data; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c index d1c31200bb91..caa4bfc4c1d6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c @@ -239,7 +239,7 @@ void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr) do {} while ((readl(ioaddr + DMA_CONTROL) & DMA_CONTROL_FTF)); } -void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], +void stmmac_set_mac_addr(void __iomem *ioaddr, const u8 addr[6], unsigned int high, unsigned int low) { unsigned long data; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index c4d78fa93663..c6c4d7948fe5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -335,7 +335,8 @@ static void dwxgmac2_pmt(struct mac_device_info *hw, unsigned long mode) } static void dwxgmac2_set_umac_addr(struct mac_device_info *hw, - unsigned char *addr, unsigned int reg_n) + const unsigned char *addr, + unsigned int reg_n) { void __iomem *ioaddr = hw->pcsr; u32 value; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 6dc1c98ebec8..6cf2c2107197 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -330,7 +330,8 @@ struct stmmac_ops { /* Set power management mode (e.g. magic frame) */ void (*pmt)(struct mac_device_info *hw, unsigned long mode); /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(struct mac_device_info *hw, unsigned char *addr, + void (*set_umac_addr)(struct mac_device_info *hw, + const unsigned char *addr, unsigned int reg_n); void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr, unsigned int reg_n); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index e649a3e6a529..be3cb63675a5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -36,7 +36,7 @@ struct stmmac_packet_attrs { int vlan_id_in; int vlan_id_out; unsigned char *src; - unsigned char *dst; + const unsigned char *dst; u32 ip_src; u32 ip_dst; int tcp; @@ -249,8 +249,8 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb, struct net_device *orig_ndev) { struct stmmac_test_priv *tpriv = pt->af_packet_priv; + const unsigned char *dst = tpriv->packet->dst; unsigned char *src = tpriv->packet->src; - unsigned char *dst = tpriv->packet->dst; struct stmmachdr *shdr; struct ethhdr *ehdr; struct udphdr *uhdr; diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index c646575e79d5..d70426670c37 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -623,7 +623,7 @@ static int bigmac_init_hw(struct bigmac *bp, bool non_blocking) void __iomem *cregs = bp->creg; void __iomem *bregs = bp->bregs; __u32 bblk_dvma = (__u32)bp->bblock_dvma; - unsigned char *e = &bp->dev->dev_addr[0]; + const unsigned char *e = &bp->dev->dev_addr[0]; /* Latch current counters into statistics. */ bigmac_get_counters(bp, bregs); diff --git a/drivers/net/ethernet/sun/sunqe.c b/drivers/net/ethernet/sun/sunqe.c index 52b1053a0a77..efe0d33f6024 100644 --- a/drivers/net/ethernet/sun/sunqe.c +++ b/drivers/net/ethernet/sun/sunqe.c @@ -144,7 +144,7 @@ static int qe_init(struct sunqe *qep, int from_irq) void __iomem *cregs = qep->qcregs; void __iomem *mregs = qep->mregs; void __iomem *gregs = qecp->gregs; - unsigned char *e = &qep->dev->dev_addr[0]; + const unsigned char *e = &qep->dev->dev_addr[0]; __u32 qblk_dvma = (__u32)qep->qblock_dvma; u32 tmp; int i; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c index bf6c1c6779ff..76eb7db80f13 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c @@ -57,7 +57,7 @@ static int xlgmac_enable_rx_csum(struct xlgmac_pdata *pdata) return 0; } -static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, u8 *addr) +static int xlgmac_set_mac_address(struct xlgmac_pdata *pdata, const u8 *addr) { unsigned int mac_addr_hi, mac_addr_lo; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac.h b/drivers/net/ethernet/synopsys/dwc-xlgmac.h index 8598aaf3ec99..98e3a271e017 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac.h +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac.h @@ -410,7 +410,7 @@ struct xlgmac_hw_ops { void (*dev_xmit)(struct xlgmac_channel *channel); int (*dev_read)(struct xlgmac_channel *channel); - int (*set_mac_address)(struct xlgmac_pdata *pdata, u8 *addr); + int (*set_mac_address)(struct xlgmac_pdata *pdata, const u8 *addr); int (*config_rx_mode)(struct xlgmac_pdata *pdata); int (*enable_rx_csum)(struct xlgmac_pdata *pdata); int (*disable_rx_csum)(struct xlgmac_pdata *pdata); diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 77c448ad67ce..eab7d78d7c72 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -184,7 +184,7 @@ static void tlan_print_list(struct tlan_list *, char *, int); static void tlan_read_and_clear_stats(struct net_device *, int); static void tlan_reset_adapter(struct net_device *); static void tlan_finish_reset(struct net_device *); -static void tlan_set_mac(struct net_device *, int areg, char *mac); +static void tlan_set_mac(struct net_device *, int areg, const char *mac); static void __tlan_phy_print(struct net_device *); static void tlan_phy_print(struct net_device *); @@ -2346,7 +2346,7 @@ tlan_finish_reset(struct net_device *dev) * **************************************************************/ -static void tlan_set_mac(struct net_device *dev, int areg, char *mac) +static void tlan_set_mac(struct net_device *dev, int areg, const char *mac) { int i; diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index 93453e5713b2..f8b9d10dc056 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -1859,7 +1859,8 @@ static struct net_device_stats *tc35815_get_stats(struct net_device *dev) return &dev->stats; } -static void tc35815_set_cam_entry(struct net_device *dev, int index, unsigned char *addr) +static void tc35815_set_cam_entry(struct net_device *dev, int index, + const unsigned char *addr) { struct tc35815_local *lp = netdev_priv(dev); struct tc35815_regs __iomem *tr = diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index b95aee8607a4..0815de581c7f 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -206,12 +206,13 @@ static void xemaclite_disable_interrupts(struct net_local *drvdata) * This function writes data from a 16-bit aligned buffer to a 32-bit aligned * address in the EmacLite device. */ -static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr, +static void xemaclite_aligned_write(const void *src_ptr, u32 *dest_ptr, unsigned length) { + const u16 *from_u16_ptr; u32 align_buffer; u32 *to_u32_ptr; - u16 *from_u16_ptr, *to_u16_ptr; + u16 *to_u16_ptr; to_u32_ptr = dest_ptr; from_u16_ptr = src_ptr; @@ -470,7 +471,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen) * buffers (if configured). */ static void xemaclite_update_address(struct net_local *drvdata, - u8 *address_ptr) + const u8 *address_ptr) { void __iomem *addr; u32 reg_data; diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index ae611e46da6a..ab513dcc3b22 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -1271,7 +1271,7 @@ struct set_address_info { unsigned int ioaddr; }; -static void set_address(struct set_address_info *sa_info, char *addr) +static void set_address(struct set_address_info *sa_info, const char *addr) { unsigned int ioaddr = sa_info->ioaddr; int i; diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 6e32da28e138..ebfeeb3c67c1 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -273,12 +273,12 @@ static int vsc85xx_downshift_set(struct phy_device *phydev, u8 count) static int vsc85xx_wol_set(struct phy_device *phydev, struct ethtool_wolinfo *wol) { + const u8 *mac_addr = phydev->attached_dev->dev_addr; int rc; u16 reg_val; u8 i; u16 pwd[3] = {0, 0, 0}; struct ethtool_wolinfo *wol_conf = wol; - u8 *mac_addr = phydev->attached_dev->dev_addr; mutex_lock(&phydev->lock); rc = phy_select_page(phydev, MSCC_PHY_PAGE_EXTENDED_2); diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index 981ac1c33780..ea06d10e1c21 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -119,7 +119,7 @@ static int aqc111_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, } static int aqc111_write_cmd(struct usbnet *dev, u8 cmd, u16 value, - u16 index, u16 size, void *data) + u16 index, u16 size, const void *data) { int ret; diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 5ed59d9dd631..ea8aa8c33241 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -209,7 +209,7 @@ static int __ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, } static int __ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data, int in_pm) + u16 size, const void *data, int in_pm) { int ret; int (*fn)(struct usbnet *, u8, u8, u16, u16, const void *, u16); @@ -272,7 +272,7 @@ static int ax88179_read_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, } static int ax88179_write_cmd_nopm(struct usbnet *dev, u8 cmd, u16 value, - u16 index, u16 size, void *data) + u16 index, u16 size, const void *data) { int ret; @@ -313,7 +313,7 @@ static int ax88179_read_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, } static int ax88179_write_cmd(struct usbnet *dev, u8 cmd, u16 value, u16 index, - u16 size, void *data) + u16 size, const void *data) { int ret; @@ -463,7 +463,7 @@ static int ax88179_auto_detach(struct usbnet *dev, int in_pm) u16 tmp16; u8 tmp8; int (*fnr)(struct usbnet *, u8, u16, u16, u16, void *); - int (*fnw)(struct usbnet *, u8, u16, u16, u16, void *); + int (*fnw)(struct usbnet *, u8, u16, u16, u16, const void *); if (!in_pm) { fnr = ax88179_read_cmd; diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 97ba67042d12..24db5768a3c0 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -615,7 +615,7 @@ static void catc_stats_timer(struct timer_list *t) * Receive modes. Broadcast, Multicast, Promisc. */ -static void catc_multicast(unsigned char *addr, u8 *multicast) +static void catc_multicast(const unsigned char *addr, u8 *multicast) { u32 crc; diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c index dcdb46314685..48d7d278631e 100644 --- a/drivers/net/usb/dm9601.c +++ b/drivers/net/usb/dm9601.c @@ -93,7 +93,8 @@ static int dm_write_reg(struct usbnet *dev, u8 reg, u8 value) value, reg, NULL, 0); } -static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) +static void dm_write_async(struct usbnet *dev, u8 reg, u16 length, + const void *data) { usbnet_write_cmd_async(dev, DM_WRITE_REGS, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, diff --git a/drivers/net/usb/mcs7830.c b/drivers/net/usb/mcs7830.c index cead742da381..5f42db26d200 100644 --- a/drivers/net/usb/mcs7830.c +++ b/drivers/net/usb/mcs7830.c @@ -132,7 +132,8 @@ static int mcs7830_hif_get_mac_address(struct usbnet *dev, unsigned char *addr) return 0; } -static int mcs7830_hif_set_mac_address(struct usbnet *dev, unsigned char *addr) +static int mcs7830_hif_set_mac_address(struct usbnet *dev, + const unsigned char *addr) { int ret = mcs7830_set_reg(dev, HIF_REG_ETHERNET_ADDR, ETH_ALEN, addr); diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 068f197f1786..15209de1849e 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -56,7 +56,8 @@ static int sr_write_reg(struct usbnet *dev, u8 reg, u8 value) value, reg, NULL, 0); } -static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, void *data) +static void sr_write_async(struct usbnet *dev, u8 reg, u16 length, + const void *data) { usbnet_write_cmd_async(dev, SR_WR_REGS, SR_REQ_WR_REG, 0, reg, data, length); diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 4df0bf0a0864..e1bf3219b4e6 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -331,7 +331,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, enum qed_filter_config_mode mode); int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); - int (*req_bulletin_update_mac)(struct qed_dev *cdev, u8 *mac); + int (*req_bulletin_update_mac)(struct qed_dev *cdev, const u8 *mac); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index ad220d5da18f..0dae7fcc5ef2 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1113,7 +1113,7 @@ struct qed_common_ops { * * Return: Int. */ - int (*update_mac)(struct qed_dev *cdev, u8 *mac); + int (*update_mac)(struct qed_dev *cdev, const u8 *mac); /** * update_mtu(): API to inform the change in the mtu. diff --git a/include/linux/qed/qed_rdma_if.h b/include/linux/qed/qed_rdma_if.h index aeb242cefebf..3b76c07fbcf8 100644 --- a/include/linux/qed/qed_rdma_if.h +++ b/include/linux/qed/qed_rdma_if.h @@ -662,7 +662,8 @@ struct qed_rdma_ops { u8 connection_handle, struct qed_ll2_stats *p_stats); int (*ll2_set_mac_filter)(struct qed_dev *cdev, - u8 *old_mac_address, u8 *new_mac_address); + u8 *old_mac_address, + const u8 *new_mac_address); int (*iwarp_set_engine_affin)(struct qed_dev *cdev, bool b_reset); -- cgit v1.2.3 From 54f2d8d6ca99a3e24efc9c8b055bbcbe0b583227 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 13 Oct 2021 13:44:30 -0700 Subject: ethernet: make eth_hw_addr_random() use dev_addr_set() Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. To maintain netdev->dev_addr in this tree we need to make all the writes to it got through appropriate helpers. Signed-off-by: Jakub Kicinski --- include/linux/etherdevice.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 3cf546d2ffd1..76f7ff684cbf 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -269,8 +269,11 @@ static inline void eth_zero_addr(u8 *addr) */ static inline void eth_hw_addr_random(struct net_device *dev) { + u8 addr[ETH_ALEN]; + + eth_random_addr(addr); + __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; - eth_random_addr(dev->dev_addr); } /** -- cgit v1.2.3 From ba530fea8ca1b57ee71d4e62f287a5d7ed92f789 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 13 Oct 2021 13:54:50 -0700 Subject: ethernet: remove random_ether_addr() random_ether_addr() was the original name of the helper which was kept for backward compatibility (?) after the rename in commit 0a4dd594982a ("etherdevice: Rename random_ether_addr to eth_random_addr"). We have a single random_ether_addr() caller left in tree while there are 70 callers of eth_random_addr(). Time to drop this define. Reviewed-by: Simon Horman Link: https://lore.kernel.org/r/20211013205450.328092-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- include/linux/etherdevice.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 6904bfaa5777..c092cb61416a 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1918,7 +1918,7 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) port->port_id, port->slave.mac_addr); if (!is_valid_ether_addr(port->slave.mac_addr)) { - random_ether_addr(port->slave.mac_addr); + eth_random_addr(port->slave.mac_addr); dev_err(dev, "Use random MAC address\n"); } } diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 76f7ff684cbf..23681c3d3b8a 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -234,8 +234,6 @@ static inline void eth_random_addr(u8 *addr) addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } -#define random_ether_addr(addr) eth_random_addr(addr) - /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address -- cgit v1.2.3 From 7463acfbe52ae8b7e0ea6890c1886b3f8ba8bddd Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 8 Oct 2021 22:06:01 +0200 Subject: netfilter: Rename ingress hook include file Prepare for addition of a netfilter egress hook by renaming to . The egress hook also necessitates a refactoring of the include file, but that is done in a separate commit to ease reviewing. No functional change intended. Signed-off-by: Lukas Wunner Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ingress.h | 58 --------------------------------------- include/linux/netfilter_netdev.h | 58 +++++++++++++++++++++++++++++++++++++++ net/core/dev.c | 2 +- 3 files changed, 59 insertions(+), 59 deletions(-) delete mode 100644 include/linux/netfilter_ingress.h create mode 100644 include/linux/netfilter_netdev.h (limited to 'include/linux') diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h deleted file mode 100644 index a13774be2eb5..000000000000 --- a/include/linux/netfilter_ingress.h +++ /dev/null @@ -1,58 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NETFILTER_INGRESS_H_ -#define _NETFILTER_INGRESS_H_ - -#include -#include - -#ifdef CONFIG_NETFILTER_INGRESS -static inline bool nf_hook_ingress_active(const struct sk_buff *skb) -{ -#ifdef CONFIG_JUMP_LABEL - if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) - return false; -#endif - return rcu_access_pointer(skb->dev->nf_hooks_ingress); -} - -/* caller must hold rcu_read_lock */ -static inline int nf_hook_ingress(struct sk_buff *skb) -{ - struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); - struct nf_hook_state state; - int ret; - - /* Must recheck the ingress hook head, in the event it became NULL - * after the check in nf_hook_ingress_active evaluated to true. - */ - if (unlikely(!e)) - return 0; - - nf_hook_state_init(&state, NF_NETDEV_INGRESS, - NFPROTO_NETDEV, skb->dev, NULL, NULL, - dev_net(skb->dev), NULL); - ret = nf_hook_slow(skb, &state, e, 0); - if (ret == 0) - return -1; - - return ret; -} - -static inline void nf_hook_ingress_init(struct net_device *dev) -{ - RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); -} -#else /* CONFIG_NETFILTER_INGRESS */ -static inline int nf_hook_ingress_active(struct sk_buff *skb) -{ - return 0; -} - -static inline int nf_hook_ingress(struct sk_buff *skb) -{ - return 0; -} - -static inline void nf_hook_ingress_init(struct net_device *dev) {} -#endif /* CONFIG_NETFILTER_INGRESS */ -#endif /* _NETFILTER_INGRESS_H_ */ diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h new file mode 100644 index 000000000000..a13774be2eb5 --- /dev/null +++ b/include/linux/netfilter_netdev.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _NETFILTER_INGRESS_H_ +#define _NETFILTER_INGRESS_H_ + +#include +#include + +#ifdef CONFIG_NETFILTER_INGRESS +static inline bool nf_hook_ingress_active(const struct sk_buff *skb) +{ +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) + return false; +#endif + return rcu_access_pointer(skb->dev->nf_hooks_ingress); +} + +/* caller must hold rcu_read_lock */ +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); + struct nf_hook_state state; + int ret; + + /* Must recheck the ingress hook head, in the event it became NULL + * after the check in nf_hook_ingress_active evaluated to true. + */ + if (unlikely(!e)) + return 0; + + nf_hook_state_init(&state, NF_NETDEV_INGRESS, + NFPROTO_NETDEV, skb->dev, NULL, NULL, + dev_net(skb->dev), NULL); + ret = nf_hook_slow(skb, &state, e, 0); + if (ret == 0) + return -1; + + return ret; +} + +static inline void nf_hook_ingress_init(struct net_device *dev) +{ + RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); +} +#else /* CONFIG_NETFILTER_INGRESS */ +static inline int nf_hook_ingress_active(struct sk_buff *skb) +{ + return 0; +} + +static inline int nf_hook_ingress(struct sk_buff *skb) +{ + return 0; +} + +static inline void nf_hook_ingress_init(struct net_device *dev) {} +#endif /* CONFIG_NETFILTER_INGRESS */ +#endif /* _NETFILTER_INGRESS_H_ */ diff --git a/net/core/dev.c b/net/core/dev.c index 16ab09b6a7f8..0fd3c6490e06 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -140,7 +140,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.2.3 From 17d20784223d52bf1671f984c9e8d5d9b8ea171b Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 8 Oct 2021 22:06:02 +0200 Subject: netfilter: Generalize ingress hook include file Prepare for addition of a netfilter egress hook by generalizing the ingress hook include file. No functional change intended. Signed-off-by: Lukas Wunner Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_netdev.h | 20 +++++++++++--------- net/core/dev.c | 2 +- 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index a13774be2eb5..5812b0fb0278 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NETFILTER_INGRESS_H_ -#define _NETFILTER_INGRESS_H_ +#ifndef _NETFILTER_NETDEV_H_ +#define _NETFILTER_NETDEV_H_ #include #include @@ -38,10 +38,6 @@ static inline int nf_hook_ingress(struct sk_buff *skb) return ret; } -static inline void nf_hook_ingress_init(struct net_device *dev) -{ - RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); -} #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) { @@ -52,7 +48,13 @@ static inline int nf_hook_ingress(struct sk_buff *skb) { return 0; } - -static inline void nf_hook_ingress_init(struct net_device *dev) {} #endif /* CONFIG_NETFILTER_INGRESS */ -#endif /* _NETFILTER_INGRESS_H_ */ + +static inline void nf_hook_netdev_init(struct net_device *dev) +{ +#ifdef CONFIG_NETFILTER_INGRESS + RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); +#endif +} + +#endif /* _NETFILTER_NETDEV_H_ */ diff --git a/net/core/dev.c b/net/core/dev.c index 0fd3c6490e06..e4c683029c61 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10867,7 +10867,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; - nf_hook_ingress_init(dev); + nf_hook_netdev_init(dev); return dev; -- cgit v1.2.3 From 42df6e1d221dddc0f2acf2be37e68d553ad65f96 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 8 Oct 2021 22:06:03 +0200 Subject: netfilter: Introduce egress hook MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support classifying packets with netfilter on egress to satisfy user requirements such as: * outbound security policies for containers (Laura) * filtering and mangling intra-node Direct Server Return (DSR) traffic on a load balancer (Laura) * filtering locally generated traffic coming in through AF_PACKET, such as local ARP traffic generated for clustering purposes or DHCP (Laura; the AF_PACKET plumbing is contained in a follow-up commit) * L2 filtering from ingress and egress for AVB (Audio Video Bridging) and gPTP with nftables (Pablo) * in the future: in-kernel NAT64/NAT46 (Pablo) The egress hook introduced herein complements the ingress hook added by commit e687ad60af09 ("netfilter: add netfilter ingress hook after handle_ing() under unique static key"). A patch for nftables to hook up egress rules from user space has been submitted separately, so users may immediately take advantage of the feature. Alternatively or in addition to netfilter, packets can be classified with traffic control (tc). On ingress, packets are classified first by tc, then by netfilter. On egress, the order is reversed for symmetry. Conceptually, tc and netfilter can be thought of as layers, with netfilter layered above tc. Traffic control is capable of redirecting packets to another interface (man 8 tc-mirred). E.g., an ingress packet may be redirected from the host namespace to a container via a veth connection: tc ingress (host) -> tc egress (veth host) -> tc ingress (veth container) In this case, netfilter egress classifying is not performed when leaving the host namespace! That's because the packet is still on the tc layer. If tc redirects the packet to a physical interface in the host namespace such that it leaves the system, the packet is never subjected to netfilter egress classifying. That is only logical since it hasn't passed through netfilter ingress classifying either. Packets can alternatively be redirected at the netfilter layer using nft fwd. Such a packet *is* subjected to netfilter egress classifying since it has reached the netfilter layer. Internally, the skb->nf_skip_egress flag controls whether netfilter is invoked on egress by __dev_queue_xmit(). Because __dev_queue_xmit() may be called recursively by tunnel drivers such as vxlan, the flag is reverted to false after sch_handle_egress(). This ensures that netfilter is applied both on the overlay and underlying network. Interaction between tc and netfilter is possible by setting and querying skb->mark. If netfilter egress classifying is not enabled on any interface, it is patched out of the data path by way of a static_key and doesn't make a performance difference that is discernible from noise: Before: 1537 1538 1538 1537 1538 1537 Mb/sec After: 1536 1534 1539 1539 1539 1540 Mb/sec Before + tc accept: 1418 1418 1418 1419 1419 1418 Mb/sec After + tc accept: 1419 1424 1418 1419 1422 1420 Mb/sec Before + tc drop: 1620 1619 1619 1619 1620 1620 Mb/sec After + tc drop: 1616 1624 1625 1624 1622 1619 Mb/sec When netfilter egress classifying is enabled on at least one interface, a minimal performance penalty is incurred for every egress packet, even if the interface it's transmitted over doesn't have any netfilter egress rules configured. That is caused by checking dev->nf_hooks_egress against NULL. Measurements were performed on a Core i7-3615QM. Commands to reproduce: ip link add dev foo type dummy ip link set dev foo up modprobe pktgen echo "add_device foo" > /proc/net/pktgen/kpktgend_3 samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh -i foo -n 400000000 -m "11:11:11:11:11:11" -d 1.1.1.1 Accept all traffic with tc: tc qdisc add dev foo clsact tc filter add dev foo egress bpf da bytecode '1,6 0 0 0,' Drop all traffic with tc: tc qdisc add dev foo clsact tc filter add dev foo egress bpf da bytecode '1,6 0 0 2,' Apply this patch when measuring packet drops to avoid errors in dmesg: https://lore.kernel.org/netdev/a73dda33-57f4-95d8-ea51-ed483abd6a7a@iogearbox.net/ Signed-off-by: Lukas Wunner Cc: Laura García Liébana Cc: John Fastabend Cc: Daniel Borkmann Cc: Alexei Starovoitov Cc: Eric Dumazet Cc: Thomas Graf Signed-off-by: Pablo Neira Ayuso --- drivers/net/ifb.c | 3 ++ include/linux/netdevice.h | 4 ++ include/linux/netfilter_netdev.h | 86 ++++++++++++++++++++++++++++++++++++++++ include/linux/skbuff.h | 4 ++ include/uapi/linux/netfilter.h | 1 + net/core/dev.c | 15 ++++++- net/netfilter/Kconfig | 11 +++++ net/netfilter/core.c | 34 ++++++++++++++-- net/netfilter/nfnetlink_hook.c | 16 ++++++-- net/netfilter/nft_chain_filter.c | 4 +- 10 files changed, 168 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index e9258a9f3702..2c319dd27f29 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -75,8 +76,10 @@ static void ifb_ri_tasklet(struct tasklet_struct *t) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { + /* Skip tc and netfilter to prevent redirection loop. */ skb->redirected = 0; skb->tc_skip_classify = 1; + nf_skip_egress(skb, true); u64_stats_update_begin(&txp->tsync); txp->tx_packets++; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d79163208dfd..e9a48068f306 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1861,6 +1861,7 @@ enum netdev_ml_priv_type { * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing + * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) @@ -2161,6 +2162,9 @@ struct net_device { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index 5812b0fb0278..b71b57a83bb4 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -50,11 +50,97 @@ static inline int nf_hook_ingress(struct sk_buff *skb) } #endif /* CONFIG_NETFILTER_INGRESS */ +#ifdef CONFIG_NETFILTER_EGRESS +static inline bool nf_hook_egress_active(void) +{ +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) + return false; +#endif + return true; +} + +/** + * nf_hook_egress - classify packets before transmission + * @skb: packet to be classified + * @rc: result code which shall be returned by __dev_queue_xmit() on failure + * @dev: netdev whose egress hooks shall be applied to @skb + * + * Returns @skb on success or %NULL if the packet was consumed or filtered. + * Caller must hold rcu_read_lock. + * + * On ingress, packets are classified first by tc, then by netfilter. + * On egress, the order is reversed for symmetry. Conceptually, tc and + * netfilter can be thought of as layers, with netfilter layered above tc: + * When tc redirects a packet to another interface, netfilter is not applied + * because the packet is on the tc layer. + * + * The nf_skip_egress flag controls whether netfilter is applied on egress. + * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the + * packet passes through tc and netfilter. Because __dev_queue_xmit() may be + * called recursively by tunnel drivers such as vxlan, the flag is reverted to + * false after sch_handle_egress(). This ensures that netfilter is applied + * both on the overlay and underlying network. + */ +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + struct nf_hook_entries *e; + struct nf_hook_state state; + int ret; + +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + if (skb->nf_skip_egress) + return skb; +#endif + + e = rcu_dereference(dev->nf_hooks_egress); + if (!e) + return skb; + + nf_hook_state_init(&state, NF_NETDEV_EGRESS, + NFPROTO_NETDEV, dev, NULL, NULL, + dev_net(dev), NULL); + ret = nf_hook_slow(skb, &state, e, 0); + + if (ret == 1) { + return skb; + } else if (ret < 0) { + *rc = NET_XMIT_DROP; + return NULL; + } else { /* ret == 0 */ + *rc = NET_XMIT_SUCCESS; + return NULL; + } +} +#else /* CONFIG_NETFILTER_EGRESS */ +static inline bool nf_hook_egress_active(void) +{ + return false; +} + +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + return skb; +} +#endif /* CONFIG_NETFILTER_EGRESS */ + +static inline void nf_skip_egress(struct sk_buff *skb, bool skip) +{ +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + skb->nf_skip_egress = skip; +#endif +} + static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif +#ifdef CONFIG_NETFILTER_EGRESS + RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); +#endif } #endif /* _NETFILTER_NETDEV_H_ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 841e2f0f5240..cb96f1e6460c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -652,6 +652,7 @@ typedef unsigned char *sk_buff_data_t; * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path + * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -868,6 +869,9 @@ struct sk_buff { #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + __u8 nf_skip_egress:1; +#endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index ef9a44286e23..53411ccc69db 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -51,6 +51,7 @@ enum nf_inet_hooks { enum nf_dev_hooks { NF_NETDEV_INGRESS, + NF_NETDEV_EGRESS, NF_NETDEV_NUMHOOKS }; diff --git a/net/core/dev.c b/net/core/dev.c index e4c683029c61..09d74798b440 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3920,6 +3920,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { +#ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; @@ -3955,6 +3956,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) default: break; } +#endif /* CONFIG_NET_CLS_ACT */ return skb; } @@ -4148,13 +4150,20 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; -# ifdef CONFIG_NET_EGRESS +#endif +#ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { + if (nf_hook_egress_active()) { + skb = nf_hook_egress(skb, &rc, dev); + if (!skb) + goto out; + } + nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; + nf_skip_egress(skb, false); } -# endif #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. @@ -5296,6 +5305,7 @@ skip_taps: if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; + nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) @@ -5303,6 +5313,7 @@ skip_taps: if (!skb) goto out; + nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 54395266339d..49c9fae9c62c 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -10,6 +10,17 @@ config NETFILTER_INGRESS This allows you to classify packets from ingress using the Netfilter infrastructure. +config NETFILTER_EGRESS + bool "Netfilter egress support" + default y + select NET_EGRESS + help + This allows you to classify packets before transmission using the + Netfilter infrastructure. + +config NETFILTER_SKIP_EGRESS + def_bool NETFILTER_EGRESS && (NET_CLS_ACT || IFB) + config NETFILTER_NETLINK tristate diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 63d032191e62..3a32a813fcde 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -316,6 +316,12 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hooknum == NF_NETDEV_EGRESS) { + if (dev && dev_net(dev) == net) + return &dev->nf_hooks_egress; + } #endif WARN_ON_ONCE(1); return NULL; @@ -344,6 +350,11 @@ static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) return false; } +static inline bool nf_egress_hook(const struct nf_hook_ops *reg, int pf) +{ + return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; +} + static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL @@ -383,9 +394,18 @@ static int __nf_register_net_hook(struct net *net, int pf, switch (pf) { case NFPROTO_NETDEV: - err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); - if (err < 0) - return err; +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif +#ifndef CONFIG_NETFILTER_EGRESS + if (reg->hooknum == NF_NETDEV_EGRESS) + return -EOPNOTSUPP; +#endif + if ((reg->hooknum != NF_NETDEV_INGRESS && + reg->hooknum != NF_NETDEV_EGRESS) || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) @@ -417,6 +437,10 @@ static int __nf_register_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); @@ -474,6 +498,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index f554e2ea32ee..d5c719c9e36c 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -185,7 +185,7 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) struct net_device *netdev; #endif @@ -221,9 +221,9 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); break; #endif -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) case NFPROTO_NETDEV: - if (hook != NF_NETDEV_INGRESS) + if (hook >= NF_NETDEV_NUMHOOKS) return ERR_PTR(-EOPNOTSUPP); if (!dev) @@ -233,7 +233,15 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de if (!netdev) return ERR_PTR(-ENODEV); - return rcu_dereference(netdev->nf_hooks_ingress); +#ifdef CONFIG_NETFILTER_INGRESS + if (hook == NF_NETDEV_INGRESS) + return rcu_dereference(netdev->nf_hooks_ingress); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hook == NF_NETDEV_EGRESS) + return rcu_dereference(netdev->nf_hooks_egress); +#endif + fallthrough; #endif default: return ERR_PTR(-EPROTONOSUPPORT); diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 5b02408a920b..680fe557686e 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -310,9 +310,11 @@ static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, - .hook_mask = (1 << NF_NETDEV_INGRESS), + .hook_mask = (1 << NF_NETDEV_INGRESS) | + (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; -- cgit v1.2.3 From 8844e01062ddd8196c4550df9803cc1835d123c2 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Oct 2021 17:15:10 +0200 Subject: netfilter: iptables: allow use of ipt_do_table as hookfn This is possible now that the xt_table structure is passed in via *priv. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4/ip_tables.h | 6 +++--- net/ipv4/netfilter/ip_tables.c | 7 ++++--- net/ipv4/netfilter/iptable_filter.c | 9 +-------- net/ipv4/netfilter/iptable_mangle.c | 8 ++++---- net/ipv4/netfilter/iptable_nat.c | 15 ++++----------- net/ipv4/netfilter/iptable_raw.c | 10 +--------- net/ipv4/netfilter/iptable_security.c | 9 +-------- 7 files changed, 18 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 8d09bfe850dc..132b0e4a6d4d 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -63,9 +63,9 @@ struct ipt_error { } extern void *ipt_alloc_initial_table(const struct xt_table *); -extern unsigned int ipt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table); +extern unsigned int ipt_do_table(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 13acb687c19a..2ed7c58b471a 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -222,10 +222,11 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int -ipt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table) +ipt_do_table(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) { + const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 0eb0e2ab9bfc..b9062f4552ac 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -28,13 +28,6 @@ static const struct xt_table packet_filter = { .priority = NF_IP_PRI_FILTER, }; -static unsigned int -iptable_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ @@ -90,7 +83,7 @@ static int __init iptable_filter_init(void) if (ret < 0) return ret; - filter_ops = xt_hook_ops_alloc(&packet_filter, iptable_filter_hook); + filter_ops = xt_hook_ops_alloc(&packet_filter, ipt_do_table); if (IS_ERR(filter_ops)) { xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 40417a3f930b..3abb430af9e6 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -34,7 +34,7 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *priv) +ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; const struct iphdr *iph; @@ -50,7 +50,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *pri daddr = iph->daddr; tos = iph->tos; - ret = ipt_do_table(skb, state, priv); + ret = ipt_do_table(priv, skb, state); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); @@ -75,8 +75,8 @@ iptable_mangle_hook(void *priv, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) - return ipt_mangle_out(skb, state, priv); - return ipt_do_table(skb, state, priv); + return ipt_mangle_out(priv, skb, state); + return ipt_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 45d7e072e6a5..56f6ecc43451 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -29,34 +29,27 @@ static const struct xt_table nf_nat_ipv4_table = { .af = NFPROTO_IPV4, }; -static unsigned int iptable_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static const struct nf_hook_ops nf_nat_ipv4_ops[] = { { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP_PRI_NAT_DST, }, { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_NAT_SRC, }, { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP_PRI_NAT_DST, }, { - .hook = iptable_nat_do_chain, + .hook = ipt_do_table, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP_PRI_NAT_SRC, diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 8265c6765705..ca5e5b21587c 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -32,14 +32,6 @@ static const struct xt_table packet_raw_before_defrag = { .priority = NF_IP_PRI_RAW_BEFORE_DEFRAG, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -iptable_raw_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static struct nf_hook_ops *rawtable_ops __read_mostly; static int iptable_raw_table_init(struct net *net) @@ -90,7 +82,7 @@ static int __init iptable_raw_init(void) if (ret < 0) return ret; - rawtable_ops = xt_hook_ops_alloc(table, iptable_raw_hook); + rawtable_ops = xt_hook_ops_alloc(table, ipt_do_table); if (IS_ERR(rawtable_ops)) { xt_unregister_template(table); return PTR_ERR(rawtable_ops); diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index f519162a2fa5..d885443cb267 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -33,13 +33,6 @@ static const struct xt_table security_table = { .priority = NF_IP_PRI_SECURITY, }; -static unsigned int -iptable_security_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ipt_do_table(skb, state, priv); -} - static struct nf_hook_ops *sectbl_ops __read_mostly; static int iptable_security_table_init(struct net *net) @@ -78,7 +71,7 @@ static int __init iptable_security_init(void) if (ret < 0) return ret; - sectbl_ops = xt_hook_ops_alloc(&security_table, iptable_security_hook); + sectbl_ops = xt_hook_ops_alloc(&security_table, ipt_do_table); if (IS_ERR(sectbl_ops)) { xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); -- cgit v1.2.3 From e8d225b6002673366abc2e40e30c991bdc8d62ca Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Oct 2021 17:15:12 +0200 Subject: netfilter: arp_tables: allow use of arpt_do_table as hookfn This is possible now that the xt_table structure is passed in via *priv. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_arp/arp_tables.h | 5 ++--- net/ipv4/netfilter/arp_tables.c | 7 ++++--- net/ipv4/netfilter/arptable_filter.c | 10 +--------- 3 files changed, 7 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 4f9a4b3c5892..a40aaf645fa4 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -54,9 +54,8 @@ int arpt_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops); void arpt_unregister_table(struct net *net, const char *name); void arpt_unregister_table_pre_exit(struct net *net, const char *name); -extern unsigned int arpt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table); +extern unsigned int arpt_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index c53f14b94356..ffc0cab7cf18 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -179,10 +179,11 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) return (void *)entry + entry->next_offset; } -unsigned int arpt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table) +unsigned int arpt_do_table(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) { + const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 3de78416ec76..78cd5ee24448 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -26,14 +26,6 @@ static const struct xt_table packet_filter = { .priority = NF_IP_PRI_FILTER, }; -/* The work comes in here from netfilter.c */ -static unsigned int -arptable_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return arpt_do_table(skb, state, priv); -} - static struct nf_hook_ops *arpfilter_ops __read_mostly; static int arptable_filter_table_init(struct net *net) @@ -72,7 +64,7 @@ static int __init arptable_filter_init(void) if (ret < 0) return ret; - arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arptable_filter_hook); + arpfilter_ops = xt_hook_ops_alloc(&packet_filter, arpt_do_table); if (IS_ERR(arpfilter_ops)) { xt_unregister_template(&packet_filter); return PTR_ERR(arpfilter_ops); -- cgit v1.2.3 From 44b5990e7b463240e4c116c9e8670c67dad960cc Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Oct 2021 17:15:13 +0200 Subject: netfilter: ip6tables: allow use of ip6t_do_table as hookfn This is possible now that the xt_table structure is passed via *priv. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6/ip6_tables.h | 5 ++--- net/ipv6/netfilter/ip6_tables.c | 6 +++--- net/ipv6/netfilter/ip6table_filter.c | 10 +--------- net/ipv6/netfilter/ip6table_mangle.c | 8 ++++---- net/ipv6/netfilter/ip6table_nat.c | 15 ++++----------- net/ipv6/netfilter/ip6table_raw.c | 10 +--------- net/ipv6/netfilter/ip6table_security.c | 9 +-------- 7 files changed, 16 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 79e73fd7d965..8b8885a73c76 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -29,9 +29,8 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops); void ip6t_unregister_table_pre_exit(struct net *net, const char *name); void ip6t_unregister_table_exit(struct net *net, const char *name); -extern unsigned int ip6t_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table); +extern unsigned int ip6t_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); #ifdef CONFIG_NETFILTER_XTABLES_COMPAT #include diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index a579ea14a69b..2d816277f2c5 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -247,10 +247,10 @@ ip6t_next_entry(const struct ip6t_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int -ip6t_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct xt_table *table) +ip6t_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { + const struct xt_table *table = priv; unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 727ee8097012..df785ebda0ca 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -27,14 +27,6 @@ static const struct xt_table packet_filter = { .priority = NF_IP6_PRI_FILTER, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6table_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ @@ -90,7 +82,7 @@ static int __init ip6table_filter_init(void) if (ret < 0) return ret; - filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); + filter_ops = xt_hook_ops_alloc(&packet_filter, ip6t_do_table); if (IS_ERR(filter_ops)) { xt_unregister_template(&packet_filter); return PTR_ERR(filter_ops); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 9b518ce37d6a..a88b2ce4a3cb 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -29,7 +29,7 @@ static const struct xt_table packet_mangler = { }; static unsigned int -ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *priv) +ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { unsigned int ret; struct in6_addr saddr, daddr; @@ -46,7 +46,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state, void *pr /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, state, priv); + ret = ip6t_do_table(priv, skb, state); if (ret != NF_DROP && ret != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || @@ -68,8 +68,8 @@ ip6table_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { if (state->hook == NF_INET_LOCAL_OUT) - return ip6t_mangle_out(skb, state, priv); - return ip6t_do_table(skb, state, priv); + return ip6t_mangle_out(priv, skb, state); + return ip6t_do_table(priv, skb, state); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 921c1723a01e..bf3cb3a13600 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -31,34 +31,27 @@ static const struct xt_table nf_nat_ipv6_table = { .af = NFPROTO_IPV6, }; -static unsigned int ip6table_nat_do_chain(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static const struct nf_hook_ops nf_nat_ipv6_ops[] = { { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_NAT_DST, }, { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_NAT_SRC, }, { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_NAT_DST, }, { - .hook = ip6table_nat_do_chain, + .hook = ip6t_do_table, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, .priority = NF_IP6_PRI_NAT_SRC, diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 4f2a04af71d3..08861d5d1f4d 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -31,14 +31,6 @@ static const struct xt_table packet_raw_before_defrag = { .priority = NF_IP6_PRI_RAW_BEFORE_DEFRAG, }; -/* The work comes in here from netfilter.c. */ -static unsigned int -ip6table_raw_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static struct nf_hook_ops *rawtable_ops __read_mostly; static int ip6table_raw_table_init(struct net *net) @@ -88,7 +80,7 @@ static int __init ip6table_raw_init(void) return ret; /* Register hooks */ - rawtable_ops = xt_hook_ops_alloc(table, ip6table_raw_hook); + rawtable_ops = xt_hook_ops_alloc(table, ip6t_do_table); if (IS_ERR(rawtable_ops)) { xt_unregister_template(table); return PTR_ERR(rawtable_ops); diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 931674034d8b..4df14a9bae78 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -32,13 +32,6 @@ static const struct xt_table security_table = { .priority = NF_IP6_PRI_SECURITY, }; -static unsigned int -ip6table_security_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ip6t_do_table(skb, state, priv); -} - static struct nf_hook_ops *sectbl_ops __read_mostly; static int ip6table_security_table_init(struct net *net) @@ -77,7 +70,7 @@ static int __init ip6table_security_init(void) if (ret < 0) return ret; - sectbl_ops = xt_hook_ops_alloc(&security_table, ip6table_security_hook); + sectbl_ops = xt_hook_ops_alloc(&security_table, ip6t_do_table); if (IS_ERR(sectbl_ops)) { xt_unregister_template(&security_table); return PTR_ERR(sectbl_ops); -- cgit v1.2.3 From f0d6764f7ddbf6d57302155b0f83eadb25ab0f0c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 11 Oct 2021 17:15:14 +0200 Subject: netfilter: ebtables: allow use of ebt_do_table as hookfn This is possible now that the xt_table structure is passed via *priv. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 5 ++--- net/bridge/netfilter/ebtable_broute.c | 2 +- net/bridge/netfilter/ebtable_filter.c | 13 +++---------- net/bridge/netfilter/ebtable_nat.c | 12 +++--------- net/bridge/netfilter/ebtables.c | 6 +++--- 5 files changed, 12 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 10a01978bc0d..a13296d6c7ce 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -112,9 +112,8 @@ extern int ebt_register_table(struct net *net, const struct nf_hook_ops *ops); extern void ebt_unregister_table(struct net *net, const char *tablename); void ebt_unregister_table_pre_exit(struct net *net, const char *tablename); -extern unsigned int ebt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct ebt_table *table); +extern unsigned int ebt_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state); /* True if the hook mask denotes that the rule is in a base chain, * used in the check() functions */ diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index a7af4eaff17d..1a11064f9990 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -66,7 +66,7 @@ static unsigned int ebt_broute(void *priv, struct sk_buff *skb, NFPROTO_BRIDGE, s->in, NULL, NULL, s->net, NULL); - ret = ebt_do_table(skb, &state, priv); + ret = ebt_do_table(priv, skb, &state); if (ret != NF_DROP) return ret; diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index c0b121df4a9a..cb949436bc0e 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -58,28 +58,21 @@ static const struct ebt_table frame_filter = { .me = THIS_MODULE, }; -static unsigned int -ebt_filter_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ebt_do_table(skb, state, priv); -} - static const struct nf_hook_ops ebt_ops_filter[] = { { - .hook = ebt_filter_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_IN, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { - .hook = ebt_filter_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_FILTER_BRIDGED, }, { - .hook = ebt_filter_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_FILTER_OTHER, diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 4078151c224f..5ee0531ae506 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -58,27 +58,21 @@ static const struct ebt_table frame_nat = { .me = THIS_MODULE, }; -static unsigned int ebt_nat_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - return ebt_do_table(skb, state, priv); -} - static const struct nf_hook_ops ebt_ops_nat[] = { { - .hook = ebt_nat_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_LOCAL_OUT, .priority = NF_BR_PRI_NAT_DST_OTHER, }, { - .hook = ebt_nat_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_POST_ROUTING, .priority = NF_BR_PRI_NAT_SRC, }, { - .hook = ebt_nat_hook, + .hook = ebt_do_table, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_PRE_ROUTING, .priority = NF_BR_PRI_NAT_DST_BRIDGED, diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 83d1798dfbb4..4a1508a1c566 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -189,10 +189,10 @@ ebt_get_target_c(const struct ebt_entry *e) } /* Do some firewalling */ -unsigned int ebt_do_table(struct sk_buff *skb, - const struct nf_hook_state *state, - struct ebt_table *table) +unsigned int ebt_do_table(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) { + struct ebt_table *table = priv; unsigned int hook = state->hook; int i, nentries; struct ebt_entry *point; -- cgit v1.2.3 From 8b017fbe0bbb98dd71fb4850f6b9cc0e136a26b8 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 14 Oct 2021 11:00:37 +0200 Subject: net: of: fix stub of_net helpers for CONFIG_NET=n Moving the of_net code from drivers/of/ to net/core means we no longer stub out the helpers when networking is disabled, which leads to a randconfig build failure with at least one ARM platform that calls this from non-networking code: arm-linux-gnueabi-ld: arch/arm/mach-mvebu/kirkwood.o: in function `kirkwood_dt_eth_fixup': kirkwood.c:(.init.text+0x54): undefined reference to `of_get_mac_address' Restore the way this worked before by changing that #ifdef check back to testing for both CONFIG_OF and CONFIG_NET. Fixes: e330fb14590c ("of: net: move of_net under net/") Signed-off-by: Arnd Bergmann Link: https://lore.kernel.org/r/20211014090055.2058949-1-arnd@kernel.org Signed-off-by: Jakub Kicinski --- include/linux/of_net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of_net.h b/include/linux/of_net.h index 0797e2edb8c2..0484b613ca64 100644 --- a/include/linux/of_net.h +++ b/include/linux/of_net.h @@ -8,7 +8,7 @@ #include -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_NET) #include struct net_device; -- cgit v1.2.3 From 52f88693378a58094c538662ba652aff0253c4fe Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Tue, 12 Oct 2021 09:56:13 -0700 Subject: binder: use cred instead of task for selinux checks Since binder was integrated with selinux, it has passed 'struct task_struct' associated with the binder_proc to represent the source and target of transactions. The conversion of task to SID was then done in the hook implementations. It turns out that there are race conditions which can result in an incorrect security context being used. Fix by using the 'struct cred' saved during binder_open and pass it to the selinux subsystem. Cc: stable@vger.kernel.org # 5.14 (need backport for earlier stables) Fixes: 79af73079d75 ("Add security hooks to binder and implement the hooks for SELinux.") Suggested-by: Jann Horn Signed-off-by: Todd Kjos Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- drivers/android/binder.c | 12 +++++------ include/linux/lsm_hook_defs.h | 14 ++++++------- include/linux/lsm_hooks.h | 14 ++++++------- include/linux/security.h | 28 ++++++++++++------------- security/security.c | 14 ++++++------- security/selinux/hooks.c | 48 ++++++++++++------------------------------- 6 files changed, 54 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 231cff9b3b75..1571e01cfa52 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2047,7 +2047,7 @@ static int binder_translate_binder(struct flat_binder_object *fp, ret = -EINVAL; goto done; } - if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + if (security_binder_transfer_binder(proc->cred, target_proc->cred)) { ret = -EPERM; goto done; } @@ -2093,7 +2093,7 @@ static int binder_translate_handle(struct flat_binder_object *fp, proc->pid, thread->pid, fp->handle); return -EINVAL; } - if (security_binder_transfer_binder(proc->tsk, target_proc->tsk)) { + if (security_binder_transfer_binder(proc->cred, target_proc->cred)) { ret = -EPERM; goto done; } @@ -2181,7 +2181,7 @@ static int binder_translate_fd(u32 fd, binder_size_t fd_offset, ret = -EBADF; goto err_fget; } - ret = security_binder_transfer_file(proc->tsk, target_proc->tsk, file); + ret = security_binder_transfer_file(proc->cred, target_proc->cred, file); if (ret < 0) { ret = -EPERM; goto err_security; @@ -2586,8 +2586,8 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_invalid_target_handle; } - if (security_binder_transaction(proc->tsk, - target_proc->tsk) < 0) { + if (security_binder_transaction(proc->cred, + target_proc->cred) < 0) { return_error = BR_FAILED_REPLY; return_error_param = -EPERM; return_error_line = __LINE__; @@ -4555,7 +4555,7 @@ static int binder_ioctl_set_ctx_mgr(struct file *filp, ret = -EBUSY; goto out; } - ret = security_binder_set_context_mgr(proc->tsk); + ret = security_binder_set_context_mgr(proc->cred); if (ret < 0) goto out; if (uid_valid(context->binder_context_mgr_uid)) { diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index b3c525353769..4c7ed0268ce3 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -26,13 +26,13 @@ * #undef LSM_HOOK * }; */ -LSM_HOOK(int, 0, binder_set_context_mgr, struct task_struct *mgr) -LSM_HOOK(int, 0, binder_transaction, struct task_struct *from, - struct task_struct *to) -LSM_HOOK(int, 0, binder_transfer_binder, struct task_struct *from, - struct task_struct *to) -LSM_HOOK(int, 0, binder_transfer_file, struct task_struct *from, - struct task_struct *to, struct file *file) +LSM_HOOK(int, 0, binder_set_context_mgr, const struct cred *mgr) +LSM_HOOK(int, 0, binder_transaction, const struct cred *from, + const struct cred *to) +LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from, + const struct cred *to) +LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from, + const struct cred *to, struct file *file) LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child, unsigned int mode) LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0eb0ae95c4c4..528554e9b90c 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1313,22 +1313,22 @@ * * @binder_set_context_mgr: * Check whether @mgr is allowed to be the binder context manager. - * @mgr contains the task_struct for the task being registered. + * @mgr contains the struct cred for the current binder process. * Return 0 if permission is granted. * @binder_transaction: * Check whether @from is allowed to invoke a binder transaction call * to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. + * @from contains the struct cred for the sending process. + * @to contains the struct cred for the receiving process. * @binder_transfer_binder: * Check whether @from is allowed to transfer a binder reference to @to. - * @from contains the task_struct for the sending task. - * @to contains the task_struct for the receiving task. + * @from contains the struct cred for the sending process. + * @to contains the struct cred for the receiving process. * @binder_transfer_file: * Check whether @from is allowed to transfer @file to @to. - * @from contains the task_struct for the sending task. + * @from contains the struct cred for the sending process. * @file contains the struct file being transferred. - * @to contains the task_struct for the receiving task. + * @to contains the struct cred for the receiving process. * * @ptrace_access_check: * Check permission before allowing the current process to trace the diff --git a/include/linux/security.h b/include/linux/security.h index 7979b9629a42..9be72166e859 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -258,13 +258,13 @@ extern int security_init(void); extern int early_security_init(void); /* Security operations */ -int security_binder_set_context_mgr(struct task_struct *mgr); -int security_binder_transaction(struct task_struct *from, - struct task_struct *to); -int security_binder_transfer_binder(struct task_struct *from, - struct task_struct *to); -int security_binder_transfer_file(struct task_struct *from, - struct task_struct *to, struct file *file); +int security_binder_set_context_mgr(const struct cred *mgr); +int security_binder_transaction(const struct cred *from, + const struct cred *to); +int security_binder_transfer_binder(const struct cred *from, + const struct cred *to); +int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file); int security_ptrace_access_check(struct task_struct *child, unsigned int mode); int security_ptrace_traceme(struct task_struct *parent); int security_capget(struct task_struct *target, @@ -508,25 +508,25 @@ static inline int early_security_init(void) return 0; } -static inline int security_binder_set_context_mgr(struct task_struct *mgr) +static inline int security_binder_set_context_mgr(const struct cred *mgr) { return 0; } -static inline int security_binder_transaction(struct task_struct *from, - struct task_struct *to) +static inline int security_binder_transaction(const struct cred *from, + const struct cred *to) { return 0; } -static inline int security_binder_transfer_binder(struct task_struct *from, - struct task_struct *to) +static inline int security_binder_transfer_binder(const struct cred *from, + const struct cred *to) { return 0; } -static inline int security_binder_transfer_file(struct task_struct *from, - struct task_struct *to, +static inline int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) { return 0; diff --git a/security/security.c b/security/security.c index 40518c340571..d9d53c1e466a 100644 --- a/security/security.c +++ b/security/security.c @@ -747,25 +747,25 @@ static int lsm_superblock_alloc(struct super_block *sb) /* Security operations */ -int security_binder_set_context_mgr(struct task_struct *mgr) +int security_binder_set_context_mgr(const struct cred *mgr) { return call_int_hook(binder_set_context_mgr, 0, mgr); } -int security_binder_transaction(struct task_struct *from, - struct task_struct *to) +int security_binder_transaction(const struct cred *from, + const struct cred *to) { return call_int_hook(binder_transaction, 0, from, to); } -int security_binder_transfer_binder(struct task_struct *from, - struct task_struct *to) +int security_binder_transfer_binder(const struct cred *from, + const struct cred *to) { return call_int_hook(binder_transfer_binder, 0, from, to); } -int security_binder_transfer_file(struct task_struct *from, - struct task_struct *to, struct file *file) +int security_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) { return call_int_hook(binder_transfer_file, 0, from, to, file); } diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 49d52d7a7714..b4a1bde20261 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -255,29 +255,6 @@ static inline u32 task_sid_obj(const struct task_struct *task) return sid; } -/* - * get the security ID of a task for use with binder - */ -static inline u32 task_sid_binder(const struct task_struct *task) -{ - /* - * In many case where this function is used we should be using the - * task's subjective SID, but we can't reliably access the subjective - * creds of a task other than our own so we must use the objective - * creds/SID, which are safe to access. The downside is that if a task - * is temporarily overriding it's creds it will not be reflected here; - * however, it isn't clear that binder would handle that case well - * anyway. - * - * If this ever changes and we can safely reference the subjective - * creds/SID of another task, this function will make it easier to - * identify the various places where we make use of the task SIDs in - * the binder code. It is also likely that we will need to adjust - * the main drivers/android binder code as well. - */ - return task_sid_obj(task); -} - static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dentry); /* @@ -2067,18 +2044,19 @@ static inline u32 open_file_to_av(struct file *file) /* Hook functions begin here. */ -static int selinux_binder_set_context_mgr(struct task_struct *mgr) +static int selinux_binder_set_context_mgr(const struct cred *mgr) { return avc_has_perm(&selinux_state, - current_sid(), task_sid_binder(mgr), SECCLASS_BINDER, + current_sid(), cred_sid(mgr), SECCLASS_BINDER, BINDER__SET_CONTEXT_MGR, NULL); } -static int selinux_binder_transaction(struct task_struct *from, - struct task_struct *to) +static int selinux_binder_transaction(const struct cred *from, + const struct cred *to) { u32 mysid = current_sid(); - u32 fromsid = task_sid_binder(from); + u32 fromsid = cred_sid(from); + u32 tosid = cred_sid(to); int rc; if (mysid != fromsid) { @@ -2089,24 +2067,24 @@ static int selinux_binder_transaction(struct task_struct *from, return rc; } - return avc_has_perm(&selinux_state, fromsid, task_sid_binder(to), + return avc_has_perm(&selinux_state, fromsid, tosid, SECCLASS_BINDER, BINDER__CALL, NULL); } -static int selinux_binder_transfer_binder(struct task_struct *from, - struct task_struct *to) +static int selinux_binder_transfer_binder(const struct cred *from, + const struct cred *to) { return avc_has_perm(&selinux_state, - task_sid_binder(from), task_sid_binder(to), + cred_sid(from), cred_sid(to), SECCLASS_BINDER, BINDER__TRANSFER, NULL); } -static int selinux_binder_transfer_file(struct task_struct *from, - struct task_struct *to, +static int selinux_binder_transfer_file(const struct cred *from, + const struct cred *to, struct file *file) { - u32 sid = task_sid_binder(to); + u32 sid = cred_sid(to); struct file_security_struct *fsec = selinux_file(file); struct dentry *dentry = file->f_path.dentry; struct inode_security_struct *isec; -- cgit v1.2.3 From 4d5b5539742d2554591751b4248b0204d20dcc9d Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Tue, 12 Oct 2021 09:56:14 -0700 Subject: binder: use cred instead of task for getsecid Use the 'struct cred' saved at binder_open() to lookup the security ID via security_cred_getsecid(). This ensures that the security context that opened binder is the one used to generate the secctx. Cc: stable@vger.kernel.org # 5.4+ Fixes: ec74136ded79 ("binder: create node flag to request sender's security context") Signed-off-by: Todd Kjos Suggested-by: Stephen Smalley Reported-by: kernel test robot Acked-by: Casey Schaufler Signed-off-by: Paul Moore --- drivers/android/binder.c | 11 +---------- include/linux/security.h | 5 +++++ 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 1571e01cfa52..49b08c04fa09 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2713,16 +2713,7 @@ static void binder_transaction(struct binder_proc *proc, u32 secid; size_t added_size; - /* - * Arguably this should be the task's subjective LSM secid but - * we can't reliably access the subjective creds of a task - * other than our own so we must use the objective creds, which - * are safe to access. The downside is that if a task is - * temporarily overriding it's creds it will not be reflected - * here; however, it isn't clear that binder would handle that - * case well anyway. - */ - security_task_getsecid_obj(proc->tsk, &secid); + security_cred_getsecid(proc->cred, &secid); ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); if (ret) { return_error = BR_FAILED_REPLY; diff --git a/include/linux/security.h b/include/linux/security.h index 9be72166e859..cc6d39358336 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1041,6 +1041,11 @@ static inline void security_transfer_creds(struct cred *new, { } +static inline void security_cred_getsecid(const struct cred *c, u32 *secid) +{ + *secid = 0; +} + static inline int security_kernel_act_as(struct cred *cred, u32 secid) { return 0; -- cgit v1.2.3 From c072c4ef7ef09e1d6470c48cf52570487589b76a Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Thu, 14 Oct 2021 16:35:06 +0300 Subject: soc: samsung: exynos-chipid: Pass revision reg offsets Old Exynos SoCs have both Product ID and Revision ID in one single register, while new SoCs tend to have two separate registers for those IDs. Implement handling of both cases by passing Revision ID register offsets in driver data. Previously existing macros for Exynos4210 (removed in this patch) were incorrect: #define EXYNOS_SUBREV_MASK (0xf << 4) #define EXYNOS_MAINREV_MASK (0xf << 0) Actual format of PRO_ID register in Exynos4210 (offset 0x0): [31:12] Product ID [9:8] Package information [7:4] Main Revision Number [3:0] Sub Revision Number This patch doesn't change the behavior on existing platforms, so '/sys/devices/soc0/revision' will show the same string as before. Signed-off-by: Sam Protsenko Tested-by: Henrik Grimler Link: https://lore.kernel.org/r/20211014133508.1210-1-semen.protsenko@linaro.org Signed-off-by: Krzysztof Kozlowski --- drivers/soc/samsung/exynos-chipid.c | 69 ++++++++++++++++++++++++++----- include/linux/soc/samsung/exynos-chipid.h | 6 +-- 2 files changed, 60 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/samsung/exynos-chipid.c b/drivers/soc/samsung/exynos-chipid.c index b2627a3a127a..986978e83661 100644 --- a/drivers/soc/samsung/exynos-chipid.c +++ b/drivers/soc/samsung/exynos-chipid.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -25,6 +26,17 @@ #include "exynos-asv.h" +struct exynos_chipid_variant { + unsigned int rev_reg; /* revision register offset */ + unsigned int main_rev_shift; /* main revision offset in rev_reg */ + unsigned int sub_rev_shift; /* sub revision offset in rev_reg */ +}; + +struct exynos_chipid_info { + u32 product_id; + u32 revision; +}; + static const struct exynos_soc_id { const char *name; unsigned int id; @@ -50,31 +62,57 @@ static const char *product_id_to_soc_id(unsigned int product_id) int i; for (i = 0; i < ARRAY_SIZE(soc_ids); i++) - if ((product_id & EXYNOS_MASK) == soc_ids[i].id) + if (product_id == soc_ids[i].id) return soc_ids[i].name; return NULL; } +static int exynos_chipid_get_chipid_info(struct regmap *regmap, + const struct exynos_chipid_variant *data, + struct exynos_chipid_info *soc_info) +{ + int ret; + unsigned int val, main_rev, sub_rev; + + ret = regmap_read(regmap, EXYNOS_CHIPID_REG_PRO_ID, &val); + if (ret < 0) + return ret; + soc_info->product_id = val & EXYNOS_MASK; + + if (data->rev_reg != EXYNOS_CHIPID_REG_PRO_ID) { + ret = regmap_read(regmap, data->rev_reg, &val); + if (ret < 0) + return ret; + } + main_rev = (val >> data->main_rev_shift) & EXYNOS_REV_PART_MASK; + sub_rev = (val >> data->sub_rev_shift) & EXYNOS_REV_PART_MASK; + soc_info->revision = (main_rev << EXYNOS_REV_PART_SHIFT) | sub_rev; + + return 0; +} + static int exynos_chipid_probe(struct platform_device *pdev) { + const struct exynos_chipid_variant *drv_data; + struct exynos_chipid_info soc_info; struct soc_device_attribute *soc_dev_attr; struct soc_device *soc_dev; struct device_node *root; struct regmap *regmap; - u32 product_id; - u32 revision; int ret; + drv_data = of_device_get_match_data(&pdev->dev); + if (!drv_data) + return -EINVAL; + regmap = device_node_to_regmap(pdev->dev.of_node); if (IS_ERR(regmap)) return PTR_ERR(regmap); - ret = regmap_read(regmap, EXYNOS_CHIPID_REG_PRO_ID, &product_id); + ret = exynos_chipid_get_chipid_info(regmap, drv_data, &soc_info); if (ret < 0) return ret; - revision = product_id & EXYNOS_REV_MASK; - soc_dev_attr = devm_kzalloc(&pdev->dev, sizeof(*soc_dev_attr), GFP_KERNEL); if (!soc_dev_attr) @@ -87,8 +125,8 @@ static int exynos_chipid_probe(struct platform_device *pdev) of_node_put(root); soc_dev_attr->revision = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "%x", revision); - soc_dev_attr->soc_id = product_id_to_soc_id(product_id); + "%x", soc_info.revision); + soc_dev_attr->soc_id = product_id_to_soc_id(soc_info.product_id); if (!soc_dev_attr->soc_id) { pr_err("Unknown SoC\n"); return -ENODEV; @@ -106,7 +144,7 @@ static int exynos_chipid_probe(struct platform_device *pdev) platform_set_drvdata(pdev, soc_dev); dev_info(&pdev->dev, "Exynos: CPU[%s] PRO_ID[0x%x] REV[0x%x] Detected\n", - soc_dev_attr->soc_id, product_id, revision); + soc_dev_attr->soc_id, soc_info.product_id, soc_info.revision); return 0; @@ -125,9 +163,18 @@ static int exynos_chipid_remove(struct platform_device *pdev) return 0; } +static const struct exynos_chipid_variant exynos4210_chipid_drv_data = { + .rev_reg = 0x0, + .main_rev_shift = 4, + .sub_rev_shift = 0, +}; + static const struct of_device_id exynos_chipid_of_device_ids[] = { - { .compatible = "samsung,exynos4210-chipid" }, - {} + { + .compatible = "samsung,exynos4210-chipid", + .data = &exynos4210_chipid_drv_data, + }, + { } }; MODULE_DEVICE_TABLE(of, exynos_chipid_of_device_ids); diff --git a/include/linux/soc/samsung/exynos-chipid.h b/include/linux/soc/samsung/exynos-chipid.h index 8bca6763f99c..62f0e2531068 100644 --- a/include/linux/soc/samsung/exynos-chipid.h +++ b/include/linux/soc/samsung/exynos-chipid.h @@ -9,10 +9,8 @@ #define __LINUX_SOC_EXYNOS_CHIPID_H #define EXYNOS_CHIPID_REG_PRO_ID 0x00 -#define EXYNOS_SUBREV_MASK (0xf << 4) -#define EXYNOS_MAINREV_MASK (0xf << 0) -#define EXYNOS_REV_MASK (EXYNOS_SUBREV_MASK | \ - EXYNOS_MAINREV_MASK) +#define EXYNOS_REV_PART_MASK 0xf +#define EXYNOS_REV_PART_SHIFT 4 #define EXYNOS_MASK 0xfffff000 #define EXYNOS_CHIPID_REG_PKG_ID 0x04 -- cgit v1.2.3 From 42a20f86dc19f9282d974df0ba4d226c865ab9dd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 29 Sep 2021 15:02:14 -0700 Subject: sched: Add wrapper for get_wchan() to keep task blocked Having a stable wchan means the process must be blocked and for it to stay that way while performing stack unwinding. Suggested-by: Peter Zijlstra Signed-off-by: Kees Cook Signed-off-by: Peter Zijlstra (Intel) Acked-by: Geert Uytterhoeven Acked-by: Russell King (Oracle) [arm] Tested-by: Mark Rutland [arm64] Link: https://lkml.kernel.org/r/20211008111626.332092234@infradead.org --- arch/alpha/include/asm/processor.h | 2 +- arch/alpha/kernel/process.c | 5 ++--- arch/arc/include/asm/processor.h | 2 +- arch/arc/kernel/stacktrace.c | 4 ++-- arch/arm/include/asm/processor.h | 2 +- arch/arm/kernel/process.c | 4 +--- arch/arm64/include/asm/processor.h | 2 +- arch/arm64/kernel/process.c | 4 +--- arch/csky/include/asm/processor.h | 2 +- arch/csky/kernel/stacktrace.c | 5 ++--- arch/h8300/include/asm/processor.h | 2 +- arch/h8300/kernel/process.c | 5 +---- arch/hexagon/include/asm/processor.h | 2 +- arch/hexagon/kernel/process.c | 4 +--- arch/ia64/include/asm/processor.h | 2 +- arch/ia64/kernel/process.c | 5 +---- arch/m68k/include/asm/processor.h | 2 +- arch/m68k/kernel/process.c | 4 +--- arch/microblaze/include/asm/processor.h | 2 +- arch/microblaze/kernel/process.c | 2 +- arch/mips/include/asm/processor.h | 2 +- arch/mips/kernel/process.c | 8 +++----- arch/nds32/include/asm/processor.h | 2 +- arch/nds32/kernel/process.c | 7 +------ arch/nios2/include/asm/processor.h | 2 +- arch/nios2/kernel/process.c | 5 +---- arch/openrisc/include/asm/processor.h | 2 +- arch/openrisc/kernel/process.c | 2 +- arch/parisc/include/asm/processor.h | 2 +- arch/parisc/kernel/process.c | 5 +---- arch/powerpc/include/asm/processor.h | 2 +- arch/powerpc/kernel/process.c | 9 +++------ arch/riscv/include/asm/processor.h | 2 +- arch/riscv/kernel/stacktrace.c | 12 +++++------- arch/s390/include/asm/processor.h | 2 +- arch/s390/kernel/process.c | 4 ++-- arch/sh/include/asm/processor_32.h | 2 +- arch/sh/kernel/process_32.c | 5 +---- arch/sparc/include/asm/processor_32.h | 2 +- arch/sparc/include/asm/processor_64.h | 2 +- arch/sparc/kernel/process_32.c | 5 +---- arch/sparc/kernel/process_64.c | 5 +---- arch/um/include/asm/processor-generic.h | 2 +- arch/um/kernel/process.c | 5 +---- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/process.c | 5 +---- arch/xtensa/include/asm/processor.h | 2 +- arch/xtensa/kernel/process.c | 5 +---- include/linux/sched.h | 1 + kernel/sched/core.c | 19 +++++++++++++++++++ 50 files changed, 80 insertions(+), 112 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h index 6100431da07a..090499c99c1c 100644 --- a/arch/alpha/include/asm/processor.h +++ b/arch/alpha/include/asm/processor.h @@ -42,7 +42,7 @@ extern void start_thread(struct pt_regs *, unsigned long, unsigned long); struct task_struct; extern void release_thread(struct task_struct *); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c index a5123ea426ce..5f8527081da9 100644 --- a/arch/alpha/kernel/process.c +++ b/arch/alpha/kernel/process.c @@ -376,12 +376,11 @@ thread_saved_pc(struct task_struct *t) } unsigned long -get_wchan(struct task_struct *p) +__get_wchan(struct task_struct *p) { unsigned long schedule_frame; unsigned long pc; - if (!p || p == current || task_is_running(p)) - return 0; + /* * This one depends on the frame size of schedule(). Do a * "disass schedule" in gdb to find the frame size. Also, the diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h index f28afcf5c6d1..54db9d7bb562 100644 --- a/arch/arc/include/asm/processor.h +++ b/arch/arc/include/asm/processor.h @@ -70,7 +70,7 @@ struct task_struct; extern void start_thread(struct pt_regs * regs, unsigned long pc, unsigned long usp); -extern unsigned int get_wchan(struct task_struct *p); +extern unsigned int __get_wchan(struct task_struct *p); #endif /* !__ASSEMBLY__ */ diff --git a/arch/arc/kernel/stacktrace.c b/arch/arc/kernel/stacktrace.c index c376ff3147e7..5372dc04e784 100644 --- a/arch/arc/kernel/stacktrace.c +++ b/arch/arc/kernel/stacktrace.c @@ -15,7 +15,7 @@ * = specifics of data structs where trace is saved(CONFIG_STACKTRACE etc) * * vineetg: March 2009 - * -Implemented correct versions of thread_saved_pc() and get_wchan() + * -Implemented correct versions of thread_saved_pc() and __get_wchan() * * rajeshwarr: 2008 * -Initial implementation @@ -248,7 +248,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) * Of course just returning schedule( ) would be pointless so unwind until * the function is not in schedular code */ -unsigned int get_wchan(struct task_struct *tsk) +unsigned int __get_wchan(struct task_struct *tsk) { return arc_unwind_core(tsk, NULL, __get_first_nonsched, NULL); } diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h index 9e6b97286307..6af68edfa53a 100644 --- a/arch/arm/include/asm/processor.h +++ b/arch/arm/include/asm/processor.h @@ -84,7 +84,7 @@ struct task_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1) diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 0e2d3051741e..96f577e59595 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -276,13 +276,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, return 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { struct stackframe frame; unsigned long stack_page; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; frame.fp = thread_saved_fp(p); frame.sp = thread_saved_sp(p); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index ee2bdc1b9f5b..55ca034238ea 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -257,7 +257,7 @@ struct task_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); void update_sctlr_el1(u64 sctlr); diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 40adb8cdbf5a..aacf2f5559a8 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -528,13 +528,11 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, return last; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { struct stackframe frame; unsigned long stack_page, ret = 0; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; stack_page = (unsigned long)try_get_task_stack(p); if (!stack_page) diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index 9e933021fe8e..817dd60ff152 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -81,7 +81,7 @@ static inline void release_thread(struct task_struct *dead_task) extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->usp) diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c index 1b280ef08004..9f78f5d21511 100644 --- a/arch/csky/kernel/stacktrace.c +++ b/arch/csky/kernel/stacktrace.c @@ -111,12 +111,11 @@ static bool save_wchan(unsigned long pc, void *arg) return false; } -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc = 0; - if (likely(task && task != current && !task_is_running(task))) - walk_stackframe(task, NULL, save_wchan, &pc); + walk_stackframe(task, NULL, save_wchan, &pc); return pc; } diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h index a060b41b2d31..141a23eb62b7 100644 --- a/arch/h8300/include/asm/processor.h +++ b/arch/h8300/include/asm/processor.h @@ -105,7 +105,7 @@ static inline void release_thread(struct task_struct *dead_task) { } -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) \ ({ \ diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c index 2ac27e4248a4..8833fa4f5d51 100644 --- a/arch/h8300/kernel/process.c +++ b/arch/h8300/kernel/process.c @@ -128,15 +128,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, return 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long fp, pc; unsigned long stack_page; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - stack_page = (unsigned long)p; fp = ((struct pt_regs *)p->thread.ksp)->er6; do { diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h index 9f0cc99420be..615f7e49968e 100644 --- a/arch/hexagon/include/asm/processor.h +++ b/arch/hexagon/include/asm/processor.h @@ -64,7 +64,7 @@ struct thread_struct { extern void release_thread(struct task_struct *dead_task); /* Get wait channel for task P. */ -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); /* The following stuff is pretty HEXAGON specific. */ diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c index 6a6835fb4242..232dfd8956aa 100644 --- a/arch/hexagon/kernel/process.c +++ b/arch/hexagon/kernel/process.c @@ -130,13 +130,11 @@ void flush_thread(void) * is an identification of the point at which the scheduler * was invoked by a blocked thread. */ -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long fp, pc; unsigned long stack_page; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; stack_page = (unsigned long)task_stack_page(p); fp = ((struct hexagon_switch_stack *)p->thread.switch_sp)->fp; diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index 2d8bcdc27d7f..45365c2ef598 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -330,7 +330,7 @@ struct task_struct; #define release_thread(dead_task) /* Get wait channel for task P. */ -extern unsigned long get_wchan (struct task_struct *p); +extern unsigned long __get_wchan (struct task_struct *p); /* Return instruction pointer of blocked task TSK. */ #define KSTK_EIP(tsk) \ diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c index e56d63f4abf9..834df24a88f1 100644 --- a/arch/ia64/kernel/process.c +++ b/arch/ia64/kernel/process.c @@ -523,15 +523,12 @@ exit_thread (struct task_struct *tsk) } unsigned long -get_wchan (struct task_struct *p) +__get_wchan (struct task_struct *p) { struct unw_frame_info info; unsigned long ip; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - /* * Note: p may not be a blocked task (it could be current or * another process running on some other CPU. Rather than diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h index f4d82c619a5c..ffeda9aa526a 100644 --- a/arch/m68k/include/asm/processor.h +++ b/arch/m68k/include/asm/processor.h @@ -150,7 +150,7 @@ static inline void release_thread(struct task_struct *dead_task) { } -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) \ ({ \ diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 1ab692b952cd..a6030dbaa089 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -263,13 +263,11 @@ int dump_fpu (struct pt_regs *regs, struct user_m68kfp_struct *fpu) } EXPORT_SYMBOL(dump_fpu); -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long fp, pc; unsigned long stack_page; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; stack_page = (unsigned long)task_stack_page(p); fp = ((struct switch_stack *)p->thread.ksp)->a6; diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h index 06c6e493590a..7e9e92670df3 100644 --- a/arch/microblaze/include/asm/processor.h +++ b/arch/microblaze/include/asm/processor.h @@ -68,7 +68,7 @@ static inline void release_thread(struct task_struct *dead_task) { } -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); /* The size allocated for kernel stacks. This _must_ be a power of two! */ # define KERNEL_STACK_SIZE 0x2000 diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 62aa237180b6..5e2b91c1e8ce 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -112,7 +112,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp, unsigned long arg, return 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { /* TBD (used by procfs) */ return 0; diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h index 0c3550c82b72..252ed38ce8c5 100644 --- a/arch/mips/include/asm/processor.h +++ b/arch/mips/include/asm/processor.h @@ -369,7 +369,7 @@ static inline void flush_thread(void) { } -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \ THREAD_SIZE - 32 - sizeof(struct pt_regs)) diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 95aa86fa6077..cbff1b974f88 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -511,7 +511,7 @@ static int __init frame_info_init(void) /* * Without schedule() frame info, result given by - * thread_saved_pc() and get_wchan() are not reliable. + * thread_saved_pc() and __get_wchan() are not reliable. */ if (schedule_mfi.pc_offset < 0) printk("Can't analyze schedule() prologue at %p\n", schedule); @@ -652,9 +652,9 @@ unsigned long unwind_stack(struct task_struct *task, unsigned long *sp, #endif /* - * get_wchan - a maintenance nightmare^W^Wpain in the ass ... + * __get_wchan - a maintenance nightmare^W^Wpain in the ass ... */ -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc = 0; #ifdef CONFIG_KALLSYMS @@ -662,8 +662,6 @@ unsigned long get_wchan(struct task_struct *task) unsigned long ra = 0; #endif - if (!task || task == current || task_is_running(task)) - goto out; if (!task_stack_page(task)) goto out; diff --git a/arch/nds32/include/asm/processor.h b/arch/nds32/include/asm/processor.h index b82369c7659d..e6bfc74972bb 100644 --- a/arch/nds32/include/asm/processor.h +++ b/arch/nds32/include/asm/processor.h @@ -83,7 +83,7 @@ extern struct task_struct *last_task_used_math; /* Prepare to copy thread state - unlazy all lazy status */ #define prepare_to_copy(tsk) do { } while (0) -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define cpu_relax() barrier() diff --git a/arch/nds32/kernel/process.c b/arch/nds32/kernel/process.c index 391895b54d13..49fab9e39cbf 100644 --- a/arch/nds32/kernel/process.c +++ b/arch/nds32/kernel/process.c @@ -233,15 +233,12 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t * fpu) EXPORT_SYMBOL(dump_fpu); -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long fp, lr; unsigned long stack_start, stack_end; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - if (IS_ENABLED(CONFIG_FRAME_POINTER)) { stack_start = (unsigned long)end_of_stack(p); stack_end = (unsigned long)task_stack_page(p) + THREAD_SIZE; @@ -258,5 +255,3 @@ unsigned long get_wchan(struct task_struct *p) } return 0; } - -EXPORT_SYMBOL(get_wchan); diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h index 94bcb86f679f..b8125dfbcad2 100644 --- a/arch/nios2/include/asm/processor.h +++ b/arch/nios2/include/asm/processor.h @@ -69,7 +69,7 @@ static inline void release_thread(struct task_struct *dead_task) { } -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c index 9ff37ba2bb60..f8ea522a1588 100644 --- a/arch/nios2/kernel/process.c +++ b/arch/nios2/kernel/process.c @@ -217,15 +217,12 @@ void dump(struct pt_regs *fp) pr_emerg("\n\n"); } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long fp, pc; unsigned long stack_page; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - stack_page = (unsigned long)p; fp = ((struct switch_stack *)p->thread.ksp)->fp; /* ;dgt2 */ do { diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h index ad53b3184885..aa1699c18add 100644 --- a/arch/openrisc/include/asm/processor.h +++ b/arch/openrisc/include/asm/processor.h @@ -73,7 +73,7 @@ struct thread_struct { void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp); void release_thread(struct task_struct *); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define cpu_relax() barrier() diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c index b0698d9ce14f..3c0c91bcdcba 100644 --- a/arch/openrisc/kernel/process.c +++ b/arch/openrisc/kernel/process.c @@ -263,7 +263,7 @@ void dump_elf_thread(elf_greg_t *dest, struct pt_regs* regs) dest[35] = 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { /* TODO */ diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index eeb7da064289..85a2dbfe5278 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -273,7 +273,7 @@ struct mm_struct; /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.regs.iaoq[0]) #define KSTK_ESP(tsk) ((tsk)->thread.regs.gr[30]) diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 38ec4ae81239..4f562dee65a2 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -240,15 +240,12 @@ copy_thread(unsigned long clone_flags, unsigned long usp, } unsigned long -get_wchan(struct task_struct *p) +__get_wchan(struct task_struct *p) { struct unwind_frame_info info; unsigned long ip; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - /* * These bracket the sleeping functions.. */ diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index f348e564f7dd..e39bd0ff69f3 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -300,7 +300,7 @@ struct thread_struct { #define task_pt_regs(tsk) ((tsk)->thread.regs) -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0) #define KSTK_ESP(tsk) ((tsk)->thread.regs? (tsk)->thread.regs->gpr[1]: 0) diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 50436b52c213..406d7ee9e322 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -2111,14 +2111,11 @@ int validate_sp(unsigned long sp, struct task_struct *p, EXPORT_SYMBOL(validate_sp); -static unsigned long __get_wchan(struct task_struct *p) +static unsigned long ___get_wchan(struct task_struct *p) { unsigned long ip, sp; int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - sp = p->thread.ksp; if (!validate_sp(sp, p, STACK_FRAME_OVERHEAD)) return 0; @@ -2137,14 +2134,14 @@ static unsigned long __get_wchan(struct task_struct *p) return 0; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long ret; if (!try_get_task_stack(p)) return 0; - ret = __get_wchan(p); + ret = ___get_wchan(p); put_task_stack(p); diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 46b492c78cbb..0749924d9e55 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -66,7 +66,7 @@ static inline void release_thread(struct task_struct *dead_task) { } -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); static inline void wait_for_interrupt(void) diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 315db3d0229b..0fcdc0233fac 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -128,16 +128,14 @@ static bool save_wchan(void *arg, unsigned long pc) return true; } -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc = 0; - if (likely(task && task != current && !task_is_running(task))) { - if (!try_get_task_stack(task)) - return 0; - walk_stackframe(task, NULL, save_wchan, &pc); - put_task_stack(task); - } + if (!try_get_task_stack(task)) + return 0; + walk_stackframe(task, NULL, save_wchan, &pc); + put_task_stack(task); return pc; } diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 879b8e3f609c..f54c152bf2bf 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -192,7 +192,7 @@ static inline void release_thread(struct task_struct *tsk) { } void guarded_storage_release(struct task_struct *tsk); void gs_load_bc_cb(struct pt_regs *regs); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); #define task_pt_regs(tsk) ((struct pt_regs *) \ (task_stack_page(tsk) + THREAD_SIZE) - 1) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->psw.addr) diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 350e94d0cac2..e5dd46b1bff8 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -181,12 +181,12 @@ void execve_tail(void) asm volatile("sfpc %0" : : "d" (0)); } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { struct unwind_state state; unsigned long ip = 0; - if (!p || p == current || task_is_running(p) || !task_stack_page(p)) + if (!task_stack_page(p)) return 0; if (!try_get_task_stack(p)) diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h index aa92cc933889..45240ec6b85a 100644 --- a/arch/sh/include/asm/processor_32.h +++ b/arch/sh/include/asm/processor_32.h @@ -180,7 +180,7 @@ static inline void show_code(struct pt_regs *regs) } #endif -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[15]) diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c index 717de05c81f4..1c28e3cddb60 100644 --- a/arch/sh/kernel/process_32.c +++ b/arch/sh/kernel/process_32.c @@ -182,13 +182,10 @@ __switch_to(struct task_struct *prev, struct task_struct *next) return prev; } -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long pc; - if (!p || p == current || task_is_running(p)) - return 0; - /* * The same comment as on the Alpha applies here, too ... */ diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h index b6242f7771e9..647bf0ac7beb 100644 --- a/arch/sparc/include/asm/processor_32.h +++ b/arch/sparc/include/asm/processor_32.h @@ -89,7 +89,7 @@ static inline void start_thread(struct pt_regs * regs, unsigned long pc, /* Free all resources held by a thread. */ #define release_thread(tsk) do { } while(0) -unsigned long get_wchan(struct task_struct *); +unsigned long __get_wchan(struct task_struct *); #define task_pt_regs(tsk) ((tsk)->thread.kregs) #define KSTK_EIP(tsk) ((tsk)->thread.kregs->pc) diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h index 5cf145f18f36..ae851e8fce4c 100644 --- a/arch/sparc/include/asm/processor_64.h +++ b/arch/sparc/include/asm/processor_64.h @@ -183,7 +183,7 @@ do { \ /* Free all resources held by a thread. */ #define release_thread(tsk) do { } while (0) -unsigned long get_wchan(struct task_struct *task); +unsigned long __get_wchan(struct task_struct *task); #define task_pt_regs(tsk) (task_thread_info(tsk)->kregs) #define KSTK_EIP(tsk) (task_pt_regs(tsk)->tpc) diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c index bbbe0cfef746..2dc0bf9fe62e 100644 --- a/arch/sparc/kernel/process_32.c +++ b/arch/sparc/kernel/process_32.c @@ -365,7 +365,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, return 0; } -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc, fp, bias = 0; unsigned long task_base = (unsigned long) task; @@ -373,9 +373,6 @@ unsigned long get_wchan(struct task_struct *task) struct reg_window32 *rw; int count = 0; - if (!task || task == current || task_is_running(task)) - goto out; - fp = task_thread_info(task)->ksp + bias; do { /* Bogus frame pointer? */ diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index d1cc410d2f64..f5b2cac8669f 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -663,7 +663,7 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) return 0; } -unsigned long get_wchan(struct task_struct *task) +unsigned long __get_wchan(struct task_struct *task) { unsigned long pc, fp, bias = 0; struct thread_info *tp; @@ -671,9 +671,6 @@ unsigned long get_wchan(struct task_struct *task) unsigned long ret = 0; int count = 0; - if (!task || task == current || task_is_running(task)) - goto out; - tp = task_thread_info(task); bias = STACK_BIAS; fp = task_thread_info(task)->ksp + bias; diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h index b5cf0ed116d9..579692a40a55 100644 --- a/arch/um/include/asm/processor-generic.h +++ b/arch/um/include/asm/processor-generic.h @@ -106,6 +106,6 @@ extern struct cpuinfo_um boot_cpu_data; #define cache_line_size() (boot_cpu_data.cache_alignment) #define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf) -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); #endif diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 457a38db368b..82107373ac7e 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -364,14 +364,11 @@ unsigned long arch_align_stack(unsigned long sp) } #endif -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long stack_page, sp, ip; bool seen_sched = 0; - if ((p == NULL) || (p == current) || task_is_running(p)) - return 0; - stack_page = (unsigned long) task_stack_page(p); /* Bail if the process has no kernel stack for some reason */ if (stack_page == 0) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9ad2acaaae9b..e81177edc681 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -589,7 +589,7 @@ static inline void load_sp0(unsigned long sp0) /* Free all resources held by a thread. */ extern void release_thread(struct task_struct *); -unsigned long get_wchan(struct task_struct *p); +unsigned long __get_wchan(struct task_struct *p); /* * Generic CPUID function diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index e645925f9f02..a69885a9d711 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -942,13 +942,10 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) * because the task might wake up and we might look at a stack * changing under us. */ -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long entry = 0; - if (p == current || task_is_running(p)) - return 0; - stack_trace_save_tsk(p, &entry, 1, 0); return entry; } diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 7f63aca6a0d3..ad15fbc57283 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -215,7 +215,7 @@ struct mm_struct; /* Free all resources held by a thread. */ #define release_thread(thread) do { } while(0) -extern unsigned long get_wchan(struct task_struct *p); +extern unsigned long __get_wchan(struct task_struct *p); #define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc) #define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1]) diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c index 060165340612..47f933fed870 100644 --- a/arch/xtensa/kernel/process.c +++ b/arch/xtensa/kernel/process.c @@ -298,15 +298,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp_thread_fn, * These bracket the sleeping functions.. */ -unsigned long get_wchan(struct task_struct *p) +unsigned long __get_wchan(struct task_struct *p) { unsigned long sp, pc; unsigned long stack_page = (unsigned long) task_stack_page(p); int count = 0; - if (!p || p == current || task_is_running(p)) - return 0; - sp = p->thread.sp; pc = MAKE_PC_FROM_RA(p->thread.ra, p->thread.sp); diff --git a/include/linux/sched.h b/include/linux/sched.h index 343603f77f8b..5f8db54226af 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2139,6 +2139,7 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) #endif /* CONFIG_SMP */ extern bool sched_task_on_rq(struct task_struct *p); +extern unsigned long get_wchan(struct task_struct *p); /* * In order to reduce various lock holder preemption latencies provide an diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 935c2da00339..f2611b9cf503 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1966,6 +1966,25 @@ bool sched_task_on_rq(struct task_struct *p) return task_on_rq_queued(p); } +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long ip = 0; + unsigned int state; + + if (!p || p == current) + return 0; + + /* Only get wchan if task is blocked and we can keep it that way. */ + raw_spin_lock_irq(&p->pi_lock); + state = READ_ONCE(p->__state); + smp_rmb(); /* see try_to_wake_up() */ + if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq) + ip = __get_wchan(p); + raw_spin_unlock_irq(&p->pi_lock); + + return ip; +} + static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { if (!(flags & ENQUEUE_NOCLOCK)) -- cgit v1.2.3 From c5e22feffdd736cb02b98b0f5b375c8ebc858dd4 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Fri, 24 Sep 2021 20:51:02 +1200 Subject: topology: Represent clusters of CPUs within a die Both ACPI and DT provide the ability to describe additional layers of topology between that of individual cores and higher level constructs such as the level at which the last level cache is shared. In ACPI this can be represented in PPTT as a Processor Hierarchy Node Structure [1] that is the parent of the CPU cores and in turn has a parent Processor Hierarchy Nodes Structure representing a higher level of topology. For example Kunpeng 920 has 6 or 8 clusters in each NUMA node, and each cluster has 4 cpus. All clusters share L3 cache data, but each cluster has local L3 tag. On the other hand, each clusters will share some internal system bus. +-----------------------------------+ +---------+ | +------+ +------+ +--------------------------+ | | | CPU0 | | cpu1 | | +-----------+ | | | +------+ +------+ | | | | | | +----+ L3 | | | | +------+ +------+ cluster | | tag | | | | | CPU2 | | CPU3 | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | | +-----------------------------------+ | | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | | | L3 | | | | +------+ +------+ +----+ tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | L3 | | data | +-----------------------------------+ | | | +------+ +------+ | +-----------+ | | | | | | | | | | | | | +------+ +------+ +----+ L3 | | | | | | tag | | | | +------+ +------+ | | | | | | | | | | | +-----------+ | | | +------+ +------+ +--------------------------+ | +-----------------------------------| | | +-----------------------------------| | | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | +----+ L3 | | | | +------+ +------+ | | tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | | +-----------------------------------+ | | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | | | L3 | | | | +------+ +------+ +---+ tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | | | +-----------------------------------+ | | +-----------------------------------+ | | | +------+ +------+ +--------------------------+ | | | | | | | +-----------+ | | | +------+ +------+ | | | | | | | | L3 | | | | +------+ +------+ +--+ tag | | | | | | | | | | | | | | +------+ +------+ | +-----------+ | | | | +---------+ +-----------------------------------+ That means spreading tasks among clusters will bring more bandwidth while packing tasks within one cluster will lead to smaller cache synchronization latency. So both kernel and userspace will have a chance to leverage this topology to deploy tasks accordingly to achieve either smaller cache latency within one cluster or an even distribution of load among clusters for higher throughput. This patch exposes cluster topology to both kernel and userspace. Libraried like hwloc will know cluster by cluster_cpus and related sysfs attributes. PoC of HWLOC support at [2]. Note this patch only handle the ACPI case. Special consideration is needed for SMT processors, where it is necessary to move 2 levels up the hierarchy from the leaf nodes (thus skipping the processor core level). Note that arm64 / ACPI does not provide any means of identifying a die level in the topology but that may be unrelate to the cluster level. [1] ACPI Specification 6.3 - section 5.2.29.1 processor hierarchy node structure (Type 0) [2] https://github.com/hisilicon/hwloc/tree/linux-cluster Signed-off-by: Jonathan Cameron Signed-off-by: Tian Tao Signed-off-by: Barry Song Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210924085104.44806-2-21cnbao@gmail.com --- Documentation/ABI/stable/sysfs-devices-system-cpu | 15 +++++ Documentation/admin-guide/cputopology.rst | 12 ++-- arch/arm64/kernel/topology.c | 2 + drivers/acpi/pptt.c | 67 +++++++++++++++++++++++ drivers/base/arch_topology.c | 15 +++++ drivers/base/topology.c | 10 ++++ include/linux/acpi.h | 5 ++ include/linux/arch_topology.h | 5 ++ include/linux/topology.h | 6 ++ 9 files changed, 133 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/stable/sysfs-devices-system-cpu b/Documentation/ABI/stable/sysfs-devices-system-cpu index 516dafea03eb..3965ce504484 100644 --- a/Documentation/ABI/stable/sysfs-devices-system-cpu +++ b/Documentation/ABI/stable/sysfs-devices-system-cpu @@ -42,6 +42,12 @@ Description: the CPU core ID of cpuX. Typically it is the hardware platform's architecture and platform dependent. Values: integer +What: /sys/devices/system/cpu/cpuX/topology/cluster_id +Description: the cluster ID of cpuX. Typically it is the hardware platform's + identifier (rather than the kernel's). The actual value is + architecture and platform dependent. +Values: integer + What: /sys/devices/system/cpu/cpuX/topology/book_id Description: the book ID of cpuX. Typically it is the hardware platform's identifier (rather than the kernel's). The actual value is @@ -85,6 +91,15 @@ Description: human-readable list of CPUs within the same die. The format is like 0-3, 8-11, 14,17. Values: decimal list. +What: /sys/devices/system/cpu/cpuX/topology/cluster_cpus +Description: internal kernel map of CPUs within the same cluster. +Values: hexadecimal bitmask. + +What: /sys/devices/system/cpu/cpuX/topology/cluster_cpus_list +Description: human-readable list of CPUs within the same cluster. + The format is like 0-3, 8-11, 14,17. +Values: decimal list. + What: /sys/devices/system/cpu/cpuX/topology/book_siblings Description: internal kernel map of cpuX's hardware threads within the same book_id. it's only used on s390. diff --git a/Documentation/admin-guide/cputopology.rst b/Documentation/admin-guide/cputopology.rst index b085dbac60a5..6b62e182baf4 100644 --- a/Documentation/admin-guide/cputopology.rst +++ b/Documentation/admin-guide/cputopology.rst @@ -19,11 +19,13 @@ these macros in include/asm-XXX/topology.h:: #define topology_physical_package_id(cpu) #define topology_die_id(cpu) + #define topology_cluster_id(cpu) #define topology_core_id(cpu) #define topology_book_id(cpu) #define topology_drawer_id(cpu) #define topology_sibling_cpumask(cpu) #define topology_core_cpumask(cpu) + #define topology_cluster_cpumask(cpu) #define topology_die_cpumask(cpu) #define topology_book_cpumask(cpu) #define topology_drawer_cpumask(cpu) @@ -39,10 +41,12 @@ not defined by include/asm-XXX/topology.h: 1) topology_physical_package_id: -1 2) topology_die_id: -1 -3) topology_core_id: 0 -4) topology_sibling_cpumask: just the given CPU -5) topology_core_cpumask: just the given CPU -6) topology_die_cpumask: just the given CPU +3) topology_cluster_id: -1 +4) topology_core_id: 0 +5) topology_sibling_cpumask: just the given CPU +6) topology_core_cpumask: just the given CPU +7) topology_cluster_cpumask: just the given CPU +8) topology_die_cpumask: just the given CPU For architectures that don't support books (CONFIG_SCHED_BOOK) there are no default definitions for topology_book_id() and topology_book_cpumask(). diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 4dd14a6620c1..9ab78ad826e2 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -103,6 +103,8 @@ int __init parse_acpi_topology(void) cpu_topology[cpu].thread_id = -1; cpu_topology[cpu].core_id = topology_id; } + topology_id = find_acpi_cpu_topology_cluster(cpu); + cpu_topology[cpu].cluster_id = topology_id; topology_id = find_acpi_cpu_topology_package(cpu); cpu_topology[cpu].package_id = topology_id; diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c index fe69dc518f31..701f61c01359 100644 --- a/drivers/acpi/pptt.c +++ b/drivers/acpi/pptt.c @@ -746,6 +746,73 @@ int find_acpi_cpu_topology_package(unsigned int cpu) ACPI_PPTT_PHYSICAL_PACKAGE); } +/** + * find_acpi_cpu_topology_cluster() - Determine a unique CPU cluster value + * @cpu: Kernel logical CPU number + * + * Determine a topology unique cluster ID for the given CPU/thread. + * This ID can then be used to group peers, which will have matching ids. + * + * The cluster, if present is the level of topology above CPUs. In a + * multi-thread CPU, it will be the level above the CPU, not the thread. + * It may not exist in single CPU systems. In simple multi-CPU systems, + * it may be equal to the package topology level. + * + * Return: -ENOENT if the PPTT doesn't exist, the CPU cannot be found + * or there is no toplogy level above the CPU.. + * Otherwise returns a value which represents the package for this CPU. + */ + +int find_acpi_cpu_topology_cluster(unsigned int cpu) +{ + struct acpi_table_header *table; + acpi_status status; + struct acpi_pptt_processor *cpu_node, *cluster_node; + u32 acpi_cpu_id; + int retval; + int is_thread; + + status = acpi_get_table(ACPI_SIG_PPTT, 0, &table); + if (ACPI_FAILURE(status)) { + acpi_pptt_warn_missing(); + return -ENOENT; + } + + acpi_cpu_id = get_acpi_id_for_cpu(cpu); + cpu_node = acpi_find_processor_node(table, acpi_cpu_id); + if (cpu_node == NULL || !cpu_node->parent) { + retval = -ENOENT; + goto put_table; + } + + is_thread = cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_IS_THREAD; + cluster_node = fetch_pptt_node(table, cpu_node->parent); + if (cluster_node == NULL) { + retval = -ENOENT; + goto put_table; + } + if (is_thread) { + if (!cluster_node->parent) { + retval = -ENOENT; + goto put_table; + } + cluster_node = fetch_pptt_node(table, cluster_node->parent); + if (cluster_node == NULL) { + retval = -ENOENT; + goto put_table; + } + } + if (cluster_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID) + retval = cluster_node->acpi_processor_id; + else + retval = ACPI_PTR_DIFF(cluster_node, table); + +put_table: + acpi_put_table(table); + + return retval; +} + /** * find_acpi_cpu_topology_hetero_id() - Get a core architecture tag * @cpu: Kernel logical CPU number diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 43407665918f..fc0836f460fb 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -600,6 +600,11 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return core_mask; } +const struct cpumask *cpu_clustergroup_mask(int cpu) +{ + return &cpu_topology[cpu].cluster_sibling; +} + void update_siblings_masks(unsigned int cpuid) { struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; @@ -617,6 +622,12 @@ void update_siblings_masks(unsigned int cpuid) if (cpuid_topo->package_id != cpu_topo->package_id) continue; + if (cpuid_topo->cluster_id == cpu_topo->cluster_id && + cpuid_topo->cluster_id != -1) { + cpumask_set_cpu(cpu, &cpuid_topo->cluster_sibling); + cpumask_set_cpu(cpuid, &cpu_topo->cluster_sibling); + } + cpumask_set_cpu(cpuid, &cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpuid_topo->core_sibling); @@ -635,6 +646,9 @@ static void clear_cpu_topology(int cpu) cpumask_clear(&cpu_topo->llc_sibling); cpumask_set_cpu(cpu, &cpu_topo->llc_sibling); + cpumask_clear(&cpu_topo->cluster_sibling); + cpumask_set_cpu(cpu, &cpu_topo->cluster_sibling); + cpumask_clear(&cpu_topo->core_sibling); cpumask_set_cpu(cpu, &cpu_topo->core_sibling); cpumask_clear(&cpu_topo->thread_sibling); @@ -650,6 +664,7 @@ void __init reset_cpu_topology(void) cpu_topo->thread_id = -1; cpu_topo->core_id = -1; + cpu_topo->cluster_id = -1; cpu_topo->package_id = -1; cpu_topo->llc_id = -1; diff --git a/drivers/base/topology.c b/drivers/base/topology.c index 43c0940643f5..8f2b641d0b8c 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -48,6 +48,9 @@ static DEVICE_ATTR_RO(physical_package_id); define_id_show_func(die_id); static DEVICE_ATTR_RO(die_id); +define_id_show_func(cluster_id); +static DEVICE_ATTR_RO(cluster_id); + define_id_show_func(core_id); static DEVICE_ATTR_RO(core_id); @@ -63,6 +66,10 @@ define_siblings_read_func(core_siblings, core_cpumask); static BIN_ATTR_RO(core_siblings, 0); static BIN_ATTR_RO(core_siblings_list, 0); +define_siblings_read_func(cluster_cpus, cluster_cpumask); +static BIN_ATTR_RO(cluster_cpus, 0); +static BIN_ATTR_RO(cluster_cpus_list, 0); + define_siblings_read_func(die_cpus, die_cpumask); static BIN_ATTR_RO(die_cpus, 0); static BIN_ATTR_RO(die_cpus_list, 0); @@ -94,6 +101,8 @@ static struct bin_attribute *bin_attrs[] = { &bin_attr_thread_siblings_list, &bin_attr_core_siblings, &bin_attr_core_siblings_list, + &bin_attr_cluster_cpus, + &bin_attr_cluster_cpus_list, &bin_attr_die_cpus, &bin_attr_die_cpus_list, &bin_attr_package_cpus, @@ -112,6 +121,7 @@ static struct bin_attribute *bin_attrs[] = { static struct attribute *default_attrs[] = { &dev_attr_physical_package_id.attr, &dev_attr_die_id.attr, + &dev_attr_cluster_id.attr, &dev_attr_core_id.attr, #ifdef CONFIG_SCHED_BOOK &dev_attr_book_id.attr, diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 974d497a897d..fbc2146050a4 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1353,6 +1353,7 @@ static inline int lpit_read_residency_count_address(u64 *address) #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); +int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); int find_acpi_cpu_cache_topology(unsigned int cpu, int level); @@ -1365,6 +1366,10 @@ static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } +static inline int find_acpi_cpu_topology_cluster(unsigned int cpu) +{ + return -EINVAL; +} static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index f180240dc95f..b97cea83b25e 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -62,10 +62,12 @@ void topology_set_thermal_pressure(const struct cpumask *cpus, struct cpu_topology { int thread_id; int core_id; + int cluster_id; int package_id; int llc_id; cpumask_t thread_sibling; cpumask_t core_sibling; + cpumask_t cluster_sibling; cpumask_t llc_sibling; }; @@ -73,13 +75,16 @@ struct cpu_topology { extern struct cpu_topology cpu_topology[NR_CPUS]; #define topology_physical_package_id(cpu) (cpu_topology[cpu].package_id) +#define topology_cluster_id(cpu) (cpu_topology[cpu].cluster_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) #define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_cluster_cpumask(cpu) (&cpu_topology[cpu].cluster_sibling) #define topology_llc_cpumask(cpu) (&cpu_topology[cpu].llc_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); const struct cpumask *cpu_coregroup_mask(int cpu); +const struct cpumask *cpu_clustergroup_mask(int cpu); void update_siblings_masks(unsigned int cpu); void remove_cpu_topology(unsigned int cpuid); void reset_cpu_topology(void); diff --git a/include/linux/topology.h b/include/linux/topology.h index 7634cd737061..80d27d717631 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -186,6 +186,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif +#ifndef topology_cluster_id +#define topology_cluster_id(cpu) ((void)(cpu), -1) +#endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif @@ -195,6 +198,9 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif +#ifndef topology_cluster_cpumask +#define topology_cluster_cpumask(cpu) cpumask_of(cpu) +#endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif -- cgit v1.2.3 From 778c558f49a2cb3dc7b18a80ff515e82aa813627 Mon Sep 17 00:00:00 2001 From: Barry Song Date: Fri, 24 Sep 2021 20:51:03 +1200 Subject: sched: Add cluster scheduler level in core and related Kconfig for ARM64 This patch adds scheduler level for clusters and automatically enables the load balance among clusters. It will directly benefit a lot of workload which loves more resources such as memory bandwidth, caches. Testing has widely been done in two different hardware configurations of Kunpeng920: 24 cores in one NUMA(6 clusters in each NUMA node); 32 cores in one NUMA(8 clusters in each NUMA node) Workload is running on either one NUMA node or four NUMA nodes, thus, this can estimate the effect of cluster spreading w/ and w/o NUMA load balance. * Stream benchmark: 4threads stream (on 1NUMA * 24cores = 24cores) stream stream w/o patch w/ patch MB/sec copy 29929.64 ( 0.00%) 32932.68 ( 10.03%) MB/sec scale 29861.10 ( 0.00%) 32710.58 ( 9.54%) MB/sec add 27034.42 ( 0.00%) 32400.68 ( 19.85%) MB/sec triad 27225.26 ( 0.00%) 31965.36 ( 17.41%) 6threads stream (on 1NUMA * 24cores = 24cores) stream stream w/o patch w/ patch MB/sec copy 40330.24 ( 0.00%) 42377.68 ( 5.08%) MB/sec scale 40196.42 ( 0.00%) 42197.90 ( 4.98%) MB/sec add 37427.00 ( 0.00%) 41960.78 ( 12.11%) MB/sec triad 37841.36 ( 0.00%) 42513.64 ( 12.35%) 12threads stream (on 1NUMA * 24cores = 24cores) stream stream w/o patch w/ patch MB/sec copy 52639.82 ( 0.00%) 53818.04 ( 2.24%) MB/sec scale 52350.30 ( 0.00%) 53253.38 ( 1.73%) MB/sec add 53607.68 ( 0.00%) 55198.82 ( 2.97%) MB/sec triad 54776.66 ( 0.00%) 56360.40 ( 2.89%) Thus, it could help memory-bound workload especially under medium load. Similar improvement is also seen in lkp-pbzip2: * lkp-pbzip2 benchmark 2-96 threads (on 4NUMA * 24cores = 96cores) lkp-pbzip2 lkp-pbzip2 w/o patch w/ patch Hmean tput-2 11062841.57 ( 0.00%) 11341817.51 * 2.52%* Hmean tput-5 26815503.70 ( 0.00%) 27412872.65 * 2.23%* Hmean tput-8 41873782.21 ( 0.00%) 43326212.92 * 3.47%* Hmean tput-12 61875980.48 ( 0.00%) 64578337.51 * 4.37%* Hmean tput-21 105814963.07 ( 0.00%) 111381851.01 * 5.26%* Hmean tput-30 150349470.98 ( 0.00%) 156507070.73 * 4.10%* Hmean tput-48 237195937.69 ( 0.00%) 242353597.17 * 2.17%* Hmean tput-79 360252509.37 ( 0.00%) 362635169.23 * 0.66%* Hmean tput-96 394571737.90 ( 0.00%) 400952978.48 * 1.62%* 2-24 threads (on 1NUMA * 24cores = 24cores) lkp-pbzip2 lkp-pbzip2 w/o patch w/ patch Hmean tput-2 11071705.49 ( 0.00%) 11296869.10 * 2.03%* Hmean tput-4 20782165.19 ( 0.00%) 21949232.15 * 5.62%* Hmean tput-6 30489565.14 ( 0.00%) 33023026.96 * 8.31%* Hmean tput-8 40376495.80 ( 0.00%) 42779286.27 * 5.95%* Hmean tput-12 61264033.85 ( 0.00%) 62995632.78 * 2.83%* Hmean tput-18 86697139.39 ( 0.00%) 86461545.74 ( -0.27%) Hmean tput-24 104854637.04 ( 0.00%) 104522649.46 * -0.32%* In the case of 6 threads and 8 threads, we see the greatest performance improvement. Similar improvement can be seen on lkp-pixz though the improvement is smaller: * lkp-pixz benchmark 2-24 threads lkp-pixz (on 1NUMA * 24cores = 24cores) lkp-pixz lkp-pixz w/o patch w/ patch Hmean tput-2 6486981.16 ( 0.00%) 6561515.98 * 1.15%* Hmean tput-4 11645766.38 ( 0.00%) 11614628.43 ( -0.27%) Hmean tput-6 15429943.96 ( 0.00%) 15957350.76 * 3.42%* Hmean tput-8 19974087.63 ( 0.00%) 20413746.98 * 2.20%* Hmean tput-12 28172068.18 ( 0.00%) 28751997.06 * 2.06%* Hmean tput-18 39413409.54 ( 0.00%) 39896830.55 * 1.23%* Hmean tput-24 49101815.85 ( 0.00%) 49418141.47 * 0.64%* * SPECrate benchmark 4,8,16 copies mcf_r(on 1NUMA * 32cores = 32cores) Base Base Run Time Rate ------- --------- 4 Copies w/o 580 (w/ 570) w/o 11.1 (w/ 11.3) 8 Copies w/o 647 (w/ 605) w/o 20.0 (w/ 21.4, +7%) 16 Copies w/o 844 (w/ 844) w/o 30.6 (w/ 30.6) 32 Copies(on 4NUMA * 32 cores = 128cores) [w/o patch] Base Base Base Benchmarks Copies Run Time Rate --------------- ------- --------- --------- 500.perlbench_r 32 584 87.2 * 502.gcc_r 32 503 90.2 * 505.mcf_r 32 745 69.4 * 520.omnetpp_r 32 1031 40.7 * 523.xalancbmk_r 32 597 56.6 * 525.x264_r 1 -- CE 531.deepsjeng_r 32 336 109 * 541.leela_r 32 556 95.4 * 548.exchange2_r 32 513 163 * 557.xz_r 32 530 65.2 * Est. SPECrate2017_int_base 80.3 [w/ patch] Base Base Base Benchmarks Copies Run Time Rate --------------- ------- --------- --------- 500.perlbench_r 32 580 87.8 (+0.688%) * 502.gcc_r 32 477 95.1 (+5.432%) * 505.mcf_r 32 644 80.3 (+13.574%) * 520.omnetpp_r 32 942 44.6 (+9.58%) * 523.xalancbmk_r 32 560 60.4 (+6.714%%) * 525.x264_r 1 -- CE 531.deepsjeng_r 32 337 109 (+0.000%) * 541.leela_r 32 554 95.6 (+0.210%) * 548.exchange2_r 32 515 163 (+0.000%) * 557.xz_r 32 524 66.0 (+1.227%) * Est. SPECrate2017_int_base 83.7 (+4.062%) On the other hand, it is slightly helpful to CPU-bound tasks like kernbench: * 24-96 threads kernbench (on 4NUMA * 24cores = 96cores) kernbench kernbench w/o cluster w/ cluster Min user-24 12054.67 ( 0.00%) 12024.19 ( 0.25%) Min syst-24 1751.51 ( 0.00%) 1731.68 ( 1.13%) Min elsp-24 600.46 ( 0.00%) 598.64 ( 0.30%) Min user-48 12361.93 ( 0.00%) 12315.32 ( 0.38%) Min syst-48 1917.66 ( 0.00%) 1892.73 ( 1.30%) Min elsp-48 333.96 ( 0.00%) 332.57 ( 0.42%) Min user-96 12922.40 ( 0.00%) 12921.17 ( 0.01%) Min syst-96 2143.94 ( 0.00%) 2110.39 ( 1.56%) Min elsp-96 211.22 ( 0.00%) 210.47 ( 0.36%) Amean user-24 12063.99 ( 0.00%) 12030.78 * 0.28%* Amean syst-24 1755.20 ( 0.00%) 1735.53 * 1.12%* Amean elsp-24 601.60 ( 0.00%) 600.19 ( 0.23%) Amean user-48 12362.62 ( 0.00%) 12315.56 * 0.38%* Amean syst-48 1921.59 ( 0.00%) 1894.95 * 1.39%* Amean elsp-48 334.10 ( 0.00%) 332.82 * 0.38%* Amean user-96 12925.27 ( 0.00%) 12922.63 ( 0.02%) Amean syst-96 2146.66 ( 0.00%) 2122.20 * 1.14%* Amean elsp-96 211.96 ( 0.00%) 211.79 ( 0.08%) Note this patch isn't an universal win, it might hurt those workload which can benefit from packing. Though tasks which want to take advantages of lower communication latency of one cluster won't necessarily been packed in one cluster while kernel is not aware of clusters, they have some chance to be randomly packed. But this patch will make them more likely spread. Signed-off-by: Barry Song Tested-by: Yicong Yang Signed-off-by: Peter Zijlstra (Intel) --- arch/arm64/Kconfig | 9 +++++++++ include/linux/sched/topology.h | 7 +++++++ include/linux/topology.h | 7 +++++++ kernel/sched/topology.c | 5 +++++ 4 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5c7ae4c3954b..d13677f4731d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -989,6 +989,15 @@ config SCHED_MC making when dealing with multi-core CPU chips at a cost of slightly increased overhead in some places. If unsure say N here. +config SCHED_CLUSTER + bool "Cluster scheduler support" + help + Cluster scheduler support improves the CPU scheduler's decision + making when dealing with machines that have clusters of CPUs. + Cluster usually means a couple of CPUs which are placed closely + by sharing mid-level caches, last-level cache tags or internal + busses. + config SCHED_SMT bool "SMT scheduler support" help diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 8f0f778b7c91..2f9166f6dec8 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -42,6 +42,13 @@ static inline int cpu_smt_flags(void) } #endif +#ifdef CONFIG_SCHED_CLUSTER +static inline int cpu_cluster_flags(void) +{ + return SD_SHARE_PKG_RESOURCES; +} +#endif + #ifdef CONFIG_SCHED_MC static inline int cpu_core_flags(void) { diff --git a/include/linux/topology.h b/include/linux/topology.h index 80d27d717631..0b3704ad13c8 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -212,6 +212,13 @@ static inline const struct cpumask *cpu_smt_mask(int cpu) } #endif +#if defined(CONFIG_SCHED_CLUSTER) && !defined(cpu_cluster_mask) +static inline const struct cpumask *cpu_cluster_mask(int cpu) +{ + return topology_cluster_cpumask(cpu); +} +#endif + static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 5af3edd34d6d..c1729f9a715f 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1638,6 +1638,11 @@ static struct sched_domain_topology_level default_topology[] = { #ifdef CONFIG_SCHED_SMT { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, #endif + +#ifdef CONFIG_SCHED_CLUSTER + { cpu_clustergroup_mask, cpu_cluster_flags, SD_INIT_NAME(CLS) }, +#endif + #ifdef CONFIG_SCHED_MC { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, #endif -- cgit v1.2.3 From 810979682ccc98dbd83f341c18a2e556c30a7164 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 6 Oct 2021 13:18:50 +0200 Subject: irq_work: Allow irq_work_sync() to sleep if irq_work() no IRQ support. irq_work() triggers instantly an interrupt if supported by the architecture. Otherwise the work will be processed on the next timer tick. In worst case irq_work_sync() could spin up to a jiffy. irq_work_sync() is usually used in tear down context which is fully preemptible. Based on review irq_work_sync() is invoked from preemptible context and there is one waiter at a time. This qualifies it to use rcuwait for synchronisation. Let irq_work_sync() synchronize with rcuwait if the architecture processes irqwork via the timer tick. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211006111852.1514359-3-bigeasy@linutronix.de --- include/linux/irq_work.h | 3 +++ kernel/irq_work.c | 10 ++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index ec2a47a81e42..b48955e9c920 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -3,6 +3,7 @@ #define _LINUX_IRQ_WORK_H #include +#include /* * An entry can be in one of four states: @@ -16,11 +17,13 @@ struct irq_work { struct __call_single_node node; void (*func)(struct irq_work *); + struct rcuwait irqwait; }; #define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){ \ .node = { .u_flags = (_flags), }, \ .func = (_func), \ + .irqwait = __RCUWAIT_INITIALIZER(irqwait), \ } #define IRQ_WORK_INIT(_func) __IRQ_WORK_INIT(_func, 0) diff --git a/kernel/irq_work.c b/kernel/irq_work.c index db8c248ebc8c..e789beda8297 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -160,6 +160,9 @@ void irq_work_single(void *arg) * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); + + if (!arch_irq_work_has_interrupt()) + rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) @@ -204,6 +207,13 @@ void irq_work_tick(void) void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); + might_sleep(); + + if (!arch_irq_work_has_interrupt()) { + rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), + TASK_UNINTERRUPTIBLE); + return; + } while (irq_work_is_busy(work)) cpu_relax(); -- cgit v1.2.3 From 09089db79859cbccccd8df95b034f36f7027efa6 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 6 Oct 2021 13:18:52 +0200 Subject: irq_work: Also rcuwait for !IRQ_WORK_HARD_IRQ on PREEMPT_RT On PREEMPT_RT most items are processed as LAZY via softirq context. Avoid to spin-wait for them because irq_work_sync() could have higher priority and not allow the irq-work to be completed. Wait additionally for !IRQ_WORK_HARD_IRQ irq_work items on PREEMPT_RT. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211006111852.1514359-5-bigeasy@linutronix.de --- include/linux/irq_work.h | 5 +++++ kernel/irq_work.c | 6 ++++-- 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index b48955e9c920..8cd11a223260 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -49,6 +49,11 @@ static inline bool irq_work_is_busy(struct irq_work *work) return atomic_read(&work->node.a_flags) & IRQ_WORK_BUSY; } +static inline bool irq_work_is_hard(struct irq_work *work) +{ + return atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ; +} + bool irq_work_queue(struct irq_work *work); bool irq_work_queue_on(struct irq_work *work, int cpu); diff --git a/kernel/irq_work.c b/kernel/irq_work.c index 90b6b56f92e9..f7df715ec28e 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -217,7 +217,8 @@ void irq_work_single(void *arg) */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); - if (!arch_irq_work_has_interrupt()) + if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || + !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } @@ -277,7 +278,8 @@ void irq_work_sync(struct irq_work *work) lockdep_assert_irqs_enabled(); might_sleep(); - if (!arch_irq_work_has_interrupt()) { + if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || + !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; -- cgit v1.2.3 From 8b8ff8cc3b8155c18162e8b1f70e1230db176862 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 7 Sep 2021 19:39:01 +0300 Subject: perf/x86: Add new event for AUX output counter index PEBS-via-PT records contain a mask of applicable counters. To identify which event belongs to which counter, a side-band event is needed. Until now, there has been no side-band event, and consequently users were limited to using a single event. Add such a side-band event. Note the event is optimised to output only when the counter index changes for an event. That works only so long as all PEBS-via-PT events are scheduled together, which they are for a recording session because they are in a single group. Also no attribute bit is used to select the new event, so a new kernel is not compatible with older perf tools. The assumption being that PEBS-via-PT is sufficiently esoteric that users will not be troubled by this. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210907163903.11820-2-adrian.hunter@intel.com --- arch/x86/events/core.c | 6 ++++++ arch/x86/events/intel/core.c | 16 ++++++++++++++++ arch/x86/events/perf_event.h | 1 + include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 15 +++++++++++++++ kernel/events/core.c | 30 ++++++++++++++++++++++++++++++ 6 files changed, 69 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..be33423e9762 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); +DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); + DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); @@ -1215,6 +1217,8 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; + static_call_cond(x86_pmu_assign)(event, idx); + switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: @@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable); + static_call_update(x86_pmu_assign, x86_pmu.assign); + static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..a555e7c2dce9 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2402,6 +2402,12 @@ static void intel_pmu_disable_event(struct perf_event *event) intel_pmu_pebs_disable(event); } +static void intel_pmu_assign_event(struct perf_event *event, int idx) +{ + if (is_pebs_pt(event)) + perf_report_aux_output_id(event, idx); +} + static void intel_pmu_del_event(struct perf_event *event) { if (needs_branch_stack(event)) @@ -4494,8 +4500,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value) return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; } +static void intel_aux_output_init(void) +{ + /* Refer also intel_pmu_aux_output_match() */ + if (x86_pmu.intel_cap.pebs_output_pt_available) + x86_pmu.assign = intel_pmu_assign_event; +} + static int intel_pmu_aux_output_match(struct perf_event *event) { + /* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */ if (!x86_pmu.intel_cap.pebs_output_pt_available) return 0; @@ -6301,6 +6315,8 @@ __init int intel_pmu_init(void) if (is_hybrid()) intel_pmu_check_hybrid_pmus((u64)fixed_mask); + intel_aux_output_init(); + return 0; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e3ac05c97b5e..76436a55d9ba 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -726,6 +726,7 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*assign)(struct perf_event *event, int idx); void (*add)(struct perf_event *); void (*del)(struct perf_event *); void (*read)(struct perf_event *event); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2d510ad750ed..126b3a314f3a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1397,6 +1397,7 @@ perf_event_addr_filters(struct perf_event *event) } extern void perf_event_addr_filters_sync(struct perf_event *event); +extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index f92880a15645..c89535de1ec8 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1141,6 +1141,21 @@ enum perf_event_type { */ PERF_RECORD_TEXT_POKE = 20, + /* + * Data written to the AUX area by hardware due to aux_output, may need + * to be matched to the event by an architecture-specific hardware ID. + * This records the hardware ID, but requires sample_id to provide the + * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT + * records from multiple events. + * + * struct { + * struct perf_event_header header; + * u64 hw_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 1cb1f9b8392e..0e90a5084f18 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9062,6 +9062,36 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } +void perf_report_aux_output_id(struct perf_event *event, u64 hw_id) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 hw_id; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + rec.header.type = PERF_RECORD_AUX_OUTPUT_HW_ID; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.hw_id = hw_id; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + static int __perf_event_account_interrupt(struct perf_event *event, int throttle) { -- cgit v1.2.3 From d00e60ee54b12de945b8493cf18c1ada9e422514 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 13 Oct 2021 17:19:20 +0800 Subject: page_pool: disable dma mapping support for 32-bit arch with 64-bit DMA As the 32-bit arch with 64-bit DMA seems to rare those days, and page pool might carry a lot of code and complexity for systems that possibly. So disable dma mapping support for such systems, if drivers really want to work on such systems, they have to implement their own DMA-mapping fallback tracking outside page_pool. Reviewed-by: Ilias Apalodimas Signed-off-by: Yunsheng Lin Acked-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- include/linux/mm_types.h | 13 +------------ include/net/page_pool.h | 12 +----------- net/core/page_pool.c | 10 ++++++---- 3 files changed, 8 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..436e0946d691 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -104,18 +104,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - union { - /** - * dma_addr_upper: might require a 64-bit - * value on 32-bit architectures. - */ - unsigned long dma_addr_upper; - /** - * For frag page support, not supported in - * 32-bit architectures with 64-bit DMA. - */ - atomic_long_t pp_frag_count; - }; + atomic_long_t pp_frag_count; }; struct { /* slab, slob and slub */ union { diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..3855f069627f 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,24 +216,14 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } -#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ - (sizeof(dma_addr_t) > sizeof(unsigned long)) - static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr; - - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; - - return ret; + return page->dma_addr; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) - page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 1a6978427d6c..9b60e4301a44 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,6 +49,12 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { + /* DMA-mapping is not supported on 32-bit systems with + * 64-bit DMA mapping. + */ + if (sizeof(dma_addr_t) > sizeof(unsigned long)) + return -EOPNOTSUPP; + if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -69,10 +75,6 @@ static int page_pool_init(struct page_pool *pool, */ } - if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && - pool->p.flags & PP_FLAG_PAGE_FRAG) - return -EINVAL; - if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; -- cgit v1.2.3 From 9028b2463c1ea96f51c3ba53e2479346019ff6ad Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Thu, 25 Mar 2021 15:08:44 +0100 Subject: tee: add sec_world_id to struct tee_shm Adds sec_world_id to struct tee_shm which describes a shared memory object. sec_world_id can be used by a driver to store an id assigned by secure world. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- include/linux/tee_drv.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index 3ebfea0781f1..a1f03461369b 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -197,7 +197,11 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @num_pages: number of locked pages * @dmabuf: dmabuf used to for exporting to user space * @flags: defined by TEE_SHM_* in tee_drv.h - * @id: unique id of a shared memory object on this device + * @id: unique id of a shared memory object on this device, shared + * with user space + * @sec_world_id: + * secure world assigned id of this shared memory object, not + * used by all drivers * * This pool is only supposed to be accessed directly from the TEE * subsystem and from drivers that implements their own shm pool manager. @@ -213,6 +217,7 @@ struct tee_shm { struct dma_buf *dmabuf; u32 flags; int id; + u64 sec_world_id; }; /** -- cgit v1.2.3 From 9955548919c47a6987b40d90a30fd56bbc043e7b Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Fri, 1 Oct 2021 12:12:30 +0200 Subject: remoteproc: Remove vdev_to_rvdev and vdev_to_rproc from remoteproc API These both functions are only used by the remoteproc_virtio. There is no reason to expose them in the API. Move the functions in remoteproc_virtio.c Signed-off-by: Arnaud Pouliquen Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20211001101234.4247-4-arnaud.pouliquen@foss.st.com --- drivers/remoteproc/remoteproc_virtio.c | 12 ++++++++++++ include/linux/remoteproc.h | 12 ------------ 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/remoteproc/remoteproc_virtio.c b/drivers/remoteproc/remoteproc_virtio.c index cf4d54e98e6a..70ab496d0431 100644 --- a/drivers/remoteproc/remoteproc_virtio.c +++ b/drivers/remoteproc/remoteproc_virtio.c @@ -23,6 +23,18 @@ #include "remoteproc_internal.h" +static struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) +{ + return container_of(vdev->dev.parent, struct rproc_vdev, dev); +} + +static struct rproc *vdev_to_rproc(struct virtio_device *vdev) +{ + struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); + + return rvdev->rproc; +} + /* kick the remote processor, and let it know which virtqueue to poke at */ static bool rproc_virtio_notify(struct virtqueue *vq) { diff --git a/include/linux/remoteproc.h b/include/linux/remoteproc.h index 83c09ac36b13..e0600e1e5c17 100644 --- a/include/linux/remoteproc.h +++ b/include/linux/remoteproc.h @@ -684,18 +684,6 @@ int rproc_coredump_add_custom_segment(struct rproc *rproc, void *priv); int rproc_coredump_set_elf_info(struct rproc *rproc, u8 class, u16 machine); -static inline struct rproc_vdev *vdev_to_rvdev(struct virtio_device *vdev) -{ - return container_of(vdev->dev.parent, struct rproc_vdev, dev); -} - -static inline struct rproc *vdev_to_rproc(struct virtio_device *vdev) -{ - struct rproc_vdev *rvdev = vdev_to_rvdev(vdev); - - return rvdev->rproc; -} - void rproc_add_subdev(struct rproc *rproc, struct rproc_subdev *subdev); void rproc_remove_subdev(struct rproc *rproc, struct rproc_subdev *subdev); -- cgit v1.2.3 From 789c1093f02c436b320d78a739f9610c8271cb73 Mon Sep 17 00:00:00 2001 From: Yang Yingliang Date: Mon, 11 Oct 2021 21:21:14 +0800 Subject: rtc: class: don't call cdev_device_del() when cdev_device_add() failed I got a null-ptr-deref report when doing fault injection test: general protection fault, probably for non-canonical address 0xdffffc0000000022: 0000 [#1] SMP KASAN PTI KASAN: null-ptr-deref in range [0x0000000000000110-0x0000000000000117] RIP: 0010:device_del+0x132/0xdc0 Call Trace: cdev_device_del+0x1a/0x80 devm_rtc_unregister_device+0x37/0x80 release_nodes+0xc3/0x3b0 If cdev_device_add() fails, 'dev->p' is not set, it causes null-ptr-deref when calling cdev_device_del(). Registering character device is optional, we don't return error code here, so introduce a new flag 'RTC_NO_CDEV' to indicate if it has character device, cdev_device_del() is called when this bit is not set. Reported-by: Hulk Robot Signed-off-by: Yang Yingliang Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211011132114.3663509-1-yangyingliang@huawei.com --- drivers/rtc/class.c | 9 ++++++--- include/linux/rtc.h | 1 + 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index f77bc089eb6b..654e921244bf 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -334,7 +334,8 @@ static void devm_rtc_unregister_device(void *data) * letting any rtc_class_open() users access it again */ rtc_proc_del_device(rtc); - cdev_device_del(&rtc->char_dev, &rtc->dev); + if (!test_bit(RTC_NO_CDEV, &rtc->flags)) + cdev_device_del(&rtc->char_dev, &rtc->dev); rtc->ops = NULL; mutex_unlock(&rtc->ops_lock); } @@ -397,12 +398,14 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) rtc_dev_prepare(rtc); err = cdev_device_add(&rtc->char_dev, &rtc->dev); - if (err) + if (err) { + set_bit(RTC_NO_CDEV, &rtc->flags); dev_warn(rtc->dev.parent, "failed to add char device %d:%d\n", MAJOR(rtc->dev.devt), rtc->id); - else + } else { dev_dbg(rtc->dev.parent, "char device (%d:%d)\n", MAJOR(rtc->dev.devt), rtc->id); + } rtc_proc_add_device(rtc); diff --git a/include/linux/rtc.h b/include/linux/rtc.h index bd611e26291d..354e0843ab17 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -80,6 +80,7 @@ struct rtc_timer { /* flags */ #define RTC_DEV_BUSY 0 +#define RTC_NO_CDEV 1 struct rtc_device { struct device dev; -- cgit v1.2.3 From 4b2c5fa9c9902ce34ecea6711558d9af96351b31 Mon Sep 17 00:00:00 2001 From: Amir Tzin Date: Wed, 21 Jul 2021 16:14:12 +0300 Subject: net/mlx5: Add layout to support default timeouts register Add needed structures and defines for DTOR (default timeouts register). This will be used to get timeouts values from FW instead of hard coded values in the driver code thus enabling support for slower devices which need longer timeouts. Signed-off-by: Amir Tzin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/device.h | 4 +++- include/linux/mlx5/driver.h | 1 + include/linux/mlx5/mlx5_ifc.h | 37 ++++++++++++++++++++++++++++++++++++- 3 files changed, 40 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 66eaf0aa7f69..109cc8106d16 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -577,7 +577,9 @@ struct mlx5_init_seg { __be32 rsvd1[120]; __be32 initializing; struct health_buffer health; - __be32 rsvd2[880]; + __be32 rsvd2[878]; + __be32 cmd_exec_to; + __be32 cmd_q_init_to; __be32 internal_timer_h; __be32 internal_timer_l; __be32 rsvd3[2]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 0ca719c00824..ccbd87fbd3bf 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -156,6 +156,7 @@ enum { MLX5_REG_MIRC = 0x9162, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, + MLX5_REG_DTOR = 0xC00E, }; enum mlx5_qpts_trust_state { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 993204a6c1a1..b8bff5109656 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1306,7 +1306,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_resource_manager[0x1]; u8 hca_cap_2[0x1]; - u8 reserved_at_21[0x2]; + u8 reserved_at_21[0x1]; + u8 dtor[0x1]; u8 event_on_vhca_state_teardown_request[0x1]; u8 event_on_vhca_state_in_use[0x1]; u8 event_on_vhca_state_active[0x1]; @@ -2807,6 +2808,40 @@ struct mlx5_ifc_dropped_packet_logged_bits { u8 reserved_at_0[0xe0]; }; +struct mlx5_ifc_default_timeout_bits { + u8 to_multiplier[0x3]; + u8 reserved_at_3[0x9]; + u8 to_value[0x14]; +}; + +struct mlx5_ifc_dtor_reg_bits { + u8 reserved_at_0[0x20]; + + struct mlx5_ifc_default_timeout_bits pcie_toggle_to; + + u8 reserved_at_40[0x60]; + + struct mlx5_ifc_default_timeout_bits health_poll_to; + + struct mlx5_ifc_default_timeout_bits full_crdump_to; + + struct mlx5_ifc_default_timeout_bits fw_reset_to; + + struct mlx5_ifc_default_timeout_bits flush_on_err_to; + + struct mlx5_ifc_default_timeout_bits pci_sync_update_to; + + struct mlx5_ifc_default_timeout_bits tear_down_to; + + struct mlx5_ifc_default_timeout_bits fsm_reactivate_to; + + struct mlx5_ifc_default_timeout_bits reclaim_pages_to; + + struct mlx5_ifc_default_timeout_bits reclaim_vfs_pages_to; + + u8 reserved_at_1c0[0x40]; +}; + enum { MLX5_CQ_ERROR_SYNDROME_CQ_OVERRUN = 0x1, MLX5_CQ_ERROR_SYNDROME_CQ_ACCESS_VIOLATION_ERROR = 0x2, -- cgit v1.2.3 From 5945e1adeab527ec96c75a786213c146d4d482a4 Mon Sep 17 00:00:00 2001 From: Amir Tzin Date: Thu, 7 Oct 2021 18:00:27 +0300 Subject: net/mlx5: Read timeout values from init segment Replace hard coded timeouts with values stored in firmware's init segment. Timeouts are read from init segment during driver load. If init segment timeouts are not supported then fallback to hard coded defaults instead. Also move pre initialization timeouts which cannot be read from firmware to the new mechanism. Signed-off-by: Amir Tzin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 18 ++-- drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c | 96 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h | 28 +++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 38 +++++---- include/linux/mlx5/driver.h | 5 +- 6 files changed, 161 insertions(+), 26 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 63032cd6efb1..a151575be51f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -17,7 +17,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ fs_counters.o fs_ft_pool.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ - fw_reset.o qos.o + fw_reset.o qos.o lib/tout.o # # Netdev basic diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 4dc3a822907a..f71ec4d9d68e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -45,6 +45,7 @@ #include "mlx5_core.h" #include "lib/eq.h" +#include "lib/tout.h" enum { CMD_IF_REV = 5, @@ -225,9 +226,13 @@ static void set_signature(struct mlx5_cmd_work_ent *ent, int csum) static void poll_timeout(struct mlx5_cmd_work_ent *ent) { - unsigned long poll_end = jiffies + msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC + 1000); + struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + u64 cmd_to_ms = mlx5_tout_ms(dev, CMD); + unsigned long poll_end; u8 own; + poll_end = jiffies + msecs_to_jiffies(cmd_to_ms + 1000); + do { own = READ_ONCE(ent->lay->status_own); if (!(own & CMD_OWNER_HW)) { @@ -925,15 +930,18 @@ static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); struct mlx5_cmd *cmd = ent->cmd; - struct mlx5_core_dev *dev = container_of(cmd, struct mlx5_core_dev, cmd); - unsigned long cb_timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + bool poll_cmd = ent->polling; struct mlx5_cmd_layout *lay; + struct mlx5_core_dev *dev; + unsigned long cb_timeout; struct semaphore *sem; unsigned long flags; - bool poll_cmd = ent->polling; int alloc_ret; int cmd_mode; + dev = container_of(cmd, struct mlx5_core_dev, cmd); + cb_timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); + complete(&ent->handling); sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); @@ -1073,7 +1081,7 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { - unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); + unsigned long timeout = msecs_to_jiffies(mlx5_tout_ms(dev, CMD)); struct mlx5_cmd *cmd = &dev->cmd; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c new file mode 100644 index 000000000000..ee266e0d122a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include +#include "lib/tout.h" + +struct mlx5_timeouts { + u64 to[MAX_TIMEOUT_TYPES]; +}; + +static const u32 tout_def_sw_val[MAX_TIMEOUT_TYPES] = { + [MLX5_TO_FW_PRE_INIT_TIMEOUT_MS] = 120000, + [MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS] = 20000, + [MLX5_TO_FW_PRE_INIT_WAIT_MS] = 2, + [MLX5_TO_FW_INIT_MS] = 2000, + [MLX5_TO_CMD_MS] = 60000 +}; + +static void tout_set(struct mlx5_core_dev *dev, u64 val, enum mlx5_timeouts_types type) +{ + dev->timeouts->to[type] = val; +} + +static void tout_set_def_val(struct mlx5_core_dev *dev) +{ + int i; + + for (i = MLX5_TO_FW_PRE_INIT_TIMEOUT_MS; i < MAX_TIMEOUT_TYPES; i++) + tout_set(dev, tout_def_sw_val[i], i); +} + +int mlx5_tout_init(struct mlx5_core_dev *dev) +{ + dev->timeouts = kmalloc(sizeof(*dev->timeouts), GFP_KERNEL); + if (!dev->timeouts) + return -ENOMEM; + + tout_set_def_val(dev); + return 0; +} + +void mlx5_tout_cleanup(struct mlx5_core_dev *dev) +{ + kfree(dev->timeouts); +} + +/* Time register consists of two fields to_multiplier(time out multiplier) + * and to_value(time out value). to_value is the quantity of the time units and + * to_multiplier is the type and should be one off these four values. + * 0x0: millisecond + * 0x1: seconds + * 0x2: minutes + * 0x3: hours + * this function converts the time stored in the two register fields into + * millisecond. + */ +static u64 tout_convert_reg_field_to_ms(u32 to_mul, u32 to_val) +{ + u64 msec = to_val; + + to_mul &= 0x3; + /* convert hours/minutes/seconds to miliseconds */ + if (to_mul) + msec *= 1000 * int_pow(60, to_mul - 1); + + return msec; +} + +static u64 tout_convert_iseg_to_ms(u32 iseg_to) +{ + return tout_convert_reg_field_to_ms(iseg_to >> 29, iseg_to & 0xfffff); +} + +static bool tout_is_supported(struct mlx5_core_dev *dev) +{ + return !!ioread32be(&dev->iseg->cmd_q_init_to); +} + +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev) +{ + u32 to; + + if (!tout_is_supported(dev)) + return; + + to = ioread32be(&dev->iseg->cmd_q_init_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_FW_INIT_MS); + + to = ioread32be(&dev->iseg->cmd_exec_to); + tout_set(dev, tout_convert_iseg_to_ms(to), MLX5_TO_CMD_MS); +} + +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type) +{ + return dev->timeouts->to[type]; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h new file mode 100644 index 000000000000..7e6fc61c5b45 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/tout.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef MLX5_TIMEOUTS_H +#define MLX5_TIMEOUTS_H + +enum mlx5_timeouts_types { + /* pre init timeouts (not read from FW) */ + MLX5_TO_FW_PRE_INIT_TIMEOUT_MS, + MLX5_TO_FW_PRE_INIT_WARN_MESSAGE_INTERVAL_MS, + MLX5_TO_FW_PRE_INIT_WAIT_MS, + + /* init segment timeouts */ + MLX5_TO_FW_INIT_MS, + MLX5_TO_CMD_MS, + + MAX_TIMEOUT_TYPES +}; + +struct mlx5_core_dev; +int mlx5_tout_init(struct mlx5_core_dev *dev); +void mlx5_tout_cleanup(struct mlx5_core_dev *dev); +void mlx5_tout_query_iseg(struct mlx5_core_dev *dev); +u64 _mlx5_tout_ms(struct mlx5_core_dev *dev, enum mlx5_timeouts_types type); + +#define mlx5_tout_ms(dev, type) _mlx5_tout_ms(dev, MLX5_TO_##type##_MS) + +# endif /* MLX5_TIMEOUTS_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 65313448a47c..b4893eac6ed6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -60,6 +60,7 @@ #include "devlink.h" #include "fw_reset.h" #include "lib/mlx5.h" +#include "lib/tout.h" #include "fpga/core.h" #include "fpga/ipsec.h" #include "accel/ipsec.h" @@ -176,11 +177,6 @@ static struct mlx5_profile profile[] = { }, }; -#define FW_INIT_TIMEOUT_MILI 2000 -#define FW_INIT_WAIT_MS 2 -#define FW_PRE_INIT_TIMEOUT_MILI 120000 -#define FW_INIT_WARN_MESSAGE_INTERVAL 20000 - static int fw_initializing(struct mlx5_core_dev *dev) { return ioread32be(&dev->iseg->initializing) >> 31; @@ -193,8 +189,6 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili); int err = 0; - BUILD_BUG_ON(FW_PRE_INIT_TIMEOUT_MILI < FW_INIT_WARN_MESSAGE_INTERVAL); - while (fw_initializing(dev)) { if (time_after(jiffies, end)) { err = -EBUSY; @@ -205,7 +199,7 @@ static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili, jiffies_to_msecs(end - warn) / 1000); warn = jiffies + msecs_to_jiffies(warn_time_mili); } - msleep(FW_INIT_WAIT_MS); + msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT)); } return err; @@ -975,25 +969,34 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (mlx5_core_is_pf(dev)) pcie_print_link_status(dev->pdev); + err = mlx5_tout_init(dev); + if (err) { + mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); + return err; + } + /* wait for firmware to accept initialization segments configurations */ - err = wait_fw_init(dev, FW_PRE_INIT_TIMEOUT_MILI, FW_INIT_WARN_MESSAGE_INTERVAL); + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT), + mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL)); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in pre-initializing state, aborting\n", - FW_PRE_INIT_TIMEOUT_MILI); - return err; + mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", + mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); + goto err_tout_cleanup; } err = mlx5_cmd_init(dev); if (err) { mlx5_core_err(dev, "Failed initializing command interface, aborting\n"); - return err; + goto err_tout_cleanup; } - err = wait_fw_init(dev, FW_INIT_TIMEOUT_MILI, 0); + mlx5_tout_query_iseg(dev); + + err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0); if (err) { - mlx5_core_err(dev, "Firmware over %d MS in initializing state, aborting\n", - FW_INIT_TIMEOUT_MILI); + mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n", + mlx5_tout_ms(dev, FW_INIT)); goto err_cmd_cleanup; } @@ -1062,6 +1065,8 @@ err_disable_hca: err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); +err_tout_cleanup: + mlx5_tout_cleanup(dev); return err; } @@ -1080,6 +1085,7 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); + mlx5_tout_cleanup(dev); return 0; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ccbd87fbd3bf..fb06e8870aee 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -66,10 +66,6 @@ enum { }; enum { - /* one minute for the sake of bringup. Generally, commands must always - * complete and we may need to increase this timeout value - */ - MLX5_CMD_TIMEOUT_MSEC = 60 * 1000, MLX5_CMD_WQ_MAX_NAME = 32, }; @@ -755,6 +751,7 @@ struct mlx5_core_dev { u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; u8 embedded_cpu; } caps; + struct mlx5_timeouts *timeouts; u64 sys_image_guid; phys_addr_t iseg_base; struct mlx5_init_seg __iomem *iseg; -- cgit v1.2.3 From fbfa97b4d79f26042f188b84959065213e9d3e99 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 18 Aug 2021 13:21:30 +0300 Subject: net/mlx5: Disable roce at HCA level Currently, when a user disables roce via the devlink param, this change isn't passed down to the device. If device allows disabling RoCE at device level, make use of it. This instructs the device to skip memory allocations related to RoCE functionality which otherwise is done by the device. Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 3 ++- drivers/net/ethernet/mellanox/mlx5/core/main.c | 25 ++++++++++++++++++++++- include/linux/mlx5/driver.h | 9 ++++---- include/linux/mlx5/mlx5_ifc.h | 3 ++- 4 files changed, 33 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index a85341a41cd0..1c98652b244a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -454,7 +454,8 @@ static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id, struct mlx5_core_dev *dev = devlink_priv(devlink); bool new_state = val.vbool; - if (new_state && !MLX5_CAP_GEN(dev, roce)) { + if (new_state && !MLX5_CAP_GEN(dev, roce) && + !MLX5_CAP_GEN(dev, roce_rw_supported)) { NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 75d284272119..47d92fb459ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -558,15 +558,38 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) MLX5_SET(cmd_hca_cap, set_hca_cap, num_total_dynamic_vf_msix, MLX5_CAP_GEN_MAX(dev, num_total_dynamic_vf_msix)); + if (MLX5_CAP_GEN(dev, roce_rw_supported)) + MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } +/* Cached MLX5_CAP_GEN(dev, roce) can be out of sync this early in the + * boot process. + * In case RoCE cap is writable in FW and user/devlink requested to change the + * cap, we are yet to query the final state of the above cap. + * Hence, the need for this function. + * + * Returns + * True: + * 1) RoCE cap is read only in FW and already disabled + * OR: + * 2) RoCE cap is writable in FW and user/devlink requested it off. + * + * In any other case, return False. + */ +static bool is_roce_fw_disabled(struct mlx5_core_dev *dev) +{ + return (MLX5_CAP_GEN(dev, roce_rw_supported) && !mlx5_is_roce_init_enabled(dev)) || + (!MLX5_CAP_GEN(dev, roce_rw_supported) && !MLX5_CAP_GEN(dev, roce)); +} + static int handle_hca_cap_roce(struct mlx5_core_dev *dev, void *set_ctx) { void *set_hca_cap; int err; - if (!MLX5_CAP_GEN(dev, roce)) + if (is_roce_fw_disabled(dev)) return 0; err = mlx5_core_get_caps(dev, MLX5_CAP_ROCE); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index fb06e8870aee..7c8b5f06c2cd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1251,11 +1251,12 @@ static inline bool mlx5_is_roce_init_enabled(struct mlx5_core_dev *dev) { struct devlink *devlink = priv_to_devlink(dev); union devlink_param_value val; + int err; - devlink_param_driverinit_value_get(devlink, - DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, - &val); - return val.vbool; + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + &val); + return err ? MLX5_CAP_GEN(dev, roce) : val.vbool; } #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index b8bff5109656..c614ad1da44d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1588,7 +1588,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 log_max_tis_per_sq[0x5]; u8 ext_stride_num_range[0x1]; - u8 reserved_at_3a1[0x2]; + u8 roce_rw_supported[0x1]; + u8 reserved_at_3a2[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; -- cgit v1.2.3 From 2ec16ddde1fa31a83aee04320b248e94348d9152 Mon Sep 17 00:00:00 2001 From: Rongwei Liu Date: Thu, 16 Sep 2021 10:46:17 +0300 Subject: net/mlx5: Introduce new device index wrapper Downstream patches. Signed-off-by: Rongwei Liu Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/lag.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c | 2 +- include/linux/mlx5/driver.h | 5 +++++ 6 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 86e079310ac3..ae52e7f38306 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -24,7 +24,7 @@ int mlx5e_devlink_port_register(struct mlx5e_priv *priv) if (mlx5_core_is_pf(priv->mdev)) { attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL; - attrs.phys.port_number = PCI_FUNC(priv->mdev->pdev->devfn); + attrs.phys.port_number = mlx5_get_dev_index(priv->mdev); if (MLX5_ESWITCH_MANAGER(priv->mdev)) { mlx5e_devlink_get_port_parent_id(priv->mdev, &ppid); memcpy(attrs.switch_id.id, ppid.id, ppid.id_len); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index 20af557ae30c..7f9b96d9537e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -36,7 +36,7 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 return NULL; mlx5_esw_get_port_parent_id(dev, &ppid); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); external = mlx5_core_is_ecpf_esw_manager(dev); if (external) controller_num = dev->priv.eswitch->offloads.host_number + 1; @@ -149,7 +149,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p if (IS_ERR(vport)) return PTR_ERR(vport); - pfnum = PCI_FUNC(dev->pdev->devfn); + pfnum = mlx5_get_dev_index(dev); mlx5_esw_get_port_parent_id(dev, &ppid); memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len); dl_port->attrs.switch_id.id_len = ppid.id_len; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index ca7e31a1a431..3e5a7d74020b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2798,7 +2798,7 @@ u32 mlx5_esw_match_metadata_alloc(struct mlx5_eswitch *esw) int id; /* Only 4 bits of pf_num */ - pf_num = PCI_FUNC(esw->dev->pdev->devfn); + pf_num = mlx5_get_dev_index(esw->dev); if (pf_num > max_pf_num) return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index ca5690b0a7ab..f35c8ba48aac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -688,7 +688,7 @@ static void mlx5_ldev_add_netdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev, struct net_device *netdev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; @@ -718,7 +718,7 @@ static void mlx5_ldev_remove_netdev(struct mlx5_lag *ldev, static void mlx5_ldev_add_mdev(struct mlx5_lag *ldev, struct mlx5_core_dev *dev) { - unsigned int fn = PCI_FUNC(dev->pdev->devfn); + unsigned int fn = mlx5_get_dev_index(dev); if (fn >= MLX5_MAX_PORTS) return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c index 13891fdc607e..e1bb3acf45e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c @@ -323,7 +323,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_ NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported"); return -EOPNOTSUPP; } - if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) { + if (new_attr->pfnum != mlx5_get_dev_index(dev)) { NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied"); return -EOPNOTSUPP; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7c8b5f06c2cd..aecc38b90de5 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1243,6 +1243,11 @@ static inline int mlx5_core_native_port_num(struct mlx5_core_dev *dev) return MLX5_CAP_GEN(dev, native_port_num); } +static inline int mlx5_get_dev_index(struct mlx5_core_dev *dev) +{ + return PCI_FUNC(dev->pdev->devfn); +} + enum { MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32, }; -- cgit v1.2.3 From 1021d0645d593ea86193c5fc371e33e5b208e14d Mon Sep 17 00:00:00 2001 From: Rongwei Liu Date: Tue, 12 Oct 2021 10:40:52 +0300 Subject: net/mlx5: Use native_port_num as 1st option of device index Using "native_port_num" can support more NICs. Fallback to PCIe IDs if "native_port_num" query fails. Signed-off-by: Rongwei Liu Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index aecc38b90de5..cf508685abca 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1245,7 +1245,12 @@ static inline int mlx5_core_native_port_num(struct mlx5_core_dev *dev) static inline int mlx5_get_dev_index(struct mlx5_core_dev *dev) { - return PCI_FUNC(dev->pdev->devfn); + int idx = MLX5_CAP_GEN(dev, native_port_num); + + if (idx >= 1 && idx <= MLX5_MAX_PORTS) + return idx - 1; + else + return PCI_FUNC(dev->pdev->devfn); } enum { -- cgit v1.2.3 From 72bf80cf09c4693780ad93a31b48fa5a4e17a946 Mon Sep 17 00:00:00 2001 From: Maíra Canal Date: Fri, 15 Oct 2021 12:14:35 -0300 Subject: regulator: lp872x: replacing legacy gpio interface for gpiod MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Removing all linux/gpio.h and linux/of_gpio.h dependencies and replacing them with the gpiod interface Signed-off-by: Maíra Canal Message-Id: Signed-off-by: Mark Brown --- drivers/regulator/lp872x.c | 38 +++++++++++++++----------------------- include/linux/regulator/lp872x.h | 14 +++++++------- 2 files changed, 22 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c index e84be29533f4..1dba5dbcd461 100644 --- a/drivers/regulator/lp872x.c +++ b/drivers/regulator/lp872x.c @@ -10,13 +10,12 @@ #include #include #include -#include +#include #include #include #include #include #include -#include #include /* Registers : LP8720/8725 shared */ @@ -250,12 +249,12 @@ static int lp872x_regulator_enable_time(struct regulator_dev *rdev) } static void lp872x_set_dvs(struct lp872x *lp, enum lp872x_dvs_sel dvs_sel, - int gpio) + struct gpio_desc *gpio) { enum lp872x_dvs_state state; state = dvs_sel == SEL_V1 ? DVS_HIGH : DVS_LOW; - gpio_set_value(gpio, state); + gpiod_set_value(gpio, state); lp->dvs_pin = state; } @@ -321,7 +320,7 @@ static int lp872x_buck_set_voltage_sel(struct regulator_dev *rdev, u8 addr, mask = LP872X_VOUT_M; struct lp872x_dvs *dvs = lp->pdata ? lp->pdata->dvs : NULL; - if (dvs && gpio_is_valid(dvs->gpio)) + if (dvs && dvs->gpio) lp872x_set_dvs(lp, dvs->vsel, dvs->gpio); addr = lp872x_select_buck_vout_addr(lp, buck); @@ -675,7 +674,6 @@ static const struct regulator_desc lp8725_regulator_desc[] = { static int lp872x_init_dvs(struct lp872x *lp) { - int ret, gpio; struct lp872x_dvs *dvs = lp->pdata ? lp->pdata->dvs : NULL; enum lp872x_dvs_state pinstate; u8 mask[] = { LP8720_EXT_DVS_M, LP8725_DVS1_M | LP8725_DVS2_M }; @@ -684,15 +682,15 @@ static int lp872x_init_dvs(struct lp872x *lp) if (!dvs) goto set_default_dvs_mode; - gpio = dvs->gpio; - if (!gpio_is_valid(gpio)) + if (!dvs->gpio) goto set_default_dvs_mode; pinstate = dvs->init_state; - ret = devm_gpio_request_one(lp->dev, gpio, pinstate, "LP872X DVS"); - if (ret) { - dev_err(lp->dev, "gpio request err: %d\n", ret); - return ret; + dvs->gpio = devm_gpiod_get_optional(lp->dev, "ti,dvs", pinstate); + + if (IS_ERR(dvs->gpio)) { + dev_err(lp->dev, "gpio request err: %ld\n", PTR_ERR(dvs->gpio)); + return PTR_ERR(dvs->gpio); } lp->dvs_pin = pinstate; @@ -706,20 +704,17 @@ set_default_dvs_mode: static int lp872x_hw_enable(struct lp872x *lp) { - int ret, gpio; - if (!lp->pdata) return -EINVAL; - gpio = lp->pdata->enable_gpio; - if (!gpio_is_valid(gpio)) + if (!lp->pdata->enable_gpio) return 0; /* Always set enable GPIO high. */ - ret = devm_gpio_request_one(lp->dev, gpio, GPIOF_OUT_INIT_HIGH, "LP872X EN"); - if (ret) { - dev_err(lp->dev, "gpio request err: %d\n", ret); - return ret; + lp->pdata->enable_gpio = devm_gpiod_get_optional(lp->dev, "enable", GPIOD_OUT_HIGH); + if (IS_ERR(lp->pdata->enable_gpio)) { + dev_err(lp->dev, "gpio request err: %ld\n", PTR_ERR(lp->pdata->enable_gpio)); + return PTR_ERR(lp->pdata->enable_gpio); } /* Each chip has a different enable delay. */ @@ -844,13 +839,10 @@ static struct lp872x_platform_data if (!pdata->dvs) return ERR_PTR(-ENOMEM); - pdata->dvs->gpio = of_get_named_gpio(np, "ti,dvs-gpio", 0); of_property_read_u8(np, "ti,dvs-vsel", (u8 *)&pdata->dvs->vsel); of_property_read_u8(np, "ti,dvs-state", &dvs_state); pdata->dvs->init_state = dvs_state ? DVS_HIGH : DVS_LOW; - pdata->enable_gpio = of_get_named_gpio(np, "enable-gpios", 0); - if (of_get_child_count(np) == 0) goto out; diff --git a/include/linux/regulator/lp872x.h b/include/linux/regulator/lp872x.h index d780dbb8b423..8e7e0343c6e1 100644 --- a/include/linux/regulator/lp872x.h +++ b/include/linux/regulator/lp872x.h @@ -10,7 +10,7 @@ #include #include -#include +#include #define LP872X_MAX_REGULATORS 9 @@ -41,8 +41,8 @@ enum lp872x_regulator_id { }; enum lp872x_dvs_state { - DVS_LOW = GPIOF_OUT_INIT_LOW, - DVS_HIGH = GPIOF_OUT_INIT_HIGH, + DVS_LOW = GPIOD_OUT_LOW, + DVS_HIGH = GPIOD_OUT_HIGH, }; enum lp872x_dvs_sel { @@ -52,12 +52,12 @@ enum lp872x_dvs_sel { /** * lp872x_dvs - * @gpio : gpio pin number for dvs control + * @gpio : gpio descriptor for dvs control * @vsel : dvs selector for buck v1 or buck v2 register * @init_state : initial dvs pin state */ struct lp872x_dvs { - int gpio; + struct gpio_desc *gpio; enum lp872x_dvs_sel vsel; enum lp872x_dvs_state init_state; }; @@ -78,14 +78,14 @@ struct lp872x_regulator_data { * @update_config : if LP872X_GENERAL_CFG register is updated, set true * @regulator_data : platform regulator id and init data * @dvs : dvs data for buck voltage control - * @enable_gpio : gpio pin number for enable control + * @enable_gpio : gpio descriptor for enable control */ struct lp872x_platform_data { u8 general_config; bool update_config; struct lp872x_regulator_data regulator_data[LP872X_MAX_REGULATORS]; struct lp872x_dvs *dvs; - int enable_gpio; + struct gpio_desc *enable_gpio; }; #endif -- cgit v1.2.3 From c3f69c7f629ff53c75f335754ea41426b8e095de Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Tue, 12 Oct 2021 16:35:14 -0700 Subject: scsi: ata: Switch to attribute groups struct device supports attribute groups directly but does not support struct device_attribute directly. Hence switch to attribute groups. Link: https://lore.kernel.org/r/20211012233558.4066756-3-bvanassche@acm.org Acked-by: Damien Le Moal Signed-off-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ata/ahci.h | 8 ++++---- drivers/ata/ata_piix.c | 8 +++++--- drivers/ata/libahci.c | 52 +++++++++++++++++++++++++++++++---------------- drivers/ata/libata-sata.c | 19 ++++++++++++----- drivers/ata/libata-scsi.c | 15 +++++++++++--- drivers/ata/pata_macio.c | 2 +- drivers/ata/sata_mv.c | 2 +- drivers/ata/sata_nv.c | 4 ++-- drivers/ata/sata_sil24.c | 2 +- include/linux/libata.h | 8 ++++---- 10 files changed, 79 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h index 2e89499bd9c3..eeac5482f1d1 100644 --- a/drivers/ata/ahci.h +++ b/drivers/ata/ahci.h @@ -376,8 +376,8 @@ struct ahci_host_priv { extern int ahci_ignore_sss; -extern struct device_attribute *ahci_shost_attrs[]; -extern struct device_attribute *ahci_sdev_attrs[]; +extern const struct attribute_group *ahci_shost_groups[]; +extern const struct attribute_group *ahci_sdev_groups[]; /* * This must be instantiated by the edge drivers. Read the comments @@ -388,8 +388,8 @@ extern struct device_attribute *ahci_sdev_attrs[]; .can_queue = AHCI_MAX_CMDS, \ .sg_tablesize = AHCI_MAX_SG, \ .dma_boundary = AHCI_DMA_BOUNDARY, \ - .shost_attrs = ahci_shost_attrs, \ - .sdev_attrs = ahci_sdev_attrs, \ + .shost_groups = ahci_shost_groups, \ + .sdev_groups = ahci_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth, \ .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .slave_configure = ata_scsi_slave_config diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c index 3ca7720e7d8f..0b2fcf0d1d6c 100644 --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -1085,14 +1085,16 @@ static struct ata_port_operations ich_pata_ops = { .set_dmamode = ich_set_dmamode, }; -static struct device_attribute *piix_sidpr_shost_attrs[] = { - &dev_attr_link_power_management_policy, +static struct attribute *piix_sidpr_shost_attrs[] = { + &dev_attr_link_power_management_policy.attr, NULL }; +ATTRIBUTE_GROUPS(piix_sidpr_shost); + static struct scsi_host_template piix_sidpr_sht = { ATA_BMDMA_SHT(DRV_NAME), - .shost_attrs = piix_sidpr_shost_attrs, + .shost_groups = piix_sidpr_shost_groups, }; static struct ata_port_operations piix_sidpr_sata_ops = { diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 5b3fa2cbe722..28430c093a7f 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -108,28 +108,46 @@ static DEVICE_ATTR(em_buffer, S_IWUSR | S_IRUGO, ahci_read_em_buffer, ahci_store_em_buffer); static DEVICE_ATTR(em_message_supported, S_IRUGO, ahci_show_em_supported, NULL); -struct device_attribute *ahci_shost_attrs[] = { - &dev_attr_link_power_management_policy, - &dev_attr_em_message_type, - &dev_attr_em_message, - &dev_attr_ahci_host_caps, - &dev_attr_ahci_host_cap2, - &dev_attr_ahci_host_version, - &dev_attr_ahci_port_cmd, - &dev_attr_em_buffer, - &dev_attr_em_message_supported, +static struct attribute *ahci_shost_attrs[] = { + &dev_attr_link_power_management_policy.attr, + &dev_attr_em_message_type.attr, + &dev_attr_em_message.attr, + &dev_attr_ahci_host_caps.attr, + &dev_attr_ahci_host_cap2.attr, + &dev_attr_ahci_host_version.attr, + &dev_attr_ahci_port_cmd.attr, + &dev_attr_em_buffer.attr, + &dev_attr_em_message_supported.attr, NULL }; -EXPORT_SYMBOL_GPL(ahci_shost_attrs); -struct device_attribute *ahci_sdev_attrs[] = { - &dev_attr_sw_activity, - &dev_attr_unload_heads, - &dev_attr_ncq_prio_supported, - &dev_attr_ncq_prio_enable, +static const struct attribute_group ahci_shost_attr_group = { + .attrs = ahci_shost_attrs +}; + +const struct attribute_group *ahci_shost_groups[] = { + &ahci_shost_attr_group, + NULL +}; +EXPORT_SYMBOL_GPL(ahci_shost_groups); + +struct attribute *ahci_sdev_attrs[] = { + &dev_attr_sw_activity.attr, + &dev_attr_unload_heads.attr, + &dev_attr_ncq_prio_supported.attr, + &dev_attr_ncq_prio_enable.attr, + NULL +}; + +static const struct attribute_group ahci_sdev_attr_group = { + .attrs = ahci_sdev_attrs +}; + +const struct attribute_group *ahci_sdev_groups[] = { + &ahci_sdev_attr_group, NULL }; -EXPORT_SYMBOL_GPL(ahci_sdev_attrs); +EXPORT_SYMBOL_GPL(ahci_sdev_groups); struct ata_port_operations ahci_ops = { .inherits = &sata_pmp_port_ops, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index 60418d872c12..4e88597aa9df 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -922,13 +922,22 @@ DEVICE_ATTR(ncq_prio_enable, S_IRUGO | S_IWUSR, ata_ncq_prio_enable_show, ata_ncq_prio_enable_store); EXPORT_SYMBOL_GPL(dev_attr_ncq_prio_enable); -struct device_attribute *ata_ncq_sdev_attrs[] = { - &dev_attr_unload_heads, - &dev_attr_ncq_prio_enable, - &dev_attr_ncq_prio_supported, +struct attribute *ata_ncq_sdev_attrs[] = { + &dev_attr_unload_heads.attr, + &dev_attr_ncq_prio_enable.attr, + &dev_attr_ncq_prio_supported.attr, NULL }; -EXPORT_SYMBOL_GPL(ata_ncq_sdev_attrs); + +static const struct attribute_group ata_ncq_sdev_attr_group = { + .attrs = ata_ncq_sdev_attrs +}; + +const struct attribute_group *ata_ncq_sdev_groups[] = { + &ata_ncq_sdev_attr_group, + NULL +}; +EXPORT_SYMBOL_GPL(ata_ncq_sdev_groups); static ssize_t ata_scsi_em_message_store(struct device *dev, struct device_attribute *attr, diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 4afe1abc4709..29eb7cca17a4 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -234,11 +234,20 @@ static void ata_scsi_set_invalid_parameter(struct ata_device *dev, field, 0xff, 0); } -struct device_attribute *ata_common_sdev_attrs[] = { - &dev_attr_unload_heads, +static struct attribute *ata_common_sdev_attrs[] = { + &dev_attr_unload_heads.attr, NULL }; -EXPORT_SYMBOL_GPL(ata_common_sdev_attrs); + +static const struct attribute_group ata_common_sdev_attr_group = { + .attrs = ata_common_sdev_attrs +}; + +const struct attribute_group *ata_common_sdev_groups[] = { + &ata_common_sdev_attr_group, + NULL +}; +EXPORT_SYMBOL_GPL(ata_common_sdev_groups); /** * ata_std_bios_param - generic bios head/sector/cylinder calculator used by sd. diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index be0ca8d5b345..16e8aa184a75 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -923,7 +923,7 @@ static struct scsi_host_template pata_macio_sht = { */ .max_segment_size = MAX_DBDMA_SEG, .slave_configure = pata_macio_slave_config, - .sdev_attrs = ata_common_sdev_attrs, + .sdev_groups = ata_common_sdev_groups, .can_queue = ATA_DEF_QUEUE, .tag_alloc_policy = BLK_TAG_ALLOC_RR, }; diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c index 9d86203e1e7a..24130e551b26 100644 --- a/drivers/ata/sata_mv.c +++ b/drivers/ata/sata_mv.c @@ -670,7 +670,7 @@ static struct scsi_host_template mv6_sht = { .can_queue = MV_MAX_Q_DEPTH - 1, .sg_tablesize = MV_MAX_SG_CT / 2, .dma_boundary = MV_DMA_BOUNDARY, - .sdev_attrs = ata_ncq_sdev_attrs, + .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, .tag_alloc_policy = BLK_TAG_ALLOC_RR, .slave_configure = ata_scsi_slave_config diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c index c385d18ce87b..16272c111208 100644 --- a/drivers/ata/sata_nv.c +++ b/drivers/ata/sata_nv.c @@ -380,7 +380,7 @@ static struct scsi_host_template nv_adma_sht = { .sg_tablesize = NV_ADMA_SGTBL_TOTAL_LEN, .dma_boundary = NV_ADMA_DMA_BOUNDARY, .slave_configure = nv_adma_slave_config, - .sdev_attrs = ata_ncq_sdev_attrs, + .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, .tag_alloc_policy = BLK_TAG_ALLOC_RR, }; @@ -391,7 +391,7 @@ static struct scsi_host_template nv_swncq_sht = { .sg_tablesize = LIBATA_MAX_PRD, .dma_boundary = ATA_DMA_BOUNDARY, .slave_configure = nv_swncq_slave_config, - .sdev_attrs = ata_ncq_sdev_attrs, + .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, .tag_alloc_policy = BLK_TAG_ALLOC_RR, }; diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index 06a1e27c4f84..f99ec6f7d7c0 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -379,7 +379,7 @@ static struct scsi_host_template sil24_sht = { .sg_tablesize = SIL24_MAX_SGE, .dma_boundary = ATA_DMA_BOUNDARY, .tag_alloc_policy = BLK_TAG_ALLOC_FIFO, - .sdev_attrs = ata_ncq_sdev_attrs, + .sdev_groups = ata_ncq_sdev_groups, .change_queue_depth = ata_scsi_change_queue_depth, .slave_configure = ata_scsi_slave_config }; diff --git a/include/linux/libata.h b/include/linux/libata.h index c0c64f03e107..bd1b782d1bbf 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1388,7 +1388,7 @@ extern int ata_link_nr_enabled(struct ata_link *link); */ extern const struct ata_port_operations ata_base_port_ops; extern const struct ata_port_operations sata_port_ops; -extern struct device_attribute *ata_common_sdev_attrs[]; +extern const struct attribute_group *ata_common_sdev_groups[]; /* * All sht initializers (BASE, PIO, BMDMA, NCQ) must be instantiated @@ -1418,14 +1418,14 @@ extern struct device_attribute *ata_common_sdev_attrs[]; #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ - .sdev_attrs = ata_common_sdev_attrs + .sdev_groups = ata_common_sdev_groups #ifdef CONFIG_SATA_HOST -extern struct device_attribute *ata_ncq_sdev_attrs[]; +extern const struct attribute_group *ata_ncq_sdev_groups[]; #define ATA_NCQ_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ - .sdev_attrs = ata_ncq_sdev_attrs, \ + .sdev_groups = ata_ncq_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth #endif -- cgit v1.2.3 From 05593a3fd1037b5fee85d3c8c28112f19e7baa06 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 27 Aug 2021 12:47:45 +0900 Subject: counter: stm32-lptimer-cnt: Provide defines for clock polarities The STM32 low-power timer permits configuration of the clock polarity via the LPTIMX_CFGR register CKPOL bits. This patch provides preprocessor defines for the supported clock polarities. Cc: Fabrice Gasnier Signed-off-by: William Breathitt Gray Reviewed-by: Fabrice Gasnier Link: https://lore.kernel.org/r/a111c8905c467805ca530728f88189b59430f27e.1630031207.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/stm32-lptimer-cnt.c | 6 +++--- include/linux/mfd/stm32-lptimer.h | 5 +++++ 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/stm32-lptimer-cnt.c b/drivers/counter/stm32-lptimer-cnt.c index 13656957c45f..7367f46c6f91 100644 --- a/drivers/counter/stm32-lptimer-cnt.c +++ b/drivers/counter/stm32-lptimer-cnt.c @@ -140,9 +140,9 @@ static const enum counter_function stm32_lptim_cnt_functions[] = { }; enum stm32_lptim_synapse_action { - STM32_LPTIM_SYNAPSE_ACTION_RISING_EDGE, - STM32_LPTIM_SYNAPSE_ACTION_FALLING_EDGE, - STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES, + STM32_LPTIM_SYNAPSE_ACTION_RISING_EDGE = STM32_LPTIM_CKPOL_RISING_EDGE, + STM32_LPTIM_SYNAPSE_ACTION_FALLING_EDGE = STM32_LPTIM_CKPOL_FALLING_EDGE, + STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES = STM32_LPTIM_CKPOL_BOTH_EDGES, STM32_LPTIM_SYNAPSE_ACTION_NONE, }; diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h index 90b20550c1c8..06d3f11dc3c9 100644 --- a/include/linux/mfd/stm32-lptimer.h +++ b/include/linux/mfd/stm32-lptimer.h @@ -45,6 +45,11 @@ #define STM32_LPTIM_PRESC GENMASK(11, 9) #define STM32_LPTIM_CKPOL GENMASK(2, 1) +/* STM32_LPTIM_CKPOL */ +#define STM32_LPTIM_CKPOL_RISING_EDGE 0 +#define STM32_LPTIM_CKPOL_FALLING_EDGE 1 +#define STM32_LPTIM_CKPOL_BOTH_EDGES 2 + /* STM32_LPTIM_ARR */ #define STM32_LPTIM_MAX_ARR 0xFFFF -- cgit v1.2.3 From ea434ff82649111de4fcabd76187270f8abdb63a Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 27 Aug 2021 12:47:46 +0900 Subject: counter: stm32-timer-cnt: Provide defines for slave mode selection The STM32 timer permits configuration of the counter encoder mode via the slave mode control register (SMCR) slave mode selection (SMS) bits. This patch provides preprocessor defines for the supported encoder modes. Cc: Fabrice Gasnier Signed-off-by: William Breathitt Gray Reviewed-by: Fabrice Gasnier Link: https://lore.kernel.org/r/ad3d9cd7af580d586316d368f74964cbc394f981.1630031207.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/stm32-timer-cnt.c | 16 ++++++++-------- include/linux/mfd/stm32-timers.h | 4 ++++ 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c index 3fb0debd7425..1fbc46f4ee66 100644 --- a/drivers/counter/stm32-timer-cnt.c +++ b/drivers/counter/stm32-timer-cnt.c @@ -93,16 +93,16 @@ static int stm32_count_function_get(struct counter_device *counter, regmap_read(priv->regmap, TIM_SMCR, &smcr); switch (smcr & TIM_SMCR_SMS) { - case 0: + case TIM_SMCR_SMS_SLAVE_MODE_DISABLED: *function = STM32_COUNT_SLAVE_MODE_DISABLED; return 0; - case 1: + case TIM_SMCR_SMS_ENCODER_MODE_1: *function = STM32_COUNT_ENCODER_MODE_1; return 0; - case 2: + case TIM_SMCR_SMS_ENCODER_MODE_2: *function = STM32_COUNT_ENCODER_MODE_2; return 0; - case 3: + case TIM_SMCR_SMS_ENCODER_MODE_3: *function = STM32_COUNT_ENCODER_MODE_3; return 0; default: @@ -119,16 +119,16 @@ static int stm32_count_function_set(struct counter_device *counter, switch (function) { case STM32_COUNT_SLAVE_MODE_DISABLED: - sms = 0; + sms = TIM_SMCR_SMS_SLAVE_MODE_DISABLED; break; case STM32_COUNT_ENCODER_MODE_1: - sms = 1; + sms = TIM_SMCR_SMS_ENCODER_MODE_1; break; case STM32_COUNT_ENCODER_MODE_2: - sms = 2; + sms = TIM_SMCR_SMS_ENCODER_MODE_2; break; case STM32_COUNT_ENCODER_MODE_3: - sms = 3; + sms = TIM_SMCR_SMS_ENCODER_MODE_3; break; default: return -EINVAL; diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h index f8db83aedb2b..5f5c43fd69dd 100644 --- a/include/linux/mfd/stm32-timers.h +++ b/include/linux/mfd/stm32-timers.h @@ -82,6 +82,10 @@ #define MAX_TIM_ICPSC 0x3 #define TIM_CR2_MMS_SHIFT 4 #define TIM_CR2_MMS2_SHIFT 20 +#define TIM_SMCR_SMS_SLAVE_MODE_DISABLED 0 /* counts on internal clock when CEN=1 */ +#define TIM_SMCR_SMS_ENCODER_MODE_1 1 /* counts TI1FP1 edges, depending on TI2FP2 level */ +#define TIM_SMCR_SMS_ENCODER_MODE_2 2 /* counts TI2FP2 edges, depending on TI1FP1 level */ +#define TIM_SMCR_SMS_ENCODER_MODE_3 3 /* counts on both TI1FP1 and TI2FP2 edges */ #define TIM_SMCR_TS_SHIFT 4 #define TIM_BDTR_BKF_MASK 0xF #define TIM_BDTR_BKF_SHIFT(x) (16 + (x) * 4) -- cgit v1.2.3 From aaec1a0f76ec25f46bbb17b81487c4b0e1c318c5 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 27 Aug 2021 12:47:47 +0900 Subject: counter: Internalize sysfs interface code This is a reimplementation of the Generic Counter driver interface. There are no modifications to the Counter subsystem userspace interface, so existing userspace applications should continue to run seamlessly. The purpose of this patch is to internalize the sysfs interface code among the various counter drivers into a shared module. Counter drivers pass and take data natively (i.e. u8, u64, etc.) and the shared counter module handles the translation between the sysfs interface and the device drivers. This guarantees a standard userspace interface for all counter drivers, and helps generalize the Generic Counter driver ABI in order to support the Generic Counter chrdev interface (introduced in a subsequent patch) without significant changes to the existing counter drivers. Note, Counter device registration is the same as before: drivers populate a struct counter_device with components and callbacks, then pass the structure to the devm_counter_register function. However, what's different now is how the Counter subsystem code handles this registration internally. Whereas before callbacks would interact directly with sysfs data, this interaction is now abstracted and instead callbacks interact with native C data types. The counter_comp structure forms the basis for Counter extensions. The counter-sysfs.c file contains the code to parse through the counter_device structure and register the requested components and extensions. Attributes are created and populated based on type, with respective translation functions to handle the mapping between sysfs and the counter driver callbacks. The translation performed for each attribute is straightforward: the attribute type and data is parsed from the counter_attribute structure, the respective counter driver read/write callback is called, and sysfs I/O is handled before or after the driver read/write function is called. Cc: Jarkko Nikula Cc: Patrick Havelange Cc: Kamel Bouhara Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: Dan Carpenter Acked-by: Syed Nayyar Waris Reviewed-by: David Lechner Tested-by: David Lechner Signed-off-by: William Breathitt Gray Reviewed-by: Fabrice Gasnier # for stm32 Link: https://lore.kernel.org/r/c68b4a1ffb195c1a2f65e8dd5ad7b7c14e79c6ef.1630031207.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- MAINTAINERS | 1 - drivers/counter/104-quad-8.c | 449 ++++------ drivers/counter/Makefile | 1 + drivers/counter/counter-core.c | 142 +++ drivers/counter/counter-sysfs.c | 849 ++++++++++++++++++ drivers/counter/counter-sysfs.h | 13 + drivers/counter/counter.c | 1496 ------------------------------- drivers/counter/ftm-quaddec.c | 60 +- drivers/counter/intel-qep.c | 146 ++- drivers/counter/interrupt-cnt.c | 62 +- drivers/counter/microchip-tcb-capture.c | 91 +- drivers/counter/stm32-lptimer-cnt.c | 212 +++-- drivers/counter/stm32-timer-cnt.c | 179 ++-- drivers/counter/ti-eqep.c | 180 ++-- include/linux/counter.h | 658 +++++++------- include/linux/counter_enum.h | 45 - 16 files changed, 1950 insertions(+), 2634 deletions(-) create mode 100644 drivers/counter/counter-core.c create mode 100644 drivers/counter/counter-sysfs.c create mode 100644 drivers/counter/counter-sysfs.h delete mode 100644 drivers/counter/counter.c delete mode 100644 include/linux/counter_enum.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index eeb4c70b3d5b..b98a34fcec4b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4804,7 +4804,6 @@ F: Documentation/ABI/testing/sysfs-bus-counter F: Documentation/driver-api/generic-counter.rst F: drivers/counter/ F: include/linux/counter.h -F: include/linux/counter_enum.h CP2615 I2C DRIVER M: Bence Csókás diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c index 0caa60537b14..c587f295d720 100644 --- a/drivers/counter/104-quad-8.c +++ b/drivers/counter/104-quad-8.c @@ -117,7 +117,7 @@ static int quad8_signal_read(struct counter_device *counter, } static int quad8_count_read(struct counter_device *counter, - struct counter_count *count, unsigned long *val) + struct counter_count *count, u64 *val) { struct quad8 *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id; @@ -148,7 +148,7 @@ static int quad8_count_read(struct counter_device *counter, } static int quad8_count_write(struct counter_device *counter, - struct counter_count *count, unsigned long val) + struct counter_count *count, u64 val) { struct quad8 *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id; @@ -188,22 +188,16 @@ static int quad8_count_write(struct counter_device *counter, return 0; } -enum quad8_count_function { - QUAD8_COUNT_FUNCTION_PULSE_DIRECTION = 0, - QUAD8_COUNT_FUNCTION_QUADRATURE_X1, - QUAD8_COUNT_FUNCTION_QUADRATURE_X2, - QUAD8_COUNT_FUNCTION_QUADRATURE_X4 -}; - static const enum counter_function quad8_count_functions_list[] = { - [QUAD8_COUNT_FUNCTION_PULSE_DIRECTION] = COUNTER_FUNCTION_PULSE_DIRECTION, - [QUAD8_COUNT_FUNCTION_QUADRATURE_X1] = COUNTER_FUNCTION_QUADRATURE_X1_A, - [QUAD8_COUNT_FUNCTION_QUADRATURE_X2] = COUNTER_FUNCTION_QUADRATURE_X2_A, - [QUAD8_COUNT_FUNCTION_QUADRATURE_X4] = COUNTER_FUNCTION_QUADRATURE_X4 + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X1_A, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X4, }; -static int quad8_function_get(struct counter_device *counter, - struct counter_count *count, size_t *function) +static int quad8_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { struct quad8 *const priv = counter->priv; const int id = count->id; @@ -213,25 +207,26 @@ static int quad8_function_get(struct counter_device *counter, if (priv->quadrature_mode[id]) switch (priv->quadrature_scale[id]) { case 0: - *function = QUAD8_COUNT_FUNCTION_QUADRATURE_X1; + *function = COUNTER_FUNCTION_QUADRATURE_X1_A; break; case 1: - *function = QUAD8_COUNT_FUNCTION_QUADRATURE_X2; + *function = COUNTER_FUNCTION_QUADRATURE_X2_A; break; case 2: - *function = QUAD8_COUNT_FUNCTION_QUADRATURE_X4; + *function = COUNTER_FUNCTION_QUADRATURE_X4; break; } else - *function = QUAD8_COUNT_FUNCTION_PULSE_DIRECTION; + *function = COUNTER_FUNCTION_PULSE_DIRECTION; mutex_unlock(&priv->lock); return 0; } -static int quad8_function_set(struct counter_device *counter, - struct counter_count *count, size_t function) +static int quad8_function_write(struct counter_device *counter, + struct counter_count *count, + enum counter_function function) { struct quad8 *const priv = counter->priv; const int id = count->id; @@ -247,7 +242,7 @@ static int quad8_function_set(struct counter_device *counter, mode_cfg = priv->count_mode[id] << 1; idr_cfg = priv->index_polarity[id] << 1; - if (function == QUAD8_COUNT_FUNCTION_PULSE_DIRECTION) { + if (function == COUNTER_FUNCTION_PULSE_DIRECTION) { *quadrature_mode = 0; /* Quadrature scaling only available in quadrature mode */ @@ -263,15 +258,15 @@ static int quad8_function_set(struct counter_device *counter, *quadrature_mode = 1; switch (function) { - case QUAD8_COUNT_FUNCTION_QUADRATURE_X1: + case COUNTER_FUNCTION_QUADRATURE_X1_A: *scale = 0; mode_cfg |= QUAD8_CMR_QUADRATURE_X1; break; - case QUAD8_COUNT_FUNCTION_QUADRATURE_X2: + case COUNTER_FUNCTION_QUADRATURE_X2_A: *scale = 1; mode_cfg |= QUAD8_CMR_QUADRATURE_X2; break; - case QUAD8_COUNT_FUNCTION_QUADRATURE_X4: + case COUNTER_FUNCTION_QUADRATURE_X4: *scale = 2; mode_cfg |= QUAD8_CMR_QUADRATURE_X4; break; @@ -290,8 +285,9 @@ static int quad8_function_set(struct counter_device *counter, return 0; } -static void quad8_direction_get(struct counter_device *counter, - struct counter_count *count, enum counter_count_direction *direction) +static int quad8_direction_read(struct counter_device *counter, + struct counter_count *count, + enum counter_count_direction *direction) { const struct quad8 *const priv = counter->priv; unsigned int ud_flag; @@ -302,76 +298,74 @@ static void quad8_direction_get(struct counter_device *counter, *direction = (ud_flag) ? COUNTER_COUNT_DIRECTION_FORWARD : COUNTER_COUNT_DIRECTION_BACKWARD; -} -enum quad8_synapse_action { - QUAD8_SYNAPSE_ACTION_NONE = 0, - QUAD8_SYNAPSE_ACTION_RISING_EDGE, - QUAD8_SYNAPSE_ACTION_FALLING_EDGE, - QUAD8_SYNAPSE_ACTION_BOTH_EDGES -}; + return 0; +} static const enum counter_synapse_action quad8_index_actions_list[] = { - [QUAD8_SYNAPSE_ACTION_NONE] = COUNTER_SYNAPSE_ACTION_NONE, - [QUAD8_SYNAPSE_ACTION_RISING_EDGE] = COUNTER_SYNAPSE_ACTION_RISING_EDGE + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, }; static const enum counter_synapse_action quad8_synapse_actions_list[] = { - [QUAD8_SYNAPSE_ACTION_NONE] = COUNTER_SYNAPSE_ACTION_NONE, - [QUAD8_SYNAPSE_ACTION_RISING_EDGE] = COUNTER_SYNAPSE_ACTION_RISING_EDGE, - [QUAD8_SYNAPSE_ACTION_FALLING_EDGE] = COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - [QUAD8_SYNAPSE_ACTION_BOTH_EDGES] = COUNTER_SYNAPSE_ACTION_BOTH_EDGES + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, }; -static int quad8_action_get(struct counter_device *counter, - struct counter_count *count, struct counter_synapse *synapse, - size_t *action) +static int quad8_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { struct quad8 *const priv = counter->priv; int err; - size_t function = 0; + enum counter_function function; const size_t signal_a_id = count->synapses[0].signal->id; enum counter_count_direction direction; /* Handle Index signals */ if (synapse->signal->id >= 16) { if (priv->preset_enable[count->id]) - *action = QUAD8_SYNAPSE_ACTION_RISING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; else - *action = QUAD8_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; return 0; } - err = quad8_function_get(counter, count, &function); + err = quad8_function_read(counter, count, &function); if (err) return err; /* Default action mode */ - *action = QUAD8_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; /* Determine action mode based on current count function mode */ switch (function) { - case QUAD8_COUNT_FUNCTION_PULSE_DIRECTION: + case COUNTER_FUNCTION_PULSE_DIRECTION: if (synapse->signal->id == signal_a_id) - *action = QUAD8_SYNAPSE_ACTION_RISING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; return 0; - case QUAD8_COUNT_FUNCTION_QUADRATURE_X1: + case COUNTER_FUNCTION_QUADRATURE_X1_A: if (synapse->signal->id == signal_a_id) { - quad8_direction_get(counter, count, &direction); + err = quad8_direction_read(counter, count, &direction); + if (err) + return err; if (direction == COUNTER_COUNT_DIRECTION_FORWARD) - *action = QUAD8_SYNAPSE_ACTION_RISING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; else - *action = QUAD8_SYNAPSE_ACTION_FALLING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_FALLING_EDGE; } return 0; - case QUAD8_COUNT_FUNCTION_QUADRATURE_X2: + case COUNTER_FUNCTION_QUADRATURE_X2_A: if (synapse->signal->id == signal_a_id) - *action = QUAD8_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; - case QUAD8_COUNT_FUNCTION_QUADRATURE_X4: - *action = QUAD8_SYNAPSE_ACTION_BOTH_EDGES; + case COUNTER_FUNCTION_QUADRATURE_X4: + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; default: /* should never reach this path */ @@ -383,9 +377,9 @@ static const struct counter_ops quad8_ops = { .signal_read = quad8_signal_read, .count_read = quad8_count_read, .count_write = quad8_count_write, - .function_get = quad8_function_get, - .function_set = quad8_function_set, - .action_get = quad8_action_get + .function_read = quad8_function_read, + .function_write = quad8_function_write, + .action_read = quad8_action_read }; static const char *const quad8_index_polarity_modes[] = { @@ -394,7 +388,8 @@ static const char *const quad8_index_polarity_modes[] = { }; static int quad8_index_polarity_get(struct counter_device *counter, - struct counter_signal *signal, size_t *index_polarity) + struct counter_signal *signal, + u32 *index_polarity) { const struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id - 16; @@ -405,7 +400,8 @@ static int quad8_index_polarity_get(struct counter_device *counter, } static int quad8_index_polarity_set(struct counter_device *counter, - struct counter_signal *signal, size_t index_polarity) + struct counter_signal *signal, + u32 index_polarity) { struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id - 16; @@ -426,20 +422,14 @@ static int quad8_index_polarity_set(struct counter_device *counter, return 0; } -static struct counter_signal_enum_ext quad8_index_pol_enum = { - .items = quad8_index_polarity_modes, - .num_items = ARRAY_SIZE(quad8_index_polarity_modes), - .get = quad8_index_polarity_get, - .set = quad8_index_polarity_set -}; - static const char *const quad8_synchronous_modes[] = { "non-synchronous", "synchronous" }; static int quad8_synchronous_mode_get(struct counter_device *counter, - struct counter_signal *signal, size_t *synchronous_mode) + struct counter_signal *signal, + u32 *synchronous_mode) { const struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id - 16; @@ -450,7 +440,8 @@ static int quad8_synchronous_mode_get(struct counter_device *counter, } static int quad8_synchronous_mode_set(struct counter_device *counter, - struct counter_signal *signal, size_t synchronous_mode) + struct counter_signal *signal, + u32 synchronous_mode) { struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id - 16; @@ -477,22 +468,18 @@ static int quad8_synchronous_mode_set(struct counter_device *counter, return 0; } -static struct counter_signal_enum_ext quad8_syn_mode_enum = { - .items = quad8_synchronous_modes, - .num_items = ARRAY_SIZE(quad8_synchronous_modes), - .get = quad8_synchronous_mode_get, - .set = quad8_synchronous_mode_set -}; - -static ssize_t quad8_count_floor_read(struct counter_device *counter, - struct counter_count *count, void *private, char *buf) +static int quad8_count_floor_read(struct counter_device *counter, + struct counter_count *count, u64 *floor) { /* Only a floor of 0 is supported */ - return sprintf(buf, "0\n"); + *floor = 0; + + return 0; } -static int quad8_count_mode_get(struct counter_device *counter, - struct counter_count *count, size_t *cnt_mode) +static int quad8_count_mode_read(struct counter_device *counter, + struct counter_count *count, + enum counter_count_mode *cnt_mode) { const struct quad8 *const priv = counter->priv; @@ -515,26 +502,28 @@ static int quad8_count_mode_get(struct counter_device *counter, return 0; } -static int quad8_count_mode_set(struct counter_device *counter, - struct counter_count *count, size_t cnt_mode) +static int quad8_count_mode_write(struct counter_device *counter, + struct counter_count *count, + enum counter_count_mode cnt_mode) { struct quad8 *const priv = counter->priv; + unsigned int count_mode; unsigned int mode_cfg; const int base_offset = priv->base + 2 * count->id + 1; /* Map Generic Counter count mode to 104-QUAD-8 count mode */ switch (cnt_mode) { case COUNTER_COUNT_MODE_NORMAL: - cnt_mode = 0; + count_mode = 0; break; case COUNTER_COUNT_MODE_RANGE_LIMIT: - cnt_mode = 1; + count_mode = 1; break; case COUNTER_COUNT_MODE_NON_RECYCLE: - cnt_mode = 2; + count_mode = 2; break; case COUNTER_COUNT_MODE_MODULO_N: - cnt_mode = 3; + count_mode = 3; break; default: /* should never reach this path */ @@ -543,10 +532,10 @@ static int quad8_count_mode_set(struct counter_device *counter, mutex_lock(&priv->lock); - priv->count_mode[count->id] = cnt_mode; + priv->count_mode[count->id] = count_mode; /* Set count mode configuration value */ - mode_cfg = cnt_mode << 1; + mode_cfg = count_mode << 1; /* Add quadrature mode configuration */ if (priv->quadrature_mode[count->id]) @@ -560,56 +549,35 @@ static int quad8_count_mode_set(struct counter_device *counter, return 0; } -static struct counter_count_enum_ext quad8_cnt_mode_enum = { - .items = counter_count_mode_str, - .num_items = ARRAY_SIZE(counter_count_mode_str), - .get = quad8_count_mode_get, - .set = quad8_count_mode_set -}; - -static ssize_t quad8_count_direction_read(struct counter_device *counter, - struct counter_count *count, void *priv, char *buf) -{ - enum counter_count_direction dir; - - quad8_direction_get(counter, count, &dir); - - return sprintf(buf, "%s\n", counter_count_direction_str[dir]); -} - -static ssize_t quad8_count_enable_read(struct counter_device *counter, - struct counter_count *count, void *private, char *buf) +static int quad8_count_enable_read(struct counter_device *counter, + struct counter_count *count, u8 *enable) { const struct quad8 *const priv = counter->priv; - return sprintf(buf, "%u\n", priv->ab_enable[count->id]); + *enable = priv->ab_enable[count->id]; + + return 0; } -static ssize_t quad8_count_enable_write(struct counter_device *counter, - struct counter_count *count, void *private, const char *buf, size_t len) +static int quad8_count_enable_write(struct counter_device *counter, + struct counter_count *count, u8 enable) { struct quad8 *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id; - int err; - bool ab_enable; unsigned int ior_cfg; - err = kstrtobool(buf, &ab_enable); - if (err) - return err; - mutex_lock(&priv->lock); - priv->ab_enable[count->id] = ab_enable; + priv->ab_enable[count->id] = enable; - ior_cfg = ab_enable | priv->preset_enable[count->id] << 1; + ior_cfg = enable | priv->preset_enable[count->id] << 1; /* Load I/O control configuration */ outb(QUAD8_CTR_IOR | ior_cfg, base_offset + 1); mutex_unlock(&priv->lock); - return len; + return 0; } static const char *const quad8_noise_error_states[] = { @@ -618,7 +586,7 @@ static const char *const quad8_noise_error_states[] = { }; static int quad8_error_noise_get(struct counter_device *counter, - struct counter_count *count, size_t *noise_error) + struct counter_count *count, u32 *noise_error) { const struct quad8 *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id + 1; @@ -628,18 +596,14 @@ static int quad8_error_noise_get(struct counter_device *counter, return 0; } -static struct counter_count_enum_ext quad8_error_noise_enum = { - .items = quad8_noise_error_states, - .num_items = ARRAY_SIZE(quad8_noise_error_states), - .get = quad8_error_noise_get -}; - -static ssize_t quad8_count_preset_read(struct counter_device *counter, - struct counter_count *count, void *private, char *buf) +static int quad8_count_preset_read(struct counter_device *counter, + struct counter_count *count, u64 *preset) { const struct quad8 *const priv = counter->priv; - return sprintf(buf, "%u\n", priv->preset[count->id]); + *preset = priv->preset[count->id]; + + return 0; } static void quad8_preset_register_set(struct quad8 *const priv, const int id, @@ -658,16 +622,10 @@ static void quad8_preset_register_set(struct quad8 *const priv, const int id, outb(preset >> (8 * i), base_offset); } -static ssize_t quad8_count_preset_write(struct counter_device *counter, - struct counter_count *count, void *private, const char *buf, size_t len) +static int quad8_count_preset_write(struct counter_device *counter, + struct counter_count *count, u64 preset) { struct quad8 *const priv = counter->priv; - unsigned int preset; - int ret; - - ret = kstrtouint(buf, 0, &preset); - if (ret) - return ret; /* Only 24-bit values are supported */ if (preset > 0xFFFFFF) @@ -679,11 +637,11 @@ static ssize_t quad8_count_preset_write(struct counter_device *counter, mutex_unlock(&priv->lock); - return len; + return 0; } -static ssize_t quad8_count_ceiling_read(struct counter_device *counter, - struct counter_count *count, void *private, char *buf) +static int quad8_count_ceiling_read(struct counter_device *counter, + struct counter_count *count, u64 *ceiling) { struct quad8 *const priv = counter->priv; @@ -693,26 +651,23 @@ static ssize_t quad8_count_ceiling_read(struct counter_device *counter, switch (priv->count_mode[count->id]) { case 1: case 3: - mutex_unlock(&priv->lock); - return sprintf(buf, "%u\n", priv->preset[count->id]); + *ceiling = priv->preset[count->id]; + break; + default: + /* By default 0x1FFFFFF (25 bits unsigned) is maximum count */ + *ceiling = 0x1FFFFFF; + break; } mutex_unlock(&priv->lock); - /* By default 0x1FFFFFF (25 bits unsigned) is maximum count */ - return sprintf(buf, "33554431\n"); + return 0; } -static ssize_t quad8_count_ceiling_write(struct counter_device *counter, - struct counter_count *count, void *private, const char *buf, size_t len) +static int quad8_count_ceiling_write(struct counter_device *counter, + struct counter_count *count, u64 ceiling) { struct quad8 *const priv = counter->priv; - unsigned int ceiling; - int ret; - - ret = kstrtouint(buf, 0, &ceiling); - if (ret) - return ret; /* Only 24-bit values are supported */ if (ceiling > 0xFFFFFF) @@ -726,7 +681,7 @@ static ssize_t quad8_count_ceiling_write(struct counter_device *counter, case 3: quad8_preset_register_set(priv, count->id, ceiling); mutex_unlock(&priv->lock); - return len; + return 0; } mutex_unlock(&priv->lock); @@ -734,27 +689,25 @@ static ssize_t quad8_count_ceiling_write(struct counter_device *counter, return -EINVAL; } -static ssize_t quad8_count_preset_enable_read(struct counter_device *counter, - struct counter_count *count, void *private, char *buf) +static int quad8_count_preset_enable_read(struct counter_device *counter, + struct counter_count *count, + u8 *preset_enable) { const struct quad8 *const priv = counter->priv; - return sprintf(buf, "%u\n", !priv->preset_enable[count->id]); + *preset_enable = !priv->preset_enable[count->id]; + + return 0; } -static ssize_t quad8_count_preset_enable_write(struct counter_device *counter, - struct counter_count *count, void *private, const char *buf, size_t len) +static int quad8_count_preset_enable_write(struct counter_device *counter, + struct counter_count *count, + u8 preset_enable) { struct quad8 *const priv = counter->priv; const int base_offset = priv->base + 2 * count->id + 1; - bool preset_enable; - int ret; unsigned int ior_cfg; - ret = kstrtobool(buf, &preset_enable); - if (ret) - return ret; - /* Preset enable is active low in Input/Output Control register */ preset_enable = !preset_enable; @@ -762,25 +715,24 @@ static ssize_t quad8_count_preset_enable_write(struct counter_device *counter, priv->preset_enable[count->id] = preset_enable; - ior_cfg = priv->ab_enable[count->id] | (unsigned int)preset_enable << 1; + ior_cfg = priv->ab_enable[count->id] | preset_enable << 1; /* Load I/O control configuration to Input / Output Control Register */ outb(QUAD8_CTR_IOR | ior_cfg, base_offset); mutex_unlock(&priv->lock); - return len; + return 0; } -static ssize_t quad8_signal_cable_fault_read(struct counter_device *counter, - struct counter_signal *signal, - void *private, char *buf) +static int quad8_signal_cable_fault_read(struct counter_device *counter, + struct counter_signal *signal, + u8 *cable_fault) { struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id / 2; bool disabled; unsigned int status; - unsigned int fault; mutex_lock(&priv->lock); @@ -797,36 +749,31 @@ static ssize_t quad8_signal_cable_fault_read(struct counter_device *counter, mutex_unlock(&priv->lock); /* Mask respective channel and invert logic */ - fault = !(status & BIT(channel_id)); + *cable_fault = !(status & BIT(channel_id)); - return sprintf(buf, "%u\n", fault); + return 0; } -static ssize_t quad8_signal_cable_fault_enable_read( - struct counter_device *counter, struct counter_signal *signal, - void *private, char *buf) +static int quad8_signal_cable_fault_enable_read(struct counter_device *counter, + struct counter_signal *signal, + u8 *enable) { const struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id / 2; - const unsigned int enb = !!(priv->cable_fault_enable & BIT(channel_id)); - return sprintf(buf, "%u\n", enb); + *enable = !!(priv->cable_fault_enable & BIT(channel_id)); + + return 0; } -static ssize_t quad8_signal_cable_fault_enable_write( - struct counter_device *counter, struct counter_signal *signal, - void *private, const char *buf, size_t len) +static int quad8_signal_cable_fault_enable_write(struct counter_device *counter, + struct counter_signal *signal, + u8 enable) { struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id / 2; - bool enable; - int ret; unsigned int cable_fault_enable; - ret = kstrtobool(buf, &enable); - if (ret) - return ret; - mutex_lock(&priv->lock); if (enable) @@ -841,31 +788,27 @@ static ssize_t quad8_signal_cable_fault_enable_write( mutex_unlock(&priv->lock); - return len; + return 0; } -static ssize_t quad8_signal_fck_prescaler_read(struct counter_device *counter, - struct counter_signal *signal, void *private, char *buf) +static int quad8_signal_fck_prescaler_read(struct counter_device *counter, + struct counter_signal *signal, + u8 *prescaler) { const struct quad8 *const priv = counter->priv; - const size_t channel_id = signal->id / 2; - return sprintf(buf, "%u\n", priv->fck_prescaler[channel_id]); + *prescaler = priv->fck_prescaler[signal->id / 2]; + + return 0; } -static ssize_t quad8_signal_fck_prescaler_write(struct counter_device *counter, - struct counter_signal *signal, void *private, const char *buf, - size_t len) +static int quad8_signal_fck_prescaler_write(struct counter_device *counter, + struct counter_signal *signal, + u8 prescaler) { struct quad8 *const priv = counter->priv; const size_t channel_id = signal->id / 2; const int base_offset = priv->base + 2 * channel_id; - u8 prescaler; - int ret; - - ret = kstrtou8(buf, 0, &prescaler); - if (ret) - return ret; mutex_lock(&priv->lock); @@ -881,31 +824,30 @@ static ssize_t quad8_signal_fck_prescaler_write(struct counter_device *counter, mutex_unlock(&priv->lock); - return len; + return 0; } -static const struct counter_signal_ext quad8_signal_ext[] = { - { - .name = "cable_fault", - .read = quad8_signal_cable_fault_read - }, - { - .name = "cable_fault_enable", - .read = quad8_signal_cable_fault_enable_read, - .write = quad8_signal_cable_fault_enable_write - }, - { - .name = "filter_clock_prescaler", - .read = quad8_signal_fck_prescaler_read, - .write = quad8_signal_fck_prescaler_write - } +static struct counter_comp quad8_signal_ext[] = { + COUNTER_COMP_SIGNAL_BOOL("cable_fault", quad8_signal_cable_fault_read, + NULL), + COUNTER_COMP_SIGNAL_BOOL("cable_fault_enable", + quad8_signal_cable_fault_enable_read, + quad8_signal_cable_fault_enable_write), + COUNTER_COMP_SIGNAL_U8("filter_clock_prescaler", + quad8_signal_fck_prescaler_read, + quad8_signal_fck_prescaler_write) }; -static const struct counter_signal_ext quad8_index_ext[] = { - COUNTER_SIGNAL_ENUM("index_polarity", &quad8_index_pol_enum), - COUNTER_SIGNAL_ENUM_AVAILABLE("index_polarity", &quad8_index_pol_enum), - COUNTER_SIGNAL_ENUM("synchronous_mode", &quad8_syn_mode_enum), - COUNTER_SIGNAL_ENUM_AVAILABLE("synchronous_mode", &quad8_syn_mode_enum) +static DEFINE_COUNTER_ENUM(quad8_index_pol_enum, quad8_index_polarity_modes); +static DEFINE_COUNTER_ENUM(quad8_synch_mode_enum, quad8_synchronous_modes); + +static struct counter_comp quad8_index_ext[] = { + COUNTER_COMP_SIGNAL_ENUM("index_polarity", quad8_index_polarity_get, + quad8_index_polarity_set, + quad8_index_pol_enum), + COUNTER_COMP_SIGNAL_ENUM("synchronous_mode", quad8_synchronous_mode_get, + quad8_synchronous_mode_set, + quad8_synch_mode_enum), }; #define QUAD8_QUAD_SIGNAL(_id, _name) { \ @@ -974,39 +916,30 @@ static struct counter_synapse quad8_count_synapses[][3] = { QUAD8_COUNT_SYNAPSES(6), QUAD8_COUNT_SYNAPSES(7) }; -static const struct counter_count_ext quad8_count_ext[] = { - { - .name = "ceiling", - .read = quad8_count_ceiling_read, - .write = quad8_count_ceiling_write - }, - { - .name = "floor", - .read = quad8_count_floor_read - }, - COUNTER_COUNT_ENUM("count_mode", &quad8_cnt_mode_enum), - COUNTER_COUNT_ENUM_AVAILABLE("count_mode", &quad8_cnt_mode_enum), - { - .name = "direction", - .read = quad8_count_direction_read - }, - { - .name = "enable", - .read = quad8_count_enable_read, - .write = quad8_count_enable_write - }, - COUNTER_COUNT_ENUM("error_noise", &quad8_error_noise_enum), - COUNTER_COUNT_ENUM_AVAILABLE("error_noise", &quad8_error_noise_enum), - { - .name = "preset", - .read = quad8_count_preset_read, - .write = quad8_count_preset_write - }, - { - .name = "preset_enable", - .read = quad8_count_preset_enable_read, - .write = quad8_count_preset_enable_write - } +static const enum counter_count_mode quad8_cnt_modes[] = { + COUNTER_COUNT_MODE_NORMAL, + COUNTER_COUNT_MODE_RANGE_LIMIT, + COUNTER_COUNT_MODE_NON_RECYCLE, + COUNTER_COUNT_MODE_MODULO_N, +}; + +static DEFINE_COUNTER_AVAILABLE(quad8_count_mode_available, quad8_cnt_modes); + +static DEFINE_COUNTER_ENUM(quad8_error_noise_enum, quad8_noise_error_states); + +static struct counter_comp quad8_count_ext[] = { + COUNTER_COMP_CEILING(quad8_count_ceiling_read, + quad8_count_ceiling_write), + COUNTER_COMP_FLOOR(quad8_count_floor_read, NULL), + COUNTER_COMP_COUNT_MODE(quad8_count_mode_read, quad8_count_mode_write, + quad8_count_mode_available), + COUNTER_COMP_DIRECTION(quad8_direction_read), + COUNTER_COMP_ENABLE(quad8_count_enable_read, quad8_count_enable_write), + COUNTER_COMP_COUNT_ENUM("error_noise", quad8_error_noise_get, NULL, + quad8_error_noise_enum), + COUNTER_COMP_PRESET(quad8_count_preset_read, quad8_count_preset_write), + COUNTER_COMP_PRESET_ENABLE(quad8_count_preset_enable_read, + quad8_count_preset_enable_write), }; #define QUAD8_COUNT(_id, _cntname) { \ diff --git a/drivers/counter/Makefile b/drivers/counter/Makefile index 19742e6f5e3e..1ab7e087fdc2 100644 --- a/drivers/counter/Makefile +++ b/drivers/counter/Makefile @@ -4,6 +4,7 @@ # obj-$(CONFIG_COUNTER) += counter.o +counter-y := counter-core.o counter-sysfs.o obj-$(CONFIG_104_QUAD_8) += 104-quad-8.o obj-$(CONFIG_INTERRUPT_CNT) += interrupt-cnt.o diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c new file mode 100644 index 000000000000..c533a6ff12cf --- /dev/null +++ b/drivers/counter/counter-core.c @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic Counter interface + * Copyright (C) 2020 William Breathitt Gray + */ +#include +#include +#include +#include +#include +#include +#include + +#include "counter-sysfs.h" + +/* Provides a unique ID for each counter device */ +static DEFINE_IDA(counter_ida); + +static void counter_device_release(struct device *dev) +{ + ida_free(&counter_ida, dev->id); +} + +static struct device_type counter_device_type = { + .name = "counter_device", + .release = counter_device_release, +}; + +static struct bus_type counter_bus_type = { + .name = "counter", + .dev_name = "counter", +}; + +/** + * counter_register - register Counter to the system + * @counter: pointer to Counter to register + * + * This function registers a Counter to the system. A sysfs "counter" directory + * will be created and populated with sysfs attributes correlating with the + * Counter Signals, Synapses, and Counts respectively. + */ +int counter_register(struct counter_device *const counter) +{ + struct device *const dev = &counter->dev; + int id; + int err; + + /* Acquire unique ID */ + id = ida_alloc(&counter_ida, GFP_KERNEL); + if (id < 0) + return id; + + /* Configure device structure for Counter */ + dev->id = id; + dev->type = &counter_device_type; + dev->bus = &counter_bus_type; + if (counter->parent) { + dev->parent = counter->parent; + dev->of_node = counter->parent->of_node; + } + device_initialize(dev); + dev_set_drvdata(dev, counter); + + /* Add Counter sysfs attributes */ + err = counter_sysfs_add(counter); + if (err < 0) + goto err_free_id; + + /* Add device to system */ + err = device_add(dev); + if (err < 0) + goto err_free_id; + + return 0; + +err_free_id: + put_device(dev); + return err; +} +EXPORT_SYMBOL_GPL(counter_register); + +/** + * counter_unregister - unregister Counter from the system + * @counter: pointer to Counter to unregister + * + * The Counter is unregistered from the system. + */ +void counter_unregister(struct counter_device *const counter) +{ + if (!counter) + return; + + device_unregister(&counter->dev); +} +EXPORT_SYMBOL_GPL(counter_unregister); + +static void devm_counter_release(void *counter) +{ + counter_unregister(counter); +} + +/** + * devm_counter_register - Resource-managed counter_register + * @dev: device to allocate counter_device for + * @counter: pointer to Counter to register + * + * Managed counter_register. The Counter registered with this function is + * automatically unregistered on driver detach. This function calls + * counter_register internally. Refer to that function for more information. + * + * RETURNS: + * 0 on success, negative error number on failure. + */ +int devm_counter_register(struct device *dev, + struct counter_device *const counter) +{ + int err; + + err = counter_register(counter); + if (err < 0) + return err; + + return devm_add_action_or_reset(dev, devm_counter_release, counter); +} +EXPORT_SYMBOL_GPL(devm_counter_register); + +static int __init counter_init(void) +{ + return bus_register(&counter_bus_type); +} + +static void __exit counter_exit(void) +{ + bus_unregister(&counter_bus_type); +} + +subsys_initcall(counter_init); +module_exit(counter_exit); + +MODULE_AUTHOR("William Breathitt Gray "); +MODULE_DESCRIPTION("Generic Counter interface"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/counter/counter-sysfs.c b/drivers/counter/counter-sysfs.c new file mode 100644 index 000000000000..108cbd838eb9 --- /dev/null +++ b/drivers/counter/counter-sysfs.c @@ -0,0 +1,849 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic Counter sysfs interface + * Copyright (C) 2020 William Breathitt Gray + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "counter-sysfs.h" + +/** + * struct counter_attribute - Counter sysfs attribute + * @dev_attr: device attribute for sysfs + * @l: node to add Counter attribute to attribute group list + * @comp: Counter component callbacks and data + * @scope: Counter scope of the attribute + * @parent: pointer to the parent component + */ +struct counter_attribute { + struct device_attribute dev_attr; + struct list_head l; + + struct counter_comp comp; + enum counter_scope scope; + void *parent; +}; + +#define to_counter_attribute(_dev_attr) \ + container_of(_dev_attr, struct counter_attribute, dev_attr) + +/** + * struct counter_attribute_group - container for attribute group + * @name: name of the attribute group + * @attr_list: list to keep track of created attributes + * @num_attr: number of attributes + */ +struct counter_attribute_group { + const char *name; + struct list_head attr_list; + size_t num_attr; +}; + +static const char *const counter_function_str[] = { + [COUNTER_FUNCTION_INCREASE] = "increase", + [COUNTER_FUNCTION_DECREASE] = "decrease", + [COUNTER_FUNCTION_PULSE_DIRECTION] = "pulse-direction", + [COUNTER_FUNCTION_QUADRATURE_X1_A] = "quadrature x1 a", + [COUNTER_FUNCTION_QUADRATURE_X1_B] = "quadrature x1 b", + [COUNTER_FUNCTION_QUADRATURE_X2_A] = "quadrature x2 a", + [COUNTER_FUNCTION_QUADRATURE_X2_B] = "quadrature x2 b", + [COUNTER_FUNCTION_QUADRATURE_X4] = "quadrature x4" +}; + +static const char *const counter_signal_value_str[] = { + [COUNTER_SIGNAL_LEVEL_LOW] = "low", + [COUNTER_SIGNAL_LEVEL_HIGH] = "high" +}; + +static const char *const counter_synapse_action_str[] = { + [COUNTER_SYNAPSE_ACTION_NONE] = "none", + [COUNTER_SYNAPSE_ACTION_RISING_EDGE] = "rising edge", + [COUNTER_SYNAPSE_ACTION_FALLING_EDGE] = "falling edge", + [COUNTER_SYNAPSE_ACTION_BOTH_EDGES] = "both edges" +}; + +static const char *const counter_count_direction_str[] = { + [COUNTER_COUNT_DIRECTION_FORWARD] = "forward", + [COUNTER_COUNT_DIRECTION_BACKWARD] = "backward" +}; + +static const char *const counter_count_mode_str[] = { + [COUNTER_COUNT_MODE_NORMAL] = "normal", + [COUNTER_COUNT_MODE_RANGE_LIMIT] = "range limit", + [COUNTER_COUNT_MODE_NON_RECYCLE] = "non-recycle", + [COUNTER_COUNT_MODE_MODULO_N] = "modulo-n" +}; + +static ssize_t counter_comp_u8_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + struct counter_device *const counter = dev_get_drvdata(dev); + int err; + u8 data = 0; + + switch (a->scope) { + case COUNTER_SCOPE_DEVICE: + err = a->comp.device_u8_read(counter, &data); + break; + case COUNTER_SCOPE_SIGNAL: + err = a->comp.signal_u8_read(counter, a->parent, &data); + break; + case COUNTER_SCOPE_COUNT: + err = a->comp.count_u8_read(counter, a->parent, &data); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + if (a->comp.type == COUNTER_COMP_BOOL) + /* data should already be boolean but ensure just to be safe */ + data = !!data; + + return sprintf(buf, "%u\n", (unsigned int)data); +} + +static ssize_t counter_comp_u8_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + struct counter_device *const counter = dev_get_drvdata(dev); + int err; + bool bool_data = 0; + u8 data = 0; + + if (a->comp.type == COUNTER_COMP_BOOL) { + err = kstrtobool(buf, &bool_data); + data = bool_data; + } else + err = kstrtou8(buf, 0, &data); + if (err < 0) + return err; + + switch (a->scope) { + case COUNTER_SCOPE_DEVICE: + err = a->comp.device_u8_write(counter, data); + break; + case COUNTER_SCOPE_SIGNAL: + err = a->comp.signal_u8_write(counter, a->parent, data); + break; + case COUNTER_SCOPE_COUNT: + err = a->comp.count_u8_write(counter, a->parent, data); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + return len; +} + +static ssize_t counter_comp_u32_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + struct counter_device *const counter = dev_get_drvdata(dev); + const struct counter_available *const avail = a->comp.priv; + int err; + u32 data = 0; + + switch (a->scope) { + case COUNTER_SCOPE_DEVICE: + err = a->comp.device_u32_read(counter, &data); + break; + case COUNTER_SCOPE_SIGNAL: + err = a->comp.signal_u32_read(counter, a->parent, &data); + break; + case COUNTER_SCOPE_COUNT: + if (a->comp.type == COUNTER_COMP_SYNAPSE_ACTION) + err = a->comp.action_read(counter, a->parent, + a->comp.priv, &data); + else + err = a->comp.count_u32_read(counter, a->parent, &data); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + switch (a->comp.type) { + case COUNTER_COMP_FUNCTION: + return sysfs_emit(buf, "%s\n", counter_function_str[data]); + case COUNTER_COMP_SIGNAL_LEVEL: + return sysfs_emit(buf, "%s\n", counter_signal_value_str[data]); + case COUNTER_COMP_SYNAPSE_ACTION: + return sysfs_emit(buf, "%s\n", counter_synapse_action_str[data]); + case COUNTER_COMP_ENUM: + return sysfs_emit(buf, "%s\n", avail->strs[data]); + case COUNTER_COMP_COUNT_DIRECTION: + return sysfs_emit(buf, "%s\n", counter_count_direction_str[data]); + case COUNTER_COMP_COUNT_MODE: + return sysfs_emit(buf, "%s\n", counter_count_mode_str[data]); + default: + return sprintf(buf, "%u\n", (unsigned int)data); + } +} + +static int counter_find_enum(u32 *const enum_item, const u32 *const enums, + const size_t num_enums, const char *const buf, + const char *const string_array[]) +{ + size_t index; + + for (index = 0; index < num_enums; index++) { + *enum_item = enums[index]; + if (sysfs_streq(buf, string_array[*enum_item])) + return 0; + } + + return -EINVAL; +} + +static ssize_t counter_comp_u32_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + struct counter_device *const counter = dev_get_drvdata(dev); + struct counter_count *const count = a->parent; + struct counter_synapse *const synapse = a->comp.priv; + const struct counter_available *const avail = a->comp.priv; + int err; + u32 data = 0; + + switch (a->comp.type) { + case COUNTER_COMP_FUNCTION: + err = counter_find_enum(&data, count->functions_list, + count->num_functions, buf, + counter_function_str); + break; + case COUNTER_COMP_SYNAPSE_ACTION: + err = counter_find_enum(&data, synapse->actions_list, + synapse->num_actions, buf, + counter_synapse_action_str); + break; + case COUNTER_COMP_ENUM: + err = __sysfs_match_string(avail->strs, avail->num_items, buf); + data = err; + break; + case COUNTER_COMP_COUNT_MODE: + err = counter_find_enum(&data, avail->enums, avail->num_items, + buf, counter_count_mode_str); + break; + default: + err = kstrtou32(buf, 0, &data); + break; + } + if (err < 0) + return err; + + switch (a->scope) { + case COUNTER_SCOPE_DEVICE: + err = a->comp.device_u32_write(counter, data); + break; + case COUNTER_SCOPE_SIGNAL: + err = a->comp.signal_u32_write(counter, a->parent, data); + break; + case COUNTER_SCOPE_COUNT: + if (a->comp.type == COUNTER_COMP_SYNAPSE_ACTION) + err = a->comp.action_write(counter, count, synapse, + data); + else + err = a->comp.count_u32_write(counter, count, data); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + return len; +} + +static ssize_t counter_comp_u64_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + struct counter_device *const counter = dev_get_drvdata(dev); + int err; + u64 data = 0; + + switch (a->scope) { + case COUNTER_SCOPE_DEVICE: + err = a->comp.device_u64_read(counter, &data); + break; + case COUNTER_SCOPE_SIGNAL: + err = a->comp.signal_u64_read(counter, a->parent, &data); + break; + case COUNTER_SCOPE_COUNT: + err = a->comp.count_u64_read(counter, a->parent, &data); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + return sprintf(buf, "%llu\n", (unsigned long long)data); +} + +static ssize_t counter_comp_u64_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + struct counter_device *const counter = dev_get_drvdata(dev); + int err; + u64 data = 0; + + err = kstrtou64(buf, 0, &data); + if (err < 0) + return err; + + switch (a->scope) { + case COUNTER_SCOPE_DEVICE: + err = a->comp.device_u64_write(counter, data); + break; + case COUNTER_SCOPE_SIGNAL: + err = a->comp.signal_u64_write(counter, a->parent, data); + break; + case COUNTER_SCOPE_COUNT: + err = a->comp.count_u64_write(counter, a->parent, data); + break; + default: + return -EINVAL; + } + if (err < 0) + return err; + + return len; +} + +static ssize_t enums_available_show(const u32 *const enums, + const size_t num_enums, + const char *const strs[], char *buf) +{ + size_t len = 0; + size_t index; + + for (index = 0; index < num_enums; index++) + len += sysfs_emit_at(buf, len, "%s\n", strs[enums[index]]); + + return len; +} + +static ssize_t strs_available_show(const struct counter_available *const avail, + char *buf) +{ + size_t len = 0; + size_t index; + + for (index = 0; index < avail->num_items; index++) + len += sysfs_emit_at(buf, len, "%s\n", avail->strs[index]); + + return len; +} + +static ssize_t counter_comp_available_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + const struct counter_attribute *const a = to_counter_attribute(attr); + const struct counter_count *const count = a->parent; + const struct counter_synapse *const synapse = a->comp.priv; + const struct counter_available *const avail = a->comp.priv; + + switch (a->comp.type) { + case COUNTER_COMP_FUNCTION: + return enums_available_show(count->functions_list, + count->num_functions, + counter_function_str, buf); + case COUNTER_COMP_SYNAPSE_ACTION: + return enums_available_show(synapse->actions_list, + synapse->num_actions, + counter_synapse_action_str, buf); + case COUNTER_COMP_ENUM: + return strs_available_show(avail, buf); + case COUNTER_COMP_COUNT_MODE: + return enums_available_show(avail->enums, avail->num_items, + counter_count_mode_str, buf); + default: + return -EINVAL; + } +} + +static int counter_avail_attr_create(struct device *const dev, + struct counter_attribute_group *const group, + const struct counter_comp *const comp, void *const parent) +{ + struct counter_attribute *counter_attr; + struct device_attribute *dev_attr; + + counter_attr = devm_kzalloc(dev, sizeof(*counter_attr), GFP_KERNEL); + if (!counter_attr) + return -ENOMEM; + + /* Configure Counter attribute */ + counter_attr->comp.type = comp->type; + counter_attr->comp.priv = comp->priv; + counter_attr->parent = parent; + + /* Initialize sysfs attribute */ + dev_attr = &counter_attr->dev_attr; + sysfs_attr_init(&dev_attr->attr); + + /* Configure device attribute */ + dev_attr->attr.name = devm_kasprintf(dev, GFP_KERNEL, "%s_available", + comp->name); + if (!dev_attr->attr.name) + return -ENOMEM; + dev_attr->attr.mode = 0444; + dev_attr->show = counter_comp_available_show; + + /* Store list node */ + list_add(&counter_attr->l, &group->attr_list); + group->num_attr++; + + return 0; +} + +static int counter_attr_create(struct device *const dev, + struct counter_attribute_group *const group, + const struct counter_comp *const comp, + const enum counter_scope scope, + void *const parent) +{ + struct counter_attribute *counter_attr; + struct device_attribute *dev_attr; + + counter_attr = devm_kzalloc(dev, sizeof(*counter_attr), GFP_KERNEL); + if (!counter_attr) + return -ENOMEM; + + /* Configure Counter attribute */ + counter_attr->comp = *comp; + counter_attr->scope = scope; + counter_attr->parent = parent; + + /* Configure device attribute */ + dev_attr = &counter_attr->dev_attr; + sysfs_attr_init(&dev_attr->attr); + dev_attr->attr.name = comp->name; + switch (comp->type) { + case COUNTER_COMP_U8: + case COUNTER_COMP_BOOL: + if (comp->device_u8_read) { + dev_attr->attr.mode |= 0444; + dev_attr->show = counter_comp_u8_show; + } + if (comp->device_u8_write) { + dev_attr->attr.mode |= 0200; + dev_attr->store = counter_comp_u8_store; + } + break; + case COUNTER_COMP_SIGNAL_LEVEL: + case COUNTER_COMP_FUNCTION: + case COUNTER_COMP_SYNAPSE_ACTION: + case COUNTER_COMP_ENUM: + case COUNTER_COMP_COUNT_DIRECTION: + case COUNTER_COMP_COUNT_MODE: + if (comp->device_u32_read) { + dev_attr->attr.mode |= 0444; + dev_attr->show = counter_comp_u32_show; + } + if (comp->device_u32_write) { + dev_attr->attr.mode |= 0200; + dev_attr->store = counter_comp_u32_store; + } + break; + case COUNTER_COMP_U64: + if (comp->device_u64_read) { + dev_attr->attr.mode |= 0444; + dev_attr->show = counter_comp_u64_show; + } + if (comp->device_u64_write) { + dev_attr->attr.mode |= 0200; + dev_attr->store = counter_comp_u64_store; + } + break; + default: + return -EINVAL; + } + + /* Store list node */ + list_add(&counter_attr->l, &group->attr_list); + group->num_attr++; + + /* Create "*_available" attribute if needed */ + switch (comp->type) { + case COUNTER_COMP_FUNCTION: + case COUNTER_COMP_SYNAPSE_ACTION: + case COUNTER_COMP_ENUM: + case COUNTER_COMP_COUNT_MODE: + return counter_avail_attr_create(dev, group, comp, parent); + default: + return 0; + } +} + +static ssize_t counter_comp_name_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", to_counter_attribute(attr)->comp.name); +} + +static int counter_name_attr_create(struct device *const dev, + struct counter_attribute_group *const group, + const char *const name) +{ + struct counter_attribute *counter_attr; + + counter_attr = devm_kzalloc(dev, sizeof(*counter_attr), GFP_KERNEL); + if (!counter_attr) + return -ENOMEM; + + /* Configure Counter attribute */ + counter_attr->comp.name = name; + + /* Configure device attribute */ + sysfs_attr_init(&counter_attr->dev_attr.attr); + counter_attr->dev_attr.attr.name = "name"; + counter_attr->dev_attr.attr.mode = 0444; + counter_attr->dev_attr.show = counter_comp_name_show; + + /* Store list node */ + list_add(&counter_attr->l, &group->attr_list); + group->num_attr++; + + return 0; +} + +static struct counter_comp counter_signal_comp = { + .type = COUNTER_COMP_SIGNAL_LEVEL, + .name = "signal", +}; + +static int counter_signal_attrs_create(struct counter_device *const counter, + struct counter_attribute_group *const cattr_group, + struct counter_signal *const signal) +{ + const enum counter_scope scope = COUNTER_SCOPE_SIGNAL; + struct device *const dev = &counter->dev; + int err; + struct counter_comp comp; + size_t i; + + /* Create main Signal attribute */ + comp = counter_signal_comp; + comp.signal_u32_read = counter->ops->signal_read; + err = counter_attr_create(dev, cattr_group, &comp, scope, signal); + if (err < 0) + return err; + + /* Create Signal name attribute */ + err = counter_name_attr_create(dev, cattr_group, signal->name); + if (err < 0) + return err; + + /* Create an attribute for each extension */ + for (i = 0; i < signal->num_ext; i++) { + err = counter_attr_create(dev, cattr_group, signal->ext + i, + scope, signal); + if (err < 0) + return err; + } + + return 0; +} + +static int counter_sysfs_signals_add(struct counter_device *const counter, + struct counter_attribute_group *const groups) +{ + size_t i; + int err; + + /* Add each Signal */ + for (i = 0; i < counter->num_signals; i++) { + /* Generate Signal attribute directory name */ + groups[i].name = devm_kasprintf(&counter->dev, GFP_KERNEL, + "signal%zu", i); + if (!groups[i].name) + return -ENOMEM; + + /* Create all attributes associated with Signal */ + err = counter_signal_attrs_create(counter, groups + i, + counter->signals + i); + if (err < 0) + return err; + } + + return 0; +} + +static int counter_sysfs_synapses_add(struct counter_device *const counter, + struct counter_attribute_group *const group, + struct counter_count *const count) +{ + size_t i; + + /* Add each Synapse */ + for (i = 0; i < count->num_synapses; i++) { + struct device *const dev = &counter->dev; + struct counter_synapse *synapse; + size_t id; + struct counter_comp comp; + int err; + + synapse = count->synapses + i; + + /* Generate Synapse action name */ + id = synapse->signal - counter->signals; + comp.name = devm_kasprintf(dev, GFP_KERNEL, "signal%zu_action", + id); + if (!comp.name) + return -ENOMEM; + + /* Create action attribute */ + comp.type = COUNTER_COMP_SYNAPSE_ACTION; + comp.action_read = counter->ops->action_read; + comp.action_write = counter->ops->action_write; + comp.priv = synapse; + err = counter_attr_create(dev, group, &comp, + COUNTER_SCOPE_COUNT, count); + if (err < 0) + return err; + } + + return 0; +} + +static struct counter_comp counter_count_comp = + COUNTER_COMP_COUNT_U64("count", NULL, NULL); + +static struct counter_comp counter_function_comp = { + .type = COUNTER_COMP_FUNCTION, + .name = "function", +}; + +static int counter_count_attrs_create(struct counter_device *const counter, + struct counter_attribute_group *const cattr_group, + struct counter_count *const count) +{ + const enum counter_scope scope = COUNTER_SCOPE_COUNT; + struct device *const dev = &counter->dev; + int err; + struct counter_comp comp; + size_t i; + + /* Create main Count attribute */ + comp = counter_count_comp; + comp.count_u64_read = counter->ops->count_read; + comp.count_u64_write = counter->ops->count_write; + err = counter_attr_create(dev, cattr_group, &comp, scope, count); + if (err < 0) + return err; + + /* Create Count name attribute */ + err = counter_name_attr_create(dev, cattr_group, count->name); + if (err < 0) + return err; + + /* Create Count function attribute */ + comp = counter_function_comp; + comp.count_u32_read = counter->ops->function_read; + comp.count_u32_write = counter->ops->function_write; + err = counter_attr_create(dev, cattr_group, &comp, scope, count); + if (err < 0) + return err; + + /* Create an attribute for each extension */ + for (i = 0; i < count->num_ext; i++) { + err = counter_attr_create(dev, cattr_group, count->ext + i, + scope, count); + if (err < 0) + return err; + } + + return 0; +} + +static int counter_sysfs_counts_add(struct counter_device *const counter, + struct counter_attribute_group *const groups) +{ + size_t i; + struct counter_count *count; + int err; + + /* Add each Count */ + for (i = 0; i < counter->num_counts; i++) { + count = counter->counts + i; + + /* Generate Count attribute directory name */ + groups[i].name = devm_kasprintf(&counter->dev, GFP_KERNEL, + "count%zu", i); + if (!groups[i].name) + return -ENOMEM; + + /* Add sysfs attributes of the Synapses */ + err = counter_sysfs_synapses_add(counter, groups + i, count); + if (err < 0) + return err; + + /* Create all attributes associated with Count */ + err = counter_count_attrs_create(counter, groups + i, count); + if (err < 0) + return err; + } + + return 0; +} + +static int counter_num_signals_read(struct counter_device *counter, u8 *val) +{ + *val = counter->num_signals; + return 0; +} + +static int counter_num_counts_read(struct counter_device *counter, u8 *val) +{ + *val = counter->num_counts; + return 0; +} + +static struct counter_comp counter_num_signals_comp = + COUNTER_COMP_DEVICE_U8("num_signals", counter_num_signals_read, NULL); + +static struct counter_comp counter_num_counts_comp = + COUNTER_COMP_DEVICE_U8("num_counts", counter_num_counts_read, NULL); + +static int counter_sysfs_attr_add(struct counter_device *const counter, + struct counter_attribute_group *cattr_group) +{ + const enum counter_scope scope = COUNTER_SCOPE_DEVICE; + struct device *const dev = &counter->dev; + int err; + size_t i; + + /* Add Signals sysfs attributes */ + err = counter_sysfs_signals_add(counter, cattr_group); + if (err < 0) + return err; + cattr_group += counter->num_signals; + + /* Add Counts sysfs attributes */ + err = counter_sysfs_counts_add(counter, cattr_group); + if (err < 0) + return err; + cattr_group += counter->num_counts; + + /* Create name attribute */ + err = counter_name_attr_create(dev, cattr_group, counter->name); + if (err < 0) + return err; + + /* Create num_signals attribute */ + err = counter_attr_create(dev, cattr_group, &counter_num_signals_comp, + scope, NULL); + if (err < 0) + return err; + + /* Create num_counts attribute */ + err = counter_attr_create(dev, cattr_group, &counter_num_counts_comp, + scope, NULL); + if (err < 0) + return err; + + /* Create an attribute for each extension */ + for (i = 0; i < counter->num_ext; i++) { + err = counter_attr_create(dev, cattr_group, counter->ext + i, + scope, NULL); + if (err < 0) + return err; + } + + return 0; +} + +/** + * counter_sysfs_add - Adds Counter sysfs attributes to the device structure + * @counter: Pointer to the Counter device structure + * + * Counter sysfs attributes are created and added to the respective device + * structure for later registration to the system. Resource-managed memory + * allocation is performed by this function, and this memory should be freed + * when no longer needed (automatically by a device_unregister call, or + * manually by a devres_release_all call). + */ +int counter_sysfs_add(struct counter_device *const counter) +{ + struct device *const dev = &counter->dev; + const size_t num_groups = counter->num_signals + counter->num_counts + 1; + struct counter_attribute_group *cattr_groups; + size_t i, j; + int err; + struct attribute_group *groups; + struct counter_attribute *p; + + /* Allocate space for attribute groups (signals, counts, and ext) */ + cattr_groups = devm_kcalloc(dev, num_groups, sizeof(*cattr_groups), + GFP_KERNEL); + if (!cattr_groups) + return -ENOMEM; + + /* Initialize attribute lists */ + for (i = 0; i < num_groups; i++) + INIT_LIST_HEAD(&cattr_groups[i].attr_list); + + /* Add Counter device sysfs attributes */ + err = counter_sysfs_attr_add(counter, cattr_groups); + if (err < 0) + return err; + + /* Allocate attribute group pointers for association with device */ + dev->groups = devm_kcalloc(dev, num_groups + 1, sizeof(*dev->groups), + GFP_KERNEL); + if (!dev->groups) + return -ENOMEM; + + /* Allocate space for attribute groups */ + groups = devm_kcalloc(dev, num_groups, sizeof(*groups), GFP_KERNEL); + if (!groups) + return -ENOMEM; + + /* Prepare each group of attributes for association */ + for (i = 0; i < num_groups; i++) { + groups[i].name = cattr_groups[i].name; + + /* Allocate space for attribute pointers */ + groups[i].attrs = devm_kcalloc(dev, + cattr_groups[i].num_attr + 1, + sizeof(*groups[i].attrs), + GFP_KERNEL); + if (!groups[i].attrs) + return -ENOMEM; + + /* Add attribute pointers to attribute group */ + j = 0; + list_for_each_entry(p, &cattr_groups[i].attr_list, l) + groups[i].attrs[j++] = &p->dev_attr.attr; + + /* Associate attribute group */ + dev->groups[i] = &groups[i]; + } + + return 0; +} diff --git a/drivers/counter/counter-sysfs.h b/drivers/counter/counter-sysfs.h new file mode 100644 index 000000000000..14fe566aca0e --- /dev/null +++ b/drivers/counter/counter-sysfs.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Counter sysfs interface + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _COUNTER_SYSFS_H_ +#define _COUNTER_SYSFS_H_ + +#include + +int counter_sysfs_add(struct counter_device *const counter); + +#endif /* _COUNTER_SYSFS_H_ */ diff --git a/drivers/counter/counter.c b/drivers/counter/counter.c deleted file mode 100644 index de921e8a3f72..000000000000 --- a/drivers/counter/counter.c +++ /dev/null @@ -1,1496 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Generic Counter interface - * Copyright (C) 2018 William Breathitt Gray - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -const char *const counter_count_direction_str[2] = { - [COUNTER_COUNT_DIRECTION_FORWARD] = "forward", - [COUNTER_COUNT_DIRECTION_BACKWARD] = "backward" -}; -EXPORT_SYMBOL_GPL(counter_count_direction_str); - -const char *const counter_count_mode_str[4] = { - [COUNTER_COUNT_MODE_NORMAL] = "normal", - [COUNTER_COUNT_MODE_RANGE_LIMIT] = "range limit", - [COUNTER_COUNT_MODE_NON_RECYCLE] = "non-recycle", - [COUNTER_COUNT_MODE_MODULO_N] = "modulo-n" -}; -EXPORT_SYMBOL_GPL(counter_count_mode_str); - -ssize_t counter_signal_enum_read(struct counter_device *counter, - struct counter_signal *signal, void *priv, - char *buf) -{ - const struct counter_signal_enum_ext *const e = priv; - int err; - size_t index; - - if (!e->get) - return -EINVAL; - - err = e->get(counter, signal, &index); - if (err) - return err; - - if (index >= e->num_items) - return -EINVAL; - - return sprintf(buf, "%s\n", e->items[index]); -} -EXPORT_SYMBOL_GPL(counter_signal_enum_read); - -ssize_t counter_signal_enum_write(struct counter_device *counter, - struct counter_signal *signal, void *priv, - const char *buf, size_t len) -{ - const struct counter_signal_enum_ext *const e = priv; - ssize_t index; - int err; - - if (!e->set) - return -EINVAL; - - index = __sysfs_match_string(e->items, e->num_items, buf); - if (index < 0) - return index; - - err = e->set(counter, signal, index); - if (err) - return err; - - return len; -} -EXPORT_SYMBOL_GPL(counter_signal_enum_write); - -ssize_t counter_signal_enum_available_read(struct counter_device *counter, - struct counter_signal *signal, - void *priv, char *buf) -{ - const struct counter_signal_enum_ext *const e = priv; - size_t i; - size_t len = 0; - - if (!e->num_items) - return 0; - - for (i = 0; i < e->num_items; i++) - len += sprintf(buf + len, "%s\n", e->items[i]); - - return len; -} -EXPORT_SYMBOL_GPL(counter_signal_enum_available_read); - -ssize_t counter_count_enum_read(struct counter_device *counter, - struct counter_count *count, void *priv, - char *buf) -{ - const struct counter_count_enum_ext *const e = priv; - int err; - size_t index; - - if (!e->get) - return -EINVAL; - - err = e->get(counter, count, &index); - if (err) - return err; - - if (index >= e->num_items) - return -EINVAL; - - return sprintf(buf, "%s\n", e->items[index]); -} -EXPORT_SYMBOL_GPL(counter_count_enum_read); - -ssize_t counter_count_enum_write(struct counter_device *counter, - struct counter_count *count, void *priv, - const char *buf, size_t len) -{ - const struct counter_count_enum_ext *const e = priv; - ssize_t index; - int err; - - if (!e->set) - return -EINVAL; - - index = __sysfs_match_string(e->items, e->num_items, buf); - if (index < 0) - return index; - - err = e->set(counter, count, index); - if (err) - return err; - - return len; -} -EXPORT_SYMBOL_GPL(counter_count_enum_write); - -ssize_t counter_count_enum_available_read(struct counter_device *counter, - struct counter_count *count, - void *priv, char *buf) -{ - const struct counter_count_enum_ext *const e = priv; - size_t i; - size_t len = 0; - - if (!e->num_items) - return 0; - - for (i = 0; i < e->num_items; i++) - len += sprintf(buf + len, "%s\n", e->items[i]); - - return len; -} -EXPORT_SYMBOL_GPL(counter_count_enum_available_read); - -ssize_t counter_device_enum_read(struct counter_device *counter, void *priv, - char *buf) -{ - const struct counter_device_enum_ext *const e = priv; - int err; - size_t index; - - if (!e->get) - return -EINVAL; - - err = e->get(counter, &index); - if (err) - return err; - - if (index >= e->num_items) - return -EINVAL; - - return sprintf(buf, "%s\n", e->items[index]); -} -EXPORT_SYMBOL_GPL(counter_device_enum_read); - -ssize_t counter_device_enum_write(struct counter_device *counter, void *priv, - const char *buf, size_t len) -{ - const struct counter_device_enum_ext *const e = priv; - ssize_t index; - int err; - - if (!e->set) - return -EINVAL; - - index = __sysfs_match_string(e->items, e->num_items, buf); - if (index < 0) - return index; - - err = e->set(counter, index); - if (err) - return err; - - return len; -} -EXPORT_SYMBOL_GPL(counter_device_enum_write); - -ssize_t counter_device_enum_available_read(struct counter_device *counter, - void *priv, char *buf) -{ - const struct counter_device_enum_ext *const e = priv; - size_t i; - size_t len = 0; - - if (!e->num_items) - return 0; - - for (i = 0; i < e->num_items; i++) - len += sprintf(buf + len, "%s\n", e->items[i]); - - return len; -} -EXPORT_SYMBOL_GPL(counter_device_enum_available_read); - -struct counter_attr_parm { - struct counter_device_attr_group *group; - const char *prefix; - const char *name; - ssize_t (*show)(struct device *dev, struct device_attribute *attr, - char *buf); - ssize_t (*store)(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len); - void *component; -}; - -struct counter_device_attr { - struct device_attribute dev_attr; - struct list_head l; - void *component; -}; - -static int counter_attribute_create(const struct counter_attr_parm *const parm) -{ - struct counter_device_attr *counter_attr; - struct device_attribute *dev_attr; - int err; - struct list_head *const attr_list = &parm->group->attr_list; - - /* Allocate a Counter device attribute */ - counter_attr = kzalloc(sizeof(*counter_attr), GFP_KERNEL); - if (!counter_attr) - return -ENOMEM; - dev_attr = &counter_attr->dev_attr; - - sysfs_attr_init(&dev_attr->attr); - - /* Configure device attribute */ - dev_attr->attr.name = kasprintf(GFP_KERNEL, "%s%s", parm->prefix, - parm->name); - if (!dev_attr->attr.name) { - err = -ENOMEM; - goto err_free_counter_attr; - } - if (parm->show) { - dev_attr->attr.mode |= 0444; - dev_attr->show = parm->show; - } - if (parm->store) { - dev_attr->attr.mode |= 0200; - dev_attr->store = parm->store; - } - - /* Store associated Counter component with attribute */ - counter_attr->component = parm->component; - - /* Keep track of the attribute for later cleanup */ - list_add(&counter_attr->l, attr_list); - parm->group->num_attr++; - - return 0; - -err_free_counter_attr: - kfree(counter_attr); - return err; -} - -#define to_counter_attr(_dev_attr) \ - container_of(_dev_attr, struct counter_device_attr, dev_attr) - -struct counter_signal_unit { - struct counter_signal *signal; -}; - -static const char *const counter_signal_level_str[] = { - [COUNTER_SIGNAL_LEVEL_LOW] = "low", - [COUNTER_SIGNAL_LEVEL_HIGH] = "high" -}; - -static ssize_t counter_signal_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct counter_device *const counter = dev_get_drvdata(dev); - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_signal_unit *const component = devattr->component; - struct counter_signal *const signal = component->signal; - int err; - enum counter_signal_level level; - - err = counter->ops->signal_read(counter, signal, &level); - if (err) - return err; - - return sprintf(buf, "%s\n", counter_signal_level_str[level]); -} - -struct counter_name_unit { - const char *name; -}; - -static ssize_t counter_device_attr_name_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - const struct counter_name_unit *const comp = to_counter_attr(attr)->component; - - return sprintf(buf, "%s\n", comp->name); -} - -static int counter_name_attribute_create( - struct counter_device_attr_group *const group, - const char *const name) -{ - struct counter_name_unit *name_comp; - struct counter_attr_parm parm; - int err; - - /* Skip if no name */ - if (!name) - return 0; - - /* Allocate name attribute component */ - name_comp = kmalloc(sizeof(*name_comp), GFP_KERNEL); - if (!name_comp) - return -ENOMEM; - name_comp->name = name; - - /* Allocate Signal name attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = "name"; - parm.show = counter_device_attr_name_show; - parm.store = NULL; - parm.component = name_comp; - err = counter_attribute_create(&parm); - if (err) - goto err_free_name_comp; - - return 0; - -err_free_name_comp: - kfree(name_comp); - return err; -} - -struct counter_signal_ext_unit { - struct counter_signal *signal; - const struct counter_signal_ext *ext; -}; - -static ssize_t counter_signal_ext_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_signal_ext_unit *const comp = devattr->component; - const struct counter_signal_ext *const ext = comp->ext; - - return ext->read(dev_get_drvdata(dev), comp->signal, ext->priv, buf); -} - -static ssize_t counter_signal_ext_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_signal_ext_unit *const comp = devattr->component; - const struct counter_signal_ext *const ext = comp->ext; - - return ext->write(dev_get_drvdata(dev), comp->signal, ext->priv, buf, - len); -} - -static void counter_device_attr_list_free(struct list_head *attr_list) -{ - struct counter_device_attr *p, *n; - - list_for_each_entry_safe(p, n, attr_list, l) { - /* free attribute name and associated component memory */ - kfree(p->dev_attr.attr.name); - kfree(p->component); - list_del(&p->l); - kfree(p); - } -} - -static int counter_signal_ext_register( - struct counter_device_attr_group *const group, - struct counter_signal *const signal) -{ - const size_t num_ext = signal->num_ext; - size_t i; - const struct counter_signal_ext *ext; - struct counter_signal_ext_unit *signal_ext_comp; - struct counter_attr_parm parm; - int err; - - /* Create an attribute for each extension */ - for (i = 0 ; i < num_ext; i++) { - ext = signal->ext + i; - - /* Allocate signal_ext attribute component */ - signal_ext_comp = kmalloc(sizeof(*signal_ext_comp), GFP_KERNEL); - if (!signal_ext_comp) { - err = -ENOMEM; - goto err_free_attr_list; - } - signal_ext_comp->signal = signal; - signal_ext_comp->ext = ext; - - /* Allocate a Counter device attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = ext->name; - parm.show = (ext->read) ? counter_signal_ext_show : NULL; - parm.store = (ext->write) ? counter_signal_ext_store : NULL; - parm.component = signal_ext_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(signal_ext_comp); - goto err_free_attr_list; - } - } - - return 0; - -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -static int counter_signal_attributes_create( - struct counter_device_attr_group *const group, - const struct counter_device *const counter, - struct counter_signal *const signal) -{ - struct counter_signal_unit *signal_comp; - struct counter_attr_parm parm; - int err; - - /* Allocate Signal attribute component */ - signal_comp = kmalloc(sizeof(*signal_comp), GFP_KERNEL); - if (!signal_comp) - return -ENOMEM; - signal_comp->signal = signal; - - /* Create main Signal attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = "signal"; - parm.show = (counter->ops->signal_read) ? counter_signal_show : NULL; - parm.store = NULL; - parm.component = signal_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(signal_comp); - return err; - } - - /* Create Signal name attribute */ - err = counter_name_attribute_create(group, signal->name); - if (err) - goto err_free_attr_list; - - /* Register Signal extension attributes */ - err = counter_signal_ext_register(group, signal); - if (err) - goto err_free_attr_list; - - return 0; - -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -static int counter_signals_register( - struct counter_device_attr_group *const groups_list, - const struct counter_device *const counter) -{ - const size_t num_signals = counter->num_signals; - size_t i; - struct counter_signal *signal; - const char *name; - int err; - - /* Register each Signal */ - for (i = 0; i < num_signals; i++) { - signal = counter->signals + i; - - /* Generate Signal attribute directory name */ - name = kasprintf(GFP_KERNEL, "signal%d", signal->id); - if (!name) { - err = -ENOMEM; - goto err_free_attr_groups; - } - groups_list[i].attr_group.name = name; - - /* Create all attributes associated with Signal */ - err = counter_signal_attributes_create(groups_list + i, counter, - signal); - if (err) - goto err_free_attr_groups; - } - - return 0; - -err_free_attr_groups: - do { - kfree(groups_list[i].attr_group.name); - counter_device_attr_list_free(&groups_list[i].attr_list); - } while (i--); - return err; -} - -static const char *const counter_synapse_action_str[] = { - [COUNTER_SYNAPSE_ACTION_NONE] = "none", - [COUNTER_SYNAPSE_ACTION_RISING_EDGE] = "rising edge", - [COUNTER_SYNAPSE_ACTION_FALLING_EDGE] = "falling edge", - [COUNTER_SYNAPSE_ACTION_BOTH_EDGES] = "both edges" -}; - -struct counter_action_unit { - struct counter_synapse *synapse; - struct counter_count *count; -}; - -static ssize_t counter_action_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - int err; - struct counter_device *const counter = dev_get_drvdata(dev); - const struct counter_action_unit *const component = devattr->component; - struct counter_count *const count = component->count; - struct counter_synapse *const synapse = component->synapse; - size_t action_index; - enum counter_synapse_action action; - - err = counter->ops->action_get(counter, count, synapse, &action_index); - if (err) - return err; - - synapse->action = action_index; - - action = synapse->actions_list[action_index]; - return sprintf(buf, "%s\n", counter_synapse_action_str[action]); -} - -static ssize_t counter_action_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_action_unit *const component = devattr->component; - struct counter_synapse *const synapse = component->synapse; - size_t action_index; - const size_t num_actions = synapse->num_actions; - enum counter_synapse_action action; - int err; - struct counter_device *const counter = dev_get_drvdata(dev); - struct counter_count *const count = component->count; - - /* Find requested action mode */ - for (action_index = 0; action_index < num_actions; action_index++) { - action = synapse->actions_list[action_index]; - if (sysfs_streq(buf, counter_synapse_action_str[action])) - break; - } - /* If requested action mode not found */ - if (action_index >= num_actions) - return -EINVAL; - - err = counter->ops->action_set(counter, count, synapse, action_index); - if (err) - return err; - - synapse->action = action_index; - - return len; -} - -struct counter_action_avail_unit { - const enum counter_synapse_action *actions_list; - size_t num_actions; -}; - -static ssize_t counter_synapse_action_available_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_action_avail_unit *const component = devattr->component; - size_t i; - enum counter_synapse_action action; - ssize_t len = 0; - - for (i = 0; i < component->num_actions; i++) { - action = component->actions_list[i]; - len += sprintf(buf + len, "%s\n", - counter_synapse_action_str[action]); - } - - return len; -} - -static int counter_synapses_register( - struct counter_device_attr_group *const group, - const struct counter_device *const counter, - struct counter_count *const count, const char *const count_attr_name) -{ - size_t i; - struct counter_synapse *synapse; - const char *prefix; - struct counter_action_unit *action_comp; - struct counter_attr_parm parm; - int err; - struct counter_action_avail_unit *avail_comp; - - /* Register each Synapse */ - for (i = 0; i < count->num_synapses; i++) { - synapse = count->synapses + i; - - /* Generate attribute prefix */ - prefix = kasprintf(GFP_KERNEL, "signal%d_", - synapse->signal->id); - if (!prefix) { - err = -ENOMEM; - goto err_free_attr_list; - } - - /* Allocate action attribute component */ - action_comp = kmalloc(sizeof(*action_comp), GFP_KERNEL); - if (!action_comp) { - err = -ENOMEM; - goto err_free_prefix; - } - action_comp->synapse = synapse; - action_comp->count = count; - - /* Create action attribute */ - parm.group = group; - parm.prefix = prefix; - parm.name = "action"; - parm.show = (counter->ops->action_get) ? counter_action_show : NULL; - parm.store = (counter->ops->action_set) ? counter_action_store : NULL; - parm.component = action_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(action_comp); - goto err_free_prefix; - } - - /* Allocate action available attribute component */ - avail_comp = kmalloc(sizeof(*avail_comp), GFP_KERNEL); - if (!avail_comp) { - err = -ENOMEM; - goto err_free_prefix; - } - avail_comp->actions_list = synapse->actions_list; - avail_comp->num_actions = synapse->num_actions; - - /* Create action_available attribute */ - parm.group = group; - parm.prefix = prefix; - parm.name = "action_available"; - parm.show = counter_synapse_action_available_show; - parm.store = NULL; - parm.component = avail_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(avail_comp); - goto err_free_prefix; - } - - kfree(prefix); - } - - return 0; - -err_free_prefix: - kfree(prefix); -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -struct counter_count_unit { - struct counter_count *count; -}; - -static ssize_t counter_count_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct counter_device *const counter = dev_get_drvdata(dev); - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_count_unit *const component = devattr->component; - struct counter_count *const count = component->count; - int err; - unsigned long val; - - err = counter->ops->count_read(counter, count, &val); - if (err) - return err; - - return sprintf(buf, "%lu\n", val); -} - -static ssize_t counter_count_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - struct counter_device *const counter = dev_get_drvdata(dev); - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_count_unit *const component = devattr->component; - struct counter_count *const count = component->count; - int err; - unsigned long val; - - err = kstrtoul(buf, 0, &val); - if (err) - return err; - - err = counter->ops->count_write(counter, count, val); - if (err) - return err; - - return len; -} - -static const char *const counter_function_str[] = { - [COUNTER_FUNCTION_INCREASE] = "increase", - [COUNTER_FUNCTION_DECREASE] = "decrease", - [COUNTER_FUNCTION_PULSE_DIRECTION] = "pulse-direction", - [COUNTER_FUNCTION_QUADRATURE_X1_A] = "quadrature x1 a", - [COUNTER_FUNCTION_QUADRATURE_X1_B] = "quadrature x1 b", - [COUNTER_FUNCTION_QUADRATURE_X2_A] = "quadrature x2 a", - [COUNTER_FUNCTION_QUADRATURE_X2_B] = "quadrature x2 b", - [COUNTER_FUNCTION_QUADRATURE_X4] = "quadrature x4" -}; - -static ssize_t counter_function_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - int err; - struct counter_device *const counter = dev_get_drvdata(dev); - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_count_unit *const component = devattr->component; - struct counter_count *const count = component->count; - size_t func_index; - enum counter_function function; - - err = counter->ops->function_get(counter, count, &func_index); - if (err) - return err; - - count->function = func_index; - - function = count->functions_list[func_index]; - return sprintf(buf, "%s\n", counter_function_str[function]); -} - -static ssize_t counter_function_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_count_unit *const component = devattr->component; - struct counter_count *const count = component->count; - const size_t num_functions = count->num_functions; - size_t func_index; - enum counter_function function; - int err; - struct counter_device *const counter = dev_get_drvdata(dev); - - /* Find requested Count function mode */ - for (func_index = 0; func_index < num_functions; func_index++) { - function = count->functions_list[func_index]; - if (sysfs_streq(buf, counter_function_str[function])) - break; - } - /* Return error if requested Count function mode not found */ - if (func_index >= num_functions) - return -EINVAL; - - err = counter->ops->function_set(counter, count, func_index); - if (err) - return err; - - count->function = func_index; - - return len; -} - -struct counter_count_ext_unit { - struct counter_count *count; - const struct counter_count_ext *ext; -}; - -static ssize_t counter_count_ext_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_count_ext_unit *const comp = devattr->component; - const struct counter_count_ext *const ext = comp->ext; - - return ext->read(dev_get_drvdata(dev), comp->count, ext->priv, buf); -} - -static ssize_t counter_count_ext_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_count_ext_unit *const comp = devattr->component; - const struct counter_count_ext *const ext = comp->ext; - - return ext->write(dev_get_drvdata(dev), comp->count, ext->priv, buf, - len); -} - -static int counter_count_ext_register( - struct counter_device_attr_group *const group, - struct counter_count *const count) -{ - size_t i; - const struct counter_count_ext *ext; - struct counter_count_ext_unit *count_ext_comp; - struct counter_attr_parm parm; - int err; - - /* Create an attribute for each extension */ - for (i = 0 ; i < count->num_ext; i++) { - ext = count->ext + i; - - /* Allocate count_ext attribute component */ - count_ext_comp = kmalloc(sizeof(*count_ext_comp), GFP_KERNEL); - if (!count_ext_comp) { - err = -ENOMEM; - goto err_free_attr_list; - } - count_ext_comp->count = count; - count_ext_comp->ext = ext; - - /* Allocate count_ext attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = ext->name; - parm.show = (ext->read) ? counter_count_ext_show : NULL; - parm.store = (ext->write) ? counter_count_ext_store : NULL; - parm.component = count_ext_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(count_ext_comp); - goto err_free_attr_list; - } - } - - return 0; - -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -struct counter_func_avail_unit { - const enum counter_function *functions_list; - size_t num_functions; -}; - -static ssize_t counter_function_available_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_func_avail_unit *const component = devattr->component; - const enum counter_function *const func_list = component->functions_list; - const size_t num_functions = component->num_functions; - size_t i; - enum counter_function function; - ssize_t len = 0; - - for (i = 0; i < num_functions; i++) { - function = func_list[i]; - len += sprintf(buf + len, "%s\n", - counter_function_str[function]); - } - - return len; -} - -static int counter_count_attributes_create( - struct counter_device_attr_group *const group, - const struct counter_device *const counter, - struct counter_count *const count) -{ - struct counter_count_unit *count_comp; - struct counter_attr_parm parm; - int err; - struct counter_count_unit *func_comp; - struct counter_func_avail_unit *avail_comp; - - /* Allocate count attribute component */ - count_comp = kmalloc(sizeof(*count_comp), GFP_KERNEL); - if (!count_comp) - return -ENOMEM; - count_comp->count = count; - - /* Create main Count attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = "count"; - parm.show = (counter->ops->count_read) ? counter_count_show : NULL; - parm.store = (counter->ops->count_write) ? counter_count_store : NULL; - parm.component = count_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(count_comp); - return err; - } - - /* Allocate function attribute component */ - func_comp = kmalloc(sizeof(*func_comp), GFP_KERNEL); - if (!func_comp) { - err = -ENOMEM; - goto err_free_attr_list; - } - func_comp->count = count; - - /* Create Count function attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = "function"; - parm.show = (counter->ops->function_get) ? counter_function_show : NULL; - parm.store = (counter->ops->function_set) ? counter_function_store : NULL; - parm.component = func_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(func_comp); - goto err_free_attr_list; - } - - /* Allocate function available attribute component */ - avail_comp = kmalloc(sizeof(*avail_comp), GFP_KERNEL); - if (!avail_comp) { - err = -ENOMEM; - goto err_free_attr_list; - } - avail_comp->functions_list = count->functions_list; - avail_comp->num_functions = count->num_functions; - - /* Create Count function_available attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = "function_available"; - parm.show = counter_function_available_show; - parm.store = NULL; - parm.component = avail_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(avail_comp); - goto err_free_attr_list; - } - - /* Create Count name attribute */ - err = counter_name_attribute_create(group, count->name); - if (err) - goto err_free_attr_list; - - /* Register Count extension attributes */ - err = counter_count_ext_register(group, count); - if (err) - goto err_free_attr_list; - - return 0; - -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -static int counter_counts_register( - struct counter_device_attr_group *const groups_list, - const struct counter_device *const counter) -{ - size_t i; - struct counter_count *count; - const char *name; - int err; - - /* Register each Count */ - for (i = 0; i < counter->num_counts; i++) { - count = counter->counts + i; - - /* Generate Count attribute directory name */ - name = kasprintf(GFP_KERNEL, "count%d", count->id); - if (!name) { - err = -ENOMEM; - goto err_free_attr_groups; - } - groups_list[i].attr_group.name = name; - - /* Register the Synapses associated with each Count */ - err = counter_synapses_register(groups_list + i, counter, count, - name); - if (err) - goto err_free_attr_groups; - - /* Create all attributes associated with Count */ - err = counter_count_attributes_create(groups_list + i, counter, - count); - if (err) - goto err_free_attr_groups; - } - - return 0; - -err_free_attr_groups: - do { - kfree(groups_list[i].attr_group.name); - counter_device_attr_list_free(&groups_list[i].attr_list); - } while (i--); - return err; -} - -struct counter_size_unit { - size_t size; -}; - -static ssize_t counter_device_attr_size_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - const struct counter_size_unit *const comp = to_counter_attr(attr)->component; - - return sprintf(buf, "%zu\n", comp->size); -} - -static int counter_size_attribute_create( - struct counter_device_attr_group *const group, - const size_t size, const char *const name) -{ - struct counter_size_unit *size_comp; - struct counter_attr_parm parm; - int err; - - /* Allocate size attribute component */ - size_comp = kmalloc(sizeof(*size_comp), GFP_KERNEL); - if (!size_comp) - return -ENOMEM; - size_comp->size = size; - - parm.group = group; - parm.prefix = ""; - parm.name = name; - parm.show = counter_device_attr_size_show; - parm.store = NULL; - parm.component = size_comp; - err = counter_attribute_create(&parm); - if (err) - goto err_free_size_comp; - - return 0; - -err_free_size_comp: - kfree(size_comp); - return err; -} - -struct counter_ext_unit { - const struct counter_device_ext *ext; -}; - -static ssize_t counter_device_ext_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_ext_unit *const component = devattr->component; - const struct counter_device_ext *const ext = component->ext; - - return ext->read(dev_get_drvdata(dev), ext->priv, buf); -} - -static ssize_t counter_device_ext_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - const struct counter_device_attr *const devattr = to_counter_attr(attr); - const struct counter_ext_unit *const component = devattr->component; - const struct counter_device_ext *const ext = component->ext; - - return ext->write(dev_get_drvdata(dev), ext->priv, buf, len); -} - -static int counter_device_ext_register( - struct counter_device_attr_group *const group, - struct counter_device *const counter) -{ - size_t i; - struct counter_ext_unit *ext_comp; - struct counter_attr_parm parm; - int err; - - /* Create an attribute for each extension */ - for (i = 0 ; i < counter->num_ext; i++) { - /* Allocate extension attribute component */ - ext_comp = kmalloc(sizeof(*ext_comp), GFP_KERNEL); - if (!ext_comp) { - err = -ENOMEM; - goto err_free_attr_list; - } - - ext_comp->ext = counter->ext + i; - - /* Allocate extension attribute */ - parm.group = group; - parm.prefix = ""; - parm.name = counter->ext[i].name; - parm.show = (counter->ext[i].read) ? counter_device_ext_show : NULL; - parm.store = (counter->ext[i].write) ? counter_device_ext_store : NULL; - parm.component = ext_comp; - err = counter_attribute_create(&parm); - if (err) { - kfree(ext_comp); - goto err_free_attr_list; - } - } - - return 0; - -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -static int counter_global_attr_register( - struct counter_device_attr_group *const group, - struct counter_device *const counter) -{ - int err; - - /* Create name attribute */ - err = counter_name_attribute_create(group, counter->name); - if (err) - return err; - - /* Create num_counts attribute */ - err = counter_size_attribute_create(group, counter->num_counts, - "num_counts"); - if (err) - goto err_free_attr_list; - - /* Create num_signals attribute */ - err = counter_size_attribute_create(group, counter->num_signals, - "num_signals"); - if (err) - goto err_free_attr_list; - - /* Register Counter device extension attributes */ - err = counter_device_ext_register(group, counter); - if (err) - goto err_free_attr_list; - - return 0; - -err_free_attr_list: - counter_device_attr_list_free(&group->attr_list); - return err; -} - -static void counter_device_groups_list_free( - struct counter_device_attr_group *const groups_list, - const size_t num_groups) -{ - struct counter_device_attr_group *group; - size_t i; - - /* loop through all attribute groups (signals, counts, global, etc.) */ - for (i = 0; i < num_groups; i++) { - group = groups_list + i; - - /* free all attribute group and associated attributes memory */ - kfree(group->attr_group.name); - kfree(group->attr_group.attrs); - counter_device_attr_list_free(&group->attr_list); - } - - kfree(groups_list); -} - -static int counter_device_groups_list_prepare( - struct counter_device *const counter) -{ - const size_t total_num_groups = - counter->num_signals + counter->num_counts + 1; - struct counter_device_attr_group *groups_list; - size_t i; - int err; - size_t num_groups = 0; - - /* Allocate space for attribute groups (signals, counts, and ext) */ - groups_list = kcalloc(total_num_groups, sizeof(*groups_list), - GFP_KERNEL); - if (!groups_list) - return -ENOMEM; - - /* Initialize attribute lists */ - for (i = 0; i < total_num_groups; i++) - INIT_LIST_HEAD(&groups_list[i].attr_list); - - /* Register Signals */ - err = counter_signals_register(groups_list, counter); - if (err) - goto err_free_groups_list; - num_groups += counter->num_signals; - - /* Register Counts and respective Synapses */ - err = counter_counts_register(groups_list + num_groups, counter); - if (err) - goto err_free_groups_list; - num_groups += counter->num_counts; - - /* Register Counter global attributes */ - err = counter_global_attr_register(groups_list + num_groups, counter); - if (err) - goto err_free_groups_list; - num_groups++; - - /* Store groups_list in device_state */ - counter->device_state->groups_list = groups_list; - counter->device_state->num_groups = num_groups; - - return 0; - -err_free_groups_list: - counter_device_groups_list_free(groups_list, num_groups); - return err; -} - -static int counter_device_groups_prepare( - struct counter_device_state *const device_state) -{ - size_t i, j; - struct counter_device_attr_group *group; - int err; - struct counter_device_attr *p; - - /* Allocate attribute groups for association with device */ - device_state->groups = kcalloc(device_state->num_groups + 1, - sizeof(*device_state->groups), - GFP_KERNEL); - if (!device_state->groups) - return -ENOMEM; - - /* Prepare each group of attributes for association */ - for (i = 0; i < device_state->num_groups; i++) { - group = device_state->groups_list + i; - - /* Allocate space for attribute pointers in attribute group */ - group->attr_group.attrs = kcalloc(group->num_attr + 1, - sizeof(*group->attr_group.attrs), GFP_KERNEL); - if (!group->attr_group.attrs) { - err = -ENOMEM; - goto err_free_groups; - } - - /* Add attribute pointers to attribute group */ - j = 0; - list_for_each_entry(p, &group->attr_list, l) - group->attr_group.attrs[j++] = &p->dev_attr.attr; - - /* Group attributes in attribute group */ - device_state->groups[i] = &group->attr_group; - } - /* Associate attributes with device */ - device_state->dev.groups = device_state->groups; - - return 0; - -err_free_groups: - do { - group = device_state->groups_list + i; - kfree(group->attr_group.attrs); - group->attr_group.attrs = NULL; - } while (i--); - kfree(device_state->groups); - return err; -} - -/* Provides a unique ID for each counter device */ -static DEFINE_IDA(counter_ida); - -static void counter_device_release(struct device *dev) -{ - struct counter_device *const counter = dev_get_drvdata(dev); - struct counter_device_state *const device_state = counter->device_state; - - kfree(device_state->groups); - counter_device_groups_list_free(device_state->groups_list, - device_state->num_groups); - ida_simple_remove(&counter_ida, device_state->id); - kfree(device_state); -} - -static struct device_type counter_device_type = { - .name = "counter_device", - .release = counter_device_release -}; - -static struct bus_type counter_bus_type = { - .name = "counter" -}; - -/** - * counter_register - register Counter to the system - * @counter: pointer to Counter to register - * - * This function registers a Counter to the system. A sysfs "counter" directory - * will be created and populated with sysfs attributes correlating with the - * Counter Signals, Synapses, and Counts respectively. - */ -int counter_register(struct counter_device *const counter) -{ - struct counter_device_state *device_state; - int err; - - /* Allocate internal state container for Counter device */ - device_state = kzalloc(sizeof(*device_state), GFP_KERNEL); - if (!device_state) - return -ENOMEM; - counter->device_state = device_state; - - /* Acquire unique ID */ - device_state->id = ida_simple_get(&counter_ida, 0, 0, GFP_KERNEL); - if (device_state->id < 0) { - err = device_state->id; - goto err_free_device_state; - } - - /* Configure device structure for Counter */ - device_state->dev.type = &counter_device_type; - device_state->dev.bus = &counter_bus_type; - if (counter->parent) { - device_state->dev.parent = counter->parent; - device_state->dev.of_node = counter->parent->of_node; - } - dev_set_name(&device_state->dev, "counter%d", device_state->id); - device_initialize(&device_state->dev); - dev_set_drvdata(&device_state->dev, counter); - - /* Prepare device attributes */ - err = counter_device_groups_list_prepare(counter); - if (err) - goto err_free_id; - - /* Organize device attributes to groups and match to device */ - err = counter_device_groups_prepare(device_state); - if (err) - goto err_free_groups_list; - - /* Add device to system */ - err = device_add(&device_state->dev); - if (err) - goto err_free_groups; - - return 0; - -err_free_groups: - kfree(device_state->groups); -err_free_groups_list: - counter_device_groups_list_free(device_state->groups_list, - device_state->num_groups); -err_free_id: - ida_simple_remove(&counter_ida, device_state->id); -err_free_device_state: - kfree(device_state); - return err; -} -EXPORT_SYMBOL_GPL(counter_register); - -/** - * counter_unregister - unregister Counter from the system - * @counter: pointer to Counter to unregister - * - * The Counter is unregistered from the system; all allocated memory is freed. - */ -void counter_unregister(struct counter_device *const counter) -{ - if (counter) - device_del(&counter->device_state->dev); -} -EXPORT_SYMBOL_GPL(counter_unregister); - -static void devm_counter_unreg(struct device *dev, void *res) -{ - counter_unregister(*(struct counter_device **)res); -} - -/** - * devm_counter_register - Resource-managed counter_register - * @dev: device to allocate counter_device for - * @counter: pointer to Counter to register - * - * Managed counter_register. The Counter registered with this function is - * automatically unregistered on driver detach. This function calls - * counter_register internally. Refer to that function for more information. - * - * If an Counter registered with this function needs to be unregistered - * separately, devm_counter_unregister must be used. - * - * RETURNS: - * 0 on success, negative error number on failure. - */ -int devm_counter_register(struct device *dev, - struct counter_device *const counter) -{ - struct counter_device **ptr; - int ret; - - ptr = devres_alloc(devm_counter_unreg, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return -ENOMEM; - - ret = counter_register(counter); - if (!ret) { - *ptr = counter; - devres_add(dev, ptr); - } else { - devres_free(ptr); - } - - return ret; -} -EXPORT_SYMBOL_GPL(devm_counter_register); - -static int devm_counter_match(struct device *dev, void *res, void *data) -{ - struct counter_device **r = res; - - if (!r || !*r) { - WARN_ON(!r || !*r); - return 0; - } - - return *r == data; -} - -/** - * devm_counter_unregister - Resource-managed counter_unregister - * @dev: device this counter_device belongs to - * @counter: pointer to Counter associated with the device - * - * Unregister Counter registered with devm_counter_register. - */ -void devm_counter_unregister(struct device *dev, - struct counter_device *const counter) -{ - int rc; - - rc = devres_release(dev, devm_counter_unreg, devm_counter_match, - counter); - WARN_ON(rc); -} -EXPORT_SYMBOL_GPL(devm_counter_unregister); - -static int __init counter_init(void) -{ - return bus_register(&counter_bus_type); -} - -static void __exit counter_exit(void) -{ - bus_unregister(&counter_bus_type); -} - -subsys_initcall(counter_init); -module_exit(counter_exit); - -MODULE_AUTHOR("William Breathitt Gray "); -MODULE_DESCRIPTION("Generic Counter interface"); -MODULE_LICENSE("GPL v2"); diff --git a/drivers/counter/ftm-quaddec.c b/drivers/counter/ftm-quaddec.c index 53c15f84909b..5ef0478709cd 100644 --- a/drivers/counter/ftm-quaddec.c +++ b/drivers/counter/ftm-quaddec.c @@ -14,6 +14,7 @@ #include #include #include +#include #define FTM_FIELD_UPDATE(ftm, offset, mask, val) \ ({ \ @@ -115,8 +116,7 @@ static void ftm_quaddec_disable(void *ftm) } static int ftm_quaddec_get_prescaler(struct counter_device *counter, - struct counter_count *count, - size_t *cnt_mode) + struct counter_count *count, u32 *cnt_mode) { struct ftm_quaddec *ftm = counter->priv; uint32_t scflags; @@ -129,8 +129,7 @@ static int ftm_quaddec_get_prescaler(struct counter_device *counter, } static int ftm_quaddec_set_prescaler(struct counter_device *counter, - struct counter_count *count, - size_t cnt_mode) + struct counter_count *count, u32 cnt_mode) { struct ftm_quaddec *ftm = counter->priv; @@ -151,33 +150,17 @@ static const char * const ftm_quaddec_prescaler[] = { "1", "2", "4", "8", "16", "32", "64", "128" }; -static struct counter_count_enum_ext ftm_quaddec_prescaler_enum = { - .items = ftm_quaddec_prescaler, - .num_items = ARRAY_SIZE(ftm_quaddec_prescaler), - .get = ftm_quaddec_get_prescaler, - .set = ftm_quaddec_set_prescaler -}; - -enum ftm_quaddec_synapse_action { - FTM_QUADDEC_SYNAPSE_ACTION_BOTH_EDGES, -}; - static const enum counter_synapse_action ftm_quaddec_synapse_actions[] = { - [FTM_QUADDEC_SYNAPSE_ACTION_BOTH_EDGES] = COUNTER_SYNAPSE_ACTION_BOTH_EDGES }; -enum ftm_quaddec_count_function { - FTM_QUADDEC_COUNT_ENCODER_MODE_1, -}; - static const enum counter_function ftm_quaddec_count_functions[] = { - [FTM_QUADDEC_COUNT_ENCODER_MODE_1] = COUNTER_FUNCTION_QUADRATURE_X4 + COUNTER_FUNCTION_QUADRATURE_X4 }; static int ftm_quaddec_count_read(struct counter_device *counter, struct counter_count *count, - unsigned long *val) + u64 *val) { struct ftm_quaddec *const ftm = counter->priv; uint32_t cntval; @@ -191,7 +174,7 @@ static int ftm_quaddec_count_read(struct counter_device *counter, static int ftm_quaddec_count_write(struct counter_device *counter, struct counter_count *count, - const unsigned long val) + const u64 val) { struct ftm_quaddec *const ftm = counter->priv; @@ -205,21 +188,21 @@ static int ftm_quaddec_count_write(struct counter_device *counter, return 0; } -static int ftm_quaddec_count_function_get(struct counter_device *counter, - struct counter_count *count, - size_t *function) +static int ftm_quaddec_count_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { - *function = FTM_QUADDEC_COUNT_ENCODER_MODE_1; + *function = COUNTER_FUNCTION_QUADRATURE_X4; return 0; } -static int ftm_quaddec_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t *action) +static int ftm_quaddec_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { - *action = FTM_QUADDEC_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; } @@ -227,8 +210,8 @@ static int ftm_quaddec_action_get(struct counter_device *counter, static const struct counter_ops ftm_quaddec_cnt_ops = { .count_read = ftm_quaddec_count_read, .count_write = ftm_quaddec_count_write, - .function_get = ftm_quaddec_count_function_get, - .action_get = ftm_quaddec_action_get, + .function_read = ftm_quaddec_count_function_read, + .action_read = ftm_quaddec_action_read, }; static struct counter_signal ftm_quaddec_signals[] = { @@ -255,9 +238,12 @@ static struct counter_synapse ftm_quaddec_count_synapses[] = { } }; -static const struct counter_count_ext ftm_quaddec_count_ext[] = { - COUNTER_COUNT_ENUM("prescaler", &ftm_quaddec_prescaler_enum), - COUNTER_COUNT_ENUM_AVAILABLE("prescaler", &ftm_quaddec_prescaler_enum), +static DEFINE_COUNTER_ENUM(ftm_quaddec_prescaler_enum, ftm_quaddec_prescaler); + +static struct counter_comp ftm_quaddec_count_ext[] = { + COUNTER_COMP_COUNT_ENUM("prescaler", ftm_quaddec_get_prescaler, + ftm_quaddec_set_prescaler, + ftm_quaddec_prescaler_enum), }; static struct counter_count ftm_quaddec_counts = { diff --git a/drivers/counter/intel-qep.c b/drivers/counter/intel-qep.c index 8a6847d5fb2b..0924d16de6e2 100644 --- a/drivers/counter/intel-qep.c +++ b/drivers/counter/intel-qep.c @@ -62,13 +62,6 @@ #define INTEL_QEP_CLK_PERIOD_NS 10 -#define INTEL_QEP_COUNTER_EXT_RW(_name) \ -{ \ - .name = #_name, \ - .read = _name##_read, \ - .write = _name##_write, \ -} - struct intel_qep { struct counter_device counter; struct mutex lock; @@ -114,8 +107,7 @@ static void intel_qep_init(struct intel_qep *qep) } static int intel_qep_count_read(struct counter_device *counter, - struct counter_count *count, - unsigned long *val) + struct counter_count *count, u64 *val) { struct intel_qep *const qep = counter->priv; @@ -130,11 +122,11 @@ static const enum counter_function intel_qep_count_functions[] = { COUNTER_FUNCTION_QUADRATURE_X4, }; -static int intel_qep_function_get(struct counter_device *counter, - struct counter_count *count, - size_t *function) +static int intel_qep_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { - *function = 0; + *function = COUNTER_FUNCTION_QUADRATURE_X4; return 0; } @@ -143,19 +135,19 @@ static const enum counter_synapse_action intel_qep_synapse_actions[] = { COUNTER_SYNAPSE_ACTION_BOTH_EDGES, }; -static int intel_qep_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t *action) +static int intel_qep_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { - *action = 0; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; } static const struct counter_ops intel_qep_counter_ops = { .count_read = intel_qep_count_read, - .function_get = intel_qep_function_get, - .action_get = intel_qep_action_get, + .function_read = intel_qep_function_read, + .action_read = intel_qep_action_read, }; #define INTEL_QEP_SIGNAL(_id, _name) { \ @@ -181,31 +173,27 @@ static struct counter_synapse intel_qep_count_synapses[] = { INTEL_QEP_SYNAPSE(2), }; -static ssize_t ceiling_read(struct counter_device *counter, - struct counter_count *count, - void *priv, char *buf) +static int intel_qep_ceiling_read(struct counter_device *counter, + struct counter_count *count, u64 *ceiling) { struct intel_qep *qep = counter->priv; - u32 reg; pm_runtime_get_sync(qep->dev); - reg = intel_qep_readl(qep, INTEL_QEPMAX); + *ceiling = intel_qep_readl(qep, INTEL_QEPMAX); pm_runtime_put(qep->dev); - return sysfs_emit(buf, "%u\n", reg); + return 0; } -static ssize_t ceiling_write(struct counter_device *counter, - struct counter_count *count, - void *priv, const char *buf, size_t len) +static int intel_qep_ceiling_write(struct counter_device *counter, + struct counter_count *count, u64 max) { struct intel_qep *qep = counter->priv; - u32 max; - int ret; + int ret = 0; - ret = kstrtou32(buf, 0, &max); - if (ret < 0) - return ret; + /* Intel QEP ceiling configuration only supports 32-bit values */ + if (max != (u32)max) + return -ERANGE; mutex_lock(&qep->lock); if (qep->enabled) { @@ -216,34 +204,28 @@ static ssize_t ceiling_write(struct counter_device *counter, pm_runtime_get_sync(qep->dev); intel_qep_writel(qep, INTEL_QEPMAX, max); pm_runtime_put(qep->dev); - ret = len; out: mutex_unlock(&qep->lock); return ret; } -static ssize_t enable_read(struct counter_device *counter, - struct counter_count *count, - void *priv, char *buf) +static int intel_qep_enable_read(struct counter_device *counter, + struct counter_count *count, u8 *enable) { struct intel_qep *qep = counter->priv; - return sysfs_emit(buf, "%u\n", qep->enabled); + *enable = qep->enabled; + + return 0; } -static ssize_t enable_write(struct counter_device *counter, - struct counter_count *count, - void *priv, const char *buf, size_t len) +static int intel_qep_enable_write(struct counter_device *counter, + struct counter_count *count, u8 val) { struct intel_qep *qep = counter->priv; u32 reg; - bool val, changed; - int ret; - - ret = kstrtobool(buf, &val); - if (ret) - return ret; + bool changed; mutex_lock(&qep->lock); changed = val ^ qep->enabled; @@ -267,12 +249,12 @@ static ssize_t enable_write(struct counter_device *counter, out: mutex_unlock(&qep->lock); - return len; + return 0; } -static ssize_t spike_filter_ns_read(struct counter_device *counter, - struct counter_count *count, - void *priv, char *buf) +static int intel_qep_spike_filter_ns_read(struct counter_device *counter, + struct counter_count *count, + u64 *length) { struct intel_qep *qep = counter->priv; u32 reg; @@ -281,33 +263,31 @@ static ssize_t spike_filter_ns_read(struct counter_device *counter, reg = intel_qep_readl(qep, INTEL_QEPCON); if (!(reg & INTEL_QEPCON_FLT_EN)) { pm_runtime_put(qep->dev); - return sysfs_emit(buf, "0\n"); + return 0; } reg = INTEL_QEPFLT_MAX_COUNT(intel_qep_readl(qep, INTEL_QEPFLT)); pm_runtime_put(qep->dev); - return sysfs_emit(buf, "%u\n", (reg + 2) * INTEL_QEP_CLK_PERIOD_NS); + *length = (reg + 2) * INTEL_QEP_CLK_PERIOD_NS; + + return 0; } -static ssize_t spike_filter_ns_write(struct counter_device *counter, - struct counter_count *count, - void *priv, const char *buf, size_t len) +static int intel_qep_spike_filter_ns_write(struct counter_device *counter, + struct counter_count *count, + u64 length) { struct intel_qep *qep = counter->priv; - u32 reg, length; + u32 reg; bool enable; - int ret; - - ret = kstrtou32(buf, 0, &length); - if (ret < 0) - return ret; + int ret = 0; /* * Spike filter length is (MAX_COUNT + 2) clock periods. * Disable filter when userspace writes 0, enable for valid * nanoseconds values and error out otherwise. */ - length /= INTEL_QEP_CLK_PERIOD_NS; + do_div(length, INTEL_QEP_CLK_PERIOD_NS); if (length == 0) { enable = false; length = 0; @@ -336,16 +316,15 @@ static ssize_t spike_filter_ns_write(struct counter_device *counter, intel_qep_writel(qep, INTEL_QEPFLT, length); intel_qep_writel(qep, INTEL_QEPCON, reg); pm_runtime_put(qep->dev); - ret = len; out: mutex_unlock(&qep->lock); return ret; } -static ssize_t preset_enable_read(struct counter_device *counter, - struct counter_count *count, - void *priv, char *buf) +static int intel_qep_preset_enable_read(struct counter_device *counter, + struct counter_count *count, + u8 *preset_enable) { struct intel_qep *qep = counter->priv; u32 reg; @@ -353,21 +332,18 @@ static ssize_t preset_enable_read(struct counter_device *counter, pm_runtime_get_sync(qep->dev); reg = intel_qep_readl(qep, INTEL_QEPCON); pm_runtime_put(qep->dev); - return sysfs_emit(buf, "%u\n", !(reg & INTEL_QEPCON_COUNT_RST_MODE)); + + *preset_enable = !(reg & INTEL_QEPCON_COUNT_RST_MODE); + + return 0; } -static ssize_t preset_enable_write(struct counter_device *counter, - struct counter_count *count, - void *priv, const char *buf, size_t len) +static int intel_qep_preset_enable_write(struct counter_device *counter, + struct counter_count *count, u8 val) { struct intel_qep *qep = counter->priv; u32 reg; - bool val; - int ret; - - ret = kstrtobool(buf, &val); - if (ret) - return ret; + int ret = 0; mutex_lock(&qep->lock); if (qep->enabled) { @@ -384,7 +360,6 @@ static ssize_t preset_enable_write(struct counter_device *counter, intel_qep_writel(qep, INTEL_QEPCON, reg); pm_runtime_put(qep->dev); - ret = len; out: mutex_unlock(&qep->lock); @@ -392,11 +367,14 @@ out: return ret; } -static const struct counter_count_ext intel_qep_count_ext[] = { - INTEL_QEP_COUNTER_EXT_RW(ceiling), - INTEL_QEP_COUNTER_EXT_RW(enable), - INTEL_QEP_COUNTER_EXT_RW(spike_filter_ns), - INTEL_QEP_COUNTER_EXT_RW(preset_enable) +static struct counter_comp intel_qep_count_ext[] = { + COUNTER_COMP_ENABLE(intel_qep_enable_read, intel_qep_enable_write), + COUNTER_COMP_CEILING(intel_qep_ceiling_read, intel_qep_ceiling_write), + COUNTER_COMP_PRESET_ENABLE(intel_qep_preset_enable_read, + intel_qep_preset_enable_write), + COUNTER_COMP_COUNT_U64("spike_filter_ns", + intel_qep_spike_filter_ns_read, + intel_qep_spike_filter_ns_write), }; static struct counter_count intel_qep_counter_count[] = { diff --git a/drivers/counter/interrupt-cnt.c b/drivers/counter/interrupt-cnt.c index 1de4243db488..8514a87fcbee 100644 --- a/drivers/counter/interrupt-cnt.c +++ b/drivers/counter/interrupt-cnt.c @@ -10,6 +10,7 @@ #include #include #include +#include #define INTERRUPT_CNT_NAME "interrupt-cnt" @@ -33,30 +34,23 @@ static irqreturn_t interrupt_cnt_isr(int irq, void *dev_id) return IRQ_HANDLED; } -static ssize_t interrupt_cnt_enable_read(struct counter_device *counter, - struct counter_count *count, - void *private, char *buf) +static int interrupt_cnt_enable_read(struct counter_device *counter, + struct counter_count *count, u8 *enable) { struct interrupt_cnt_priv *priv = counter->priv; - return sysfs_emit(buf, "%d\n", priv->enabled); + *enable = priv->enabled; + + return 0; } -static ssize_t interrupt_cnt_enable_write(struct counter_device *counter, - struct counter_count *count, - void *private, const char *buf, - size_t len) +static int interrupt_cnt_enable_write(struct counter_device *counter, + struct counter_count *count, u8 enable) { struct interrupt_cnt_priv *priv = counter->priv; - bool enable; - ssize_t ret; - - ret = kstrtobool(buf, &enable); - if (ret) - return ret; if (priv->enabled == enable) - return len; + return 0; if (enable) { priv->enabled = true; @@ -66,33 +60,30 @@ static ssize_t interrupt_cnt_enable_write(struct counter_device *counter, priv->enabled = false; } - return len; + return 0; } -static const struct counter_count_ext interrupt_cnt_ext[] = { - { - .name = "enable", - .read = interrupt_cnt_enable_read, - .write = interrupt_cnt_enable_write, - }, +static struct counter_comp interrupt_cnt_ext[] = { + COUNTER_COMP_ENABLE(interrupt_cnt_enable_read, + interrupt_cnt_enable_write), }; static const enum counter_synapse_action interrupt_cnt_synapse_actions[] = { COUNTER_SYNAPSE_ACTION_RISING_EDGE, }; -static int interrupt_cnt_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t *action) +static int interrupt_cnt_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { - *action = 0; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; return 0; } static int interrupt_cnt_read(struct counter_device *counter, - struct counter_count *count, unsigned long *val) + struct counter_count *count, u64 *val) { struct interrupt_cnt_priv *priv = counter->priv; @@ -102,8 +93,7 @@ static int interrupt_cnt_read(struct counter_device *counter, } static int interrupt_cnt_write(struct counter_device *counter, - struct counter_count *count, - const unsigned long val) + struct counter_count *count, const u64 val) { struct interrupt_cnt_priv *priv = counter->priv; @@ -119,11 +109,11 @@ static const enum counter_function interrupt_cnt_functions[] = { COUNTER_FUNCTION_INCREASE, }; -static int interrupt_cnt_function_get(struct counter_device *counter, - struct counter_count *count, - size_t *function) +static int interrupt_cnt_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { - *function = 0; + *function = COUNTER_FUNCTION_INCREASE; return 0; } @@ -148,10 +138,10 @@ static int interrupt_cnt_signal_read(struct counter_device *counter, } static const struct counter_ops interrupt_cnt_ops = { - .action_get = interrupt_cnt_action_get, + .action_read = interrupt_cnt_action_read, .count_read = interrupt_cnt_read, .count_write = interrupt_cnt_write, - .function_get = interrupt_cnt_function_get, + .function_read = interrupt_cnt_function_read, .signal_read = interrupt_cnt_signal_read, }; diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c index 1aa70b9c4833..79e0c84a3b81 100644 --- a/drivers/counter/microchip-tcb-capture.c +++ b/drivers/counter/microchip-tcb-capture.c @@ -32,28 +32,16 @@ struct mchp_tc_data { bool trig_inverted; }; -enum mchp_tc_count_function { - MCHP_TC_FUNCTION_INCREASE, - MCHP_TC_FUNCTION_QUADRATURE, -}; - static const enum counter_function mchp_tc_count_functions[] = { - [MCHP_TC_FUNCTION_INCREASE] = COUNTER_FUNCTION_INCREASE, - [MCHP_TC_FUNCTION_QUADRATURE] = COUNTER_FUNCTION_QUADRATURE_X4, -}; - -enum mchp_tc_synapse_action { - MCHP_TC_SYNAPSE_ACTION_NONE = 0, - MCHP_TC_SYNAPSE_ACTION_RISING_EDGE, - MCHP_TC_SYNAPSE_ACTION_FALLING_EDGE, - MCHP_TC_SYNAPSE_ACTION_BOTH_EDGE + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_QUADRATURE_X4, }; static const enum counter_synapse_action mchp_tc_synapse_actions[] = { - [MCHP_TC_SYNAPSE_ACTION_NONE] = COUNTER_SYNAPSE_ACTION_NONE, - [MCHP_TC_SYNAPSE_ACTION_RISING_EDGE] = COUNTER_SYNAPSE_ACTION_RISING_EDGE, - [MCHP_TC_SYNAPSE_ACTION_FALLING_EDGE] = COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - [MCHP_TC_SYNAPSE_ACTION_BOTH_EDGE] = COUNTER_SYNAPSE_ACTION_BOTH_EDGES, + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, }; static struct counter_signal mchp_tc_count_signals[] = { @@ -80,23 +68,23 @@ static struct counter_synapse mchp_tc_count_synapses[] = { } }; -static int mchp_tc_count_function_get(struct counter_device *counter, - struct counter_count *count, - size_t *function) +static int mchp_tc_count_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { struct mchp_tc_data *const priv = counter->priv; if (priv->qdec_mode) - *function = MCHP_TC_FUNCTION_QUADRATURE; + *function = COUNTER_FUNCTION_QUADRATURE_X4; else - *function = MCHP_TC_FUNCTION_INCREASE; + *function = COUNTER_FUNCTION_INCREASE; return 0; } -static int mchp_tc_count_function_set(struct counter_device *counter, - struct counter_count *count, - size_t function) +static int mchp_tc_count_function_write(struct counter_device *counter, + struct counter_count *count, + enum counter_function function) { struct mchp_tc_data *const priv = counter->priv; u32 bmr, cmr; @@ -108,7 +96,7 @@ static int mchp_tc_count_function_set(struct counter_device *counter, cmr &= ~ATMEL_TC_WAVE; switch (function) { - case MCHP_TC_FUNCTION_INCREASE: + case COUNTER_FUNCTION_INCREASE: priv->qdec_mode = 0; /* Set highest rate based on whether soc has gclk or not */ bmr &= ~(ATMEL_TC_QDEN | ATMEL_TC_POSEN); @@ -120,7 +108,7 @@ static int mchp_tc_count_function_set(struct counter_device *counter, cmr |= ATMEL_TC_CMR_MASK; cmr &= ~(ATMEL_TC_ABETRG | ATMEL_TC_XC0); break; - case MCHP_TC_FUNCTION_QUADRATURE: + case COUNTER_FUNCTION_QUADRATURE_X4: if (!priv->tc_cfg->has_qdec) return -EINVAL; /* In QDEC mode settings both channels 0 and 1 are required */ @@ -176,10 +164,10 @@ static int mchp_tc_count_signal_read(struct counter_device *counter, return 0; } -static int mchp_tc_count_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t *action) +static int mchp_tc_count_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { struct mchp_tc_data *const priv = counter->priv; u32 cmr; @@ -188,26 +176,26 @@ static int mchp_tc_count_action_get(struct counter_device *counter, switch (cmr & ATMEL_TC_ETRGEDG) { default: - *action = MCHP_TC_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; break; case ATMEL_TC_ETRGEDG_RISING: - *action = MCHP_TC_SYNAPSE_ACTION_RISING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; break; case ATMEL_TC_ETRGEDG_FALLING: - *action = MCHP_TC_SYNAPSE_ACTION_FALLING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_FALLING_EDGE; break; case ATMEL_TC_ETRGEDG_BOTH: - *action = MCHP_TC_SYNAPSE_ACTION_BOTH_EDGE; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; break; } return 0; } -static int mchp_tc_count_action_set(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t action) +static int mchp_tc_count_action_write(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action action) { struct mchp_tc_data *const priv = counter->priv; u32 edge = ATMEL_TC_ETRGEDG_NONE; @@ -217,16 +205,16 @@ static int mchp_tc_count_action_set(struct counter_device *counter, return -EINVAL; switch (action) { - case MCHP_TC_SYNAPSE_ACTION_NONE: + case COUNTER_SYNAPSE_ACTION_NONE: edge = ATMEL_TC_ETRGEDG_NONE; break; - case MCHP_TC_SYNAPSE_ACTION_RISING_EDGE: + case COUNTER_SYNAPSE_ACTION_RISING_EDGE: edge = ATMEL_TC_ETRGEDG_RISING; break; - case MCHP_TC_SYNAPSE_ACTION_FALLING_EDGE: + case COUNTER_SYNAPSE_ACTION_FALLING_EDGE: edge = ATMEL_TC_ETRGEDG_FALLING; break; - case MCHP_TC_SYNAPSE_ACTION_BOTH_EDGE: + case COUNTER_SYNAPSE_ACTION_BOTH_EDGES: edge = ATMEL_TC_ETRGEDG_BOTH; break; default: @@ -240,8 +228,7 @@ static int mchp_tc_count_action_set(struct counter_device *counter, } static int mchp_tc_count_read(struct counter_device *counter, - struct counter_count *count, - unsigned long *val) + struct counter_count *count, u64 *val) { struct mchp_tc_data *const priv = counter->priv; u32 cnt; @@ -264,12 +251,12 @@ static struct counter_count mchp_tc_counts[] = { }; static const struct counter_ops mchp_tc_ops = { - .signal_read = mchp_tc_count_signal_read, - .count_read = mchp_tc_count_read, - .function_get = mchp_tc_count_function_get, - .function_set = mchp_tc_count_function_set, - .action_get = mchp_tc_count_action_get, - .action_set = mchp_tc_count_action_set + .signal_read = mchp_tc_count_signal_read, + .count_read = mchp_tc_count_read, + .function_read = mchp_tc_count_function_read, + .function_write = mchp_tc_count_function_write, + .action_read = mchp_tc_count_action_read, + .action_write = mchp_tc_count_action_write }; static const struct atmel_tcb_config tcb_rm9200_config = { diff --git a/drivers/counter/stm32-lptimer-cnt.c b/drivers/counter/stm32-lptimer-cnt.c index 7367f46c6f91..5168833b1fdf 100644 --- a/drivers/counter/stm32-lptimer-cnt.c +++ b/drivers/counter/stm32-lptimer-cnt.c @@ -17,6 +17,7 @@ #include #include #include +#include struct stm32_lptim_cnt { struct counter_device counter; @@ -107,11 +108,7 @@ static int stm32_lptim_setup(struct stm32_lptim_cnt *priv, int enable) return regmap_update_bits(priv->regmap, STM32_LPTIM_CFGR, mask, val); } -/** - * enum stm32_lptim_cnt_function - enumerates LPTimer counter & encoder modes - * @STM32_LPTIM_COUNTER_INCREASE: up count on IN1 rising, falling or both edges - * @STM32_LPTIM_ENCODER_BOTH_EDGE: count on both edges (IN1 & IN2 quadrature) - * +/* * In non-quadrature mode, device counts up on active edge. * In quadrature mode, encoder counting scenarios are as follows: * +---------+----------+--------------------+--------------------+ @@ -129,33 +126,20 @@ static int stm32_lptim_setup(struct stm32_lptim_cnt *priv, int enable) * | edges | Low -> | Up | Down | Down | Up | * +---------+----------+----------+---------+----------+---------+ */ -enum stm32_lptim_cnt_function { - STM32_LPTIM_COUNTER_INCREASE, - STM32_LPTIM_ENCODER_BOTH_EDGE, -}; - static const enum counter_function stm32_lptim_cnt_functions[] = { - [STM32_LPTIM_COUNTER_INCREASE] = COUNTER_FUNCTION_INCREASE, - [STM32_LPTIM_ENCODER_BOTH_EDGE] = COUNTER_FUNCTION_QUADRATURE_X4, -}; - -enum stm32_lptim_synapse_action { - STM32_LPTIM_SYNAPSE_ACTION_RISING_EDGE = STM32_LPTIM_CKPOL_RISING_EDGE, - STM32_LPTIM_SYNAPSE_ACTION_FALLING_EDGE = STM32_LPTIM_CKPOL_FALLING_EDGE, - STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES = STM32_LPTIM_CKPOL_BOTH_EDGES, - STM32_LPTIM_SYNAPSE_ACTION_NONE, + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_QUADRATURE_X4, }; static const enum counter_synapse_action stm32_lptim_cnt_synapse_actions[] = { - /* Index must match with stm32_lptim_cnt_polarity[] (priv->polarity) */ - [STM32_LPTIM_SYNAPSE_ACTION_RISING_EDGE] = COUNTER_SYNAPSE_ACTION_RISING_EDGE, - [STM32_LPTIM_SYNAPSE_ACTION_FALLING_EDGE] = COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - [STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES] = COUNTER_SYNAPSE_ACTION_BOTH_EDGES, - [STM32_LPTIM_SYNAPSE_ACTION_NONE] = COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, + COUNTER_SYNAPSE_ACTION_NONE, }; static int stm32_lptim_cnt_read(struct counter_device *counter, - struct counter_count *count, unsigned long *val) + struct counter_count *count, u64 *val) { struct stm32_lptim_cnt *const priv = counter->priv; u32 cnt; @@ -170,28 +154,28 @@ static int stm32_lptim_cnt_read(struct counter_device *counter, return 0; } -static int stm32_lptim_cnt_function_get(struct counter_device *counter, - struct counter_count *count, - size_t *function) +static int stm32_lptim_cnt_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { struct stm32_lptim_cnt *const priv = counter->priv; if (!priv->quadrature_mode) { - *function = STM32_LPTIM_COUNTER_INCREASE; + *function = COUNTER_FUNCTION_INCREASE; return 0; } - if (priv->polarity == STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES) { - *function = STM32_LPTIM_ENCODER_BOTH_EDGE; + if (priv->polarity == STM32_LPTIM_CKPOL_BOTH_EDGES) { + *function = COUNTER_FUNCTION_QUADRATURE_X4; return 0; } return -EINVAL; } -static int stm32_lptim_cnt_function_set(struct counter_device *counter, - struct counter_count *count, - size_t function) +static int stm32_lptim_cnt_function_write(struct counter_device *counter, + struct counter_count *count, + enum counter_function function) { struct stm32_lptim_cnt *const priv = counter->priv; @@ -199,12 +183,12 @@ static int stm32_lptim_cnt_function_set(struct counter_device *counter, return -EBUSY; switch (function) { - case STM32_LPTIM_COUNTER_INCREASE: + case COUNTER_FUNCTION_INCREASE: priv->quadrature_mode = 0; return 0; - case STM32_LPTIM_ENCODER_BOTH_EDGE: + case COUNTER_FUNCTION_QUADRATURE_X4: priv->quadrature_mode = 1; - priv->polarity = STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES; + priv->polarity = STM32_LPTIM_CKPOL_BOTH_EDGES; return 0; default: /* should never reach this path */ @@ -212,9 +196,9 @@ static int stm32_lptim_cnt_function_set(struct counter_device *counter, } } -static ssize_t stm32_lptim_cnt_enable_read(struct counter_device *counter, - struct counter_count *count, - void *private, char *buf) +static int stm32_lptim_cnt_enable_read(struct counter_device *counter, + struct counter_count *count, + u8 *enable) { struct stm32_lptim_cnt *const priv = counter->priv; int ret; @@ -223,22 +207,18 @@ static ssize_t stm32_lptim_cnt_enable_read(struct counter_device *counter, if (ret < 0) return ret; - return scnprintf(buf, PAGE_SIZE, "%u\n", ret); + *enable = ret; + + return 0; } -static ssize_t stm32_lptim_cnt_enable_write(struct counter_device *counter, - struct counter_count *count, - void *private, - const char *buf, size_t len) +static int stm32_lptim_cnt_enable_write(struct counter_device *counter, + struct counter_count *count, + u8 enable) { struct stm32_lptim_cnt *const priv = counter->priv; - bool enable; int ret; - ret = kstrtobool(buf, &enable); - if (ret) - return ret; - /* Check nobody uses the timer, or already disabled/enabled */ ret = stm32_lptim_is_enabled(priv); if ((ret < 0) || (!ret && !enable)) @@ -254,78 +234,81 @@ static ssize_t stm32_lptim_cnt_enable_write(struct counter_device *counter, if (ret) return ret; - return len; + return 0; } -static ssize_t stm32_lptim_cnt_ceiling_read(struct counter_device *counter, - struct counter_count *count, - void *private, char *buf) +static int stm32_lptim_cnt_ceiling_read(struct counter_device *counter, + struct counter_count *count, + u64 *ceiling) { struct stm32_lptim_cnt *const priv = counter->priv; - return snprintf(buf, PAGE_SIZE, "%u\n", priv->ceiling); + *ceiling = priv->ceiling; + + return 0; } -static ssize_t stm32_lptim_cnt_ceiling_write(struct counter_device *counter, - struct counter_count *count, - void *private, - const char *buf, size_t len) +static int stm32_lptim_cnt_ceiling_write(struct counter_device *counter, + struct counter_count *count, + u64 ceiling) { struct stm32_lptim_cnt *const priv = counter->priv; - unsigned int ceiling; - int ret; if (stm32_lptim_is_enabled(priv)) return -EBUSY; - ret = kstrtouint(buf, 0, &ceiling); - if (ret) - return ret; - if (ceiling > STM32_LPTIM_MAX_ARR) return -ERANGE; priv->ceiling = ceiling; - return len; + return 0; } -static const struct counter_count_ext stm32_lptim_cnt_ext[] = { - { - .name = "enable", - .read = stm32_lptim_cnt_enable_read, - .write = stm32_lptim_cnt_enable_write - }, - { - .name = "ceiling", - .read = stm32_lptim_cnt_ceiling_read, - .write = stm32_lptim_cnt_ceiling_write - }, +static struct counter_comp stm32_lptim_cnt_ext[] = { + COUNTER_COMP_ENABLE(stm32_lptim_cnt_enable_read, + stm32_lptim_cnt_enable_write), + COUNTER_COMP_CEILING(stm32_lptim_cnt_ceiling_read, + stm32_lptim_cnt_ceiling_write), }; -static int stm32_lptim_cnt_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t *action) +static int stm32_lptim_cnt_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { struct stm32_lptim_cnt *const priv = counter->priv; - size_t function; + enum counter_function function; int err; - err = stm32_lptim_cnt_function_get(counter, count, &function); + err = stm32_lptim_cnt_function_read(counter, count, &function); if (err) return err; switch (function) { - case STM32_LPTIM_COUNTER_INCREASE: + case COUNTER_FUNCTION_INCREASE: /* LP Timer acts as up-counter on input 1 */ - if (synapse->signal->id == count->synapses[0].signal->id) - *action = priv->polarity; - else - *action = STM32_LPTIM_SYNAPSE_ACTION_NONE; - return 0; - case STM32_LPTIM_ENCODER_BOTH_EDGE: - *action = priv->polarity; + if (synapse->signal->id != count->synapses[0].signal->id) { + *action = COUNTER_SYNAPSE_ACTION_NONE; + return 0; + } + + switch (priv->polarity) { + case STM32_LPTIM_CKPOL_RISING_EDGE: + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; + return 0; + case STM32_LPTIM_CKPOL_FALLING_EDGE: + *action = COUNTER_SYNAPSE_ACTION_FALLING_EDGE; + return 0; + case STM32_LPTIM_CKPOL_BOTH_EDGES: + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; + return 0; + default: + /* should never reach this path */ + return -EINVAL; + } + case COUNTER_FUNCTION_QUADRATURE_X4: + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; default: /* should never reach this path */ @@ -333,43 +316,48 @@ static int stm32_lptim_cnt_action_get(struct counter_device *counter, } } -static int stm32_lptim_cnt_action_set(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t action) +static int stm32_lptim_cnt_action_write(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action action) { struct stm32_lptim_cnt *const priv = counter->priv; - size_t function; + enum counter_function function; int err; if (stm32_lptim_is_enabled(priv)) return -EBUSY; - err = stm32_lptim_cnt_function_get(counter, count, &function); + err = stm32_lptim_cnt_function_read(counter, count, &function); if (err) return err; /* only set polarity when in counter mode (on input 1) */ - if (function == STM32_LPTIM_COUNTER_INCREASE - && synapse->signal->id == count->synapses[0].signal->id) { - switch (action) { - case STM32_LPTIM_SYNAPSE_ACTION_RISING_EDGE: - case STM32_LPTIM_SYNAPSE_ACTION_FALLING_EDGE: - case STM32_LPTIM_SYNAPSE_ACTION_BOTH_EDGES: - priv->polarity = action; - return 0; - } - } + if (function != COUNTER_FUNCTION_INCREASE + || synapse->signal->id != count->synapses[0].signal->id) + return -EINVAL; - return -EINVAL; + switch (action) { + case COUNTER_SYNAPSE_ACTION_RISING_EDGE: + priv->polarity = STM32_LPTIM_CKPOL_RISING_EDGE; + return 0; + case COUNTER_SYNAPSE_ACTION_FALLING_EDGE: + priv->polarity = STM32_LPTIM_CKPOL_FALLING_EDGE; + return 0; + case COUNTER_SYNAPSE_ACTION_BOTH_EDGES: + priv->polarity = STM32_LPTIM_CKPOL_BOTH_EDGES; + return 0; + default: + return -EINVAL; + } } static const struct counter_ops stm32_lptim_cnt_ops = { .count_read = stm32_lptim_cnt_read, - .function_get = stm32_lptim_cnt_function_get, - .function_set = stm32_lptim_cnt_function_set, - .action_get = stm32_lptim_cnt_action_get, - .action_set = stm32_lptim_cnt_action_set, + .function_read = stm32_lptim_cnt_function_read, + .function_write = stm32_lptim_cnt_function_write, + .action_read = stm32_lptim_cnt_action_read, + .action_write = stm32_lptim_cnt_action_write, }; static struct counter_signal stm32_lptim_cnt_signals[] = { diff --git a/drivers/counter/stm32-timer-cnt.c b/drivers/counter/stm32-timer-cnt.c index 1fbc46f4ee66..0546e932db0c 100644 --- a/drivers/counter/stm32-timer-cnt.c +++ b/drivers/counter/stm32-timer-cnt.c @@ -13,6 +13,7 @@ #include #include #include +#include #define TIM_CCMR_CCXS (BIT(8) | BIT(0)) #define TIM_CCMR_MASK (TIM_CCMR_CC1S | TIM_CCMR_CC2S | \ @@ -36,29 +37,15 @@ struct stm32_timer_cnt { struct stm32_timer_regs bak; }; -/** - * enum stm32_count_function - enumerates stm32 timer counter encoder modes - * @STM32_COUNT_SLAVE_MODE_DISABLED: counts on internal clock when CEN=1 - * @STM32_COUNT_ENCODER_MODE_1: counts TI1FP1 edges, depending on TI2FP2 level - * @STM32_COUNT_ENCODER_MODE_2: counts TI2FP2 edges, depending on TI1FP1 level - * @STM32_COUNT_ENCODER_MODE_3: counts on both TI1FP1 and TI2FP2 edges - */ -enum stm32_count_function { - STM32_COUNT_SLAVE_MODE_DISABLED, - STM32_COUNT_ENCODER_MODE_1, - STM32_COUNT_ENCODER_MODE_2, - STM32_COUNT_ENCODER_MODE_3, -}; - static const enum counter_function stm32_count_functions[] = { - [STM32_COUNT_SLAVE_MODE_DISABLED] = COUNTER_FUNCTION_INCREASE, - [STM32_COUNT_ENCODER_MODE_1] = COUNTER_FUNCTION_QUADRATURE_X2_A, - [STM32_COUNT_ENCODER_MODE_2] = COUNTER_FUNCTION_QUADRATURE_X2_B, - [STM32_COUNT_ENCODER_MODE_3] = COUNTER_FUNCTION_QUADRATURE_X4, + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X2_B, + COUNTER_FUNCTION_QUADRATURE_X4, }; static int stm32_count_read(struct counter_device *counter, - struct counter_count *count, unsigned long *val) + struct counter_count *count, u64 *val) { struct stm32_timer_cnt *const priv = counter->priv; u32 cnt; @@ -70,8 +57,7 @@ static int stm32_count_read(struct counter_device *counter, } static int stm32_count_write(struct counter_device *counter, - struct counter_count *count, - const unsigned long val) + struct counter_count *count, const u64 val) { struct stm32_timer_cnt *const priv = counter->priv; u32 ceiling; @@ -83,9 +69,9 @@ static int stm32_count_write(struct counter_device *counter, return regmap_write(priv->regmap, TIM_CNT, val); } -static int stm32_count_function_get(struct counter_device *counter, - struct counter_count *count, - size_t *function) +static int stm32_count_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { struct stm32_timer_cnt *const priv = counter->priv; u32 smcr; @@ -94,40 +80,40 @@ static int stm32_count_function_get(struct counter_device *counter, switch (smcr & TIM_SMCR_SMS) { case TIM_SMCR_SMS_SLAVE_MODE_DISABLED: - *function = STM32_COUNT_SLAVE_MODE_DISABLED; + *function = COUNTER_FUNCTION_INCREASE; return 0; case TIM_SMCR_SMS_ENCODER_MODE_1: - *function = STM32_COUNT_ENCODER_MODE_1; + *function = COUNTER_FUNCTION_QUADRATURE_X2_A; return 0; case TIM_SMCR_SMS_ENCODER_MODE_2: - *function = STM32_COUNT_ENCODER_MODE_2; + *function = COUNTER_FUNCTION_QUADRATURE_X2_B; return 0; case TIM_SMCR_SMS_ENCODER_MODE_3: - *function = STM32_COUNT_ENCODER_MODE_3; + *function = COUNTER_FUNCTION_QUADRATURE_X4; return 0; default: return -EINVAL; } } -static int stm32_count_function_set(struct counter_device *counter, - struct counter_count *count, - size_t function) +static int stm32_count_function_write(struct counter_device *counter, + struct counter_count *count, + enum counter_function function) { struct stm32_timer_cnt *const priv = counter->priv; u32 cr1, sms; switch (function) { - case STM32_COUNT_SLAVE_MODE_DISABLED: + case COUNTER_FUNCTION_INCREASE: sms = TIM_SMCR_SMS_SLAVE_MODE_DISABLED; break; - case STM32_COUNT_ENCODER_MODE_1: + case COUNTER_FUNCTION_QUADRATURE_X2_A: sms = TIM_SMCR_SMS_ENCODER_MODE_1; break; - case STM32_COUNT_ENCODER_MODE_2: + case COUNTER_FUNCTION_QUADRATURE_X2_B: sms = TIM_SMCR_SMS_ENCODER_MODE_2; break; - case STM32_COUNT_ENCODER_MODE_3: + case COUNTER_FUNCTION_QUADRATURE_X4: sms = TIM_SMCR_SMS_ENCODER_MODE_3; break; default: @@ -150,44 +136,37 @@ static int stm32_count_function_set(struct counter_device *counter, return 0; } -static ssize_t stm32_count_direction_read(struct counter_device *counter, +static int stm32_count_direction_read(struct counter_device *counter, struct counter_count *count, - void *private, char *buf) + enum counter_count_direction *direction) { struct stm32_timer_cnt *const priv = counter->priv; - const char *direction; u32 cr1; regmap_read(priv->regmap, TIM_CR1, &cr1); - direction = (cr1 & TIM_CR1_DIR) ? "backward" : "forward"; + *direction = (cr1 & TIM_CR1_DIR) ? COUNTER_COUNT_DIRECTION_BACKWARD : + COUNTER_COUNT_DIRECTION_FORWARD; - return scnprintf(buf, PAGE_SIZE, "%s\n", direction); + return 0; } -static ssize_t stm32_count_ceiling_read(struct counter_device *counter, - struct counter_count *count, - void *private, char *buf) +static int stm32_count_ceiling_read(struct counter_device *counter, + struct counter_count *count, u64 *ceiling) { struct stm32_timer_cnt *const priv = counter->priv; u32 arr; regmap_read(priv->regmap, TIM_ARR, &arr); - return snprintf(buf, PAGE_SIZE, "%u\n", arr); + *ceiling = arr; + + return 0; } -static ssize_t stm32_count_ceiling_write(struct counter_device *counter, - struct counter_count *count, - void *private, - const char *buf, size_t len) +static int stm32_count_ceiling_write(struct counter_device *counter, + struct counter_count *count, u64 ceiling) { struct stm32_timer_cnt *const priv = counter->priv; - unsigned int ceiling; - int ret; - - ret = kstrtouint(buf, 0, &ceiling); - if (ret) - return ret; if (ceiling > priv->max_arr) return -ERANGE; @@ -196,34 +175,27 @@ static ssize_t stm32_count_ceiling_write(struct counter_device *counter, regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0); regmap_write(priv->regmap, TIM_ARR, ceiling); - return len; + return 0; } -static ssize_t stm32_count_enable_read(struct counter_device *counter, - struct counter_count *count, - void *private, char *buf) +static int stm32_count_enable_read(struct counter_device *counter, + struct counter_count *count, u8 *enable) { struct stm32_timer_cnt *const priv = counter->priv; u32 cr1; regmap_read(priv->regmap, TIM_CR1, &cr1); - return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)(cr1 & TIM_CR1_CEN)); + *enable = cr1 & TIM_CR1_CEN; + + return 0; } -static ssize_t stm32_count_enable_write(struct counter_device *counter, - struct counter_count *count, - void *private, - const char *buf, size_t len) +static int stm32_count_enable_write(struct counter_device *counter, + struct counter_count *count, u8 enable) { struct stm32_timer_cnt *const priv = counter->priv; - int err; u32 cr1; - bool enable; - - err = kstrtobool(buf, &enable); - if (err) - return err; if (enable) { regmap_read(priv->regmap, TIM_CR1, &cr1); @@ -242,70 +214,55 @@ static ssize_t stm32_count_enable_write(struct counter_device *counter, /* Keep enabled state to properly handle low power states */ priv->enabled = enable; - return len; + return 0; } -static const struct counter_count_ext stm32_count_ext[] = { - { - .name = "direction", - .read = stm32_count_direction_read, - }, - { - .name = "enable", - .read = stm32_count_enable_read, - .write = stm32_count_enable_write - }, - { - .name = "ceiling", - .read = stm32_count_ceiling_read, - .write = stm32_count_ceiling_write - }, -}; - -enum stm32_synapse_action { - STM32_SYNAPSE_ACTION_NONE, - STM32_SYNAPSE_ACTION_BOTH_EDGES +static struct counter_comp stm32_count_ext[] = { + COUNTER_COMP_DIRECTION(stm32_count_direction_read), + COUNTER_COMP_ENABLE(stm32_count_enable_read, stm32_count_enable_write), + COUNTER_COMP_CEILING(stm32_count_ceiling_read, + stm32_count_ceiling_write), }; static const enum counter_synapse_action stm32_synapse_actions[] = { - [STM32_SYNAPSE_ACTION_NONE] = COUNTER_SYNAPSE_ACTION_NONE, - [STM32_SYNAPSE_ACTION_BOTH_EDGES] = COUNTER_SYNAPSE_ACTION_BOTH_EDGES + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES }; -static int stm32_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, - size_t *action) +static int stm32_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { - size_t function; + enum counter_function function; int err; - err = stm32_count_function_get(counter, count, &function); + err = stm32_count_function_read(counter, count, &function); if (err) return err; switch (function) { - case STM32_COUNT_SLAVE_MODE_DISABLED: + case COUNTER_FUNCTION_INCREASE: /* counts on internal clock when CEN=1 */ - *action = STM32_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; return 0; - case STM32_COUNT_ENCODER_MODE_1: + case COUNTER_FUNCTION_QUADRATURE_X2_A: /* counts up/down on TI1FP1 edge depending on TI2FP2 level */ if (synapse->signal->id == count->synapses[0].signal->id) - *action = STM32_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; else - *action = STM32_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; return 0; - case STM32_COUNT_ENCODER_MODE_2: + case COUNTER_FUNCTION_QUADRATURE_X2_B: /* counts up/down on TI2FP2 edge depending on TI1FP1 level */ if (synapse->signal->id == count->synapses[1].signal->id) - *action = STM32_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; else - *action = STM32_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; return 0; - case STM32_COUNT_ENCODER_MODE_3: + case COUNTER_FUNCTION_QUADRATURE_X4: /* counts up/down on both TI1FP1 and TI2FP2 edges */ - *action = STM32_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; default: return -EINVAL; @@ -315,9 +272,9 @@ static int stm32_action_get(struct counter_device *counter, static const struct counter_ops stm32_timer_cnt_ops = { .count_read = stm32_count_read, .count_write = stm32_count_write, - .function_get = stm32_count_function_get, - .function_set = stm32_count_function_set, - .action_get = stm32_action_get, + .function_read = stm32_count_function_read, + .function_write = stm32_count_function_write, + .action_read = stm32_action_read, }; static struct counter_signal stm32_signals[] = { diff --git a/drivers/counter/ti-eqep.c b/drivers/counter/ti-eqep.c index 94fe58bb3eab..09817c953f9a 100644 --- a/drivers/counter/ti-eqep.c +++ b/drivers/counter/ti-eqep.c @@ -13,6 +13,7 @@ #include #include #include +#include /* 32-bit registers */ #define QPOSCNT 0x0 @@ -73,19 +74,13 @@ enum { }; /* Position Counter Input Modes */ -enum { +enum ti_eqep_count_func { TI_EQEP_COUNT_FUNC_QUAD_COUNT, TI_EQEP_COUNT_FUNC_DIR_COUNT, TI_EQEP_COUNT_FUNC_UP_COUNT, TI_EQEP_COUNT_FUNC_DOWN_COUNT, }; -enum { - TI_EQEP_SYNAPSE_ACTION_BOTH_EDGES, - TI_EQEP_SYNAPSE_ACTION_RISING_EDGE, - TI_EQEP_SYNAPSE_ACTION_NONE, -}; - struct ti_eqep_cnt { struct counter_device counter; struct regmap *regmap32; @@ -93,7 +88,7 @@ struct ti_eqep_cnt { }; static int ti_eqep_count_read(struct counter_device *counter, - struct counter_count *count, unsigned long *val) + struct counter_count *count, u64 *val) { struct ti_eqep_cnt *priv = counter->priv; u32 cnt; @@ -105,7 +100,7 @@ static int ti_eqep_count_read(struct counter_device *counter, } static int ti_eqep_count_write(struct counter_device *counter, - struct counter_count *count, unsigned long val) + struct counter_count *count, u64 val) { struct ti_eqep_cnt *priv = counter->priv; u32 max; @@ -117,64 +112,100 @@ static int ti_eqep_count_write(struct counter_device *counter, return regmap_write(priv->regmap32, QPOSCNT, val); } -static int ti_eqep_function_get(struct counter_device *counter, - struct counter_count *count, size_t *function) +static int ti_eqep_function_read(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function) { struct ti_eqep_cnt *priv = counter->priv; u32 qdecctl; regmap_read(priv->regmap16, QDECCTL, &qdecctl); - *function = (qdecctl & QDECCTL_QSRC) >> QDECCTL_QSRC_SHIFT; + + switch ((qdecctl & QDECCTL_QSRC) >> QDECCTL_QSRC_SHIFT) { + case TI_EQEP_COUNT_FUNC_QUAD_COUNT: + *function = COUNTER_FUNCTION_QUADRATURE_X4; + break; + case TI_EQEP_COUNT_FUNC_DIR_COUNT: + *function = COUNTER_FUNCTION_PULSE_DIRECTION; + break; + case TI_EQEP_COUNT_FUNC_UP_COUNT: + *function = COUNTER_FUNCTION_INCREASE; + break; + case TI_EQEP_COUNT_FUNC_DOWN_COUNT: + *function = COUNTER_FUNCTION_DECREASE; + break; + } return 0; } -static int ti_eqep_function_set(struct counter_device *counter, - struct counter_count *count, size_t function) +static int ti_eqep_function_write(struct counter_device *counter, + struct counter_count *count, + enum counter_function function) { struct ti_eqep_cnt *priv = counter->priv; + enum ti_eqep_count_func qsrc; + + switch (function) { + case COUNTER_FUNCTION_QUADRATURE_X4: + qsrc = TI_EQEP_COUNT_FUNC_QUAD_COUNT; + break; + case COUNTER_FUNCTION_PULSE_DIRECTION: + qsrc = TI_EQEP_COUNT_FUNC_DIR_COUNT; + break; + case COUNTER_FUNCTION_INCREASE: + qsrc = TI_EQEP_COUNT_FUNC_UP_COUNT; + break; + case COUNTER_FUNCTION_DECREASE: + qsrc = TI_EQEP_COUNT_FUNC_DOWN_COUNT; + break; + default: + /* should never reach this path */ + return -EINVAL; + } return regmap_write_bits(priv->regmap16, QDECCTL, QDECCTL_QSRC, - function << QDECCTL_QSRC_SHIFT); + qsrc << QDECCTL_QSRC_SHIFT); } -static int ti_eqep_action_get(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, size_t *action) +static int ti_eqep_action_read(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action) { struct ti_eqep_cnt *priv = counter->priv; - size_t function; + enum counter_function function; u32 qdecctl; int err; - err = ti_eqep_function_get(counter, count, &function); + err = ti_eqep_function_read(counter, count, &function); if (err) return err; switch (function) { - case TI_EQEP_COUNT_FUNC_QUAD_COUNT: + case COUNTER_FUNCTION_QUADRATURE_X4: /* In quadrature mode, the rising and falling edge of both * QEPA and QEPB trigger QCLK. */ - *action = TI_EQEP_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; return 0; - case TI_EQEP_COUNT_FUNC_DIR_COUNT: + case COUNTER_FUNCTION_PULSE_DIRECTION: /* In direction-count mode only rising edge of QEPA is counted * and QEPB gives direction. */ switch (synapse->signal->id) { case TI_EQEP_SIGNAL_QEPA: - *action = TI_EQEP_SYNAPSE_ACTION_RISING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; return 0; case TI_EQEP_SIGNAL_QEPB: - *action = TI_EQEP_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; return 0; default: /* should never reach this path */ return -EINVAL; } - case TI_EQEP_COUNT_FUNC_UP_COUNT: - case TI_EQEP_COUNT_FUNC_DOWN_COUNT: + case COUNTER_FUNCTION_INCREASE: + case COUNTER_FUNCTION_DECREASE: /* In up/down-count modes only QEPA is counted and QEPB is not * used. */ @@ -185,12 +216,12 @@ static int ti_eqep_action_get(struct counter_device *counter, return err; if (qdecctl & QDECCTL_XCR) - *action = TI_EQEP_SYNAPSE_ACTION_BOTH_EDGES; + *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES; else - *action = TI_EQEP_SYNAPSE_ACTION_RISING_EDGE; + *action = COUNTER_SYNAPSE_ACTION_RISING_EDGE; return 0; case TI_EQEP_SIGNAL_QEPB: - *action = TI_EQEP_SYNAPSE_ACTION_NONE; + *action = COUNTER_SYNAPSE_ACTION_NONE; return 0; default: /* should never reach this path */ @@ -205,82 +236,67 @@ static int ti_eqep_action_get(struct counter_device *counter, static const struct counter_ops ti_eqep_counter_ops = { .count_read = ti_eqep_count_read, .count_write = ti_eqep_count_write, - .function_get = ti_eqep_function_get, - .function_set = ti_eqep_function_set, - .action_get = ti_eqep_action_get, + .function_read = ti_eqep_function_read, + .function_write = ti_eqep_function_write, + .action_read = ti_eqep_action_read, }; -static ssize_t ti_eqep_position_ceiling_read(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, char *buf) +static int ti_eqep_position_ceiling_read(struct counter_device *counter, + struct counter_count *count, + u64 *ceiling) { struct ti_eqep_cnt *priv = counter->priv; u32 qposmax; regmap_read(priv->regmap32, QPOSMAX, &qposmax); - return sprintf(buf, "%u\n", qposmax); + *ceiling = qposmax; + + return 0; } -static ssize_t ti_eqep_position_ceiling_write(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, const char *buf, - size_t len) +static int ti_eqep_position_ceiling_write(struct counter_device *counter, + struct counter_count *count, + u64 ceiling) { struct ti_eqep_cnt *priv = counter->priv; - int err; - u32 res; - err = kstrtouint(buf, 0, &res); - if (err < 0) - return err; + if (ceiling != (u32)ceiling) + return -ERANGE; - regmap_write(priv->regmap32, QPOSMAX, res); + regmap_write(priv->regmap32, QPOSMAX, ceiling); - return len; + return 0; } -static ssize_t ti_eqep_position_enable_read(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, char *buf) +static int ti_eqep_position_enable_read(struct counter_device *counter, + struct counter_count *count, u8 *enable) { struct ti_eqep_cnt *priv = counter->priv; u32 qepctl; regmap_read(priv->regmap16, QEPCTL, &qepctl); - return sprintf(buf, "%u\n", !!(qepctl & QEPCTL_PHEN)); + *enable = !!(qepctl & QEPCTL_PHEN); + + return 0; } -static ssize_t ti_eqep_position_enable_write(struct counter_device *counter, - struct counter_count *count, - void *ext_priv, const char *buf, - size_t len) +static int ti_eqep_position_enable_write(struct counter_device *counter, + struct counter_count *count, u8 enable) { struct ti_eqep_cnt *priv = counter->priv; - int err; - bool res; - - err = kstrtobool(buf, &res); - if (err < 0) - return err; - regmap_write_bits(priv->regmap16, QEPCTL, QEPCTL_PHEN, res ? -1 : 0); + regmap_write_bits(priv->regmap16, QEPCTL, QEPCTL_PHEN, enable ? -1 : 0); - return len; + return 0; } -static struct counter_count_ext ti_eqep_position_ext[] = { - { - .name = "ceiling", - .read = ti_eqep_position_ceiling_read, - .write = ti_eqep_position_ceiling_write, - }, - { - .name = "enable", - .read = ti_eqep_position_enable_read, - .write = ti_eqep_position_enable_write, - }, +static struct counter_comp ti_eqep_position_ext[] = { + COUNTER_COMP_CEILING(ti_eqep_position_ceiling_read, + ti_eqep_position_ceiling_write), + COUNTER_COMP_ENABLE(ti_eqep_position_enable_read, + ti_eqep_position_enable_write), }; static struct counter_signal ti_eqep_signals[] = { @@ -295,16 +311,16 @@ static struct counter_signal ti_eqep_signals[] = { }; static const enum counter_function ti_eqep_position_functions[] = { - [TI_EQEP_COUNT_FUNC_QUAD_COUNT] = COUNTER_FUNCTION_QUADRATURE_X4, - [TI_EQEP_COUNT_FUNC_DIR_COUNT] = COUNTER_FUNCTION_PULSE_DIRECTION, - [TI_EQEP_COUNT_FUNC_UP_COUNT] = COUNTER_FUNCTION_INCREASE, - [TI_EQEP_COUNT_FUNC_DOWN_COUNT] = COUNTER_FUNCTION_DECREASE, + COUNTER_FUNCTION_QUADRATURE_X4, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_DECREASE, }; static const enum counter_synapse_action ti_eqep_position_synapse_actions[] = { - [TI_EQEP_SYNAPSE_ACTION_BOTH_EDGES] = COUNTER_SYNAPSE_ACTION_BOTH_EDGES, - [TI_EQEP_SYNAPSE_ACTION_RISING_EDGE] = COUNTER_SYNAPSE_ACTION_RISING_EDGE, - [TI_EQEP_SYNAPSE_ACTION_NONE] = COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_NONE, }; static struct counter_synapse ti_eqep_position_synapses[] = { diff --git a/include/linux/counter.h b/include/linux/counter.h index d16ce2819b48..b69277f5c4c5 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -6,42 +6,184 @@ #ifndef _COUNTER_H_ #define _COUNTER_H_ -#include #include +#include #include +struct counter_device; +struct counter_count; +struct counter_synapse; +struct counter_signal; + +enum counter_comp_type { + COUNTER_COMP_U8, + COUNTER_COMP_U64, + COUNTER_COMP_BOOL, + COUNTER_COMP_SIGNAL_LEVEL, + COUNTER_COMP_FUNCTION, + COUNTER_COMP_SYNAPSE_ACTION, + COUNTER_COMP_ENUM, + COUNTER_COMP_COUNT_DIRECTION, + COUNTER_COMP_COUNT_MODE, +}; + +enum counter_scope { + COUNTER_SCOPE_DEVICE, + COUNTER_SCOPE_SIGNAL, + COUNTER_SCOPE_COUNT, +}; + enum counter_count_direction { - COUNTER_COUNT_DIRECTION_FORWARD = 0, - COUNTER_COUNT_DIRECTION_BACKWARD + COUNTER_COUNT_DIRECTION_FORWARD, + COUNTER_COUNT_DIRECTION_BACKWARD, }; -extern const char *const counter_count_direction_str[2]; enum counter_count_mode { - COUNTER_COUNT_MODE_NORMAL = 0, + COUNTER_COUNT_MODE_NORMAL, COUNTER_COUNT_MODE_RANGE_LIMIT, COUNTER_COUNT_MODE_NON_RECYCLE, - COUNTER_COUNT_MODE_MODULO_N + COUNTER_COUNT_MODE_MODULO_N, }; -extern const char *const counter_count_mode_str[4]; -struct counter_device; -struct counter_signal; +enum counter_function { + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_DECREASE, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X1_A, + COUNTER_FUNCTION_QUADRATURE_X1_B, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X2_B, + COUNTER_FUNCTION_QUADRATURE_X4, +}; + +enum counter_signal_level { + COUNTER_SIGNAL_LEVEL_LOW, + COUNTER_SIGNAL_LEVEL_HIGH, +}; + +enum counter_synapse_action { + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, +}; /** - * struct counter_signal_ext - Counter Signal extensions - * @name: attribute name - * @read: read callback for this attribute; may be NULL - * @write: write callback for this attribute; may be NULL - * @priv: data private to the driver + * struct counter_comp - Counter component node + * @type: Counter component data type + * @name: device-specific component name + * @priv: component-relevant data + * @action_read Synapse action mode read callback. The read value of the + * respective Synapse action mode should be passed back via + * the action parameter. + * @device_u8_read Device u8 component read callback. The read value of the + * respective Device u8 component should be passed back via + * the val parameter. + * @count_u8_read Count u8 component read callback. The read value of the + * respective Count u8 component should be passed back via + * the val parameter. + * @signal_u8_read Signal u8 component read callback. The read value of the + * respective Signal u8 component should be passed back via + * the val parameter. + * @device_u32_read Device u32 component read callback. The read value of + * the respective Device u32 component should be passed + * back via the val parameter. + * @count_u32_read Count u32 component read callback. The read value of the + * respective Count u32 component should be passed back via + * the val parameter. + * @signal_u32_read Signal u32 component read callback. The read value of + * the respective Signal u32 component should be passed + * back via the val parameter. + * @device_u64_read Device u64 component read callback. The read value of + * the respective Device u64 component should be passed + * back via the val parameter. + * @count_u64_read Count u64 component read callback. The read value of the + * respective Count u64 component should be passed back via + * the val parameter. + * @signal_u64_read Signal u64 component read callback. The read value of + * the respective Signal u64 component should be passed + * back via the val parameter. + * @action_write Synapse action mode write callback. The write value of + * the respective Synapse action mode is passed via the + * action parameter. + * @device_u8_write Device u8 component write callback. The write value of + * the respective Device u8 component is passed via the val + * parameter. + * @count_u8_write Count u8 component write callback. The write value of + * the respective Count u8 component is passed via the val + * parameter. + * @signal_u8_write Signal u8 component write callback. The write value of + * the respective Signal u8 component is passed via the val + * parameter. + * @device_u32_write Device u32 component write callback. The write value of + * the respective Device u32 component is passed via the + * val parameter. + * @count_u32_write Count u32 component write callback. The write value of + * the respective Count u32 component is passed via the val + * parameter. + * @signal_u32_write Signal u32 component write callback. The write value of + * the respective Signal u32 component is passed via the + * val parameter. + * @device_u64_write Device u64 component write callback. The write value of + * the respective Device u64 component is passed via the + * val parameter. + * @count_u64_write Count u64 component write callback. The write value of + * the respective Count u64 component is passed via the val + * parameter. + * @signal_u64_write Signal u64 component write callback. The write value of + * the respective Signal u64 component is passed via the + * val parameter. */ -struct counter_signal_ext { +struct counter_comp { + enum counter_comp_type type; const char *name; - ssize_t (*read)(struct counter_device *counter, - struct counter_signal *signal, void *priv, char *buf); - ssize_t (*write)(struct counter_device *counter, - struct counter_signal *signal, void *priv, - const char *buf, size_t len); void *priv; + union { + int (*action_read)(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action); + int (*device_u8_read)(struct counter_device *counter, u8 *val); + int (*count_u8_read)(struct counter_device *counter, + struct counter_count *count, u8 *val); + int (*signal_u8_read)(struct counter_device *counter, + struct counter_signal *signal, u8 *val); + int (*device_u32_read)(struct counter_device *counter, + u32 *val); + int (*count_u32_read)(struct counter_device *counter, + struct counter_count *count, u32 *val); + int (*signal_u32_read)(struct counter_device *counter, + struct counter_signal *signal, u32 *val); + int (*device_u64_read)(struct counter_device *counter, + u64 *val); + int (*count_u64_read)(struct counter_device *counter, + struct counter_count *count, u64 *val); + int (*signal_u64_read)(struct counter_device *counter, + struct counter_signal *signal, u64 *val); + }; + union { + int (*action_write)(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action action); + int (*device_u8_write)(struct counter_device *counter, u8 val); + int (*count_u8_write)(struct counter_device *counter, + struct counter_count *count, u8 val); + int (*signal_u8_write)(struct counter_device *counter, + struct counter_signal *signal, u8 val); + int (*device_u32_write)(struct counter_device *counter, + u32 val); + int (*count_u32_write)(struct counter_device *counter, + struct counter_count *count, u32 val); + int (*signal_u32_write)(struct counter_device *counter, + struct counter_signal *signal, u32 val); + int (*device_u64_write)(struct counter_device *counter, + u64 val); + int (*count_u64_write)(struct counter_device *counter, + struct counter_count *count, u64 val); + int (*signal_u64_write)(struct counter_device *counter, + struct counter_signal *signal, u64 val); + }; }; /** @@ -51,248 +193,52 @@ struct counter_signal_ext { * as it appears in the datasheet documentation * @ext: optional array of Counter Signal extensions * @num_ext: number of Counter Signal extensions specified in @ext - * @priv: optional private data supplied by driver */ struct counter_signal { int id; const char *name; - const struct counter_signal_ext *ext; + struct counter_comp *ext; size_t num_ext; - - void *priv; -}; - -/** - * struct counter_signal_enum_ext - Signal enum extension attribute - * @items: Array of strings - * @num_items: Number of items specified in @items - * @set: Set callback function; may be NULL - * @get: Get callback function; may be NULL - * - * The counter_signal_enum_ext structure can be used to implement enum style - * Signal extension attributes. Enum style attributes are those which have a set - * of strings that map to unsigned integer values. The Generic Counter Signal - * enum extension helper code takes care of mapping between value and string, as - * well as generating a "_available" file which contains a list of all available - * items. The get callback is used to query the currently active item; the index - * of the item within the respective items array is returned via the 'item' - * parameter. The set callback is called when the attribute is updated; the - * 'item' parameter contains the index of the newly activated item within the - * respective items array. - */ -struct counter_signal_enum_ext { - const char * const *items; - size_t num_items; - int (*get)(struct counter_device *counter, - struct counter_signal *signal, size_t *item); - int (*set)(struct counter_device *counter, - struct counter_signal *signal, size_t item); -}; - -/** - * COUNTER_SIGNAL_ENUM() - Initialize Signal enum extension - * @_name: Attribute name - * @_e: Pointer to a counter_signal_enum_ext structure - * - * This should usually be used together with COUNTER_SIGNAL_ENUM_AVAILABLE() - */ -#define COUNTER_SIGNAL_ENUM(_name, _e) \ -{ \ - .name = (_name), \ - .read = counter_signal_enum_read, \ - .write = counter_signal_enum_write, \ - .priv = (_e) \ -} - -/** - * COUNTER_SIGNAL_ENUM_AVAILABLE() - Initialize Signal enum available extension - * @_name: Attribute name ("_available" will be appended to the name) - * @_e: Pointer to a counter_signal_enum_ext structure - * - * Creates a read only attribute that lists all the available enum items in a - * newline separated list. This should usually be used together with - * COUNTER_SIGNAL_ENUM() - */ -#define COUNTER_SIGNAL_ENUM_AVAILABLE(_name, _e) \ -{ \ - .name = (_name "_available"), \ - .read = counter_signal_enum_available_read, \ - .priv = (_e) \ -} - -enum counter_synapse_action { - COUNTER_SYNAPSE_ACTION_NONE = 0, - COUNTER_SYNAPSE_ACTION_RISING_EDGE, - COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - COUNTER_SYNAPSE_ACTION_BOTH_EDGES }; /** * struct counter_synapse - Counter Synapse node - * @action: index of current action mode * @actions_list: array of available action modes * @num_actions: number of action modes specified in @actions_list * @signal: pointer to associated signal */ struct counter_synapse { - size_t action; const enum counter_synapse_action *actions_list; size_t num_actions; struct counter_signal *signal; }; -struct counter_count; - -/** - * struct counter_count_ext - Counter Count extension - * @name: attribute name - * @read: read callback for this attribute; may be NULL - * @write: write callback for this attribute; may be NULL - * @priv: data private to the driver - */ -struct counter_count_ext { - const char *name; - ssize_t (*read)(struct counter_device *counter, - struct counter_count *count, void *priv, char *buf); - ssize_t (*write)(struct counter_device *counter, - struct counter_count *count, void *priv, - const char *buf, size_t len); - void *priv; -}; - -enum counter_function { - COUNTER_FUNCTION_INCREASE = 0, - COUNTER_FUNCTION_DECREASE, - COUNTER_FUNCTION_PULSE_DIRECTION, - COUNTER_FUNCTION_QUADRATURE_X1_A, - COUNTER_FUNCTION_QUADRATURE_X1_B, - COUNTER_FUNCTION_QUADRATURE_X2_A, - COUNTER_FUNCTION_QUADRATURE_X2_B, - COUNTER_FUNCTION_QUADRATURE_X4 -}; - /** * struct counter_count - Counter Count node * @id: unique ID used to identify Count * @name: device-specific Count name; ideally, this should match * the name as it appears in the datasheet documentation - * @function: index of current function mode * @functions_list: array available function modes * @num_functions: number of function modes specified in @functions_list * @synapses: array of synapses for initialization * @num_synapses: number of synapses specified in @synapses * @ext: optional array of Counter Count extensions * @num_ext: number of Counter Count extensions specified in @ext - * @priv: optional private data supplied by driver */ struct counter_count { int id; const char *name; - size_t function; const enum counter_function *functions_list; size_t num_functions; struct counter_synapse *synapses; size_t num_synapses; - const struct counter_count_ext *ext; + struct counter_comp *ext; size_t num_ext; - - void *priv; -}; - -/** - * struct counter_count_enum_ext - Count enum extension attribute - * @items: Array of strings - * @num_items: Number of items specified in @items - * @set: Set callback function; may be NULL - * @get: Get callback function; may be NULL - * - * The counter_count_enum_ext structure can be used to implement enum style - * Count extension attributes. Enum style attributes are those which have a set - * of strings that map to unsigned integer values. The Generic Counter Count - * enum extension helper code takes care of mapping between value and string, as - * well as generating a "_available" file which contains a list of all available - * items. The get callback is used to query the currently active item; the index - * of the item within the respective items array is returned via the 'item' - * parameter. The set callback is called when the attribute is updated; the - * 'item' parameter contains the index of the newly activated item within the - * respective items array. - */ -struct counter_count_enum_ext { - const char * const *items; - size_t num_items; - int (*get)(struct counter_device *counter, struct counter_count *count, - size_t *item); - int (*set)(struct counter_device *counter, struct counter_count *count, - size_t item); -}; - -/** - * COUNTER_COUNT_ENUM() - Initialize Count enum extension - * @_name: Attribute name - * @_e: Pointer to a counter_count_enum_ext structure - * - * This should usually be used together with COUNTER_COUNT_ENUM_AVAILABLE() - */ -#define COUNTER_COUNT_ENUM(_name, _e) \ -{ \ - .name = (_name), \ - .read = counter_count_enum_read, \ - .write = counter_count_enum_write, \ - .priv = (_e) \ -} - -/** - * COUNTER_COUNT_ENUM_AVAILABLE() - Initialize Count enum available extension - * @_name: Attribute name ("_available" will be appended to the name) - * @_e: Pointer to a counter_count_enum_ext structure - * - * Creates a read only attribute that lists all the available enum items in a - * newline separated list. This should usually be used together with - * COUNTER_COUNT_ENUM() - */ -#define COUNTER_COUNT_ENUM_AVAILABLE(_name, _e) \ -{ \ - .name = (_name "_available"), \ - .read = counter_count_enum_available_read, \ - .priv = (_e) \ -} - -/** - * struct counter_device_attr_group - internal container for attribute group - * @attr_group: Counter sysfs attributes group - * @attr_list: list to keep track of created Counter sysfs attributes - * @num_attr: number of Counter sysfs attributes - */ -struct counter_device_attr_group { - struct attribute_group attr_group; - struct list_head attr_list; - size_t num_attr; -}; - -/** - * struct counter_device_state - internal state container for a Counter device - * @id: unique ID used to identify the Counter - * @dev: internal device structure - * @groups_list: attribute groups list (for Signals, Counts, and ext) - * @num_groups: number of attribute groups containers - * @groups: Counter sysfs attribute groups (to populate @dev.groups) - */ -struct counter_device_state { - int id; - struct device dev; - struct counter_device_attr_group *groups_list; - size_t num_groups; - const struct attribute_group **groups; -}; - -enum counter_signal_level { - COUNTER_SIGNAL_LEVEL_LOW, - COUNTER_SIGNAL_LEVEL_HIGH, }; /** @@ -306,117 +252,47 @@ enum counter_signal_level { * @count_write: optional write callback for Count attribute. The write * value for the respective Count is passed in via the val * parameter. - * @function_get: function to get the current count function mode. Returns - * 0 on success and negative error code on error. The index - * of the respective Count's returned function mode should - * be passed back via the function parameter. - * @function_set: function to set the count function mode. function is the - * index of the requested function mode from the respective - * Count's functions_list array. - * @action_get: function to get the current action mode. Returns 0 on - * success and negative error code on error. The index of - * the respective Synapse's returned action mode should be - * passed back via the action parameter. - * @action_set: function to set the action mode. action is the index of - * the requested action mode from the respective Synapse's - * actions_list array. + * @function_read: read callback the Count function modes. The read + * function mode of the respective Count should be passed + * back via the function parameter. + * @function_write: write callback for Count function modes. The function + * mode to write for the respective Count is passed in via + * the function parameter. + * @action_read: read callback the Synapse action modes. The read action + * mode of the respective Synapse should be passed back via + * the action parameter. + * @action_write: write callback for Synapse action modes. The action mode + * to write for the respective Synapse is passed in via the + * action parameter. */ struct counter_ops { int (*signal_read)(struct counter_device *counter, struct counter_signal *signal, enum counter_signal_level *level); int (*count_read)(struct counter_device *counter, - struct counter_count *count, unsigned long *val); + struct counter_count *count, u64 *value); int (*count_write)(struct counter_device *counter, - struct counter_count *count, unsigned long val); - int (*function_get)(struct counter_device *counter, - struct counter_count *count, size_t *function); - int (*function_set)(struct counter_device *counter, - struct counter_count *count, size_t function); - int (*action_get)(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, size_t *action); - int (*action_set)(struct counter_device *counter, - struct counter_count *count, - struct counter_synapse *synapse, size_t action); -}; - -/** - * struct counter_device_ext - Counter device extension - * @name: attribute name - * @read: read callback for this attribute; may be NULL - * @write: write callback for this attribute; may be NULL - * @priv: data private to the driver - */ -struct counter_device_ext { - const char *name; - ssize_t (*read)(struct counter_device *counter, void *priv, char *buf); - ssize_t (*write)(struct counter_device *counter, void *priv, - const char *buf, size_t len); - void *priv; + struct counter_count *count, u64 value); + int (*function_read)(struct counter_device *counter, + struct counter_count *count, + enum counter_function *function); + int (*function_write)(struct counter_device *counter, + struct counter_count *count, + enum counter_function function); + int (*action_read)(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action *action); + int (*action_write)(struct counter_device *counter, + struct counter_count *count, + struct counter_synapse *synapse, + enum counter_synapse_action action); }; -/** - * struct counter_device_enum_ext - Counter enum extension attribute - * @items: Array of strings - * @num_items: Number of items specified in @items - * @set: Set callback function; may be NULL - * @get: Get callback function; may be NULL - * - * The counter_device_enum_ext structure can be used to implement enum style - * Counter extension attributes. Enum style attributes are those which have a - * set of strings that map to unsigned integer values. The Generic Counter enum - * extension helper code takes care of mapping between value and string, as well - * as generating a "_available" file which contains a list of all available - * items. The get callback is used to query the currently active item; the index - * of the item within the respective items array is returned via the 'item' - * parameter. The set callback is called when the attribute is updated; the - * 'item' parameter contains the index of the newly activated item within the - * respective items array. - */ -struct counter_device_enum_ext { - const char * const *items; - size_t num_items; - int (*get)(struct counter_device *counter, size_t *item); - int (*set)(struct counter_device *counter, size_t item); -}; - -/** - * COUNTER_DEVICE_ENUM() - Initialize Counter enum extension - * @_name: Attribute name - * @_e: Pointer to a counter_device_enum_ext structure - * - * This should usually be used together with COUNTER_DEVICE_ENUM_AVAILABLE() - */ -#define COUNTER_DEVICE_ENUM(_name, _e) \ -{ \ - .name = (_name), \ - .read = counter_device_enum_read, \ - .write = counter_device_enum_write, \ - .priv = (_e) \ -} - -/** - * COUNTER_DEVICE_ENUM_AVAILABLE() - Initialize Counter enum available extension - * @_name: Attribute name ("_available" will be appended to the name) - * @_e: Pointer to a counter_device_enum_ext structure - * - * Creates a read only attribute that lists all the available enum items in a - * newline separated list. This should usually be used together with - * COUNTER_DEVICE_ENUM() - */ -#define COUNTER_DEVICE_ENUM_AVAILABLE(_name, _e) \ -{ \ - .name = (_name "_available"), \ - .read = counter_device_enum_available_read, \ - .priv = (_e) \ -} - /** * struct counter_device - Counter data structure * @name: name of the device as it appears in the datasheet * @parent: optional parent device providing the counters - * @device_state: internal device state container * @ops: callbacks from driver * @signals: array of Signals * @num_signals: number of Signals specified in @signals @@ -425,11 +301,11 @@ struct counter_device_enum_ext { * @ext: optional array of Counter device extensions * @num_ext: number of Counter device extensions specified in @ext * @priv: optional private data supplied by driver + * @dev: internal device structure */ struct counter_device { const char *name; struct device *parent; - struct counter_device_state *device_state; const struct counter_ops *ops; @@ -438,17 +314,159 @@ struct counter_device { struct counter_count *counts; size_t num_counts; - const struct counter_device_ext *ext; + struct counter_comp *ext; size_t num_ext; void *priv; + + struct device dev; }; int counter_register(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, struct counter_device *const counter); -void devm_counter_unregister(struct device *dev, - struct counter_device *const counter); + +#define COUNTER_COMP_DEVICE_U8(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_U8, \ + .name = (_name), \ + .device_u8_read = (_read), \ + .device_u8_write = (_write), \ +} +#define COUNTER_COMP_COUNT_U8(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_U8, \ + .name = (_name), \ + .count_u8_read = (_read), \ + .count_u8_write = (_write), \ +} +#define COUNTER_COMP_SIGNAL_U8(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_U8, \ + .name = (_name), \ + .signal_u8_read = (_read), \ + .signal_u8_write = (_write), \ +} + +#define COUNTER_COMP_DEVICE_U64(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_U64, \ + .name = (_name), \ + .device_u64_read = (_read), \ + .device_u64_write = (_write), \ +} +#define COUNTER_COMP_COUNT_U64(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_U64, \ + .name = (_name), \ + .count_u64_read = (_read), \ + .count_u64_write = (_write), \ +} +#define COUNTER_COMP_SIGNAL_U64(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_U64, \ + .name = (_name), \ + .signal_u64_read = (_read), \ + .signal_u64_write = (_write), \ +} + +#define COUNTER_COMP_DEVICE_BOOL(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_BOOL, \ + .name = (_name), \ + .device_u8_read = (_read), \ + .device_u8_write = (_write), \ +} +#define COUNTER_COMP_COUNT_BOOL(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_BOOL, \ + .name = (_name), \ + .count_u8_read = (_read), \ + .count_u8_write = (_write), \ +} +#define COUNTER_COMP_SIGNAL_BOOL(_name, _read, _write) \ +{ \ + .type = COUNTER_COMP_BOOL, \ + .name = (_name), \ + .signal_u8_read = (_read), \ + .signal_u8_write = (_write), \ +} + +struct counter_available { + union { + const u32 *enums; + const char *const *strs; + }; + size_t num_items; +}; + +#define DEFINE_COUNTER_AVAILABLE(_name, _enums) \ + struct counter_available _name = { \ + .enums = (_enums), \ + .num_items = ARRAY_SIZE(_enums), \ + } + +#define DEFINE_COUNTER_ENUM(_name, _strs) \ + struct counter_available _name = { \ + .strs = (_strs), \ + .num_items = ARRAY_SIZE(_strs), \ + } + +#define COUNTER_COMP_DEVICE_ENUM(_name, _get, _set, _available) \ +{ \ + .type = COUNTER_COMP_ENUM, \ + .name = (_name), \ + .device_u32_read = (_get), \ + .device_u32_write = (_set), \ + .priv = &(_available), \ +} +#define COUNTER_COMP_COUNT_ENUM(_name, _get, _set, _available) \ +{ \ + .type = COUNTER_COMP_ENUM, \ + .name = (_name), \ + .count_u32_read = (_get), \ + .count_u32_write = (_set), \ + .priv = &(_available), \ +} +#define COUNTER_COMP_SIGNAL_ENUM(_name, _get, _set, _available) \ +{ \ + .type = COUNTER_COMP_ENUM, \ + .name = (_name), \ + .signal_u32_read = (_get), \ + .signal_u32_write = (_set), \ + .priv = &(_available), \ +} + +#define COUNTER_COMP_CEILING(_read, _write) \ + COUNTER_COMP_COUNT_U64("ceiling", _read, _write) + +#define COUNTER_COMP_COUNT_MODE(_read, _write, _available) \ +{ \ + .type = COUNTER_COMP_COUNT_MODE, \ + .name = "count_mode", \ + .count_u32_read = (_read), \ + .count_u32_write = (_write), \ + .priv = &(_available), \ +} + +#define COUNTER_COMP_DIRECTION(_read) \ +{ \ + .type = COUNTER_COMP_COUNT_DIRECTION, \ + .name = "direction", \ + .count_u32_read = (_read), \ +} + +#define COUNTER_COMP_ENABLE(_read, _write) \ + COUNTER_COMP_COUNT_BOOL("enable", _read, _write) + +#define COUNTER_COMP_FLOOR(_read, _write) \ + COUNTER_COMP_COUNT_U64("floor", _read, _write) + +#define COUNTER_COMP_PRESET(_read, _write) \ + COUNTER_COMP_COUNT_U64("preset", _read, _write) + +#define COUNTER_COMP_PRESET_ENABLE(_read, _write) \ + COUNTER_COMP_COUNT_BOOL("preset_enable", _read, _write) #endif /* _COUNTER_H_ */ diff --git a/include/linux/counter_enum.h b/include/linux/counter_enum.h deleted file mode 100644 index 9f917298a88f..000000000000 --- a/include/linux/counter_enum.h +++ /dev/null @@ -1,45 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Counter interface enum functions - * Copyright (C) 2018 William Breathitt Gray - */ -#ifndef _COUNTER_ENUM_H_ -#define _COUNTER_ENUM_H_ - -#include - -struct counter_device; -struct counter_signal; -struct counter_count; - -ssize_t counter_signal_enum_read(struct counter_device *counter, - struct counter_signal *signal, void *priv, - char *buf); -ssize_t counter_signal_enum_write(struct counter_device *counter, - struct counter_signal *signal, void *priv, - const char *buf, size_t len); - -ssize_t counter_signal_enum_available_read(struct counter_device *counter, - struct counter_signal *signal, - void *priv, char *buf); - -ssize_t counter_count_enum_read(struct counter_device *counter, - struct counter_count *count, void *priv, - char *buf); -ssize_t counter_count_enum_write(struct counter_device *counter, - struct counter_count *count, void *priv, - const char *buf, size_t len); - -ssize_t counter_count_enum_available_read(struct counter_device *counter, - struct counter_count *count, - void *priv, char *buf); - -ssize_t counter_device_enum_read(struct counter_device *counter, void *priv, - char *buf); -ssize_t counter_device_enum_write(struct counter_device *counter, void *priv, - const char *buf, size_t len); - -ssize_t counter_device_enum_available_read(struct counter_device *counter, - void *priv, char *buf); - -#endif /* _COUNTER_ENUM_H_ */ -- cgit v1.2.3 From 712392f558ef4280b67659fb2d52854dcfc7c8ba Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Fri, 27 Aug 2021 12:47:48 +0900 Subject: counter: Update counter.h comments to reflect sysfs internalization The Counter subsystem architecture and driver implementations have changed in order to handle Counter sysfs interactions in a more consistent way. This patch updates the Generic Counter interface header file comments to reflect the changes. Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/19da8ae0c05381b0967c8a334b67f86b814eb880.1630031207.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/counter-core.c | 3 ++ include/linux/counter.h | 62 ++++++++++++++++++++---------------------- 2 files changed, 33 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index c533a6ff12cf..3cda2c47bacb 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -38,6 +38,9 @@ static struct bus_type counter_bus_type = { * This function registers a Counter to the system. A sysfs "counter" directory * will be created and populated with sysfs attributes correlating with the * Counter Signals, Synapses, and Counts respectively. + * + * RETURNS: + * 0 on success, negative error number on failure. */ int counter_register(struct counter_device *const counter) { diff --git a/include/linux/counter.h b/include/linux/counter.h index b69277f5c4c5..445f22d8bfe2 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -188,11 +188,10 @@ struct counter_comp { /** * struct counter_signal - Counter Signal node - * @id: unique ID used to identify signal - * @name: device-specific Signal name; ideally, this should match the name - * as it appears in the datasheet documentation - * @ext: optional array of Counter Signal extensions - * @num_ext: number of Counter Signal extensions specified in @ext + * @id: unique ID used to identify the Signal + * @name: device-specific Signal name + * @ext: optional array of Signal extensions + * @num_ext: number of Signal extensions specified in @ext */ struct counter_signal { int id; @@ -206,7 +205,7 @@ struct counter_signal { * struct counter_synapse - Counter Synapse node * @actions_list: array of available action modes * @num_actions: number of action modes specified in @actions_list - * @signal: pointer to associated signal + * @signal: pointer to the associated Signal */ struct counter_synapse { const enum counter_synapse_action *actions_list; @@ -217,15 +216,14 @@ struct counter_synapse { /** * struct counter_count - Counter Count node - * @id: unique ID used to identify Count - * @name: device-specific Count name; ideally, this should match - * the name as it appears in the datasheet documentation - * @functions_list: array available function modes + * @id: unique ID used to identify the Count + * @name: device-specific Count name + * @functions_list: array of available function modes * @num_functions: number of function modes specified in @functions_list - * @synapses: array of synapses for initialization - * @num_synapses: number of synapses specified in @synapses - * @ext: optional array of Counter Count extensions - * @num_ext: number of Counter Count extensions specified in @ext + * @synapses: array of Synapses for initialization + * @num_synapses: number of Synapses specified in @synapses + * @ext: optional array of Count extensions + * @num_ext: number of Count extensions specified in @ext */ struct counter_count { int id; @@ -243,27 +241,27 @@ struct counter_count { /** * struct counter_ops - Callbacks from driver - * @signal_read: optional read callback for Signal attribute. The read - * level of the respective Signal should be passed back via - * the level parameter. - * @count_read: optional read callback for Count attribute. The read - * value of the respective Count should be passed back via - * the val parameter. - * @count_write: optional write callback for Count attribute. The write - * value for the respective Count is passed in via the val + * @signal_read: optional read callback for Signals. The read level of + * the respective Signal should be passed back via the + * level parameter. + * @count_read: read callback for Counts. The read value of the + * respective Count should be passed back via the value + * parameter. + * @count_write: optional write callback for Counts. The write value for + * the respective Count is passed in via the value * parameter. * @function_read: read callback the Count function modes. The read * function mode of the respective Count should be passed * back via the function parameter. - * @function_write: write callback for Count function modes. The function - * mode to write for the respective Count is passed in via - * the function parameter. - * @action_read: read callback the Synapse action modes. The read action - * mode of the respective Synapse should be passed back via - * the action parameter. - * @action_write: write callback for Synapse action modes. The action mode - * to write for the respective Synapse is passed in via the - * action parameter. + * @function_write: optional write callback for Count function modes. The + * function mode to write for the respective Count is + * passed in via the function parameter. + * @action_read: optional read callback the Synapse action modes. The + * read action mode of the respective Synapse should be + * passed back via the action parameter. + * @action_write: optional write callback for Synapse action modes. The + * action mode to write for the respective Synapse is + * passed in via the action parameter. */ struct counter_ops { int (*signal_read)(struct counter_device *counter, @@ -291,7 +289,7 @@ struct counter_ops { /** * struct counter_device - Counter data structure - * @name: name of the device as it appears in the datasheet + * @name: name of the device * @parent: optional parent device providing the counters * @ops: callbacks from driver * @signals: array of Signals -- cgit v1.2.3 From e65c26f413718ed2e6d788491adcd8cebc0f44b6 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 29 Sep 2021 12:15:58 +0900 Subject: counter: Move counter enums to uapi header This is in preparation for a subsequent patch implementing a character device interface for the Counter subsystem. Reviewed-by: David Lechner Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/962a5f2027fafcf4f77c10e1baf520463960d1ee.1632884256.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- MAINTAINERS | 1 + include/linux/counter.h | 42 +-------------------------------- include/uapi/linux/counter.h | 56 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 58 insertions(+), 41 deletions(-) create mode 100644 include/uapi/linux/counter.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index b98a34fcec4b..8310a42abdab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4804,6 +4804,7 @@ F: Documentation/ABI/testing/sysfs-bus-counter F: Documentation/driver-api/generic-counter.rst F: drivers/counter/ F: include/linux/counter.h +F: include/uapi/linux/counter.h CP2615 I2C DRIVER M: Bence Csókás diff --git a/include/linux/counter.h b/include/linux/counter.h index 445f22d8bfe2..7c9f7e23953a 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -9,6 +9,7 @@ #include #include #include +#include struct counter_device; struct counter_count; @@ -27,47 +28,6 @@ enum counter_comp_type { COUNTER_COMP_COUNT_MODE, }; -enum counter_scope { - COUNTER_SCOPE_DEVICE, - COUNTER_SCOPE_SIGNAL, - COUNTER_SCOPE_COUNT, -}; - -enum counter_count_direction { - COUNTER_COUNT_DIRECTION_FORWARD, - COUNTER_COUNT_DIRECTION_BACKWARD, -}; - -enum counter_count_mode { - COUNTER_COUNT_MODE_NORMAL, - COUNTER_COUNT_MODE_RANGE_LIMIT, - COUNTER_COUNT_MODE_NON_RECYCLE, - COUNTER_COUNT_MODE_MODULO_N, -}; - -enum counter_function { - COUNTER_FUNCTION_INCREASE, - COUNTER_FUNCTION_DECREASE, - COUNTER_FUNCTION_PULSE_DIRECTION, - COUNTER_FUNCTION_QUADRATURE_X1_A, - COUNTER_FUNCTION_QUADRATURE_X1_B, - COUNTER_FUNCTION_QUADRATURE_X2_A, - COUNTER_FUNCTION_QUADRATURE_X2_B, - COUNTER_FUNCTION_QUADRATURE_X4, -}; - -enum counter_signal_level { - COUNTER_SIGNAL_LEVEL_LOW, - COUNTER_SIGNAL_LEVEL_HIGH, -}; - -enum counter_synapse_action { - COUNTER_SYNAPSE_ACTION_NONE, - COUNTER_SYNAPSE_ACTION_RISING_EDGE, - COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - COUNTER_SYNAPSE_ACTION_BOTH_EDGES, -}; - /** * struct counter_comp - Counter component node * @type: Counter component data type diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h new file mode 100644 index 000000000000..6113938a6044 --- /dev/null +++ b/include/uapi/linux/counter.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Userspace ABI for Counter character devices + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _UAPI_COUNTER_H_ +#define _UAPI_COUNTER_H_ + +/* Component scope definitions */ +enum counter_scope { + COUNTER_SCOPE_DEVICE, + COUNTER_SCOPE_SIGNAL, + COUNTER_SCOPE_COUNT, +}; + +/* Count direction values */ +enum counter_count_direction { + COUNTER_COUNT_DIRECTION_FORWARD, + COUNTER_COUNT_DIRECTION_BACKWARD, +}; + +/* Count mode values */ +enum counter_count_mode { + COUNTER_COUNT_MODE_NORMAL, + COUNTER_COUNT_MODE_RANGE_LIMIT, + COUNTER_COUNT_MODE_NON_RECYCLE, + COUNTER_COUNT_MODE_MODULO_N, +}; + +/* Count function values */ +enum counter_function { + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_DECREASE, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X1_A, + COUNTER_FUNCTION_QUADRATURE_X1_B, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X2_B, + COUNTER_FUNCTION_QUADRATURE_X4, +}; + +/* Signal values */ +enum counter_signal_level { + COUNTER_SIGNAL_LEVEL_LOW, + COUNTER_SIGNAL_LEVEL_HIGH, +}; + +/* Action mode values */ +enum counter_synapse_action { + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, +}; + +#endif /* _UAPI_COUNTER_H_ */ -- cgit v1.2.3 From b6c50affda5957a3629b149a91c7f6688ffce7f7 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 29 Sep 2021 12:15:59 +0900 Subject: counter: Add character device interface This patch introduces a character device interface for the Counter subsystem. Device data is exposed through standard character device read operations. Device data is gathered when a Counter event is pushed by the respective Counter device driver. Configuration is handled via ioctl operations on the respective Counter character device node. Cc: David Lechner Cc: Gwendal Grignou Cc: Dan Carpenter Cc: Oleksij Rempel Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/b8b8c64b4065aedff43699ad1f0e2f8d1419c15b.1632884256.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/Makefile | 2 +- drivers/counter/counter-chrdev.c | 578 +++++++++++++++++++++++++++++++++++++++ drivers/counter/counter-chrdev.h | 14 + drivers/counter/counter-core.c | 56 +++- include/linux/counter.h | 56 ++++ include/uapi/linux/counter.h | 98 +++++++ 6 files changed, 798 insertions(+), 6 deletions(-) create mode 100644 drivers/counter/counter-chrdev.c create mode 100644 drivers/counter/counter-chrdev.h (limited to 'include/linux') diff --git a/drivers/counter/Makefile b/drivers/counter/Makefile index 1ab7e087fdc2..8fde6c100ebc 100644 --- a/drivers/counter/Makefile +++ b/drivers/counter/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_COUNTER) += counter.o -counter-y := counter-core.o counter-sysfs.o +counter-y := counter-core.o counter-sysfs.o counter-chrdev.o obj-$(CONFIG_104_QUAD_8) += 104-quad-8.o obj-$(CONFIG_INTERRUPT_CNT) += interrupt-cnt.o diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c new file mode 100644 index 000000000000..967c94ae95bb --- /dev/null +++ b/drivers/counter/counter-chrdev.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic Counter character device interface + * Copyright (C) 2020 William Breathitt Gray + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "counter-chrdev.h" + +struct counter_comp_node { + struct list_head l; + struct counter_component component; + struct counter_comp comp; + void *parent; +}; + +#define counter_comp_read_is_equal(a, b) \ + (a.action_read == b.action_read || \ + a.device_u8_read == b.device_u8_read || \ + a.count_u8_read == b.count_u8_read || \ + a.signal_u8_read == b.signal_u8_read || \ + a.device_u32_read == b.device_u32_read || \ + a.count_u32_read == b.count_u32_read || \ + a.signal_u32_read == b.signal_u32_read || \ + a.device_u64_read == b.device_u64_read || \ + a.count_u64_read == b.count_u64_read || \ + a.signal_u64_read == b.signal_u64_read) + +#define counter_comp_read_is_set(comp) \ + (comp.action_read || \ + comp.device_u8_read || \ + comp.count_u8_read || \ + comp.signal_u8_read || \ + comp.device_u32_read || \ + comp.count_u32_read || \ + comp.signal_u32_read || \ + comp.device_u64_read || \ + comp.count_u64_read || \ + comp.signal_u64_read) + +static ssize_t counter_chrdev_read(struct file *filp, char __user *buf, + size_t len, loff_t *f_ps) +{ + struct counter_device *const counter = filp->private_data; + int err; + unsigned int copied; + + if (!counter->ops) + return -ENODEV; + + if (len < sizeof(struct counter_event)) + return -EINVAL; + + do { + if (kfifo_is_empty(&counter->events)) { + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + err = wait_event_interruptible(counter->events_wait, + !kfifo_is_empty(&counter->events) || + !counter->ops); + if (err < 0) + return err; + if (!counter->ops) + return -ENODEV; + } + + if (mutex_lock_interruptible(&counter->events_lock)) + return -ERESTARTSYS; + err = kfifo_to_user(&counter->events, buf, len, &copied); + mutex_unlock(&counter->events_lock); + if (err < 0) + return err; + } while (!copied); + + return copied; +} + +static __poll_t counter_chrdev_poll(struct file *filp, + struct poll_table_struct *pollt) +{ + struct counter_device *const counter = filp->private_data; + __poll_t events = 0; + + if (!counter->ops) + return events; + + poll_wait(filp, &counter->events_wait, pollt); + + if (!kfifo_is_empty(&counter->events)) + events = EPOLLIN | EPOLLRDNORM; + + return events; +} + +static void counter_events_list_free(struct list_head *const events_list) +{ + struct counter_event_node *p, *n; + struct counter_comp_node *q, *o; + + list_for_each_entry_safe(p, n, events_list, l) { + /* Free associated component nodes */ + list_for_each_entry_safe(q, o, &p->comp_list, l) { + list_del(&q->l); + kfree(q); + } + + /* Free event node */ + list_del(&p->l); + kfree(p); + } +} + +static int counter_set_event_node(struct counter_device *const counter, + struct counter_watch *const watch, + const struct counter_comp_node *const cfg) +{ + struct counter_event_node *event_node; + int err = 0; + struct counter_comp_node *comp_node; + + /* Search for event in the list */ + list_for_each_entry(event_node, &counter->next_events_list, l) + if (event_node->event == watch->event && + event_node->channel == watch->channel) + break; + + /* If event is not already in the list */ + if (&event_node->l == &counter->next_events_list) { + /* Allocate new event node */ + event_node = kmalloc(sizeof(*event_node), GFP_KERNEL); + if (!event_node) + return -ENOMEM; + + /* Configure event node and add to the list */ + event_node->event = watch->event; + event_node->channel = watch->channel; + INIT_LIST_HEAD(&event_node->comp_list); + list_add(&event_node->l, &counter->next_events_list); + } + + /* Check if component watch has already been set before */ + list_for_each_entry(comp_node, &event_node->comp_list, l) + if (comp_node->parent == cfg->parent && + counter_comp_read_is_equal(comp_node->comp, cfg->comp)) { + err = -EINVAL; + goto exit_free_event_node; + } + + /* Allocate component node */ + comp_node = kmalloc(sizeof(*comp_node), GFP_KERNEL); + if (!comp_node) { + err = -ENOMEM; + goto exit_free_event_node; + } + *comp_node = *cfg; + + /* Add component node to event node */ + list_add_tail(&comp_node->l, &event_node->comp_list); + +exit_free_event_node: + /* Free event node if no one else is watching */ + if (list_empty(&event_node->comp_list)) { + list_del(&event_node->l); + kfree(event_node); + } + + return err; +} + +static int counter_enable_events(struct counter_device *const counter) +{ + unsigned long flags; + int err = 0; + + mutex_lock(&counter->n_events_list_lock); + spin_lock_irqsave(&counter->events_list_lock, flags); + + counter_events_list_free(&counter->events_list); + list_replace_init(&counter->next_events_list, + &counter->events_list); + + if (counter->ops->events_configure) + err = counter->ops->events_configure(counter); + + spin_unlock_irqrestore(&counter->events_list_lock, flags); + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static int counter_disable_events(struct counter_device *const counter) +{ + unsigned long flags; + int err = 0; + + spin_lock_irqsave(&counter->events_list_lock, flags); + + counter_events_list_free(&counter->events_list); + + if (counter->ops->events_configure) + err = counter->ops->events_configure(counter); + + spin_unlock_irqrestore(&counter->events_list_lock, flags); + + mutex_lock(&counter->n_events_list_lock); + + counter_events_list_free(&counter->next_events_list); + + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static int counter_add_watch(struct counter_device *const counter, + const unsigned long arg) +{ + void __user *const uwatch = (void __user *)arg; + struct counter_watch watch; + struct counter_comp_node comp_node = {}; + size_t parent, id; + struct counter_comp *ext; + size_t num_ext; + int err = 0; + + if (copy_from_user(&watch, uwatch, sizeof(watch))) + return -EFAULT; + + if (watch.component.type == COUNTER_COMPONENT_NONE) + goto no_component; + + parent = watch.component.parent; + + /* Configure parent component info for comp node */ + switch (watch.component.scope) { + case COUNTER_SCOPE_DEVICE: + ext = counter->ext; + num_ext = counter->num_ext; + break; + case COUNTER_SCOPE_SIGNAL: + if (parent >= counter->num_signals) + return -EINVAL; + parent = array_index_nospec(parent, counter->num_signals); + + comp_node.parent = counter->signals + parent; + + ext = counter->signals[parent].ext; + num_ext = counter->signals[parent].num_ext; + break; + case COUNTER_SCOPE_COUNT: + if (parent >= counter->num_counts) + return -EINVAL; + parent = array_index_nospec(parent, counter->num_counts); + + comp_node.parent = counter->counts + parent; + + ext = counter->counts[parent].ext; + num_ext = counter->counts[parent].num_ext; + break; + default: + return -EINVAL; + } + + id = watch.component.id; + + /* Configure component info for comp node */ + switch (watch.component.type) { + case COUNTER_COMPONENT_SIGNAL: + if (watch.component.scope != COUNTER_SCOPE_SIGNAL) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_SIGNAL_LEVEL; + comp_node.comp.signal_u32_read = counter->ops->signal_read; + break; + case COUNTER_COMPONENT_COUNT: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_U64; + comp_node.comp.count_u64_read = counter->ops->count_read; + break; + case COUNTER_COMPONENT_FUNCTION: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_FUNCTION; + comp_node.comp.count_u32_read = counter->ops->function_read; + break; + case COUNTER_COMPONENT_SYNAPSE_ACTION: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + if (id >= counter->counts[parent].num_synapses) + return -EINVAL; + id = array_index_nospec(id, counter->counts[parent].num_synapses); + + comp_node.comp.type = COUNTER_COMP_SYNAPSE_ACTION; + comp_node.comp.action_read = counter->ops->action_read; + comp_node.comp.priv = counter->counts[parent].synapses + id; + break; + case COUNTER_COMPONENT_EXTENSION: + if (id >= num_ext) + return -EINVAL; + id = array_index_nospec(id, num_ext); + + comp_node.comp = ext[id]; + break; + default: + return -EINVAL; + } + if (!counter_comp_read_is_set(comp_node.comp)) + return -EOPNOTSUPP; + +no_component: + mutex_lock(&counter->n_events_list_lock); + + if (counter->ops->watch_validate) { + err = counter->ops->watch_validate(counter, &watch); + if (err < 0) + goto err_exit; + } + + comp_node.component = watch.component; + + err = counter_set_event_node(counter, &watch, &comp_node); + +err_exit: + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static long counter_chrdev_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct counter_device *const counter = filp->private_data; + int ret = -ENODEV; + + mutex_lock(&counter->ops_exist_lock); + + if (!counter->ops) + goto out_unlock; + + switch (cmd) { + case COUNTER_ADD_WATCH_IOCTL: + ret = counter_add_watch(counter, arg); + break; + case COUNTER_ENABLE_EVENTS_IOCTL: + ret = counter_enable_events(counter); + break; + case COUNTER_DISABLE_EVENTS_IOCTL: + ret = counter_disable_events(counter); + break; + default: + ret = -ENOIOCTLCMD; + break; + } + +out_unlock: + mutex_unlock(&counter->ops_exist_lock); + + return ret; +} + +static int counter_chrdev_open(struct inode *inode, struct file *filp) +{ + struct counter_device *const counter = container_of(inode->i_cdev, + typeof(*counter), + chrdev); + + /* Ensure chrdev is not opened more than 1 at a time */ + if (!atomic_add_unless(&counter->chrdev_lock, 1, 1)) + return -EBUSY; + + get_device(&counter->dev); + filp->private_data = counter; + + return nonseekable_open(inode, filp); +} + +static int counter_chrdev_release(struct inode *inode, struct file *filp) +{ + struct counter_device *const counter = filp->private_data; + int ret = 0; + + mutex_lock(&counter->ops_exist_lock); + + if (!counter->ops) { + /* Free any lingering held memory */ + counter_events_list_free(&counter->events_list); + counter_events_list_free(&counter->next_events_list); + ret = -ENODEV; + goto out_unlock; + } + + ret = counter_disable_events(counter); + if (ret < 0) { + mutex_unlock(&counter->ops_exist_lock); + return ret; + } + +out_unlock: + mutex_unlock(&counter->ops_exist_lock); + + put_device(&counter->dev); + atomic_dec(&counter->chrdev_lock); + + return ret; +} + +static const struct file_operations counter_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = counter_chrdev_read, + .poll = counter_chrdev_poll, + .unlocked_ioctl = counter_chrdev_ioctl, + .open = counter_chrdev_open, + .release = counter_chrdev_release, +}; + +int counter_chrdev_add(struct counter_device *const counter) +{ + /* Initialize Counter events lists */ + INIT_LIST_HEAD(&counter->events_list); + INIT_LIST_HEAD(&counter->next_events_list); + spin_lock_init(&counter->events_list_lock); + mutex_init(&counter->n_events_list_lock); + init_waitqueue_head(&counter->events_wait); + mutex_init(&counter->events_lock); + + /* Initialize character device */ + atomic_set(&counter->chrdev_lock, 0); + cdev_init(&counter->chrdev, &counter_fops); + + /* Allocate Counter events queue */ + return kfifo_alloc(&counter->events, 64, GFP_KERNEL); +} + +void counter_chrdev_remove(struct counter_device *const counter) +{ + kfifo_free(&counter->events); +} + +static int counter_get_data(struct counter_device *const counter, + const struct counter_comp_node *const comp_node, + u64 *const value) +{ + const struct counter_comp *const comp = &comp_node->comp; + void *const parent = comp_node->parent; + u8 value_u8 = 0; + u32 value_u32 = 0; + int ret; + + if (comp_node->component.type == COUNTER_COMPONENT_NONE) + return 0; + + switch (comp->type) { + case COUNTER_COMP_U8: + case COUNTER_COMP_BOOL: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + ret = comp->device_u8_read(counter, &value_u8); + break; + case COUNTER_SCOPE_SIGNAL: + ret = comp->signal_u8_read(counter, parent, &value_u8); + break; + case COUNTER_SCOPE_COUNT: + ret = comp->count_u8_read(counter, parent, &value_u8); + break; + } + *value = value_u8; + return ret; + case COUNTER_COMP_SIGNAL_LEVEL: + case COUNTER_COMP_FUNCTION: + case COUNTER_COMP_ENUM: + case COUNTER_COMP_COUNT_DIRECTION: + case COUNTER_COMP_COUNT_MODE: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + ret = comp->device_u32_read(counter, &value_u32); + break; + case COUNTER_SCOPE_SIGNAL: + ret = comp->signal_u32_read(counter, parent, + &value_u32); + break; + case COUNTER_SCOPE_COUNT: + ret = comp->count_u32_read(counter, parent, &value_u32); + break; + } + *value = value_u32; + return ret; + case COUNTER_COMP_U64: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + return comp->device_u64_read(counter, value); + case COUNTER_SCOPE_SIGNAL: + return comp->signal_u64_read(counter, parent, value); + case COUNTER_SCOPE_COUNT: + return comp->count_u64_read(counter, parent, value); + default: + return -EINVAL; + } + case COUNTER_COMP_SYNAPSE_ACTION: + ret = comp->action_read(counter, parent, comp->priv, + &value_u32); + *value = value_u32; + return ret; + default: + return -EINVAL; + } +} + +/** + * counter_push_event - queue event for userspace reading + * @counter: pointer to Counter structure + * @event: triggered event + * @channel: event channel + * + * Note: If no one is watching for the respective event, it is silently + * discarded. + */ +void counter_push_event(struct counter_device *const counter, const u8 event, + const u8 channel) +{ + struct counter_event ev; + unsigned int copied = 0; + unsigned long flags; + struct counter_event_node *event_node; + struct counter_comp_node *comp_node; + + ev.timestamp = ktime_get_ns(); + ev.watch.event = event; + ev.watch.channel = channel; + + /* Could be in an interrupt context, so use a spin lock */ + spin_lock_irqsave(&counter->events_list_lock, flags); + + /* Search for event in the list */ + list_for_each_entry(event_node, &counter->events_list, l) + if (event_node->event == event && + event_node->channel == channel) + break; + + /* If event is not in the list */ + if (&event_node->l == &counter->events_list) + goto exit_early; + + /* Read and queue relevant comp for userspace */ + list_for_each_entry(comp_node, &event_node->comp_list, l) { + ev.watch.component = comp_node->component; + ev.status = -counter_get_data(counter, comp_node, &ev.value); + + copied += kfifo_in(&counter->events, &ev, 1); + } + +exit_early: + spin_unlock_irqrestore(&counter->events_list_lock, flags); + + if (copied) + wake_up_poll(&counter->events_wait, EPOLLIN); +} +EXPORT_SYMBOL_GPL(counter_push_event); diff --git a/drivers/counter/counter-chrdev.h b/drivers/counter/counter-chrdev.h new file mode 100644 index 000000000000..5529d16703c4 --- /dev/null +++ b/drivers/counter/counter-chrdev.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Counter character device interface + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _COUNTER_CHRDEV_H_ +#define _COUNTER_CHRDEV_H_ + +#include + +int counter_chrdev_add(struct counter_device *const counter); +void counter_chrdev_remove(struct counter_device *const counter); + +#endif /* _COUNTER_CHRDEV_H_ */ diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index 3cda2c47bacb..5acc54539623 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -3,14 +3,22 @@ * Generic Counter interface * Copyright (C) 2020 William Breathitt Gray */ +#include #include #include +#include #include +#include #include #include #include +#include #include +#include +#include +#include +#include "counter-chrdev.h" #include "counter-sysfs.h" /* Provides a unique ID for each counter device */ @@ -18,6 +26,9 @@ static DEFINE_IDA(counter_ida); static void counter_device_release(struct device *dev) { + struct counter_device *const counter = dev_get_drvdata(dev); + + counter_chrdev_remove(counter); ida_free(&counter_ida, dev->id); } @@ -31,6 +42,8 @@ static struct bus_type counter_bus_type = { .dev_name = "counter", }; +static dev_t counter_devt; + /** * counter_register - register Counter to the system * @counter: pointer to Counter to register @@ -53,10 +66,13 @@ int counter_register(struct counter_device *const counter) if (id < 0) return id; + mutex_init(&counter->ops_exist_lock); + /* Configure device structure for Counter */ dev->id = id; dev->type = &counter_device_type; dev->bus = &counter_bus_type; + dev->devt = MKDEV(MAJOR(counter_devt), id); if (counter->parent) { dev->parent = counter->parent; dev->of_node = counter->parent->of_node; @@ -64,18 +80,22 @@ int counter_register(struct counter_device *const counter) device_initialize(dev); dev_set_drvdata(dev, counter); - /* Add Counter sysfs attributes */ err = counter_sysfs_add(counter); if (err < 0) goto err_free_id; - /* Add device to system */ - err = device_add(dev); + err = counter_chrdev_add(counter); if (err < 0) goto err_free_id; + err = cdev_device_add(&counter->chrdev, dev); + if (err < 0) + goto err_remove_chrdev; + return 0; +err_remove_chrdev: + counter_chrdev_remove(counter); err_free_id: put_device(dev); return err; @@ -93,7 +113,16 @@ void counter_unregister(struct counter_device *const counter) if (!counter) return; - device_unregister(&counter->dev); + cdev_device_del(&counter->chrdev, &counter->dev); + + mutex_lock(&counter->ops_exist_lock); + + counter->ops = NULL; + wake_up(&counter->events_wait); + + mutex_unlock(&counter->ops_exist_lock); + + put_device(&counter->dev); } EXPORT_SYMBOL_GPL(counter_unregister); @@ -127,13 +156,30 @@ int devm_counter_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_counter_register); +#define COUNTER_DEV_MAX 256 + static int __init counter_init(void) { - return bus_register(&counter_bus_type); + int err; + + err = bus_register(&counter_bus_type); + if (err < 0) + return err; + + err = alloc_chrdev_region(&counter_devt, 0, COUNTER_DEV_MAX, "counter"); + if (err < 0) + goto err_unregister_bus; + + return 0; + +err_unregister_bus: + bus_unregister(&counter_bus_type); + return err; } static void __exit counter_exit(void) { + unregister_chrdev_region(counter_devt, COUNTER_DEV_MAX); bus_unregister(&counter_bus_type); } diff --git a/include/linux/counter.h b/include/linux/counter.h index 7c9f7e23953a..22b14a552b1d 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -6,9 +6,14 @@ #ifndef _COUNTER_H_ #define _COUNTER_H_ +#include #include #include +#include +#include +#include #include +#include #include struct counter_device; @@ -199,6 +204,20 @@ struct counter_count { size_t num_ext; }; +/** + * struct counter_event_node - Counter Event node + * @l: list of current watching Counter events + * @event: event that triggers + * @channel: event channel + * @comp_list: list of components to watch when event triggers + */ +struct counter_event_node { + struct list_head l; + u8 event; + u8 channel; + struct list_head comp_list; +}; + /** * struct counter_ops - Callbacks from driver * @signal_read: optional read callback for Signals. The read level of @@ -222,6 +241,13 @@ struct counter_count { * @action_write: optional write callback for Synapse action modes. The * action mode to write for the respective Synapse is * passed in via the action parameter. + * @events_configure: optional write callback to configure events. The list of + * struct counter_event_node may be accessed via the + * events_list member of the counter parameter. + * @watch_validate: optional callback to validate a watch. The Counter + * component watch configuration is passed in via the watch + * parameter. A return value of 0 indicates a valid Counter + * component watch configuration. */ struct counter_ops { int (*signal_read)(struct counter_device *counter, @@ -245,6 +271,9 @@ struct counter_ops { struct counter_count *count, struct counter_synapse *synapse, enum counter_synapse_action action); + int (*events_configure)(struct counter_device *counter); + int (*watch_validate)(struct counter_device *counter, + const struct counter_watch *watch); }; /** @@ -260,6 +289,16 @@ struct counter_ops { * @num_ext: number of Counter device extensions specified in @ext * @priv: optional private data supplied by driver * @dev: internal device structure + * @chrdev: internal character device structure + * @events_list: list of current watching Counter events + * @events_list_lock: lock to protect Counter events list operations + * @next_events_list: list of next watching Counter events + * @n_events_list_lock: lock to protect Counter next events list operations + * @events: queue of detected Counter events + * @events_wait: wait queue to allow blocking reads of Counter events + * @events_lock: lock to protect Counter events queue read operations + * @chrdev_lock: lock to limit chrdev to a single open at a time + * @ops_exist_lock: lock to prevent use during removal */ struct counter_device { const char *name; @@ -278,12 +317,29 @@ struct counter_device { void *priv; struct device dev; + struct cdev chrdev; + struct list_head events_list; + spinlock_t events_list_lock; + struct list_head next_events_list; + struct mutex n_events_list_lock; + DECLARE_KFIFO_PTR(events, struct counter_event); + wait_queue_head_t events_wait; + struct mutex events_lock; + /* + * chrdev_lock is locked by counter_chrdev_open() and unlocked by + * counter_chrdev_release(), so a mutex is not possible here because + * chrdev_lock will invariably be held when returning to user space + */ + atomic_t chrdev_lock; + struct mutex ops_exist_lock; }; int counter_register(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, struct counter_device *const counter); +void counter_push_event(struct counter_device *const counter, const u8 event, + const u8 channel); #define COUNTER_COMP_DEVICE_U8(_name, _read, _write) \ { \ diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h index 6113938a6044..d0aa95aeff7b 100644 --- a/include/uapi/linux/counter.h +++ b/include/uapi/linux/counter.h @@ -6,6 +6,19 @@ #ifndef _UAPI_COUNTER_H_ #define _UAPI_COUNTER_H_ +#include +#include + +/* Component type definitions */ +enum counter_component_type { + COUNTER_COMPONENT_NONE, + COUNTER_COMPONENT_SIGNAL, + COUNTER_COMPONENT_COUNT, + COUNTER_COMPONENT_FUNCTION, + COUNTER_COMPONENT_SYNAPSE_ACTION, + COUNTER_COMPONENT_EXTENSION, +}; + /* Component scope definitions */ enum counter_scope { COUNTER_SCOPE_DEVICE, @@ -13,6 +26,91 @@ enum counter_scope { COUNTER_SCOPE_COUNT, }; +/** + * struct counter_component - Counter component identification + * @type: component type (one of enum counter_component_type) + * @scope: component scope (one of enum counter_scope) + * @parent: parent ID (matching the ID suffix of the respective parent sysfs + * path as described by the ABI documentation file + * Documentation/ABI/testing/sysfs-bus-counter) + * @id: component ID (matching the ID provided by the respective *_component_id + * sysfs attribute of the desired component) + * + * For example, if the Count 2 ceiling extension of Counter device 4 is desired, + * set type equal to COUNTER_COMPONENT_EXTENSION, scope equal to + * COUNTER_COUNT_SCOPE, parent equal to 2, and id equal to the value provided by + * the respective /sys/bus/counter/devices/counter4/count2/ceiling_component_id + * sysfs attribute. + */ +struct counter_component { + __u8 type; + __u8 scope; + __u8 parent; + __u8 id; +}; + +/* Event type definitions */ +enum counter_event_type { + /* Count value increased past ceiling */ + COUNTER_EVENT_OVERFLOW, + /* Count value decreased past floor */ + COUNTER_EVENT_UNDERFLOW, + /* Count value increased past ceiling, or decreased past floor */ + COUNTER_EVENT_OVERFLOW_UNDERFLOW, + /* Count value reached threshold */ + COUNTER_EVENT_THRESHOLD, + /* Index signal detected */ + COUNTER_EVENT_INDEX, +}; + +/** + * struct counter_watch - Counter component watch configuration + * @component: component to watch when event triggers + * @event: event that triggers (one of enum counter_event_type) + * @channel: event channel (typically 0 unless the device supports concurrent + * events of the same type) + */ +struct counter_watch { + struct counter_component component; + __u8 event; + __u8 channel; +}; + +/* + * Queues a Counter watch for the specified event. + * + * The queued watches will not be applied until COUNTER_ENABLE_EVENTS_IOCTL is + * called. + */ +#define COUNTER_ADD_WATCH_IOCTL _IOW(0x3E, 0x00, struct counter_watch) +/* + * Enables monitoring the events specified by the Counter watches that were + * queued by COUNTER_ADD_WATCH_IOCTL. + * + * If events are already enabled, the new set of watches replaces the old one. + * Calling this ioctl also has the effect of clearing the queue of watches added + * by COUNTER_ADD_WATCH_IOCTL. + */ +#define COUNTER_ENABLE_EVENTS_IOCTL _IO(0x3E, 0x01) +/* + * Stops monitoring the previously enabled events. + */ +#define COUNTER_DISABLE_EVENTS_IOCTL _IO(0x3E, 0x02) + +/** + * struct counter_event - Counter event data + * @timestamp: best estimate of time of event occurrence, in nanoseconds + * @value: component value + * @watch: component watch configuration + * @status: return status (system error number) + */ +struct counter_event { + __aligned_u64 timestamp; + __aligned_u64 value; + struct counter_watch watch; + __u8 status; +}; + /* Count direction values */ enum counter_count_direction { COUNTER_COUNT_DIRECTION_FORWARD, -- cgit v1.2.3 From 914ff7719e8adaf87131dd7cd0a3520afcf89516 Mon Sep 17 00:00:00 2001 From: Kyung Min Park Date: Thu, 14 Oct 2021 13:38:32 +0800 Subject: iommu/vt-d: Dump DMAR translation structure when DMA fault occurs When the dmar translation fault happens, the kernel prints a single line fault reason with corresponding hexadecimal code defined in the Intel VT-d specification. Currently, when user wants to debug the translation fault in detail, debugfs is used for dumping the dmar_translation_struct, which is not available when the kernel failed to boot. Dump the DMAR translation structure, pagewalk the IO page table and print the page table entry when the fault happens. This takes effect only when CONFIG_DMAR_DEBUG is enabled. Signed-off-by: Kyung Min Park Link: https://lore.kernel.org/r/20210815203845.31287-1-kyung.min.park@intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20211014053839.727419-3-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/Kconfig | 4 ++ drivers/iommu/intel/dmar.c | 10 +++- drivers/iommu/intel/iommu.c | 113 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/dmar.h | 8 ++++ 4 files changed, 133 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig index 0ddb77115be7..247d0f2d5fdf 100644 --- a/drivers/iommu/intel/Kconfig +++ b/drivers/iommu/intel/Kconfig @@ -6,6 +6,9 @@ config DMAR_TABLE config DMAR_PERF bool +config DMAR_DEBUG + bool + config INTEL_IOMMU bool "Support for Intel IOMMU using DMA Remapping Devices" depends on PCI_MSI && ACPI && (X86 || IA64) @@ -31,6 +34,7 @@ config INTEL_IOMMU_DEBUGFS bool "Export Intel IOMMU internals in Debugfs" depends on IOMMU_DEBUGFS select DMAR_PERF + select DMAR_DEBUG help !!!WARNING!!! diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index b7708b93f3fa..915bff76fe96 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -1941,12 +1941,16 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, reason = dmar_get_fault_reason(fault_reason, &fault_type); - if (fault_type == INTR_REMAP) + if (fault_type == INTR_REMAP) { pr_err("[INTR-REMAP] Request device [%02x:%02x.%d] fault index 0x%llx [fault reason 0x%02x] %s\n", source_id >> 8, PCI_SLOT(source_id & 0xFF), PCI_FUNC(source_id & 0xFF), addr >> 48, fault_reason, reason); - else if (pasid == INVALID_IOASID) + + return 0; + } + + if (pasid == INVALID_IOASID) pr_err("[%s NO_PASID] Request device [%02x:%02x.%d] fault addr 0x%llx [fault reason 0x%02x] %s\n", type ? "DMA Read" : "DMA Write", source_id >> 8, PCI_SLOT(source_id & 0xFF), @@ -1959,6 +1963,8 @@ static int dmar_fault_do_one(struct intel_iommu *iommu, int type, PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason); + dmar_fault_dump_ptes(iommu, source_id, addr, pasid); + return 0; } diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 9a356075d345..abb2599998b1 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -156,6 +156,8 @@ static struct intel_iommu **g_iommus; static void __init check_tylersburg_isoch(void); static int rwbf_quirk; +static inline struct device_domain_info * +dmar_search_domain_by_dev_info(int segment, int bus, int devfn); /* * set to 1 to panic kernel if can't successfully enable VT-d @@ -996,6 +998,117 @@ out: spin_unlock_irqrestore(&iommu->lock, flags); } +#ifdef CONFIG_DMAR_DEBUG +static void pgtable_walk(struct intel_iommu *iommu, unsigned long pfn, u8 bus, u8 devfn) +{ + struct device_domain_info *info; + struct dma_pte *parent, *pte; + struct dmar_domain *domain; + int offset, level; + + info = dmar_search_domain_by_dev_info(iommu->segment, bus, devfn); + if (!info || !info->domain) { + pr_info("device [%02x:%02x.%d] not probed\n", + bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); + return; + } + + domain = info->domain; + level = agaw_to_level(domain->agaw); + parent = domain->pgd; + if (!parent) { + pr_info("no page table setup\n"); + return; + } + + while (1) { + offset = pfn_level_offset(pfn, level); + pte = &parent[offset]; + if (!pte || (dma_pte_superpage(pte) || !dma_pte_present(pte))) { + pr_info("PTE not present at level %d\n", level); + break; + } + + pr_info("pte level: %d, pte value: 0x%016llx\n", level, pte->val); + + if (level == 1) + break; + + parent = phys_to_virt(dma_pte_addr(pte)); + level--; + } +} + +void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, + unsigned long long addr, u32 pasid) +{ + struct pasid_dir_entry *dir, *pde; + struct pasid_entry *entries, *pte; + struct context_entry *ctx_entry; + struct root_entry *rt_entry; + u8 devfn = source_id & 0xff; + u8 bus = source_id >> 8; + int i, dir_index, index; + + pr_info("Dump %s table entries for IOVA 0x%llx\n", iommu->name, addr); + + /* root entry dump */ + rt_entry = &iommu->root_entry[bus]; + if (!rt_entry) { + pr_info("root table entry is not present\n"); + return; + } + + if (sm_supported(iommu)) + pr_info("scalable mode root entry: hi 0x%016llx, low 0x%016llx\n", + rt_entry->hi, rt_entry->lo); + else + pr_info("root entry: 0x%016llx", rt_entry->lo); + + /* context entry dump */ + ctx_entry = iommu_context_addr(iommu, bus, devfn, 0); + if (!ctx_entry) { + pr_info("context table entry is not present\n"); + return; + } + + pr_info("context entry: hi 0x%016llx, low 0x%016llx\n", + ctx_entry->hi, ctx_entry->lo); + + /* legacy mode does not require PASID entries */ + if (!sm_supported(iommu)) + goto pgtable_walk; + + /* get the pointer to pasid directory entry */ + dir = phys_to_virt(ctx_entry->lo & VTD_PAGE_MASK); + if (!dir) { + pr_info("pasid directory entry is not present\n"); + return; + } + /* For request-without-pasid, get the pasid from context entry */ + if (intel_iommu_sm && pasid == INVALID_IOASID) + pasid = PASID_RID2PASID; + + dir_index = pasid >> PASID_PDE_SHIFT; + pde = &dir[dir_index]; + pr_info("pasid dir entry: 0x%016llx\n", pde->val); + + /* get the pointer to the pasid table entry */ + entries = get_pasid_table_from_pde(pde); + if (!entries) { + pr_info("pasid table entry is not present\n"); + return; + } + index = pasid & PASID_PTE_MASK; + pte = &entries[index]; + for (i = 0; i < ARRAY_SIZE(pte->val); i++) + pr_info("pasid table entry[%d]: 0x%016llx\n", i, pte->val[i]); + +pgtable_walk: + pgtable_walk(iommu, addr >> VTD_PAGE_SHIFT, bus, devfn); +} +#endif + static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain, unsigned long pfn, int *target_level) { diff --git a/include/linux/dmar.h b/include/linux/dmar.h index e04436a7ff27..45e903d84733 100644 --- a/include/linux/dmar.h +++ b/include/linux/dmar.h @@ -131,6 +131,14 @@ static inline int dmar_res_noop(struct acpi_dmar_header *hdr, void *arg) return 0; } +#ifdef CONFIG_DMAR_DEBUG +void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, + unsigned long long addr, u32 pasid); +#else +static inline void dmar_fault_dump_ptes(struct intel_iommu *iommu, u16 source_id, + unsigned long long addr, u32 pasid) {} +#endif + #ifdef CONFIG_INTEL_IOMMU extern int iommu_detected, no_iommu; extern int intel_iommu_init(void); -- cgit v1.2.3 From b34380a6d767c54480a937951e6189a7f9699443 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 14 Oct 2021 13:38:33 +0800 Subject: iommu/vt-d: Remove duplicate identity domain flag The iommu_domain data structure already has the "type" field to keep the type of a domain. It's unnecessary to have the DOMAIN_FLAG_STATIC_IDENTITY flag in the vt-d implementation. This cleans it up with no functionality change. Signed-off-by: Lu Baolu Reviewed-by: Kevin Tian Link: https://lore.kernel.org/r/20210926114535.923263-1-baolu.lu@linux.intel.com Link: https://lore.kernel.org/r/20211014053839.727419-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 9 ++++----- include/linux/intel-iommu.h | 3 --- 2 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index abb2599998b1..ec9ceb2dcf57 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -528,7 +528,7 @@ static inline void free_devinfo_mem(void *vaddr) static inline int domain_type_is_si(struct dmar_domain *domain) { - return domain->flags & DOMAIN_FLAG_STATIC_IDENTITY; + return domain->domain.type == IOMMU_DOMAIN_IDENTITY; } static inline bool domain_use_first_level(struct dmar_domain *domain) @@ -1996,7 +1996,7 @@ static bool first_level_by_default(void) return scalable_mode_support() && intel_cap_flts_sanity(); } -static struct dmar_domain *alloc_domain(int flags) +static struct dmar_domain *alloc_domain(unsigned int type) { struct dmar_domain *domain; @@ -2006,7 +2006,6 @@ static struct dmar_domain *alloc_domain(int flags) memset(domain, 0, sizeof(*domain)); domain->nid = NUMA_NO_NODE; - domain->flags = flags; if (first_level_by_default()) domain->flags |= DOMAIN_FLAG_USE_FIRST_LEVEL; domain->has_iotlb_device = false; @@ -2825,7 +2824,7 @@ static int __init si_domain_init(int hw) struct device *dev; int i, nid, ret; - si_domain = alloc_domain(DOMAIN_FLAG_STATIC_IDENTITY); + si_domain = alloc_domain(IOMMU_DOMAIN_IDENTITY); if (!si_domain) return -EFAULT; @@ -4634,7 +4633,7 @@ static struct iommu_domain *intel_iommu_domain_alloc(unsigned type) case IOMMU_DOMAIN_DMA: case IOMMU_DOMAIN_DMA_FQ: case IOMMU_DOMAIN_UNMANAGED: - dmar_domain = alloc_domain(0); + dmar_domain = alloc_domain(type); if (!dmar_domain) { pr_err("Can't allocate dmar_domain\n"); return NULL; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 05a65eb155f7..65b15af3cf1a 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -517,9 +517,6 @@ struct context_entry { u64 hi; }; -/* si_domain contains mulitple devices */ -#define DOMAIN_FLAG_STATIC_IDENTITY BIT(0) - /* * When VT-d works in the scalable mode, it allows DMA translation to * happen through either first level or second level page table. This -- cgit v1.2.3 From 37c8041a818dec2cea22ea48a3f90d512a9e1fcd Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Thu, 14 Oct 2021 13:38:38 +0800 Subject: iommu/vt-d: Convert the return type of first_pte_in_page to bool The first_pte_in_page() returns true or false, so let's convert its return type to bool. In addition, use 'IS_ALIGNED' to make the code more readable and neater. Signed-off-by: Longpeng(Mike) Link: https://lore.kernel.org/r/20211008000433.1115-1-longpeng2@huawei.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20211014053839.727419-9-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-iommu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 65b15af3cf1a..52481625838c 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -705,9 +705,9 @@ static inline bool dma_pte_superpage(struct dma_pte *pte) return (pte->val & DMA_PTE_LARGE_PAGE); } -static inline int first_pte_in_page(struct dma_pte *pte) +static inline bool first_pte_in_page(struct dma_pte *pte) { - return !((unsigned long)pte & ~VTD_PAGE_MASK); + return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE); } extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); -- cgit v1.2.3 From 9906b9352a35427508d974db3a496eb3c49e2010 Mon Sep 17 00:00:00 2001 From: "Longpeng(Mike)" Date: Thu, 14 Oct 2021 13:38:39 +0800 Subject: iommu/vt-d: Avoid duplicate removing in __domain_mapping() The __domain_mapping() always removes the pages in the range from 'iov_pfn' to 'end_pfn', but the 'end_pfn' is always the last pfn of the range that the caller wants to map. This would introduce too many duplicated removing and leads the map operation take too long, for example: Map iova=0x100000,nr_pages=0x7d61800 iov_pfn: 0x100000, end_pfn: 0x7e617ff iov_pfn: 0x140000, end_pfn: 0x7e617ff iov_pfn: 0x180000, end_pfn: 0x7e617ff iov_pfn: 0x1c0000, end_pfn: 0x7e617ff iov_pfn: 0x200000, end_pfn: 0x7e617ff ... it takes about 50ms in total. We can reduce the cost by recalculate the 'end_pfn' and limit it to the boundary of the end of this pte page. Map iova=0x100000,nr_pages=0x7d61800 iov_pfn: 0x100000, end_pfn: 0x13ffff iov_pfn: 0x140000, end_pfn: 0x17ffff iov_pfn: 0x180000, end_pfn: 0x1bffff iov_pfn: 0x1c0000, end_pfn: 0x1fffff iov_pfn: 0x200000, end_pfn: 0x23ffff ... it only need 9ms now. This also removes a meaningless BUG_ON() in __domain_mapping(). Signed-off-by: Longpeng(Mike) Tested-by: Liujunjie Link: https://lore.kernel.org/r/20211008000433.1115-1-longpeng2@huawei.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20211014053839.727419-10-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.c | 11 ++++++----- include/linux/intel-iommu.h | 6 ++++++ 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 16a35669a9d0..0bde0c8b4126 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2479,12 +2479,17 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, return -ENOMEM; first_pte = pte; + lvl_pages = lvl_to_nr_pages(largepage_lvl); + /* It is large page*/ if (largepage_lvl > 1) { unsigned long end_pfn; + unsigned long pages_to_remove; pteval |= DMA_PTE_LARGE_PAGE; - end_pfn = ((iov_pfn + nr_pages) & level_mask(largepage_lvl)) - 1; + pages_to_remove = min_t(unsigned long, nr_pages, + nr_pte_to_next_page(pte) * lvl_pages); + end_pfn = iov_pfn + pages_to_remove - 1; switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl); } else { pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE; @@ -2506,10 +2511,6 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn, WARN_ON(1); } - lvl_pages = lvl_to_nr_pages(largepage_lvl); - - BUG_ON(nr_pages < lvl_pages); - nr_pages -= lvl_pages; iov_pfn += lvl_pages; phys_pfn += lvl_pages; diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h index 52481625838c..69230fd695ea 100644 --- a/include/linux/intel-iommu.h +++ b/include/linux/intel-iommu.h @@ -710,6 +710,12 @@ static inline bool first_pte_in_page(struct dma_pte *pte) return IS_ALIGNED((unsigned long)pte, VTD_PAGE_SIZE); } +static inline int nr_pte_to_next_page(struct dma_pte *pte) +{ + return first_pte_in_page(pte) ? BIT_ULL(VTD_STRIDE_SHIFT) : + (struct dma_pte *)ALIGN((unsigned long)pte, VTD_PAGE_SIZE) - pte; +} + extern struct dmar_drhd_unit * dmar_find_matched_drhd_unit(struct pci_dev *dev); extern int dmar_find_matched_atsr_unit(struct pci_dev *dev); -- cgit v1.2.3 From 53c36de0701f2fdda6b1d209dc89e2bad4a9c7b8 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 30 Dec 2020 10:21:39 -0500 Subject: mm: Add kmap_local_folio() This allows us to map a portion of a folio. Callers can only expect to access up to the next page boundary. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Vlastimil Babka --- include/linux/highmem-internal.h | 11 +++++++++++ include/linux/highmem.h | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 4aa1031d3e4c..0a0b2b09b1b8 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -73,6 +73,12 @@ static inline void *kmap_local_page(struct page *page) return __kmap_local_page_prot(page, kmap_prot); } +static inline void *kmap_local_folio(struct folio *folio, size_t offset) +{ + struct page *page = folio_page(folio, offset / PAGE_SIZE); + return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE; +} + static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return __kmap_local_page_prot(page, prot); @@ -171,6 +177,11 @@ static inline void *kmap_local_page(struct page *page) return page_address(page); } +static inline void *kmap_local_folio(struct folio *folio, size_t offset) +{ + return page_address(&folio->page) + offset; +} + static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot) { return kmap_local_page(page); diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..27cdd715c5f9 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -96,6 +96,43 @@ static inline void kmap_flush_unused(void); */ static inline void *kmap_local_page(struct page *page); +/** + * kmap_local_folio - Map a page in this folio for temporary usage + * @folio: The folio containing the page. + * @offset: The byte offset within the folio which identifies the page. + * + * Requires careful handling when nesting multiple mappings because the map + * management is stack based. The unmap has to be in the reverse order of + * the map operation:: + * + * addr1 = kmap_local_folio(folio1, offset1); + * addr2 = kmap_local_folio(folio2, offset2); + * ... + * kunmap_local(addr2); + * kunmap_local(addr1); + * + * Unmapping addr1 before addr2 is invalid and causes malfunction. + * + * Contrary to kmap() mappings the mapping is only valid in the context of + * the caller and cannot be handed to other contexts. + * + * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the + * virtual address of the direct mapping. Only real highmem pages are + * temporarily mapped. + * + * While it is significantly faster than kmap() for the higmem case it + * comes with restrictions about the pointer validity. Only use when really + * necessary. + * + * On HIGHMEM enabled systems mapping a highmem page has the side effect of + * disabling migration in order to keep the virtual address stable across + * preemption. No caller of kmap_local_folio() can rely on this side effect. + * + * Context: Can be invoked from any context. + * Return: The virtual address of @offset. + */ +static inline void *kmap_local_folio(struct folio *folio, size_t offset); + /** * kmap_atomic - Atomically map a page for temporary usage - Deprecated! * @page: Pointer to the page to be mapped -- cgit v1.2.3 From b424de33c42dbd03e39ca8f521126d39acb6c335 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 24 Apr 2021 14:50:36 -0400 Subject: mm: Add arch_make_folio_accessible() As a default implementation, call arch_make_page_accessible n times. If an architecture can do better, it can override this. Also move the default implementation of arch_make_page_accessible() from gfp.h to mm.h. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/gfp.h | 6 ------ include/linux/mm.h | 23 +++++++++++++++++++++++ 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 55b2ec1f965a..dc5ff40608ce 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -520,12 +520,6 @@ static inline void arch_free_page(struct page *page, int order) { } #ifndef HAVE_ARCH_ALLOC_PAGE static inline void arch_alloc_page(struct page *page, int order) { } #endif -#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE -static inline int arch_make_page_accessible(struct page *page) -{ - return 0; -} -#endif struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); diff --git a/include/linux/mm.h b/include/linux/mm.h index 47143f3e7f0a..c28cace6fe6b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1734,6 +1734,29 @@ static inline size_t folio_size(struct folio *folio) return PAGE_SIZE << folio_order(folio); } +#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE +static inline int arch_make_page_accessible(struct page *page) +{ + return 0; +} +#endif + +#ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE +static inline int arch_make_folio_accessible(struct folio *folio) +{ + int ret; + long i, nr = folio_nr_pages(folio); + + for (i = 0; i < nr; i++) { + ret = arch_make_page_accessible(folio_page(folio, i)); + if (ret) + break; + } + + return ret; +} +#endif + /* * Some inline functions in vmstat.h depend on page_zone() */ -- cgit v1.2.3 From 35a020ba0802f732ba070e03e50b140aea4373c4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 27 Apr 2021 09:00:12 -0400 Subject: mm: Add folio_young and folio_idle Idle page tracking is handled through page_ext on 32-bit architectures. Add folio equivalents for 32-bit and move all the page compatibility parts to common code. Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Vlastimil Babka Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig Reviewed-by: David Howells --- include/linux/page_idle.h | 99 +++++++++++++++++++++++------------------------ 1 file changed, 49 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index d8a6aecf99cb..83abf95e9fa7 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -8,46 +8,16 @@ #ifdef CONFIG_PAGE_IDLE_FLAG -#ifdef CONFIG_64BIT -static inline bool page_is_young(struct page *page) -{ - return PageYoung(page); -} - -static inline void set_page_young(struct page *page) -{ - SetPageYoung(page); -} - -static inline bool test_and_clear_page_young(struct page *page) -{ - return TestClearPageYoung(page); -} - -static inline bool page_is_idle(struct page *page) -{ - return PageIdle(page); -} - -static inline void set_page_idle(struct page *page) -{ - SetPageIdle(page); -} - -static inline void clear_page_idle(struct page *page) -{ - ClearPageIdle(page); -} -#else /* !CONFIG_64BIT */ +#ifndef CONFIG_64BIT /* * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ extern struct page_ext_operations page_idle_ops; -static inline bool page_is_young(struct page *page) +static inline bool folio_test_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return false; @@ -55,9 +25,9 @@ static inline bool page_is_young(struct page *page) return test_bit(PAGE_EXT_YOUNG, &page_ext->flags); } -static inline void set_page_young(struct page *page) +static inline void folio_set_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return; @@ -65,9 +35,9 @@ static inline void set_page_young(struct page *page) set_bit(PAGE_EXT_YOUNG, &page_ext->flags); } -static inline bool test_and_clear_page_young(struct page *page) +static inline bool folio_test_clear_young(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return false; @@ -75,9 +45,9 @@ static inline bool test_and_clear_page_young(struct page *page) return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); } -static inline bool page_is_idle(struct page *page) +static inline bool folio_test_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return false; @@ -85,9 +55,9 @@ static inline bool page_is_idle(struct page *page) return test_bit(PAGE_EXT_IDLE, &page_ext->flags); } -static inline void set_page_idle(struct page *page) +static inline void folio_set_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return; @@ -95,46 +65,75 @@ static inline void set_page_idle(struct page *page) set_bit(PAGE_EXT_IDLE, &page_ext->flags); } -static inline void clear_page_idle(struct page *page) +static inline void folio_clear_idle(struct folio *folio) { - struct page_ext *page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(&folio->page); if (unlikely(!page_ext)) return; clear_bit(PAGE_EXT_IDLE, &page_ext->flags); } -#endif /* CONFIG_64BIT */ +#endif /* !CONFIG_64BIT */ #else /* !CONFIG_PAGE_IDLE_FLAG */ -static inline bool page_is_young(struct page *page) +static inline bool folio_test_young(struct folio *folio) { return false; } -static inline void set_page_young(struct page *page) +static inline void folio_set_young(struct folio *folio) { } -static inline bool test_and_clear_page_young(struct page *page) +static inline bool folio_test_clear_young(struct folio *folio) { return false; } -static inline bool page_is_idle(struct page *page) +static inline bool folio_test_idle(struct folio *folio) { return false; } -static inline void set_page_idle(struct page *page) +static inline void folio_set_idle(struct folio *folio) { } -static inline void clear_page_idle(struct page *page) +static inline void folio_clear_idle(struct folio *folio) { } #endif /* CONFIG_PAGE_IDLE_FLAG */ +static inline bool page_is_young(struct page *page) +{ + return folio_test_young(page_folio(page)); +} + +static inline void set_page_young(struct page *page) +{ + folio_set_young(page_folio(page)); +} + +static inline bool test_and_clear_page_young(struct page *page) +{ + return folio_test_clear_young(page_folio(page)); +} + +static inline bool page_is_idle(struct page *page) +{ + return folio_test_idle(page_folio(page)); +} + +static inline void set_page_idle(struct page *page) +{ + folio_set_idle(page_folio(page)); +} + +static inline void clear_page_idle(struct page *page) +{ + folio_clear_idle(page_folio(page)); +} #endif /* _LINUX_MM_PAGE_IDLE_H */ -- cgit v1.2.3 From 76580b6529db622964b4ffee59ded25efcb73748 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 27 Apr 2021 10:47:39 -0400 Subject: mm/swap: Add folio_mark_accessed() Convert mark_page_accessed() to folio_mark_accessed(). It already operated on the entire compound page, but now we can avoid calling compound_head quite so many times. Shrinks the function from 424 bytes to 295 bytes (shrinking by 129 bytes). The compatibility wrapper is 30 bytes, plus the 8 bytes for the exported symbol means the kernel shrinks by 91 bytes. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/swap.h | 3 ++- mm/folio-compat.c | 7 +++++++ mm/swap.c | 34 ++++++++++++++++------------------ 3 files changed, 25 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 0fc84797623f..067b7af5242c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -352,7 +352,8 @@ extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); -extern void mark_page_accessed(struct page *); +void mark_page_accessed(struct page *); +void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 7044fcc8a8aa..a374747ae1c6 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -5,6 +5,7 @@ */ #include +#include struct address_space *page_mapping(struct page *page) { @@ -41,3 +42,9 @@ bool page_mapped(struct page *page) return folio_mapped(page_folio(page)); } EXPORT_SYMBOL(page_mapped); + +void mark_page_accessed(struct page *page) +{ + folio_mark_accessed(page_folio(page)); +} +EXPORT_SYMBOL(mark_page_accessed); diff --git a/mm/swap.c b/mm/swap.c index 3860d6bc8c8a..b95fd6d05768 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -368,7 +368,7 @@ static void folio_activate(struct folio *folio) } #endif -static void __lru_cache_activate_page(struct page *page) +static void __lru_cache_activate_folio(struct folio *folio) { struct pagevec *pvec; int i; @@ -389,8 +389,8 @@ static void __lru_cache_activate_page(struct page *page) for (i = pagevec_count(pvec) - 1; i >= 0; i--) { struct page *pagevec_page = pvec->pages[i]; - if (pagevec_page == page) { - SetPageActive(page); + if (pagevec_page == &folio->page) { + folio_set_active(folio); break; } } @@ -408,36 +408,34 @@ static void __lru_cache_activate_page(struct page *page) * When a newly allocated page is not yet visible, so safe for non-atomic ops, * __SetPageReferenced(page) may be substituted for mark_page_accessed(page). */ -void mark_page_accessed(struct page *page) +void folio_mark_accessed(struct folio *folio) { - page = compound_head(page); - - if (!PageReferenced(page)) { - SetPageReferenced(page); - } else if (PageUnevictable(page)) { + if (!folio_test_referenced(folio)) { + folio_set_referenced(folio); + } else if (folio_test_unevictable(folio)) { /* * Unevictable pages are on the "LRU_UNEVICTABLE" list. But, * this list is never rotated or maintained, so marking an * evictable page accessed has no effect. */ - } else if (!PageActive(page)) { + } else if (!folio_test_active(folio)) { /* * If the page is on the LRU, queue it for activation via * lru_pvecs.activate_page. Otherwise, assume the page is on a * pagevec, mark it active and it'll be moved to the active * LRU on the next drain. */ - if (PageLRU(page)) - folio_activate(page_folio(page)); + if (folio_test_lru(folio)) + folio_activate(folio); else - __lru_cache_activate_page(page); - ClearPageReferenced(page); - workingset_activation(page_folio(page)); + __lru_cache_activate_folio(folio); + folio_clear_referenced(folio); + workingset_activation(folio); } - if (page_is_idle(page)) - clear_page_idle(page); + if (folio_test_idle(folio)) + folio_clear_idle(folio); } -EXPORT_SYMBOL(mark_page_accessed); +EXPORT_SYMBOL(folio_mark_accessed); /** * lru_cache_add - add a page to a page list -- cgit v1.2.3 From d9c08e2232fbca4fa56b9350f7f84835c4aa3add Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 28 Feb 2021 16:02:57 -0500 Subject: mm/rmap: Add folio_mkclean() Transform page_mkclean() into folio_mkclean() and add a page_mkclean() wrapper around folio_mkclean(). folio_mkclean is 15 bytes smaller than page_mkclean, but the kernel is enlarged by 33 bytes due to inlining page_folio() into each caller. This will go away once the callers are converted to use folio_mkclean(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/rmap.h | 10 ++++++---- mm/rmap.c | 12 ++++++------ 2 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rmap.h b/include/linux/rmap.h index c976cc6de257..e704b1a4c06c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -235,7 +235,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); * * returns the number of cleaned PTEs. */ -int page_mkclean(struct page *); +int folio_mkclean(struct folio *); /* * called in munlock()/munmap() path to check for other vmas holding @@ -295,12 +295,14 @@ static inline void try_to_unmap(struct page *page, enum ttu_flags flags) { } -static inline int page_mkclean(struct page *page) +static inline int folio_mkclean(struct folio *folio) { return 0; } - - #endif /* CONFIG_MMU */ +static inline int page_mkclean(struct page *page) +{ + return folio_mkclean(page_folio(page)); +} #endif /* _LINUX_RMAP_H */ diff --git a/mm/rmap.c b/mm/rmap.c index 059556dbefec..3a1059c284c3 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -981,7 +981,7 @@ static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) return true; } -int page_mkclean(struct page *page) +int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; @@ -991,20 +991,20 @@ int page_mkclean(struct page *page) .invalid_vma = invalid_mkclean_vma, }; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - if (!page_mapped(page)) + if (!folio_mapped(folio)) return 0; - mapping = page_mapping(page); + mapping = folio_mapping(folio); if (!mapping) return 0; - rmap_walk(page, &rwc); + rmap_walk(&folio->page, &rwc); return cleaned; } -EXPORT_SYMBOL_GPL(page_mkclean); +EXPORT_SYMBOL_GPL(folio_mkclean); /** * page_move_anon_rmap - move a page to our anon_vma -- cgit v1.2.3 From 3417013e0d183be9b42d794082eec0ec1c5b5f15 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 7 May 2021 07:28:40 -0400 Subject: mm/migrate: Add folio_migrate_mapping() Reimplement migrate_page_move_mapping() as a wrapper around folio_migrate_mapping(). Saves 193 bytes of kernel text. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/migrate.h | 2 ++ mm/folio-compat.c | 11 +++++++ mm/migrate.c | 85 +++++++++++++++++++++++++------------------------ 3 files changed, 57 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c8077e936691..58b3af645e20 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -57,6 +57,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +int folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int extra_count); #else static inline void putback_movable_pages(struct list_head *l) {} diff --git a/mm/folio-compat.c b/mm/folio-compat.c index a374747ae1c6..d883d964fd52 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -4,6 +4,7 @@ * eventually. */ +#include #include #include @@ -48,3 +49,13 @@ void mark_page_accessed(struct page *page) folio_mark_accessed(page_folio(page)); } EXPORT_SYMBOL(mark_page_accessed); + +#ifdef CONFIG_MIGRATION +int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page, int extra_count) +{ + return folio_migrate_mapping(mapping, page_folio(newpage), + page_folio(page), extra_count); +} +EXPORT_SYMBOL(migrate_page_move_mapping); +#endif diff --git a/mm/migrate.c b/mm/migrate.c index bfb8ba490479..0e408ee4b7b2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -364,7 +364,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) */ expected_count += is_device_private_page(page); if (mapping) - expected_count += thp_nr_pages(page) + page_has_private(page); + expected_count += compound_nr(page) + page_has_private(page); return expected_count; } @@ -377,74 +377,75 @@ static int expected_page_refs(struct address_space *mapping, struct page *page) * 2 for pages with a mapping * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ -int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page, int extra_count) +int folio_migrate_mapping(struct address_space *mapping, + struct folio *newfolio, struct folio *folio, int extra_count) { - XA_STATE(xas, &mapping->i_pages, page_index(page)); + XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct zone *oldzone, *newzone; int dirty; - int expected_count = expected_page_refs(mapping, page) + extra_count; - int nr = thp_nr_pages(page); + int expected_count = expected_page_refs(mapping, &folio->page) + extra_count; + long nr = folio_nr_pages(folio); if (!mapping) { /* Anonymous page without mapping */ - if (page_count(page) != expected_count) + if (folio_ref_count(folio) != expected_count) return -EAGAIN; /* No turning back from here */ - newpage->index = page->index; - newpage->mapping = page->mapping; - if (PageSwapBacked(page)) - __SetPageSwapBacked(newpage); + newfolio->index = folio->index; + newfolio->mapping = folio->mapping; + if (folio_test_swapbacked(folio)) + __folio_set_swapbacked(newfolio); return MIGRATEPAGE_SUCCESS; } - oldzone = page_zone(page); - newzone = page_zone(newpage); + oldzone = folio_zone(folio); + newzone = folio_zone(newfolio); xas_lock_irq(&xas); - if (page_count(page) != expected_count || xas_load(&xas) != page) { + if (folio_ref_count(folio) != expected_count || + xas_load(&xas) != folio) { xas_unlock_irq(&xas); return -EAGAIN; } - if (!page_ref_freeze(page, expected_count)) { + if (!folio_ref_freeze(folio, expected_count)) { xas_unlock_irq(&xas); return -EAGAIN; } /* - * Now we know that no one else is looking at the page: + * Now we know that no one else is looking at the folio: * no turning back from here. */ - newpage->index = page->index; - newpage->mapping = page->mapping; - page_ref_add(newpage, nr); /* add cache reference */ - if (PageSwapBacked(page)) { - __SetPageSwapBacked(newpage); - if (PageSwapCache(page)) { - SetPageSwapCache(newpage); - set_page_private(newpage, page_private(page)); + newfolio->index = folio->index; + newfolio->mapping = folio->mapping; + folio_ref_add(newfolio, nr); /* add cache reference */ + if (folio_test_swapbacked(folio)) { + __folio_set_swapbacked(newfolio); + if (folio_test_swapcache(folio)) { + folio_set_swapcache(newfolio); + newfolio->private = folio_get_private(folio); } } else { - VM_BUG_ON_PAGE(PageSwapCache(page), page); + VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio); } /* Move dirty while page refs frozen and newpage not yet exposed */ - dirty = PageDirty(page); + dirty = folio_test_dirty(folio); if (dirty) { - ClearPageDirty(page); - SetPageDirty(newpage); + folio_clear_dirty(folio); + folio_set_dirty(newfolio); } - xas_store(&xas, newpage); - if (PageTransHuge(page)) { + xas_store(&xas, newfolio); + if (nr > 1) { int i; for (i = 1; i < nr; i++) { xas_next(&xas); - xas_store(&xas, newpage); + xas_store(&xas, newfolio); } } @@ -453,7 +454,7 @@ int migrate_page_move_mapping(struct address_space *mapping, * to one less reference. * We know this isn't the last reference. */ - page_ref_unfreeze(page, expected_count - nr); + folio_ref_unfreeze(folio, expected_count - nr); xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ @@ -472,18 +473,18 @@ int migrate_page_move_mapping(struct address_space *mapping, struct lruvec *old_lruvec, *new_lruvec; struct mem_cgroup *memcg; - memcg = page_memcg(page); + memcg = folio_memcg(folio); old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat); new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat); __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr); __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr); - if (PageSwapBacked(page) && !PageSwapCache(page)) { + if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) { __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr); __mod_lruvec_state(new_lruvec, NR_SHMEM, nr); } #ifdef CONFIG_SWAP - if (PageSwapCache(page)) { + if (folio_test_swapcache(folio)) { __mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr); __mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr); } @@ -499,11 +500,11 @@ int migrate_page_move_mapping(struct address_space *mapping, return MIGRATEPAGE_SUCCESS; } -EXPORT_SYMBOL(migrate_page_move_mapping); +EXPORT_SYMBOL(folio_migrate_mapping); /* * The expected number of remaining references is the same as that - * of migrate_page_move_mapping(). + * of folio_migrate_mapping(). */ int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page) @@ -564,7 +565,7 @@ void migrate_page_states(struct page *newpage, struct page *page) if (PageMappedToDisk(page)) SetPageMappedToDisk(newpage); - /* Move dirty on pages not done by migrate_page_move_mapping() */ + /* Move dirty on pages not done by folio_migrate_mapping() */ if (PageDirty(page)) SetPageDirty(newpage); @@ -640,11 +641,13 @@ int migrate_page(struct address_space *mapping, struct page *newpage, struct page *page, enum migrate_mode mode) { + struct folio *newfolio = page_folio(newpage); + struct folio *folio = page_folio(page); int rc; - BUG_ON(PageWriteback(page)); /* Writeback must be complete */ + BUG_ON(folio_test_writeback(folio)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page, 0); + rc = folio_migrate_mapping(mapping, newfolio, folio, 0); if (rc != MIGRATEPAGE_SUCCESS) return rc; @@ -2470,7 +2473,7 @@ static void migrate_vma_collect(struct migrate_vma *migrate) * @page: struct page to check * * Pinned pages cannot be migrated. This is the same test as in - * migrate_page_move_mapping(), except that here we allow migration of a + * folio_migrate_mapping(), except that here we allow migration of a * ZONE_DEVICE page. */ static bool migrate_vma_check_page(struct page *page) -- cgit v1.2.3 From 19138349ed59b90ce58aca319b873eca2e04ad43 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 7 May 2021 15:26:29 -0400 Subject: mm/migrate: Add folio_migrate_flags() Turn migrate_page_states() into a wrapper around folio_migrate_flags(). Also convert two functions only called from folio_migrate_flags() to be folio-based. ksm_migrate_page() becomes folio_migrate_ksm() and copy_page_owner() becomes folio_copy_owner(). folio_migrate_flags() alone shrinks by two thirds -- 1967 bytes down to 642 bytes. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/ksm.h | 4 +-- include/linux/migrate.h | 1 + include/linux/page_owner.h | 8 ++--- mm/folio-compat.c | 6 ++++ mm/ksm.c | 31 ++++++++++------- mm/migrate.c | 84 ++++++++++++++++++++++------------------------ mm/page_owner.c | 10 +++--- 7 files changed, 77 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ksm.h b/include/linux/ksm.h index 161e8164abcf..a38a5bca1ba5 100644 --- a/include/linux/ksm.h +++ b/include/linux/ksm.h @@ -52,7 +52,7 @@ struct page *ksm_might_need_to_copy(struct page *page, struct vm_area_struct *vma, unsigned long address); void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); -void ksm_migrate_page(struct page *newpage, struct page *oldpage); +void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); #else /* !CONFIG_KSM */ @@ -83,7 +83,7 @@ static inline void rmap_walk_ksm(struct page *page, { } -static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) +static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 58b3af645e20..aa875b83f7ba 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -57,6 +57,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +void folio_migrate_flags(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); #else diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 719bfe5108c5..43c638c51c1f 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -12,7 +12,7 @@ extern void __reset_page_owner(struct page *page, unsigned int order); extern void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask); extern void __split_page_owner(struct page *page, unsigned int nr); -extern void __copy_page_owner(struct page *oldpage, struct page *newpage); +extern void __folio_copy_owner(struct folio *newfolio, struct folio *old); extern void __set_page_owner_migrate_reason(struct page *page, int reason); extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, @@ -36,10 +36,10 @@ static inline void split_page_owner(struct page *page, unsigned int nr) if (static_branch_unlikely(&page_owner_inited)) __split_page_owner(page, nr); } -static inline void copy_page_owner(struct page *oldpage, struct page *newpage) +static inline void folio_copy_owner(struct folio *newfolio, struct folio *old) { if (static_branch_unlikely(&page_owner_inited)) - __copy_page_owner(oldpage, newpage); + __folio_copy_owner(newfolio, old); } static inline void set_page_owner_migrate_reason(struct page *page, int reason) { @@ -63,7 +63,7 @@ static inline void split_page_owner(struct page *page, unsigned int order) { } -static inline void copy_page_owner(struct page *oldpage, struct page *newpage) +static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio) { } static inline void set_page_owner_migrate_reason(struct page *page, int reason) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index d883d964fd52..3f00ad92d1ff 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -58,4 +58,10 @@ int migrate_page_move_mapping(struct address_space *mapping, page_folio(page), extra_count); } EXPORT_SYMBOL(migrate_page_move_mapping); + +void migrate_page_states(struct page *newpage, struct page *page) +{ + folio_migrate_flags(page_folio(newpage), page_folio(page)); +} +EXPORT_SYMBOL(migrate_page_states); #endif diff --git a/mm/ksm.c b/mm/ksm.c index c246a0b0ac75..0662093237e4 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -751,7 +751,7 @@ stale: /* * We come here from above when page->mapping or !PageSwapCache * suggests that the node is stale; but it might be under migration. - * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(), + * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(), * before checking whether node->kpfn has been changed. */ smp_rmb(); @@ -852,9 +852,14 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, return err; } +static inline struct stable_node *folio_stable_node(struct folio *folio) +{ + return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL; +} + static inline struct stable_node *page_stable_node(struct page *page) { - return PageKsm(page) ? page_rmapping(page) : NULL; + return folio_stable_node(page_folio(page)); } static inline void set_page_stable_node(struct page *page, @@ -2659,26 +2664,26 @@ again: } #ifdef CONFIG_MIGRATION -void ksm_migrate_page(struct page *newpage, struct page *oldpage) +void folio_migrate_ksm(struct folio *newfolio, struct folio *folio) { struct stable_node *stable_node; - VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); - VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); - VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio); + VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio); - stable_node = page_stable_node(newpage); + stable_node = folio_stable_node(folio); if (stable_node) { - VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage); - stable_node->kpfn = page_to_pfn(newpage); + VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio); + stable_node->kpfn = folio_pfn(newfolio); /* - * newpage->mapping was set in advance; now we need smp_wmb() + * newfolio->mapping was set in advance; now we need smp_wmb() * to make sure that the new stable_node->kpfn is visible - * to get_ksm_page() before it can see that oldpage->mapping - * has gone stale (or that PageSwapCache has been cleared). + * to get_ksm_page() before it can see that folio->mapping + * has gone stale (or that folio_test_swapcache has been cleared). */ smp_wmb(); - set_page_stable_node(oldpage, NULL); + set_page_stable_node(&folio->page, NULL); } } #endif /* CONFIG_MIGRATION */ diff --git a/mm/migrate.c b/mm/migrate.c index 0e408ee4b7b2..f6e0017ef0bf 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -539,82 +539,80 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, } /* - * Copy the page to its new location + * Copy the flags and some other ancillary information */ -void migrate_page_states(struct page *newpage, struct page *page) +void folio_migrate_flags(struct folio *newfolio, struct folio *folio) { - struct folio *folio = page_folio(page); - struct folio *newfolio = page_folio(newpage); int cpupid; - if (PageError(page)) - SetPageError(newpage); - if (PageReferenced(page)) - SetPageReferenced(newpage); - if (PageUptodate(page)) - SetPageUptodate(newpage); - if (TestClearPageActive(page)) { - VM_BUG_ON_PAGE(PageUnevictable(page), page); - SetPageActive(newpage); - } else if (TestClearPageUnevictable(page)) - SetPageUnevictable(newpage); - if (PageWorkingset(page)) - SetPageWorkingset(newpage); - if (PageChecked(page)) - SetPageChecked(newpage); - if (PageMappedToDisk(page)) - SetPageMappedToDisk(newpage); + if (folio_test_error(folio)) + folio_set_error(newfolio); + if (folio_test_referenced(folio)) + folio_set_referenced(newfolio); + if (folio_test_uptodate(folio)) + folio_mark_uptodate(newfolio); + if (folio_test_clear_active(folio)) { + VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio); + folio_set_active(newfolio); + } else if (folio_test_clear_unevictable(folio)) + folio_set_unevictable(newfolio); + if (folio_test_workingset(folio)) + folio_set_workingset(newfolio); + if (folio_test_checked(folio)) + folio_set_checked(newfolio); + if (folio_test_mappedtodisk(folio)) + folio_set_mappedtodisk(newfolio); /* Move dirty on pages not done by folio_migrate_mapping() */ - if (PageDirty(page)) - SetPageDirty(newpage); + if (folio_test_dirty(folio)) + folio_set_dirty(newfolio); - if (page_is_young(page)) - set_page_young(newpage); - if (page_is_idle(page)) - set_page_idle(newpage); + if (folio_test_young(folio)) + folio_set_young(newfolio); + if (folio_test_idle(folio)) + folio_set_idle(newfolio); /* * Copy NUMA information to the new page, to prevent over-eager * future migrations of this same page. */ - cpupid = page_cpupid_xchg_last(page, -1); - page_cpupid_xchg_last(newpage, cpupid); + cpupid = page_cpupid_xchg_last(&folio->page, -1); + page_cpupid_xchg_last(&newfolio->page, cpupid); - ksm_migrate_page(newpage, page); + folio_migrate_ksm(newfolio, folio); /* * Please do not reorder this without considering how mm/ksm.c's * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). */ - if (PageSwapCache(page)) - ClearPageSwapCache(page); - ClearPagePrivate(page); + if (folio_test_swapcache(folio)) + folio_clear_swapcache(folio); + folio_clear_private(folio); /* page->private contains hugetlb specific flags */ - if (!PageHuge(page)) - set_page_private(page, 0); + if (!folio_test_hugetlb(folio)) + folio->private = NULL; /* * If any waiters have accumulated on the new page then * wake them up. */ - if (PageWriteback(newpage)) - end_page_writeback(newpage); + if (folio_test_writeback(newfolio)) + folio_end_writeback(newfolio); /* * PG_readahead shares the same bit with PG_reclaim. The above * end_page_writeback() may clear PG_readahead mistakenly, so set the * bit after that. */ - if (PageReadahead(page)) - SetPageReadahead(newpage); + if (folio_test_readahead(folio)) + folio_set_readahead(newfolio); - copy_page_owner(page, newpage); + folio_copy_owner(newfolio, folio); - if (!PageHuge(page)) + if (!folio_test_hugetlb(folio)) mem_cgroup_migrate(folio, newfolio); } -EXPORT_SYMBOL(migrate_page_states); +EXPORT_SYMBOL(folio_migrate_flags); void migrate_page_copy(struct page *newpage, struct page *page) { @@ -655,7 +653,7 @@ int migrate_page(struct address_space *mapping, if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); else - migrate_page_states(newpage, page); + folio_migrate_flags(newfolio, folio); return MIGRATEPAGE_SUCCESS; } EXPORT_SYMBOL(migrate_page); diff --git a/mm/page_owner.c b/mm/page_owner.c index 62402d22539b..d24ed221357c 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -210,10 +210,10 @@ void __split_page_owner(struct page *page, unsigned int nr) } } -void __copy_page_owner(struct page *oldpage, struct page *newpage) +void __folio_copy_owner(struct folio *newfolio, struct folio *old) { - struct page_ext *old_ext = lookup_page_ext(oldpage); - struct page_ext *new_ext = lookup_page_ext(newpage); + struct page_ext *old_ext = lookup_page_ext(&old->page); + struct page_ext *new_ext = lookup_page_ext(&newfolio->page); struct page_owner *old_page_owner, *new_page_owner; if (unlikely(!old_ext || !new_ext)) @@ -231,11 +231,11 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) new_page_owner->free_ts_nsec = old_page_owner->ts_nsec; /* - * We don't clear the bit on the oldpage as it's going to be freed + * We don't clear the bit on the old folio as it's going to be freed * after migration. Until then, the info can be useful in case of * a bug, and the overall stats will be off a bit only temporarily. * Also, migrate_misplaced_transhuge_page() can still fail the - * migration and then we want the oldpage to retain the info. But + * migration and then we want the old folio to retain the info. But * in that case we also don't need to explicitly clear the info from * the new page, which will be freed. */ -- cgit v1.2.3 From 715cbfd6c5c595bc8b7a6f9ad1fe9fec0122bb20 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 7 May 2021 15:05:06 -0400 Subject: mm/migrate: Add folio_migrate_copy() This is the folio equivalent of migrate_page_copy(), which is retained as a wrapper for filesystems which are not yet converted to folios. Also convert copy_huge_page() to folio_copy(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Zi Yan Acked-by: Vlastimil Babka --- include/linux/migrate.h | 1 + include/linux/mm.h | 2 +- mm/folio-compat.c | 6 ++++++ mm/hugetlb.c | 2 +- mm/migrate.c | 14 +++++--------- mm/util.c | 21 +++++++++++++++++---- 6 files changed, 31 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index aa875b83f7ba..0d2aeb9b0f66 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -58,6 +58,7 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); +void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, struct folio *newfolio, struct folio *folio, int extra_count); #else diff --git a/include/linux/mm.h b/include/linux/mm.h index c28cace6fe6b..93d5fbe2e4e3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -912,7 +912,7 @@ void __put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); -void copy_huge_page(struct page *dst, struct page *src); +void folio_copy(struct folio *dst, struct folio *src); /* * Compound pages have a destructor function. Provide a diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 3f00ad92d1ff..2ccd8f213fc4 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -64,4 +64,10 @@ void migrate_page_states(struct page *newpage, struct page *page) folio_migrate_flags(page_folio(newpage), page_folio(page)); } EXPORT_SYMBOL(migrate_page_states); + +void migrate_page_copy(struct page *newpage, struct page *page) +{ + folio_migrate_copy(page_folio(newpage), page_folio(page)); +} +EXPORT_SYMBOL(migrate_page_copy); #endif diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 95dc7b83381f..6378c1066459 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5302,7 +5302,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, *pagep = NULL; goto out; } - copy_huge_page(page, *pagep); + folio_copy(page_folio(page), page_folio(*pagep)); put_page(*pagep); *pagep = NULL; } diff --git a/mm/migrate.c b/mm/migrate.c index f6e0017ef0bf..433c453b47f9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -614,16 +614,12 @@ void folio_migrate_flags(struct folio *newfolio, struct folio *folio) } EXPORT_SYMBOL(folio_migrate_flags); -void migrate_page_copy(struct page *newpage, struct page *page) +void folio_migrate_copy(struct folio *newfolio, struct folio *folio) { - if (PageHuge(page) || PageTransHuge(page)) - copy_huge_page(newpage, page); - else - copy_highpage(newpage, page); - - migrate_page_states(newpage, page); + folio_copy(newfolio, folio); + folio_migrate_flags(newfolio, folio); } -EXPORT_SYMBOL(migrate_page_copy); +EXPORT_SYMBOL(folio_migrate_copy); /************************************************************ * Migration functions @@ -651,7 +647,7 @@ int migrate_page(struct address_space *mapping, return rc; if (mode != MIGRATE_SYNC_NO_COPY) - migrate_page_copy(newpage, page); + folio_migrate_copy(newfolio, folio); else folio_migrate_flags(newfolio, folio); return MIGRATEPAGE_SUCCESS; diff --git a/mm/util.c b/mm/util.c index bf860838282c..e58151a61255 100644 --- a/mm/util.c +++ b/mm/util.c @@ -747,13 +747,26 @@ int __page_mapcount(struct page *page) } EXPORT_SYMBOL_GPL(__page_mapcount); -void copy_huge_page(struct page *dst, struct page *src) +/** + * folio_copy - Copy the contents of one folio to another. + * @dst: Folio to copy to. + * @src: Folio to copy from. + * + * The bytes in the folio represented by @src are copied to @dst. + * Assumes the caller has validated that @dst is at least as large as @src. + * Can be called in atomic context for order-0 folios, but if the folio is + * larger, it may sleep. + */ +void folio_copy(struct folio *dst, struct folio *src) { - unsigned i, nr = compound_nr(src); + long i = 0; + long nr = folio_nr_pages(src); - for (i = 0; i < nr; i++) { + for (;;) { + copy_highpage(folio_page(dst, i), folio_page(src, i)); + if (++i == nr) + break; cond_resched(); - copy_highpage(nth_page(dst, i), nth_page(src, i)); } } -- cgit v1.2.3 From bd3488e7b4d61780eb3dfaca1cc6f4026bcffd48 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 19 Mar 2021 08:39:50 -0400 Subject: mm/writeback: Rename __add_wb_stat() to wb_stat_mod() Make this look like the newly renamed vmstat functions. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/backing-dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..a62e72dd829f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -64,7 +64,7 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) return atomic_long_read(&bdi->tot_write_bandwidth); } -static inline void __add_wb_stat(struct bdi_writeback *wb, +static inline void wb_stat_mod(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); @@ -72,12 +72,12 @@ static inline void __add_wb_stat(struct bdi_writeback *wb, static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - __add_wb_stat(wb, item, 1); + wb_stat_mod(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { - __add_wb_stat(wb, item, -1); + wb_stat_mod(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) -- cgit v1.2.3 From be5f1797523004d0d9aaee81a523d86e3b890007 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 20 Mar 2021 16:34:54 -0400 Subject: flex_proportions: Allow N events instead of 1 When batching events (such as writing back N pages in a single I/O), it is better to do one flex_proportion operation instead of N. There is only one caller of __fprop_inc_percpu_max(), and it's the one we're going to change in the next patch, so rename it instead of adding a compatibility wrapper. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Jan Kara --- include/linux/flex_proportions.h | 9 +++++---- lib/flex_proportions.c | 28 +++++++++++++++++++--------- mm/page-writeback.c | 4 ++-- 3 files changed, 26 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h index c12df59d3f5f..3e378b1fb0bc 100644 --- a/include/linux/flex_proportions.h +++ b/include/linux/flex_proportions.h @@ -83,9 +83,10 @@ struct fprop_local_percpu { int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp); void fprop_local_destroy_percpu(struct fprop_local_percpu *pl); -void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl); -void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl, - int max_frac); +void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, + long nr); +void __fprop_add_percpu_max(struct fprop_global *p, + struct fprop_local_percpu *pl, int max_frac, long nr); void fprop_fraction_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, unsigned long *numerator, unsigned long *denominator); @@ -96,7 +97,7 @@ void fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) unsigned long flags; local_irq_save(flags); - __fprop_inc_percpu(p, pl); + __fprop_add_percpu(p, pl, 1); local_irq_restore(flags); } diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c index 451543937524..53e7eb1dd76c 100644 --- a/lib/flex_proportions.c +++ b/lib/flex_proportions.c @@ -217,11 +217,12 @@ static void fprop_reflect_period_percpu(struct fprop_global *p, } /* Event of type pl happened */ -void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl) +void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl, + long nr) { fprop_reflect_period_percpu(p, pl); - percpu_counter_add_batch(&pl->events, 1, PROP_BATCH); - percpu_counter_add(&p->events, 1); + percpu_counter_add_batch(&pl->events, nr, PROP_BATCH); + percpu_counter_add(&p->events, nr); } void fprop_fraction_percpu(struct fprop_global *p, @@ -253,20 +254,29 @@ void fprop_fraction_percpu(struct fprop_global *p, } /* - * Like __fprop_inc_percpu() except that event is counted only if the given + * Like __fprop_add_percpu() except that event is counted only if the given * type has fraction smaller than @max_frac/FPROP_FRAC_BASE */ -void __fprop_inc_percpu_max(struct fprop_global *p, - struct fprop_local_percpu *pl, int max_frac) +void __fprop_add_percpu_max(struct fprop_global *p, + struct fprop_local_percpu *pl, int max_frac, long nr) { if (unlikely(max_frac < FPROP_FRAC_BASE)) { unsigned long numerator, denominator; + s64 tmp; fprop_fraction_percpu(p, pl, &numerator, &denominator); - if (numerator > - (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT) + /* Adding 'nr' to fraction exceeds max_frac/FPROP_FRAC_BASE? */ + tmp = (u64)denominator * max_frac - + ((u64)numerator << FPROP_FRAC_SHIFT); + if (tmp < 0) { + /* Maximum fraction already exceeded? */ return; + } else if (tmp < nr * (FPROP_FRAC_BASE - max_frac)) { + /* Add just enough for the fraction to saturate */ + nr = div_u64(tmp + FPROP_FRAC_BASE - max_frac - 1, + FPROP_FRAC_BASE - max_frac); + } } - __fprop_inc_percpu(p, pl); + __fprop_add_percpu(p, pl, nr); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 1d8f2ee2e065..cb7387d0e77d 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -566,8 +566,8 @@ static void wb_domain_writeout_inc(struct wb_domain *dom, struct fprop_local_percpu *completions, unsigned int max_prop_frac) { - __fprop_inc_percpu_max(&dom->completions, completions, - max_prop_frac); + __fprop_add_percpu_max(&dom->completions, completions, + max_prop_frac, 1); /* First event after period switching was turned off? */ if (unlikely(!dom->period_time)) { /* -- cgit v1.2.3 From 269ccca3899f6bce49e004f50f623e0b161fb027 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 15 Jan 2021 23:34:16 -0500 Subject: mm/writeback: Add __folio_end_writeback() test_clear_page_writeback() is actually an mm-internal function, although it's named as if it's a pagecache function. Move it to mm/internal.h, rename it to __folio_end_writeback() and change the return type to bool. The conversion from page to folio is mostly about accounting the number of pages being written back, although it does eliminate a couple of calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/page-flags.h | 1 - mm/filemap.c | 2 +- mm/internal.h | 1 + mm/page-writeback.c | 29 +++++++++++++++-------------- 4 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 2491e84b8e52..3aebb2060a26 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -657,7 +657,6 @@ static __always_inline void SetPageUptodate(struct page *page) CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) -int test_clear_page_writeback(struct page *page); int __test_set_page_writeback(struct page *page, bool keep_write); #define test_set_page_writeback(page) \ diff --git a/mm/filemap.c b/mm/filemap.c index 5368a4dcc35e..5cb18399a1b6 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1590,7 +1590,7 @@ void folio_end_writeback(struct folio *folio) * reused before the folio_wake(). */ folio_get(folio); - if (!test_clear_page_writeback(&folio->page)) + if (!__folio_end_writeback(folio)) BUG(); smp_mb__after_atomic(); diff --git a/mm/internal.h b/mm/internal.h index 187a032fed4d..08fb03b16d3d 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -43,6 +43,7 @@ static inline void *folio_raw_mapping(struct folio *folio) vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); +bool __folio_end_writeback(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 943cf74a76ed..9ff9a33bced1 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -583,7 +583,7 @@ static void wb_domain_writeout_add(struct wb_domain *dom, /* * Increment @wb's writeout completion count and the global writeout - * completion count. Called from test_clear_page_writeback(). + * completion count. Called from __folio_end_writeback(). */ static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr) { @@ -2766,27 +2766,28 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb) queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL); } -int test_clear_page_writeback(struct page *page) +bool __folio_end_writeback(struct folio *folio) { - struct address_space *mapping = page_mapping(page); - int ret; + long nr = folio_nr_pages(folio); + struct address_space *mapping = folio_mapping(folio); + bool ret; - lock_page_memcg(page); + folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - ret = TestClearPageWriteback(page); + ret = folio_test_clear_writeback(folio); if (ret) { - __xa_clear_mark(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_WRITEBACK); if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); - dec_wb_stat(wb, WB_WRITEBACK); - __wb_writeout_add(wb, 1); + wb_stat_mod(wb, WB_WRITEBACK, -nr); + __wb_writeout_add(wb, nr); if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) wb_inode_writeback_end(wb); @@ -2799,14 +2800,14 @@ int test_clear_page_writeback(struct page *page) xa_unlock_irqrestore(&mapping->i_pages, flags); } else { - ret = TestClearPageWriteback(page); + ret = folio_test_clear_writeback(folio); } if (ret) { - dec_lruvec_page_state(page, NR_WRITEBACK); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - inc_node_page_state(page, NR_WRITTEN); + lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + node_stat_mod_folio(folio, NR_WRITTEN, nr); } - unlock_page_memcg(page); + folio_memcg_unlock(folio); return ret; } -- cgit v1.2.3 From f143f1ea5a5380b2682e6836fcd24338a2aa82c7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 24 Apr 2021 12:00:48 -0400 Subject: mm/writeback: Add folio_start_writeback() Rename set_page_writeback() to folio_start_writeback() to match folio_end_writeback(). Do not bother with wrappers that return void; callers are perfectly capable of ignoring return values. Add wrappers for set_page_writeback(), set_page_writeback_keepwrite() and test_set_page_writeback() for compatibililty with existing filesystems. The main advantage of this patch is getting the statistics right, although it does eliminate a couple of calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/page-flags.h | 19 ++++++++++--------- mm/folio-compat.c | 6 ++++++ mm/page-writeback.c | 39 ++++++++++++++++++++------------------- 3 files changed, 36 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 3aebb2060a26..a68af80649a4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -657,21 +657,22 @@ static __always_inline void SetPageUptodate(struct page *page) CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL) -int __test_set_page_writeback(struct page *page, bool keep_write); +bool __folio_start_writeback(struct folio *folio, bool keep_write); +bool set_page_writeback(struct page *page); -#define test_set_page_writeback(page) \ - __test_set_page_writeback(page, false) -#define test_set_page_writeback_keepwrite(page) \ - __test_set_page_writeback(page, true) +#define folio_start_writeback(folio) \ + __folio_start_writeback(folio, false) +#define folio_start_writeback_keepwrite(folio) \ + __folio_start_writeback(folio, true) -static inline void set_page_writeback(struct page *page) +static inline void set_page_writeback_keepwrite(struct page *page) { - test_set_page_writeback(page); + folio_start_writeback_keepwrite(page_folio(page)); } -static inline void set_page_writeback_keepwrite(struct page *page) +static inline bool test_set_page_writeback(struct page *page) { - test_set_page_writeback_keepwrite(page); + return set_page_writeback(page); } __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 2ccd8f213fc4..10ce5582d869 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -71,3 +71,9 @@ void migrate_page_copy(struct page *newpage, struct page *page) } EXPORT_SYMBOL(migrate_page_copy); #endif + +bool set_page_writeback(struct page *page) +{ + return folio_start_writeback(page_folio(page)); +} +EXPORT_SYMBOL(set_page_writeback); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 9ff9a33bced1..82938b037103 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2811,21 +2811,23 @@ bool __folio_end_writeback(struct folio *folio) return ret; } -int __test_set_page_writeback(struct page *page, bool keep_write) +bool __folio_start_writeback(struct folio *folio, bool keep_write) { - struct address_space *mapping = page_mapping(page); - int ret, access_ret; + long nr = folio_nr_pages(folio); + struct address_space *mapping = folio_mapping(folio); + bool ret; + int access_ret; - lock_page_memcg(page); + folio_memcg_lock(folio); if (mapping && mapping_use_writeback_tags(mapping)) { - XA_STATE(xas, &mapping->i_pages, page_index(page)); + XA_STATE(xas, &mapping->i_pages, folio_index(folio)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); - ret = TestSetPageWriteback(page); + ret = folio_test_set_writeback(folio); if (!ret) { bool on_wblist; @@ -2836,43 +2838,42 @@ int __test_set_page_writeback(struct page *page, bool keep_write) if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) { struct bdi_writeback *wb = inode_to_wb(inode); - inc_wb_stat(wb, WB_WRITEBACK); + wb_stat_mod(wb, WB_WRITEBACK, nr); if (!on_wblist) wb_inode_writeback_start(wb); } /* - * We can come through here when swapping anonymous - * pages, so we don't necessarily have an inode to track - * for sync. + * We can come through here when swapping + * anonymous folios, so we don't necessarily + * have an inode to track for sync. */ if (mapping->host && !on_wblist) sb_mark_inode_writeback(mapping->host); } - if (!PageDirty(page)) + if (!folio_test_dirty(folio)) xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); } else { - ret = TestSetPageWriteback(page); + ret = folio_test_set_writeback(folio); } if (!ret) { - inc_lruvec_page_state(page, NR_WRITEBACK); - inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); + lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); } - unlock_page_memcg(page); - access_ret = arch_make_page_accessible(page); + folio_memcg_unlock(folio); + access_ret = arch_make_folio_accessible(folio); /* * If writeback has been triggered on a page that cannot be made * accessible, it is too late to recover here. */ - VM_BUG_ON_PAGE(access_ret != 0, page); + VM_BUG_ON_FOLIO(access_ret != 0, folio); return ret; - } -EXPORT_SYMBOL(__test_set_page_writeback); +EXPORT_SYMBOL(__folio_start_writeback); /** * folio_wait_writeback - Wait for a folio to finish writeback. -- cgit v1.2.3 From b5e84594cafb934e023ee7d4ea4208b6c6b65fcc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 26 Apr 2021 23:53:10 -0400 Subject: mm/writeback: Add folio_mark_dirty() Reimplement set_page_dirty() as a wrapper around folio_mark_dirty(). There is no change to filesystems as they were already being called with the compound_head of the page being marked dirty. We avoid several calls to compound_head(), both statically (through using folio_test_dirty() instead of PageDirty() and dynamically by calling folio_mapping() instead of page_mapping(). Also return bool instead of int to show the range of values actually returned, and add kernel-doc. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 3 ++- mm/folio-compat.c | 6 ++++++ mm/page-writeback.c | 35 +++++++++++++++++++---------------- 3 files changed, 27 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 93d5fbe2e4e3..00510b02ffe1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2008,7 +2008,8 @@ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); void account_page_cleaned(struct page *page, struct address_space *mapping, struct bdi_writeback *wb); -int set_page_dirty(struct page *page); +bool folio_mark_dirty(struct folio *folio); +bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); void __cancel_dirty_page(struct page *page); static inline void cancel_dirty_page(struct page *page) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 10ce5582d869..2c2b3917b5dc 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -77,3 +77,9 @@ bool set_page_writeback(struct page *page) return folio_start_writeback(page_folio(page)); } EXPORT_SYMBOL(set_page_writeback); + +bool set_page_dirty(struct page *page) +{ + return folio_mark_dirty(page_folio(page)); +} +EXPORT_SYMBOL(set_page_dirty); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 82938b037103..c79801656f5b 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2581,18 +2581,21 @@ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) } EXPORT_SYMBOL(redirty_page_for_writepage); -/* - * Dirty a page. +/** + * folio_mark_dirty - Mark a folio as being modified. + * @folio: The folio. + * + * For folios with a mapping this should be done under the page lock + * for the benefit of asynchronous memory errors who prefer a consistent + * dirty state. This rule can be broken in some special cases, + * but should be better not to. * - * For pages with a mapping this should be done under the page lock for the - * benefit of asynchronous memory errors who prefer a consistent dirty state. - * This rule can be broken in some special cases, but should be better not to. + * Return: True if the folio was newly dirtied, false if it was already dirty. */ -int set_page_dirty(struct page *page) +bool folio_mark_dirty(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); - page = compound_head(page); if (likely(mapping)) { /* * readahead/lru_deactivate_page could remain @@ -2604,17 +2607,17 @@ int set_page_dirty(struct page *page) * it will confuse readahead and make it restart the size rampup * process. But it's a trivial problem. */ - if (PageReclaim(page)) - ClearPageReclaim(page); - return mapping->a_ops->set_page_dirty(page); + if (folio_test_reclaim(folio)) + folio_clear_reclaim(folio); + return mapping->a_ops->set_page_dirty(&folio->page); } - if (!PageDirty(page)) { - if (!TestSetPageDirty(page)) - return 1; + if (!folio_test_dirty(folio)) { + if (!folio_test_set_dirty(folio)) + return true; } - return 0; + return false; } -EXPORT_SYMBOL(set_page_dirty); +EXPORT_SYMBOL(folio_mark_dirty); /* * set_page_dirty() is racy if the caller has no reference against -- cgit v1.2.3 From 203a31516616111b8eaaf00c16fa3fcaa25e6f81 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 4 May 2021 11:01:10 -0400 Subject: mm/writeback: Add __folio_mark_dirty() Turn __set_page_dirty() into a wrapper around __folio_mark_dirty(). Convert account_page_dirtied() into folio_account_dirtied() and account the number of pages in the folio to support multi-page folios. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/memcontrol.h | 5 ++--- include/linux/pagemap.h | 7 ++++++- mm/page-writeback.c | 41 +++++++++++++++++++++-------------------- 3 files changed, 29 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 7bd78c13d1fa..e34bf0cbdf55 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1615,10 +1615,9 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); -static inline void mem_cgroup_track_foreign_dirty(struct page *page, +static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { - struct folio *folio = page_folio(page); if (mem_cgroup_disabled()) return; @@ -1643,7 +1642,7 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, { } -static inline void mem_cgroup_track_foreign_dirty(struct page *page, +static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index bdbd7be67812..aa9a083083df 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -772,8 +772,13 @@ void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void wait_for_stable_page(struct page *page); void folio_wait_stable(struct folio *folio); +void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); +static inline void __set_page_dirty(struct page *page, + struct address_space *mapping, int warn) +{ + __folio_mark_dirty(page_folio(page), mapping, warn); +} -void __set_page_dirty(struct page *, struct address_space *, int warn); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index c79801656f5b..40d77597385f 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2438,29 +2438,30 @@ EXPORT_SYMBOL(__set_page_dirty_no_writeback); * * NOTE: This relies on being atomic wrt interrupts. */ -static void account_page_dirtied(struct page *page, +static void folio_account_dirtied(struct folio *folio, struct address_space *mapping) { struct inode *inode = mapping->host; - trace_writeback_dirty_page(page, mapping); + trace_writeback_dirty_page(&folio->page, mapping); if (mapping_can_writeback(mapping)) { struct bdi_writeback *wb; + long nr = folio_nr_pages(folio); - inode_attach_wb(inode, page); + inode_attach_wb(inode, &folio->page); wb = inode_to_wb(inode); - __inc_lruvec_page_state(page, NR_FILE_DIRTY); - __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING); - __inc_node_page_state(page, NR_DIRTIED); - inc_wb_stat(wb, WB_RECLAIMABLE); - inc_wb_stat(wb, WB_DIRTIED); - task_io_account_write(PAGE_SIZE); - current->nr_dirtied++; - __this_cpu_inc(bdp_ratelimits); + __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr); + __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr); + __node_stat_mod_folio(folio, NR_DIRTIED, nr); + wb_stat_mod(wb, WB_RECLAIMABLE, nr); + wb_stat_mod(wb, WB_DIRTIED, nr); + task_io_account_write(nr * PAGE_SIZE); + current->nr_dirtied += nr; + __this_cpu_add(bdp_ratelimits, nr); - mem_cgroup_track_foreign_dirty(page, wb); + mem_cgroup_track_foreign_dirty(folio, wb); } } @@ -2481,24 +2482,24 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, } /* - * Mark the page dirty, and set it dirty in the page cache, and mark the inode - * dirty. + * Mark the folio dirty, and set it dirty in the page cache, and mark + * the inode dirty. * - * If warn is true, then emit a warning if the page is not uptodate and has + * If warn is true, then emit a warning if the folio is not uptodate and has * not been truncated. * * The caller must hold lock_page_memcg(). */ -void __set_page_dirty(struct page *page, struct address_space *mapping, +void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, int warn) { unsigned long flags; xa_lock_irqsave(&mapping->i_pages, flags); - if (page->mapping) { /* Race with truncate? */ - WARN_ON_ONCE(warn && !PageUptodate(page)); - account_page_dirtied(page, mapping); - __xa_set_mark(&mapping->i_pages, page_index(page), + if (folio->mapping) { /* Race with truncate? */ + WARN_ON_ONCE(warn && !folio_test_uptodate(folio)); + folio_account_dirtied(folio, mapping); + __xa_set_mark(&mapping->i_pages, folio_index(folio), PAGECACHE_TAG_DIRTY); } xa_unlock_irqrestore(&mapping->i_pages, flags); -- cgit v1.2.3 From 85d4d2ebc86f02740c5f5f72ec43cc47d3560720 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 3 May 2021 23:30:44 -0400 Subject: mm/writeback: Add filemap_dirty_folio() Reimplement __set_page_dirty_nobuffers() as a wrapper around filemap_dirty_folio(). Eventually folio_mark_dirty() will pass the folio's mapping to the address space's ->dirty_folio() operation, so add the parameter to filemap_dirty_folio() now. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/writeback.h | 1 + mm/folio-compat.c | 6 +++++ mm/page-writeback.c | 60 ++++++++++++++++++++++++----------------------- 3 files changed, 38 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d1f65adf6a26..d4f24eba066f 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -393,6 +393,7 @@ void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); +bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio); void account_page_redirty(struct page *page); void sb_mark_inode_writeback(struct inode *inode); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 2c2b3917b5dc..dad962b920e5 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -83,3 +83,9 @@ bool set_page_dirty(struct page *page) return folio_mark_dirty(page_folio(page)); } EXPORT_SYMBOL(set_page_dirty); + +int __set_page_dirty_nobuffers(struct page *page) +{ + return filemap_dirty_folio(page_mapping(page), page_folio(page)); +} +EXPORT_SYMBOL(__set_page_dirty_nobuffers); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index ebbd15f0d841..a501dad430af 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2505,41 +2505,43 @@ void __folio_mark_dirty(struct folio *folio, struct address_space *mapping, xa_unlock_irqrestore(&mapping->i_pages, flags); } -/* - * For address_spaces which do not use buffers. Just tag the page as dirty in - * the xarray. - * - * This is also used when a single buffer is being dirtied: we want to set the - * page dirty in that case, but not all the buffers. This is a "bottom-up" - * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. - * - * The caller must ensure this doesn't race with truncation. Most will simply - * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and - * the pte lock held, which also locks out truncation. +/** + * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads. + * @mapping: Address space this folio belongs to. + * @folio: Folio to be marked as dirty. + * + * Filesystems which do not use buffer heads should call this function + * from their set_page_dirty address space operation. It ignores the + * contents of folio_get_private(), so if the filesystem marks individual + * blocks as dirty, the filesystem should handle that itself. + * + * This is also sometimes used by filesystems which use buffer_heads when + * a single buffer is being dirtied: we want to set the folio dirty in + * that case, but not all the buffers. This is a "bottom-up" dirtying, + * whereas __set_page_dirty_buffers() is a "top-down" dirtying. + * + * The caller must ensure this doesn't race with truncation. Most will + * simply hold the folio lock, but e.g. zap_pte_range() calls with the + * folio mapped and the pte lock held, which also locks out truncation. */ -int __set_page_dirty_nobuffers(struct page *page) +bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) { - lock_page_memcg(page); - if (!TestSetPageDirty(page)) { - struct address_space *mapping = page_mapping(page); + folio_memcg_lock(folio); + if (folio_test_set_dirty(folio)) { + folio_memcg_unlock(folio); + return false; + } - if (!mapping) { - unlock_page_memcg(page); - return 1; - } - __set_page_dirty(page, mapping, !PagePrivate(page)); - unlock_page_memcg(page); + __folio_mark_dirty(folio, mapping, !folio_test_private(folio)); + folio_memcg_unlock(folio); - if (mapping->host) { - /* !PageAnon && !swapper_space */ - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - } - return 1; + if (mapping->host) { + /* !PageAnon && !swapper_space */ + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } - unlock_page_memcg(page); - return 0; + return true; } -EXPORT_SYMBOL(__set_page_dirty_nobuffers); +EXPORT_SYMBOL(filemap_dirty_folio); /* * Call this whenever redirtying a page, to de-account the dirty counters -- cgit v1.2.3 From fc9b6a538b222eaeb4d1e3f93e716b6626d9b653 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 4 May 2021 16:12:09 -0400 Subject: mm/writeback: Add folio_account_cleaned() Get the statistics right; compound pages were being accounted as a single page. This didn't matter before now as no filesystem which supported compound pages did writeback. Also move the declaration to pagemap.h since this is part of the page cache. Add a wrapper for account_page_cleaned(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 3 --- include/linux/pagemap.h | 7 +++++++ mm/page-writeback.c | 11 ++++++----- 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 00510b02ffe1..f47af4ca4873 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -39,7 +39,6 @@ struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; -struct bdi_writeback; struct pt_regs; extern int sysctl_page_lock_unfairness; @@ -2006,8 +2005,6 @@ extern void do_invalidatepage(struct page *page, unsigned int offset, int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page); -void account_page_cleaned(struct page *page, struct address_space *mapping, - struct bdi_writeback *wb); bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index aa9a083083df..8ba7da513ac4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -778,6 +778,13 @@ static inline void __set_page_dirty(struct page *page, { __folio_mark_dirty(page_folio(page), mapping, warn); } +void folio_account_cleaned(struct folio *folio, struct address_space *mapping, + struct bdi_writeback *wb); +static inline void account_page_cleaned(struct page *page, + struct address_space *mapping, struct bdi_writeback *wb) +{ + return folio_account_cleaned(page_folio(page), mapping, wb); +} int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index a501dad430af..82e3bc3d4eae 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2470,14 +2470,15 @@ static void folio_account_dirtied(struct folio *folio, * * Caller must hold lock_page_memcg(). */ -void account_page_cleaned(struct page *page, struct address_space *mapping, +void folio_account_cleaned(struct folio *folio, struct address_space *mapping, struct bdi_writeback *wb) { if (mapping_can_writeback(mapping)) { - dec_lruvec_page_state(page, NR_FILE_DIRTY); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - dec_wb_stat(wb, WB_RECLAIMABLE); - task_io_account_cancelled_write(PAGE_SIZE); + long nr = folio_nr_pages(folio); + lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + wb_stat_mod(wb, WB_RECLAIMABLE, -nr); + task_io_account_cancelled_write(nr * PAGE_SIZE); } } -- cgit v1.2.3 From fdaf532a23795e320c47e1caab50a53c202135c5 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 8 Mar 2021 16:43:04 -0500 Subject: mm/writeback: Add folio_cancel_dirty() Turn __cancel_dirty_page() into __folio_cancel_dirty() and add wrappers. Move the prototypes into pagemap.h since this is page cache functionality. Saves 44 bytes of kernel text in total; 33 bytes from __folio_cancel_dirty and 11 from two callers of cancel_dirty_page(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 7 ------- include/linux/pagemap.h | 11 +++++++++++ mm/page-writeback.c | 16 ++++++++-------- 3 files changed, 19 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f47af4ca4873..3bc394aafbc0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2008,13 +2008,6 @@ int redirty_page_for_writepage(struct writeback_control *wbc, bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); -void __cancel_dirty_page(struct page *page); -static inline void cancel_dirty_page(struct page *page) -{ - /* Avoid atomic ops, locking, etc. when not actually needed. */ - if (PageDirty(page)) - __cancel_dirty_page(page); -} int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8ba7da513ac4..8f4a9ba0bfb0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -785,6 +785,17 @@ static inline void account_page_cleaned(struct page *page, { return folio_account_cleaned(page_folio(page), mapping, wb); } +void __folio_cancel_dirty(struct folio *folio); +static inline void folio_cancel_dirty(struct folio *folio) +{ + /* Avoid atomic ops, locking, etc. when not actually needed. */ + if (folio_test_dirty(folio)) + __folio_cancel_dirty(folio); +} +static inline void cancel_dirty_page(struct page *page) +{ + folio_cancel_dirty(page_folio(page)); +} int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 82e3bc3d4eae..16c4ab0cc1c9 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2657,28 +2657,28 @@ EXPORT_SYMBOL(set_page_dirty_lock); * page without actually doing it through the VM. Can you say "ext3 is * horribly ugly"? Thought you could. */ -void __cancel_dirty_page(struct page *page) +void __folio_cancel_dirty(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio_mapping(folio); if (mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; - lock_page_memcg(page); + folio_memcg_lock(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); - if (TestClearPageDirty(page)) - account_page_cleaned(page, mapping, wb); + if (folio_test_clear_dirty(folio)) + folio_account_cleaned(folio, mapping, wb); unlocked_inode_to_wb_end(inode, &cookie); - unlock_page_memcg(page); + folio_memcg_unlock(folio); } else { - ClearPageDirty(page); + folio_clear_dirty(folio); } } -EXPORT_SYMBOL(__cancel_dirty_page); +EXPORT_SYMBOL(__folio_cancel_dirty); /* * Clear a page's dirty flag, while caring for dirty memory accounting. -- cgit v1.2.3 From 9350f20a070d27a6c6a292a2b6f6091e7ea90a65 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 28 Feb 2021 16:21:20 -0500 Subject: mm/writeback: Add folio_clear_dirty_for_io() Transform clear_page_dirty_for_io() into folio_clear_dirty_for_io() and add a compatibility wrapper. Also move the declaration to pagemap.h as this is page cache functionality that doesn't need to be used by the rest of the kernel. Increases the size of the kernel by 79 bytes. While we remove a few calls to compound_head(), we add a call to folio_nr_pages() to get the stats correct for the eventual support of multi-page folios. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 1 - include/linux/pagemap.h | 2 ++ mm/folio-compat.c | 6 +++++ mm/page-writeback.c | 63 +++++++++++++++++++++++++------------------------ 4 files changed, 40 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 3bc394aafbc0..dd5c6970ba67 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2008,7 +2008,6 @@ int redirty_page_for_writepage(struct writeback_control *wbc, bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); -int clear_page_dirty_for_io(struct page *page); int get_cmdline(struct task_struct *task, char *buffer, int buflen); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8f4a9ba0bfb0..0dda6459d2d1 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -796,6 +796,8 @@ static inline void cancel_dirty_page(struct page *page) { folio_cancel_dirty(page_folio(page)); } +bool folio_clear_dirty_for_io(struct folio *folio); +bool clear_page_dirty_for_io(struct page *page); int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index dad962b920e5..39f5a8d963b1 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -89,3 +89,9 @@ int __set_page_dirty_nobuffers(struct page *page) return filemap_dirty_folio(page_mapping(page), page_folio(page)); } EXPORT_SYMBOL(__set_page_dirty_nobuffers); + +bool clear_page_dirty_for_io(struct page *page) +{ + return folio_clear_dirty_for_io(page_folio(page)); +} +EXPORT_SYMBOL(clear_page_dirty_for_io); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 16c4ab0cc1c9..85c04445de97 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2681,25 +2681,25 @@ void __folio_cancel_dirty(struct folio *folio) EXPORT_SYMBOL(__folio_cancel_dirty); /* - * Clear a page's dirty flag, while caring for dirty memory accounting. - * Returns true if the page was previously dirty. - * - * This is for preparing to put the page under writeout. We leave the page - * tagged as dirty in the xarray so that a concurrent write-for-sync - * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage - * implementation will run either set_page_writeback() or set_page_dirty(), - * at which stage we bring the page's dirty flag and xarray dirty tag - * back into sync. - * - * This incoherency between the page's dirty flag and xarray tag is - * unfortunate, but it only exists while the page is locked. + * Clear a folio's dirty flag, while caring for dirty memory accounting. + * Returns true if the folio was previously dirty. + * + * This is for preparing to put the folio under writeout. We leave + * the folio tagged as dirty in the xarray so that a concurrent + * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk. + * The ->writepage implementation will run either folio_start_writeback() + * or folio_mark_dirty(), at which stage we bring the folio's dirty flag + * and xarray dirty tag back into sync. + * + * This incoherency between the folio's dirty flag and xarray tag is + * unfortunate, but it only exists while the folio is locked. */ -int clear_page_dirty_for_io(struct page *page) +bool folio_clear_dirty_for_io(struct folio *folio) { - struct address_space *mapping = page_mapping(page); - int ret = 0; + struct address_space *mapping = folio_mapping(folio); + bool ret = false; - VM_BUG_ON_PAGE(!PageLocked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; @@ -2712,48 +2712,49 @@ int clear_page_dirty_for_io(struct page *page) * We use this sequence to make sure that * (a) we account for dirty stats properly * (b) we tell the low-level filesystem to - * mark the whole page dirty if it was + * mark the whole folio dirty if it was * dirty in a pagetable. Only to then - * (c) clean the page again and return 1 to + * (c) clean the folio again and return 1 to * cause the writeback. * * This way we avoid all nasty races with the * dirty bit in multiple places and clearing * them concurrently from different threads. * - * Note! Normally the "set_page_dirty(page)" + * Note! Normally the "folio_mark_dirty(folio)" * has no effect on the actual dirty bit - since * that will already usually be set. But we * need the side effects, and it can help us * avoid races. * - * We basically use the page "master dirty bit" + * We basically use the folio "master dirty bit" * as a serialization point for all the different * threads doing their things. */ - if (page_mkclean(page)) - set_page_dirty(page); + if (folio_mkclean(folio)) + folio_mark_dirty(folio); /* * We carefully synchronise fault handlers against - * installing a dirty pte and marking the page dirty + * installing a dirty pte and marking the folio dirty * at this point. We do this by having them hold the - * page lock while dirtying the page, and pages are + * page lock while dirtying the folio, and folios are * always locked coming in here, so we get the desired * exclusion. */ wb = unlocked_inode_to_wb_begin(inode, &cookie); - if (TestClearPageDirty(page)) { - dec_lruvec_page_state(page, NR_FILE_DIRTY); - dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); - dec_wb_stat(wb, WB_RECLAIMABLE); - ret = 1; + if (folio_test_clear_dirty(folio)) { + long nr = folio_nr_pages(folio); + lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr); + zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr); + wb_stat_mod(wb, WB_RECLAIMABLE, -nr); + ret = true; } unlocked_inode_to_wb_end(inode, &cookie); return ret; } - return TestClearPageDirty(page); + return folio_test_clear_dirty(folio); } -EXPORT_SYMBOL(clear_page_dirty_for_io); +EXPORT_SYMBOL(folio_clear_dirty_for_io); static void wb_inode_writeback_start(struct bdi_writeback *wb) { -- cgit v1.2.3 From 25ff8b15537dfa0e1a62d55cfcc48f3c8bd8a76c Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 3 May 2021 10:06:55 -0400 Subject: mm/writeback: Add folio_account_redirty() Account the number of pages in the folio that we're redirtying. Turn account_page_dirty() into a wrapper around it. Also turn the comment on folio_account_redirty() into kernel-doc and edit it slightly so it makes sense to its potential callers. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/writeback.h | 6 +++++- mm/page-writeback.c | 32 +++++++++++++++++++------------- 2 files changed, 24 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d4f24eba066f..852100bea351 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -394,7 +394,11 @@ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio); -void account_page_redirty(struct page *page); +void folio_account_redirty(struct folio *folio); +static inline void account_page_redirty(struct page *page) +{ + folio_account_redirty(page_folio(page)); +} void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 85c04445de97..7ef904363fb7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1084,7 +1084,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb, * write_bandwidth = --------------------------------------------------- * period * - * @written may have decreased due to account_page_redirty(). + * @written may have decreased due to folio_account_redirty(). * Avoid underflowing @bw calculation. */ bw = written - min(written, wb->written_stamp); @@ -2544,30 +2544,36 @@ bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio) } EXPORT_SYMBOL(filemap_dirty_folio); -/* - * Call this whenever redirtying a page, to de-account the dirty counters - * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written - * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to - * systematic errors in balanced_dirty_ratelimit and the dirty pages position - * control. +/** + * folio_account_redirty - Manually account for redirtying a page. + * @folio: The folio which is being redirtied. + * + * Most filesystems should call folio_redirty_for_writepage() instead + * of this fuction. If your filesystem is doing writeback outside the + * context of a writeback_control(), it can call this when redirtying + * a folio, to de-account the dirty counters (NR_DIRTIED, WB_DIRTIED, + * tsk->nr_dirtied), so that they match the written counters (NR_WRITTEN, + * WB_WRITTEN) in long term. The mismatches will lead to systematic errors + * in balanced_dirty_ratelimit and the dirty pages position control. */ -void account_page_redirty(struct page *page) +void folio_account_redirty(struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; if (mapping && mapping_can_writeback(mapping)) { struct inode *inode = mapping->host; struct bdi_writeback *wb; struct wb_lock_cookie cookie = {}; + long nr = folio_nr_pages(folio); wb = unlocked_inode_to_wb_begin(inode, &cookie); - current->nr_dirtied--; - dec_node_page_state(page, NR_DIRTIED); - dec_wb_stat(wb, WB_DIRTIED); + current->nr_dirtied -= nr; + node_stat_mod_folio(folio, NR_DIRTIED, -nr); + wb_stat_mod(wb, WB_DIRTIED, -nr); unlocked_inode_to_wb_end(inode, &cookie); } } -EXPORT_SYMBOL(account_page_redirty); +EXPORT_SYMBOL(folio_account_redirty); /* * When a writepage implementation decides that it doesn't want to write this -- cgit v1.2.3 From cd78ab11a8810dd297f4751d17cc53e3dce36024 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 2 May 2021 23:22:52 -0400 Subject: mm/writeback: Add folio_redirty_for_writepage() Reimplement redirty_page_for_writepage() as a wrapper around folio_redirty_for_writepage(). Account the number of pages in the folio, add kernel-doc and move the prototype to writeback.h. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- fs/jfs/jfs_metapage.c | 1 + include/linux/mm.h | 4 ---- include/linux/writeback.h | 2 ++ mm/folio-compat.c | 7 +++++++ mm/page-writeback.c | 30 ++++++++++++++++++++---------- 5 files changed, 30 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 176580f54af9..104ae698443e 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "jfs_incore.h" #include "jfs_superblock.h" #include "jfs_filsys.h" diff --git a/include/linux/mm.h b/include/linux/mm.h index dd5c6970ba67..23ab040aa65a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -36,9 +36,7 @@ struct mempolicy; struct anon_vma; struct anon_vma_chain; -struct file_ra_state; struct user_struct; -struct writeback_control; struct pt_regs; extern int sysctl_page_lock_unfairness; @@ -2003,8 +2001,6 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); -int redirty_page_for_writepage(struct writeback_control *wbc, - struct page *page); bool folio_mark_dirty(struct folio *folio); bool set_page_dirty(struct page *page); int set_page_dirty_lock(struct page *page); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 852100bea351..3571f383dfb6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -399,6 +399,8 @@ static inline void account_page_redirty(struct page *page) { folio_account_redirty(page_folio(page)); } +bool folio_redirty_for_writepage(struct writeback_control *, struct folio *); +bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 39f5a8d963b1..c1e01bc36d32 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -95,3 +95,10 @@ bool clear_page_dirty_for_io(struct page *page) return folio_clear_dirty_for_io(page_folio(page)); } EXPORT_SYMBOL(clear_page_dirty_for_io); + +bool redirty_page_for_writepage(struct writeback_control *wbc, + struct page *page) +{ + return folio_redirty_for_writepage(wbc, page_folio(page)); +} +EXPORT_SYMBOL(redirty_page_for_writepage); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 7ef904363fb7..a0c35a9d8029 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2575,21 +2575,31 @@ void folio_account_redirty(struct folio *folio) } EXPORT_SYMBOL(folio_account_redirty); -/* - * When a writepage implementation decides that it doesn't want to write this - * page for some reason, it should redirty the locked page via - * redirty_page_for_writepage() and it should then unlock the page and return 0 +/** + * folio_redirty_for_writepage - Decline to write a dirty folio. + * @wbc: The writeback control. + * @folio: The folio. + * + * When a writepage implementation decides that it doesn't want to write + * @folio for some reason, it should call this function, unlock @folio and + * return 0. + * + * Return: True if we redirtied the folio. False if someone else dirtied + * it first. */ -int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) +bool folio_redirty_for_writepage(struct writeback_control *wbc, + struct folio *folio) { - int ret; + bool ret; + long nr = folio_nr_pages(folio); + + wbc->pages_skipped += nr; + ret = filemap_dirty_folio(folio->mapping, folio); + folio_account_redirty(folio); - wbc->pages_skipped++; - ret = __set_page_dirty_nobuffers(page); - account_page_redirty(page); return ret; } -EXPORT_SYMBOL(redirty_page_for_writepage); +EXPORT_SYMBOL(folio_redirty_for_writepage); /** * folio_mark_dirty - Mark a folio as being modified. -- cgit v1.2.3 From 9eb7c76dd31a53331bec795faaf7daa7ffb80071 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 27 Apr 2021 23:11:28 -0400 Subject: mm/filemap: Add i_blocks_per_folio() Reimplement i_blocks_per_page() as a wrapper around i_blocks_per_folio(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 0dda6459d2d1..5431d9920dc0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1149,19 +1149,25 @@ static inline int page_mkwrite_check_truncate(struct page *page, } /** - * i_blocks_per_page - How many blocks fit in this page. + * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. - * @page: The page (head page if the page is a THP). + * @folio: The folio. * - * If the block size is larger than the size of this page, return zero. + * If the block size is larger than the size of this folio, return zero. * - * Context: The caller should hold a refcount on the page to prevent it + * Context: The caller should hold a refcount on the folio to prevent it * from being split. - * Return: The number of filesystem blocks covered by this page. + * Return: The number of filesystem blocks covered by this folio. */ +static inline +unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio) +{ + return folio_size(folio) >> inode->i_blkbits; +} + static inline unsigned int i_blocks_per_page(struct inode *inode, struct page *page) { - return thp_size(page) >> inode->i_blkbits; + return i_blocks_per_folio(inode, page_folio(page)); } #endif /* _LINUX_PAGEMAP_H */ -- cgit v1.2.3 From f705bf84eab2aa3b9842974b8443587727ccb23a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 28 Apr 2021 22:30:06 -0400 Subject: mm/filemap: Add folio_mkwrite_check_truncate() This is the folio equivalent of page_mkwrite_check_truncate(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells --- include/linux/pagemap.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 5431d9920dc0..4b74d83c5571 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1120,6 +1120,34 @@ static inline unsigned long dir_pages(struct inode *inode) PAGE_SHIFT; } +/** + * folio_mkwrite_check_truncate - check if folio was truncated + * @folio: the folio to check + * @inode: the inode to check the folio against + * + * Return: the number of bytes in the folio up to EOF, + * or -EFAULT if the folio was truncated. + */ +static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio, + struct inode *inode) +{ + loff_t size = i_size_read(inode); + pgoff_t index = size >> PAGE_SHIFT; + size_t offset = offset_in_folio(folio, size); + + if (!folio->mapping) + return -EFAULT; + + /* folio is wholly inside EOF */ + if (folio_next_index(folio) - 1 < index) + return folio_size(folio); + /* folio is wholly past EOF */ + if (folio->index > index || !offset) + return -EFAULT; + /* folio is partially inside EOF */ + return offset; +} + /** * page_mkwrite_check_truncate - check if page was truncated * @page: the page to check -- cgit v1.2.3 From 9bf70167e3c61473b95f40771decc3778bf0fb9f Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 27 Apr 2021 16:37:09 -0400 Subject: mm/filemap: Add readahead_folio() The pointers stored in the page cache are folios, by definition. This change comes with a behaviour change -- callers of readahead_folio() are no longer required to put the page reference themselves. This matches how readpage works, rather than matching how readpages used to work. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 54 +++++++++++++++++++++++++++++++++++-------------- 1 file changed, 39 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 4b74d83c5571..fea9615bab35 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -987,33 +987,57 @@ void page_cache_async_readahead(struct address_space *mapping, page_cache_async_ra(&ractl, page, req_count); } +static inline struct folio *__readahead_folio(struct readahead_control *ractl) +{ + struct folio *folio; + + BUG_ON(ractl->_batch_count > ractl->_nr_pages); + ractl->_nr_pages -= ractl->_batch_count; + ractl->_index += ractl->_batch_count; + + if (!ractl->_nr_pages) { + ractl->_batch_count = 0; + return NULL; + } + + folio = xa_load(&ractl->mapping->i_pages, ractl->_index); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + ractl->_batch_count = folio_nr_pages(folio); + + return folio; +} + /** * readahead_page - Get the next page to read. - * @rac: The current readahead request. + * @ractl: The current readahead request. * * Context: The page is locked and has an elevated refcount. The caller * should decreases the refcount once the page has been submitted for I/O * and unlock the page once all I/O to that page has completed. * Return: A pointer to the next page, or %NULL if we are done. */ -static inline struct page *readahead_page(struct readahead_control *rac) +static inline struct page *readahead_page(struct readahead_control *ractl) { - struct page *page; + struct folio *folio = __readahead_folio(ractl); - BUG_ON(rac->_batch_count > rac->_nr_pages); - rac->_nr_pages -= rac->_batch_count; - rac->_index += rac->_batch_count; - - if (!rac->_nr_pages) { - rac->_batch_count = 0; - return NULL; - } + return &folio->page; +} - page = xa_load(&rac->mapping->i_pages, rac->_index); - VM_BUG_ON_PAGE(!PageLocked(page), page); - rac->_batch_count = thp_nr_pages(page); +/** + * readahead_folio - Get the next folio to read. + * @ractl: The current readahead request. + * + * Context: The folio is locked. The caller should unlock the folio once + * all I/O to that folio has completed. + * Return: A pointer to the next folio, or %NULL if we are done. + */ +static inline struct folio *readahead_folio(struct readahead_control *ractl) +{ + struct folio *folio = __readahead_folio(ractl); - return page; + if (folio) + folio_put(folio); + return folio; } static inline unsigned int __readahead_batch(struct readahead_control *rac, -- cgit v1.2.3 From 0995d7e568141226f10f8216aa4965e06ab5db8a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 29 Apr 2021 10:27:16 -0400 Subject: mm/workingset: Convert workingset_refault() to take a folio This nets us 178 bytes of savings from removing calls to compound_head. The three callers all grow a little, but each of them will be converted to use folios soon, so that's fine. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/swap.h | 4 ++-- include/linux/vmstat.h | 6 ------ mm/filemap.c | 2 +- mm/memory.c | 3 ++- mm/swap.c | 7 +++---- mm/swap_state.c | 2 +- mm/workingset.c | 42 ++++++++++++++++++++++-------------------- 7 files changed, 31 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 067b7af5242c..892faac942da 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -329,7 +329,7 @@ static inline swp_entry_t folio_swap_entry(struct folio *folio) /* linux/mm/workingset.c */ void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg); -void workingset_refault(struct page *page, void *shadow); +void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* Only track the nodes of mappings with shadow entries */ @@ -350,7 +350,7 @@ extern unsigned long nr_free_buffer_pages(void); /* linux/mm/swap.c */ extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); -extern void lru_note_cost_page(struct page *); +extern void lru_note_cost_folio(struct folio *); extern void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 241bd0f53fb9..bfe38869498d 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -597,12 +597,6 @@ static inline void mod_lruvec_page_state(struct page *page, #endif /* CONFIG_MEMCG */ -static inline void inc_lruvec_state(struct lruvec *lruvec, - enum node_stat_item idx) -{ - mod_lruvec_state(lruvec, idx, 1); -} - static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { diff --git a/mm/filemap.c b/mm/filemap.c index 5cb18399a1b6..c4a7f3fdca12 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -998,7 +998,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, */ WARN_ON_ONCE(PageActive(page)); if (!(gfp_mask & __GFP_WRITE) && shadow) - workingset_refault(page, shadow); + workingset_refault(page_folio(page), shadow); lru_cache_add(page); } return ret; diff --git a/mm/memory.c b/mm/memory.c index b67d80526bee..6308eeaed136 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3539,7 +3539,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) shadow = get_shadow_from_swap_cache(entry); if (shadow) - workingset_refault(page, shadow); + workingset_refault(page_folio(page), + shadow); lru_cache_add(page); diff --git a/mm/swap.c b/mm/swap.c index b95fd6d05768..5c1674c98f82 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -293,11 +293,10 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) } while ((lruvec = parent_lruvec(lruvec))); } -void lru_note_cost_page(struct page *page) +void lru_note_cost_folio(struct folio *folio) { - struct folio *folio = page_folio(page); - lru_note_cost(folio_lruvec(folio), - page_is_file_lru(page), thp_nr_pages(page)); + lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio), + folio_nr_pages(folio)); } static void __folio_activate(struct folio *folio, struct lruvec *lruvec) diff --git a/mm/swap_state.c b/mm/swap_state.c index bc7cee6b2ec5..8d4104242100 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -498,7 +498,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, mem_cgroup_swapin_uncharge_swap(entry); if (shadow) - workingset_refault(page, shadow); + workingset_refault(page_folio(page), shadow); /* Caller will initiate read into locked page */ lru_cache_add(page); diff --git a/mm/workingset.c b/mm/workingset.c index 1c96ed525a0e..109ab978251a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -273,17 +273,17 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) } /** - * workingset_refault - evaluate the refault of a previously evicted page - * @page: the freshly allocated replacement page - * @shadow: shadow entry of the evicted page + * workingset_refault - Evaluate the refault of a previously evicted folio. + * @folio: The freshly allocated replacement folio. + * @shadow: Shadow entry of the evicted folio. * * Calculates and evaluates the refault distance of the previously - * evicted page in the context of the node and the memcg whose memory + * evicted folio in the context of the node and the memcg whose memory * pressure caused the eviction. */ -void workingset_refault(struct page *page, void *shadow) +void workingset_refault(struct folio *folio, void *shadow) { - bool file = page_is_file_lru(page); + bool file = folio_is_file_lru(folio); struct mem_cgroup *eviction_memcg; struct lruvec *eviction_lruvec; unsigned long refault_distance; @@ -295,16 +295,17 @@ void workingset_refault(struct page *page, void *shadow) unsigned long refault; bool workingset; int memcgid; + long nr; unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* * Look up the memcg associated with the stored ID. It might - * have been deleted since the page's eviction. + * have been deleted since the folio's eviction. * * Note that in rare events the ID could have been recycled - * for a new cgroup that refaults a shared page. This is + * for a new cgroup that refaults a shared folio. This is * impossible to tell from the available data. However, this * should be a rare and limited disturbance, and activations * are always speculative anyway. Ultimately, it's the aging @@ -340,17 +341,18 @@ void workingset_refault(struct page *page, void *shadow) refault_distance = (refault - eviction) & EVICTION_MASK; /* - * The activation decision for this page is made at the level + * The activation decision for this folio is made at the level * where the eviction occurred, as that is where the LRU order - * during page reclaim is being determined. + * during folio reclaim is being determined. * - * However, the cgroup that will own the page is the one that + * However, the cgroup that will own the folio is the one that * is actually experiencing the refault event. */ - memcg = page_memcg(page); + nr = folio_nr_pages(folio); + memcg = folio_memcg(folio); lruvec = mem_cgroup_lruvec(memcg, pgdat); - inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file); + mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr); mem_cgroup_flush_stats(); /* @@ -376,16 +378,16 @@ void workingset_refault(struct page *page, void *shadow) if (refault_distance > workingset_size) goto out; - SetPageActive(page); - workingset_age_nonresident(lruvec, thp_nr_pages(page)); - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file); + folio_set_active(folio); + workingset_age_nonresident(lruvec, nr); + mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr); - /* Page was active prior to eviction */ + /* Folio was active prior to eviction */ if (workingset) { - SetPageWorkingset(page); + folio_set_workingset(folio); /* XXX: Move to lru_cache_add() when it supports new vs putback */ - lru_note_cost_page(page); - inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file); + lru_note_cost_folio(folio); + mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr); } out: rcu_read_unlock(); -- cgit v1.2.3 From 0d31125d2d3267ec349796418a16761bbda20387 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 29 Apr 2021 11:09:31 -0400 Subject: mm/lru: Add folio_add_lru() Reimplement lru_cache_add() as a wrapper around folio_add_lru(). Saves 159 bytes of kernel text due to removing calls to compound_head(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/swap.h | 1 + mm/folio-compat.c | 6 ++++++ mm/swap.c | 22 +++++++++++----------- 3 files changed, 18 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index 892faac942da..cdf0957a88a4 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -351,6 +351,7 @@ extern unsigned long nr_free_buffer_pages(void); extern void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages); extern void lru_note_cost_folio(struct folio *); +extern void folio_add_lru(struct folio *); extern void lru_cache_add(struct page *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index c1e01bc36d32..6de3cd78a4ae 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -102,3 +102,9 @@ bool redirty_page_for_writepage(struct writeback_control *wbc, return folio_redirty_for_writepage(wbc, page_folio(page)); } EXPORT_SYMBOL(redirty_page_for_writepage); + +void lru_cache_add(struct page *page) +{ + folio_add_lru(page_folio(page)); +} +EXPORT_SYMBOL(lru_cache_add); diff --git a/mm/swap.c b/mm/swap.c index 858b4a8220ca..8ff9ba7cf2de 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -437,29 +437,29 @@ void folio_mark_accessed(struct folio *folio) EXPORT_SYMBOL(folio_mark_accessed); /** - * lru_cache_add - add a page to a page list - * @page: the page to be added to the LRU. + * folio_add_lru - Add a folio to an LRU list. + * @folio: The folio to be added to the LRU. * - * Queue the page for addition to the LRU via pagevec. The decision on whether + * Queue the folio for addition to the LRU. The decision on whether * to add the page to the [in]active [file|anon] list is deferred until the - * pagevec is drained. This gives a chance for the caller of lru_cache_add() - * have the page added to the active list using mark_page_accessed(). + * pagevec is drained. This gives a chance for the caller of folio_add_lru() + * have the folio added to the active list using folio_mark_accessed(). */ -void lru_cache_add(struct page *page) +void folio_add_lru(struct folio *folio) { struct pagevec *pvec; - VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page); - VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio); + VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - get_page(page); + folio_get(folio); local_lock(&lru_pvecs.lock); pvec = this_cpu_ptr(&lru_pvecs.lru_add); - if (pagevec_add_and_need_flush(pvec, page)) + if (pagevec_add_and_need_flush(pvec, &folio->page)) __pagevec_lru_add(pvec); local_unlock(&lru_pvecs.lock); } -EXPORT_SYMBOL(lru_cache_add); +EXPORT_SYMBOL(folio_add_lru); /** * lru_cache_add_inactive_or_unevictable -- cgit v1.2.3 From cc09cb134124a42fbe3bdcebefdc54e286d8f3e5 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 15 Dec 2020 22:55:54 -0500 Subject: mm/page_alloc: Add folio allocation functions The __folio_alloc(), __folio_alloc_node() and folio_alloc() functions are mostly for type safety, but they also ensure that the page allocator allocates a compound page and initialises the deferred list if the page is large enough to have one. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Acked-by: Vlastimil Babka --- include/linux/gfp.h | 16 ++++++++++++++++ mm/mempolicy.c | 10 ++++++++++ mm/page_alloc.c | 12 ++++++++++++ 3 files changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index dc5ff40608ce..3745efd21cf6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -523,6 +523,8 @@ static inline void arch_alloc_page(struct page *page, int order) { } struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid, nodemask_t *nodemask); +struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask); unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, nodemask_t *nodemask, int nr_pages, @@ -564,6 +566,15 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order) return __alloc_pages(gfp_mask, order, nid, NULL); } +static inline +struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid) +{ + VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES); + VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid)); + + return __folio_alloc(gfp, order, nid, NULL); +} + /* * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE, * prefer the current CPU's closest node. Otherwise node must be valid and @@ -580,6 +591,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask, #ifdef CONFIG_NUMA struct page *alloc_pages(gfp_t gfp, unsigned int order); +struct folio *folio_alloc(gfp_t gfp, unsigned order); extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, int node, bool hugepage); @@ -590,6 +602,10 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { return alloc_pages_node(numa_node_id(), gfp_mask, order); } +static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) +{ + return __folio_alloc_node(gfp, order, numa_node_id()); +} #define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 1592b081c58e..251df91ddc80 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2202,6 +2202,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned order) } EXPORT_SYMBOL(alloc_pages); +struct folio *folio_alloc(gfp_t gfp, unsigned order) +{ + struct page *page = alloc_pages(gfp | __GFP_COMP, order); + + if (page && order > 1) + prep_transhuge_page(page); + return (struct folio *)page; +} +EXPORT_SYMBOL(folio_alloc); + int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 869d0b06e1ef..544ff5a11cb8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5400,6 +5400,18 @@ out: } EXPORT_SYMBOL(__alloc_pages); +struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid, + nodemask_t *nodemask) +{ + struct page *page = __alloc_pages(gfp | __GFP_COMP, order, + preferred_nid, nodemask); + + if (page && order > 1) + prep_transhuge_page(page); + return (struct folio *)page; +} +EXPORT_SYMBOL(__folio_alloc); + /* * Common helper functions. Never use with __GFP_HIGHMEM because the returned * address cannot represent highmem pages. Use alloc_pages and then kmap if -- cgit v1.2.3 From bb3c579e25e5757bc5bac1333f4a56dfebf7cb91 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 15 Dec 2020 23:11:07 -0500 Subject: mm/filemap: Add filemap_alloc_folio Reimplement __page_cache_alloc as a wrapper around filemap_alloc_folio to allow filesystems to be converted at our leisure. Increases kernel text size by 133 bytes, mostly in cachefiles_read_backing_file(). pagecache_get_page() shrinks by 32 bytes, though. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 11 ++++++++--- mm/filemap.c | 14 +++++++------- 2 files changed, 15 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index fea9615bab35..51c190ae3b0b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -262,14 +262,19 @@ static inline void *detach_page_private(struct page *page) } #ifdef CONFIG_NUMA -extern struct page *__page_cache_alloc(gfp_t gfp); +struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order); #else -static inline struct page *__page_cache_alloc(gfp_t gfp) +static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) { - return alloc_pages(gfp, 0); + return folio_alloc(gfp, order); } #endif +static inline struct page *__page_cache_alloc(gfp_t gfp) +{ + return &filemap_alloc_folio(gfp, 0)->page; +} + static inline struct page *page_cache_alloc(struct address_space *x) { return __page_cache_alloc(mapping_gfp_mask(x)); diff --git a/mm/filemap.c b/mm/filemap.c index c4a7f3fdca12..6976fb4af390 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1006,24 +1006,24 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, EXPORT_SYMBOL_GPL(add_to_page_cache_lru); #ifdef CONFIG_NUMA -struct page *__page_cache_alloc(gfp_t gfp) +struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) { int n; - struct page *page; + struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); - page = __alloc_pages_node(n, gfp, 0); - } while (!page && read_mems_allowed_retry(cpuset_mems_cookie)); + folio = __folio_alloc_node(gfp, order, n); + } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); - return page; + return folio; } - return alloc_pages(gfp, 0); + return folio_alloc(gfp, order); } -EXPORT_SYMBOL(__page_cache_alloc); +EXPORT_SYMBOL(filemap_alloc_folio); #endif /* -- cgit v1.2.3 From 9dd3d069406cea073fc633e77bc59abbfde8c6c4 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 8 Dec 2020 08:56:28 -0500 Subject: mm/filemap: Add filemap_add_folio() Convert __add_to_page_cache_locked() into __filemap_add_folio(). Add an assertion to it that (for !hugetlbfs), the folio is naturally aligned within the file. Move the prototype from mm.h to pagemap.h. Convert add_to_page_cache_lru() into filemap_add_folio(). Add a compatibility wrapper for unconverted callers. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/mm.h | 7 ----- include/linux/pagemap.h | 10 +++++-- kernel/bpf/verifier.c | 2 +- mm/filemap.c | 70 ++++++++++++++++++++++++------------------------- mm/folio-compat.c | 7 +++++ 5 files changed, 50 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 23ab040aa65a..efcb06fc6116 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -213,13 +213,6 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *, loff_t *); -/* - * Any attempt to mark this function as static leads to build failure - * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked() - * is referred to by BPF code. This must be visible for error injection. - */ -int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp, void **shadowp); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 51c190ae3b0b..a10eb6dc3866 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -876,9 +876,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, size_t size) } int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp); +int filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp); extern void delete_from_page_cache(struct page *page); extern void __delete_from_page_cache(struct page *page, void *shadow); void replace_page_cache_page(struct page *old, struct page *new); @@ -903,6 +905,10 @@ static inline int add_to_page_cache(struct page *page, return error; } +/* Must be non-static for BPF error injection */ +int __filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp, void **shadowp); + /** * struct readahead_control - Describes a readahead request. * diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e76b55917905..de006552be8a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13319,7 +13319,7 @@ BTF_SET_START(btf_non_sleepable_error_inject) /* Three functions below can be called from sleepable and non-sleepable context. * Assume non-sleepable from bpf safety point of view. */ -BTF_ID(func, __add_to_page_cache_locked) +BTF_ID(func, __filemap_add_folio) BTF_ID(func, should_fail_alloc_page) BTF_ID(func, should_failslab) BTF_SET_END(btf_non_sleepable_error_inject) diff --git a/mm/filemap.c b/mm/filemap.c index 6976fb4af390..3902e7e8877d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -872,26 +872,25 @@ void replace_page_cache_page(struct page *old, struct page *new) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -noinline int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp, - void **shadowp) +noinline int __filemap_add_folio(struct address_space *mapping, + struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { - XA_STATE(xas, &mapping->i_pages, offset); - int huge = PageHuge(page); + XA_STATE(xas, &mapping->i_pages, index); + int huge = folio_test_hugetlb(folio); int error; bool charged = false; - VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(PageSwapBacked(page), page); + VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); + VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); - get_page(page); - page->mapping = mapping; - page->index = offset; + folio_get(folio); + folio->mapping = mapping; + folio->index = index; if (!huge) { - error = mem_cgroup_charge(page_folio(page), NULL, gfp); + error = mem_cgroup_charge(folio, NULL, gfp); + VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); if (error) goto error; charged = true; @@ -903,7 +902,7 @@ noinline int __add_to_page_cache_locked(struct page *page, unsigned int order = xa_get_order(xas.xa, xas.xa_index); void *entry, *old = NULL; - if (order > thp_order(page)) + if (order > folio_order(folio)) xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index), order, gfp); xas_lock_irq(&xas); @@ -920,13 +919,13 @@ noinline int __add_to_page_cache_locked(struct page *page, *shadowp = old; /* entry may have been split before we acquired lock */ order = xa_get_order(xas.xa, xas.xa_index); - if (order > thp_order(page)) { + if (order > folio_order(folio)) { xas_split(&xas, old, order); xas_reset(&xas); } } - xas_store(&xas, page); + xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; @@ -934,7 +933,7 @@ noinline int __add_to_page_cache_locked(struct page *page, /* hugetlb pages do not participate in page cache accounting */ if (!huge) - __inc_lruvec_page_state(page, NR_FILE_PAGES); + __lruvec_stat_add_folio(folio, NR_FILE_PAGES); unlock: xas_unlock_irq(&xas); } while (xas_nomem(&xas, gfp)); @@ -942,19 +941,19 @@ unlock: if (xas_error(&xas)) { error = xas_error(&xas); if (charged) - mem_cgroup_uncharge(page_folio(page)); + mem_cgroup_uncharge(folio); goto error; } - trace_mm_filemap_add_to_page_cache(page); + trace_mm_filemap_add_to_page_cache(&folio->page); return 0; error: - page->mapping = NULL; + folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - put_page(page); + folio_put(folio); return error; } -ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); +ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); /** * add_to_page_cache_locked - add a locked page to the pagecache @@ -971,39 +970,38 @@ ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO); int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { - return __add_to_page_cache_locked(page, mapping, offset, + return __filemap_add_folio(mapping, page_folio(page), offset, gfp_mask, NULL); } EXPORT_SYMBOL(add_to_page_cache_locked); -int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +int filemap_add_folio(struct address_space *mapping, struct folio *folio, + pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; - __SetPageLocked(page); - ret = __add_to_page_cache_locked(page, mapping, offset, - gfp_mask, &shadow); + __folio_set_locked(folio); + ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) - __ClearPageLocked(page); + __folio_clear_locked(folio); else { /* - * The page might have been evicted from cache only + * The folio might have been evicted from cache only * recently, in which case it should be activated like - * any other repeatedly accessed page. - * The exception is pages getting rewritten; evicting other + * any other repeatedly accessed folio. + * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - WARN_ON_ONCE(PageActive(page)); - if (!(gfp_mask & __GFP_WRITE) && shadow) - workingset_refault(page_folio(page), shadow); - lru_cache_add(page); + WARN_ON_ONCE(folio_test_active(folio)); + if (!(gfp & __GFP_WRITE) && shadow) + workingset_refault(folio, shadow); + folio_add_lru(folio); } return ret; } -EXPORT_SYMBOL_GPL(add_to_page_cache_lru); +EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 6de3cd78a4ae..6b19bc4ed6b0 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -108,3 +108,10 @@ void lru_cache_add(struct page *page) folio_add_lru(page_folio(page)); } EXPORT_SYMBOL(lru_cache_add); + +int add_to_page_cache_lru(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp) +{ + return filemap_add_folio(mapping, page_folio(page), index, gfp); +} +EXPORT_SYMBOL(add_to_page_cache_lru); -- cgit v1.2.3 From 3f0c6a07fee6a1c2618a2e12ffb8e9aa24384fde Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 8 Mar 2021 11:45:35 -0500 Subject: mm/filemap: Add filemap_get_folio filemap_get_folio() is a replacement for find_get_page(). Turn pagecache_get_page() into a wrapper around __filemap_get_folio(). Remove find_lock_head() as this use case is now covered by filemap_get_folio(). Reduces overall kernel size by 209 bytes. __filemap_get_folio() is 316 bytes shorter than pagecache_get_page() was, but the new pagecache_get_page() wrapper is 99 bytes. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 41 +++++++++++----------- mm/filemap.c | 92 +++++++++++++++++++++++-------------------------- mm/folio-compat.c | 12 +++++++ 3 files changed, 76 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index a10eb6dc3866..401a90336a2c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -302,8 +302,26 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_HEAD 0x00000080 #define FGP_ENTRY 0x00000100 -struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, - int fgp_flags, gfp_t cache_gfp_mask); +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp); +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp); + +/** + * filemap_get_folio - Find and get a folio. + * @mapping: The address_space to search. + * @index: The page index. + * + * Looks up the page cache entry at @mapping & @index. If a folio is + * present, it is returned with an increased refcount. + * + * Otherwise, %NULL is returned. + */ +static inline struct folio *filemap_get_folio(struct address_space *mapping, + pgoff_t index) +{ + return __filemap_get_folio(mapping, index, 0, 0); +} /** * find_get_page - find and get a page reference @@ -346,25 +364,6 @@ static inline struct page *find_lock_page(struct address_space *mapping, return pagecache_get_page(mapping, index, FGP_LOCK, 0); } -/** - * find_lock_head - Locate, pin and lock a pagecache page. - * @mapping: The address_space to search. - * @index: The page index. - * - * Looks up the page cache entry at @mapping & @index. If there is a - * page cache page, its head page is returned locked and with an increased - * refcount. - * - * Context: May sleep. - * Return: A struct page which is !PageTail, or %NULL if there is no page - * in the cache for this index. - */ -static inline struct page *find_lock_head(struct address_space *mapping, - pgoff_t index) -{ - return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0); -} - /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space diff --git a/mm/filemap.c b/mm/filemap.c index 5c99fd9a789d..de4cc1b9aa9b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1849,93 +1849,89 @@ out: } /** - * pagecache_get_page - Find and get a reference to a page. + * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. - * @fgp_flags: %FGP flags modify how the page is returned. - * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified. + * @fgp_flags: %FGP flags modify how the folio is returned. + * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * @fgp_flags can be zero or more of these flags: * - * * %FGP_ACCESSED - The page will be marked accessed. - * * %FGP_LOCK - The page is returned locked. - * * %FGP_HEAD - If the page is present and a THP, return the head page - * rather than the exact page specified by the index. + * * %FGP_ACCESSED - The folio will be marked accessed. + * * %FGP_LOCK - The folio is returned locked. * * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it - * instead of allocating a new page to replace it. + * instead of allocating a new folio to replace it. * * %FGP_CREAT - If no page is present then a new page is allocated using - * @gfp_mask and added to the page cache and the VM's LRU list. + * @gfp and added to the page cache and the VM's LRU list. * The page is returned locked and with an increased refcount. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * page is already in cache. If the page was allocated, unlock it before * returning so the caller can do the same dance. - * * %FGP_WRITE - The page will be written - * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask - * * %FGP_NOWAIT - Don't get blocked by page lock + * * %FGP_WRITE - The page will be written to by the caller. + * * %FGP_NOFS - __GFP_FS will get cleared in gfp. + * * %FGP_NOWAIT - Don't get blocked by page lock. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If there is a page cache page, it is returned with an increased refcount. * - * Return: The found page or %NULL otherwise. + * Return: The found folio or %NULL otherwise. */ -struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, - int fgp_flags, gfp_t gfp_mask) +struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp) { - struct page *page; + struct folio *folio; repeat: - page = mapping_get_entry(mapping, index); - if (xa_is_value(page)) { + folio = mapping_get_entry(mapping, index); + if (xa_is_value(folio)) { if (fgp_flags & FGP_ENTRY) - return page; - page = NULL; + return folio; + folio = NULL; } - if (!page) + if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return NULL; } } else { - lock_page(page); + folio_lock(folio); } /* Has the page been truncated? */ - if (unlikely(page->mapping != mapping)) { - unlock_page(page); - put_page(page); + if (unlikely(folio->mapping != mapping)) { + folio_unlock(folio); + folio_put(folio); goto repeat; } - VM_BUG_ON_PAGE(!thp_contains(page, index), page); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) - mark_page_accessed(page); + folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ - if (page_is_idle(page)) - clear_page_idle(page); + if (folio_test_idle(folio)) + folio_clear_idle(folio); } - if (!(fgp_flags & FGP_HEAD)) - page = find_subpage(page, index); no_page: - if (!page && (fgp_flags & FGP_CREAT)) { + if (!folio && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) - gfp_mask |= __GFP_WRITE; + gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) - gfp_mask &= ~__GFP_FS; + gfp &= ~__GFP_FS; - page = __page_cache_alloc(gfp_mask); - if (!page) + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return NULL; if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) @@ -1943,27 +1939,27 @@ no_page: /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) - __SetPageReferenced(page); + __folio_set_referenced(folio); - err = add_to_page_cache_lru(page, mapping, index, gfp_mask); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); - page = NULL; + folio_put(folio); + folio = NULL; if (err == -EEXIST) goto repeat; } /* - * add_to_page_cache_lru locks the page, and for mmap we expect - * an unlocked page. + * filemap_add_folio locks the page, and for mmap + * we expect an unlocked page. */ - if (page && (fgp_flags & FGP_FOR_MMAP)) - unlock_page(page); + if (folio && (fgp_flags & FGP_FOR_MMAP)) + folio_unlock(folio); } - return page; + return folio; } -EXPORT_SYMBOL(pagecache_get_page); +EXPORT_SYMBOL(__filemap_get_folio); static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 6b19bc4ed6b0..e833e680e944 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -115,3 +115,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, return filemap_add_folio(mapping, page_folio(page), index, gfp); } EXPORT_SYMBOL(add_to_page_cache_lru); + +struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, + int fgp_flags, gfp_t gfp) +{ + struct folio *folio; + + folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); + if ((fgp_flags & FGP_HEAD) || !folio || xa_is_value(folio)) + return &folio->page; + return folio_file_page(folio, index); +} +EXPORT_SYMBOL(pagecache_get_page); -- cgit v1.2.3 From b27652d935f41793c5e229a1e8b3a8bb3afe3cc1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 24 Dec 2020 12:55:56 -0500 Subject: mm/filemap: Add FGP_STABLE Allow filemap_get_folio() to wait for writeback to complete (if the filesystem wants that behaviour). This is the folio equivalent of grab_cache_page_write_begin(), which is moved into the folio-compat file as a reminder to migrate all the code using it. This paves the way for getting rid of AOP_FLAG_NOFS once grab_cache_page_write_begin() is removed. Kernel grows by 11 bytes. filemap_get_folio() grows by 33 bytes but grab_cache_page_write_begin() shrinks by 22 bytes to make up for it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells Acked-by: Vlastimil Babka --- include/linux/pagemap.h | 1 + mm/filemap.c | 25 +++---------------------- mm/folio-compat.c | 13 +++++++++++++ 3 files changed, 17 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 401a90336a2c..b68b053e581f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -301,6 +301,7 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping, #define FGP_FOR_MMAP 0x00000040 #define FGP_HEAD 0x00000080 #define FGP_ENTRY 0x00000100 +#define FGP_STABLE 0x00000200 struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp); diff --git a/mm/filemap.c b/mm/filemap.c index de4cc1b9aa9b..3e9feb5cc570 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1872,6 +1872,7 @@ out: * * %FGP_WRITE - The page will be written to by the caller. * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't get blocked by page lock. + * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. @@ -1922,6 +1923,8 @@ repeat: folio_clear_idle(folio); } + if (fgp_flags & FGP_STABLE) + folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { int err; @@ -3704,28 +3707,6 @@ out: } EXPORT_SYMBOL(generic_file_direct_write); -/* - * Find or create a page at the given pagecache position. Return the locked - * page. This function is specifically for buffered writes. - */ -struct page *grab_cache_page_write_begin(struct address_space *mapping, - pgoff_t index, unsigned flags) -{ - struct page *page; - int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT; - - if (flags & AOP_FLAG_NOFS) - fgp_flags |= FGP_NOFS; - - page = pagecache_get_page(mapping, index, fgp_flags, - mapping_gfp_mask(mapping)); - if (page) - wait_for_stable_page(page); - - return page; -} -EXPORT_SYMBOL(grab_cache_page_write_begin); - ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { diff --git a/mm/folio-compat.c b/mm/folio-compat.c index e833e680e944..5b6ae1da314e 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -116,6 +116,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, } EXPORT_SYMBOL(add_to_page_cache_lru); +noinline struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, int fgp_flags, gfp_t gfp) { @@ -127,3 +128,15 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, return folio_file_page(folio, index); } EXPORT_SYMBOL(pagecache_get_page); + +struct page *grab_cache_page_write_begin(struct address_space *mapping, + pgoff_t index, unsigned flags) +{ + unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + + if (flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + return pagecache_get_page(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); +} +EXPORT_SYMBOL(grab_cache_page_write_begin); -- cgit v1.2.3 From 121703c1c817b3c77f61002466d0bfca7e39f25d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 9 Mar 2021 13:48:03 -0500 Subject: mm/writeback: Add folio_write_one Transform write_one_page() into folio_write_one() and add a compatibility wrapper. Also move the declaration to pagemap.h as this is page cache functionality that doesn't need to be used by the rest of the kernel. Saves 58 bytes of kernel text. While folio_write_one() is 101 bytes smaller than write_one_page(), the inlined call to page_folio() expands each caller. There are fewer than ten callers so it doesn't seem worth putting a wrapper in the core. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: David Howells --- include/linux/mm.h | 4 ---- include/linux/pagemap.h | 5 +++++ mm/page-writeback.c | 30 +++++++++++++++--------------- 3 files changed, 20 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index efcb06fc6116..40ff114aaf9e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2788,10 +2788,6 @@ extern vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf); -/* mm/page-writeback.c */ -int __must_check write_one_page(struct page *page); -void task_dirty_inc(struct task_struct *tsk); - extern unsigned long stack_guard_gap; /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b68b053e581f..013cdc90f5fd 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -803,6 +803,11 @@ static inline void cancel_dirty_page(struct page *page) } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); +int __must_check folio_write_one(struct folio *folio); +static inline int __must_check write_one_page(struct page *page) +{ + return folio_write_one(page_folio(page)); +} int __set_page_dirty_nobuffers(struct page *page); int __set_page_dirty_no_writeback(struct page *page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index a0c35a9d8029..9c64490171e0 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2381,44 +2381,44 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc) } /** - * write_one_page - write out a single page and wait on I/O - * @page: the page to write + * folio_write_one - write out a single folio and wait on I/O. + * @folio: The folio to write. * - * The page must be locked by the caller and will be unlocked upon return. + * The folio must be locked by the caller and will be unlocked upon return. * * Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this * function returns. * * Return: %0 on success, negative error code otherwise */ -int write_one_page(struct page *page) +int folio_write_one(struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; int ret = 0; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, - .nr_to_write = 1, + .nr_to_write = folio_nr_pages(folio), }; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); - wait_on_page_writeback(page); + folio_wait_writeback(folio); - if (clear_page_dirty_for_io(page)) { - get_page(page); - ret = mapping->a_ops->writepage(page, &wbc); + if (folio_clear_dirty_for_io(folio)) { + folio_get(folio); + ret = mapping->a_ops->writepage(&folio->page, &wbc); if (ret == 0) - wait_on_page_writeback(page); - put_page(page); + folio_wait_writeback(folio); + folio_put(folio); } else { - unlock_page(page); + folio_unlock(folio); } if (!ret) ret = filemap_check_errors(mapping); return ret; } -EXPORT_SYMBOL(write_one_page); +EXPORT_SYMBOL(folio_write_one); /* * For address_spaces which do not use buffers nor write back. -- cgit v1.2.3 From f2efdb17928924c9c935c136dea764a081032006 Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Sat, 16 Oct 2021 10:49:06 +0200 Subject: u64_stats: Introduce u64_stats_set() Allow to directly set a u64_stats_t value which is used to provide an init function which sets it directly to zero intead of memset() the value. Add u64_stats_set() to the u64_stats API. [bigeasy: commit message. ] Signed-off-by: Ahmed S. Darwish Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e81856c0ba13..e8ec116c916b 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -83,6 +83,11 @@ static inline u64 u64_stats_read(const u64_stats_t *p) return local64_read(&p->v); } +static inline void u64_stats_set(u64_stats_t *p, u64 val) +{ + local64_set(&p->v, val); +} + static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { local64_add(val, &p->v); @@ -104,6 +109,11 @@ static inline u64 u64_stats_read(const u64_stats_t *p) return p->v; } +static inline void u64_stats_set(u64_stats_t *p, u64 val) +{ + p->v = val; +} + static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { p->v += val; -- cgit v1.2.3 From 29cbcd85828372333aa87542c51f2b2b0fd4380c Mon Sep 17 00:00:00 2001 From: "Ahmed S. Darwish" Date: Sat, 16 Oct 2021 10:49:10 +0200 Subject: net: sched: Remove Qdisc::running sequence counter The Qdisc::running sequence counter has two uses: 1. Reliably reading qdisc's tc statistics while the qdisc is running (a seqcount read/retry loop at gnet_stats_add_basic()). 2. As a flag, indicating whether the qdisc in question is running (without any retry loops). For the first usage, the Qdisc::running sequence counter write section, qdisc_run_begin() => qdisc_run_end(), covers a much wider area than what is actually needed: the raw qdisc's bstats update. A u64_stats sync point was thus introduced (in previous commits) inside the bstats structure itself. A local u64_stats write section is then started and stopped for the bstats updates. Use that u64_stats sync point mechanism for the bstats read/retry loop at gnet_stats_add_basic(). For the second qdisc->running usage, a __QDISC_STATE_RUNNING bit flag, accessed with atomic bitops, is sufficient. Using a bit flag instead of a sequence counter at qdisc_run_begin/end() and qdisc_is_running() leads to the SMP barriers implicitly added through raw_read_seqcount() and write_seqcount_begin/end() getting removed. All call sites have been surveyed though, and no required ordering was identified. Now that the qdisc->running sequence counter is no longer used, remove it. Note, using u64_stats implies no sequence counter protection for 64-bit architectures. This can lead to the qdisc tc statistics "packets" vs. "bytes" values getting out of sync on rare occasions. The individual values will still be valid. Signed-off-by: Ahmed S. Darwish Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ---- include/net/gen_stats.h | 19 ++++++++---------- include/net/sch_generic.h | 33 +++++++++++++------------------ net/core/gen_estimator.c | 16 +++++++++------ net/core/gen_stats.c | 50 ++++++++++++++++++++++++++--------------------- net/sched/act_api.c | 9 +++++---- net/sched/act_police.c | 2 +- net/sched/sch_api.c | 16 +++------------ net/sched/sch_atm.c | 3 +-- net/sched/sch_cbq.c | 9 +++------ net/sched/sch_drr.c | 10 +++------- net/sched/sch_ets.c | 3 +-- net/sched/sch_generic.c | 10 ++-------- net/sched/sch_hfsc.c | 8 +++----- net/sched/sch_htb.c | 7 +++---- net/sched/sch_mq.c | 7 +++---- net/sched/sch_mqprio.c | 14 ++++++------- net/sched/sch_multiq.c | 3 +-- net/sched/sch_prio.c | 4 ++-- net/sched/sch_qfq.c | 7 +++---- net/sched/sch_taprio.c | 2 +- 21 files changed, 102 insertions(+), 134 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 173984414f38..f9cd6fea213f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1916,7 +1916,6 @@ enum netdev_ml_priv_type { * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock - * @qdisc_running_key: lockdep class annotating Qdisc->running seqcount * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the @@ -2250,7 +2249,6 @@ struct net_device { struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; - struct lock_class_key *qdisc_running_key; bool proto_down; unsigned wol_enabled:1; unsigned threaded:1; @@ -2360,13 +2358,11 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, #define netdev_lockdep_set_classes(dev) \ { \ static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_running_key; \ static struct lock_class_key qdisc_xmit_lock_key; \ static struct lock_class_key dev_addr_list_lock_key; \ unsigned int i; \ \ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - (dev)->qdisc_running_key = &qdisc_running_key; \ lockdep_set_class(&(dev)->addr_list_lock, \ &dev_addr_list_lock_key); \ for (i = 0; i < (dev)->num_tx_queues; i++) \ diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h index 52b87588f467..7aa2b8e1fb29 100644 --- a/include/net/gen_stats.h +++ b/include/net/gen_stats.h @@ -46,18 +46,15 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type, spinlock_t *lock, struct gnet_dump *d, int padattr); -int gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, +int gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b); -void gnet_stats_add_basic(const seqcount_t *running, - struct gnet_stats_basic_sync *bstats, + struct gnet_stats_basic_sync *b, bool running); +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b); -int gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, + struct gnet_stats_basic_sync *b, bool running); +int gnet_stats_copy_basic_hw(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b); + struct gnet_stats_basic_sync *b, bool running); int gnet_stats_copy_rate_est(struct gnet_dump *d, struct net_rate_estimator __rcu **ptr); int gnet_stats_copy_queue(struct gnet_dump *d, @@ -74,13 +71,13 @@ int gen_new_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **ptr, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt); + bool running, struct nlattr *opt); bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, struct gnet_stats_rate_est64 *sample); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 7882e3aa6448..baad2ab4d971 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -38,6 +38,10 @@ enum qdisc_state_t { __QDISC_STATE_DEACTIVATED, __QDISC_STATE_MISSED, __QDISC_STATE_DRAINING, + /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. + * Use qdisc_run_begin/end() or qdisc_is_running() instead. + */ + __QDISC_STATE_RUNNING, }; #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) @@ -108,7 +112,6 @@ struct Qdisc { struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; - seqcount_t running; struct gnet_stats_queue qstats; unsigned long state; struct Qdisc *next_sched; @@ -143,11 +146,15 @@ static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc) return NULL; } +/* For !TCQ_F_NOLOCK qdisc: callers must either call this within a qdisc + * root_lock section, or provide their own memory barriers -- ordering + * against qdisc_run_begin/end() atomic bit operations. + */ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); - return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; + return test_bit(__QDISC_STATE_RUNNING, &qdisc->state); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) @@ -167,6 +174,9 @@ static inline bool qdisc_is_empty(const struct Qdisc *qdisc) return !READ_ONCE(qdisc->q.qlen); } +/* For !TCQ_F_NOLOCK qdisc, qdisc_run_begin/end() must be invoked with + * the qdisc root lock acquired. + */ static inline bool qdisc_run_begin(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) { @@ -206,15 +216,8 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) * after it releases the lock at the end of qdisc_run_end(). */ return spin_trylock(&qdisc->seqlock); - } else if (qdisc_is_running(qdisc)) { - return false; } - /* Variant of write_seqcount_begin() telling lockdep a trylock - * was attempted. - */ - raw_write_seqcount_begin(&qdisc->running); - seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); - return true; + return test_and_set_bit(__QDISC_STATE_RUNNING, &qdisc->state); } static inline void qdisc_run_end(struct Qdisc *qdisc) @@ -226,7 +229,7 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) &qdisc->state))) __netif_schedule(qdisc); } else { - write_seqcount_end(&qdisc->running); + clear_bit(__QDISC_STATE_RUNNING, &qdisc->state); } } @@ -592,14 +595,6 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc) return qdisc_lock(root); } -static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) -{ - struct Qdisc *root = qdisc_root_sleeping(qdisc); - - ASSERT_RTNL(); - return &root->running; -} - static inline struct net_device *qdisc_dev(const struct Qdisc *qdisc) { return qdisc->dev_queue->dev; diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index a73ad0bf324c..4fcbdd71c59f 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -42,7 +42,7 @@ struct net_rate_estimator { struct gnet_stats_basic_sync *bstats; spinlock_t *stats_lock; - seqcount_t *running; + bool running; struct gnet_stats_basic_sync __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ @@ -66,7 +66,7 @@ static void est_fetch_counters(struct net_rate_estimator *e, if (e->stats_lock) spin_lock(e->stats_lock); - gnet_stats_add_basic(e->running, b, e->cpu_bstats, e->bstats); + gnet_stats_add_basic(b, e->cpu_bstats, e->bstats, e->running); if (e->stats_lock) spin_unlock(e->stats_lock); @@ -113,7 +113,9 @@ static void est_timer(struct timer_list *t) * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path - * @running: qdisc running seqcount + * @running: true if @bstats represents a running qdisc, thus @bstats' + * internal values might change during basic reads. Only used + * if @bstats_cpu is NULL * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est @@ -129,7 +131,7 @@ int gen_new_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, + bool running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); @@ -218,7 +220,9 @@ EXPORT_SYMBOL(gen_kill_estimator); * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path - * @running: qdisc running seqcount (might be NULL) + * @running: true if @bstats represents a running qdisc, thus @bstats' + * internal values might change during basic reads. Only used + * if @cpu_bstats is NULL * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling @@ -230,7 +234,7 @@ int gen_replace_estimator(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, - seqcount_t *running, struct nlattr *opt) + bool running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 5f57f761def6..5516ea0d5da0 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -146,42 +146,42 @@ static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_sync *bstats, _bstats_update(bstats, t_bytes, t_packets); } -void gnet_stats_add_basic(const seqcount_t *running, - struct gnet_stats_basic_sync *bstats, +void gnet_stats_add_basic(struct gnet_stats_basic_sync *bstats, struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b) + struct gnet_stats_basic_sync *b, bool running) { - unsigned int seq; + unsigned int start; u64 bytes = 0; u64 packets = 0; + WARN_ON_ONCE((cpu || running) && !in_task()); + if (cpu) { gnet_stats_add_basic_cpu(bstats, cpu); return; } do { if (running) - seq = read_seqcount_begin(running); + start = u64_stats_fetch_begin_irq(&b->syncp); bytes = u64_stats_read(&b->bytes); packets = u64_stats_read(&b->packets); - } while (running && read_seqcount_retry(running, seq)); + } while (running && u64_stats_fetch_retry_irq(&b->syncp, start)); _bstats_update(bstats, bytes, packets); } EXPORT_SYMBOL(gnet_stats_add_basic); static int -___gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, +___gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, struct gnet_stats_basic_sync *b, - int type) + int type, bool running) { struct gnet_stats_basic_sync bstats; u64 bstats_bytes, bstats_packets; gnet_stats_basic_sync_init(&bstats); - gnet_stats_add_basic(running, &bstats, cpu, b); + gnet_stats_add_basic(&bstats, cpu, b, running); bstats_bytes = u64_stats_read(&bstats.bytes); bstats_packets = u64_stats_read(&bstats.packets); @@ -210,10 +210,14 @@ ___gnet_stats_copy_basic(const seqcount_t *running, /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV - * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics + * @running: true if @b represents a running qdisc, thus @b's + * internal values might change during basic reads. + * Only used if @cpu is NULL + * + * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). @@ -222,22 +226,25 @@ ___gnet_stats_copy_basic(const seqcount_t *running, * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic(const seqcount_t *running, - struct gnet_dump *d, +gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b) + struct gnet_stats_basic_sync *b, + bool running) { - return ___gnet_stats_copy_basic(running, d, cpu, b, - TCA_STATS_BASIC); + return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC, running); } EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_basic_hw - copy basic hw statistics into statistic TLV - * @running: seqcount_t pointer * @d: dumping handle * @cpu: copy statistic per cpu * @b: basic statistics + * @running: true if @b represents a running qdisc, thus @b's + * internal values might change during basic reads. + * Only used if @cpu is NULL + * + * Context: task; must not be run from IRQ or BH contexts * * Appends the basic statistics to the top level TLV created by * gnet_stats_start_copy(). @@ -246,13 +253,12 @@ EXPORT_SYMBOL(gnet_stats_copy_basic); * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_basic_hw(const seqcount_t *running, - struct gnet_dump *d, +gnet_stats_copy_basic_hw(struct gnet_dump *d, struct gnet_stats_basic_sync __percpu *cpu, - struct gnet_stats_basic_sync *b) + struct gnet_stats_basic_sync *b, + bool running) { - return ___gnet_stats_copy_basic(running, d, cpu, b, - TCA_STATS_BASIC_HW); + return ___gnet_stats_copy_basic(d, cpu, b, TCA_STATS_BASIC_HW, running); } EXPORT_SYMBOL(gnet_stats_copy_basic_hw); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 585829ffa0c4..3258da3d5bed 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -501,7 +501,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, if (est) { err = gen_new_estimator(&p->tcfa_bstats, p->cpu_bstats, &p->tcfa_rate_est, - &p->tcfa_lock, NULL, est); + &p->tcfa_lock, false, est); if (err) goto err4; } @@ -1173,9 +1173,10 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p, if (err < 0) goto errout; - if (gnet_stats_copy_basic(NULL, &d, p->cpu_bstats, &p->tcfa_bstats) < 0 || - gnet_stats_copy_basic_hw(NULL, &d, p->cpu_bstats_hw, - &p->tcfa_bstats_hw) < 0 || + if (gnet_stats_copy_basic(&d, p->cpu_bstats, + &p->tcfa_bstats, false) < 0 || + gnet_stats_copy_basic_hw(&d, p->cpu_bstats_hw, + &p->tcfa_bstats_hw, false) < 0 || gnet_stats_copy_rate_est(&d, &p->tcfa_rate_est) < 0 || gnet_stats_copy_queue(&d, p->cpu_qstats, &p->tcfa_qstats, diff --git a/net/sched/act_police.c b/net/sched/act_police.c index c9383805222d..9e77ba8401e5 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -125,7 +125,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, - NULL, est); + false, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 70f006cbf212..efcd0b5e9a32 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -943,8 +943,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, cpu_qstats = q->cpu_qstats; } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(q), - &d, cpu_bstats, &q->bstats) < 0 || + if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats, true) < 0 || gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; @@ -1265,26 +1264,17 @@ static struct Qdisc *qdisc_create(struct net_device *dev, rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { - seqcount_t *running; - err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); goto err_out4; } - if (sch->parent != TC_H_ROOT && - !(sch->flags & TCQ_F_INGRESS) && - (!p || !(p->flags & TCQ_F_MQROOT))) - running = qdisc_root_sleeping_running(sch); - else - running = &sch->running; - err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, - running, + true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); @@ -1360,7 +1350,7 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, sch->cpu_bstats, &sch->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); } out: diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index fbfe4ce9497b..4c8e994cf0a5 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -653,8 +653,7 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, { struct atm_flow_data *flow = (struct atm_flow_data *)arg; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &flow->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &flow->bstats, true) < 0 || gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) return -1; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index f0b1282fae11..02d9f0dfe356 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1383,8 +1383,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (cl->undertime != PSCHED_PASTPERFECT) cl->xstats.undertime = cl->undertime - q->now; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; @@ -1518,7 +1517,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); @@ -1619,9 +1618,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); tcf_block_put(cl->block); diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c index 7243617a3595..18e4f7a0b291 100644 --- a/net/sched/sch_drr.c +++ b/net/sched/sch_drr.c @@ -85,8 +85,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); @@ -119,9 +118,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to replace estimator"); qdisc_put(cl->qdisc); @@ -268,8 +265,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg, if (qlen) xstats.deficit = cl->deficit; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0) return -1; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index af56d155e7fc..0eae9ff5edf6 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -325,8 +325,7 @@ static int ets_class_dump_stats(struct Qdisc *sch, unsigned long arg, struct ets_class *cl = ets_class_from_arg(sch, arg); struct Qdisc *cl_q = cl->qdisc; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 989186e7f1a0..b0ff0dff2773 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -304,8 +304,8 @@ trace: /* * Transmit possibly several skbs, and handle the return status as - * required. Owning running seqcount bit guarantees that - * only one CPU can execute this function. + * required. Owning qdisc running bit guarantees that only one CPU + * can execute this function. * * Returns to the caller: * false - hardware queue frozen backoff @@ -606,7 +606,6 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, - .running = SEQCNT_ZERO(noop_qdisc.running), .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, @@ -867,7 +866,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; -static struct lock_class_key qdisc_running_key; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, @@ -917,10 +915,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - seqcount_init(&sch->running); - lockdep_set_class(&sch->running, - dev->qdisc_running_key ?: &qdisc_running_key); - sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 181c2905ff98..d3979a6000e7 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -965,7 +965,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -1033,9 +1033,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (tca[TCA_RATE]) { err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); + NULL, true, tca[TCA_RATE]); if (err) { tcf_block_put(cl->block); kfree(cl); @@ -1328,7 +1326,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.work = cl->cl_total; xstats.rtwork = cl->cl_cumul; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) return -1; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index adceb9e210f6..cf1d45db4e84 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1368,8 +1368,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) } } - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || gnet_stats_copy_queue(d, NULL, &qs, qlen) < 0) return -1; @@ -1865,7 +1864,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE] ? : &est.nla); if (err) goto err_block_put; @@ -1991,7 +1990,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index cedd0b3ef9cf..83d2e54bf303 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -144,8 +144,8 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - gnet_stats_add_basic(NULL, &sch->bstats, qdisc->cpu_bstats, - &qdisc->bstats); + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats); sch->q.qlen += qdisc_qlen(qdisc); @@ -231,8 +231,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, - &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, sch->cpu_bstats, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 3f7f756f92ca..b29f3453c6ea 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -402,8 +402,8 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping; spin_lock_bh(qdisc_lock(qdisc)); - gnet_stats_add_basic(NULL, &sch->bstats, qdisc->cpu_bstats, - &qdisc->bstats); + gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats); sch->q.qlen += qdisc_qlen(qdisc); @@ -519,8 +519,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, spin_lock_bh(qdisc_lock(qdisc)); - gnet_stats_add_basic(NULL, &bstats, qdisc->cpu_bstats, - &qdisc->bstats); + gnet_stats_add_basic(&bstats, qdisc->cpu_bstats, + &qdisc->bstats, false); gnet_stats_add_queue(&qstats, qdisc->cpu_qstats, &qdisc->qstats); sch->q.qlen += qdisc_qlen(qdisc); @@ -532,15 +532,15 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, /* Reclaim root sleeping lock before completing stats */ if (d->lock) spin_lock_bh(d->lock); - if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &bstats, false) < 0 || gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0) return -1; } else { struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, - sch->cpu_bstats, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, sch->cpu_bstats, + &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e282e7382117..cd8ab90c4765 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -338,8 +338,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 03fdf31ccb6a..3b8d7197c06b 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -361,8 +361,8 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct Qdisc *cl_q; cl_q = q->queues[cl - 1]; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || + if (gnet_stats_copy_basic(d, cl_q->cpu_bstats, + &cl_q->bstats, true) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index a35200f591a2..0b7f9ba28deb 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -451,7 +451,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) return err; @@ -478,7 +478,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, NULL, - qdisc_root_sleeping_running(sch), + true, tca[TCA_RATE]); if (err) goto destroy_class; @@ -640,8 +640,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg, xstats.weight = cl->agg->class_weight; xstats.lmax = cl->agg->lmax; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 || gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || qdisc_qstats_copy(d, cl->qdisc) < 0) return -1; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index b9fd18d98646..9ab068fa2672 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1977,7 +1977,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(d, NULL, &sch->bstats, true) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; -- cgit v1.2.3 From 82a8daaecfd9382e9450a05f86be8a274cf69a27 Mon Sep 17 00:00:00 2001 From: Marc Bonnici Date: Fri, 15 Oct 2021 17:57:42 +0100 Subject: firmware: arm_ffa: Add support for MEM_LEND As part of the FF-A spec, an endpoint is allowed to transfer access of, or lend, a memory region to one or more borrowers. Extend the existing memory sharing implementation to support FF-A MEM_LEND functionality and expose this to other kernel drivers. Note that upon a successful MEM_LEND request the caller must ensure that the memory region specified is not accessed until a successful MEM_RECALIM call has been made. On systems with a hypervisor present this will been enforced, however on systems without a hypervisor the responsibility falls to the calling kernel driver to prevent access. Link: https://lore.kernel.org/r/20211015165742.2513065-1-marc.bonnici@arm.com Reviewed-by: Jens Wiklander Signed-off-by: Marc Bonnici Signed-off-by: Sudeep Holla --- drivers/firmware/arm_ffa/driver.c | 17 +++++++++++++++++ include/linux/arm_ffa.h | 2 ++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index 6e0c883ab708..12f4c87c4555 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -613,6 +613,22 @@ ffa_memory_share(struct ffa_device *dev, struct ffa_mem_ops_args *args) return ffa_memory_ops(FFA_FN_NATIVE(MEM_SHARE), args); } +static int +ffa_memory_lend(struct ffa_device *dev, struct ffa_mem_ops_args *args) +{ + /* Note that upon a successful MEM_LEND request the caller + * must ensure that the memory region specified is not accessed + * until a successful MEM_RECALIM call has been made. + * On systems with a hypervisor present this will been enforced, + * however on systems without a hypervisor the responsibility + * falls to the calling kernel driver to prevent access. + */ + if (dev->mode_32bit) + return ffa_memory_ops(FFA_MEM_LEND, args); + + return ffa_memory_ops(FFA_FN_NATIVE(MEM_LEND), args); +} + static const struct ffa_dev_ops ffa_ops = { .api_version_get = ffa_api_version_get, .partition_info_get = ffa_partition_info_get, @@ -620,6 +636,7 @@ static const struct ffa_dev_ops ffa_ops = { .sync_send_receive = ffa_sync_send_receive, .memory_reclaim = ffa_memory_reclaim, .memory_share = ffa_memory_share, + .memory_lend = ffa_memory_lend, }; const struct ffa_dev_ops *ffa_dev_ops_get(struct ffa_device *dev) diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index 505c679b6a9b..85651e41ded8 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -262,6 +262,8 @@ struct ffa_dev_ops { int (*memory_reclaim)(u64 g_handle, u32 flags); int (*memory_share)(struct ffa_device *dev, struct ffa_mem_ops_args *args); + int (*memory_lend)(struct ffa_device *dev, + struct ffa_mem_ops_args *args); }; #endif /* _LINUX_ARM_FFA_H */ -- cgit v1.2.3 From 348332e000697b4ca82ef96719e02876434b8346 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:12 +0200 Subject: mm: don't include in blk-cgroup.h pulls in blkdev.h and thus pretty much all the block headers. Break this dependency chain by turning wbc_blkcg_css into a macro and dropping the blk-cgroup.h include. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-2-hch@lst.de Signed-off-by: Jens Axboe --- drivers/gpu/drm/i915/i915_utils.h | 1 + fs/btrfs/inode.c | 1 + fs/quota/quota.c | 1 + include/linux/writeback.h | 14 +++++--------- lib/random32.c | 1 + 5 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index 5259edacde38..066a9118c374 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -30,6 +30,7 @@ #include #include #include +#include struct drm_i915_private; struct timer_list; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 487533c35ddb..4a9077c52444 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 2bcc9a6f1bfc..052f143e2e0e 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/writeback.h b/include/linux/writeback.h index d1f65adf6a26..8eb165760752 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -11,7 +11,6 @@ #include #include #include -#include struct bio; @@ -109,15 +108,12 @@ static inline int wbc_to_write_flags(struct writeback_control *wbc) return flags; } -static inline struct cgroup_subsys_state * -wbc_blkcg_css(struct writeback_control *wbc) -{ #ifdef CONFIG_CGROUP_WRITEBACK - if (wbc->wb) - return wbc->wb->blkcg_css; -#endif - return blkcg_root_css; -} +#define wbc_blkcg_css(wbc) \ + ((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css) +#else +#define wbc_blkcg_css(wbc) (blkcg_root_css) +#endif /* CONFIG_CGROUP_WRITEBACK */ /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to diff --git a/lib/random32.c b/lib/random32.c index 4d0e05e471d7..a57a0e18819d 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3 From e41d12f539f7c8bac9b0897031fee6cc9158a6be Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:13 +0200 Subject: mm: don't include in There is no need to pull blk-cgroup.h and thus blkdev.h in here, so break the include chain. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-3-hch@lst.de Signed-off-by: Jens Axboe --- arch/powerpc/platforms/cell/spufs/inode.c | 1 + block/blk-iolatency.c | 1 + block/blk-mq.c | 1 + block/bounce.c | 1 + drivers/md/dm-ima.c | 1 + fs/btrfs/compression.c | 1 + fs/btrfs/ctree.c | 1 + fs/f2fs/compress.c | 1 + fs/orangefs/super.c | 1 + fs/ramfs/inode.c | 1 + include/linux/backing-dev.h | 3 ++- mm/backing-dev.c | 3 ++- mm/swapfile.c | 2 +- 13 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index bed05b644c2c..cb25acccd746 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index c0545f9da549..6593c7123b97 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -74,6 +74,7 @@ #include #include #include +#include #include "blk-rq-qos.h" #include "blk-stat.h" #include "blk.h" diff --git a/block/blk-mq.c b/block/blk-mq.c index bc026372de43..0fefe00cebd4 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/block/bounce.c b/block/bounce.c index 05fc7148489d..7af1a72835b9 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/md/dm-ima.c b/drivers/md/dm-ima.c index 2c5edfbd7711..957999998d70 100644 --- a/drivers/md/dm-ima.c +++ b/drivers/md/dm-ima.c @@ -12,6 +12,7 @@ #include "dm-ima.h" #include +#include #include #include #include diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 7869ad12bc6e..ddc4f5436cc9 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 84627cbd5b5b..66290b214f2b 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "ctree.h" #include "disk-io.h" #include "transaction.h" diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index c1bf9ad4c220..20a083dc9042 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c index 2f2e430461b2..8bb0a53a658b 100644 --- a/fs/orangefs/super.c +++ b/fs/orangefs/super.c @@ -11,6 +11,7 @@ #include #include +#include /* a cache for orangefs-inode objects (i.e. orangefs inode private data) */ static struct kmem_cache *orangefs_inode_cache; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index 65e7e56005b8..e2302342a67f 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -38,6 +38,7 @@ #include #include #include +#include #include "internal.h" struct ramfs_mount_opts { diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..843bf4be675f 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -15,10 +15,11 @@ #include #include #include -#include #include #include +struct blkcg; + static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 4a9d4e27d0d9..5245744437dc 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -2,8 +2,9 @@ #include #include -#include #include +#include +#include #include #include #include diff --git a/mm/swapfile.c b/mm/swapfile.c index 22d10f713848..30db362749c0 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.2.3 From ccdf774189b6466457ca9c7de1fe9ed18547d249 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:14 +0200 Subject: mm: don't include in Move inode_to_bdi out of line to avoid having to include blkdev.h. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-4-hch@lst.de Signed-off-by: Jens Axboe --- drivers/mtd/mtdsuper.c | 1 + fs/ntfs/file.c | 1 + fs/ntfs3/file.c | 1 + fs/orangefs/inode.c | 2 +- include/linux/backing-dev.h | 16 +--------------- mm/backing-dev.c | 16 ++++++++++++++++ 6 files changed, 21 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c index 38b6aa849c63..5ff001140ef4 100644 --- a/drivers/mtd/mtdsuper.c +++ b/drivers/mtd/mtdsuper.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include "mtdcore.h" diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index ab4f3362466d..373dbb627657 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -5,6 +5,7 @@ * Copyright (c) 2001-2015 Anton Altaparmakov and Tuxera Inc. */ +#include #include #include #include diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 43b1451bff53..a3cd3c3f091e 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index c1bb4c4b5d67..e5e3e500ed46 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -10,7 +10,7 @@ * Linux VFS inode operations. */ -#include +#include #include #include "protocol.h" #include "orangefs-kernel.h" diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 843bf4be675f..4ac7ce096013 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -134,20 +133,7 @@ static inline bool writeback_in_progress(struct bdi_writeback *wb) return test_bit(WB_writeback_running, &wb->state); } -static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) -{ - struct super_block *sb; - - if (!inode) - return &noop_backing_dev_info; - - sb = inode->i_sb; -#ifdef CONFIG_BLOCK - if (sb_is_blkdev_sb(sb)) - return I_BDEV(inode)->bd_disk->bdi; -#endif - return sb->s_bdi; -} +struct backing_dev_info *inode_to_bdi(struct inode *inode); static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5245744437dc..c878d995af06 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -978,6 +978,22 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); +struct backing_dev_info *inode_to_bdi(struct inode *inode) +{ + struct super_block *sb; + + if (!inode) + return &noop_backing_dev_info; + + sb = inode->i_sb; +#ifdef CONFIG_BLOCK + if (sb_is_blkdev_sb(sb)) + return I_BDEV(inode)->bd_disk->bdi; +#endif + return sb->s_bdi; +} +EXPORT_SYMBOL(inode_to_bdi); + const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) -- cgit v1.2.3 From 1d9433cdd04adf7cfd5e3ef81f5acb29d80aae9b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:19 +0200 Subject: block: remove the unused rq_end_sector macro Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-9-hch@lst.de Signed-off-by: Jens Axboe --- drivers/md/dm-rq.c | 1 - include/linux/elevator.h | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index a896dea9750e..579ab6183d4d 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -7,7 +7,6 @@ #include "dm-core.h" #include "dm-rq.h" -#include /* for rq_end_sector() */ #include #define DM_MSG_PREFIX "core-rq" diff --git a/include/linux/elevator.h b/include/linux/elevator.h index ef9ceead3db1..80633f3b600c 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -162,7 +162,6 @@ extern struct request *elv_rb_find(struct rb_root *, sector_t); #define ELEVATOR_INSERT_FLUSH 5 #define ELEVATOR_INSERT_SORT_MERGE 6 -#define rq_end_sector(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq)) #define rb_entry_rq(node) rb_entry((node), struct request, rb_node) #define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) -- cgit v1.2.3 From 90138237a56282f99d71130ab7c68903a2eba5a7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:20 +0200 Subject: block: remove the unused blk_queue_state enum Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-10-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 12b9dbcc980e..9e367509bea1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -262,11 +262,6 @@ enum blk_eh_timer_return { BLK_EH_RESET_TIMER, /* reset timer and try again */ }; -enum blk_queue_state { - Queue_down, - Queue_up, -}; - #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ -- cgit v1.2.3 From 713e4e11088875bf7aee3df81b167c8b2f6c5d65 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:21 +0200 Subject: block: remove the cmd_size field from struct request_queue Entirely unused. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-11-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9e367509bea1..6737e484280d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -544,8 +544,6 @@ struct request_queue { bool mq_sysfs_init_done; - size_t cmd_size; - #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -- cgit v1.2.3 From 9778ac77c2027827ffdbb33d3e936b3a0ae9f0f9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:22 +0200 Subject: block: remove the struct blk_queue_ctx forward declaration This type doesn't exist at all, so no need to forward declare it. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-12-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6737e484280d..4bcbb1ae2d66 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -253,8 +253,6 @@ static inline unsigned short req_get_ioprio(struct request *req) #include -struct blk_queue_ctx; - struct bio_vec; enum blk_eh_timer_return { -- cgit v1.2.3 From 2e9bc3465ac54d282b855b073409c2c3a7d1ae00 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:23 +0200 Subject: block: move elevator.h to block/ Except for the features passed to blk_queue_required_elevator_features, elevator.h is only needed internally to the block layer. Move the ELEVATOR_F_* definitions to blkdev.h, and the move elevator.h to block/, dropping all the spurious includes outside of that. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-13-hch@lst.de Signed-off-by: Jens Axboe --- block/bfq-cgroup.c | 2 +- block/bfq-iosched.c | 2 +- block/blk-mq-sched.h | 1 + block/blk-mq-tag.h | 2 + block/blk.h | 2 + block/elevator.c | 2 +- block/elevator.h | 166 +++++++++++++++++++++++++++++++++++++++++++ block/kyber-iosched.c | 2 +- block/mq-deadline.c | 2 +- drivers/block/amiflop.c | 1 - drivers/scsi/lpfc/lpfc.h | 1 + include/linux/blkdev.h | 11 ++- include/linux/elevator.h | 180 ----------------------------------------------- init/main.c | 1 - 14 files changed, 186 insertions(+), 189 deletions(-) create mode 100644 block/elevator.h delete mode 100644 include/linux/elevator.h (limited to 'include/linux') diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 85b8e1c3a762..882ec4bc51ad 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -6,13 +6,13 @@ #include #include #include -#include #include #include #include #include #include +#include "elevator.h" #include "bfq-iosched.h" #ifdef CONFIG_BFQ_CGROUP_DEBUG diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 480e1a134859..b5ef23f63d51 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -117,7 +117,6 @@ #include #include #include -#include #include #include #include @@ -127,6 +126,7 @@ #include +#include "elevator.h" #include "blk.h" #include "blk-mq.h" #include "blk-mq-tag.h" diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 5246ae040704..5181487db792 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -2,6 +2,7 @@ #ifndef BLK_MQ_SCHED_H #define BLK_MQ_SCHED_H +#include "elevator.h" #include "blk-mq.h" #include "blk-mq-tag.h" diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 8ed55af08427..f0a0ee758a55 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -2,6 +2,8 @@ #ifndef INT_BLK_MQ_TAG_H #define INT_BLK_MQ_TAG_H +struct blk_mq_alloc_data; + /* * Tag address space map. */ diff --git a/block/blk.h b/block/blk.h index 6c3c00a8fe19..f24569980905 100644 --- a/block/blk.h +++ b/block/blk.h @@ -12,6 +12,8 @@ #include "blk-mq.h" #include "blk-mq-sched.h" +struct elevator_type; + /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) diff --git a/block/elevator.c b/block/elevator.c index ff45d8388f48..57be09cd7f6d 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include @@ -40,6 +39,7 @@ #include +#include "elevator.h" #include "blk.h" #include "blk-mq-sched.h" #include "blk-pm.h" diff --git a/block/elevator.h b/block/elevator.h new file mode 100644 index 000000000000..16cd8bdedb7e --- /dev/null +++ b/block/elevator.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ELEVATOR_H +#define _ELEVATOR_H + +#include +#include + +struct io_cq; +struct elevator_type; +struct blk_mq_debugfs_attr; + +/* + * Return values from elevator merger + */ +enum elv_merge { + ELEVATOR_NO_MERGE = 0, + ELEVATOR_FRONT_MERGE = 1, + ELEVATOR_BACK_MERGE = 2, + ELEVATOR_DISCARD_MERGE = 3, +}; + +struct blk_mq_alloc_data; +struct blk_mq_hw_ctx; + +struct elevator_mq_ops { + int (*init_sched)(struct request_queue *, struct elevator_type *); + void (*exit_sched)(struct elevator_queue *); + int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); + + bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); + bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int); + int (*request_merge)(struct request_queue *q, struct request **, struct bio *); + void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); + void (*requests_merged)(struct request_queue *, struct request *, struct request *); + void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); + void (*prepare_request)(struct request *); + void (*finish_request)(struct request *); + void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); + struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); + bool (*has_work)(struct blk_mq_hw_ctx *); + void (*completed_request)(struct request *, u64); + void (*requeue_request)(struct request *); + struct request *(*former_request)(struct request_queue *, struct request *); + struct request *(*next_request)(struct request_queue *, struct request *); + void (*init_icq)(struct io_cq *); + void (*exit_icq)(struct io_cq *); +}; + +#define ELV_NAME_MAX (16) + +struct elv_fs_entry { + struct attribute attr; + ssize_t (*show)(struct elevator_queue *, char *); + ssize_t (*store)(struct elevator_queue *, const char *, size_t); +}; + +/* + * identifies an elevator type, such as AS or deadline + */ +struct elevator_type +{ + /* managed by elevator core */ + struct kmem_cache *icq_cache; + + /* fields provided by elevator implementation */ + struct elevator_mq_ops ops; + + size_t icq_size; /* see iocontext.h */ + size_t icq_align; /* ditto */ + struct elv_fs_entry *elevator_attrs; + const char *elevator_name; + const char *elevator_alias; + const unsigned int elevator_features; + struct module *elevator_owner; +#ifdef CONFIG_BLK_DEBUG_FS + const struct blk_mq_debugfs_attr *queue_debugfs_attrs; + const struct blk_mq_debugfs_attr *hctx_debugfs_attrs; +#endif + + /* managed by elevator core */ + char icq_cache_name[ELV_NAME_MAX + 6]; /* elvname + "_io_cq" */ + struct list_head list; +}; + +#define ELV_HASH_BITS 6 + +void elv_rqhash_del(struct request_queue *q, struct request *rq); +void elv_rqhash_add(struct request_queue *q, struct request *rq); +void elv_rqhash_reposition(struct request_queue *q, struct request *rq); +struct request *elv_rqhash_find(struct request_queue *q, sector_t offset); + +/* + * each queue has an elevator_queue associated with it + */ +struct elevator_queue +{ + struct elevator_type *type; + void *elevator_data; + struct kobject kobj; + struct mutex sysfs_lock; + unsigned int registered:1; + DECLARE_HASHTABLE(hash, ELV_HASH_BITS); +}; + +/* + * block elevator interface + */ +extern enum elv_merge elv_merge(struct request_queue *, struct request **, + struct bio *); +extern void elv_merge_requests(struct request_queue *, struct request *, + struct request *); +extern void elv_merged_request(struct request_queue *, struct request *, + enum elv_merge); +extern bool elv_attempt_insert_merge(struct request_queue *, struct request *, + struct list_head *); +extern struct request *elv_former_request(struct request_queue *, struct request *); +extern struct request *elv_latter_request(struct request_queue *, struct request *); +void elevator_init_mq(struct request_queue *q); + +/* + * io scheduler registration + */ +extern int elv_register(struct elevator_type *); +extern void elv_unregister(struct elevator_type *); + +/* + * io scheduler sysfs switching + */ +extern ssize_t elv_iosched_show(struct request_queue *, char *); +extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); + +extern bool elv_bio_merge_ok(struct request *, struct bio *); +extern struct elevator_queue *elevator_alloc(struct request_queue *, + struct elevator_type *); + +/* + * Helper functions. + */ +extern struct request *elv_rb_former_request(struct request_queue *, struct request *); +extern struct request *elv_rb_latter_request(struct request_queue *, struct request *); + +/* + * rb support functions. + */ +extern void elv_rb_add(struct rb_root *, struct request *); +extern void elv_rb_del(struct rb_root *, struct request *); +extern struct request *elv_rb_find(struct rb_root *, sector_t); + +/* + * Insertion selection + */ +#define ELEVATOR_INSERT_FRONT 1 +#define ELEVATOR_INSERT_BACK 2 +#define ELEVATOR_INSERT_SORT 3 +#define ELEVATOR_INSERT_REQUEUE 4 +#define ELEVATOR_INSERT_FLUSH 5 +#define ELEVATOR_INSERT_SORT_MERGE 6 + +#define rb_entry_rq(node) rb_entry((node), struct request, rb_node) + +#define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) +#define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist) + +#endif /* _ELEVATOR_H */ diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index a0ffbabfac2c..53dafc4bcd72 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -9,12 +9,12 @@ #include #include #include -#include #include #include #include +#include "elevator.h" #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 7f3c3932b723..47f042fa6a68 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -9,7 +9,6 @@ #include #include #include -#include #include #include #include @@ -20,6 +19,7 @@ #include +#include "elevator.h" #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 8b1714021498..b892e5185d6f 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -64,7 +64,6 @@ #include #include #include -#include #include #include diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index befeb7c34290..337e6ed24821 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -22,6 +22,7 @@ *******************************************************************/ #include +#include #include #include diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4bcbb1ae2d66..d815238f61ed 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -251,8 +251,6 @@ static inline unsigned short req_get_ioprio(struct request *req) return req->ioprio; } -#include - struct bio_vec; enum blk_eh_timer_return { @@ -1124,6 +1122,15 @@ extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); + +/* + * Elevator features for blk_queue_required_elevator_features: + */ +/* Supports zoned block devices sequential write constraint */ +#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) +/* Supports scheduling on multiple hardware queues */ +#define ELEVATOR_F_MQ_AWARE (1U << 1) + extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, diff --git a/include/linux/elevator.h b/include/linux/elevator.h deleted file mode 100644 index 80633f3b600c..000000000000 --- a/include/linux/elevator.h +++ /dev/null @@ -1,180 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_ELEVATOR_H -#define _LINUX_ELEVATOR_H - -#include -#include - -#ifdef CONFIG_BLOCK - -struct io_cq; -struct elevator_type; -#ifdef CONFIG_BLK_DEBUG_FS -struct blk_mq_debugfs_attr; -#endif - -/* - * Return values from elevator merger - */ -enum elv_merge { - ELEVATOR_NO_MERGE = 0, - ELEVATOR_FRONT_MERGE = 1, - ELEVATOR_BACK_MERGE = 2, - ELEVATOR_DISCARD_MERGE = 3, -}; - -struct blk_mq_alloc_data; -struct blk_mq_hw_ctx; - -struct elevator_mq_ops { - int (*init_sched)(struct request_queue *, struct elevator_type *); - void (*exit_sched)(struct elevator_queue *); - int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); - void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); - void (*depth_updated)(struct blk_mq_hw_ctx *); - - bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); - bool (*bio_merge)(struct request_queue *, struct bio *, unsigned int); - int (*request_merge)(struct request_queue *q, struct request **, struct bio *); - void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); - void (*requests_merged)(struct request_queue *, struct request *, struct request *); - void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); - void (*prepare_request)(struct request *); - void (*finish_request)(struct request *); - void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); - struct request *(*dispatch_request)(struct blk_mq_hw_ctx *); - bool (*has_work)(struct blk_mq_hw_ctx *); - void (*completed_request)(struct request *, u64); - void (*requeue_request)(struct request *); - struct request *(*former_request)(struct request_queue *, struct request *); - struct request *(*next_request)(struct request_queue *, struct request *); - void (*init_icq)(struct io_cq *); - void (*exit_icq)(struct io_cq *); -}; - -#define ELV_NAME_MAX (16) - -struct elv_fs_entry { - struct attribute attr; - ssize_t (*show)(struct elevator_queue *, char *); - ssize_t (*store)(struct elevator_queue *, const char *, size_t); -}; - -/* - * identifies an elevator type, such as AS or deadline - */ -struct elevator_type -{ - /* managed by elevator core */ - struct kmem_cache *icq_cache; - - /* fields provided by elevator implementation */ - struct elevator_mq_ops ops; - - size_t icq_size; /* see iocontext.h */ - size_t icq_align; /* ditto */ - struct elv_fs_entry *elevator_attrs; - const char *elevator_name; - const char *elevator_alias; - const unsigned int elevator_features; - struct module *elevator_owner; -#ifdef CONFIG_BLK_DEBUG_FS - const struct blk_mq_debugfs_attr *queue_debugfs_attrs; - const struct blk_mq_debugfs_attr *hctx_debugfs_attrs; -#endif - - /* managed by elevator core */ - char icq_cache_name[ELV_NAME_MAX + 6]; /* elvname + "_io_cq" */ - struct list_head list; -}; - -#define ELV_HASH_BITS 6 - -void elv_rqhash_del(struct request_queue *q, struct request *rq); -void elv_rqhash_add(struct request_queue *q, struct request *rq); -void elv_rqhash_reposition(struct request_queue *q, struct request *rq); -struct request *elv_rqhash_find(struct request_queue *q, sector_t offset); - -/* - * each queue has an elevator_queue associated with it - */ -struct elevator_queue -{ - struct elevator_type *type; - void *elevator_data; - struct kobject kobj; - struct mutex sysfs_lock; - unsigned int registered:1; - DECLARE_HASHTABLE(hash, ELV_HASH_BITS); -}; - -/* - * block elevator interface - */ -extern enum elv_merge elv_merge(struct request_queue *, struct request **, - struct bio *); -extern void elv_merge_requests(struct request_queue *, struct request *, - struct request *); -extern void elv_merged_request(struct request_queue *, struct request *, - enum elv_merge); -extern bool elv_attempt_insert_merge(struct request_queue *, struct request *, - struct list_head *); -extern struct request *elv_former_request(struct request_queue *, struct request *); -extern struct request *elv_latter_request(struct request_queue *, struct request *); -void elevator_init_mq(struct request_queue *q); - -/* - * io scheduler registration - */ -extern int elv_register(struct elevator_type *); -extern void elv_unregister(struct elevator_type *); - -/* - * io scheduler sysfs switching - */ -extern ssize_t elv_iosched_show(struct request_queue *, char *); -extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t); - -extern bool elv_bio_merge_ok(struct request *, struct bio *); -extern struct elevator_queue *elevator_alloc(struct request_queue *, - struct elevator_type *); - -/* - * Helper functions. - */ -extern struct request *elv_rb_former_request(struct request_queue *, struct request *); -extern struct request *elv_rb_latter_request(struct request_queue *, struct request *); - -/* - * rb support functions. - */ -extern void elv_rb_add(struct rb_root *, struct request *); -extern void elv_rb_del(struct rb_root *, struct request *); -extern struct request *elv_rb_find(struct rb_root *, sector_t); - -/* - * Insertion selection - */ -#define ELEVATOR_INSERT_FRONT 1 -#define ELEVATOR_INSERT_BACK 2 -#define ELEVATOR_INSERT_SORT 3 -#define ELEVATOR_INSERT_REQUEUE 4 -#define ELEVATOR_INSERT_FLUSH 5 -#define ELEVATOR_INSERT_SORT_MERGE 6 - -#define rb_entry_rq(node) rb_entry((node), struct request, rb_node) - -#define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) -#define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist) - -/* - * Elevator features. - */ - -/* Supports zoned block devices sequential write constraint */ -#define ELEVATOR_F_ZBD_SEQ_WRITE (1U << 0) -/* Supports scheduling on multiple hardware queues */ -#define ELEVATOR_F_MQ_AWARE (1U << 1) - -#endif /* CONFIG_BLOCK */ -#endif diff --git a/init/main.c b/init/main.c index 3c4054a95545..4162d7f3179f 100644 --- a/init/main.c +++ b/init/main.c @@ -83,7 +83,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From 3ab0bc78e96bd03a5096e4801550926d81b3e19d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:24 +0200 Subject: block: drop unused includes in Drop various include not actually used in blkdev.h itself. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-14-hch@lst.de Signed-off-by: Jens Axboe --- drivers/md/dm-ps-historical-service-time.c | 1 + drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 1 + include/linux/blkdev.h | 7 ------- 3 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/md/dm-ps-historical-service-time.c b/drivers/md/dm-ps-historical-service-time.c index 1856a1b125cc..875bca30a0dd 100644 --- a/drivers/md/dm-ps-historical-service-time.c +++ b/drivers/md/dm-ps-historical-service-time.c @@ -27,6 +27,7 @@ #include #include #include +#include #define DM_MSG_PREFIX "multipath historical-service-time" diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 3ab669dc806f..27884f3106ab 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -3,6 +3,7 @@ * Copyright (c) 2017 Hisilicon Limited. */ +#include #include "hisi_sas.h" #define DRV_NAME "hisi_sas_v3_hw" diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d815238f61ed..46a703394f7f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -3,8 +3,6 @@ #define _LINUX_BLKDEV_H #include -#include -#include #include #include #include @@ -12,17 +10,12 @@ #include #include #include -#include -#include #include -#include #include -#include #include #include #include #include -#include #include struct module; -- cgit v1.2.3 From b81e0c2372e65e5627864ba034433b64b2fc73f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:25 +0200 Subject: block: drop unused includes in Drop various include not actually used in genhd.h itself, and move the remaning includes closer together. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-15-hch@lst.de Signed-off-by: Jens Axboe --- arch/um/drivers/ubd_kern.c | 1 + block/genhd.c | 1 + block/holder.c | 1 + block/partitions/core.c | 1 + drivers/block/amiflop.c | 1 + drivers/block/ataflop.c | 1 + drivers/block/floppy.c | 1 + drivers/block/swim.c | 1 + drivers/block/xen-blkfront.c | 1 + drivers/md/md.c | 1 + drivers/s390/block/dasd_genhd.c | 1 + drivers/scsi/sd.c | 1 + drivers/scsi/sg.c | 1 + drivers/scsi/sr.c | 1 + drivers/scsi/st.c | 1 + include/linux/genhd.h | 14 ++------------ include/linux/part_stat.h | 1 + 17 files changed, 18 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index cd9dc0556e91..fefd343412c7 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include diff --git a/block/genhd.c b/block/genhd.c index b49858550fa6..ffbdb9b24555 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include diff --git a/block/holder.c b/block/holder.c index 9dc084182337..27cddce1b446 100644 --- a/block/holder.c +++ b/block/holder.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include +#include struct bd_holder_disk { struct list_head list; diff --git a/block/partitions/core.c b/block/partitions/core.c index 58c4c362c94f..3a4898433c43 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -5,6 +5,7 @@ * Copyright (C) 2020 Christoph Hellwig */ #include +#include #include #include #include diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index b892e5185d6f..2909fd9e72fb 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -61,6 +61,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index a093644ac39f..58e921ab5729 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -68,6 +68,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index fef79ea52e3e..6288ce888414 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -184,6 +184,7 @@ static int print_unex = 1; #include #include #include +#include #include #include #include diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 7ccc8d2a41bc..3911d0833e1b 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 72902104f111..df0deb927760 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/md/md.c b/drivers/md/md.c index 6c0c3d0d905a..1b9bc8dbd95d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -51,6 +51,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c index fa966e0db6ca..3a6f3af240fa 100644 --- a/drivers/s390/block/dasd_genhd.c +++ b/drivers/s390/block/dasd_genhd.c @@ -14,6 +14,7 @@ #define KMSG_COMPONENT "dasd" #include +#include #include #include diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 523bf2fdc253..d8f6add416c0 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 8f05248920e8..3c98f08dc25d 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -31,6 +31,7 @@ static int sg_version_num = 30536; /* 2 digits for each component */ #include #include #include +#include #include #include #include diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8b17b35283aa..115f7ef7a5de 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index ae8636d3780b..9933722acfd9 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -32,6 +32,7 @@ static const char *verstr = "20160209"; #include #include #include +#include #include #include #include diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0f5315c2b5a3..0b48a0cf4262 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -12,12 +12,10 @@ #include #include -#include -#include -#include #include #include -#include +#include +#include extern const struct device_type disk_type; extern struct device_type part_type; @@ -26,14 +24,6 @@ extern struct class block_class; #define DISK_MAX_PARTS 256 #define DISK_NAME_LEN 32 -#include -#include -#include -#include -#include -#include -#include - #define PARTITION_META_INFO_VOLNAMELTH 64 /* * Enough for the string representation of any kind of UUID plus NULL. diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h index d2558121d48c..6f7949b2fd8d 100644 --- a/include/linux/part_stat.h +++ b/include/linux/part_stat.h @@ -3,6 +3,7 @@ #define _LINUX_PART_STAT_H #include +#include struct disk_stats { u64 nsecs[NR_STAT_GROUPS]; -- cgit v1.2.3 From badf7f64378796d460c79eb0f182fa7282eb65d5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:26 +0200 Subject: block: move a few merge helpers out of These are block-layer internal helpers, so move them to block/blk.h and block/blk-merge.c. Also update a comment a bit to use better grammar. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-16-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-merge.c | 24 +++++++++++++++++++ block/blk.h | 38 ++++++++++++++++++++++++++++++ include/linux/blkdev.h | 64 -------------------------------------------------- 3 files changed, 62 insertions(+), 64 deletions(-) (limited to 'include/linux') diff --git a/block/blk-merge.c b/block/blk-merge.c index 7a5c81c02c80..39f210da399a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -558,6 +558,23 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq) return queue_max_segments(rq->q); } +static inline unsigned int blk_rq_get_max_sectors(struct request *rq, + sector_t offset) +{ + struct request_queue *q = rq->q; + + if (blk_rq_is_passthrough(rq)) + return q->limits.max_hw_sectors; + + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) + return blk_queue_get_max_sectors(q, req_op(rq)); + + return min(blk_max_size_offset(q, offset, 0), + blk_queue_get_max_sectors(q, req_op(rq))); +} + static inline int ll_new_hw_segment(struct request *req, struct bio *bio, unsigned int nr_phys_segs) { @@ -718,6 +735,13 @@ static enum elv_merge blk_try_req_merge(struct request *req, return ELEVATOR_NO_MERGE; } +static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) +{ + if (bio_page(a) == bio_page(b) && bio_offset(a) == bio_offset(b)) + return true; + return false; +} + /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. diff --git a/block/blk.h b/block/blk.h index f24569980905..fa90691cfdab 100644 --- a/block/blk.h +++ b/block/blk.h @@ -96,6 +96,44 @@ static inline bool bvec_gap_to_prev(struct request_queue *q, return __bvec_gap_to_prev(q, bprv, offset); } +static inline bool rq_mergeable(struct request *rq) +{ + if (blk_rq_is_passthrough(rq)) + return false; + + if (req_op(rq) == REQ_OP_FLUSH) + return false; + + if (req_op(rq) == REQ_OP_WRITE_ZEROES) + return false; + + if (req_op(rq) == REQ_OP_ZONE_APPEND) + return false; + + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) + return false; + if (rq->rq_flags & RQF_NOMERGE_FLAGS) + return false; + + return true; +} + +/* + * There are two different ways to handle DISCARD merges: + * 1) If max_discard_segments > 1, the driver treats every bio as a range and + * send the bios to controller together. The ranges don't need to be + * contiguous. + * 2) Otherwise, the request will be normal read/write requests. The ranges + * need to be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + #ifdef CONFIG_BLK_DEV_INTEGRITY void blk_flush_integrity(void); bool __bio_integrity_endio(struct bio *); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 46a703394f7f..be534040ca9c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -745,37 +745,6 @@ static inline bool rq_is_sync(struct request *rq) return op_is_sync(rq->cmd_flags); } -static inline bool rq_mergeable(struct request *rq) -{ - if (blk_rq_is_passthrough(rq)) - return false; - - if (req_op(rq) == REQ_OP_FLUSH) - return false; - - if (req_op(rq) == REQ_OP_WRITE_ZEROES) - return false; - - if (req_op(rq) == REQ_OP_ZONE_APPEND) - return false; - - if (rq->cmd_flags & REQ_NOMERGE_FLAGS) - return false; - if (rq->rq_flags & RQF_NOMERGE_FLAGS) - return false; - - return true; -} - -static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) -{ - if (bio_page(a) == bio_page(b) && - bio_offset(a) == bio_offset(b)) - return true; - - return false; -} - static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) @@ -1030,23 +999,6 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, return min(q->limits.max_sectors, chunk_sectors); } -static inline unsigned int blk_rq_get_max_sectors(struct request *rq, - sector_t offset) -{ - struct request_queue *q = rq->q; - - if (blk_rq_is_passthrough(rq)) - return q->limits.max_hw_sectors; - - if (!q->limits.chunk_sectors || - req_op(rq) == REQ_OP_DISCARD || - req_op(rq) == REQ_OP_SECURE_ERASE) - return blk_queue_get_max_sectors(q, req_op(rq)); - - return min(blk_max_size_offset(q, offset, 0), - blk_queue_get_max_sectors(q, req_op(rq))); -} - static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; @@ -1490,22 +1442,6 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector return offset << SECTOR_SHIFT; } -/* - * Two cases of handling DISCARD merge: - * If max_discard_segments > 1, the driver takes every bio - * as a range and send them to controller together. The ranges - * needn't to be contiguous. - * Otherwise, the bios/requests will be handled as same as - * others which should be contiguous. - */ -static inline bool blk_discard_mergable(struct request *req) -{ - if (req_op(req) == REQ_OP_DISCARD && - queue_max_discard_segments(req->q) > 1) - return true; - return false; -} - static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); -- cgit v1.2.3 From fe45e630a1035aea94c29016f2598bbde149bbe3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:27 +0200 Subject: block: move integrity handling out of Split the integrity/metadata handling definitions out into a new header. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-17-hch@lst.de Signed-off-by: Jens Axboe --- block/bdev.c | 1 + block/bio-integrity.c | 2 +- block/blk-core.c | 1 + block/blk-integrity.c | 2 +- block/blk-merge.c | 1 + block/blk-mq.c | 1 + block/keyslot-manager.c | 1 + block/t10-pi.c | 2 +- drivers/md/dm-bio-record.h | 1 + drivers/md/dm-crypt.c | 1 + drivers/md/dm-table.c | 1 + drivers/md/md.c | 1 + drivers/nvdimm/core.c | 1 + drivers/nvme/host/core.c | 1 + drivers/nvme/host/pci.c | 1 + drivers/nvme/host/rdma.c | 1 + drivers/nvme/target/io-cmd-bdev.c | 1 + drivers/nvme/target/rdma.c | 1 + drivers/scsi/scsi_lib.c | 1 + drivers/scsi/sd_dif.c | 2 +- drivers/scsi/virtio_scsi.c | 1 + drivers/target/target_core_iblock.c | 1 + include/linux/blk-integrity.h | 183 ++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 183 ------------------------------------ 24 files changed, 205 insertions(+), 187 deletions(-) create mode 100644 include/linux/blk-integrity.h (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index 485a258b0ab3..93b1188d7e58 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 6b47cddbbca1..21234ff966d9 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -6,7 +6,7 @@ * Written by: Martin K. Petersen */ -#include +#include #include #include #include diff --git a/block/blk-core.c b/block/blk-core.c index 4d8f5fe91588..d2c6caadef89 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 16d5d5338392..cef534a7cbc9 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -6,7 +6,7 @@ * Written by: Martin K. Petersen */ -#include +#include #include #include #include diff --git a/block/blk-merge.c b/block/blk-merge.c index 39f210da399a..5b4f23014df8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include diff --git a/block/blk-mq.c b/block/blk-mq.c index 0fefe00cebd4..2539ba976949 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c index 2c4a55bea6ca..1792159d12d1 100644 --- a/block/keyslot-manager.c +++ b/block/keyslot-manager.c @@ -35,6 +35,7 @@ #include #include #include +#include struct blk_ksm_keyslot { atomic_t slot_refs; diff --git a/block/t10-pi.c b/block/t10-pi.c index 00c203b2a921..25a52a2a09a8 100644 --- a/block/t10-pi.c +++ b/block/t10-pi.c @@ -5,7 +5,7 @@ */ #include -#include +#include #include #include #include diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h index a3b71350eec8..745e3ab4aa0a 100644 --- a/drivers/md/dm-bio-record.h +++ b/drivers/md/dm-bio-record.h @@ -8,6 +8,7 @@ #define DM_BIO_RECORD_H #include +#include /* * There are lots of mutable fields in the bio struct that get diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 916b7da16de2..292f7896f733 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 2111daaacaba..1fa4d5582dca 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/md/md.c b/drivers/md/md.c index 1b9bc8dbd95d..ec09083ff0ef 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 7de592d7eff4..6a45fa91e8a3 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f8dd664b2eda..3d444b13cd69 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -6,6 +6,7 @@ #include #include +#include #include #include #include diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 149ecf73df38..896328271471 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 042c594bc57e..40317e1b9183 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 0fc2781ab970..6139e1de50a6 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -5,6 +5,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include "nvmet.h" diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 891174ccd44b..38d1f292ecc2 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -5,6 +5,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 572673873ddf..33fd9a01330c 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c index 4cadb26070a8..349950616adc 100644 --- a/drivers/scsi/sd_dif.c +++ b/drivers/scsi/sd_dif.c @@ -6,7 +6,7 @@ * Written by: Martin K. Petersen */ -#include +#include #include #include diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 07d0250f17c3..b8455fcbf18b 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 4069a1edcfa3..d39b87e2ed10 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h new file mode 100644 index 000000000000..8a038ea0717e --- /dev/null +++ b/include/linux/blk-integrity.h @@ -0,0 +1,183 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BLK_INTEGRITY_H +#define _LINUX_BLK_INTEGRITY_H + +#include + +struct request; + +enum blk_integrity_flags { + BLK_INTEGRITY_VERIFY = 1 << 0, + BLK_INTEGRITY_GENERATE = 1 << 1, + BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, + BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, +}; + +struct blk_integrity_iter { + void *prot_buf; + void *data_buf; + sector_t seed; + unsigned int data_size; + unsigned short interval; + const char *disk_name; +}; + +typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); +typedef void (integrity_prepare_fn) (struct request *); +typedef void (integrity_complete_fn) (struct request *, unsigned int); + +struct blk_integrity_profile { + integrity_processing_fn *generate_fn; + integrity_processing_fn *verify_fn; + integrity_prepare_fn *prepare_fn; + integrity_complete_fn *complete_fn; + const char *name; +}; + +#ifdef CONFIG_BLK_DEV_INTEGRITY +void blk_integrity_register(struct gendisk *, struct blk_integrity *); +void blk_integrity_unregister(struct gendisk *); +int blk_integrity_compare(struct gendisk *, struct gendisk *); +int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, + struct scatterlist *); +int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); + +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + struct blk_integrity *bi = &disk->queue->integrity; + + if (!bi->profile) + return NULL; + + return bi; +} + +static inline struct blk_integrity * +bdev_get_integrity(struct block_device *bdev) +{ + return blk_get_integrity(bdev->bd_disk); +} + +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return q->integrity.profile; +} + +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ + q->limits.max_integrity_segments = segs; +} + +static inline unsigned short +queue_max_integrity_segments(const struct request_queue *q) +{ + return q->limits.max_integrity_segments; +} + +/** + * bio_integrity_intervals - Return number of integrity intervals for a bio + * @bi: blk_integrity profile for device + * @sectors: Size of the bio in 512-byte sectors + * + * Description: The block layer calculates everything in 512 byte + * sectors but integrity metadata is done in terms of the data integrity + * interval size of the storage device. Convert the block layer sectors + * to the appropriate number of integrity intervals. + */ +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return sectors >> (bi->interval_exp - 9); +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return bio_integrity_intervals(bi, sectors) * bi->tuple_size; +} + +static inline bool blk_integrity_rq(struct request *rq) +{ + return rq->cmd_flags & REQ_INTEGRITY; +} + +/* + * Return the first bvec that contains integrity data. Only drivers that are + * limited to a single integrity segment should use this helper. + */ +static inline struct bio_vec *rq_integrity_vec(struct request *rq) +{ + if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) + return NULL; + return rq->bio->bi_integrity->bip_vec; +} +#else /* CONFIG_BLK_DEV_INTEGRITY */ +static inline int blk_rq_count_integrity_sg(struct request_queue *q, + struct bio *b) +{ + return 0; +} +static inline int blk_rq_map_integrity_sg(struct request_queue *q, + struct bio *b, + struct scatterlist *s) +{ + return 0; +} +static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) +{ + return NULL; +} +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + return NULL; +} +static inline bool +blk_integrity_queue_supports_integrity(struct request_queue *q) +{ + return false; +} +static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) +{ + return 0; +} +static inline void blk_integrity_register(struct gendisk *d, + struct blk_integrity *b) +{ +} +static inline void blk_integrity_unregister(struct gendisk *d) +{ +} +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ +} +static inline unsigned short +queue_max_integrity_segments(const struct request_queue *q) +{ + return 0; +} + +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} +static inline int blk_integrity_rq(struct request *rq) +{ + return 0; +} + +static inline struct bio_vec *rq_integrity_vec(struct request *rq) +{ + return NULL; +} +#endif /* CONFIG_BLK_DEV_INTEGRITY */ +#endif /* _LINUX_BLK_INTEGRITY_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index be534040ca9c..56e60e5c09d0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1555,189 +1555,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") -#if defined(CONFIG_BLK_DEV_INTEGRITY) - -enum blk_integrity_flags { - BLK_INTEGRITY_VERIFY = 1 << 0, - BLK_INTEGRITY_GENERATE = 1 << 1, - BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, - BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, -}; - -struct blk_integrity_iter { - void *prot_buf; - void *data_buf; - sector_t seed; - unsigned int data_size; - unsigned short interval; - const char *disk_name; -}; - -typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); -typedef void (integrity_prepare_fn) (struct request *); -typedef void (integrity_complete_fn) (struct request *, unsigned int); - -struct blk_integrity_profile { - integrity_processing_fn *generate_fn; - integrity_processing_fn *verify_fn; - integrity_prepare_fn *prepare_fn; - integrity_complete_fn *complete_fn; - const char *name; -}; - -extern void blk_integrity_register(struct gendisk *, struct blk_integrity *); -extern void blk_integrity_unregister(struct gendisk *); -extern int blk_integrity_compare(struct gendisk *, struct gendisk *); -extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, - struct scatterlist *); -extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); - -static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) -{ - struct blk_integrity *bi = &disk->queue->integrity; - - if (!bi->profile) - return NULL; - - return bi; -} - -static inline -struct blk_integrity *bdev_get_integrity(struct block_device *bdev) -{ - return blk_get_integrity(bdev->bd_disk); -} - -static inline bool -blk_integrity_queue_supports_integrity(struct request_queue *q) -{ - return q->integrity.profile; -} - -static inline bool blk_integrity_rq(struct request *rq) -{ - return rq->cmd_flags & REQ_INTEGRITY; -} - -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ - q->limits.max_integrity_segments = segs; -} - -static inline unsigned short -queue_max_integrity_segments(const struct request_queue *q) -{ - return q->limits.max_integrity_segments; -} - -/** - * bio_integrity_intervals - Return number of integrity intervals for a bio - * @bi: blk_integrity profile for device - * @sectors: Size of the bio in 512-byte sectors - * - * Description: The block layer calculates everything in 512 byte - * sectors but integrity metadata is done in terms of the data integrity - * interval size of the storage device. Convert the block layer sectors - * to the appropriate number of integrity intervals. - */ -static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, - unsigned int sectors) -{ - return sectors >> (bi->interval_exp - 9); -} - -static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, - unsigned int sectors) -{ - return bio_integrity_intervals(bi, sectors) * bi->tuple_size; -} - -/* - * Return the first bvec that contains integrity data. Only drivers that are - * limited to a single integrity segment should use this helper. - */ -static inline struct bio_vec *rq_integrity_vec(struct request *rq) -{ - if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) - return NULL; - return rq->bio->bi_integrity->bip_vec; -} - -#else /* CONFIG_BLK_DEV_INTEGRITY */ - -struct bio; -struct block_device; -struct gendisk; -struct blk_integrity; - -static inline int blk_integrity_rq(struct request *rq) -{ - return 0; -} -static inline int blk_rq_count_integrity_sg(struct request_queue *q, - struct bio *b) -{ - return 0; -} -static inline int blk_rq_map_integrity_sg(struct request_queue *q, - struct bio *b, - struct scatterlist *s) -{ - return 0; -} -static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) -{ - return NULL; -} -static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) -{ - return NULL; -} -static inline bool -blk_integrity_queue_supports_integrity(struct request_queue *q) -{ - return false; -} -static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) -{ - return 0; -} -static inline void blk_integrity_register(struct gendisk *d, - struct blk_integrity *b) -{ -} -static inline void blk_integrity_unregister(struct gendisk *d) -{ -} -static inline void blk_queue_max_integrity_segments(struct request_queue *q, - unsigned int segs) -{ -} -static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) -{ - return 0; -} - -static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, - unsigned int sectors) -{ - return 0; -} - -static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, - unsigned int sectors) -{ - return 0; -} - -static inline struct bio_vec *rq_integrity_vec(struct request *rq) -{ - return NULL; -} - -#endif /* CONFIG_BLK_DEV_INTEGRITY */ - #ifdef CONFIG_BLK_INLINE_ENCRYPTION bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); -- cgit v1.2.3 From 24b83deb29b7f06a5573b65f2ce96f5482755d43 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Sep 2021 14:33:28 +0200 Subject: block: move struct request to blk-mq.h struct request is only used by blk-mq drivers, so move it and all related declarations to blk-mq.h. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210920123328.1399408-18-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-crypto-fallback.c | 1 + block/blk-crypto-internal.h | 2 +- drivers/block/rnbd/rnbd-proto.h | 2 +- drivers/md/dm-verity-target.c | 1 + drivers/mmc/core/sd.c | 1 + drivers/target/target_core_file.c | 1 + drivers/target/target_core_iblock.c | 1 + include/linux/blk-mq.h | 465 +++++++++++++++++++++++++++++++++++ include/linux/blk_types.h | 2 - include/linux/blkdev.h | 469 +----------------------------------- include/linux/blktrace_api.h | 2 +- include/linux/t10-pi.h | 2 +- include/scsi/scsi_device.h | 2 +- 13 files changed, 476 insertions(+), 475 deletions(-) (limited to 'include/linux') diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index c322176a1e09..ec4c7823541c 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "blk-crypto-internal.h" diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h index 0d36aae538d7..2fb0d65a464c 100644 --- a/block/blk-crypto-internal.h +++ b/block/blk-crypto-internal.h @@ -7,7 +7,7 @@ #define __LINUX_BLK_CRYPTO_INTERNAL_H #include -#include +#include /* Represents a crypto mode supported by blk-crypto */ struct blk_crypto_mode { diff --git a/drivers/block/rnbd/rnbd-proto.h b/drivers/block/rnbd/rnbd-proto.h index c1bc5c0fef71..de5d5a8df81d 100644 --- a/drivers/block/rnbd/rnbd-proto.h +++ b/drivers/block/rnbd/rnbd-proto.h @@ -10,7 +10,7 @@ #define RNBD_PROTO_H #include -#include +#include #include #include #include diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 88288c8d6bc8..aae48a8b1a04 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -18,6 +18,7 @@ #include "dm-verity-verify-sig.h" #include #include +#include #define DM_MSG_PREFIX "verity" diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index 4646b7a03db6..c9db24e16af1 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index ef4a8e189fba..02f64453b4c5 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index d39b87e2ed10..31df20abe141 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 13ba1861e688..bd4086a6f28e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -6,10 +6,218 @@ #include #include #include +#include struct blk_mq_tags; struct blk_flush_queue; +#define BLKDEV_MIN_RQ 4 +#define BLKDEV_MAX_RQ 128 /* Default maximum */ + +typedef void (rq_end_io_fn)(struct request *, blk_status_t); + +/* + * request flags */ +typedef __u32 __bitwise req_flags_t; + +/* drive already may have started this one */ +#define RQF_STARTED ((__force req_flags_t)(1 << 1)) +/* may not be passed by ioscheduler */ +#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) +/* request for flush sequence */ +#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) +/* merge of different types, fail separately */ +#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) +/* track inflight for MQ */ +#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) +/* don't call prep for this one */ +#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) +/* vaguely specified driver internal error. Ignored by the block layer */ +#define RQF_FAILED ((__force req_flags_t)(1 << 10)) +/* don't warn about errors */ +#define RQF_QUIET ((__force req_flags_t)(1 << 11)) +/* elevator private data attached */ +#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) +/* account into disk and partition IO statistics */ +#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) +/* runtime pm request */ +#define RQF_PM ((__force req_flags_t)(1 << 15)) +/* on IO scheduler merge hash */ +#define RQF_HASHED ((__force req_flags_t)(1 << 16)) +/* track IO completion time */ +#define RQF_STATS ((__force req_flags_t)(1 << 17)) +/* Look at ->special_vec for the actual data payload instead of the + bio chain. */ +#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) +/* The per-zone write lock is held for this request */ +#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) +/* already slept for hybrid poll */ +#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) +/* ->timeout has been called, don't expire again */ +#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) + +/* flags that prevent us from merging requests: */ +#define RQF_NOMERGE_FLAGS \ + (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) + +enum mq_rq_state { + MQ_RQ_IDLE = 0, + MQ_RQ_IN_FLIGHT = 1, + MQ_RQ_COMPLETE = 2, +}; + +/* + * Try to put the fields that are referenced together in the same cacheline. + * + * If you modify this structure, make sure to update blk_rq_init() and + * especially blk_mq_rq_ctx_init() to take care of the added fields. + */ +struct request { + struct request_queue *q; + struct blk_mq_ctx *mq_ctx; + struct blk_mq_hw_ctx *mq_hctx; + + unsigned int cmd_flags; /* op and common flags */ + req_flags_t rq_flags; + + int tag; + int internal_tag; + + /* the following two fields are internal, NEVER access directly */ + unsigned int __data_len; /* total data len */ + sector_t __sector; /* sector cursor */ + + struct bio *bio; + struct bio *biotail; + + struct list_head queuelist; + + /* + * The hash is used inside the scheduler, and killed once the + * request reaches the dispatch list. The ipi_list is only used + * to queue the request for softirq completion, which is long + * after the request has been unhashed (and even removed from + * the dispatch list). + */ + union { + struct hlist_node hash; /* merge hash */ + struct llist_node ipi_list; + }; + + /* + * The rb_node is only used inside the io scheduler, requests + * are pruned when moved to the dispatch queue. So let the + * completion_data share space with the rb_node. + */ + union { + struct rb_node rb_node; /* sort/lookup */ + struct bio_vec special_vec; + void *completion_data; + int error_count; /* for legacy drivers, don't use */ + }; + + /* + * Three pointers are available for the IO schedulers, if they need + * more they have to dynamically allocate it. Flush requests are + * never put on the IO scheduler. So let the flush fields share + * space with the elevator data. + */ + union { + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + + struct { + unsigned int seq; + struct list_head list; + rq_end_io_fn *saved_end_io; + } flush; + }; + + struct gendisk *rq_disk; + struct block_device *part; +#ifdef CONFIG_BLK_RQ_ALLOC_TIME + /* Time that the first bio started allocating this request. */ + u64 alloc_time_ns; +#endif + /* Time that this request was allocated for this IO. */ + u64 start_time_ns; + /* Time that I/O was submitted to the device. */ + u64 io_start_time_ns; + +#ifdef CONFIG_BLK_WBT + unsigned short wbt_flags; +#endif + /* + * rq sectors used for blk stats. It has the same value + * with blk_rq_sectors(rq), except that it never be zeroed + * by completion. + */ + unsigned short stats_sectors; + + /* + * Number of scatter-gather DMA addr+len pairs after + * physical address coalescing is performed. + */ + unsigned short nr_phys_segments; + +#ifdef CONFIG_BLK_DEV_INTEGRITY + unsigned short nr_integrity_segments; +#endif + +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + struct bio_crypt_ctx *crypt_ctx; + struct blk_ksm_keyslot *crypt_keyslot; +#endif + + unsigned short write_hint; + unsigned short ioprio; + + enum mq_rq_state state; + refcount_t ref; + + unsigned int timeout; + unsigned long deadline; + + union { + struct __call_single_data csd; + u64 fifo_time; + }; + + /* + * completion callback. + */ + rq_end_io_fn *end_io; + void *end_io_data; +}; + +#define req_op(req) \ + ((req)->cmd_flags & REQ_OP_MASK) + +static inline bool blk_rq_is_passthrough(struct request *rq) +{ + return blk_op_is_passthrough(req_op(rq)); +} + +static inline unsigned short req_get_ioprio(struct request *req) +{ + return req->ioprio; +} + +#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) + +#define rq_dma_dir(rq) \ + (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) + +enum blk_eh_timer_return { + BLK_EH_DONE, /* drivers has completed the command */ + BLK_EH_RESET_TIMER, /* reset timer and try again */ +}; + +#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ +#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ + /** * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware * block device @@ -637,4 +845,261 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio); void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); +static inline bool rq_is_sync(struct request *rq) +{ + return op_is_sync(rq->cmd_flags); +} + +void blk_rq_init(struct request_queue *q, struct request *rq); +void blk_put_request(struct request *rq); +struct request *blk_get_request(struct request_queue *q, unsigned int op, + blk_mq_req_flags_t flags); +int blk_rq_prep_clone(struct request *rq, struct request *rq_src, + struct bio_set *bs, gfp_t gfp_mask, + int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); +void blk_rq_unprep_clone(struct request *rq); +blk_status_t blk_insert_cloned_request(struct request_queue *q, + struct request *rq); + +struct rq_map_data { + struct page **pages; + int page_order; + int nr_entries; + unsigned long offset; + int null_mapped; + int from_user; +}; + +int blk_rq_map_user(struct request_queue *, struct request *, + struct rq_map_data *, void __user *, unsigned long, gfp_t); +int blk_rq_map_user_iov(struct request_queue *, struct request *, + struct rq_map_data *, const struct iov_iter *, gfp_t); +int blk_rq_unmap_user(struct bio *); +int blk_rq_map_kern(struct request_queue *, struct request *, void *, + unsigned int, gfp_t); +int blk_rq_append_bio(struct request *rq, struct bio *bio); +void blk_execute_rq_nowait(struct gendisk *, struct request *, int, + rq_end_io_fn *); +blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, + int at_head); + +struct req_iterator { + struct bvec_iter iter; + struct bio *bio; +}; + +#define __rq_for_each_bio(_bio, rq) \ + if ((rq->bio)) \ + for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) + +#define rq_for_each_segment(bvl, _rq, _iter) \ + __rq_for_each_bio(_iter.bio, _rq) \ + bio_for_each_segment(bvl, _iter.bio, _iter.iter) + +#define rq_for_each_bvec(bvl, _rq, _iter) \ + __rq_for_each_bio(_iter.bio, _rq) \ + bio_for_each_bvec(bvl, _iter.bio, _iter.iter) + +#define rq_iter_last(bvec, _iter) \ + (_iter.bio->bi_next == NULL && \ + bio_iter_last(bvec, _iter.iter)) + +/* + * blk_rq_pos() : the current sector + * blk_rq_bytes() : bytes left in the entire request + * blk_rq_cur_bytes() : bytes left in the current segment + * blk_rq_err_bytes() : bytes left till the next error boundary + * blk_rq_sectors() : sectors left in the entire request + * blk_rq_cur_sectors() : sectors left in the current segment + * blk_rq_stats_sectors() : sectors of the entire request used for stats + */ +static inline sector_t blk_rq_pos(const struct request *rq) +{ + return rq->__sector; +} + +static inline unsigned int blk_rq_bytes(const struct request *rq) +{ + return rq->__data_len; +} + +static inline int blk_rq_cur_bytes(const struct request *rq) +{ + return rq->bio ? bio_cur_bytes(rq->bio) : 0; +} + +unsigned int blk_rq_err_bytes(const struct request *rq); + +static inline unsigned int blk_rq_sectors(const struct request *rq) +{ + return blk_rq_bytes(rq) >> SECTOR_SHIFT; +} + +static inline unsigned int blk_rq_cur_sectors(const struct request *rq) +{ + return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; +} + +static inline unsigned int blk_rq_stats_sectors(const struct request *rq) +{ + return rq->stats_sectors; +} + +/* + * Some commands like WRITE SAME have a payload or data transfer size which + * is different from the size of the request. Any driver that supports such + * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to + * calculate the data transfer size. + */ +static inline unsigned int blk_rq_payload_bytes(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec.bv_len; + return blk_rq_bytes(rq); +} + +/* + * Return the first full biovec in the request. The caller needs to check that + * there are any bvecs before calling this helper. + */ +static inline struct bio_vec req_bvec(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return rq->special_vec; + return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); +} + +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + +void blk_steal_bios(struct bio_list *list, struct request *rq); + +/* + * Request completion related functions. + * + * blk_update_request() completes given number of bytes and updates + * the request without completing it. + */ +bool blk_update_request(struct request *rq, blk_status_t error, + unsigned int nr_bytes); +void blk_abort_request(struct request *); + +/* + * Number of physical segments as sent to the device. + * + * Normally this is the number of discontiguous data segments sent by the + * submitter. But for data-less command like discard we might have no + * actual data segments submitted, but the driver might have to add it's + * own special payload. In that case we still return 1 here so that this + * special payload will be mapped. + */ +static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) +{ + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) + return 1; + return rq->nr_phys_segments; +} + +/* + * Number of discard segments (or ranges) the driver needs to fill in. + * Each discard bio merged into a request is counted as one segment. + */ +static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) +{ + return max_t(unsigned short, rq->nr_phys_segments, 1); +} + +int __blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist, struct scatterlist **last_sg); +static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist) +{ + struct scatterlist *last_sg = NULL; + + return __blk_rq_map_sg(q, rq, sglist, &last_sg); +} +void blk_dump_rq_flags(struct request *, char *); + +#ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int blk_rq_zone_no(struct request *rq) +{ + return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); +} + +static inline unsigned int blk_rq_zone_is_seq(struct request *rq) +{ + return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); +} + +bool blk_req_needs_zone_write_lock(struct request *rq); +bool blk_req_zone_write_trylock(struct request *rq); +void __blk_req_zone_write_lock(struct request *rq); +void __blk_req_zone_write_unlock(struct request *rq); + +static inline void blk_req_zone_write_lock(struct request *rq) +{ + if (blk_req_needs_zone_write_lock(rq)) + __blk_req_zone_write_lock(rq); +} + +static inline void blk_req_zone_write_unlock(struct request *rq) +{ + if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) + __blk_req_zone_write_unlock(rq); +} + +static inline bool blk_req_zone_is_write_locked(struct request *rq) +{ + return rq->q->seq_zones_wlock && + test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); +} + +static inline bool blk_req_can_dispatch_to_zone(struct request *rq) +{ + if (!blk_req_needs_zone_write_lock(rq)) + return true; + return !blk_req_zone_is_write_locked(rq); +} +#else /* CONFIG_BLK_DEV_ZONED */ +static inline bool blk_req_needs_zone_write_lock(struct request *rq) +{ + return false; +} + +static inline void blk_req_zone_write_lock(struct request *rq) +{ +} + +static inline void blk_req_zone_write_unlock(struct request *rq) +{ +} +static inline bool blk_req_zone_is_write_locked(struct request *rq) +{ + return false; +} + +static inline bool blk_req_can_dispatch_to_zone(struct request *rq) +{ + return true; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" #endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +void rq_flush_dcache_pages(struct request *rq); +#else +static inline void rq_flush_dcache_pages(struct request *rq) +{ +} +#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ +#endif /* BLK_MQ_H */ diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index be622b5a21ed..3b967053e9f5 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -431,8 +431,6 @@ enum stat_group { #define bio_op(bio) \ ((bio)->bi_opf & REQ_OP_MASK) -#define req_op(req) \ - ((req)->cmd_flags & REQ_OP_MASK) /* obsolete, don't use in new code */ static inline void bio_set_op_attrs(struct bio *bio, unsigned op, diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 56e60e5c09d0..0e960d74615e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -14,7 +14,6 @@ #include #include #include -#include #include #include @@ -32,9 +31,6 @@ struct blk_queue_stats; struct blk_stat_callback; struct blk_keyslot_manager; -#define BLKDEV_MIN_RQ 4 -#define BLKDEV_MAX_RQ 128 /* Default maximum */ - /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 @@ -47,213 +43,12 @@ struct blk_keyslot_manager; */ #define BLKCG_MAX_POLS 6 -typedef void (rq_end_io_fn)(struct request *, blk_status_t); - -/* - * request flags */ -typedef __u32 __bitwise req_flags_t; - -/* drive already may have started this one */ -#define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* may not be passed by ioscheduler */ -#define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) -/* request for flush sequence */ -#define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) -/* merge of different types, fail separately */ -#define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) -/* track inflight for MQ */ -#define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) -/* don't call prep for this one */ -#define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) -/* vaguely specified driver internal error. Ignored by the block layer */ -#define RQF_FAILED ((__force req_flags_t)(1 << 10)) -/* don't warn about errors */ -#define RQF_QUIET ((__force req_flags_t)(1 << 11)) -/* elevator private data attached */ -#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) -/* account into disk and partition IO statistics */ -#define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) -/* runtime pm request */ -#define RQF_PM ((__force req_flags_t)(1 << 15)) -/* on IO scheduler merge hash */ -#define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* track IO completion time */ -#define RQF_STATS ((__force req_flags_t)(1 << 17)) -/* Look at ->special_vec for the actual data payload instead of the - bio chain. */ -#define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) -/* The per-zone write lock is held for this request */ -#define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* already slept for hybrid poll */ -#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) -/* ->timeout has been called, don't expire again */ -#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) - -/* flags that prevent us from merging requests: */ -#define RQF_NOMERGE_FLAGS \ - (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) - -/* - * Request state for blk-mq. - */ -enum mq_rq_state { - MQ_RQ_IDLE = 0, - MQ_RQ_IN_FLIGHT = 1, - MQ_RQ_COMPLETE = 2, -}; - -/* - * Try to put the fields that are referenced together in the same cacheline. - * - * If you modify this structure, make sure to update blk_rq_init() and - * especially blk_mq_rq_ctx_init() to take care of the added fields. - */ -struct request { - struct request_queue *q; - struct blk_mq_ctx *mq_ctx; - struct blk_mq_hw_ctx *mq_hctx; - - unsigned int cmd_flags; /* op and common flags */ - req_flags_t rq_flags; - - int tag; - int internal_tag; - - /* the following two fields are internal, NEVER access directly */ - unsigned int __data_len; /* total data len */ - sector_t __sector; /* sector cursor */ - - struct bio *bio; - struct bio *biotail; - - struct list_head queuelist; - - /* - * The hash is used inside the scheduler, and killed once the - * request reaches the dispatch list. The ipi_list is only used - * to queue the request for softirq completion, which is long - * after the request has been unhashed (and even removed from - * the dispatch list). - */ - union { - struct hlist_node hash; /* merge hash */ - struct llist_node ipi_list; - }; - - /* - * The rb_node is only used inside the io scheduler, requests - * are pruned when moved to the dispatch queue. So let the - * completion_data share space with the rb_node. - */ - union { - struct rb_node rb_node; /* sort/lookup */ - struct bio_vec special_vec; - void *completion_data; - int error_count; /* for legacy drivers, don't use */ - }; - - /* - * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. Flush requests are - * never put on the IO scheduler. So let the flush fields share - * space with the elevator data. - */ - union { - struct { - struct io_cq *icq; - void *priv[2]; - } elv; - - struct { - unsigned int seq; - struct list_head list; - rq_end_io_fn *saved_end_io; - } flush; - }; - - struct gendisk *rq_disk; - struct block_device *part; -#ifdef CONFIG_BLK_RQ_ALLOC_TIME - /* Time that the first bio started allocating this request. */ - u64 alloc_time_ns; -#endif - /* Time that this request was allocated for this IO. */ - u64 start_time_ns; - /* Time that I/O was submitted to the device. */ - u64 io_start_time_ns; - -#ifdef CONFIG_BLK_WBT - unsigned short wbt_flags; -#endif - /* - * rq sectors used for blk stats. It has the same value - * with blk_rq_sectors(rq), except that it never be zeroed - * by completion. - */ - unsigned short stats_sectors; - - /* - * Number of scatter-gather DMA addr+len pairs after - * physical address coalescing is performed. - */ - unsigned short nr_phys_segments; - -#if defined(CONFIG_BLK_DEV_INTEGRITY) - unsigned short nr_integrity_segments; -#endif - -#ifdef CONFIG_BLK_INLINE_ENCRYPTION - struct bio_crypt_ctx *crypt_ctx; - struct blk_ksm_keyslot *crypt_keyslot; -#endif - - unsigned short write_hint; - unsigned short ioprio; - - enum mq_rq_state state; - refcount_t ref; - - unsigned int timeout; - unsigned long deadline; - - union { - struct __call_single_data csd; - u64 fifo_time; - }; - - /* - * completion callback. - */ - rq_end_io_fn *end_io; - void *end_io_data; -}; - static inline bool blk_op_is_passthrough(unsigned int op) { op &= REQ_OP_MASK; return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } -static inline bool blk_rq_is_passthrough(struct request *rq) -{ - return blk_op_is_passthrough(req_op(rq)); -} - -static inline unsigned short req_get_ioprio(struct request *req) -{ - return req->ioprio; -} - -struct bio_vec; - -enum blk_eh_timer_return { - BLK_EH_DONE, /* drivers has completed the command */ - BLK_EH_RESET_TIMER, /* reset timer and try again */ -}; - -#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ -#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ - /* * Zoned block device models (zoned limit). * @@ -620,11 +415,6 @@ extern void blk_clear_pm_only(struct request_queue *q); #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) - -#define rq_dma_dir(rq) \ - (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) - #define dma_map_bvec(dev, bv, dir, attrs) \ dma_map_page_attrs(dev, (bv)->bv_page, (bv)->bv_offset, (bv)->bv_len, \ (dir), (attrs)) @@ -740,11 +530,6 @@ static inline unsigned int queue_max_active_zones(const struct request_queue *q) } #endif /* CONFIG_BLK_DEV_ZONED */ -static inline bool rq_is_sync(struct request *rq) -{ - return op_is_sync(rq->cmd_flags); -} - static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) @@ -759,83 +544,20 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) -struct rq_map_data { - struct page **pages; - int page_order; - int nr_entries; - unsigned long offset; - int null_mapped; - int from_user; -}; - -struct req_iterator { - struct bvec_iter iter; - struct bio *bio; -}; - /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) -#define __rq_for_each_bio(_bio, rq) \ - if ((rq->bio)) \ - for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) - -#define rq_for_each_segment(bvl, _rq, _iter) \ - __rq_for_each_bio(_iter.bio, _rq) \ - bio_for_each_segment(bvl, _iter.bio, _iter.iter) -#define rq_for_each_bvec(bvl, _rq, _iter) \ - __rq_for_each_bio(_iter.bio, _rq) \ - bio_for_each_bvec(bvl, _iter.bio, _iter.iter) - -#define rq_iter_last(bvec, _iter) \ - (_iter.bio->bi_next == NULL && \ - bio_iter_last(bvec, _iter.iter)) - -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" -#endif -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -extern void rq_flush_dcache_pages(struct request *rq); -#else -static inline void rq_flush_dcache_pages(struct request *rq) -{ -} -#endif extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); blk_qc_t submit_bio_noacct(struct bio *bio); -extern void blk_rq_init(struct request_queue *q, struct request *rq); -extern void blk_put_request(struct request *); -extern struct request *blk_get_request(struct request_queue *, unsigned int op, - blk_mq_req_flags_t flags); + extern int blk_lld_busy(struct request_queue *q); -extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, - struct bio_set *bs, gfp_t gfp_mask, - int (*bio_ctr)(struct bio *, struct bio *, void *), - void *data); -extern void blk_rq_unprep_clone(struct request *rq); -extern blk_status_t blk_insert_cloned_request(struct request_queue *q, - struct request *rq); -int blk_rq_append_bio(struct request *rq, struct bio *bio); extern void blk_queue_split(struct bio **); extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); -extern int blk_rq_map_user(struct request_queue *, struct request *, - struct rq_map_data *, void __user *, unsigned long, - gfp_t); -extern int blk_rq_unmap_user(struct bio *); -extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); -extern int blk_rq_map_user_iov(struct request_queue *, struct request *, - struct rq_map_data *, const struct iov_iter *, - gfp_t); -extern void blk_execute_rq_nowait(struct gendisk *, - struct request *, int, rq_end_io_fn *); - -blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, - int at_head); /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(unsigned int op); @@ -867,47 +589,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) #define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) #define SECTOR_MASK (PAGE_SECTORS - 1) -/* - * blk_rq_pos() : the current sector - * blk_rq_bytes() : bytes left in the entire request - * blk_rq_cur_bytes() : bytes left in the current segment - * blk_rq_err_bytes() : bytes left till the next error boundary - * blk_rq_sectors() : sectors left in the entire request - * blk_rq_cur_sectors() : sectors left in the current segment - * blk_rq_stats_sectors() : sectors of the entire request used for stats - */ -static inline sector_t blk_rq_pos(const struct request *rq) -{ - return rq->__sector; -} - -static inline unsigned int blk_rq_bytes(const struct request *rq) -{ - return rq->__data_len; -} - -static inline int blk_rq_cur_bytes(const struct request *rq) -{ - return rq->bio ? bio_cur_bytes(rq->bio) : 0; -} - -extern unsigned int blk_rq_err_bytes(const struct request *rq); - -static inline unsigned int blk_rq_sectors(const struct request *rq) -{ - return blk_rq_bytes(rq) >> SECTOR_SHIFT; -} - -static inline unsigned int blk_rq_cur_sectors(const struct request *rq) -{ - return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; -} - -static inline unsigned int blk_rq_stats_sectors(const struct request *rq) -{ - return rq->stats_sectors; -} - #ifdef CONFIG_BLK_DEV_ZONED /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ @@ -924,42 +605,8 @@ static inline unsigned int bio_zone_is_seq(struct bio *bio) return blk_queue_zone_is_seq(bdev_get_queue(bio->bi_bdev), bio->bi_iter.bi_sector); } - -static inline unsigned int blk_rq_zone_no(struct request *rq) -{ - return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); -} - -static inline unsigned int blk_rq_zone_is_seq(struct request *rq) -{ - return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); -} #endif /* CONFIG_BLK_DEV_ZONED */ -/* - * Some commands like WRITE SAME have a payload or data transfer size which - * is different from the size of the request. Any driver that supports such - * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to - * calculate the data transfer size. - */ -static inline unsigned int blk_rq_payload_bytes(struct request *rq) -{ - if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - return rq->special_vec.bv_len; - return blk_rq_bytes(rq); -} - -/* - * Return the first full biovec in the request. The caller needs to check that - * there are any bvecs before calling this helper. - */ -static inline struct bio_vec req_bvec(struct request *rq) -{ - if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - return rq->special_vec; - return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); -} - static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { @@ -999,30 +646,6 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, return min(q->limits.max_sectors, chunk_sectors); } -static inline unsigned int blk_rq_count_bios(struct request *rq) -{ - unsigned int nr_bios = 0; - struct bio *bio; - - __rq_for_each_bio(bio, rq) - nr_bios++; - - return nr_bios; -} - -void blk_steal_bios(struct bio_list *list, struct request *rq); - -/* - * Request completion related functions. - * - * blk_update_request() completes given number of bytes and updates - * the request without completing it. - */ -extern bool blk_update_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes); - -extern void blk_abort_request(struct request *); - /* * Access functions for manipulating queue properties */ @@ -1081,42 +704,6 @@ extern void blk_queue_required_elevator_features(struct request_queue *q, extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev); -/* - * Number of physical segments as sent to the device. - * - * Normally this is the number of discontiguous data segments sent by the - * submitter. But for data-less command like discard we might have no - * actual data segments submitted, but the driver might have to add it's - * own special payload. In that case we still return 1 here so that this - * special payload will be mapped. - */ -static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) -{ - if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - return 1; - return rq->nr_phys_segments; -} - -/* - * Number of discard segments (or ranges) the driver needs to fill in. - * Each discard bio merged into a request is counted as one segment. - */ -static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) -{ - return max_t(unsigned short, rq->nr_phys_segments, 1); -} - -int __blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist, struct scatterlist **last_sg); -static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist) -{ - struct scatterlist *last_sg = NULL; - - return __blk_rq_map_sg(q, rq, sglist, &last_sg); -} -extern void blk_dump_rq_flags(struct request *, char *); - bool __must_check blk_get_queue(struct request_queue *); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); @@ -1613,60 +1200,6 @@ extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); -#ifdef CONFIG_BLK_DEV_ZONED -bool blk_req_needs_zone_write_lock(struct request *rq); -bool blk_req_zone_write_trylock(struct request *rq); -void __blk_req_zone_write_lock(struct request *rq); -void __blk_req_zone_write_unlock(struct request *rq); - -static inline void blk_req_zone_write_lock(struct request *rq) -{ - if (blk_req_needs_zone_write_lock(rq)) - __blk_req_zone_write_lock(rq); -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ - if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) - __blk_req_zone_write_unlock(rq); -} - -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return rq->q->seq_zones_wlock && - test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - if (!blk_req_needs_zone_write_lock(rq)) - return true; - return !blk_req_zone_is_write_locked(rq); -} -#else -static inline bool blk_req_needs_zone_write_lock(struct request *rq) -{ - return false; -} - -static inline void blk_req_zone_write_lock(struct request *rq) -{ -} - -static inline void blk_req_zone_write_unlock(struct request *rq) -{ -} -static inline bool blk_req_zone_is_write_locked(struct request *rq) -{ - return false; -} - -static inline bool blk_req_can_dispatch_to_zone(struct request *rq) -{ - return true; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - static inline void blk_wake_io_task(struct task_struct *waiter) { /* diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index a083e15df608..22501a293fa5 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -2,7 +2,7 @@ #ifndef BLKTRACE_H #define BLKTRACE_H -#include +#include #include #include #include diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h index 96305a64a5a7..c635c2e014e3 100644 --- a/include/linux/t10-pi.h +++ b/include/linux/t10-pi.h @@ -3,7 +3,7 @@ #define _LINUX_T10_PI_H #include -#include +#include /* * A T10 PI-capable target device can be formatted with different diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index b97e142a7ca9..430b73bd02ac 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -5,7 +5,7 @@ #include #include #include -#include +#include #include #include #include -- cgit v1.2.3 From d2a27964e60ff18e637334864042af54de383902 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 5 Oct 2021 18:23:27 +0800 Subject: block: Rename BLKDEV_MAX_RQ -> BLKDEV_DEFAULT_RQ It is a bit confusing that there is BLKDEV_MAX_RQ and MAX_SCHED_RQ, as the name BLKDEV_MAX_RQ would imply the max requests always, which it is not. Rename to BLKDEV_MAX_RQ to BLKDEV_DEFAULT_RQ, matching its usage - that being the default number of requests assigned when allocating a request queue. Signed-off-by: John Garry Reviewed-by: Ming Lei Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/1633429419-228500-3-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- block/blk-mq-sched.c | 2 +- block/blk-mq-sched.h | 2 +- drivers/block/rbd.c | 2 +- include/linux/blk-mq.h | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 469550845244..2590e7724990 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -587,7 +587,7 @@ struct request_queue *blk_alloc_queue(int node_id) blk_queue_dma_alignment(q, 511); blk_set_default_limits(&q->limits); - q->nr_requests = BLKDEV_MAX_RQ; + q->nr_requests = BLKDEV_DEFAULT_RQ; return q; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 0f006cabfd91..2231fb0d4c35 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -606,7 +606,7 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) * Additionally, this is a per-hw queue depth. */ q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth, - BLKDEV_MAX_RQ); + BLKDEV_DEFAULT_RQ); queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_sched_alloc_tags(q, hctx, i); diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index 5181487db792..f6a1ce9e31f3 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -6,7 +6,7 @@ #include "blk-mq.h" #include "blk-mq-tag.h" -#define MAX_SCHED_RQ (16 * BLKDEV_MAX_RQ) +#define MAX_SCHED_RQ (16 * BLKDEV_DEFAULT_RQ) void blk_mq_sched_assign_ioc(struct request *rq); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index e65c9d706f6f..bf60aebd0cfb 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -836,7 +836,7 @@ struct rbd_options { u32 alloc_hint_flags; /* CEPH_OSD_OP_ALLOC_HINT_FLAG_* */ }; -#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ +#define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_DEFAULT_RQ #define RBD_ALLOC_SIZE_DEFAULT (64 * 1024) #define RBD_LOCK_TIMEOUT_DEFAULT 0 /* no timeout */ #define RBD_READ_ONLY_DEFAULT false diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index bd4086a6f28e..31cc41dfef6b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -12,7 +12,7 @@ struct blk_mq_tags; struct blk_flush_queue; #define BLKDEV_MIN_RQ 4 -#define BLKDEV_MAX_RQ 128 /* Default maximum */ +#define BLKDEV_DEFAULT_RQ 128 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3 From e155b0c238b20f0a866f4334d292656665836c8a Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 5 Oct 2021 18:23:37 +0800 Subject: blk-mq: Use shared tags for shared sbitmap support Currently we use separate sbitmap pairs and active_queues atomic_t for shared sbitmap support. However a full sets of static requests are used per HW queue, which is quite wasteful, considering that the total number of requests usable at any given time across all HW queues is limited by the shared sbitmap depth. As such, it is considerably more memory efficient in the case of shared sbitmap to allocate a set of static rqs per tag set or request queue, and not per HW queue. So replace the sbitmap pairs and active_queues atomic_t with a shared tags per tagset and request queue, which will hold a set of shared static rqs. Since there is now no valid HW queue index to be passed to the blk_mq_ops .init and .exit_request callbacks, pass an invalid index token. This changes the semantics of the APIs, such that the callback would need to validate the HW queue index before using it. Currently no user of shared sbitmap actually uses the HW queue index (as would be expected). Signed-off-by: John Garry Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/1633429419-228500-13-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 82 +++++++++++++++++++-------------------- block/blk-mq-tag.c | 63 ++++++++++-------------------- block/blk-mq-tag.h | 6 +-- block/blk-mq.c | 101 +++++++++++++++++++++++++------------------------ block/blk-mq.h | 7 ++-- include/linux/blk-mq.h | 15 ++++---- include/linux/blkdev.h | 3 +- 7 files changed, 125 insertions(+), 152 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index d1b56bb9ac64..428da4949d80 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -519,6 +519,11 @@ static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { + if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { + hctx->sched_tags = q->shared_sbitmap_tags; + return 0; + } + hctx->sched_tags = blk_mq_alloc_map_and_rqs(q->tag_set, hctx_idx, q->nr_requests); @@ -527,61 +532,54 @@ static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q, return 0; } +static void blk_mq_exit_sched_shared_sbitmap(struct request_queue *queue) +{ + blk_mq_free_rq_map(queue->shared_sbitmap_tags); + queue->shared_sbitmap_tags = NULL; +} + /* called in queue's release handler, tagset has gone away */ -static void blk_mq_sched_tags_teardown(struct request_queue *q) +static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int flags) { struct blk_mq_hw_ctx *hctx; int i; queue_for_each_hw_ctx(q, hctx, i) { if (hctx->sched_tags) { - blk_mq_free_rq_map(hctx->sched_tags, hctx->flags); + if (!blk_mq_is_sbitmap_shared(q->tag_set->flags)) + blk_mq_free_rq_map(hctx->sched_tags); hctx->sched_tags = NULL; } } + + if (blk_mq_is_sbitmap_shared(flags)) + blk_mq_exit_sched_shared_sbitmap(q); } static int blk_mq_init_sched_shared_sbitmap(struct request_queue *queue) { struct blk_mq_tag_set *set = queue->tag_set; - int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); - struct blk_mq_hw_ctx *hctx; - int ret, i; /* * Set initial depth at max so that we don't need to reallocate for * updating nr_requests. */ - ret = blk_mq_init_bitmaps(&queue->sched_bitmap_tags, - &queue->sched_breserved_tags, - MAX_SCHED_RQ, set->reserved_tags, - set->numa_node, alloc_policy); - if (ret) - return ret; - - queue_for_each_hw_ctx(queue, hctx, i) { - hctx->sched_tags->bitmap_tags = - &queue->sched_bitmap_tags; - hctx->sched_tags->breserved_tags = - &queue->sched_breserved_tags; - } + queue->shared_sbitmap_tags = blk_mq_alloc_map_and_rqs(set, + BLK_MQ_NO_HCTX_IDX, + MAX_SCHED_RQ); + if (!queue->shared_sbitmap_tags) + return -ENOMEM; blk_mq_tag_update_sched_shared_sbitmap(queue); return 0; } -static void blk_mq_exit_sched_shared_sbitmap(struct request_queue *queue) -{ - sbitmap_queue_free(&queue->sched_bitmap_tags); - sbitmap_queue_free(&queue->sched_breserved_tags); -} - int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) { + unsigned int i, flags = q->tag_set->flags; struct blk_mq_hw_ctx *hctx; struct elevator_queue *eq; - unsigned int i; int ret; if (!e) { @@ -598,21 +596,21 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth, BLKDEV_DEFAULT_RQ); - queue_for_each_hw_ctx(q, hctx, i) { - ret = blk_mq_sched_alloc_map_and_rqs(q, hctx, i); + if (blk_mq_is_sbitmap_shared(flags)) { + ret = blk_mq_init_sched_shared_sbitmap(q); if (ret) - goto err_free_map_and_rqs; + return ret; } - if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { - ret = blk_mq_init_sched_shared_sbitmap(q); + queue_for_each_hw_ctx(q, hctx, i) { + ret = blk_mq_sched_alloc_map_and_rqs(q, hctx, i); if (ret) goto err_free_map_and_rqs; } ret = e->ops.init_sched(q, e); if (ret) - goto err_free_sbitmap; + goto err_free_map_and_rqs; blk_mq_debugfs_register_sched(q); @@ -632,12 +630,10 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) return 0; -err_free_sbitmap: - if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) - blk_mq_exit_sched_shared_sbitmap(q); err_free_map_and_rqs: blk_mq_sched_free_rqs(q); - blk_mq_sched_tags_teardown(q); + blk_mq_sched_tags_teardown(q, flags); + q->elevator = NULL; return ret; } @@ -651,9 +647,15 @@ void blk_mq_sched_free_rqs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; int i; - queue_for_each_hw_ctx(q, hctx, i) { - if (hctx->sched_tags) - blk_mq_free_rqs(q->tag_set, hctx->sched_tags, i); + if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { + blk_mq_free_rqs(q->tag_set, q->shared_sbitmap_tags, + BLK_MQ_NO_HCTX_IDX); + } else { + queue_for_each_hw_ctx(q, hctx, i) { + if (hctx->sched_tags) + blk_mq_free_rqs(q->tag_set, + hctx->sched_tags, i); + } } } @@ -674,8 +676,6 @@ void blk_mq_exit_sched(struct request_queue *q, struct elevator_queue *e) blk_mq_debugfs_unregister_sched(q); if (e->type->ops.exit_sched) e->type->ops.exit_sched(e); - blk_mq_sched_tags_teardown(q); - if (blk_mq_is_sbitmap_shared(flags)) - blk_mq_exit_sched_shared_sbitmap(q); + blk_mq_sched_tags_teardown(q, flags); q->elevator = NULL; } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index a0ecc6d88f84..0e10e8404bf0 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -26,11 +26,10 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; - struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) - atomic_inc(&set->active_queues_shared_sbitmap); + atomic_inc(&hctx->tags->active_queues); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) @@ -57,14 +56,14 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; - struct request_queue *q = hctx->queue; - struct blk_mq_tag_set *set = q->tag_set; if (blk_mq_is_sbitmap_shared(hctx->flags)) { + struct request_queue *q = hctx->queue; + if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; - atomic_dec(&set->active_queues_shared_sbitmap); + atomic_dec(&tags->active_queues); } else { if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; @@ -510,38 +509,10 @@ static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, return 0; } -int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set) -{ - int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); - int i, ret; - - ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags, - set->queue_depth, set->reserved_tags, - set->numa_node, alloc_policy); - if (ret) - return ret; - - for (i = 0; i < set->nr_hw_queues; i++) { - struct blk_mq_tags *tags = set->tags[i]; - - tags->bitmap_tags = &set->__bitmap_tags; - tags->breserved_tags = &set->__breserved_tags; - } - - return 0; -} - -void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) -{ - sbitmap_queue_free(&set->__bitmap_tags); - sbitmap_queue_free(&set->__breserved_tags); -} - struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, - int node, unsigned int flags) + int node, int alloc_policy) { - int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags); struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { @@ -557,9 +528,6 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_reserved_tags = reserved_tags; spin_lock_init(&tags->lock); - if (blk_mq_is_sbitmap_shared(flags)) - return tags; - if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) { kfree(tags); return NULL; @@ -567,12 +535,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, return tags; } -void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags) +void blk_mq_free_tags(struct blk_mq_tags *tags) { - if (!blk_mq_is_sbitmap_shared(flags)) { - sbitmap_queue_free(tags->bitmap_tags); - sbitmap_queue_free(tags->breserved_tags); - } + sbitmap_queue_free(tags->bitmap_tags); + sbitmap_queue_free(tags->breserved_tags); kfree(tags); } @@ -603,6 +569,13 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, if (tdepth > MAX_SCHED_RQ) return -EINVAL; + /* + * Only the sbitmap needs resizing since we allocated the max + * initially. + */ + if (blk_mq_is_sbitmap_shared(set->flags)) + return 0; + new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth); if (!new) return -ENOMEM; @@ -623,12 +596,14 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) { - sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags); + struct blk_mq_tags *tags = set->shared_sbitmap_tags; + + sbitmap_queue_resize(&tags->__bitmap_tags, size - set->reserved_tags); } void blk_mq_tag_update_sched_shared_sbitmap(struct request_queue *q) { - sbitmap_queue_resize(&q->sched_bitmap_tags, + sbitmap_queue_resize(q->shared_sbitmap_tags->bitmap_tags, q->nr_requests - q->tag_set->reserved_tags); } diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index a9f5f1824819..e43f7589b96c 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -32,16 +32,14 @@ struct blk_mq_tags { extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, - int node, unsigned int flags); -extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); + int node, int alloc_policy); +extern void blk_mq_free_tags(struct blk_mq_tags *tags); extern int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, struct sbitmap_queue *breserved_tags, unsigned int queue_depth, unsigned int reserved, int node, int alloc_policy); -extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set); -extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); diff --git a/block/blk-mq.c b/block/blk-mq.c index c27591a04c4f..5537375f6400 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2353,7 +2353,10 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, struct blk_mq_tags *drv_tags; struct page *page; - drv_tags = set->tags[hctx_idx]; + if (blk_mq_is_sbitmap_shared(set->flags)) + drv_tags = set->shared_sbitmap_tags; + else + drv_tags = set->tags[hctx_idx]; if (tags->static_rqs && set->ops->exit_request) { int i; @@ -2382,21 +2385,20 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, } } -void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags) +void blk_mq_free_rq_map(struct blk_mq_tags *tags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; - blk_mq_free_tags(tags, flags); + blk_mq_free_tags(tags); } static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, - unsigned int reserved_tags, - unsigned int flags) + unsigned int reserved_tags) { struct blk_mq_tags *tags; int node; @@ -2405,7 +2407,8 @@ static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, if (node == NUMA_NO_NODE) node = set->numa_node; - tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags); + tags = blk_mq_init_tags(nr_tags, reserved_tags, node, + BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); if (!tags) return NULL; @@ -2413,7 +2416,7 @@ static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) { - blk_mq_free_tags(tags, flags); + blk_mq_free_tags(tags); return NULL; } @@ -2422,7 +2425,7 @@ static struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, node); if (!tags->static_rqs) { kfree(tags->rqs); - blk_mq_free_tags(tags, flags); + blk_mq_free_tags(tags); return NULL; } @@ -2864,14 +2867,13 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags; int ret; - tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags, - set->flags); + tags = blk_mq_alloc_rq_map(set, hctx_idx, depth, set->reserved_tags); if (!tags) return NULL; ret = blk_mq_alloc_rqs(set, tags, hctx_idx, depth); if (ret) { - blk_mq_free_rq_map(tags, set->flags); + blk_mq_free_rq_map(tags); return NULL; } @@ -2881,6 +2883,12 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, int hctx_idx) { + if (blk_mq_is_sbitmap_shared(set->flags)) { + set->tags[hctx_idx] = set->shared_sbitmap_tags; + + return true; + } + set->tags[hctx_idx] = blk_mq_alloc_map_and_rqs(set, hctx_idx, set->queue_depth); @@ -2891,14 +2899,21 @@ void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx) { - unsigned int flags = set->flags; - if (tags) { blk_mq_free_rqs(set, tags, hctx_idx); - blk_mq_free_rq_map(tags, flags); + blk_mq_free_rq_map(tags); } } +static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, + unsigned int hctx_idx) +{ + if (!blk_mq_is_sbitmap_shared(set->flags)) + blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx); + + set->tags[hctx_idx] = NULL; +} + static void blk_mq_map_swqueue(struct request_queue *q) { unsigned int i, j, hctx_idx; @@ -2976,10 +2991,8 @@ static void blk_mq_map_swqueue(struct request_queue *q) * fallback in case of a new remap fails * allocation */ - if (i && set->tags[i]) { - blk_mq_free_map_and_rqs(set, set->tags[i], i); - set->tags[i] = NULL; - } + if (i) + __blk_mq_free_map_and_rqs(set, i); hctx->tags = NULL; continue; @@ -3275,8 +3288,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx = hctxs[j]; if (hctx) { - blk_mq_free_map_and_rqs(set, set->tags[j], j); - set->tags[j] = NULL; + __blk_mq_free_map_and_rqs(set, j); blk_mq_exit_hctx(q, set, hctx, j); hctxs[j] = NULL; } @@ -3363,6 +3375,14 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; + if (blk_mq_is_sbitmap_shared(set->flags)) { + set->shared_sbitmap_tags = blk_mq_alloc_map_and_rqs(set, + BLK_MQ_NO_HCTX_IDX, + set->queue_depth); + if (!set->shared_sbitmap_tags) + return -ENOMEM; + } + for (i = 0; i < set->nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_rqs(set, i)) goto out_unwind; @@ -3372,9 +3392,12 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) return 0; out_unwind: - while (--i >= 0) { - blk_mq_free_map_and_rqs(set, set->tags[i], i); - set->tags[i] = NULL; + while (--i >= 0) + __blk_mq_free_map_and_rqs(set, i); + + if (blk_mq_is_sbitmap_shared(set->flags)) { + blk_mq_free_map_and_rqs(set, set->shared_sbitmap_tags, + BLK_MQ_NO_HCTX_IDX); } return -ENOMEM; @@ -3555,25 +3578,11 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (ret) goto out_free_mq_map; - if (blk_mq_is_sbitmap_shared(set->flags)) { - atomic_set(&set->active_queues_shared_sbitmap, 0); - - if (blk_mq_init_shared_sbitmap(set)) { - ret = -ENOMEM; - goto out_free_mq_rq_maps; - } - } - mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; -out_free_mq_rq_maps: - for (i = 0; i < set->nr_hw_queues; i++) { - blk_mq_free_map_and_rqs(set, set->tags[i], i); - set->tags[i] = NULL; - } out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); @@ -3605,13 +3614,13 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; - for (i = 0; i < set->nr_hw_queues; i++) { - blk_mq_free_map_and_rqs(set, set->tags[i], i); - set->tags[i] = NULL; - } + for (i = 0; i < set->nr_hw_queues; i++) + __blk_mq_free_map_and_rqs(set, i); - if (blk_mq_is_sbitmap_shared(set->flags)) - blk_mq_exit_shared_sbitmap(set); + if (blk_mq_is_sbitmap_shared(set->flags)) { + blk_mq_free_map_and_rqs(set, set->shared_sbitmap_tags, + BLK_MQ_NO_HCTX_IDX); + } for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); @@ -3649,12 +3658,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) if (hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); - if (blk_mq_is_sbitmap_shared(set->flags)) { - hctx->sched_tags->bitmap_tags = - &q->sched_bitmap_tags; - hctx->sched_tags->breserved_tags = - &q->sched_breserved_tags; - } } else { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); diff --git a/block/blk-mq.h b/block/blk-mq.h index bcb0ca89d37a..8824ae03215a 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -54,7 +54,7 @@ void blk_mq_put_rq_ref(struct request *rq); */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); -void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags); +void blk_mq_free_rq_map(struct blk_mq_tags *tags); struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int depth); void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, @@ -330,17 +330,16 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, if (blk_mq_is_sbitmap_shared(hctx->flags)) { struct request_queue *q = hctx->queue; - struct blk_mq_tag_set *set = q->tag_set; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return true; - users = atomic_read(&set->active_queues_shared_sbitmap); } else { if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return true; - users = atomic_read(&hctx->tags->active_queues); } + users = atomic_read(&hctx->tags->active_queues); + if (!users) return true; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 31cc41dfef6b..faa20a19bfcc 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -440,13 +440,11 @@ enum hctx_type { * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. - * @active_queues_shared_sbitmap: - * number of active request queues per tag set. - * @__bitmap_tags: A shared tags sbitmap, used over all hctx's - * @__breserved_tags: - * A shared reserved tags sbitmap, used over all hctx's * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. + * @shared_sbitmap_tags: + * Shared sbitmap set of tags. Has @nr_hw_queues elements. If + * set, shared by all @tags. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. @@ -463,12 +461,11 @@ struct blk_mq_tag_set { unsigned int timeout; unsigned int flags; void *driver_data; - atomic_t active_queues_shared_sbitmap; - struct sbitmap_queue __bitmap_tags; - struct sbitmap_queue __breserved_tags; struct blk_mq_tags **tags; + struct blk_mq_tags *shared_sbitmap_tags; + struct mutex tag_list_lock; struct list_head tag_list; }; @@ -640,6 +637,8 @@ enum { ((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \ << BLK_MQ_F_ALLOC_POLICY_START_BIT) +#define BLK_MQ_NO_HCTX_IDX (-1U) + struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, struct lock_class_key *lkclass); #define blk_mq_alloc_disk(set, queuedata) \ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0e960d74615e..cf92c13eb80e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -238,8 +238,7 @@ struct request_queue { atomic_t nr_active_requests_shared_sbitmap; - struct sbitmap_queue sched_bitmap_tags; - struct sbitmap_queue sched_breserved_tags; + struct blk_mq_tags *shared_sbitmap_tags; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP -- cgit v1.2.3 From 079a2e3e862548087041a1873bbffceb41a72a33 Mon Sep 17 00:00:00 2001 From: John Garry Date: Tue, 5 Oct 2021 18:23:39 +0800 Subject: blk-mq: Change shared sbitmap naming to shared tags Now that shared sbitmap support really means shared tags, rename symbols to match that. Signed-off-by: John Garry Link: https://lore.kernel.org/r/1633429419-228500-15-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- block/blk-mq-sched.c | 32 ++++++++++++++++---------------- block/blk-mq-tag.c | 18 +++++++++--------- block/blk-mq-tag.h | 4 ++-- block/blk-mq.c | 32 ++++++++++++++++---------------- block/blk-mq.h | 16 ++++++++-------- block/elevator.c | 2 +- include/linux/blk-mq.h | 8 ++++---- include/linux/blkdev.h | 4 ++-- 9 files changed, 59 insertions(+), 59 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 0ed17547bfed..b08aed26e6bb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -554,7 +554,7 @@ struct request_queue *blk_alloc_queue(int node_id) q->node = node_id; - atomic_set(&q->nr_active_requests_shared_sbitmap, 0); + atomic_set(&q->nr_active_requests_shared_tags, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 428da4949d80..27312da7d638 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -519,8 +519,8 @@ static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { - if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { - hctx->sched_tags = q->shared_sbitmap_tags; + if (blk_mq_is_shared_tags(q->tag_set->flags)) { + hctx->sched_tags = q->sched_shared_tags; return 0; } @@ -532,10 +532,10 @@ static int blk_mq_sched_alloc_map_and_rqs(struct request_queue *q, return 0; } -static void blk_mq_exit_sched_shared_sbitmap(struct request_queue *queue) +static void blk_mq_exit_sched_shared_tags(struct request_queue *queue) { - blk_mq_free_rq_map(queue->shared_sbitmap_tags); - queue->shared_sbitmap_tags = NULL; + blk_mq_free_rq_map(queue->sched_shared_tags); + queue->sched_shared_tags = NULL; } /* called in queue's release handler, tagset has gone away */ @@ -546,17 +546,17 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int fla queue_for_each_hw_ctx(q, hctx, i) { if (hctx->sched_tags) { - if (!blk_mq_is_sbitmap_shared(q->tag_set->flags)) + if (!blk_mq_is_shared_tags(q->tag_set->flags)) blk_mq_free_rq_map(hctx->sched_tags); hctx->sched_tags = NULL; } } - if (blk_mq_is_sbitmap_shared(flags)) - blk_mq_exit_sched_shared_sbitmap(q); + if (blk_mq_is_shared_tags(flags)) + blk_mq_exit_sched_shared_tags(q); } -static int blk_mq_init_sched_shared_sbitmap(struct request_queue *queue) +static int blk_mq_init_sched_shared_tags(struct request_queue *queue) { struct blk_mq_tag_set *set = queue->tag_set; @@ -564,13 +564,13 @@ static int blk_mq_init_sched_shared_sbitmap(struct request_queue *queue) * Set initial depth at max so that we don't need to reallocate for * updating nr_requests. */ - queue->shared_sbitmap_tags = blk_mq_alloc_map_and_rqs(set, + queue->sched_shared_tags = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, MAX_SCHED_RQ); - if (!queue->shared_sbitmap_tags) + if (!queue->sched_shared_tags) return -ENOMEM; - blk_mq_tag_update_sched_shared_sbitmap(queue); + blk_mq_tag_update_sched_shared_tags(queue); return 0; } @@ -596,8 +596,8 @@ int blk_mq_init_sched(struct request_queue *q, struct elevator_type *e) q->nr_requests = 2 * min_t(unsigned int, q->tag_set->queue_depth, BLKDEV_DEFAULT_RQ); - if (blk_mq_is_sbitmap_shared(flags)) { - ret = blk_mq_init_sched_shared_sbitmap(q); + if (blk_mq_is_shared_tags(flags)) { + ret = blk_mq_init_sched_shared_tags(q); if (ret) return ret; } @@ -647,8 +647,8 @@ void blk_mq_sched_free_rqs(struct request_queue *q) struct blk_mq_hw_ctx *hctx; int i; - if (blk_mq_is_sbitmap_shared(q->tag_set->flags)) { - blk_mq_free_rqs(q->tag_set, q->shared_sbitmap_tags, + if (blk_mq_is_shared_tags(q->tag_set->flags)) { + blk_mq_free_rqs(q->tag_set, q->sched_shared_tags, BLK_MQ_NO_HCTX_IDX); } else { queue_for_each_hw_ctx(q, hctx, i) { diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 211068a5f676..72a2724a4eee 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -24,7 +24,7 @@ */ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { - if (blk_mq_is_sbitmap_shared(hctx->flags)) { + if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && @@ -57,19 +57,19 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; - if (blk_mq_is_sbitmap_shared(hctx->flags)) { + if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) return; - atomic_dec(&tags->active_queues); } else { if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) return; - atomic_dec(&tags->active_queues); } + atomic_dec(&tags->active_queues); + blk_mq_tag_wakeup_all(tags, false); } @@ -557,7 +557,7 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, * Only the sbitmap needs resizing since we allocated the max * initially. */ - if (blk_mq_is_sbitmap_shared(set->flags)) + if (blk_mq_is_shared_tags(set->flags)) return 0; new = blk_mq_alloc_map_and_rqs(set, hctx->queue_num, tdepth); @@ -578,16 +578,16 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, return 0; } -void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) +void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size) { - struct blk_mq_tags *tags = set->shared_sbitmap_tags; + struct blk_mq_tags *tags = set->shared_tags; sbitmap_queue_resize(&tags->bitmap_tags, size - set->reserved_tags); } -void blk_mq_tag_update_sched_shared_sbitmap(struct request_queue *q) +void blk_mq_tag_update_sched_shared_tags(struct request_queue *q) { - sbitmap_queue_resize(&q->shared_sbitmap_tags->bitmap_tags, + sbitmap_queue_resize(&q->sched_shared_tags->bitmap_tags, q->nr_requests - q->tag_set->reserved_tags); } diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 1052d69147ba..d8ce89fa1686 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -43,9 +43,9 @@ extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); -extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, +extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, unsigned int size); -extern void blk_mq_tag_update_sched_shared_sbitmap(struct request_queue *q); +extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q); extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, diff --git a/block/blk-mq.c b/block/blk-mq.c index e026e5ebe2c9..f7428e11b109 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2235,7 +2235,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); } else if (plug && (q->nr_hw_queues == 1 || - blk_mq_is_sbitmap_shared(rq->mq_hctx->flags) || + blk_mq_is_shared_tags(rq->mq_hctx->flags) || q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) { /* * Use plugging if we have a ->commit_rqs() hook as well, as @@ -2353,8 +2353,8 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, struct blk_mq_tags *drv_tags; struct page *page; - if (blk_mq_is_sbitmap_shared(set->flags)) - drv_tags = set->shared_sbitmap_tags; + if (blk_mq_is_shared_tags(set->flags)) + drv_tags = set->shared_tags; else drv_tags = set->tags[hctx_idx]; @@ -2883,8 +2883,8 @@ struct blk_mq_tags *blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, static bool __blk_mq_alloc_map_and_rqs(struct blk_mq_tag_set *set, int hctx_idx) { - if (blk_mq_is_sbitmap_shared(set->flags)) { - set->tags[hctx_idx] = set->shared_sbitmap_tags; + if (blk_mq_is_shared_tags(set->flags)) { + set->tags[hctx_idx] = set->shared_tags; return true; } @@ -2908,7 +2908,7 @@ void blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, static void __blk_mq_free_map_and_rqs(struct blk_mq_tag_set *set, unsigned int hctx_idx) { - if (!blk_mq_is_sbitmap_shared(set->flags)) + if (!blk_mq_is_shared_tags(set->flags)) blk_mq_free_map_and_rqs(set, set->tags[hctx_idx], hctx_idx); set->tags[hctx_idx] = NULL; @@ -3375,11 +3375,11 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; - if (blk_mq_is_sbitmap_shared(set->flags)) { - set->shared_sbitmap_tags = blk_mq_alloc_map_and_rqs(set, + if (blk_mq_is_shared_tags(set->flags)) { + set->shared_tags = blk_mq_alloc_map_and_rqs(set, BLK_MQ_NO_HCTX_IDX, set->queue_depth); - if (!set->shared_sbitmap_tags) + if (!set->shared_tags) return -ENOMEM; } @@ -3395,8 +3395,8 @@ out_unwind: while (--i >= 0) __blk_mq_free_map_and_rqs(set, i); - if (blk_mq_is_sbitmap_shared(set->flags)) { - blk_mq_free_map_and_rqs(set, set->shared_sbitmap_tags, + if (blk_mq_is_shared_tags(set->flags)) { + blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } @@ -3617,8 +3617,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) for (i = 0; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); - if (blk_mq_is_sbitmap_shared(set->flags)) { - blk_mq_free_map_and_rqs(set, set->shared_sbitmap_tags, + if (blk_mq_is_shared_tags(set->flags)) { + blk_mq_free_map_and_rqs(set, set->shared_tags, BLK_MQ_NO_HCTX_IDX); } @@ -3669,11 +3669,11 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } if (!ret) { q->nr_requests = nr; - if (blk_mq_is_sbitmap_shared(set->flags)) { + if (blk_mq_is_shared_tags(set->flags)) { if (q->elevator) - blk_mq_tag_update_sched_shared_sbitmap(q); + blk_mq_tag_update_sched_shared_tags(q); else - blk_mq_tag_resize_shared_sbitmap(set, nr); + blk_mq_tag_resize_shared_tags(set, nr); } } diff --git a/block/blk-mq.h b/block/blk-mq.h index 8824ae03215a..171e8cdcff54 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -157,7 +157,7 @@ struct blk_mq_alloc_data { struct blk_mq_hw_ctx *hctx; }; -static inline bool blk_mq_is_sbitmap_shared(unsigned int flags) +static inline bool blk_mq_is_shared_tags(unsigned int flags) { return flags & BLK_MQ_F_TAG_HCTX_SHARED; } @@ -217,24 +217,24 @@ static inline int blk_mq_get_rq_budget_token(struct request *rq) static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) { - if (blk_mq_is_sbitmap_shared(hctx->flags)) - atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap); + if (blk_mq_is_shared_tags(hctx->flags)) + atomic_inc(&hctx->queue->nr_active_requests_shared_tags); else atomic_inc(&hctx->nr_active); } static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) { - if (blk_mq_is_sbitmap_shared(hctx->flags)) - atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap); + if (blk_mq_is_shared_tags(hctx->flags)) + atomic_dec(&hctx->queue->nr_active_requests_shared_tags); else atomic_dec(&hctx->nr_active); } static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) { - if (blk_mq_is_sbitmap_shared(hctx->flags)) - return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap); + if (blk_mq_is_shared_tags(hctx->flags)) + return atomic_read(&hctx->queue->nr_active_requests_shared_tags); return atomic_read(&hctx->nr_active); } static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, @@ -328,7 +328,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, if (bt->sb.depth == 1) return true; - if (blk_mq_is_sbitmap_shared(hctx->flags)) { + if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) diff --git a/block/elevator.c b/block/elevator.c index 57be09cd7f6d..1f39f6e8ebb9 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -637,7 +637,7 @@ static struct elevator_type *elevator_get_default(struct request_queue *q) return NULL; if (q->nr_hw_queues != 1 && - !blk_mq_is_sbitmap_shared(q->tag_set->flags)) + !blk_mq_is_shared_tags(q->tag_set->flags)) return NULL; return elevator_get(q, "mq-deadline", false); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index faa20a19bfcc..75d75657df21 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -442,9 +442,9 @@ enum hctx_type { * tag set. * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. - * @shared_sbitmap_tags: - * Shared sbitmap set of tags. Has @nr_hw_queues elements. If - * set, shared by all @tags. + * @shared_tags: + * Shared set of tags. Has @nr_hw_queues elements. If set, + * shared by all @tags. * @tag_list_lock: Serializes tag_list accesses. * @tag_list: List of the request queues that use this tag set. See also * request_queue.tag_set_list. @@ -464,7 +464,7 @@ struct blk_mq_tag_set { struct blk_mq_tags **tags; - struct blk_mq_tags *shared_sbitmap_tags; + struct blk_mq_tags *shared_tags; struct mutex tag_list_lock; struct list_head tag_list; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf92c13eb80e..b19172db7eef 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -236,9 +236,9 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; - atomic_t nr_active_requests_shared_sbitmap; + atomic_t nr_active_requests_shared_tags; - struct blk_mq_tags *shared_sbitmap_tags; + struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP -- cgit v1.2.3 From ba0ffdd8ce48ad7f7e85191cd29f9674caca3745 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 6 Oct 2021 12:01:07 -0600 Subject: block: bump max plugged deferred size from 16 to 32 Particularly for NVMe with efficient deferred submission for many requests, there are nice benefits to be seen by bumping the default max plug count from 16 to 32. This is especially true for virtualized setups, where the submit part is more expensive. But can be noticed even on native hardware. Reduce the multiple queue factor from 4 to 2, since we're changing the default size. While changing it, move the defines into the block layer private header. These aren't values that anyone outside of the block layer uses, or should use. Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 ++-- block/blk.h | 6 ++++++ include/linux/blkdev.h | 2 -- 3 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 8e41d88fcb8a..d861a969b2e0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2152,14 +2152,14 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) } /* - * Allow 4x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple + * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple * queues. This is important for md arrays to benefit from merging * requests. */ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) { if (plug->multiple_queues) - return BLK_MAX_REQUEST_COUNT * 4; + return BLK_MAX_REQUEST_COUNT * 2; return BLK_MAX_REQUEST_COUNT; } diff --git a/block/blk.h b/block/blk.h index 7aaccbc26db4..019c50a140ba 100644 --- a/block/blk.h +++ b/block/blk.h @@ -224,6 +224,12 @@ bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, void blk_account_io_start(struct request *req); void blk_account_io_done(struct request *req, u64 now); +/* + * Plug flush limits + */ +#define BLK_MAX_REQUEST_COUNT 32 +#define BLK_PLUG_FLUSH_SIZE (128 * 1024) + /* * Internal elevator interface */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b19172db7eef..472b4ab007c6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -727,8 +727,6 @@ struct blk_plug { bool multiple_queues; bool nowait; }; -#define BLK_MAX_REQUEST_COUNT 16 -#define BLK_PLUG_FLUSH_SIZE (128 * 1024) struct blk_plug_cb; typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); -- cgit v1.2.3 From 47c122e35d7e43b14129ceb9ed3a7e67599978fa Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 6 Oct 2021 06:34:11 -0600 Subject: block: pre-allocate requests if plug is started and is a batch The caller typically has a good (or even exact) idea of how many requests it needs to submit. We can make the request/tag allocation a lot more efficient if we just allocate N requests/tags upfront when we queue the first bio from the batch. Provide a new plug start helper that allows the caller to specify how many IOs are expected. This sets plug->nr_ios, and we can use that for smarter request allocation. The plug provides a holding spot for requests, and request allocation will check it before calling into the normal request allocation path. The blk_finish_plug() is called, check if there are unused requests and free them. This should not happen in normal operations. The exception is if we get merging, then we may be left with requests that need freeing when done. This raises the per-core performance on my setup from ~5.8M to ~6.1M IOPS. Signed-off-by: Jens Axboe --- block/blk-core.c | 47 +++++++++++++++++++-------------- block/blk-mq.c | 70 +++++++++++++++++++++++++++++++++++++++++--------- block/blk-mq.h | 5 ++++ include/linux/blk-mq.h | 5 +++- include/linux/blkdev.h | 15 ++++++++++- 5 files changed, 109 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 3b5ee3f7cc1e..e25a1c3f8b76 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1632,6 +1632,31 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); +void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) +{ + struct task_struct *tsk = current; + + /* + * If this is a nested plug, don't actually assign it. + */ + if (tsk->plug) + return; + + INIT_LIST_HEAD(&plug->mq_list); + plug->cached_rq = NULL; + plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); + plug->rq_count = 0; + plug->multiple_queues = false; + plug->nowait = false; + INIT_LIST_HEAD(&plug->cb_list); + + /* + * Store ordering should not be needed here, since a potential + * preempt will imply a full memory barrier + */ + tsk->plug = plug; +} + /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized @@ -1657,25 +1682,7 @@ EXPORT_SYMBOL(kblockd_mod_delayed_work_on); */ void blk_start_plug(struct blk_plug *plug) { - struct task_struct *tsk = current; - - /* - * If this is a nested plug, don't actually assign it. - */ - if (tsk->plug) - return; - - INIT_LIST_HEAD(&plug->mq_list); - INIT_LIST_HEAD(&plug->cb_list); - plug->rq_count = 0; - plug->multiple_queues = false; - plug->nowait = false; - - /* - * Store ordering should not be needed here, since a potential - * preempt will imply a full memory barrier - */ - tsk->plug = plug; + blk_start_plug_nr_ios(plug, 1); } EXPORT_SYMBOL(blk_start_plug); @@ -1727,6 +1734,8 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) if (!list_empty(&plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); + if (unlikely(!from_schedule && plug->cached_rq)) + blk_mq_free_plug_rqs(plug); } /** diff --git a/block/blk-mq.c b/block/blk-mq.c index d861a969b2e0..d9f14d3c2b8c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -359,6 +359,7 @@ static struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data) struct request_queue *q = data->q; struct elevator_queue *e = q->elevator; u64 alloc_time_ns = 0; + struct request *rq; unsigned int tag; /* alloc_time includes depth and tag waits */ @@ -392,10 +393,21 @@ retry: * case just retry the hctx assignment and tag allocation as CPU hotplug * should have migrated us to an online CPU by now. */ - tag = blk_mq_get_tag(data); - if (tag == BLK_MQ_NO_TAG) { + do { + tag = blk_mq_get_tag(data); + if (tag != BLK_MQ_NO_TAG) { + rq = blk_mq_rq_ctx_init(data, tag, alloc_time_ns); + if (!--data->nr_tags) + return rq; + if (e || data->hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + return rq; + rq->rq_next = *data->cached_rq; + *data->cached_rq = rq; + data->flags |= BLK_MQ_REQ_NOWAIT; + continue; + } if (data->flags & BLK_MQ_REQ_NOWAIT) - return NULL; + break; /* * Give up the CPU and sleep for a random short time to ensure @@ -404,8 +416,15 @@ retry: */ msleep(3); goto retry; + } while (1); + + if (data->cached_rq) { + rq = *data->cached_rq; + *data->cached_rq = rq->rq_next; + return rq; } - return blk_mq_rq_ctx_init(data, tag, alloc_time_ns); + + return NULL; } struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, @@ -415,6 +434,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, .q = q, .flags = flags, .cmd_flags = op, + .nr_tags = 1, }; struct request *rq; int ret; @@ -443,6 +463,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, .q = q, .flags = flags, .cmd_flags = op, + .nr_tags = 1, }; u64 alloc_time_ns = 0; unsigned int cpu; @@ -544,6 +565,18 @@ void blk_mq_free_request(struct request *rq) } EXPORT_SYMBOL_GPL(blk_mq_free_request); +void blk_mq_free_plug_rqs(struct blk_plug *plug) +{ + while (plug->cached_rq) { + struct request *rq; + + rq = plug->cached_rq; + plug->cached_rq = rq->rq_next; + percpu_ref_get(&rq->q->q_usage_counter); + blk_mq_free_request(rq); + } +} + inline void __blk_mq_end_request(struct request *rq, blk_status_t error) { u64 now = 0; @@ -2185,6 +2218,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) const int is_flush_fua = op_is_flush(bio->bi_opf); struct blk_mq_alloc_data data = { .q = q, + .nr_tags = 1, }; struct request *rq; struct blk_plug *plug; @@ -2211,13 +2245,26 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) hipri = bio->bi_opf & REQ_HIPRI; - data.cmd_flags = bio->bi_opf; - rq = __blk_mq_alloc_request(&data); - if (unlikely(!rq)) { - rq_qos_cleanup(q, bio); - if (bio->bi_opf & REQ_NOWAIT) - bio_wouldblock_error(bio); - goto queue_exit; + plug = blk_mq_plug(q, bio); + if (plug && plug->cached_rq) { + rq = plug->cached_rq; + plug->cached_rq = rq->rq_next; + INIT_LIST_HEAD(&rq->queuelist); + data.hctx = rq->mq_hctx; + } else { + data.cmd_flags = bio->bi_opf; + if (plug) { + data.nr_tags = plug->nr_ios; + plug->nr_ios = 1; + data.cached_rq = &plug->cached_rq; + } + rq = __blk_mq_alloc_request(&data); + if (unlikely(!rq)) { + rq_qos_cleanup(q, bio); + if (bio->bi_opf & REQ_NOWAIT) + bio_wouldblock_error(bio); + goto queue_exit; + } } trace_block_getrq(bio); @@ -2236,7 +2283,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) return BLK_QC_T_NONE; } - plug = blk_mq_plug(q, bio); if (unlikely(is_flush_fua)) { /* Bypass scheduler for flush requests */ blk_insert_flush(rq); diff --git a/block/blk-mq.h b/block/blk-mq.h index 171e8cdcff54..5da970bb8865 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -125,6 +125,7 @@ extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q); extern int blk_mq_sysfs_register(struct request_queue *q); extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); +void blk_mq_free_plug_rqs(struct blk_plug *plug); void blk_mq_release(struct request_queue *q); @@ -152,6 +153,10 @@ struct blk_mq_alloc_data { unsigned int shallow_depth; unsigned int cmd_flags; + /* allocate multiple requests/tags in one go */ + unsigned int nr_tags; + struct request **cached_rq; + /* input & output parameter */ struct blk_mq_ctx *ctx; struct blk_mq_hw_ctx *hctx; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 75d75657df21..0e941f217578 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -90,7 +90,10 @@ struct request { struct bio *bio; struct bio *biotail; - struct list_head queuelist; + union { + struct list_head queuelist; + struct request *rq_next; + }; /* * The hash is used inside the scheduler, and killed once the diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 472b4ab007c6..17705c970d7e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -722,10 +722,17 @@ extern void blk_set_queue_dying(struct request_queue *); */ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ - struct list_head cb_list; /* md requires an unplug callback */ + + /* if ios_left is > 1, we can batch tag/rq allocations */ + struct request *cached_rq; + unsigned short nr_ios; + unsigned short rq_count; + bool multiple_queues; bool nowait; + + struct list_head cb_list; /* md requires an unplug callback */ }; struct blk_plug_cb; @@ -738,6 +745,7 @@ struct blk_plug_cb { extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size); extern void blk_start_plug(struct blk_plug *); +extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); @@ -772,6 +780,11 @@ long nr_blockdev_pages(void); struct blk_plug { }; +static inline void blk_start_plug_nr_ios(struct blk_plug *plug, + unsigned short nr_ios) +{ +} + static inline void blk_start_plug(struct blk_plug *plug) { } -- cgit v1.2.3 From 84b8514b46b417e299746b1297d3d0899e8539f3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 12:44:49 +0200 Subject: block: move the *blkdev_ioctl declarations out of blkdev.h These are only used inside of block/. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012104450.659013-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk.h | 4 ++++ include/linux/genhd.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/block/blk.h b/block/blk.h index 019c50a140ba..eadb2a640a69 100644 --- a/block/blk.h +++ b/block/blk.h @@ -405,6 +405,10 @@ static inline void bio_clear_hipri(struct bio *bio) bio->bi_opf &= ~REQ_HIPRI; } +int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, + unsigned long arg); +long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); + extern const struct address_space_operations def_blk_aops; #endif /* BLK_INTERNAL_H */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0b48a0cf4262..cd4038fd5743 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -281,10 +281,6 @@ bool bdev_check_media_change(struct block_device *bdev); int __invalidate_device(struct block_device *bdev, bool kill_dirty); void set_capacity(struct gendisk *disk, sector_t size); -/* for drivers/char/raw.c: */ -int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); - #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); -- cgit v1.2.3 From 9e8c0d0d4d21d2c2c60132e2c18a73d08a230b42 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:17:57 +0200 Subject: block: remove BIO_BUG_ON BIO_DEBUG is always defined, so just switch the two instances to use BUG_ON directly. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-2-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 4 ++-- include/linux/bio.h | 8 -------- 2 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index a6fb6a0b4295..35b875563c8b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -156,7 +156,7 @@ out: void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs) { - BIO_BUG_ON(nr_vecs > BIO_MAX_VECS); + BUG_ON(nr_vecs > BIO_MAX_VECS); if (nr_vecs == BIO_MAX_VECS) mempool_free(bv, pool); @@ -677,7 +677,7 @@ static void bio_alloc_cache_destroy(struct bio_set *bs) void bio_put(struct bio *bio) { if (unlikely(bio_flagged(bio, BIO_REFFED))) { - BIO_BUG_ON(!atomic_read(&bio->__bi_cnt)); + BUG_ON(!atomic_read(&bio->__bi_cnt)); if (!atomic_dec_and_test(&bio->__bi_cnt)) return; } diff --git a/include/linux/bio.h b/include/linux/bio.h index 00952e92eae1..65a356fa7110 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -11,14 +11,6 @@ #include #include -#define BIO_DEBUG - -#ifdef BIO_DEBUG -#define BIO_BUG_ON BUG_ON -#else -#define BIO_BUG_ON -#endif - #define BIO_MAX_VECS 256U static inline unsigned int bio_max_segs(unsigned int nr_segs) -- cgit v1.2.3 From 11d9cab1ca6ed08747c6c5a274c6a8e8307aefbc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:17:58 +0200 Subject: block: don't include in bio.h doesn't need any of the definitions from ioprio.h. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 65a356fa7110..ae94794d07c9 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -6,7 +6,6 @@ #define __LINUX_BIO_H #include -#include /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include #include -- cgit v1.2.3 From 8addffd657a956944c1b8a74a1c9aabcfc5b4530 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:17:59 +0200 Subject: block: move bio_mergeable out of bio.h bio_mergeable is only needed by I/O schedulers, so move it to blk-mq-sched.h. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-4-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq-sched.h | 5 +++++ include/linux/bio.h | 8 -------- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index c97b816c3800..fe252278ed9a 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -37,6 +37,11 @@ static inline void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) __blk_mq_sched_restart(hctx); } +static inline bool bio_mergeable(struct bio *bio) +{ + return !(bio->bi_opf & REQ_NOMERGE_FLAGS); +} + static inline bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) diff --git a/include/linux/bio.h b/include/linux/bio.h index ae94794d07c9..ec255f282994 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -69,14 +69,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio) bio_op(bio) == REQ_OP_WRITE_ZEROES; } -static inline bool bio_mergeable(struct bio *bio) -{ - if (bio->bi_opf & REQ_NOMERGE_FLAGS) - return false; - - return true; -} - static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio_has_data(bio)) -- cgit v1.2.3 From b6559d8f9fdd7f0e139161cffea2645bd8d084c6 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:18:00 +0200 Subject: block: fold bio_cur_bytes into blk_rq_cur_bytes Fold bio_cur_bytes into the only caller. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-5-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bio.h | 8 -------- include/linux/blk-mq.h | 6 +++++- 2 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index ec255f282994..cffd5eba401e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -69,14 +69,6 @@ static inline bool bio_no_advance_iter(const struct bio *bio) bio_op(bio) == REQ_OP_WRITE_ZEROES; } -static inline unsigned int bio_cur_bytes(struct bio *bio) -{ - if (bio_has_data(bio)) - return bio_iovec(bio).bv_len; - else /* dataless requests such as discard */ - return bio->bi_iter.bi_size; -} - static inline void *bio_data(struct bio *bio) { if (bio_has_data(bio)) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 0e941f217578..2219e9277118 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -927,7 +927,11 @@ static inline unsigned int blk_rq_bytes(const struct request *rq) static inline int blk_rq_cur_bytes(const struct request *rq) { - return rq->bio ? bio_cur_bytes(rq->bio) : 0; + if (!rq->bio) + return 0; + if (!bio_has_data(rq->bio)) /* dataless requests such as discard */ + return rq->bio->bi_iter.bi_size; + return bio_iovec(rq->bio).bv_len; } unsigned int blk_rq_err_bytes(const struct request *rq); -- cgit v1.2.3 From 9a6083becbe113ed1e28059ce659dc8ae71b33c3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:18:01 +0200 Subject: block: move bio_full out of bio.h bio_full is only used in bio.c, so move it there. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-6-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 17 +++++++++++++++++ include/linux/bio.h | 19 ------------------- 2 files changed, 17 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 35b875563c8b..7e2899071de2 100644 --- a/block/bio.c +++ b/block/bio.c @@ -772,6 +772,23 @@ const char *bio_devname(struct bio *bio, char *buf) } EXPORT_SYMBOL(bio_devname); +/** + * bio_full - check if the bio is full + * @bio: bio to check + * @len: length of one segment to be added + * + * Return true if @bio is full and one segment with @len bytes can't be + * added to the bio, otherwise return false + */ +static inline bool bio_full(struct bio *bio, unsigned len) +{ + if (bio->bi_vcnt >= bio->bi_max_vecs) + return true; + if (bio->bi_iter.bi_size > UINT_MAX - len) + return true; + return false; +} + static inline bool page_is_mergeable(const struct bio_vec *bv, struct page *page, unsigned int len, unsigned int off, bool *same_page) diff --git a/include/linux/bio.h b/include/linux/bio.h index cffd5eba401e..2ffc7c768091 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -77,25 +77,6 @@ static inline void *bio_data(struct bio *bio) return NULL; } -/** - * bio_full - check if the bio is full - * @bio: bio to check - * @len: length of one segment to be added - * - * Return true if @bio is full and one segment with @len bytes can't be - * added to the bio, otherwise return false - */ -static inline bool bio_full(struct bio *bio, unsigned len) -{ - if (bio->bi_vcnt >= bio->bi_max_vecs) - return true; - - if (bio->bi_iter.bi_size > UINT_MAX - len) - return true; - - return false; -} - static inline bool bio_next_segment(const struct bio *bio, struct bvec_iter_all *iter) { -- cgit v1.2.3 From 9774b39175fe3606ce2a836a47134c53b75681c9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:18:02 +0200 Subject: block: mark __bio_try_merge_page static Mark __bio_try_merge_page static and move it up a bit to avoid the need for a forward declaration. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-7-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 77 ++++++++++++++++++++++++++--------------------------- include/linux/bio.h | 2 -- 2 files changed, 38 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 7e2899071de2..c89e402356a5 100644 --- a/block/bio.c +++ b/block/bio.c @@ -808,6 +808,44 @@ static inline bool page_is_mergeable(const struct bio_vec *bv, return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE); } +/** + * __bio_try_merge_page - try appending data to an existing bvec. + * @bio: destination bio + * @page: start page to add + * @len: length of the data to add + * @off: offset of the data relative to @page + * @same_page: return if the segment has been merged inside the same page + * + * Try to add the data at @page + @off to the last bvec of @bio. This is a + * useful optimisation for file systems with a block size smaller than the + * page size. + * + * Warn if (@len, @off) crosses pages in case that @same_page is true. + * + * Return %true on success or %false on failure. + */ +static bool __bio_try_merge_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off, bool *same_page) +{ + if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) + return false; + + if (bio->bi_vcnt > 0) { + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + + if (page_is_mergeable(bv, page, len, off, same_page)) { + if (bio->bi_iter.bi_size > UINT_MAX - len) { + *same_page = false; + return false; + } + bv->bv_len += len; + bio->bi_iter.bi_size += len; + return true; + } + } + return false; +} + /* * Try to merge a page into a segment, while obeying the hardware segment * size limit. This is not for normal read/write bios, but for passthrough @@ -939,45 +977,6 @@ int bio_add_zone_append_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL_GPL(bio_add_zone_append_page); -/** - * __bio_try_merge_page - try appending data to an existing bvec. - * @bio: destination bio - * @page: start page to add - * @len: length of the data to add - * @off: offset of the data relative to @page - * @same_page: return if the segment has been merged inside the same page - * - * Try to add the data at @page + @off to the last bvec of @bio. This is a - * useful optimisation for file systems with a block size smaller than the - * page size. - * - * Warn if (@len, @off) crosses pages in case that @same_page is true. - * - * Return %true on success or %false on failure. - */ -bool __bio_try_merge_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int off, bool *same_page) -{ - if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) - return false; - - if (bio->bi_vcnt > 0) { - struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - - if (page_is_mergeable(bv, page, len, off, same_page)) { - if (bio->bi_iter.bi_size > UINT_MAX - len) { - *same_page = false; - return false; - } - bv->bv_len += len; - bio->bi_iter.bi_size += len; - return true; - } - } - return false; -} -EXPORT_SYMBOL_GPL(__bio_try_merge_page); - /** * __bio_add_page - add page(s) to a bio in a new segment * @bio: destination bio diff --git a/include/linux/bio.h b/include/linux/bio.h index 2ffc7c768091..faa0a2fabaf0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -425,8 +425,6 @@ extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset); -bool __bio_try_merge_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int off, bool *same_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); -- cgit v1.2.3 From ff18d77b5f0cf3e25aa13741eed4d788a13c04d7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:18:03 +0200 Subject: block: move bio_get_{first,last}_bvec out of bio.h bio_get_first_bvec and bio_get_last_bvec are only used in blk-merge.c, so move them there. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-8-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-merge.c | 31 +++++++++++++++++++++++++++++++ include/linux/bio.h | 31 ------------------------------- 2 files changed, 31 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/block/blk-merge.c b/block/blk-merge.c index bf7aedaad8f8..14ce19607cd8 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -15,6 +15,37 @@ #include "blk-rq-qos.h" #include "blk-throttle.h" +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + bio_get_first_bvec(bio, bv); + if (bv->bv_len == bio->bi_iter.bi_size) + return; /* this bio only has a single bvec */ + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} + static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) { diff --git a/include/linux/bio.h b/include/linux/bio.h index faa0a2fabaf0..4c5106f2ed57 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -221,37 +221,6 @@ static inline void bio_clear_flag(struct bio *bio, unsigned int bit) bio->bi_flags &= ~(1U << bit); } -static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) -{ - *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); -} - -static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) -{ - struct bvec_iter iter = bio->bi_iter; - int idx; - - bio_get_first_bvec(bio, bv); - if (bv->bv_len == bio->bi_iter.bi_size) - return; /* this bio only has a single bvec */ - - bio_advance_iter(bio, &iter, iter.bi_size); - - if (!iter.bi_bvec_done) - idx = iter.bi_idx - 1; - else /* in the middle of bvec */ - idx = iter.bi_idx; - - *bv = bio->bi_io_vec[idx]; - - /* - * iter.bi_bvec_done records actual length of the last bvec - * if this bio ends in the middle of one io vector - */ - if (iter.bi_bvec_done) - bv->bv_len = iter.bi_bvec_done; -} - static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); -- cgit v1.2.3 From 4f7ab09a1ca0bc955635705c359ab3021b405fd0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 18:18:04 +0200 Subject: block: mark bio_truncate static bio_truncate is only used in bio.c, so mark it static. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211012161804.991559-9-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 2 +- include/linux/bio.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index c89e402356a5..d5120451c36a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -546,7 +546,7 @@ EXPORT_SYMBOL(zero_fill_bio); * REQ_OP_READ, zero the truncated part. This function should only * be used for handling corner cases, such as bio eod. */ -void bio_truncate(struct bio *bio, unsigned new_size) +static void bio_truncate(struct bio *bio, unsigned new_size) { struct bio_vec bv; struct bvec_iter iter; diff --git a/include/linux/bio.h b/include/linux/bio.h index 4c5106f2ed57..d8d27742a75f 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -405,7 +405,6 @@ extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); -void bio_truncate(struct bio *bio, unsigned new_size); void guard_bio_eod(struct bio *bio); void zero_fill_bio(struct bio *bio); -- cgit v1.2.3 From 9672b0d43782047b1825a96bafee1b6aefa35bc2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 9 Oct 2021 13:02:23 -0600 Subject: sbitmap: add __sbitmap_queue_get_batch() The block layer tag allocation batching still calls into sbitmap to get each tag, but we can improve on that. Add __sbitmap_queue_get_batch(), which returns a mask of tags all at once, along with an offset for those tags. An example return would be 0xff, where bits 0..7 are set, with tag_offset == 128. The valid tags in this case would be 128..135. A batch is specific to an individual sbitmap_map, hence it cannot be larger than that. The requested number of tags is automatically reduced to the max that can be satisfied with a single map. On failure, 0 is returned. Caller should fall back to single tag allocation at that point/ Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 13 +++++++++++++ lib/sbitmap.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 2713e689ad66..e30b56023ead 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -426,6 +426,19 @@ void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth); */ int __sbitmap_queue_get(struct sbitmap_queue *sbq); +/** + * __sbitmap_queue_get_batch() - Try to allocate a batch of free bits + * @sbq: Bitmap queue to allocate from. + * @nr_tags: number of tags requested + * @offset: offset to add to returned bits + * + * Return: Mask of allocated tags, 0 if none are found. Each tag allocated is + * a bit in the mask returned, and the caller must add @offset to the value to + * get the absolute tag value. + */ +unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, + unsigned int *offset); + /** * __sbitmap_queue_get_shallow() - Try to allocate a free bit from a &struct * sbitmap_queue, limiting the depth used from each word, with preemption diff --git a/lib/sbitmap.c b/lib/sbitmap.c index b25db9be938a..f398e0ae548e 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -489,6 +489,57 @@ int __sbitmap_queue_get(struct sbitmap_queue *sbq) } EXPORT_SYMBOL_GPL(__sbitmap_queue_get); +unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags, + unsigned int *offset) +{ + struct sbitmap *sb = &sbq->sb; + unsigned int hint, depth; + unsigned long index, nr; + int i; + + if (unlikely(sb->round_robin)) + return 0; + + depth = READ_ONCE(sb->depth); + hint = update_alloc_hint_before_get(sb, depth); + + index = SB_NR_TO_INDEX(sb, hint); + + for (i = 0; i < sb->map_nr; i++) { + struct sbitmap_word *map = &sb->map[index]; + unsigned long get_mask; + + sbitmap_deferred_clear(map); + if (map->word == (1UL << (map->depth - 1)) - 1) + continue; + + nr = find_first_zero_bit(&map->word, map->depth); + if (nr + nr_tags <= map->depth) { + atomic_long_t *ptr = (atomic_long_t *) &map->word; + int map_tags = min_t(int, nr_tags, map->depth); + unsigned long val, ret; + + get_mask = ((1UL << map_tags) - 1) << nr; + do { + val = READ_ONCE(map->word); + ret = atomic_long_cmpxchg(ptr, val, get_mask | val); + } while (ret != val); + get_mask = (get_mask & ~ret) >> nr; + if (get_mask) { + *offset = nr + (index << sb->shift); + update_alloc_hint_after_get(sb, depth, hint, + *offset + map_tags - 1); + return get_mask; + } + } + /* Jump to next index. */ + if (++index >= sb->map_nr) + index = 0; + } + + return 0; +} + int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int shallow_depth) { -- cgit v1.2.3 From f70299f0d58e0e21f7f5f5ab27e601e8d3f0373e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:15 +0200 Subject: blk-mq: factor out a blk_qc_to_hctx helper Add a helper to get the hctx from a request_queue and cookie, and fold the blk_qc_t_to_queue_num helper into it as no other callers are left. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-6-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 +++++++- include/linux/blk_types.h | 5 ----- 2 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 97b911866de1..35b2ab0a373a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -65,6 +65,12 @@ static int blk_mq_poll_stats_bkt(const struct request *rq) return bucket; } +static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q, + blk_qc_t qc) +{ + return q->queue_hw_ctx[(qc & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT]; +} + /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. @@ -4071,7 +4077,7 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) if (current->plug) blk_flush_plug_list(current->plug, false); - hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; + hctx = blk_qc_to_hctx(q, cookie); /* * If we sleep, have the caller restart the poll loop to reset diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 3b967053e9f5..000351c5312a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -505,11 +505,6 @@ static inline bool blk_qc_t_valid(blk_qc_t cookie) return cookie != BLK_QC_T_NONE; } -static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) -{ - return (cookie & ~BLK_QC_T_INTERNAL) >> BLK_QC_T_SHIFT; -} - static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) { return cookie & ((1u << BLK_QC_T_SHIFT) - 1); -- cgit v1.2.3 From efbabbe121f96d4b1a98a2c2ef5d2e8f7fb41c87 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:17 +0200 Subject: blk-mq: remove blk_qc_t_to_tag and blk_qc_t_is_internal Merge both functions into their only caller to keep the blk-mq tag to blk_qc_t mapping as private as possible in blk-mq.c. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-8-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 +++++--- include/linux/blk_types.h | 10 ---------- 2 files changed, 5 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 636773056874..24a10c973f79 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -74,9 +74,11 @@ static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q, static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx, blk_qc_t qc) { - if (blk_qc_t_is_internal(qc)) - return blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(qc)); - return blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(qc)); + unsigned int tag = qc & ((1U << BLK_QC_T_SHIFT) - 1); + + if (qc & BLK_QC_T_INTERNAL) + return blk_mq_tag_to_rq(hctx->sched_tags, tag); + return blk_mq_tag_to_rq(hctx->tags, tag); } /* diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 000351c5312a..fb7c1477617b 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -505,16 +505,6 @@ static inline bool blk_qc_t_valid(blk_qc_t cookie) return cookie != BLK_QC_T_NONE; } -static inline unsigned int blk_qc_t_to_tag(blk_qc_t cookie) -{ - return cookie & ((1u << BLK_QC_T_SHIFT) - 1); -} - -static inline bool blk_qc_t_is_internal(blk_qc_t cookie) -{ - return (cookie & BLK_QC_T_INTERNAL) != 0; -} - struct blk_rq_stat { u64 mean; u64 min; -- cgit v1.2.3 From 28a1ae6b9daba6ac65700eeb38479bd6fadec089 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:18 +0200 Subject: blk-mq: remove blk_qc_t_valid Move the trivial check into the only caller. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-9-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 +- include/linux/blk_types.h | 5 ----- 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 24a10c973f79..7d0d947921a6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4098,7 +4098,7 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, */ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) { - if (!blk_qc_t_valid(cookie) || + if (cookie == BLK_QC_T_NONE || !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return 0; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index fb7c1477617b..5017ba8fc539 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -500,11 +500,6 @@ typedef unsigned int blk_qc_t; #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) -static inline bool blk_qc_t_valid(blk_qc_t cookie) -{ - return cookie != BLK_QC_T_NONE; -} - struct blk_rq_stat { u64 mean; u64 min; -- cgit v1.2.3 From ef99b2d37666b7a600baab9e1c4944436652b0a2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:19 +0200 Subject: block: replace the spin argument to blk_iopoll with a flags argument Switch the boolean spin argument to blk_poll to passing a set of flags instead. This will allow to control polling behavior in a more fine grained way. Signed-off-by: Christoph Hellwig Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-10-hch@lst.de [axboe: adapt to changed io_uring iopoll] Signed-off-by: Jens Axboe --- block/blk-exec.c | 2 +- block/blk-mq.c | 17 +++++++---------- block/fops.c | 8 ++++---- fs/io_uring.c | 9 +++++---- fs/iomap/direct-io.c | 6 +++--- include/linux/blkdev.h | 4 +++- include/linux/fs.h | 2 +- include/linux/iomap.h | 2 +- mm/page_io.c | 2 +- 9 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/block/blk-exec.c b/block/blk-exec.c index d6cd501c0d34..1fa7f25e5726 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -71,7 +71,7 @@ static bool blk_rq_is_poll(struct request *rq) static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { - blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), true); + blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), 0); cond_resched(); } while (!completion_done(wait)); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 7d0d947921a6..6609e10657a8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4052,7 +4052,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc) } static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, - bool spin) + unsigned int flags) { struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie); long state = get_current_state(); @@ -4075,7 +4075,7 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, if (task_is_running(current)) return 1; - if (ret < 0 || !spin) + if (ret < 0 || (flags & BLK_POLL_ONESHOT)) break; cpu_relax(); } while (!need_resched()); @@ -4088,15 +4088,13 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, * blk_poll - poll for IO completions * @q: the queue * @cookie: cookie passed back at IO submission time - * @spin: whether to spin for completions + * @flags: BLK_POLL_* flags that control the behavior * * Description: * Poll for completions on the passed in queue. Returns number of - * completed entries found. If @spin is true, then blk_poll will continue - * looping until at least one completion is found, unless the task is - * otherwise marked running (or we need to reschedule). + * completed entries found. */ -int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) +int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags) { if (cookie == BLK_QC_T_NONE || !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) @@ -4105,12 +4103,11 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) if (current->plug) blk_flush_plug_list(current->plug, false); - /* If specified not to spin, we also should not sleep. */ - if (spin && q->poll_nsec != BLK_MQ_POLL_CLASSIC) { + if (q->poll_nsec != BLK_MQ_POLL_CLASSIC) { if (blk_mq_poll_hybrid(q, cookie)) return 1; } - return blk_mq_poll_classic(q, cookie, spin); + return blk_mq_poll_classic(q, cookie, flags); } EXPORT_SYMBOL_GPL(blk_poll); diff --git a/block/fops.c b/block/fops.c index 15324f2e5a91..db8f2fe68dd2 100644 --- a/block/fops.c +++ b/block/fops.c @@ -108,7 +108,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, if (!READ_ONCE(bio.bi_private)) break; if (!(iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(bdev_get_queue(bdev), qc, true)) + !blk_poll(bdev_get_queue(bdev), qc, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); @@ -141,12 +141,12 @@ struct blkdev_dio { static struct bio_set blkdev_dio_pool; -static int blkdev_iopoll(struct kiocb *kiocb, bool wait) +static int blkdev_iopoll(struct kiocb *kiocb, unsigned int flags) { struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host); struct request_queue *q = bdev_get_queue(bdev); - return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait); + return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags); } static void blkdev_bio_end_io(struct bio *bio) @@ -297,7 +297,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (!READ_ONCE(dio->waiter)) break; - if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, true)) + if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/fs/io_uring.c b/fs/io_uring.c index d2e86788c872..541fec2bd49a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2457,14 +2457,15 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, long min) { struct io_kiocb *req, *tmp; + unsigned int poll_flags = 0; LIST_HEAD(done); - bool spin; /* * Only spin for completions if we don't have multiple devices hanging * off our complete list, and we're under the requested amount. */ - spin = !ctx->poll_multi_queue && *nr_events < min; + if (ctx->poll_multi_queue || *nr_events >= min) + poll_flags |= BLK_POLL_ONESHOT; list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { struct kiocb *kiocb = &req->rw.kiocb; @@ -2482,11 +2483,11 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, if (!list_empty(&done)) break; - ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin); + ret = kiocb->ki_filp->f_op->iopoll(kiocb, poll_flags); if (unlikely(ret < 0)) return ret; else if (ret) - spin = false; + poll_flags |= BLK_POLL_ONESHOT; /* iopoll may have completed current req */ if (READ_ONCE(req->iopoll_completed)) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 560ae967f70e..236aba256cd1 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -49,13 +49,13 @@ struct iomap_dio { }; }; -int iomap_dio_iopoll(struct kiocb *kiocb, bool spin) +int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags) { struct request_queue *q = READ_ONCE(kiocb->private); if (!q) return 0; - return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin); + return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags); } EXPORT_SYMBOL_GPL(iomap_dio_iopoll); @@ -642,7 +642,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (!(iocb->ki_flags & IOCB_HIPRI) || !dio->submit.last_queue || !blk_poll(dio->submit.last_queue, - dio->submit.cookie, true)) + dio->submit.cookie, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 17705c970d7e..e177346bc020 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -564,7 +564,9 @@ extern const char *blk_op_str(unsigned int op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); -int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); +/* only poll the hardware once, don't continue until a completion was found */ +#define BLK_POLL_ONESHOT (1 << 0) +int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { diff --git a/include/linux/fs.h b/include/linux/fs.h index e7a633353fd2..c443cddf414f 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2075,7 +2075,7 @@ struct file_operations { ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); - int (*iopoll)(struct kiocb *kiocb, bool spin); + int (*iopoll)(struct kiocb *kiocb, unsigned int flags); int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 24f8489583ca..1e86b65567c2 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -337,7 +337,7 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags); ssize_t iomap_dio_complete(struct iomap_dio *dio); -int iomap_dio_iopoll(struct kiocb *kiocb, bool spin); +int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags); #ifdef CONFIG_SWAP struct file; diff --git a/mm/page_io.c b/mm/page_io.c index c493ce9ebcf5..5d5543fcefa4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -428,7 +428,7 @@ int swap_readpage(struct page *page, bool synchronous) if (!READ_ONCE(bio->bi_private)) break; - if (!blk_poll(disk->queue, qc, true)) + if (!blk_poll(disk->queue, qc, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From d729cf9acb9311956c8a37113dcfa0160a2d9665 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:20 +0200 Subject: io_uring: don't sleep when polling for I/O There is no point in sleeping for the expected I/O completion timeout in the io_uring async polling model as we never poll for a specific I/O. Signed-off-by: Christoph Hellwig Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-11-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 ++- fs/io_uring.c | 2 +- include/linux/blkdev.h | 2 ++ 3 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 6609e10657a8..97c24e461d0a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4103,7 +4103,8 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags) if (current->plug) blk_flush_plug_list(current->plug, false); - if (q->poll_nsec != BLK_MQ_POLL_CLASSIC) { + if (!(flags & BLK_POLL_NOSLEEP) && + q->poll_nsec != BLK_MQ_POLL_CLASSIC) { if (blk_mq_poll_hybrid(q, cookie)) return 1; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 541fec2bd49a..c5066146b8de 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2457,7 +2457,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, long min) { struct io_kiocb *req, *tmp; - unsigned int poll_flags = 0; + unsigned int poll_flags = BLK_POLL_NOSLEEP; LIST_HEAD(done); /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e177346bc020..2b80c98fc373 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -566,6 +566,8 @@ blk_status_t errno_to_blk_status(int errno); /* only poll the hardware once, don't continue until a completion was found */ #define BLK_POLL_ONESHOT (1 << 0) +/* do not sleep to wait for the expected completion time */ +#define BLK_POLL_NOSLEEP (1 << 1) int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) -- cgit v1.2.3 From 6ce913fe3eee14f40f778e85999c9e599dda8c6b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:21 +0200 Subject: block: rename REQ_HIPRI to REQ_POLLED Unlike the RWF_HIPRI userspace ABI which is intentionally kept vague, the bio flag is specific to the polling implementation, so rename and document it properly. Signed-off-by: Christoph Hellwig Reviewed-by: Sagi Grimberg Reviewed-by: Chaitanya Kulkarni Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-12-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- block/blk-merge.c | 3 +-- block/blk-mq-debugfs.c | 2 +- block/blk-mq.c | 4 ++-- block/blk-mq.h | 4 ++-- block/blk.h | 4 ++-- drivers/nvme/host/core.c | 2 +- drivers/scsi/scsi_debug.c | 10 +++++----- include/linux/bio.h | 2 +- include/linux/blk_types.h | 4 ++-- mm/page_io.c | 2 +- 11 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 80fa7aa394c7..8eb0e08d5395 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -842,7 +842,7 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) } if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) - bio_clear_hipri(bio); + bio_clear_polled(bio); switch (bio_op(bio)) { case REQ_OP_DISCARD: diff --git a/block/blk-merge.c b/block/blk-merge.c index 9b77b4d6c2a1..f88d7863f997 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -318,8 +318,7 @@ split: * iopoll in direct IO routine. Given performance gain of iopoll for * big IO can be trival, disable iopoll when split needed. */ - bio_clear_hipri(bio); - + bio_clear_polled(bio); return bio_split(bio, sectors, GFP_NOIO, bs); } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 3daea160d670..409a8256d9ff 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -287,7 +287,7 @@ static const char *const cmd_flag_name[] = { CMD_FLAG_NAME(BACKGROUND), CMD_FLAG_NAME(NOWAIT), CMD_FLAG_NAME(NOUNMAP), - CMD_FLAG_NAME(HIPRI), + CMD_FLAG_NAME(POLLED), }; #undef CMD_FLAG_NAME diff --git a/block/blk-mq.c b/block/blk-mq.c index 97c24e461d0a..a34ffcf861c3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -732,7 +732,7 @@ bool blk_mq_complete_request_remote(struct request *rq) * For a polled request, always complete locallly, it's pointless * to redirect the completion. */ - if (rq->cmd_flags & REQ_HIPRI) + if (rq->cmd_flags & REQ_POLLED) return false; if (blk_mq_complete_need_ipi(rq)) { @@ -2278,7 +2278,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) rq_qos_throttle(q, bio); - hipri = bio->bi_opf & REQ_HIPRI; + hipri = bio->bi_opf & REQ_POLLED; plug = blk_mq_plug(q, bio); if (plug && plug->cached_rq) { diff --git a/block/blk-mq.h b/block/blk-mq.h index 5da970bb8865..a9fe01e14951 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -106,9 +106,9 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, enum hctx_type type = HCTX_TYPE_DEFAULT; /* - * The caller ensure that if REQ_HIPRI, poll must be enabled. + * The caller ensure that if REQ_POLLED, poll must be enabled. */ - if (flags & REQ_HIPRI) + if (flags & REQ_POLLED) type = HCTX_TYPE_POLL; else if ((flags & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; diff --git a/block/blk.h b/block/blk.h index cab8d659d8a6..fa05d3f07976 100644 --- a/block/blk.h +++ b/block/blk.h @@ -416,11 +416,11 @@ extern struct device_attribute dev_attr_events; extern struct device_attribute dev_attr_events_async; extern struct device_attribute dev_attr_events_poll_msecs; -static inline void bio_clear_hipri(struct bio *bio) +static inline void bio_clear_polled(struct bio *bio) { /* can't support alloc cache if we turn off polling */ bio_clear_flag(bio, BIO_PERCPU_CACHE); - bio->bi_opf &= ~REQ_HIPRI; + bio->bi_opf &= ~REQ_POLLED; } long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 3d444b13cd69..ae15cb714596 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -632,7 +632,7 @@ static inline void nvme_init_request(struct request *req, req->cmd_flags |= REQ_FAILFAST_DRIVER; if (req->mq_hctx->type == HCTX_TYPE_POLL) - req->cmd_flags |= REQ_HIPRI; + req->cmd_flags |= REQ_POLLED; nvme_clear_nvme_request(req); memcpy(nvme_req(req)->cmd, cmd, sizeof(*cmd)); } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 66f507469a31..40b473eea357 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5384,7 +5384,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, { bool new_sd_dp; bool inject = false; - bool hipri = scsi_cmd_to_rq(cmnd)->cmd_flags & REQ_HIPRI; + bool polled = scsi_cmd_to_rq(cmnd)->cmd_flags & REQ_POLLED; int k, num_in_q, qdepth; unsigned long iflags; u64 ns_from_boot = 0; @@ -5471,7 +5471,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, if (sdebug_host_max_queue) sd_dp->hc_idx = get_tag(cmnd); - if (hipri) + if (polled) ns_from_boot = ktime_get_boottime_ns(); /* one of the resp_*() response functions is called here */ @@ -5531,7 +5531,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, kt -= d; } } - if (hipri) { + if (polled) { sd_dp->cmpl_ts = ktime_add(ns_to_ktime(ns_from_boot), kt); spin_lock_irqsave(&sqp->qc_lock, iflags); if (!sd_dp->init_poll) { @@ -5562,7 +5562,7 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, if (unlikely((sdebug_opts & SDEBUG_OPT_CMD_ABORT) && atomic_read(&sdeb_inject_pending))) sd_dp->aborted = true; - if (hipri) { + if (polled) { sd_dp->cmpl_ts = ns_to_ktime(ns_from_boot); spin_lock_irqsave(&sqp->qc_lock, iflags); if (!sd_dp->init_poll) { @@ -7331,7 +7331,7 @@ static int sdebug_blk_mq_poll(struct Scsi_Host *shost, unsigned int queue_num) if (kt_from_boot < sd_dp->cmpl_ts) continue; - } else /* ignoring non REQ_HIPRI requests */ + } else /* ignoring non REQ_POLLED requests */ continue; devip = (struct sdebug_dev_info *)scp->device->hostdata; if (likely(devip)) diff --git a/include/linux/bio.h b/include/linux/bio.h index d8d27742a75f..c7a2d880e927 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -706,7 +706,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page, */ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { - bio->bi_opf |= REQ_HIPRI; + bio->bi_opf |= REQ_POLLED; if (!is_sync_kiocb(kiocb)) bio->bi_opf |= REQ_NOWAIT; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5017ba8fc539..f8b9fce68834 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -384,7 +384,7 @@ enum req_flag_bits { /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_HIPRI, + __REQ_POLLED, /* caller polls for completion using blk_poll */ /* for driver use */ __REQ_DRV, @@ -409,7 +409,7 @@ enum req_flag_bits { #define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT) #define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP) -#define REQ_HIPRI (1ULL << __REQ_HIPRI) +#define REQ_POLLED (1ULL << __REQ_POLLED) #define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) diff --git a/mm/page_io.c b/mm/page_io.c index 5d5543fcefa4..ed2eded74f3a 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -416,7 +416,7 @@ int swap_readpage(struct page *page, bool synchronous) * attempt to access it in the page fault retry time check. */ if (synchronous) { - bio->bi_opf |= REQ_HIPRI; + bio->bi_opf |= REQ_POLLED; get_task_struct(current); bio->bi_private = current; } -- cgit v1.2.3 From 19416123ab3e1348b3532347af221d8f60838431 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 12 Oct 2021 13:12:23 +0200 Subject: block: define 'struct bvec_iter' as packed 'struct bvec_iter' is embedded into 'struct bio', define it as packed so that we can get one extra 4bytes for other uses without expanding bio. 'struct bvec_iter' is often allocated on stack, so making it packed doesn't affect performance. Also I have run io_uring on both nvme/null_blk, and not observe performance effect in this way. Suggested-by: Christoph Hellwig Signed-off-by: Ming Lei Reviewed-by: Sagi Grimberg Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-14-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/bvec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 0e9bdd42dafb..35c25dff651a 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -44,7 +44,7 @@ struct bvec_iter { unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ -}; +} __packed; struct bvec_iter_all { struct bio_vec bv; -- cgit v1.2.3 From 3e08773c3841e9db7a520908cc2b136a77d275ff Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 12 Oct 2021 13:12:24 +0200 Subject: block: switch polling to be bio based Replace the blk_poll interface that requires the caller to keep a queue and cookie from the submissions with polling based on the bio. Polling for the bio itself leads to a few advantages: - the cookie construction can made entirely private in blk-mq.c - the caller does not need to remember the request_queue and cookie separately and thus sidesteps their lifetime issues - keeping the device and the cookie inside the bio allows to trivially support polling BIOs remapping by stacking drivers - a lot of code to propagate the cookie back up the submission path can be removed entirely. Signed-off-by: Christoph Hellwig Tested-by: Mark Wunderlich Link: https://lore.kernel.org/r/20211012111226.760968-15-hch@lst.de Signed-off-by: Jens Axboe --- arch/m68k/emu/nfblock.c | 3 +- arch/xtensa/platforms/iss/simdisk.c | 3 +- block/bio.c | 1 + block/blk-core.c | 127 +++++++++++++++++++++++++++--------- block/blk-exec.c | 10 ++- block/blk-mq.c | 72 +++++++------------- block/blk-mq.h | 2 + block/fops.c | 25 +++---- drivers/block/brd.c | 12 ++-- drivers/block/drbd/drbd_int.h | 2 +- drivers/block/drbd/drbd_req.c | 3 +- drivers/block/n64cart.c | 12 ++-- drivers/block/null_blk/main.c | 3 +- drivers/block/pktcdvd.c | 7 +- drivers/block/ps3vram.c | 6 +- drivers/block/rsxx/dev.c | 7 +- drivers/block/zram/zram_drv.c | 10 +-- drivers/md/bcache/request.c | 13 ++-- drivers/md/bcache/request.h | 4 +- drivers/md/dm.c | 28 +++----- drivers/md/md.c | 10 ++- drivers/nvdimm/blk.c | 5 +- drivers/nvdimm/btt.c | 5 +- drivers/nvdimm/pmem.c | 3 +- drivers/nvme/host/multipath.c | 6 +- drivers/s390/block/dcssblk.c | 7 +- fs/btrfs/inode.c | 8 +-- fs/ext4/file.c | 2 +- fs/gfs2/file.c | 4 +- fs/iomap/direct-io.c | 36 ++++------ fs/xfs/xfs_file.c | 2 +- fs/zonefs/super.c | 2 +- include/linux/bio.h | 2 +- include/linux/blk-mq.h | 15 +---- include/linux/blk_types.h | 12 ++-- include/linux/blkdev.h | 8 ++- include/linux/fs.h | 6 +- include/linux/iomap.h | 5 +- mm/page_io.c | 8 +-- 39 files changed, 232 insertions(+), 264 deletions(-) (limited to 'include/linux') diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 9a8394e96388..4ef457ba5220 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -58,7 +58,7 @@ struct nfhd_device { struct gendisk *disk; }; -static blk_qc_t nfhd_submit_bio(struct bio *bio) +static void nfhd_submit_bio(struct bio *bio) { struct nfhd_device *dev = bio->bi_bdev->bd_disk->private_data; struct bio_vec bvec; @@ -76,7 +76,6 @@ static blk_qc_t nfhd_submit_bio(struct bio *bio) sec += len; } bio_endio(bio); - return BLK_QC_T_NONE; } static int nfhd_getgeo(struct block_device *bdev, struct hd_geometry *geo) diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 3cdfa00738e0..ddd1fe3db474 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -100,7 +100,7 @@ static void simdisk_transfer(struct simdisk *dev, unsigned long sector, spin_unlock(&dev->lock); } -static blk_qc_t simdisk_submit_bio(struct bio *bio) +static void simdisk_submit_bio(struct bio *bio) { struct simdisk *dev = bio->bi_bdev->bd_disk->private_data; struct bio_vec bvec; @@ -118,7 +118,6 @@ static blk_qc_t simdisk_submit_bio(struct bio *bio) } bio_endio(bio); - return BLK_QC_T_NONE; } static int simdisk_open(struct block_device *bdev, fmode_t mode) diff --git a/block/bio.c b/block/bio.c index df45f4b996ac..a3c9ff23a036 100644 --- a/block/bio.c +++ b/block/bio.c @@ -282,6 +282,7 @@ void bio_init(struct bio *bio, struct bio_vec *table, atomic_set(&bio->__bi_remaining, 1); atomic_set(&bio->__bi_cnt, 1); + bio->bi_cookie = BLK_QC_T_NONE; bio->bi_max_vecs = max_vecs; bio->bi_io_vec = table; diff --git a/block/blk-core.c b/block/blk-core.c index 8eb0e08d5395..f008c38ae967 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -915,25 +915,22 @@ end_io: return false; } -static blk_qc_t __submit_bio(struct bio *bio) +static void __submit_bio(struct bio *bio) { struct gendisk *disk = bio->bi_bdev->bd_disk; - blk_qc_t ret = BLK_QC_T_NONE; if (unlikely(bio_queue_enter(bio) != 0)) - return BLK_QC_T_NONE; + return; if (!submit_bio_checks(bio) || !blk_crypto_bio_prep(&bio)) goto queue_exit; - if (disk->fops->submit_bio) { - ret = disk->fops->submit_bio(bio); - goto queue_exit; + if (!disk->fops->submit_bio) { + blk_mq_submit_bio(bio); + return; } - return blk_mq_submit_bio(bio); - + disk->fops->submit_bio(bio); queue_exit: blk_queue_exit(disk->queue); - return ret; } /* @@ -955,10 +952,9 @@ queue_exit: * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio_bio, but that haven't been processed yet. */ -static blk_qc_t __submit_bio_noacct(struct bio *bio) +static void __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; - blk_qc_t ret = BLK_QC_T_NONE; BUG_ON(bio->bi_next); @@ -975,7 +971,7 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio) bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); - ret = __submit_bio(bio); + __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the @@ -998,22 +994,19 @@ static blk_qc_t __submit_bio_noacct(struct bio *bio) } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; - return ret; } -static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) +static void __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; - blk_qc_t ret; current->bio_list = bio_list; do { - ret = __submit_bio(bio); + __submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; - return ret; } /** @@ -1025,7 +1018,7 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) * systems and other upper level users of the block layer should use * submit_bio() instead. */ -blk_qc_t submit_bio_noacct(struct bio *bio) +void submit_bio_noacct(struct bio *bio) { /* * We only want one ->submit_bio to be active at a time, else stack @@ -1033,14 +1026,12 @@ blk_qc_t submit_bio_noacct(struct bio *bio) * to collect a list of requests submited by a ->submit_bio method while * it is active, and then process them after it returned. */ - if (current->bio_list) { + if (current->bio_list) bio_list_add(¤t->bio_list[0], bio); - return BLK_QC_T_NONE; - } - - if (!bio->bi_bdev->bd_disk->fops->submit_bio) - return __submit_bio_noacct_mq(bio); - return __submit_bio_noacct(bio); + else if (!bio->bi_bdev->bd_disk->fops->submit_bio) + __submit_bio_noacct_mq(bio); + else + __submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio_noacct); @@ -1057,10 +1048,10 @@ EXPORT_SYMBOL(submit_bio_noacct); * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has * been called. */ -blk_qc_t submit_bio(struct bio *bio) +void submit_bio(struct bio *bio) { if (blkcg_punt_bio_submit(bio)) - return BLK_QC_T_NONE; + return; /* * If it's a regular read/write or a barrier with data attached, @@ -1092,19 +1083,91 @@ blk_qc_t submit_bio(struct bio *bio) if (unlikely(bio_op(bio) == REQ_OP_READ && bio_flagged(bio, BIO_WORKINGSET))) { unsigned long pflags; - blk_qc_t ret; psi_memstall_enter(&pflags); - ret = submit_bio_noacct(bio); + submit_bio_noacct(bio); psi_memstall_leave(&pflags); - - return ret; + return; } - return submit_bio_noacct(bio); + submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); +/** + * bio_poll - poll for BIO completions + * @bio: bio to poll for + * @flags: BLK_POLL_* flags that control the behavior + * + * Poll for completions on queue associated with the bio. Returns number of + * completed entries found. + * + * Note: the caller must either be the context that submitted @bio, or + * be in a RCU critical section to prevent freeing of @bio. + */ +int bio_poll(struct bio *bio, unsigned int flags) +{ + struct request_queue *q = bio->bi_bdev->bd_disk->queue; + blk_qc_t cookie = READ_ONCE(bio->bi_cookie); + int ret; + + if (cookie == BLK_QC_T_NONE || + !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + return 0; + + if (current->plug) + blk_flush_plug_list(current->plug, false); + + if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT)) + return 0; + if (WARN_ON_ONCE(!queue_is_mq(q))) + ret = 0; /* not yet implemented, should not happen */ + else + ret = blk_mq_poll(q, cookie, flags); + blk_queue_exit(q); + return ret; +} +EXPORT_SYMBOL_GPL(bio_poll); + +/* + * Helper to implement file_operations.iopoll. Requires the bio to be stored + * in iocb->private, and cleared before freeing the bio. + */ +int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags) +{ + struct bio *bio; + int ret = 0; + + /* + * Note: the bio cache only uses SLAB_TYPESAFE_BY_RCU, so bio can + * point to a freshly allocated bio at this point. If that happens + * we have a few cases to consider: + * + * 1) the bio is beeing initialized and bi_bdev is NULL. We can just + * simply nothing in this case + * 2) the bio points to a not poll enabled device. bio_poll will catch + * this and return 0 + * 3) the bio points to a poll capable device, including but not + * limited to the one that the original bio pointed to. In this + * case we will call into the actual poll method and poll for I/O, + * even if we don't need to, but it won't cause harm either. + * + * For cases 2) and 3) above the RCU grace period ensures that bi_bdev + * is still allocated. Because partitions hold a reference to the whole + * device bdev and thus disk, the disk is also still valid. Grabbing + * a reference to the queue in bio_poll() ensures the hctxs and requests + * are still valid as well. + */ + rcu_read_lock(); + bio = READ_ONCE(kiocb->private); + if (bio && bio->bi_bdev) + ret = bio_poll(bio, flags); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL_GPL(iocb_bio_iopoll); + /** * blk_cloned_rq_check_limits - Helper function to check a cloned request * for the new queue limits diff --git a/block/blk-exec.c b/block/blk-exec.c index 1fa7f25e5726..55f0cd34b37b 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -65,13 +65,19 @@ EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); static bool blk_rq_is_poll(struct request *rq) { - return rq->mq_hctx && rq->mq_hctx->type == HCTX_TYPE_POLL; + if (!rq->mq_hctx) + return false; + if (rq->mq_hctx->type != HCTX_TYPE_POLL) + return false; + if (WARN_ON_ONCE(!rq->bio)) + return false; + return true; } static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { - blk_poll(rq->q, request_to_qc_t(rq->mq_hctx, rq), 0); + bio_poll(rq->bio, 0); cond_resched(); } while (!completion_done(wait)); } diff --git a/block/blk-mq.c b/block/blk-mq.c index a34ffcf861c3..0860f622099f 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -65,6 +65,9 @@ static int blk_mq_poll_stats_bkt(const struct request *rq) return bucket; } +#define BLK_QC_T_SHIFT 16 +#define BLK_QC_T_INTERNAL (1U << 31) + static inline struct blk_mq_hw_ctx *blk_qc_to_hctx(struct request_queue *q, blk_qc_t qc) { @@ -81,6 +84,13 @@ static inline struct request *blk_qc_to_rq(struct blk_mq_hw_ctx *hctx, return blk_mq_tag_to_rq(hctx->tags, tag); } +static inline blk_qc_t blk_rq_to_qc(struct request *rq) +{ + return (rq->mq_hctx->queue_num << BLK_QC_T_SHIFT) | + (rq->tag != -1 ? + rq->tag : (rq->internal_tag | BLK_QC_T_INTERNAL)); +} + /* * Check if any of the ctx, dispatch list or elevator * have pending work in this hardware queue. @@ -819,6 +829,8 @@ void blk_mq_start_request(struct request *rq) if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE) q->integrity.profile->prepare_fn(rq); #endif + if (rq->bio && rq->bio->bi_opf & REQ_POLLED) + WRITE_ONCE(rq->bio->bi_cookie, blk_rq_to_qc(rq)); } EXPORT_SYMBOL(blk_mq_start_request); @@ -2045,19 +2057,15 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, } static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, - struct request *rq, - blk_qc_t *cookie, bool last) + struct request *rq, bool last) { struct request_queue *q = rq->q; struct blk_mq_queue_data bd = { .rq = rq, .last = last, }; - blk_qc_t new_cookie; blk_status_t ret; - new_cookie = request_to_qc_t(hctx, rq); - /* * For OK queue, we are done. For error, caller may kill it. * Any other error (busy), just add it to our list as we @@ -2067,7 +2075,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, switch (ret) { case BLK_STS_OK: blk_mq_update_dispatch_busy(hctx, false); - *cookie = new_cookie; break; case BLK_STS_RESOURCE: case BLK_STS_DEV_RESOURCE: @@ -2076,7 +2083,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, break; default: blk_mq_update_dispatch_busy(hctx, false); - *cookie = BLK_QC_T_NONE; break; } @@ -2085,7 +2091,6 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx, static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, struct request *rq, - blk_qc_t *cookie, bool bypass_insert, bool last) { struct request_queue *q = rq->q; @@ -2119,7 +2124,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, goto insert; } - return __blk_mq_issue_directly(hctx, rq, cookie, last); + return __blk_mq_issue_directly(hctx, rq, last); insert: if (bypass_insert) return BLK_STS_RESOURCE; @@ -2133,7 +2138,6 @@ insert: * blk_mq_try_issue_directly - Try to send a request directly to device driver. * @hctx: Pointer of the associated hardware queue. * @rq: Pointer to request to be sent. - * @cookie: Request queue cookie. * * If the device has enough resources to accept a new request now, send the * request directly to device driver. Else, insert at hctx->dispatch queue, so @@ -2141,7 +2145,7 @@ insert: * queue have higher priority. */ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, - struct request *rq, blk_qc_t *cookie) + struct request *rq) { blk_status_t ret; int srcu_idx; @@ -2150,7 +2154,7 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, hctx_lock(hctx, &srcu_idx); - ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true); + ret = __blk_mq_try_issue_directly(hctx, rq, false, true); if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) blk_mq_request_bypass_insert(rq, false, true); else if (ret != BLK_STS_OK) @@ -2163,11 +2167,10 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last) { blk_status_t ret; int srcu_idx; - blk_qc_t unused_cookie; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; hctx_lock(hctx, &srcu_idx); - ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last); + ret = __blk_mq_try_issue_directly(hctx, rq, true, last); hctx_unlock(hctx, srcu_idx); return ret; @@ -2247,10 +2250,8 @@ static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug) * * It will not queue the request if there is an error with the bio, or at the * request creation. - * - * Returns: Request queue cookie. */ -blk_qc_t blk_mq_submit_bio(struct bio *bio) +void blk_mq_submit_bio(struct bio *bio) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; const int is_sync = op_is_sync(bio->bi_opf); @@ -2259,9 +2260,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) struct blk_plug *plug; struct request *same_queue_rq = NULL; unsigned int nr_segs; - blk_qc_t cookie; blk_status_t ret; - bool hipri; blk_queue_bounce(q, &bio); __blk_queue_split(&bio, &nr_segs); @@ -2278,8 +2277,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) rq_qos_throttle(q, bio); - hipri = bio->bi_opf & REQ_POLLED; - plug = blk_mq_plug(q, bio); if (plug && plug->cached_rq) { rq = plug->cached_rq; @@ -2310,8 +2307,6 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) rq_qos_track(q, rq, bio); - cookie = request_to_qc_t(rq->mq_hctx, rq); - blk_mq_bio_to_request(rq, bio, nr_segs); ret = blk_crypto_init_request(rq); @@ -2319,7 +2314,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) bio->bi_status = ret; bio_endio(bio); blk_mq_free_request(rq); - return BLK_QC_T_NONE; + return; } if (unlikely(is_flush_fua)) { @@ -2375,7 +2370,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) if (same_queue_rq) { trace_block_unplug(q, 1, true); blk_mq_try_issue_directly(same_queue_rq->mq_hctx, - same_queue_rq, &cookie); + same_queue_rq); } } else if ((q->nr_hw_queues > 1 && is_sync) || !rq->mq_hctx->dispatch_busy) { @@ -2383,18 +2378,15 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio) * There is no scheduler and we can try to send directly * to the hardware. */ - blk_mq_try_issue_directly(rq->mq_hctx, rq, &cookie); + blk_mq_try_issue_directly(rq->mq_hctx, rq); } else { /* Default case. */ blk_mq_sched_insert_request(rq, false, true, true); } - if (!hipri) - return BLK_QC_T_NONE; - return cookie; + return; queue_exit: blk_queue_exit(q); - return BLK_QC_T_NONE; } static size_t order_to_size(unsigned int order) @@ -4084,25 +4076,8 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, return 0; } -/** - * blk_poll - poll for IO completions - * @q: the queue - * @cookie: cookie passed back at IO submission time - * @flags: BLK_POLL_* flags that control the behavior - * - * Description: - * Poll for completions on the passed in queue. Returns number of - * completed entries found. - */ -int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags) +int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags) { - if (cookie == BLK_QC_T_NONE || - !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) - return 0; - - if (current->plug) - blk_flush_plug_list(current->plug, false); - if (!(flags & BLK_POLL_NOSLEEP) && q->poll_nsec != BLK_MQ_POLL_CLASSIC) { if (blk_mq_poll_hybrid(q, cookie)) @@ -4110,7 +4085,6 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags) } return blk_mq_poll_classic(q, cookie, flags); } -EXPORT_SYMBOL_GPL(blk_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { diff --git a/block/blk-mq.h b/block/blk-mq.h index a9fe01e14951..8be447995106 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -37,6 +37,8 @@ struct blk_mq_ctx { struct kobject kobj; } ____cacheline_aligned_in_smp; +void blk_mq_submit_bio(struct bio *bio); +int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags); void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); diff --git a/block/fops.c b/block/fops.c index db8f2fe68dd2..ce1255529ba2 100644 --- a/block/fops.c +++ b/block/fops.c @@ -61,7 +61,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, bool should_dirty = false; struct bio bio; ssize_t ret; - blk_qc_t qc; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) @@ -102,13 +101,12 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, if (iocb->ki_flags & IOCB_HIPRI) bio_set_polled(&bio, iocb); - qc = submit_bio(&bio); + submit_bio(&bio); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(bio.bi_private)) break; - if (!(iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(bdev_get_queue(bdev), qc, 0)) + if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); @@ -141,14 +139,6 @@ struct blkdev_dio { static struct bio_set blkdev_dio_pool; -static int blkdev_iopoll(struct kiocb *kiocb, unsigned int flags) -{ - struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host); - struct request_queue *q = bdev_get_queue(bdev); - - return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags); -} - static void blkdev_bio_end_io(struct bio *bio) { struct blkdev_dio *dio = bio->bi_private; @@ -162,6 +152,8 @@ static void blkdev_bio_end_io(struct bio *bio) struct kiocb *iocb = dio->iocb; ssize_t ret; + WRITE_ONCE(iocb->private, NULL); + if (likely(!dio->bio.bi_status)) { ret = dio->size; iocb->ki_pos += ret; @@ -200,7 +192,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, bool do_poll = (iocb->ki_flags & IOCB_HIPRI); bool is_read = (iov_iter_rw(iter) == READ), is_sync; loff_t pos = iocb->ki_pos; - blk_qc_t qc = BLK_QC_T_NONE; int ret = 0; if ((pos | iov_iter_alignment(iter)) & @@ -262,9 +253,9 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (!nr_pages) { if (do_poll) bio_set_polled(bio, iocb); - qc = submit_bio(bio); + submit_bio(bio); if (do_poll) - WRITE_ONCE(iocb->ki_cookie, qc); + WRITE_ONCE(iocb->private, bio); break; } if (!dio->multi_bio) { @@ -297,7 +288,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (!READ_ONCE(dio->waiter)) break; - if (!do_poll || !blk_poll(bdev_get_queue(bdev), qc, 0)) + if (!do_poll || !bio_poll(bio, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); @@ -594,7 +585,7 @@ const struct file_operations def_blk_fops = { .llseek = blkdev_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, - .iopoll = blkdev_iopoll, + .iopoll = iocb_bio_iopoll, .mmap = generic_file_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = blkdev_ioctl, diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 530b31240203..aa0472718dce 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -282,7 +282,7 @@ out: return err; } -static blk_qc_t brd_submit_bio(struct bio *bio) +static void brd_submit_bio(struct bio *bio) { struct brd_device *brd = bio->bi_bdev->bd_disk->private_data; sector_t sector = bio->bi_iter.bi_sector; @@ -299,16 +299,14 @@ static blk_qc_t brd_submit_bio(struct bio *bio) err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset, bio_op(bio), sector); - if (err) - goto io_error; + if (err) { + bio_io_error(bio); + return; + } sector += len >> SECTOR_SHIFT; } bio_endio(bio); - return BLK_QC_T_NONE; -io_error: - bio_io_error(bio); - return BLK_QC_T_NONE; } static int brd_rw_page(struct block_device *bdev, sector_t sector, diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 5d9181382ce1..6674a0b88341 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1448,7 +1448,7 @@ extern void conn_free_crypto(struct drbd_connection *connection); /* drbd_req */ extern void do_submit(struct work_struct *ws); extern void __drbd_make_request(struct drbd_device *, struct bio *); -extern blk_qc_t drbd_submit_bio(struct bio *bio); +void drbd_submit_bio(struct bio *bio); extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req); extern int is_valid_ar_handle(struct drbd_request *, sector_t); diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 5ca233644d70..3235532ae077 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -1596,7 +1596,7 @@ void do_submit(struct work_struct *ws) } } -blk_qc_t drbd_submit_bio(struct bio *bio) +void drbd_submit_bio(struct bio *bio) { struct drbd_device *device = bio->bi_bdev->bd_disk->private_data; @@ -1609,7 +1609,6 @@ blk_qc_t drbd_submit_bio(struct bio *bio) inc_ap_bio(device); __drbd_make_request(device, bio); - return BLK_QC_T_NONE; } static bool net_timeout_reached(struct drbd_request *net_req, diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 26798da661bd..b168ca25b6c9 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -84,7 +84,7 @@ static bool n64cart_do_bvec(struct device *dev, struct bio_vec *bv, u32 pos) return true; } -static blk_qc_t n64cart_submit_bio(struct bio *bio) +static void n64cart_submit_bio(struct bio *bio) { struct bio_vec bvec; struct bvec_iter iter; @@ -92,16 +92,14 @@ static blk_qc_t n64cart_submit_bio(struct bio *bio) u32 pos = bio->bi_iter.bi_sector << SECTOR_SHIFT; bio_for_each_segment(bvec, bio, iter) { - if (!n64cart_do_bvec(dev, &bvec, pos)) - goto io_error; + if (!n64cart_do_bvec(dev, &bvec, pos)) { + bio_io_error(bio); + return; + } pos += bvec.bv_len; } bio_endio(bio); - return BLK_QC_T_NONE; -io_error: - bio_io_error(bio); - return BLK_QC_T_NONE; } static const struct block_device_operations n64cart_fops = { diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 187d779c8ca0..e5cbcf582233 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1422,7 +1422,7 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb) return &nullb->queues[index]; } -static blk_qc_t null_submit_bio(struct bio *bio) +static void null_submit_bio(struct bio *bio) { sector_t sector = bio->bi_iter.bi_sector; sector_t nr_sectors = bio_sectors(bio); @@ -1434,7 +1434,6 @@ static blk_qc_t null_submit_bio(struct bio *bio) cmd->bio = bio; null_handle_cmd(cmd, sector, nr_sectors, bio_op(bio)); - return BLK_QC_T_NONE; } static bool should_timeout_request(struct request *rq) diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 0f26b2510a75..cb52cce6fb03 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2400,7 +2400,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) } } -static blk_qc_t pkt_submit_bio(struct bio *bio) +static void pkt_submit_bio(struct bio *bio) { struct pktcdvd_device *pd; char b[BDEVNAME_SIZE]; @@ -2423,7 +2423,7 @@ static blk_qc_t pkt_submit_bio(struct bio *bio) */ if (bio_data_dir(bio) == READ) { pkt_make_request_read(pd, bio); - return BLK_QC_T_NONE; + return; } if (!test_bit(PACKET_WRITABLE, &pd->flags)) { @@ -2455,10 +2455,9 @@ static blk_qc_t pkt_submit_bio(struct bio *bio) pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split); } while (split != bio); - return BLK_QC_T_NONE; + return; end_io: bio_io_error(bio); - return BLK_QC_T_NONE; } static void pkt_init_queue(struct pktcdvd_device *pd) diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index c7b19e128b03..d1ebf193cb9a 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -578,7 +578,7 @@ out: return next; } -static blk_qc_t ps3vram_submit_bio(struct bio *bio) +static void ps3vram_submit_bio(struct bio *bio) { struct ps3_system_bus_device *dev = bio->bi_bdev->bd_disk->private_data; struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); @@ -594,13 +594,11 @@ static blk_qc_t ps3vram_submit_bio(struct bio *bio) spin_unlock_irq(&priv->lock); if (busy) - return BLK_QC_T_NONE; + return; do { bio = ps3vram_do_bio(dev, bio); } while (bio); - - return BLK_QC_T_NONE; } static const struct block_device_operations ps3vram_fops = { diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 1cc40b0ea761..268252380e88 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -50,7 +50,7 @@ struct rsxx_bio_meta { static struct kmem_cache *bio_meta_pool; -static blk_qc_t rsxx_submit_bio(struct bio *bio); +static void rsxx_submit_bio(struct bio *bio); /*----------------- Block Device Operations -----------------*/ static int rsxx_blkdev_ioctl(struct block_device *bdev, @@ -120,7 +120,7 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card, } } -static blk_qc_t rsxx_submit_bio(struct bio *bio) +static void rsxx_submit_bio(struct bio *bio) { struct rsxx_cardinfo *card = bio->bi_bdev->bd_disk->private_data; struct rsxx_bio_meta *bio_meta; @@ -169,7 +169,7 @@ static blk_qc_t rsxx_submit_bio(struct bio *bio) if (st) goto queue_err; - return BLK_QC_T_NONE; + return; queue_err: kmem_cache_free(bio_meta_pool, bio_meta); @@ -177,7 +177,6 @@ req_err: if (st) bio->bi_status = st; bio_endio(bio); - return BLK_QC_T_NONE; } /*----------------- Device Setup -------------------*/ diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index fcaf2750f68f..a68297fb51a2 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1598,22 +1598,18 @@ static void __zram_make_request(struct zram *zram, struct bio *bio) /* * Handler function for all zram I/O requests. */ -static blk_qc_t zram_submit_bio(struct bio *bio) +static void zram_submit_bio(struct bio *bio) { struct zram *zram = bio->bi_bdev->bd_disk->private_data; if (!valid_io_request(zram, bio->bi_iter.bi_sector, bio->bi_iter.bi_size)) { atomic64_inc(&zram->stats.invalid_io); - goto error; + bio_io_error(bio); + return; } __zram_make_request(zram, bio); - return BLK_QC_T_NONE; - -error: - bio_io_error(bio); - return BLK_QC_T_NONE; } static void zram_slot_free_notify(struct block_device *bdev, diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 6d1de889baeb..23b28edae90f 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1163,7 +1163,7 @@ static void quit_max_writeback_rate(struct cache_set *c, /* Cached devices - read & write stuff */ -blk_qc_t cached_dev_submit_bio(struct bio *bio) +void cached_dev_submit_bio(struct bio *bio) { struct search *s; struct block_device *orig_bdev = bio->bi_bdev; @@ -1176,7 +1176,7 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio) dc->io_disable)) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); - return BLK_QC_T_NONE; + return; } if (likely(d->c)) { @@ -1222,8 +1222,6 @@ blk_qc_t cached_dev_submit_bio(struct bio *bio) } else /* I/O request sent to backing device */ detached_dev_do_request(d, bio, orig_bdev, start_time); - - return BLK_QC_T_NONE; } static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, @@ -1273,7 +1271,7 @@ static void flash_dev_nodata(struct closure *cl) continue_at(cl, search_free, NULL); } -blk_qc_t flash_dev_submit_bio(struct bio *bio) +void flash_dev_submit_bio(struct bio *bio) { struct search *s; struct closure *cl; @@ -1282,7 +1280,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio) if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); - return BLK_QC_T_NONE; + return; } s = search_alloc(bio, d, bio->bi_bdev, bio_start_io_acct(bio)); @@ -1298,7 +1296,7 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio) continue_at_nobarrier(&s->cl, flash_dev_nodata, bcache_wq); - return BLK_QC_T_NONE; + return; } else if (bio_data_dir(bio)) { bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys, &KEY(d->id, bio->bi_iter.bi_sector, 0), @@ -1314,7 +1312,6 @@ blk_qc_t flash_dev_submit_bio(struct bio *bio) } continue_at(cl, search_free, NULL); - return BLK_QC_T_NONE; } static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode, diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 82b38366a95d..38ab4856eaab 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -37,10 +37,10 @@ unsigned int bch_get_congested(const struct cache_set *c); void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); -blk_qc_t cached_dev_submit_bio(struct bio *bio); +void cached_dev_submit_bio(struct bio *bio); void bch_flash_dev_request_init(struct bcache_device *d); -blk_qc_t flash_dev_submit_bio(struct bio *bio); +void flash_dev_submit_bio(struct bio *bio); extern struct kmem_cache *bch_search_cache; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 76d9da49fda7..7870e6460633 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1183,14 +1183,13 @@ static noinline void __set_swap_bios_limit(struct mapped_device *md, int latch) mutex_unlock(&md->swap_bios_lock); } -static blk_qc_t __map_bio(struct dm_target_io *tio) +static void __map_bio(struct dm_target_io *tio) { int r; sector_t sector; struct bio *clone = &tio->clone; struct dm_io *io = tio->io; struct dm_target *ti = tio->ti; - blk_qc_t ret = BLK_QC_T_NONE; clone->bi_end_io = clone_endio; @@ -1226,7 +1225,7 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) case DM_MAPIO_REMAPPED: /* the bio has been remapped so dispatch it */ trace_block_bio_remap(clone, bio_dev(io->orig_bio), sector); - ret = submit_bio_noacct(clone); + submit_bio_noacct(clone); break; case DM_MAPIO_KILL: if (unlikely(swap_bios_limit(ti, clone))) { @@ -1248,8 +1247,6 @@ static blk_qc_t __map_bio(struct dm_target_io *tio) DMWARN("unimplemented target map return value: %d", r); BUG(); } - - return ret; } static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len) @@ -1336,7 +1333,7 @@ static void alloc_multiple_bios(struct bio_list *blist, struct clone_info *ci, } } -static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci, +static void __clone_and_map_simple_bio(struct clone_info *ci, struct dm_target_io *tio, unsigned *len) { struct bio *clone = &tio->clone; @@ -1346,8 +1343,7 @@ static blk_qc_t __clone_and_map_simple_bio(struct clone_info *ci, __bio_clone_fast(clone, ci->bio); if (len) bio_setup_sector(clone, ci->sector, *len); - - return __map_bio(tio); + __map_bio(tio); } static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, @@ -1361,7 +1357,7 @@ static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti, while ((bio = bio_list_pop(&blist))) { tio = container_of(bio, struct dm_target_io, clone); - (void) __clone_and_map_simple_bio(ci, tio, len); + __clone_and_map_simple_bio(ci, tio, len); } } @@ -1405,7 +1401,7 @@ static int __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti, free_tio(tio); return r; } - (void) __map_bio(tio); + __map_bio(tio); return 0; } @@ -1520,11 +1516,10 @@ static void init_clone_info(struct clone_info *ci, struct mapped_device *md, /* * Entry point to split a bio into clones and submit them to the targets. */ -static blk_qc_t __split_and_process_bio(struct mapped_device *md, +static void __split_and_process_bio(struct mapped_device *md, struct dm_table *map, struct bio *bio) { struct clone_info ci; - blk_qc_t ret = BLK_QC_T_NONE; int error = 0; init_clone_info(&ci, md, map, bio); @@ -1567,19 +1562,17 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, bio_chain(b, bio); trace_block_split(b, bio->bi_iter.bi_sector); - ret = submit_bio_noacct(bio); + submit_bio_noacct(bio); } } /* drop the extra reference count */ dm_io_dec_pending(ci.io, errno_to_blk_status(error)); - return ret; } -static blk_qc_t dm_submit_bio(struct bio *bio) +static void dm_submit_bio(struct bio *bio) { struct mapped_device *md = bio->bi_bdev->bd_disk->private_data; - blk_qc_t ret = BLK_QC_T_NONE; int srcu_idx; struct dm_table *map; @@ -1609,10 +1602,9 @@ static blk_qc_t dm_submit_bio(struct bio *bio) if (is_abnormal_io(bio)) blk_queue_split(&bio); - ret = __split_and_process_bio(md, map, bio); + __split_and_process_bio(md, map, bio); out: dm_put_live_table(md, srcu_idx); - return ret; } /*----------------------------------------------------------------- diff --git a/drivers/md/md.c b/drivers/md/md.c index ec09083ff0ef..22310d5d8d41 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -443,19 +443,19 @@ check_suspended: } EXPORT_SYMBOL(md_handle_request); -static blk_qc_t md_submit_bio(struct bio *bio) +static void md_submit_bio(struct bio *bio) { const int rw = bio_data_dir(bio); struct mddev *mddev = bio->bi_bdev->bd_disk->private_data; if (mddev == NULL || mddev->pers == NULL) { bio_io_error(bio); - return BLK_QC_T_NONE; + return; } if (unlikely(test_bit(MD_BROKEN, &mddev->flags)) && (rw == WRITE)) { bio_io_error(bio); - return BLK_QC_T_NONE; + return; } blk_queue_split(&bio); @@ -464,15 +464,13 @@ static blk_qc_t md_submit_bio(struct bio *bio) if (bio_sectors(bio) != 0) bio->bi_status = BLK_STS_IOERR; bio_endio(bio); - return BLK_QC_T_NONE; + return; } /* bio could be mergeable after passing to underlayer */ bio->bi_opf &= ~REQ_NOMERGE; md_handle_request(mddev, bio); - - return BLK_QC_T_NONE; } /* mddev_suspend makes sure no new requests are submitted diff --git a/drivers/nvdimm/blk.c b/drivers/nvdimm/blk.c index 088d3dd6f6fa..b6c6866f9259 100644 --- a/drivers/nvdimm/blk.c +++ b/drivers/nvdimm/blk.c @@ -162,7 +162,7 @@ static int nsblk_do_bvec(struct nd_namespace_blk *nsblk, return err; } -static blk_qc_t nd_blk_submit_bio(struct bio *bio) +static void nd_blk_submit_bio(struct bio *bio) { struct bio_integrity_payload *bip; struct nd_namespace_blk *nsblk = bio->bi_bdev->bd_disk->private_data; @@ -173,7 +173,7 @@ static blk_qc_t nd_blk_submit_bio(struct bio *bio) bool do_acct; if (!bio_integrity_prep(bio)) - return BLK_QC_T_NONE; + return; bip = bio_integrity(bio); rw = bio_data_dir(bio); @@ -199,7 +199,6 @@ static blk_qc_t nd_blk_submit_bio(struct bio *bio) bio_end_io_acct(bio, start); bio_endio(bio); - return BLK_QC_T_NONE; } static int nsblk_rw_bytes(struct nd_namespace_common *ndns, diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 92dec4952297..4295fa809420 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1440,7 +1440,7 @@ static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip, return ret; } -static blk_qc_t btt_submit_bio(struct bio *bio) +static void btt_submit_bio(struct bio *bio) { struct bio_integrity_payload *bip = bio_integrity(bio); struct btt *btt = bio->bi_bdev->bd_disk->private_data; @@ -1451,7 +1451,7 @@ static blk_qc_t btt_submit_bio(struct bio *bio) bool do_acct; if (!bio_integrity_prep(bio)) - return BLK_QC_T_NONE; + return; do_acct = blk_queue_io_stat(bio->bi_bdev->bd_disk->queue); if (do_acct) @@ -1483,7 +1483,6 @@ static blk_qc_t btt_submit_bio(struct bio *bio) bio_end_io_acct(bio, start); bio_endio(bio); - return BLK_QC_T_NONE; } static int btt_rw_page(struct block_device *bdev, sector_t sector, diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index ef4950f80832..a67a3ad1d413 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -190,7 +190,7 @@ static blk_status_t pmem_do_write(struct pmem_device *pmem, return rc; } -static blk_qc_t pmem_submit_bio(struct bio *bio) +static void pmem_submit_bio(struct bio *bio) { int ret = 0; blk_status_t rc = 0; @@ -229,7 +229,6 @@ static blk_qc_t pmem_submit_bio(struct bio *bio) bio->bi_status = errno_to_blk_status(ret); bio_endio(bio); - return BLK_QC_T_NONE; } static int pmem_rw_page(struct block_device *bdev, sector_t sector, diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fba06618c6c2..ab78aa5d28c6 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -312,12 +312,11 @@ static bool nvme_available_path(struct nvme_ns_head *head) return false; } -static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio) +static void nvme_ns_head_submit_bio(struct bio *bio) { struct nvme_ns_head *head = bio->bi_bdev->bd_disk->private_data; struct device *dev = disk_to_dev(head->disk); struct nvme_ns *ns; - blk_qc_t ret = BLK_QC_T_NONE; int srcu_idx; /* @@ -334,7 +333,7 @@ static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio) bio->bi_opf |= REQ_NVME_MPATH; trace_block_bio_remap(bio, disk_devt(ns->head->disk), bio->bi_iter.bi_sector); - ret = submit_bio_noacct(bio); + submit_bio_noacct(bio); } else if (nvme_available_path(head)) { dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n"); @@ -349,7 +348,6 @@ static blk_qc_t nvme_ns_head_submit_bio(struct bio *bio) } srcu_read_unlock(&head->srcu, srcu_idx); - return ret; } static int nvme_ns_head_open(struct block_device *bdev, fmode_t mode) diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 5be3d1c39a78..59e513d34b0f 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -30,7 +30,7 @@ static int dcssblk_open(struct block_device *bdev, fmode_t mode); static void dcssblk_release(struct gendisk *disk, fmode_t mode); -static blk_qc_t dcssblk_submit_bio(struct bio *bio); +static void dcssblk_submit_bio(struct bio *bio); static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); @@ -854,7 +854,7 @@ dcssblk_release(struct gendisk *disk, fmode_t mode) up_write(&dcssblk_devices_sem); } -static blk_qc_t +static void dcssblk_submit_bio(struct bio *bio) { struct dcssblk_dev_info *dev_info; @@ -907,10 +907,9 @@ dcssblk_submit_bio(struct bio *bio) bytes_done += bvec.bv_len; } bio_endio(bio); - return BLK_QC_T_NONE; + return; fail: bio_io_error(bio); - return BLK_QC_T_NONE; } static long diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4a9077c52444..04090ba0ef73 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8248,7 +8248,7 @@ static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio, return dip; } -static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter, +static void btrfs_submit_direct(const struct iomap_iter *iter, struct bio *dio_bio, loff_t file_offset) { struct inode *inode = iter->inode; @@ -8278,7 +8278,7 @@ static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter, } dio_bio->bi_status = BLK_STS_RESOURCE; bio_endio(dio_bio); - return BLK_QC_T_NONE; + return; } if (!write) { @@ -8372,15 +8372,13 @@ static blk_qc_t btrfs_submit_direct(const struct iomap_iter *iter, free_extent_map(em); } while (submit_len > 0); - return BLK_QC_T_NONE; + return; out_err_em: free_extent_map(em); out_err: dip->dio_bio->bi_status = status; btrfs_dio_private_put(dip); - - return BLK_QC_T_NONE; } const struct iomap_ops btrfs_dio_iomap_ops = { diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ac0e11bbb445..9c5559faacda 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -915,7 +915,7 @@ const struct file_operations ext4_file_operations = { .llseek = ext4_llseek, .read_iter = ext4_file_read_iter, .write_iter = ext4_file_write_iter, - .iopoll = iomap_dio_iopoll, + .iopoll = iocb_bio_iopoll, .unlocked_ioctl = ext4_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ext4_compat_ioctl, diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index c559827cb6f9..635f0e3f10ec 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -1353,7 +1353,7 @@ const struct file_operations gfs2_file_fops = { .llseek = gfs2_llseek, .read_iter = gfs2_file_read_iter, .write_iter = gfs2_file_write_iter, - .iopoll = iomap_dio_iopoll, + .iopoll = iocb_bio_iopoll, .unlocked_ioctl = gfs2_ioctl, .compat_ioctl = gfs2_compat_ioctl, .mmap = gfs2_mmap, @@ -1386,7 +1386,7 @@ const struct file_operations gfs2_file_fops_nolock = { .llseek = gfs2_llseek, .read_iter = gfs2_file_read_iter, .write_iter = gfs2_file_write_iter, - .iopoll = iomap_dio_iopoll, + .iopoll = iocb_bio_iopoll, .unlocked_ioctl = gfs2_ioctl, .compat_ioctl = gfs2_compat_ioctl, .mmap = gfs2_mmap, diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 236aba256cd1..8efab177011d 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -38,8 +38,7 @@ struct iomap_dio { struct { struct iov_iter *iter; struct task_struct *waiter; - struct request_queue *last_queue; - blk_qc_t cookie; + struct bio *poll_bio; } submit; /* used for aio completion: */ @@ -49,29 +48,20 @@ struct iomap_dio { }; }; -int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags) -{ - struct request_queue *q = READ_ONCE(kiocb->private); - - if (!q) - return 0; - return blk_poll(q, READ_ONCE(kiocb->ki_cookie), flags); -} -EXPORT_SYMBOL_GPL(iomap_dio_iopoll); - static void iomap_dio_submit_bio(const struct iomap_iter *iter, struct iomap_dio *dio, struct bio *bio, loff_t pos) { atomic_inc(&dio->ref); - if (dio->iocb->ki_flags & IOCB_HIPRI) + if (dio->iocb->ki_flags & IOCB_HIPRI) { bio_set_polled(bio, dio->iocb); + dio->submit.poll_bio = bio; + } - dio->submit.last_queue = bdev_get_queue(iter->iomap.bdev); if (dio->dops && dio->dops->submit_io) - dio->submit.cookie = dio->dops->submit_io(iter, bio, pos); + dio->dops->submit_io(iter, bio, pos); else - dio->submit.cookie = submit_bio(bio); + submit_bio(bio); } ssize_t iomap_dio_complete(struct iomap_dio *dio) @@ -164,9 +154,11 @@ static void iomap_dio_bio_end_io(struct bio *bio) } else if (dio->flags & IOMAP_DIO_WRITE) { struct inode *inode = file_inode(dio->iocb->ki_filp); + WRITE_ONCE(dio->iocb->private, NULL); INIT_WORK(&dio->aio.work, iomap_dio_complete_work); queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work); } else { + WRITE_ONCE(dio->iocb->private, NULL); iomap_dio_complete_work(&dio->aio.work); } } @@ -497,8 +489,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->submit.iter = iter; dio->submit.waiter = current; - dio->submit.cookie = BLK_QC_T_NONE; - dio->submit.last_queue = NULL; + dio->submit.poll_bio = NULL; if (iov_iter_rw(iter) == READ) { if (iomi.pos >= dio->i_size) @@ -611,8 +602,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (dio->flags & IOMAP_DIO_WRITE_FUA) dio->flags &= ~IOMAP_DIO_NEED_SYNC; - WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie); - WRITE_ONCE(iocb->private, dio->submit.last_queue); + WRITE_ONCE(iocb->private, dio->submit.poll_bio); /* * We are about to drop our additional submission reference, which @@ -639,10 +629,8 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (!READ_ONCE(dio->submit.waiter)) break; - if (!(iocb->ki_flags & IOCB_HIPRI) || - !dio->submit.last_queue || - !blk_poll(dio->submit.last_queue, - dio->submit.cookie, 0)) + if (!dio->submit.poll_bio || + !bio_poll(dio->submit.poll_bio, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 7aa943edfc02..62e7fbe4e54c 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1452,7 +1452,7 @@ const struct file_operations xfs_file_operations = { .write_iter = xfs_file_write_iter, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, - .iopoll = iomap_dio_iopoll, + .iopoll = iocb_bio_iopoll, .unlocked_ioctl = xfs_file_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = xfs_file_compat_ioctl, diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index ddc346a9df9b..3ce5f47338cb 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -1128,7 +1128,7 @@ static const struct file_operations zonefs_file_operations = { .write_iter = zonefs_file_write_iter, .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, - .iopoll = iomap_dio_iopoll, + .iopoll = iocb_bio_iopoll, }; static struct kmem_cache *zonefs_inode_cachep; diff --git a/include/linux/bio.h b/include/linux/bio.h index c7a2d880e927..62d684b7dd4c 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -349,7 +349,7 @@ static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned short nr_iovecs) return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } -extern blk_qc_t submit_bio(struct bio *); +void submit_bio(struct bio *bio); extern void bio_endio(struct bio *); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2219e9277118..a9c1d0882550 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -359,9 +359,9 @@ struct blk_mq_hw_ctx { /** @kobj: Kernel object for sysfs. */ struct kobject kobj; - /** @poll_considered: Count times blk_poll() was called. */ + /** @poll_considered: Count times blk_mq_poll() was called. */ unsigned long poll_considered; - /** @poll_invoked: Count how many requests blk_poll() polled. */ + /** @poll_invoked: Count how many requests blk_mq_poll() polled. */ unsigned long poll_invoked; /** @poll_success: Count how many polled requests were completed. */ unsigned long poll_success; @@ -815,16 +815,6 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq) for ((i) = 0; (i) < (hctx)->nr_ctx && \ ({ ctx = (hctx)->ctxs[(i)]; 1; }); (i)++) -static inline blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, - struct request *rq) -{ - if (rq->tag != -1) - return rq->tag | (hctx->queue_num << BLK_QC_T_SHIFT); - - return rq->internal_tag | (hctx->queue_num << BLK_QC_T_SHIFT) | - BLK_QC_T_INTERNAL; -} - static inline void blk_mq_cleanup_rq(struct request *rq) { if (rq->q->mq_ops->cleanup_rq) @@ -843,7 +833,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, rq->rq_disk = bio->bi_bdev->bd_disk; } -blk_qc_t blk_mq_submit_bio(struct bio *bio); void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, struct lock_class_key *key); diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f8b9fce68834..72736b4c057c 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -208,6 +208,9 @@ static inline void bio_issue_init(struct bio_issue *issue, ((u64)size << BIO_ISSUE_SIZE_SHIFT)); } +typedef unsigned int blk_qc_t; +#define BLK_QC_T_NONE -1U + /* * main unit of I/O for the block layer and lower layers (ie drivers and * stacking drivers) @@ -227,8 +230,8 @@ struct bio { struct bvec_iter bi_iter; + blk_qc_t bi_cookie; bio_end_io_t *bi_end_io; - void *bi_private; #ifdef CONFIG_BLK_CGROUP /* @@ -384,7 +387,7 @@ enum req_flag_bits { /* command specific flags for REQ_OP_WRITE_ZEROES: */ __REQ_NOUNMAP, /* do not free blocks when zeroing */ - __REQ_POLLED, /* caller polls for completion using blk_poll */ + __REQ_POLLED, /* caller polls for completion using bio_poll */ /* for driver use */ __REQ_DRV, @@ -495,11 +498,6 @@ static inline int op_stat_group(unsigned int op) return op_is_write(op); } -typedef unsigned int blk_qc_t; -#define BLK_QC_T_NONE -1U -#define BLK_QC_T_SHIFT 16 -#define BLK_QC_T_INTERNAL (1U << 31) - struct blk_rq_stat { u64 mean; u64 min; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2b80c98fc373..2a8689e949b4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -25,6 +25,7 @@ struct request; struct sg_io_hdr; struct blkcg_gq; struct blk_flush_queue; +struct kiocb; struct pr_ops; struct rq_qos; struct blk_queue_stats; @@ -550,7 +551,7 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -blk_qc_t submit_bio_noacct(struct bio *bio); +void submit_bio_noacct(struct bio *bio); extern int blk_lld_busy(struct request_queue *q); extern void blk_queue_split(struct bio **); @@ -568,7 +569,8 @@ blk_status_t errno_to_blk_status(int errno); #define BLK_POLL_ONESHOT (1 << 0) /* do not sleep to wait for the expected completion time */ #define BLK_POLL_NOSLEEP (1 << 1) -int blk_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags); +int bio_poll(struct bio *bio, unsigned int flags); +int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { @@ -1176,7 +1178,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { } struct block_device_operations { - blk_qc_t (*submit_bio) (struct bio *bio); + void (*submit_bio)(struct bio *bio); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); diff --git a/include/linux/fs.h b/include/linux/fs.h index c443cddf414f..f595f4097cb7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -334,11 +334,7 @@ struct kiocb { int ki_flags; u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ - union { - unsigned int ki_cookie; /* for ->iopoll */ - struct wait_page_queue *ki_waitq; /* for async buffered IO */ - }; - + struct wait_page_queue *ki_waitq; /* for async buffered IO */ randomized_struct_fields_end }; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 1e86b65567c2..63f4ea4dac9b 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -313,8 +313,8 @@ int iomap_writepages(struct address_space *mapping, struct iomap_dio_ops { int (*end_io)(struct kiocb *iocb, ssize_t size, int error, unsigned flags); - blk_qc_t (*submit_io)(const struct iomap_iter *iter, struct bio *bio, - loff_t file_offset); + void (*submit_io)(const struct iomap_iter *iter, struct bio *bio, + loff_t file_offset); }; /* @@ -337,7 +337,6 @@ struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags); ssize_t iomap_dio_complete(struct iomap_dio *dio); -int iomap_dio_iopoll(struct kiocb *kiocb, unsigned int flags); #ifdef CONFIG_SWAP struct file; diff --git a/mm/page_io.c b/mm/page_io.c index ed2eded74f3a..a68faab5b310 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -358,8 +358,6 @@ int swap_readpage(struct page *page, bool synchronous) struct bio *bio; int ret = 0; struct swap_info_struct *sis = page_swap_info(page); - blk_qc_t qc; - struct gendisk *disk; unsigned long pflags; VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page); @@ -409,8 +407,6 @@ int swap_readpage(struct page *page, bool synchronous) bio->bi_iter.bi_sector = swap_page_sector(page); bio->bi_end_io = end_swap_bio_read; bio_add_page(bio, page, thp_size(page), 0); - - disk = bio->bi_bdev->bd_disk; /* * Keep this task valid during swap readpage because the oom killer may * attempt to access it in the page fault retry time check. @@ -422,13 +418,13 @@ int swap_readpage(struct page *page, bool synchronous) } count_vm_event(PSWPIN); bio_get(bio); - qc = submit_bio(bio); + submit_bio(bio); while (synchronous) { set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(bio->bi_private)) break; - if (!blk_poll(disk->queue, qc, 0)) + if (!bio_poll(bio, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From 17220ca5ce9606c1b015c4316fca18734c2df0bb Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 14 Oct 2021 15:03:26 +0100 Subject: block: cache request queue in bdev There are tons of places where we need to get a request_queue only having bdev, which turns into bdev->bd_disk->queue. There are probably a hundred of such places considering inline helpers, and enough of them are in hot paths. Cache queue pointer in struct block_device and make use of it in bdev_get_queue(). Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a3bfaecdd28956f03629d0ca5c63ebc096e1c809.1634219547.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- block/bdev.c | 1 + block/genhd.c | 4 +++- include/linux/blk_types.h | 1 + include/linux/blkdev.h | 2 +- 4 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index 93b1188d7e58..fed8d0c041c7 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -493,6 +493,7 @@ struct block_device *bdev_alloc(struct gendisk *disk, u8 partno) spin_lock_init(&bdev->bd_size_lock); bdev->bd_partno = partno; bdev->bd_inode = inode; + bdev->bd_queue = disk->queue; bdev->bd_stats = alloc_percpu(struct disk_stats); if (!bdev->bd_stats) { iput(inode); diff --git a/block/genhd.c b/block/genhd.c index ffbdb9b24555..d148c38450d7 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1267,6 +1267,9 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, if (!disk->bdi) goto out_free_disk; + /* bdev_alloc() might need the queue, set before the first call */ + disk->queue = q; + disk->part0 = bdev_alloc(disk, 0); if (!disk->part0) goto out_free_bdi; @@ -1282,7 +1285,6 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, disk_to_dev(disk)->type = &disk_type; device_initialize(disk_to_dev(disk)); inc_diskseq(disk); - disk->queue = q; q->disk = disk; lockdep_init_map(&disk->lockdep_map, "(bio completion)", lkclass, 0); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 72736b4c057c..1e370929c89e 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -38,6 +38,7 @@ struct block_device { u8 bd_partno; spinlock_t bd_size_lock; /* for bd_inode->i_size updates */ struct gendisk * bd_disk; + struct request_queue * bd_queue; /* The counter of freeze processes */ int bd_fsfreeze_count; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2a8689e949b4..d5b21fc8f49e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -574,7 +574,7 @@ int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { - return bdev->bd_disk->queue; /* this is never NULL */ + return bdev->bd_queue; /* this is never NULL */ } /* -- cgit v1.2.3 From b5f9c644eb1baafcd349ad134e2110773f8d0a38 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Mon, 4 Oct 2021 14:59:35 +0200 Subject: PCI: Remove struct pci_dev->driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no remaining uses of the struct pci_dev->driver pointer, so remove it. Link: https://lore.kernel.org/r/20211004125935.2300113-12-u.kleine-koenig@pengutronix.de Signed-off-by: Uwe Kleine-König Signed-off-by: Bjorn Helgaas --- drivers/pci/pci-driver.c | 4 ---- include/linux/pci.h | 1 - 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index b919c5361694..3da121cb8cbf 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -319,12 +319,10 @@ static long local_pci_probe(void *_ddi) * its remove routine. */ pm_runtime_get_sync(dev); - pci_dev->driver = pci_drv; rc = pci_drv->probe(pci_dev, ddi->id); if (!rc) return rc; if (rc < 0) { - pci_dev->driver = NULL; pm_runtime_put_sync(dev); return rc; } @@ -390,7 +388,6 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, * @pci_dev: PCI device being probed * * returns 0 on success, else error. - * side-effect: pci_dev->driver is set to drv when drv claims pci_dev. */ static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev) { @@ -465,7 +462,6 @@ static void pci_device_remove(struct device *dev) pm_runtime_put_noidle(dev); } pcibios_free_irq(pci_dev); - pci_dev->driver = NULL; pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ diff --git a/include/linux/pci.h b/include/linux/pci.h index a2d62165a7f7..03bfdb25a55c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -342,7 +342,6 @@ struct pci_dev { u16 pcie_flags_reg; /* Cached PCIe Capabilities Register */ unsigned long *dma_alias_mask;/* Mask of enabled devfn aliases */ - struct pci_driver *driver; /* Driver bound to this device */ u64 dma_mask; /* Mask of the bits of bus address this device implements. Normally this is 0xffffffff. You only need to change -- cgit v1.2.3 From bb523b406c849eef8f265a07cd7f320f1f177743 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 2 Aug 2021 13:44:20 +0200 Subject: gup: Turn fault_in_pages_{readable,writeable} into fault_in_{readable,writeable} Turn fault_in_pages_{readable,writeable} into versions that return the number of bytes not faulted in, similar to copy_to_user, instead of returning a non-zero value when any of the requested pages couldn't be faulted in. This supports the existing users that require all pages to be faulted in as well as new users that are happy if any pages can be faulted in. Rename the functions to fault_in_{readable,writeable} to make sure this change doesn't silently break things. Neither of these functions is entirely trivial and it doesn't seem useful to inline them, so move them to mm/gup.c. Signed-off-by: Andreas Gruenbacher --- arch/powerpc/kernel/kvm.c | 3 +- arch/powerpc/kernel/signal_32.c | 4 +-- arch/powerpc/kernel/signal_64.c | 2 +- arch/x86/kernel/fpu/signal.c | 7 ++-- drivers/gpu/drm/armada/armada_gem.c | 7 ++-- fs/btrfs/ioctl.c | 5 ++- include/linux/pagemap.h | 57 ++--------------------------- lib/iov_iter.c | 10 +++--- mm/filemap.c | 2 +- mm/gup.c | 72 +++++++++++++++++++++++++++++++++++++ 10 files changed, 93 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c index d89cf802d9aa..6568823cf306 100644 --- a/arch/powerpc/kernel/kvm.c +++ b/arch/powerpc/kernel/kvm.c @@ -669,7 +669,8 @@ static void __init kvm_use_magic_page(void) on_each_cpu(kvm_map_magic_page, &features, 1); /* Quick self-test to see if the mapping works */ - if (fault_in_pages_readable((const char *)KVM_MAGIC_PAGE, sizeof(u32))) { + if (fault_in_readable((const char __user *)KVM_MAGIC_PAGE, + sizeof(u32))) { kvm_patching_worked = false; return; } diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 0608581967f0..38c3eae40c14 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1048,7 +1048,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, if (new_ctx == NULL) return 0; if (!access_ok(new_ctx, ctx_size) || - fault_in_pages_readable((u8 __user *)new_ctx, ctx_size)) + fault_in_readable((char __user *)new_ctx, ctx_size)) return -EFAULT; /* @@ -1237,7 +1237,7 @@ SYSCALL_DEFINE3(debug_setcontext, struct ucontext __user *, ctx, #endif if (!access_ok(ctx, sizeof(*ctx)) || - fault_in_pages_readable((u8 __user *)ctx, sizeof(*ctx))) + fault_in_readable((char __user *)ctx, sizeof(*ctx))) return -EFAULT; /* diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index 1831bba0582e..9f471b4a11e3 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -688,7 +688,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, if (new_ctx == NULL) return 0; if (!access_ok(new_ctx, ctx_size) || - fault_in_pages_readable((u8 __user *)new_ctx, ctx_size)) + fault_in_readable((char __user *)new_ctx, ctx_size)) return -EFAULT; /* diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index fa17a27390ab..164c96434704 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -205,7 +205,7 @@ retry: fpregs_unlock(); if (ret) { - if (!fault_in_pages_writeable(buf_fx, fpu_user_xstate_size)) + if (!fault_in_writeable(buf_fx, fpu_user_xstate_size)) goto retry; return -EFAULT; } @@ -278,10 +278,9 @@ retry: if (ret != -EFAULT) return -EINVAL; - ret = fault_in_pages_readable(buf, size); - if (!ret) + if (!fault_in_readable(buf, size)) goto retry; - return ret; + return -EFAULT; } /* diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c index 21909642ee4c..8fbb25913327 100644 --- a/drivers/gpu/drm/armada/armada_gem.c +++ b/drivers/gpu/drm/armada/armada_gem.c @@ -336,7 +336,7 @@ int armada_gem_pwrite_ioctl(struct drm_device *dev, void *data, struct drm_armada_gem_pwrite *args = data; struct armada_gem_object *dobj; char __user *ptr; - int ret; + int ret = 0; DRM_DEBUG_DRIVER("handle %u off %u size %u ptr 0x%llx\n", args->handle, args->offset, args->size, args->ptr); @@ -349,9 +349,8 @@ int armada_gem_pwrite_ioctl(struct drm_device *dev, void *data, if (!access_ok(ptr, args->size)) return -EFAULT; - ret = fault_in_pages_readable(ptr, args->size); - if (ret) - return ret; + if (fault_in_readable(ptr, args->size)) + return -EFAULT; dobj = armada_gem_object_lookup(file, args->handle); if (dobj == NULL) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index cc61813213d8..c0739f0af634 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2261,9 +2261,8 @@ static noinline int search_ioctl(struct inode *inode, key.offset = sk->min_offset; while (1) { - ret = fault_in_pages_writeable(ubuf + sk_offset, - *buf_size - sk_offset); - if (ret) + ret = -EFAULT; + if (fault_in_writeable(ubuf + sk_offset, *buf_size - sk_offset)) break; ret = btrfs_search_forward(root, &key, path, sk->min_transid); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 62db6b0176b9..9fe94f7a4f7e 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -733,61 +733,10 @@ int wait_on_page_private_2_killable(struct page *page); extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); /* - * Fault everything in given userspace address range in. + * Fault in userspace address range. */ -static inline int fault_in_pages_writeable(char __user *uaddr, size_t size) -{ - char __user *end = uaddr + size - 1; - - if (unlikely(size == 0)) - return 0; - - if (unlikely(uaddr > end)) - return -EFAULT; - /* - * Writing zeroes into userspace here is OK, because we know that if - * the zero gets there, we'll be overwriting it. - */ - do { - if (unlikely(__put_user(0, uaddr) != 0)) - return -EFAULT; - uaddr += PAGE_SIZE; - } while (uaddr <= end); - - /* Check whether the range spilled into the next page. */ - if (((unsigned long)uaddr & PAGE_MASK) == - ((unsigned long)end & PAGE_MASK)) - return __put_user(0, end); - - return 0; -} - -static inline int fault_in_pages_readable(const char __user *uaddr, size_t size) -{ - volatile char c; - const char __user *end = uaddr + size - 1; - - if (unlikely(size == 0)) - return 0; - - if (unlikely(uaddr > end)) - return -EFAULT; - - do { - if (unlikely(__get_user(c, uaddr) != 0)) - return -EFAULT; - uaddr += PAGE_SIZE; - } while (uaddr <= end); - - /* Check whether the range spilled into the next page. */ - if (((unsigned long)uaddr & PAGE_MASK) == - ((unsigned long)end & PAGE_MASK)) { - return __get_user(c, end); - } - - (void)c; - return 0; -} +size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_readable(const char __user *uaddr, size_t size); int add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 60b5e6edfbaa..c88908f0f138 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -191,7 +191,7 @@ static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t b buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); - if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_writeable(buf, copy)) { + if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_writeable(buf, copy)) { kaddr = kmap_atomic(page); from = kaddr + offset; @@ -275,7 +275,7 @@ static size_t copy_page_from_iter_iovec(struct page *page, size_t offset, size_t buf = iov->iov_base + skip; copy = min(bytes, iov->iov_len - skip); - if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_pages_readable(buf, copy)) { + if (IS_ENABLED(CONFIG_HIGHMEM) && !fault_in_readable(buf, copy)) { kaddr = kmap_atomic(page); to = kaddr + offset; @@ -446,13 +446,11 @@ int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes) bytes = i->count; for (p = i->iov, skip = i->iov_offset; bytes; p++, skip = 0) { size_t len = min(bytes, p->iov_len - skip); - int err; if (unlikely(!len)) continue; - err = fault_in_pages_readable(p->iov_base + skip, len); - if (unlikely(err)) - return err; + if (fault_in_readable(p->iov_base + skip, len)) + return -EFAULT; bytes -= len; } } diff --git a/mm/filemap.c b/mm/filemap.c index dae481293b5d..ff34f4087f87 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -90,7 +90,7 @@ * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) - * ->mmap_lock (fault_in_pages_readable->do_page_fault) + * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) diff --git a/mm/gup.c b/mm/gup.c index 886d6148d3d0..a7efb027d6cf 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1656,6 +1656,78 @@ finish_or_fault: } #endif /* !CONFIG_MMU */ +/** + * fault_in_writeable - fault in userspace address range for writing + * @uaddr: start of address range + * @size: size of address range + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). + */ +size_t fault_in_writeable(char __user *uaddr, size_t size) +{ + char __user *start = uaddr, *end; + + if (unlikely(size == 0)) + return 0; + if (!PAGE_ALIGNED(uaddr)) { + if (unlikely(__put_user(0, uaddr) != 0)) + return size; + uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); + } + end = (char __user *)PAGE_ALIGN((unsigned long)start + size); + if (unlikely(end < start)) + end = NULL; + while (uaddr != end) { + if (unlikely(__put_user(0, uaddr) != 0)) + goto out; + uaddr += PAGE_SIZE; + } + +out: + if (size > uaddr - start) + return size - (uaddr - start); + return 0; +} +EXPORT_SYMBOL(fault_in_writeable); + +/** + * fault_in_readable - fault in userspace address range for reading + * @uaddr: start of user address range + * @size: size of user address range + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). + */ +size_t fault_in_readable(const char __user *uaddr, size_t size) +{ + const char __user *start = uaddr, *end; + volatile char c; + + if (unlikely(size == 0)) + return 0; + if (!PAGE_ALIGNED(uaddr)) { + if (unlikely(__get_user(c, uaddr) != 0)) + return size; + uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); + } + end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); + if (unlikely(end < start)) + end = NULL; + while (uaddr != end) { + if (unlikely(__get_user(c, uaddr) != 0)) + goto out; + uaddr += PAGE_SIZE; + } + +out: + (void)c; + if (size > uaddr - start) + return size - (uaddr - start); + return 0; +} +EXPORT_SYMBOL(fault_in_readable); + /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address -- cgit v1.2.3 From a6294593e8a1290091d0b078d5d33da5e0cd3dfe Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 2 Aug 2021 14:54:16 +0200 Subject: iov_iter: Turn iov_iter_fault_in_readable into fault_in_iov_iter_readable Turn iov_iter_fault_in_readable into a function that returns the number of bytes not faulted in, similar to copy_to_user, instead of returning a non-zero value when any of the requested pages couldn't be faulted in. This supports the existing users that require all pages to be faulted in as well as new users that are happy if any pages can be faulted in. Rename iov_iter_fault_in_readable to fault_in_iov_iter_readable to make sure this change doesn't silently break things. Signed-off-by: Andreas Gruenbacher --- fs/btrfs/file.c | 2 +- fs/f2fs/file.c | 2 +- fs/fuse/file.c | 2 +- fs/iomap/buffered-io.c | 2 +- fs/ntfs/file.c | 2 +- fs/ntfs3/file.c | 2 +- include/linux/uio.h | 2 +- lib/iov_iter.c | 33 +++++++++++++++++++++------------ mm/filemap.c | 2 +- 9 files changed, 29 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7ff577005d0f..f37211d3bb69 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1710,7 +1710,7 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, * Fault pages before locking them in prepare_pages * to avoid recursive lock */ - if (unlikely(iov_iter_fault_in_readable(i, write_bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, write_bytes))) { ret = -EFAULT; break; } diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 9c8ef33bd8d3..eb971e1e7227 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -4276,7 +4276,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) size_t target_size = 0; int err; - if (iov_iter_fault_in_readable(from, iov_iter_count(from))) + if (fault_in_iov_iter_readable(from, iov_iter_count(from))) set_inode_flag(inode, FI_NO_PREALLOC); if ((iocb->ki_flags & IOCB_NOWAIT)) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 11404f8c21c7..4b6d8e13322d 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1164,7 +1164,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia, again: err = -EFAULT; - if (iov_iter_fault_in_readable(ii, bytes)) + if (fault_in_iov_iter_readable(ii, bytes)) break; err = -ENOMEM; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 9cc5798423d1..1753c26c8e76 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -750,7 +750,7 @@ again: * same page as we're writing to, without it being marked * up-to-date. */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, bytes))) { status = -EFAULT; break; } diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index ab4f3362466d..a43adeacd930 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -1829,7 +1829,7 @@ again: * pages being swapped out between us bringing them into memory * and doing the actual copying. */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, bytes))) { status = -EFAULT; break; } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 424450e77ad5..a52388387175 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -987,7 +987,7 @@ static ssize_t ntfs_compress_write(struct kiocb *iocb, struct iov_iter *from) frame_vbo = pos & ~(frame_size - 1); index = frame_vbo >> PAGE_SHIFT; - if (unlikely(iov_iter_fault_in_readable(from, bytes))) { + if (unlikely(fault_in_iov_iter_readable(from, bytes))) { err = -EFAULT; goto out; } diff --git a/include/linux/uio.h b/include/linux/uio.h index 207101a9c5c3..d18458af6681 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -133,7 +133,7 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, size_t bytes, struct iov_iter *i); void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); -int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes); +size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index c88908f0f138..ce3d4f610626 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -430,33 +430,42 @@ out: } /* + * fault_in_iov_iter_readable - fault in iov iterator for reading + * @i: iterator + * @size: maximum length + * * Fault in one or more iovecs of the given iov_iter, to a maximum length of - * bytes. For each iovec, fault in each page that constitutes the iovec. + * @size. For each iovec, fault in each page that constitutes the iovec. + * + * Returns the number of bytes not faulted in (like copy_to_user() and + * copy_from_user()). * - * Return 0 on success, or non-zero if the memory could not be accessed (i.e. - * because it is an invalid address). + * Always returns 0 for non-userspace iterators. */ -int iov_iter_fault_in_readable(const struct iov_iter *i, size_t bytes) +size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size) { if (iter_is_iovec(i)) { + size_t count = min(size, iov_iter_count(i)); const struct iovec *p; size_t skip; - if (bytes > i->count) - bytes = i->count; - for (p = i->iov, skip = i->iov_offset; bytes; p++, skip = 0) { - size_t len = min(bytes, p->iov_len - skip); + size -= count; + for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) { + size_t len = min(count, p->iov_len - skip); + size_t ret; if (unlikely(!len)) continue; - if (fault_in_readable(p->iov_base + skip, len)) - return -EFAULT; - bytes -= len; + ret = fault_in_readable(p->iov_base + skip, len); + count -= len - ret; + if (ret) + break; } + return count + size; } return 0; } -EXPORT_SYMBOL(iov_iter_fault_in_readable); +EXPORT_SYMBOL(fault_in_iov_iter_readable); void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, diff --git a/mm/filemap.c b/mm/filemap.c index ff34f4087f87..4dd5edcd39fd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3757,7 +3757,7 @@ again: * same page as we're writing to, without it being marked * up-to-date. */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { + if (unlikely(fault_in_iov_iter_readable(i, bytes))) { status = -EFAULT; break; } -- cgit v1.2.3 From d4aa57a1cac3c99ffd641f7c8e0a7aff5656de0d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 13 Oct 2021 09:01:43 -0600 Subject: block: don't bother iter advancing a fully done bio If we're completing nbytes and nbytes is the size of the bio, don't bother with calling into the iterator increment helpers. Just clear the bio size and we're done. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/bio.c | 15 ++------------- include/linux/bio.h | 24 ++++++++++++++++++++++-- 2 files changed, 24 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 5fb8092577bf..4f397ba47db5 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1278,18 +1278,7 @@ int submit_bio_wait(struct bio *bio) } EXPORT_SYMBOL(submit_bio_wait); -/** - * bio_advance - increment/complete a bio by some number of bytes - * @bio: bio to advance - * @bytes: number of bytes to complete - * - * This updates bi_sector, bi_size and bi_idx; if the number of bytes to - * complete doesn't align with a bvec boundary, then bv_len and bv_offset will - * be updated on the last bvec as well. - * - * @bio will then represent the remaining, uncompleted portion of the io. - */ -void bio_advance(struct bio *bio, unsigned bytes) +void __bio_advance(struct bio *bio, unsigned bytes) { if (bio_integrity(bio)) bio_integrity_advance(bio, bytes); @@ -1297,7 +1286,7 @@ void bio_advance(struct bio *bio, unsigned bytes) bio_crypt_advance(bio, bytes); bio_advance_iter(bio, &bio->bi_iter, bytes); } -EXPORT_SYMBOL(bio_advance); +EXPORT_SYMBOL(__bio_advance); void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter) diff --git a/include/linux/bio.h b/include/linux/bio.h index 62d684b7dd4c..9538f20ffaa5 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -119,6 +119,28 @@ static inline void bio_advance_iter_single(const struct bio *bio, bvec_iter_advance_single(bio->bi_io_vec, iter, bytes); } +void __bio_advance(struct bio *, unsigned bytes); + +/** + * bio_advance - increment/complete a bio by some number of bytes + * @bio: bio to advance + * @bytes: number of bytes to complete + * + * This updates bi_sector, bi_size and bi_idx; if the number of bytes to + * complete doesn't align with a bvec boundary, then bv_len and bv_offset will + * be updated on the last bvec as well. + * + * @bio will then represent the remaining, uncompleted portion of the io. + */ +static inline void bio_advance(struct bio *bio, unsigned int nbytes) +{ + if (nbytes == bio->bi_iter.bi_size) { + bio->bi_iter.bi_size = 0; + return; + } + __bio_advance(bio, nbytes); +} + #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ @@ -381,8 +403,6 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs) struct request_queue; extern int submit_bio_wait(struct bio *bio); -extern void bio_advance(struct bio *, unsigned); - extern void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs); extern void bio_uninit(struct bio *); -- cgit v1.2.3 From b60876296847e6cd7f1da4b8b7f0f31399d59aa1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 Oct 2021 15:03:52 -0600 Subject: block: improve layout of struct request It's been a while since this was analyzed, move some members around to better flow with the use case. Initial state up top, and queued state after that. This improves my peak case by about 1.5%, from 7750K to 7900K IOPS. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 90 ++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a9c1d0882550..8ca9728cc7f2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -83,6 +83,8 @@ struct request { int tag; int internal_tag; + unsigned int timeout; + /* the following two fields are internal, NEVER access directly */ unsigned int __data_len; /* total data len */ sector_t __sector; /* sector cursor */ @@ -95,49 +97,6 @@ struct request { struct request *rq_next; }; - /* - * The hash is used inside the scheduler, and killed once the - * request reaches the dispatch list. The ipi_list is only used - * to queue the request for softirq completion, which is long - * after the request has been unhashed (and even removed from - * the dispatch list). - */ - union { - struct hlist_node hash; /* merge hash */ - struct llist_node ipi_list; - }; - - /* - * The rb_node is only used inside the io scheduler, requests - * are pruned when moved to the dispatch queue. So let the - * completion_data share space with the rb_node. - */ - union { - struct rb_node rb_node; /* sort/lookup */ - struct bio_vec special_vec; - void *completion_data; - int error_count; /* for legacy drivers, don't use */ - }; - - /* - * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. Flush requests are - * never put on the IO scheduler. So let the flush fields share - * space with the elevator data. - */ - union { - struct { - struct io_cq *icq; - void *priv[2]; - } elv; - - struct { - unsigned int seq; - struct list_head list; - rq_end_io_fn *saved_end_io; - } flush; - }; - struct gendisk *rq_disk; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME @@ -180,9 +139,52 @@ struct request { enum mq_rq_state state; refcount_t ref; - unsigned int timeout; unsigned long deadline; + /* + * The hash is used inside the scheduler, and killed once the + * request reaches the dispatch list. The ipi_list is only used + * to queue the request for softirq completion, which is long + * after the request has been unhashed (and even removed from + * the dispatch list). + */ + union { + struct hlist_node hash; /* merge hash */ + struct llist_node ipi_list; + }; + + /* + * The rb_node is only used inside the io scheduler, requests + * are pruned when moved to the dispatch queue. So let the + * completion_data share space with the rb_node. + */ + union { + struct rb_node rb_node; /* sort/lookup */ + struct bio_vec special_vec; + void *completion_data; + int error_count; /* for legacy drivers, don't use */ + }; + + + /* + * Three pointers are available for the IO schedulers, if they need + * more they have to dynamically allocate it. Flush requests are + * never put on the IO scheduler. So let the flush fields share + * space with the elevator data. + */ + union { + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + + struct { + unsigned int seq; + struct list_head list; + rq_end_io_fn *saved_end_io; + } flush; + }; + union { struct __call_single_data csd; u64 fifo_time; -- cgit v1.2.3 From 2ff0682da6e09c1e0db63a2d2abcd4efb531c8db Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 15 Oct 2021 09:44:38 -0600 Subject: block: store elevator state in request Add an rq private RQF_ELV flag, which tells the block layer that this request was initialized on a queue that has an IO scheduler attached. This allows for faster checking in the fast path, rather than having to deference rq->q later on. Elevator switching does full quiesce of the queue before detaching an IO scheduler, so it's safe to cache this in the request itself. Signed-off-by: Jens Axboe --- block/blk-mq-sched.h | 27 ++++++++++++++++----------- block/blk-mq.c | 20 +++++++++++--------- include/linux/blk-mq.h | 2 ++ 3 files changed, 29 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h index fe252278ed9a..98836106b25f 100644 --- a/block/blk-mq-sched.h +++ b/block/blk-mq-sched.h @@ -56,29 +56,34 @@ static inline bool blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq, struct bio *bio) { - struct elevator_queue *e = q->elevator; - - if (e && e->type->ops.allow_merge) - return e->type->ops.allow_merge(q, rq, bio); + if (rq->rq_flags & RQF_ELV) { + struct elevator_queue *e = q->elevator; + if (e->type->ops.allow_merge) + return e->type->ops.allow_merge(q, rq, bio); + } return true; } static inline void blk_mq_sched_completed_request(struct request *rq, u64 now) { - struct elevator_queue *e = rq->q->elevator; + if (rq->rq_flags & RQF_ELV) { + struct elevator_queue *e = rq->q->elevator; - if (e && e->type->ops.completed_request) - e->type->ops.completed_request(rq, now); + if (e->type->ops.completed_request) + e->type->ops.completed_request(rq, now); + } } static inline void blk_mq_sched_requeue_request(struct request *rq) { - struct request_queue *q = rq->q; - struct elevator_queue *e = q->elevator; + if (rq->rq_flags & RQF_ELV) { + struct request_queue *q = rq->q; + struct elevator_queue *e = q->elevator; - if ((rq->rq_flags & RQF_ELVPRIV) && e && e->type->ops.requeue_request) - e->type->ops.requeue_request(rq); + if ((rq->rq_flags & RQF_ELVPRIV) && e->type->ops.requeue_request) + e->type->ops.requeue_request(rq); + } } static inline bool blk_mq_sched_has_work(struct blk_mq_hw_ctx *hctx) diff --git a/block/blk-mq.c b/block/blk-mq.c index 9cff9e8eada4..28eb1f3c6f76 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -306,7 +306,7 @@ void blk_mq_wake_waiters(struct request_queue *q) */ static inline bool blk_mq_need_time_stamp(struct request *rq) { - return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS)) || rq->q->elevator; + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); } static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, @@ -316,9 +316,11 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, struct request *rq = tags->static_rqs[tag]; if (data->q->elevator) { + rq->rq_flags = RQF_ELV; rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = tag; } else { + rq->rq_flags = 0; rq->tag = tag; rq->internal_tag = BLK_MQ_NO_TAG; } @@ -327,7 +329,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->q = data->q; rq->mq_ctx = data->ctx; rq->mq_hctx = data->hctx; - rq->rq_flags = 0; rq->cmd_flags = data->cmd_flags; if (data->flags & BLK_MQ_REQ_PM) rq->rq_flags |= RQF_PM; @@ -363,11 +364,11 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, data->ctx->rq_dispatched[op_is_sync(data->cmd_flags)]++; refcount_set(&rq->ref, 1); - if (!op_is_flush(data->cmd_flags)) { + if (!op_is_flush(data->cmd_flags) && (rq->rq_flags & RQF_ELV)) { struct elevator_queue *e = data->q->elevator; rq->elv.icq = NULL; - if (e && e->type->ops.prepare_request) { + if (e->type->ops.prepare_request) { if (e->type->icq_cache) blk_mq_sched_assign_ioc(rq); @@ -588,12 +589,13 @@ static void __blk_mq_free_request(struct request *rq) void blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; - struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; struct blk_mq_hw_ctx *hctx = rq->mq_hctx; - if (rq->rq_flags & RQF_ELVPRIV) { - if (e && e->type->ops.finish_request) + if (rq->rq_flags & (RQF_ELVPRIV | RQF_ELV)) { + struct elevator_queue *e = q->elevator; + + if (e->type->ops.finish_request) e->type->ops.finish_request(rq); if (rq->elv.icq) { put_io_context(rq->elv.icq->ioc); @@ -2254,7 +2256,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, goto insert; } - if (q->elevator && !bypass_insert) + if ((rq->rq_flags & RQF_ELV) && !bypass_insert) goto insert; budget_token = blk_mq_get_dispatch_budget(q); @@ -2492,7 +2494,7 @@ void blk_mq_submit_bio(struct bio *bio) } blk_add_rq_to_plug(plug, rq); - } else if (q->elevator) { + } else if (rq->rq_flags & RQF_ELV) { /* Insert the request at the IO scheduler queue */ blk_mq_sched_insert_request(rq, false, true, true); } else if (plug && !blk_queue_nomerges(q)) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8ca9728cc7f2..95c3bd3a008e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -55,6 +55,8 @@ typedef __u32 __bitwise req_flags_t; #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) +/* queue has elevator attached */ +#define RQF_ELV ((__force req_flags_t)(1 << 22)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ -- cgit v1.2.3 From 0d20e9fb1262b1f9ac895b287db892bc75b05b84 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:31 +0200 Subject: rtc: add BSM parameter BSM or Backup Switch Mode is a common feature on RTCs, allowing to select how the RTC will decide when to switch from its primary power supply to the backup power supply. It is necessary to be able to set it from userspace as there are uses cases where it has to be done dynamically. Supported values are: RTC_BSM_DISABLED: disabled RTC_BSM_DIRECT: switching will happen as soon as Vbackup > Vdd RTC_BSM_LEVEL: switching will happen around a threshold, usually with an hysteresis RTC_BSM_STANDBY: switching will not happen until Vdd > Vbackup, this is useful to ensure the RTC doesn't draw any power until the device is first powered on. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-6-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 10 ++++++++-- include/linux/rtc.h | 2 ++ include/uapi/linux/rtc.h | 9 ++++++++- 3 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index abee1fc4705e..e104972a28fd 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -409,7 +409,10 @@ static long rtc_dev_ioctl(struct file *file, break; default: - err = -EINVAL; + if (rtc->ops->param_get) + err = rtc->ops->param_get(rtc->dev.parent, ¶m); + else + err = -EINVAL; } if (!err) @@ -436,7 +439,10 @@ static long rtc_dev_ioctl(struct file *file, return rtc_set_offset(rtc, param.svalue); default: - err = -EINVAL; + if (rtc->ops->param_set) + err = rtc->ops->param_set(rtc->dev.parent, ¶m); + else + err = -EINVAL; } break; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 354e0843ab17..47fd1c2d3a57 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -66,6 +66,8 @@ struct rtc_class_ops { int (*alarm_irq_enable)(struct device *, unsigned int enabled); int (*read_offset)(struct device *, long *offset); int (*set_offset)(struct device *, long offset); + int (*param_get)(struct device *, struct rtc_param *param); + int (*param_set)(struct device *, struct rtc_param *param); }; struct rtc_device; diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 5debe82439c2..03e5b776e597 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -132,11 +132,18 @@ struct rtc_param { #define RTC_FEATURE_ALARM_RES_2S 3 #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CORRECTION 5 -#define RTC_FEATURE_CNT 6 +#define RTC_FEATURE_BACKUP_SWITCH_MODE 6 +#define RTC_FEATURE_CNT 7 /* parameter list */ #define RTC_PARAM_FEATURES 0 #define RTC_PARAM_CORRECTION 1 +#define RTC_PARAM_BACKUP_SWITCH_MODE 2 + +#define RTC_BSM_DISABLED 0 +#define RTC_BSM_DIRECT 1 +#define RTC_BSM_LEVEL 2 +#define RTC_BSM_STANDBY 3 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 88dee3b0efe4b769fb22ce2e963aabae403e6801 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Mon, 18 Oct 2021 20:41:09 +0800 Subject: PCI: Remove unused pci_pool wrappers The pci_pool users have been converted to dma_pool. Remove the unused pci_pool wrappers. Link: https://lore.kernel.org/r/20211018124110.214-1-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..2ae9dd7f975f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1498,19 +1498,8 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, #define PCI_IRQ_ALL_TYPES \ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) -/* kmem_cache style wrapper around pci_alloc_consistent() */ - #include -#define pci_pool dma_pool -#define pci_pool_create(name, pdev, size, align, allocation) \ - dma_pool_create(name, &pdev->dev, size, align, allocation) -#define pci_pool_destroy(pool) dma_pool_destroy(pool) -#define pci_pool_alloc(pool, flags, handle) dma_pool_alloc(pool, flags, handle) -#define pci_pool_zalloc(pool, flags, handle) \ - dma_pool_zalloc(pool, flags, handle) -#define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr) - struct msix_entry { u32 vector; /* Kernel uses to write allocated vector */ u16 entry; /* Driver uses to specify entry, OS writes */ -- cgit v1.2.3 From 4797632f4f1d8af4e0670adcb97bf9800dc3beca Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 17 May 2021 20:16:57 -0700 Subject: string.h: Introduce memset_after() for wiping trailing members/padding A common idiom in kernel code is to wipe the contents of a structure after a given member. This is especially useful in places where there is trailing padding. These open-coded cases are usually difficult to read and very sensitive to struct layout changes. Introduce a new helper, memset_after() that takes the target struct instance, the byte to write, and the member name after which the zeroing should start. Cc: Steffen Klassert Cc: Herbert Xu Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Andrew Morton Cc: Francis Laniel Cc: Vincenzo Frascino Cc: Daniel Axtens Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook --- include/linux/string.h | 17 +++++++++++++++++ lib/memcpy_kunit.c | 13 +++++++++++++ 2 files changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index ac1c769a5a80..da490c2154a9 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -271,6 +271,23 @@ static inline void memcpy_and_pad(void *dest, size_t dest_len, memcpy(dest, src, dest_len); } +/** + * memset_after - Set a value after a struct member to the end of a struct + * + * @obj: Address of target struct instance + * @v: Byte value to repeatedly write + * @member: after which struct member to start writing bytes + * + * This is good for clearing padding following the given member. + */ +#define memset_after(obj, v, member) \ +({ \ + u8 *__ptr = (u8 *)(obj); \ + typeof(v) __val = (v); \ + memset(__ptr + offsetofend(typeof(*(obj)), member), __val, \ + sizeof(*(obj)) - offsetofend(typeof(*(obj)), member)); \ +}) + /** * str_has_prefix - Test if a string has a given prefix * @str: The string to test diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 8b2109bb62df..5c5b4f3221d9 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -215,6 +215,13 @@ static void memset_test(struct kunit *test) 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, }, }; + struct some_bytes after = { + .data = { 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x72, + 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, + 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, + 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, + }, + }; struct some_bytes dest = { }; int count, value; u8 *ptr; @@ -245,6 +252,12 @@ static void memset_test(struct kunit *test) ptr += 8; memset(ptr++, value++, count++); compare("argument side-effects", dest, three); + + /* Verify memset_after() */ + dest = control; + memset_after(&dest, 0x72, three); + compare("memset_after()", dest, after); + #undef TEST_OP } -- cgit v1.2.3 From 6dbefad40815a61aecbcf9b552e87ef57ab8cc7d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 17 May 2021 20:16:57 -0700 Subject: string.h: Introduce memset_startat() for wiping trailing members and padding A common idiom in kernel code is to wipe the contents of a structure starting from a given member. These open-coded cases are usually difficult to read and very sensitive to struct layout changes. Like memset_after(), introduce a new helper, memset_startat() that takes the target struct instance, the byte to write, and the member name where zeroing should start. Note that this doesn't zero padding preceding the target member. For those cases, memset_after() should be used on the preceding member. Cc: Steffen Klassert Cc: Herbert Xu Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Andrew Morton Cc: Francis Laniel Cc: Vincenzo Frascino Cc: Daniel Axtens Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook --- include/linux/string.h | 18 ++++++++++++++++++ lib/memcpy_kunit.c | 11 +++++++++++ 2 files changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index da490c2154a9..5a36608144a9 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -288,6 +288,24 @@ static inline void memcpy_and_pad(void *dest, size_t dest_len, sizeof(*(obj)) - offsetofend(typeof(*(obj)), member)); \ }) +/** + * memset_startat - Set a value starting at a member to the end of a struct + * + * @obj: Address of target struct instance + * @v: Byte value to repeatedly write + * @member: struct member to start writing at + * + * Note that if there is padding between the prior member and the target + * member, memset_after() should be used to clear the prior padding. + */ +#define memset_startat(obj, v, member) \ +({ \ + u8 *__ptr = (u8 *)(obj); \ + typeof(v) __val = (v); \ + memset(__ptr + offsetof(typeof(*(obj)), member), __val, \ + sizeof(*(obj)) - offsetof(typeof(*(obj)), member)); \ +}) + /** * str_has_prefix - Test if a string has a given prefix * @str: The string to test diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 5c5b4f3221d9..62f8ffcbbaa3 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -222,6 +222,13 @@ static void memset_test(struct kunit *test) 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, 0x72, }, }; + struct some_bytes startat = { + .data = { 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, + 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, + 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, + 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, 0x79, + }, + }; struct some_bytes dest = { }; int count, value; u8 *ptr; @@ -258,6 +265,10 @@ static void memset_test(struct kunit *test) memset_after(&dest, 0x72, three); compare("memset_after()", dest, after); + /* Verify memset_startat() */ + dest = control; + memset_startat(&dest, 0x79, four); + compare("memset_startat()", dest, startat); #undef TEST_OP } -- cgit v1.2.3 From 3080ea5553cc909b000d1f1d964a9041962f2c5b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 9 Aug 2021 11:21:23 -0700 Subject: stddef: Introduce DECLARE_FLEX_ARRAY() helper There are many places where kernel code wants to have several different typed trailing flexible arrays. This would normally be done with multiple flexible arrays in a union, but since GCC and Clang don't (on the surface) allow this, there have been many open-coded workarounds, usually involving neighboring 0-element arrays at the end of a structure. For example, instead of something like this: struct thing { ... union { struct type1 foo[]; struct type2 bar[]; }; }; code works around the compiler with: struct thing { ... struct type1 foo[0]; struct type2 bar[]; }; Another case is when a flexible array is wanted as the single member within a struct (which itself is usually in a union). For example, this would be worked around as: union many { ... struct { struct type3 baz[0]; }; }; These kinds of work-arounds cause problems with size checks against such zero-element arrays (for example when building with -Warray-bounds and -Wzero-length-bounds, and with the coming FORTIFY_SOURCE improvements), so they must all be converted to "real" flexible arrays, avoiding warnings like this: fs/hpfs/anode.c: In function 'hpfs_add_sector_to_btree': fs/hpfs/anode.c:209:27: warning: array subscript 0 is outside the bounds of an interior zero-length array 'struct bplus_internal_node[0]' [-Wzero-length-bounds] 209 | anode->btree.u.internal[0].down = cpu_to_le32(a); | ~~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from fs/hpfs/hpfs_fn.h:26, from fs/hpfs/anode.c:10: fs/hpfs/hpfs.h:412:32: note: while referencing 'internal' 412 | struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving | ^~~~~~~~ drivers/net/can/usb/etas_es58x/es58x_fd.c: In function 'es58x_fd_tx_can_msg': drivers/net/can/usb/etas_es58x/es58x_fd.c:360:35: warning: array subscript 65535 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[]'} [-Wzero-length-bounds] 360 | tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/net/can/usb/etas_es58x/es58x_core.h:22, from drivers/net/can/usb/etas_es58x/es58x_fd.c:17: drivers/net/can/usb/etas_es58x/es58x_fd.h:231:6: note: while referencing 'raw_msg' 231 | u8 raw_msg[0]; | ^~~~~~~ However, it _is_ entirely possible to have one or more flexible arrays in a struct or union: it just has to be in another struct. And since it cannot be alone in a struct, such a struct must have at least 1 other named member -- but that member can be zero sized. Wrap all this nonsense into the new DECLARE_FLEX_ARRAY() in support of having flexible arrays in unions (or alone in a struct). As with struct_group(), since this is needed in UAPI headers as well, implement the core there, with a non-UAPI wrapper. Additionally update kernel-doc to understand its existence. https://github.com/KSPP/linux/issues/137 Cc: Arnd Bergmann Cc: "Gustavo A. R. Silva" Signed-off-by: Kees Cook --- include/linux/stddef.h | 13 +++++++++++++ include/uapi/linux/stddef.h | 16 ++++++++++++++++ scripts/kernel-doc | 2 ++ 3 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 8b103a53b000..ca507bd5f808 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -84,4 +84,17 @@ enum { #define struct_group_tagged(TAG, NAME, MEMBERS...) \ __struct_group(TAG, NAME, /* no attrs */, MEMBERS) +/** + * DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define DECLARE_FLEX_ARRAY(TYPE, NAME) \ + __DECLARE_FLEX_ARRAY(TYPE, NAME) + #endif diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 610204f7c275..3021ea25a284 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -25,3 +25,19 @@ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ } + +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 38aa799a776c..5d54b57ff90c 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1263,6 +1263,8 @@ sub dump_struct($$) { $members =~ s/DECLARE_KFIFO\s*\($args,\s*$args,\s*$args\)/$2 \*$1/gos; # replace DECLARE_KFIFO_PTR $members =~ s/DECLARE_KFIFO_PTR\s*\($args,\s*$args\)/$2 \*$1/gos; + # replace DECLARE_FLEX_ARRAY + $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\($args,\s*$args\)/$1 $2\[\]/gos; my $declaration = $members; # Split nested struct/union elements as newer ones -- cgit v1.2.3 From fa7845cfd53f3b1d3f60efa55db89805595bc045 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 9 Aug 2021 11:29:33 -0700 Subject: treewide: Replace open-coded flex arrays in unions In support of enabling -Warray-bounds and -Wzero-length-bounds and correctly handling run-time memcpy() bounds checking, replace all open-coded flexible arrays (i.e. 0-element arrays) in unions with the DECLARE_FLEX_ARRAY() helper macro. This fixes warnings such as: fs/hpfs/anode.c: In function 'hpfs_add_sector_to_btree': fs/hpfs/anode.c:209:27: warning: array subscript 0 is outside the bounds of an interior zero-length array 'struct bplus_internal_node[0]' [-Wzero-length-bounds] 209 | anode->btree.u.internal[0].down = cpu_to_le32(a); | ~~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from fs/hpfs/hpfs_fn.h:26, from fs/hpfs/anode.c:10: fs/hpfs/hpfs.h:412:32: note: while referencing 'internal' 412 | struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving | ^~~~~~~~ drivers/net/can/usb/etas_es58x/es58x_fd.c: In function 'es58x_fd_tx_can_msg': drivers/net/can/usb/etas_es58x/es58x_fd.c:360:35: warning: array subscript 65535 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[]'} [-Wzero-length-bounds] 360 | tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/net/can/usb/etas_es58x/es58x_core.h:22, from drivers/net/can/usb/etas_es58x/es58x_fd.c:17: drivers/net/can/usb/etas_es58x/es58x_fd.h:231:6: note: while referencing 'raw_msg' 231 | u8 raw_msg[0]; | ^~~~~~~ Cc: "Gustavo A. R. Silva" Cc: Arnd Bergmann Cc: Ayush Sawal Cc: Vinay Kumar Yadav Cc: Rohit Maheshwari Cc: Herbert Xu Cc: "David S. Miller" Cc: Kalle Valo Cc: Jakub Kicinski Cc: Stanislaw Gruszka Cc: Luca Coelho Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Alexei Starovoitov Cc: Daniel Borkmann Cc: Andrii Nakryiko Cc: Martin KaFai Lau Cc: Song Liu Cc: Yonghong Song Cc: John Fastabend Cc: KP Singh Cc: Johannes Berg Cc: Mordechay Goodstein Cc: Lee Jones Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: Arunachalam Santhanam Cc: Vincent Mailhol Cc: Mikulas Patocka Cc: linux-crypto@vger.kernel.org Cc: ath10k@lists.infradead.org Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: linux-can@vger.kernel.org Cc: bpf@vger.kernel.org Acked-by: Marc Kleine-Budde # drivers/net/can/usb/etas_es58x/* Signed-off-by: Kees Cook --- drivers/crypto/chelsio/chcr_crypto.h | 14 +++++++++----- drivers/net/can/usb/etas_es58x/es581_4.h | 2 +- drivers/net/can/usb/etas_es58x/es58x_fd.h | 2 +- drivers/net/wireless/ath/ath10k/htt.h | 7 +++++-- drivers/net/wireless/intel/iwlegacy/commands.h | 6 ++++-- drivers/net/wireless/intel/iwlwifi/dvm/commands.h | 6 ++++-- drivers/net/wireless/intel/iwlwifi/fw/api/tx.h | 12 ++++++++---- drivers/scsi/aic94xx/aic94xx_sds.c | 6 ++++-- fs/hpfs/hpfs.h | 8 ++++---- include/linux/filter.h | 6 ++++-- include/scsi/sas.h | 12 ++++++++---- include/uapi/rdma/rdma_user_rxe.h | 4 ++-- include/uapi/sound/asoc.h | 4 ++-- 13 files changed, 56 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h index e89f9e0094b4..c7816c83e324 100644 --- a/drivers/crypto/chelsio/chcr_crypto.h +++ b/drivers/crypto/chelsio/chcr_crypto.h @@ -222,8 +222,10 @@ struct chcr_authenc_ctx { }; struct __aead_ctx { - struct chcr_gcm_ctx gcm[0]; - struct chcr_authenc_ctx authenc[]; + union { + DECLARE_FLEX_ARRAY(struct chcr_gcm_ctx, gcm); + DECLARE_FLEX_ARRAY(struct chcr_authenc_ctx, authenc); + }; }; struct chcr_aead_ctx { @@ -245,9 +247,11 @@ struct hmac_ctx { }; struct __crypto_ctx { - struct hmac_ctx hmacctx[0]; - struct ablk_ctx ablkctx[0]; - struct chcr_aead_ctx aeadctx[]; + union { + DECLARE_FLEX_ARRAY(struct hmac_ctx, hmacctx); + DECLARE_FLEX_ARRAY(struct ablk_ctx, ablkctx); + DECLARE_FLEX_ARRAY(struct chcr_aead_ctx, aeadctx); + }; }; struct chcr_context { diff --git a/drivers/net/can/usb/etas_es58x/es581_4.h b/drivers/net/can/usb/etas_es58x/es581_4.h index 4bc60a6df697..667ecb77168c 100644 --- a/drivers/net/can/usb/etas_es58x/es581_4.h +++ b/drivers/net/can/usb/etas_es58x/es581_4.h @@ -192,7 +192,7 @@ struct es581_4_urb_cmd { struct es581_4_rx_cmd_ret rx_cmd_ret; __le64 timestamp; u8 rx_cmd_ret_u8; - u8 raw_msg[0]; + DECLARE_FLEX_ARRAY(u8, raw_msg); } __packed; __le16 reserved_for_crc16_do_not_use; diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.h b/drivers/net/can/usb/etas_es58x/es58x_fd.h index a191891b8777..c4b19a6a33ae 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.h +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.h @@ -219,7 +219,7 @@ struct es58x_fd_urb_cmd { struct es58x_fd_tx_ack_msg tx_ack_msg; __le64 timestamp; __le32 rx_cmd_ret_le32; - u8 raw_msg[0]; + DECLARE_FLEX_ARRAY(u8, raw_msg); } __packed; __le16 reserved_for_crc16_do_not_use; diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index ec689e3ce48a..a6de08d3bf4a 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -1674,8 +1674,11 @@ struct htt_tx_fetch_ind { __le32 token; __le16 num_resp_ids; __le16 num_records; - __le32 resp_ids[0]; /* ath10k_htt_get_tx_fetch_ind_resp_ids() */ - struct htt_tx_fetch_record records[]; + union { + /* ath10k_htt_get_tx_fetch_ind_resp_ids() */ + DECLARE_FLEX_ARRAY(__le32, resp_ids); + DECLARE_FLEX_ARRAY(struct htt_tx_fetch_record, records); + }; } __packed; static inline void * diff --git a/drivers/net/wireless/intel/iwlegacy/commands.h b/drivers/net/wireless/intel/iwlegacy/commands.h index 89c6671b32bc..4a97310f8fee 100644 --- a/drivers/net/wireless/intel/iwlegacy/commands.h +++ b/drivers/net/wireless/intel/iwlegacy/commands.h @@ -1408,8 +1408,10 @@ struct il3945_tx_cmd { * MAC header goes here, followed by 2 bytes padding if MAC header * length is 26 or 30 bytes, followed by payload data */ - u8 payload[0]; - struct ieee80211_hdr hdr[]; + union { + DECLARE_FLEX_ARRAY(u8, payload); + DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr); + }; } __packed; /* diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/commands.h b/drivers/net/wireless/intel/iwlwifi/dvm/commands.h index 235c7a2e3483..75a4b8e26232 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/dvm/commands.h @@ -1251,8 +1251,10 @@ struct iwl_tx_cmd { * MAC header goes here, followed by 2 bytes padding if MAC header * length is 26 or 30 bytes, followed by payload data */ - u8 payload[0]; - struct ieee80211_hdr hdr[]; + union { + DECLARE_FLEX_ARRAY(u8, payload); + DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr); + }; } __packed; /* diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h index 24e4a82a55da..5fddfd391941 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h @@ -239,8 +239,10 @@ struct iwl_tx_cmd { u8 tid_tspec; __le16 pm_frame_timeout; __le16 reserved4; - u8 payload[0]; - struct ieee80211_hdr hdr[0]; + union { + DECLARE_FLEX_ARRAY(u8, payload); + DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr); + }; } __packed; /* TX_CMD_API_S_VER_6 */ struct iwl_dram_sec_info { @@ -713,8 +715,10 @@ struct iwl_mvm_compressed_ba_notif { __le32 tx_rate; __le16 tfd_cnt; __le16 ra_tid_cnt; - struct iwl_mvm_compressed_ba_ratid ra_tid[0]; - struct iwl_mvm_compressed_ba_tfd tfd[]; + union { + DECLARE_FLEX_ARRAY(struct iwl_mvm_compressed_ba_ratid, ra_tid); + DECLARE_FLEX_ARRAY(struct iwl_mvm_compressed_ba_tfd, tfd); + }; } __packed; /* COMPRESSED_BA_RES_API_S_VER_4 */ /** diff --git a/drivers/scsi/aic94xx/aic94xx_sds.c b/drivers/scsi/aic94xx/aic94xx_sds.c index 46815e65f7a4..5def83c88f13 100644 --- a/drivers/scsi/aic94xx/aic94xx_sds.c +++ b/drivers/scsi/aic94xx/aic94xx_sds.c @@ -517,8 +517,10 @@ struct asd_ms_conn_map { u8 num_nodes; u8 usage_model_id; u32 _resvd; - struct asd_ms_conn_desc conn_desc[0]; - struct asd_ms_node_desc node_desc[]; + union { + DECLARE_FLEX_ARRAY(struct asd_ms_conn_desc, conn_desc); + DECLARE_FLEX_ARRAY(struct asd_ms_node_desc, node_desc); + }; } __attribute__ ((packed)); struct asd_ctrla_phy_entry { diff --git a/fs/hpfs/hpfs.h b/fs/hpfs/hpfs.h index d92c4af3e1b4..281dec8f636b 100644 --- a/fs/hpfs/hpfs.h +++ b/fs/hpfs/hpfs.h @@ -409,10 +409,10 @@ struct bplus_header __le16 first_free; /* offset from start of header to first free node in array */ union { - struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving - subtree pointers */ - struct bplus_leaf_node external[0]; /* (external) 3-word entries giving - sector runs */ + /* (internal) 2-word entries giving subtree pointers */ + DECLARE_FLEX_ARRAY(struct bplus_internal_node, internal); + /* (external) 3-word entries giving sector runs */ + DECLARE_FLEX_ARRAY(struct bplus_leaf_node, external); } u; }; diff --git a/include/linux/filter.h b/include/linux/filter.h index 4a93c12543ee..4298c5e428a3 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -586,8 +586,10 @@ struct bpf_prog { struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ - struct sock_filter insns[0]; - struct bpf_insn insnsi[]; + union { + DECLARE_FLEX_ARRAY(struct sock_filter, insns); + DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); + }; }; struct sk_filter { diff --git a/include/scsi/sas.h b/include/scsi/sas.h index 4726c1bbec65..64154c1fed02 100644 --- a/include/scsi/sas.h +++ b/include/scsi/sas.h @@ -323,8 +323,10 @@ struct ssp_response_iu { __be32 sense_data_len; __be32 response_data_len; - u8 resp_data[0]; - u8 sense_data[]; + union { + DECLARE_FLEX_ARRAY(u8, resp_data); + DECLARE_FLEX_ARRAY(u8, sense_data); + }; } __attribute__ ((packed)); struct ssp_command_iu { @@ -554,8 +556,10 @@ struct ssp_response_iu { __be32 sense_data_len; __be32 response_data_len; - u8 resp_data[0]; - u8 sense_data[]; + union { + DECLARE_FLEX_ARRAY(u8, resp_data); + DECLARE_FLEX_ARRAY(u8, sense_data); + }; } __attribute__ ((packed)); struct ssp_command_iu { diff --git a/include/uapi/rdma/rdma_user_rxe.h b/include/uapi/rdma/rdma_user_rxe.h index e283c2220aba..7f44d54bb0ab 100644 --- a/include/uapi/rdma/rdma_user_rxe.h +++ b/include/uapi/rdma/rdma_user_rxe.h @@ -141,8 +141,8 @@ struct rxe_dma_info { __u32 sge_offset; __u32 reserved; union { - __u8 inline_data[0]; - struct rxe_sge sge[0]; + __DECLARE_FLEX_ARRAY(__u8, inline_data); + __DECLARE_FLEX_ARRAY(struct rxe_sge, sge); }; }; diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index da61398b1f8f..053949287ce8 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -240,8 +240,8 @@ struct snd_soc_tplg_vendor_array { struct snd_soc_tplg_private { __le32 size; /* in bytes of private data */ union { - char data[0]; - struct snd_soc_tplg_vendor_array array[0]; + __DECLARE_FLEX_ARRAY(char, data); + __DECLARE_FLEX_ARRAY(struct snd_soc_tplg_vendor_array, array); }; } __attribute__((packed)); -- cgit v1.2.3 From 47c662486cccf03e7062139d069b07ab0126ef59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 13 Aug 2021 12:19:24 -0700 Subject: treewide: Replace 0-element memcpy() destinations with flexible arrays The 0-element arrays that are used as memcpy() destinations are actually flexible arrays. Adjust their structures accordingly so that memcpy() can better reason able their destination size (i.e. they need to be seen as "unknown" length rather than "zero"). In some cases, use of the DECLARE_FLEX_ARRAY() helper is needed when a flexible array is alone in a struct. Cc: "Gustavo A. R. Silva" Cc: Arnd Bergmann Cc: Kalle Valo Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Nilesh Javali Cc: Manish Rangankar Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Larry Finger Cc: Phillip Potter Cc: Greg Kroah-Hartman Cc: Florian Schilhabel Cc: Johannes Berg Cc: Christophe JAILLET Cc: Fabio Aiuto Cc: Ross Schmidt Cc: Marco Cesati Cc: ath10k@lists.infradead.org Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: linux-staging@lists.linux.dev Signed-off-by: Kees Cook --- drivers/net/wireless/ath/ath10k/bmi.h | 10 ++++----- drivers/scsi/qla4xxx/ql4_def.h | 4 ++-- drivers/staging/r8188eu/include/ieee80211.h | 6 +++--- drivers/staging/rtl8712/ieee80211.h | 4 ++-- drivers/staging/rtl8723bs/include/ieee80211.h | 6 +++--- include/linux/ieee80211.h | 30 +++++++++++++-------------- include/uapi/linux/dlm_device.h | 4 ++-- 7 files changed, 32 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/ath/ath10k/bmi.h b/drivers/net/wireless/ath/ath10k/bmi.h index f6fadcbdd86e..0685c0d2d4ea 100644 --- a/drivers/net/wireless/ath/ath10k/bmi.h +++ b/drivers/net/wireless/ath/ath10k/bmi.h @@ -109,7 +109,7 @@ struct bmi_cmd { struct { __le32 addr; __le32 len; - u8 payload[0]; + u8 payload[]; } write_mem; struct { __le32 addr; @@ -138,18 +138,18 @@ struct bmi_cmd { } rompatch_uninstall; struct { __le32 count; - __le32 patch_ids[0]; /* length of @count */ + __le32 patch_ids[]; /* length of @count */ } rompatch_activate; struct { __le32 count; - __le32 patch_ids[0]; /* length of @count */ + __le32 patch_ids[]; /* length of @count */ } rompatch_deactivate; struct { __le32 addr; } lz_start; struct { __le32 len; /* max BMI_MAX_DATA_SIZE */ - u8 payload[0]; /* length of @len */ + u8 payload[]; /* length of @len */ } lz_data; struct { u8 name[BMI_NVRAM_SEG_NAME_SZ]; @@ -160,7 +160,7 @@ struct bmi_cmd { union bmi_resp { struct { - u8 payload[0]; + DECLARE_FLEX_ARRAY(u8, payload); } read_mem; struct { __le32 result; diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index 031569c496e5..69a590546bf9 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -366,13 +366,13 @@ struct qla4_work_evt { struct { enum iscsi_host_event_code code; uint32_t data_size; - uint8_t data[0]; + uint8_t data[]; } aen; struct { uint32_t status; uint32_t pid; uint32_t data_size; - uint8_t data[0]; + uint8_t data[]; } ping; } u; }; diff --git a/drivers/staging/r8188eu/include/ieee80211.h b/drivers/staging/r8188eu/include/ieee80211.h index bc5b030e9c40..9204dd42f319 100644 --- a/drivers/staging/r8188eu/include/ieee80211.h +++ b/drivers/staging/r8188eu/include/ieee80211.h @@ -185,7 +185,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct { int command; @@ -198,7 +198,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; #ifdef CONFIG_88EU_AP_MODE struct { @@ -210,7 +210,7 @@ struct ieee_param { } add_sta; struct { u8 reserved[2];/* for set max_num_sta */ - u8 buf[0]; + u8 buf[]; } bcn_ie; #endif diff --git a/drivers/staging/rtl8712/ieee80211.h b/drivers/staging/rtl8712/ieee80211.h index 61eff7c5746b..65ceaca9b51e 100644 --- a/drivers/staging/rtl8712/ieee80211.h +++ b/drivers/staging/rtl8712/ieee80211.h @@ -78,7 +78,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct { int command; @@ -91,7 +91,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; } u; }; diff --git a/drivers/staging/rtl8723bs/include/ieee80211.h b/drivers/staging/rtl8723bs/include/ieee80211.h index d6236f5b069d..c11d7e2d2347 100644 --- a/drivers/staging/rtl8723bs/include/ieee80211.h +++ b/drivers/staging/rtl8723bs/include/ieee80211.h @@ -172,7 +172,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct{ int command; @@ -185,7 +185,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; struct { u16 aid; @@ -196,7 +196,7 @@ struct ieee_param { } add_sta; struct { u8 reserved[2];/* for set max_num_sta */ - u8 buf[0]; + u8 buf[]; } bcn_ie; } u; }; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 694264503119..ada3dd79cd08 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1143,7 +1143,7 @@ struct ieee80211_mgmt { __le16 auth_transaction; __le16 status_code; /* possibly followed by Challenge text */ - u8 variable[0]; + u8 variable[]; } __packed auth; struct { __le16 reason_code; @@ -1152,26 +1152,26 @@ struct ieee80211_mgmt { __le16 capab_info; __le16 listen_interval; /* followed by SSID and Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed assoc_req; struct { __le16 capab_info; __le16 status_code; __le16 aid; /* followed by Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed assoc_resp, reassoc_resp; struct { __le16 capab_info; __le16 status_code; - u8 variable[0]; + u8 variable[]; } __packed s1g_assoc_resp, s1g_reassoc_resp; struct { __le16 capab_info; __le16 listen_interval; u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed reassoc_req; struct { __le16 reason_code; @@ -1182,11 +1182,11 @@ struct ieee80211_mgmt { __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params, TIM */ - u8 variable[0]; + u8 variable[]; } __packed beacon; struct { /* only variable items: SSID, Supported rates */ - u8 variable[0]; + DECLARE_FLEX_ARRAY(u8, variable); } __packed probe_req; struct { __le64 timestamp; @@ -1194,7 +1194,7 @@ struct ieee80211_mgmt { __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params */ - u8 variable[0]; + u8 variable[]; } __packed probe_resp; struct { u8 category; @@ -1203,16 +1203,16 @@ struct ieee80211_mgmt { u8 action_code; u8 dialog_token; u8 status_code; - u8 variable[0]; + u8 variable[]; } __packed wme_action; struct{ u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed chan_switch; struct{ u8 action_code; struct ieee80211_ext_chansw_ie data; - u8 variable[0]; + u8 variable[]; } __packed ext_chan_switch; struct{ u8 action_code; @@ -1228,7 +1228,7 @@ struct ieee80211_mgmt { __le16 timeout; __le16 start_seq_num; /* followed by BA Extension */ - u8 variable[0]; + u8 variable[]; } __packed addba_req; struct{ u8 action_code; @@ -1244,11 +1244,11 @@ struct ieee80211_mgmt { } __packed delba; struct { u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed self_prot; struct{ u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed mesh_action; struct { u8 action; @@ -1292,7 +1292,7 @@ struct ieee80211_mgmt { u8 toa[6]; __le16 tod_error; __le16 toa_error; - u8 variable[0]; + u8 variable[]; } __packed ftm; struct { u8 action_code; diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index f880d2831160..e83954c69fff 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[0]; + char name[]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[0]; + char name[]; }; struct dlm_purge_params { -- cgit v1.2.3 From afd7de03c5268f74202c1dd4780a8532a11f4c6b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Oct 2021 08:53:19 -0600 Subject: block: remove some blk_mq_hw_ctx debugfs entries Just like the blk_mq_ctx counterparts, we've got a bunch of counters in here that are only for debugfs and are of questionnable value. They are: - dispatched, index of how many requests were dispatched in one go - poll_{considered,invoked,success}, which track poll sucess rates. We're confident in the iopoll implementation at this point, don't bother tracking these. As a bonus, this shrinks each hardware queue from 576 bytes to 512 bytes, dropping a whole cacheline. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 67 -------------------------------------------------- block/blk-mq.c | 16 ------------ include/linux/blk-mq.h | 10 -------- 3 files changed, 93 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 928a16af9175..68ca5d21cda7 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -529,70 +529,6 @@ out: return res; } -static int hctx_io_poll_show(void *data, struct seq_file *m) -{ - struct blk_mq_hw_ctx *hctx = data; - - seq_printf(m, "considered=%lu\n", hctx->poll_considered); - seq_printf(m, "invoked=%lu\n", hctx->poll_invoked); - seq_printf(m, "success=%lu\n", hctx->poll_success); - return 0; -} - -static ssize_t hctx_io_poll_write(void *data, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct blk_mq_hw_ctx *hctx = data; - - hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0; - return count; -} - -static int hctx_dispatched_show(void *data, struct seq_file *m) -{ - struct blk_mq_hw_ctx *hctx = data; - int i; - - seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]); - - for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) { - unsigned int d = 1U << (i - 1); - - seq_printf(m, "%8u\t%lu\n", d, hctx->dispatched[i]); - } - - seq_printf(m, "%8u+\t%lu\n", 1U << (i - 1), hctx->dispatched[i]); - return 0; -} - -static ssize_t hctx_dispatched_write(void *data, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct blk_mq_hw_ctx *hctx = data; - int i; - - for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++) - hctx->dispatched[i] = 0; - return count; -} - -static int hctx_queued_show(void *data, struct seq_file *m) -{ - struct blk_mq_hw_ctx *hctx = data; - - seq_printf(m, "%lu\n", hctx->queued); - return 0; -} - -static ssize_t hctx_queued_write(void *data, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct blk_mq_hw_ctx *hctx = data; - - hctx->queued = 0; - return count; -} - static int hctx_run_show(void *data, struct seq_file *m) { struct blk_mq_hw_ctx *hctx = data; @@ -738,9 +674,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = { {"tags_bitmap", 0400, hctx_tags_bitmap_show}, {"sched_tags", 0400, hctx_sched_tags_show}, {"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show}, - {"io_poll", 0600, hctx_io_poll_show, hctx_io_poll_write}, - {"dispatched", 0600, hctx_dispatched_show, hctx_dispatched_write}, - {"queued", 0600, hctx_queued_show, hctx_queued_write}, {"run", 0600, hctx_run_show, hctx_run_write}, {"active", 0400, hctx_active_show}, {"dispatch_busy", 0400, hctx_dispatch_busy_show}, diff --git a/block/blk-mq.c b/block/blk-mq.c index 990d214a7658..bd241fd7ee49 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -382,7 +382,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, } } - data->hctx->queued++; return rq; } @@ -1301,14 +1300,6 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, return data.rq; } -static inline unsigned int queued_to_index(unsigned int queued) -{ - if (!queued) - return 0; - - return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1); -} - static bool __blk_mq_get_driver_tag(struct request *rq) { struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; @@ -1632,8 +1623,6 @@ out: if (!list_empty(&zone_list)) list_splice_tail_init(&zone_list, list); - hctx->dispatched[queued_to_index(queued)]++; - /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ @@ -4200,14 +4189,9 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, long state = get_current_state(); int ret; - hctx->poll_considered++; - do { - hctx->poll_invoked++; - ret = q->mq_ops->poll(hctx); if (ret > 0) { - hctx->poll_success++; __set_current_state(TASK_RUNNING); return ret; } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 95c3bd3a008e..9fb8618fb957 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -341,9 +341,6 @@ struct blk_mq_hw_ctx { unsigned long queued; /** @run: Number of dispatched requests. */ unsigned long run; -#define BLK_MQ_MAX_DISPATCH_ORDER 7 - /** @dispatched: Number of dispatch requests by queue. */ - unsigned long dispatched[BLK_MQ_MAX_DISPATCH_ORDER]; /** @numa_node: NUMA node the storage adapter has been connected to. */ unsigned int numa_node; @@ -363,13 +360,6 @@ struct blk_mq_hw_ctx { /** @kobj: Kernel object for sysfs. */ struct kobject kobj; - /** @poll_considered: Count times blk_mq_poll() was called. */ - unsigned long poll_considered; - /** @poll_invoked: Count how many requests blk_mq_poll() polled. */ - unsigned long poll_invoked; - /** @poll_success: Count how many polled requests were completed. */ - unsigned long poll_success; - #ifdef CONFIG_BLK_DEBUG_FS /** * @debugfs_dir: debugfs directory for this hardware queue. Named -- cgit v1.2.3 From 013a7f95438144f4ab39a1017a0bff2765d2551a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 13 Oct 2021 07:58:52 -0600 Subject: block: provide helpers for rq_list manipulation Instead of open-coding the list additions, traversal, and removal, provide a basic set of helpers. Suggested-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 19 +++++-------------- include/linux/blkdev.h | 29 +++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index bd241fd7ee49..74505b545dd3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -404,17 +404,11 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data, tag = tag_offset + i; tags &= ~(1UL << i); rq = blk_mq_rq_ctx_init(data, tag, alloc_time_ns); - rq->rq_next = *data->cached_rq; - *data->cached_rq = rq; + rq_list_add(data->cached_rq, rq); } data->nr_tags -= nr; - if (!data->cached_rq) - return NULL; - - rq = *data->cached_rq; - *data->cached_rq = rq->rq_next; - return rq; + return rq_list_pop(data->cached_rq); } static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) @@ -622,11 +616,9 @@ EXPORT_SYMBOL_GPL(blk_mq_free_request); void blk_mq_free_plug_rqs(struct blk_plug *plug) { - while (plug->cached_rq) { - struct request *rq; + struct request *rq; - rq = plug->cached_rq; - plug->cached_rq = rq->rq_next; + while ((rq = rq_list_pop(&plug->cached_rq)) != NULL) { percpu_ref_get(&rq->q->q_usage_counter); blk_mq_free_request(rq); } @@ -2418,8 +2410,7 @@ void blk_mq_submit_bio(struct bio *bio) plug = blk_mq_plug(q, bio); if (plug && plug->cached_rq) { - rq = plug->cached_rq; - plug->cached_rq = rq->rq_next; + rq = rq_list_pop(&plug->cached_rq); INIT_LIST_HEAD(&rq->queuelist); } else { struct blk_mq_alloc_data data = { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d5b21fc8f49e..b0a322172965 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1298,4 +1298,33 @@ int fsync_bdev(struct block_device *bdev); int freeze_bdev(struct block_device *bdev); int thaw_bdev(struct block_device *bdev); +#define rq_list_add(listptr, rq) do { \ + (rq)->rq_next = *(listptr); \ + *(listptr) = rq; \ +} while (0) + +#define rq_list_pop(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) { \ + __req = *(listptr); \ + *(listptr) = __req->rq_next; \ + } \ + __req; \ +}) + +#define rq_list_peek(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) \ + __req = *(listptr); \ + __req; \ +}) + +#define rq_list_for_each(listptr, pos) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \ + +#define rq_list_next(rq) (rq)->rq_next +#define rq_list_empty(list) ((list) == (struct request *) NULL) + #endif /* _LINUX_BLKDEV_H */ -- cgit v1.2.3 From 5a72e899ceb465d731c413d57c6c12cdbf88303c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Oct 2021 09:24:29 -0600 Subject: block: add a struct io_comp_batch argument to fops->iopoll() struct io_comp_batch contains a list head and a completion handler, which will allow completions to more effciently completed batches of IO. For now, no functional changes in this patch, we just define the io_comp_batch structure and add the argument to the file_operations iopoll handler. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 9 +++++---- block/blk-exec.c | 2 +- block/blk-mq.c | 9 +++++---- block/blk-mq.h | 3 ++- block/fops.c | 4 ++-- drivers/block/rnbd/rnbd-clt.c | 2 +- drivers/nvme/host/pci.c | 4 ++-- drivers/nvme/host/rdma.c | 2 +- drivers/nvme/host/tcp.c | 2 +- drivers/scsi/scsi_lib.c | 2 +- fs/io_uring.c | 2 +- fs/iomap/direct-io.c | 2 +- include/linux/blk-mq.h | 2 +- include/linux/blkdev.h | 13 +++++++++++-- include/linux/fs.h | 4 +++- mm/page_io.c | 2 +- 16 files changed, 39 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 20b6cc06461a..d0c2e11411d0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1078,7 +1078,7 @@ EXPORT_SYMBOL(submit_bio); * Note: the caller must either be the context that submitted @bio, or * be in a RCU critical section to prevent freeing of @bio. */ -int bio_poll(struct bio *bio, unsigned int flags) +int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) { struct request_queue *q = bio->bi_bdev->bd_disk->queue; blk_qc_t cookie = READ_ONCE(bio->bi_cookie); @@ -1096,7 +1096,7 @@ int bio_poll(struct bio *bio, unsigned int flags) if (WARN_ON_ONCE(!queue_is_mq(q))) ret = 0; /* not yet implemented, should not happen */ else - ret = blk_mq_poll(q, cookie, flags); + ret = blk_mq_poll(q, cookie, iob, flags); blk_queue_exit(q); return ret; } @@ -1106,7 +1106,8 @@ EXPORT_SYMBOL_GPL(bio_poll); * Helper to implement file_operations.iopoll. Requires the bio to be stored * in iocb->private, and cleared before freeing the bio. */ -int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags) +int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, + unsigned int flags) { struct bio *bio; int ret = 0; @@ -1134,7 +1135,7 @@ int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags) rcu_read_lock(); bio = READ_ONCE(kiocb->private); if (bio && bio->bi_bdev) - ret = bio_poll(bio, flags); + ret = bio_poll(bio, iob, flags); rcu_read_unlock(); return ret; diff --git a/block/blk-exec.c b/block/blk-exec.c index 55f0cd34b37b..1b8b47f6e79b 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -77,7 +77,7 @@ static bool blk_rq_is_poll(struct request *rq) static void blk_rq_poll_completion(struct request *rq, struct completion *wait) { do { - bio_poll(rq->bio, 0); + bio_poll(rq->bio, NULL, 0); cond_resched(); } while (!completion_done(wait)); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 74505b545dd3..79c25b64e8b0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4174,14 +4174,14 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, blk_qc_t qc) } static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, - unsigned int flags) + struct io_comp_batch *iob, unsigned int flags) { struct blk_mq_hw_ctx *hctx = blk_qc_to_hctx(q, cookie); long state = get_current_state(); int ret; do { - ret = q->mq_ops->poll(hctx); + ret = q->mq_ops->poll(hctx, iob); if (ret > 0) { __set_current_state(TASK_RUNNING); return ret; @@ -4201,14 +4201,15 @@ static int blk_mq_poll_classic(struct request_queue *q, blk_qc_t cookie, return 0; } -int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags) +int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, + unsigned int flags) { if (!(flags & BLK_POLL_NOSLEEP) && q->poll_nsec != BLK_MQ_POLL_CLASSIC) { if (blk_mq_poll_hybrid(q, cookie)) return 1; } - return blk_mq_poll_classic(q, cookie, flags); + return blk_mq_poll_classic(q, cookie, iob, flags); } unsigned int blk_mq_rq_cpu(struct request *rq) diff --git a/block/blk-mq.h b/block/blk-mq.h index 1b91a3fdaa01..ebf67f4d4f2e 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -31,7 +31,8 @@ struct blk_mq_ctx { } ____cacheline_aligned_in_smp; void blk_mq_submit_bio(struct bio *bio); -int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, unsigned int flags); +int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, struct io_comp_batch *iob, + unsigned int flags); void blk_mq_exit_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); diff --git a/block/fops.c b/block/fops.c index 1d4f862950bb..2c43e493e37c 100644 --- a/block/fops.c +++ b/block/fops.c @@ -105,7 +105,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, set_current_state(TASK_UNINTERRUPTIBLE); if (!READ_ONCE(bio.bi_private)) break; - if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, 0)) + if (!(iocb->ki_flags & IOCB_HIPRI) || !bio_poll(&bio, NULL, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); @@ -291,7 +291,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, if (!READ_ONCE(dio->waiter)) break; - if (!do_poll || !bio_poll(bio, 0)) + if (!do_poll || !bio_poll(bio, NULL, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index bd4a41afbbfc..0ec0191d4196 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1176,7 +1176,7 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx, return ret; } -static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx) +static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct rnbd_queue *q = hctx->driver_data; struct rnbd_clt_dev *dev = q->dev; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 896328271471..bb0482dfab3c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1092,7 +1092,7 @@ static void nvme_poll_irqdisable(struct nvme_queue *nvmeq) enable_irq(pci_irq_vector(pdev, nvmeq->cq_vector)); } -static int nvme_poll(struct blk_mq_hw_ctx *hctx) +static int nvme_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct nvme_queue *nvmeq = hctx->driver_data; bool found; @@ -1274,7 +1274,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) * Did we miss an interrupt? */ if (test_bit(NVMEQ_POLLED, &nvmeq->flags)) - nvme_poll(req->mq_hctx); + nvme_poll(req->mq_hctx, NULL); else nvme_poll_irqdisable(nvmeq); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 40317e1b9183..1624da3702d4 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -2106,7 +2106,7 @@ unmap_qe: return ret; } -static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx) +static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct nvme_rdma_queue *queue = hctx->driver_data; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 3c1c29dd3020..9ce3458ee1dd 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2429,7 +2429,7 @@ static int nvme_tcp_map_queues(struct blk_mq_tag_set *set) return 0; } -static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx) +static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct nvme_tcp_queue *queue = hctx->driver_data; struct sock *sk = queue->sock->sk; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 33fd9a01330c..30f7d0b4eb73 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1784,7 +1784,7 @@ static void scsi_mq_exit_request(struct blk_mq_tag_set *set, struct request *rq, } -static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx) +static int scsi_mq_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) { struct Scsi_Host *shost = hctx->driver_data; diff --git a/fs/io_uring.c b/fs/io_uring.c index c5066146b8de..cd77a137f2d8 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2483,7 +2483,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, if (!list_empty(&done)) break; - ret = kiocb->ki_filp->f_op->iopoll(kiocb, poll_flags); + ret = kiocb->ki_filp->f_op->iopoll(kiocb, NULL, poll_flags); if (unlikely(ret < 0)) return ret; else if (ret) diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 8efab177011d..83ecfba53abe 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -630,7 +630,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, break; if (!dio->submit.poll_bio || - !bio_poll(dio->submit.poll_bio, 0)) + !bio_poll(dio->submit.poll_bio, NULL, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9fb8618fb957..4c79439af2f2 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -532,7 +532,7 @@ struct blk_mq_ops { /** * @poll: Called to poll for completion of a specific tag. */ - int (*poll)(struct blk_mq_hw_ctx *); + int (*poll)(struct blk_mq_hw_ctx *, struct io_comp_batch *); /** * @complete: Mark the request as complete. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b0a322172965..fd9771a1da09 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -569,8 +569,9 @@ blk_status_t errno_to_blk_status(int errno); #define BLK_POLL_ONESHOT (1 << 0) /* do not sleep to wait for the expected completion time */ #define BLK_POLL_NOSLEEP (1 << 1) -int bio_poll(struct bio *bio, unsigned int flags); -int iocb_bio_iopoll(struct kiocb *kiocb, unsigned int flags); +int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags); +int iocb_bio_iopoll(struct kiocb *kiocb, struct io_comp_batch *iob, + unsigned int flags); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { @@ -1298,6 +1299,14 @@ int fsync_bdev(struct block_device *bdev); int freeze_bdev(struct block_device *bdev); int thaw_bdev(struct block_device *bdev); +struct io_comp_batch { + struct request *req_list; + bool need_ts; + void (*complete)(struct io_comp_batch *); +}; + +#define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } + #define rq_list_add(listptr, rq) do { \ (rq)->rq_next = *(listptr); \ *(listptr) = rq; \ diff --git a/include/linux/fs.h b/include/linux/fs.h index f595f4097cb7..31029a91f440 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -48,6 +48,7 @@ struct backing_dev_info; struct bdi_writeback; struct bio; +struct io_comp_batch; struct export_operations; struct fiemap_extent_info; struct hd_geometry; @@ -2071,7 +2072,8 @@ struct file_operations { ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); - int (*iopoll)(struct kiocb *kiocb, unsigned int flags); + int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *, + unsigned int flags); int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); diff --git a/mm/page_io.c b/mm/page_io.c index a68faab5b310..6010fb07f231 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -424,7 +424,7 @@ int swap_readpage(struct page *page, bool synchronous) if (!READ_ONCE(bio->bi_private)) break; - if (!bio_poll(bio, 0)) + if (!bio_poll(bio, NULL, 0)) blk_io_schedule(); } __set_current_state(TASK_RUNNING); -- cgit v1.2.3 From 1aec5e4a2962f7e0b3fb3e7308dd726be2472c26 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 8 Oct 2021 05:44:23 -0600 Subject: sbitmap: add helper to clear a batch of tags sbitmap currently only supports clearing tags one-by-one, add a helper that allows the caller to pass in an array of tags to clear. Signed-off-by: Jens Axboe --- include/linux/sbitmap.h | 11 +++++++++++ lib/sbitmap.c | 44 +++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 52 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index e30b56023ead..4a6ff274335a 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -528,6 +528,17 @@ void sbitmap_queue_min_shallow_depth(struct sbitmap_queue *sbq, void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu); +/** + * sbitmap_queue_clear_batch() - Free a batch of allocated bits + * &struct sbitmap_queue. + * @sbq: Bitmap to free from. + * @offset: offset for each tag in array + * @tags: array of tags + * @nr_tags: number of tags in array + */ +void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, + int *tags, int nr_tags); + static inline int sbq_index_inc(int index) { return (index + 1) & (SBQ_WAIT_QUEUES - 1); diff --git a/lib/sbitmap.c b/lib/sbitmap.c index f398e0ae548e..c6e2f1f2c4d2 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -628,6 +628,46 @@ void sbitmap_queue_wake_up(struct sbitmap_queue *sbq) } EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up); +static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag) +{ + if (likely(!sb->round_robin && tag < sb->depth)) + *per_cpu_ptr(sb->alloc_hint, cpu) = tag; +} + +void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset, + int *tags, int nr_tags) +{ + struct sbitmap *sb = &sbq->sb; + unsigned long *addr = NULL; + unsigned long mask = 0; + int i; + + smp_mb__before_atomic(); + for (i = 0; i < nr_tags; i++) { + const int tag = tags[i] - offset; + unsigned long *this_addr; + + /* since we're clearing a batch, skip the deferred map */ + this_addr = &sb->map[SB_NR_TO_INDEX(sb, tag)].word; + if (!addr) { + addr = this_addr; + } else if (addr != this_addr) { + atomic_long_andnot(mask, (atomic_long_t *) addr); + mask = 0; + addr = this_addr; + } + mask |= (1UL << SB_NR_TO_BIT(sb, tag)); + } + + if (mask) + atomic_long_andnot(mask, (atomic_long_t *) addr); + + smp_mb__after_atomic(); + sbitmap_queue_wake_up(sbq); + sbitmap_update_cpu_hint(&sbq->sb, raw_smp_processor_id(), + tags[nr_tags - 1] - offset); +} + void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, unsigned int cpu) { @@ -652,9 +692,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, */ smp_mb__after_atomic(); sbitmap_queue_wake_up(sbq); - - if (likely(!sbq->sb.round_robin && nr < sbq->sb.depth)) - *per_cpu_ptr(sbq->sb.alloc_hint, cpu) = nr; + sbitmap_update_cpu_hint(&sbq->sb, cpu, nr); } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); -- cgit v1.2.3 From f794f3351f2672d782b8df0fa59f3cef38cffa59 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 8 Oct 2021 05:50:46 -0600 Subject: block: add support for blk_mq_end_request_batch() Instead of calling blk_mq_end_request() on a single request, add a helper that takes the new struct io_comp_batch and completes any request stored in there. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 6 ++++ block/blk-mq-tag.h | 1 + block/blk-mq.c | 82 ++++++++++++++++++++++++++++++++++++++------------ include/linux/blk-mq.h | 29 ++++++++++++++++++ 4 files changed, 99 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index c43b97201161..b94c3e8ef392 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -207,6 +207,12 @@ void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, } } +void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags) +{ + sbitmap_queue_clear_batch(&tags->bitmap_tags, tags->nr_reserved_tags, + tag_array, nr_tags); +} + struct bt_iter_data { struct blk_mq_hw_ctx *hctx; busy_iter_fn *fn; diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 71c2f7d8e9b7..78ae2fb8e2a4 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -42,6 +42,7 @@ unsigned long blk_mq_get_tags(struct blk_mq_alloc_data *data, int nr_tags, unsigned int *offset); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); +void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); diff --git a/block/blk-mq.c b/block/blk-mq.c index 79c25b64e8b0..9248edd8a7d3 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -300,15 +300,6 @@ void blk_mq_wake_waiters(struct request_queue *q) blk_mq_tag_wakeup_all(hctx->tags, true); } -/* - * Only need start/end time stamping if we have iostat or - * blk stats enabled, or using an IO scheduler. - */ -static inline bool blk_mq_need_time_stamp(struct request *rq) -{ - return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); -} - static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, unsigned int tag, u64 alloc_time_ns) { @@ -768,19 +759,21 @@ bool blk_update_request(struct request *req, blk_status_t error, } EXPORT_SYMBOL_GPL(blk_update_request); -inline void __blk_mq_end_request(struct request *rq, blk_status_t error) +static inline void __blk_mq_end_request_acct(struct request *rq, u64 now) { - if (blk_mq_need_time_stamp(rq)) { - u64 now = ktime_get_ns(); + if (rq->rq_flags & RQF_STATS) { + blk_mq_poll_stats_start(rq->q); + blk_stat_add(rq, now); + } - if (rq->rq_flags & RQF_STATS) { - blk_mq_poll_stats_start(rq->q); - blk_stat_add(rq, now); - } + blk_mq_sched_completed_request(rq, now); + blk_account_io_done(rq, now); +} - blk_mq_sched_completed_request(rq, now); - blk_account_io_done(rq, now); - } +inline void __blk_mq_end_request(struct request *rq, blk_status_t error) +{ + if (blk_mq_need_time_stamp(rq)) + __blk_mq_end_request_acct(rq, ktime_get_ns()); if (rq->end_io) { rq_qos_done(rq->q, rq); @@ -799,6 +792,57 @@ void blk_mq_end_request(struct request *rq, blk_status_t error) } EXPORT_SYMBOL(blk_mq_end_request); +#define TAG_COMP_BATCH 32 + +static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx, + int *tag_array, int nr_tags) +{ + struct request_queue *q = hctx->queue; + + blk_mq_put_tags(hctx->tags, tag_array, nr_tags); + percpu_ref_put_many(&q->q_usage_counter, nr_tags); +} + +void blk_mq_end_request_batch(struct io_comp_batch *iob) +{ + int tags[TAG_COMP_BATCH], nr_tags = 0; + struct blk_mq_hw_ctx *last_hctx = NULL; + struct request *rq; + u64 now = 0; + + if (iob->need_ts) + now = ktime_get_ns(); + + while ((rq = rq_list_pop(&iob->req_list)) != NULL) { + prefetch(rq->bio); + prefetch(rq->rq_next); + + blk_update_request(rq, BLK_STS_OK, blk_rq_bytes(rq)); + if (iob->need_ts) + __blk_mq_end_request_acct(rq, now); + + WRITE_ONCE(rq->state, MQ_RQ_IDLE); + if (!refcount_dec_and_test(&rq->ref)) + continue; + + blk_crypto_free_request(rq); + blk_pm_mark_last_busy(rq); + rq_qos_done(rq->q, rq); + + if (nr_tags == TAG_COMP_BATCH || + (last_hctx && last_hctx != rq->mq_hctx)) { + blk_mq_flush_tag_batch(last_hctx, tags, nr_tags); + nr_tags = 0; + } + tags[nr_tags++] = rq->tag; + last_hctx = rq->mq_hctx; + } + + if (nr_tags) + blk_mq_flush_tag_batch(last_hctx, tags, nr_tags); +} +EXPORT_SYMBOL_GPL(blk_mq_end_request_batch); + static void blk_complete_reqs(struct llist_head *list) { struct llist_node *entry = llist_reverse_order(llist_del_all(list)); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 4c79439af2f2..656fe34bdb6c 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -728,6 +728,35 @@ static inline void blk_mq_set_request_complete(struct request *rq) void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); +void blk_mq_end_request_batch(struct io_comp_batch *ib); + +/* + * Only need start/end time stamping if we have iostat or + * blk stats enabled, or using an IO scheduler. + */ +static inline bool blk_mq_need_time_stamp(struct request *rq) +{ + return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV)); +} + +/* + * Batched completions only work when there is no I/O error and no special + * ->end_io handler. + */ +static inline bool blk_mq_add_to_batch(struct request *req, + struct io_comp_batch *iob, int ioerror, + void (*complete)(struct io_comp_batch *)) +{ + if (!iob || (req->rq_flags & RQF_ELV) || req->end_io || ioerror) + return false; + if (!iob->complete) + iob->complete = complete; + else if (iob->complete != complete) + return false; + iob->need_ts |= blk_mq_need_time_stamp(req); + rq_list_add(&iob->req_list, req); + return true; +} void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); -- cgit v1.2.3 From 99457db8b40c66941072a383a5ab4e36bc53fd3d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Oct 2021 12:11:01 +0200 Subject: block: move the SECTOR_SIZE related definitions to blk_types.h Ensure these are always available for inlines in the various block layer headers. Signed-off-by: Christoph Hellwig Reviewed-by: Kees Cook Reviewed-by: Jan Kara Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20211018101130.1838532-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 17 +++++++++++++++++ include/linux/blkdev.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1e370929c89e..472e55e0e94f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -20,6 +20,23 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +/* + * The basic unit of block I/O is a sector. It is used in a number of contexts + * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 + * bytes. Variables of type sector_t represent an offset or size that is a + * multiple of 512 bytes. Hence these two constants. + */ +#ifndef SECTOR_SHIFT +#define SECTOR_SHIFT 9 +#endif +#ifndef SECTOR_SIZE +#define SECTOR_SIZE (1 << SECTOR_SHIFT) +#endif + +#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) +#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) +#define SECTOR_MASK (PAGE_SECTORS - 1) + struct block_device { sector_t bd_start_sect; struct disk_stats __percpu *bd_stats; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fd9771a1da09..abe721591e80 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -578,23 +578,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_queue; /* this is never NULL */ } -/* - * The basic unit of block I/O is a sector. It is used in a number of contexts - * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 - * bytes. Variables of type sector_t represent an offset or size that is a - * multiple of 512 bytes. Hence these two constants. - */ -#ifndef SECTOR_SHIFT -#define SECTOR_SHIFT 9 -#endif -#ifndef SECTOR_SIZE -#define SECTOR_SIZE (1 << SECTOR_SHIFT) -#endif - -#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) -#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) -#define SECTOR_MASK (PAGE_SECTORS - 1) - #ifdef CONFIG_BLK_DEV_ZONED /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ -- cgit v1.2.3 From 6436bd90f76e75d2c5786a50203b05a9b7f7100d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Oct 2021 12:11:02 +0200 Subject: block: add a bdev_nr_bytes helper Add a helper to query the size of a block device in bytes. This will be used to remove open coded access to ->bd_inode. Signed-off-by: Christoph Hellwig Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20211018101130.1838532-3-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index cd4038fd5743..01d27f3a970e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -236,9 +236,14 @@ static inline sector_t get_start_sect(struct block_device *bdev) return bdev->bd_start_sect; } +static inline loff_t bdev_nr_bytes(struct block_device *bdev) +{ + return i_size_read(bdev->bd_inode); +} + static inline sector_t bdev_nr_sectors(struct block_device *bdev) { - return i_size_read(bdev->bd_inode) >> 9; + return bdev_nr_bytes(bdev) >> SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) -- cgit v1.2.3 From bcc6e2cfaa48a4ad2e17719194f6d97a8e03f6c1 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 18 Oct 2021 12:11:25 +0200 Subject: block: add a sb_bdev_nr_blocks helper Add a helper to return the size of sb->s_bdev in sb->s_blocksize_bits based unites. Signed-off-by: Christoph Hellwig Reviewed-by: Kees Cook Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20211018101130.1838532-26-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 01d27f3a970e..7b0326661a1e 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -251,6 +251,12 @@ static inline sector_t get_capacity(struct gendisk *disk) return bdev_nr_sectors(disk->part0); } +static inline u64 sb_bdev_nr_blocks(struct super_block *sb) +{ + return bdev_nr_sectors(sb->s_bdev) >> + (sb->s_blocksize_bits - SECTOR_SHIFT); +} + int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); -- cgit v1.2.3 From f09313c57a17683cbcb305989daf1d94b49fd32c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Oct 2021 11:39:45 -0600 Subject: block: cache inode size in bdev Reading the inode size brings in a new cacheline for IO submit, and it's in the hot path being checked for every single IO. When doing millions of IOs per core per second, this is noticeable overhead. Cache the nr_sectors in the bdev itself. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/genhd.c | 1 + block/partitions/core.c | 1 + include/linux/blk_types.h | 1 + include/linux/genhd.h | 8 ++++---- 4 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 759bc06810f8..53495e3391e3 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -58,6 +58,7 @@ void set_capacity(struct gendisk *disk, sector_t sectors) spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + bdev->bd_nr_sectors = sectors; spin_unlock(&bdev->bd_size_lock); } EXPORT_SYMBOL(set_capacity); diff --git a/block/partitions/core.c b/block/partitions/core.c index 9dbddc355b40..66ef9bc6d6a1 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -91,6 +91,7 @@ static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) { spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + bdev->bd_nr_sectors = sectors; spin_unlock(&bdev->bd_size_lock); } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 472e55e0e94f..fe065c394fff 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -39,6 +39,7 @@ struct bio_crypt_ctx; struct block_device { sector_t bd_start_sect; + sector_t bd_nr_sectors; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 7b0326661a1e..900325aa5d31 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -236,14 +236,14 @@ static inline sector_t get_start_sect(struct block_device *bdev) return bdev->bd_start_sect; } -static inline loff_t bdev_nr_bytes(struct block_device *bdev) +static inline sector_t bdev_nr_sectors(struct block_device *bdev) { - return i_size_read(bdev->bd_inode); + return bdev->bd_nr_sectors; } -static inline sector_t bdev_nr_sectors(struct block_device *bdev) +static inline loff_t bdev_nr_bytes(struct block_device *bdev) { - return bdev_nr_bytes(bdev) >> SECTOR_SHIFT; + return bdev_nr_sectors(bdev) << SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) -- cgit v1.2.3 From 425a563acb1d1872c0036fbcb644247640edbbc6 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Sun, 23 May 2021 13:34:28 +0300 Subject: net/mlx5: Introduce port selection namespace Add new port selection flow steering namespace. Flow steering rules in this namespaceare are used to determine the physical port for egress packets. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 26 +++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 7 ++++-- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 6 ++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 + include/linux/mlx5/device.h | 15 +++++++++++++ include/linux/mlx5/fs.h | 1 + include/linux/mlx5/mlx5_ifc.h | 25 ++++++++++++++++++++-- 8 files changed, 78 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7db8df64a60e..caefdb7dfefe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -969,6 +969,7 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ case FS_FT_NIC_TX: case FS_FT_RDMA_RX: case FS_FT_RDMA_TX: + case FS_FT_PORT_SEL: return mlx5_fs_cmd_get_fw_cmds(); default: return mlx5_fs_cmd_get_stub_cmds(); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index fe501ba88bea..8d8696f7c3f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2191,6 +2191,10 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->fdb_root_ns) return &steering->fdb_root_ns->ns; return NULL; + case MLX5_FLOW_NAMESPACE_PORT_SEL: + if (steering->port_sel_root_ns) + return &steering->port_sel_root_ns->ns; + return NULL; case MLX5_FLOW_NAMESPACE_SNIFFER_RX: if (steering->sniffer_rx_root_ns) return &steering->sniffer_rx_root_ns->ns; @@ -2596,6 +2600,7 @@ void mlx5_cleanup_fs(struct mlx5_core_dev *dev) steering->fdb_root_ns = NULL; kfree(steering->fdb_sub_ns); steering->fdb_sub_ns = NULL; + cleanup_root_ns(steering->port_sel_root_ns); cleanup_root_ns(steering->sniffer_rx_root_ns); cleanup_root_ns(steering->sniffer_tx_root_ns); cleanup_root_ns(steering->rdma_rx_root_ns); @@ -2634,6 +2639,21 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) return PTR_ERR_OR_ZERO(prio); } +#define PORT_SEL_NUM_LEVELS 3 +static int init_port_sel_root_ns(struct mlx5_flow_steering *steering) +{ + struct fs_prio *prio; + + steering->port_sel_root_ns = create_root_ns(steering, FS_FT_PORT_SEL); + if (!steering->port_sel_root_ns) + return -ENOMEM; + + /* Create single prio */ + prio = fs_create_prio(&steering->port_sel_root_ns->ns, 0, + PORT_SEL_NUM_LEVELS); + return PTR_ERR_OR_ZERO(prio); +} + static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) { int err; @@ -3020,6 +3040,12 @@ int mlx5_init_fs(struct mlx5_core_dev *dev) goto err; } + if (MLX5_CAP_FLOWTABLE_PORT_SELECTION(dev, ft_support)) { + err = init_port_sel_root_ns(steering); + if (err) + goto err; + } + if (MLX5_CAP_FLOWTABLE_RDMA_RX(dev, ft_support) && MLX5_CAP_FLOWTABLE_RDMA_RX(dev, table_miss_action_domain)) { err = init_rdma_rx_root_ns(steering); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 98240badc342..79d37530afb3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -97,7 +97,8 @@ enum fs_flow_table_type { FS_FT_SNIFFER_TX = 0X6, FS_FT_RDMA_RX = 0X7, FS_FT_RDMA_TX = 0X8, - FS_FT_MAX_TYPE = FS_FT_RDMA_TX, + FS_FT_PORT_SEL = 0X9, + FS_FT_MAX_TYPE = FS_FT_PORT_SEL, }; enum fs_flow_table_op_mod { @@ -129,6 +130,7 @@ struct mlx5_flow_steering { struct mlx5_flow_root_namespace *rdma_rx_root_ns; struct mlx5_flow_root_namespace *rdma_tx_root_ns; struct mlx5_flow_root_namespace *egress_root_ns; + struct mlx5_flow_root_namespace *port_sel_root_ns; int esw_egress_acl_vports; int esw_ingress_acl_vports; }; @@ -341,7 +343,8 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node); (type == FS_FT_SNIFFER_TX) ? MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) : \ (type == FS_FT_RDMA_RX) ? MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) : \ (type == FS_FT_RDMA_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) : \ - (BUILD_BUG_ON_ZERO(FS_FT_RDMA_TX != FS_FT_MAX_TYPE))\ + (type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) : \ + (BUILD_BUG_ON_ZERO(FS_FT_PORT_SEL != FS_FT_MAX_TYPE))\ ) #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index f4f8993eac17..1037e3629e7e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -149,6 +149,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) if (err) return err; + if (MLX5_CAP_GEN(dev, port_selection_cap)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_PORT_SELECTION); + if (err) + return err; + } + if (MLX5_CAP_GEN(dev, hca_cap_2)) { err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL_2); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 47d92fb459ed..f8446395163a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1416,6 +1416,7 @@ static const int types[] = { MLX5_CAP_TLS, MLX5_CAP_VDPA_EMULATION, MLX5_CAP_IPSEC, + MLX5_CAP_PORT_SELECTION, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 109cc8106d16..347167c18802 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1185,6 +1185,7 @@ enum mlx5_cap_type { MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, MLX5_CAP_GENERAL_2 = 0x20, + MLX5_CAP_PORT_SELECTION = 0x25, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1342,6 +1343,20 @@ enum mlx5_qcam_feature_groups { MLX5_GET(e_switch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap) +#define MLX5_CAP_PORT_SELECTION(mdev, cap) \ + MLX5_GET(port_selection_cap, \ + mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap) + +#define MLX5_CAP_PORT_SELECTION_MAX(mdev, cap) \ + MLX5_GET(port_selection_cap, \ + mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->max, cap) + +#define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ + MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) + +#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \ + MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap) + #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap) diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 0106c67e8ccb..259fcc168340 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -83,6 +83,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_RX, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL, MLX5_FLOW_NAMESPACE_RDMA_TX, + MLX5_FLOW_NAMESPACE_PORT_SEL, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c614ad1da44d..db1d9c69c1fa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -767,6 +767,18 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 reserved_at_20c0[0x5f40]; }; +struct mlx5_ifc_port_selection_cap_bits { + u8 reserved_at_0[0x10]; + u8 port_select_flow_table[0x1]; + u8 reserved_at_11[0xf]; + + u8 reserved_at_20[0x1e0]; + + struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection; + + u8 reserved_at_400[0x7c00]; +}; + enum { MLX5_FDB_TO_VPORT_REG_C_0 = 0x01, MLX5_FDB_TO_VPORT_REG_C_1 = 0x02, @@ -1515,7 +1527,8 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 uar_4k[0x1]; u8 reserved_at_241[0x9]; u8 uar_sz[0x6]; - u8 reserved_at_248[0x2]; + u8 port_selection_cap[0x1]; + u8 reserved_at_248[0x1]; u8 umem_uid_0[0x1]; u8 reserved_at_250[0x5]; u8 log_pg_sz[0x8]; @@ -3164,6 +3177,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; + struct mlx5_ifc_port_selection_cap_bits port_selection_cap; struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap; struct mlx5_ifc_qos_cap_bits qos_cap; struct mlx5_ifc_debug_cap_bits debug_cap; @@ -10434,9 +10448,16 @@ struct mlx5_ifc_dcbx_param_bits { u8 reserved_at_a0[0x160]; }; +enum { + MLX5_LAG_PORT_SELECT_MODE_QUEUE_AFFINITY = 0, + MLX5_LAG_PORT_SELECT_MODE_PORT_SELECT_FT, +}; + struct mlx5_ifc_lagc_bits { u8 fdb_selection_mode[0x1]; - u8 reserved_at_1[0x1c]; + u8 reserved_at_1[0x14]; + u8 port_select_mode[0x3]; + u8 reserved_at_18[0x5]; u8 lag_state[0x3]; u8 reserved_at_20[0x14]; -- cgit v1.2.3 From e7e2519e3632396a25031b7e828ed35332e5dd07 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 6 Jul 2021 17:48:26 +0300 Subject: net/mlx5: Add support to create match definer Introduce new APIs to create and destroy flow matcher for given format id. Flow match definer object is used for defining the fields and mask used for the hash calculation. User should mask the desired fields like done in the match criteria. This object is assigned to flow group of type hash. In this flow group type, packets lookup is done based on the hash result. This patch also adds the required bits to create such flow group. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 57 +++++ drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h | 4 + drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 46 ++++ drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 5 + .../ethernet/mellanox/mlx5/core/steering/fs_dr.c | 15 ++ include/linux/mlx5/fs.h | 8 + include/linux/mlx5/mlx5_ifc.h | 272 +++++++++++++++++++-- 7 files changed, 380 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index caefdb7dfefe..2c82dc118460 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -185,6 +185,20 @@ static int mlx5_cmd_set_slave_root_fdb(struct mlx5_core_dev *master, return mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out)); } +static int +mlx5_cmd_stub_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return 0; +} + +static int +mlx5_cmd_stub_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return 0; +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) @@ -909,6 +923,45 @@ static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, mlx5_cmd_exec_in(dev, dealloc_modify_header_context, in); } +static int mlx5_cmd_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)]; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, definer_id); + + return mlx5_cmd_exec(ns->dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_cmd_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + u32 out[MLX5_ST_SZ_DW(create_match_definer_out)] = {}; + u32 in[MLX5_ST_SZ_DW(create_match_definer_in)] = {}; + struct mlx5_core_dev *dev = ns->dev; + void *ptr; + int err; + + MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(create_match_definer_in, in, general_obj_in_cmd_hdr.obj_type, + MLX5_OBJ_TYPE_MATCH_DEFINER); + + ptr = MLX5_ADDR_OF(create_match_definer_in, in, obj_context); + MLX5_SET(match_definer, ptr, format_id, format_id); + + ptr = MLX5_ADDR_OF(match_definer, ptr, match_mask); + memcpy(ptr, match_mask, MLX5_FLD_SZ_BYTES(match_definer, match_mask)); + + err = mlx5_cmd_exec_inout(dev, create_match_definer, in, out); + return err ? err : MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); +} + static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, .destroy_flow_table = mlx5_cmd_destroy_flow_table, @@ -923,6 +976,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_modify_header_dealloc, + .create_match_definer = mlx5_cmd_create_match_definer, + .destroy_match_definer = mlx5_cmd_destroy_match_definer, .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, @@ -942,6 +997,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc, + .create_match_definer = mlx5_cmd_stub_create_match_definer, + .destroy_match_definer = mlx5_cmd_stub_destroy_match_definer, .set_peer = mlx5_cmd_stub_set_peer, .create_ns = mlx5_cmd_stub_create_ns, .destroy_ns = mlx5_cmd_stub_destroy_ns, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index 5ecd33cdc087..220ec632d35a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -97,6 +97,10 @@ struct mlx5_flow_cmds { int (*create_ns)(struct mlx5_flow_root_namespace *ns); int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); + int (*create_match_definer)(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask); + int (*destroy_match_definer)(struct mlx5_flow_root_namespace *ns, + int definer_id); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 8d8696f7c3f5..873efde0d458 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -3250,6 +3250,52 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); +int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer) +{ + return definer->id; +} + +struct mlx5_flow_definer * +mlx5_create_match_definer(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type ns_type, u16 format_id, + u32 *match_mask) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_flow_definer *definer; + int id; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + definer = kzalloc(sizeof(*definer), GFP_KERNEL); + if (!definer) + return ERR_PTR(-ENOMEM); + + definer->ns_type = ns_type; + id = root->cmds->create_match_definer(root, format_id, match_mask); + if (id < 0) { + mlx5_core_warn(root->dev, "Failed to create match definer (%d)\n", id); + kfree(definer); + return ERR_PTR(id); + } + definer->id = id; + return definer; +} + +void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, + struct mlx5_flow_definer *definer) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, definer->ns_type); + if (WARN_ON(!root)) + return; + + root->cmds->destroy_match_definer(root, definer->id); + kfree(definer); +} + int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_root_namespace *peer_ns) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 79d37530afb3..7711db245c63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -49,6 +49,11 @@ #define FDB_TC_MAX_PRIO 16 #define FDB_TC_LEVELS_PER_PRIO 2 +struct mlx5_flow_definer { + enum mlx5_flow_namespace_type ns_type; + u32 id; +}; + struct mlx5_modify_hdr { enum mlx5_flow_namespace_type ns_type; union { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 230e920e3845..2632d5ae9bc0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -625,6 +625,19 @@ static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *n mlx5dr_action_destroy(modify_hdr->action.dr_action); } +static int +mlx5_cmd_dr_destroy_match_definer(struct mlx5_flow_root_namespace *ns, + int definer_id) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_dr_create_match_definer(struct mlx5_flow_root_namespace *ns, + u16 format_id, u32 *match_mask) +{ + return -EOPNOTSUPP; +} + static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct fs_fte *fte) @@ -727,6 +740,8 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { .packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc, .modify_header_alloc = mlx5_cmd_dr_modify_header_alloc, .modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc, + .create_match_definer = mlx5_cmd_dr_create_match_definer, + .destroy_match_definer = mlx5_cmd_dr_destroy_match_definer, .set_peer = mlx5_cmd_dr_set_peer, .create_ns = mlx5_cmd_dr_create_ns, .destroy_ns = mlx5_cmd_dr_destroy_ns, diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 259fcc168340..7a43fec63a35 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -98,6 +98,7 @@ enum { struct mlx5_pkt_reformat; struct mlx5_modify_hdr; +struct mlx5_flow_definer; struct mlx5_flow_table; struct mlx5_flow_group; struct mlx5_flow_namespace; @@ -258,6 +259,13 @@ struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, void *modify_actions); void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, struct mlx5_modify_hdr *modify_hdr); +struct mlx5_flow_definer * +mlx5_create_match_definer(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type ns_type, u16 format_id, + u32 *match_mask); +void mlx5_destroy_match_definer(struct mlx5_core_dev *dev, + struct mlx5_flow_definer *definer); +int mlx5_get_match_definer_id(struct mlx5_flow_definer *definer); struct mlx5_pkt_reformat_params { int type; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index db1d9c69c1fa..8f41145bc6ef 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -94,6 +94,7 @@ enum { enum { MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b, MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d, + MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018, MLX5_OBJ_TYPE_MKEY = 0xff01, MLX5_OBJ_TYPE_QP = 0xff02, MLX5_OBJ_TYPE_PSV = 0xff03, @@ -1731,7 +1732,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 flex_parser_id_outer_first_mpls_over_gre[0x4]; u8 flex_parser_id_outer_first_mpls_over_udp_label[0x4]; - u8 reserved_at_6e0[0x10]; + u8 max_num_match_definer[0x10]; u8 sf_base_id[0x10]; u8 flex_parser_id_gtpu_dw_2[0x4]; @@ -1746,7 +1747,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_760[0x20]; u8 vhca_tunnel_commands[0x40]; - u8 reserved_at_7c0[0x40]; + u8 match_definer_format_supported[0x40]; }; struct mlx5_ifc_cmd_hca_cap_2_bits { @@ -5666,6 +5667,236 @@ struct mlx5_ifc_query_fte_in_bits { u8 reserved_at_120[0xe0]; }; +struct mlx5_ifc_match_definer_format_0_bits { + u8 reserved_at_0[0x100]; + + u8 metadata_reg_c_0[0x20]; + + u8 metadata_reg_c_1[0x20]; + + u8 outer_dmac_47_16[0x20]; + + u8 outer_dmac_15_0[0x10]; + u8 outer_ethertype[0x10]; + + u8 reserved_at_180[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 outer_ip_frag[0x1]; + u8 outer_qp_type[0x2]; + u8 outer_encap_type[0x2]; + u8 port_number[0x2]; + u8 outer_l3_type[0x2]; + u8 outer_l4_type[0x2]; + u8 outer_first_vlan_type[0x2]; + u8 outer_first_vlan_prio[0x3]; + u8 outer_first_vlan_cfi[0x1]; + u8 outer_first_vlan_vid[0xc]; + + u8 outer_l4_type_ext[0x4]; + u8 reserved_at_1a4[0x2]; + u8 outer_ipsec_layer[0x2]; + u8 outer_l2_type[0x2]; + u8 force_lb[0x1]; + u8 outer_l2_ok[0x1]; + u8 outer_l3_ok[0x1]; + u8 outer_l4_ok[0x1]; + u8 outer_second_vlan_type[0x2]; + u8 outer_second_vlan_prio[0x3]; + u8 outer_second_vlan_cfi[0x1]; + u8 outer_second_vlan_vid[0xc]; + + u8 outer_smac_47_16[0x20]; + + u8 outer_smac_15_0[0x10]; + u8 inner_ipv4_checksum_ok[0x1]; + u8 inner_l4_checksum_ok[0x1]; + u8 outer_ipv4_checksum_ok[0x1]; + u8 outer_l4_checksum_ok[0x1]; + u8 inner_l3_ok[0x1]; + u8 inner_l4_ok[0x1]; + u8 outer_l3_ok_duplicate[0x1]; + u8 outer_l4_ok_duplicate[0x1]; + u8 outer_tcp_cwr[0x1]; + u8 outer_tcp_ece[0x1]; + u8 outer_tcp_urg[0x1]; + u8 outer_tcp_ack[0x1]; + u8 outer_tcp_psh[0x1]; + u8 outer_tcp_rst[0x1]; + u8 outer_tcp_syn[0x1]; + u8 outer_tcp_fin[0x1]; +}; + +struct mlx5_ifc_match_definer_format_22_bits { + u8 reserved_at_0[0x100]; + + u8 outer_ip_src_addr[0x20]; + + u8 outer_ip_dest_addr[0x20]; + + u8 outer_l4_sport[0x10]; + u8 outer_l4_dport[0x10]; + + u8 reserved_at_160[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 outer_ip_frag[0x1]; + u8 outer_qp_type[0x2]; + u8 outer_encap_type[0x2]; + u8 port_number[0x2]; + u8 outer_l3_type[0x2]; + u8 outer_l4_type[0x2]; + u8 outer_first_vlan_type[0x2]; + u8 outer_first_vlan_prio[0x3]; + u8 outer_first_vlan_cfi[0x1]; + u8 outer_first_vlan_vid[0xc]; + + u8 metadata_reg_c_0[0x20]; + + u8 outer_dmac_47_16[0x20]; + + u8 outer_smac_47_16[0x20]; + + u8 outer_smac_15_0[0x10]; + u8 outer_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_format_23_bits { + u8 reserved_at_0[0x100]; + + u8 inner_ip_src_addr[0x20]; + + u8 inner_ip_dest_addr[0x20]; + + u8 inner_l4_sport[0x10]; + u8 inner_l4_dport[0x10]; + + u8 reserved_at_160[0x1]; + u8 sx_sniffer[0x1]; + u8 functional_lb[0x1]; + u8 inner_ip_frag[0x1]; + u8 inner_qp_type[0x2]; + u8 inner_encap_type[0x2]; + u8 port_number[0x2]; + u8 inner_l3_type[0x2]; + u8 inner_l4_type[0x2]; + u8 inner_first_vlan_type[0x2]; + u8 inner_first_vlan_prio[0x3]; + u8 inner_first_vlan_cfi[0x1]; + u8 inner_first_vlan_vid[0xc]; + + u8 tunnel_header_0[0x20]; + + u8 inner_dmac_47_16[0x20]; + + u8 inner_smac_47_16[0x20]; + + u8 inner_smac_15_0[0x10]; + u8 inner_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_format_29_bits { + u8 reserved_at_0[0xc0]; + + u8 outer_ip_dest_addr[0x80]; + + u8 outer_ip_src_addr[0x80]; + + u8 outer_l4_sport[0x10]; + u8 outer_l4_dport[0x10]; + + u8 reserved_at_1e0[0x20]; +}; + +struct mlx5_ifc_match_definer_format_30_bits { + u8 reserved_at_0[0xa0]; + + u8 outer_ip_dest_addr[0x80]; + + u8 outer_ip_src_addr[0x80]; + + u8 outer_dmac_47_16[0x20]; + + u8 outer_smac_47_16[0x20]; + + u8 outer_smac_15_0[0x10]; + u8 outer_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_format_31_bits { + u8 reserved_at_0[0xc0]; + + u8 inner_ip_dest_addr[0x80]; + + u8 inner_ip_src_addr[0x80]; + + u8 inner_l4_sport[0x10]; + u8 inner_l4_dport[0x10]; + + u8 reserved_at_1e0[0x20]; +}; + +struct mlx5_ifc_match_definer_format_32_bits { + u8 reserved_at_0[0xa0]; + + u8 inner_ip_dest_addr[0x80]; + + u8 inner_ip_src_addr[0x80]; + + u8 inner_dmac_47_16[0x20]; + + u8 inner_smac_47_16[0x20]; + + u8 inner_smac_15_0[0x10]; + u8 inner_dmac_15_0[0x10]; +}; + +struct mlx5_ifc_match_definer_bits { + u8 modify_field_select[0x40]; + + u8 reserved_at_40[0x40]; + + u8 reserved_at_80[0x10]; + u8 format_id[0x10]; + + u8 reserved_at_a0[0x160]; + + u8 match_mask[16][0x20]; +}; + +struct mlx5_ifc_general_obj_in_cmd_hdr_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + + u8 vhca_tunnel_id[0x10]; + u8 obj_type[0x10]; + + u8 obj_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_general_obj_out_cmd_hdr_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 obj_id[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_create_match_definer_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits general_obj_in_cmd_hdr; + + struct mlx5_ifc_match_definer_bits obj_context; +}; + +struct mlx5_ifc_create_match_definer_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; +}; + enum { MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, @@ -8139,6 +8370,11 @@ struct mlx5_ifc_create_flow_group_out_bits { u8 reserved_at_60[0x20]; }; +enum { + MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_TCAM_SUBTABLE = 0x0, + MLX5_CREATE_FLOW_GROUP_IN_GROUP_TYPE_HASH_SPLIT = 0x1, +}; + enum { MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_CREATE_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, @@ -8160,7 +8396,9 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x4]; + u8 group_type[0x4]; + u8 reserved_at_90[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8175,7 +8413,10 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 end_flow_index[0x20]; - u8 reserved_at_140[0xa0]; + u8 reserved_at_140[0x10]; + u8 match_definer_id[0x10]; + + u8 reserved_at_160[0x80]; u8 reserved_at_1e0[0x18]; u8 match_criteria_enable[0x8]; @@ -10671,29 +10912,6 @@ struct mlx5_ifc_dealloc_memic_out_bits { u8 reserved_at_40[0x40]; }; -struct mlx5_ifc_general_obj_in_cmd_hdr_bits { - u8 opcode[0x10]; - u8 uid[0x10]; - - u8 vhca_tunnel_id[0x10]; - u8 obj_type[0x10]; - - u8 obj_id[0x20]; - - u8 reserved_at_60[0x20]; -}; - -struct mlx5_ifc_general_obj_out_cmd_hdr_bits { - u8 status[0x8]; - u8 reserved_at_8[0x18]; - - u8 syndrome[0x20]; - - u8 obj_id[0x20]; - - u8 reserved_at_60[0x20]; -}; - struct mlx5_ifc_umem_bits { u8 reserved_at_0[0x80]; -- cgit v1.2.3 From 58a606dba708f114e7f412b5c3024027e8a73e34 Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Tue, 3 Aug 2021 10:04:41 +0300 Subject: net/mlx5: Introduce new uplink destination type The uplink destination type should be used in rules to steer the packet to the uplink when the device is in steering based LAG mode. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c | 3 +++ drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 8 +++++++- include/linux/mlx5/mlx5_ifc.h | 1 + 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c index 87d65f6b5310..7841ef6c193c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c @@ -235,6 +235,9 @@ const char *parse_fs_dst(struct trace_seq *p, const char *ret = trace_seq_buffer_ptr(p); switch (dst->type) { + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: + trace_seq_printf(p, "uplink\n"); + break; case MLX5_FLOW_DESTINATION_TYPE_VPORT: trace_seq_printf(p, "vport=%u\n", dst->vport.num); break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 2c82dc118460..750b21124a1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -577,8 +577,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: id = dst->dest_attr.ft->id; break; + case MLX5_FLOW_DESTINATION_TYPE_UPLINK: case MLX5_FLOW_DESTINATION_TYPE_VPORT: - id = dst->dest_attr.vport.num; MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id_valid, !!(dst->dest_attr.vport.flags & @@ -586,6 +586,12 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(dest_format_struct, in_dests, destination_eswitch_owner_vhca_id, dst->dest_attr.vport.vhca_id); + if (type == MLX5_FLOW_DESTINATION_TYPE_UPLINK) { + /* destination_id is reserved */ + id = 0; + break; + } + id = dst->dest_attr.vport.num; if (extended_dest && dst->dest_attr.vport.pkt_reformat) { MLX5_SET(dest_format_struct, in_dests, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 8f41145bc6ef..09e43019d877 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1766,6 +1766,7 @@ enum mlx5_flow_destination_type { MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE = 0x1, MLX5_FLOW_DESTINATION_TYPE_TIR = 0x2, MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER = 0x6, + MLX5_FLOW_DESTINATION_TYPE_UPLINK = 0x8, MLX5_FLOW_DESTINATION_TYPE_PORT = 0x99, MLX5_FLOW_DESTINATION_TYPE_COUNTER = 0x100, -- cgit v1.2.3 From 25c02edfd41f0dd7aad9115149625d7e7f441b7d Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Fri, 3 Sep 2021 10:29:13 +0300 Subject: iio: inkern: introduce devm_iio_map_array_register() short-hand function This change introduces a device-managed variant to the iio_map_array_register() function. It's a simple implementation of calling iio_map_array_register() and registering a callback to iio_map_array_unregister() with the devm_add_action_or_reset(). The function uses an explicit 'dev' parameter to bind the unwinding to. It could have been implemented to implicitly use the parent of the IIO device, however it shouldn't be too expensive to callers to just specify to which device object to bind this unwind call. It would make the API a bit more flexible. Signed-off-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20210903072917.45769-2-aardelean@deviqon.com Signed-off-by: Jonathan Cameron --- Documentation/driver-api/driver-model/devres.rst | 1 + drivers/iio/inkern.c | 17 +++++++++++++++++ include/linux/iio/driver.h | 14 ++++++++++++++ 3 files changed, 32 insertions(+) (limited to 'include/linux') diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index 650096523f4f..148e19381b79 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -287,6 +287,7 @@ IIO devm_iio_device_register() devm_iio_dmaengine_buffer_setup() devm_iio_kfifo_buffer_setup() + devm_iio_map_array_register() devm_iio_triggered_buffer_setup() devm_iio_trigger_alloc() devm_iio_trigger_register() diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c index 391a3380a1d1..0222885b334c 100644 --- a/drivers/iio/inkern.c +++ b/drivers/iio/inkern.c @@ -85,6 +85,23 @@ int iio_map_array_unregister(struct iio_dev *indio_dev) } EXPORT_SYMBOL_GPL(iio_map_array_unregister); +static void iio_map_array_unregister_cb(void *indio_dev) +{ + iio_map_array_unregister(indio_dev); +} + +int devm_iio_map_array_register(struct device *dev, struct iio_dev *indio_dev, struct iio_map *maps) +{ + int ret; + + ret = iio_map_array_register(indio_dev, maps); + if (ret) + return ret; + + return devm_add_action_or_reset(dev, iio_map_array_unregister_cb, indio_dev); +} +EXPORT_SYMBOL_GPL(devm_iio_map_array_register); + static const struct iio_chan_spec *iio_chan_spec_from_name(const struct iio_dev *indio_dev, const char *name) { diff --git a/include/linux/iio/driver.h b/include/linux/iio/driver.h index 36de60a5da7a..7a157ed218f6 100644 --- a/include/linux/iio/driver.h +++ b/include/linux/iio/driver.h @@ -8,6 +8,7 @@ #ifndef _IIO_INKERN_H_ #define _IIO_INKERN_H_ +struct device; struct iio_dev; struct iio_map; @@ -26,4 +27,17 @@ int iio_map_array_register(struct iio_dev *indio_dev, */ int iio_map_array_unregister(struct iio_dev *indio_dev); +/** + * devm_iio_map_array_register - device-managed version of iio_map_array_register + * @dev: Device object to which to bind the unwinding of this registration + * @indio_dev: Pointer to the iio_dev structure + * @maps: Pointer to an IIO map object which is to be registered to this IIO device + * + * This function will call iio_map_array_register() to register an IIO map object + * and will also hook a callback to the iio_map_array_unregister() function to + * handle de-registration of the IIO map object when the device's refcount goes to + * zero. + */ +int devm_iio_map_array_register(struct device *dev, struct iio_dev *indio_dev, struct iio_map *maps); + #endif -- cgit v1.2.3 From 31fa357ac809affd9f9a7d0b5d1991951e16beec Mon Sep 17 00:00:00 2001 From: Nuno Sá Date: Fri, 3 Sep 2021 16:14:20 +0200 Subject: iio: adis: handle devices that cannot unmask the drdy pin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some devices can't mask/unmask the data ready pin and in those cases each driver was just calling '{dis}enable_irq()' to control the trigger state. This change, moves that handling into the library by introducing a new boolean in the data structure that tells the library that the device cannot unmask the pin. On top of controlling the trigger state, we can also use this flag to automatically request the IRQ with 'IRQF_NO_AUTOEN' in case it is set. So far, all users of the library want to start operation with IRQs/DRDY pin disabled so it should be fairly safe to do this inside the library. Signed-off-by: Nuno Sá Link: https://lore.kernel.org/r/20210903141423.517028-3-nuno.sa@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/imu/adis.c | 15 ++++++++++++++- drivers/iio/imu/adis_trigger.c | 4 ++++ include/linux/iio/imu/adis.h | 2 ++ 3 files changed, 20 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/imu/adis.c b/drivers/iio/imu/adis.c index d4e692b187cd..cb0d66bf6561 100644 --- a/drivers/iio/imu/adis.c +++ b/drivers/iio/imu/adis.c @@ -286,6 +286,13 @@ int adis_enable_irq(struct adis *adis, bool enable) if (adis->data->enable_irq) { ret = adis->data->enable_irq(adis, enable); goto out_unlock; + } else if (adis->data->unmasked_drdy) { + if (enable) + enable_irq(adis->spi->irq); + else + disable_irq(adis->spi->irq); + + goto out_unlock; } ret = __adis_read_reg_16(adis, adis->data->msc_ctrl_reg, &msc); @@ -430,7 +437,13 @@ int __adis_initial_startup(struct adis *adis) if (ret) return ret; - adis_enable_irq(adis, false); + /* + * don't bother calling this if we can't unmask the IRQ as in this case + * the IRQ is most likely not yet requested and we will request it + * with 'IRQF_NO_AUTOEN' anyways. + */ + if (!adis->data->unmasked_drdy) + adis_enable_irq(adis, false); if (!adis->data->prod_id_reg) return 0; diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index 48eedc29b28a..c461bd1e8e69 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -30,6 +30,10 @@ static const struct iio_trigger_ops adis_trigger_ops = { static int adis_validate_irq_flag(struct adis *adis) { unsigned long direction = adis->irq_flag & IRQF_TRIGGER_MASK; + + /* We cannot mask the interrupt so ensure it's not enabled at request */ + if (adis->data->unmasked_drdy) + adis->irq_flag |= IRQF_NO_AUTOEN; /* * Typically this devices have data ready either on the rising edge or * on the falling edge of the data ready pin. This checks enforces that diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h index cf49997d5903..7c02f5292eea 100644 --- a/include/linux/iio/imu/adis.h +++ b/include/linux/iio/imu/adis.h @@ -49,6 +49,7 @@ struct adis_timeout { * @status_error_mask: Bitmask of errors supported by the device * @timeouts: Chip specific delays * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable + * @unmasked_drdy: True for devices that cannot mask/unmask the data ready pin * @has_paging: True if ADIS device has paged registers * @burst_reg_cmd: Register command that triggers burst * @burst_len: Burst size in the SPI RX buffer. If @burst_max_len is defined, @@ -78,6 +79,7 @@ struct adis_data { unsigned int status_error_mask; int (*enable_irq)(struct adis *adis, bool enable); + bool unmasked_drdy; bool has_paging; -- cgit v1.2.3 From 95ec3fdf2b79eaff79e78688bbc2f7dbb98d68b6 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 13 Jun 2021 16:10:36 +0100 Subject: iio: core: Introduce iio_push_to_buffers_with_ts_unaligned() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Whilst it is almost always possible to arrange for scan data to be read directly into a buffer that is suitable for passing to iio_push_to_buffers_with_timestamp(), there are a few places where leading data needs to be skipped over. For these cases introduce a function that will allocate an appropriate sized and aligned bounce buffer (if not already allocated) and copy the unaligned data into that before calling iio_push_to_buffers_with_timestamp() on the bounce buffer. We tie the lifespace of this buffer to that of the iio_dev.dev which should ensure no memory leaks occur. Signed-off-by: Jonathan Cameron Reviewed-by: Nuno Sá Link: https://lore.kernel.org/r/20210613151039.569883-2-jic23@kernel.org --- drivers/iio/industrialio-buffer.c | 46 +++++++++++++++++++++++++++++++++++++++ include/linux/iio/buffer.h | 4 ++++ include/linux/iio/iio-opaque.h | 4 ++++ 3 files changed, 54 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index a95cc2da56be..4209e933ab80 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -1731,6 +1731,52 @@ int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data) } EXPORT_SYMBOL_GPL(iio_push_to_buffers); +/** + * iio_push_to_buffers_with_ts_unaligned() - push to registered buffer, + * no alignment or space requirements. + * @indio_dev: iio_dev structure for device. + * @data: channel data excluding the timestamp. + * @data_sz: size of data. + * @timestamp: timestamp for the sample data. + * + * This special variant of iio_push_to_buffers_with_timestamp() does + * not require space for the timestamp, or 8 byte alignment of data. + * It does however require an allocation on first call and additional + * copies on all calls, so should be avoided if possible. + */ +int iio_push_to_buffers_with_ts_unaligned(struct iio_dev *indio_dev, + const void *data, + size_t data_sz, + int64_t timestamp) +{ + struct iio_dev_opaque *iio_dev_opaque = to_iio_dev_opaque(indio_dev); + + /* + * Conservative estimate - we can always safely copy the minimum + * of either the data provided or the length of the destination buffer. + * This relaxed limit allows the calling drivers to be lax about + * tracking the size of the data they are pushing, at the cost of + * unnecessary copying of padding. + */ + data_sz = min_t(size_t, indio_dev->scan_bytes, data_sz); + if (iio_dev_opaque->bounce_buffer_size != indio_dev->scan_bytes) { + void *bb; + + bb = devm_krealloc(&indio_dev->dev, + iio_dev_opaque->bounce_buffer, + indio_dev->scan_bytes, GFP_KERNEL); + if (!bb) + return -ENOMEM; + iio_dev_opaque->bounce_buffer = bb; + iio_dev_opaque->bounce_buffer_size = indio_dev->scan_bytes; + } + memcpy(iio_dev_opaque->bounce_buffer, data, data_sz); + return iio_push_to_buffers_with_timestamp(indio_dev, + iio_dev_opaque->bounce_buffer, + timestamp); +} +EXPORT_SYMBOL_GPL(iio_push_to_buffers_with_ts_unaligned); + /** * iio_buffer_release() - Free a buffer's resources * @ref: Pointer to the kref embedded in the iio_buffer struct diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index b6928ac5c63d..451379a3984a 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -38,6 +38,10 @@ static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev, return iio_push_to_buffers(indio_dev, data); } +int iio_push_to_buffers_with_ts_unaligned(struct iio_dev *indio_dev, + const void *data, size_t data_sz, + int64_t timestamp); + bool iio_validate_scan_mask_onehot(struct iio_dev *indio_dev, const unsigned long *mask); diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h index c9504e9da571..2be12b7b5dc5 100644 --- a/include/linux/iio/iio-opaque.h +++ b/include/linux/iio/iio-opaque.h @@ -23,6 +23,8 @@ * @groupcounter: index of next attribute group * @legacy_scan_el_group: attribute group for legacy scan elements attribute group * @legacy_buffer_group: attribute group for legacy buffer attributes group + * @bounce_buffer: for devices that call iio_push_to_buffers_with_timestamp_unaligned() + * @bounce_buffer_size: size of currently allocate bounce buffer * @scan_index_timestamp: cache of the index to the timestamp * @clock_id: timestamping clock posix identifier * @chrdev: associated character device @@ -50,6 +52,8 @@ struct iio_dev_opaque { int groupcounter; struct attribute_group legacy_scan_el_group; struct attribute_group legacy_buffer_group; + void *bounce_buffer; + size_t bounce_buffer_size; unsigned int scan_index_timestamp; clockid_t clock_id; -- cgit v1.2.3 From 9eeee3b0bf190b4f677af27e24ba0cd1c030e49b Mon Sep 17 00:00:00 2001 From: Mihail Chindris Date: Thu, 7 Oct 2021 08:00:30 +0000 Subject: iio: Add output buffer support Currently IIO only supports buffer mode for capture devices like ADCs. Add support for buffered mode for output devices like DACs. The output buffer implementation is analogous to the input buffer implementation. Instead of using read() to get data from the buffer write() is used to copy data into the buffer. poll() with POLLOUT will wakeup if there is space available. Drivers can remove data from a buffer using iio_pop_from_buffer(), the function can e.g. called from a trigger handler to write the data to hardware. A buffer can only be either a output buffer or an input, but not both. So, for a device that has an ADC and DAC path, this will mean 2 IIO buffers (one for each direction). The direction of the buffer is decided by the new direction field of the iio_buffer struct and should be set after allocating and before registering it. Co-developed-by: Lars-Peter Clausen Signed-off-by: Lars-Peter Clausen Co-developed-by: Alexandru Ardelean Signed-off-by: Alexandru Ardelean Signed-off-by: Mihail Chindris Link: https://lore.kernel.org/r/20211007080035.2531-2-mihail.chindris@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/iio_core.h | 4 ++ drivers/iio/industrialio-buffer.c | 127 +++++++++++++++++++++++++++++++++++++- drivers/iio/industrialio-core.c | 1 + include/linux/iio/buffer.h | 7 +++ include/linux/iio/buffer_impl.h | 11 ++++ 5 files changed, 148 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/iio_core.h b/drivers/iio/iio_core.h index 8f4a9b264962..61e318431de9 100644 --- a/drivers/iio/iio_core.h +++ b/drivers/iio/iio_core.h @@ -68,12 +68,15 @@ __poll_t iio_buffer_poll_wrapper(struct file *filp, struct poll_table_struct *wait); ssize_t iio_buffer_read_wrapper(struct file *filp, char __user *buf, size_t n, loff_t *f_ps); +ssize_t iio_buffer_write_wrapper(struct file *filp, const char __user *buf, + size_t n, loff_t *f_ps); int iio_buffers_alloc_sysfs_and_mask(struct iio_dev *indio_dev); void iio_buffers_free_sysfs_and_mask(struct iio_dev *indio_dev); #define iio_buffer_poll_addr (&iio_buffer_poll_wrapper) #define iio_buffer_read_outer_addr (&iio_buffer_read_wrapper) +#define iio_buffer_write_outer_addr (&iio_buffer_write_wrapper) void iio_disable_all_buffers(struct iio_dev *indio_dev); void iio_buffer_wakeup_poll(struct iio_dev *indio_dev); @@ -83,6 +86,7 @@ void iio_device_detach_buffers(struct iio_dev *indio_dev); #define iio_buffer_poll_addr NULL #define iio_buffer_read_outer_addr NULL +#define iio_buffer_write_outer_addr NULL static inline int iio_buffers_alloc_sysfs_and_mask(struct iio_dev *indio_dev) { diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 4209e933ab80..b884d78657cb 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -120,6 +120,9 @@ static ssize_t iio_buffer_read(struct file *filp, char __user *buf, if (!rb || !rb->access->read) return -EINVAL; + if (rb->direction != IIO_BUFFER_DIRECTION_IN) + return -EPERM; + datum_size = rb->bytes_per_datum; /* @@ -161,6 +164,65 @@ static ssize_t iio_buffer_read(struct file *filp, char __user *buf, return ret; } +static size_t iio_buffer_space_available(struct iio_buffer *buf) +{ + if (buf->access->space_available) + return buf->access->space_available(buf); + + return SIZE_MAX; +} + +static ssize_t iio_buffer_write(struct file *filp, const char __user *buf, + size_t n, loff_t *f_ps) +{ + struct iio_dev_buffer_pair *ib = filp->private_data; + struct iio_buffer *rb = ib->buffer; + struct iio_dev *indio_dev = ib->indio_dev; + DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret; + size_t written; + + if (!indio_dev->info) + return -ENODEV; + + if (!rb || !rb->access->write) + return -EINVAL; + + if (rb->direction != IIO_BUFFER_DIRECTION_OUT) + return -EPERM; + + written = 0; + add_wait_queue(&rb->pollq, &wait); + do { + if (indio_dev->info == NULL) + return -ENODEV; + + if (!iio_buffer_space_available(rb)) { + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } + + wait_woken(&wait, TASK_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + continue; + } + + ret = rb->access->write(rb, n - written, buf + written); + if (ret == 0 && (filp->f_flags & O_NONBLOCK)) + ret = -EAGAIN; + + if (ret > 0) { + written += ret; + if (written != n && !(filp->f_flags & O_NONBLOCK)) + continue; + } + } while (ret == 0); + remove_wait_queue(&rb->pollq, &wait); + + return ret < 0 ? ret : n; +} + /** * iio_buffer_poll() - poll the buffer to find out if it has data * @filp: File structure pointer for device access @@ -181,8 +243,18 @@ static __poll_t iio_buffer_poll(struct file *filp, return 0; poll_wait(filp, &rb->pollq, wait); - if (iio_buffer_ready(indio_dev, rb, rb->watermark, 0)) - return EPOLLIN | EPOLLRDNORM; + + switch (rb->direction) { + case IIO_BUFFER_DIRECTION_IN: + if (iio_buffer_ready(indio_dev, rb, rb->watermark, 0)) + return EPOLLIN | EPOLLRDNORM; + break; + case IIO_BUFFER_DIRECTION_OUT: + if (iio_buffer_space_available(rb)) + return EPOLLOUT | EPOLLWRNORM; + break; + } + return 0; } @@ -199,6 +271,19 @@ ssize_t iio_buffer_read_wrapper(struct file *filp, char __user *buf, return iio_buffer_read(filp, buf, n, f_ps); } +ssize_t iio_buffer_write_wrapper(struct file *filp, const char __user *buf, + size_t n, loff_t *f_ps) +{ + struct iio_dev_buffer_pair *ib = filp->private_data; + struct iio_buffer *rb = ib->buffer; + + /* check if buffer was opened through new API */ + if (test_bit(IIO_BUSY_BIT_POS, &rb->flags)) + return -EBUSY; + + return iio_buffer_write(filp, buf, n, f_ps); +} + __poll_t iio_buffer_poll_wrapper(struct file *filp, struct poll_table_struct *wait) { @@ -231,6 +316,15 @@ void iio_buffer_wakeup_poll(struct iio_dev *indio_dev) } } +int iio_pop_from_buffer(struct iio_buffer *buffer, void *data) +{ + if (!buffer || !buffer->access || !buffer->access->remove_from) + return -EINVAL; + + return buffer->access->remove_from(buffer, data); +} +EXPORT_SYMBOL_GPL(iio_pop_from_buffer); + void iio_buffer_init(struct iio_buffer *buffer) { INIT_LIST_HEAD(&buffer->demux_list); @@ -1156,6 +1250,10 @@ int iio_update_buffers(struct iio_dev *indio_dev, if (insert_buffer == remove_buffer) return 0; + if (insert_buffer && + (insert_buffer->direction == IIO_BUFFER_DIRECTION_OUT)) + return -EINVAL; + mutex_lock(&iio_dev_opaque->info_exist_lock); mutex_lock(&indio_dev->mlock); @@ -1277,6 +1375,22 @@ static ssize_t iio_dma_show_data_available(struct device *dev, return sysfs_emit(buf, "%zu\n", iio_buffer_data_available(buffer)); } +static ssize_t direction_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct iio_buffer *buffer = to_iio_dev_attr(attr)->buffer; + + switch (buffer->direction) { + case IIO_BUFFER_DIRECTION_IN: + return sprintf(buf, "in\n"); + case IIO_BUFFER_DIRECTION_OUT: + return sprintf(buf, "out\n"); + default: + return -EINVAL; + } +} + static DEVICE_ATTR(length, S_IRUGO | S_IWUSR, iio_buffer_read_length, iio_buffer_write_length); static struct device_attribute dev_attr_length_ro = __ATTR(length, @@ -1289,12 +1403,20 @@ static struct device_attribute dev_attr_watermark_ro = __ATTR(watermark, S_IRUGO, iio_buffer_show_watermark, NULL); static DEVICE_ATTR(data_available, S_IRUGO, iio_dma_show_data_available, NULL); +static DEVICE_ATTR_RO(direction); +/* + * When adding new attributes here, put the at the end, at least until + * the code that handles the length/length_ro & watermark/watermark_ro + * assignments gets cleaned up. Otherwise these can create some weird + * duplicate attributes errors under some setups. + */ static struct attribute *iio_buffer_attrs[] = { &dev_attr_length.attr, &dev_attr_enable.attr, &dev_attr_watermark.attr, &dev_attr_data_available.attr, + &dev_attr_direction.attr, }; #define to_dev_attr(_attr) container_of(_attr, struct device_attribute, attr) @@ -1397,6 +1519,7 @@ static const struct file_operations iio_buffer_chrdev_fileops = { .owner = THIS_MODULE, .llseek = noop_llseek, .read = iio_buffer_read, + .write = iio_buffer_write, .poll = iio_buffer_poll, .release = iio_buffer_chrdev_release, }; diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 2dbb37e09b8c..537a08549a69 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -1822,6 +1822,7 @@ static const struct file_operations iio_buffer_fileops = { .owner = THIS_MODULE, .llseek = noop_llseek, .read = iio_buffer_read_outer_addr, + .write = iio_buffer_write_outer_addr, .poll = iio_buffer_poll_addr, .unlocked_ioctl = iio_ioctl, .compat_ioctl = compat_ptr_ioctl, diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h index 451379a3984a..418b1307d3f2 100644 --- a/include/linux/iio/buffer.h +++ b/include/linux/iio/buffer.h @@ -11,8 +11,15 @@ struct iio_buffer; +enum iio_buffer_direction { + IIO_BUFFER_DIRECTION_IN, + IIO_BUFFER_DIRECTION_OUT, +}; + int iio_push_to_buffers(struct iio_dev *indio_dev, const void *data); +int iio_pop_from_buffer(struct iio_buffer *buffer, void *data); + /** * iio_push_to_buffers_with_timestamp() - push data and timestamp to buffers * @indio_dev: iio_dev structure for device. diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index 245b32918ae1..e2ca8ea23e19 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -7,6 +7,7 @@ #ifdef CONFIG_IIO_BUFFER #include +#include struct iio_dev; struct iio_buffer; @@ -23,6 +24,10 @@ struct iio_buffer; * @read: try to get a specified number of bytes (must exist) * @data_available: indicates how much data is available for reading from * the buffer. + * @remove_from: remove scan from buffer. Drivers should calls this to + * remove a scan from a buffer. + * @write: try to write a number of bytes + * @space_available: returns the amount of bytes available in a buffer * @request_update: if a parameter change has been marked, update underlying * storage. * @set_bytes_per_datum:set number of bytes per datum @@ -49,6 +54,9 @@ struct iio_buffer_access_funcs { int (*store_to)(struct iio_buffer *buffer, const void *data); int (*read)(struct iio_buffer *buffer, size_t n, char __user *buf); size_t (*data_available)(struct iio_buffer *buffer); + int (*remove_from)(struct iio_buffer *buffer, void *data); + int (*write)(struct iio_buffer *buffer, size_t n, const char __user *buf); + size_t (*space_available)(struct iio_buffer *buffer); int (*request_update)(struct iio_buffer *buffer); @@ -80,6 +88,9 @@ struct iio_buffer { /** @bytes_per_datum: Size of individual datum including timestamp. */ size_t bytes_per_datum; + /* @direction: Direction of the data stream (in/out). */ + enum iio_buffer_direction direction; + /** * @access: Buffer access functions associated with the * implementation. -- cgit v1.2.3 From c02cd5c19c17698f12b731e898127095f9bc2921 Mon Sep 17 00:00:00 2001 From: Alexandru Ardelean Date: Thu, 7 Oct 2021 08:00:32 +0000 Subject: iio: triggered-buffer: extend support to configure output buffers Now that output (kfifo) buffers are supported, we need to extend the {devm_}iio_triggered_buffer_setup_ext() parameter list to take a direction parameter. This allows us to attach an output triggered buffer to a DAC device. Unfortunately it's a bit difficult to add another macro to avoid changing 5 drivers where {devm_}iio_triggered_buffer_setup_ext() is used. Well, it's doable, but may not be worth the trouble vs just updating all these 5 drivers. Signed-off-by: Alexandru Ardelean Signed-off-by: Mihail Chindris Link: https://lore.kernel.org/r/20211007080035.2531-4-mihail.chindris@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/adxl372.c | 1 + drivers/iio/accel/bmc150-accel-core.c | 1 + drivers/iio/adc/at91-sama5d2_adc.c | 4 ++-- drivers/iio/buffer/industrialio-triggered-buffer.c | 8 ++++++-- drivers/iio/common/hid-sensors/hid-sensor-trigger.c | 5 +++-- include/linux/iio/triggered_buffer.h | 11 +++++++++-- 6 files changed, 22 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c index fc9592407717..758952584f8c 100644 --- a/drivers/iio/accel/adxl372.c +++ b/drivers/iio/accel/adxl372.c @@ -1214,6 +1214,7 @@ int adxl372_probe(struct device *dev, struct regmap *regmap, ret = devm_iio_triggered_buffer_setup_ext(dev, indio_dev, NULL, adxl372_trigger_handler, + IIO_BUFFER_DIRECTION_IN, &adxl372_buffer_ops, adxl372_fifo_attributes); if (ret < 0) diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index e8693a42ad46..63216321cdb5 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -1734,6 +1734,7 @@ int bmc150_accel_core_probe(struct device *dev, struct regmap *regmap, int irq, ret = iio_triggered_buffer_setup_ext(indio_dev, &iio_pollfunc_store_time, bmc150_accel_trigger_handler, + IIO_BUFFER_DIRECTION_IN, &bmc150_accel_buffer_ops, fifo_attrs); if (ret < 0) { diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c index dabe8cdcfd08..4c922ef634f8 100644 --- a/drivers/iio/adc/at91-sama5d2_adc.c +++ b/drivers/iio/adc/at91-sama5d2_adc.c @@ -1894,8 +1894,8 @@ static int at91_adc_buffer_and_trigger_init(struct device *dev, fifo_attrs = NULL; ret = devm_iio_triggered_buffer_setup_ext(&indio->dev, indio, - &iio_pollfunc_store_time, - &at91_adc_trigger_handler, &at91_buffer_setup_ops, fifo_attrs); + &iio_pollfunc_store_time, &at91_adc_trigger_handler, + IIO_BUFFER_DIRECTION_IN, &at91_buffer_setup_ops, fifo_attrs); if (ret < 0) { dev_err(dev, "couldn't initialize the buffer.\n"); return ret; diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c index f77c4538141e..8d4fc97d1005 100644 --- a/drivers/iio/buffer/industrialio-triggered-buffer.c +++ b/drivers/iio/buffer/industrialio-triggered-buffer.c @@ -19,6 +19,7 @@ * @indio_dev: IIO device structure * @h: Function which will be used as pollfunc top half * @thread: Function which will be used as pollfunc bottom half + * @direction: Direction of the data stream (in/out). * @setup_ops: Buffer setup functions to use for this device. * If NULL the default setup functions for triggered * buffers will be used. @@ -38,6 +39,7 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev, irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), + enum iio_buffer_direction direction, const struct iio_buffer_setup_ops *setup_ops, const struct attribute **buffer_attrs) { @@ -68,6 +70,7 @@ int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev, /* Flag that polled ring buffering is possible */ indio_dev->modes |= INDIO_BUFFER_TRIGGERED; + buffer->direction = direction; buffer->attrs = buffer_attrs; ret = iio_device_attach_buffer(indio_dev, buffer); @@ -105,13 +108,14 @@ int devm_iio_triggered_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), + enum iio_buffer_direction direction, const struct iio_buffer_setup_ops *ops, const struct attribute **buffer_attrs) { int ret; - ret = iio_triggered_buffer_setup_ext(indio_dev, h, thread, ops, - buffer_attrs); + ret = iio_triggered_buffer_setup_ext(indio_dev, h, thread, direction, + ops, buffer_attrs); if (ret) return ret; diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c index a4ec11a3b68a..1151434038d4 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c @@ -241,8 +241,9 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name, fifo_attrs = NULL; ret = iio_triggered_buffer_setup_ext(indio_dev, - &iio_pollfunc_store_time, - NULL, NULL, fifo_attrs); + &iio_pollfunc_store_time, NULL, + IIO_BUFFER_DIRECTION_IN, + NULL, fifo_attrs); if (ret) { dev_err(&indio_dev->dev, "Triggered Buffer Setup Failed\n"); return ret; diff --git a/include/linux/iio/triggered_buffer.h b/include/linux/iio/triggered_buffer.h index 7f154d1f8739..7490b05fc5b2 100644 --- a/include/linux/iio/triggered_buffer.h +++ b/include/linux/iio/triggered_buffer.h @@ -2,6 +2,7 @@ #ifndef _LINUX_IIO_TRIGGERED_BUFFER_H_ #define _LINUX_IIO_TRIGGERED_BUFFER_H_ +#include #include struct attribute; @@ -11,21 +12,27 @@ struct iio_buffer_setup_ops; int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev, irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), + enum iio_buffer_direction direction, const struct iio_buffer_setup_ops *setup_ops, const struct attribute **buffer_attrs); void iio_triggered_buffer_cleanup(struct iio_dev *indio_dev); #define iio_triggered_buffer_setup(indio_dev, h, thread, setup_ops) \ - iio_triggered_buffer_setup_ext((indio_dev), (h), (thread), (setup_ops), NULL) + iio_triggered_buffer_setup_ext((indio_dev), (h), (thread), \ + IIO_BUFFER_DIRECTION_IN, (setup_ops), \ + NULL) int devm_iio_triggered_buffer_setup_ext(struct device *dev, struct iio_dev *indio_dev, irqreturn_t (*h)(int irq, void *p), irqreturn_t (*thread)(int irq, void *p), + enum iio_buffer_direction direction, const struct iio_buffer_setup_ops *ops, const struct attribute **buffer_attrs); #define devm_iio_triggered_buffer_setup(dev, indio_dev, h, thread, setup_ops) \ - devm_iio_triggered_buffer_setup_ext((dev), (indio_dev), (h), (thread), (setup_ops), NULL) + devm_iio_triggered_buffer_setup_ext((dev), (indio_dev), (h), (thread), \ + IIO_BUFFER_DIRECTION_IN, \ + (setup_ops), NULL) #endif -- cgit v1.2.3 From aafa1cafedca7c64d6a43cd21488d28d1d1be884 Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sat, 2 Oct 2021 12:32:30 +0300 Subject: platform_data/mlxreg: Add new type to support modular systems Add new types for the Nvidia modular systems MSN4800 which could be equipped with the different types of replaceable line cards. Add new type to specify the kind of hotplug events for the line cards. The line card events are generated by the programmable device located on the main board. This device implements interrupt controller logic. Line card interrupts are associated with different line cards states during its initialization: insertion, security signature validation, power good state, security validation, hardware-firmware synchronization state, line card PHYs readiness state, firmware availability for line card ports. Also under some circumstances hardware can generate thermal shutdown for particular line card. Add new type specifying the action, which should be performed when particular hotplug event is received. This action defines in which way hotplug event should be handled by hotplug driver. There are the next actions types: - Connect I2C device with empty 'platform_data' field according to the platform topology, if device is configured (for example, power unit micro-controller driver, when power unit is connected to power source (this is what is currently supported). - Connect device with 'platform_data' field set according to the platform topology. The purpose is to pass 'platform_data' through hotplug driver to underlying device (for example line card driver). - No device is associated with hotplug event - just send "udev" event (this is what is currently supported). Extend structure 'mlxreg_hotplug_device' with hotplug action field. Extend structure 'mlxreg_core_data' with: - Registers for line card power and enabling control. - Slot number field, to indicate at which physical slot replaceable line card device is located. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Link: https://lore.kernel.org/r/20211002093238.3771419-2-vadimp@nvidia.com Signed-off-by: Hans de Goede --- include/linux/platform_data/mlxreg.h | 57 ++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 101333fe2b8d..49f0e15a10dd 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -24,6 +24,51 @@ enum mlxreg_wdt_type { MLX_WDT_TYPE3, }; +/** + * enum mlxreg_hotplug_kind - kind of hotplug entry + * + * @MLXREG_HOTPLUG_DEVICE_NA: do not care; + * @MLXREG_HOTPLUG_LC_PRESENT: entry for line card presence in/out events; + * @MLXREG_HOTPLUG_LC_VERIFIED: entry for line card verification status events + * coming after line card security signature validation; + * @MLXREG_HOTPLUG_LC_POWERED: entry for line card power on/off events; + * @MLXREG_HOTPLUG_LC_SYNCED: entry for line card synchronization events, coming + * after hardware-firmware synchronization handshake; + * @MLXREG_HOTPLUG_LC_READY: entry for line card ready events, indicating line card + PHYs ready / unready state; + * @MLXREG_HOTPLUG_LC_ACTIVE: entry for line card active events, indicating firmware + * availability / unavailability for the ports on line card; + * @MLXREG_HOTPLUG_LC_THERMAL: entry for line card thermal shutdown events, positive + * event indicates that system should power off the line + * card for which this event has been received; + */ +enum mlxreg_hotplug_kind { + MLXREG_HOTPLUG_DEVICE_NA = 0, + MLXREG_HOTPLUG_LC_PRESENT = 1, + MLXREG_HOTPLUG_LC_VERIFIED = 2, + MLXREG_HOTPLUG_LC_POWERED = 3, + MLXREG_HOTPLUG_LC_SYNCED = 4, + MLXREG_HOTPLUG_LC_READY = 5, + MLXREG_HOTPLUG_LC_ACTIVE = 6, + MLXREG_HOTPLUG_LC_THERMAL = 7, +}; + +/** + * enum mlxreg_hotplug_device_action - hotplug device action required for + * driver's connectivity + * + * @MLXREG_HOTPLUG_DEVICE_DEFAULT_ACTION: probe device for 'on' event, remove + * for 'off' event; + * @MLXREG_HOTPLUG_DEVICE_PLATFORM_ACTION: probe platform device for 'on' + * event, remove for 'off' event; + * @MLXREG_HOTPLUG_DEVICE_NO_ACTION: no connectivity action is required; + */ +enum mlxreg_hotplug_device_action { + MLXREG_HOTPLUG_DEVICE_DEFAULT_ACTION = 0, + MLXREG_HOTPLUG_DEVICE_PLATFORM_ACTION = 1, + MLXREG_HOTPLUG_DEVICE_NO_ACTION = 2, +}; + /** * struct mlxreg_hotplug_device - I2C device data: * @@ -31,6 +76,7 @@ enum mlxreg_wdt_type { * @client: I2C device client; * @brdinfo: device board information; * @nr: I2C device adapter number, to which device is to be attached; + * @action: action to be performed upon event receiving; * * Structure represents I2C hotplug device static data (board topology) and * dynamic data (related kernel objects handles). @@ -40,6 +86,7 @@ struct mlxreg_hotplug_device { struct i2c_client *client; struct i2c_board_info *brdinfo; int nr; + enum mlxreg_hotplug_device_action action; }; /** @@ -51,12 +98,16 @@ struct mlxreg_hotplug_device { * @bit: attribute effective bit; * @capability: attribute capability register; * @reg_prsnt: attribute presence register; + * @reg_sync: attribute synch register; + * @reg_pwr: attribute power register; + * @reg_ena: attribute enable register; * @mode: access mode; * @np - pointer to node platform associated with attribute; * @hpdev - hotplug device data; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; * @regnum: number of registers occupied by multi-register attribute; + * @slot: slot number, at which device is located; */ struct mlxreg_core_data { char label[MLXREG_CORE_LABEL_MAX_SIZE]; @@ -65,18 +116,23 @@ struct mlxreg_core_data { u32 bit; u32 capability; u32 reg_prsnt; + u32 reg_sync; + u32 reg_pwr; + u32 reg_ena; umode_t mode; struct device_node *np; struct mlxreg_hotplug_device hpdev; u32 health_cntr; bool attached; u8 regnum; + u8 slot; }; /** * struct mlxreg_core_item - same type components controlled by the driver: * * @data: component data; + * @kind: kind of hotplug attribute; * @aggr_mask: group aggregation mask; * @reg: group interrupt status register; * @mask: group interrupt mask; @@ -89,6 +145,7 @@ struct mlxreg_core_data { */ struct mlxreg_core_item { struct mlxreg_core_data *data; + enum mlxreg_hotplug_kind kind; u32 aggr_mask; u32 reg; u32 mask; -- cgit v1.2.3 From bb1023b6da379985ff888dcd7bc601735d02267a Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sat, 2 Oct 2021 12:32:32 +0300 Subject: platform/mellanox: mlxreg-hotplug: Extend logic for hotplug devices operations Extend the structure 'mlxreg_hotplug_device" with platform device field to allow transition of the register map and system interrupt line number to underlying hotplug devices, sharing the same register map and same interrupt line with 'mlxreg-hotplug' driver. Extend logic for hotplug devices creation and removing according to the action associated with the hotplug device description. Previously hotplug driver was capable to attach / de-attach upon hotplug events only I2C devices handled by simple I2C drivers. Now it should be able to attach also devices handled by the platform drivers. The motivation is to allow transition of platform data like: - system interrupt line number, sharing with 'mlxreg-hotplug' to underlying hotplug devices. - shared register map of programmable devices on main board to underlying hotplug devices. Additioanlly the number of 'sysfs' attributes is increased, since modular system defines more 'sysfs' attributes. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Link: https://lore.kernel.org/r/20211002093238.3771419-4-vadimp@nvidia.com Signed-off-by: Hans de Goede --- drivers/platform/mellanox/mlxreg-hotplug.c | 123 +++++++++++++++++++++-------- include/linux/platform_data/mlxreg.h | 24 ++++++ 2 files changed, 112 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/mellanox/mlxreg-hotplug.c b/drivers/platform/mellanox/mlxreg-hotplug.c index b013445147dd..117bc3f395fd 100644 --- a/drivers/platform/mellanox/mlxreg-hotplug.c +++ b/drivers/platform/mellanox/mlxreg-hotplug.c @@ -28,7 +28,7 @@ /* ASIC good health mask. */ #define MLXREG_HOTPLUG_GOOD_HEALTH_MASK 0x02 -#define MLXREG_HOTPLUG_ATTRS_MAX 24 +#define MLXREG_HOTPLUG_ATTRS_MAX 128 #define MLXREG_HOTPLUG_NOT_ASSERT 3 /** @@ -89,9 +89,20 @@ mlxreg_hotplug_udev_event_send(struct kobject *kobj, return kobject_uevent_env(kobj, KOBJ_CHANGE, mlxreg_hotplug_udev_envp); } +static void +mlxreg_hotplug_pdata_export(void *pdata, void *regmap) +{ + struct mlxreg_core_hotplug_platform_data *dev_pdata = pdata; + + /* Export regmap to underlying device. */ + dev_pdata->regmap = regmap; +} + static int mlxreg_hotplug_device_create(struct mlxreg_hotplug_priv_data *priv, - struct mlxreg_core_data *data) + struct mlxreg_core_data *data, + enum mlxreg_hotplug_kind kind) { + struct i2c_board_info *brdinfo = data->hpdev.brdinfo; struct mlxreg_core_hotplug_platform_data *pdata; struct i2c_client *client; @@ -106,46 +117,88 @@ static int mlxreg_hotplug_device_create(struct mlxreg_hotplug_priv_data *priv, return 0; pdata = dev_get_platdata(&priv->pdev->dev); - data->hpdev.adapter = i2c_get_adapter(data->hpdev.nr + - pdata->shift_nr); - if (!data->hpdev.adapter) { - dev_err(priv->dev, "Failed to get adapter for bus %d\n", - data->hpdev.nr + pdata->shift_nr); - return -EFAULT; - } + switch (data->hpdev.action) { + case MLXREG_HOTPLUG_DEVICE_DEFAULT_ACTION: + data->hpdev.adapter = i2c_get_adapter(data->hpdev.nr + + pdata->shift_nr); + if (!data->hpdev.adapter) { + dev_err(priv->dev, "Failed to get adapter for bus %d\n", + data->hpdev.nr + pdata->shift_nr); + return -EFAULT; + } - client = i2c_new_client_device(data->hpdev.adapter, - data->hpdev.brdinfo); - if (IS_ERR(client)) { - dev_err(priv->dev, "Failed to create client %s at bus %d at addr 0x%02x\n", - data->hpdev.brdinfo->type, data->hpdev.nr + - pdata->shift_nr, data->hpdev.brdinfo->addr); + /* Export platform data to underlying device. */ + if (brdinfo->platform_data) + mlxreg_hotplug_pdata_export(brdinfo->platform_data, pdata->regmap); - i2c_put_adapter(data->hpdev.adapter); - data->hpdev.adapter = NULL; - return PTR_ERR(client); + client = i2c_new_client_device(data->hpdev.adapter, + brdinfo); + if (IS_ERR(client)) { + dev_err(priv->dev, "Failed to create client %s at bus %d at addr 0x%02x\n", + brdinfo->type, data->hpdev.nr + + pdata->shift_nr, brdinfo->addr); + + i2c_put_adapter(data->hpdev.adapter); + data->hpdev.adapter = NULL; + return PTR_ERR(client); + } + + data->hpdev.client = client; + break; + case MLXREG_HOTPLUG_DEVICE_PLATFORM_ACTION: + /* Export platform data to underlying device. */ + if (data->hpdev.brdinfo && data->hpdev.brdinfo->platform_data) + mlxreg_hotplug_pdata_export(data->hpdev.brdinfo->platform_data, + pdata->regmap); + /* Pass parent hotplug device handle to underlying device. */ + data->notifier = data->hpdev.notifier; + data->hpdev.pdev = platform_device_register_resndata(&priv->pdev->dev, + brdinfo->type, + data->hpdev.nr, + NULL, 0, data, + sizeof(*data)); + if (IS_ERR(data->hpdev.pdev)) + return PTR_ERR(data->hpdev.pdev); + + break; + default: + break; } - data->hpdev.client = client; + if (data->hpdev.notifier && data->hpdev.notifier->user_handler) + return data->hpdev.notifier->user_handler(data->hpdev.notifier->handle, kind, 1); return 0; } static void mlxreg_hotplug_device_destroy(struct mlxreg_hotplug_priv_data *priv, - struct mlxreg_core_data *data) + struct mlxreg_core_data *data, + enum mlxreg_hotplug_kind kind) { /* Notify user by sending hwmon uevent. */ mlxreg_hotplug_udev_event_send(&priv->hwmon->kobj, data, false); + if (data->hpdev.notifier && data->hpdev.notifier->user_handler) + data->hpdev.notifier->user_handler(data->hpdev.notifier->handle, kind, 0); + + switch (data->hpdev.action) { + case MLXREG_HOTPLUG_DEVICE_DEFAULT_ACTION: + if (data->hpdev.client) { + i2c_unregister_device(data->hpdev.client); + data->hpdev.client = NULL; + } - if (data->hpdev.client) { - i2c_unregister_device(data->hpdev.client); - data->hpdev.client = NULL; - } - - if (data->hpdev.adapter) { - i2c_put_adapter(data->hpdev.adapter); - data->hpdev.adapter = NULL; + if (data->hpdev.adapter) { + i2c_put_adapter(data->hpdev.adapter); + data->hpdev.adapter = NULL; + } + break; + case MLXREG_HOTPLUG_DEVICE_PLATFORM_ACTION: + if (data->hpdev.pdev) + platform_device_unregister(data->hpdev.pdev); + break; + default: + break; } } @@ -317,14 +370,14 @@ mlxreg_hotplug_work_helper(struct mlxreg_hotplug_priv_data *priv, data = item->data + bit; if (regval & BIT(bit)) { if (item->inversed) - mlxreg_hotplug_device_destroy(priv, data); + mlxreg_hotplug_device_destroy(priv, data, item->kind); else - mlxreg_hotplug_device_create(priv, data); + mlxreg_hotplug_device_create(priv, data, item->kind); } else { if (item->inversed) - mlxreg_hotplug_device_create(priv, data); + mlxreg_hotplug_device_create(priv, data, item->kind); else - mlxreg_hotplug_device_destroy(priv, data); + mlxreg_hotplug_device_destroy(priv, data, item->kind); } } @@ -381,7 +434,7 @@ mlxreg_hotplug_health_work_helper(struct mlxreg_hotplug_priv_data *priv, * ASIC is in steady state. Connect associated * device, if configured. */ - mlxreg_hotplug_device_create(priv, data); + mlxreg_hotplug_device_create(priv, data, item->kind); data->attached = true; } } else { @@ -391,7 +444,7 @@ mlxreg_hotplug_health_work_helper(struct mlxreg_hotplug_priv_data *priv, * in steady state. Disconnect associated * device, if it has been connected. */ - mlxreg_hotplug_device_destroy(priv, data); + mlxreg_hotplug_device_destroy(priv, data, item->kind); data->attached = false; data->health_cntr = 0; } @@ -630,7 +683,7 @@ static void mlxreg_hotplug_unset_irq(struct mlxreg_hotplug_priv_data *priv) /* Remove all the attached devices in group. */ count = item->count; for (j = 0; j < count; j++, data++) - mlxreg_hotplug_device_destroy(priv, data); + mlxreg_hotplug_device_destroy(priv, data, item->kind); } } diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 49f0e15a10dd..3122d550dc00 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -69,6 +69,19 @@ enum mlxreg_hotplug_device_action { MLXREG_HOTPLUG_DEVICE_NO_ACTION = 2, }; +/** + * struct mlxreg_core_hotplug_notifier - hotplug notifier block: + * + * @identity: notifier identity name; + * @handle: user handle to be passed by user handler function; + * @user_handler: user handler function associated with the event; + */ +struct mlxreg_core_hotplug_notifier { + char identity[MLXREG_CORE_LABEL_MAX_SIZE]; + void *handle; + int (*user_handler)(void *handle, enum mlxreg_hotplug_kind kind, u8 action); +}; + /** * struct mlxreg_hotplug_device - I2C device data: * @@ -76,7 +89,11 @@ enum mlxreg_hotplug_device_action { * @client: I2C device client; * @brdinfo: device board information; * @nr: I2C device adapter number, to which device is to be attached; + * @pdev: platform device, if device is instantiated as a platform device; * @action: action to be performed upon event receiving; + * @handle: user handle to be passed by user handler function; + * @user_handler: user handler function associated with the event; + * @notifier: pointer to event notifier block; * * Structure represents I2C hotplug device static data (board topology) and * dynamic data (related kernel objects handles). @@ -86,7 +103,11 @@ struct mlxreg_hotplug_device { struct i2c_client *client; struct i2c_board_info *brdinfo; int nr; + struct platform_device *pdev; enum mlxreg_hotplug_device_action action; + void *handle; + int (*user_handler)(void *handle, enum mlxreg_hotplug_kind kind, u8 action); + struct mlxreg_core_hotplug_notifier *notifier; }; /** @@ -104,10 +125,12 @@ struct mlxreg_hotplug_device { * @mode: access mode; * @np - pointer to node platform associated with attribute; * @hpdev - hotplug device data; + * @notifier: pointer to event notifier block; * @health_cntr: dynamic device health indication counter; * @attached: true if device has been attached after good health indication; * @regnum: number of registers occupied by multi-register attribute; * @slot: slot number, at which device is located; + * @secured: if set indicates that entry access is secured; */ struct mlxreg_core_data { char label[MLXREG_CORE_LABEL_MAX_SIZE]; @@ -122,6 +145,7 @@ struct mlxreg_core_data { umode_t mode; struct device_node *np; struct mlxreg_hotplug_device hpdev; + struct mlxreg_core_hotplug_notifier *notifier; u32 health_cntr; bool attached; u8 regnum; -- cgit v1.2.3 From 9d93d7877c9158d059028681b66a0c192f85c64d Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Sat, 2 Oct 2021 12:32:35 +0300 Subject: platform_data/mlxreg: Add new field for secured access Extend structure 'mlxreg_core_data' with the field "secured". The purpose of this field is to restrict access to some attributes, if kernel is configured with security options, like: LOCK_DOWN_KERNEL_FORCE_CONFIDENTIALITY. Access to some attributes, which for example, allow burning of some hardware components, like FPGA, CPLD, SPI, etcetera can break the system. In case user does not want to allow such access, it can disable it by setting security options. Signed-off-by: Vadim Pasternak Reviewed-by: Michael Shych Link: https://lore.kernel.org/r/20211002093238.3771419-7-vadimp@nvidia.com Signed-off-by: Hans de Goede --- include/linux/platform_data/mlxreg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/platform_data/mlxreg.h b/include/linux/platform_data/mlxreg.h index 3122d550dc00..40185f9d7c14 100644 --- a/include/linux/platform_data/mlxreg.h +++ b/include/linux/platform_data/mlxreg.h @@ -150,6 +150,7 @@ struct mlxreg_core_data { bool attached; u8 regnum; u8 slot; + u8 secured; }; /** -- cgit v1.2.3 From 54f5b3615f199673ecb23f0a6847fd9c43aaa012 Mon Sep 17 00:00:00 2001 From: Wang Kefeng Date: Mon, 23 Aug 2021 10:41:41 +0100 Subject: ARM: 9121/1: amba: Drop unused functions about APB/AHB devices add No one use the following functions, kill them. amba_aphb_device_add() amba_apb_device_add() amba_apb_device_add_res() amba_ahb_device_add() amba_ahb_device_add_res() Cc: Linus Walleij Reviewed-by: Rob Herring Signed-off-by: Kefeng Wang Signed-off-by: Russell King (Oracle) --- drivers/amba/bus.c | 72 ------------------------------------------------ include/linux/amba/bus.h | 18 ------------ 2 files changed, 90 deletions(-) (limited to 'include/linux') diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index 962041148482..2f2137518be0 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -579,78 +579,6 @@ int amba_device_add(struct amba_device *dev, struct resource *parent) } EXPORT_SYMBOL_GPL(amba_device_add); -static struct amba_device * -amba_aphb_device_add(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, int irq2, - void *pdata, unsigned int periphid, u64 dma_mask, - struct resource *resbase) -{ - struct amba_device *dev; - int ret; - - dev = amba_device_alloc(name, base, size); - if (!dev) - return ERR_PTR(-ENOMEM); - - dev->dev.coherent_dma_mask = dma_mask; - dev->irq[0] = irq1; - dev->irq[1] = irq2; - dev->periphid = periphid; - dev->dev.platform_data = pdata; - dev->dev.parent = parent; - - ret = amba_device_add(dev, resbase); - if (ret) { - amba_device_put(dev); - return ERR_PTR(ret); - } - - return dev; -} - -struct amba_device * -amba_apb_device_add(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, int irq2, - void *pdata, unsigned int periphid) -{ - return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata, - periphid, 0, &iomem_resource); -} -EXPORT_SYMBOL_GPL(amba_apb_device_add); - -struct amba_device * -amba_ahb_device_add(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, int irq2, - void *pdata, unsigned int periphid) -{ - return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata, - periphid, ~0ULL, &iomem_resource); -} -EXPORT_SYMBOL_GPL(amba_ahb_device_add); - -struct amba_device * -amba_apb_device_add_res(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, - int irq2, void *pdata, unsigned int periphid, - struct resource *resbase) -{ - return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata, - periphid, 0, resbase); -} -EXPORT_SYMBOL_GPL(amba_apb_device_add_res); - -struct amba_device * -amba_ahb_device_add_res(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, - int irq2, void *pdata, unsigned int periphid, - struct resource *resbase) -{ - return amba_aphb_device_add(parent, name, base, size, irq1, irq2, pdata, - periphid, ~0ULL, resbase); -} -EXPORT_SYMBOL_GPL(amba_ahb_device_add_res); - - static void amba_device_initialize(struct amba_device *dev, const char *name) { device_initialize(&dev->dev); diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index c68d87b87283..edfcf7a14dcd 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -122,24 +122,6 @@ struct amba_device *amba_device_alloc(const char *, resource_size_t, size_t); void amba_device_put(struct amba_device *); int amba_device_add(struct amba_device *, struct resource *); int amba_device_register(struct amba_device *, struct resource *); -struct amba_device *amba_apb_device_add(struct device *parent, const char *name, - resource_size_t base, size_t size, - int irq1, int irq2, void *pdata, - unsigned int periphid); -struct amba_device *amba_ahb_device_add(struct device *parent, const char *name, - resource_size_t base, size_t size, - int irq1, int irq2, void *pdata, - unsigned int periphid); -struct amba_device * -amba_apb_device_add_res(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, - int irq2, void *pdata, unsigned int periphid, - struct resource *resbase); -struct amba_device * -amba_ahb_device_add_res(struct device *parent, const char *name, - resource_size_t base, size_t size, int irq1, - int irq2, void *pdata, unsigned int periphid, - struct resource *resbase); void amba_device_unregister(struct amba_device *); struct amba_device *amba_find_device(const char *, struct device *, unsigned int, unsigned int); int amba_request_regions(struct amba_device *, const char *); -- cgit v1.2.3 From f5245a5fdf757f50a6c905fc16cceb1a6146ccf5 Mon Sep 17 00:00:00 2001 From: David Lechner Date: Sun, 17 Oct 2021 13:55:21 -0500 Subject: counter: drop chrdev_lock This removes the chrdev_lock from the counter subsystem. This was intended to prevent opening the chrdev more than once. However, this doesn't work in practice since userspace can duplicate file descriptors and pass file descriptors to other processes. Since this protection can't be relied on, it is best to just remove it. Suggested-by: Greg KH Acked-by: William Breathitt Gray Signed-off-by: David Lechner Link: https://lore.kernel.org/r/20211017185521.3468640-1-david@lechnology.com Signed-off-by: Greg Kroah-Hartman --- drivers/counter/counter-chrdev.c | 6 ------ drivers/counter/counter-sysfs.c | 13 +++---------- include/linux/counter.h | 7 ------- 3 files changed, 3 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c index 967c94ae95bb..b747dc81cfc6 100644 --- a/drivers/counter/counter-chrdev.c +++ b/drivers/counter/counter-chrdev.c @@ -384,10 +384,6 @@ static int counter_chrdev_open(struct inode *inode, struct file *filp) typeof(*counter), chrdev); - /* Ensure chrdev is not opened more than 1 at a time */ - if (!atomic_add_unless(&counter->chrdev_lock, 1, 1)) - return -EBUSY; - get_device(&counter->dev); filp->private_data = counter; @@ -419,7 +415,6 @@ out_unlock: mutex_unlock(&counter->ops_exist_lock); put_device(&counter->dev); - atomic_dec(&counter->chrdev_lock); return ret; } @@ -445,7 +440,6 @@ int counter_chrdev_add(struct counter_device *const counter) mutex_init(&counter->events_lock); /* Initialize character device */ - atomic_set(&counter->chrdev_lock, 0); cdev_init(&counter->chrdev, &counter_fops); /* Allocate Counter events queue */ diff --git a/drivers/counter/counter-sysfs.c b/drivers/counter/counter-sysfs.c index c2fddbb0d442..8c2d7c29ea59 100644 --- a/drivers/counter/counter-sysfs.c +++ b/drivers/counter/counter-sysfs.c @@ -796,25 +796,18 @@ static int counter_events_queue_size_write(struct counter_device *counter, u64 val) { DECLARE_KFIFO_PTR(events, struct counter_event); - int err = 0; - - /* Ensure chrdev is not opened more than 1 at a time */ - if (!atomic_add_unless(&counter->chrdev_lock, 1, 1)) - return -EBUSY; + int err; /* Allocate new events queue */ err = kfifo_alloc(&events, val, GFP_KERNEL); if (err) - goto exit_early; + return err; /* Swap in new events queue */ kfifo_free(&counter->events); counter->events.kfifo = events.kfifo; -exit_early: - atomic_dec(&counter->chrdev_lock); - - return err; + return 0; } static struct counter_comp counter_num_signals_comp = diff --git a/include/linux/counter.h b/include/linux/counter.h index 22b14a552b1d..0fd99e255a50 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -297,7 +297,6 @@ struct counter_ops { * @events: queue of detected Counter events * @events_wait: wait queue to allow blocking reads of Counter events * @events_lock: lock to protect Counter events queue read operations - * @chrdev_lock: lock to limit chrdev to a single open at a time * @ops_exist_lock: lock to prevent use during removal */ struct counter_device { @@ -325,12 +324,6 @@ struct counter_device { DECLARE_KFIFO_PTR(events, struct counter_event); wait_queue_head_t events_wait; struct mutex events_lock; - /* - * chrdev_lock is locked by counter_chrdev_open() and unlocked by - * counter_chrdev_release(), so a mutex is not possible here because - * chrdev_lock will invariably be held when returning to user space - */ - atomic_t chrdev_lock; struct mutex ops_exist_lock; }; -- cgit v1.2.3 From 5c67aa59bd8f99d70c81b5e71bd02083056a8486 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 14 Oct 2021 16:26:11 +0300 Subject: mmc: sdhci-pci: Remove dead code (struct sdhci_pci_data et al) The last user of this struct gone a couple of releases ago. Besides that there were not so many users of this API for more than 10 years: 1/ The one is Intel Merrifield, that had been added 2016-08-31 by the commit 3976b0380b31 ("x86/platform/intel-mid: Enable SD card detection on Merrifield") and removed 2021-02-11 by the commit 4590d98f5a4f ("sfi: Remove framework for deprecated firmware"). 2/ The other is Intel Sunrisepoint related, that had been added 2015-02-06 by the commit e1bfad6d936d ("mmc: sdhci-pci: Add support for drive strength selection for SPT") and removed 2017-03-20 by the commit 51ced59cc02e ("mmc: sdhci-pci: Use ACPI DSM to get driver strength for some Intel devices"). Effectively this is a revert of the commit 52c506f0bc72 ("mmc: sdhci-pci: add platform data"). Signed-off-by: Andy Shevchenko Acked-by: Adrian Hunter Link: https://lore.kernel.org/r/20211014132613.27861-4-andriy.shevchenko@linux.intel.com Signed-off-by: Ulf Hansson --- drivers/mmc/host/Makefile | 1 - drivers/mmc/host/sdhci-pci-core.c | 31 ++++--------------------------- drivers/mmc/host/sdhci-pci-data.c | 6 ------ drivers/mmc/host/sdhci-pci.h | 1 - include/linux/mmc/sdhci-pci-data.h | 18 ------------------ 5 files changed, 4 insertions(+), 53 deletions(-) delete mode 100644 drivers/mmc/host/sdhci-pci-data.c delete mode 100644 include/linux/mmc/sdhci-pci-data.h (limited to 'include/linux') diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile index 14004cc09aaa..ea36d379bd3c 100644 --- a/drivers/mmc/host/Makefile +++ b/drivers/mmc/host/Makefile @@ -14,7 +14,6 @@ obj-$(CONFIG_MMC_SDHCI) += sdhci.o obj-$(CONFIG_MMC_SDHCI_PCI) += sdhci-pci.o sdhci-pci-y += sdhci-pci-core.o sdhci-pci-o2micro.o sdhci-pci-arasan.o \ sdhci-pci-dwc-mshc.o sdhci-pci-gli.o -obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI)) += sdhci-pci-data.o obj-$(CONFIG_MMC_SDHCI_ACPI) += sdhci-acpi.o obj-$(CONFIG_MMC_SDHCI_PXAV3) += sdhci-pxav3.o obj-$(CONFIG_MMC_SDHCI_PXAV2) += sdhci-pxav2.o diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 19e13dfae593..8938c63b1e77 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -17,8 +17,6 @@ #include #include #include -#include -#include #include #include #include @@ -26,11 +24,13 @@ #include #include #include -#include -#include #include #include +#include +#include +#include + #ifdef CONFIG_X86 #include #endif @@ -2131,22 +2131,6 @@ static struct sdhci_pci_slot *sdhci_pci_probe_slot( slot->cd_gpio = -EINVAL; slot->cd_idx = -1; - /* Retrieve platform data if there is any */ - if (*sdhci_pci_get_data) - slot->data = sdhci_pci_get_data(pdev, slotno); - - if (slot->data) { - if (slot->data->setup) { - ret = slot->data->setup(slot->data); - if (ret) { - dev_err(&pdev->dev, "platform setup failed\n"); - goto free; - } - } - slot->rst_n_gpio = slot->data->rst_n_gpio; - slot->cd_gpio = slot->data->cd_gpio; - } - host->hw_name = "PCI"; host->ops = chip->fixes && chip->fixes->ops ? chip->fixes->ops : @@ -2233,10 +2217,6 @@ remove: chip->fixes->remove_slot(slot, 0); cleanup: - if (slot->data && slot->data->cleanup) - slot->data->cleanup(slot->data); - -free: sdhci_free_host(host); return ERR_PTR(ret); @@ -2259,9 +2239,6 @@ static void sdhci_pci_remove_slot(struct sdhci_pci_slot *slot) if (slot->chip->fixes && slot->chip->fixes->remove_slot) slot->chip->fixes->remove_slot(slot, dead); - if (slot->data && slot->data->cleanup) - slot->data->cleanup(slot->data); - sdhci_free_host(slot->host); } diff --git a/drivers/mmc/host/sdhci-pci-data.c b/drivers/mmc/host/sdhci-pci-data.c deleted file mode 100644 index 18638fb363d8..000000000000 --- a/drivers/mmc/host/sdhci-pci-data.c +++ /dev/null @@ -1,6 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -#include -#include - -struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, int slotno); -EXPORT_SYMBOL_GPL(sdhci_pci_get_data); diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h index 8f90c4163bb5..15b36cd47860 100644 --- a/drivers/mmc/host/sdhci-pci.h +++ b/drivers/mmc/host/sdhci-pci.h @@ -156,7 +156,6 @@ struct sdhci_pci_fixes { struct sdhci_pci_slot { struct sdhci_pci_chip *chip; struct sdhci_host *host; - struct sdhci_pci_data *data; int rst_n_gpio; int cd_gpio; diff --git a/include/linux/mmc/sdhci-pci-data.h b/include/linux/mmc/sdhci-pci-data.h deleted file mode 100644 index 1d42872d22f3..000000000000 --- a/include/linux/mmc/sdhci-pci-data.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef LINUX_MMC_SDHCI_PCI_DATA_H -#define LINUX_MMC_SDHCI_PCI_DATA_H - -struct pci_dev; - -struct sdhci_pci_data { - struct pci_dev *pdev; - int slotno; - int rst_n_gpio; /* Set to -EINVAL if unused */ - int cd_gpio; /* Set to -EINVAL if unused */ - int (*setup)(struct sdhci_pci_data *data); - void (*cleanup)(struct sdhci_pci_data *data); -}; - -extern struct sdhci_pci_data *(*sdhci_pci_get_data)(struct pci_dev *pdev, - int slotno); -#endif -- cgit v1.2.3 From cf6a8b1b24d675afc35a01cccd081160014a0125 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 12 Oct 2021 13:26:30 +0300 Subject: RDMA/mlx5: Remove iova from struct mlx5_core_mkey iova is already stored in ibmr->iova, no need to store it here. Signed-off-by: Aharon Landau Reviewed-by: Shay Drory Acked-by: Michael S. Tsirkin Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 1 - drivers/infiniband/hw/mlx5/mr.c | 16 ++++++++-------- drivers/infiniband/hw/mlx5/odp.c | 8 ++++---- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 1 - drivers/vdpa/mlx5/core/resources.c | 1 - include/linux/mlx5/driver.h | 1 - 6 files changed, 12 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index e95967aefe78..00ad24044c3a 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1303,7 +1303,6 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj, mkey->key = mlx5_idx_to_mkey( MLX5_GET(create_mkey_out, out, mkey_index)) | key; mkey->type = MLX5_MKEY_INDIRECT_DEVX; - mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); mkey->pd = MLX5_GET(mkc, mkc, pd); devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 3be36ebbf67a..6815500cfdaa 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -911,12 +911,13 @@ static struct mlx5_cache_ent *mr_cache_ent_from_order(struct mlx5_ib_dev *dev, } static void set_mr_fields(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, - u64 length, int access_flags) + u64 length, int access_flags, u64 iova) { mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; mr->ibmr.length = length; mr->ibmr.device = &dev->ib_dev; + mr->ibmr.iova = iova; mr->access_flags = access_flags; } @@ -974,11 +975,10 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd, mr->ibmr.pd = pd; mr->umem = umem; - mr->mmkey.iova = iova; mr->mmkey.size = umem->length; mr->mmkey.pd = to_mpd(pd)->pdn; mr->page_shift = order_base_2(page_size); - set_mr_fields(dev, mr, umem->length, access_flags); + set_mr_fields(dev, mr, umem->length, access_flags, iova); return mr; } @@ -1088,7 +1088,7 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr, wr->pd = mr->ibmr.pd; wr->mkey = mr->mmkey.key; wr->length = mr->mmkey.size; - wr->virt_addr = mr->mmkey.iova; + wr->virt_addr = mr->ibmr.iova; wr->access_flags = mr->access_flags; wr->page_shift = mr->page_shift; wr->xlt_size = sg->length; @@ -1341,7 +1341,7 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem, mr->mmkey.type = MLX5_MKEY_MR; mr->desc_size = sizeof(struct mlx5_mtt); mr->umem = umem; - set_mr_fields(dev, mr, umem->length, access_flags); + set_mr_fields(dev, mr, umem->length, access_flags, iova); kvfree(in); mlx5_ib_dbg(dev, "mkey = 0x%x\n", mr->mmkey.key); @@ -1388,7 +1388,7 @@ static struct ib_mr *mlx5_ib_get_dm_mr(struct ib_pd *pd, u64 start_addr, kfree(in); - set_mr_fields(dev, mr, length, acc); + set_mr_fields(dev, mr, length, acc, start_addr); return &mr->ibmr; @@ -1763,7 +1763,7 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd, } mr->ibmr.length = new_umem->length; - mr->mmkey.iova = iova; + mr->ibmr.iova = iova; mr->mmkey.size = new_umem->length; mr->page_shift = order_base_2(page_size); mr->umem = new_umem; @@ -1834,7 +1834,7 @@ struct ib_mr *mlx5_ib_rereg_user_mr(struct ib_mr *ib_mr, int flags, u64 start, mr->umem = NULL; atomic_sub(ib_umem_num_pages(umem), &dev->mdev->priv.reg_pages); - return create_real_mr(new_pd, umem, mr->mmkey.iova, + return create_real_mr(new_pd, umem, mr->ibmr.iova, new_access_flags); } diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index d0d98e584ebc..d119ba3101a3 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -430,7 +430,7 @@ static struct mlx5_ib_mr *implicit_get_child_mr(struct mlx5_ib_mr *imr, mr->umem = &odp->umem; mr->ibmr.lkey = mr->mmkey.key; mr->ibmr.rkey = mr->mmkey.key; - mr->mmkey.iova = idx * MLX5_IMR_MTT_SIZE; + mr->ibmr.iova = idx * MLX5_IMR_MTT_SIZE; mr->parent = imr; odp->private = mr; @@ -500,7 +500,7 @@ struct mlx5_ib_mr *mlx5_ib_alloc_implicit_mr(struct mlx5_ib_pd *pd, } imr->ibmr.pd = &pd->ibpd; - imr->mmkey.iova = 0; + imr->ibmr.iova = 0; imr->umem = &umem_odp->umem; imr->ibmr.lkey = imr->mmkey.key; imr->ibmr.rkey = imr->mmkey.key; @@ -738,7 +738,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, { struct ib_umem_odp *odp = to_ib_umem_odp(mr->umem); - if (unlikely(io_virt < mr->mmkey.iova)) + if (unlikely(io_virt < mr->ibmr.iova)) return -EFAULT; if (mr->umem->is_dmabuf) @@ -747,7 +747,7 @@ static int pagefault_mr(struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, if (!odp->is_implicit_odp) { u64 user_va; - if (check_add_overflow(io_virt - mr->mmkey.iova, + if (check_add_overflow(io_virt - mr->ibmr.iova, (u64)odp->umem.address, &user_va)) return -EFAULT; if (unlikely(user_va >= ib_umem_end(odp) || diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 174f71ed5280..d239d559994f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -52,7 +52,6 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 15e266d0e27a..14d4314cdc29 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -215,7 +215,6 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->iova = MLX5_GET64(mkc, mkc, start_addr); mkey->size = MLX5_GET64(mkc, mkc, len); mkey->key |= mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index e23417424373..669904f9986e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -364,7 +364,6 @@ enum { }; struct mlx5_core_mkey { - u64 iova; u64 size; u32 key; u32 pd; -- cgit v1.2.3 From 062fd731e51ee29ba745b2fd1c7ac87dd460d4ca Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 12 Oct 2021 13:26:31 +0300 Subject: RDMA/mlx5: Remove size from struct mlx5_core_mkey mkey->size is already stored in ibmr->length, no need to store it here. Signed-off-by: Aharon Landau Reviewed-by: Shay Drory Acked-by: Michael S. Tsirkin Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 1 - drivers/infiniband/hw/mlx5/mr.c | 5 ++--- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 1 - drivers/vdpa/mlx5/core/resources.c | 1 - include/linux/mlx5/driver.h | 1 - 5 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 00ad24044c3a..8f6e1350cd37 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1303,7 +1303,6 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj, mkey->key = mlx5_idx_to_mkey( MLX5_GET(create_mkey_out, out, mkey_index)) | key; mkey->type = MLX5_MKEY_INDIRECT_DEVX; - mkey->size = MLX5_GET64(mkc, mkc, len); mkey->pd = MLX5_GET(mkc, mkc, pd); devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size); init_waitqueue_head(&mkey->wait); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 6815500cfdaa..1b1367c87a6b 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -975,7 +975,6 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd, mr->ibmr.pd = pd; mr->umem = umem; - mr->mmkey.size = umem->length; mr->mmkey.pd = to_mpd(pd)->pdn; mr->page_shift = order_base_2(page_size); set_mr_fields(dev, mr, umem->length, access_flags, iova); @@ -1087,7 +1086,7 @@ static void *mlx5_ib_create_xlt_wr(struct mlx5_ib_mr *mr, wr->wr.opcode = MLX5_IB_WR_UMR; wr->pd = mr->ibmr.pd; wr->mkey = mr->mmkey.key; - wr->length = mr->mmkey.size; + wr->length = mr->ibmr.length; wr->virt_addr = mr->ibmr.iova; wr->access_flags = mr->access_flags; wr->page_shift = mr->page_shift; @@ -1764,7 +1763,7 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd, mr->ibmr.length = new_umem->length; mr->ibmr.iova = iova; - mr->mmkey.size = new_umem->length; + mr->ibmr.length = new_umem->length; mr->page_shift = order_base_2(page_size); mr->umem = new_umem; err = mlx5_ib_update_mr_pas(mr, upd_flags); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index d239d559994f..b5dd44944265 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -52,7 +52,6 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->size = MLX5_GET64(mkc, mkc, len); mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); init_waitqueue_head(&mkey->wait); diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 14d4314cdc29..d3d8b8b4e377 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -215,7 +215,6 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->size = MLX5_GET64(mkc, mkc, len); mkey->key |= mlx5_idx_to_mkey(mkey_index); mkey->pd = MLX5_GET(mkc, mkc, pd); return 0; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 669904f9986e..ff1e991314e2 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -364,7 +364,6 @@ enum { }; struct mlx5_core_mkey { - u64 size; u32 key; u32 pd; u32 type; -- cgit v1.2.3 From c64674168b6a2f293e92caf33c917ccf10886801 Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 12 Oct 2021 13:26:32 +0300 Subject: RDMA/mlx5: Remove pd from struct mlx5_core_mkey There is no read of mkey->pd, only write. Remove it. Signed-off-by: Aharon Landau Reviewed-by: Shay Drory Acked-by: Michael S. Tsirkin Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 1 - drivers/infiniband/hw/mlx5/mr.c | 3 --- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 3 --- drivers/vdpa/mlx5/core/resources.c | 3 --- include/linux/mlx5/driver.h | 1 - 5 files changed, 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 8f6e1350cd37..5322d787c094 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1303,7 +1303,6 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj, mkey->key = mlx5_idx_to_mkey( MLX5_GET(create_mkey_out, out, mkey_index)) | key; mkey->type = MLX5_MKEY_INDIRECT_DEVX; - mkey->pd = MLX5_GET(mkc, mkc, pd); devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size); init_waitqueue_head(&mkey->wait); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 1b1367c87a6b..9d7f1cadaa76 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -975,7 +975,6 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd, mr->ibmr.pd = pd; mr->umem = umem; - mr->mmkey.pd = to_mpd(pd)->pdn; mr->page_shift = order_base_2(page_size); set_mr_fields(dev, mr, umem->length, access_flags, iova); @@ -1708,7 +1707,6 @@ static int umr_rereg_pd_access(struct mlx5_ib_mr *mr, struct ib_pd *pd, return err; mr->access_flags = access_flags; - mr->mmkey.pd = to_mpd(pd)->pdn; return 0; } @@ -1753,7 +1751,6 @@ static int umr_rereg_pas(struct mlx5_ib_mr *mr, struct ib_pd *pd, if (flags & IB_MR_REREG_PD) { mr->ibmr.pd = pd; - mr->mmkey.pd = to_mpd(pd)->pdn; upd_flags |= MLX5_IB_UPD_XLT_PD; } if (flags & IB_MR_REREG_ACCESS) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index b5dd44944265..6e99fd166f98 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -41,7 +41,6 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, { u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {}; u32 mkey_index; - void *mkc; int err; MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY); @@ -50,10 +49,8 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, if (err) return err; - mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); - mkey->pd = MLX5_GET(mkc, mkc, pd); init_waitqueue_head(&mkey->wait); mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, mkey->key); diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index d3d8b8b4e377..72b2d80e75b0 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -203,7 +203,6 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk { u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {}; u32 mkey_index; - void *mkc; int err; MLX5_SET(create_mkey_in, in, opcode, MLX5_CMD_OP_CREATE_MKEY); @@ -213,10 +212,8 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk if (err) return err; - mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); mkey->key |= mlx5_idx_to_mkey(mkey_index); - mkey->pd = MLX5_GET(mkc, mkc, pd); return 0; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index ff1e991314e2..f0ce7d4dc4ff 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -365,7 +365,6 @@ enum { struct mlx5_core_mkey { u32 key; - u32 pd; u32 type; struct wait_queue_head wait; refcount_t usecount; -- cgit v1.2.3 From 83fec3f12a5904b62330fd1a89af6d892afc387e Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 12 Oct 2021 13:26:33 +0300 Subject: RDMA/mlx5: Replace struct mlx5_core_mkey by u32 key In mlx5_core and vdpa there is no use of mlx5_core_mkey members except for the key itself. As preparation for moving mlx5_core_mkey to mlx5_ib, the occurrences of struct mlx5_core_mkey in all modules except for mlx5_ib are replaced by a u32 key. Signed-off-by: Aharon Landau Reviewed-by: Shay Drory Acked-by: Michael S. Tsirkin Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/mr.c | 21 ++++++++++++++------- drivers/infiniband/hw/mlx5/odp.c | 2 +- .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 6 +++--- .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h | 2 +- .../ethernet/mellanox/mlx5/core/diag/rsc_dump.c | 10 +++++----- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/trap.c | 2 +- .../net/ethernet/mellanox/mlx5/core/en_common.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 13 ++++++------- .../net/ethernet/mellanox/mlx5/core/fpga/conn.c | 10 +++++----- .../net/ethernet/mellanox/mlx5/core/fpga/core.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/mr.c | 22 ++++++++++------------ .../mellanox/mlx5/core/steering/dr_icm_pool.c | 10 +++++----- .../ethernet/mellanox/mlx5/core/steering/dr_send.c | 11 +++++------ .../mellanox/mlx5/core/steering/dr_types.h | 2 +- drivers/vdpa/mlx5/core/mlx5_vdpa.h | 8 ++++---- drivers/vdpa/mlx5/core/mr.c | 8 ++++---- drivers/vdpa/mlx5/core/resources.c | 8 ++++---- drivers/vdpa/mlx5/net/mlx5_vnet.c | 2 +- include/linux/mlx5/driver.h | 14 ++++++-------- 21 files changed, 82 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 9d7f1cadaa76..e2f020472ae2 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -104,8 +104,14 @@ static int mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey, u32 *in, int inlen) { + int ret; + assign_mkey_variant(dev, mkey, in); - return mlx5_core_create_mkey(dev->mdev, mkey, in, inlen); + ret = mlx5_core_create_mkey(dev->mdev, &mkey->key, in, inlen); + if (!ret) + init_waitqueue_head(&mkey->wait); + + return ret; } static int @@ -133,7 +139,7 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr) { WARN_ON(xa_load(&dev->odp_mkeys, mlx5_base_mkey(mr->mmkey.key))); - return mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); + return mlx5_core_destroy_mkey(dev->mdev, mr->mmkey.key); } static void create_mkey_callback(int status, struct mlx5_async_work *context) @@ -260,10 +266,11 @@ static struct mlx5_ib_mr *create_cache_mr(struct mlx5_cache_ent *ent) goto free_in; } - err = mlx5_core_create_mkey(ent->dev->mdev, &mr->mmkey, in, inlen); + err = mlx5_core_create_mkey(ent->dev->mdev, &mr->mmkey.key, in, inlen); if (err) goto free_mr; + init_waitqueue_head(&mr->mmkey.wait); mr->mmkey.type = MLX5_MKEY_MR; WRITE_ONCE(ent->dev->cache.last_add, jiffies); spin_lock_irq(&ent->lock); @@ -290,7 +297,7 @@ static void remove_cache_mr_locked(struct mlx5_cache_ent *ent) ent->available_mrs--; ent->total_mrs--; spin_unlock_irq(&ent->lock); - mlx5_core_destroy_mkey(ent->dev->mdev, &mr->mmkey); + mlx5_core_destroy_mkey(ent->dev->mdev, mr->mmkey.key); kfree(mr); spin_lock_irq(&ent->lock); } @@ -658,7 +665,7 @@ static void clean_keys(struct mlx5_ib_dev *dev, int c) ent->available_mrs--; ent->total_mrs--; spin_unlock_irq(&ent->lock); - mlx5_core_destroy_mkey(dev->mdev, &mr->mmkey); + mlx5_core_destroy_mkey(dev->mdev, mr->mmkey.key); } list_for_each_entry_safe(mr, tmp_mr, &del_list, list) { @@ -2326,7 +2333,7 @@ int mlx5_ib_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata) return 0; free_mkey: - mlx5_core_destroy_mkey(dev->mdev, &mw->mmkey); + mlx5_core_destroy_mkey(dev->mdev, mw->mmkey.key); free: kfree(in); return err; @@ -2345,7 +2352,7 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw) */ mlx5r_deref_wait_odp_mkey(&mmw->mmkey); - return mlx5_core_destroy_mkey(dev->mdev, &mmw->mmkey); + return mlx5_core_destroy_mkey(dev->mdev, mmw->mmkey.key); } int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask, diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index d119ba3101a3..a654367af056 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -909,7 +909,7 @@ next_mr: pklm = (struct mlx5_klm *)MLX5_ADDR_OF(query_mkey_out, out, bsf0_klm0_pas_mtt0_1); - ret = mlx5_core_query_mkey(dev->mdev, mmkey, out, outlen); + ret = mlx5_core_query_mkey(dev->mdev, mmkey->key, out, outlen); if (ret) goto end; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index f9cf9fb31547..02db3148240a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -745,7 +745,7 @@ static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer) MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY); MLX5_SET(mtrc_conf, in, log_trace_buffer_size, ilog2(TRACER_BUFFER_PAGE_NUM)); - MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key); + MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey); err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MTRC_CONF, 0, 1); @@ -1028,7 +1028,7 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer) err_notifier_unregister: mlx5_eq_notifier_unregister(dev, &tracer->nb); - mlx5_core_destroy_mkey(dev, &tracer->buff.mkey); + mlx5_core_destroy_mkey(dev, tracer->buff.mkey); err_dealloc_pd: mlx5_core_dealloc_pd(dev, tracer->buff.pdn); err_cancel_work: @@ -1051,7 +1051,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer) if (tracer->owner) mlx5_fw_tracer_ownership_release(tracer); - mlx5_core_destroy_mkey(tracer->dev, &tracer->buff.mkey); + mlx5_core_destroy_mkey(tracer->dev, tracer->buff.mkey); mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h index 97252a85d65e..4762b55b0b0e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h @@ -89,7 +89,7 @@ struct mlx5_fw_tracer { void *log_buf; dma_addr_t dma; u32 size; - struct mlx5_core_mkey mkey; + u32 mkey; u32 consumer_index; } buff; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c index ed4fb79b4db7..538adab6878b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/rsc_dump.c @@ -30,7 +30,7 @@ static const char *const mlx5_rsc_sgmt_name[] = { struct mlx5_rsc_dump { u32 pdn; - struct mlx5_core_mkey mkey; + u32 mkey; u16 fw_segment_type[MLX5_SGMT_TYPE_NUM]; }; @@ -89,7 +89,7 @@ static int mlx5_rsc_dump_trigger(struct mlx5_core_dev *dev, struct mlx5_rsc_dump return -ENOMEM; in_seq_num = MLX5_GET(resource_dump, cmd->cmd, seq_num); - MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey.key); + MLX5_SET(resource_dump, cmd->cmd, mkey, rsc_dump->mkey); MLX5_SET64(resource_dump, cmd->cmd, address, dma); err = mlx5_core_access_reg(dev, cmd->cmd, sizeof(cmd->cmd), cmd->cmd, @@ -202,7 +202,7 @@ free_page: } static int mlx5_rsc_dump_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_core_mkey *mkey) + u32 *mkey) { int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; @@ -276,7 +276,7 @@ int mlx5_rsc_dump_init(struct mlx5_core_dev *dev) return err; destroy_mkey: - mlx5_core_destroy_mkey(dev, &rsc_dump->mkey); + mlx5_core_destroy_mkey(dev, rsc_dump->mkey); free_pd: mlx5_core_dealloc_pd(dev, rsc_dump->pdn); return err; @@ -287,6 +287,6 @@ void mlx5_rsc_dump_cleanup(struct mlx5_core_dev *dev) if (IS_ERR_OR_NULL(dev->rsc_dump)) return; - mlx5_core_destroy_mkey(dev, &dev->rsc_dump->mkey); + mlx5_core_destroy_mkey(dev, dev->rsc_dump->mkey); mlx5_core_dealloc_pd(dev, dev->rsc_dump->pdn); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 03a7a4ce5cd5..7761daa25f63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -665,7 +665,7 @@ struct mlx5e_rq { u8 wq_type; u32 rqn; struct mlx5_core_dev *mdev; - struct mlx5_core_mkey umr_mkey; + u32 umr_mkey; struct mlx5e_dma_info wqe_overflow; /* XDP read-mostly */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 3a86f66d1295..18d542b1c5cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -682,7 +682,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, c->tstamp = &priv->tstamp; c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); + c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->stats = &priv->ptp_stats.ch; c->lag_port = lag_port; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index d54607a42740..a55b066746cb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -137,7 +137,7 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) t->tstamp = &priv->tstamp; t->pdev = mlx5_core_dma_dev(priv->mdev); t->netdev = priv->netdev; - t->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); + t->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); t->stats = &priv->trap_stats.ch; netif_napi_add(netdev, &t->napi, mlx5e_trap_napi_poll, 64); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 84eb7201c142..c0f409c195bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -47,7 +47,7 @@ void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc) } static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_core_mkey *mkey) + u32 *mkey) { int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; @@ -108,7 +108,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) return 0; err_destroy_mkey: - mlx5_core_destroy_mkey(mdev, &res->mkey); + mlx5_core_destroy_mkey(mdev, res->mkey); err_dealloc_transport_domain: mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); err_dealloc_pd: @@ -121,7 +121,7 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) struct mlx5e_hw_objs *res = &mdev->mlx5e_res.hw_objs; mlx5_free_bfreg(mdev, &res->bfreg); - mlx5_core_destroy_mkey(mdev, &res->mkey); + mlx5_core_destroy_mkey(mdev, res->mkey); mlx5_core_dealloc_transport_domain(mdev, res->td.tdn); mlx5_core_dealloc_pd(mdev, res->pdn); memset(res, 0, sizeof(*res)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 09c8b71b186c..63076d0e8b63 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -234,8 +234,7 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node) } static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, - u64 npages, u8 page_shift, - struct mlx5_core_mkey *umr_mkey, + u64 npages, u8 page_shift, u32 *umr_mkey, dma_addr_t filler_addr) { struct mlx5_mtt *mtt; @@ -455,7 +454,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) goto err_rq_drop_page; - rq->mkey_be = cpu_to_be32(rq->umr_mkey.key); + rq->mkey_be = cpu_to_be32(rq->umr_mkey); err = mlx5e_rq_alloc_mpwqe_info(rq, node); if (err) @@ -487,7 +486,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, if (err) goto err_rq_frags; - rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey.key); + rq->mkey_be = cpu_to_be32(mdev->mlx5e_res.hw_objs.mkey); } if (xsk) { @@ -574,7 +573,7 @@ err_free_by_rq_type: case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); err_rq_mkey: - mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); + mlx5_core_destroy_mkey(mdev, rq->umr_mkey); err_rq_drop_page: mlx5e_free_mpwqe_rq_drop_page(rq); break; @@ -607,7 +606,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); - mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); + mlx5_core_destroy_mkey(rq->mdev, rq->umr_mkey); mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ @@ -1991,7 +1990,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->cpu = cpu; c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey.key); + c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); c->num_tc = mlx5e_get_dcb_num_tc(params); c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix].ch; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 306279b7f9e7..12abe991583a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -115,7 +115,7 @@ static int mlx5_fpga_conn_post_recv(struct mlx5_fpga_conn *conn, ix = conn->qp.rq.pc & (conn->qp.rq.size - 1); data = mlx5_wq_cyc_get_wqe(&conn->qp.wq.rq, ix); data->byte_count = cpu_to_be32(buf->sg[0].size); - data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey.key); + data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey); data->addr = cpu_to_be64(buf->sg[0].dma_addr); conn->qp.rq.pc++; @@ -155,7 +155,7 @@ static void mlx5_fpga_conn_post_send(struct mlx5_fpga_conn *conn, if (!buf->sg[sgi].data) break; data->byte_count = cpu_to_be32(buf->sg[sgi].size); - data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey.key); + data->lkey = cpu_to_be32(conn->fdev->conn_res.mkey); data->addr = cpu_to_be64(buf->sg[sgi].dma_addr); data++; size++; @@ -221,7 +221,7 @@ static int mlx5_fpga_conn_post_recv_buf(struct mlx5_fpga_conn *conn) } static int mlx5_fpga_conn_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_core_mkey *mkey) + u32 *mkey) { int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); void *mkc; @@ -978,7 +978,7 @@ int mlx5_fpga_conn_device_init(struct mlx5_fpga_device *fdev) mlx5_fpga_err(fdev, "create mkey failed, %d\n", err); goto err_dealloc_pd; } - mlx5_fpga_dbg(fdev, "Created mkey 0x%x\n", fdev->conn_res.mkey.key); + mlx5_fpga_dbg(fdev, "Created mkey 0x%x\n", fdev->conn_res.mkey); return 0; @@ -994,7 +994,7 @@ out: void mlx5_fpga_conn_device_cleanup(struct mlx5_fpga_device *fdev) { - mlx5_core_destroy_mkey(fdev->mdev, &fdev->conn_res.mkey); + mlx5_core_destroy_mkey(fdev->mdev, fdev->conn_res.mkey); mlx5_core_dealloc_pd(fdev->mdev, fdev->conn_res.pdn); mlx5_put_uars_page(fdev->mdev, fdev->conn_res.uar); mlx5_nic_vport_disable_roce(fdev->mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h index 52c9dee91ea4..2a984e82ae16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h @@ -54,7 +54,7 @@ struct mlx5_fpga_device { /* QP Connection resources */ struct { u32 pdn; - struct mlx5_core_mkey mkey; + u32 mkey; struct mlx5_uars_page *uar; } conn_res; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 6e99fd166f98..f099a087400e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -35,9 +35,8 @@ #include #include "mlx5_core.h" -int mlx5_core_create_mkey(struct mlx5_core_dev *dev, - struct mlx5_core_mkey *mkey, - u32 *in, int inlen) +int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, + int inlen) { u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {}; u32 mkey_index; @@ -50,33 +49,32 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, return err; mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->key = (u32)mlx5_mkey_variant(mkey->key) | mlx5_idx_to_mkey(mkey_index); - init_waitqueue_head(&mkey->wait); + *mkey = MLX5_GET(create_mkey_in, in, memory_key_mkey_entry.mkey_7_0) | + mlx5_idx_to_mkey(mkey_index); - mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, mkey->key); + mlx5_core_dbg(dev, "out 0x%x, mkey 0x%x\n", mkey_index, *mkey); return 0; } EXPORT_SYMBOL(mlx5_core_create_mkey); -int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, - struct mlx5_core_mkey *mkey) +int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey) { u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {}; MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY); - MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); + MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey)); return mlx5_cmd_exec_in(dev, destroy_mkey, in); } EXPORT_SYMBOL(mlx5_core_destroy_mkey); -int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *out, int outlen) +int mlx5_core_query_mkey(struct mlx5_core_dev *dev, u32 mkey, u32 *out, + int outlen) { u32 in[MLX5_ST_SZ_DW(query_mkey_in)] = {}; memset(out, 0, outlen); MLX5_SET(query_mkey_in, in, opcode, MLX5_CMD_OP_QUERY_MKEY); - MLX5_SET(query_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); + MLX5_SET(query_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey)); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } EXPORT_SYMBOL(mlx5_core_query_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index 66c24767e3b0..7f6fd9c5e371 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -24,7 +24,7 @@ struct mlx5dr_icm_dm { }; struct mlx5dr_icm_mr { - struct mlx5_core_mkey mkey; + u32 mkey; struct mlx5dr_icm_dm dm; struct mlx5dr_domain *dmn; size_t length; @@ -33,7 +33,7 @@ struct mlx5dr_icm_mr { static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev, u32 pd, u64 length, u64 start_addr, int mode, - struct mlx5_core_mkey *mkey) + u32 *mkey) { u32 inlen = MLX5_ST_SZ_BYTES(create_mkey_in); u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; @@ -116,7 +116,7 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool) return icm_mr; free_mkey: - mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); + mlx5_core_destroy_mkey(mdev, icm_mr->mkey); free_dm: mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0, icm_mr->dm.addr, icm_mr->dm.obj_id); @@ -130,7 +130,7 @@ static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) struct mlx5_core_dev *mdev = icm_mr->dmn->mdev; struct mlx5dr_icm_dm *dm = &icm_mr->dm; - mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); + mlx5_core_destroy_mkey(mdev, icm_mr->mkey); mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0, dm->addr, dm->obj_id); kvfree(icm_mr); @@ -252,7 +252,7 @@ dr_icm_chunk_create(struct mlx5dr_icm_pool *pool, offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg; - chunk->rkey = buddy_mem_pool->icm_mr->mkey.key; + chunk->rkey = buddy_mem_pool->icm_mr->mkey; chunk->mr_addr = offset; chunk->icm_addr = (uintptr_t)buddy_mem_pool->icm_mr->icm_start_addr + offset; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index bfb14b4b1906..00aef47d7682 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -350,7 +350,7 @@ static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring, send_info->read.length = send_info->write.length; /* Read into the same write area */ send_info->read.addr = (uintptr_t)send_info->write.addr; - send_info->read.lkey = send_ring->mr->mkey.key; + send_info->read.lkey = send_ring->mr->mkey; if (send_ring->pending_wqe % send_ring->signal_th == 0) send_info->read.send_flags = IB_SEND_SIGNALED; @@ -388,7 +388,7 @@ static int dr_postsend_icm_data(struct mlx5dr_domain *dmn, (void *)(uintptr_t)send_info->write.addr, send_info->write.length); send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset; - send_info->write.lkey = send_ring->mr->mkey.key; + send_info->write.lkey = send_ring->mr->mkey; } send_ring->tx_head++; @@ -848,8 +848,7 @@ static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq) kfree(cq); } -static int -dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey) +static int dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey) { u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; void *mkc; @@ -908,7 +907,7 @@ static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev, static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr) { - mlx5_core_destroy_mkey(mdev, &mr->mkey); + mlx5_core_destroy_mkey(mdev, mr->mkey); dma_unmap_single(mlx5_core_dma_dev(mdev), mr->dma_addr, mr->size, DMA_BIDIRECTIONAL); kfree(mr); @@ -1039,7 +1038,7 @@ int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn) send_info.write.lkey = 0; /* Using the sync_mr in order to write/read */ send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr; - send_info.rkey = send_ring->sync_mr->mkey.key; + send_info.rkey = send_ring->sync_mr->mkey; for (i = 0; i < num_of_sends_req; i++) { ret = dr_postsend_icm_data(dmn, &send_info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index b20e8aabb861..6c67185c05c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -1275,7 +1275,7 @@ struct mlx5dr_cq { struct mlx5dr_mr { struct mlx5_core_dev *mdev; - struct mlx5_core_mkey mkey; + u32 mkey; dma_addr_t dma_addr; void *addr; size_t size; diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 01a848adf590..3163b313a470 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -15,7 +15,7 @@ struct mlx5_vdpa_direct_mr { u64 start; u64 end; u32 perm; - struct mlx5_core_mkey mr; + u32 mr; struct sg_table sg_head; int log_size; int nsg; @@ -25,7 +25,7 @@ struct mlx5_vdpa_direct_mr { }; struct mlx5_vdpa_mr { - struct mlx5_core_mkey mkey; + u32 mkey; /* list of direct MRs descendants of this indirect mr */ struct list_head head; @@ -99,9 +99,9 @@ int mlx5_vdpa_alloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 *tdn); void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn); int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev); void mlx5_vdpa_free_resources(struct mlx5_vdpa_dev *mvdev); -int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in, +int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in, int inlen); -int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey); +int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey); int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb, bool *change_map); int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb); diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index ff010c6d0cd3..a639b9208d41 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -88,7 +88,7 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct static void destroy_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) { - mlx5_vdpa_destroy_mkey(mvdev, &mr->mr); + mlx5_vdpa_destroy_mkey(mvdev, mr->mr); } static u64 map_start(struct vhost_iotlb_map *map, struct mlx5_vdpa_direct_mr *mr) @@ -162,7 +162,7 @@ again: } if (preve == dmr->start) { - klm->key = cpu_to_be32(dmr->mr.key); + klm->key = cpu_to_be32(dmr->mr); klm->bcount = cpu_to_be32(klm_bcount(dmr->end - dmr->start)); preve = dmr->end; } else { @@ -217,7 +217,7 @@ static int create_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mkey) { - mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey); + mlx5_vdpa_destroy_mkey(mvdev, mkey->mkey); } static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr, @@ -449,7 +449,7 @@ static int create_dma_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr) static void destroy_dma_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr) { - mlx5_vdpa_destroy_mkey(mvdev, &mr->mkey); + mlx5_vdpa_destroy_mkey(mvdev, mr->mkey); } static int dup_iotlb(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *src) diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 72b2d80e75b0..9800f9bec225 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -198,7 +198,7 @@ void mlx5_vdpa_dealloc_transport_domain(struct mlx5_vdpa_dev *mvdev, u32 tdn) mlx5_cmd_exec_in(mvdev->mdev, dealloc_transport_domain, in); } -int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey, u32 *in, +int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, u32 *mkey, u32 *in, int inlen) { u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {}; @@ -213,17 +213,17 @@ int mlx5_vdpa_create_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mk return err; mkey_index = MLX5_GET(create_mkey_out, lout, mkey_index); - mkey->key |= mlx5_idx_to_mkey(mkey_index); + *mkey |= mlx5_idx_to_mkey(mkey_index); return 0; } -int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, struct mlx5_core_mkey *mkey) +int mlx5_vdpa_destroy_mkey(struct mlx5_vdpa_dev *mvdev, u32 mkey) { u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)] = {}; MLX5_SET(destroy_mkey_in, in, uid, mvdev->res.uid); MLX5_SET(destroy_mkey_in, in, opcode, MLX5_CMD_OP_DESTROY_MKEY); - MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey->key)); + MLX5_SET(destroy_mkey_in, in, mkey_index, mlx5_mkey_to_idx(mkey)); return mlx5_cmd_exec_in(mvdev->mdev, destroy_mkey, in); } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index bd56de7484dc..5c7d2a953dbd 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -865,7 +865,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr); MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr); MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr); - MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey.key); + MLX5_SET(virtio_q, vq_ctx, virtio_q_mkey, ndev->mvdev.mr.mkey); MLX5_SET(virtio_q, vq_ctx, umem_1_id, mvq->umem1.id); MLX5_SET(virtio_q, vq_ctx, umem_1_size, mvq->umem1.size); MLX5_SET(virtio_q, vq_ctx, umem_2_id, mvq->umem2.id); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f0ce7d4dc4ff..bd99f713720b 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -650,7 +650,7 @@ struct mlx5e_resources { struct mlx5e_hw_objs { u32 pdn; struct mlx5_td td; - struct mlx5_core_mkey mkey; + u32 mkey; struct mlx5_sq_bfreg bfreg; } hw_objs; struct devlink_port dl_port; @@ -1021,13 +1021,11 @@ struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, gfp_t flags, int npages); void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *head); -int mlx5_core_create_mkey(struct mlx5_core_dev *dev, - struct mlx5_core_mkey *mkey, - u32 *in, int inlen); -int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, - struct mlx5_core_mkey *mkey); -int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *out, int outlen); +int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, + int inlen); +int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey); +int mlx5_core_query_mkey(struct mlx5_core_dev *dev, u32 mkey, u32 *out, + int outlen); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); int mlx5_pagealloc_init(struct mlx5_core_dev *dev); -- cgit v1.2.3 From 4123bfb0b28b77b944360be8c758b1a0974e96ad Mon Sep 17 00:00:00 2001 From: Aharon Landau Date: Tue, 12 Oct 2021 13:26:34 +0300 Subject: RDMA/mlx5: Move struct mlx5_core_mkey to mlx5_ib Move mlx5_core_mkey struct to mlx5_ib, as the mlx5_core doesn't use it at this point. Signed-off-by: Aharon Landau Reviewed-by: Shay Drory Acked-by: Michael S. Tsirkin Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/devx.c | 2 +- drivers/infiniband/hw/mlx5/mlx5_ib.h | 25 +++++++++++++++++++------ drivers/infiniband/hw/mlx5/mr.c | 12 +++++------- drivers/infiniband/hw/mlx5/odp.c | 8 ++++---- include/linux/mlx5/driver.h | 13 ------------- 5 files changed, 29 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 5322d787c094..d07a21a13ac0 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1293,7 +1293,7 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj, void *in, void *out) { struct mlx5_ib_devx_mr *devx_mr = &obj->devx_mr; - struct mlx5_core_mkey *mkey; + struct mlx5_ib_mkey *mkey; void *mkc; u8 key; diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index bf20a388eabe..8f754c52d469 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -619,6 +619,19 @@ struct mlx5_user_mmap_entry { u32 page_idx; }; +enum mlx5_mkey_type { + MLX5_MKEY_MR = 1, + MLX5_MKEY_MW, + MLX5_MKEY_INDIRECT_DEVX, +}; + +struct mlx5_ib_mkey { + u32 key; + enum mlx5_mkey_type type; + struct wait_queue_head wait; + refcount_t usecount; +}; + #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE) #define MLX5_IB_DM_MEMIC_ALLOWED_ACCESS (IB_ACCESS_LOCAL_WRITE |\ @@ -637,7 +650,7 @@ struct mlx5_user_mmap_entry { struct mlx5_ib_mr { struct ib_mr ibmr; - struct mlx5_core_mkey mmkey; + struct mlx5_ib_mkey mmkey; /* User MR data */ struct mlx5_cache_ent *cache_ent; @@ -713,12 +726,12 @@ static inline bool is_dmabuf_mr(struct mlx5_ib_mr *mr) struct mlx5_ib_mw { struct ib_mw ibmw; - struct mlx5_core_mkey mmkey; + struct mlx5_ib_mkey mmkey; int ndescs; }; struct mlx5_ib_devx_mr { - struct mlx5_core_mkey mmkey; + struct mlx5_ib_mkey mmkey; int ndescs; }; @@ -1579,7 +1592,7 @@ static inline bool mlx5_ib_can_reconfig_with_umr(struct mlx5_ib_dev *dev, } static inline int mlx5r_store_odp_mkey(struct mlx5_ib_dev *dev, - struct mlx5_core_mkey *mmkey) + struct mlx5_ib_mkey *mmkey) { refcount_set(&mmkey->usecount, 1); @@ -1588,14 +1601,14 @@ static inline int mlx5r_store_odp_mkey(struct mlx5_ib_dev *dev, } /* deref an mkey that can participate in ODP flow */ -static inline void mlx5r_deref_odp_mkey(struct mlx5_core_mkey *mmkey) +static inline void mlx5r_deref_odp_mkey(struct mlx5_ib_mkey *mmkey) { if (refcount_dec_and_test(&mmkey->usecount)) wake_up(&mmkey->wait); } /* deref an mkey that can participate in ODP flow and wait for relese */ -static inline void mlx5r_deref_wait_odp_mkey(struct mlx5_core_mkey *mmkey) +static inline void mlx5r_deref_wait_odp_mkey(struct mlx5_ib_mkey *mmkey) { mlx5r_deref_odp_mkey(mmkey); wait_event(mmkey->wait, refcount_read(&mmkey->usecount) == 0); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index e2f020472ae2..5afc3e965c28 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -88,9 +88,8 @@ static void set_mkc_access_pd_addr_fields(void *mkc, int acc, u64 start_addr, MLX5_SET64(mkc, mkc, start_addr, start_addr); } -static void -assign_mkey_variant(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in) +static void assign_mkey_variant(struct mlx5_ib_dev *dev, + struct mlx5_ib_mkey *mkey, u32 *in) { u8 key = atomic_inc_return(&dev->mkey_var); void *mkc; @@ -100,9 +99,8 @@ assign_mkey_variant(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey, mkey->key = key; } -static int -mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in, int inlen) +static int mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, + struct mlx5_ib_mkey *mkey, u32 *in, int inlen) { int ret; @@ -116,7 +114,7 @@ mlx5_ib_create_mkey(struct mlx5_ib_dev *dev, struct mlx5_core_mkey *mkey, static int mlx5_ib_create_mkey_cb(struct mlx5_ib_dev *dev, - struct mlx5_core_mkey *mkey, + struct mlx5_ib_mkey *mkey, struct mlx5_async_ctx *async_ctx, u32 *in, int inlen, u32 *out, int outlen, struct mlx5_async_work *context) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index a654367af056..7ab0a9b752f6 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -788,7 +788,7 @@ struct pf_frame { int depth; }; -static bool mkey_is_eq(struct mlx5_core_mkey *mmkey, u32 key) +static bool mkey_is_eq(struct mlx5_ib_mkey *mmkey, u32 key) { if (!mmkey) return false; @@ -797,7 +797,7 @@ static bool mkey_is_eq(struct mlx5_core_mkey *mmkey, u32 key) return mmkey->key == key; } -static int get_indirect_num_descs(struct mlx5_core_mkey *mmkey) +static int get_indirect_num_descs(struct mlx5_ib_mkey *mmkey) { struct mlx5_ib_mw *mw; struct mlx5_ib_devx_mr *devx_mr; @@ -831,7 +831,7 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev, { int npages = 0, ret, i, outlen, cur_outlen = 0, depth = 0; struct pf_frame *head = NULL, *frame; - struct mlx5_core_mkey *mmkey; + struct mlx5_ib_mkey *mmkey; struct mlx5_ib_mr *mr; struct mlx5_klm *pklm; u32 *out = NULL; @@ -1703,8 +1703,8 @@ get_prefetchable_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice, u32 lkey) { struct mlx5_ib_dev *dev = to_mdev(pd->device); - struct mlx5_core_mkey *mmkey; struct mlx5_ib_mr *mr = NULL; + struct mlx5_ib_mkey *mmkey; xa_lock(&dev->odp_mkeys); mmkey = xa_load(&dev->odp_mkeys, mlx5_base_mkey(lkey)); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index bd99f713720b..70b6aff4940a 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -357,19 +357,6 @@ struct mlx5_core_sig_ctx { u32 sigerr_count; }; -enum { - MLX5_MKEY_MR = 1, - MLX5_MKEY_MW, - MLX5_MKEY_INDIRECT_DEVX, -}; - -struct mlx5_core_mkey { - u32 key; - u32 type; - struct wait_queue_head wait; - refcount_t usecount; -}; - #define MLX5_24BIT_MASK ((1 << 24) - 1) enum mlx5_res_type { -- cgit v1.2.3 From e80094a473eefad9d856ce3ab0d7afdbb64800c4 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 18 Oct 2021 14:10:02 -0700 Subject: ethernet: add a helper for assigning port addresses We have 5 drivers which offset base MAC addr by port id. Create a helper for them. This helper takes care of overflows, which some drivers did not do, please complain if that's going to break anything! Signed-off-by: Jakub Kicinski Reviewed-by: Vladimir Oltean Reviewed-by: Shannon Nelson Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 23681c3d3b8a..2ad71cc90b37 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -551,6 +551,27 @@ static inline unsigned long compare_ether_header(const void *a, const void *b) #endif } +/** + * eth_hw_addr_gen - Generate and assign Ethernet address to a port + * @dev: pointer to port's net_device structure + * @base_addr: base Ethernet address + * @id: offset to add to the base address + * + * Generate a MAC address using a base address and an offset and assign it + * to a net_device. Commonly used by switch drivers which need to compute + * addresses for all their ports. addr_assign_type is not changed. + */ +static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, + unsigned int id) +{ + u64 u = ether_addr_to_u64(base_addr); + u8 addr[ETH_ALEN]; + + u += id; + u64_to_ether_addr(u, addr); + eth_hw_addr_set(dev, addr); +} + /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad -- cgit v1.2.3 From db9a02baa23267c695a44234a0f2f4607992780e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 6 Oct 2021 06:15:04 -0600 Subject: block: move bdev_read_only() into the header This is called for every write in the fast path, move it inline next to get_disk_ro() which is called internally. Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Signed-off-by: Jens Axboe --- block/genhd.c | 6 ------ include/linux/genhd.h | 5 +++++ 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 759bc06810f8..80943c123c3e 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1389,12 +1389,6 @@ void set_disk_ro(struct gendisk *disk, bool read_only) } EXPORT_SYMBOL(set_disk_ro); -int bdev_read_only(struct block_device *bdev) -{ - return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); -} -EXPORT_SYMBOL(bdev_read_only); - void inc_diskseq(struct gendisk *disk) { disk->diskseq = atomic64_inc_return(&diskseq); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index cd4038fd5743..c70bc5fce4db 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -221,6 +221,11 @@ static inline int get_disk_ro(struct gendisk *disk) test_bit(GD_READ_ONLY, &disk->state); } +static inline int bdev_read_only(struct block_device *bdev) +{ + return bdev->bd_read_only || get_disk_ro(bdev->bd_disk); +} + extern void disk_block_events(struct gendisk *disk); extern void disk_unblock_events(struct gendisk *disk); extern void disk_flush_events(struct gendisk *disk, unsigned int mask); -- cgit v1.2.3 From e028f167eca5fc56938e6c1680d40eed0bc39e80 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 16 Oct 2021 16:38:14 -0600 Subject: block: move blk_mq_tag_to_rq() inline This is in the fast path of driver issue or completion, and it's a single array index operation. Move it inline to avoid a function call for it. This does mean making struct blk_mq_tags block layer public, but there's not really much in there. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq-tag.h | 23 ----------------------- block/blk-mq.c | 11 ----------- include/linux/blk-mq.h | 36 +++++++++++++++++++++++++++++++++++- 3 files changed, 35 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 78ae2fb8e2a4..df787b5a23bd 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -4,29 +4,6 @@ struct blk_mq_alloc_data; -/* - * Tag address space map. - */ -struct blk_mq_tags { - unsigned int nr_tags; - unsigned int nr_reserved_tags; - - atomic_t active_queues; - - struct sbitmap_queue bitmap_tags; - struct sbitmap_queue breserved_tags; - - struct request **rqs; - struct request **static_rqs; - struct list_head page_list; - - /* - * used to clear request reference in rqs[] before freeing one - * request pool - */ - spinlock_t lock; -}; - extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy); diff --git a/block/blk-mq.c b/block/blk-mq.c index 104019c0ea41..8f5c1662335b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1120,17 +1120,6 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); -struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag) -{ - if (tag < tags->nr_tags) { - prefetch(tags->rqs[tag]); - return tags->rqs[tag]; - } - - return NULL; -} -EXPORT_SYMBOL(blk_mq_tag_to_rq); - static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 656fe34bdb6c..6cf35de151a9 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -7,6 +7,7 @@ #include #include #include +#include struct blk_mq_tags; struct blk_flush_queue; @@ -675,7 +676,40 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, struct request *blk_mq_alloc_request_hctx(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx); -struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag); + +/* + * Tag address space map. + */ +struct blk_mq_tags { + unsigned int nr_tags; + unsigned int nr_reserved_tags; + + atomic_t active_queues; + + struct sbitmap_queue bitmap_tags; + struct sbitmap_queue breserved_tags; + + struct request **rqs; + struct request **static_rqs; + struct list_head page_list; + + /* + * used to clear request reference in rqs[] before freeing one + * request pool + */ + spinlock_t lock; +}; + +static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, + unsigned int tag) +{ + if (tag < tags->nr_tags) { + prefetch(tags->rqs[tag]); + return tags->rqs[tag]; + } + + return NULL; +} enum { BLK_MQ_UNIQUE_TAG_BITS = 16, -- cgit v1.2.3 From bc490f81731e181b07b8d7577425c06ae91692c8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 18 Oct 2021 10:12:12 -0600 Subject: block: change plugging to use a singly linked list Use a singly linked list for the blk_plug. This saves 8 bytes in the blk_plug struct, and makes for faster list manipulations than doubly linked lists. As we don't use the doubly linked lists for anything, singly linked is just fine. This yields a bump in default (merging enabled) performance from 7.0 to 7.1M IOPS, and ~7.5M IOPS with merging disabled. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 4 +-- block/blk-merge.c | 4 +-- block/blk-mq.c | 80 ++++++++++++++++++++++++++++---------------------- include/linux/blkdev.h | 5 ++-- 4 files changed, 51 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index d0c2e11411d0..14d20909f61a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1550,7 +1550,7 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) if (tsk->plug) return; - INIT_LIST_HEAD(&plug->mq_list); + plug->mq_list = NULL; plug->cached_rq = NULL; plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); plug->rq_count = 0; @@ -1640,7 +1640,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { flush_plug_callbacks(plug, from_schedule); - if (!list_empty(&plug->mq_list)) + if (!rq_list_empty(plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); if (unlikely(!from_schedule && plug->cached_rq)) blk_mq_free_plug_rqs(plug); diff --git a/block/blk-merge.c b/block/blk-merge.c index c273b58378ce..3e6fa449caff 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -1090,11 +1090,11 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, struct request *rq; plug = blk_mq_plug(q, bio); - if (!plug || list_empty(&plug->mq_list)) + if (!plug || rq_list_empty(plug->mq_list)) return false; /* check the previously added entry for a quick merge attempt */ - rq = list_last_entry(&plug->mq_list, struct request, queuelist); + rq = rq_list_peek(&plug->mq_list); if (rq->q == q) { /* * Only blk-mq multiple hardware queues case checks the rq in diff --git a/block/blk-mq.c b/block/blk-mq.c index 8f5c1662335b..7fa302730d4a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2151,34 +2151,46 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { + struct blk_mq_hw_ctx *this_hctx; + struct blk_mq_ctx *this_ctx; + unsigned int depth; LIST_HEAD(list); - if (list_empty(&plug->mq_list)) + if (rq_list_empty(plug->mq_list)) return; - list_splice_init(&plug->mq_list, &list); plug->rq_count = 0; + this_hctx = NULL; + this_ctx = NULL; + depth = 0; do { - struct list_head rq_list; - struct request *rq, *head_rq = list_entry_rq(list.next); - struct list_head *pos = &head_rq->queuelist; /* skip first */ - struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx; - struct blk_mq_ctx *this_ctx = head_rq->mq_ctx; - unsigned int depth = 1; - - list_for_each_continue(pos, &list) { - rq = list_entry_rq(pos); - BUG_ON(!rq->q); - if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx) - break; - depth++; + struct request *rq; + + rq = rq_list_pop(&plug->mq_list); + + if (!this_hctx) { + this_hctx = rq->mq_hctx; + this_ctx = rq->mq_ctx; + } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { + trace_block_unplug(this_hctx->queue, depth, + !from_schedule); + blk_mq_sched_insert_requests(this_hctx, this_ctx, + &list, from_schedule); + depth = 0; + this_hctx = rq->mq_hctx; + this_ctx = rq->mq_ctx; + } - list_cut_before(&rq_list, &list, pos); - trace_block_unplug(head_rq->q, depth, !from_schedule); - blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list, + list_add(&rq->queuelist, &list); + depth++; + } while (!rq_list_empty(plug->mq_list)); + + if (!list_empty(&list)) { + trace_block_unplug(this_hctx->queue, depth, !from_schedule); + blk_mq_sched_insert_requests(this_hctx, this_ctx, &list, from_schedule); - } while(!list_empty(&list)); + } } static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, @@ -2358,16 +2370,15 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) { - list_add_tail(&rq->queuelist, &plug->mq_list); - plug->rq_count++; - if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) { - struct request *tmp; + if (!plug->multiple_queues) { + struct request *nxt = rq_list_peek(&plug->mq_list); - tmp = list_first_entry(&plug->mq_list, struct request, - queuelist); - if (tmp->q != rq->q) + if (nxt && nxt->q != rq->q) plug->multiple_queues = true; } + rq->rq_next = NULL; + rq_list_add(&plug->mq_list, rq); + plug->rq_count++; } /* @@ -2479,13 +2490,15 @@ void blk_mq_submit_bio(struct bio *bio) unsigned int request_count = plug->rq_count; struct request *last = NULL; - if (!request_count) + if (!request_count) { trace_block_plug(q); - else - last = list_entry_rq(plug->mq_list.prev); + } else if (!blk_queue_nomerges(q)) { + last = rq_list_peek(&plug->mq_list); + if (blk_rq_bytes(last) < BLK_PLUG_FLUSH_SIZE) + last = NULL; + } - if (request_count >= blk_plug_max_rq_count(plug) || (last && - blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { + if (request_count >= blk_plug_max_rq_count(plug) || last) { blk_flush_plug_list(plug, false); trace_block_plug(q); } @@ -2505,10 +2518,7 @@ void blk_mq_submit_bio(struct bio *bio) * the plug list is empty, and same_queue_rq is invalid. */ if (same_queue_rq) { - next_rq = list_last_entry(&plug->mq_list, - struct request, - queuelist); - list_del_init(&next_rq->queuelist); + next_rq = rq_list_pop(&plug->mq_list); plug->rq_count--; } blk_add_rq_to_plug(plug, rq); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fd9771a1da09..4027112b9851 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -728,7 +728,7 @@ extern void blk_set_queue_dying(struct request_queue *); * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { - struct list_head mq_list; /* blk-mq requests */ + struct request *mq_list; /* blk-mq requests */ /* if ios_left is > 1, we can batch tag/rq allocations */ struct request *cached_rq; @@ -777,8 +777,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) struct blk_plug *plug = tsk->plug; return plug && - (!list_empty(&plug->mq_list) || - !list_empty(&plug->cb_list)); + (plug->mq_list || !list_empty(&plug->cb_list)); } int blkdev_issue_flush(struct block_device *bdev); -- cgit v1.2.3 From dc5fc361d891e089dfd9c0a975dc78041036b906 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 19 Oct 2021 06:02:30 -0600 Subject: block: attempt direct issue of plug list If we have just one queue type in the plug list, then we can extend our direct issue to cover a full plug list as well. This allows sending a batch of requests for direct issue, which is more efficient than doing one-at-a-time kind of issue. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + block/blk-mq.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 1 + 3 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 14d20909f61a..e6ad5b51d0c3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1555,6 +1555,7 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios) plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT); plug->rq_count = 0; plug->multiple_queues = false; + plug->has_elevator = false; plug->nowait = false; INIT_LIST_HEAD(&plug->cb_list); diff --git a/block/blk-mq.c b/block/blk-mq.c index 7fa302730d4a..71ab7521dd3d 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2149,6 +2149,58 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx, spin_unlock(&ctx->lock); } +static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int *queued, + bool from_schedule) +{ + if (hctx->queue->mq_ops->commit_rqs) { + trace_block_unplug(hctx->queue, *queued, !from_schedule); + hctx->queue->mq_ops->commit_rqs(hctx); + } + *queued = 0; +} + +static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule) +{ + struct blk_mq_hw_ctx *hctx = NULL; + struct request *rq; + int queued = 0; + int errors = 0; + + while ((rq = rq_list_pop(&plug->mq_list))) { + bool last = rq_list_empty(plug->mq_list); + blk_status_t ret; + + if (hctx != rq->mq_hctx) { + if (hctx) + blk_mq_commit_rqs(hctx, &queued, from_schedule); + hctx = rq->mq_hctx; + } + + ret = blk_mq_request_issue_directly(rq, last); + switch (ret) { + case BLK_STS_OK: + queued++; + break; + case BLK_STS_RESOURCE: + case BLK_STS_DEV_RESOURCE: + blk_mq_request_bypass_insert(rq, false, last); + blk_mq_commit_rqs(hctx, &queued, from_schedule); + return; + default: + blk_mq_end_request(rq, ret); + errors++; + break; + } + } + + /* + * If we didn't flush the entire list, we could have told the driver + * there was more coming, but that turned out to be a lie. + */ + if (errors) + blk_mq_commit_rqs(hctx, &queued, from_schedule); +} + void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct blk_mq_hw_ctx *this_hctx; @@ -2160,6 +2212,12 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) return; plug->rq_count = 0; + if (!plug->multiple_queues && !plug->has_elevator) { + blk_mq_plug_issue_direct(plug, from_schedule); + if (rq_list_empty(plug->mq_list)) + return; + } + this_hctx = NULL; this_ctx = NULL; depth = 0; @@ -2376,6 +2434,8 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) if (nxt && nxt->q != rq->q) plug->multiple_queues = true; } + if (!plug->has_elevator && (rq->rq_flags & RQF_ELV)) + plug->has_elevator = true; rq->rq_next = NULL; rq_list_add(&plug->mq_list, rq); plug->rq_count++; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4027112b9851..f13091d3d476 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -737,6 +737,7 @@ struct blk_plug { unsigned short rq_count; bool multiple_queues; + bool has_elevator; bool nowait; struct list_head cb_list; /* md requires an unplug callback */ -- cgit v1.2.3 From cd45c9bf8b43cd387e167cf166ae5c517f56d658 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Mon, 18 Oct 2021 16:33:22 +0200 Subject: ASoC: Intel: Move soc_intel_is_foo() helpers to a generic header The soc_intel_is_foo() helpers from sound/soc/intel/common/soc-intel-quirks.h are useful outside of the sound subsystem too. Move these to include/linux/platform_data/x86/soc.h, so that other code can use them too. Suggested-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Acked-by: Mark Brown Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20211018143324.296961-2-hdegoede@redhat.com --- include/linux/platform_data/x86/soc.h | 65 +++++++++++++++++++++++++++++++ sound/soc/intel/common/soc-intel-quirks.h | 51 ++---------------------- 2 files changed, 68 insertions(+), 48 deletions(-) create mode 100644 include/linux/platform_data/x86/soc.h (limited to 'include/linux') diff --git a/include/linux/platform_data/x86/soc.h b/include/linux/platform_data/x86/soc.h new file mode 100644 index 000000000000..da05f425587a --- /dev/null +++ b/include/linux/platform_data/x86/soc.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Helpers for Intel SoC model detection + * + * Copyright (c) 2019, Intel Corporation. + */ + +#ifndef __PLATFORM_DATA_X86_SOC_H +#define __PLATFORM_DATA_X86_SOC_H + +#if IS_ENABLED(CONFIG_X86) + +#include +#include + +#define SOC_INTEL_IS_CPU(soc, type) \ +static inline bool soc_intel_is_##soc(void) \ +{ \ + static const struct x86_cpu_id soc##_cpu_ids[] = { \ + X86_MATCH_INTEL_FAM6_MODEL(type, NULL), \ + {} \ + }; \ + const struct x86_cpu_id *id; \ + \ + id = x86_match_cpu(soc##_cpu_ids); \ + if (id) \ + return true; \ + return false; \ +} + +SOC_INTEL_IS_CPU(byt, ATOM_SILVERMONT); +SOC_INTEL_IS_CPU(cht, ATOM_AIRMONT); +SOC_INTEL_IS_CPU(apl, ATOM_GOLDMONT); +SOC_INTEL_IS_CPU(glk, ATOM_GOLDMONT_PLUS); +SOC_INTEL_IS_CPU(cml, KABYLAKE_L); + +#else /* IS_ENABLED(CONFIG_X86) */ + +static inline bool soc_intel_is_byt(void) +{ + return false; +} + +static inline bool soc_intel_is_cht(void) +{ + return false; +} + +static inline bool soc_intel_is_apl(void) +{ + return false; +} + +static inline bool soc_intel_is_glk(void) +{ + return false; +} + +static inline bool soc_intel_is_cml(void) +{ + return false; +} +#endif /* IS_ENABLED(CONFIG_X86) */ + +#endif /* __PLATFORM_DATA_X86_SOC_H */ diff --git a/sound/soc/intel/common/soc-intel-quirks.h b/sound/soc/intel/common/soc-intel-quirks.h index a93987ab7f4d..de4e550c5b34 100644 --- a/sound/soc/intel/common/soc-intel-quirks.h +++ b/sound/soc/intel/common/soc-intel-quirks.h @@ -9,34 +9,13 @@ #ifndef _SND_SOC_INTEL_QUIRKS_H #define _SND_SOC_INTEL_QUIRKS_H +#include + #if IS_ENABLED(CONFIG_X86) #include -#include -#include #include -#define SOC_INTEL_IS_CPU(soc, type) \ -static inline bool soc_intel_is_##soc(void) \ -{ \ - static const struct x86_cpu_id soc##_cpu_ids[] = { \ - X86_MATCH_INTEL_FAM6_MODEL(type, NULL), \ - {} \ - }; \ - const struct x86_cpu_id *id; \ - \ - id = x86_match_cpu(soc##_cpu_ids); \ - if (id) \ - return true; \ - return false; \ -} - -SOC_INTEL_IS_CPU(byt, ATOM_SILVERMONT); -SOC_INTEL_IS_CPU(cht, ATOM_AIRMONT); -SOC_INTEL_IS_CPU(apl, ATOM_GOLDMONT); -SOC_INTEL_IS_CPU(glk, ATOM_GOLDMONT_PLUS); -SOC_INTEL_IS_CPU(cml, KABYLAKE_L); - static inline bool soc_intel_is_byt_cr(struct platform_device *pdev) { /* @@ -114,30 +93,6 @@ static inline bool soc_intel_is_byt_cr(struct platform_device *pdev) return false; } -static inline bool soc_intel_is_byt(void) -{ - return false; -} - -static inline bool soc_intel_is_cht(void) -{ - return false; -} - -static inline bool soc_intel_is_apl(void) -{ - return false; -} - -static inline bool soc_intel_is_glk(void) -{ - return false; -} - -static inline bool soc_intel_is_cml(void) -{ - return false; -} #endif - #endif /* _SND_SOC_INTEL_QUIRKS_H */ +#endif /* _SND_SOC_INTEL_QUIRKS_H */ -- cgit v1.2.3 From aaa2975f2b07b04ee16b2cad1072cbdea3e1c50a Mon Sep 17 00:00:00 2001 From: Lasse Collin Date: Mon, 11 Oct 2021 05:31:42 +0800 Subject: lib/xz: Add MicroLZMA decoder MicroLZMA is a yet another header format variant where the first byte of a raw LZMA stream (without the end of stream marker) has been replaced with a bitwise-negation of the lc/lp/pb properties byte. MicroLZMA was created to be used in EROFS but can be used by other things too where wasting minimal amount of space for headers is important. This is implemented using most of the LZMA2 code as is so the amount of new code is small. The API has a few extra features compared to the XZ decoder. On the other hand, the API lacks XZ_BUF_ERROR support which is important to take into account when using this API. MicroLZMA doesn't support BCJ filters. In theory they could be added later as there are many unused/reserved values for the first byte of the compressed stream but in practice it is somewhat unlikely to happen due to a few implementation reasons. Link: https://lore.kernel.org/r/20211010213145.17462-5-xiang@kernel.org Signed-off-by: Lasse Collin Signed-off-by: Gao Xiang --- include/linux/xz.h | 106 ++++++++++++++++++++++++++++++++++ lib/xz/Kconfig | 13 +++++ lib/xz/xz_dec_lzma2.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++++- lib/xz/xz_dec_syms.c | 9 ++- lib/xz/xz_private.h | 3 + 5 files changed, 284 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xz.h b/include/linux/xz.h index 9884c8440188..7285ca5d56e9 100644 --- a/include/linux/xz.h +++ b/include/linux/xz.h @@ -233,6 +233,112 @@ XZ_EXTERN void xz_dec_reset(struct xz_dec *s); */ XZ_EXTERN void xz_dec_end(struct xz_dec *s); +/* + * Decompressor for MicroLZMA, an LZMA variant with a very minimal header. + * See xz_dec_microlzma_alloc() below for details. + * + * These functions aren't used or available in preboot code and thus aren't + * marked with XZ_EXTERN. This avoids warnings about static functions that + * are never defined. + */ +/** + * struct xz_dec_microlzma - Opaque type to hold the MicroLZMA decoder state + */ +struct xz_dec_microlzma; + +/** + * xz_dec_microlzma_alloc() - Allocate memory for the MicroLZMA decoder + * @mode XZ_SINGLE or XZ_PREALLOC + * @dict_size LZMA dictionary size. This must be at least 4 KiB and + * at most 3 GiB. + * + * In contrast to xz_dec_init(), this function only allocates the memory + * and remembers the dictionary size. xz_dec_microlzma_reset() must be used + * before calling xz_dec_microlzma_run(). + * + * The amount of allocated memory is a little less than 30 KiB with XZ_SINGLE. + * With XZ_PREALLOC also a dictionary buffer of dict_size bytes is allocated. + * + * On success, xz_dec_microlzma_alloc() returns a pointer to + * struct xz_dec_microlzma. If memory allocation fails or + * dict_size is invalid, NULL is returned. + * + * The compressed format supported by this decoder is a raw LZMA stream + * whose first byte (always 0x00) has been replaced with bitwise-negation + * of the LZMA properties (lc/lp/pb) byte. For example, if lc/lp/pb is + * 3/0/2, the first byte is 0xA2. This way the first byte can never be 0x00. + * Just like with LZMA2, lc + lp <= 4 must be true. The LZMA end-of-stream + * marker must not be used. The unused values are reserved for future use. + * This MicroLZMA header format was created for use in EROFS but may be used + * by others too. + */ +extern struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, + uint32_t dict_size); + +/** + * xz_dec_microlzma_reset() - Reset the MicroLZMA decoder state + * @s Decoder state allocated using xz_dec_microlzma_alloc() + * @comp_size Compressed size of the input stream + * @uncomp_size Uncompressed size of the input stream. A value smaller + * than the real uncompressed size of the input stream can + * be specified if uncomp_size_is_exact is set to false. + * uncomp_size can never be set to a value larger than the + * expected real uncompressed size because it would eventually + * result in XZ_DATA_ERROR. + * @uncomp_size_is_exact This is an int instead of bool to avoid + * requiring stdbool.h. This should normally be set to true. + * When this is set to false, error detection is weaker. + */ +extern void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, + uint32_t comp_size, uint32_t uncomp_size, + int uncomp_size_is_exact); + +/** + * xz_dec_microlzma_run() - Run the MicroLZMA decoder + * @s Decoder state initialized using xz_dec_microlzma_reset() + * @b: Input and output buffers + * + * This works similarly to xz_dec_run() with a few important differences. + * Only the differences are documented here. + * + * The only possible return values are XZ_OK, XZ_STREAM_END, and + * XZ_DATA_ERROR. This function cannot return XZ_BUF_ERROR: if no progress + * is possible due to lack of input data or output space, this function will + * keep returning XZ_OK. Thus, the calling code must be written so that it + * will eventually provide input and output space matching (or exceeding) + * comp_size and uncomp_size arguments given to xz_dec_microlzma_reset(). + * If the caller cannot do this (for example, if the input file is truncated + * or otherwise corrupt), the caller must detect this error by itself to + * avoid an infinite loop. + * + * If the compressed data seems to be corrupt, XZ_DATA_ERROR is returned. + * This can happen also when incorrect dictionary, uncompressed, or + * compressed sizes have been specified. + * + * With XZ_PREALLOC only: As an extra feature, b->out may be NULL to skip over + * uncompressed data. This way the caller doesn't need to provide a temporary + * output buffer for the bytes that will be ignored. + * + * With XZ_SINGLE only: In contrast to xz_dec_run(), the return value XZ_OK + * is also possible and thus XZ_SINGLE is actually a limited multi-call mode. + * After XZ_OK the bytes decoded so far may be read from the output buffer. + * It is possible to continue decoding but the variables b->out and b->out_pos + * MUST NOT be changed by the caller. Increasing the value of b->out_size is + * allowed to make more output space available; one doesn't need to provide + * space for the whole uncompressed data on the first call. The input buffer + * may be changed normally like with XZ_PREALLOC. This way input data can be + * provided from non-contiguous memory. + */ +extern enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s, + struct xz_buf *b); + +/** + * xz_dec_microlzma_end() - Free the memory allocated for the decoder state + * @s: Decoder state allocated using xz_dec_microlzma_alloc(). + * If s is NULL, this function does nothing. + */ +extern void xz_dec_microlzma_end(struct xz_dec_microlzma *s); + /* * Standalone build (userspace build or in-kernel build for boot time use) * needs a CRC32 implementation. For normal in-kernel use, kernel's own diff --git a/lib/xz/Kconfig b/lib/xz/Kconfig index 5cb50245a878..adce22ac18d6 100644 --- a/lib/xz/Kconfig +++ b/lib/xz/Kconfig @@ -39,6 +39,19 @@ config XZ_DEC_SPARC default y select XZ_DEC_BCJ +config XZ_DEC_MICROLZMA + bool "MicroLZMA decoder" + default n + help + MicroLZMA is a header format variant where the first byte + of a raw LZMA stream (without the end of stream marker) has + been replaced with a bitwise-negation of the lc/lp/pb + properties byte. MicroLZMA was created to be used in EROFS + but can be used by other things too where wasting minimal + amount of space for headers is important. + + Unless you know that you need this, say N. + endif config XZ_DEC_BCJ diff --git a/lib/xz/xz_dec_lzma2.c b/lib/xz/xz_dec_lzma2.c index 22b789645ce5..46b186d7eb45 100644 --- a/lib/xz/xz_dec_lzma2.c +++ b/lib/xz/xz_dec_lzma2.c @@ -248,6 +248,10 @@ struct lzma2_dec { * before the first LZMA chunk. */ bool need_props; + +#ifdef XZ_DEC_MICROLZMA + bool pedantic_microlzma; +#endif }; struct xz_dec_lzma2 { @@ -419,6 +423,12 @@ static void dict_uncompressed(struct dictionary *dict, struct xz_buf *b, } } +#ifdef XZ_DEC_MICROLZMA +# define DICT_FLUSH_SUPPORTS_SKIPPING true +#else +# define DICT_FLUSH_SUPPORTS_SKIPPING false +#endif + /* * Flush pending data from dictionary to b->out. It is assumed that there is * enough space in b->out. This is guaranteed because caller uses dict_limit() @@ -437,9 +447,14 @@ static uint32_t dict_flush(struct dictionary *dict, struct xz_buf *b) * decompression because in multi-call mode dict->buf * has been allocated by us in this file; it's not * provided by the caller like in single-call mode. + * + * With MicroLZMA, b->out can be NULL to skip bytes that + * the caller doesn't need. This cannot be done with XZ + * because it would break BCJ filters. */ - memcpy(b->out + b->out_pos, dict->buf + dict->start, - copy_size); + if (!DICT_FLUSH_SUPPORTS_SKIPPING || b->out != NULL) + memcpy(b->out + b->out_pos, dict->buf + dict->start, + copy_size); } dict->start = dict->pos; @@ -1190,3 +1205,140 @@ XZ_EXTERN void xz_dec_lzma2_end(struct xz_dec_lzma2 *s) kfree(s); } + +#ifdef XZ_DEC_MICROLZMA +/* This is a wrapper struct to have a nice struct name in the public API. */ +struct xz_dec_microlzma { + struct xz_dec_lzma2 s; +}; + +enum xz_ret xz_dec_microlzma_run(struct xz_dec_microlzma *s_ptr, + struct xz_buf *b) +{ + struct xz_dec_lzma2 *s = &s_ptr->s; + + /* + * sequence is SEQ_PROPERTIES before the first input byte, + * SEQ_LZMA_PREPARE until a total of five bytes have been read, + * and SEQ_LZMA_RUN for the rest of the input stream. + */ + if (s->lzma2.sequence != SEQ_LZMA_RUN) { + if (s->lzma2.sequence == SEQ_PROPERTIES) { + /* One byte is needed for the props. */ + if (b->in_pos >= b->in_size) + return XZ_OK; + + /* + * Don't increment b->in_pos here. The same byte is + * also passed to rc_read_init() which will ignore it. + */ + if (!lzma_props(s, ~b->in[b->in_pos])) + return XZ_DATA_ERROR; + + s->lzma2.sequence = SEQ_LZMA_PREPARE; + } + + /* + * xz_dec_microlzma_reset() doesn't validate the compressed + * size so we do it here. We have to limit the maximum size + * to avoid integer overflows in lzma2_lzma(). 3 GiB is a nice + * round number and much more than users of this code should + * ever need. + */ + if (s->lzma2.compressed < RC_INIT_BYTES + || s->lzma2.compressed > (3U << 30)) + return XZ_DATA_ERROR; + + if (!rc_read_init(&s->rc, b)) + return XZ_OK; + + s->lzma2.compressed -= RC_INIT_BYTES; + s->lzma2.sequence = SEQ_LZMA_RUN; + + dict_reset(&s->dict, b); + } + + /* This is to allow increasing b->out_size between calls. */ + if (DEC_IS_SINGLE(s->dict.mode)) + s->dict.end = b->out_size - b->out_pos; + + while (true) { + dict_limit(&s->dict, min_t(size_t, b->out_size - b->out_pos, + s->lzma2.uncompressed)); + + if (!lzma2_lzma(s, b)) + return XZ_DATA_ERROR; + + s->lzma2.uncompressed -= dict_flush(&s->dict, b); + + if (s->lzma2.uncompressed == 0) { + if (s->lzma2.pedantic_microlzma) { + if (s->lzma2.compressed > 0 || s->lzma.len > 0 + || !rc_is_finished(&s->rc)) + return XZ_DATA_ERROR; + } + + return XZ_STREAM_END; + } + + if (b->out_pos == b->out_size) + return XZ_OK; + + if (b->in_pos == b->in_size + && s->temp.size < s->lzma2.compressed) + return XZ_OK; + } +} + +struct xz_dec_microlzma *xz_dec_microlzma_alloc(enum xz_mode mode, + uint32_t dict_size) +{ + struct xz_dec_microlzma *s; + + /* Restrict dict_size to the same range as in the LZMA2 code. */ + if (dict_size < 4096 || dict_size > (3U << 30)) + return NULL; + + s = kmalloc(sizeof(*s), GFP_KERNEL); + if (s == NULL) + return NULL; + + s->s.dict.mode = mode; + s->s.dict.size = dict_size; + + if (DEC_IS_MULTI(mode)) { + s->s.dict.end = dict_size; + + s->s.dict.buf = vmalloc(dict_size); + if (s->s.dict.buf == NULL) { + kfree(s); + return NULL; + } + } + + return s; +} + +void xz_dec_microlzma_reset(struct xz_dec_microlzma *s, uint32_t comp_size, + uint32_t uncomp_size, int uncomp_size_is_exact) +{ + /* + * comp_size is validated in xz_dec_microlzma_run(). + * uncomp_size can safely be anything. + */ + s->s.lzma2.compressed = comp_size; + s->s.lzma2.uncompressed = uncomp_size; + s->s.lzma2.pedantic_microlzma = uncomp_size_is_exact; + + s->s.lzma2.sequence = SEQ_PROPERTIES; + s->s.temp.size = 0; +} + +void xz_dec_microlzma_end(struct xz_dec_microlzma *s) +{ + if (DEC_IS_MULTI(s->s.dict.mode)) + vfree(s->s.dict.buf); + + kfree(s); +} +#endif diff --git a/lib/xz/xz_dec_syms.c b/lib/xz/xz_dec_syms.c index 32eb3c03aede..61098c67a413 100644 --- a/lib/xz/xz_dec_syms.c +++ b/lib/xz/xz_dec_syms.c @@ -15,8 +15,15 @@ EXPORT_SYMBOL(xz_dec_reset); EXPORT_SYMBOL(xz_dec_run); EXPORT_SYMBOL(xz_dec_end); +#ifdef CONFIG_XZ_DEC_MICROLZMA +EXPORT_SYMBOL(xz_dec_microlzma_alloc); +EXPORT_SYMBOL(xz_dec_microlzma_reset); +EXPORT_SYMBOL(xz_dec_microlzma_run); +EXPORT_SYMBOL(xz_dec_microlzma_end); +#endif + MODULE_DESCRIPTION("XZ decompressor"); -MODULE_VERSION("1.0"); +MODULE_VERSION("1.1"); MODULE_AUTHOR("Lasse Collin and Igor Pavlov"); /* diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h index 09360ebb510e..bf1e94ec7873 100644 --- a/lib/xz/xz_private.h +++ b/lib/xz/xz_private.h @@ -37,6 +37,9 @@ # ifdef CONFIG_XZ_DEC_SPARC # define XZ_DEC_SPARC # endif +# ifdef CONFIG_XZ_DEC_MICROLZMA +# define XZ_DEC_MICROLZMA +# endif # define memeq(a, b, size) (memcmp(a, b, size) == 0) # define memzero(buf, size) memset(buf, 0, size) # endif -- cgit v1.2.3 From e70feb8b3e6886c525c88943b5f1508d02f5a683 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 14 Oct 2021 16:17:10 +0800 Subject: blk-mq: support concurrent queue quiesce/unquiesce blk_mq_quiesce_queue() has been used a bit wide now, so far we don't support concurrent/nested quiesce. One biggest issue is that unquiesce can happen unexpectedly in case that quiesce/unquiesce are run concurrently from more than one context. This patch introduces q->mq_quiesce_depth to deal concurrent quiesce, and we only unquiesce queue when it is the last/outer-most one of all contexts. Several kernel panic issue has been reported[1][2][3] when running stress quiesce test. And this patch has been verified in these reports. [1] https://lore.kernel.org/linux-block/9b21c797-e505-3821-4f5b-df7bf9380328@huawei.com/T/#m1fc52431fad7f33b1ffc3f12c4450e4238540787 [2] https://lore.kernel.org/linux-block/9b21c797-e505-3821-4f5b-df7bf9380328@huawei.com/T/#m10ad90afeb9c8cc318334190a7c24c8b5c5e0722 [3] https://listman.redhat.com/archives/dm-devel/2021-September/msg00189.html Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211014081710.1871747-7-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/blk-mq.c | 22 +++++++++++++++++++--- include/linux/blkdev.h | 2 ++ 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index bf5936d72de8..31d9e612d236 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -241,7 +241,12 @@ EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue); */ void blk_mq_quiesce_queue_nowait(struct request_queue *q) { - blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); + unsigned long flags; + + spin_lock_irqsave(&q->queue_lock, flags); + if (!q->quiesce_depth++) + blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q); + spin_unlock_irqrestore(&q->queue_lock, flags); } EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); @@ -282,10 +287,21 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); */ void blk_mq_unquiesce_queue(struct request_queue *q) { - blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); + unsigned long flags; + bool run_queue = false; + + spin_lock_irqsave(&q->queue_lock, flags); + if (WARN_ON_ONCE(q->quiesce_depth <= 0)) { + ; + } else if (!--q->quiesce_depth) { + blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q); + run_queue = true; + } + spin_unlock_irqrestore(&q->queue_lock, flags); /* dispatch requests which are inserted during quiescing */ - blk_mq_run_hw_queues(q, true); + if (run_queue) + blk_mq_run_hw_queues(q, true); } EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f13091d3d476..2b22fa36e568 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -315,6 +315,8 @@ struct request_queue { */ struct mutex mq_freeze_lock; + int quiesce_depth; + struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set bio_split; -- cgit v1.2.3 From 34cdd18b8d245f3e901e5325313c27de727ab80d Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Wed, 17 Jun 2020 16:56:16 -0400 Subject: tracing: Use linker magic instead of recasting ftrace_ops_list_func() In an effort to enable -Wcast-function-type in the top-level Makefile to support Control Flow Integrity builds, all function casts need to be removed. This means that ftrace_ops_list_func() can no longer be defined as ftrace_ops_no_ops(). The reason for ftrace_ops_no_ops() is to use that when an architecture calls ftrace_ops_list_func() with only two parameters (called from assembly). And to make sure there's no C side-effects, those archs call ftrace_ops_no_ops() which only has two parameters, as ftrace_ops_list_func() has four parameters. Instead of a typecast, use vmlinux.lds.h to define ftrace_ops_list_func() to arch_ftrace_ops_list_func() that will define the proper set of parameters. Link: https://lore.kernel.org/r/20200614070154.6039-1-oscar.carter@gmx.com Link: https://lkml.kernel.org/r/20200617165616.52241bde@oasis.local.home Link: https://lore.kernel.org/all/20211005053922.GA702049@embeddedor/ Requested-by: Oscar Carter Reported-by: kernel test robot Signed-off-by: Steven Rostedt (VMware) --- include/asm-generic/vmlinux.lds.h | 10 ++++++++-- include/linux/ftrace.h | 12 ++++++++++-- kernel/trace/ftrace.c | 23 ++++++++++------------- 3 files changed, 28 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index f2984af2b85b..8771c435f34b 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -164,16 +164,22 @@ * Need to also make ftrace_stub_graph point to ftrace_stub * so that the same stub location may have different protocols * and not mess up with C verifiers. + * + * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func + * as some archs will have a different prototype for that function + * but ftrace_ops_list_func() will have a single prototype. */ #define MCOUNT_REC() . = ALIGN(8); \ __start_mcount_loc = .; \ KEEP(*(__mcount_loc)) \ KEEP(*(__patchable_function_entries)) \ __stop_mcount_loc = .; \ - ftrace_stub_graph = ftrace_stub; + ftrace_stub_graph = ftrace_stub; \ + ftrace_ops_list_func = arch_ftrace_ops_list_func; #else # ifdef CONFIG_FUNCTION_TRACER -# define MCOUNT_REC() ftrace_stub_graph = ftrace_stub; +# define MCOUNT_REC() ftrace_stub_graph = ftrace_stub; \ + ftrace_ops_list_func = arch_ftrace_ops_list_func; # else # define MCOUNT_REC() # endif diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 832e65f06754..12fcfa2d23ea 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -30,16 +30,26 @@ #define ARCH_SUPPORTS_FTRACE_OPS 0 #endif +#ifdef CONFIG_FUNCTION_TRACER +struct ftrace_ops; +struct ftrace_regs; /* * If the arch's mcount caller does not support all of ftrace's * features, then it must call an indirect function that * does. Or at least does enough to prevent any unwelcome side effects. + * + * Also define the function prototype that these architectures use + * to call the ftrace_ops_list_func(). */ #if !ARCH_SUPPORTS_FTRACE_OPS # define FTRACE_FORCE_LIST_FUNC 1 +void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); #else # define FTRACE_FORCE_LIST_FUNC 0 +void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); #endif +#endif /* CONFIG_FUNCTION_TRACER */ /* Main tracing buffer and events set up */ #ifdef CONFIG_TRACING @@ -88,8 +98,6 @@ extern int ftrace_enable_sysctl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -struct ftrace_ops; - #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS struct ftrace_regs { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2c3e9760df7f..8b5801881271 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -119,14 +119,9 @@ struct ftrace_ops __rcu *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; struct ftrace_ops global_ops; -#if ARCH_SUPPORTS_FTRACE_OPS -static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct ftrace_regs *fregs); -#else -/* See comment below, where ftrace_ops_list_func is defined */ -static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); -#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) -#endif +/* Defined by vmlinux.lds.h see the commment above arch_ftrace_ops_list_func for details */ +void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); static inline void ftrace_ops_init(struct ftrace_ops *ops) { @@ -7032,21 +7027,23 @@ out: * Note, CONFIG_DYNAMIC_FTRACE_WITH_REGS expects a full regs to be saved. * An architecture can pass partial regs with ftrace_ops and still * set the ARCH_SUPPORTS_FTRACE_OPS. + * + * In vmlinux.lds.h, ftrace_ops_list_func() is defined to be + * arch_ftrace_ops_list_func. */ #if ARCH_SUPPORTS_FTRACE_OPS -static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *op, struct ftrace_regs *fregs) +void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) { __ftrace_ops_list_func(ip, parent_ip, NULL, fregs); } -NOKPROBE_SYMBOL(ftrace_ops_list_func); #else -static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) { __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); } -NOKPROBE_SYMBOL(ftrace_ops_no_ops); #endif +NOKPROBE_SYMBOL(arch_ftrace_ops_list_func); /* * If there's only one function registered but it does not support -- cgit v1.2.3 From 9b84fadc444de5456ab5f5487e2108311c724c3f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 15 Oct 2021 13:42:40 -0400 Subject: tracing: Reuse logic from perf's get_recursion_context() Instead of having branches that adds noise to the branch prediction, use the addition logic to set the bit for the level of interrupt context that the state is currently in. This copies the logic from perf's get_recursion_context() function. Link: https://lore.kernel.org/all/20211015161702.GF174703@worktop.programming.kicks-ass.net/ Suggested-by: Peter Zijlstra Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 11 ++++++----- kernel/trace/ring_buffer.c | 12 ++++++------ 2 files changed, 12 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index a9f9c5714e65..f6da7a03bff0 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -137,12 +137,13 @@ enum { static __always_inline int trace_get_context_bit(void) { unsigned long pc = preempt_count(); + unsigned char bit = 0; - if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) - return TRACE_CTX_NORMAL; - else - return pc & NMI_MASK ? TRACE_CTX_NMI : - pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ; + bit += !!(pc & (NMI_MASK)); + bit += !!(pc & (NMI_MASK | HARDIRQ_MASK)); + bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); + + return TRACE_CTX_NORMAL - bit; } #ifdef CONFIG_FTRACE_RECORD_RECURSION diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index c5a3fbf19617..15d4380006e3 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3168,13 +3168,13 @@ trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { unsigned int val = cpu_buffer->current_context; unsigned long pc = preempt_count(); - int bit; + int bit = 0; - if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) - bit = RB_CTX_NORMAL; - else - bit = pc & NMI_MASK ? RB_CTX_NMI : - pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ; + bit += !!(pc & (NMI_MASK)); + bit += !!(pc & (NMI_MASK | HARDIRQ_MASK)); + bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); + + bit = RB_CTX_NORMAL - bit; if (unlikely(val & (1 << (bit + cpu_buffer->nest)))) { /* -- cgit v1.2.3 From 91ebe8bcbff9d2ff21303e73bf7434f39a98b255 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 15 Oct 2021 15:01:19 -0400 Subject: tracing/perf: Add interrupt_context_level() helper Now that there are three different instances of doing the addition trick to the preempt_count() and NMI_MASK, HARDIRQ_MASK and SOFTIRQ_OFFSET macros, it deserves a helper function defined in the preempt.h header. Add the interrupt_context_level() helper and replace the three instances that do that logic with it. Link: https://lore.kernel.org/all/20211015142541.4badd8a9@gandalf.local.home/ Signed-off-by: Steven Rostedt (VMware) --- include/linux/preempt.h | 21 +++++++++++++++++++++ include/linux/trace_recursion.h | 7 +------ kernel/events/internal.h | 7 +------ kernel/trace/ring_buffer.c | 7 +------ 4 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 4d244e295e85..b32e3dabe28b 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -77,6 +77,27 @@ /* preempt_count() and related functions, depends on PREEMPT_NEED_RESCHED */ #include +/** + * interrupt_context_level - return interrupt context level + * + * Returns the current interrupt context level. + * 0 - normal context + * 1 - softirq context + * 2 - hardirq context + * 3 - NMI context + */ +static __always_inline unsigned char interrupt_context_level(void) +{ + unsigned long pc = preempt_count(); + unsigned char level = 0; + + level += !!(pc & (NMI_MASK)); + level += !!(pc & (NMI_MASK | HARDIRQ_MASK)); + level += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); + + return level; +} + #define nmi_count() (preempt_count() & NMI_MASK) #define hardirq_count() (preempt_count() & HARDIRQ_MASK) #ifdef CONFIG_PREEMPT_RT diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index f6da7a03bff0..1d8cce02c3fb 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -136,12 +136,7 @@ enum { static __always_inline int trace_get_context_bit(void) { - unsigned long pc = preempt_count(); - unsigned char bit = 0; - - bit += !!(pc & (NMI_MASK)); - bit += !!(pc & (NMI_MASK | HARDIRQ_MASK)); - bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); + unsigned char bit = interrupt_context_level(); return TRACE_CTX_NORMAL - bit; } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 228801e20788..082832738c8f 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -205,12 +205,7 @@ DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) static inline int get_recursion_context(int *recursion) { - unsigned int pc = preempt_count(); - unsigned char rctx = 0; - - rctx += !!(pc & (NMI_MASK)); - rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK)); - rctx += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); + unsigned char rctx = interrupt_context_level(); if (recursion[rctx]) return -1; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 15d4380006e3..f6520d0a4c8c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3167,12 +3167,7 @@ static __always_inline int trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer) { unsigned int val = cpu_buffer->current_context; - unsigned long pc = preempt_count(); - int bit = 0; - - bit += !!(pc & (NMI_MASK)); - bit += !!(pc & (NMI_MASK | HARDIRQ_MASK)); - bit += !!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)); + int bit = interrupt_context_level(); bit = RB_CTX_NORMAL - bit; -- cgit v1.2.3 From 15bf32398ad488c0df1cbaf16431422c87e4feea Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Tue, 12 Oct 2021 09:23:07 -0400 Subject: security: Return xattr name from security_dentry_init_security() Right now security_dentry_init_security() only supports single security label and is used by SELinux only. There are two users of this hook, namely ceph and nfs. NFS does not care about xattr name. Ceph hardcodes the xattr name to security.selinux (XATTR_NAME_SELINUX). I am making changes to fuse/virtiofs to send security label to virtiofsd and I need to send xattr name as well. I also hardcoded the name of xattr to security.selinux. Stephen Smalley suggested that it probably is a good idea to modify security_dentry_init_security() to also return name of xattr so that we can avoid this hardcoding in the callers. This patch adds a new parameter "const char **xattr_name" to security_dentry_init_security() and LSM puts the name of xattr too if caller asked for it (xattr_name != NULL). Signed-off-by: Vivek Goyal Reviewed-by: Jeff Layton Reviewed-by: Christian Brauner Acked-by: James Morris [PM: fixed typos in the commit description] Signed-off-by: Paul Moore --- fs/ceph/xattr.c | 3 +-- fs/nfs/nfs4proc.c | 3 ++- include/linux/lsm_hook_defs.h | 3 ++- include/linux/lsm_hooks.h | 3 +++ include/linux/security.h | 6 ++++-- security/security.c | 7 ++++--- security/selinux/hooks.c | 6 +++++- 7 files changed, 21 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index 159a1ffa4f4b..fcf7dfdecf96 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1311,7 +1311,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, int err; err = security_dentry_init_security(dentry, mode, &dentry->d_name, - &as_ctx->sec_ctx, + &name, &as_ctx->sec_ctx, &as_ctx->sec_ctxlen); if (err < 0) { WARN_ON_ONCE(err != -EOPNOTSUPP); @@ -1335,7 +1335,6 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode, * It only supports single security module and only selinux has * dentry_init_security hook. */ - name = XATTR_NAME_SELINUX; name_len = strlen(name); err = ceph_pagelist_reserve(pagelist, 4 * 2 + name_len + as_ctx->sec_ctxlen); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e1214bb6b7ee..459860aa8fd7 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -127,7 +127,8 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry, return NULL; err = security_dentry_init_security(dentry, sattr->ia_mode, - &dentry->d_name, (void **)&label->label, &label->len); + &dentry->d_name, NULL, + (void **)&label->label, &label->len); if (err == 0) return label; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 4c7ed0268ce3..a9ac70ae01ab 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -83,7 +83,8 @@ LSM_HOOK(int, 0, sb_add_mnt_opt, const char *option, const char *val, LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, - int mode, const struct qstr *name, void **ctx, u32 *ctxlen) + int mode, const struct qstr *name, const char **xattr_name, + void **ctx, u32 *ctxlen) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, struct cred *new) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 528554e9b90c..0bada4df23fc 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -196,6 +196,9 @@ * @dentry dentry to use in calculating the context. * @mode mode used to determine resource type. * @name name of the last path component used to create file + * @xattr_name pointer to place the pointer to security xattr name. + * Caller does not have to free the resulting pointer. Its + * a pointer to static string. * @ctx pointer to place the pointer to the resulting context in. * @ctxlen point to place the length of the resulting context. * @dentry_create_files_as: diff --git a/include/linux/security.h b/include/linux/security.h index cc6d39358336..7e0ba63b5dde 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -317,8 +317,9 @@ int security_add_mnt_opt(const char *option, const char *val, int len, void **mnt_opts); int security_move_mount(const struct path *from_path, const struct path *to_path); int security_dentry_init_security(struct dentry *dentry, int mode, - const struct qstr *name, void **ctx, - u32 *ctxlen); + const struct qstr *name, + const char **xattr_name, void **ctx, + u32 *ctxlen); int security_dentry_create_files_as(struct dentry *dentry, int mode, struct qstr *name, const struct cred *old, @@ -739,6 +740,7 @@ static inline void security_inode_free(struct inode *inode) static inline int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, + const char **xattr_name, void **ctx, u32 *ctxlen) { diff --git a/security/security.c b/security/security.c index d9d53c1e466a..95e30fadba78 100644 --- a/security/security.c +++ b/security/security.c @@ -1052,11 +1052,12 @@ void security_inode_free(struct inode *inode) } int security_dentry_init_security(struct dentry *dentry, int mode, - const struct qstr *name, void **ctx, - u32 *ctxlen) + const struct qstr *name, + const char **xattr_name, void **ctx, + u32 *ctxlen) { return call_int_hook(dentry_init_security, -EOPNOTSUPP, dentry, mode, - name, ctx, ctxlen); + name, xattr_name, ctx, ctxlen); } EXPORT_SYMBOL(security_dentry_init_security); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 6f08cd2fc6a8..1af2fbc08588 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2927,7 +2927,8 @@ static void selinux_inode_free_security(struct inode *inode) } static int selinux_dentry_init_security(struct dentry *dentry, int mode, - const struct qstr *name, void **ctx, + const struct qstr *name, + const char **xattr_name, void **ctx, u32 *ctxlen) { u32 newsid; @@ -2940,6 +2941,9 @@ static int selinux_dentry_init_security(struct dentry *dentry, int mode, if (rc) return rc; + if (xattr_name) + *xattr_name = XATTR_NAME_SELINUX; + return security_sid_to_context(&selinux_state, newsid, (char **)ctx, ctxlen); } -- cgit v1.2.3 From cf6d6238cdd319eca404756dee05bf55a748b6a9 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 19 Oct 2021 22:24:10 +0100 Subject: block: turn macro helpers into inline functions Replace bio_set_dev() with an identical inline helper and move it further to fix a dependency problem with bio_associate_blkg(). Do the same for bio_copy_dev(). Reviewed-by: Christoph Hellwig Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- include/linux/bio.h | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 9538f20ffaa5..b12453d7b8a8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -430,22 +430,6 @@ void zero_fill_bio(struct bio *bio); extern const char *bio_devname(struct bio *bio, char *buffer); -#define bio_set_dev(bio, bdev) \ -do { \ - bio_clear_flag(bio, BIO_REMAPPED); \ - if ((bio)->bi_bdev != (bdev)) \ - bio_clear_flag(bio, BIO_THROTTLED); \ - (bio)->bi_bdev = (bdev); \ - bio_associate_blkg(bio); \ -} while (0) - -#define bio_copy_dev(dst, src) \ -do { \ - bio_clear_flag(dst, BIO_REMAPPED); \ - (dst)->bi_bdev = (src)->bi_bdev; \ - bio_clone_blkg_association(dst, src); \ -} while (0) - #define bio_dev(bio) \ disk_devt((bio)->bi_bdev->bd_disk) @@ -463,6 +447,22 @@ static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ +static inline void bio_set_dev(struct bio *bio, struct block_device *bdev) +{ + bio_clear_flag(bio, BIO_REMAPPED); + if (bio->bi_bdev != bdev) + bio_clear_flag(bio, BIO_THROTTLED); + bio->bi_bdev = bdev; + bio_associate_blkg(bio); +} + +static inline void bio_copy_dev(struct bio *dst, struct bio *src) +{ + bio_clear_flag(dst, BIO_REMAPPED); + dst->bi_bdev = src->bi_bdev; + bio_clone_blkg_association(dst, src); +} + /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * -- cgit v1.2.3 From c809084ab033a8d4ee404e2ac3c5d3dc80cb65f7 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 19 Oct 2021 22:24:14 +0100 Subject: block: inline a part of bio_release_pages() Inline BIO_NO_PAGE_REF check of bio_release_pages() to avoid function call. Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- block/bio.c | 7 ++----- include/linux/bio.h | 8 +++++++- 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 4f397ba47db5..46a87c72d2b4 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1033,21 +1033,18 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); -void bio_release_pages(struct bio *bio, bool mark_dirty) +void __bio_release_pages(struct bio *bio, bool mark_dirty) { struct bvec_iter_all iter_all; struct bio_vec *bvec; - if (bio_flagged(bio, BIO_NO_PAGE_REF)) - return; - bio_for_each_segment_all(bvec, bio, iter_all) { if (mark_dirty && !PageCompound(bvec->bv_page)) set_page_dirty_lock(bvec->bv_page); put_page(bvec->bv_page); } } -EXPORT_SYMBOL_GPL(bio_release_pages); +EXPORT_SYMBOL_GPL(__bio_release_pages); static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) { diff --git a/include/linux/bio.h b/include/linux/bio.h index b12453d7b8a8..c88700d1bdc3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -417,7 +417,7 @@ int bio_add_zone_append_page(struct bio *bio, struct page *page, void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); -void bio_release_pages(struct bio *bio, bool mark_dirty); +void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); @@ -428,6 +428,12 @@ extern void bio_free_pages(struct bio *bio); void guard_bio_eod(struct bio *bio); void zero_fill_bio(struct bio *bio); +static inline void bio_release_pages(struct bio *bio, bool mark_dirty) +{ + if (!bio_flagged(bio, BIO_NO_PAGE_REF)) + __bio_release_pages(bio, mark_dirty); +} + extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_dev(bio) \ -- cgit v1.2.3 From dbb6f764a079d1dea883c6f2439d91db4f0fb2f2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Oct 2021 16:41:17 +0200 Subject: blk-mq: move blk_mq_flush_plug_list to block/blk-mq.h This helper is internal to the block layer. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211020144119.142582-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.h | 1 + include/linux/blk-mq.h | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.h b/block/blk-mq.h index d8ccb341e82e..08fb5922e611 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -122,6 +122,7 @@ extern int blk_mq_sysfs_register(struct request_queue *q); extern void blk_mq_sysfs_unregister(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_free_plug_rqs(struct blk_plug *plug); +void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); void blk_mq_release(struct request_queue *q); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 6cf35de151a9..e13780236550 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -656,8 +656,6 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set, unsigned int set_flags); void blk_mq_free_tag_set(struct blk_mq_tag_set *set); -void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); - void blk_mq_free_request(struct request *rq); bool blk_mq_queue_inflight(struct request_queue *q); -- cgit v1.2.3 From 008f75a20e7072d0840ec323c39b42206f3fa8a0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 20 Oct 2021 16:41:19 +0200 Subject: block: cleanup the flush plug helpers Consolidate the various helpers into a single blk_flush_plug helper that takes a plk_plug and the from_scheduler bool and switch all callsites to call it directly. Checks that the plug is non-NULL must be performed by the caller, something that most already do anyway. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211020144119.142582-5-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 13 ++++++------- fs/fs-writeback.c | 5 +++-- include/linux/blkdev.h | 29 ++++------------------------- kernel/sched/core.c | 5 +++-- 4 files changed, 16 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index db8b2fe0ceaf..dfa199312c2f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1089,7 +1089,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags) return 0; if (current->plug) - blk_flush_plug_list(current->plug, false); + blk_flush_plug(current->plug, false); if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT)) return 0; @@ -1637,7 +1637,7 @@ struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, } EXPORT_SYMBOL(blk_check_plugged); -void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) +void blk_flush_plug(struct blk_plug *plug, bool from_schedule) { if (!list_empty(&plug->cb_list)) flush_plug_callbacks(plug, from_schedule); @@ -1659,11 +1659,10 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) */ void blk_finish_plug(struct blk_plug *plug) { - if (plug != current->plug) - return; - blk_flush_plug_list(plug, false); - - current->plug = NULL; + if (plug == current->plug) { + blk_flush_plug(plug, false); + current->plug = NULL; + } } EXPORT_SYMBOL(blk_finish_plug); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 81ec192ce067..4124a89a1a5d 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1893,7 +1893,8 @@ static long writeback_sb_inodes(struct super_block *sb, * unplug, so get our IOs out the door before we * give up the CPU. */ - blk_flush_plug(current); + if (current->plug) + blk_flush_plug(current->plug, false); cond_resched(); } @@ -2291,7 +2292,7 @@ void wakeup_flusher_threads(enum wb_reason reason) * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) - blk_schedule_flush_plug(current); + blk_flush_plug(current->plug, true); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2b22fa36e568..c7b1e9355123 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -725,9 +725,8 @@ extern void blk_set_queue_dying(struct request_queue *); * as the lock contention for request_queue lock is reduced. * * It is ok not to disable preemption when adding the request to the plug list - * or when attempting a merge, because blk_schedule_flush_list() will only flush - * the plug list when the task sleeps by itself. For details, please see - * schedule() where blk_schedule_flush_plug() is called. + * or when attempting a merge. For details, please see schedule() where + * blk_flush_plug() is called. */ struct blk_plug { struct request *mq_list; /* blk-mq requests */ @@ -757,23 +756,8 @@ extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, extern void blk_start_plug(struct blk_plug *); extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short); extern void blk_finish_plug(struct blk_plug *); -extern void blk_flush_plug_list(struct blk_plug *, bool); -static inline void blk_flush_plug(struct task_struct *tsk) -{ - struct blk_plug *plug = tsk->plug; - - if (plug) - blk_flush_plug_list(plug, false); -} - -static inline void blk_schedule_flush_plug(struct task_struct *tsk) -{ - struct blk_plug *plug = tsk->plug; - - if (plug) - blk_flush_plug_list(plug, true); -} +void blk_flush_plug(struct blk_plug *plug, bool from_schedule); static inline bool blk_needs_flush_plug(struct task_struct *tsk) { @@ -802,15 +786,10 @@ static inline void blk_finish_plug(struct blk_plug *plug) { } -static inline void blk_flush_plug(struct task_struct *task) -{ -} - -static inline void blk_schedule_flush_plug(struct task_struct *task) +static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } - static inline bool blk_needs_flush_plug(struct task_struct *tsk) { return false; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 92ef7b68198c..34f37502c27e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6343,7 +6343,7 @@ static inline void sched_submit_work(struct task_struct *tsk) * make sure to submit it to avoid deadlocks. */ if (blk_needs_flush_plug(tsk)) - blk_schedule_flush_plug(tsk); + blk_flush_plug(tsk->plug, true); } static void sched_update_worker(struct task_struct *tsk) @@ -8354,7 +8354,8 @@ int io_schedule_prepare(void) int old_iowait = current->in_iowait; current->in_iowait = 1; - blk_schedule_flush_plug(current); + if (current->plug) + blk_flush_plug(current->plug, true); return old_iowait; } -- cgit v1.2.3 From 55df0933be74bd2e52aba0b67eb743ae0feabe7e Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Wed, 20 Oct 2021 14:09:00 +1100 Subject: workqueue: Introduce show_one_worker_pool and show_one_workqueue. Currently show_workqueue_state shows the state of all workqueues and of all worker pools. In certain cases we may need to dump state of only a specific workqueue or worker pool. For example in destroy_workqueue we only need to show state of the workqueue which is getting destroyed. So rename show_workqueue_state to show_all_workqueues(to signify it dumps state of all busy workqueues) and divide it into more granular functions (show_one_workqueue and show_one_worker_pool), that would show states of individual workqueues and worker pools and can be used in cases such as the one mentioned above. Also, as mentioned earlier, make destroy_workqueue dump data pertaining to only the workqueue that is being destroyed and make user(s) of earlier interface(show_workqueue_state), use new interface (show_all_workqueues). Signed-off-by: Imran Khan Signed-off-by: Tejun Heo --- drivers/tty/sysrq.c | 2 +- include/linux/workqueue.h | 3 +- kernel/power/process.c | 2 +- kernel/workqueue.c | 172 ++++++++++++++++++++++++++-------------------- 4 files changed, 100 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/sysrq.c b/drivers/tty/sysrq.c index c911196ac893..8d0f07509ca7 100644 --- a/drivers/tty/sysrq.c +++ b/drivers/tty/sysrq.c @@ -296,7 +296,7 @@ static const struct sysrq_key_op sysrq_showregs_op = { static void sysrq_handle_showstate(int key) { show_state(); - show_workqueue_state(); + show_all_workqueues(); } static const struct sysrq_key_op sysrq_showstate_op = { .handler = sysrq_handle_showstate, diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h index 74d3c1efd9bb..7fee9b6cfede 100644 --- a/include/linux/workqueue.h +++ b/include/linux/workqueue.h @@ -469,7 +469,8 @@ extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); -extern void show_workqueue_state(void); +extern void show_all_workqueues(void); +extern void show_one_workqueue(struct workqueue_struct *wq); extern void wq_worker_comm(char *buf, size_t size, struct task_struct *task); /** diff --git a/kernel/power/process.c b/kernel/power/process.c index 37401c99b7d7..b7e7798637b8 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -94,7 +94,7 @@ static int try_to_freeze_tasks(bool user_only) todo - wq_busy, wq_busy); if (wq_busy) - show_workqueue_state(); + show_all_workqueues(); if (!wakeup || pm_debug_messages_on) { read_lock(&tasklist_lock); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 76988f39ed5a..1a7df882f55e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -375,6 +375,7 @@ EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); +static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include @@ -4447,7 +4448,7 @@ void destroy_workqueue(struct workqueue_struct *wq) raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); - show_workqueue_state(); + show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); @@ -4797,97 +4798,116 @@ static void show_pwq(struct pool_workqueue *pwq) } /** - * show_workqueue_state - dump workqueue state - * - * Called from a sysrq handler or try_to_freeze_tasks() and prints out - * all busy workqueues and pools. + * show_one_workqueue - dump state of specified workqueue + * @wq: workqueue whose state will be printed */ -void show_workqueue_state(void) +void show_one_workqueue(struct workqueue_struct *wq) { - struct workqueue_struct *wq; - struct worker_pool *pool; + struct pool_workqueue *pwq; + bool idle = true; unsigned long flags; - int pi; - - rcu_read_lock(); - pr_info("Showing busy workqueues and worker pools:\n"); - - list_for_each_entry_rcu(wq, &workqueues, list) { - struct pool_workqueue *pwq; - bool idle = true; - - for_each_pwq(pwq, wq) { - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { - idle = false; - break; - } + for_each_pwq(pwq, wq) { + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { + idle = false; + break; } - if (idle) - continue; + } + if (idle) /* Nothing to print for idle workqueue */ + return; - pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); + pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); - for_each_pwq(pwq, wq) { - raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { - /* - * Defer printing to avoid deadlocks in console - * drivers that queue work while holding locks - * also taken in their write paths. - */ - printk_deferred_enter(); - show_pwq(pwq); - printk_deferred_exit(); - } - raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); + for_each_pwq(pwq, wq) { + raw_spin_lock_irqsave(&pwq->pool->lock, flags); + if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { /* - * We could be printing a lot from atomic context, e.g. - * sysrq-t -> show_workqueue_state(). Avoid triggering - * hard lockup. + * Defer printing to avoid deadlocks in console + * drivers that queue work while holding locks + * also taken in their write paths. */ - touch_nmi_watchdog(); - } - } - - for_each_pool(pool, pi) { - struct worker *worker; - bool first = true; - - raw_spin_lock_irqsave(&pool->lock, flags); - if (pool->nr_workers == pool->nr_idle) - goto next_pool; - /* - * Defer printing to avoid deadlocks in console drivers that - * queue work while holding locks also taken in their write - * paths. - */ - printk_deferred_enter(); - pr_info("pool %d:", pool->id); - pr_cont_pool_info(pool); - pr_cont(" hung=%us workers=%d", - jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000, - pool->nr_workers); - if (pool->manager) - pr_cont(" manager: %d", - task_pid_nr(pool->manager->task)); - list_for_each_entry(worker, &pool->idle_list, entry) { - pr_cont(" %s%d", first ? "idle: " : "", - task_pid_nr(worker->task)); - first = false; + printk_deferred_enter(); + show_pwq(pwq); + printk_deferred_exit(); } - pr_cont("\n"); - printk_deferred_exit(); - next_pool: - raw_spin_unlock_irqrestore(&pool->lock, flags); + raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); /* * We could be printing a lot from atomic context, e.g. - * sysrq-t -> show_workqueue_state(). Avoid triggering + * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } +} + +/** + * show_one_worker_pool - dump state of specified worker pool + * @pool: worker pool whose state will be printed + */ +static void show_one_worker_pool(struct worker_pool *pool) +{ + struct worker *worker; + bool first = true; + unsigned long flags; + + raw_spin_lock_irqsave(&pool->lock, flags); + if (pool->nr_workers == pool->nr_idle) + goto next_pool; + /* + * Defer printing to avoid deadlocks in console drivers that + * queue work while holding locks also taken in their write + * paths. + */ + printk_deferred_enter(); + pr_info("pool %d:", pool->id); + pr_cont_pool_info(pool); + pr_cont(" hung=%us workers=%d", + jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000, + pool->nr_workers); + if (pool->manager) + pr_cont(" manager: %d", + task_pid_nr(pool->manager->task)); + list_for_each_entry(worker, &pool->idle_list, entry) { + pr_cont(" %s%d", first ? "idle: " : "", + task_pid_nr(worker->task)); + first = false; + } + pr_cont("\n"); + printk_deferred_exit(); +next_pool: + raw_spin_unlock_irqrestore(&pool->lock, flags); + /* + * We could be printing a lot from atomic context, e.g. + * sysrq-t -> show_all_workqueues(). Avoid triggering + * hard lockup. + */ + touch_nmi_watchdog(); + +} + +/** + * show_all_workqueues - dump workqueue state + * + * Called from a sysrq handler or try_to_freeze_tasks() and prints out + * all busy workqueues and pools. + */ +void show_all_workqueues(void) +{ + struct workqueue_struct *wq; + struct worker_pool *pool; + int pi; + + rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + + list_for_each_entry_rcu(wq, &workqueues, list) + show_one_workqueue(wq); + + for_each_pool(pool, pi) + show_one_worker_pool(pool); + rcu_read_unlock(); } @@ -5876,7 +5896,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) rcu_read_unlock(); if (lockup_detected) - show_workqueue_state(); + show_all_workqueues(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); -- cgit v1.2.3 From f783484381ad088490a497abb4faab47511774c5 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:35 +0200 Subject: mfd: ti_am335x_tscadc: Use driver data So far every sub-cell parameter in this driver was hardcoded: cell name, cell compatible, specific clock name and desired clock frequency. As we are about to introduce support for ADC1/magnetic reader, we need a bit of flexibility. Let's add a driver data structure which will contain these information. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-18-miquel.raynal@bootlin.com --- drivers/mfd/ti_am335x_tscadc.c | 22 ++++++++++++++++------ include/linux/mfd/ti_am335x_tscadc.h | 9 +++++++++ 2 files changed, 25 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index ba821109e98b..69b0eff1a55e 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -137,6 +137,8 @@ static int ti_tscadc_probe(struct platform_device *pdev) return -EINVAL; } + tscadc->data = of_device_get_match_data(&pdev->dev); + node = of_get_child_by_name(pdev->dev.of_node, "tsc"); of_property_read_u32(node, "ti,wires", &tsc_wires); of_property_read_u32(node, "ti,coordiante-readouts", &readouts); @@ -212,7 +214,7 @@ static int ti_tscadc_probe(struct platform_device *pdev) goto err_disable_clk; } - tscadc->clk_div = (clk_get_rate(clk) / ADC_CLK) - 1; + tscadc->clk_div = (clk_get_rate(clk) / tscadc->data->target_clk_rate) - 1; regmap_write(tscadc->regmap, REG_CLKDIV, tscadc->clk_div); /* Set the control register bits */ @@ -241,8 +243,8 @@ static int ti_tscadc_probe(struct platform_device *pdev) if (tsc_wires > 0) { tscadc->tsc_cell = tscadc->used_cells; cell = &tscadc->cells[tscadc->used_cells++]; - cell->name = "TI-am335x-tsc"; - cell->of_compatible = "ti,am3359-tsc"; + cell->name = tscadc->data->secondary_feature_name; + cell->of_compatible = tscadc->data->secondary_feature_compatible; cell->platform_data = &tscadc; cell->pdata_size = sizeof(tscadc); } @@ -251,8 +253,8 @@ static int ti_tscadc_probe(struct platform_device *pdev) if (adc_channels > 0) { tscadc->adc_cell = tscadc->used_cells; cell = &tscadc->cells[tscadc->used_cells++]; - cell->name = "TI-am335x-adc"; - cell->of_compatible = "ti,am3359-adc"; + cell->name = tscadc->data->adc_feature_name; + cell->of_compatible = tscadc->data->adc_feature_compatible; cell->platform_data = &tscadc; cell->pdata_size = sizeof(tscadc); } @@ -338,8 +340,16 @@ static int __maybe_unused tscadc_resume(struct device *dev) static SIMPLE_DEV_PM_OPS(tscadc_pm_ops, tscadc_suspend, tscadc_resume); +static const struct ti_tscadc_data tscdata = { + .adc_feature_name = "TI-am335x-adc", + .adc_feature_compatible = "ti,am3359-adc", + .secondary_feature_name = "TI-am335x-tsc", + .secondary_feature_compatible = "ti,am3359-tsc", + .target_clk_rate = ADC_CLK, +}; + static const struct of_device_id ti_tscadc_dt_ids[] = { - { .compatible = "ti,am3359-tscadc", }, + { .compatible = "ti,am3359-tscadc", .data = &tscdata }, { } }; MODULE_DEVICE_TABLE(of, ti_tscadc_dt_ids); diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ffc091b77633..bb3b56ade3fb 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -162,11 +162,20 @@ #define TSCADC_CELLS 2 +struct ti_tscadc_data { + char *adc_feature_name; + char *adc_feature_compatible; + char *secondary_feature_name; + char *secondary_feature_compatible; + unsigned int target_clk_rate; +}; + struct ti_tscadc_dev { struct device *dev; struct regmap *regmap; void __iomem *tscadc_base; phys_addr_t tscadc_phys_base; + const struct ti_tscadc_data *data; int irq; int used_cells; /* 1-2 */ int tsc_wires; -- cgit v1.2.3 From 7c605802f33176d872ffb6a3830ba4d88d9f21f6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:37 +0200 Subject: mfd: ti_am335x_tscadc: Drop useless variables from the driver structure Keeping the count of tsc_cells and adc_cells is completely redundant, we can derive this information from other variables. Plus, these variables are not used anywhere else now. Let's get rid of them. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-20-miquel.raynal@bootlin.com --- drivers/mfd/ti_am335x_tscadc.c | 15 ++++----------- include/linux/mfd/ti_am335x_tscadc.h | 3 --- 2 files changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index d9c0b16d8d0d..9ce1a3e34c1e 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -122,7 +122,7 @@ static int ti_tscadc_probe(struct platform_device *pdev) const __be32 *cur; u32 val; int err, ctrl; - int tsc_wires = 0, adc_channels = 0, total_channels; + int tsc_wires = 0, adc_channels = 0, cell_idx = 0, total_channels; int readouts = 0; /* Allocate memory for device */ @@ -235,14 +235,9 @@ static int ti_tscadc_probe(struct platform_device *pdev) ctrl |= CNTRLREG_TSCSSENB; regmap_write(tscadc->regmap, REG_CTRL, ctrl); - tscadc->used_cells = 0; - tscadc->tsc_cell = -1; - tscadc->adc_cell = -1; - /* TSC Cell */ if (tsc_wires > 0) { - tscadc->tsc_cell = tscadc->used_cells; - cell = &tscadc->cells[tscadc->used_cells++]; + cell = &tscadc->cells[cell_idx++]; cell->name = tscadc->data->secondary_feature_name; cell->of_compatible = tscadc->data->secondary_feature_compatible; cell->platform_data = &tscadc; @@ -251,8 +246,7 @@ static int ti_tscadc_probe(struct platform_device *pdev) /* ADC Cell */ if (adc_channels > 0) { - tscadc->adc_cell = tscadc->used_cells; - cell = &tscadc->cells[tscadc->used_cells++]; + cell = &tscadc->cells[cell_idx++]; cell->name = tscadc->data->adc_feature_name; cell->of_compatible = tscadc->data->adc_feature_compatible; cell->platform_data = &tscadc; @@ -260,8 +254,7 @@ static int ti_tscadc_probe(struct platform_device *pdev) } err = mfd_add_devices(&pdev->dev, PLATFORM_DEVID_AUTO, - tscadc->cells, tscadc->used_cells, NULL, - 0, NULL); + tscadc->cells, cell_idx, NULL, 0, NULL); if (err < 0) goto err_disable_clk; diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index bb3b56ade3fb..23442059d271 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -177,10 +177,7 @@ struct ti_tscadc_dev { phys_addr_t tscadc_phys_base; const struct ti_tscadc_data *data; int irq; - int used_cells; /* 1-2 */ int tsc_wires; - int tsc_cell; /* -1 if not used */ - int adc_cell; /* -1 if not used */ struct mfd_cell cells[TSCADC_CELLS]; u32 reg_se_cache; bool adc_waiting; -- cgit v1.2.3 From b813f32030e2b70adf68f73e99853f91526aa3a1 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:40 +0200 Subject: mfd: ti_am335x_tscadc: Gather the ctrl register logic in one place Instead of deriving in the probe and in the resume path the value of the ctrl register, let's do it only once in the probe, save the value of this register (all but the subsystem enable bit) in the driver's structure and use it from the resume callback. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-23-miquel.raynal@bootlin.com --- drivers/mfd/ti_am335x_tscadc.c | 39 +++++++++++++----------------------- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 2 files changed, 15 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index 01c2b7d1c18c..df4f905a7b52 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -121,7 +121,7 @@ static int ti_tscadc_probe(struct platform_device *pdev) struct property *prop; const __be32 *cur; u32 val; - int err, ctrl; + int err; int tsc_wires = 0, adc_channels = 0, cell_idx = 0, total_channels; int readouts = 0; @@ -217,22 +217,25 @@ static int ti_tscadc_probe(struct platform_device *pdev) tscadc->clk_div = (clk_get_rate(clk) / tscadc->data->target_clk_rate) - 1; regmap_write(tscadc->regmap, REG_CLKDIV, tscadc->clk_div); - /* Set the control register bits */ - ctrl = CNTRLREG_STEPCONFIGWRT | CNTRLREG_STEPID; + /* + * Set the control register bits. tscadc->ctrl stores the configuration + * of the CTRL register but not the subsystem enable bit which must be + * added manually when timely. + */ + tscadc->ctrl = CNTRLREG_STEPCONFIGWRT | CNTRLREG_STEPID; if (tsc_wires > 0) { - tscadc->tsc_wires = tsc_wires; + tscadc->ctrl |= CNTRLREG_TSCENB; if (tsc_wires == 5) - ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB; + tscadc->ctrl |= CNTRLREG_5WIRE; else - ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB; + tscadc->ctrl |= CNTRLREG_4WIRE; } - regmap_write(tscadc->regmap, REG_CTRL, ctrl); + regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl); tscadc_idle_config(tscadc); /* Enable the TSC module enable bit */ - ctrl |= CNTRLREG_TSCSSENB; - regmap_write(tscadc->regmap, REG_CTRL, ctrl); + regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_TSCSSENB); /* TSC Cell */ if (tsc_wires > 0) { @@ -307,27 +310,13 @@ static int __maybe_unused tscadc_suspend(struct device *dev) static int __maybe_unused tscadc_resume(struct device *dev) { struct ti_tscadc_dev *tscadc = dev_get_drvdata(dev); - u32 ctrl; pm_runtime_get_sync(dev); - /* context restore */ regmap_write(tscadc->regmap, REG_CLKDIV, tscadc->clk_div); - - ctrl = CNTRLREG_STEPCONFIGWRT | CNTRLREG_STEPID; - if (tscadc->tsc_wires > 0) { - if (tscadc->tsc_wires == 5) - ctrl |= CNTRLREG_5WIRE | CNTRLREG_TSCENB; - else - ctrl |= CNTRLREG_4WIRE | CNTRLREG_TSCENB; - } - - regmap_write(tscadc->regmap, REG_CTRL, ctrl); - + regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl); tscadc_idle_config(tscadc); - - ctrl |= CNTRLREG_TSCSSENB; - regmap_write(tscadc->regmap, REG_CTRL, ctrl); + regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_TSCSSENB); return 0; } diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 23442059d271..c9c6f0b29181 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -177,8 +177,8 @@ struct ti_tscadc_dev { phys_addr_t tscadc_phys_base; const struct ti_tscadc_data *data; int irq; - int tsc_wires; struct mfd_cell cells[TSCADC_CELLS]; + u32 ctrl; u32 reg_se_cache; bool adc_waiting; bool adc_in_use; -- cgit v1.2.3 From 36782dab984a8b4ef8f4ec8c2270c56468cbbbeb Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:41 +0200 Subject: mfd: ti_am335x_tscadc: Replace the header license text with SPDX tag Drop the text license and replace it with an equivalent SPDX license tag identifier. Signed-off-by: Miquel Raynal Acked-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-24-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index c9c6f0b29181..2b8a5f58a3b6 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -1,21 +1,13 @@ -#ifndef __LINUX_TI_AM335X_TSCADC_MFD_H -#define __LINUX_TI_AM335X_TSCADC_MFD_H - +/* SPDX-License-Identifier: GPL-2.0-only */ /* * TI Touch Screen / ADC MFD driver * * Copyright (C) 2012 Texas Instruments Incorporated - https://www.ti.com/ - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any - * kind, whether express or implied; without even the implied warranty - * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ +#ifndef __LINUX_TI_AM335X_TSCADC_MFD_H +#define __LINUX_TI_AM335X_TSCADC_MFD_H + #include #define REG_RAWIRQSTATUS 0x024 -- cgit v1.2.3 From 3831abe135566813341cc36b1493d75f6ac460c3 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:42 +0200 Subject: mfd: ti_am335x_tscadc: Fix header spacing Harmonize the spacing within macro definitions. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-25-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 2b8a5f58a3b6..893c474c1f8c 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -41,7 +41,7 @@ /* Step Enable */ #define STEPENB_MASK (0x1FFFF << 0) #define STEPENB(val) ((val) << 0) -#define ENB(val) (1 << (val)) +#define ENB(val) (1 << (val)) #define STPENB_STEPENB STEPENB(0x1FFFF) #define STPENB_STEPENB_TC STEPENB(0x1FFF) @@ -122,15 +122,15 @@ #define CNTRLREG_TSCENB BIT(7) /* FIFO READ Register */ -#define FIFOREAD_DATA_MASK (0xfff << 0) -#define FIFOREAD_CHNLID_MASK (0xf << 16) +#define FIFOREAD_DATA_MASK (0xfff << 0) +#define FIFOREAD_CHNLID_MASK (0xf << 16) /* DMA ENABLE/CLEAR Register */ #define DMA_FIFO0 BIT(0) #define DMA_FIFO1 BIT(1) /* Sequencer Status */ -#define SEQ_STATUS BIT(5) +#define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 #define ADC_CLK 3000000 @@ -150,7 +150,7 @@ * * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 83 /* milliseconds */ +#define IDLE_TIMEOUT 83 /* milliseconds */ #define TSCADC_CELLS 2 -- cgit v1.2.3 From 48959fcdca8b335afa4485e71114008c81291bf9 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:43 +0200 Subject: mfd: ti_am335x_tscadc: Use the new HZ_PER_MHZ macro Before adding another frequency with even more zeroes, use the HZ_PER_MHZ macro to clarify the number. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-26-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 893c474c1f8c..a85643677bef 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -9,6 +9,7 @@ #define __LINUX_TI_AM335X_TSCADC_MFD_H #include +#include #define REG_RAWIRQSTATUS 0x024 #define REG_IRQSTATUS 0x028 @@ -133,7 +134,7 @@ #define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 -#define ADC_CLK 3000000 +#define ADC_CLK (3 * HZ_PER_MHZ) #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 #define FIFO1_THRESHOLD 19 -- cgit v1.2.3 From 65de5532a317b22f7fb93001cd0ed494145d3f4e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:44 +0200 Subject: mfd: ti_am335x_tscadc: Drop unused definitions from the header The STEP ENABLE definitions are highly unclear and not used so drop them. Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-27-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index a85643677bef..1cd8cd34f2b7 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -39,13 +39,6 @@ /* IRQ wakeup enable */ #define IRQWKUP_ENB BIT(0) -/* Step Enable */ -#define STEPENB_MASK (0x1FFFF << 0) -#define STEPENB(val) ((val) << 0) -#define ENB(val) (1 << (val)) -#define STPENB_STEPENB STEPENB(0x1FFFF) -#define STPENB_STEPENB_TC STEPENB(0x1FFF) - /* IRQ enable */ #define IRQENB_HW_PEN BIT(0) #define IRQENB_EOS BIT(1) -- cgit v1.2.3 From b7cb7bf11817129c623fa921a1d6cd86b3cb727b Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:45 +0200 Subject: mfd: ti_am335x_tscadc: Use BIT(), GENMASK() and FIELD_PREP() when relevant Clean the ti_am335x_tscadc.h header by: * converting masks to GENMASK() * converting regular shifts to BIT() * using FIELD_PREP() when relevant Sometimes reorder the lines to be able to use the relevant bitmask. Mind the s/%d/%ld/ change in a log due to the type change following the use of FIELD_PREP() in the header. Suggested-by: Jonathan Cameron Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-28-miquel.raynal@bootlin.com --- drivers/iio/adc/ti_am335x_adc.c | 2 +- include/linux/mfd/ti_am335x_tscadc.h | 61 ++++++++++++++++++------------------ 2 files changed, 32 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 855cc2d64ac8..3dec115e68ee 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -126,7 +126,7 @@ static void tiadc_step_config(struct iio_dev *indio_dev) chan = adc_dev->channel_line[i]; if (adc_dev->step_avg[i] > STEPCONFIG_AVG_16) { - dev_warn(dev, "chan %d step_avg truncating to %d\n", + dev_warn(dev, "chan %d step_avg truncating to %ld\n", chan, STEPCONFIG_AVG_16); adc_dev->step_avg[i] = STEPCONFIG_AVG_16; } diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 1cd8cd34f2b7..ae694fa2d711 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -8,6 +8,7 @@ #ifndef __LINUX_TI_AM335X_TSCADC_MFD_H #define __LINUX_TI_AM335X_TSCADC_MFD_H +#include #include #include @@ -51,12 +52,12 @@ #define IRQENB_PENUP BIT(9) /* Step Configuration */ -#define STEPCONFIG_MODE_MASK (3 << 0) -#define STEPCONFIG_MODE(val) ((val) << 0) +#define STEPCONFIG_MODE_MASK GENMASK(1, 0) +#define STEPCONFIG_MODE(val) FIELD_PREP(STEPCONFIG_MODE_MASK, (val)) #define STEPCONFIG_MODE_SWCNT STEPCONFIG_MODE(1) #define STEPCONFIG_MODE_HWSYNC STEPCONFIG_MODE(2) -#define STEPCONFIG_AVG_MASK (7 << 2) -#define STEPCONFIG_AVG(val) ((val) << 2) +#define STEPCONFIG_AVG_MASK GENMASK(4, 2) +#define STEPCONFIG_AVG(val) FIELD_PREP(STEPCONFIG_AVG_MASK, (val)) #define STEPCONFIG_AVG_16 STEPCONFIG_AVG(4) #define STEPCONFIG_XPP BIT(5) #define STEPCONFIG_XNN BIT(6) @@ -64,43 +65,43 @@ #define STEPCONFIG_YNN BIT(8) #define STEPCONFIG_XNP BIT(9) #define STEPCONFIG_YPN BIT(10) -#define STEPCONFIG_RFP(val) ((val) << 12) -#define STEPCONFIG_RFP_VREFP (0x3 << 12) -#define STEPCONFIG_INM_MASK (0xF << 15) -#define STEPCONFIG_INM(val) ((val) << 15) +#define STEPCONFIG_RFP_VREFP GENMASK(13, 12) +#define STEPCONFIG_RFP(val) FIELD_PREP(STEPCONFIG_RFP_VREFP, (val)) +#define STEPCONFIG_INM_MASK GENMASK(18, 15) +#define STEPCONFIG_INM(val) FIELD_PREP(STEPCONFIG_INM_MASK, (val)) #define STEPCONFIG_INM_ADCREFM STEPCONFIG_INM(8) -#define STEPCONFIG_INP_MASK (0xF << 19) -#define STEPCONFIG_INP(val) ((val) << 19) +#define STEPCONFIG_INP_MASK GENMASK(22, 19) +#define STEPCONFIG_INP(val) FIELD_PREP(STEPCONFIG_INP_MASK, (val)) #define STEPCONFIG_INP_AN4 STEPCONFIG_INP(4) #define STEPCONFIG_INP_ADCREFM STEPCONFIG_INP(8) #define STEPCONFIG_FIFO1 BIT(26) -#define STEPCONFIG_RFM(val) ((val) << 23) -#define STEPCONFIG_RFM_VREFN (0x3 << 23) +#define STEPCONFIG_RFM_VREFN GENMASK(24, 23) +#define STEPCONFIG_RFM(val) FIELD_PREP(STEPCONFIG_RFM_VREFN, (val)) /* Delay register */ -#define STEPDELAY_OPEN_MASK (0x3FFFF << 0) -#define STEPDELAY_OPEN(val) ((val) << 0) +#define STEPDELAY_OPEN_MASK GENMASK(17, 0) +#define STEPDELAY_OPEN(val) FIELD_PREP(STEPDELAY_OPEN_MASK, (val)) #define STEPCONFIG_OPENDLY STEPDELAY_OPEN(0x098) -#define STEPDELAY_SAMPLE_MASK (0xFF << 24) -#define STEPDELAY_SAMPLE(val) ((val) << 24) +#define STEPDELAY_SAMPLE_MASK GENMASK(31, 24) +#define STEPDELAY_SAMPLE(val) FIELD_PREP(STEPDELAY_SAMPLE_MASK, (val)) #define STEPCONFIG_SAMPLEDLY STEPDELAY_SAMPLE(0) /* Charge Config */ -#define STEPCHARGE_RFP_MASK (7 << 12) -#define STEPCHARGE_RFP(val) ((val) << 12) +#define STEPCHARGE_RFP_MASK GENMASK(14, 12) +#define STEPCHARGE_RFP(val) FIELD_PREP(STEPCHARGE_RFP_MASK, (val)) #define STEPCHARGE_RFP_XPUL STEPCHARGE_RFP(1) -#define STEPCHARGE_INM_MASK (0xF << 15) -#define STEPCHARGE_INM(val) ((val) << 15) +#define STEPCHARGE_INM_MASK GENMASK(18, 15) +#define STEPCHARGE_INM(val) FIELD_PREP(STEPCHARGE_INM_MASK, (val)) #define STEPCHARGE_INM_AN1 STEPCHARGE_INM(1) -#define STEPCHARGE_INP_MASK (0xF << 19) -#define STEPCHARGE_INP(val) ((val) << 19) -#define STEPCHARGE_RFM_MASK (3 << 23) -#define STEPCHARGE_RFM(val) ((val) << 23) +#define STEPCHARGE_INP_MASK GENMASK(22, 19) +#define STEPCHARGE_INP(val) FIELD_PREP(STEPCHARGE_INP_MASK, (val)) +#define STEPCHARGE_RFM_MASK GENMASK(24, 23) +#define STEPCHARGE_RFM(val) FIELD_PREP(STEPCHARGE_RFM_MASK, (val)) #define STEPCHARGE_RFM_XNUR STEPCHARGE_RFM(1) /* Charge delay */ -#define CHARGEDLY_OPEN_MASK (0x3FFFF << 0) -#define CHARGEDLY_OPEN(val) ((val) << 0) +#define CHARGEDLY_OPEN_MASK GENMASK(17, 0) +#define CHARGEDLY_OPEN(val) FIELD_PREP(CHARGEDLY_OPEN_MASK, (val)) #define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ @@ -108,16 +109,16 @@ #define CNTRLREG_STEPID BIT(1) #define CNTRLREG_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -#define CNTRLREG_AFE_CTRL_MASK (3 << 5) -#define CNTRLREG_AFE_CTRL(val) ((val) << 5) +#define CNTRLREG_AFE_CTRL_MASK GENMASK(6, 5) +#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(CNTRLREG_AFE_CTRL_MASK, (val)) #define CNTRLREG_4WIRE CNTRLREG_AFE_CTRL(1) #define CNTRLREG_5WIRE CNTRLREG_AFE_CTRL(2) #define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) #define CNTRLREG_TSCENB BIT(7) /* FIFO READ Register */ -#define FIFOREAD_DATA_MASK (0xfff << 0) -#define FIFOREAD_CHNLID_MASK (0xf << 16) +#define FIFOREAD_DATA_MASK GENMASK(11, 0) +#define FIFOREAD_CHNLID_MASK GENMASK(19, 16) /* DMA ENABLE/CLEAR Register */ #define DMA_FIFO0 BIT(0) -- cgit v1.2.3 From 01d838164b4c305c1cafb0c3f71fb0027d99358b Mon Sep 17 00:00:00 2001 From: Saurav Kashyap Date: Mon, 23 Aug 2021 05:56:48 -0700 Subject: nvme-fc: add support for ->map_queues NVMe FC don't have support for map queues, unlike the PCI, RDMA and TCP transports. Add a ->map_queues callout for the LLDDs to provide such functionality. Signed-off-by: Saurav Kashyap Signed-off-by: Nilesh Javali Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 24 ++++++++++++++++++++++++ include/linux/nvme-fc-driver.h | 7 +++++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index aa14ad963d91..34f7a7c236bf 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -16,6 +16,7 @@ #include #include "fc.h" #include +#include /* *************************** Data Structures/Defines ****************** */ @@ -2841,6 +2842,28 @@ nvme_fc_complete_rq(struct request *rq) nvme_fc_ctrl_put(ctrl); } +static int nvme_fc_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_fc_ctrl *ctrl = set->driver_data; + int i; + + for (i = 0; i < set->nr_maps; i++) { + struct blk_mq_queue_map *map = &set->map[i]; + + if (!map->nr_queues) { + WARN_ON(i == HCTX_TYPE_DEFAULT); + continue; + } + + /* Call LLDD map queue functionality if defined */ + if (ctrl->lport->ops->map_queues) + ctrl->lport->ops->map_queues(&ctrl->lport->localport, + map); + else + blk_mq_map_queues(map); + } + return 0; +} static const struct blk_mq_ops nvme_fc_mq_ops = { .queue_rq = nvme_fc_queue_rq, @@ -2849,6 +2872,7 @@ static const struct blk_mq_ops nvme_fc_mq_ops = { .exit_request = nvme_fc_exit_request, .init_hctx = nvme_fc_init_hctx, .timeout = nvme_fc_timeout, + .map_queues = nvme_fc_map_queues, }; static int diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 2a38f2b477a5..cb909edb76c4 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -7,6 +7,7 @@ #define _NVME_FC_DRIVER_H 1 #include +#include /* @@ -497,6 +498,8 @@ struct nvme_fc_port_template { int (*xmt_ls_rsp)(struct nvme_fc_local_port *localport, struct nvme_fc_remote_port *rport, struct nvmefc_ls_rsp *ls_rsp); + void (*map_queues)(struct nvme_fc_local_port *localport, + struct blk_mq_queue_map *map); u32 max_hw_queues; u16 max_sgl_segments; @@ -779,6 +782,10 @@ struct nvmet_fc_target_port { * LS received. * Entrypoint is Mandatory. * + * @map_queues: This functions lets the driver expose the queue mapping + * to the block layer. + * Entrypoint is Optional. + * * @fcp_op: Called to perform a data transfer or transmit a response. * The nvmefc_tgt_fcp_req structure is the same LLDD-supplied * exchange structure specified in the nvmet_fc_rcv_fcp_req() call -- cgit v1.2.3 From 44c3c6257e99c6284f312206de73783575fc8906 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 23 Sep 2021 00:55:35 +0300 Subject: nvme-rdma: limit the maximal queue size for RDMA controllers Corrent limit of 1024 isn't valid for some of the RDMA based ctrls. In case the target expose a cap of larger amount of entries (e.g. 1024), the initiator may fail to create a QP with this size. Thus limit to a value that works for all RDMA adapters. Future general solution should use RDMA/core API to calculate this size according to device capabilities and number of WRs needed per NVMe IO request. Signed-off-by: Max Gurtovoy Signed-off-by: Christoph Hellwig --- drivers/nvme/host/rdma.c | 7 +++++++ include/linux/nvme-rdma.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 1624da3702d4..027ee57cbdb0 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1112,6 +1112,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1); } + if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) { + dev_warn(ctrl->ctrl.device, + "ctrl sqsize %u > max queue size %u, clamping down\n", + ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE); + ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1; + } + if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) { dev_warn(ctrl->ctrl.device, "sqsize %u > ctrl maxcmd %u, clamping down\n", diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index 3ec8e50efa16..4dd7e6fe92fb 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -6,6 +6,8 @@ #ifndef _LINUX_NVME_RDMA_H #define _LINUX_NVME_RDMA_H +#define NVME_RDMA_MAX_QUEUE_SIZE 128 + enum nvme_rdma_cm_fmt { NVME_RDMA_CM_FMT_1_0 = 0x0, }; -- cgit v1.2.3 From e15a8a9755659ff5972f30de4dd64867c97f242d Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 22 Sep 2021 08:35:20 +0200 Subject: nvme: add CNTRLTYPE definitions for 'identify controller' Update the 'identify controller' structure to define the newly added CNTRLTYPE field. Signed-off-by: Hannes Reinecke Reviewed-by: Chaitanya Kulkarni Reviewed-by: Himanshu Madhani Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b7c4c4130b65..ed2428918bca 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -31,6 +31,12 @@ enum nvme_subsys_type { NVME_NQN_NVME = 2, /* NVME type target subsystem */ }; +enum nvme_ctrl_type { + NVME_CTRL_IO = 1, /* I/O controller */ + NVME_CTRL_DISC = 2, /* Discovery controller */ + NVME_CTRL_ADMIN = 3, /* Administrative controller */ +}; + /* Address Family codes for Discovery Log Page entry ADRFAM field */ enum { NVMF_ADDR_FAMILY_PCI = 0, /* PCIe */ @@ -244,7 +250,9 @@ struct nvme_id_ctrl { __le32 rtd3e; __le32 oaes; __le32 ctratt; - __u8 rsvd100[28]; + __u8 rsvd100[11]; + __u8 cntrltype; + __u8 fguid[16]; __le16 crdt1; __le16 crdt2; __le16 crdt3; -- cgit v1.2.3 From d56ae18f063e38eba47550c632519c9fe3f76b19 Mon Sep 17 00:00:00 2001 From: Max Gurtovoy Date: Thu, 23 Sep 2021 13:17:44 +0300 Subject: nvmet: use macro definitions for setting cmic value This makes the code more readable. Signed-off-by: Max Gurtovoy Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- drivers/nvme/target/admin-cmd.c | 3 ++- include/linux/nvme.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index dce53030b375..6e75890bc8d9 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -385,7 +385,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) */ /* we support multiple ports, multiples hosts and ANA: */ - id->cmic = (1 << 0) | (1 << 1) | (1 << 3); + id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL | + NVME_CTRL_CMIC_ANA; /* Limit MDTS according to transport capability */ if (ctrl->ops->get_mdts) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index ed2428918bca..357482dedb59 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -320,6 +320,7 @@ struct nvme_id_ctrl { }; enum { + NVME_CTRL_CMIC_MULTI_PORT = 1 << 0, NVME_CTRL_CMIC_MULTI_CTRL = 1 << 1, NVME_CTRL_CMIC_ANA = 1 << 3, NVME_CTRL_ONCS_COMPARE = 1 << 0, -- cgit v1.2.3 From cdd591fc86e38ad3899196066219fbbd845f3162 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 5 Jul 2021 17:26:28 +0200 Subject: iov_iter: Introduce fault_in_iov_iter_writeable Introduce a new fault_in_iov_iter_writeable helper for safely faulting in an iterator for writing. Uses get_user_pages() to fault in the pages without actually writing to them, which would be destructive. We'll use fault_in_iov_iter_writeable in gfs2 once we've determined that the iterator passed to .read_iter isn't in memory. Signed-off-by: Andreas Gruenbacher --- include/linux/pagemap.h | 1 + include/linux/uio.h | 1 + lib/iov_iter.c | 39 ++++++++++++++++++++++++++++++ mm/gup.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 104 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9fe94f7a4f7e..2f7dd14083d9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -736,6 +736,7 @@ extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter); * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); +size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); int add_to_page_cache_locked(struct page *page, struct address_space *mapping, diff --git a/include/linux/uio.h b/include/linux/uio.h index d18458af6681..25d1c24fd829 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -134,6 +134,7 @@ size_t copy_page_from_iter_atomic(struct page *page, unsigned offset, void iov_iter_advance(struct iov_iter *i, size_t bytes); void iov_iter_revert(struct iov_iter *i, size_t bytes); size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes); +size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(const struct iov_iter *i); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index ce3d4f610626..ac9a87e727a3 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -467,6 +467,45 @@ size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t size) } EXPORT_SYMBOL(fault_in_iov_iter_readable); +/* + * fault_in_iov_iter_writeable - fault in iov iterator for writing + * @i: iterator + * @size: maximum length + * + * Faults in the iterator using get_user_pages(), i.e., without triggering + * hardware page faults. This is primarily useful when we already know that + * some or all of the pages in @i aren't in memory. + * + * Returns the number of bytes not faulted in, like copy_to_user() and + * copy_from_user(). + * + * Always returns 0 for non-user-space iterators. + */ +size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size) +{ + if (iter_is_iovec(i)) { + size_t count = min(size, iov_iter_count(i)); + const struct iovec *p; + size_t skip; + + size -= count; + for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) { + size_t len = min(count, p->iov_len - skip); + size_t ret; + + if (unlikely(!len)) + continue; + ret = fault_in_safe_writeable(p->iov_base + skip, len); + count -= len - ret; + if (ret) + break; + } + return count + size; + } + return 0; +} +EXPORT_SYMBOL(fault_in_iov_iter_writeable); + void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) diff --git a/mm/gup.c b/mm/gup.c index a7efb027d6cf..795f15c410cc 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1691,6 +1691,69 @@ out: } EXPORT_SYMBOL(fault_in_writeable); +/* + * fault_in_safe_writeable - fault in an address range for writing + * @uaddr: start of address range + * @size: length of address range + * + * Faults in an address range using get_user_pages, i.e., without triggering + * hardware page faults. This is primarily useful when we already know that + * some or all of the pages in the address range aren't in memory. + * + * Other than fault_in_writeable(), this function is non-destructive. + * + * Note that we don't pin or otherwise hold the pages referenced that we fault + * in. There's no guarantee that they'll stay in memory for any duration of + * time. + * + * Returns the number of bytes not faulted in, like copy_to_user() and + * copy_from_user(). + */ +size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) +{ + unsigned long start = (unsigned long)untagged_addr(uaddr); + unsigned long end, nstart, nend; + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma = NULL; + int locked = 0; + + nstart = start & PAGE_MASK; + end = PAGE_ALIGN(start + size); + if (end < nstart) + end = 0; + for (; nstart != end; nstart = nend) { + unsigned long nr_pages; + long ret; + + if (!locked) { + locked = 1; + mmap_read_lock(mm); + vma = find_vma(mm, nstart); + } else if (nstart >= vma->vm_end) + vma = vma->vm_next; + if (!vma || vma->vm_start >= end) + break; + nend = end ? min(end, vma->vm_end) : vma->vm_end; + if (vma->vm_flags & (VM_IO | VM_PFNMAP)) + continue; + if (nstart < vma->vm_start) + nstart = vma->vm_start; + nr_pages = (nend - nstart) / PAGE_SIZE; + ret = __get_user_pages_locked(mm, nstart, nr_pages, + NULL, NULL, &locked, + FOLL_TOUCH | FOLL_WRITE); + if (ret <= 0) + break; + nend = nstart + ret * PAGE_SIZE; + } + if (locked) + mmap_read_unlock(mm); + if (nstart == end) + return 0; + return size - min_t(size_t, nstart - start, size); +} +EXPORT_SYMBOL(fault_in_safe_writeable); + /** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range -- cgit v1.2.3 From a164ff53cbd34479aeac3366840669b10845ce53 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 14 Oct 2021 16:47:54 +0300 Subject: driver core: Provide device_match_acpi_handle() helper We have a couple of users of this helper, make it available for them. The prototype for the helper is specifically crafted in order to be easily used with bus_find_device() call. That's why its location is in the driver core rather than ACPI. Reviewed-by: Rafael J. Wysocki Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211014134756.39092-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 6 ++++++ include/linux/device/bus.h | 1 + 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index b67ebe6a323c..fd034d742447 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -4838,6 +4838,12 @@ int device_match_acpi_dev(struct device *dev, const void *adev) } EXPORT_SYMBOL(device_match_acpi_dev); +int device_match_acpi_handle(struct device *dev, const void *handle) +{ + return ACPI_HANDLE(dev) == handle; +} +EXPORT_SYMBOL(device_match_acpi_handle); + int device_match_any(struct device *dev, const void *unused) { return 1; diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h index 062777a45a74..a039ab809753 100644 --- a/include/linux/device/bus.h +++ b/include/linux/device/bus.h @@ -143,6 +143,7 @@ int device_match_of_node(struct device *dev, const void *np); int device_match_fwnode(struct device *dev, const void *fwnode); int device_match_devt(struct device *dev, const void *pdevt); int device_match_acpi_dev(struct device *dev, const void *adev); +int device_match_acpi_handle(struct device *dev, const void *handle); int device_match_any(struct device *dev, const void *unused); /* iterator helpers for buses */ -- cgit v1.2.3 From f1985002839af80d6c84e9537834a81fb1364d6e Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 20 Oct 2021 09:33:21 +0100 Subject: irqchip: Provide stronger type checking for IRQCHIP_MATCH/IRQCHIP_DECLARE Both IRQCHIP_DECLARE() and IRQCHIP_MATCH() use an underlying of_device_id() structure to encode the matching property and the init callback. However, this callback is stored in as a void * pointer, which obviously defeat any attempt at stronger type checking. Work around this by providing a new macro that builds on top of the __typecheck() primitive, and that can be used to warn when there is a discrepency between the drivers and core code. Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211020104527.3066268-1-maz@kernel.org --- include/linux/irqchip.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 67351aac65ef..5de0dfc5d64d 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -14,8 +14,15 @@ #include #include #include +#include #include +/* Undefined on purpose */ +extern of_irq_init_cb_t typecheck_irq_init_cb; + +#define typecheck_irq_init_cb(fn) \ + (__typecheck(typecheck_irq_init_cb, &fn) ? fn : fn) + /* * This macro must be used by the different irqchip drivers to declare * the association between their DT compatible string and their @@ -26,14 +33,16 @@ * @compstr: compatible string of the irqchip driver * @fn: initialization function */ -#define IRQCHIP_DECLARE(name, compat, fn) OF_DECLARE_2(irqchip, name, compat, fn) +#define IRQCHIP_DECLARE(name, compat, fn) \ + OF_DECLARE_2(irqchip, name, compat, typecheck_irq_init_cb(fn)) extern int platform_irqchip_probe(struct platform_device *pdev); #define IRQCHIP_PLATFORM_DRIVER_BEGIN(drv_name) \ static const struct of_device_id drv_name##_irqchip_match_table[] = { -#define IRQCHIP_MATCH(compat, fn) { .compatible = compat, .data = fn }, +#define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ + .data = typecheck_irq_init_cb(fn), }, #define IRQCHIP_PLATFORM_DRIVER_END(drv_name) \ {}, \ -- cgit v1.2.3 From 795e92ec5fd79027648bd7f779d34bad5b6f2f55 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 6 Oct 2021 11:43:21 -0500 Subject: of: Add of_get_cpu_hwid() to read hardware ID from CPU nodes There are various open coded implementions parsing the CPU node 'reg' property which contains the CPU's hardware ID. Introduce a new function, of_get_cpu_hwid(), to read the hardware ID. All the callers should be DT only code, so no need for an empty function. Cc: Frank Rowand Signed-off-by: Rob Herring Tested-by: Florian Fainelli Reviewed-by: Sudeep Holla Link: https://lore.kernel.org/r/20211006164332.1981454-2-robh@kernel.org --- drivers/of/base.c | 22 ++++++++++++++++++++++ include/linux/of.h | 1 + 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index f720c0d246f2..e587ab44be22 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -286,6 +286,28 @@ const void *of_get_property(const struct device_node *np, const char *name, } EXPORT_SYMBOL(of_get_property); +/** + * of_get_cpu_hwid - Get the hardware ID from a CPU device node + * + * @cpun: CPU number(logical index) for which device node is required + * @thread: The local thread number to get the hardware ID for. + * + * Return: The hardware ID for the CPU node or ~0ULL if not found. + */ +u64 of_get_cpu_hwid(struct device_node *cpun, unsigned int thread) +{ + const __be32 *cell; + int ac, len; + + ac = of_n_addr_cells(cpun); + cell = of_get_property(cpun, "reg", &len); + if (!cell || !ac || ((sizeof(*cell) * ac * (thread + 1)) > len)) + return ~0ULL; + + cell += ac * thread; + return of_read_number(cell, ac); +} + /* * arch_match_cpu_phys_id - Match the given logical CPU and physical id * diff --git a/include/linux/of.h b/include/linux/of.h index 6f1c41f109bb..807f8168dad9 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -353,6 +353,7 @@ extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); extern struct device_node *of_get_next_cpu_node(struct device_node *prev); extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node, int index); +extern u64 of_get_cpu_hwid(struct device_node *cpun, unsigned int thread); #define for_each_property_of_node(dn, pp) \ for (pp = dn->properties; pp != NULL; pp = pp->next) -- cgit v1.2.3 From a3c85b2ee098c4a293148fab4eb96299e92b9524 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Thu, 14 Oct 2021 12:30:55 -0500 Subject: of: make of_node_check_flag() device_node parameter const The device_node argument isn't modified by of_node_check_flag(), so mark it const. Signed-off-by: Nathan Lynch Link: https://lore.kernel.org/r/20211014173055.2117872-1-nathanl@linux.ibm.com Signed-off-by: Rob Herring --- include/linux/of.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 807f8168dad9..ff143a027abc 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -185,7 +185,7 @@ static inline bool of_node_is_root(const struct device_node *node) return node && (node->parent == NULL); } -static inline int of_node_check_flag(struct device_node *n, unsigned long flag) +static inline int of_node_check_flag(const struct device_node *n, unsigned long flag) { return test_bit(flag, &n->_flags); } -- cgit v1.2.3 From b8419e7be6c6029eee3448fda45f4f9ad340c4ca Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 20 Oct 2021 11:48:59 -0700 Subject: irqchip: Fix kernel-doc parameter typo for IRQCHIP_DECLARE The documentation refers to "compstr" when we have the parameter named "compat", fix the typo. Signed-off-by: Florian Fainelli Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211020184859.2705451-14-f.fainelli@gmail.com --- include/linux/irqchip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 5de0dfc5d64d..7f007b9c23f8 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -30,7 +30,7 @@ extern of_irq_init_cb_t typecheck_irq_init_cb; * * @name: name that must be unique across all IRQCHIP_DECLARE of the * same file. - * @compstr: compatible string of the irqchip driver + * @compat: compatible string of the irqchip driver * @fn: initialization function */ #define IRQCHIP_DECLARE(name, compat, fn) \ -- cgit v1.2.3 From 133a48abf6ecc535d7eddc6da1c3e4c972445882 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 4 Oct 2021 15:37:42 -0400 Subject: NFS: Fix up commit deadlocks If O_DIRECT bumps the commit_info rpcs_out field, then that could lead to fsync() hangs. The fix is to ensure that O_DIRECT calls nfs_commit_end(). Fixes: 723c921e7dfc ("sched/wait, fs/nfs: Convert wait_on_atomic_t() usage to the new wait_var_event() API") Signed-off-by: Trond Myklebust --- fs/nfs/direct.c | 2 +- fs/nfs/pnfs_nfs.c | 2 -- fs/nfs/write.c | 9 ++++++--- include/linux/nfs_fs.h | 1 + 4 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 2e894fec036b..3c0335c15a73 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -620,7 +620,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data) nfs_unlock_and_release_request(req); } - if (atomic_dec_and_test(&cinfo.mds->rpcs_out)) + if (nfs_commit_end(cinfo.mds)) nfs_direct_write_complete(dreq); } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 02bd6e83961d..316f68f96e57 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -468,7 +468,6 @@ pnfs_bucket_alloc_ds_commits(struct list_head *list, goto out_error; data->ds_commit_index = i; list_add_tail(&data->list, list); - atomic_inc(&cinfo->mds->rpcs_out); nreq++; } mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); @@ -520,7 +519,6 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, data->ds_commit_index = -1; list_splice_init(mds_pages, &data->pages); list_add_tail(&data->list, &list); - atomic_inc(&cinfo->mds->rpcs_out); nreq++; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 38f181e1343a..465220f47142 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1673,10 +1673,13 @@ static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) atomic_inc(&cinfo->rpcs_out); } -static void nfs_commit_end(struct nfs_mds_commit_info *cinfo) +bool nfs_commit_end(struct nfs_mds_commit_info *cinfo) { - if (atomic_dec_and_test(&cinfo->rpcs_out)) + if (atomic_dec_and_test(&cinfo->rpcs_out)) { wake_up_var(&cinfo->rpcs_out); + return true; + } + return false; } void nfs_commitdata_release(struct nfs_commit_data *data) @@ -1776,6 +1779,7 @@ void nfs_init_commit(struct nfs_commit_data *data, data->res.fattr = &data->fattr; data->res.verf = &data->verf; nfs_fattr_init(&data->fattr); + nfs_commit_begin(cinfo->mds); } EXPORT_SYMBOL_GPL(nfs_init_commit); @@ -1822,7 +1826,6 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, /* Set up the argument struct */ nfs_init_commit(data, head, NULL, cinfo); - atomic_inc(&cinfo->mds->rpcs_out); if (NFS_SERVER(inode)->nfs_client->cl_minorversion) task_flags = RPC_TASK_MOVEABLE; return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index ca547cc5458c..e58b78da7a98 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -568,6 +568,7 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page); extern int nfs_commit_inode(struct inode *, int); extern struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail); extern void nfs_commit_free(struct nfs_commit_data *data); +bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int nfs_have_writebacks(struct inode *inode) -- cgit v1.2.3 From 0ebeebcf59601bcfa0284f4bb7abdec051eb856d Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Sun, 10 Oct 2021 18:23:13 -0400 Subject: NFS: Fix WARN_ON due to unionization of nfs_inode.nrequests Fixes the following WARN_ON WARNING: CPU: 2 PID: 18678 at fs/nfs/inode.c:123 nfs_clear_inode+0x3b/0x50 [nfs] ... Call Trace: nfs4_evict_inode+0x57/0x70 [nfsv4] evict+0xd1/0x180 dispose_list+0x48/0x60 evict_inodes+0x156/0x190 generic_shutdown_super+0x37/0x110 nfs_kill_super+0x1d/0x40 [nfs] deactivate_locked_super+0x36/0xa0 Signed-off-by: Dave Wysochanski Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index e58b78da7a98..457b866a2d9e 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -573,7 +573,9 @@ bool nfs_commit_end(struct nfs_mds_commit_info *cinfo); static inline int nfs_have_writebacks(struct inode *inode) { - return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + if (S_ISREG(inode->i_mode)) + return atomic_long_read(&NFS_I(inode)->nrequests) != 0; + return 0; } /* -- cgit v1.2.3 From e591b298d7ecb851e200f65946e3d53fe78a3c4f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 28 Sep 2021 17:41:41 -0400 Subject: NFS: Save some space in the inode Save some space in the nfs_inode by setting up an anonymous union with the fields that are peculiar to a specific type of filesystem object. Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 26 ++++++++++++++++++-------- include/linux/nfs_fs.h | 42 ++++++++++++++++++++++++------------------ 2 files changed, 42 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index a10572f278e6..b81b2d2f47ad 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -431,6 +431,22 @@ nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh) return inode; } +static void nfs_inode_init_regular(struct nfs_inode *nfsi) +{ + atomic_long_set(&nfsi->nrequests, 0); + INIT_LIST_HEAD(&nfsi->commit_info.list); + atomic_long_set(&nfsi->commit_info.ncommit, 0); + atomic_set(&nfsi->commit_info.rpcs_out, 0); + mutex_init(&nfsi->commit_mutex); +} + +static void nfs_inode_init_dir(struct nfs_inode *nfsi) +{ + nfsi->cache_change_attribute = 0; + memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + init_rwsem(&nfsi->rmdir_sem); +} + /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. @@ -485,10 +501,12 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st if (S_ISREG(inode->i_mode)) { inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops; inode->i_data.a_ops = &nfs_file_aops; + nfs_inode_init_regular(nfsi); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; inode->i_data.a_ops = &nfs_dir_aops; + nfs_inode_init_dir(nfsi); /* Deal with crossing mountpoints */ if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT || fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { @@ -514,7 +532,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st inode->i_uid = make_kuid(&init_user_ns, -2); inode->i_gid = make_kgid(&init_user_ns, -2); inode->i_blocks = 0; - memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); nfsi->write_io = 0; nfsi->read_io = 0; @@ -2259,14 +2276,7 @@ static void init_once(void *foo) INIT_LIST_HEAD(&nfsi->open_files); INIT_LIST_HEAD(&nfsi->access_cache_entry_lru); INIT_LIST_HEAD(&nfsi->access_cache_inode_lru); - INIT_LIST_HEAD(&nfsi->commit_info.list); - atomic_long_set(&nfsi->nrequests, 0); - atomic_long_set(&nfsi->commit_info.ncommit, 0); - atomic_set(&nfsi->commit_info.rpcs_out, 0); - init_rwsem(&nfsi->rmdir_sem); - mutex_init(&nfsi->commit_mutex); nfs4_init_once(nfsi); - nfsi->cache_change_attribute = 0; } static int __init nfs_init_inodecache(void) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 457b866a2d9e..739ca1ef934f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -155,33 +155,39 @@ struct nfs_inode { unsigned long attrtimeo_timestamp; unsigned long attr_gencount; - /* "Generation counter" for the attribute cache. This is - * bumped whenever we update the metadata on the - * server. - */ - unsigned long cache_change_attribute; struct rb_root access_cache; struct list_head access_cache_entry_lru; struct list_head access_cache_inode_lru; - /* - * This is the cookie verifier used for NFSv3 readdir - * operations - */ - __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; - - atomic_long_t nrequests; - struct nfs_mds_commit_info commit_info; + union { + /* Directory */ + struct { + /* "Generation counter" for the attribute cache. + * This is bumped whenever we update the metadata + * on the server. + */ + unsigned long cache_change_attribute; + /* + * This is the cookie verifier used for NFSv3 readdir + * operations + */ + __be32 cookieverf[NFS_DIR_VERIFIER_SIZE]; + /* Readers: in-flight sillydelete RPC calls */ + /* Writers: rmdir */ + struct rw_semaphore rmdir_sem; + }; + /* Regular file */ + struct { + atomic_long_t nrequests; + struct nfs_mds_commit_info commit_info; + struct mutex commit_mutex; + }; + }; /* Open contexts for shared mmap writes */ struct list_head open_files; - /* Readers: in-flight sillydelete RPC calls */ - /* Writers: rmdir */ - struct rw_semaphore rmdir_sem; - struct mutex commit_mutex; - #if IS_ENABLED(CONFIG_NFS_V4) struct nfs4_cached_acl *nfs4_acl; /* NFSv4 state */ -- cgit v1.2.3 From 0c0593b45c9b4e5b212ffb3fb28bb8d3c0ec0dc8 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Fri, 8 Oct 2021 11:13:31 +0200 Subject: x86/ftrace: Make function graph use ftrace directly We don't need special hook for graph tracer entry point, but instead we can use graph_ops::func function to install the return_hooker. This moves the graph tracing setup _before_ the direct trampoline prepares the stack, so the return_hooker will be called when the direct trampoline is finished. This simplifies the code, because we don't need to take into account the direct trampoline setup when preparing the graph tracer hooker and we can allow function graph tracer on entries registered with direct trampoline. Link: https://lkml.kernel.org/r/20211008091336.33616-4-jolsa@kernel.org [fixed compile error reported by kernel test robot ] Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- arch/x86/include/asm/ftrace.h | 9 +++++++-- arch/x86/kernel/ftrace.c | 37 ++++++++++++++++++++++++++++++++++--- arch/x86/kernel/ftrace_64.S | 29 +---------------------------- include/linux/ftrace.h | 9 +++++++++ kernel/trace/fgraph.c | 6 ++++-- 5 files changed, 55 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 9f3130f40807..024d9797646e 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -57,6 +57,13 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) #define ftrace_instruction_pointer_set(fregs, _ip) \ do { (fregs)->regs.ip = (_ip); } while (0) + +struct ftrace_ops; +#define ftrace_graph_func ftrace_graph_func +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#else +#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif #ifdef CONFIG_DYNAMIC_FTRACE @@ -65,8 +72,6 @@ struct dyn_arch_ftrace { /* No extra data needed for x86 */ }; -#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR - #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* __ASSEMBLY__ */ #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 7f12eacdf1ae..c39f906cdc4e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -522,7 +522,7 @@ static void *addr_from_call(void *ptr) return ptr + CALL_INSN_SIZE + call.disp; } -void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, unsigned long frame_pointer); /* @@ -536,7 +536,8 @@ static void *static_tramp_func(struct ftrace_ops *ops, struct dyn_ftrace *rec) void *ptr; if (ops && ops->trampoline) { -#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) && \ + defined(CONFIG_FUNCTION_GRAPH_TRACER) /* * We only know about function graph tracer setting as static * trampoline. @@ -584,8 +585,9 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops) #ifdef CONFIG_FUNCTION_GRAPH_TRACER #ifdef CONFIG_DYNAMIC_FTRACE -extern void ftrace_graph_call(void); +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +extern void ftrace_graph_call(void); static const char *ftrace_jmp_replace(unsigned long ip, unsigned long addr) { return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr); @@ -613,7 +615,17 @@ int ftrace_disable_ftrace_graph_caller(void) return ftrace_mod_jmp(ip, &ftrace_stub); } +#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ +int ftrace_enable_ftrace_graph_caller(void) +{ + return 0; +} +int ftrace_disable_ftrace_graph_caller(void) +{ + return 0; +} +#endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* !CONFIG_DYNAMIC_FTRACE */ /* @@ -624,6 +636,7 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, unsigned long frame_pointer) { unsigned long return_hooker = (unsigned long)&return_to_handler; + int bit; /* * When resuming from suspend-to-ram, this function can be indirectly @@ -643,7 +656,25 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, if (unlikely(atomic_read(¤t->tracing_graph_pause))) return; + bit = ftrace_test_recursion_trylock(ip, *parent); + if (bit < 0) + return; + if (!function_graph_enter(*parent, ip, frame_pointer, parent)) *parent = return_hooker; + + ftrace_test_recursion_unlock(bit); +} + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + struct pt_regs *regs = &fregs->regs; + unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs); + + prepare_ftrace_return(ip, (unsigned long *)stack, 0); } +#endif + #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index a8eb084a7a9a..7a879901f103 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -174,11 +174,6 @@ SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL) SYM_FUNC_END(ftrace_caller); SYM_FUNC_START(ftrace_epilogue) -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) - jmp ftrace_stub -#endif - /* * This is weak to keep gas from relaxing the jumps. * It is also used to copy the retq for trampolines. @@ -288,15 +283,6 @@ SYM_FUNC_START(__fentry__) cmpq $ftrace_stub, ftrace_trace_function jnz trace -fgraph_trace: -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpq $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpq $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif - SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL) retq @@ -314,25 +300,12 @@ trace: CALL_NOSPEC r8 restore_mcount_regs - jmp fgraph_trace + jmp ftrace_stub SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -SYM_FUNC_START(ftrace_graph_caller) - /* Saves rbp into %rdx and fills first parameter */ - save_mcount_regs - - leaq MCOUNT_REG_SIZE+8(%rsp), %rsi - movq $0, %rdx /* No framepointers needed */ - call prepare_ftrace_return - - restore_mcount_regs - - retq -SYM_FUNC_END(ftrace_graph_caller) - SYM_FUNC_START(return_to_handler) subq $24, %rsp diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 12fcfa2d23ea..16a7baaba702 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -803,6 +803,15 @@ static inline bool is_ftrace_trampoline(unsigned long addr) } #endif /* CONFIG_DYNAMIC_FTRACE */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +#ifndef ftrace_graph_func +#define ftrace_graph_func ftrace_stub +#define FTRACE_OPS_GRAPH_STUB FTRACE_OPS_FL_STUB +#else +#define FTRACE_OPS_GRAPH_STUB 0 +#endif +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + /* totally disable ftrace - can not re-enable after this */ void ftrace_kill(void); diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index b8a0d1d564fb..22061d38fc00 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -115,6 +115,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, { struct ftrace_graph_ent trace; +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS /* * Skip graph tracing if the return location is served by direct trampoline, * since call sequence and return addresses are unpredictable anyway. @@ -124,6 +125,7 @@ int function_graph_enter(unsigned long ret, unsigned long func, if (ftrace_direct_func_count && ftrace_find_rec_direct(ret - MCOUNT_INSN_SIZE)) return -EBUSY; +#endif trace.func = func; trace.depth = ++current->curr_ret_depth; @@ -333,10 +335,10 @@ unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx, #endif /* HAVE_FUNCTION_GRAPH_RET_ADDR_PTR */ static struct ftrace_ops graph_ops = { - .func = ftrace_stub, + .func = ftrace_graph_func, .flags = FTRACE_OPS_FL_INITIALIZED | FTRACE_OPS_FL_PID | - FTRACE_OPS_FL_STUB, + FTRACE_OPS_GRAPH_STUB, #ifdef FTRACE_GRAPH_TRAMP_ADDR .trampoline = FTRACE_GRAPH_TRAMP_ADDR, /* trampoline_size is only needed for dynamically allocated tramps */ -- cgit v1.2.3 From e967b60eb51116d2347093655e555aa036dd40d8 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:46 +0200 Subject: mfd: ti_am335x_tscadc: Clarify the maximum values for DT entries Clearly define the maximum open delay and sample delay. Use these definitions in place of a mask (which works because this is the first field in the register) and an open-coded value. While at it reword a little bit the error messages to make them look clearer and similar. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-29-miquel.raynal@bootlin.com --- drivers/iio/adc/ti_am335x_adc.c | 18 +++++++++--------- include/linux/mfd/ti_am335x_tscadc.h | 2 ++ 2 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 3dec115e68ee..a241e6fa3564 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -126,7 +126,7 @@ static void tiadc_step_config(struct iio_dev *indio_dev) chan = adc_dev->channel_line[i]; if (adc_dev->step_avg[i] > STEPCONFIG_AVG_16) { - dev_warn(dev, "chan %d step_avg truncating to %ld\n", + dev_warn(dev, "chan %d: wrong step avg, truncated to %ld\n", chan, STEPCONFIG_AVG_16); adc_dev->step_avg[i] = STEPCONFIG_AVG_16; } @@ -147,16 +147,16 @@ static void tiadc_step_config(struct iio_dev *indio_dev) STEPCONFIG_RFP_VREFP | STEPCONFIG_RFM_VREFN); - if (adc_dev->open_delay[i] > STEPDELAY_OPEN_MASK) { - dev_warn(dev, "chan %d open delay truncating to 0x3FFFF\n", - chan); - adc_dev->open_delay[i] = STEPDELAY_OPEN_MASK; + if (adc_dev->open_delay[i] > STEPCONFIG_MAX_OPENDLY) { + dev_warn(dev, "chan %d: wrong open delay, truncated to 0x%lX\n", + chan, STEPCONFIG_MAX_OPENDLY); + adc_dev->open_delay[i] = STEPCONFIG_MAX_OPENDLY; } - if (adc_dev->sample_delay[i] > 0xFF) { - dev_warn(dev, "chan %d sample delay truncating to 0xFF\n", - chan); - adc_dev->sample_delay[i] = 0xFF; + if (adc_dev->sample_delay[i] > STEPCONFIG_MAX_SAMPLE) { + dev_warn(dev, "chan %d: wrong sample delay, truncated to 0x%lX\n", + chan, STEPCONFIG_MAX_SAMPLE); + adc_dev->sample_delay[i] = STEPCONFIG_MAX_SAMPLE; } tiadc_writel(adc_dev, REG_STEPDELAY(steps), diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ae694fa2d711..31cffb6e8b17 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -84,7 +84,9 @@ #define STEPCONFIG_OPENDLY STEPDELAY_OPEN(0x098) #define STEPDELAY_SAMPLE_MASK GENMASK(31, 24) #define STEPDELAY_SAMPLE(val) FIELD_PREP(STEPDELAY_SAMPLE_MASK, (val)) +#define STEPCONFIG_MAX_OPENDLY GENMASK(17, 0) #define STEPCONFIG_SAMPLEDLY STEPDELAY_SAMPLE(0) +#define STEPCONFIG_MAX_SAMPLE GENMASK(7, 0) /* Charge Config */ #define STEPCHARGE_RFP_MASK GENMASK(14, 12) -- cgit v1.2.3 From 0fd12262613116a38fd76aefa396e9bc116fbfe2 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:47 +0200 Subject: mfd: ti_am335x_tscadc: Drop useless definitions from the header Drop useless definitions from the header like the "masks" definitions which are only used by the following definition. It could be possible to got even further by removing these definitions entirely and use FIELD_PREP() macros from the code directly, but while I have no troubles making these changes in the header, changing the values in the code directly could darkening a bit the logic and hardening future git-blames for very little added value IMHO (but this is of course a personal taste). Certain macros are using GENMASK() to define the value of a particular field, while this is purely "by chance" that the value and the mask have the same value. In this case, drop the "mask" definition, use FIELD_PREP() and GENMASK() in the macro defining the field, and use the new macro to define the particular value by feeding directly the actual number advertised in the datasheet into that macro, as in: -#define STEPCONFIG_RFM_VREFN GENMASK(24, 23) -#define STEPCONFIG_RFM(val) FIELD_PREP(STEPCONFIG_RFM_VREFN, (val)) +#define STEPCONFIG_RFM(val) FIELD_PREP(GENMASK(24, 23), (val)) +#define STEPCONFIG_RFM_VREFN STEPCONFIG_RFM(3) Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-30-miquel.raynal@bootlin.com --- include/linux/mfd/ti_am335x_tscadc.h | 44 +++++++++++++----------------------- 1 file changed, 16 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 31cffb6e8b17..51d987080cd3 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -52,12 +52,10 @@ #define IRQENB_PENUP BIT(9) /* Step Configuration */ -#define STEPCONFIG_MODE_MASK GENMASK(1, 0) -#define STEPCONFIG_MODE(val) FIELD_PREP(STEPCONFIG_MODE_MASK, (val)) +#define STEPCONFIG_MODE(val) FIELD_PREP(GENMASK(1, 0), (val)) #define STEPCONFIG_MODE_SWCNT STEPCONFIG_MODE(1) #define STEPCONFIG_MODE_HWSYNC STEPCONFIG_MODE(2) -#define STEPCONFIG_AVG_MASK GENMASK(4, 2) -#define STEPCONFIG_AVG(val) FIELD_PREP(STEPCONFIG_AVG_MASK, (val)) +#define STEPCONFIG_AVG(val) FIELD_PREP(GENMASK(4, 2), (val)) #define STEPCONFIG_AVG_16 STEPCONFIG_AVG(4) #define STEPCONFIG_XPP BIT(5) #define STEPCONFIG_XNN BIT(6) @@ -65,45 +63,36 @@ #define STEPCONFIG_YNN BIT(8) #define STEPCONFIG_XNP BIT(9) #define STEPCONFIG_YPN BIT(10) -#define STEPCONFIG_RFP_VREFP GENMASK(13, 12) -#define STEPCONFIG_RFP(val) FIELD_PREP(STEPCONFIG_RFP_VREFP, (val)) -#define STEPCONFIG_INM_MASK GENMASK(18, 15) -#define STEPCONFIG_INM(val) FIELD_PREP(STEPCONFIG_INM_MASK, (val)) +#define STEPCONFIG_RFP(val) FIELD_PREP(GENMASK(13, 12), (val)) +#define STEPCONFIG_RFP_VREFP STEPCONFIG_RFP(3) +#define STEPCONFIG_INM(val) FIELD_PREP(GENMASK(18, 15), (val)) #define STEPCONFIG_INM_ADCREFM STEPCONFIG_INM(8) -#define STEPCONFIG_INP_MASK GENMASK(22, 19) -#define STEPCONFIG_INP(val) FIELD_PREP(STEPCONFIG_INP_MASK, (val)) +#define STEPCONFIG_INP(val) FIELD_PREP(GENMASK(22, 19), (val)) #define STEPCONFIG_INP_AN4 STEPCONFIG_INP(4) #define STEPCONFIG_INP_ADCREFM STEPCONFIG_INP(8) #define STEPCONFIG_FIFO1 BIT(26) -#define STEPCONFIG_RFM_VREFN GENMASK(24, 23) -#define STEPCONFIG_RFM(val) FIELD_PREP(STEPCONFIG_RFM_VREFN, (val)) +#define STEPCONFIG_RFM(val) FIELD_PREP(GENMASK(24, 23), (val)) +#define STEPCONFIG_RFM_VREFN STEPCONFIG_RFM(3) /* Delay register */ -#define STEPDELAY_OPEN_MASK GENMASK(17, 0) -#define STEPDELAY_OPEN(val) FIELD_PREP(STEPDELAY_OPEN_MASK, (val)) +#define STEPDELAY_OPEN(val) FIELD_PREP(GENMASK(17, 0), (val)) #define STEPCONFIG_OPENDLY STEPDELAY_OPEN(0x098) -#define STEPDELAY_SAMPLE_MASK GENMASK(31, 24) -#define STEPDELAY_SAMPLE(val) FIELD_PREP(STEPDELAY_SAMPLE_MASK, (val)) #define STEPCONFIG_MAX_OPENDLY GENMASK(17, 0) +#define STEPDELAY_SAMPLE(val) FIELD_PREP(GENMASK(31, 24), (val)) #define STEPCONFIG_SAMPLEDLY STEPDELAY_SAMPLE(0) #define STEPCONFIG_MAX_SAMPLE GENMASK(7, 0) /* Charge Config */ -#define STEPCHARGE_RFP_MASK GENMASK(14, 12) -#define STEPCHARGE_RFP(val) FIELD_PREP(STEPCHARGE_RFP_MASK, (val)) +#define STEPCHARGE_RFP(val) FIELD_PREP(GENMASK(14, 12), (val)) #define STEPCHARGE_RFP_XPUL STEPCHARGE_RFP(1) -#define STEPCHARGE_INM_MASK GENMASK(18, 15) -#define STEPCHARGE_INM(val) FIELD_PREP(STEPCHARGE_INM_MASK, (val)) +#define STEPCHARGE_INM(val) FIELD_PREP(GENMASK(18, 15), (val)) #define STEPCHARGE_INM_AN1 STEPCHARGE_INM(1) -#define STEPCHARGE_INP_MASK GENMASK(22, 19) -#define STEPCHARGE_INP(val) FIELD_PREP(STEPCHARGE_INP_MASK, (val)) -#define STEPCHARGE_RFM_MASK GENMASK(24, 23) -#define STEPCHARGE_RFM(val) FIELD_PREP(STEPCHARGE_RFM_MASK, (val)) +#define STEPCHARGE_INP(val) FIELD_PREP(GENMASK(22, 19), (val)) +#define STEPCHARGE_RFM(val) FIELD_PREP(GENMASK(24, 23), (val)) #define STEPCHARGE_RFM_XNUR STEPCHARGE_RFM(1) /* Charge delay */ -#define CHARGEDLY_OPEN_MASK GENMASK(17, 0) -#define CHARGEDLY_OPEN(val) FIELD_PREP(CHARGEDLY_OPEN_MASK, (val)) +#define CHARGEDLY_OPEN(val) FIELD_PREP(GENMASK(17, 0), (val)) #define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ @@ -111,8 +100,7 @@ #define CNTRLREG_STEPID BIT(1) #define CNTRLREG_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -#define CNTRLREG_AFE_CTRL_MASK GENMASK(6, 5) -#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(CNTRLREG_AFE_CTRL_MASK, (val)) +#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) #define CNTRLREG_4WIRE CNTRLREG_AFE_CTRL(1) #define CNTRLREG_5WIRE CNTRLREG_AFE_CTRL(2) #define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) -- cgit v1.2.3 From c3e36b5d069241f3cbc0e647cf297c5a329cd7a6 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:48 +0200 Subject: mfd: ti_am335x_tscadc: Rename the subsystem enable macro This bit is common to all devices (ADC, Touchscreen, Magnetic reader) so make it clear that it can be used from any location by operating a mechanical rename: s/CNTRLREG_TSCSSENB/CNTRLREG_SSENB/ Signed-off-by: Miquel Raynal Acked-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-31-miquel.raynal@bootlin.com --- drivers/iio/adc/ti_am335x_adc.c | 6 +++--- drivers/mfd/ti_am335x_tscadc.c | 6 +++--- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index a241e6fa3564..1cc2efbb2875 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -184,7 +184,7 @@ static irqreturn_t tiadc_irq_h(int irq, void *private) if (status & IRQENB_FIFO1OVRRUN) { /* FIFO Overrun. Clear flag. Disable/Enable ADC to recover */ config = tiadc_readl(adc_dev, REG_CTRL); - config &= ~(CNTRLREG_TSCSSENB); + config &= ~(CNTRLREG_SSENB); tiadc_writel(adc_dev, REG_CTRL, config); tiadc_writel(adc_dev, REG_IRQSTATUS, IRQENB_FIFO1OVRRUN | IRQENB_FIFO1UNDRFLW | IRQENB_FIFO1THRES); @@ -197,7 +197,7 @@ static irqreturn_t tiadc_irq_h(int irq, void *private) adc_fsm = tiadc_readl(adc_dev, REG_ADCFSM); } while (adc_fsm != 0x10 && count++ < 100); - tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_TSCSSENB)); + tiadc_writel(adc_dev, REG_CTRL, (config | CNTRLREG_SSENB)); return IRQ_HANDLED; } else if (status & IRQENB_FIFO1THRES) { /* Disable irq and wake worker thread */ @@ -671,7 +671,7 @@ static int __maybe_unused tiadc_suspend(struct device *dev) unsigned int idle; idle = tiadc_readl(adc_dev, REG_CTRL); - idle &= ~(CNTRLREG_TSCSSENB); + idle &= ~(CNTRLREG_SSENB); tiadc_writel(adc_dev, REG_CTRL, (idle | CNTRLREG_POWERDOWN)); diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index df4f905a7b52..a34ca378e82c 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -235,7 +235,7 @@ static int ti_tscadc_probe(struct platform_device *pdev) tscadc_idle_config(tscadc); /* Enable the TSC module enable bit */ - regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_TSCSSENB); + regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_SSENB); /* TSC Cell */ if (tsc_wires > 0) { @@ -299,7 +299,7 @@ static int __maybe_unused tscadc_suspend(struct device *dev) regmap_read(tscadc->regmap, REG_CTRL, &ctrl); ctrl &= ~(CNTRLREG_POWERDOWN); - ctrl |= CNTRLREG_TSCSSENB; + ctrl |= CNTRLREG_SSENB; regmap_write(tscadc->regmap, REG_CTRL, ctrl); } pm_runtime_put_sync(dev); @@ -316,7 +316,7 @@ static int __maybe_unused tscadc_resume(struct device *dev) regmap_write(tscadc->regmap, REG_CLKDIV, tscadc->clk_div); regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl); tscadc_idle_config(tscadc); - regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_TSCSSENB); + regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_SSENB); return 0; } diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 51d987080cd3..860289ae8516 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -96,7 +96,7 @@ #define CHARGEDLY_OPENDLY CHARGEDLY_OPEN(0x400) /* Control register */ -#define CNTRLREG_TSCSSENB BIT(0) +#define CNTRLREG_SSENB BIT(0) #define CNTRLREG_STEPID BIT(1) #define CNTRLREG_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -- cgit v1.2.3 From 2f89c2619ce93bf2b0e6e721614fc33e8cf48f03 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:49 +0200 Subject: mfd: ti_am335x_tscadc: Add TSC prefix in certain macros While the register list (and names) between ADC0 and ADC1 are pretty close, the bits inside changed a little bit. To avoid any future confusion, let's add the TSC prefix when some bits are in a register that is common to both revisions of the ADC, but are specific to the am33xx hardware. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-32-miquel.raynal@bootlin.com --- drivers/mfd/ti_am335x_tscadc.c | 10 +++++----- include/linux/mfd/ti_am335x_tscadc.h | 14 +++++++------- 2 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index a34ca378e82c..ffd52e021c2c 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -222,13 +222,13 @@ static int ti_tscadc_probe(struct platform_device *pdev) * of the CTRL register but not the subsystem enable bit which must be * added manually when timely. */ - tscadc->ctrl = CNTRLREG_STEPCONFIGWRT | CNTRLREG_STEPID; + tscadc->ctrl = CNTRLREG_TSC_STEPCONFIGWRT | CNTRLREG_STEPID; if (tsc_wires > 0) { - tscadc->ctrl |= CNTRLREG_TSCENB; + tscadc->ctrl |= CNTRLREG_TSC_ENB; if (tsc_wires == 5) - tscadc->ctrl |= CNTRLREG_5WIRE; + tscadc->ctrl |= CNTRLREG_TSC_5WIRE; else - tscadc->ctrl |= CNTRLREG_4WIRE; + tscadc->ctrl |= CNTRLREG_TSC_4WIRE; } regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl); @@ -328,7 +328,7 @@ static const struct ti_tscadc_data tscdata = { .adc_feature_compatible = "ti,am3359-adc", .secondary_feature_name = "TI-am335x-tsc", .secondary_feature_compatible = "ti,am3359-tsc", - .target_clk_rate = ADC_CLK, + .target_clk_rate = TSC_ADC_CLK, }; static const struct of_device_id ti_tscadc_dt_ids[] = { diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 860289ae8516..cc6de9258455 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -98,13 +98,13 @@ /* Control register */ #define CNTRLREG_SSENB BIT(0) #define CNTRLREG_STEPID BIT(1) -#define CNTRLREG_STEPCONFIGWRT BIT(2) +#define CNTRLREG_TSC_STEPCONFIGWRT BIT(2) #define CNTRLREG_POWERDOWN BIT(4) -#define CNTRLREG_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) -#define CNTRLREG_4WIRE CNTRLREG_AFE_CTRL(1) -#define CNTRLREG_5WIRE CNTRLREG_AFE_CTRL(2) -#define CNTRLREG_8WIRE CNTRLREG_AFE_CTRL(3) -#define CNTRLREG_TSCENB BIT(7) +#define CNTRLREG_TSC_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) +#define CNTRLREG_TSC_4WIRE CNTRLREG_TSC_AFE_CTRL(1) +#define CNTRLREG_TSC_5WIRE CNTRLREG_TSC_AFE_CTRL(2) +#define CNTRLREG_TSC_8WIRE CNTRLREG_TSC_AFE_CTRL(3) +#define CNTRLREG_TSC_ENB BIT(7) /* FIFO READ Register */ #define FIFOREAD_DATA_MASK GENMASK(11, 0) @@ -118,7 +118,7 @@ #define SEQ_STATUS BIT(5) #define CHARGE_STEP 0x11 -#define ADC_CLK (3 * HZ_PER_MHZ) +#define TSC_ADC_CLK (3 * HZ_PER_MHZ) #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 #define FIFO1_THRESHOLD 19 -- cgit v1.2.3 From bf0f394c7b1e4d623ca2afdf59b3b4b95cc6f592 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:53 +0200 Subject: mfd: ti_am335x_tscadc: Introduce a helper to deal with the type of hardware One way of knowing which hardware we are dealing with is to check the compatible string. When this must be done at several places, it's best and certainly more clear to use a helper for that. Introduce ti_adc_with_touchscreen() to indicate if there is a touchscreen controller available (meaning it's an am33xx-like ADC). This helper does not indicate if it is actually used (that is the purpose of the use_tsc boolean). Introducing this helper helps making a difference in the code between what is generic to both types of ADCs and what is specific to the am33xx hardware before introducing support for the am437x hardware. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-36-miquel.raynal@bootlin.com --- drivers/mfd/ti_am335x_tscadc.c | 36 +++++++++++++++++++++--------------- include/linux/mfd/ti_am335x_tscadc.h | 6 ++++++ 2 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index f7cfe2016bbc..4f76b5498077 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -105,8 +105,9 @@ static void tscadc_idle_config(struct ti_tscadc_dev *tscadc) { unsigned int idleconfig; - idleconfig = STEPCONFIG_YNN | STEPCONFIG_INM_ADCREFM | - STEPCONFIG_INP_ADCREFM | STEPCONFIG_YPN; + idleconfig = STEPCONFIG_INM_ADCREFM | STEPCONFIG_INP_ADCREFM; + if (ti_adc_with_touchscreen(tscadc)) + idleconfig |= STEPCONFIG_YNN | STEPCONFIG_YPN; regmap_write(tscadc->regmap, REG_IDLECONFIG, idleconfig); } @@ -140,12 +141,14 @@ static int ti_tscadc_probe(struct platform_device *pdev) tscadc->data = of_device_get_match_data(&pdev->dev); - node = of_get_child_by_name(pdev->dev.of_node, "tsc"); - of_property_read_u32(node, "ti,wires", &tscmag_wires); - of_property_read_u32(node, "ti,coordiante-readouts", &readouts); - of_node_put(node); - if (tscmag_wires) - use_tsc = true; + if (ti_adc_with_touchscreen(tscadc)) { + node = of_get_child_by_name(pdev->dev.of_node, "tsc"); + of_property_read_u32(node, "ti,wires", &tscmag_wires); + of_property_read_u32(node, "ti,coordiante-readouts", &readouts); + of_node_put(node); + if (tscmag_wires) + use_tsc = true; + } node = of_get_child_by_name(pdev->dev.of_node, "adc"); of_property_for_each_u32(node, "ti,adc-channels", prop, cur, val) { @@ -225,13 +228,16 @@ static int ti_tscadc_probe(struct platform_device *pdev) * of the CTRL register but not the subsystem enable bit which must be * added manually when timely. */ - tscadc->ctrl = CNTRLREG_TSC_STEPCONFIGWRT | CNTRLREG_STEPID; - if (use_tsc) { - tscadc->ctrl |= CNTRLREG_TSC_ENB; - if (tscmag_wires == 5) - tscadc->ctrl |= CNTRLREG_TSC_5WIRE; - else - tscadc->ctrl |= CNTRLREG_TSC_4WIRE; + tscadc->ctrl = CNTRLREG_STEPID; + if (ti_adc_with_touchscreen(tscadc)) { + tscadc->ctrl |= CNTRLREG_TSC_STEPCONFIGWRT; + if (use_tsc) { + tscadc->ctrl |= CNTRLREG_TSC_ENB; + if (tscmag_wires == 5) + tscadc->ctrl |= CNTRLREG_TSC_5WIRE; + else + tscadc->ctrl |= CNTRLREG_TSC_4WIRE; + } } regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl); diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index cc6de9258455..ee160b2036c1 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -177,6 +177,12 @@ static inline struct ti_tscadc_dev *ti_tscadc_dev_get(struct platform_device *p) return *tscadc_dev; } +static inline bool ti_adc_with_touchscreen(struct ti_tscadc_dev *tscadc) +{ + return of_device_is_compatible(tscadc->dev->of_node, + "ti,am3359-tscadc"); +} + void am335x_tsc_se_set_cache(struct ti_tscadc_dev *tsadc, u32 val); void am335x_tsc_se_set_once(struct ti_tscadc_dev *tsadc, u32 val); void am335x_tsc_se_clr(struct ti_tscadc_dev *tsadc, u32 val); -- cgit v1.2.3 From 0a1233031c16d8575be6b864e6fd353b6fd758c4 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:14:54 +0200 Subject: mfd: ti_am335x_tscadc: Add ADC1/magnetic reader support Introduce a new compatible that has another set of driver data, targeting am437x SoCs with a magnetic reader instead of the touchscreen and a more featureful set of registers. Signed-off-by: Miquel Raynal Reviewed-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-37-miquel.raynal@bootlin.com --- drivers/mfd/ti_am335x_tscadc.c | 37 +++++++++++++++++++++++++++++------- include/linux/mfd/ti_am335x_tscadc.h | 6 ++++++ 2 files changed, 36 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/ti_am335x_tscadc.c b/drivers/mfd/ti_am335x_tscadc.c index 4f76b5498077..bfbc8288a71e 100644 --- a/drivers/mfd/ti_am335x_tscadc.c +++ b/drivers/mfd/ti_am335x_tscadc.c @@ -121,11 +121,11 @@ static int ti_tscadc_probe(struct platform_device *pdev) struct mfd_cell *cell; struct property *prop; const __be32 *cur; - bool use_tsc = false; + bool use_tsc = false, use_mag = false; u32 val; int err; int tscmag_wires = 0, adc_channels = 0, cell_idx = 0, total_channels; - int readouts = 0; + int readouts = 0, mag_tracks = 0; /* Allocate memory for device */ tscadc = devm_kzalloc(&pdev->dev, sizeof(*tscadc), GFP_KERNEL); @@ -148,6 +148,16 @@ static int ti_tscadc_probe(struct platform_device *pdev) of_node_put(node); if (tscmag_wires) use_tsc = true; + } else { + /* + * When adding support for the magnetic stripe reader, here is + * the place to look for the number of tracks used from device + * tree. Let's default to 0 for now. + */ + mag_tracks = 0; + tscmag_wires = mag_tracks * 2; + if (tscmag_wires) + use_mag = true; } node = of_get_child_by_name(pdev->dev.of_node, "adc"); @@ -209,8 +219,9 @@ static int ti_tscadc_probe(struct platform_device *pdev) * The TSC_ADC_Subsystem has 2 clock domains: OCP_CLK and ADC_CLK. * ADCs produce a 12-bit sample every 15 ADC_CLK cycles. * am33xx ADCs expect to capture 200ksps. - * We need the ADC clocks to run at 3MHz. - * This frequency is valid since TSC_ADC_SS controller design + * am47xx ADCs expect to capture 867ksps. + * We need ADC clocks respectively running at 3MHz and 13MHz. + * These frequencies are valid since TSC_ADC_SS controller design * assumes the OCP clock is at least 6x faster than the ADC clock. */ clk = devm_clk_get(&pdev->dev, NULL); @@ -238,6 +249,9 @@ static int ti_tscadc_probe(struct platform_device *pdev) else tscadc->ctrl |= CNTRLREG_TSC_4WIRE; } + } else { + tscadc->ctrl |= CNTRLREG_MAG_PREAMP_PWRDOWN | + CNTRLREG_MAG_PREAMP_BYPASS; } regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl); @@ -246,8 +260,8 @@ static int ti_tscadc_probe(struct platform_device *pdev) /* Enable the TSC module enable bit */ regmap_write(tscadc->regmap, REG_CTRL, tscadc->ctrl | CNTRLREG_SSENB); - /* TSC Cell */ - if (tscmag_wires > 0) { + /* TSC or MAG Cell */ + if (use_tsc || use_mag) { cell = &tscadc->cells[cell_idx++]; cell->name = tscadc->data->secondary_feature_name; cell->of_compatible = tscadc->data->secondary_feature_compatible; @@ -340,8 +354,17 @@ static const struct ti_tscadc_data tscdata = { .target_clk_rate = TSC_ADC_CLK, }; +static const struct ti_tscadc_data magdata = { + .adc_feature_name = "TI-am43xx-adc", + .adc_feature_compatible = "ti,am4372-adc", + .secondary_feature_name = "TI-am43xx-mag", + .secondary_feature_compatible = "ti,am4372-mag", + .target_clk_rate = MAG_ADC_CLK, +}; + static const struct of_device_id ti_tscadc_dt_ids[] = { { .compatible = "ti,am3359-tscadc", .data = &tscdata }, + { .compatible = "ti,am4372-magadc", .data = &magdata }, { } }; MODULE_DEVICE_TABLE(of, ti_tscadc_dt_ids); @@ -359,6 +382,6 @@ static struct platform_driver ti_tscadc_driver = { module_platform_driver(ti_tscadc_driver); -MODULE_DESCRIPTION("TI touchscreen / ADC MFD controller driver"); +MODULE_DESCRIPTION("TI touchscreen/magnetic stripe reader/ADC MFD controller driver"); MODULE_AUTHOR("Rachna Patil "); MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ee160b2036c1..5225e3fc194d 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -106,6 +106,11 @@ #define CNTRLREG_TSC_8WIRE CNTRLREG_TSC_AFE_CTRL(3) #define CNTRLREG_TSC_ENB BIT(7) +/*Control registers bitfields for MAGADC IP */ +#define CNTRLREG_MAGADCENB BIT(0) +#define CNTRLREG_MAG_PREAMP_PWRDOWN BIT(5) +#define CNTRLREG_MAG_PREAMP_BYPASS BIT(6) + /* FIFO READ Register */ #define FIFOREAD_DATA_MASK GENMASK(11, 0) #define FIFOREAD_CHNLID_MASK GENMASK(19, 16) @@ -119,6 +124,7 @@ #define CHARGE_STEP 0x11 #define TSC_ADC_CLK (3 * HZ_PER_MHZ) +#define MAG_ADC_CLK (13 * HZ_PER_MHZ) #define TOTAL_STEPS 16 #define TOTAL_CHANNELS 8 #define FIFO1_THRESHOLD 19 -- cgit v1.2.3 From 789e5ebcc61b72a71717b02b62e6c6f10fdbb722 Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Fri, 15 Oct 2021 10:15:01 +0200 Subject: iio: adc: ti_am335x_adc: Add a unit to the timeout delay The lack of unit in the macro name kind of tricked me when I was troubleshooting an issue. Physical constants should always get a unit. Signed-off-by: Miquel Raynal Acked-by: Jonathan Cameron Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211015081506.933180-44-miquel.raynal@bootlin.com --- drivers/iio/adc/ti_am335x_adc.c | 4 ++-- include/linux/mfd/ti_am335x_tscadc.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index 6f47a1ace3d4..e7dba10b29b4 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -101,7 +101,7 @@ static int tiadc_wait_idle(struct tiadc_device *adc_dev) return readl_poll_timeout(adc_dev->mfd_tscadc->tscadc_base + REG_ADCFSM, val, !(val & SEQ_STATUS), 10, - IDLE_TIMEOUT * 1000 * adc_dev->channels); + IDLE_TIMEOUT_MS * 1000 * adc_dev->channels); } static void tiadc_step_config(struct iio_dev *indio_dev) @@ -461,7 +461,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, am335x_tsc_se_set_once(adc_dev->mfd_tscadc, step_en); /* Wait for Fifo threshold interrupt */ - timeout = jiffies + msecs_to_jiffies(IDLE_TIMEOUT * adc_dev->channels); + timeout = jiffies + msecs_to_jiffies(IDLE_TIMEOUT_MS * adc_dev->channels); while (1) { fifo1count = tiadc_readl(adc_dev, REG_FIFO1CNT); if (fifo1count) diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 5225e3fc194d..ba13e043d910 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -141,7 +141,7 @@ * * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 83 /* milliseconds */ +#define IDLE_TIMEOUT_MS 83 /* milliseconds */ #define TSCADC_CELLS 2 -- cgit v1.2.3 From 9a48e7564ac83fb0f1d5b0eac5fe8a7af62da398 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 20 Oct 2021 13:00:39 -0700 Subject: compiler-gcc.h: Define __SANITIZE_ADDRESS__ under hwaddress sanitizer When Clang is using the hwaddress sanitizer, it sets __SANITIZE_ADDRESS__ explicitly: #if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) /* Emulate GCC's __SANITIZE_ADDRESS__ flag */ #define __SANITIZE_ADDRESS__ #endif Once hwaddress sanitizer was added to GCC, however, a separate define was created, __SANITIZE_HWADDRESS__. The kernel is expecting to find __SANITIZE_ADDRESS__ in either case, though, and the existing string macros break on supported architectures: #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(__SANITIZE_ADDRESS__) where as other architectures (like arm32) have no idea about hwaddress sanitizer and just check for __SANITIZE_ADDRESS__: #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) This would lead to compiler foritfy self-test warnings when building with CONFIG_KASAN_SW_TAGS=y: warning: unsafe memmove() usage lacked '__read_overflow2' symbol in lib/test_fortify/read_overflow2-memmove.c warning: unsafe memcpy() usage lacked '__write_overflow' symbol in lib/test_fortify/write_overflow-memcpy.c ... Sort this out by also defining __SANITIZE_ADDRESS__ in GCC under the hwaddress sanitizer. Suggested-by: Arnd Bergmann Cc: Nick Desaulniers Cc: Andrew Morton Cc: Will Deacon Cc: Arvind Sankar Cc: Masahiro Yamada Cc: llvm@lists.linux.dev Signed-off-by: Kees Cook Reviewed-by: Nathan Chancellor Acked-by: Miguel Ojeda Reviewed-by: Marco Elver Link: https://lore.kernel.org/r/20211020200039.170424-1-keescook@chromium.org --- include/linux/compiler-gcc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 9957085b8148..7bbd8df02532 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -121,6 +121,14 @@ #define __no_sanitize_coverage #endif +/* + * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel, + * matching the defines used by Clang. + */ +#ifdef __SANITIZE_HWADDRESS__ +#define __SANITIZE_ADDRESS__ +#endif + /* * Turn individual warnings and errors on and off locally, depending * on version. -- cgit v1.2.3 From 3598b30bd970bbc09dba0cf31aa0a04105f37207 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 20 Oct 2021 21:08:06 +0200 Subject: cpufreq: Fix typo in cpufreq.h s/internale/internal/ Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ff88bb3e44fc..3317887027b5 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -385,7 +385,7 @@ struct cpufreq_driver { /* flags */ /* - * Set by drivers that need to update internale upper and lower boundaries along + * Set by drivers that need to update internal upper and lower boundaries along * with the target frequency and so the core and governors should also invoke * the diver if the target frequency does not change, but the policy min or max * may have changed. -- cgit v1.2.3 From e279317e9aeb11d8670e0a5acb10d50566eea9c9 Mon Sep 17 00:00:00 2001 From: Arnaud Pouliquen Date: Fri, 15 Oct 2021 11:47:00 +0200 Subject: rpmsg: core: add API to get MTU Return the rpmsg buffer MTU for sending message, so rpmsg users can split a long message in several sub rpmsg buffers. Reviewed-by: Mathieu Poirier Reviewed-by: Bjorn Andersson Acked-by: Suman Anna Signed-off-by: Arnaud Pouliquen Link: https://lore.kernel.org/r/20211015094701.5732-2-arnaud.pouliquen@foss.st.com Signed-off-by: Greg Kroah-Hartman --- drivers/rpmsg/rpmsg_core.c | 21 +++++++++++++++++++++ drivers/rpmsg/rpmsg_internal.h | 2 ++ drivers/rpmsg/virtio_rpmsg_bus.c | 10 ++++++++++ include/linux/rpmsg.h | 10 ++++++++++ 4 files changed, 43 insertions(+) (limited to 'include/linux') diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c index 9151836190ce..d3eb60059ef1 100644 --- a/drivers/rpmsg/rpmsg_core.c +++ b/drivers/rpmsg/rpmsg_core.c @@ -327,6 +327,27 @@ int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, } EXPORT_SYMBOL(rpmsg_trysend_offchannel); +/** + * rpmsg_get_mtu() - get maximum transmission buffer size for sending message. + * @ept: the rpmsg endpoint + * + * This function returns maximum buffer size available for a single outgoing message. + * + * Return: the maximum transmission size on success and an appropriate error + * value on failure. + */ + +ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept) +{ + if (WARN_ON(!ept)) + return -EINVAL; + if (!ept->ops->get_mtu) + return -ENOTSUPP; + + return ept->ops->get_mtu(ept); +} +EXPORT_SYMBOL(rpmsg_get_mtu); + /* * match a rpmsg channel with a channel info struct. * this is used to make sure we're not creating rpmsg devices for channels diff --git a/drivers/rpmsg/rpmsg_internal.h b/drivers/rpmsg/rpmsg_internal.h index a76c344253bf..b1245d3ed7c6 100644 --- a/drivers/rpmsg/rpmsg_internal.h +++ b/drivers/rpmsg/rpmsg_internal.h @@ -53,6 +53,7 @@ struct rpmsg_device_ops { * @trysendto: see @rpmsg_trysendto(), optional * @trysend_offchannel: see @rpmsg_trysend_offchannel(), optional * @poll: see @rpmsg_poll(), optional + * @get_mtu: see @rpmsg_get_mtu(), optional * * Indirection table for the operations that a rpmsg backend should implement. * In addition to @destroy_ept, the backend must at least implement @send and @@ -72,6 +73,7 @@ struct rpmsg_endpoint_ops { void *data, int len); __poll_t (*poll)(struct rpmsg_endpoint *ept, struct file *filp, poll_table *wait); + ssize_t (*get_mtu)(struct rpmsg_endpoint *ept); }; struct device *rpmsg_find_device(struct device *parent, diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 8e49a3bacfc7..05fd06fc67e9 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -149,6 +149,7 @@ static int virtio_rpmsg_trysendto(struct rpmsg_endpoint *ept, void *data, int len, u32 dst); static int virtio_rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, void *data, int len); +static ssize_t virtio_rpmsg_get_mtu(struct rpmsg_endpoint *ept); static struct rpmsg_device *__rpmsg_create_channel(struct virtproc_info *vrp, struct rpmsg_channel_info *chinfo); @@ -160,6 +161,7 @@ static const struct rpmsg_endpoint_ops virtio_endpoint_ops = { .trysend = virtio_rpmsg_trysend, .trysendto = virtio_rpmsg_trysendto, .trysend_offchannel = virtio_rpmsg_trysend_offchannel, + .get_mtu = virtio_rpmsg_get_mtu, }; /** @@ -696,6 +698,14 @@ static int virtio_rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, return rpmsg_send_offchannel_raw(rpdev, src, dst, data, len, false); } +static ssize_t virtio_rpmsg_get_mtu(struct rpmsg_endpoint *ept) +{ + struct rpmsg_device *rpdev = ept->rpdev; + struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev); + + return vch->vrp->buf_size - sizeof(struct rpmsg_hdr); +} + static int rpmsg_recv_single(struct virtproc_info *vrp, struct device *dev, struct rpmsg_hdr *msg, unsigned int len) { diff --git a/include/linux/rpmsg.h b/include/linux/rpmsg.h index d97dcd049f18..990b80fb49ad 100644 --- a/include/linux/rpmsg.h +++ b/include/linux/rpmsg.h @@ -186,6 +186,8 @@ int rpmsg_trysend_offchannel(struct rpmsg_endpoint *ept, u32 src, u32 dst, __poll_t rpmsg_poll(struct rpmsg_endpoint *ept, struct file *filp, poll_table *wait); +ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept); + #else static inline int rpmsg_register_device(struct rpmsg_device *rpdev) @@ -296,6 +298,14 @@ static inline __poll_t rpmsg_poll(struct rpmsg_endpoint *ept, return 0; } +static inline ssize_t rpmsg_get_mtu(struct rpmsg_endpoint *ept) +{ + /* This shouldn't be possible */ + WARN_ON(1); + + return -ENXIO; +} + #endif /* IS_ENABLED(CONFIG_RPMSG) */ /* use a macro to avoid include chaining to get THIS_MODULE */ -- cgit v1.2.3 From 8ac33b8b6841e99a624ace543d92cbf598a91381 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Thu, 21 Oct 2021 19:35:40 +0900 Subject: counter: Fix use-after-free race condition for events_queue_size write A race condition is possible when writing to events_queue_size where the events kfifo is freed during the execution of a kfifo_in(), resulting in a use-after-free. This patch prevents such a scenario by protecting the events queue in operation with a spinlock and locking before performing the events queue size adjustment. The existing events_lock mutex is renamed to events_out_lock to reflect that it only protects events queue out operations. Because the events queue in operations can occur in an interrupt context, a new events_in_lock spinlock is introduced and utilized. Fixes: feff17a550c7 ("counter: Implement events_queue_size sysfs attribute") Cc: David Lechner Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/20211021103540.955639-1-vilhelm.gray@gmail.com Signed-off-by: Greg Kroah-Hartman --- drivers/counter/counter-chrdev.c | 10 ++++++---- drivers/counter/counter-sysfs.c | 7 +++++++ include/linux/counter.h | 6 ++++-- 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c index 0c82613582f1..b7c62f957a6a 100644 --- a/drivers/counter/counter-chrdev.c +++ b/drivers/counter/counter-chrdev.c @@ -81,10 +81,10 @@ static ssize_t counter_chrdev_read(struct file *filp, char __user *buf, return -ENODEV; } - if (mutex_lock_interruptible(&counter->events_lock)) + if (mutex_lock_interruptible(&counter->events_out_lock)) return -ERESTARTSYS; err = kfifo_to_user(&counter->events, buf, len, &copied); - mutex_unlock(&counter->events_lock); + mutex_unlock(&counter->events_out_lock); if (err < 0) return err; } while (!copied); @@ -436,7 +436,8 @@ int counter_chrdev_add(struct counter_device *const counter) spin_lock_init(&counter->events_list_lock); mutex_init(&counter->n_events_list_lock); init_waitqueue_head(&counter->events_wait); - mutex_init(&counter->events_lock); + spin_lock_init(&counter->events_in_lock); + mutex_init(&counter->events_out_lock); /* Initialize character device */ cdev_init(&counter->chrdev, &counter_fops); @@ -559,7 +560,8 @@ void counter_push_event(struct counter_device *const counter, const u8 event, ev.watch.component = comp_node->component; ev.status = -counter_get_data(counter, comp_node, &ev.value); - copied += kfifo_in(&counter->events, &ev, 1); + copied += kfifo_in_spinlocked_noirqsave(&counter->events, &ev, + 1, &counter->events_in_lock); } exit_early: diff --git a/drivers/counter/counter-sysfs.c b/drivers/counter/counter-sysfs.c index 67a988851657..7cc4d1d523ea 100644 --- a/drivers/counter/counter-sysfs.c +++ b/drivers/counter/counter-sysfs.c @@ -11,6 +11,8 @@ #include #include #include +#include +#include #include #include #include @@ -796,6 +798,7 @@ static int counter_events_queue_size_write(struct counter_device *counter, { DECLARE_KFIFO_PTR(events, struct counter_event); int err; + unsigned long flags; /* Allocate new events queue */ err = kfifo_alloc(&events, val, GFP_KERNEL); @@ -803,8 +806,12 @@ static int counter_events_queue_size_write(struct counter_device *counter, return err; /* Swap in new events queue */ + mutex_lock(&counter->events_out_lock); + spin_lock_irqsave(&counter->events_in_lock, flags); kfifo_free(&counter->events); counter->events.kfifo = events.kfifo; + spin_unlock_irqrestore(&counter->events_in_lock, flags); + mutex_unlock(&counter->events_out_lock); return 0; } diff --git a/include/linux/counter.h b/include/linux/counter.h index 0fd99e255a50..b7d0a00a61cf 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -296,7 +296,8 @@ struct counter_ops { * @n_events_list_lock: lock to protect Counter next events list operations * @events: queue of detected Counter events * @events_wait: wait queue to allow blocking reads of Counter events - * @events_lock: lock to protect Counter events queue read operations + * @events_in_lock: lock to protect Counter events queue in operations + * @events_out_lock: lock to protect Counter events queue out operations * @ops_exist_lock: lock to prevent use during removal */ struct counter_device { @@ -323,7 +324,8 @@ struct counter_device { struct mutex n_events_list_lock; DECLARE_KFIFO_PTR(events, struct counter_event); wait_queue_head_t events_wait; - struct mutex events_lock; + spinlock_t events_in_lock; + struct mutex events_out_lock; struct mutex ops_exist_lock; }; -- cgit v1.2.3 From 992e5cc7be8e693aba1f0ee7905d34c87fd7872a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Wed, 20 Oct 2021 20:49:55 +0300 Subject: net: dsa: tag_8021q: make dsa_8021q_{rx,tx}_vid take dp as argument Pass a single argument to dsa_8021q_rx_vid and dsa_8021q_tx_vid that contains the necessary information from the two arguments that are currently provided: the switch and the port number. Also rename those functions so that they have a dsa_port_* prefix, since they operate on a struct dsa_port *. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_vl.c | 3 ++- include/linux/dsa/8021q.h | 5 +++-- net/dsa/tag_8021q.c | 32 ++++++++++++++++---------------- net/dsa/tag_ocelot_8021q.c | 2 +- net/dsa/tag_sja1105.c | 4 ++-- 5 files changed, 24 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index d55572994e1f..f5dca6a9b0f9 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -394,7 +394,8 @@ static int sja1105_init_virtual_links(struct sja1105_private *priv, vl_lookup[k].vlanid = rule->key.vl.vid; vl_lookup[k].vlanprior = rule->key.vl.pcp; } else { - u16 vid = dsa_8021q_rx_vid(priv->ds, port); + struct dsa_port *dp = dsa_to_port(priv->ds, port); + u16 vid = dsa_tag_8021q_rx_vid(dp); vl_lookup[k].vlanid = vid; vl_lookup[k].vlanprior = 0; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index c7fa4a3498fe..254b165f2b44 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -9,6 +9,7 @@ #include struct dsa_switch; +struct dsa_port; struct sk_buff; struct net_device; @@ -45,9 +46,9 @@ void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); +u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); +u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp); int dsa_8021q_rx_switch_id(u16 vid); diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 8f4e0af2f74f..72cac2c0af7b 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -77,22 +77,22 @@ EXPORT_SYMBOL_GPL(dsa_8021q_bridge_tx_fwd_offload_vid); /* Returns the VID to be inserted into the frame from xmit for switch steering * instructions on egress. Encodes switch ID and port ID. */ -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) +u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp) { - return DSA_8021Q_DIR_TX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port); + return DSA_8021Q_DIR_TX | DSA_8021Q_SWITCH_ID(dp->ds->index) | + DSA_8021Q_PORT(dp->index); } -EXPORT_SYMBOL_GPL(dsa_8021q_tx_vid); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_tx_vid); /* Returns the VID that will be installed as pvid for this switch port, sent as * tagged egress towards the CPU port and decoded by the rcv function. */ -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) +u16 dsa_tag_8021q_rx_vid(const struct dsa_port *dp) { - return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(ds->index) | - DSA_8021Q_PORT(port); + return DSA_8021Q_DIR_RX | DSA_8021Q_SWITCH_ID(dp->ds->index) | + DSA_8021Q_PORT(dp->index); } -EXPORT_SYMBOL_GPL(dsa_8021q_rx_vid); +EXPORT_SYMBOL_GPL(dsa_tag_8021q_rx_vid); /* Returns the decoded switch ID from the RX VID. */ int dsa_8021q_rx_switch_id(u16 vid) @@ -354,10 +354,10 @@ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); targeted_dp = dsa_to_port(targeted_ds, info->port); - targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); + targeted_rx_vid = dsa_tag_8021q_rx_vid(targeted_dp); dsa_switch_for_each_port(dp, ds) { - u16 rx_vid = dsa_8021q_rx_vid(ds, dp->index); + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); if (!dsa_port_tag_8021q_bridge_match(dp, info)) continue; @@ -389,10 +389,10 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, targeted_ds = dsa_switch_find(info->tree_index, info->sw_index); targeted_dp = dsa_to_port(targeted_ds, info->port); - targeted_rx_vid = dsa_8021q_rx_vid(targeted_ds, info->port); + targeted_rx_vid = dsa_tag_8021q_rx_vid(targeted_dp); dsa_switch_for_each_port(dp, ds) { - u16 rx_vid = dsa_8021q_rx_vid(ds, dp->index); + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); if (!dsa_port_tag_8021q_bridge_match(dp, info)) continue; @@ -433,8 +433,8 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ds, port); + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); struct net_device *master; int err; @@ -478,8 +478,8 @@ static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) { struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); - u16 rx_vid = dsa_8021q_rx_vid(ds, port); - u16 tx_vid = dsa_8021q_tx_vid(ds, port); + u16 rx_vid = dsa_tag_8021q_rx_vid(dp); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); struct net_device *master; /* The CPU port is implicitly configured by diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 3412051981d7..a1919ea5e828 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -39,9 +39,9 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); struct ethhdr *hdr = eth_hdr(skb); if (ocelot_ptp_rew_op(skb) || is_link_local_ether_addr(hdr->h_dest)) diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 8b2d458f72b3..262c8833a910 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -235,9 +235,9 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); if (skb->offload_fwd_mark) return sja1105_imprecise_xmit(skb, netdev); @@ -263,9 +263,9 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct dsa_port *dp = dsa_slave_to_port(netdev); - u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); + u16 tx_vid = dsa_tag_8021q_tx_vid(dp); __be32 *tx_trailer; __be16 *tx_header; int trailer_pos; -- cgit v1.2.3 From 061514dbfb79910ef60eb40dd9fc528be3f45d62 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 18 Oct 2021 17:43:35 -0700 Subject: regulator: lp872x: Remove lp872x_dvs_state After this driver was converted to gpiod, clang started warning: vers/regulator/lp872x.c:689:57: error: implicit conversion from enumeration type 'enum lp872x_dvs_state' to different enumeration type 'enum gpiod_flags' [-Werror,-Wenum-conversion] dvs->gpio = devm_gpiod_get_optional(lp->dev, "ti,dvs", pinstate); ~~~~~~~~~~~~~~~~~~~~~~~ ^~~~~~~~ 1 error generated. lp872x_dvs_state was updated to have values from gpiod_flags but this is not enough to avoid an implicit conversion warning from either GCC or clang (although GCC enables this warning under -Wextra instead of -Wall like clang so it is not seen under normal builds). Eliminate lp872x_dvs_state in favor of using gpiod_flags everywhere so that there is no more warning about an implicit conversion. Fixes: 72bf80cf09c4 ("regulator: lp872x: replacing legacy gpio interface for gpiod") Link: https://github.com/ClangBuiltLinux/linux/issues/1481 Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20211019004335.193492-1-nathan@kernel.org Signed-off-by: Mark Brown --- drivers/regulator/lp872x.c | 14 +++++++------- include/linux/regulator/lp872x.h | 7 +------ 2 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/lp872x.c b/drivers/regulator/lp872x.c index 1dba5dbcd461..35d826fe9def 100644 --- a/drivers/regulator/lp872x.c +++ b/drivers/regulator/lp872x.c @@ -103,7 +103,7 @@ struct lp872x { enum lp872x_id chipid; struct lp872x_platform_data *pdata; int num_regulators; - enum lp872x_dvs_state dvs_pin; + enum gpiod_flags dvs_pin; }; /* LP8720/LP8725 shared voltage table for LDOs */ @@ -251,9 +251,9 @@ static int lp872x_regulator_enable_time(struct regulator_dev *rdev) static void lp872x_set_dvs(struct lp872x *lp, enum lp872x_dvs_sel dvs_sel, struct gpio_desc *gpio) { - enum lp872x_dvs_state state; + enum gpiod_flags state; - state = dvs_sel == SEL_V1 ? DVS_HIGH : DVS_LOW; + state = dvs_sel == SEL_V1 ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; gpiod_set_value(gpio, state); lp->dvs_pin = state; } @@ -269,7 +269,7 @@ static u8 lp872x_select_buck_vout_addr(struct lp872x *lp, switch (buck) { case LP8720_ID_BUCK: if (val & LP8720_EXT_DVS_M) { - addr = (lp->dvs_pin == DVS_HIGH) ? + addr = (lp->dvs_pin == GPIOD_OUT_HIGH) ? LP8720_BUCK_VOUT1 : LP8720_BUCK_VOUT2; } else { if (lp872x_read_byte(lp, LP8720_ENABLE, &val)) @@ -283,7 +283,7 @@ static u8 lp872x_select_buck_vout_addr(struct lp872x *lp, if (val & LP8725_DVS1_M) addr = LP8725_BUCK1_VOUT1; else - addr = (lp->dvs_pin == DVS_HIGH) ? + addr = (lp->dvs_pin == GPIOD_OUT_HIGH) ? LP8725_BUCK1_VOUT1 : LP8725_BUCK1_VOUT2; break; case LP8725_ID_BUCK2: @@ -675,7 +675,7 @@ static const struct regulator_desc lp8725_regulator_desc[] = { static int lp872x_init_dvs(struct lp872x *lp) { struct lp872x_dvs *dvs = lp->pdata ? lp->pdata->dvs : NULL; - enum lp872x_dvs_state pinstate; + enum gpiod_flags pinstate; u8 mask[] = { LP8720_EXT_DVS_M, LP8725_DVS1_M | LP8725_DVS2_M }; u8 default_dvs_mode[] = { LP8720_DEFAULT_DVS, LP8725_DEFAULT_DVS }; @@ -841,7 +841,7 @@ static struct lp872x_platform_data of_property_read_u8(np, "ti,dvs-vsel", (u8 *)&pdata->dvs->vsel); of_property_read_u8(np, "ti,dvs-state", &dvs_state); - pdata->dvs->init_state = dvs_state ? DVS_HIGH : DVS_LOW; + pdata->dvs->init_state = dvs_state ? GPIOD_OUT_HIGH : GPIOD_OUT_LOW; if (of_get_child_count(np) == 0) goto out; diff --git a/include/linux/regulator/lp872x.h b/include/linux/regulator/lp872x.h index 8e7e0343c6e1..b62e45aa1dd3 100644 --- a/include/linux/regulator/lp872x.h +++ b/include/linux/regulator/lp872x.h @@ -40,11 +40,6 @@ enum lp872x_regulator_id { LP872X_ID_MAX, }; -enum lp872x_dvs_state { - DVS_LOW = GPIOD_OUT_LOW, - DVS_HIGH = GPIOD_OUT_HIGH, -}; - enum lp872x_dvs_sel { SEL_V1, SEL_V2, @@ -59,7 +54,7 @@ enum lp872x_dvs_sel { struct lp872x_dvs { struct gpio_desc *gpio; enum lp872x_dvs_sel vsel; - enum lp872x_dvs_state init_state; + enum gpiod_flags init_state; }; /** -- cgit v1.2.3 From 6a8b5bb0f1350fc4cf398435a1119db12b0bd50e Mon Sep 17 00:00:00 2001 From: Maíra Canal Date: Sun, 17 Oct 2021 15:06:39 -0300 Subject: regulator: tps62360: replacing legacy gpio interface for gpiod MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Removing all linux/gpio.h and linux/of_gpio.h dependencies and replacing them with the gpiod interface. Signed-off-by: Maíra Canal Link: https://lore.kernel.org/r/YWxmL2baF5AdzyHv@fedora Signed-off-by: Mark Brown --- drivers/regulator/tps62360-regulator.c | 59 +++++++++++++++------------------- include/linux/regulator/tps62360.h | 6 ---- 2 files changed, 26 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/regulator/tps62360-regulator.c b/drivers/regulator/tps62360-regulator.c index 315cd5daf480..574958690ace 100644 --- a/drivers/regulator/tps62360-regulator.c +++ b/drivers/regulator/tps62360-regulator.c @@ -28,13 +28,12 @@ #include #include #include -#include #include #include #include #include #include -#include +#include #include #include #include @@ -65,8 +64,8 @@ struct tps62360_chip { struct regulator_desc desc; struct regulator_dev *rdev; struct regmap *regmap; - int vsel0_gpio; - int vsel1_gpio; + struct gpio_desc *vsel0_gpio; + struct gpio_desc *vsel1_gpio; u8 voltage_reg_mask; bool en_internal_pulldn; bool en_discharge; @@ -165,8 +164,8 @@ static int tps62360_dcdc_set_voltage_sel(struct regulator_dev *dev, /* Select proper VSET register vio gpios */ if (tps->valid_gpios) { - gpio_set_value_cansleep(tps->vsel0_gpio, new_vset_id & 0x1); - gpio_set_value_cansleep(tps->vsel1_gpio, + gpiod_set_value_cansleep(tps->vsel0_gpio, new_vset_id & 0x1); + gpiod_set_value_cansleep(tps->vsel1_gpio, (new_vset_id >> 1) & 0x1); } return 0; @@ -310,9 +309,6 @@ static struct tps62360_regulator_platform_data * return NULL; } - pdata->vsel0_gpio = of_get_named_gpio(np, "vsel0-gpio", 0); - pdata->vsel1_gpio = of_get_named_gpio(np, "vsel1-gpio", 0); - if (of_find_property(np, "ti,vsel0-state-high", NULL)) pdata->vsel0_def_state = 1; @@ -349,6 +345,7 @@ static int tps62360_probe(struct i2c_client *client, int ret; int i; int chip_id; + int gpio_flags; pdata = dev_get_platdata(&client->dev); @@ -390,8 +387,6 @@ static int tps62360_probe(struct i2c_client *client, tps->en_discharge = pdata->en_discharge; tps->en_internal_pulldn = pdata->en_internal_pulldn; - tps->vsel0_gpio = pdata->vsel0_gpio; - tps->vsel1_gpio = pdata->vsel1_gpio; tps->dev = &client->dev; switch (chip_id) { @@ -426,29 +421,27 @@ static int tps62360_probe(struct i2c_client *client, tps->lru_index[0] = tps->curr_vset_id; tps->valid_gpios = false; - if (gpio_is_valid(tps->vsel0_gpio) && gpio_is_valid(tps->vsel1_gpio)) { - int gpio_flags; - gpio_flags = (pdata->vsel0_def_state) ? - GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW; - ret = devm_gpio_request_one(&client->dev, tps->vsel0_gpio, - gpio_flags, "tps62360-vsel0"); - if (ret) { - dev_err(&client->dev, - "%s(): Could not obtain vsel0 GPIO %d: %d\n", - __func__, tps->vsel0_gpio, ret); - return ret; - } + gpio_flags = (pdata->vsel0_def_state) ? + GPIOD_OUT_HIGH : GPIOD_OUT_LOW; + tps->vsel0_gpio = devm_gpiod_get_optional(&client->dev, "vsel0", gpio_flags); + if (IS_ERR(tps->vsel0_gpio)) { + dev_err(&client->dev, + "%s(): Could not obtain vsel0 GPIO: %ld\n", + __func__, PTR_ERR(tps->vsel0_gpio)); + return PTR_ERR(tps->vsel0_gpio); + } - gpio_flags = (pdata->vsel1_def_state) ? - GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW; - ret = devm_gpio_request_one(&client->dev, tps->vsel1_gpio, - gpio_flags, "tps62360-vsel1"); - if (ret) { - dev_err(&client->dev, - "%s(): Could not obtain vsel1 GPIO %d: %d\n", - __func__, tps->vsel1_gpio, ret); - return ret; - } + gpio_flags = (pdata->vsel1_def_state) ? + GPIOD_OUT_HIGH : GPIOD_OUT_LOW; + tps->vsel1_gpio = devm_gpiod_get_optional(&client->dev, "vsel1", gpio_flags); + if (IS_ERR(tps->vsel1_gpio)) { + dev_err(&client->dev, + "%s(): Could not obtain vsel1 GPIO: %ld\n", + __func__, PTR_ERR(tps->vsel1_gpio)); + return PTR_ERR(tps->vsel1_gpio); + } + + if (tps->vsel0_gpio != NULL && tps->vsel1_gpio != NULL) { tps->valid_gpios = true; /* diff --git a/include/linux/regulator/tps62360.h b/include/linux/regulator/tps62360.h index 94a90c06f1e5..398e74a1d941 100644 --- a/include/linux/regulator/tps62360.h +++ b/include/linux/regulator/tps62360.h @@ -19,10 +19,6 @@ * @en_discharge: Enable discharge the output capacitor via internal * register. * @en_internal_pulldn: internal pull down enable or not. - * @vsel0_gpio: Gpio number for vsel0. It should be -1 if this is tied with - * fixed logic. - * @vsel1_gpio: Gpio number for vsel1. It should be -1 if this is tied with - * fixed logic. * @vsel0_def_state: Default state of vsel0. 1 if it is high else 0. * @vsel1_def_state: Default state of vsel1. 1 if it is high else 0. */ @@ -30,8 +26,6 @@ struct tps62360_regulator_platform_data { struct regulator_init_data *reg_init_data; bool en_discharge; bool en_internal_pulldn; - int vsel0_gpio; - int vsel1_gpio; int vsel0_def_state; int vsel1_def_state; }; -- cgit v1.2.3 From 4570ddda43387e5a130dd85e71a1947b0c11da77 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 12 Mar 2021 14:04:07 +0100 Subject: powercap/drivers/dtpm: Encapsulate even more the code In order to increase the self-encapsulation of the dtpm generic code, the following changes are adding a power update ops to the dtpm ops. That allows the generic code to call directly the dtpm backend function to update the power values. The power update function does compute the power characteristics when the function is invoked. In the case of the CPUs, the power consumption depends on the number of online CPUs. The online CPUs mask is not up to date at CPUHP_AP_ONLINE_DYN state in the tear down callback. That is the reason why the online / offline are at separate state. As there is already an existing state for DTPM, this one is only moved to the DEAD state, so there is no addition of new state with these changes. The dtpm node is not removed when the cpu is unplugged. That simplifies the code for the next changes and results in a more self-encapsulated code. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/20210312130411.29833-1-daniel.lezcano@linaro.org --- drivers/powercap/dtpm.c | 54 ++++++++-------- drivers/powercap/dtpm_cpu.c | 148 ++++++++++++++++++++------------------------ include/linux/cpuhotplug.h | 2 +- include/linux/dtpm.h | 3 +- 4 files changed, 97 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index c2185ec5f887..58433b8ef9a1 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -116,8 +116,6 @@ static void __dtpm_sub_power(struct dtpm *dtpm) parent->power_limit -= dtpm->power_limit; parent = parent->parent; } - - __dtpm_rebalance_weight(root); } static void __dtpm_add_power(struct dtpm *dtpm) @@ -130,45 +128,45 @@ static void __dtpm_add_power(struct dtpm *dtpm) parent->power_limit += dtpm->power_limit; parent = parent->parent; } +} + +static int __dtpm_update_power(struct dtpm *dtpm) +{ + int ret; + + __dtpm_sub_power(dtpm); - __dtpm_rebalance_weight(root); + ret = dtpm->ops->update_power_uw(dtpm); + if (ret) + pr_err("Failed to update power for '%s': %d\n", + dtpm->zone.name, ret); + + if (!test_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags)) + dtpm->power_limit = dtpm->power_max; + + __dtpm_add_power(dtpm); + + if (root) + __dtpm_rebalance_weight(root); + + return ret; } /** * dtpm_update_power - Update the power on the dtpm * @dtpm: a pointer to a dtpm structure to update - * @power_min: a u64 representing the new power_min value - * @power_max: a u64 representing the new power_max value * * Function to update the power values of the dtpm node specified in * parameter. These new values will be propagated to the tree. * * Return: zero on success, -EINVAL if the values are inconsistent */ -int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max) +int dtpm_update_power(struct dtpm *dtpm) { - int ret = 0; + int ret; mutex_lock(&dtpm_lock); - - if (power_min == dtpm->power_min && power_max == dtpm->power_max) - goto unlock; - - if (power_max < power_min) { - ret = -EINVAL; - goto unlock; - } - - __dtpm_sub_power(dtpm); - - dtpm->power_min = power_min; - dtpm->power_max = power_max; - if (!test_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags)) - dtpm->power_limit = power_max; - - __dtpm_add_power(dtpm); - -unlock: + ret = __dtpm_update_power(dtpm); mutex_unlock(&dtpm_lock); return ret; @@ -436,6 +434,7 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) if (dtpm->ops && !(dtpm->ops->set_power_uw && dtpm->ops->get_power_uw && + dtpm->ops->update_power_uw && dtpm->ops->release)) return -EINVAL; @@ -455,7 +454,8 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) root = dtpm; } - __dtpm_add_power(dtpm); + if (dtpm->ops && !dtpm->ops->update_power_uw(dtpm)) + __dtpm_add_power(dtpm); pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n", dtpm->zone.name, dtpm->power_min, dtpm->power_max); diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 51c366938acd..f6076de39540 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -14,6 +14,8 @@ * The CPU hotplug is supported and the power numbers will be updated * if a CPU is hot plugged / unplugged. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include #include #include @@ -23,8 +25,6 @@ #include #include -static struct dtpm *__parent; - static DEFINE_PER_CPU(struct dtpm *, dtpm_per_cpu); struct dtpm_cpu { @@ -32,57 +32,16 @@ struct dtpm_cpu { int cpu; }; -/* - * When a new CPU is inserted at hotplug or boot time, add the power - * contribution and update the dtpm tree. - */ -static int power_add(struct dtpm *dtpm, struct em_perf_domain *em) -{ - u64 power_min, power_max; - - power_min = em->table[0].power; - power_min *= MICROWATT_PER_MILLIWATT; - power_min += dtpm->power_min; - - power_max = em->table[em->nr_perf_states - 1].power; - power_max *= MICROWATT_PER_MILLIWATT; - power_max += dtpm->power_max; - - return dtpm_update_power(dtpm, power_min, power_max); -} - -/* - * When a CPU is unplugged, remove its power contribution from the - * dtpm tree. - */ -static int power_sub(struct dtpm *dtpm, struct em_perf_domain *em) -{ - u64 power_min, power_max; - - power_min = em->table[0].power; - power_min *= MICROWATT_PER_MILLIWATT; - power_min = dtpm->power_min - power_min; - - power_max = em->table[em->nr_perf_states - 1].power; - power_max *= MICROWATT_PER_MILLIWATT; - power_max = dtpm->power_max - power_max; - - return dtpm_update_power(dtpm, power_min, power_max); -} - static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) { struct dtpm_cpu *dtpm_cpu = dtpm->private; - struct em_perf_domain *pd; + struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu); struct cpumask cpus; unsigned long freq; u64 power; int i, nr_cpus; - pd = em_cpu_get(dtpm_cpu->cpu); - cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); - nr_cpus = cpumask_weight(&cpus); for (i = 0; i < pd->nr_perf_states; i++) { @@ -113,6 +72,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) pd = em_cpu_get(dtpm_cpu->cpu); freq = cpufreq_quick_get(dtpm_cpu->cpu); + cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus)); nr_cpus = cpumask_weight(&cpus); @@ -128,6 +88,27 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) return 0; } +static int update_pd_power_uw(struct dtpm *dtpm) +{ + struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu); + struct cpumask cpus; + int nr_cpus; + + cpumask_and(&cpus, cpu_online_mask, to_cpumask(em->cpus)); + nr_cpus = cpumask_weight(&cpus); + + dtpm->power_min = em->table[0].power; + dtpm->power_min *= MICROWATT_PER_MILLIWATT; + dtpm->power_min *= nr_cpus; + + dtpm->power_max = em->table[em->nr_perf_states - 1].power; + dtpm->power_max *= MICROWATT_PER_MILLIWATT; + dtpm->power_max *= nr_cpus; + + return 0; +} + static void pd_release(struct dtpm *dtpm) { struct dtpm_cpu *dtpm_cpu = dtpm->private; @@ -139,39 +120,24 @@ static void pd_release(struct dtpm *dtpm) } static struct dtpm_ops dtpm_ops = { - .set_power_uw = set_pd_power_limit, - .get_power_uw = get_pd_power_uw, - .release = pd_release, + .set_power_uw = set_pd_power_limit, + .get_power_uw = get_pd_power_uw, + .update_power_uw = update_pd_power_uw, + .release = pd_release, }; static int cpuhp_dtpm_cpu_offline(unsigned int cpu) { - struct cpufreq_policy *policy; struct em_perf_domain *pd; struct dtpm *dtpm; - policy = cpufreq_cpu_get(cpu); - - if (!policy) - return 0; - pd = em_cpu_get(cpu); if (!pd) return -EINVAL; dtpm = per_cpu(dtpm_per_cpu, cpu); - power_sub(dtpm, pd); - - if (cpumask_weight(policy->cpus) != 1) - return 0; - - for_each_cpu(cpu, policy->related_cpus) - per_cpu(dtpm_per_cpu, cpu) = NULL; - - dtpm_unregister(dtpm); - - return 0; + return dtpm_update_power(dtpm); } static int cpuhp_dtpm_cpu_online(unsigned int cpu) @@ -184,7 +150,6 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu) int ret = -ENOMEM; policy = cpufreq_cpu_get(cpu); - if (!policy) return 0; @@ -194,7 +159,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu) dtpm = per_cpu(dtpm_per_cpu, cpu); if (dtpm) - return power_add(dtpm, pd); + return dtpm_update_power(dtpm); dtpm = dtpm_alloc(&dtpm_ops); if (!dtpm) @@ -210,27 +175,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu) for_each_cpu(cpu, policy->related_cpus) per_cpu(dtpm_per_cpu, cpu) = dtpm; - sprintf(name, "cpu%d", dtpm_cpu->cpu); + snprintf(name, sizeof(name), "cpu%d-cpufreq", dtpm_cpu->cpu); - ret = dtpm_register(name, dtpm, __parent); + ret = dtpm_register(name, dtpm, NULL); if (ret) goto out_kfree_dtpm_cpu; - ret = power_add(dtpm, pd); - if (ret) - goto out_dtpm_unregister; - ret = freq_qos_add_request(&policy->constraints, &dtpm_cpu->qos_req, FREQ_QOS_MAX, pd->table[pd->nr_perf_states - 1].frequency); if (ret) - goto out_power_sub; + goto out_dtpm_unregister; return 0; -out_power_sub: - power_sub(dtpm, pd); - out_dtpm_unregister: dtpm_unregister(dtpm); dtpm_cpu = NULL; @@ -248,10 +206,38 @@ out_kfree_dtpm: int dtpm_register_cpu(struct dtpm *parent) { - __parent = parent; + int ret; + + /* + * The callbacks at CPU hotplug time are calling + * dtpm_update_power() which in turns calls update_pd_power(). + * + * The function update_pd_power() uses the online mask to + * figure out the power consumption limits. + * + * At CPUHP_AP_ONLINE_DYN, the CPU is present in the CPU + * online mask when the cpuhp_dtpm_cpu_online function is + * called, but the CPU is still in the online mask for the + * tear down callback. So the power can not be updated when + * the CPU is unplugged. + * + * At CPUHP_AP_DTPM_CPU_DEAD, the situation is the opposite as + * above. The CPU online mask is not up to date when the CPU + * is plugged in. + * + * For this reason, we need to call the online and offline + * callbacks at different moments when the CPU online mask is + * consistent with the power numbers we want to update. + */ + ret = cpuhp_setup_state(CPUHP_AP_DTPM_CPU_DEAD, "dtpm_cpu:offline", + NULL, cpuhp_dtpm_cpu_offline); + if (ret < 0) + return ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "dtpm_cpu:online", + cpuhp_dtpm_cpu_online, NULL); + if (ret < 0) + return ret; - return cpuhp_setup_state(CPUHP_AP_DTPM_CPU_ONLINE, - "dtpm_cpu:online", - cpuhp_dtpm_cpu_online, - cpuhp_dtpm_cpu_offline); + return 0; } diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 832d8a74fa59..ad9a34a80440 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -97,6 +97,7 @@ enum cpuhp_state { CPUHP_LUSTRE_CFS_DEAD, CPUHP_AP_ARM_CACHE_B15_RAC_DEAD, CPUHP_PADATA_DEAD, + CPUHP_AP_DTPM_CPU_DEAD, CPUHP_WORKQUEUE_PREP, CPUHP_POWER_NUMA_PREPARE, CPUHP_HRTIMERS_PREPARE, @@ -242,7 +243,6 @@ enum cpuhp_state { CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30, CPUHP_AP_X86_HPET_ONLINE, CPUHP_AP_X86_KVM_CLK_ONLINE, - CPUHP_AP_DTPM_CPU_ONLINE, CPUHP_AP_ACTIVE, CPUHP_ONLINE, }; diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index e80a332e3d8a..acf8d3638988 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -29,6 +29,7 @@ struct dtpm { struct dtpm_ops { u64 (*set_power_uw)(struct dtpm *, u64); u64 (*get_power_uw)(struct dtpm *); + int (*update_power_uw)(struct dtpm *); void (*release)(struct dtpm *); }; @@ -62,7 +63,7 @@ static inline struct dtpm *to_dtpm(struct powercap_zone *zone) return container_of(zone, struct dtpm, zone); } -int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max); +int dtpm_update_power(struct dtpm *dtpm); int dtpm_release_zone(struct powercap_zone *pcz); -- cgit v1.2.3 From 7a89d7eacf8e84f2afb94db5ae9d9f9faa93f01c Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 12 Mar 2021 14:04:09 +0100 Subject: powercap/drivers/dtpm: Simplify the dtpm table The dtpm table is an array of pointers, that forces the user of the table to define initdata along with the declaration of the table entry. It is more efficient to create an array of dtpm structure, so the declaration of the table entry can be done by initializing the different fields. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/20210312130411.29833-3-daniel.lezcano@linaro.org --- drivers/powercap/dtpm.c | 4 ++-- drivers/powercap/dtpm_cpu.c | 4 +++- include/linux/dtpm.h | 20 +++++++++----------- 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index 58433b8ef9a1..8c032398f6ce 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -467,7 +467,7 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) static int __init dtpm_init(void) { - struct dtpm_descr **dtpm_descr; + struct dtpm_descr *dtpm_descr; pct = powercap_register_control_type(NULL, "dtpm", NULL); if (IS_ERR(pct)) { @@ -476,7 +476,7 @@ static int __init dtpm_init(void) } for_each_dtpm_table(dtpm_descr) - (*dtpm_descr)->init(*dtpm_descr); + dtpm_descr->init(); return 0; } diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index f6076de39540..98841524a782 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -204,7 +204,7 @@ out_kfree_dtpm: return ret; } -int dtpm_register_cpu(struct dtpm *parent) +static int __init dtpm_cpu_init(void) { int ret; @@ -241,3 +241,5 @@ int dtpm_register_cpu(struct dtpm *parent) return 0; } + +DTPM_DECLARE(dtpm_cpu, dtpm_cpu_init); diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index acf8d3638988..1e53db6bd5f9 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -33,25 +33,23 @@ struct dtpm_ops { void (*release)(struct dtpm *); }; -struct dtpm_descr; - -typedef int (*dtpm_init_t)(struct dtpm_descr *); +typedef int (*dtpm_init_t)(void); struct dtpm_descr { - struct dtpm *parent; - const char *name; dtpm_init_t init; }; /* Init section thermal table */ -extern struct dtpm_descr *__dtpm_table[]; -extern struct dtpm_descr *__dtpm_table_end[]; +extern struct dtpm_descr __dtpm_table[]; +extern struct dtpm_descr __dtpm_table_end[]; -#define DTPM_TABLE_ENTRY(name) \ - static typeof(name) *__dtpm_table_entry_##name \ - __used __section("__dtpm_table") = &name +#define DTPM_TABLE_ENTRY(name, __init) \ + static struct dtpm_descr __dtpm_table_entry_##name \ + __used __section("__dtpm_table") = { \ + .init = __init, \ + } -#define DTPM_DECLARE(name) DTPM_TABLE_ENTRY(name) +#define DTPM_DECLARE(name, init) DTPM_TABLE_ENTRY(name, init) #define for_each_dtpm_table(__dtpm) \ for (__dtpm = __dtpm_table; \ -- cgit v1.2.3 From d2cdc6adc30879d81160199fc7c6ab890fc4bd4c Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Fri, 12 Mar 2021 14:04:10 +0100 Subject: powercap/drivers/dtpm: Use container_of instead of a private data field The dtpm framework provides an API to allocate a dtpm node. However when a backend dtpm driver needs to allocate a dtpm node it must define its own structure and store the pointer of this structure in the private field of the dtpm structure. It is more elegant to use the container_of macro and add the dtpm structure inside the dtpm backend specific structure. The code will be able to deal properly with the dtpm structure as a generic entity, making all this even more self-encapsulated. The dtpm_alloc() function does no longer make sense as the dtpm structure will be allocated when allocating the device specific dtpm structure. The dtpm_init() is provided instead. Signed-off-by: Daniel Lezcano Reviewed-by: Lukasz Luba Link: https://lore.kernel.org/r/20210312130411.29833-4-daniel.lezcano@linaro.org --- drivers/powercap/dtpm.c | 18 ++++++----------- drivers/powercap/dtpm_cpu.c | 48 ++++++++++++++++++++++----------------------- include/linux/dtpm.h | 3 +-- 3 files changed, 30 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c index 8c032398f6ce..c7c5529b61eb 100644 --- a/drivers/powercap/dtpm.c +++ b/drivers/powercap/dtpm.c @@ -357,24 +357,18 @@ static struct powercap_zone_ops zone_ops = { }; /** - * dtpm_alloc - Allocate and initialize a dtpm struct - * @name: a string specifying the name of the node - * - * Return: a struct dtpm pointer, NULL in case of error + * dtpm_init - Allocate and initialize a dtpm struct + * @dtpm: The dtpm struct pointer to be initialized + * @ops: The dtpm device specific ops, NULL for a virtual node */ -struct dtpm *dtpm_alloc(struct dtpm_ops *ops) +void dtpm_init(struct dtpm *dtpm, struct dtpm_ops *ops) { - struct dtpm *dtpm; - - dtpm = kzalloc(sizeof(*dtpm), GFP_KERNEL); if (dtpm) { INIT_LIST_HEAD(&dtpm->children); INIT_LIST_HEAD(&dtpm->sibling); dtpm->weight = 1024; dtpm->ops = ops; } - - return dtpm; } /** @@ -465,7 +459,7 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent) return 0; } -static int __init dtpm_init(void) +static int __init init_dtpm(void) { struct dtpm_descr *dtpm_descr; @@ -480,4 +474,4 @@ static int __init dtpm_init(void) return 0; } -late_initcall(dtpm_init); +late_initcall(init_dtpm); diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index 98841524a782..2e21e4e2b01f 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -25,16 +25,22 @@ #include #include -static DEFINE_PER_CPU(struct dtpm *, dtpm_per_cpu); - struct dtpm_cpu { + struct dtpm dtpm; struct freq_qos_request qos_req; int cpu; }; +static DEFINE_PER_CPU(struct dtpm_cpu *, dtpm_per_cpu); + +static struct dtpm_cpu *to_dtpm_cpu(struct dtpm *dtpm) +{ + return container_of(dtpm, struct dtpm_cpu, dtpm); +} + static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) { - struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu); struct cpumask cpus; unsigned long freq; @@ -64,7 +70,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) static u64 get_pd_power_uw(struct dtpm *dtpm) { - struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); struct em_perf_domain *pd; struct cpumask cpus; unsigned long freq; @@ -90,7 +96,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm) static int update_pd_power_uw(struct dtpm *dtpm) { - struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu); struct cpumask cpus; int nr_cpus; @@ -111,7 +117,7 @@ static int update_pd_power_uw(struct dtpm *dtpm) static void pd_release(struct dtpm *dtpm) { - struct dtpm_cpu *dtpm_cpu = dtpm->private; + struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm); if (freq_qos_request_active(&dtpm_cpu->qos_req)) freq_qos_remove_request(&dtpm_cpu->qos_req); @@ -129,20 +135,19 @@ static struct dtpm_ops dtpm_ops = { static int cpuhp_dtpm_cpu_offline(unsigned int cpu) { struct em_perf_domain *pd; - struct dtpm *dtpm; + struct dtpm_cpu *dtpm_cpu; pd = em_cpu_get(cpu); if (!pd) return -EINVAL; - dtpm = per_cpu(dtpm_per_cpu, cpu); + dtpm_cpu = per_cpu(dtpm_per_cpu, cpu); - return dtpm_update_power(dtpm); + return dtpm_update_power(&dtpm_cpu->dtpm); } static int cpuhp_dtpm_cpu_online(unsigned int cpu) { - struct dtpm *dtpm; struct dtpm_cpu *dtpm_cpu; struct cpufreq_policy *policy; struct em_perf_domain *pd; @@ -157,27 +162,23 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu) if (!pd) return -EINVAL; - dtpm = per_cpu(dtpm_per_cpu, cpu); - if (dtpm) - return dtpm_update_power(dtpm); - - dtpm = dtpm_alloc(&dtpm_ops); - if (!dtpm) - return -EINVAL; + dtpm_cpu = per_cpu(dtpm_per_cpu, cpu); + if (dtpm_cpu) + return dtpm_update_power(&dtpm_cpu->dtpm); dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL); if (!dtpm_cpu) - goto out_kfree_dtpm; + return -ENOMEM; - dtpm->private = dtpm_cpu; + dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops); dtpm_cpu->cpu = cpu; for_each_cpu(cpu, policy->related_cpus) - per_cpu(dtpm_per_cpu, cpu) = dtpm; + per_cpu(dtpm_per_cpu, cpu) = dtpm_cpu; snprintf(name, sizeof(name), "cpu%d-cpufreq", dtpm_cpu->cpu); - ret = dtpm_register(name, dtpm, NULL); + ret = dtpm_register(name, &dtpm_cpu->dtpm, NULL); if (ret) goto out_kfree_dtpm_cpu; @@ -190,17 +191,14 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu) return 0; out_dtpm_unregister: - dtpm_unregister(dtpm); + dtpm_unregister(&dtpm_cpu->dtpm); dtpm_cpu = NULL; - dtpm = NULL; out_kfree_dtpm_cpu: for_each_cpu(cpu, policy->related_cpus) per_cpu(dtpm_per_cpu, cpu) = NULL; kfree(dtpm_cpu); -out_kfree_dtpm: - kfree(dtpm); return ret; } diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 1e53db6bd5f9..2890f6370eb9 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -23,7 +23,6 @@ struct dtpm { u64 power_max; u64 power_min; int weight; - void *private; }; struct dtpm_ops { @@ -65,7 +64,7 @@ int dtpm_update_power(struct dtpm *dtpm); int dtpm_release_zone(struct powercap_zone *pcz); -struct dtpm *dtpm_alloc(struct dtpm_ops *ops); +void dtpm_init(struct dtpm *dtpm, struct dtpm_ops *ops); void dtpm_unregister(struct dtpm *dtpm); -- cgit v1.2.3 From 3b13c168186c115501ee7d194460ba2f8c825155 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Thu, 21 Oct 2021 14:30:51 +0100 Subject: percpu_ref: percpu_ref_tryget_live() version holding RCU Add percpu_ref_tryget_live_rcu(), which is a version of percpu_ref_tryget_live() but the user is responsible for enclosing it in a RCU read lock section. Signed-off-by: Pavel Begunkov Acked-by: Dennis Zhou Link: https://lore.kernel.org/r/3066500d7a6eb3e03f10adf98b87fdb3b1c49db8.1634822969.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- include/linux/percpu-refcount.h | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index ae16a9856305..b31d3f3312ce 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -266,6 +266,28 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) return percpu_ref_tryget_many(ref, 1); } +/** + * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the + * caller is responsible for taking RCU. + * + * This function is safe to call as long as @ref is between init and exit. + */ +static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref) +{ + unsigned long __percpu *percpu_count; + bool ret = false; + + WARN_ON_ONCE(!rcu_read_lock_held()); + + if (likely(__ref_is_percpu(ref, &percpu_count))) { + this_cpu_inc(*percpu_count); + ret = true; + } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { + ret = atomic_long_inc_not_zero(&ref->data->count); + } + return ret; +} + /** * percpu_ref_tryget_live - try to increment a live percpu refcount * @ref: percpu_ref to try-get @@ -283,20 +305,11 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref) */ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref) { - unsigned long __percpu *percpu_count; bool ret = false; rcu_read_lock(); - - if (__ref_is_percpu(ref, &percpu_count)) { - this_cpu_inc(*percpu_count); - ret = true; - } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) { - ret = atomic_long_inc_not_zero(&ref->data->count); - } - + ret = percpu_ref_tryget_live_rcu(ref); rcu_read_unlock(); - return ret; } -- cgit v1.2.3 From f059a1d2e23a165bf86e33673c6a7535a08c6341 Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Wed, 22 Sep 2021 20:37:08 +0800 Subject: block: Add invalidate_disk() helper to invalidate the gendisk To hide internal implementation and simplify some driver code, this adds a helper to invalidate the gendisk. It will clean the gendisk's associated buffer/page caches and reset its internal states. Signed-off-by: Xie Yongji Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20210922123711.187-2-xieyongji@bytedance.com Signed-off-by: Jens Axboe --- block/genhd.c | 20 ++++++++++++++++++++ include/linux/genhd.h | 2 ++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 80943c123c3e..64f83c4aee99 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -624,6 +624,26 @@ void del_gendisk(struct gendisk *disk) } EXPORT_SYMBOL(del_gendisk); +/** + * invalidate_disk - invalidate the disk + * @disk: the struct gendisk to invalidate + * + * A helper to invalidates the disk. It will clean the disk's associated + * buffer/page caches and reset its internal states so that the disk + * can be reused by the drivers. + * + * Context: can sleep + */ +void invalidate_disk(struct gendisk *disk) +{ + struct block_device *bdev = disk->part0; + + invalidate_bdev(bdev); + bdev->bd_inode->i_mapping->wb_err = 0; + set_capacity(disk, 0); +} +EXPORT_SYMBOL(invalidate_disk); + /* sysfs access to bad-blocks list. */ static ssize_t disk_badblocks_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c70bc5fce4db..13f313ab99e7 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -213,6 +213,8 @@ static inline int add_disk(struct gendisk *disk) } extern void del_gendisk(struct gendisk *gp); +void invalidate_disk(struct gendisk *disk); + void set_disk_ro(struct gendisk *disk, bool read_only); static inline int get_disk_ro(struct gendisk *disk) -- cgit v1.2.3 From 1e8d44bddf57f6d878e083f281a34d5c88feb7db Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Oct 2021 11:04:51 -0700 Subject: blk-crypto: rename keyslot-manager files to blk-crypto-profile In preparation for renaming struct blk_keyslot_manager to struct blk_crypto_profile, rename the keyslot-manager.h and keyslot-manager.c source files. Renaming these files separately before making a lot of changes to their contents makes it easier for git to understand that they were renamed. Acked-by: Ulf Hansson # For MMC Reviewed-by: Christoph Hellwig Reviewed-by: Mike Snitzer Reviewed-by: Martin K. Petersen Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20211018180453.40441-3-ebiggers@kernel.org Signed-off-by: Jens Axboe --- block/Makefile | 2 +- block/blk-crypto-fallback.c | 2 +- block/blk-crypto-profile.c | 579 +++++++++++++++++++++++++++++++++++++ block/blk-crypto.c | 2 +- block/keyslot-manager.c | 579 ------------------------------------- drivers/md/dm-core.h | 2 +- drivers/md/dm.c | 2 +- drivers/mmc/host/cqhci-crypto.c | 2 +- drivers/scsi/ufs/ufshcd.h | 2 +- include/linux/blk-crypto-profile.h | 120 ++++++++ include/linux/keyslot-manager.h | 120 -------- include/linux/mmc/host.h | 2 +- 12 files changed, 707 insertions(+), 707 deletions(-) create mode 100644 block/blk-crypto-profile.c delete mode 100644 block/keyslot-manager.c create mode 100644 include/linux/blk-crypto-profile.h delete mode 100644 include/linux/keyslot-manager.h (limited to 'include/linux') diff --git a/block/Makefile b/block/Makefile index 74df168729ec..602f7f47b7b6 100644 --- a/block/Makefile +++ b/block/Makefile @@ -36,6 +36,6 @@ obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o obj-$(CONFIG_BLK_PM) += blk-pm.o -obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o blk-crypto.o +obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += blk-crypto.o blk-crypto-profile.o obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED) += holder.o diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 1bcc1a151424..08bfea292c75 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -12,9 +12,9 @@ #include #include #include +#include #include #include -#include #include #include #include diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c new file mode 100644 index 000000000000..1a235fa3c3e8 --- /dev/null +++ b/block/blk-crypto-profile.c @@ -0,0 +1,579 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2019 Google LLC + */ + +/** + * DOC: The Keyslot Manager + * + * Many devices with inline encryption support have a limited number of "slots" + * into which encryption contexts may be programmed, and requests can be tagged + * with a slot number to specify the key to use for en/decryption. + * + * As the number of slots is limited, and programming keys is expensive on + * many inline encryption hardware, we don't want to program the same key into + * multiple slots - if multiple requests are using the same key, we want to + * program just one slot with that key and use that slot for all requests. + * + * The keyslot manager manages these keyslots appropriately, and also acts as + * an abstraction between the inline encryption hardware and the upper layers. + * + * Lower layer devices will set up a keyslot manager in their request queue + * and tell it how to perform device specific operations like programming/ + * evicting keys from keyslots. + * + * Upper layers will call blk_ksm_get_slot_for_key() to program a + * key into some slot in the inline encryption hardware. + */ + +#define pr_fmt(fmt) "blk-crypto: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +struct blk_ksm_keyslot { + atomic_t slot_refs; + struct list_head idle_slot_node; + struct hlist_node hash_node; + const struct blk_crypto_key *key; + struct blk_keyslot_manager *ksm; +}; + +static inline void blk_ksm_hw_enter(struct blk_keyslot_manager *ksm) +{ + /* + * Calling into the driver requires ksm->lock held and the device + * resumed. But we must resume the device first, since that can acquire + * and release ksm->lock via blk_ksm_reprogram_all_keys(). + */ + if (ksm->dev) + pm_runtime_get_sync(ksm->dev); + down_write(&ksm->lock); +} + +static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm) +{ + up_write(&ksm->lock); + if (ksm->dev) + pm_runtime_put_sync(ksm->dev); +} + +static inline bool blk_ksm_is_passthrough(struct blk_keyslot_manager *ksm) +{ + return ksm->num_slots == 0; +} + +/** + * blk_ksm_init() - Initialize a keyslot manager + * @ksm: The keyslot_manager to initialize. + * @num_slots: The number of key slots to manage. + * + * Allocate memory for keyslots and initialize a keyslot manager. Called by + * e.g. storage drivers to set up a keyslot manager in their request_queue. + * + * Return: 0 on success, or else a negative error code. + */ +int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) +{ + unsigned int slot; + unsigned int i; + unsigned int slot_hashtable_size; + + memset(ksm, 0, sizeof(*ksm)); + + if (num_slots == 0) + return -EINVAL; + + ksm->slots = kvcalloc(num_slots, sizeof(ksm->slots[0]), GFP_KERNEL); + if (!ksm->slots) + return -ENOMEM; + + ksm->num_slots = num_slots; + + init_rwsem(&ksm->lock); + + init_waitqueue_head(&ksm->idle_slots_wait_queue); + INIT_LIST_HEAD(&ksm->idle_slots); + + for (slot = 0; slot < num_slots; slot++) { + ksm->slots[slot].ksm = ksm; + list_add_tail(&ksm->slots[slot].idle_slot_node, + &ksm->idle_slots); + } + + spin_lock_init(&ksm->idle_slots_lock); + + slot_hashtable_size = roundup_pow_of_two(num_slots); + /* + * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2 + * buckets. This only makes a difference when there is only 1 keyslot. + */ + if (slot_hashtable_size < 2) + slot_hashtable_size = 2; + + ksm->log_slot_ht_size = ilog2(slot_hashtable_size); + ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size, + sizeof(ksm->slot_hashtable[0]), + GFP_KERNEL); + if (!ksm->slot_hashtable) + goto err_destroy_ksm; + for (i = 0; i < slot_hashtable_size; i++) + INIT_HLIST_HEAD(&ksm->slot_hashtable[i]); + + return 0; + +err_destroy_ksm: + blk_ksm_destroy(ksm); + return -ENOMEM; +} +EXPORT_SYMBOL_GPL(blk_ksm_init); + +static void blk_ksm_destroy_callback(void *ksm) +{ + blk_ksm_destroy(ksm); +} + +/** + * devm_blk_ksm_init() - Resource-managed blk_ksm_init() + * @dev: The device which owns the blk_keyslot_manager. + * @ksm: The blk_keyslot_manager to initialize. + * @num_slots: The number of key slots to manage. + * + * Like blk_ksm_init(), but causes blk_ksm_destroy() to be called automatically + * on driver detach. + * + * Return: 0 on success, or else a negative error code. + */ +int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, + unsigned int num_slots) +{ + int err = blk_ksm_init(ksm, num_slots); + + if (err) + return err; + + return devm_add_action_or_reset(dev, blk_ksm_destroy_callback, ksm); +} +EXPORT_SYMBOL_GPL(devm_blk_ksm_init); + +static inline struct hlist_head * +blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + return &ksm->slot_hashtable[hash_ptr(key, ksm->log_slot_ht_size)]; +} + +static void blk_ksm_remove_slot_from_lru_list(struct blk_ksm_keyslot *slot) +{ + struct blk_keyslot_manager *ksm = slot->ksm; + unsigned long flags; + + spin_lock_irqsave(&ksm->idle_slots_lock, flags); + list_del(&slot->idle_slot_node); + spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); +} + +static struct blk_ksm_keyslot *blk_ksm_find_keyslot( + struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + const struct hlist_head *head = blk_ksm_hash_bucket_for_key(ksm, key); + struct blk_ksm_keyslot *slotp; + + hlist_for_each_entry(slotp, head, hash_node) { + if (slotp->key == key) + return slotp; + } + return NULL; +} + +static struct blk_ksm_keyslot *blk_ksm_find_and_grab_keyslot( + struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + struct blk_ksm_keyslot *slot; + + slot = blk_ksm_find_keyslot(ksm, key); + if (!slot) + return NULL; + if (atomic_inc_return(&slot->slot_refs) == 1) { + /* Took first reference to this slot; remove it from LRU list */ + blk_ksm_remove_slot_from_lru_list(slot); + } + return slot; +} + +unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot) +{ + return slot - slot->ksm->slots; +} +EXPORT_SYMBOL_GPL(blk_ksm_get_slot_idx); + +/** + * blk_ksm_get_slot_for_key() - Program a key into a keyslot. + * @ksm: The keyslot manager to program the key into. + * @key: Pointer to the key object to program, including the raw key, crypto + * mode, and data unit size. + * @slot_ptr: A pointer to return the pointer of the allocated keyslot. + * + * Get a keyslot that's been programmed with the specified key. If one already + * exists, return it with incremented refcount. Otherwise, wait for a keyslot + * to become idle and program it. + * + * Context: Process context. Takes and releases ksm->lock. + * Return: BLK_STS_OK on success (and keyslot is set to the pointer of the + * allocated keyslot), or some other blk_status_t otherwise (and + * keyslot is set to NULL). + */ +blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + struct blk_ksm_keyslot **slot_ptr) +{ + struct blk_ksm_keyslot *slot; + int slot_idx; + int err; + + *slot_ptr = NULL; + + if (blk_ksm_is_passthrough(ksm)) + return BLK_STS_OK; + + down_read(&ksm->lock); + slot = blk_ksm_find_and_grab_keyslot(ksm, key); + up_read(&ksm->lock); + if (slot) + goto success; + + for (;;) { + blk_ksm_hw_enter(ksm); + slot = blk_ksm_find_and_grab_keyslot(ksm, key); + if (slot) { + blk_ksm_hw_exit(ksm); + goto success; + } + + /* + * If we're here, that means there wasn't a slot that was + * already programmed with the key. So try to program it. + */ + if (!list_empty(&ksm->idle_slots)) + break; + + blk_ksm_hw_exit(ksm); + wait_event(ksm->idle_slots_wait_queue, + !list_empty(&ksm->idle_slots)); + } + + slot = list_first_entry(&ksm->idle_slots, struct blk_ksm_keyslot, + idle_slot_node); + slot_idx = blk_ksm_get_slot_idx(slot); + + err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot_idx); + if (err) { + wake_up(&ksm->idle_slots_wait_queue); + blk_ksm_hw_exit(ksm); + return errno_to_blk_status(err); + } + + /* Move this slot to the hash list for the new key. */ + if (slot->key) + hlist_del(&slot->hash_node); + slot->key = key; + hlist_add_head(&slot->hash_node, blk_ksm_hash_bucket_for_key(ksm, key)); + + atomic_set(&slot->slot_refs, 1); + + blk_ksm_remove_slot_from_lru_list(slot); + + blk_ksm_hw_exit(ksm); +success: + *slot_ptr = slot; + return BLK_STS_OK; +} + +/** + * blk_ksm_put_slot() - Release a reference to a slot + * @slot: The keyslot to release the reference of. + * + * Context: Any context. + */ +void blk_ksm_put_slot(struct blk_ksm_keyslot *slot) +{ + struct blk_keyslot_manager *ksm; + unsigned long flags; + + if (!slot) + return; + + ksm = slot->ksm; + + if (atomic_dec_and_lock_irqsave(&slot->slot_refs, + &ksm->idle_slots_lock, flags)) { + list_add_tail(&slot->idle_slot_node, &ksm->idle_slots); + spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); + wake_up(&ksm->idle_slots_wait_queue); + } +} + +/** + * blk_ksm_crypto_cfg_supported() - Find out if a crypto configuration is + * supported by a ksm. + * @ksm: The keyslot manager to check + * @cfg: The crypto configuration to check for. + * + * Checks for crypto_mode/data unit size/dun bytes support. + * + * Return: Whether or not this ksm supports the specified crypto config. + */ +bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, + const struct blk_crypto_config *cfg) +{ + if (!ksm) + return false; + if (!(ksm->crypto_modes_supported[cfg->crypto_mode] & + cfg->data_unit_size)) + return false; + if (ksm->max_dun_bytes_supported < cfg->dun_bytes) + return false; + return true; +} + +/** + * blk_ksm_evict_key() - Evict a key from the lower layer device. + * @ksm: The keyslot manager to evict from + * @key: The key to evict + * + * Find the keyslot that the specified key was programmed into, and evict that + * slot from the lower layer device. The slot must not be in use by any + * in-flight IO when this function is called. + * + * Context: Process context. Takes and releases ksm->lock. + * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY + * if the keyslot is still in use, or another -errno value on other + * error. + */ +int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key) +{ + struct blk_ksm_keyslot *slot; + int err = 0; + + if (blk_ksm_is_passthrough(ksm)) { + if (ksm->ksm_ll_ops.keyslot_evict) { + blk_ksm_hw_enter(ksm); + err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1); + blk_ksm_hw_exit(ksm); + return err; + } + return 0; + } + + blk_ksm_hw_enter(ksm); + slot = blk_ksm_find_keyslot(ksm, key); + if (!slot) + goto out_unlock; + + if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) { + err = -EBUSY; + goto out_unlock; + } + err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, + blk_ksm_get_slot_idx(slot)); + if (err) + goto out_unlock; + + hlist_del(&slot->hash_node); + slot->key = NULL; + err = 0; +out_unlock: + blk_ksm_hw_exit(ksm); + return err; +} + +/** + * blk_ksm_reprogram_all_keys() - Re-program all keyslots. + * @ksm: The keyslot manager + * + * Re-program all keyslots that are supposed to have a key programmed. This is + * intended only for use by drivers for hardware that loses its keys on reset. + * + * Context: Process context. Takes and releases ksm->lock. + */ +void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm) +{ + unsigned int slot; + + if (blk_ksm_is_passthrough(ksm)) + return; + + /* This is for device initialization, so don't resume the device */ + down_write(&ksm->lock); + for (slot = 0; slot < ksm->num_slots; slot++) { + const struct blk_crypto_key *key = ksm->slots[slot].key; + int err; + + if (!key) + continue; + + err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot); + WARN_ON(err); + } + up_write(&ksm->lock); +} +EXPORT_SYMBOL_GPL(blk_ksm_reprogram_all_keys); + +void blk_ksm_destroy(struct blk_keyslot_manager *ksm) +{ + if (!ksm) + return; + kvfree(ksm->slot_hashtable); + kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots); + memzero_explicit(ksm, sizeof(*ksm)); +} +EXPORT_SYMBOL_GPL(blk_ksm_destroy); + +bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) +{ + if (blk_integrity_queue_supports_integrity(q)) { + pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); + return false; + } + q->ksm = ksm; + return true; +} +EXPORT_SYMBOL_GPL(blk_ksm_register); + +void blk_ksm_unregister(struct request_queue *q) +{ + q->ksm = NULL; +} + +/** + * blk_ksm_intersect_modes() - restrict supported modes by child device + * @parent: The keyslot manager for parent device + * @child: The keyslot manager for child device, or NULL + * + * Clear any crypto mode support bits in @parent that aren't set in @child. + * If @child is NULL, then all parent bits are cleared. + * + * Only use this when setting up the keyslot manager for a layered device, + * before it's been exposed yet. + */ +void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, + const struct blk_keyslot_manager *child) +{ + if (child) { + unsigned int i; + + parent->max_dun_bytes_supported = + min(parent->max_dun_bytes_supported, + child->max_dun_bytes_supported); + for (i = 0; i < ARRAY_SIZE(child->crypto_modes_supported); + i++) { + parent->crypto_modes_supported[i] &= + child->crypto_modes_supported[i]; + } + } else { + parent->max_dun_bytes_supported = 0; + memset(parent->crypto_modes_supported, 0, + sizeof(parent->crypto_modes_supported)); + } +} +EXPORT_SYMBOL_GPL(blk_ksm_intersect_modes); + +/** + * blk_ksm_is_superset() - Check if a KSM supports a superset of crypto modes + * and DUN bytes that another KSM supports. Here, + * "superset" refers to the mathematical meaning of the + * word - i.e. if two KSMs have the *same* capabilities, + * they *are* considered supersets of each other. + * @ksm_superset: The KSM that we want to verify is a superset + * @ksm_subset: The KSM that we want to verify is a subset + * + * Return: True if @ksm_superset supports a superset of the crypto modes and DUN + * bytes that @ksm_subset supports. + */ +bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, + struct blk_keyslot_manager *ksm_subset) +{ + int i; + + if (!ksm_subset) + return true; + + if (!ksm_superset) + return false; + + for (i = 0; i < ARRAY_SIZE(ksm_superset->crypto_modes_supported); i++) { + if (ksm_subset->crypto_modes_supported[i] & + (~ksm_superset->crypto_modes_supported[i])) { + return false; + } + } + + if (ksm_subset->max_dun_bytes_supported > + ksm_superset->max_dun_bytes_supported) { + return false; + } + + return true; +} +EXPORT_SYMBOL_GPL(blk_ksm_is_superset); + +/** + * blk_ksm_update_capabilities() - Update the restrictions of a KSM to those of + * another KSM + * @target_ksm: The KSM whose restrictions to update. + * @reference_ksm: The KSM to whose restrictions this function will update + * @target_ksm's restrictions to. + * + * Blk-crypto requires that crypto capabilities that were + * advertised when a bio was created continue to be supported by the + * device until that bio is ended. This is turn means that a device cannot + * shrink its advertised crypto capabilities without any explicit + * synchronization with upper layers. So if there's no such explicit + * synchronization, @reference_ksm must support all the crypto capabilities that + * @target_ksm does + * (i.e. we need blk_ksm_is_superset(@reference_ksm, @target_ksm) == true). + * + * Note also that as long as the crypto capabilities are being expanded, the + * order of updates becoming visible is not important because it's alright + * for blk-crypto to see stale values - they only cause blk-crypto to + * believe that a crypto capability isn't supported when it actually is (which + * might result in blk-crypto-fallback being used if available, or the bio being + * failed). + */ +void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, + struct blk_keyslot_manager *reference_ksm) +{ + memcpy(target_ksm->crypto_modes_supported, + reference_ksm->crypto_modes_supported, + sizeof(target_ksm->crypto_modes_supported)); + + target_ksm->max_dun_bytes_supported = + reference_ksm->max_dun_bytes_supported; +} +EXPORT_SYMBOL_GPL(blk_ksm_update_capabilities); + +/** + * blk_ksm_init_passthrough() - Init a passthrough keyslot manager + * @ksm: The keyslot manager to init + * + * Initialize a passthrough keyslot manager. + * Called by e.g. storage drivers to set up a keyslot manager in their + * request_queue, when the storage driver wants to manage its keys by itself. + * This is useful for inline encryption hardware that doesn't have the concept + * of keyslots, and for layered devices. + */ +void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm) +{ + memset(ksm, 0, sizeof(*ksm)); + init_rwsem(&ksm->lock); +} +EXPORT_SYMBOL_GPL(blk_ksm_init_passthrough); diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 8f53f4a1f9e2..76ce7a5d2676 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -11,7 +11,7 @@ #include #include -#include +#include #include #include diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c deleted file mode 100644 index 1792159d12d1..000000000000 --- a/block/keyslot-manager.c +++ /dev/null @@ -1,579 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright 2019 Google LLC - */ - -/** - * DOC: The Keyslot Manager - * - * Many devices with inline encryption support have a limited number of "slots" - * into which encryption contexts may be programmed, and requests can be tagged - * with a slot number to specify the key to use for en/decryption. - * - * As the number of slots is limited, and programming keys is expensive on - * many inline encryption hardware, we don't want to program the same key into - * multiple slots - if multiple requests are using the same key, we want to - * program just one slot with that key and use that slot for all requests. - * - * The keyslot manager manages these keyslots appropriately, and also acts as - * an abstraction between the inline encryption hardware and the upper layers. - * - * Lower layer devices will set up a keyslot manager in their request queue - * and tell it how to perform device specific operations like programming/ - * evicting keys from keyslots. - * - * Upper layers will call blk_ksm_get_slot_for_key() to program a - * key into some slot in the inline encryption hardware. - */ - -#define pr_fmt(fmt) "blk-crypto: " fmt - -#include -#include -#include -#include -#include -#include -#include -#include - -struct blk_ksm_keyslot { - atomic_t slot_refs; - struct list_head idle_slot_node; - struct hlist_node hash_node; - const struct blk_crypto_key *key; - struct blk_keyslot_manager *ksm; -}; - -static inline void blk_ksm_hw_enter(struct blk_keyslot_manager *ksm) -{ - /* - * Calling into the driver requires ksm->lock held and the device - * resumed. But we must resume the device first, since that can acquire - * and release ksm->lock via blk_ksm_reprogram_all_keys(). - */ - if (ksm->dev) - pm_runtime_get_sync(ksm->dev); - down_write(&ksm->lock); -} - -static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm) -{ - up_write(&ksm->lock); - if (ksm->dev) - pm_runtime_put_sync(ksm->dev); -} - -static inline bool blk_ksm_is_passthrough(struct blk_keyslot_manager *ksm) -{ - return ksm->num_slots == 0; -} - -/** - * blk_ksm_init() - Initialize a keyslot manager - * @ksm: The keyslot_manager to initialize. - * @num_slots: The number of key slots to manage. - * - * Allocate memory for keyslots and initialize a keyslot manager. Called by - * e.g. storage drivers to set up a keyslot manager in their request_queue. - * - * Return: 0 on success, or else a negative error code. - */ -int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) -{ - unsigned int slot; - unsigned int i; - unsigned int slot_hashtable_size; - - memset(ksm, 0, sizeof(*ksm)); - - if (num_slots == 0) - return -EINVAL; - - ksm->slots = kvcalloc(num_slots, sizeof(ksm->slots[0]), GFP_KERNEL); - if (!ksm->slots) - return -ENOMEM; - - ksm->num_slots = num_slots; - - init_rwsem(&ksm->lock); - - init_waitqueue_head(&ksm->idle_slots_wait_queue); - INIT_LIST_HEAD(&ksm->idle_slots); - - for (slot = 0; slot < num_slots; slot++) { - ksm->slots[slot].ksm = ksm; - list_add_tail(&ksm->slots[slot].idle_slot_node, - &ksm->idle_slots); - } - - spin_lock_init(&ksm->idle_slots_lock); - - slot_hashtable_size = roundup_pow_of_two(num_slots); - /* - * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2 - * buckets. This only makes a difference when there is only 1 keyslot. - */ - if (slot_hashtable_size < 2) - slot_hashtable_size = 2; - - ksm->log_slot_ht_size = ilog2(slot_hashtable_size); - ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size, - sizeof(ksm->slot_hashtable[0]), - GFP_KERNEL); - if (!ksm->slot_hashtable) - goto err_destroy_ksm; - for (i = 0; i < slot_hashtable_size; i++) - INIT_HLIST_HEAD(&ksm->slot_hashtable[i]); - - return 0; - -err_destroy_ksm: - blk_ksm_destroy(ksm); - return -ENOMEM; -} -EXPORT_SYMBOL_GPL(blk_ksm_init); - -static void blk_ksm_destroy_callback(void *ksm) -{ - blk_ksm_destroy(ksm); -} - -/** - * devm_blk_ksm_init() - Resource-managed blk_ksm_init() - * @dev: The device which owns the blk_keyslot_manager. - * @ksm: The blk_keyslot_manager to initialize. - * @num_slots: The number of key slots to manage. - * - * Like blk_ksm_init(), but causes blk_ksm_destroy() to be called automatically - * on driver detach. - * - * Return: 0 on success, or else a negative error code. - */ -int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, - unsigned int num_slots) -{ - int err = blk_ksm_init(ksm, num_slots); - - if (err) - return err; - - return devm_add_action_or_reset(dev, blk_ksm_destroy_callback, ksm); -} -EXPORT_SYMBOL_GPL(devm_blk_ksm_init); - -static inline struct hlist_head * -blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) -{ - return &ksm->slot_hashtable[hash_ptr(key, ksm->log_slot_ht_size)]; -} - -static void blk_ksm_remove_slot_from_lru_list(struct blk_ksm_keyslot *slot) -{ - struct blk_keyslot_manager *ksm = slot->ksm; - unsigned long flags; - - spin_lock_irqsave(&ksm->idle_slots_lock, flags); - list_del(&slot->idle_slot_node); - spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); -} - -static struct blk_ksm_keyslot *blk_ksm_find_keyslot( - struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) -{ - const struct hlist_head *head = blk_ksm_hash_bucket_for_key(ksm, key); - struct blk_ksm_keyslot *slotp; - - hlist_for_each_entry(slotp, head, hash_node) { - if (slotp->key == key) - return slotp; - } - return NULL; -} - -static struct blk_ksm_keyslot *blk_ksm_find_and_grab_keyslot( - struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) -{ - struct blk_ksm_keyslot *slot; - - slot = blk_ksm_find_keyslot(ksm, key); - if (!slot) - return NULL; - if (atomic_inc_return(&slot->slot_refs) == 1) { - /* Took first reference to this slot; remove it from LRU list */ - blk_ksm_remove_slot_from_lru_list(slot); - } - return slot; -} - -unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot) -{ - return slot - slot->ksm->slots; -} -EXPORT_SYMBOL_GPL(blk_ksm_get_slot_idx); - -/** - * blk_ksm_get_slot_for_key() - Program a key into a keyslot. - * @ksm: The keyslot manager to program the key into. - * @key: Pointer to the key object to program, including the raw key, crypto - * mode, and data unit size. - * @slot_ptr: A pointer to return the pointer of the allocated keyslot. - * - * Get a keyslot that's been programmed with the specified key. If one already - * exists, return it with incremented refcount. Otherwise, wait for a keyslot - * to become idle and program it. - * - * Context: Process context. Takes and releases ksm->lock. - * Return: BLK_STS_OK on success (and keyslot is set to the pointer of the - * allocated keyslot), or some other blk_status_t otherwise (and - * keyslot is set to NULL). - */ -blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - struct blk_ksm_keyslot **slot_ptr) -{ - struct blk_ksm_keyslot *slot; - int slot_idx; - int err; - - *slot_ptr = NULL; - - if (blk_ksm_is_passthrough(ksm)) - return BLK_STS_OK; - - down_read(&ksm->lock); - slot = blk_ksm_find_and_grab_keyslot(ksm, key); - up_read(&ksm->lock); - if (slot) - goto success; - - for (;;) { - blk_ksm_hw_enter(ksm); - slot = blk_ksm_find_and_grab_keyslot(ksm, key); - if (slot) { - blk_ksm_hw_exit(ksm); - goto success; - } - - /* - * If we're here, that means there wasn't a slot that was - * already programmed with the key. So try to program it. - */ - if (!list_empty(&ksm->idle_slots)) - break; - - blk_ksm_hw_exit(ksm); - wait_event(ksm->idle_slots_wait_queue, - !list_empty(&ksm->idle_slots)); - } - - slot = list_first_entry(&ksm->idle_slots, struct blk_ksm_keyslot, - idle_slot_node); - slot_idx = blk_ksm_get_slot_idx(slot); - - err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot_idx); - if (err) { - wake_up(&ksm->idle_slots_wait_queue); - blk_ksm_hw_exit(ksm); - return errno_to_blk_status(err); - } - - /* Move this slot to the hash list for the new key. */ - if (slot->key) - hlist_del(&slot->hash_node); - slot->key = key; - hlist_add_head(&slot->hash_node, blk_ksm_hash_bucket_for_key(ksm, key)); - - atomic_set(&slot->slot_refs, 1); - - blk_ksm_remove_slot_from_lru_list(slot); - - blk_ksm_hw_exit(ksm); -success: - *slot_ptr = slot; - return BLK_STS_OK; -} - -/** - * blk_ksm_put_slot() - Release a reference to a slot - * @slot: The keyslot to release the reference of. - * - * Context: Any context. - */ -void blk_ksm_put_slot(struct blk_ksm_keyslot *slot) -{ - struct blk_keyslot_manager *ksm; - unsigned long flags; - - if (!slot) - return; - - ksm = slot->ksm; - - if (atomic_dec_and_lock_irqsave(&slot->slot_refs, - &ksm->idle_slots_lock, flags)) { - list_add_tail(&slot->idle_slot_node, &ksm->idle_slots); - spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); - wake_up(&ksm->idle_slots_wait_queue); - } -} - -/** - * blk_ksm_crypto_cfg_supported() - Find out if a crypto configuration is - * supported by a ksm. - * @ksm: The keyslot manager to check - * @cfg: The crypto configuration to check for. - * - * Checks for crypto_mode/data unit size/dun bytes support. - * - * Return: Whether or not this ksm supports the specified crypto config. - */ -bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, - const struct blk_crypto_config *cfg) -{ - if (!ksm) - return false; - if (!(ksm->crypto_modes_supported[cfg->crypto_mode] & - cfg->data_unit_size)) - return false; - if (ksm->max_dun_bytes_supported < cfg->dun_bytes) - return false; - return true; -} - -/** - * blk_ksm_evict_key() - Evict a key from the lower layer device. - * @ksm: The keyslot manager to evict from - * @key: The key to evict - * - * Find the keyslot that the specified key was programmed into, and evict that - * slot from the lower layer device. The slot must not be in use by any - * in-flight IO when this function is called. - * - * Context: Process context. Takes and releases ksm->lock. - * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY - * if the keyslot is still in use, or another -errno value on other - * error. - */ -int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) -{ - struct blk_ksm_keyslot *slot; - int err = 0; - - if (blk_ksm_is_passthrough(ksm)) { - if (ksm->ksm_ll_ops.keyslot_evict) { - blk_ksm_hw_enter(ksm); - err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1); - blk_ksm_hw_exit(ksm); - return err; - } - return 0; - } - - blk_ksm_hw_enter(ksm); - slot = blk_ksm_find_keyslot(ksm, key); - if (!slot) - goto out_unlock; - - if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) { - err = -EBUSY; - goto out_unlock; - } - err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, - blk_ksm_get_slot_idx(slot)); - if (err) - goto out_unlock; - - hlist_del(&slot->hash_node); - slot->key = NULL; - err = 0; -out_unlock: - blk_ksm_hw_exit(ksm); - return err; -} - -/** - * blk_ksm_reprogram_all_keys() - Re-program all keyslots. - * @ksm: The keyslot manager - * - * Re-program all keyslots that are supposed to have a key programmed. This is - * intended only for use by drivers for hardware that loses its keys on reset. - * - * Context: Process context. Takes and releases ksm->lock. - */ -void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm) -{ - unsigned int slot; - - if (blk_ksm_is_passthrough(ksm)) - return; - - /* This is for device initialization, so don't resume the device */ - down_write(&ksm->lock); - for (slot = 0; slot < ksm->num_slots; slot++) { - const struct blk_crypto_key *key = ksm->slots[slot].key; - int err; - - if (!key) - continue; - - err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot); - WARN_ON(err); - } - up_write(&ksm->lock); -} -EXPORT_SYMBOL_GPL(blk_ksm_reprogram_all_keys); - -void blk_ksm_destroy(struct blk_keyslot_manager *ksm) -{ - if (!ksm) - return; - kvfree(ksm->slot_hashtable); - kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots); - memzero_explicit(ksm, sizeof(*ksm)); -} -EXPORT_SYMBOL_GPL(blk_ksm_destroy); - -bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) -{ - if (blk_integrity_queue_supports_integrity(q)) { - pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); - return false; - } - q->ksm = ksm; - return true; -} -EXPORT_SYMBOL_GPL(blk_ksm_register); - -void blk_ksm_unregister(struct request_queue *q) -{ - q->ksm = NULL; -} - -/** - * blk_ksm_intersect_modes() - restrict supported modes by child device - * @parent: The keyslot manager for parent device - * @child: The keyslot manager for child device, or NULL - * - * Clear any crypto mode support bits in @parent that aren't set in @child. - * If @child is NULL, then all parent bits are cleared. - * - * Only use this when setting up the keyslot manager for a layered device, - * before it's been exposed yet. - */ -void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, - const struct blk_keyslot_manager *child) -{ - if (child) { - unsigned int i; - - parent->max_dun_bytes_supported = - min(parent->max_dun_bytes_supported, - child->max_dun_bytes_supported); - for (i = 0; i < ARRAY_SIZE(child->crypto_modes_supported); - i++) { - parent->crypto_modes_supported[i] &= - child->crypto_modes_supported[i]; - } - } else { - parent->max_dun_bytes_supported = 0; - memset(parent->crypto_modes_supported, 0, - sizeof(parent->crypto_modes_supported)); - } -} -EXPORT_SYMBOL_GPL(blk_ksm_intersect_modes); - -/** - * blk_ksm_is_superset() - Check if a KSM supports a superset of crypto modes - * and DUN bytes that another KSM supports. Here, - * "superset" refers to the mathematical meaning of the - * word - i.e. if two KSMs have the *same* capabilities, - * they *are* considered supersets of each other. - * @ksm_superset: The KSM that we want to verify is a superset - * @ksm_subset: The KSM that we want to verify is a subset - * - * Return: True if @ksm_superset supports a superset of the crypto modes and DUN - * bytes that @ksm_subset supports. - */ -bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, - struct blk_keyslot_manager *ksm_subset) -{ - int i; - - if (!ksm_subset) - return true; - - if (!ksm_superset) - return false; - - for (i = 0; i < ARRAY_SIZE(ksm_superset->crypto_modes_supported); i++) { - if (ksm_subset->crypto_modes_supported[i] & - (~ksm_superset->crypto_modes_supported[i])) { - return false; - } - } - - if (ksm_subset->max_dun_bytes_supported > - ksm_superset->max_dun_bytes_supported) { - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(blk_ksm_is_superset); - -/** - * blk_ksm_update_capabilities() - Update the restrictions of a KSM to those of - * another KSM - * @target_ksm: The KSM whose restrictions to update. - * @reference_ksm: The KSM to whose restrictions this function will update - * @target_ksm's restrictions to. - * - * Blk-crypto requires that crypto capabilities that were - * advertised when a bio was created continue to be supported by the - * device until that bio is ended. This is turn means that a device cannot - * shrink its advertised crypto capabilities without any explicit - * synchronization with upper layers. So if there's no such explicit - * synchronization, @reference_ksm must support all the crypto capabilities that - * @target_ksm does - * (i.e. we need blk_ksm_is_superset(@reference_ksm, @target_ksm) == true). - * - * Note also that as long as the crypto capabilities are being expanded, the - * order of updates becoming visible is not important because it's alright - * for blk-crypto to see stale values - they only cause blk-crypto to - * believe that a crypto capability isn't supported when it actually is (which - * might result in blk-crypto-fallback being used if available, or the bio being - * failed). - */ -void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, - struct blk_keyslot_manager *reference_ksm) -{ - memcpy(target_ksm->crypto_modes_supported, - reference_ksm->crypto_modes_supported, - sizeof(target_ksm->crypto_modes_supported)); - - target_ksm->max_dun_bytes_supported = - reference_ksm->max_dun_bytes_supported; -} -EXPORT_SYMBOL_GPL(blk_ksm_update_capabilities); - -/** - * blk_ksm_init_passthrough() - Init a passthrough keyslot manager - * @ksm: The keyslot manager to init - * - * Initialize a passthrough keyslot manager. - * Called by e.g. storage drivers to set up a keyslot manager in their - * request_queue, when the storage driver wants to manage its keys by itself. - * This is useful for inline encryption hardware that doesn't have the concept - * of keyslots, and for layered devices. - */ -void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm) -{ - memset(ksm, 0, sizeof(*ksm)); - init_rwsem(&ksm->lock); -} -EXPORT_SYMBOL_GPL(blk_ksm_init_passthrough); diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 55dccdfbcb22..841ed87999e7 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 7870e6460633..4184fd8ccb08 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -29,7 +29,7 @@ #include #include #include -#include +#include #define DM_MSG_PREFIX "core" diff --git a/drivers/mmc/host/cqhci-crypto.c b/drivers/mmc/host/cqhci-crypto.c index 6419cfbb4ab7..628bbfaf8312 100644 --- a/drivers/mmc/host/cqhci-crypto.c +++ b/drivers/mmc/host/cqhci-crypto.c @@ -6,7 +6,7 @@ */ #include -#include +#include #include #include "cqhci-crypto.h" diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 41f6e06f9185..885fcf2e5922 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include "unipro.h" #include diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h new file mode 100644 index 000000000000..a27605e2f826 --- /dev/null +++ b/include/linux/blk-crypto-profile.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2019 Google LLC + */ + +#ifndef __LINUX_KEYSLOT_MANAGER_H +#define __LINUX_KEYSLOT_MANAGER_H + +#include +#include + +struct blk_keyslot_manager; + +/** + * struct blk_ksm_ll_ops - functions to manage keyslots in hardware + * @keyslot_program: Program the specified key into the specified slot in the + * inline encryption hardware. + * @keyslot_evict: Evict key from the specified keyslot in the hardware. + * The key is provided so that e.g. dm layers can evict + * keys from the devices that they map over. + * Returns 0 on success, -errno otherwise. + * + * This structure should be provided by storage device drivers when they set up + * a keyslot manager - this structure holds the function ptrs that the keyslot + * manager will use to manipulate keyslots in the hardware. + */ +struct blk_ksm_ll_ops { + int (*keyslot_program)(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot); + int (*keyslot_evict)(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + unsigned int slot); +}; + +struct blk_keyslot_manager { + /* + * The struct blk_ksm_ll_ops that this keyslot manager will use + * to perform operations like programming and evicting keys on the + * device + */ + struct blk_ksm_ll_ops ksm_ll_ops; + + /* + * The maximum number of bytes supported for specifying the data unit + * number. + */ + unsigned int max_dun_bytes_supported; + + /* + * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents + * whether a crypto mode and data unit size are supported. The i'th + * bit of crypto_mode_supported[crypto_mode] is set iff a data unit + * size of (1 << i) is supported. We only support data unit sizes + * that are powers of 2. + */ + unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX]; + + /* Device for runtime power management (NULL if none) */ + struct device *dev; + + /* Here onwards are *private* fields for internal keyslot manager use */ + + unsigned int num_slots; + + /* Protects programming and evicting keys from the device */ + struct rw_semaphore lock; + + /* List of idle slots, with least recently used slot at front */ + wait_queue_head_t idle_slots_wait_queue; + struct list_head idle_slots; + spinlock_t idle_slots_lock; + + /* + * Hash table which maps struct *blk_crypto_key to keyslots, so that we + * can find a key's keyslot in O(1) time rather than O(num_slots). + * Protected by 'lock'. + */ + struct hlist_head *slot_hashtable; + unsigned int log_slot_ht_size; + + /* Per-keyslot data */ + struct blk_ksm_keyslot *slots; +}; + +int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); + +int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, + unsigned int num_slots); + +blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key, + struct blk_ksm_keyslot **slot_ptr); + +unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot); + +void blk_ksm_put_slot(struct blk_ksm_keyslot *slot); + +bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, + const struct blk_crypto_config *cfg); + +int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, + const struct blk_crypto_key *key); + +void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); + +void blk_ksm_destroy(struct blk_keyslot_manager *ksm); + +void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, + const struct blk_keyslot_manager *child); + +void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); + +bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, + struct blk_keyslot_manager *ksm_subset); + +void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, + struct blk_keyslot_manager *reference_ksm); + +#endif /* __LINUX_KEYSLOT_MANAGER_H */ diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h deleted file mode 100644 index a27605e2f826..000000000000 --- a/include/linux/keyslot-manager.h +++ /dev/null @@ -1,120 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright 2019 Google LLC - */ - -#ifndef __LINUX_KEYSLOT_MANAGER_H -#define __LINUX_KEYSLOT_MANAGER_H - -#include -#include - -struct blk_keyslot_manager; - -/** - * struct blk_ksm_ll_ops - functions to manage keyslots in hardware - * @keyslot_program: Program the specified key into the specified slot in the - * inline encryption hardware. - * @keyslot_evict: Evict key from the specified keyslot in the hardware. - * The key is provided so that e.g. dm layers can evict - * keys from the devices that they map over. - * Returns 0 on success, -errno otherwise. - * - * This structure should be provided by storage device drivers when they set up - * a keyslot manager - this structure holds the function ptrs that the keyslot - * manager will use to manipulate keyslots in the hardware. - */ -struct blk_ksm_ll_ops { - int (*keyslot_program)(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - unsigned int slot); - int (*keyslot_evict)(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - unsigned int slot); -}; - -struct blk_keyslot_manager { - /* - * The struct blk_ksm_ll_ops that this keyslot manager will use - * to perform operations like programming and evicting keys on the - * device - */ - struct blk_ksm_ll_ops ksm_ll_ops; - - /* - * The maximum number of bytes supported for specifying the data unit - * number. - */ - unsigned int max_dun_bytes_supported; - - /* - * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents - * whether a crypto mode and data unit size are supported. The i'th - * bit of crypto_mode_supported[crypto_mode] is set iff a data unit - * size of (1 << i) is supported. We only support data unit sizes - * that are powers of 2. - */ - unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX]; - - /* Device for runtime power management (NULL if none) */ - struct device *dev; - - /* Here onwards are *private* fields for internal keyslot manager use */ - - unsigned int num_slots; - - /* Protects programming and evicting keys from the device */ - struct rw_semaphore lock; - - /* List of idle slots, with least recently used slot at front */ - wait_queue_head_t idle_slots_wait_queue; - struct list_head idle_slots; - spinlock_t idle_slots_lock; - - /* - * Hash table which maps struct *blk_crypto_key to keyslots, so that we - * can find a key's keyslot in O(1) time rather than O(num_slots). - * Protected by 'lock'. - */ - struct hlist_head *slot_hashtable; - unsigned int log_slot_ht_size; - - /* Per-keyslot data */ - struct blk_ksm_keyslot *slots; -}; - -int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); - -int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, - unsigned int num_slots); - -blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - struct blk_ksm_keyslot **slot_ptr); - -unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot); - -void blk_ksm_put_slot(struct blk_ksm_keyslot *slot); - -bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, - const struct blk_crypto_config *cfg); - -int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key); - -void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); - -void blk_ksm_destroy(struct blk_keyslot_manager *ksm); - -void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, - const struct blk_keyslot_manager *child); - -void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); - -bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, - struct blk_keyslot_manager *ksm_subset); - -void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, - struct blk_keyslot_manager *reference_ksm); - -#endif /* __LINUX_KEYSLOT_MANAGER_H */ diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 0c0c9a0fdf57..725b1de41767 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -15,7 +15,7 @@ #include #include #include -#include +#include struct mmc_ios { unsigned int clock; /* clock rate */ -- cgit v1.2.3 From cb77cb5abe1f4fae4a33b735606aae22f9eaa1c7 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Mon, 18 Oct 2021 11:04:52 -0700 Subject: blk-crypto: rename blk_keyslot_manager to blk_crypto_profile blk_keyslot_manager is misnamed because it doesn't necessarily manage keyslots. It actually does several different things: - Contains the crypto capabilities of the device. - Provides functions to control the inline encryption hardware. Originally these were just for programming/evicting keyslots; however, new functionality (hardware-wrapped keys) will require new functions here which are unrelated to keyslots. Moreover, device-mapper devices already (ab)use "keyslot_evict" to pass key eviction requests to their underlying devices even though device-mapper devices don't have any keyslots themselves (so it really should be "evict_key", not "keyslot_evict"). - Sometimes (but not always!) it manages keyslots. Originally it always did, but device-mapper devices don't have keyslots themselves, so they use a "passthrough keyslot manager" which doesn't actually manage keyslots. This hack works, but the terminology is unnatural. Also, some hardware doesn't have keyslots and thus also uses a "passthrough keyslot manager" (support for such hardware is yet to be upstreamed, but it will happen eventually). Let's stop having keyslot managers which don't actually manage keyslots. Instead, rename blk_keyslot_manager to blk_crypto_profile. This is a fairly big change, since for consistency it also has to update keyslot manager-related function names, variable names, and comments -- not just the actual struct name. However it's still a fairly straightforward change, as it doesn't change any actual functionality. Acked-by: Ulf Hansson # For MMC Reviewed-by: Mike Snitzer Reviewed-by: Martin K. Petersen Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20211018180453.40441-4-ebiggers@kernel.org Signed-off-by: Jens Axboe --- block/blk-crypto-fallback.c | 71 +++-- block/blk-crypto-profile.c | 520 ++++++++++++++++++------------------- block/blk-crypto.c | 27 +- block/blk-integrity.c | 4 +- drivers/md/dm-core.h | 2 +- drivers/md/dm-table.c | 168 ++++++------ drivers/md/dm.c | 8 +- drivers/mmc/core/crypto.c | 11 +- drivers/mmc/host/cqhci-crypto.c | 31 +-- drivers/scsi/ufs/ufshcd-crypto.c | 32 +-- drivers/scsi/ufs/ufshcd-crypto.h | 9 +- drivers/scsi/ufs/ufshcd.c | 2 +- drivers/scsi/ufs/ufshcd.h | 4 +- include/linux/blk-crypto-profile.h | 164 +++++++----- include/linux/blk-mq.h | 2 +- include/linux/blkdev.h | 16 +- include/linux/device-mapper.h | 4 +- include/linux/mmc/host.h | 2 +- 18 files changed, 555 insertions(+), 522 deletions(-) (limited to 'include/linux') diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index 08bfea292c75..c87aba8584c6 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -78,7 +78,7 @@ static struct blk_crypto_fallback_keyslot { struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX]; } *blk_crypto_keyslots; -static struct blk_keyslot_manager blk_crypto_ksm; +static struct blk_crypto_profile blk_crypto_fallback_profile; static struct workqueue_struct *blk_crypto_wq; static mempool_t *blk_crypto_bounce_page_pool; static struct bio_set crypto_bio_split; @@ -104,9 +104,10 @@ static void blk_crypto_fallback_evict_keyslot(unsigned int slot) slotp->crypto_mode = BLK_ENCRYPTION_MODE_INVALID; } -static int blk_crypto_fallback_keyslot_program(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - unsigned int slot) +static int +blk_crypto_fallback_keyslot_program(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + unsigned int slot) { struct blk_crypto_fallback_keyslot *slotp = &blk_crypto_keyslots[slot]; const enum blk_crypto_mode_num crypto_mode = @@ -127,7 +128,7 @@ static int blk_crypto_fallback_keyslot_program(struct blk_keyslot_manager *ksm, return 0; } -static int blk_crypto_fallback_keyslot_evict(struct blk_keyslot_manager *ksm, +static int blk_crypto_fallback_keyslot_evict(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { @@ -135,14 +136,9 @@ static int blk_crypto_fallback_keyslot_evict(struct blk_keyslot_manager *ksm, return 0; } -/* - * The crypto API fallback KSM ops - only used for a bio when it specifies a - * blk_crypto_key that was not supported by the device's inline encryption - * hardware. - */ -static const struct blk_ksm_ll_ops blk_crypto_ksm_ll_ops = { - .keyslot_program = blk_crypto_fallback_keyslot_program, - .keyslot_evict = blk_crypto_fallback_keyslot_evict, +static const struct blk_crypto_ll_ops blk_crypto_fallback_ll_ops = { + .keyslot_program = blk_crypto_fallback_keyslot_program, + .keyslot_evict = blk_crypto_fallback_keyslot_evict, }; static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio) @@ -188,13 +184,13 @@ static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src) } static bool -blk_crypto_fallback_alloc_cipher_req(struct blk_ksm_keyslot *slot, +blk_crypto_fallback_alloc_cipher_req(struct blk_crypto_keyslot *slot, struct skcipher_request **ciph_req_ret, struct crypto_wait *wait) { struct skcipher_request *ciph_req; const struct blk_crypto_fallback_keyslot *slotp; - int keyslot_idx = blk_ksm_get_slot_idx(slot); + int keyslot_idx = blk_crypto_keyslot_index(slot); slotp = &blk_crypto_keyslots[keyslot_idx]; ciph_req = skcipher_request_alloc(slotp->tfms[slotp->crypto_mode], @@ -266,7 +262,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr) { struct bio *src_bio, *enc_bio; struct bio_crypt_ctx *bc; - struct blk_ksm_keyslot *slot; + struct blk_crypto_keyslot *slot; int data_unit_size; struct skcipher_request *ciph_req = NULL; DECLARE_CRYPTO_WAIT(wait); @@ -293,10 +289,11 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr) } /* - * Use the crypto API fallback keyslot manager to get a crypto_skcipher - * for the algorithm and key specified for this bio. + * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for + * this bio's algorithm and key. */ - blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot); + blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile, + bc->bc_key, &slot); if (blk_st != BLK_STS_OK) { src_bio->bi_status = blk_st; goto out_put_enc_bio; @@ -364,7 +361,7 @@ out_free_bounce_pages: out_free_ciph_req: skcipher_request_free(ciph_req); out_release_keyslot: - blk_ksm_put_slot(slot); + blk_crypto_put_keyslot(slot); out_put_enc_bio: if (enc_bio) bio_put(enc_bio); @@ -382,7 +379,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work) container_of(work, struct bio_fallback_crypt_ctx, work); struct bio *bio = f_ctx->bio; struct bio_crypt_ctx *bc = &f_ctx->crypt_ctx; - struct blk_ksm_keyslot *slot; + struct blk_crypto_keyslot *slot; struct skcipher_request *ciph_req = NULL; DECLARE_CRYPTO_WAIT(wait); u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]; @@ -395,10 +392,11 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work) blk_status_t blk_st; /* - * Use the crypto API fallback keyslot manager to get a crypto_skcipher - * for the algorithm and key specified for this bio. + * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for + * this bio's algorithm and key. */ - blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot); + blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile, + bc->bc_key, &slot); if (blk_st != BLK_STS_OK) { bio->bi_status = blk_st; goto out_no_keyslot; @@ -436,7 +434,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work) out: skcipher_request_free(ciph_req); - blk_ksm_put_slot(slot); + blk_crypto_put_keyslot(slot); out_no_keyslot: mempool_free(f_ctx, bio_fallback_crypt_ctx_pool); bio_endio(bio); @@ -501,8 +499,8 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) return false; } - if (!blk_ksm_crypto_cfg_supported(&blk_crypto_ksm, - &bc->bc_key->crypto_cfg)) { + if (!__blk_crypto_cfg_supported(&blk_crypto_fallback_profile, + &bc->bc_key->crypto_cfg)) { bio->bi_status = BLK_STS_NOTSUPP; return false; } @@ -528,7 +526,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr) int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key) { - return blk_ksm_evict_key(&blk_crypto_ksm, key); + return __blk_crypto_evict_key(&blk_crypto_fallback_profile, key); } static bool blk_crypto_fallback_inited; @@ -536,6 +534,7 @@ static int blk_crypto_fallback_init(void) { int i; int err; + struct blk_crypto_profile *profile = &blk_crypto_fallback_profile; if (blk_crypto_fallback_inited) return 0; @@ -546,24 +545,24 @@ static int blk_crypto_fallback_init(void) if (err) goto out; - err = blk_ksm_init(&blk_crypto_ksm, blk_crypto_num_keyslots); + err = blk_crypto_profile_init(profile, blk_crypto_num_keyslots); if (err) goto fail_free_bioset; err = -ENOMEM; - blk_crypto_ksm.ksm_ll_ops = blk_crypto_ksm_ll_ops; - blk_crypto_ksm.max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; + profile->ll_ops = blk_crypto_fallback_ll_ops; + profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE; /* All blk-crypto modes have a crypto API fallback. */ for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++) - blk_crypto_ksm.crypto_modes_supported[i] = 0xFFFFFFFF; - blk_crypto_ksm.crypto_modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; + profile->modes_supported[i] = 0xFFFFFFFF; + profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0; blk_crypto_wq = alloc_workqueue("blk_crypto_wq", WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM, num_online_cpus()); if (!blk_crypto_wq) - goto fail_free_ksm; + goto fail_destroy_profile; blk_crypto_keyslots = kcalloc(blk_crypto_num_keyslots, sizeof(blk_crypto_keyslots[0]), @@ -597,8 +596,8 @@ fail_free_keyslots: kfree(blk_crypto_keyslots); fail_free_wq: destroy_workqueue(blk_crypto_wq); -fail_free_ksm: - blk_ksm_destroy(&blk_crypto_ksm); +fail_destroy_profile: + blk_crypto_profile_destroy(profile); fail_free_bioset: bioset_exit(&crypto_bio_split); out: diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c index 1a235fa3c3e8..605ba0626a5c 100644 --- a/block/blk-crypto-profile.c +++ b/block/blk-crypto-profile.c @@ -4,26 +4,22 @@ */ /** - * DOC: The Keyslot Manager + * DOC: blk-crypto profiles * - * Many devices with inline encryption support have a limited number of "slots" - * into which encryption contexts may be programmed, and requests can be tagged - * with a slot number to specify the key to use for en/decryption. + * 'struct blk_crypto_profile' contains all generic inline encryption-related + * state for a particular inline encryption device. blk_crypto_profile serves + * as the way that drivers for inline encryption hardware expose their crypto + * capabilities and certain functions (e.g., functions to program and evict + * keys) to upper layers. Device drivers that want to support inline encryption + * construct a crypto profile, then associate it with the disk's request_queue. * - * As the number of slots is limited, and programming keys is expensive on - * many inline encryption hardware, we don't want to program the same key into - * multiple slots - if multiple requests are using the same key, we want to - * program just one slot with that key and use that slot for all requests. + * If the device has keyslots, then its blk_crypto_profile also handles managing + * these keyslots in a device-independent way, using the driver-provided + * functions to program and evict keys as needed. This includes keeping track + * of which key and how many I/O requests are using each keyslot, getting + * keyslots for I/O requests, and handling key eviction requests. * - * The keyslot manager manages these keyslots appropriately, and also acts as - * an abstraction between the inline encryption hardware and the upper layers. - * - * Lower layer devices will set up a keyslot manager in their request queue - * and tell it how to perform device specific operations like programming/ - * evicting keys from keyslots. - * - * Upper layers will call blk_ksm_get_slot_for_key() to program a - * key into some slot in the inline encryption hardware. + * For more information, see Documentation/block/inline-encryption.rst. */ #define pr_fmt(fmt) "blk-crypto: " fmt @@ -37,77 +33,75 @@ #include #include -struct blk_ksm_keyslot { +struct blk_crypto_keyslot { atomic_t slot_refs; struct list_head idle_slot_node; struct hlist_node hash_node; const struct blk_crypto_key *key; - struct blk_keyslot_manager *ksm; + struct blk_crypto_profile *profile; }; -static inline void blk_ksm_hw_enter(struct blk_keyslot_manager *ksm) +static inline void blk_crypto_hw_enter(struct blk_crypto_profile *profile) { /* - * Calling into the driver requires ksm->lock held and the device + * Calling into the driver requires profile->lock held and the device * resumed. But we must resume the device first, since that can acquire - * and release ksm->lock via blk_ksm_reprogram_all_keys(). + * and release profile->lock via blk_crypto_reprogram_all_keys(). */ - if (ksm->dev) - pm_runtime_get_sync(ksm->dev); - down_write(&ksm->lock); + if (profile->dev) + pm_runtime_get_sync(profile->dev); + down_write(&profile->lock); } -static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm) +static inline void blk_crypto_hw_exit(struct blk_crypto_profile *profile) { - up_write(&ksm->lock); - if (ksm->dev) - pm_runtime_put_sync(ksm->dev); -} - -static inline bool blk_ksm_is_passthrough(struct blk_keyslot_manager *ksm) -{ - return ksm->num_slots == 0; + up_write(&profile->lock); + if (profile->dev) + pm_runtime_put_sync(profile->dev); } /** - * blk_ksm_init() - Initialize a keyslot manager - * @ksm: The keyslot_manager to initialize. - * @num_slots: The number of key slots to manage. + * blk_crypto_profile_init() - Initialize a blk_crypto_profile + * @profile: the blk_crypto_profile to initialize + * @num_slots: the number of keyslots * - * Allocate memory for keyslots and initialize a keyslot manager. Called by - * e.g. storage drivers to set up a keyslot manager in their request_queue. + * Storage drivers must call this when starting to set up a blk_crypto_profile, + * before filling in additional fields. * * Return: 0 on success, or else a negative error code. */ -int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) +int blk_crypto_profile_init(struct blk_crypto_profile *profile, + unsigned int num_slots) { unsigned int slot; unsigned int i; unsigned int slot_hashtable_size; - memset(ksm, 0, sizeof(*ksm)); + memset(profile, 0, sizeof(*profile)); + init_rwsem(&profile->lock); if (num_slots == 0) - return -EINVAL; + return 0; - ksm->slots = kvcalloc(num_slots, sizeof(ksm->slots[0]), GFP_KERNEL); - if (!ksm->slots) - return -ENOMEM; + /* Initialize keyslot management data. */ - ksm->num_slots = num_slots; + profile->slots = kvcalloc(num_slots, sizeof(profile->slots[0]), + GFP_KERNEL); + if (!profile->slots) + return -ENOMEM; - init_rwsem(&ksm->lock); + profile->num_slots = num_slots; - init_waitqueue_head(&ksm->idle_slots_wait_queue); - INIT_LIST_HEAD(&ksm->idle_slots); + init_waitqueue_head(&profile->idle_slots_wait_queue); + INIT_LIST_HEAD(&profile->idle_slots); for (slot = 0; slot < num_slots; slot++) { - ksm->slots[slot].ksm = ksm; - list_add_tail(&ksm->slots[slot].idle_slot_node, - &ksm->idle_slots); + profile->slots[slot].profile = profile; + list_add_tail(&profile->slots[slot].idle_slot_node, + &profile->idle_slots); } - spin_lock_init(&ksm->idle_slots_lock); + spin_lock_init(&profile->idle_slots_lock); slot_hashtable_size = roundup_pow_of_two(num_slots); /* @@ -117,74 +111,80 @@ int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots) if (slot_hashtable_size < 2) slot_hashtable_size = 2; - ksm->log_slot_ht_size = ilog2(slot_hashtable_size); - ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size, - sizeof(ksm->slot_hashtable[0]), - GFP_KERNEL); - if (!ksm->slot_hashtable) - goto err_destroy_ksm; + profile->log_slot_ht_size = ilog2(slot_hashtable_size); + profile->slot_hashtable = + kvmalloc_array(slot_hashtable_size, + sizeof(profile->slot_hashtable[0]), GFP_KERNEL); + if (!profile->slot_hashtable) + goto err_destroy; for (i = 0; i < slot_hashtable_size; i++) - INIT_HLIST_HEAD(&ksm->slot_hashtable[i]); + INIT_HLIST_HEAD(&profile->slot_hashtable[i]); return 0; -err_destroy_ksm: - blk_ksm_destroy(ksm); +err_destroy: + blk_crypto_profile_destroy(profile); return -ENOMEM; } -EXPORT_SYMBOL_GPL(blk_ksm_init); +EXPORT_SYMBOL_GPL(blk_crypto_profile_init); -static void blk_ksm_destroy_callback(void *ksm) +static void blk_crypto_profile_destroy_callback(void *profile) { - blk_ksm_destroy(ksm); + blk_crypto_profile_destroy(profile); } /** - * devm_blk_ksm_init() - Resource-managed blk_ksm_init() - * @dev: The device which owns the blk_keyslot_manager. - * @ksm: The blk_keyslot_manager to initialize. - * @num_slots: The number of key slots to manage. + * devm_blk_crypto_profile_init() - Resource-managed blk_crypto_profile_init() + * @dev: the device which owns the blk_crypto_profile + * @profile: the blk_crypto_profile to initialize + * @num_slots: the number of keyslots * - * Like blk_ksm_init(), but causes blk_ksm_destroy() to be called automatically - * on driver detach. + * Like blk_crypto_profile_init(), but causes blk_crypto_profile_destroy() to be + * called automatically on driver detach. * * Return: 0 on success, or else a negative error code. */ -int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, - unsigned int num_slots) +int devm_blk_crypto_profile_init(struct device *dev, + struct blk_crypto_profile *profile, + unsigned int num_slots) { - int err = blk_ksm_init(ksm, num_slots); + int err = blk_crypto_profile_init(profile, num_slots); if (err) return err; - return devm_add_action_or_reset(dev, blk_ksm_destroy_callback, ksm); + return devm_add_action_or_reset(dev, + blk_crypto_profile_destroy_callback, + profile); } -EXPORT_SYMBOL_GPL(devm_blk_ksm_init); +EXPORT_SYMBOL_GPL(devm_blk_crypto_profile_init); static inline struct hlist_head * -blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) +blk_crypto_hash_bucket_for_key(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key) { - return &ksm->slot_hashtable[hash_ptr(key, ksm->log_slot_ht_size)]; + return &profile->slot_hashtable[ + hash_ptr(key, profile->log_slot_ht_size)]; } -static void blk_ksm_remove_slot_from_lru_list(struct blk_ksm_keyslot *slot) +static void +blk_crypto_remove_slot_from_lru_list(struct blk_crypto_keyslot *slot) { - struct blk_keyslot_manager *ksm = slot->ksm; + struct blk_crypto_profile *profile = slot->profile; unsigned long flags; - spin_lock_irqsave(&ksm->idle_slots_lock, flags); + spin_lock_irqsave(&profile->idle_slots_lock, flags); list_del(&slot->idle_slot_node); - spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); + spin_unlock_irqrestore(&profile->idle_slots_lock, flags); } -static struct blk_ksm_keyslot *blk_ksm_find_keyslot( - struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) +static struct blk_crypto_keyslot * +blk_crypto_find_keyslot(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key) { - const struct hlist_head *head = blk_ksm_hash_bucket_for_key(ksm, key); - struct blk_ksm_keyslot *slotp; + const struct hlist_head *head = + blk_crypto_hash_bucket_for_key(profile, key); + struct blk_crypto_keyslot *slotp; hlist_for_each_entry(slotp, head, hash_node) { if (slotp->key == key) @@ -193,68 +193,79 @@ static struct blk_ksm_keyslot *blk_ksm_find_keyslot( return NULL; } -static struct blk_ksm_keyslot *blk_ksm_find_and_grab_keyslot( - struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) +static struct blk_crypto_keyslot * +blk_crypto_find_and_grab_keyslot(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key) { - struct blk_ksm_keyslot *slot; + struct blk_crypto_keyslot *slot; - slot = blk_ksm_find_keyslot(ksm, key); + slot = blk_crypto_find_keyslot(profile, key); if (!slot) return NULL; if (atomic_inc_return(&slot->slot_refs) == 1) { /* Took first reference to this slot; remove it from LRU list */ - blk_ksm_remove_slot_from_lru_list(slot); + blk_crypto_remove_slot_from_lru_list(slot); } return slot; } -unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot) +/** + * blk_crypto_keyslot_index() - Get the index of a keyslot + * @slot: a keyslot that blk_crypto_get_keyslot() returned + * + * Return: the 0-based index of the keyslot within the device's keyslots. + */ +unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot) { - return slot - slot->ksm->slots; + return slot - slot->profile->slots; } -EXPORT_SYMBOL_GPL(blk_ksm_get_slot_idx); +EXPORT_SYMBOL_GPL(blk_crypto_keyslot_index); /** - * blk_ksm_get_slot_for_key() - Program a key into a keyslot. - * @ksm: The keyslot manager to program the key into. - * @key: Pointer to the key object to program, including the raw key, crypto - * mode, and data unit size. - * @slot_ptr: A pointer to return the pointer of the allocated keyslot. + * blk_crypto_get_keyslot() - Get a keyslot for a key, if needed. + * @profile: the crypto profile of the device the key will be used on + * @key: the key that will be used + * @slot_ptr: If a keyslot is allocated, an opaque pointer to the keyslot struct + * will be stored here; otherwise NULL will be stored here. + * + * If the device has keyslots, this gets a keyslot that's been programmed with + * the specified key. If the key is already in a slot, this reuses it; + * otherwise this waits for a slot to become idle and programs the key into it. * - * Get a keyslot that's been programmed with the specified key. If one already - * exists, return it with incremented refcount. Otherwise, wait for a keyslot - * to become idle and program it. + * This must be paired with a call to blk_crypto_put_keyslot(). * - * Context: Process context. Takes and releases ksm->lock. - * Return: BLK_STS_OK on success (and keyslot is set to the pointer of the - * allocated keyslot), or some other blk_status_t otherwise (and - * keyslot is set to NULL). + * Context: Process context. Takes and releases profile->lock. + * Return: BLK_STS_OK on success, meaning that either a keyslot was allocated or + * one wasn't needed; or a blk_status_t error on failure. */ -blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - struct blk_ksm_keyslot **slot_ptr) +blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + struct blk_crypto_keyslot **slot_ptr) { - struct blk_ksm_keyslot *slot; + struct blk_crypto_keyslot *slot; int slot_idx; int err; *slot_ptr = NULL; - if (blk_ksm_is_passthrough(ksm)) + /* + * If the device has no concept of "keyslots", then there is no need to + * get one. + */ + if (profile->num_slots == 0) return BLK_STS_OK; - down_read(&ksm->lock); - slot = blk_ksm_find_and_grab_keyslot(ksm, key); - up_read(&ksm->lock); + down_read(&profile->lock); + slot = blk_crypto_find_and_grab_keyslot(profile, key); + up_read(&profile->lock); if (slot) goto success; for (;;) { - blk_ksm_hw_enter(ksm); - slot = blk_ksm_find_and_grab_keyslot(ksm, key); + blk_crypto_hw_enter(profile); + slot = blk_crypto_find_and_grab_keyslot(profile, key); if (slot) { - blk_ksm_hw_exit(ksm); + blk_crypto_hw_exit(profile); goto success; } @@ -262,22 +273,22 @@ blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, * If we're here, that means there wasn't a slot that was * already programmed with the key. So try to program it. */ - if (!list_empty(&ksm->idle_slots)) + if (!list_empty(&profile->idle_slots)) break; - blk_ksm_hw_exit(ksm); - wait_event(ksm->idle_slots_wait_queue, - !list_empty(&ksm->idle_slots)); + blk_crypto_hw_exit(profile); + wait_event(profile->idle_slots_wait_queue, + !list_empty(&profile->idle_slots)); } - slot = list_first_entry(&ksm->idle_slots, struct blk_ksm_keyslot, + slot = list_first_entry(&profile->idle_slots, struct blk_crypto_keyslot, idle_slot_node); - slot_idx = blk_ksm_get_slot_idx(slot); + slot_idx = blk_crypto_keyslot_index(slot); - err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot_idx); + err = profile->ll_ops.keyslot_program(profile, key, slot_idx); if (err) { - wake_up(&ksm->idle_slots_wait_queue); - blk_ksm_hw_exit(ksm); + wake_up(&profile->idle_slots_wait_queue); + blk_crypto_hw_exit(profile); return errno_to_blk_status(err); } @@ -285,97 +296,98 @@ blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, if (slot->key) hlist_del(&slot->hash_node); slot->key = key; - hlist_add_head(&slot->hash_node, blk_ksm_hash_bucket_for_key(ksm, key)); + hlist_add_head(&slot->hash_node, + blk_crypto_hash_bucket_for_key(profile, key)); atomic_set(&slot->slot_refs, 1); - blk_ksm_remove_slot_from_lru_list(slot); + blk_crypto_remove_slot_from_lru_list(slot); - blk_ksm_hw_exit(ksm); + blk_crypto_hw_exit(profile); success: *slot_ptr = slot; return BLK_STS_OK; } /** - * blk_ksm_put_slot() - Release a reference to a slot - * @slot: The keyslot to release the reference of. + * blk_crypto_put_keyslot() - Release a reference to a keyslot + * @slot: The keyslot to release the reference of (may be NULL). * * Context: Any context. */ -void blk_ksm_put_slot(struct blk_ksm_keyslot *slot) +void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot) { - struct blk_keyslot_manager *ksm; + struct blk_crypto_profile *profile; unsigned long flags; if (!slot) return; - ksm = slot->ksm; + profile = slot->profile; if (atomic_dec_and_lock_irqsave(&slot->slot_refs, - &ksm->idle_slots_lock, flags)) { - list_add_tail(&slot->idle_slot_node, &ksm->idle_slots); - spin_unlock_irqrestore(&ksm->idle_slots_lock, flags); - wake_up(&ksm->idle_slots_wait_queue); + &profile->idle_slots_lock, flags)) { + list_add_tail(&slot->idle_slot_node, &profile->idle_slots); + spin_unlock_irqrestore(&profile->idle_slots_lock, flags); + wake_up(&profile->idle_slots_wait_queue); } } /** - * blk_ksm_crypto_cfg_supported() - Find out if a crypto configuration is - * supported by a ksm. - * @ksm: The keyslot manager to check - * @cfg: The crypto configuration to check for. - * - * Checks for crypto_mode/data unit size/dun bytes support. + * __blk_crypto_cfg_supported() - Check whether the given crypto profile + * supports the given crypto configuration. + * @profile: the crypto profile to check + * @cfg: the crypto configuration to check for * - * Return: Whether or not this ksm supports the specified crypto config. + * Return: %true if @profile supports the given @cfg. */ -bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, - const struct blk_crypto_config *cfg) +bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile, + const struct blk_crypto_config *cfg) { - if (!ksm) + if (!profile) return false; - if (!(ksm->crypto_modes_supported[cfg->crypto_mode] & - cfg->data_unit_size)) + if (!(profile->modes_supported[cfg->crypto_mode] & cfg->data_unit_size)) return false; - if (ksm->max_dun_bytes_supported < cfg->dun_bytes) + if (profile->max_dun_bytes_supported < cfg->dun_bytes) return false; return true; } /** - * blk_ksm_evict_key() - Evict a key from the lower layer device. - * @ksm: The keyslot manager to evict from - * @key: The key to evict + * __blk_crypto_evict_key() - Evict a key from a device. + * @profile: the crypto profile of the device + * @key: the key to evict. It must not still be used in any I/O. + * + * If the device has keyslots, this finds the keyslot (if any) that contains the + * specified key and calls the driver's keyslot_evict function to evict it. * - * Find the keyslot that the specified key was programmed into, and evict that - * slot from the lower layer device. The slot must not be in use by any - * in-flight IO when this function is called. + * Otherwise, this just calls the driver's keyslot_evict function if it is + * implemented, passing just the key (without any particular keyslot). This + * allows layered devices to evict the key from their underlying devices. * - * Context: Process context. Takes and releases ksm->lock. + * Context: Process context. Takes and releases profile->lock. * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY * if the keyslot is still in use, or another -errno value on other * error. */ -int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key) +int __blk_crypto_evict_key(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key) { - struct blk_ksm_keyslot *slot; + struct blk_crypto_keyslot *slot; int err = 0; - if (blk_ksm_is_passthrough(ksm)) { - if (ksm->ksm_ll_ops.keyslot_evict) { - blk_ksm_hw_enter(ksm); - err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1); - blk_ksm_hw_exit(ksm); + if (profile->num_slots == 0) { + if (profile->ll_ops.keyslot_evict) { + blk_crypto_hw_enter(profile); + err = profile->ll_ops.keyslot_evict(profile, key, -1); + blk_crypto_hw_exit(profile); return err; } return 0; } - blk_ksm_hw_enter(ksm); - slot = blk_ksm_find_keyslot(ksm, key); + blk_crypto_hw_enter(profile); + slot = blk_crypto_find_keyslot(profile, key); if (!slot) goto out_unlock; @@ -383,8 +395,8 @@ int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, err = -EBUSY; goto out_unlock; } - err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, - blk_ksm_get_slot_idx(slot)); + err = profile->ll_ops.keyslot_evict(profile, key, + blk_crypto_keyslot_index(slot)); if (err) goto out_unlock; @@ -392,81 +404,84 @@ int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, slot->key = NULL; err = 0; out_unlock: - blk_ksm_hw_exit(ksm); + blk_crypto_hw_exit(profile); return err; } /** - * blk_ksm_reprogram_all_keys() - Re-program all keyslots. - * @ksm: The keyslot manager + * blk_crypto_reprogram_all_keys() - Re-program all keyslots. + * @profile: The crypto profile * * Re-program all keyslots that are supposed to have a key programmed. This is * intended only for use by drivers for hardware that loses its keys on reset. * - * Context: Process context. Takes and releases ksm->lock. + * Context: Process context. Takes and releases profile->lock. */ -void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm) +void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile) { unsigned int slot; - if (blk_ksm_is_passthrough(ksm)) + if (profile->num_slots == 0) return; /* This is for device initialization, so don't resume the device */ - down_write(&ksm->lock); - for (slot = 0; slot < ksm->num_slots; slot++) { - const struct blk_crypto_key *key = ksm->slots[slot].key; + down_write(&profile->lock); + for (slot = 0; slot < profile->num_slots; slot++) { + const struct blk_crypto_key *key = profile->slots[slot].key; int err; if (!key) continue; - err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot); + err = profile->ll_ops.keyslot_program(profile, key, slot); WARN_ON(err); } - up_write(&ksm->lock); + up_write(&profile->lock); } -EXPORT_SYMBOL_GPL(blk_ksm_reprogram_all_keys); +EXPORT_SYMBOL_GPL(blk_crypto_reprogram_all_keys); -void blk_ksm_destroy(struct blk_keyslot_manager *ksm) +void blk_crypto_profile_destroy(struct blk_crypto_profile *profile) { - if (!ksm) + if (!profile) return; - kvfree(ksm->slot_hashtable); - kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots); - memzero_explicit(ksm, sizeof(*ksm)); + kvfree(profile->slot_hashtable); + kvfree_sensitive(profile->slots, + sizeof(profile->slots[0]) * profile->num_slots); + memzero_explicit(profile, sizeof(*profile)); } -EXPORT_SYMBOL_GPL(blk_ksm_destroy); +EXPORT_SYMBOL_GPL(blk_crypto_profile_destroy); -bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) +bool blk_crypto_register(struct blk_crypto_profile *profile, + struct request_queue *q) { if (blk_integrity_queue_supports_integrity(q)) { pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); return false; } - q->ksm = ksm; + q->crypto_profile = profile; return true; } -EXPORT_SYMBOL_GPL(blk_ksm_register); +EXPORT_SYMBOL_GPL(blk_crypto_register); -void blk_ksm_unregister(struct request_queue *q) +void blk_crypto_unregister(struct request_queue *q) { - q->ksm = NULL; + q->crypto_profile = NULL; } /** - * blk_ksm_intersect_modes() - restrict supported modes by child device - * @parent: The keyslot manager for parent device - * @child: The keyslot manager for child device, or NULL + * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities + * by child device + * @parent: the crypto profile for the parent device + * @child: the crypto profile for the child device, or NULL * - * Clear any crypto mode support bits in @parent that aren't set in @child. - * If @child is NULL, then all parent bits are cleared. + * This clears all crypto capabilities in @parent that aren't set in @child. If + * @child is NULL, then this clears all parent capabilities. * - * Only use this when setting up the keyslot manager for a layered device, - * before it's been exposed yet. + * Only use this when setting up the crypto profile for a layered device, before + * it's been exposed yet. */ -void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, - const struct blk_keyslot_manager *child) +void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent, + const struct blk_crypto_profile *child) { if (child) { unsigned int i; @@ -474,73 +489,63 @@ void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, parent->max_dun_bytes_supported = min(parent->max_dun_bytes_supported, child->max_dun_bytes_supported); - for (i = 0; i < ARRAY_SIZE(child->crypto_modes_supported); - i++) { - parent->crypto_modes_supported[i] &= - child->crypto_modes_supported[i]; - } + for (i = 0; i < ARRAY_SIZE(child->modes_supported); i++) + parent->modes_supported[i] &= child->modes_supported[i]; } else { parent->max_dun_bytes_supported = 0; - memset(parent->crypto_modes_supported, 0, - sizeof(parent->crypto_modes_supported)); + memset(parent->modes_supported, 0, + sizeof(parent->modes_supported)); } } -EXPORT_SYMBOL_GPL(blk_ksm_intersect_modes); +EXPORT_SYMBOL_GPL(blk_crypto_intersect_capabilities); /** - * blk_ksm_is_superset() - Check if a KSM supports a superset of crypto modes - * and DUN bytes that another KSM supports. Here, - * "superset" refers to the mathematical meaning of the - * word - i.e. if two KSMs have the *same* capabilities, - * they *are* considered supersets of each other. - * @ksm_superset: The KSM that we want to verify is a superset - * @ksm_subset: The KSM that we want to verify is a subset + * blk_crypto_has_capabilities() - Check whether @target supports at least all + * the crypto capabilities that @reference does. + * @target: the target profile + * @reference: the reference profile * - * Return: True if @ksm_superset supports a superset of the crypto modes and DUN - * bytes that @ksm_subset supports. + * Return: %true if @target supports all the crypto capabilities of @reference. */ -bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, - struct blk_keyslot_manager *ksm_subset) +bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target, + const struct blk_crypto_profile *reference) { int i; - if (!ksm_subset) + if (!reference) return true; - if (!ksm_superset) + if (!target) return false; - for (i = 0; i < ARRAY_SIZE(ksm_superset->crypto_modes_supported); i++) { - if (ksm_subset->crypto_modes_supported[i] & - (~ksm_superset->crypto_modes_supported[i])) { + for (i = 0; i < ARRAY_SIZE(target->modes_supported); i++) { + if (reference->modes_supported[i] & ~target->modes_supported[i]) return false; - } } - if (ksm_subset->max_dun_bytes_supported > - ksm_superset->max_dun_bytes_supported) { + if (reference->max_dun_bytes_supported > + target->max_dun_bytes_supported) return false; - } return true; } -EXPORT_SYMBOL_GPL(blk_ksm_is_superset); +EXPORT_SYMBOL_GPL(blk_crypto_has_capabilities); /** - * blk_ksm_update_capabilities() - Update the restrictions of a KSM to those of - * another KSM - * @target_ksm: The KSM whose restrictions to update. - * @reference_ksm: The KSM to whose restrictions this function will update - * @target_ksm's restrictions to. + * blk_crypto_update_capabilities() - Update the capabilities of a crypto + * profile to match those of another crypto + * profile. + * @dst: The crypto profile whose capabilities to update. + * @src: The crypto profile whose capabilities this function will update @dst's + * capabilities to. * * Blk-crypto requires that crypto capabilities that were * advertised when a bio was created continue to be supported by the * device until that bio is ended. This is turn means that a device cannot * shrink its advertised crypto capabilities without any explicit * synchronization with upper layers. So if there's no such explicit - * synchronization, @reference_ksm must support all the crypto capabilities that - * @target_ksm does - * (i.e. we need blk_ksm_is_superset(@reference_ksm, @target_ksm) == true). + * synchronization, @src must support all the crypto capabilities that + * @dst does (i.e. we need blk_crypto_has_capabilities(@src, @dst)). * * Note also that as long as the crypto capabilities are being expanded, the * order of updates becoming visible is not important because it's alright @@ -549,31 +554,12 @@ EXPORT_SYMBOL_GPL(blk_ksm_is_superset); * might result in blk-crypto-fallback being used if available, or the bio being * failed). */ -void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, - struct blk_keyslot_manager *reference_ksm) +void blk_crypto_update_capabilities(struct blk_crypto_profile *dst, + const struct blk_crypto_profile *src) { - memcpy(target_ksm->crypto_modes_supported, - reference_ksm->crypto_modes_supported, - sizeof(target_ksm->crypto_modes_supported)); + memcpy(dst->modes_supported, src->modes_supported, + sizeof(dst->modes_supported)); - target_ksm->max_dun_bytes_supported = - reference_ksm->max_dun_bytes_supported; -} -EXPORT_SYMBOL_GPL(blk_ksm_update_capabilities); - -/** - * blk_ksm_init_passthrough() - Init a passthrough keyslot manager - * @ksm: The keyslot manager to init - * - * Initialize a passthrough keyslot manager. - * Called by e.g. storage drivers to set up a keyslot manager in their - * request_queue, when the storage driver wants to manage its keys by itself. - * This is useful for inline encryption hardware that doesn't have the concept - * of keyslots, and for layered devices. - */ -void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm) -{ - memset(ksm, 0, sizeof(*ksm)); - init_rwsem(&ksm->lock); + dst->max_dun_bytes_supported = src->max_dun_bytes_supported; } -EXPORT_SYMBOL_GPL(blk_ksm_init_passthrough); +EXPORT_SYMBOL_GPL(blk_crypto_update_capabilities); diff --git a/block/blk-crypto.c b/block/blk-crypto.c index 76ce7a5d2676..ec9efeeeca91 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -218,8 +218,9 @@ static bool bio_crypt_check_alignment(struct bio *bio) blk_status_t __blk_crypto_init_request(struct request *rq) { - return blk_ksm_get_slot_for_key(rq->q->ksm, rq->crypt_ctx->bc_key, - &rq->crypt_keyslot); + return blk_crypto_get_keyslot(rq->q->crypto_profile, + rq->crypt_ctx->bc_key, + &rq->crypt_keyslot); } /** @@ -233,7 +234,7 @@ blk_status_t __blk_crypto_init_request(struct request *rq) */ void __blk_crypto_free_request(struct request *rq) { - blk_ksm_put_slot(rq->crypt_keyslot); + blk_crypto_put_keyslot(rq->crypt_keyslot); mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool); blk_crypto_rq_set_defaults(rq); } @@ -264,6 +265,7 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr) { struct bio *bio = *bio_ptr; const struct blk_crypto_key *bc_key = bio->bi_crypt_context->bc_key; + struct blk_crypto_profile *profile; /* Error if bio has no data. */ if (WARN_ON_ONCE(!bio_has_data(bio))) { @@ -280,8 +282,8 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr) * Success if device supports the encryption context, or if we succeeded * in falling back to the crypto API. */ - if (blk_ksm_crypto_cfg_supported(bdev_get_queue(bio->bi_bdev)->ksm, - &bc_key->crypto_cfg)) + profile = bdev_get_queue(bio->bi_bdev)->crypto_profile; + if (__blk_crypto_cfg_supported(profile, &bc_key->crypto_cfg)) return true; if (blk_crypto_fallback_bio_prep(bio_ptr)) @@ -357,7 +359,7 @@ bool blk_crypto_config_supported(struct request_queue *q, const struct blk_crypto_config *cfg) { return IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) || - blk_ksm_crypto_cfg_supported(q->ksm, cfg); + __blk_crypto_cfg_supported(q->crypto_profile, cfg); } /** @@ -378,7 +380,7 @@ bool blk_crypto_config_supported(struct request_queue *q, int blk_crypto_start_using_key(const struct blk_crypto_key *key, struct request_queue *q) { - if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) + if (__blk_crypto_cfg_supported(q->crypto_profile, &key->crypto_cfg)) return 0; return blk_crypto_fallback_start_using_mode(key->crypto_cfg.crypto_mode); } @@ -394,18 +396,17 @@ int blk_crypto_start_using_key(const struct blk_crypto_key *key, * evicted from any hardware that it might have been programmed into. The key * must not be in use by any in-flight IO when this function is called. * - * Return: 0 on success or if key is not present in the q's ksm, -err on error. + * Return: 0 on success or if the key wasn't in any keyslot; -errno on error. */ int blk_crypto_evict_key(struct request_queue *q, const struct blk_crypto_key *key) { - if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg)) - return blk_ksm_evict_key(q->ksm, key); + if (__blk_crypto_cfg_supported(q->crypto_profile, &key->crypto_cfg)) + return __blk_crypto_evict_key(q->crypto_profile, key); /* - * If the request queue's associated inline encryption hardware didn't - * have support for the key, then the key might have been programmed - * into the fallback keyslot manager, so try to evict from there. + * If the request_queue didn't support the key, then blk-crypto-fallback + * may have been used, so try to evict the key from blk-crypto-fallback. */ return blk_crypto_fallback_evict_key(key); } diff --git a/block/blk-integrity.c b/block/blk-integrity.c index cef534a7cbc9..d670d54e5f7a 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -409,9 +409,9 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); #ifdef CONFIG_BLK_INLINE_ENCRYPTION - if (disk->queue->ksm) { + if (disk->queue->crypto_profile) { pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); - blk_ksm_unregister(disk->queue); + blk_crypto_unregister(disk->queue); } #endif } diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 841ed87999e7..b855fef4f38a 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -200,7 +200,7 @@ struct dm_table { struct dm_md_mempools *mempools; #ifdef CONFIG_BLK_INLINE_ENCRYPTION - struct blk_keyslot_manager *ksm; + struct blk_crypto_profile *crypto_profile; #endif }; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 1fa4d5582dca..8b0f27a745d9 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -170,7 +170,7 @@ static void free_devices(struct list_head *devices, struct mapped_device *md) } } -static void dm_table_destroy_keyslot_manager(struct dm_table *t); +static void dm_table_destroy_crypto_profile(struct dm_table *t); void dm_table_destroy(struct dm_table *t) { @@ -200,7 +200,7 @@ void dm_table_destroy(struct dm_table *t) dm_free_md_mempools(t->mempools); - dm_table_destroy_keyslot_manager(t); + dm_table_destroy_crypto_profile(t); kfree(t); } @@ -1187,8 +1187,8 @@ static int dm_table_register_integrity(struct dm_table *t) #ifdef CONFIG_BLK_INLINE_ENCRYPTION -struct dm_keyslot_manager { - struct blk_keyslot_manager ksm; +struct dm_crypto_profile { + struct blk_crypto_profile profile; struct mapped_device *md; }; @@ -1214,13 +1214,11 @@ static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev, * When an inline encryption key is evicted from a device-mapper device, evict * it from all the underlying devices. */ -static int dm_keyslot_evict(struct blk_keyslot_manager *ksm, +static int dm_keyslot_evict(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct dm_keyslot_manager *dksm = container_of(ksm, - struct dm_keyslot_manager, - ksm); - struct mapped_device *md = dksm->md; + struct mapped_device *md = + container_of(profile, struct dm_crypto_profile, profile)->md; struct dm_keyslot_evict_args args = { key }; struct dm_table *t; int srcu_idx; @@ -1240,150 +1238,148 @@ static int dm_keyslot_evict(struct blk_keyslot_manager *ksm, return args.err; } -static const struct blk_ksm_ll_ops dm_ksm_ll_ops = { - .keyslot_evict = dm_keyslot_evict, -}; - -static int device_intersect_crypto_modes(struct dm_target *ti, - struct dm_dev *dev, sector_t start, - sector_t len, void *data) +static int +device_intersect_crypto_capabilities(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct blk_keyslot_manager *parent = data; - struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm; + struct blk_crypto_profile *parent = data; + struct blk_crypto_profile *child = + bdev_get_queue(dev->bdev)->crypto_profile; - blk_ksm_intersect_modes(parent, child); + blk_crypto_intersect_capabilities(parent, child); return 0; } -void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm) +void dm_destroy_crypto_profile(struct blk_crypto_profile *profile) { - struct dm_keyslot_manager *dksm = container_of(ksm, - struct dm_keyslot_manager, - ksm); + struct dm_crypto_profile *dmcp = container_of(profile, + struct dm_crypto_profile, + profile); - if (!ksm) + if (!profile) return; - blk_ksm_destroy(ksm); - kfree(dksm); + blk_crypto_profile_destroy(profile); + kfree(dmcp); } -static void dm_table_destroy_keyslot_manager(struct dm_table *t) +static void dm_table_destroy_crypto_profile(struct dm_table *t) { - dm_destroy_keyslot_manager(t->ksm); - t->ksm = NULL; + dm_destroy_crypto_profile(t->crypto_profile); + t->crypto_profile = NULL; } /* - * Constructs and initializes t->ksm with a keyslot manager that - * represents the common set of crypto capabilities of the devices - * described by the dm_table. However, if the constructed keyslot - * manager does not support a superset of the crypto capabilities - * supported by the current keyslot manager of the mapped_device, - * it returns an error instead, since we don't support restricting - * crypto capabilities on table changes. Finally, if the constructed - * keyslot manager doesn't actually support any crypto modes at all, - * it just returns NULL. + * Constructs and initializes t->crypto_profile with a crypto profile that + * represents the common set of crypto capabilities of the devices described by + * the dm_table. However, if the constructed crypto profile doesn't support all + * crypto capabilities that are supported by the current mapped_device, it + * returns an error instead, since we don't support removing crypto capabilities + * on table changes. Finally, if the constructed crypto profile is "empty" (has + * no crypto capabilities at all), it just sets t->crypto_profile to NULL. */ -static int dm_table_construct_keyslot_manager(struct dm_table *t) +static int dm_table_construct_crypto_profile(struct dm_table *t) { - struct dm_keyslot_manager *dksm; - struct blk_keyslot_manager *ksm; + struct dm_crypto_profile *dmcp; + struct blk_crypto_profile *profile; struct dm_target *ti; unsigned int i; - bool ksm_is_empty = true; + bool empty_profile = true; - dksm = kmalloc(sizeof(*dksm), GFP_KERNEL); - if (!dksm) + dmcp = kmalloc(sizeof(*dmcp), GFP_KERNEL); + if (!dmcp) return -ENOMEM; - dksm->md = t->md; + dmcp->md = t->md; - ksm = &dksm->ksm; - blk_ksm_init_passthrough(ksm); - ksm->ksm_ll_ops = dm_ksm_ll_ops; - ksm->max_dun_bytes_supported = UINT_MAX; - memset(ksm->crypto_modes_supported, 0xFF, - sizeof(ksm->crypto_modes_supported)); + profile = &dmcp->profile; + blk_crypto_profile_init(profile, 0); + profile->ll_ops.keyslot_evict = dm_keyslot_evict; + profile->max_dun_bytes_supported = UINT_MAX; + memset(profile->modes_supported, 0xFF, + sizeof(profile->modes_supported)); for (i = 0; i < dm_table_get_num_targets(t); i++) { ti = dm_table_get_target(t, i); if (!dm_target_passes_crypto(ti->type)) { - blk_ksm_intersect_modes(ksm, NULL); + blk_crypto_intersect_capabilities(profile, NULL); break; } if (!ti->type->iterate_devices) continue; - ti->type->iterate_devices(ti, device_intersect_crypto_modes, - ksm); + ti->type->iterate_devices(ti, + device_intersect_crypto_capabilities, + profile); } - if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) { + if (t->md->queue && + !blk_crypto_has_capabilities(profile, + t->md->queue->crypto_profile)) { DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); - dm_destroy_keyslot_manager(ksm); + dm_destroy_crypto_profile(profile); return -EINVAL; } /* - * If the new KSM doesn't actually support any crypto modes, we may as - * well represent it with a NULL ksm. + * If the new profile doesn't actually support any crypto capabilities, + * we may as well represent it with a NULL profile. */ - ksm_is_empty = true; - for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) { - if (ksm->crypto_modes_supported[i]) { - ksm_is_empty = false; + for (i = 0; i < ARRAY_SIZE(profile->modes_supported); i++) { + if (profile->modes_supported[i]) { + empty_profile = false; break; } } - if (ksm_is_empty) { - dm_destroy_keyslot_manager(ksm); - ksm = NULL; + if (empty_profile) { + dm_destroy_crypto_profile(profile); + profile = NULL; } /* - * t->ksm is only set temporarily while the table is being set - * up, and it gets set to NULL after the capabilities have - * been transferred to the request_queue. + * t->crypto_profile is only set temporarily while the table is being + * set up, and it gets set to NULL after the profile has been + * transferred to the request_queue. */ - t->ksm = ksm; + t->crypto_profile = profile; return 0; } -static void dm_update_keyslot_manager(struct request_queue *q, - struct dm_table *t) +static void dm_update_crypto_profile(struct request_queue *q, + struct dm_table *t) { - if (!t->ksm) + if (!t->crypto_profile) return; - /* Make the ksm less restrictive */ - if (!q->ksm) { - blk_ksm_register(t->ksm, q); + /* Make the crypto profile less restrictive. */ + if (!q->crypto_profile) { + blk_crypto_register(t->crypto_profile, q); } else { - blk_ksm_update_capabilities(q->ksm, t->ksm); - dm_destroy_keyslot_manager(t->ksm); + blk_crypto_update_capabilities(q->crypto_profile, + t->crypto_profile); + dm_destroy_crypto_profile(t->crypto_profile); } - t->ksm = NULL; + t->crypto_profile = NULL; } #else /* CONFIG_BLK_INLINE_ENCRYPTION */ -static int dm_table_construct_keyslot_manager(struct dm_table *t) +static int dm_table_construct_crypto_profile(struct dm_table *t) { return 0; } -void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm) +void dm_destroy_crypto_profile(struct blk_crypto_profile *profile) { } -static void dm_table_destroy_keyslot_manager(struct dm_table *t) +static void dm_table_destroy_crypto_profile(struct dm_table *t) { } -static void dm_update_keyslot_manager(struct request_queue *q, - struct dm_table *t) +static void dm_update_crypto_profile(struct request_queue *q, + struct dm_table *t) { } @@ -1415,9 +1411,9 @@ int dm_table_complete(struct dm_table *t) return r; } - r = dm_table_construct_keyslot_manager(t); + r = dm_table_construct_crypto_profile(t); if (r) { - DMERR("could not construct keyslot manager."); + DMERR("could not construct crypto profile."); return r; } @@ -2071,7 +2067,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, return r; } - dm_update_keyslot_manager(q, t); + dm_update_crypto_profile(q, t); disk_update_readahead(t->md->disk); return 0; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4184fd8ccb08..8b91f4f0e053 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1663,14 +1663,14 @@ static const struct dax_operations dm_dax_ops; static void dm_wq_work(struct work_struct *work); #ifdef CONFIG_BLK_INLINE_ENCRYPTION -static void dm_queue_destroy_keyslot_manager(struct request_queue *q) +static void dm_queue_destroy_crypto_profile(struct request_queue *q) { - dm_destroy_keyslot_manager(q->ksm); + dm_destroy_crypto_profile(q->crypto_profile); } #else /* CONFIG_BLK_INLINE_ENCRYPTION */ -static inline void dm_queue_destroy_keyslot_manager(struct request_queue *q) +static inline void dm_queue_destroy_crypto_profile(struct request_queue *q) { } #endif /* !CONFIG_BLK_INLINE_ENCRYPTION */ @@ -1696,7 +1696,7 @@ static void cleanup_mapped_device(struct mapped_device *md) dm_sysfs_exit(md); del_gendisk(md->disk); } - dm_queue_destroy_keyslot_manager(md->queue); + dm_queue_destroy_crypto_profile(md->queue); blk_cleanup_disk(md->disk); } diff --git a/drivers/mmc/core/crypto.c b/drivers/mmc/core/crypto.c index 67557808cada..fec4fbf16a5b 100644 --- a/drivers/mmc/core/crypto.c +++ b/drivers/mmc/core/crypto.c @@ -16,13 +16,13 @@ void mmc_crypto_set_initial_state(struct mmc_host *host) { /* Reset might clear all keys, so reprogram all the keys. */ if (host->caps2 & MMC_CAP2_CRYPTO) - blk_ksm_reprogram_all_keys(&host->ksm); + blk_crypto_reprogram_all_keys(&host->crypto_profile); } void mmc_crypto_setup_queue(struct request_queue *q, struct mmc_host *host) { if (host->caps2 & MMC_CAP2_CRYPTO) - blk_ksm_register(&host->ksm, q); + blk_crypto_register(&host->crypto_profile, q); } EXPORT_SYMBOL_GPL(mmc_crypto_setup_queue); @@ -30,12 +30,15 @@ void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq) { struct request *req = mmc_queue_req_to_req(mqrq); struct mmc_request *mrq = &mqrq->brq.mrq; + struct blk_crypto_keyslot *keyslot; if (!req->crypt_ctx) return; mrq->crypto_ctx = req->crypt_ctx; - if (req->crypt_keyslot) - mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot); + + keyslot = req->crypt_keyslot; + if (keyslot) + mrq->crypto_key_slot = blk_crypto_keyslot_index(keyslot); } EXPORT_SYMBOL_GPL(mmc_crypto_prepare_req); diff --git a/drivers/mmc/host/cqhci-crypto.c b/drivers/mmc/host/cqhci-crypto.c index 628bbfaf8312..d5f4b6972f63 100644 --- a/drivers/mmc/host/cqhci-crypto.c +++ b/drivers/mmc/host/cqhci-crypto.c @@ -23,9 +23,10 @@ static const struct cqhci_crypto_alg_entry { }; static inline struct cqhci_host * -cqhci_host_from_ksm(struct blk_keyslot_manager *ksm) +cqhci_host_from_crypto_profile(struct blk_crypto_profile *profile) { - struct mmc_host *mmc = container_of(ksm, struct mmc_host, ksm); + struct mmc_host *mmc = + container_of(profile, struct mmc_host, crypto_profile); return mmc->cqe_private; } @@ -57,12 +58,12 @@ static int cqhci_crypto_program_key(struct cqhci_host *cq_host, return 0; } -static int cqhci_crypto_keyslot_program(struct blk_keyslot_manager *ksm, +static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct cqhci_host *cq_host = cqhci_host_from_ksm(ksm); + struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile); const union cqhci_crypto_cap_entry *ccap_array = cq_host->crypto_cap_array; const struct cqhci_crypto_alg_entry *alg = @@ -115,11 +116,11 @@ static int cqhci_crypto_clear_keyslot(struct cqhci_host *cq_host, int slot) return cqhci_crypto_program_key(cq_host, &cfg, slot); } -static int cqhci_crypto_keyslot_evict(struct blk_keyslot_manager *ksm, +static int cqhci_crypto_keyslot_evict(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct cqhci_host *cq_host = cqhci_host_from_ksm(ksm); + struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile); return cqhci_crypto_clear_keyslot(cq_host, slot); } @@ -132,7 +133,7 @@ static int cqhci_crypto_keyslot_evict(struct blk_keyslot_manager *ksm, * "enabled" when these are called, i.e. CQHCI_ENABLE might not be set in the * CQHCI_CFG register. But the hardware allows that. */ -static const struct blk_ksm_ll_ops cqhci_ksm_ops = { +static const struct blk_crypto_ll_ops cqhci_crypto_ops = { .keyslot_program = cqhci_crypto_keyslot_program, .keyslot_evict = cqhci_crypto_keyslot_evict, }; @@ -157,8 +158,8 @@ cqhci_find_blk_crypto_mode(union cqhci_crypto_cap_entry cap) * * If the driver previously set MMC_CAP2_CRYPTO and the CQE declares * CQHCI_CAP_CS, initialize the crypto support. This involves reading the - * crypto capability registers, initializing the keyslot manager, clearing all - * keyslots, and enabling 128-bit task descriptors. + * crypto capability registers, initializing the blk_crypto_profile, clearing + * all keyslots, and enabling 128-bit task descriptors. * * Return: 0 if crypto was initialized or isn't supported; whether * MMC_CAP2_CRYPTO remains set indicates which one of those cases it is. @@ -168,7 +169,7 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) { struct mmc_host *mmc = cq_host->mmc; struct device *dev = mmc_dev(mmc); - struct blk_keyslot_manager *ksm = &mmc->ksm; + struct blk_crypto_profile *profile = &mmc->crypto_profile; unsigned int num_keyslots; unsigned int cap_idx; enum blk_crypto_mode_num blk_mode_num; @@ -199,15 +200,15 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) */ num_keyslots = cq_host->crypto_capabilities.config_count + 1; - err = devm_blk_ksm_init(dev, ksm, num_keyslots); + err = devm_blk_crypto_profile_init(dev, profile, num_keyslots); if (err) goto out; - ksm->ksm_ll_ops = cqhci_ksm_ops; - ksm->dev = dev; + profile->ll_ops = cqhci_crypto_ops; + profile->dev = dev; /* Unfortunately, CQHCI crypto only supports 32 DUN bits. */ - ksm->max_dun_bytes_supported = 4; + profile->max_dun_bytes_supported = 4; /* * Cache all the crypto capabilities and advertise the supported crypto @@ -223,7 +224,7 @@ int cqhci_crypto_init(struct cqhci_host *cq_host) cq_host->crypto_cap_array[cap_idx]); if (blk_mode_num == BLK_ENCRYPTION_MODE_INVALID) continue; - ksm->crypto_modes_supported[blk_mode_num] |= + profile->modes_supported[blk_mode_num] |= cq_host->crypto_cap_array[cap_idx].sdus_mask * 512; } diff --git a/drivers/scsi/ufs/ufshcd-crypto.c b/drivers/scsi/ufs/ufshcd-crypto.c index d70cdcd35e43..67402baf6fae 100644 --- a/drivers/scsi/ufs/ufshcd-crypto.c +++ b/drivers/scsi/ufs/ufshcd-crypto.c @@ -48,11 +48,12 @@ out: return err; } -static int ufshcd_crypto_keyslot_program(struct blk_keyslot_manager *ksm, +static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct ufs_hba *hba = container_of(ksm, struct ufs_hba, ksm); + struct ufs_hba *hba = + container_of(profile, struct ufs_hba, crypto_profile); const union ufs_crypto_cap_entry *ccap_array = hba->crypto_cap_array; const struct ufs_crypto_alg_entry *alg = &ufs_crypto_algs[key->crypto_cfg.crypto_mode]; @@ -105,11 +106,12 @@ static int ufshcd_clear_keyslot(struct ufs_hba *hba, int slot) return ufshcd_program_key(hba, &cfg, slot); } -static int ufshcd_crypto_keyslot_evict(struct blk_keyslot_manager *ksm, +static int ufshcd_crypto_keyslot_evict(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot) { - struct ufs_hba *hba = container_of(ksm, struct ufs_hba, ksm); + struct ufs_hba *hba = + container_of(profile, struct ufs_hba, crypto_profile); return ufshcd_clear_keyslot(hba, slot); } @@ -120,11 +122,11 @@ bool ufshcd_crypto_enable(struct ufs_hba *hba) return false; /* Reset might clear all keys, so reprogram all the keys. */ - blk_ksm_reprogram_all_keys(&hba->ksm); + blk_crypto_reprogram_all_keys(&hba->crypto_profile); return true; } -static const struct blk_ksm_ll_ops ufshcd_ksm_ops = { +static const struct blk_crypto_ll_ops ufshcd_crypto_ops = { .keyslot_program = ufshcd_crypto_keyslot_program, .keyslot_evict = ufshcd_crypto_keyslot_evict, }; @@ -179,15 +181,16 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba) } /* The actual number of configurations supported is (CFGC+1) */ - err = devm_blk_ksm_init(hba->dev, &hba->ksm, - hba->crypto_capabilities.config_count + 1); + err = devm_blk_crypto_profile_init( + hba->dev, &hba->crypto_profile, + hba->crypto_capabilities.config_count + 1); if (err) goto out; - hba->ksm.ksm_ll_ops = ufshcd_ksm_ops; + hba->crypto_profile.ll_ops = ufshcd_crypto_ops; /* UFS only supports 8 bytes for any DUN */ - hba->ksm.max_dun_bytes_supported = 8; - hba->ksm.dev = hba->dev; + hba->crypto_profile.max_dun_bytes_supported = 8; + hba->crypto_profile.dev = hba->dev; /* * Cache all the UFS crypto capabilities and advertise the supported @@ -202,7 +205,7 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba) blk_mode_num = ufshcd_find_blk_crypto_mode( hba->crypto_cap_array[cap_idx]); if (blk_mode_num != BLK_ENCRYPTION_MODE_INVALID) - hba->ksm.crypto_modes_supported[blk_mode_num] |= + hba->crypto_profile.modes_supported[blk_mode_num] |= hba->crypto_cap_array[cap_idx].sdus_mask * 512; } @@ -230,9 +233,8 @@ void ufshcd_init_crypto(struct ufs_hba *hba) ufshcd_clear_keyslot(hba, slot); } -void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba, - struct request_queue *q) +void ufshcd_crypto_register(struct ufs_hba *hba, struct request_queue *q) { if (hba->caps & UFSHCD_CAP_CRYPTO) - blk_ksm_register(&hba->ksm, q); + blk_crypto_register(&hba->crypto_profile, q); } diff --git a/drivers/scsi/ufs/ufshcd-crypto.h b/drivers/scsi/ufs/ufshcd-crypto.h index 78a58e788dff..e18c01276873 100644 --- a/drivers/scsi/ufs/ufshcd-crypto.h +++ b/drivers/scsi/ufs/ufshcd-crypto.h @@ -18,7 +18,7 @@ static inline void ufshcd_prepare_lrbp_crypto(struct request *rq, return; } - lrbp->crypto_key_slot = blk_ksm_get_slot_idx(rq->crypt_keyslot); + lrbp->crypto_key_slot = blk_crypto_keyslot_index(rq->crypt_keyslot); lrbp->data_unit_num = rq->crypt_ctx->bc_dun[0]; } @@ -40,8 +40,7 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba); void ufshcd_init_crypto(struct ufs_hba *hba); -void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba, - struct request_queue *q); +void ufshcd_crypto_register(struct ufs_hba *hba, struct request_queue *q); #else /* CONFIG_SCSI_UFS_CRYPTO */ @@ -64,8 +63,8 @@ static inline int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba) static inline void ufshcd_init_crypto(struct ufs_hba *hba) { } -static inline void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba, - struct request_queue *q) { } +static inline void ufshcd_crypto_register(struct ufs_hba *hba, + struct request_queue *q) { } #endif /* CONFIG_SCSI_UFS_CRYPTO */ diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 95be7ecdfe10..bf81da2ecf98 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -4986,7 +4986,7 @@ static int ufshcd_slave_configure(struct scsi_device *sdev) else if (ufshcd_is_rpm_autosuspend_allowed(hba)) sdev->rpm_autosuspend = 1; - ufshcd_crypto_setup_rq_keyslot_manager(hba, q); + ufshcd_crypto_register(hba, q); return 0; } diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index 885fcf2e5922..62bdc412d38a 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -766,7 +766,7 @@ struct ufs_hba_monitor { * @crypto_capabilities: Content of crypto capabilities register (0x100) * @crypto_cap_array: Array of crypto capabilities * @crypto_cfg_register: Start of the crypto cfg array - * @ksm: the keyslot manager tied to this hba + * @crypto_profile: the crypto profile of this hba (if applicable) */ struct ufs_hba { void __iomem *mmio_base; @@ -911,7 +911,7 @@ struct ufs_hba { union ufs_crypto_capabilities crypto_capabilities; union ufs_crypto_cap_entry *crypto_cap_array; u32 crypto_cfg_register; - struct blk_keyslot_manager ksm; + struct blk_crypto_profile crypto_profile; #endif #ifdef CONFIG_DEBUG_FS struct dentry *debugfs_root; diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h index a27605e2f826..bbab65bd5428 100644 --- a/include/linux/blk-crypto-profile.h +++ b/include/linux/blk-crypto-profile.h @@ -3,67 +3,113 @@ * Copyright 2019 Google LLC */ -#ifndef __LINUX_KEYSLOT_MANAGER_H -#define __LINUX_KEYSLOT_MANAGER_H +#ifndef __LINUX_BLK_CRYPTO_PROFILE_H +#define __LINUX_BLK_CRYPTO_PROFILE_H #include #include -struct blk_keyslot_manager; +struct blk_crypto_profile; /** - * struct blk_ksm_ll_ops - functions to manage keyslots in hardware - * @keyslot_program: Program the specified key into the specified slot in the - * inline encryption hardware. - * @keyslot_evict: Evict key from the specified keyslot in the hardware. - * The key is provided so that e.g. dm layers can evict - * keys from the devices that they map over. - * Returns 0 on success, -errno otherwise. + * struct blk_crypto_ll_ops - functions to control inline encryption hardware * - * This structure should be provided by storage device drivers when they set up - * a keyslot manager - this structure holds the function ptrs that the keyslot - * manager will use to manipulate keyslots in the hardware. + * Low-level operations for controlling inline encryption hardware. This + * interface must be implemented by storage drivers that support inline + * encryption. All functions may sleep, are serialized by profile->lock, and + * are never called while profile->dev (if set) is runtime-suspended. */ -struct blk_ksm_ll_ops { - int (*keyslot_program)(struct blk_keyslot_manager *ksm, +struct blk_crypto_ll_ops { + + /** + * @keyslot_program: Program a key into the inline encryption hardware. + * + * Program @key into the specified @slot in the inline encryption + * hardware, overwriting any key that the keyslot may already contain. + * The keyslot is guaranteed to not be in-use by any I/O. + * + * This is required if the device has keyslots. Otherwise (i.e. if the + * device is a layered device, or if the device is real hardware that + * simply doesn't have the concept of keyslots) it is never called. + * + * Must return 0 on success, or -errno on failure. + */ + int (*keyslot_program)(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot); - int (*keyslot_evict)(struct blk_keyslot_manager *ksm, + + /** + * @keyslot_evict: Evict a key from the inline encryption hardware. + * + * If the device has keyslots, this function must evict the key from the + * specified @slot. The slot will contain @key, but there should be no + * need for the @key argument to be used as @slot should be sufficient. + * The keyslot is guaranteed to not be in-use by any I/O. + * + * If the device doesn't have keyslots itself, this function must evict + * @key from any underlying devices. @slot won't be valid in this case. + * + * If there are no keyslots and no underlying devices, this function + * isn't required. + * + * Must return 0 on success, or -errno on failure. + */ + int (*keyslot_evict)(struct blk_crypto_profile *profile, const struct blk_crypto_key *key, unsigned int slot); }; -struct blk_keyslot_manager { - /* - * The struct blk_ksm_ll_ops that this keyslot manager will use - * to perform operations like programming and evicting keys on the - * device +/** + * struct blk_crypto_profile - inline encryption profile for a device + * + * This struct contains a storage device's inline encryption capabilities (e.g. + * the supported crypto algorithms), driver-provided functions to control the + * inline encryption hardware (e.g. programming and evicting keys), and optional + * device-independent keyslot management data. + */ +struct blk_crypto_profile { + + /* public: Drivers must initialize the following fields. */ + + /** + * @ll_ops: Driver-provided functions to control the inline encryption + * hardware, e.g. program and evict keys. */ - struct blk_ksm_ll_ops ksm_ll_ops; + struct blk_crypto_ll_ops ll_ops; - /* - * The maximum number of bytes supported for specifying the data unit - * number. + /** + * @max_dun_bytes_supported: The maximum number of bytes supported for + * specifying the data unit number (DUN). Specifically, the range of + * supported DUNs is 0 through (1 << (8 * max_dun_bytes_supported)) - 1. */ unsigned int max_dun_bytes_supported; - /* - * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents - * whether a crypto mode and data unit size are supported. The i'th - * bit of crypto_mode_supported[crypto_mode] is set iff a data unit - * size of (1 << i) is supported. We only support data unit sizes - * that are powers of 2. + /** + * @modes_supported: Array of bitmasks that specifies whether each + * combination of crypto mode and data unit size is supported. + * Specifically, the i'th bit of modes_supported[crypto_mode] is set if + * crypto_mode can be used with a data unit size of (1 << i). Note that + * only data unit sizes that are powers of 2 can be supported. */ - unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX]; + unsigned int modes_supported[BLK_ENCRYPTION_MODE_MAX]; - /* Device for runtime power management (NULL if none) */ + /** + * @dev: An optional device for runtime power management. If the driver + * provides this device, it will be runtime-resumed before any function + * in @ll_ops is called and will remain resumed during the call. + */ struct device *dev; - /* Here onwards are *private* fields for internal keyslot manager use */ + /* private: The following fields shouldn't be accessed by drivers. */ + /* Number of keyslots, or 0 if not applicable */ unsigned int num_slots; - /* Protects programming and evicting keys from the device */ + /* + * Serializes all calls to functions in @ll_ops as well as all changes + * to @slot_hashtable. This can also be taken in read mode to look up + * keyslots while ensuring that they can't be changed concurrently. + */ struct rw_semaphore lock; /* List of idle slots, with least recently used slot at front */ @@ -80,41 +126,41 @@ struct blk_keyslot_manager { unsigned int log_slot_ht_size; /* Per-keyslot data */ - struct blk_ksm_keyslot *slots; + struct blk_crypto_keyslot *slots; }; -int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots); - -int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm, - unsigned int num_slots); +int blk_crypto_profile_init(struct blk_crypto_profile *profile, + unsigned int num_slots); -blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key, - struct blk_ksm_keyslot **slot_ptr); +int devm_blk_crypto_profile_init(struct device *dev, + struct blk_crypto_profile *profile, + unsigned int num_slots); -unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot); +unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot); -void blk_ksm_put_slot(struct blk_ksm_keyslot *slot); +blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, + struct blk_crypto_keyslot **slot_ptr); -bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm, - const struct blk_crypto_config *cfg); +void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot); -int blk_ksm_evict_key(struct blk_keyslot_manager *ksm, - const struct blk_crypto_key *key); +bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile, + const struct blk_crypto_config *cfg); -void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm); +int __blk_crypto_evict_key(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key); -void blk_ksm_destroy(struct blk_keyslot_manager *ksm); +void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile); -void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent, - const struct blk_keyslot_manager *child); +void blk_crypto_profile_destroy(struct blk_crypto_profile *profile); -void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm); +void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent, + const struct blk_crypto_profile *child); -bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset, - struct blk_keyslot_manager *ksm_subset); +bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target, + const struct blk_crypto_profile *reference); -void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm, - struct blk_keyslot_manager *reference_ksm); +void blk_crypto_update_capabilities(struct blk_crypto_profile *dst, + const struct blk_crypto_profile *src); -#endif /* __LINUX_KEYSLOT_MANAGER_H */ +#endif /* __LINUX_BLK_CRYPTO_PROFILE_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index e13780236550..b4039fdf1b04 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -133,7 +133,7 @@ struct request { #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; - struct blk_ksm_keyslot *crypt_keyslot; + struct blk_crypto_keyslot *crypt_keyslot; #endif unsigned short write_hint; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c7b1e9355123..f72ccb2829db 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -30,7 +30,7 @@ struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; -struct blk_keyslot_manager; +struct blk_crypto_profile; /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 @@ -224,8 +224,7 @@ struct request_queue { unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION - /* Inline crypto capabilities */ - struct blk_keyslot_manager *ksm; + struct blk_crypto_profile *crypto_profile; #endif unsigned int rq_timeout; @@ -1142,19 +1141,20 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo #ifdef CONFIG_BLK_INLINE_ENCRYPTION -bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); +bool blk_crypto_register(struct blk_crypto_profile *profile, + struct request_queue *q); -void blk_ksm_unregister(struct request_queue *q); +void blk_crypto_unregister(struct request_queue *q); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ -static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm, - struct request_queue *q) +static inline bool blk_crypto_register(struct blk_crypto_profile *profile, + struct request_queue *q) { return true; } -static inline void blk_ksm_unregister(struct request_queue *q) { } +static inline void blk_crypto_unregister(struct request_queue *q) { } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 114553b487ef..a7df155ea49b 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -576,9 +576,9 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *t); /* - * Table keyslot manager functions + * Table blk_crypto_profile functions */ -void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm); +void dm_destroy_crypto_profile(struct blk_crypto_profile *profile); /*----------------------------------------------------------------- * Macros. diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index 725b1de41767..52eae8c45b8d 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -492,7 +492,7 @@ struct mmc_host { /* Inline encryption support */ #ifdef CONFIG_MMC_CRYPTO - struct blk_keyslot_manager ksm; + struct blk_crypto_profile crypto_profile; #endif /* Host Software Queue support */ -- cgit v1.2.3 From f64dd4627ec6edc39bf1430fe6dbc923d2300a88 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Oct 2021 11:13:34 +0200 Subject: ftrace: Add multi direct register/unregister interface Adding interface to register multiple direct functions within single call. Adding following functions: register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) The register_ftrace_direct_multi registers direct function (addr) with all functions in ops filter. The ops filter can be updated before with ftrace_set_filter_ip calls. All requested functions must not have direct function currently registered, otherwise register_ftrace_direct_multi will fail. The unregister_ftrace_direct_multi unregisters ops related direct functions. Link: https://lkml.kernel.org/r/20211008091336.33616-7-jolsa@kernel.org Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 11 ++++ kernel/trace/ftrace.c | 142 +++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 153 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 16a7baaba702..0158261cac9f 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -324,7 +324,10 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, unsigned long old_addr, unsigned long new_addr); unsigned long ftrace_find_rec_direct(unsigned long ip); +int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); +int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); #else +struct ftrace_ops; # define ftrace_direct_func_count 0 static inline int register_ftrace_direct(unsigned long ip, unsigned long addr) { @@ -354,6 +357,14 @@ static inline unsigned long ftrace_find_rec_direct(unsigned long ip) { return 0; } +static inline int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} +static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index ccbd8377e580..a05b25fb77d8 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5401,6 +5401,148 @@ int modify_ftrace_direct(unsigned long ip, return ret; } EXPORT_SYMBOL_GPL(modify_ftrace_direct); + +#define MULTI_FLAGS (FTRACE_OPS_FL_IPMODIFY | FTRACE_OPS_FL_DIRECT | \ + FTRACE_OPS_FL_SAVE_REGS) + +static int check_direct_multi(struct ftrace_ops *ops) +{ + if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) + return -EINVAL; + if ((ops->flags & MULTI_FLAGS) != MULTI_FLAGS) + return -EINVAL; + return 0; +} + +static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long addr) +{ + struct ftrace_func_entry *entry, *del; + int size, i; + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + del = __ftrace_lookup_ip(direct_functions, entry->ip); + if (del && del->direct == addr) { + remove_hash_entry(direct_functions, del); + kfree(del); + } + } + } +} + +/** + * register_ftrace_direct_multi - Call a custom trampoline directly + * for multiple functions registered in @ops + * @ops: The address of the struct ftrace_ops object + * @addr: The address of the trampoline to call at @ops functions + * + * This is used to connect a direct calls to @addr from the nop locations + * of the functions registered in @ops (with by ftrace_set_filter_ip + * function). + * + * The location that it calls (@addr) must be able to handle a direct call, + * and save the parameters of the function being traced, and restore them + * (or inject new ones if needed), before returning. + * + * Returns: + * 0 on success + * -EINVAL - The @ops object was already registered with this call or + * when there are no functions in @ops object. + * -EBUSY - Another direct function is already attached (there can be only one) + * -ENODEV - @ip does not point to a ftrace nop location (or not supported) + * -ENOMEM - There was an allocation failure. + */ +int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +{ + struct ftrace_hash *hash, *free_hash = NULL; + struct ftrace_func_entry *entry, *new; + int err = -EBUSY, size, i; + + if (ops->func || ops->trampoline) + return -EINVAL; + if (!(ops->flags & FTRACE_OPS_FL_INITIALIZED)) + return -EINVAL; + if (ops->flags & FTRACE_OPS_FL_ENABLED) + return -EINVAL; + + hash = ops->func_hash->filter_hash; + if (ftrace_hash_empty(hash)) + return -EINVAL; + + mutex_lock(&direct_mutex); + + /* Make sure requested entries are not already registered.. */ + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + if (ftrace_find_rec_direct(entry->ip)) + goto out_unlock; + } + } + + /* ... and insert them to direct_functions hash. */ + err = -ENOMEM; + for (i = 0; i < size; i++) { + hlist_for_each_entry(entry, &hash->buckets[i], hlist) { + new = ftrace_add_rec_direct(entry->ip, addr, &free_hash); + if (!new) + goto out_remove; + entry->direct = addr; + } + } + + ops->func = call_direct_funcs; + ops->flags = MULTI_FLAGS; + ops->trampoline = FTRACE_REGS_ADDR; + + err = register_ftrace_function(ops); + + out_remove: + if (err) + remove_direct_functions_hash(hash, addr); + + out_unlock: + mutex_unlock(&direct_mutex); + + if (free_hash) { + synchronize_rcu_tasks(); + free_ftrace_hash(free_hash); + } + return err; +} +EXPORT_SYMBOL_GPL(register_ftrace_direct_multi); + +/** + * unregister_ftrace_direct_multi - Remove calls to custom trampoline + * previously registered by register_ftrace_direct_multi for @ops object. + * @ops: The address of the struct ftrace_ops object + * + * This is used to remove a direct calls to @addr from the nop locations + * of the functions registered in @ops (with by ftrace_set_filter_ip + * function). + * + * Returns: + * 0 on success + * -EINVAL - The @ops object was not properly registered. + */ +int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +{ + struct ftrace_hash *hash = ops->func_hash->filter_hash; + int err; + + if (check_direct_multi(ops)) + return -EINVAL; + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EINVAL; + + mutex_lock(&direct_mutex); + err = unregister_ftrace_function(ops); + remove_direct_functions_hash(hash, addr); + mutex_unlock(&direct_mutex); + return err; +} +EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi); #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /** -- cgit v1.2.3 From ccf5a89efd6f0a9483cea8acd4a0822b1a47e59a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 8 Oct 2021 11:13:35 +0200 Subject: ftrace: Add multi direct modify interface Adding interface to modify registered direct function for ftrace_ops. Adding following function: modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) The function changes the currently registered direct function for all attached functions. Link: https://lkml.kernel.org/r/20211008091336.33616-8-jolsa@kernel.org Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 6 +++++ kernel/trace/ftrace.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 68 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0158261cac9f..9999e29187de 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -326,6 +326,8 @@ int ftrace_modify_direct_caller(struct ftrace_func_entry *entry, unsigned long ftrace_find_rec_direct(unsigned long ip); int register_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); +int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr); + #else struct ftrace_ops; # define ftrace_direct_func_count 0 @@ -365,6 +367,10 @@ static inline int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigne { return -ENODEV; } +static inline int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +{ + return -ENODEV; +} #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ #ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a05b25fb77d8..30120342176e 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5543,6 +5543,68 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) return err; } EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi); + +/** + * modify_ftrace_direct_multi - Modify an existing direct 'multi' call + * to call something else + * @ops: The address of the struct ftrace_ops object + * @addr: The address of the new trampoline to call at @ops functions + * + * This is used to unregister currently registered direct caller and + * register new one @addr on functions registered in @ops object. + * + * Note there's window between ftrace_shutdown and ftrace_startup calls + * where there will be no callbacks called. + * + * Returns: zero on success. Non zero on error, which includes: + * -EINVAL - The @ops object was not properly registered. + */ +int modify_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) +{ + struct ftrace_hash *hash = ops->func_hash->filter_hash; + struct ftrace_func_entry *entry, *iter; + int i, size; + int err; + + if (check_direct_multi(ops)) + return -EINVAL; + if (!(ops->flags & FTRACE_OPS_FL_ENABLED)) + return -EINVAL; + + mutex_lock(&direct_mutex); + mutex_lock(&ftrace_lock); + + /* + * Shutdown the ops, change 'direct' pointer for each + * ops entry in direct_functions hash and startup the + * ops back again. + * + * Note there is no callback called for @ops object after + * this ftrace_shutdown call until ftrace_startup is called + * later on. + */ + err = ftrace_shutdown(ops, 0); + if (err) + goto out_unlock; + + size = 1 << hash->size_bits; + for (i = 0; i < size; i++) { + hlist_for_each_entry(iter, &hash->buckets[i], hlist) { + entry = __ftrace_lookup_ip(direct_functions, iter->ip); + if (!entry) + continue; + entry->direct = addr; + } + } + + err = ftrace_startup(ops, 0); + + out_unlock: + mutex_unlock(&ftrace_lock); + mutex_unlock(&direct_mutex); + return err; +} +EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi); #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ /** -- cgit v1.2.3 From bce5c81cb31f7f124ce231ec79df9e85a8bac132 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 19 Oct 2021 09:25:20 -0400 Subject: tracing: Explain the trace recursion transition bit better The current text of the explanation of the transition bit in the trace recursion protection is not very clear. Improve the text, so that when all the archs no longer have the issue of tracing between a start of a new (interrupt) context and updating the preempt_count to reflect the new context, that it may be removed. Link: https://lore.kernel.org/all/20211018220203.064a42ed@gandalf.local.home/ Suggested-by: Petr Mladek Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_recursion.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index 1d8cce02c3fb..24f284eb55a7 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -168,8 +168,12 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign bit = trace_get_context_bit() + start; if (unlikely(val & (1 << bit))) { /* - * It could be that preempt_count has not been updated during - * a switch between contexts. Allow for a single recursion. + * If an interrupt occurs during a trace, and another trace + * happens in that interrupt but before the preempt_count is + * updated to reflect the new interrupt context, then this + * will think a recursion occurred, and the event will be dropped. + * Let a single instance happen via the TRANSITION_BIT to + * not drop those events. */ bit = TRACE_TRANSITION_BIT; if (val & (1 << bit)) { -- cgit v1.2.3 From 17b5b576ff5faff99a4c8140d521cd4d7fff5c16 Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Thu, 7 Oct 2021 15:46:39 +0200 Subject: mux: add support for delay after muxing Hardware may require some time for the muxed analog signals to settle after the muxing is changed. Allow users of the mux subsystem to specify this delay with the new mux_control_select_delay() function (and the _try equivalent). Signed-off-by: Vincent Whitchurch Reviewed-by: Lars-Peter Clausen Tested-by: Lars-Peter Clausen Acked-by: Peter Rosin Link: https://lore.kernel.org/r/20211007134641.13417-2-vincent.whitchurch@axis.com Signed-off-by: Jonathan Cameron --- drivers/mux/core.c | 38 ++++++++++++++++++++++++++++++++------ include/linux/mux/consumer.h | 23 +++++++++++++++++++---- include/linux/mux/driver.h | 4 ++++ 3 files changed, 55 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/mux/core.c b/drivers/mux/core.c index 1fb22388e7e0..22f4709768d1 100644 --- a/drivers/mux/core.c +++ b/drivers/mux/core.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) "mux-core: " fmt +#include #include #include #include @@ -116,6 +117,7 @@ struct mux_chip *mux_chip_alloc(struct device *dev, sema_init(&mux->lock, 1); mux->cached_state = MUX_CACHE_UNKNOWN; mux->idle_state = MUX_IDLE_AS_IS; + mux->last_change = ktime_get(); } device_initialize(&mux_chip->dev); @@ -129,6 +131,8 @@ static int mux_control_set(struct mux_control *mux, int state) int ret = mux->chip->ops->set(mux, state); mux->cached_state = ret < 0 ? MUX_CACHE_UNKNOWN : state; + if (ret >= 0) + mux->last_change = ktime_get(); return ret; } @@ -314,10 +318,25 @@ static int __mux_control_select(struct mux_control *mux, int state) return ret; } +static void mux_control_delay(struct mux_control *mux, unsigned int delay_us) +{ + ktime_t delayend; + s64 remaining; + + if (!delay_us) + return; + + delayend = ktime_add_us(mux->last_change, delay_us); + remaining = ktime_us_delta(delayend, ktime_get()); + if (remaining > 0) + fsleep(remaining); +} + /** - * mux_control_select() - Select the given multiplexer state. + * mux_control_select_delay() - Select the given multiplexer state. * @mux: The mux-control to request a change of state from. * @state: The new requested state. + * @delay_us: The time to delay (in microseconds) if the mux state is changed. * * On successfully selecting the mux-control state, it will be locked until * there is a call to mux_control_deselect(). If the mux-control is already @@ -331,7 +350,8 @@ static int __mux_control_select(struct mux_control *mux, int state) * Return: 0 when the mux-control state has the requested state or a negative * errno on error. */ -int mux_control_select(struct mux_control *mux, unsigned int state) +int mux_control_select_delay(struct mux_control *mux, unsigned int state, + unsigned int delay_us) { int ret; @@ -340,18 +360,21 @@ int mux_control_select(struct mux_control *mux, unsigned int state) return ret; ret = __mux_control_select(mux, state); + if (ret >= 0) + mux_control_delay(mux, delay_us); if (ret < 0) up(&mux->lock); return ret; } -EXPORT_SYMBOL_GPL(mux_control_select); +EXPORT_SYMBOL_GPL(mux_control_select_delay); /** - * mux_control_try_select() - Try to select the given multiplexer state. + * mux_control_try_select_delay() - Try to select the given multiplexer state. * @mux: The mux-control to request a change of state from. * @state: The new requested state. + * @delay_us: The time to delay (in microseconds) if the mux state is changed. * * On successfully selecting the mux-control state, it will be locked until * mux_control_deselect() called. @@ -363,7 +386,8 @@ EXPORT_SYMBOL_GPL(mux_control_select); * Return: 0 when the mux-control state has the requested state or a negative * errno on error. Specifically -EBUSY if the mux-control is contended. */ -int mux_control_try_select(struct mux_control *mux, unsigned int state) +int mux_control_try_select_delay(struct mux_control *mux, unsigned int state, + unsigned int delay_us) { int ret; @@ -371,13 +395,15 @@ int mux_control_try_select(struct mux_control *mux, unsigned int state) return -EBUSY; ret = __mux_control_select(mux, state); + if (ret >= 0) + mux_control_delay(mux, delay_us); if (ret < 0) up(&mux->lock); return ret; } -EXPORT_SYMBOL_GPL(mux_control_try_select); +EXPORT_SYMBOL_GPL(mux_control_try_select_delay); /** * mux_control_deselect() - Deselect the previously selected multiplexer state. diff --git a/include/linux/mux/consumer.h b/include/linux/mux/consumer.h index 5fc6bb2fefad..7a09b040ac39 100644 --- a/include/linux/mux/consumer.h +++ b/include/linux/mux/consumer.h @@ -16,10 +16,25 @@ struct device; struct mux_control; unsigned int mux_control_states(struct mux_control *mux); -int __must_check mux_control_select(struct mux_control *mux, - unsigned int state); -int __must_check mux_control_try_select(struct mux_control *mux, - unsigned int state); +int __must_check mux_control_select_delay(struct mux_control *mux, + unsigned int state, + unsigned int delay_us); +int __must_check mux_control_try_select_delay(struct mux_control *mux, + unsigned int state, + unsigned int delay_us); + +static inline int __must_check mux_control_select(struct mux_control *mux, + unsigned int state) +{ + return mux_control_select_delay(mux, state, 0); +} + +static inline int __must_check mux_control_try_select(struct mux_control *mux, + unsigned int state) +{ + return mux_control_try_select_delay(mux, state, 0); +} + int mux_control_deselect(struct mux_control *mux); struct mux_control *mux_control_get(struct device *dev, const char *mux_name); diff --git a/include/linux/mux/driver.h b/include/linux/mux/driver.h index 627a2c6bc02d..18824064f8c0 100644 --- a/include/linux/mux/driver.h +++ b/include/linux/mux/driver.h @@ -12,6 +12,7 @@ #include #include +#include #include struct mux_chip; @@ -33,6 +34,7 @@ struct mux_control_ops { * @states: The number of mux controller states. * @idle_state: The mux controller state to use when inactive, or one * of MUX_IDLE_AS_IS and MUX_IDLE_DISCONNECT. + * @last_change: Timestamp of last change * * Mux drivers may only change @states and @idle_state, and may only do so * between allocation and registration of the mux controller. Specifically, @@ -47,6 +49,8 @@ struct mux_control { unsigned int states; int idle_state; + + ktime_t last_change; }; /** -- cgit v1.2.3 From 9eeb3aa33ae005526f672b394c1791578463513f Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Thu, 21 Oct 2021 21:47:51 +0800 Subject: bpf: Add bpf_skc_to_unix_sock() helper The helper is used in tracing programs to cast a socket pointer to a unix_sock pointer. The return value could be NULL if the casting is illegal. Suggested-by: Yonghong Song Signed-off-by: Hengqi Chen Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211021134752.1223426-2-hengqi.chen@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 7 +++++++ kernel/trace/bpf_trace.c | 2 ++ net/core/filter.c | 23 +++++++++++++++++++++++ scripts/bpf_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 7 +++++++ 6 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d604c8251d88..be3102b4554b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2093,6 +2093,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6b3153841a33..cbcd0d6fca7c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1608,6 +1608,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; + case BPF_FUNC_skc_to_unix_sock: + return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/filter.c b/net/core/filter.c index 4bace37a6a44..8e8d3b49c297 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10723,6 +10723,26 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; +BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) +{ + /* unix_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct unix_sock); + if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { + .func = bpf_skc_to_unix_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], +}; + BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); @@ -10762,6 +10782,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; + case BPF_FUNC_skc_to_unix_sock: + func = &bpf_skc_to_unix_sock_proto; + break; default: return bpf_base_func_proto(func_id); } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 00ac7b79cddb..a6403ddf5de7 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -537,6 +537,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct __sk_buff', @@ -589,6 +590,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct path', 'struct btf_ptr', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From d08fd747d0ed682b6c6c280ba454cafcad33563d Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 14 Oct 2021 16:35:11 +0200 Subject: Compiler Attributes: remove GCC 5.1 mention GCC 5.1 is now the minimum version. Acked-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_attributes.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index e6ec63403965..87d1e773400c 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -104,7 +104,6 @@ #define __deprecated /* - * Optional: only supported since gcc >= 5.1 * Optional: not supported by clang * Optional: not supported by icc * -- cgit v1.2.3 From aba64c7da98330141dcdadd5612f088043a83696 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Wed, 20 Oct 2021 00:48:17 -0700 Subject: bpf: Add verified_insns to bpf_prog_info and fdinfo This stat is currently printed in the verifier log and not stored anywhere. To ease consumption of this data, add a field to bpf_prog_aux so it can be exposed via BPF_OBJ_GET_INFO_BY_FD and fdinfo. Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20211020074818.1017682-2-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 8 ++++++-- kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be3102b4554b..31421c74ba08 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -887,6 +887,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ + u32 verified_insns; struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e50c0bfdb7d..5beb321b3b3b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1848,7 +1848,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" - "recursion_misses:\t%llu\n", + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, @@ -1856,7 +1857,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) prog->aux->id, stats.nsecs, stats.cnt, - stats.misses); + stats.misses, + prog->aux->verified_insns); } #endif @@ -3625,6 +3627,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; + info.verified_insns = prog->aux->verified_insns; + if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 21cdff35a2f9..c6616e325803 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14033,6 +14033,7 @@ skip_full_check: env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); + env->prog->aux->verified_insns = env->insn_processed; if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From 7c00621dcaeea206d7489b3e8b50b1864841ae69 Mon Sep 17 00:00:00 2001 From: Miguel Ojeda Date: Thu, 14 Oct 2021 15:23:31 +0200 Subject: compiler_types: mark __compiletime_assert failure as __noreturn `__compiletime_assert` declares a fake `extern` function which appears (to the compiler) to be called when the test fails. Therefore, compilers may emit possibly-uninitialized warnings in some cases, even if it will be an error anyway (for compilers supporting the `error` attribute, e.g. GCC and Clang >= 14) or a link failure (for those that do not, e.g. Clang < 14). Annotating the fake function as `__noreturn` gives them the information they need to avoid the warning, e.g. see https://godbolt.org/z/x1v69jjYY. Link: https://lore.kernel.org/llvm/202110100514.3h9CI4s0-lkp@intel.com/ Reported-by: kernel test robot Reviewed-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Miguel Ojeda --- include/linux/compiler_types.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b6ff83a714ca..ca1a66b8cd2f 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -298,7 +298,13 @@ struct ftrace_likely_data { #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ - extern void prefix ## suffix(void) __compiletime_error(msg); \ + /* \ + * __noreturn is needed to give the compiler enough \ + * information to avoid certain possibly-uninitialized \ + * warnings (regardless of the build failing). \ + */ \ + __noreturn extern void prefix ## suffix(void) \ + __compiletime_error(msg); \ if (!(condition)) \ prefix ## suffix(); \ } while (0) -- cgit v1.2.3 From 008d3825a805557464c5e75f9eb806a3aa2f5e6d Mon Sep 17 00:00:00 2001 From: Eddie James Date: Tue, 19 Oct 2021 15:53:04 -0500 Subject: fsi: occ: Use a large buffer for responses Allocate a large buffer for each OCC to handle response data. This removes memory allocation during an operation, and also allows for the maximum amount of SBE FFDC. Previously for the putsram and attn commands, only 32 words would have been available, and for getsram, only up to the size of the transfer. SBE FFDC might be up to 8Kb. The SBE interface expects data to be specified in units of words (4 bytes), defined as OCC_MAX_RESP_WORDS. This change allows the full FFDC capture to be implemented, where before it was not available. Signed-off-by: Eddie James Link: https://lore.kernel.org/r/20211019205307.36946-2-eajames@linux.ibm.com Signed-off-by: Joel Stanley --- drivers/fsi/fsi-occ.c | 110 +++++++++++++++++++----------------------------- include/linux/fsi-occ.h | 2 + 2 files changed, 46 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/fsi/fsi-occ.c b/drivers/fsi/fsi-occ.c index ecf738411fe2..b4302776026d 100644 --- a/drivers/fsi/fsi-occ.c +++ b/drivers/fsi/fsi-occ.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -33,13 +34,6 @@ #define OCC_P10_SRAM_MODE 0x58 /* Normal mode, OCB channel 2 */ -/* - * Assume we don't have much FFDC, if we do we'll overflow and - * fail the command. This needs to be big enough for simple - * commands as well. - */ -#define OCC_SBE_STATUS_WORDS 32 - #define OCC_TIMEOUT_MS 1000 #define OCC_CMD_IN_PRG_WAIT_MS 50 @@ -51,6 +45,7 @@ struct occ { char name[32]; int idx; u8 sequence_number; + void *buffer; enum versions version; struct miscdevice mdev; struct mutex occ_lock; @@ -241,8 +236,10 @@ static int occ_verify_checksum(struct occ *occ, struct occ_response *resp, static int occ_getsram(struct occ *occ, u32 offset, void *data, ssize_t len) { u32 data_len = ((len + 7) / 8) * 8; /* must be multiples of 8 B */ - size_t cmd_len, resp_len, resp_data_len; - __be32 *resp, cmd[6]; + size_t cmd_len, resp_data_len; + size_t resp_len = OCC_MAX_RESP_WORDS; + __be32 *resp = occ->buffer; + __be32 cmd[6]; int idx = 0, rc; /* @@ -269,19 +266,19 @@ static int occ_getsram(struct occ *occ, u32 offset, void *data, ssize_t len) cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_OCC_SRAM); cmd[4 + idx] = cpu_to_be32(data_len); - resp_len = (data_len >> 2) + OCC_SBE_STATUS_WORDS; - resp = kzalloc(resp_len << 2, GFP_KERNEL); - if (!resp) - return -ENOMEM; - rc = sbefifo_submit(occ->sbefifo, cmd, cmd_len, resp, &resp_len); if (rc) - goto free; + return rc; rc = sbefifo_parse_status(occ->sbefifo, SBEFIFO_CMD_GET_OCC_SRAM, resp, resp_len, &resp_len); - if (rc) - goto free; + if (rc > 0) { + dev_err(occ->dev, "SRAM read returned failure status: %08x\n", + rc); + return -EBADMSG; + } else if (rc) { + return rc; + } resp_data_len = be32_to_cpu(resp[resp_len - 1]); if (resp_data_len != data_len) { @@ -292,39 +289,21 @@ static int occ_getsram(struct occ *occ, u32 offset, void *data, ssize_t len) memcpy(data, resp, len); } -free: - /* Convert positive SBEI status */ - if (rc > 0) { - dev_err(occ->dev, "SRAM read returned failure status: %08x\n", - rc); - rc = -EBADMSG; - } - - kfree(resp); return rc; } static int occ_putsram(struct occ *occ, const void *data, ssize_t len, u8 seq_no, u16 checksum) { - size_t cmd_len, buf_len, resp_len, resp_data_len; u32 data_len = ((len + 7) / 8) * 8; /* must be multiples of 8 B */ - __be32 *buf; + size_t cmd_len, resp_data_len; + size_t resp_len = OCC_MAX_RESP_WORDS; + __be32 *buf = occ->buffer; u8 *byte_buf; int idx = 0, rc; cmd_len = (occ->version == occ_p10) ? 6 : 5; - - /* - * We use the same buffer for command and response, make - * sure it's big enough - */ - resp_len = OCC_SBE_STATUS_WORDS; cmd_len += data_len >> 2; - buf_len = max(cmd_len, resp_len); - buf = kzalloc(buf_len << 2, GFP_KERNEL); - if (!buf) - return -ENOMEM; /* * Magic sequence to do SBE putsram command. SBE will transfer @@ -361,12 +340,17 @@ static int occ_putsram(struct occ *occ, const void *data, ssize_t len, rc = sbefifo_submit(occ->sbefifo, buf, cmd_len, buf, &resp_len); if (rc) - goto free; + return rc; rc = sbefifo_parse_status(occ->sbefifo, SBEFIFO_CMD_PUT_OCC_SRAM, buf, resp_len, &resp_len); - if (rc) - goto free; + if (rc > 0) { + dev_err(occ->dev, "SRAM write returned failure status: %08x\n", + rc); + return -EBADMSG; + } else if (rc) { + return rc; + } if (resp_len != 1) { dev_err(occ->dev, "SRAM write response length invalid: %zd\n", @@ -382,27 +366,16 @@ static int occ_putsram(struct occ *occ, const void *data, ssize_t len, } } -free: - /* Convert positive SBEI status */ - if (rc > 0) { - dev_err(occ->dev, "SRAM write returned failure status: %08x\n", - rc); - rc = -EBADMSG; - } - - kfree(buf); return rc; } static int occ_trigger_attn(struct occ *occ) { - __be32 buf[OCC_SBE_STATUS_WORDS]; - size_t cmd_len, resp_len, resp_data_len; + __be32 *buf = occ->buffer; + size_t cmd_len, resp_data_len; + size_t resp_len = OCC_MAX_RESP_WORDS; int idx = 0, rc; - BUILD_BUG_ON(OCC_SBE_STATUS_WORDS < 8); - resp_len = OCC_SBE_STATUS_WORDS; - switch (occ->version) { default: case occ_p9: @@ -427,12 +400,17 @@ static int occ_trigger_attn(struct occ *occ) rc = sbefifo_submit(occ->sbefifo, buf, cmd_len, buf, &resp_len); if (rc) - goto error; + return rc; rc = sbefifo_parse_status(occ->sbefifo, SBEFIFO_CMD_PUT_OCC_SRAM, buf, resp_len, &resp_len); - if (rc) - goto error; + if (rc > 0) { + dev_err(occ->dev, "SRAM attn returned failure status: %08x\n", + rc); + return -EBADMSG; + } else if (rc) { + return rc; + } if (resp_len != 1) { dev_err(occ->dev, "SRAM attn response length invalid: %zd\n", @@ -448,14 +426,6 @@ static int occ_trigger_attn(struct occ *occ) } } - error: - /* Convert positive SBEI status */ - if (rc > 0) { - dev_err(occ->dev, "SRAM attn returned failure status: %08x\n", - rc); - rc = -EBADMSG; - } - return rc; } @@ -590,6 +560,11 @@ static int occ_probe(struct platform_device *pdev) if (!occ) return -ENOMEM; + /* SBE words are always four bytes */ + occ->buffer = kvmalloc(OCC_MAX_RESP_WORDS * 4, GFP_KERNEL); + if (!occ->buffer) + return -ENOMEM; + occ->version = (uintptr_t)of_device_get_match_data(dev); occ->dev = dev; occ->sbefifo = dev->parent; @@ -625,6 +600,7 @@ static int occ_probe(struct platform_device *pdev) if (rc) { dev_err(dev, "failed to register miscdevice: %d\n", rc); ida_simple_remove(&occ_ida, occ->idx); + kvfree(occ->buffer); return rc; } @@ -640,6 +616,8 @@ static int occ_remove(struct platform_device *pdev) { struct occ *occ = platform_get_drvdata(pdev); + kvfree(occ->buffer); + misc_deregister(&occ->mdev); device_for_each_child(&pdev->dev, NULL, occ_unregister_child); diff --git a/include/linux/fsi-occ.h b/include/linux/fsi-occ.h index d4cdc2aa6e33..7ee3dbd7f4b3 100644 --- a/include/linux/fsi-occ.h +++ b/include/linux/fsi-occ.h @@ -19,6 +19,8 @@ struct device; #define OCC_RESP_CRIT_OCB 0xE3 #define OCC_RESP_CRIT_HW 0xE4 +#define OCC_MAX_RESP_WORDS 2048 + int fsi_occ_submit(struct device *dev, const void *request, size_t req_len, void *response, size_t *resp_len); -- cgit v1.2.3 From dc0fd0acb6e0e8025a0a43ada54513b216254fac Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 21 Oct 2021 15:09:03 +0200 Subject: HID: surface-hid: Use correct event registry for managing HID events Until now, we have only ever seen the REG-category registry being used on devices addressed with target ID 2. In fact, we have only ever seen Surface Aggregator Module (SAM) HID devices with target ID 2. For those devices, the registry also has to be addressed with target ID 2. Some devices, like the new Surface Laptop Studio, however, address their HID devices on target ID 1. As a result of this, any target ID 2 commands time out. This includes event management commands addressed to the target ID 2 REG-category registry. For these devices, the registry has to be addressed via target ID 1 instead. We therefore assume that the target ID of the registry to be used depends on the target ID of the respective device. Implement this accordingly. Note that we currently allow the surface HID driver to only load against devices with target ID 2, so these timeouts are not happening (yet). This is just a preparation step before we allow the driver to load against all target IDs. Cc: stable@vger.kernel.org # 5.14+ Signed-off-by: Maximilian Luz Acked-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211021130904.862610-3-luzmaximilian@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/hid/surface-hid/surface_hid.c | 2 +- include/linux/surface_aggregator/controller.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/surface-hid/surface_hid.c b/drivers/hid/surface-hid/surface_hid.c index a3a70e4f3f6c..daa452367c0b 100644 --- a/drivers/hid/surface-hid/surface_hid.c +++ b/drivers/hid/surface-hid/surface_hid.c @@ -209,7 +209,7 @@ static int surface_hid_probe(struct ssam_device *sdev) shid->notif.base.priority = 1; shid->notif.base.fn = ssam_hid_event_fn; - shid->notif.event.reg = SSAM_EVENT_REGISTRY_REG; + shid->notif.event.reg = SSAM_EVENT_REGISTRY_REG(sdev->uid.target); shid->notif.event.id.target_category = sdev->uid.category; shid->notif.event.id.instance = sdev->uid.instance; shid->notif.event.mask = SSAM_EVENT_MASK_STRICT; diff --git a/include/linux/surface_aggregator/controller.h b/include/linux/surface_aggregator/controller.h index 068e1982ad37..74bfdffaf7b0 100644 --- a/include/linux/surface_aggregator/controller.h +++ b/include/linux/surface_aggregator/controller.h @@ -792,8 +792,8 @@ enum ssam_event_mask { #define SSAM_EVENT_REGISTRY_KIP \ SSAM_EVENT_REGISTRY(SSAM_SSH_TC_KIP, 0x02, 0x27, 0x28) -#define SSAM_EVENT_REGISTRY_REG \ - SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, 0x02, 0x01, 0x02) +#define SSAM_EVENT_REGISTRY_REG(tid)\ + SSAM_EVENT_REGISTRY(SSAM_SSH_TC_REG, tid, 0x01, 0x02) /** * enum ssam_event_notifier_flags - Flags for event notifiers. -- cgit v1.2.3 From dd66f56caea6bb1a3703fb3bfc3106444d05a930 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 21 Oct 2021 08:55:24 +0200 Subject: dma-buf: fix kerneldoc for renamed members MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Those members where renamed, update the kerneldoc as well. Signed-off-by: Christian König Reviewed-by: Alex Deucher Acked-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20211021141945.84023-1-christian.koenig@amd.com --- include/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 02c2eb874da6..9807aef33685 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -433,8 +433,8 @@ struct dma_buf { /** @poll: for userspace poll support */ wait_queue_head_t poll; - /** @cb_excl: for userspace poll support */ - /** @cb_shared: for userspace poll support */ + /** @cb_in: for userspace poll support */ + /** @cb_out: for userspace poll support */ struct dma_buf_poll_cb_t { struct dma_fence_cb cb; wait_queue_head_t *poll; -- cgit v1.2.3 From 48d09e97876bed4bcc503d528bdba8c907e43cb3 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 21 Oct 2021 08:58:34 -0700 Subject: firmware_loader: formalize built-in firmware API Formalize the built-in firmware with a proper API. This can later be used by other callers where all they need is built-in firmware. We export the firmware_request_builtin() call for now only under the TEST_FIRMWARE symbol namespace as there are no direct modular users for it. If they pop up they are free to export it generally. Built-in code always gets access to the callers and we'll demonstrate a hidden user which has been lurking in the kernel for a while and the reason why using a proper API was better long term. Reviewed-by: Borislav Petkov Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20211021155843.1969401-2-mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/builtin/Makefile | 6 +- drivers/base/firmware_loader/builtin/main.c | 100 ++++++++++++++++++++++++++ drivers/base/firmware_loader/firmware.h | 17 +++++ drivers/base/firmware_loader/main.c | 78 +------------------- include/linux/firmware.h | 15 ++++ 5 files changed, 137 insertions(+), 79 deletions(-) create mode 100644 drivers/base/firmware_loader/builtin/main.c (limited to 'include/linux') diff --git a/drivers/base/firmware_loader/builtin/Makefile b/drivers/base/firmware_loader/builtin/Makefile index 101754ad48d9..eb4be452062a 100644 --- a/drivers/base/firmware_loader/builtin/Makefile +++ b/drivers/base/firmware_loader/builtin/Makefile @@ -1,11 +1,13 @@ # SPDX-License-Identifier: GPL-2.0 +obj-y += main.o # Create $(fwdir) from $(CONFIG_EXTRA_FIRMWARE_DIR) -- if it doesn't have a # leading /, it's relative to $(srctree). fwdir := $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE_DIR)) fwdir := $(addprefix $(srctree)/,$(filter-out /%,$(fwdir)))$(filter /%,$(fwdir)) -obj-y := $(addsuffix .gen.o, $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE))) +firmware := $(addsuffix .gen.o, $(subst $(quote),,$(CONFIG_EXTRA_FIRMWARE))) +obj-y += $(firmware) FWNAME = $(patsubst $(obj)/%.gen.S,%,$@) FWSTR = $(subst $(comma),_,$(subst /,_,$(subst .,_,$(subst -,_,$(FWNAME))))) @@ -34,7 +36,7 @@ $(obj)/%.gen.S: FORCE $(call filechk,fwbin) # The .o files depend on the binaries directly; the .S files don't. -$(addprefix $(obj)/, $(obj-y)): $(obj)/%.gen.o: $(fwdir)/% +$(addprefix $(obj)/, $(firmware)): $(obj)/%.gen.o: $(fwdir)/% targets := $(patsubst $(obj)/%,%, \ $(shell find $(obj) -name \*.gen.S 2>/dev/null)) diff --git a/drivers/base/firmware_loader/builtin/main.c b/drivers/base/firmware_loader/builtin/main.c new file mode 100644 index 000000000000..d85626b2fdf5 --- /dev/null +++ b/drivers/base/firmware_loader/builtin/main.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Builtin firmware support */ + +#include +#include "../firmware.h" + +/* Only if FW_LOADER=y */ +#ifdef CONFIG_FW_LOADER + +extern struct builtin_fw __start_builtin_fw[]; +extern struct builtin_fw __end_builtin_fw[]; + +static bool fw_copy_to_prealloc_buf(struct firmware *fw, + void *buf, size_t size) +{ + if (!buf) + return true; + if (size < fw->size) + return false; + memcpy(buf, fw->data, fw->size); + return true; +} + +/** + * firmware_request_builtin() - load builtin firmware + * @fw: pointer to firmware struct + * @name: name of firmware file + * + * Some use cases in the kernel have a requirement so that no memory allocator + * is involved as these calls take place early in boot process. An example is + * the x86 CPU microcode loader. In these cases all the caller wants is to see + * if the firmware was built-in and if so use it right away. This can be used + * for such cases. + * + * This looks for the firmware in the built-in kernel. Only if the kernel was + * built-in with the firmware you are looking for will this return successfully. + * + * Callers of this API do not need to use release_firmware() as the pointer to + * the firmware is expected to be provided locally on the stack of the caller. + **/ +bool firmware_request_builtin(struct firmware *fw, const char *name) +{ + struct builtin_fw *b_fw; + + if (!fw) + return false; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { + if (strcmp(name, b_fw->name) == 0) { + fw->size = b_fw->size; + fw->data = b_fw->data; + return true; + } + } + + return false; +} +EXPORT_SYMBOL_NS_GPL(firmware_request_builtin, TEST_FIRMWARE); + +/** + * firmware_request_builtin_buf() - load builtin firmware into optional buffer + * @fw: pointer to firmware struct + * @name: name of firmware file + * @buf: If set this lets you use a pre-allocated buffer so that the built-in + * firmware into is copied into. This field can be NULL. It is used by + * callers such as request_firmware_into_buf() and + * request_partial_firmware_into_buf() + * @size: if buf was provided, the max size of the allocated buffer available. + * If the built-in firmware does not fit into the pre-allocated @buf this + * call will fail. + * + * This looks for the firmware in the built-in kernel. Only if the kernel was + * built-in with the firmware you are looking for will this call possibly + * succeed. If you passed a @buf the firmware will be copied into it *iff* the + * built-in firmware fits into the pre-allocated buffer size specified in + * @size. + * + * This caller is to be used internally by the firmware_loader only. + **/ +bool firmware_request_builtin_buf(struct firmware *fw, const char *name, + void *buf, size_t size) +{ + if (!firmware_request_builtin(fw, name)) + return false; + + return fw_copy_to_prealloc_buf(fw, buf, size); +} + +bool firmware_is_builtin(const struct firmware *fw) +{ + struct builtin_fw *b_fw; + + for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) + if (fw->data == b_fw->data) + return true; + + return false; +} + +#endif diff --git a/drivers/base/firmware_loader/firmware.h b/drivers/base/firmware_loader/firmware.h index a3014e9e2c85..2889f446ad41 100644 --- a/drivers/base/firmware_loader/firmware.h +++ b/drivers/base/firmware_loader/firmware.h @@ -151,6 +151,23 @@ static inline void fw_state_done(struct fw_priv *fw_priv) int assign_fw(struct firmware *fw, struct device *device); +#ifdef CONFIG_FW_LOADER +bool firmware_is_builtin(const struct firmware *fw); +bool firmware_request_builtin_buf(struct firmware *fw, const char *name, + void *buf, size_t size); +#else /* module case */ +static inline bool firmware_is_builtin(const struct firmware *fw) +{ + return false; +} +static inline bool firmware_request_builtin_buf(struct firmware *fw, + const char *name, + void *buf, size_t size) +{ + return false; +} +#endif + #ifdef CONFIG_FW_LOADER_PAGED_BUF void fw_free_paged_buf(struct fw_priv *fw_priv); int fw_grow_paged_buf(struct fw_priv *fw_priv, int pages_needed); diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index d95b5fe5f700..94d1789a233e 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -93,82 +93,6 @@ DEFINE_MUTEX(fw_lock); static struct firmware_cache fw_cache; -/* Builtin firmware support */ - -#ifdef CONFIG_FW_LOADER - -extern struct builtin_fw __start_builtin_fw[]; -extern struct builtin_fw __end_builtin_fw[]; - -static bool fw_copy_to_prealloc_buf(struct firmware *fw, - void *buf, size_t size) -{ - if (!buf) - return true; - if (size < fw->size) - return false; - memcpy(buf, fw->data, fw->size); - return true; -} - -static bool firmware_request_builtin(struct firmware *fw, const char *name) -{ - struct builtin_fw *b_fw; - - if (!fw) - return false; - - for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) { - if (strcmp(name, b_fw->name) == 0) { - fw->size = b_fw->size; - fw->data = b_fw->data; - return true; - } - } - - return false; -} - -static bool firmware_request_builtin_buf(struct firmware *fw, const char *name, - void *buf, size_t size) -{ - if (!firmware_request_builtin(fw, name)) - return false; - return fw_copy_to_prealloc_buf(fw, buf, size); -} - -static bool fw_is_builtin_firmware(const struct firmware *fw) -{ - struct builtin_fw *b_fw; - - for (b_fw = __start_builtin_fw; b_fw != __end_builtin_fw; b_fw++) - if (fw->data == b_fw->data) - return true; - - return false; -} - -#else /* Module case - no builtin firmware support */ - -static inline bool firmware_request_builtin(struct firmware *fw, - const char *name) -{ - return false; -} - -static inline bool firmware_request_builtin_buf(struct firmware *fw, - const char *name, void *buf, - size_t size) -{ - return false; -} - -static inline bool fw_is_builtin_firmware(const struct firmware *fw) -{ - return false; -} -#endif - static void fw_state_init(struct fw_priv *fw_priv) { struct fw_state *fw_st = &fw_priv->fw_st; @@ -1068,7 +992,7 @@ EXPORT_SYMBOL(request_partial_firmware_into_buf); void release_firmware(const struct firmware *fw) { if (fw) { - if (!fw_is_builtin_firmware(fw)) + if (!firmware_is_builtin(fw)) firmware_free_data(fw); kfree(fw); } diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 25109192cebe..d743a8d1c2fe 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -20,12 +20,19 @@ struct firmware { struct module; struct device; +/* + * Built-in firmware functionality is only available if FW_LOADER=y, but not + * FW_LOADER=m + */ +#ifdef CONFIG_FW_LOADER struct builtin_fw { char *name; void *data; unsigned long size; }; +bool firmware_request_builtin(struct firmware *fw, const char *name); + /* We have to play tricks here much like stringify() to get the __COUNTER__ macro to be expanded as we want it */ #define __fw_concat1(x, y) x##y @@ -38,6 +45,14 @@ struct builtin_fw { static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \ __used __section(".builtin_fw") = { name, blob, size } +#else +static inline bool firmware_request_builtin(struct firmware *fw, + const char *name) +{ + return false; +} +#endif + #if defined(CONFIG_FW_LOADER) || (defined(CONFIG_FW_LOADER_MODULE) && defined(MODULE)) int request_firmware(const struct firmware **fw, const char *name, struct device *device); -- cgit v1.2.3 From e520ecf4546fdaa7169ba75a35d24e2c53403a6e Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 21 Oct 2021 08:58:35 -0700 Subject: firmware_loader: remove old DECLARE_BUILTIN_FIRMWARE() This was never used upstream. Time to get rid of it. We don't carry around unused baggage. Reviewed-by: Borislav Petkov Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20211021155843.1969401-3-mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/firmware.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/firmware.h b/include/linux/firmware.h index d743a8d1c2fe..34e8d5844fa0 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -32,19 +32,6 @@ struct builtin_fw { }; bool firmware_request_builtin(struct firmware *fw, const char *name); - -/* We have to play tricks here much like stringify() to get the - __COUNTER__ macro to be expanded as we want it */ -#define __fw_concat1(x, y) x##y -#define __fw_concat(x, y) __fw_concat1(x, y) - -#define DECLARE_BUILTIN_FIRMWARE(name, blob) \ - DECLARE_BUILTIN_FIRMWARE_SIZE(name, &(blob), sizeof(blob)) - -#define DECLARE_BUILTIN_FIRMWARE_SIZE(name, blob, size) \ - static const struct builtin_fw __fw_concat(__builtin_fw,__COUNTER__) \ - __used __section(".builtin_fw") = { name, blob, size } - #else static inline bool firmware_request_builtin(struct firmware *fw, const char *name) -- cgit v1.2.3 From e2e2c0f20f321b0ec36e8bde467259c0adf1fecb Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Thu, 21 Oct 2021 08:58:37 -0700 Subject: firmware_loader: move struct builtin_fw to the only place used Now that x86 doesn't abuse picking at internals to the firmware loader move out the built-in firmware struct to its only user. Reviewed-by: Borislav Petkov Signed-off-by: Luis Chamberlain Link: https://lore.kernel.org/r/20211021155843.1969401-5-mcgrof@kernel.org Signed-off-by: Greg Kroah-Hartman --- drivers/base/firmware_loader/builtin/main.c | 6 ++++++ include/linux/firmware.h | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/firmware_loader/builtin/main.c b/drivers/base/firmware_loader/builtin/main.c index d85626b2fdf5..a065c3150897 100644 --- a/drivers/base/firmware_loader/builtin/main.c +++ b/drivers/base/firmware_loader/builtin/main.c @@ -7,6 +7,12 @@ /* Only if FW_LOADER=y */ #ifdef CONFIG_FW_LOADER +struct builtin_fw { + char *name; + void *data; + unsigned long size; +}; + extern struct builtin_fw __start_builtin_fw[]; extern struct builtin_fw __end_builtin_fw[]; diff --git a/include/linux/firmware.h b/include/linux/firmware.h index 34e8d5844fa0..3b057dfc8284 100644 --- a/include/linux/firmware.h +++ b/include/linux/firmware.h @@ -25,12 +25,6 @@ struct device; * FW_LOADER=m */ #ifdef CONFIG_FW_LOADER -struct builtin_fw { - char *name; - void *data; - unsigned long size; -}; - bool firmware_request_builtin(struct firmware *fw, const char *name); #else static inline bool firmware_request_builtin(struct firmware *fw, -- cgit v1.2.3 From 9208d414975895f69e9aca49153060ddd31b18d0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Oct 2021 08:06:01 +0200 Subject: block: add a ->get_unique_id method Add a method to query unique IDs from block devices. It will be used to remove code that deeply pokes into SCSI internals in the NFS server. The implementation in the sd driver itself is also much nicer as it can use the cached VPD page instead of always sending a command as the current NFS code does. For now the interface is kept very minimal but could be easily extended when other users like a block-layer sysfs interface for uniquue IDs shows up. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20211021060607.264371-2-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f72ccb2829db..0d5826066e16 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1158,6 +1158,14 @@ static inline void blk_crypto_unregister(struct request_queue *q) { } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ +enum blk_unique_id { + /* these match the Designator Types specified in SPC */ + BLK_UID_T10 = 1, + BLK_UID_EUI64 = 2, + BLK_UID_NAA = 3, +}; + +#define NFL4_UFLG_MASK 0x0000003F struct block_device_operations { void (*submit_bio)(struct bio *bio); @@ -1176,6 +1184,9 @@ struct block_device_operations { int (*report_zones)(struct gendisk *, sector_t sector, unsigned int nr_zones, report_zones_cb cb, void *data); char *(*devnode)(struct gendisk *disk, umode_t *mode); + /* returns the length of the identifier or a negative errno: */ + int (*get_unique_id)(struct gendisk *disk, u8 id[16], + enum blk_unique_id id_type); struct module *owner; const struct pr_ops *pr_ops; -- cgit v1.2.3 From 4abafdc4360d993104c2b2f85943938a0c6ad025 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Oct 2021 08:06:06 +0200 Subject: block: remove the initialize_rq_fn blk_mq_ops method Entirely unused now. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20211021060607.264371-7-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 9 +-------- include/linux/blk-mq.h | 5 ----- 2 files changed, 1 insertion(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index fd389a16013c..5ffe05b1d17c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -606,16 +606,9 @@ EXPORT_SYMBOL(blk_get_queue); struct request *blk_get_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { - struct request *req; - WARN_ON_ONCE(op & REQ_NOWAIT); WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); - - req = blk_mq_alloc_request(q, op, flags); - if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) - q->mq_ops->initialize_rq_fn(req); - - return req; + return blk_mq_alloc_request(q, op, flags); } EXPORT_SYMBOL(blk_get_request); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b4039fdf1b04..ebc45cf0450b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -566,11 +566,6 @@ struct blk_mq_ops { void (*exit_request)(struct blk_mq_tag_set *set, struct request *, unsigned int); - /** - * @initialize_rq_fn: Called from inside blk_get_request(). - */ - void (*initialize_rq_fn)(struct request *rq); - /** * @cleanup_rq: Called before freeing one request which isn't completed * yet, and usually for freeing the driver private data. -- cgit v1.2.3 From 4845012eb5b4e56cadb5f484cb55dd4fd9d1df80 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 21 Oct 2021 08:06:07 +0200 Subject: block: remove QUEUE_FLAG_SCSI_PASSTHROUGH Export scsi_device_from_queue for use with pktcdvd and use that instead of the otherwise unused QUEUE_FLAG_SCSI_PASSTHROUGH queue flag. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Link: https://lore.kernel.org/r/20211021060607.264371-8-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 1 - drivers/block/pktcdvd.c | 5 ++++- drivers/scsi/scsi_lib.c | 8 ++++++++ drivers/scsi/scsi_scan.c | 1 - include/linux/blkdev.h | 3 --- 5 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 68ca5d21cda7..a317f05de466 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -124,7 +124,6 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(STATS), QUEUE_FLAG_NAME(POLL_STATS), QUEUE_FLAG_NAME(REGISTERED), - QUEUE_FLAG_NAME(SCSI_PASSTHROUGH), QUEUE_FLAG_NAME(QUIESCED), QUEUE_FLAG_NAME(PCI_P2PDMA), QUEUE_FLAG_NAME(ZONE_RESETALL), diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index ea2262ec76d2..cacf64eedad8 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2536,6 +2536,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) int i; char b[BDEVNAME_SIZE]; struct block_device *bdev; + struct scsi_device *sdev; if (pd->pkt_dev == dev) { pkt_err(pd, "recursive setup not allowed\n"); @@ -2559,10 +2560,12 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL); if (IS_ERR(bdev)) return PTR_ERR(bdev); - if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) { + sdev = scsi_device_from_queue(bdev->bd_disk->queue); + if (!sdev) { blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); return -EINVAL; } + put_device(&sdev->sdev_gendev); /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index a0f801fc8943..9823b65d1536 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1967,6 +1967,14 @@ struct scsi_device *scsi_device_from_queue(struct request_queue *q) return sdev; } +/* + * pktcdvd should have been integrated into the SCSI layers, but for historical + * reasons like the old IDE driver it isn't. This export allows it to safely + * probe if a given device is a SCSI one and only attach to that. + */ +#ifdef CONFIG_CDROM_PKTCDVD_MODULE +EXPORT_SYMBOL_GPL(scsi_device_from_queue); +#endif /** * scsi_block_requests - Utility function used by low-level drivers to prevent diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index fe22191522a3..2808c0cb5711 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -280,7 +280,6 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget, sdev->request_queue = q; q->queuedata = sdev; __scsi_init_queue(sdev->host, q); - blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, q); WARN_ON_ONCE(!blk_get_queue(q)); depth = sdev->host->cmd_per_lun ?: 1; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0d5826066e16..1ad30f85d30e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -357,7 +357,6 @@ struct request_queue { #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ -#define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ @@ -391,8 +390,6 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) -#define blk_queue_scsi_passthrough(q) \ - test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #ifdef CONFIG_BLK_RQ_ALLOC_TIME -- cgit v1.2.3 From 70164eb6ccb76ab679b016b4b60123bf4ec6c162 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Oct 2021 08:25:25 +0200 Subject: block: remove __sync_blockdev Instead offer a new sync_blockdev_nowait helper for the !wait case. This new helper is exported as it will grow modular callers in a bit. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211019062530.2174626-3-hch@lst.de Signed-off-by: Jens Axboe --- block/bdev.c | 11 ++++++----- fs/internal.h | 5 ----- fs/sync.c | 7 ++++--- include/linux/blkdev.h | 5 +++++ 4 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index 7e6156203a71..9a33c414f450 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -185,14 +185,13 @@ int sb_min_blocksize(struct super_block *sb, int size) EXPORT_SYMBOL(sb_min_blocksize); -int __sync_blockdev(struct block_device *bdev, int wait) +int sync_blockdev_nowait(struct block_device *bdev) { if (!bdev) return 0; - if (!wait) - return filemap_flush(bdev->bd_inode->i_mapping); - return filemap_write_and_wait(bdev->bd_inode->i_mapping); + return filemap_flush(bdev->bd_inode->i_mapping); } +EXPORT_SYMBOL_GPL(sync_blockdev_nowait); /* * Write out and wait upon all the dirty data associated with a block @@ -200,7 +199,9 @@ int __sync_blockdev(struct block_device *bdev, int wait) */ int sync_blockdev(struct block_device *bdev) { - return __sync_blockdev(bdev, 1); + if (!bdev) + return 0; + return filemap_write_and_wait(bdev->bd_inode->i_mapping); } EXPORT_SYMBOL(sync_blockdev); diff --git a/fs/internal.h b/fs/internal.h index 3cd065c8a66b..b5caa16f4645 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -23,7 +23,6 @@ struct pipe_inode_info; #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); -extern int __sync_blockdev(struct block_device *bdev, int wait); void iterate_bdevs(void (*)(struct block_device *, void *), void *); void emergency_thaw_bdev(struct super_block *sb); #else @@ -31,10 +30,6 @@ static inline void bdev_cache_init(void) { } -static inline int __sync_blockdev(struct block_device *bdev, int wait) -{ - return 0; -} static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { diff --git a/fs/sync.c b/fs/sync.c index 0d6cdc507cb9..a621089eb07e 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -3,6 +3,7 @@ * High-level sync()-related operations */ +#include #include #include #include @@ -45,7 +46,7 @@ int sync_filesystem(struct super_block *sb) /* * Do the filesystem syncing work. For simple filesystems * writeback_inodes_sb(sb) just dirties buffers with inodes so we have - * to submit I/O for these buffers via __sync_blockdev(). This also + * to submit I/O for these buffers via sync_blockdev(). This also * speeds up the wait == 1 case since in that case write_inode() * methods call sync_dirty_buffer() and thus effectively write one block * at a time. @@ -53,14 +54,14 @@ int sync_filesystem(struct super_block *sb) writeback_inodes_sb(sb, WB_REASON_SYNC); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, 0); - ret = __sync_blockdev(sb->s_bdev, 0); + ret = sync_blockdev_nowait(sb->s_bdev); if (ret < 0) return ret; sync_inodes_sb(sb); if (sb->s_op->sync_fs) sb->s_op->sync_fs(sb, 1); - return __sync_blockdev(sb->s_bdev, 1); + return sync_blockdev(sb->s_bdev); } EXPORT_SYMBOL(sync_filesystem); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f72ccb2829db..4b5a6bbdacd0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1266,6 +1266,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); +int sync_blockdev_nowait(struct block_device *bdev); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1274,6 +1275,10 @@ static inline int sync_blockdev(struct block_device *bdev) { return 0; } +static inline int sync_blockdev_nowait(struct block_device *bdev) +{ + return 0; +} #endif int fsync_bdev(struct block_device *bdev); -- cgit v1.2.3 From 1e03a36bdff4709c1bbf0f57f60ae3f776d51adf Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 19 Oct 2021 08:25:30 +0200 Subject: block: simplify the block device syncing code Get rid of the indirections and just provide a sync_bdevs helper for the generic sync code. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211019062530.2174626-8-hch@lst.de Signed-off-by: Jens Axboe --- block/bdev.c | 17 ++++++++++++++--- fs/internal.h | 6 ------ fs/sync.c | 23 ++++------------------- include/linux/blkdev.h | 4 ++++ 4 files changed, 22 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index 9a33c414f450..b4dab2fb6a74 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -1021,7 +1021,7 @@ int __invalidate_device(struct block_device *bdev, bool kill_dirty) } EXPORT_SYMBOL(__invalidate_device); -void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) +void sync_bdevs(bool wait) { struct inode *inode, *old_inode = NULL; @@ -1052,8 +1052,19 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) bdev = I_BDEV(inode); mutex_lock(&bdev->bd_disk->open_mutex); - if (bdev->bd_openers) - func(bdev, arg); + if (!bdev->bd_openers) { + ; /* skip */ + } else if (wait) { + /* + * We keep the error status of individual mapping so + * that applications can catch the writeback error using + * fsync(2). See filemap_fdatawait_keep_errors() for + * details. + */ + filemap_fdatawait_keep_errors(inode->i_mapping); + } else { + filemap_fdatawrite(inode->i_mapping); + } mutex_unlock(&bdev->bd_disk->open_mutex); spin_lock(&blockdev_superblock->s_inode_list_lock); diff --git a/fs/internal.h b/fs/internal.h index b5caa16f4645..cdd83d4899bb 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -23,17 +23,11 @@ struct pipe_inode_info; #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); -void iterate_bdevs(void (*)(struct block_device *, void *), void *); void emergency_thaw_bdev(struct super_block *sb); #else static inline void bdev_cache_init(void) { } - -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), - void *arg) -{ -} static inline int emergency_thaw_bdev(struct super_block *sb) { return 0; diff --git a/fs/sync.c b/fs/sync.c index a621089eb07e..3ce8e2137f31 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -78,21 +78,6 @@ static void sync_fs_one_sb(struct super_block *sb, void *arg) sb->s_op->sync_fs(sb, *(int *)arg); } -static void fdatawrite_one_bdev(struct block_device *bdev, void *arg) -{ - filemap_fdatawrite(bdev->bd_inode->i_mapping); -} - -static void fdatawait_one_bdev(struct block_device *bdev, void *arg) -{ - /* - * We keep the error status of individual mapping so that - * applications can catch the writeback error using fsync(2). - * See filemap_fdatawait_keep_errors() for details. - */ - filemap_fdatawait_keep_errors(bdev->bd_inode->i_mapping); -} - /* * Sync everything. We start by waking flusher threads so that most of * writeback runs on all devices in parallel. Then we sync all inodes reliably @@ -111,8 +96,8 @@ void ksys_sync(void) iterate_supers(sync_inodes_one_sb, NULL); iterate_supers(sync_fs_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &wait); - iterate_bdevs(fdatawrite_one_bdev, NULL); - iterate_bdevs(fdatawait_one_bdev, NULL); + sync_bdevs(false); + sync_bdevs(true); if (unlikely(laptop_mode)) laptop_sync_completion(); } @@ -133,10 +118,10 @@ static void do_sync_work(struct work_struct *work) */ iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); - iterate_bdevs(fdatawrite_one_bdev, NULL); + sync_bdevs(false); iterate_supers(sync_inodes_one_sb, &nowait); iterate_supers(sync_fs_one_sb, &nowait); - iterate_bdevs(fdatawrite_one_bdev, NULL); + sync_bdevs(false); printk("Emergency Sync complete\n"); kfree(work); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4b5a6bbdacd0..09fdf7018b7f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1267,6 +1267,7 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart, void invalidate_bdev(struct block_device *bdev); int sync_blockdev(struct block_device *bdev); int sync_blockdev_nowait(struct block_device *bdev); +void sync_bdevs(bool wait); #else static inline void invalidate_bdev(struct block_device *bdev) { @@ -1279,6 +1280,9 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) { return 0; } +static inline void sync_bdevs(bool wait) +{ +} #endif int fsync_bdev(struct block_device *bdev); -- cgit v1.2.3 From 599593a82fc57f5e9453c8ef7420df3206934a0c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 22 Oct 2021 19:35:45 -0600 Subject: sched: make task_struct->plug always defined MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If CONFIG_BLOCK isn't set, then it's an empty struct anyway. Just make it generally available, so we don't break the compile: kernel/sched/core.c: In function ‘sched_submit_work’: kernel/sched/core.c:6346:35: error: ‘struct task_struct’ has no member named ‘plug’ 6346 | blk_flush_plug(tsk->plug, true); | ^~ kernel/sched/core.c: In function ‘io_schedule_prepare’: kernel/sched/core.c:8357:20: error: ‘struct task_struct’ has no member named ‘plug’ 8357 | if (current->plug) | ^~ kernel/sched/core.c:8358:39: error: ‘struct task_struct’ has no member named ‘plug’ 8358 | blk_flush_plug(current->plug, true); | ^~ Reported-by: Nathan Chancellor Fixes: 008f75a20e70 ("block: cleanup the flush plug helpers") Signed-off-by: Jens Axboe --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index c1a927ddec64..e0454e60fe8f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1160,10 +1160,8 @@ struct task_struct { /* Stacked block device info: */ struct bio_list *bio_list; -#ifdef CONFIG_BLOCK /* Stack plugging: */ struct blk_plug *plug; -#endif /* VM state: */ struct reclaim_state *reclaim_state; -- cgit v1.2.3 From 0ebecb2644c834d8a69f07c5d44a130835950171 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 22 Oct 2021 11:59:12 -0400 Subject: net: mdio: Add helper functions for accessing MDIO devices This adds some helpers for accessing non-phy MDIO devices. They are analogous to phy_(read|write|modify), except that they take an mdio_device and not a phy_device. Signed-off-by: Sean Anderson Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/mdio.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index f622888a4ba8..9f3587a61e14 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -352,6 +352,30 @@ int mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask, int mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum, u16 mask, u16 set); +static inline int mdiodev_read(struct mdio_device *mdiodev, u32 regnum) +{ + return mdiobus_read(mdiodev->bus, mdiodev->addr, regnum); +} + +static inline int mdiodev_write(struct mdio_device *mdiodev, u32 regnum, + u16 val) +{ + return mdiobus_write(mdiodev->bus, mdiodev->addr, regnum, val); +} + +static inline int mdiodev_modify(struct mdio_device *mdiodev, u32 regnum, + u16 mask, u16 set) +{ + return mdiobus_modify(mdiodev->bus, mdiodev->addr, regnum, mask, set); +} + +static inline int mdiodev_modify_changed(struct mdio_device *mdiodev, + u32 regnum, u16 mask, u16 set) +{ + return mdiobus_modify_changed(mdiodev->bus, mdiodev->addr, regnum, + mask, set); +} + static inline u32 mdiobus_c45_addr(int devad, u16 regnum) { return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; -- cgit v1.2.3 From 218f23e8a96fea7185dac68ceb3722d0831a8bcb Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 22 Oct 2021 09:17:01 -0700 Subject: net: phy: bcm7xxx: Add EPHY entry for 7712 7712 is a 16nm process SoC with a 10/100 integrated Ethernet PHY, utilize the recently defined 16nm EPHY macro to configure that PHY. Signed-off-by: Florian Fainelli Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 2 ++ include/linux/brcmphy.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 6ceadd2a0082..75593e7d1118 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -936,6 +936,7 @@ static struct phy_driver bcm7xxx_driver[] = { BCM7XXX_40NM_EPHY(PHY_ID_BCM7425, "Broadcom BCM7425"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7429, "Broadcom BCM7429"), BCM7XXX_40NM_EPHY(PHY_ID_BCM7435, "Broadcom BCM7435"), + BCM7XXX_16NM_EPHY(PHY_ID_BCM7712, "Broadcom BCM7712"), }; static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { @@ -958,6 +959,7 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM7439, 0xfffffff0, }, { PHY_ID_BCM7435, 0xfffffff0, }, { PHY_ID_BCM7445, 0xfffffff0, }, + { PHY_ID_BCM7712, 0xfffffff0, }, { } }; diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 27d9b6683f0e..747fad264033 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -50,6 +50,7 @@ #define PHY_ID_BCM7439 0x600d8480 #define PHY_ID_BCM7439_2 0xae025080 #define PHY_ID_BCM7445 0x600d8510 +#define PHY_ID_BCM7712 0x35905330 #define PHY_ID_BCM_CYGNUS 0xae025200 #define PHY_ID_BCM_OMEGA 0xae025100 -- cgit v1.2.3 From 97308f8b0d867e9ef59528cd97f0db55ffdf5651 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Fri, 23 Jul 2021 01:59:41 +0200 Subject: iomap: Support partial direct I/O on user copy failures In iomap_dio_rw, when iomap_apply returns an -EFAULT error and the IOMAP_DIO_PARTIAL flag is set, complete the request synchronously and return a partial result. This allows the caller to deal with the page fault and retry the remainder of the request. Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong --- fs/iomap/direct-io.c | 6 ++++++ include/linux/iomap.h | 7 +++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index a2a368e824c0..a434fb7887b2 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -581,6 +581,12 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (iov_iter_rw(iter) == READ && iomi.pos >= dio->i_size) iov_iter_revert(iter, iomi.pos - dio->i_size); + if (ret == -EFAULT && dio->size && (dio_flags & IOMAP_DIO_PARTIAL)) { + if (!(iocb->ki_flags & IOCB_NOWAIT)) + wait_for_completion = true; + ret = 0; + } + /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { wait_for_completion = true; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 24f8489583ca..2a213b0d1e1f 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -330,6 +330,13 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_OVERWRITE_ONLY (1 << 1) +/* + * When a page fault occurs, return a partial synchronous result and allow + * the caller to retry the rest of the operation after dealing with the page + * fault. + */ +#define IOMAP_DIO_PARTIAL (1 << 2) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags); -- cgit v1.2.3 From 4fdccaa0d184c202f98d73b24e3ec8eeee88ab8d Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Sat, 24 Jul 2021 12:26:41 +0200 Subject: iomap: Add done_before argument to iomap_dio_rw Add a done_before argument to iomap_dio_rw that indicates how much of the request has already been transferred. When the request succeeds, we report that done_before additional bytes were tranferred. This is useful for finishing a request asynchronously when part of the request has already been completed synchronously. We'll use that to allow iomap_dio_rw to be used with page faults disabled: when a page fault occurs while submitting a request, we synchronously complete the part of the request that has already been submitted. The caller can then take care of the page fault and call iomap_dio_rw again for the rest of the request, passing in the number of bytes already tranferred. Signed-off-by: Andreas Gruenbacher Reviewed-by: Darrick J. Wong --- fs/btrfs/file.c | 5 +++-- fs/erofs/data.c | 2 +- fs/ext4/file.c | 5 +++-- fs/gfs2/file.c | 4 ++-- fs/iomap/direct-io.c | 19 ++++++++++++++++--- fs/xfs/xfs_file.c | 6 +++--- fs/zonefs/super.c | 4 ++-- include/linux/iomap.h | 4 ++-- 8 files changed, 32 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f37211d3bb69..9d41b28c67ba 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1957,7 +1957,7 @@ relock: } dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - 0); + 0, 0); btrfs_inode_unlock(inode, ilock_flags); @@ -3658,7 +3658,8 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to) return 0; btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, 0); + ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + 0, 0); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); return ret; } diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 9db829715652..16a41d0db55a 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -287,7 +287,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (!err) return iomap_dio_rw(iocb, to, &erofs_iomap_ops, - NULL, 0); + NULL, 0, 0); if (err < 0) return err; } diff --git a/fs/ext4/file.c b/fs/ext4/file.c index ac0e11bbb445..b25c1f8f7c4f 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -74,7 +74,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to) return generic_file_read_iter(iocb, to); } - ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0); + ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0); inode_unlock_shared(inode); file_accessed(iocb->ki_filp); @@ -566,7 +566,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ilock_shared) iomap_ops = &ext4_iomap_overwrite_ops; ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops, - (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0); + (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0, + 0); if (ret == -ENOTBLK) ret = 0; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index d9126e3e6dd6..f772ee0fcae3 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -822,7 +822,7 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to, if (ret) goto out_uninit; - ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0); + ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0, 0); gfs2_glock_dq(gh); out_uninit: gfs2_holder_uninit(gh); @@ -856,7 +856,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from, if (offset + len > i_size_read(&ip->i_inode)) goto out; - ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0); + ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0, 0); if (ret == -ENOTBLK) ret = 0; out: diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index a434fb7887b2..468dcbba45bc 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -31,6 +31,7 @@ struct iomap_dio { atomic_t ref; unsigned flags; int error; + size_t done_before; bool wait_for_completion; union { @@ -124,6 +125,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC)) ret = generic_write_sync(iocb, ret); + if (ret > 0) + ret += dio->done_before; + kfree(dio); return ret; @@ -450,13 +454,21 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter, * may be pure data writes. In that case, we still need to do a full data sync * completion. * + * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL, + * __iomap_dio_rw can return a partial result if it encounters a non-resident + * page in @iter after preparing a transfer. In that case, the non-resident + * pages can be faulted in and the request resumed with @done_before set to the + * number of bytes previously transferred. The request will then complete with + * the correct total number of bytes transferred; this is essential for + * completing partial requests asynchronously. + * * Returns -ENOTBLK In case of a page invalidation invalidation failure for * writes. The callers needs to fall back to buffered I/O in this case. */ struct iomap_dio * __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags) + unsigned int dio_flags, size_t done_before) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = file_inode(iocb->ki_filp); @@ -486,6 +498,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->dops = dops; dio->error = 0; dio->flags = 0; + dio->done_before = done_before; dio->submit.iter = iter; dio->submit.waiter = current; @@ -652,11 +665,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw); ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags) + unsigned int dio_flags, size_t done_before) { struct iomap_dio *dio; - dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags); + dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before); if (IS_ERR_OR_NULL(dio)) return PTR_ERR_OR_ZERO(dio); return iomap_dio_complete(dio); diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 7aa943edfc02..240eb932c014 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -259,7 +259,7 @@ xfs_file_dio_read( ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED); if (ret) return ret; - ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0); + ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0); xfs_iunlock(ip, XFS_IOLOCK_SHARED); return ret; @@ -569,7 +569,7 @@ xfs_file_dio_write_aligned( } trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, 0); + &xfs_dio_write_ops, 0, 0); out_unlock: if (iolock) xfs_iunlock(ip, iolock); @@ -647,7 +647,7 @@ retry_exclusive: trace_xfs_file_direct_write(iocb, from); ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops, - &xfs_dio_write_ops, flags); + &xfs_dio_write_ops, flags, 0); /* * Retry unaligned I/O with exclusive blocking semantics if the DIO diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index ddc346a9df9b..6122c38ab44d 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -852,7 +852,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) ret = zonefs_file_dio_append(iocb, from); else ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops, - &zonefs_write_dio_ops, 0); + &zonefs_write_dio_ops, 0, 0); if (zi->i_ztype == ZONEFS_ZTYPE_SEQ && (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) @@ -987,7 +987,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } file_accessed(iocb->ki_filp); ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops, - &zonefs_read_dio_ops, 0); + &zonefs_read_dio_ops, 0, 0); } else { ret = generic_file_read_iter(iocb, to); if (ret == -EIO) diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 2a213b0d1e1f..829f2325ecba 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -339,10 +339,10 @@ struct iomap_dio_ops { ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags); + unsigned int dio_flags, size_t done_before); struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, - unsigned int dio_flags); + unsigned int dio_flags, size_t done_before); ssize_t iomap_dio_complete(struct iomap_dio *dio); int iomap_dio_iopoll(struct kiocb *kiocb, bool spin); -- cgit v1.2.3 From 55b8fe703bc51200d4698596c90813453b35ae63 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Tue, 17 Aug 2021 22:52:08 +0200 Subject: gup: Introduce FOLL_NOFAULT flag to disable page faults Introduce a new FOLL_NOFAULT flag that causes get_user_pages to return -EFAULT when it would otherwise trigger a page fault. This is roughly similar to FOLL_FAST_ONLY but available on all architectures, and less fragile. Signed-off-by: Andreas Gruenbacher --- include/linux/mm.h | 3 ++- mm/gup.c | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..2f0e6b9f8f3b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2851,7 +2851,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ #define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO * and return without waiting upon it */ -#define FOLL_POPULATE 0x40 /* fault in page */ +#define FOLL_POPULATE 0x40 /* fault in pages (with FOLL_MLOCK) */ +#define FOLL_NOFAULT 0x80 /* do not fault in pages */ #define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ #define FOLL_NUMA 0x200 /* force NUMA hinting page fault */ #define FOLL_MIGRATION 0x400 /* wait for page to replace migration entry */ diff --git a/mm/gup.c b/mm/gup.c index 795f15c410cc..e1c7e4bde11f 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -918,6 +918,8 @@ static int faultin_page(struct vm_area_struct *vma, /* mlock all present pages, but do not fault in new pages */ if ((*flags & (FOLL_POPULATE | FOLL_MLOCK)) == FOLL_MLOCK) return -ENOENT; + if (*flags & FOLL_NOFAULT) + return -EFAULT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) @@ -2843,7 +2845,7 @@ static int internal_get_user_pages_fast(unsigned long start, if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | - FOLL_FAST_ONLY))) + FOLL_FAST_ONLY | FOLL_NOFAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) -- cgit v1.2.3 From 3337ab08d08b1a375f88471d9c8b1cac968cb054 Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Mon, 12 Jul 2021 12:06:14 +0200 Subject: iov_iter: Introduce nofault flag to disable page faults Introduce a new nofault flag to indicate to iov_iter_get_pages not to fault in user pages. This is implemented by passing the FOLL_NOFAULT flag to get_user_pages, which causes get_user_pages to fail when it would otherwise fault in a page. We'll use the ->nofault flag to prevent iomap_dio_rw from faulting in pages when page faults are not allowed. Signed-off-by: Andreas Gruenbacher --- include/linux/uio.h | 1 + lib/iov_iter.c | 20 +++++++++++++++----- 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 25d1c24fd829..6350354f97e9 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -35,6 +35,7 @@ struct iov_iter_state { struct iov_iter { u8 iter_type; + bool nofault; bool data_source; size_t iov_offset; size_t count; diff --git a/lib/iov_iter.c b/lib/iov_iter.c index ac9a87e727a3..66a740e6e153 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -513,6 +513,7 @@ void iov_iter_init(struct iov_iter *i, unsigned int direction, WARN_ON(direction & ~(READ | WRITE)); *i = (struct iov_iter) { .iter_type = ITER_IOVEC, + .nofault = false, .data_source = direction, .iov = iov, .nr_segs = nr_segs, @@ -1527,13 +1528,17 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, return 0; if (likely(iter_is_iovec(i))) { + unsigned int gup_flags = 0; unsigned long addr; + if (iov_iter_rw(i) != WRITE) + gup_flags |= FOLL_WRITE; + if (i->nofault) + gup_flags |= FOLL_NOFAULT; + addr = first_iovec_segment(i, &len, start, maxsize, maxpages); n = DIV_ROUND_UP(len, PAGE_SIZE); - res = get_user_pages_fast(addr, n, - iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, - pages); + res = get_user_pages_fast(addr, n, gup_flags, pages); if (unlikely(res <= 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; @@ -1649,15 +1654,20 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, return 0; if (likely(iter_is_iovec(i))) { + unsigned int gup_flags = 0; unsigned long addr; + if (iov_iter_rw(i) != WRITE) + gup_flags |= FOLL_WRITE; + if (i->nofault) + gup_flags |= FOLL_NOFAULT; + addr = first_iovec_segment(i, &len, start, maxsize, ~0U); n = DIV_ROUND_UP(len, PAGE_SIZE); p = get_pages_array(n); if (!p) return -ENOMEM; - res = get_user_pages_fast(addr, n, - iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, p); + res = get_user_pages_fast(addr, n, gup_flags, p); if (unlikely(res <= 0)) { kvfree(p); *pages = NULL; -- cgit v1.2.3 From 63dfe0709643528290c8a6825f278eda0e3f3c2e Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:32 +0900 Subject: can: bittiming: allow TDC{V,O} to be zero and add can_tdc_const::tdc{v,o,f}_min ISO 11898-1 specifies in section 11.3.3 "Transmitter delay compensation" that "the configuration range for [the] SSP position shall be at least 0 to 63 minimum time quanta." Because SSP = TDCV + TDCO, it means that we should allow both TDCV and TDCO to hold zero value in order to honor SSP's minimum possible value. However, current implementation assigned special meaning to TDCV and TDCO's zero values: * TDCV = 0 -> TDCV is automatically measured by the transceiver. * TDCO = 0 -> TDC is off. In order to allow for those values to really be zero and to maintain current features, we introduce two new flags: * CAN_CTRLMODE_TDC_AUTO indicates that the controller support automatic measurement of TDCV. * CAN_CTRLMODE_TDC_MANUAL indicates that the controller support manual configuration of TDCV. N.B.: current implementation failed to provide an option for the driver to indicate that only manual mode was supported. TDC is disabled if both CAN_CTRLMODE_TDC_AUTO and CAN_CTRLMODE_TDC_MANUAL flags are off, c.f. the helper function can_tdc_is_enabled() which is also introduced in this patch. Also, this patch adds three fields: tdcv_min, tdco_min and tdcf_min to struct can_tdc_const. While we are not convinced that those three fields could be anything else than zero, we can imagine that some controllers might specify a lower bound on these. Thus, those minimums are really added "just in case". Comments of struct can_tdc and can_tdc_const are updated accordingly. Finally, the changes are applied to the etas_es58x driver. Link: https://lore.kernel.org/all/20210918095637.20108-2-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/bittiming.c | 10 +++-- drivers/net/can/usb/etas_es58x/es58x_fd.c | 7 +++- include/linux/can/bittiming.h | 64 +++++++++++++++++++++++-------- include/linux/can/dev.h | 4 ++ include/uapi/linux/can/netlink.h | 2 + 5 files changed, 65 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index b1b5a82f0829..9dda44c0ae9d 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -182,9 +182,12 @@ void can_calc_tdco(struct net_device *dev) struct can_tdc *tdc = &priv->tdc; const struct can_tdc_const *tdc_const = priv->tdc_const; - if (!tdc_const) + if (!tdc_const || + !(priv->ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO)) return; + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + /* As specified in ISO 11898-1 section 11.3.3 "Transmitter * delay compensation" (TDC) is only applicable if data BRP is * one or two. @@ -193,9 +196,10 @@ void can_calc_tdco(struct net_device *dev) /* Reuse "normal" sample point and convert it to time quanta */ u32 sample_point_in_tq = can_bit_time(dbt) * dbt->sample_point / 1000; + if (sample_point_in_tq < tdc_const->tdco_min) + return; tdc->tdco = min(sample_point_in_tq, tdc_const->tdco_max); - } else { - tdc->tdco = 0; + priv->ctrlmode |= CAN_CTRLMODE_TDC_AUTO; } } #endif /* CONFIG_CAN_CALC_BITTIMING */ diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index af042aa55f59..4f0cae29f4d8 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -428,7 +428,7 @@ static int es58x_fd_enable_channel(struct es58x_priv *priv) es58x_fd_convert_bittiming(&tx_conf_msg.data_bittiming, &priv->can.data_bittiming); - if (priv->can.tdc.tdco) { + if (can_tdc_is_enabled(&priv->can)) { tx_conf_msg.tdc_enabled = 1; tx_conf_msg.tdco = cpu_to_le16(priv->can.tdc.tdco); tx_conf_msg.tdcf = cpu_to_le16(priv->can.tdc.tdcf); @@ -505,8 +505,11 @@ static const struct can_bittiming_const es58x_fd_data_bittiming_const = { * Register" from Microchip. */ static const struct can_tdc_const es58x_tdc_const = { + .tdcv_min = 0, .tdcv_max = 0, /* Manual mode not supported. */ + .tdco_min = 0, .tdco_max = 127, + .tdcf_min = 0, .tdcf_max = 127 }; @@ -523,7 +526,7 @@ const struct es58x_parameters es58x_fd_param = { .clock = {.freq = 80 * CAN_MHZ}, .ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC, + CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO, .tx_start_of_frame = 0xCEFA, /* FACE in little endian */ .rx_start_of_frame = 0xFECA, /* CAFE in little endian */ .tx_urb_cmd_max_len = ES58X_FD_TX_URB_CMD_MAX_LEN, diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 9de6e9053e34..9e20260611cc 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -19,6 +19,9 @@ /* Megahertz */ #define CAN_MHZ 1000000UL +#define CAN_CTRLMODE_TDC_MASK \ + (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) + /* * struct can_tdc - CAN FD Transmission Delay Compensation parameters * @@ -33,29 +36,43 @@ * * This structure contains the parameters to calculate that SSP. * - * @tdcv: Transmitter Delay Compensation Value. Distance, in time - * quanta, from when the bit is sent on the TX pin to when it is - * received on the RX pin of the transmitter. Possible options: + * -+----------- one bit ----------+-- TX pin + * |<--- Sample Point --->| + * + * --+----------- one bit ----------+-- RX pin + * |<-------- TDCV -------->| + * |<------- TDCO ------->| + * |<----------- Secondary Sample Point ---------->| + * + * @tdcv: Transmitter Delay Compensation Value. The time needed for + * the signal to propagate, i.e. the distance, in time quanta, + * from the start of the bit on the TX pin to when it is received + * on the RX pin. @tdcv depends on the controller modes: + * + * CAN_CTRLMODE_TDC_AUTO is set: The transceiver dynamically + * measures @tdcv for each transmitted CAN FD frame and the + * value provided here should be ignored. * - * 0: automatic mode. The controller dynamically measures @tdcv - * for each transmitted CAN FD frame. + * CAN_CTRLMODE_TDC_MANUAL is set: use the fixed provided @tdcv + * value. * - * Other values: manual mode. Use the fixed provided value. + * N.B. CAN_CTRLMODE_TDC_AUTO and CAN_CTRLMODE_TDC_MANUAL are + * mutually exclusive. Only one can be set at a time. If both + * CAN_TDC_CTRLMODE_AUTO and CAN_TDC_CTRLMODE_MANUAL are unset, + * TDC is disabled and all the values of this structure should be + * ignored. * * @tdco: Transmitter Delay Compensation Offset. Offset value, in time * quanta, defining the distance between the start of the bit * reception on the RX pin of the transceiver and the SSP * position such that SSP = @tdcv + @tdco. * - * If @tdco is zero, then TDC is disabled and both @tdcv and - * @tdcf should be ignored. - * * @tdcf: Transmitter Delay Compensation Filter window. Defines the - * minimum value for the SSP position in time quanta. If SSP is - * less than @tdcf, then no delay compensations occur and the - * normal sampling point is used instead. The feature is enabled - * if and only if @tdcv is set to zero (automatic mode) and @tdcf - * is configured to a value greater than @tdco. + * minimum value for the SSP position in time quanta. If the SSP + * position is less than @tdcf, then no delay compensations occur + * and the normal sampling point is used instead. The feature is + * enabled if and only if @tdcv is set to zero (automatic mode) + * and @tdcf is configured to a value greater than @tdco. */ struct can_tdc { u32 tdcv; @@ -67,19 +84,32 @@ struct can_tdc { * struct can_tdc_const - CAN hardware-dependent constant for * Transmission Delay Compensation * - * @tdcv_max: Transmitter Delay Compensation Value maximum value. - * Should be set to zero if the controller does not support - * manual mode for tdcv. + * @tdcv_min: Transmitter Delay Compensation Value minimum value. If + * the controller does not support manual mode for tdcv + * (c.f. flag CAN_CTRLMODE_TDC_MANUAL) then this value is + * ignored. + * @tdcv_max: Transmitter Delay Compensation Value maximum value. If + * the controller does not support manual mode for tdcv + * (c.f. flag CAN_CTRLMODE_TDC_MANUAL) then this value is + * ignored. + * + * @tdco_min: Transmitter Delay Compensation Offset minimum value. * @tdco_max: Transmitter Delay Compensation Offset maximum value. * Should not be zero. If the controller does not support TDC, * then the pointer to this structure should be NULL. + * + * @tdcf_min: Transmitter Delay Compensation Filter window minimum + * value. If @tdcf_max is zero, this value is ignored. * @tdcf_max: Transmitter Delay Compensation Filter window maximum * value. Should be set to zero if the controller does not * support this feature. */ struct can_tdc_const { + u32 tdcv_min; u32 tdcv_max; + u32 tdco_min; u32 tdco_max; + u32 tdcf_min; u32 tdcf_max; }; diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 2413253e54c7..6dacbbb41e68 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -96,6 +96,10 @@ struct can_priv { #endif }; +static inline bool can_tdc_is_enabled(const struct can_priv *priv) +{ + return !!(priv->ctrlmode & CAN_CTRLMODE_TDC_MASK); +} /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index f730d443b918..004cd09a7d49 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -101,6 +101,8 @@ struct can_ctrlmode { #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ #define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ #define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */ +#define CAN_CTRLMODE_TDC_AUTO 0x200 /* CAN transiver automatically calculates TDCV */ +#define CAN_CTRLMODE_TDC_MANUAL 0x400 /* TDCV is manually set up by user */ /* * CAN device statistics -- cgit v1.2.3 From 39f66c9e229797a58a12ea78388cbbad1f81aec9 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:33 +0900 Subject: can: bittiming: change unit of TDC parameters to clock periods MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the current implementation, all Transmission Delay Compensation (TDC) parameters are expressed in time quantum. However, ISO 11898-1 actually specifies that these should be expressed in *minimum* time quantum. Furthermore, the minimum time quantum is specified to be "one node clock period long" (c.f. paragraph 11.3.1.1 "Bit time"). For sake of simplicity, we prefer to use the "clock period" term instead of "minimum time quantum" because we believe that it is more broadly understood. This patch fixes that discrepancy by updating the documentation and the formula for TDCO calculation. N.B. In can_calc_tdco(), the sample point (in time quantum) was calculated using a division, thus introducing a risk of rounding and truncation errors. On top of changing the unit to clock period, we also modified the formula to use only additions. Link: https://lore.kernel.org/all/20210918095637.20108-3-mailhol.vincent@wanadoo.fr Suggested-by: Stefan Mätje Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/bittiming.c | 9 +++++---- include/linux/can/bittiming.h | 28 +++++++++++++++++----------- 2 files changed, 22 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 9dda44c0ae9d..0ccf982ca301 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -193,12 +193,13 @@ void can_calc_tdco(struct net_device *dev) * one or two. */ if (dbt->brp == 1 || dbt->brp == 2) { - /* Reuse "normal" sample point and convert it to time quanta */ - u32 sample_point_in_tq = can_bit_time(dbt) * dbt->sample_point / 1000; + /* Sample point in clock periods */ + u32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg + + dbt->phase_seg1) * dbt->brp; - if (sample_point_in_tq < tdc_const->tdco_min) + if (sample_point_in_tc < tdc_const->tdco_min) return; - tdc->tdco = min(sample_point_in_tq, tdc_const->tdco_max); + tdc->tdco = min(sample_point_in_tc, tdc_const->tdco_max); priv->ctrlmode |= CAN_CTRLMODE_TDC_AUTO; } } diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 9e20260611cc..aebbe65dab7e 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -31,8 +31,8 @@ * * To solve this issue, ISO 11898-1 introduces in section 11.3.3 * "Transmitter delay compensation" a SSP (Secondary Sample Point) - * equal to the distance, in time quanta, from the start of the bit - * time on the TX pin to the actual measurement on the RX pin. + * equal to the distance from the start of the bit time on the TX pin + * to the actual measurement on the RX pin. * * This structure contains the parameters to calculate that SSP. * @@ -44,8 +44,13 @@ * |<------- TDCO ------->| * |<----------- Secondary Sample Point ---------->| * + * To increase precision, contrary to the other bittiming parameters + * which are measured in time quanta, the TDC parameters are measured + * in clock periods (also referred as "minimum time quantum" in ISO + * 11898-1). + * * @tdcv: Transmitter Delay Compensation Value. The time needed for - * the signal to propagate, i.e. the distance, in time quanta, + * the signal to propagate, i.e. the distance, in clock periods, * from the start of the bit on the TX pin to when it is received * on the RX pin. @tdcv depends on the controller modes: * @@ -62,17 +67,18 @@ * TDC is disabled and all the values of this structure should be * ignored. * - * @tdco: Transmitter Delay Compensation Offset. Offset value, in time - * quanta, defining the distance between the start of the bit - * reception on the RX pin of the transceiver and the SSP + * @tdco: Transmitter Delay Compensation Offset. Offset value, in + * clock periods, defining the distance between the start of the + * bit reception on the RX pin of the transceiver and the SSP * position such that SSP = @tdcv + @tdco. * * @tdcf: Transmitter Delay Compensation Filter window. Defines the - * minimum value for the SSP position in time quanta. If the SSP - * position is less than @tdcf, then no delay compensations occur - * and the normal sampling point is used instead. The feature is - * enabled if and only if @tdcv is set to zero (automatic mode) - * and @tdcf is configured to a value greater than @tdco. + * minimum value for the SSP position in clock periods. If the + * SSP position is less than @tdcf, then no delay compensations + * occur and the normal sampling point is used instead. The + * feature is enabled if and only if @tdcv is set to zero + * (automatic mode) and @tdcf is configured to a value greater + * than @tdco. */ struct can_tdc { u32 tdcv; -- cgit v1.2.3 From da45a1e4d7b9d6b5a8231acb812df719fe3228b4 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:34 +0900 Subject: can: bittiming: change can_calc_tdco()'s prototype to not directly modify priv The function can_calc_tdco() directly retrieves can_priv from the net_device and directly modifies it. This is annoying for the upcoming patch. In drivers/net/can/dev/netlink.c:can_changelink(), the data bittiming are written to a temporary structure and memcpyed to can_priv only after everything succeeded. In the next patch, where we will introduce the netlink interface for TDC parameters, we will add a new TDC block which can potentially fail. For this reason, the data bittiming temporary structure has to be copied after that to-be-introduced TDC block. However, TDC also needs to access data bittiming information. We change the prototype so that the data bittiming structure is passed to can_calc_tdco() as an argument instead of retrieving it from priv. This way can_calc_tdco() can access the data bittiming before it gets memcpyed to priv. Link: https://lore.kernel.org/all/20210918095637.20108-4-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/bittiming.c | 17 +++++++---------- drivers/net/can/dev/netlink.c | 3 ++- include/linux/can/bittiming.h | 9 +++++++-- 3 files changed, 16 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 0ccf982ca301..0509625c3082 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -175,18 +175,15 @@ int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, return 0; } -void can_calc_tdco(struct net_device *dev) -{ - struct can_priv *priv = netdev_priv(dev); - const struct can_bittiming *dbt = &priv->data_bittiming; - struct can_tdc *tdc = &priv->tdc; - const struct can_tdc_const *tdc_const = priv->tdc_const; +void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, + const struct can_bittiming *dbt, + u32 *ctrlmode, u32 ctrlmode_supported) - if (!tdc_const || - !(priv->ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO)) +{ + if (!tdc_const || !(ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO)) return; - priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + *ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; /* As specified in ISO 11898-1 section 11.3.3 "Transmitter * delay compensation" (TDC) is only applicable if data BRP is @@ -200,7 +197,7 @@ void can_calc_tdco(struct net_device *dev) if (sample_point_in_tc < tdc_const->tdco_min) return; tdc->tdco = min(sample_point_in_tc, tdc_const->tdco_max); - priv->ctrlmode |= CAN_CTRLMODE_TDC_AUTO; + *ctrlmode |= CAN_CTRLMODE_TDC_AUTO; } } #endif /* CONFIG_CAN_CALC_BITTIMING */ diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 80425636049d..e79c9a2ffbfc 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -189,7 +189,8 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); - can_calc_tdco(dev); + can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + &priv->ctrlmode, priv->ctrlmode_supported); if (priv->do_set_data_bittiming) { /* Finally, set the bit-timing registers */ diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index aebbe65dab7e..20b50baf3a02 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -123,7 +123,9 @@ struct can_tdc_const { int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, const struct can_bittiming_const *btc); -void can_calc_tdco(struct net_device *dev); +void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, + const struct can_bittiming *dbt, + u32 *ctrlmode, u32 ctrlmode_supported); #else /* !CONFIG_CAN_CALC_BITTIMING */ static inline int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, @@ -133,7 +135,10 @@ can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, return -EINVAL; } -static inline void can_calc_tdco(struct net_device *dev) +static inline void +can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const, + const struct can_bittiming *dbt, + u32 *ctrlmode, u32 ctrlmode_supported) { } #endif /* CONFIG_CAN_CALC_BITTIMING */ -- cgit v1.2.3 From e8060f08cd69d1d692cfb9f0a2808477a501f35a Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:36 +0900 Subject: can: netlink: add can_priv::do_get_auto_tdcv() to retrieve tdcv from device MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Some CAN device can measure the TDCV (Transmission Delay Compensation Value) automatically for each transmitted CAN frames. A callback function do_get_auto_tdcv() is added to retrieve that value. This function is used only if CAN_CTRLMODE_TDC_AUTO is enabled (if CAN_CTRLMODE_TDC_MANUAL is selected, the TDCV value is provided by the user). If the device does not support reporting of TDCV, do_get_auto_tdcv() should be set to NULL and TDCV will not be reported by the netlink interface. On success, do_get_auto_tdcv() shall return 0. If the value can not be measured by the device, for example because network is down or because no frames were transmitted yet, can_priv::do_get_auto_tdcv() shall return a negative error code (e.g. -EINVAL) to signify that the value is not yet available. In such cases, TDCV is not reported by the netlink interface. Link: https://lore.kernel.org/all/20210918095637.20108-6-mailhol.vincent@wanadoo.fr CC: Stefan Mätje Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/netlink.c | 15 ++++++++++++--- include/linux/can/dev.h | 1 + 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index c77cc6ae88b6..95cca4e5251f 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -372,7 +372,8 @@ static size_t can_tdc_get_size(const struct net_device *dev) } if (can_tdc_is_enabled(priv)) { - if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL) + if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL || + priv->do_get_auto_tdcv) size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV */ size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO */ if (priv->tdc_const->tdcf_max) @@ -445,8 +446,16 @@ static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev) goto err_cancel; if (can_tdc_is_enabled(priv)) { - if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL && - nla_put_u32(skb, IFLA_CAN_TDC_TDCV, tdc->tdcv)) + u32 tdcv; + int err = -EINVAL; + + if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL) { + tdcv = tdc->tdcv; + err = 0; + } else if (priv->do_get_auto_tdcv) { + err = priv->do_get_auto_tdcv(dev, &tdcv); + } + if (!err && nla_put_u32(skb, IFLA_CAN_TDC_TDCV, tdcv)) goto err_cancel; if (nla_put_u32(skb, IFLA_CAN_TDC_TDCO, tdc->tdco)) goto err_cancel; diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 6dacbbb41e68..b4aa0f048cab 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -82,6 +82,7 @@ struct can_priv { enum can_state *state); int (*do_get_berr_counter)(const struct net_device *dev, struct can_berr_counter *bec); + int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); unsigned int echo_skb_max; struct sk_buff **echo_skb; -- cgit v1.2.3 From fa759a9395ea81c17db613dde43c46f0607df7e7 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:37 +0900 Subject: can: dev: add can_tdc_get_relative_tdco() helper function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit struct can_tdc::tdco represents the absolute offset from TDCV. Some controllers use instead an offset relative to the Sample Point (SP) such that: | SSP = TDCV + absolute TDCO | = TDCV + SP + relative TDCO Consequently: | relative TDCO = absolute TDCO - SP The function can_tdc_get_relative_tdco() allow to retrieve this relative TDCO value. Link: https://lore.kernel.org/all/20210918095637.20108-7-mailhol.vincent@wanadoo.fr CC: Stefan Mätje Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index b4aa0f048cab..45f19d9db5ca 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -102,6 +102,35 @@ static inline bool can_tdc_is_enabled(const struct can_priv *priv) return !!(priv->ctrlmode & CAN_CTRLMODE_TDC_MASK); } +/* + * can_get_relative_tdco() - TDCO relative to the sample point + * + * struct can_tdc::tdco represents the absolute offset from TDCV. Some + * controllers use instead an offset relative to the Sample Point (SP) + * such that: + * + * SSP = TDCV + absolute TDCO + * = TDCV + SP + relative TDCO + * + * -+----------- one bit ----------+-- TX pin + * |<--- Sample Point --->| + * + * --+----------- one bit ----------+-- RX pin + * |<-------- TDCV -------->| + * |<------------------------>| absolute TDCO + * |<--- Sample Point --->| + * | |<->| relative TDCO + * |<------------- Secondary Sample Point ------------>| + */ +static inline s32 can_get_relative_tdco(const struct can_priv *priv) +{ + const struct can_bittiming *dbt = &priv->data_bittiming; + s32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg + + dbt->phase_seg1) * dbt->brp; + + return (s32)priv->tdc.tdco - sample_point_in_tc; +} + /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) -- cgit v1.2.3 From b3b180e735409ca0c76642014304b59482e0e653 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 20 Sep 2021 14:20:07 +0200 Subject: dmaengine: remove debugfs #ifdef The ptdma driver has added debugfs support, but this fails to build when debugfs is disabled: drivers/dma/ptdma/ptdma-debugfs.c: In function 'ptdma_debugfs_setup': drivers/dma/ptdma/ptdma-debugfs.c:93:54: error: 'struct dma_device' has no member named 'dbg_dev_root' 93 | debugfs_create_file("info", 0400, pt->dma_dev.dbg_dev_root, pt, | ^ drivers/dma/ptdma/ptdma-debugfs.c:96:55: error: 'struct dma_device' has no member named 'dbg_dev_root' 96 | debugfs_create_file("stats", 0400, pt->dma_dev.dbg_dev_root, pt, | ^ drivers/dma/ptdma/ptdma-debugfs.c:102:52: error: 'struct dma_device' has no member named 'dbg_dev_root' 102 | debugfs_create_dir("q", pt->dma_dev.dbg_dev_root); | ^ Remove the #ifdef in the header, as this only saves a few bytes, but would require ugly #ifdefs in each driver using it. Simplify the other user while we're at it. Fixes: e2fb2e2a33fa ("dmaengine: ptdma: Add debugfs entries for PTDMA") Fixes: 26cf132de6f7 ("dmaengine: Create debug directories for DMA devices") Signed-off-by: Arnd Bergmann Reviewed-by: Laurent Pinchart Link: https://lore.kernel.org/r/20210920122017.205975-1-arnd@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/xilinx/xilinx_dpdma.c | 15 +-------------- include/linux/dmaengine.h | 2 -- 2 files changed, 1 insertion(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index b280a53e8570..ce5c66e6897d 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -271,9 +271,6 @@ struct xilinx_dpdma_device { /* ----------------------------------------------------------------------------- * DebugFS */ - -#ifdef CONFIG_DEBUG_FS - #define XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE 32 #define XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR "65535" @@ -299,7 +296,7 @@ struct xilinx_dpdma_debugfs_request { static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan) { - if (chan->id == dpdma_debugfs.chan_id) + if (IS_ENABLED(CONFIG_DEBUG_FS) && chan->id == dpdma_debugfs.chan_id) dpdma_debugfs.xilinx_dpdma_irq_done_count++; } @@ -462,16 +459,6 @@ static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev) dev_err(xdev->dev, "Failed to create debugfs testcase file\n"); } -#else -static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev) -{ -} - -static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan) -{ -} -#endif /* CONFIG_DEBUG_FS */ - /* ----------------------------------------------------------------------------- * I/O Accessors */ diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index e5c2c9e71bf1..9000f3ffce8b 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -944,10 +944,8 @@ struct dma_device { void (*device_issue_pending)(struct dma_chan *chan); void (*device_release)(struct dma_device *dev); /* debugfs support */ -#ifdef CONFIG_DEBUG_FS void (*dbg_summary_show)(struct seq_file *s, struct dma_device *dev); struct dentry *dbg_dev_root; -#endif }; static inline int dmaengine_slave_config(struct dma_chan *chan, -- cgit v1.2.3 From 1ba5478270a5c3a02b08052a3c003c282f2db94a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 22 Oct 2021 17:49:21 +0200 Subject: irqchip: Fix compile-testing without CONFIG_OF Drivers using the new IRQCHIP_PLATFORM_DRIVER_BEGIN helper fail to link when compile-testing without CONFIG_OF, as that means CONFIG_IRQCHIP is disabled as well: ld.lld: error: undefined symbol: platform_irqchip_probe >>> referenced by irq-meson-gpio.c >>> irqchip/irq-meson-gpio.o:(meson_gpio_intc_driver) in archive drivers/built-in.a >>> referenced by irq-mchp-eic.c >>> irqchip/irq-mchp-eic.o:(mchp_eic_driver) in archive drivers/built-in.a As the drivers are not actually used in this case, just making the reference to this symbol conditional helps avoid the link failure. Fixes: f8410e626569 ("irqchip: Add IRQCHIP_PLATFORM_DRIVER_BEGIN/END and IRQCHIP_MATCH helper macros") Signed-off-by: Arnd Bergmann Reviewed-by: Florian Fainelli Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211022154927.920491-1-arnd@kernel.org --- include/linux/irqchip.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index 67351aac65ef..29dbe675fc7a 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -39,8 +39,9 @@ static const struct of_device_id drv_name##_irqchip_match_table[] = { {}, \ }; \ MODULE_DEVICE_TABLE(of, drv_name##_irqchip_match_table); \ -static struct platform_driver drv_name##_driver = { \ - .probe = platform_irqchip_probe, \ +static struct platform_driver drv_name##_driver = { \ + .probe = IS_ENABLED(CONFIG_IRQCHIP) ? \ + platform_irqchip_probe : NULL, \ .driver = { \ .name = #drv_name, \ .owner = THIS_MODULE, \ -- cgit v1.2.3 From f2739ca15c414ebad88f4333e3186fd4144c1753 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Fri, 22 Oct 2021 11:46:42 -0500 Subject: x86/of: Kill unused early_init_dt_scan_chosen_arch() There are no callers for early_init_dt_scan_chosen_arch(), so remove it. Signed-off-by: Rob Herring Signed-off-by: Borislav Petkov Reviewed-by: Frank Rowand Link: https://lkml.kernel.org/r/20211022164642.2815706-1-robh@kernel.org --- arch/x86/kernel/devicetree.c | 5 ----- include/linux/of_fdt.h | 1 - 2 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 6a4cb71c2498..78b2311b3b8b 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -31,11 +31,6 @@ char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -void __init early_init_dt_scan_chosen_arch(unsigned long node) -{ - BUG(); -} - void __init early_init_dt_add_memory_arch(u64 base, u64 size) { BUG(); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index cf6a65b94d40..cf48983d3c86 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -65,7 +65,6 @@ extern int early_init_dt_scan_memory(unsigned long node, const char *uname, extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); -extern void __init early_init_dt_scan_chosen_arch(unsigned long node); extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); -- cgit v1.2.3 From a1b09501971435ef213251891753afb0d7f3d27a Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 20 Oct 2021 11:24:06 +0100 Subject: irq: add generic_handle_arch_irq() Several architectures select GENERIC_IRQ_MULTI_HANDLER and branch to handle_arch_irq() without performing any entry accounting. Add a generic wrapper to handle the common irqentry work when invoking handle_arch_irq(). Where an architecture needs to perform some entry accounting itself, it will need to invoke handle_arch_irq() itself. In subsequent patches it will become the responsibilty of the entry code to set the irq regs when entering an IRQ (rather than deferring this to an irqchip handler), so generic_handle_arch_irq() is made to set the irq regs now. This can be redundant in some cases, but is never harmful as saving/restoring the old regs nests safely. Signed-off-by: Mark Rutland Reviewed-by: Marc Zyngier Reviewed-by: Guo Ren Cc: Thomas Gleixner --- include/linux/irq.h | 1 + kernel/irq/handle.c | 18 ++++++++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index c8293c817646..988c225eef2d 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1261,6 +1261,7 @@ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)); * top-level IRQ handler. */ extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init; +asmlinkage void generic_handle_arch_irq(struct pt_regs *regs); #else #ifndef set_handle_irq #define set_handle_irq(handle_irq) \ diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 221d80c31e94..27182003b879 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -14,6 +14,8 @@ #include #include +#include + #include #include "internals.h" @@ -226,4 +228,20 @@ int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) handle_arch_irq = handle_irq; return 0; } + +/** + * generic_handle_arch_irq - root irq handler for architectures which do no + * entry accounting themselves + * @regs: Register file coming from the low-level handling code + */ +asmlinkage void noinstr generic_handle_arch_irq(struct pt_regs *regs) +{ + struct pt_regs *old_regs; + + irq_enter(); + old_regs = set_irq_regs(regs); + handle_arch_irq(regs); + set_irq_regs(old_regs); + irq_exit(); +} #endif -- cgit v1.2.3 From 63c67f526db86d3102a77437a510c949f6debb08 Mon Sep 17 00:00:00 2001 From: Luo Jie Date: Sun, 24 Oct 2021 16:27:34 +0800 Subject: net: phy: add genphy_c45_fast_retrain Add generic fast retrain auto-negotiation function for C45 PHYs. Signed-off-by: Luo Jie Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/phy/phy-c45.c | 34 ++++++++++++++++++++++++++++++++++ include/linux/phy.h | 1 + 2 files changed, 35 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index c617dbcad6ea..b01180e1f578 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -611,6 +611,40 @@ int genphy_c45_loopback(struct phy_device *phydev, bool enable) } EXPORT_SYMBOL_GPL(genphy_c45_loopback); +/** + * genphy_c45_fast_retrain - configure fast retrain registers + * @phydev: target phy_device struct + * + * Description: If fast-retrain is enabled, we configure PHY as + * advertising fast retrain capable and THP Bypass Request, then + * enable fast retrain. If it is not enabled, we configure fast + * retrain disabled. + */ +int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable) +{ + int ret; + + if (!enable) + return phy_clear_bits_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FSRT_CSR, + MDIO_PMA_10GBR_FSRT_ENABLE); + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, phydev->supported)) { + ret = phy_set_bits_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, + MDIO_AN_10GBT_CTRL_ADVFSRT2_5G); + if (ret) + return ret; + + ret = phy_set_bits_mmd(phydev, MDIO_MMD_AN, MDIO_AN_CTRL2, + MDIO_AN_THP_BP2_5GT); + if (ret) + return ret; + } + + return phy_set_bits_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_FSRT_CSR, + MDIO_PMA_10GBR_FSRT_ENABLE); +} +EXPORT_SYMBOL_GPL(genphy_c45_fast_retrain); + struct phy_driver genphy_c45_driver = { .phy_id = 0xffffffff, .phy_id_mask = 0xffffffff, diff --git a/include/linux/phy.h b/include/linux/phy.h index 736e1d1a47c4..04e90423fa88 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1584,6 +1584,7 @@ int genphy_c45_config_aneg(struct phy_device *phydev); int genphy_c45_loopback(struct phy_device *phydev, bool enable); int genphy_c45_pma_resume(struct phy_device *phydev); int genphy_c45_pma_suspend(struct phy_device *phydev); +int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; -- cgit v1.2.3 From 1705643faecde95bdeb11bea5ab5baed084e9f91 Mon Sep 17 00:00:00 2001 From: Sean Wang Date: Tue, 19 Oct 2021 05:30:20 +0800 Subject: mmc: add MT7921 SDIO identifiers for MediaTek Bluetooth devices The MT7961 SDIO identifier for MediaTek Bluetooth devices were being referred in the MediaTek Bluetooth driver. Co-developed-by: Mark-yw Chen Signed-off-by: Mark-yw Chen Signed-off-by: Sean Wang Signed-off-by: Marcel Holtmann --- include/linux/mmc/sdio_ids.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index a85c9f0bd470..53f0efa0bccf 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -105,6 +105,7 @@ #define SDIO_VENDOR_ID_MEDIATEK 0x037a #define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 #define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 +#define SDIO_DEVICE_ID_MEDIATEK_MT7961 0x7961 #define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 #define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 -- cgit v1.2.3 From 6b19b766e8f077f29cdb47da5003469a85bbfb9c Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 21 Oct 2021 09:22:35 -0600 Subject: fs: get rid of the res2 iocb->ki_complete argument The second argument was only used by the USB gadget code, yet everyone pays the overhead of passing a zero to be passed into aio, where it ends up being part of the aio res2 value. Now that everybody is passing in zero, kill off the extra argument. Reviewed-by: Darrick J. Wong Signed-off-by: Jens Axboe --- block/fops.c | 2 +- crypto/af_alg.c | 2 +- drivers/block/loop.c | 4 ++-- drivers/nvme/target/io-cmd-file.c | 4 ++-- drivers/target/target_core_file.c | 4 ++-- drivers/usb/gadget/function/f_fs.c | 2 +- drivers/usb/gadget/legacy/inode.c | 5 ++--- fs/aio.c | 6 +++--- fs/cachefiles/io.c | 12 ++++++------ fs/ceph/file.c | 2 +- fs/cifs/file.c | 4 ++-- fs/direct-io.c | 2 +- fs/fuse/file.c | 2 +- fs/io_uring.c | 6 +++--- fs/iomap/direct-io.c | 2 +- fs/nfs/direct.c | 2 +- fs/overlayfs/file.c | 4 ++-- include/linux/fs.h | 2 +- 18 files changed, 33 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/block/fops.c b/block/fops.c index 396537598e3e..d86ebda73e8c 100644 --- a/block/fops.c +++ b/block/fops.c @@ -164,7 +164,7 @@ static void blkdev_bio_end_io(struct bio *bio) ret = blk_status_to_errno(dio->bio.bi_status); } - dio->iocb->ki_complete(iocb, ret, 0); + dio->iocb->ki_complete(iocb, ret); if (dio->flags & DIO_MULTI_BIO) bio_put(&dio->bio); } else { diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 8bd288d2b089..3dd5a773c320 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -1076,7 +1076,7 @@ void af_alg_async_cb(struct crypto_async_request *_req, int err) af_alg_free_resources(areq); sock_put(sk); - iocb->ki_complete(iocb, err ? err : (int)resultlen, 0); + iocb->ki_complete(iocb, err ? err : (int)resultlen); } EXPORT_SYMBOL_GPL(af_alg_async_cb); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 7bf4686af774..469d87e24fd4 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -554,7 +554,7 @@ static void lo_rw_aio_do_completion(struct loop_cmd *cmd) blk_mq_complete_request(rq); } -static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) +static void lo_rw_aio_complete(struct kiocb *iocb, long ret) { struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); @@ -627,7 +627,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, lo_rw_aio_do_completion(cmd); if (ret != -EIOCBQUEUED) - cmd->iocb.ki_complete(&cmd->iocb, ret, 0); + lo_rw_aio_complete(&cmd->iocb, ret); return 0; } diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 1dd1a0fe2e81..6aa30f30b572 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -125,7 +125,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, return call_iter(iocb, &iter); } -static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2) +static void nvmet_file_io_done(struct kiocb *iocb, long ret) { struct nvmet_req *req = container_of(iocb, struct nvmet_req, f.iocb); u16 status = NVME_SC_SUCCESS; @@ -222,7 +222,7 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags) } complete: - nvmet_file_io_done(&req->f.iocb, ret, 0); + nvmet_file_io_done(&req->f.iocb, ret); return true; } diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 02f64453b4c5..8190b840065f 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -245,7 +245,7 @@ struct target_core_file_cmd { struct bio_vec bvecs[]; }; -static void cmd_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) +static void cmd_rw_aio_complete(struct kiocb *iocb, long ret) { struct target_core_file_cmd *cmd; @@ -303,7 +303,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, ret = call_read_iter(file, &aio_cmd->iocb, &iter); if (ret != -EIOCBQUEUED) - cmd_rw_aio_complete(&aio_cmd->iocb, ret, 0); + cmd_rw_aio_complete(&aio_cmd->iocb, ret); return 0; } diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 7bd22398d52f..e20c19a0f106 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -831,7 +831,7 @@ static void ffs_user_copy_worker(struct work_struct *work) kthread_unuse_mm(io_data->mm); } - io_data->kiocb->ki_complete(io_data->kiocb, ret, 0); + io_data->kiocb->ki_complete(io_data->kiocb, ret); if (io_data->ffs->ffs_eventfd && !kiocb_has_eventfd) eventfd_signal(io_data->ffs->ffs_eventfd, 1); diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 28d3d4e71182..78be94750232 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -469,7 +469,7 @@ static void ep_user_copy_worker(struct work_struct *work) ret = -EFAULT; /* completing the iocb can drop the ctx and mm, don't touch mm after */ - iocb->ki_complete(iocb, ret, 0); + iocb->ki_complete(iocb, ret); kfree(priv->buf); kfree(priv->to_free); @@ -497,8 +497,7 @@ static void ep_aio_complete(struct usb_ep *ep, struct usb_request *req) kfree(priv); iocb->private = NULL; iocb->ki_complete(iocb, - req->actual ? req->actual : (long)req->status, - 0); + req->actual ? req->actual : (long)req->status); } else { /* ep_copy_to_user() won't report both; we hide some faults */ if (unlikely(0 != req->status)) diff --git a/fs/aio.c b/fs/aio.c index 51b08ab01dff..836dc7e48db7 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1417,7 +1417,7 @@ static void aio_remove_iocb(struct aio_kiocb *iocb) spin_unlock_irqrestore(&ctx->ctx_lock, flags); } -static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) +static void aio_complete_rw(struct kiocb *kiocb, long res) { struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw); @@ -1437,7 +1437,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) } iocb->ki_res.res = res; - iocb->ki_res.res2 = res2; + iocb->ki_res.res2 = 0; iocb_put(iocb); } @@ -1508,7 +1508,7 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret) ret = -EINTR; fallthrough; default: - req->ki_complete(req, ret, 0); + req->ki_complete(req, ret); } } diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index fac2e8e7b533..effe37ef8629 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -37,11 +37,11 @@ static inline void cachefiles_put_kiocb(struct cachefiles_kiocb *ki) /* * Handle completion of a read from the cache. */ -static void cachefiles_read_complete(struct kiocb *iocb, long ret, long ret2) +static void cachefiles_read_complete(struct kiocb *iocb, long ret) { struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb); - _enter("%ld,%ld", ret, ret2); + _enter("%ld", ret); if (ki->term_func) { if (ret >= 0) @@ -139,7 +139,7 @@ static int cachefiles_read(struct netfs_cache_resources *cres, fallthrough; default: ki->was_async = false; - cachefiles_read_complete(&ki->iocb, ret, 0); + cachefiles_read_complete(&ki->iocb, ret); if (ret > 0) ret = 0; break; @@ -159,12 +159,12 @@ presubmission_error: /* * Handle completion of a write to the cache. */ -static void cachefiles_write_complete(struct kiocb *iocb, long ret, long ret2) +static void cachefiles_write_complete(struct kiocb *iocb, long ret) { struct cachefiles_kiocb *ki = container_of(iocb, struct cachefiles_kiocb, iocb); struct inode *inode = file_inode(ki->iocb.ki_filp); - _enter("%ld,%ld", ret, ret2); + _enter("%ld", ret); /* Tell lockdep we inherited freeze protection from submission thread */ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); @@ -244,7 +244,7 @@ static int cachefiles_write(struct netfs_cache_resources *cres, fallthrough; default: ki->was_async = false; - cachefiles_write_complete(&ki->iocb, ret, 0); + cachefiles_write_complete(&ki->iocb, ret); if (ret > 0) ret = 0; break; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index d16fd2d5fd42..e10a80c1b581 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1023,7 +1023,7 @@ static void ceph_aio_complete(struct inode *inode, ceph_put_cap_refs(ci, (aio_req->write ? CEPH_CAP_FILE_WR : CEPH_CAP_FILE_RD)); - aio_req->iocb->ki_complete(aio_req->iocb, ret, 0); + aio_req->iocb->ki_complete(aio_req->iocb, ret); ceph_free_cap_flush(aio_req->prealloc_cf); kfree(aio_req); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 13f3182cf796..1b855fcb179e 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -3184,7 +3184,7 @@ restart_loop: mutex_unlock(&ctx->aio_mutex); if (ctx->iocb && ctx->iocb->ki_complete) - ctx->iocb->ki_complete(ctx->iocb, ctx->rc, 0); + ctx->iocb->ki_complete(ctx->iocb, ctx->rc); else complete(&ctx->done); } @@ -3917,7 +3917,7 @@ again: mutex_unlock(&ctx->aio_mutex); if (ctx->iocb && ctx->iocb->ki_complete) - ctx->iocb->ki_complete(ctx->iocb, ctx->rc, 0); + ctx->iocb->ki_complete(ctx->iocb, ctx->rc); else complete(&ctx->done); } diff --git a/fs/direct-io.c b/fs/direct-io.c index 453dcff0e7f5..654443558047 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -307,7 +307,7 @@ static ssize_t dio_complete(struct dio *dio, ssize_t ret, unsigned int flags) if (ret > 0 && dio->op == REQ_OP_WRITE) ret = generic_write_sync(dio->iocb, ret); - dio->iocb->ki_complete(dio->iocb, ret, 0); + dio->iocb->ki_complete(dio->iocb, ret); } kmem_cache_free(dio_cache, dio); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 11404f8c21c7..e6039f22311b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -687,7 +687,7 @@ static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos) spin_unlock(&fi->lock); } - io->iocb->ki_complete(io->iocb, res, 0); + io->iocb->ki_complete(io->iocb, res); } kref_put(&io->refcnt, fuse_io_release); diff --git a/fs/io_uring.c b/fs/io_uring.c index d4631a55a692..edf29406ba8b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2689,7 +2689,7 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, __io_req_complete(req, issue_flags, req->result, io_put_rw_kbuf(req)); } -static void io_complete_rw(struct kiocb *kiocb, long res, long res2) +static void io_complete_rw(struct kiocb *kiocb, long res) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); @@ -2700,7 +2700,7 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2) io_req_task_work_add(req); } -static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) +static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); @@ -2913,7 +2913,7 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) ret = -EINTR; fallthrough; default: - kiocb->ki_complete(kiocb, ret, 0); + kiocb->ki_complete(kiocb, ret); } } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 83ecfba53abe..811c898125a5 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -125,7 +125,7 @@ static void iomap_dio_complete_work(struct work_struct *work) struct iomap_dio *dio = container_of(work, struct iomap_dio, aio.work); struct kiocb *iocb = dio->iocb; - iocb->ki_complete(iocb, iomap_dio_complete(dio), 0); + iocb->ki_complete(iocb, iomap_dio_complete(dio)); } /* diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 2e894fec036b..7a5f287c5391 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -275,7 +275,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq) res = (long) dreq->count; WARN_ON_ONCE(dreq->count < 0); } - dreq->iocb->ki_complete(dreq->iocb, res, 0); + dreq->iocb->ki_complete(dreq->iocb, res); } complete(&dreq->completion); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index c88ac571593d..ac461a499882 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -272,14 +272,14 @@ static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req) kmem_cache_free(ovl_aio_request_cachep, aio_req); } -static void ovl_aio_rw_complete(struct kiocb *iocb, long res, long res2) +static void ovl_aio_rw_complete(struct kiocb *iocb, long res) { struct ovl_aio_req *aio_req = container_of(iocb, struct ovl_aio_req, iocb); struct kiocb *orig_iocb = aio_req->orig_iocb; ovl_aio_cleanup_handler(aio_req); - orig_iocb->ki_complete(orig_iocb, res, res2); + orig_iocb->ki_complete(orig_iocb, res); } static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) diff --git a/include/linux/fs.h b/include/linux/fs.h index 31029a91f440..0dcb9020a7b3 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -330,7 +330,7 @@ struct kiocb { randomized_struct_fields_start loff_t ki_pos; - void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); + void (*ki_complete)(struct kiocb *iocb, long ret); void *private; int ki_flags; u16 ki_hint; -- cgit v1.2.3 From cb464ba53c0cb497dcb4a3daaf4fad4b75291863 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Mon, 11 Oct 2021 13:14:28 +0300 Subject: net/mlx5: Extend health buffer dump Enhance health buffer to include: - assert_var5: expose the 6'th assert variable. - time: error's time-stamp in seconds (epoch time). - rfr: Recovery Flow Requiered. When set, indicates that the error cannot be recovered without flow involving reset. - severity: error's severity value, ranging from emergency to debug. Expose them in the health buffer dump (dmesg and devlink fw reporter). Health buffer in dmesg: mlx5_core 0000:08:00.0: print_health_info:425:(pid 912): Health issue observed, firmware internal error, severity(3) ERROR: mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[0] 0x08040700 mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[1] 0x00000000 mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[2] 0x00000000 mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[3] 0x00000000 mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[4] 0x00000000 mlx5_core 0000:08:00.0: print_health_info:429:(pid 912): assert_var[5] 0x00000000 mlx5_core 0000:08:00.0: print_health_info:432:(pid 912): assert_exit_ptr 0x00aaf800 mlx5_core 0000:08:00.0: print_health_info:434:(pid 912): assert_callra 0x00aaf70c mlx5_core 0000:08:00.0: print_health_info:436:(pid 912): fw_ver 16.32.492 mlx5_core 0000:08:00.0: print_health_info:437:(pid 912): time 1634819758 mlx5_core 0000:08:00.0: print_health_info:438:(pid 912): hw_id 0x0000020d mlx5_core 0000:08:00.0: print_health_info:439:(pid 912): rfr 0 mlx5_core 0000:08:00.0: print_health_info:440:(pid 912): severity 3 (ERROR) mlx5_core 0000:08:00.0: print_health_info:441:(pid 912): irisc_index 9 mlx5_core 0000:08:00.0: print_health_info:442:(pid 912): synd 0x1: firmware internal error mlx5_core 0000:08:00.0: print_health_info:444:(pid 912): ext_synd 0x802b mlx5_core 0000:08:00.0: print_health_info:445:(pid 912): raw fw_ver 0x102001ec Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 73 +++++++++++++++++++++--- include/linux/mlx5/device.h | 14 +++-- include/linux/mlx5/mlx5_ifc.h | 10 +++- 3 files changed, 82 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 6a4dd7f78958..538ef392f54c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "mlx5_core.h" #include "lib/eq.h" #include "lib/mlx5.h" @@ -74,6 +75,11 @@ enum { MLX5_SENSOR_FW_SYND_RFR = 5, }; +enum { + MLX5_SEVERITY_MASK = 0x7, + MLX5_SEVERITY_VALID_MASK = 0x8, +}; + u8 mlx5_get_nic_state(struct mlx5_core_dev *dev) { return (ioread32be(&dev->iseg->cmdq_addr_l_sz) >> 8) & 7; @@ -98,12 +104,19 @@ static bool sensor_pci_not_working(struct mlx5_core_dev *dev) return (ioread32be(&h->fw_ver) == 0xffffffff); } +static int mlx5_health_get_rfr(u8 rfr_severity) +{ + return rfr_severity >> MLX5_RFR_BIT_OFFSET; +} + static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - u32 rfr = ioread32be(&h->rfr) >> MLX5_RFR_OFFSET; u8 synd = ioread8(&h->synd); + u8 rfr; + + rfr = mlx5_health_get_rfr(ioread8(&h->rfr_severity)); if (rfr && synd) mlx5_core_dbg(dev, "FW requests reset, synd: %d\n", synd); @@ -366,18 +379,52 @@ static const char *hsynd_str(u8 synd) } } +static const char *mlx5_loglevel_str(int level) +{ + switch (level) { + case LOGLEVEL_EMERG: + return "EMERGENCY"; + case LOGLEVEL_ALERT: + return "ALERT"; + case LOGLEVEL_CRIT: + return "CRITICAL"; + case LOGLEVEL_ERR: + return "ERROR"; + case LOGLEVEL_WARNING: + return "WARNING"; + case LOGLEVEL_NOTICE: + return "NOTICE"; + case LOGLEVEL_INFO: + return "INFO"; + case LOGLEVEL_DEBUG: + return "DEBUG"; + } + return "Unknown log level"; +} + +static int mlx5_health_get_severity(u8 rfr_severity) +{ + return rfr_severity & MLX5_SEVERITY_VALID_MASK ? + rfr_severity & MLX5_SEVERITY_MASK : LOGLEVEL_ERR; +} + static void print_health_info(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - char fw_str[18]; - u32 fw; + u8 rfr_severity; + int severity; int i; /* If the syndrome is 0, the device is OK and no need to print buffer */ if (!ioread8(&h->synd)) return; + rfr_severity = ioread8(&h->rfr_severity); + severity = mlx5_health_get_severity(rfr_severity); + mlx5_core_err(dev, "Health issue observed, %s, severity(%d) %s:\n", + hsynd_str(ioread8(&h->synd)), severity, mlx5_loglevel_str(severity)); + for (i = 0; i < ARRAY_SIZE(h->assert_var); i++) mlx5_core_err(dev, "assert_var[%d] 0x%08x\n", i, ioread32be(h->assert_var + i)); @@ -386,15 +433,16 @@ static void print_health_info(struct mlx5_core_dev *dev) ioread32be(&h->assert_exit_ptr)); mlx5_core_err(dev, "assert_callra 0x%08x\n", ioread32be(&h->assert_callra)); - sprintf(fw_str, "%d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev)); - mlx5_core_err(dev, "fw_ver %s\n", fw_str); + mlx5_core_err(dev, "fw_ver %d.%d.%d", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev)); + mlx5_core_err(dev, "time %u\n", ioread32be(&h->time)); mlx5_core_err(dev, "hw_id 0x%08x\n", ioread32be(&h->hw_id)); + mlx5_core_err(dev, "rfr %d\n", mlx5_health_get_rfr(rfr_severity)); + mlx5_core_err(dev, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity)); mlx5_core_err(dev, "irisc_index %d\n", ioread8(&h->irisc_index)); mlx5_core_err(dev, "synd 0x%x: %s\n", ioread8(&h->synd), hsynd_str(ioread8(&h->synd))); mlx5_core_err(dev, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd)); - fw = ioread32be(&h->fw_ver); - mlx5_core_err(dev, "raw fw_ver 0x%08x\n", fw); + mlx5_core_err(dev, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver)); } static int @@ -443,6 +491,7 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; + u8 rfr_severity; int err; int i; @@ -473,9 +522,19 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, return err; err = devlink_fmsg_u32_pair_put(fmsg, "assert_callra", ioread32be(&h->assert_callra)); + if (err) + return err; + err = devlink_fmsg_u32_pair_put(fmsg, "time", ioread32be(&h->time)); if (err) return err; err = devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id)); + if (err) + return err; + rfr_severity = ioread8(&h->rfr_severity); + err = devlink_fmsg_u8_pair_put(fmsg, "rfr", mlx5_health_get_rfr(rfr_severity)); + if (err) + return err; + err = devlink_fmsg_u8_pair_put(fmsg, "severity", mlx5_health_get_severity(rfr_severity)); if (err) return err; err = devlink_fmsg_u8_pair_put(fmsg, "irisc_index", diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 347167c18802..f8a0bbb42c3b 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -541,19 +541,21 @@ struct mlx5_cmd_layout { u8 status_own; }; -enum mlx5_fatal_assert_bit_offsets { - MLX5_RFR_OFFSET = 31, +enum mlx5_rfr_severity_bit_offsets { + MLX5_RFR_BIT_OFFSET = 0x7, }; struct health_buffer { - __be32 assert_var[5]; - __be32 rsvd0[3]; + __be32 assert_var[6]; + __be32 rsvd0[2]; __be32 assert_exit_ptr; __be32 assert_callra; - __be32 rsvd1[2]; + __be32 rsvd1[1]; + __be32 time; __be32 fw_ver; __be32 hw_id; - __be32 rfr; + u8 rfr_severity; + u8 rsvd2[3]; u8 irisc_index; u8 synd; __be16 ext_synd; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 09e43019d877..6d292b5b8992 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -4149,13 +4149,19 @@ struct mlx5_ifc_health_buffer_bits { u8 assert_callra[0x20]; - u8 reserved_at_140[0x40]; + u8 reserved_at_140[0x20]; + + u8 time[0x20]; u8 fw_version[0x20]; u8 hw_id[0x20]; - u8 reserved_at_1c0[0x20]; + u8 rfr[0x1]; + u8 reserved_at_1c1[0x3]; + u8 valid[0x1]; + u8 severity[0x3]; + u8 reserved_at_1c8[0x18]; u8 irisc_index[0x8]; u8 synd[0x8]; -- cgit v1.2.3 From 5a1023deeed02a2078bcc11eec1c4be31e85892d Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Wed, 13 Oct 2021 09:45:22 +0300 Subject: net/mlx5: Add periodic update of host time to firmware Firmware logs its asserts also to non-volatile memory. In order to reduce drift between the NIC and the host, the driver sets the host epoch-time to the firmware every hour. Signed-off-by: Aya Levin Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 30 ++++++++++++++++++++++++ include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 12 ++++++++++ 3 files changed, 44 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index c35a27255232..64f1abc4dc36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -752,6 +752,31 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev) spin_unlock_irqrestore(&health->wq_lock, flags); } +#define MLX5_MSEC_PER_HOUR (MSEC_PER_SEC * 60 * 60) +static void mlx5_health_log_ts_update(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + u32 out[MLX5_ST_SZ_DW(mrtc_reg)] = {}; + u32 in[MLX5_ST_SZ_DW(mrtc_reg)] = {}; + struct mlx5_core_health *health; + struct mlx5_core_dev *dev; + struct mlx5_priv *priv; + u64 now_us; + + health = container_of(dwork, struct mlx5_core_health, update_fw_log_ts_work); + priv = container_of(health, struct mlx5_priv, health); + dev = container_of(priv, struct mlx5_core_dev, priv); + + now_us = ktime_to_us(ktime_get_real()); + + MLX5_SET(mrtc_reg, in, time_h, now_us >> 32); + MLX5_SET(mrtc_reg, in, time_l, now_us & 0xFFFFFFFF); + mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out), MLX5_REG_MRTC, 0, 1); + + queue_delayed_work(health->wq, &health->update_fw_log_ts_work, + msecs_to_jiffies(MLX5_MSEC_PER_HOUR)); +} + static void poll_health(struct timer_list *t) { struct mlx5_core_dev *dev = from_timer(dev, t, priv.health.timer); @@ -834,6 +859,7 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev) spin_lock_irqsave(&health->wq_lock, flags); set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); spin_unlock_irqrestore(&health->wq_lock, flags); + cancel_delayed_work_sync(&health->update_fw_log_ts_work); cancel_work_sync(&health->report_work); cancel_work_sync(&health->fatal_report_work); } @@ -849,6 +875,7 @@ void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; + cancel_delayed_work_sync(&health->update_fw_log_ts_work); destroy_workqueue(health->wq); mlx5_fw_reporters_destroy(dev); } @@ -874,6 +901,9 @@ int mlx5_health_init(struct mlx5_core_dev *dev) spin_lock_init(&health->wq_lock); INIT_WORK(&health->fatal_report_work, mlx5_fw_fatal_reporter_err_work); INIT_WORK(&health->report_work, mlx5_fw_reporter_err_work); + INIT_DELAYED_WORK(&health->update_fw_log_ts_work, mlx5_health_log_ts_update); + if (mlx5_core_is_pf(dev)) + queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0); return 0; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3f4c0f2314a5..f617dfbcd9fd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -134,6 +134,7 @@ enum { MLX5_REG_MCIA = 0x9014, MLX5_REG_MFRL = 0x9028, MLX5_REG_MLCR = 0x902b, + MLX5_REG_MRTC = 0x902d, MLX5_REG_MTRC_CAP = 0x9040, MLX5_REG_MTRC_CONF = 0x9041, MLX5_REG_MTRC_STDB = 0x9042, @@ -440,6 +441,7 @@ struct mlx5_core_health { struct work_struct report_work; struct devlink_health_reporter *fw_reporter; struct devlink_health_reporter *fw_fatal_reporter; + struct delayed_work update_fw_log_ts_work; }; struct mlx5_qp_table { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 6d292b5b8992..746381eccccf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10358,6 +10358,17 @@ struct mlx5_ifc_pddr_reg_bits { union mlx5_ifc_pddr_reg_page_data_auto_bits page_data; }; +struct mlx5_ifc_mrtc_reg_bits { + u8 time_synced[0x1]; + u8 reserved_at_1[0x1f]; + + u8 reserved_at_20[0x20]; + + u8 time_h[0x20]; + + u8 time_l[0x20]; +}; + union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_bufferx_reg_bits bufferx_reg; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout; @@ -10419,6 +10430,7 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_mirc_reg_bits mirc_reg; struct mlx5_ifc_mfrl_reg_bits mfrl_reg; struct mlx5_ifc_mtutc_reg_bits mtutc_reg; + struct mlx5_ifc_mrtc_reg_bits mrtc_reg; u8 reserved_at_0[0x60e0]; }; -- cgit v1.2.3 From 46ae40b94d8826591472798114a723cc7feac7a7 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 12 Aug 2021 11:53:34 +0300 Subject: net/mlx5: Let user configure io_eq_size param Currently, each I/O EQ is taking 128KB of memory. This size is not needed in all use cases, and is critical with large scale. Hence, allow user to configure the size of I/O EQs. For example, to reduce I/O EQ size to 64, execute: $ devlink resource set pci/0000:00:0b.0 path /io_eq_size/ size 64 $ devlink dev reload pci/0000:00:0b.0 Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- Documentation/networking/devlink/mlx5.rst | 12 +++++ drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/devlink.h | 11 +++++ .../net/ethernet/mellanox/mlx5/core/devlink_res.c | 56 ++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/eq.c | 3 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 3 ++ include/linux/mlx5/driver.h | 4 -- 7 files changed, 85 insertions(+), 6 deletions(-) create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c (limited to 'include/linux') diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 4e4b97f7971a..4e6020570292 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -46,6 +46,18 @@ parameters. The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD`` +Resources +========= + +.. list-table:: Driver-specific resources implemented + :widths: 5 5 5 85 + + * - Name + - Description + * - ``comp_eq_size`` + - Control the size of I/O completion EQs. + * The default value is 1024, and the range is between 64 and 4096. + Info versions ============= diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index bdb271b604d9..79c15ee62cde 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -16,7 +16,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ - diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ + diag/fw_tracer.o diag/crdump.o devlink.o devlink_res.o diag/rsc_dump.o \ fw_reset.o qos.o lib/tout.o # diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 30bf4882779b..4192f23b1446 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -6,6 +6,13 @@ #include +enum mlx5_devlink_resource_id { + MLX5_DL_RES_COMP_EQ = 1, + + __MLX5_ID_RES_MAX, + MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1, +}; + enum mlx5_devlink_param_id { MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE, @@ -31,6 +38,10 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev); int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id, enum devlink_trap_action *action); +void mlx5_devlink_res_register(struct mlx5_core_dev *dev); +void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev); +size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id); + struct devlink *mlx5_devlink_alloc(struct device *dev); void mlx5_devlink_free(struct devlink *devlink); int mlx5_devlink_register(struct devlink *devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c new file mode 100644 index 000000000000..3beedfb8534a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ + +#include "devlink.h" +#include "mlx5_core.h" + +enum { + MLX5_EQ_MIN_SIZE = 64, + MLX5_EQ_MAX_SIZE = 4096, + MLX5_COMP_EQ_SIZE = 1024, +}; + +static int comp_eq_res_register(struct mlx5_core_dev *dev) +{ + struct devlink_resource_size_params comp_eq_size; + struct devlink *devlink = priv_to_devlink(dev); + + devlink_resource_size_params_init(&comp_eq_size, MLX5_EQ_MIN_SIZE, + MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY); + return devlink_resource_register(devlink, "io_eq_size", MLX5_COMP_EQ_SIZE, + MLX5_DL_RES_COMP_EQ, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &comp_eq_size); +} + +void mlx5_devlink_res_register(struct mlx5_core_dev *dev) +{ + int err; + + err = comp_eq_res_register(dev); + if (err) + mlx5_core_err(dev, "Failed to register resources, err = %d\n", err); +} + +void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev) +{ + devlink_resources_unregister(priv_to_devlink(dev), NULL); +} + +static const size_t default_vals[MLX5_ID_RES_MAX + 1] = { + [MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE, +}; + +size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id) +{ + struct devlink *devlink = priv_to_devlink(dev); + u64 size; + int err; + + err = devlink_resource_size_get(devlink, id, &size); + if (!err) + return size; + mlx5_core_err(dev, "Failed to get param. using default. err = %d, id = %u\n", + err, id); + return default_vals[id]; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 792e0d6aa861..4dda6e2a4cbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -19,6 +19,7 @@ #include "lib/clock.h" #include "diag/fw_tracer.h" #include "mlx5_irq.h" +#include "devlink.h" enum { MLX5_EQE_OWNER_INIT_VAL = 0x1, @@ -807,7 +808,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) INIT_LIST_HEAD(&table->comp_eqs_list); ncomp_eqs = table->num_comp_eqs; - nent = MLX5_COMP_EQ_SIZE; + nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_COMP_EQ); for (i = 0; i < ncomp_eqs; i++) { struct mlx5_eq_param param = {}; int vecidx = i; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f8446395163a..96fdbc0c87bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -922,6 +922,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) dev->hv_vhca = mlx5_hv_vhca_create(dev); dev->rsc_dump = mlx5_rsc_dump_create(dev); + mlx5_devlink_res_register(dev); + return 0; err_sf_table_cleanup: @@ -957,6 +959,7 @@ err_devcom: static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { + mlx5_devlink_res_unregister(dev); mlx5_rsc_dump_destroy(dev); mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f617dfbcd9fd..47c07f95bbe1 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -797,10 +797,6 @@ struct mlx5_db { int index; }; -enum { - MLX5_COMP_EQ_SIZE = 1024, -}; - enum { MLX5_PTYS_IB = 1 << 0, MLX5_PTYS_EN = 1 << 2, -- cgit v1.2.3 From a6cb08daa3b459e3dab1d98c67cb8c931f4d81a5 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Wed, 13 Oct 2021 09:57:54 +0300 Subject: net/mlx5: Let user configure event_eq_size param Event EQ is an EQ which received the notification of almost all the events generated by the NIC. Currently, each event EQ is taking 512KB of memory. This size is not needed in most use cases, and is critical with large scale. Hence, allow user to configure the size of the event EQ. For example to reduce event EQ size to 64, execute:: $ devlink resource set pci/0000:00:0b.0 path /event_eq_size/ size 64 $ devlink dev reload pci/0000:00:0b.0 Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- Documentation/networking/devlink/mlx5.rst | 4 ++++ drivers/net/ethernet/mellanox/mlx5/core/devlink.h | 1 + .../net/ethernet/mellanox/mlx5/core/devlink_res.c | 26 +++++++++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 2 +- include/linux/mlx5/eq.h | 1 - 5 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 4e6020570292..5b77863f9c88 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -57,6 +57,10 @@ Resources * - ``comp_eq_size`` - Control the size of I/O completion EQs. * The default value is 1024, and the range is between 64 and 4096. + * - ``event_eq_size`` + - Control the size of the asynchronous control events EQ. + * The default value is 4096, and the range is between 64 and 4096. + Info versions ============= diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 4192f23b1446..674415fd0b3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -8,6 +8,7 @@ enum mlx5_devlink_resource_id { MLX5_DL_RES_COMP_EQ = 1, + MLX5_DL_RES_ASYNC_EQ, __MLX5_ID_RES_MAX, MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c index 3beedfb8534a..549d23745942 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c @@ -7,6 +7,7 @@ enum { MLX5_EQ_MIN_SIZE = 64, MLX5_EQ_MAX_SIZE = 4096, + MLX5_NUM_ASYNC_EQE = 4096, MLX5_COMP_EQ_SIZE = 1024, }; @@ -23,13 +24,35 @@ static int comp_eq_res_register(struct mlx5_core_dev *dev) &comp_eq_size); } +static int async_eq_resource_register(struct mlx5_core_dev *dev) +{ + struct devlink_resource_size_params async_eq_size; + struct devlink *devlink = priv_to_devlink(dev); + + devlink_resource_size_params_init(&async_eq_size, MLX5_EQ_MIN_SIZE, + MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY); + return devlink_resource_register(devlink, "event_eq_size", + MLX5_NUM_ASYNC_EQE, MLX5_DL_RES_ASYNC_EQ, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &async_eq_size); +} + void mlx5_devlink_res_register(struct mlx5_core_dev *dev) { int err; err = comp_eq_res_register(dev); if (err) - mlx5_core_err(dev, "Failed to register resources, err = %d\n", err); + goto err_msg; + + err = async_eq_resource_register(dev); + if (err) + goto err; + return; +err: + devlink_resources_unregister(priv_to_devlink(dev), NULL); +err_msg: + mlx5_core_err(dev, "Failed to register resources, err = %d\n", err); } void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev) @@ -39,6 +62,7 @@ void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev) static const size_t default_vals[MLX5_ID_RES_MAX + 1] = { [MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE, + [MLX5_DL_RES_ASYNC_EQ] = MLX5_NUM_ASYNC_EQE, }; size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 4dda6e2a4cbc..31e69067284b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -647,7 +647,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) param = (struct mlx5_eq_param) { .irq_index = MLX5_IRQ_EQ_CTRL, - .nent = MLX5_NUM_ASYNC_EQE, + .nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_ASYNC_EQ), }; gather_async_events_mask(dev, param.mask); diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index ea3ff5a8ced3..11161e427608 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -5,7 +5,6 @@ #define MLX5_CORE_EQ_H #define MLX5_NUM_CMD_EQE (32) -#define MLX5_NUM_ASYNC_EQE (0x1000) #define MLX5_NUM_SPARE_EQE (0x80) struct mlx5_eq; -- cgit v1.2.3 From 554604061979d656bbbec50f101526349cd5aa5f Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Mon, 16 Aug 2021 08:41:08 +0300 Subject: net/mlx5: Let user configure max_macs param Currently, max_macs is taking 70Kbytes of memory per function. This size is not needed in all use cases, and is critical with large scale. Hence, allow user to configure the number of max_macs. For example, to reduce the number of max_macs to 1, execute:: $ devlink dev param set pci/0000:00:0b.0 name max_macs value 1 \ cmode driverinit $ devlink dev reload pci/0000:00:0b.0 Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- Documentation/networking/devlink/mlx5.rst | 4 ++ drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 69 +++++++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 18 ++++++ include/linux/mlx5/mlx5_ifc.h | 2 +- 4 files changed, 92 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 5b77863f9c88..d467e770906e 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -14,8 +14,12 @@ Parameters * - Name - Mode + - Validation * - ``enable_roce`` - driverinit + * - ``max_macs`` + - driverinit + - The range is between 1 and 2^31. Only power of 2 values are supported. The ``mlx5`` driver also implements the following driver-specific parameters. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index 1c98652b244a..fc78c745ead1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -752,6 +752,68 @@ static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink) mlx5_devlink_eth_param_unregister(devlink); } +static int mlx5_devlink_max_uc_list_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + /* At least one unicast mac is needed */ + if (val.vu32 == 0) { + NL_SET_ERR_MSG_MOD(extack, "max_macs value must be greater than 0"); + return -EINVAL; + } + /* Check if its power of 2 or not */ + if (!is_power_of_2(val.vu32)) { + NL_SET_ERR_MSG_MOD(extack, + "Only power of 2 values are supported for max_macs"); + return -EOPNOTSUPP; + } + + if (ilog2(val.vu32) > + MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list)) { + NL_SET_ERR_MSG_MOD(extack, "max_macs value is out of the supported range"); + return -EOPNOTSUPP; + } + + return 0; +} + +static const struct devlink_param max_uc_list_param = + DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, mlx5_devlink_max_uc_list_validate); + +static int mlx5_devlink_max_uc_list_param_register(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + union devlink_param_value value; + int err; + + if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported)) + return 0; + + err = devlink_param_register(devlink, &max_uc_list_param); + if (err) + return err; + + value.vu32 = 1 << MLX5_CAP_GEN(dev, log_max_current_uc_list); + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + value); + return 0; +} + +static void +mlx5_devlink_max_uc_list_param_unregister(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported)) + return; + + devlink_param_unregister(devlink, &max_uc_list_param); +} + #define MLX5_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ @@ -815,11 +877,17 @@ int mlx5_devlink_register(struct devlink *devlink) if (err) goto traps_reg_err; + err = mlx5_devlink_max_uc_list_param_register(devlink); + if (err) + goto uc_list_reg_err; + if (!mlx5_core_is_mp_slave(dev)) devlink_set_features(devlink, DEVLINK_F_RELOAD); return 0; +uc_list_reg_err: + mlx5_devlink_traps_unregister(devlink); traps_reg_err: mlx5_devlink_auxdev_params_unregister(devlink); auxdev_reg_err: @@ -830,6 +898,7 @@ auxdev_reg_err: void mlx5_devlink_unregister(struct devlink *devlink) { + mlx5_devlink_max_uc_list_param_unregister(devlink); mlx5_devlink_traps_unregister(devlink); mlx5_devlink_auxdev_params_unregister(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 96fdbc0c87bf..079ee9e8da10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -484,10 +484,23 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP); } +static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + &val); + return err ? 0 : val.vu32; +} + static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; + u32 max_uc_list; int err; err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL); @@ -561,6 +574,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) if (MLX5_CAP_GEN(dev, roce_rw_supported)) MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + max_uc_list = max_uc_list_get_devlink_param(dev); + if (max_uc_list) + MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list, + ilog2(max_uc_list)); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 746381eccccf..97465d00de9d 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1603,7 +1603,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ext_stride_num_range[0x1]; u8 roce_rw_supported[0x1]; - u8 reserved_at_3a2[0x1]; + u8 log_max_current_uc_list_wr_supported[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; -- cgit v1.2.3 From 95cadae320be46583078690ac89ffe63c95cc9d2 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Mon, 25 Oct 2021 17:05:28 -0400 Subject: fortify: strlen: Avoid shadowing previous locals The __compiletime_strlen() macro expansion will shadow p_size and p_len local variables. No callers currently use any of the shadowed names for their "p" variable, so there are no code generation problems. Add "__" prefixes to variable definitions __compiletime_strlen() to avoid new W=2 warnings: ./include/linux/fortify-string.h: In function 'strnlen': ./include/linux/fortify-string.h:17:9: warning: declaration of 'p_size' shadows a previous local [-Wshadow] 17 | size_t p_size = __builtin_object_size(p, 1); \ | ^~~~~~ ./include/linux/fortify-string.h:77:17: note: in expansion of macro '__compiletime_strlen' 77 | size_t p_len = __compiletime_strlen(p); | ^~~~~~~~~~~~~~~~~~~~ ./include/linux/fortify-string.h:76:9: note: shadowed declaration is here 76 | size_t p_size = __builtin_object_size(p, 1); | ^~~~~~ Signed-off-by: Qian Cai Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20211025210528.261643-1-quic_qiancai@quicinc.com --- include/linux/fortify-string.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index fdb0a74c9ca2..a6cd6815f249 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -10,18 +10,18 @@ void __read_overflow(void) __compiletime_error("detected read beyond size of obj void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)"); void __write_overflow(void) __compiletime_error("detected write beyond size of object (1st parameter)"); -#define __compiletime_strlen(p) \ -({ \ - unsigned char *__p = (unsigned char *)(p); \ - size_t ret = (size_t)-1; \ - size_t p_size = __builtin_object_size(p, 1); \ - if (p_size != (size_t)-1) { \ - size_t p_len = p_size - 1; \ - if (__builtin_constant_p(__p[p_len]) && \ - __p[p_len] == '\0') \ - ret = __builtin_strlen(__p); \ - } \ - ret; \ +#define __compiletime_strlen(p) \ +({ \ + unsigned char *__p = (unsigned char *)(p); \ + size_t __ret = (size_t)-1; \ + size_t __p_size = __builtin_object_size(p, 1); \ + if (__p_size != (size_t)-1) { \ + size_t __p_len = __p_size - 1; \ + if (__builtin_constant_p(__p[__p_len]) && \ + __p[__p_len] == '\0') \ + __ret = __builtin_strlen(__p); \ + } \ + __ret; \ }) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -- cgit v1.2.3 From ef57c1610dd8fba5031bf71e0db73356190de151 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 25 Oct 2021 09:48:17 -0700 Subject: ipv6: move inet6_sk(sk)->rx_dst_cookie to sk->sk_rx_dst_cookie Increase cache locality by moving rx_dst_coookie next to sk->sk_rx_dst This removes one or two cache line misses in IPv6 early demux (TCP/UDP) Signed-off-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 1 - include/net/sock.h | 2 ++ net/ipv6/tcp_ipv6.c | 6 +++--- net/ipv6/udp.c | 4 ++-- 4 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index ef4a69865737..c383630d3f06 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -282,7 +282,6 @@ struct ipv6_pinfo { __be32 rcv_flowinfo; __u32 dst_cookie; - __u32 rx_dst_cookie; struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; diff --git a/include/net/sock.h b/include/net/sock.h index 0bfb3f138bda..99c4194cb61a 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -260,6 +260,7 @@ struct bpf_local_storage; * @sk_wq: sock wait queue and async head * @sk_rx_dst: receive input route used by early demux * @sk_rx_dst_ifindex: ifindex for @sk_rx_dst + * @sk_rx_dst_cookie: cookie for @sk_rx_dst * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy @@ -432,6 +433,7 @@ struct sock { #endif struct dst_entry *sk_rx_dst; int sk_rx_dst_ifindex; + u32 sk_rx_dst_cookie; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 3e8669b6d636..50d9578e945b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -109,7 +109,7 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) sk->sk_rx_dst = dst; sk->sk_rx_dst_ifindex = skb->skb_iif; - tcp_inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); + sk->sk_rx_dst_cookie = rt6_get_cookie(rt); } } @@ -1511,7 +1511,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (dst) { if (sk->sk_rx_dst_ifindex != skb->skb_iif || INDIRECT_CALL_1(dst->ops->check, ip6_dst_check, - dst, np->rx_dst_cookie) == NULL) { + dst, sk->sk_rx_dst_cookie) == NULL) { dst_release(dst); sk->sk_rx_dst = NULL; } @@ -1872,7 +1872,7 @@ INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst); if (dst) - dst = dst_check(dst, tcp_inet6_sk(sk)->rx_dst_cookie); + dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst && sk->sk_rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8d785232b479..14a94cddcf0b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -884,7 +884,7 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) if (udp_sk_rx_dst_set(sk, dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); + sk->sk_rx_dst_cookie = rt6_get_cookie(rt); } } @@ -1073,7 +1073,7 @@ INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) dst = READ_ONCE(sk->sk_rx_dst); if (dst) - dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie); + dst = dst_check(dst, sk->sk_rx_dst_cookie); if (dst) { /* set noref for now. * any place which wants to hold dst has to call -- cgit v1.2.3 From 79ca6f74dae067681a779fd573c2eb59649989bc Mon Sep 17 00:00:00 2001 From: Hao Wu Date: Wed, 8 Sep 2021 02:26:06 -0700 Subject: tpm: fix Atmel TPM crash caused by too frequent queries The Atmel TPM 1.2 chips crash with error `tpm_try_transmit: send(): error -62` since kernel 4.14. It is observed from the kernel log after running `tpm_sealdata -z`. The error thrown from the command is as follows ``` $ tpm_sealdata -z Tspi_Key_LoadKey failed: 0x00001087 - layer=tddl, code=0087 (135), I/O error ``` The issue was reproduced with the following Atmel TPM chip: ``` $ tpm_version T0 TPM 1.2 Version Info: Chip Version: 1.2.66.1 Spec Level: 2 Errata Revision: 3 TPM Vendor ID: ATML TPM Version: 01010000 Manufacturer Info: 41544d4c ``` The root cause of the issue is due to the TPM calls to msleep() were replaced with usleep_range() [1], which reduces the actual timeout. Via experiments, it is observed that the original msleep(5) actually sleeps for 15ms. Because of a known timeout issue in Atmel TPM 1.2 chip, the shorter timeout than 15ms can cause the error described above. A few further changes in kernel 4.16 [2] and 4.18 [3, 4] further reduced the timeout to less than 1ms. With experiments, the problematic timeout in the latest kernel is the one for `wait_for_tpm_stat`. To fix it, the patch reverts the timeout of `wait_for_tpm_stat` to 15ms for all Atmel TPM 1.2 chips, but leave it untouched for Ateml TPM 2.0 chip, and chips from other vendors. As explained above, the chosen 15ms timeout is the actual timeout before this issue introduced, thus the old value is used here. Particularly, TPM_ATML_TIMEOUT_WAIT_STAT_MIN is set to 14700us, TPM_ATML_TIMEOUT_WAIT_STAT_MIN is set to 15000us according to the existing TPM_TIMEOUT_RANGE_US (300us). The fixed has been tested in the system with the affected Atmel chip with no issues observed after boot up. References: [1] 9f3fc7bcddcb tpm: replace msleep() with usleep_range() in TPM 1.2/2.0 generic drivers [2] cf151a9a44d5 tpm: reduce tpm polling delay in tpm_tis_core [3] 59f5a6b07f64 tpm: reduce poll sleep time in tpm_transmit() [4] 424eaf910c32 tpm: reduce polling time to usecs for even finer granularity Fixes: 9f3fc7bcddcb ("tpm: replace msleep() with usleep_range() in TPM 1.2/2.0 generic drivers") Link: https://patchwork.kernel.org/project/linux-integrity/patch/20200926223150.109645-1-hao.wu@rubrik.com/ Signed-off-by: Hao Wu Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm_tis_core.c | 26 ++++++++++++++++++-------- drivers/char/tpm/tpm_tis_core.h | 4 ++++ include/linux/tpm.h | 1 + 3 files changed, 23 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 69579efb247b..b2659a4c4016 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -48,6 +48,7 @@ static int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask, unsigned long timeout, wait_queue_head_t *queue, bool check_cancel) { + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); unsigned long stop; long rc; u8 status; @@ -80,8 +81,8 @@ again: } } else { do { - usleep_range(TPM_TIMEOUT_USECS_MIN, - TPM_TIMEOUT_USECS_MAX); + usleep_range(priv->timeout_min, + priv->timeout_max); status = chip->ops->status(chip); if ((status & mask) == mask) return 0; @@ -945,7 +946,22 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, chip->timeout_b = msecs_to_jiffies(TIS_TIMEOUT_B_MAX); chip->timeout_c = msecs_to_jiffies(TIS_TIMEOUT_C_MAX); chip->timeout_d = msecs_to_jiffies(TIS_TIMEOUT_D_MAX); + priv->timeout_min = TPM_TIMEOUT_USECS_MIN; + priv->timeout_max = TPM_TIMEOUT_USECS_MAX; priv->phy_ops = phy_ops; + + rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor); + if (rc < 0) + goto out_err; + + priv->manufacturer_id = vendor; + + if (priv->manufacturer_id == TPM_VID_ATML && + !(chip->flags & TPM_CHIP_FLAG_TPM2)) { + priv->timeout_min = TIS_TIMEOUT_MIN_ATML; + priv->timeout_max = TIS_TIMEOUT_MAX_ATML; + } + dev_set_drvdata(&chip->dev, priv); if (is_bsw()) { @@ -988,12 +1004,6 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, if (rc) goto out_err; - rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor); - if (rc < 0) - goto out_err; - - priv->manufacturer_id = vendor; - rc = tpm_tis_read8(priv, TPM_RID(0), &rid); if (rc < 0) goto out_err; diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index b2a3c6c72882..3be24f221e32 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -54,6 +54,8 @@ enum tis_defaults { TIS_MEM_LEN = 0x5000, TIS_SHORT_TIMEOUT = 750, /* ms */ TIS_LONG_TIMEOUT = 2000, /* 2 sec */ + TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */ + TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */ }; /* Some timeout values are needed before it is known whether the chip is @@ -98,6 +100,8 @@ struct tpm_tis_data { wait_queue_head_t read_queue; const struct tpm_tis_phy_ops *phy_ops; unsigned short rng_quality; + unsigned int timeout_min; /* usecs */ + unsigned int timeout_max; /* usecs */ }; struct tpm_tis_phy_ops { diff --git a/include/linux/tpm.h b/include/linux/tpm.h index aa11fe323c56..12d827734686 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -269,6 +269,7 @@ enum tpm2_cc_attrs { #define TPM_VID_INTEL 0x8086 #define TPM_VID_WINBOND 0x1050 #define TPM_VID_STM 0x104A +#define TPM_VID_ATML 0x1114 enum tpm_chip_flags { TPM_CHIP_FLAG_TPM2 = BIT(1), -- cgit v1.2.3 From 1bdda24c4af64cd2d65dec5192ab624c5fee7ca0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Oct 2021 15:55:05 -0700 Subject: signal: Add an optional check for altstack size New x86 FPU features will be very large, requiring ~10k of stack in signal handlers. These new features require a new approach called "dynamic features". The kernel currently tries to ensure that altstacks are reasonably sized. Right now, on x86, sys_sigaltstack() requires a size of >=2k. However, that 2k is a constant. Simply raising that 2k requirement to >10k for the new features would break existing apps which have a compiled-in size of 2k. Instead of universally enforcing a larger stack, prohibit a process from using dynamic features without properly-sized altstacks. This must be enforced in two places: * A dynamic feature can not be enabled without an large-enough altstack for each process thread. * Once a dynamic feature is enabled, any request to install a too-small altstack will be rejected The dynamic feature enabling code must examine each thread in a process to ensure that the altstacks are large enough. Add a new lock (sigaltstack_lock()) to ensure that threads can not race and change their altstack after being examined. Add the infrastructure in form of a config option and provide empty stubs for architectures which do not need dynamic altstack size checks. This implementation will be fleshed out for x86 in a future patch called x86/arch_prctl: Add controls for dynamic XSTATE components [dhansen: commit message. ] Signed-off-by: Thomas Gleixner Signed-off-by: Chang S. Bae Signed-off-by: Borislav Petkov Link: https://lkml.kernel.org/r/20211021225527.10184-2-chang.seok.bae@intel.com --- arch/Kconfig | 3 +++ include/linux/signal.h | 6 ++++++ kernel/signal.c | 35 +++++++++++++++++++++++++++++------ 3 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 8df1c7102643..af5cf3009b4f 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1288,6 +1288,9 @@ config ARCH_HAS_ELFCORE_COMPAT config ARCH_HAS_PARANOID_L1D_FLUSH bool +config DYNAMIC_SIGFRAME + bool + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/include/linux/signal.h b/include/linux/signal.h index 3f96a6374e4f..7d34105e20c6 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -464,6 +464,12 @@ int __save_altstack(stack_t __user *, unsigned long); unsafe_put_user(t->sas_ss_size, &__uss->ss_size, label); \ } while (0); +#ifdef CONFIG_DYNAMIC_SIGFRAME +bool sigaltstack_size_valid(size_t ss_size); +#else +static inline bool sigaltstack_size_valid(size_t size) { return true; } +#endif /* !CONFIG_DYNAMIC_SIGFRAME */ + #ifdef CONFIG_PROC_FS struct seq_file; extern void render_sigset_t(struct seq_file *, const char *, sigset_t *); diff --git a/kernel/signal.c b/kernel/signal.c index 952741f6d0f9..9278f5291ed6 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -4151,11 +4151,29 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) return 0; } +#ifdef CONFIG_DYNAMIC_SIGFRAME +static inline void sigaltstack_lock(void) + __acquires(¤t->sighand->siglock) +{ + spin_lock_irq(¤t->sighand->siglock); +} + +static inline void sigaltstack_unlock(void) + __releases(¤t->sighand->siglock) +{ + spin_unlock_irq(¤t->sighand->siglock); +} +#else +static inline void sigaltstack_lock(void) { } +static inline void sigaltstack_unlock(void) { } +#endif + static int do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, size_t min_ss_size) { struct task_struct *t = current; + int ret = 0; if (oss) { memset(oss, 0, sizeof(stack_t)); @@ -4179,19 +4197,24 @@ do_sigaltstack (const stack_t *ss, stack_t *oss, unsigned long sp, ss_mode != 0)) return -EINVAL; + sigaltstack_lock(); if (ss_mode == SS_DISABLE) { ss_size = 0; ss_sp = NULL; } else { if (unlikely(ss_size < min_ss_size)) - return -ENOMEM; + ret = -ENOMEM; + if (!sigaltstack_size_valid(ss_size)) + ret = -ENOMEM; } - - t->sas_ss_sp = (unsigned long) ss_sp; - t->sas_ss_size = ss_size; - t->sas_ss_flags = ss_flags; + if (!ret) { + t->sas_ss_sp = (unsigned long) ss_sp; + t->sas_ss_size = ss_size; + t->sas_ss_flags = ss_flags; + } + sigaltstack_unlock(); } - return 0; + return ret; } SYSCALL_DEFINE2(sigaltstack,const stack_t __user *,uss, stack_t __user *,uoss) -- cgit v1.2.3 From 0953fb263714e1c8c1c3d395036d9a14310081dd Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 20 Oct 2021 20:23:09 +0100 Subject: irq: remove handle_domain_{irq,nmi}() Now that entry code handles IRQ entry (including setting the IRQ regs) before calling irqchip code, irqchip code can safely call generic_handle_domain_irq(), and there's no functional reason for it to call handle_domain_irq(). Let's cement this split of responsibility and remove handle_domain_irq() entirely, updating irqchip drivers to call generic_handle_domain_irq(). For consistency, handle_domain_nmi() is similarly removed and replaced with a generic_handle_domain_nmi() function which also does not perform any entry logic. Previously handle_domain_{irq,nmi}() had a WARN_ON() which would fire when they were called in an inappropriate context. So that we can identify similar issues going forward, similar WARN_ON_ONCE() logic is added to the generic_handle_*() functions, and comments are updated for clarity and consistency. Signed-off-by: Mark Rutland Reviewed-by: Marc Zyngier Cc: Thomas Gleixner --- Documentation/core-api/irq/irq-domain.rst | 3 -- arch/arm/Kconfig | 1 - arch/arm/mach-imx/avic.c | 2 +- arch/arm/mach-imx/tzic.c | 2 +- arch/arm/mach-omap1/irq.c | 2 +- arch/arm/mach-s3c/irq-s3c24xx.c | 2 +- arch/arm64/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/riscv/Kconfig | 1 - drivers/irqchip/irq-apple-aic.c | 20 ++++----- drivers/irqchip/irq-armada-370-xp.c | 13 ++---- drivers/irqchip/irq-aspeed-vic.c | 2 +- drivers/irqchip/irq-atmel-aic.c | 2 +- drivers/irqchip/irq-atmel-aic5.c | 2 +- drivers/irqchip/irq-bcm2835.c | 2 +- drivers/irqchip/irq-bcm2836.c | 2 +- drivers/irqchip/irq-clps711x.c | 8 ++-- drivers/irqchip/irq-csky-apb-intc.c | 2 +- drivers/irqchip/irq-csky-mpintc.c | 4 +- drivers/irqchip/irq-davinci-aintc.c | 2 +- drivers/irqchip/irq-davinci-cp-intc.c | 2 +- drivers/irqchip/irq-digicolor.c | 2 +- drivers/irqchip/irq-dw-apb-ictl.c | 2 +- drivers/irqchip/irq-ftintc010.c | 2 +- drivers/irqchip/irq-gic-v3.c | 4 +- drivers/irqchip/irq-gic.c | 2 +- drivers/irqchip/irq-hip04.c | 2 +- drivers/irqchip/irq-ixp4xx.c | 4 +- drivers/irqchip/irq-lpc32xx.c | 2 +- drivers/irqchip/irq-mmp.c | 4 +- drivers/irqchip/irq-mxs.c | 2 +- drivers/irqchip/irq-nvic.c | 6 +-- drivers/irqchip/irq-omap-intc.c | 2 +- drivers/irqchip/irq-or1k-pic.c | 2 +- drivers/irqchip/irq-orion.c | 4 +- drivers/irqchip/irq-rda-intc.c | 2 +- drivers/irqchip/irq-riscv-intc.c | 2 +- drivers/irqchip/irq-sa11x0.c | 4 +- drivers/irqchip/irq-sun4i.c | 2 +- drivers/irqchip/irq-versatile-fpga.c | 2 +- drivers/irqchip/irq-vic.c | 2 +- drivers/irqchip/irq-vt8500.c | 2 +- drivers/irqchip/irq-wpcm450-aic.c | 2 +- drivers/irqchip/irq-zevio.c | 2 +- include/linux/irqdesc.h | 9 +--- kernel/irq/Kconfig | 7 ---- kernel/irq/irqdesc.c | 68 ++++++++----------------------- 48 files changed, 80 insertions(+), 141 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/irq/irq-domain.rst b/Documentation/core-api/irq/irq-domain.rst index 9c0e8758037a..d30b4d0a9769 100644 --- a/Documentation/core-api/irq/irq-domain.rst +++ b/Documentation/core-api/irq/irq-domain.rst @@ -67,9 +67,6 @@ variety of methods: deprecated - generic_handle_domain_irq() handles an interrupt described by a domain and a hwirq number -- handle_domain_irq() does the same thing for root interrupt - controllers and deals with the set_irq_reg()/irq_enter() sequences - that most architecture requires Note that irq domain lookups must happen in contexts that are compatible with a RCU read-side critical section. diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index fc196421b2ce..3361a6c29ee9 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -64,7 +64,6 @@ config ARM select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD - select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c index 21bce4049cec..cf6546ddc7a3 100644 --- a/arch/arm/mach-imx/avic.c +++ b/arch/arm/mach-imx/avic.c @@ -154,7 +154,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs) if (nivector == 0xffff) break; - handle_domain_irq(domain, nivector, regs); + generic_handle_domain_irq(domain, nivector); } while (1); } diff --git a/arch/arm/mach-imx/tzic.c b/arch/arm/mach-imx/tzic.c index 479a01bdac56..8b3d98d288d9 100644 --- a/arch/arm/mach-imx/tzic.c +++ b/arch/arm/mach-imx/tzic.c @@ -134,7 +134,7 @@ static void __exception_irq_entry tzic_handle_irq(struct pt_regs *regs) while (stat) { handled = 1; irqofs = fls(stat) - 1; - handle_domain_irq(domain, irqofs + i * 32, regs); + generic_handle_domain_irq(domain, irqofs + i * 32); stat &= ~(1 << irqofs); } } diff --git a/arch/arm/mach-omap1/irq.c b/arch/arm/mach-omap1/irq.c index b11edc8a46f0..ee6a93083154 100644 --- a/arch/arm/mach-omap1/irq.c +++ b/arch/arm/mach-omap1/irq.c @@ -165,7 +165,7 @@ asmlinkage void __exception_irq_entry omap1_handle_irq(struct pt_regs *regs) } irq: if (irqnr) - handle_domain_irq(domain, irqnr, regs); + generic_handle_domain_irq(domain, irqnr); else break; } while (irqnr); diff --git a/arch/arm/mach-s3c/irq-s3c24xx.c b/arch/arm/mach-s3c/irq-s3c24xx.c index 3edc5f614eef..45dfd546e6fa 100644 --- a/arch/arm/mach-s3c/irq-s3c24xx.c +++ b/arch/arm/mach-s3c/irq-s3c24xx.c @@ -354,7 +354,7 @@ static inline int s3c24xx_handle_intc(struct s3c_irq_intc *intc, if (!(pnd & (1 << offset))) offset = __ffs(pnd); - handle_domain_irq(intc->domain, intc_offset + offset, regs); + generic_handle_domain_irq(intc->domain, intc_offset + offset); return true; } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5c7ae4c3954b..e6593a03ea27 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -133,7 +133,6 @@ config ARM64 select GENERIC_TIME_VSYSCALL select GENERIC_GETTIMEOFDAY select GENERIC_VDSO_TIME_NS - select HANDLE_DOMAIN_IRQ select HARDIRQS_SW_RESEND select HAVE_MOVE_PMD select HAVE_MOVE_PUD diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 9d4d898df76b..e0bd71b9e23f 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -17,7 +17,6 @@ config CSKY select CSKY_APB_INTC select DMA_DIRECT_REMAP select IRQ_DOMAIN - select HANDLE_DOMAIN_IRQ select DW_APB_TIMER_OF select GENERIC_IOREMAP select GENERIC_LIB_ASHLDI3 diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index e804026b4797..c2491b295d60 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -13,7 +13,6 @@ config OPENRISC select OF select OF_EARLY_FLATTREE select IRQ_DOMAIN - select HANDLE_DOMAIN_IRQ select GPIOLIB select HAVE_ARCH_TRACEHOOK select SPARSE_IRQ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 301a54233c7e..353e28f5f849 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -62,7 +62,6 @@ config RISCV select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL if MMU && 64BIT - select HANDLE_DOMAIN_IRQ select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL select HAVE_ARCH_JUMP_LABEL_RELATIVE if !XIP_KERNEL diff --git a/drivers/irqchip/irq-apple-aic.c b/drivers/irqchip/irq-apple-aic.c index 6fc145aacaf0..3759dc36cc8f 100644 --- a/drivers/irqchip/irq-apple-aic.c +++ b/drivers/irqchip/irq-apple-aic.c @@ -245,7 +245,7 @@ static void __exception_irq_entry aic_handle_irq(struct pt_regs *regs) irq = FIELD_GET(AIC_EVENT_NUM, event); if (type == AIC_EVENT_TYPE_HW) - handle_domain_irq(aic_irqc->hw_domain, irq, regs); + generic_handle_domain_irq(aic_irqc->hw_domain, irq); else if (type == AIC_EVENT_TYPE_IPI && irq == 1) aic_handle_ipi(regs); else if (event != 0) @@ -392,25 +392,25 @@ static void __exception_irq_entry aic_handle_fiq(struct pt_regs *regs) } if (TIMER_FIRING(read_sysreg(cntp_ctl_el0))) - handle_domain_irq(aic_irqc->hw_domain, - aic_irqc->nr_hw + AIC_TMR_EL0_PHYS, regs); + generic_handle_domain_irq(aic_irqc->hw_domain, + aic_irqc->nr_hw + AIC_TMR_EL0_PHYS); if (TIMER_FIRING(read_sysreg(cntv_ctl_el0))) - handle_domain_irq(aic_irqc->hw_domain, - aic_irqc->nr_hw + AIC_TMR_EL0_VIRT, regs); + generic_handle_domain_irq(aic_irqc->hw_domain, + aic_irqc->nr_hw + AIC_TMR_EL0_VIRT); if (is_kernel_in_hyp_mode()) { uint64_t enabled = read_sysreg_s(SYS_IMP_APL_VM_TMR_FIQ_ENA_EL2); if ((enabled & VM_TMR_FIQ_ENABLE_P) && TIMER_FIRING(read_sysreg_s(SYS_CNTP_CTL_EL02))) - handle_domain_irq(aic_irqc->hw_domain, - aic_irqc->nr_hw + AIC_TMR_EL02_PHYS, regs); + generic_handle_domain_irq(aic_irqc->hw_domain, + aic_irqc->nr_hw + AIC_TMR_EL02_PHYS); if ((enabled & VM_TMR_FIQ_ENABLE_V) && TIMER_FIRING(read_sysreg_s(SYS_CNTV_CTL_EL02))) - handle_domain_irq(aic_irqc->hw_domain, - aic_irqc->nr_hw + AIC_TMR_EL02_VIRT, regs); + generic_handle_domain_irq(aic_irqc->hw_domain, + aic_irqc->nr_hw + AIC_TMR_EL02_VIRT); } if ((read_sysreg_s(SYS_IMP_APL_PMCR0_EL1) & (PMCR0_IMODE | PMCR0_IACT)) == @@ -674,7 +674,7 @@ static void aic_handle_ipi(struct pt_regs *regs) firing = atomic_fetch_andnot(enabled, this_cpu_ptr(&aic_vipi_flag)) & enabled; for_each_set_bit(i, &firing, AIC_NR_SWIPI) - handle_domain_irq(aic_irqc->ipi_domain, i, regs); + generic_handle_domain_irq(aic_irqc->ipi_domain, i); /* * No ordering needed here; at worst this just changes the timing of diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 53e0fb0562c1..80906bfec845 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -589,12 +589,7 @@ static void armada_370_xp_handle_msi_irq(struct pt_regs *regs, bool is_chained) irq = msinr - PCI_MSI_DOORBELL_START; - if (is_chained) - generic_handle_domain_irq(armada_370_xp_msi_inner_domain, - irq); - else - handle_domain_irq(armada_370_xp_msi_inner_domain, - irq, regs); + generic_handle_domain_irq(armada_370_xp_msi_inner_domain, irq); } } #else @@ -646,8 +641,8 @@ armada_370_xp_handle_irq(struct pt_regs *regs) break; if (irqnr > 1) { - handle_domain_irq(armada_370_xp_mpic_domain, - irqnr, regs); + generic_handle_domain_irq(armada_370_xp_mpic_domain, + irqnr); continue; } @@ -666,7 +661,7 @@ armada_370_xp_handle_irq(struct pt_regs *regs) & IPI_DOORBELL_MASK; for_each_set_bit(ipi, &ipimask, IPI_DOORBELL_END) - handle_domain_irq(ipi_domain, ipi, regs); + generic_handle_domain_irq(ipi_domain, ipi); } #endif diff --git a/drivers/irqchip/irq-aspeed-vic.c b/drivers/irqchip/irq-aspeed-vic.c index 58717cd44f99..62ccf2c0c414 100644 --- a/drivers/irqchip/irq-aspeed-vic.c +++ b/drivers/irqchip/irq-aspeed-vic.c @@ -100,7 +100,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs) if (stat == 0) break; irq += ffs(stat) - 1; - handle_domain_irq(vic->dom, irq, regs); + generic_handle_domain_irq(vic->dom, irq); } } diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c index 2c999dc310c1..4631f6847953 100644 --- a/drivers/irqchip/irq-atmel-aic.c +++ b/drivers/irqchip/irq-atmel-aic.c @@ -71,7 +71,7 @@ aic_handle(struct pt_regs *regs) if (!irqstat) irq_reg_writel(gc, 0, AT91_AIC_EOICR); else - handle_domain_irq(aic_domain, irqnr, regs); + generic_handle_domain_irq(aic_domain, irqnr); } static int aic_retrigger(struct irq_data *d) diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c index fb4ad2aaa727..145535bd7560 100644 --- a/drivers/irqchip/irq-atmel-aic5.c +++ b/drivers/irqchip/irq-atmel-aic5.c @@ -80,7 +80,7 @@ aic5_handle(struct pt_regs *regs) if (!irqstat) irq_reg_writel(bgc, 0, AT91_AIC5_EOICR); else - handle_domain_irq(aic5_domain, irqnr, regs); + generic_handle_domain_irq(aic5_domain, irqnr); } static void aic5_mask(struct irq_data *d) diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c index adc1556ed332..e94e2882286c 100644 --- a/drivers/irqchip/irq-bcm2835.c +++ b/drivers/irqchip/irq-bcm2835.c @@ -246,7 +246,7 @@ static void __exception_irq_entry bcm2835_handle_irq( u32 hwirq; while ((hwirq = get_next_armctrl_hwirq()) != ~0) - handle_domain_irq(intc.domain, hwirq, regs); + generic_handle_domain_irq(intc.domain, hwirq); } static void bcm2836_chained_handle_irq(struct irq_desc *desc) diff --git a/drivers/irqchip/irq-bcm2836.c b/drivers/irqchip/irq-bcm2836.c index 501facdb4570..51491c3c6fdd 100644 --- a/drivers/irqchip/irq-bcm2836.c +++ b/drivers/irqchip/irq-bcm2836.c @@ -143,7 +143,7 @@ __exception_irq_entry bcm2836_arm_irqchip_handle_irq(struct pt_regs *regs) if (stat) { u32 hwirq = ffs(stat) - 1; - handle_domain_irq(intc.domain, hwirq, regs); + generic_handle_domain_irq(intc.domain, hwirq); } } diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c index d0da29aeedc8..77ebe7e47e0e 100644 --- a/drivers/irqchip/irq-clps711x.c +++ b/drivers/irqchip/irq-clps711x.c @@ -77,14 +77,14 @@ static asmlinkage void __exception_irq_entry clps711x_irqh(struct pt_regs *regs) irqstat = readw_relaxed(clps711x_intc->intmr[0]) & readw_relaxed(clps711x_intc->intsr[0]); if (irqstat) - handle_domain_irq(clps711x_intc->domain, - fls(irqstat) - 1, regs); + generic_handle_domain_irq(clps711x_intc->domain, + fls(irqstat) - 1); irqstat = readw_relaxed(clps711x_intc->intmr[1]) & readw_relaxed(clps711x_intc->intsr[1]); if (irqstat) - handle_domain_irq(clps711x_intc->domain, - fls(irqstat) - 1 + 16, regs); + generic_handle_domain_irq(clps711x_intc->domain, + fls(irqstat) - 1 + 16); } while (irqstat); } diff --git a/drivers/irqchip/irq-csky-apb-intc.c b/drivers/irqchip/irq-csky-apb-intc.c index ab91afa86755..d36f536506ba 100644 --- a/drivers/irqchip/irq-csky-apb-intc.c +++ b/drivers/irqchip/irq-csky-apb-intc.c @@ -138,7 +138,7 @@ static inline bool handle_irq_perbit(struct pt_regs *regs, u32 hwirq, if (hwirq == 0) return 0; - handle_domain_irq(root_domain, irq_base + __fls(hwirq), regs); + generic_handle_domain_irq(root_domain, irq_base + __fls(hwirq)); return 1; } diff --git a/drivers/irqchip/irq-csky-mpintc.c b/drivers/irqchip/irq-csky-mpintc.c index a1534edef7fa..cb403c960ac0 100644 --- a/drivers/irqchip/irq-csky-mpintc.c +++ b/drivers/irqchip/irq-csky-mpintc.c @@ -74,8 +74,8 @@ static void csky_mpintc_handler(struct pt_regs *regs) { void __iomem *reg_base = this_cpu_read(intcl_reg); - handle_domain_irq(root_domain, - readl_relaxed(reg_base + INTCL_RDYIR), regs); + generic_handle_domain_irq(root_domain, + readl_relaxed(reg_base + INTCL_RDYIR)); } static void csky_mpintc_enable(struct irq_data *d) diff --git a/drivers/irqchip/irq-davinci-aintc.c b/drivers/irqchip/irq-davinci-aintc.c index 810ccc4fe476..123eb7bfc117 100644 --- a/drivers/irqchip/irq-davinci-aintc.c +++ b/drivers/irqchip/irq-davinci-aintc.c @@ -73,7 +73,7 @@ davinci_aintc_handle_irq(struct pt_regs *regs) irqnr >>= 2; irqnr -= 1; - handle_domain_irq(davinci_aintc_irq_domain, irqnr, regs); + generic_handle_domain_irq(davinci_aintc_irq_domain, irqnr); } /* ARM Interrupt Controller Initialization */ diff --git a/drivers/irqchip/irq-davinci-cp-intc.c b/drivers/irqchip/irq-davinci-cp-intc.c index 276da2772e7f..7482c8ed34b2 100644 --- a/drivers/irqchip/irq-davinci-cp-intc.c +++ b/drivers/irqchip/irq-davinci-cp-intc.c @@ -135,7 +135,7 @@ davinci_cp_intc_handle_irq(struct pt_regs *regs) return; } - handle_domain_irq(davinci_cp_intc_irq_domain, irqnr, regs); + generic_handle_domain_irq(davinci_cp_intc_irq_domain, irqnr); } static int davinci_cp_intc_host_map(struct irq_domain *h, unsigned int virq, diff --git a/drivers/irqchip/irq-digicolor.c b/drivers/irqchip/irq-digicolor.c index fc38d2da11b9..3b0d78aac13b 100644 --- a/drivers/irqchip/irq-digicolor.c +++ b/drivers/irqchip/irq-digicolor.c @@ -50,7 +50,7 @@ static void __exception_irq_entry digicolor_handle_irq(struct pt_regs *regs) return; } - handle_domain_irq(digicolor_irq_domain, hwirq, regs); + generic_handle_domain_irq(digicolor_irq_domain, hwirq); } while (1); } diff --git a/drivers/irqchip/irq-dw-apb-ictl.c b/drivers/irqchip/irq-dw-apb-ictl.c index a67266e44491..d5c1c750c8d2 100644 --- a/drivers/irqchip/irq-dw-apb-ictl.c +++ b/drivers/irqchip/irq-dw-apb-ictl.c @@ -42,7 +42,7 @@ static void __irq_entry dw_apb_ictl_handle_irq(struct pt_regs *regs) while (stat) { u32 hwirq = ffs(stat) - 1; - handle_domain_irq(d, hwirq, regs); + generic_handle_domain_irq(d, hwirq); stat &= ~BIT(hwirq); } } diff --git a/drivers/irqchip/irq-ftintc010.c b/drivers/irqchip/irq-ftintc010.c index 0bf98425dca5..5cc268880f8e 100644 --- a/drivers/irqchip/irq-ftintc010.c +++ b/drivers/irqchip/irq-ftintc010.c @@ -134,7 +134,7 @@ asmlinkage void __exception_irq_entry ft010_irqchip_handle_irq(struct pt_regs *r while ((status = readl(FT010_IRQ_STATUS(f->base)))) { irq = ffs(status) - 1; - handle_domain_irq(f->domain, irq, regs); + generic_handle_domain_irq(f->domain, irq); } } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index fd4e9a37fea6..daec3309b014 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -660,7 +660,7 @@ static inline void gic_handle_nmi(u32 irqnr, struct pt_regs *regs) * PSR.I will be restored when we ERET to the * interrupted context. */ - err = handle_domain_nmi(gic_data.domain, irqnr, regs); + err = generic_handle_domain_nmi(gic_data.domain, irqnr); if (err) gic_deactivate_unhandled(irqnr); @@ -728,7 +728,7 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs else isb(); - if (handle_domain_irq(gic_data.domain, irqnr, regs)) { + if (generic_handle_domain_irq(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected interrupt received!\n"); gic_deactivate_unhandled(irqnr); } diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 5f22c9d65e57..b8bb46c65a97 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -369,7 +369,7 @@ static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) this_cpu_write(sgi_intid, irqstat); } - handle_domain_irq(gic->domain, irqnr, regs); + generic_handle_domain_irq(gic->domain, irqnr); } while (1); } diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c index 058ebaebe2c4..46161f6ff289 100644 --- a/drivers/irqchip/irq-hip04.c +++ b/drivers/irqchip/irq-hip04.c @@ -206,7 +206,7 @@ static void __exception_irq_entry hip04_handle_irq(struct pt_regs *regs) irqnr = irqstat & GICC_IAR_INT_ID_MASK; if (irqnr <= HIP04_MAX_IRQS) - handle_domain_irq(hip04_data.domain, irqnr, regs); + generic_handle_domain_irq(hip04_data.domain, irqnr); } while (irqnr > HIP04_MAX_IRQS); } diff --git a/drivers/irqchip/irq-ixp4xx.c b/drivers/irqchip/irq-ixp4xx.c index 37e0749215c7..fb68f8c59fbb 100644 --- a/drivers/irqchip/irq-ixp4xx.c +++ b/drivers/irqchip/irq-ixp4xx.c @@ -114,7 +114,7 @@ asmlinkage void __exception_irq_entry ixp4xx_handle_irq(struct pt_regs *regs) status = __raw_readl(ixi->irqbase + IXP4XX_ICIP); for_each_set_bit(i, &status, 32) - handle_domain_irq(ixi->domain, i, regs); + generic_handle_domain_irq(ixi->domain, i); /* * IXP465/IXP435 has an upper IRQ status register @@ -122,7 +122,7 @@ asmlinkage void __exception_irq_entry ixp4xx_handle_irq(struct pt_regs *regs) if (ixi->is_356) { status = __raw_readl(ixi->irqbase + IXP4XX_ICIP2); for_each_set_bit(i, &status, 32) - handle_domain_irq(ixi->domain, i + 32, regs); + generic_handle_domain_irq(ixi->domain, i + 32); } } diff --git a/drivers/irqchip/irq-lpc32xx.c b/drivers/irqchip/irq-lpc32xx.c index 5e6f6e25f2ae..a29357f39450 100644 --- a/drivers/irqchip/irq-lpc32xx.c +++ b/drivers/irqchip/irq-lpc32xx.c @@ -126,7 +126,7 @@ static void __exception_irq_entry lpc32xx_handle_irq(struct pt_regs *regs) while (hwirq) { irq = __ffs(hwirq); hwirq &= ~BIT(irq); - handle_domain_irq(lpc32xx_mic_irqc->domain, irq, regs); + generic_handle_domain_irq(lpc32xx_mic_irqc->domain, irq); } } diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 4a74ac7b7c42..83455ca72439 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -230,7 +230,7 @@ static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs) if (!(hwirq & SEL_INT_PENDING)) return; hwirq &= SEL_INT_NUM_MASK; - handle_domain_irq(icu_data[0].domain, hwirq, regs); + generic_handle_domain_irq(icu_data[0].domain, hwirq); } static void __exception_irq_entry mmp2_handle_irq(struct pt_regs *regs) @@ -241,7 +241,7 @@ static void __exception_irq_entry mmp2_handle_irq(struct pt_regs *regs) if (!(hwirq & SEL_INT_PENDING)) return; hwirq &= SEL_INT_NUM_MASK; - handle_domain_irq(icu_data[0].domain, hwirq, regs); + generic_handle_domain_irq(icu_data[0].domain, hwirq); } /* MMP (ARMv5) */ diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index d1f5740cd575..55cb6b5a686e 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -136,7 +136,7 @@ asmlinkage void __exception_irq_entry icoll_handle_irq(struct pt_regs *regs) irqnr = __raw_readl(icoll_priv.stat); __raw_writel(irqnr, icoll_priv.vector); - handle_domain_irq(icoll_domain, irqnr, regs); + generic_handle_domain_irq(icoll_domain, irqnr); } static int icoll_irq_domain_map(struct irq_domain *d, unsigned int virq, diff --git a/drivers/irqchip/irq-nvic.c b/drivers/irqchip/irq-nvic.c index b2bd96253d40..63bac3f78863 100644 --- a/drivers/irqchip/irq-nvic.c +++ b/drivers/irqchip/irq-nvic.c @@ -37,9 +37,9 @@ static struct irq_domain *nvic_irq_domain; -static void __nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs) +static void __nvic_handle_irq(irq_hw_number_t hwirq) { - handle_domain_irq(nvic_irq_domain, hwirq, regs); + generic_handle_domain_irq(nvic_irq_domain, hwirq); } /* @@ -53,7 +53,7 @@ nvic_handle_irq(irq_hw_number_t hwirq, struct pt_regs *regs) irq_enter(); old_regs = set_irq_regs(regs); - __nvic_handle_irq(hwirq, regs); + __nvic_handle_irq(hwirq); set_irq_regs(old_regs); irq_exit(); } diff --git a/drivers/irqchip/irq-omap-intc.c b/drivers/irqchip/irq-omap-intc.c index d360a6eddd6d..dc82162ba763 100644 --- a/drivers/irqchip/irq-omap-intc.c +++ b/drivers/irqchip/irq-omap-intc.c @@ -357,7 +357,7 @@ omap_intc_handle_irq(struct pt_regs *regs) } irqnr &= ACTIVEIRQ_MASK; - handle_domain_irq(domain, irqnr, regs); + generic_handle_domain_irq(domain, irqnr); } static int __init intc_of_init(struct device_node *node, diff --git a/drivers/irqchip/irq-or1k-pic.c b/drivers/irqchip/irq-or1k-pic.c index 03d2366118dd..49b47e787644 100644 --- a/drivers/irqchip/irq-or1k-pic.c +++ b/drivers/irqchip/irq-or1k-pic.c @@ -116,7 +116,7 @@ static void or1k_pic_handle_irq(struct pt_regs *regs) int irq = -1; while ((irq = pic_get_irq(irq + 1)) != NO_IRQ) - handle_domain_irq(root_domain, irq, regs); + generic_handle_domain_irq(root_domain, irq); } static int or1k_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c index b6868f7b805a..17c2c7a07f10 100644 --- a/drivers/irqchip/irq-orion.c +++ b/drivers/irqchip/irq-orion.c @@ -42,8 +42,8 @@ __exception_irq_entry orion_handle_irq(struct pt_regs *regs) gc->mask_cache; while (stat) { u32 hwirq = __fls(stat); - handle_domain_irq(orion_irq_domain, - gc->irq_base + hwirq, regs); + generic_handle_domain_irq(orion_irq_domain, + gc->irq_base + hwirq); stat &= ~(1 << hwirq); } } diff --git a/drivers/irqchip/irq-rda-intc.c b/drivers/irqchip/irq-rda-intc.c index 960168303b73..9f0144a73777 100644 --- a/drivers/irqchip/irq-rda-intc.c +++ b/drivers/irqchip/irq-rda-intc.c @@ -53,7 +53,7 @@ static void __exception_irq_entry rda_handle_irq(struct pt_regs *regs) while (stat) { hwirq = __fls(stat); - handle_domain_irq(rda_irq_domain, hwirq, regs); + generic_handle_domain_irq(rda_irq_domain, hwirq); stat &= ~BIT(hwirq); } } diff --git a/drivers/irqchip/irq-riscv-intc.c b/drivers/irqchip/irq-riscv-intc.c index 8017f6d32d52..b65bd8878d4f 100644 --- a/drivers/irqchip/irq-riscv-intc.c +++ b/drivers/irqchip/irq-riscv-intc.c @@ -37,7 +37,7 @@ static asmlinkage void riscv_intc_irq(struct pt_regs *regs) break; #endif default: - handle_domain_irq(intc_domain, cause, regs); + generic_handle_domain_irq(intc_domain, cause); break; } } diff --git a/drivers/irqchip/irq-sa11x0.c b/drivers/irqchip/irq-sa11x0.c index dbccc7dafbf8..31c202a1ae62 100644 --- a/drivers/irqchip/irq-sa11x0.c +++ b/drivers/irqchip/irq-sa11x0.c @@ -140,8 +140,8 @@ sa1100_handle_irq(struct pt_regs *regs) if (mask == 0) break; - handle_domain_irq(sa1100_normal_irqdomain, - ffs(mask) - 1, regs); + generic_handle_domain_irq(sa1100_normal_irqdomain, + ffs(mask) - 1); } while (1); } diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c index 8a315d6a3399..dd506ebfdacb 100644 --- a/drivers/irqchip/irq-sun4i.c +++ b/drivers/irqchip/irq-sun4i.c @@ -195,7 +195,7 @@ static void __exception_irq_entry sun4i_handle_irq(struct pt_regs *regs) return; do { - handle_domain_irq(irq_ic_data->irq_domain, hwirq, regs); + generic_handle_domain_irq(irq_ic_data->irq_domain, hwirq); hwirq = readl(irq_ic_data->irq_base + SUN4I_IRQ_VECTOR_REG) >> 2; } while (hwirq != 0); diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c index 75be350cf82f..f2757b6aecc8 100644 --- a/drivers/irqchip/irq-versatile-fpga.c +++ b/drivers/irqchip/irq-versatile-fpga.c @@ -105,7 +105,7 @@ static int handle_one_fpga(struct fpga_irq_data *f, struct pt_regs *regs) while ((status = readl(f->base + IRQ_STATUS))) { irq = ffs(status) - 1; - handle_domain_irq(f->domain, irq, regs); + generic_handle_domain_irq(f->domain, irq); handled = 1; } diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c index 1e1f2d115257..9e3d5561e04e 100644 --- a/drivers/irqchip/irq-vic.c +++ b/drivers/irqchip/irq-vic.c @@ -208,7 +208,7 @@ static int handle_one_vic(struct vic_device *vic, struct pt_regs *regs) while ((stat = readl_relaxed(vic->base + VIC_IRQ_STATUS))) { irq = ffs(stat) - 1; - handle_domain_irq(vic->domain, irq, regs); + generic_handle_domain_irq(vic->domain, irq); handled = 1; } diff --git a/drivers/irqchip/irq-vt8500.c b/drivers/irqchip/irq-vt8500.c index 5bce936af5d9..e17dd3a8c2d5 100644 --- a/drivers/irqchip/irq-vt8500.c +++ b/drivers/irqchip/irq-vt8500.c @@ -183,7 +183,7 @@ static void __exception_irq_entry vt8500_handle_irq(struct pt_regs *regs) continue; } - handle_domain_irq(intc[i].domain, irqnr, regs); + generic_handle_domain_irq(intc[i].domain, irqnr); } } diff --git a/drivers/irqchip/irq-wpcm450-aic.c b/drivers/irqchip/irq-wpcm450-aic.c index f3ac392d5bc8..0dcbeb1a05a1 100644 --- a/drivers/irqchip/irq-wpcm450-aic.c +++ b/drivers/irqchip/irq-wpcm450-aic.c @@ -69,7 +69,7 @@ static void __exception_irq_entry wpcm450_aic_handle_irq(struct pt_regs *regs) /* Read IPER to signal that nIRQ can be de-asserted */ hwirq = readl(aic->regs + AIC_IPER) / 4; - handle_domain_irq(aic->domain, hwirq, regs); + generic_handle_domain_irq(aic->domain, hwirq); } static void wpcm450_aic_eoi(struct irq_data *d) diff --git a/drivers/irqchip/irq-zevio.c b/drivers/irqchip/irq-zevio.c index 84163f1ebfcf..7a72620fc478 100644 --- a/drivers/irqchip/irq-zevio.c +++ b/drivers/irqchip/irq-zevio.c @@ -50,7 +50,7 @@ static void __exception_irq_entry zevio_handle_irq(struct pt_regs *regs) while (readl(zevio_irq_io + IO_STATUS)) { irqnr = readl(zevio_irq_io + IO_CURRENT); - handle_domain_irq(zevio_irq_domain, irqnr, regs); + generic_handle_domain_irq(zevio_irq_domain, irqnr); } } diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index 59aea39785bf..93d270ca0c56 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -168,14 +168,7 @@ int generic_handle_irq(unsigned int irq); * conversion failed. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq); - -#ifdef CONFIG_HANDLE_DOMAIN_IRQ -int handle_domain_irq(struct irq_domain *domain, - unsigned int hwirq, struct pt_regs *regs); - -int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, - struct pt_regs *regs); -#endif +int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq); #endif /* Test to see if a driver has successfully requested an irq */ diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 897dfc552bb0..1b41078222f3 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -97,13 +97,6 @@ config GENERIC_MSI_IRQ_DOMAIN config IRQ_MSI_IOMMU bool -config HANDLE_DOMAIN_IRQ - bool - -# Legacy behaviour; architectures should call irq_{enter,exit}() themselves -config HANDLE_DOMAIN_IRQ_IRQENTRY - bool - config IRQ_TIMINGS bool diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 7041698a7bff..2267e6527db3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -651,7 +651,11 @@ int handle_irq_desc(struct irq_desc *desc) * generic_handle_irq - Invoke the handler for a particular irq * @irq: The irq number to handle * - */ + * Returns: 0 on success, or -EINVAL if conversion has failed + * + * This function must be called from an IRQ context with irq regs + * initialized. + */ int generic_handle_irq(unsigned int irq) { return handle_irq_desc(irq_to_desc(irq)); @@ -661,77 +665,39 @@ EXPORT_SYMBOL_GPL(generic_handle_irq); #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging - * to a domain, usually for a non-root interrupt - * controller + * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * + * This function must be called from an IRQ context with irq regs + * initialized. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { + WARN_ON_ONCE(!in_irq()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); -#ifdef CONFIG_HANDLE_DOMAIN_IRQ /** - * handle_domain_irq - Invoke the handler for a HW irq belonging to a domain, - * usually for a root interrupt controller + * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging + * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one - * @regs: Register file coming from the low-level handling code - * - * This function must be called from an IRQ context. * * Returns: 0 on success, or -EINVAL if conversion has failed - */ -int handle_domain_irq(struct irq_domain *domain, - unsigned int hwirq, struct pt_regs *regs) -{ - struct pt_regs *old_regs = set_irq_regs(regs); - int ret; - - /* - * IRQ context needs to be setup earlier. - */ - WARN_ON(!in_irq()); - - ret = generic_handle_domain_irq(domain, hwirq); - - set_irq_regs(old_regs); - return ret; -} - -/** - * handle_domain_nmi - Invoke the handler for a HW irq belonging to a domain - * @domain: The domain where to perform the lookup - * @hwirq: The HW irq number to convert to a logical one - * @regs: Register file coming from the low-level handling code - * - * This function must be called from an NMI context. * - * Returns: 0 on success, or -EINVAL if conversion has failed - */ -int handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq, - struct pt_regs *regs) + * This function must be called from an NMI context with irq regs + * initialized. + **/ +int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq) { - struct pt_regs *old_regs = set_irq_regs(regs); - int ret; - - /* - * NMI context needs to be setup earlier in order to deal with tracing. - */ - WARN_ON(!in_nmi()); - - ret = generic_handle_domain_irq(domain, hwirq); - - set_irq_regs(old_regs); - return ret; + WARN_ON_ONCE(!in_nmi()); + return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } #endif -#endif /* Dynamic interrupt handling */ -- cgit v1.2.3 From 8d15a7295d33538954df2bca6a4011e4311a9cc2 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 21 Oct 2021 18:04:14 +0100 Subject: genirq: Hide irq_cpu_{on,off}line() behind a deprecated option irq_cpu_{on,off}line() are now only used by the Octeon platform. Make their use conditional on this plaform being enabled, and otherwise hidden away. Signed-off-by: Marc Zyngier Reviewed-by: Florian Fainelli Tested-by: Serge Semin Link: https://lore.kernel.org/r/20211021170414.3341522-4-maz@kernel.org --- include/linux/irq.h | 5 ++++- kernel/irq/Kconfig | 7 +++++++ kernel/irq/chip.c | 2 ++ 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irq.h b/include/linux/irq.h index c8293c817646..0c746d325206 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -524,9 +524,10 @@ struct irq_chip { void (*irq_bus_lock)(struct irq_data *data); void (*irq_bus_sync_unlock)(struct irq_data *data); +#ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE void (*irq_cpu_online)(struct irq_data *data); void (*irq_cpu_offline)(struct irq_data *data); - +#endif void (*irq_suspend)(struct irq_data *data); void (*irq_resume)(struct irq_data *data); void (*irq_pm_shutdown)(struct irq_data *data); @@ -606,8 +607,10 @@ struct irqaction; extern int setup_percpu_irq(unsigned int irq, struct irqaction *new); extern void remove_percpu_irq(unsigned int irq, struct irqaction *act); +#ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE extern void irq_cpu_online(void); extern void irq_cpu_offline(void); +#endif extern int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *cpumask, bool force); extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info); diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index fbc54c2a7f23..c0b9d4607147 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -144,3 +144,10 @@ config GENERIC_IRQ_MULTI_HANDLER bool help Allow to specify the low level IRQ handler at run time. + +# Cavium Octeon is the last system to use this deprecated option +# Do not even think of enabling this on any new platform +config DEPRECATED_IRQ_CPU_ONOFFLINE + bool + depends on CAVIUM_OCTEON_SOC + default CAVIUM_OCTEON_SOC diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index a98bcfc4be7b..f895265d7548 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1122,6 +1122,7 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) } EXPORT_SYMBOL_GPL(irq_modify_status); +#ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE /** * irq_cpu_online - Invoke all irq_cpu_online functions. * @@ -1181,6 +1182,7 @@ void irq_cpu_offline(void) raw_spin_unlock_irqrestore(&desc->lock, flags); } } +#endif #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY -- cgit v1.2.3 From 99ce45d5e7dbde399997a630f45ac9f654fa4bcc Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 26 Oct 2021 09:57:28 +0800 Subject: mctp: Implement extended addressing This change allows an extended address struct - struct sockaddr_mctp_ext - to be passed to sendmsg/recvmsg. This allows userspace to specify output ifindex and physical address information (for sendmsg) or receive the input ifindex/physaddr for incoming messages (for recvmsg). This is typically used by userspace for MCTP address discovery and assignment operations. The extended addressing facility is conditional on a new sockopt: MCTP_OPT_ADDR_EXT; userspace must explicitly enable addressing before the kernel will consume/populate the extended address data. Includes a fix for an uninitialised var: Reported-by: kernel test robot Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/net/mctp.h | 13 +++++-- include/uapi/linux/mctp.h | 11 ++++++ net/mctp/af_mctp.c | 86 ++++++++++++++++++++++++++++++++++++----- net/mctp/route.c | 98 +++++++++++++++++++++++++++++++++++------------ 5 files changed, 170 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7612d760b6a9..8ef26d89ef49 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -365,6 +365,7 @@ struct ucred { #define SOL_TLS 282 #define SOL_XDP 283 #define SOL_MPTCP 284 +#define SOL_MCTP 285 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/mctp.h b/include/net/mctp.h index 2a83443bdfac..23bec708f4c7 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -11,6 +11,7 @@ #include #include +#include #include #include @@ -58,6 +59,9 @@ struct mctp_sock { mctp_eid_t bind_addr; __u8 bind_type; + /* sendmsg()/recvmsg() uses struct sockaddr_mctp_ext */ + bool addr_ext; + /* list of mctp_sk_key, for incoming tag lookup. updates protected * by sk->net->keys_lock */ @@ -153,7 +157,10 @@ struct mctp_sk_key { struct mctp_skb_cb { unsigned int magic; unsigned int net; + int ifindex; /* extended/direct addressing if set */ mctp_eid_t src; + unsigned char halen; + unsigned char haddr[MAX_ADDR_LEN]; }; /* skb control-block accessors with a little extra debugging for initial @@ -177,6 +184,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) { struct mctp_skb_cb *cb = (void *)skb->cb; + BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb)); WARN_ON(cb->magic != 0x4d435450); return (void *)(skb->cb); } @@ -189,8 +197,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) * * Updates to the route table are performed under rtnl; all reads under RCU, * so routes cannot be referenced over a RCU grace period. Specifically: A - * caller cannot block between mctp_route_lookup and passing the route to - * mctp_do_route. + * caller cannot block between mctp_route_lookup and mctp_route_release() */ struct mctp_route { mctp_eid_t min, max; @@ -210,8 +217,6 @@ struct mctp_route { struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, mctp_eid_t daddr); -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); - int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 6acd4ccafbf7..07b0318716fc 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -11,6 +11,7 @@ #include #include +#include typedef __u8 mctp_eid_t; @@ -28,6 +29,14 @@ struct sockaddr_mctp { __u8 __smctp_pad1; }; +struct sockaddr_mctp_ext { + struct sockaddr_mctp smctp_base; + int smctp_ifindex; + __u8 smctp_halen; + __u8 __smctp_pad0[3]; + __u8 smctp_haddr[MAX_ADDR_LEN]; +}; + #define MCTP_NET_ANY 0x0 #define MCTP_ADDR_NULL 0x00 @@ -36,4 +45,6 @@ struct sockaddr_mctp { #define MCTP_TAG_MASK 0x07 #define MCTP_TAG_OWNER 0x08 +#define MCTP_OPT_ADDR_EXT 1 + #endif /* __UAPI_MCTP_H */ diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 66a411d60b6c..d344b02a1cde 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -77,6 +77,7 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; struct sk_buff *skb; @@ -100,11 +101,6 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) - return -EHOSTUNREACH; - skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -116,19 +112,45 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) *(u8 *)skb_put(skb, 1) = addr->smctp_type; rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len); - if (rc < 0) { - kfree_skb(skb); - return rc; - } + if (rc < 0) + goto err_free; /* set up cb */ cb = __mctp_cb(skb); cb->net = addr->smctp_network; + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + + if (extaddr->smctp_halen > sizeof(cb->haddr)) { + rc = -EINVAL; + goto err_free; + } + + cb->ifindex = extaddr->smctp_ifindex; + cb->halen = extaddr->smctp_halen; + memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); + + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + } + rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, addr->smctp_tag); return rc ? : len; + +err_free: + kfree_skb(skb); + return rc; } static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, @@ -136,6 +158,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct sk_buff *skb; size_t msglen; u8 type; @@ -181,6 +204,16 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, addr->smctp_tag = hdr->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); msg->msg_namelen = sizeof(*addr); + + if (msk->addr_ext) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae, + msg->msg_name); + msg->msg_namelen = sizeof(*ae); + ae->smctp_ifindex = cb->ifindex; + ae->smctp_halen = cb->halen; + memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr)); + memcpy(ae->smctp_haddr, cb->haddr, cb->halen); + } } rc = len; @@ -196,12 +229,45 @@ out_free: static int mctp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { - return -EINVAL; + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + int val; + + if (level != SOL_MCTP) + return -EINVAL; + + if (optname == MCTP_OPT_ADDR_EXT) { + if (optlen != sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + msk->addr_ext = val; + return 0; + } + + return -ENOPROTOOPT; } static int mctp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + int len, val; + + if (level != SOL_MCTP) + return -EINVAL; + + if (get_user(len, optlen)) + return -EFAULT; + + if (optname == MCTP_OPT_ADDR_EXT) { + if (len != sizeof(int)) + return -EINVAL; + val = !!msk->addr_ext; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; + } + return -EINVAL; } diff --git a/net/mctp/route.c b/net/mctp/route.c index 82fb5ae524f6..c23ab3547ee5 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -434,6 +434,7 @@ static unsigned int mctp_route_mtu(struct mctp_route *rt) static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) { + struct mctp_skb_cb *cb = mctp_cb(skb); struct mctp_hdr *hdr = mctp_hdr(skb); char daddr_buf[MAX_ADDR_LEN]; char *daddr = NULL; @@ -448,9 +449,14 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) return -EMSGSIZE; } - /* If lookup fails let the device handle daddr==NULL */ - if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) - daddr = daddr_buf; + if (cb->ifindex) { + /* direct route; use the hwaddr we stashed in sendmsg */ + daddr = cb->haddr; + } else { + /* If lookup fails let the device handle daddr==NULL */ + if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) + daddr = daddr_buf; + } rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); @@ -649,16 +655,6 @@ static struct mctp_route *mctp_route_lookup_null(struct net *net, return NULL; } -/* sends a skb to rt and releases the route. */ -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb) -{ - int rc; - - rc = rt->output(rt, skb); - mctp_route_release(rt); - return rc; -} - static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, unsigned int mtu, u8 tag) { @@ -725,7 +721,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* copy message payload */ skb_copy_bits(skb, pos, skb_transport_header(skb2), size); - /* do route, but don't drop the rt reference */ + /* do route */ rc = rt->output(rt, skb2); if (rc) break; @@ -734,7 +730,6 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, pos += size; } - mctp_route_release(rt); consume_skb(skb); return rc; } @@ -744,15 +739,51 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb = mctp_cb(skb); + struct mctp_route tmp_rt; + struct net_device *dev; struct mctp_hdr *hdr; unsigned long flags; unsigned int mtu; mctp_eid_t saddr; + bool ext_rt; int rc; u8 tag; - if (WARN_ON(!rt->dev)) + rc = -ENODEV; + + if (rt) { + ext_rt = false; + dev = NULL; + + if (WARN_ON(!rt->dev)) + goto out_release; + + } else if (cb->ifindex) { + ext_rt = true; + rt = &tmp_rt; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex); + if (!dev) { + rcu_read_unlock(); + return rc; + } + + rt->dev = __mctp_dev_get(dev); + rcu_read_unlock(); + + if (!rt->dev) + goto out_release; + + /* establish temporary route - we set up enough to keep + * mctp_route_output happy + */ + rt->output = mctp_route_output; + rt->mtu = 0; + + } else { return -EINVAL; + } spin_lock_irqsave(&rt->dev->addrs_lock, flags); if (rt->dev->num_addrs == 0) { @@ -765,18 +796,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, spin_unlock_irqrestore(&rt->dev->addrs_lock, flags); if (rc) - return rc; + goto out_release; if (req_tag & MCTP_HDR_FLAG_TO) { rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag); if (rc) - return rc; + goto out_release; tag |= MCTP_HDR_FLAG_TO; } else { tag = req_tag; } - skb->protocol = htons(ETH_P_MCTP); skb->priority = 0; skb_reset_transport_header(skb); @@ -796,12 +826,22 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, mtu = mctp_route_mtu(rt); if (skb->len + sizeof(struct mctp_hdr) <= mtu) { - hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM | - tag; - return mctp_do_route(rt, skb); + hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | + MCTP_HDR_FLAG_EOM | tag; + rc = rt->output(rt, skb); } else { - return mctp_do_fragment_route(rt, skb, mtu, tag); + rc = mctp_do_fragment_route(rt, skb, mtu, tag); } + +out_release: + if (!ext_rt) + mctp_route_release(rt); + + if (dev) + dev_put(dev); + + return rc; + } /* route management */ @@ -942,8 +982,15 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX) goto err_drop; - cb = __mctp_cb(skb); + /* MCTP drivers must populate halen/haddr */ + if (dev->type == ARPHRD_MCTP) { + cb = mctp_cb(skb); + } else { + cb = __mctp_cb(skb); + cb->halen = 0; + } cb->net = READ_ONCE(mdev->net); + cb->ifindex = dev->ifindex; rt = mctp_route_lookup(net, cb->net, mh->dest); @@ -954,7 +1001,8 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, if (!rt) goto err_drop; - mctp_do_route(rt, skb); + rt->output(rt, skb); + mctp_route_release(rt); return NET_RX_SUCCESS; -- cgit v1.2.3 From 8e20f591f204f8db7f1182918f8e2285d3f589e0 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 26 Oct 2021 11:06:01 +0100 Subject: net: phy: add phy_interface_t bitmap support Add support for a bitmap for phy interface modes, which includes: - a macro to declare the interface bitmap - an inline helper to zero the interface bitmap - an inline helper to detect an empty interface bitmap - inline helpers to do a bitwise AND and OR operations on two interface bitmaps Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- include/linux/phy.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 04e90423fa88..96e43fbb2dd8 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -155,6 +155,40 @@ typedef enum { PHY_INTERFACE_MODE_MAX, } phy_interface_t; +/* PHY interface mode bitmap handling */ +#define DECLARE_PHY_INTERFACE_MASK(name) \ + DECLARE_BITMAP(name, PHY_INTERFACE_MODE_MAX) + +static inline void phy_interface_zero(unsigned long *intf) +{ + bitmap_zero(intf, PHY_INTERFACE_MODE_MAX); +} + +static inline bool phy_interface_empty(const unsigned long *intf) +{ + return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); +} + +static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_and(dst, a, b, PHY_INTERFACE_MODE_MAX); +} + +static inline void phy_interface_or(unsigned long *dst, const unsigned long *a, + const unsigned long *b) +{ + bitmap_or(dst, a, b, PHY_INTERFACE_MODE_MAX); +} + +static inline void phy_interface_set_rgmii(unsigned long *intf) +{ + __set_bit(PHY_INTERFACE_MODE_RGMII, intf); + __set_bit(PHY_INTERFACE_MODE_RGMII_ID, intf); + __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, intf); + __set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf); +} + /* * phy_supported_speeds - return all speeds currently supported by a PHY device */ -- cgit v1.2.3 From 38c310eb46f5f80213a92093af11af270c209a76 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 26 Oct 2021 11:06:06 +0100 Subject: net: phylink: add MAC phy_interface_t bitmap Add a phy_interface_t bitmap so the MAC driver can specifiy which PHY interface modes it supports. Signed-off-by: Russell King Signed-off-by: David S. Miller --- include/linux/phylink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index f7b5ed06a815..bc4b866cd99b 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -76,6 +76,7 @@ struct phylink_config { bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); + DECLARE_PHY_INTERFACE_MASK(supported_interfaces); }; /** -- cgit v1.2.3 From d25f3a74f30aace819163dfa54f2a4b8ca1dc932 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 26 Oct 2021 11:06:11 +0100 Subject: net: phylink: use supported_interfaces for phylink validation If the network device supplies a supported interface bitmap, we can use that during phylink's validation to simplify MAC drivers in two ways by using the supported_interfaces bitmap to: 1. reject unsupported interfaces before calling into the MAC driver. 2. generate the set of all supported link modes across all supported interfaces (used mainly for SFP, but also some 10G PHYs.) Suggested-by: Sean Anderson Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 36 ++++++++++++++++++++++++++++++++++++ include/linux/phylink.h | 12 ++++++++++-- 2 files changed, 46 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 14c7d73790b4..6da245dacca4 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -166,9 +166,45 @@ static const char *phylink_an_mode_str(unsigned int mode) return mode < ARRAY_SIZE(modestr) ? modestr[mode] : "unknown"; } +static int phylink_validate_any(struct phylink *pl, unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(all_adv) = { 0, }; + __ETHTOOL_DECLARE_LINK_MODE_MASK(all_s) = { 0, }; + __ETHTOOL_DECLARE_LINK_MODE_MASK(s); + struct phylink_link_state t; + int intf; + + for (intf = 0; intf < PHY_INTERFACE_MODE_MAX; intf++) { + if (test_bit(intf, pl->config->supported_interfaces)) { + linkmode_copy(s, supported); + + t = *state; + t.interface = intf; + pl->mac_ops->validate(pl->config, s, &t); + linkmode_or(all_s, all_s, s); + linkmode_or(all_adv, all_adv, t.advertising); + } + } + + linkmode_copy(supported, all_s); + linkmode_copy(state->advertising, all_adv); + + return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; +} + static int phylink_validate(struct phylink *pl, unsigned long *supported, struct phylink_link_state *state) { + if (!phy_interface_empty(pl->config->supported_interfaces)) { + if (state->interface == PHY_INTERFACE_MODE_NA) + return phylink_validate_any(pl, supported, state); + + if (!test_bit(state->interface, + pl->config->supported_interfaces)) + return -EINVAL; + } + pl->mac_ops->validate(pl->config, supported, state); return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index bc4b866cd99b..f037470b6fb3 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -67,6 +67,8 @@ enum phylink_op_type { * @ovr_an_inband: if true, override PCS to MLO_AN_INBAND * @get_fixed_state: callback to execute to determine the fixed link state, * if MAC link is at %MLO_AN_FIXED mode. + * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx + * are supported by the MAC/PCS. */ struct phylink_config { struct device *dev; @@ -134,8 +136,14 @@ struct phylink_mac_ops { * based on @state->advertising and/or @state->speed and update * @state->interface accordingly. See phylink_helper_basex_speed(). * - * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink expects the - * MAC driver to return all supported link modes. + * When @config->supported_interfaces has been set, phylink will iterate + * over the supported interfaces to determine the full capability of the + * MAC. The validation function must not print errors if @state->interface + * is set to an unexpected value. + * + * When @config->supported_interfaces is empty, phylink will call this + * function with @state->interface set to %PHY_INTERFACE_MODE_NA, and + * expects the MAC driver to return all supported link modes. * * If the @state->interface mode is not supported, then the @supported * mask must be cleared. -- cgit v1.2.3 From e60feb445fce9e51c1558a6aa7faf9dd5ded533b Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 14 Oct 2021 13:11:00 -0400 Subject: fs: export an inode_update_time helper If you already have an inode and need to update the time on the inode there is no way to do this properly. Export this helper to allow file systems to update time on the inode so the appropriate handler is called, either ->update_time or generic_update_time. Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/inode.c | 7 ++++--- include/linux/fs.h | 2 ++ 2 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index ed0cab8a32db..9abc88d7959c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1782,12 +1782,13 @@ EXPORT_SYMBOL(generic_update_time); * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ -static int update_time(struct inode *inode, struct timespec64 *time, int flags) +int inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { if (inode->i_op->update_time) return inode->i_op->update_time(inode, time, flags); return generic_update_time(inode, time, flags); } +EXPORT_SYMBOL(inode_update_time); /** * atime_needs_update - update the access time @@ -1857,7 +1858,7 @@ void touch_atime(const struct path *path) * of the fs read only, e.g. subvolumes in Btrfs. */ now = current_time(inode); - update_time(inode, &now, S_ATIME); + inode_update_time(inode, &now, S_ATIME); __mnt_drop_write(mnt); skip_update: sb_end_write(inode->i_sb); @@ -2002,7 +2003,7 @@ int file_update_time(struct file *file) if (__mnt_want_write_file(file)) return 0; - ret = update_time(inode, &now, sync_it); + ret = inode_update_time(inode, &now, sync_it); __mnt_drop_write_file(file); return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index e7a633353fd2..56eba723477e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2498,6 +2498,8 @@ enum file_time_flags { extern bool atime_needs_update(const struct path *, struct inode *); extern void touch_atime(const struct path *); +int inode_update_time(struct inode *inode, struct timespec64 *time, int flags); + static inline void file_accessed(struct file *file) { if (!(file->f_flags & O_NOATIME)) -- cgit v1.2.3 From 6b3671746a8a3aa05316b829e1357060f35009c1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 26 Oct 2021 08:29:39 -0700 Subject: net/mlx5: remove the recent devlink params revert commit 46ae40b94d88 ("net/mlx5: Let user configure io_eq_size param") revert commit a6cb08daa3b4 ("net/mlx5: Let user configure event_eq_size param") revert commit 554604061979 ("net/mlx5: Let user configure max_macs param") The EQE parameters are applicable to more drivers, they should be configured via standard API, probably ethtool. Example of another driver needing something similar: https://lore.kernel.org/all/1633454136-14679-3-git-send-email-sbhatta@marvell.com/ The last param for "max_macs" is probably fine but the documentation is severely lacking. The meaning and implications for changing the param need to be stated. Link: https://lore.kernel.org/r/20211026152939.3125950-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/mlx5.rst | 20 ------ drivers/net/ethernet/mellanox/mlx5/core/Makefile | 2 +- drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 69 ------------------- drivers/net/ethernet/mellanox/mlx5/core/devlink.h | 12 ---- .../net/ethernet/mellanox/mlx5/core/devlink_res.c | 80 ---------------------- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 5 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 21 ------ include/linux/mlx5/driver.h | 4 ++ include/linux/mlx5/eq.h | 1 + include/linux/mlx5/mlx5_ifc.h | 2 +- 10 files changed, 9 insertions(+), 207 deletions(-) delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c (limited to 'include/linux') diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index d467e770906e..4e4b97f7971a 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -14,12 +14,8 @@ Parameters * - Name - Mode - - Validation * - ``enable_roce`` - driverinit - * - ``max_macs`` - - driverinit - - The range is between 1 and 2^31. Only power of 2 values are supported. The ``mlx5`` driver also implements the following driver-specific parameters. @@ -50,22 +46,6 @@ parameters. The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD`` -Resources -========= - -.. list-table:: Driver-specific resources implemented - :widths: 5 5 5 85 - - * - Name - - Description - * - ``comp_eq_size`` - - Control the size of I/O completion EQs. - * The default value is 1024, and the range is between 64 and 4096. - * - ``event_eq_size`` - - Control the size of the asynchronous control events EQ. - * The default value is 4096, and the range is between 64 and 4096. - - Info versions ============= diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 79c15ee62cde..bdb271b604d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -16,7 +16,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o fs_ft_pool.o rl.o lag/lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o lib/pci_vsc.o lib/dm.o lib/fs_ttc.o diag/fs_tracepoint.o \ - diag/fw_tracer.o diag/crdump.o devlink.o devlink_res.o diag/rsc_dump.o \ + diag/fw_tracer.o diag/crdump.o devlink.o diag/rsc_dump.o \ fw_reset.o qos.o lib/tout.o # diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index fc78c745ead1..1c98652b244a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -752,68 +752,6 @@ static void mlx5_devlink_auxdev_params_unregister(struct devlink *devlink) mlx5_devlink_eth_param_unregister(devlink); } -static int mlx5_devlink_max_uc_list_validate(struct devlink *devlink, u32 id, - union devlink_param_value val, - struct netlink_ext_ack *extack) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - - /* At least one unicast mac is needed */ - if (val.vu32 == 0) { - NL_SET_ERR_MSG_MOD(extack, "max_macs value must be greater than 0"); - return -EINVAL; - } - /* Check if its power of 2 or not */ - if (!is_power_of_2(val.vu32)) { - NL_SET_ERR_MSG_MOD(extack, - "Only power of 2 values are supported for max_macs"); - return -EOPNOTSUPP; - } - - if (ilog2(val.vu32) > - MLX5_CAP_GEN_MAX(dev, log_max_current_uc_list)) { - NL_SET_ERR_MSG_MOD(extack, "max_macs value is out of the supported range"); - return -EOPNOTSUPP; - } - - return 0; -} - -static const struct devlink_param max_uc_list_param = - DEVLINK_PARAM_GENERIC(MAX_MACS, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), - NULL, NULL, mlx5_devlink_max_uc_list_validate); - -static int mlx5_devlink_max_uc_list_param_register(struct devlink *devlink) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - union devlink_param_value value; - int err; - - if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported)) - return 0; - - err = devlink_param_register(devlink, &max_uc_list_param); - if (err) - return err; - - value.vu32 = 1 << MLX5_CAP_GEN(dev, log_max_current_uc_list); - devlink_param_driverinit_value_set(devlink, - DEVLINK_PARAM_GENERIC_ID_MAX_MACS, - value); - return 0; -} - -static void -mlx5_devlink_max_uc_list_param_unregister(struct devlink *devlink) -{ - struct mlx5_core_dev *dev = devlink_priv(devlink); - - if (!MLX5_CAP_GEN(dev, log_max_current_uc_list_wr_supported)) - return; - - devlink_param_unregister(devlink, &max_uc_list_param); -} - #define MLX5_TRAP_DROP(_id, _group_id) \ DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ DEVLINK_TRAP_GROUP_GENERIC_ID_##_group_id, \ @@ -877,17 +815,11 @@ int mlx5_devlink_register(struct devlink *devlink) if (err) goto traps_reg_err; - err = mlx5_devlink_max_uc_list_param_register(devlink); - if (err) - goto uc_list_reg_err; - if (!mlx5_core_is_mp_slave(dev)) devlink_set_features(devlink, DEVLINK_F_RELOAD); return 0; -uc_list_reg_err: - mlx5_devlink_traps_unregister(devlink); traps_reg_err: mlx5_devlink_auxdev_params_unregister(devlink); auxdev_reg_err: @@ -898,7 +830,6 @@ auxdev_reg_err: void mlx5_devlink_unregister(struct devlink *devlink) { - mlx5_devlink_max_uc_list_param_unregister(devlink); mlx5_devlink_traps_unregister(devlink); mlx5_devlink_auxdev_params_unregister(devlink); devlink_params_unregister(devlink, mlx5_devlink_params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h index 674415fd0b3a..30bf4882779b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.h @@ -6,14 +6,6 @@ #include -enum mlx5_devlink_resource_id { - MLX5_DL_RES_COMP_EQ = 1, - MLX5_DL_RES_ASYNC_EQ, - - __MLX5_ID_RES_MAX, - MLX5_ID_RES_MAX = __MLX5_ID_RES_MAX - 1, -}; - enum mlx5_devlink_param_id { MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, MLX5_DEVLINK_PARAM_ID_FLOW_STEERING_MODE, @@ -39,10 +31,6 @@ int mlx5_devlink_trap_get_num_active(struct mlx5_core_dev *dev); int mlx5_devlink_traps_get_action(struct mlx5_core_dev *dev, int trap_id, enum devlink_trap_action *action); -void mlx5_devlink_res_register(struct mlx5_core_dev *dev); -void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev); -size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id); - struct devlink *mlx5_devlink_alloc(struct device *dev); void mlx5_devlink_free(struct devlink *devlink); int mlx5_devlink_register(struct devlink *devlink); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c deleted file mode 100644 index 549d23745942..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink_res.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB -/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. */ - -#include "devlink.h" -#include "mlx5_core.h" - -enum { - MLX5_EQ_MIN_SIZE = 64, - MLX5_EQ_MAX_SIZE = 4096, - MLX5_NUM_ASYNC_EQE = 4096, - MLX5_COMP_EQ_SIZE = 1024, -}; - -static int comp_eq_res_register(struct mlx5_core_dev *dev) -{ - struct devlink_resource_size_params comp_eq_size; - struct devlink *devlink = priv_to_devlink(dev); - - devlink_resource_size_params_init(&comp_eq_size, MLX5_EQ_MIN_SIZE, - MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY); - return devlink_resource_register(devlink, "io_eq_size", MLX5_COMP_EQ_SIZE, - MLX5_DL_RES_COMP_EQ, - DEVLINK_RESOURCE_ID_PARENT_TOP, - &comp_eq_size); -} - -static int async_eq_resource_register(struct mlx5_core_dev *dev) -{ - struct devlink_resource_size_params async_eq_size; - struct devlink *devlink = priv_to_devlink(dev); - - devlink_resource_size_params_init(&async_eq_size, MLX5_EQ_MIN_SIZE, - MLX5_EQ_MAX_SIZE, 1, DEVLINK_RESOURCE_UNIT_ENTRY); - return devlink_resource_register(devlink, "event_eq_size", - MLX5_NUM_ASYNC_EQE, MLX5_DL_RES_ASYNC_EQ, - DEVLINK_RESOURCE_ID_PARENT_TOP, - &async_eq_size); -} - -void mlx5_devlink_res_register(struct mlx5_core_dev *dev) -{ - int err; - - err = comp_eq_res_register(dev); - if (err) - goto err_msg; - - err = async_eq_resource_register(dev); - if (err) - goto err; - return; -err: - devlink_resources_unregister(priv_to_devlink(dev), NULL); -err_msg: - mlx5_core_err(dev, "Failed to register resources, err = %d\n", err); -} - -void mlx5_devlink_res_unregister(struct mlx5_core_dev *dev) -{ - devlink_resources_unregister(priv_to_devlink(dev), NULL); -} - -static const size_t default_vals[MLX5_ID_RES_MAX + 1] = { - [MLX5_DL_RES_COMP_EQ] = MLX5_COMP_EQ_SIZE, - [MLX5_DL_RES_ASYNC_EQ] = MLX5_NUM_ASYNC_EQE, -}; - -size_t mlx5_devlink_res_size(struct mlx5_core_dev *dev, enum mlx5_devlink_resource_id id) -{ - struct devlink *devlink = priv_to_devlink(dev); - u64 size; - int err; - - err = devlink_resource_size_get(devlink, id, &size); - if (!err) - return size; - mlx5_core_err(dev, "Failed to get param. using default. err = %d, id = %u\n", - err, id); - return default_vals[id]; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 31e69067284b..792e0d6aa861 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -19,7 +19,6 @@ #include "lib/clock.h" #include "diag/fw_tracer.h" #include "mlx5_irq.h" -#include "devlink.h" enum { MLX5_EQE_OWNER_INIT_VAL = 0x1, @@ -647,7 +646,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) param = (struct mlx5_eq_param) { .irq_index = MLX5_IRQ_EQ_CTRL, - .nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_ASYNC_EQ), + .nent = MLX5_NUM_ASYNC_EQE, }; gather_async_events_mask(dev, param.mask); @@ -808,7 +807,7 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) INIT_LIST_HEAD(&table->comp_eqs_list); ncomp_eqs = table->num_comp_eqs; - nent = mlx5_devlink_res_size(dev, MLX5_DL_RES_COMP_EQ); + nent = MLX5_COMP_EQ_SIZE; for (i = 0; i < ncomp_eqs; i++) { struct mlx5_eq_param param = {}; int vecidx = i; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 079ee9e8da10..f8446395163a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -484,23 +484,10 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP); } -static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev) -{ - struct devlink *devlink = priv_to_devlink(dev); - union devlink_param_value val; - int err; - - err = devlink_param_driverinit_value_get(devlink, - DEVLINK_PARAM_GENERIC_ID_MAX_MACS, - &val); - return err ? 0 : val.vu32; -} - static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; - u32 max_uc_list; int err; err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL); @@ -574,11 +561,6 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) if (MLX5_CAP_GEN(dev, roce_rw_supported)) MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); - max_uc_list = max_uc_list_get_devlink_param(dev); - if (max_uc_list) - MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list, - ilog2(max_uc_list)); - return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } @@ -940,8 +922,6 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) dev->hv_vhca = mlx5_hv_vhca_create(dev); dev->rsc_dump = mlx5_rsc_dump_create(dev); - mlx5_devlink_res_register(dev); - return 0; err_sf_table_cleanup: @@ -977,7 +957,6 @@ err_devcom: static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { - mlx5_devlink_res_unregister(dev); mlx5_rsc_dump_destroy(dev); mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 47c07f95bbe1..f617dfbcd9fd 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -797,6 +797,10 @@ struct mlx5_db { int index; }; +enum { + MLX5_COMP_EQ_SIZE = 1024, +}; + enum { MLX5_PTYS_IB = 1 << 0, MLX5_PTYS_EN = 1 << 2, diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index 11161e427608..ea3ff5a8ced3 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -5,6 +5,7 @@ #define MLX5_CORE_EQ_H #define MLX5_NUM_CMD_EQE (32) +#define MLX5_NUM_ASYNC_EQE (0x1000) #define MLX5_NUM_SPARE_EQE (0x80) struct mlx5_eq; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 97465d00de9d..746381eccccf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1603,7 +1603,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ext_stride_num_range[0x1]; u8 roce_rw_supported[0x1]; - u8 log_max_current_uc_list_wr_supported[0x1]; + u8 reserved_at_3a2[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; -- cgit v1.2.3 From cfe6807d82e97e81c3209dca9448f091e1448a57 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 26 Oct 2021 18:58:11 +0100 Subject: gpio: Allow per-parent interrupt data The core gpiolib code is able to deal with multiple interrupt parents for a single gpio irqchip. It however only allows a single piece of data to be conveyed to all flow handlers (either the gpio_chip or some other, driver-specific data). This means that drivers have to go through some interesting dance to find the correct context, something that isn't great in interrupt context (see aebdc8abc9db86e2bd33070fc2f961012fff74b4 for a prime example). Instead, offer an optional way for a pinctrl/gpio driver to provide an array of pointers which gets used to provide the correct context to the flow handler. Signed-off-by: Marc Zyngier Signed-off-by: Joey Gouly Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20211026175815.52703-2-joey.gouly@arm.com Signed-off-by: Linus Walleij --- drivers/gpio/gpiolib.c | 9 +++++++-- include/linux/gpio/driver.h | 19 +++++++++++++++++-- 2 files changed, 24 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index d1b9b721218f..abfbf546d159 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1534,9 +1534,14 @@ static int gpiochip_add_irqchip(struct gpio_chip *gc, } if (gc->irq.parent_handler) { - void *data = gc->irq.parent_handler_data ?: gc; - for (i = 0; i < gc->irq.num_parents; i++) { + void *data; + + if (gc->irq.per_parent_data) + data = gc->irq.parent_handler_data_array[i]; + else + data = gc->irq.parent_handler_data ?: gc; + /* * The parent IRQ chip is already using the chip_data * for this IRQ chip, so our callbacks simply use the diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index a0f9901dcae6..a673a359e20b 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -168,11 +168,18 @@ struct gpio_irq_chip { /** * @parent_handler_data: + * @parent_handler_data_array: * * Data associated, and passed to, the handler for the parent - * interrupt. + * interrupt. Can either be a single pointer if @per_parent_data + * is false, or an array of @num_parents pointers otherwise. If + * @per_parent_data is true, @parent_handler_data_array cannot be + * NULL. */ - void *parent_handler_data; + union { + void *parent_handler_data; + void **parent_handler_data_array; + }; /** * @num_parents: @@ -203,6 +210,14 @@ struct gpio_irq_chip { */ bool threaded; + /** + * @per_parent_data: + * + * True if parent_handler_data_array describes a @num_parents + * sized array to be used as parent data. + */ + bool per_parent_data; + /** * @init_hw: optional routine to initialize hardware before * an IRQ chip will be added. This is quite useful when -- cgit v1.2.3 From 7529cc7fbd9c02eda6851f3260416cbe198a321d Mon Sep 17 00:00:00 2001 From: Tariq Toukan Date: Wed, 30 Dec 2020 11:41:52 +0200 Subject: lib: bitmap: Introduce node-aware alloc API Expose new node-aware API for bitmap allocation: bitmap_alloc_node() / bitmap_zalloc_node(). Signed-off-by: Tariq Toukan Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/bitmap.h | 2 ++ lib/bitmap.c | 13 +++++++++++++ 2 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 37f36dad18bd..a241dcf50f39 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -123,6 +123,8 @@ struct device; */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags); +unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node); +unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node); void bitmap_free(const unsigned long *bitmap); /* Managed variants of the above. */ diff --git a/lib/bitmap.c b/lib/bitmap.c index 663dd81967d4..926408883456 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -1398,6 +1398,19 @@ unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) } EXPORT_SYMBOL(bitmap_zalloc); +unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node) +{ + return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long), + flags, node); +} +EXPORT_SYMBOL(bitmap_alloc_node); + +unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node) +{ + return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node); +} +EXPORT_SYMBOL(bitmap_zalloc_node); + void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); -- cgit v1.2.3 From 50f477fe9933193e960785f1192be801d7cd307a Mon Sep 17 00:00:00 2001 From: Ben Ben-Ishay Date: Thu, 2 Jul 2020 17:22:45 +0300 Subject: net/mlx5e: Rename lro_timeout to packet_merge_timeout TIR stands for transport interface receive, the TIR object is responsible for performing all transport related operations on the receive side like packet processing, demultiplexing the packets to different RQ's, etc. lro_timeout is a field in the TIR that is used to set the timeout for lro session, this series introduces new packet merge type, therefore rename lro_timeout to packet_merge_timeout for all packet merge types. Signed-off-by: Ben Ben-Ishay Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/params.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/tir.c | 6 +++--- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 6 +++--- 5 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index a3a4fece0cac..26e3f413386a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -265,7 +265,7 @@ struct mlx5e_params { bool scatter_fcs_en; bool rx_dim_enabled; bool tx_dim_enabled; - u32 lro_timeout; + u32 packet_merge_timeout; u32 pflags; struct bpf_prog *xdp_prog; struct mlx5e_xsk *xsk; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 3cbb596821e8..2b2b3c5cdbd5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -173,7 +173,7 @@ struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params) lro_param = (struct mlx5e_lro_param) { .enabled = params->lro_en, - .timeout = params->lro_timeout, + .timeout = params->packet_merge_timeout, }; return lro_param; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c index de936dc4bc48..857ea0979159 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -82,9 +82,9 @@ void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, if (!lro_param->enabled) return; - MLX5_SET(tirc, tirc, lro_enable_mask, - MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO | - MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO); + MLX5_SET(tirc, tirc, packet_merge_mask, + MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO | + MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO); MLX5_SET(tirc, tirc, lro_max_ip_payload_size, (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8); MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index f3dec58026d9..0e7a8afeb9bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4404,7 +4404,7 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) params->lro_en = !slow_pci_heuristic(mdev); } - params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); + params->packet_merge_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ? diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 746381eccccf..21c0fd478afa 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3361,8 +3361,8 @@ enum { }; enum { - MLX5_TIRC_LRO_ENABLE_MASK_IPV4_LRO = 0x1, - MLX5_TIRC_LRO_ENABLE_MASK_IPV6_LRO = 0x2, + MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO = BIT(0), + MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO = BIT(1), }; enum { @@ -3387,7 +3387,7 @@ struct mlx5_ifc_tirc_bits { u8 reserved_at_80[0x4]; u8 lro_timeout_period_usecs[0x10]; - u8 lro_enable_mask[0x4]; + u8 packet_merge_mask[0x4]; u8 lro_max_ip_payload_size[0x8]; u8 reserved_at_a0[0x40]; -- cgit v1.2.3 From 7025329d208cae45937d2a0910786a45b9981475 Mon Sep 17 00:00:00 2001 From: Ben Ben-Ishay Date: Wed, 9 Sep 2020 17:36:39 +0300 Subject: net/mlx5: Add SHAMPO caps, HW bits and enumerations This commit adds SHAMPO bit to hca_cap and SHAMPO capabilities structure, SHAMPO related HW spec hardware fields and enumerations. SHAMPO stands for: split headers and merge payload offload. SHAMPO new fields: WQ: - headers_mkey: mkey that represents the headers buffer, where the packets headers will be written by the HW. - shampo_enable: flag to verify if the WQ supports SHAMPO feature. - log_reservation_size: the log of the reservation size where the data of the packet will be written by the HW. - log_max_num_of_packets_per_reservation: log of the maximum number of packets that can be written to the same reservation. - log_headers_entry_size: log of the header entry size of the headers buffer. - log_headers_buffer_entry_num: log of the entries number of the headers buffer. RQ: - shampo_no_match_alignment_granularity: the HW alignment granularity in case the received packet doesn't match the current session. - shampo_match_criteria_type: the type of match criteria. - reservation_timeout: the maximum time that the HW will hold the reservation. mlx5_ifc_shampo_cap_bits, the capabilities of the SHAMPO feature: - shampo_log_max_reservation_size: the maximum allowed value of the field WQ.log_reservation_size. - log_reservation_size: the minimum allowed value of the field WQ.log_reservation_size. - shampo_min_mss_size: the minimum payload size of packet that can open a new session or be merged to a session. - shampo_max_log_headers_entry_size: the maximum allowed value of the field WQ.log_headers_entry_size Signed-off-by: Ben Ben-Ishay Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/fw.c | 6 +++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 1 + include/linux/mlx5/device.h | 4 ++ include/linux/mlx5/mlx5_ifc.h | 56 ++++++++++++++++++++++++-- 4 files changed, 64 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index 1037e3629e7e..2d8406fab844 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -269,6 +269,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev) return err; } + if (MLX5_CAP_GEN(dev, shampo)) { + err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_SHAMPO); + if (err) + return err; + } + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index f8446395163a..a92a92a52346 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1417,6 +1417,7 @@ static const int types[] = { MLX5_CAP_VDPA_EMULATION, MLX5_CAP_IPSEC, MLX5_CAP_PORT_SELECTION, + MLX5_CAP_DEV_SHAMPO, }; static void mlx5_hca_caps_free(struct mlx5_core_dev *dev) diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index f8a0bbb42c3b..0d30a6184e1d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1186,6 +1186,7 @@ enum mlx5_cap_type { MLX5_CAP_VDPA_EMULATION = 0x13, MLX5_CAP_DEV_EVENT = 0x14, MLX5_CAP_IPSEC, + MLX5_CAP_DEV_SHAMPO = 0x1d, MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, /* NUM OF CAP Types */ @@ -1431,6 +1432,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_IPSEC(mdev, cap)\ MLX5_GET(ipsec_cap, (mdev)->caps.hca[MLX5_CAP_IPSEC]->cur, cap) +#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\ + MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap) + enum { MLX5_CMD_STAT_OK = 0x0, MLX5_CMD_STAT_INT_ERR = 0x1, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 21c0fd478afa..f1c134af5fcf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1350,7 +1350,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_b0[0x1]; u8 uplink_follow[0x1]; u8 ts_cqe_to_dest_cqn[0x1]; - u8 reserved_at_b3[0xd]; + u8 reserved_at_b3[0x7]; + u8 shampo[0x1]; + u8 reserved_at_bb[0x5]; u8 max_sgl_for_optimized_performance[0x8]; u8 log_max_cq_sz[0x8]; @@ -1893,7 +1895,21 @@ struct mlx5_ifc_wq_bits { u8 reserved_at_139[0x4]; u8 log_wqe_stride_size[0x3]; - u8 reserved_at_140[0x4c0]; + u8 reserved_at_140[0x80]; + + u8 headers_mkey[0x20]; + + u8 shampo_enable[0x1]; + u8 reserved_at_1e1[0x4]; + u8 log_reservation_size[0x3]; + u8 reserved_at_1e8[0x5]; + u8 log_max_num_of_packets_per_reservation[0x3]; + u8 reserved_at_1f0[0x6]; + u8 log_headers_entry_size[0x2]; + u8 reserved_at_1f8[0x4]; + u8 log_headers_buffer_entry_num[0x4]; + + u8 reserved_at_200[0x400]; struct mlx5_ifc_cmd_pas_bits pas[]; }; @@ -3169,6 +3185,20 @@ struct mlx5_ifc_roce_addr_layout_bits { u8 reserved_at_e0[0x20]; }; +struct mlx5_ifc_shampo_cap_bits { + u8 reserved_at_0[0x3]; + u8 shampo_log_max_reservation_size[0x5]; + u8 reserved_at_8[0x3]; + u8 shampo_log_min_reservation_size[0x5]; + u8 shampo_min_mss_size[0x10]; + + u8 reserved_at_20[0x3]; + u8 shampo_max_log_headers_entry_size[0x5]; + u8 reserved_at_28[0x18]; + + u8 reserved_at_40[0x7c0]; +}; + union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap; struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2; @@ -3187,6 +3217,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_tls_cap_bits tls_cap; struct mlx5_ifc_device_mem_cap_bits device_mem_cap; struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap; + struct mlx5_ifc_shampo_cap_bits shampo_cap; u8 reserved_at_0[0x8000]; }; @@ -3363,6 +3394,7 @@ enum { enum { MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO = BIT(0), MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO = BIT(1), + MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO = BIT(2), }; enum { @@ -3569,6 +3601,18 @@ enum { MLX5_RQC_STATE_ERR = 0x3, }; +enum { + MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_BYTE = 0x0, + MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_STRIDE = 0x1, + MLX5_RQC_SHAMPO_NO_MATCH_ALIGNMENT_GRANULARITY_PAGE = 0x2, +}; + +enum { + MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_NO_MATCH = 0x0, + MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_EXTENDED = 0x1, + MLX5_RQC_SHAMPO_MATCH_CRITERIA_TYPE_FIVE_TUPLE = 0x2, +}; + struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; u8 delay_drop_en[0x1]; @@ -3601,7 +3645,13 @@ struct mlx5_ifc_rqc_bits { u8 reserved_at_c0[0x10]; u8 hairpin_peer_vhca[0x10]; - u8 reserved_at_e0[0xa0]; + u8 reserved_at_e0[0x46]; + u8 shampo_no_match_alignment_granularity[0x2]; + u8 reserved_at_128[0x6]; + u8 shampo_match_criteria_type[0x2]; + u8 reservation_timeout[0x10]; + + u8 reserved_at_140[0x40]; struct mlx5_ifc_wq_bits wq; }; -- cgit v1.2.3 From eaee12f046924eeb1210c7e4f3b326603ff1bd85 Mon Sep 17 00:00:00 2001 From: Khalid Manaa Date: Wed, 9 Jun 2021 12:27:32 +0300 Subject: net/mlx5e: Rename TIR lro functions to TIR packet merge functions This series introduces new packet merge type, therefore rename lro functions to packet merge to support the new merge type: - Generalize + rename mlx5e_build_tir_ctx_lro to mlx5e_build_tir_ctx_packet_merge. - Rename mlx5e_modify_tirs_lro to mlx5e_modify_tirs_packet_merge. - Rename lro bit in mlx5_ifc_modify_tir_bitmask_bits to packet_merge. - Rename lro_en in mlx5e_params to packet_merge_type type and combine packet_merge params into one struct mlx5e_packet_merge_param. Signed-off-by: Khalid Manaa Signed-off-by: Ben Ben-Ishay Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 14 ++++++- .../net/ethernet/mellanox/mlx5/core/en/params.c | 21 +++------- .../net/ethernet/mellanox/mlx5/core/en/params.h | 6 --- drivers/net/ethernet/mellanox/mlx5/core/en/rss.c | 23 +++++------ drivers/net/ethernet/mellanox/mlx5/core/en/rss.h | 7 ++-- .../net/ethernet/mellanox/mlx5/core/en/rx_res.c | 25 ++++++------ .../net/ethernet/mellanox/mlx5/core/en/rx_res.h | 5 ++- drivers/net/ethernet/mellanox/mlx5/core/en/tir.c | 10 ++--- drivers/net/ethernet/mellanox/mlx5/core/en/tir.h | 6 +-- .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 4 +- .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 6 +-- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 46 ++++++++++++---------- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 5 +-- .../net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 7 ++-- include/linux/mlx5/mlx5_ifc.h | 2 +- 15 files changed, 95 insertions(+), 92 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 26e3f413386a..8c3e7464b30f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -242,6 +242,17 @@ enum mlx5e_priv_flag { #define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag)))) +enum packet_merge { + MLX5E_PACKET_MERGE_NONE, + MLX5E_PACKET_MERGE_LRO, + MLX5E_PACKET_MERGE_SHAMPO, +}; + +struct mlx5e_packet_merge_param { + enum packet_merge type; + u32 timeout; +}; + struct mlx5e_params { u8 log_sq_size; u8 rq_wq_type; @@ -259,13 +270,12 @@ struct mlx5e_params { bool tunneled_offload_en; struct dim_cq_moder rx_cq_moderation; struct dim_cq_moder tx_cq_moderation; - bool lro_en; + struct mlx5e_packet_merge_param packet_merge; u8 tx_min_inline_mode; bool vlan_strip_disable; bool scatter_fcs_en; bool rx_dim_enabled; bool tx_dim_enabled; - u32 packet_merge_timeout; u32 pflags; struct bpf_prog *xdp_prog; struct mlx5e_xsk *xsk; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 2b2b3c5cdbd5..15f441a1b80c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -87,7 +87,8 @@ bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params, u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk), mlx5e_rx_get_linear_frag_sz(params, NULL)); - return !params->lro_en && linear_frag_sz <= PAGE_SIZE; + return params->packet_merge.type == MLX5E_PACKET_MERGE_NONE && + linear_frag_sz <= PAGE_SIZE; } bool mlx5e_verify_rx_mpwqe_strides(struct mlx5_core_dev *mdev, @@ -164,19 +165,8 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, mlx5e_rx_is_linear_skb(params, xsk) : mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk); - return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; -} - -struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params) -{ - struct mlx5e_lro_param lro_param; - - lro_param = (struct mlx5e_lro_param) { - .enabled = params->lro_en, - .timeout = params->packet_merge_timeout, - }; - - return lro_param; + return is_linear_skb || params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO ? + mlx5e_get_linear_rq_headroom(params, xsk) : 0; } u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) @@ -485,10 +475,11 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev, static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { + bool lro_en = params->packet_merge.type == MLX5E_PACKET_MERGE_LRO; bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) && MLX5_CAP_GEN(mdev, relaxed_ordering_write); - return ro && params->lro_en ? + return ro && lro_en ? MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 879ad46d754e..e9593f5f0661 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -11,11 +11,6 @@ struct mlx5e_xsk_param { u16 chunk_size; }; -struct mlx5e_lro_param { - bool enabled; - u32 timeout; -}; - struct mlx5e_cq_param { u32 cqc[MLX5_ST_SZ_DW(cqc)]; struct mlx5_wq_param wq; @@ -125,7 +120,6 @@ u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); -struct mlx5e_lro_param mlx5e_get_lro_param(struct mlx5e_params *params); /* Build queue parameters */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index b8b481b335cf..c1cdd8c2e37a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -127,7 +127,7 @@ mlx5e_rss_get_tt_config(struct mlx5e_rss *rss, enum mlx5_traffic_types tt) static int mlx5e_rss_create_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner) { struct mlx5e_rss_params_traffic_type rss_tt; @@ -161,7 +161,7 @@ static int mlx5e_rss_create_tir(struct mlx5e_rss *rss, rqtn = mlx5e_rqt_get_rqtn(&rss->rqt); mlx5e_tir_builder_build_rqt(builder, rss->mdev->mlx5e_res.hw_objs.td.tdn, rqtn, rss->inner_ft_support); - mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param); rss_tt = mlx5e_rss_get_tt_config(rss, tt); mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner); @@ -198,14 +198,14 @@ static void mlx5e_rss_destroy_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types } static int mlx5e_rss_create_tirs(struct mlx5e_rss *rss, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner) { enum mlx5_traffic_types tt, max_tt; int err; for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) { - err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner); + err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner); if (err) goto err_destroy_tirs; } @@ -297,7 +297,7 @@ int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn, - const struct mlx5e_lro_param *init_lro_param) + const struct mlx5e_packet_merge_param *init_pkt_merge_param) { int err; @@ -305,12 +305,12 @@ int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, if (err) goto err_out; - err = mlx5e_rss_create_tirs(rss, init_lro_param, false); + err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, false); if (err) goto err_destroy_rqt; if (inner_ft_support) { - err = mlx5e_rss_create_tirs(rss, init_lro_param, true); + err = mlx5e_rss_create_tirs(rss, init_pkt_merge_param, true); if (err) goto err_destroy_tirs; } @@ -372,7 +372,7 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, */ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn) { struct mlx5e_tir *tir; @@ -381,7 +381,7 @@ int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, if (!tir) { /* TIR doesn't exist, create one */ int err; - err = mlx5e_rss_create_tir(rss, tt, init_lro_param, inner); + err = mlx5e_rss_create_tir(rss, tt, init_pkt_merge_param, inner); if (err) return err; tir = rss_get_tir(rss, tt, inner); @@ -419,7 +419,8 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss) mlx5e_rqt_get_rqtn(&rss->rqt), rss->drop_rqn, err); } -int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param) +int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, + struct mlx5e_packet_merge_param *pkt_merge_param) { struct mlx5e_tir_builder *builder; enum mlx5_traffic_types tt; @@ -429,7 +430,7 @@ int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_p if (!builder) return -ENOMEM; - mlx5e_tir_builder_build_lro(builder, lro_param); + mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param); final_err = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h index d522a10dadf3..c6b216416344 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -17,7 +17,7 @@ struct mlx5e_rss *mlx5e_rss_alloc(void); void mlx5e_rss_free(struct mlx5e_rss *rss); int mlx5e_rss_init(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn, - const struct mlx5e_lro_param *init_lro_param); + const struct mlx5e_packet_merge_param *init_pkt_merge_param); int mlx5e_rss_init_no_tirs(struct mlx5e_rss *rss, struct mlx5_core_dev *mdev, bool inner_ft_support, u32 drop_rqn); int mlx5e_rss_cleanup(struct mlx5e_rss *rss); @@ -30,13 +30,14 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner); int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, bool inner, u32 *tirn); void mlx5e_rss_enable(struct mlx5e_rss *rss, u32 *rqns, unsigned int num_rqns); void mlx5e_rss_disable(struct mlx5e_rss *rss); -int mlx5e_rss_lro_set_param(struct mlx5e_rss *rss, struct mlx5e_lro_param *lro_param); +int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss, + struct mlx5e_packet_merge_param *pkt_merge_param); int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc); int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir, const u8 *key, const u8 *hfunc, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index 13056cb9757d..142953847996 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -34,7 +34,7 @@ struct mlx5e_rx_res { /* API for rx_res_rss_* */ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res, - const struct mlx5e_lro_param *init_lro_param, + const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; @@ -49,7 +49,7 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res, return -ENOMEM; err = mlx5e_rss_init(rss, res->mdev, inner_ft_support, res->drop_rqn, - init_lro_param); + init_pkt_merge_param); if (err) goto err_rss_free; @@ -275,7 +275,7 @@ struct mlx5e_rx_res *mlx5e_rx_res_alloc(void) } static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, - const struct mlx5e_lro_param *init_lro_param) + const struct mlx5e_packet_merge_param *init_pkt_merge_param) { bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; struct mlx5e_tir_builder *builder; @@ -306,7 +306,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), inner_ft_support); - mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param); mlx5e_tir_builder_build_direct(builder); err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true); @@ -336,7 +336,7 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res, mlx5e_tir_builder_build_rqt(builder, res->mdev->mlx5e_res.hw_objs.td.tdn, mlx5e_rqt_get_rqtn(&res->channels[ix].xsk_rqt), inner_ft_support); - mlx5e_tir_builder_build_lro(builder, init_lro_param); + mlx5e_tir_builder_build_packet_merge(builder, init_pkt_merge_param); mlx5e_tir_builder_build_direct(builder); err = mlx5e_tir_init(&res->channels[ix].xsk_tir, builder, res->mdev, true); @@ -437,7 +437,7 @@ static void mlx5e_rx_res_ptp_destroy(struct mlx5e_rx_res *res) int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features features, unsigned int max_nch, - u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param, + u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch) { int err; @@ -447,11 +447,11 @@ int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, res->max_nch = max_nch; res->drop_rqn = drop_rqn; - err = mlx5e_rx_res_rss_init_def(res, init_lro_param, init_nch); + err = mlx5e_rx_res_rss_init_def(res, init_pkt_merge_param, init_nch); if (err) goto err_out; - err = mlx5e_rx_res_channels_init(res, init_lro_param); + err = mlx5e_rx_res_channels_init(res, init_pkt_merge_param); if (err) goto err_rss_destroy; @@ -645,7 +645,8 @@ int mlx5e_rx_res_xsk_deactivate(struct mlx5e_rx_res *res, unsigned int ix) return err; } -int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param) +int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res, + struct mlx5e_packet_merge_param *pkt_merge_param) { struct mlx5e_tir_builder *builder; int err, final_err; @@ -655,7 +656,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param if (!builder) return -ENOMEM; - mlx5e_tir_builder_build_lro(builder, lro_param); + mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param); final_err = 0; @@ -665,7 +666,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param if (!rss) continue; - err = mlx5e_rss_lro_set_param(rss, lro_param); + err = mlx5e_rss_packet_merge_set_param(rss, pkt_merge_param); if (err) final_err = final_err ? : err; } @@ -673,7 +674,7 @@ int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param for (ix = 0; ix < res->max_nch; ix++) { err = mlx5e_tir_modify(&res->channels[ix].direct_tir, builder); if (err) { - mlx5_core_warn(res->mdev, "Failed to update LRO state of direct TIR %#x for channel %u: err = %d\n", + mlx5_core_warn(res->mdev, "Failed to update packet merge state of direct TIR %#x for channel %u: err = %d\n", mlx5e_tir_get_tirn(&res->channels[ix].direct_tir), ix, err); if (!final_err) final_err = err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index 4a15942d79f7..d09f7d174a51 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -25,7 +25,7 @@ enum mlx5e_rx_res_features { struct mlx5e_rx_res *mlx5e_rx_res_alloc(void); int mlx5e_rx_res_init(struct mlx5e_rx_res *res, struct mlx5_core_dev *mdev, enum mlx5e_rx_res_features features, unsigned int max_nch, - u32 drop_rqn, const struct mlx5e_lro_param *init_lro_param, + u32 drop_rqn, const struct mlx5e_packet_merge_param *init_pkt_merge_param, unsigned int init_nch); void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res); void mlx5e_rx_res_free(struct mlx5e_rx_res *res); @@ -57,7 +57,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx, u8 mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt); int mlx5e_rx_res_rss_set_hash_fields(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt, u8 rx_hash_fields); -int mlx5e_rx_res_lro_set_param(struct mlx5e_rx_res *res, struct mlx5e_lro_param *lro_param); +int mlx5e_rx_res_packet_merge_set_param(struct mlx5e_rx_res *res, + struct mlx5e_packet_merge_param *pkt_merge_param); int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 *rss_idx, unsigned int init_nch); int mlx5e_rx_res_rss_destroy(struct mlx5e_rx_res *res, u32 rss_idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c index 857ea0979159..a1afb8585e37 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -70,16 +70,16 @@ void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn, MLX5_SET(tirc, tirc, tunneled_offload_en, inner_ft_support); } -void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, - const struct mlx5e_lro_param *lro_param) +void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder, + const struct mlx5e_packet_merge_param *pkt_merge_param) { void *tirc = mlx5e_tir_builder_get_tirc(builder); const unsigned int rough_max_l2_l3_hdr_sz = 256; if (builder->modify) - MLX5_SET(modify_tir_in, builder->in, bitmask.lro, 1); + MLX5_SET(modify_tir_in, builder->in, bitmask.packet_merge, 1); - if (!lro_param->enabled) + if (pkt_merge_param->type == MLX5E_PACKET_MERGE_NONE) return; MLX5_SET(tirc, tirc, packet_merge_mask, @@ -87,7 +87,7 @@ void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO); MLX5_SET(tirc, tirc, lro_max_ip_payload_size, (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8); - MLX5_SET(tirc, tirc, lro_timeout_period_usecs, lro_param->timeout); + MLX5_SET(tirc, tirc, lro_timeout_period_usecs, pkt_merge_param->timeout); } static int mlx5e_hfunc_to_hw(u8 hfunc) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h index e45149a78ed9..857a84bcd53a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h @@ -18,7 +18,7 @@ struct mlx5e_rss_params_traffic_type { }; struct mlx5e_tir_builder; -struct mlx5e_lro_param; +struct mlx5e_packet_merge_param; struct mlx5e_tir_builder *mlx5e_tir_builder_alloc(bool modify); void mlx5e_tir_builder_free(struct mlx5e_tir_builder *builder); @@ -27,8 +27,8 @@ void mlx5e_tir_builder_clear(struct mlx5e_tir_builder *builder); void mlx5e_tir_builder_build_inline(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqn); void mlx5e_tir_builder_build_rqt(struct mlx5e_tir_builder *builder, u32 tdn, u32 rqtn, bool inner_ft_support); -void mlx5e_tir_builder_build_lro(struct mlx5e_tir_builder *builder, - const struct mlx5e_lro_param *lro_param); +void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder, + const struct mlx5e_packet_merge_param *pkt_merge_param); void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder, const struct mlx5e_rss_params_hash *rss_hash, const struct mlx5e_rss_params_traffic_type *rss_tt, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 25926e581d18..5a46b6e1b9da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1952,8 +1952,8 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable) return -EOPNOTSUPP; if (!mlx5e_striding_rq_possible(mdev, &priv->channels.params)) return -EINVAL; - } else if (priv->channels.params.lro_en) { - netdev_warn(netdev, "Can't set legacy RQ with LRO, disable LRO first\n"); + } else if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) { + netdev_warn(netdev, "Can't set legacy RQ with HW-GRO/LRO, disable them first\n"); return -EINVAL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 81ebf281cdb4..ad0d234632a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -411,7 +411,7 @@ static int flow_get_tirn(struct mlx5e_priv *priv, u32 rss_context, u32 *tirn) { if (fs->flow_type & FLOW_RSS) { - struct mlx5e_lro_param lro_param; + struct mlx5e_packet_merge_param pkt_merge_param; struct mlx5e_rss *rss; u32 flow_type; int err; @@ -426,8 +426,8 @@ static int flow_get_tirn(struct mlx5e_priv *priv, if (tt < 0) return -EINVAL; - lro_param = mlx5e_get_lro_param(&priv->channels.params); - err = mlx5e_rss_obtain_tirn(rss, tt, &lro_param, false, tirn); + pkt_merge_param = priv->channels.params.packet_merge; + err = mlx5e_rss_obtain_tirn(rss, tt, &pkt_merge_param, false, tirn); if (err) return err; eth_rule->rss = rss; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 0e7a8afeb9bd..0c039906a1fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2222,17 +2222,14 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) chs->num = 0; } -static int mlx5e_modify_tirs_lro(struct mlx5e_priv *priv) +static int mlx5e_modify_tirs_packet_merge(struct mlx5e_priv *priv) { struct mlx5e_rx_res *res = priv->rx_res; - struct mlx5e_lro_param lro_param; - lro_param = mlx5e_get_lro_param(&priv->channels.params); - - return mlx5e_rx_res_lro_set_param(res, &lro_param); + return mlx5e_rx_res_packet_merge_set_param(res, &priv->channels.params.packet_merge); } -static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_lro); +static MLX5E_DEFINE_PREACTIVATE_WRAPPER_CTX(mlx5e_modify_tirs_packet_merge); static int mlx5e_set_mtu(struct mlx5_core_dev *mdev, struct mlx5e_params *params, u16 mtu) @@ -3351,16 +3348,25 @@ static int set_feature_lro(struct net_device *netdev, bool enable) } new_params = *cur_params; - new_params.lro_en = enable; - if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) == - mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL)) - reset = false; + if (enable) + new_params.packet_merge.type = MLX5E_PACKET_MERGE_LRO; + else if (new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO) + new_params.packet_merge.type = MLX5E_PACKET_MERGE_NONE; + else + goto out; + + if (!(cur_params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO && + new_params.packet_merge.type == MLX5E_PACKET_MERGE_LRO)) { + if (cur_params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + if (mlx5e_rx_mpwqe_is_linear_skb(mdev, cur_params, NULL) == + mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_params, NULL)) + reset = false; + } } err = mlx5e_safe_switch_params(priv, &new_params, - mlx5e_modify_tirs_lro_ctx, NULL, reset); + mlx5e_modify_tirs_packet_merge_ctx, NULL, reset); out: mutex_unlock(&priv->state_lock); return err; @@ -3687,7 +3693,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, goto out; } - if (params->lro_en) + if (params->packet_merge.type == MLX5E_PACKET_MERGE_LRO) reset = false; if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -4144,8 +4150,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) struct net_device *netdev = priv->netdev; struct mlx5e_params new_params; - if (priv->channels.params.lro_en) { - netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n"); + if (priv->channels.params.packet_merge.type != MLX5E_PACKET_MERGE_NONE) { + netdev_warn(netdev, "can't set XDP while HW-GRO/LRO is on, disable them first\n"); return -EINVAL; } @@ -4402,9 +4408,10 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { /* No XSK params: checking the availability of striding RQ in general. */ if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) - params->lro_en = !slow_pci_heuristic(mdev); + params->packet_merge.type = slow_pci_heuristic(mdev) ? + MLX5E_PACKET_MERGE_NONE : MLX5E_PACKET_MERGE_LRO; } - params->packet_merge_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); + params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ rx_cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ? @@ -4693,7 +4700,6 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; enum mlx5e_rx_res_features features; - struct mlx5e_lro_param lro_param; int err; priv->rx_res = mlx5e_rx_res_alloc(); @@ -4711,9 +4717,9 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) features = MLX5E_RX_RES_FEATURE_XSK | MLX5E_RX_RES_FEATURE_PTP; if (priv->channels.params.tunneled_offload_en) features |= MLX5E_RX_RES_FEATURE_INNER_FT; - lro_param = mlx5e_get_lro_param(&priv->channels.params); err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, features, - priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (err) goto err_close_drop_rq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 0684ac6699b2..5230e0422cae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -793,7 +793,6 @@ int mlx5e_rep_bond_update(struct mlx5e_priv *priv, bool cleanup) static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5e_lro_param lro_param; int err; priv->rx_res = mlx5e_rx_res_alloc(); @@ -808,9 +807,9 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) return err; } - lro_param = mlx5e_get_lro_param(&priv->channels.params); err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, - priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (err) goto err_close_drop_rq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 3b8d8ada1a01..84297cc1b509 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -67,7 +67,7 @@ static void mlx5i_build_nic_params(struct mlx5_core_dev *mdev, MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE : MLX5I_PARAMS_DEFAULT_LOG_RQ_SIZE; - params->lro_en = false; + params->packet_merge.type = MLX5E_PACKET_MERGE_NONE; params->hard_mtu = MLX5_IB_GRH_BYTES + MLX5_IPOIB_HARD_LEN; params->tunneled_offload_en = false; } @@ -356,7 +356,6 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; - struct mlx5e_lro_param lro_param; int err; priv->rx_res = mlx5e_rx_res_alloc(); @@ -371,9 +370,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) goto err_destroy_q_counters; } - lro_param = mlx5e_get_lro_param(&priv->channels.params); err = mlx5e_rx_res_init(priv->rx_res, priv->mdev, 0, - priv->max_nch, priv->drop_rq.rqn, &lro_param, + priv->max_nch, priv->drop_rq.rqn, + &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (err) goto err_close_drop_rq; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index f1c134af5fcf..0bb78c04336c 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -6707,7 +6707,7 @@ struct mlx5_ifc_modify_tir_bitmask_bits { u8 reserved_at_3c[0x1]; u8 hash[0x1]; u8 reserved_at_3e[0x1]; - u8 lro[0x1]; + u8 packet_merge[0x1]; }; struct mlx5_ifc_modify_tir_out_bits { -- cgit v1.2.3 From d7b896acbdcb3ef5dab1fd2f33ba5a8da6ba1dda Mon Sep 17 00:00:00 2001 From: Ben Ben-Ishay Date: Tue, 14 Jul 2020 14:40:32 +0300 Subject: net/mlx5e: Add support to klm_umr_wqe This commit adds the needed definitions for using the klm_umr_wqe. UMR stands for user-mode memory registration, is a mechanism to alter address translation properties of MKEY by posting WorkQueueElement aka WQE on send queue. MKEY stands for memory key, MKEY are used to describe a region in memory that can be later used by HW. KLM stands for {Key, Length, MemVa}, KLM_MKEY is indirect MKEY that enables to map multiple memory spaces with different sizes in unified MKEY. klm_umr_wqe is a UMR that use to update a KLM_MKEY. SHAMPO feature uses KLM_MKEY for memory registration of his header buffer. Signed-off-by: Ben Ben-Ishay Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 24 +++++++++++++++++++++++- include/linux/mlx5/device.h | 1 + 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8c3e7464b30f..98b56d8bddb8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -152,6 +152,25 @@ struct page_pool; #define MLX5E_UMR_WQEBBS \ (DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB)) +#define MLX5E_KLM_UMR_WQE_SZ(sgl_len)\ + (sizeof(struct mlx5e_umr_wqe) +\ + (sizeof(struct mlx5_klm) * (sgl_len))) + +#define MLX5E_KLM_UMR_WQEBBS(klm_entries) \ + (DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_BB)) + +#define MLX5E_KLM_UMR_DS_CNT(klm_entries)\ + (DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_DS)) + +#define MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size)\ + (((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm)) + +#define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\ + ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_ALIGNMENT) + +#define MLX5E_MAX_KLM_PER_WQE(mdev) \ + MLX5E_KLM_ENTRIES_PER_WQE(MLX5E_TX_MPW_MAX_NUM_DS << MLX5_MKEY_BSF_OCTO_SIZE) + #define MLX5E_MSG_LEVEL NETIF_MSG_LINK #define mlx5e_dbg(mlevel, priv, format, ...) \ @@ -217,7 +236,10 @@ struct mlx5e_umr_wqe { struct mlx5_wqe_ctrl_seg ctrl; struct mlx5_wqe_umr_ctrl_seg uctrl; struct mlx5_mkey_seg mkc; - struct mlx5_mtt inline_mtts[0]; + union { + struct mlx5_mtt inline_mtts[0]; + struct mlx5_klm inline_klms[0]; + }; }; enum mlx5e_priv_flag { diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0d30a6184e1d..c920e5932368 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -290,6 +290,7 @@ enum { MLX5_UMR_INLINE = (1 << 7), }; +#define MLX5_UMR_KLM_ALIGNMENT 4 #define MLX5_UMR_MTT_ALIGNMENT 0x40 #define MLX5_UMR_MTT_MASK (MLX5_UMR_MTT_ALIGNMENT - 1) #define MLX5_UMR_MTT_MIN_CHUNK_SIZE MLX5_UMR_MTT_ALIGNMENT -- cgit v1.2.3 From f97d5c2a453e26071e3b0ec12161de57c4a237c4 Mon Sep 17 00:00:00 2001 From: Khalid Manaa Date: Tue, 19 May 2020 15:45:38 +0300 Subject: net/mlx5e: Add handle SHAMPO cqe support This patch adds the new CQE SHAMPO fields: - flush: indicates that we must close the current session and pass the SKB to the network stack. - match: indicates that the current packet matches the oppened session, the packet will be merge into the current SKB. - header_size: the size of the packet headers that written into the headers buffer. - header_entry_index: the entry index in the headers buffer. - data_offset: packets data offset in the WQE. Also new cqe handler is added to handle SHAMPO packets: - The new handler uses CQE SHAMPO fields to build the SKB. CQE's Flush and match fields are not used in this patch, packets are not merged in this patch. Signed-off-by: Khalid Manaa Reviewed-by: Tariq Toukan Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 205 ++++++++++++++++++++---- include/linux/mlx5/device.h | 23 ++- 3 files changed, 194 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 8431cdd8006c..c95b6b65c4de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -943,6 +943,7 @@ struct mlx5e_priv { struct mlx5e_rx_handlers { mlx5e_fp_handle_rx_cqe handle_rx_cqe; mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe; + mlx5e_fp_handle_rx_cqe handle_rx_cqe_mpwqe_shampo; }; extern const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 397a4e769076..68759c8fd31e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -62,10 +62,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w u16 cqe_bcnt, u32 head_offset, u32 page_idx); static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); +static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); const struct mlx5e_rx_handlers mlx5e_rx_handlers_nic = { .handle_rx_cqe = mlx5e_handle_rx_cqe, .handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq, + .handle_rx_cqe_mpwqe_shampo = mlx5e_handle_rx_cqe_mpwrq_shampo, }; static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) @@ -185,8 +187,9 @@ static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq, mlx5e_read_mini_arr_slot(wq, cqd, cqcc); mlx5e_decompress_cqe_no_hash(rq, wq, cqcc); - INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, - mlx5e_handle_rx_cqe, rq, &cqd->title); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe_mpwrq_shampo, mlx5e_handle_rx_cqe, + rq, &cqd->title); } mlx5e_cqes_update_owner(wq, cqcc - wq->cc); wq->cc = cqcc; @@ -206,8 +209,9 @@ static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq, mlx5e_read_title_slot(rq, wq, cc); mlx5e_read_mini_arr_slot(wq, cqd, cc + 1); mlx5e_decompress_cqe(rq, wq, cc); - INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, - mlx5e_handle_rx_cqe, rq, &cqd->title); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe_mpwrq_shampo, mlx5e_handle_rx_cqe, + rq, &cqd->title); cqd->mini_arr_idx++; return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1; @@ -448,13 +452,13 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb, static inline void mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, struct mlx5e_dma_info *dma_info, - int offset_from, u32 headlen) + int offset_from, int dma_offset, u32 headlen) { const void *from = page_address(dma_info->page) + offset_from; /* Aligning len to sizeof(long) optimizes memcpy performance */ unsigned int len = ALIGN(headlen, sizeof(long)); - dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len, + dma_sync_single_for_cpu(pdev, dma_info->addr + dma_offset, len, DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, from, len); } @@ -820,8 +824,8 @@ static void mlx5e_lro_update_tcp_hdr(struct mlx5_cqe64 *cqe, struct tcphdr *tcp) if (tcp_ack) { tcp->ack = 1; - tcp->ack_seq = cqe->lro_ack_seq_num; - tcp->window = cqe->lro_tcp_win; + tcp->ack_seq = cqe->lro.ack_seq_num; + tcp->window = cqe->lro.tcp_win; } } @@ -847,7 +851,7 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, tcp = ip_p + sizeof(struct iphdr); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; - ipv4->ttl = cqe->lro_min_ttl; + ipv4->ttl = cqe->lro.min_ttl; ipv4->tot_len = cpu_to_be16(tot_len); ipv4->check = 0; ipv4->check = ip_fast_csum((unsigned char *)ipv4, @@ -867,7 +871,7 @@ static void mlx5e_lro_update_hdr(struct sk_buff *skb, struct mlx5_cqe64 *cqe, tcp = ip_p + sizeof(struct ipv6hdr); skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; - ipv6->hop_limit = cqe->lro_min_ttl; + ipv6->hop_limit = cqe->lro.min_ttl; ipv6->payload_len = cpu_to_be16(payload_len); mlx5e_lro_update_tcp_hdr(cqe, tcp); @@ -1237,7 +1241,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, } /* copy header */ - mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, headlen); + mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, head_wi->offset, + headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; skb->len += headlen; @@ -1433,6 +1438,30 @@ const struct mlx5e_rx_handlers mlx5e_rx_handlers_rep = { }; #endif +static void +mlx5e_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq, struct mlx5e_dma_info *di, + u32 data_bcnt, u32 data_offset) +{ + net_prefetchw(skb->data); + + while (data_bcnt) { + u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - data_offset, data_bcnt); + unsigned int truesize; + + if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) + truesize = pg_consumed_bytes; + else + truesize = ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); + + mlx5e_add_skb_frag(rq, skb, di, data_offset, + pg_consumed_bytes, truesize); + + data_bcnt -= pg_consumed_bytes; + data_offset = 0; + di++; + } +} + static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, u16 cqe_bcnt, u32 head_offset, u32 page_idx) @@ -1458,20 +1487,9 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w frag_offset -= PAGE_SIZE; } - while (byte_cnt) { - u32 pg_consumed_bytes = - min_t(u32, PAGE_SIZE - frag_offset, byte_cnt); - unsigned int truesize = - ALIGN(pg_consumed_bytes, BIT(rq->mpwqe.log_stride_sz)); - - mlx5e_add_skb_frag(rq, skb, di, frag_offset, - pg_consumed_bytes, truesize); - byte_cnt -= pg_consumed_bytes; - frag_offset = 0; - di++; - } + mlx5e_fill_skb_data(skb, rq, di, byte_cnt, frag_offset); /* copy header */ - mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, headlen); + mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, head_offset, headlen); /* skb linear part was allocated with headlen and aligned to long */ skb->tail += headlen; skb->len += headlen; @@ -1525,6 +1543,123 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, return skb; } +static struct sk_buff * +mlx5e_skb_from_cqe_shampo(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, + struct mlx5_cqe64 *cqe, u16 header_index) +{ + struct mlx5e_dma_info *head = &rq->mpwqe.shampo->info[header_index]; + u16 head_offset = head->addr & (PAGE_SIZE - 1); + u16 head_size = cqe->shampo.header_size; + u16 rx_headroom = rq->buff.headroom; + struct sk_buff *skb = NULL; + void *hdr, *data; + u32 frag_size; + + hdr = page_address(head->page) + head_offset; + data = hdr + rx_headroom; + frag_size = MLX5_SKB_FRAG_SZ(rx_headroom + head_size); + + if (likely(frag_size <= BIT(MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE))) { + /* build SKB around header */ + dma_sync_single_range_for_cpu(rq->pdev, head->addr, 0, frag_size, DMA_FROM_DEVICE); + prefetchw(hdr); + prefetch(data); + skb = mlx5e_build_linear_skb(rq, hdr, frag_size, rx_headroom, head_size); + + if (unlikely(!skb)) + return NULL; + + /* queue up for recycling/reuse */ + page_ref_inc(head->page); + + } else { + /* allocate SKB and copy header for large header */ + skb = napi_alloc_skb(rq->cq.napi, + ALIGN(head_size, sizeof(long))); + if (unlikely(!skb)) { + rq->stats->buff_alloc_err++; + return NULL; + } + + prefetchw(skb->data); + mlx5e_copy_skb_header(rq->pdev, skb, head, + head_offset + rx_headroom, + rx_headroom, head_size); + /* skb linear part was allocated with headlen and aligned to long */ + skb->tail += head_size; + skb->len += head_size; + } + return skb; +} + +static void +mlx5e_free_rx_shampo_hd_entry(struct mlx5e_rq *rq, u16 header_index) +{ + struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo; + u64 addr = shampo->info[header_index].addr; + + if (((header_index + 1) & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) == 0) { + shampo->info[header_index].addr = ALIGN_DOWN(addr, PAGE_SIZE); + mlx5e_page_release(rq, &shampo->info[header_index], true); + } + bitmap_clear(shampo->bitmap, header_index, 1); +} + +static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + u16 data_bcnt = mpwrq_get_cqe_byte_cnt(cqe) - cqe->shampo.header_size; + u16 header_index = be16_to_cpu(cqe->shampo.header_entry_index); + u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset); + u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); + u32 data_offset = wqe_offset & (PAGE_SIZE - 1); + u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe); + u16 wqe_id = be16_to_cpu(cqe->wqe_id); + u32 page_idx = wqe_offset >> PAGE_SHIFT; + struct mlx5e_rx_wqe_ll *wqe; + struct sk_buff *skb = NULL; + struct mlx5e_dma_info *di; + struct mlx5e_mpw_info *wi; + struct mlx5_wq_ll *wq; + + wi = &rq->mpwqe.info[wqe_id]; + wi->consumed_strides += cstrides; + + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + trigger_report(rq, cqe); + rq->stats->wqe_err++; + goto mpwrq_cqe_out; + } + + if (unlikely(mpwrq_is_filler_cqe(cqe))) { + struct mlx5e_rq_stats *stats = rq->stats; + + stats->mpwqe_filler_cqes++; + stats->mpwqe_filler_strides += cstrides; + goto mpwrq_cqe_out; + } + + skb = mlx5e_skb_from_cqe_shampo(rq, wi, cqe, header_index); + + if (unlikely(!skb)) + goto free_hd_entry; + + di = &wi->umr.dma_info[page_idx]; + mlx5e_fill_skb_data(skb, rq, di, data_bcnt, data_offset); + + mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); + napi_gro_receive(rq->cq.napi, skb); +free_hd_entry: + mlx5e_free_rx_shampo_hd_entry(rq, header_index); +mpwrq_cqe_out: + if (likely(wi->consumed_strides < rq->mpwqe.num_strides)) + return; + + wq = &rq->mpwqe.wq; + wqe = mlx5_wq_ll_get_wqe(wq, wqe_id); + mlx5e_free_rx_mpwqe(rq, wi, true); + mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index); +} + static void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe); @@ -1617,8 +1752,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) mlx5_cqwq_pop(cqwq); - INDIRECT_CALL_2(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, - mlx5e_handle_rx_cqe, rq, cqe); + INDIRECT_CALL_3(rq->handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq, + mlx5e_handle_rx_cqe, mlx5e_handle_rx_cqe_mpwrq_shampo, + rq, cqe); } while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq))); out: @@ -1822,15 +1958,24 @@ int mlx5e_rq_set_handlers(struct mlx5e_rq *rq, struct mlx5e_params *params, bool rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; - rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe; if (mlx5_fpga_is_ipsec_device(mdev)) { netdev_err(netdev, "MPWQE RQ with Innova IPSec offload not supported\n"); return -EINVAL; } - if (!rq->handle_rx_cqe) { - netdev_err(netdev, "RX handler of MPWQE RQ is not set\n"); - return -EINVAL; + if (params->packet_merge.type == MLX5E_PACKET_MERGE_SHAMPO) { + rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe_shampo; + if (!rq->handle_rx_cqe) { + netdev_err(netdev, "RX handler of SHAMPO MPWQE RQ is not set\n"); + return -EINVAL; + } + } else { + rq->handle_rx_cqe = priv->profile->rx_handlers->handle_rx_cqe_mpwqe; + if (!rq->handle_rx_cqe) { + netdev_err(netdev, "RX handler of MPWQE RQ is not set\n"); + return -EINVAL; + } } + break; default: /* MLX5_WQ_TYPE_CYCLIC */ rq->wqe.skb_from_cqe = xsk ? diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index c920e5932368..56bcf95d4ab7 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -800,10 +800,23 @@ struct mlx5_cqe64 { u8 tls_outer_l3_tunneled; u8 rsvd0; __be16 wqe_id; - u8 lro_tcppsh_abort_dupack; - u8 lro_min_ttl; - __be16 lro_tcp_win; - __be32 lro_ack_seq_num; + union { + struct { + u8 tcppsh_abort_dupack; + u8 min_ttl; + __be16 tcp_win; + __be32 ack_seq_num; + } lro; + struct { + u8 reserved0:1; + u8 match:1; + u8 flush:1; + u8 reserved3:5; + u8 header_size; + __be16 header_entry_index; + __be32 data_offset; + } shampo; + }; __be32 rss_hash_result; u8 rss_hash_type; u8 ml_path; @@ -873,7 +886,7 @@ static inline u8 get_cqe_opcode(struct mlx5_cqe64 *cqe) static inline u8 get_cqe_lro_tcppsh(struct mlx5_cqe64 *cqe) { - return (cqe->lro_tcppsh_abort_dupack >> 6) & 1; + return (cqe->lro.tcppsh_abort_dupack >> 6) & 1; } static inline u8 get_cqe_l4_hdr_type(struct mlx5_cqe64 *cqe) -- cgit v1.2.3 From a2247f19ee1c5ad75ef095cdfb909a3244b88aa8 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 27 Oct 2021 11:22:19 +0900 Subject: block: Add independent access ranges support The Concurrent Positioning Ranges VPD page (for SCSI) and data log page (for ATA) contain parameters describing the set of contiguous LBAs that can be served independently by a single LUN multi-actuator hard-disk. Similarly, a logically defined block device composed of multiple disks can in some cases execute requests directed at different sector ranges in parallel. A dm-linear device aggregating 2 block devices together is an example. This patch implements support for exposing a block device independent access ranges to the user through sysfs to allow optimizing device accesses to increase performance. To describe the set of independent sector ranges of a device (actuators of a multi-actuator HDDs or table entries of a dm-linear device), The type struct blk_independent_access_ranges is introduced. This structure describes the sector ranges using an array of struct blk_independent_access_range structures. This range structure defines the start sector and number of sectors of the access range. The ranges in the array cannot overlap and must contain all sectors within the device capacity. The function disk_set_independent_access_ranges() allows a device driver to signal to the block layer that a device has multiple independent access ranges. In this case, a struct blk_independent_access_ranges is attached to the device request queue by the function disk_set_independent_access_ranges(). The function disk_alloc_independent_access_ranges() is provided for drivers to allocate this structure. struct blk_independent_access_ranges contains kobjects (struct kobject) to expose to the user through sysfs the set of independent access ranges supported by a device. When the device is initialized, sysfs registration of the ranges information is done from blk_register_queue() using the block layer internal function disk_register_independent_access_ranges(). If a driver calls disk_set_independent_access_ranges() for a registered queue, e.g. when a device is revalidated, disk_set_independent_access_ranges() will execute disk_register_independent_access_ranges() to update the sysfs attribute files. The sysfs file structure created starts from the independent_access_ranges sub-directory and contains the start sector and number of sectors of each range, with the information for each range grouped in numbered sub-directories. E.g. for a dual actuator HDD, the user sees: $ tree /sys/block/sdk/queue/independent_access_ranges/ /sys/block/sdk/queue/independent_access_ranges/ |-- 0 | |-- nr_sectors | `-- sector `-- 1 |-- nr_sectors `-- sector For a regular device with a single access range, the independent_access_ranges sysfs directory does not exist. Device revalidation may lead to changes to this structure and to the attribute values. When manipulated, the queue sysfs_lock and sysfs_dir_lock mutexes are held for atomicity, similarly to how the blk-mq and elevator sysfs queue sub-directories are protected. The code related to the management of independent access ranges is added in the new file block/blk-ia-ranges.c. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Martin K. Petersen Reviewed-by: Keith Busch Link: https://lore.kernel.org/r/20211027022223.183838-2-damien.lemoal@wdc.com Signed-off-by: Jens Axboe --- block/Makefile | 2 +- block/blk-ia-ranges.c | 348 +++++++++++++++++++++++++++++++++++++++++++++++++ block/blk-sysfs.c | 26 ++-- block/blk.h | 4 + include/linux/blkdev.h | 39 ++++++ 5 files changed, 410 insertions(+), 9 deletions(-) create mode 100644 block/blk-ia-ranges.c (limited to 'include/linux') diff --git a/block/Makefile b/block/Makefile index 602f7f47b7b6..44df57e562bf 100644 --- a/block/Makefile +++ b/block/Makefile @@ -9,7 +9,7 @@ obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \ genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \ - disk-events.o + disk-events.o blk-ia-ranges.o obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c new file mode 100644 index 000000000000..c246c425d0d7 --- /dev/null +++ b/block/blk-ia-ranges.c @@ -0,0 +1,348 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Block device concurrent positioning ranges. + * + * Copyright (C) 2021 Western Digital Corporation or its Affiliates. + */ +#include +#include +#include +#include + +#include "blk.h" + +static ssize_t +blk_ia_range_sector_show(struct blk_independent_access_range *iar, + char *buf) +{ + return sprintf(buf, "%llu\n", iar->sector); +} + +static ssize_t +blk_ia_range_nr_sectors_show(struct blk_independent_access_range *iar, + char *buf) +{ + return sprintf(buf, "%llu\n", iar->nr_sectors); +} + +struct blk_ia_range_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct blk_independent_access_range *iar, char *buf); +}; + +static struct blk_ia_range_sysfs_entry blk_ia_range_sector_entry = { + .attr = { .name = "sector", .mode = 0444 }, + .show = blk_ia_range_sector_show, +}; + +static struct blk_ia_range_sysfs_entry blk_ia_range_nr_sectors_entry = { + .attr = { .name = "nr_sectors", .mode = 0444 }, + .show = blk_ia_range_nr_sectors_show, +}; + +static struct attribute *blk_ia_range_attrs[] = { + &blk_ia_range_sector_entry.attr, + &blk_ia_range_nr_sectors_entry.attr, + NULL, +}; +ATTRIBUTE_GROUPS(blk_ia_range); + +static ssize_t blk_ia_range_sysfs_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct blk_ia_range_sysfs_entry *entry = + container_of(attr, struct blk_ia_range_sysfs_entry, attr); + struct blk_independent_access_range *iar = + container_of(kobj, struct blk_independent_access_range, kobj); + ssize_t ret; + + mutex_lock(&iar->queue->sysfs_lock); + ret = entry->show(iar, buf); + mutex_unlock(&iar->queue->sysfs_lock); + + return ret; +} + +static const struct sysfs_ops blk_ia_range_sysfs_ops = { + .show = blk_ia_range_sysfs_show, +}; + +/* + * Independent access range entries are not freed individually, but alltogether + * with struct blk_independent_access_ranges and its array of ranges. Since + * kobject_add() takes a reference on the parent kobject contained in + * struct blk_independent_access_ranges, the array of independent access range + * entries cannot be freed until kobject_del() is called for all entries. + * So we do not need to do anything here, but still need this no-op release + * operation to avoid complaints from the kobject code. + */ +static void blk_ia_range_sysfs_nop_release(struct kobject *kobj) +{ +} + +static struct kobj_type blk_ia_range_ktype = { + .sysfs_ops = &blk_ia_range_sysfs_ops, + .default_groups = blk_ia_range_groups, + .release = blk_ia_range_sysfs_nop_release, +}; + +/* + * This will be executed only after all independent access range entries are + * removed with kobject_del(), at which point, it is safe to free everything, + * including the array of ranges. + */ +static void blk_ia_ranges_sysfs_release(struct kobject *kobj) +{ + struct blk_independent_access_ranges *iars = + container_of(kobj, struct blk_independent_access_ranges, kobj); + + kfree(iars); +} + +static struct kobj_type blk_ia_ranges_ktype = { + .release = blk_ia_ranges_sysfs_release, +}; + +/** + * disk_register_ia_ranges - register with sysfs a set of independent + * access ranges + * @disk: Target disk + * @new_iars: New set of independent access ranges + * + * Register with sysfs a set of independent access ranges for @disk. + * If @new_iars is not NULL, this set of ranges is registered and the old set + * specified by q->ia_ranges is unregistered. Otherwise, q->ia_ranges is + * registered if it is not already. + */ +int disk_register_independent_access_ranges(struct gendisk *disk, + struct blk_independent_access_ranges *new_iars) +{ + struct request_queue *q = disk->queue; + struct blk_independent_access_ranges *iars; + int i, ret; + + lockdep_assert_held(&q->sysfs_dir_lock); + lockdep_assert_held(&q->sysfs_lock); + + /* If a new range set is specified, unregister the old one */ + if (new_iars) { + if (q->ia_ranges) + disk_unregister_independent_access_ranges(disk); + q->ia_ranges = new_iars; + } + + iars = q->ia_ranges; + if (!iars) + return 0; + + /* + * At this point, iars is the new set of sector access ranges that needs + * to be registered with sysfs. + */ + WARN_ON(iars->sysfs_registered); + ret = kobject_init_and_add(&iars->kobj, &blk_ia_ranges_ktype, + &q->kobj, "%s", "independent_access_ranges"); + if (ret) { + q->ia_ranges = NULL; + kfree(iars); + return ret; + } + + for (i = 0; i < iars->nr_ia_ranges; i++) { + iars->ia_range[i].queue = q; + ret = kobject_init_and_add(&iars->ia_range[i].kobj, + &blk_ia_range_ktype, &iars->kobj, + "%d", i); + if (ret) { + while (--i >= 0) + kobject_del(&iars->ia_range[i].kobj); + kobject_del(&iars->kobj); + kobject_put(&iars->kobj); + return ret; + } + } + + iars->sysfs_registered = true; + + return 0; +} + +void disk_unregister_independent_access_ranges(struct gendisk *disk) +{ + struct request_queue *q = disk->queue; + struct blk_independent_access_ranges *iars = q->ia_ranges; + int i; + + lockdep_assert_held(&q->sysfs_dir_lock); + lockdep_assert_held(&q->sysfs_lock); + + if (!iars) + return; + + if (iars->sysfs_registered) { + for (i = 0; i < iars->nr_ia_ranges; i++) + kobject_del(&iars->ia_range[i].kobj); + kobject_del(&iars->kobj); + kobject_put(&iars->kobj); + } else { + kfree(iars); + } + + q->ia_ranges = NULL; +} + +static struct blk_independent_access_range * +disk_find_ia_range(struct blk_independent_access_ranges *iars, + sector_t sector) +{ + struct blk_independent_access_range *iar; + int i; + + for (i = 0; i < iars->nr_ia_ranges; i++) { + iar = &iars->ia_range[i]; + if (sector >= iar->sector && + sector < iar->sector + iar->nr_sectors) + return iar; + } + + return NULL; +} + +static bool disk_check_ia_ranges(struct gendisk *disk, + struct blk_independent_access_ranges *iars) +{ + struct blk_independent_access_range *iar, *tmp; + sector_t capacity = get_capacity(disk); + sector_t sector = 0; + int i; + + /* + * While sorting the ranges in increasing LBA order, check that the + * ranges do not overlap, that there are no sector holes and that all + * sectors belong to one range. + */ + for (i = 0; i < iars->nr_ia_ranges; i++) { + tmp = disk_find_ia_range(iars, sector); + if (!tmp || tmp->sector != sector) { + pr_warn("Invalid non-contiguous independent access ranges\n"); + return false; + } + + iar = &iars->ia_range[i]; + if (tmp != iar) { + swap(iar->sector, tmp->sector); + swap(iar->nr_sectors, tmp->nr_sectors); + } + + sector += iar->nr_sectors; + } + + if (sector != capacity) { + pr_warn("Independent access ranges do not match disk capacity\n"); + return false; + } + + return true; +} + +static bool disk_ia_ranges_changed(struct gendisk *disk, + struct blk_independent_access_ranges *new) +{ + struct blk_independent_access_ranges *old = disk->queue->ia_ranges; + int i; + + if (!old) + return true; + + if (old->nr_ia_ranges != new->nr_ia_ranges) + return true; + + for (i = 0; i < old->nr_ia_ranges; i++) { + if (new->ia_range[i].sector != old->ia_range[i].sector || + new->ia_range[i].nr_sectors != old->ia_range[i].nr_sectors) + return true; + } + + return false; +} + +/** + * disk_alloc_independent_access_ranges - Allocate an independent access ranges + * data structure + * @disk: target disk + * @nr_ia_ranges: Number of independent access ranges + * + * Allocate a struct blk_independent_access_ranges structure with @nr_ia_ranges + * access range descriptors. + */ +struct blk_independent_access_ranges * +disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges) +{ + struct blk_independent_access_ranges *iars; + + iars = kzalloc_node(struct_size(iars, ia_range, nr_ia_ranges), + GFP_KERNEL, disk->queue->node); + if (iars) + iars->nr_ia_ranges = nr_ia_ranges; + return iars; +} +EXPORT_SYMBOL_GPL(disk_alloc_independent_access_ranges); + +/** + * disk_set_independent_access_ranges - Set a disk independent access ranges + * @disk: target disk + * @iars: independent access ranges structure + * + * Set the independent access ranges information of the request queue + * of @disk to @iars. If @iars is NULL and the independent access ranges + * structure already set is cleared. If there are no differences between + * @iars and the independent access ranges structure already set, @iars + * is freed. + */ +void disk_set_independent_access_ranges(struct gendisk *disk, + struct blk_independent_access_ranges *iars) +{ + struct request_queue *q = disk->queue; + + if (WARN_ON_ONCE(iars && !iars->nr_ia_ranges)) { + kfree(iars); + iars = NULL; + } + + mutex_lock(&q->sysfs_dir_lock); + mutex_lock(&q->sysfs_lock); + + if (iars) { + if (!disk_check_ia_ranges(disk, iars)) { + kfree(iars); + iars = NULL; + goto reg; + } + + if (!disk_ia_ranges_changed(disk, iars)) { + kfree(iars); + goto unlock; + } + } + + /* + * This may be called for a registered queue. E.g. during a device + * revalidation. If that is the case, we need to unregister the old + * set of independent access ranges and register the new set. If the + * queue is not registered, registration of the device request queue + * will register the independent access ranges, so only swap in the + * new set and free the old one. + */ +reg: + if (blk_queue_registered(q)) { + disk_register_independent_access_ranges(disk, iars); + } else { + swap(q->ia_ranges, iars); + kfree(iars); + } + +unlock: + mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->sysfs_dir_lock); +} +EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 36f14d658e81..cef1f713370b 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -873,16 +873,15 @@ int blk_register_queue(struct gendisk *disk) } mutex_lock(&q->sysfs_lock); + + ret = disk_register_independent_access_ranges(disk, NULL); + if (ret) + goto put_dev; + if (q->elevator) { ret = elv_register_queue(q, false); - if (ret) { - mutex_unlock(&q->sysfs_lock); - mutex_unlock(&q->sysfs_dir_lock); - kobject_del(&q->kobj); - blk_trace_remove_sysfs(dev); - kobject_put(&dev->kobj); - return ret; - } + if (ret) + goto put_dev; } blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); @@ -913,6 +912,16 @@ unlock: percpu_ref_switch_to_percpu(&q->q_usage_counter); } + return ret; + +put_dev: + disk_unregister_independent_access_ranges(disk); + mutex_unlock(&q->sysfs_lock); + mutex_unlock(&q->sysfs_dir_lock); + kobject_del(&q->kobj); + blk_trace_remove_sysfs(dev); + kobject_put(&dev->kobj); + return ret; } @@ -958,6 +967,7 @@ void blk_unregister_queue(struct gendisk *disk) mutex_lock(&q->sysfs_lock); if (q->elevator) elv_unregister_queue(q); + disk_unregister_independent_access_ranges(disk); mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_dir_lock); diff --git a/block/blk.h b/block/blk.h index 6a039e6c7d07..7afffd548daf 100644 --- a/block/blk.h +++ b/block/blk.h @@ -454,4 +454,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); extern const struct address_space_operations def_blk_aops; +int disk_register_independent_access_ranges(struct gendisk *disk, + struct blk_independent_access_ranges *new_iars); +void disk_unregister_independent_access_ranges(struct gendisk *disk); + #endif /* BLK_INTERNAL_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f72ccb2829db..6d95a4b36cfa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -150,6 +150,34 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, #endif /* CONFIG_BLK_DEV_ZONED */ +/* + * Independent access ranges: struct blk_independent_access_range describes + * a range of contiguous sectors that can be accessed using device command + * execution resources that are independent from the resources used for + * other access ranges. This is typically found with single-LUN multi-actuator + * HDDs where each access range is served by a different set of heads. + * The set of independent ranges supported by the device is defined using + * struct blk_independent_access_ranges. The independent ranges must not overlap + * and must include all sectors within the disk capacity (no sector holes + * allowed). + * For a device with multiple ranges, requests targeting sectors in different + * ranges can be executed in parallel. A request can straddle an access range + * boundary. + */ +struct blk_independent_access_range { + struct kobject kobj; + struct request_queue *queue; + sector_t sector; + sector_t nr_sectors; +}; + +struct blk_independent_access_ranges { + struct kobject kobj; + bool sysfs_registered; + unsigned int nr_ia_ranges; + struct blk_independent_access_range ia_range[]; +}; + struct request_queue { struct request *last_merge; struct elevator_queue *elevator; @@ -331,6 +359,12 @@ struct request_queue { #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; + + /* + * Independent sector access ranges. This is always NULL for + * devices that do not have multiple independent access ranges. + */ + struct blk_independent_access_ranges *ia_ranges; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ @@ -698,6 +732,11 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); +struct blk_independent_access_ranges * +disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges); +void disk_set_independent_access_ranges(struct gendisk *disk, + struct blk_independent_access_ranges *iars); + /* * Elevator features for blk_queue_required_elevator_features: */ -- cgit v1.2.3 From fe22e1c2f705676a705d821301fc52eecc2fe055 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 27 Oct 2021 11:22:21 +0900 Subject: libata: support concurrent positioning ranges log Add support to discover if an ATA device supports the Concurrent Positioning Ranges data log (address 0x47), indicating that the device is capable of seeking to multiple different locations in parallel using multiple actuators serving different LBA ranges. Also add support to translate the concurrent positioning ranges log into its equivalent Concurrent Positioning Ranges VPD page B9h in libata-scsi.c. The format of the Concurrent Positioning Ranges Log is defined in ACS-5 r9. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen Reviewed-by: Keith Busch Link: https://lore.kernel.org/r/20211027022223.183838-4-damien.lemoal@wdc.com Signed-off-by: Jens Axboe --- drivers/ata/libata-core.c | 57 +++++++++++++++++++++++++++++++++++++++++++++-- drivers/ata/libata-scsi.c | 48 +++++++++++++++++++++++++++++++-------- include/linux/ata.h | 1 + include/linux/libata.h | 15 +++++++++++++ 4 files changed, 110 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index eed65311b5d1..75f1a6cd6621 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2459,18 +2459,70 @@ static void ata_dev_config_devslp(struct ata_device *dev) } } +static void ata_dev_config_cpr(struct ata_device *dev) +{ + unsigned int err_mask; + size_t buf_len; + int i, nr_cpr = 0; + struct ata_cpr_log *cpr_log = NULL; + u8 *desc, *buf = NULL; + + if (!ata_identify_page_supported(dev, + ATA_LOG_CONCURRENT_POSITIONING_RANGES)) + goto out; + + /* + * Read IDENTIFY DEVICE data log, page 0x47 + * (concurrent positioning ranges). We can have at most 255 32B range + * descriptors plus a 64B header. + */ + buf_len = (64 + 255 * 32 + 511) & ~511; + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) + goto out; + + err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, + ATA_LOG_CONCURRENT_POSITIONING_RANGES, + buf, buf_len >> 9); + if (err_mask) + goto out; + + nr_cpr = buf[0]; + if (!nr_cpr) + goto out; + + cpr_log = kzalloc(struct_size(cpr_log, cpr, nr_cpr), GFP_KERNEL); + if (!cpr_log) + goto out; + + cpr_log->nr_cpr = nr_cpr; + desc = &buf[64]; + for (i = 0; i < nr_cpr; i++, desc += 32) { + cpr_log->cpr[i].num = desc[0]; + cpr_log->cpr[i].num_storage_elements = desc[1]; + cpr_log->cpr[i].start_lba = get_unaligned_le64(&desc[8]); + cpr_log->cpr[i].num_lbas = get_unaligned_le64(&desc[16]); + } + +out: + swap(dev->cpr_log, cpr_log); + kfree(cpr_log); + kfree(buf); +} + static void ata_dev_print_features(struct ata_device *dev) { if (!(dev->flags & ATA_DFLAG_FEATURES_MASK)) return; ata_dev_info(dev, - "Features:%s%s%s%s%s\n", + "Features:%s%s%s%s%s%s\n", dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "", dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "", dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "", dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "", - dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : ""); + dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "", + dev->cpr_log ? " CPR" : ""); } /** @@ -2634,6 +2686,7 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_sense_reporting(dev); ata_dev_config_zac(dev); ata_dev_config_trusted(dev); + ata_dev_config_cpr(dev); dev->cdb_len = 32; if (ata_msg_drv(ap) && print_info) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 1fb4611f7eeb..15a279f773c7 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1895,7 +1895,7 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) */ static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf) { - int num_pages; + int i, num_pages = 0; static const u8 pages[] = { 0x00, /* page 0x00, this page */ 0x80, /* page 0x80, unit serial no page */ @@ -1905,13 +1905,17 @@ static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf) 0xb1, /* page 0xb1, block device characteristics page */ 0xb2, /* page 0xb2, thin provisioning page */ 0xb6, /* page 0xb6, zoned block device characteristics */ + 0xb9, /* page 0xb9, concurrent positioning ranges */ }; - num_pages = sizeof(pages); - if (!(args->dev->flags & ATA_DFLAG_ZAC)) - num_pages--; + for (i = 0; i < sizeof(pages); i++) { + if (pages[i] == 0xb6 && + !(args->dev->flags & ATA_DFLAG_ZAC)) + continue; + rbuf[num_pages + 4] = pages[i]; + num_pages++; + } rbuf[3] = num_pages; /* number of supported VPD pages */ - memcpy(rbuf + 4, pages, num_pages); return 0; } @@ -2121,6 +2125,26 @@ static unsigned int ata_scsiop_inq_b6(struct ata_scsi_args *args, u8 *rbuf) return 0; } +static unsigned int ata_scsiop_inq_b9(struct ata_scsi_args *args, u8 *rbuf) +{ + struct ata_cpr_log *cpr_log = args->dev->cpr_log; + u8 *desc = &rbuf[64]; + int i; + + /* SCSI Concurrent Positioning Ranges VPD page: SBC-5 rev 1 or later */ + rbuf[1] = 0xb9; + put_unaligned_be16(64 + (int)cpr_log->nr_cpr * 32 - 4, &rbuf[3]); + + for (i = 0; i < cpr_log->nr_cpr; i++, desc += 32) { + desc[0] = cpr_log->cpr[i].num; + desc[1] = cpr_log->cpr[i].num_storage_elements; + put_unaligned_be64(cpr_log->cpr[i].start_lba, &desc[8]); + put_unaligned_be64(cpr_log->cpr[i].num_lbas, &desc[16]); + } + + return 0; +} + /** * modecpy - Prepare response for MODE SENSE * @dest: output buffer @@ -4120,11 +4144,17 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b2); break; case 0xb6: - if (dev->flags & ATA_DFLAG_ZAC) { + if (dev->flags & ATA_DFLAG_ZAC) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b6); - break; - } - fallthrough; + else + ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); + break; + case 0xb9: + if (dev->cpr_log) + ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b9); + else + ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); + break; default: ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); break; diff --git a/include/linux/ata.h b/include/linux/ata.h index 1b44f40c7700..199e47e97d64 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -329,6 +329,7 @@ enum { ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, diff --git a/include/linux/libata.h b/include/linux/libata.h index c0c64f03e107..236ec689056a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -676,6 +676,18 @@ struct ata_ering { struct ata_ering_entry ring[ATA_ERING_SIZE]; }; +struct ata_cpr { + u8 num; + u8 num_storage_elements; + u64 start_lba; + u64 num_lbas; +}; + +struct ata_cpr_log { + u8 nr_cpr; + struct ata_cpr cpr[]; +}; + struct ata_device { struct ata_link *link; unsigned int devno; /* 0 or 1 */ @@ -735,6 +747,9 @@ struct ata_device { u32 zac_zones_optimal_nonseq; u32 zac_zones_max_open; + /* Concurrent positioning ranges */ + struct ata_cpr_log *cpr_log; + /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ -- cgit v1.2.3 From 785d584c30ffc1224027536fe55bdc15ee509f14 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 18 Oct 2021 17:21:37 +0200 Subject: nvme: add new discovery log page entry definitions TP8014 adds a new SUBTYPE value and a new field EFLAGS for the discovery log page entry. Signed-off-by: Hannes Reinecke Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 357482dedb59..855dd9b3e84b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -27,8 +27,14 @@ #define NVME_NSID_ALL 0xffffffff enum nvme_subsys_type { - NVME_NQN_DISC = 1, /* Discovery type target subsystem */ - NVME_NQN_NVME = 2, /* NVME type target subsystem */ + /* Referral to another discovery type target subsystem */ + NVME_NQN_DISC = 1, + + /* NVME type target subsystem */ + NVME_NQN_NVME = 2, + + /* Current discovery type target subsystem */ + NVME_NQN_CURR = 3, }; enum nvme_ctrl_type { @@ -1312,6 +1318,12 @@ struct nvmf_common_command { #define MAX_DISC_LOGS 255 +/* Discovery log page entry flags (EFLAGS): */ +enum { + NVME_DISC_EFLAGS_EPCSD = (1 << 1), + NVME_DISC_EFLAGS_DUPRETINFO = (1 << 0), +}; + /* Discovery log page entry */ struct nvmf_disc_rsp_page_entry { __u8 trtype; @@ -1321,7 +1333,8 @@ struct nvmf_disc_rsp_page_entry { __le16 portid; __le16 cntlid; __le16 asqsz; - __u8 resv8[22]; + __le16 eflags; + __u8 resv10[20]; char trsvcid[NVMF_TRSVCID_SIZE]; __u8 resv64[192]; char subnqn[NVMF_NQN_FIELD_LEN]; -- cgit v1.2.3 From 33f98a9798f55fd77c36ce79d8cfa5329e55a789 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 13 Oct 2021 10:57:41 -0700 Subject: x86/boot/compressed: Avoid duplicate malloc() implementations The early malloc() and free() implementation in include/linux/decompress/mm.h (which is also included by the static decompressors) is static. This is fine when the only thing interested in using malloc() is the decompression code, but the x86 early boot environment may use malloc() in a couple places, leading to a potential collision when the static copies of the available memory region ("malloc_ptr") gets reset to the global "free_mem_ptr" value. As it happened, the existing usage pattern was accidentally safe because each user did 1 malloc() and 1 free() before returning and were not nested: extract_kernel() (misc.c) choose_random_location() (kaslr.c) mem_avoid_init() handle_mem_options() malloc() ... free() ... parse_elf() (misc.c) malloc() ... free() Once the future FGKASLR series is added, however, it will insert additional malloc() calls local to fgkaslr.c in the middle of parse_elf()'s malloc()/free() pair: parse_elf() (misc.c) malloc() if (...) { layout_randomized_image(output, &ehdr, phdrs); malloc() <- boom ... else layout_image(output, &ehdr, phdrs); free() To avoid collisions, there must be a single implementation of malloc(). Adjust include/linux/decompress/mm.h so that visibility can be controlled, provide prototypes in misc.h, and implement the functions in misc.c. This also results in a small size savings: $ size vmlinux.before vmlinux.after text data bss dec hex filename 8842314 468 178320 9021102 89a6ae vmlinux.before 8842240 468 178320 9021028 89a664 vmlinux.after Signed-off-by: Kees Cook Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211013175742.1197608-4-keescook@chromium.org --- arch/x86/boot/compressed/kaslr.c | 4 ---- arch/x86/boot/compressed/misc.c | 3 +++ arch/x86/boot/compressed/misc.h | 2 ++ include/linux/decompress/mm.h | 12 ++++++++++-- 4 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 67c3208b668a..411b268bc0a2 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -32,10 +32,6 @@ #include #include -/* Macros used by the included decompressor code below. */ -#define STATIC -#include - #define _SETUP #include /* For COMMAND_LINE_SIZE */ #undef _SETUP diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 743f13ea25c1..a4339cb2d247 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -28,6 +28,9 @@ /* Macros used by the included decompressor code below. */ #define STATIC static +/* Define an externally visible malloc()/free(). */ +#define MALLOC_VISIBLE +#include /* * Provide definitions of memzero and memmove as some of the decompressors will diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 31139256859f..975ef4ae7395 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -44,6 +44,8 @@ extern char _head[], _end[]; /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; +void *malloc(int size); +void free(void *where); extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h index 868e9eacd69e..9192986b1a73 100644 --- a/include/linux/decompress/mm.h +++ b/include/linux/decompress/mm.h @@ -25,13 +25,21 @@ #define STATIC_RW_DATA static #endif +/* + * When an architecture needs to share the malloc()/free() implementation + * between compilation units, it needs to have non-local visibility. + */ +#ifndef MALLOC_VISIBLE +#define MALLOC_VISIBLE static +#endif + /* A trivial malloc implementation, adapted from * malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994 */ STATIC_RW_DATA unsigned long malloc_ptr; STATIC_RW_DATA int malloc_count; -static void *malloc(int size) +MALLOC_VISIBLE void *malloc(int size) { void *p; @@ -52,7 +60,7 @@ static void *malloc(int size) return p; } -static void free(void *where) +MALLOC_VISIBLE void free(void *where) { malloc_count--; if (!malloc_count) -- cgit v1.2.3 From 9baf93d68bcc3d0a6042283b82603c076e25e4f5 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:16 -0300 Subject: fsnotify: pass data_type to fsnotify_name() Align the arguments of fsnotify_name() to those of fsnotify(). Link: https://lore.kernel.org/r/20211025192746.66445-2-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 12d3a7d308ab..d1144d7c3536 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -26,20 +26,21 @@ * FS_EVENT_ON_CHILD mask on the parent inode and will not be reported if only * the child is interested and not the parent. */ -static inline void fsnotify_name(struct inode *dir, __u32 mask, - struct inode *child, - const struct qstr *name, u32 cookie) +static inline int fsnotify_name(__u32 mask, const void *data, int data_type, + struct inode *dir, const struct qstr *name, + u32 cookie) { if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0) - return; + return 0; - fsnotify(mask, child, FSNOTIFY_EVENT_INODE, dir, name, NULL, cookie); + return fsnotify(mask, data, data_type, dir, name, NULL, cookie); } static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(dir, mask, d_inode(dentry), &dentry->d_name, 0); + fsnotify_name(mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, + dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -154,8 +155,10 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, new_dir_mask |= FS_ISDIR; } - fsnotify_name(old_dir, old_dir_mask, source, old_name, fs_cookie); - fsnotify_name(new_dir, new_dir_mask, source, new_name, fs_cookie); + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, + old_dir, old_name, fs_cookie); + fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, + new_dir, new_name, fs_cookie); if (target) fsnotify_link_count(target); @@ -209,7 +212,8 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, fsnotify_link_count(inode); audit_inode_child(dir, new_dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_name(dir, FS_CREATE, inode, &new_dentry->d_name, 0); + fsnotify_name(FS_CREATE, inode, FSNOTIFY_EVENT_INODE, + dir, &new_dentry->d_name, 0); } /* -- cgit v1.2.3 From fd5a3ff49a19aa69e2bc1e26e98037c2d778e61a Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:17 -0300 Subject: fsnotify: pass dentry instead of inode data Define a new data type to pass for event - FSNOTIFY_EVENT_DENTRY. Use it to pass the dentry instead of it's ->d_inode where available. This is needed in preparation to the refactor to retrieve the super block from the data field. In some cases (i.e. mkdir in kernfs), the data inode comes from a negative dentry, such that no super block information would be available. By receiving the dentry itself, instead of the inode, fsnotify can derive the super block even on these cases. Link: https://lore.kernel.org/r/20211025192746.66445-3-krisman@collabora.com Reviewed-by: Jan Kara Signed-off-by: Amir Goldstein [Expand explanation in commit message] Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 5 ++--- include/linux/fsnotify_backend.h | 16 ++++++++++++++++ 2 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index d1144d7c3536..df0fa4687a18 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -39,8 +39,7 @@ static inline int fsnotify_name(__u32 mask, const void *data, int data_type, static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry, __u32 mask) { - fsnotify_name(mask, d_inode(dentry), FSNOTIFY_EVENT_INODE, - dir, &dentry->d_name, 0); + fsnotify_name(mask, dentry, FSNOTIFY_EVENT_DENTRY, dir, &dentry->d_name, 0); } static inline void fsnotify_inode(struct inode *inode, __u32 mask) @@ -87,7 +86,7 @@ notify_child: */ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) { - fsnotify_parent(dentry, mask, d_inode(dentry), FSNOTIFY_EVENT_INODE); + fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY); } static inline int fsnotify_file(struct file *file, __u32 mask) diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 1ce66748a2d2..a2db821e8a8f 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -248,6 +248,7 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, + FSNOTIFY_EVENT_DENTRY, }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -255,6 +256,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; + case FSNOTIFY_EVENT_DENTRY: + return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); default: @@ -262,6 +265,19 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) } } +static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_DENTRY: + /* Non const is needed for dget() */ + return (struct dentry *)data; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry; + default: + return NULL; + } +} + static inline const struct path *fsnotify_data_path(const void *data, int data_type) { -- cgit v1.2.3 From dabe729dddca550446e9cc118c96d1f91703345b Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 25 Oct 2021 16:27:18 -0300 Subject: fsnotify: clarify contract for create event hooks Clarify argument names and contract for fsnotify_create() and fsnotify_mkdir() to reflect the anomaly of kernfs, which leaves dentries negavite after mkdir/create. Remove the WARN_ON(!inode) in audit code that were added by the Fixes commit under the wrong assumption that dentries cannot be negative after mkdir/create. Fixes: aa93bdc5500c ("fsnotify: use helpers to access data by data_type") Link: https://lore.kernel.org/linux-fsdevel/87mtp5yz0q.fsf@collabora.com/ Link: https://lore.kernel.org/r/20211025192746.66445-4-krisman@collabora.com Reviewed-by: Jan Kara Reported-by: Gabriel Krisman Bertazi Signed-off-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 22 ++++++++++++++++------ kernel/audit_fsnotify.c | 3 +-- kernel/audit_watch.c | 3 +-- 3 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index df0fa4687a18..1e5f7435a4b5 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -192,16 +192,22 @@ static inline void fsnotify_inoderemove(struct inode *inode) /* * fsnotify_create - 'name' was linked in + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_create(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_create(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE); + fsnotify_dirent(dir, dentry, FS_CREATE); } /* * fsnotify_link - new hardlink in 'inode' directory + * + * Caller must make sure that new_dentry->d_name is stable. * Note: We have to pass also the linked inode ptr as some filesystems leave * new_dentry->d_inode NULL and instantiate inode pointer later */ @@ -230,12 +236,16 @@ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) /* * fsnotify_mkdir - directory 'name' was created + * + * Caller must make sure that dentry->d_name is stable. + * Note: some filesystems (e.g. kernfs) leave @dentry negative and instantiate + * ->d_inode later */ -static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry) +static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) { - audit_inode_child(inode, dentry, AUDIT_TYPE_CHILD_CREATE); + audit_inode_child(dir, dentry, AUDIT_TYPE_CHILD_CREATE); - fsnotify_dirent(inode, dentry, FS_CREATE | FS_ISDIR); + fsnotify_dirent(dir, dentry, FS_CREATE | FS_ISDIR); } /* diff --git a/kernel/audit_fsnotify.c b/kernel/audit_fsnotify.c index 60739d5e3373..02348b48447c 100644 --- a/kernel/audit_fsnotify.c +++ b/kernel/audit_fsnotify.c @@ -160,8 +160,7 @@ static int audit_mark_handle_event(struct fsnotify_mark *inode_mark, u32 mask, audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_fsnotify_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) { diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2acf7ca49154..223eed7b39cd 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -472,8 +472,7 @@ static int audit_watch_handle_event(struct fsnotify_mark *inode_mark, u32 mask, parent = container_of(inode_mark, struct audit_parent, mark); - if (WARN_ON_ONCE(inode_mark->group != audit_watch_group) || - WARN_ON_ONCE(!inode)) + if (WARN_ON_ONCE(inode_mark->group != audit_watch_group)) return 0; if (mask & (FS_CREATE|FS_MOVED_TO) && inode) -- cgit v1.2.3 From 808967a0a4d2f4ce6a2005c5692fffbecaf018c1 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:23 -0300 Subject: fsnotify: Add helper to detect overflow_event Similarly to fanotify_is_perm_event and friends, provide a helper predicate to say whether a mask is of an overflow event. Link: https://lore.kernel.org/r/20211025192746.66445-9-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.h | 3 ++- include/linux/fsnotify_backend.h | 5 +++++ 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index 4a5e555dc3d2..c42cf8fd7d79 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -315,7 +315,8 @@ static inline struct path *fanotify_event_path(struct fanotify_event *event) */ static inline bool fanotify_is_hashed_event(u32 mask) { - return !fanotify_is_perm_event(mask) && !(mask & FS_Q_OVERFLOW); + return !(fanotify_is_perm_event(mask) || + fsnotify_is_overflow_event(mask)); } static inline unsigned int fanotify_event_hash_bucket( diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index a2db821e8a8f..749bc85e1d1c 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -510,6 +510,11 @@ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) fsnotify_add_event(group, group->overflow_event, NULL, NULL); } +static inline bool fsnotify_is_overflow_event(u32 mask) +{ + return mask & FS_Q_OVERFLOW; +} + static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); -- cgit v1.2.3 From 1ad03c3a326a86e259389592117252c851873395 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:24 -0300 Subject: fsnotify: Add wrapper around fsnotify_add_event fsnotify_add_event is growing in number of parameters, which in most case are just passed a NULL pointer. So, split out a new fsnotify_insert_event function to clean things up for users who don't need an insert hook. Link: https://lore.kernel.org/r/20211025192746.66445-10-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 4 ++-- fs/notify/inotify/inotify_fsnotify.c | 2 +- fs/notify/notification.c | 12 ++++++------ include/linux/fsnotify_backend.h | 23 ++++++++++++++++------- 4 files changed, 25 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 310246f8d3f1..f82e20228999 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -781,8 +781,8 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, } fsn_event = &event->fse; - ret = fsnotify_add_event(group, fsn_event, fanotify_merge, - fanotify_insert_event); + ret = fsnotify_insert_event(group, fsn_event, fanotify_merge, + fanotify_insert_event); if (ret) { /* Permission events shouldn't be merged */ BUG_ON(ret == 1 && mask & FANOTIFY_PERM_EVENTS); diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index d1a64daa0171..a96582cbfad1 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -116,7 +116,7 @@ int inotify_handle_inode_event(struct fsnotify_mark *inode_mark, u32 mask, if (len) strcpy(event->name, name->name); - ret = fsnotify_add_event(group, fsn_event, inotify_merge, NULL); + ret = fsnotify_add_event(group, fsn_event, inotify_merge); if (ret) { /* Our event wasn't used in the end. Free it. */ fsnotify_destroy_event(group, fsn_event); diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 32f45543b9c6..44bb10f50715 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -78,12 +78,12 @@ void fsnotify_destroy_event(struct fsnotify_group *group, * 2 if the event was not queued - either the queue of events has overflown * or the group is shutting down. */ -int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)) +int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)) { int ret = 0; struct list_head *list = &group->notification_list; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 749bc85e1d1c..b323d0c4b967 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -498,16 +498,25 @@ extern int fsnotify_fasync(int fd, struct file *file, int on); extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct fsnotify_group *, - struct fsnotify_event *), - void (*insert)(struct fsnotify_group *, - struct fsnotify_event *)); +extern int fsnotify_insert_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *), + void (*insert)(struct fsnotify_group *, + struct fsnotify_event *)); + +static inline int fsnotify_add_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct fsnotify_group *, + struct fsnotify_event *)) +{ + return fsnotify_insert_event(group, event, merge, NULL); +} + /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { - fsnotify_add_event(group, group->overflow_event, NULL, NULL); + fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) -- cgit v1.2.3 From 29335033c574a15334015d8c4e36862cff3d3384 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:25 -0300 Subject: fsnotify: Retrieve super block from the data field Some file system events (i.e. FS_ERROR) might not be associated with an inode or directory. For these, we can retrieve the super block from the data field. But, since the super_block is available in the data field on every event type, simplify the code to always retrieve it from there, through a new helper. Link: https://lore.kernel.org/r/20211025192746.66445-11-krisman@collabora.com Suggested-by: Jan Kara Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fsnotify.c | 7 +++---- include/linux/fsnotify_backend.h | 15 +++++++++++++++ 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 963e6ce75b96..fde3a1115a17 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -455,16 +455,16 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) * @file_name is relative to * @file_name: optional file name associated with event * @inode: optional inode associated with event - - * either @dir or @inode must be non-NULL. - * if both are non-NULL event may be reported to both. + * If @dir and @inode are both non-NULL, event may be + * reported to both. * @cookie: inotify rename cookie */ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, struct inode *inode, u32 cookie) { const struct path *path = fsnotify_data_path(data, data_type); + struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; - struct super_block *sb; struct mount *mnt = NULL; struct inode *parent = NULL; int ret = 0; @@ -483,7 +483,6 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, */ parent = dir; } - sb = inode->i_sb; /* * Optimization: srcu_read_lock() has a memory barrier which can diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b323d0c4b967..035438fe4a43 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -289,6 +289,21 @@ static inline const struct path *fsnotify_data_path(const void *data, } } +static inline struct super_block *fsnotify_data_sb(const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_INODE: + return ((struct inode *)data)->i_sb; + case FSNOTIFY_EVENT_DENTRY: + return ((struct dentry *)data)->d_sb; + case FSNOTIFY_EVENT_PATH: + return ((const struct path *)data)->dentry->d_sb; + default: + return NULL; + } +} + enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_PARENT, -- cgit v1.2.3 From 24dca90590509a7a6cbe0650100c90c5b8a3468a Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:26 -0300 Subject: fsnotify: Protect fsnotify_handle_inode_event from no-inode events FAN_FS_ERROR allows events without inodes - i.e. for file system-wide errors. Even though fsnotify_handle_inode_event is not currently used by fanotify, this patch protects other backends from cases where neither inode or dir are provided. Also document the constraints of the interface (inode and dir cannot be both NULL). Link: https://lore.kernel.org/r/20211025192746.66445-12-krisman@collabora.com Suggested-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Jan Kara --- fs/nfsd/filecache.c | 3 +++ fs/notify/fsnotify.c | 3 +++ include/linux/fsnotify_backend.h | 1 + 3 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index be3c1aad50ea..fdf89fcf1a0c 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -602,6 +602,9 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *name, u32 cookie) { + if (WARN_ON_ONCE(!inode)) + return 0; + trace_nfsd_file_fsnotify_handle_event(inode, mask); /* Should be no marks on non-regular files */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index fde3a1115a17..4034ca566f95 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -252,6 +252,9 @@ static int fsnotify_handle_inode_event(struct fsnotify_group *group, if (WARN_ON_ONCE(!ops->handle_inode_event)) return 0; + if (WARN_ON_ONCE(!inode && !dir)) + return 0; + if ((inode_mark->mask & FS_EXCL_UNLINK) && path && d_unlinked(path->dentry)) return 0; diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 035438fe4a43..b71dc788018e 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -136,6 +136,7 @@ struct mem_cgroup; * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. + * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * -- cgit v1.2.3 From 330ae77d2a5b0af32c0f29e139bf28ec8591de59 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:27 -0300 Subject: fsnotify: Pass group argument to free_event For group-wide mempool backed events, like FS_ERROR, the free_event callback will need to reference the group's mempool to free the memory. Wire that argument into the current callers. Link: https://lore.kernel.org/r/20211025192746.66445-13-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 3 ++- fs/notify/group.c | 2 +- fs/notify/inotify/inotify_fsnotify.c | 3 ++- fs/notify/notification.c | 2 +- include/linux/fsnotify_backend.h | 2 +- 5 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index f82e20228999..c620b4f6fe12 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -835,7 +835,8 @@ static void fanotify_free_name_event(struct fanotify_event *event) kfree(FANOTIFY_NE(event)); } -static void fanotify_free_event(struct fsnotify_event *fsn_event) +static void fanotify_free_event(struct fsnotify_group *group, + struct fsnotify_event *fsn_event) { struct fanotify_event *event; diff --git a/fs/notify/group.c b/fs/notify/group.c index fb89c351295d..6a297efc4788 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -88,7 +88,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group) * that deliberately ignores overflow events. */ if (group->overflow_event) - group->ops->free_event(group->overflow_event); + group->ops->free_event(group, group->overflow_event); fsnotify_put_group(group); } diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c index a96582cbfad1..d92d7b0adc9a 100644 --- a/fs/notify/inotify/inotify_fsnotify.c +++ b/fs/notify/inotify/inotify_fsnotify.c @@ -177,7 +177,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group) dec_inotify_instances(group->inotify_data.ucounts); } -static void inotify_free_event(struct fsnotify_event *fsn_event) +static void inotify_free_event(struct fsnotify_group *group, + struct fsnotify_event *fsn_event) { kfree(INOTIFY_E(fsn_event)); } diff --git a/fs/notify/notification.c b/fs/notify/notification.c index 44bb10f50715..9022ae650cf8 100644 --- a/fs/notify/notification.c +++ b/fs/notify/notification.c @@ -64,7 +64,7 @@ void fsnotify_destroy_event(struct fsnotify_group *group, WARN_ON(!list_empty(&event->list)); spin_unlock(&group->notification_lock); } - group->ops->free_event(event); + group->ops->free_event(group, event); } /* diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b71dc788018e..3a7c31436182 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -156,7 +156,7 @@ struct fsnotify_ops { const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); - void (*free_event)(struct fsnotify_event *event); + void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; -- cgit v1.2.3 From 4fe595cf1c80e7a5af4d00c4da29def64aff57a2 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:31 -0300 Subject: fanotify: Require fid_mode for any non-fd event Like inode events, FAN_FS_ERROR will require fid mode. Therefore, convert the verification during fanotify_mark(2) to require fid for any non-fd event. This means fid_mode will not only be required for inode events, but for any event that doesn't provide a descriptor. Link: https://lore.kernel.org/r/20211025192746.66445-17-krisman@collabora.com Suggested-by: Amir Goldstein Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 12 ++++++------ include/linux/fanotify.h | 3 +++ 2 files changed, 9 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index adeae6d65e35..66ee3c2805c7 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1458,14 +1458,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, goto fput_and_out; /* - * Events with data type inode do not carry enough information to report - * event->fd, so we do not allow setting a mask for inode events unless - * group supports reporting fid. - * inode events are not supported on a mount mark, because they do not - * carry enough information (i.e. path) to be filtered by mount point. + * Events that do not carry enough information to report + * event->fd require a group that supports reporting fid. Those + * events are not supported on a mount mark, because they do not + * carry enough information (i.e. path) to be filtered by mount + * point. */ fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); - if (mask & FANOTIFY_INODE_EVENTS && + if (mask & ~(FANOTIFY_FD_EVENTS|FANOTIFY_EVENT_FLAGS) && (!fid_mode || mark_type == FAN_MARK_MOUNT)) goto fput_and_out; diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index eec3b7c40811..52d464802d99 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -84,6 +84,9 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ */ #define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +/* Events that can be reported with event->fd */ +#define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) + /* Events that can only be reported with data type FSNOTIFY_EVENT_INODE */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) -- cgit v1.2.3 From 9daa811073fa19c08e8aad3b90f9235fed161acf Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:32 -0300 Subject: fsnotify: Support FS_ERROR event type Expose a new type of fsnotify event for filesystems to report errors for userspace monitoring tools. fanotify will send this type of notification for FAN_FS_ERROR events. This also introduce a helper for generating the new event. Link: https://lore.kernel.org/r/20211025192746.66445-18-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- include/linux/fsnotify.h | 13 +++++++++++++ include/linux/fsnotify_backend.h | 32 +++++++++++++++++++++++++++++++- 2 files changed, 44 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 1e5f7435a4b5..787545e87eeb 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -339,4 +339,17 @@ static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid) fsnotify_dentry(dentry, mask); } +static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode, + int error) +{ + struct fs_error_report report = { + .error = error, + .inode = inode, + .sb = sb, + }; + + return fsnotify(FS_ERROR, &report, FSNOTIFY_EVENT_ERROR, + NULL, NULL, NULL, 0); +} + #endif /* _LINUX_FS_NOTIFY_H */ diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3a7c31436182..00dbaafbcf95 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -42,6 +42,12 @@ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ + +/* + * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify + * which does not support FS_ERROR. + */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ @@ -95,7 +101,8 @@ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ - FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED) + FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ + FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_EXCL_UNLINK | FS_ISDIR | FS_IN_ONESHOT | \ @@ -250,6 +257,13 @@ enum fsnotify_data_type { FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, + FSNOTIFY_EVENT_ERROR, +}; + +struct fs_error_report { + int error; + struct inode *inode; + struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) @@ -261,6 +275,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type) return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); + case FSNOTIFY_EVENT_ERROR: + return ((struct fs_error_report *)data)->inode; default: return NULL; } @@ -300,6 +316,20 @@ static inline struct super_block *fsnotify_data_sb(const void *data, return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; + case FSNOTIFY_EVENT_ERROR: + return ((struct fs_error_report *) data)->sb; + default: + return NULL; + } +} + +static inline struct fs_error_report *fsnotify_data_error_report( + const void *data, + int data_type) +{ + switch (data_type) { + case FSNOTIFY_EVENT_ERROR: + return (struct fs_error_report *) data; default: return NULL; } -- cgit v1.2.3 From 734a1a5eccc5f7473002b0669f788e135f1f64aa Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:34 -0300 Subject: fanotify: Pre-allocate pool of error events Pre-allocate slots for file system errors to have greater chances of succeeding, since error events can happen in GFP_NOFS context. This patch introduces a group-wide mempool of error events, shared by all FAN_FS_ERROR marks in this group. Link: https://lore.kernel.org/r/20211025192746.66445-20-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 3 +++ fs/notify/fanotify/fanotify.h | 11 +++++++++++ fs/notify/fanotify/fanotify_user.c | 26 +++++++++++++++++++++++++- include/linux/fsnotify_backend.h | 2 ++ 4 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 8f152445d75c..01d68dfc74aa 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -819,6 +819,9 @@ static void fanotify_free_group_priv(struct fsnotify_group *group) if (group->fanotify_data.ucounts) dec_ucount(group->fanotify_data.ucounts, UCOUNT_FANOTIFY_GROUPS); + + if (mempool_initialized(&group->fanotify_data.error_events_pool)) + mempool_exit(&group->fanotify_data.error_events_pool); } static void fanotify_free_path_event(struct fanotify_event *event) diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index c42cf8fd7d79..a577e87fac2b 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -141,6 +141,7 @@ enum fanotify_event_type { FANOTIFY_EVENT_TYPE_PATH, FANOTIFY_EVENT_TYPE_PATH_PERM, FANOTIFY_EVENT_TYPE_OVERFLOW, /* struct fanotify_event */ + FANOTIFY_EVENT_TYPE_FS_ERROR, /* struct fanotify_error_event */ __FANOTIFY_EVENT_TYPE_NUM }; @@ -196,6 +197,16 @@ FANOTIFY_NE(struct fanotify_event *event) return container_of(event, struct fanotify_name_event, fae); } +struct fanotify_error_event { + struct fanotify_event fae; +}; + +static inline struct fanotify_error_event * +FANOTIFY_EE(struct fanotify_event *event) +{ + return container_of(event, struct fanotify_error_event, fae); +} + static inline __kernel_fsid_t *fanotify_event_fsid(struct fanotify_event *event) { if (event->type == FANOTIFY_EVENT_TYPE_FID) diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 66ee3c2805c7..2f4182b754b2 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -30,6 +30,7 @@ #define FANOTIFY_DEFAULT_MAX_EVENTS 16384 #define FANOTIFY_OLD_DEFAULT_MAX_MARKS 8192 #define FANOTIFY_DEFAULT_MAX_GROUPS 128 +#define FANOTIFY_DEFAULT_FEE_POOL_SIZE 32 /* * Legacy fanotify marks limits (8192) is per group and we introduced a tunable @@ -1054,6 +1055,15 @@ out_dec_ucounts: return ERR_PTR(ret); } +static int fanotify_group_init_error_pool(struct fsnotify_group *group) +{ + if (mempool_initialized(&group->fanotify_data.error_events_pool)) + return 0; + + return mempool_init_kmalloc_pool(&group->fanotify_data.error_events_pool, + FANOTIFY_DEFAULT_FEE_POOL_SIZE, + sizeof(struct fanotify_error_event)); +} static int fanotify_add_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, unsigned int type, @@ -1062,6 +1072,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, { struct fsnotify_mark *fsn_mark; __u32 added; + int ret = 0; mutex_lock(&group->mark_mutex); fsn_mark = fsnotify_find_mark(connp, group); @@ -1072,13 +1083,26 @@ static int fanotify_add_mark(struct fsnotify_group *group, return PTR_ERR(fsn_mark); } } + + /* + * Error events are pre-allocated per group, only if strictly + * needed (i.e. FAN_FS_ERROR was requested). + */ + if (!(flags & FAN_MARK_IGNORED_MASK) && (mask & FAN_FS_ERROR)) { + ret = fanotify_group_init_error_pool(group); + if (ret) + goto out; + } + added = fanotify_mark_add_to_mask(fsn_mark, mask, flags); if (added & ~fsnotify_conn_mask(fsn_mark->connector)) fsnotify_recalc_mask(fsn_mark->connector); + +out: mutex_unlock(&group->mark_mutex); fsnotify_put_mark(fsn_mark); - return 0; + return ret; } static int fanotify_add_vfsmount_mark(struct fsnotify_group *group, diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 00dbaafbcf95..51ef2b079bfa 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -19,6 +19,7 @@ #include #include #include +#include /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily @@ -246,6 +247,7 @@ struct fsnotify_group { int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; + mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; -- cgit v1.2.3 From 9709bd548f11a092d124698118013f66e1740f9b Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:43 -0300 Subject: fanotify: Allow users to request FAN_FS_ERROR events Wire up the FAN_FS_ERROR event in the fanotify_mark syscall, allowing user space to request the monitoring of FAN_FS_ERROR events. These events are limited to filesystem marks, so check it is the case in the syscall handler. Link: https://lore.kernel.org/r/20211025192746.66445-29-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 2 +- fs/notify/fanotify/fanotify_user.c | 4 ++++ include/linux/fanotify.h | 6 +++++- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index af61425e6e3b..b6091775aa6e 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -822,7 +822,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20); mask = fanotify_group_event_mask(group, iter_info, mask, data, data_type, dir); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index fb817028d0b6..559bc1e9926d 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1520,6 +1520,10 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, group->priority == FS_PRIO_0) goto fput_and_out; + if (mask & FAN_FS_ERROR && + mark_type != FAN_MARK_FILESYSTEM) + goto fput_and_out; + /* * Events that do not carry enough information to report * event->fd require a group that supports reporting fid. Those diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 52d464802d99..616af2ea20f3 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -91,9 +91,13 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_INODE_EVENTS (FANOTIFY_DIRENT_EVENTS | \ FAN_ATTRIB | FAN_MOVE_SELF | FAN_DELETE_SELF) +/* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */ +#define FANOTIFY_ERROR_EVENTS (FAN_FS_ERROR) + /* Events that user can request to be notified on */ #define FANOTIFY_EVENTS (FANOTIFY_PATH_EVENTS | \ - FANOTIFY_INODE_EVENTS) + FANOTIFY_INODE_EVENTS | \ + FANOTIFY_ERROR_EVENTS) /* Events that require a permission response from user */ #define FANOTIFY_PERM_EVENTS (FAN_OPEN_PERM | FAN_ACCESS_PERM | \ -- cgit v1.2.3 From 1bb6b81029456f4e2e6727c5167f43bdfc34bee5 Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Wed, 27 Oct 2021 13:21:07 +0100 Subject: block: avoid extra iter advance with async iocb Nobody cares about iov iterators state if we return -EIOCBQUEUED, so as the we now have __blkdev_direct_IO_async(), which gets pages only once, we can skip expensive iov_iter_advance(). It's around 1-2% of all CPU spent. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/a6158edfbfa2ae3bc24aed29a72f035df18fad2f.1635337135.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- block/bio.c | 2 +- block/fops.c | 20 +++++++++++++++----- include/linux/bio.h | 1 + 3 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index ead1f8a9ff5e..15ab0d6d1c06 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1046,7 +1046,7 @@ void __bio_release_pages(struct bio *bio, bool mark_dirty) } EXPORT_SYMBOL_GPL(__bio_release_pages); -static void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) +void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) { size_t size = iov_iter_count(iter); diff --git a/block/fops.c b/block/fops.c index a7b328296912..092e5079e827 100644 --- a/block/fops.c +++ b/block/fops.c @@ -352,11 +352,21 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, bio->bi_end_io = blkdev_bio_end_io_async; bio->bi_ioprio = iocb->ki_ioprio; - ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - return ret; + if (iov_iter_is_bvec(iter)) { + /* + * Users don't rely on the iterator being in any particular + * state for async I/O returning -EIOCBQUEUED, hence we can + * avoid expensive iov_iter_advance(). Bypass + * bio_iov_iter_get_pages() and set the bvec directly. + */ + bio_iov_bvec_set(bio, iter); + } else { + ret = bio_iov_iter_get_pages(bio, iter); + if (unlikely(ret)) { + bio->bi_status = BLK_STS_IOERR; + bio_endio(bio); + return ret; + } } dio->size = bio->bi_iter.bi_size; diff --git a/include/linux/bio.h b/include/linux/bio.h index c88700d1bdc3..fe6bdfbbef66 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -417,6 +417,7 @@ int bio_add_zone_append_page(struct bio *bio, struct page *page, void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); +void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter); void __bio_release_pages(struct bio *bio, bool mark_dirty); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); -- cgit v1.2.3 From 5460601de590158b37619f8e18b678aa18da6345 Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Tue, 12 Oct 2021 15:09:01 +0300 Subject: dma-buf: Fix pin callback comment MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The pin callback does not necessarily have to move the memory to system memory, remove the sentence from the comment. Link: https://lore.kernel.org/r/20211012120903.96933-2-galpress@amazon.com Signed-off-by: Gal Pressman Reviewed-by: Christian König Signed-off-by: Jason Gunthorpe --- include/linux/dma-buf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 8b32b4bdd590..8afe182fe8f2 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -86,8 +86,8 @@ struct dma_buf_ops { * @pin: * * This is called by dma_buf_pin() and lets the exporter know that the - * DMA-buf can't be moved any more. The exporter should pin the buffer - * into system memory to make sure it is generally accessible by other + * DMA-buf can't be moved any more. Ideally, the exporter should + * pin the buffer so that it is generally accessible by all * devices. * * This is called with the &dmabuf.resv object locked and is mutual -- cgit v1.2.3 From 3ab7b6ac5d829e60c3b89d415811ff1c9f358c8e Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Mon, 25 Oct 2021 10:09:23 -0700 Subject: pwm: Introduce single-PWM of_xlate function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The existing pxa driver and the upcoming addition of PWM support in the TI sn565dsi86 DSI/eDP bridge driver both has a single PWM channel and thereby a need for a of_xlate function with the period as its single argument. Introduce a common helper function in the core that can be used as of_xlate by such drivers and migrate the pxa driver to use this. Signed-off-by: Bjorn Andersson Acked-by: Uwe Kleine-König Tested-by: Steev Klimaszewski Tested-By: Steev Klimaszewski Signed-off-by: Robert Foss Link: https://patchwork.freedesktop.org/patch/msgid/20211025170925.3096444-1-bjorn.andersson@linaro.org --- drivers/pwm/core.c | 26 ++++++++++++++++++++++++++ drivers/pwm/pwm-pxa.c | 16 +--------------- include/linux/pwm.h | 2 ++ 3 files changed, 29 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 4527f09a5c50..2c6b155002a2 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -152,6 +152,32 @@ of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args) } EXPORT_SYMBOL_GPL(of_pwm_xlate_with_flags); +struct pwm_device * +of_pwm_single_xlate(struct pwm_chip *pc, const struct of_phandle_args *args) +{ + struct pwm_device *pwm; + + if (pc->of_pwm_n_cells < 1) + return ERR_PTR(-EINVAL); + + /* validate that one cell is specified, optionally with flags */ + if (args->args_count != 1 && args->args_count != 2) + return ERR_PTR(-EINVAL); + + pwm = pwm_request_from_chip(pc, 0, NULL); + if (IS_ERR(pwm)) + return pwm; + + pwm->args.period = args->args[0]; + pwm->args.polarity = PWM_POLARITY_NORMAL; + + if (args->args_count == 2 && args->args[2] & PWM_POLARITY_INVERTED) + pwm->args.polarity = PWM_POLARITY_INVERSED; + + return pwm; +} +EXPORT_SYMBOL_GPL(of_pwm_single_xlate); + static void of_pwmchip_add(struct pwm_chip *chip) { if (!chip->dev || !chip->dev->of_node) diff --git a/drivers/pwm/pwm-pxa.c b/drivers/pwm/pwm-pxa.c index a9efdcf839ae..238ec88c130b 100644 --- a/drivers/pwm/pwm-pxa.c +++ b/drivers/pwm/pwm-pxa.c @@ -148,20 +148,6 @@ static const struct platform_device_id *pxa_pwm_get_id_dt(struct device *dev) return id ? id->data : NULL; } -static struct pwm_device * -pxa_pwm_of_xlate(struct pwm_chip *pc, const struct of_phandle_args *args) -{ - struct pwm_device *pwm; - - pwm = pwm_request_from_chip(pc, 0, NULL); - if (IS_ERR(pwm)) - return pwm; - - pwm->args.period = args->args[0]; - - return pwm; -} - static int pwm_probe(struct platform_device *pdev) { const struct platform_device_id *id = platform_get_device_id(pdev); @@ -187,7 +173,7 @@ static int pwm_probe(struct platform_device *pdev) pc->chip.npwm = (id->driver_data & HAS_SECONDARY_PWM) ? 2 : 1; if (IS_ENABLED(CONFIG_OF)) { - pc->chip.of_xlate = pxa_pwm_of_xlate; + pc->chip.of_xlate = of_pwm_single_xlate; pc->chip.of_pwm_n_cells = 1; } diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 725c9b784e60..dd51d4931fdc 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -414,6 +414,8 @@ struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, struct pwm_device *of_pwm_xlate_with_flags(struct pwm_chip *pc, const struct of_phandle_args *args); +struct pwm_device *of_pwm_single_xlate(struct pwm_chip *pc, + const struct of_phandle_args *args); struct pwm_device *pwm_get(struct device *dev, const char *con_id); struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, -- cgit v1.2.3 From ce5e48036c9e76a2a5bd4d9079eac273087a533a Mon Sep 17 00:00:00 2001 From: 王贇 Date: Wed, 27 Oct 2021 11:14:44 +0800 Subject: ftrace: disable preemption when recursion locked As the documentation explained, ftrace_test_recursion_trylock() and ftrace_test_recursion_unlock() were supposed to disable and enable preemption properly, however currently this work is done outside of the function, which could be missing by mistake. And since the internal using of trace_test_and_set_recursion() and trace_clear_recursion() also require preemption disabled, we can just merge the logical. This patch will make sure the preemption has been disabled when trace_test_and_set_recursion() return bit >= 0, and trace_clear_recursion() will enable the preemption if previously enabled. Link: https://lkml.kernel.org/r/13bde807-779c-aa4c-0672-20515ae365ea@linux.alibaba.com CC: Petr Mladek Cc: Guo Ren Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Helge Deller Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Paul Walmsley Cc: Palmer Dabbelt Cc: Albert Ou Cc: Thomas Gleixner Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: Josh Poimboeuf Cc: Jiri Kosina Cc: Joe Lawrence Cc: Masami Hiramatsu Cc: Nicholas Piggin Cc: Jisheng Zhang CC: Steven Rostedt CC: Miroslav Benes Reported-by: Abaci Suggested-by: Peter Zijlstra Signed-off-by: Michael Wang [ Removed extra line in comment - SDR ] Signed-off-by: Steven Rostedt (VMware) --- arch/csky/kernel/probes/ftrace.c | 2 -- arch/parisc/kernel/ftrace.c | 2 -- arch/powerpc/kernel/kprobes-ftrace.c | 2 -- arch/riscv/kernel/probes/ftrace.c | 2 -- arch/x86/kernel/kprobes/ftrace.c | 2 -- include/linux/trace_recursion.h | 11 ++++++++++- kernel/livepatch/patch.c | 12 ++++++------ kernel/trace/ftrace.c | 15 +++++---------- kernel/trace/trace_functions.c | 5 ----- 9 files changed, 21 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c index b388228abbf2..834cffcfbce3 100644 --- a/arch/csky/kernel/probes/ftrace.c +++ b/arch/csky/kernel/probes/ftrace.c @@ -17,7 +17,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, return; regs = ftrace_get_regs(fregs); - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (!p) { p = get_kprobe((kprobe_opcode_t *)(ip - MCOUNT_INSN_SIZE)); @@ -57,7 +56,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c index 01581f715737..b14011d3c2f1 100644 --- a/arch/parisc/kernel/ftrace.c +++ b/arch/parisc/kernel/ftrace.c @@ -211,7 +211,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, return; regs = ftrace_get_regs(fregs); - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -240,7 +239,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, } __this_cpu_write(current_kprobe, NULL); out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c index 7154d58338cc..072ebe7f290b 100644 --- a/arch/powerpc/kernel/kprobes-ftrace.c +++ b/arch/powerpc/kernel/kprobes-ftrace.c @@ -26,7 +26,6 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, return; regs = ftrace_get_regs(fregs); - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)nip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -61,7 +60,6 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index aab85a82f419..7142ec42e889 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -15,7 +15,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -52,7 +51,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 596de2f6d3a5..dd2ec14adb77 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,7 +25,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) goto out; @@ -59,7 +58,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, __this_cpu_write(current_kprobe, NULL); } out: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h index 24f284eb55a7..a13f23b04d73 100644 --- a/include/linux/trace_recursion.h +++ b/include/linux/trace_recursion.h @@ -155,6 +155,9 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip); # define do_ftrace_record_recursion(ip, pip) do { } while (0) #endif +/* + * Preemption is promised to be disabled when return bit >= 0. + */ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip, int start, int max) { @@ -189,14 +192,20 @@ static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsign current->trace_recursion = val; barrier(); + preempt_disable_notrace(); + return bit + 1; } +/* + * Preemption will be enabled (if it was previously enabled). + */ static __always_inline void trace_clear_recursion(int bit) { if (!bit) return; + preempt_enable_notrace(); barrier(); bit--; trace_recursion_clear(bit); @@ -209,7 +218,7 @@ static __always_inline void trace_clear_recursion(int bit) * tracing recursed in the same context (normal vs interrupt), * * Returns: -1 if a recursion happened. - * >= 0 if no recursion + * >= 0 if no recursion. */ static __always_inline int ftrace_test_recursion_trylock(unsigned long ip, unsigned long parent_ip) diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c index e8029aea67f1..fe316c021d73 100644 --- a/kernel/livepatch/patch.c +++ b/kernel/livepatch/patch.c @@ -49,14 +49,15 @@ static void notrace klp_ftrace_handler(unsigned long ip, ops = container_of(fops, struct klp_ops, fops); + /* + * The ftrace_test_recursion_trylock() will disable preemption, + * which is required for the variant of synchronize_rcu() that is + * used to allow patching functions where RCU is not watching. + * See klp_synchronize_transition() for more details. + */ bit = ftrace_test_recursion_trylock(ip, parent_ip); if (WARN_ON_ONCE(bit < 0)) return; - /* - * A variant of synchronize_rcu() is used to allow patching functions - * where RCU is not watching, see klp_synchronize_transition(). - */ - preempt_disable_notrace(); func = list_first_or_null_rcu(&ops->func_stack, struct klp_func, stack_node); @@ -120,7 +121,6 @@ static void notrace klp_ftrace_handler(unsigned long ip, klp_arch_set_pc(fregs, (unsigned long)func->new_func); unlock: - preempt_enable_notrace(); ftrace_test_recursion_unlock(bit); } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2057ad363772..b4ed1a301232 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7198,16 +7198,15 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op; int bit; + /* + * The ftrace_test_and_set_recursion() will disable preemption, + * which is required since some of the ops may be dynamically + * allocated, they must be freed after a synchronize_rcu(). + */ bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return; - /* - * Some of the ops may be dynamically allocated, - * they must be freed after a synchronize_rcu(). - */ - preempt_disable_notrace(); - do_for_each_ftrace_op(op, ftrace_ops_list) { /* Stub functions don't need to be called nor tested */ if (op->flags & FTRACE_OPS_FL_STUB) @@ -7231,7 +7230,6 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, } } while_for_each_ftrace_op(op); out: - preempt_enable_notrace(); trace_clear_recursion(bit); } @@ -7279,12 +7277,9 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - preempt_disable_notrace(); - if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) op->func(ip, parent_ip, op, fregs); - preempt_enable_notrace(); trace_clear_recursion(bit); } NOKPROBE_SYMBOL(ftrace_ops_assist_func); diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 1f0e63f5d1f9..9f1bfbe105e8 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -186,7 +186,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, return; trace_ctx = tracing_gen_ctx(); - preempt_disable_notrace(); cpu = smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); @@ -194,7 +193,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, trace_function(tr, ip, parent_ip, trace_ctx); ftrace_test_recursion_unlock(bit); - preempt_enable_notrace(); } #ifdef CONFIG_UNWINDER_ORC @@ -298,8 +296,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, if (bit < 0) return; - preempt_disable_notrace(); - cpu = smp_processor_id(); data = per_cpu_ptr(tr->array_buffer.data, cpu); if (atomic_read(&data->disabled)) @@ -324,7 +320,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, out: ftrace_test_recursion_unlock(bit); - preempt_enable_notrace(); } static void -- cgit v1.2.3 From e531e90b5ab0f7ce5ff298e165214c1aec6ed187 Mon Sep 17 00:00:00 2001 From: "Robin H. Johnson" Date: Mon, 30 Aug 2021 21:37:23 -0700 Subject: tracing: Increase PERF_MAX_TRACE_SIZE to handle Sentinel1 and docker together Running endpoint security solutions like Sentinel1 that use perf-based tracing heavily lead to this repeated dump complaining about dockerd. The default value of 2048 is nowhere near not large enough. Using the prior patch "tracing: show size of requested buffer", we get "perf buffer not large enough, wanted 6644, have 6144", after repeated up-sizing (I did 2/4/6/8K). With 8K, the problem doesn't occur at all, so below is the trace for 6K. I'm wondering if this value should be selectable at boot time, but this is a good starting point. ``` ------------[ cut here ]------------ perf buffer not large enough, wanted 6644, have 6144 WARNING: CPU: 1 PID: 4997 at kernel/trace/trace_event_perf.c:402 perf_trace_buf_alloc+0x8c/0xa0 Modules linked in: [..] CPU: 1 PID: 4997 Comm: sh Tainted: G T 5.13.13-x86_64-00039-gb3959163488e #63 Hardware name: LENOVO 20KH002JUS/20KH002JUS, BIOS N23ET66W (1.41 ) 09/02/2019 RIP: 0010:perf_trace_buf_alloc+0x8c/0xa0 Code: 80 3d 43 97 d0 01 00 74 07 31 c0 5b 5d 41 5c c3 ba 00 18 00 00 89 ee 48 c7 c7 00 82 7d 91 c6 05 25 97 d0 01 01 e8 22 ee bc 00 <0f> 0b 31 c0 eb db 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 55 89 RSP: 0018:ffffb922026b7d58 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff9da5ee012000 RCX: 0000000000000027 RDX: ffff9da881657828 RSI: 0000000000000001 RDI: ffff9da881657820 RBP: 00000000000019f4 R08: 0000000000000000 R09: ffffb922026b7b80 R10: ffffb922026b7b78 R11: ffffffff91dda688 R12: 000000000000000f R13: ffff9da5ee012108 R14: ffff9da8816570a0 R15: ffffb922026b7e30 FS: 00007f420db1a080(0000) GS:ffff9da881640000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000060 CR3: 00000002504a8006 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: kprobe_perf_func+0x11e/0x270 ? do_execveat_common.isra.0+0x1/0x1c0 ? do_execveat_common.isra.0+0x5/0x1c0 kprobe_ftrace_handler+0x10e/0x1d0 0xffffffffc03aa0c8 ? do_execveat_common.isra.0+0x1/0x1c0 do_execveat_common.isra.0+0x5/0x1c0 __x64_sys_execve+0x33/0x40 do_syscall_64+0x6b/0xc0 ? do_syscall_64+0x11/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f420dc1db37 Code: ff ff 76 e7 f7 d8 64 41 89 00 eb df 0f 1f 80 00 00 00 00 f7 d8 64 41 89 00 eb dc 0f 1f 84 00 00 00 00 00 b8 3b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 01 43 0f 00 f7 d8 64 89 01 48 RSP: 002b:00007ffd4e8b4e38 EFLAGS: 00000246 ORIG_RAX: 000000000000003b RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f420dc1db37 RDX: 0000564338d1e740 RSI: 0000564338d32d50 RDI: 0000564338d28f00 RBP: 0000564338d28f00 R08: 0000564338d32d50 R09: 0000000000000020 R10: 00000000000001b6 R11: 0000000000000246 R12: 0000564338d28f00 R13: 0000564338d32d50 R14: 0000564338d1e740 R15: 0000564338d28c60 ---[ end trace 83ab3e8e16275e49 ]--- ``` Link: https://lkml.kernel.org/r/20210831043723.13481-2-robbat2@gentoo.org Signed-off-by: Robin H. Johnson Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3e475eeb5a99..50453b287615 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -671,7 +671,7 @@ struct trace_event_file { } \ early_initcall(trace_init_perf_perm_##name); -#define PERF_MAX_TRACE_SIZE 2048 +#define PERF_MAX_TRACE_SIZE 8192 #define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ -- cgit v1.2.3 From f941eadd8d6d4ee2f8c9aeab8e1da5e647533a7d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2021 14:41:31 -0700 Subject: bpf: Avoid races in __bpf_prog_run() for 32bit arches __bpf_prog_run() can run from non IRQ contexts, meaning it could be re entered if interrupted. This calls for the irq safe variant of u64_stats_update_{begin|end}, or risk a deadlock. This patch is a nop on 64bit arches, fortunately. syzbot report: WARNING: inconsistent lock state 5.12.0-rc3-syzkaller #0 Not tainted -------------------------------- inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. udevd/4013 [HC0[0]:SC0[0]:HE1:SE1] takes: ff7c9dec (&(&pstats->syncp)->seq){+.?.}-{0:0}, at: sk_filter include/linux/filter.h:867 [inline] ff7c9dec (&(&pstats->syncp)->seq){+.?.}-{0:0}, at: do_one_broadcast net/netlink/af_netlink.c:1468 [inline] ff7c9dec (&(&pstats->syncp)->seq){+.?.}-{0:0}, at: netlink_broadcast_filtered+0x27c/0x4fc net/netlink/af_netlink.c:1520 {IN-SOFTIRQ-W} state was registered at: lock_acquire.part.0+0xf0/0x41c kernel/locking/lockdep.c:5510 lock_acquire+0x6c/0x74 kernel/locking/lockdep.c:5483 do_write_seqcount_begin_nested include/linux/seqlock.h:520 [inline] do_write_seqcount_begin include/linux/seqlock.h:545 [inline] u64_stats_update_begin include/linux/u64_stats_sync.h:129 [inline] bpf_prog_run_pin_on_cpu include/linux/filter.h:624 [inline] bpf_prog_run_clear_cb+0x1bc/0x270 include/linux/filter.h:755 run_filter+0xa0/0x17c net/packet/af_packet.c:2031 packet_rcv+0xc0/0x3e0 net/packet/af_packet.c:2104 dev_queue_xmit_nit+0x2bc/0x39c net/core/dev.c:2387 xmit_one net/core/dev.c:3588 [inline] dev_hard_start_xmit+0x94/0x518 net/core/dev.c:3609 sch_direct_xmit+0x11c/0x1f0 net/sched/sch_generic.c:313 qdisc_restart net/sched/sch_generic.c:376 [inline] __qdisc_run+0x194/0x7f8 net/sched/sch_generic.c:384 qdisc_run include/net/pkt_sched.h:136 [inline] qdisc_run include/net/pkt_sched.h:128 [inline] __dev_xmit_skb net/core/dev.c:3795 [inline] __dev_queue_xmit+0x65c/0xf84 net/core/dev.c:4150 dev_queue_xmit+0x14/0x18 net/core/dev.c:4215 neigh_resolve_output net/core/neighbour.c:1491 [inline] neigh_resolve_output+0x170/0x228 net/core/neighbour.c:1471 neigh_output include/net/neighbour.h:510 [inline] ip6_finish_output2+0x2e4/0x9fc net/ipv6/ip6_output.c:117 __ip6_finish_output net/ipv6/ip6_output.c:182 [inline] __ip6_finish_output+0x164/0x3f8 net/ipv6/ip6_output.c:161 ip6_finish_output+0x2c/0xb0 net/ipv6/ip6_output.c:192 NF_HOOK_COND include/linux/netfilter.h:290 [inline] ip6_output+0x74/0x294 net/ipv6/ip6_output.c:215 dst_output include/net/dst.h:448 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] NF_HOOK include/linux/netfilter.h:295 [inline] mld_sendpack+0x2a8/0x7e4 net/ipv6/mcast.c:1679 mld_send_cr net/ipv6/mcast.c:1975 [inline] mld_ifc_timer_expire+0x1e8/0x494 net/ipv6/mcast.c:2474 call_timer_fn+0xd0/0x570 kernel/time/timer.c:1431 expire_timers kernel/time/timer.c:1476 [inline] __run_timers kernel/time/timer.c:1745 [inline] run_timer_softirq+0x2e4/0x384 kernel/time/timer.c:1758 __do_softirq+0x204/0x7ac kernel/softirq.c:345 do_softirq_own_stack include/asm-generic/softirq_stack.h:10 [inline] invoke_softirq kernel/softirq.c:228 [inline] __irq_exit_rcu+0x1d8/0x200 kernel/softirq.c:422 irq_exit+0x10/0x3c kernel/softirq.c:446 __handle_domain_irq+0xb4/0x120 kernel/irq/irqdesc.c:692 handle_domain_irq include/linux/irqdesc.h:176 [inline] gic_handle_irq+0x84/0xac drivers/irqchip/irq-gic.c:370 __irq_svc+0x5c/0x94 arch/arm/kernel/entry-armv.S:205 debug_smp_processor_id+0x0/0x24 lib/smp_processor_id.c:53 rcu_read_lock_held_common kernel/rcu/update.c:108 [inline] rcu_read_lock_sched_held+0x24/0x7c kernel/rcu/update.c:123 trace_lock_acquire+0x24c/0x278 include/trace/events/lock.h:13 lock_acquire+0x3c/0x74 kernel/locking/lockdep.c:5481 rcu_lock_acquire include/linux/rcupdate.h:267 [inline] rcu_read_lock include/linux/rcupdate.h:656 [inline] avc_has_perm_noaudit+0x6c/0x260 security/selinux/avc.c:1150 selinux_inode_permission+0x140/0x220 security/selinux/hooks.c:3141 security_inode_permission+0x44/0x60 security/security.c:1268 inode_permission.part.0+0x5c/0x13c fs/namei.c:521 inode_permission fs/namei.c:494 [inline] may_lookup fs/namei.c:1652 [inline] link_path_walk.part.0+0xd4/0x38c fs/namei.c:2208 link_path_walk fs/namei.c:2189 [inline] path_lookupat+0x3c/0x1b8 fs/namei.c:2419 filename_lookup+0xa8/0x1a4 fs/namei.c:2453 user_path_at_empty+0x74/0x90 fs/namei.c:2733 do_readlinkat+0x5c/0x12c fs/stat.c:417 __do_sys_readlink fs/stat.c:450 [inline] sys_readlink+0x24/0x28 fs/stat.c:447 ret_fast_syscall+0x0/0x2c arch/arm/mm/proc-v7.S:64 0x7eaa4974 irq event stamp: 298277 hardirqs last enabled at (298277): [<802000d0>] no_work_pending+0x4/0x34 hardirqs last disabled at (298276): [<8020c9b8>] do_work_pending+0x9c/0x648 arch/arm/kernel/signal.c:676 softirqs last enabled at (298216): [<8020167c>] __do_softirq+0x584/0x7ac kernel/softirq.c:372 softirqs last disabled at (298201): [<8024dff4>] do_softirq_own_stack include/asm-generic/softirq_stack.h:10 [inline] softirqs last disabled at (298201): [<8024dff4>] invoke_softirq kernel/softirq.c:228 [inline] softirqs last disabled at (298201): [<8024dff4>] __irq_exit_rcu+0x1d8/0x200 kernel/softirq.c:422 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&pstats->syncp)->seq); lock(&(&pstats->syncp)->seq); *** DEADLOCK *** 1 lock held by udevd/4013: #0: 82b09c5c (rcu_read_lock){....}-{1:2}, at: sk_filter_trim_cap+0x54/0x434 net/core/filter.c:139 stack backtrace: CPU: 1 PID: 4013 Comm: udevd Not tainted 5.12.0-rc3-syzkaller #0 Hardware name: ARM-Versatile Express Backtrace: [<81802550>] (dump_backtrace) from [<818027c4>] (show_stack+0x18/0x1c arch/arm/kernel/traps.c:252) r7:00000080 r6:600d0093 r5:00000000 r4:82b58344 [<818027ac>] (show_stack) from [<81809e98>] (__dump_stack lib/dump_stack.c:79 [inline]) [<818027ac>] (show_stack) from [<81809e98>] (dump_stack+0xb8/0xe8 lib/dump_stack.c:120) [<81809de0>] (dump_stack) from [<81804a00>] (print_usage_bug.part.0+0x228/0x230 kernel/locking/lockdep.c:3806) r7:86bcb768 r6:81a0326c r5:830f96a8 r4:86bcb0c0 [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (print_usage_bug kernel/locking/lockdep.c:3776 [inline]) [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (valid_state kernel/locking/lockdep.c:3818 [inline]) [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (mark_lock_irq kernel/locking/lockdep.c:4021 [inline]) [<818047d8>] (print_usage_bug.part.0) from [<802bb1b8>] (mark_lock.part.0+0xc34/0x136c kernel/locking/lockdep.c:4478) r10:83278fe8 r9:82c6d748 r8:00000000 r7:82c6d2d4 r6:00000004 r5:86bcb768 r4:00000006 [<802ba584>] (mark_lock.part.0) from [<802bc644>] (mark_lock kernel/locking/lockdep.c:4442 [inline]) [<802ba584>] (mark_lock.part.0) from [<802bc644>] (mark_usage kernel/locking/lockdep.c:4391 [inline]) [<802ba584>] (mark_lock.part.0) from [<802bc644>] (__lock_acquire+0x9bc/0x3318 kernel/locking/lockdep.c:4854) r10:86bcb768 r9:86bcb0c0 r8:00000001 r7:00040000 r6:0000075a r5:830f96a8 r4:00000000 [<802bbc88>] (__lock_acquire) from [<802bfb90>] (lock_acquire.part.0+0xf0/0x41c kernel/locking/lockdep.c:5510) r10:00000000 r9:600d0013 r8:00000000 r7:00000000 r6:828a2680 r5:828a2680 r4:861e5bc8 [<802bfaa0>] (lock_acquire.part.0) from [<802bff28>] (lock_acquire+0x6c/0x74 kernel/locking/lockdep.c:5483) r10:8146137c r9:00000000 r8:00000001 r7:00000000 r6:00000000 r5:00000000 r4:ff7c9dec [<802bfebc>] (lock_acquire) from [<81381eb4>] (do_write_seqcount_begin_nested include/linux/seqlock.h:520 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (do_write_seqcount_begin include/linux/seqlock.h:545 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (u64_stats_update_begin include/linux/u64_stats_sync.h:129 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (__bpf_prog_run_save_cb include/linux/filter.h:727 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (bpf_prog_run_save_cb include/linux/filter.h:741 [inline]) [<802bfebc>] (lock_acquire) from [<81381eb4>] (sk_filter_trim_cap+0x26c/0x434 net/core/filter.c:149) r10:a4095dd0 r9:ff7c9dd0 r8:e44be000 r7:8146137c r6:00000001 r5:8611ba80 r4:00000000 [<81381c48>] (sk_filter_trim_cap) from [<8146137c>] (sk_filter include/linux/filter.h:867 [inline]) [<81381c48>] (sk_filter_trim_cap) from [<8146137c>] (do_one_broadcast net/netlink/af_netlink.c:1468 [inline]) [<81381c48>] (sk_filter_trim_cap) from [<8146137c>] (netlink_broadcast_filtered+0x27c/0x4fc net/netlink/af_netlink.c:1520) r10:00000001 r9:833d6b1c r8:00000000 r7:8572f864 r6:8611ba80 r5:8698d800 r4:8572f800 [<81461100>] (netlink_broadcast_filtered) from [<81463e60>] (netlink_broadcast net/netlink/af_netlink.c:1544 [inline]) [<81461100>] (netlink_broadcast_filtered) from [<81463e60>] (netlink_sendmsg+0x3d0/0x478 net/netlink/af_netlink.c:1925) r10:00000000 r9:00000002 r8:8698d800 r7:000000b7 r6:8611b900 r5:861e5f50 r4:86aa3000 [<81463a90>] (netlink_sendmsg) from [<81321f54>] (sock_sendmsg_nosec net/socket.c:654 [inline]) [<81463a90>] (netlink_sendmsg) from [<81321f54>] (sock_sendmsg+0x3c/0x4c net/socket.c:674) r10:00000000 r9:861e5dd4 r8:00000000 r7:86570000 r6:00000000 r5:86570000 r4:861e5f50 [<81321f18>] (sock_sendmsg) from [<813234d0>] (____sys_sendmsg+0x230/0x29c net/socket.c:2350) r5:00000040 r4:861e5f50 [<813232a0>] (____sys_sendmsg) from [<8132549c>] (___sys_sendmsg+0xac/0xe4 net/socket.c:2404) r10:00000128 r9:861e4000 r8:00000000 r7:00000000 r6:86570000 r5:861e5f50 r4:00000000 [<813253f0>] (___sys_sendmsg) from [<81325684>] (__sys_sendmsg net/socket.c:2433 [inline]) [<813253f0>] (___sys_sendmsg) from [<81325684>] (__do_sys_sendmsg net/socket.c:2442 [inline]) [<813253f0>] (___sys_sendmsg) from [<81325684>] (sys_sendmsg+0x58/0xa0 net/socket.c:2440) r8:80200224 r7:00000128 r6:00000000 r5:7eaa541c r4:86570000 [<8132562c>] (sys_sendmsg) from [<80200060>] (ret_fast_syscall+0x0/0x2c arch/arm/mm/proc-v7.S:64) Exception stack(0x861e5fa8 to 0x861e5ff0) 5fa0: 00000000 00000000 0000000c 7eaa541c 00000000 00000000 5fc0: 00000000 00000000 76fbf840 00000128 00000000 0000008f 7eaa541c 000563f8 5fe0: 00056110 7eaa53e0 00036cec 76c9bf44 r6:76fbf840 r5:00000000 r4:00000000 Fixes: 492ecee892c2 ("bpf: enable program stats") Reported-by: syzbot Signed-off-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211026214133.3114279-2-eric.dumazet@gmail.com --- include/linux/filter.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 47f80adbe744..2fffe9cc50f9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -612,13 +612,14 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 start = sched_clock(); + unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); stats = this_cpu_ptr(prog->stats); - u64_stats_update_begin(&stats->syncp); + flags = u64_stats_update_begin_irqsave(&stats->syncp); stats->cnt++; stats->nsecs += sched_clock() - start; - u64_stats_update_end(&stats->syncp); + u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } -- cgit v1.2.3 From 61a0abaee2092eee69e44fe60336aa2f5b578938 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2021 14:41:33 -0700 Subject: bpf: Use u64_stats_t in struct bpf_prog_stats Commit 316580b69d0a ("u64_stats: provide u64_stats_t type") fixed possible load/store tearing on 64bit arches. For instance the following C code stats->nsecs += sched_clock() - start; Could be rightfully implemented like this by a compiler, confusing concurrent readers a lot: stats->nsecs += sched_clock(); // arbitrary delay stats->nsecs -= start; Signed-off-by: Eric Dumazet Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211026214133.3114279-4-eric.dumazet@gmail.com --- include/linux/filter.h | 10 +++++----- kernel/bpf/syscall.c | 18 ++++++++++++------ kernel/bpf/trampoline.c | 6 +++--- 3 files changed, 20 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 2fffe9cc50f9..9782e3245852 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -553,9 +553,9 @@ struct bpf_binary_header { }; struct bpf_prog_stats { - u64 cnt; - u64 nsecs; - u64 misses; + u64_stats_t cnt; + u64_stats_t nsecs; + u64_stats_t misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); @@ -617,8 +617,8 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, ret = dfunc(ctx, prog->insnsi, prog->bpf_func); stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); - stats->cnt++; - stats->nsecs += sched_clock() - start; + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, sched_clock() - start); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5beb321b3b3b..3e1c024ce3ed 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1804,8 +1804,14 @@ static int bpf_prog_release(struct inode *inode, struct file *filp) return 0; } +struct bpf_prog_kstats { + u64 nsecs; + u64 cnt; + u64 misses; +}; + static void bpf_prog_get_stats(const struct bpf_prog *prog, - struct bpf_prog_stats *stats) + struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; @@ -1818,9 +1824,9 @@ static void bpf_prog_get_stats(const struct bpf_prog *prog, st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin_irq(&st->syncp); - tnsecs = st->nsecs; - tcnt = st->cnt; - tmisses = st->misses; + tnsecs = u64_stats_read(&st->nsecs); + tcnt = u64_stats_read(&st->cnt); + tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry_irq(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; @@ -1836,7 +1842,7 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); @@ -3577,7 +3583,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_prog_info info; u32 info_len = attr->info.info_len; - struct bpf_prog_stats stats; + struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e5963de368ed..e98de5e73ba5 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -545,7 +545,7 @@ static void notrace inc_misses_counter(struct bpf_prog *prog) stats = this_cpu_ptr(prog->stats); u64_stats_update_begin(&stats->syncp); - stats->misses++; + u64_stats_inc(&stats->misses); u64_stats_update_end(&stats->syncp); } @@ -590,8 +590,8 @@ static void notrace update_prog_stats(struct bpf_prog *prog, stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); - stats->cnt++; - stats->nsecs += sched_clock() - start; + u64_stats_inc(&stats->cnt); + u64_stats_add(&stats->nsecs, sched_clock() - start); u64_stats_update_end_irqrestore(&stats->syncp, flags); } } -- cgit v1.2.3 From 259714100d98b50bf04d36a21bf50ca8b829fc11 Mon Sep 17 00:00:00 2001 From: Chunfeng Yun Date: Mon, 25 Oct 2021 15:01:53 +0800 Subject: PM / wakeirq: support enabling wake-up irq after runtime_suspend called When the dedicated wake IRQ is level trigger, and it uses the device's low-power status as the wakeup source, that means if the device is not in low-power state, the wake IRQ will be triggered if enabled; For this case, need enable the wake IRQ after running the device's ->runtime_suspend() which make it enter low-power state. e.g. Assume the wake IRQ is a low level trigger type, and the wakeup signal comes from the low-power status of the device. The wakeup signal is low level at running time (0), and becomes high level when the device enters low-power state (runtime_suspend (1) is called), a wakeup event at (2) make the device exit low-power state, then the wakeup signal also becomes low level. ------------------ | ^ ^| ---------------- | | -------------- |<---(0)--->|<--(1)--| (3) (2) (4) if enable the wake IRQ before running runtime_suspend during (0), a wake IRQ will arise, it causes resume immediately; it works if enable wake IRQ ( e.g. at (3) or (4)) after running ->runtime_suspend(). This patch introduces a new status WAKE_IRQ_DEDICATED_REVERSE to optionally support enabling wake IRQ after running ->runtime_suspend(). Suggested-by: Rafael J. Wysocki Signed-off-by: Chunfeng Yun Signed-off-by: Rafael J. Wysocki --- drivers/base/power/power.h | 7 ++- drivers/base/power/runtime.c | 6 ++- drivers/base/power/wakeirq.c | 101 ++++++++++++++++++++++++++++++++++--------- include/linux/pm_wakeirq.h | 9 +++- 4 files changed, 96 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h index 54292cdd7808..0eb7f02b3ad5 100644 --- a/drivers/base/power/power.h +++ b/drivers/base/power/power.h @@ -25,8 +25,10 @@ extern u64 pm_runtime_active_time(struct device *dev); #define WAKE_IRQ_DEDICATED_ALLOCATED BIT(0) #define WAKE_IRQ_DEDICATED_MANAGED BIT(1) +#define WAKE_IRQ_DEDICATED_REVERSE BIT(2) #define WAKE_IRQ_DEDICATED_MASK (WAKE_IRQ_DEDICATED_ALLOCATED | \ - WAKE_IRQ_DEDICATED_MANAGED) + WAKE_IRQ_DEDICATED_MANAGED | \ + WAKE_IRQ_DEDICATED_REVERSE) struct wake_irq { struct device *dev; @@ -39,7 +41,8 @@ extern void dev_pm_arm_wake_irq(struct wake_irq *wirq); extern void dev_pm_disarm_wake_irq(struct wake_irq *wirq); extern void dev_pm_enable_wake_irq_check(struct device *dev, bool can_change_status); -extern void dev_pm_disable_wake_irq_check(struct device *dev); +extern void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable); +extern void dev_pm_enable_wake_irq_complete(struct device *dev); #ifdef CONFIG_PM_SLEEP diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index ec94049442b9..d504cd4ab3cb 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -645,6 +645,8 @@ static int rpm_suspend(struct device *dev, int rpmflags) if (retval) goto fail; + dev_pm_enable_wake_irq_complete(dev); + no_callback: __update_runtime_status(dev, RPM_SUSPENDED); pm_runtime_deactivate_timer(dev); @@ -690,7 +692,7 @@ static int rpm_suspend(struct device *dev, int rpmflags) return retval; fail: - dev_pm_disable_wake_irq_check(dev); + dev_pm_disable_wake_irq_check(dev, true); __update_runtime_status(dev, RPM_ACTIVE); dev->power.deferred_resume = false; wake_up_all(&dev->power.wait_queue); @@ -873,7 +875,7 @@ static int rpm_resume(struct device *dev, int rpmflags) callback = RPM_GET_CALLBACK(dev, runtime_resume); - dev_pm_disable_wake_irq_check(dev); + dev_pm_disable_wake_irq_check(dev, false); retval = rpm_callback(callback, dev); if (retval) { __update_runtime_status(dev, RPM_SUSPENDED); diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c index b91a3a9bf9f6..0004db4a9d3b 100644 --- a/drivers/base/power/wakeirq.c +++ b/drivers/base/power/wakeirq.c @@ -142,24 +142,7 @@ static irqreturn_t handle_threaded_wake_irq(int irq, void *_wirq) return IRQ_HANDLED; } -/** - * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt - * @dev: Device entry - * @irq: Device wake-up interrupt - * - * Unless your hardware has separate wake-up interrupts in addition - * to the device IO interrupts, you don't need this. - * - * Sets up a threaded interrupt handler for a device that has - * a dedicated wake-up interrupt in addition to the device IO - * interrupt. - * - * The interrupt starts disabled, and needs to be managed for - * the device by the bus code or the device driver using - * dev_pm_enable_wake_irq() and dev_pm_disable_wake_irq() - * functions. - */ -int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) +static int __dev_pm_set_dedicated_wake_irq(struct device *dev, int irq, unsigned int flag) { struct wake_irq *wirq; int err; @@ -197,7 +180,7 @@ int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) if (err) goto err_free_irq; - wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED; + wirq->status = WAKE_IRQ_DEDICATED_ALLOCATED | flag; return err; @@ -210,8 +193,57 @@ err_free: return err; } + + +/** + * dev_pm_set_dedicated_wake_irq - Request a dedicated wake-up interrupt + * @dev: Device entry + * @irq: Device wake-up interrupt + * + * Unless your hardware has separate wake-up interrupts in addition + * to the device IO interrupts, you don't need this. + * + * Sets up a threaded interrupt handler for a device that has + * a dedicated wake-up interrupt in addition to the device IO + * interrupt. + * + * The interrupt starts disabled, and needs to be managed for + * the device by the bus code or the device driver using + * dev_pm_enable_wake_irq*() and dev_pm_disable_wake_irq*() + * functions. + */ +int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) +{ + return __dev_pm_set_dedicated_wake_irq(dev, irq, 0); +} EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq); +/** + * dev_pm_set_dedicated_wake_irq_reverse - Request a dedicated wake-up interrupt + * with reverse enable ordering + * @dev: Device entry + * @irq: Device wake-up interrupt + * + * Unless your hardware has separate wake-up interrupts in addition + * to the device IO interrupts, you don't need this. + * + * Sets up a threaded interrupt handler for a device that has a dedicated + * wake-up interrupt in addition to the device IO interrupt. It sets + * the status of WAKE_IRQ_DEDICATED_REVERSE to tell rpm_suspend() + * to enable dedicated wake-up interrupt after running the runtime suspend + * callback for @dev. + * + * The interrupt starts disabled, and needs to be managed for + * the device by the bus code or the device driver using + * dev_pm_enable_wake_irq*() and dev_pm_disable_wake_irq*() + * functions. + */ +int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq) +{ + return __dev_pm_set_dedicated_wake_irq(dev, irq, WAKE_IRQ_DEDICATED_REVERSE); +} +EXPORT_SYMBOL_GPL(dev_pm_set_dedicated_wake_irq_reverse); + /** * dev_pm_enable_wake_irq - Enable device wake-up interrupt * @dev: Device @@ -282,27 +314,54 @@ void dev_pm_enable_wake_irq_check(struct device *dev, return; enable: - enable_irq(wirq->irq); + if (!can_change_status || !(wirq->status & WAKE_IRQ_DEDICATED_REVERSE)) + enable_irq(wirq->irq); } /** * dev_pm_disable_wake_irq_check - Checks and disables wake-up interrupt * @dev: Device + * @cond_disable: if set, also check WAKE_IRQ_DEDICATED_REVERSE * * Disables wake-up interrupt conditionally based on status. * Should be only called from rpm_suspend() and rpm_resume() path. */ -void dev_pm_disable_wake_irq_check(struct device *dev) +void dev_pm_disable_wake_irq_check(struct device *dev, bool cond_disable) { struct wake_irq *wirq = dev->power.wakeirq; if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK)) return; + if (cond_disable && (wirq->status & WAKE_IRQ_DEDICATED_REVERSE)) + return; + if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED) disable_irq_nosync(wirq->irq); } +/** + * dev_pm_enable_wake_irq_complete - enable wake IRQ not enabled before + * @dev: Device using the wake IRQ + * + * Enable wake IRQ conditionally based on status, mainly used if want to + * enable wake IRQ after running ->runtime_suspend() which depends on + * WAKE_IRQ_DEDICATED_REVERSE. + * + * Should be only called from rpm_suspend() path. + */ +void dev_pm_enable_wake_irq_complete(struct device *dev) +{ + struct wake_irq *wirq = dev->power.wakeirq; + + if (!wirq || !(wirq->status & WAKE_IRQ_DEDICATED_MASK)) + return; + + if (wirq->status & WAKE_IRQ_DEDICATED_MANAGED && + wirq->status & WAKE_IRQ_DEDICATED_REVERSE) + enable_irq(wirq->irq); +} + /** * dev_pm_arm_wake_irq - Arm device wake-up * @wirq: Device wake-up interrupt diff --git a/include/linux/pm_wakeirq.h b/include/linux/pm_wakeirq.h index cd5b62db9084..e63a63aa47a3 100644 --- a/include/linux/pm_wakeirq.h +++ b/include/linux/pm_wakeirq.h @@ -17,8 +17,8 @@ #ifdef CONFIG_PM extern int dev_pm_set_wake_irq(struct device *dev, int irq); -extern int dev_pm_set_dedicated_wake_irq(struct device *dev, - int irq); +extern int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq); +extern int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq); extern void dev_pm_clear_wake_irq(struct device *dev); extern void dev_pm_enable_wake_irq(struct device *dev); extern void dev_pm_disable_wake_irq(struct device *dev); @@ -35,6 +35,11 @@ static inline int dev_pm_set_dedicated_wake_irq(struct device *dev, int irq) return 0; } +static inline int dev_pm_set_dedicated_wake_irq_reverse(struct device *dev, int irq) +{ + return 0; +} + static inline void dev_pm_clear_wake_irq(struct device *dev) { } -- cgit v1.2.3 From 570b1cac477643cbf01a45fa5d018430a1fddbce Mon Sep 17 00:00:00 2001 From: Xie Yongji Date: Tue, 26 Oct 2021 22:40:12 +0800 Subject: block: Add a helper to validate the block size There are some duplicated codes to validate the block size in block drivers. This limitation actually comes from block layer, so this patch tries to add a new block layer helper for that. Signed-off-by: Xie Yongji Link: https://lore.kernel.org/r/20211026144015.188-2-xieyongji@bytedance.com Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6d95a4b36cfa..d2d627e2c782 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -44,6 +44,14 @@ struct blk_crypto_profile; */ #define BLKCG_MAX_POLS 6 +static inline int blk_validate_block_size(unsigned int bsize) +{ + if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) + return -EINVAL; + + return 0; +} + static inline bool blk_op_is_passthrough(unsigned int op) { op &= REQ_OP_MASK; -- cgit v1.2.3 From 9dfc685e0262d4c5e44e13302f89841fa75173ca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 26 Oct 2021 14:30:14 -0700 Subject: inet: remove races in inet{6}_getname() syzbot reported data-races in inet_getname() multiple times, it is time we fix this instead of pretending applications should not trigger them. getsockname() and getpeername() are not really considered fast path. v2: added the missing BPF_CGROUP_RUN_SA_PROG() declaration needed when CONFIG_CGROUP_BPF=n, as reported by kernel test robot syzbot typical report: BUG: KCSAN: data-race in __inet_hash_connect / inet_getname write to 0xffff888136d66cf8 of 2 bytes by task 14374 on cpu 1: __inet_hash_connect+0x7ec/0x950 net/ipv4/inet_hashtables.c:831 inet_hash_connect+0x85/0x90 net/ipv4/inet_hashtables.c:853 tcp_v4_connect+0x782/0xbb0 net/ipv4/tcp_ipv4.c:275 __inet_stream_connect+0x156/0x6e0 net/ipv4/af_inet.c:664 inet_stream_connect+0x44/0x70 net/ipv4/af_inet.c:728 __sys_connect_file net/socket.c:1896 [inline] __sys_connect+0x254/0x290 net/socket.c:1913 __do_sys_connect net/socket.c:1923 [inline] __se_sys_connect net/socket.c:1920 [inline] __x64_sys_connect+0x3d/0x50 net/socket.c:1920 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xa0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888136d66cf8 of 2 bytes by task 14408 on cpu 0: inet_getname+0x11f/0x170 net/ipv4/af_inet.c:790 __sys_getsockname+0x11d/0x1b0 net/socket.c:1946 __do_sys_getsockname net/socket.c:1961 [inline] __se_sys_getsockname net/socket.c:1958 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:1958 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xa0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x0000 -> 0xdee0 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 14408 Comm: syz-executor.3 Not tainted 5.15.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20211026213014.3026708-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/bpf-cgroup.h | 1 + net/ipv4/af_inet.c | 16 +++++++++------- net/ipv6/af_inet6.c | 21 +++++++++++---------- 3 files changed, 21 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 2746fd804216..3536ab432b30 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -517,6 +517,7 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define cgroup_bpf_enabled(atype) (0) #define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 8eb428387bac..31d5cefa9979 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -769,26 +769,28 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); sin->sin_family = AF_INET; + lock_sock(sk); if (peer) { if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && - peer == 1)) + peer == 1)) { + release_sock(sk); return -ENOTCONN; + } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - CGROUP_INET4_GETPEERNAME, - NULL); + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; if (!addr) addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - CGROUP_INET4_GETSOCKNAME, - NULL); + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + CGROUP_INET4_GETSOCKNAME); } + release_sock(sk); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); return sizeof(*sin); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b5878bb8e419..0c4da163535a 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -521,31 +521,32 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_family = AF_INET6; sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; + lock_sock(sk); if (peer) { - if (!inet->inet_dport) - return -ENOTCONN; - if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && - peer == 1) + if (!inet->inet_dport || + (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && + peer == 1)) { + release_sock(sk); return -ENOTCONN; + } sin->sin6_port = inet->inet_dport; sin->sin6_addr = sk->sk_v6_daddr; if (np->sndflow) sin->sin6_flowinfo = np->flow_label; - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - CGROUP_INET6_GETPEERNAME, - NULL); + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + CGROUP_INET6_GETPEERNAME); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) sin->sin6_addr = np->saddr; else sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, (struct sockaddr *)sin, - CGROUP_INET6_GETSOCKNAME, - NULL); + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + CGROUP_INET6_GETSOCKNAME); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); + release_sock(sk); return sizeof(*sin); } EXPORT_SYMBOL(inet6_getname); -- cgit v1.2.3 From d4dccf353db80e209f262e3973c834e6e48ba9a9 Mon Sep 17 00:00:00 2001 From: Tianyu Lan Date: Mon, 25 Oct 2021 08:21:09 -0400 Subject: Drivers: hv: vmbus: Mark vmbus ring buffer visible to host in Isolation VM Mark vmbus ring buffer visible with set_memory_decrypted() when establish gpadl handle. Reviewed-by: Michael Kelley Signed-off-by: Tianyu Lan Link: https://lore.kernel.org/r/20211025122116.264793-5-ltykernel@gmail.com Signed-off-by: Wei Liu --- drivers/hv/channel.c | 53 +++++++++++++++++++++++++++++------------ drivers/net/hyperv/hyperv_net.h | 5 ++-- drivers/net/hyperv/netvsc.c | 15 ++++++------ drivers/uio/uio_hv_generic.c | 18 +++++++------- include/linux/hyperv.h | 12 +++++++--- 5 files changed, 65 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index f3761c73b074..b37ff4a39224 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -456,7 +457,7 @@ nomem: static int __vmbus_establish_gpadl(struct vmbus_channel *channel, enum hv_gpadl_type type, void *kbuffer, u32 size, u32 send_offset, - u32 *gpadl_handle) + struct vmbus_gpadl *gpadl) { struct vmbus_channel_gpadl_header *gpadlmsg; struct vmbus_channel_gpadl_body *gpadl_body; @@ -474,6 +475,15 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, if (ret) return ret; + ret = set_memory_decrypted((unsigned long)kbuffer, + PFN_UP(size)); + if (ret) { + dev_warn(&channel->device_obj->device, + "Failed to set host visibility for new GPADL %d.\n", + ret); + return ret; + } + init_completion(&msginfo->waitevent); msginfo->waiting_channel = channel; @@ -537,7 +547,10 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, } /* At this point, we received the gpadl created msg */ - *gpadl_handle = gpadlmsg->gpadl; + gpadl->gpadl_handle = gpadlmsg->gpadl; + gpadl->buffer = kbuffer; + gpadl->size = size; + cleanup: spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); @@ -549,6 +562,11 @@ cleanup: } kfree(msginfo); + + if (ret) + set_memory_encrypted((unsigned long)kbuffer, + PFN_UP(size)); + return ret; } @@ -561,10 +579,10 @@ cleanup: * @gpadl_handle: some funky thing */ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, - u32 size, u32 *gpadl_handle) + u32 size, struct vmbus_gpadl *gpadl) { return __vmbus_establish_gpadl(channel, HV_GPADL_BUFFER, kbuffer, size, - 0U, gpadl_handle); + 0U, gpadl); } EXPORT_SYMBOL_GPL(vmbus_establish_gpadl); @@ -675,7 +693,7 @@ static int __vmbus_open(struct vmbus_channel *newchannel, goto error_clean_ring; /* Establish the gpadl for the ring buffer */ - newchannel->ringbuffer_gpadlhandle = 0; + newchannel->ringbuffer_gpadlhandle.gpadl_handle = 0; err = __vmbus_establish_gpadl(newchannel, HV_GPADL_RING, page_address(newchannel->ringbuffer_page), @@ -701,7 +719,8 @@ static int __vmbus_open(struct vmbus_channel *newchannel, open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL; open_msg->openid = newchannel->offermsg.child_relid; open_msg->child_relid = newchannel->offermsg.child_relid; - open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle; + open_msg->ringbuffer_gpadlhandle + = newchannel->ringbuffer_gpadlhandle.gpadl_handle; /* * The unit of ->downstream_ringbuffer_pageoffset is HV_HYP_PAGE and * the unit of ->ringbuffer_send_offset (i.e. send_pages) is PAGE, so @@ -759,8 +778,7 @@ error_clean_msglist: error_free_info: kfree(open_info); error_free_gpadl: - vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle); - newchannel->ringbuffer_gpadlhandle = 0; + vmbus_teardown_gpadl(newchannel, &newchannel->ringbuffer_gpadlhandle); error_clean_ring: hv_ringbuffer_cleanup(&newchannel->outbound); hv_ringbuffer_cleanup(&newchannel->inbound); @@ -806,7 +824,7 @@ EXPORT_SYMBOL_GPL(vmbus_open); /* * vmbus_teardown_gpadl -Teardown the specified GPADL handle */ -int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) +int vmbus_teardown_gpadl(struct vmbus_channel *channel, struct vmbus_gpadl *gpadl) { struct vmbus_channel_gpadl_teardown *msg; struct vmbus_channel_msginfo *info; @@ -825,7 +843,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) msg->header.msgtype = CHANNELMSG_GPADL_TEARDOWN; msg->child_relid = channel->offermsg.child_relid; - msg->gpadl = gpadl_handle; + msg->gpadl = gpadl->gpadl_handle; spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_add_tail(&info->msglistentry, @@ -845,6 +863,8 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle) wait_for_completion(&info->waitevent); + gpadl->gpadl_handle = 0; + post_msg_err: /* * If the channel has been rescinded; @@ -859,6 +879,12 @@ post_msg_err: spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); kfree(info); + + ret = set_memory_encrypted((unsigned long)gpadl->buffer, + PFN_UP(gpadl->size)); + if (ret) + pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret); + return ret; } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); @@ -933,9 +959,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel) } /* Tear down the gpadl for the channel's ring buffer */ - else if (channel->ringbuffer_gpadlhandle) { - ret = vmbus_teardown_gpadl(channel, - channel->ringbuffer_gpadlhandle); + else if (channel->ringbuffer_gpadlhandle.gpadl_handle) { + ret = vmbus_teardown_gpadl(channel, &channel->ringbuffer_gpadlhandle); if (ret) { pr_err("Close failed: teardown gpadl return %d\n", ret); /* @@ -943,8 +968,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel) * it is perhaps better to leak memory. */ } - - channel->ringbuffer_gpadlhandle = 0; } if (!ret) diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index bc48855dff10..315278a7cf88 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1075,14 +1075,15 @@ struct netvsc_device { /* Receive buffer allocated by us but manages by NetVSP */ void *recv_buf; u32 recv_buf_size; /* allocated bytes */ - u32 recv_buf_gpadl_handle; + struct vmbus_gpadl recv_buf_gpadl_handle; u32 recv_section_cnt; u32 recv_section_size; u32 recv_completion_cnt; /* Send buffer allocated by us */ void *send_buf; - u32 send_buf_gpadl_handle; + u32 send_buf_size; + struct vmbus_gpadl send_buf_gpadl_handle; u32 send_section_cnt; u32 send_section_size; unsigned long *send_section_map; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 7bd935412853..396bc1c204e6 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -278,9 +278,9 @@ static void netvsc_teardown_recv_gpadl(struct hv_device *device, { int ret; - if (net_device->recv_buf_gpadl_handle) { + if (net_device->recv_buf_gpadl_handle.gpadl_handle) { ret = vmbus_teardown_gpadl(device->channel, - net_device->recv_buf_gpadl_handle); + &net_device->recv_buf_gpadl_handle); /* If we failed here, we might as well return and have a leak * rather than continue and a bugchk @@ -290,7 +290,6 @@ static void netvsc_teardown_recv_gpadl(struct hv_device *device, "unable to teardown receive buffer's gpadl\n"); return; } - net_device->recv_buf_gpadl_handle = 0; } } @@ -300,9 +299,9 @@ static void netvsc_teardown_send_gpadl(struct hv_device *device, { int ret; - if (net_device->send_buf_gpadl_handle) { + if (net_device->send_buf_gpadl_handle.gpadl_handle) { ret = vmbus_teardown_gpadl(device->channel, - net_device->send_buf_gpadl_handle); + &net_device->send_buf_gpadl_handle); /* If we failed here, we might as well return and have a leak * rather than continue and a bugchk @@ -312,7 +311,6 @@ static void netvsc_teardown_send_gpadl(struct hv_device *device, "unable to teardown send buffer's gpadl\n"); return; } - net_device->send_buf_gpadl_handle = 0; } } @@ -380,7 +378,7 @@ static int netvsc_init_buf(struct hv_device *device, memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_RECV_BUF; init_packet->msg.v1_msg.send_recv_buf. - gpadl_handle = net_device->recv_buf_gpadl_handle; + gpadl_handle = net_device->recv_buf_gpadl_handle.gpadl_handle; init_packet->msg.v1_msg. send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID; @@ -463,6 +461,7 @@ static int netvsc_init_buf(struct hv_device *device, ret = -ENOMEM; goto cleanup; } + net_device->send_buf_size = buf_size; /* Establish the gpadl handle for this buffer on this * channel. Note: This call uses the vmbus connection rather @@ -482,7 +481,7 @@ static int netvsc_init_buf(struct hv_device *device, memset(init_packet, 0, sizeof(struct nvsp_message)); init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF; init_packet->msg.v1_msg.send_send_buf.gpadl_handle = - net_device->send_buf_gpadl_handle; + net_device->send_buf_gpadl_handle.gpadl_handle; init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID; trace_nvsp_send(ndev, init_packet); diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 652fe2547587..c08a6cfd119f 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -58,11 +58,11 @@ struct hv_uio_private_data { atomic_t refcnt; void *recv_buf; - u32 recv_gpadl; + struct vmbus_gpadl recv_gpadl; char recv_name[32]; /* "recv_4294967295" */ void *send_buf; - u32 send_gpadl; + struct vmbus_gpadl send_gpadl; char send_name[32]; }; @@ -179,15 +179,13 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) static void hv_uio_cleanup(struct hv_device *dev, struct hv_uio_private_data *pdata) { - if (pdata->send_gpadl) { - vmbus_teardown_gpadl(dev->channel, pdata->send_gpadl); - pdata->send_gpadl = 0; + if (pdata->send_gpadl.gpadl_handle) { + vmbus_teardown_gpadl(dev->channel, &pdata->send_gpadl); vfree(pdata->send_buf); } - if (pdata->recv_gpadl) { - vmbus_teardown_gpadl(dev->channel, pdata->recv_gpadl); - pdata->recv_gpadl = 0; + if (pdata->recv_gpadl.gpadl_handle) { + vmbus_teardown_gpadl(dev->channel, &pdata->recv_gpadl); vfree(pdata->recv_buf); } } @@ -303,7 +301,7 @@ hv_uio_probe(struct hv_device *dev, /* put Global Physical Address Label in name */ snprintf(pdata->recv_name, sizeof(pdata->recv_name), - "recv:%u", pdata->recv_gpadl); + "recv:%u", pdata->recv_gpadl.gpadl_handle); pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name; pdata->info.mem[RECV_BUF_MAP].addr = (uintptr_t)pdata->recv_buf; @@ -324,7 +322,7 @@ hv_uio_probe(struct hv_device *dev, } snprintf(pdata->send_name, sizeof(pdata->send_name), - "send:%u", pdata->send_gpadl); + "send:%u", pdata->send_gpadl.gpadl_handle); pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name; pdata->info.mem[SEND_BUF_MAP].addr = (uintptr_t)pdata->send_buf; diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index ddc8713ce57b..a9e0bc3b1511 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -803,6 +803,12 @@ struct vmbus_device { #define VMBUS_DEFAULT_MAX_PKT_SIZE 4096 +struct vmbus_gpadl { + u32 gpadl_handle; + u32 size; + void *buffer; +}; + struct vmbus_channel { struct list_head listentry; @@ -822,7 +828,7 @@ struct vmbus_channel { bool rescind_ref; /* got rescind msg, got channel reference */ struct completion rescind_event; - u32 ringbuffer_gpadlhandle; + struct vmbus_gpadl ringbuffer_gpadlhandle; /* Allocated memory for ring buffer */ struct page *ringbuffer_page; @@ -1192,10 +1198,10 @@ extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, extern int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, u32 size, - u32 *gpadl_handle); + struct vmbus_gpadl *gpadl); extern int vmbus_teardown_gpadl(struct vmbus_channel *channel, - u32 gpadl_handle); + struct vmbus_gpadl *gpadl); void vmbus_reset_channel_cb(struct vmbus_channel *channel); -- cgit v1.2.3 From 20cf6616ccd50256a14fb2a7a3cc730080c90cd0 Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Mon, 25 Oct 2021 12:54:34 -0700 Subject: Drivers: hv: vmbus: Remove unused code to check for subchannels The last caller of vmbus_are_subchannels_present() was removed in commit c967590457ca ("scsi: storvsc: Fix a race in sub-channel creation that can cause panic"). Remove this dead code, and the utility function invoke_sc_cb() that it is the only caller of. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/1635191674-34407-1-git-send-email-mikelley@microsoft.com Signed-off-by: Wei Liu --- drivers/hv/channel_mgmt.c | 34 ---------------------------------- include/linux/hyperv.h | 13 ------------- 2 files changed, 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 142308526ec6..2829575fd9b7 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -1581,21 +1581,6 @@ cleanup: return ret; } -static void invoke_sc_cb(struct vmbus_channel *primary_channel) -{ - struct list_head *cur, *tmp; - struct vmbus_channel *cur_channel; - - if (primary_channel->sc_creation_callback == NULL) - return; - - list_for_each_safe(cur, tmp, &primary_channel->sc_list) { - cur_channel = list_entry(cur, struct vmbus_channel, sc_list); - - primary_channel->sc_creation_callback(cur_channel); - } -} - void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, void (*sc_cr_cb)(struct vmbus_channel *new_sc)) { @@ -1603,25 +1588,6 @@ void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, } EXPORT_SYMBOL_GPL(vmbus_set_sc_create_callback); -bool vmbus_are_subchannels_present(struct vmbus_channel *primary) -{ - bool ret; - - ret = !list_empty(&primary->sc_list); - - if (ret) { - /* - * Invoke the callback on sub-channel creation. - * This will present a uniform interface to the - * clients. - */ - invoke_sc_cb(primary); - } - - return ret; -} -EXPORT_SYMBOL_GPL(vmbus_are_subchannels_present); - void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel, void (*chn_rescind_cb)(struct vmbus_channel *)) { diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index a9e0bc3b1511..b823311eac79 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1106,19 +1106,6 @@ void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel, void (*chn_rescind_cb)(struct vmbus_channel *)); -/* - * Check if sub-channels have already been offerred. This API will be useful - * when the driver is unloaded after establishing sub-channels. In this case, - * when the driver is re-loaded, the driver would have to check if the - * subchannels have already been established before attempting to request - * the creation of sub-channels. - * This function returns TRUE to indicate that subchannels have already been - * created. - * This function should be invoked after setting the callback function for - * sub-channel creation. - */ -bool vmbus_are_subchannels_present(struct vmbus_channel *primary); - /* The format must be the same as struct vmdata_gpa_direct */ struct vmbus_channel_packet_page_buffer { u16 type; -- cgit v1.2.3 From 9330986c03006ab1d33d243b7cfe598a7a3c1baa Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 27 Oct 2021 16:45:00 -0700 Subject: bpf: Add bloom filter map implementation This patch adds the kernel-side changes for the implementation of a bpf bloom filter map. The bloom filter map supports peek (determining whether an element is present in the map) and push (adding an element to the map) operations.These operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_UPDATE_ELEM -> push The bloom filter map does not have keys, only values. In light of this, the bloom filter map's API matches that of queue stack maps: user applications use BPF_MAP_LOOKUP_ELEM/BPF_MAP_UPDATE_ELEM which correspond internally to bpf_map_peek_elem/bpf_map_push_elem, and bpf programs must use the bpf_map_peek_elem and bpf_map_push_elem APIs to query or add an element to the bloom filter map. When the bloom filter map is created, it must be created with a key_size of 0. For updates, the user will pass in the element to add to the map as the value, with a NULL key. For lookups, the user will pass in the element to query in the map as the value, with a NULL key. In the verifier layer, this requires us to modify the argument type of a bloom filter's BPF_FUNC_map_peek_elem call to ARG_PTR_TO_MAP_VALUE; as well, in the syscall layer, we need to copy over the user value so that in bpf_map_peek_elem, we know which specific value to query. A few things to please take note of: * If there are any concurrent lookups + updates, the user is responsible for synchronizing this to ensure no false negative lookups occur. * The number of hashes to use for the bloom filter is configurable from userspace. If no number is specified, the default used will be 5 hash functions. The benchmarks later in this patchset can help compare the performance of using different number of hashes on different entry sizes. In general, using more hashes decreases both the false positive rate and the speed of a lookup. * Deleting an element in the bloom filter map is not supported. * The bloom filter map may be used as an inner map. * The "max_entries" size that is specified at map creation time is used to approximate a reasonable bitmap size for the bloom filter, and is not otherwise strictly enforced. If the user wishes to insert more entries into the bloom filter than "max_entries", they may do so but they should be aware that this may lead to a higher false positive rate. Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211027234504.30744-2-joannekoong@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 9 ++ kernel/bpf/Makefile | 2 +- kernel/bpf/bloom_filter.c | 195 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 24 ++++- kernel/bpf/verifier.c | 19 +++- tools/include/uapi/linux/bpf.h | 9 ++ 8 files changed, 253 insertions(+), 7 deletions(-) create mode 100644 kernel/bpf/bloom_filter.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 31421c74ba08..50105e0b8fcc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -169,6 +169,7 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; + u64 map_extra; /* any per-map-type extra fields */ int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..c4424ac2fa02 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 7f33098ca63f..cf6ca339f3cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,7 +7,7 @@ endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c new file mode 100644 index 000000000000..7c50232b7571 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include +#include +#include +#include +#include +#include + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +struct bpf_bloom_filter { + struct bpf_map map; + u32 bitset_mask; + u32 hash_seed; + /* If the size of the values in the bloom filter is u32 aligned, + * then it is more performant to use jhash2 as the underlying hash + * function, else we use jhash. This tracks the number of u32s + * in an u32-aligned value size. If the value size is not u32 aligned, + * this will be 0. + */ + u32 aligned_u32_count; + u32 nr_hash_funcs; + unsigned long bitset[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + if (bloom->aligned_u32_count) + h = jhash2(value, bloom->aligned_u32_count, + bloom->hash_seed + index); + else + h = jhash(value, value_size, bloom->hash_seed + index); + + return h & bloom->bitset_mask; +} + +static int peek_elem(struct bpf_map *map, void *value) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +static int push_elem(struct bpf_map *map, void *value, u64 flags) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static int pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static struct bpf_map *map_alloc(union bpf_attr *attr) +{ + u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_bloom_filter *bloom; + + if (!bpf_capable()) + return ERR_PTR(-EPERM); + + if (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + /* The lower 4 bits of map_extra specify the number of hash functions */ + nr_hash_funcs = attr->map_extra & 0xF; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, attr); + + bloom->nr_hash_funcs = nr_hash_funcs; + bloom->bitset_mask = bitset_mask; + + /* Check whether the value size is u32-aligned */ + if ((attr->value_size & (sizeof(u32) - 1)) == 0) + bloom->aligned_u32_count = + attr->value_size / sizeof(u32); + + if (!(attr->map_flags & BPF_F_ZERO_SEED)) + bloom->hash_seed = get_random_int(); + + return &bloom->map; +} + +static void map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +static int update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + /* The eBPF program should use map_push_elem instead */ + return -EINVAL; +} + +static int check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + return btf_type_is_void(key_type) ? 0 : -EINVAL; +} + +static int bpf_bloom_btf_id; +const struct bpf_map_ops bloom_filter_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = map_alloc, + .map_free = map_free, + .map_push_elem = push_elem, + .map_peek_elem = peek_elem, + .map_pop_elem = pop_elem, + .map_lookup_elem = lookup_elem, + .map_update_elem = update_elem, + .map_check_btf = check_btf, + .map_btf_name = "bpf_bloom_filter", + .map_btf_id = &bpf_bloom_btf_id, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3e1c024ce3ed..f7c2c6354add 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -199,7 +199,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); @@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -553,6 +556,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -561,6 +565,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, + (unsigned long long)map->map_extra, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); @@ -810,7 +815,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -831,6 +836,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -1080,6 +1089,14 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -3881,6 +3898,7 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6616e325803..3c8aa7df1773 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5002,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, return -EINVAL; } break; - + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; default: break; } @@ -5577,6 +5580,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -5644,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; - case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: - case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { -- cgit v1.2.3 From d6aef08a872b9e23eecc92d0e92393473b13c497 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 28 Oct 2021 12:04:54 +0530 Subject: bpf: Add bpf_kallsyms_lookup_name helper This helper allows us to get the address of a kernel symbol from inside a BPF_PROG_TYPE_SYSCALL prog (used by gen_loader), so that we can relocate typeless ksym vars. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211028063501.2239335-2-memxor@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/bpf/syscall.c | 27 +++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 60 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50105e0b8fcc..6deebf8bf78f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2110,6 +2110,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f7c2c6354add..e12a217ead34 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4781,6 +4781,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -4791,6 +4816,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 78476d315e190533757ab894255c4f2c2f254bce Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 29 Oct 2021 11:01:44 +0800 Subject: mctp: Add flow extension to skb This change adds a new skb extension for MCTP, to represent a request/response flow. The intention is to use this in a later change to allow i2c controllers to correctly configure a multiplexer over a flow. Since we have a cleanup function in the core path (if an extension is present), we'll need to make CONFIG_MCTP a bool, rather than a tristate. Includes a fix for a build warning with clang: Reported-by: kernel test robot Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/linux/skbuff.h | 3 +++ include/net/mctp.h | 7 +++++++ net/core/skbuff.c | 19 +++++++++++++++++++ net/mctp/Kconfig | 7 ++++++- 4 files changed, 35 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cb96f1e6460c..0bd6520329f6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4243,6 +4243,9 @@ enum skb_ext_id { #endif #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, +#endif +#if IS_ENABLED(CONFIG_MCTP_FLOWS) + SKB_EXT_MCTP, #endif SKB_EXT_NUM, /* must be last */ }; diff --git a/include/net/mctp.h b/include/net/mctp.h index 23bec708f4c7..7a5ba801703c 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -189,6 +189,13 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) return (void *)(skb->cb); } +/* If CONFIG_MCTP_FLOWS, we may add one of these as a SKB extension, + * indicating the flow to the device driver. + */ +struct mctp_flow { + struct mctp_sk_key *key; +}; + /* Route definition. * * These are held in the pernet->mctp.routes list, with RCU protection for diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 09b8cf8ab234..67a9188d8a49 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -70,6 +70,7 @@ #include #include #include +#include #include #include @@ -4440,6 +4441,9 @@ static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif +#if IS_ENABLED(CONFIG_MCTP_FLOWS) + [SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow), +#endif }; static __always_inline unsigned int skb_ext_total_length(void) @@ -4456,6 +4460,9 @@ static __always_inline unsigned int skb_ext_total_length(void) #endif #if IS_ENABLED(CONFIG_MPTCP) skb_ext_type_len[SKB_EXT_MPTCP] + +#endif +#if IS_ENABLED(CONFIG_MCTP_FLOWS) + skb_ext_type_len[SKB_EXT_MCTP] + #endif 0; } @@ -6529,6 +6536,14 @@ static void skb_ext_put_sp(struct sec_path *sp) } #endif +#ifdef CONFIG_MCTP_FLOWS +static void skb_ext_put_mctp(struct mctp_flow *flow) +{ + if (flow->key) + mctp_key_unref(flow->key); +} +#endif + void __skb_ext_del(struct sk_buff *skb, enum skb_ext_id id) { struct skb_ext *ext = skb->extensions; @@ -6564,6 +6579,10 @@ free_now: if (__skb_ext_exist(ext, SKB_EXT_SEC_PATH)) skb_ext_put_sp(skb_ext_get_ptr(ext, SKB_EXT_SEC_PATH)); #endif +#ifdef CONFIG_MCTP_FLOWS + if (__skb_ext_exist(ext, SKB_EXT_MCTP)) + skb_ext_put_mctp(skb_ext_get_ptr(ext, SKB_EXT_MCTP)); +#endif kmem_cache_free(skbuff_ext_cache, ext); } diff --git a/net/mctp/Kconfig b/net/mctp/Kconfig index 868c92272cbd..3a5c0e70da77 100644 --- a/net/mctp/Kconfig +++ b/net/mctp/Kconfig @@ -1,7 +1,7 @@ menuconfig MCTP depends on NET - tristate "MCTP core protocol support" + bool "MCTP core protocol support" help Management Component Transport Protocol (MCTP) is an in-system protocol for communicating between management controllers and @@ -16,3 +16,8 @@ config MCTP_TEST bool "MCTP core tests" if !KUNIT_ALL_TESTS depends on MCTP=y && KUNIT=y default KUNIT_ALL_TESTS + +config MCTP_FLOWS + bool + depends on MCTP + select SKB_EXTENSIONS -- cgit v1.2.3 From 0bf6d96cb8294094ce1e44cbe8cf65b0899d0a3a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 25 Oct 2021 09:05:07 +0200 Subject: block: remove blk_{get,put}_request These are now pointless wrappers around blk_mq_{alloc,free}_request, so remove them. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Link: https://lore.kernel.org/r/20211025070517.1548584-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 21 --------------------- drivers/block/paride/pd.c | 4 ++-- drivers/block/pktcdvd.c | 2 +- drivers/block/virtio_blk.c | 4 ++-- drivers/md/dm-mpath.c | 4 ++-- drivers/mmc/core/block.c | 20 ++++++++++---------- drivers/scsi/scsi_bsg.c | 2 +- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/scsi_ioctl.c | 4 ++-- drivers/scsi/scsi_lib.c | 4 ++-- drivers/scsi/sg.c | 6 +++--- drivers/scsi/sr.c | 2 +- drivers/scsi/st.c | 4 ++-- drivers/scsi/ufs/ufshcd.c | 20 ++++++++++---------- drivers/scsi/ufs/ufshpb.c | 8 ++++---- drivers/target/target_core_pscsi.c | 4 ++-- include/linux/blk-mq.h | 3 --- 17 files changed, 45 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 5ffe05b1d17c..ac1de7d73a45 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -597,27 +597,6 @@ bool blk_get_queue(struct request_queue *q) } EXPORT_SYMBOL(blk_get_queue); -/** - * blk_get_request - allocate a request - * @q: request queue to allocate a request for - * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. - * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. - */ -struct request *blk_get_request(struct request_queue *q, unsigned int op, - blk_mq_req_flags_t flags) -{ - WARN_ON_ONCE(op & REQ_NOWAIT); - WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); - return blk_mq_alloc_request(q, op, flags); -} -EXPORT_SYMBOL(blk_get_request); - -void blk_put_request(struct request *req) -{ - blk_mq_free_request(req); -} -EXPORT_SYMBOL(blk_put_request); - static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 675327df6aff..9cd0bd509b88 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -775,14 +775,14 @@ static int pd_special_command(struct pd_unit *disk, struct request *rq; struct pd_req *req; - rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, 0); + rq = blk_mq_alloc_request(disk->gd->queue, REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); req = blk_mq_rq_to_pdu(rq); req->func = func; blk_execute_rq(disk->gd, rq, 0); - blk_put_request(rq); + blk_mq_free_request(rq); return 0; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index cacf64eedad8..40e7a45e3347 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -726,7 +726,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * if (scsi_req(rq)->result) ret = -EIO; out: - blk_put_request(rq); + blk_mq_free_request(rq); return ret; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 303caf2d17d0..f81a768943e1 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -312,7 +312,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) struct request *req; int err; - req = blk_get_request(q, REQ_OP_DRV_IN, 0); + req = blk_mq_alloc_request(q, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) return PTR_ERR(req); @@ -323,7 +323,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) blk_execute_rq(vblk->disk, req, false); err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req))); out: - blk_put_request(req); + blk_mq_free_request(req); return err; } diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 694aaca4eea2..510f6c3ab98d 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -530,7 +530,7 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, bdev = pgpath->path.dev->bdev; q = bdev_get_queue(bdev); - clone = blk_get_request(q, rq->cmd_flags | REQ_NOMERGE, + clone = blk_mq_alloc_request(q, rq->cmd_flags | REQ_NOMERGE, BLK_MQ_REQ_NOWAIT); if (IS_ERR(clone)) { /* EBUSY, ENODEV or EWOULDBLOCK: requeue */ @@ -579,7 +579,7 @@ static void multipath_release_clone(struct request *clone, clone->io_start_time_ns); } - blk_put_request(clone); + blk_mq_free_request(clone); } /* diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 431af5e8be2f..74882fa0f86d 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -258,7 +258,7 @@ static ssize_t power_ro_lock_store(struct device *dev, mq = &md->queue; /* Dispatch locking to the block layer */ - req = blk_get_request(mq->queue, REQ_OP_DRV_OUT, 0); + req = blk_mq_alloc_request(mq->queue, REQ_OP_DRV_OUT, 0); if (IS_ERR(req)) { count = PTR_ERR(req); goto out_put; @@ -266,7 +266,7 @@ static ssize_t power_ro_lock_store(struct device *dev, req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP; blk_execute_rq(NULL, req, 0); ret = req_to_mmc_queue_req(req)->drv_op_result; - blk_put_request(req); + blk_mq_free_request(req); if (!ret) { pr_info("%s: Locking boot partition ro until next power on\n", @@ -646,7 +646,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, * Dispatch the ioctl() into the block request queue. */ mq = &md->queue; - req = blk_get_request(mq->queue, + req = blk_mq_alloc_request(mq->queue, idata->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -660,7 +660,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, blk_execute_rq(NULL, req, 0); ioc_err = req_to_mmc_queue_req(req)->drv_op_result; err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata); - blk_put_request(req); + blk_mq_free_request(req); cmd_done: kfree(idata->buf); @@ -716,7 +716,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, * Dispatch the ioctl()s into the block request queue. */ mq = &md->queue; - req = blk_get_request(mq->queue, + req = blk_mq_alloc_request(mq->queue, idata[0]->ic.write_flag ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(req)) { err = PTR_ERR(req); @@ -733,7 +733,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, for (i = 0; i < num_of_cmds && !err; i++) err = mmc_blk_ioctl_copy_to_user(&cmds[i], idata[i]); - blk_put_request(req); + blk_mq_free_request(req); cmd_err: for (i = 0; i < num_of_cmds; i++) { @@ -2730,7 +2730,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) int ret; /* Ask the block layer about the card status */ - req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0); + req = blk_mq_alloc_request(mq->queue, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) return PTR_ERR(req); req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS; @@ -2740,7 +2740,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) *val = ret; ret = 0; } - blk_put_request(req); + blk_mq_free_request(req); return ret; } @@ -2766,7 +2766,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) return -ENOMEM; /* Ask the block layer for the EXT CSD */ - req = blk_get_request(mq->queue, REQ_OP_DRV_IN, 0); + req = blk_mq_alloc_request(mq->queue, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) { err = PTR_ERR(req); goto out_free; @@ -2775,7 +2775,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) req_to_mmc_queue_req(req)->drv_op_data = &ext_csd; blk_execute_rq(NULL, req, 0); err = req_to_mmc_queue_req(req)->drv_op_result; - blk_put_request(req); + blk_mq_free_request(req); if (err) { pr_err("FAILED %d\n", err); goto out_free; diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 551727a6f694..081b84bb7985 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -95,7 +95,7 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, out_free_cmd: scsi_req_free_cmd(scsi_req(rq)); out_put_request: - blk_put_request(rq); + blk_mq_free_request(rq); return ret; } diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 71d027b94be4..36870b41c888 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1979,7 +1979,7 @@ maybe_retry: static void eh_lock_door_done(struct request *req, blk_status_t status) { - blk_put_request(req); + blk_mq_free_request(req); } /** diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 0078975e3c07..34412eac4566 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -490,7 +490,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk, out_free_cdb: scsi_req_free_cmd(req); out_put_request: - blk_put_request(rq); + blk_mq_free_request(rq); return ret; } @@ -634,7 +634,7 @@ static int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, } error: - blk_put_request(rq); + blk_mq_free_request(rq); error_free_buffer: kfree(buffer); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 9823b65d1536..9c2b99e12ce3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -260,7 +260,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, scsi_normalize_sense(rq->sense, rq->sense_len, sshdr); ret = rq->result; out: - blk_put_request(req); + blk_mq_free_request(req); return ret; } @@ -1100,7 +1100,7 @@ struct request *scsi_alloc_request(struct request_queue *q, { struct request *rq; - rq = blk_get_request(q, op, flags); + rq = blk_mq_alloc_request(q, op, flags); if (!IS_ERR(rq)) scsi_initialize_rq(rq); return rq; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 85f57ac0b844..141099ab9092 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -815,7 +815,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, if (atomic_read(&sdp->detaching)) { if (srp->bio) { scsi_req_free_cmd(scsi_req(srp->rq)); - blk_put_request(srp->rq); + blk_mq_free_request(srp->rq); srp->rq = NULL; } @@ -1390,7 +1390,7 @@ sg_rq_end_io(struct request *rq, blk_status_t status) */ srp->rq = NULL; scsi_req_free_cmd(scsi_req(rq)); - blk_put_request(rq); + blk_mq_free_request(rq); write_lock_irqsave(&sfp->rq_list_lock, iflags); if (unlikely(srp->orphan)) { @@ -1830,7 +1830,7 @@ sg_finish_rem_req(Sg_request *srp) if (srp->rq) { scsi_req_free_cmd(scsi_req(srp->rq)); - blk_put_request(srp->rq); + blk_mq_free_request(srp->rq); } if (srp->res_used) diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 7c4d9a964799..3009b986d1d7 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -1003,7 +1003,7 @@ static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf, if (blk_rq_unmap_user(bio)) ret = -EFAULT; out_put_request: - blk_put_request(rq); + blk_mq_free_request(rq); return ret; } diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 1275299f6159..c2d5608f6b1a 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -530,7 +530,7 @@ static void st_scsi_execute_end(struct request *req, blk_status_t status) complete(SRpnt->waiting); blk_rq_unmap_user(tmp); - blk_put_request(req); + blk_mq_free_request(req); } static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, @@ -557,7 +557,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, err = blk_rq_map_user(req->q, req, mdata, NULL, bufflen, GFP_KERNEL); if (err) { - blk_put_request(req); + blk_mq_free_request(req); return err; } } diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index bf81da2ecf98..c85f540f6af4 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -2925,7 +2925,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, * Even though we use wait_event() which sleeps indefinitely, * the maximum wait time is bounded by SCSI request timeout. */ - req = blk_get_request(q, REQ_OP_DRV_OUT, 0); + req = blk_mq_alloc_request(q, REQ_OP_DRV_OUT, 0); if (IS_ERR(req)) { err = PTR_ERR(req); goto out_unlock; @@ -2952,7 +2952,7 @@ static int ufshcd_exec_dev_cmd(struct ufs_hba *hba, (struct utp_upiu_req *)lrbp->ucd_rsp_ptr); out: - blk_put_request(req); + blk_mq_free_request(req); out_unlock: up_read(&hba->clk_scaling_lock); return err; @@ -6517,9 +6517,9 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, int task_tag, err; /* - * blk_get_request() is used here only to get a free tag. + * blk_mq_alloc_request() is used here only to get a free tag. */ - req = blk_get_request(q, REQ_OP_DRV_OUT, 0); + req = blk_mq_alloc_request(q, REQ_OP_DRV_OUT, 0); if (IS_ERR(req)) return PTR_ERR(req); @@ -6575,7 +6575,7 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, spin_unlock_irqrestore(hba->host->host_lock, flags); ufshcd_release(hba); - blk_put_request(req); + blk_mq_free_request(req); return err; } @@ -6660,7 +6660,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba, down_read(&hba->clk_scaling_lock); - req = blk_get_request(q, REQ_OP_DRV_OUT, 0); + req = blk_mq_alloc_request(q, REQ_OP_DRV_OUT, 0); if (IS_ERR(req)) { err = PTR_ERR(req); goto out_unlock; @@ -6741,7 +6741,7 @@ static int ufshcd_issue_devman_upiu_cmd(struct ufs_hba *hba, (struct utp_upiu_req *)lrbp->ucd_rsp_ptr); out: - blk_put_request(req); + blk_mq_free_request(req); out_unlock: up_read(&hba->clk_scaling_lock); return err; @@ -7912,7 +7912,7 @@ static void ufshcd_request_sense_done(struct request *rq, blk_status_t error) if (error != BLK_STS_OK) pr_err("%s: REQUEST SENSE failed (%d)\n", __func__, error); kfree(rq->end_io_data); - blk_put_request(rq); + blk_mq_free_request(rq); } static int @@ -7932,7 +7932,7 @@ ufshcd_request_sense_async(struct ufs_hba *hba, struct scsi_device *sdev) if (!buffer) return -ENOMEM; - req = blk_get_request(sdev->request_queue, REQ_OP_DRV_IN, + req = blk_mq_alloc_request(sdev->request_queue, REQ_OP_DRV_IN, /*flags=*/BLK_MQ_REQ_PM); if (IS_ERR(req)) { ret = PTR_ERR(req); @@ -7957,7 +7957,7 @@ ufshcd_request_sense_async(struct ufs_hba *hba, struct scsi_device *sdev) return 0; out_put: - blk_put_request(req); + blk_mq_free_request(req); out_free: kfree(buffer); return ret; diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index 589af5f6b940..a2a3080071e9 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -564,7 +564,7 @@ static int ufshpb_issue_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd, int _read_id; int ret = 0; - req = blk_get_request(cmd->device->request_queue, + req = blk_mq_alloc_request(cmd->device->request_queue, REQ_OP_DRV_OUT | REQ_SYNC, BLK_MQ_REQ_NOWAIT); if (IS_ERR(req)) return -EAGAIN; @@ -592,7 +592,7 @@ free_pre_req: ufshpb_put_pre_req(hpb, pre_req); unlock_out: spin_unlock_irqrestore(&hpb->rgn_state_lock, flags); - blk_put_request(req); + blk_mq_free_request(req); return ret; } @@ -721,7 +721,7 @@ static struct ufshpb_req *ufshpb_get_req(struct ufshpb_lu *hpb, return NULL; retry: - req = blk_get_request(hpb->sdev_ufs_lu->request_queue, dir, + req = blk_mq_alloc_request(hpb->sdev_ufs_lu->request_queue, dir, BLK_MQ_REQ_NOWAIT); if (!atomic && (PTR_ERR(req) == -EWOULDBLOCK) && (--retries > 0)) { @@ -745,7 +745,7 @@ free_rq: static void ufshpb_put_req(struct ufshpb_lu *hpb, struct ufshpb_req *rq) { - blk_put_request(rq->req); + blk_mq_free_request(rq->req); kmem_cache_free(hpb->map_req_cache, rq); } diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index b5705a2bd761..7fa57fb57bf2 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1011,7 +1011,7 @@ pscsi_execute_cmd(struct se_cmd *cmd) return 0; fail_put_request: - blk_put_request(req); + blk_mq_free_request(req); fail: kfree(pt); return ret; @@ -1066,7 +1066,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status) break; } - blk_put_request(req); + blk_mq_free_request(req); kfree(pt); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ebc45cf0450b..8682663e7368 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -892,9 +892,6 @@ static inline bool rq_is_sync(struct request *rq) } void blk_rq_init(struct request_queue *q, struct request *rq); -void blk_put_request(struct request *rq); -struct request *blk_get_request(struct request_queue *q, unsigned int op, - blk_mq_req_flags_t flags); int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); -- cgit v1.2.3 From ee12203746e5cec678c7d126c9901548bfec1dd5 Mon Sep 17 00:00:00 2001 From: Ben Widawsky Date: Sat, 9 Oct 2021 09:44:39 -0700 Subject: PCI: Add pci_find_dvsec_capability to find designated VSEC Add pci_find_dvsec_capability to locate a Designated Vendor-Specific Extended Capability with the specified Vendor ID and Capability ID. The Designated Vendor-Specific Extended Capability (DVSEC) allows one or more "vendor" specific capabilities that are not tied to the Vendor ID of the PCI component. Where the DVSEC Vendor may be a standards body like CXL. Cc: David E. Box Cc: Jonathan Cameron Cc: Bjorn Helgaas Cc: Dan Williams Cc: linux-pci@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Cc: Andrew Donnellan Cc: Lu Baolu Reviewed-by: Frederic Barrat Signed-off-by: Ben Widawsky Reviewed-by: Andrew Donnellan Acked-by: Bjorn Helgaas Tested-by: Kan Liang Signed-off-by: Kan Liang Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/163379787943.692348.6814373487017444007.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/pci/pci.c | 32 ++++++++++++++++++++++++++++++++ include/linux/pci.h | 1 + 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index ce2ab62b64cf..94ac86ff28b0 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -732,6 +732,38 @@ u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap) } EXPORT_SYMBOL_GPL(pci_find_vsec_capability); +/** + * pci_find_dvsec_capability - Find DVSEC for vendor + * @dev: PCI device to query + * @vendor: Vendor ID to match for the DVSEC + * @dvsec: Designated Vendor-specific capability ID + * + * If DVSEC has Vendor ID @vendor and DVSEC ID @dvsec return the capability + * offset in config space; otherwise return 0. + */ +u16 pci_find_dvsec_capability(struct pci_dev *dev, u16 vendor, u16 dvsec) +{ + int pos; + + pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_DVSEC); + if (!pos) + return 0; + + while (pos) { + u16 v, id; + + pci_read_config_word(dev, pos + PCI_DVSEC_HEADER1, &v); + pci_read_config_word(dev, pos + PCI_DVSEC_HEADER2, &id); + if (vendor == v && dvsec == id) + return pos; + + pos = pci_find_next_ext_capability(dev, pos, PCI_EXT_CAP_ID_DVSEC); + } + + return 0; +} +EXPORT_SYMBOL_GPL(pci_find_dvsec_capability); + /** * pci_find_parent_resource - return resource region of parent bus of given * region diff --git a/include/linux/pci.h b/include/linux/pci.h index cd8aa6fce204..c93ccfa4571b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1130,6 +1130,7 @@ u16 pci_find_ext_capability(struct pci_dev *dev, int cap); u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 pos, int cap); struct pci_bus *pci_find_next_bus(const struct pci_bus *from); u16 pci_find_vsec_capability(struct pci_dev *dev, u16 vendor, int cap); +u16 pci_find_dvsec_capability(struct pci_dev *dev, u16 vendor, u16 dvsec); u64 pci_get_dsn(struct pci_dev *dev); -- cgit v1.2.3 From 26d5badbccddcc063dc5174a2baffd13a23322aa Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 20 Oct 2021 12:43:59 -0500 Subject: signal: Implement force_fatal_sig Add a simple helper force_fatal_sig that causes a signal to be delivered to a process as if the signal handler was set to SIG_DFL. Reimplement force_sigsegv based upon this new helper. This fixes force_sigsegv so that when it forces the default signal handler to be used the code now forces the signal to be unblocked as well. Reusing the tested logic in force_sig_info_to_task that was built for force_sig_seccomp this makes the implementation trivial. This is interesting both because it makes force_sigsegv simpler and because there are a couple of buggy places in the kernel that call do_exit(SIGILL) or do_exit(SIGSYS) because there is no straight forward way today for those places to simply force the exit of a process with the chosen signal. Creating force_fatal_sig allows those places to be implemented with normal signal exits. Link: https://lkml.kernel.org/r/20211020174406.17889-13-ebiederm@xmission.com Signed-off-by: Eric W. Biederman --- include/linux/sched/signal.h | 1 + kernel/signal.c | 26 +++++++++++++++++--------- 2 files changed, 18 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index e5f4ce622ee6..e2dc9f119ada 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -338,6 +338,7 @@ extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); +extern void force_fatal_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); diff --git a/kernel/signal.c b/kernel/signal.c index 952741f6d0f9..6a5e1802b9a2 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1662,6 +1662,19 @@ void force_sig(int sig) } EXPORT_SYMBOL(force_sig); +void force_fatal_sig(int sig) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info_to_task(&info, current, true); +} + /* * When things go south during signal handling, we * will force a SIGSEGV. And if the signal that caused @@ -1670,15 +1683,10 @@ EXPORT_SYMBOL(force_sig); */ void force_sigsegv(int sig) { - struct task_struct *p = current; - - if (sig == SIGSEGV) { - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - p->sighand->action[sig - 1].sa.sa_handler = SIG_DFL; - spin_unlock_irqrestore(&p->sighand->siglock, flags); - } - force_sig(SIGSEGV); + if (sig == SIGSEGV) + force_fatal_sig(SIGSEGV); + else + force_sig(SIGSEGV); } int force_sig_fault_to_task(int sig, int code, void __user *addr -- cgit v1.2.3 From 5bf84b29938579a9350a4a9c2c4f8b5da2aa6992 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 7 May 2021 15:09:10 -0700 Subject: virtchnl: Remove unused VIRTCHNL_VF_OFFLOAD_RSVD define Remove unused define that is currently marked as reserved. This will open up space for a new feature if/when it's introduced. Also, there is no reason to keep unused defines around. Suggested-by: Tony Nguyen Signed-off-by: Brett Creeley Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index db0e099c2399..2e1e1379b569 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -240,7 +240,6 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); */ #define VIRTCHNL_VF_OFFLOAD_L2 0x00000001 #define VIRTCHNL_VF_OFFLOAD_IWARP 0x00000002 -#define VIRTCHNL_VF_OFFLOAD_RSVD 0x00000004 #define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 #define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 #define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 -- cgit v1.2.3 From 4a15022f82ee0f2e14a7f953b7bbc0f5c983b663 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Fri, 7 May 2021 15:09:11 -0700 Subject: virtchnl: Use the BIT() macro for capability/offload flags Currently raw hex values are used to define specific bits for each capability/offload in virtchnl.h. Using raw hex values makes it unclear which bits are used/available. Fix this by using the BIT() macro so it's immediately obvious which bits are used/available. Also, move the VIRTCHNL_VF_CAP_ADV_LINK_SPEED define in the correct place to line up with the other bit values and add a comment for its purpose. Signed-off-by: Brett Creeley Tested-by: Tony Brelinski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 2e1e1379b569..b30a1bc74fc7 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -238,26 +238,26 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); * VIRTCHNL_VF_OFFLOAD_L2 flag is inclusive of base mode L2 offloads including * TX/RX Checksum offloading and TSO for non-tunnelled packets. */ -#define VIRTCHNL_VF_OFFLOAD_L2 0x00000001 -#define VIRTCHNL_VF_OFFLOAD_IWARP 0x00000002 -#define VIRTCHNL_VF_OFFLOAD_RSS_AQ 0x00000008 -#define VIRTCHNL_VF_OFFLOAD_RSS_REG 0x00000010 -#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR 0x00000020 -#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES 0x00000040 -#define VIRTCHNL_VF_OFFLOAD_VLAN 0x00010000 -#define VIRTCHNL_VF_OFFLOAD_RX_POLLING 0x00020000 -#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 0x00040000 -#define VIRTCHNL_VF_OFFLOAD_RSS_PF 0X00080000 -#define VIRTCHNL_VF_OFFLOAD_ENCAP 0X00100000 -#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM 0X00200000 -#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM 0X00400000 -#define VIRTCHNL_VF_OFFLOAD_ADQ 0X00800000 -#define VIRTCHNL_VF_OFFLOAD_USO 0X02000000 -#define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF 0X08000000 -#define VIRTCHNL_VF_OFFLOAD_FDIR_PF 0X10000000 - -/* Define below the capability flags that are not offloads */ -#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED 0x00000080 +#define VIRTCHNL_VF_OFFLOAD_L2 BIT(0) +#define VIRTCHNL_VF_OFFLOAD_IWARP BIT(1) +#define VIRTCHNL_VF_OFFLOAD_RSS_AQ BIT(3) +#define VIRTCHNL_VF_OFFLOAD_RSS_REG BIT(4) +#define VIRTCHNL_VF_OFFLOAD_WB_ON_ITR BIT(5) +#define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) +/* used to negotiate communicating link speeds in Mbps */ +#define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) +#define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) +#define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 BIT(18) +#define VIRTCHNL_VF_OFFLOAD_RSS_PF BIT(19) +#define VIRTCHNL_VF_OFFLOAD_ENCAP BIT(20) +#define VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM BIT(21) +#define VIRTCHNL_VF_OFFLOAD_RX_ENCAP_CSUM BIT(22) +#define VIRTCHNL_VF_OFFLOAD_ADQ BIT(23) +#define VIRTCHNL_VF_OFFLOAD_USO BIT(25) +#define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF BIT(27) +#define VIRTCHNL_VF_OFFLOAD_FDIR_PF BIT(28) + #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \ VIRTCHNL_VF_OFFLOAD_VLAN | \ VIRTCHNL_VF_OFFLOAD_RSS_PF) -- cgit v1.2.3 From 504e15724893a839213fad5eedfbd511d9ba75cc Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Sun, 11 Jul 2021 16:56:54 +0300 Subject: net/mlx5: Allow skipping counter refresh on creation CT creates a counter for each CT rule, and for each such counter, fs_counters tries to queue mlx5_fc_stats_work() work again via mod_delayed_work(0) call to refresh all counters. This call has a large performance impact when reaching high insertion rate and accounts for ~8% of the insertion time when using software steering. Allow skipping the refresh of all counters during counter creation. Change CT to use this refresh skipping for it's counters. Signed-off-by: Paul Blakey Reviewed-by: Roi Dayan Reviewed-by: Oz Shlomo Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c | 14 +++++++++++--- include/linux/mlx5/fs.h | 4 ++++ 3 files changed, 16 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index f44e5de25037..c1c6e74c79c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -889,7 +889,7 @@ mlx5_tc_ct_counter_create(struct mlx5_tc_ct_priv *ct_priv) return ERR_PTR(-ENOMEM); counter->is_shared = false; - counter->counter = mlx5_fc_create(ct_priv->dev, true); + counter->counter = mlx5_fc_create_ex(ct_priv->dev, true); if (IS_ERR(counter->counter)) { ct_dbg("Failed to create counter for ct entry"); ret = PTR_ERR(counter->counter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 60c9df1bc912..31c99d53faf7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -301,7 +301,7 @@ static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) return mlx5_fc_single_alloc(dev); } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging) { struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; @@ -332,8 +332,6 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) goto err_out_alloc; llist_add(&counter->addlist, &fc_stats->addlist); - - mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); } return counter; @@ -342,6 +340,16 @@ err_out_alloc: mlx5_fc_release(dev, counter); return ERR_PTR(err); } + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_create_ex(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (aging) + mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); + return counter; +} EXPORT_SYMBOL(mlx5_fc_create); u32 mlx5_fc_id(struct mlx5_fc *counter) diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index a7e1155bc4da..cd2d4c572367 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -245,6 +245,10 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler, struct mlx5_flow_destination *old_dest); struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging); + +/* As mlx5_fc_create() but doesn't queue stats refresh thread. */ +struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging); + void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter); u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter); void mlx5_fc_query_cached(struct mlx5_fc *counter, -- cgit v1.2.3 From f89f9c56e7372b2dda144f83dce61311b298c559 Mon Sep 17 00:00:00 2001 From: Sven Peter Date: Mon, 25 Oct 2021 08:22:04 +0200 Subject: mailbox: apple: Add driver for Apple mailboxes Apple SoCs such as the M1 come with various co-processors. Mailboxes are used to communicate with those. This driver adds support for two variants of those mailboxes. Signed-off-by: Sven Peter Signed-off-by: Jassi Brar --- drivers/mailbox/Kconfig | 12 ++ drivers/mailbox/Makefile | 2 + drivers/mailbox/apple-mailbox.c | 384 ++++++++++++++++++++++++++++++++++++++++ include/linux/apple-mailbox.h | 19 ++ 4 files changed, 417 insertions(+) create mode 100644 drivers/mailbox/apple-mailbox.c create mode 100644 include/linux/apple-mailbox.h (limited to 'include/linux') diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig index c9fc06c7e685..d9cd3606040e 100644 --- a/drivers/mailbox/Kconfig +++ b/drivers/mailbox/Kconfig @@ -8,6 +8,18 @@ menuconfig MAILBOX if MAILBOX +config APPLE_MAILBOX + tristate "Apple Mailbox driver" + depends on ARCH_APPLE || (ARM64 && COMPILE_TEST) + default ARCH_APPLE + help + Apple SoCs have various co-processors required for certain + peripherals to work (NVMe, display controller, etc.). This + driver adds support for the mailbox controller used to + communicate with those. + + Say Y here if you have a Apple SoC. + config ARM_MHU tristate "ARM MHU Mailbox" depends on ARM_AMBA diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile index c2089f04887e..338cc05e5431 100644 --- a/drivers/mailbox/Makefile +++ b/drivers/mailbox/Makefile @@ -58,3 +58,5 @@ obj-$(CONFIG_SUN6I_MSGBOX) += sun6i-msgbox.o obj-$(CONFIG_SPRD_MBOX) += sprd-mailbox.o obj-$(CONFIG_QCOM_IPCC) += qcom-ipcc.o + +obj-$(CONFIG_APPLE_MAILBOX) += apple-mailbox.o diff --git a/drivers/mailbox/apple-mailbox.c b/drivers/mailbox/apple-mailbox.c new file mode 100644 index 000000000000..72942002a54a --- /dev/null +++ b/drivers/mailbox/apple-mailbox.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only OR MIT +/* + * Apple mailbox driver + * + * Copyright (C) 2021 The Asahi Linux Contributors + * + * This driver adds support for two mailbox variants (called ASC and M3 by + * Apple) found in Apple SoCs such as the M1. It consists of two FIFOs used to + * exchange 64+32 bit messages between the main CPU and a co-processor. + * Various coprocessors implement different IPC protocols based on these simple + * messages and shared memory buffers. + * + * Both the main CPU and the co-processor see the same set of registers but + * the first FIFO (A2I) is always used to transfer messages from the application + * processor (us) to the I/O processor and the second one (I2A) for the + * other direction. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define APPLE_ASC_MBOX_CONTROL_FULL BIT(16) +#define APPLE_ASC_MBOX_CONTROL_EMPTY BIT(17) + +#define APPLE_ASC_MBOX_A2I_CONTROL 0x110 +#define APPLE_ASC_MBOX_A2I_SEND0 0x800 +#define APPLE_ASC_MBOX_A2I_SEND1 0x808 +#define APPLE_ASC_MBOX_A2I_RECV0 0x810 +#define APPLE_ASC_MBOX_A2I_RECV1 0x818 + +#define APPLE_ASC_MBOX_I2A_CONTROL 0x114 +#define APPLE_ASC_MBOX_I2A_SEND0 0x820 +#define APPLE_ASC_MBOX_I2A_SEND1 0x828 +#define APPLE_ASC_MBOX_I2A_RECV0 0x830 +#define APPLE_ASC_MBOX_I2A_RECV1 0x838 + +#define APPLE_M3_MBOX_CONTROL_FULL BIT(16) +#define APPLE_M3_MBOX_CONTROL_EMPTY BIT(17) + +#define APPLE_M3_MBOX_A2I_CONTROL 0x50 +#define APPLE_M3_MBOX_A2I_SEND0 0x60 +#define APPLE_M3_MBOX_A2I_SEND1 0x68 +#define APPLE_M3_MBOX_A2I_RECV0 0x70 +#define APPLE_M3_MBOX_A2I_RECV1 0x78 + +#define APPLE_M3_MBOX_I2A_CONTROL 0x80 +#define APPLE_M3_MBOX_I2A_SEND0 0x90 +#define APPLE_M3_MBOX_I2A_SEND1 0x98 +#define APPLE_M3_MBOX_I2A_RECV0 0xa0 +#define APPLE_M3_MBOX_I2A_RECV1 0xa8 + +#define APPLE_M3_MBOX_IRQ_ENABLE 0x48 +#define APPLE_M3_MBOX_IRQ_ACK 0x4c +#define APPLE_M3_MBOX_IRQ_A2I_EMPTY BIT(0) +#define APPLE_M3_MBOX_IRQ_A2I_NOT_EMPTY BIT(1) +#define APPLE_M3_MBOX_IRQ_I2A_EMPTY BIT(2) +#define APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY BIT(3) + +#define APPLE_MBOX_MSG1_OUTCNT GENMASK(56, 52) +#define APPLE_MBOX_MSG1_INCNT GENMASK(51, 48) +#define APPLE_MBOX_MSG1_OUTPTR GENMASK(47, 44) +#define APPLE_MBOX_MSG1_INPTR GENMASK(43, 40) +#define APPLE_MBOX_MSG1_MSG GENMASK(31, 0) + +struct apple_mbox_hw { + unsigned int control_full; + unsigned int control_empty; + + unsigned int a2i_control; + unsigned int a2i_send0; + unsigned int a2i_send1; + + unsigned int i2a_control; + unsigned int i2a_recv0; + unsigned int i2a_recv1; + + bool has_irq_controls; + unsigned int irq_enable; + unsigned int irq_ack; + unsigned int irq_bit_recv_not_empty; + unsigned int irq_bit_send_empty; +}; + +struct apple_mbox { + void __iomem *regs; + const struct apple_mbox_hw *hw; + + int irq_recv_not_empty; + int irq_send_empty; + + struct mbox_chan chan; + + struct device *dev; + struct mbox_controller controller; +}; + +static const struct of_device_id apple_mbox_of_match[]; + +static bool apple_mbox_hw_can_send(struct apple_mbox *apple_mbox) +{ + u32 mbox_ctrl = + readl_relaxed(apple_mbox->regs + apple_mbox->hw->a2i_control); + + return !(mbox_ctrl & apple_mbox->hw->control_full); +} + +static int apple_mbox_hw_send(struct apple_mbox *apple_mbox, + struct apple_mbox_msg *msg) +{ + if (!apple_mbox_hw_can_send(apple_mbox)) + return -EBUSY; + + dev_dbg(apple_mbox->dev, "> TX %016llx %08x\n", msg->msg0, msg->msg1); + + writeq_relaxed(msg->msg0, apple_mbox->regs + apple_mbox->hw->a2i_send0); + writeq_relaxed(FIELD_PREP(APPLE_MBOX_MSG1_MSG, msg->msg1), + apple_mbox->regs + apple_mbox->hw->a2i_send1); + + return 0; +} + +static bool apple_mbox_hw_can_recv(struct apple_mbox *apple_mbox) +{ + u32 mbox_ctrl = + readl_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_control); + + return !(mbox_ctrl & apple_mbox->hw->control_empty); +} + +static int apple_mbox_hw_recv(struct apple_mbox *apple_mbox, + struct apple_mbox_msg *msg) +{ + if (!apple_mbox_hw_can_recv(apple_mbox)) + return -ENOMSG; + + msg->msg0 = readq_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_recv0); + msg->msg1 = FIELD_GET( + APPLE_MBOX_MSG1_MSG, + readq_relaxed(apple_mbox->regs + apple_mbox->hw->i2a_recv1)); + + dev_dbg(apple_mbox->dev, "< RX %016llx %08x\n", msg->msg0, msg->msg1); + + return 0; +} + +static int apple_mbox_chan_send_data(struct mbox_chan *chan, void *data) +{ + struct apple_mbox *apple_mbox = chan->con_priv; + struct apple_mbox_msg *msg = data; + int ret; + + ret = apple_mbox_hw_send(apple_mbox, msg); + if (ret) + return ret; + + /* + * The interrupt is level triggered and will keep firing as long as the + * FIFO is empty. It will also keep firing if the FIFO was empty + * at any point in the past until it has been acknowledged at the + * mailbox level. By acknowledging it here we can ensure that we will + * only get the interrupt once the FIFO has been cleared again. + * If the FIFO is already empty before the ack it will fire again + * immediately after the ack. + */ + if (apple_mbox->hw->has_irq_controls) { + writel_relaxed(apple_mbox->hw->irq_bit_send_empty, + apple_mbox->regs + apple_mbox->hw->irq_ack); + } + enable_irq(apple_mbox->irq_send_empty); + + return 0; +} + +static irqreturn_t apple_mbox_send_empty_irq(int irq, void *data) +{ + struct apple_mbox *apple_mbox = data; + + /* + * We don't need to acknowledge the interrupt at the mailbox level + * here even if supported by the hardware. It will keep firing but that + * doesn't matter since it's disabled at the main interrupt controller. + * apple_mbox_chan_send_data will acknowledge it before enabling + * it at the main controller again. + */ + disable_irq_nosync(apple_mbox->irq_send_empty); + mbox_chan_txdone(&apple_mbox->chan, 0); + return IRQ_HANDLED; +} + +static irqreturn_t apple_mbox_recv_irq(int irq, void *data) +{ + struct apple_mbox *apple_mbox = data; + struct apple_mbox_msg msg; + + while (apple_mbox_hw_recv(apple_mbox, &msg) == 0) + mbox_chan_received_data(&apple_mbox->chan, (void *)&msg); + + /* + * The interrupt will keep firing even if there are no more messages + * unless we also acknowledge it at the mailbox level here. + * There's no race if a message comes in between the check in the while + * loop above and the ack below: If a new messages arrives inbetween + * those two the interrupt will just fire again immediately after the + * ack since it's level triggered. + */ + if (apple_mbox->hw->has_irq_controls) { + writel_relaxed(apple_mbox->hw->irq_bit_recv_not_empty, + apple_mbox->regs + apple_mbox->hw->irq_ack); + } + + return IRQ_HANDLED; +} + +static int apple_mbox_chan_startup(struct mbox_chan *chan) +{ + struct apple_mbox *apple_mbox = chan->con_priv; + + /* + * Only some variants of this mailbox HW provide interrupt control + * at the mailbox level. We therefore need to handle enabling/disabling + * interrupts at the main interrupt controller anyway for hardware that + * doesn't. Just always keep the interrupts we care about enabled at + * the mailbox level so that both hardware revisions behave almost + * the same. + */ + if (apple_mbox->hw->has_irq_controls) { + writel_relaxed(apple_mbox->hw->irq_bit_recv_not_empty | + apple_mbox->hw->irq_bit_send_empty, + apple_mbox->regs + apple_mbox->hw->irq_enable); + } + + enable_irq(apple_mbox->irq_recv_not_empty); + return 0; +} + +static void apple_mbox_chan_shutdown(struct mbox_chan *chan) +{ + struct apple_mbox *apple_mbox = chan->con_priv; + + disable_irq(apple_mbox->irq_recv_not_empty); +} + +static const struct mbox_chan_ops apple_mbox_ops = { + .send_data = apple_mbox_chan_send_data, + .startup = apple_mbox_chan_startup, + .shutdown = apple_mbox_chan_shutdown, +}; + +static struct mbox_chan *apple_mbox_of_xlate(struct mbox_controller *mbox, + const struct of_phandle_args *args) +{ + if (args->args_count != 0) + return ERR_PTR(-EINVAL); + + return &mbox->chans[0]; +} + +static int apple_mbox_probe(struct platform_device *pdev) +{ + int ret; + const struct of_device_id *match; + char *irqname; + struct apple_mbox *mbox; + struct device *dev = &pdev->dev; + + match = of_match_node(apple_mbox_of_match, pdev->dev.of_node); + if (!match) + return -EINVAL; + if (!match->data) + return -EINVAL; + + mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL); + if (!mbox) + return -ENOMEM; + platform_set_drvdata(pdev, mbox); + + mbox->dev = dev; + mbox->regs = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(mbox->regs)) + return PTR_ERR(mbox->regs); + + mbox->hw = match->data; + mbox->irq_recv_not_empty = + platform_get_irq_byname(pdev, "recv-not-empty"); + if (mbox->irq_recv_not_empty < 0) + return -ENODEV; + + mbox->irq_send_empty = platform_get_irq_byname(pdev, "send-empty"); + if (mbox->irq_send_empty < 0) + return -ENODEV; + + mbox->controller.dev = mbox->dev; + mbox->controller.num_chans = 1; + mbox->controller.chans = &mbox->chan; + mbox->controller.ops = &apple_mbox_ops; + mbox->controller.txdone_irq = true; + mbox->controller.of_xlate = apple_mbox_of_xlate; + mbox->chan.con_priv = mbox; + + irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-recv", dev_name(dev)); + if (!irqname) + return -ENOMEM; + + ret = devm_request_threaded_irq(dev, mbox->irq_recv_not_empty, NULL, + apple_mbox_recv_irq, + IRQF_NO_AUTOEN | IRQF_ONESHOT, irqname, + mbox); + if (ret) + return ret; + + irqname = devm_kasprintf(dev, GFP_KERNEL, "%s-send", dev_name(dev)); + if (!irqname) + return -ENOMEM; + + ret = devm_request_irq(dev, mbox->irq_send_empty, + apple_mbox_send_empty_irq, IRQF_NO_AUTOEN, + irqname, mbox); + if (ret) + return ret; + + return devm_mbox_controller_register(dev, &mbox->controller); +} + +static const struct apple_mbox_hw apple_mbox_asc_hw = { + .control_full = APPLE_ASC_MBOX_CONTROL_FULL, + .control_empty = APPLE_ASC_MBOX_CONTROL_EMPTY, + + .a2i_control = APPLE_ASC_MBOX_A2I_CONTROL, + .a2i_send0 = APPLE_ASC_MBOX_A2I_SEND0, + .a2i_send1 = APPLE_ASC_MBOX_A2I_SEND1, + + .i2a_control = APPLE_ASC_MBOX_I2A_CONTROL, + .i2a_recv0 = APPLE_ASC_MBOX_I2A_RECV0, + .i2a_recv1 = APPLE_ASC_MBOX_I2A_RECV1, + + .has_irq_controls = false, +}; + +static const struct apple_mbox_hw apple_mbox_m3_hw = { + .control_full = APPLE_M3_MBOX_CONTROL_FULL, + .control_empty = APPLE_M3_MBOX_CONTROL_EMPTY, + + .a2i_control = APPLE_M3_MBOX_A2I_CONTROL, + .a2i_send0 = APPLE_M3_MBOX_A2I_SEND0, + .a2i_send1 = APPLE_M3_MBOX_A2I_SEND1, + + .i2a_control = APPLE_M3_MBOX_I2A_CONTROL, + .i2a_recv0 = APPLE_M3_MBOX_I2A_RECV0, + .i2a_recv1 = APPLE_M3_MBOX_I2A_RECV1, + + .has_irq_controls = true, + .irq_enable = APPLE_M3_MBOX_IRQ_ENABLE, + .irq_ack = APPLE_M3_MBOX_IRQ_ACK, + .irq_bit_recv_not_empty = APPLE_M3_MBOX_IRQ_I2A_NOT_EMPTY, + .irq_bit_send_empty = APPLE_M3_MBOX_IRQ_A2I_EMPTY, +}; + +static const struct of_device_id apple_mbox_of_match[] = { + { .compatible = "apple,t8103-asc-mailbox", .data = &apple_mbox_asc_hw }, + { .compatible = "apple,t8103-m3-mailbox", .data = &apple_mbox_m3_hw }, + {} +}; +MODULE_DEVICE_TABLE(of, apple_mbox_of_match); + +static struct platform_driver apple_mbox_driver = { + .driver = { + .name = "apple-mailbox", + .of_match_table = apple_mbox_of_match, + }, + .probe = apple_mbox_probe, +}; +module_platform_driver(apple_mbox_driver); + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_AUTHOR("Sven Peter "); +MODULE_DESCRIPTION("Apple Mailbox driver"); diff --git a/include/linux/apple-mailbox.h b/include/linux/apple-mailbox.h new file mode 100644 index 000000000000..720fbb70294a --- /dev/null +++ b/include/linux/apple-mailbox.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR MIT */ +/* + * Apple mailbox message format + * + * Copyright (C) 2021 The Asahi Linux Contributors + */ + +#ifndef _LINUX_APPLE_MAILBOX_H_ +#define _LINUX_APPLE_MAILBOX_H_ + +#include + +/* encodes a single 96bit message sent over the single channel */ +struct apple_mbox_msg { + u64 msg0; + u32 msg1; +}; + +#endif -- cgit v1.2.3 From 97961f78e8bc7f50ff7113fec030af6fa5f004d0 Mon Sep 17 00:00:00 2001 From: Peng Fan Date: Fri, 22 Oct 2021 18:18:56 +0800 Subject: mailbox: imx: support i.MX8ULP S4 MU Like i.MX8 SCU, i.MX8ULP S4 also has vendor specific protocol. - bind SCU/S4 MU part to share one tx/rx/init API to make code simple. - S4 msg max size is very large, so alloc the space at driver probe, not use local on stack variable. - S4 MU has 8 TR and 4 RR which is different with i.MX8 MU, so adapt code to reflect this. Tested on i.MX8MP, i.MX8ULP Signed-off-by: Peng Fan Signed-off-by: Jassi Brar --- drivers/mailbox/imx-mailbox.c | 124 ++++++++++++++++++++++++++++------------ include/linux/firmware/imx/s4.h | 20 +++++++ 2 files changed, 107 insertions(+), 37 deletions(-) create mode 100644 include/linux/firmware/imx/s4.h (limited to 'include/linux') diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c index 0ce75c6b36b6..ffe36a6bef9e 100644 --- a/drivers/mailbox/imx-mailbox.c +++ b/drivers/mailbox/imx-mailbox.c @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -18,6 +19,8 @@ #define IMX_MU_CHANS 16 /* TX0/RX0/RXDB[0-3] */ #define IMX_MU_SCU_CHANS 6 +/* TX0/RX0 */ +#define IMX_MU_S4_CHANS 2 #define IMX_MU_CHAN_NAME_SIZE 20 enum imx_mu_chan_type { @@ -47,6 +50,11 @@ struct imx_sc_rpc_msg_max { u32 data[7]; }; +struct imx_s4_rpc_msg_max { + struct imx_s4_rpc_msg hdr; + u32 data[254]; +}; + struct imx_mu_con_priv { unsigned int idx; char irq_desc[IMX_MU_CHAN_NAME_SIZE]; @@ -58,6 +66,7 @@ struct imx_mu_con_priv { struct imx_mu_priv { struct device *dev; void __iomem *base; + void *msg; spinlock_t xcr_lock; /* control register lock */ struct mbox_controller mbox; @@ -75,7 +84,8 @@ struct imx_mu_priv { enum imx_mu_type { IMX_MU_V1, - IMX_MU_V2, + IMX_MU_V2 = BIT(1), + IMX_MU_V2_S4 = BIT(15), }; struct imx_mu_dcfg { @@ -89,18 +99,18 @@ struct imx_mu_dcfg { u32 xCR[4]; /* Control Registers */ }; -#define IMX_MU_xSR_GIPn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(28 + (3 - (x)))) -#define IMX_MU_xSR_RFn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(24 + (3 - (x)))) -#define IMX_MU_xSR_TEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(20 + (3 - (x)))) +#define IMX_MU_xSR_GIPn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(28 + (3 - (x)))) +#define IMX_MU_xSR_RFn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(24 + (3 - (x)))) +#define IMX_MU_xSR_TEn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(20 + (3 - (x)))) /* General Purpose Interrupt Enable */ -#define IMX_MU_xCR_GIEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(28 + (3 - (x)))) +#define IMX_MU_xCR_GIEn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(28 + (3 - (x)))) /* Receive Interrupt Enable */ -#define IMX_MU_xCR_RIEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(24 + (3 - (x)))) +#define IMX_MU_xCR_RIEn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(24 + (3 - (x)))) /* Transmit Interrupt Enable */ -#define IMX_MU_xCR_TIEn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(20 + (3 - (x)))) +#define IMX_MU_xCR_TIEn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(20 + (3 - (x)))) /* General Purpose Interrupt Request */ -#define IMX_MU_xCR_GIRn(type, x) (type == IMX_MU_V2 ? BIT(x) : BIT(16 + (3 - (x)))) +#define IMX_MU_xCR_GIRn(type, x) (type & IMX_MU_V2 ? BIT(x) : BIT(16 + (3 - (x)))) static struct imx_mu_priv *to_imx_mu_priv(struct mbox_controller *mbox) @@ -167,14 +177,22 @@ static int imx_mu_generic_rx(struct imx_mu_priv *priv, return 0; } -static int imx_mu_scu_tx(struct imx_mu_priv *priv, - struct imx_mu_con_priv *cp, - void *data) +static int imx_mu_specific_tx(struct imx_mu_priv *priv, struct imx_mu_con_priv *cp, void *data) { - struct imx_sc_rpc_msg_max *msg = data; u32 *arg = data; int i, ret; u32 xsr; + u32 size, max_size, num_tr; + + if (priv->dcfg->type & IMX_MU_V2_S4) { + size = ((struct imx_s4_rpc_msg_max *)data)->hdr.size; + max_size = sizeof(struct imx_s4_rpc_msg_max); + num_tr = 8; + } else { + size = ((struct imx_sc_rpc_msg_max *)data)->hdr.size; + max_size = sizeof(struct imx_sc_rpc_msg_max); + num_tr = 4; + } switch (cp->type) { case IMX_MU_TYPE_TX: @@ -183,27 +201,27 @@ static int imx_mu_scu_tx(struct imx_mu_priv *priv, * sizeof yields bytes. */ - if (msg->hdr.size > sizeof(*msg) / 4) { + if (size > max_size / 4) { /* * The real message size can be different to - * struct imx_sc_rpc_msg_max size + * struct imx_sc_rpc_msg_max/imx_s4_rpc_msg_max size */ - dev_err(priv->dev, "Maximal message size (%zu bytes) exceeded on TX; got: %i bytes\n", sizeof(*msg), msg->hdr.size << 2); + dev_err(priv->dev, "Maximal message size (%u bytes) exceeded on TX; got: %i bytes\n", max_size, size << 2); return -EINVAL; } - for (i = 0; i < 4 && i < msg->hdr.size; i++) - imx_mu_write(priv, *arg++, priv->dcfg->xTR + (i % 4) * 4); - for (; i < msg->hdr.size; i++) { + for (i = 0; i < num_tr && i < size; i++) + imx_mu_write(priv, *arg++, priv->dcfg->xTR + (i % num_tr) * 4); + for (; i < size; i++) { ret = readl_poll_timeout(priv->base + priv->dcfg->xSR[IMX_MU_TSR], xsr, - xsr & IMX_MU_xSR_TEn(priv->dcfg->type, i % 4), + xsr & IMX_MU_xSR_TEn(priv->dcfg->type, i % num_tr), 0, 100); if (ret) { dev_err(priv->dev, "Send data index: %d timeout\n", i); return ret; } - imx_mu_write(priv, *arg++, priv->dcfg->xTR + (i % 4) * 4); + imx_mu_write(priv, *arg++, priv->dcfg->xTR + (i % num_tr) * 4); } imx_mu_xcr_rmw(priv, IMX_MU_TCR, IMX_MU_xCR_TIEn(priv->dcfg->type, cp->idx), 0); @@ -216,23 +234,32 @@ static int imx_mu_scu_tx(struct imx_mu_priv *priv, return 0; } -static int imx_mu_scu_rx(struct imx_mu_priv *priv, - struct imx_mu_con_priv *cp) +static int imx_mu_specific_rx(struct imx_mu_priv *priv, struct imx_mu_con_priv *cp) { - struct imx_sc_rpc_msg_max msg; - u32 *data = (u32 *)&msg; + u32 *data; int i, ret; u32 xsr; + u32 size, max_size; + + data = (u32 *)priv->msg; imx_mu_xcr_rmw(priv, IMX_MU_RCR, 0, IMX_MU_xCR_RIEn(priv->dcfg->type, 0)); *data++ = imx_mu_read(priv, priv->dcfg->xRR); - if (msg.hdr.size > sizeof(msg) / 4) { - dev_err(priv->dev, "Maximal message size (%zu bytes) exceeded on RX; got: %i bytes\n", sizeof(msg), msg.hdr.size << 2); + if (priv->dcfg->type & IMX_MU_V2_S4) { + size = ((struct imx_s4_rpc_msg_max *)priv->msg)->hdr.size; + max_size = sizeof(struct imx_s4_rpc_msg_max); + } else { + size = ((struct imx_sc_rpc_msg_max *)priv->msg)->hdr.size; + max_size = sizeof(struct imx_sc_rpc_msg_max); + } + + if (size > max_size / 4) { + dev_err(priv->dev, "Maximal message size (%u bytes) exceeded on RX; got: %i bytes\n", max_size, size << 2); return -EINVAL; } - for (i = 1; i < msg.hdr.size; i++) { + for (i = 1; i < size; i++) { ret = readl_poll_timeout(priv->base + priv->dcfg->xSR[IMX_MU_RSR], xsr, xsr & IMX_MU_xSR_RFn(priv->dcfg->type, i % 4), 0, 100); if (ret) { @@ -243,7 +270,7 @@ static int imx_mu_scu_rx(struct imx_mu_priv *priv, } imx_mu_xcr_rmw(priv, IMX_MU_RCR, IMX_MU_xCR_RIEn(priv->dcfg->type, 0), 0); - mbox_chan_received_data(cp->chan, (void *)&msg); + mbox_chan_received_data(cp->chan, (void *)priv->msg); return 0; } @@ -394,8 +421,8 @@ static const struct mbox_chan_ops imx_mu_ops = { .shutdown = imx_mu_shutdown, }; -static struct mbox_chan *imx_mu_scu_xlate(struct mbox_controller *mbox, - const struct of_phandle_args *sp) +static struct mbox_chan *imx_mu_specific_xlate(struct mbox_controller *mbox, + const struct of_phandle_args *sp) { u32 type, idx, chan; @@ -478,11 +505,12 @@ static void imx_mu_init_generic(struct imx_mu_priv *priv) imx_mu_write(priv, 0, priv->dcfg->xCR[i]); } -static void imx_mu_init_scu(struct imx_mu_priv *priv) +static void imx_mu_init_specific(struct imx_mu_priv *priv) { unsigned int i; + int num_chans = priv->dcfg->type & IMX_MU_V2_S4 ? IMX_MU_S4_CHANS : IMX_MU_SCU_CHANS; - for (i = 0; i < IMX_MU_SCU_CHANS; i++) { + for (i = 0; i < num_chans; i++) { struct imx_mu_con_priv *cp = &priv->con_priv[i]; cp->idx = i < 2 ? 0 : i - 2; @@ -493,8 +521,8 @@ static void imx_mu_init_scu(struct imx_mu_priv *priv) "imx_mu_chan[%i-%i]", cp->type, cp->idx); } - priv->mbox.num_chans = IMX_MU_SCU_CHANS; - priv->mbox.of_xlate = imx_mu_scu_xlate; + priv->mbox.num_chans = num_chans; + priv->mbox.of_xlate = imx_mu_specific_xlate; /* Set default MU configuration */ for (i = 0; i < IMX_MU_xCR_MAX; i++) @@ -508,6 +536,7 @@ static int imx_mu_probe(struct platform_device *pdev) struct imx_mu_priv *priv; const struct imx_mu_dcfg *dcfg; int ret; + u32 size; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -528,6 +557,15 @@ static int imx_mu_probe(struct platform_device *pdev) return -EINVAL; priv->dcfg = dcfg; + if (priv->dcfg->type & IMX_MU_V2_S4) + size = sizeof(struct imx_s4_rpc_msg_max); + else + size = sizeof(struct imx_sc_rpc_msg_max); + + priv->msg = devm_kzalloc(dev, size, GFP_KERNEL); + if (IS_ERR(priv->msg)) + return PTR_ERR(priv->msg); + priv->clk = devm_clk_get(dev, NULL); if (IS_ERR(priv->clk)) { if (PTR_ERR(priv->clk) != -ENOENT) @@ -623,10 +661,21 @@ static const struct imx_mu_dcfg imx_mu_cfg_imx8ulp = { .xCR = {0x110, 0x114, 0x120, 0x128}, }; +static const struct imx_mu_dcfg imx_mu_cfg_imx8ulp_s4 = { + .tx = imx_mu_specific_tx, + .rx = imx_mu_specific_rx, + .init = imx_mu_init_specific, + .type = IMX_MU_V2 | IMX_MU_V2_S4, + .xTR = 0x200, + .xRR = 0x280, + .xSR = {0xC, 0x118, 0x124, 0x12C}, + .xCR = {0x110, 0x114, 0x120, 0x128}, +}; + static const struct imx_mu_dcfg imx_mu_cfg_imx8_scu = { - .tx = imx_mu_scu_tx, - .rx = imx_mu_scu_rx, - .init = imx_mu_init_scu, + .tx = imx_mu_specific_tx, + .rx = imx_mu_specific_rx, + .init = imx_mu_init_specific, .xTR = 0x0, .xRR = 0x10, .xSR = {0x20, 0x20, 0x20, 0x20}, @@ -637,6 +686,7 @@ static const struct of_device_id imx_mu_dt_ids[] = { { .compatible = "fsl,imx7ulp-mu", .data = &imx_mu_cfg_imx7ulp }, { .compatible = "fsl,imx6sx-mu", .data = &imx_mu_cfg_imx6sx }, { .compatible = "fsl,imx8ulp-mu", .data = &imx_mu_cfg_imx8ulp }, + { .compatible = "fsl,imx8ulp-mu-s4", .data = &imx_mu_cfg_imx8ulp_s4 }, { .compatible = "fsl,imx8-mu-scu", .data = &imx_mu_cfg_imx8_scu }, { }, }; diff --git a/include/linux/firmware/imx/s4.h b/include/linux/firmware/imx/s4.h new file mode 100644 index 000000000000..9e34923ae1d6 --- /dev/null +++ b/include/linux/firmware/imx/s4.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright 2021 NXP + * + * Header file for the IPC implementation. + */ + +#ifndef _S4_IPC_H +#define _S4_IPC_H + +struct imx_s4_ipc; + +struct imx_s4_rpc_msg { + uint8_t ver; + uint8_t size; + uint8_t cmd; + uint8_t tag; +} __packed; + +#endif /* _S4_IPC_H */ -- cgit v1.2.3 From cc8d7b4aea79df7cb45b74f9bc5b8a8bd2ed4c07 Mon Sep 17 00:00:00 2001 From: Anssi Hannula Date: Wed, 27 Oct 2021 13:21:24 +0300 Subject: tty: Fix extra "not" in TTY_DRIVER_REAL_RAW description TTY_DRIVER_REAL_RAW flag (which is always set for e.g. serial ports) documentation says that driver must always set special character handling flags in certain conditions. However, as the following sentence makes clear, what is actually intended is the opposite. Fix that by removing the unintended double negation. Acked-by: Johan Hovold Signed-off-by: Anssi Hannula Link: https://lore.kernel.org/r/20211027102124.3049414-1-anssi.hannula@bitwise.fi Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 29e1cf178afb..795b94ccdeb6 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -360,7 +360,7 @@ static inline void tty_set_operations(struct tty_driver *driver, * Used for PTY's, in particular. * * TTY_DRIVER_REAL_RAW --- if set, indicates that the driver will - * guarantee never not to set any special character handling + * guarantee never to set any special character handling * flags if ((IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || * !INPCK)). That is, if there is no reason for the driver to * send notifications of parity and break characters up to the -- cgit v1.2.3 From f98a3dccfcb0b9b9c3bef8df9edd61cda80ad937 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 22 Oct 2021 13:59:38 +0200 Subject: locking: Remove spin_lock_flags() etc parisc, ia64 and powerpc32 are the only remaining architectures that provide custom arch_{spin,read,write}_lock_flags() functions, which are meant to re-enable interrupts while waiting for a spinlock. However, none of these can actually run into this codepath, because it is only called on architectures without CONFIG_GENERIC_LOCKBREAK, or when CONFIG_DEBUG_LOCK_ALLOC is set without CONFIG_LOCKDEP, and none of those combinations are possible on the three architectures. Going back in the git history, it appears that arch/mn10300 may have been able to run into this code path, but there is a good chance that it never worked. On the architectures that still exist, it was already impossible to hit back in 2008 after the introduction of CONFIG_GENERIC_LOCKBREAK, and possibly earlier. As this is all dead code, just remove it and the helper functions built around it. For arch/ia64, the inline asm could be cleaned up, but it seems safer to leave it untouched. Signed-off-by: Arnd Bergmann Signed-off-by: Peter Zijlstra (Intel) Acked-by: Helge Deller # parisc Link: https://lore.kernel.org/r/20211022120058.1031690-1-arnd@kernel.org --- arch/ia64/include/asm/spinlock.h | 23 ++++++----------------- arch/openrisc/include/asm/spinlock.h | 3 --- arch/parisc/include/asm/spinlock.h | 15 --------------- arch/powerpc/include/asm/simple_spinlock.h | 21 --------------------- arch/s390/include/asm/spinlock.h | 8 -------- include/linux/lockdep.h | 17 ----------------- include/linux/rwlock.h | 15 --------------- include/linux/rwlock_api_smp.h | 6 ++---- include/linux/spinlock.h | 13 ------------- include/linux/spinlock_api_smp.h | 9 --------- include/linux/spinlock_up.h | 1 - kernel/locking/spinlock.c | 3 +-- 12 files changed, 9 insertions(+), 125 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 864775970c50..0e5c1ad3239c 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -124,18 +124,13 @@ static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) __ticket_spin_unlock(lock); } -static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, - unsigned long flags) -{ - arch_spin_lock(lock); -} -#define arch_spin_lock_flags arch_spin_lock_flags - #ifdef ASM_SUPPORTED static __always_inline void -arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags) +arch_read_lock(arch_rwlock_t *lock) { + unsigned long flags = 0; + __asm__ __volatile__ ( "tbit.nz p6, p0 = %1,%2\n" "br.few 3f\n" @@ -157,13 +152,8 @@ arch_read_lock_flags(arch_rwlock_t *lock, unsigned long flags) : "p6", "p7", "r2", "memory"); } -#define arch_read_lock_flags arch_read_lock_flags -#define arch_read_lock(lock) arch_read_lock_flags(lock, 0) - #else /* !ASM_SUPPORTED */ -#define arch_read_lock_flags(rw, flags) arch_read_lock(rw) - #define arch_read_lock(rw) \ do { \ arch_rwlock_t *__read_lock_ptr = (rw); \ @@ -186,8 +176,10 @@ do { \ #ifdef ASM_SUPPORTED static __always_inline void -arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags) +arch_write_lock(arch_rwlock_t *lock) { + unsigned long flags = 0; + __asm__ __volatile__ ( "tbit.nz p6, p0 = %1, %2\n" "mov ar.ccv = r0\n" @@ -210,9 +202,6 @@ arch_write_lock_flags(arch_rwlock_t *lock, unsigned long flags) : "ar.ccv", "p6", "p7", "r2", "r29", "memory"); } -#define arch_write_lock_flags arch_write_lock_flags -#define arch_write_lock(rw) arch_write_lock_flags(rw, 0) - #define arch_write_trylock(rw) \ ({ \ register long result; \ diff --git a/arch/openrisc/include/asm/spinlock.h b/arch/openrisc/include/asm/spinlock.h index a8940bdfcb7e..264944a71535 100644 --- a/arch/openrisc/include/asm/spinlock.h +++ b/arch/openrisc/include/asm/spinlock.h @@ -19,9 +19,6 @@ #include -#define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#define arch_write_lock_flags(lock, flags) arch_write_lock(lock) - #define arch_spin_relax(lock) cpu_relax() #define arch_read_relax(lock) cpu_relax() #define arch_write_relax(lock) cpu_relax() diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h index fa5ee8a45dbd..a6e5d66a7656 100644 --- a/arch/parisc/include/asm/spinlock.h +++ b/arch/parisc/include/asm/spinlock.h @@ -23,21 +23,6 @@ static inline void arch_spin_lock(arch_spinlock_t *x) continue; } -static inline void arch_spin_lock_flags(arch_spinlock_t *x, - unsigned long flags) -{ - volatile unsigned int *a; - - a = __ldcw_align(x); - while (__ldcw(a) == 0) - while (*a == 0) - if (flags & PSW_SM_I) { - local_irq_enable(); - local_irq_disable(); - } -} -#define arch_spin_lock_flags arch_spin_lock_flags - static inline void arch_spin_unlock(arch_spinlock_t *x) { volatile unsigned int *a; diff --git a/arch/powerpc/include/asm/simple_spinlock.h b/arch/powerpc/include/asm/simple_spinlock.h index 8985791a2ba5..7ae6aeef8464 100644 --- a/arch/powerpc/include/asm/simple_spinlock.h +++ b/arch/powerpc/include/asm/simple_spinlock.h @@ -123,27 +123,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lock) } } -static inline -void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - unsigned long flags_dis; - - while (1) { - if (likely(__arch_spin_trylock(lock) == 0)) - break; - local_save_flags(flags_dis); - local_irq_restore(flags); - do { - HMT_low(); - if (is_shared_processor()) - splpar_spin_yield(lock); - } while (unlikely(lock->slock != 0)); - HMT_medium(); - local_irq_restore(flags_dis); - } -} -#define arch_spin_lock_flags arch_spin_lock_flags - static inline void arch_spin_unlock(arch_spinlock_t *lock) { __asm__ __volatile__("# arch_spin_unlock\n\t" diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index ef59588a3042..888a2f1c9ee3 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -67,14 +67,6 @@ static inline void arch_spin_lock(arch_spinlock_t *lp) arch_spin_lock_wait(lp); } -static inline void arch_spin_lock_flags(arch_spinlock_t *lp, - unsigned long flags) -{ - if (!arch_spin_trylock_once(lp)) - arch_spin_lock_wait(lp); -} -#define arch_spin_lock_flags arch_spin_lock_flags - static inline int arch_spin_trylock(arch_spinlock_t *lp) { if (!arch_spin_trylock_once(lp)) diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 9fe165beb0f9..467b94257105 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -481,23 +481,6 @@ do { \ #endif /* CONFIG_LOCK_STAT */ -#ifdef CONFIG_LOCKDEP - -/* - * On lockdep we dont want the hand-coded irq-enable of - * _raw_*_lock_flags() code, because lockdep assumes - * that interrupts are not re-enabled during lock-acquire: - */ -#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ - LOCK_CONTENDED((_lock), (try), (lock)) - -#else /* CONFIG_LOCKDEP */ - -#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \ - lockfl((_lock), (flags)) - -#endif /* CONFIG_LOCKDEP */ - #ifdef CONFIG_PROVE_LOCKING extern void print_irqtrace_events(struct task_struct *curr); #else diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 7ce9a51ae5c0..2c0ad417ce3c 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -30,31 +30,16 @@ do { \ #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_read_lock(rwlock_t *lock) __acquires(lock); -#define do_raw_read_lock_flags(lock, flags) do_raw_read_lock(lock) extern int do_raw_read_trylock(rwlock_t *lock); extern void do_raw_read_unlock(rwlock_t *lock) __releases(lock); extern void do_raw_write_lock(rwlock_t *lock) __acquires(lock); -#define do_raw_write_lock_flags(lock, flags) do_raw_write_lock(lock) extern int do_raw_write_trylock(rwlock_t *lock); extern void do_raw_write_unlock(rwlock_t *lock) __releases(lock); #else - -#ifndef arch_read_lock_flags -# define arch_read_lock_flags(lock, flags) arch_read_lock(lock) -#endif - -#ifndef arch_write_lock_flags -# define arch_write_lock_flags(lock, flags) arch_write_lock(lock) -#endif - # define do_raw_read_lock(rwlock) do {__acquire(lock); arch_read_lock(&(rwlock)->raw_lock); } while (0) -# define do_raw_read_lock_flags(lock, flags) \ - do {__acquire(lock); arch_read_lock_flags(&(lock)->raw_lock, *(flags)); } while (0) # define do_raw_read_trylock(rwlock) arch_read_trylock(&(rwlock)->raw_lock) # define do_raw_read_unlock(rwlock) do {arch_read_unlock(&(rwlock)->raw_lock); __release(lock); } while (0) # define do_raw_write_lock(rwlock) do {__acquire(lock); arch_write_lock(&(rwlock)->raw_lock); } while (0) -# define do_raw_write_lock_flags(lock, flags) \ - do {__acquire(lock); arch_write_lock_flags(&(lock)->raw_lock, *(flags)); } while (0) # define do_raw_write_trylock(rwlock) arch_write_trylock(&(rwlock)->raw_lock) # define do_raw_write_unlock(rwlock) do {arch_write_unlock(&(rwlock)->raw_lock); __release(lock); } while (0) #endif diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index abfb53ab11be..f1db6f17c4fb 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -157,8 +157,7 @@ static inline unsigned long __raw_read_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED_FLAGS(lock, do_raw_read_trylock, do_raw_read_lock, - do_raw_read_lock_flags, &flags); + LOCK_CONTENDED(lock, do_raw_read_trylock, do_raw_read_lock); return flags; } @@ -184,8 +183,7 @@ static inline unsigned long __raw_write_lock_irqsave(rwlock_t *lock) local_irq_save(flags); preempt_disable(); rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_); - LOCK_CONTENDED_FLAGS(lock, do_raw_write_trylock, do_raw_write_lock, - do_raw_write_lock_flags, &flags); + LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); return flags; } diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 45310ea1b1d7..f0447062eecd 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -177,7 +177,6 @@ do { \ #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); -#define do_raw_spin_lock_flags(lock, flags) do_raw_spin_lock(lock) extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else @@ -188,18 +187,6 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) mmiowb_spin_lock(); } -#ifndef arch_spin_lock_flags -#define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) -#endif - -static inline void -do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lock) -{ - __acquire(lock); - arch_spin_lock_flags(&lock->raw_lock, *flags); - mmiowb_spin_lock(); -} - static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h index 6b8e1a0b137b..51fa0dab68c4 100644 --- a/include/linux/spinlock_api_smp.h +++ b/include/linux/spinlock_api_smp.h @@ -108,16 +108,7 @@ static inline unsigned long __raw_spin_lock_irqsave(raw_spinlock_t *lock) local_irq_save(flags); preempt_disable(); spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); - /* - * On lockdep we dont want the hand-coded irq-enable of - * do_raw_spin_lock_flags() code, because lockdep assumes - * that interrupts are not re-enabled during lock-acquire: - */ -#ifdef CONFIG_LOCKDEP LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); -#else - do_raw_spin_lock_flags(lock, &flags); -#endif return flags; } diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h index 0ac9112c1bbe..16521074b6f7 100644 --- a/include/linux/spinlock_up.h +++ b/include/linux/spinlock_up.h @@ -62,7 +62,6 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock) #define arch_spin_is_locked(lock) ((void)(lock), 0) /* for sched/core.c and kernel_lock.c: */ # define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0) -# define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0) # define arch_spin_unlock(lock) do { barrier(); (void)(lock); } while (0) # define arch_spin_trylock(lock) ({ barrier(); (void)(lock); 1; }) #endif /* DEBUG_SPINLOCK */ diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index c5830cfa379a..b562f9289372 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -378,8 +378,7 @@ unsigned long __lockfunc _raw_spin_lock_irqsave_nested(raw_spinlock_t *lock, local_irq_save(flags); preempt_disable(); spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); - LOCK_CONTENDED_FLAGS(lock, do_raw_spin_trylock, do_raw_spin_lock, - do_raw_spin_lock_flags, &flags); + LOCK_CONTENDED(lock, do_raw_spin_trylock, do_raw_spin_lock); return flags; } EXPORT_SYMBOL(_raw_spin_lock_irqsave_nested); -- cgit v1.2.3 From 9cc2fa4f4a92ccc6760d764e7341be46ee8aaaa1 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Tue, 5 Oct 2021 00:05:43 +0200 Subject: task_stack: Fix end_of_stack() for architectures with upwards-growing stack The function end_of_stack() returns a pointer to the last entry of a stack. For architectures like parisc where the stack grows upwards return the pointer to the highest address in the stack. Without this change I faced a crash on parisc, because the stackleak functionality wrote STACKLEAK_POISON to the lowest address and thus overwrote the first 4 bytes of the task_struct which included the TIF_FLAGS. Signed-off-by: Helge Deller --- include/linux/sched/task_stack.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h index 2413427e439c..d10150587d81 100644 --- a/include/linux/sched/task_stack.h +++ b/include/linux/sched/task_stack.h @@ -25,7 +25,11 @@ static inline void *task_stack_page(const struct task_struct *task) static inline unsigned long *end_of_stack(const struct task_struct *task) { +#ifdef CONFIG_STACK_GROWSUP + return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; +#else return task->stack; +#endif } #elif !defined(__HAVE_THREAD_FUNCTIONS) -- cgit v1.2.3 From e60b56e46b384cee1ad34e6adc164d883049c6c3 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 19 Oct 2021 14:35:35 +0200 Subject: sched/fair: Wait before decaying max_newidle_lb_cost Decay max_newidle_lb_cost only when it has not been updated for a while and ensure to not decay a recently changed value. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Dietmar Eggemann Acked-by: Mel Gorman Link: https://lore.kernel.org/r/20211019123537.17146-4-vincent.guittot@linaro.org --- include/linux/sched/topology.h | 2 +- kernel/sched/fair.c | 36 +++++++++++++++++++++++++++--------- kernel/sched/topology.c | 2 +- 3 files changed, 29 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 2f9166f6dec8..c07bfa2d80f2 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -105,7 +105,7 @@ struct sched_domain { /* idle_balance() stats */ u64 max_newidle_lb_cost; - unsigned long next_decay_max_lb_cost; + unsigned long last_decay_max_lb_cost; u64 avg_scan_cost; /* select_idle_sibling */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c4c36865321b..e50fd751e1df 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10239,6 +10239,30 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } +static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +{ + if (cost > sd->max_newidle_lb_cost) { + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + sd->max_newidle_lb_cost = cost; + sd->last_decay_max_lb_cost = jiffies; + } else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) { + /* + * Decay the newidle max times by ~1% per second to ensure that + * it is not outdated and the current max cost is actually + * shorter. + */ + sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256; + sd->last_decay_max_lb_cost = jiffies; + + return true; + } + + return false; +} + /* * It checks each scheduling domain to see if it is due to be balanced, * and initiates a balancing operation if so. @@ -10262,14 +10286,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) for_each_domain(cpu, sd) { /* * Decay the newidle max times here because this is a regular - * visit to all the domains. Decay ~1% per second. + * visit to all the domains. */ - if (time_after(jiffies, sd->next_decay_max_lb_cost)) { - sd->max_newidle_lb_cost = - (sd->max_newidle_lb_cost * 253) / 256; - sd->next_decay_max_lb_cost = jiffies + HZ; - need_decay = 1; - } + need_decay = update_newidle_cost(sd, 0); max_cost += sd->max_newidle_lb_cost; /* @@ -10911,8 +10930,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) t1 = sched_clock_cpu(this_cpu); domain_cost = t1 - t0; - if (domain_cost > sd->max_newidle_lb_cost) - sd->max_newidle_lb_cost = domain_cost; + update_newidle_cost(sd, domain_cost); curr_cost += domain_cost; t0 = t1; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index e81246787560..30169c7685b6 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1568,7 +1568,7 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, .max_newidle_lb_cost = 0, - .next_decay_max_lb_cost = jiffies, + .last_decay_max_lb_cost = jiffies, .child = child, #ifdef CONFIG_SCHED_DEBUG .name = tl->name, -- cgit v1.2.3 From 7ff22787ba49c2e66dcec92f3e2b79ef6b6a0d71 Mon Sep 17 00:00:00 2001 From: Prashant Malani Date: Mon, 4 Oct 2021 10:07:09 -0700 Subject: platform/chrome: cros_ec_proto: Use EC struct for features The Chrome EC's features are returned through an ec_response_get_features struct, but they are stored in an independent array. Although the two are effectively the same at present (2 unsigned 32 bit ints), there is the possibility that they could go out of sync. Avoid this by only using the EC struct to store the features. Signed-off-by: Prashant Malani Link: https://lore.kernel.org/r/20211004170716.86601-1-pmalani@chromium.org Signed-off-by: Benson Leung --- drivers/mfd/cros_ec_dev.c | 4 ++-- drivers/platform/chrome/cros_ec_proto.c | 15 ++++++++------- include/linux/platform_data/cros_ec_proto.h | 2 +- 3 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/cros_ec_dev.c b/drivers/mfd/cros_ec_dev.c index 8c08d1c55726..6ee1f410eb53 100644 --- a/drivers/mfd/cros_ec_dev.c +++ b/drivers/mfd/cros_ec_dev.c @@ -146,8 +146,8 @@ static int ec_device_probe(struct platform_device *pdev) ec->ec_dev = dev_get_drvdata(dev->parent); ec->dev = dev; ec->cmd_offset = ec_platform->cmd_offset; - ec->features[0] = -1U; /* Not cached yet */ - ec->features[1] = -1U; /* Not cached yet */ + ec->features.flags[0] = -1U; /* Not cached yet */ + ec->features.flags[1] = -1U; /* Not cached yet */ device_initialize(&ec->class_dev); for (i = 0; i < ARRAY_SIZE(cros_mcu_devices); i++) { diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c index a9f1867e5d8f..b908cdd680e3 100644 --- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -812,36 +812,37 @@ EXPORT_SYMBOL(cros_ec_get_host_event); */ bool cros_ec_check_features(struct cros_ec_dev *ec, int feature) { + struct ec_response_get_features *features = &ec->features; struct cros_ec_command *msg; int ret; - if (ec->features[0] == -1U && ec->features[1] == -1U) { + if (features->flags[0] == -1U && features->flags[1] == -1U) { /* features bitmap not read yet */ - msg = kzalloc(sizeof(*msg) + sizeof(ec->features), GFP_KERNEL); + msg = kzalloc(sizeof(*msg) + sizeof(*features), GFP_KERNEL); if (!msg) { dev_err(ec->dev, "failed to allocate memory to get EC features\n"); return false; } msg->command = EC_CMD_GET_FEATURES + ec->cmd_offset; - msg->insize = sizeof(ec->features); + msg->insize = sizeof(*features); ret = cros_ec_cmd_xfer_status(ec->ec_dev, msg); if (ret < 0) { dev_warn(ec->dev, "cannot get EC features: %d/%d\n", ret, msg->result); - memset(ec->features, 0, sizeof(ec->features)); + memset(features, 0, sizeof(*features)); } else { - memcpy(ec->features, msg->data, sizeof(ec->features)); + memcpy(features, msg->data, sizeof(*features)); } dev_dbg(ec->dev, "EC features %08x %08x\n", - ec->features[0], ec->features[1]); + features->flags[0], features->flags[1]); kfree(msg); } - return !!(ec->features[feature / 32] & EC_FEATURE_MASK_0(feature)); + return !!(features->flags[feature / 32] & EC_FEATURE_MASK_0(feature)); } EXPORT_SYMBOL_GPL(cros_ec_check_features); diff --git a/include/linux/platform_data/cros_ec_proto.h b/include/linux/platform_data/cros_ec_proto.h index 9d370816a419..df3c78c92ca2 100644 --- a/include/linux/platform_data/cros_ec_proto.h +++ b/include/linux/platform_data/cros_ec_proto.h @@ -205,7 +205,7 @@ struct cros_ec_dev { struct cros_ec_debugfs *debug_info; bool has_kb_wake_angle; u16 cmd_offset; - u32 features[2]; + struct ec_response_get_features features; }; #define to_cros_ec_dev(dev) container_of(dev, struct cros_ec_dev, class_dev) -- cgit v1.2.3 From d89c8169bd7052c78731137da4c4c06986409c62 Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Fri, 29 Oct 2021 17:14:42 +0800 Subject: virtio-pci: introduce legacy device module Split common codes from virtio-pci-legacy so vDPA driver can reuse it later. Signed-off-by: Wu Zongyong Acked-by: Jason Wang Link: https://lore.kernel.org/r/71605acde5e97fcb2760a6973e406279fb1bbd33.1635493219.git.wuzongyong@linux.alibaba.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/Kconfig | 10 ++ drivers/virtio/Makefile | 1 + drivers/virtio/virtio_pci_common.c | 10 +- drivers/virtio/virtio_pci_common.h | 9 +- drivers/virtio/virtio_pci_legacy.c | 101 ++++----------- drivers/virtio/virtio_pci_legacy_dev.c | 220 +++++++++++++++++++++++++++++++++ include/linux/virtio_pci_legacy.h | 42 +++++++ 7 files changed, 310 insertions(+), 83 deletions(-) create mode 100644 drivers/virtio/virtio_pci_legacy_dev.c create mode 100644 include/linux/virtio_pci_legacy.h (limited to 'include/linux') diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index ce1b3f6ec325..8fcf94cd2c96 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -20,6 +20,15 @@ config VIRTIO_PCI_LIB PCI device with possible vendor specific extensions. Any module that selects this module must depend on PCI. +config VIRTIO_PCI_LIB_LEGACY + tristate + help + Legacy PCI device (Virtio PCI Card 0.9.x Draft and older device) + implementation. + This module implements the basic probe and control for devices + which are based on legacy PCI device. Any module that selects this + module must depend on PCI. + menuconfig VIRTIO_MENU bool "Virtio drivers" default y @@ -43,6 +52,7 @@ config VIRTIO_PCI_LEGACY bool "Support for legacy virtio draft 0.9.X and older devices" default y depends on VIRTIO_PCI + select VIRTIO_PCI_LIB_LEGACY help Virtio PCI Card 0.9.X Draft (circa 2014) and older device support. diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index 699bbea0465f..0a82d0873248 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio_pci_modern_dev.o +obj-$(CONFIG_VIRTIO_PCI_LIB_LEGACY) += virtio_pci_legacy_dev.o obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index b35bb2d57f62..d724f676608b 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -549,6 +549,8 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, pci_set_master(pci_dev); + vp_dev->is_legacy = vp_dev->ldev.ioaddr ? true : false; + rc = register_virtio_device(&vp_dev->vdev); reg_dev = vp_dev; if (rc) @@ -557,10 +559,10 @@ static int virtio_pci_probe(struct pci_dev *pci_dev, return 0; err_register: - if (vp_dev->ioaddr) - virtio_pci_legacy_remove(vp_dev); + if (vp_dev->is_legacy) + virtio_pci_legacy_remove(vp_dev); else - virtio_pci_modern_remove(vp_dev); + virtio_pci_modern_remove(vp_dev); err_probe: pci_disable_device(pci_dev); err_enable_device: @@ -587,7 +589,7 @@ static void virtio_pci_remove(struct pci_dev *pci_dev) unregister_virtio_device(&vp_dev->vdev); - if (vp_dev->ioaddr) + if (vp_dev->is_legacy) virtio_pci_legacy_remove(vp_dev); else virtio_pci_modern_remove(vp_dev); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index beec047a8f8d..eb17a29fc7ef 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -44,16 +45,14 @@ struct virtio_pci_vq_info { struct virtio_pci_device { struct virtio_device vdev; struct pci_dev *pci_dev; + struct virtio_pci_legacy_device ldev; struct virtio_pci_modern_device mdev; - /* In legacy mode, these two point to within ->legacy. */ + bool is_legacy; + /* Where to read and clear interrupt */ u8 __iomem *isr; - /* Legacy only field */ - /* the IO mapping for the PCI config space */ - void __iomem *ioaddr; - /* a list of queues so we can dispatch IRQs */ spinlock_t lock; struct list_head virtqueues; diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c index d62e9835aeec..82eb437ad920 100644 --- a/drivers/virtio/virtio_pci_legacy.c +++ b/drivers/virtio/virtio_pci_legacy.c @@ -14,6 +14,7 @@ * Michael S. Tsirkin */ +#include "linux/virtio_pci_legacy.h" #include "virtio_pci_common.h" /* virtio config->get_features() implementation */ @@ -23,7 +24,7 @@ static u64 vp_get_features(struct virtio_device *vdev) /* When someone needs more than 32 feature bits, we'll need to * steal a bit to indicate that the rest are somewhere else. */ - return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES); + return vp_legacy_get_features(&vp_dev->ldev); } /* virtio config->finalize_features() implementation */ @@ -38,7 +39,7 @@ static int vp_finalize_features(struct virtio_device *vdev) BUG_ON((u32)vdev->features != vdev->features); /* We only support 32 feature bits. */ - iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES); + vp_legacy_set_features(&vp_dev->ldev, vdev->features); return 0; } @@ -48,7 +49,7 @@ static void vp_get(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - void __iomem *ioaddr = vp_dev->ioaddr + + void __iomem *ioaddr = vp_dev->ldev.ioaddr + VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) + offset; u8 *ptr = buf; @@ -64,7 +65,7 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, const void *buf, unsigned len) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - void __iomem *ioaddr = vp_dev->ioaddr + + void __iomem *ioaddr = vp_dev->ldev.ioaddr + VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) + offset; const u8 *ptr = buf; @@ -78,7 +79,7 @@ static void vp_set(struct virtio_device *vdev, unsigned offset, static u8 vp_get_status(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); - return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS); + return vp_legacy_get_status(&vp_dev->ldev); } static void vp_set_status(struct virtio_device *vdev, u8 status) @@ -86,28 +87,24 @@ static void vp_set_status(struct virtio_device *vdev, u8 status) struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* We should never be setting status to 0. */ BUG_ON(status == 0); - iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS); + vp_legacy_set_status(&vp_dev->ldev, status); } static void vp_reset(struct virtio_device *vdev) { struct virtio_pci_device *vp_dev = to_vp_device(vdev); /* 0 status means a reset. */ - iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS); + vp_legacy_set_status(&vp_dev->ldev, 0); /* Flush out the status write, and flush in device writes, * including MSi-X interrupts, if any. */ - ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS); + vp_legacy_get_status(&vp_dev->ldev); /* Flush pending VQ/configuration callbacks. */ vp_synchronize_vectors(vdev); } static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector) { - /* Setup the vector used for configuration events */ - iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR); - /* Verify we had enough resources to assign the vector */ - /* Will also flush the write out to device */ - return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR); + return vp_legacy_config_vector(&vp_dev->ldev, vector); } static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, @@ -123,12 +120,9 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, int err; u64 q_pfn; - /* Select the queue we're interested in */ - iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL); - /* Check if queue is either not available or already active. */ - num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM); - if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN)) + num = vp_legacy_get_queue_size(&vp_dev->ldev, index); + if (!num || vp_legacy_get_queue_enable(&vp_dev->ldev, index)) return ERR_PTR(-ENOENT); info->msix_vector = msix_vec; @@ -151,13 +145,12 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, } /* activate the queue */ - iowrite32(q_pfn, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN); + vp_legacy_set_queue_address(&vp_dev->ldev, index, q_pfn); - vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY; + vq->priv = (void __force *)vp_dev->ldev.ioaddr + VIRTIO_PCI_QUEUE_NOTIFY; if (msix_vec != VIRTIO_MSI_NO_VECTOR) { - iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); - msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); + msix_vec = vp_legacy_queue_vector(&vp_dev->ldev, index, msix_vec); if (msix_vec == VIRTIO_MSI_NO_VECTOR) { err = -EBUSY; goto out_deactivate; @@ -167,7 +160,7 @@ static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev, return vq; out_deactivate: - iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN); + vp_legacy_set_queue_address(&vp_dev->ldev, index, 0); out_del_vq: vring_del_virtqueue(vq); return ERR_PTR(err); @@ -178,17 +171,15 @@ static void del_vq(struct virtio_pci_vq_info *info) struct virtqueue *vq = info->vq; struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev); - iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL); - if (vp_dev->msix_enabled) { - iowrite16(VIRTIO_MSI_NO_VECTOR, - vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); + vp_legacy_queue_vector(&vp_dev->ldev, vq->index, + VIRTIO_MSI_NO_VECTOR); /* Flush the write out to device */ - ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR); + ioread8(vp_dev->ldev.ioaddr + VIRTIO_PCI_ISR); } /* Select and deactivate the queue */ - iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN); + vp_legacy_set_queue_address(&vp_dev->ldev, vq->index, 0); vring_del_virtqueue(vq); } @@ -211,51 +202,18 @@ static const struct virtio_config_ops virtio_pci_config_ops = { /* the PCI probing function */ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev) { + struct virtio_pci_legacy_device *ldev = &vp_dev->ldev; struct pci_dev *pci_dev = vp_dev->pci_dev; int rc; - /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */ - if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f) - return -ENODEV; - - if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) { - printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n", - VIRTIO_PCI_ABI_VERSION, pci_dev->revision); - return -ENODEV; - } - - rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64)); - if (rc) { - rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); - } else { - /* - * The virtio ring base address is expressed as a 32-bit PFN, - * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT. - */ - dma_set_coherent_mask(&pci_dev->dev, - DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT)); - } - - if (rc) - dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + ldev->pci_dev = pci_dev; - rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy"); + rc = vp_legacy_probe(ldev); if (rc) return rc; - rc = -ENOMEM; - vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0); - if (!vp_dev->ioaddr) - goto err_iomap; - - vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR; - - /* we use the subsystem vendor/device id as the virtio vendor/device - * id. this allows us to use the same PCI vendor/device id for all - * virtio devices and to identify the particular virtio driver by - * the subsystem ids */ - vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor; - vp_dev->vdev.id.device = pci_dev->subsystem_device; + vp_dev->isr = ldev->isr; + vp_dev->vdev.id = ldev->id; vp_dev->vdev.config = &virtio_pci_config_ops; @@ -264,16 +222,11 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev) vp_dev->del_vq = del_vq; return 0; - -err_iomap: - pci_release_region(pci_dev, 0); - return rc; } void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev) { - struct pci_dev *pci_dev = vp_dev->pci_dev; + struct virtio_pci_legacy_device *ldev = &vp_dev->ldev; - pci_iounmap(pci_dev, vp_dev->ioaddr); - pci_release_region(pci_dev, 0); + vp_legacy_remove(ldev); } diff --git a/drivers/virtio/virtio_pci_legacy_dev.c b/drivers/virtio/virtio_pci_legacy_dev.c new file mode 100644 index 000000000000..9b97680dd02b --- /dev/null +++ b/drivers/virtio/virtio_pci_legacy_dev.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "linux/virtio_pci.h" +#include +#include +#include + + +/* + * vp_legacy_probe: probe the legacy virtio pci device, note that the + * caller is required to enable PCI device before calling this function. + * @ldev: the legacy virtio-pci device + * + * Return 0 on succeed otherwise fail + */ +int vp_legacy_probe(struct virtio_pci_legacy_device *ldev) +{ + struct pci_dev *pci_dev = ldev->pci_dev; + int rc; + + /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */ + if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f) + return -ENODEV; + + if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) + return -ENODEV; + + rc = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(64)); + if (rc) { + rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); + } else { + /* + * The virtio ring base address is expressed as a 32-bit PFN, + * with a page size of 1 << VIRTIO_PCI_QUEUE_ADDR_SHIFT. + */ + dma_set_coherent_mask(&pci_dev->dev, + DMA_BIT_MASK(32 + VIRTIO_PCI_QUEUE_ADDR_SHIFT)); + } + + if (rc) + dev_warn(&pci_dev->dev, "Failed to enable 64-bit or 32-bit DMA. Trying to continue, but this might not work.\n"); + + rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy"); + if (rc) + return rc; + + ldev->ioaddr = pci_iomap(pci_dev, 0, 0); + if (!ldev->ioaddr) + goto err_iomap; + + ldev->isr = ldev->ioaddr + VIRTIO_PCI_ISR; + + ldev->id.vendor = pci_dev->subsystem_vendor; + ldev->id.device = pci_dev->subsystem_device; + + return 0; +err_iomap: + pci_release_region(pci_dev, 0); + return rc; +} +EXPORT_SYMBOL_GPL(vp_legacy_probe); + +/* + * vp_legacy_probe: remove and cleanup the legacy virtio pci device + * @ldev: the legacy virtio-pci device + */ +void vp_legacy_remove(struct virtio_pci_legacy_device *ldev) +{ + struct pci_dev *pci_dev = ldev->pci_dev; + + pci_iounmap(pci_dev, ldev->ioaddr); + pci_release_region(pci_dev, 0); +} +EXPORT_SYMBOL_GPL(vp_legacy_remove); + +/* + * vp_legacy_get_features - get features from device + * @ldev: the legacy virtio-pci device + * + * Returns the features read from the device + */ +u64 vp_legacy_get_features(struct virtio_pci_legacy_device *ldev) +{ + + return ioread32(ldev->ioaddr + VIRTIO_PCI_HOST_FEATURES); +} +EXPORT_SYMBOL_GPL(vp_legacy_get_features); + +/* + * vp_legacy_get_driver_features - get driver features from device + * @ldev: the legacy virtio-pci device + * + * Returns the driver features read from the device + */ +u64 vp_legacy_get_driver_features(struct virtio_pci_legacy_device *ldev) +{ + return ioread32(ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES); +} +EXPORT_SYMBOL_GPL(vp_legacy_get_driver_features); + +/* + * vp_legacy_set_features - set features to device + * @ldev: the legacy virtio-pci device + * @features: the features set to device + */ +void vp_legacy_set_features(struct virtio_pci_legacy_device *ldev, + u32 features) +{ + iowrite32(features, ldev->ioaddr + VIRTIO_PCI_GUEST_FEATURES); +} +EXPORT_SYMBOL_GPL(vp_legacy_set_features); + +/* + * vp_legacy_get_status - get the device status + * @ldev: the legacy virtio-pci device + * + * Returns the status read from device + */ +u8 vp_legacy_get_status(struct virtio_pci_legacy_device *ldev) +{ + return ioread8(ldev->ioaddr + VIRTIO_PCI_STATUS); +} +EXPORT_SYMBOL_GPL(vp_legacy_get_status); + +/* + * vp_legacy_set_status - set status to device + * @ldev: the legacy virtio-pci device + * @status: the status set to device + */ +void vp_legacy_set_status(struct virtio_pci_legacy_device *ldev, + u8 status) +{ + iowrite8(status, ldev->ioaddr + VIRTIO_PCI_STATUS); +} +EXPORT_SYMBOL_GPL(vp_legacy_set_status); + +/* + * vp_legacy_queue_vector - set the MSIX vector for a specific virtqueue + * @ldev: the legacy virtio-pci device + * @index: queue index + * @vector: the config vector + * + * Returns the config vector read from the device + */ +u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev, + u16 index, u16 vector) +{ + iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); + iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); + /* Flush the write out to device */ + return ioread16(ldev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR); +} +EXPORT_SYMBOL_GPL(vp_legacy_queue_vector); + +/* + * vp_legacy_config_vector - set the vector for config interrupt + * @ldev: the legacy virtio-pci device + * @vector: the config vector + * + * Returns the config vector read from the device + */ +u16 vp_legacy_config_vector(struct virtio_pci_legacy_device *ldev, + u16 vector) +{ + /* Setup the vector used for configuration events */ + iowrite16(vector, ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR); + /* Verify we had enough resources to assign the vector */ + /* Will also flush the write out to device */ + return ioread16(ldev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR); +} +EXPORT_SYMBOL_GPL(vp_legacy_config_vector); + +/* + * vp_legacy_set_queue_address - set the virtqueue address + * @ldev: the legacy virtio-pci device + * @index: the queue index + * @queue_pfn: pfn of the virtqueue + */ +void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev, + u16 index, u32 queue_pfn) +{ + iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); + iowrite32(queue_pfn, ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN); +} +EXPORT_SYMBOL_GPL(vp_legacy_set_queue_address); + +/* + * vp_legacy_get_queue_enable - enable a virtqueue + * @ldev: the legacy virtio-pci device + * @index: the queue index + * + * Returns whether a virtqueue is enabled or not + */ +bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev, + u16 index) +{ + iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); + return ioread32(ldev->ioaddr + VIRTIO_PCI_QUEUE_PFN); +} +EXPORT_SYMBOL_GPL(vp_legacy_get_queue_enable); + +/* + * vp_legacy_get_queue_size - get size for a virtqueue + * @ldev: the legacy virtio-pci device + * @index: the queue index + * + * Returns the size of the virtqueue + */ +u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev, + u16 index) +{ + iowrite16(index, ldev->ioaddr + VIRTIO_PCI_QUEUE_SEL); + return ioread16(ldev->ioaddr + VIRTIO_PCI_QUEUE_NUM); +} +EXPORT_SYMBOL_GPL(vp_legacy_get_queue_size); + +MODULE_VERSION("0.1"); +MODULE_DESCRIPTION("Legacy Virtio PCI Device"); +MODULE_AUTHOR("Wu Zongyong "); +MODULE_LICENSE("GPL"); diff --git a/include/linux/virtio_pci_legacy.h b/include/linux/virtio_pci_legacy.h new file mode 100644 index 000000000000..e5d665faf00e --- /dev/null +++ b/include/linux/virtio_pci_legacy.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_VIRTIO_PCI_LEGACY_H +#define _LINUX_VIRTIO_PCI_LEGACY_H + +#include "linux/mod_devicetable.h" +#include +#include + +struct virtio_pci_legacy_device { + struct pci_dev *pci_dev; + + /* Where to read and clear interrupt */ + u8 __iomem *isr; + /* The IO mapping for the PCI config space (legacy mode only) */ + void __iomem *ioaddr; + + struct virtio_device_id id; +}; + +u64 vp_legacy_get_features(struct virtio_pci_legacy_device *ldev); +u64 vp_legacy_get_driver_features(struct virtio_pci_legacy_device *ldev); +void vp_legacy_set_features(struct virtio_pci_legacy_device *ldev, + u32 features); +u8 vp_legacy_get_status(struct virtio_pci_legacy_device *ldev); +void vp_legacy_set_status(struct virtio_pci_legacy_device *ldev, + u8 status); +u16 vp_legacy_queue_vector(struct virtio_pci_legacy_device *ldev, + u16 idx, u16 vector); +u16 vp_legacy_config_vector(struct virtio_pci_legacy_device *ldev, + u16 vector); +void vp_legacy_set_queue_address(struct virtio_pci_legacy_device *ldev, + u16 index, u32 queue_pfn); +bool vp_legacy_get_queue_enable(struct virtio_pci_legacy_device *ldev, + u16 idx); +void vp_legacy_set_queue_size(struct virtio_pci_legacy_device *ldev, + u16 idx, u16 size); +u16 vp_legacy_get_queue_size(struct virtio_pci_legacy_device *ldev, + u16 idx); +int vp_legacy_probe(struct virtio_pci_legacy_device *ldev); +void vp_legacy_remove(struct virtio_pci_legacy_device *ldev); + +#endif -- cgit v1.2.3 From d0ae1fbfcff48e889bf993ba16890e30f6615593 Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Fri, 29 Oct 2021 17:14:43 +0800 Subject: vdpa: fix typo Signed-off-by: Wu Zongyong Acked-by: Jason Wang Link: https://lore.kernel.org/r/4b5153262e4ba64986bb567d7425ad4829ca7bcc.1635493219.git.wuzongyong@linux.alibaba.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 3972ab765de1..a896ee021e5f 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -257,7 +257,7 @@ struct vdpa_config_ops { struct vdpa_notification_area (*get_vq_notification)(struct vdpa_device *vdev, u16 idx); /* vq irq is not expected to be changed once DRIVER_OK is set */ - int (*get_vq_irq)(struct vdpa_device *vdv, u16 idx); + int (*get_vq_irq)(struct vdpa_device *vdev, u16 idx); /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); -- cgit v1.2.3 From 3b970a5842c9114c82e60744c84a7d06ee51b6f9 Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Fri, 29 Oct 2021 17:14:45 +0800 Subject: vdpa: add new callback get_vq_num_min in vdpa_config_ops This callback is optional. For vdpa devices that not support to change virtqueue size, get_vq_num_min and get_vq_num_max will return the same value, so that users can choose a correct value for that device. Suggested-by: Jason Wang Signed-off-by: Wu Zongyong Acked-by: Jason Wang Link: https://lore.kernel.org/r/f4af5b0abd660d9a29ab6b2f67bd6df10284a230.1635493219.git.wuzongyong@linux.alibaba.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index a896ee021e5f..30864848950b 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -171,6 +171,9 @@ struct vdpa_map_file { * @get_vq_num_max: Get the max size of virtqueue * @vdev: vdpa device * Returns u16: max size of virtqueue + * @get_vq_num_min: Get the min size of virtqueue (optional) + * @vdev: vdpa device + * Returns u16: min size of virtqueue * @get_device_id: Get virtio device id * @vdev: vdpa device * Returns u32: virtio device id @@ -266,6 +269,7 @@ struct vdpa_config_ops { void (*set_config_cb)(struct vdpa_device *vdev, struct vdpa_callback *cb); u16 (*get_vq_num_max)(struct vdpa_device *vdev); + u16 (*get_vq_num_min)(struct vdpa_device *vdev); u32 (*get_device_id)(struct vdpa_device *vdev); u32 (*get_vendor_id)(struct vdpa_device *vdev); u8 (*get_status)(struct vdpa_device *vdev); -- cgit v1.2.3 From d50497eb4e554e1f0351e1836ee7241c059592e6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 19 Oct 2021 15:01:45 +0800 Subject: virtio_config: introduce a new .enable_cbs method This patch introduces a new method to enable the callbacks for config and virtqueues. This will be used for making sure the virtqueue callbacks are only enabled after virtio_device_ready() if transport implements this method. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20211019070152.8236-4-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- include/linux/virtio_config.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 8519b3ae5d52..4d107ad31149 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -23,6 +23,8 @@ struct virtio_shm_region { * any of @get/@set, @get_status/@set_status, or @get_features/ * @finalize_features are NOT safe to be called from an atomic * context. + * @enable_cbs: enable the callbacks + * vdev: the virtio_device * @get: read the value of a configuration field * vdev: the virtio_device * offset: the offset of the configuration field @@ -75,6 +77,7 @@ struct virtio_shm_region { */ typedef void vq_callback_t(struct virtqueue *); struct virtio_config_ops { + void (*enable_cbs)(struct virtio_device *vdev); void (*get)(struct virtio_device *vdev, unsigned offset, void *buf, unsigned len); void (*set)(struct virtio_device *vdev, unsigned offset, @@ -229,6 +232,9 @@ void virtio_device_ready(struct virtio_device *dev) { unsigned status = dev->config->get_status(dev); + if (dev->config->enable_cbs) + dev->config->enable_cbs(dev); + BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK); dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK); } -- cgit v1.2.3 From 939779f5152d161b34f612af29e7dc1ac4472fcf Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Wed, 27 Oct 2021 10:21:04 +0800 Subject: virtio_ring: validate used buffer length This patch validate the used buffer length provided by the device before trying to use it. This is done by record the in buffer length in a new field in desc_state structure during virtqueue_add(), then we can fail the virtqueue_get_buf() when we find the device is trying to give us a used buffer length which is greater than the in buffer length. Since some drivers have already done the validation by themselves, this patch tries to makes the core validation optional. For the driver that doesn't want the validation, it can set the suppress_used_validation to be true (which could be overridden by force_used_validation module parameter). To be more efficient, a dedicate array is used for storing the validate used length, this helps to eliminate the cache stress if validation is done by the driver. Signed-off-by: Jason Wang Link: https://lore.kernel.org/r/20211027022107.14357-2-jasowang@redhat.com Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 60 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/virtio.h | 2 ++ 2 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 6d2614e34470..00f64f2f8b72 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -14,6 +14,9 @@ #include #include +static bool force_used_validation = false; +module_param(force_used_validation, bool, 0444); + #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ #define BAD_RING(_vq, fmt, args...) \ @@ -182,6 +185,9 @@ struct vring_virtqueue { } packed; }; + /* Per-descriptor in buffer length */ + u32 *buflen; + /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); @@ -490,6 +496,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, unsigned int i, n, avail, descs_used, prev, err_idx; int head; bool indirect; + u32 buflen = 0; START_USE(vq); @@ -571,6 +578,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE, indirect); + buflen += sg->length; } } /* Last one doesn't continue. */ @@ -610,6 +618,10 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, else vq->split.desc_state[head].indir_desc = ctx; + /* Store in buffer length if necessary */ + if (vq->buflen) + vq->buflen[head] = buflen; + /* Put entry in available array (but don't update avail->idx until they * do sync). */ avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1); @@ -784,6 +796,11 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq, BAD_RING(vq, "id %u is not a head!\n", i); return NULL; } + if (vq->buflen && unlikely(*len > vq->buflen[i])) { + BAD_RING(vq, "used len %d is larger than in buflen %u\n", + *len, vq->buflen[i]); + return NULL; + } /* detach_buf_split clears data, so grab it now. */ ret = vq->split.desc_state[i].data; @@ -1062,6 +1079,7 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, unsigned int i, n, err_idx; u16 head, id; dma_addr_t addr; + u32 buflen = 0; head = vq->packed.next_avail_idx; desc = alloc_indirect_packed(total_sg, gfp); @@ -1091,6 +1109,8 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(sg->length); i++; + if (n >= out_sgs) + buflen += sg->length; } } @@ -1144,6 +1164,10 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, vq->packed.desc_state[id].indir_desc = desc; vq->packed.desc_state[id].last = id; + /* Store in buffer length if necessary */ + if (vq->buflen) + vq->buflen[id] = buflen; + vq->num_added += 1; pr_debug("Added buffer head %i to %p\n", head, vq); @@ -1179,6 +1203,7 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, __le16 head_flags, flags; u16 head, id, prev, curr, avail_used_flags; int err; + u32 buflen = 0; START_USE(vq); @@ -1258,6 +1283,8 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } + if (n >= out_sgs) + buflen += sg->length; } } @@ -1277,6 +1304,10 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, vq->packed.desc_state[id].indir_desc = ctx; vq->packed.desc_state[id].last = prev; + /* Store in buffer length if necessary */ + if (vq->buflen) + vq->buflen[id] = buflen; + /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising @@ -1463,6 +1494,11 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, BAD_RING(vq, "id %u is not a head!\n", id); return NULL; } + if (vq->buflen && unlikely(*len > vq->buflen[id])) { + BAD_RING(vq, "used len %d is larger than in buflen %u\n", + *len, vq->buflen[id]); + return NULL; + } /* detach_buf_packed clears data, so grab it now. */ ret = vq->packed.desc_state[id].data; @@ -1668,6 +1704,7 @@ static struct virtqueue *vring_create_virtqueue_packed( struct vring_virtqueue *vq; struct vring_packed_desc *ring; struct vring_packed_desc_event *driver, *device; + struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver); dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr; size_t ring_size_in_bytes, event_size_in_bytes; @@ -1757,6 +1794,15 @@ static struct virtqueue *vring_create_virtqueue_packed( if (!vq->packed.desc_extra) goto err_desc_extra; + if (!drv->suppress_used_validation || force_used_validation) { + vq->buflen = kmalloc_array(num, sizeof(*vq->buflen), + GFP_KERNEL); + if (!vq->buflen) + goto err_buflen; + } else { + vq->buflen = NULL; + } + /* No callback? Tell other side not to bother us. */ if (!callback) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; @@ -1769,6 +1815,8 @@ static struct virtqueue *vring_create_virtqueue_packed( spin_unlock(&vdev->vqs_list_lock); return &vq->vq; +err_buflen: + kfree(vq->packed.desc_extra); err_desc_extra: kfree(vq->packed.desc_state); err_desc_state: @@ -2176,6 +2224,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, void (*callback)(struct virtqueue *), const char *name) { + struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver); struct vring_virtqueue *vq; if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) @@ -2235,6 +2284,15 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, if (!vq->split.desc_extra) goto err_extra; + if (!drv->suppress_used_validation || force_used_validation) { + vq->buflen = kmalloc_array(vring.num, sizeof(*vq->buflen), + GFP_KERNEL); + if (!vq->buflen) + goto err_buflen; + } else { + vq->buflen = NULL; + } + /* Put everything in free lists. */ vq->free_head = 0; memset(vq->split.desc_state, 0, vring.num * @@ -2245,6 +2303,8 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, spin_unlock(&vdev->vqs_list_lock); return &vq->vq; +err_buflen: + kfree(vq->split.desc_extra); err_extra: kfree(vq->split.desc_state); err_state: diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 41edbc01ffa4..44d0e09da2d9 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -152,6 +152,7 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); * @feature_table_size: number of entries in the feature table array. * @feature_table_legacy: same as feature_table but when working in legacy mode. * @feature_table_size_legacy: number of entries in feature table legacy array. + * @suppress_used_validation: set to not have core validate used length * @probe: the function to call when a device is found. Returns 0 or -errno. * @scan: optional function to call after successful probe; intended * for virtio-scsi to invoke a scan. @@ -168,6 +169,7 @@ struct virtio_driver { unsigned int feature_table_size; const unsigned int *feature_table_legacy; unsigned int feature_table_size_legacy; + bool suppress_used_validation; int (*validate)(struct virtio_device *dev); int (*probe)(struct virtio_device *dev); void (*scan)(struct virtio_device *dev); -- cgit v1.2.3 From 6dbb1f1687a2ccdfc5b84b0a35bbc6dfefc4de3b Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 26 Oct 2021 20:55:12 +0300 Subject: vdpa: Introduce and use vdpa device get, set config helpers Subsequent patches enable get and set configuration either via management device or via vdpa device' config ops. This requires synchronization between multiple callers to get and set config callbacks. Features setting also influence the layout of the configuration fields endianness. To avoid exposing synchronization primitives to callers, introduce helper for setting the configuration and use it. Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Acked-by: Jason Wang Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211026175519.87795-2-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 36 ++++++++++++++++++++++++++++++++++++ drivers/vhost/vdpa.c | 3 +-- drivers/virtio/virtio_vdpa.c | 3 +-- include/linux/vdpa.h | 19 ++++--------------- 4 files changed, 42 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index fcf02a364878..cbc8fc69cf9b 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -297,6 +297,42 @@ void vdpa_mgmtdev_unregister(struct vdpa_mgmt_dev *mdev) } EXPORT_SYMBOL_GPL(vdpa_mgmtdev_unregister); +/** + * vdpa_get_config - Get one or more device configuration fields. + * @vdev: vdpa device to operate on + * @offset: starting byte offset of the field + * @buf: buffer pointer to read to + * @len: length of the configuration fields in bytes + */ +void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, + void *buf, unsigned int len) +{ + const struct vdpa_config_ops *ops = vdev->config; + + /* + * Config accesses aren't supposed to trigger before features are set. + * If it does happen we assume a legacy guest. + */ + if (!vdev->features_valid) + vdpa_set_features(vdev, 0); + ops->get_config(vdev, offset, buf, len); +} +EXPORT_SYMBOL_GPL(vdpa_get_config); + +/** + * vdpa_set_config - Set one or more device configuration fields. + * @vdev: vdpa device to operate on + * @offset: starting byte offset of the field + * @buf: buffer pointer to read from + * @length: length of the configuration fields in bytes + */ +void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, + const void *buf, unsigned int length) +{ + vdev->config->set_config(vdev, offset, buf, length); +} +EXPORT_SYMBOL_GPL(vdpa_set_config); + static bool mgmtdev_handle_match(const struct vdpa_mgmt_dev *mdev, const char *busname, const char *devname) { diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 39039e046117..01c59ce7e250 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -237,7 +237,6 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v, struct vhost_vdpa_config __user *c) { struct vdpa_device *vdpa = v->vdpa; - const struct vdpa_config_ops *ops = vdpa->config; struct vhost_vdpa_config config; unsigned long size = offsetof(struct vhost_vdpa_config, buf); u8 *buf; @@ -251,7 +250,7 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v, if (IS_ERR(buf)) return PTR_ERR(buf); - ops->set_config(vdpa, config.off, buf, config.len); + vdpa_set_config(vdpa, config.off, buf, config.len); kvfree(buf); return 0; diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index 6b62aaf08cc5..f85f860bc10b 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -65,9 +65,8 @@ static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset, const void *buf, unsigned len) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - ops->set_config(vdpa, offset, buf, len); + vdpa_set_config(vdpa, offset, buf, len); } static u32 virtio_vdpa_generation(struct virtio_device *vdev) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 30864848950b..267236aab34c 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -386,21 +386,10 @@ static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) return ops->set_features(vdev, features); } -static inline void vdpa_get_config(struct vdpa_device *vdev, - unsigned int offset, void *buf, - unsigned int len) -{ - const struct vdpa_config_ops *ops = vdev->config; - - /* - * Config accesses aren't supposed to trigger before features are set. - * If it does happen we assume a legacy guest. - */ - if (!vdev->features_valid) - vdpa_set_features(vdev, 0); - ops->get_config(vdev, offset, buf, len); -} - +void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, + void *buf, unsigned int len); +void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, + const void *buf, unsigned int length); /** * struct vdpa_mgmtdev_ops - vdpa device ops * @dev_add: Add a vdpa device using alloc and register -- cgit v1.2.3 From ad69dd0bf26b88ec6ab26f8bbe5cd74fbed7672a Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 26 Oct 2021 20:55:13 +0300 Subject: vdpa: Introduce query of device config layout Introduce a command to query a device config layout. An example query of network vdpa device: $ vdpa dev add name bar mgmtdev vdpasim_net $ vdpa dev config show bar: mac 00:35:09:19:48:05 link up link_announce false mtu 1500 $ vdpa dev config show -jp { "config": { "bar": { "mac": "00:35:09:19:48:05", "link ": "up", "link_announce ": false, "mtu": 1500, } } } Signed-off-by: Parav Pandit Signed-off-by: Eli Cohen Acked-by: Jason Wang Link: https://lore.kernel.org/r/20211026175519.87795-3-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 2 + include/uapi/linux/vdpa.h | 6 ++ 3 files changed, 184 insertions(+) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index cbc8fc69cf9b..8fcbdda8590c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include static LIST_HEAD(mdev_head); /* A global mutex that protects vdpa management device and device level operations. */ @@ -66,6 +68,7 @@ static void vdpa_release_dev(struct device *d) ops->free(vdev); ida_simple_remove(&vdpa_index_ida, vdev->index); + mutex_destroy(&vdev->cf_mutex); kfree(vdev); } @@ -127,6 +130,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, if (err) goto err_name; + mutex_init(&vdev->cf_mutex); device_initialize(&vdev->dev); return vdev; @@ -309,6 +313,7 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, { const struct vdpa_config_ops *ops = vdev->config; + mutex_lock(&vdev->cf_mutex); /* * Config accesses aren't supposed to trigger before features are set. * If it does happen we assume a legacy guest. @@ -316,6 +321,7 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, if (!vdev->features_valid) vdpa_set_features(vdev, 0); ops->get_config(vdev, offset, buf, len); + mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_get_config); @@ -329,7 +335,9 @@ EXPORT_SYMBOL_GPL(vdpa_get_config); void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, const void *buf, unsigned int length) { + mutex_lock(&vdev->cf_mutex); vdev->config->set_config(vdev, offset, buf, length); + mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_set_config); @@ -661,6 +669,168 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba return msg->len; } +static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev, + struct sk_buff *msg, u64 features, + const struct virtio_net_config *config) +{ + u16 val_u16; + + if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0) + return 0; + + val_u16 = le16_to_cpu(config->max_virtqueue_pairs); + return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16); +} + +static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) +{ + struct virtio_net_config config = {}; + u64 features; + u16 val_u16; + + vdpa_get_config(vdev, 0, &config, sizeof(config)); + + if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac), + config.mac)) + return -EMSGSIZE; + + val_u16 = le16_to_cpu(config.status); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16)) + return -EMSGSIZE; + + val_u16 = le16_to_cpu(config.mtu); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16)) + return -EMSGSIZE; + + features = vdev->config->get_features(vdev); + + return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); +} + +static int +vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u32 device_id; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, + VDPA_CMD_DEV_CONFIG_GET); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) { + err = -EMSGSIZE; + goto msg_err; + } + + device_id = vdev->config->get_device_id(vdev); + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) { + err = -EMSGSIZE; + goto msg_err; + } + + switch (device_id) { + case VIRTIO_ID_NET: + err = vdpa_dev_net_config_fill(vdev, msg); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + goto msg_err; + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device"); + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_config_fill(vdev, msg, info->snd_portid, info->snd_seq, + 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); + +mdev_err: + put_device(dev); +dev_err: + mutex_unlock(&vdpa_dev_mutex); + if (err) + nlmsg_free(msg); + return err; +} + +static int vdpa_dev_config_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_config_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, + info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int +vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + mutex_lock(&vdpa_dev_mutex); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_config_dump); + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = info.idx; + return msg->len; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, @@ -692,6 +862,12 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_get_doit, .dumpit = vdpa_nl_cmd_dev_get_dumpit, }, + { + .cmd = VDPA_CMD_DEV_CONFIG_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_config_get_doit, + .dumpit = vdpa_nl_cmd_dev_config_get_dumpit, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 267236aab34c..5cc5e501397f 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -63,6 +63,7 @@ struct vdpa_mgmt_dev; * @dev: underlying device * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. + * @cf_mutex: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests * @use_va: indicate whether virtual address must be used by this device @@ -74,6 +75,7 @@ struct vdpa_device { struct device dev; struct device *dma_dev; const struct vdpa_config_ops *config; + struct mutex cf_mutex; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index e3b87879514c..a252f06f9dfd 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -17,6 +17,7 @@ enum vdpa_command { VDPA_CMD_DEV_NEW, VDPA_CMD_DEV_DEL, VDPA_CMD_DEV_GET, /* can dump */ + VDPA_CMD_DEV_CONFIG_GET, /* can dump */ }; enum vdpa_attr { @@ -34,6 +35,11 @@ enum vdpa_attr { VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ VDPA_ATTR_DEV_MIN_VQ_SIZE, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MACADDR, /* binary */ + VDPA_ATTR_DEV_NET_STATUS, /* u8 */ + VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From 960deb33be3d08e55a39e40e0286a51c7448e053 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 26 Oct 2021 20:55:14 +0300 Subject: vdpa: Use kernel coding style for structure comments As subsequent patch adds new structure field with comment, move the structure comment to follow kernel coding style. Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Acked-by: Jason Wang Reviewed-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211026175519.87795-4-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- include/linux/vdpa.h | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 5cc5e501397f..fafb7202482c 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -411,10 +411,17 @@ struct vdpa_mgmtdev_ops { void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); }; +/** + * struct vdpa_mgmt_dev - vdpa management device + * @device: Management parent device + * @ops: operations supported by management device + * @id_table: Pointer to device id table of supported ids + * @list: list entry + */ struct vdpa_mgmt_dev { struct device *device; const struct vdpa_mgmtdev_ops *ops; - const struct virtio_device_id *id_table; /* supported ids */ + const struct virtio_device_id *id_table; struct list_head list; }; -- cgit v1.2.3 From d8ca2fa5be1bdb9d08cfe1f831cddb622a01dfd4 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 26 Oct 2021 20:55:15 +0300 Subject: vdpa: Enable user to set mac and mtu of vdpa device $ vdpa dev add name bar mgmtdev vdpasim_net mac 00:11:22:33:44:55 mtu 9000 $ vdpa dev config show bar: mac 00:11:22:33:44:55 link up link_announce false mtu 9000 $ vdpa dev config show -jp { "config": { "bar": { "mac": "00:11:22:33:44:55", "link ": "up", "link_announce ": false, "mtu": 9000, } } } Signed-off-by: Parav Pandit Reviewed-by: Eli Cohen Acked-by: Jason Wang Link: https://lore.kernel.org/r/20211026175519.87795-5-parav@nvidia.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Stefano Garzarella --- drivers/vdpa/ifcvf/ifcvf_main.c | 3 ++- drivers/vdpa/mlx5/net/mlx5_vnet.c | 3 ++- drivers/vdpa/vdpa.c | 38 ++++++++++++++++++++++++++++++++++-- drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 3 ++- drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 3 ++- drivers/vdpa/vdpa_user/vduse_dev.c | 3 ++- include/linux/vdpa.h | 17 +++++++++++++++- 7 files changed, 62 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index dcd648e1f7e7..6dc75ca70b37 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -499,7 +499,8 @@ static u32 get_dev_type(struct pci_dev *pdev) return dev_type; } -static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) { struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev; struct ifcvf_adapter *adapter; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index b5bd1a553256..6bbdc0ece707 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -2482,7 +2482,8 @@ static int event_handler(struct notifier_block *nb, unsigned long event, void *p return ret; } -static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name) +static int mlx5_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name, + const struct vdpa_dev_set_config *add_config) { struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev); struct virtio_net_config *config; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 8fcbdda8590c..7332a74a4b00 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -14,7 +14,6 @@ #include #include #include -#include #include static LIST_HEAD(mdev_head); @@ -480,9 +479,15 @@ out: return msg->len; } +#define VDPA_DEV_NET_ATTRS_MASK ((1 << VDPA_ATTR_DEV_NET_CFG_MACADDR) | \ + (1 << VDPA_ATTR_DEV_NET_CFG_MTU)) + static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) { + struct vdpa_dev_set_config config = {}; + struct nlattr **nl_attrs = info->attrs; struct vdpa_mgmt_dev *mdev; + const u8 *macaddr; const char *name; int err = 0; @@ -491,6 +496,26 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i name = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]) { + macaddr = nla_data(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MACADDR]); + memcpy(config.net.mac, macaddr, sizeof(config.net.mac)); + config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR); + } + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]) { + config.net.mtu = + nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]); + config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MTU); + } + + /* Skip checking capability if user didn't prefer to configure any + * device networking attributes. It is likely that user might have used + * a device specific method to configure such attributes or using device + * default attributes. + */ + if ((config.mask & VDPA_DEV_NET_ATTRS_MASK) && + !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + mutex_lock(&vdpa_dev_mutex); mdev = vdpa_mgmtdev_get_from_attr(info->attrs); if (IS_ERR(mdev)) { @@ -498,8 +523,14 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i err = PTR_ERR(mdev); goto err; } + if ((config.mask & mdev->config_attr_mask) != config.mask) { + NL_SET_ERR_MSG_MOD(info->extack, + "All provided attributes are not supported"); + err = -EOPNOTSUPP; + goto err; + } - err = mdev->ops->dev_add(mdev, name); + err = mdev->ops->dev_add(mdev, name, &config); err: mutex_unlock(&vdpa_dev_mutex); return err; @@ -835,6 +866,9 @@ static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, [VDPA_ATTR_DEV_NAME] = { .type = NLA_STRING }, + [VDPA_ATTR_DEV_NET_CFG_MACADDR] = NLA_POLICY_ETH_ADDR, + /* virtio spec 1.1 section 5.1.4.1 for valid MTU range */ + [VDPA_ATTR_DEV_NET_CFG_MTU] = NLA_POLICY_MIN(NLA_U16, 68), }; static const struct genl_ops vdpa_nl_ops[] = { diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index a790903f243e..42d401d43911 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -248,7 +248,8 @@ static struct device vdpasim_blk_mgmtdev = { .release = vdpasim_blk_mgmtdev_release, }; -static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) { struct vdpasim_dev_attr dev_attr = {}; struct vdpasim *simdev; diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c index a1ab6163f7d1..d681e423e64f 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c @@ -126,7 +126,8 @@ static struct device vdpasim_net_mgmtdev = { .release = vdpasim_net_mgmtdev_release, }; -static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) { struct vdpasim_dev_attr dev_attr = {}; struct vdpasim *simdev; diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index 841667a896dd..c9204c62f339 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -1503,7 +1503,8 @@ static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name) return 0; } -static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name) +static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config) { struct vduse_dev *dev; int ret; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index fafb7202482c..c3011ccda430 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -6,6 +6,8 @@ #include #include #include +#include +#include /** * struct vdpa_calllback - vDPA callback definition. @@ -93,6 +95,14 @@ struct vdpa_iova_range { u64 last; }; +struct vdpa_dev_set_config { + struct { + u8 mac[ETH_ALEN]; + u16 mtu; + } net; + u64 mask; +}; + /** * Corresponding file area for device memory mapping * @file: vma->vm_file for the mapping @@ -397,6 +407,7 @@ void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, * @dev_add: Add a vdpa device using alloc and register * @mdev: parent device to use for device addition * @name: name of the new vdpa device + * @config: config attributes to apply to the device under creation * Driver need to add a new device using _vdpa_register_device() * after fully initializing the vdpa device. Driver must return 0 * on success or appropriate error code. @@ -407,7 +418,8 @@ void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, * _vdpa_unregister_device(). */ struct vdpa_mgmtdev_ops { - int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name); + int (*dev_add)(struct vdpa_mgmt_dev *mdev, const char *name, + const struct vdpa_dev_set_config *config); void (*dev_del)(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev); }; @@ -416,12 +428,15 @@ struct vdpa_mgmtdev_ops { * @device: Management parent device * @ops: operations supported by management device * @id_table: Pointer to device id table of supported ids + * @config_attr_mask: bit mask of attributes of type enum vdpa_attr that + * management device support during dev_add callback * @list: list entry */ struct vdpa_mgmt_dev { struct device *device; const struct vdpa_mgmtdev_ops *ops; const struct virtio_device_id *id_table; + u64 config_attr_mask; struct list_head list; }; -- cgit v1.2.3 From 7303524e04af49a47991e19f895c3b8cdc3796c7 Mon Sep 17 00:00:00 2001 From: Liu Jian Date: Fri, 29 Oct 2021 22:12:14 +0800 Subject: skmsg: Lose offset info in sk_psock_skb_ingress If sockmap enable strparser, there are lose offset info in sk_psock_skb_ingress(). If the length determined by parse_msg function is not skb->len, the skb will be converted to sk_msg multiple times, and userspace app will get the data multiple times. Fix this by get the offset and length from strp_msg. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser. Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian Signed-off-by: Daniel Borkmann Reviewed-by: Cong Wang Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com --- include/linux/skmsg.h | 18 ++++++++++++++++-- net/core/skmsg.c | 43 +++++++++++++++++++++++++++++++++---------- 2 files changed, 49 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 14ab0c0bc924..94e2a1f6e58d 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -508,8 +508,22 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) #if IS_ENABLED(CONFIG_NET_SOCK_MSG) -/* We only have one bit so far. */ -#define BPF_F_PTR_MASK ~(BPF_F_INGRESS) +#define BPF_F_STRPARSER (1UL << 1) + +/* We only have two bits so far. */ +#define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) + +static inline bool skb_bpf_strparser(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return sk_redir & BPF_F_STRPARSER; +} + +static inline void skb_bpf_set_strparser(struct sk_buff *skb) +{ + skb->_sk_redir |= BPF_F_STRPARSER; +} static inline bool skb_bpf_ingress(const struct sk_buff *skb) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2d6249b28928..9701a1404ccb 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -494,6 +494,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk, } static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, + u32 off, u32 len, struct sk_psock *psock, struct sock *sk, struct sk_msg *msg) @@ -507,11 +508,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, */ if (skb_linearize(skb)) return -EAGAIN; - num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len); + num_sge = skb_to_sgvec(skb, msg->sg.data, off, len); if (unlikely(num_sge < 0)) return num_sge; - copied = skb->len; + copied = len; msg->sg.start = 0; msg->sg.size = copied; msg->sg.end = num_sge; @@ -522,9 +523,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return copied; } -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb); +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len); -static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sock *sk = psock->sk; struct sk_msg *msg; @@ -535,7 +538,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * correctly. */ if (unlikely(skb->sk == sk)) - return sk_psock_skb_ingress_self(psock, skb); + return sk_psock_skb_ingress_self(psock, skb, off, len); msg = sk_psock_create_ingress_msg(sk, skb); if (!msg) return -EAGAIN; @@ -547,7 +550,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * into user buffers. */ skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -557,7 +560,8 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) * skb. In this case we do not need to check memory limits or skb_set_owner_r * because the skb is already accounted for here. */ -static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb) +static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb, + u32 off, u32 len) { struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); struct sock *sk = psock->sk; @@ -567,7 +571,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb return -EAGAIN; sk_msg_init(msg); skb_set_owner_r(skb, sk); - err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); + err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg); if (err < 0) kfree(msg); return err; @@ -581,7 +585,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, return -EAGAIN; return skb_send_sock(psock->sk, skb, off, len); } - return sk_psock_skb_ingress(psock, skb); + return sk_psock_skb_ingress(psock, skb, off, len); } static void sk_psock_skb_state(struct sk_psock *psock, @@ -624,6 +628,12 @@ static void sk_psock_backlog(struct work_struct *work) while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); @@ -863,6 +873,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { + skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } @@ -930,6 +941,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, { struct sock *sk_other; int err = 0; + u32 len, off; switch (verdict) { case __SK_PASS: @@ -937,6 +949,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + skb_bpf_redirect_clear(skb); goto out_free; } @@ -949,7 +962,15 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, * retrying later from workqueue. */ if (skb_queue_empty(&psock->ingress_skb)) { - err = sk_psock_skb_ingress_self(psock, skb); + len = skb->len; + off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } + err = sk_psock_skb_ingress_self(psock, skb, off, len); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); @@ -1015,6 +1036,8 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); + if (ret == SK_PASS) + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; } -- cgit v1.2.3 From 588e5d8766486e52ee332a4bb097b016a355b465 Mon Sep 17 00:00:00 2001 From: He Fengqing Date: Fri, 29 Oct 2021 02:39:06 +0000 Subject: cgroup: bpf: Move wrapper for __cgroup_bpf_*() to kernel/bpf/cgroup.c In commit 324bda9e6c5a("bpf: multi program support for cgroup+bpf") cgroup_bpf_*() called from kernel/bpf/syscall.c, but now they are only used in kernel/bpf/cgroup.c, so move these function to kernel/bpf/cgroup.c, like cgroup_bpf_replace(). Signed-off-by: He Fengqing Signed-off-by: Tejun Heo --- include/linux/bpf-cgroup.h | 20 ----------------- kernel/bpf/cgroup.c | 54 ++++++++++++++++++++++++++++++++++++++-------- kernel/cgroup/cgroup.c | 38 -------------------------------- 3 files changed, 45 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 2746fd804216..9aad4e3ca29b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -157,26 +157,6 @@ struct cgroup_bpf { int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); -int __cgroup_bpf_attach(struct cgroup *cgrp, - struct bpf_prog *prog, struct bpf_prog *replace_prog, - struct bpf_cgroup_link *link, - enum bpf_attach_type type, u32 flags); -int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_cgroup_link *link, - enum bpf_attach_type type); -int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr); - -/* Wrapper for __cgroup_bpf_*() protected by cgroup_mutex */ -int cgroup_bpf_attach(struct cgroup *cgrp, - struct bpf_prog *prog, struct bpf_prog *replace_prog, - struct bpf_cgroup_link *link, enum bpf_attach_type type, - u32 flags); -int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type); -int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr); - int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 03145d45e3d5..2ca643af9a54 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -430,10 +430,10 @@ static struct bpf_prog_list *find_attach_entry(struct list_head *progs, * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_attach(struct cgroup *cgrp, - struct bpf_prog *prog, struct bpf_prog *replace_prog, - struct bpf_cgroup_link *link, - enum bpf_attach_type type, u32 flags) +static int __cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, + enum bpf_attach_type type, u32 flags) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); struct bpf_prog *old_prog = NULL; @@ -523,6 +523,20 @@ cleanup: return err; } +static int cgroup_bpf_attach(struct cgroup *cgrp, + struct bpf_prog *prog, struct bpf_prog *replace_prog, + struct bpf_cgroup_link *link, + enum bpf_attach_type type, + u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} + /* Swap updated BPF program for given link in effective program arrays across * all descendant cgroups. This function is guaranteed to succeed. */ @@ -672,14 +686,14 @@ static struct bpf_prog_list *find_detach_entry(struct list_head *progs, * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to detach or NULL - * @prog: A link to detach or NULL + * @link: A link to detach or NULL * @type: Type of detach operation * * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ -int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - struct bpf_cgroup_link *link, enum bpf_attach_type type) +static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + struct bpf_cgroup_link *link, enum bpf_attach_type type) { enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; @@ -730,9 +744,20 @@ cleanup: return err; } +static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); + mutex_unlock(&cgroup_mutex); + return ret; +} + /* Must be called with cgroup_mutex held to avoid races. */ -int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr) +static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); enum bpf_attach_type type = attr->query.attach_type; @@ -789,6 +814,17 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, return ret; } +static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_query(cgrp, attr, uattr); + mutex_unlock(&cgroup_mutex); + return ret; +} + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 003204c85893..c73f634c8328 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6676,44 +6676,6 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ -#ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_attach(struct cgroup *cgrp, - struct bpf_prog *prog, struct bpf_prog *replace_prog, - struct bpf_cgroup_link *link, - enum bpf_attach_type type, - u32 flags) -{ - int ret; - - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); - mutex_unlock(&cgroup_mutex); - return ret; -} - -int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type) -{ - int ret; - - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); - mutex_unlock(&cgroup_mutex); - return ret; -} - -int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, - union bpf_attr __user *uattr) -{ - int ret; - - mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_query(cgrp, attr, uattr); - mutex_unlock(&cgroup_mutex); - return ret; -} -#endif /* CONFIG_CGROUP_BPF */ - #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) -- cgit v1.2.3 From ebe4560ed5c8cbfe3759f16c23ca5a6df090c6b5 Mon Sep 17 00:00:00 2001 From: Oscar Carter Date: Sat, 30 May 2020 11:08:39 +0200 Subject: firewire: Remove function callback casts In 1394 OHCI specification, Isochronous Receive DMA context has several modes. One of mode is 'BufferFill' and Linux FireWire stack uses it to receive isochronous packets for multiple isochronous channel as FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL. The mode is not used by in-kernel driver, while it's available for userspace. The character device driver in firewire-core includes cast of function callback for the mode since the type of callback function is different from the other modes. The case is inconvenient to effort of Control Flow Integrity builds due to -Wcast-function-type warning. This commit removes the cast. A static helper function is newly added to initialize isochronous context for the mode. The helper function arranges isochronous context to assign specific callback function after call of existent kernel API. It's noticeable that the number of isochronous channel, speed, and the size of header are not required for the mode. The helper function is used for the mode by character device driver instead of direct call of existent kernel API. The same goal can be achieved (in the ioctl_create_iso_context function) without this helper function as follows: - Call the fw_iso_context_create function passing NULL to the callback parameter. - Then setting the context->callback.sc or context->callback.mc variables based on the a->type value. However using the helper function created in this patch makes code more clear and declarative. This way avoid the call to a function with one purpose to achieved another one. Co-developed-by: Takashi Sakamoto Signed-off-by: Takashi Sakamoto Co-developed-by: Stefan Richter Signed-off-by: Stefan Richter Signed-off-by: Oscar Carter Reviewed-by: Takashi Sakamoto Testeb-by: Takashi Sakamoto Signed-off-by: Gustavo A. R. Silva --- drivers/firewire/core-cdev.c | 32 ++++++++++++++++++++++++++------ include/linux/firewire.h | 11 +++++++---- 2 files changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index fb6c651214f3..9f89c17730b1 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -953,11 +954,25 @@ static enum dma_data_direction iso_dma_direction(struct fw_iso_context *context) return DMA_FROM_DEVICE; } +static struct fw_iso_context *fw_iso_mc_context_create(struct fw_card *card, + fw_iso_mc_callback_t callback, + void *callback_data) +{ + struct fw_iso_context *ctx; + + ctx = fw_iso_context_create(card, FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL, + 0, 0, 0, NULL, callback_data); + if (!IS_ERR(ctx)) + ctx->callback.mc = callback; + + return ctx; +} + static int ioctl_create_iso_context(struct client *client, union ioctl_arg *arg) { struct fw_cdev_create_iso_context *a = &arg->create_iso_context; struct fw_iso_context *context; - fw_iso_callback_t cb; + union fw_iso_callback cb; int ret; BUILD_BUG_ON(FW_CDEV_ISO_CONTEXT_TRANSMIT != FW_ISO_CONTEXT_TRANSMIT || @@ -970,7 +985,7 @@ static int ioctl_create_iso_context(struct client *client, union ioctl_arg *arg) if (a->speed > SCODE_3200 || a->channel > 63) return -EINVAL; - cb = iso_callback; + cb.sc = iso_callback; break; case FW_ISO_CONTEXT_RECEIVE: @@ -978,19 +993,24 @@ static int ioctl_create_iso_context(struct client *client, union ioctl_arg *arg) a->channel > 63) return -EINVAL; - cb = iso_callback; + cb.sc = iso_callback; break; case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL: - cb = (fw_iso_callback_t)iso_mc_callback; + cb.mc = iso_mc_callback; break; default: return -EINVAL; } - context = fw_iso_context_create(client->device->card, a->type, - a->channel, a->speed, a->header_size, cb, client); + if (a->type == FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL) + context = fw_iso_mc_context_create(client->device->card, cb.mc, + client); + else + context = fw_iso_context_create(client->device->card, a->type, + a->channel, a->speed, + a->header_size, cb.sc, client); if (IS_ERR(context)) return PTR_ERR(context); if (client->version < FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW) diff --git a/include/linux/firewire.h b/include/linux/firewire.h index aec8f30ab200..07967a450eaa 100644 --- a/include/linux/firewire.h +++ b/include/linux/firewire.h @@ -436,6 +436,12 @@ typedef void (*fw_iso_callback_t)(struct fw_iso_context *context, void *header, void *data); typedef void (*fw_iso_mc_callback_t)(struct fw_iso_context *context, dma_addr_t completed, void *data); + +union fw_iso_callback { + fw_iso_callback_t sc; + fw_iso_mc_callback_t mc; +}; + struct fw_iso_context { struct fw_card *card; int type; @@ -443,10 +449,7 @@ struct fw_iso_context { int speed; bool drop_overflow_headers; size_t header_size; - union { - fw_iso_callback_t sc; - fw_iso_mc_callback_t mc; - } callback; + union fw_iso_callback callback; void *callback_data; }; -- cgit v1.2.3 From 74128d801b5165650ae6222e8cf23780fbc55e67 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 23 Sep 2021 01:09:45 +0200 Subject: watchdog: ux500_wdt: Drop platform data Drop the platform data passing from the PRCMU driver. This platform data was part of the ambition to support more SoCs, which in turn were never mass produced. Only a name remains of the MFD cell so switch to MFD_CELL_NAME(). Cc: Lee Jones Signed-off-by: Linus Walleij Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20210922230947.1864357-1-linus.walleij@linaro.org Acked-by: Lee Jones Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/mfd/db8500-prcmu.c | 13 +------------ drivers/watchdog/ux500_wdt.c | 13 ++----------- include/linux/platform_data/ux500_wdt.h | 18 ------------------ 3 files changed, 3 insertions(+), 41 deletions(-) delete mode 100644 include/linux/platform_data/ux500_wdt.h (limited to 'include/linux') diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c index c1d3e7c116cf..ccf6be922b39 100644 --- a/drivers/mfd/db8500-prcmu.c +++ b/drivers/mfd/db8500-prcmu.c @@ -36,7 +36,6 @@ #include #include #include -#include #include "db8500-prcmu-regs.h" /* Index of different voltages to be used when accessing AVSData */ @@ -2939,18 +2938,8 @@ static struct regulator_init_data db8500_regulators[DB8500_NUM_REGULATORS] = { }, }; -static struct ux500_wdt_data db8500_wdt_pdata = { - .timeout = 600, /* 10 minutes */ - .has_28_bits_resolution = true, -}; - static const struct mfd_cell common_prcmu_devs[] = { - { - .name = "ux500_wdt", - .platform_data = &db8500_wdt_pdata, - .pdata_size = sizeof(db8500_wdt_pdata), - .id = -1, - }, + MFD_CELL_NAME("ux500_wdt"), MFD_CELL_NAME("db8500-cpuidle"), }; diff --git a/drivers/watchdog/ux500_wdt.c b/drivers/watchdog/ux500_wdt.c index 072758106865..40f8cf1cb234 100644 --- a/drivers/watchdog/ux500_wdt.c +++ b/drivers/watchdog/ux500_wdt.c @@ -15,7 +15,6 @@ #include #include #include -#include #include @@ -23,7 +22,6 @@ #define WATCHDOG_MIN 0 #define WATCHDOG_MAX28 268435 /* 28 bit resolution in ms == 268435.455 s */ -#define WATCHDOG_MAX32 4294967 /* 32 bit resolution in ms == 4294967.295 s */ static unsigned int timeout = WATCHDOG_TIMEOUT; module_param(timeout, uint, 0); @@ -80,22 +78,15 @@ static struct watchdog_device ux500_wdt = { .info = &ux500_wdt_info, .ops = &ux500_wdt_ops, .min_timeout = WATCHDOG_MIN, - .max_timeout = WATCHDOG_MAX32, + .max_timeout = WATCHDOG_MAX28, }; static int ux500_wdt_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; int ret; - struct ux500_wdt_data *pdata = dev_get_platdata(dev); - - if (pdata) { - if (pdata->timeout > 0) - timeout = pdata->timeout; - if (pdata->has_28_bits_resolution) - ux500_wdt.max_timeout = WATCHDOG_MAX28; - } + timeout = 600; /* Default to 10 minutes */ ux500_wdt.parent = dev; watchdog_set_nowayout(&ux500_wdt, nowayout); diff --git a/include/linux/platform_data/ux500_wdt.h b/include/linux/platform_data/ux500_wdt.h deleted file mode 100644 index de6a4ad41e76..000000000000 --- a/include/linux/platform_data/ux500_wdt.h +++ /dev/null @@ -1,18 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) ST Ericsson SA 2011 - * - * STE Ux500 Watchdog platform data - */ -#ifndef __UX500_WDT_H -#define __UX500_WDT_H - -/** - * struct ux500_wdt_data - */ -struct ux500_wdt_data { - unsigned int timeout; - bool has_28_bits_resolution; -}; - -#endif /* __UX500_WDT_H */ -- cgit v1.2.3 From 31a645aea4f8da5bb190ce322c6e5aacaef13855 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:22 +0800 Subject: bpf: Factor out a helper to prepare trampoline for struct_ops prog Factor out a helper bpf_struct_ops_prepare_trampoline() to prepare trampoline for BPF_PROG_TYPE_STRUCT_OPS prog. It will be used by .test_run callback in following patch. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-2-houtao1@huawei.com --- include/linux/bpf.h | 4 ++++ kernel/bpf/bpf_struct_ops.c | 29 +++++++++++++++++++---------- 2 files changed, 23 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6deebf8bf78f..aabd3540aaaf 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1000,6 +1000,10 @@ bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, + struct bpf_prog *prog, + const struct btf_func_model *model, + void *image, void *image_end); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 9abcc33f02cf..44be101f2562 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -312,6 +312,20 @@ static int check_zero_holes(const struct btf_type *t, void *data) return 0; } +int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_progs *tprogs, + struct bpf_prog *prog, + const struct btf_func_model *model, + void *image, void *image_end) +{ + u32 flags; + + tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; + tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = model->ret_size > 0 ? BPF_TRAMP_F_RET_FENTRY_RET : 0; + return arch_prepare_bpf_trampoline(NULL, image, image_end, + model, flags, tprogs, NULL); +} + static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { @@ -323,7 +337,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_tramp_progs *tprogs = NULL; void *udata, *kdata; int prog_fd, err = 0; - void *image; + void *image, *image_end; u32 i; if (flags) @@ -363,12 +377,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; image = st_map->image; + image_end = st_map->image + PAGE_SIZE; for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; - u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -430,14 +444,9 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, goto reset_unlock; } - tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; - tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; - flags = st_ops->func_models[i].ret_size > 0 ? - BPF_TRAMP_F_RET_FENTRY_RET : 0; - err = arch_prepare_bpf_trampoline(NULL, image, - st_map->image + PAGE_SIZE, - &st_ops->func_models[i], - flags, tprogs, NULL); + err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + &st_ops->func_models[i], + image, image_end); if (err < 0) goto reset_unlock; -- cgit v1.2.3 From 35346ab64132d0f5919b06932d708c0d10360553 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:23 +0800 Subject: bpf: Factor out helpers for ctx access checking Factor out two helpers to check the read access of ctx for raw tp and BTF function. bpf_tracing_ctx_access() is used to check the read access to argument is valid, and bpf_tracing_btf_ctx_access() checks whether the btf type of argument is valid besides the checking of argument read. bpf_tracing_btf_ctx_access() will be used by the following patch. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-3-houtao1@huawei.com --- include/linux/bpf.h | 23 +++++++++++++++++++++++ kernel/trace/bpf_trace.c | 16 ++-------------- net/ipv4/bpf_tcp_ca.c | 9 +-------- 3 files changed, 26 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index aabd3540aaaf..67f71e7def56 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1650,6 +1650,29 @@ bool bpf_prog_test_check_kfunc_call(u32 kfunc_id, struct module *owner); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); + +static inline bool bpf_tracing_ctx_access(int off, int size, + enum bpf_access_type type) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + return true; +} + +static inline bool bpf_tracing_btf_ctx_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (!bpf_tracing_ctx_access(off, size, type)) + return false; + return btf_ctx_access(off, size, type, prog, info); +} + int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cbcd0d6fca7c..7396488793ff 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1646,13 +1646,7 @@ static bool raw_tp_prog_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - return true; + return bpf_tracing_ctx_access(off, size, type); } static bool tracing_prog_is_valid_access(int off, int size, @@ -1660,13 +1654,7 @@ static bool tracing_prog_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - return btf_ctx_access(off, size, type, prog, info); + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); } int __weak bpf_prog_test_run_tracing(struct bpf_prog *prog, diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 57709ac09fb2..2cf02b4d77fb 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -81,14 +81,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) - return false; - if (type != BPF_READ) - return false; - if (off % size != 0) - return false; - - if (!btf_ctx_access(off, size, type, prog, info)) + if (!bpf_tracing_btf_ctx_access(off, size, type, prog, info)) return false; if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) -- cgit v1.2.3 From c196906d50e360d82ed9aa5596a9d0ce89b7ab78 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Mon, 25 Oct 2021 14:40:24 +0800 Subject: bpf: Add dummy BPF STRUCT_OPS for test purpose Currently the test of BPF STRUCT_OPS depends on the specific bpf implementation of tcp_congestion_ops, but it can not cover all basic functionalities (e.g, return value handling), so introduce a dummy BPF STRUCT_OPS for test purpose. Loading a bpf_dummy_ops implementation from userspace is prohibited, and its only purpose is to run BPF_PROG_TYPE_STRUCT_OPS program through bpf(BPF_PROG_TEST_RUN). Now programs for test_1() & test_2() are supported. The following three cases are exercised in bpf_dummy_struct_ops_test_run(): (1) test and check the value returned from state arg in test_1(state) The content of state is copied from userspace pointer and copied back after calling test_1(state). The user pointer is saved in an u64 array and the array address is passed through ctx_in. (2) test and check the return value of test_1(NULL) Just simulate the case in which an invalid input argument is passed in. (3) test multiple arguments passing in test_2(state, ...) 5 arguments are passed through ctx_in in form of u64 array. The first element of array is userspace pointer of state and others 4 arguments follow. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211025064025.2567443-4-houtao1@huawei.com --- include/linux/bpf.h | 16 +++ kernel/bpf/bpf_struct_ops.c | 3 + kernel/bpf/bpf_struct_ops_types.h | 3 + net/bpf/Makefile | 3 + net/bpf/bpf_dummy_struct_ops.c | 200 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 225 insertions(+) create mode 100644 net/bpf/bpf_dummy_struct_ops.c (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 67f71e7def56..c098089c1b54 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1018,6 +1018,22 @@ static inline void bpf_module_put(const void *data, struct module *owner) else module_put(owner); } + +#ifdef CONFIG_NET +/* Define it here to avoid the use of forward declaration */ +struct bpf_dummy_ops_state { + int val; +}; + +struct bpf_dummy_ops { + int (*test_1)(struct bpf_dummy_ops_state *cb); + int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, + char a3, unsigned long a4); +}; + +int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr); +#endif #else static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) { diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 44be101f2562..8ecfe4752769 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -93,6 +93,9 @@ const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; const struct bpf_prog_ops bpf_struct_ops_prog_ops = { +#ifdef CONFIG_NET + .test_run = bpf_struct_ops_test_run, +#endif }; static const struct btf_type *module_type; diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h index 066d83ea1c99..5678a9ddf817 100644 --- a/kernel/bpf/bpf_struct_ops_types.h +++ b/kernel/bpf/bpf_struct_ops_types.h @@ -2,6 +2,9 @@ /* internal file - do not include directly */ #ifdef CONFIG_BPF_JIT +#ifdef CONFIG_NET +BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) +#endif #ifdef CONFIG_INET #include BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) diff --git a/net/bpf/Makefile b/net/bpf/Makefile index 1c0a98d8c28f..1ebe270bde23 100644 --- a/net/bpf/Makefile +++ b/net/bpf/Makefile @@ -1,2 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_BPF_SYSCALL) := test_run.o +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_dummy_struct_ops.o +endif diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c new file mode 100644 index 000000000000..fbc896323bec --- /dev/null +++ b/net/bpf/bpf_dummy_struct_ops.c @@ -0,0 +1,200 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021. Huawei Technologies Co., Ltd + */ +#include +#include +#include +#include + +extern struct bpf_struct_ops bpf_bpf_dummy_ops; + +/* A common type for test_N with return value in bpf_dummy_ops */ +typedef int (*dummy_ops_test_ret_fn)(struct bpf_dummy_ops_state *state, ...); + +struct bpf_dummy_ops_test_args { + u64 args[MAX_BPF_FUNC_ARGS]; + struct bpf_dummy_ops_state state; +}; + +static struct bpf_dummy_ops_test_args * +dummy_ops_init_args(const union bpf_attr *kattr, unsigned int nr) +{ + __u32 size_in; + struct bpf_dummy_ops_test_args *args; + void __user *ctx_in; + void __user *u_state; + + size_in = kattr->test.ctx_size_in; + if (size_in != sizeof(u64) * nr) + return ERR_PTR(-EINVAL); + + args = kzalloc(sizeof(*args), GFP_KERNEL); + if (!args) + return ERR_PTR(-ENOMEM); + + ctx_in = u64_to_user_ptr(kattr->test.ctx_in); + if (copy_from_user(args->args, ctx_in, size_in)) + goto out; + + /* args[0] is 0 means state argument of test_N will be NULL */ + u_state = u64_to_user_ptr(args->args[0]); + if (u_state && copy_from_user(&args->state, u_state, + sizeof(args->state))) + goto out; + + return args; +out: + kfree(args); + return ERR_PTR(-EFAULT); +} + +static int dummy_ops_copy_args(struct bpf_dummy_ops_test_args *args) +{ + void __user *u_state; + + u_state = u64_to_user_ptr(args->args[0]); + if (u_state && copy_to_user(u_state, &args->state, sizeof(args->state))) + return -EFAULT; + + return 0; +} + +static int dummy_ops_call_op(void *image, struct bpf_dummy_ops_test_args *args) +{ + dummy_ops_test_ret_fn test = (void *)image; + struct bpf_dummy_ops_state *state = NULL; + + /* state needs to be NULL if args[0] is 0 */ + if (args->args[0]) + state = &args->state; + return test(state, args->args[1], args->args[2], + args->args[3], args->args[4]); +} + +int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + const struct bpf_struct_ops *st_ops = &bpf_bpf_dummy_ops; + const struct btf_type *func_proto; + struct bpf_dummy_ops_test_args *args; + struct bpf_tramp_progs *tprogs; + void *image = NULL; + unsigned int op_idx; + int prog_ret; + int err; + + if (prog->aux->attach_btf_id != st_ops->type_id) + return -EOPNOTSUPP; + + func_proto = prog->aux->attach_func_proto; + args = dummy_ops_init_args(kattr, btf_type_vlen(func_proto)); + if (IS_ERR(args)) + return PTR_ERR(args); + + tprogs = kcalloc(BPF_TRAMP_MAX, sizeof(*tprogs), GFP_KERNEL); + if (!tprogs) { + err = -ENOMEM; + goto out; + } + + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) { + err = -ENOMEM; + goto out; + } + set_vm_flush_reset_perms(image); + + op_idx = prog->expected_attach_type; + err = bpf_struct_ops_prepare_trampoline(tprogs, prog, + &st_ops->func_models[op_idx], + image, image + PAGE_SIZE); + if (err < 0) + goto out; + + set_memory_ro((long)image, 1); + set_memory_x((long)image, 1); + prog_ret = dummy_ops_call_op(image, args); + + err = dummy_ops_copy_args(args); + if (err) + goto out; + if (put_user(prog_ret, &uattr->test.retval)) + err = -EFAULT; +out: + kfree(args); + bpf_jit_free_exec(image); + kfree(tprogs); + return err; +} + +static int bpf_dummy_init(struct btf *btf) +{ + return 0; +} + +static bool bpf_dummy_ops_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + return bpf_tracing_btf_ctx_access(off, size, type, prog, info); +} + +static int bpf_dummy_ops_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id) +{ + const struct btf_type *state; + s32 type_id; + int err; + + type_id = btf_find_by_name_kind(btf, "bpf_dummy_ops_state", + BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + + state = btf_type_by_id(btf, type_id); + if (t != state) { + bpf_log(log, "only access to bpf_dummy_ops_state is supported\n"); + return -EACCES; + } + + err = btf_struct_access(log, btf, t, off, size, atype, next_btf_id); + if (err < 0) + return err; + + return atype == BPF_READ ? err : NOT_INIT; +} + +static const struct bpf_verifier_ops bpf_dummy_verifier_ops = { + .is_valid_access = bpf_dummy_ops_is_valid_access, + .btf_struct_access = bpf_dummy_ops_btf_struct_access, +}; + +static int bpf_dummy_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + return -EOPNOTSUPP; +} + +static int bpf_dummy_reg(void *kdata) +{ + return -EOPNOTSUPP; +} + +static void bpf_dummy_unreg(void *kdata) +{ +} + +struct bpf_struct_ops bpf_bpf_dummy_ops = { + .verifier_ops = &bpf_dummy_verifier_ops, + .init = bpf_dummy_init, + .init_member = bpf_dummy_init_member, + .reg = bpf_dummy_reg, + .unreg = bpf_dummy_unreg, + .name = "bpf_dummy_ops", +}; -- cgit v1.2.3 From 8845b4681bf44b9d2d2badf2c67cf476e42a86bd Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Fri, 29 Oct 2021 15:49:08 -0700 Subject: bpf: Add alignment padding for "map_extra" + consolidate holes This patch makes 2 changes regarding alignment padding for the "map_extra" field. 1) In the kernel header, "map_extra" and "btf_value_type_id" are rearranged to consolidate the hole. Before: struct bpf_map { ... u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ /* XXX 4 bytes hole, try to pack */ u64 map_extra; /* 48 8 */ int spin_lock_off; /* 56 4 */ int timer_off; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 id; /* 64 4 */ int numa_node; /* 68 4 */ ... bool frozen; /* 117 1 */ /* XXX 10 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 2, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 10 */ } __attribute__((__aligned__(64))); After: struct bpf_map { ... u32 max_entries; /* 36 4 */ u64 map_extra; /* 40 8 */ u32 map_flags; /* 48 4 */ int spin_lock_off; /* 52 4 */ int timer_off; /* 56 4 */ u32 id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ int numa_node; /* 64 4 */ ... bool frozen /* 113 1 */ /* XXX 14 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 1, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 14 */ } __attribute__((__aligned__(64))); 2) Add alignment padding to the bpf_map_info struct More details can be found in commit 36f9814a494a ("bpf: fix uapi hole for 32 bit compat applications") Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211029224909.1721024-3-joannekoong@fb.com --- include/linux/bpf.h | 6 +++--- include/uapi/linux/bpf.h | 1 + tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c098089c1b54..f6743d4bb531 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,23 +168,23 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; - u32 map_flags; u64 map_extra; /* any per-map-type extra fields */ + u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; + u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; - u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 22 bytes hole */ + /* 14 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3 From e66435936756d9bce96433be183358a8994a0f0d Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Mon, 1 Nov 2021 14:56:37 -0700 Subject: mm: fix mismerge of folio page flag manipulators I had missed a semantic conflict between commit d389a4a81155 ("mm: Add folio flag manipulation functions") from the folio tree, and commit eac96c3efdb5 ("mm: filemap: check if THP has hwpoisoned subpage for PMD page fault") that added a new set of page flags. My build tests had too many options enabled, which hid this issue. But if you didn't have MEMORY_FAILURE or TRANSPARENT_HUGEPAGE enabled, you'd end up with build errors like this: include/linux/page-flags.h:806:29: error: macro "PAGEFLAG_FALSE" requires 2 arguments, but only 1 given 806 | PAGEFLAG_FALSE(HasHWPoisoned) | ^ due to the missing lowercase name used for folio function naming. Fixes: 49f8275c7d92 ("Merge tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache") Reported-by: Naresh Kamboju Reported-by: Yang Shi Cc: Matthew Wilcox Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index d8623d6e1141..981341a3c3c4 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -803,8 +803,8 @@ PAGEFLAG_FALSE(DoubleMap, double_map) PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND) #else -PAGEFLAG_FALSE(HasHWPoisoned) - TESTSCFLAG_FALSE(HasHWPoisoned) +PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) + TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned) #endif /* -- cgit v1.2.3 From f1a456f8f3fc5828d8abcad941860380ae147b1d Mon Sep 17 00:00:00 2001 From: Talal Ahmad Date: Fri, 29 Oct 2021 22:05:42 -0400 Subject: net: avoid double accounting for pure zerocopy skbs Track skbs with only zerocopy data and avoid charging them to kernel memory to correctly account the memory utilization for msg_zerocopy. All of the data in such skbs is held in user pages which are already accounted to user. Before this change, they are charged again in kernel in __zerocopy_sg_from_iter. The charging in kernel is excessive because data is not being copied into skb frags. This excessive charging can lead to kernel going into memory pressure state which impacts all sockets in the system adversely. Mark pure zerocopy skbs with a SKBFL_PURE_ZEROCOPY flag and remove charge/uncharge for data in such skbs. Initially, an skb is marked pure zerocopy when it is empty and in zerocopy path. skb can then change from a pure zerocopy skb to mixed data skb (zerocopy and copy data) if it is at tail of write queue and there is room available in it and non-zerocopy data is being sent in the next sendmsg call. At this time sk_mem_charge is done for the pure zerocopied data and the pure zerocopy flag is unmarked. We found that this happens very rarely on workloads that pass MSG_ZEROCOPY. A pure zerocopy skb can later be coalesced into normal skb if they are next to each other in queue but this patch prevents coalescing from happening. This avoids complexity of charging when skb downgrades from pure zerocopy to mixed. This is also rare. In sk_wmem_free_skb, if it is a pure zerocopy skb, an sk_mem_uncharge for SKB_TRUESIZE(MAX_TCP_HEADER) is done for sk_mem_charge in tcp_skb_entail for an skb without data. Testing with the msg_zerocopy.c benchmark between two hosts(100G nics) with zerocopy showed that before this patch the 'sock' variable in memory.stat for cgroup2 that tracks sum of sk_forward_alloc, sk_rmem_alloc and sk_wmem_queued is around 1822720 and with this change it is 0. This is due to no charge to sk_forward_alloc for zerocopy data and shows memory utilization for kernel is lowered. Signed-off-by: Talal Ahmad Acked-by: Arjun Roy Acked-by: Soheil Hassas Yeganeh Signed-off-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 19 ++++++++++++++++++- include/net/tcp.h | 8 ++++++-- net/core/datagram.c | 3 ++- net/core/skbuff.c | 3 ++- net/ipv4/tcp.c | 22 ++++++++++++++++++++-- net/ipv4/tcp_output.c | 7 +++++-- 6 files changed, 53 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0bd6520329f6..10869906cc57 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -454,9 +454,15 @@ enum { * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), + + /* segment contains only zerocopy data and should not be + * charged to the kernel memory. + */ + SKBFL_PURE_ZEROCOPY = BIT(2), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1464,6 +1470,17 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } +static inline bool skb_zcopy_pure(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; +} + +static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ + return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); +} + static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); @@ -1528,7 +1545,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } diff --git a/include/net/tcp.h b/include/net/tcp.h index 70972f3ac8fa..af91f370432e 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -293,7 +293,10 @@ static inline bool tcp_out_of_memory(struct sock *sk) static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); - sk_mem_uncharge(sk, skb->truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, skb->truesize); + else + sk_mem_uncharge(sk, SKB_TRUESIZE(MAX_TCP_HEADER)); __kfree_skb(skb); } @@ -974,7 +977,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && - mptcp_skb_can_collapse(to, from)); + mptcp_skb_can_collapse(to, from) && + skb_pure_zcopy_same(to, from)); } /* Events passed to congestion control interface */ diff --git a/net/core/datagram.c b/net/core/datagram.c index 15ab9ffb27fe..ee290776c661 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -646,7 +646,8 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { sk_wmem_queued_add(sk, truesize); - sk_mem_charge(sk, truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 67a9188d8a49..29e617d8d7fb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3433,8 +3433,9 @@ static inline void skb_split_no_header(struct sk_buff *skb, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; - skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bc7f419184aa..2561c14a6e63 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -863,6 +863,7 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, if (likely(skb)) { bool mem_scheduled; + skb->truesize = SKB_TRUESIZE(size + MAX_TCP_HEADER); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); @@ -1319,6 +1320,15 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); + /* skb changing from pure zc to mixed, must charge zc */ + if (unlikely(skb_zcopy_pure(skb))) { + if (!sk_wmem_schedule(sk, skb->data_len)) + goto wait_for_space; + + sk_mem_charge(sk, skb->data_len); + skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; + } + if (!sk_wmem_schedule(sk, copy)) goto wait_for_space; @@ -1339,8 +1349,16 @@ new_segment: } pfrag->offset += copy; } else { - if (!sk_wmem_schedule(sk, copy)) - goto wait_for_space; + /* First append to a fragless skb builds initial + * pure zerocopy skb + */ + if (!skb->len) + skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; + + if (!skb_zcopy_pure(skb)) { + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; + } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6fbbf1558033..287b57aadc37 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1677,7 +1677,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); - sk_mem_uncharge(sk, delta_truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, delta_truesize); } /* Any change of skb->len requires recalculation of tso factor. */ @@ -2295,7 +2296,9 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) + if (unlikely(TCP_SKB_CB(skb)->eor) || + tcp_has_tx_tstamp(skb) || + !skb_pure_zcopy_same(skb, next)) return false; len -= skb->len; -- cgit v1.2.3 From fcdb44d08a95003c3d040aecdee286156ec6f34e Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 1 Nov 2021 10:36:28 -0700 Subject: net: arp: introduce arp_evict_nocarrier sysctl parameter This change introduces a new sysctl parameter, arp_evict_nocarrier. When set (default) the ARP cache will be cleared on a NOCARRIER event. This new option has been defaulted to '1' which maintains existing behavior. Clearing the ARP cache on NOCARRIER is relatively new, introduced by: commit 859bd2ef1fc1110a8031b967ee656c53a6260a76 Author: David Ahern Date: Thu Oct 11 20:33:49 2018 -0700 net: Evict neighbor entries on carrier down The reason for this changes is to prevent the ARP cache from being cleared when a wireless device roams. Specifically for wireless roams the ARP cache should not be cleared because the underlying network has not changed. Clearing the ARP cache in this case can introduce significant delays sending out packets after a roam. A user reported such a situation here: https://lore.kernel.org/linux-wireless/CACsRnHWa47zpx3D1oDq9JYnZWniS8yBwW1h0WAVZ6vrbwL_S0w@mail.gmail.com/ After some investigation it was found that the kernel was holding onto packets until ARP finished which resulted in this 1 second delay. It was also found that the first ARP who-has was never responded to, which is actually what caues the delay. This change is more or less working around this behavior, but again, there is no reason to clear the cache on a roam anyways. As for the unanswered who-has, we know the packet made it OTA since it was seen while monitoring. Why it never received a response is unknown. In any case, since this is a problem on the AP side of things all that can be done is to work around it until it is solved. Some background on testing/reproducing the packet delay: Hardware: - 2 access points configured for Fast BSS Transition (Though I don't see why regular reassociation wouldn't have the same behavior) - Wireless station running IWD as supplicant - A device on network able to respond to pings (I used one of the APs) Procedure: - Connect to first AP - Ping once to establish an ARP entry - Start a tcpdump - Roam to second AP - Wait for operstate UP event, and note the timestamp - Start pinging Results: Below is the tcpdump after UP. It was recorded the interface went UP at 10:42:01.432875. 10:42:01.461871 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.497976 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.507162 ARP, Reply 192.168.254.1 is-at ac:86:74:55:b0:20, length 46 10:42:02.507185 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 1, length 64 10:42:02.507205 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 2, length 64 10:42:02.507212 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 3, length 64 10:42:02.507219 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 4, length 64 10:42:02.507225 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 5, length 64 10:42:02.507232 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 6, length 64 10:42:02.515373 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 1, length 64 10:42:02.521399 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 2, length 64 10:42:02.521612 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 3, length 64 10:42:02.521941 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 4, length 64 10:42:02.522419 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 5, length 64 10:42:02.523085 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 6, length 64 You can see the first ARP who-has went out very quickly after UP, but was never responded to. Nearly a second later the kernel retries and gets a response. Only then do the ping packets go out. If an ARP entry is manually added prior to UP (after the cache is cleared) it is seen that the first ping is never responded to, so its not only an issue with ARP but with data packets in general. As mentioned prior, the wireless interface was also monitored to verify the ping/ARP packet made it OTA which was observed to be true. Signed-off-by: James Prestwood Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 9 +++++++++ include/linux/inetdevice.h | 2 ++ include/uapi/linux/ip.h | 1 + include/uapi/linux/sysctl.h | 1 + net/ipv4/arp.c | 11 ++++++++++- net/ipv4/devinet.c | 4 ++++ 6 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 16b8bf72feaf..18fde4ed7a5e 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1611,6 +1611,15 @@ arp_accept - BOOLEAN gratuitous arp frame, the arp table will be updated regardless if this setting is on or off. +arp_evict_nocarrier - BOOLEAN + Clears the ARP cache on NOCARRIER events. This option is important for + wireless devices where the ARP cache should not be cleared when roaming + between access points on the same network. In most cases this should + remain as the default (1). + + - 1 - (default): Clear the ARP cache on NOCARRIER events + - 0 - Do not clear ARP cache on NOCARRIER events + mcast_solicit - INTEGER The maximum number of multicast probes in INCOMPLETE state, when the associated hardware address is unknown. Defaults diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a038feb63f23..518b484a7f07 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -133,6 +133,8 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) +#define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ + ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index e42d13b55cf3..e00bbb9c47bb 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -169,6 +169,7 @@ enum IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, IPV4_DEVCONF_DROP_GRATUITOUS_ARP, IPV4_DEVCONF_BC_FORWARDING, + IPV4_DEVCONF_ARP_EVICT_NOCARRIER, __IPV4_DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 1e05d3caa712..6a3b194c50fe 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -482,6 +482,7 @@ enum NET_IPV4_CONF_PROMOTE_SECONDARIES=20, NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, + NET_IPV4_CONF_ARP_EVICT_NOCARRIER=23, }; /* /proc/sys/net/ipv4/netfilter */ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 922dd73e5740..857a144b1ea9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1247,6 +1247,8 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; + struct in_device *in_dev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: @@ -1257,7 +1259,14 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&arp_tbl, dev); - if (!netif_carrier_ok(dev)) + + in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + evict_nocarrier = true; + else + evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev); + + if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&arp_tbl, dev); break; default: diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f4468980b675..ec73a0d52d3e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -75,6 +75,7 @@ static struct ipv4_devconf ipv4_devconf = { [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -87,6 +88,7 @@ static struct ipv4_devconf ipv4_devconf_dflt = { [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -2532,6 +2534,8 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), + DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, + "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), -- cgit v1.2.3 From 18ac597af25e9760b76471524096f5b29eb820e6 Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 1 Nov 2021 10:36:29 -0700 Subject: net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter In most situations the neighbor discovery cache should be cleared on a NOCARRIER event which is currently done unconditionally. But for wireless roams the neighbor discovery cache can and should remain intact since the underlying network has not changed. This patch introduces a sysctl option ndisc_evict_nocarrier which can be disabled by a wireless supplicant during a roam. This allows packets to be sent after a roam immediately without having to wait for neighbor discovery. A user reported roughly a 1 second delay after a roam before packets could be sent out (note, on IPv4). This delay was due to the ARP cache being cleared. During testing of this same scenario using IPv6 no delay was noticed, but regardless there is no reason to clear the ndisc cache for wireless roams. Signed-off-by: James Prestwood Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 9 +++++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 12 ++++++++++++ net/ipv6/ndisc.c | 12 +++++++++++- 5 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 18fde4ed7a5e..c61cc0219f4c 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2350,6 +2350,15 @@ ndisc_tclass - INTEGER * 0 - (default) +ndisc_evict_nocarrier - BOOLEAN + Clears the neighbor discovery table on NOCARRIER events. This option is + important for wireless devices where the neighbor discovery cache should + not be cleared when roaming between access points on the same network. + In most cases this should remain as the default (1). + + - 1 - (default): Clear neighbor discover cache on NOCARRIER events. + - 0 - Do not clear neighbor discovery cache on NOCARRIER events. + mldv1_unsolicited_report_interval - INTEGER The interval in milliseconds in which the next unsolicited MLDv1 report retransmit will take place. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c383630d3f06..20c1f968da7c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -79,6 +79,7 @@ struct ipv6_devconf { __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; + __u8 ndisc_evict_nocarrier; struct ctl_table_header *sysctl_header; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index b243a53fa985..d4178dace0bf 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -193,6 +193,7 @@ enum { DEVCONF_IOAM6_ENABLED, DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, + DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9e1463a2acae..3445f8017430 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -241,6 +241,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, + .ndisc_evict_nocarrier = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -300,6 +301,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, + .ndisc_evict_nocarrier = 1, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -5545,6 +5547,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; + array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; } static inline size_t inet6_ifla6_size(void) @@ -6986,6 +6989,15 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_douintvec, }, + { + .procname = "ndisc_evict_nocarrier", + .data = &ipv6_devconf.ndisc_evict_nocarrier, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)SYSCTL_ONE, + }, { /* sentinel */ } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 184190b9ea25..f03b597e4121 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1794,6 +1794,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: @@ -1810,10 +1811,19 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, in6_dev_put(idev); break; case NETDEV_CHANGE: + idev = in6_dev_get(dev); + if (!idev) + evict_nocarrier = true; + else { + evict_nocarrier = idev->cnf.ndisc_evict_nocarrier && + net->ipv6.devconf_all->ndisc_evict_nocarrier; + in6_dev_put(idev); + } + change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); - if (!netif_carrier_ok(dev)) + if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: -- cgit v1.2.3 From 4a08e3271c55f8b5d56906a8aa5bd041911cf897 Mon Sep 17 00:00:00 2001 From: "Hector.Yuan" Date: Mon, 4 Oct 2021 22:42:33 +0800 Subject: cpufreq: Fix parameter in parse_perf_domain() Pass cpu to parse_perf_domain() instead of pcpu. Fixes: 8486a32dd484 ("cpufreq: Add of_perf_domain_get_sharing_cpumask") Signed-off-by: Hector.Yuan [ Viresh: Massaged changelog ] Signed-off-by: Viresh Kumar --- include/linux/cpufreq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ff88bb3e44fc..66a1f495f01a 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1041,7 +1041,7 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_ if (cpu == pcpu) continue; - ret = parse_perf_domain(pcpu, list_name, cell_name); + ret = parse_perf_domain(cpu, list_name, cell_name); if (ret < 0) continue; -- cgit v1.2.3 From 84882cf72cd774cf16fd338bdbf00f69ac9f9194 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 1 Nov 2021 22:26:08 -0700 Subject: Revert "net: avoid double accounting for pure zerocopy skbs" This reverts commit f1a456f8f3fc5828d8abcad941860380ae147b1d. WARNING: CPU: 1 PID: 6819 at net/core/skbuff.c:5429 skb_try_coalesce+0x78b/0x7e0 CPU: 1 PID: 6819 Comm: xxxxxxx Kdump: loaded Tainted: G S 5.15.0-04194-gd852503f7711 #16 RIP: 0010:skb_try_coalesce+0x78b/0x7e0 Code: e8 2a bf 41 ff 44 8b b3 bc 00 00 00 48 8b 7c 24 30 e8 19 c0 41 ff 44 89 f0 48 03 83 c0 00 00 00 48 89 44 24 40 e9 47 fb ff ff <0f> 0b e9 ca fc ff ff 4c 8d 70 ff 48 83 c0 07 48 89 44 24 38 e9 61 RSP: 0018:ffff88881f449688 EFLAGS: 00010282 RAX: 00000000fffffe96 RBX: ffff8881566e4460 RCX: ffffffff82079f7e RDX: 0000000000000003 RSI: dffffc0000000000 RDI: ffff8881566e47b0 RBP: ffff8881566e46e0 R08: ffffed102619235d R09: ffffed102619235d R10: ffff888130c91ae3 R11: ffffed102619235c R12: ffff88881f4498a0 R13: 0000000000000056 R14: 0000000000000009 R15: ffff888130c91ac0 FS: 00007fec2cbb9700(0000) GS:ffff88881f440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fec1b060d80 CR3: 00000003acf94005 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_try_coalesce+0xeb/0x290 ? tcp_parse_options+0x610/0x610 ? mark_held_locks+0x79/0xa0 tcp_queue_rcv+0x69/0x2f0 tcp_rcv_established+0xa49/0xd40 ? tcp_data_queue+0x18a0/0x18a0 tcp_v6_do_rcv+0x1c9/0x880 ? rt6_mtu_change_route+0x100/0x100 tcp_v6_rcv+0x1624/0x1830 Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 19 +------------------ include/net/tcp.h | 8 ++------ net/core/datagram.c | 3 +-- net/core/skbuff.c | 3 +-- net/ipv4/tcp.c | 22 ++-------------------- net/ipv4/tcp_output.c | 7 ++----- 6 files changed, 9 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 10869906cc57..0bd6520329f6 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -454,15 +454,9 @@ enum { * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), - - /* segment contains only zerocopy data and should not be - * charged to the kernel memory. - */ - SKBFL_PURE_ZEROCOPY = BIT(2), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) -#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1470,17 +1464,6 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } -static inline bool skb_zcopy_pure(const struct sk_buff *skb) -{ - return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; -} - -static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, - const struct sk_buff *skb2) -{ - return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); -} - static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); @@ -1545,7 +1528,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; + skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; } } diff --git a/include/net/tcp.h b/include/net/tcp.h index af91f370432e..70972f3ac8fa 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -293,10 +293,7 @@ static inline bool tcp_out_of_memory(struct sock *sk) static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); - if (!skb_zcopy_pure(skb)) - sk_mem_uncharge(sk, skb->truesize); - else - sk_mem_uncharge(sk, SKB_TRUESIZE(MAX_TCP_HEADER)); + sk_mem_uncharge(sk, skb->truesize); __kfree_skb(skb); } @@ -977,8 +974,7 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && - mptcp_skb_can_collapse(to, from) && - skb_pure_zcopy_same(to, from)); + mptcp_skb_can_collapse(to, from)); } /* Events passed to congestion control interface */ diff --git a/net/core/datagram.c b/net/core/datagram.c index ee290776c661..15ab9ffb27fe 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -646,8 +646,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { sk_wmem_queued_add(sk, truesize); - if (!skb_zcopy_pure(skb)) - sk_mem_charge(sk, truesize); + sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 29e617d8d7fb..67a9188d8a49 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3433,9 +3433,8 @@ static inline void skb_split_no_header(struct sk_buff *skb, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); - const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; - skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2561c14a6e63..bc7f419184aa 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -863,7 +863,6 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, if (likely(skb)) { bool mem_scheduled; - skb->truesize = SKB_TRUESIZE(size + MAX_TCP_HEADER); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); @@ -1320,15 +1319,6 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); - /* skb changing from pure zc to mixed, must charge zc */ - if (unlikely(skb_zcopy_pure(skb))) { - if (!sk_wmem_schedule(sk, skb->data_len)) - goto wait_for_space; - - sk_mem_charge(sk, skb->data_len); - skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; - } - if (!sk_wmem_schedule(sk, copy)) goto wait_for_space; @@ -1349,16 +1339,8 @@ new_segment: } pfrag->offset += copy; } else { - /* First append to a fragless skb builds initial - * pure zerocopy skb - */ - if (!skb->len) - skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; - - if (!skb_zcopy_pure(skb)) { - if (!sk_wmem_schedule(sk, copy)) - goto wait_for_space; - } + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 287b57aadc37..6fbbf1558033 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1677,8 +1677,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); - if (!skb_zcopy_pure(skb)) - sk_mem_uncharge(sk, delta_truesize); + sk_mem_uncharge(sk, delta_truesize); } /* Any change of skb->len requires recalculation of tso factor. */ @@ -2296,9 +2295,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor) || - tcp_has_tx_tstamp(skb) || - !skb_pure_zcopy_same(skb, next)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; -- cgit v1.2.3 From ca7752caeaa70bd31d1714af566c9809688544af Mon Sep 17 00:00:00 2001 From: Michael Pratt Date: Mon, 1 Nov 2021 17:06:15 -0400 Subject: posix-cpu-timers: Clear task::posix_cputimers_work in copy_process() copy_process currently copies task_struct.posix_cputimers_work as-is. If a timer interrupt arrives while handling clone and before dup_task_struct completes then the child task will have: 1. posix_cputimers_work.scheduled = true 2. posix_cputimers_work.work queued. copy_process clears task_struct.task_works, so (2) will have no effect and posix_cpu_timers_work will never run (not to mention it doesn't make sense for two tasks to share a common linked list). Since posix_cpu_timers_work never runs, posix_cputimers_work.scheduled is never cleared. Since scheduled is set, future timer interrupts will skip scheduling work, with the ultimate result that the task will never receive timer expirations. Together, the complete flow is: 1. Task 1 calls clone(), enters kernel. 2. Timer interrupt fires, schedules task work on Task 1. 2a. task_struct.posix_cputimers_work.scheduled = true 2b. task_struct.posix_cputimers_work.work added to task_struct.task_works. 3. dup_task_struct() copies Task 1 to Task 2. 4. copy_process() clears task_struct.task_works for Task 2. 5. Future timer interrupts on Task 2 see task_struct.posix_cputimers_work.scheduled = true and skip scheduling work. Fix this by explicitly clearing contents of task_struct.posix_cputimers_work in copy_process(). This was never meant to be shared or inherited across tasks in the first place. Fixes: 1fb497dd0030 ("posix-cpu-timers: Provide mechanisms to defer timer handling to task_work") Reported-by: Rhys Hiltner Signed-off-by: Michael Pratt Signed-off-by: Thomas Gleixner Cc: Link: https://lore.kernel.org/r/20211101210615.716522-1-mpratt@google.com --- include/linux/posix-timers.h | 2 ++ kernel/fork.c | 1 + kernel/time/posix-cpu-timers.c | 19 +++++++++++++++++-- 3 files changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index 00fef0064355..5bbcd280bfd2 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -184,8 +184,10 @@ static inline void posix_cputimers_group_init(struct posix_cputimers *pct, #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK +void clear_posix_cputimers_work(struct task_struct *p); void posix_cputimers_init_work(void); #else +static inline void clear_posix_cputimers_work(struct task_struct *p) { } static inline void posix_cputimers_init_work(void) { } #endif diff --git a/kernel/fork.c b/kernel/fork.c index 8e9feeef555e..8269ae2e5d7c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2279,6 +2279,7 @@ static __latent_entropy struct task_struct *copy_process( p->pdeath_signal = 0; INIT_LIST_HEAD(&p->thread_group); p->task_works = NULL; + clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 643d412ac623..96b4e7810426 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -1158,14 +1158,29 @@ static void posix_cpu_timers_work(struct callback_head *work) handle_posix_cpu_timers(current); } +/* + * Clear existing posix CPU timers task work. + */ +void clear_posix_cputimers_work(struct task_struct *p) +{ + /* + * A copied work entry from the old task is not meaningful, clear it. + * N.B. init_task_work will not do this. + */ + memset(&p->posix_cputimers_work.work, 0, + sizeof(p->posix_cputimers_work.work)); + init_task_work(&p->posix_cputimers_work.work, + posix_cpu_timers_work); + p->posix_cputimers_work.scheduled = false; +} + /* * Initialize posix CPU timers task work in init task. Out of line to * keep the callback static and to avoid header recursion hell. */ void __init posix_cputimers_init_work(void) { - init_task_work(¤t->posix_cputimers_work.work, - posix_cpu_timers_work); + clear_posix_cputimers_work(current); } /* -- cgit v1.2.3 From 8791545eda52e8f3bc48e3cd902e38bf4ba4c9de Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Fri, 22 Oct 2021 16:17:03 -0400 Subject: NFS: Move NFS protocol display macros to global header Refactor: surface useful show_ macros so they can be shared between the client and server trace code. Additional clean up: - Housekeeping: ensure the correct #include files are pulled in and add proper TRACE_DEFINE_ENUM where they are missing - Use a consistent naming scheme for the helpers - Store values to be displayed symbolically as unsigned long, as that is the type that the __print_yada() functions take Signed-off-by: Chuck Lever Signed-off-by: Trond Myklebust --- fs/nfs/nfs4trace.h | 403 ++++----------------------------------------- fs/nfs/nfstrace.h | 117 +++---------- fs/nfs/pnfs.h | 4 - fs/nfsd/trace.h | 1 + include/linux/nfs4.h | 4 + include/trace/events/nfs.h | 375 +++++++++++++++++++++++++++++++++++++++++ 6 files changed, 433 insertions(+), 471 deletions(-) create mode 100644 include/trace/events/nfs.h (limited to 'include/linux') diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index 424d9cd4c196..18f149f72160 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -12,309 +12,7 @@ #include #include - -TRACE_DEFINE_ENUM(EPERM); -TRACE_DEFINE_ENUM(ENOENT); -TRACE_DEFINE_ENUM(EIO); -TRACE_DEFINE_ENUM(ENXIO); -TRACE_DEFINE_ENUM(EACCES); -TRACE_DEFINE_ENUM(EEXIST); -TRACE_DEFINE_ENUM(EXDEV); -TRACE_DEFINE_ENUM(ENOTDIR); -TRACE_DEFINE_ENUM(EISDIR); -TRACE_DEFINE_ENUM(EFBIG); -TRACE_DEFINE_ENUM(ENOSPC); -TRACE_DEFINE_ENUM(EROFS); -TRACE_DEFINE_ENUM(EMLINK); -TRACE_DEFINE_ENUM(ENAMETOOLONG); -TRACE_DEFINE_ENUM(ENOTEMPTY); -TRACE_DEFINE_ENUM(EDQUOT); -TRACE_DEFINE_ENUM(ESTALE); -TRACE_DEFINE_ENUM(EBADHANDLE); -TRACE_DEFINE_ENUM(EBADCOOKIE); -TRACE_DEFINE_ENUM(ENOTSUPP); -TRACE_DEFINE_ENUM(ETOOSMALL); -TRACE_DEFINE_ENUM(EREMOTEIO); -TRACE_DEFINE_ENUM(EBADTYPE); -TRACE_DEFINE_ENUM(EAGAIN); -TRACE_DEFINE_ENUM(ELOOP); -TRACE_DEFINE_ENUM(EOPNOTSUPP); -TRACE_DEFINE_ENUM(EDEADLK); -TRACE_DEFINE_ENUM(ENOMEM); -TRACE_DEFINE_ENUM(EKEYEXPIRED); -TRACE_DEFINE_ENUM(ETIMEDOUT); -TRACE_DEFINE_ENUM(ERESTARTSYS); -TRACE_DEFINE_ENUM(ECONNREFUSED); -TRACE_DEFINE_ENUM(ECONNRESET); -TRACE_DEFINE_ENUM(ENETUNREACH); -TRACE_DEFINE_ENUM(EHOSTUNREACH); -TRACE_DEFINE_ENUM(EHOSTDOWN); -TRACE_DEFINE_ENUM(EPIPE); -TRACE_DEFINE_ENUM(EPFNOSUPPORT); -TRACE_DEFINE_ENUM(EPROTONOSUPPORT); - -TRACE_DEFINE_ENUM(NFS4_OK); -TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); -TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); -TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); -TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); -TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); -TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); -TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); -TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); -TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); -TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); -TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); -TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); -TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); -TRACE_DEFINE_ENUM(NFS4ERR_DELAY); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); -TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); -TRACE_DEFINE_ENUM(NFS4ERR_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); -TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); -TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_EXIST); -TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FBIG); -TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); -TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); -TRACE_DEFINE_ENUM(NFS4ERR_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_INVAL); -TRACE_DEFINE_ENUM(NFS4ERR_IO); -TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); -TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); -TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); -TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); -TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); -TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); -TRACE_DEFINE_ENUM(NFS4ERR_MLINK); -TRACE_DEFINE_ENUM(NFS4ERR_MOVED); -TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFS4ERR_NOENT); -TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); -TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); -TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); -TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); -TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); -TRACE_DEFINE_ENUM(NFS4ERR_NXIO); -TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); -TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); -TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); -TRACE_DEFINE_ENUM(NFS4ERR_PERM); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); -TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); -TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); -TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); -TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); -TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); -TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); -TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); -TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); -TRACE_DEFINE_ENUM(NFS4ERR_ROFS); -TRACE_DEFINE_ENUM(NFS4ERR_SAME); -TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); -TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); -TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); -TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFS4ERR_STALE); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); -TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); -TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); -TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); -TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); -TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); -TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); -TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); -TRACE_DEFINE_ENUM(NFS4ERR_XDEV); - -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); -TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); - -#define show_nfsv4_errors(error) \ - __print_symbolic(error, \ - { NFS4_OK, "OK" }, \ - /* Mapped by nfs4_stat_to_errno() */ \ - { EPERM, "EPERM" }, \ - { ENOENT, "ENOENT" }, \ - { EIO, "EIO" }, \ - { ENXIO, "ENXIO" }, \ - { EACCES, "EACCES" }, \ - { EEXIST, "EEXIST" }, \ - { EXDEV, "EXDEV" }, \ - { ENOTDIR, "ENOTDIR" }, \ - { EISDIR, "EISDIR" }, \ - { EFBIG, "EFBIG" }, \ - { ENOSPC, "ENOSPC" }, \ - { EROFS, "EROFS" }, \ - { EMLINK, "EMLINK" }, \ - { ENAMETOOLONG, "ENAMETOOLONG" }, \ - { ENOTEMPTY, "ENOTEMPTY" }, \ - { EDQUOT, "EDQUOT" }, \ - { ESTALE, "ESTALE" }, \ - { EBADHANDLE, "EBADHANDLE" }, \ - { EBADCOOKIE, "EBADCOOKIE" }, \ - { ENOTSUPP, "ENOTSUPP" }, \ - { ETOOSMALL, "ETOOSMALL" }, \ - { EREMOTEIO, "EREMOTEIO" }, \ - { EBADTYPE, "EBADTYPE" }, \ - { EAGAIN, "EAGAIN" }, \ - { ELOOP, "ELOOP" }, \ - { EOPNOTSUPP, "EOPNOTSUPP" }, \ - { EDEADLK, "EDEADLK" }, \ - /* RPC errors */ \ - { ENOMEM, "ENOMEM" }, \ - { EKEYEXPIRED, "EKEYEXPIRED" }, \ - { ETIMEDOUT, "ETIMEDOUT" }, \ - { ERESTARTSYS, "ERESTARTSYS" }, \ - { ECONNREFUSED, "ECONNREFUSED" }, \ - { ECONNRESET, "ECONNRESET" }, \ - { ENETUNREACH, "ENETUNREACH" }, \ - { EHOSTUNREACH, "EHOSTUNREACH" }, \ - { EHOSTDOWN, "EHOSTDOWN" }, \ - { EPIPE, "EPIPE" }, \ - { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ - { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ - /* NFSv4 native errors */ \ - { NFS4ERR_ACCESS, "ACCESS" }, \ - { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ - { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ - { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ - { NFS4ERR_BADCHAR, "BADCHAR" }, \ - { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ - { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ - { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ - { NFS4ERR_BADLABEL, "BADLABEL" }, \ - { NFS4ERR_BADNAME, "BADNAME" }, \ - { NFS4ERR_BADOWNER, "BADOWNER" }, \ - { NFS4ERR_BADSESSION, "BADSESSION" }, \ - { NFS4ERR_BADSLOT, "BADSLOT" }, \ - { NFS4ERR_BADTYPE, "BADTYPE" }, \ - { NFS4ERR_BADXDR, "BADXDR" }, \ - { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ - { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ - { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ - { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ - { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ - { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ - { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ - { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ - { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ - { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, \ - "CONN_NOT_BOUND_TO_SESSION" }, \ - { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ - { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ - { NFS4ERR_DELAY, "DELAY" }, \ - { NFS4ERR_DELEG_ALREADY_WANTED, \ - "DELEG_ALREADY_WANTED" }, \ - { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ - { NFS4ERR_DENIED, "DENIED" }, \ - { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ - { NFS4ERR_DQUOT, "DQUOT" }, \ - { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ - { NFS4ERR_EXIST, "EXIST" }, \ - { NFS4ERR_EXPIRED, "EXPIRED" }, \ - { NFS4ERR_FBIG, "FBIG" }, \ - { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ - { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ - { NFS4ERR_GRACE, "GRACE" }, \ - { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ - { NFS4ERR_INVAL, "INVAL" }, \ - { NFS4ERR_IO, "IO" }, \ - { NFS4ERR_ISDIR, "ISDIR" }, \ - { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ - { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ - { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ - { NFS4ERR_LOCKED, "LOCKED" }, \ - { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ - { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ - { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ - { NFS4ERR_MLINK, "MLINK" }, \ - { NFS4ERR_MOVED, "MOVED" }, \ - { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFS4ERR_NOENT, "NOENT" }, \ - { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ - { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ - { NFS4ERR_NOSPC, "NOSPC" }, \ - { NFS4ERR_NOTDIR, "NOTDIR" }, \ - { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ - { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ - { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ - { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ - { NFS4ERR_NXIO, "NXIO" }, \ - { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ - { NFS4ERR_OPENMODE, "OPENMODE" }, \ - { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ - { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ - { NFS4ERR_PERM, "PERM" }, \ - { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ - { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ - { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ - { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ - { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ - { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ - { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ - { NFS4ERR_REP_TOO_BIG_TO_CACHE, \ - "REP_TOO_BIG_TO_CACHE" }, \ - { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ - { NFS4ERR_RESOURCE, "RESOURCE" }, \ - { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ - { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ - { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ - { NFS4ERR_ROFS, "ROFS" }, \ - { NFS4ERR_SAME, "SAME" }, \ - { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ - { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ - { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ - { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ - { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ - { NFS4ERR_STALE, "STALE" }, \ - { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ - { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ - { NFS4ERR_SYMLINK, "SYMLINK" }, \ - { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ - { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ - { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ - { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ - { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ - { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ - { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ - { NFS4ERR_XDEV, "XDEV" }, \ - /* ***** Internal to Linux NFS client ***** */ \ - { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ - { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) +#include #define show_nfs_fattr_flags(valid) \ __print_flags((unsigned long)valid, "|", \ @@ -355,7 +53,7 @@ DECLARE_EVENT_CLASS(nfs4_clientid_event, TP_printk( "error=%ld (%s) dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __get_str(dstaddr) ) ); @@ -379,29 +77,6 @@ DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session); DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence); DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete); -#define show_nfs4_sequence_status_flags(status) \ - __print_flags((unsigned long)status, "|", \ - { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, \ - "CB_GSS_CONTEXTS_EXPIRING" }, \ - { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, \ - "CB_GSS_CONTEXTS_EXPIRED" }, \ - { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, \ - "EXPIRED_ALL_STATE_REVOKED" }, \ - { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, \ - "EXPIRED_SOME_STATE_REVOKED" }, \ - { SEQ4_STATUS_ADMIN_STATE_REVOKED, \ - "ADMIN_STATE_REVOKED" }, \ - { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, \ - "RECALLABLE_STATE_REVOKED" }, \ - { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ - { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, \ - "RESTART_RECLAIM_NEEDED" }, \ - { SEQ4_STATUS_CB_PATH_DOWN_SESSION, \ - "CB_PATH_DOWN_SESSION" }, \ - { SEQ4_STATUS_BACKCHANNEL_FAULT, \ - "BACKCHANNEL_FAULT" }) - TRACE_EVENT(nfs4_sequence_done, TP_PROTO( const struct nfs4_session *session, @@ -415,7 +90,7 @@ TRACE_EVENT(nfs4_sequence_done, __field(unsigned int, seq_nr) __field(unsigned int, highest_slotid) __field(unsigned int, target_highest_slotid) - __field(unsigned int, status_flags) + __field(unsigned long, status_flags) __field(unsigned long, error) ), @@ -434,16 +109,16 @@ TRACE_EVENT(nfs4_sequence_done, TP_printk( "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u target_highest_slotid=%u " - "status_flags=%u (%s)", + "status_flags=0x%lx (%s)", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, __entry->highest_slotid, __entry->target_highest_slotid, __entry->status_flags, - show_nfs4_sequence_status_flags(__entry->status_flags) + show_nfs4_seq4_status(__entry->status_flags) ) ); @@ -480,7 +155,7 @@ TRACE_EVENT(nfs4_cb_sequence, "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, @@ -517,7 +192,7 @@ TRACE_EVENT(nfs4_cb_seqid_err, "error=%ld (%s) session=0x%08x slot_nr=%u seq_nr=%u " "highest_slotid=%u", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->session, __entry->slot_nr, __entry->seq_nr, @@ -651,7 +326,7 @@ TRACE_EVENT(nfs4_state_mgr_failed, "hostname=%s clp state=%s error=%ld (%s) section=%s", __get_str(hostname), show_nfs4_clp_state(__entry->state), -__entry->error, - show_nfsv4_errors(__entry->error), __get_str(section) + show_nfs4_status(__entry->error), __get_str(section) ) ) @@ -722,7 +397,7 @@ DECLARE_EVENT_CLASS(nfs4_xdr_event, TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x error=%ld (%s) operation=%u", __entry->task_id, __entry->client_id, __entry->xid, - -__entry->error, show_nfsv4_errors(__entry->error), + -__entry->error, show_nfs4_status(__entry->error), __entry->op ) ); @@ -837,7 +512,7 @@ DECLARE_EVENT_CLASS(nfs4_open_event, "name=%02x:%02x:%llu/%s stateid=%d:0x%08x " "openstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), show_fs_fmode_flags(__entry->fmode), @@ -941,7 +616,7 @@ TRACE_EVENT(nfs4_close, "error=%ld (%s) fmode=%s fileid=%02x:%02x:%llu " "fhandle=0x%08x openstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), __entry->fmode ? show_fs_fmode_flags(__entry->fmode) : "closed", MAJOR(__entry->dev), MINOR(__entry->dev), @@ -996,7 +671,7 @@ DECLARE_EVENT_CLASS(nfs4_lock_event, "fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), show_fs_fcntl_cmd(__entry->cmd), show_fs_fcntl_lock_type(__entry->type), (long long)__entry->start, @@ -1072,7 +747,7 @@ TRACE_EVENT(nfs4_set_lock, "fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x lockstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), show_fs_fcntl_cmd(__entry->cmd), show_fs_fcntl_lock_type(__entry->type), (long long)__entry->start, @@ -1238,7 +913,7 @@ TRACE_EVENT(nfs4_delegreturn_exit, "error=%ld (%s) dev=%02x:%02x fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fhandle, __entry->stateid_seq, __entry->stateid_hash @@ -1281,7 +956,7 @@ DECLARE_EVENT_CLASS(nfs4_test_stateid_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1328,7 +1003,7 @@ DECLARE_EVENT_CLASS(nfs4_lookup_event, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -1375,7 +1050,7 @@ TRACE_EVENT(nfs4_lookupp, TP_printk( "error=%ld (%s) inode=%02x:%02x:%llu", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->ino ) @@ -1414,7 +1089,7 @@ TRACE_EVENT(nfs4_rename, "error=%ld (%s) oldname=%02x:%02x:%llu/%s " "newname=%02x:%02x:%llu/%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->olddir, __get_str(oldname), @@ -1449,7 +1124,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_event, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle @@ -1507,7 +1182,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1560,7 +1235,7 @@ DECLARE_EVENT_CLASS(nfs4_getattr_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "valid=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1616,7 +1291,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1677,7 +1352,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "stateid=%d:0x%08x dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1726,7 +1401,7 @@ DECLARE_EVENT_CLASS(nfs4_idmap_event, TP_printk( "error=%ld (%s) id=%u name=%s", - -__entry->error, show_nfsv4_errors(__entry->error), + -__entry->error, show_nfs4_status(__entry->error), __entry->id, __get_str(name) ) @@ -1804,7 +1479,7 @@ DECLARE_EVENT_CLASS(nfs4_read_event, "offset=%lld count=%u res=%u stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1878,7 +1553,7 @@ DECLARE_EVENT_CLASS(nfs4_write_event, "offset=%lld count=%u res=%u stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1942,7 +1617,7 @@ DECLARE_EVENT_CLASS(nfs4_commit_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%lld count=%u layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -1962,16 +1637,6 @@ DEFINE_NFS4_COMMIT_EVENT(nfs4_commit); #ifdef CONFIG_NFS_V4_1 DEFINE_NFS4_COMMIT_EVENT(nfs4_pnfs_commit_ds); -TRACE_DEFINE_ENUM(IOMODE_READ); -TRACE_DEFINE_ENUM(IOMODE_RW); -TRACE_DEFINE_ENUM(IOMODE_ANY); - -#define show_pnfs_iomode(iomode) \ - __print_symbolic(iomode, \ - { IOMODE_READ, "READ" }, \ - { IOMODE_RW, "RW" }, \ - { IOMODE_ANY, "ANY" }) - TRACE_EVENT(nfs4_layoutget, TP_PROTO( const struct nfs_open_context *ctx, @@ -2027,11 +1692,11 @@ TRACE_EVENT(nfs4_layoutget, "iomode=%s offset=%llu count=%llu stateid=%d:0x%08x " "layoutstateid=%d:0x%08x", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->offset, (unsigned long long)__entry->count, __entry->stateid_seq, __entry->stateid_hash, @@ -2125,7 +1790,7 @@ TRACE_EVENT(pnfs_update_layout, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->pos, (unsigned long long)__entry->count, __entry->layoutstateid_seq, __entry->layoutstateid_hash, @@ -2179,7 +1844,7 @@ DECLARE_EVENT_CLASS(pnfs_layout_event, MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, - show_pnfs_iomode(__entry->iomode), + show_pnfs_layout_iomode(__entry->iomode), (unsigned long long)__entry->pos, (unsigned long long)__entry->count, __entry->layoutstateid_seq, __entry->layoutstateid_hash, @@ -2324,7 +1989,7 @@ DECLARE_EVENT_CLASS(nfs4_flexfiles_io_event, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%llu count=%u stateid=%d:0x%08x dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -2380,7 +2045,7 @@ TRACE_EVENT(ff_layout_commit_error, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "offset=%llu count=%u dstaddr=%s", -__entry->error, - show_nfsv4_errors(__entry->error), + show_nfs4_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 331bcc0c0a75..76f04aa3367c 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -12,6 +12,7 @@ #include #include +#include #include #define nfs_show_cache_validity(v) \ @@ -115,7 +116,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event_done, "error=%ld (%s) fileid=%02x:%02x:%llu fhandle=0x%08x " "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s)", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -206,7 +207,7 @@ TRACE_EVENT(nfs_access_exit, "type=%u (%s) version=%llu size=%lld " "cache_validity=0x%lx (%s) nfs_flags=0x%lx (%s) " "mask=0x%x permitted=0x%x", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->fileid, __entry->fhandle, @@ -342,7 +343,7 @@ DECLARE_EVENT_CLASS(nfs_lookup_event_done, TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_lookup_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -433,7 +434,7 @@ TRACE_EVENT(nfs_atomic_open_exit, TP_printk( "error=%ld (%s) flags=0x%lx (%s) fmode=%s " "name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), show_fs_fmode_flags(__entry->fmode), @@ -504,7 +505,7 @@ TRACE_EVENT(nfs_create_exit, TP_printk( "error=%ld (%s) flags=0x%lx (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), __entry->flags, show_fs_fcntl_open_flags(__entry->flags), MAJOR(__entry->dev), MINOR(__entry->dev), @@ -574,7 +575,7 @@ DECLARE_EVENT_CLASS(nfs_directory_event_done, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -664,7 +665,7 @@ TRACE_EVENT(nfs_link_exit, TP_printk( "error=%ld (%s) fileid=%02x:%02x:%llu name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), __entry->fileid, MAJOR(__entry->dev), MINOR(__entry->dev), @@ -751,7 +752,7 @@ DECLARE_EVENT_CLASS(nfs_rename_event_done, TP_printk( "error=%ld (%s) old_name=%02x:%02x:%llu/%s " "new_name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->old_dir, __get_str(old_name), @@ -805,7 +806,7 @@ TRACE_EVENT(nfs_sillyrename_unlink, TP_printk( "error=%ld (%s) name=%02x:%02x:%llu/%s", - -__entry->error, nfs_show_status(__entry->error), + -__entry->error, show_nfs_status(__entry->error), MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->dir, __get_str(name) @@ -1134,16 +1135,6 @@ TRACE_EVENT(nfs_pgio_error, ) ); -TRACE_DEFINE_ENUM(NFS_UNSTABLE); -TRACE_DEFINE_ENUM(NFS_DATA_SYNC); -TRACE_DEFINE_ENUM(NFS_FILE_SYNC); - -#define nfs_show_stable(stable) \ - __print_symbolic(stable, \ - { NFS_UNSTABLE, "UNSTABLE" }, \ - { NFS_DATA_SYNC, "DATA_SYNC" }, \ - { NFS_FILE_SYNC, "FILE_SYNC" }) - TRACE_EVENT(nfs_initiate_write, TP_PROTO( const struct nfs_pgio_header *hdr @@ -1157,7 +1148,7 @@ TRACE_EVENT(nfs_initiate_write, __field(u64, fileid) __field(loff_t, offset) __field(u32, count) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) ), TP_fast_assign( @@ -1181,7 +1172,7 @@ TRACE_EVENT(nfs_initiate_write, (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->count, - nfs_show_stable(__entry->stable) + show_nfs_stable_how(__entry->stable) ) ); @@ -1201,7 +1192,7 @@ TRACE_EVENT(nfs_writeback_done, __field(u32, arg_count) __field(u32, res_count) __field(int, status) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1234,8 +1225,8 @@ TRACE_EVENT(nfs_writeback_done, __entry->fhandle, (long long)__entry->offset, __entry->arg_count, __entry->res_count, __entry->status, - nfs_show_stable(__entry->stable), - __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + show_nfs_stable_how(__entry->stable), + show_nfs4_verifier(__entry->verifier) ) ); @@ -1336,7 +1327,7 @@ TRACE_EVENT(nfs_commit_done, __field(u64, fileid) __field(loff_t, offset) __field(int, status) - __field(enum nfs3_stable_how, stable) + __field(unsigned long, stable) __array(char, verifier, NFS4_VERIFIER_SIZE) ), @@ -1365,8 +1356,8 @@ TRACE_EVENT(nfs_commit_done, (unsigned long long)__entry->fileid, __entry->fhandle, (long long)__entry->offset, __entry->status, - nfs_show_stable(__entry->stable), - __print_hex_str(__entry->verifier, NFS4_VERIFIER_SIZE) + show_nfs_stable_how(__entry->stable), + show_nfs4_verifier(__entry->verifier) ) ); @@ -1403,76 +1394,6 @@ TRACE_EVENT(nfs_fh_to_dentry, ) ); -TRACE_DEFINE_ENUM(NFS_OK); -TRACE_DEFINE_ENUM(NFSERR_PERM); -TRACE_DEFINE_ENUM(NFSERR_NOENT); -TRACE_DEFINE_ENUM(NFSERR_IO); -TRACE_DEFINE_ENUM(NFSERR_NXIO); -TRACE_DEFINE_ENUM(ECHILD); -TRACE_DEFINE_ENUM(NFSERR_EAGAIN); -TRACE_DEFINE_ENUM(NFSERR_ACCES); -TRACE_DEFINE_ENUM(NFSERR_EXIST); -TRACE_DEFINE_ENUM(NFSERR_XDEV); -TRACE_DEFINE_ENUM(NFSERR_NODEV); -TRACE_DEFINE_ENUM(NFSERR_NOTDIR); -TRACE_DEFINE_ENUM(NFSERR_ISDIR); -TRACE_DEFINE_ENUM(NFSERR_INVAL); -TRACE_DEFINE_ENUM(NFSERR_FBIG); -TRACE_DEFINE_ENUM(NFSERR_NOSPC); -TRACE_DEFINE_ENUM(NFSERR_ROFS); -TRACE_DEFINE_ENUM(NFSERR_MLINK); -TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); -TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); -TRACE_DEFINE_ENUM(NFSERR_DQUOT); -TRACE_DEFINE_ENUM(NFSERR_STALE); -TRACE_DEFINE_ENUM(NFSERR_REMOTE); -TRACE_DEFINE_ENUM(NFSERR_WFLUSH); -TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); -TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); -TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); -TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); -TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); -TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); -TRACE_DEFINE_ENUM(NFSERR_BADTYPE); -TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); - -#define nfs_show_status(x) \ - __print_symbolic(x, \ - { NFS_OK, "OK" }, \ - { NFSERR_PERM, "PERM" }, \ - { NFSERR_NOENT, "NOENT" }, \ - { NFSERR_IO, "IO" }, \ - { NFSERR_NXIO, "NXIO" }, \ - { ECHILD, "CHILD" }, \ - { NFSERR_EAGAIN, "AGAIN" }, \ - { NFSERR_ACCES, "ACCES" }, \ - { NFSERR_EXIST, "EXIST" }, \ - { NFSERR_XDEV, "XDEV" }, \ - { NFSERR_NODEV, "NODEV" }, \ - { NFSERR_NOTDIR, "NOTDIR" }, \ - { NFSERR_ISDIR, "ISDIR" }, \ - { NFSERR_INVAL, "INVAL" }, \ - { NFSERR_FBIG, "FBIG" }, \ - { NFSERR_NOSPC, "NOSPC" }, \ - { NFSERR_ROFS, "ROFS" }, \ - { NFSERR_MLINK, "MLINK" }, \ - { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ - { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ - { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ - { NFSERR_DQUOT, "DQUOT" }, \ - { NFSERR_STALE, "STALE" }, \ - { NFSERR_REMOTE, "REMOTE" }, \ - { NFSERR_WFLUSH, "WFLUSH" }, \ - { NFSERR_BADHANDLE, "BADHANDLE" }, \ - { NFSERR_NOT_SYNC, "NOTSYNC" }, \ - { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ - { NFSERR_NOTSUPP, "NOTSUPP" }, \ - { NFSERR_TOOSMALL, "TOOSMALL" }, \ - { NFSERR_SERVERFAULT, "REMOTEIO" }, \ - { NFSERR_BADTYPE, "BADTYPE" }, \ - { NFSERR_JUKEBOX, "JUKEBOX" }) - DECLARE_EVENT_CLASS(nfs_xdr_event, TP_PROTO( const struct xdr_stream *xdr, @@ -1512,7 +1433,7 @@ DECLARE_EVENT_CLASS(nfs_xdr_event, __entry->task_id, __entry->client_id, __entry->xid, __get_str(program), __entry->version, __get_str(procedure), -__entry->error, - nfs_show_status(__entry->error) + show_nfs_status(__entry->error) ) ); #define DEFINE_NFS_XDR_EVENT(name) \ diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index a0f6ff094b3a..f4d7548d67b2 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -82,10 +82,6 @@ enum pnfs_try_status { PNFS_TRY_AGAIN = 2, }; -/* error codes for internal use */ -#define NFS4ERR_RESET_TO_MDS 12001 -#define NFS4ERR_RESET_TO_PNFS 12002 - #ifdef CONFIG_NFS_V4_1 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 538520957a81..f1e0d3c51bc2 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -9,6 +9,7 @@ #define _NFSD_TRACE_H #include + #include "export.h" #include "nfsfh.h" diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 15004c469807..5662d8be04eb 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -292,6 +292,10 @@ enum nfsstat4 { NFS4ERR_XATTR2BIG = 10096, }; +/* error codes for internal client use */ +#define NFS4ERR_RESET_TO_MDS 12001 +#define NFS4ERR_RESET_TO_PNFS 12002 + static inline bool seqid_mutating_err(u32 err) { /* See RFC 7530, section 9.1.7 */ diff --git a/include/trace/events/nfs.h b/include/trace/events/nfs.h new file mode 100644 index 000000000000..09ffdbb04134 --- /dev/null +++ b/include/trace/events/nfs.h @@ -0,0 +1,375 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Display helpers for NFS protocol elements + * + * Author: Chuck Lever + * + * Copyright (c) 2020, Oracle and/or its affiliates. + */ + +#include +#include +#include + +TRACE_DEFINE_ENUM(NFS_OK); +TRACE_DEFINE_ENUM(NFSERR_PERM); +TRACE_DEFINE_ENUM(NFSERR_NOENT); +TRACE_DEFINE_ENUM(NFSERR_IO); +TRACE_DEFINE_ENUM(NFSERR_NXIO); +TRACE_DEFINE_ENUM(NFSERR_EAGAIN); +TRACE_DEFINE_ENUM(NFSERR_ACCES); +TRACE_DEFINE_ENUM(NFSERR_EXIST); +TRACE_DEFINE_ENUM(NFSERR_XDEV); +TRACE_DEFINE_ENUM(NFSERR_NODEV); +TRACE_DEFINE_ENUM(NFSERR_NOTDIR); +TRACE_DEFINE_ENUM(NFSERR_ISDIR); +TRACE_DEFINE_ENUM(NFSERR_INVAL); +TRACE_DEFINE_ENUM(NFSERR_FBIG); +TRACE_DEFINE_ENUM(NFSERR_NOSPC); +TRACE_DEFINE_ENUM(NFSERR_ROFS); +TRACE_DEFINE_ENUM(NFSERR_MLINK); +TRACE_DEFINE_ENUM(NFSERR_OPNOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFSERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFSERR_DQUOT); +TRACE_DEFINE_ENUM(NFSERR_STALE); +TRACE_DEFINE_ENUM(NFSERR_REMOTE); +TRACE_DEFINE_ENUM(NFSERR_WFLUSH); +TRACE_DEFINE_ENUM(NFSERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFSERR_NOT_SYNC); +TRACE_DEFINE_ENUM(NFSERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFSERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFSERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFSERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFSERR_BADTYPE); +TRACE_DEFINE_ENUM(NFSERR_JUKEBOX); + +#define show_nfs_status(x) \ + __print_symbolic(x, \ + { NFS_OK, "OK" }, \ + { NFSERR_PERM, "PERM" }, \ + { NFSERR_NOENT, "NOENT" }, \ + { NFSERR_IO, "IO" }, \ + { NFSERR_NXIO, "NXIO" }, \ + { ECHILD, "CHILD" }, \ + { NFSERR_EAGAIN, "AGAIN" }, \ + { NFSERR_ACCES, "ACCES" }, \ + { NFSERR_EXIST, "EXIST" }, \ + { NFSERR_XDEV, "XDEV" }, \ + { NFSERR_NODEV, "NODEV" }, \ + { NFSERR_NOTDIR, "NOTDIR" }, \ + { NFSERR_ISDIR, "ISDIR" }, \ + { NFSERR_INVAL, "INVAL" }, \ + { NFSERR_FBIG, "FBIG" }, \ + { NFSERR_NOSPC, "NOSPC" }, \ + { NFSERR_ROFS, "ROFS" }, \ + { NFSERR_MLINK, "MLINK" }, \ + { NFSERR_OPNOTSUPP, "OPNOTSUPP" }, \ + { NFSERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFSERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFSERR_DQUOT, "DQUOT" }, \ + { NFSERR_STALE, "STALE" }, \ + { NFSERR_REMOTE, "REMOTE" }, \ + { NFSERR_WFLUSH, "WFLUSH" }, \ + { NFSERR_BADHANDLE, "BADHANDLE" }, \ + { NFSERR_NOT_SYNC, "NOTSYNC" }, \ + { NFSERR_BAD_COOKIE, "BADCOOKIE" }, \ + { NFSERR_NOTSUPP, "NOTSUPP" }, \ + { NFSERR_TOOSMALL, "TOOSMALL" }, \ + { NFSERR_SERVERFAULT, "REMOTEIO" }, \ + { NFSERR_BADTYPE, "BADTYPE" }, \ + { NFSERR_JUKEBOX, "JUKEBOX" }) + +TRACE_DEFINE_ENUM(NFS_UNSTABLE); +TRACE_DEFINE_ENUM(NFS_DATA_SYNC); +TRACE_DEFINE_ENUM(NFS_FILE_SYNC); + +#define show_nfs_stable_how(x) \ + __print_symbolic(x, \ + { NFS_UNSTABLE, "UNSTABLE" }, \ + { NFS_DATA_SYNC, "DATA_SYNC" }, \ + { NFS_FILE_SYNC, "FILE_SYNC" }) + +TRACE_DEFINE_ENUM(NFS4_OK); +TRACE_DEFINE_ENUM(NFS4ERR_ACCESS); +TRACE_DEFINE_ENUM(NFS4ERR_ATTRNOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_ADMIN_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_BACK_CHAN_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_BADCHAR); +TRACE_DEFINE_ENUM(NFS4ERR_BADHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_BADIOMODE); +TRACE_DEFINE_ENUM(NFS4ERR_BADLAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_BADLABEL); +TRACE_DEFINE_ENUM(NFS4ERR_BADNAME); +TRACE_DEFINE_ENUM(NFS4ERR_BADOWNER); +TRACE_DEFINE_ENUM(NFS4ERR_BADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_BADSLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BADTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_BADXDR); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_COOKIE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_HIGH_SLOT); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SEQID); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_SESSION_DIGEST); +TRACE_DEFINE_ENUM(NFS4ERR_BAD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_CB_PATH_DOWN); +TRACE_DEFINE_ENUM(NFS4ERR_CLID_INUSE); +TRACE_DEFINE_ENUM(NFS4ERR_CLIENTID_BUSY); +TRACE_DEFINE_ENUM(NFS4ERR_COMPLETE_ALREADY); +TRACE_DEFINE_ENUM(NFS4ERR_CONN_NOT_BOUND_TO_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DEADLOCK); +TRACE_DEFINE_ENUM(NFS4ERR_DEADSESSION); +TRACE_DEFINE_ENUM(NFS4ERR_DELAY); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_ALREADY_WANTED); +TRACE_DEFINE_ENUM(NFS4ERR_DELEG_REVOKED); +TRACE_DEFINE_ENUM(NFS4ERR_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_DIRDELEG_UNAVAIL); +TRACE_DEFINE_ENUM(NFS4ERR_DQUOT); +TRACE_DEFINE_ENUM(NFS4ERR_ENCR_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_EXIST); +TRACE_DEFINE_ENUM(NFS4ERR_EXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FBIG); +TRACE_DEFINE_ENUM(NFS4ERR_FHEXPIRED); +TRACE_DEFINE_ENUM(NFS4ERR_FILE_OPEN); +TRACE_DEFINE_ENUM(NFS4ERR_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_HASH_ALG_UNSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_INVAL); +TRACE_DEFINE_ENUM(NFS4ERR_IO); +TRACE_DEFINE_ENUM(NFS4ERR_ISDIR); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTTRYLATER); +TRACE_DEFINE_ENUM(NFS4ERR_LAYOUTUNAVAILABLE); +TRACE_DEFINE_ENUM(NFS4ERR_LEASE_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKED); +TRACE_DEFINE_ENUM(NFS4ERR_LOCKS_HELD); +TRACE_DEFINE_ENUM(NFS4ERR_LOCK_RANGE); +TRACE_DEFINE_ENUM(NFS4ERR_MINOR_VERS_MISMATCH); +TRACE_DEFINE_ENUM(NFS4ERR_MLINK); +TRACE_DEFINE_ENUM(NFS4ERR_MOVED); +TRACE_DEFINE_ENUM(NFS4ERR_NAMETOOLONG); +TRACE_DEFINE_ENUM(NFS4ERR_NOENT); +TRACE_DEFINE_ENUM(NFS4ERR_NOFILEHANDLE); +TRACE_DEFINE_ENUM(NFS4ERR_NOMATCHING_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_NOSPC); +TRACE_DEFINE_ENUM(NFS4ERR_NOTDIR); +TRACE_DEFINE_ENUM(NFS4ERR_NOTEMPTY); +TRACE_DEFINE_ENUM(NFS4ERR_NOTSUPP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_ONLY_OP); +TRACE_DEFINE_ENUM(NFS4ERR_NOT_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_NO_GRACE); +TRACE_DEFINE_ENUM(NFS4ERR_NXIO); +TRACE_DEFINE_ENUM(NFS4ERR_OLD_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_OPENMODE); +TRACE_DEFINE_ENUM(NFS4ERR_OP_ILLEGAL); +TRACE_DEFINE_ENUM(NFS4ERR_OP_NOT_IN_SESSION); +TRACE_DEFINE_ENUM(NFS4ERR_PERM); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_IO_HOLE); +TRACE_DEFINE_ENUM(NFS4ERR_PNFS_NO_LAYOUT); +TRACE_DEFINE_ENUM(NFS4ERR_RECALLCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_BAD); +TRACE_DEFINE_ENUM(NFS4ERR_RECLAIM_CONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_REJECT_DELEG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_REP_TOO_BIG_TO_CACHE); +TRACE_DEFINE_ENUM(NFS4ERR_REQ_TOO_BIG); +TRACE_DEFINE_ENUM(NFS4ERR_RESOURCE); +TRACE_DEFINE_ENUM(NFS4ERR_RESTOREFH); +TRACE_DEFINE_ENUM(NFS4ERR_RETRY_UNCACHED_REP); +TRACE_DEFINE_ENUM(NFS4ERR_RETURNCONFLICT); +TRACE_DEFINE_ENUM(NFS4ERR_ROFS); +TRACE_DEFINE_ENUM(NFS4ERR_SAME); +TRACE_DEFINE_ENUM(NFS4ERR_SHARE_DENIED); +TRACE_DEFINE_ENUM(NFS4ERR_SEQUENCE_POS); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_FALSE_RETRY); +TRACE_DEFINE_ENUM(NFS4ERR_SEQ_MISORDERED); +TRACE_DEFINE_ENUM(NFS4ERR_SERVERFAULT); +TRACE_DEFINE_ENUM(NFS4ERR_STALE); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_CLIENTID); +TRACE_DEFINE_ENUM(NFS4ERR_STALE_STATEID); +TRACE_DEFINE_ENUM(NFS4ERR_SYMLINK); +TRACE_DEFINE_ENUM(NFS4ERR_TOOSMALL); +TRACE_DEFINE_ENUM(NFS4ERR_TOO_MANY_OPS); +TRACE_DEFINE_ENUM(NFS4ERR_UNKNOWN_LAYOUTTYPE); +TRACE_DEFINE_ENUM(NFS4ERR_UNSAFE_COMPOUND); +TRACE_DEFINE_ENUM(NFS4ERR_WRONGSEC); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_CRED); +TRACE_DEFINE_ENUM(NFS4ERR_WRONG_TYPE); +TRACE_DEFINE_ENUM(NFS4ERR_XDEV); + +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_MDS); +TRACE_DEFINE_ENUM(NFS4ERR_RESET_TO_PNFS); + +#define show_nfs4_status(x) \ + __print_symbolic(x, \ + { NFS4_OK, "OK" }, \ + { EPERM, "EPERM" }, \ + { ENOENT, "ENOENT" }, \ + { EIO, "EIO" }, \ + { ENXIO, "ENXIO" }, \ + { EACCES, "EACCES" }, \ + { EEXIST, "EEXIST" }, \ + { EXDEV, "EXDEV" }, \ + { ENOTDIR, "ENOTDIR" }, \ + { EISDIR, "EISDIR" }, \ + { EFBIG, "EFBIG" }, \ + { ENOSPC, "ENOSPC" }, \ + { EROFS, "EROFS" }, \ + { EMLINK, "EMLINK" }, \ + { ENAMETOOLONG, "ENAMETOOLONG" }, \ + { ENOTEMPTY, "ENOTEMPTY" }, \ + { EDQUOT, "EDQUOT" }, \ + { ESTALE, "ESTALE" }, \ + { EBADHANDLE, "EBADHANDLE" }, \ + { EBADCOOKIE, "EBADCOOKIE" }, \ + { ENOTSUPP, "ENOTSUPP" }, \ + { ETOOSMALL, "ETOOSMALL" }, \ + { EREMOTEIO, "EREMOTEIO" }, \ + { EBADTYPE, "EBADTYPE" }, \ + { EAGAIN, "EAGAIN" }, \ + { ELOOP, "ELOOP" }, \ + { EOPNOTSUPP, "EOPNOTSUPP" }, \ + { EDEADLK, "EDEADLK" }, \ + { ENOMEM, "ENOMEM" }, \ + { EKEYEXPIRED, "EKEYEXPIRED" }, \ + { ETIMEDOUT, "ETIMEDOUT" }, \ + { ERESTARTSYS, "ERESTARTSYS" }, \ + { ECONNREFUSED, "ECONNREFUSED" }, \ + { ECONNRESET, "ECONNRESET" }, \ + { ENETUNREACH, "ENETUNREACH" }, \ + { EHOSTUNREACH, "EHOSTUNREACH" }, \ + { EHOSTDOWN, "EHOSTDOWN" }, \ + { EPIPE, "EPIPE" }, \ + { EPFNOSUPPORT, "EPFNOSUPPORT" }, \ + { EPROTONOSUPPORT, "EPROTONOSUPPORT" }, \ + { NFS4ERR_ACCESS, "ACCESS" }, \ + { NFS4ERR_ATTRNOTSUPP, "ATTRNOTSUPP" }, \ + { NFS4ERR_ADMIN_REVOKED, "ADMIN_REVOKED" }, \ + { NFS4ERR_BACK_CHAN_BUSY, "BACK_CHAN_BUSY" }, \ + { NFS4ERR_BADCHAR, "BADCHAR" }, \ + { NFS4ERR_BADHANDLE, "BADHANDLE" }, \ + { NFS4ERR_BADIOMODE, "BADIOMODE" }, \ + { NFS4ERR_BADLAYOUT, "BADLAYOUT" }, \ + { NFS4ERR_BADLABEL, "BADLABEL" }, \ + { NFS4ERR_BADNAME, "BADNAME" }, \ + { NFS4ERR_BADOWNER, "BADOWNER" }, \ + { NFS4ERR_BADSESSION, "BADSESSION" }, \ + { NFS4ERR_BADSLOT, "BADSLOT" }, \ + { NFS4ERR_BADTYPE, "BADTYPE" }, \ + { NFS4ERR_BADXDR, "BADXDR" }, \ + { NFS4ERR_BAD_COOKIE, "BAD_COOKIE" }, \ + { NFS4ERR_BAD_HIGH_SLOT, "BAD_HIGH_SLOT" }, \ + { NFS4ERR_BAD_RANGE, "BAD_RANGE" }, \ + { NFS4ERR_BAD_SEQID, "BAD_SEQID" }, \ + { NFS4ERR_BAD_SESSION_DIGEST, "BAD_SESSION_DIGEST" }, \ + { NFS4ERR_BAD_STATEID, "BAD_STATEID" }, \ + { NFS4ERR_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { NFS4ERR_CLID_INUSE, "CLID_INUSE" }, \ + { NFS4ERR_CLIENTID_BUSY, "CLIENTID_BUSY" }, \ + { NFS4ERR_COMPLETE_ALREADY, "COMPLETE_ALREADY" }, \ + { NFS4ERR_CONN_NOT_BOUND_TO_SESSION, "CONN_NOT_BOUND_TO_SESSION" }, \ + { NFS4ERR_DEADLOCK, "DEADLOCK" }, \ + { NFS4ERR_DEADSESSION, "DEAD_SESSION" }, \ + { NFS4ERR_DELAY, "DELAY" }, \ + { NFS4ERR_DELEG_ALREADY_WANTED, "DELEG_ALREADY_WANTED" }, \ + { NFS4ERR_DELEG_REVOKED, "DELEG_REVOKED" }, \ + { NFS4ERR_DENIED, "DENIED" }, \ + { NFS4ERR_DIRDELEG_UNAVAIL, "DIRDELEG_UNAVAIL" }, \ + { NFS4ERR_DQUOT, "DQUOT" }, \ + { NFS4ERR_ENCR_ALG_UNSUPP, "ENCR_ALG_UNSUPP" }, \ + { NFS4ERR_EXIST, "EXIST" }, \ + { NFS4ERR_EXPIRED, "EXPIRED" }, \ + { NFS4ERR_FBIG, "FBIG" }, \ + { NFS4ERR_FHEXPIRED, "FHEXPIRED" }, \ + { NFS4ERR_FILE_OPEN, "FILE_OPEN" }, \ + { NFS4ERR_GRACE, "GRACE" }, \ + { NFS4ERR_HASH_ALG_UNSUPP, "HASH_ALG_UNSUPP" }, \ + { NFS4ERR_INVAL, "INVAL" }, \ + { NFS4ERR_IO, "IO" }, \ + { NFS4ERR_ISDIR, "ISDIR" }, \ + { NFS4ERR_LAYOUTTRYLATER, "LAYOUTTRYLATER" }, \ + { NFS4ERR_LAYOUTUNAVAILABLE, "LAYOUTUNAVAILABLE" }, \ + { NFS4ERR_LEASE_MOVED, "LEASE_MOVED" }, \ + { NFS4ERR_LOCKED, "LOCKED" }, \ + { NFS4ERR_LOCKS_HELD, "LOCKS_HELD" }, \ + { NFS4ERR_LOCK_RANGE, "LOCK_RANGE" }, \ + { NFS4ERR_MINOR_VERS_MISMATCH, "MINOR_VERS_MISMATCH" }, \ + { NFS4ERR_MLINK, "MLINK" }, \ + { NFS4ERR_MOVED, "MOVED" }, \ + { NFS4ERR_NAMETOOLONG, "NAMETOOLONG" }, \ + { NFS4ERR_NOENT, "NOENT" }, \ + { NFS4ERR_NOFILEHANDLE, "NOFILEHANDLE" }, \ + { NFS4ERR_NOMATCHING_LAYOUT, "NOMATCHING_LAYOUT" }, \ + { NFS4ERR_NOSPC, "NOSPC" }, \ + { NFS4ERR_NOTDIR, "NOTDIR" }, \ + { NFS4ERR_NOTEMPTY, "NOTEMPTY" }, \ + { NFS4ERR_NOTSUPP, "NOTSUPP" }, \ + { NFS4ERR_NOT_ONLY_OP, "NOT_ONLY_OP" }, \ + { NFS4ERR_NOT_SAME, "NOT_SAME" }, \ + { NFS4ERR_NO_GRACE, "NO_GRACE" }, \ + { NFS4ERR_NXIO, "NXIO" }, \ + { NFS4ERR_OLD_STATEID, "OLD_STATEID" }, \ + { NFS4ERR_OPENMODE, "OPENMODE" }, \ + { NFS4ERR_OP_ILLEGAL, "OP_ILLEGAL" }, \ + { NFS4ERR_OP_NOT_IN_SESSION, "OP_NOT_IN_SESSION" }, \ + { NFS4ERR_PERM, "PERM" }, \ + { NFS4ERR_PNFS_IO_HOLE, "PNFS_IO_HOLE" }, \ + { NFS4ERR_PNFS_NO_LAYOUT, "PNFS_NO_LAYOUT" }, \ + { NFS4ERR_RECALLCONFLICT, "RECALLCONFLICT" }, \ + { NFS4ERR_RECLAIM_BAD, "RECLAIM_BAD" }, \ + { NFS4ERR_RECLAIM_CONFLICT, "RECLAIM_CONFLICT" }, \ + { NFS4ERR_REJECT_DELEG, "REJECT_DELEG" }, \ + { NFS4ERR_REP_TOO_BIG, "REP_TOO_BIG" }, \ + { NFS4ERR_REP_TOO_BIG_TO_CACHE, "REP_TOO_BIG_TO_CACHE" }, \ + { NFS4ERR_REQ_TOO_BIG, "REQ_TOO_BIG" }, \ + { NFS4ERR_RESOURCE, "RESOURCE" }, \ + { NFS4ERR_RESTOREFH, "RESTOREFH" }, \ + { NFS4ERR_RETRY_UNCACHED_REP, "RETRY_UNCACHED_REP" }, \ + { NFS4ERR_RETURNCONFLICT, "RETURNCONFLICT" }, \ + { NFS4ERR_ROFS, "ROFS" }, \ + { NFS4ERR_SAME, "SAME" }, \ + { NFS4ERR_SHARE_DENIED, "SHARE_DENIED" }, \ + { NFS4ERR_SEQUENCE_POS, "SEQUENCE_POS" }, \ + { NFS4ERR_SEQ_FALSE_RETRY, "SEQ_FALSE_RETRY" }, \ + { NFS4ERR_SEQ_MISORDERED, "SEQ_MISORDERED" }, \ + { NFS4ERR_SERVERFAULT, "SERVERFAULT" }, \ + { NFS4ERR_STALE, "STALE" }, \ + { NFS4ERR_STALE_CLIENTID, "STALE_CLIENTID" }, \ + { NFS4ERR_STALE_STATEID, "STALE_STATEID" }, \ + { NFS4ERR_SYMLINK, "SYMLINK" }, \ + { NFS4ERR_TOOSMALL, "TOOSMALL" }, \ + { NFS4ERR_TOO_MANY_OPS, "TOO_MANY_OPS" }, \ + { NFS4ERR_UNKNOWN_LAYOUTTYPE, "UNKNOWN_LAYOUTTYPE" }, \ + { NFS4ERR_UNSAFE_COMPOUND, "UNSAFE_COMPOUND" }, \ + { NFS4ERR_WRONGSEC, "WRONGSEC" }, \ + { NFS4ERR_WRONG_CRED, "WRONG_CRED" }, \ + { NFS4ERR_WRONG_TYPE, "WRONG_TYPE" }, \ + { NFS4ERR_XDEV, "XDEV" }, \ + /* ***** Internal to Linux NFS client ***** */ \ + { NFS4ERR_RESET_TO_MDS, "RESET_TO_MDS" }, \ + { NFS4ERR_RESET_TO_PNFS, "RESET_TO_PNFS" }) + +#define show_nfs4_verifier(x) \ + __print_hex_str(x, NFS4_VERIFIER_SIZE) + +TRACE_DEFINE_ENUM(IOMODE_READ); +TRACE_DEFINE_ENUM(IOMODE_RW); +TRACE_DEFINE_ENUM(IOMODE_ANY); + +#define show_pnfs_layout_iomode(x) \ + __print_symbolic(x, \ + { IOMODE_READ, "READ" }, \ + { IOMODE_RW, "RW" }, \ + { IOMODE_ANY, "ANY" }) + +#define show_nfs4_seq4_status(x) \ + __print_flags(x, "|", \ + { SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING, "CB_GSS_CONTEXTS_EXPIRING" }, \ + { SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED, "CB_GSS_CONTEXTS_EXPIRED" }, \ + { SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED, "EXPIRED_ALL_STATE_REVOKED" }, \ + { SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED, "EXPIRED_SOME_STATE_REVOKED" }, \ + { SEQ4_STATUS_ADMIN_STATE_REVOKED, "ADMIN_STATE_REVOKED" }, \ + { SEQ4_STATUS_RECALLABLE_STATE_REVOKED, "RECALLABLE_STATE_REVOKED" }, \ + { SEQ4_STATUS_LEASE_MOVED, "LEASE_MOVED" }, \ + { SEQ4_STATUS_RESTART_RECLAIM_NEEDED, "RESTART_RECLAIM_NEEDED" }, \ + { SEQ4_STATUS_CB_PATH_DOWN_SESSION, "CB_PATH_DOWN_SESSION" }, \ + { SEQ4_STATUS_BACKCHANNEL_FAULT, "BACKCHANNEL_FAULT" }) -- cgit v1.2.3 From c4777efa751d293e369aec464ce6875e957be255 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 1 Nov 2021 17:45:55 -0700 Subject: net: add and use skb_unclone_keeptruesize() helper While commit 097b9146c0e2 ("net: fix up truesize of cloned skb in skb_prepare_for_shift()") fixed immediate issues found when KFENCE was enabled/tested, there are still similar issues, when tcp_trim_head() hits KFENCE while the master skb is cloned. This happens under heavy networking TX workloads, when the TX completion might be delayed after incoming ACK. This patch fixes the WARNING in sk_stream_kill_queues when sk->sk_mem_queued/sk->sk_forward_alloc are not zero. Fixes: d3fb45f370d9 ("mm, kfence: insert KFENCE hooks for SLAB") Signed-off-by: Eric Dumazet Acked-by: Marco Elver Link: https://lore.kernel.org/r/20211102004555.1359210-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 16 ++++++++++++++++ net/core/skbuff.c | 14 +------------- net/ipv4/tcp_output.c | 6 +++--- 3 files changed, 20 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 0bd6520329f6..a63e13082397 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1675,6 +1675,22 @@ static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) return 0; } +/* This variant of skb_unclone() makes sure skb->truesize is not changed */ +static inline int skb_unclone_keeptruesize(struct sk_buff *skb, gfp_t pri) +{ + might_sleep_if(gfpflags_allow_blocking(pri)); + + if (skb_cloned(skb)) { + unsigned int save = skb->truesize; + int res; + + res = pskb_expand_head(skb, 0, 0, pri); + skb->truesize = save; + return res; + } + return 0; +} + /** * skb_header_cloned - is the header a clone * @skb: buffer to check diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 67a9188d8a49..3ec42cdee16a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3449,19 +3449,7 @@ EXPORT_SYMBOL(skb_split); */ static int skb_prepare_for_shift(struct sk_buff *skb) { - int ret = 0; - - if (skb_cloned(skb)) { - /* Save and restore truesize: pskb_expand_head() may reallocate - * memory where ksize(kmalloc(S)) != ksize(kmalloc(S)), but we - * cannot change truesize at this point. - */ - unsigned int save_truesize = skb->truesize; - - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - skb->truesize = save_truesize; - } - return ret; + return skb_unclone_keeptruesize(skb, GFP_ATOMIC); } /** diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6fbbf1558033..76cc1641beb4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1559,7 +1559,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; } - if (skb_unclone(skb, gfp)) + if (skb_unclone_keeptruesize(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ @@ -1667,7 +1667,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { u32 delta_truesize; - if (skb_unclone(skb, GFP_ATOMIC)) + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; delta_truesize = __pskb_trim_head(skb, len); @@ -3166,7 +3166,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { - if (skb_unclone(skb, GFP_ATOMIC)) + if (skb_unclone_keeptruesize(skb, GFP_ATOMIC)) return -ENOMEM; diff = tcp_skb_pcount(skb); -- cgit v1.2.3 From 0dc54bd4d6e03be1f0b678c4297170b79f1a44ab Mon Sep 17 00:00:00 2001 From: Dominique Martinet Date: Wed, 3 Nov 2021 17:34:05 +0900 Subject: fscache_cookie_enabled: check cookie is valid before accessing it fscache_cookie_enabled() could be called on NULL cookies and cause a null pointer dereference when accessing cookie flags: just make sure the cookie is valid first Suggested-by: David Howells Acked-by: David Howells Signed-off-by: Dominique Martinet --- include/linux/fscache.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index a4dab5998613..3b2282c157f7 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -167,7 +167,7 @@ struct fscache_cookie { static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) { - return test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); + return fscache_cookie_valid(cookie) && test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); } /* -- cgit v1.2.3 From c081d53f97a1a90a38e4296dd3d6fda5e38dca2c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 2 Nov 2021 08:02:47 -0400 Subject: security: pass asoc to sctp_assoc_request and sctp_sk_clone This patch is to move secid and peer_secid from endpoint to association, and pass asoc to sctp_assoc_request and sctp_sk_clone instead of ep. As ep is the local endpoint and asoc represents a connection, and in SCTP one sk/ep could have multiple asoc/connection, saving secid/peer_secid for new asoc will overwrite the old asoc's. Note that since asoc can be passed as NULL, security_sctp_assoc_request() is moved to the place right after the new_asoc is created in sctp_sf_do_5_1B_init() and sctp_sf_do_unexpected_init(). v1->v2: - fix the description of selinux_netlbl_skbuff_setsid(), as Jakub noticed. - fix the annotation in selinux_sctp_assoc_request(), as Richard Noticed. Fixes: 72e89f50084c ("security: Add support for SCTP security hooks") Reported-by: Prashanth Prahlad Reviewed-by: Richard Haines Tested-by: Richard Haines Signed-off-by: Xin Long Signed-off-by: David S. Miller --- Documentation/security/SCTP.rst | 28 ++++++++++++++-------------- include/linux/lsm_hook_defs.h | 4 ++-- include/linux/lsm_hooks.h | 8 ++++---- include/linux/security.h | 10 +++++----- include/net/sctp/structs.h | 20 ++++++++++---------- net/sctp/sm_statefuns.c | 26 +++++++++++++------------- net/sctp/socket.c | 5 ++--- security/security.c | 8 ++++---- security/selinux/hooks.c | 22 +++++++++++----------- security/selinux/include/netlabel.h | 4 ++-- security/selinux/netlabel.c | 18 +++++++++--------- 11 files changed, 76 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/Documentation/security/SCTP.rst b/Documentation/security/SCTP.rst index 0bcf6c1245ee..415b548d9ce0 100644 --- a/Documentation/security/SCTP.rst +++ b/Documentation/security/SCTP.rst @@ -26,11 +26,11 @@ described in the `SCTP SELinux Support`_ chapter. security_sctp_assoc_request() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Passes the ``@ep`` and ``@chunk->skb`` of the association INIT packet to the +Passes the ``@asoc`` and ``@chunk->skb`` of the association INIT packet to the security module. Returns 0 on success, error on failure. :: - @ep - pointer to sctp endpoint structure. + @asoc - pointer to sctp association structure. @skb - pointer to skbuff of association packet. @@ -117,9 +117,9 @@ Called whenever a new socket is created by **accept**\(2) calls **sctp_peeloff**\(3). :: - @ep - pointer to current sctp endpoint structure. + @asoc - pointer to current sctp association structure. @sk - pointer to current sock structure. - @sk - pointer to new sock structure. + @newsk - pointer to new sock structure. security_inet_conn_established() @@ -200,22 +200,22 @@ hooks with the SELinux specifics expanded below:: security_sctp_assoc_request() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Passes the ``@ep`` and ``@chunk->skb`` of the association INIT packet to the +Passes the ``@asoc`` and ``@chunk->skb`` of the association INIT packet to the security module. Returns 0 on success, error on failure. :: - @ep - pointer to sctp endpoint structure. + @asoc - pointer to sctp association structure. @skb - pointer to skbuff of association packet. The security module performs the following operations: - IF this is the first association on ``@ep->base.sk``, then set the peer + IF this is the first association on ``@asoc->base.sk``, then set the peer sid to that in ``@skb``. This will ensure there is only one peer sid - assigned to ``@ep->base.sk`` that may support multiple associations. + assigned to ``@asoc->base.sk`` that may support multiple associations. - ELSE validate the ``@ep->base.sk peer_sid`` against the ``@skb peer sid`` + ELSE validate the ``@asoc->base.sk peer_sid`` against the ``@skb peer sid`` to determine whether the association should be allowed or denied. - Set the sctp ``@ep sid`` to socket's sid (from ``ep->base.sk``) with + Set the sctp ``@asoc sid`` to socket's sid (from ``asoc->base.sk``) with MLS portion taken from ``@skb peer sid``. This will be used by SCTP TCP style sockets and peeled off connections as they cause a new socket to be generated. @@ -259,13 +259,13 @@ security_sctp_sk_clone() Called whenever a new socket is created by **accept**\(2) (i.e. a TCP style socket) or when a socket is 'peeled off' e.g userspace calls **sctp_peeloff**\(3). ``security_sctp_sk_clone()`` will set the new -sockets sid and peer sid to that contained in the ``@ep sid`` and -``@ep peer sid`` respectively. +sockets sid and peer sid to that contained in the ``@asoc sid`` and +``@asoc peer sid`` respectively. :: - @ep - pointer to current sctp endpoint structure. + @asoc - pointer to current sctp association structure. @sk - pointer to current sock structure. - @sk - pointer to new sock structure. + @newsk - pointer to new sock structure. security_inet_conn_established() diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index a9ac70ae01ab..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -329,11 +329,11 @@ LSM_HOOK(int, 0, tun_dev_create, void) LSM_HOOK(int, 0, tun_dev_attach_queue, void *security) LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security) LSM_HOOK(int, 0, tun_dev_open, void *security) -LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_endpoint *ep, +LSM_HOOK(int, 0, sctp_assoc_request, struct sctp_association *asoc, struct sk_buff *skb) LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) -LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_endpoint *ep, +LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) #endif /* CONFIG_SECURITY_NETWORK */ diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 0bada4df23fc..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1027,9 +1027,9 @@ * Security hooks for SCTP * * @sctp_assoc_request: - * Passes the @ep and @chunk->skb of the association INIT packet to + * Passes the @asoc and @chunk->skb of the association INIT packet to * the security module. - * @ep pointer to sctp endpoint structure. + * @asoc pointer to sctp association structure. * @skb pointer to skbuff of association packet. * Return 0 on success, error on failure. * @sctp_bind_connect: @@ -1047,9 +1047,9 @@ * Called whenever a new socket is created by accept(2) (i.e. a TCP * style socket) or when a socket is 'peeled off' e.g userspace * calls sctp_peeloff(3). - * @ep pointer to current sctp endpoint structure. + * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. - * @sk pointer to new sock structure. + * @newsk pointer to new sock structure. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 7e0ba63b5dde..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -179,7 +179,7 @@ struct xfrm_policy; struct xfrm_state; struct xfrm_user_sec_ctx; struct seq_file; -struct sctp_endpoint; +struct sctp_association; #ifdef CONFIG_MMU extern unsigned long mmap_min_addr; @@ -1425,10 +1425,10 @@ int security_tun_dev_create(void); int security_tun_dev_attach_queue(void *security); int security_tun_dev_attach(struct sock *sk, void *security); int security_tun_dev_open(void *security); -int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb); +int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb); int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); -void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); #else /* CONFIG_SECURITY_NETWORK */ @@ -1631,7 +1631,7 @@ static inline int security_tun_dev_open(void *security) return 0; } -static inline int security_sctp_assoc_request(struct sctp_endpoint *ep, +static inline int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return 0; @@ -1644,7 +1644,7 @@ static inline int security_sctp_bind_connect(struct sock *sk, int optname, return 0; } -static inline void security_sctp_sk_clone(struct sctp_endpoint *ep, +static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 651bba654d77..899c29c326ba 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1355,16 +1355,6 @@ struct sctp_endpoint { reconf_enable:1; __u8 strreset_enable; - - /* Security identifiers from incoming (INIT). These are set by - * security_sctp_assoc_request(). These will only be used by - * SCTP TCP type sockets and peeled off connections as they - * cause a new socket to be generated. security_sctp_sk_clone() - * will then plug these into the new socket. - */ - - u32 secid; - u32 peer_secid; }; /* Recover the outter endpoint structure. */ @@ -2104,6 +2094,16 @@ struct sctp_association { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; + /* Security identifiers from incoming (INIT). These are set by + * security_sctp_assoc_request(). These will only be used by + * SCTP TCP type sockets and peeled off connections as they + * cause a new socket to be generated. security_sctp_sk_clone() + * will then plug these into the new socket. + */ + + u32 secid; + u32 peer_secid; + struct rcu_head rcu; }; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index fb3da4d8f4a3..3206374209bc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -326,11 +326,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, struct sctp_packet *packet; int len; - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. @@ -415,6 +410,12 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net, if (!new_asoc) goto nomem; + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + if (sctp_assoc_set_bind_addr_from_ep(new_asoc, sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) @@ -780,7 +781,6 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, } } - /* Delay state machine commands until later. * * Re-build the bind address for the association is done in @@ -1517,11 +1517,6 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( struct sctp_packet *packet; int len; - /* Update socket peer label if first association. */ - if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - /* 6.10 Bundling * An endpoint MUST NOT bundle INIT, INIT ACK or * SHUTDOWN COMPLETE with any other chunks. @@ -1594,6 +1589,12 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( if (!new_asoc) goto nomem; + /* Update socket peer label if first association. */ + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } + if (sctp_assoc_set_bind_addr_from_ep(new_asoc, sctp_scope(sctp_source(chunk)), GFP_ATOMIC) < 0) goto nomem; @@ -2255,8 +2256,7 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( } /* Update socket peer label if first association. */ - if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) { + if (security_sctp_assoc_request(new_asoc, chunk->skb)) { sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6b937bfd4751..33391254fa82 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9412,7 +9412,6 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; struct sctp_sock *sp = sctp_sk(sk); - struct sctp_endpoint *ep = sp->ep; newsk->sk_type = sk->sk_type; newsk->sk_bound_dev_if = sk->sk_bound_dev_if; @@ -9457,9 +9456,9 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, net_enable_timestamp(); /* Set newsk security attributes from original sk and connection - * security attribute from ep. + * security attribute from asoc. */ - security_sctp_sk_clone(ep, sk, newsk); + security_sctp_sk_clone(asoc, sk, newsk); } static inline void sctp_copy_descendant(struct sock *sk_to, diff --git a/security/security.c b/security/security.c index 95e30fadba78..c88167a414b4 100644 --- a/security/security.c +++ b/security/security.c @@ -2367,9 +2367,9 @@ int security_tun_dev_open(void *security) } EXPORT_SYMBOL(security_tun_dev_open); -int security_sctp_assoc_request(struct sctp_endpoint *ep, struct sk_buff *skb) +int security_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { - return call_int_hook(sctp_assoc_request, 0, ep, skb); + return call_int_hook(sctp_assoc_request, 0, asoc, skb); } EXPORT_SYMBOL(security_sctp_assoc_request); @@ -2381,10 +2381,10 @@ int security_sctp_bind_connect(struct sock *sk, int optname, } EXPORT_SYMBOL(security_sctp_bind_connect); -void security_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { - call_void_hook(sctp_sk_clone, ep, sk, newsk); + call_void_hook(sctp_sk_clone, asoc, sk, newsk); } EXPORT_SYMBOL(security_sctp_sk_clone); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index ea7b2876a5ae..62d30c0a30c2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5339,10 +5339,10 @@ static void selinux_sock_graft(struct sock *sk, struct socket *parent) * connect(2), sctp_connectx(3) or sctp_sendmsg(3) (with no association * already present). */ -static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, +static int selinux_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { - struct sk_security_struct *sksec = ep->base.sk->sk_security; + struct sk_security_struct *sksec = asoc->base.sk->sk_security; struct common_audit_data ad; struct lsm_network_audit net = {0,}; u8 peerlbl_active; @@ -5359,7 +5359,7 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, /* This will return peer_sid = SECSID_NULL if there are * no peer labels, see security_net_peersid_resolve(). */ - err = selinux_skb_peerlbl_sid(skb, ep->base.sk->sk_family, + err = selinux_skb_peerlbl_sid(skb, asoc->base.sk->sk_family, &peer_sid); if (err) return err; @@ -5383,7 +5383,7 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, */ ad.type = LSM_AUDIT_DATA_NET; ad.u.net = &net; - ad.u.net->sk = ep->base.sk; + ad.u.net->sk = asoc->base.sk; err = avc_has_perm(&selinux_state, sksec->peer_sid, peer_sid, sksec->sclass, SCTP_SOCKET__ASSOCIATION, &ad); @@ -5392,7 +5392,7 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, } /* Compute the MLS component for the connection and store - * the information in ep. This will be used by SCTP TCP type + * the information in asoc. This will be used by SCTP TCP type * sockets and peeled off connections as they cause a new * socket to be generated. selinux_sctp_sk_clone() will then * plug this into the new socket. @@ -5401,11 +5401,11 @@ static int selinux_sctp_assoc_request(struct sctp_endpoint *ep, if (err) return err; - ep->secid = conn_sid; - ep->peer_secid = peer_sid; + asoc->secid = conn_sid; + asoc->peer_secid = peer_sid; /* Set any NetLabel labels including CIPSO/CALIPSO options. */ - return selinux_netlbl_sctp_assoc_request(ep, skb); + return selinux_netlbl_sctp_assoc_request(asoc, skb); } /* Check if sctp IPv4/IPv6 addresses are valid for binding or connecting @@ -5490,7 +5490,7 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname, } /* Called whenever a new socket is created by accept(2) or sctp_peeloff(3). */ -static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, +static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk) { struct sk_security_struct *sksec = sk->sk_security; @@ -5502,8 +5502,8 @@ static void selinux_sctp_sk_clone(struct sctp_endpoint *ep, struct sock *sk, if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); - newsksec->sid = ep->secid; - newsksec->peer_sid = ep->peer_secid; + newsksec->sid = asoc->secid; + newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); } diff --git a/security/selinux/include/netlabel.h b/security/selinux/include/netlabel.h index 0c58f62dc6ab..4d0456d3d459 100644 --- a/security/selinux/include/netlabel.h +++ b/security/selinux/include/netlabel.h @@ -39,7 +39,7 @@ int selinux_netlbl_skbuff_getsid(struct sk_buff *skb, int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family, u32 sid); -int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, +int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb); int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family); void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family); @@ -98,7 +98,7 @@ static inline int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, return 0; } -static inline int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, +static inline int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { return 0; diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c index 29b88e81869b..1321f15799e2 100644 --- a/security/selinux/netlabel.c +++ b/security/selinux/netlabel.c @@ -261,30 +261,30 @@ skbuff_setsid_return: /** * selinux_netlbl_sctp_assoc_request - Label an incoming sctp association. - * @ep: incoming association endpoint. + * @asoc: incoming association. * @skb: the packet. * * Description: - * A new incoming connection is represented by @ep, ...... + * A new incoming connection is represented by @asoc, ...... * Returns zero on success, negative values on failure. * */ -int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, +int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc, struct sk_buff *skb) { int rc; struct netlbl_lsm_secattr secattr; - struct sk_security_struct *sksec = ep->base.sk->sk_security; + struct sk_security_struct *sksec = asoc->base.sk->sk_security; struct sockaddr_in addr4; struct sockaddr_in6 addr6; - if (ep->base.sk->sk_family != PF_INET && - ep->base.sk->sk_family != PF_INET6) + if (asoc->base.sk->sk_family != PF_INET && + asoc->base.sk->sk_family != PF_INET6) return 0; netlbl_secattr_init(&secattr); rc = security_netlbl_sid_to_secattr(&selinux_state, - ep->secid, &secattr); + asoc->secid, &secattr); if (rc != 0) goto assoc_request_return; @@ -294,11 +294,11 @@ int selinux_netlbl_sctp_assoc_request(struct sctp_endpoint *ep, if (ip_hdr(skb)->version == 4) { addr4.sin_family = AF_INET; addr4.sin_addr.s_addr = ip_hdr(skb)->saddr; - rc = netlbl_conn_setattr(ep->base.sk, (void *)&addr4, &secattr); + rc = netlbl_conn_setattr(asoc->base.sk, (void *)&addr4, &secattr); } else if (IS_ENABLED(CONFIG_IPV6) && ip_hdr(skb)->version == 6) { addr6.sin6_family = AF_INET6; addr6.sin6_addr = ipv6_hdr(skb)->saddr; - rc = netlbl_conn_setattr(ep->base.sk, (void *)&addr6, &secattr); + rc = netlbl_conn_setattr(asoc->base.sk, (void *)&addr6, &secattr); } else { rc = -EAFNOSUPPORT; } -- cgit v1.2.3 From 7c2ef0240e6abfd3cc59511339517358350a8910 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Tue, 2 Nov 2021 08:02:49 -0400 Subject: security: add sctp_assoc_established hook security_sctp_assoc_established() is added to replace security_inet_conn_established() called in sctp_sf_do_5_1E_ca(), so that asoc can be accessed in security subsystem and save the peer secid to asoc->peer_secid. v1->v2: - fix the return value of security_sctp_assoc_established() in security.h, found by kernel test robot and Ondrej. Fixes: 72e89f50084c ("security: Add support for SCTP security hooks") Reported-by: Prashanth Prahlad Reviewed-by: Richard Haines Tested-by: Richard Haines Signed-off-by: Xin Long Signed-off-by: David S. Miller --- Documentation/security/SCTP.rst | 22 ++++++++++------------ include/linux/lsm_hook_defs.h | 2 ++ include/linux/lsm_hooks.h | 5 +++++ include/linux/security.h | 7 +++++++ net/sctp/sm_statefuns.c | 2 +- security/security.c | 7 +++++++ 6 files changed, 32 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/security/SCTP.rst b/Documentation/security/SCTP.rst index d5fd6ccc3dcb..406cc68b8808 100644 --- a/Documentation/security/SCTP.rst +++ b/Documentation/security/SCTP.rst @@ -15,10 +15,7 @@ For security module support, three SCTP specific hooks have been implemented:: security_sctp_assoc_request() security_sctp_bind_connect() security_sctp_sk_clone() - -Also the following security hook has been utilised:: - - security_inet_conn_established() + security_sctp_assoc_established() The usage of these hooks are described below with the SELinux implementation described in the `SCTP SELinux Support`_ chapter. @@ -122,11 +119,12 @@ calls **sctp_peeloff**\(3). @newsk - pointer to new sock structure. -security_inet_conn_established() +security_sctp_assoc_established() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Called when a COOKIE ACK is received:: +Called when a COOKIE ACK is received, and the peer secid will be +saved into ``@asoc->peer_secid`` for client:: - @sk - pointer to sock structure. + @asoc - pointer to sctp association structure. @skb - pointer to skbuff of the COOKIE ACK packet. @@ -134,7 +132,7 @@ Security Hooks used for Association Establishment ------------------------------------------------- The following diagram shows the use of ``security_sctp_bind_connect()``, -``security_sctp_assoc_request()``, ``security_inet_conn_established()`` when +``security_sctp_assoc_request()``, ``security_sctp_assoc_established()`` when establishing an association. :: @@ -172,7 +170,7 @@ establishing an association. <------------------------------------------- COOKIE ACK | | sctp_sf_do_5_1E_ca | - Call security_inet_conn_established() | + Call security_sctp_assoc_established() | to set the peer label. | | | | If SCTP_SOCKET_TCP or peeled off @@ -198,7 +196,7 @@ hooks with the SELinux specifics expanded below:: security_sctp_assoc_request() security_sctp_bind_connect() security_sctp_sk_clone() - security_inet_conn_established() + security_sctp_assoc_established() security_sctp_assoc_request() @@ -271,12 +269,12 @@ sockets sid and peer sid to that contained in the ``@asoc sid`` and @newsk - pointer to new sock structure. -security_inet_conn_established() +security_sctp_assoc_established() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Called when a COOKIE ACK is received where it sets the connection's peer sid to that in ``@skb``:: - @sk - pointer to sock structure. + @asoc - pointer to sctp association structure. @skb - pointer to skbuff of the COOKIE ACK packet. diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index df8de62f4710..442a611fa0fb 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -335,6 +335,8 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) +LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc, + struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d45b6f6e27fd..d6823214d5c1 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1050,6 +1050,11 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. + * @sctp_assoc_established: + * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet + * to the security module. + * @asoc pointer to sctp association structure. + * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index bbf44a466832..06eac4e61a13 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1430,6 +1430,8 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); +void security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1649,6 +1651,11 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } + +static inline void security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb) +{ +} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index b818532c3fc2..5fabaa54b77d 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -946,7 +946,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); /* Set peer label for connection. */ - security_inet_conn_established(ep->base.sk, chunk->skb); + security_sctp_assoc_established((struct sctp_association *)asoc, chunk->skb); /* RFC 2960 5.1 Normal Establishment of an Association * diff --git a/security/security.c b/security/security.c index c88167a414b4..779a9edea0a0 100644 --- a/security/security.c +++ b/security/security.c @@ -2388,6 +2388,13 @@ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, } EXPORT_SYMBOL(security_sctp_sk_clone); +void security_sctp_assoc_established(struct sctp_association *asoc, + struct sk_buff *skb) +{ + call_void_hook(sctp_assoc_established, asoc, skb); +} +EXPORT_SYMBOL(security_sctp_assoc_established); + #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND -- cgit v1.2.3 From 9b65b17db72313b7a4fe9bc9502928c88be57986 Mon Sep 17 00:00:00 2001 From: Talal Ahmad Date: Tue, 2 Nov 2021 22:58:44 -0400 Subject: net: avoid double accounting for pure zerocopy skbs Track skbs containing only zerocopy data and avoid charging them to kernel memory to correctly account the memory utilization for msg_zerocopy. All of the data in such skbs is held in user pages which are already accounted to user. Before this change, they are charged again in kernel in __zerocopy_sg_from_iter. The charging in kernel is excessive because data is not being copied into skb frags. This excessive charging can lead to kernel going into memory pressure state which impacts all sockets in the system adversely. Mark pure zerocopy skbs with a SKBFL_PURE_ZEROCOPY flag and remove charge/uncharge for data in such skbs. Initially, an skb is marked pure zerocopy when it is empty and in zerocopy path. skb can then change from a pure zerocopy skb to mixed data skb (zerocopy and copy data) if it is at tail of write queue and there is room available in it and non-zerocopy data is being sent in the next sendmsg call. At this time sk_mem_charge is done for the pure zerocopied data and the pure zerocopy flag is unmarked. We found that this happens very rarely on workloads that pass MSG_ZEROCOPY. A pure zerocopy skb can later be coalesced into normal skb if they are next to each other in queue but this patch prevents coalescing from happening. This avoids complexity of charging when skb downgrades from pure zerocopy to mixed. This is also rare. In sk_wmem_free_skb, if it is a pure zerocopy skb, an sk_mem_uncharge for SKB_TRUESIZE(skb_end_offset(skb)) is done for sk_mem_charge in tcp_skb_entail for an skb without data. Testing with the msg_zerocopy.c benchmark between two hosts(100G nics) with zerocopy showed that before this patch the 'sock' variable in memory.stat for cgroup2 that tracks sum of sk_forward_alloc, sk_rmem_alloc and sk_wmem_queued is around 1822720 and with this change it is 0. This is due to no charge to sk_forward_alloc for zerocopy data and shows memory utilization for kernel is lowered. With this commit we don't see the warning we saw in previous commit which resulted in commit 84882cf72cd774cf16fd338bdbf00f69ac9f9194. Signed-off-by: Talal Ahmad Acked-by: Arjun Roy Acked-by: Soheil Hassas Yeganeh Signed-off-by: Willem de Bruijn Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 19 ++++++++++++++++++- include/net/tcp.h | 8 ++++++-- net/core/datagram.c | 3 ++- net/core/skbuff.c | 3 ++- net/ipv4/tcp.c | 22 ++++++++++++++++++++-- net/ipv4/tcp_output.c | 7 +++++-- 6 files changed, 53 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a63e13082397..686a666d073d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -454,9 +454,15 @@ enum { * all frags to avoid possible bad checksum */ SKBFL_SHARED_FRAG = BIT(1), + + /* segment contains only zerocopy data and should not be + * charged to the kernel memory. + */ + SKBFL_PURE_ZEROCOPY = BIT(2), }; #define SKBFL_ZEROCOPY_FRAG (SKBFL_ZEROCOPY_ENABLE | SKBFL_SHARED_FRAG) +#define SKBFL_ALL_ZEROCOPY (SKBFL_ZEROCOPY_FRAG | SKBFL_PURE_ZEROCOPY) /* * The callback notifies userspace to release buffers when skb DMA is done in @@ -1464,6 +1470,17 @@ static inline struct ubuf_info *skb_zcopy(struct sk_buff *skb) return is_zcopy ? skb_uarg(skb) : NULL; } +static inline bool skb_zcopy_pure(const struct sk_buff *skb) +{ + return skb_shinfo(skb)->flags & SKBFL_PURE_ZEROCOPY; +} + +static inline bool skb_pure_zcopy_same(const struct sk_buff *skb1, + const struct sk_buff *skb2) +{ + return skb_zcopy_pure(skb1) == skb_zcopy_pure(skb2); +} + static inline void net_zcopy_get(struct ubuf_info *uarg) { refcount_inc(&uarg->refcnt); @@ -1528,7 +1545,7 @@ static inline void skb_zcopy_clear(struct sk_buff *skb, bool zerocopy_success) if (!skb_zcopy_is_nouarg(skb)) uarg->callback(skb, uarg, zerocopy_success); - skb_shinfo(skb)->flags &= ~SKBFL_ZEROCOPY_FRAG; + skb_shinfo(skb)->flags &= ~SKBFL_ALL_ZEROCOPY; } } diff --git a/include/net/tcp.h b/include/net/tcp.h index 70972f3ac8fa..4da22b41bde6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -293,7 +293,10 @@ static inline bool tcp_out_of_memory(struct sock *sk) static inline void tcp_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sk_wmem_queued_add(sk, -skb->truesize); - sk_mem_uncharge(sk, skb->truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, skb->truesize); + else + sk_mem_uncharge(sk, SKB_TRUESIZE(skb_end_offset(skb))); __kfree_skb(skb); } @@ -974,7 +977,8 @@ static inline bool tcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { return likely(tcp_skb_can_collapse_to(to) && - mptcp_skb_can_collapse(to, from)); + mptcp_skb_can_collapse(to, from) && + skb_pure_zcopy_same(to, from)); } /* Events passed to congestion control interface */ diff --git a/net/core/datagram.c b/net/core/datagram.c index 15ab9ffb27fe..ee290776c661 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -646,7 +646,8 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { sk_wmem_queued_add(sk, truesize); - sk_mem_charge(sk, truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3ec42cdee16a..ba2f38246f07 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3433,8 +3433,9 @@ static inline void skb_split_no_header(struct sk_buff *skb, void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) { int pos = skb_headlen(skb); + const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; - skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ skb_split_inside_header(skb, skb1, len, pos); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index bc7f419184aa..b461ae573afc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -863,6 +863,7 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, if (likely(skb)) { bool mem_scheduled; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); if (force_schedule) { mem_scheduled = true; sk_forced_mem_schedule(sk, skb->truesize); @@ -1319,6 +1320,15 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); + /* skb changing from pure zc to mixed, must charge zc */ + if (unlikely(skb_zcopy_pure(skb))) { + if (!sk_wmem_schedule(sk, skb->data_len)) + goto wait_for_space; + + sk_mem_charge(sk, skb->data_len); + skb_shinfo(skb)->flags &= ~SKBFL_PURE_ZEROCOPY; + } + if (!sk_wmem_schedule(sk, copy)) goto wait_for_space; @@ -1339,8 +1349,16 @@ new_segment: } pfrag->offset += copy; } else { - if (!sk_wmem_schedule(sk, copy)) - goto wait_for_space; + /* First append to a fragless skb builds initial + * pure zerocopy skb + */ + if (!skb->len) + skb_shinfo(skb)->flags |= SKBFL_PURE_ZEROCOPY; + + if (!skb_zcopy_pure(skb)) { + if (!sk_wmem_schedule(sk, copy)) + goto wait_for_space; + } err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); if (err == -EMSGSIZE || err == -EEXIST) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 76cc1641beb4..6f7860e283c6 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1677,7 +1677,8 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; sk_wmem_queued_add(sk, -delta_truesize); - sk_mem_uncharge(sk, delta_truesize); + if (!skb_zcopy_pure(skb)) + sk_mem_uncharge(sk, delta_truesize); } /* Any change of skb->len requires recalculation of tso factor. */ @@ -2295,7 +2296,9 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) + if (unlikely(TCP_SKB_CB(skb)->eor) || + tcp_has_tx_tstamp(skb) || + !skb_pure_zcopy_same(skb, next)) return false; len -= skb->len; -- cgit v1.2.3 From 1aabe578dd86e9f2867c4db4fba9a15f4ba1825d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 2 Nov 2021 15:02:36 -0700 Subject: ethtool: fix ethtool msg len calculation for pause stats ETHTOOL_A_PAUSE_STAT_MAX is the MAX attribute id, so we need to subtract non-stats and add one to get a count (IOW -2+1 == -1). Otherwise we'll see: ethnl cmd 21: calculated reply length 40, but consumed 52 Fixes: 9a27a33027f2 ("ethtool: add standard pause stats") Signed-off-by: Jakub Kicinski Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 3 +++ include/uapi/linux/ethtool_netlink.h | 4 +++- net/ethtool/pause.c | 3 +-- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 1e7bf78cb382..aba348d58ff6 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -10,6 +10,9 @@ #define __ETHTOOL_LINK_MODE_MASK_NWORDS \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) +#define ETHTOOL_PAUSE_STAT_CNT (__ETHTOOL_A_PAUSE_STAT_CNT - \ + ETHTOOL_A_PAUSE_STAT_TX_FRAMES) + enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index ca5fbb59fa42..999777d32dcf 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -411,7 +411,9 @@ enum { ETHTOOL_A_PAUSE_STAT_TX_FRAMES, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, - /* add new constants above here */ + /* add new constants above here + * adjust ETHTOOL_PAUSE_STAT_CNT if adding non-stats! + */ __ETHTOOL_A_PAUSE_STAT_CNT, ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) }; diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 9009f412151e..ee1e5806bc93 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -56,8 +56,7 @@ static int pause_reply_size(const struct ethnl_req_info *req_base, if (req_base->flags & ETHTOOL_FLAG_STATS) n += nla_total_size(0) + /* _PAUSE_STATS */ - nla_total_size_64bit(sizeof(u64)) * - (ETHTOOL_A_PAUSE_STAT_MAX - 2); + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } -- cgit v1.2.3 From 4330fe35b8213e92ff51907b4cb6323be943a9ad Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:01:56 -0600 Subject: nfs: remove unused header Commit 19fcae3d4f2dd ("scsi: remove the SCSI OSD library") deleted the last file that included but left that file behind. It's unused, get rid of it now. Cc: Christoph Hellwig Cc: Trond Myklebust Cc: Anna Schumaker Cc: linux-nfs@vger.kernel.org Signed-off-by: Jonathan Corbet Signed-off-by: Trond Myklebust --- include/linux/pnfs_osd_xdr.h | 317 ------------------------------------------- 1 file changed, 317 deletions(-) delete mode 100644 include/linux/pnfs_osd_xdr.h (limited to 'include/linux') diff --git a/include/linux/pnfs_osd_xdr.h b/include/linux/pnfs_osd_xdr.h deleted file mode 100644 index 17d7d0d20eca..000000000000 --- a/include/linux/pnfs_osd_xdr.h +++ /dev/null @@ -1,317 +0,0 @@ -/* - * pNFS-osd on-the-wire data structures - * - * Copyright (C) 2007 Panasas Inc. [year of first publication] - * All rights reserved. - * - * Benny Halevy - * Boaz Harrosh - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 - * See the file COPYING included with this distribution for more details. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in the - * documentation and/or other materials provided with the distribution. - * 3. Neither the name of the Panasas company nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED - * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE - * DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE - * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR - * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF - * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR - * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ -#ifndef __PNFS_OSD_XDR_H__ -#define __PNFS_OSD_XDR_H__ - -#include - -/* - * draft-ietf-nfsv4-minorversion-22 - * draft-ietf-nfsv4-pnfs-obj-12 - */ - -/* Layout Structure */ - -enum pnfs_osd_raid_algorithm4 { - PNFS_OSD_RAID_0 = 1, - PNFS_OSD_RAID_4 = 2, - PNFS_OSD_RAID_5 = 3, - PNFS_OSD_RAID_PQ = 4 /* Reed-Solomon P+Q */ -}; - -/* struct pnfs_osd_data_map4 { - * uint32_t odm_num_comps; - * length4 odm_stripe_unit; - * uint32_t odm_group_width; - * uint32_t odm_group_depth; - * uint32_t odm_mirror_cnt; - * pnfs_osd_raid_algorithm4 odm_raid_algorithm; - * }; - */ -struct pnfs_osd_data_map { - u32 odm_num_comps; - u64 odm_stripe_unit; - u32 odm_group_width; - u32 odm_group_depth; - u32 odm_mirror_cnt; - u32 odm_raid_algorithm; -}; - -/* struct pnfs_osd_objid4 { - * deviceid4 oid_device_id; - * uint64_t oid_partition_id; - * uint64_t oid_object_id; - * }; - */ -struct pnfs_osd_objid { - struct nfs4_deviceid oid_device_id; - u64 oid_partition_id; - u64 oid_object_id; -}; - -/* For printout. I use: - * kprint("dev(%llx:%llx)", _DEVID_LO(pointer), _DEVID_HI(pointer)); - * BE style - */ -#define _DEVID_LO(oid_device_id) \ - (unsigned long long)be64_to_cpup((__be64 *)(oid_device_id)->data) - -#define _DEVID_HI(oid_device_id) \ - (unsigned long long)be64_to_cpup(((__be64 *)(oid_device_id)->data) + 1) - -enum pnfs_osd_version { - PNFS_OSD_MISSING = 0, - PNFS_OSD_VERSION_1 = 1, - PNFS_OSD_VERSION_2 = 2 -}; - -struct pnfs_osd_opaque_cred { - u32 cred_len; - void *cred; -}; - -enum pnfs_osd_cap_key_sec { - PNFS_OSD_CAP_KEY_SEC_NONE = 0, - PNFS_OSD_CAP_KEY_SEC_SSV = 1, -}; - -/* struct pnfs_osd_object_cred4 { - * pnfs_osd_objid4 oc_object_id; - * pnfs_osd_version4 oc_osd_version; - * pnfs_osd_cap_key_sec4 oc_cap_key_sec; - * opaque oc_capability_key<>; - * opaque oc_capability<>; - * }; - */ -struct pnfs_osd_object_cred { - struct pnfs_osd_objid oc_object_id; - u32 oc_osd_version; - u32 oc_cap_key_sec; - struct pnfs_osd_opaque_cred oc_cap_key; - struct pnfs_osd_opaque_cred oc_cap; -}; - -/* struct pnfs_osd_layout4 { - * pnfs_osd_data_map4 olo_map; - * uint32_t olo_comps_index; - * pnfs_osd_object_cred4 olo_components<>; - * }; - */ -struct pnfs_osd_layout { - struct pnfs_osd_data_map olo_map; - u32 olo_comps_index; - u32 olo_num_comps; - struct pnfs_osd_object_cred *olo_comps; -}; - -/* Device Address */ -enum pnfs_osd_targetid_type { - OBJ_TARGET_ANON = 1, - OBJ_TARGET_SCSI_NAME = 2, - OBJ_TARGET_SCSI_DEVICE_ID = 3, -}; - -/* union pnfs_osd_targetid4 switch (pnfs_osd_targetid_type4 oti_type) { - * case OBJ_TARGET_SCSI_NAME: - * string oti_scsi_name<>; - * - * case OBJ_TARGET_SCSI_DEVICE_ID: - * opaque oti_scsi_device_id<>; - * - * default: - * void; - * }; - * - * union pnfs_osd_targetaddr4 switch (bool ota_available) { - * case TRUE: - * netaddr4 ota_netaddr; - * case FALSE: - * void; - * }; - * - * struct pnfs_osd_deviceaddr4 { - * pnfs_osd_targetid4 oda_targetid; - * pnfs_osd_targetaddr4 oda_targetaddr; - * uint64_t oda_lun; - * opaque oda_systemid<>; - * pnfs_osd_object_cred4 oda_root_obj_cred; - * opaque oda_osdname<>; - * }; - */ -struct pnfs_osd_targetid { - u32 oti_type; - struct nfs4_string oti_scsi_device_id; -}; - -/* struct netaddr4 { - * // see struct rpcb in RFC1833 - * string r_netid<>; // network id - * string r_addr<>; // universal address - * }; - */ -struct pnfs_osd_net_addr { - struct nfs4_string r_netid; - struct nfs4_string r_addr; -}; - -struct pnfs_osd_targetaddr { - u32 ota_available; - struct pnfs_osd_net_addr ota_netaddr; -}; - -struct pnfs_osd_deviceaddr { - struct pnfs_osd_targetid oda_targetid; - struct pnfs_osd_targetaddr oda_targetaddr; - u8 oda_lun[8]; - struct nfs4_string oda_systemid; - struct pnfs_osd_object_cred oda_root_obj_cred; - struct nfs4_string oda_osdname; -}; - -/* LAYOUTCOMMIT: layoutupdate */ - -/* union pnfs_osd_deltaspaceused4 switch (bool dsu_valid) { - * case TRUE: - * int64_t dsu_delta; - * case FALSE: - * void; - * }; - * - * struct pnfs_osd_layoutupdate4 { - * pnfs_osd_deltaspaceused4 olu_delta_space_used; - * bool olu_ioerr_flag; - * }; - */ -struct pnfs_osd_layoutupdate { - u32 dsu_valid; - s64 dsu_delta; - u32 olu_ioerr_flag; -}; - -/* LAYOUTRETURN: I/O Rrror Report */ - -enum pnfs_osd_errno { - PNFS_OSD_ERR_EIO = 1, - PNFS_OSD_ERR_NOT_FOUND = 2, - PNFS_OSD_ERR_NO_SPACE = 3, - PNFS_OSD_ERR_BAD_CRED = 4, - PNFS_OSD_ERR_NO_ACCESS = 5, - PNFS_OSD_ERR_UNREACHABLE = 6, - PNFS_OSD_ERR_RESOURCE = 7 -}; - -/* struct pnfs_osd_ioerr4 { - * pnfs_osd_objid4 oer_component; - * length4 oer_comp_offset; - * length4 oer_comp_length; - * bool oer_iswrite; - * pnfs_osd_errno4 oer_errno; - * }; - */ -struct pnfs_osd_ioerr { - struct pnfs_osd_objid oer_component; - u64 oer_comp_offset; - u64 oer_comp_length; - u32 oer_iswrite; - u32 oer_errno; -}; - -/* OSD XDR Client API */ -/* Layout helpers */ -/* Layout decoding is done in two parts: - * 1. First Call pnfs_osd_xdr_decode_layout_map to read in only the header part - * of the layout. @iter members need not be initialized. - * Returned: - * @layout members are set. (@layout->olo_comps set to NULL). - * - * Zero on success, or negative error if passed xdr is broken. - * - * 2. 2nd Call pnfs_osd_xdr_decode_layout_comp() in a loop until it returns - * false, to decode the next component. - * Returned: - * true if there is more to decode or false if we are done or error. - * - * Example: - * struct pnfs_osd_xdr_decode_layout_iter iter; - * struct pnfs_osd_layout layout; - * struct pnfs_osd_object_cred comp; - * int status; - * - * status = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr); - * if (unlikely(status)) - * goto err; - * while(pnfs_osd_xdr_decode_layout_comp(&comp, &iter, xdr, &status)) { - * // All of @comp strings point to inside the xdr_buffer - * // or scrach buffer. Copy them out to user memory eg. - * copy_single_comp(dest_comp++, &comp); - * } - * if (unlikely(status)) - * goto err; - */ - -struct pnfs_osd_xdr_decode_layout_iter { - unsigned total_comps; - unsigned decoded_comps; -}; - -extern int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout, - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr); - -extern bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp, - struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr, - int *err); - -/* Device Info helpers */ - -/* Note: All strings inside @deviceaddr point to space inside @p. - * @p should stay valid while @deviceaddr is in use. - */ -extern void pnfs_osd_xdr_decode_deviceaddr( - struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p); - -/* layoutupdate (layout_commit) xdr helpers */ -extern int -pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr, - struct pnfs_osd_layoutupdate *lou); - -/* osd_ioerror encoding (layout_return) */ -extern __be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr); -extern void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr); - -#endif /* __PNFS_OSD_XDR_H__ */ -- cgit v1.2.3 From 92f62485b3715882cd397b0cbd80a96d179b86d6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 2 Nov 2021 21:31:22 +0200 Subject: net: dsa: felix: fix broken VLAN-tagged PTP under VLAN-aware bridge Normally it is expected that the dsa_device_ops :: rcv() method finishes parsing the DSA tag and consumes it, then never looks at it again. But commit c0bcf537667c ("net: dsa: ocelot: add hardware timestamping support for Felix") added support for RX timestamping in a very unconventional way. On this switch, a partial timestamp is available in the DSA header, but the driver got away with not parsing that timestamp right away, but instead delayed that parsing for a little longer: dsa_switch_rcv(): nskb = cpu_dp->rcv(skb, dev); <------------- not here -> ocelot_rcv() ... skb = nskb; skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); ... if (dsa_skb_defer_rx_timestamp(p, skb)) <--- but here -> felix_rxtstamp() return 0; When in felix_rxtstamp(), this driver accounted for the fact that eth_type_trans() happened in the meanwhile, so it got a hold of the extraction header again by subtracting (ETH_HLEN + OCELOT_TAG_LEN) bytes from the current skb->data. This worked for quite some time but was quite fragile from the very beginning. Not to mention that having DSA tag parsing split in two different files, under different folders (net/dsa/tag_ocelot.c vs drivers/net/dsa/ocelot/felix.c) made it quite non-obvious for patches to come that they might break this. Finally, the blamed commit does the following: at the end of ocelot_rcv(), it checks whether the skb payload contains a VLAN header. If it does, and this port is under a VLAN-aware bridge, that VLAN ID might not be correct in the sense that the packet might have suffered VLAN rewriting due to TCAM rules (VCAP IS1). So we consume the VLAN ID from the skb payload using __skb_vlan_pop(), and take the classified VLAN ID from the DSA tag, and construct a hwaccel VLAN tag with the classified VLAN, and the skb payload is VLAN-untagged. The big problem is that __skb_vlan_pop() does: memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); __skb_pull(skb, VLAN_HLEN); aka it moves the Ethernet header 4 bytes to the right, and pulls 4 bytes from the skb headroom (effectively also moving skb->data, by definition). So for felix_rxtstamp()'s fragile logic, all bets are off now. Instead of having the "extraction" pointer point to the DSA header, it actually points to 4 bytes _inside_ the extraction header. Corollary, the last 4 bytes of the "extraction" header are in fact 4 stale bytes of the destination MAC address from the Ethernet header, from prior to the __skb_vlan_pop() movement. So of course, RX timestamps are completely bogus when the system is configured in this way. The fix is actually very simple: just don't structure the code like that. For better or worse, the DSA PTP timestamping API does not offer a straightforward way for drivers to present their RX timestamps, but other drivers (sja1105) have established a simple mechanism to carry their RX timestamp from dsa_device_ops :: rcv() all the way to dsa_switch_ops :: port_rxtstamp() and even later. That mechanism is to simply save the partial timestamp to the skb->cb, and complete it later. Question: why don't we simply populate the skb's struct skb_shared_hwtstamps from ocelot_rcv(), and bother with this complication of propagating the timestamp to felix_rxtstamp()? Answer: dsa_switch_ops :: port_rxtstamp() answers the question whether PTP packets need sleepable context to retrieve the full RX timestamp. Currently felix_rxtstamp() answers "no, thanks" to that question, and calls ocelot_ptp_gettime64() from softirq atomic context. This is understandable, since Felix VSC9959 is a PCIe memory-mapped switch, so hardware access does not require sleeping. But the felix driver is preparing for the introduction of other switches where hardware access is over a slow bus like SPI or MDIO: https://lore.kernel.org/lkml/20210814025003.2449143-1-colin.foster@in-advantage.com/ So I would like to keep this code structure, so the rework needed when that driver will need PTP support will be minimal (answer "yes, I need deferred context for this skb's RX timestamp", then the partial timestamp will still be found in the skb->cb. Fixes: ea440cd2d9b2 ("net: dsa: tag_ocelot: use VLAN information from tagging header when available") Reported-by: Po Liu Cc: Yangbo Lu Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 9 +++------ include/linux/dsa/ocelot.h | 1 + net/dsa/tag_ocelot.c | 3 +++ 3 files changed, 7 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 83808e7dbdda..327cc4654806 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1370,12 +1370,12 @@ out: static bool felix_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb, unsigned int type) { - u8 *extraction = skb->data - ETH_HLEN - OCELOT_TAG_LEN; + u32 tstamp_lo = OCELOT_SKB_CB(skb)->tstamp_lo; struct skb_shared_hwtstamps *shhwtstamps; struct ocelot *ocelot = ds->priv; - u32 tstamp_lo, tstamp_hi; struct timespec64 ts; - u64 tstamp, val; + u32 tstamp_hi; + u64 tstamp; /* If the "no XTR IRQ" workaround is in use, tell DSA to defer this skb * for RX timestamping. Then free it, and poll for its copy through @@ -1390,9 +1390,6 @@ static bool felix_rxtstamp(struct dsa_switch *ds, int port, ocelot_ptp_gettime64(&ocelot->ptp_info, &ts); tstamp = ktime_set(ts.tv_sec, ts.tv_nsec); - ocelot_xfh_get_rew_val(extraction, &val); - tstamp_lo = (u32)val; - tstamp_hi = tstamp >> 32; if ((tstamp & 0xffffffff) < tstamp_lo) tstamp_hi--; diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index d42010cf5468..7ee708ad7df2 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -12,6 +12,7 @@ struct ocelot_skb_cb { struct sk_buff *clone; unsigned int ptp_class; /* valid only for clones */ + u32 tstamp_lo; u8 ptp_cmd; u8 ts_id; }; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index cd60b94fc175..de1c849a0a70 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -101,6 +101,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct dsa_port *dp; u8 *extraction; u16 vlan_tpid; + u64 rew_val; /* Revert skb->data by the amount consumed by the DSA master, * so it points to the beginning of the frame. @@ -130,6 +131,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, ocelot_xfh_get_qos_class(extraction, &qos_class); ocelot_xfh_get_tag_type(extraction, &tag_type); ocelot_xfh_get_vlan_tci(extraction, &vlan_tci); + ocelot_xfh_get_rew_val(extraction, &rew_val); skb->dev = dsa_master_find_slave(netdev, 0, src_port); if (!skb->dev) @@ -143,6 +145,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, dsa_default_offload_fwd_mark(skb); skb->priority = qos_class; + OCELOT_SKB_CB(skb)->tstamp_lo = rew_val; /* Ocelot switches copy frames unmodified to the CPU. However, it is * possible for the user to request a VLAN modification through -- cgit v1.2.3 From 6429e46304ac7820eebbea2bf5d73b90c18e0e06 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 28 Oct 2021 10:47:21 +0100 Subject: libfs: Move shmem_exchange to simple_rename_exchange Move shmem_exchange and make it available to other callers. Suggested-by: Miklos Szeredi Signed-off-by: Lorenz Bauer Signed-off-by: Daniel Borkmann Acked-by: Miklos Szeredi Cc: Al Viro Cc: Christian Brauner Cc: Greg Kroah-Hartman Link: https://lore.kernel.org/bpf/20211028094724.59043-2-lmb@cloudflare.com --- fs/libfs.c | 24 ++++++++++++++++++++++++ include/linux/fs.h | 2 ++ mm/shmem.c | 24 +----------------------- 3 files changed, 27 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/libfs.c b/fs/libfs.c index 51b4de3b3447..1cf144dc9ed2 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -448,6 +448,30 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry) } EXPORT_SYMBOL(simple_rmdir); +int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + bool old_is_dir = d_is_dir(old_dentry); + bool new_is_dir = d_is_dir(new_dentry); + + if (old_dir != new_dir && old_is_dir != new_is_dir) { + if (old_is_dir) { + drop_nlink(old_dir); + inc_nlink(new_dir); + } else { + drop_nlink(new_dir); + inc_nlink(old_dir); + } + } + old_dir->i_ctime = old_dir->i_mtime = + new_dir->i_ctime = new_dir->i_mtime = + d_inode(old_dentry)->i_ctime = + d_inode(new_dentry)->i_ctime = current_time(old_dir); + + return 0; +} +EXPORT_SYMBOL_GPL(simple_rename_exchange); + int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) diff --git a/include/linux/fs.h b/include/linux/fs.h index f3cfca5edc9a..bc4e97b82ddd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3383,6 +3383,8 @@ extern int simple_open(struct inode *inode, struct file *file); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); +extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry); extern int simple_rename(struct user_namespace *, struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); diff --git a/mm/shmem.c b/mm/shmem.c index 17e344e26e73..56616aabe0a1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2947,28 +2947,6 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) return shmem_unlink(dir, dentry); } -static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) -{ - bool old_is_dir = d_is_dir(old_dentry); - bool new_is_dir = d_is_dir(new_dentry); - - if (old_dir != new_dir && old_is_dir != new_is_dir) { - if (old_is_dir) { - drop_nlink(old_dir); - inc_nlink(new_dir); - } else { - drop_nlink(new_dir); - inc_nlink(old_dir); - } - } - old_dir->i_ctime = old_dir->i_mtime = - new_dir->i_ctime = new_dir->i_mtime = - d_inode(old_dentry)->i_ctime = - d_inode(new_dentry)->i_ctime = current_time(old_dir); - - return 0; -} - static int shmem_whiteout(struct user_namespace *mnt_userns, struct inode *old_dir, struct dentry *old_dentry) { @@ -3014,7 +2992,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns, return -EINVAL; if (flags & RENAME_EXCHANGE) - return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry); + return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry); if (!simple_empty(new_dentry)) return -ENOTEMPTY; -- cgit v1.2.3 From b18c1ad685d9a6af5189d4cc037a653270a07b4c Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 18 Oct 2021 15:17:25 +0300 Subject: i2c: Allow an ACPI driver to manage the device's power state during probe Enable drivers to tell ACPI that there's no need to power on a device for probe. Drivers should still perform this by themselves if there's a need to. In some cases powering on the device during probe is undesirable, and this change enables a driver to choose what fits best for it. Add a field called "flags" into struct i2c_driver for driver flags, and a flag I2C_DRV_ACPI_WAIVE_D0_PROBE to tell a driver supports probe in ACPI D states other than 0. Signed-off-by: Sakari Ailus Reviewed-by: Tomasz Figa Acked-by: Wolfram Sang Signed-off-by: Rafael J. Wysocki --- drivers/i2c/i2c-core-acpi.c | 10 ++++++++++ drivers/i2c/i2c-core-base.c | 7 ++++--- include/linux/i2c.h | 18 ++++++++++++++++++ 3 files changed, 32 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 546cc935e035..c025919cdaae 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -526,6 +526,16 @@ struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, } EXPORT_SYMBOL_GPL(i2c_acpi_new_device); +bool i2c_acpi_waive_d0_probe(struct device *dev) +{ + struct i2c_driver *driver = to_i2c_driver(dev->driver); + struct acpi_device *adev = ACPI_COMPANION(dev); + + return driver->flags & I2C_DRV_ACPI_WAIVE_D0_PROBE && + adev && adev->power.state_for_enumeration >= adev->power.state; +} +EXPORT_SYMBOL_GPL(i2c_acpi_waive_d0_probe); + #ifdef CONFIG_ACPI_I2C_OPREGION static int acpi_gsb_i2c_read_bytes(struct i2c_client *client, u8 cmd, u8 *data, u8 data_len) diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 54964fbe3f03..f193f9058584 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -551,7 +551,8 @@ static int i2c_device_probe(struct device *dev) if (status < 0) goto err_clear_wakeup_irq; - status = dev_pm_domain_attach(&client->dev, true); + status = dev_pm_domain_attach(&client->dev, + !i2c_acpi_waive_d0_probe(dev)); if (status) goto err_clear_wakeup_irq; @@ -590,7 +591,7 @@ static int i2c_device_probe(struct device *dev) err_release_driver_resources: devres_release_group(&client->dev, client->devres_group_id); err_detach_pm_domain: - dev_pm_domain_detach(&client->dev, true); + dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev)); err_clear_wakeup_irq: dev_pm_clear_wake_irq(&client->dev); device_init_wakeup(&client->dev, false); @@ -621,7 +622,7 @@ static void i2c_device_remove(struct device *dev) devres_release_group(&client->dev, client->devres_group_id); - dev_pm_domain_detach(&client->dev, true); + dev_pm_domain_detach(&client->dev, !i2c_acpi_waive_d0_probe(dev)); if (!pm_runtime_status_suspended(&client->dev) && adap->bus_regulator) regulator_disable(adap->bus_regulator); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 2ce3efbe9198..16119ac1aa97 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -11,6 +11,7 @@ #define _LINUX_I2C_H #include /* for acpi_handle */ +#include #include #include /* for struct device */ #include /* for completion */ @@ -222,6 +223,15 @@ enum i2c_alert_protocol { I2C_PROTOCOL_SMBUS_HOST_NOTIFY, }; +/** + * enum i2c_driver_flags - Flags for an I2C device driver + * + * @I2C_DRV_ACPI_WAIVE_D0_PROBE: Don't put the device in D0 state for probe + */ +enum i2c_driver_flags { + I2C_DRV_ACPI_WAIVE_D0_PROBE = BIT(0), +}; + /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) @@ -236,6 +246,7 @@ enum i2c_alert_protocol { * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) * @clients: List of detected clients we created (for i2c-core use only) + * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. @@ -294,6 +305,8 @@ struct i2c_driver { int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; struct list_head clients; + + u32 flags; }; #define to_i2c_driver(d) container_of(d, struct i2c_driver, driver) @@ -1015,6 +1028,7 @@ u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info); struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); +bool i2c_acpi_waive_d0_probe(struct device *dev); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) @@ -1038,6 +1052,10 @@ static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle ha { return NULL; } +static inline bool i2c_acpi_waive_d0_probe(struct device *dev) +{ + return false; +} #endif /* CONFIG_ACPI */ #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From b82a7df4a7f3841896aaec1ad81e654bc87b5989 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Mon, 18 Oct 2021 15:17:27 +0300 Subject: ACPI: Add a convenience function to tell a device is in D0 state Add a convenience function to tell whether a device is in D0 state, primarily for use in drivers' probe or remove functions on busses where the custom is to power on the device for the duration of both. Returns false on non-ACPI systems. Suggested-by: Mika Westerberg Signed-off-by: Sakari Ailus Reviewed-by: Tomasz Figa Signed-off-by: Rafael J. Wysocki --- drivers/acpi/device_pm.c | 26 ++++++++++++++++++++++++++ include/linux/acpi.h | 5 +++++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 0028b6b51c87..19b33c028f35 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -1400,4 +1400,30 @@ bool acpi_storage_d3(struct device *dev) } EXPORT_SYMBOL_GPL(acpi_storage_d3); +/** + * acpi_dev_state_d0 - Tell if the device is in D0 power state + * @dev: Physical device the ACPI power state of which to check + * + * On a system without ACPI, return true. On a system with ACPI, return true if + * the current ACPI power state of the device is D0, or false otherwise. + * + * Note that the power state of a device is not well-defined after it has been + * passed to acpi_device_set_power() and before that function returns, so it is + * not valid to ask for the ACPI power state of the device in that time frame. + * + * This function is intended to be used in a driver's probe or remove + * function. See Documentation/firmware-guide/acpi/low-power-probe.rst for + * more information. + */ +bool acpi_dev_state_d0(struct device *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(dev); + + if (!adev) + return true; + + return adev->power.state == ACPI_STATE_D0; +} +EXPORT_SYMBOL_GPL(acpi_dev_state_d0); + #endif /* CONFIG_PM */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fbc2146050a4..df70fc27afd7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1016,6 +1016,7 @@ int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); +bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } @@ -1027,6 +1028,10 @@ static inline bool acpi_storage_d3(struct device *dev) { return false; } +static inline bool acpi_dev_state_d0(struct device *dev) +{ + return true; +} #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) -- cgit v1.2.3 From 5c4e0a21fae877a7ef89be6dcc6263ec672372b8 Mon Sep 17 00:00:00 2001 From: Guenter Roeck Date: Tue, 2 Nov 2021 07:24:20 -0700 Subject: string: uninline memcpy_and_pad When building m68k:allmodconfig, recent versions of gcc generate the following error if the length of UTS_RELEASE is less than 8 bytes. In function 'memcpy_and_pad', inlined from 'nvmet_execute_disc_identify' at drivers/nvme/target/discovery.c:268:2: arch/m68k/include/asm/string.h:72:25: error: '__builtin_memcpy' reading 8 bytes from a region of size 7 Discussions around the problem suggest that this only happens if an architecture does not provide strlen(), if -ffreestanding is provided as compiler option, and if CONFIG_FORTIFY_SOURCE=n. All of this is the case for m68k. The exact reasons are unknown, but seem to be related to the ability of the compiler to evaluate the return value of strlen() and the resulting execution flow in memcpy_and_pad(). It would be possible to work around the problem by using sizeof(UTS_RELEASE) instead of strlen(UTS_RELEASE), but that would only postpone the problem until the function is called in a similar way. Uninline memcpy_and_pad() instead to solve the problem for good. Suggested-by: Linus Torvalds Reviewed-by: Geert Uytterhoeven Acked-by: Andy Shevchenko Signed-off-by: Guenter Roeck Signed-off-by: Linus Torvalds --- include/linux/string.h | 19 ++----------------- lib/string_helpers.c | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 5a36608144a9..b6572aeca2f5 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -253,23 +253,8 @@ static inline const char *kbasename(const char *path) #include #endif -/** - * memcpy_and_pad - Copy one buffer to another with padding - * @dest: Where to copy to - * @dest_len: The destination buffer size - * @src: Where to copy from - * @count: The number of bytes to copy - * @pad: Character to use for padding if space is left in destination. - */ -static inline void memcpy_and_pad(void *dest, size_t dest_len, - const void *src, size_t count, int pad) -{ - if (dest_len > count) { - memcpy(dest, src, count); - memset(dest + count, pad, dest_len - count); - } else - memcpy(dest, src, dest_len); -} +void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, + int pad); /** * memset_after - Set a value after a struct member to the end of a struct diff --git a/lib/string_helpers.c b/lib/string_helpers.c index faa9d8e4e2c5..d5d008f5b1d9 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -883,6 +883,26 @@ char *strreplace(char *s, char old, char new) } EXPORT_SYMBOL(strreplace); +/** + * memcpy_and_pad - Copy one buffer to another with padding + * @dest: Where to copy to + * @dest_len: The destination buffer size + * @src: Where to copy from + * @count: The number of bytes to copy + * @pad: Character to use for padding if space is left in destination. + */ +void memcpy_and_pad(void *dest, size_t dest_len, const void *src, size_t count, + int pad) +{ + if (dest_len > count) { + memcpy(dest, src, count); + memset(dest + count, pad, dest_len - count); + } else { + memcpy(dest, src, dest_len); + } +} +EXPORT_SYMBOL(memcpy_and_pad); + #ifdef CONFIG_FORTIFY_SOURCE void fortify_panic(const char *name) { -- cgit v1.2.3 From 00b06da29cf9dc633cdba87acd3f57f4df3fd5c7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 29 Oct 2021 09:14:19 -0500 Subject: signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed As Andy pointed out that there are races between force_sig_info_to_task and sigaction[1] when force_sig_info_task. As Kees discovered[2] ptrace is also able to change these signals. In the case of seeccomp killing a process with a signal it is a security violation to allow the signal to be caught or manipulated. Solve this problem by introducing a new flag SA_IMMUTABLE that prevents sigaction and ptrace from modifying these forced signals. This flag is carefully made kernel internal so that no new ABI is introduced. Longer term I think this can be solved by guaranteeing short circuit delivery of signals in this case. Unfortunately reliable and guaranteed short circuit delivery of these signals is still a ways off from being implemented, tested, and merged. So I have implemented a much simpler alternative for now. [1] https://lkml.kernel.org/r/b5d52d25-7bde-4030-a7b1-7c6f8ab90660@www.fastmail.com [2] https://lkml.kernel.org/r/202110281136.5CE65399A7@keescook Cc: stable@vger.kernel.org Fixes: 307d522f5eb8 ("signal/seccomp: Refactor seccomp signal and coredump generation") Tested-by: Andrea Righi Tested-by: Kees Cook Signed-off-by: "Eric W. Biederman" --- include/linux/signal_types.h | 3 +++ include/uapi/asm-generic/signal-defs.h | 1 + kernel/signal.c | 8 +++++++- 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal_types.h b/include/linux/signal_types.h index 34cb28b8f16c..a70b2bdbf4d9 100644 --- a/include/linux/signal_types.h +++ b/include/linux/signal_types.h @@ -70,6 +70,9 @@ struct ksignal { int sig; }; +/* Used to kill the race between sigaction and forced signals */ +#define SA_IMMUTABLE 0x00800000 + #ifndef __ARCH_UAPI_SA_FLAGS #ifdef SA_RESTORER #define __ARCH_UAPI_SA_FLAGS SA_RESTORER diff --git a/include/uapi/asm-generic/signal-defs.h b/include/uapi/asm-generic/signal-defs.h index fe929e7b77ca..7572f2f46ee8 100644 --- a/include/uapi/asm-generic/signal-defs.h +++ b/include/uapi/asm-generic/signal-defs.h @@ -45,6 +45,7 @@ #define SA_UNSUPPORTED 0x00000400 #define SA_EXPOSE_TAGBITS 0x00000800 /* 0x00010000 used on mips */ +/* 0x00800000 used for internal SA_IMMUTABLE */ /* 0x01000000 used on x86 */ /* 0x02000000 used on x86 */ /* diff --git a/kernel/signal.c b/kernel/signal.c index 6a5e1802b9a2..056a107e3cbc 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1336,6 +1336,7 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t, bool blocked = sigismember(&t->blocked, sig); if (blocked || ignored || sigdfl) { action->sa.sa_handler = SIG_DFL; + action->sa.sa_flags |= SA_IMMUTABLE; if (blocked) { sigdelset(&t->blocked, sig); recalc_sigpending_and_wake(t); @@ -2760,7 +2761,8 @@ relock: if (!signr) break; /* will return 0 */ - if (unlikely(current->ptrace) && signr != SIGKILL) { + if (unlikely(current->ptrace) && (signr != SIGKILL) && + !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { signr = ptrace_signal(signr, &ksig->info); if (!signr) continue; @@ -4110,6 +4112,10 @@ int do_sigaction(int sig, struct k_sigaction *act, struct k_sigaction *oact) k = &p->sighand->action[sig-1]; spin_lock_irq(&p->sighand->siglock); + if (k->sa.sa_flags & SA_IMMUTABLE) { + spin_unlock_irq(&p->sighand->siglock); + return -EINVAL; + } if (oact) *oact = *k; -- cgit v1.2.3 From 2116274af46b12df7cea1dc5698f3cf2f231f8a9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 4 Nov 2021 18:20:37 +0100 Subject: block: add a loff_t cast to bdev_nr_bytes Not really needed as both loff_t and sector_t are always 64-bits wide, but this documents the different types a bit better. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211104172037.531803-1-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 900325aa5d31..1dce769c4596 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -243,7 +243,7 @@ static inline sector_t bdev_nr_sectors(struct block_device *bdev) static inline loff_t bdev_nr_bytes(struct block_device *bdev) { - return bdev_nr_sectors(bdev) << SECTOR_SHIFT; + return (loff_t)bdev_nr_sectors(bdev) << SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) -- cgit v1.2.3 From 0ab8d0f6ae3f1234e38eaedc3ff7c22bfdf7f78c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 29 Sep 2021 17:38:34 +0100 Subject: irqdomain: Make of_phandle_args_to_fwspec() generally available of_phandle_args_to_fwspec() can be generally useful to code extracting a DT of_phandle and using an irq_fwspec to use the hierarchical irqdomain API. Make it visible to the rest of the kernel, including modules. Link: https://lore.kernel.org/r/20210929163847.2807812-2-maz@kernel.org Tested-by: Alyssa Rosenzweig Signed-off-by: Marc Zyngier Signed-off-by: Lorenzo Pieralisi Signed-off-by: Bjorn Helgaas --- include/linux/irqdomain.h | 4 ++++ kernel/irq/irqdomain.c | 6 +++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 23e4ee523576..cfd442316f39 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -64,6 +64,10 @@ struct irq_fwspec { u32 param[IRQ_DOMAIN_IRQ_SPEC_PARAMS]; }; +/* Conversion function from of_phandle_args fields to fwspec */ +void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, + unsigned int count, struct irq_fwspec *fwspec); + /* * Should several domains have the same device node, but serve * different purposes (for example one domain is for PCI/MSI, and the diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 19e83e9b723c..5a698c1f6cc6 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -744,9 +744,8 @@ static int irq_domain_translate(struct irq_domain *d, return 0; } -static void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, - unsigned int count, - struct irq_fwspec *fwspec) +void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, + unsigned int count, struct irq_fwspec *fwspec) { int i; @@ -756,6 +755,7 @@ static void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, for (i = 0; i < count; i++) fwspec->param[i] = args[i]; } +EXPORT_SYMBOL_GPL(of_phandle_args_to_fwspec); unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) { -- cgit v1.2.3 From 439b08c57c3fe1df85cfe9d00accdf9b62cb3275 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 3 Nov 2021 16:51:36 +0100 Subject: Revert "usb: core: hcd: Add support for deferring roothub registration" This reverts commit 58877b0824da15698bd85a0a9dbfa8c354e6ecb7. It has been reported to be causing problems in Arch and Fedora bug reports. Reported-by: Hans de Goede Link: https://bbs.archlinux.org/viewtopic.php?pid=2000956#p2000956 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2019542 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2019576 Link: https://lore.kernel.org/r/42bcbea6-5eb8-16c7-336a-2cb72e71bc36@redhat.com Cc: Mathias Nyman Cc: Chris Chiu Cc: Alan Stern Cc: Kishon Vijay Abraham I Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hcd.c | 29 ++++++----------------------- include/linux/usb/hcd.h | 2 -- 2 files changed, 6 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c index a3311e937847..4d326ee12c36 100644 --- a/drivers/usb/core/hcd.c +++ b/drivers/usb/core/hcd.c @@ -2795,7 +2795,6 @@ int usb_add_hcd(struct usb_hcd *hcd, { int retval; struct usb_device *rhdev; - struct usb_hcd *shared_hcd; if (!hcd->skip_phy_initialization && usb_hcd_is_primary_hcd(hcd)) { hcd->phy_roothub = usb_phy_roothub_alloc(hcd->self.sysdev); @@ -2956,26 +2955,13 @@ int usb_add_hcd(struct usb_hcd *hcd, goto err_hcd_driver_start; } - /* starting here, usbcore will pay attention to the shared HCD roothub */ - shared_hcd = hcd->shared_hcd; - if (!usb_hcd_is_primary_hcd(hcd) && shared_hcd && HCD_DEFER_RH_REGISTER(shared_hcd)) { - retval = register_root_hub(shared_hcd); - if (retval != 0) - goto err_register_root_hub; - - if (shared_hcd->uses_new_polling && HCD_POLL_RH(shared_hcd)) - usb_hcd_poll_rh_status(shared_hcd); - } - /* starting here, usbcore will pay attention to this root hub */ - if (!HCD_DEFER_RH_REGISTER(hcd)) { - retval = register_root_hub(hcd); - if (retval != 0) - goto err_register_root_hub; + retval = register_root_hub(hcd); + if (retval != 0) + goto err_register_root_hub; - if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) - usb_hcd_poll_rh_status(hcd); - } + if (hcd->uses_new_polling && HCD_POLL_RH(hcd)) + usb_hcd_poll_rh_status(hcd); return retval; @@ -3013,7 +2999,6 @@ EXPORT_SYMBOL_GPL(usb_add_hcd); void usb_remove_hcd(struct usb_hcd *hcd) { struct usb_device *rhdev = hcd->self.root_hub; - bool rh_registered; dev_info(hcd->self.controller, "remove, state %x\n", hcd->state); @@ -3024,7 +3009,6 @@ void usb_remove_hcd(struct usb_hcd *hcd) dev_dbg(hcd->self.controller, "roothub graceful disconnect\n"); spin_lock_irq (&hcd_root_hub_lock); - rh_registered = hcd->rh_registered; hcd->rh_registered = 0; spin_unlock_irq (&hcd_root_hub_lock); @@ -3034,8 +3018,7 @@ void usb_remove_hcd(struct usb_hcd *hcd) cancel_work_sync(&hcd->died_work); mutex_lock(&usb_bus_idr_lock); - if (rh_registered) - usb_disconnect(&rhdev); /* Sets rhdev to NULL */ + usb_disconnect(&rhdev); /* Sets rhdev to NULL */ mutex_unlock(&usb_bus_idr_lock); /* diff --git a/include/linux/usb/hcd.h b/include/linux/usb/hcd.h index 2c1fc9212cf2..548a028f2dab 100644 --- a/include/linux/usb/hcd.h +++ b/include/linux/usb/hcd.h @@ -124,7 +124,6 @@ struct usb_hcd { #define HCD_FLAG_RH_RUNNING 5 /* root hub is running? */ #define HCD_FLAG_DEAD 6 /* controller has died? */ #define HCD_FLAG_INTF_AUTHORIZED 7 /* authorize interfaces? */ -#define HCD_FLAG_DEFER_RH_REGISTER 8 /* Defer roothub registration */ /* The flags can be tested using these macros; they are likely to * be slightly faster than test_bit(). @@ -135,7 +134,6 @@ struct usb_hcd { #define HCD_WAKEUP_PENDING(hcd) ((hcd)->flags & (1U << HCD_FLAG_WAKEUP_PENDING)) #define HCD_RH_RUNNING(hcd) ((hcd)->flags & (1U << HCD_FLAG_RH_RUNNING)) #define HCD_DEAD(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEAD)) -#define HCD_DEFER_RH_REGISTER(hcd) ((hcd)->flags & (1U << HCD_FLAG_DEFER_RH_REGISTER)) /* * Specifies if interfaces are authorized by default -- cgit v1.2.3 From 27d9a4d69433af1827a764fe235866d5d5501fdb Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 9 Sep 2021 11:48:48 +0200 Subject: pwm: Add might_sleep() annotations for !CONFIG_PWM API functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The normal implementations of these functions make use of mutexes. To make it obvious that these functions might sleep also add annotations to the dummy implementations in the !CONFIG_PWM case. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- include/linux/pwm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 725c9b784e60..515e33978e97 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -429,11 +429,13 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev, #else static inline struct pwm_device *pwm_request(int pwm_id, const char *label) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline void pwm_free(struct pwm_device *pwm) { + might_sleep(); } static inline int pwm_apply_state(struct pwm_device *pwm, @@ -493,12 +495,14 @@ static inline struct pwm_device *pwm_request_from_chip(struct pwm_chip *chip, unsigned int index, const char *label) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline struct pwm_device *pwm_get(struct device *dev, const char *consumer) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -506,16 +510,19 @@ static inline struct pwm_device *of_pwm_get(struct device *dev, struct device_node *np, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } static inline void pwm_put(struct pwm_device *pwm) { + might_sleep(); } static inline struct pwm_device *devm_pwm_get(struct device *dev, const char *consumer) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -523,6 +530,7 @@ static inline struct pwm_device *devm_of_pwm_get(struct device *dev, struct device_node *np, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } @@ -530,6 +538,7 @@ static inline struct pwm_device * devm_fwnode_pwm_get(struct device *dev, struct fwnode_handle *fwnode, const char *con_id) { + might_sleep(); return ERR_PTR(-ENODEV); } #endif -- cgit v1.2.3 From 4ad91a227817ae48f931595d1101fc7100073ce9 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 9 Sep 2021 11:48:49 +0200 Subject: pwm: Make it explicit that pwm_apply_state() might sleep MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At least some implementations sleep. So mark pwm_apply_state() with a might_sleep() to make callers aware. In the worst case this uncovers a valid atomic user, then we revert this patch and at least gained some more knowledge and then can work on a concept similar to gpio_get_value/gpio_get_value_cansleep. Signed-off-by: Uwe Kleine-König Signed-off-by: Thierry Reding --- drivers/pwm/core.c | 9 +++++++++ include/linux/pwm.h | 4 ++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c index 4527f09a5c50..fb04a439462c 100644 --- a/drivers/pwm/core.c +++ b/drivers/pwm/core.c @@ -532,6 +532,15 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) struct pwm_chip *chip; int err; + /* + * Some lowlevel driver's implementations of .apply() make use of + * mutexes, also with some drivers only returning when the new + * configuration is active calling pwm_apply_state() from atomic context + * is a bad idea. So make it explicit that calling this function might + * sleep. + */ + might_sleep(); + if (!pwm || !state || !state->period || state->duty_cycle > state->period) return -EINVAL; diff --git a/include/linux/pwm.h b/include/linux/pwm.h index 515e33978e97..e6dac95e4960 100644 --- a/include/linux/pwm.h +++ b/include/linux/pwm.h @@ -441,6 +441,7 @@ static inline void pwm_free(struct pwm_device *pwm) static inline int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state) { + might_sleep(); return -ENOTSUPP; } @@ -452,6 +453,7 @@ static inline int pwm_adjust_config(struct pwm_device *pwm) static inline int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns) { + might_sleep(); return -EINVAL; } @@ -464,11 +466,13 @@ static inline int pwm_capture(struct pwm_device *pwm, static inline int pwm_enable(struct pwm_device *pwm) { + might_sleep(); return -EINVAL; } static inline void pwm_disable(struct pwm_device *pwm) { + might_sleep(); } static inline int pwm_set_chip_data(struct pwm_device *pwm, void *data) -- cgit v1.2.3 From c9a20383578abd8f7fb8ba88f4c6d25b47924c34 Mon Sep 17 00:00:00 2001 From: Carlos de Paula Date: Mon, 30 Aug 2021 16:53:45 -0300 Subject: mfd: da9063: Add support for latest EA silicon revision This update adds new regmap to support the latest EA silicon which will be selected based on the chip and variant information read from the device. Signed-off-by: Carlos de Paula Reviewed-by: Adam Thomson Signed-off-by: Lee Jones --- drivers/mfd/da9063-i2c.c | 2 ++ include/linux/mfd/da9063/core.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/drivers/mfd/da9063-i2c.c b/drivers/mfd/da9063-i2c.c index 4b7f707b7952..343ed6e96d87 100644 --- a/drivers/mfd/da9063-i2c.c +++ b/drivers/mfd/da9063-i2c.c @@ -391,6 +391,7 @@ static int da9063_i2c_probe(struct i2c_client *i2c, &da9063_bb_da_volatile_table; break; case PMIC_DA9063_DA: + case PMIC_DA9063_EA: da9063_regmap_config.rd_table = &da9063_da_readable_table; da9063_regmap_config.wr_table = @@ -416,6 +417,7 @@ static int da9063_i2c_probe(struct i2c_client *i2c, &da9063l_bb_da_volatile_table; break; case PMIC_DA9063_DA: + case PMIC_DA9063_EA: da9063_regmap_config.rd_table = &da9063l_da_readable_table; da9063_regmap_config.wr_table = diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h index fa7a43f02f27..8db52324f416 100644 --- a/include/linux/mfd/da9063/core.h +++ b/include/linux/mfd/da9063/core.h @@ -36,6 +36,7 @@ enum da9063_variant_codes { PMIC_DA9063_BB = 0x5, PMIC_DA9063_CA = 0x6, PMIC_DA9063_DA = 0x7, + PMIC_DA9063_EA = 0x8, }; /* Interrupts */ -- cgit v1.2.3 From ec14d90dee8ec6960324ae9f1116103efcde8a52 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Tue, 12 Oct 2021 17:39:35 +0200 Subject: mfd: tps65912: Make tps65912_device_exit() return void MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Up to now tps65912_device_exit() returns zero unconditionally. Make it return void instead which makes it easier to see in the callers that there is no error to handle. Also the return value of i2c and spi remove callbacks is ignored anyway. Signed-off-by: Uwe Kleine-König Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211012153945.2651412-11-u.kleine-koenig@pengutronix.de --- drivers/mfd/tps65912-core.c | 4 +--- drivers/mfd/tps65912-i2c.c | 4 +++- drivers/mfd/tps65912-spi.c | 4 +++- include/linux/mfd/tps65912.h | 2 +- 4 files changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/mfd/tps65912-core.c b/drivers/mfd/tps65912-core.c index b55b1d5d6955..c282a05e7146 100644 --- a/drivers/mfd/tps65912-core.c +++ b/drivers/mfd/tps65912-core.c @@ -115,11 +115,9 @@ int tps65912_device_init(struct tps65912 *tps) } EXPORT_SYMBOL_GPL(tps65912_device_init); -int tps65912_device_exit(struct tps65912 *tps) +void tps65912_device_exit(struct tps65912 *tps) { regmap_del_irq_chip(tps->irq, tps->irq_data); - - return 0; } EXPORT_SYMBOL_GPL(tps65912_device_exit); diff --git a/drivers/mfd/tps65912-i2c.c b/drivers/mfd/tps65912-i2c.c index f7c22ea7b36c..06eb2784d322 100644 --- a/drivers/mfd/tps65912-i2c.c +++ b/drivers/mfd/tps65912-i2c.c @@ -55,7 +55,9 @@ static int tps65912_i2c_remove(struct i2c_client *client) { struct tps65912 *tps = i2c_get_clientdata(client); - return tps65912_device_exit(tps); + tps65912_device_exit(tps); + + return 0; } static const struct i2c_device_id tps65912_i2c_id_table[] = { diff --git a/drivers/mfd/tps65912-spi.c b/drivers/mfd/tps65912-spi.c index 21a8d6ac5c4a..d701926aa46e 100644 --- a/drivers/mfd/tps65912-spi.c +++ b/drivers/mfd/tps65912-spi.c @@ -54,7 +54,9 @@ static int tps65912_spi_remove(struct spi_device *spi) { struct tps65912 *tps = spi_get_drvdata(spi); - return tps65912_device_exit(tps); + tps65912_device_exit(tps); + + return 0; } static const struct spi_device_id tps65912_spi_id_table[] = { diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h index 7943e413deae..8a61386cb8c1 100644 --- a/include/linux/mfd/tps65912.h +++ b/include/linux/mfd/tps65912.h @@ -322,6 +322,6 @@ struct tps65912 { extern const struct regmap_config tps65912_regmap_config; int tps65912_device_init(struct tps65912 *tps); -int tps65912_device_exit(struct tps65912 *tps); +void tps65912_device_exit(struct tps65912 *tps); #endif /* __LINUX_MFD_TPS65912_H */ -- cgit v1.2.3 From 0cee0416563d7cac807c8f092941f3e37ede05db Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Tue, 19 Oct 2021 16:59:11 +0200 Subject: mfd: max77686: Correct tab-based alignment of register addresses Some lines have an extra tab, remove them for proper visual alignment as present on the rest of this file. Signed-off-by: Luca Ceresoli Reviewed-by: Krzysztof Kozlowski Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211019145919.7327-2-luca@lucaceresoli.net --- include/linux/mfd/max77686-private.h | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h index 833e578e051e..b1482b3cf353 100644 --- a/include/linux/mfd/max77686-private.h +++ b/include/linux/mfd/max77686-private.h @@ -133,35 +133,35 @@ enum max77686_pmic_reg { /* Reserved: 0x7A-0x7D */ MAX77686_REG_BBAT_CHG = 0x7E, - MAX77686_REG_32KHZ = 0x7F, + MAX77686_REG_32KHZ = 0x7F, MAX77686_REG_PMIC_END = 0x80, }; enum max77686_rtc_reg { - MAX77686_RTC_INT = 0x00, - MAX77686_RTC_INTM = 0x01, + MAX77686_RTC_INT = 0x00, + MAX77686_RTC_INTM = 0x01, MAX77686_RTC_CONTROLM = 0x02, MAX77686_RTC_CONTROL = 0x03, MAX77686_RTC_UPDATE0 = 0x04, /* Reserved: 0x5 */ MAX77686_WTSR_SMPL_CNTL = 0x06, - MAX77686_RTC_SEC = 0x07, - MAX77686_RTC_MIN = 0x08, - MAX77686_RTC_HOUR = 0x09, + MAX77686_RTC_SEC = 0x07, + MAX77686_RTC_MIN = 0x08, + MAX77686_RTC_HOUR = 0x09, MAX77686_RTC_WEEKDAY = 0x0A, - MAX77686_RTC_MONTH = 0x0B, - MAX77686_RTC_YEAR = 0x0C, - MAX77686_RTC_DATE = 0x0D, - MAX77686_ALARM1_SEC = 0x0E, - MAX77686_ALARM1_MIN = 0x0F, + MAX77686_RTC_MONTH = 0x0B, + MAX77686_RTC_YEAR = 0x0C, + MAX77686_RTC_DATE = 0x0D, + MAX77686_ALARM1_SEC = 0x0E, + MAX77686_ALARM1_MIN = 0x0F, MAX77686_ALARM1_HOUR = 0x10, MAX77686_ALARM1_WEEKDAY = 0x11, MAX77686_ALARM1_MONTH = 0x12, MAX77686_ALARM1_YEAR = 0x13, MAX77686_ALARM1_DATE = 0x14, - MAX77686_ALARM2_SEC = 0x15, - MAX77686_ALARM2_MIN = 0x16, + MAX77686_ALARM2_SEC = 0x15, + MAX77686_ALARM2_MIN = 0x16, MAX77686_ALARM2_HOUR = 0x17, MAX77686_ALARM2_WEEKDAY = 0x18, MAX77686_ALARM2_MONTH = 0x19, -- cgit v1.2.3 From b20cd02f7fef68ae395d9df0a9fb9edcf414b5a2 Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 21 Oct 2021 22:22:58 +0300 Subject: mfd: tps80031: Remove driver Driver was upstreamed in 2013 and never got a user, remove it. Signed-off-by: Dmitry Osipenko Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211021192258.21968-4-digetx@gmail.com --- drivers/mfd/Kconfig | 14 - drivers/mfd/Makefile | 1 - drivers/mfd/tps80031.c | 526 ----------------------------------- include/linux/mfd/tps80031.h | 637 ------------------------------------------- 4 files changed, 1178 deletions(-) delete mode 100644 drivers/mfd/tps80031.c delete mode 100644 include/linux/mfd/tps80031.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index f99334fa0ae6..bc75156dd96f 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1624,20 +1624,6 @@ config MFD_TPS65912_SPI If you say yes here you get support for the TPS65912 series of PM chips with SPI interface. -config MFD_TPS80031 - bool "TI TPS80031/TPS80032 Power Management chips" - depends on I2C=y - select MFD_CORE - select REGMAP_I2C - select REGMAP_IRQ - help - If you say yes here you get support for the Texas Instruments - TPS80031/ TPS80032 Fully Integrated Power Management with Power - Path and Battery Charger. The device provides five configurable - step-down converters, 11 general purpose LDOs, USB OTG Module, - ADC, RTC, 2 PWM, System Voltage Regulator/Battery Charger with - Power Path from USB, 32K clock generator. - config TWL4030_CORE bool "TI TWL4030/TWL5030/TWL6030/TPS659x0 Support" depends on I2C=y diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 2ba6646e874c..0b1b629aef3e 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -105,7 +105,6 @@ obj-$(CONFIG_MFD_TPS65910) += tps65910.o obj-$(CONFIG_MFD_TPS65912) += tps65912-core.o obj-$(CONFIG_MFD_TPS65912_I2C) += tps65912-i2c.o obj-$(CONFIG_MFD_TPS65912_SPI) += tps65912-spi.o -obj-$(CONFIG_MFD_TPS80031) += tps80031.o obj-$(CONFIG_MENELAUS) += menelaus.o obj-$(CONFIG_TWL4030_CORE) += twl-core.o twl4030-irq.o twl6030-irq.o diff --git a/drivers/mfd/tps80031.c b/drivers/mfd/tps80031.c deleted file mode 100644 index 3c4e62c3406a..000000000000 --- a/drivers/mfd/tps80031.c +++ /dev/null @@ -1,526 +0,0 @@ -/* - * tps80031.c -- TI TPS80031/TPS80032 mfd core driver. - * - * MFD core driver for TI TPS80031/TPS80032 Fully Integrated - * Power Management with Power Path and Battery Charger - * - * Copyright (c) 2012, NVIDIA Corporation. - * - * Author: Laxman Dewangan - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind, - * whether express or implied; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - * 02111-1307, USA - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static const struct resource tps80031_rtc_resources[] = { - DEFINE_RES_IRQ(TPS80031_INT_RTC_ALARM), -}; - -/* TPS80031 sub mfd devices */ -static const struct mfd_cell tps80031_cell[] = { - { - .name = "tps80031-pmic", - }, - { - .name = "tps80031-clock", - }, - { - .name = "tps80031-rtc", - .num_resources = ARRAY_SIZE(tps80031_rtc_resources), - .resources = tps80031_rtc_resources, - }, - { - .name = "tps80031-gpadc", - }, - { - .name = "tps80031-fuel-gauge", - }, - { - .name = "tps80031-charger", - }, -}; - -static int tps80031_slave_address[TPS80031_NUM_SLAVES] = { - TPS80031_I2C_ID0_ADDR, - TPS80031_I2C_ID1_ADDR, - TPS80031_I2C_ID2_ADDR, - TPS80031_I2C_ID3_ADDR, -}; - -struct tps80031_pupd_data { - u8 reg; - u8 pullup_bit; - u8 pulldown_bit; -}; - -#define TPS80031_IRQ(_reg, _mask) \ - { \ - .reg_offset = (TPS80031_INT_MSK_LINE_##_reg) - \ - TPS80031_INT_MSK_LINE_A, \ - .mask = BIT(_mask), \ - } - -static const struct regmap_irq tps80031_main_irqs[] = { - [TPS80031_INT_PWRON] = TPS80031_IRQ(A, 0), - [TPS80031_INT_RPWRON] = TPS80031_IRQ(A, 1), - [TPS80031_INT_SYS_VLOW] = TPS80031_IRQ(A, 2), - [TPS80031_INT_RTC_ALARM] = TPS80031_IRQ(A, 3), - [TPS80031_INT_RTC_PERIOD] = TPS80031_IRQ(A, 4), - [TPS80031_INT_HOT_DIE] = TPS80031_IRQ(A, 5), - [TPS80031_INT_VXX_SHORT] = TPS80031_IRQ(A, 6), - [TPS80031_INT_SPDURATION] = TPS80031_IRQ(A, 7), - [TPS80031_INT_WATCHDOG] = TPS80031_IRQ(B, 0), - [TPS80031_INT_BAT] = TPS80031_IRQ(B, 1), - [TPS80031_INT_SIM] = TPS80031_IRQ(B, 2), - [TPS80031_INT_MMC] = TPS80031_IRQ(B, 3), - [TPS80031_INT_RES] = TPS80031_IRQ(B, 4), - [TPS80031_INT_GPADC_RT] = TPS80031_IRQ(B, 5), - [TPS80031_INT_GPADC_SW2_EOC] = TPS80031_IRQ(B, 6), - [TPS80031_INT_CC_AUTOCAL] = TPS80031_IRQ(B, 7), - [TPS80031_INT_ID_WKUP] = TPS80031_IRQ(C, 0), - [TPS80031_INT_VBUSS_WKUP] = TPS80031_IRQ(C, 1), - [TPS80031_INT_ID] = TPS80031_IRQ(C, 2), - [TPS80031_INT_VBUS] = TPS80031_IRQ(C, 3), - [TPS80031_INT_CHRG_CTRL] = TPS80031_IRQ(C, 4), - [TPS80031_INT_EXT_CHRG] = TPS80031_IRQ(C, 5), - [TPS80031_INT_INT_CHRG] = TPS80031_IRQ(C, 6), - [TPS80031_INT_RES2] = TPS80031_IRQ(C, 7), -}; - -static struct regmap_irq_chip tps80031_irq_chip = { - .name = "tps80031", - .irqs = tps80031_main_irqs, - .num_irqs = ARRAY_SIZE(tps80031_main_irqs), - .num_regs = 3, - .status_base = TPS80031_INT_STS_A, - .mask_base = TPS80031_INT_MSK_LINE_A, -}; - -#define PUPD_DATA(_reg, _pulldown_bit, _pullup_bit) \ - { \ - .reg = TPS80031_CFG_INPUT_PUPD##_reg, \ - .pulldown_bit = _pulldown_bit, \ - .pullup_bit = _pullup_bit, \ - } - -static const struct tps80031_pupd_data tps80031_pupds[] = { - [TPS80031_PREQ1] = PUPD_DATA(1, BIT(0), BIT(1)), - [TPS80031_PREQ2A] = PUPD_DATA(1, BIT(2), BIT(3)), - [TPS80031_PREQ2B] = PUPD_DATA(1, BIT(4), BIT(5)), - [TPS80031_PREQ2C] = PUPD_DATA(1, BIT(6), BIT(7)), - [TPS80031_PREQ3] = PUPD_DATA(2, BIT(0), BIT(1)), - [TPS80031_NRES_WARM] = PUPD_DATA(2, 0, BIT(2)), - [TPS80031_PWM_FORCE] = PUPD_DATA(2, BIT(5), 0), - [TPS80031_CHRG_EXT_CHRG_STATZ] = PUPD_DATA(2, 0, BIT(6)), - [TPS80031_SIM] = PUPD_DATA(3, BIT(0), BIT(1)), - [TPS80031_MMC] = PUPD_DATA(3, BIT(2), BIT(3)), - [TPS80031_GPADC_START] = PUPD_DATA(3, BIT(4), 0), - [TPS80031_DVSI2C_SCL] = PUPD_DATA(4, 0, BIT(0)), - [TPS80031_DVSI2C_SDA] = PUPD_DATA(4, 0, BIT(1)), - [TPS80031_CTLI2C_SCL] = PUPD_DATA(4, 0, BIT(2)), - [TPS80031_CTLI2C_SDA] = PUPD_DATA(4, 0, BIT(3)), -}; -static struct tps80031 *tps80031_power_off_dev; - -int tps80031_ext_power_req_config(struct device *dev, - unsigned long ext_ctrl_flag, int preq_bit, - int state_reg_add, int trans_reg_add) -{ - u8 res_ass_reg = 0; - int preq_mask_bit = 0; - int ret; - - if (!(ext_ctrl_flag & TPS80031_EXT_PWR_REQ)) - return 0; - - if (ext_ctrl_flag & TPS80031_PWR_REQ_INPUT_PREQ1) { - res_ass_reg = TPS80031_PREQ1_RES_ASS_A + (preq_bit >> 3); - preq_mask_bit = 5; - } else if (ext_ctrl_flag & TPS80031_PWR_REQ_INPUT_PREQ2) { - res_ass_reg = TPS80031_PREQ2_RES_ASS_A + (preq_bit >> 3); - preq_mask_bit = 6; - } else if (ext_ctrl_flag & TPS80031_PWR_REQ_INPUT_PREQ3) { - res_ass_reg = TPS80031_PREQ3_RES_ASS_A + (preq_bit >> 3); - preq_mask_bit = 7; - } - - /* Configure REQ_ASS registers */ - ret = tps80031_set_bits(dev, TPS80031_SLAVE_ID1, res_ass_reg, - BIT(preq_bit & 0x7)); - if (ret < 0) { - dev_err(dev, "reg 0x%02x setbit failed, err = %d\n", - res_ass_reg, ret); - return ret; - } - - /* Unmask the PREQ */ - ret = tps80031_clr_bits(dev, TPS80031_SLAVE_ID1, - TPS80031_PHOENIX_MSK_TRANSITION, BIT(preq_mask_bit)); - if (ret < 0) { - dev_err(dev, "reg 0x%02x clrbit failed, err = %d\n", - TPS80031_PHOENIX_MSK_TRANSITION, ret); - return ret; - } - - /* Switch regulator control to resource now */ - if (ext_ctrl_flag & (TPS80031_PWR_REQ_INPUT_PREQ2 | - TPS80031_PWR_REQ_INPUT_PREQ3)) { - ret = tps80031_update(dev, TPS80031_SLAVE_ID1, state_reg_add, - 0x0, TPS80031_STATE_MASK); - if (ret < 0) - dev_err(dev, "reg 0x%02x update failed, err = %d\n", - state_reg_add, ret); - } else { - ret = tps80031_update(dev, TPS80031_SLAVE_ID1, trans_reg_add, - TPS80031_TRANS_SLEEP_OFF, - TPS80031_TRANS_SLEEP_MASK); - if (ret < 0) - dev_err(dev, "reg 0x%02x update failed, err = %d\n", - trans_reg_add, ret); - } - return ret; -} -EXPORT_SYMBOL_GPL(tps80031_ext_power_req_config); - -static void tps80031_power_off(void) -{ - dev_info(tps80031_power_off_dev->dev, "switching off PMU\n"); - tps80031_write(tps80031_power_off_dev->dev, TPS80031_SLAVE_ID1, - TPS80031_PHOENIX_DEV_ON, TPS80031_DEVOFF); -} - -static void tps80031_pupd_init(struct tps80031 *tps80031, - struct tps80031_platform_data *pdata) -{ - struct tps80031_pupd_init_data *pupd_init_data = pdata->pupd_init_data; - int data_size = pdata->pupd_init_data_size; - int i; - - for (i = 0; i < data_size; ++i) { - struct tps80031_pupd_init_data *pupd_init = &pupd_init_data[i]; - const struct tps80031_pupd_data *pupd = - &tps80031_pupds[pupd_init->input_pin]; - u8 update_value = 0; - u8 update_mask = pupd->pulldown_bit | pupd->pullup_bit; - - if (pupd_init->setting == TPS80031_PUPD_PULLDOWN) - update_value = pupd->pulldown_bit; - else if (pupd_init->setting == TPS80031_PUPD_PULLUP) - update_value = pupd->pullup_bit; - - tps80031_update(tps80031->dev, TPS80031_SLAVE_ID1, pupd->reg, - update_value, update_mask); - } -} - -static int tps80031_init_ext_control(struct tps80031 *tps80031, - struct tps80031_platform_data *pdata) -{ - struct device *dev = tps80031->dev; - int ret; - int i; - - /* Clear all external control for this rail */ - for (i = 0; i < 9; ++i) { - ret = tps80031_write(dev, TPS80031_SLAVE_ID1, - TPS80031_PREQ1_RES_ASS_A + i, 0); - if (ret < 0) { - dev_err(dev, "reg 0x%02x write failed, err = %d\n", - TPS80031_PREQ1_RES_ASS_A + i, ret); - return ret; - } - } - - /* Mask the PREQ */ - ret = tps80031_set_bits(dev, TPS80031_SLAVE_ID1, - TPS80031_PHOENIX_MSK_TRANSITION, 0x7 << 5); - if (ret < 0) { - dev_err(dev, "reg 0x%02x set_bits failed, err = %d\n", - TPS80031_PHOENIX_MSK_TRANSITION, ret); - return ret; - } - return ret; -} - -static int tps80031_irq_init(struct tps80031 *tps80031, int irq, int irq_base) -{ - struct device *dev = tps80031->dev; - int i, ret; - - /* - * The MASK register used for updating status register when - * interrupt occurs and LINE register used to pass the status - * to actual interrupt line. As per datasheet: - * When INT_MSK_LINE [i] is set to 1, the associated interrupt - * number i is INT line masked, which means that no interrupt is - * generated on the INT line. - * When INT_MSK_LINE [i] is set to 0, the associated interrupt - * number i is line enabled: An interrupt is generated on the - * INT line. - * In any case, the INT_STS [i] status bit may or may not be updated, - * only linked to the INT_MSK_STS [i] configuration register bit. - * - * When INT_MSK_STS [i] is set to 1, the associated interrupt number - * i is status masked, which means that no interrupt is stored in - * the INT_STS[i] status bit. Note that no interrupt number i is - * generated on the INT line, even if the INT_MSK_LINE [i] register - * bit is set to 0. - * When INT_MSK_STS [i] is set to 0, the associated interrupt number i - * is status enabled: An interrupt status is updated in the INT_STS [i] - * register. The interrupt may or may not be generated on the INT line, - * depending on the INT_MSK_LINE [i] configuration register bit. - */ - for (i = 0; i < 3; i++) - tps80031_write(dev, TPS80031_SLAVE_ID2, - TPS80031_INT_MSK_STS_A + i, 0x00); - - ret = regmap_add_irq_chip(tps80031->regmap[TPS80031_SLAVE_ID2], irq, - IRQF_ONESHOT, irq_base, - &tps80031_irq_chip, &tps80031->irq_data); - if (ret < 0) { - dev_err(dev, "add irq failed, err = %d\n", ret); - return ret; - } - return ret; -} - -static bool rd_wr_reg_id0(struct device *dev, unsigned int reg) -{ - switch (reg) { - case TPS80031_SMPS1_CFG_FORCE ... TPS80031_SMPS2_CFG_VOLTAGE: - return true; - default: - return false; - } -} - -static bool rd_wr_reg_id1(struct device *dev, unsigned int reg) -{ - switch (reg) { - case TPS80031_SECONDS_REG ... TPS80031_RTC_RESET_STATUS_REG: - case TPS80031_VALIDITY0 ... TPS80031_VALIDITY7: - case TPS80031_PHOENIX_START_CONDITION ... TPS80031_KEY_PRESS_DUR_CFG: - case TPS80031_SMPS4_CFG_TRANS ... TPS80031_SMPS3_CFG_VOLTAGE: - case TPS80031_BROADCAST_ADDR_ALL ... TPS80031_BROADCAST_ADDR_CLK_RST: - case TPS80031_VANA_CFG_TRANS ... TPS80031_LDO7_CFG_VOLTAGE: - case TPS80031_REGEN1_CFG_TRANS ... TPS80031_TMP_CFG_STATE: - case TPS80031_PREQ1_RES_ASS_A ... TPS80031_PREQ3_RES_ASS_C: - case TPS80031_SMPS_OFFSET ... TPS80031_BATDEBOUNCING: - case TPS80031_CFG_INPUT_PUPD1 ... TPS80031_CFG_SMPS_PD: - case TPS80031_BACKUP_REG: - return true; - default: - return false; - } -} - -static bool is_volatile_reg_id1(struct device *dev, unsigned int reg) -{ - switch (reg) { - case TPS80031_SMPS4_CFG_TRANS ... TPS80031_SMPS3_CFG_VOLTAGE: - case TPS80031_VANA_CFG_TRANS ... TPS80031_LDO7_CFG_VOLTAGE: - case TPS80031_REGEN1_CFG_TRANS ... TPS80031_TMP_CFG_STATE: - case TPS80031_PREQ1_RES_ASS_A ... TPS80031_PREQ3_RES_ASS_C: - case TPS80031_SMPS_OFFSET ... TPS80031_BATDEBOUNCING: - case TPS80031_CFG_INPUT_PUPD1 ... TPS80031_CFG_SMPS_PD: - return true; - default: - return false; - } -} - -static bool rd_wr_reg_id2(struct device *dev, unsigned int reg) -{ - switch (reg) { - case TPS80031_USB_VENDOR_ID_LSB ... TPS80031_USB_OTG_REVISION: - case TPS80031_GPADC_CTRL ... TPS80031_CTRL_P1: - case TPS80031_RTCH0_LSB ... TPS80031_GPCH0_MSB: - case TPS80031_TOGGLE1 ... TPS80031_VIBMODE: - case TPS80031_PWM1ON ... TPS80031_PWM2OFF: - case TPS80031_FG_REG_00 ... TPS80031_FG_REG_11: - case TPS80031_INT_STS_A ... TPS80031_INT_MSK_STS_C: - case TPS80031_CONTROLLER_CTRL2 ... TPS80031_LED_PWM_CTRL2: - return true; - default: - return false; - } -} - -static bool rd_wr_reg_id3(struct device *dev, unsigned int reg) -{ - switch (reg) { - case TPS80031_GPADC_TRIM0 ... TPS80031_GPADC_TRIM18: - return true; - default: - return false; - } -} - -static const struct regmap_config tps80031_regmap_configs[] = { - { - .reg_bits = 8, - .val_bits = 8, - .writeable_reg = rd_wr_reg_id0, - .readable_reg = rd_wr_reg_id0, - .max_register = TPS80031_MAX_REGISTER, - }, - { - .reg_bits = 8, - .val_bits = 8, - .writeable_reg = rd_wr_reg_id1, - .readable_reg = rd_wr_reg_id1, - .volatile_reg = is_volatile_reg_id1, - .max_register = TPS80031_MAX_REGISTER, - }, - { - .reg_bits = 8, - .val_bits = 8, - .writeable_reg = rd_wr_reg_id2, - .readable_reg = rd_wr_reg_id2, - .max_register = TPS80031_MAX_REGISTER, - }, - { - .reg_bits = 8, - .val_bits = 8, - .writeable_reg = rd_wr_reg_id3, - .readable_reg = rd_wr_reg_id3, - .max_register = TPS80031_MAX_REGISTER, - }, -}; - -static int tps80031_probe(struct i2c_client *client, - const struct i2c_device_id *id) -{ - struct tps80031_platform_data *pdata = dev_get_platdata(&client->dev); - struct tps80031 *tps80031; - int ret; - uint8_t es_version; - uint8_t ep_ver; - int i; - - if (!pdata) { - dev_err(&client->dev, "tps80031 requires platform data\n"); - return -EINVAL; - } - - tps80031 = devm_kzalloc(&client->dev, sizeof(*tps80031), GFP_KERNEL); - if (!tps80031) - return -ENOMEM; - - for (i = 0; i < TPS80031_NUM_SLAVES; i++) { - if (tps80031_slave_address[i] == client->addr) - tps80031->clients[i] = client; - else - tps80031->clients[i] = devm_i2c_new_dummy_device(&client->dev, - client->adapter, tps80031_slave_address[i]); - if (IS_ERR(tps80031->clients[i])) { - dev_err(&client->dev, "can't attach client %d\n", i); - return PTR_ERR(tps80031->clients[i]); - } - - i2c_set_clientdata(tps80031->clients[i], tps80031); - tps80031->regmap[i] = devm_regmap_init_i2c(tps80031->clients[i], - &tps80031_regmap_configs[i]); - if (IS_ERR(tps80031->regmap[i])) { - ret = PTR_ERR(tps80031->regmap[i]); - dev_err(&client->dev, - "regmap %d init failed, err %d\n", i, ret); - return ret; - } - } - - ret = tps80031_read(&client->dev, TPS80031_SLAVE_ID3, - TPS80031_JTAGVERNUM, &es_version); - if (ret < 0) { - dev_err(&client->dev, - "Silicon version number read failed: %d\n", ret); - return ret; - } - - ret = tps80031_read(&client->dev, TPS80031_SLAVE_ID3, - TPS80031_EPROM_REV, &ep_ver); - if (ret < 0) { - dev_err(&client->dev, - "Silicon eeprom version read failed: %d\n", ret); - return ret; - } - - dev_info(&client->dev, "ES version 0x%02x and EPROM version 0x%02x\n", - es_version, ep_ver); - tps80031->es_version = es_version; - tps80031->dev = &client->dev; - i2c_set_clientdata(client, tps80031); - tps80031->chip_info = id->driver_data; - - ret = tps80031_irq_init(tps80031, client->irq, pdata->irq_base); - if (ret) { - dev_err(&client->dev, "IRQ init failed: %d\n", ret); - return ret; - } - - tps80031_pupd_init(tps80031, pdata); - - tps80031_init_ext_control(tps80031, pdata); - - ret = mfd_add_devices(tps80031->dev, -1, - tps80031_cell, ARRAY_SIZE(tps80031_cell), - NULL, 0, - regmap_irq_get_domain(tps80031->irq_data)); - if (ret < 0) { - dev_err(&client->dev, "mfd_add_devices failed: %d\n", ret); - goto fail_mfd_add; - } - - if (pdata->use_power_off && !pm_power_off) { - tps80031_power_off_dev = tps80031; - pm_power_off = tps80031_power_off; - } - return 0; - -fail_mfd_add: - regmap_del_irq_chip(client->irq, tps80031->irq_data); - return ret; -} - -static const struct i2c_device_id tps80031_id_table[] = { - { "tps80031", TPS80031 }, - { "tps80032", TPS80032 }, - { } -}; - -static struct i2c_driver tps80031_driver = { - .driver = { - .name = "tps80031", - .suppress_bind_attrs = true, - }, - .probe = tps80031_probe, - .id_table = tps80031_id_table, -}; - -static int __init tps80031_init(void) -{ - return i2c_add_driver(&tps80031_driver); -} -subsys_initcall(tps80031_init); diff --git a/include/linux/mfd/tps80031.h b/include/linux/mfd/tps80031.h deleted file mode 100644 index 2c75c9c9318f..000000000000 --- a/include/linux/mfd/tps80031.h +++ /dev/null @@ -1,637 +0,0 @@ -/* - * tps80031.h -- TI TPS80031 and TI TPS80032 PMIC driver. - * - * Copyright (c) 2012, NVIDIA Corporation. - * - * Author: Laxman Dewangan - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation version 2. - * - * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind, - * whether express or implied; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - * 02111-1307, USA - */ - -#ifndef __LINUX_MFD_TPS80031_H -#define __LINUX_MFD_TPS80031_H - -#include -#include - -/* Pull-ups/Pull-downs */ -#define TPS80031_CFG_INPUT_PUPD1 0xF0 -#define TPS80031_CFG_INPUT_PUPD2 0xF1 -#define TPS80031_CFG_INPUT_PUPD3 0xF2 -#define TPS80031_CFG_INPUT_PUPD4 0xF3 -#define TPS80031_CFG_LDO_PD1 0xF4 -#define TPS80031_CFG_LDO_PD2 0xF5 -#define TPS80031_CFG_SMPS_PD 0xF6 - -/* Real Time Clock */ -#define TPS80031_SECONDS_REG 0x00 -#define TPS80031_MINUTES_REG 0x01 -#define TPS80031_HOURS_REG 0x02 -#define TPS80031_DAYS_REG 0x03 -#define TPS80031_MONTHS_REG 0x04 -#define TPS80031_YEARS_REG 0x05 -#define TPS80031_WEEKS_REG 0x06 -#define TPS80031_ALARM_SECONDS_REG 0x08 -#define TPS80031_ALARM_MINUTES_REG 0x09 -#define TPS80031_ALARM_HOURS_REG 0x0A -#define TPS80031_ALARM_DAYS_REG 0x0B -#define TPS80031_ALARM_MONTHS_REG 0x0C -#define TPS80031_ALARM_YEARS_REG 0x0D -#define TPS80031_RTC_CTRL_REG 0x10 -#define TPS80031_RTC_STATUS_REG 0x11 -#define TPS80031_RTC_INTERRUPTS_REG 0x12 -#define TPS80031_RTC_COMP_LSB_REG 0x13 -#define TPS80031_RTC_COMP_MSB_REG 0x14 -#define TPS80031_RTC_RESET_STATUS_REG 0x16 - -/*PMC Master Module */ -#define TPS80031_PHOENIX_START_CONDITION 0x1F -#define TPS80031_PHOENIX_MSK_TRANSITION 0x20 -#define TPS80031_STS_HW_CONDITIONS 0x21 -#define TPS80031_PHOENIX_LAST_TURNOFF_STS 0x22 -#define TPS80031_VSYSMIN_LO_THRESHOLD 0x23 -#define TPS80031_VSYSMIN_HI_THRESHOLD 0x24 -#define TPS80031_PHOENIX_DEV_ON 0x25 -#define TPS80031_STS_PWR_GRP_STATE 0x27 -#define TPS80031_PH_CFG_VSYSLOW 0x28 -#define TPS80031_PH_STS_BOOT 0x29 -#define TPS80031_PHOENIX_SENS_TRANSITION 0x2A -#define TPS80031_PHOENIX_SEQ_CFG 0x2B -#define TPS80031_PRIMARY_WATCHDOG_CFG 0X2C -#define TPS80031_KEY_PRESS_DUR_CFG 0X2D -#define TPS80031_SMPS_LDO_SHORT_STS 0x2E - -/* PMC Slave Module - Broadcast */ -#define TPS80031_BROADCAST_ADDR_ALL 0x31 -#define TPS80031_BROADCAST_ADDR_REF 0x32 -#define TPS80031_BROADCAST_ADDR_PROV 0x33 -#define TPS80031_BROADCAST_ADDR_CLK_RST 0x34 - -/* PMC Slave Module SMPS Regulators */ -#define TPS80031_SMPS4_CFG_TRANS 0x41 -#define TPS80031_SMPS4_CFG_STATE 0x42 -#define TPS80031_SMPS4_CFG_VOLTAGE 0x44 -#define TPS80031_VIO_CFG_TRANS 0x47 -#define TPS80031_VIO_CFG_STATE 0x48 -#define TPS80031_VIO_CFG_FORCE 0x49 -#define TPS80031_VIO_CFG_VOLTAGE 0x4A -#define TPS80031_VIO_CFG_STEP 0x48 -#define TPS80031_SMPS1_CFG_TRANS 0x53 -#define TPS80031_SMPS1_CFG_STATE 0x54 -#define TPS80031_SMPS1_CFG_FORCE 0x55 -#define TPS80031_SMPS1_CFG_VOLTAGE 0x56 -#define TPS80031_SMPS1_CFG_STEP 0x57 -#define TPS80031_SMPS2_CFG_TRANS 0x59 -#define TPS80031_SMPS2_CFG_STATE 0x5A -#define TPS80031_SMPS2_CFG_FORCE 0x5B -#define TPS80031_SMPS2_CFG_VOLTAGE 0x5C -#define TPS80031_SMPS2_CFG_STEP 0x5D -#define TPS80031_SMPS3_CFG_TRANS 0x65 -#define TPS80031_SMPS3_CFG_STATE 0x66 -#define TPS80031_SMPS3_CFG_VOLTAGE 0x68 - -/* PMC Slave Module LDO Regulators */ -#define TPS80031_VANA_CFG_TRANS 0x81 -#define TPS80031_VANA_CFG_STATE 0x82 -#define TPS80031_VANA_CFG_VOLTAGE 0x83 -#define TPS80031_LDO2_CFG_TRANS 0x85 -#define TPS80031_LDO2_CFG_STATE 0x86 -#define TPS80031_LDO2_CFG_VOLTAGE 0x87 -#define TPS80031_LDO4_CFG_TRANS 0x89 -#define TPS80031_LDO4_CFG_STATE 0x8A -#define TPS80031_LDO4_CFG_VOLTAGE 0x8B -#define TPS80031_LDO3_CFG_TRANS 0x8D -#define TPS80031_LDO3_CFG_STATE 0x8E -#define TPS80031_LDO3_CFG_VOLTAGE 0x8F -#define TPS80031_LDO6_CFG_TRANS 0x91 -#define TPS80031_LDO6_CFG_STATE 0x92 -#define TPS80031_LDO6_CFG_VOLTAGE 0x93 -#define TPS80031_LDOLN_CFG_TRANS 0x95 -#define TPS80031_LDOLN_CFG_STATE 0x96 -#define TPS80031_LDOLN_CFG_VOLTAGE 0x97 -#define TPS80031_LDO5_CFG_TRANS 0x99 -#define TPS80031_LDO5_CFG_STATE 0x9A -#define TPS80031_LDO5_CFG_VOLTAGE 0x9B -#define TPS80031_LDO1_CFG_TRANS 0x9D -#define TPS80031_LDO1_CFG_STATE 0x9E -#define TPS80031_LDO1_CFG_VOLTAGE 0x9F -#define TPS80031_LDOUSB_CFG_TRANS 0xA1 -#define TPS80031_LDOUSB_CFG_STATE 0xA2 -#define TPS80031_LDOUSB_CFG_VOLTAGE 0xA3 -#define TPS80031_LDO7_CFG_TRANS 0xA5 -#define TPS80031_LDO7_CFG_STATE 0xA6 -#define TPS80031_LDO7_CFG_VOLTAGE 0xA7 - -/* PMC Slave Module External Control */ -#define TPS80031_REGEN1_CFG_TRANS 0xAE -#define TPS80031_REGEN1_CFG_STATE 0xAF -#define TPS80031_REGEN2_CFG_TRANS 0xB1 -#define TPS80031_REGEN2_CFG_STATE 0xB2 -#define TPS80031_SYSEN_CFG_TRANS 0xB4 -#define TPS80031_SYSEN_CFG_STATE 0xB5 - -/* PMC Slave Module Internal Control */ -#define TPS80031_NRESPWRON_CFG_TRANS 0xB7 -#define TPS80031_NRESPWRON_CFG_STATE 0xB8 -#define TPS80031_CLK32KAO_CFG_TRANS 0xBA -#define TPS80031_CLK32KAO_CFG_STATE 0xBB -#define TPS80031_CLK32KG_CFG_TRANS 0xBD -#define TPS80031_CLK32KG_CFG_STATE 0xBE -#define TPS80031_CLK32KAUDIO_CFG_TRANS 0xC0 -#define TPS80031_CLK32KAUDIO_CFG_STATE 0xC1 -#define TPS80031_VRTC_CFG_TRANS 0xC3 -#define TPS80031_VRTC_CFG_STATE 0xC4 -#define TPS80031_BIAS_CFG_TRANS 0xC6 -#define TPS80031_BIAS_CFG_STATE 0xC7 -#define TPS80031_VSYSMIN_HI_CFG_TRANS 0xC9 -#define TPS80031_VSYSMIN_HI_CFG_STATE 0xCA -#define TPS80031_RC6MHZ_CFG_TRANS 0xCC -#define TPS80031_RC6MHZ_CFG_STATE 0xCD -#define TPS80031_TMP_CFG_TRANS 0xCF -#define TPS80031_TMP_CFG_STATE 0xD0 - -/* PMC Slave Module resources assignment */ -#define TPS80031_PREQ1_RES_ASS_A 0xD7 -#define TPS80031_PREQ1_RES_ASS_B 0xD8 -#define TPS80031_PREQ1_RES_ASS_C 0xD9 -#define TPS80031_PREQ2_RES_ASS_A 0xDA -#define TPS80031_PREQ2_RES_ASS_B 0xDB -#define TPS80031_PREQ2_RES_ASS_C 0xDC -#define TPS80031_PREQ3_RES_ASS_A 0xDD -#define TPS80031_PREQ3_RES_ASS_B 0xDE -#define TPS80031_PREQ3_RES_ASS_C 0xDF - -/* PMC Slave Module Miscellaneous */ -#define TPS80031_SMPS_OFFSET 0xE0 -#define TPS80031_SMPS_MULT 0xE3 -#define TPS80031_MISC1 0xE4 -#define TPS80031_MISC2 0xE5 -#define TPS80031_BBSPOR_CFG 0xE6 -#define TPS80031_TMP_CFG 0xE7 - -/* Battery Charging Controller and Indicator LED */ -#define TPS80031_CONTROLLER_CTRL2 0xDA -#define TPS80031_CONTROLLER_VSEL_COMP 0xDB -#define TPS80031_CHARGERUSB_VSYSREG 0xDC -#define TPS80031_CHARGERUSB_VICHRG_PC 0xDD -#define TPS80031_LINEAR_CHRG_STS 0xDE -#define TPS80031_CONTROLLER_INT_MASK 0xE0 -#define TPS80031_CONTROLLER_CTRL1 0xE1 -#define TPS80031_CONTROLLER_WDG 0xE2 -#define TPS80031_CONTROLLER_STAT1 0xE3 -#define TPS80031_CHARGERUSB_INT_STATUS 0xE4 -#define TPS80031_CHARGERUSB_INT_MASK 0xE5 -#define TPS80031_CHARGERUSB_STATUS_INT1 0xE6 -#define TPS80031_CHARGERUSB_STATUS_INT2 0xE7 -#define TPS80031_CHARGERUSB_CTRL1 0xE8 -#define TPS80031_CHARGERUSB_CTRL2 0xE9 -#define TPS80031_CHARGERUSB_CTRL3 0xEA -#define TPS80031_CHARGERUSB_STAT1 0xEB -#define TPS80031_CHARGERUSB_VOREG 0xEC -#define TPS80031_CHARGERUSB_VICHRG 0xED -#define TPS80031_CHARGERUSB_CINLIMIT 0xEE -#define TPS80031_CHARGERUSB_CTRLLIMIT1 0xEF -#define TPS80031_CHARGERUSB_CTRLLIMIT2 0xF0 -#define TPS80031_LED_PWM_CTRL1 0xF4 -#define TPS80031_LED_PWM_CTRL2 0xF5 - -/* USB On-The-Go */ -#define TPS80031_BACKUP_REG 0xFA -#define TPS80031_USB_VENDOR_ID_LSB 0x00 -#define TPS80031_USB_VENDOR_ID_MSB 0x01 -#define TPS80031_USB_PRODUCT_ID_LSB 0x02 -#define TPS80031_USB_PRODUCT_ID_MSB 0x03 -#define TPS80031_USB_VBUS_CTRL_SET 0x04 -#define TPS80031_USB_VBUS_CTRL_CLR 0x05 -#define TPS80031_USB_ID_CTRL_SET 0x06 -#define TPS80031_USB_ID_CTRL_CLR 0x07 -#define TPS80031_USB_VBUS_INT_SRC 0x08 -#define TPS80031_USB_VBUS_INT_LATCH_SET 0x09 -#define TPS80031_USB_VBUS_INT_LATCH_CLR 0x0A -#define TPS80031_USB_VBUS_INT_EN_LO_SET 0x0B -#define TPS80031_USB_VBUS_INT_EN_LO_CLR 0x0C -#define TPS80031_USB_VBUS_INT_EN_HI_SET 0x0D -#define TPS80031_USB_VBUS_INT_EN_HI_CLR 0x0E -#define TPS80031_USB_ID_INT_SRC 0x0F -#define TPS80031_USB_ID_INT_LATCH_SET 0x10 -#define TPS80031_USB_ID_INT_LATCH_CLR 0x11 -#define TPS80031_USB_ID_INT_EN_LO_SET 0x12 -#define TPS80031_USB_ID_INT_EN_LO_CLR 0x13 -#define TPS80031_USB_ID_INT_EN_HI_SET 0x14 -#define TPS80031_USB_ID_INT_EN_HI_CLR 0x15 -#define TPS80031_USB_OTG_ADP_CTRL 0x16 -#define TPS80031_USB_OTG_ADP_HIGH 0x17 -#define TPS80031_USB_OTG_ADP_LOW 0x18 -#define TPS80031_USB_OTG_ADP_RISE 0x19 -#define TPS80031_USB_OTG_REVISION 0x1A - -/* Gas Gauge */ -#define TPS80031_FG_REG_00 0xC0 -#define TPS80031_FG_REG_01 0xC1 -#define TPS80031_FG_REG_02 0xC2 -#define TPS80031_FG_REG_03 0xC3 -#define TPS80031_FG_REG_04 0xC4 -#define TPS80031_FG_REG_05 0xC5 -#define TPS80031_FG_REG_06 0xC6 -#define TPS80031_FG_REG_07 0xC7 -#define TPS80031_FG_REG_08 0xC8 -#define TPS80031_FG_REG_09 0xC9 -#define TPS80031_FG_REG_10 0xCA -#define TPS80031_FG_REG_11 0xCB - -/* General Purpose ADC */ -#define TPS80031_GPADC_CTRL 0x2E -#define TPS80031_GPADC_CTRL2 0x2F -#define TPS80031_RTSELECT_LSB 0x32 -#define TPS80031_RTSELECT_ISB 0x33 -#define TPS80031_RTSELECT_MSB 0x34 -#define TPS80031_GPSELECT_ISB 0x35 -#define TPS80031_CTRL_P1 0x36 -#define TPS80031_RTCH0_LSB 0x37 -#define TPS80031_RTCH0_MSB 0x38 -#define TPS80031_RTCH1_LSB 0x39 -#define TPS80031_RTCH1_MSB 0x3A -#define TPS80031_GPCH0_LSB 0x3B -#define TPS80031_GPCH0_MSB 0x3C - -/* SIM, MMC and Battery Detection */ -#define TPS80031_SIMDEBOUNCING 0xEB -#define TPS80031_SIMCTRL 0xEC -#define TPS80031_MMCDEBOUNCING 0xED -#define TPS80031_MMCCTRL 0xEE -#define TPS80031_BATDEBOUNCING 0xEF - -/* Vibrator Driver and PWMs */ -#define TPS80031_VIBCTRL 0x9B -#define TPS80031_VIBMODE 0x9C -#define TPS80031_PWM1ON 0xBA -#define TPS80031_PWM1OFF 0xBB -#define TPS80031_PWM2ON 0xBD -#define TPS80031_PWM2OFF 0xBE - -/* Control Interface */ -#define TPS80031_INT_STS_A 0xD0 -#define TPS80031_INT_STS_B 0xD1 -#define TPS80031_INT_STS_C 0xD2 -#define TPS80031_INT_MSK_LINE_A 0xD3 -#define TPS80031_INT_MSK_LINE_B 0xD4 -#define TPS80031_INT_MSK_LINE_C 0xD5 -#define TPS80031_INT_MSK_STS_A 0xD6 -#define TPS80031_INT_MSK_STS_B 0xD7 -#define TPS80031_INT_MSK_STS_C 0xD8 -#define TPS80031_TOGGLE1 0x90 -#define TPS80031_TOGGLE2 0x91 -#define TPS80031_TOGGLE3 0x92 -#define TPS80031_PWDNSTATUS1 0x93 -#define TPS80031_PWDNSTATUS2 0x94 -#define TPS80031_VALIDITY0 0x17 -#define TPS80031_VALIDITY1 0x18 -#define TPS80031_VALIDITY2 0x19 -#define TPS80031_VALIDITY3 0x1A -#define TPS80031_VALIDITY4 0x1B -#define TPS80031_VALIDITY5 0x1C -#define TPS80031_VALIDITY6 0x1D -#define TPS80031_VALIDITY7 0x1E - -/* Version number related register */ -#define TPS80031_JTAGVERNUM 0x87 -#define TPS80031_EPROM_REV 0xDF - -/* GPADC Trimming Bits. */ -#define TPS80031_GPADC_TRIM0 0xCC -#define TPS80031_GPADC_TRIM1 0xCD -#define TPS80031_GPADC_TRIM2 0xCE -#define TPS80031_GPADC_TRIM3 0xCF -#define TPS80031_GPADC_TRIM4 0xD0 -#define TPS80031_GPADC_TRIM5 0xD1 -#define TPS80031_GPADC_TRIM6 0xD2 -#define TPS80031_GPADC_TRIM7 0xD3 -#define TPS80031_GPADC_TRIM8 0xD4 -#define TPS80031_GPADC_TRIM9 0xD5 -#define TPS80031_GPADC_TRIM10 0xD6 -#define TPS80031_GPADC_TRIM11 0xD7 -#define TPS80031_GPADC_TRIM12 0xD8 -#define TPS80031_GPADC_TRIM13 0xD9 -#define TPS80031_GPADC_TRIM14 0xDA -#define TPS80031_GPADC_TRIM15 0xDB -#define TPS80031_GPADC_TRIM16 0xDC -#define TPS80031_GPADC_TRIM17 0xDD -#define TPS80031_GPADC_TRIM18 0xDE - -/* TPS80031_CONTROLLER_STAT1 bit fields */ -#define TPS80031_CONTROLLER_STAT1_BAT_TEMP 0 -#define TPS80031_CONTROLLER_STAT1_BAT_REMOVED 1 -#define TPS80031_CONTROLLER_STAT1_VBUS_DET 2 -#define TPS80031_CONTROLLER_STAT1_VAC_DET 3 -#define TPS80031_CONTROLLER_STAT1_FAULT_WDG 4 -#define TPS80031_CONTROLLER_STAT1_LINCH_GATED 6 -/* TPS80031_CONTROLLER_INT_MASK bit filed */ -#define TPS80031_CONTROLLER_INT_MASK_MVAC_DET 0 -#define TPS80031_CONTROLLER_INT_MASK_MVBUS_DET 1 -#define TPS80031_CONTROLLER_INT_MASK_MBAT_TEMP 2 -#define TPS80031_CONTROLLER_INT_MASK_MFAULT_WDG 3 -#define TPS80031_CONTROLLER_INT_MASK_MBAT_REMOVED 4 -#define TPS80031_CONTROLLER_INT_MASK_MLINCH_GATED 5 - -#define TPS80031_CHARGE_CONTROL_SUB_INT_MASK 0x3F - -/* TPS80031_PHOENIX_DEV_ON bit field */ -#define TPS80031_DEVOFF 0x1 - -#define TPS80031_EXT_CONTROL_CFG_TRANS 0 -#define TPS80031_EXT_CONTROL_CFG_STATE 1 - -/* State register field */ -#define TPS80031_STATE_OFF 0x00 -#define TPS80031_STATE_ON 0x01 -#define TPS80031_STATE_MASK 0x03 - -/* Trans register field */ -#define TPS80031_TRANS_ACTIVE_OFF 0x00 -#define TPS80031_TRANS_ACTIVE_ON 0x01 -#define TPS80031_TRANS_ACTIVE_MASK 0x03 -#define TPS80031_TRANS_SLEEP_OFF 0x00 -#define TPS80031_TRANS_SLEEP_ON 0x04 -#define TPS80031_TRANS_SLEEP_MASK 0x0C -#define TPS80031_TRANS_OFF_OFF 0x00 -#define TPS80031_TRANS_OFF_ACTIVE 0x10 -#define TPS80031_TRANS_OFF_MASK 0x30 - -#define TPS80031_EXT_PWR_REQ (TPS80031_PWR_REQ_INPUT_PREQ1 | \ - TPS80031_PWR_REQ_INPUT_PREQ2 | \ - TPS80031_PWR_REQ_INPUT_PREQ3) - -/* TPS80031_BBSPOR_CFG bit field */ -#define TPS80031_BBSPOR_CHG_EN 0x8 -#define TPS80031_MAX_REGISTER 0xFF - -struct i2c_client; - -/* Supported chips */ -enum chips { - TPS80031 = 0x00000001, - TPS80032 = 0x00000002, -}; - -enum { - TPS80031_INT_PWRON, - TPS80031_INT_RPWRON, - TPS80031_INT_SYS_VLOW, - TPS80031_INT_RTC_ALARM, - TPS80031_INT_RTC_PERIOD, - TPS80031_INT_HOT_DIE, - TPS80031_INT_VXX_SHORT, - TPS80031_INT_SPDURATION, - TPS80031_INT_WATCHDOG, - TPS80031_INT_BAT, - TPS80031_INT_SIM, - TPS80031_INT_MMC, - TPS80031_INT_RES, - TPS80031_INT_GPADC_RT, - TPS80031_INT_GPADC_SW2_EOC, - TPS80031_INT_CC_AUTOCAL, - TPS80031_INT_ID_WKUP, - TPS80031_INT_VBUSS_WKUP, - TPS80031_INT_ID, - TPS80031_INT_VBUS, - TPS80031_INT_CHRG_CTRL, - TPS80031_INT_EXT_CHRG, - TPS80031_INT_INT_CHRG, - TPS80031_INT_RES2, - TPS80031_INT_BAT_TEMP_OVRANGE, - TPS80031_INT_BAT_REMOVED, - TPS80031_INT_VBUS_DET, - TPS80031_INT_VAC_DET, - TPS80031_INT_FAULT_WDG, - TPS80031_INT_LINCH_GATED, - - /* Last interrupt id to get the end number */ - TPS80031_INT_NR, -}; - -/* TPS80031 Slave IDs */ -#define TPS80031_NUM_SLAVES 4 -#define TPS80031_SLAVE_ID0 0 -#define TPS80031_SLAVE_ID1 1 -#define TPS80031_SLAVE_ID2 2 -#define TPS80031_SLAVE_ID3 3 - -/* TPS80031 I2C addresses */ -#define TPS80031_I2C_ID0_ADDR 0x12 -#define TPS80031_I2C_ID1_ADDR 0x48 -#define TPS80031_I2C_ID2_ADDR 0x49 -#define TPS80031_I2C_ID3_ADDR 0x4A - -enum { - TPS80031_REGULATOR_VIO, - TPS80031_REGULATOR_SMPS1, - TPS80031_REGULATOR_SMPS2, - TPS80031_REGULATOR_SMPS3, - TPS80031_REGULATOR_SMPS4, - TPS80031_REGULATOR_VANA, - TPS80031_REGULATOR_LDO1, - TPS80031_REGULATOR_LDO2, - TPS80031_REGULATOR_LDO3, - TPS80031_REGULATOR_LDO4, - TPS80031_REGULATOR_LDO5, - TPS80031_REGULATOR_LDO6, - TPS80031_REGULATOR_LDO7, - TPS80031_REGULATOR_LDOLN, - TPS80031_REGULATOR_LDOUSB, - TPS80031_REGULATOR_VBUS, - TPS80031_REGULATOR_REGEN1, - TPS80031_REGULATOR_REGEN2, - TPS80031_REGULATOR_SYSEN, - TPS80031_REGULATOR_MAX, -}; - -/* Different configurations for the rails */ -enum { - /* USBLDO input selection */ - TPS80031_USBLDO_INPUT_VSYS = 0x00000001, - TPS80031_USBLDO_INPUT_PMID = 0x00000002, - - /* LDO3 output mode */ - TPS80031_LDO3_OUTPUT_VIB = 0x00000004, - - /* VBUS configuration */ - TPS80031_VBUS_DISCHRG_EN_PDN = 0x00000004, - TPS80031_VBUS_SW_ONLY = 0x00000008, - TPS80031_VBUS_SW_N_ID = 0x00000010, -}; - -/* External controls requests */ -enum tps80031_ext_control { - TPS80031_PWR_REQ_INPUT_NONE = 0x00000000, - TPS80031_PWR_REQ_INPUT_PREQ1 = 0x00000001, - TPS80031_PWR_REQ_INPUT_PREQ2 = 0x00000002, - TPS80031_PWR_REQ_INPUT_PREQ3 = 0x00000004, - TPS80031_PWR_OFF_ON_SLEEP = 0x00000008, - TPS80031_PWR_ON_ON_SLEEP = 0x00000010, -}; - -enum tps80031_pupd_pins { - TPS80031_PREQ1 = 0, - TPS80031_PREQ2A, - TPS80031_PREQ2B, - TPS80031_PREQ2C, - TPS80031_PREQ3, - TPS80031_NRES_WARM, - TPS80031_PWM_FORCE, - TPS80031_CHRG_EXT_CHRG_STATZ, - TPS80031_SIM, - TPS80031_MMC, - TPS80031_GPADC_START, - TPS80031_DVSI2C_SCL, - TPS80031_DVSI2C_SDA, - TPS80031_CTLI2C_SCL, - TPS80031_CTLI2C_SDA, -}; - -enum tps80031_pupd_settings { - TPS80031_PUPD_NORMAL, - TPS80031_PUPD_PULLDOWN, - TPS80031_PUPD_PULLUP, -}; - -struct tps80031 { - struct device *dev; - unsigned long chip_info; - int es_version; - struct i2c_client *clients[TPS80031_NUM_SLAVES]; - struct regmap *regmap[TPS80031_NUM_SLAVES]; - struct regmap_irq_chip_data *irq_data; -}; - -struct tps80031_pupd_init_data { - int input_pin; - int setting; -}; - -/* - * struct tps80031_regulator_platform_data - tps80031 regulator platform data. - * - * @reg_init_data: The regulator init data. - * @ext_ctrl_flag: External control flag for sleep/power request control. - * @config_flags: Configuration flag to configure the rails. - * It should be ORed of config enums. - */ - -struct tps80031_regulator_platform_data { - struct regulator_init_data *reg_init_data; - unsigned int ext_ctrl_flag; - unsigned int config_flags; -}; - -struct tps80031_platform_data { - int irq_base; - bool use_power_off; - struct tps80031_pupd_init_data *pupd_init_data; - int pupd_init_data_size; - struct tps80031_regulator_platform_data - *regulator_pdata[TPS80031_REGULATOR_MAX]; -}; - -static inline int tps80031_write(struct device *dev, int sid, - int reg, uint8_t val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_write(tps80031->regmap[sid], reg, val); -} - -static inline int tps80031_writes(struct device *dev, int sid, int reg, - int len, uint8_t *val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_bulk_write(tps80031->regmap[sid], reg, val, len); -} - -static inline int tps80031_read(struct device *dev, int sid, - int reg, uint8_t *val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - unsigned int ival; - int ret; - - ret = regmap_read(tps80031->regmap[sid], reg, &ival); - if (ret < 0) { - dev_err(dev, "failed reading from reg 0x%02x\n", reg); - return ret; - } - - *val = ival; - return ret; -} - -static inline int tps80031_reads(struct device *dev, int sid, - int reg, int len, uint8_t *val) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_bulk_read(tps80031->regmap[sid], reg, val, len); -} - -static inline int tps80031_set_bits(struct device *dev, int sid, - int reg, uint8_t bit_mask) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_update_bits(tps80031->regmap[sid], reg, - bit_mask, bit_mask); -} - -static inline int tps80031_clr_bits(struct device *dev, int sid, - int reg, uint8_t bit_mask) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_update_bits(tps80031->regmap[sid], reg, bit_mask, 0); -} - -static inline int tps80031_update(struct device *dev, int sid, - int reg, uint8_t val, uint8_t mask) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_update_bits(tps80031->regmap[sid], reg, mask, val); -} - -static inline unsigned long tps80031_get_chip_info(struct device *dev) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return tps80031->chip_info; -} - -static inline int tps80031_get_pmu_version(struct device *dev) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return tps80031->es_version; -} - -static inline int tps80031_irq_get_virq(struct device *dev, int irq) -{ - struct tps80031 *tps80031 = dev_get_drvdata(dev); - - return regmap_irq_get_virq(tps80031->irq_data, irq); -} - -extern int tps80031_ext_power_req_config(struct device *dev, - unsigned long ext_ctrl_flag, int preq_bit, - int state_reg_add, int trans_reg_add); -#endif /*__LINUX_MFD_TPS80031_H */ -- cgit v1.2.3 From d755ad8dc752d44545613ea04d660aed674e540d Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:00 -0400 Subject: NFS: Create a new nfs_alloc_fattr_with_label() function For creating fattrs with the label field already allocated for us. I also update nfs_free_fattr() to free the label in the end. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/getroot.c | 17 ++++++----------- fs/nfs/inode.c | 17 +++++++++++++++++ fs/nfs/internal.h | 9 --------- include/linux/nfs_fs.h | 13 +++++++++++++ 4 files changed, 36 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 59355c106ece..7604cb6a0ac2 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -80,18 +80,15 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) goto out; /* get the actual root for this mount */ - fsinfo.fattr = nfs_alloc_fattr(); + fsinfo.fattr = nfs_alloc_fattr_with_label(server); if (fsinfo.fattr == NULL) goto out_name; - fsinfo.fattr->label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(fsinfo.fattr->label)) - goto out_fattr; error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo); if (error < 0) { dprintk("nfs_get_root: getattr error = %d\n", -error); nfs_errorf(fc, "NFS: Couldn't getattr on root"); - goto out_label; + goto out_fattr; } inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr, NULL); @@ -99,12 +96,12 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) dprintk("nfs_get_root: get root inode failed\n"); error = PTR_ERR(inode); nfs_errorf(fc, "NFS: Couldn't get root inode"); - goto out_label; + goto out_fattr; } error = nfs_superblock_set_dummy_root(s, inode); if (error != 0) - goto out_label; + goto out_fattr; /* root dentries normally start off anonymous and get spliced in later * if the dentry tree reaches them; however if the dentry already @@ -115,7 +112,7 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) dprintk("nfs_get_root: get root dentry failed\n"); error = PTR_ERR(root); nfs_errorf(fc, "NFS: Couldn't get root dentry"); - goto out_label; + goto out_fattr; } security_d_instantiate(root, inode); @@ -154,8 +151,6 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) nfs_setsecurity(inode, fsinfo.fattr, fsinfo.fattr->label); error = 0; -out_label: - nfs4_label_free(fsinfo.fattr->label); out_fattr: nfs_free_fattr(fsinfo.fattr); out_name: @@ -165,5 +160,5 @@ out: error_splat_root: dput(fc->root); fc->root = NULL; - goto out_label; + goto out_fattr; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 0b5b1e44b2c4..84c7efa2ea87 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1606,6 +1606,23 @@ struct nfs_fattr *nfs_alloc_fattr(void) } EXPORT_SYMBOL_GPL(nfs_alloc_fattr); +struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server) +{ + struct nfs_fattr *fattr = nfs_alloc_fattr(); + + if (!fattr) + return NULL; + + fattr->label = nfs4_label_alloc(server, GFP_NOFS); + if (IS_ERR(fattr->label)) { + kfree(fattr); + return NULL; + } + + return fattr; +} +EXPORT_SYMBOL_GPL(nfs_alloc_fattr_with_label); + struct nfs_fh *nfs_alloc_fhandle(void) { struct nfs_fh *fh; diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 123078c76495..12f6acb483bb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -342,14 +342,6 @@ nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src) return dst; } -static inline void nfs4_label_free(struct nfs4_label *label) -{ - if (label) { - kfree(label->label); - kfree(label); - } - return; -} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { @@ -358,7 +350,6 @@ static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) } #else static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } -static inline void nfs4_label_free(void *label) {} static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi) { } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 739ca1ef934f..88c3aed8ad39 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -426,9 +426,22 @@ extern void nfs_fattr_set_barrier(struct nfs_fattr *fattr); extern unsigned long nfs_inc_attr_generation_counter(void); extern struct nfs_fattr *nfs_alloc_fattr(void); +extern struct nfs_fattr *nfs_alloc_fattr_with_label(struct nfs_server *server); + +static inline void nfs4_label_free(struct nfs4_label *label) +{ +#ifdef CONFIG_NFS_V4_SECURITY_LABEL + if (label) { + kfree(label->label); + kfree(label); + } +#endif +} static inline void nfs_free_fattr(const struct nfs_fattr *fattr) { + if (fattr) + nfs4_label_free(fattr->label); kfree(fattr); } -- cgit v1.2.3 From b1db9a401d464d526d5941f0544e7c9ea37fa731 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:01 -0400 Subject: NFS: Remove the nfs4_label from the nfs_entry struct And instead allocate the fattr using nfs_alloc_fattr_with_label() Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 21 +++++++-------------- fs/nfs/nfs4xdr.c | 2 +- include/linux/nfs_xdr.h | 1 - 3 files changed, 8 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 36cb1012c7e1..92530c3c1694 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -682,7 +682,8 @@ again: nfs_set_verifier(dentry, dir_verifier); status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) - nfs_setsecurity(d_inode(dentry), entry->fattr, entry->label); + nfs_setsecurity(d_inode(dentry), entry->fattr, + entry->fattr->label); goto out; } else { d_invalidate(dentry); @@ -696,7 +697,7 @@ again: goto out; } - inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label); + inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->fattr->label); alias = d_splice_alias(inode, dentry); d_lookup_done(dentry); if (alias) { @@ -732,8 +733,8 @@ static int nfs_readdir_page_filler(struct nfs_readdir_descriptor *desc, xdr_set_scratch_page(&stream, scratch); do { - if (entry->label) - entry->label->len = NFS4_MAXLABELLEN; + if (entry->fattr->label) + entry->fattr->label->len = NFS4_MAXLABELLEN; status = xdr_decode(desc, entry, &stream); if (status != 0) @@ -838,21 +839,15 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, return -ENOMEM; entry->cookie = nfs_readdir_page_last_cookie(page); entry->fh = nfs_alloc_fhandle(); - entry->fattr = nfs_alloc_fattr(); + entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); entry->server = NFS_SERVER(inode); if (entry->fh == NULL || entry->fattr == NULL) goto out; - entry->label = nfs4_label_alloc(NFS_SERVER(inode), GFP_NOWAIT); - if (IS_ERR(entry->label)) { - status = PTR_ERR(entry->label); - goto out; - } - array_size = (dtsize + PAGE_SIZE - 1) >> PAGE_SHIFT; pages = nfs_readdir_alloc_pages(array_size); if (!pages) - goto out_release_label; + goto out; do { unsigned int pglen; @@ -875,8 +870,6 @@ static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc, } while (!status && nfs_readdir_page_needs_filling(page)); nfs_readdir_free_pages(pages, array_size); -out_release_label: - nfs4_label_free(entry->label); out: nfs_free_fattr(entry->fattr); nfs_free_fhandle(entry->fh); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 63a12181e6c7..fba89f82e7b7 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -7467,7 +7467,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, return -EAGAIN; if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh, - NULL, entry->label, entry->server) < 0) + NULL, entry->fattr->label, entry->server) < 0) return -EAGAIN; if (entry->fattr->valid & NFS_ATTR_FATTR_MOUNTED_ON_FILEID) entry->ino = entry->fattr->mounted_on_fileid; diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index e9698b6278a5..9960f6628066 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -753,7 +753,6 @@ struct nfs_entry { int eof; struct nfs_fh * fh; struct nfs_fattr * fattr; - struct nfs4_label *label; unsigned char d_type; struct nfs_server * server; }; -- cgit v1.2.3 From 68be1742c22983558f0f148a4467eb9127d56b86 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:02 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_create_res struct Instead, use the label embedded in the attached fattr. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 12 +++++------- fs/nfs/nfs4xdr.c | 2 +- include/linux/nfs_xdr.h | 1 - 3 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 127388fabda8..2e07550dd0d4 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4850,7 +4850,6 @@ struct nfs4_createdata { struct nfs4_create_res res; struct nfs_fh fh; struct nfs_fattr fattr; - struct nfs4_label *label; }; static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, @@ -4862,8 +4861,8 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, if (data != NULL) { struct nfs_server *server = NFS_SERVER(dir); - data->label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(data->label)) + data->fattr.label = nfs4_label_alloc(server, GFP_KERNEL); + if (IS_ERR(data->fattr.label)) goto out_free; data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE]; @@ -4874,12 +4873,11 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir, data->arg.name = name; data->arg.attrs = sattr; data->arg.ftype = ftype; - data->arg.bitmask = nfs4_bitmask(server, data->label); + data->arg.bitmask = nfs4_bitmask(server, data->fattr.label); data->arg.umask = current_umask(); data->res.server = server; data->res.fh = &data->fh; data->res.fattr = &data->fattr; - data->res.label = data->label; nfs_fattr_init(data->res.fattr); } return data; @@ -4901,14 +4899,14 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ data->res.fattr->time_start, NFS_INO_INVALID_DATA); spin_unlock(&dir->i_lock); - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.label); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.fattr->label); } return status; } static void nfs4_free_createdata(struct nfs4_createdata *data) { - nfs4_label_free(data->label); + nfs4_label_free(data->fattr.label); kfree(data); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index fba89f82e7b7..38c74833f263 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6353,7 +6353,7 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - decode_getfattr_label(xdr, res->fattr, res->label, res->server); + decode_getfattr_label(xdr, res->fattr, res->fattr->label, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9960f6628066..5aba81b74c98 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1040,7 +1040,6 @@ struct nfs4_create_res { const struct nfs_server * server; struct nfs_fh * fh; struct nfs_fattr * fattr; - struct nfs4_label *label; struct nfs4_change_info dir_cinfo; }; -- cgit v1.2.3 From aa7ca3b2de190675543d84adaa1ff74e7867c76f Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:03 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_link_res struct Again, use the fattr's label field instead. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 16 +++------------- fs/nfs/nfs4xdr.c | 2 +- include/linux/nfs_xdr.h | 1 - 3 files changed, 4 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 2e07550dd0d4..bde5b5723046 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4790,7 +4790,6 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct }; struct nfs4_link_res res = { .server = server, - .label = NULL, }; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LINK], @@ -4799,18 +4798,12 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct }; int status = -ENOMEM; - res.fattr = nfs_alloc_fattr(); + res.fattr = nfs_alloc_fattr_with_label(server); if (res.fattr == NULL) goto out; - res.label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(res.label)) { - status = PTR_ERR(res.label); - goto out; - } - nfs4_inode_make_writeable(inode); - nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.label), inode, + nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, res.fattr->label), inode, NFS_INO_INVALID_CHANGE); status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); if (!status) { @@ -4819,12 +4812,9 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct nfs4_inc_nlink(inode); status = nfs_post_op_update_inode(inode, res.fattr); if (!status) - nfs_setsecurity(inode, res.fattr, res.label); + nfs_setsecurity(inode, res.fattr, res.fattr->label); } - - nfs4_label_free(res.label); - out: nfs_free_fattr(res.fattr); return status; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 38c74833f263..4c9d66fac3fd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6323,7 +6323,7 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_restorefh(xdr); if (status) goto out; - decode_getfattr_label(xdr, res->fattr, res->label, res->server); + decode_getfattr_label(xdr, res->fattr, res->fattr->label, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 5aba81b74c98..d55bf3fd5167 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1079,7 +1079,6 @@ struct nfs4_link_res { struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_label *label; struct nfs4_change_info cinfo; struct nfs_fattr * dir_attr; }; -- cgit v1.2.3 From 9558a007dbc383d48e7f5a123d0b5ff656c71068 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:04 -0400 Subject: NFS: Remove the label from the nfs4_lookup_res struct And usethe fattr's label field instead. I also adjust function calls to remove labels along the way. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 34 ++++++++++++---------------------- fs/nfs/namespace.c | 3 +-- fs/nfs/nfs3proc.c | 3 +-- fs/nfs/nfs4proc.c | 16 +++++++--------- fs/nfs/nfs4xdr.c | 4 ++-- fs/nfs/proc.c | 3 +-- include/linux/nfs_xdr.h | 4 +--- 7 files changed, 25 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 92530c3c1694..8a327971d485 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1494,19 +1494,17 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, { struct nfs_fh *fhandle; struct nfs_fattr *fattr; - struct nfs4_label *label; unsigned long dir_verifier; int ret; ret = -ENOMEM; fhandle = nfs_alloc_fhandle(); - fattr = nfs_alloc_fattr(); - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (fhandle == NULL || fattr == NULL || IS_ERR(label)) + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); + if (fhandle == NULL || fattr == NULL) goto out; dir_verifier = nfs_save_change_attribute(dir); - ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); + ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); if (ret < 0) { switch (ret) { case -ESTALE: @@ -1525,7 +1523,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, if (nfs_refresh_inode(inode, fattr) < 0) goto out; - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr, fattr->label); nfs_set_verifier(dentry, dir_verifier); /* set a readdirplus hint that we had a cache miss */ @@ -1534,7 +1532,6 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, out: nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); - nfs4_label_free(label); /* * If the lookup failed despite the dentry change attribute being @@ -1754,7 +1751,6 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in struct inode *inode = NULL; struct nfs_fh *fhandle = NULL; struct nfs_fattr *fattr = NULL; - struct nfs4_label *label = NULL; unsigned long dir_verifier; int error; @@ -1773,27 +1769,23 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in res = ERR_PTR(-ENOMEM); fhandle = nfs_alloc_fhandle(); - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(dir)); if (fhandle == NULL || fattr == NULL) goto out; - label = nfs4_label_alloc(NFS_SERVER(dir), GFP_NOWAIT); - if (IS_ERR(label)) - goto out; - dir_verifier = nfs_save_change_attribute(dir); trace_nfs_lookup_enter(dir, dentry, flags); - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, label); + error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); if (error == -ENOENT) goto no_entry; if (error < 0) { res = ERR_PTR(error); - goto out_label; + goto out; } - inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); + inode = nfs_fhget(dentry->d_sb, fhandle, fattr, fattr->label); res = ERR_CAST(inode); if (IS_ERR(res)) - goto out_label; + goto out; /* Notify readdir to use READDIRPLUS */ nfs_force_use_readdirplus(dir); @@ -1802,14 +1794,12 @@ no_entry: res = d_splice_alias(inode, dentry); if (res != NULL) { if (IS_ERR(res)) - goto out_label; + goto out; dentry = res; } nfs_set_verifier(dentry, dir_verifier); -out_label: - trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res)); - nfs4_label_free(label); out: + trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res)); nfs_free_fattr(fattr); nfs_free_fhandle(fhandle); return res; @@ -2058,7 +2048,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, d_drop(dentry); if (fhandle->size == 0) { - error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr, NULL); + error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr); if (error) goto out_error; } diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index bc0c698f3350..3295af4110f1 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -308,8 +308,7 @@ int nfs_submount(struct fs_context *fc, struct nfs_server *server) /* Look it up again to get its attributes */ err = server->nfs_client->rpc_ops->lookup(d_inode(parent), dentry, - ctx->mntfh, ctx->clone_data.fattr, - NULL); + ctx->mntfh, ctx->clone_data.fattr); dput(parent); if (err != 0) return err; diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index f7524310ddf4..717eb651f0fd 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -193,8 +193,7 @@ __nfs3_proc_lookup(struct inode *dir, const char *name, size_t len, static int nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { unsigned short task_flags = 0; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index bde5b5723046..7af73fd34b22 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4294,7 +4294,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { struct nfs_server *server = NFS_SERVER(dir); int status; @@ -4306,7 +4306,6 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct nfs4_lookup_res res = { .server = server, .fattr = fattr, - .label = label, .fh = fhandle, }; struct rpc_message msg = { @@ -4323,7 +4322,7 @@ static int _nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, if (nfs_lookup_is_soft_revalidate(dentry)) task_flags |= RPC_TASK_TIMEOUT; - args.bitmask = nfs4_bitmask(server, label); + args.bitmask = nfs4_bitmask(server, fattr->label); nfs_fattr_init(fattr); @@ -4345,7 +4344,7 @@ static void nfs_fixup_secinfo_attributes(struct nfs_fattr *fattr) static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { struct nfs4_exception exception = { .interruptible = true, @@ -4354,7 +4353,7 @@ static int nfs4_proc_lookup_common(struct rpc_clnt **clnt, struct inode *dir, const struct qstr *name = &dentry->d_name; int err; do { - err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr, label); + err = _nfs4_proc_lookup(client, dir, dentry, fhandle, fattr); trace_nfs4_lookup(dir, name, err); switch (err) { case -NFS4ERR_BADNAME: @@ -4390,13 +4389,12 @@ out: } static int nfs4_proc_lookup(struct inode *dir, struct dentry *dentry, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { int status; struct rpc_clnt *client = NFS_CLIENT(dir); - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, label); + status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); if (client != NFS_CLIENT(dir)) { rpc_shutdown_client(client); nfs_fixup_secinfo_attributes(fattr); @@ -4411,7 +4409,7 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry, struct rpc_clnt *client = NFS_CLIENT(dir); int status; - status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr, NULL); + status = nfs4_proc_lookup_common(&client, dir, dentry, fhandle, fattr); if (status < 0) return ERR_PTR(status); return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 4c9d66fac3fd..960e2b2a7a58 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6171,7 +6171,7 @@ static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); + status = decode_getfattr_label(xdr, res->fattr, res->fattr->label, res->server); out: return status; } @@ -6229,7 +6229,7 @@ static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp, status = decode_getfh(xdr, res->fh); if (status == 0) status = decode_getfattr_label(xdr, res->fattr, - res->label, res->server); + res->fattr->label, res->server); out: return status; } diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index ecc4e717808c..98a8901ede2e 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -154,8 +154,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, static int nfs_proc_lookup(struct inode *dir, struct dentry *dentry, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs_diropargs arg = { .fh = NFS_FH(dir), diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d55bf3fd5167..95219d5a8668 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1095,7 +1095,6 @@ struct nfs4_lookup_res { const struct nfs_server * server; struct nfs_fattr * fattr; struct nfs_fh * fh; - struct nfs4_label *label; }; struct nfs4_lookupp_arg { @@ -1740,8 +1739,7 @@ struct nfs_rpc_ops { int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); int (*lookup) (struct inode *, struct dentry *, - struct nfs_fh *, struct nfs_fattr *, - struct nfs4_label *); + struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *, struct nfs4_label *); int (*access) (struct inode *, struct nfs_access_entry *); -- cgit v1.2.3 From ba4bc8dc4d937df2b407393435a302550be0ad82 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:05 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_lookupp_res struct Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/export.c | 26 +++++++------------------- fs/nfs/nfs3proc.c | 2 +- fs/nfs/nfs4proc.c | 10 ++++------ fs/nfs/nfs4xdr.c | 2 +- include/linux/nfs_xdr.h | 3 +-- 5 files changed, 14 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/export.c b/fs/nfs/export.c index d772c20bbfd1..895b404888dd 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -131,7 +131,6 @@ nfs_get_parent(struct dentry *dentry) struct super_block *sb = inode->i_sb; struct nfs_server *server = NFS_SB(sb); struct nfs_fattr *fattr = NULL; - struct nfs4_label *label = NULL; struct dentry *parent; struct nfs_rpc_ops const *ops = server->nfs_client->rpc_ops; struct nfs_fh fh; @@ -139,31 +138,20 @@ nfs_get_parent(struct dentry *dentry) if (!ops->lookupp) return ERR_PTR(-EACCES); - fattr = nfs_alloc_fattr(); - if (fattr == NULL) { - parent = ERR_PTR(-ENOMEM); - goto out; - } - - label = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(label)) { - parent = ERR_CAST(label); - goto out_free_fattr; - } + fattr = nfs_alloc_fattr_with_label(server); + if (fattr == NULL) + return ERR_PTR(-ENOMEM); - ret = ops->lookupp(inode, &fh, fattr, label); + ret = ops->lookupp(inode, &fh, fattr); if (ret) { parent = ERR_PTR(ret); - goto out_free_label; + goto out; } - pinode = nfs_fhget(sb, &fh, fattr, label); + pinode = nfs_fhget(sb, &fh, fattr, fattr->label); parent = d_obtain_alias(pinode); -out_free_label: - nfs4_label_free(label); -out_free_fattr: - nfs_free_fattr(fattr); out: + nfs_free_fattr(fattr); return parent; } diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 717eb651f0fd..516f3340b226 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -208,7 +208,7 @@ nfs3_proc_lookup(struct inode *dir, struct dentry *dentry, } static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { const char dotdot[] = ".."; const size_t len = strlen(dotdot); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7af73fd34b22..caa5a1467f94 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4416,8 +4416,7 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, struct dentry *dentry, } static int _nfs4_proc_lookupp(struct inode *inode, - struct nfs_fh *fhandle, struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct rpc_clnt *clnt = NFS_CLIENT(inode); struct nfs_server *server = NFS_SERVER(inode); @@ -4429,7 +4428,6 @@ static int _nfs4_proc_lookupp(struct inode *inode, struct nfs4_lookupp_res res = { .server = server, .fattr = fattr, - .label = label, .fh = fhandle, }; struct rpc_message msg = { @@ -4442,7 +4440,7 @@ static int _nfs4_proc_lookupp(struct inode *inode, if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL) task_flags |= RPC_TASK_TIMEOUT; - args.bitmask = nfs4_bitmask(server, label); + args.bitmask = nfs4_bitmask(server, fattr->label); nfs_fattr_init(fattr); @@ -4454,14 +4452,14 @@ static int _nfs4_proc_lookupp(struct inode *inode, } static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label) + struct nfs_fattr *fattr) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_lookupp(inode, fhandle, fattr, label); + err = _nfs4_proc_lookupp(inode, fhandle, fattr); trace_nfs4_lookupp(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 960e2b2a7a58..0044747f9314 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6201,7 +6201,7 @@ static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_getfh(xdr, res->fh); if (status) goto out; - status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); + status = decode_getfattr_label(xdr, res->fattr, res->fattr->label, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 95219d5a8668..f0a685d9b8bd 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1108,7 +1108,6 @@ struct nfs4_lookupp_res { const struct nfs_server *server; struct nfs_fattr *fattr; struct nfs_fh *fh; - struct nfs4_label *label; }; struct nfs4_lookup_root_arg { @@ -1741,7 +1740,7 @@ struct nfs_rpc_ops { int (*lookup) (struct inode *, struct dentry *, struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); int (*access) (struct inode *, struct nfs_access_entry *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); -- cgit v1.2.3 From 76baa2b29c7161bc65a3051d311297b7d7fc827a Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:06 -0400 Subject: NFS: Remove the f_label from the nfs4_opendata and nfs_openres Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/nfs4_fs.h | 1 - fs/nfs/nfs4proc.c | 35 +++++++++++------------------------ fs/nfs/nfs4xdr.c | 2 +- include/linux/nfs_xdr.h | 1 - 4 files changed, 12 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index ba78df4b13d9..b621e29e6187 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -234,7 +234,6 @@ struct nfs4_opendata { struct nfs4_string group_name; struct nfs4_label *a_label; struct nfs_fattr f_attr; - struct nfs4_label *f_label; struct dentry *dir; struct dentry *dentry; struct nfs4_state_owner *owner; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index caa5a1467f94..cb0613e0ef8f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1329,7 +1329,6 @@ nfs4_map_atomic_open_claim(struct nfs_server *server, static void nfs4_init_opendata_res(struct nfs4_opendata *p) { p->o_res.f_attr = &p->f_attr; - p->o_res.f_label = p->f_label; p->o_res.seqid = p->o_arg.seqid; p->c_res.seqid = p->c_arg.seqid; p->o_res.server = p->o_arg.server; @@ -1355,8 +1354,8 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, if (p == NULL) goto err; - p->f_label = nfs4_label_alloc(server, gfp_mask); - if (IS_ERR(p->f_label)) + p->f_attr.label = nfs4_label_alloc(server, gfp_mask); + if (IS_ERR(p->f_attr.label)) goto err_free_p; p->a_label = nfs4_label_alloc(server, gfp_mask); @@ -1434,7 +1433,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry, err_free_label: nfs4_label_free(p->a_label); err_free_f: - nfs4_label_free(p->f_label); + nfs4_label_free(p->f_attr.label); err_free_p: kfree(p); err: @@ -1456,7 +1455,7 @@ static void nfs4_opendata_free(struct kref *kref) nfs4_put_state_owner(p->owner); nfs4_label_free(p->a_label); - nfs4_label_free(p->f_label); + nfs4_label_free(p->f_attr.label); dput(p->dir); dput(p->dentry); @@ -2009,7 +2008,7 @@ nfs4_opendata_get_inode(struct nfs4_opendata *data) if (!(data->f_attr.valid & NFS_ATTR_FATTR)) return ERR_PTR(-EAGAIN); inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, - &data->f_attr, data->f_label); + &data->f_attr, data->f_attr.label); break; default: inode = d_inode(data->dentry); @@ -2709,7 +2708,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data, if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) { nfs4_sequence_free_slot(&o_res->seq_res); nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, - o_res->f_label, NULL); + o_res->f_attr->label, NULL); } return 0; } @@ -3125,7 +3124,6 @@ static int _nfs4_do_open(struct inode *dir, enum open_claim_type4 claim = NFS4_OPEN_CLAIM_NULL; struct iattr *sattr = c->sattr; struct nfs4_label *label = c->label; - struct nfs4_label *olabel = NULL; int status; /* Protect against reboot recovery conflicts */ @@ -3148,19 +3146,11 @@ static int _nfs4_do_open(struct inode *dir, if (opendata == NULL) goto err_put_state_owner; - if (label) { - olabel = nfs4_label_alloc(server, GFP_KERNEL); - if (IS_ERR(olabel)) { - status = PTR_ERR(olabel); - goto err_opendata_put; - } - } - if (server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) { if (!opendata->f_attr.mdsthreshold) { opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc(); if (!opendata->f_attr.mdsthreshold) - goto err_free_label; + goto err_opendata_put; } opendata->o_arg.open_bitmap = &nfs4_pnfs_open_bitmap[0]; } @@ -3169,7 +3159,7 @@ static int _nfs4_do_open(struct inode *dir, status = _nfs4_open_and_get_state(opendata, flags, ctx); if (status != 0) - goto err_free_label; + goto err_opendata_put; state = ctx->state; if ((opendata->o_arg.open_flags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL) && @@ -3186,11 +3176,12 @@ static int _nfs4_do_open(struct inode *dir, nfs_fattr_init(opendata->o_res.f_attr); status = nfs4_do_setattr(state->inode, cred, opendata->o_res.f_attr, sattr, - ctx, label, olabel); + ctx, label, opendata->o_res.f_attr->label); if (status == 0) { nfs_setattr_update_inode(state->inode, sattr, opendata->o_res.f_attr); - nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel); + nfs_setsecurity(state->inode, opendata->o_res.f_attr, + opendata->o_res.f_attr->label); } sattr->ia_valid = ia_old; } @@ -3203,13 +3194,9 @@ static int _nfs4_do_open(struct inode *dir, opendata->f_attr.mdsthreshold = NULL; } - nfs4_label_free(olabel); - nfs4_opendata_put(opendata); nfs4_put_state_owner(sp); return 0; -err_free_label: - nfs4_label_free(olabel); err_opendata_put: nfs4_opendata_put(opendata); err_put_state_owner: diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 0044747f9314..09bd1d121318 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6524,7 +6524,7 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, goto out; if (res->access_request) decode_access(xdr, &res->access_supported, &res->access_result); - decode_getfattr_label(xdr, res->f_attr, res->f_label, res->server); + decode_getfattr_label(xdr, res->f_attr, res->f_attr->label, res->server); if (res->lg_res) decode_layoutget(xdr, rqstp, res->lg_res); out: diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index f0a685d9b8bd..cb28e01ea41e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -488,7 +488,6 @@ struct nfs_openres { struct nfs4_change_info cinfo; __u32 rflags; struct nfs_fattr * f_attr; - struct nfs4_label *f_label; struct nfs_seqid * seqid; const struct nfs_server *server; fmode_t delegation_type; -- cgit v1.2.3 From 2ef61e0eaa333e4e9c348c41a4b7abfb34b8736d Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:07 -0400 Subject: NFS: Remove the nfs4_label from the nfs4_getattr_res Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/client.c | 2 +- fs/nfs/dir.c | 2 +- fs/nfs/export.c | 18 ++++-------------- fs/nfs/inode.c | 20 +++++--------------- fs/nfs/nfs3proc.c | 3 +-- fs/nfs/nfs4_fs.h | 3 +-- fs/nfs/nfs4file.c | 2 +- fs/nfs/nfs4proc.c | 25 +++++++++++-------------- fs/nfs/nfs4xdr.c | 2 +- fs/nfs/proc.c | 3 +-- include/linux/nfs_xdr.h | 4 +--- 11 files changed, 28 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 960b9d87648e..1e4dc1ab9312 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1048,7 +1048,7 @@ struct nfs_server *nfs_create_server(struct fs_context *fc) if (!(fattr->valid & NFS_ATTR_FATTR)) { error = ctx->nfs_mod->rpc_ops->getattr(server, ctx->mntfh, - fattr, NULL, NULL); + fattr, NULL); if (error < 0) { dprintk("nfs_create_server: getattr error = %d\n", -error); goto error; diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8a327971d485..aa95a898ad0f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2056,7 +2056,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, if (!(fattr->valid & NFS_ATTR_FATTR)) { struct nfs_server *server = NFS_SB(dentry->d_sb); error = server->nfs_client->rpc_ops->getattr(server, fhandle, - fattr, NULL, NULL); + fattr, NULL); if (error < 0) goto out_error; } diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 895b404888dd..a0462f7e7e35 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -64,7 +64,6 @@ static struct dentry * nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { - struct nfs4_label *label = NULL; struct nfs_fattr *fattr = NULL; struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw); size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size; @@ -79,7 +78,7 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, if (fh_len < len || fh_type != len) return NULL; - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SB(sb)); if (fattr == NULL) { dentry = ERR_PTR(-ENOMEM); goto out; @@ -95,28 +94,19 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, if (inode) goto out_found; - label = nfs4_label_alloc(NFS_SB(sb), GFP_KERNEL); - if (IS_ERR(label)) { - dentry = ERR_CAST(label); - goto out_free_fattr; - } - rpc_ops = NFS_SB(sb)->nfs_client->rpc_ops; - ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label, NULL); + ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, NULL); if (ret) { dprintk("%s: getattr failed %d\n", __func__, ret); trace_nfs_fh_to_dentry(sb, server_fh, fattr->fileid, ret); dentry = ERR_PTR(ret); - goto out_free_label; + goto out_free_fattr; } - inode = nfs_fhget(sb, server_fh, fattr, label); + inode = nfs_fhget(sb, server_fh, fattr, fattr->label); out_found: dentry = d_obtain_alias(inode); - -out_free_label: - nfs4_label_free(label); out_free_fattr: nfs_free_fattr(fattr); out: diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 84c7efa2ea87..7d9dca781956 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -1194,7 +1194,6 @@ int __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { int status = -ESTALE; - struct nfs4_label *label = NULL; struct nfs_fattr *fattr = NULL; struct nfs_inode *nfsi = NFS_I(inode); @@ -1216,20 +1215,13 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) } status = -ENOMEM; - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) goto out; nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (IS_ERR(label)) { - status = PTR_ERR(label); - goto out; - } - - status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, - label, inode); + status = NFS_PROTO(inode)->getattr(server, NFS_FH(inode), fattr, inode); if (status != 0) { dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) getattr failed, error=%d\n", inode->i_sb->s_id, @@ -1246,7 +1238,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) else nfs_zap_caches(inode); } - goto err_out; + goto out; } status = nfs_refresh_inode(inode, fattr); @@ -1254,20 +1246,18 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) dfprintk(PAGECACHE, "nfs_revalidate_inode: (%s/%Lu) refresh failed, error=%d\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode), status); - goto err_out; + goto out; } if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr, fattr->label); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, (unsigned long long)NFS_FILEID(inode)); -err_out: - nfs4_label_free(label); out: nfs_free_fattr(fattr); trace_nfs_revalidate_inode_exit(inode, status); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 516f3340b226..7bae21a2ba05 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -100,8 +100,7 @@ nfs3_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, */ static int nfs3_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { struct rpc_message msg = { .rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR], diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index b621e29e6187..ed5eaca6801e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -316,8 +316,7 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid, const struct nfs_lock_context *l_ctx, fmode_t fmode); extern int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode); + struct nfs_fattr *fattr, struct inode *inode); extern int update_open_stateid(struct nfs4_state *state, const nfs4_stateid *open_stateid, const nfs4_stateid *deleg_stateid, diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 92a1b992a141..e2451f66024c 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -331,7 +331,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, if (!fattr) return ERR_PTR(-ENOMEM); - status = nfs4_proc_getattr(server, src_fh, fattr, NULL, NULL); + status = nfs4_proc_getattr(server, src_fh, fattr, NULL); if (status < 0) { res = ERR_PTR(status); goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index cb0613e0ef8f..f0262397faec 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -93,7 +93,8 @@ struct nfs4_opendata; static int _nfs4_recover_proc_open(struct nfs4_opendata *data); static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *); static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr); -static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct nfs4_label *label, struct inode *inode); +static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, + struct nfs_fattr *fattr, struct inode *inode); static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, struct nfs_open_context *ctx, struct nfs4_label *ilabel, @@ -2707,8 +2708,7 @@ static int _nfs4_proc_open(struct nfs4_opendata *data, } if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) { nfs4_sequence_free_slot(&o_res->seq_res); - nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, - o_res->f_attr->label, NULL); + nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, NULL); } return 0; } @@ -4090,7 +4090,6 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh, { int error; struct nfs_fattr *fattr = info->fattr; - struct nfs4_label *label = fattr->label; error = nfs4_server_capabilities(server, mntfh); if (error < 0) { @@ -4098,7 +4097,7 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh, return error; } - error = nfs4_proc_getattr(server, mntfh, fattr, label, NULL); + error = nfs4_proc_getattr(server, mntfh, fattr, NULL); if (error < 0) { dprintk("nfs4_get_root: getattr error = %d\n", -error); goto out; @@ -4161,8 +4160,7 @@ out: } static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { __u32 bitmask[NFS4_BITMASK_SZ]; struct nfs4_getattr_arg args = { @@ -4171,7 +4169,6 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, }; struct nfs4_getattr_res res = { .fattr = fattr, - .label = label, .server = server, }; struct rpc_message msg = { @@ -4188,7 +4185,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) task_flags |= RPC_TASK_TIMEOUT; - nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, label), inode, 0); + nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), inode, 0); nfs_fattr_init(fattr); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); return nfs4_do_call_sync(server->client, server, &msg, @@ -4196,15 +4193,14 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, } int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_getattr(server, fhandle, fattr, label, inode); + err = _nfs4_proc_getattr(server, fhandle, fattr, inode); trace_nfs4_getattr(server, fhandle, fattr, err); err = nfs4_handle_exception(server, err, &exception); @@ -5972,17 +5968,18 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf, size_t buflen) { struct nfs_server *server = NFS_SERVER(inode); - struct nfs_fattr fattr; struct nfs4_label label = {0, 0, buflen, buf}; u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL }; + struct nfs_fattr fattr = { + .label = &label, + }; struct nfs4_getattr_arg arg = { .fh = NFS_FH(inode), .bitmask = bitmask, }; struct nfs4_getattr_res res = { .fattr = &fattr, - .label = &label, .server = server, }; struct rpc_message msg = { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 09bd1d121318..d1b61b76bc82 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6386,7 +6386,7 @@ static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_putfh(xdr); if (status) goto out; - status = decode_getfattr_label(xdr, res->fattr, res->label, res->server); + status = decode_getfattr_label(xdr, res->fattr, res->fattr->label, res->server); out: return status; } diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 98a8901ede2e..baee21c2c091 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -100,8 +100,7 @@ nfs_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle, */ static int nfs_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, struct nfs4_label *label, - struct inode *inode) + struct nfs_fattr *fattr, struct inode *inode) { struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_GETATTR], diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index cb28e01ea41e..817f1bf5f187 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1063,7 +1063,6 @@ struct nfs4_getattr_res { struct nfs4_sequence_res seq_res; const struct nfs_server * server; struct nfs_fattr * fattr; - struct nfs4_label *label; }; struct nfs4_link_arg { @@ -1732,8 +1731,7 @@ struct nfs_rpc_ops { int (*submount) (struct fs_context *, struct nfs_server *); int (*try_get_tree) (struct fs_context *); int (*getattr) (struct nfs_server *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *, - struct inode *); + struct nfs_fattr *, struct inode *); int (*setattr) (struct dentry *, struct nfs_fattr *, struct iattr *); int (*lookup) (struct inode *, struct dentry *, -- cgit v1.2.3 From 1b00ad657997c8984a9e627a3bd37ea14f20beb2 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:08 -0400 Subject: NFS: Remove the nfs4_label from the nfs_setattrres Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/inode.c | 2 +- fs/nfs/nfs4proc.c | 56 ++++++++++++++----------------------------------- fs/nfs/nfs4xdr.c | 2 +- include/linux/nfs_xdr.h | 1 - 4 files changed, 18 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7d9dca781956..df109287f2e0 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -650,7 +650,7 @@ nfs_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - fattr = nfs_alloc_fattr(); + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { error = -ENOMEM; goto out; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f0262397faec..a0762ecc0c73 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -97,8 +97,7 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode); static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, - struct nfs_open_context *ctx, struct nfs4_label *ilabel, - struct nfs4_label *olabel); + struct nfs_open_context *ctx, struct nfs4_label *ilabel); #ifdef CONFIG_NFS_V4_1 static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, const struct cred *cred, @@ -3176,7 +3175,7 @@ static int _nfs4_do_open(struct inode *dir, nfs_fattr_init(opendata->o_res.f_attr); status = nfs4_do_setattr(state->inode, cred, opendata->o_res.f_attr, sattr, - ctx, label, opendata->o_res.f_attr->label); + ctx, label); if (status == 0) { nfs_setattr_update_inode(state->inode, sattr, opendata->o_res.f_attr); @@ -3341,8 +3340,7 @@ zero_stateid: static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, struct nfs_fattr *fattr, struct iattr *sattr, - struct nfs_open_context *ctx, struct nfs4_label *ilabel, - struct nfs4_label *olabel) + struct nfs_open_context *ctx, struct nfs4_label *ilabel) { struct nfs_server *server = NFS_SERVER(inode); __u32 bitmask[NFS4_BITMASK_SZ]; @@ -3356,7 +3354,6 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, }; struct nfs_setattrres res = { .fattr = fattr, - .label = olabel, .server = server, }; struct nfs4_exception exception = { @@ -3373,7 +3370,7 @@ static int nfs4_do_setattr(struct inode *inode, const struct cred *cred, adjust_flags |= NFS_INO_INVALID_OTHER; do { - nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, olabel), + nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), inode, adjust_flags); err = _nfs4_do_setattr(inode, &arg, &res, cred, ctx); @@ -4232,7 +4229,6 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, struct inode *inode = d_inode(dentry); const struct cred *cred = NULL; struct nfs_open_context *ctx = NULL; - struct nfs4_label *label = NULL; int status; if (pnfs_ld_layoutret_on_setattr(inode) && @@ -4258,20 +4254,15 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, cred = ctx->cred; } - label = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (IS_ERR(label)) - return PTR_ERR(label); - /* Return any delegations if we're going to change ACLs */ if ((sattr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) nfs4_inode_make_writeable(inode); - status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL, label); + status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL); if (status == 0) { nfs_setattr_update_inode(inode, sattr, fattr); - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr, fattr->label); } - nfs4_label_free(label); return status; } @@ -6021,8 +6012,7 @@ static int nfs4_get_security_label(struct inode *inode, void *buf, static int _nfs4_do_set_security_label(struct inode *inode, struct nfs4_label *ilabel, - struct nfs_fattr *fattr, - struct nfs4_label *olabel) + struct nfs_fattr *fattr) { struct iattr sattr = {0}; @@ -6037,7 +6027,6 @@ static int _nfs4_do_set_security_label(struct inode *inode, }; struct nfs_setattrres res = { .fattr = fattr, - .label = olabel, .server = server, }; struct rpc_message msg = { @@ -6058,15 +6047,13 @@ static int _nfs4_do_set_security_label(struct inode *inode, static int nfs4_do_set_security_label(struct inode *inode, struct nfs4_label *ilabel, - struct nfs_fattr *fattr, - struct nfs4_label *olabel) + struct nfs_fattr *fattr) { struct nfs4_exception exception = { }; int err; do { - err = _nfs4_do_set_security_label(inode, ilabel, - fattr, olabel); + err = _nfs4_do_set_security_label(inode, ilabel, fattr); trace_nfs4_set_security_label(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); @@ -6077,32 +6064,21 @@ static int nfs4_do_set_security_label(struct inode *inode, static int nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) { - struct nfs4_label ilabel, *olabel = NULL; - struct nfs_fattr fattr; + struct nfs4_label ilabel = {0, 0, buflen, (char *)buf }; + struct nfs_fattr *fattr; int status; if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL)) return -EOPNOTSUPP; - nfs_fattr_init(&fattr); - - ilabel.pi = 0; - ilabel.lfs = 0; - ilabel.label = (char *)buf; - ilabel.len = buflen; - - olabel = nfs4_label_alloc(NFS_SERVER(inode), GFP_KERNEL); - if (IS_ERR(olabel)) { - status = -PTR_ERR(olabel); - goto out; - } + fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); + if (fattr == NULL) + return -ENOMEM; - status = nfs4_do_set_security_label(inode, &ilabel, &fattr, olabel); + status = nfs4_do_set_security_label(inode, &ilabel, fattr); if (status == 0) - nfs_setsecurity(inode, &fattr, olabel); + nfs_setsecurity(inode, fattr, fattr->label); - nfs4_label_free(olabel); -out: return status; } #endif /* CONFIG_NFS_V4_SECURITY_LABEL */ diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index d1b61b76bc82..e3df7ada5988 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -6608,7 +6608,7 @@ static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp, status = decode_setattr(xdr); if (status) goto out; - decode_getfattr_label(xdr, res->fattr, res->label, res->server); + decode_getfattr_label(xdr, res->fattr, res->fattr->label, res->server); out: return status; } diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 817f1bf5f187..967a0098f0a9 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -832,7 +832,6 @@ struct nfs_getaclres { struct nfs_setattrres { struct nfs4_sequence_res seq_res; struct nfs_fattr * fattr; - struct nfs4_label *label; const struct nfs_server * server; }; -- cgit v1.2.3 From d91bfc46426d3d772fc0d9d165e3435fd0f0a79e Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:09 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_instantiate() Pull the label from the fattr instead. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 5 ++--- fs/nfs/nfs4proc.c | 2 +- fs/nfs/proc.c | 8 ++++---- include/linux/nfs_fs.h | 2 +- 4 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index aa95a898ad0f..48ea69af9446 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2075,12 +2075,11 @@ EXPORT_SYMBOL_GPL(nfs_add_or_obtain); * Code common to create, mkdir, and mknod. */ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fattr *fattr) { struct dentry *d; - d = nfs_add_or_obtain(dentry, fhandle, fattr, label); + d = nfs_add_or_obtain(dentry, fhandle, fattr, fattr->label); if (IS_ERR(d)) return PTR_ERR(d); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a0762ecc0c73..4d09c81502cf 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4859,7 +4859,7 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_ data->res.fattr->time_start, NFS_INO_INVALID_DATA); spin_unlock(&dir->i_lock); - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, data->res.fattr->label); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); } return status; } diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index baee21c2c091..73dcaa99fa9b 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -255,7 +255,7 @@ nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); nfs_mark_for_revalidate(dir); if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); nfs_free_createdata(data); out: dprintk("NFS reply create: %d\n", status); @@ -302,7 +302,7 @@ nfs_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr, status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); } if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); nfs_free_createdata(data); out: dprintk("NFS reply mknod: %d\n", status); @@ -434,7 +434,7 @@ nfs_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page, * should fill in the data with a LOOKUP call on the wire. */ if (status == 0) - status = nfs_instantiate(dentry, fh, fattr, NULL); + status = nfs_instantiate(dentry, fh, fattr); out_free: nfs_free_fattr(fattr); @@ -463,7 +463,7 @@ nfs_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr) status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); nfs_mark_for_revalidate(dir); if (status == 0) - status = nfs_instantiate(dentry, data->res.fh, data->res.fattr, NULL); + status = nfs_instantiate(dentry, data->res.fh, data->res.fattr); nfs_free_createdata(data); out: dprintk("NFS reply mkdir: %d\n", status); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 88c3aed8ad39..a8a9b71aeea6 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -532,7 +532,7 @@ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, - struct nfs_fattr *fattr, struct nfs4_label *label); + struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, -- cgit v1.2.3 From cc6f32989c3202349b90edde0c4702b098410fe8 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:10 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_add_or_obtain() Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 7 +++---- fs/nfs/nfs3proc.c | 2 +- include/linux/nfs_fs.h | 3 +-- 3 files changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 48ea69af9446..1c74f9d2f3a1 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2036,8 +2036,7 @@ static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct dentry * nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, - struct nfs_fattr *fattr, - struct nfs4_label *label) + struct nfs_fattr *fattr) { struct dentry *parent = dget_parent(dentry); struct inode *dir = d_inode(parent); @@ -2060,7 +2059,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, if (error < 0) goto out_error; } - inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label); + inode = nfs_fhget(dentry->d_sb, fhandle, fattr, fattr->label); d = d_splice_alias(inode, dentry); out: dput(parent); @@ -2079,7 +2078,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, { struct dentry *d; - d = nfs_add_or_obtain(dentry, fhandle, fattr, fattr->label); + d = nfs_add_or_obtain(dentry, fhandle, fattr); if (IS_ERR(d)) return PTR_ERR(d); diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 7bae21a2ba05..7100514d306b 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -321,7 +321,7 @@ nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata if (status != 0) return ERR_PTR(status); - return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr, NULL); + return nfs_add_or_obtain(dentry, data->res.fh, data->res.fattr); } static void nfs3_free_createdata(struct nfs3_createdata *data) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index a8a9b71aeea6..6eda001b306b 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -529,8 +529,7 @@ extern void nfs_set_verifier(struct dentry * dentry, unsigned long verf); extern void nfs_clear_verifier_delegated(struct inode *inode); #endif /* IS_ENABLED(CONFIG_NFS_V4) */ extern struct dentry *nfs_add_or_obtain(struct dentry *dentry, - struct nfs_fh *fh, struct nfs_fattr *fattr, - struct nfs4_label *label); + struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); -- cgit v1.2.3 From cf7ab00aabbf9c8f1ec72edff15849ddc23aa6a7 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:11 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_fhget() Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 6 +++--- fs/nfs/export.c | 4 ++-- fs/nfs/getroot.c | 2 +- fs/nfs/inode.c | 4 ++-- fs/nfs/nfs4file.c | 3 +-- fs/nfs/nfs4proc.c | 2 +- include/linux/nfs_fs.h | 2 +- 7 files changed, 11 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 1c74f9d2f3a1..bd89f39e8ba9 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -697,7 +697,7 @@ again: goto out; } - inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->fattr->label); + inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); alias = d_splice_alias(inode, dentry); d_lookup_done(dentry); if (alias) { @@ -1782,7 +1782,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in res = ERR_PTR(error); goto out; } - inode = nfs_fhget(dentry->d_sb, fhandle, fattr, fattr->label); + inode = nfs_fhget(dentry->d_sb, fhandle, fattr); res = ERR_CAST(inode); if (IS_ERR(res)) goto out; @@ -2059,7 +2059,7 @@ nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle, if (error < 0) goto out_error; } - inode = nfs_fhget(dentry->d_sb, fhandle, fattr, fattr->label); + inode = nfs_fhget(dentry->d_sb, fhandle, fattr); d = d_splice_alias(inode, dentry); out: dput(parent); diff --git a/fs/nfs/export.c b/fs/nfs/export.c index a0462f7e7e35..171c424cb6d5 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -103,7 +103,7 @@ nfs_fh_to_dentry(struct super_block *sb, struct fid *fid, goto out_free_fattr; } - inode = nfs_fhget(sb, server_fh, fattr, fattr->label); + inode = nfs_fhget(sb, server_fh, fattr); out_found: dentry = d_obtain_alias(inode); @@ -138,7 +138,7 @@ nfs_get_parent(struct dentry *dentry) goto out; } - pinode = nfs_fhget(sb, &fh, fattr, fattr->label); + pinode = nfs_fhget(sb, &fh, fattr); parent = d_obtain_alias(pinode); out: nfs_free_fattr(fattr); diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 7604cb6a0ac2..0aedee201166 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -91,7 +91,7 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) goto out_fattr; } - inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr, NULL); + inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr); if (IS_ERR(inode)) { dprintk("nfs_get_root: get root inode failed\n"); error = PTR_ERR(inode); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index df109287f2e0..be28f0251dee 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -448,7 +448,7 @@ static void nfs_inode_init_dir(struct nfs_inode *nfsi) * instead of inode number. */ struct inode * -nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, struct nfs4_label *label) +nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) { struct nfs_find_desc desc = { .fh = fh, @@ -581,7 +581,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); - nfs_setsecurity(inode, fattr, label); + nfs_setsecurity(inode, fattr, fattr->label); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index e2451f66024c..e79ae4cbc395 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -344,8 +344,7 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt, goto out; snprintf(read_name, len, SSC_READ_NAME_BODY, read_name_gen++); - r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr, - NULL); + r_ino = nfs_fhget(ss_mnt->mnt_root->d_inode->i_sb, src_fh, fattr); if (IS_ERR(r_ino)) { res = ERR_CAST(r_ino); goto out_free_name; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4d09c81502cf..b25adb2250ef 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2008,7 +2008,7 @@ nfs4_opendata_get_inode(struct nfs4_opendata *data) if (!(data->f_attr.valid & NFS_ATTR_FATTR)) return ERR_PTR(-EAGAIN); inode = nfs_fhget(data->dir->d_sb, &data->o_res.fh, - &data->f_attr, data->f_attr.label); + &data->f_attr); break; default: inode = d_inode(data->dentry); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 6eda001b306b..c36c6a559fc9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -388,7 +388,7 @@ extern void nfs_zap_caches(struct inode *); extern void nfs_set_inode_stale(struct inode *inode); extern void nfs_invalidate_atime(struct inode *); extern struct inode *nfs_fhget(struct super_block *, struct nfs_fh *, - struct nfs_fattr *, struct nfs4_label *); + struct nfs_fattr *); struct inode *nfs_ilookup(struct super_block *sb, struct nfs_fattr *, struct nfs_fh *); extern int nfs_refresh_inode(struct inode *, struct nfs_fattr *); extern int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr); -- cgit v1.2.3 From dd225cb3b02b827271a2284f89102fc81efcbf6f Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Fri, 22 Oct 2021 13:11:12 -0400 Subject: NFS: Remove the nfs4_label argument from nfs_setsecurity Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- fs/nfs/dir.c | 5 ++--- fs/nfs/getroot.c | 2 +- fs/nfs/inode.c | 20 +++++++++----------- fs/nfs/nfs4proc.c | 9 ++++----- include/linux/nfs_fs.h | 3 +-- 5 files changed, 17 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index bd89f39e8ba9..731d31015b6a 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -682,8 +682,7 @@ again: nfs_set_verifier(dentry, dir_verifier); status = nfs_refresh_inode(d_inode(dentry), entry->fattr); if (!status) - nfs_setsecurity(d_inode(dentry), entry->fattr, - entry->fattr->label); + nfs_setsecurity(d_inode(dentry), entry->fattr); goto out; } else { d_invalidate(dentry); @@ -1523,7 +1522,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry, if (nfs_refresh_inode(inode, fattr) < 0) goto out; - nfs_setsecurity(inode, fattr, fattr->label); + nfs_setsecurity(inode, fattr); nfs_set_verifier(dentry, dir_verifier); /* set a readdirplus hint that we had a cache miss */ diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index 0aedee201166..11ff2b2e060f 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -148,7 +148,7 @@ int nfs_get_root(struct super_block *s, struct fs_context *fc) !(kflags_out & SECURITY_LSM_NATIVE_LABELS)) server->caps &= ~NFS_CAP_SECURITY_LABEL; - nfs_setsecurity(inode, fsinfo.fattr, fsinfo.fattr->label); + nfs_setsecurity(inode, fsinfo.fattr); error = 0; out_fattr: diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index be28f0251dee..dd53704c3f40 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -355,23 +355,22 @@ static void nfs_clear_label_invalid(struct inode *inode) spin_unlock(&inode->i_lock); } -void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label) +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { int error; - if (label == NULL) + if (fattr->label == NULL) return; if ((fattr->valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL) && inode->i_security) { - error = security_inode_notifysecctx(inode, label->label, - label->len); + error = security_inode_notifysecctx(inode, fattr->label->label, + fattr->label->len); if (error) printk(KERN_ERR "%s() %s %d " "security_inode_notifysecctx() %d\n", __func__, - (char *)label->label, - label->len, error); + (char *)fattr->label->label, + fattr->label->len, error); nfs_clear_label_invalid(inode); } } @@ -398,8 +397,7 @@ struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) } EXPORT_SYMBOL_GPL(nfs4_label_alloc); #else -void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label) +void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr) { } #endif @@ -581,7 +579,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) fattr->size != 0) nfs_set_cache_invalid(inode, NFS_INO_INVALID_BLOCKS); - nfs_setsecurity(inode, fattr, fattr->label); + nfs_setsecurity(inode, fattr); nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = now; @@ -1252,7 +1250,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); - nfs_setsecurity(inode, fattr, fattr->label); + nfs_setsecurity(inode, fattr); dfprintk(PAGECACHE, "NFS: (%s/%Lu) revalidation complete\n", inode->i_sb->s_id, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index b25adb2250ef..535436dbdc9a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3179,8 +3179,7 @@ static int _nfs4_do_open(struct inode *dir, if (status == 0) { nfs_setattr_update_inode(state->inode, sattr, opendata->o_res.f_attr); - nfs_setsecurity(state->inode, opendata->o_res.f_attr, - opendata->o_res.f_attr->label); + nfs_setsecurity(state->inode, opendata->o_res.f_attr); } sattr->ia_valid = ia_old; } @@ -4261,7 +4260,7 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr, status = nfs4_do_setattr(inode, cred, fattr, sattr, ctx, NULL); if (status == 0) { nfs_setattr_update_inode(inode, sattr, fattr); - nfs_setsecurity(inode, fattr, fattr->label); + nfs_setsecurity(inode, fattr); } return status; } @@ -4782,7 +4781,7 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, const struct nfs4_inc_nlink(inode); status = nfs_post_op_update_inode(inode, res.fattr); if (!status) - nfs_setsecurity(inode, res.fattr, res.fattr->label); + nfs_setsecurity(inode, res.fattr); } out: @@ -6077,7 +6076,7 @@ nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen) status = nfs4_do_set_security_label(inode, &ilabel, fattr); if (status == 0) - nfs_setsecurity(inode, fattr, fattr->label); + nfs_setsecurity(inode, fattr); return status; } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c36c6a559fc9..05f249f20f55 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -409,8 +409,7 @@ extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *map extern int nfs_revalidate_mapping_rcu(struct inode *inode); extern int nfs_setattr(struct user_namespace *, struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, struct nfs_fattr *); -extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr, - struct nfs4_label *label); +extern void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, const struct cred *cred, fmode_t mode); -- cgit v1.2.3 From 3990ed4c426652fcd469f8c9dc08156294b36c28 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 5 Nov 2021 18:40:14 -0700 Subject: bpf: Stop caching subprog index in the bpf_pseudo_func insn This patch is to fix an out-of-bound access issue when jit-ing the bpf_pseudo_func insn (i.e. ld_imm64 with src_reg == BPF_PSEUDO_FUNC) In jit_subprog(), it currently reuses the subprog index cached in insn[1].imm. This subprog index is an index into a few array related to subprogs. For example, in jit_subprog(), it is an index to the newly allocated 'struct bpf_prog **func' array. The subprog index was cached in insn[1].imm after add_subprog(). However, this could become outdated (and too big in this case) if some subprogs are completely removed during dead code elimination (in adjust_subprog_starts_after_remove). The cached index in insn[1].imm is not updated accordingly and causing out-of-bound issue in the later jit_subprog(). Unlike bpf_pseudo_'func' insn, the current bpf_pseudo_'call' insn is handling the DCE properly by calling find_subprog(insn->imm) to figure out the index instead of caching the subprog index. The existing bpf_adj_branches() will adjust the insn->imm whenever insn is added or removed. Instead of having two ways handling subprog index, this patch is to make bpf_pseudo_func works more like bpf_pseudo_call. First change is to stop caching the subprog index result in insn[1].imm after add_subprog(). The verification process will use find_subprog(insn->imm) to figure out the subprog index. Second change is in bpf_adj_branches() and have it to adjust the insn->imm for the bpf_pseudo_func insn also whenever insn is added or removed. Third change is in jit_subprog(). Like the bpf_pseudo_call handling, bpf_pseudo_func temporarily stores the find_subprog() result in insn->off. It is fine because the prog's insn has been finalized at this point. insn->off will be reset back to 0 later to avoid confusing the userspace prog dump tool. Fixes: 69c087ba6225 ("bpf: Add bpf_for_each_map_elem() helper") Signed-off-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211106014014.651018-1-kafai@fb.com --- include/linux/bpf.h | 6 ++++++ kernel/bpf/core.c | 7 +++++++ kernel/bpf/verifier.c | 37 ++++++++++++++----------------------- 3 files changed, 27 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2be6dfd68df9..f715e8863f4d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -484,6 +484,12 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) aux->ctx_field_size = size; } +static inline bool bpf_pseudo_func(const struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && + insn->src_reg == BPF_PSEUDO_FUNC; +} + struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 327e3996eadb..2405e39d800f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -390,6 +390,13 @@ static int bpf_adj_branches(struct bpf_prog *prog, u32 pos, s32 end_old, i = end_new; insn = prog->insnsi + end_old; } + if (bpf_pseudo_func(insn)) { + ret = bpf_adj_delta_to_imm(insn, pos, end_old, + end_new, i, probe_pass); + if (ret) + return ret; + continue; + } code = insn->code; if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) || diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5f8d9128860a..890b3ec375a3 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -240,12 +240,6 @@ static bool bpf_pseudo_kfunc_call(const struct bpf_insn *insn) insn->src_reg == BPF_PSEUDO_KFUNC_CALL; } -static bool bpf_pseudo_func(const struct bpf_insn *insn) -{ - return insn->code == (BPF_LD | BPF_IMM | BPF_DW) && - insn->src_reg == BPF_PSEUDO_FUNC; -} - struct bpf_call_arg_meta { struct bpf_map *map_ptr; bool raw_mode; @@ -1960,16 +1954,10 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env) return -EPERM; } - if (bpf_pseudo_func(insn)) { + if (bpf_pseudo_func(insn) || bpf_pseudo_call(insn)) ret = add_subprog(env, i + insn->imm + 1); - if (ret >= 0) - /* remember subprog */ - insn[1].imm = ret; - } else if (bpf_pseudo_call(insn)) { - ret = add_subprog(env, i + insn->imm + 1); - } else { + else ret = add_kfunc_call(env, insn->imm, insn->off); - } if (ret < 0) return ret; @@ -9387,7 +9375,8 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->src_reg == BPF_PSEUDO_FUNC) { struct bpf_prog_aux *aux = env->prog->aux; - u32 subprogno = insn[1].imm; + u32 subprogno = find_subprog(env, + env->insn_idx + insn->imm + 1); if (!aux->func_info) { verbose(env, "missing btf func_info\n"); @@ -12557,14 +12546,9 @@ static int jit_subprogs(struct bpf_verifier_env *env) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { - if (bpf_pseudo_func(insn)) { - env->insn_aux_data[i].call_imm = insn->imm; - /* subprog is encoded in insn[1].imm */ + if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn)) continue; - } - if (!bpf_pseudo_call(insn)) - continue; /* Upon error here we cannot fall back to interpreter but * need a hard reject of the program. Thus -EFAULT is * propagated in any case. @@ -12585,6 +12569,12 @@ static int jit_subprogs(struct bpf_verifier_env *env) env->insn_aux_data[i].call_imm = insn->imm; /* point imm to __bpf_call_base+1 from JITs point of view */ insn->imm = 1; + if (bpf_pseudo_func(insn)) + /* jit (e.g. x86_64) may emit fewer instructions + * if it learns a u32 imm is the same as a u64 imm. + * Force a non zero here. + */ + insn[1].imm = 1; } err = bpf_prog_alloc_jited_linfo(prog); @@ -12669,7 +12659,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (bpf_pseudo_func(insn)) { - subprog = insn[1].imm; + subprog = insn->off; insn[0].imm = (u32)(long)func[subprog]->bpf_func; insn[1].imm = ((u64)(long)func[subprog]->bpf_func) >> 32; continue; @@ -12720,7 +12710,8 @@ static int jit_subprogs(struct bpf_verifier_env *env) for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { if (bpf_pseudo_func(insn)) { insn[0].imm = env->insn_aux_data[i].call_imm; - insn[1].imm = find_subprog(env, i + insn[0].imm + 1); + insn[1].imm = insn->off; + insn->off = 0; continue; } if (!bpf_pseudo_call(insn)) -- cgit v1.2.3 From 8587ca6f34152ea650bad4b2db68456601159024 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 5 Nov 2021 13:35:07 -0700 Subject: mm: move kvmalloc-related functions to slab.h Not all files in the kernel should include mm.h. Migrating callers from kmalloc to kvmalloc is easier if the kvmalloc functions are in slab.h. [akpm@linux-foundation.org: move the new kvrealloc() also] [akpm@linux-foundation.org: drivers/hwmon/occ/p9_sbe.c needs slab.h] Link: https://lkml.kernel.org/r/20210622215757.3525604-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Pekka Enberg Cc: Christoph Lameter Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/hwmon/occ/p9_sbe.c | 1 + drivers/of/kexec.c | 1 + include/linux/mm.h | 34 ---------------------------------- include/linux/slab.h | 34 ++++++++++++++++++++++++++++++++++ 4 files changed, 36 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/hwmon/occ/p9_sbe.c b/drivers/hwmon/occ/p9_sbe.c index f6387cc0b754..6c540b24b32f 100644 --- a/drivers/hwmon/occ/p9_sbe.c +++ b/drivers/hwmon/occ/p9_sbe.c @@ -3,6 +3,7 @@ #include #include +#include #include #include #include diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index 761fd870d1db..053e241f593c 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #define RNG_SEED_SIZE 128 diff --git a/include/linux/mm.h b/include/linux/mm.h index 73a52aba448f..32b2ecc47408 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -799,40 +799,6 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif -extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kvmalloc(size_t size, gfp_t flags) -{ - return kvmalloc_node(size, flags, NUMA_NO_NODE); -} -static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) -{ - return kvmalloc_node(size, flags | __GFP_ZERO, node); -} -static inline void *kvzalloc(size_t size, gfp_t flags) -{ - return kvmalloc(size, flags | __GFP_ZERO); -} - -static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) -{ - size_t bytes; - - if (unlikely(check_mul_overflow(n, size, &bytes))) - return NULL; - - return kvmalloc(bytes, flags); -} - -static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) -{ - return kvmalloc_array(n, size, flags | __GFP_ZERO); -} - -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, - gfp_t flags); -extern void kvfree(const void *addr); -extern void kvfree_sensitive(const void *addr, size_t len); - static inline int head_compound_mapcount(struct page *head) { return atomic_read(compound_mapcount_ptr(head)) + 1; diff --git a/include/linux/slab.h b/include/linux/slab.h index 083f3ce550bc..c0d46b6fa12a 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -732,6 +732,40 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node) return kmalloc_node(size, flags | __GFP_ZERO, node); } +extern void *kvmalloc_node(size_t size, gfp_t flags, int node); +static inline void *kvmalloc(size_t size, gfp_t flags) +{ + return kvmalloc_node(size, flags, NUMA_NO_NODE); +} +static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +{ + return kvmalloc_node(size, flags | __GFP_ZERO, node); +} +static inline void *kvzalloc(size_t size, gfp_t flags) +{ + return kvmalloc(size, flags | __GFP_ZERO); +} + +static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + + return kvmalloc(bytes, flags); +} + +static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +{ + return kvmalloc_array(n, size, flags | __GFP_ZERO); +} + +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, + gfp_t flags); +extern void kvfree(const void *addr); +extern void kvfree_sensitive(const void *addr, size_t len); + unsigned int kmem_cache_size(struct kmem_cache *s); void __init kmem_cache_init_late(void); -- cgit v1.2.3 From b47291ef02b0bee85ffb7efd6c336060ad1fe1a4 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 5 Nov 2021 13:35:17 -0700 Subject: mm, slub: change percpu partial accounting from objects to pages With CONFIG_SLUB_CPU_PARTIAL enabled, SLUB keeps a percpu list of partial slabs that can be promoted to cpu slab when the previous one is depleted, without accessing the shared partial list. A slab can be added to this list by 1) refill of an empty list from get_partial_node() - once we really have to access the shared partial list, we acquire multiple slabs to amortize the cost of locking, and 2) first free to a previously full slab - instead of putting the slab on a shared partial list, we can more cheaply freeze it and put it on the per-cpu list. To control how large a percpu partial list can grow for a kmem cache, set_cpu_partial() calculates a target number of free objects on each cpu's percpu partial list, and this can be also set by the sysfs file cpu_partial. However, the tracking of actual number of objects is imprecise, in order to limit overhead from cpu X freeing an objects to a slab on percpu partial list of cpu Y. Basically, the percpu partial slabs form a single linked list, and when we add a new slab to the list with current head "oldpage", we set in the struct page of the slab we're adding: page->pages = oldpage->pages + 1; // this is precise page->pobjects = oldpage->pobjects + (page->objects - page->inuse); page->next = oldpage; Thus the real number of free objects in the slab (objects - inuse) is only determined at the moment of adding the slab to the percpu partial list, and further freeing doesn't update the pobjects counter nor propagate it to the current list head. As Jann reports [1], this can easily lead to large inaccuracies, where the target number of objects (up to 30 by default) can translate to the same number of (empty) slab pages on the list. In case 2) above, we put a slab with 1 free object on the list, thus only increase page->pobjects by 1, even if there are subsequent frees on the same slab. Jann has noticed this in practice and so did we [2] when investigating significant increase of kmemcg usage after switching from SLAB to SLUB. While this is no longer a problem in kmemcg context thanks to the accounting rewrite in 5.9, the memory waste is still not ideal and it's questionable whether it makes sense to perform free object count based control when object counts can easily become so much inaccurate. So this patch converts the accounting to be based on number of pages only (which is precise) and removes the page->pobjects field completely. This is also ultimately simpler. To retain the existing set_cpu_partial() heuristic, first calculate the target number of objects as previously, but then convert it to target number of pages by assuming the pages will be half-filled on average. This assumption might obviously also be inaccurate in practice, but cannot degrade to actual number of pages being equal to the target number of objects. We could also skip the intermediate step with target number of objects and rewrite the heuristic in terms of pages. However we still have the sysfs file cpu_partial which uses number of objects and could break existing users if it suddenly becomes number of pages, so this patch doesn't do that. In practice, after this patch the heuristics limit the size of percpu partial list up to 2 pages. In case of a reported regression (which would mean some workload has benefited from the previous imprecise object based counting), we can tune the heuristics to get a better compromise within the new scheme, while still avoid the unexpectedly long percpu partial lists. [1] https://lore.kernel.org/linux-mm/CAG48ez2Qx5K1Cab-m8BdSibp6wLTip6ro4=-umR7BLsEgjEYzA@mail.gmail.com/ [2] https://lore.kernel.org/all/2f0f46e8-2535-410a-1859-e9cfa4e57c18@suse.cz/ ========== Evaluation ========== Mel was kind enough to run v1 through mmtests machinery for netperf (localhost) and hackbench and, for most significant results see below. So there are some apparent regressions, especially with hackbench, which I think ultimately boils down to having shorter percpu partial lists on average and some benchmarks benefiting from longer ones. Monitoring slab usage also indicated less memory usage by slab. Based on that, the following patch will bump the defaults to allow longer percpu partial lists than after this patch. However the goal is certainly not such that we would limit the percpu partial lists to 30 pages just because previously a specific alloc/free pattern could lead to the limit of 30 objects translate to a limit to 30 pages - that would make little sense. This is a correctness patch, and if a workload benefits from larger lists, the sysfs tuning knobs are still there to allow that. Netperf 2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM TCP-RR: hmean before 127045.79 after 121092.94 (-4.69%, worse) stddev before 2634.37 after 1254.08 UDP-RR: hmean before 166985.45 after 160668.94 ( -3.78%, worse) stddev before 4059.69 after 1943.63 2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM TCP-RR: hmean before 84173.25 after 76914.72 ( -8.62%, worse) UDP-RR: hmean before 93571.12 after 96428.69 ( 3.05%, better) stddev before 23118.54 after 16828.14 2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM TCP-RR: hmean before 49984.92 after 48922.27 ( -2.13%, worse) stddev before 6248.15 after 4740.51 UDP-RR: hmean before 61854.31 after 68761.81 ( 11.17%, better) stddev before 4093.54 after 5898.91 other machines - within 2% Hackbench (results before and after the patch, negative % means worse) 2-socket AMD EPYC 7713 (64 cores, 128 threads per core), 256GB RAM hackbench-process-sockets Amean 1 0.5380 0.5583 ( -3.78%) Amean 4 0.7510 0.8150 ( -8.52%) Amean 7 0.7930 0.9533 ( -20.22%) Amean 12 0.7853 1.1313 ( -44.06%) Amean 21 1.1520 1.4993 ( -30.15%) Amean 30 1.6223 1.9237 ( -18.57%) Amean 48 2.6767 2.9903 ( -11.72%) Amean 79 4.0257 5.1150 ( -27.06%) Amean 110 5.5193 7.4720 ( -35.38%) Amean 141 7.2207 9.9840 ( -38.27%) Amean 172 8.4770 12.1963 ( -43.88%) Amean 203 9.6473 14.3137 ( -48.37%) Amean 234 11.3960 18.7917 ( -64.90%) Amean 265 13.9627 22.4607 ( -60.86%) Amean 296 14.9163 26.0483 ( -74.63%) hackbench-thread-sockets Amean 1 0.5597 0.5877 ( -5.00%) Amean 4 0.7913 0.8960 ( -13.23%) Amean 7 0.8190 1.0017 ( -22.30%) Amean 12 0.9560 1.1727 ( -22.66%) Amean 21 1.7587 1.5660 ( 10.96%) Amean 30 2.4477 1.9807 ( 19.08%) Amean 48 3.4573 3.0630 ( 11.41%) Amean 79 4.7903 5.1733 ( -8.00%) Amean 110 6.1370 7.4220 ( -20.94%) Amean 141 7.5777 9.2617 ( -22.22%) Amean 172 9.2280 11.0907 ( -20.18%) Amean 203 10.2793 13.3470 ( -29.84%) Amean 234 11.2410 17.1070 ( -52.18%) Amean 265 12.5970 23.3323 ( -85.22%) Amean 296 17.1540 24.2857 ( -41.57%) 2-socket Intel(R) Xeon(R) Gold 5218R CPU @ 2.10GHz (20 cores, 40 threads per socket), 384GB RAM hackbench-process-sockets Amean 1 0.5760 0.4793 ( 16.78%) Amean 4 0.9430 0.9707 ( -2.93%) Amean 7 1.5517 1.8843 ( -21.44%) Amean 12 2.4903 2.7267 ( -9.49%) Amean 21 3.9560 4.2877 ( -8.38%) Amean 30 5.4613 5.8343 ( -6.83%) Amean 48 8.5337 9.2937 ( -8.91%) Amean 79 14.0670 15.2630 ( -8.50%) Amean 110 19.2253 21.2467 ( -10.51%) Amean 141 23.7557 25.8550 ( -8.84%) Amean 172 28.4407 29.7603 ( -4.64%) Amean 203 33.3407 33.9927 ( -1.96%) Amean 234 38.3633 39.1150 ( -1.96%) Amean 265 43.4420 43.8470 ( -0.93%) Amean 296 48.3680 48.9300 ( -1.16%) hackbench-thread-sockets Amean 1 0.6080 0.6493 ( -6.80%) Amean 4 1.0000 1.0513 ( -5.13%) Amean 7 1.6607 2.0260 ( -22.00%) Amean 12 2.7637 2.9273 ( -5.92%) Amean 21 5.0613 4.5153 ( 10.79%) Amean 30 6.3340 6.1140 ( 3.47%) Amean 48 9.0567 9.5577 ( -5.53%) Amean 79 14.5657 15.7983 ( -8.46%) Amean 110 19.6213 21.6333 ( -10.25%) Amean 141 24.1563 26.2697 ( -8.75%) Amean 172 28.9687 30.2187 ( -4.32%) Amean 203 33.9763 34.6970 ( -2.12%) Amean 234 38.8647 39.3207 ( -1.17%) Amean 265 44.0813 44.1507 ( -0.16%) Amean 296 49.2040 49.4330 ( -0.47%) 2-socket Intel(R) Xeon(R) CPU E5-2698 v4 @ 2.20GHz (20 cores, 40 threads per socket), 512GB RAM hackbench-process-sockets Amean 1 0.5027 0.5017 ( 0.20%) Amean 4 1.1053 1.2033 ( -8.87%) Amean 7 1.8760 2.1820 ( -16.31%) Amean 12 2.9053 3.1810 ( -9.49%) Amean 21 4.6777 4.9920 ( -6.72%) Amean 30 6.5180 6.7827 ( -4.06%) Amean 48 10.0710 10.5227 ( -4.48%) Amean 79 16.4250 17.5053 ( -6.58%) Amean 110 22.6203 24.4617 ( -8.14%) Amean 141 28.0967 31.0363 ( -10.46%) Amean 172 34.4030 36.9233 ( -7.33%) Amean 203 40.5933 43.0850 ( -6.14%) Amean 234 46.6477 48.7220 ( -4.45%) Amean 265 53.0530 53.9597 ( -1.71%) Amean 296 59.2760 59.9213 ( -1.09%) hackbench-thread-sockets Amean 1 0.5363 0.5330 ( 0.62%) Amean 4 1.1647 1.2157 ( -4.38%) Amean 7 1.9237 2.2833 ( -18.70%) Amean 12 2.9943 3.3110 ( -10.58%) Amean 21 4.9987 5.1880 ( -3.79%) Amean 30 6.7583 7.0043 ( -3.64%) Amean 48 10.4547 10.8353 ( -3.64%) Amean 79 16.6707 17.6790 ( -6.05%) Amean 110 22.8207 24.4403 ( -7.10%) Amean 141 28.7090 31.0533 ( -8.17%) Amean 172 34.9387 36.8260 ( -5.40%) Amean 203 41.1567 43.0450 ( -4.59%) Amean 234 47.3790 48.5307 ( -2.43%) Amean 265 53.9543 54.6987 ( -1.38%) Amean 296 60.0820 60.2163 ( -0.22%) 1-socket Intel(R) Xeon(R) CPU E3-1240 v5 @ 3.50GHz (4 cores, 8 threads), 32 GB RAM hackbench-process-sockets Amean 1 1.4760 1.5773 ( -6.87%) Amean 3 3.9370 4.0910 ( -3.91%) Amean 5 6.6797 6.9357 ( -3.83%) Amean 7 9.3367 9.7150 ( -4.05%) Amean 12 15.7627 16.1400 ( -2.39%) Amean 18 23.5360 23.6890 ( -0.65%) Amean 24 31.0663 31.3137 ( -0.80%) Amean 30 38.7283 39.0037 ( -0.71%) Amean 32 41.3417 41.6097 ( -0.65%) hackbench-thread-sockets Amean 1 1.5250 1.6043 ( -5.20%) Amean 3 4.0897 4.2603 ( -4.17%) Amean 5 6.7760 7.0933 ( -4.68%) Amean 7 9.4817 9.9157 ( -4.58%) Amean 12 15.9610 16.3937 ( -2.71%) Amean 18 23.9543 24.3417 ( -1.62%) Amean 24 31.4400 31.7217 ( -0.90%) Amean 30 39.2457 39.5467 ( -0.77%) Amean 32 41.8267 42.1230 ( -0.71%) 2-socket Intel(R) Xeon(R) CPU E5-2670 v3 @ 2.30GHz (12 cores, 24 threads per socket), 64GB RAM hackbench-process-sockets Amean 1 1.0347 1.0880 ( -5.15%) Amean 4 1.7267 1.8527 ( -7.30%) Amean 7 2.6707 2.8110 ( -5.25%) Amean 12 4.1617 4.3383 ( -4.25%) Amean 21 7.0070 7.2600 ( -3.61%) Amean 30 9.9187 10.2397 ( -3.24%) Amean 48 15.6710 16.3923 ( -4.60%) Amean 79 24.7743 26.1247 ( -5.45%) Amean 110 34.3000 35.9307 ( -4.75%) Amean 141 44.2043 44.8010 ( -1.35%) Amean 172 54.2430 54.7260 ( -0.89%) Amean 192 60.6557 60.9777 ( -0.53%) hackbench-thread-sockets Amean 1 1.0610 1.1353 ( -7.01%) Amean 4 1.7543 1.9140 ( -9.10%) Amean 7 2.7840 2.9573 ( -6.23%) Amean 12 4.3813 4.4937 ( -2.56%) Amean 21 7.3460 7.5350 ( -2.57%) Amean 30 10.2313 10.5190 ( -2.81%) Amean 48 15.9700 16.5940 ( -3.91%) Amean 79 25.3973 26.6637 ( -4.99%) Amean 110 35.1087 36.4797 ( -3.91%) Amean 141 45.8220 46.3053 ( -1.05%) Amean 172 55.4917 55.7320 ( -0.43%) Amean 192 62.7490 62.5410 ( 0.33%) Link: https://lkml.kernel.org/r/20211012134651.11258-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Reported-by: Jann Horn Cc: Roman Gushchin Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 -- include/linux/slub_def.h | 13 ++----- mm/slub.c | 89 ++++++++++++++++++++++++++++++++---------------- 3 files changed, 61 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7f8ee09c711f..68ffa064b7a8 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -124,10 +124,8 @@ struct page { struct page *next; #ifdef CONFIG_64BIT int pages; /* Nr of pages left */ - int pobjects; /* Approximate count */ #else short int pages; - short int pobjects; #endif }; }; diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 85499f0586b0..0fa751b946fa 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -99,6 +99,8 @@ struct kmem_cache { #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; + /* Number of per cpu partial pages to keep around */ + unsigned int cpu_partial_pages; #endif struct kmem_cache_order_objects oo; @@ -141,17 +143,6 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -#ifdef CONFIG_SLUB_CPU_PARTIAL -#define slub_cpu_partial(s) ((s)->cpu_partial) -#define slub_set_cpu_partial(s, n) \ -({ \ - slub_cpu_partial(s) = (n); \ -}) -#else -#define slub_cpu_partial(s) (0) -#define slub_set_cpu_partial(s, n) -#endif /* CONFIG_SLUB_CPU_PARTIAL */ - #ifdef CONFIG_SYSFS #define SLAB_SUPPORTS_SYSFS void sysfs_slab_unlink(struct kmem_cache *); diff --git a/mm/slub.c b/mm/slub.c index b6a1790812f7..0df81ea24b91 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -414,6 +414,29 @@ static inline unsigned int oo_objects(struct kmem_cache_order_objects x) return x.x & OO_MASK; } +#ifdef CONFIG_SLUB_CPU_PARTIAL +static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) +{ + unsigned int nr_pages; + + s->cpu_partial = nr_objects; + + /* + * We take the number of objects but actually limit the number of + * pages on the per cpu partial list, in order to limit excessive + * growth of the list. For simplicity we assume that the pages will + * be half-full. + */ + nr_pages = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo)); + s->cpu_partial_pages = nr_pages; +} +#else +static inline void +slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) +{ +} +#endif /* CONFIG_SLUB_CPU_PARTIAL */ + /* * Per slab locking using the pagelock */ @@ -2052,7 +2075,7 @@ static inline void remove_partial(struct kmem_cache_node *n, */ static inline void *acquire_slab(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page, - int mode, int *objects) + int mode) { void *freelist; unsigned long counters; @@ -2068,7 +2091,6 @@ static inline void *acquire_slab(struct kmem_cache *s, freelist = page->freelist; counters = page->counters; new.counters = counters; - *objects = new.objects - new.inuse; if (mode) { new.inuse = page->objects; new.freelist = NULL; @@ -2106,9 +2128,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, { struct page *page, *page2; void *object = NULL; - unsigned int available = 0; unsigned long flags; - int objects; + unsigned int partial_pages = 0; /* * Racy check. If we mistakenly see no partial slabs then we @@ -2126,11 +2147,10 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, if (!pfmemalloc_match(page, gfpflags)) continue; - t = acquire_slab(s, n, page, object == NULL, &objects); + t = acquire_slab(s, n, page, object == NULL); if (!t) break; - available += objects; if (!object) { *ret_page = page; stat(s, ALLOC_FROM_PARTIAL); @@ -2138,10 +2158,15 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, } else { put_cpu_partial(s, page, 0); stat(s, CPU_PARTIAL_NODE); + partial_pages++; } +#ifdef CONFIG_SLUB_CPU_PARTIAL if (!kmem_cache_has_cpu_partial(s) - || available > slub_cpu_partial(s) / 2) + || partial_pages > s->cpu_partial_pages / 2) break; +#else + break; +#endif } spin_unlock_irqrestore(&n->list_lock, flags); @@ -2546,14 +2571,13 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) struct page *page_to_unfreeze = NULL; unsigned long flags; int pages = 0; - int pobjects = 0; local_lock_irqsave(&s->cpu_slab->lock, flags); oldpage = this_cpu_read(s->cpu_slab->partial); if (oldpage) { - if (drain && oldpage->pobjects > slub_cpu_partial(s)) { + if (drain && oldpage->pages >= s->cpu_partial_pages) { /* * Partial array is full. Move the existing set to the * per node partial list. Postpone the actual unfreezing @@ -2562,16 +2586,13 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) page_to_unfreeze = oldpage; oldpage = NULL; } else { - pobjects = oldpage->pobjects; pages = oldpage->pages; } } pages++; - pobjects += page->objects - page->inuse; page->pages = pages; - page->pobjects = pobjects; page->next = oldpage; this_cpu_write(s->cpu_slab->partial, page); @@ -3991,6 +4012,8 @@ static void set_min_partial(struct kmem_cache *s, unsigned long min) static void set_cpu_partial(struct kmem_cache *s) { #ifdef CONFIG_SLUB_CPU_PARTIAL + unsigned int nr_objects; + /* * cpu_partial determined the maximum number of objects kept in the * per cpu partial lists of a processor. @@ -4000,24 +4023,22 @@ static void set_cpu_partial(struct kmem_cache *s) * filled up again with minimal effort. The slab will never hit the * per node partial lists and therefore no locking will be required. * - * This setting also determines - * - * A) The number of objects from per cpu partial slabs dumped to the - * per node list when we reach the limit. - * B) The number of objects in cpu partial slabs to extract from the - * per node list when we run out of per cpu objects. We only fetch - * 50% to keep some capacity around for frees. + * For backwards compatibility reasons, this is determined as number + * of objects, even though we now limit maximum number of pages, see + * slub_set_cpu_partial() */ if (!kmem_cache_has_cpu_partial(s)) - slub_set_cpu_partial(s, 0); + nr_objects = 0; else if (s->size >= PAGE_SIZE) - slub_set_cpu_partial(s, 2); + nr_objects = 2; else if (s->size >= 1024) - slub_set_cpu_partial(s, 6); + nr_objects = 6; else if (s->size >= 256) - slub_set_cpu_partial(s, 13); + nr_objects = 13; else - slub_set_cpu_partial(s, 30); + nr_objects = 30; + + slub_set_cpu_partial(s, nr_objects); #endif } @@ -5392,7 +5413,12 @@ SLAB_ATTR(min_partial); static ssize_t cpu_partial_show(struct kmem_cache *s, char *buf) { - return sysfs_emit(buf, "%u\n", slub_cpu_partial(s)); + unsigned int nr_partial = 0; +#ifdef CONFIG_SLUB_CPU_PARTIAL + nr_partial = s->cpu_partial; +#endif + + return sysfs_emit(buf, "%u\n", nr_partial); } static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf, @@ -5463,12 +5489,12 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); - if (page) { + if (page) pages += page->pages; - objects += page->pobjects; - } } + /* Approximate half-full pages , see slub_set_cpu_partial() */ + objects = (pages * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, "%d(%d)", objects, pages); #ifdef CONFIG_SMP @@ -5476,9 +5502,12 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) struct page *page; page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); - if (page) + if (page) { + pages = READ_ONCE(page->pages); + objects = (pages * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, " C%d=%d(%d)", - cpu, page->pobjects, page->pages); + cpu, objects, pages); + } } #endif len += sysfs_emit_at(buf, len, "\n"); -- cgit v1.2.3 From 96c84dde362a3e4ff67a12eaac2ea6e88e963c07 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:35:30 -0700 Subject: mm: don't include in Not required at all, and having this causes a huge kernel rebuild as soon as something in dax.h changes. Link: https://lkml.kernel.org/r/20210921082253.1859794-1-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Naoya Horiguchi Reviewed-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 1 - mm/memory-failure.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4091692bed8c..097bbbb37493 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -8,7 +8,6 @@ #include #include -#include #include #include #include diff --git a/mm/memory-failure.c b/mm/memory-failure.c index bdbbb32211a5..8376cfe0efce 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 7857ccdf94e94f1dd56496b90084fdcaa5e655a4 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:33 -0700 Subject: lib/stackdepot: include gfp.h Patch series "stackdepot, kasan, workqueue: Avoid expanding stackdepot slabs when holding raw_spin_lock", v2. Shuah Khan reported [1]: | When CONFIG_PROVE_RAW_LOCK_NESTING=y and CONFIG_KASAN are enabled, | kasan_record_aux_stack() runs into "BUG: Invalid wait context" when | it tries to allocate memory attempting to acquire spinlock in page | allocation code while holding workqueue pool raw_spinlock. | | There are several instances of this problem when block layer tries | to __queue_work(). Call trace from one of these instances is below: | | kblockd_mod_delayed_work_on() | mod_delayed_work_on() | __queue_delayed_work() | __queue_work() (rcu_read_lock, raw_spin_lock pool->lock held) | insert_work() | kasan_record_aux_stack() | kasan_save_stack() | stack_depot_save() | alloc_pages() | __alloc_pages() | get_page_from_freelist() | rm_queue() | rm_queue_pcplist() | local_lock_irqsave(&pagesets.lock, flags); | [ BUG: Invalid wait context triggered ] PROVE_RAW_LOCK_NESTING is pointing out that (on RT kernels) the locking rules are being violated. More generally, memory is being allocated from a non-preemptive context (raw_spin_lock'd c-s) where it is not allowed. To properly fix this, we must prevent stackdepot from replenishing its "stack slab" pool if memory allocations cannot be done in the current context: it's a bug to use either GFP_ATOMIC nor GFP_NOWAIT in certain non-preemptive contexts, including raw_spin_locks (see gfp.h and commit ab00db216c9c7). The only downside is that saving a stack trace may fail if: stackdepot runs out of space AND the same stack trace has not been recorded before. I expect this to be unlikely, and a simple experiment (boot the kernel) didn't result in any failure to record stack trace from insert_work(). The series includes a few minor fixes to stackdepot that I noticed in preparing the series. It then introduces __stack_depot_save(), which exposes the option to force stackdepot to not allocate any memory. Finally, KASAN is changed to use the new stackdepot interface and provide kasan_record_aux_stack_noalloc(), which is then used by workqueue code. [1] https://lkml.kernel.org/r/20210902200134.25603-1-skhan@linuxfoundation.org This patch (of 6): refers to gfp_t, but doesn't include gfp.h. Fix it by including . Link: https://lkml.kernel.org/r/20210913112609.2651084-1-elver@google.com Link: https://lkml.kernel.org/r/20210913112609.2651084-2-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Tejun Heo Cc: Lai Jiangshan Cc: Walter Wu Cc: Thomas Gleixner Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: "Gustavo A. R. Silva" Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 6bb4bc1a5f54..97b36dc53301 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -11,6 +11,8 @@ #ifndef _LINUX_STACKDEPOT_H #define _LINUX_STACKDEPOT_H +#include + typedef u32 depot_stack_handle_t; depot_stack_handle_t stack_depot_save(unsigned long *entries, -- cgit v1.2.3 From 11ac25c62cd2f3bb8da9e1df2e71afdebe76f093 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:39 -0700 Subject: lib/stackdepot: introduce __stack_depot_save() Add __stack_depot_save(), which provides more fine-grained control over stackdepot's memory allocation behaviour, in case stackdepot runs out of "stack slabs". Normally stackdepot uses alloc_pages() in case it runs out of space; passing can_alloc==false to __stack_depot_save() prohibits this, at the cost of more likely failure to record a stack trace. Link: https://lkml.kernel.org/r/20210913112609.2651084-4-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: "Gustavo A. R. Silva" Cc: Lai Jiangshan Cc: Taras Madan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 4 ++++ lib/stackdepot.c | 43 +++++++++++++++++++++++++++++++++++++------ 2 files changed, 41 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 97b36dc53301..b2f7e7c6ba54 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -15,6 +15,10 @@ typedef u32 depot_stack_handle_t; +depot_stack_handle_t __stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + gfp_t gfp_flags, bool can_alloc); + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index c80a9f734253..bda58597e375 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -248,17 +248,28 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, EXPORT_SYMBOL_GPL(stack_depot_fetch); /** - * stack_depot_save - Save a stack trace from an array + * __stack_depot_save - Save a stack trace from an array * * @entries: Pointer to storage array * @nr_entries: Size of the storage array * @alloc_flags: Allocation gfp flags + * @can_alloc: Allocate stack slabs (increased chance of failure if false) + * + * Saves a stack trace from @entries array of size @nr_entries. If @can_alloc is + * %true, is allowed to replenish the stack slab pool in case no space is left + * (allocates using GFP flags of @alloc_flags). If @can_alloc is %false, avoids + * any allocations and will fail if no space is left to store the stack trace. + * + * Context: Any context, but setting @can_alloc to %false is required if + * alloc_pages() cannot be used from the current context. Currently + * this is the case from contexts where neither %GFP_ATOMIC nor + * %GFP_NOWAIT can be used (NMI, raw_spin_lock). * - * Return: The handle of the stack struct stored in depot + * Return: The handle of the stack struct stored in depot, 0 on failure. */ -depot_stack_handle_t stack_depot_save(unsigned long *entries, - unsigned int nr_entries, - gfp_t alloc_flags) +depot_stack_handle_t __stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + gfp_t alloc_flags, bool can_alloc) { struct stack_record *found = NULL, **bucket; depot_stack_handle_t retval = 0; @@ -291,7 +302,7 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, * The smp_load_acquire() here pairs with smp_store_release() to * |next_slab_inited| in depot_alloc_stack() and init_stack_slab(). */ - if (unlikely(!smp_load_acquire(&next_slab_inited))) { + if (unlikely(can_alloc && !smp_load_acquire(&next_slab_inited))) { /* * Zero out zone modifiers, as we don't have specific zone * requirements. Keep the flags related to allocation in atomic @@ -339,6 +350,26 @@ exit: fast_exit: return retval; } +EXPORT_SYMBOL_GPL(__stack_depot_save); + +/** + * stack_depot_save - Save a stack trace from an array + * + * @entries: Pointer to storage array + * @nr_entries: Size of the storage array + * @alloc_flags: Allocation gfp flags + * + * Context: Contexts where allocations via alloc_pages() are allowed. + * See __stack_depot_save() for more details. + * + * Return: The handle of the stack struct stored in depot, 0 on failure. + */ +depot_stack_handle_t stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + gfp_t alloc_flags) +{ + return __stack_depot_save(entries, nr_entries, alloc_flags, true); +} EXPORT_SYMBOL_GPL(stack_depot_save); static inline int in_irqentry_text(unsigned long ptr) -- cgit v1.2.3 From 7cb3007ce2da27ec02a1a3211941e7fe6875b642 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:35:46 -0700 Subject: kasan: generic: introduce kasan_record_aux_stack_noalloc() Introduce a variant of kasan_record_aux_stack() that does not do any memory allocation through stackdepot. This will permit using it in contexts that cannot allocate any memory. Link: https://lkml.kernel.org/r/20210913112609.2651084-6-elver@google.com Signed-off-by: Marco Elver Tested-by: Shuah Khan Acked-by: Sebastian Andrzej Siewior Reviewed-by: Andrey Konovalov Cc: Alexander Potapenko Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: "Gustavo A. R. Silva" Cc: Lai Jiangshan Cc: Taras Madan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vijayanand Jitta Cc: Vinayak Menon Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kasan.h | 2 ++ mm/kasan/generic.c | 14 ++++++++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index dd874a1ee862..736d7b458996 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -370,12 +370,14 @@ static inline void kasan_unpoison_task_stack(struct task_struct *task) {} void kasan_cache_shrink(struct kmem_cache *cache); void kasan_cache_shutdown(struct kmem_cache *cache); void kasan_record_aux_stack(void *ptr); +void kasan_record_aux_stack_noalloc(void *ptr); #else /* CONFIG_KASAN_GENERIC */ static inline void kasan_cache_shrink(struct kmem_cache *cache) {} static inline void kasan_cache_shutdown(struct kmem_cache *cache) {} static inline void kasan_record_aux_stack(void *ptr) {} +static inline void kasan_record_aux_stack_noalloc(void *ptr) {} #endif /* CONFIG_KASAN_GENERIC */ diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 2a8e59e6326d..84a038b07c6f 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -328,7 +328,7 @@ DEFINE_ASAN_SET_SHADOW(f3); DEFINE_ASAN_SET_SHADOW(f5); DEFINE_ASAN_SET_SHADOW(f8); -void kasan_record_aux_stack(void *addr) +static void __kasan_record_aux_stack(void *addr, bool can_alloc) { struct page *page = kasan_addr_to_page(addr); struct kmem_cache *cache; @@ -345,7 +345,17 @@ void kasan_record_aux_stack(void *addr) return; alloc_meta->aux_stack[1] = alloc_meta->aux_stack[0]; - alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT, true); + alloc_meta->aux_stack[0] = kasan_save_stack(GFP_NOWAIT, can_alloc); +} + +void kasan_record_aux_stack(void *addr) +{ + return __kasan_record_aux_stack(addr, true); +} + +void kasan_record_aux_stack_noalloc(void *addr) +{ + return __kasan_record_aux_stack(addr, false); } void kasan_set_free_info(struct kmem_cache *cache, -- cgit v1.2.3 From 86cffecdeaa278444870c8745ab166a65865dbf0 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:19 -0700 Subject: Compiler Attributes: add __alloc_size() for better bounds checking GCC and Clang can use the "alloc_size" attribute to better inform the results of __builtin_object_size() (for compile-time constant values). Clang can additionally use alloc_size to inform the results of __builtin_dynamic_object_size() (for run-time values). Because GCC sees the frequent use of struct_size() as an allocator size argument, and notices it can return SIZE_MAX (the overflow indication), it complains about these call sites overflowing (since SIZE_MAX is greater than the default -Walloc-size-larger-than=PTRDIFF_MAX). This isn't helpful since we already know a SIZE_MAX will be caught at run-time (this was an intentional design). To deal with this, we must disable this check as it is both a false positive and redundant. (Clang does not have this warning option.) Unfortunately, just checking the -Wno-alloc-size-larger-than is not sufficient to make the __alloc_size attribute behave correctly under older GCC versions. The attribute itself must be disabled in those situations too, as there appears to be no way to reliably silence the SIZE_MAX constant expression cases for GCC versions less than 9.1: In file included from ./include/linux/resource_ext.h:11, from ./include/linux/pci.h:40, from drivers/net/ethernet/intel/ixgbe/ixgbe.h:9, from drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c:4: In function 'kmalloc_node', inlined from 'ixgbe_alloc_q_vector' at ./include/linux/slab.h:743:9: ./include/linux/slab.h:618:9: error: argument 1 value '18446744073709551615' exceeds maximum object size 9223372036854775807 [-Werror=alloc-size-larger-than=] return __kmalloc_node(size, flags, node); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ./include/linux/slab.h: In function 'ixgbe_alloc_q_vector': ./include/linux/slab.h:455:7: note: in a call to allocation function '__kmalloc_node' declared here void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_slab_alignment __malloc; ^~~~~~~~~~~~~~ Specifically: '-Wno-alloc-size-larger-than' is not correctly handled by GCC < 9.1 https://godbolt.org/z/hqsfG7q84 (doesn't disable) https://godbolt.org/z/P9jdrPTYh (doesn't admit to not knowing about option) https://godbolt.org/z/465TPMWKb (only warns when other warnings appear) '-Walloc-size-larger-than=18446744073709551615' is not handled by GCC < 8.2 https://godbolt.org/z/73hh1EPxz (ignores numeric value) Since anything marked with __alloc_size would also qualify for marking with __malloc, just include __malloc along with it to avoid redundant markings. (Suggested by Linus Torvalds.) Finally, make sure checkpatch.pl doesn't get confused about finding the __alloc_size attribute on functions. (Thanks to Joe Perches.) Link: https://lkml.kernel.org/r/20210930222704.2631604-3-keescook@chromium.org Signed-off-by: Kees Cook Tested-by: Randy Dunlap Cc: Andy Whitcroft Cc: Christoph Lameter Cc: Daniel Micay Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Makefile | 15 +++++++++++++++ include/linux/compiler-gcc.h | 8 ++++++++ include/linux/compiler_attributes.h | 10 ++++++++++ include/linux/compiler_types.h | 12 ++++++++++++ scripts/checkpatch.pl | 3 ++- 5 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Makefile b/Makefile index ed6e7ec60eff..d09ac84a170b 100644 --- a/Makefile +++ b/Makefile @@ -1008,6 +1008,21 @@ ifdef CONFIG_CC_IS_GCC KBUILD_CFLAGS += -Wno-maybe-uninitialized endif +ifdef CONFIG_CC_IS_GCC +# The allocators already balk at large sizes, so silence the compiler +# warnings for bounds checks involving those possible values. While +# -Wno-alloc-size-larger-than would normally be used here, earlier versions +# of gcc (<9.1) weirdly don't handle the option correctly when _other_ +# warnings are produced (?!). Using -Walloc-size-larger-than=SIZE_MAX +# doesn't work (as it is documented to), silently resolving to "0" prior to +# version 9.1 (and producing an error more recently). Numeric values larger +# than PTRDIFF_MAX also don't work prior to version 9.1, which are silently +# ignored, continuing to default to PTRDIFF_MAX. So, left with no other +# choice, we must perform a versioned check to disable this warning. +# https://lore.kernel.org/lkml/20210824115859.187f272f@canb.auug.org.au +KBUILD_CFLAGS += $(call cc-ifversion, -ge, 0901, -Wno-alloc-size-larger-than) +endif + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += -fno-strict-overflow diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index bd2b881c6b63..b9d5f9c373a0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -144,3 +144,11 @@ #else #define __diag_GCC_8(s) #endif + +/* + * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size" + * attribute) do not work, and must be disabled. + */ +#if GCC_VERSION < 90100 +#undef __alloc_size__ +#endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index e6ec63403965..3de06a8fae73 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -33,6 +33,15 @@ #define __aligned(x) __attribute__((__aligned__(x))) #define __aligned_largest __attribute__((__aligned__)) +/* + * Note: do not use this directly. Instead, use __alloc_size() since it is conditionally + * available and includes other attributes. + * + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-alloc_005fsize-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#alloc-size + */ +#define __alloc_size__(x, ...) __attribute__((__alloc_size__(x, ## __VA_ARGS__))) + /* * Note: users of __always_inline currently do not write "inline" themselves, * which seems to be required by gcc to apply the attribute according @@ -153,6 +162,7 @@ /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-malloc-function-attribute + * clang: https://clang.llvm.org/docs/AttributeReference.html#malloc */ #define __malloc __attribute__((__malloc__)) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index b6ff83a714ca..4f2203c4a257 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -250,6 +250,18 @@ struct ftrace_likely_data { # define __cficanonical #endif +/* + * Any place that could be marked with the "alloc_size" attribute is also + * a place to be marked with the "malloc" attribute. Do this as part of the + * __alloc_size macro to avoid redundant attributes and to avoid missing a + * __malloc marking. + */ +#ifdef __alloc_size__ +# define __alloc_size(x, ...) __alloc_size__(x, ## __VA_ARGS__) __malloc +#else +# define __alloc_size(x, ...) __malloc +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index c27d2312cfc3..88cb294dc447 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -489,7 +489,8 @@ our $Attribute = qr{ ____cacheline_aligned| ____cacheline_aligned_in_smp| ____cacheline_internodealigned_in_smp| - __weak + __weak| + __alloc_size\s*\(\s*\d+\s*(?:,\s*\d+\s*)?\) }x; our $Modifier; our $Inline = qr{inline|__always_inline|noinline|__inline|__inline__}; -- cgit v1.2.3 From 72d67229f522e3331d1eabd9f58d36ae080eb228 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:23 -0700 Subject: slab: clean up function prototypes Based on feedback from Joe Perches and Linus Torvalds, regularize the slab function prototypes before making attribute changes. Link: https://lkml.kernel.org/r/20210930222704.2631604-4-keescook@chromium.org Signed-off-by: Kees Cook Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Andy Whitcroft Cc: Daniel Micay Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: Joe Perches Cc: John Hubbard Cc: kernel test robot Cc: Lukas Bulwahn Cc: Matt Porter Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Randy Dunlap Cc: Souptick Joarder Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 68 ++++++++++++++++++++++++++-------------------------- 1 file changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index c0d46b6fa12a..d05de03bdcdd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -152,8 +152,8 @@ struct kmem_cache *kmem_cache_create_usercopy(const char *name, slab_flags_t flags, unsigned int useroffset, unsigned int usersize, void (*ctor)(void *)); -void kmem_cache_destroy(struct kmem_cache *); -int kmem_cache_shrink(struct kmem_cache *); +void kmem_cache_destroy(struct kmem_cache *s); +int kmem_cache_shrink(struct kmem_cache *s); /* * Please use this macro to create slab caches. Simply specify the @@ -181,11 +181,11 @@ int kmem_cache_shrink(struct kmem_cache *); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *, size_t, gfp_t); -void kfree(const void *); -void kfree_sensitive(const void *); -size_t __ksize(const void *); -size_t ksize(const void *); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags); +void kfree(const void *objp); +void kfree_sensitive(const void *objp); +size_t __ksize(const void *objp); +size_t ksize(const void *objp); #ifdef CONFIG_PRINTK bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); @@ -426,8 +426,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, #endif /* !CONFIG_SLOB */ void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; -void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; -void kmem_cache_free(struct kmem_cache *, void *); +void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void kmem_cache_free(struct kmem_cache *s, void *objp); /* * Bulk allocation and freeing operations. These are accelerated in an @@ -436,8 +436,8 @@ void kmem_cache_free(struct kmem_cache *, void *); * * Note that interrupts must be enabled when calling these functions. */ -void kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); -int kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); +void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p); +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p); /* * Caller must not use kfree_bulk() on memory not originally allocated @@ -450,7 +450,8 @@ static __always_inline void kfree_bulk(size_t size, void **p) #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; -void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment + __malloc; #else static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) { @@ -464,25 +465,24 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #endif #ifdef CONFIG_TRACING -extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc; +extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) + __assume_slab_alignment __malloc; #ifdef CONFIG_NUMA -extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment __malloc; +extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) __assume_slab_alignment __malloc; #else -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) +static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, int node, + size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ -static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, - gfp_t flags, size_t size) +static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, + size_t size) { void *ret = kmem_cache_alloc(s, flags); @@ -490,10 +490,8 @@ static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, return ret; } -static __always_inline void * -kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, - int node, size_t size) +static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, + int node, size_t size) { void *ret = kmem_cache_alloc_node(s, gfpflags, node); @@ -502,13 +500,14 @@ kmem_cache_alloc_node_trace(struct kmem_cache *s, } #endif /* CONFIG_TRACING */ -extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; +extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment + __malloc; #ifdef CONFIG_TRACING -extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment __malloc; +extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) + __assume_page_alignment __malloc; #else -static __always_inline void * -kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +static __always_inline void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { return kmalloc_order(size, flags, order); } @@ -638,8 +637,8 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static __must_check inline void * -krealloc_array(void *p, size_t new_n, size_t new_size, gfp_t flags) +static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t new_size, + gfp_t flags) { size_t bytes; @@ -668,7 +667,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t, gfp_t, unsigned long); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) @@ -691,7 +690,8 @@ static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) #ifdef CONFIG_NUMA -extern void *__kmalloc_node_track_caller(size_t, gfp_t, int, unsigned long); +extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, + unsigned long caller); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) -- cgit v1.2.3 From c37495d6254c237578db3121dcf79857e033f8ff Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:27 -0700 Subject: slab: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for regular kmalloc interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-5-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Reviewed-by: Nick Desaulniers Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Andy Whitcroft Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Tejun Heo Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 61 ++++++++++++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index d05de03bdcdd..b5bf0537975b 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -181,7 +181,7 @@ int kmem_cache_shrink(struct kmem_cache *s); /* * Common kmalloc functions provided by all allocators */ -void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags); +void * __must_check krealloc(const void *objp, size_t new_size, gfp_t flags) __alloc_size(2); void kfree(const void *objp); void kfree_sensitive(const void *objp); size_t __ksize(const void *objp); @@ -425,7 +425,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, #define kmalloc_index(s) __kmalloc_index(s, true) #endif /* !CONFIG_SLOB */ -void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; +void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); @@ -449,11 +449,12 @@ static __always_inline void kfree_bulk(size_t size, void **p) } #ifdef CONFIG_NUMA -void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; +void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment + __alloc_size(1); void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t flags, int node) __assume_slab_alignment __malloc; #else -static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *__kmalloc_node(size_t size, gfp_t flags, int node) { return __kmalloc(size, flags); } @@ -466,23 +467,23 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f #ifdef CONFIG_TRACING extern void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, size_t size) - __assume_slab_alignment __malloc; + __assume_slab_alignment __alloc_size(3); #ifdef CONFIG_NUMA extern void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, - int node, size_t size) __assume_slab_alignment __malloc; + int node, size_t size) __assume_slab_alignment + __alloc_size(4); #else -static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, - gfp_t gfpflags, int node, - size_t size) +static __always_inline __alloc_size(4) void *kmem_cache_alloc_node_trace(struct kmem_cache *s, + gfp_t gfpflags, int node, size_t size) { return kmem_cache_alloc_trace(s, gfpflags, size); } #endif /* CONFIG_NUMA */ #else /* CONFIG_TRACING */ -static __always_inline void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t flags, - size_t size) +static __always_inline __alloc_size(3) void *kmem_cache_alloc_trace(struct kmem_cache *s, + gfp_t flags, size_t size) { void *ret = kmem_cache_alloc(s, flags); @@ -501,19 +502,20 @@ static __always_inline void *kmem_cache_alloc_node_trace(struct kmem_cache *s, g #endif /* CONFIG_TRACING */ extern void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) __assume_page_alignment - __malloc; + __alloc_size(1); #ifdef CONFIG_TRACING extern void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) - __assume_page_alignment __malloc; + __assume_page_alignment __alloc_size(1); #else -static __always_inline void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) +static __always_inline __alloc_size(1) void *kmalloc_order_trace(size_t size, gfp_t flags, + unsigned int order) { return kmalloc_order(size, flags, order); } #endif -static __always_inline void *kmalloc_large(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc_large(size_t size, gfp_t flags) { unsigned int order = get_order(size); return kmalloc_order_trace(size, flags, order); @@ -573,7 +575,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) * Try really hard to succeed the allocation but fail * eventually. */ -static __always_inline void *kmalloc(size_t size, gfp_t flags) +static __always_inline __alloc_size(1) void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { #ifndef CONFIG_SLOB @@ -595,7 +597,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) return __kmalloc(size, flags); } -static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline __alloc_size(1) void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && @@ -619,7 +621,7 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -637,8 +639,10 @@ static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags) * @new_size: new size of a single member of the array * @flags: the type of memory to allocate (see kmalloc) */ -static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t new_size, - gfp_t flags) +static inline __alloc_size(2, 3) void * __must_check krealloc_array(void *p, + size_t new_n, + size_t new_size, + gfp_t flags) { size_t bytes; @@ -654,7 +658,7 @@ static inline void * __must_check krealloc_array(void *p, size_t new_n, size_t n * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kcalloc(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flags) { return kmalloc_array(n, size, flags | __GFP_ZERO); } @@ -667,12 +671,13 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags) * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) + __alloc_size(1); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) -static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, - int node) +static inline __alloc_size(1, 2) void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, + int node) { size_t bytes; @@ -683,7 +688,7 @@ static inline void *kmalloc_array_node(size_t n, size_t size, gfp_t flags, return __kmalloc_node(bytes, flags, node); } -static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) +static inline __alloc_size(1, 2) void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) { return kmalloc_array_node(n, size, flags | __GFP_ZERO, node); } @@ -691,7 +696,7 @@ static inline void *kcalloc_node(size_t n, size_t size, gfp_t flags, int node) #ifdef CONFIG_NUMA extern void *__kmalloc_node_track_caller(size_t size, gfp_t flags, int node, - unsigned long caller); + unsigned long caller) __alloc_size(1); #define kmalloc_node_track_caller(size, flags, node) \ __kmalloc_node_track_caller(size, flags, node, \ _RET_IP_) @@ -716,7 +721,7 @@ static inline void *kmem_cache_zalloc(struct kmem_cache *k, gfp_t flags) * @size: how many bytes of memory are required. * @flags: the type of memory to allocate (see kmalloc). */ -static inline void *kzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kzalloc(size_t size, gfp_t flags) { return kmalloc(size, flags | __GFP_ZERO); } @@ -727,7 +732,7 @@ static inline void *kzalloc(size_t size, gfp_t flags) * @flags: the type of memory to allocate (see kmalloc). * @node: memory node from which to allocate */ -static inline void *kzalloc_node(size_t size, gfp_t flags, int node) +static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int node) { return kmalloc_node(size, flags | __GFP_ZERO, node); } -- cgit v1.2.3 From 56bcf40f91c7d7f53b77abe161a7d18ef9f981ba Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:31 -0700 Subject: mm/kvmalloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for regular kvmalloc interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-6-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Reviewed-by: Nick Desaulniers Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Andy Whitcroft Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Tejun Heo Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index b5bf0537975b..837cb16232ef 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -737,21 +737,21 @@ static inline __alloc_size(1) void *kzalloc_node(size_t size, gfp_t flags, int n return kmalloc_node(size, flags | __GFP_ZERO, node); } -extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -static inline void *kvmalloc(size_t size, gfp_t flags) +extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __alloc_size(1); +static inline __alloc_size(1) void *kvmalloc(size_t size, gfp_t flags) { return kvmalloc_node(size, flags, NUMA_NO_NODE); } -static inline void *kvzalloc_node(size_t size, gfp_t flags, int node) +static inline __alloc_size(1) void *kvzalloc_node(size_t size, gfp_t flags, int node) { return kvmalloc_node(size, flags | __GFP_ZERO, node); } -static inline void *kvzalloc(size_t size, gfp_t flags) +static inline __alloc_size(1) void *kvzalloc(size_t size, gfp_t flags) { return kvmalloc(size, flags | __GFP_ZERO); } -static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kvmalloc_array(size_t n, size_t size, gfp_t flags) { size_t bytes; @@ -761,13 +761,13 @@ static inline void *kvmalloc_array(size_t n, size_t size, gfp_t flags) return kvmalloc(bytes, flags); } -static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) +static inline __alloc_size(1, 2) void *kvcalloc(size_t n, size_t size, gfp_t flags) { return kvmalloc_array(n, size, flags | __GFP_ZERO); } -extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, - gfp_t flags); +extern void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags) + __alloc_size(3); extern void kvfree(const void *addr); extern void kvfree_sensitive(const void *addr, size_t len); -- cgit v1.2.3 From 894f24bb569afd4fe4a874c636f82d47f1c9beed Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:34 -0700 Subject: mm/vmalloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate vmalloc allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-7-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Cc: Andy Whitcroft Cc: Christoph Lameter Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 671d402c3778..0ed56fc10c11 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -136,21 +136,21 @@ static inline void vmalloc_init(void) static inline unsigned long vmalloc_nr_pages(void) { return 0; } #endif -extern void *vmalloc(unsigned long size); -extern void *vzalloc(unsigned long size); -extern void *vmalloc_user(unsigned long size); -extern void *vmalloc_node(unsigned long size, int node); -extern void *vzalloc_node(unsigned long size, int node); -extern void *vmalloc_32(unsigned long size); -extern void *vmalloc_32_user(unsigned long size); -extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); +extern void *vmalloc(unsigned long size) __alloc_size(1); +extern void *vzalloc(unsigned long size) __alloc_size(1); +extern void *vmalloc_user(unsigned long size) __alloc_size(1); +extern void *vmalloc_node(unsigned long size, int node) __alloc_size(1); +extern void *vzalloc_node(unsigned long size, int node) __alloc_size(1); +extern void *vmalloc_32(unsigned long size) __alloc_size(1); +extern void *vmalloc_32_user(unsigned long size) __alloc_size(1); +extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __alloc_size(1); extern void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, - const void *caller); + const void *caller) __alloc_size(1); void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, - int node, const void *caller); -void *vmalloc_no_huge(unsigned long size); + int node, const void *caller) __alloc_size(1); +void *vmalloc_no_huge(unsigned long size) __alloc_size(1); extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); -- cgit v1.2.3 From abd58f38dfb4771ef06e25d71a84aa0932c52f1a Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:38 -0700 Subject: mm/page_alloc: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate page allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Link: https://lkml.kernel.org/r/20210930222704.2631604-8-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Cc: Andy Whitcroft Cc: Christoph Lameter Cc: David Rientjes Cc: Dennis Zhou Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Tejun Heo Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 55b2ec1f965a..fbd4abc33f24 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -608,9 +608,9 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); -void *alloc_pages_exact(size_t size, gfp_t gfp_mask); +void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); +__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) -- cgit v1.2.3 From 17197dd460469c6fca66e274f5cd51ee43bb6ddd Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 5 Nov 2021 13:36:42 -0700 Subject: percpu: add __alloc_size attributes for better bounds checking As already done in GrapheneOS, add the __alloc_size attribute for appropriate percpu allocator interfaces, to provide additional hinting for better bounds checking, assisting CONFIG_FORTIFY_SOURCE and other compiler optimizations. Note that due to the implementation of the percpu API, this is unlikely to ever actually provide compile-time checking beyond very simple non-SMP builds. But, since they are technically allocators, mark them as such. Link: https://lkml.kernel.org/r/20210930222704.2631604-9-keescook@chromium.org Signed-off-by: Kees Cook Co-developed-by: Daniel Micay Signed-off-by: Daniel Micay Acked-by: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Andy Whitcroft Cc: David Rientjes Cc: Dwaipayan Ray Cc: Joe Perches Cc: Joonsoo Kim Cc: Lukas Bulwahn Cc: Miguel Ojeda Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Pekka Enberg Cc: Vlastimil Babka Cc: Alexandre Bounine Cc: Gustavo A. R. Silva Cc: Ira Weiny Cc: Jing Xiangfeng Cc: John Hubbard Cc: kernel test robot Cc: Matt Porter Cc: Randy Dunlap Cc: Souptick Joarder Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/percpu.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 5e76af742c80..98a9371133f8 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -123,7 +123,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif -extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); +extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); extern bool is_kernel_percpu_address(unsigned long addr); @@ -131,8 +131,8 @@ extern bool is_kernel_percpu_address(unsigned long addr); extern void __init setup_per_cpu_areas(void); #endif -extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp); -extern void __percpu *__alloc_percpu(size_t size, size_t align); +extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); +extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); extern phys_addr_t per_cpu_ptr_to_phys(void *addr); -- cgit v1.2.3 From 0b3ea0926afb8dde70cfab00316ae0a70b93a7cc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:36:58 -0700 Subject: fs: explicitly unregister per-superblock BDIs Add a new SB_I_ flag to mark superblocks that have an ephemeral bdi associated with them, and unregister it when the superblock is shut down. Link: https://lkml.kernel.org/r/20211021124441.668816-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/super.c | 3 +++ include/linux/fs.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/fs/super.c b/fs/super.c index bcef3a6f4c4b..3bfc0f8fbd5b 100644 --- a/fs/super.c +++ b/fs/super.c @@ -476,6 +476,8 @@ void generic_shutdown_super(struct super_block *sb) spin_unlock(&sb_lock); up_write(&sb->s_umount); if (sb->s_bdi != &noop_backing_dev_info) { + if (sb->s_iflags & SB_I_PERSB_BDI) + bdi_unregister(sb->s_bdi); bdi_put(sb->s_bdi); sb->s_bdi = &noop_backing_dev_info; } @@ -1562,6 +1564,7 @@ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...) } WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi; + sb->s_iflags |= SB_I_PERSB_BDI; return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index e7a633353fd2..226de651f52e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1443,6 +1443,7 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_UNTRUSTED_MOUNTER 0x00000040 #define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ +#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ /* Possible states of 'frozen' field */ enum { -- cgit v1.2.3 From efee17134ca464639a2f5b4d036ce40caf1b247a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 5 Nov 2021 13:37:04 -0700 Subject: mm: simplify bdi refcounting Move grabbing and releasing the bdi refcount out of the common wb_init/wb_exit helpers into code that is only used for the non-default memcg driven bdi_writeback structures. [hch@lst.de: add comment] Link: https://lkml.kernel.org/r/20211027074207.GA12793@lst.de [akpm@linux-foundation.org: fix typo] Link: https://lkml.kernel.org/r/20211021124441.668816-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev-defs.h | 3 +++ mm/backing-dev.c | 13 +++++-------- 2 files changed, 8 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 33207004cfde..993c5628a726 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -103,6 +103,9 @@ struct wb_completion { * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. + * + * Each bdi_writeback that is not embedded into the backing_dev_info must hold + * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 768e9ae489f6..5ccb25089808 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -291,8 +291,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, memset(wb, 0, sizeof(*wb)); - if (wb != &bdi->wb) - bdi_get(bdi); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); @@ -316,7 +314,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, err = fprop_local_init_percpu(&wb->completions, gfp); if (err) - goto out_put_bdi; + return err; for (i = 0; i < NR_WB_STAT_ITEMS; i++) { err = percpu_counter_init(&wb->stat[i], 0, gfp); @@ -330,9 +328,6 @@ out_destroy_stat: while (i--) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); -out_put_bdi: - if (wb != &bdi->wb) - bdi_put(bdi); return err; } @@ -373,8 +368,6 @@ static void wb_exit(struct bdi_writeback *wb) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); - if (wb != &wb->bdi->wb) - bdi_put(wb->bdi); } #ifdef CONFIG_CGROUP_WRITEBACK @@ -397,6 +390,7 @@ static void cgwb_release_workfn(struct work_struct *work) struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); + struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -416,6 +410,7 @@ static void cgwb_release_workfn(struct work_struct *work) percpu_ref_exit(&wb->refcnt); wb_exit(wb); + bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); kfree_rcu(wb, rcu); } @@ -497,6 +492,7 @@ static int cgwb_create(struct backing_dev_info *bdi, INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); + bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and @@ -528,6 +524,7 @@ static int cgwb_create(struct backing_dev_info *bdi, goto out_put; err_fprop_exit: + bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); -- cgit v1.2.3 From e80216d9f1f5c90b3cab834cd4fb492d731f70aa Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 5 Nov 2021 13:37:56 -0700 Subject: mm: memcontrol: remove the kmem states Now the kmem states is only used to indicate whether the kmem is offline. However, we can set ->kmemcg_id to -1 to indicate whether the kmem is offline. Finally, we can remove the kmem states to simplify the code. Link: https://lkml.kernel.org/r/20211025125259.56624-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Shakeel Butt Cc: Matthew Wilcox (Oracle) Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 7 ------- mm/memcontrol.c | 7 ++----- 2 files changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3096c9a0ee01..f207f98bdb76 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -180,12 +180,6 @@ struct mem_cgroup_thresholds { struct mem_cgroup_threshold_ary *spare; }; -enum memcg_kmem_state { - KMEM_NONE, - KMEM_ALLOCATED, - KMEM_ONLINE, -}; - #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; @@ -318,7 +312,6 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; - enum memcg_kmem_state kmem_state; struct obj_cgroup __rcu *objcg; struct list_head objcg_list; /* list of inherited objcgs */ #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 1e2d3f378edd..b4a17b7a10d3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3626,7 +3626,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) return 0; BUG_ON(memcg->kmemcg_id >= 0); - BUG_ON(memcg->kmem_state); memcg_id = memcg_alloc_cache_id(); if (memcg_id < 0) @@ -3643,7 +3642,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) static_branch_enable(&memcg_kmem_enabled_key); memcg->kmemcg_id = memcg_id; - memcg->kmem_state = KMEM_ONLINE; return 0; } @@ -3653,11 +3651,9 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) struct mem_cgroup *parent; int kmemcg_id; - if (memcg->kmem_state != KMEM_ONLINE) + if (memcg->kmemcg_id == -1) return; - memcg->kmem_state = KMEM_ALLOCATED; - parent = parent_mem_cgroup(memcg); if (!parent) parent = root_mem_cgroup; @@ -3676,6 +3672,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) memcg_drain_all_list_lrus(kmemcg_id, parent); memcg_free_cache_id(kmemcg_id); + memcg->kmemcg_id = -1; } #else static int memcg_online_kmem(struct mem_cgroup *memcg) -- cgit v1.2.3 From f1dc0db296bd25960273649fc6ef2ecbf5aaa0e0 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Fri, 5 Nov 2021 13:38:15 -0700 Subject: mm: use __pfn_to_section() instead of open coding it It is defined in the same file just a few lines above. Link: https://lkml.kernel.org/r/4598487.Rc0NezkW7i@mobilepool36.emlix.com Signed-off-by: Rolf Eike Beer Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6a1d79d84675..832aa49d0d8e 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1481,7 +1481,7 @@ static inline int pfn_valid(unsigned long pfn) if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - ms = __nr_to_section(pfn_to_section_nr(pfn)); + ms = __pfn_to_section(pfn); if (!valid_section(ms)) return 0; /* @@ -1496,7 +1496,7 @@ static inline int pfn_in_present_section(unsigned long pfn) { if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; - return present_section(__nr_to_section(pfn_to_section_nr(pfn))); + return present_section(__pfn_to_section(pfn)); } static inline unsigned long next_present_section_nr(unsigned long section_nr) -- cgit v1.2.3 From 232a6a1c0619d1b4d9cd8d21949b2f13821be0af Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:38:31 -0700 Subject: mm: drop first_index/last_index in zap_details The first_index/last_index parameters in zap_details are actually only used in unmap_mapping_range_tree(). At the meantime, this function is only called by unmap_mapping_pages() once. Instead of passing these two variables through the whole stack of page zapping code, remove them from zap_details and let them simply be parameters of unmap_mapping_range_tree(), which is inlined. Link: https://lkml.kernel.org/r/20210915181535.11238-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Reviewed-by: David Hildenbrand Reviewed-by: Liam Howlett Acked-by: Hugh Dickins Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Rapoport Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- mm/memory.c | 31 ++++++++++++++++++------------- 2 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 32b2ecc47408..c5b600d7f85b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1688,8 +1688,6 @@ extern void user_shm_unlock(size_t, struct ucounts *); */ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ - pgoff_t first_index; /* Lowest page->index to unmap */ - pgoff_t last_index; /* Highest page->index to unmap */ struct page *single_page; /* Locked page to be unmapped */ }; diff --git a/mm/memory.c b/mm/memory.c index cf7b059b57a7..d4ed701e3e5d 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3321,20 +3321,20 @@ static void unmap_mapping_range_vma(struct vm_area_struct *vma, } static inline void unmap_mapping_range_tree(struct rb_root_cached *root, + pgoff_t first_index, + pgoff_t last_index, struct zap_details *details) { struct vm_area_struct *vma; pgoff_t vba, vea, zba, zea; - vma_interval_tree_foreach(vma, root, - details->first_index, details->last_index) { - + vma_interval_tree_foreach(vma, root, first_index, last_index) { vba = vma->vm_pgoff; vea = vba + vma_pages(vma) - 1; - zba = details->first_index; + zba = first_index; if (zba < vba) zba = vba; - zea = details->last_index; + zea = last_index; if (zea > vea) zea = vea; @@ -3360,18 +3360,22 @@ void unmap_mapping_page(struct page *page) { struct address_space *mapping = page->mapping; struct zap_details details = { }; + pgoff_t first_index; + pgoff_t last_index; VM_BUG_ON(!PageLocked(page)); VM_BUG_ON(PageTail(page)); + first_index = page->index; + last_index = page->index + thp_nr_pages(page) - 1; + details.check_mapping = mapping; - details.first_index = page->index; - details.last_index = page->index + thp_nr_pages(page) - 1; details.single_page = page; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) - unmap_mapping_range_tree(&mapping->i_mmap, &details); + unmap_mapping_range_tree(&mapping->i_mmap, first_index, + last_index, &details); i_mmap_unlock_write(mapping); } @@ -3391,16 +3395,17 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { struct zap_details details = { }; + pgoff_t first_index = start; + pgoff_t last_index = start + nr - 1; details.check_mapping = even_cows ? NULL : mapping; - details.first_index = start; - details.last_index = start + nr - 1; - if (details.last_index < details.first_index) - details.last_index = ULONG_MAX; + if (last_index < first_index) + last_index = ULONG_MAX; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) - unmap_mapping_range_tree(&mapping->i_mmap, &details); + unmap_mapping_range_tree(&mapping->i_mmap, first_index, + last_index, &details); i_mmap_unlock_write(mapping); } EXPORT_SYMBOL_GPL(unmap_mapping_pages); -- cgit v1.2.3 From 91b61ef333cf43f96b3522a086c9ac925763d6e5 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:38:34 -0700 Subject: mm: add zap_skip_check_mapping() helper Use the helper for the checks. Rename "check_mapping" into "zap_mapping" because "check_mapping" looks like a bool but in fact it stores the mapping itself. When it's set, we check the mapping (it must be non-NULL). When it's cleared we skip the check, which works like the old way. Move the duplicated comments to the helper too. Link: https://lkml.kernel.org/r/20210915181538.11288-1-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: Alistair Popple Cc: Andrea Arcangeli Cc: Axel Rasmussen Cc: David Hildenbrand Cc: Hugh Dickins Cc: Jerome Glisse Cc: "Kirill A . Shutemov" Cc: Liam Howlett Cc: Matthew Wilcox Cc: Miaohe Lin Cc: Mike Rapoport Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 16 +++++++++++++++- mm/memory.c | 29 ++++++----------------------- 2 files changed, 21 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c5b600d7f85b..6e29deb1e0d4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1687,10 +1687,24 @@ extern void user_shm_unlock(size_t, struct ucounts *); * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { - struct address_space *check_mapping; /* Check page->mapping if set */ + struct address_space *zap_mapping; /* Check page->mapping if set */ struct page *single_page; /* Locked page to be unmapped */ }; +/* + * We set details->zap_mappings when we want to unmap shared but keep private + * pages. Return true if skip zapping this page, false otherwise. + */ +static inline bool +zap_skip_check_mapping(struct zap_details *details, struct page *page) +{ + if (!details || !page) + return false; + + return details->zap_mapping && + (details->zap_mapping != page_rmapping(page)); +} + struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, diff --git a/mm/memory.c b/mm/memory.c index d4ed701e3e5d..48b2e048d267 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1333,16 +1333,8 @@ again: struct page *page; page = vm_normal_page(vma, addr, ptent); - if (unlikely(details) && page) { - /* - * unmap_shared_mapping_pages() wants to - * invalidate cache without truncating: - * unmap shared but keep private pages. - */ - if (details->check_mapping && - details->check_mapping != page_rmapping(page)) - continue; - } + if (unlikely(zap_skip_check_mapping(details, page))) + continue; ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); @@ -1375,17 +1367,8 @@ again: is_device_exclusive_entry(entry)) { struct page *page = pfn_swap_entry_to_page(entry); - if (unlikely(details && details->check_mapping)) { - /* - * unmap_shared_mapping_pages() wants to - * invalidate cache without truncating: - * unmap shared but keep private pages. - */ - if (details->check_mapping != - page_rmapping(page)) - continue; - } - + if (unlikely(zap_skip_check_mapping(details, page))) + continue; pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); rss[mm_counter(page)]--; @@ -3369,7 +3352,7 @@ void unmap_mapping_page(struct page *page) first_index = page->index; last_index = page->index + thp_nr_pages(page) - 1; - details.check_mapping = mapping; + details.zap_mapping = mapping; details.single_page = page; i_mmap_lock_write(mapping); @@ -3398,7 +3381,7 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t first_index = start; pgoff_t last_index = start + nr - 1; - details.check_mapping = even_cows ? NULL : mapping; + details.zap_mapping = even_cows ? NULL : mapping; if (last_index < first_index) last_index = ULONG_MAX; -- cgit v1.2.3 From e26e0cc30b48cad5f2704f6a22fa5cac9fdaaece Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Fri, 5 Nov 2021 13:39:00 -0700 Subject: memory: remove unused CONFIG_MEM_BLOCK_SIZE Commit 3947be1969a9 ("[PATCH] memory hotplug: sysfs and add/remove functions") defines CONFIG_MEM_BLOCK_SIZE, but this has never been utilized anywhere. It is a good practice to keep the CONFIG_* defines exclusively for the Kbuild system. So, drop this unused definition. This issue was noticed due to running ./scripts/checkkconfigsymbols.py. Link: https://lkml.kernel.org/r/20211006120354.7468-1-lukas.bulwahn@gmail.com Signed-off-by: Lukas Bulwahn Reviewed-by: David Hildenbrand Cc: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memory.h b/include/linux/memory.h index 182c606adb06..053a530c7bdd 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -140,7 +140,6 @@ typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *); extern int walk_memory_blocks(unsigned long start, unsigned long size, void *arg, walk_memory_blocks_func_t func); extern int for_each_memory_block(void *arg, walk_memory_blocks_func_t func); -#define CONFIG_MEM_BLOCK_SIZE (PAGES_PER_SECTION< Date: Fri, 5 Nov 2021 13:39:10 -0700 Subject: include/linux/io-mapping.h: remove fallback for writecombine The fallback was introduced in commit 80c33624e472 ("io-mapping: Fixup for different names of writecombine") to fix the build on microblaze. 5 years later, it seems all archs now provide a pgprot_writecombine(), so just remove the other possible fallbacks. For microblaze, pgprot_writecombine() is available since commit 97ccedd793ac ("microblaze: Provide pgprot_device/writecombine macros for nommu"). This is build-tested on microblaze with a hack to always build mm/io-mapping.o and without DIYing on an x86-only macro (_PAGE_CACHE_MASK) Link: https://lkml.kernel.org/r/20211020204838.1142908-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi Cc: Chris Wilson Cc: Daniel Vetter Cc: Joonas Lahtinen Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/io-mapping.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h index e9743cfd8585..66a774d2710e 100644 --- a/include/linux/io-mapping.h +++ b/include/linux/io-mapping.h @@ -132,13 +132,7 @@ io_mapping_init_wc(struct io_mapping *iomap, iomap->base = base; iomap->size = size; -#if defined(pgprot_noncached_wc) /* archs can't agree on a name ... */ - iomap->prot = pgprot_noncached_wc(PAGE_KERNEL); -#elif defined(pgprot_writecombine) iomap->prot = pgprot_writecombine(PAGE_KERNEL); -#else - iomap->prot = pgprot_noncached(PAGE_KERNEL); -#endif return iomap; } -- cgit v1.2.3 From bd1a8fb2d43f7c293383f76691d7a55f7f89d9da Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 5 Nov 2021 13:39:22 -0700 Subject: mm/vmalloc: don't allow VM_NO_GUARD on vmap() The vmalloc guard pages are added on top of each allocation, thereby isolating any two allocations from one another. The top guard of the lower allocation is the bottom guard guard of the higher allocation etc. Therefore VM_NO_GUARD is dangerous; it breaks the basic premise of isolating separate allocations. There are only two in-tree users of this flag, neither of which use it through the exported interface. Ensure it stays this way. Link: https://lkml.kernel.org/r/YUMfdA36fuyZ+/xt@hirez.programming.kicks-ass.net Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Christoph Hellwig Reviewed-by: David Hildenbrand Acked-by: Will Deacon Acked-by: Kees Cook Cc: Andrey Konovalov Cc: Mel Gorman Cc: Uladzislau Rezki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- mm/vmalloc.c | 7 +++++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 0ed56fc10c11..6e022cc712e6 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -22,7 +22,7 @@ struct notifier_block; /* in notifier.h */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ -#define VM_NO_GUARD 0x00000040 /* don't add guard page */ +#define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f43c88fa08cf..4a11abd9e70f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2743,6 +2743,13 @@ void *vmap(struct page **pages, unsigned int count, might_sleep(); + /* + * Your top guard is someone else's bottom guard. Not having a top + * guard compromises someone else's mappings too. + */ + if (WARN_ON_ONCE(flags & VM_NO_GUARD)) + flags &= ~VM_NO_GUARD; + if (count > totalram_pages()) return NULL; -- cgit v1.2.3 From 3252b1d8309ea42bc6329d9341072ecf1c9505c0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 5 Nov 2021 13:39:47 -0700 Subject: kasan: arm64: fix pcpu_page_first_chunk crash with KASAN_VMALLOC With KASAN_VMALLOC and NEED_PER_CPU_PAGE_FIRST_CHUNK the kernel crashes: Unable to handle kernel paging request at virtual address ffff7000028f2000 ... swapper pgtable: 64k pages, 48-bit VAs, pgdp=0000000042440000 [ffff7000028f2000] pgd=000000063e7c0003, p4d=000000063e7c0003, pud=000000063e7c0003, pmd=000000063e7b0003, pte=0000000000000000 Internal error: Oops: 96000007 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 5.13.0-rc4-00003-gc6e6e28f3f30-dirty #62 Hardware name: linux,dummy-virt (DT) pstate: 200000c5 (nzCv daIF -PAN -UAO -TCO BTYPE=--) pc : kasan_check_range+0x90/0x1a0 lr : memcpy+0x88/0xf4 sp : ffff80001378fe20 ... Call trace: kasan_check_range+0x90/0x1a0 pcpu_page_first_chunk+0x3f0/0x568 setup_per_cpu_areas+0xb8/0x184 start_kernel+0x8c/0x328 The vm area used in vm_area_register_early() has no kasan shadow memory, Let's add a new kasan_populate_early_vm_area_shadow() function to populate the vm area shadow memory to fix the issue. [wangkefeng.wang@huawei.com: fix redefinition of 'kasan_populate_early_vm_area_shadow'] Link: https://lkml.kernel.org/r/20211011123211.3936196-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210910053354.26721-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Acked-by: Marco Elver [KASAN] Acked-by: Andrey Konovalov [KASAN] Acked-by: Catalin Marinas Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Greg Kroah-Hartman Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/mm/kasan_init.c | 16 ++++++++++++++++ include/linux/kasan.h | 6 ++++++ mm/kasan/shadow.c | 5 +++++ mm/vmalloc.c | 1 + 4 files changed, 28 insertions(+) (limited to 'include/linux') diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 61b52a92b8b6..5b996ca4d996 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -287,6 +287,22 @@ static void __init kasan_init_depth(void) init_task.kasan_depth = 0; } +#ifdef CONFIG_KASAN_VMALLOC +void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size) +{ + unsigned long shadow_start, shadow_end; + + if (!is_vmalloc_or_module_addr(start)) + return; + + shadow_start = (unsigned long)kasan_mem_to_shadow(start); + shadow_start = ALIGN_DOWN(shadow_start, PAGE_SIZE); + shadow_end = (unsigned long)kasan_mem_to_shadow(start + size); + shadow_end = ALIGN(shadow_end, PAGE_SIZE); + kasan_map_populate(shadow_start, shadow_end, NUMA_NO_NODE); +} +#endif + void __init kasan_init(void) { kasan_init_shadow(); diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 736d7b458996..65487a3b2a71 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -436,6 +436,8 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, unsigned long free_region_start, unsigned long free_region_end); +void kasan_populate_early_vm_area_shadow(void *start, unsigned long size); + #else /* CONFIG_KASAN_VMALLOC */ static inline int kasan_populate_vmalloc(unsigned long start, @@ -453,6 +455,10 @@ static inline void kasan_release_vmalloc(unsigned long start, unsigned long free_region_start, unsigned long free_region_end) {} +static inline void kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ } + #endif /* CONFIG_KASAN_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 8d95ee52d019..4a4929b29a23 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -254,6 +254,11 @@ core_initcall(kasan_memhotplug_init); #ifdef CONFIG_KASAN_VMALLOC +void __init __weak kasan_populate_early_vm_area_shadow(void *start, + unsigned long size) +{ +} + static int kasan_populate_vmalloc_pte(pte_t *ptep, unsigned long addr, void *unused) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 74da45a8beec..75fa100f5424 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2291,6 +2291,7 @@ void __init vm_area_register_early(struct vm_struct *vm, size_t align) vm->addr = (void *)addr; vm->next = *p; *p = vm; + kasan_populate_early_vm_area_shadow(vm->addr, vm->size); } static void vmap_init_free_space(void) -- cgit v1.2.3 From c00b6b9610991c042ff4c3153daaa3ea8522c210 Mon Sep 17 00:00:00 2001 From: Chen Wandun Date: Fri, 5 Nov 2021 13:39:53 -0700 Subject: mm/vmalloc: introduce alloc_pages_bulk_array_mempolicy to accelerate memory allocation Commit ffb29b1c255a ("mm/vmalloc: fix numa spreading for large hash tables") can cause significant performance regressions in some situations as Andrew mentioned in [1]. The main situation is vmalloc, vmalloc will allocate pages with NUMA_NO_NODE by default, that will result in alloc page one by one; In order to solve this, __alloc_pages_bulk and mempolicy should be considered at the same time. 1) If node is specified in memory allocation request, it will alloc all pages by __alloc_pages_bulk. 2) If interleaving allocate memory, it will cauculate how many pages should be allocated in each node, and use __alloc_pages_bulk to alloc pages in each node. [1]: https://lore.kernel.org/lkml/CALvZod4G3SzP3kWxQYn0fj+VgG-G3yWXz=gz17+3N57ru1iajw@mail.gmail.com/t/#m750c8e3231206134293b089feaa090590afa0f60 [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: make two functions static] [akpm@linux-foundation.org: fix CONFIG_NUMA=n build] Link: https://lkml.kernel.org/r/20211021080744.874701-3-chenwandun@huawei.com Signed-off-by: Chen Wandun Reviewed-by: Uladzislau Rezki (Sony) Cc: Eric Dumazet Cc: Shakeel Butt Cc: Nicholas Piggin Cc: Kefeng Wang Cc: Hanjun Guo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++ mm/mempolicy.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/vmalloc.c | 20 ++++++++++--- 3 files changed, 102 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index fbd4abc33f24..c1b262725dca 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -535,6 +535,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid, struct list_head *page_list, struct page **page_array); +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, + struct page **page_array); + /* Bulk allocate order-0 pages */ static inline unsigned long alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d12e0608fced..ce722333d9f6 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2196,6 +2196,88 @@ struct page *alloc_pages(gfp_t gfp, unsigned order) } EXPORT_SYMBOL(alloc_pages); +static unsigned long alloc_pages_bulk_array_interleave(gfp_t gfp, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + int nodes; + unsigned long nr_pages_per_node; + int delta; + int i; + unsigned long nr_allocated; + unsigned long total_allocated = 0; + + nodes = nodes_weight(pol->nodes); + nr_pages_per_node = nr_pages / nodes; + delta = nr_pages - nodes * nr_pages_per_node; + + for (i = 0; i < nodes; i++) { + if (delta) { + nr_allocated = __alloc_pages_bulk(gfp, + interleave_nodes(pol), NULL, + nr_pages_per_node + 1, NULL, + page_array); + delta--; + } else { + nr_allocated = __alloc_pages_bulk(gfp, + interleave_nodes(pol), NULL, + nr_pages_per_node, NULL, page_array); + } + + page_array += nr_allocated; + total_allocated += nr_allocated; + } + + return total_allocated; +} + +static unsigned long alloc_pages_bulk_array_preferred_many(gfp_t gfp, int nid, + struct mempolicy *pol, unsigned long nr_pages, + struct page **page_array) +{ + gfp_t preferred_gfp; + unsigned long nr_allocated = 0; + + preferred_gfp = gfp | __GFP_NOWARN; + preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); + + nr_allocated = __alloc_pages_bulk(preferred_gfp, nid, &pol->nodes, + nr_pages, NULL, page_array); + + if (nr_allocated < nr_pages) + nr_allocated += __alloc_pages_bulk(gfp, numa_node_id(), NULL, + nr_pages - nr_allocated, NULL, + page_array + nr_allocated); + return nr_allocated; +} + +/* alloc pages bulk and mempolicy should be considered at the + * same time in some situation such as vmalloc. + * + * It can accelerate memory allocation especially interleaving + * allocate memory. + */ +unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp, + unsigned long nr_pages, struct page **page_array) +{ + struct mempolicy *pol = &default_policy; + + if (!in_interrupt() && !(gfp & __GFP_THISNODE)) + pol = get_task_policy(current); + + if (pol->mode == MPOL_INTERLEAVE) + return alloc_pages_bulk_array_interleave(gfp, pol, + nr_pages, page_array); + + if (pol->mode == MPOL_PREFERRED_MANY) + return alloc_pages_bulk_array_preferred_many(gfp, + numa_node_id(), pol, nr_pages, page_array); + + return __alloc_pages_bulk(gfp, policy_node(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol), nr_pages, NULL, + page_array); +} + int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(vma_policy(src)); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c56720136c45..d2a00ad4e1dd 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2843,7 +2843,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, * to fails, fallback to a single page allocator that is * more permissive. */ - if (!order && nid != NUMA_NO_NODE) { + if (!order) { while (nr_allocated < nr_pages) { unsigned int nr, nr_pages_request; @@ -2855,8 +2855,20 @@ vm_area_alloc_pages(gfp_t gfp, int nid, */ nr_pages_request = min(100U, nr_pages - nr_allocated); - nr = alloc_pages_bulk_array_node(gfp, nid, - nr_pages_request, pages + nr_allocated); + /* memory allocation should consider mempolicy, we can't + * wrongly use nearest node when nid == NUMA_NO_NODE, + * otherwise memory may be allocated in only one node, + * but mempolcy want to alloc memory by interleaving. + */ + if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE) + nr = alloc_pages_bulk_array_mempolicy(gfp, + nr_pages_request, + pages + nr_allocated); + + else + nr = alloc_pages_bulk_array_node(gfp, nid, + nr_pages_request, + pages + nr_allocated); nr_allocated += nr; cond_resched(); @@ -2868,7 +2880,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid, if (nr != nr_pages_request) break; } - } else if (order) + } else /* * Compound pages required for remap_vmalloc_page if * high-order pages. -- cgit v1.2.3 From 8ca1b5a49885f0c0c486544da46a9e0ac790831d Mon Sep 17 00:00:00 2001 From: Feng Tang Date: Fri, 5 Nov 2021 13:40:34 -0700 Subject: mm/page_alloc: detect allocation forbidden by cpuset and bail out early There was a report that starting an Ubuntu in docker while using cpuset to bind it to movable nodes (a node only has movable zone, like a node for hotplug or a Persistent Memory node in normal usage) will fail due to memory allocation failure, and then OOM is involved and many other innocent processes got killed. It can be reproduced with command: $ docker run -it --rm --cpuset-mems 4 ubuntu:latest bash -c "grep Mems_allowed /proc/self/status" (where node 4 is a movable node) runc:[2:INIT] invoked oom-killer: gfp_mask=0x500cc2(GFP_HIGHUSER|__GFP_ACCOUNT), order=0, oom_score_adj=0 CPU: 8 PID: 8291 Comm: runc:[2:INIT] Tainted: G W I E 5.8.2-0.g71b519a-default #1 openSUSE Tumbleweed (unreleased) Hardware name: Dell Inc. PowerEdge R640/0PHYDR, BIOS 2.6.4 04/09/2020 Call Trace: dump_stack+0x6b/0x88 dump_header+0x4a/0x1e2 oom_kill_process.cold+0xb/0x10 out_of_memory.part.0+0xaf/0x230 out_of_memory+0x3d/0x80 __alloc_pages_slowpath.constprop.0+0x954/0xa20 __alloc_pages_nodemask+0x2d3/0x300 pipe_write+0x322/0x590 new_sync_write+0x196/0x1b0 vfs_write+0x1c3/0x1f0 ksys_write+0xa7/0xe0 do_syscall_64+0x52/0xd0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Mem-Info: active_anon:392832 inactive_anon:182 isolated_anon:0 active_file:68130 inactive_file:151527 isolated_file:0 unevictable:2701 dirty:0 writeback:7 slab_reclaimable:51418 slab_unreclaimable:116300 mapped:45825 shmem:735 pagetables:2540 bounce:0 free:159849484 free_pcp:73 free_cma:0 Node 4 active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:0kB dirty:0kB writeback:0kB shmem:0kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 0kB writeback_tmp:0kB all_unreclaimable? no Node 4 Movable free:130021408kB min:9140kB low:139160kB high:269180kB reserved_highatomic:0KB active_anon:1448kB inactive_anon:0kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:130023424kB managed:130023424kB mlocked:0kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:292kB local_pcp:84kB free_cma:0kB lowmem_reserve[]: 0 0 0 0 0 Node 4 Movable: 1*4kB (M) 0*8kB 0*16kB 1*32kB (M) 0*64kB 0*128kB 1*256kB (M) 1*512kB (M) 1*1024kB (M) 0*2048kB 31743*4096kB (M) = 130021156kB oom-kill:constraint=CONSTRAINT_CPUSET,nodemask=(null),cpuset=docker-9976a269caec812c134fa317f27487ee36e1129beba7278a463dd53e5fb9997b.scope,mems_allowed=4,global_oom,task_memcg=/system.slice/containerd.service,task=containerd,pid=4100,uid=0 Out of memory: Killed process 4100 (containerd) total-vm:4077036kB, anon-rss:51184kB, file-rss:26016kB, shmem-rss:0kB, UID:0 pgtables:676kB oom_score_adj:0 oom_reaper: reaped process 8248 (docker), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 2054 (node_exporter), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 1452 (systemd-journal), now anon-rss:0kB, file-rss:8564kB, shmem-rss:4kB oom_reaper: reaped process 2146 (munin-node), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB oom_reaper: reaped process 8291 (runc:[2:INIT]), now anon-rss:0kB, file-rss:0kB, shmem-rss:0kB The reason is that in this case, the target cpuset nodes only have movable zone, while the creation of an OS in docker sometimes needs to allocate memory in non-movable zones (dma/dma32/normal) like GFP_HIGHUSER, and the cpuset limit forbids the allocation, then out-of-memory killing is involved even when normal nodes and movable nodes both have many free memory. The OOM killer cannot help to resolve the situation as there is no usable memory for the request in the cpuset scope. The only reasonable measure to take is to fail the allocation right away and have the caller to deal with it. So add a check for cases like this in the slowpath of allocation, and bail out early returning NULL for the allocation. As page allocation is one of the hottest path in kernel, this check will hurt all users with sane cpuset configuration, add a static branch check and detect the abnormal config in cpuset memory binding setup so that the extra check cost in page allocation is not paid by everyone. [thanks to Micho Hocko and David Rientjes for suggesting not handling it inside OOM code, adding cpuset check, refining comments] Link: https://lkml.kernel.org/r/1632481657-68112-1-git-send-email-feng.tang@intel.com Signed-off-by: Feng Tang Suggested-by: Michal Hocko Acked-by: Michal Hocko Cc: David Rientjes Cc: Tejun Heo Cc: Zefan Li Cc: Johannes Weiner Cc: Mel Gorman Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cpuset.h | 17 +++++++++++++++++ include/linux/mmzone.h | 22 ++++++++++++++++++++++ kernel/cgroup/cpuset.c | 23 +++++++++++++++++++++++ mm/page_alloc.c | 13 +++++++++++++ 4 files changed, 75 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index d2b9c41c8edf..d58e0476ee8e 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -34,6 +34,8 @@ */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; +extern struct static_key_false cpusets_insane_config_key; + static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); @@ -51,6 +53,19 @@ static inline void cpuset_dec(void) static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } +/* + * This will get enabled whenever a cpuset configuration is considered + * unsupportable in general. E.g. movable only node which cannot satisfy + * any non movable allocations (see update_nodemask). Page allocator + * needs to make additional checks for those configurations and this + * check is meant to guard those checks without any overhead for sane + * configurations. + */ +static inline bool cpusets_insane_config(void) +{ + return static_branch_unlikely(&cpusets_insane_config_key); +} + extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); @@ -167,6 +182,8 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline bool cpusets_enabled(void) { return false; } +static inline bool cpusets_insane_config(void) { return false; } + static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 832aa49d0d8e..fb36a29e3aae 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1220,6 +1220,28 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #define for_each_zone_zonelist(zone, z, zlist, highidx) \ for_each_zone_zonelist_nodemask(zone, z, zlist, highidx, NULL) +/* Whether the 'nodes' are all movable nodes */ +static inline bool movable_only_nodes(nodemask_t *nodes) +{ + struct zonelist *zonelist; + struct zoneref *z; + int nid; + + if (nodes_empty(*nodes)) + return false; + + /* + * We can chose arbitrary node from the nodemask to get a + * zonelist as they are interlinked. We just need to find + * at least one zone that can satisfy kernel allocations. + */ + nid = first_node(*nodes); + zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK]; + z = first_zones_zonelist(zonelist, ZONE_NORMAL, nodes); + return (!z->zone) ? true : false; +} + + #ifdef CONFIG_SPARSEMEM #include #endif diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2a9695ccb65f..d0e163a02099 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -69,6 +69,13 @@ DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); +/* + * There could be abnormal cpuset configurations for cpu or memory + * node binding, add this key to provide a quick low-cost judgement + * of the situation. + */ +DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key); + /* See "Frequency meter" comments, below. */ struct fmeter { @@ -372,6 +379,17 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); +static inline void check_insane_mems_config(nodemask_t *nodes) +{ + if (!cpusets_insane_config() && + movable_only_nodes(nodes)) { + static_branch_enable(&cpusets_insane_config_key); + pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n" + "Cpuset allocations might fail even with a lot of memory available.\n", + nodemask_pr_args(nodes)); + } +} + /* * Cgroup v2 behavior is used on the "cpus" and "mems" control files when * on default hierarchy or when the cpuset_v2_mode flag is set by mounting @@ -1870,6 +1888,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, if (retval < 0) goto done; + check_insane_mems_config(&trialcs->mems_allowed); + spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); @@ -3173,6 +3193,9 @@ update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); + if (mems_updated) + check_insane_mems_config(&new_mems); + if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e891560e0a80..e493d7da2614 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4910,6 +4910,19 @@ retry_cpuset: if (!ac->preferred_zoneref->zone) goto nopage; + /* + * Check for insane configurations where the cpuset doesn't contain + * any suitable zone to satisfy the request - e.g. non-movable + * GFP_HIGHUSER allocations from MOVABLE nodes only. + */ + if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) { + struct zoneref *z = first_zones_zonelist(ac->zonelist, + ac->highest_zoneidx, + &cpuset_current_mems_allowed); + if (!z->zone) + goto nopage; + } + if (alloc_flags & ALLOC_KSWAPD) wake_all_kswapds(order, gfp_mask, ac); -- cgit v1.2.3 From d2635f2012a44e3d469ab9a4022162dbe0e53f21 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Fri, 5 Nov 2021 13:40:40 -0700 Subject: mm: create a new system state and fix core_kernel_text() core_kernel_text() considers that until system_state in at least SYSTEM_RUNNING, init memory is valid. But init memory is freed a few lines before setting SYSTEM_RUNNING, so we have a small period of time when core_kernel_text() is wrong. Create an intermediate system state called SYSTEM_FREEING_INIT that is set before starting freeing init memory, and use it in core_kernel_text() to report init memory invalid earlier. Link: https://lkml.kernel.org/r/9ecfdee7dd4d741d172cb93ff1d87f1c58127c9a.1633001016.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy Cc: Gerald Schaefer Cc: Kefeng Wang Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Heiko Carstens Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 1 + init/main.c | 2 ++ kernel/extable.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 2776423a587e..471bc0593679 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -248,6 +248,7 @@ extern bool early_boot_irqs_disabled; extern enum system_states { SYSTEM_BOOTING, SYSTEM_SCHEDULING, + SYSTEM_FREEING_INITMEM, SYSTEM_RUNNING, SYSTEM_HALT, SYSTEM_POWER_OFF, diff --git a/init/main.c b/init/main.c index 3c4054a95545..767ee2672176 100644 --- a/init/main.c +++ b/init/main.c @@ -1506,6 +1506,8 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + + system_state = SYSTEM_FREEING_INITMEM; kprobe_free_init_mem(); ftrace_free_init_mem(); kgdb_free_init_mem(); diff --git a/kernel/extable.c b/kernel/extable.c index b0ea5eb0c3b4..290661f68e6b 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -76,7 +76,7 @@ int notrace core_kernel_text(unsigned long addr) addr < (unsigned long)_etext) return 1; - if (system_state < SYSTEM_RUNNING && + if (system_state < SYSTEM_FREEING_INITMEM && init_kernel_text(addr)) return 1; return 0; -- cgit v1.2.3 From 477d01fce8dacb41cae9363136ea56812e8baa59 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:40:58 -0700 Subject: mm: fix data race in PagePoisoned() PagePoisoned() accesses page->flags which can be updated concurrently: | BUG: KCSAN: data-race in next_uptodate_page / unlock_page | | write (marked) to 0xffffea00050f37c0 of 8 bytes by task 1872 on cpu 1: | instrument_atomic_write include/linux/instrumented.h:87 [inline] | clear_bit_unlock_is_negative_byte include/asm-generic/bitops/instrumented-lock.h:74 [inline] | unlock_page+0x102/0x1b0 mm/filemap.c:1465 | filemap_map_pages+0x6c6/0x890 mm/filemap.c:3057 | ... | read to 0xffffea00050f37c0 of 8 bytes by task 1873 on cpu 0: | PagePoisoned include/linux/page-flags.h:204 [inline] | PageReadahead include/linux/page-flags.h:382 [inline] | next_uptodate_page+0x456/0x830 mm/filemap.c:2975 | ... | CPU: 0 PID: 1873 Comm: systemd-udevd Not tainted 5.11.0-rc4-00001-gf9ce0be71d1f #1 To avoid the compiler tearing or otherwise optimizing the access, use READ_ONCE() to access flags. Link: https://lore.kernel.org/all/20210826144157.GA26950@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/20210913113542.2658064-1-elver@google.com Reported-by: kernel test robot Signed-off-by: Marco Elver Acked-by: Kirill A. Shutemov Acked-by: Will Deacon Cc: Marco Elver Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index fbfd3fad48f2..dd80cf0bb579 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -215,7 +215,7 @@ static __always_inline int PageCompound(struct page *page) #define PAGE_POISON_PATTERN -1l static inline int PagePoisoned(const struct page *page) { - return page->flags == PAGE_POISON_PATTERN; + return READ_ONCE(page->flags) == PAGE_POISON_PATTERN; } #ifdef CONFIG_DEBUG_VM -- cgit v1.2.3 From 73c54763482b841d9c14bad87eec98f80f700e0b Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Fri, 5 Nov 2021 13:41:17 -0700 Subject: mm/hugetlb: drop __unmap_hugepage_range definition from hugetlb.h Remove __unmap_hugepage_range() from the header file, because it is only used in hugetlb.c. Link: https://lkml.kernel.org/r/20210917165108.9341-1-peterx@redhat.com Signed-off-by: Peter Xu Suggested-by: Mike Kravetz Reviewed-by: Mike Kravetz Reviewed-by: John Hubbard Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 10 ---------- mm/hugetlb.c | 6 +++--- 2 files changed, 3 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 1faebe1cd0ed..3cbf60464398 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -143,9 +143,6 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page); -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo(void); @@ -385,13 +382,6 @@ static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, BUG(); } -static inline void __unmap_hugepage_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page) -{ - BUG(); -} - static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 95dc7b83381f..d394d9545c4e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4426,9 +4426,9 @@ again: return ret; } -void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page) +static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page) { struct mm_struct *mm = vma->vm_mm; unsigned long address; -- cgit v1.2.3 From 79dfc695525f60c8410015362b8aa4eb5c57210c Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:20 -0700 Subject: hugetlb: add demote hugetlb page sysfs interfaces Patch series "hugetlb: add demote/split page functionality", v4. The concurrent use of multiple hugetlb page sizes on a single system is becoming more common. One of the reasons is better TLB support for gigantic page sizes on x86 hardware. In addition, hugetlb pages are being used to back VMs in hosting environments. When using hugetlb pages to back VMs, it is often desirable to preallocate hugetlb pools. This avoids the delay and uncertainty of allocating hugetlb pages at VM startup. In addition, preallocating huge pages minimizes the issue of memory fragmentation that increases the longer the system is up and running. In such environments, a combination of larger and smaller hugetlb pages are preallocated in anticipation of backing VMs of various sizes. Over time, the preallocated pool of smaller hugetlb pages may become depleted while larger hugetlb pages still remain. In such situations, it is desirable to convert larger hugetlb pages to smaller hugetlb pages. Converting larger to smaller hugetlb pages can be accomplished today by first freeing the larger page to the buddy allocator and then allocating the smaller pages. For example, to convert 50 GB pages on x86: gb_pages=`cat .../hugepages-1048576kB/nr_hugepages` m2_pages=`cat .../hugepages-2048kB/nr_hugepages` echo $(($gb_pages - 50)) > .../hugepages-1048576kB/nr_hugepages echo $(($m2_pages + 25600)) > .../hugepages-2048kB/nr_hugepages On an idle system this operation is fairly reliable and results are as expected. The number of 2MB pages is increased as expected and the time of the operation is a second or two. However, when there is activity on the system the following issues arise: 1) This process can take quite some time, especially if allocation of the smaller pages is not immediate and requires migration/compaction. 2) There is no guarantee that the total size of smaller pages allocated will match the size of the larger page which was freed. This is because the area freed by the larger page could quickly be fragmented. In a test environment with a load that continually fills the page cache with clean pages, results such as the following can be observed: Unexpected number of 2MB pages allocated: Expected 25600, have 19944 real 0m42.092s user 0m0.008s sys 0m41.467s To address these issues, introduce the concept of hugetlb page demotion. Demotion provides a means of 'in place' splitting of a hugetlb page to pages of a smaller size. This avoids freeing pages to buddy and then trying to allocate from buddy. Page demotion is controlled via sysfs files that reside in the per-hugetlb page size and per node directories. - demote_size Target page size for demotion, a smaller huge page size. File can be written to chose a smaller huge page size if multiple are available. - demote Writable number of hugetlb pages to be demoted To demote 50 GB huge pages, one would: cat .../hugepages-1048576kB/free_hugepages /* optional, verify free pages */ cat .../hugepages-1048576kB/demote_size /* optional, verify target size */ echo 50 > .../hugepages-1048576kB/demote Only hugetlb pages which are free at the time of the request can be demoted. Demotion does not add to the complexity of surplus pages and honors reserved huge pages. Therefore, when a value is written to the sysfs demote file, that value is only the maximum number of pages which will be demoted. It is possible fewer will actually be demoted. The recently introduced per-hstate mutex is used to synchronize demote operations with other operations that modify hugetlb pools. Real world use cases -------------------- The above scenario describes a real world use case where hugetlb pages are used to back VMs on x86. Both issues of long allocation times and not necessarily getting the expected number of smaller huge pages after a free and allocate cycle have been experienced. The occurrence of these issues is dependent on other activity within the host and can not be predicted. This patch (of 5): Two new sysfs files are added to demote hugtlb pages. These files are both per-hugetlb page size and per node. Files are: demote_size - The size in Kb that pages are demoted to. (read-write) demote - The number of huge pages to demote. (write-only) By default, demote_size is the next smallest huge page size. Valid huge page sizes less than huge page size may be written to this file. When huge pages are demoted, they are demoted to this size. Writing a value to demote will result in an attempt to demote that number of hugetlb pages to an appropriate number of demote_size pages. NOTE: Demote interfaces are only provided for huge page sizes if there is a smaller target demote huge page size. For example, on x86 1GB huge pages will have demote interfaces. 2MB huge pages will not have demote interfaces. This patch does not provide full demote functionality. It only provides the sysfs interfaces. It also provides documentation for the new interfaces. [mike.kravetz@oracle.com: n_mask initialization does not need to be protected by the mutex] Link: https://lkml.kernel.org/r/0530e4ef-2492-5186-f919-5db68edea654@oracle.com Link: https://lkml.kernel.org/r/20211007181918.136982-2-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Reviewed-by: Oscar Salvador Cc: David Hildenbrand Cc: Michal Hocko Cc: Zi Yan Cc: Muchun Song Cc: Naoya Horiguchi Cc: David Rientjes Cc: "Aneesh Kumar K . V" Cc: Nghia Le Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/mm/hugetlbpage.rst | 30 +++++- include/linux/hugetlb.h | 1 + mm/hugetlb.c | 155 ++++++++++++++++++++++++++- 3 files changed, 183 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index 8abaeb144e44..bb90de3885d1 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -234,8 +234,12 @@ will exist, of the form:: hugepages-${size}kB -Inside each of these directories, the same set of files will exist:: +Inside each of these directories, the set of files contained in ``/proc`` +will exist. In addition, two additional interfaces for demoting huge +pages may exist:: + demote + demote_size nr_hugepages nr_hugepages_mempolicy nr_overcommit_hugepages @@ -243,7 +247,29 @@ Inside each of these directories, the same set of files will exist:: resv_hugepages surplus_hugepages -which function as described above for the default huge page-sized case. +The demote interfaces provide the ability to split a huge page into +smaller huge pages. For example, the x86 architecture supports both +1GB and 2MB huge pages sizes. A 1GB huge page can be split into 512 +2MB huge pages. Demote interfaces are not available for the smallest +huge page size. The demote interfaces are: + +demote_size + is the size of demoted pages. When a page is demoted a corresponding + number of huge pages of demote_size will be created. By default, + demote_size is set to the next smaller huge page size. If there are + multiple smaller huge page sizes, demote_size can be set to any of + these smaller sizes. Only huge page sizes less than the current huge + pages size are allowed. + +demote + is used to demote a number of huge pages. A user with root privileges + can write to this file. It may not be possible to demote the + requested number of huge pages. To determine how many pages were + actually demoted, compare the value of nr_hugepages before and after + writing to the demote interface. demote is a write only interface. + +The interfaces which are the same as in ``/proc`` (all except demote and +demote_size) function as described above for the default huge page-sized case. .. _mem_policy_and_hp_alloc: diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 3cbf60464398..2bddd6c38204 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -586,6 +586,7 @@ struct hstate { int next_nid_to_alloc; int next_nid_to_free; unsigned int order; + unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index d394d9545c4e..1a18ff2f0001 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2986,7 +2986,7 @@ free: static void __init hugetlb_init_hstates(void) { - struct hstate *h; + struct hstate *h, *h2; for_each_hstate(h) { if (minimum_order > huge_page_order(h)) @@ -2995,6 +2995,22 @@ static void __init hugetlb_init_hstates(void) /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); + + /* + * Set demote order for each hstate. Note that + * h->demote_order is initially 0. + * - We can not demote gigantic pages if runtime freeing + * is not supported, so skip this. + */ + if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported()) + continue; + for_each_hstate(h2) { + if (h2 == h) + continue; + if (h2->order < h->order && + h2->order > h->demote_order) + h->demote_order = h2->order; + } } VM_BUG_ON(minimum_order == UINT_MAX); } @@ -3235,9 +3251,31 @@ out: return 0; } +static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed) + __must_hold(&hugetlb_lock) +{ + int rc = 0; + + lockdep_assert_held(&hugetlb_lock); + + /* We should never get here if no demote order */ + if (!h->demote_order) { + pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); + return -EINVAL; /* internal error */ + } + + /* + * TODO - demote fucntionality will be added in subsequent patch + */ + return rc; +} + #define HSTATE_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) +#define HSTATE_ATTR_WO(_name) \ + static struct kobj_attribute _name##_attr = __ATTR_WO(_name) + #define HSTATE_ATTR(_name) \ static struct kobj_attribute _name##_attr = \ __ATTR(_name, 0644, _name##_show, _name##_store) @@ -3433,6 +3471,105 @@ static ssize_t surplus_hugepages_show(struct kobject *kobj, } HSTATE_ATTR_RO(surplus_hugepages); +static ssize_t demote_store(struct kobject *kobj, + struct kobj_attribute *attr, const char *buf, size_t len) +{ + unsigned long nr_demote; + unsigned long nr_available; + nodemask_t nodes_allowed, *n_mask; + struct hstate *h; + int err = 0; + int nid; + + err = kstrtoul(buf, 10, &nr_demote); + if (err) + return err; + h = kobj_to_hstate(kobj, &nid); + + if (nid != NUMA_NO_NODE) { + init_nodemask_of_node(&nodes_allowed, nid); + n_mask = &nodes_allowed; + } else { + n_mask = &node_states[N_MEMORY]; + } + + /* Synchronize with other sysfs operations modifying huge pages */ + mutex_lock(&h->resize_lock); + spin_lock_irq(&hugetlb_lock); + + while (nr_demote) { + /* + * Check for available pages to demote each time thorough the + * loop as demote_pool_huge_page will drop hugetlb_lock. + * + * NOTE: demote_pool_huge_page does not yet drop hugetlb_lock + * but will when full demote functionality is added in a later + * patch. + */ + if (nid != NUMA_NO_NODE) + nr_available = h->free_huge_pages_node[nid]; + else + nr_available = h->free_huge_pages; + nr_available -= h->resv_huge_pages; + if (!nr_available) + break; + + err = demote_pool_huge_page(h, n_mask); + if (err) + break; + + nr_demote--; + } + + spin_unlock_irq(&hugetlb_lock); + mutex_unlock(&h->resize_lock); + + if (err) + return err; + return len; +} +HSTATE_ATTR_WO(demote); + +static ssize_t demote_size_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + int nid; + struct hstate *h = kobj_to_hstate(kobj, &nid); + unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K; + + return sysfs_emit(buf, "%lukB\n", demote_size); +} + +static ssize_t demote_size_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + struct hstate *h, *demote_hstate; + unsigned long demote_size; + unsigned int demote_order; + int nid; + + demote_size = (unsigned long)memparse(buf, NULL); + + demote_hstate = size_to_hstate(demote_size); + if (!demote_hstate) + return -EINVAL; + demote_order = demote_hstate->order; + + /* demote order must be smaller than hstate order */ + h = kobj_to_hstate(kobj, &nid); + if (demote_order >= h->order) + return -EINVAL; + + /* resize_lock synchronizes access to demote size and writes */ + mutex_lock(&h->resize_lock); + h->demote_order = demote_order; + mutex_unlock(&h->resize_lock); + + return count; +} +HSTATE_ATTR(demote_size); + static struct attribute *hstate_attrs[] = { &nr_hugepages_attr.attr, &nr_overcommit_hugepages_attr.attr, @@ -3449,6 +3586,16 @@ static const struct attribute_group hstate_attr_group = { .attrs = hstate_attrs, }; +static struct attribute *hstate_demote_attrs[] = { + &demote_size_attr.attr, + &demote_attr.attr, + NULL, +}; + +static const struct attribute_group hstate_demote_attr_group = { + .attrs = hstate_demote_attrs, +}; + static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, struct kobject **hstate_kobjs, const struct attribute_group *hstate_attr_group) @@ -3466,6 +3613,12 @@ static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent, hstate_kobjs[hi] = NULL; } + if (h->demote_order) { + if (sysfs_create_group(hstate_kobjs[hi], + &hstate_demote_attr_group)) + pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name); + } + return retval; } -- cgit v1.2.3 From 9871e2ded6c1ff61a59988d7a0e975f012105d52 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Nov 2021 13:41:23 -0700 Subject: mm/cma: add cma_pages_valid to determine if pages are in CMA Add new interface cma_pages_valid() which indicates if the specified pages are part of a CMA region. This interface will be used in a subsequent patch by hugetlb code. In order to keep the same amount of DEBUG information, a pr_debug() call was added to cma_pages_valid(). In the case where the page passed to cma_release is not in cma region, the debug message will be printed from cma_pages_valid as opposed to cma_release. Link: https://lkml.kernel.org/r/20211007181918.136982-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: "Aneesh Kumar K . V" Cc: David Rientjes Cc: Michal Hocko Cc: Muchun Song Cc: Naoya Horiguchi Cc: Nghia Le Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/cma.h | 1 + mm/cma.c | 24 ++++++++++++++++++++---- 2 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cma.h b/include/linux/cma.h index 53fd8c3cdbd0..bd801023504b 100644 --- a/include/linux/cma.h +++ b/include/linux/cma.h @@ -46,6 +46,7 @@ extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, struct cma **res_cma); extern struct page *cma_alloc(struct cma *cma, unsigned long count, unsigned int align, bool no_warn); +extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned long count); extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count); extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data); diff --git a/mm/cma.c b/mm/cma.c index 995e15480937..11152c3fb23c 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -524,6 +524,25 @@ out: return page; } +bool cma_pages_valid(struct cma *cma, const struct page *pages, + unsigned long count) +{ + unsigned long pfn; + + if (!cma || !pages) + return false; + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) { + pr_debug("%s(page %p, count %lu)\n", __func__, + (void *)pages, count); + return false; + } + + return true; +} + /** * cma_release() - release allocated pages * @cma: Contiguous memory region for which the allocation is performed. @@ -539,16 +558,13 @@ bool cma_release(struct cma *cma, const struct page *pages, { unsigned long pfn; - if (!cma || !pages) + if (!cma_pages_valid(cma, pages, count)) return false; pr_debug("%s(page %p, count %lu)\n", __func__, (void *)pages, count); pfn = page_to_pfn(pages); - if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) - return false; - VM_BUG_ON(pfn + count > cma->base_pfn + cma->count); free_contig_range(pfn, count); -- cgit v1.2.3 From bd3400ea173fb611cdf2030d03620185ff6c0b0e Mon Sep 17 00:00:00 2001 From: Liangcai Fan Date: Fri, 5 Nov 2021 13:41:36 -0700 Subject: mm: khugepaged: recalculate min_free_kbytes after stopping khugepaged When initializing transparent huge pages, min_free_kbytes would be calculated according to what khugepaged expected. So when transparent huge pages get disabled, min_free_kbytes should be recalculated instead of the higher value set by khugepaged. Link: https://lkml.kernel.org/r/1633937809-16558-1-git-send-email-liangcaifan19@gmail.com Signed-off-by: Liangcai Fan Signed-off-by: Chunyan Zhang Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + mm/khugepaged.c | 10 ++++++++-- mm/page_alloc.c | 7 ++++++- 3 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 6e29deb1e0d4..7e37c726b9db 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2453,6 +2453,7 @@ extern void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int migratetype); extern void setup_per_zone_wmarks(void); +extern void calculate_min_free_kbytes(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 8a8b3aa92937..629961966854 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2299,6 +2299,11 @@ static void set_recommended_min_free_kbytes(void) int nr_zones = 0; unsigned long recommended_min; + if (!khugepaged_enabled()) { + calculate_min_free_kbytes(); + goto update_wmarks; + } + for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of @@ -2334,6 +2339,8 @@ static void set_recommended_min_free_kbytes(void) min_free_kbytes = recommended_min; } + +update_wmarks: setup_per_zone_wmarks(); } @@ -2355,12 +2362,11 @@ int start_stop_khugepaged(void) if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); - - set_recommended_min_free_kbytes(); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } + set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a7035467bf6d..09a0f1c5d5d2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -8469,7 +8469,7 @@ void setup_per_zone_wmarks(void) * 8192MB: 11584k * 16384MB: 16384k */ -int __meminit init_per_zone_wmark_min(void) +void calculate_min_free_kbytes(void) { unsigned long lowmem_kbytes; int new_min_free_kbytes; @@ -8483,6 +8483,11 @@ int __meminit init_per_zone_wmark_min(void) pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n", new_min_free_kbytes, user_min_free_kbytes); +} + +int __meminit init_per_zone_wmark_min(void) +{ + calculate_min_free_kbytes(); setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); -- cgit v1.2.3 From 550a7d60bd5e35a56942dba6d8a26752beb26c9f Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 5 Nov 2021 13:41:40 -0700 Subject: mm, hugepages: add mremap() support for hugepage backed vma Support mremap() for hugepage backed vma segment by simply repositioning page table entries. The page table entries are repositioned to the new virtual address on mremap(). Hugetlb mremap() support is of course generic; my motivating use case is a library (hugepage_text), which reloads the ELF text of executables in hugepages. This significantly increases the execution performance of said executables. Restrict the mremap operation on hugepages to up to the size of the original mapping as the underlying hugetlb reservation is not yet capable of handling remapping to a larger size. During the mremap() operation we detect pmd_share'd mappings and we unshare those during the mremap(). On access and fault the sharing is established again. Link: https://lkml.kernel.org/r/20211013195825.3058275-1-almasrymina@google.com Signed-off-by: Mina Almasry Reviewed-by: Mike Kravetz Cc: Ken Chen Cc: Chris Kennelly Cc: Michal Hocko Cc: Vlastimil Babka Cc: Kirill Shutemov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 19 +++++++++ mm/hugetlb.c | 111 +++++++++++++++++++++++++++++++++++++++++++++--- mm/mremap.c | 36 ++++++++++++++-- 3 files changed, 157 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 2bddd6c38204..c0a20781b28e 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -124,6 +124,7 @@ struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, void hugepage_put_subpool(struct hugepage_subpool *spool); void reset_vma_resv_huge_pages(struct vm_area_struct *vma); +void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int hugetlb_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); int hugetlb_overcommit_handler(struct ctl_table *, int, void *, size_t *, loff_t *); @@ -132,6 +133,10 @@ int hugetlb_treat_movable_handler(struct ctl_table *, int, void *, size_t *, int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int, void *, size_t *, loff_t *); +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *); long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, @@ -215,6 +220,10 @@ static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma) { } +static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ +} + static inline unsigned long hugetlb_total_pages(void) { return 0; @@ -262,6 +271,16 @@ static inline int copy_hugetlb_page_range(struct mm_struct *dst, return 0; } +static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, + unsigned long new_addr, + unsigned long len) +{ + BUG(); + return 0; +} + static inline void hugetlb_report_meminfo(struct seq_file *m) { } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1835d548fecc..8028fb7677eb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1014,6 +1014,35 @@ void reset_vma_resv_huge_pages(struct vm_area_struct *vma) vma->vm_private_data = (void *)0; } +/* + * Reset and decrement one ref on hugepage private reservation. + * Called with mm->mmap_sem writer semaphore held. + * This function should be only used by move_vma() and operate on + * same sized vma. It should never come here with last ref on the + * reservation. + */ +void clear_vma_resv_huge_pages(struct vm_area_struct *vma) +{ + /* + * Clear the old hugetlb private page reservation. + * It has already been transferred to new_vma. + * + * During a mremap() operation of a hugetlb vma we call move_vma() + * which copies vma into new_vma and unmaps vma. After the copy + * operation both new_vma and vma share a reference to the resv_map + * struct, and at that point vma is about to be unmapped. We don't + * want to return the reservation to the pool at unmap of vma because + * the reservation still lives on in new_vma, so simply decrement the + * ref here and remove the resv_map reference from this vma. + */ + struct resv_map *reservations = vma_resv_map(vma); + + if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + kref_put(&reservations->refs, resv_map_release); + + reset_vma_resv_huge_pages(vma); +} + /* Returns true if the VMA has associated reserve pages */ static bool vma_has_reserves(struct vm_area_struct *vma, long chg) { @@ -4718,6 +4747,82 @@ again: return ret; } +static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, + unsigned long new_addr, pte_t *src_pte) +{ + struct hstate *h = hstate_vma(vma); + struct mm_struct *mm = vma->vm_mm; + pte_t *dst_pte, pte; + spinlock_t *src_ptl, *dst_ptl; + + dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h)); + dst_ptl = huge_pte_lock(h, mm, dst_pte); + src_ptl = huge_pte_lockptr(h, mm, src_pte); + + /* + * We don't have to worry about the ordering of src and dst ptlocks + * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock. + */ + if (src_ptl != dst_ptl) + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + + pte = huge_ptep_get_and_clear(mm, old_addr, src_pte); + set_huge_pte_at(mm, new_addr, dst_pte, pte); + + if (src_ptl != dst_ptl) + spin_unlock(src_ptl); + spin_unlock(dst_ptl); +} + +int move_hugetlb_page_tables(struct vm_area_struct *vma, + struct vm_area_struct *new_vma, + unsigned long old_addr, unsigned long new_addr, + unsigned long len) +{ + struct hstate *h = hstate_vma(vma); + struct address_space *mapping = vma->vm_file->f_mapping; + unsigned long sz = huge_page_size(h); + struct mm_struct *mm = vma->vm_mm; + unsigned long old_end = old_addr + len; + unsigned long old_addr_copy; + pte_t *src_pte, *dst_pte; + struct mmu_notifier_range range; + + mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, old_addr, + old_end); + adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); + mmu_notifier_invalidate_range_start(&range); + /* Prevent race with file truncation */ + i_mmap_lock_write(mapping); + for (; old_addr < old_end; old_addr += sz, new_addr += sz) { + src_pte = huge_pte_offset(mm, old_addr, sz); + if (!src_pte) + continue; + if (huge_pte_none(huge_ptep_get(src_pte))) + continue; + + /* old_addr arg to huge_pmd_unshare() is a pointer and so the + * arg may be modified. Pass a copy instead to preserve the + * value in old_addr. + */ + old_addr_copy = old_addr; + + if (huge_pmd_unshare(mm, vma, &old_addr_copy, src_pte)) + continue; + + dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); + if (!dst_pte) + break; + + move_huge_pte(vma, old_addr, new_addr, src_pte); + } + i_mmap_unlock_write(mapping); + flush_tlb_range(vma, old_end - len, old_end); + mmu_notifier_invalidate_range_end(&range); + + return len + old_addr - old_end; +} + static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page) @@ -6257,12 +6362,6 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * sharing is possible. For hugetlbfs, this prevents removal of any page * table entries associated with the address space. This is important as we * are setting up sharing based on existing page table entries (mappings). - * - * NOTE: This routine is only called from huge_pte_alloc. Some callers of - * huge_pte_alloc know that sharing is not possible and do not take - * i_mmap_rwsem as a performance optimization. This is handled by the - * if !vma_shareable check at the beginning of the routine. i_mmap_rwsem is - * only required for subsequent processing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) diff --git a/mm/mremap.c b/mm/mremap.c index c0b6c41b7b78..002eec83e91e 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -489,6 +489,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma, old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); + if (is_vm_hugetlb_page(vma)) + return move_hugetlb_page_tables(vma, new_vma, old_addr, + new_addr, len); + mmu_notifier_range_init(&range, MMU_NOTIFY_UNMAP, 0, vma, vma->vm_mm, old_addr, old_end); mmu_notifier_invalidate_range_start(&range); @@ -646,6 +650,10 @@ static unsigned long move_vma(struct vm_area_struct *vma, mremap_userfaultfd_prep(new_vma, uf); } + if (is_vm_hugetlb_page(vma)) { + clear_vma_resv_huge_pages(vma); + } + /* Conceal VM_ACCOUNT so old reservation is not undone */ if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP)) { vma->vm_flags &= ~VM_ACCOUNT; @@ -739,9 +747,6 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, (vma->vm_flags & (VM_DONTEXPAND | VM_PFNMAP))) return ERR_PTR(-EINVAL); - if (is_vm_hugetlb_page(vma)) - return ERR_PTR(-EINVAL); - /* We can't remap across vm area boundaries */ if (old_len > vma->vm_end - addr) return ERR_PTR(-EFAULT); @@ -937,6 +942,31 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, if (mmap_write_lock_killable(current->mm)) return -EINTR; + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) { + ret = EFAULT; + goto out; + } + + if (is_vm_hugetlb_page(vma)) { + struct hstate *h __maybe_unused = hstate_vma(vma); + + old_len = ALIGN(old_len, huge_page_size(h)); + new_len = ALIGN(new_len, huge_page_size(h)); + + /* addrs must be huge page aligned */ + if (addr & ~huge_page_mask(h)) + goto out; + if (new_addr & ~huge_page_mask(h)) + goto out; + + /* + * Don't allow remap expansion, because the underlying hugetlb + * reservation is not yet capable to handle split reservation. + */ + if (new_len > old_len) + goto out; + } if (flags & (MREMAP_FIXED | MREMAP_DONTUNMAP)) { ret = mremap_to(addr, old_len, new_addr, new_len, -- cgit v1.2.3 From 8cd7c588decf470bf7e14f2be93b709f839a965e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:25 -0700 Subject: mm/vmscan: throttle reclaim until some writeback completes if congested Patch series "Remove dependency on congestion_wait in mm/", v5. This series that removes all calls to congestion_wait in mm/ and deletes wait_iff_congested. It's not a clever implementation but congestion_wait has been broken for a long time [1]. Even if congestion throttling worked, it was never a great idea. While excessive dirty/writeback pages at the tail of the LRU is one possibility that reclaim may be slow, there is also the problem of too many pages being isolated and reclaim failing for other reasons (elevated references, too many pages isolated, excessive LRU contention etc). This series replaces the "congestion" throttling with 3 different types. - If there are too many dirty/writeback pages, sleep until a timeout or enough pages get cleaned - If too many pages are isolated, sleep until enough isolated pages are either reclaimed or put back on the LRU - If no progress is being made, direct reclaim tasks sleep until another task makes progress with acceptable efficiency. This was initially tested with a mix of workloads that used to trigger corner cases that no longer work. A new test case was created called "stutterp" (pagereclaim-stutterp-noreaders in mmtests) using a freshly created XFS filesystem. Note that it may be necessary to increase the timeout of ssh if executing remotely as ssh itself can get throttled and the connection may timeout. stutterp varies the number of "worker" processes from 4 up to NR_CPUS*4 to check the impact as the number of direct reclaimers increase. It has four types of worker. - One "anon latency" worker creates small mappings with mmap() and times how long it takes to fault the mapping reading it 4K at a time - X file writers which is fio randomly writing X files where the total size of the files add up to the allowed dirty_ratio. fio is allowed to run for a warmup period to allow some file-backed pages to accumulate. The duration of the warmup is based on the best-case linear write speed of the storage. - Y file readers which is fio randomly reading small files - Z anon memory hogs which continually map (100-dirty_ratio)% of memory - Total estimated WSS = (100+dirty_ration) percentage of memory X+Y+Z+1 == NR_WORKERS varying from 4 up to NR_CPUS*4 The intent is to maximise the total WSS with a mix of file and anon memory where some anonymous memory must be swapped and there is a high likelihood of dirty/writeback pages reaching the end of the LRU. The test can be configured to have no background readers to stress dirty/writeback pages. The results below are based on having zero readers. The short summary of the results is that the series works and stalls until some event occurs but the timeouts may need adjustment. The test results are not broken down by patch as the series should be treated as one block that replaces a broken throttling mechanism with a working one. Finally, three machines were tested but I'm reporting the worst set of results. The other two machines had much better latencies for example. First the results of the "anon latency" latency stutterp 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r4 Amean mmap-4 31.4003 ( 0.00%) 2661.0198 (-8374.52%) Amean mmap-7 38.1641 ( 0.00%) 149.2891 (-291.18%) Amean mmap-12 60.0981 ( 0.00%) 187.8105 (-212.51%) Amean mmap-21 161.2699 ( 0.00%) 213.9107 ( -32.64%) Amean mmap-30 174.5589 ( 0.00%) 377.7548 (-116.41%) Amean mmap-48 8106.8160 ( 0.00%) 1070.5616 ( 86.79%) Stddev mmap-4 41.3455 ( 0.00%) 27573.9676 (-66591.66%) Stddev mmap-7 53.5556 ( 0.00%) 4608.5860 (-8505.23%) Stddev mmap-12 171.3897 ( 0.00%) 5559.4542 (-3143.75%) Stddev mmap-21 1506.6752 ( 0.00%) 5746.2507 (-281.39%) Stddev mmap-30 557.5806 ( 0.00%) 7678.1624 (-1277.05%) Stddev mmap-48 61681.5718 ( 0.00%) 14507.2830 ( 76.48%) Max-90 mmap-4 31.4243 ( 0.00%) 83.1457 (-164.59%) Max-90 mmap-7 41.0410 ( 0.00%) 41.0720 ( -0.08%) Max-90 mmap-12 66.5255 ( 0.00%) 53.9073 ( 18.97%) Max-90 mmap-21 146.7479 ( 0.00%) 105.9540 ( 27.80%) Max-90 mmap-30 193.9513 ( 0.00%) 64.3067 ( 66.84%) Max-90 mmap-48 277.9137 ( 0.00%) 591.0594 (-112.68%) Max mmap-4 1913.8009 ( 0.00%) 299623.9695 (-15555.96%) Max mmap-7 2423.9665 ( 0.00%) 204453.1708 (-8334.65%) Max mmap-12 6845.6573 ( 0.00%) 221090.3366 (-3129.64%) Max mmap-21 56278.6508 ( 0.00%) 213877.3496 (-280.03%) Max mmap-30 19716.2990 ( 0.00%) 216287.6229 (-997.00%) Max mmap-48 477923.9400 ( 0.00%) 245414.8238 ( 48.65%) For most thread counts, the time to mmap() is unfortunately increased. In earlier versions of the series, this was lower but a large number of throttling events were reaching their timeout increasing the amount of inefficient scanning of the LRU. There is no prioritisation of reclaim tasks making progress based on each tasks rate of page allocation versus progress of reclaim. The variance is also impacted for high worker counts but in all cases, the differences in latency are not statistically significant due to very large maximum outliers. Max-90 shows that 90% of the stalls are comparable but the Max results show the massive outliers which are increased to to stalling. It is expected that this will be very machine dependant. Due to the test design, reclaim is difficult so allocations stall and there are variances depending on whether THPs can be allocated or not. The amount of memory will affect exactly how bad the corner cases are and how often they trigger. The warmup period calculation is not ideal as it's based on linear writes where as fio is randomly writing multiple files from multiple tasks so the start state of the test is variable. For example, these are the latencies on a single-socket machine that had more memory Amean mmap-4 42.2287 ( 0.00%) 49.6838 * -17.65%* Amean mmap-7 216.4326 ( 0.00%) 47.4451 * 78.08%* Amean mmap-12 2412.0588 ( 0.00%) 51.7497 ( 97.85%) Amean mmap-21 5546.2548 ( 0.00%) 51.8862 ( 99.06%) Amean mmap-30 1085.3121 ( 0.00%) 72.1004 ( 93.36%) The overall system CPU usage and elapsed time is as follows 5.15.0-rc3 5.15.0-rc3 vanilla mm-reclaimcongest-v5r4 Duration User 6989.03 983.42 Duration System 7308.12 799.68 Duration Elapsed 2277.67 2092.98 The patches reduce system CPU usage by 89% as the vanilla kernel is rarely stalling. The high-level /proc/vmstats show 5.15.0-rc1 5.15.0-rc1 vanilla mm-reclaimcongest-v5r2 Ops Direct pages scanned 1056608451.00 503594991.00 Ops Kswapd pages scanned 109795048.00 147289810.00 Ops Kswapd pages reclaimed 63269243.00 31036005.00 Ops Direct pages reclaimed 10803973.00 6328887.00 Ops Kswapd efficiency % 57.62 21.07 Ops Kswapd velocity 48204.98 57572.86 Ops Direct efficiency % 1.02 1.26 Ops Direct velocity 463898.83 196845.97 Kswapd scanned less pages but the detailed pattern is different. The vanilla kernel scans slowly over time where as the patches exhibits burst patterns of scan activity. Direct reclaim scanning is reduced by 52% due to stalling. The pattern for stealing pages is also slightly different. Both kernels exhibit spikes but the vanilla kernel when reclaiming shows pages being reclaimed over a period of time where as the patches tend to reclaim in spikes. The difference is that vanilla is not throttling and instead scanning constantly finding some pages over time where as the patched kernel throttles and reclaims in spikes. Ops Percentage direct scans 90.59 77.37 For direct reclaim, vanilla scanned 90.59% of pages where as with the patches, 77.37% were direct reclaim due to throttling Ops Page writes by reclaim 2613590.00 1687131.00 Page writes from reclaim context are reduced. Ops Page writes anon 2932752.00 1917048.00 And there is less swapping. Ops Page reclaim immediate 996248528.00 107664764.00 The number of pages encountered at the tail of the LRU tagged for immediate reclaim but still dirty/writeback is reduced by 89%. Ops Slabs scanned 164284.00 153608.00 Slab scan activity is similar. ftrace was used to gather stall activity Vanilla ------- 1 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=16000 2 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=12000 8 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=8000 29 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=4000 82394 writeback_wait_iff_congested: usec_timeout=100000 usec_delayed=0 The fast majority of wait_iff_congested calls do not stall at all. What is likely happening is that cond_resched() reschedules the task for a short period when the BDI is not registering congestion (which it never will in this test setup). 1 writeback_congestion_wait: usec_timeout=100000 usec_delayed=120000 2 writeback_congestion_wait: usec_timeout=100000 usec_delayed=132000 4 writeback_congestion_wait: usec_timeout=100000 usec_delayed=112000 380 writeback_congestion_wait: usec_timeout=100000 usec_delayed=108000 778 writeback_congestion_wait: usec_timeout=100000 usec_delayed=104000 congestion_wait if called always exceeds the timeout as there is no trigger to wake it up. Bottom line: Vanilla will throttle but it's not effective. Patch series ------------ Kswapd throttle activity was always due to scanning pages tagged for immediate reclaim at the tail of the LRU 1 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 4 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 94 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 112 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK The majority of events did not stall or stalled for a short period. Roughly 16% of stalls reached the timeout before expiry. For direct reclaim, the number of times stalled for each reason were 6624 reason=VMSCAN_THROTTLE_ISOLATED 93246 reason=VMSCAN_THROTTLE_NOPROGRESS 96934 reason=VMSCAN_THROTTLE_WRITEBACK The most common reason to stall was due to excessive pages tagged for immediate reclaim at the tail of the LRU followed by a failure to make forward. A relatively small number were due to too many pages isolated from the LRU by parallel threads For VMSCAN_THROTTLE_ISOLATED, the breakdown of delays was 9 usec_timeout=20000 usect_delayed=4000 reason=VMSCAN_THROTTLE_ISOLATED 12 usec_timeout=20000 usect_delayed=16000 reason=VMSCAN_THROTTLE_ISOLATED 83 usec_timeout=20000 usect_delayed=20000 reason=VMSCAN_THROTTLE_ISOLATED 6520 usec_timeout=20000 usect_delayed=0 reason=VMSCAN_THROTTLE_ISOLATED Most did not stall at all. A small number reached the timeout. For VMSCAN_THROTTLE_NOPROGRESS, the breakdown of stalls were all over the map 1 usec_timeout=500000 usect_delayed=324000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=332000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=348000 reason=VMSCAN_THROTTLE_NOPROGRESS 1 usec_timeout=500000 usect_delayed=360000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=228000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=260000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=340000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=364000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=372000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=428000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=460000 reason=VMSCAN_THROTTLE_NOPROGRESS 2 usec_timeout=500000 usect_delayed=464000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=244000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=252000 reason=VMSCAN_THROTTLE_NOPROGRESS 3 usec_timeout=500000 usect_delayed=272000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=188000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=268000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=328000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=380000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=392000 reason=VMSCAN_THROTTLE_NOPROGRESS 4 usec_timeout=500000 usect_delayed=432000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=204000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=220000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=412000 reason=VMSCAN_THROTTLE_NOPROGRESS 5 usec_timeout=500000 usect_delayed=436000 reason=VMSCAN_THROTTLE_NOPROGRESS 6 usec_timeout=500000 usect_delayed=488000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=212000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=300000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=316000 reason=VMSCAN_THROTTLE_NOPROGRESS 7 usec_timeout=500000 usect_delayed=472000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=248000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=356000 reason=VMSCAN_THROTTLE_NOPROGRESS 8 usec_timeout=500000 usect_delayed=456000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=124000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=376000 reason=VMSCAN_THROTTLE_NOPROGRESS 9 usec_timeout=500000 usect_delayed=484000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=172000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=420000 reason=VMSCAN_THROTTLE_NOPROGRESS 10 usec_timeout=500000 usect_delayed=452000 reason=VMSCAN_THROTTLE_NOPROGRESS 11 usec_timeout=500000 usect_delayed=256000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=112000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=116000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=144000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=152000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=264000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=384000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=424000 reason=VMSCAN_THROTTLE_NOPROGRESS 12 usec_timeout=500000 usect_delayed=492000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=184000 reason=VMSCAN_THROTTLE_NOPROGRESS 13 usec_timeout=500000 usect_delayed=444000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=308000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=440000 reason=VMSCAN_THROTTLE_NOPROGRESS 14 usec_timeout=500000 usect_delayed=476000 reason=VMSCAN_THROTTLE_NOPROGRESS 16 usec_timeout=500000 usect_delayed=140000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=232000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=240000 reason=VMSCAN_THROTTLE_NOPROGRESS 17 usec_timeout=500000 usect_delayed=280000 reason=VMSCAN_THROTTLE_NOPROGRESS 18 usec_timeout=500000 usect_delayed=404000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=148000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=216000 reason=VMSCAN_THROTTLE_NOPROGRESS 20 usec_timeout=500000 usect_delayed=468000 reason=VMSCAN_THROTTLE_NOPROGRESS 21 usec_timeout=500000 usect_delayed=448000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=168000 reason=VMSCAN_THROTTLE_NOPROGRESS 23 usec_timeout=500000 usect_delayed=296000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=132000 reason=VMSCAN_THROTTLE_NOPROGRESS 25 usec_timeout=500000 usect_delayed=352000 reason=VMSCAN_THROTTLE_NOPROGRESS 26 usec_timeout=500000 usect_delayed=180000 reason=VMSCAN_THROTTLE_NOPROGRESS 27 usec_timeout=500000 usect_delayed=284000 reason=VMSCAN_THROTTLE_NOPROGRESS 28 usec_timeout=500000 usect_delayed=164000 reason=VMSCAN_THROTTLE_NOPROGRESS 29 usec_timeout=500000 usect_delayed=136000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=200000 reason=VMSCAN_THROTTLE_NOPROGRESS 30 usec_timeout=500000 usect_delayed=400000 reason=VMSCAN_THROTTLE_NOPROGRESS 31 usec_timeout=500000 usect_delayed=196000 reason=VMSCAN_THROTTLE_NOPROGRESS 32 usec_timeout=500000 usect_delayed=156000 reason=VMSCAN_THROTTLE_NOPROGRESS 33 usec_timeout=500000 usect_delayed=224000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=128000 reason=VMSCAN_THROTTLE_NOPROGRESS 35 usec_timeout=500000 usect_delayed=176000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=368000 reason=VMSCAN_THROTTLE_NOPROGRESS 36 usec_timeout=500000 usect_delayed=496000 reason=VMSCAN_THROTTLE_NOPROGRESS 37 usec_timeout=500000 usect_delayed=312000 reason=VMSCAN_THROTTLE_NOPROGRESS 38 usec_timeout=500000 usect_delayed=304000 reason=VMSCAN_THROTTLE_NOPROGRESS 40 usec_timeout=500000 usect_delayed=288000 reason=VMSCAN_THROTTLE_NOPROGRESS 43 usec_timeout=500000 usect_delayed=408000 reason=VMSCAN_THROTTLE_NOPROGRESS 55 usec_timeout=500000 usect_delayed=416000 reason=VMSCAN_THROTTLE_NOPROGRESS 56 usec_timeout=500000 usect_delayed=76000 reason=VMSCAN_THROTTLE_NOPROGRESS 58 usec_timeout=500000 usect_delayed=120000 reason=VMSCAN_THROTTLE_NOPROGRESS 59 usec_timeout=500000 usect_delayed=208000 reason=VMSCAN_THROTTLE_NOPROGRESS 61 usec_timeout=500000 usect_delayed=68000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=192000 reason=VMSCAN_THROTTLE_NOPROGRESS 71 usec_timeout=500000 usect_delayed=480000 reason=VMSCAN_THROTTLE_NOPROGRESS 79 usec_timeout=500000 usect_delayed=60000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=320000 reason=VMSCAN_THROTTLE_NOPROGRESS 82 usec_timeout=500000 usect_delayed=92000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=64000 reason=VMSCAN_THROTTLE_NOPROGRESS 85 usec_timeout=500000 usect_delayed=80000 reason=VMSCAN_THROTTLE_NOPROGRESS 88 usec_timeout=500000 usect_delayed=84000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=160000 reason=VMSCAN_THROTTLE_NOPROGRESS 90 usec_timeout=500000 usect_delayed=292000 reason=VMSCAN_THROTTLE_NOPROGRESS 94 usec_timeout=500000 usect_delayed=56000 reason=VMSCAN_THROTTLE_NOPROGRESS 118 usec_timeout=500000 usect_delayed=88000 reason=VMSCAN_THROTTLE_NOPROGRESS 119 usec_timeout=500000 usect_delayed=72000 reason=VMSCAN_THROTTLE_NOPROGRESS 126 usec_timeout=500000 usect_delayed=108000 reason=VMSCAN_THROTTLE_NOPROGRESS 146 usec_timeout=500000 usect_delayed=52000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=36000 reason=VMSCAN_THROTTLE_NOPROGRESS 148 usec_timeout=500000 usect_delayed=48000 reason=VMSCAN_THROTTLE_NOPROGRESS 159 usec_timeout=500000 usect_delayed=28000 reason=VMSCAN_THROTTLE_NOPROGRESS 178 usec_timeout=500000 usect_delayed=44000 reason=VMSCAN_THROTTLE_NOPROGRESS 183 usec_timeout=500000 usect_delayed=40000 reason=VMSCAN_THROTTLE_NOPROGRESS 237 usec_timeout=500000 usect_delayed=100000 reason=VMSCAN_THROTTLE_NOPROGRESS 266 usec_timeout=500000 usect_delayed=32000 reason=VMSCAN_THROTTLE_NOPROGRESS 313 usec_timeout=500000 usect_delayed=24000 reason=VMSCAN_THROTTLE_NOPROGRESS 347 usec_timeout=500000 usect_delayed=96000 reason=VMSCAN_THROTTLE_NOPROGRESS 470 usec_timeout=500000 usect_delayed=20000 reason=VMSCAN_THROTTLE_NOPROGRESS 559 usec_timeout=500000 usect_delayed=16000 reason=VMSCAN_THROTTLE_NOPROGRESS 964 usec_timeout=500000 usect_delayed=12000 reason=VMSCAN_THROTTLE_NOPROGRESS 2001 usec_timeout=500000 usect_delayed=104000 reason=VMSCAN_THROTTLE_NOPROGRESS 2447 usec_timeout=500000 usect_delayed=8000 reason=VMSCAN_THROTTLE_NOPROGRESS 7888 usec_timeout=500000 usect_delayed=4000 reason=VMSCAN_THROTTLE_NOPROGRESS 22727 usec_timeout=500000 usect_delayed=0 reason=VMSCAN_THROTTLE_NOPROGRESS 51305 usec_timeout=500000 usect_delayed=500000 reason=VMSCAN_THROTTLE_NOPROGRESS The full timeout is often hit but a large number also do not stall at all. The remainder slept a little allowing other reclaim tasks to make progress. While this timeout could be further increased, it could also negatively impact worst-case behaviour when there is no prioritisation of what task should make progress. For VMSCAN_THROTTLE_WRITEBACK, the breakdown was 1 usec_timeout=100000 usect_delayed=44000 reason=VMSCAN_THROTTLE_WRITEBACK 2 usec_timeout=100000 usect_delayed=76000 reason=VMSCAN_THROTTLE_WRITEBACK 3 usec_timeout=100000 usect_delayed=80000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=48000 reason=VMSCAN_THROTTLE_WRITEBACK 5 usec_timeout=100000 usect_delayed=84000 reason=VMSCAN_THROTTLE_WRITEBACK 6 usec_timeout=100000 usect_delayed=72000 reason=VMSCAN_THROTTLE_WRITEBACK 7 usec_timeout=100000 usect_delayed=88000 reason=VMSCAN_THROTTLE_WRITEBACK 11 usec_timeout=100000 usect_delayed=56000 reason=VMSCAN_THROTTLE_WRITEBACK 12 usec_timeout=100000 usect_delayed=64000 reason=VMSCAN_THROTTLE_WRITEBACK 16 usec_timeout=100000 usect_delayed=92000 reason=VMSCAN_THROTTLE_WRITEBACK 24 usec_timeout=100000 usect_delayed=68000 reason=VMSCAN_THROTTLE_WRITEBACK 28 usec_timeout=100000 usect_delayed=32000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=60000 reason=VMSCAN_THROTTLE_WRITEBACK 30 usec_timeout=100000 usect_delayed=96000 reason=VMSCAN_THROTTLE_WRITEBACK 32 usec_timeout=100000 usect_delayed=52000 reason=VMSCAN_THROTTLE_WRITEBACK 42 usec_timeout=100000 usect_delayed=40000 reason=VMSCAN_THROTTLE_WRITEBACK 77 usec_timeout=100000 usect_delayed=28000 reason=VMSCAN_THROTTLE_WRITEBACK 99 usec_timeout=100000 usect_delayed=36000 reason=VMSCAN_THROTTLE_WRITEBACK 137 usec_timeout=100000 usect_delayed=24000 reason=VMSCAN_THROTTLE_WRITEBACK 190 usec_timeout=100000 usect_delayed=20000 reason=VMSCAN_THROTTLE_WRITEBACK 339 usec_timeout=100000 usect_delayed=16000 reason=VMSCAN_THROTTLE_WRITEBACK 518 usec_timeout=100000 usect_delayed=12000 reason=VMSCAN_THROTTLE_WRITEBACK 852 usec_timeout=100000 usect_delayed=8000 reason=VMSCAN_THROTTLE_WRITEBACK 3359 usec_timeout=100000 usect_delayed=4000 reason=VMSCAN_THROTTLE_WRITEBACK 7147 usec_timeout=100000 usect_delayed=0 reason=VMSCAN_THROTTLE_WRITEBACK 83962 usec_timeout=100000 usect_delayed=100000 reason=VMSCAN_THROTTLE_WRITEBACK The majority hit the timeout in direct reclaim context although a sizable number did not stall at all. This is very different to kswapd where only a tiny percentage of stalls due to writeback reached the timeout. Bottom line, the throttling appears to work and the wakeup events may limit worst case stalls. There might be some grounds for adjusting timeouts but it's likely futile as the worst-case scenarios depend on the workload, memory size and the speed of the storage. A better approach to improve the series further would be to prioritise tasks based on their rate of allocation with the caveat that it may be very expensive to track. This patch (of 5): Page reclaim throttles on wait_iff_congested under the following conditions: - kswapd is encountering pages under writeback and marked for immediate reclaim implying that pages are cycling through the LRU faster than pages can be cleaned. - Direct reclaim will stall if all dirty pages are backed by congested inodes. wait_iff_congested is almost completely broken with few exceptions. This patch adds a new node-based workqueue and tracks the number of throttled tasks and pages written back since throttling started. If enough pages belonging to the node are written back then the throttled tasks will wake early. If not, the throttled tasks sleeps until the timeout expires. [neilb@suse.de: Uninterruptible sleep and simpler wakeups] [hdanton@sina.com: Avoid race when reclaim starts] [vbabka@suse.cz: vmstat irq-safe api, clarifications] Link: https://lore.kernel.org/linux-mm/45d8b7a6-8548-65f5-cccf-9f451d4ae3d4@kernel.dk/ [1] Link: https://lkml.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lkml.kernel.org/r/20211022144651.19914-2-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: NeilBrown Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Matthew Wilcox Cc: Michal Hocko Cc: Dave Chinner Cc: Rik van Riel Cc: Johannes Weiner Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/backing-dev.h | 1 - include/linux/mmzone.h | 13 +++++++ include/trace/events/vmscan.h | 34 +++++++++++++++++ include/trace/events/writeback.h | 7 ---- mm/backing-dev.c | 48 ----------------------- mm/filemap.c | 1 + mm/internal.h | 11 ++++++ mm/page_alloc.c | 5 +++ mm/vmscan.c | 82 ++++++++++++++++++++++++++++++++++------ mm/vmstat.c | 1 + 10 files changed, 135 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index ac7f231b8825..9fb1f0ae273c 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -154,7 +154,6 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) } long congestion_wait(int sync, long timeout); -long wait_iff_congested(int sync, long timeout); static inline bool mapping_can_writeback(struct address_space *mapping) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index fb36a29e3aae..5a5e19b90dab 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -199,6 +199,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_THROTTLED_WRITTEN, /* NR_WRITTEN while reclaim throttled */ NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_FOLL_PIN_ACQUIRED, /* via: pin_user_page(), gup flag: FOLL_PIN */ NR_FOLL_PIN_RELEASED, /* pages returned via unpin_user_page() */ @@ -272,6 +273,11 @@ enum lru_list { NR_LRU_LISTS }; +enum vmscan_throttle_state { + VMSCAN_THROTTLE_WRITEBACK, + NR_VMSCAN_THROTTLE, +}; + #define for_each_lru(lru) for (lru = 0; lru < NR_LRU_LISTS; lru++) #define for_each_evictable_lru(lru) for (lru = 0; lru <= LRU_ACTIVE_FILE; lru++) @@ -841,6 +847,13 @@ typedef struct pglist_data { int node_id; wait_queue_head_t kswapd_wait; wait_queue_head_t pfmemalloc_wait; + + /* workqueues for throttling reclaim for different reasons. */ + wait_queue_head_t reclaim_wait[NR_VMSCAN_THROTTLE]; + + atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */ + unsigned long nr_reclaim_start; /* nr pages written while throttled + * when throttling started. */ struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ int kswapd_order; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index 88faf2400ec2..c317f9fe0d17 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -27,6 +27,14 @@ {RECLAIM_WB_ASYNC, "RECLAIM_WB_ASYNC"} \ ) : "RECLAIM_WB_NONE" +#define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) + +#define show_throttle_flags(flags) \ + (flags) ? __print_flags(flags, "|", \ + {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"} \ + ) : "VMSCAN_THROTTLE_NONE" + + #define trace_reclaim_flags(file) ( \ (file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \ (RECLAIM_WB_ASYNC) \ @@ -454,6 +462,32 @@ DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_node_reclaim_end, TP_ARGS(nr_reclaimed) ); +TRACE_EVENT(mm_vmscan_throttled, + + TP_PROTO(int nid, int usec_timeout, int usec_delayed, int reason), + + TP_ARGS(nid, usec_timeout, usec_delayed, reason), + + TP_STRUCT__entry( + __field(int, nid) + __field(int, usec_timeout) + __field(int, usec_delayed) + __field(int, reason) + ), + + TP_fast_assign( + __entry->nid = nid; + __entry->usec_timeout = usec_timeout; + __entry->usec_delayed = usec_delayed; + __entry->reason = 1U << reason; + ), + + TP_printk("nid=%d usec_timeout=%d usect_delayed=%d reason=%s", + __entry->nid, + __entry->usec_timeout, + __entry->usec_delayed, + show_throttle_flags(__entry->reason)) +); #endif /* _TRACE_VMSCAN_H */ /* This part must be outside protection */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 840d1ba84cf5..3bc759b81897 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -763,13 +763,6 @@ DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait, TP_ARGS(usec_timeout, usec_delayed) ); -DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested, - - TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed), - - TP_ARGS(usec_timeout, usec_delayed) -); - DECLARE_EVENT_CLASS(writeback_single_inode_template, TP_PROTO(struct inode *inode, diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 5ccb25089808..3d2983752e24 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -1038,51 +1038,3 @@ long congestion_wait(int sync, long timeout) return ret; } EXPORT_SYMBOL(congestion_wait); - -/** - * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes - * @sync: SYNC or ASYNC IO - * @timeout: timeout in jiffies - * - * In the event of a congested backing_dev (any backing_dev) this waits - * for up to @timeout jiffies for either a BDI to exit congestion of the - * given @sync queue or a write to complete. - * - * The return value is 0 if the sleep is for the full timeout. Otherwise, - * it is the number of jiffies that were still remaining when the function - * returned. return_value == timeout implies the function did not sleep. - */ -long wait_iff_congested(int sync, long timeout) -{ - long ret; - unsigned long start = jiffies; - DEFINE_WAIT(wait); - wait_queue_head_t *wqh = &congestion_wqh[sync]; - - /* - * If there is no congestion, yield if necessary instead - * of sleeping on the congestion queue - */ - if (atomic_read(&nr_wb_congested[sync]) == 0) { - cond_resched(); - - /* In case we scheduled, work out time remaining */ - ret = timeout - (jiffies - start); - if (ret < 0) - ret = 0; - - goto out; - } - - /* Sleep until uncongested or a write happens */ - prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); - ret = io_schedule_timeout(timeout); - finish_wait(wqh, &wait); - -out: - trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout), - jiffies_to_usecs(jiffies - start)); - - return ret; -} -EXPORT_SYMBOL(wait_iff_congested); diff --git a/mm/filemap.c b/mm/filemap.c index 6f2c4bd6a571..b6140debc2da 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1612,6 +1612,7 @@ void end_page_writeback(struct page *page) smp_mb__after_atomic(); wake_up_page(page, PG_writeback); + acct_reclaim_writeback(page); put_page(page); } EXPORT_SYMBOL(end_page_writeback); diff --git a/mm/internal.h b/mm/internal.h index 6c3e1a9f8c5a..a59b5626f968 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -34,6 +34,17 @@ void page_writeback_init(void); +void __acct_reclaim_writeback(pg_data_t *pgdat, struct page *page, + int nr_throttled); +static inline void acct_reclaim_writeback(struct page *page) +{ + pg_data_t *pgdat = page_pgdat(page); + int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); + + if (nr_throttled) + __acct_reclaim_writeback(pgdat, page, nr_throttled); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 09a0f1c5d5d2..0f1f1f353211 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7408,6 +7408,8 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat) {} static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { + int i; + pgdat_resize_init(pgdat); pgdat_init_split_queue(pgdat); @@ -7416,6 +7418,9 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); + for (i = 0; i < NR_VMSCAN_THROTTLE; i++) + init_waitqueue_head(&pgdat->reclaim_wait[i]); + pgdat_page_ext_init(pgdat); lruvec_init(&pgdat->__lruvec); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 9483dd6af550..09beeb55546c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,6 +1006,64 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +static void +reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, + long timeout) +{ + wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; + long ret; + DEFINE_WAIT(wait); + + /* + * Do not throttle IO workers, kthreads other than kswapd or + * workqueues. They may be required for reclaim to make + * forward progress (e.g. journalling workqueues or kthreads). + */ + if (!current_is_kswapd() && + current->flags & (PF_IO_WORKER|PF_KTHREAD)) + return; + + if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + WRITE_ONCE(pgdat->nr_reclaim_start, + node_page_state(pgdat, NR_THROTTLED_WRITTEN)); + } + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = schedule_timeout(timeout); + finish_wait(wqh, &wait); + atomic_dec(&pgdat->nr_writeback_throttled); + + trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), + jiffies_to_usecs(timeout - ret), + reason); +} + +/* + * Account for pages written if tasks are throttled waiting on dirty + * pages to clean. If enough pages have been cleaned since throttling + * started then wakeup the throttled tasks. + */ +void __acct_reclaim_writeback(pg_data_t *pgdat, struct page *page, + int nr_throttled) +{ + unsigned long nr_written; + + inc_node_page_state(page, NR_THROTTLED_WRITTEN); + + /* + * This is an inaccurate read as the per-cpu deltas may not + * be synchronised. However, given that the system is + * writeback throttled, it is not worth taking the penalty + * of getting an accurate count. At worst, the throttle + * timeout guarantees forward progress. + */ + nr_written = node_page_state(pgdat, NR_THROTTLED_WRITTEN) - + READ_ONCE(pgdat->nr_reclaim_start); + + if (nr_written > SWAP_CLUSTER_MAX * nr_throttled) + wake_up(&pgdat->reclaim_wait[VMSCAN_THROTTLE_WRITEBACK]); +} + /* possible outcome of pageout() */ typedef enum { /* failed to write page out, page is locked */ @@ -1411,9 +1469,8 @@ retry: /* * The number of dirty pages determines if a node is marked - * reclaim_congested which affects wait_iff_congested. kswapd - * will stall and start writing pages if the tail of the LRU - * is all dirty unqueued pages. + * reclaim_congested. kswapd will stall and start writing + * pages if the tail of the LRU is all dirty unqueued pages. */ page_check_dirty_writeback(page, &dirty, &writeback); if (dirty || writeback) @@ -3179,19 +3236,19 @@ again: * If kswapd scans pages marked for immediate * reclaim and under writeback (nr_immediate), it * implies that pages are cycling through the LRU - * faster than they are written so also forcibly stall. + * faster than they are written so forcibly stall + * until some pages complete writeback. */ if (sc->nr.immediate) - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); } /* - * Tag a node/memcg as congested if all the dirty pages - * scanned were backed by a congested BDI and - * wait_iff_congested will stall. + * Tag a node/memcg as congested if all the dirty pages were marked + * for writeback and immediate reclaim (counted in nr.congested). * * Legacy memcg will stall in page writeback so avoid forcibly - * stalling in wait_iff_congested(). + * stalling in reclaim_throttle(). */ if ((current_is_kswapd() || (cgroup_reclaim(sc) && writeback_throttling_sane(sc))) && @@ -3199,15 +3256,15 @@ again: set_bit(LRUVEC_CONGESTED, &target_lruvec->flags); /* - * Stall direct reclaim for IO completions if underlying BDIs - * and node is congested. Allow kswapd to continue until it + * Stall direct reclaim for IO completions if the lruvec is + * node is congested. Allow kswapd to continue until it * starts encountering unqueued dirty pages or cycling through * the LRU too quickly. */ if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - wait_iff_congested(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK, HZ/10); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -4285,6 +4342,7 @@ static int kswapd(void *p) WRITE_ONCE(pgdat->kswapd_order, 0); WRITE_ONCE(pgdat->kswapd_highest_zoneidx, MAX_NR_ZONES); + atomic_set(&pgdat->nr_writeback_throttled, 0); for ( ; ; ) { bool ret; diff --git a/mm/vmstat.c b/mm/vmstat.c index ae87c90e0b4e..0f4643e5324d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1225,6 +1225,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", + "nr_throttled_written", "nr_kernel_misc_reclaimable", "nr_foll_pin_acquired", "nr_foll_pin_released", -- cgit v1.2.3 From d818fca1cac31b1fc9301bda83e195a46fb4ebaa Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:29 -0700 Subject: mm/vmscan: throttle reclaim and compaction when too may pages are isolated Page reclaim throttles on congestion if too many parallel reclaim instances have isolated too many pages. This makes no sense, excessive parallelisation has nothing to do with writeback or congestion. This patch creates an additional workqueue to sleep on when too many pages are isolated. The throttled tasks are woken when the number of isolated pages is reduced or a timeout occurs. There may be some false positive wakeups for GFP_NOIO/GFP_NOFS callers but the tasks will throttle again if necessary. [shy828301@gmail.com: Wake up from compaction context] [vbabka@suse.cz: Account number of throttled tasks only for writeback] Link: https://lkml.kernel.org/r/20211022144651.19914-3-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/trace/events/vmscan.h | 4 +++- mm/compaction.c | 10 ++++++++-- mm/internal.h | 11 +++++++++++ mm/vmscan.c | 22 ++++++++++++++++------ 5 files changed, 39 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 5a5e19b90dab..312c1ea9aafa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -275,6 +275,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, + VMSCAN_THROTTLE_ISOLATED, NR_VMSCAN_THROTTLE, }; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index c317f9fe0d17..d4905bd9e9c4 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -28,10 +28,12 @@ ) : "RECLAIM_WB_NONE" #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) +#define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ - {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"} \ + {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ + {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/mm/compaction.c b/mm/compaction.c index bfc93da1c2c7..7359093d8ac0 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -761,6 +761,8 @@ isolate_freepages_range(struct compact_control *cc, /* Similar to reclaim, but different enough that they don't share logic */ static bool too_many_isolated(pg_data_t *pgdat) { + bool too_many; + unsigned long active, inactive, isolated; inactive = node_page_state(pgdat, NR_INACTIVE_FILE) + @@ -770,7 +772,11 @@ static bool too_many_isolated(pg_data_t *pgdat) isolated = node_page_state(pgdat, NR_ISOLATED_FILE) + node_page_state(pgdat, NR_ISOLATED_ANON); - return isolated > (inactive + active) / 2; + too_many = isolated > (inactive + active) / 2; + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /** @@ -822,7 +828,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, if (cc->mode == MIGRATE_ASYNC) return -EAGAIN; - congestion_wait(BLK_RW_ASYNC, HZ/10); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10); if (fatal_signal_pending(current)) return -EINTR; diff --git a/mm/internal.h b/mm/internal.h index a59b5626f968..7dfe74f827bf 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -45,6 +45,15 @@ static inline void acct_reclaim_writeback(struct page *page) __acct_reclaim_writeback(pgdat, page, nr_throttled); } +static inline void wake_throttle_isolated(pg_data_t *pgdat) +{ + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; + if (waitqueue_active(wqh)) + wake_up(wqh); +} + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, @@ -121,6 +130,8 @@ extern unsigned long highest_memmap_pfn; */ extern int isolate_lru_page(struct page *page); extern void putback_lru_page(struct page *page); +extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, + long timeout); /* * in mm/rmap.c: diff --git a/mm/vmscan.c b/mm/vmscan.c index 09beeb55546c..7bfd62f81e16 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1006,12 +1006,12 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } -static void -reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, +void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, long timeout) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; long ret; + bool acct_writeback = (reason == VMSCAN_THROTTLE_WRITEBACK); DEFINE_WAIT(wait); /* @@ -1023,7 +1023,8 @@ reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, current->flags & (PF_IO_WORKER|PF_KTHREAD)) return; - if (atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { + if (acct_writeback && + atomic_inc_return(&pgdat->nr_writeback_throttled) == 1) { WRITE_ONCE(pgdat->nr_reclaim_start, node_page_state(pgdat, NR_THROTTLED_WRITTEN)); } @@ -1031,7 +1032,9 @@ reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason, prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); ret = schedule_timeout(timeout); finish_wait(wqh, &wait); - atomic_dec(&pgdat->nr_writeback_throttled); + + if (acct_writeback) + atomic_dec(&pgdat->nr_writeback_throttled); trace_mm_vmscan_throttled(pgdat->node_id, jiffies_to_usecs(timeout), jiffies_to_usecs(timeout - ret), @@ -2175,6 +2178,7 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, struct scan_control *sc) { unsigned long inactive, isolated; + bool too_many; if (current_is_kswapd()) return 0; @@ -2198,7 +2202,13 @@ static int too_many_isolated(struct pglist_data *pgdat, int file, if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) inactive >>= 3; - return isolated > inactive; + too_many = isolated > inactive; + + /* Wake up tasks throttled due to too_many_isolated. */ + if (!too_many) + wake_throttle_isolated(pgdat); + + return too_many; } /* @@ -2307,8 +2317,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, return 0; /* wait a bit for the reclaimer. */ - msleep(100); stalled = true; + reclaim_throttle(pgdat, VMSCAN_THROTTLE_ISOLATED, HZ/10); /* We are about to die and free our memory. Return now. */ if (fatal_signal_pending(current)) -- cgit v1.2.3 From 69392a403f49e6e33f9dfb1d6edb87c8006f83c2 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 5 Nov 2021 13:42:32 -0700 Subject: mm/vmscan: throttle reclaim when no progress is being made Memcg reclaim throttles on congestion if no reclaim progress is made. This makes little sense, it might be due to writeback or a host of other factors. For !memcg reclaim, it's messy. Direct reclaim primarily is throttled in the page allocator if it is failing to make progress. Kswapd throttles if too many pages are under writeback and marked for immediate reclaim. This patch explicitly throttles if reclaim is failing to make progress. [vbabka@suse.cz: Remove redundant code] Link: https://lkml.kernel.org/r/20211022144651.19914-4-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Vlastimil Babka Cc: Andreas Dilger Cc: "Darrick J . Wong" Cc: Dave Chinner Cc: Johannes Weiner Cc: Jonathan Corbet Cc: Matthew Wilcox Cc: Michal Hocko Cc: NeilBrown Cc: Rik van Riel Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/trace/events/vmscan.h | 4 +++- mm/memcontrol.c | 10 +--------- mm/vmscan.c | 28 ++++++++++++++++++++++++++++ 4 files changed, 33 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 312c1ea9aafa..58e744b78c2c 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -276,6 +276,7 @@ enum lru_list { enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, + VMSCAN_THROTTLE_NOPROGRESS, NR_VMSCAN_THROTTLE, }; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index d4905bd9e9c4..f25a6149d3ba 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -29,11 +29,13 @@ #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) +#define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ - {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"} \ + {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ + {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cf0321d7a784..965b3cf7046b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3487,19 +3487,11 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) /* try to free all pages in this cgroup */ while (nr_retries && page_counter_read(&memcg->memory)) { - int progress; - if (signal_pending(current)) return -EINTR; - progress = try_to_free_mem_cgroup_pages(memcg, 1, - GFP_KERNEL, true); - if (!progress) { + if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true)) nr_retries--; - /* maybe some writeback is necessary */ - congestion_wait(BLK_RW_ASYNC, HZ/10); - } - } return 0; diff --git a/mm/vmscan.c b/mm/vmscan.c index 7bfd62f81e16..7d3fe5938e3b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3322,6 +3322,33 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) return zone_watermark_ok_safe(zone, 0, watermark, sc->reclaim_idx); } +static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) +{ + /* If reclaim is making progress, wake any throttled tasks. */ + if (sc->nr_reclaimed) { + wait_queue_head_t *wqh; + + wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_NOPROGRESS]; + if (waitqueue_active(wqh)) + wake_up(wqh); + + return; + } + + /* + * Do not throttle kswapd on NOPROGRESS as it will throttle on + * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under + * writeback and marked for immediate reclaim at the tail of + * the LRU. + */ + if (current_is_kswapd()) + return; + + /* Throttle if making no progress at high prioities. */ + if (sc->priority < DEF_PRIORITY - 2) + reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS, HZ/10); +} + /* * This is the direct reclaim path, for page-allocating processes. We only * try to reclaim pages from zones which will satisfy the caller's allocation @@ -3406,6 +3433,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); + consider_reclaim_throttle(zone->zone_pgdat, sc); } /* -- cgit v1.2.3 From 7e6ec49c18988f1b8dab0677271dafde5f8d9a43 Mon Sep 17 00:00:00 2001 From: Yuanzheng Song Date: Fri, 5 Nov 2021 13:42:52 -0700 Subject: mm/vmpressure: fix data-race with memcg->socket_pressure When reading memcg->socket_pressure in mem_cgroup_under_socket_pressure() and writing memcg->socket_pressure in vmpressure() at the same time, the following data-race occurs: BUG: KCSAN: data-race in __sk_mem_reduce_allocated / vmpressure write to 0xffff8881286f4938 of 8 bytes by task 24550 on cpu 3: vmpressure+0x218/0x230 mm/vmpressure.c:307 shrink_node_memcgs+0x2b9/0x410 mm/vmscan.c:2658 shrink_node+0x9d2/0x11d0 mm/vmscan.c:2769 shrink_zones+0x29f/0x470 mm/vmscan.c:2972 do_try_to_free_pages+0x193/0x6e0 mm/vmscan.c:3027 try_to_free_mem_cgroup_pages+0x1c0/0x3f0 mm/vmscan.c:3345 reclaim_high mm/memcontrol.c:2440 [inline] mem_cgroup_handle_over_high+0x18b/0x4d0 mm/memcontrol.c:2624 tracehook_notify_resume include/linux/tracehook.h:197 [inline] exit_to_user_mode_loop kernel/entry/common.c:164 [inline] exit_to_user_mode_prepare+0x110/0x170 kernel/entry/common.c:191 syscall_exit_to_user_mode+0x16/0x30 kernel/entry/common.c:266 ret_from_fork+0x15/0x30 arch/x86/entry/entry_64.S:289 read to 0xffff8881286f4938 of 8 bytes by interrupt on cpu 1: mem_cgroup_under_socket_pressure include/linux/memcontrol.h:1483 [inline] sk_under_memory_pressure include/net/sock.h:1314 [inline] __sk_mem_reduce_allocated+0x1d2/0x270 net/core/sock.c:2696 __sk_mem_reclaim+0x44/0x50 net/core/sock.c:2711 sk_mem_reclaim include/net/sock.h:1490 [inline] ...... net_rx_action+0x17a/0x480 net/core/dev.c:6864 __do_softirq+0x12c/0x2af kernel/softirq.c:298 run_ksoftirqd+0x13/0x20 kernel/softirq.c:653 smpboot_thread_fn+0x33f/0x510 kernel/smpboot.c:165 kthread+0x1fc/0x220 kernel/kthread.c:292 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:296 Fix it by using READ_ONCE() and WRITE_ONCE() to read and write memcg->socket_pressure. Link: https://lkml.kernel.org/r/20211025082843.671690-1-songyuanzheng@huawei.com Signed-off-by: Yuanzheng Song Reviewed-by: Muchun Song Cc: Shakeel Butt Cc: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Matthew Wilcox (Oracle) Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- mm/vmpressure.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index f207f98bdb76..9d96238d9c21 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1606,7 +1606,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { - if (time_before(jiffies, memcg->socket_pressure)) + if (time_before(jiffies, READ_ONCE(memcg->socket_pressure))) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 76518e4166dc..b52644771cc4 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -308,7 +308,7 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, * asserted for a second in which subsequent * pressure events can occur. */ - memcg->socket_pressure = jiffies + HZ; + WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } } } -- cgit v1.2.3 From fa27717110ae51b9b9013ced0b5143888257bb79 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:13 -0700 Subject: memblock: drop memblock_free_early_nid() and memblock_free_early() memblock_free_early_nid() is unused and memblock_free_early() is an alias for memblock_free(). Replace calls to memblock_free_early() with calls to memblock_free() and remove memblock_free_early() and memblock_free_early_nid(). Link: https://lkml.kernel.org/r/20210930185031.18648-4-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/init.c | 2 +- arch/powerpc/platforms/pseries/svm.c | 3 +-- arch/s390/kernel/smp.c | 2 +- drivers/base/arch_numa.c | 2 +- drivers/s390/char/sclp_early.c | 2 +- include/linux/memblock.h | 12 ------------ kernel/dma/swiotlb.c | 2 +- lib/cpumask.c | 2 +- mm/percpu.c | 8 ++++---- mm/sparse.c | 2 +- 10 files changed, 12 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 19347dc6bbf8..21a5a7ac0037 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index 87f001b4c4e4..f12229ce7301 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -56,8 +56,7 @@ void __init svm_swiotlb_init(void) return; - memblock_free_early(__pa(vstart), - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free(__pa(vstart), PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1a04e5bdf655..066efd6d9345 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -880,7 +880,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ __smp_rescan_cpus(info, true); - memblock_free_early((unsigned long)info, sizeof(*info)); + memblock_free((unsigned long)info, sizeof(*info)); } /* diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index a6491673dc1f..ade8934764f6 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -166,7 +166,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(__pa(ptr), size); } #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index f3d5c7f4c13d..f01d942e1c1d 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -139,7 +139,7 @@ int __init sclp_early_get_core_info(struct sclp_core_info *info) } sclp_fill_core_info(info, sccb); out: - memblock_free_early((unsigned long)sccb, length); + memblock_free((unsigned long)sccb, length); return rc; } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 34de69b3b8ba..fc8183be340c 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -441,18 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_early(phys_addr_t base, - phys_addr_t size) -{ - memblock_free(base, size); -} - -static inline void memblock_free_early_nid(phys_addr_t base, - phys_addr_t size, int nid) -{ - memblock_free(base, size); -} - static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) { __memblock_free_late(base, size); diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 87c40517e822..430d2f78d540 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_free_early(__pa(tlb), bytes); + memblock_free(__pa(tlb), bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/lib/cpumask.c b/lib/cpumask.c index c3c76b833384..045779446a18 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -188,7 +188,7 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - memblock_free_early(__pa(mask), cpumask_size()); + memblock_free(__pa(mask), cpumask_size()); } #endif diff --git a/mm/percpu.c b/mm/percpu.c index e0a986818903..f58318cb04c0 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_free_early(__pa(ai), ai->__ai_size); + memblock_free(__pa(ai), ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_free_early(__pa(areas), areas_size); + memblock_free(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_free_early(__pa(pages), pages_size); + memblock_free(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_free_early(__pa(ptr), size); + memblock_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/mm/sparse.c b/mm/sparse.c index 120bc8ea5293..55fea0c2f927 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_free_early(__pa(sparsemap_buf), size); + memblock_free(__pa(sparsemap_buf), size); } static void __init sparse_buffer_init(unsigned long size, int nid) -- cgit v1.2.3 From 621d973901cf9fa6c6e31b31bdd36c5c5f3c9c9e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:16 -0700 Subject: memblock: stop aliasing __memblock_free_late with memblock_free_late memblock_free_late() is a NOP wrapper for __memblock_free_late(), there is no point to keep this indirection. Drop the wrapper and rename __memblock_free_late() to memblock_free_late(). Link: https://lkml.kernel.org/r/20210930185031.18648-5-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 7 +------ mm/memblock.c | 8 ++++---- 2 files changed, 5 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index fc8183be340c..e25f964fdd60 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -133,7 +133,7 @@ void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags, struct memblock_type *type_b, phys_addr_t *out_start, phys_addr_t *out_end, int *out_nid); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); +void memblock_free_late(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, @@ -441,11 +441,6 @@ static inline void *memblock_alloc_node(phys_addr_t size, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } -static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - /* * Set the allocation direction to bottom-up or top-down. */ diff --git a/mm/memblock.c b/mm/memblock.c index 5096500b2647..849060013d3c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -366,14 +366,14 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + memblock_free_late(addr, size); } memblock_memory = NULL; @@ -1589,7 +1589,7 @@ void * __init memblock_alloc_try_nid( } /** - * __memblock_free_late - free pages directly to buddy allocator + * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * @@ -1597,7 +1597,7 @@ void * __init memblock_alloc_try_nid( * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ -void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; -- cgit v1.2.3 From 3ecc68349bbab6bff1d12cbc7951ca6019b2faf6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:19 -0700 Subject: memblock: rename memblock_free to memblock_phys_free Since memblock_free() operates on a physical range, make its name reflect it and rename it to memblock_phys_free(), so it will be a logical counterpart to memblock_phys_alloc(). The callers are updated with the below semantic patch: @@ expression addr; expression size; @@ - memblock_free(addr, size); + memblock_phys_free(addr, size); Link: https://lkml.kernel.org/r/20210930185031.18648-6-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_irongate.c | 3 ++- arch/arc/mm/init.c | 2 +- arch/arm/mach-hisi/platmcpm.c | 2 +- arch/arm/mm/init.c | 2 +- arch/arm64/mm/mmu.c | 4 ++-- arch/mips/mm/init.c | 2 +- arch/mips/sgi-ip30/ip30-setup.c | 6 +++--- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 ++-- arch/powerpc/kernel/paca.c | 8 ++++---- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- arch/powerpc/platforms/pseries/svm.c | 3 ++- arch/riscv/kernel/setup.c | 5 +++-- arch/s390/kernel/setup.c | 8 ++++---- arch/s390/kernel/smp.c | 4 ++-- arch/s390/kernel/uv.c | 2 +- arch/s390/mm/kasan_init.c | 2 +- arch/sh/boards/mach-ap325rxa/setup.c | 2 +- arch/sh/boards/mach-ecovec24/setup.c | 4 ++-- arch/sh/boards/mach-kfr2r09/setup.c | 2 +- arch/sh/boards/mach-migor/setup.c | 2 +- arch/sh/boards/mach-se/7724/setup.c | 4 ++-- arch/sparc/kernel/smp_64.c | 2 +- arch/um/kernel/mem.c | 2 +- arch/x86/kernel/setup.c | 4 ++-- arch/x86/mm/init.c | 2 +- arch/x86/xen/mmu_pv.c | 6 +++--- arch/x86/xen/setup.c | 6 +++--- drivers/base/arch_numa.c | 2 +- drivers/firmware/efi/memmap.c | 2 +- drivers/of/kexec.c | 3 +-- drivers/of/of_reserved_mem.c | 5 +++-- drivers/s390/char/sclp_early.c | 2 +- drivers/usb/early/xhci-dbc.c | 10 +++++----- drivers/xen/swiotlb-xen.c | 2 +- include/linux/memblock.h | 2 +- init/initramfs.c | 2 +- kernel/dma/swiotlb.c | 2 +- lib/cpumask.c | 2 +- mm/cma.c | 2 +- mm/memblock.c | 8 ++++---- mm/memory_hotplug.c | 2 +- mm/percpu.c | 8 ++++---- mm/sparse.c | 2 +- 45 files changed, 79 insertions(+), 76 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index 72af1e72d833..ee26dcc49418 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -233,7 +233,8 @@ albacore_init_arch(void) unsigned long size; size = initrd_end - initrd_start; - memblock_free(__pa(initrd_start), PAGE_ALIGN(size)); + memblock_phys_free(__pa(initrd_start), + PAGE_ALIGN(size)); if (!move_initrd(pci_mem)) printk("irongate_init_arch: initrd too big " "(%ldK)\ndisabling initrd\n", diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 699ecf119641..59408f6a02d4 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -173,7 +173,7 @@ static void __init highmem_init(void) #ifdef CONFIG_HIGHMEM unsigned long tmp; - memblock_free(high_mem_start, high_mem_sz); + memblock_phys_free(high_mem_start, high_mem_sz); for (tmp = min_high_pfn; tmp < max_high_pfn; tmp++) free_highmem_page(pfn_to_page(tmp)); #endif diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c index 96a484095194..258586e31333 100644 --- a/arch/arm/mach-hisi/platmcpm.c +++ b/arch/arm/mach-hisi/platmcpm.c @@ -339,7 +339,7 @@ err_fabric: err_sysctrl: iounmap(relocation); err_reloc: - memblock_free(hip04_boot_method[0], hip04_boot_method[1]); + memblock_phys_free(hip04_boot_method[0], hip04_boot_method[1]); err: return ret; } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 6162a070a410..6d0cb0f7bc54 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -158,7 +158,7 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align) panic("Failed to steal %pa bytes at %pS\n", &size, (void *)_RET_IP_); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); return phys; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index cfd9deb347c3..f68c2d953617 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -738,8 +738,8 @@ void __init paging_init(void) cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); init_mm.pgd = swapper_pg_dir; - memblock_free(__pa_symbol(init_pg_dir), - __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + memblock_phys_free(__pa_symbol(init_pg_dir), + __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); memblock_allow_resize(); } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 21a5a7ac0037..3be1c29084fa 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/arch/mips/sgi-ip30/ip30-setup.c b/arch/mips/sgi-ip30/ip30-setup.c index 44b1607e964d..75a34684e704 100644 --- a/arch/mips/sgi-ip30/ip30-setup.c +++ b/arch/mips/sgi-ip30/ip30-setup.c @@ -69,10 +69,10 @@ static void __init ip30_mem_init(void) total_mem += size; if (addr >= IP30_REAL_MEMORY_START) - memblock_free(addr, size); + memblock_phys_free(addr, size); else if ((addr + size) > IP30_REAL_MEMORY_START) - memblock_free(IP30_REAL_MEMORY_START, - size - IP30_MAX_PROM_MEMORY); + memblock_phys_free(IP30_REAL_MEMORY_START, + size - IP30_MAX_PROM_MEMORY); } pr_info("Detected %luMB of physical memory.\n", MEM_SHIFT(total_mem)); } diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 358aee7c2d79..42839d6bd486 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1095,8 +1095,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char cpufeatures_setup_finished(); - memblock_free(__pa(dt_cpu_features), - sizeof(struct dt_cpu_feature)*nr_dt_cpu_features); + memblock_phys_free(__pa(dt_cpu_features), + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); return 0; } diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 9bd30cac852b..4208b4044d12 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -322,8 +322,8 @@ void __init free_unused_pacas(void) new_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; if (new_ptrs_size < paca_ptrs_size) - memblock_free(__pa(paca_ptrs) + new_ptrs_size, - paca_ptrs_size - new_ptrs_size); + memblock_phys_free(__pa(paca_ptrs) + new_ptrs_size, + paca_ptrs_size - new_ptrs_size); paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = new_ptrs_size; @@ -331,8 +331,8 @@ void __init free_unused_pacas(void) #ifdef CONFIG_PPC_BOOK3S_64 if (early_radix_enabled()) { /* Ugly fixup, see new_slb_shadow() */ - memblock_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), - sizeof(struct slb_shadow)); + memblock_phys_free(__pa(paca_ptrs[boot_cpuid]->slb_shadow_ptr), + sizeof(struct slb_shadow)); paca_ptrs[boot_cpuid]->slb_shadow_ptr = NULL; } #endif diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index b1e43b69a559..5af8993a8e6d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -825,7 +825,7 @@ static void __init smp_setup_pacas(void) set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]); } - memblock_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); + memblock_phys_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); cpu_to_phys_id = NULL; } #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eaa79a0996d1..75bc294ac40d 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -812,7 +812,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 3dd35c327d1c..b5a9d343b720 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2981,7 +2981,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!phb->hose) { pr_err(" Can't allocate PCI controller for %pOF\n", np); - memblock_free(__pa(phb), sizeof(struct pnv_phb)); + memblock_phys_free(__pa(phb), sizeof(struct pnv_phb)); return; } diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index f12229ce7301..b7c017bb40f7 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -56,7 +56,8 @@ void __init svm_swiotlb_init(void) return; - memblock_free(__pa(vstart), PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_phys_free(__pa(vstart), + PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index b9620e5f00ba..6ea7c53b82cd 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -230,13 +230,14 @@ static void __init init_resources(void) /* Clean-up any unused pre-allocated resources */ if (res_idx >= 0) - memblock_free(__pa(mem_res), (res_idx + 1) * sizeof(*mem_res)); + memblock_phys_free(__pa(mem_res), + (res_idx + 1) * sizeof(*mem_res)); return; error: /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); - memblock_free(__pa(mem_res), mem_res_sz); + memblock_phys_free(__pa(mem_res), mem_res_sz); } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 67e5fff96ee0..7fc836e9e194 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -693,7 +693,7 @@ static void __init reserve_crashkernel(void) } if (register_memory_notifier(&kdump_mem_nb)) { - memblock_free(crash_base, crash_size); + memblock_phys_free(crash_base, crash_size); return; } @@ -748,7 +748,7 @@ static void __init free_mem_detect_info(void) get_mem_detect_reserved(&start, &size); if (size) - memblock_free(start, size); + memblock_phys_free(start, size); } static const char * __init get_mem_info_source(void) @@ -793,7 +793,7 @@ static void __init check_initrd(void) if (initrd_data.start && initrd_data.size && !memblock_is_region_memory(initrd_data.start, initrd_data.size)) { pr_err("The initial RAM disk does not fit into the memory\n"); - memblock_free(initrd_data.start, initrd_data.size); + memblock_phys_free(initrd_data.start, initrd_data.size); initrd_start = initrd_end = 0; } #endif @@ -890,7 +890,7 @@ static void __init setup_randomness(void) if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); - memblock_free((unsigned long) vmms, PAGE_SIZE); + memblock_phys_free((unsigned long)vmms, PAGE_SIZE); } /* diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 066efd6d9345..78a8ea6fd582 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -723,7 +723,7 @@ void __init smp_save_dump_cpus(void) /* Get the CPU registers */ smp_save_cpu_regs(sa, addr, is_boot_cpu, page); } - memblock_free(page, PAGE_SIZE); + memblock_phys_free(page, PAGE_SIZE); diag_amode31_ops.diag308_reset(); pcpu_set_smt(0); } @@ -880,7 +880,7 @@ void __init smp_detect_cpus(void) /* Add CPUs present at boot */ __smp_rescan_cpus(info, true); - memblock_free((unsigned long)info, sizeof(*info)); + memblock_phys_free((unsigned long)info, sizeof(*info)); } /* diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 5a656c7b7a67..d57457b16fe5 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -64,7 +64,7 @@ void __init setup_uv(void) } if (uv_init(uv_stor_base, uv_info.uv_base_stor_len)) { - memblock_free(uv_stor_base, uv_info.uv_base_stor_len); + memblock_phys_free(uv_stor_base, uv_info.uv_base_stor_len); goto fail; } diff --git a/arch/s390/mm/kasan_init.c b/arch/s390/mm/kasan_init.c index 3e4735168019..483b9dbe0970 100644 --- a/arch/s390/mm/kasan_init.c +++ b/arch/s390/mm/kasan_init.c @@ -399,5 +399,5 @@ void __init kasan_copy_shadow_mapping(void) void __init kasan_free_early_identity(void) { - memblock_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos); + memblock_phys_free(pgalloc_pos, pgalloc_freeable - pgalloc_pos); } diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c index bac8a058ebd7..c77b5f00a66a 100644 --- a/arch/sh/boards/mach-ap325rxa/setup.c +++ b/arch/sh/boards/mach-ap325rxa/setup.c @@ -560,7 +560,7 @@ static void __init ap325rxa_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu_dma_membase = phys; diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index bab91a99124e..2b22ce792147 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -1502,7 +1502,7 @@ static void __init ecovec_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU0 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu0_dma_membase = phys; @@ -1510,7 +1510,7 @@ static void __init ecovec_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU1 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu1_dma_membase = phys; } diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c index eeb5ce341efd..20f4db778ed6 100644 --- a/arch/sh/boards/mach-kfr2r09/setup.c +++ b/arch/sh/boards/mach-kfr2r09/setup.c @@ -633,7 +633,7 @@ static void __init kfr2r09_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu_dma_membase = phys; diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index 6703a2122c0d..f60061283c48 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -633,7 +633,7 @@ static void __init migor_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu_dma_membase = phys; diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index 8d6541ba0186..8bbf5a6aa423 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -966,7 +966,7 @@ static void __init ms7724se_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU0 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu0_dma_membase = phys; @@ -974,7 +974,7 @@ static void __init ms7724se_mv_mem_reserve(void) if (!phys) panic("Failed to allocate CEU1 memory\n"); - memblock_free(phys, size); + memblock_phys_free(phys, size); memblock_remove(phys, size); ceu1_dma_membase = phys; } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 0224d8f19ed6..2507549538df 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1567,7 +1567,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 8e636ce02949..d1710ebb44f4 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -47,7 +47,7 @@ void __init mem_init(void) */ brk_end = (unsigned long) UML_ROUND_UP(sbrk(0)); map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); - memblock_free(__pa(brk_end), uml_reserved - brk_end); + memblock_phys_free(__pa(brk_end), uml_reserved - brk_end); uml_reserved = brk_end; /* this will put all low memory onto the freelists */ diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 40ed44ead063..49b596db5631 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -322,7 +322,7 @@ static void __init reserve_initrd(void) relocate_initrd(); - memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); + memblock_phys_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else @@ -521,7 +521,7 @@ static void __init reserve_crashkernel(void) } if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) { - memblock_free(crash_base, crash_size); + memblock_phys_free(crash_base, crash_size); return; } diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 23a14d82e783..1895986842b9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -618,7 +618,7 @@ static void __init memory_map_top_down(unsigned long map_start, */ addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start, map_end); - memblock_free(addr, PMD_SIZE); + memblock_phys_free(addr, PMD_SIZE); real_end = addr + PMD_SIZE; /* step_size need to be small so pgt_buf from BRK could cover it */ diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 3359c23573c5..676d8d292f8a 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1025,7 +1025,7 @@ static void __init xen_free_ro_pages(unsigned long paddr, unsigned long size) for (; vaddr < vaddr_end; vaddr += PAGE_SIZE) make_lowmem_page_readwrite(vaddr); - memblock_free(paddr, size); + memblock_phys_free(paddr, size); } static void __init xen_cleanmfnmap_free_pgtbl(void *pgtbl, bool unpin) @@ -1151,7 +1151,7 @@ static void __init xen_pagetable_p2m_free(void) xen_cleanhighmap(addr, addr + size); size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_free(__pa(addr), size); + memblock_phys_free(__pa(addr), size); } else { xen_cleanmfnmap(addr); } @@ -1955,7 +1955,7 @@ void __init xen_relocate_p2m(void) pfn_end = p2m_pfn_end; } - memblock_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); + memblock_phys_free(PFN_PHYS(pfn), PAGE_SIZE * (pfn_end - pfn)); while (pfn < pfn_end) { if (pfn == p2m_pfn) { pfn = p2m_pfn_end; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8bfc10330107..f387fc7e5250 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -153,7 +153,7 @@ static void __init xen_del_extra_mem(unsigned long start_pfn, break; } } - memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); + memblock_phys_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } /* @@ -719,7 +719,7 @@ static void __init xen_reserve_xen_mfnlist(void) return; xen_relocate_p2m(); - memblock_free(start, size); + memblock_phys_free(start, size); } /** @@ -885,7 +885,7 @@ char * __init xen_memory_setup(void) xen_phys_memcpy(new_area, start, size); pr_info("initrd moved from [mem %#010llx-%#010llx] to [mem %#010llx-%#010llx]\n", start, start + size, new_area, new_area + size); - memblock_free(start, size); + memblock_phys_free(start, size); boot_params.hdr.ramdisk_image = new_area; boot_params.ext_ramdisk_image = new_area >> 32; } diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index ade8934764f6..712edef03929 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -166,7 +166,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 2ff1883dc788..4df55a55da84 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -35,7 +35,7 @@ void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags) if (slab_is_available()) memblock_free_late(phys, size); else - memblock_free(phys, size); + memblock_phys_free(phys, size); } else if (flags & EFI_MEMMAP_SLAB) { struct page *p = pfn_to_page(PHYS_PFN(phys)); unsigned int order = get_order(size); diff --git a/drivers/of/kexec.c b/drivers/of/kexec.c index 053e241f593c..b9bd1cff1793 100644 --- a/drivers/of/kexec.c +++ b/drivers/of/kexec.c @@ -171,8 +171,7 @@ int ima_free_kexec_buffer(void) if (ret) return ret; - return memblock_free(addr, size); - + return memblock_phys_free(addr, size); } /** diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 9da8835ba5a5..9c0fb962c22b 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -46,7 +46,7 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, if (nomap) { err = memblock_mark_nomap(base, size); if (err) - memblock_free(base, size); + memblock_phys_free(base, size); kmemleak_ignore_phys(base); } @@ -284,7 +284,8 @@ void __init fdt_init_reserved_mem(void) if (nomap) memblock_clear_nomap(rmem->base, rmem->size); else - memblock_free(rmem->base, rmem->size); + memblock_phys_free(rmem->base, + rmem->size); } } } diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c index f01d942e1c1d..c0052655fc4f 100644 --- a/drivers/s390/char/sclp_early.c +++ b/drivers/s390/char/sclp_early.c @@ -139,7 +139,7 @@ int __init sclp_early_get_core_info(struct sclp_core_info *info) } sclp_fill_core_info(info, sccb); out: - memblock_free((unsigned long)sccb, length); + memblock_phys_free((unsigned long)sccb, length); return rc; } diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index be4ecbabdd58..933d77ad0a64 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -185,7 +185,7 @@ static void __init xdbc_free_ring(struct xdbc_ring *ring) if (!seg) return; - memblock_free(seg->dma, PAGE_SIZE); + memblock_phys_free(seg->dma, PAGE_SIZE); ring->segment = NULL; } @@ -665,10 +665,10 @@ int __init early_xdbc_setup_hardware(void) xdbc_free_ring(&xdbc.in_ring); if (xdbc.table_dma) - memblock_free(xdbc.table_dma, PAGE_SIZE); + memblock_phys_free(xdbc.table_dma, PAGE_SIZE); if (xdbc.out_dma) - memblock_free(xdbc.out_dma, PAGE_SIZE); + memblock_phys_free(xdbc.out_dma, PAGE_SIZE); xdbc.table_base = NULL; xdbc.out_buf = NULL; @@ -987,8 +987,8 @@ free_and_quit: xdbc_free_ring(&xdbc.evt_ring); xdbc_free_ring(&xdbc.out_ring); xdbc_free_ring(&xdbc.in_ring); - memblock_free(xdbc.table_dma, PAGE_SIZE); - memblock_free(xdbc.out_dma, PAGE_SIZE); + memblock_phys_free(xdbc.table_dma, PAGE_SIZE); + memblock_phys_free(xdbc.out_dma, PAGE_SIZE); writel(0, &xdbc.xdbc_reg->control); early_iounmap(xdbc.xhci_base, xdbc.xhci_length); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index e56a5faac395..4b671cc0a7ea 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -241,7 +241,7 @@ retry: */ rc = xen_swiotlb_fixup(start, nslabs); if (rc) { - memblock_free(__pa(start), PAGE_ALIGN(bytes)); + memblock_phys_free(__pa(start), PAGE_ALIGN(bytes)); if (nslabs > 1024 && repeat--) { /* Min is 2MB */ nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e25f964fdd60..d32d41709513 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -103,7 +103,7 @@ void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); -int memblock_free(phys_addr_t base, phys_addr_t size); +int memblock_phys_free(phys_addr_t base, phys_addr_t size); int memblock_reserve(phys_addr_t base, phys_addr_t size); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP int memblock_physmem_add(phys_addr_t base, phys_addr_t size); diff --git a/init/initramfs.c b/init/initramfs.c index a842c0544745..1a971f070dd4 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -607,7 +607,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); - memblock_free(__pa(aligned_start), aligned_end - aligned_start); + memblock_phys_free(__pa(aligned_start), aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 430d2f78d540..b9fa173e5e56 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_free(__pa(tlb), bytes); + memblock_phys_free(__pa(tlb), bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/lib/cpumask.c b/lib/cpumask.c index 045779446a18..a90786b77c1c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -188,7 +188,7 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - memblock_free(__pa(mask), cpumask_size()); + memblock_phys_free(__pa(mask), cpumask_size()); } #endif diff --git a/mm/cma.c b/mm/cma.c index 11152c3fb23c..bc9ca8f3c487 100644 --- a/mm/cma.c +++ b/mm/cma.c @@ -378,7 +378,7 @@ int __init cma_declare_contiguous_nid(phys_addr_t base, return 0; free_mem: - memblock_free(base, size); + memblock_phys_free(base, size); err: pr_err("Failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); return ret; diff --git a/mm/memblock.c b/mm/memblock.c index 849060013d3c..52e34abc4abe 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -806,18 +806,18 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) void __init_memblock memblock_free_ptr(void *ptr, size_t size) { if (ptr) - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } /** - * memblock_free - free boot memory block + * memblock_phys_free - free boot memory block * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ -int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; @@ -1937,7 +1937,7 @@ static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) * memmap array. */ if (pg < pgend) - memblock_free(pg, pgend - pg); + memblock_phys_free(pg, pgend - pg); } /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9fd0be32a281..feffaa9423fe 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -2204,7 +2204,7 @@ static int __ref try_remove_memory(u64 start, u64 size) arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - memblock_free(start, size); + memblock_phys_free(start, size); memblock_remove(start, size); } diff --git a/mm/percpu.c b/mm/percpu.c index f58318cb04c0..d65ddf6f2a35 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_free(__pa(ai), ai->__ai_size); + memblock_phys_free(__pa(ai), ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_free(__pa(areas), areas_size); + memblock_phys_free(__pa(areas), areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_free(__pa(pages), pages_size); + memblock_phys_free(__pa(pages), pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_free(__pa(ptr), size); + memblock_phys_free(__pa(ptr), size); } void __init setup_per_cpu_areas(void) diff --git a/mm/sparse.c b/mm/sparse.c index 55fea0c2f927..fc3ab8d3b6bc 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_free(__pa(sparsemap_buf), size); + memblock_phys_free(__pa(sparsemap_buf), size); } static void __init sparse_buffer_init(unsigned long size, int nid) -- cgit v1.2.3 From 4421cca0a3e4833b3bf0f20de98eb580ab8c7290 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:22 -0700 Subject: memblock: use memblock_free for freeing virtual pointers Rename memblock_free_ptr() to memblock_free() and use memblock_free() when freeing a virtual pointer so that memblock_free() will be a counterpart of memblock_alloc() The callers are updated with the below semantic patch and manual addition of (void *) casting to pointers that are represented by unsigned long variables. @@ identifier vaddr; expression size; @@ ( - memblock_phys_free(__pa(vaddr), size); + memblock_free(vaddr, size); | - memblock_free_ptr(vaddr, size); + memblock_free(vaddr, size); ) [sfr@canb.auug.org.au: fixup] Link: https://lkml.kernel.org/r/20211018192940.3d1d532f@canb.auug.org.au Link: https://lkml.kernel.org/r/20210930185031.18648-7-rppt@kernel.org Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_irongate.c | 3 +-- arch/mips/mm/init.c | 2 +- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 ++-- arch/powerpc/kernel/setup-common.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 2 +- arch/powerpc/platforms/pseries/svm.c | 3 +-- arch/riscv/kernel/setup.c | 5 ++--- arch/sparc/kernel/smp_64.c | 2 +- arch/um/kernel/mem.c | 2 +- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 4 ++-- arch/x86/mm/numa.c | 2 +- arch/x86/mm/numa_emulation.c | 2 +- arch/x86/xen/mmu_pv.c | 2 +- arch/x86/xen/p2m.c | 2 +- drivers/base/arch_numa.c | 4 ++-- drivers/macintosh/smu.c | 2 +- drivers/xen/swiotlb-xen.c | 2 +- include/linux/memblock.h | 2 +- init/initramfs.c | 2 +- init/main.c | 4 ++-- kernel/dma/swiotlb.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/bootconfig.c | 2 +- lib/cpumask.c | 2 +- mm/memblock.c | 6 +++--- mm/percpu.c | 8 ++++---- mm/sparse.c | 2 +- 29 files changed, 40 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index ee26dcc49418..6b8ed12936b6 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -233,8 +233,7 @@ albacore_init_arch(void) unsigned long size; size = initrd_end - initrd_start; - memblock_phys_free(__pa(initrd_start), - PAGE_ALIGN(size)); + memblock_free((void *)initrd_start, PAGE_ALIGN(size)); if (!move_initrd(pci_mem)) printk("irongate_init_arch: initrd too big " "(%ldK)\ndisabling initrd\n", diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 3be1c29084fa..325e1552cbea 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -529,7 +529,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } void __init setup_per_cpu_areas(void) diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index 42839d6bd486..ba527fb52993 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1095,8 +1095,8 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char cpufeatures_setup_finished(); - memblock_phys_free(__pa(dt_cpu_features), - sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); + memblock_free(dt_cpu_features, + sizeof(struct dt_cpu_feature) * nr_dt_cpu_features); return 0; } diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 5af8993a8e6d..6b1338db8779 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -825,7 +825,7 @@ static void __init smp_setup_pacas(void) set_hard_smp_processor_id(cpu, cpu_to_phys_id[cpu]); } - memblock_phys_free(__pa(cpu_to_phys_id), nr_cpu_ids * sizeof(u32)); + memblock_free(cpu_to_phys_id, nr_cpu_ids * sizeof(u32)); cpu_to_phys_id = NULL; } #endif diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 75bc294ac40d..1777e992b20b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -812,7 +812,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index b5a9d343b720..004cd6a96c8a 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2981,7 +2981,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, if (!phb->hose) { pr_err(" Can't allocate PCI controller for %pOF\n", np); - memblock_phys_free(__pa(phb), sizeof(struct pnv_phb)); + memblock_free(phb, sizeof(struct pnv_phb)); return; } diff --git a/arch/powerpc/platforms/pseries/svm.c b/arch/powerpc/platforms/pseries/svm.c index b7c017bb40f7..6332365d2891 100644 --- a/arch/powerpc/platforms/pseries/svm.c +++ b/arch/powerpc/platforms/pseries/svm.c @@ -56,8 +56,7 @@ void __init svm_swiotlb_init(void) return; - memblock_phys_free(__pa(vstart), - PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); + memblock_free(vstart, PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT)); panic("SVM: Cannot allocate SWIOTLB buffer"); } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 6ea7c53b82cd..b42bfdc67482 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -230,14 +230,13 @@ static void __init init_resources(void) /* Clean-up any unused pre-allocated resources */ if (res_idx >= 0) - memblock_phys_free(__pa(mem_res), - (res_idx + 1) * sizeof(*mem_res)); + memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res)); return; error: /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); - memblock_phys_free(__pa(mem_res), mem_res_sz); + memblock_free(mem_res, mem_res_sz); } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 2507549538df..b98a7bbe6728 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1567,7 +1567,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index d1710ebb44f4..0039771eb01c 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -47,7 +47,7 @@ void __init mem_init(void) */ brk_end = (unsigned long) UML_ROUND_UP(sbrk(0)); map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); - memblock_phys_free(__pa(brk_end), uml_reserved - brk_end); + memblock_free((void *)brk_end, uml_reserved - brk_end); uml_reserved = brk_end; /* this will put all low memory onto the freelists */ diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 5afd98559193..7b65275544b2 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -135,7 +135,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_free_ptr(ptr, size); + memblock_free(ptr, size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index ef885370719a..e7b9b464a82f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -49,7 +49,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; - memblock_free_ptr(p, PMD_SIZE); + memblock_free(p, PMD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); @@ -85,7 +85,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; - memblock_free_ptr(p, PUD_SIZE); + memblock_free(p, PUD_SIZE); } p = early_alloc(PAGE_SIZE, nid, true); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1e9b93b088db..c6b1213086d6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -355,7 +355,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_free_ptr(numa_distance, size); + memblock_free(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index e801e30089c4..1a02b791d273 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -517,7 +517,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) } /* free the copied physical distance table */ - memblock_free_ptr(phys_dist, phys_size); + memblock_free(phys_dist, phys_size); return; no_emu: diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 676d8d292f8a..173de1e29bda 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1151,7 +1151,7 @@ static void __init xen_pagetable_p2m_free(void) xen_cleanhighmap(addr, addr + size); size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); - memblock_phys_free(__pa(addr), size); + memblock_free((void *)addr, size); } else { xen_cleanmfnmap(addr); } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 141bb9dbd2fb..58db86f7b384 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -197,7 +197,7 @@ static void * __ref alloc_p2m_page(void) static void __ref free_p2m_page(void *p) { if (unlikely(!slab_is_available())) { - memblock_free_ptr(p, PAGE_SIZE); + memblock_free(p, PAGE_SIZE); return; } diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 712edef03929..bc1876915457 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -166,7 +166,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_fc_free(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK @@ -326,7 +326,7 @@ void __init numa_free_distance(void) size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - memblock_free_ptr(numa_distance, size); + memblock_free(numa_distance, size); numa_distance_cnt = 0; numa_distance = NULL; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index fe63d5ee201b..f62152111236 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -570,7 +570,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - memblock_free_ptr(smu, sizeof(struct smu_device)); + memblock_free(smu, sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 4b671cc0a7ea..f083194e2634 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -241,7 +241,7 @@ retry: */ rc = xen_swiotlb_fixup(start, nslabs); if (rc) { - memblock_phys_free(__pa(start), PAGE_ALIGN(bytes)); + memblock_free(start, PAGE_ALIGN(bytes)); if (nslabs > 1024 && repeat--) { /* Min is 2MB */ nslabs = max(1024UL, ALIGN(nslabs >> 1, IO_TLB_SEGSIZE)); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d32d41709513..484650681bee 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -118,7 +118,7 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); void memblock_free_all(void); -void memblock_free_ptr(void *ptr, size_t size); +void memblock_free(void *ptr, size_t size); void reset_node_managed_pages(pg_data_t *pgdat); void reset_all_zones_managed_pages(void); diff --git a/init/initramfs.c b/init/initramfs.c index 1a971f070dd4..2f3d96dc3db6 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -607,7 +607,7 @@ void __weak __init free_initrd_mem(unsigned long start, unsigned long end) unsigned long aligned_start = ALIGN_DOWN(start, PAGE_SIZE); unsigned long aligned_end = ALIGN(end, PAGE_SIZE); - memblock_phys_free(__pa(aligned_start), aligned_end - aligned_start); + memblock_free((void *)aligned_start, aligned_end - aligned_start); #endif free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM, diff --git a/init/main.c b/init/main.c index 767ee2672176..f0001af8ebb9 100644 --- a/init/main.c +++ b/init/main.c @@ -382,7 +382,7 @@ static char * __init xbc_make_cmdline(const char *key) ret = xbc_snprint_cmdline(new_cmdline, len + 1, root); if (ret < 0 || ret > len) { pr_err("Failed to print extra kernel cmdline.\n"); - memblock_free_ptr(new_cmdline, len + 1); + memblock_free(new_cmdline, len + 1); return NULL; } @@ -925,7 +925,7 @@ static void __init print_unknown_bootoptions(void) end += sprintf(end, " %s", *p); pr_notice("Unknown command line parameters:%s\n", unknown_options); - memblock_free_ptr(unknown_options, len); + memblock_free(unknown_options, len); } asmlinkage __visible void __init __no_sanitize_address start_kernel(void) diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b9fa173e5e56..02656d7ccbfd 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -247,7 +247,7 @@ swiotlb_init(int verbose) return; fail_free_mem: - memblock_phys_free(__pa(tlb), bytes); + memblock_free(tlb, bytes); fail: pr_warn("Cannot allocate buffer"); } diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a8d0a58deebc..2cae1bfa6be7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early) return; err_free_descs: - memblock_free_ptr(new_descs, new_descs_size); + memblock_free(new_descs, new_descs_size); err_free_log_buf: - memblock_free_ptr(new_log_buf, new_log_buf_len); + memblock_free(new_log_buf, new_log_buf_len); } static bool __read_mostly ignore_loglevel; diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 5ae248b29373..547558d80e64 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -792,7 +792,7 @@ void __init xbc_destroy_all(void) xbc_data = NULL; xbc_data_size = 0; xbc_node_num = 0; - memblock_free_ptr(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); + memblock_free(xbc_nodes, sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; brace_index = 0; } diff --git a/lib/cpumask.c b/lib/cpumask.c index a90786b77c1c..a971a82d2f43 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -188,7 +188,7 @@ EXPORT_SYMBOL(free_cpumask_var); */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { - memblock_phys_free(__pa(mask), cpumask_size()); + memblock_free(mask, cpumask_size()); } #endif diff --git a/mm/memblock.c b/mm/memblock.c index 52e34abc4abe..fb0c7f48e627 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -472,7 +472,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free_ptr(old_array, old_alloc_size); + memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -796,14 +796,14 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) } /** - * memblock_free_ptr - free boot memory allocation + * memblock_free - free boot memory allocation * @ptr: starting address of the boot memory allocation * @size: size of the boot memory block in bytes * * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ -void __init_memblock memblock_free_ptr(void *ptr, size_t size) +void __init_memblock memblock_free(void *ptr, size_t size) { if (ptr) memblock_phys_free(__pa(ptr), size); diff --git a/mm/percpu.c b/mm/percpu.c index d65ddf6f2a35..f5b2c2ea5a54 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2472,7 +2472,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, */ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai) { - memblock_phys_free(__pa(ai), ai->__ai_size); + memblock_free(ai, ai->__ai_size); } /** @@ -3134,7 +3134,7 @@ out_free_areas: out_free: pcpu_free_alloc_info(ai); if (areas) - memblock_phys_free(__pa(areas), areas_size); + memblock_free(areas, areas_size); return rc; } #endif /* BUILD_EMBED_FIRST_CHUNK */ @@ -3256,7 +3256,7 @@ enomem: free_fn(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: - memblock_phys_free(__pa(pages), pages_size); + memblock_free(pages, pages_size); pcpu_free_alloc_info(ai); return rc; } @@ -3286,7 +3286,7 @@ static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, static void __init pcpu_dfl_fc_free(void *ptr, size_t size) { - memblock_phys_free(__pa(ptr), size); + memblock_free(ptr, size); } void __init setup_per_cpu_areas(void) diff --git a/mm/sparse.c b/mm/sparse.c index fc3ab8d3b6bc..e5c84b0cf0c9 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -451,7 +451,7 @@ static void *sparsemap_buf_end __meminitdata; static inline void __meminit sparse_buffer_free(unsigned long size) { WARN_ON(!sparsemap_buf || size == 0); - memblock_phys_free(__pa(sparsemap_buf), size); + memblock_free(sparsemap_buf, size); } static void __init sparse_buffer_init(unsigned long size, int nid) -- cgit v1.2.3 From b5389086ad7be0453c55e0069a89856d1fbdf605 Mon Sep 17 00:00:00 2001 From: Zhenguo Yao Date: Fri, 5 Nov 2021 13:43:28 -0700 Subject: hugetlbfs: extend the definition of hugepages parameter to support node allocation We can specify the number of hugepages to allocate at boot. But the hugepages is balanced in all nodes at present. In some scenarios, we only need hugepages in one node. For example: DPDK needs hugepages which are in the same node as NIC. If DPDK needs four hugepages of 1G size in node1 and system has 16 numa nodes we must reserve 64 hugepages on the kernel cmdline. But only four hugepages are used. The others should be free after boot. If the system memory is low(for example: 64G), it will be an impossible task. So extend the hugepages parameter to support specifying hugepages on a specific node. For example add following parameter: hugepagesz=1G hugepages=0:1,1:3 It will allocate 1 hugepage in node0 and 3 hugepages in node1. Link: https://lkml.kernel.org/r/20211005054729.86457-1-yaozhenguo1@gmail.com Signed-off-by: Zhenguo Yao Reviewed-by: Mike Kravetz Cc: Zhenguo Yao Cc: Dan Carpenter Cc: Nathan Chancellor Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Jonathan Corbet Cc: Mike Rapoport Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 8 +- Documentation/admin-guide/mm/hugetlbpage.rst | 12 +- arch/powerpc/mm/hugetlbpage.c | 9 +- include/linux/hugetlb.h | 6 +- mm/hugetlb.c | 153 ++++++++++++++++++++---- 5 files changed, 155 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e7f7904edf20..02eeda2a11ad 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1601,9 +1601,11 @@ the number of pages of hugepagesz to be allocated. If this is the first HugeTLB parameter on the command line, it specifies the number of pages to allocate for - the default huge page size. See also - Documentation/admin-guide/mm/hugetlbpage.rst. - Format: + the default huge page size. If using node format, the + number of pages to allocate per-node can be specified. + See also Documentation/admin-guide/mm/hugetlbpage.rst. + Format: or (node format) + :[,:] hugepagesz= [HW] The size of the HugeTLB pages. This is used in diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst index bb90de3885d1..0166f9de3428 100644 --- a/Documentation/admin-guide/mm/hugetlbpage.rst +++ b/Documentation/admin-guide/mm/hugetlbpage.rst @@ -128,7 +128,9 @@ hugepages implicitly specifies the number of huge pages of default size to allocate. If the number of huge pages of default size is implicitly specified, it can not be overwritten by a hugepagesz,hugepages - parameter pair for the default size. + parameter pair for the default size. This parameter also has a + node format. The node format specifies the number of huge pages + to allocate on specific nodes. For example, on an architecture with 2M default huge page size:: @@ -138,6 +140,14 @@ hugepages indicating that the hugepages=512 parameter is ignored. If a hugepages parameter is preceded by an invalid hugepagesz parameter, it will be ignored. + + Node format example:: + + hugepagesz=2M hugepages=0:1,1:2 + + It will allocate 1 2M hugepage on node0 and 2 2M hugepages on node1. + If the node number is invalid, the parameter will be ignored. + default_hugepagesz Specify the default huge page size. This parameter can only be specified once on the command line. default_hugepagesz can diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 9a75ba078e1b..82d8b368ca6d 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -229,17 +229,22 @@ static int __init pseries_alloc_bootmem_huge_page(struct hstate *hstate) m->hstate = hstate; return 1; } + +bool __init hugetlb_node_alloc_supported(void) +{ + return false; +} #endif -int __init alloc_bootmem_huge_page(struct hstate *h) +int __init alloc_bootmem_huge_page(struct hstate *h, int nid) { #ifdef CONFIG_PPC_BOOK3S_64 if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled()) return pseries_alloc_bootmem_huge_page(h); #endif - return __alloc_bootmem_huge_page(h); + return __alloc_bootmem_huge_page(h, nid); } #ifndef CONFIG_PPC_BOOK3S_64 diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c0a20781b28e..44c2ab0dfa59 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -615,6 +615,7 @@ struct hstate { unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; + unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; @@ -647,8 +648,9 @@ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct page *page); /* arch callback */ -int __init __alloc_bootmem_huge_page(struct hstate *h); -int __init alloc_bootmem_huge_page(struct hstate *h); +int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); +int __init alloc_bootmem_huge_page(struct hstate *h, int nid); +bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5eab627a170b..24543dab9c4b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -77,6 +77,7 @@ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; +static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, @@ -2963,33 +2964,39 @@ out_subpool_put: return ERR_PTR(-ENOSPC); } -int alloc_bootmem_huge_page(struct hstate *h) +int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); -int __alloc_bootmem_huge_page(struct hstate *h) +int __alloc_bootmem_huge_page(struct hstate *h, int nid) { - struct huge_bootmem_page *m; + struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node; + if (nid >= nr_online_nodes) + return 0; + /* do node specific alloc */ + if (nid != NUMA_NO_NODE) { + m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), + 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); + if (!m) + return 0; + goto found; + } + /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { - void *addr; - - addr = memblock_alloc_try_nid_raw( + m = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); - if (addr) { - /* - * Use the beginning of the huge page to store the - * huge_bootmem_page struct (until gather_bootmem - * puts them into the mem_map). - */ - m = addr; - goto found; - } + /* + * Use the beginning of the huge page to store the + * huge_bootmem_page struct (until gather_bootmem + * puts them into the mem_map). + */ + if (!m) + return 0; + goto found; } - return 0; found: - BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h))); /* Put them into a private list first because mem_map is not up yet */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages); @@ -3029,12 +3036,61 @@ static void __init gather_bootmem_prealloc(void) cond_resched(); } } +static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) +{ + unsigned long i; + char buf[32]; + + for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { + if (hstate_is_gigantic(h)) { + if (!alloc_bootmem_huge_page(h, nid)) + break; + } else { + struct page *page; + gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; + + page = alloc_fresh_huge_page(h, gfp_mask, nid, + &node_states[N_MEMORY], NULL); + if (!page) + break; + put_page(page); /* free it into the hugepage allocator */ + } + cond_resched(); + } + if (i == h->max_huge_pages_node[nid]) + return; + + string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); + pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", + h->max_huge_pages_node[nid], buf, nid, i); + h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); + h->max_huge_pages_node[nid] = i; +} static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long i; nodemask_t *node_alloc_noretry; + bool node_specific_alloc = false; + /* skip gigantic hugepages allocation if hugetlb_cma enabled */ + if (hstate_is_gigantic(h) && hugetlb_cma_size) { + pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); + return; + } + + /* do node specific alloc */ + for (i = 0; i < nr_online_nodes; i++) { + if (h->max_huge_pages_node[i] > 0) { + hugetlb_hstate_alloc_pages_onenode(h, i); + node_specific_alloc = true; + } + } + + if (node_specific_alloc) + return; + + /* below will do all node balanced alloc */ if (!hstate_is_gigantic(h)) { /* * Bit mask controlling how hard we retry per-node allocations. @@ -3055,11 +3111,7 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) for (i = 0; i < h->max_huge_pages; ++i) { if (hstate_is_gigantic(h)) { - if (hugetlb_cma_size) { - pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); - goto free; - } - if (!alloc_bootmem_huge_page(h)) + if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; } else if (!alloc_pool_huge_page(h, &node_states[N_MEMORY], @@ -3075,7 +3127,6 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) h->max_huge_pages, buf, i); h->max_huge_pages = i; } -free: kfree(node_alloc_noretry); } @@ -3990,6 +4041,10 @@ static int __init hugetlb_init(void) } default_hstate.max_huge_pages = default_hstate_max_huge_pages; + + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; } } @@ -4050,6 +4105,10 @@ void __init hugetlb_add_hstate(unsigned int order) parsed_hstate = h; } +bool __init __weak hugetlb_node_alloc_supported(void) +{ + return true; +} /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz @@ -4061,6 +4120,10 @@ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; + int node = NUMA_NO_NODE; + int count; + unsigned long tmp; + char *p = s; if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); @@ -4084,8 +4147,40 @@ static int __init hugepages_setup(char *s) return 0; } - if (sscanf(s, "%lu", mhp) <= 0) - *mhp = 0; + while (*p) { + count = 0; + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + /* Parameter is node format */ + if (p[count] == ':') { + if (!hugetlb_node_alloc_supported()) { + pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); + return 0; + } + node = tmp; + p += count + 1; + if (node < 0 || node >= nr_online_nodes) + goto invalid; + /* Parse hugepages */ + if (sscanf(p, "%lu%n", &tmp, &count) != 1) + goto invalid; + if (!hugetlb_max_hstate) + default_hugepages_in_node[node] = tmp; + else + parsed_hstate->max_huge_pages_node[node] = tmp; + *mhp += tmp; + /* Go to parse next node*/ + if (p[count] == ',') + p += count + 1; + else + break; + } else { + if (p != s) + goto invalid; + *mhp = tmp; + break; + } + } /* * Global state is always initialized later in hugetlb_init. @@ -4098,6 +4193,10 @@ static int __init hugepages_setup(char *s) last_mhp = mhp; return 1; + +invalid: + pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); + return 0; } __setup("hugepages=", hugepages_setup); @@ -4159,6 +4258,7 @@ __setup("hugepagesz=", hugepagesz_setup); static int __init default_hugepagesz_setup(char *s) { unsigned long size; + int i; parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { @@ -4187,6 +4287,9 @@ static int __init default_hugepagesz_setup(char *s) */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; + for (i = 0; i < nr_online_nodes; i++) + default_hstate.max_huge_pages_node[i] = + default_hugepages_in_node[i]; if (hstate_is_gigantic(&default_hstate)) hugetlb_hstate_alloc_pages(&default_hstate); default_hstate_max_huge_pages = 0; -- cgit v1.2.3 From 8eb42beac8d369f5443addd469879d152422a28d Mon Sep 17 00:00:00 2001 From: John Hubbard Date: Fri, 5 Nov 2021 13:43:32 -0700 Subject: mm/migrate: de-duplicate migrate_reason strings In order to remove the need to manually keep three different files in synch, provide a common definition of the mapping between enum migrate_reason, and the associated strings for each enum item. 1. Use the tracing system's mapping of enums to strings, by redefining and reusing the MIGRATE_REASON and supporting macros, and using that to populate the string array in mm/debug.c. 2. Move enum migrate_reason to migrate_mode.h. This is not strictly necessary for this patch, but migrate mode and migrate reason go together, so this will slightly clarify things. Link: https://lkml.kernel.org/r/20210922041755.141817-2-jhubbard@nvidia.com Signed-off-by: John Hubbard Reviewed-by: Weizhao Ouyang Cc: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 19 +------------------ include/linux/migrate_mode.h | 13 +++++++++++++ mm/debug.c | 20 +++++++++++--------- 3 files changed, 25 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index c8077e936691..3d154fe03c96 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -19,24 +19,7 @@ struct migration_target_control; */ #define MIGRATEPAGE_SUCCESS 0 -/* - * Keep sync with: - * - macro MIGRATE_REASON in include/trace/events/migrate.h - * - migrate_reason_names[MR_TYPES] in mm/debug.c - */ -enum migrate_reason { - MR_COMPACTION, - MR_MEMORY_FAILURE, - MR_MEMORY_HOTPLUG, - MR_SYSCALL, /* also applies to cpusets */ - MR_MEMPOLICY_MBIND, - MR_NUMA_MISPLACED, - MR_CONTIG_RANGE, - MR_LONGTERM_PIN, - MR_DEMOTION, - MR_TYPES -}; - +/* Defined in mm/debug.c: */ extern const char *migrate_reason_names[MR_TYPES]; #ifdef CONFIG_MIGRATION diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h index 883c99249033..f37cc03f9369 100644 --- a/include/linux/migrate_mode.h +++ b/include/linux/migrate_mode.h @@ -19,4 +19,17 @@ enum migrate_mode { MIGRATE_SYNC_NO_COPY, }; +enum migrate_reason { + MR_COMPACTION, + MR_MEMORY_FAILURE, + MR_MEMORY_HOTPLUG, + MR_SYSCALL, /* also applies to cpusets */ + MR_MEMPOLICY_MBIND, + MR_NUMA_MISPLACED, + MR_CONTIG_RANGE, + MR_LONGTERM_PIN, + MR_DEMOTION, + MR_TYPES +}; + #endif /* MIGRATE_MODE_H_INCLUDED */ diff --git a/mm/debug.c b/mm/debug.c index fae0f81ad831..4333b6784a20 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -16,17 +16,19 @@ #include #include "internal.h" +#include + +/* + * Define EM() and EMe() so that MIGRATE_REASON from trace/events/migrate.h can + * be used to populate migrate_reason_names[]. + */ +#undef EM +#undef EMe +#define EM(a, b) b, +#define EMe(a, b) b const char *migrate_reason_names[MR_TYPES] = { - "compaction", - "memory_failure", - "memory_hotplug", - "syscall_or_cpuset", - "mempolicy_mbind", - "numa_misplaced", - "contig_range", - "longterm_pin", - "demotion", + MIGRATE_REASON }; const struct trace_print_flags pageflag_names[] = { -- cgit v1.2.3 From 20f9ba4f995247bb79e243741b8fdddbd76dd923 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 5 Nov 2021 13:43:35 -0700 Subject: mm: migrate: make demotion knob depend on migration The memory demotion needs to call migrate_pages() to do the jobs. And it is controlled by a knob, however, the knob doesn't depend on CONFIG_MIGRATION. The knob could be truned on even though MIGRATION is disabled, this will not cause any crash since migrate_pages() would just return -ENOSYS. But it is definitely not optimal to go through demotion path then retry regular swap every time. And it doesn't make too much sense to have the knob visible to the users when !MIGRATION. Move the related code from mempolicy.[h|c] to migrate.[h|c]. Link: https://lkml.kernel.org/r/20211015005559.246709-1-shy828301@gmail.com Signed-off-by: Yang Shi Acked-by: "Huang, Ying" Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ---- include/linux/migrate.h | 4 ++++ mm/mempolicy.c | 61 ----------------------------------------------- mm/migrate.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 65 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 097bbbb37493..3c7595e81150 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -183,8 +183,6 @@ extern bool vma_migratable(struct vm_area_struct *vma); extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); extern void mpol_put_task_policy(struct task_struct *); -extern bool numa_demotion_enabled; - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); @@ -300,8 +298,6 @@ static inline nodemask_t *policy_nodemask_current(gfp_t gfp) return NULL; } -#define numa_demotion_enabled false - static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 3d154fe03c96..2d8130e05dc0 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,6 +40,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); + +extern bool numa_demotion_enabled; #else static inline void putback_movable_pages(struct list_head *l) {} @@ -65,6 +67,8 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, { return -ENOSYS; } + +#define numa_demotion_enabled false #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_COMPACTION diff --git a/mm/mempolicy.c b/mm/mempolicy.c index ce722333d9f6..f1080e0a566a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -3057,64 +3057,3 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } - -bool numa_demotion_enabled = false; - -#ifdef CONFIG_SYSFS -static ssize_t numa_demotion_enabled_show(struct kobject *kobj, - struct kobj_attribute *attr, char *buf) -{ - return sysfs_emit(buf, "%s\n", - numa_demotion_enabled? "true" : "false"); -} - -static ssize_t numa_demotion_enabled_store(struct kobject *kobj, - struct kobj_attribute *attr, - const char *buf, size_t count) -{ - if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) - numa_demotion_enabled = true; - else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) - numa_demotion_enabled = false; - else - return -EINVAL; - - return count; -} - -static struct kobj_attribute numa_demotion_enabled_attr = - __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, - numa_demotion_enabled_store); - -static struct attribute *numa_attrs[] = { - &numa_demotion_enabled_attr.attr, - NULL, -}; - -static const struct attribute_group numa_attr_group = { - .attrs = numa_attrs, -}; - -static int __init numa_init_sysfs(void) -{ - int err; - struct kobject *numa_kobj; - - numa_kobj = kobject_create_and_add("numa", mm_kobj); - if (!numa_kobj) { - pr_err("failed to create numa kobject\n"); - return -ENOMEM; - } - err = sysfs_create_group(numa_kobj, &numa_attr_group); - if (err) { - pr_err("failed to register numa group\n"); - goto delete_obj; - } - return 0; - -delete_obj: - kobject_put(numa_kobj); - return err; -} -subsys_initcall(numa_init_sysfs); -#endif diff --git a/mm/migrate.c b/mm/migrate.c index 1852d787e6ab..51e310a94516 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -3306,3 +3306,64 @@ static int __init migrate_on_reclaim_init(void) } late_initcall(migrate_on_reclaim_init); #endif /* CONFIG_HOTPLUG_CPU */ + +bool numa_demotion_enabled = false; + +#ifdef CONFIG_SYSFS +static ssize_t numa_demotion_enabled_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%s\n", + numa_demotion_enabled ? "true" : "false"); +} + +static ssize_t numa_demotion_enabled_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t count) +{ + if (!strncmp(buf, "true", 4) || !strncmp(buf, "1", 1)) + numa_demotion_enabled = true; + else if (!strncmp(buf, "false", 5) || !strncmp(buf, "0", 1)) + numa_demotion_enabled = false; + else + return -EINVAL; + + return count; +} + +static struct kobj_attribute numa_demotion_enabled_attr = + __ATTR(demotion_enabled, 0644, numa_demotion_enabled_show, + numa_demotion_enabled_store); + +static struct attribute *numa_attrs[] = { + &numa_demotion_enabled_attr.attr, + NULL, +}; + +static const struct attribute_group numa_attr_group = { + .attrs = numa_attrs, +}; + +static int __init numa_init_sysfs(void) +{ + int err; + struct kobject *numa_kobj; + + numa_kobj = kobject_create_and_add("numa", mm_kobj); + if (!numa_kobj) { + pr_err("failed to create numa kobject\n"); + return -ENOMEM; + } + err = sysfs_create_group(numa_kobj, &numa_attr_group); + if (err) { + pr_err("failed to register numa group\n"); + goto delete_obj; + } + return 0; + +delete_obj: + kobject_put(numa_kobj); + return err; +} +subsys_initcall(numa_init_sysfs); +#endif -- cgit v1.2.3 From 50f9481ed9fb8a2d2a06a155634c7f9eeff9fa61 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:24 -0700 Subject: mm/memory_hotplug: remove CONFIG_MEMORY_HOTPLUG_SPARSE CONFIG_MEMORY_HOTPLUG depends on CONFIG_SPARSEMEM, so there is no need for CONFIG_MEMORY_HOTPLUG_SPARSE anymore; adjust all instances to use CONFIG_MEMORY_HOTPLUG and remove CONFIG_MEMORY_HOTPLUG_SPARSE. Link: https://lkml.kernel.org/r/20210929143600.49379-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Shuah Khan [kselftest] Acked-by: Greg Kroah-Hartman Acked-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/machdep.h | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/setup.c | 4 ++-- arch/powerpc/platforms/pseries/setup.c | 2 +- drivers/base/Makefile | 2 +- drivers/base/node.c | 9 ++++----- drivers/virtio/Kconfig | 2 +- include/linux/memory.h | 24 ++++++++++-------------- include/linux/node.h | 4 ++-- lib/Kconfig.debug | 2 +- mm/Kconfig | 4 ---- mm/memory_hotplug.c | 2 -- tools/testing/selftests/memory-hotplug/config | 1 - 13 files changed, 24 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 764f2732a821..d8a2ca007082 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -32,7 +32,7 @@ struct machdep_calls { void (*iommu_save)(void); void (*iommu_restore)(void); #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long (*memory_block_size)(void); #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 1777e992b20b..6052f5d5ded3 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -912,7 +912,7 @@ void __init setup_per_cpu_areas(void) } #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long memory_block_size_bytes(void) { if (ppc_md.memory_block_size) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a8db3f153063..ad56a54ac9c5 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -440,7 +440,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) } #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static unsigned long pnv_memory_block_size(void) { /* @@ -553,7 +553,7 @@ define_machine(powernv) { #ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pnv_memory_block_size, #endif }; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index f79126f16258..d29f6f1f7f37 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -1089,7 +1089,7 @@ define_machine(pseries) { .machine_kexec = pSeries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pseries_memory_block_size, #endif }; diff --git a/drivers/base/Makefile b/drivers/base/Makefile index ef8e44a7d288..02f7f1358e86 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -13,7 +13,7 @@ obj-y += power/ obj-$(CONFIG_ISA_BUS_API) += isa.o obj-y += firmware_loader/ obj-$(CONFIG_NUMA) += node.o -obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o ifeq ($(CONFIG_SYSFS),y) obj-$(CONFIG_MODULES) += module.o endif diff --git a/drivers/base/node.c b/drivers/base/node.c index c56d34f8158f..b5a4ba18f9f9 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -629,7 +629,7 @@ static void node_device_release(struct device *dev) { struct node *node = to_node(dev); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) /* * We schedule the work only when a memory section is * onlined/offlined on this node. When we come here, @@ -782,7 +782,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) return 0; } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static int __ref get_nid_for_pfn(unsigned long pfn) { #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -958,10 +958,9 @@ static int node_memory_callback(struct notifier_block *self, return NOTIFY_OK; } #endif /* CONFIG_HUGETLBFS */ -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ -#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \ - !defined(CONFIG_HUGETLBFS) +#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS) static inline int node_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index ce1b3f6ec325..3654def9915c 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -98,7 +98,7 @@ config VIRTIO_MEM default m depends on X86_64 depends on VIRTIO - depends on MEMORY_HOTPLUG_SPARSE + depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE depends on CONTIG_ALLOC help diff --git a/include/linux/memory.h b/include/linux/memory.h index 053a530c7bdd..0328ec039c38 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -110,7 +110,7 @@ struct mem_section; #define SLAB_CALLBACK_PRI 1 #define IPC_CALLBACK_PRI 10 -#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifndef CONFIG_MEMORY_HOTPLUG static inline void memory_dev_init(void) { return; @@ -126,7 +126,14 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -#else +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} +/* These aren't inline functions due to a GCC bug. */ +#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) +#else /* CONFIG_MEMORY_HOTPLUG */ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, @@ -148,9 +155,6 @@ struct memory_group *memory_group_find_by_id(int mgid); typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, struct memory_group *excluded, void *arg); -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ - -#ifdef CONFIG_MEMORY_HOTPLUG #define hotplug_memory_notifier(fn, pri) ({ \ static __meminitdata struct notifier_block fn##_mem_nb =\ { .notifier_call = fn, .priority = pri };\ @@ -158,15 +162,7 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) -#else -static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) -{ - return 0; -} -/* These aren't inline functions due to a GCC bug. */ -#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) -#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -#endif +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * Kernel text modification mutex, used for code patching. Users of this lock diff --git a/include/linux/node.h b/include/linux/node.h index 8e5a29897936..bb21fd631b16 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -85,7 +85,7 @@ struct node { struct device dev; struct list_head access_list; -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) struct work_struct node_work; #endif #ifdef CONFIG_HMEM_REPORTING @@ -98,7 +98,7 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, enum meminit_context context); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2a9b6dcdac4f..669fee1d26b8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -877,7 +877,7 @@ config DEBUG_MEMORY_INIT config MEMORY_NOTIFIER_ERROR_INJECT tristate "Memory hotplug notifier error injection module" - depends on MEMORY_HOTPLUG_SPARSE && NOTIFIER_ERROR_INJECTION + depends on MEMORY_HOTPLUG && NOTIFIER_ERROR_INJECTION help This option provides the ability to inject artificial errors to memory hotplug notifier chain callbacks. It is controlled through diff --git a/mm/Kconfig b/mm/Kconfig index b2bf73c90a38..0148a9c4fa2a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -128,10 +128,6 @@ config MEMORY_HOTPLUG depends on 64BIT || BROKEN select NUMA_KEEP_MEMINFO if NUMA -config MEMORY_HOTPLUG_SPARSE - def_bool y - depends on SPARSEMEM && MEMORY_HOTPLUG - config MEMORY_HOTPLUG_DEFAULT_ONLINE bool "Online the newly added memory blocks by default" depends on MEMORY_HOTPLUG diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index afaae370b8cd..fc07ce7b5842 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -220,7 +220,6 @@ static void release_memory_resource(struct resource *res) kfree(res); } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -1163,7 +1162,6 @@ failed_addition: mem_hotplug_done(); return ret; } -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ static void reset_node_present_pages(pg_data_t *pgdat) { diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index a7e8cd5bb265..1eef042a31e1 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -1,5 +1,4 @@ CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_MEMORY_HOTREMOVE=y -- cgit v1.2.3 From 6b740c6c3aa371cd70ac07f8d071f2a8af28c51c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:31 -0700 Subject: mm/memory_hotplug: remove HIGHMEM leftovers We don't support CONFIG_MEMORY_HOTPLUG on 32 bit and consequently not HIGHMEM. Let's remove any leftover code -- including the unused "status_change_nid_high" field part of the memory notifier. Link: https://lkml.kernel.org/r/20210929143600.49379-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/memory-hotplug.rst | 3 -- .../translations/zh_CN/core-api/memory-hotplug.rst | 4 --- include/linux/memory.h | 1 - mm/memory_hotplug.c | 36 ++-------------------- 4 files changed, 2 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst index de7467e48067..682259ee633a 100644 --- a/Documentation/core-api/memory-hotplug.rst +++ b/Documentation/core-api/memory-hotplug.rst @@ -57,7 +57,6 @@ The third argument (arg) passes a pointer of struct memory_notify:: unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; } @@ -65,8 +64,6 @@ The third argument (arg) passes a pointer of struct memory_notify:: - nr_pages is # of pages of online/offline memory. - status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask is (will be) set/clear, if this is -1, then nodemask status is not changed. -- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask - is (will be) set/clear, if this is -1, then nodemask status is not changed. - status_change_nid is set node id when N_MEMORY of nodemask is (will be) set/clear. It means a new(memoryless) node gets new memory by online and a node loses all memory. If this is -1, then nodemask status is not changed. diff --git a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst index 161f4d2c18cc..9a204eb196f2 100644 --- a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst +++ b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst @@ -63,7 +63,6 @@ memory_notify结构体的指针:: unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; } @@ -74,9 +73,6 @@ memory_notify结构体的指针:: - status_change_nid_normal是当nodemask的N_NORMAL_MEMORY被设置/清除时设置节 点id，如果是-1，则nodemask状态不改变。 -- status_change_nid_high是当nodemask的N_HIGH_MEMORY被设置/清除时设置的节点 - id，如果这个值为-1，那么nodemask状态不会改变。 - - status_change_nid是当nodemask的N_MEMORY被（将）设置/清除时设置的节点id。这 意味着一个新的（没上线的）节点通过联机获得新的内存，而一个节点失去了所有的内 存。如果这个值为-1，那么nodemask的状态就不会改变。 diff --git a/include/linux/memory.h b/include/linux/memory.h index 0328ec039c38..88eb587b5143 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,7 +96,6 @@ struct memory_notify { unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; }; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fc07ce7b5842..0aa7ca3dfbc9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include @@ -585,10 +584,6 @@ void generic_online_page(struct page *page, unsigned int order) debug_pagealloc_map_pages(page, 1 << order); __free_pages_core(page, order); totalram_pages_add(1UL << order); -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages_add(1UL << order); -#endif } EXPORT_SYMBOL_GPL(generic_online_page); @@ -625,16 +620,11 @@ static void node_states_check_changes_online(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; if (!node_state(nid, N_MEMORY)) arg->status_change_nid = nid; if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY)) arg->status_change_nid_normal = nid; -#ifdef CONFIG_HIGHMEM - if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY)) - arg->status_change_nid_high = nid; -#endif } static void node_states_set_node(int node, struct memory_notify *arg) @@ -642,9 +632,6 @@ static void node_states_set_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_set_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_set_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_set_state(node, N_MEMORY); } @@ -1801,7 +1788,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; /* * Check whether node_states[N_NORMAL_MEMORY] will be changed. @@ -1816,24 +1802,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages, if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages) arg->status_change_nid_normal = zone_to_nid(zone); -#ifdef CONFIG_HIGHMEM - /* - * node_states[N_HIGH_MEMORY] contains nodes which - * have normal memory or high memory. - * Here we add the present_pages belonging to ZONE_HIGHMEM. - * If the zone is within the range of [0..ZONE_HIGHMEM), and - * we determine that the zones in that range become empty, - * we need to clear the node for N_HIGH_MEMORY. - */ - present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages; - if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages) - arg->status_change_nid_high = zone_to_nid(zone); -#endif - /* - * We have accounted the pages from [0..ZONE_NORMAL), and - * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM - * as well. + * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM + * does not apply as we don't support 32bit. * Here we count the possible pages from ZONE_MOVABLE. * If after having accounted all the pages, we see that the nr_pages * to be offlined is over or equal to the accounted pages, @@ -1851,9 +1822,6 @@ static void node_states_clear_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_clear_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_clear_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_clear_state(node, N_MEMORY); } -- cgit v1.2.3 From 43e3aa2a3247c9ca348884866a9846d788ec5ed6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:35 -0700 Subject: mm/memory_hotplug: remove stale function declarations These functions no longer exist. Link: https://lkml.kernel.org/r/20210929143600.49379-6-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index e5a867c950b2..be48e003a518 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -98,9 +98,6 @@ static inline void zone_seqlock_init(struct zone *zone) { seqlock_init(&zone->span_seqlock); } -extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages); -extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages); -extern int add_one_highpage(struct page *page, int pfn, int bad_ppro); extern void adjust_present_page_count(struct page *page, struct memory_group *group, long nr_pages); -- cgit v1.2.3 From e14b41556d9ec20af60a9f672ac6f64dd450763c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:46 -0700 Subject: memblock: improve MEMBLOCK_HOTPLUG documentation The description of MEMBLOCK_HOTPLUG is currently short and consequently misleading: we're actually dealing with a memory region that might get hotunplugged later (i.e., the platform+firmware supports it), yet it is indicated in the firmware-provided memory map as system ram that will just get used by the system for any purpose when not taking special care. The firmware marked this memory region as a hot(un)plugged (e.g., hotplugged before reboot), implying that it might get hotunplugged again later. Whether we consider this information depends on the "movable_node" kernel commandline parameter: only with "movable_node" set, we'll try keeping this memory hotunpluggable, for example, by not serving early allocations from this memory region and by letting the buddy manage it using the ZONE_MOVABLE. Let's make this clearer by extending the documentation. Note: kexec *has to* indicate this memory to the second kernel. With "movable_node" set, we don't want to place kexec-images on this memory. Without "movable_node" set, we don't care and can place kexec-images on this memory. In both cases, after successful memory hotunplug, kexec has to be re-armed to update the memory map for the second kernel and to place the kexec-images somewhere else. Link: https://lkml.kernel.org/r/20211004093605.5830-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 484650681bee..1d2b3e902a84 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -28,7 +28,11 @@ extern unsigned long long max_possible_pfn; /** * enum memblock_flags - definition of memory region attributes * @MEMBLOCK_NONE: no special request - * @MEMBLOCK_HOTPLUG: hotpluggable region + * @MEMBLOCK_HOTPLUG: memory region indicated in the firmware-provided memory + * map during early boot as hot(un)pluggable system RAM (e.g., memory range + * that might get hotunplugged later). With "movable_node" set on the kernel + * commandline, try keeping this memory region hotunpluggable. Does not apply + * to memblocks added ("hotplugged") after early boot. * @MEMBLOCK_MIRROR: mirrored region * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description -- cgit v1.2.3 From 952eea9b01e4bbb7011329f1b7240844e61e5128 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:49 -0700 Subject: memblock: allow to specify flags with memblock_add_node() We want to specify flags when hotplugging memory. Let's prepare to pass flags to memblock_add_node() by adjusting all existing users. Note that when hotplugging memory the system is already up and running and we might have concurrent memblock users: for example, while we're hotplugging memory, kexec_file code might search for suitable memory regions to place kexec images. It's important to add the memory directly to memblock via a single call with the right flags, instead of adding the memory first and apply flags later: otherwise, concurrent memblock users might temporarily stumble over memblocks with wrong flags, which will be important in a follow-up patch that introduces a new flag to properly handle add_memory_driver_managed(). Link: https://lkml.kernel.org/r/20211004093605.5830-4-david@redhat.com Acked-by: Geert Uytterhoeven Acked-by: Heiko Carstens Signed-off-by: David Hildenbrand Acked-by: Shahab Vahedi [arch/arc] Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/mm/init.c | 4 ++-- arch/ia64/mm/contig.c | 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c | 3 ++- arch/m68k/mm/motorola.c | 6 ++++-- arch/mips/loongson64/init.c | 4 +++- arch/mips/sgi-ip27/ip27-memory.c | 3 ++- arch/s390/kernel/setup.c | 3 ++- include/linux/memblock.h | 3 ++- include/linux/mm.h | 2 +- mm/memblock.c | 9 +++++---- mm/memory_hotplug.c | 2 +- 12 files changed, 26 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 59408f6a02d4..ce4e939a7f07 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -59,13 +59,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) low_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 0); + memblock_add_node(base, size, 0, MEMBLOCK_NONE); } else { #ifdef CONFIG_HIGHMEM high_mem_start = base; high_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 1); + memblock_add_node(base, size, 1, MEMBLOCK_NONE); memblock_reserve(base, size); #endif } diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 42e025cfbd08..24901d809301 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -153,7 +153,7 @@ find_memory (void) efi_memmap_walk(find_max_min_low_pfn, NULL); max_pfn = max_low_pfn; - memblock_add_node(0, PFN_PHYS(max_low_pfn), 0); + memblock_add_node(0, PFN_PHYS(max_low_pfn), 0, MEMBLOCK_NONE); find_initrd(); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 5c6da8d83c1a..5d165607bf35 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -378,7 +378,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid) #endif if (start < end) - memblock_add_node(__pa(start), end - start, nid); + memblock_add_node(__pa(start), end - start, nid, MEMBLOCK_NONE); return 0; } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index eac9dde65193..6f1f25125294 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -174,7 +174,8 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 9f3f77785aa7..2b05bb2bac00 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -410,7 +410,8 @@ void __init paging_init(void) min_addr = m68k_memory[0].addr; max_addr = min_addr + m68k_memory[0].size; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); for (i = 1; i < m68k_num_memory;) { if (m68k_memory[i].addr < min_addr) { printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n", @@ -421,7 +422,8 @@ void __init paging_init(void) (m68k_num_memory - i) * sizeof(struct m68k_mem_info)); continue; } - memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i); + memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i, + MEMBLOCK_NONE); addr = m68k_memory[i].addr + m68k_memory[i].size; if (addr > max_addr) max_addr = addr; diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index 76e0a9636a0e..4ac5ba80bbf6 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -77,7 +77,9 @@ void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(node_psize), node); + memblock_add_node(PFN_PHYS(start_pfn), + PFN_PHYS(node_psize), node, + MEMBLOCK_NONE); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 6173684b5aaa..adc2faeecf7c 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -341,7 +341,8 @@ static void __init szmem(void) continue; } memblock_add_node(PFN_PHYS(slot_getbasepfn(node, slot)), - PFN_PHYS(slot_psize), node); + PFN_PHYS(slot_psize), node, + MEMBLOCK_NONE); } } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 7fc836e9e194..8a378d426239 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -593,7 +593,8 @@ static void __init setup_resources(void) * part of the System RAM resource. */ if (crashk_res.end) { - memblock_add_node(crashk_res.start, resource_size(&crashk_res), 0); + memblock_add_node(crashk_res.start, resource_size(&crashk_res), + 0, MEMBLOCK_NONE); memblock_reserve(crashk_res.start, resource_size(&crashk_res)); insert_resource(&iomem_resource, &crashk_res); } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1d2b3e902a84..8b6560dc7a9e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -104,7 +104,8 @@ static inline void memblock_discard(void) {} #endif void memblock_allow_resize(void); -int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); +int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, + enum memblock_flags flags); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_phys_free(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e37c726b9db..15058d9cec99 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2425,7 +2425,7 @@ static inline unsigned long get_num_physpages(void) * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() - * memblock_add_node(base, size, nid) + * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); diff --git a/mm/memblock.c b/mm/memblock.c index fb0c7f48e627..1b0cd8a52a13 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -655,6 +655,7 @@ repeat: * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details @@ -663,14 +664,14 @@ repeat: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, - int nid) + int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; - memblock_dbg("%s: [%pa-%pa] nid=%d %pS\n", __func__, - &base, &end, nid, (void *)_RET_IP_); + memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, + &base, &end, nid, flags, (void *)_RET_IP_); - return memblock_add_range(&memblock.memory, base, size, nid, 0); + return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9d254e88221e..cedeaa4d6f0e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1370,7 +1370,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - ret = memblock_add_node(start, size, nid); + ret = memblock_add_node(start, size, nid, MEMBLOCK_NONE); if (ret) goto error_mem_hotplug_end; } -- cgit v1.2.3 From f7892d8e288d4b090176f26d9bf7943dbbb639a6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:53 -0700 Subject: memblock: add MEMBLOCK_DRIVER_MANAGED to mimic IORESOURCE_SYSRAM_DRIVER_MANAGED Let's add a flag that corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED, indicating that we're dealing with a memory region that is never indicated in the firmware-provided memory map, but always detected and added by a driver. Similar to MEMBLOCK_HOTPLUG, most infrastructure has to treat such memory regions like ordinary MEMBLOCK_NONE memory regions -- for example, when selecting memory regions to add to the vmcore for dumping in the crashkernel via for_each_mem_range(). However, especially kexec_file is not supposed to select such memblocks via for_each_free_mem_range() / for_each_free_mem_range_reverse() to place kexec images, similar to how we handle IORESOURCE_SYSRAM_DRIVER_MANAGED without CONFIG_ARCH_KEEP_MEMBLOCK. We'll make sure that memory hotplug code sets the flag where applicable (IORESOURCE_SYSRAM_DRIVER_MANAGED) next. This prepares architectures that need CONFIG_ARCH_KEEP_MEMBLOCK, such as arm64, for virtio-mem support. Note that kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Let's add a comment to kexec_walk_memblock(), documenting how we handle MEMBLOCK_DRIVER_MANAGED now just like using IORESOURCE_SYSRAM_DRIVER_MANAGED in locate_mem_hole_callback() for kexec_walk_resources(). Also note that MEMBLOCK_HOTPLUG cannot be reused due to different semantics: MEMBLOCK_HOTPLUG: memory is indicated as "System RAM" in the firmware-provided memory map and added to the system early during boot; kexec *has to* indicate this memory to the second kernel and can place kexec-images on this memory. After memory hotunplug, kexec has to be re-armed. We mostly ignore this flag when "movable_node" is not set on the kernel command line, because then we're told to not care about hotunpluggability of such memory regions. MEMBLOCK_DRIVER_MANAGED: memory is not indicated as "System RAM" in the firmware-provided memory map; this memory is always detected and added to the system by a driver; memory might not actually be physically hotunpluggable. kexec *must not* indicate this memory to the second kernel and *must not* place kexec-images on this memory. Link: https://lkml.kernel.org/r/20211004093605.5830-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 16 ++++++++++++++-- kernel/kexec_file.c | 5 +++++ mm/memblock.c | 4 ++++ 3 files changed, 23 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8b6560dc7a9e..7df557b16c1e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -37,12 +37,17 @@ extern unsigned long long max_possible_pfn; * @MEMBLOCK_NOMAP: don't add to kernel direct mapping and treat as * reserved in the memory map; refer to memblock_mark_nomap() description * for further details + * @MEMBLOCK_DRIVER_MANAGED: memory region that is always detected and added + * via a driver, and never indicated in the firmware-provided memory map as + * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the + * kernel resource tree. */ enum memblock_flags { MEMBLOCK_NONE = 0x0, /* No special request */ MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */ MEMBLOCK_MIRROR = 0x2, /* mirrored region */ MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */ + MEMBLOCK_DRIVER_MANAGED = 0x8, /* always detected via a driver */ }; /** @@ -213,7 +218,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range(i, p_start, p_end) \ __for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED, \ + p_start, p_end, NULL) /** * for_each_mem_range_rev - reverse iterate through memblock areas from @@ -224,7 +230,8 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type, */ #define for_each_mem_range_rev(i, p_start, p_end) \ __for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \ - MEMBLOCK_HOTPLUG, p_start, p_end, NULL) + MEMBLOCK_HOTPLUG | MEMBLOCK_DRIVER_MANAGED,\ + p_start, p_end, NULL) /** * for_each_reserved_mem_range - iterate over all reserved memblock areas @@ -254,6 +261,11 @@ static inline bool memblock_is_nomap(struct memblock_region *m) return m->flags & MEMBLOCK_NOMAP; } +static inline bool memblock_is_driver_managed(struct memblock_region *m) +{ + return m->flags & MEMBLOCK_DRIVER_MANAGED; +} + int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn); void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 33400ff051a8..8347fc158d2b 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -556,6 +556,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, if (kbuf->image->type == KEXEC_TYPE_CRASH) return func(&crashk_res, kbuf); + /* + * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See + * IORESOURCE_SYSRAM_DRIVER_MANAGED handling in + * locate_mem_hole_callback(). + */ if (kbuf->top_down) { for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE, &mstart, &mend, NULL) { diff --git a/mm/memblock.c b/mm/memblock.c index 1b0cd8a52a13..659bf0ffb086 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -982,6 +982,10 @@ static bool should_skip_region(struct memblock_type *type, if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; + /* skip driver-managed memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) + return true; + return false; } -- cgit v1.2.3 From d2c20e51e3966bc668ef1ef21fbe90704286c8d0 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Fri, 5 Nov 2021 13:45:06 -0700 Subject: mm/highmem: remove deprecated kmap_atomic kmap_atomic() is being deprecated in favor of kmap_local_page(). Replace the uses of kmap_atomic() within the highmem code. On profiling clear_huge_page() using ftrace an improvement of 62% was observed on the below setup. Setup:- Below data has been collected on Qualcomm's SM7250 SoC THP enabled (kernel v4.19.113) with only CPU-0(Cortex-A55) and CPU-7(Cortex-A76) switched on and set to max frequency, also DDR set to perf governor. FTRACE Data:- Base data:- Number of iterations: 48 Mean of allocation time: 349.5 us std deviation: 74.5 us v4 data:- Number of iterations: 48 Mean of allocation time: 131 us std deviation: 32.7 us The following simple userspace experiment to allocate 100MB(BUF_SZ) of pages and writing to it gave us a good insight, we observed an improvement of 42% in allocation and writing timings. ------------------------------------------------------------- Test code snippet ------------------------------------------------------------- clock_start(); buf = malloc(BUF_SZ); /* Allocate 100 MB of memory */ for(i=0; i < BUF_SZ_PAGES; i++) { *((int *)(buf + (i*PAGE_SIZE))) = 1; } clock_end(); ------------------------------------------------------------- Malloc test timings for 100MB anon allocation:- Base data:- Number of iterations: 100 Mean of allocation time: 31831 us std deviation: 4286 us v4 data:- Number of iterations: 100 Mean of allocation time: 18193 us std deviation: 4915 us [willy@infradead.org: fix zero_user_segments()] Link: https://lkml.kernel.org/r/YYVhHCJcm2DM2G9u@casper.infradead.org Link: https://lkml.kernel.org/r/20210204073255.20769-2-prathu.baronia@oneplus.com Signed-off-by: Ira Weiny Signed-off-by: Prathu Baronia Cc: Thomas Gleixner Cc: Matthew Wilcox Cc: Peter Zijlstra Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/highmem.h | 28 ++++++++++++++-------------- mm/highmem.c | 6 +++--- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b4c49f9cc379..31ebee36f26c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -143,9 +143,9 @@ static inline void invalidate_kernel_vmap_range(void *vaddr, int size) #ifndef clear_user_highpage static inline void clear_user_highpage(struct page *page, unsigned long vaddr) { - void *addr = kmap_atomic(page); + void *addr = kmap_local_page(page); clear_user_page(addr, vaddr, page); - kunmap_atomic(addr); + kunmap_local(addr); } #endif @@ -177,9 +177,9 @@ alloc_zeroed_user_highpage_movable(struct vm_area_struct *vma, static inline void clear_highpage(struct page *page) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); clear_page(kaddr); - kunmap_atomic(kaddr); + kunmap_local(kaddr); } #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE @@ -202,7 +202,7 @@ static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { - void *kaddr = kmap_atomic(page); + void *kaddr = kmap_local_page(page); unsigned int i; BUG_ON(end1 > page_size(page) || end2 > page_size(page)); @@ -213,7 +213,7 @@ static inline void zero_user_segments(struct page *page, if (end2 > start2) memset(kaddr + start2, 0, end2 - start2); - kunmap_atomic(kaddr); + kunmap_local(kaddr); for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } @@ -238,11 +238,11 @@ static inline void copy_user_highpage(struct page *to, struct page *from, { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_user_page(vto, vfrom, vaddr, to); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif @@ -253,11 +253,11 @@ static inline void copy_highpage(struct page *to, struct page *from) { char *vfrom, *vto; - vfrom = kmap_atomic(from); - vto = kmap_atomic(to); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_page(vto, vfrom); - kunmap_atomic(vto); - kunmap_atomic(vfrom); + kunmap_local(vto); + kunmap_local(vfrom); } #endif diff --git a/mm/highmem.c b/mm/highmem.c index 4212ad0e4a19..eb3b8c288de4 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -383,7 +383,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned this_end = min_t(unsigned, end1, PAGE_SIZE); if (end1 > start1) { - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start1, 0, this_end - start1); } end1 -= this_end; @@ -398,7 +398,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, if (end2 > start2) { if (!kaddr) - kaddr = kmap_atomic(page + i); + kaddr = kmap_local_page(page + i); memset(kaddr + start2, 0, this_end - start2); } end2 -= this_end; @@ -406,7 +406,7 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, } if (kaddr) { - kunmap_atomic(kaddr); + kunmap_local(kaddr); flush_dcache_page(page + i); } -- cgit v1.2.3 From 53944f171a89dff4e2a3d76f42e6eedb551bb861 Mon Sep 17 00:00:00 2001 From: Stephen Kitt Date: Fri, 5 Nov 2021 13:45:18 -0700 Subject: mm: remove HARDENED_USERCOPY_FALLBACK This has served its purpose and is no longer used. All usercopy violations appear to have been handled by now, any remaining instances (or new bugs) will cause copies to be rejected. This isn't a direct revert of commit 2d891fbc3bb6 ("usercopy: Allow strict enforcement of whitelists"); since usercopy_fallback is effectively 0, the fallback handling is removed too. This also removes the usercopy_fallback module parameter on slab_common. Link: https://github.com/KSPP/linux/issues/153 Link: https://lkml.kernel.org/r/20210921061149.1091163-1-steve@sk2.org Signed-off-by: Stephen Kitt Suggested-by: Kees Cook Acked-by: Kees Cook Reviewed-by: Joel Stanley [defconfig change] Acked-by: David Rientjes Cc: Christoph Lameter Cc: Pekka Enberg Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: James Morris Cc: "Serge E . Hallyn" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/configs/skiroot_defconfig | 1 - include/linux/slab.h | 2 -- mm/slab.c | 13 ------------- mm/slab_common.c | 8 -------- mm/slub.c | 14 -------------- security/Kconfig | 14 -------------- 6 files changed, 52 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig index b806a5d3a695..c3ba614c973d 100644 --- a/arch/powerpc/configs/skiroot_defconfig +++ b/arch/powerpc/configs/skiroot_defconfig @@ -275,7 +275,6 @@ CONFIG_NLS_UTF8=y CONFIG_ENCRYPTED_KEYS=y CONFIG_SECURITY=y CONFIG_HARDENED_USERCOPY=y -# CONFIG_HARDENED_USERCOPY_FALLBACK is not set CONFIG_HARDENED_USERCOPY_PAGESPAN=y CONFIG_FORTIFY_SOURCE=y CONFIG_SECURITY_LOCKDOWN_LSM=y diff --git a/include/linux/slab.h b/include/linux/slab.h index 837cb16232ef..181045148b06 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -142,8 +142,6 @@ struct mem_cgroup; void __init kmem_cache_init(void); bool slab_is_available(void); -extern bool usercopy_fallback; - struct kmem_cache *kmem_cache_create(const char *name, unsigned int size, unsigned int align, slab_flags_t flags, void (*ctor)(void *)); diff --git a/mm/slab.c b/mm/slab.c index 64ec17a3bc2b..da132a9ae6f8 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4204,19 +4204,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, n <= cachep->useroffset - offset + cachep->usersize) return; - /* - * If the copy is still within the allocated object, produce - * a warning instead of rejecting the copy. This is intended - * to be a temporary method to find any missing usercopy - * whitelists. - */ - if (usercopy_fallback && - offset <= cachep->object_size && - n <= cachep->object_size - offset) { - usercopy_warn("SLAB object", cachep->name, to_user, offset, n); - return; - } - usercopy_abort("SLAB object", cachep->name, to_user, offset, n); } #endif /* CONFIG_HARDENED_USERCOPY */ diff --git a/mm/slab_common.c b/mm/slab_common.c index ec2bb0beed75..e5d080a93009 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -37,14 +37,6 @@ LIST_HEAD(slab_caches); DEFINE_MUTEX(slab_mutex); struct kmem_cache *kmem_cache; -#ifdef CONFIG_HARDENED_USERCOPY -bool usercopy_fallback __ro_after_init = - IS_ENABLED(CONFIG_HARDENED_USERCOPY_FALLBACK); -module_param(usercopy_fallback, bool, 0400); -MODULE_PARM_DESC(usercopy_fallback, - "WARN instead of reject usercopy whitelist violations"); -#endif - static LIST_HEAD(slab_caches_to_rcu_destroy); static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work); static DECLARE_WORK(slab_caches_to_rcu_destroy_work, diff --git a/mm/slub.c b/mm/slub.c index e9a51dcf8bf9..432145d7b4ec 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4489,7 +4489,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, { struct kmem_cache *s; unsigned int offset; - size_t object_size; bool is_kfence = is_kfence_address(ptr); ptr = kasan_reset_tag(ptr); @@ -4522,19 +4521,6 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, n <= s->useroffset - offset + s->usersize) return; - /* - * If the copy is still within the allocated object, produce - * a warning instead of rejecting the copy. This is intended - * to be a temporary method to find any missing usercopy - * whitelists. - */ - object_size = slab_ksize(s); - if (usercopy_fallback && - offset <= object_size && n <= object_size - offset) { - usercopy_warn("SLUB object", s->name, to_user, offset, n); - return; - } - usercopy_abort("SLUB object", s->name, to_user, offset, n); } #endif /* CONFIG_HARDENED_USERCOPY */ diff --git a/security/Kconfig b/security/Kconfig index 0ced7fd33e4d..d9698900c9b7 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -163,20 +163,6 @@ config HARDENED_USERCOPY or are part of the kernel text. This kills entire classes of heap overflow exploits and similar kernel memory exposures. -config HARDENED_USERCOPY_FALLBACK - bool "Allow usercopy whitelist violations to fallback to object size" - depends on HARDENED_USERCOPY - default y - help - This is a temporary option that allows missing usercopy whitelists - to be discovered via a WARN() to the kernel log, instead of - rejecting the copy, falling back to non-whitelisted hardened - usercopy that checks the slab allocation size instead of the - whitelist size. This option will be removed once it seems like - all missing usercopy whitelists have been identified and fixed. - Booting with "slab_common.usercopy_fallback=Y/N" can change - this setting. - config HARDENED_USERCOPY_PAGESPAN bool "Refuse to copy allocations that span multiple pages" depends on HARDENED_USERCOPY -- cgit v1.2.3 From a1554c002699cbc9ced2e9f44f9c1357181bead3 Mon Sep 17 00:00:00 2001 From: Mianhan Liu Date: Fri, 5 Nov 2021 13:45:21 -0700 Subject: include/linux/mm.h: move nr_free_buffer_pages from swap.h to mm.h nr_free_buffer_pages could be exposed through mm.h instead of swap.h. The advantage of this change is that it can reduce the obsolete includes. For example, net/ipv4/tcp.c wouldn't need swap.h any more since it has already included mm.h. Similarly, after checking all the other files, it comes that tcp.c, udp.c meter.c ,... follow the same rule, so these files can have swap.h removed too. Moreover, after preprocessing all the files that use nr_free_buffer_pages, it turns out that those files have already included mm.h.Thus, we can move nr_free_buffer_pages from swap.h to mm.h safely. This change will not affect the compilation of other files. Link: https://lkml.kernel.org/r/20210912133640.1624-1-liumh1@shanghaitech.edu.cn Signed-off-by: Mianhan Liu Cc: Jakub Kicinski CC: Ulf Hansson Cc: "David S . Miller" Cc: Simon Horman Cc: Pravin B Shelar Cc: Vlad Yasevich Cc: Marcelo Ricardo Leitner Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/mmc/core/mmc_test.c | 1 - include/linux/mm.h | 2 ++ include/linux/swap.h | 1 - net/ipv4/tcp.c | 1 - net/ipv4/udp.c | 1 - net/netfilter/ipvs/ip_vs_ctl.c | 1 - net/openvswitch/meter.c | 1 - net/sctp/protocol.c | 1 - 8 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c index 63524551a13a..e6a2fd2c6d5c 100644 --- a/drivers/mmc/core/mmc_test.c +++ b/drivers/mmc/core/mmc_test.c @@ -10,7 +10,6 @@ #include #include -#include /* For nr_free_buffer_pages() */ #include #include diff --git a/include/linux/mm.h b/include/linux/mm.h index 15058d9cec99..b1720aa63727 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -875,6 +875,8 @@ void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); void copy_huge_page(struct page *dst, struct page *src); +unsigned long nr_free_buffer_pages(void); + /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. diff --git a/include/linux/swap.h b/include/linux/swap.h index ba52f3a3478e..53f759a59996 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -335,7 +335,6 @@ void workingset_update_node(struct xa_node *node); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; -extern unsigned long nr_free_buffer_pages(void); /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f5c336f8b0c8..c5e07a2c6c52 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -260,7 +260,6 @@ #include #include #include -#include #include #include #include diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2fffcf2b54f3..319dd7bbfe33 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -78,7 +78,6 @@ #include #include #include -#include #include #include #include diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 29ec3ef63edc..6ea4b882435e 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 896b8f5bc885..04a060ac7fdf 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ec0f52567c16..35928fefae33 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From f39f21b3ddc7fc0f87eb6dc75ddc81b5bbfb7672 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:25 -0700 Subject: stacktrace: move filter_irq_stacks() to kernel/stacktrace.c filter_irq_stacks() has little to do with the stackdepot implementation, except that it is usually used by users (such as KASAN) of stackdepot to reduce the stack trace. However, filter_irq_stacks() itself is not useful without a stack trace as obtained by stack_trace_save() and friends. Therefore, move filter_irq_stacks() to kernel/stacktrace.c, so that new users of filter_irq_stacks() do not have to start depending on STACKDEPOT only for filter_irq_stacks(). Link: https://lkml.kernel.org/r/20210923104803.2620285-1-elver@google.com Signed-off-by: Marco Elver Acked-by: Dmitry Vyukov Cc: Alexander Potapenko Cc: Jann Horn Cc: Aleksandr Nogikh Cc: Taras Madan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 -- include/linux/stacktrace.h | 1 + kernel/stacktrace.c | 30 ++++++++++++++++++++++++++++++ lib/stackdepot.c | 24 ------------------------ 4 files changed, 31 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index b2f7e7c6ba54..d29860966bc9 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,8 +25,6 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); -unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); - #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); #else diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 9edecb494e9e..bef158815e83 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -21,6 +21,7 @@ unsigned int stack_trace_save_tsk(struct task_struct *task, unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, unsigned int size, unsigned int skipnr); unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); /* Internal interfaces. Do not use in generic code */ #ifdef CONFIG_ARCH_STACKWALK diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index 9f8117c7cfdd..9c625257023d 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -13,6 +13,7 @@ #include #include #include +#include /** * stack_trace_print - Print the entries in the stack trace @@ -373,3 +374,32 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) #endif /* CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* !CONFIG_ARCH_STACKWALK */ + +static inline bool in_irqentry_text(unsigned long ptr) +{ + return (ptr >= (unsigned long)&__irqentry_text_start && + ptr < (unsigned long)&__irqentry_text_end) || + (ptr >= (unsigned long)&__softirqentry_text_start && + ptr < (unsigned long)&__softirqentry_text_end); +} + +/** + * filter_irq_stacks - Find first IRQ stack entry in trace + * @entries: Pointer to stack trace array + * @nr_entries: Number of entries in the storage array + * + * Return: Number of trace entries until IRQ stack starts. + */ +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries) +{ + unsigned int i; + + for (i = 0; i < nr_entries; i++) { + if (in_irqentry_text(entries[i])) { + /* Include the irqentry function into the stack. */ + return i + 1; + } + } + return nr_entries; +} +EXPORT_SYMBOL_GPL(filter_irq_stacks); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index bda58597e375..09485dc5bd12 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -20,7 +20,6 @@ */ #include -#include #include #include #include @@ -371,26 +370,3 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, return __stack_depot_save(entries, nr_entries, alloc_flags, true); } EXPORT_SYMBOL_GPL(stack_depot_save); - -static inline int in_irqentry_text(unsigned long ptr) -{ - return (ptr >= (unsigned long)&__irqentry_text_start && - ptr < (unsigned long)&__irqentry_text_end) || - (ptr >= (unsigned long)&__softirqentry_text_start && - ptr < (unsigned long)&__softirqentry_text_end); -} - -unsigned int filter_irq_stacks(unsigned long *entries, - unsigned int nr_entries) -{ - unsigned int i; - - for (i = 0; i < nr_entries; i++) { - if (in_irqentry_text(entries[i])) { - /* Include the irqentry function into the stack. */ - return i + 1; - } - } - return nr_entries; -} -EXPORT_SYMBOL_GPL(filter_irq_stacks); -- cgit v1.2.3 From 07e8481d3c38f461d7b79c1d5c9afe013b162b0c Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 5 Nov 2021 13:45:46 -0700 Subject: kfence: always use static branches to guard kfence_alloc() Regardless of KFENCE mode (CONFIG_KFENCE_STATIC_KEYS: either using static keys to gate allocations, or using a simple dynamic branch), always use a static branch to avoid the dynamic branch in kfence_alloc() if KFENCE was disabled at boot. For CONFIG_KFENCE_STATIC_KEYS=n, this now avoids the dynamic branch if KFENCE was disabled at boot. To simplify, also unifies the location where kfence_allocation_gate is read-checked to just be inline in kfence_alloc(). Link: https://lkml.kernel.org/r/20211019102524.2807208-1-elver@google.com Signed-off-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jann Horn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 21 +++++++++++---------- mm/kfence/core.c | 16 +++++++--------- 2 files changed, 18 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 3fe6dd8a18c1..4b5e3679a72c 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -14,6 +14,9 @@ #ifdef CONFIG_KFENCE +#include +#include + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an @@ -22,13 +25,8 @@ #define KFENCE_POOL_SIZE ((CONFIG_KFENCE_NUM_OBJECTS + 1) * 2 * PAGE_SIZE) extern char *__kfence_pool; -#ifdef CONFIG_KFENCE_STATIC_KEYS -#include DECLARE_STATIC_KEY_FALSE(kfence_allocation_key); -#else -#include extern atomic_t kfence_allocation_gate; -#endif /** * is_kfence_address() - check if an address belongs to KFENCE pool @@ -116,13 +114,16 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags); */ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { -#ifdef CONFIG_KFENCE_STATIC_KEYS - if (static_branch_unlikely(&kfence_allocation_key)) +#if defined(CONFIG_KFENCE_STATIC_KEYS) || CONFIG_KFENCE_SAMPLE_INTERVAL == 0 + if (!static_branch_unlikely(&kfence_allocation_key)) + return NULL; #else - if (unlikely(!atomic_read(&kfence_allocation_gate))) + if (!static_branch_likely(&kfence_allocation_key)) + return NULL; #endif - return __kfence_alloc(s, size, flags); - return NULL; + if (likely(atomic_read(&kfence_allocation_gate))) + return NULL; + return __kfence_alloc(s, size, flags); } /** diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 802905b1c89b..09945784df9e 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -104,10 +104,11 @@ struct kfence_metadata kfence_metadata[CONFIG_KFENCE_NUM_OBJECTS]; static struct list_head kfence_freelist = LIST_HEAD_INIT(kfence_freelist); static DEFINE_RAW_SPINLOCK(kfence_freelist_lock); /* Lock protecting freelist. */ -#ifdef CONFIG_KFENCE_STATIC_KEYS -/* The static key to set up a KFENCE allocation. */ +/* + * The static key to set up a KFENCE allocation; or if static keys are not used + * to gate allocations, to avoid a load and compare if KFENCE is disabled. + */ DEFINE_STATIC_KEY_FALSE(kfence_allocation_key); -#endif /* Gates the allocation, ensuring only one succeeds in a given period. */ atomic_t kfence_allocation_gate = ATOMIC_INIT(1); @@ -774,6 +775,8 @@ void __init kfence_init(void) return; } + if (!IS_ENABLED(CONFIG_KFENCE_STATIC_KEYS)) + static_branch_enable(&kfence_allocation_key); WRITE_ONCE(kfence_enabled, true); queue_delayed_work(system_unbound_wq, &kfence_timer, 0); pr_info("initialized - using %lu bytes for %d objects at 0x%p-0x%p\n", KFENCE_POOL_SIZE, @@ -866,12 +869,7 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) return NULL; } - /* - * allocation_gate only needs to become non-zero, so it doesn't make - * sense to continue writing to it and pay the associated contention - * cost, in case we have a large number of concurrent allocations. - */ - if (atomic_read(&kfence_allocation_gate) || atomic_inc_return(&kfence_allocation_gate) > 1) + if (atomic_inc_return(&kfence_allocation_gate) > 1) return NULL; #ifdef CONFIG_KFENCE_STATIC_KEYS /* -- cgit v1.2.3 From d2f272b35a84ace2ef04334a9822fd726a7f061b Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:04 -0700 Subject: include/linux/damon.h: fix kernel-doc comments for 'damon_callback' A few Kernel-doc comments in 'damon.h' are broken. This fixes them. Link: https://lkml.kernel.org/r/20210917123958.3819-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index d68b67b8d458..755d70804705 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -62,7 +62,7 @@ struct damon_target { struct damon_ctx; /** - * struct damon_primitive Monitoring primitives for given use cases. + * struct damon_primitive - Monitoring primitives for given use cases. * * @init: Initialize primitive-internal data structures. * @update: Update primitive-internal data structures. @@ -108,8 +108,8 @@ struct damon_primitive { void (*cleanup)(struct damon_ctx *context); }; -/* - * struct damon_callback Monitoring events notification callbacks. +/** + * struct damon_callback - Monitoring events notification callbacks. * * @before_start: Called before starting the monitoring. * @after_sampling: Called after each sampling. -- cgit v1.2.3 From fda504fade7f124858d7022341dc46ff35b45274 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:18 -0700 Subject: mm/damon/core: account age of target regions Patch series "Implement Data Access Monitoring-based Memory Operation Schemes". Introduction ============ DAMON[1] can be used as a primitive for data access aware memory management optimizations. For that, users who want such optimizations should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. Such efforts will be inevitable for some complicated optimizations. However, in many other cases, the users would simply want the system to apply a memory management action to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB keeping only rare accesses more than 2 minutes", or "Do not use THP for a memory region larger than 2 MiB rarely accessed for more than 1 seconds". To make the works easier and non-redundant, this patchset implements a new feature of DAMON, which is called Data Access Monitoring-based Operation Schemes (DAMOS). Using the feature, users can describe the normal schemes in a simple way and ask DAMON to execute those on its own. [1] https://damonitor.github.io Evaluations =========== DAMOS is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the showcase web site's evaluation document[1] for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/v34/vm/damon/eval.html Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://git.kernel.org/sj/h/damon/for-v5.4.y - For v5.10.y: https://git.kernel.org/sj/h/damon/for-v5.10.y Sequence Of Patches =================== The 1st patch accounts age of each region. The 2nd patch implements the core of the DAMON-based operation schemes feature. The 3rd patch makes the default monitoring primitives for virtual address spaces to support the schemes. From this point, the kernel space users can use DAMOS. The 4th patch exports the feature to the user space via the debugfs interface. The 5th patch implements schemes statistics feature for easier tuning of the schemes and runtime access pattern analysis, and the 6th patch adds selftests for these changes. Finally, the 7th patch documents this new feature. This patch (of 7): DAMON can be used for data access pattern aware memory management optimizations. For that, users should run DAMON, read the monitoring results, analyze it, plan a new memory management scheme, and apply the new scheme by themselves. It would not be too hard, but still require some level of effort. For complicated cases, this effort is inevitable. That said, in many cases, users would simply want to apply an actions to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". For such optimizations, users will need to first account the age of each region themselves. To reduce such efforts, this implements a simple age account of each region in DAMON. For each aggregation step, DAMON compares the access frequency with that from last aggregation and reset the age of the region if the change is significant. Else, the age is incremented. Also, in case of the merge of regions, the region size-weighted average of the ages is set as the age of merged new region. Link: https://lkml.kernel.org/r/20211001125604.29660-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211001125604.29660-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rienjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 ++++++++++ mm/damon/core.c | 13 +++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 755d70804705..3e8215debbd4 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -31,12 +31,22 @@ struct damon_addr_range { * @sampling_addr: Address of the sample for the next access check. * @nr_accesses: Access frequency of this region. * @list: List head for siblings. + * @age: Age of this region. + * + * @age is initially zero, increased for each aggregation interval, and reset + * to zero again if the access frequency is significantly changed. If two + * regions are merged into a new region, both @nr_accesses and @age of the new + * region are set as region size-weighted average of those of the two regions. */ struct damon_region { struct damon_addr_range ar; unsigned long sampling_addr; unsigned int nr_accesses; struct list_head list; + + unsigned int age; +/* private: Internal value for age calculation. */ + unsigned int last_nr_accesses; }; /** diff --git a/mm/damon/core.c b/mm/damon/core.c index d993db50280c..3efbe80779db 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -45,6 +45,9 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) region->nr_accesses = 0; INIT_LIST_HEAD(®ion->list); + region->age = 0; + region->last_nr_accesses = 0; + return region; } @@ -444,6 +447,7 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) damon_for_each_region(r, t) { trace_damon_aggregated(t, r, damon_nr_regions(t)); + r->last_nr_accesses = r->nr_accesses; r->nr_accesses = 0; } } @@ -461,6 +465,7 @@ static void damon_merge_two_regions(struct damon_target *t, l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) / (sz_l + sz_r); + l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r); l->ar.end = r->ar.end; damon_destroy_region(r, t); } @@ -480,6 +485,11 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres, struct damon_region *r, *prev = NULL, *next; damon_for_each_region_safe(r, next, t) { + if (diff_of(r->nr_accesses, r->last_nr_accesses) > thres) + r->age = 0; + else + r->age++; + if (prev && prev->ar.end == r->ar.start && diff_of(prev->nr_accesses, r->nr_accesses) <= thres && sz_damon_region(prev) + sz_damon_region(r) <= sz_limit) @@ -527,6 +537,9 @@ static void damon_split_region_at(struct damon_ctx *ctx, r->ar.end = new->ar.start; + new->age = r->age; + new->last_nr_accesses = r->last_nr_accesses; + damon_insert_region(new, r, damon_next_region(r), t); } -- cgit v1.2.3 From 1f366e421c8f69583ed37b56d86e3747331869c3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:22 -0700 Subject: mm/damon/core: implement DAMON-based Operation Schemes (DAMOS) In many cases, users might use DAMON for simple data access aware memory management optimizations such as applying an operation scheme to a memory region of a specific size having a specific access frequency for a specific time. For example, "page out a memory region larger than 100 MiB but having a low access frequency more than 10 minutes", or "Use THP for a memory region larger than 2 MiB having a high access frequency for more than 2 seconds". Most simple form of the solution would be doing offline data access pattern profiling using DAMON and modifying the application source code or system configuration based on the profiling results. Or, developing a daemon constructed with two modules (one for access monitoring and the other for applying memory management actions via mlock(), madvise(), sysctl, etc) is imaginable. To avoid users spending their time for implementation of such simple data access monitoring-based operation schemes, this makes DAMON to handle such schemes directly. With this change, users can simply specify their desired schemes to DAMON. Then, DAMON will automatically apply the schemes to the user-specified target processes. Each of the schemes is composed with conditions for filtering of the target memory regions and desired memory management action for the target. Specifically, the format is:: The filtering conditions are size of memory region, number of accesses to the region monitored by DAMON, and the age of the region. The age of region is incremented periodically but reset when its addresses or access frequency has significantly changed or the action of a scheme was applied. For the action, current implementation supports a few of madvise()-like hints, ``WILLNEED``, ``COLD``, ``PAGEOUT``, ``HUGEPAGE``, and ``NOHUGEPAGE``. Because DAMON supports various address spaces and application of the actions to a monitoring target region is dependent to the type of the target address space, the application code should be implemented by each primitives and registered to the framework. Note that this only implements the framework part. Following commit will implement the action applications for virtual address spaces primitives. Link: https://lkml.kernel.org/r/20211001125604.29660-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 66 ++++++++++++++++++++++++++++++ mm/damon/core.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 175 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3e8215debbd4..dbe18b0fb795 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -69,6 +69,48 @@ struct damon_target { struct list_head list; }; +/** + * enum damos_action - Represents an action of a Data Access Monitoring-based + * Operation Scheme. + * + * @DAMOS_WILLNEED: Call ``madvise()`` for the region with MADV_WILLNEED. + * @DAMOS_COLD: Call ``madvise()`` for the region with MADV_COLD. + * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. + * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. + * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + */ +enum damos_action { + DAMOS_WILLNEED, + DAMOS_COLD, + DAMOS_PAGEOUT, + DAMOS_HUGEPAGE, + DAMOS_NOHUGEPAGE, +}; + +/** + * struct damos - Represents a Data Access Monitoring-based Operation Scheme. + * @min_sz_region: Minimum size of target regions. + * @max_sz_region: Maximum size of target regions. + * @min_nr_accesses: Minimum ``->nr_accesses`` of target regions. + * @max_nr_accesses: Maximum ``->nr_accesses`` of target regions. + * @min_age_region: Minimum age of target regions. + * @max_age_region: Maximum age of target regions. + * @action: &damo_action to be applied to the target regions. + * @list: List head for siblings. + * + * Note that both the minimums and the maximums are inclusive. + */ +struct damos { + unsigned long min_sz_region; + unsigned long max_sz_region; + unsigned int min_nr_accesses; + unsigned int max_nr_accesses; + unsigned int min_age_region; + unsigned int max_age_region; + enum damos_action action; + struct list_head list; +}; + struct damon_ctx; /** @@ -79,6 +121,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. * @@ -104,6 +147,9 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @apply_scheme is called from @kdamond when a region for user provided + * DAMON-based operation scheme is found. It should apply the scheme's action + * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -114,6 +160,8 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); }; @@ -192,6 +240,7 @@ struct damon_callback { * @min_nr_regions: The minimum number of adaptive monitoring regions. * @max_nr_regions: The maximum number of adaptive monitoring regions. * @adaptive_targets: Head of monitoring targets (&damon_target) list. + * @schemes: Head of schemes (&damos) list. */ struct damon_ctx { unsigned long sample_interval; @@ -213,6 +262,7 @@ struct damon_ctx { unsigned long min_nr_regions; unsigned long max_nr_regions; struct list_head adaptive_targets; + struct list_head schemes; }; #define damon_next_region(r) \ @@ -233,6 +283,12 @@ struct damon_ctx { #define damon_for_each_target_safe(t, next, ctx) \ list_for_each_entry_safe(t, next, &(ctx)->adaptive_targets, list) +#define damon_for_each_scheme(s, ctx) \ + list_for_each_entry(s, &(ctx)->schemes, list) + +#define damon_for_each_scheme_safe(s, next, ctx) \ + list_for_each_entry_safe(s, next, &(ctx)->schemes, list) + #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); @@ -242,6 +298,14 @@ inline void damon_insert_region(struct damon_region *r, void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action); +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); +void damon_destroy_scheme(struct damos *s); + struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); void damon_free_target(struct damon_target *t); @@ -255,6 +319,8 @@ int damon_set_targets(struct damon_ctx *ctx, int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, unsigned long aggr_int, unsigned long primitive_upd_int, unsigned long min_nr_reg, unsigned long max_nr_reg); +int damon_set_schemes(struct damon_ctx *ctx, + struct damos **schemes, ssize_t nr_schemes); int damon_nr_running_ctxs(void); int damon_start(struct damon_ctx **ctxs, int nr_ctxs); diff --git a/mm/damon/core.c b/mm/damon/core.c index 3efbe80779db..0ed97b21cbb6 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -85,6 +85,50 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t) damon_free_region(r); } +struct damos *damon_new_scheme( + unsigned long min_sz_region, unsigned long max_sz_region, + unsigned int min_nr_accesses, unsigned int max_nr_accesses, + unsigned int min_age_region, unsigned int max_age_region, + enum damos_action action) +{ + struct damos *scheme; + + scheme = kmalloc(sizeof(*scheme), GFP_KERNEL); + if (!scheme) + return NULL; + scheme->min_sz_region = min_sz_region; + scheme->max_sz_region = max_sz_region; + scheme->min_nr_accesses = min_nr_accesses; + scheme->max_nr_accesses = max_nr_accesses; + scheme->min_age_region = min_age_region; + scheme->max_age_region = max_age_region; + scheme->action = action; + INIT_LIST_HEAD(&scheme->list); + + return scheme; +} + +void damon_add_scheme(struct damon_ctx *ctx, struct damos *s) +{ + list_add_tail(&s->list, &ctx->schemes); +} + +static void damon_del_scheme(struct damos *s) +{ + list_del(&s->list); +} + +static void damon_free_scheme(struct damos *s) +{ + kfree(s); +} + +void damon_destroy_scheme(struct damos *s) +{ + damon_del_scheme(s); + damon_free_scheme(s); +} + /* * Construct a damon_target struct * @@ -156,6 +200,7 @@ struct damon_ctx *damon_new_ctx(void) ctx->max_nr_regions = 1000; INIT_LIST_HEAD(&ctx->adaptive_targets); + INIT_LIST_HEAD(&ctx->schemes); return ctx; } @@ -175,7 +220,13 @@ static void damon_destroy_targets(struct damon_ctx *ctx) void damon_destroy_ctx(struct damon_ctx *ctx) { + struct damos *s, *next_s; + damon_destroy_targets(ctx); + + damon_for_each_scheme_safe(s, next_s, ctx) + damon_destroy_scheme(s); + kfree(ctx); } @@ -250,6 +301,30 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int, return 0; } +/** + * damon_set_schemes() - Set data access monitoring based operation schemes. + * @ctx: monitoring context + * @schemes: array of the schemes + * @nr_schemes: number of entries in @schemes + * + * This function should not be called while the kdamond of the context is + * running. + * + * Return: 0 if success, or negative error code otherwise. + */ +int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes, + ssize_t nr_schemes) +{ + struct damos *s, *next; + ssize_t i; + + damon_for_each_scheme_safe(s, next, ctx) + damon_destroy_scheme(s); + for (i = 0; i < nr_schemes; i++) + damon_add_scheme(ctx, schemes[i]); + return 0; +} + /** * damon_nr_running_ctxs() - Return number of currently running contexts. */ @@ -453,6 +528,39 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } +static void damon_do_apply_schemes(struct damon_ctx *c, + struct damon_target *t, + struct damon_region *r) +{ + struct damos *s; + unsigned long sz; + + damon_for_each_scheme(s, c) { + sz = r->ar.end - r->ar.start; + if (sz < s->min_sz_region || s->max_sz_region < sz) + continue; + if (r->nr_accesses < s->min_nr_accesses || + s->max_nr_accesses < r->nr_accesses) + continue; + if (r->age < s->min_age_region || s->max_age_region < r->age) + continue; + if (c->primitive.apply_scheme) + c->primitive.apply_scheme(c, t, r, s); + r->age = 0; + } +} + +static void kdamond_apply_schemes(struct damon_ctx *c) +{ + struct damon_target *t; + struct damon_region *r; + + damon_for_each_target(t, c) { + damon_for_each_region(r, t) + damon_do_apply_schemes(c, t, r); + } +} + #define sz_damon_region(r) (r->ar.end - r->ar.start) /* @@ -693,6 +801,7 @@ static int kdamond_fn(void *data) if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) set_kdamond_stop(ctx); + kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); if (ctx->primitive.reset_aggregated) -- cgit v1.2.3 From 6dea8add4d2875b80843e4a4c8acd334a4db8c8f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:25 -0700 Subject: mm/damon/vaddr: support DAMON-based Operation Schemes This makes DAMON's default primitives for virtual address spaces to support DAMON-based Operation Schemes (DAMOS) by implementing actions application functions and registering it to the monitoring context. The implementation simply links 'madvise()' for related DAMOS actions. That is, 'madvise(MADV_WILLNEED)' is called for 'WILLNEED' DAMOS action and similar for other actions ('COLD', 'PAGEOUT', 'HUGEPAGE', 'NOHUGEPAGE'). So, the kernel space DAMON users can now use the DAMON-based optimizations with only small amount of code. Link: https://lkml.kernel.org/r/20211001125604.29660-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ mm/damon/vaddr.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index dbe18b0fb795..be6b6e81e8ee 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -337,6 +337,8 @@ void damon_va_prepare_access_checks(struct damon_ctx *ctx); unsigned int damon_va_check_accesses(struct damon_ctx *ctx); bool damon_va_target_valid(void *t); void damon_va_cleanup(struct damon_ctx *ctx); +int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 58c1fb2aafa9..3e1c74d36bab 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "damon-va: " fmt +#include #include #include #include @@ -658,6 +659,60 @@ bool damon_va_target_valid(void *target) return false; } +#ifndef CONFIG_ADVISE_SYSCALLS +static int damos_madvise(struct damon_target *target, struct damon_region *r, + int behavior) +{ + return -EINVAL; +} +#else +static int damos_madvise(struct damon_target *target, struct damon_region *r, + int behavior) +{ + struct mm_struct *mm; + int ret = -ENOMEM; + + mm = damon_get_mm(target); + if (!mm) + goto out; + + ret = do_madvise(mm, PAGE_ALIGN(r->ar.start), + PAGE_ALIGN(r->ar.end - r->ar.start), behavior); + mmput(mm); +out: + return ret; +} +#endif /* CONFIG_ADVISE_SYSCALLS */ + +int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + int madv_action; + + switch (scheme->action) { + case DAMOS_WILLNEED: + madv_action = MADV_WILLNEED; + break; + case DAMOS_COLD: + madv_action = MADV_COLD; + break; + case DAMOS_PAGEOUT: + madv_action = MADV_PAGEOUT; + break; + case DAMOS_HUGEPAGE: + madv_action = MADV_HUGEPAGE; + break; + case DAMOS_NOHUGEPAGE: + madv_action = MADV_NOHUGEPAGE; + break; + default: + pr_warn("Wrong action %d\n", scheme->action); + return -EINVAL; + } + + return damos_madvise(t, r, madv_action); +} + void damon_va_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = damon_va_init; @@ -667,6 +722,7 @@ void damon_va_set_primitives(struct damon_ctx *ctx) ctx->primitive.reset_aggregated = NULL; ctx->primitive.target_valid = damon_va_target_valid; ctx->primitive.cleanup = NULL; + ctx->primitive.apply_scheme = damon_va_apply_scheme; } #include "vaddr-test.h" -- cgit v1.2.3 From 2f0b548c9f03a78f4ce6ab48986e3108028936a6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:32 -0700 Subject: mm/damon/schemes: implement statistics feature To tune the DAMON-based operation schemes, knowing how many and how large regions are affected by each of the schemes will be helful. Those stats could be used for not only the tuning, but also monitoring of the working set size and the number of regions, if the scheme does not change the program behavior too much. For the reason, this implements the statistics for the schemes. The total number and size of the regions that each scheme is applied are exported to users via '->stat_count' and '->stat_sz' of 'struct damos'. Admins can also check the number by reading 'schemes' debugfs file. The last two integers now represents the stats. To allow collecting the stats without changing the program behavior, this also adds new scheme action, 'DAMOS_STAT'. Note that 'DAMOS_STAT' is not only making no memory operation actions, but also does not reset the age of regions. Link: https://lkml.kernel.org/r/20211001125604.29660-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 +++++++++- mm/damon/core.c | 7 ++++++- mm/damon/dbgfs.c | 5 +++-- mm/damon/vaddr.c | 2 ++ 4 files changed, 20 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index be6b6e81e8ee..f301bb53381c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -78,6 +78,7 @@ struct damon_target { * @DAMOS_PAGEOUT: Call ``madvise()`` for the region with MADV_PAGEOUT. * @DAMOS_HUGEPAGE: Call ``madvise()`` for the region with MADV_HUGEPAGE. * @DAMOS_NOHUGEPAGE: Call ``madvise()`` for the region with MADV_NOHUGEPAGE. + * @DAMOS_STAT: Do nothing but count the stat. */ enum damos_action { DAMOS_WILLNEED, @@ -85,6 +86,7 @@ enum damos_action { DAMOS_PAGEOUT, DAMOS_HUGEPAGE, DAMOS_NOHUGEPAGE, + DAMOS_STAT, /* Do nothing but only record the stat */ }; /** @@ -96,9 +98,13 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @stat_count: Total number of regions that this scheme is applied. + * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * Note that both the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON applies @action to monitoring target + * regions fit in the condition and updates the statistics. Note that both + * the minimums and the maximums are inclusive. */ struct damos { unsigned long min_sz_region; @@ -108,6 +114,8 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + unsigned long stat_count; + unsigned long stat_sz; struct list_head list; }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 0ed97b21cbb6..2f6785737902 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -103,6 +103,8 @@ struct damos *damon_new_scheme( scheme->min_age_region = min_age_region; scheme->max_age_region = max_age_region; scheme->action = action; + scheme->stat_count = 0; + scheme->stat_sz = 0; INIT_LIST_HEAD(&scheme->list); return scheme; @@ -544,9 +546,12 @@ static void damon_do_apply_schemes(struct damon_ctx *c, continue; if (r->age < s->min_age_region || s->max_age_region < r->age) continue; + s->stat_count++; + s->stat_sz += sz; if (c->primitive.apply_scheme) c->primitive.apply_scheme(c, t, r, s); - r->age = 0; + if (s->action != DAMOS_STAT) + r->age = 0; } } diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 78b7a04490c5..28d6abf27763 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -106,11 +106,11 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) damon_for_each_scheme(s, c) { rc = scnprintf(&buf[written], len - written, - "%lu %lu %u %u %u %u %d\n", + "%lu %lu %u %u %u %u %d %lu %lu\n", s->min_sz_region, s->max_sz_region, s->min_nr_accesses, s->max_nr_accesses, s->min_age_region, s->max_age_region, - s->action); + s->action, s->stat_count, s->stat_sz); if (!rc) return -ENOMEM; @@ -159,6 +159,7 @@ static bool damos_action_valid(int action) case DAMOS_PAGEOUT: case DAMOS_HUGEPAGE: case DAMOS_NOHUGEPAGE: + case DAMOS_STAT: return true; default: return false; diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 3e1c74d36bab..953c145b4f08 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -705,6 +705,8 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, case DAMOS_NOHUGEPAGE: madv_action = MADV_NOHUGEPAGE; break; + case DAMOS_STAT: + return 0; default: pr_warn("Wrong action %d\n", scheme->action); return -EINVAL; -- cgit v1.2.3 From a28397beb55b68bd0f15c6778540e8ae1bc26d21 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:46:56 -0700 Subject: mm/damon: implement primitives for physical address space monitoring This implements the monitoring primitives for the physical memory address space. Internally, it uses the PTE Accessed bit, similar to that of the virtual address spaces monitoring primitives. It supports only user memory pages, as idle pages tracking does. If the monitoring target physical memory address range contains non-user memory pages, access check of the pages will do nothing but simply treat the pages as not accessed. Link: https://lkml.kernel.org/r/20211012205711.29216-6-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Brendan Higgins Cc: David Hildenbrand Cc: David Rienjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 10 +++ mm/damon/Kconfig | 8 ++ mm/damon/Makefile | 1 + mm/damon/paddr.c | 224 ++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 243 insertions(+) create mode 100644 mm/damon/paddr.c (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index f301bb53381c..715dadd21f7c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -351,4 +351,14 @@ void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ +#ifdef CONFIG_DAMON_PADDR + +/* Monitoring primitives for the physical memory address space */ +void damon_pa_prepare_access_checks(struct damon_ctx *ctx); +unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); +bool damon_pa_target_valid(void *t); +void damon_pa_set_primitives(struct damon_ctx *ctx); + +#endif /* CONFIG_DAMON_PADDR */ + #endif /* _DAMON_H */ diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig index ba8898c7eb8e..2a5923be631e 100644 --- a/mm/damon/Kconfig +++ b/mm/damon/Kconfig @@ -32,6 +32,14 @@ config DAMON_VADDR This builds the default data access monitoring primitives for DAMON that work for virtual address spaces. +config DAMON_PADDR + bool "Data access monitoring primitives for the physical address space" + depends on DAMON && MMU + select PAGE_IDLE_FLAG + help + This builds the default data access monitoring primitives for DAMON + that works for the physical address space. + config DAMON_VADDR_KUNIT_TEST bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS depends on DAMON_VADDR && KUNIT=y diff --git a/mm/damon/Makefile b/mm/damon/Makefile index 99b1bfe01ff5..8d9b0df79702 100644 --- a/mm/damon/Makefile +++ b/mm/damon/Makefile @@ -2,4 +2,5 @@ obj-$(CONFIG_DAMON) := core.o obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o +obj-$(CONFIG_DAMON_PADDR) += prmtv-common.o paddr.o obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c new file mode 100644 index 000000000000..d7a2ecd09ed0 --- /dev/null +++ b/mm/damon/paddr.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DAMON Primitives for The Physical Address Space + * + * Author: SeongJae Park + */ + +#define pr_fmt(fmt) "damon-pa: " fmt + +#include +#include +#include +#include + +#include "prmtv-common.h" + +static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) + damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr); + else + damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr); + } + return true; +} + +static void damon_pa_mkold(unsigned long paddr) +{ + struct page *page = damon_get_page(PHYS_PFN(paddr)); + struct rmap_walk_control rwc = { + .rmap_one = __damon_pa_mkold, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page) + return; + + if (!page_mapped(page) || !page_rmapping(page)) { + set_page_idle(page); + goto out; + } + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) + goto out; + + rmap_walk(page, &rwc); + + if (need_lock) + unlock_page(page); + +out: + put_page(page); +} + +static void __damon_pa_prepare_access_check(struct damon_ctx *ctx, + struct damon_region *r) +{ + r->sampling_addr = damon_rand(r->ar.start, r->ar.end); + + damon_pa_mkold(r->sampling_addr); +} + +void damon_pa_prepare_access_checks(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) + __damon_pa_prepare_access_check(ctx, r); + } +} + +struct damon_pa_access_chk_result { + unsigned long page_sz; + bool accessed; +}; + +static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma, + unsigned long addr, void *arg) +{ + struct damon_pa_access_chk_result *result = arg; + struct page_vma_mapped_walk pvmw = { + .page = page, + .vma = vma, + .address = addr, + }; + + result->accessed = false; + result->page_sz = PAGE_SIZE; + while (page_vma_mapped_walk(&pvmw)) { + addr = pvmw.address; + if (pvmw.pte) { + result->accessed = pte_young(*pvmw.pte) || + !page_is_idle(page) || + mmu_notifier_test_young(vma->vm_mm, addr); + } else { +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + result->accessed = pmd_young(*pvmw.pmd) || + !page_is_idle(page) || + mmu_notifier_test_young(vma->vm_mm, addr); + result->page_sz = ((1UL) << HPAGE_PMD_SHIFT); +#else + WARN_ON_ONCE(1); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + } + if (result->accessed) { + page_vma_mapped_walk_done(&pvmw); + break; + } + } + + /* If accessed, stop walking */ + return !result->accessed; +} + +static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz) +{ + struct page *page = damon_get_page(PHYS_PFN(paddr)); + struct damon_pa_access_chk_result result = { + .page_sz = PAGE_SIZE, + .accessed = false, + }; + struct rmap_walk_control rwc = { + .arg = &result, + .rmap_one = __damon_pa_young, + .anon_lock = page_lock_anon_vma_read, + }; + bool need_lock; + + if (!page) + return false; + + if (!page_mapped(page) || !page_rmapping(page)) { + if (page_is_idle(page)) + result.accessed = false; + else + result.accessed = true; + put_page(page); + goto out; + } + + need_lock = !PageAnon(page) || PageKsm(page); + if (need_lock && !trylock_page(page)) { + put_page(page); + return NULL; + } + + rmap_walk(page, &rwc); + + if (need_lock) + unlock_page(page); + put_page(page); + +out: + *page_sz = result.page_sz; + return result.accessed; +} + +static void __damon_pa_check_access(struct damon_ctx *ctx, + struct damon_region *r) +{ + static unsigned long last_addr; + static unsigned long last_page_sz = PAGE_SIZE; + static bool last_accessed; + + /* If the region is in the last checked page, reuse the result */ + if (ALIGN_DOWN(last_addr, last_page_sz) == + ALIGN_DOWN(r->sampling_addr, last_page_sz)) { + if (last_accessed) + r->nr_accesses++; + return; + } + + last_accessed = damon_pa_young(r->sampling_addr, &last_page_sz); + if (last_accessed) + r->nr_accesses++; + + last_addr = r->sampling_addr; +} + +unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) +{ + struct damon_target *t; + struct damon_region *r; + unsigned int max_nr_accesses = 0; + + damon_for_each_target(t, ctx) { + damon_for_each_region(r, t) { + __damon_pa_check_access(ctx, r); + max_nr_accesses = max(r->nr_accesses, max_nr_accesses); + } + } + + return max_nr_accesses; +} + +bool damon_pa_target_valid(void *t) +{ + return true; +} + +void damon_pa_set_primitives(struct damon_ctx *ctx) +{ + ctx->primitive.init = NULL; + ctx->primitive.update = NULL; + ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks; + ctx->primitive.check_accesses = damon_pa_check_accesses; + ctx->primitive.reset_aggregated = NULL; + ctx->primitive.target_valid = damon_pa_target_valid; + ctx->primitive.cleanup = NULL; + ctx->primitive.apply_scheme = NULL; +} -- cgit v1.2.3 From 57223ac295845b1d72ec1bd02b5fab992b77a021 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:13 -0700 Subject: mm/damon/paddr: support the pageout scheme Introduction ============ This patchset 1) makes the engine for general data access pattern-oriented memory management (DAMOS) be more useful for production environments, and 2) implements a static kernel module for lightweight proactive reclamation using the engine. Proactive Reclamation --------------------- On general memory over-committed systems, proactively reclaiming cold pages helps saving memory and reducing latency spikes that incurred by the direct reclaim or the CPU consumption of kswapd, while incurring only minimal performance degradation[2]. A Free Pages Reporting[8] based memory over-commit virtualization system would be one more specific use case. In the system, the guest VMs reports their free memory to host, and the host reallocates the reported memory to other guests. As a result, the system's memory utilization can be maximized. However, the guests could be not so memory-frugal, because some kernel subsystems and user-space applications are designed to use as much memory as available. Then, guests would report only small amount of free memory to host, results in poor memory utilization. Running the proactive reclamation in such guests could help mitigating this problem. Google has also implemented this idea and using it in their data center. They further proposed upstreaming it in LSFMM'19, and "the general consensus was that, while this sort of proactive reclaim would be useful for a number of users, the cost of this particular solution was too high to consider merging it upstream"[3]. The cost mainly comes from the coldness tracking. Roughly speaking, the implementation periodically scans the 'Accessed' bit of each page. For the reason, the overhead linearly increases as the size of the memory and the scanning frequency grows. As a result, Google is known to dedicating one CPU for the work. That's a reasonable option to someone like Google, but it wouldn't be so to some others. DAMON and DAMOS: An engine for data access pattern-oriented memory management ----------------------------------------------------------------------------- DAMON[4] is a framework for general data access monitoring. Its adaptive monitoring overhead control feature minimizes its monitoring overhead. It also let the upper-bound of the overhead be configurable by clients, regardless of the size of the monitoring target memory. While monitoring 70 GiB memory of a production system every 5 milliseconds, it consumes less than 1% single CPU time. For this, it could sacrify some of the quality of the monitoring results. Nevertheless, the lower-bound of the quality is configurable, and it uses a best-effort algorithm for better quality. Our test results[5] show the quality is practical enough. From the production system monitoring, we were able to find a 4 KiB region in the 70 GiB memory that shows highest access frequency. We normally don't monitor the data access pattern just for fun but to improve something like memory management. Proactive reclamation is one such usage. For such general cases, DAMON provides a feature called DAMon-based Operation Schemes (DAMOS)[6]. It makes DAMON an engine for general data access pattern oriented memory management. Using this, clients can ask DAMON to find memory regions of specific data access pattern and apply some memory management action (e.g., page out, move to head of the LRU list, use huge page, ...). We call the request 'scheme'. Proactive Reclamation on top of DAMON/DAMOS ------------------------------------------- Therefore, by using DAMON for the cold pages detection, the proactive reclamation's monitoring overhead issue can be solved. Actually, we previously implemented a version of proactive reclamation using DAMOS and achieved noticeable improvements with our evaluation setup[5]. Nevertheless, it more for a proof-of-concept, rather than production uses. It supports only virtual address spaces of processes, and require additional tuning efforts for given workloads and the hardware. For the tuning, we introduced a simple auto-tuning user space tool[8]. Google is also known to using a ML-based similar approach for their fleets[2]. But, making it just works with intuitive knobs in the kernel would be helpful for general users. To this end, this patchset improves DAMOS to be ready for such production usages, and implements another version of the proactive reclamation, namely DAMON_RECLAIM, on top of it. DAMOS Improvements: Aggressiveness Control, Prioritization, and Watermarks -------------------------------------------------------------------------- First of all, the current version of DAMOS supports only virtual address spaces. This patchset makes it supports the physical address space for the page out action. Next major problem of the current version of DAMOS is the lack of the aggressiveness control, which can results in arbitrary overhead. For example, if huge memory regions having the data access pattern of interest are found, applying the requested action to all of the regions could incur significant overhead. It can be controlled by tuning the target data access pattern with manual or automated approaches[2,7]. But, some people would prefer the kernel to just work with only intuitive tuning or default values. For such cases, this patchset implements a safeguard, namely time/size quota. Using this, the clients can specify up to how much time can be used for applying the action, and/or up to how much memory regions the action can be applied within a user-specified time duration. A followup question is, to which memory regions should the action applied within the limits? We implement a simple regions prioritization mechanism for each action and make DAMOS to apply the action to high priority regions first. It also allows clients tune the prioritization mechanism to use different weights for size, access frequency, and age of memory regions. This means we could use not only LRU but also LFU or some fancy algorithms like CAR[9] with lightweight overhead. Though DAMON is lightweight, someone would want to remove even the cold pages monitoring overhead when it is unnecessary. Currently, it should manually turned on and off by clients, but some clients would simply want to turn it on and off based on some metrics like free memory ratio or memory fragmentation. For such cases, this patchset implements a watermarks-based automatic activation feature. It allows the clients configure the metric of their interest, and three watermarks of the metric. If the metric is higher than the high watermark or lower than the low watermark, the scheme is deactivated. If the metric is lower than the mid watermark but higher than the low watermark, the scheme is activated. DAMON-based Reclaim ------------------- Using the improved version of DAMOS, this patchset implements a static kernel module called 'damon_reclaim'. It finds memory regions that didn't accessed for specific time duration and page out. Consuming too much CPU for the paging out operations, or doing pageout too frequently can be critical for systems configuring their swap devices with software-defined in-memory block devices like zram/zswap or total number of writes limited devices like SSDs, respectively. To avoid the problems, the time/size quotas can be configured. Under the quotas, it pages out memory regions that didn't accessed longer first. Also, to remove the monitoring overhead under peaceful situation, and to fall back to the LRU-list based page granularity reclamation when it doesn't make progress, the three watermarks based activation mechanism is used, with the free memory ratio as the watermark metric. For convenient configurations, it provides several module parameters. Using these, sysadmins can enable/disable it, and tune its parameters including the coldness identification time threshold, the time/size quotas and the three watermarks. Evaluation ========== In short, DAMON_RECLAIM with 50ms/s time quota and regions prioritization on v5.15-rc5 Linux kernel with ZRAM swap device achieves 38.58% memory saving with only 1.94% runtime overhead. For this, DAMON_RECLAIM consumes only 4.97% of single CPU time. Setup ----- We evaluate DAMON_RECLAIM to show how each of the DAMOS improvements make effect. For this, we measure DAMON_RECLAIM's CPU consumption, entire system memory footprint, total number of major page faults, and runtime of 24 realistic workloads in PARSEC3 and SPLASH-2X benchmark suites on my QEMU/KVM based virtual machine. The virtual machine runs on an i3.metal AWS instance, has 130GiB memory, and runs a linux kernel built on latest -mm tree[1] plus this patchset. It also utilizes a 4 GiB ZRAM swap device. We repeats the measurement 5 times and use averages. [1] https://github.com/hnaz/linux-mm/tree/v5.15-rc5-mmots-2021-10-13-19-55 Detailed Results ---------------- The results are summarized in the below table. With coldness identification threshold of 5 seconds, DAMON_RECLAIM without the time quota-based speed limit achieves 47.21% memory saving, but incur 4.59% runtime slowdown to the workloads on average. For this, DAMON_RECLAIM consumes about 11.28% single CPU time. Applying time quotas of 200ms/s, 50ms/s, and 10ms/s without the regions prioritization reduces the slowdown to 4.89%, 2.65%, and 1.5%, respectively. Time quota of 200ms/s (20%) makes no real change compared to the quota unapplied version, because the quota unapplied version consumes only 11.28% CPU time. DAMON_RECLAIM's CPU utilization also similarly reduced: 11.24%, 5.51%, and 2.01% of single CPU time. That is, the overhead is proportional to the speed limit. Nevertheless, it also reduces the memory saving because it becomes less aggressive. In detail, the three variants show 48.76%, 37.83%, and 7.85% memory saving, respectively. Applying the regions prioritization (page out regions that not accessed longer first within the time quota) further reduces the performance degradation. Runtime slowdowns and total number of major page faults increase has been 4.89%/218,690% -> 4.39%/166,136% (200ms/s), 2.65%/111,886% -> 1.94%/59,053% (50ms/s), and 1.5%/34,973.40% -> 2.08%/8,781.75% (10ms/s). The runtime under 10ms/s time quota has increased with prioritization, but apparently that's under the margin of error. time quota prioritization memory_saving cpu_util slowdown pgmajfaults overhead N N 47.21% 11.28% 4.59% 194,802% 200ms/s N 48.76% 11.24% 4.89% 218,690% 50ms/s N 37.83% 5.51% 2.65% 111,886% 10ms/s N 7.85% 2.01% 1.5% 34,793.40% 200ms/s Y 50.08% 10.38% 4.39% 166,136% 50ms/s Y 38.58% 4.97% 1.94% 59,053% 10ms/s Y 3.63% 1.73% 2.08% 8,781.75% Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree (v5.15-rc5-mmots-2021-10-13-19-55). You can also clone the complete git tree from: $ git clone git://github.com/sjp38/linux -b damon_reclaim/patches/v1 The web is also available: https://git.kernel.org/pub/scm/linux/kernel/git/sj/linux.git/tag/?h=damon_reclaim/patches/v1 Sequence Of Patches =================== The first patch makes DAMOS support the physical address space for the page out action. Following five patches (patches 2-6) implement the time/size quotas. Next four patches (patches 7-10) implement the memory regions prioritization within the limit. Then, three following patches (patches 11-13) implement the watermarks-based schemes activation. Finally, the last two patches (patches 14-15) implement and document the DAMON-based reclamation using the advanced DAMOS. [1] https://www.kernel.org/doc/html/v5.15-rc1/vm/damon/index.html [2] https://research.google/pubs/pub48551/ [3] https://lwn.net/Articles/787611/ [4] https://damonitor.github.io [5] https://damonitor.github.io/doc/html/latest/vm/damon/eval.html [6] https://lore.kernel.org/linux-mm/20211001125604.29660-1-sj@kernel.org/ [7] https://github.com/awslabs/damoos [8] https://www.kernel.org/doc/html/latest/vm/free_page_reporting.html [9] https://www.usenix.org/conference/fast-04/car-clock-adaptive-replacement This patch (of 15): This makes the DAMON primitives for physical address space support the pageout action for DAMON-based Operation Schemes. With this commit, hence, users can easily implement system-level data access-aware reclamations using DAMOS. [sj@kernel.org: fix missing-prototype build warning] Link: https://lkml.kernel.org/r/20211025064220.13904-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211019150731.16699-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Cameron Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: Jonathan Corbet Cc: David Hildenbrand Cc: David Woodhouse Cc: Marco Elver Cc: Leonard Foerster Cc: Greg Thelen Cc: Markus Boehme Cc: David Rientjes Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ mm/damon/paddr.c | 37 ++++++++++++++++++++++++++++++++++++- 2 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 715dadd21f7c..9a327bc787b5 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -357,6 +357,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx); void damon_pa_prepare_access_checks(struct damon_ctx *ctx); unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); +int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index d7a2ecd09ed0..957ada55de77 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -11,7 +11,9 @@ #include #include #include +#include +#include "../internal.h" #include "prmtv-common.h" static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma, @@ -211,6 +213,39 @@ bool damon_pa_target_valid(void *t) return true; } +int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + unsigned long addr; + LIST_HEAD(page_list); + + if (scheme->action != DAMOS_PAGEOUT) + return -EINVAL; + + for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { + struct page *page = damon_get_page(PHYS_PFN(addr)); + + if (!page) + continue; + + ClearPageReferenced(page); + test_and_clear_page_young(page); + if (isolate_lru_page(page)) { + put_page(page); + continue; + } + if (PageUnevictable(page)) { + putback_lru_page(page); + } else { + list_add(&page->lru, &page_list); + put_page(page); + } + } + reclaim_pages(&page_list); + cond_resched(); + return 0; +} + void damon_pa_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = NULL; @@ -220,5 +255,5 @@ void damon_pa_set_primitives(struct damon_ctx *ctx) ctx->primitive.reset_aggregated = NULL; ctx->primitive.target_valid = damon_pa_target_valid; ctx->primitive.cleanup = NULL; - ctx->primitive.apply_scheme = NULL; + ctx->primitive.apply_scheme = damon_pa_apply_scheme; } -- cgit v1.2.3 From 2b8a248d5873343aa16f6c5ede30517693995f13 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:16 -0700 Subject: mm/damon/schemes: implement size quota for schemes application speed control There could be arbitrarily large memory regions fulfilling the target data access pattern of a DAMON-based operation scheme. In the case, applying the action of the scheme could incur too high overhead. To provide an intuitive way for avoiding it, this implements a feature called size quota. If the quota is set, DAMON tries to apply the action only up to the given amount of memory regions within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-3-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 36 +++++++++++++++++++++++++++---- mm/damon/core.c | 60 ++++++++++++++++++++++++++++++++++++++++++++------- mm/damon/dbgfs.c | 4 +++- 3 files changed, 87 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 9a327bc787b5..3a1ce9d9921c 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -89,6 +89,26 @@ enum damos_action { DAMOS_STAT, /* Do nothing but only record the stat */ }; +/** + * struct damos_quota - Controls the aggressiveness of the given scheme. + * @sz: Maximum bytes of memory that the action can be applied. + * @reset_interval: Charge reset interval in milliseconds. + * + * To avoid consuming too much CPU time or IO resources for applying the + * &struct damos->action to large memory, DAMON allows users to set a size + * quota. The quota can be set by writing non-zero values to &sz. If the size + * quota is set, DAMON tries to apply the action only up to &sz bytes within + * &reset_interval. + */ +struct damos_quota { + unsigned long sz; + unsigned long reset_interval; + +/* private: For charging the quota */ + unsigned long charged_sz; + unsigned long charged_from; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -98,13 +118,20 @@ enum damos_action { * @min_age_region: Minimum age of target regions. * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. + * @quota: Control the aggressiveness of this scheme. * @stat_count: Total number of regions that this scheme is applied. * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. * - * For each aggregation interval, DAMON applies @action to monitoring target - * regions fit in the condition and updates the statistics. Note that both - * the minimums and the maximums are inclusive. + * For each aggregation interval, DAMON finds regions which fit in the + * condition (&min_sz_region, &max_sz_region, &min_nr_accesses, + * &max_nr_accesses, &min_age_region, &max_age_region) and applies &action to + * those. To avoid consuming too much CPU time or IO resources for the + * &action, "a is used. + * + * After applying the &action to each region, &stat_count and &stat_sz is + * updated to reflect the number of regions and total size of regions that the + * &action is applied. */ struct damos { unsigned long min_sz_region; @@ -114,6 +141,7 @@ struct damos { unsigned int min_age_region; unsigned int max_age_region; enum damos_action action; + struct damos_quota quota; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -310,7 +338,7 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action); + enum damos_action action, struct damos_quota *quota); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); diff --git a/mm/damon/core.c b/mm/damon/core.c index 2f6785737902..cce14a0d5c72 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -89,7 +89,7 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action) + enum damos_action action, struct damos_quota *quota) { struct damos *scheme; @@ -107,6 +107,11 @@ struct damos *damon_new_scheme( scheme->stat_sz = 0; INIT_LIST_HEAD(&scheme->list); + scheme->quota.sz = quota->sz; + scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.charged_sz = 0; + scheme->quota.charged_from = 0; + return scheme; } @@ -530,15 +535,25 @@ static void kdamond_reset_aggregated(struct damon_ctx *c) } } +static void damon_split_region_at(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + unsigned long sz_r); + static void damon_do_apply_schemes(struct damon_ctx *c, struct damon_target *t, struct damon_region *r) { struct damos *s; - unsigned long sz; damon_for_each_scheme(s, c) { - sz = r->ar.end - r->ar.start; + struct damos_quota *quota = &s->quota; + unsigned long sz = r->ar.end - r->ar.start; + + /* Check the quota */ + if (quota->sz && quota->charged_sz >= quota->sz) + continue; + + /* Check the target regions condition */ if (sz < s->min_sz_region || s->max_sz_region < sz) continue; if (r->nr_accesses < s->min_nr_accesses || @@ -546,22 +561,51 @@ static void damon_do_apply_schemes(struct damon_ctx *c, continue; if (r->age < s->min_age_region || s->max_age_region < r->age) continue; - s->stat_count++; - s->stat_sz += sz; - if (c->primitive.apply_scheme) + + /* Apply the scheme */ + if (c->primitive.apply_scheme) { + if (quota->sz && quota->charged_sz + sz > quota->sz) { + sz = ALIGN_DOWN(quota->sz - quota->charged_sz, + DAMON_MIN_REGION); + if (!sz) + goto update_stat; + damon_split_region_at(c, t, r, sz); + } c->primitive.apply_scheme(c, t, r, s); + quota->charged_sz += sz; + } if (s->action != DAMOS_STAT) r->age = 0; + +update_stat: + s->stat_count++; + s->stat_sz += sz; } } static void kdamond_apply_schemes(struct damon_ctx *c) { struct damon_target *t; - struct damon_region *r; + struct damon_region *r, *next_r; + struct damos *s; + + damon_for_each_scheme(s, c) { + struct damos_quota *quota = &s->quota; + + if (!quota->sz) + continue; + + /* New charge window starts */ + if (time_after_eq(jiffies, quota->charged_from + + msecs_to_jiffies( + quota->reset_interval))) { + quota->charged_from = jiffies; + quota->charged_sz = 0; + } + } damon_for_each_target(t, c) { - damon_for_each_region(r, t) + damon_for_each_region_safe(r, next_r, t) damon_do_apply_schemes(c, t, r); } } diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index c90988a20fa4..a04bd50cc4c4 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -188,6 +188,8 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, *nr_schemes = 0; while (pos < len && *nr_schemes < max_nr_schemes) { + struct damos_quota quota = {}; + ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u%n", &min_sz, &max_sz, &min_nr_a, &max_nr_a, &min_age, &max_age, &action, &parsed); @@ -200,7 +202,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, pos += parsed; scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, - min_age, max_age, action); + min_age, max_age, action, "a); if (!scheme) goto fail; -- cgit v1.2.3 From 50585192bc2ef9309d32dabdbb5e735679f4f128 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:20 -0700 Subject: mm/damon/schemes: skip already charged targets and regions If DAMOS has stopped applying action in the middle of a group of memory regions due to its size quota, it starts the work again from the beginning of the address space in the next charge window. If there is a huge memory region at the beginning of the address space and it fulfills the scheme's target data access pattern always, the action will applied to only the region. This mitigates the case by skipping memory regions that charged in current charge window at the beginning of next charge window. Link: https://lkml.kernel.org/r/20211019150731.16699-4-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 5 +++++ mm/damon/core.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3a1ce9d9921c..585d985768fd 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -107,6 +107,8 @@ struct damos_quota { /* private: For charging the quota */ unsigned long charged_sz; unsigned long charged_from; + struct damon_target *charge_target_from; + unsigned long charge_addr_from; }; /** @@ -307,6 +309,9 @@ struct damon_ctx { #define damon_prev_region(r) \ (container_of(r->list.prev, struct damon_region, list)) +#define damon_last_region(t) \ + (list_last_entry(&t->regions_list, struct damon_region, list)) + #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/mm/damon/core.c b/mm/damon/core.c index cce14a0d5c72..693b75bc3450 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -111,6 +111,8 @@ struct damos *damon_new_scheme( scheme->quota.reset_interval = quota->reset_interval; scheme->quota.charged_sz = 0; scheme->quota.charged_from = 0; + scheme->quota.charge_target_from = NULL; + scheme->quota.charge_addr_from = 0; return scheme; } @@ -553,6 +555,37 @@ static void damon_do_apply_schemes(struct damon_ctx *c, if (quota->sz && quota->charged_sz >= quota->sz) continue; + /* Skip previously charged regions */ + if (quota->charge_target_from) { + if (t != quota->charge_target_from) + continue; + if (r == damon_last_region(t)) { + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + continue; + } + if (quota->charge_addr_from && + r->ar.end <= quota->charge_addr_from) + continue; + + if (quota->charge_addr_from && r->ar.start < + quota->charge_addr_from) { + sz = ALIGN_DOWN(quota->charge_addr_from - + r->ar.start, DAMON_MIN_REGION); + if (!sz) { + if (r->ar.end - r->ar.start <= + DAMON_MIN_REGION) + continue; + sz = DAMON_MIN_REGION; + } + damon_split_region_at(c, t, r, sz); + r = damon_next_region(r); + sz = r->ar.end - r->ar.start; + } + quota->charge_target_from = NULL; + quota->charge_addr_from = 0; + } + /* Check the target regions condition */ if (sz < s->min_sz_region || s->max_sz_region < sz) continue; @@ -573,6 +606,10 @@ static void damon_do_apply_schemes(struct damon_ctx *c, } c->primitive.apply_scheme(c, t, r, s); quota->charged_sz += sz; + if (quota->sz && quota->charged_sz >= quota->sz) { + quota->charge_target_from = t; + quota->charge_addr_from = r->ar.end + 1; + } } if (s->action != DAMOS_STAT) r->age = 0; -- cgit v1.2.3 From 1cd2430300594a230dba9178ac9e286d868d9da2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:23 -0700 Subject: mm/damon/schemes: implement time quota The size quota feature of DAMOS is useful for IO resource-critical systems, but not so intuitive for CPU time-critical systems. Systems using zram or zswap-like swap device would be examples. To provide another intuitive ways for such systems, this implements time-based quota for DAMON-based Operation Schemes. If the quota is set, DAMOS tries to use only up to the user-defined quota of CPU time within a given time window. Link: https://lkml.kernel.org/r/20211019150731.16699-5-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 25 ++++++++++++++++++++----- mm/damon/core.c | 45 ++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 60 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 585d985768fd..1e7671bf3d23 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -91,20 +91,35 @@ enum damos_action { /** * struct damos_quota - Controls the aggressiveness of the given scheme. + * @ms: Maximum milliseconds that the scheme can use. * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * * To avoid consuming too much CPU time or IO resources for applying the - * &struct damos->action to large memory, DAMON allows users to set a size - * quota. The quota can be set by writing non-zero values to &sz. If the size - * quota is set, DAMON tries to apply the action only up to &sz bytes within - * &reset_interval. + * &struct damos->action to large memory, DAMON allows users to set time and/or + * size quotas. The quotas can be set by writing non-zero values to &ms and + * &sz, respectively. If the time quota is set, DAMON tries to use only up to + * &ms milliseconds within &reset_interval for applying the action. If the + * size quota is set, DAMON tries to apply the action only up to &sz bytes + * within &reset_interval. + * + * Internally, the time quota is transformed to a size quota using estimated + * throughput of the scheme's action. DAMON then compares it against &sz and + * uses smaller one as the effective quota. */ struct damos_quota { + unsigned long ms; unsigned long sz; unsigned long reset_interval; -/* private: For charging the quota */ +/* private: */ + /* For throughput estimation */ + unsigned long total_charged_sz; + unsigned long total_charged_ns; + + unsigned long esz; /* Effective size quota in bytes */ + + /* For charging the quota */ unsigned long charged_sz; unsigned long charged_from; struct damon_target *charge_target_from; diff --git a/mm/damon/core.c b/mm/damon/core.c index 693b75bc3450..d1da4bef96ed 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -107,8 +107,12 @@ struct damos *damon_new_scheme( scheme->stat_sz = 0; INIT_LIST_HEAD(&scheme->list); + scheme->quota.ms = quota->ms; scheme->quota.sz = quota->sz; scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.total_charged_sz = 0; + scheme->quota.total_charged_ns = 0; + scheme->quota.esz = 0; scheme->quota.charged_sz = 0; scheme->quota.charged_from = 0; scheme->quota.charge_target_from = NULL; @@ -550,9 +554,10 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; unsigned long sz = r->ar.end - r->ar.start; + struct timespec64 begin, end; /* Check the quota */ - if (quota->sz && quota->charged_sz >= quota->sz) + if (quota->esz && quota->charged_sz >= quota->esz) continue; /* Skip previously charged regions */ @@ -597,16 +602,21 @@ static void damon_do_apply_schemes(struct damon_ctx *c, /* Apply the scheme */ if (c->primitive.apply_scheme) { - if (quota->sz && quota->charged_sz + sz > quota->sz) { - sz = ALIGN_DOWN(quota->sz - quota->charged_sz, + if (quota->esz && + quota->charged_sz + sz > quota->esz) { + sz = ALIGN_DOWN(quota->esz - quota->charged_sz, DAMON_MIN_REGION); if (!sz) goto update_stat; damon_split_region_at(c, t, r, sz); } + ktime_get_coarse_ts64(&begin); c->primitive.apply_scheme(c, t, r, s); + ktime_get_coarse_ts64(&end); + quota->total_charged_ns += timespec64_to_ns(&end) - + timespec64_to_ns(&begin); quota->charged_sz += sz; - if (quota->sz && quota->charged_sz >= quota->sz) { + if (quota->esz && quota->charged_sz >= quota->esz) { quota->charge_target_from = t; quota->charge_addr_from = r->ar.end + 1; } @@ -620,6 +630,29 @@ update_stat: } } +/* Shouldn't be called if quota->ms and quota->sz are zero */ +static void damos_set_effective_quota(struct damos_quota *quota) +{ + unsigned long throughput; + unsigned long esz; + + if (!quota->ms) { + quota->esz = quota->sz; + return; + } + + if (quota->total_charged_ns) + throughput = quota->total_charged_sz * 1000000 / + quota->total_charged_ns; + else + throughput = PAGE_SIZE * 1024; + esz = throughput * quota->ms; + + if (quota->sz && quota->sz < esz) + esz = quota->sz; + quota->esz = esz; +} + static void kdamond_apply_schemes(struct damon_ctx *c) { struct damon_target *t; @@ -629,15 +662,17 @@ static void kdamond_apply_schemes(struct damon_ctx *c) damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; - if (!quota->sz) + if (!quota->ms && !quota->sz) continue; /* New charge window starts */ if (time_after_eq(jiffies, quota->charged_from + msecs_to_jiffies( quota->reset_interval))) { + quota->total_charged_sz += quota->charged_sz; quota->charged_from = jiffies; quota->charged_sz = 0; + damos_set_effective_quota(quota); } } -- cgit v1.2.3 From 38683e003153f7abfa612d7b7fe147efa4624af2 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:33 -0700 Subject: mm/damon/schemes: prioritize regions within the quotas This makes DAMON apply schemes to regions having higher priority first, if it cannot apply schemes to all regions due to the quotas. The prioritization function should be implemented in the monitoring primitives. Those would commonly calculate the priority of the region using attributes of regions, namely 'size', 'nr_accesses', and 'age'. For example, some primitive would calculate the priority of each region using a weighted sum of 'nr_accesses' and 'age' of the region. The optimal weights would depend on give environments, so this makes those customizable. Nevertheless, the score calculation functions are only encouraged to respect the weights, not mandated. Link: https://lkml.kernel.org/r/20211019150731.16699-8-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 26 +++++++++++++++++++++ mm/damon/core.c | 62 +++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 81 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1e7671bf3d23..5d47ad9e3911 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -14,6 +14,8 @@ /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE +/* Max priority score for DAMON-based operation schemes */ +#define DAMOS_MAX_SCORE (99) /** * struct damon_addr_range - Represents an address region of [@start, @end). @@ -95,6 +97,10 @@ enum damos_action { * @sz: Maximum bytes of memory that the action can be applied. * @reset_interval: Charge reset interval in milliseconds. * + * @weight_sz: Weight of the region's size for prioritization. + * @weight_nr_accesses: Weight of the region's nr_accesses for prioritization. + * @weight_age: Weight of the region's age for prioritization. + * * To avoid consuming too much CPU time or IO resources for applying the * &struct damos->action to large memory, DAMON allows users to set time and/or * size quotas. The quotas can be set by writing non-zero values to &ms and @@ -106,12 +112,22 @@ enum damos_action { * Internally, the time quota is transformed to a size quota using estimated * throughput of the scheme's action. DAMON then compares it against &sz and * uses smaller one as the effective quota. + * + * For selecting regions within the quota, DAMON prioritizes current scheme's + * target memory regions using the &struct damon_primitive->get_scheme_score. + * You could customize the prioritization logic by setting &weight_sz, + * &weight_nr_accesses, and &weight_age, because monitoring primitives are + * encouraged to respect those. */ struct damos_quota { unsigned long ms; unsigned long sz; unsigned long reset_interval; + unsigned int weight_sz; + unsigned int weight_nr_accesses; + unsigned int weight_age; + /* private: */ /* For throughput estimation */ unsigned long total_charged_sz; @@ -124,6 +140,10 @@ struct damos_quota { unsigned long charged_from; struct damon_target *charge_target_from; unsigned long charge_addr_from; + + /* For prioritization */ + unsigned long histogram[DAMOS_MAX_SCORE + 1]; + unsigned int min_score; }; /** @@ -174,6 +194,7 @@ struct damon_ctx; * @prepare_access_checks: Prepare next access check of target regions. * @check_accesses: Check the accesses to target regions. * @reset_aggregated: Reset aggregated accesses monitoring results. + * @get_scheme_score: Get the score of a region for a scheme. * @apply_scheme: Apply a DAMON-based operation scheme. * @target_valid: Determine if the target is valid. * @cleanup: Clean up the context. @@ -200,6 +221,8 @@ struct damon_ctx; * of its update. The value will be used for regions adjustment threshold. * @reset_aggregated should reset the access monitoring results that aggregated * by @check_accesses. + * @get_scheme_score should return the priority score of a region for a scheme + * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. @@ -213,6 +236,9 @@ struct damon_primitive { void (*prepare_access_checks)(struct damon_ctx *context); unsigned int (*check_accesses)(struct damon_ctx *context); void (*reset_aggregated)(struct damon_ctx *context); + int (*get_scheme_score)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); bool (*target_valid)(void *target); diff --git a/mm/damon/core.c b/mm/damon/core.c index d1da4bef96ed..fad25778e2ec 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -12,6 +12,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -110,6 +111,9 @@ struct damos *damon_new_scheme( scheme->quota.ms = quota->ms; scheme->quota.sz = quota->sz; scheme->quota.reset_interval = quota->reset_interval; + scheme->quota.weight_sz = quota->weight_sz; + scheme->quota.weight_nr_accesses = quota->weight_nr_accesses; + scheme->quota.weight_age = quota->weight_age; scheme->quota.total_charged_sz = 0; scheme->quota.total_charged_ns = 0; scheme->quota.esz = 0; @@ -545,6 +549,28 @@ static void damon_split_region_at(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, unsigned long sz_r); +static bool __damos_valid_target(struct damon_region *r, struct damos *s) +{ + unsigned long sz; + + sz = r->ar.end - r->ar.start; + return s->min_sz_region <= sz && sz <= s->max_sz_region && + s->min_nr_accesses <= r->nr_accesses && + r->nr_accesses <= s->max_nr_accesses && + s->min_age_region <= r->age && r->age <= s->max_age_region; +} + +static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t, + struct damon_region *r, struct damos *s) +{ + bool ret = __damos_valid_target(r, s); + + if (!ret || !s->quota.esz || !c->primitive.get_scheme_score) + return ret; + + return c->primitive.get_scheme_score(c, t, r, s) >= s->quota.min_score; +} + static void damon_do_apply_schemes(struct damon_ctx *c, struct damon_target *t, struct damon_region *r) @@ -591,13 +617,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, quota->charge_addr_from = 0; } - /* Check the target regions condition */ - if (sz < s->min_sz_region || s->max_sz_region < sz) - continue; - if (r->nr_accesses < s->min_nr_accesses || - s->max_nr_accesses < r->nr_accesses) - continue; - if (r->age < s->min_age_region || s->max_age_region < r->age) + if (!damos_valid_target(c, t, r, s)) continue; /* Apply the scheme */ @@ -661,6 +681,8 @@ static void kdamond_apply_schemes(struct damon_ctx *c) damon_for_each_scheme(s, c) { struct damos_quota *quota = &s->quota; + unsigned long cumulated_sz; + unsigned int score, max_score = 0; if (!quota->ms && !quota->sz) continue; @@ -674,6 +696,32 @@ static void kdamond_apply_schemes(struct damon_ctx *c) quota->charged_sz = 0; damos_set_effective_quota(quota); } + + if (!c->primitive.get_scheme_score) + continue; + + /* Fill up the score histogram */ + memset(quota->histogram, 0, sizeof(quota->histogram)); + damon_for_each_target(t, c) { + damon_for_each_region(r, t) { + if (!__damos_valid_target(r, s)) + continue; + score = c->primitive.get_scheme_score( + c, t, r, s); + quota->histogram[score] += + r->ar.end - r->ar.start; + if (score > max_score) + max_score = score; + } + } + + /* Set the min score limit */ + for (cumulated_sz = 0, score = max_score; ; score--) { + cumulated_sz += quota->histogram[score]; + if (cumulated_sz >= quota->esz || !score) + break; + } + quota->min_score = score; } damon_for_each_target(t, c) { -- cgit v1.2.3 From 198f0f4c58b9f481e4e51c8c70a6ab9852bbab7f Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:37 -0700 Subject: mm/damon/vaddr,paddr: support pageout prioritization This makes the default monitoring primitives for virtual address spaces and the physical address sapce to support memory regions prioritization for 'PAGEOUT' DAMOS action. It calculates hotness of each region as weighted sum of 'nr_accesses' and 'age' of the region and get the priority score as reverse of the hotness, so that cold regions can be paged out first. Link: https://lkml.kernel.org/r/20211019150731.16699-9-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ mm/damon/paddr.c | 14 ++++++++++++++ mm/damon/prmtv-common.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ mm/damon/prmtv-common.h | 3 +++ mm/damon/vaddr.c | 15 +++++++++++++++ 5 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 5d47ad9e3911..1217566a0ebc 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -421,6 +421,8 @@ bool damon_va_target_valid(void *t); void damon_va_cleanup(struct damon_ctx *ctx); int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); +int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_VADDR */ @@ -433,6 +435,8 @@ unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); +int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); #endif /* CONFIG_DAMON_PADDR */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 957ada55de77..a496d6f203d6 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -246,6 +246,19 @@ int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, return 0; } +int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pageout_score(context, r, scheme); + default: + break; + } + + return DAMOS_MAX_SCORE; +} + void damon_pa_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = NULL; @@ -256,4 +269,5 @@ void damon_pa_set_primitives(struct damon_ctx *ctx) ctx->primitive.target_valid = damon_pa_target_valid; ctx->primitive.cleanup = NULL; ctx->primitive.apply_scheme = damon_pa_apply_scheme; + ctx->primitive.get_scheme_score = damon_pa_scheme_score; } diff --git a/mm/damon/prmtv-common.c b/mm/damon/prmtv-common.c index 7e62ee54fb54..92a04f5831d6 100644 --- a/mm/damon/prmtv-common.c +++ b/mm/damon/prmtv-common.c @@ -85,3 +85,49 @@ void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr) put_page(page); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ } + +#define DAMON_MAX_SUBSCORE (100) +#define DAMON_MAX_AGE_IN_LOG (32) + +int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s) +{ + unsigned int max_nr_accesses; + int freq_subscore; + unsigned int age_in_sec; + int age_in_log, age_subscore; + unsigned int freq_weight = s->quota.weight_nr_accesses; + unsigned int age_weight = s->quota.weight_age; + int hotness; + + max_nr_accesses = c->aggr_interval / c->sample_interval; + freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses; + + age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000; + for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec; + age_in_log++, age_in_sec >>= 1) + ; + + /* If frequency is 0, higher age means it's colder */ + if (freq_subscore == 0) + age_in_log *= -1; + + /* + * Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG]. + * Scale it to be in [0, 100] and set it as age subscore. + */ + age_in_log += DAMON_MAX_AGE_IN_LOG; + age_subscore = age_in_log * DAMON_MAX_SUBSCORE / + DAMON_MAX_AGE_IN_LOG / 2; + + hotness = (freq_weight * freq_subscore + age_weight * age_subscore); + if (freq_weight + age_weight) + hotness /= freq_weight + age_weight; + /* + * Transform it to fit in [0, DAMOS_MAX_SCORE] + */ + hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE; + + /* Return coldness of the region */ + return DAMOS_MAX_SCORE - hotness; +} diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h index 7093d19e5d42..61f27037603e 100644 --- a/mm/damon/prmtv-common.h +++ b/mm/damon/prmtv-common.h @@ -15,3 +15,6 @@ struct page *damon_get_page(unsigned long pfn); void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr); void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr); + +int damon_pageout_score(struct damon_ctx *c, struct damon_region *r, + struct damos *s); diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 758501b8d97d..675cd8c7df9b 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -633,6 +633,20 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, return damos_madvise(t, r, madv_action); } +int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, + struct damon_region *r, struct damos *scheme) +{ + + switch (scheme->action) { + case DAMOS_PAGEOUT: + return damon_pageout_score(context, r, scheme); + default: + break; + } + + return DAMOS_MAX_SCORE; +} + void damon_va_set_primitives(struct damon_ctx *ctx) { ctx->primitive.init = damon_va_init; @@ -643,6 +657,7 @@ void damon_va_set_primitives(struct damon_ctx *ctx) ctx->primitive.target_valid = damon_va_target_valid; ctx->primitive.cleanup = NULL; ctx->primitive.apply_scheme = damon_va_apply_scheme; + ctx->primitive.get_scheme_score = damon_va_scheme_score; } #include "vaddr-test.h" -- cgit v1.2.3 From ee801b7dd7822a82fd7663048ad649545fac6df3 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 5 Nov 2021 13:47:47 -0700 Subject: mm/damon/schemes: activate schemes based on a watermarks mechanism DAMON-based operation schemes need to be manually turned on and off. In some use cases, however, the condition for turning a scheme on and off would depend on the system's situation. For example, schemes for proactive pages reclamation would need to be turned on when some memory pressure is detected, and turned off when the system has enough free memory. For easier control of schemes activation based on the system situation, this introduces a watermarks-based mechanism. The client can describe the watermark metric (e.g., amount of free memory in the system), watermark check interval, and three watermarks, namely high, mid, and low. If the scheme is deactivated, it only gets the metric and compare that to the three watermarks for every check interval. If the metric is higher than the high watermark, the scheme is deactivated. If the metric is between the mid watermark and the low watermark, the scheme is activated. If the metric is lower than the low watermark, the scheme is deactivated again. This is to allow users fall back to traditional page-granularity mechanisms. Link: https://lkml.kernel.org/r/20211019150731.16699-12-sj@kernel.org Signed-off-by: SeongJae Park Cc: Amit Shah Cc: Benjamin Herrenschmidt Cc: David Hildenbrand Cc: David Rientjes Cc: David Woodhouse Cc: Greg Thelen Cc: Jonathan Cameron Cc: Jonathan Corbet Cc: Leonard Foerster Cc: Marco Elver Cc: Markus Boehme Cc: Shakeel Butt Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 52 ++++++++++++++++++++++++++- mm/damon/core.c | 97 ++++++++++++++++++++++++++++++++++++++++++++++++++- mm/damon/dbgfs.c | 5 ++- 3 files changed, 151 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1217566a0ebc..c93325efddd7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -146,6 +146,45 @@ struct damos_quota { unsigned int min_score; }; +/** + * enum damos_wmark_metric - Represents the watermark metric. + * + * @DAMOS_WMARK_NONE: Ignore the watermarks of the given scheme. + * @DAMOS_WMARK_FREE_MEM_RATE: Free memory rate of the system in [0,1000]. + */ +enum damos_wmark_metric { + DAMOS_WMARK_NONE, + DAMOS_WMARK_FREE_MEM_RATE, +}; + +/** + * struct damos_watermarks - Controls when a given scheme should be activated. + * @metric: Metric for the watermarks. + * @interval: Watermarks check time interval in microseconds. + * @high: High watermark. + * @mid: Middle watermark. + * @low: Low watermark. + * + * If &metric is &DAMOS_WMARK_NONE, the scheme is always active. Being active + * means DAMON does monitoring and applying the action of the scheme to + * appropriate memory regions. Else, DAMON checks &metric of the system for at + * least every &interval microseconds and works as below. + * + * If &metric is higher than &high, the scheme is inactivated. If &metric is + * between &mid and &low, the scheme is activated. If &metric is lower than + * &low, the scheme is inactivated. + */ +struct damos_watermarks { + enum damos_wmark_metric metric; + unsigned long interval; + unsigned long high; + unsigned long mid; + unsigned long low; + +/* private: */ + bool activated; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -156,6 +195,7 @@ struct damos_quota { * @max_age_region: Maximum age of target regions. * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. + * @wmarks: Watermarks for automated (in)activation of this scheme. * @stat_count: Total number of regions that this scheme is applied. * @stat_sz: Total size of regions that this scheme is applied. * @list: List head for siblings. @@ -166,6 +206,14 @@ struct damos_quota { * those. To avoid consuming too much CPU time or IO resources for the * &action, "a is used. * + * To do the work only when needed, schemes can be activated for specific + * system situations using &wmarks. If all schemes that registered to the + * monitoring context are inactive, DAMON stops monitoring either, and just + * repeatedly checks the watermarks. + * + * If all schemes that registered to a &struct damon_ctx are inactive, DAMON + * stops monitoring and just repeatedly checks the watermarks. + * * After applying the &action to each region, &stat_count and &stat_sz is * updated to reflect the number of regions and total size of regions that the * &action is applied. @@ -179,6 +227,7 @@ struct damos { unsigned int max_age_region; enum damos_action action; struct damos_quota quota; + struct damos_watermarks wmarks; unsigned long stat_count; unsigned long stat_sz; struct list_head list; @@ -384,7 +433,8 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota); + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks); void damon_add_scheme(struct damon_ctx *ctx, struct damos *s); void damon_destroy_scheme(struct damos *s); diff --git a/mm/damon/core.c b/mm/damon/core.c index fad25778e2ec..6993c60ae31c 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -90,7 +91,8 @@ struct damos *damon_new_scheme( unsigned long min_sz_region, unsigned long max_sz_region, unsigned int min_nr_accesses, unsigned int max_nr_accesses, unsigned int min_age_region, unsigned int max_age_region, - enum damos_action action, struct damos_quota *quota) + enum damos_action action, struct damos_quota *quota, + struct damos_watermarks *wmarks) { struct damos *scheme; @@ -122,6 +124,13 @@ struct damos *damon_new_scheme( scheme->quota.charge_target_from = NULL; scheme->quota.charge_addr_from = 0; + scheme->wmarks.metric = wmarks->metric; + scheme->wmarks.interval = wmarks->interval; + scheme->wmarks.high = wmarks->high; + scheme->wmarks.mid = wmarks->mid; + scheme->wmarks.low = wmarks->low; + scheme->wmarks.activated = true; + return scheme; } @@ -582,6 +591,9 @@ static void damon_do_apply_schemes(struct damon_ctx *c, unsigned long sz = r->ar.end - r->ar.start; struct timespec64 begin, end; + if (!s->wmarks.activated) + continue; + /* Check the quota */ if (quota->esz && quota->charged_sz >= quota->esz) continue; @@ -684,6 +696,9 @@ static void kdamond_apply_schemes(struct damon_ctx *c) unsigned long cumulated_sz; unsigned int score, max_score = 0; + if (!s->wmarks.activated) + continue; + if (!quota->ms && !quota->sz) continue; @@ -924,6 +939,83 @@ static bool kdamond_need_stop(struct damon_ctx *ctx) return true; } +static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric) +{ + struct sysinfo i; + + switch (metric) { + case DAMOS_WMARK_FREE_MEM_RATE: + si_meminfo(&i); + return i.freeram * 1000 / i.totalram; + default: + break; + } + return -EINVAL; +} + +/* + * Returns zero if the scheme is active. Else, returns time to wait for next + * watermark check in micro-seconds. + */ +static unsigned long damos_wmark_wait_us(struct damos *scheme) +{ + unsigned long metric; + + if (scheme->wmarks.metric == DAMOS_WMARK_NONE) + return 0; + + metric = damos_wmark_metric_value(scheme->wmarks.metric); + /* higher than high watermark or lower than low watermark */ + if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) { + if (scheme->wmarks.activated) + pr_debug("inactivate a scheme (%d) for %s wmark\n", + scheme->action, + metric > scheme->wmarks.high ? + "high" : "low"); + scheme->wmarks.activated = false; + return scheme->wmarks.interval; + } + + /* inactive and higher than middle watermark */ + if ((scheme->wmarks.high >= metric && metric >= scheme->wmarks.mid) && + !scheme->wmarks.activated) + return scheme->wmarks.interval; + + if (!scheme->wmarks.activated) + pr_debug("activate a scheme (%d)\n", scheme->action); + scheme->wmarks.activated = true; + return 0; +} + +static void kdamond_usleep(unsigned long usecs) +{ + if (usecs > 100 * 1000) + schedule_timeout_interruptible(usecs_to_jiffies(usecs)); + else + usleep_range(usecs, usecs + 1); +} + +/* Returns negative error code if it's not activated but should return */ +static int kdamond_wait_activation(struct damon_ctx *ctx) +{ + struct damos *s; + unsigned long wait_time; + unsigned long min_wait_time = 0; + + while (!kdamond_need_stop(ctx)) { + damon_for_each_scheme(s, ctx) { + wait_time = damos_wmark_wait_us(s); + if (!min_wait_time || wait_time < min_wait_time) + min_wait_time = wait_time; + } + if (!min_wait_time) + return 0; + + kdamond_usleep(min_wait_time); + } + return -EBUSY; +} + static void set_kdamond_stop(struct damon_ctx *ctx) { mutex_lock(&ctx->kdamond_lock); @@ -952,6 +1044,9 @@ static int kdamond_fn(void *data) sz_limit = damon_region_sz_limit(ctx); while (!kdamond_need_stop(ctx)) { + if (kdamond_wait_activation(ctx)) + continue; + if (ctx->primitive.prepare_access_checks) ctx->primitive.prepare_access_checks(ctx); if (ctx->callback.after_sampling && diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 20c4feb8b918..9f13060d1058 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -195,6 +195,9 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, *nr_schemes = 0; while (pos < len && *nr_schemes < max_nr_schemes) { struct damos_quota quota = {}; + struct damos_watermarks wmarks = { + .metric = DAMOS_WMARK_NONE, + }; ret = sscanf(&str[pos], "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u%n", @@ -212,7 +215,7 @@ static struct damos **str_to_schemes(const char *str, ssize_t len, pos += parsed; scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a, - min_age, max_age, action, "a); + min_age, max_age, action, "a, &wmarks); if (!scheme) goto fail; -- cgit v1.2.3 From b5ca3e83ddb05342b1b30700b999cb9b107511f6 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 5 Nov 2021 13:48:07 -0700 Subject: mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on When the ctx->adaptive_targets list is empty, I did some test on monitor_on interface like this. # cat /sys/kernel/debug/damon/target_ids # # echo on > /sys/kernel/debug/damon/monitor_on # damon: kdamond (5390) starts Though the ctx->adaptive_targets list is empty, but the kthread_run still be called, and the kdamond.x thread still be created, this is meaningless. So there adds a judgment in 'dbgfs_monitor_on_write', if the ctx->adaptive_targets list is empty, return -EINVAL. Link: https://lkml.kernel.org/r/0a60a6e8ec9d71989e0848a4dc3311996ca3b5d4.1634720326.git.xhao@linux.alibaba.com Signed-off-by: Xin Hao Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 + mm/damon/core.c | 5 +++++ mm/damon/dbgfs.c | 15 ++++++++++++--- 3 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index c93325efddd7..fa7f32614b65 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -440,6 +440,7 @@ void damon_destroy_scheme(struct damos *s); struct damon_target *damon_new_target(unsigned long id); void damon_add_target(struct damon_ctx *ctx, struct damon_target *t); +bool damon_targets_empty(struct damon_ctx *ctx); void damon_free_target(struct damon_target *t); void damon_destroy_target(struct damon_target *t); unsigned int damon_nr_regions(struct damon_target *t); diff --git a/mm/damon/core.c b/mm/damon/core.c index 6993c60ae31c..46a6afea3030 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -180,6 +180,11 @@ void damon_add_target(struct damon_ctx *ctx, struct damon_target *t) list_add_tail(&t->list, &ctx->adaptive_targets); } +bool damon_targets_empty(struct damon_ctx *ctx) +{ + return list_empty(&ctx->adaptive_targets); +} + static void damon_del_target(struct damon_target *t) { list_del(&t->list); diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index 6828e463348b..befb27a29aab 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -878,12 +878,21 @@ static ssize_t dbgfs_monitor_on_write(struct file *file, return -EINVAL; } - if (!strncmp(kbuf, "on", count)) + if (!strncmp(kbuf, "on", count)) { + int i; + + for (i = 0; i < dbgfs_nr_ctxs; i++) { + if (damon_targets_empty(dbgfs_ctxs[i])) { + kfree(kbuf); + return -EINVAL; + } + } ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs); - else if (!strncmp(kbuf, "off", count)) + } else if (!strncmp(kbuf, "off", count)) { ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs); - else + } else { ret = -EINVAL; + } if (!ret) ret = count; -- cgit v1.2.3 From 0f91d13366a402420bf98eaaf393db03946c13e0 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:22 -0700 Subject: mm/damon: simplify stop mechanism A kernel thread can exit gracefully with kthread_stop(). So we don't need a new flag 'kdamond_stop'. And to make sure the task struct is not freed when accessing it, get reference to it before termination. Link: https://lkml.kernel.org/r/20211027130517.4404-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 1 - mm/damon/core.c | 51 +++++++++++++++------------------------------------ 2 files changed, 15 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index fa7f32614b65..321de9d72360 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -381,7 +381,6 @@ struct damon_ctx { /* public: */ struct task_struct *kdamond; - bool kdamond_stop; struct mutex kdamond_lock; struct damon_primitive primitive; diff --git a/mm/damon/core.c b/mm/damon/core.c index 46a6afea3030..f37c17b53814 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -390,17 +390,6 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx) return sz; } -static bool damon_kdamond_running(struct damon_ctx *ctx) -{ - bool running; - - mutex_lock(&ctx->kdamond_lock); - running = ctx->kdamond != NULL; - mutex_unlock(&ctx->kdamond_lock); - - return running; -} - static int kdamond_fn(void *data); /* @@ -418,7 +407,6 @@ static int __damon_start(struct damon_ctx *ctx) mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; - ctx->kdamond_stop = false; ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { @@ -474,13 +462,15 @@ int damon_start(struct damon_ctx **ctxs, int nr_ctxs) */ static int __damon_stop(struct damon_ctx *ctx) { + struct task_struct *tsk; + mutex_lock(&ctx->kdamond_lock); - if (ctx->kdamond) { - ctx->kdamond_stop = true; + tsk = ctx->kdamond; + if (tsk) { + get_task_struct(tsk); mutex_unlock(&ctx->kdamond_lock); - while (damon_kdamond_running(ctx)) - usleep_range(ctx->sample_interval, - ctx->sample_interval * 2); + kthread_stop(tsk); + put_task_struct(tsk); return 0; } mutex_unlock(&ctx->kdamond_lock); @@ -925,12 +915,8 @@ static bool kdamond_need_update_primitive(struct damon_ctx *ctx) static bool kdamond_need_stop(struct damon_ctx *ctx) { struct damon_target *t; - bool stop; - mutex_lock(&ctx->kdamond_lock); - stop = ctx->kdamond_stop; - mutex_unlock(&ctx->kdamond_lock); - if (stop) + if (kthread_should_stop()) return true; if (!ctx->primitive.target_valid) @@ -1021,13 +1007,6 @@ static int kdamond_wait_activation(struct damon_ctx *ctx) return -EBUSY; } -static void set_kdamond_stop(struct damon_ctx *ctx) -{ - mutex_lock(&ctx->kdamond_lock); - ctx->kdamond_stop = true; - mutex_unlock(&ctx->kdamond_lock); -} - /* * The monitoring daemon that runs as a kernel thread */ @@ -1038,17 +1017,18 @@ static int kdamond_fn(void *data) struct damon_region *r, *next; unsigned int max_nr_accesses = 0; unsigned long sz_limit = 0; + bool done = false; pr_debug("kdamond (%d) starts\n", current->pid); if (ctx->primitive.init) ctx->primitive.init(ctx); if (ctx->callback.before_start && ctx->callback.before_start(ctx)) - set_kdamond_stop(ctx); + done = true; sz_limit = damon_region_sz_limit(ctx); - while (!kdamond_need_stop(ctx)) { + while (!kdamond_need_stop(ctx) && !done) { if (kdamond_wait_activation(ctx)) continue; @@ -1056,7 +1036,7 @@ static int kdamond_fn(void *data) ctx->primitive.prepare_access_checks(ctx); if (ctx->callback.after_sampling && ctx->callback.after_sampling(ctx)) - set_kdamond_stop(ctx); + done = true; usleep_range(ctx->sample_interval, ctx->sample_interval + 1); @@ -1069,7 +1049,7 @@ static int kdamond_fn(void *data) sz_limit); if (ctx->callback.after_aggregation && ctx->callback.after_aggregation(ctx)) - set_kdamond_stop(ctx); + done = true; kdamond_apply_schemes(ctx); kdamond_reset_aggregated(ctx); kdamond_split_regions(ctx); @@ -1088,9 +1068,8 @@ static int kdamond_fn(void *data) damon_destroy_region(r, t); } - if (ctx->callback.before_terminate && - ctx->callback.before_terminate(ctx)) - set_kdamond_stop(ctx); + if (ctx->callback.before_terminate) + ctx->callback.before_terminate(ctx); if (ctx->primitive.cleanup) ctx->primitive.cleanup(ctx); -- cgit v1.2.3 From 658f9ae761b5965893727dd4edcdad56e5a439bb Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Fri, 5 Nov 2021 13:48:27 -0700 Subject: mm/damon: remove return value from before_terminate callback Since the return value of 'before_terminate' callback is never used, we make it have no return value. Link: https://lkml.kernel.org/r/20211029005023.8895-1-changbin.du@gmail.com Signed-off-by: Changbin Du Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- mm/damon/dbgfs.c | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 321de9d72360..b4d4be3cc987 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -322,7 +322,7 @@ struct damon_callback { int (*before_start)(struct damon_ctx *context); int (*after_sampling)(struct damon_ctx *context); int (*after_aggregation)(struct damon_ctx *context); - int (*before_terminate)(struct damon_ctx *context); + void (*before_terminate)(struct damon_ctx *context); }; /** diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index befb27a29aab..eccc14b34901 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -645,18 +645,17 @@ static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx) debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]); } -static int dbgfs_before_terminate(struct damon_ctx *ctx) +static void dbgfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; if (!targetid_is_pid(ctx)) - return 0; + return; damon_for_each_target_safe(t, next, ctx) { put_pid((struct pid *)t->id); damon_destroy_target(t); } - return 0; } static struct damon_ctx *dbgfs_new_ctx(void) -- cgit v1.2.3 From 7c7e3d31e7856a8260a254f8c71db416f7f9f5a1 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 5 Nov 2021 16:23:29 -0700 Subject: bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Tested-by: Hengqi Chen Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 20 +++++++++++ kernel/bpf/btf.c | 5 ++- kernel/bpf/mmap_unlock_work.h | 65 ++++++++++++++++++++++++++++++++++ kernel/bpf/stackmap.c | 80 ++++-------------------------------------- kernel/bpf/task_iter.c | 76 +++++++++++++++++++++++++++++++++++---- kernel/bpf/verifier.c | 34 ++++++++++++++++++ kernel/trace/bpf_trace.c | 2 ++ tools/include/uapi/linux/bpf.h | 20 +++++++++++ 9 files changed, 222 insertions(+), 81 deletions(-) create mode 100644 kernel/bpf/mmap_unlock_work.h (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 2be6dfd68df9..df3410bff4b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2157,6 +2157,7 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; +extern const struct bpf_func_proto bpf_find_vma_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba5af15e25f5..509eee5f0393 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4938,6 +4938,25 @@ union bpf_attr { * **-ENOENT** if symbol is not found. * * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5120,6 +5139,7 @@ union bpf_attr { FN(trace_vprintk), \ FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ + FN(find_vma), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dbc3ad07e21b..cdb0fba65600 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6342,7 +6342,10 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .arg4_type = ARG_ANYTHING, }; -BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) +BTF_ID_LIST_GLOBAL(btf_task_struct_ids) +BTF_ID(struct, task_struct) +BTF_ID(struct, file) +BTF_ID(struct, vm_area_struct) /* BTF ID set registration API for modules */ diff --git a/kernel/bpf/mmap_unlock_work.h b/kernel/bpf/mmap_unlock_work.h new file mode 100644 index 000000000000..5d18d7d85bef --- /dev/null +++ b/kernel/bpf/mmap_unlock_work.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021 Facebook + */ + +#ifndef __MMAP_UNLOCK_WORK_H__ +#define __MMAP_UNLOCK_WORK_H__ +#include + +/* irq_work to run mmap_read_unlock() in irq_work */ +struct mmap_unlock_irq_work { + struct irq_work irq_work; + struct mm_struct *mm; +}; + +DECLARE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +/* + * We cannot do mmap_read_unlock() when the irq is disabled, because of + * risk to deadlock with rq_lock. To look up vma when the irqs are + * disabled, we need to run mmap_read_unlock() in irq_work. We use a + * percpu variable to do the irq_work. If the irq_work is already used + * by another lookup, we fall over. + */ +static inline bool bpf_mmap_unlock_get_irq_work(struct mmap_unlock_irq_work **work_ptr) +{ + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = false; + + if (irqs_disabled()) { + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + work = this_cpu_ptr(&mmap_unlock_work); + if (irq_work_is_busy(&work->irq_work)) { + /* cannot queue more up_read, fallback */ + irq_work_busy = true; + } + } else { + /* + * PREEMPT_RT does not allow to trylock mmap sem in + * interrupt disabled context. Force the fallback code. + */ + irq_work_busy = true; + } + } + + *work_ptr = work; + return irq_work_busy; +} + +static inline void bpf_mmap_unlock_mm(struct mmap_unlock_irq_work *work, struct mm_struct *mm) +{ + if (!work) { + mmap_read_unlock(mm); + } else { + work->mm = mm; + + /* The lock will be released once we're out of interrupt + * context. Tell lockdep that we've released it now so + * it doesn't complain that we forgot to release it. + */ + rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_); + irq_work_queue(&work->irq_work); + } +} + +#endif /* __MMAP_UNLOCK_WORK_H__ */ diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 6e75bbee39f0..1de0a1b03636 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -7,10 +7,10 @@ #include #include #include -#include #include #include #include "percpu_freelist.h" +#include "mmap_unlock_work.h" #define STACK_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY | \ @@ -31,25 +31,6 @@ struct bpf_stack_map { struct stack_map_bucket *buckets[]; }; -/* irq_work to run up_read() for build_id lookup in nmi context */ -struct stack_map_irq_work { - struct irq_work irq_work; - struct mm_struct *mm; -}; - -static void do_up_read(struct irq_work *entry) -{ - struct stack_map_irq_work *work; - - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) - return; - - work = container_of(entry, struct stack_map_irq_work, irq_work); - mmap_read_unlock_non_owner(work->mm); -} - -static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work); - static inline bool stack_map_use_build_id(struct bpf_map *map) { return (map->map_flags & BPF_F_STACK_BUILD_ID); @@ -149,35 +130,13 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; + struct mmap_unlock_irq_work *work = NULL; + bool irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); struct vm_area_struct *vma; - bool irq_work_busy = false; - struct stack_map_irq_work *work = NULL; - - if (irqs_disabled()) { - if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { - work = this_cpu_ptr(&up_read_work); - if (irq_work_is_busy(&work->irq_work)) { - /* cannot queue more up_read, fallback */ - irq_work_busy = true; - } - } else { - /* - * PREEMPT_RT does not allow to trylock mmap sem in - * interrupt disabled context. Force the fallback code. - */ - irq_work_busy = true; - } - } - /* - * We cannot do up_read() when the irq is disabled, because of - * risk to deadlock with rq_lock. To do build_id lookup when the - * irqs are disabled, we need to run up_read() in irq_work. We use - * a percpu variable to do the irq_work. If the irq_work is - * already used by another lookup, we fall back to report ips. - * - * Same fallback is used for kernel stack (!user) on a stackmap - * with build_id. + /* If the irq_work is in use, fall back to report ips. Same + * fallback is used for kernel stack (!user) on a stackmap with + * build_id. */ if (!user || !current || !current->mm || irq_work_busy || !mmap_read_trylock(current->mm)) { @@ -203,19 +162,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, - vma->vm_start; id_offs[i].status = BPF_STACK_BUILD_ID_VALID; } - - if (!work) { - mmap_read_unlock(current->mm); - } else { - work->mm = current->mm; - - /* The lock will be released once we're out of interrupt - * context. Tell lockdep that we've released it now so - * it doesn't complain that we forgot to release it. - */ - rwsem_release(¤t->mm->mmap_lock.dep_map, _RET_IP_); - irq_work_queue(&work->irq_work); - } + bpf_mmap_unlock_mm(work, current->mm); } static struct perf_callchain_entry * @@ -719,16 +666,3 @@ const struct bpf_map_ops stack_trace_map_ops = { .map_btf_name = "bpf_stack_map", .map_btf_id = &stack_trace_map_btf_id, }; - -static int __init stack_map_init(void) -{ - int cpu; - struct stack_map_irq_work *work; - - for_each_possible_cpu(cpu) { - work = per_cpu_ptr(&up_read_work, cpu); - init_irq_work(&work->irq_work, do_up_read); - } - return 0; -} -subsys_initcall(stack_map_init); diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index b48750bfba5a..f171479f7dd6 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -8,6 +8,7 @@ #include #include #include +#include "mmap_unlock_work.h" struct bpf_iter_seq_task_common { struct pid_namespace *ns; @@ -524,10 +525,6 @@ static const struct seq_operations task_vma_seq_ops = { .show = task_vma_seq_show, }; -BTF_ID_LIST(btf_task_file_ids) -BTF_ID(struct, file) -BTF_ID(struct, vm_area_struct) - static const struct bpf_iter_seq_info task_seq_info = { .seq_ops = &task_seq_ops, .init_seq_private = init_seq_pidns, @@ -586,9 +583,74 @@ static struct bpf_iter_reg task_vma_reg_info = { .seq_info = &task_vma_seq_info, }; +BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start, + bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags) +{ + struct mmap_unlock_irq_work *work = NULL; + struct vm_area_struct *vma; + bool irq_work_busy = false; + struct mm_struct *mm; + int ret = -ENOENT; + + if (flags) + return -EINVAL; + + if (!task) + return -ENOENT; + + mm = task->mm; + if (!mm) + return -ENOENT; + + irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); + + if (irq_work_busy || !mmap_read_trylock(mm)) + return -EBUSY; + + vma = find_vma(mm, start); + + if (vma && vma->vm_start <= start && vma->vm_end > start) { + callback_fn((u64)(long)task, (u64)(long)vma, + (u64)(long)callback_ctx, 0, 0); + ret = 0; + } + bpf_mmap_unlock_mm(work, mm); + return ret; +} + +const struct bpf_func_proto bpf_find_vma_proto = { + .func = bpf_find_vma, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_task_struct_ids[0], + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_FUNC, + .arg4_type = ARG_PTR_TO_STACK_OR_NULL, + .arg5_type = ARG_ANYTHING, +}; + +DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +static void do_mmap_read_unlock(struct irq_work *entry) +{ + struct mmap_unlock_irq_work *work; + + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + + work = container_of(entry, struct mmap_unlock_irq_work, irq_work); + mmap_read_unlock_non_owner(work->mm); +} + static int __init task_iter_init(void) { - int ret; + struct mmap_unlock_irq_work *work; + int ret, cpu; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&mmap_unlock_work, cpu); + init_irq_work(&work->irq_work, do_mmap_read_unlock); + } task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; ret = bpf_iter_reg_target(&task_reg_info); @@ -596,13 +658,13 @@ static int __init task_iter_init(void) return ret; task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[0]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_struct_ids[1]; ret = bpf_iter_reg_target(&task_file_reg_info); if (ret) return ret; task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_struct_ids[2]; return bpf_iter_reg_target(&task_vma_reg_info); } late_initcall(task_iter_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0dca726ebfd..1aafb43f61d1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6132,6 +6132,33 @@ static int set_timer_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_find_vma_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_find_vma(struct task_struct *task, u64 addr, + * void *callback_fn, void *callback_ctx, u64 flags) + * (callback_fn)(struct task_struct *task, + * struct vm_area_struct *vma, void *callback_ctx); + */ + callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1]; + + callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; + __mark_reg_known_zero(&callee->regs[BPF_REG_2]); + callee->regs[BPF_REG_2].btf = btf_vmlinux; + callee->regs[BPF_REG_2].btf_id = btf_task_struct_ids[2]; + + /* pointer to stack or null */ + callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + callee->in_callback_fn = true; + return 0; +} + static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { struct bpf_verifier_state *state = env->cur_state; @@ -6489,6 +6516,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } + if (func_id == BPF_FUNC_find_vma) { + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_find_vma_callback_state); + if (err < 0) + return -EINVAL; + } + if (func_id == BPF_FUNC_snprintf) { err = check_bpf_snprintf_call(env, regs); if (err < 0) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7396488793ff..390176a3031a 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1208,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_find_vma: + return &bpf_find_vma_proto; case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index ba5af15e25f5..509eee5f0393 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4938,6 +4938,25 @@ union bpf_attr { * **-ENOENT** if symbol is not found. * * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5120,6 +5139,7 @@ union bpf_attr { FN(trace_vprintk), \ FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ + FN(find_vma), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From e1c9788cb39777e81ebfbf31ae80b4ec14eb6f6d Mon Sep 17 00:00:00 2001 From: Kotresh HR Date: Mon, 27 Sep 2021 19:22:27 +0530 Subject: ceph: don't rely on error_string to validate blocklisted session. The "error_string" in the metadata of MClientSession is being parsed by kclient to validate whether the session is blocklisted. The "error_string" is for humans and shouldn't be relied on it. Hence added the flag to MClientsession to indicate the session is blocklisted. [ jlayton: minor formatting cleanup ] URL: https://tracker.ceph.com/issues/47450 Signed-off-by: Kotresh HR Signed-off-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/mds_client.c | 21 +++++++++++++++++++-- include/linux/ceph/ceph_fs.h | 2 ++ 2 files changed, 21 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 52d1b538c656..522790c64db4 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3361,9 +3361,14 @@ static void handle_session(struct ceph_mds_session *session, if (msg_version >= 3) { u32 len; - /* version >= 2, metadata */ - if (__decode_session_metadata(&p, end, &blocklisted) < 0) + /* version >= 2 and < 5, decode metadata, skip otherwise + * as it's handled via flags. + */ + if (msg_version >= 5) + ceph_decode_skip_map(&p, end, string, string, bad); + else if (__decode_session_metadata(&p, end, &blocklisted) < 0) goto bad; + /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); if (len) { @@ -3372,6 +3377,18 @@ static void handle_session(struct ceph_mds_session *session, } } + if (msg_version >= 5) { + u32 flags; + /* version >= 4, struct_v, struct_cv, len, metric_spec */ + ceph_decode_skip_n(&p, end, 2 + sizeof(u32) * 2, bad); + /* version >= 5, flags */ + ceph_decode_32_safe(&p, end, flags, bad); + if (flags & CEPH_SESSION_BLOCKLISTED) { + pr_warn("mds%d session blocklisted\n", session->s_mds); + blocklisted = true; + } + } + mutex_lock(&mdsc->mutex); if (op == CEPH_SESSION_CLOSE) { ceph_get_mds_session(session); diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h index bc2699feddbe..7ad6c3d0db7d 100644 --- a/include/linux/ceph/ceph_fs.h +++ b/include/linux/ceph/ceph_fs.h @@ -302,6 +302,8 @@ enum { CEPH_SESSION_REQUEST_FLUSH_MDLOG, }; +#define CEPH_SESSION_BLOCKLISTED (1 << 0) /* session blocklisted */ + extern const char *ceph_session_op_name(int op); struct ceph_mds_session_head { -- cgit v1.2.3 From aca39d9e86f3edeaac5d2c467f5fd31e0b0df606 Mon Sep 17 00:00:00 2001 From: Luís Henriques Date: Thu, 4 Nov 2021 12:31:46 +0000 Subject: libceph, ceph: move ceph_osdc_copy_from() into cephfs code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch moves ceph_osdc_copy_from() function out of libceph code into cephfs. There are no other users for this function, and there is the need (in another patch) to access internal ceph_osd_request struct members. Signed-off-by: Luís Henriques Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- fs/ceph/file.c | 74 +++++++++++++++++++++++++++++++++++------ include/linux/ceph/osd_client.h | 19 +++++------ net/ceph/osd_client.c | 60 +++++---------------------------- 3 files changed, 80 insertions(+), 73 deletions(-) (limited to 'include/linux') diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 6005b430f6f7..6c77f203e7b5 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2211,6 +2211,54 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode, return 0; } +static struct ceph_osd_request * +ceph_alloc_copyfrom_request(struct ceph_osd_client *osdc, + u64 src_snapid, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + struct ceph_object_id *dst_oid, + struct ceph_object_locator *dst_oloc, + u32 truncate_seq, u64 truncate_size) +{ + struct ceph_osd_request *req; + int ret; + u32 src_fadvise_flags = + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_NOCACHE; + u32 dst_fadvise_flags = + CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | + CEPH_OSD_OP_FLAG_FADVISE_DONTNEED; + + req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); + if (!req) + return ERR_PTR(-ENOMEM); + + req->r_flags = CEPH_OSD_FLAG_WRITE; + + ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); + ceph_oid_copy(&req->r_t.base_oid, dst_oid); + + ret = osd_req_op_copy_from_init(req, src_snapid, 0, + src_oid, src_oloc, + src_fadvise_flags, + dst_fadvise_flags, + truncate_seq, + truncate_size, + CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + if (ret) + goto out; + + ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); + if (ret) + goto out; + + return req; + +out: + ceph_osdc_put_request(req); + return ERR_PTR(ret); +} + static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off, struct ceph_inode_info *dst_ci, u64 *dst_off, struct ceph_fs_client *fsc, @@ -2218,6 +2266,8 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off { struct ceph_object_locator src_oloc, dst_oloc; struct ceph_object_id src_oid, dst_oid; + struct ceph_osd_client *osdc; + struct ceph_osd_request *req; size_t bytes = 0; u64 src_objnum, src_objoff, dst_objnum, dst_objoff; u32 src_objlen, dst_objlen; @@ -2228,6 +2278,7 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns); dst_oloc.pool = dst_ci->i_layout.pool_id; dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns); + osdc = &fsc->client->osdc; while (len >= object_size) { ceph_calc_file_object_mapping(&src_ci->i_layout, *src_off, @@ -2243,17 +2294,18 @@ static ssize_t ceph_do_objects_copy(struct ceph_inode_info *src_ci, u64 *src_off ceph_oid_printf(&dst_oid, "%llx.%08llx", dst_ci->i_vino.ino, dst_objnum); /* Do an object remote copy */ - ret = ceph_osdc_copy_from(&fsc->client->osdc, - src_ci->i_vino.snap, 0, - &src_oid, &src_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_NOCACHE, - &dst_oid, &dst_oloc, - CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL | - CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, - dst_ci->i_truncate_seq, - dst_ci->i_truncate_size, - CEPH_OSD_COPY_FROM_FLAG_TRUNCATE_SEQ); + req = ceph_alloc_copyfrom_request(osdc, src_ci->i_vino.snap, + &src_oid, &src_oloc, + &dst_oid, &dst_oloc, + dst_ci->i_truncate_seq, + dst_ci->i_truncate_size); + if (IS_ERR(req)) + ret = PTR_ERR(req); + else { + ceph_osdc_start_request(osdc, req, false); + ret = ceph_osdc_wait_request(osdc, req); + ceph_osdc_put_request(req); + } if (ret) { if (ret == -EOPNOTSUPP) { fsc->have_copy_from2 = false; diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 83fa08a06507..3431011f364d 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -475,6 +475,14 @@ extern void osd_req_op_alloc_hint_init(struct ceph_osd_request *osd_req, u64 expected_object_size, u64 expected_write_size, u32 flags); +extern int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u32 dst_fadvise_flags, + u32 truncate_seq, u64 truncate_size, + u8 copy_from_flags); extern struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc, struct ceph_snap_context *snapc, @@ -515,17 +523,6 @@ int ceph_osdc_call(struct ceph_osd_client *osdc, struct page *req_page, size_t req_len, struct page **resp_pages, size_t *resp_len); -int ceph_osdc_copy_from(struct ceph_osd_client *osdc, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - struct ceph_object_id *dst_oid, - struct ceph_object_locator *dst_oloc, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags); - /* watch/notify */ struct ceph_osd_linger_request * ceph_osdc_watch(struct ceph_osd_client *osdc, diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index ff8624a7c964..1c5815530e0d 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -5310,14 +5310,14 @@ void ceph_osdc_stop(struct ceph_osd_client *osdc) ceph_msgpool_destroy(&osdc->msgpool_op_reply); } -static int osd_req_op_copy_from_init(struct ceph_osd_request *req, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags) +int osd_req_op_copy_from_init(struct ceph_osd_request *req, + u64 src_snapid, u64 src_version, + struct ceph_object_id *src_oid, + struct ceph_object_locator *src_oloc, + u32 src_fadvise_flags, + u32 dst_fadvise_flags, + u32 truncate_seq, u64 truncate_size, + u8 copy_from_flags) { struct ceph_osd_req_op *op; struct page **pages; @@ -5346,49 +5346,7 @@ static int osd_req_op_copy_from_init(struct ceph_osd_request *req, op->indata_len, 0, false, true); return 0; } - -int ceph_osdc_copy_from(struct ceph_osd_client *osdc, - u64 src_snapid, u64 src_version, - struct ceph_object_id *src_oid, - struct ceph_object_locator *src_oloc, - u32 src_fadvise_flags, - struct ceph_object_id *dst_oid, - struct ceph_object_locator *dst_oloc, - u32 dst_fadvise_flags, - u32 truncate_seq, u64 truncate_size, - u8 copy_from_flags) -{ - struct ceph_osd_request *req; - int ret; - - req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL); - if (!req) - return -ENOMEM; - - req->r_flags = CEPH_OSD_FLAG_WRITE; - - ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc); - ceph_oid_copy(&req->r_t.base_oid, dst_oid); - - ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid, - src_oloc, src_fadvise_flags, - dst_fadvise_flags, truncate_seq, - truncate_size, copy_from_flags); - if (ret) - goto out; - - ret = ceph_osdc_alloc_messages(req, GFP_KERNEL); - if (ret) - goto out; - - ceph_osdc_start_request(osdc, req, false); - ret = ceph_osdc_wait_request(osdc, req); - -out: - ceph_osdc_put_request(req); - return ret; -} -EXPORT_SYMBOL(ceph_osdc_copy_from); +EXPORT_SYMBOL(osd_req_op_copy_from_init); int __init ceph_osdc_setup(void) { -- cgit v1.2.3 From c6975d7cab5b903aadbc0f78f9af4fae1bd23a50 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Fri, 5 Nov 2021 11:05:09 -0400 Subject: arm64: Track no early_pgtable_alloc() for kmemleak After switched page size from 64KB to 4KB on several arm64 servers here, kmemleak starts to run out of early memory pool due to a huge number of those early_pgtable_alloc() calls: kmemleak_alloc_phys() memblock_alloc_range_nid() memblock_phys_alloc_range() early_pgtable_alloc() init_pmd() alloc_init_pud() __create_pgd_mapping() __map_memblock() paging_init() setup_arch() start_kernel() Increased the default value of DEBUG_KMEMLEAK_MEM_POOL_SIZE by 4 times won't be enough for a server with 200GB+ memory. There isn't much interesting to check memory leaks for those early page tables and those early memory mappings should not reference to other memory. Hence, no kmemleak false positives, and we can safely skip tracking those early allocations from kmemleak like we did in the commit fed84c785270 ("mm/memblock.c: skip kmemleak for kasan_init()") without needing to introduce complications to automatically scale the value depends on the runtime memory size etc. After the patch, the default value of DEBUG_KMEMLEAK_MEM_POOL_SIZE becomes sufficient again. Signed-off-by: Qian Cai Reviewed-by: Catalin Marinas Reviewed-by: Mike Rapoport Link: https://lore.kernel.org/r/20211105150509.7826-1-quic_qiancai@quicinc.com Signed-off-by: Will Deacon --- arch/arm/mm/kasan_init.c | 2 +- arch/arm64/mm/kasan_init.c | 5 +++-- arch/arm64/mm/mmu.c | 3 ++- include/linux/memblock.h | 2 +- mm/memblock.c | 9 ++++++--- 5 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/kasan_init.c b/arch/arm/mm/kasan_init.c index 9c348042a724..4508aba8a58b 100644 --- a/arch/arm/mm/kasan_init.c +++ b/arch/arm/mm/kasan_init.c @@ -32,7 +32,7 @@ pmd_t tmp_pmd_table[PTRS_PER_PMD] __page_aligned_bss; static __init void *kasan_alloc_block(size_t size) { return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_KASAN, NUMA_NO_NODE); + MEMBLOCK_ALLOC_NOLEAKTRACE, NUMA_NO_NODE); } static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 61b52a92b8b6..995ac7540e6a 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -36,7 +36,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node) { void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_KASAN, node); + MEMBLOCK_ALLOC_NOLEAKTRACE, node); if (!p) panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n", __func__, PAGE_SIZE, PAGE_SIZE, node, @@ -49,7 +49,8 @@ static phys_addr_t __init kasan_alloc_raw_page(int node) { void *p = memblock_alloc_try_nid_raw(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_KASAN, node); + MEMBLOCK_ALLOC_NOLEAKTRACE, + node); if (!p) panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%llx\n", __func__, PAGE_SIZE, PAGE_SIZE, node, diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index fd85b51b9d50..4b83b7a9fafb 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -96,7 +96,8 @@ static phys_addr_t __init early_pgtable_alloc(int shift) phys_addr_t phys; void *ptr; - phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); + phys = memblock_phys_alloc_range(PAGE_SIZE, PAGE_SIZE, 0, + MEMBLOCK_ALLOC_NOLEAKTRACE); if (!phys) panic("Failed to allocate page table page\n"); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 34de69b3b8ba..efc896155dae 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -372,7 +372,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r) /* Flags for memblock allocation APIs */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 -#define MEMBLOCK_ALLOC_KASAN 1 +#define MEMBLOCK_ALLOC_NOLEAKTRACE 1 /* We are using top down, so it is safe to use 0 here */ #define MEMBLOCK_LOW_LIMIT 0 diff --git a/mm/memblock.c b/mm/memblock.c index 184dcd2e5d99..fdc93a97bac2 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -287,7 +287,7 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, { /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || - end == MEMBLOCK_ALLOC_KASAN) + end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ @@ -1379,8 +1379,11 @@ again: return 0; done: - /* Skip kmemleak for kasan_init() due to high volume. */ - if (end != MEMBLOCK_ALLOC_KASAN) + /* + * Skip kmemleak for those places like kasan_init() and + * early_pgtable_alloc() due to high volume. + */ + if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* * The min_count is set to 0 so that memblock allocated * blocks are never reported as leaks. This is because many -- cgit v1.2.3 From dfd5bb23ad75bdabde89ac3166705a450bf16acb Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Wed, 5 May 2021 14:00:06 +0200 Subject: PCI: Export pci_dev_lock() Commit e3a9b1212b9d ("PCI: Export pci_dev_trylock() and pci_dev_unlock()") already exported pci_dev_trylock()/pci_dev_unlock() however in some circumstances such as during error recovery it makes sense to block waiting to get full access to the device so also export pci_dev_lock(). Link: https://lore.kernel.org/all/20210928181014.GA713179@bhelgaas/ Acked-by: Pierre Morel Acked-by: Bjorn Helgaas Signed-off-by: Niklas Schnelle Signed-off-by: Vasily Gorbik --- drivers/pci/pci.c | 3 ++- include/linux/pci.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index da75c422ba85..193bfcda9c26 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -5074,12 +5074,13 @@ static int pci_reset_bus_function(struct pci_dev *dev, bool probe) return pci_parent_bus_reset(dev, probe); } -static void pci_dev_lock(struct pci_dev *dev) +void pci_dev_lock(struct pci_dev *dev) { pci_cfg_access_lock(dev); /* block PM suspend, driver probe, etc. */ device_lock(&dev->dev); } +EXPORT_SYMBOL_GPL(pci_dev_lock); /* Return 1 on successful lock, 0 on contention */ int pci_dev_trylock(struct pci_dev *dev) diff --git a/include/linux/pci.h b/include/linux/pci.h index b4dbcc86b3f1..d307b071b65e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1664,6 +1664,7 @@ void pci_cfg_access_lock(struct pci_dev *dev); bool pci_cfg_access_trylock(struct pci_dev *dev); void pci_cfg_access_unlock(struct pci_dev *dev); +void pci_dev_lock(struct pci_dev *dev); int pci_dev_trylock(struct pci_dev *dev); void pci_dev_unlock(struct pci_dev *dev); -- cgit v1.2.3 From 40a34121ac1dc52ed9cd34a8f4e48e32517a52fd Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Wed, 3 Nov 2021 13:47:32 -0700 Subject: bpf, sockmap: Use stricter sk state checks in sk_lookup_assign In order to fix an issue with sockets in TCP sockmap redirect cases we plan to allow CLOSE state sockets to exist in the sockmap. However, the check in bpf_sk_lookup_assign() currently only invalidates sockets in the TCP_ESTABLISHED case relying on the checks on sockmap insert to ensure we never SOCK_CLOSE state sockets in the map. To prepare for this change we flip the logic in bpf_sk_lookup_assign() to explicitly test for the accepted cases. Namely, a tcp socket in TCP_LISTEN or a udp socket in TCP_CLOSE state. This also makes the code more resilent to future changes. Suggested-by: Jakub Sitnicki Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20211103204736.248403-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 12 ++++++++++++ net/core/filter.c | 6 ++++-- net/core/sock_map.c | 6 ------ 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index b4256847c707..584d94be9c8b 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -507,6 +507,18 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } +static inline bool sk_is_tcp(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && + sk->sk_protocol == IPPROTO_TCP; +} + +static inline bool sk_is_udp(const struct sock *sk) +{ + return sk->sk_type == SOCK_DGRAM && + sk->sk_protocol == IPPROTO_UDP; +} + #if IS_ENABLED(CONFIG_NET_SOCK_MSG) #define BPF_F_STRPARSER (1UL << 1) diff --git a/net/core/filter.c b/net/core/filter.c index 8e8d3b49c297..a68418268e92 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10423,8 +10423,10 @@ BPF_CALL_3(bpf_sk_lookup_assign, struct bpf_sk_lookup_kern *, ctx, return -EINVAL; if (unlikely(sk && sk_is_refcounted(sk))) return -ESOCKTNOSUPPORT; /* reject non-RCU freed sockets */ - if (unlikely(sk && sk->sk_state == TCP_ESTABLISHED)) - return -ESOCKTNOSUPPORT; /* reject connected sockets */ + if (unlikely(sk && sk_is_tcp(sk) && sk->sk_state != TCP_LISTEN)) + return -ESOCKTNOSUPPORT; /* only accept TCP socket in LISTEN */ + if (unlikely(sk && sk_is_udp(sk) && sk->sk_state != TCP_CLOSE)) + return -ESOCKTNOSUPPORT; /* only accept UDP socket in CLOSE */ /* Check if socket is suitable for packet L3/L4 protocol */ if (sk && sk->sk_protocol != ctx->protocol) diff --git a/net/core/sock_map.c b/net/core/sock_map.c index e252b8ec2b85..f39ef79ced67 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -511,12 +511,6 @@ static bool sock_map_op_okay(const struct bpf_sock_ops_kern *ops) ops->op == BPF_SOCK_OPS_TCP_LISTEN_CB; } -static bool sk_is_tcp(const struct sock *sk) -{ - return sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP; -} - static bool sock_map_redirect_allowed(const struct sock *sk) { if (sk_is_tcp(sk)) -- cgit v1.2.3 From cf30f6a5f0c60ec98a637b836bef6915f602c6ab Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Fri, 11 Sep 2020 16:49:00 -0700 Subject: lib: zstd: Add kernel-specific API This patch: - Moves `include/linux/zstd.h` -> `include/linux/zstd_lib.h` - Updates modified zstd headers to yearless copyright - Adds a new API in `include/linux/zstd.h` that is functionally equivalent to the in-use subset of the current API. Functions are renamed to avoid symbol collisions with zstd, to make it clear it is not the upstream zstd API, and to follow the kernel style guide. - Updates all callers to use the new API. There are no functional changes in this patch. Since there are no functional change, I felt it was okay to update all the callers in a single patch. Once the API is approved, the callers are mechanically changed. This patch is preparing for the 3rd patch in this series, which updates zstd to version 1.4.10. Since the upstream zstd API is no longer exposed to callers, the update can happen transparently. Signed-off-by: Nick Terrell Tested By: Paul Jones Tested-by: Oleksandr Natalenko Tested-by: Sedat Dilek # LLVM/Clang v13.0.0 on x86-64 Tested-by: Jean-Denis Girard --- crypto/zstd.c | 28 +- fs/btrfs/zstd.c | 68 +-- fs/f2fs/compress.c | 56 +- fs/f2fs/super.c | 2 +- fs/pstore/platform.c | 2 +- fs/squashfs/zstd_wrapper.c | 16 +- include/linux/zstd.h | 1243 ++++++++++---------------------------------- include/linux/zstd_lib.h | 1157 +++++++++++++++++++++++++++++++++++++++++ lib/decompress_unzstd.c | 42 +- lib/zstd/compress.c | 123 +++-- lib/zstd/decompress.c | 112 ++-- 11 files changed, 1691 insertions(+), 1158 deletions(-) create mode 100644 include/linux/zstd_lib.h (limited to 'include/linux') diff --git a/crypto/zstd.c b/crypto/zstd.c index 1a3309f066f7..154a969c83a8 100644 --- a/crypto/zstd.c +++ b/crypto/zstd.c @@ -18,22 +18,22 @@ #define ZSTD_DEF_LEVEL 3 struct zstd_ctx { - ZSTD_CCtx *cctx; - ZSTD_DCtx *dctx; + zstd_cctx *cctx; + zstd_dctx *dctx; void *cwksp; void *dwksp; }; -static ZSTD_parameters zstd_params(void) +static zstd_parameters zstd_params(void) { - return ZSTD_getParams(ZSTD_DEF_LEVEL, 0, 0); + return zstd_get_params(ZSTD_DEF_LEVEL, 0); } static int zstd_comp_init(struct zstd_ctx *ctx) { int ret = 0; - const ZSTD_parameters params = zstd_params(); - const size_t wksp_size = ZSTD_CCtxWorkspaceBound(params.cParams); + const zstd_parameters params = zstd_params(); + const size_t wksp_size = zstd_cctx_workspace_bound(¶ms.cParams); ctx->cwksp = vzalloc(wksp_size); if (!ctx->cwksp) { @@ -41,7 +41,7 @@ static int zstd_comp_init(struct zstd_ctx *ctx) goto out; } - ctx->cctx = ZSTD_initCCtx(ctx->cwksp, wksp_size); + ctx->cctx = zstd_init_cctx(ctx->cwksp, wksp_size); if (!ctx->cctx) { ret = -EINVAL; goto out_free; @@ -56,7 +56,7 @@ out_free: static int zstd_decomp_init(struct zstd_ctx *ctx) { int ret = 0; - const size_t wksp_size = ZSTD_DCtxWorkspaceBound(); + const size_t wksp_size = zstd_dctx_workspace_bound(); ctx->dwksp = vzalloc(wksp_size); if (!ctx->dwksp) { @@ -64,7 +64,7 @@ static int zstd_decomp_init(struct zstd_ctx *ctx) goto out; } - ctx->dctx = ZSTD_initDCtx(ctx->dwksp, wksp_size); + ctx->dctx = zstd_init_dctx(ctx->dwksp, wksp_size); if (!ctx->dctx) { ret = -EINVAL; goto out_free; @@ -152,10 +152,10 @@ static int __zstd_compress(const u8 *src, unsigned int slen, { size_t out_len; struct zstd_ctx *zctx = ctx; - const ZSTD_parameters params = zstd_params(); + const zstd_parameters params = zstd_params(); - out_len = ZSTD_compressCCtx(zctx->cctx, dst, *dlen, src, slen, params); - if (ZSTD_isError(out_len)) + out_len = zstd_compress_cctx(zctx->cctx, dst, *dlen, src, slen, ¶ms); + if (zstd_is_error(out_len)) return -EINVAL; *dlen = out_len; return 0; @@ -182,8 +182,8 @@ static int __zstd_decompress(const u8 *src, unsigned int slen, size_t out_len; struct zstd_ctx *zctx = ctx; - out_len = ZSTD_decompressDCtx(zctx->dctx, dst, *dlen, src, slen); - if (ZSTD_isError(out_len)) + out_len = zstd_decompress_dctx(zctx->dctx, dst, *dlen, src, slen); + if (zstd_is_error(out_len)) return -EINVAL; *dlen = out_len; return 0; diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c index f06b68040352..fc42dd0badd7 100644 --- a/fs/btrfs/zstd.c +++ b/fs/btrfs/zstd.c @@ -28,10 +28,10 @@ /* 307s to avoid pathologically clashing with transaction commit */ #define ZSTD_BTRFS_RECLAIM_JIFFIES (307 * HZ) -static ZSTD_parameters zstd_get_btrfs_parameters(unsigned int level, +static zstd_parameters zstd_get_btrfs_parameters(unsigned int level, size_t src_len) { - ZSTD_parameters params = ZSTD_getParams(level, src_len, 0); + zstd_parameters params = zstd_get_params(level, src_len); if (params.cParams.windowLog > ZSTD_BTRFS_MAX_WINDOWLOG) params.cParams.windowLog = ZSTD_BTRFS_MAX_WINDOWLOG; @@ -48,8 +48,8 @@ struct workspace { unsigned long last_used; /* jiffies */ struct list_head list; struct list_head lru_list; - ZSTD_inBuffer in_buf; - ZSTD_outBuffer out_buf; + zstd_in_buffer in_buf; + zstd_out_buffer out_buf; }; /* @@ -155,12 +155,12 @@ static void zstd_calc_ws_mem_sizes(void) unsigned int level; for (level = 1; level <= ZSTD_BTRFS_MAX_LEVEL; level++) { - ZSTD_parameters params = + zstd_parameters params = zstd_get_btrfs_parameters(level, ZSTD_BTRFS_MAX_INPUT); size_t level_size = max_t(size_t, - ZSTD_CStreamWorkspaceBound(params.cParams), - ZSTD_DStreamWorkspaceBound(ZSTD_BTRFS_MAX_INPUT)); + zstd_cstream_workspace_bound(¶ms.cParams), + zstd_dstream_workspace_bound(ZSTD_BTRFS_MAX_INPUT)); max_size = max_t(size_t, max_size, level_size); zstd_ws_mem_sizes[level - 1] = max_size; @@ -371,7 +371,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long *total_in, unsigned long *total_out) { struct workspace *workspace = list_entry(ws, struct workspace, list); - ZSTD_CStream *stream; + zstd_cstream *stream; int ret = 0; int nr_pages = 0; struct page *in_page = NULL; /* The current page to read */ @@ -381,7 +381,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, unsigned long len = *total_out; const unsigned long nr_dest_pages = *out_pages; unsigned long max_out = nr_dest_pages * PAGE_SIZE; - ZSTD_parameters params = zstd_get_btrfs_parameters(workspace->req_level, + zstd_parameters params = zstd_get_btrfs_parameters(workspace->req_level, len); *out_pages = 0; @@ -389,10 +389,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, *total_in = 0; /* Initialize the stream */ - stream = ZSTD_initCStream(params, len, workspace->mem, + stream = zstd_init_cstream(¶ms, len, workspace->mem, workspace->size); if (!stream) { - pr_warn("BTRFS: ZSTD_initCStream failed\n"); + pr_warn("BTRFS: zstd_init_cstream failed\n"); ret = -EIO; goto out; } @@ -418,11 +418,11 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, while (1) { size_t ret2; - ret2 = ZSTD_compressStream(stream, &workspace->out_buf, + ret2 = zstd_compress_stream(stream, &workspace->out_buf, &workspace->in_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_compressStream returned %d\n", - ZSTD_getErrorCode(ret2)); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_compress_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto out; } @@ -487,10 +487,10 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping, while (1) { size_t ret2; - ret2 = ZSTD_endStream(stream, &workspace->out_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_endStream returned %d\n", - ZSTD_getErrorCode(ret2)); + ret2 = zstd_end_stream(stream, &workspace->out_buf); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_end_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto out; } @@ -548,17 +548,17 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) struct workspace *workspace = list_entry(ws, struct workspace, list); struct page **pages_in = cb->compressed_pages; size_t srclen = cb->compressed_len; - ZSTD_DStream *stream; + zstd_dstream *stream; int ret = 0; unsigned long page_in_index = 0; unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE); unsigned long buf_start; unsigned long total_out = 0; - stream = ZSTD_initDStream( + stream = zstd_init_dstream( ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); if (!stream) { - pr_debug("BTRFS: ZSTD_initDStream failed\n"); + pr_debug("BTRFS: zstd_init_dstream failed\n"); ret = -EIO; goto done; } @@ -574,11 +574,11 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb) while (1) { size_t ret2; - ret2 = ZSTD_decompressStream(stream, &workspace->out_buf, + ret2 = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", - ZSTD_getErrorCode(ret2)); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_decompress_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto done; } @@ -624,16 +624,16 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in, size_t destlen) { struct workspace *workspace = list_entry(ws, struct workspace, list); - ZSTD_DStream *stream; + zstd_dstream *stream; int ret = 0; size_t ret2; unsigned long total_out = 0; unsigned long pg_offset = 0; - stream = ZSTD_initDStream( + stream = zstd_init_dstream( ZSTD_BTRFS_MAX_INPUT, workspace->mem, workspace->size); if (!stream) { - pr_warn("BTRFS: ZSTD_initDStream failed\n"); + pr_warn("BTRFS: zstd_init_dstream failed\n"); ret = -EIO; goto finish; } @@ -657,15 +657,15 @@ int zstd_decompress(struct list_head *ws, unsigned char *data_in, /* Check if the frame is over and we still need more input */ if (ret2 == 0) { - pr_debug("BTRFS: ZSTD_decompressStream ended early\n"); + pr_debug("BTRFS: zstd_decompress_stream ended early\n"); ret = -EIO; goto finish; } - ret2 = ZSTD_decompressStream(stream, &workspace->out_buf, + ret2 = zstd_decompress_stream(stream, &workspace->out_buf, &workspace->in_buf); - if (ZSTD_isError(ret2)) { - pr_debug("BTRFS: ZSTD_decompressStream returned %d\n", - ZSTD_getErrorCode(ret2)); + if (zstd_is_error(ret2)) { + pr_debug("BTRFS: zstd_decompress_stream returned %d\n", + zstd_get_error_code(ret2)); ret = -EIO; goto finish; } diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c index 20a083dc9042..b8d70deddfb7 100644 --- a/fs/f2fs/compress.c +++ b/fs/f2fs/compress.c @@ -336,8 +336,8 @@ static const struct f2fs_compress_ops f2fs_lz4_ops = { static int zstd_init_compress_ctx(struct compress_ctx *cc) { - ZSTD_parameters params; - ZSTD_CStream *stream; + zstd_parameters params; + zstd_cstream *stream; void *workspace; unsigned int workspace_size; unsigned char level = F2FS_I(cc->inode)->i_compress_flag >> @@ -346,17 +346,17 @@ static int zstd_init_compress_ctx(struct compress_ctx *cc) if (!level) level = F2FS_ZSTD_DEFAULT_CLEVEL; - params = ZSTD_getParams(level, cc->rlen, 0); - workspace_size = ZSTD_CStreamWorkspaceBound(params.cParams); + params = zstd_get_params(F2FS_ZSTD_DEFAULT_CLEVEL, cc->rlen); + workspace_size = zstd_cstream_workspace_bound(¶ms.cParams); workspace = f2fs_kvmalloc(F2FS_I_SB(cc->inode), workspace_size, GFP_NOFS); if (!workspace) return -ENOMEM; - stream = ZSTD_initCStream(params, 0, workspace, workspace_size); + stream = zstd_init_cstream(¶ms, 0, workspace, workspace_size); if (!stream) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initCStream failed\n", + printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_cstream failed\n", KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, __func__); kvfree(workspace); @@ -379,9 +379,9 @@ static void zstd_destroy_compress_ctx(struct compress_ctx *cc) static int zstd_compress_pages(struct compress_ctx *cc) { - ZSTD_CStream *stream = cc->private2; - ZSTD_inBuffer inbuf; - ZSTD_outBuffer outbuf; + zstd_cstream *stream = cc->private2; + zstd_in_buffer inbuf; + zstd_out_buffer outbuf; int src_size = cc->rlen; int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE; int ret; @@ -394,19 +394,19 @@ static int zstd_compress_pages(struct compress_ctx *cc) outbuf.dst = cc->cbuf->cdata; outbuf.size = dst_size; - ret = ZSTD_compressStream(stream, &outbuf, &inbuf); - if (ZSTD_isError(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n", + ret = zstd_compress_stream(stream, &outbuf, &inbuf); + if (zstd_is_error(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s zstd_compress_stream failed, ret: %d\n", KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, - __func__, ZSTD_getErrorCode(ret)); + __func__, zstd_get_error_code(ret)); return -EIO; } - ret = ZSTD_endStream(stream, &outbuf); - if (ZSTD_isError(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_endStream returned %d\n", + ret = zstd_end_stream(stream, &outbuf); + if (zstd_is_error(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s zstd_end_stream returned %d\n", KERN_ERR, F2FS_I_SB(cc->inode)->sb->s_id, - __func__, ZSTD_getErrorCode(ret)); + __func__, zstd_get_error_code(ret)); return -EIO; } @@ -423,22 +423,22 @@ static int zstd_compress_pages(struct compress_ctx *cc) static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) { - ZSTD_DStream *stream; + zstd_dstream *stream; void *workspace; unsigned int workspace_size; unsigned int max_window_size = MAX_COMPRESS_WINDOW_SIZE(dic->log_cluster_size); - workspace_size = ZSTD_DStreamWorkspaceBound(max_window_size); + workspace_size = zstd_dstream_workspace_bound(max_window_size); workspace = f2fs_kvmalloc(F2FS_I_SB(dic->inode), workspace_size, GFP_NOFS); if (!workspace) return -ENOMEM; - stream = ZSTD_initDStream(max_window_size, workspace, workspace_size); + stream = zstd_init_dstream(max_window_size, workspace, workspace_size); if (!stream) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_initDStream failed\n", + printk_ratelimited("%sF2FS-fs (%s): %s zstd_init_dstream failed\n", KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, __func__); kvfree(workspace); @@ -460,9 +460,9 @@ static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic) static int zstd_decompress_pages(struct decompress_io_ctx *dic) { - ZSTD_DStream *stream = dic->private2; - ZSTD_inBuffer inbuf; - ZSTD_outBuffer outbuf; + zstd_dstream *stream = dic->private2; + zstd_in_buffer inbuf; + zstd_out_buffer outbuf; int ret; inbuf.pos = 0; @@ -473,11 +473,11 @@ static int zstd_decompress_pages(struct decompress_io_ctx *dic) outbuf.dst = dic->rbuf; outbuf.size = dic->rlen; - ret = ZSTD_decompressStream(stream, &outbuf, &inbuf); - if (ZSTD_isError(ret)) { - printk_ratelimited("%sF2FS-fs (%s): %s ZSTD_compressStream failed, ret: %d\n", + ret = zstd_decompress_stream(stream, &outbuf, &inbuf); + if (zstd_is_error(ret)) { + printk_ratelimited("%sF2FS-fs (%s): %s zstd_decompress_stream failed, ret: %d\n", KERN_ERR, F2FS_I_SB(dic->inode)->sb->s_id, - __func__, ZSTD_getErrorCode(ret)); + __func__, zstd_get_error_code(ret)); return -EIO; } diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index cf049a042482..78b64bf5e0f7 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -592,7 +592,7 @@ static int f2fs_set_zstd_level(struct f2fs_sb_info *sbi, const char *str) if (kstrtouint(str + 1, 10, &level)) return -EINVAL; - if (!level || level > ZSTD_maxCLevel()) { + if (!level || level > zstd_max_clevel()) { f2fs_info(sbi, "invalid zstd compress level: %d", level); return -EINVAL; } diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c index b9614db48b1d..f243cb5e6a4f 100644 --- a/fs/pstore/platform.c +++ b/fs/pstore/platform.c @@ -218,7 +218,7 @@ static int zbufsize_842(size_t size) #if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS) static int zbufsize_zstd(size_t size) { - return ZSTD_compressBound(size); + return zstd_compress_bound(size); } #endif diff --git a/fs/squashfs/zstd_wrapper.c b/fs/squashfs/zstd_wrapper.c index 0015cf8b5582..c40445dbf38c 100644 --- a/fs/squashfs/zstd_wrapper.c +++ b/fs/squashfs/zstd_wrapper.c @@ -34,7 +34,7 @@ static void *zstd_init(struct squashfs_sb_info *msblk, void *buff) goto failed; wksp->window_size = max_t(size_t, msblk->block_size, SQUASHFS_METADATA_SIZE); - wksp->mem_size = ZSTD_DStreamWorkspaceBound(wksp->window_size); + wksp->mem_size = zstd_dstream_workspace_bound(wksp->window_size); wksp->mem = vmalloc(wksp->mem_size); if (wksp->mem == NULL) goto failed; @@ -63,15 +63,15 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, struct squashfs_page_actor *output) { struct workspace *wksp = strm; - ZSTD_DStream *stream; + zstd_dstream *stream; size_t total_out = 0; int error = 0; - ZSTD_inBuffer in_buf = { NULL, 0, 0 }; - ZSTD_outBuffer out_buf = { NULL, 0, 0 }; + zstd_in_buffer in_buf = { NULL, 0, 0 }; + zstd_out_buffer out_buf = { NULL, 0, 0 }; struct bvec_iter_all iter_all = {}; struct bio_vec *bvec = bvec_init_iter_all(&iter_all); - stream = ZSTD_initDStream(wksp->window_size, wksp->mem, wksp->mem_size); + stream = zstd_init_dstream(wksp->window_size, wksp->mem, wksp->mem_size); if (!stream) { ERROR("Failed to initialize zstd decompressor\n"); @@ -116,14 +116,14 @@ static int zstd_uncompress(struct squashfs_sb_info *msblk, void *strm, } total_out -= out_buf.pos; - zstd_err = ZSTD_decompressStream(stream, &out_buf, &in_buf); + zstd_err = zstd_decompress_stream(stream, &out_buf, &in_buf); total_out += out_buf.pos; /* add the additional data produced */ if (zstd_err == 0) break; - if (ZSTD_isError(zstd_err)) { + if (zstd_is_error(zstd_err)) { ERROR("zstd decompression error: %d\n", - (int)ZSTD_getErrorCode(zstd_err)); + (int)zstd_get_error_code(zstd_err)); error = -EIO; break; } diff --git a/include/linux/zstd.h b/include/linux/zstd.h index e87f78c9b19c..9fbc7729b0a0 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -1,138 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of https://github.com/facebook/zstd) and + * the GPLv2 (found in the COPYING file in the root directory of + * https://github.com/facebook/zstd). You may select, at your option, one of the + * above-listed licenses. */ -#ifndef ZSTD_H -#define ZSTD_H +#ifndef LINUX_ZSTD_H +#define LINUX_ZSTD_H -/* ====== Dependency ======*/ -#include /* size_t */ +/** + * This is a kernel-style API that wraps the upstream zstd API, which cannot be + * used directly because the symbols aren't exported. It exposes the minimal + * functionality which is currently required by users of zstd in the kernel. + * Expose extra functions from lib/zstd/zstd.h as needed. + */ +/* ====== Dependency ====== */ +#include +#include -/*-***************************************************************************** - * Introduction +/* ====== Helper Functions ====== */ +/** + * zstd_compress_bound() - maximum compressed size in worst case scenario + * @src_size: The size of the data to compress. * - * zstd, short for Zstandard, is a fast lossless compression algorithm, - * targeting real-time compression scenarios at zlib-level and better - * compression ratios. The zstd compression library provides in-memory - * compression and decompression functions. The library supports compression - * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled - * ultra, should be used with caution, as they require more memory. - * Compression can be done in: - * - a single step, reusing a context (described as Explicit memory management) - * - unbounded multiple steps (described as Streaming compression) - * The compression ratio achievable on small data can be highly improved using - * compression with a dictionary in: - * - a single step (described as Simple dictionary API) - * - a single step, reusing a dictionary (described as Fast dictionary API) - ******************************************************************************/ - -/*====== Helper functions ======*/ + * Return: The maximum compressed size in the worst case scenario. + */ +size_t zstd_compress_bound(size_t src_size); /** - * enum ZSTD_ErrorCode - zstd error codes + * zstd_is_error() - tells if a size_t function result is an error code + * @code: The function result to check for error. * - * Functions that return size_t can be checked for errors using ZSTD_isError() - * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + * Return: Non-zero iff the code is an error. + */ +unsigned int zstd_is_error(size_t code); + +/** + * enum zstd_error_code - zstd error codes */ -typedef enum { - ZSTD_error_no_error, - ZSTD_error_GENERIC, - ZSTD_error_prefix_unknown, - ZSTD_error_version_unsupported, - ZSTD_error_parameter_unknown, - ZSTD_error_frameParameter_unsupported, - ZSTD_error_frameParameter_unsupportedBy32bits, - ZSTD_error_frameParameter_windowTooLarge, - ZSTD_error_compressionParameter_unsupported, - ZSTD_error_init_missing, - ZSTD_error_memory_allocation, - ZSTD_error_stage_wrong, - ZSTD_error_dstSize_tooSmall, - ZSTD_error_srcSize_wrong, - ZSTD_error_corruption_detected, - ZSTD_error_checksum_wrong, - ZSTD_error_tableLog_tooLarge, - ZSTD_error_maxSymbolValue_tooLarge, - ZSTD_error_maxSymbolValue_tooSmall, - ZSTD_error_dictionary_corrupted, - ZSTD_error_dictionary_wrong, - ZSTD_error_dictionaryCreation_failed, - ZSTD_error_maxCode -} ZSTD_ErrorCode; +typedef ZSTD_ErrorCode zstd_error_code; /** - * ZSTD_maxCLevel() - maximum compression level available + * zstd_get_error_code() - translates an error function result to an error code + * @code: The function result for which zstd_is_error(code) is true. * - * Return: Maximum compression level available. + * Return: A unique error code for this error. */ -int ZSTD_maxCLevel(void); +zstd_error_code zstd_get_error_code(size_t code); + /** - * ZSTD_compressBound() - maximum compressed size in worst case scenario - * @srcSize: The size of the data to compress. + * zstd_get_error_name() - translates an error function result to a string + * @code: The function result for which zstd_is_error(code) is true. * - * Return: The maximum compressed size in the worst case scenario. + * Return: An error string corresponding to the error code. */ -size_t ZSTD_compressBound(size_t srcSize); +const char *zstd_get_error_name(size_t code); + /** - * ZSTD_isError() - tells if a size_t function result is an error code - * @code: The function result to check for error. + * zstd_min_clevel() - minimum allowed compression level * - * Return: Non-zero iff the code is an error. + * Return: The minimum allowed compression level. */ -static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) -{ - return code > (size_t)-ZSTD_error_maxCode; -} +int zstd_min_clevel(void); + /** - * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode - * @functionResult: The result of a function for which ZSTD_isError() is true. + * zstd_max_clevel() - maximum allowed compression level * - * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 - * if the functionResult isn't an error. + * Return: The maximum allowed compression level. */ -static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( - size_t functionResult) -{ - if (!ZSTD_isError(functionResult)) - return (ZSTD_ErrorCode)0; - return (ZSTD_ErrorCode)(0 - functionResult); -} +int zstd_max_clevel(void); + +/* ====== Parameter Selection ====== */ /** - * enum ZSTD_strategy - zstd compression search strategy + * enum zstd_strategy - zstd compression search strategy * - * From faster to stronger. + * From faster to stronger. See zstd_lib.h. */ -typedef enum { - ZSTD_fast, - ZSTD_dfast, - ZSTD_greedy, - ZSTD_lazy, - ZSTD_lazy2, - ZSTD_btlazy2, - ZSTD_btopt, - ZSTD_btopt2 -} ZSTD_strategy; +typedef ZSTD_strategy zstd_strategy; /** - * struct ZSTD_compressionParameters - zstd compression parameters + * struct zstd_compression_parameters - zstd compression parameters * @windowLog: Log of the largest match distance. Larger means more * compression, and more memory needed during decompression. - * @chainLog: Fully searched segment. Larger means more compression, slower, - * and more memory (useless for fast). + * @chainLog: Fully searched segment. Larger means more compression, + * slower, and more memory (useless for fast). * @hashLog: Dispatch table. Larger means more compression, * slower, and more memory. * @searchLog: Number of searches. Larger means more compression and slower. @@ -141,1017 +99,342 @@ typedef enum { * @targetLength: Acceptable match size for optimal parser (only). Larger means * more compression, and slower. * @strategy: The zstd compression strategy. + * + * See zstd_lib.h. */ -typedef struct { - unsigned int windowLog; - unsigned int chainLog; - unsigned int hashLog; - unsigned int searchLog; - unsigned int searchLength; - unsigned int targetLength; - ZSTD_strategy strategy; -} ZSTD_compressionParameters; +typedef ZSTD_compressionParameters zstd_compression_parameters; /** - * struct ZSTD_frameParameters - zstd frame parameters - * @contentSizeFlag: Controls whether content size will be present in the frame - * header (when known). - * @checksumFlag: Controls whether a 32-bit checksum is generated at the end - * of the frame for error detection. - * @noDictIDFlag: Controls whether dictID will be saved into the frame header - * when using dictionary compression. + * struct zstd_frame_parameters - zstd frame parameters + * @contentSizeFlag: Controls whether content size will be present in the + * frame header (when known). + * @checksumFlag: Controls whether a 32-bit checksum is generated at the + * end of the frame for error detection. + * @noDictIDFlag: Controls whether dictID will be saved into the frame + * header when using dictionary compression. * - * The default value is all fields set to 0. + * The default value is all fields set to 0. See zstd_lib.h. */ -typedef struct { - unsigned int contentSizeFlag; - unsigned int checksumFlag; - unsigned int noDictIDFlag; -} ZSTD_frameParameters; +typedef ZSTD_frameParameters zstd_frame_parameters; /** - * struct ZSTD_parameters - zstd parameters + * struct zstd_parameters - zstd parameters * @cParams: The compression parameters. * @fParams: The frame parameters. */ -typedef struct { - ZSTD_compressionParameters cParams; - ZSTD_frameParameters fParams; -} ZSTD_parameters; +typedef ZSTD_parameters zstd_parameters; /** - * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * zstd_get_params() - returns zstd_parameters for selected level + * @level: The compression level + * @estimated_src_size: The estimated source size to compress or 0 + * if unknown. * - * Return: The selected ZSTD_compressionParameters. + * Return: The selected zstd_parameters. */ -ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); +zstd_parameters zstd_get_params(int level, + unsigned long long estimated_src_size); -/** - * ZSTD_getParams() - returns ZSTD_parameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. - * - * The same as ZSTD_getCParams() except also selects the default frame - * parameters (all zero). - * - * Return: The selected ZSTD_parameters. - */ -ZSTD_parameters ZSTD_getParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); +/* ====== Single-pass Compression ====== */ -/*-************************************* - * Explicit memory management - **************************************/ +typedef ZSTD_CCtx zstd_cctx; /** - * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx - * @cParams: The compression parameters to be used for compression. + * zstd_cctx_workspace_bound() - max memory needed to initialize a zstd_cctx + * @parameters: The compression parameters to be used. * * If multiple compression parameters might be used, the caller must call - * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum + * zstd_cctx_workspace_bound() for each set of parameters and use the maximum * size. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCCtx(). + * Return: A lower bound on the size of the workspace that is passed to + * zstd_init_cctx(). */ -size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); +size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *parameters); /** - * struct ZSTD_CCtx - the zstd compression context - * - * When compressing many times it is recommended to allocate a context just once - * and reuse it for each successive compression operation. - */ -typedef struct ZSTD_CCtx_s ZSTD_CCtx; -/** - * ZSTD_initCCtx() - initialize a zstd compression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to - * determine how large the workspace must be. - * - * Return: A compression context emplaced into workspace. - */ -ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_compressCCtx() - compress src into dst - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, ZSTD_parameters params); - -/** - * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDCtx(). - */ -size_t ZSTD_DCtxWorkspaceBound(void); - -/** - * struct ZSTD_DCtx - the zstd decompression context - * - * When decompressing many times it is recommended to allocate a context just - * once and reuse it for each successive decompression operation. - */ -typedef struct ZSTD_DCtx_s ZSTD_DCtx; -/** - * ZSTD_initDCtx() - initialize a zstd decompression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to - * determine how large the workspace must be. - * - * Return: A decompression context emplaced into workspace. - */ -ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_decompressDCtx() - decompress zstd compressed src into dst - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - -/*-************************ - * Simple dictionary API - **************************/ - -/** - * ZSTD_compress_usingDict() - compress src into dst using a dictionary - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @dict: The dictionary to use for compression. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Compression using a predefined dictionary. The same dictionary must be used - * during decompression. - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize, - ZSTD_parameters params); - -/** - * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @dict: The dictionary to use for decompression. The same dictionary - * must've been used to compress the data. - * @dictSize: The size of the dictionary. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize); - -/*-************************** - * Fast dictionary API - ***************************/ - -/** - * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict - * @cParams: The compression parameters to be used for compression. + * zstd_init_cctx() - initialize a zstd compression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspace_size: The size of workspace. Use zstd_cctx_workspace_bound() to + * determine how large the workspace must be. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCDict(). - */ -size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); - -/** - * struct ZSTD_CDict - a digested dictionary to be used for compression + * Return: A zstd compression context or NULL on error. */ -typedef struct ZSTD_CDict_s ZSTD_CDict; +zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size); /** - * ZSTD_initCDict() - initialize a digested dictionary for compression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_CDict so it must outlive the returned ZSTD_CDict. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * @workspace: The workspace. It must outlive the returned ZSTD_CDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_CDictWorkspaceBound(params.cParams). + * zstd_compress_cctx() - compress src into dst with the initialized parameters + * @cctx: The context. Must have been initialized with zstd_init_cctx(). + * @dst: The buffer to compress src into. + * @dst_capacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @src_size: The size of the data to compress. + * @parameters: The compression parameters to be used. * - * When compressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_CDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_CDict. - * - * Return: The digested dictionary emplaced into workspace. + * Return: The compressed size or an error, which can be checked using + * zstd_is_error(). */ -ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, - ZSTD_parameters params, void *workspace, size_t workspaceSize); +size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size, const zstd_parameters *parameters); -/** - * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(cParams) where - * cParams are the compression parameters used to initialize the - * cdict. - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @cdict: The digested dictionary to use for compression. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Compression using a digested dictionary. The same dictionary must be used - * during decompression. - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const ZSTD_CDict *cdict); +/* ====== Single-pass Decompression ====== */ +typedef ZSTD_DCtx zstd_dctx; /** - * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict + * zstd_dctx_workspace_bound() - max memory needed to initialize a zstd_dctx * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDDict(). - */ -size_t ZSTD_DDictWorkspaceBound(void); - -/** - * struct ZSTD_DDict - a digested dictionary to be used for decompression + * Return: A lower bound on the size of the workspace that is passed to + * zstd_init_dctx(). */ -typedef struct ZSTD_DDict_s ZSTD_DDict; +size_t zstd_dctx_workspace_bound(void); /** - * ZSTD_initDDict() - initialize a digested dictionary for decompression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_DDict so it must outlive the returned ZSTD_DDict. - * @dictSize: The size of the dictionary. - * @workspace: The workspace. It must outlive the returned ZSTD_DDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_DDictWorkspaceBound(). - * - * When decompressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_DDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_DDict. + * zstd_init_dctx() - initialize a zstd decompression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspace_size: The size of workspace. Use zstd_dctx_workspace_bound() to + * determine how large the workspace must be. * - * Return: The digested dictionary emplaced into workspace. + * Return: A zstd decompression context or NULL on error. */ -ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, - void *workspace, size_t workspaceSize); +zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size); /** - * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @ddict: The digested dictionary to use for decompression. The same - * dictionary must've been used to compress the data. + * zstd_decompress_dctx() - decompress zstd compressed src into dst + * @dctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dst_capacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @src_size: The exact size of the data to decompress. * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). + * Return: The decompressed size or an error, which can be checked using + * zstd_is_error(). */ -size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, - size_t dstCapacity, const void *src, size_t srcSize, - const ZSTD_DDict *ddict); +size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size); - -/*-************************** - * Streaming - ***************************/ +/* ====== Streaming Buffers ====== */ /** - * struct ZSTD_inBuffer - input buffer for streaming + * struct zstd_in_buffer - input buffer for streaming * @src: Start of the input buffer. * @size: Size of the input buffer. * @pos: Position where reading stopped. Will be updated. * Necessarily 0 <= pos <= size. + * + * See zstd_lib.h. */ -typedef struct ZSTD_inBuffer_s { - const void *src; - size_t size; - size_t pos; -} ZSTD_inBuffer; +typedef ZSTD_inBuffer zstd_in_buffer; /** - * struct ZSTD_outBuffer - output buffer for streaming + * struct zstd_out_buffer - output buffer for streaming * @dst: Start of the output buffer. * @size: Size of the output buffer. * @pos: Position where writing stopped. Will be updated. * Necessarily 0 <= pos <= size. + * + * See zstd_lib.h. */ -typedef struct ZSTD_outBuffer_s { - void *dst; - size_t size; - size_t pos; -} ZSTD_outBuffer; +typedef ZSTD_outBuffer zstd_out_buffer; +/* ====== Streaming Compression ====== */ - -/*-***************************************************************************** - * Streaming compression - HowTo - * - * A ZSTD_CStream object is required to track streaming operation. - * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. - * ZSTD_CStream objects can be reused multiple times on consecutive compression - * operations. It is recommended to re-use ZSTD_CStream in situations where many - * streaming operations will be achieved consecutively. Use one separate - * ZSTD_CStream per thread for parallel execution. - * - * Use ZSTD_compressStream() repetitively to consume input stream. - * The function will automatically update both `pos` fields. - * Note that it may not consume the entire input, in which case `pos < size`, - * and it's up to the caller to present again remaining data. - * It returns a hint for the preferred number of bytes to use as an input for - * the next function call. - * - * At any moment, it's possible to flush whatever data remains within internal - * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might - * still be some content left within the internal buffer if `output->size` is - * too small. It returns the number of bytes left in the internal buffer and - * must be called until it returns 0. - * - * ZSTD_endStream() instructs to finish a frame. It will perform a flush and - * write frame epilogue. The epilogue is required for decoders to consider a - * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush - * the full content if `output->size` is too small. In which case, call again - * ZSTD_endStream() to complete the flush. It returns the number of bytes left - * in the internal buffer and must be called until it returns 0. - ******************************************************************************/ +typedef ZSTD_CStream zstd_cstream; /** - * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream - * @cParams: The compression parameters to be used for compression. + * zstd_cstream_workspace_bound() - memory needed to initialize a zstd_cstream + * @cparams: The compression parameters to be used for compression. * * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). - */ -size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); - -/** - * struct ZSTD_CStream - the zstd streaming compression context + * zstd_init_cstream(). */ -typedef struct ZSTD_CStream_s ZSTD_CStream; +size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams); -/*===== ZSTD_CStream management functions =====*/ /** - * ZSTD_initCStream() - initialize a zstd streaming compression context - * @params: The zstd compression parameters. - * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must - * pass the source size (zero means empty source). Otherwise, - * the caller may optionally pass the source size, or zero if - * unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine - * how large the workspace must be. + * zstd_init_cstream() - initialize a zstd streaming compression context + * @parameters The zstd parameters to use for compression. + * @pledged_src_size: If params.fParams.contentSizeFlag == 1 then the caller + * must pass the source size (zero means empty source). + * Otherwise, the caller may optionally pass the source + * size, or zero if unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspace_size: The size of workspace. + * Use zstd_cstream_workspace_bound(params->cparams) to + * determine how large the workspace must be. * - * Return: The zstd streaming compression context. + * Return: The zstd streaming compression context or NULL on error. */ -ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); +zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters, + unsigned long long pledged_src_size, void *workspace, size_t workspace_size); /** - * ZSTD_initCStream_usingCDict() - initialize a streaming compression context - * @cdict: The digested dictionary to use for compression. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() - * with the cParams used to initialize the cdict to determine - * how large the workspace must be. - * - * Return: The zstd streaming compression context. - */ -ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); - -/*===== Streaming compression functions =====*/ -/** - * ZSTD_resetCStream() - reset the context using parameters from creation - * @zcs: The zstd streaming compression context to reset. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * zstd_reset_cstream() - reset the context using parameters from creation + * @cstream: The zstd streaming compression context to reset. + * @pledged_src_size: Optionally the source size, or zero if unknown. * * Resets the context using the parameters from creation. Skips dictionary - * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame + * loading, since it can be reused. If `pledged_src_size` is non-zero the frame * content size is always written into the frame header. * - * Return: Zero or an error, which can be checked using ZSTD_isError(). + * Return: Zero or an error, which can be checked using + * zstd_is_error(). */ -size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); +size_t zstd_reset_cstream(zstd_cstream *cstream, + unsigned long long pledged_src_size); + /** - * ZSTD_compressStream() - streaming compress some of input into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * @input: Source buffer. `input->pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input->pos < input->size`, and it's up to the caller to present - * remaining data again. + * zstd_compress_stream() - streaming compress some of input into output + * @cstream: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * @input: Source buffer. `input->pos` is updated to indicate how much data + * was read. Note that it may not consume the entire input, in which + * case `input->pos < input->size`, and it's up to the caller to + * present remaining data again. * * The `input` and `output` buffers may be any size. Guaranteed to make some * forward progress if `input` and `output` are not empty. * - * Return: A hint for the number of bytes to use as the input for the next - * function call or an error, which can be checked using - * ZSTD_isError(). + * Return: A hint for the number of bytes to use as the input for the next + * function call or an error, which can be checked using + * zstd_is_error(). */ -size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); +size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output, + zstd_in_buffer *input); + /** - * ZSTD_flushStream() - flush internal buffers into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. + * zstd_flush_stream() - flush internal buffers into output + * @cstream: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. * - * ZSTD_flushStream() must be called until it returns 0, meaning all the data - * has been flushed. Since ZSTD_flushStream() causes a block to be ended, + * zstd_flush_stream() must be called until it returns 0, meaning all the data + * has been flushed. Since zstd_flush_stream() causes a block to be ended, * calling it too often will degrade the compression ratio. * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); -/** - * ZSTD_endStream() - flush internal buffers into output and end the frame - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * - * ZSTD_endStream() must be called until it returns 0, meaning all the data has - * been flushed and the frame epilogue has been written. - * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using zstd_is_error(). */ -size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); +size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output); /** - * ZSTD_CStreamInSize() - recommended size for the input buffer - * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_CStreamInSize(void); -/** - * ZSTD_CStreamOutSize() - recommended size for the output buffer + * zstd_end_stream() - flush internal buffers into output and end the frame + * @cstream: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete compressed block. + * zstd_end_stream() must be called until it returns 0, meaning all the data has + * been flushed and the frame epilogue has been written. * - * Return: The recommended size for the output buffer. + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using zstd_is_error(). */ -size_t ZSTD_CStreamOutSize(void); +size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output); +/* ====== Streaming Decompression ====== */ - -/*-***************************************************************************** - * Streaming decompression - HowTo - * - * A ZSTD_DStream object is required to track streaming operations. - * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. - * ZSTD_DStream objects can be re-used multiple times. - * - * Use ZSTD_decompressStream() repetitively to consume your input. - * The function will update both `pos` fields. - * If `input->pos < input->size`, some input has not been consumed. - * It's up to the caller to present again remaining data. - * If `output->pos < output->size`, decoder has flushed everything it could. - * Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise it returns a suggested next input size that will never load more - * than the current frame. - ******************************************************************************/ +typedef ZSTD_DStream zstd_dstream; /** - * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream - * @maxWindowSize: The maximum window size allowed for compressed frames. + * zstd_dstream_workspace_bound() - memory needed to initialize a zstd_dstream + * @max_window_size: The maximum window size allowed for compressed frames. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). + * Return: A lower bound on the size of the workspace that is passed + * to zstd_init_dstream(). */ -size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); +size_t zstd_dstream_workspace_bound(size_t max_window_size); /** - * struct ZSTD_DStream - the zstd streaming decompression context - */ -typedef struct ZSTD_DStream_s ZSTD_DStream; -/*===== ZSTD_DStream management functions =====*/ -/** - * ZSTD_initDStream() - initialize a zstd streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. - * - * Return: The zstd streaming decompression context. - */ -ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, - size_t workspaceSize); -/** - * ZSTD_initDStream_usingDDict() - initialize streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @ddict: The digested dictionary to use for decompression. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. + * zstd_init_dstream() - initialize a zstd streaming decompression context + * @max_window_size: The maximum window size allowed for compressed frames. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use zstd_dstream_workspace_bound(max_window_size) to + * determine how large the workspace must be. * - * Return: The zstd streaming decompression context. + * Return: The zstd streaming decompression context. */ -ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, - const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); +zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace, + size_t workspace_size); -/*===== Streaming decompression functions =====*/ /** - * ZSTD_resetDStream() - reset the context using parameters from creation - * @zds: The zstd streaming decompression context to reset. + * zstd_reset_dstream() - reset the context using parameters from creation + * @dstream: The zstd streaming decompression context to reset. * * Resets the context using the parameters from creation. Skips dictionary * loading, since it can be reused. * - * Return: Zero or an error, which can be checked using ZSTD_isError(). + * Return: Zero or an error, which can be checked using zstd_is_error(). */ -size_t ZSTD_resetDStream(ZSTD_DStream *zds); +size_t zstd_reset_dstream(zstd_dstream *dstream); + /** - * ZSTD_decompressStream() - streaming decompress some of input into output - * @zds: The zstd streaming decompression context. - * @output: Destination buffer. `output.pos` is updated to indicate how much - * decompressed data was written. - * @input: Source buffer. `input.pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input.pos < input.size`, and it's up to the caller to present - * remaining data again. + * zstd_decompress_stream() - streaming decompress some of input into output + * @dstream: The zstd streaming decompression context. + * @output: Destination buffer. `output.pos` is updated to indicate how much + * decompressed data was written. + * @input: Source buffer. `input.pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input.pos < input.size`, and it's up to the caller to present + * remaining data again. * * The `input` and `output` buffers may be any size. Guaranteed to make some * forward progress if `input` and `output` are not empty. - * ZSTD_decompressStream() will not consume the last byte of the frame until + * zstd_decompress_stream() will not consume the last byte of the frame until * the entire frame is flushed. * - * Return: Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise returns a hint for the number of bytes to use as the input - * for the next function call or an error, which can be checked using - * ZSTD_isError(). The size hint will never load more than the frame. - */ -size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); - -/** - * ZSTD_DStreamInSize() - recommended size for the input buffer - * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_DStreamInSize(void); -/** - * ZSTD_DStreamOutSize() - recommended size for the output buffer - * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete decompressed block. - * - * Return: The recommended size for the output buffer. - */ -size_t ZSTD_DStreamOutSize(void); - - -/* --- Constants ---*/ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ -#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U - -#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) -#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) - -#define ZSTD_WINDOWLOG_MAX_32 27 -#define ZSTD_WINDOWLOG_MAX_64 27 -#define ZSTD_WINDOWLOG_MAX \ - ((unsigned int)(sizeof(size_t) == 4 \ - ? ZSTD_WINDOWLOG_MAX_32 \ - : ZSTD_WINDOWLOG_MAX_64)) -#define ZSTD_WINDOWLOG_MIN 10 -#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX -#define ZSTD_HASHLOG_MIN 6 -#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) -#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN -#define ZSTD_HASHLOG3_MAX 17 -#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) -#define ZSTD_SEARCHLOG_MIN 1 -/* only for ZSTD_fast, other strategies are limited to 6 */ -#define ZSTD_SEARCHLENGTH_MAX 7 -/* only for ZSTD_btopt, other strategies are limited to 4 */ -#define ZSTD_SEARCHLENGTH_MIN 3 -#define ZSTD_TARGETLENGTH_MIN 4 -#define ZSTD_TARGETLENGTH_MAX 999 - -/* for static allocation */ -#define ZSTD_FRAMEHEADERSIZE_MAX 18 -#define ZSTD_FRAMEHEADERSIZE_MIN 6 -#define ZSTD_frameHeaderSize_prefix 5 -#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN -#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX -/* magic number + skippable frame length */ -#define ZSTD_skippableHeaderSize 8 - - -/*-************************************* - * Compressed size functions - **************************************/ - -/** - * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame - * @src: Source buffer. It should point to the start of a zstd encoded frame - * or a skippable frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * size of the frame. - * - * Return: The compressed size of the frame pointed to by `src` or an error, - * which can be check with ZSTD_isError(). - * Suitable to pass to ZSTD_decompress() or similar functions. - */ -size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Decompressed size functions - **************************************/ -/** - * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header - * @src: It should point to the start of a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. - * - * Return: The frame content size stored in the frame header if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the - * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. - */ -unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); - -/** - * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames - * @src: It should point to the start of a series of zstd encoded and/or - * skippable frames. - * @srcSize: The exact size of the series of frames. - * - * If any zstd encoded frame in the series doesn't have the frame content size - * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always - * set when using ZSTD_compress(). The decompressed size can be very large. - * If the source is untrusted, the decompressed size could be wrong or - * intentionally modified. Always ensure the result fits within the - * application's authorized limits. ZSTD_findDecompressedSize() handles multiple - * frames, and so it must traverse the input to read each frame header. This is - * efficient as most of the data is skipped, however it does mean that all frame - * data must be present and valid. - * - * Return: Decompressed size of all the data contained in the frames if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. - * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. - */ -unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Advanced compression functions - **************************************/ -/** - * ZSTD_checkCParams() - ensure parameter values remain within authorized range - * @cParams: The zstd compression parameters. - * - * Return: Zero or an error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); - -/** - * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize - * @srcSize: Optionally the estimated source size, or zero if unknown. - * @dictSize: Optionally the estimated dictionary size, or zero if unknown. - * - * Return: The optimized parameters. - */ -ZSTD_compressionParameters ZSTD_adjustCParams( - ZSTD_compressionParameters cParams, unsigned long long srcSize, - size_t dictSize); - -/*--- Advanced decompression functions ---*/ - -/** - * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame - * @buffer: The source buffer to check. - * @size: The size of the source buffer, must be at least 4 bytes. - * - * Return: True iff the buffer starts with a zstd or skippable frame identifier. - */ -unsigned int ZSTD_isFrame(const void *buffer, size_t size); - -/** - * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary - * @dict: The dictionary buffer. - * @dictSize: The size of the dictionary buffer. - * - * Return: The dictionary id stored within the dictionary or 0 if the - * dictionary is not a zstd dictionary. If it returns 0 the - * dictionary can still be loaded as a content-only dictionary. + * Return: Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise returns a hint for the number of bytes to use as the + * input for the next function call or an error, which can be checked + * using zstd_is_error(). The size hint will never load more than the + * frame. */ -unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); +size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output, + zstd_in_buffer *input); -/** - * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict - * @ddict: The ddict to find the id of. - * - * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not - * a zstd dictionary. If it returns 0 `ddict` will be loaded as a - * content-only dictionary. - */ -unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); +/* ====== Frame Inspection Functions ====== */ /** - * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame - * @src: Source buffer. It must be a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * zstd_find_frame_compressed_size() - returns the size of a compressed frame + * @src: Source buffer. It should point to the start of a zstd encoded + * frame or a skippable frame. + * @src_size: The size of the source buffer. It must be at least as large as the + * size of the frame. * - * Return: The dictionary id required to decompress the frame stored within - * `src` or 0 if the dictionary id could not be decoded. It can return - * 0 if the frame does not require a dictionary, the dictionary id - * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` - * is too small. + * Return: The compressed size of the frame pointed to by `src` or an error, + * which can be check with zstd_is_error(). + * Suitable to pass to ZSTD_decompress() or similar functions. */ -unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); +size_t zstd_find_frame_compressed_size(const void *src, size_t src_size); /** - * struct ZSTD_frameParams - zstd frame parameters stored in the frame header + * struct zstd_frame_params - zstd frame parameters stored in the frame header * @frameContentSize: The frame content size, or 0 if not present. * @windowSize: The window size, or 0 if the frame is a skippable frame. * @dictID: The dictionary id, or 0 if not present. * @checksumFlag: Whether a checksum was used. */ -typedef struct { - unsigned long long frameContentSize; - unsigned int windowSize; - unsigned int dictID; - unsigned int checksumFlag; -} ZSTD_frameParams; +typedef ZSTD_frameParams zstd_frame_header; /** - * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame - * @fparamsPtr: On success the frame parameters are written here. - * @src: The source buffer. It must point to a zstd or skippable frame. - * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is - * always large enough to succeed. + * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame + * @params: On success the frame parameters are written here. + * @src: The source buffer. It must point to a zstd or skippable frame. + * @src_size: The size of the source buffer. * - * Return: 0 on success. If more data is required it returns how many bytes - * must be provided to make forward progress. Otherwise it returns - * an error, which can be checked using ZSTD_isError(). + * Return: 0 on success. If more data is required it returns how many bytes + * must be provided to make forward progress. Otherwise it returns + * an error, which can be checked using zstd_is_error(). */ -size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, - size_t srcSize); - -/*-***************************************************************************** - * Buffer-less and synchronous inner streaming functions - * - * This is an advanced API, giving full control over buffer management, for - * users which need direct control over memory. - * But it's also a complex one, with many restrictions (documented below). - * Prefer using normal streaming API for an easier experience - ******************************************************************************/ - -/*-***************************************************************************** - * Buffer-less streaming compression (synchronous mode) - * - * A ZSTD_CCtx object is required to track streaming operations. - * Use ZSTD_initCCtx() to initialize a context. - * ZSTD_CCtx object can be re-used multiple times within successive compression - * operations. - * - * Start by initializing a context. - * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary - * compression, - * or ZSTD_compressBegin_advanced(), for finer parameter control. - * It's also possible to duplicate a reference context which has already been - * initialized, using ZSTD_copyCCtx() - * - * Then, consume your input using ZSTD_compressContinue(). - * There are some important considerations to keep in mind when using this - * advanced function : - * - ZSTD_compressContinue() has no internal buffer. It uses externally provided - * buffer only. - * - Interface is synchronous : input is consumed entirely and produce 1+ - * (or more) compressed blocks. - * - Caller must ensure there is enough space in `dst` to store compressed data - * under worst case scenario. Worst case evaluation is provided by - * ZSTD_compressBound(). - * ZSTD_compressContinue() doesn't guarantee recover after a failed - * compression. - * - ZSTD_compressContinue() presumes prior input ***is still accessible and - * unmodified*** (up to maximum distance size, see WindowLog). - * It remembers all previous contiguous blocks, plus one separated memory - * segment (which can itself consists of multiple contiguous blocks) - * - ZSTD_compressContinue() detects that prior input has been overwritten when - * `src` buffer overlaps. In which case, it will "discard" the relevant memory - * section from its history. - * - * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) - * and optional checksum. It's possible to use srcSize==0, in which case, it - * will write a final empty block to end the frame. Without last block mark, - * frames will be considered unfinished (corrupted) by decoders. - * - * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new - * frame. - ******************************************************************************/ - -/*===== Buffer-less streaming compression functions =====*/ -size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); -size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, int compressionLevel); -size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, ZSTD_parameters params, - unsigned long long pledgedSrcSize); -size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - - - -/*-***************************************************************************** - * Buffer-less streaming decompression (synchronous mode) - * - * A ZSTD_DCtx object is required to track streaming operations. - * Use ZSTD_initDCtx() to initialize a context. - * A ZSTD_DCtx object can be re-used multiple times. - * - * First typical operation is to retrieve frame parameters, using - * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide - * important information to correctly decode the frame, such as the minimum - * rolling buffer size to allocate to decompress data (`windowSize`), and the - * dictionary ID used. - * Note: content size is optional, it may not be present. 0 means unknown. - * Note that these values could be wrong, either because of data malformation, - * or because an attacker is spoofing deliberate false information. As a - * consequence, check that values remain within valid application range, - * especially `windowSize`, before allocation. Each application can set its own - * limit, depending on local restrictions. For extended interoperability, it is - * recommended to support at least 8 MB. - * Frame parameters are extracted from the beginning of the compressed frame. - * Data fragment must be large enough to ensure successful decoding, typically - * `ZSTD_frameHeaderSize_max` bytes. - * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. - * >0: `srcSize` is too small, provide at least this many bytes. - * errorCode, which can be tested using ZSTD_isError(). - * - * Start decompression, with ZSTD_decompressBegin() or - * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared - * context, using ZSTD_copyDCtx(). - * - * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() - * alternatively. - * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' - * to ZSTD_decompressContinue(). - * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will - * fail. - * - * The result of ZSTD_decompressContinue() is the number of bytes regenerated - * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an - * error; it just means ZSTD_decompressContinue() has decoded some metadata - * item. It can also be an error code, which can be tested with ZSTD_isError(). - * - * ZSTD_decompressContinue() needs previous data blocks during decompression, up - * to `windowSize`. They should preferably be located contiguously, prior to - * current block. Alternatively, a round buffer of sufficient size is also - * possible. Sufficient size is determined by frame parameters. - * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't - * follow each other, make sure that either the compressor breaks contiguity at - * the same place, or that previous contiguous segment is large enough to - * properly handle maximum back-reference. - * - * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. - * Context can then be reset to start a new decompression. - * - * Note: it's possible to know if next input to present is a header or a block, - * using ZSTD_nextInputType(). This information is not required to properly - * decode a frame. - * - * == Special case: skippable frames == - * - * Skippable frames allow integration of user-defined data into a flow of - * concatenated frames. Skippable frames will be ignored (skipped) by a - * decompressor. The format of skippable frames is as follows: - * a) Skippable frame ID - 4 Bytes, Little endian format, any value from - * 0x184D2A50 to 0x184D2A5F - * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits - * c) Frame Content - any content (User Data) of length equal to Frame Size - * For skippable frames ZSTD_decompressContinue() always returns 0. - * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 - * what means that a frame is skippable. - * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might - * actually be a zstd encoded frame with no content. For purposes of - * decompression, it is valid in both cases to skip the frame using - * ZSTD_findFrameCompressedSize() to find its size in bytes. - * It also returns frame size as fparamsPtr->frameContentSize. - ******************************************************************************/ - -/*===== Buffer-less streaming decompression functions =====*/ -size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); -size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, - size_t dictSize); -void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); -size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); -size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -typedef enum { - ZSTDnit_frameHeader, - ZSTDnit_blockHeader, - ZSTDnit_block, - ZSTDnit_lastBlock, - ZSTDnit_checksum, - ZSTDnit_skippableFrame -} ZSTD_nextInputType_e; -ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); - -/*-***************************************************************************** - * Block functions - * - * Block functions produce and decode raw zstd blocks, without frame metadata. - * Frame metadata cost is typically ~18 bytes, which can be non-negligible for - * very small blocks (< 100 bytes). User will have to take in charge required - * information to regenerate data, such as compressed and content sizes. - * - * A few rules to respect: - * - Compressing and decompressing require a context structure - * + Use ZSTD_initCCtx() and ZSTD_initDCtx() - * - It is necessary to init context before starting - * + compression : ZSTD_compressBegin() - * + decompression : ZSTD_decompressBegin() - * + variants _usingDict() are also allowed - * + copyCCtx() and copyDCtx() work too - * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() - * + If you need to compress more, cut data into multiple blocks - * + Consider using the regular ZSTD_compress() instead, as frame metadata - * costs become negligible when source size is large. - * - When a block is considered not compressible enough, ZSTD_compressBlock() - * result will be zero. In which case, nothing is produced into `dst`. - * + User must test for such outcome and deal directly with uncompressed data - * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! - * + In case of multiple successive blocks, decoder must be informed of - * uncompressed block existence to follow proper history. Use - * ZSTD_insertBlock() in such a case. - ******************************************************************************/ - -/* Define for static allocation */ -#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) -/*===== Raw zstd block functions =====*/ -size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); -size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, - size_t blockSize); +size_t zstd_get_frame_header(zstd_frame_header *params, const void *src, + size_t src_size); -#endif /* ZSTD_H */ +#endif /* LINUX_ZSTD_H */ diff --git a/include/linux/zstd_lib.h b/include/linux/zstd_lib.h new file mode 100644 index 000000000000..13151c34f725 --- /dev/null +++ b/include/linux/zstd_lib.h @@ -0,0 +1,1157 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of https://github.com/facebook/zstd. + * An additional grant of patent rights can be found in the PATENTS file in the + * same directory. + * + * This program is free software; you can redistribute it and/or modify it under + * the terms of the GNU General Public License version 2 as published by the + * Free Software Foundation. This program is dual-licensed; you may select + * either version 2 of the GNU General Public License ("GPL") or BSD license + * ("BSD"). + */ + +#ifndef ZSTD_H +#define ZSTD_H + +/* ====== Dependency ======*/ +#include /* size_t */ + + +/*-***************************************************************************** + * Introduction + * + * zstd, short for Zstandard, is a fast lossless compression algorithm, + * targeting real-time compression scenarios at zlib-level and better + * compression ratios. The zstd compression library provides in-memory + * compression and decompression functions. The library supports compression + * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled + * ultra, should be used with caution, as they require more memory. + * Compression can be done in: + * - a single step, reusing a context (described as Explicit memory management) + * - unbounded multiple steps (described as Streaming compression) + * The compression ratio achievable on small data can be highly improved using + * compression with a dictionary in: + * - a single step (described as Simple dictionary API) + * - a single step, reusing a dictionary (described as Fast dictionary API) + ******************************************************************************/ + +/*====== Helper functions ======*/ + +/** + * enum ZSTD_ErrorCode - zstd error codes + * + * Functions that return size_t can be checked for errors using ZSTD_isError() + * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + */ +typedef enum { + ZSTD_error_no_error, + ZSTD_error_GENERIC, + ZSTD_error_prefix_unknown, + ZSTD_error_version_unsupported, + ZSTD_error_parameter_unknown, + ZSTD_error_frameParameter_unsupported, + ZSTD_error_frameParameter_unsupportedBy32bits, + ZSTD_error_frameParameter_windowTooLarge, + ZSTD_error_compressionParameter_unsupported, + ZSTD_error_init_missing, + ZSTD_error_memory_allocation, + ZSTD_error_stage_wrong, + ZSTD_error_dstSize_tooSmall, + ZSTD_error_srcSize_wrong, + ZSTD_error_corruption_detected, + ZSTD_error_checksum_wrong, + ZSTD_error_tableLog_tooLarge, + ZSTD_error_maxSymbolValue_tooLarge, + ZSTD_error_maxSymbolValue_tooSmall, + ZSTD_error_dictionary_corrupted, + ZSTD_error_dictionary_wrong, + ZSTD_error_dictionaryCreation_failed, + ZSTD_error_maxCode +} ZSTD_ErrorCode; + +/** + * ZSTD_maxCLevel() - maximum compression level available + * + * Return: Maximum compression level available. + */ +int ZSTD_maxCLevel(void); +/** + * ZSTD_compressBound() - maximum compressed size in worst case scenario + * @srcSize: The size of the data to compress. + * + * Return: The maximum compressed size in the worst case scenario. + */ +size_t ZSTD_compressBound(size_t srcSize); +/** + * ZSTD_isError() - tells if a size_t function result is an error code + * @code: The function result to check for error. + * + * Return: Non-zero iff the code is an error. + */ +static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) +{ + return code > (size_t)-ZSTD_error_maxCode; +} +/** + * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode + * @functionResult: The result of a function for which ZSTD_isError() is true. + * + * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 + * if the functionResult isn't an error. + */ +static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( + size_t functionResult) +{ + if (!ZSTD_isError(functionResult)) + return (ZSTD_ErrorCode)0; + return (ZSTD_ErrorCode)(0 - functionResult); +} + +/** + * enum ZSTD_strategy - zstd compression search strategy + * + * From faster to stronger. + */ +typedef enum { + ZSTD_fast, + ZSTD_dfast, + ZSTD_greedy, + ZSTD_lazy, + ZSTD_lazy2, + ZSTD_btlazy2, + ZSTD_btopt, + ZSTD_btopt2 +} ZSTD_strategy; + +/** + * struct ZSTD_compressionParameters - zstd compression parameters + * @windowLog: Log of the largest match distance. Larger means more + * compression, and more memory needed during decompression. + * @chainLog: Fully searched segment. Larger means more compression, slower, + * and more memory (useless for fast). + * @hashLog: Dispatch table. Larger means more compression, + * slower, and more memory. + * @searchLog: Number of searches. Larger means more compression and slower. + * @searchLength: Match length searched. Larger means faster decompression, + * sometimes less compression. + * @targetLength: Acceptable match size for optimal parser (only). Larger means + * more compression, and slower. + * @strategy: The zstd compression strategy. + */ +typedef struct { + unsigned int windowLog; + unsigned int chainLog; + unsigned int hashLog; + unsigned int searchLog; + unsigned int searchLength; + unsigned int targetLength; + ZSTD_strategy strategy; +} ZSTD_compressionParameters; + +/** + * struct ZSTD_frameParameters - zstd frame parameters + * @contentSizeFlag: Controls whether content size will be present in the frame + * header (when known). + * @checksumFlag: Controls whether a 32-bit checksum is generated at the end + * of the frame for error detection. + * @noDictIDFlag: Controls whether dictID will be saved into the frame header + * when using dictionary compression. + * + * The default value is all fields set to 0. + */ +typedef struct { + unsigned int contentSizeFlag; + unsigned int checksumFlag; + unsigned int noDictIDFlag; +} ZSTD_frameParameters; + +/** + * struct ZSTD_parameters - zstd parameters + * @cParams: The compression parameters. + * @fParams: The frame parameters. + */ +typedef struct { + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; +} ZSTD_parameters; + +/** + * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * Return: The selected ZSTD_compressionParameters. + */ +ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/** + * ZSTD_getParams() - returns ZSTD_parameters for selected level + * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). + * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. + * @dictSize: The dictionary size or 0 if a dictionary isn't being used. + * + * The same as ZSTD_getCParams() except also selects the default frame + * parameters (all zero). + * + * Return: The selected ZSTD_parameters. + */ +ZSTD_parameters ZSTD_getParams(int compressionLevel, + unsigned long long estimatedSrcSize, size_t dictSize); + +/*-************************************* + * Explicit memory management + **************************************/ + +/** + * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx + * @cParams: The compression parameters to be used for compression. + * + * If multiple compression parameters might be used, the caller must call + * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum + * size. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCCtx(). + */ +size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CCtx - the zstd compression context + * + * When compressing many times it is recommended to allocate a context just once + * and reuse it for each successive compression operation. + */ +typedef struct ZSTD_CCtx_s ZSTD_CCtx; +/** + * ZSTD_initCCtx() - initialize a zstd compression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A compression context emplaced into workspace. + */ +ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_compressCCtx() - compress src into dst + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, ZSTD_parameters params); + +/** + * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDCtx(). + */ +size_t ZSTD_DCtxWorkspaceBound(void); + +/** + * struct ZSTD_DCtx - the zstd decompression context + * + * When decompressing many times it is recommended to allocate a context just + * once and reuse it for each successive decompression operation. + */ +typedef struct ZSTD_DCtx_s ZSTD_DCtx; +/** + * ZSTD_initDCtx() - initialize a zstd decompression context + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to + * determine how large the workspace must be. + * + * Return: A decompression context emplaced into workspace. + */ +ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompressDCtx() - decompress zstd compressed src into dst + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + +/*-************************ + * Simple dictionary API + **************************/ + +/** + * ZSTD_compress_usingDict() - compress src into dst using a dictionary + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @dict: The dictionary to use for compression. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a predefined dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize, + ZSTD_parameters params); + +/** + * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @dict: The dictionary to use for decompression. The same dictionary + * must've been used to compress the data. + * @dictSize: The size of the dictionary. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const void *dict, size_t dictSize); + +/*-************************** + * Fast dictionary API + ***************************/ + +/** + * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCDict(). + */ +size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CDict - a digested dictionary to be used for compression + */ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/** + * ZSTD_initCDict() - initialize a digested dictionary for compression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_CDict so it must outlive the returned ZSTD_CDict. + * @dictSize: The size of the dictionary. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * @workspace: The workspace. It must outlive the returned ZSTD_CDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_CDictWorkspaceBound(params.cParams). + * + * When compressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_CDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_CDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, + ZSTD_parameters params, void *workspace, size_t workspaceSize); + +/** + * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict + * @ctx: The context. Must have been initialized with a workspace at + * least as large as ZSTD_CCtxWorkspaceBound(cParams) where + * cParams are the compression parameters used to initialize the + * cdict. + * @dst: The buffer to compress src into. + * @dstCapacity: The size of the destination buffer. May be any size, but + * ZSTD_compressBound(srcSize) is guaranteed to be large enough. + * @src: The data to compress. + * @srcSize: The size of the data to compress. + * @cdict: The digested dictionary to use for compression. + * @params: The parameters to use for compression. See ZSTD_getParams(). + * + * Compression using a digested dictionary. The same dictionary must be used + * during decompression. + * + * Return: The compressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize, const ZSTD_CDict *cdict); + + +/** + * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDDict(). + */ +size_t ZSTD_DDictWorkspaceBound(void); + +/** + * struct ZSTD_DDict - a digested dictionary to be used for decompression + */ +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/** + * ZSTD_initDDict() - initialize a digested dictionary for decompression + * @dictBuffer: The dictionary to digest. The buffer is referenced by the + * ZSTD_DDict so it must outlive the returned ZSTD_DDict. + * @dictSize: The size of the dictionary. + * @workspace: The workspace. It must outlive the returned ZSTD_DDict. + * @workspaceSize: The workspace size. Must be at least + * ZSTD_DDictWorkspaceBound(). + * + * When decompressing multiple messages / blocks with the same dictionary it is + * recommended to load it just once. The ZSTD_DDict merely references the + * dictBuffer, so it must outlive the returned ZSTD_DDict. + * + * Return: The digested dictionary emplaced into workspace. + */ +ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, + void *workspace, size_t workspaceSize); + +/** + * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict + * @ctx: The decompression context. + * @dst: The buffer to decompress src into. + * @dstCapacity: The size of the destination buffer. Must be at least as large + * as the decompressed size. If the caller cannot upper bound the + * decompressed size, then it's better to use the streaming API. + * @src: The zstd compressed data to decompress. Multiple concatenated + * frames and skippable frames are allowed. + * @srcSize: The exact size of the data to decompress. + * @ddict: The digested dictionary to use for decompression. The same + * dictionary must've been used to compress the data. + * + * Return: The decompressed size or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, + size_t dstCapacity, const void *src, size_t srcSize, + const ZSTD_DDict *ddict); + + +/*-************************** + * Streaming + ***************************/ + +/** + * struct ZSTD_inBuffer - input buffer for streaming + * @src: Start of the input buffer. + * @size: Size of the input buffer. + * @pos: Position where reading stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_inBuffer_s { + const void *src; + size_t size; + size_t pos; +} ZSTD_inBuffer; + +/** + * struct ZSTD_outBuffer - output buffer for streaming + * @dst: Start of the output buffer. + * @size: Size of the output buffer. + * @pos: Position where writing stopped. Will be updated. + * Necessarily 0 <= pos <= size. + */ +typedef struct ZSTD_outBuffer_s { + void *dst; + size_t size; + size_t pos; +} ZSTD_outBuffer; + + + +/*-***************************************************************************** + * Streaming compression - HowTo + * + * A ZSTD_CStream object is required to track streaming operation. + * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. + * ZSTD_CStream objects can be reused multiple times on consecutive compression + * operations. It is recommended to re-use ZSTD_CStream in situations where many + * streaming operations will be achieved consecutively. Use one separate + * ZSTD_CStream per thread for parallel execution. + * + * Use ZSTD_compressStream() repetitively to consume input stream. + * The function will automatically update both `pos` fields. + * Note that it may not consume the entire input, in which case `pos < size`, + * and it's up to the caller to present again remaining data. + * It returns a hint for the preferred number of bytes to use as an input for + * the next function call. + * + * At any moment, it's possible to flush whatever data remains within internal + * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might + * still be some content left within the internal buffer if `output->size` is + * too small. It returns the number of bytes left in the internal buffer and + * must be called until it returns 0. + * + * ZSTD_endStream() instructs to finish a frame. It will perform a flush and + * write frame epilogue. The epilogue is required for decoders to consider a + * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush + * the full content if `output->size` is too small. In which case, call again + * ZSTD_endStream() to complete the flush. It returns the number of bytes left + * in the internal buffer and must be called until it returns 0. + ******************************************************************************/ + +/** + * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream + * @cParams: The compression parameters to be used for compression. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). + */ +size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); + +/** + * struct ZSTD_CStream - the zstd streaming compression context + */ +typedef struct ZSTD_CStream_s ZSTD_CStream; + +/*===== ZSTD_CStream management functions =====*/ +/** + * ZSTD_initCStream() - initialize a zstd streaming compression context + * @params: The zstd compression parameters. + * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must + * pass the source size (zero means empty source). Otherwise, + * the caller may optionally pass the source size, or zero if + * unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/** + * ZSTD_initCStream_usingCDict() - initialize a streaming compression context + * @cdict: The digested dictionary to use for compression. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() + * with the cParams used to initialize the cdict to determine + * how large the workspace must be. + * + * Return: The zstd streaming compression context. + */ +ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize, void *workspace, + size_t workspaceSize); + +/*===== Streaming compression functions =====*/ +/** + * ZSTD_resetCStream() - reset the context using parameters from creation + * @zcs: The zstd streaming compression context to reset. + * @pledgedSrcSize: Optionally the source size, or zero if unknown. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame + * content size is always written into the frame header. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); +/** + * ZSTD_compressStream() - streaming compress some of input into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * @input: Source buffer. `input->pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input->pos < input->size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * + * Return: A hint for the number of bytes to use as the input for the next + * function call or an error, which can be checked using + * ZSTD_isError(). + */ +size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); +/** + * ZSTD_flushStream() - flush internal buffers into output + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_flushStream() must be called until it returns 0, meaning all the data + * has been flushed. Since ZSTD_flushStream() causes a block to be ended, + * calling it too often will degrade the compression ratio. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); +/** + * ZSTD_endStream() - flush internal buffers into output and end the frame + * @zcs: The zstd streaming compression context. + * @output: Destination buffer. `output->pos` is updated to indicate how much + * compressed data was written. + * + * ZSTD_endStream() must be called until it returns 0, meaning all the data has + * been flushed and the frame epilogue has been written. + * + * Return: The number of bytes still present within internal buffers or an + * error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); + +/** + * ZSTD_CStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_CStreamInSize(void); +/** + * ZSTD_CStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete compressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_CStreamOutSize(void); + + + +/*-***************************************************************************** + * Streaming decompression - HowTo + * + * A ZSTD_DStream object is required to track streaming operations. + * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. + * ZSTD_DStream objects can be re-used multiple times. + * + * Use ZSTD_decompressStream() repetitively to consume your input. + * The function will update both `pos` fields. + * If `input->pos < input->size`, some input has not been consumed. + * It's up to the caller to present again remaining data. + * If `output->pos < output->size`, decoder has flushed everything it could. + * Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise it returns a suggested next input size that will never load more + * than the current frame. + ******************************************************************************/ + +/** + * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream + * @maxWindowSize: The maximum window size allowed for compressed frames. + * + * Return: A lower bound on the size of the workspace that is passed to + * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). + */ +size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); + +/** + * struct ZSTD_DStream - the zstd streaming decompression context + */ +typedef struct ZSTD_DStream_s ZSTD_DStream; +/*===== ZSTD_DStream management functions =====*/ +/** + * ZSTD_initDStream() - initialize a zstd streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, + size_t workspaceSize); +/** + * ZSTD_initDStream_usingDDict() - initialize streaming decompression context + * @maxWindowSize: The maximum window size allowed for compressed frames. + * @ddict: The digested dictionary to use for decompression. + * @workspace: The workspace to emplace the context into. It must outlive + * the returned context. + * @workspaceSize: The size of workspace. + * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine + * how large the workspace must be. + * + * Return: The zstd streaming decompression context. + */ +ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, + const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); + +/*===== Streaming decompression functions =====*/ +/** + * ZSTD_resetDStream() - reset the context using parameters from creation + * @zds: The zstd streaming decompression context to reset. + * + * Resets the context using the parameters from creation. Skips dictionary + * loading, since it can be reused. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_resetDStream(ZSTD_DStream *zds); +/** + * ZSTD_decompressStream() - streaming decompress some of input into output + * @zds: The zstd streaming decompression context. + * @output: Destination buffer. `output.pos` is updated to indicate how much + * decompressed data was written. + * @input: Source buffer. `input.pos` is updated to indicate how much data was + * read. Note that it may not consume the entire input, in which case + * `input.pos < input.size`, and it's up to the caller to present + * remaining data again. + * + * The `input` and `output` buffers may be any size. Guaranteed to make some + * forward progress if `input` and `output` are not empty. + * ZSTD_decompressStream() will not consume the last byte of the frame until + * the entire frame is flushed. + * + * Return: Returns 0 iff a frame is completely decoded and fully flushed. + * Otherwise returns a hint for the number of bytes to use as the input + * for the next function call or an error, which can be checked using + * ZSTD_isError(). The size hint will never load more than the frame. + */ +size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, + ZSTD_inBuffer *input); + +/** + * ZSTD_DStreamInSize() - recommended size for the input buffer + * + * Return: The recommended size for the input buffer. + */ +size_t ZSTD_DStreamInSize(void); +/** + * ZSTD_DStreamOutSize() - recommended size for the output buffer + * + * When the output buffer is at least this large, it is guaranteed to be large + * enough to flush at least one complete decompressed block. + * + * Return: The recommended size for the output buffer. + */ +size_t ZSTD_DStreamOutSize(void); + + +/* --- Constants ---*/ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U + +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) + +#define ZSTD_WINDOWLOG_MAX_32 27 +#define ZSTD_WINDOWLOG_MAX_64 27 +#define ZSTD_WINDOWLOG_MAX \ + ((unsigned int)(sizeof(size_t) == 4 \ + ? ZSTD_WINDOWLOG_MAX_32 \ + : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_HASHLOG3_MAX 17 +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +/* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_SEARCHLENGTH_MAX 7 +/* only for ZSTD_btopt, other strategies are limited to 4 */ +#define ZSTD_SEARCHLENGTH_MIN 3 +#define ZSTD_TARGETLENGTH_MIN 4 +#define ZSTD_TARGETLENGTH_MAX 999 + +/* for static allocation */ +#define ZSTD_FRAMEHEADERSIZE_MAX 18 +#define ZSTD_FRAMEHEADERSIZE_MIN 6 +#define ZSTD_frameHeaderSize_prefix 5 +#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN +#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX +/* magic number + skippable frame length */ +#define ZSTD_skippableHeaderSize 8 + + +/*-************************************* + * Compressed size functions + **************************************/ + +/** + * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame + * @src: Source buffer. It should point to the start of a zstd encoded frame + * or a skippable frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * size of the frame. + * + * Return: The compressed size of the frame pointed to by `src` or an error, + * which can be check with ZSTD_isError(). + * Suitable to pass to ZSTD_decompress() or similar functions. + */ +size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Decompressed size functions + **************************************/ +/** + * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header + * @src: It should point to the start of a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The frame content size stored in the frame header if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the + * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. + */ +unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/** + * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames + * @src: It should point to the start of a series of zstd encoded and/or + * skippable frames. + * @srcSize: The exact size of the series of frames. + * + * If any zstd encoded frame in the series doesn't have the frame content size + * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always + * set when using ZSTD_compress(). The decompressed size can be very large. + * If the source is untrusted, the decompressed size could be wrong or + * intentionally modified. Always ensure the result fits within the + * application's authorized limits. ZSTD_findDecompressedSize() handles multiple + * frames, and so it must traverse the input to read each frame header. This is + * efficient as most of the data is skipped, however it does mean that all frame + * data must be present and valid. + * + * Return: Decompressed size of all the data contained in the frames if known. + * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. + * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. + */ +unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); + +/*-************************************* + * Advanced compression functions + **************************************/ +/** + * ZSTD_checkCParams() - ensure parameter values remain within authorized range + * @cParams: The zstd compression parameters. + * + * Return: Zero or an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); + +/** + * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize + * @srcSize: Optionally the estimated source size, or zero if unknown. + * @dictSize: Optionally the estimated dictionary size, or zero if unknown. + * + * Return: The optimized parameters. + */ +ZSTD_compressionParameters ZSTD_adjustCParams( + ZSTD_compressionParameters cParams, unsigned long long srcSize, + size_t dictSize); + +/*--- Advanced decompression functions ---*/ + +/** + * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame + * @buffer: The source buffer to check. + * @size: The size of the source buffer, must be at least 4 bytes. + * + * Return: True iff the buffer starts with a zstd or skippable frame identifier. + */ +unsigned int ZSTD_isFrame(const void *buffer, size_t size); + +/** + * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary + * @dict: The dictionary buffer. + * @dictSize: The size of the dictionary buffer. + * + * Return: The dictionary id stored within the dictionary or 0 if the + * dictionary is not a zstd dictionary. If it returns 0 the + * dictionary can still be loaded as a content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); + +/** + * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict + * @ddict: The ddict to find the id of. + * + * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not + * a zstd dictionary. If it returns 0 `ddict` will be loaded as a + * content-only dictionary. + */ +unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); + +/** + * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame + * @src: Source buffer. It must be a zstd encoded frame. + * @srcSize: The size of the source buffer. It must be at least as large as the + * frame header. `ZSTD_frameHeaderSize_max` is always large enough. + * + * Return: The dictionary id required to decompress the frame stored within + * `src` or 0 if the dictionary id could not be decoded. It can return + * 0 if the frame does not require a dictionary, the dictionary id + * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` + * is too small. + */ +unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); + +/** + * struct ZSTD_frameParams - zstd frame parameters stored in the frame header + * @frameContentSize: The frame content size, or 0 if not present. + * @windowSize: The window size, or 0 if the frame is a skippable frame. + * @dictID: The dictionary id, or 0 if not present. + * @checksumFlag: Whether a checksum was used. + */ +typedef struct { + unsigned long long frameContentSize; + unsigned int windowSize; + unsigned int dictID; + unsigned int checksumFlag; +} ZSTD_frameParams; + +/** + * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame + * @fparamsPtr: On success the frame parameters are written here. + * @src: The source buffer. It must point to a zstd or skippable frame. + * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is + * always large enough to succeed. + * + * Return: 0 on success. If more data is required it returns how many bytes + * must be provided to make forward progress. Otherwise it returns + * an error, which can be checked using ZSTD_isError(). + */ +size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, + size_t srcSize); + +/*-***************************************************************************** + * Buffer-less and synchronous inner streaming functions + * + * This is an advanced API, giving full control over buffer management, for + * users which need direct control over memory. + * But it's also a complex one, with many restrictions (documented below). + * Prefer using normal streaming API for an easier experience + ******************************************************************************/ + +/*-***************************************************************************** + * Buffer-less streaming compression (synchronous mode) + * + * A ZSTD_CCtx object is required to track streaming operations. + * Use ZSTD_initCCtx() to initialize a context. + * ZSTD_CCtx object can be re-used multiple times within successive compression + * operations. + * + * Start by initializing a context. + * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary + * compression, + * or ZSTD_compressBegin_advanced(), for finer parameter control. + * It's also possible to duplicate a reference context which has already been + * initialized, using ZSTD_copyCCtx() + * + * Then, consume your input using ZSTD_compressContinue(). + * There are some important considerations to keep in mind when using this + * advanced function : + * - ZSTD_compressContinue() has no internal buffer. It uses externally provided + * buffer only. + * - Interface is synchronous : input is consumed entirely and produce 1+ + * (or more) compressed blocks. + * - Caller must ensure there is enough space in `dst` to store compressed data + * under worst case scenario. Worst case evaluation is provided by + * ZSTD_compressBound(). + * ZSTD_compressContinue() doesn't guarantee recover after a failed + * compression. + * - ZSTD_compressContinue() presumes prior input ***is still accessible and + * unmodified*** (up to maximum distance size, see WindowLog). + * It remembers all previous contiguous blocks, plus one separated memory + * segment (which can itself consists of multiple contiguous blocks) + * - ZSTD_compressContinue() detects that prior input has been overwritten when + * `src` buffer overlaps. In which case, it will "discard" the relevant memory + * section from its history. + * + * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) + * and optional checksum. It's possible to use srcSize==0, in which case, it + * will write a final empty block to end the frame. Without last block mark, + * frames will be considered unfinished (corrupted) by decoders. + * + * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new + * frame. + ******************************************************************************/ + +/*===== Buffer-less streaming compression functions =====*/ +size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); +size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, int compressionLevel); +size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, + size_t dictSize, ZSTD_parameters params, + unsigned long long pledgedSrcSize); +size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, + unsigned long long pledgedSrcSize); +size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); + + + +/*-***************************************************************************** + * Buffer-less streaming decompression (synchronous mode) + * + * A ZSTD_DCtx object is required to track streaming operations. + * Use ZSTD_initDCtx() to initialize a context. + * A ZSTD_DCtx object can be re-used multiple times. + * + * First typical operation is to retrieve frame parameters, using + * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide + * important information to correctly decode the frame, such as the minimum + * rolling buffer size to allocate to decompress data (`windowSize`), and the + * dictionary ID used. + * Note: content size is optional, it may not be present. 0 means unknown. + * Note that these values could be wrong, either because of data malformation, + * or because an attacker is spoofing deliberate false information. As a + * consequence, check that values remain within valid application range, + * especially `windowSize`, before allocation. Each application can set its own + * limit, depending on local restrictions. For extended interoperability, it is + * recommended to support at least 8 MB. + * Frame parameters are extracted from the beginning of the compressed frame. + * Data fragment must be large enough to ensure successful decoding, typically + * `ZSTD_frameHeaderSize_max` bytes. + * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. + * >0: `srcSize` is too small, provide at least this many bytes. + * errorCode, which can be tested using ZSTD_isError(). + * + * Start decompression, with ZSTD_decompressBegin() or + * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared + * context, using ZSTD_copyDCtx(). + * + * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() + * alternatively. + * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' + * to ZSTD_decompressContinue(). + * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will + * fail. + * + * The result of ZSTD_decompressContinue() is the number of bytes regenerated + * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an + * error; it just means ZSTD_decompressContinue() has decoded some metadata + * item. It can also be an error code, which can be tested with ZSTD_isError(). + * + * ZSTD_decompressContinue() needs previous data blocks during decompression, up + * to `windowSize`. They should preferably be located contiguously, prior to + * current block. Alternatively, a round buffer of sufficient size is also + * possible. Sufficient size is determined by frame parameters. + * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't + * follow each other, make sure that either the compressor breaks contiguity at + * the same place, or that previous contiguous segment is large enough to + * properly handle maximum back-reference. + * + * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. + * Context can then be reset to start a new decompression. + * + * Note: it's possible to know if next input to present is a header or a block, + * using ZSTD_nextInputType(). This information is not required to properly + * decode a frame. + * + * == Special case: skippable frames == + * + * Skippable frames allow integration of user-defined data into a flow of + * concatenated frames. Skippable frames will be ignored (skipped) by a + * decompressor. The format of skippable frames is as follows: + * a) Skippable frame ID - 4 Bytes, Little endian format, any value from + * 0x184D2A50 to 0x184D2A5F + * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits + * c) Frame Content - any content (User Data) of length equal to Frame Size + * For skippable frames ZSTD_decompressContinue() always returns 0. + * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 + * what means that a frame is skippable. + * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might + * actually be a zstd encoded frame with no content. For purposes of + * decompression, it is valid in both cases to skip the frame using + * ZSTD_findFrameCompressedSize() to find its size in bytes. + * It also returns frame size as fparamsPtr->frameContentSize. + ******************************************************************************/ + +/*===== Buffer-less streaming decompression functions =====*/ +size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); +size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, + size_t dictSize); +void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); +size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); +size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +typedef enum { + ZSTDnit_frameHeader, + ZSTDnit_blockHeader, + ZSTDnit_block, + ZSTDnit_lastBlock, + ZSTDnit_checksum, + ZSTDnit_skippableFrame +} ZSTD_nextInputType_e; +ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); + +/*-***************************************************************************** + * Block functions + * + * Block functions produce and decode raw zstd blocks, without frame metadata. + * Frame metadata cost is typically ~18 bytes, which can be non-negligible for + * very small blocks (< 100 bytes). User will have to take in charge required + * information to regenerate data, such as compressed and content sizes. + * + * A few rules to respect: + * - Compressing and decompressing require a context structure + * + Use ZSTD_initCCtx() and ZSTD_initDCtx() + * - It is necessary to init context before starting + * + compression : ZSTD_compressBegin() + * + decompression : ZSTD_decompressBegin() + * + variants _usingDict() are also allowed + * + copyCCtx() and copyDCtx() work too + * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() + * + If you need to compress more, cut data into multiple blocks + * + Consider using the regular ZSTD_compress() instead, as frame metadata + * costs become negligible when source size is large. + * - When a block is considered not compressible enough, ZSTD_compressBlock() + * result will be zero. In which case, nothing is produced into `dst`. + * + User must test for such outcome and deal directly with uncompressed data + * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! + * + In case of multiple successive blocks, decoder must be informed of + * uncompressed block existence to follow proper history. Use + * ZSTD_insertBlock() in such a case. + ******************************************************************************/ + +/* Define for static allocation */ +#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) +/*===== Raw zstd block functions =====*/ +size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); +size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, + const void *src, size_t srcSize); +size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, + size_t blockSize); + +#endif /* ZSTD_H */ diff --git a/lib/decompress_unzstd.c b/lib/decompress_unzstd.c index 6b629ab31c1e..c076d6f05064 100644 --- a/lib/decompress_unzstd.c +++ b/lib/decompress_unzstd.c @@ -91,11 +91,15 @@ static int INIT handle_zstd_error(size_t ret, void (*error)(char *x)) { - const int err = ZSTD_getErrorCode(ret); + const zstd_error_code err = zstd_get_error_code(ret); - if (!ZSTD_isError(ret)) + if (!zstd_is_error(ret)) return 0; + /* + * zstd_get_error_name() cannot be used because error takes a char * + * not a const char * + */ switch (err) { case ZSTD_error_memory_allocation: error("ZSTD decompressor ran out of memory"); @@ -124,28 +128,28 @@ static int INIT decompress_single(const u8 *in_buf, long in_len, u8 *out_buf, long out_len, long *in_pos, void (*error)(char *x)) { - const size_t wksp_size = ZSTD_DCtxWorkspaceBound(); + const size_t wksp_size = zstd_dctx_workspace_bound(); void *wksp = large_malloc(wksp_size); - ZSTD_DCtx *dctx = ZSTD_initDCtx(wksp, wksp_size); + zstd_dctx *dctx = zstd_init_dctx(wksp, wksp_size); int err; size_t ret; if (dctx == NULL) { - error("Out of memory while allocating ZSTD_DCtx"); + error("Out of memory while allocating zstd_dctx"); err = -1; goto out; } /* * Find out how large the frame actually is, there may be junk at - * the end of the frame that ZSTD_decompressDCtx() can't handle. + * the end of the frame that zstd_decompress_dctx() can't handle. */ - ret = ZSTD_findFrameCompressedSize(in_buf, in_len); + ret = zstd_find_frame_compressed_size(in_buf, in_len); err = handle_zstd_error(ret, error); if (err) goto out; in_len = (long)ret; - ret = ZSTD_decompressDCtx(dctx, out_buf, out_len, in_buf, in_len); + ret = zstd_decompress_dctx(dctx, out_buf, out_len, in_buf, in_len); err = handle_zstd_error(ret, error); if (err) goto out; @@ -167,14 +171,14 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len, long *in_pos, void (*error)(char *x)) { - ZSTD_inBuffer in; - ZSTD_outBuffer out; - ZSTD_frameParams params; + zstd_in_buffer in; + zstd_out_buffer out; + zstd_frame_header header; void *in_allocated = NULL; void *out_allocated = NULL; void *wksp = NULL; size_t wksp_size; - ZSTD_DStream *dstream; + zstd_dstream *dstream; int err; size_t ret; @@ -238,13 +242,13 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len, out.size = out_len; /* - * We need to know the window size to allocate the ZSTD_DStream. + * We need to know the window size to allocate the zstd_dstream. * Since we are streaming, we need to allocate a buffer for the sliding * window. The window size varies from 1 KB to ZSTD_WINDOWSIZE_MAX * (8 MB), so it is important to use the actual value so as not to * waste memory when it is smaller. */ - ret = ZSTD_getFrameParams(¶ms, in.src, in.size); + ret = zstd_get_frame_header(&header, in.src, in.size); err = handle_zstd_error(ret, error); if (err) goto out; @@ -253,19 +257,19 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len, err = -1; goto out; } - if (params.windowSize > ZSTD_WINDOWSIZE_MAX) { + if (header.windowSize > ZSTD_WINDOWSIZE_MAX) { error("ZSTD-compressed data has too large a window size"); err = -1; goto out; } /* - * Allocate the ZSTD_DStream now that we know how much memory is + * Allocate the zstd_dstream now that we know how much memory is * required. */ - wksp_size = ZSTD_DStreamWorkspaceBound(params.windowSize); + wksp_size = zstd_dstream_workspace_bound(header.windowSize); wksp = large_malloc(wksp_size); - dstream = ZSTD_initDStream(params.windowSize, wksp, wksp_size); + dstream = zstd_init_dstream(header.windowSize, wksp, wksp_size); if (dstream == NULL) { error("Out of memory while allocating ZSTD_DStream"); err = -1; @@ -298,7 +302,7 @@ static int INIT __unzstd(unsigned char *in_buf, long in_len, in.size = in_len; } /* Returns zero when the frame is complete. */ - ret = ZSTD_decompressStream(dstream, &out, &in); + ret = zstd_decompress_stream(dstream, &out, &in); err = handle_zstd_error(ret, error); if (err) goto out; diff --git a/lib/zstd/compress.c b/lib/zstd/compress.c index b080264ed3ad..57aaa64306a0 100644 --- a/lib/zstd/compress.c +++ b/lib/zstd/compress.c @@ -3443,43 +3443,92 @@ ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, return params; } -EXPORT_SYMBOL(ZSTD_maxCLevel); -EXPORT_SYMBOL(ZSTD_compressBound); - -EXPORT_SYMBOL(ZSTD_CCtxWorkspaceBound); -EXPORT_SYMBOL(ZSTD_initCCtx); -EXPORT_SYMBOL(ZSTD_compressCCtx); -EXPORT_SYMBOL(ZSTD_compress_usingDict); - -EXPORT_SYMBOL(ZSTD_CDictWorkspaceBound); -EXPORT_SYMBOL(ZSTD_initCDict); -EXPORT_SYMBOL(ZSTD_compress_usingCDict); - -EXPORT_SYMBOL(ZSTD_CStreamWorkspaceBound); -EXPORT_SYMBOL(ZSTD_initCStream); -EXPORT_SYMBOL(ZSTD_initCStream_usingCDict); -EXPORT_SYMBOL(ZSTD_resetCStream); -EXPORT_SYMBOL(ZSTD_compressStream); -EXPORT_SYMBOL(ZSTD_flushStream); -EXPORT_SYMBOL(ZSTD_endStream); -EXPORT_SYMBOL(ZSTD_CStreamInSize); -EXPORT_SYMBOL(ZSTD_CStreamOutSize); - -EXPORT_SYMBOL(ZSTD_getCParams); -EXPORT_SYMBOL(ZSTD_getParams); -EXPORT_SYMBOL(ZSTD_checkCParams); -EXPORT_SYMBOL(ZSTD_adjustCParams); - -EXPORT_SYMBOL(ZSTD_compressBegin); -EXPORT_SYMBOL(ZSTD_compressBegin_usingDict); -EXPORT_SYMBOL(ZSTD_compressBegin_advanced); -EXPORT_SYMBOL(ZSTD_copyCCtx); -EXPORT_SYMBOL(ZSTD_compressBegin_usingCDict); -EXPORT_SYMBOL(ZSTD_compressContinue); -EXPORT_SYMBOL(ZSTD_compressEnd); - -EXPORT_SYMBOL(ZSTD_getBlockSizeMax); -EXPORT_SYMBOL(ZSTD_compressBlock); +size_t zstd_compress_bound(size_t src_size) +{ + return ZSTD_compressBound(src_size); +} +EXPORT_SYMBOL(zstd_compress_bound); + +int zstd_min_clevel(void) +{ + /* + * zstd-1.3.1 doesn't implement ZSTD_minCLevel(). + * Return 0 (default level). + */ + return 0; +} +EXPORT_SYMBOL(zstd_min_clevel); + +int zstd_max_clevel(void) +{ + return ZSTD_maxCLevel(); +} +EXPORT_SYMBOL(zstd_max_clevel); + +zstd_parameters zstd_get_params(int level, + unsigned long long estimated_src_size) +{ + return ZSTD_getParams(level, estimated_src_size, 0); +} +EXPORT_SYMBOL(zstd_get_params); + +size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams) +{ + return ZSTD_CCtxWorkspaceBound(*cparams); +} +EXPORT_SYMBOL(zstd_cctx_workspace_bound); + +zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size) +{ + return ZSTD_initCCtx(workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_cctx); + +size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size, const zstd_parameters *parameters) +{ + return ZSTD_compressCCtx(cctx, dst, dst_capacity, src, src_size, *parameters); +} +EXPORT_SYMBOL(zstd_compress_cctx); + +size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams) +{ + return ZSTD_CStreamWorkspaceBound(*cparams); +} +EXPORT_SYMBOL(zstd_cstream_workspace_bound); + +zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters, + unsigned long long pledged_src_size, void *workspace, size_t workspace_size) +{ + return ZSTD_initCStream(*parameters, pledged_src_size, workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_cstream); + +size_t zstd_reset_cstream(zstd_cstream *cstream, + unsigned long long pledged_src_size) +{ + return ZSTD_resetCStream(cstream, pledged_src_size); +} +EXPORT_SYMBOL(zstd_reset_cstream); + +size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output, + zstd_in_buffer *input) +{ + return ZSTD_compressStream(cstream, output, input); +} +EXPORT_SYMBOL(zstd_compress_stream); + +size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output) +{ + return ZSTD_flushStream(cstream, output); +} +EXPORT_SYMBOL(zstd_flush_stream); + +size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output) +{ + return ZSTD_endStream(cstream, output); +} +EXPORT_SYMBOL(zstd_end_stream); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("Zstd Compressor"); diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c index 66cd487a326a..02e92c2cbf4f 100644 --- a/lib/zstd/decompress.c +++ b/lib/zstd/decompress.c @@ -2490,42 +2490,82 @@ size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inB } } -EXPORT_SYMBOL(ZSTD_DCtxWorkspaceBound); -EXPORT_SYMBOL(ZSTD_initDCtx); -EXPORT_SYMBOL(ZSTD_decompressDCtx); -EXPORT_SYMBOL(ZSTD_decompress_usingDict); - -EXPORT_SYMBOL(ZSTD_DDictWorkspaceBound); -EXPORT_SYMBOL(ZSTD_initDDict); -EXPORT_SYMBOL(ZSTD_decompress_usingDDict); - -EXPORT_SYMBOL(ZSTD_DStreamWorkspaceBound); -EXPORT_SYMBOL(ZSTD_initDStream); -EXPORT_SYMBOL(ZSTD_initDStream_usingDDict); -EXPORT_SYMBOL(ZSTD_resetDStream); -EXPORT_SYMBOL(ZSTD_decompressStream); -EXPORT_SYMBOL(ZSTD_DStreamInSize); -EXPORT_SYMBOL(ZSTD_DStreamOutSize); - -EXPORT_SYMBOL(ZSTD_findFrameCompressedSize); -EXPORT_SYMBOL(ZSTD_getFrameContentSize); -EXPORT_SYMBOL(ZSTD_findDecompressedSize); - -EXPORT_SYMBOL(ZSTD_isFrame); -EXPORT_SYMBOL(ZSTD_getDictID_fromDict); -EXPORT_SYMBOL(ZSTD_getDictID_fromDDict); -EXPORT_SYMBOL(ZSTD_getDictID_fromFrame); - -EXPORT_SYMBOL(ZSTD_getFrameParams); -EXPORT_SYMBOL(ZSTD_decompressBegin); -EXPORT_SYMBOL(ZSTD_decompressBegin_usingDict); -EXPORT_SYMBOL(ZSTD_copyDCtx); -EXPORT_SYMBOL(ZSTD_nextSrcSizeToDecompress); -EXPORT_SYMBOL(ZSTD_decompressContinue); -EXPORT_SYMBOL(ZSTD_nextInputType); - -EXPORT_SYMBOL(ZSTD_decompressBlock); -EXPORT_SYMBOL(ZSTD_insertBlock); +unsigned int zstd_is_error(size_t code) +{ + return ZSTD_isError(code); +} +EXPORT_SYMBOL(zstd_is_error); + +zstd_error_code zstd_get_error_code(size_t code) +{ + return ZSTD_getErrorCode(code); +} +EXPORT_SYMBOL(zstd_get_error_code); + +const char *zstd_get_error_name(size_t code) +{ + /* Real implementation in zstd-1.4.6. */ + return "GENERIC"; +} +EXPORT_SYMBOL(zstd_get_error_name); + +size_t zstd_dctx_workspace_bound(void) +{ + return ZSTD_DCtxWorkspaceBound(); +} +EXPORT_SYMBOL(zstd_dctx_workspace_bound); + +zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size) +{ + return ZSTD_initDCtx(workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_dctx); + +size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size) +{ + return ZSTD_decompressDCtx(dctx, dst, dst_capacity, src, src_size); +} +EXPORT_SYMBOL(zstd_decompress_dctx); + +size_t zstd_dstream_workspace_bound(size_t max_window_size) +{ + return ZSTD_DStreamWorkspaceBound(max_window_size); +} +EXPORT_SYMBOL(zstd_dstream_workspace_bound); + +zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace, + size_t workspace_size) +{ + return ZSTD_initDStream(max_window_size, workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_dstream); + +size_t zstd_reset_dstream(zstd_dstream *dstream) +{ + return ZSTD_resetDStream(dstream); +} +EXPORT_SYMBOL(zstd_reset_dstream); + +size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output, + zstd_in_buffer *input) +{ + return ZSTD_decompressStream(dstream, output, input); +} +EXPORT_SYMBOL(zstd_decompress_stream); + +size_t zstd_find_frame_compressed_size(const void *src, size_t src_size) +{ + return ZSTD_findFrameCompressedSize(src, src_size); +} +EXPORT_SYMBOL(zstd_find_frame_compressed_size); + +size_t zstd_get_frame_header(zstd_frame_header *header, const void *src, + size_t src_size) +{ + return ZSTD_getFrameParams(header, src, src_size); +} +EXPORT_SYMBOL(zstd_get_frame_header); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("Zstd Decompressor"); -- cgit v1.2.3 From e0c1b49f5b674cca7b10549c53b3791d0bbc90a8 Mon Sep 17 00:00:00 2001 From: Nick Terrell Date: Fri, 11 Sep 2020 16:37:08 -0700 Subject: lib: zstd: Upgrade to latest upstream zstd version 1.4.10 Upgrade to the latest upstream zstd version 1.4.10. This patch is 100% generated from upstream zstd commit 20821a46f412 [0]. This patch is very large because it is transitioning from the custom kernel zstd to using upstream directly. The new zstd follows upstreams file structure which is different. Future update patches will be much smaller because they will only contain the changes from one upstream zstd release. As an aid for review I've created a commit [1] that shows the diff between upstream zstd as-is (which doesn't compile), and the zstd code imported in this patch. The verion of zstd in this patch is generated from upstream with changes applied by automation to replace upstreams libc dependencies, remove unnecessary portability macros, replace `/**` comments with `/*` comments, and use the kernel's xxhash instead of bundling it. The benefits of this patch are as follows: 1. Using upstream directly with automated script to generate kernel code. This allows us to update the kernel every upstream release, so the kernel gets the latest bug fixes and performance improvements, and doesn't get 3 years out of date again. The automation and the translated code are tested every upstream commit to ensure it continues to work. 2. Upgrades from a custom zstd based on 1.3.1 to 1.4.10, getting 3 years of performance improvements and bug fixes. On x86_64 I've measured 15% faster BtrFS and SquashFS decompression+read speeds, 35% faster kernel decompression, and 30% faster ZRAM decompression+read speeds. 3. Zstd-1.4.10 supports negative compression levels, which allow zstd to match or subsume lzo's performance. 4. Maintains the same kernel-specific wrapper API, so no callers have to be modified with zstd version updates. One concern that was brought up was stack usage. Upstream zstd had already removed most of its heavy stack usage functions, but I just removed the last functions that allocate arrays on the stack. I've measured the high water mark for both compression and decompression before and after this patch. Decompression is approximately neutral, using about 1.2KB of stack space. Compression levels up to 3 regressed from 1.4KB -> 1.6KB, and higher compression levels regressed from 1.5KB -> 2KB. We've added unit tests upstream to prevent further regression. I believe that this is a reasonable increase, and if it does end up causing problems, this commit can be cleanly reverted, because it only touches zstd. I chose the bulk update instead of replaying upstream commits because there have been ~3500 upstream commits since the 1.3.1 release, zstd wasn't ready to be used in the kernel as-is before a month ago, and not all upstream zstd commits build. The bulk update preserves bisectablity because bugs can be bisected to the zstd version update. At that point the update can be reverted, and we can work with upstream to find and fix the bug. Note that upstream zstd release 1.4.10 doesn't exist yet. I have cut a staging branch at 20821a46f412 [0] and will apply any changes requested to the staging branch. Once we're ready to merge this update I will cut a zstd release at the commit we merge, so we have a known zstd release in the kernel. The implementation of the kernel API is contained in zstd_compress_module.c and zstd_decompress_module.c. [0] https://github.com/facebook/zstd/commit/20821a46f4122f9abd7c7b245d28162dde8129c9 [1] https://github.com/terrelln/linux/commit/e0fa481d0e3df26918da0a13749740a1f6777574 Signed-off-by: Nick Terrell Tested By: Paul Jones Tested-by: Oleksandr Natalenko Tested-by: Sedat Dilek # LLVM/Clang v13.0.0 on x86-64 Tested-by: Jean-Denis Girard --- include/linux/zstd.h | 13 +- include/linux/zstd_errors.h | 77 + include/linux/zstd_lib.h | 3367 +++++++++++----- lib/zstd/Makefile | 46 +- lib/zstd/bitstream.h | 380 -- lib/zstd/common/bitstream.h | 437 ++ lib/zstd/common/compiler.h | 170 + lib/zstd/common/cpu.h | 194 + lib/zstd/common/debug.c | 24 + lib/zstd/common/debug.h | 101 + lib/zstd/common/entropy_common.c | 357 ++ lib/zstd/common/error_private.c | 56 + lib/zstd/common/error_private.h | 66 + lib/zstd/common/fse.h | 710 ++++ lib/zstd/common/fse_decompress.c | 390 ++ lib/zstd/common/huf.h | 356 ++ lib/zstd/common/mem.h | 259 ++ lib/zstd/common/zstd_common.c | 83 + lib/zstd/common/zstd_deps.h | 125 + lib/zstd/common/zstd_internal.h | 450 +++ lib/zstd/compress.c | 3534 ---------------- lib/zstd/compress/fse_compress.c | 625 +++ lib/zstd/compress/hist.c | 165 + lib/zstd/compress/hist.h | 75 + lib/zstd/compress/huf_compress.c | 905 +++++ lib/zstd/compress/zstd_compress.c | 5109 ++++++++++++++++++++++++ lib/zstd/compress/zstd_compress_internal.h | 1188 ++++++ lib/zstd/compress/zstd_compress_literals.c | 158 + lib/zstd/compress/zstd_compress_literals.h | 29 + lib/zstd/compress/zstd_compress_sequences.c | 439 ++ lib/zstd/compress/zstd_compress_sequences.h | 54 + lib/zstd/compress/zstd_compress_superblock.c | 850 ++++ lib/zstd/compress/zstd_compress_superblock.h | 32 + lib/zstd/compress/zstd_cwksp.h | 482 +++ lib/zstd/compress/zstd_double_fast.c | 519 +++ lib/zstd/compress/zstd_double_fast.h | 32 + lib/zstd/compress/zstd_fast.c | 496 +++ lib/zstd/compress/zstd_fast.h | 31 + lib/zstd/compress/zstd_lazy.c | 1414 +++++++ lib/zstd/compress/zstd_lazy.h | 81 + lib/zstd/compress/zstd_ldm.c | 686 ++++ lib/zstd/compress/zstd_ldm.h | 110 + lib/zstd/compress/zstd_ldm_geartab.h | 103 + lib/zstd/compress/zstd_opt.c | 1346 +++++++ lib/zstd/compress/zstd_opt.h | 50 + lib/zstd/decompress.c | 2571 ------------ lib/zstd/decompress/huf_decompress.c | 1206 ++++++ lib/zstd/decompress/zstd_ddict.c | 241 ++ lib/zstd/decompress/zstd_ddict.h | 44 + lib/zstd/decompress/zstd_decompress.c | 2085 ++++++++++ lib/zstd/decompress/zstd_decompress_block.c | 1540 +++++++ lib/zstd/decompress/zstd_decompress_block.h | 62 + lib/zstd/decompress/zstd_decompress_internal.h | 202 + lib/zstd/decompress_sources.h | 15 +- lib/zstd/entropy_common.c | 243 -- lib/zstd/error_private.h | 53 - lib/zstd/fse.h | 575 --- lib/zstd/fse_compress.c | 795 ---- lib/zstd/fse_decompress.c | 325 -- lib/zstd/huf.h | 212 - lib/zstd/huf_compress.c | 773 ---- lib/zstd/huf_decompress.c | 960 ----- lib/zstd/mem.h | 151 - lib/zstd/zstd_common.c | 75 - lib/zstd/zstd_compress_module.c | 160 + lib/zstd/zstd_decompress_module.c | 105 + lib/zstd/zstd_internal.h | 273 -- lib/zstd/zstd_opt.h | 1014 ----- 68 files changed, 26861 insertions(+), 12993 deletions(-) create mode 100644 include/linux/zstd_errors.h delete mode 100644 lib/zstd/bitstream.h create mode 100644 lib/zstd/common/bitstream.h create mode 100644 lib/zstd/common/compiler.h create mode 100644 lib/zstd/common/cpu.h create mode 100644 lib/zstd/common/debug.c create mode 100644 lib/zstd/common/debug.h create mode 100644 lib/zstd/common/entropy_common.c create mode 100644 lib/zstd/common/error_private.c create mode 100644 lib/zstd/common/error_private.h create mode 100644 lib/zstd/common/fse.h create mode 100644 lib/zstd/common/fse_decompress.c create mode 100644 lib/zstd/common/huf.h create mode 100644 lib/zstd/common/mem.h create mode 100644 lib/zstd/common/zstd_common.c create mode 100644 lib/zstd/common/zstd_deps.h create mode 100644 lib/zstd/common/zstd_internal.h delete mode 100644 lib/zstd/compress.c create mode 100644 lib/zstd/compress/fse_compress.c create mode 100644 lib/zstd/compress/hist.c create mode 100644 lib/zstd/compress/hist.h create mode 100644 lib/zstd/compress/huf_compress.c create mode 100644 lib/zstd/compress/zstd_compress.c create mode 100644 lib/zstd/compress/zstd_compress_internal.h create mode 100644 lib/zstd/compress/zstd_compress_literals.c create mode 100644 lib/zstd/compress/zstd_compress_literals.h create mode 100644 lib/zstd/compress/zstd_compress_sequences.c create mode 100644 lib/zstd/compress/zstd_compress_sequences.h create mode 100644 lib/zstd/compress/zstd_compress_superblock.c create mode 100644 lib/zstd/compress/zstd_compress_superblock.h create mode 100644 lib/zstd/compress/zstd_cwksp.h create mode 100644 lib/zstd/compress/zstd_double_fast.c create mode 100644 lib/zstd/compress/zstd_double_fast.h create mode 100644 lib/zstd/compress/zstd_fast.c create mode 100644 lib/zstd/compress/zstd_fast.h create mode 100644 lib/zstd/compress/zstd_lazy.c create mode 100644 lib/zstd/compress/zstd_lazy.h create mode 100644 lib/zstd/compress/zstd_ldm.c create mode 100644 lib/zstd/compress/zstd_ldm.h create mode 100644 lib/zstd/compress/zstd_ldm_geartab.h create mode 100644 lib/zstd/compress/zstd_opt.c create mode 100644 lib/zstd/compress/zstd_opt.h delete mode 100644 lib/zstd/decompress.c create mode 100644 lib/zstd/decompress/huf_decompress.c create mode 100644 lib/zstd/decompress/zstd_ddict.c create mode 100644 lib/zstd/decompress/zstd_ddict.h create mode 100644 lib/zstd/decompress/zstd_decompress.c create mode 100644 lib/zstd/decompress/zstd_decompress_block.c create mode 100644 lib/zstd/decompress/zstd_decompress_block.h create mode 100644 lib/zstd/decompress/zstd_decompress_internal.h delete mode 100644 lib/zstd/entropy_common.c delete mode 100644 lib/zstd/error_private.h delete mode 100644 lib/zstd/fse.h delete mode 100644 lib/zstd/fse_compress.c delete mode 100644 lib/zstd/fse_decompress.c delete mode 100644 lib/zstd/huf.h delete mode 100644 lib/zstd/huf_compress.c delete mode 100644 lib/zstd/huf_decompress.c delete mode 100644 lib/zstd/mem.h delete mode 100644 lib/zstd/zstd_common.c create mode 100644 lib/zstd/zstd_compress_module.c create mode 100644 lib/zstd/zstd_decompress_module.c delete mode 100644 lib/zstd/zstd_internal.h delete mode 100644 lib/zstd/zstd_opt.h (limited to 'include/linux') diff --git a/include/linux/zstd.h b/include/linux/zstd.h index 9fbc7729b0a0..113408eef6ec 100644 --- a/include/linux/zstd.h +++ b/include/linux/zstd.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ /* * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. @@ -22,6 +22,7 @@ /* ====== Dependency ====== */ #include +#include #include /* ====== Helper Functions ====== */ @@ -417,12 +418,18 @@ size_t zstd_find_frame_compressed_size(const void *src, size_t src_size); /** * struct zstd_frame_params - zstd frame parameters stored in the frame header - * @frameContentSize: The frame content size, or 0 if not present. + * @frameContentSize: The frame content size, or ZSTD_CONTENTSIZE_UNKNOWN if not + * present. * @windowSize: The window size, or 0 if the frame is a skippable frame. + * @blockSizeMax: The maximum block size. + * @frameType: The frame type (zstd or skippable) + * @headerSize: The size of the frame header. * @dictID: The dictionary id, or 0 if not present. * @checksumFlag: Whether a checksum was used. + * + * See zstd_lib.h. */ -typedef ZSTD_frameParams zstd_frame_header; +typedef ZSTD_frameHeader zstd_frame_header; /** * zstd_get_frame_header() - extracts parameters from a zstd or skippable frame diff --git a/include/linux/zstd_errors.h b/include/linux/zstd_errors.h new file mode 100644 index 000000000000..58b6dd45a969 --- /dev/null +++ b/include/linux/zstd_errors.h @@ -0,0 +1,77 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_ERRORS_H_398273423 +#define ZSTD_ERRORS_H_398273423 + + +/*===== dependency =====*/ +#include /* size_t */ + + +/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ +#define ZSTDERRORLIB_VISIBILITY +#define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY + +/*-********************************************* + * Error codes list + *-********************************************* + * Error codes _values_ are pinned down since v1.3.1 only. + * Therefore, don't rely on values if you may link to any version < v1.3.1. + * + * Only values < 100 are considered stable. + * + * note 1 : this API shall be used with static linking only. + * dynamic linking is not yet officially supported. + * note 2 : Prefer relying on the enum than on its value whenever possible + * This is the only supported way to use the error list < v1.3.1 + * note 3 : ZSTD_isError() is always correct, whatever the library version. + **********************************************/ +typedef enum { + ZSTD_error_no_error = 0, + ZSTD_error_GENERIC = 1, + ZSTD_error_prefix_unknown = 10, + ZSTD_error_version_unsupported = 12, + ZSTD_error_frameParameter_unsupported = 14, + ZSTD_error_frameParameter_windowTooLarge = 16, + ZSTD_error_corruption_detected = 20, + ZSTD_error_checksum_wrong = 22, + ZSTD_error_dictionary_corrupted = 30, + ZSTD_error_dictionary_wrong = 32, + ZSTD_error_dictionaryCreation_failed = 34, + ZSTD_error_parameter_unsupported = 40, + ZSTD_error_parameter_outOfBound = 42, + ZSTD_error_tableLog_tooLarge = 44, + ZSTD_error_maxSymbolValue_tooLarge = 46, + ZSTD_error_maxSymbolValue_tooSmall = 48, + ZSTD_error_stage_wrong = 60, + ZSTD_error_init_missing = 62, + ZSTD_error_memory_allocation = 64, + ZSTD_error_workSpace_tooSmall= 66, + ZSTD_error_dstSize_tooSmall = 70, + ZSTD_error_srcSize_wrong = 72, + ZSTD_error_dstBuffer_null = 74, + /* following error codes are __NOT STABLE__, they can be removed or changed in future versions */ + ZSTD_error_frameIndex_tooLarge = 100, + ZSTD_error_seekableIO = 102, + ZSTD_error_dstBuffer_wrong = 104, + ZSTD_error_srcBuffer_wrong = 105, + ZSTD_error_maxCode = 120 /* never EVER use this value directly, it can change in future versions! Use ZSTD_isError() instead */ +} ZSTD_ErrorCode; + +/*! ZSTD_getErrorCode() : + convert a `size_t` function result into a `ZSTD_ErrorCode` enum type, + which can be used to compare with enum list published above */ +ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); +ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); /*< Same as ZSTD_getErrorName, but using a `ZSTD_ErrorCode` enum argument */ + + + +#endif /* ZSTD_ERRORS_H_398273423 */ diff --git a/include/linux/zstd_lib.h b/include/linux/zstd_lib.h index 13151c34f725..b8c7dbf98390 100644 --- a/include/linux/zstd_lib.h +++ b/include/linux/zstd_lib.h @@ -2,1156 +2,2431 @@ * Copyright (c) Yann Collet, Facebook, Inc. * All rights reserved. * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. */ -#ifndef ZSTD_H -#define ZSTD_H +#ifndef ZSTD_H_235446 +#define ZSTD_H_235446 /* ====== Dependency ======*/ +#include /* INT_MAX */ #include /* size_t */ -/*-***************************************************************************** - * Introduction - * - * zstd, short for Zstandard, is a fast lossless compression algorithm, - * targeting real-time compression scenarios at zlib-level and better - * compression ratios. The zstd compression library provides in-memory - * compression and decompression functions. The library supports compression - * levels from 1 up to ZSTD_maxCLevel() which is 22. Levels >= 20, labeled - * ultra, should be used with caution, as they require more memory. - * Compression can be done in: - * - a single step, reusing a context (described as Explicit memory management) - * - unbounded multiple steps (described as Streaming compression) - * The compression ratio achievable on small data can be highly improved using - * compression with a dictionary in: - * - a single step (described as Simple dictionary API) - * - a single step, reusing a dictionary (described as Fast dictionary API) - ******************************************************************************/ +/* ===== ZSTDLIB_API : control library symbols visibility ===== */ +#define ZSTDLIB_VISIBILITY +#define ZSTDLIB_API ZSTDLIB_VISIBILITY + + +/* ***************************************************************************** + Introduction + + zstd, short for Zstandard, is a fast lossless compression algorithm, targeting + real-time compression scenarios at zlib-level and better compression ratios. + The zstd compression library provides in-memory compression and decompression + functions. + + The library supports regular compression levels from 1 up to ZSTD_maxCLevel(), + which is currently 22. Levels >= 20, labeled `--ultra`, should be used with + caution, as they require more memory. The library also offers negative + compression levels, which extend the range of speed vs. ratio preferences. + The lower the level, the faster the speed (at the cost of compression). + + Compression can be done in: + - a single step (described as Simple API) + - a single step, reusing a context (described as Explicit context) + - unbounded multiple steps (described as Streaming compression) + + The compression ratio achievable on small data can be highly improved using + a dictionary. Dictionary compression can be performed in: + - a single step (described as Simple dictionary API) + - a single step, reusing a dictionary (described as Bulk-processing + dictionary API) + + Advanced experimental functions can be accessed using + `#define ZSTD_STATIC_LINKING_ONLY` before including zstd.h. + + Advanced experimental APIs should never be used with a dynamically-linked + library. They are not "stable"; their definitions or signatures may change in + the future. Only static linking is allowed. +*******************************************************************************/ + +/*------ Version ------*/ +#define ZSTD_VERSION_MAJOR 1 +#define ZSTD_VERSION_MINOR 4 +#define ZSTD_VERSION_RELEASE 10 +#define ZSTD_VERSION_NUMBER (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE) + +/*! ZSTD_versionNumber() : + * Return runtime library version, the value is (MAJOR*100*100 + MINOR*100 + RELEASE). */ +ZSTDLIB_API unsigned ZSTD_versionNumber(void); + +#define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE +#define ZSTD_QUOTE(str) #str +#define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str) +#define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION) + +/*! ZSTD_versionString() : + * Return runtime library version, like "1.4.5". Requires v1.3.0+. */ +ZSTDLIB_API const char* ZSTD_versionString(void); + +/* ************************************* + * Default constant + ***************************************/ +#ifndef ZSTD_CLEVEL_DEFAULT +# define ZSTD_CLEVEL_DEFAULT 3 +#endif + +/* ************************************* + * Constants + ***************************************/ + +/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* valid since v0.8.0 */ +#define ZSTD_MAGIC_DICTIONARY 0xEC30A437 /* valid since v0.7.0 */ +#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50 /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */ +#define ZSTD_MAGIC_SKIPPABLE_MASK 0xFFFFFFF0 + +#define ZSTD_BLOCKSIZELOG_MAX 17 +#define ZSTD_BLOCKSIZE_MAX (1<= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel); + +/*! ZSTD_decompress() : + * `compressedSize` : must be the _exact_ size of some number of compressed and/or skippable frames. + * `dstCapacity` is an upper bound of originalSize to regenerate. + * If user cannot imply a maximum upper bound, it's better to use streaming mode to decompress data. + * @return : the number of bytes decompressed into `dst` (<= `dstCapacity`), + * or an errorCode if it fails (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity, + const void* src, size_t compressedSize); + +/*! ZSTD_getFrameContentSize() : requires v1.3.0+ + * `src` should point to the start of a ZSTD encoded frame. + * `srcSize` must be at least as large as the frame header. + * hint : any size >= `ZSTD_frameHeaderSize_max` is large enough. + * @return : - decompressed size of `src` frame content, if known + * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined + * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) + * note 1 : a 0 return value means the frame is valid but "empty". + * note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode. + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * Optionally, application can rely on some implicit limit, + * as ZSTD_decompress() only needs an upper bound of decompressed size. + * (For example, data could be necessarily cut into blocks <= 16 KB). + * note 3 : decompressed size is always present when compression is completed using single-pass functions, + * such as ZSTD_compress(), ZSTD_compressCCtx() ZSTD_compress_usingDict() or ZSTD_compress_usingCDict(). + * note 4 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure return value fits within application's authorized limits. + * Each application can set its own limits. + * note 6 : This function replaces ZSTD_getDecompressedSize() */ +#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) +#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) +ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); + +/*! ZSTD_getDecompressedSize() : + * NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize(). + * Both functions work the same way, but ZSTD_getDecompressedSize() blends + * "empty", "unknown" and "error" results to the same return value (0), + * while ZSTD_getFrameContentSize() gives them separate return values. + * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */ +ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize); + +/*! ZSTD_findFrameCompressedSize() : + * `src` should point to the start of a ZSTD frame or skippable frame. + * `srcSize` must be >= first frame size + * @return : the compressed size of the first frame starting at `src`, + * suitable to pass as `srcSize` to `ZSTD_decompress` or similar, + * or an error code if input is invalid */ +ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize); + /*====== Helper functions ======*/ +#define ZSTD_COMPRESSBOUND(srcSize) ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0)) /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */ +ZSTDLIB_API size_t ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */ +ZSTDLIB_API unsigned ZSTD_isError(size_t code); /*!< tells if a `size_t` function result is an error code */ +ZSTDLIB_API const char* ZSTD_getErrorName(size_t code); /*!< provides readable string from an error code */ +ZSTDLIB_API int ZSTD_minCLevel(void); /*!< minimum negative compression level allowed */ +ZSTDLIB_API int ZSTD_maxCLevel(void); /*!< maximum compression level available */ + + +/* ************************************* +* Explicit context +***************************************/ +/*= Compression context + * When compressing many times, + * it is recommended to allocate a context just once, + * and re-use it for each successive compression operation. + * This will make workload friendlier for system's memory. + * Note : re-using context is just a speed / resource optimization. + * It doesn't change the compression ratio, which remains identical. + * Note 2 : In multi-threaded environments, + * use one different context per thread for parallel execution. + */ +typedef struct ZSTD_CCtx_s ZSTD_CCtx; +ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx(void); +ZSTDLIB_API size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx); /* accept NULL pointer */ + +/*! ZSTD_compressCCtx() : + * Same as ZSTD_compress(), using an explicit ZSTD_CCtx. + * Important : in order to behave similarly to `ZSTD_compress()`, + * this function compresses at requested compression level, + * __ignoring any other parameter__ . + * If any advanced parameter was set using the advanced API, + * they will all be reset. Only `compressionLevel` remains. + */ +ZSTDLIB_API size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel); + +/*= Decompression context + * When decompressing many times, + * it is recommended to allocate a context only once, + * and re-use it for each successive compression operation. + * This will make workload friendlier for system's memory. + * Use one context per thread for parallel execution. */ +typedef struct ZSTD_DCtx_s ZSTD_DCtx; +ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx(void); +ZSTDLIB_API size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx); /* accept NULL pointer */ + +/*! ZSTD_decompressDCtx() : + * Same as ZSTD_decompress(), + * requires an allocated ZSTD_DCtx. + * Compatible with sticky parameters. + */ +ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); -/** - * enum ZSTD_ErrorCode - zstd error codes + +/* ************************************* +* Advanced compression API +***************************************/ + +/* API design : + * Parameters are pushed one by one into an existing context, + * using ZSTD_CCtx_set*() functions. + * Pushed parameters are sticky : they are valid for next compressed frame, and any subsequent frame. + * "sticky" parameters are applicable to `ZSTD_compress2()` and `ZSTD_compressStream*()` ! + * __They do not apply to "simple" one-shot variants such as ZSTD_compressCCtx()__ . + * + * It's possible to reset all parameters to "default" using ZSTD_CCtx_reset(). * - * Functions that return size_t can be checked for errors using ZSTD_isError() - * and the ZSTD_ErrorCode can be extracted using ZSTD_getErrorCode(). + * This API supercedes all other "advanced" API entry points in the experimental section. + * In the future, we expect to remove from experimental API entry points which are redundant with this API. + */ + + +/* Compression strategies, listed from fastest to strongest */ +typedef enum { ZSTD_fast=1, + ZSTD_dfast=2, + ZSTD_greedy=3, + ZSTD_lazy=4, + ZSTD_lazy2=5, + ZSTD_btlazy2=6, + ZSTD_btopt=7, + ZSTD_btultra=8, + ZSTD_btultra2=9 + /* note : new strategies _might_ be added in the future. + Only the order (from fast to strong) is guaranteed */ +} ZSTD_strategy; + + +typedef enum { + + /* compression parameters + * Note: When compressing with a ZSTD_CDict these parameters are superseded + * by the parameters used to construct the ZSTD_CDict. + * See ZSTD_CCtx_refCDict() for more info (superseded-by-cdict). */ + ZSTD_c_compressionLevel=100, /* Set compression parameters according to pre-defined cLevel table. + * Note that exact compression parameters are dynamically determined, + * depending on both compression level and srcSize (when known). + * Default level is ZSTD_CLEVEL_DEFAULT==3. + * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT. + * Note 1 : it's possible to pass a negative compression level. + * Note 2 : setting a level does not automatically set all other compression parameters + * to default. Setting this will however eventually dynamically impact the compression + * parameters which have not been manually set. The manually set + * ones will 'stick'. */ + /* Advanced compression parameters : + * It's possible to pin down compression parameters to some specific values. + * In which case, these values are no longer dynamically selected by the compressor */ + ZSTD_c_windowLog=101, /* Maximum allowed back-reference distance, expressed as power of 2. + * This will set a memory budget for streaming decompression, + * with larger values requiring more memory + * and typically compressing more. + * Must be clamped between ZSTD_WINDOWLOG_MIN and ZSTD_WINDOWLOG_MAX. + * Special: value 0 means "use default windowLog". + * Note: Using a windowLog greater than ZSTD_WINDOWLOG_LIMIT_DEFAULT + * requires explicitly allowing such size at streaming decompression stage. */ + ZSTD_c_hashLog=102, /* Size of the initial probe table, as a power of 2. + * Resulting memory usage is (1 << (hashLog+2)). + * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX. + * Larger tables improve compression ratio of strategies <= dFast, + * and improve speed of strategies > dFast. + * Special: value 0 means "use default hashLog". */ + ZSTD_c_chainLog=103, /* Size of the multi-probe search table, as a power of 2. + * Resulting memory usage is (1 << (chainLog+2)). + * Must be clamped between ZSTD_CHAINLOG_MIN and ZSTD_CHAINLOG_MAX. + * Larger tables result in better and slower compression. + * This parameter is useless for "fast" strategy. + * It's still useful when using "dfast" strategy, + * in which case it defines a secondary probe table. + * Special: value 0 means "use default chainLog". */ + ZSTD_c_searchLog=104, /* Number of search attempts, as a power of 2. + * More attempts result in better and slower compression. + * This parameter is useless for "fast" and "dFast" strategies. + * Special: value 0 means "use default searchLog". */ + ZSTD_c_minMatch=105, /* Minimum size of searched matches. + * Note that Zstandard can still find matches of smaller size, + * it just tweaks its search algorithm to look for this size and larger. + * Larger values increase compression and decompression speed, but decrease ratio. + * Must be clamped between ZSTD_MINMATCH_MIN and ZSTD_MINMATCH_MAX. + * Note that currently, for all strategies < btopt, effective minimum is 4. + * , for all strategies > fast, effective maximum is 6. + * Special: value 0 means "use default minMatchLength". */ + ZSTD_c_targetLength=106, /* Impact of this field depends on strategy. + * For strategies btopt, btultra & btultra2: + * Length of Match considered "good enough" to stop search. + * Larger values make compression stronger, and slower. + * For strategy fast: + * Distance between match sampling. + * Larger values make compression faster, and weaker. + * Special: value 0 means "use default targetLength". */ + ZSTD_c_strategy=107, /* See ZSTD_strategy enum definition. + * The higher the value of selected strategy, the more complex it is, + * resulting in stronger and slower compression. + * Special: value 0 means "use default strategy". */ + + /* LDM mode parameters */ + ZSTD_c_enableLongDistanceMatching=160, /* Enable long distance matching. + * This parameter is designed to improve compression ratio + * for large inputs, by finding large matches at long distance. + * It increases memory usage and window size. + * Note: enabling this parameter increases default ZSTD_c_windowLog to 128 MB + * except when expressly set to a different value. + * Note: will be enabled by default if ZSTD_c_windowLog >= 128 MB and + * compression strategy >= ZSTD_btopt (== compression level 16+) */ + ZSTD_c_ldmHashLog=161, /* Size of the table for long distance matching, as a power of 2. + * Larger values increase memory usage and compression ratio, + * but decrease compression speed. + * Must be clamped between ZSTD_HASHLOG_MIN and ZSTD_HASHLOG_MAX + * default: windowlog - 7. + * Special: value 0 means "automatically determine hashlog". */ + ZSTD_c_ldmMinMatch=162, /* Minimum match size for long distance matcher. + * Larger/too small values usually decrease compression ratio. + * Must be clamped between ZSTD_LDM_MINMATCH_MIN and ZSTD_LDM_MINMATCH_MAX. + * Special: value 0 means "use default value" (default: 64). */ + ZSTD_c_ldmBucketSizeLog=163, /* Log size of each bucket in the LDM hash table for collision resolution. + * Larger values improve collision resolution but decrease compression speed. + * The maximum value is ZSTD_LDM_BUCKETSIZELOG_MAX. + * Special: value 0 means "use default value" (default: 3). */ + ZSTD_c_ldmHashRateLog=164, /* Frequency of inserting/looking up entries into the LDM hash table. + * Must be clamped between 0 and (ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN). + * Default is MAX(0, (windowLog - ldmHashLog)), optimizing hash table usage. + * Larger values improve compression speed. + * Deviating far from default value will likely result in a compression ratio decrease. + * Special: value 0 means "automatically determine hashRateLog". */ + + /* frame parameters */ + ZSTD_c_contentSizeFlag=200, /* Content size will be written into frame header _whenever known_ (default:1) + * Content size must be known at the beginning of compression. + * This is automatically the case when using ZSTD_compress2(), + * For streaming scenarios, content size must be provided with ZSTD_CCtx_setPledgedSrcSize() */ + ZSTD_c_checksumFlag=201, /* A 32-bits checksum of content is written at end of frame (default:0) */ + ZSTD_c_dictIDFlag=202, /* When applicable, dictionary's ID is written into frame header (default:1) */ + + /* multi-threading parameters */ + /* These parameters are only active if multi-threading is enabled (compiled with build macro ZSTD_MULTITHREAD). + * Otherwise, trying to set any other value than default (0) will be a no-op and return an error. + * In a situation where it's unknown if the linked library supports multi-threading or not, + * setting ZSTD_c_nbWorkers to any value >= 1 and consulting the return value provides a quick way to check this property. + */ + ZSTD_c_nbWorkers=400, /* Select how many threads will be spawned to compress in parallel. + * When nbWorkers >= 1, triggers asynchronous mode when invoking ZSTD_compressStream*() : + * ZSTD_compressStream*() consumes input and flush output if possible, but immediately gives back control to caller, + * while compression is performed in parallel, within worker thread(s). + * (note : a strong exception to this rule is when first invocation of ZSTD_compressStream2() sets ZSTD_e_end : + * in which case, ZSTD_compressStream2() delegates to ZSTD_compress2(), which is always a blocking call). + * More workers improve speed, but also increase memory usage. + * Default value is `0`, aka "single-threaded mode" : no worker is spawned, + * compression is performed inside Caller's thread, and all invocations are blocking */ + ZSTD_c_jobSize=401, /* Size of a compression job. This value is enforced only when nbWorkers >= 1. + * Each compression job is completed in parallel, so this value can indirectly impact the nb of active threads. + * 0 means default, which is dynamically determined based on compression parameters. + * Job size must be a minimum of overlap size, or 1 MB, whichever is largest. + * The minimum size is automatically and transparently enforced. */ + ZSTD_c_overlapLog=402, /* Control the overlap size, as a fraction of window size. + * The overlap size is an amount of data reloaded from previous job at the beginning of a new job. + * It helps preserve compression ratio, while each job is compressed in parallel. + * This value is enforced only when nbWorkers >= 1. + * Larger values increase compression ratio, but decrease speed. + * Possible values range from 0 to 9 : + * - 0 means "default" : value will be determined by the library, depending on strategy + * - 1 means "no overlap" + * - 9 means "full overlap", using a full window size. + * Each intermediate rank increases/decreases load size by a factor 2 : + * 9: full window; 8: w/2; 7: w/4; 6: w/8; 5:w/16; 4: w/32; 3:w/64; 2:w/128; 1:no overlap; 0:default + * default value varies between 6 and 9, depending on strategy */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_c_rsyncable + * ZSTD_c_format + * ZSTD_c_forceMaxWindow + * ZSTD_c_forceAttachDict + * ZSTD_c_literalCompressionMode + * ZSTD_c_targetCBlockSize + * ZSTD_c_srcSizeHint + * ZSTD_c_enableDedicatedDictSearch + * ZSTD_c_stableInBuffer + * ZSTD_c_stableOutBuffer + * ZSTD_c_blockDelimiters + * ZSTD_c_validateSequences + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly; + * also, the enums values themselves are unstable and can still change. + */ + ZSTD_c_experimentalParam1=500, + ZSTD_c_experimentalParam2=10, + ZSTD_c_experimentalParam3=1000, + ZSTD_c_experimentalParam4=1001, + ZSTD_c_experimentalParam5=1002, + ZSTD_c_experimentalParam6=1003, + ZSTD_c_experimentalParam7=1004, + ZSTD_c_experimentalParam8=1005, + ZSTD_c_experimentalParam9=1006, + ZSTD_c_experimentalParam10=1007, + ZSTD_c_experimentalParam11=1008, + ZSTD_c_experimentalParam12=1009 +} ZSTD_cParameter; + +typedef struct { + size_t error; + int lowerBound; + int upperBound; +} ZSTD_bounds; + +/*! ZSTD_cParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - lower and upper bounds, both inclusive + */ +ZSTDLIB_API ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter cParam); + +/*! ZSTD_CCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_cParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_cParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * Setting a parameter is generally only possible during frame initialization (before starting compression). + * Exception : when using multi-threading mode (nbWorkers >= 1), + * the following parameters can be updated _during_ compression (within same frame): + * => compressionLevel, hashLog, chainLog, searchLog, minMatch, targetLength and strategy. + * new parameters will be active for next job only (after a flush()). + * @return : an error code (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value); + +/*! ZSTD_CCtx_setPledgedSrcSize() : + * Total input data size to be compressed as a single frame. + * Value will be written in frame header, unless if explicitly forbidden using ZSTD_c_contentSizeFlag. + * This value will also be controlled at end of frame, and trigger an error if not respected. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : pledgedSrcSize==0 actually means zero, aka an empty frame. + * In order to mean "unknown content size", pass constant ZSTD_CONTENTSIZE_UNKNOWN. + * ZSTD_CONTENTSIZE_UNKNOWN is default value for any new frame. + * Note 2 : pledgedSrcSize is only valid once, for the next frame. + * It's discarded at the end of the frame, and replaced by ZSTD_CONTENTSIZE_UNKNOWN. + * Note 3 : Whenever all input data is provided and consumed in a single round, + * for example with ZSTD_compress2(), + * or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end), + * this value is automatically overridden by srcSize instead. + */ +ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize); + typedef enum { - ZSTD_error_no_error, - ZSTD_error_GENERIC, - ZSTD_error_prefix_unknown, - ZSTD_error_version_unsupported, - ZSTD_error_parameter_unknown, - ZSTD_error_frameParameter_unsupported, - ZSTD_error_frameParameter_unsupportedBy32bits, - ZSTD_error_frameParameter_windowTooLarge, - ZSTD_error_compressionParameter_unsupported, - ZSTD_error_init_missing, - ZSTD_error_memory_allocation, - ZSTD_error_stage_wrong, - ZSTD_error_dstSize_tooSmall, - ZSTD_error_srcSize_wrong, - ZSTD_error_corruption_detected, - ZSTD_error_checksum_wrong, - ZSTD_error_tableLog_tooLarge, - ZSTD_error_maxSymbolValue_tooLarge, - ZSTD_error_maxSymbolValue_tooSmall, - ZSTD_error_dictionary_corrupted, - ZSTD_error_dictionary_wrong, - ZSTD_error_dictionaryCreation_failed, - ZSTD_error_maxCode -} ZSTD_ErrorCode; - -/** - * ZSTD_maxCLevel() - maximum compression level available - * - * Return: Maximum compression level available. - */ -int ZSTD_maxCLevel(void); -/** - * ZSTD_compressBound() - maximum compressed size in worst case scenario - * @srcSize: The size of the data to compress. - * - * Return: The maximum compressed size in the worst case scenario. - */ -size_t ZSTD_compressBound(size_t srcSize); -/** - * ZSTD_isError() - tells if a size_t function result is an error code - * @code: The function result to check for error. - * - * Return: Non-zero iff the code is an error. - */ -static __attribute__((unused)) unsigned int ZSTD_isError(size_t code) -{ - return code > (size_t)-ZSTD_error_maxCode; -} -/** - * ZSTD_getErrorCode() - translates an error function result to a ZSTD_ErrorCode - * @functionResult: The result of a function for which ZSTD_isError() is true. - * - * Return: The ZSTD_ErrorCode corresponding to the functionResult or 0 - * if the functionResult isn't an error. - */ -static __attribute__((unused)) ZSTD_ErrorCode ZSTD_getErrorCode( - size_t functionResult) -{ - if (!ZSTD_isError(functionResult)) - return (ZSTD_ErrorCode)0; - return (ZSTD_ErrorCode)(0 - functionResult); -} - -/** - * enum ZSTD_strategy - zstd compression search strategy - * - * From faster to stronger. + ZSTD_reset_session_only = 1, + ZSTD_reset_parameters = 2, + ZSTD_reset_session_and_parameters = 3 +} ZSTD_ResetDirective; + +/*! ZSTD_CCtx_reset() : + * There are 2 different things that can be reset, independently or jointly : + * - The session : will stop compressing current frame, and make CCtx ready to start a new one. + * Useful after an error, or to interrupt any ongoing compression. + * Any internal data not yet flushed is cancelled. + * Compression parameters and dictionary remain unchanged. + * They will be used to compress next frame. + * Resetting session never fails. + * - The parameters : changes all parameters back to "default". + * This removes any reference to any dictionary too. + * Parameters can only be changed between 2 sessions (i.e. no compression is currently ongoing) + * otherwise the reset fails, and function returns an error value (which can be tested using ZSTD_isError()) + * - Both : similar to resetting the session, followed by resetting parameters. */ +ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset); + +/*! ZSTD_compress2() : + * Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API. + * ZSTD_compress2() always starts a new frame. + * Should cctx hold data from a previously unfinished frame, everything about it is forgotten. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - The function is always blocking, returns when compression is completed. + * Hint : compression runs faster if `dstCapacity` >= `ZSTD_compressBound(srcSize)`. + * @return : compressed size written into `dst` (<= `dstCapacity), + * or an error code if it fails (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize); + + +/* ************************************* +* Advanced decompression API +***************************************/ + +/* The advanced API pushes parameters one by one into an existing DCtx context. + * Parameters are sticky, and remain valid for all following frames + * using the same DCtx context. + * It's possible to reset parameters to default values using ZSTD_DCtx_reset(). + * Note : This API is compatible with existing ZSTD_decompressDCtx() and ZSTD_decompressStream(). + * Therefore, no new decompression function is necessary. + */ + typedef enum { - ZSTD_fast, - ZSTD_dfast, - ZSTD_greedy, - ZSTD_lazy, - ZSTD_lazy2, - ZSTD_btlazy2, - ZSTD_btopt, - ZSTD_btopt2 -} ZSTD_strategy; -/** - * struct ZSTD_compressionParameters - zstd compression parameters - * @windowLog: Log of the largest match distance. Larger means more - * compression, and more memory needed during decompression. - * @chainLog: Fully searched segment. Larger means more compression, slower, - * and more memory (useless for fast). - * @hashLog: Dispatch table. Larger means more compression, - * slower, and more memory. - * @searchLog: Number of searches. Larger means more compression and slower. - * @searchLength: Match length searched. Larger means faster decompression, - * sometimes less compression. - * @targetLength: Acceptable match size for optimal parser (only). Larger means - * more compression, and slower. - * @strategy: The zstd compression strategy. + ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which + * the streaming API will refuse to allocate memory buffer + * in order to protect the host from unreasonable memory requirements. + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT). + * Special: value 0 means "use default maximum windowLog". */ + + /* note : additional experimental parameters are also available + * within the experimental section of the API. + * At the time of this writing, they include : + * ZSTD_d_format + * ZSTD_d_stableOutBuffer + * ZSTD_d_forceIgnoreChecksum + * ZSTD_d_refMultipleDDicts + * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them. + * note : never ever use experimentalParam? names directly + */ + ZSTD_d_experimentalParam1=1000, + ZSTD_d_experimentalParam2=1001, + ZSTD_d_experimentalParam3=1002, + ZSTD_d_experimentalParam4=1003 + +} ZSTD_dParameter; + +/*! ZSTD_dParam_getBounds() : + * All parameters must belong to an interval with lower and upper bounds, + * otherwise they will either trigger an error or be automatically clamped. + * @return : a structure, ZSTD_bounds, which contains + * - an error status field, which must be tested using ZSTD_isError() + * - both lower and upper bounds, inclusive */ -typedef struct { - unsigned int windowLog; - unsigned int chainLog; - unsigned int hashLog; - unsigned int searchLog; - unsigned int searchLength; - unsigned int targetLength; - ZSTD_strategy strategy; -} ZSTD_compressionParameters; +ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam); + +/*! ZSTD_DCtx_setParameter() : + * Set one compression parameter, selected by enum ZSTD_dParameter. + * All parameters have valid bounds. Bounds can be queried using ZSTD_dParam_getBounds(). + * Providing a value beyond bound will either clamp it, or trigger an error (depending on parameter). + * Setting a parameter is only possible during frame initialization (before starting decompression). + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value); + +/*! ZSTD_DCtx_reset() : + * Return a DCtx to clean state. + * Session and parameters can be reset jointly or separately. + * Parameters can only be reset when no active frame is being decompressed. + * @return : 0, or an error code, which can be tested with ZSTD_isError() + */ +ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset); + + +/* ************************** +* Streaming +****************************/ + +typedef struct ZSTD_inBuffer_s { + const void* src; /*< start of input buffer */ + size_t size; /*< size of input buffer */ + size_t pos; /*< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_inBuffer; + +typedef struct ZSTD_outBuffer_s { + void* dst; /*< start of output buffer */ + size_t size; /*< size of output buffer */ + size_t pos; /*< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */ +} ZSTD_outBuffer; + -/** - * struct ZSTD_frameParameters - zstd frame parameters - * @contentSizeFlag: Controls whether content size will be present in the frame - * header (when known). - * @checksumFlag: Controls whether a 32-bit checksum is generated at the end - * of the frame for error detection. - * @noDictIDFlag: Controls whether dictID will be saved into the frame header - * when using dictionary compression. + +/*-*********************************************************************** +* Streaming compression - HowTo +* +* A ZSTD_CStream object is required to track streaming operation. +* Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources. +* ZSTD_CStream objects can be reused multiple times on consecutive compression operations. +* It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory. +* +* For parallel execution, use one separate ZSTD_CStream per thread. +* +* note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing. +* +* Parameters are sticky : when starting a new compression on the same context, +* it will re-use the same sticky parameters as previous compression session. +* When in doubt, it's recommended to fully initialize the context before usage. +* Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(), +* ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to +* set more specific parameters, the pledged source size, or load a dictionary. +* +* Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to +* consume input stream. The function will automatically update both `pos` +* fields within `input` and `output`. +* Note that the function may not consume the entire input, for example, because +* the output buffer is already full, in which case `input.pos < input.size`. +* The caller must check if input has been entirely consumed. +* If not, the caller must make some room to receive more compressed data, +* and then present again remaining input data. +* note: ZSTD_e_continue is guaranteed to make some forward progress when called, +* but doesn't guarantee maximal forward progress. This is especially relevant +* when compressing with multiple threads. The call won't block if it can +* consume some input, but if it can't it will wait for some, but not all, +* output to be flushed. +* @return : provides a minimum amount of data remaining to be flushed from internal buffers +* or an error code, which can be tested using ZSTD_isError(). +* +* At any moment, it's possible to flush whatever data might remain stuck within internal buffer, +* using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated. +* Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0). +* In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the +* operation. +* note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if internal buffers are entirely flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), +* or an error code, which can be tested using ZSTD_isError(). +* +* Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame. +* It will perform a flush and write frame epilogue. +* The epilogue is required for decoders to consider a frame completed. +* flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush. +* You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to +* start a new frame. +* note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will +* block until the flush is complete or the output buffer is full. +* @return : 0 if frame fully completed and fully flushed, +* >0 if some data still present within internal buffer (the value is minimal estimation of remaining size), +* or an error code, which can be tested using ZSTD_isError(). +* +* *******************************************************************/ + +typedef ZSTD_CCtx ZSTD_CStream; /*< CCtx and CStream are now effectively same object (>= v1.3.0) */ + /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */ +/*===== ZSTD_CStream management functions =====*/ +ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void); +ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs); /* accept NULL pointer */ + +/*===== Streaming compression functions =====*/ +typedef enum { + ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */ + ZSTD_e_flush=1, /* flush any data provided so far, + * it creates (at least) one new block, that can be decoded immediately on reception; + * frame will continue: any future data can still reference previously compressed data, improving compression. + * note : multithreaded compression will block to flush as much output as possible. */ + ZSTD_e_end=2 /* flush any remaining data _and_ close current frame. + * note that frame is only closed after compressed data is fully flushed (return value == 0). + * After that point, any additional data starts a new frame. + * note : each frame is independent (does not reference any content from previous frame). + : note : multithreaded compression will block to flush as much output as possible. */ +} ZSTD_EndDirective; + +/*! ZSTD_compressStream2() : + * Behaves about the same as ZSTD_compressStream, with additional control on end directive. + * - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*() + * - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode) + * - output->pos must be <= dstCapacity, input->pos must be <= srcSize + * - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit. + * - endOp must be a valid directive + * - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller. + * - When nbWorkers>=1, function is non-blocking : it copies a portion of input, distributes jobs to internal worker threads, flush to output whatever is available, + * and then immediately returns, just indicating that there is some data remaining to be flushed. + * The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte. + * - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking. + * - @return provides a minimum amount of data remaining to be flushed from internal buffers + * or an error code, which can be tested using ZSTD_isError(). + * if @return != 0, flush is not fully completed, there is still some data left within internal buffers. + * This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers. + * For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed. + * - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0), + * only ZSTD_e_end or ZSTD_e_flush operations are allowed. + * Before starting a new compression job, or changing compression parameters, + * it is required to fully flush internal buffers. + */ +ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp); + + +/* These buffer sizes are softly recommended. + * They are not required : ZSTD_compressStream*() happily accepts any buffer size, for both input and output. + * Respecting the recommended size just makes it a bit easier for ZSTD_compressStream*(), + * reducing the amount of memory shuffling and buffering, resulting in minor performance savings. + * + * However, note that these recommendations are from the perspective of a C caller program. + * If the streaming interface is invoked from some other language, + * especially managed ones such as Java or Go, through a foreign function interface such as jni or cgo, + * a major performance rule is to reduce crossing such interface to an absolute minimum. + * It's not rare that performance ends being spent more into the interface, rather than compression itself. + * In which cases, prefer using large buffers, as large as practical, + * for both input and output, to reduce the nb of roundtrips. + */ +ZSTDLIB_API size_t ZSTD_CStreamInSize(void); /*< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_CStreamOutSize(void); /*< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block. */ + + +/* ***************************************************************************** + * This following is a legacy streaming API. + * It can be replaced by ZSTD_CCtx_reset() and ZSTD_compressStream2(). + * It is redundant, but remains fully supported. + * Advanced parameters and dictionary compression can only be used through the + * new API. + ******************************************************************************/ + +/*! + * Equivalent to: * - * The default value is all fields set to 0. + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + */ +ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel); +/*! + * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue). + * NOTE: The return value is different. ZSTD_compressStream() returns a hint for + * the next read size (if non-zero and not an error). ZSTD_compressStream2() + * returns the minimum nb of bytes left to flush (if non-zero and not an error). */ +ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input); +/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */ +ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); +/*! Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */ +ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output); + + +/*-*************************************************************************** +* Streaming decompression - HowTo +* +* A ZSTD_DStream object is required to track streaming operations. +* Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources. +* ZSTD_DStream objects can be re-used multiple times. +* +* Use ZSTD_initDStream() to start a new decompression operation. +* @return : recommended first input size +* Alternatively, use advanced API to set specific properties. +* +* Use ZSTD_decompressStream() repetitively to consume your input. +* The function will update both `pos` fields. +* If `input.pos < input.size`, some input has not been consumed. +* It's up to the caller to present again remaining data. +* The function tries to flush all data decoded immediately, respecting output buffer size. +* If `output.pos < output.size`, decoder has flushed everything it could. +* But if `output.pos == output.size`, there might be some data left within internal buffers., +* In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer. +* Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX. +* @return : 0 when a frame is completely decoded and fully flushed, +* or an error code, which can be tested using ZSTD_isError(), +* or any other value > 0, which means there is still some decoding or flushing to do to complete current frame : +* the return value is a suggested next input size (just a hint for better latency) +* that will never request more than the remaining frame size. +* *******************************************************************************/ + +typedef ZSTD_DCtx ZSTD_DStream; /*< DCtx and DStream are now effectively same object (>= v1.3.0) */ + /* For compatibility with versions <= v1.2.0, prefer differentiating them. */ +/*===== ZSTD_DStream management functions =====*/ +ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void); +ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds); /* accept NULL pointer */ + +/*===== Streaming decompression functions =====*/ + +/* This function is redundant with the advanced API and equivalent to: + * + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, NULL); + */ +ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds); + +ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input); + +ZSTDLIB_API size_t ZSTD_DStreamInSize(void); /*!< recommended size for input buffer */ +ZSTDLIB_API size_t ZSTD_DStreamOutSize(void); /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */ + + +/* ************************ +* Simple dictionary API +***************************/ +/*! ZSTD_compress_usingDict() : + * Compression at an explicit compression level using a Dictionary. + * A dictionary can be any arbitrary data segment (also called a prefix), + * or a buffer with specified information (see dictBuilder/zdict.h). + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + int compressionLevel); + +/*! ZSTD_decompress_usingDict() : + * Decompression using a known Dictionary. + * Dictionary must be identical to the one used during compression. + * Note : This function loads the dictionary, resulting in significant startup delay. + * It's intended for a dictionary used only once. + * Note : When `dict == NULL || dictSize < 8` no dictionary is used. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize); + + +/* ********************************* + * Bulk processing dictionary API + **********************************/ +typedef struct ZSTD_CDict_s ZSTD_CDict; + +/*! ZSTD_createCDict() : + * When compressing multiple messages or blocks using the same dictionary, + * it's recommended to digest the dictionary only once, since it's a costly operation. + * ZSTD_createCDict() will create a state from digesting a dictionary. + * The resulting state can be used for future compression operations with very limited startup cost. + * ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only. + * @dictBuffer can be released after ZSTD_CDict creation, because its content is copied within CDict. + * Note 1 : Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate @dictBuffer content. + * Note 2 : A ZSTD_CDict can be created from an empty @dictBuffer, + * in which case the only thing that it transports is the @compressionLevel. + * This can be useful in a pipeline featuring ZSTD_compress_usingCDict() exclusively, + * expecting a ZSTD_CDict parameter with any data, including those without a known dictionary. */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, + int compressionLevel); + +/*! ZSTD_freeCDict() : + * Function frees memory allocated by ZSTD_createCDict(). + * If a NULL pointer is passed, no operation is performed. */ +ZSTDLIB_API size_t ZSTD_freeCDict(ZSTD_CDict* CDict); + +/*! ZSTD_compress_usingCDict() : + * Compression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. + * Note : compression level is _decided at dictionary creation time_, + * and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */ +ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict); + + +typedef struct ZSTD_DDict_s ZSTD_DDict; + +/*! ZSTD_createDDict() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * dictBuffer can be released after DDict creation, as its content is copied inside DDict. */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); + +/*! ZSTD_freeDDict() : + * Function frees memory allocated with ZSTD_createDDict() + * If a NULL pointer is passed, no operation is performed. */ +ZSTDLIB_API size_t ZSTD_freeDDict(ZSTD_DDict* ddict); + +/*! ZSTD_decompress_usingDDict() : + * Decompression using a digested Dictionary. + * Recommended when same dictionary is used multiple times. */ +ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_DDict* ddict); + + +/* ****************************** + * Dictionary helper functions + *******************************/ + +/*! ZSTD_getDictID_fromDict() : + * Provides the dictID stored within dictionary. + * if @return == 0, the dictionary is not conformant with Zstandard specification. + * It can still be loaded, but as a content-only dictionary. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); + +/*! ZSTD_getDictID_fromDDict() : + * Provides the dictID of the dictionary loaded into `ddict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); + +/*! ZSTD_getDictID_fromFrame() : + * Provides the dictID required to decompressed the frame stored within `src`. + * If @return == 0, the dictID could not be decoded. + * This could for one of the following reasons : + * - The frame does not require a dictionary to be decoded (most common case). + * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. + * Note : this use case also happens when using a non-conformant dictionary. + * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). + * - This is not a Zstandard frame. + * When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); + + +/* ***************************************************************************** + * Advanced dictionary and prefix API + * + * This API allows dictionaries to be used with ZSTD_compress2(), + * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and + * only reset with the context is reset with ZSTD_reset_parameters or + * ZSTD_reset_session_and_parameters. Prefixes are single-use. + ******************************************************************************/ + + +/*! ZSTD_CCtx_loadDictionary() : + * Create an internal CDict from `dict` buffer. + * Decompression will have to use same dictionary. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Dictionary is sticky, it will be used for all future compressed frames. + * To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters). + * Note 2 : Loading a dictionary involves building tables. + * It's also a CPU consuming operation, with non-negligible impact on latency. + * Tables are dependent on compression parameters, and for this reason, + * compression parameters can no longer be changed after loading a dictionary. + * Note 3 :`dict` content will be copied internally. + * Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead. + * In such a case, dictionary buffer must outlive its users. + * Note 4 : Use ZSTD_CCtx_loadDictionary_advanced() + * to precisely select how dictionary content must be interpreted. */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); + +/*! ZSTD_CCtx_refCDict() : + * Reference a prepared dictionary, to be used for all next compressed frames. + * Note that compression parameters are enforced from within CDict, + * and supersede any compression parameter previously set within CCtx. + * The parameters ignored are labelled as "superseded-by-cdict" in the ZSTD_cParameter enum docs. + * The ignored parameters will be used again if the CCtx is returned to no-dictionary mode. + * The dictionary will remain valid for future compressed frames using same CCtx. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Referencing a NULL CDict means "return to no-dictionary mode". + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. */ +ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); + +/*! ZSTD_CCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) for next compressed frame. + * A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end). + * Decompression will need same prefix to properly regenerate data. + * Compressing with a prefix is similar in outcome as performing a diff and compressing it, + * but performs much faster, especially during decompression (compression speed is tunable with compression level). + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary + * Note 1 : Prefix buffer is referenced. It **must** outlive compression. + * Its content must remain unmodified during compression. + * Note 2 : If the intention is to diff some large src data blob with some prior version of itself, + * ensure that the window size is large enough to contain the entire source. + * See ZSTD_c_windowLog. + * Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters. + * It's a CPU consuming operation, with non-negligible impact on latency. + * If there is a need to use the same prefix multiple times, consider loadDictionary instead. + * Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dct_rawContent). + * Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. */ +ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, + const void* prefix, size_t prefixSize); + +/*! ZSTD_DCtx_loadDictionary() : + * Create an internal DDict from dict buffer, + * to be used to decompress next frames. + * The dictionary remains valid for all future frames, until explicitly invalidated. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Special : Adding a NULL (or 0-size) dictionary invalidates any previous dictionary, + * meaning "return to no-dictionary mode". + * Note 1 : Loading a dictionary involves building tables, + * which has a non-negligible impact on CPU usage and latency. + * It's recommended to "load once, use many times", to amortize the cost + * Note 2 :`dict` content will be copied internally, so `dict` can be released after loading. + * Use ZSTD_DCtx_loadDictionary_byReference() to reference dictionary content instead. + * Note 3 : Use ZSTD_DCtx_loadDictionary_advanced() to take control of + * how dictionary content is loaded and interpreted. + */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! ZSTD_DCtx_refDDict() : + * Reference a prepared dictionary, to be used to decompress next frames. + * The dictionary remains active for decompression of future frames using same DCtx. + * + * If called with ZSTD_d_refMultipleDDicts enabled, repeated calls of this function + * will store the DDict references in a table, and the DDict used for decompression + * will be determined at decompression time, as per the dict ID in the frame. + * The memory for the table is allocated on the first call to refDDict, and can be + * freed with ZSTD_freeDCtx(). + * + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Currently, only one dictionary can be managed. + * Referencing a new dictionary effectively "discards" any previous one. + * Special: referencing a NULL DDict means "return to no-dictionary mode". + * Note 2 : DDict is just referenced, its lifetime must outlive its usage from DCtx. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + +/*! ZSTD_DCtx_refPrefix() : + * Reference a prefix (single-usage dictionary) to decompress next frame. + * This is the reverse operation of ZSTD_CCtx_refPrefix(), + * and must use the same prefix as the one used during compression. + * Prefix is **only used once**. Reference is discarded at end of frame. + * End of frame is reached when ZSTD_decompressStream() returns 0. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + * Note 1 : Adding any prefix (including NULL) invalidates any previously set prefix or dictionary + * Note 2 : Prefix buffer is referenced. It **must** outlive decompression. + * Prefix buffer must remain unmodified up to the end of frame, + * reached when ZSTD_decompressStream() returns 0. + * Note 3 : By default, the prefix is treated as raw content (ZSTD_dct_rawContent). + * Use ZSTD_CCtx_refPrefix_advanced() to alter dictMode (Experimental section) + * Note 4 : Referencing a raw content prefix has almost no cpu nor memory cost. + * A full dictionary is more costly, as it requires building tables. + */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, + const void* prefix, size_t prefixSize); + +/* === Memory management === */ + +/*! ZSTD_sizeof_*() : + * These functions give the _current_ memory usage of selected object. + * Note that object memory usage can evolve (increase or decrease) over time. */ +ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs); +ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds); +ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict); +ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); + +#endif /* ZSTD_H_235446 */ + + +/* ************************************************************************************** + * ADVANCED AND EXPERIMENTAL FUNCTIONS + **************************************************************************************** + * The definitions in the following section are considered experimental. + * They are provided for advanced scenarios. + * They should never be used with a dynamic library, as prototypes may change in the future. + * Use them only in association with static linking. + * ***************************************************************************************/ + +#if !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY) +#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY + +/* ************************************************************************************** + * experimental API (static linking only) + **************************************************************************************** + * The following symbols and constants + * are not planned to join "stable API" status in the near future. + * They can still change in future versions. + * Some of them are planned to remain in the static_only section indefinitely. + * Some of them might be removed in the future (especially when redundant with existing stable functions) + * ***************************************************************************************/ + +#define ZSTD_FRAMEHEADERSIZE_PREFIX(format) ((format) == ZSTD_f_zstd1 ? 5 : 1) /* minimum input size required to query frame header size */ +#define ZSTD_FRAMEHEADERSIZE_MIN(format) ((format) == ZSTD_f_zstd1 ? 6 : 2) +#define ZSTD_FRAMEHEADERSIZE_MAX 18 /* can be useful for static allocation */ +#define ZSTD_SKIPPABLEHEADERSIZE 8 + +/* compression parameter bounds */ +#define ZSTD_WINDOWLOG_MAX_32 30 +#define ZSTD_WINDOWLOG_MAX_64 31 +#define ZSTD_WINDOWLOG_MAX ((int)(sizeof(size_t) == 4 ? ZSTD_WINDOWLOG_MAX_32 : ZSTD_WINDOWLOG_MAX_64)) +#define ZSTD_WINDOWLOG_MIN 10 +#define ZSTD_HASHLOG_MAX ((ZSTD_WINDOWLOG_MAX < 30) ? ZSTD_WINDOWLOG_MAX : 30) +#define ZSTD_HASHLOG_MIN 6 +#define ZSTD_CHAINLOG_MAX_32 29 +#define ZSTD_CHAINLOG_MAX_64 30 +#define ZSTD_CHAINLOG_MAX ((int)(sizeof(size_t) == 4 ? ZSTD_CHAINLOG_MAX_32 : ZSTD_CHAINLOG_MAX_64)) +#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN +#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) +#define ZSTD_SEARCHLOG_MIN 1 +#define ZSTD_MINMATCH_MAX 7 /* only for ZSTD_fast, other strategies are limited to 6 */ +#define ZSTD_MINMATCH_MIN 3 /* only for ZSTD_btopt+, faster strategies are limited to 4 */ +#define ZSTD_TARGETLENGTH_MAX ZSTD_BLOCKSIZE_MAX +#define ZSTD_TARGETLENGTH_MIN 0 /* note : comparing this constant to an unsigned results in a tautological test */ +#define ZSTD_STRATEGY_MIN ZSTD_fast +#define ZSTD_STRATEGY_MAX ZSTD_btultra2 + + +#define ZSTD_OVERLAPLOG_MIN 0 +#define ZSTD_OVERLAPLOG_MAX 9 + +#define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27 /* by default, the streaming decoder will refuse any frame + * requiring larger than (1< 0: + * If litLength != 0: + * rep == 1 --> offset == repeat_offset_1 + * rep == 2 --> offset == repeat_offset_2 + * rep == 3 --> offset == repeat_offset_3 + * If litLength == 0: + * rep == 1 --> offset == repeat_offset_2 + * rep == 2 --> offset == repeat_offset_3 + * rep == 3 --> offset == repeat_offset_1 - 1 + * + * Note: This field is optional. ZSTD_generateSequences() will calculate the value of + * 'rep', but repeat offsets do not necessarily need to be calculated from an external + * sequence provider's perspective. For example, ZSTD_compressSequences() does not + * use this 'rep' field at all (as of now). + */ +} ZSTD_Sequence; + +typedef struct { + unsigned windowLog; /*< largest match distance : larger == more compression, more memory needed during decompression */ + unsigned chainLog; /*< fully searched segment : larger == more compression, slower, more memory (useless for fast) */ + unsigned hashLog; /*< dispatch table : larger == faster, more memory */ + unsigned searchLog; /*< nb of searches : larger == more compression, slower */ + unsigned minMatch; /*< match length searched : larger == faster decompression, sometimes less compression */ + unsigned targetLength; /*< acceptable match size for optimal parser (only) : larger == more compression, slower */ + ZSTD_strategy strategy; /*< see ZSTD_strategy definition above */ +} ZSTD_compressionParameters; + +typedef struct { + int contentSizeFlag; /*< 1: content size will be in frame header (when known) */ + int checksumFlag; /*< 1: generate a 32-bits checksum using XXH64 algorithm at end of frame, for error detection */ + int noDictIDFlag; /*< 1: no dictID will be saved into frame header (dictID is only useful for dictionary compression) */ } ZSTD_frameParameters; -/** - * struct ZSTD_parameters - zstd parameters - * @cParams: The compression parameters. - * @fParams: The frame parameters. - */ typedef struct { - ZSTD_compressionParameters cParams; - ZSTD_frameParameters fParams; + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; } ZSTD_parameters; -/** - * ZSTD_getCParams() - returns ZSTD_compressionParameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. - * - * Return: The selected ZSTD_compressionParameters. +typedef enum { + ZSTD_dct_auto = 0, /* dictionary is "full" when starting with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */ + ZSTD_dct_rawContent = 1, /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */ + ZSTD_dct_fullDict = 2 /* refuses to load a dictionary if it does not respect Zstandard's specification, starting with ZSTD_MAGIC_DICTIONARY */ +} ZSTD_dictContentType_e; + +typedef enum { + ZSTD_dlm_byCopy = 0, /*< Copy dictionary content internally */ + ZSTD_dlm_byRef = 1 /*< Reference dictionary content -- the dictionary buffer must outlive its users. */ +} ZSTD_dictLoadMethod_e; + +typedef enum { + ZSTD_f_zstd1 = 0, /* zstd frame format, specified in zstd_compression_format.md (default) */ + ZSTD_f_zstd1_magicless = 1 /* Variant of zstd frame format, without initial 4-bytes magic number. + * Useful to save 4 bytes per generated frame. + * Decoder cannot recognise automatically this format, requiring this instruction. */ +} ZSTD_format_e; + +typedef enum { + /* Note: this enum controls ZSTD_d_forceIgnoreChecksum */ + ZSTD_d_validateChecksum = 0, + ZSTD_d_ignoreChecksum = 1 +} ZSTD_forceIgnoreChecksum_e; + +typedef enum { + /* Note: this enum controls ZSTD_d_refMultipleDDicts */ + ZSTD_rmd_refSingleDDict = 0, + ZSTD_rmd_refMultipleDDicts = 1 +} ZSTD_refMultipleDDicts_e; + +typedef enum { + /* Note: this enum and the behavior it controls are effectively internal + * implementation details of the compressor. They are expected to continue + * to evolve and should be considered only in the context of extremely + * advanced performance tuning. + * + * Zstd currently supports the use of a CDict in three ways: + * + * - The contents of the CDict can be copied into the working context. This + * means that the compression can search both the dictionary and input + * while operating on a single set of internal tables. This makes + * the compression faster per-byte of input. However, the initial copy of + * the CDict's tables incurs a fixed cost at the beginning of the + * compression. For small compressions (< 8 KB), that copy can dominate + * the cost of the compression. + * + * - The CDict's tables can be used in-place. In this model, compression is + * slower per input byte, because the compressor has to search two sets of + * tables. However, this model incurs no start-up cost (as long as the + * working context's tables can be reused). For small inputs, this can be + * faster than copying the CDict's tables. + * + * - The CDict's tables are not used at all, and instead we use the working + * context alone to reload the dictionary and use params based on the source + * size. See ZSTD_compress_insertDictionary() and ZSTD_compress_usingDict(). + * This method is effective when the dictionary sizes are very small relative + * to the input size, and the input size is fairly large to begin with. + * + * Zstd has a simple internal heuristic that selects which strategy to use + * at the beginning of a compression. However, if experimentation shows that + * Zstd is making poor choices, it is possible to override that choice with + * this enum. + */ + ZSTD_dictDefaultAttach = 0, /* Use the default heuristic. */ + ZSTD_dictForceAttach = 1, /* Never copy the dictionary. */ + ZSTD_dictForceCopy = 2, /* Always copy the dictionary. */ + ZSTD_dictForceLoad = 3 /* Always reload the dictionary */ +} ZSTD_dictAttachPref_e; + +typedef enum { + ZSTD_lcm_auto = 0, /*< Automatically determine the compression mode based on the compression level. + * Negative compression levels will be uncompressed, and positive compression + * levels will be compressed. */ + ZSTD_lcm_huffman = 1, /*< Always attempt Huffman compression. Uncompressed literals will still be + * emitted if Huffman compression is not profitable. */ + ZSTD_lcm_uncompressed = 2 /*< Always emit uncompressed literals. */ +} ZSTD_literalCompressionMode_e; + + +/* ************************************* +* Frame size functions +***************************************/ + +/*! ZSTD_findDecompressedSize() : + * `src` should point to the start of a series of ZSTD encoded and/or skippable frames + * `srcSize` must be the _exact_ size of this series + * (i.e. there should be a frame boundary at `src + srcSize`) + * @return : - decompressed size of all data in all successive frames + * - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN + * - if an error occurred: ZSTD_CONTENTSIZE_ERROR + * + * note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode. + * When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size. + * In which case, it's necessary to use streaming mode to decompress data. + * note 2 : decompressed size is always present when compression is done with ZSTD_compress() + * note 3 : decompressed size can be very large (64-bits value), + * potentially larger than what local system can handle as a single memory segment. + * In which case, it's necessary to use streaming mode to decompress data. + * note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified. + * Always ensure result fits within application's authorized limits. + * Each application can set its own limits. + * note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to + * read each contained frame header. This is fast as most of the data is skipped, + * however it does mean that all frame data must be present and valid. */ +ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize); + +/*! ZSTD_decompressBound() : + * `src` should point to the start of a series of ZSTD encoded and/or skippable frames + * `srcSize` must be the _exact_ size of this series + * (i.e. there should be a frame boundary at `src + srcSize`) + * @return : - upper-bound for the decompressed size of all data in all successive frames + * - if an error occurred: ZSTD_CONTENTSIZE_ERROR + * + * note 1 : an error can occur if `src` contains an invalid or incorrectly formatted frame. + * note 2 : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`. + * in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value. + * note 3 : when the decompressed size field isn't available, the upper-bound for that frame is calculated by: + * upper-bound = # blocks * min(128 KB, Window_Size) */ -ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); +ZSTDLIB_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize); -/** - * ZSTD_getParams() - returns ZSTD_parameters for selected level - * @compressionLevel: The compression level from 1 to ZSTD_maxCLevel(). - * @estimatedSrcSize: The estimated source size to compress or 0 if unknown. - * @dictSize: The dictionary size or 0 if a dictionary isn't being used. +/*! ZSTD_frameHeaderSize() : + * srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX. + * @return : size of the Frame Header, + * or an error code (if srcSize is too small) */ +ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize); + +typedef enum { + ZSTD_sf_noBlockDelimiters = 0, /* Representation of ZSTD_Sequence has no block delimiters, sequences only */ + ZSTD_sf_explicitBlockDelimiters = 1 /* Representation of ZSTD_Sequence contains explicit block delimiters */ +} ZSTD_sequenceFormat_e; + +/*! ZSTD_generateSequences() : + * Generate sequences using ZSTD_compress2, given a source buffer. + * + * Each block will end with a dummy sequence + * with offset == 0, matchLength == 0, and litLength == length of last literals. + * litLength may be == 0, and if so, then the sequence of (of: 0 ml: 0 ll: 0) + * simply acts as a block delimiter. * - * The same as ZSTD_getCParams() except also selects the default frame - * parameters (all zero). + * zc can be used to insert custom compression params. + * This function invokes ZSTD_compress2 * - * Return: The selected ZSTD_parameters. + * The output of this function can be fed into ZSTD_compressSequences() with CCtx + * setting of ZSTD_c_blockDelimiters as ZSTD_sf_explicitBlockDelimiters + * @return : number of sequences generated */ -ZSTD_parameters ZSTD_getParams(int compressionLevel, - unsigned long long estimatedSrcSize, size_t dictSize); -/*-************************************* - * Explicit memory management - **************************************/ +ZSTDLIB_API size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, + size_t outSeqsSize, const void* src, size_t srcSize); -/** - * ZSTD_CCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_CCtx - * @cParams: The compression parameters to be used for compression. +/*! ZSTD_mergeBlockDelimiters() : + * Given an array of ZSTD_Sequence, remove all sequences that represent block delimiters/last literals + * by merging them into into the literals of the next sequence. * - * If multiple compression parameters might be used, the caller must call - * ZSTD_CCtxWorkspaceBound() for each set of parameters and use the maximum - * size. + * As such, the final generated result has no explicit representation of block boundaries, + * and the final last literals segment is not represented in the sequences. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCCtx(). + * The output of this function can be fed into ZSTD_compressSequences() with CCtx + * setting of ZSTD_c_blockDelimiters as ZSTD_sf_noBlockDelimiters + * @return : number of sequences left after merging + */ +ZSTDLIB_API size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize); + +/*! ZSTD_compressSequences() : + * Compress an array of ZSTD_Sequence, generated from the original source buffer, into dst. + * If a dictionary is included, then the cctx should reference the dict. (see: ZSTD_CCtx_refCDict(), ZSTD_CCtx_loadDictionary(), etc.) + * The entire source is compressed into a single frame. + * + * The compression behavior changes based on cctx params. In particular: + * If ZSTD_c_blockDelimiters == ZSTD_sf_noBlockDelimiters, the array of ZSTD_Sequence is expected to contain + * no block delimiters (defined in ZSTD_Sequence). Block boundaries are roughly determined based on + * the block size derived from the cctx, and sequences may be split. This is the default setting. + * + * If ZSTD_c_blockDelimiters == ZSTD_sf_explicitBlockDelimiters, the array of ZSTD_Sequence is expected to contain + * block delimiters (defined in ZSTD_Sequence). Behavior is undefined if no block delimiters are provided. + * + * If ZSTD_c_validateSequences == 0, this function will blindly accept the sequences provided. Invalid sequences cause undefined + * behavior. If ZSTD_c_validateSequences == 1, then if sequence is invalid (see doc/zstd_compression_format.md for + * specifics regarding offset/matchlength requirements) then the function will bail out and return an error. + * + * In addition to the two adjustable experimental params, there are other important cctx params. + * - ZSTD_c_minMatch MUST be set as less than or equal to the smallest match generated by the match finder. It has a minimum value of ZSTD_MINMATCH_MIN. + * - ZSTD_c_compressionLevel accordingly adjusts the strength of the entropy coder, as it would in typical compression. + * - ZSTD_c_windowLog affects offset validation: this function will return an error at higher debug levels if a provided offset + * is larger than what the spec allows for a given window log and dictionary (if present). See: doc/zstd_compression_format.md + * + * Note: Repcodes are, as of now, always re-calculated within this function, so ZSTD_Sequence::rep is unused. + * Note 2: Once we integrate ability to ingest repcodes, the explicit block delims mode must respect those repcodes exactly, + * and cannot emit an RLE block that disagrees with the repcode history + * @return : final compressed size or a ZSTD error. */ -size_t ZSTD_CCtxWorkspaceBound(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstSize, + const ZSTD_Sequence* inSeqs, size_t inSeqsSize, + const void* src, size_t srcSize); -/** - * struct ZSTD_CCtx - the zstd compression context + +/*! ZSTD_writeSkippableFrame() : + * Generates a zstd skippable frame containing data given by src, and writes it to dst buffer. * - * When compressing many times it is recommended to allocate a context just once - * and reuse it for each successive compression operation. - */ -typedef struct ZSTD_CCtx_s ZSTD_CCtx; -/** - * ZSTD_initCCtx() - initialize a zstd compression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_CCtxWorkspaceBound() to - * determine how large the workspace must be. + * Skippable frames begin with a a 4-byte magic number. There are 16 possible choices of magic number, + * ranging from ZSTD_MAGIC_SKIPPABLE_START to ZSTD_MAGIC_SKIPPABLE_START+15. + * As such, the parameter magicVariant controls the exact skippable frame magic number variant used, so + * the magic number used will be ZSTD_MAGIC_SKIPPABLE_START + magicVariant. * - * Return: A compression context emplaced into workspace. - */ -ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_compressCCtx() - compress src into dst - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @params: The parameters to use for compression. See ZSTD_getParams(). + * Returns an error if destination buffer is not large enough, if the source size is not representable + * with a 4-byte unsigned int, or if the parameter magicVariant is greater than 15 (and therefore invalid). * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). + * @return : number of bytes written or a ZSTD error. */ -size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, ZSTD_parameters params); - -/** - * ZSTD_DCtxWorkspaceBound() - amount of memory needed to initialize a ZSTD_DCtx - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDCtx(). +ZSTDLIB_API size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity, + const void* src, size_t srcSize, unsigned magicVariant); + + +/* ************************************* +* Memory management +***************************************/ + +/*! ZSTD_estimate*() : + * These functions make it possible to estimate memory usage + * of a future {D,C}Ctx, before its creation. + * + * ZSTD_estimateCCtxSize() will provide a memory budget large enough + * for any compression level up to selected one. + * Note : Unlike ZSTD_estimateCStreamSize*(), this estimate + * does not include space for a window buffer. + * Therefore, the estimation is only guaranteed for single-shot compressions, not streaming. + * The estimate will assume the input may be arbitrarily large, + * which is the worst case. + * + * When srcSize can be bound by a known and rather "small" value, + * this fact can be used to provide a tighter estimation + * because the CCtx compression context will need less memory. + * This tighter estimation can be provided by more advanced functions + * ZSTD_estimateCCtxSize_usingCParams(), which can be used in tandem with ZSTD_getCParams(), + * and ZSTD_estimateCCtxSize_usingCCtxParams(), which can be used in tandem with ZSTD_CCtxParams_setParameter(). + * Both can be used to estimate memory using custom compression parameters and arbitrary srcSize limits. + * + * Note 2 : only single-threaded compression is supported. + * ZSTD_estimateCCtxSize_usingCCtxParams() will return an error code if ZSTD_c_nbWorkers is >= 1. + */ +ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel); +ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params); +ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void); + +/*! ZSTD_estimateCStreamSize() : + * ZSTD_estimateCStreamSize() will provide a budget large enough for any compression level up to selected one. + * It will also consider src size to be arbitrarily "large", which is worst case. + * If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation. + * ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel. + * ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1. + * Note : CStream size estimation is only correct for single-threaded compression. + * ZSTD_DStream memory budget depends on window Size. + * This information can be passed manually, using ZSTD_estimateDStreamSize, + * or deducted from a valid frame Header, using ZSTD_estimateDStreamSize_fromFrame(); + * Note : if streaming is init with function ZSTD_init?Stream_usingDict(), + * an internal ?Dict will be created, which additional size is not estimated here. + * In this case, get total size by adding ZSTD_estimate?DictSize */ +ZSTDLIB_API size_t ZSTD_estimateCStreamSize(int compressionLevel); +ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params); +ZSTDLIB_API size_t ZSTD_estimateDStreamSize(size_t windowSize); +ZSTDLIB_API size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize); + +/*! ZSTD_estimate?DictSize() : + * ZSTD_estimateCDictSize() will bet that src size is relatively "small", and content is copied, like ZSTD_createCDict(). + * ZSTD_estimateCDictSize_advanced() makes it possible to control compression parameters precisely, like ZSTD_createCDict_advanced(). + * Note : dictionaries created by reference (`ZSTD_dlm_byRef`) are logically smaller. + */ +ZSTDLIB_API size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel); +ZSTDLIB_API size_t ZSTD_estimateCDictSize_advanced(size_t dictSize, ZSTD_compressionParameters cParams, ZSTD_dictLoadMethod_e dictLoadMethod); +ZSTDLIB_API size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod); + +/*! ZSTD_initStatic*() : + * Initialize an object using a pre-allocated fixed-size buffer. + * workspace: The memory area to emplace the object into. + * Provided pointer *must be 8-bytes aligned*. + * Buffer must outlive object. + * workspaceSize: Use ZSTD_estimate*Size() to determine + * how large workspace must be to support target scenario. + * @return : pointer to object (same address as workspace, just different type), + * or NULL if error (size too small, incorrect alignment, etc.) + * Note : zstd will never resize nor malloc() when using a static buffer. + * If the object requires more memory than available, + * zstd will just error out (typically ZSTD_error_memory_allocation). + * Note 2 : there is no corresponding "free" function. + * Since workspace is allocated externally, it must be freed externally too. + * Note 3 : cParams : use ZSTD_getCParams() to convert a compression level + * into its associated cParams. + * Limitation 1 : currently not compatible with internal dictionary creation, triggered by + * ZSTD_CCtx_loadDictionary(), ZSTD_initCStream_usingDict() or ZSTD_initDStream_usingDict(). + * Limitation 2 : static cctx currently not compatible with multi-threading. + * Limitation 3 : static dctx is incompatible with legacy support. */ -size_t ZSTD_DCtxWorkspaceBound(void); +ZSTDLIB_API ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize); +ZSTDLIB_API ZSTD_CStream* ZSTD_initStaticCStream(void* workspace, size_t workspaceSize); /*< same as ZSTD_initStaticCCtx() */ + +ZSTDLIB_API ZSTD_DCtx* ZSTD_initStaticDCtx(void* workspace, size_t workspaceSize); +ZSTDLIB_API ZSTD_DStream* ZSTD_initStaticDStream(void* workspace, size_t workspaceSize); /*< same as ZSTD_initStaticDCtx() */ + +ZSTDLIB_API const ZSTD_CDict* ZSTD_initStaticCDict( + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams); + +ZSTDLIB_API const ZSTD_DDict* ZSTD_initStaticDDict( + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType); + + +/*! Custom memory allocation : + * These prototypes make it possible to pass your own allocation/free functions. + * ZSTD_customMem is provided at creation time, using ZSTD_create*_advanced() variants listed below. + * All allocation/free operations will be completed using these custom variants instead of regular ones. + */ +typedef void* (*ZSTD_allocFunction) (void* opaque, size_t size); +typedef void (*ZSTD_freeFunction) (void* opaque, void* address); +typedef struct { ZSTD_allocFunction customAlloc; ZSTD_freeFunction customFree; void* opaque; } ZSTD_customMem; +static +__attribute__((__unused__)) +ZSTD_customMem const ZSTD_defaultCMem = { NULL, NULL, NULL }; /*< this constant defers to stdlib's functions */ + +ZSTDLIB_API ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem); +ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); +ZSTDLIB_API ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem); +ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); + +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams, + ZSTD_customMem customMem); + +/* ! Thread pool : + * These prototypes make it possible to share a thread pool among multiple compression contexts. + * This can limit resources for applications with multiple threads where each one uses + * a threaded compression mode (via ZSTD_c_nbWorkers parameter). + * ZSTD_createThreadPool creates a new thread pool with a given number of threads. + * Note that the lifetime of such pool must exist while being used. + * ZSTD_CCtx_refThreadPool assigns a thread pool to a context (use NULL argument value + * to use an internal thread pool). + * ZSTD_freeThreadPool frees a thread pool, accepts NULL pointer. + */ +typedef struct POOL_ctx_s ZSTD_threadPool; +ZSTDLIB_API ZSTD_threadPool* ZSTD_createThreadPool(size_t numThreads); +ZSTDLIB_API void ZSTD_freeThreadPool (ZSTD_threadPool* pool); /* accept NULL pointer */ +ZSTDLIB_API size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool); -/** - * struct ZSTD_DCtx - the zstd decompression context - * - * When decompressing many times it is recommended to allocate a context just - * once and reuse it for each successive decompression operation. + +/* + * This API is temporary and is expected to change or disappear in the future! */ -typedef struct ZSTD_DCtx_s ZSTD_DCtx; -/** - * ZSTD_initDCtx() - initialize a zstd decompression context - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Use ZSTD_DCtxWorkspaceBound() to - * determine how large the workspace must be. - * - * Return: A decompression context emplaced into workspace. - */ -ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize); - -/** - * ZSTD_decompressDCtx() - decompress zstd compressed src into dst - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompressDCtx(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - -/*-************************ - * Simple dictionary API - **************************/ - -/** - * ZSTD_compress_usingDict() - compress src into dst using a dictionary - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(params.cParams). - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @dict: The dictionary to use for compression. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * - * Compression using a predefined dictionary. The same dictionary must be used - * during decompression. - * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize, - ZSTD_parameters params); - -/** - * ZSTD_decompress_usingDict() - decompress src into dst using a dictionary - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @dict: The dictionary to use for decompression. The same dictionary - * must've been used to compress the data. - * @dictSize: The size of the dictionary. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompress_usingDict(ZSTD_DCtx *ctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const void *dict, size_t dictSize); - -/*-************************** - * Fast dictionary API - ***************************/ - -/** - * ZSTD_CDictWorkspaceBound() - memory needed to initialize a ZSTD_CDict - * @cParams: The compression parameters to be used for compression. - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCDict(). - */ -size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams); - -/** - * struct ZSTD_CDict - a digested dictionary to be used for compression +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced2( + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + const ZSTD_CCtx_params* cctxParams, + ZSTD_customMem customMem); + +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced( + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_customMem customMem); + + +/* ************************************* +* Advanced compression functions +***************************************/ + +/*! ZSTD_createCDict_byReference() : + * Create a digested dictionary for compression + * Dictionary content is just referenced, not duplicated. + * As a consequence, `dictBuffer` **must** outlive CDict, + * and its content must remain unmodified throughout the lifetime of CDict. + * note: equivalent to ZSTD_createCDict_advanced(), with dictLoadMethod==ZSTD_dlm_byRef */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel); + +/*! ZSTD_getDictID_fromCDict() : + * Provides the dictID of the dictionary loaded into `cdict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +ZSTDLIB_API unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict); + +/*! ZSTD_getCParams() : + * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize. + * `estimatedSrcSize` value is optional, select 0 if not known */ +ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); + +/*! ZSTD_getParams() : + * same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`. + * All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */ +ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize); + +/*! ZSTD_checkCParams() : + * Ensure param values remain within authorized range. + * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */ +ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params); + +/*! ZSTD_adjustCParams() : + * optimize params for a given `srcSize` and `dictSize`. + * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN. + * `dictSize` must be `0` when there is no dictionary. + * cPar can be invalid : all parameters will be clamped within valid range in the @return struct. + * This function never fails (wide contract) */ +ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize); + +/*! ZSTD_compress_advanced() : + * Note : this function is now DEPRECATED. + * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_setParameter() and other parameter setters. + * This prototype will be marked as deprecated and generate compilation warning on reaching v1.5.x */ +ZSTDLIB_API size_t ZSTD_compress_advanced(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + ZSTD_parameters params); + +/*! ZSTD_compress_usingCDict_advanced() : + * Note : this function is now REDUNDANT. + * It can be replaced by ZSTD_compress2(), in combination with ZSTD_CCtx_loadDictionary() and other parameter setters. + * This prototype will be marked as deprecated and generate compilation warning in some future version */ +ZSTDLIB_API size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams); + + +/*! ZSTD_CCtx_loadDictionary_byReference() : + * Same as ZSTD_CCtx_loadDictionary(), but dictionary content is referenced, instead of being copied into CCtx. + * It saves some memory, but also requires that `dict` outlives its usage within `cctx` */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference(ZSTD_CCtx* cctx, const void* dict, size_t dictSize); + +/*! ZSTD_CCtx_loadDictionary_advanced() : + * Same as ZSTD_CCtx_loadDictionary(), but gives finer control over + * how to load the dictionary (by copy ? by reference ?) + * and how to interpret it (automatic ? force raw mode ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_CCtx_refPrefix_advanced() : + * Same as ZSTD_CCtx_refPrefix(), but gives finer control over + * how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType); + +/* === experimental parameters === */ +/* these parameters can be used with ZSTD_setParameter() + * they are not guaranteed to remain supported in the future */ + + /* Enables rsyncable mode, + * which makes compressed files more rsync friendly + * by adding periodic synchronization points to the compressed data. + * The target average block size is ZSTD_c_jobSize / 2. + * It's possible to modify the job size to increase or decrease + * the granularity of the synchronization point. + * Once the jobSize is smaller than the window size, + * it will result in compression ratio degradation. + * NOTE 1: rsyncable mode only works when multithreading is enabled. + * NOTE 2: rsyncable performs poorly in combination with long range mode, + * since it will decrease the effectiveness of synchronization points, + * though mileage may vary. + * NOTE 3: Rsyncable mode limits maximum compression speed to ~400 MB/s. + * If the selected compression level is already running significantly slower, + * the overall speed won't be significantly impacted. + */ + #define ZSTD_c_rsyncable ZSTD_c_experimentalParam1 + +/* Select a compression format. + * The value must be of type ZSTD_format_e. + * See ZSTD_format_e enum definition for details */ +#define ZSTD_c_format ZSTD_c_experimentalParam2 + +/* Force back-reference distances to remain < windowSize, + * even when referencing into Dictionary content (default:0) */ +#define ZSTD_c_forceMaxWindow ZSTD_c_experimentalParam3 + +/* Controls whether the contents of a CDict + * are used in place, or copied into the working context. + * Accepts values from the ZSTD_dictAttachPref_e enum. + * See the comments on that enum for an explanation of the feature. */ +#define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4 + +/* Controls how the literals are compressed (default is auto). + * The value must be of type ZSTD_literalCompressionMode_e. + * See ZSTD_literalCompressionMode_t enum definition for details. */ -typedef struct ZSTD_CDict_s ZSTD_CDict; +#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5 + +/* Tries to fit compressed block size to be around targetCBlockSize. + * No target when targetCBlockSize == 0. + * There is no guarantee on compressed block size (default:0) */ +#define ZSTD_c_targetCBlockSize ZSTD_c_experimentalParam6 + +/* User's best guess of source size. + * Hint is not valid when srcSizeHint == 0. + * There is no guarantee that hint is close to actual source size, + * but compression ratio may regress significantly if guess considerably underestimates */ +#define ZSTD_c_srcSizeHint ZSTD_c_experimentalParam7 + +/* Controls whether the new and experimental "dedicated dictionary search + * structure" can be used. This feature is still rough around the edges, be + * prepared for surprising behavior! + * + * How to use it: + * + * When using a CDict, whether to use this feature or not is controlled at + * CDict creation, and it must be set in a CCtxParams set passed into that + * construction (via ZSTD_createCDict_advanced2()). A compression will then + * use the feature or not based on how the CDict was constructed; the value of + * this param, set in the CCtx, will have no effect. + * + * However, when a dictionary buffer is passed into a CCtx, such as via + * ZSTD_CCtx_loadDictionary(), this param can be set on the CCtx to control + * whether the CDict that is created internally can use the feature or not. + * + * What it does: + * + * Normally, the internal data structures of the CDict are analogous to what + * would be stored in a CCtx after compressing the contents of a dictionary. + * To an approximation, a compression using a dictionary can then use those + * data structures to simply continue what is effectively a streaming + * compression where the simulated compression of the dictionary left off. + * Which is to say, the search structures in the CDict are normally the same + * format as in the CCtx. + * + * It is possible to do better, since the CDict is not like a CCtx: the search + * structures are written once during CDict creation, and then are only read + * after that, while the search structures in the CCtx are both read and + * written as the compression goes along. This means we can choose a search + * structure for the dictionary that is read-optimized. + * + * This feature enables the use of that different structure. + * + * Note that some of the members of the ZSTD_compressionParameters struct have + * different semantics and constraints in the dedicated search structure. It is + * highly recommended that you simply set a compression level in the CCtxParams + * you pass into the CDict creation call, and avoid messing with the cParams + * directly. + * + * Effects: + * + * This will only have any effect when the selected ZSTD_strategy + * implementation supports this feature. Currently, that's limited to + * ZSTD_greedy, ZSTD_lazy, and ZSTD_lazy2. + * + * Note that this means that the CDict tables can no longer be copied into the + * CCtx, so the dict attachment mode ZSTD_dictForceCopy will no longer be + * useable. The dictionary can only be attached or reloaded. + * + * In general, you should expect compression to be faster--sometimes very much + * so--and CDict creation to be slightly slower. Eventually, we will probably + * make this mode the default. + */ +#define ZSTD_c_enableDedicatedDictSearch ZSTD_c_experimentalParam8 + +/* ZSTD_c_stableInBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. + * + * Tells the compressor that the ZSTD_inBuffer will ALWAYS be the same + * between calls, except for the modifications that zstd makes to pos (the + * caller must not modify pos). This is checked by the compressor, and + * compression will fail if it ever changes. This means the only flush + * mode that makes sense is ZSTD_e_end, so zstd will error if ZSTD_e_end + * is not used. The data in the ZSTD_inBuffer in the range [src, src + pos) + * MUST not be modified during compression or you will get data corruption. + * + * When this flag is enabled zstd won't allocate an input window buffer, + * because the user guarantees it can reference the ZSTD_inBuffer until + * the frame is complete. But, it will still allocate an output buffer + * large enough to fit a block (see ZSTD_c_stableOutBuffer). This will also + * avoid the memcpy() from the input buffer to the input window buffer. + * + * NOTE: ZSTD_compressStream2() will error if ZSTD_e_end is not used. + * That means this flag cannot be used with ZSTD_compressStream(). + * + * NOTE: So long as the ZSTD_inBuffer always points to valid memory, using + * this flag is ALWAYS memory safe, and will never access out-of-bounds + * memory. However, compression WILL fail if you violate the preconditions. + * + * WARNING: The data in the ZSTD_inBuffer in the range [dst, dst + pos) MUST + * not be modified during compression or you will get data corruption. This + * is because zstd needs to reference data in the ZSTD_inBuffer to find + * matches. Normally zstd maintains its own window buffer for this purpose, + * but passing this flag tells zstd to use the user provided buffer. + */ +#define ZSTD_c_stableInBuffer ZSTD_c_experimentalParam9 -/** - * ZSTD_initCDict() - initialize a digested dictionary for compression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_CDict so it must outlive the returned ZSTD_CDict. - * @dictSize: The size of the dictionary. - * @params: The parameters to use for compression. See ZSTD_getParams(). - * @workspace: The workspace. It must outlive the returned ZSTD_CDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_CDictWorkspaceBound(params.cParams). +/* ZSTD_c_stableOutBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. * - * When compressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_CDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_CDict. + * Tells he compressor that the ZSTD_outBuffer will not be resized between + * calls. Specifically: (out.size - out.pos) will never grow. This gives the + * compressor the freedom to say: If the compressed data doesn't fit in the + * output buffer then return ZSTD_error_dstSizeTooSmall. This allows us to + * always decompress directly into the output buffer, instead of decompressing + * into an internal buffer and copying to the output buffer. * - * Return: The digested dictionary emplaced into workspace. + * When this flag is enabled zstd won't allocate an output buffer, because + * it can write directly to the ZSTD_outBuffer. It will still allocate the + * input window buffer (see ZSTD_c_stableInBuffer). + * + * Zstd will check that (out.size - out.pos) never grows and return an error + * if it does. While not strictly necessary, this should prevent surprises. */ -ZSTD_CDict *ZSTD_initCDict(const void *dictBuffer, size_t dictSize, - ZSTD_parameters params, void *workspace, size_t workspaceSize); +#define ZSTD_c_stableOutBuffer ZSTD_c_experimentalParam10 -/** - * ZSTD_compress_usingCDict() - compress src into dst using a ZSTD_CDict - * @ctx: The context. Must have been initialized with a workspace at - * least as large as ZSTD_CCtxWorkspaceBound(cParams) where - * cParams are the compression parameters used to initialize the - * cdict. - * @dst: The buffer to compress src into. - * @dstCapacity: The size of the destination buffer. May be any size, but - * ZSTD_compressBound(srcSize) is guaranteed to be large enough. - * @src: The data to compress. - * @srcSize: The size of the data to compress. - * @cdict: The digested dictionary to use for compression. - * @params: The parameters to use for compression. See ZSTD_getParams(). +/* ZSTD_c_blockDelimiters + * Default is 0 == ZSTD_sf_noBlockDelimiters. * - * Compression using a digested dictionary. The same dictionary must be used - * during decompression. + * For use with sequence compression API: ZSTD_compressSequences(). * - * Return: The compressed size or an error, which can be checked using - * ZSTD_isError(). + * Designates whether or not the given array of ZSTD_Sequence contains block delimiters + * and last literals, which are defined as sequences with offset == 0 and matchLength == 0. + * See the definition of ZSTD_Sequence for more specifics. */ -size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize, const ZSTD_CDict *cdict); - +#define ZSTD_c_blockDelimiters ZSTD_c_experimentalParam11 -/** - * ZSTD_DDictWorkspaceBound() - memory needed to initialize a ZSTD_DDict +/* ZSTD_c_validateSequences + * Default is 0 == disabled. Set to 1 to enable sequence validation. + * + * For use with sequence compression API: ZSTD_compressSequences(). + * Designates whether or not we validate sequences provided to ZSTD_compressSequences() + * during function execution. + * + * Without validation, providing a sequence that does not conform to the zstd spec will cause + * undefined behavior, and may produce a corrupted block. + * + * With validation enabled, a if sequence is invalid (see doc/zstd_compression_format.md for + * specifics regarding offset/matchlength requirements) then the function will bail out and + * return an error. * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDDict(). */ -size_t ZSTD_DDictWorkspaceBound(void); +#define ZSTD_c_validateSequences ZSTD_c_experimentalParam12 -/** - * struct ZSTD_DDict - a digested dictionary to be used for decompression +/*! ZSTD_CCtx_getParameter() : + * Get the requested compression parameter value, selected by enum ZSTD_cParameter, + * and store it into int* value. + * @return : 0, or an error code (which can be tested with ZSTD_isError()). */ -typedef struct ZSTD_DDict_s ZSTD_DDict; - -/** - * ZSTD_initDDict() - initialize a digested dictionary for decompression - * @dictBuffer: The dictionary to digest. The buffer is referenced by the - * ZSTD_DDict so it must outlive the returned ZSTD_DDict. - * @dictSize: The size of the dictionary. - * @workspace: The workspace. It must outlive the returned ZSTD_DDict. - * @workspaceSize: The workspace size. Must be at least - * ZSTD_DDictWorkspaceBound(). - * - * When decompressing multiple messages / blocks with the same dictionary it is - * recommended to load it just once. The ZSTD_DDict merely references the - * dictBuffer, so it must outlive the returned ZSTD_DDict. - * - * Return: The digested dictionary emplaced into workspace. - */ -ZSTD_DDict *ZSTD_initDDict(const void *dictBuffer, size_t dictSize, - void *workspace, size_t workspaceSize); - -/** - * ZSTD_decompress_usingDDict() - decompress src into dst using a ZSTD_DDict - * @ctx: The decompression context. - * @dst: The buffer to decompress src into. - * @dstCapacity: The size of the destination buffer. Must be at least as large - * as the decompressed size. If the caller cannot upper bound the - * decompressed size, then it's better to use the streaming API. - * @src: The zstd compressed data to decompress. Multiple concatenated - * frames and skippable frames are allowed. - * @srcSize: The exact size of the data to decompress. - * @ddict: The digested dictionary to use for decompression. The same - * dictionary must've been used to compress the data. - * - * Return: The decompressed size or an error, which can be checked using - * ZSTD_isError(). - */ -size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, - size_t dstCapacity, const void *src, size_t srcSize, - const ZSTD_DDict *ddict); - - -/*-************************** - * Streaming - ***************************/ - -/** - * struct ZSTD_inBuffer - input buffer for streaming - * @src: Start of the input buffer. - * @size: Size of the input buffer. - * @pos: Position where reading stopped. Will be updated. - * Necessarily 0 <= pos <= size. +ZSTDLIB_API size_t ZSTD_CCtx_getParameter(const ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value); + + +/*! ZSTD_CCtx_params : + * Quick howto : + * - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure + * - ZSTD_CCtxParams_setParameter() : Push parameters one by one into + * an existing ZSTD_CCtx_params structure. + * This is similar to + * ZSTD_CCtx_setParameter(). + * - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to + * an existing CCtx. + * These parameters will be applied to + * all subsequent frames. + * - ZSTD_compressStream2() : Do compression using the CCtx. + * - ZSTD_freeCCtxParams() : Free the memory, accept NULL pointer. + * + * This can be used with ZSTD_estimateCCtxSize_advanced_usingCCtxParams() + * for static allocation of CCtx for single-threaded compression. */ -typedef struct ZSTD_inBuffer_s { - const void *src; - size_t size; - size_t pos; -} ZSTD_inBuffer; +ZSTDLIB_API ZSTD_CCtx_params* ZSTD_createCCtxParams(void); +ZSTDLIB_API size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params); /* accept NULL pointer */ -/** - * struct ZSTD_outBuffer - output buffer for streaming - * @dst: Start of the output buffer. - * @size: Size of the output buffer. - * @pos: Position where writing stopped. Will be updated. - * Necessarily 0 <= pos <= size. +/*! ZSTD_CCtxParams_reset() : + * Reset params to default values. */ -typedef struct ZSTD_outBuffer_s { - void *dst; - size_t size; - size_t pos; -} ZSTD_outBuffer; - - +ZSTDLIB_API size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params); -/*-***************************************************************************** - * Streaming compression - HowTo - * - * A ZSTD_CStream object is required to track streaming operation. - * Use ZSTD_initCStream() to initialize a ZSTD_CStream object. - * ZSTD_CStream objects can be reused multiple times on consecutive compression - * operations. It is recommended to re-use ZSTD_CStream in situations where many - * streaming operations will be achieved consecutively. Use one separate - * ZSTD_CStream per thread for parallel execution. - * - * Use ZSTD_compressStream() repetitively to consume input stream. - * The function will automatically update both `pos` fields. - * Note that it may not consume the entire input, in which case `pos < size`, - * and it's up to the caller to present again remaining data. - * It returns a hint for the preferred number of bytes to use as an input for - * the next function call. - * - * At any moment, it's possible to flush whatever data remains within internal - * buffer, using ZSTD_flushStream(). `output->pos` will be updated. There might - * still be some content left within the internal buffer if `output->size` is - * too small. It returns the number of bytes left in the internal buffer and - * must be called until it returns 0. - * - * ZSTD_endStream() instructs to finish a frame. It will perform a flush and - * write frame epilogue. The epilogue is required for decoders to consider a - * frame completed. Similar to ZSTD_flushStream(), it may not be able to flush - * the full content if `output->size` is too small. In which case, call again - * ZSTD_endStream() to complete the flush. It returns the number of bytes left - * in the internal buffer and must be called until it returns 0. - ******************************************************************************/ +/*! ZSTD_CCtxParams_init() : + * Initializes the compression parameters of cctxParams according to + * compression level. All other parameters are reset to their default values. + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel); -/** - * ZSTD_CStreamWorkspaceBound() - memory needed to initialize a ZSTD_CStream - * @cParams: The compression parameters to be used for compression. - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initCStream() and ZSTD_initCStream_usingCDict(). +/*! ZSTD_CCtxParams_init_advanced() : + * Initializes the compression and frame parameters of cctxParams according to + * params. All other parameters are reset to their default values. */ -size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams); +ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params); + +/*! ZSTD_CCtxParams_setParameter() : + * Similar to ZSTD_CCtx_setParameter. + * Set one compression parameter, selected by enum ZSTD_cParameter. + * Parameters must be applied to a ZSTD_CCtx using + * ZSTD_CCtx_setParametersUsingCCtxParams(). + * @result : a code representing success or failure (which can be tested with + * ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value); -/** - * struct ZSTD_CStream - the zstd streaming compression context +/*! ZSTD_CCtxParams_getParameter() : + * Similar to ZSTD_CCtx_getParameter. + * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter. + * @result : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(const ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value); + +/*! ZSTD_CCtx_setParametersUsingCCtxParams() : + * Apply a set of ZSTD_CCtx_params to the compression context. + * This can be done even after compression is started, + * if nbWorkers==0, this will have no impact until a new compression is started. + * if nbWorkers>=1, new parameters will be picked up at next job, + * with a few restrictions (windowLog, pledgedSrcSize, nbWorkers, jobSize, and overlapLog are not updated). + */ +ZSTDLIB_API size_t ZSTD_CCtx_setParametersUsingCCtxParams( + ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params); + +/*! ZSTD_compressStream2_simpleArgs() : + * Same as ZSTD_compressStream2(), + * but using only integral types as arguments. + * This variant might be helpful for binders from dynamic languages + * which have troubles handling structures containing memory pointers. */ -typedef struct ZSTD_CStream_s ZSTD_CStream; +ZSTDLIB_API size_t ZSTD_compressStream2_simpleArgs ( + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos, + ZSTD_EndDirective endOp); + + +/* ************************************* +* Advanced decompression functions +***************************************/ + +/*! ZSTD_isFrame() : + * Tells if the content of `buffer` starts with a valid Frame Identifier. + * Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0. + * Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled. + * Note 3 : Skippable Frame Identifiers are considered valid. */ +ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size); + +/*! ZSTD_createDDict_byReference() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * Dictionary content is referenced, and therefore stays in dictBuffer. + * It is important that dictBuffer outlives DDict, + * it must remain read accessible throughout the lifetime of DDict */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); + +/*! ZSTD_DCtx_loadDictionary_byReference() : + * Same as ZSTD_DCtx_loadDictionary(), + * but references `dict` content instead of copying it into `dctx`. + * This saves memory if `dict` remains around., + * However, it's imperative that `dict` remains accessible (and unmodified) while being used, so it must outlive decompression. */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); + +/*! ZSTD_DCtx_loadDictionary_advanced() : + * Same as ZSTD_DCtx_loadDictionary(), + * but gives direct control over + * how to load the dictionary (by copy ? by reference ?) + * and how to interpret it (automatic ? force raw mode ? full mode only ?). */ +ZSTDLIB_API size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, const void* dict, size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_DCtx_refPrefix_advanced() : + * Same as ZSTD_DCtx_refPrefix(), but gives finer control over + * how to interpret prefix content (automatic ? force raw mode (default) ? full mode only ?) */ +ZSTDLIB_API size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType); + +/*! ZSTD_DCtx_setMaxWindowSize() : + * Refuses allocating internal buffers for frames requiring a window size larger than provided limit. + * This protects a decoder context from reserving too much memory for itself (potential attack scenario). + * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode. + * By default, a decompression context accepts all window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) + * @return : 0, or an error code (which can be tested using ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize); -/*===== ZSTD_CStream management functions =====*/ -/** - * ZSTD_initCStream() - initialize a zstd streaming compression context - * @params: The zstd compression parameters. - * @pledgedSrcSize: If params.fParams.contentSizeFlag == 1 then the caller must - * pass the source size (zero means empty source). Otherwise, - * the caller may optionally pass the source size, or zero if - * unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_CStreamWorkspaceBound(params.cParams) to determine - * how large the workspace must be. - * - * Return: The zstd streaming compression context. - */ -ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); - -/** - * ZSTD_initCStream_usingCDict() - initialize a streaming compression context - * @cdict: The digested dictionary to use for compression. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. Call ZSTD_CStreamWorkspaceBound() - * with the cParams used to initialize the cdict to determine - * how large the workspace must be. - * - * Return: The zstd streaming compression context. - */ -ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize, void *workspace, - size_t workspaceSize); +/*! ZSTD_DCtx_getParameter() : + * Get the requested decompression parameter value, selected by enum ZSTD_dParameter, + * and store it into int* value. + * @return : 0, or an error code (which can be tested with ZSTD_isError()). + */ +ZSTDLIB_API size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int* value); -/*===== Streaming compression functions =====*/ -/** - * ZSTD_resetCStream() - reset the context using parameters from creation - * @zcs: The zstd streaming compression context to reset. - * @pledgedSrcSize: Optionally the source size, or zero if unknown. - * - * Resets the context using the parameters from creation. Skips dictionary - * loading, since it can be reused. If `pledgedSrcSize` is non-zero the frame - * content size is always written into the frame header. - * - * Return: Zero or an error, which can be checked using ZSTD_isError(). +/* ZSTD_d_format + * experimental parameter, + * allowing selection between ZSTD_format_e input compression formats */ -size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize); -/** - * ZSTD_compressStream() - streaming compress some of input into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * @input: Source buffer. `input->pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input->pos < input->size`, and it's up to the caller to present - * remaining data again. - * - * The `input` and `output` buffers may be any size. Guaranteed to make some - * forward progress if `input` and `output` are not empty. - * - * Return: A hint for the number of bytes to use as the input for the next - * function call or an error, which can be checked using - * ZSTD_isError(). +#define ZSTD_d_format ZSTD_d_experimentalParam1 +/* ZSTD_d_stableOutBuffer + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable. + * + * Tells the decompressor that the ZSTD_outBuffer will ALWAYS be the same + * between calls, except for the modifications that zstd makes to pos (the + * caller must not modify pos). This is checked by the decompressor, and + * decompression will fail if it ever changes. Therefore the ZSTD_outBuffer + * MUST be large enough to fit the entire decompressed frame. This will be + * checked when the frame content size is known. The data in the ZSTD_outBuffer + * in the range [dst, dst + pos) MUST not be modified during decompression + * or you will get data corruption. + * + * When this flags is enabled zstd won't allocate an output buffer, because + * it can write directly to the ZSTD_outBuffer, but it will still allocate + * an input buffer large enough to fit any compressed block. This will also + * avoid the memcpy() from the internal output buffer to the ZSTD_outBuffer. + * If you need to avoid the input buffer allocation use the buffer-less + * streaming API. + * + * NOTE: So long as the ZSTD_outBuffer always points to valid memory, using + * this flag is ALWAYS memory safe, and will never access out-of-bounds + * memory. However, decompression WILL fail if you violate the preconditions. + * + * WARNING: The data in the ZSTD_outBuffer in the range [dst, dst + pos) MUST + * not be modified during decompression or you will get data corruption. This + * is because zstd needs to reference data in the ZSTD_outBuffer to regenerate + * matches. Normally zstd maintains its own buffer for this purpose, but passing + * this flag tells zstd to use the user provided buffer. */ -size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); -/** - * ZSTD_flushStream() - flush internal buffers into output - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. - * - * ZSTD_flushStream() must be called until it returns 0, meaning all the data - * has been flushed. Since ZSTD_flushStream() causes a block to be ended, - * calling it too often will degrade the compression ratio. +#define ZSTD_d_stableOutBuffer ZSTD_d_experimentalParam2 + +/* ZSTD_d_forceIgnoreChecksum + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). + * Tells the decompressor to skip checksum validation during decompression, regardless + * of whether checksumming was specified during compression. This offers some + * slight performance benefits, and may be useful for debugging. + * Param has values of type ZSTD_forceIgnoreChecksum_e */ -size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); -/** - * ZSTD_endStream() - flush internal buffers into output and end the frame - * @zcs: The zstd streaming compression context. - * @output: Destination buffer. `output->pos` is updated to indicate how much - * compressed data was written. +#define ZSTD_d_forceIgnoreChecksum ZSTD_d_experimentalParam3 + +/* ZSTD_d_refMultipleDDicts + * Experimental parameter. + * Default is 0 == disabled. Set to 1 to enable * - * ZSTD_endStream() must be called until it returns 0, meaning all the data has - * been flushed and the frame epilogue has been written. + * If enabled and dctx is allocated on the heap, then additional memory will be allocated + * to store references to multiple ZSTD_DDict. That is, multiple calls of ZSTD_refDDict() + * using a given ZSTD_DCtx, rather than overwriting the previous DDict reference, will instead + * store all references. At decompression time, the appropriate dictID is selected + * from the set of DDicts based on the dictID in the frame. * - * Return: The number of bytes still present within internal buffers or an - * error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output); - -/** - * ZSTD_CStreamInSize() - recommended size for the input buffer + * Usage is simply calling ZSTD_refDDict() on multiple dict buffers. * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_CStreamInSize(void); -/** - * ZSTD_CStreamOutSize() - recommended size for the output buffer + * Param has values of byte ZSTD_refMultipleDDicts_e * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete compressed block. + * WARNING: Enabling this parameter and calling ZSTD_DCtx_refDDict(), will trigger memory + * allocation for the hash table. ZSTD_freeDCtx() also frees this memory. + * Memory is allocated as per ZSTD_DCtx::customMem. * - * Return: The recommended size for the output buffer. + * Although this function allocates memory for the table, the user is still responsible for + * memory management of the underlying ZSTD_DDict* themselves. */ -size_t ZSTD_CStreamOutSize(void); - +#define ZSTD_d_refMultipleDDicts ZSTD_d_experimentalParam4 -/*-***************************************************************************** - * Streaming decompression - HowTo - * - * A ZSTD_DStream object is required to track streaming operations. - * Use ZSTD_initDStream() to initialize a ZSTD_DStream object. - * ZSTD_DStream objects can be re-used multiple times. - * - * Use ZSTD_decompressStream() repetitively to consume your input. - * The function will update both `pos` fields. - * If `input->pos < input->size`, some input has not been consumed. - * It's up to the caller to present again remaining data. - * If `output->pos < output->size`, decoder has flushed everything it could. - * Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise it returns a suggested next input size that will never load more - * than the current frame. - ******************************************************************************/ +/*! ZSTD_DCtx_setFormat() : + * Instruct the decoder context about what kind of data to decode next. + * This instruction is mandatory to decode data without a fully-formed header, + * such ZSTD_f_zstd1_magicless for example. + * @return : 0, or an error code (which can be tested using ZSTD_isError()). */ +ZSTDLIB_API size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format); -/** - * ZSTD_DStreamWorkspaceBound() - memory needed to initialize a ZSTD_DStream - * @maxWindowSize: The maximum window size allowed for compressed frames. - * - * Return: A lower bound on the size of the workspace that is passed to - * ZSTD_initDStream() and ZSTD_initDStream_usingDDict(). +/*! ZSTD_decompressStream_simpleArgs() : + * Same as ZSTD_decompressStream(), + * but using only integral types as arguments. + * This can be helpful for binders from dynamic languages + * which have troubles handling structures containing memory pointers. */ -size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize); +ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs ( + ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos); + + +/* ****************************************************************** +* Advanced streaming functions +* Warning : most of these functions are now redundant with the Advanced API. +* Once Advanced API reaches "stable" status, +* redundant functions will be deprecated, and then at some point removed. +********************************************************************/ + +/*===== Advanced Streaming compression functions =====*/ + +/*! ZSTD_initCStream_srcSize() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any) + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * pledgedSrcSize must be correct. If it is not known at init time, use + * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, + * "0" also disables frame content size field. It may be enabled in the future. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, + int compressionLevel, + unsigned long long pledgedSrcSize); + +/*! ZSTD_initCStream_usingDict() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * Creates of an internal CDict (incompatible with static CCtx), except if + * dict == NULL or dictSize < 8, in which case no dict is used. + * Note: dict is loaded with ZSTD_dct_auto (treated as a full zstd dictionary if + * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + int compressionLevel); + +/*! ZSTD_initCStream_advanced() : + * This function is deprecated, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * // Pseudocode: Set each zstd parameter and leave the rest as-is. + * for ((param, value) : params) { + * ZSTD_CCtx_setParameter(zcs, param, value); + * } + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_loadDictionary(zcs, dict, dictSize); + * + * dict is loaded with ZSTD_dct_auto and ZSTD_dlm_byCopy. + * pledgedSrcSize must be correct. + * If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_advanced(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + ZSTD_parameters params, + unsigned long long pledgedSrcSize); + +/*! ZSTD_initCStream_usingCDict() : + * This function is deprecated, and equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * note : cdict will just be referenced, and must outlive compression session + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); + +/*! ZSTD_initCStream_usingCDict_advanced() : + * This function is DEPRECATED, and is approximately equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * // Pseudocode: Set each zstd frame parameter and leave the rest as-is. + * for ((fParam, value) : fParams) { + * ZSTD_CCtx_setParameter(zcs, fParam, value); + * } + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * ZSTD_CCtx_refCDict(zcs, cdict); + * + * same as ZSTD_initCStream_usingCDict(), with control over frame parameters. + * pledgedSrcSize must be correct. If srcSize is not known at init time, use + * value ZSTD_CONTENTSIZE_UNKNOWN. + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t +ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams, + unsigned long long pledgedSrcSize); + +/*! ZSTD_resetCStream() : + * This function is deprecated, and is equivalent to: + * ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + * ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize); + * + * start a new frame, using same parameters from previous frame. + * This is typically useful to skip dictionary loading stage, since it will re-use it in-place. + * Note that zcs must be init at least once before using ZSTD_resetCStream(). + * If pledgedSrcSize is not known at reset time, use macro ZSTD_CONTENTSIZE_UNKNOWN. + * If pledgedSrcSize > 0, its value must be correct, as it will be written in header, and controlled at the end. + * For the time being, pledgedSrcSize==0 is interpreted as "srcSize unknown" for compatibility with older programs, + * but it will change to mean "empty" in future version, so use macro ZSTD_CONTENTSIZE_UNKNOWN instead. + * @return : 0, or an error code (which can be tested using ZSTD_isError()) + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x + */ +ZSTDLIB_API size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize); -/** - * struct ZSTD_DStream - the zstd streaming decompression context + +typedef struct { + unsigned long long ingested; /* nb input bytes read and buffered */ + unsigned long long consumed; /* nb input bytes actually compressed */ + unsigned long long produced; /* nb of compressed bytes generated and buffered */ + unsigned long long flushed; /* nb of compressed bytes flushed : not provided; can be tracked from caller side */ + unsigned currentJobID; /* MT only : latest started job nb */ + unsigned nbActiveWorkers; /* MT only : nb of workers actively compressing at probe time */ +} ZSTD_frameProgression; + +/* ZSTD_getFrameProgression() : + * tells how much data has been ingested (read from input) + * consumed (input actually compressed) and produced (output) for current frame. + * Note : (ingested - consumed) is amount of input data buffered internally, not yet compressed. + * Aggregates progression inside active worker threads. */ -typedef struct ZSTD_DStream_s ZSTD_DStream; -/*===== ZSTD_DStream management functions =====*/ -/** - * ZSTD_initDStream() - initialize a zstd streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. - * - * Return: The zstd streaming decompression context. - */ -ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, - size_t workspaceSize); -/** - * ZSTD_initDStream_usingDDict() - initialize streaming decompression context - * @maxWindowSize: The maximum window size allowed for compressed frames. - * @ddict: The digested dictionary to use for decompression. - * @workspace: The workspace to emplace the context into. It must outlive - * the returned context. - * @workspaceSize: The size of workspace. - * Use ZSTD_DStreamWorkspaceBound(maxWindowSize) to determine - * how large the workspace must be. - * - * Return: The zstd streaming decompression context. - */ -ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, - const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize); +ZSTDLIB_API ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx); + +/*! ZSTD_toFlushNow() : + * Tell how many bytes are ready to be flushed immediately. + * Useful for multithreading scenarios (nbWorkers >= 1). + * Probe the oldest active job, defined as oldest job not yet entirely flushed, + * and check its output buffer. + * @return : amount of data stored in oldest job and ready to be flushed immediately. + * if @return == 0, it means either : + * + there is no active job (could be checked with ZSTD_frameProgression()), or + * + oldest job is still actively compressing data, + * but everything it has produced has also been flushed so far, + * therefore flush speed is limited by production speed of oldest job + * irrespective of the speed of concurrent (and newer) jobs. + */ +ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx); -/*===== Streaming decompression functions =====*/ -/** - * ZSTD_resetDStream() - reset the context using parameters from creation - * @zds: The zstd streaming decompression context to reset. + +/*===== Advanced Streaming decompression functions =====*/ + +/*! + * This function is deprecated, and is equivalent to: * - * Resets the context using the parameters from creation. Skips dictionary - * loading, since it can be reused. + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_loadDictionary(zds, dict, dictSize); * - * Return: Zero or an error, which can be checked using ZSTD_isError(). + * note: no dictionary will be used if dict == NULL or dictSize < 8 + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ -size_t ZSTD_resetDStream(ZSTD_DStream *zds); -/** - * ZSTD_decompressStream() - streaming decompress some of input into output - * @zds: The zstd streaming decompression context. - * @output: Destination buffer. `output.pos` is updated to indicate how much - * decompressed data was written. - * @input: Source buffer. `input.pos` is updated to indicate how much data was - * read. Note that it may not consume the entire input, in which case - * `input.pos < input.size`, and it's up to the caller to present - * remaining data again. +ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); + +/*! + * This function is deprecated, and is equivalent to: * - * The `input` and `output` buffers may be any size. Guaranteed to make some - * forward progress if `input` and `output` are not empty. - * ZSTD_decompressStream() will not consume the last byte of the frame until - * the entire frame is flushed. + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); + * ZSTD_DCtx_refDDict(zds, ddict); * - * Return: Returns 0 iff a frame is completely decoded and fully flushed. - * Otherwise returns a hint for the number of bytes to use as the input - * for the next function call or an error, which can be checked using - * ZSTD_isError(). The size hint will never load more than the frame. + * note : ddict is referenced, it must outlive decompression session + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ -size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, - ZSTD_inBuffer *input); +ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); -/** - * ZSTD_DStreamInSize() - recommended size for the input buffer - * - * Return: The recommended size for the input buffer. - */ -size_t ZSTD_DStreamInSize(void); -/** - * ZSTD_DStreamOutSize() - recommended size for the output buffer +/*! + * This function is deprecated, and is equivalent to: * - * When the output buffer is at least this large, it is guaranteed to be large - * enough to flush at least one complete decompressed block. + * ZSTD_DCtx_reset(zds, ZSTD_reset_session_only); * - * Return: The recommended size for the output buffer. + * re-use decompression parameters from previous init; saves dictionary loading + * Note : this prototype will be marked as deprecated and generate compilation warnings on reaching v1.5.x */ -size_t ZSTD_DStreamOutSize(void); +ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); -/* --- Constants ---*/ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ -#define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U +/* ******************************************************************* +* Buffer-less and synchronous inner streaming functions +* +* This is an advanced API, giving full control over buffer management, for users which need direct control over memory. +* But it's also a complex one, with several restrictions, documented below. +* Prefer normal streaming API for an easier experience. +********************************************************************* */ -#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1) -#define ZSTD_CONTENTSIZE_ERROR (0ULL - 2) +/* + Buffer-less streaming compression (synchronous mode) + + A ZSTD_CCtx object is required to track streaming operations. + Use ZSTD_createCCtx() / ZSTD_freeCCtx() to manage resource. + ZSTD_CCtx object can be re-used multiple times within successive compression operations. + + Start by initializing a context. + Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary compression, + or ZSTD_compressBegin_advanced(), for finer parameter control. + It's also possible to duplicate a reference context which has already been initialized, using ZSTD_copyCCtx() + + Then, consume your input using ZSTD_compressContinue(). + There are some important considerations to keep in mind when using this advanced function : + - ZSTD_compressContinue() has no internal buffer. It uses externally provided buffers only. + - Interface is synchronous : input is consumed entirely and produces 1+ compressed blocks. + - Caller must ensure there is enough space in `dst` to store compressed data under worst case scenario. + Worst case evaluation is provided by ZSTD_compressBound(). + ZSTD_compressContinue() doesn't guarantee recover after a failed compression. + - ZSTD_compressContinue() presumes prior input ***is still accessible and unmodified*** (up to maximum distance size, see WindowLog). + It remembers all previous contiguous blocks, plus one separated memory segment (which can itself consists of multiple contiguous blocks) + - ZSTD_compressContinue() detects that prior input has been overwritten when `src` buffer overlaps. + In which case, it will "discard" the relevant memory section from its history. + + Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum. + It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. + Without last block mark, frames are considered unfinished (hence corrupted) by compliant decoders. + + `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress again. +*/ -#define ZSTD_WINDOWLOG_MAX_32 27 -#define ZSTD_WINDOWLOG_MAX_64 27 -#define ZSTD_WINDOWLOG_MAX \ - ((unsigned int)(sizeof(size_t) == 4 \ - ? ZSTD_WINDOWLOG_MAX_32 \ - : ZSTD_WINDOWLOG_MAX_64)) -#define ZSTD_WINDOWLOG_MIN 10 -#define ZSTD_HASHLOG_MAX ZSTD_WINDOWLOG_MAX -#define ZSTD_HASHLOG_MIN 6 -#define ZSTD_CHAINLOG_MAX (ZSTD_WINDOWLOG_MAX+1) -#define ZSTD_CHAINLOG_MIN ZSTD_HASHLOG_MIN -#define ZSTD_HASHLOG3_MAX 17 -#define ZSTD_SEARCHLOG_MAX (ZSTD_WINDOWLOG_MAX-1) -#define ZSTD_SEARCHLOG_MIN 1 -/* only for ZSTD_fast, other strategies are limited to 6 */ -#define ZSTD_SEARCHLENGTH_MAX 7 -/* only for ZSTD_btopt, other strategies are limited to 4 */ -#define ZSTD_SEARCHLENGTH_MIN 3 -#define ZSTD_TARGETLENGTH_MIN 4 -#define ZSTD_TARGETLENGTH_MAX 999 - -/* for static allocation */ -#define ZSTD_FRAMEHEADERSIZE_MAX 18 -#define ZSTD_FRAMEHEADERSIZE_MIN 6 -#define ZSTD_frameHeaderSize_prefix 5 -#define ZSTD_frameHeaderSize_min ZSTD_FRAMEHEADERSIZE_MIN -#define ZSTD_frameHeaderSize_max ZSTD_FRAMEHEADERSIZE_MAX -/* magic number + skippable frame length */ -#define ZSTD_skippableHeaderSize 8 - - -/*-************************************* - * Compressed size functions - **************************************/ - -/** - * ZSTD_findFrameCompressedSize() - returns the size of a compressed frame - * @src: Source buffer. It should point to the start of a zstd encoded frame - * or a skippable frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * size of the frame. - * - * Return: The compressed size of the frame pointed to by `src` or an error, - * which can be check with ZSTD_isError(). - * Suitable to pass to ZSTD_decompress() or similar functions. - */ -size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Decompressed size functions - **************************************/ -/** - * ZSTD_getFrameContentSize() - returns the content size in a zstd frame header - * @src: It should point to the start of a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. - * - * Return: The frame content size stored in the frame header if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the content size isn't stored in the - * frame header. `ZSTD_CONTENTSIZE_ERROR` on invalid input. - */ -unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize); - -/** - * ZSTD_findDecompressedSize() - returns decompressed size of a series of frames - * @src: It should point to the start of a series of zstd encoded and/or - * skippable frames. - * @srcSize: The exact size of the series of frames. - * - * If any zstd encoded frame in the series doesn't have the frame content size - * set, `ZSTD_CONTENTSIZE_UNKNOWN` is returned. But frame content size is always - * set when using ZSTD_compress(). The decompressed size can be very large. - * If the source is untrusted, the decompressed size could be wrong or - * intentionally modified. Always ensure the result fits within the - * application's authorized limits. ZSTD_findDecompressedSize() handles multiple - * frames, and so it must traverse the input to read each frame header. This is - * efficient as most of the data is skipped, however it does mean that all frame - * data must be present and valid. - * - * Return: Decompressed size of all the data contained in the frames if known. - * `ZSTD_CONTENTSIZE_UNKNOWN` if the decompressed size is unknown. - * `ZSTD_CONTENTSIZE_ERROR` if an error occurred. - */ -unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize); - -/*-************************************* - * Advanced compression functions - **************************************/ -/** - * ZSTD_checkCParams() - ensure parameter values remain within authorized range - * @cParams: The zstd compression parameters. - * - * Return: Zero or an error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams); - -/** - * ZSTD_adjustCParams() - optimize parameters for a given srcSize and dictSize - * @srcSize: Optionally the estimated source size, or zero if unknown. - * @dictSize: Optionally the estimated dictionary size, or zero if unknown. - * - * Return: The optimized parameters. - */ -ZSTD_compressionParameters ZSTD_adjustCParams( - ZSTD_compressionParameters cParams, unsigned long long srcSize, - size_t dictSize); - -/*--- Advanced decompression functions ---*/ - -/** - * ZSTD_isFrame() - returns true iff the buffer starts with a valid frame - * @buffer: The source buffer to check. - * @size: The size of the source buffer, must be at least 4 bytes. - * - * Return: True iff the buffer starts with a zstd or skippable frame identifier. - */ -unsigned int ZSTD_isFrame(const void *buffer, size_t size); - -/** - * ZSTD_getDictID_fromDict() - returns the dictionary id stored in a dictionary - * @dict: The dictionary buffer. - * @dictSize: The size of the dictionary buffer. - * - * Return: The dictionary id stored within the dictionary or 0 if the - * dictionary is not a zstd dictionary. If it returns 0 the - * dictionary can still be loaded as a content-only dictionary. - */ -unsigned int ZSTD_getDictID_fromDict(const void *dict, size_t dictSize); +/*===== Buffer-less streaming compression functions =====*/ +ZSTDLIB_API size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel); +ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); +ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /*< pledgedSrcSize : If srcSize is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN */ +ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict); /*< note: fails if cdict==NULL */ +ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict_advanced(ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize); /* compression parameters are already set within cdict. pledgedSrcSize must be correct. If srcSize is not known, use macro ZSTD_CONTENTSIZE_UNKNOWN */ +ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); /*< note: if pledgedSrcSize is not known, use ZSTD_CONTENTSIZE_UNKNOWN */ -/** - * ZSTD_getDictID_fromDDict() - returns the dictionary id stored in a ZSTD_DDict - * @ddict: The ddict to find the id of. - * - * Return: The dictionary id stored within `ddict` or 0 if the dictionary is not - * a zstd dictionary. If it returns 0 `ddict` will be loaded as a - * content-only dictionary. - */ -unsigned int ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict); +ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); -/** - * ZSTD_getDictID_fromFrame() - returns the dictionary id stored in a zstd frame - * @src: Source buffer. It must be a zstd encoded frame. - * @srcSize: The size of the source buffer. It must be at least as large as the - * frame header. `ZSTD_frameHeaderSize_max` is always large enough. - * - * Return: The dictionary id required to decompress the frame stored within - * `src` or 0 if the dictionary id could not be decoded. It can return - * 0 if the frame does not require a dictionary, the dictionary id - * wasn't stored in the frame, `src` is not a zstd frame, or `srcSize` - * is too small. - */ -unsigned int ZSTD_getDictID_fromFrame(const void *src, size_t srcSize); -/** - * struct ZSTD_frameParams - zstd frame parameters stored in the frame header - * @frameContentSize: The frame content size, or 0 if not present. - * @windowSize: The window size, or 0 if the frame is a skippable frame. - * @dictID: The dictionary id, or 0 if not present. - * @checksumFlag: Whether a checksum was used. - */ +/* + Buffer-less streaming decompression (synchronous mode) + + A ZSTD_DCtx object is required to track streaming operations. + Use ZSTD_createDCtx() / ZSTD_freeDCtx() to manage it. + A ZSTD_DCtx object can be re-used multiple times. + + First typical operation is to retrieve frame parameters, using ZSTD_getFrameHeader(). + Frame header is extracted from the beginning of compressed frame, so providing only the frame's beginning is enough. + Data fragment must be large enough to ensure successful decoding. + `ZSTD_frameHeaderSize_max` bytes is guaranteed to always be large enough. + @result : 0 : successful decoding, the `ZSTD_frameHeader` structure is correctly filled. + >0 : `srcSize` is too small, please provide at least @result bytes on next attempt. + errorCode, which can be tested using ZSTD_isError(). + + It fills a ZSTD_frameHeader structure with important information to correctly decode the frame, + such as the dictionary ID, content size, or maximum back-reference distance (`windowSize`). + Note that these values could be wrong, either because of data corruption, or because a 3rd party deliberately spoofs false information. + As a consequence, check that values remain within valid application range. + For example, do not allocate memory blindly, check that `windowSize` is within expectation. + Each application can set its own limits, depending on local restrictions. + For extended interoperability, it is recommended to support `windowSize` of at least 8 MB. + + ZSTD_decompressContinue() needs previous data blocks during decompression, up to `windowSize` bytes. + ZSTD_decompressContinue() is very sensitive to contiguity, + if 2 blocks don't follow each other, make sure that either the compressor breaks contiguity at the same place, + or that previous contiguous segment is large enough to properly handle maximum back-reference distance. + There are multiple ways to guarantee this condition. + + The most memory efficient way is to use a round buffer of sufficient size. + Sufficient size is determined by invoking ZSTD_decodingBufferSize_min(), + which can @return an error code if required value is too large for current system (in 32-bits mode). + In a round buffer methodology, ZSTD_decompressContinue() decompresses each block next to previous one, + up to the moment there is not enough room left in the buffer to guarantee decoding another full block, + which maximum size is provided in `ZSTD_frameHeader` structure, field `blockSizeMax`. + At which point, decoding can resume from the beginning of the buffer. + Note that already decoded data stored in the buffer should be flushed before being overwritten. + + There are alternatives possible, for example using two or more buffers of size `windowSize` each, though they consume more memory. + + Finally, if you control the compression process, you can also ignore all buffer size rules, + as long as the encoder and decoder progress in "lock-step", + aka use exactly the same buffer sizes, break contiguity at the same place, etc. + + Once buffers are setup, start decompression, with ZSTD_decompressBegin(). + If decompression requires a dictionary, use ZSTD_decompressBegin_usingDict() or ZSTD_decompressBegin_usingDDict(). + + Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() alternatively. + ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' to ZSTD_decompressContinue(). + ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will fail. + + @result of ZSTD_decompressContinue() is the number of bytes regenerated within 'dst' (necessarily <= dstCapacity). + It can be zero : it just means ZSTD_decompressContinue() has decoded some metadata item. + It can also be an error code, which can be tested with ZSTD_isError(). + + A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. + Context can then be reset to start a new decompression. + + Note : it's possible to know if next input to present is a header or a block, using ZSTD_nextInputType(). + This information is not required to properly decode a frame. + + == Special case : skippable frames == + + Skippable frames allow integration of user-defined data into a flow of concatenated frames. + Skippable frames will be ignored (skipped) by decompressor. + The format of skippable frames is as follows : + a) Skippable frame ID - 4 Bytes, Little endian format, any value from 0x184D2A50 to 0x184D2A5F + b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits + c) Frame Content - any content (User Data) of length equal to Frame Size + For skippable frames ZSTD_getFrameHeader() returns zfhPtr->frameType==ZSTD_skippableFrame. + For skippable frames ZSTD_decompressContinue() always returns 0 : it only skips the content. +*/ + +/*===== Buffer-less streaming decompression functions =====*/ +typedef enum { ZSTD_frame, ZSTD_skippableFrame } ZSTD_frameType_e; typedef struct { - unsigned long long frameContentSize; - unsigned int windowSize; - unsigned int dictID; - unsigned int checksumFlag; -} ZSTD_frameParams; - -/** - * ZSTD_getFrameParams() - extracts parameters from a zstd or skippable frame - * @fparamsPtr: On success the frame parameters are written here. - * @src: The source buffer. It must point to a zstd or skippable frame. - * @srcSize: The size of the source buffer. `ZSTD_frameHeaderSize_max` is - * always large enough to succeed. - * - * Return: 0 on success. If more data is required it returns how many bytes - * must be provided to make forward progress. Otherwise it returns - * an error, which can be checked using ZSTD_isError(). - */ -size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, - size_t srcSize); - -/*-***************************************************************************** - * Buffer-less and synchronous inner streaming functions - * - * This is an advanced API, giving full control over buffer management, for - * users which need direct control over memory. - * But it's also a complex one, with many restrictions (documented below). - * Prefer using normal streaming API for an easier experience - ******************************************************************************/ + unsigned long long frameContentSize; /* if == ZSTD_CONTENTSIZE_UNKNOWN, it means this field is not available. 0 means "empty" */ + unsigned long long windowSize; /* can be very large, up to <= frameContentSize */ + unsigned blockSizeMax; + ZSTD_frameType_e frameType; /* if == ZSTD_skippableFrame, frameContentSize is the size of skippable content */ + unsigned headerSize; + unsigned dictID; + unsigned checksumFlag; +} ZSTD_frameHeader; + +/*! ZSTD_getFrameHeader() : + * decode Frame Header, or requires larger `srcSize`. + * @return : 0, `zfhPtr` is correctly filled, + * >0, `srcSize` is too small, value is wanted `srcSize` amount, + * or an error code, which can be tested using ZSTD_isError() */ +ZSTDLIB_API size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize); /*< doesn't consume input */ +/*! ZSTD_getFrameHeader_advanced() : + * same as ZSTD_getFrameHeader(), + * with added capability to select a format (like ZSTD_f_zstd1_magicless) */ +ZSTDLIB_API size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format); +ZSTDLIB_API size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize); /*< when frame content size is not known, pass in frameContentSize == ZSTD_CONTENTSIZE_UNKNOWN */ + +ZSTDLIB_API size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize); +ZSTDLIB_API size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + +ZSTDLIB_API size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx); +ZSTDLIB_API size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); + +/* misc */ +ZSTDLIB_API void ZSTD_copyDCtx(ZSTD_DCtx* dctx, const ZSTD_DCtx* preparedDCtx); +typedef enum { ZSTDnit_frameHeader, ZSTDnit_blockHeader, ZSTDnit_block, ZSTDnit_lastBlock, ZSTDnit_checksum, ZSTDnit_skippableFrame } ZSTD_nextInputType_e; +ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx); + + + + +/* ============================ */ +/* Block level API */ +/* ============================ */ + +/*! + Block functions produce and decode raw zstd blocks, without frame metadata. + Frame metadata cost is typically ~12 bytes, which can be non-negligible for very small blocks (< 100 bytes). + But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes. + + A few rules to respect : + - Compressing and decompressing require a context structure + + Use ZSTD_createCCtx() and ZSTD_createDCtx() + - It is necessary to init context before starting + + compression : any ZSTD_compressBegin*() variant, including with dictionary + + decompression : any ZSTD_decompressBegin*() variant, including with dictionary + + copyCCtx() and copyDCtx() can be used too + - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB + + If input is larger than a block size, it's necessary to split input data into multiple blocks + + For inputs larger than a single block, consider using regular ZSTD_compress() instead. + Frame metadata is not that costly, and quickly becomes negligible as source size grows larger than a block. + - When a block is considered not compressible enough, ZSTD_compressBlock() result will be 0 (zero) ! + ===> In which case, nothing is produced into `dst` ! + + User __must__ test for such outcome and deal directly with uncompressed data + + A block cannot be declared incompressible if ZSTD_compressBlock() return value was != 0. + Doing so would mess up with statistics history, leading to potential data corruption. + + ZSTD_decompressBlock() _doesn't accept uncompressed data as input_ !! + + In case of multiple successive blocks, should some of them be uncompressed, + decoder must be informed of their existence in order to follow proper history. + Use ZSTD_insertBlock() for such a case. +*/ -/*-***************************************************************************** - * Buffer-less streaming compression (synchronous mode) - * - * A ZSTD_CCtx object is required to track streaming operations. - * Use ZSTD_initCCtx() to initialize a context. - * ZSTD_CCtx object can be re-used multiple times within successive compression - * operations. - * - * Start by initializing a context. - * Use ZSTD_compressBegin(), or ZSTD_compressBegin_usingDict() for dictionary - * compression, - * or ZSTD_compressBegin_advanced(), for finer parameter control. - * It's also possible to duplicate a reference context which has already been - * initialized, using ZSTD_copyCCtx() - * - * Then, consume your input using ZSTD_compressContinue(). - * There are some important considerations to keep in mind when using this - * advanced function : - * - ZSTD_compressContinue() has no internal buffer. It uses externally provided - * buffer only. - * - Interface is synchronous : input is consumed entirely and produce 1+ - * (or more) compressed blocks. - * - Caller must ensure there is enough space in `dst` to store compressed data - * under worst case scenario. Worst case evaluation is provided by - * ZSTD_compressBound(). - * ZSTD_compressContinue() doesn't guarantee recover after a failed - * compression. - * - ZSTD_compressContinue() presumes prior input ***is still accessible and - * unmodified*** (up to maximum distance size, see WindowLog). - * It remembers all previous contiguous blocks, plus one separated memory - * segment (which can itself consists of multiple contiguous blocks) - * - ZSTD_compressContinue() detects that prior input has been overwritten when - * `src` buffer overlaps. In which case, it will "discard" the relevant memory - * section from its history. - * - * Finish a frame with ZSTD_compressEnd(), which will write the last block(s) - * and optional checksum. It's possible to use srcSize==0, in which case, it - * will write a final empty block to end the frame. Without last block mark, - * frames will be considered unfinished (corrupted) by decoders. - * - * `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new - * frame. - ******************************************************************************/ +/*===== Raw zstd block functions =====*/ +ZSTDLIB_API size_t ZSTD_getBlockSize (const ZSTD_CCtx* cctx); +ZSTDLIB_API size_t ZSTD_compressBlock (ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); +ZSTDLIB_API size_t ZSTD_insertBlock (ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize); /*< insert uncompressed block into `dctx` history. Useful for multi-blocks decompression. */ -/*===== Buffer-less streaming compression functions =====*/ -size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel); -size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, int compressionLevel); -size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, - size_t dictSize, ZSTD_parameters params, - unsigned long long pledgedSrcSize); -size_t ZSTD_copyCCtx(ZSTD_CCtx *cctx, const ZSTD_CCtx *preparedCCtx, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, - unsigned long long pledgedSrcSize); -size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); - - - -/*-***************************************************************************** - * Buffer-less streaming decompression (synchronous mode) - * - * A ZSTD_DCtx object is required to track streaming operations. - * Use ZSTD_initDCtx() to initialize a context. - * A ZSTD_DCtx object can be re-used multiple times. - * - * First typical operation is to retrieve frame parameters, using - * ZSTD_getFrameParams(). It fills a ZSTD_frameParams structure which provide - * important information to correctly decode the frame, such as the minimum - * rolling buffer size to allocate to decompress data (`windowSize`), and the - * dictionary ID used. - * Note: content size is optional, it may not be present. 0 means unknown. - * Note that these values could be wrong, either because of data malformation, - * or because an attacker is spoofing deliberate false information. As a - * consequence, check that values remain within valid application range, - * especially `windowSize`, before allocation. Each application can set its own - * limit, depending on local restrictions. For extended interoperability, it is - * recommended to support at least 8 MB. - * Frame parameters are extracted from the beginning of the compressed frame. - * Data fragment must be large enough to ensure successful decoding, typically - * `ZSTD_frameHeaderSize_max` bytes. - * Result: 0: successful decoding, the `ZSTD_frameParams` structure is filled. - * >0: `srcSize` is too small, provide at least this many bytes. - * errorCode, which can be tested using ZSTD_isError(). - * - * Start decompression, with ZSTD_decompressBegin() or - * ZSTD_decompressBegin_usingDict(). Alternatively, you can copy a prepared - * context, using ZSTD_copyDCtx(). - * - * Then use ZSTD_nextSrcSizeToDecompress() and ZSTD_decompressContinue() - * alternatively. - * ZSTD_nextSrcSizeToDecompress() tells how many bytes to provide as 'srcSize' - * to ZSTD_decompressContinue(). - * ZSTD_decompressContinue() requires this _exact_ amount of bytes, or it will - * fail. - * - * The result of ZSTD_decompressContinue() is the number of bytes regenerated - * within 'dst' (necessarily <= dstCapacity). It can be zero, which is not an - * error; it just means ZSTD_decompressContinue() has decoded some metadata - * item. It can also be an error code, which can be tested with ZSTD_isError(). - * - * ZSTD_decompressContinue() needs previous data blocks during decompression, up - * to `windowSize`. They should preferably be located contiguously, prior to - * current block. Alternatively, a round buffer of sufficient size is also - * possible. Sufficient size is determined by frame parameters. - * ZSTD_decompressContinue() is very sensitive to contiguity, if 2 blocks don't - * follow each other, make sure that either the compressor breaks contiguity at - * the same place, or that previous contiguous segment is large enough to - * properly handle maximum back-reference. - * - * A frame is fully decoded when ZSTD_nextSrcSizeToDecompress() returns zero. - * Context can then be reset to start a new decompression. - * - * Note: it's possible to know if next input to present is a header or a block, - * using ZSTD_nextInputType(). This information is not required to properly - * decode a frame. - * - * == Special case: skippable frames == - * - * Skippable frames allow integration of user-defined data into a flow of - * concatenated frames. Skippable frames will be ignored (skipped) by a - * decompressor. The format of skippable frames is as follows: - * a) Skippable frame ID - 4 Bytes, Little endian format, any value from - * 0x184D2A50 to 0x184D2A5F - * b) Frame Size - 4 Bytes, Little endian format, unsigned 32-bits - * c) Frame Content - any content (User Data) of length equal to Frame Size - * For skippable frames ZSTD_decompressContinue() always returns 0. - * For skippable frames ZSTD_getFrameParams() returns fparamsPtr->windowLog==0 - * what means that a frame is skippable. - * Note: If fparamsPtr->frameContentSize==0, it is ambiguous: the frame might - * actually be a zstd encoded frame with no content. For purposes of - * decompression, it is valid in both cases to skip the frame using - * ZSTD_findFrameCompressedSize() to find its size in bytes. - * It also returns frame size as fparamsPtr->frameContentSize. - ******************************************************************************/ -/*===== Buffer-less streaming decompression functions =====*/ -size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx); -size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, - size_t dictSize); -void ZSTD_copyDCtx(ZSTD_DCtx *dctx, const ZSTD_DCtx *preparedDCtx); -size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx); -size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -typedef enum { - ZSTDnit_frameHeader, - ZSTDnit_blockHeader, - ZSTDnit_block, - ZSTDnit_lastBlock, - ZSTDnit_checksum, - ZSTDnit_skippableFrame -} ZSTD_nextInputType_e; -ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx); - -/*-***************************************************************************** - * Block functions - * - * Block functions produce and decode raw zstd blocks, without frame metadata. - * Frame metadata cost is typically ~18 bytes, which can be non-negligible for - * very small blocks (< 100 bytes). User will have to take in charge required - * information to regenerate data, such as compressed and content sizes. - * - * A few rules to respect: - * - Compressing and decompressing require a context structure - * + Use ZSTD_initCCtx() and ZSTD_initDCtx() - * - It is necessary to init context before starting - * + compression : ZSTD_compressBegin() - * + decompression : ZSTD_decompressBegin() - * + variants _usingDict() are also allowed - * + copyCCtx() and copyDCtx() work too - * - Block size is limited, it must be <= ZSTD_getBlockSizeMax() - * + If you need to compress more, cut data into multiple blocks - * + Consider using the regular ZSTD_compress() instead, as frame metadata - * costs become negligible when source size is large. - * - When a block is considered not compressible enough, ZSTD_compressBlock() - * result will be zero. In which case, nothing is produced into `dst`. - * + User must test for such outcome and deal directly with uncompressed data - * + ZSTD_decompressBlock() doesn't accept uncompressed data as input!!! - * + In case of multiple successive blocks, decoder must be informed of - * uncompressed block existence to follow proper history. Use - * ZSTD_insertBlock() in such a case. - ******************************************************************************/ +#endif /* ZSTD_H_ZSTD_STATIC_LINKING_ONLY */ -/* Define for static allocation */ -#define ZSTD_BLOCKSIZE_ABSOLUTEMAX (128 * 1024) -/*===== Raw zstd block functions =====*/ -size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx); -size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, - const void *src, size_t srcSize); -size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, - size_t blockSize); - -#endif /* ZSTD_H */ diff --git a/lib/zstd/Makefile b/lib/zstd/Makefile index f5d778e7e5c7..65218ec5b8f2 100644 --- a/lib/zstd/Makefile +++ b/lib/zstd/Makefile @@ -1,10 +1,46 @@ -# SPDX-License-Identifier: GPL-2.0-only +# SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause +# ################################################################ +# Copyright (c) Facebook, Inc. +# All rights reserved. +# +# This source code is licensed under both the BSD-style license (found in the +# LICENSE file in the root directory of this source tree) and the GPLv2 (found +# in the COPYING file in the root directory of this source tree). +# You may select, at your option, one of the above-listed licenses. +# ################################################################ obj-$(CONFIG_ZSTD_COMPRESS) += zstd_compress.o obj-$(CONFIG_ZSTD_DECOMPRESS) += zstd_decompress.o ccflags-y += -O3 -zstd_compress-y := fse_compress.o huf_compress.o compress.o \ - entropy_common.o fse_decompress.o zstd_common.o -zstd_decompress-y := huf_decompress.o decompress.o \ - entropy_common.o fse_decompress.o zstd_common.o +zstd_compress-y := \ + zstd_compress_module.o \ + common/debug.o \ + common/entropy_common.o \ + common/error_private.o \ + common/fse_decompress.o \ + common/zstd_common.o \ + compress/fse_compress.o \ + compress/hist.o \ + compress/huf_compress.o \ + compress/zstd_compress.o \ + compress/zstd_compress_literals.o \ + compress/zstd_compress_sequences.o \ + compress/zstd_compress_superblock.o \ + compress/zstd_double_fast.o \ + compress/zstd_fast.o \ + compress/zstd_lazy.o \ + compress/zstd_ldm.o \ + compress/zstd_opt.o \ + +zstd_decompress-y := \ + zstd_decompress_module.o \ + common/debug.o \ + common/entropy_common.o \ + common/error_private.o \ + common/fse_decompress.o \ + common/zstd_common.o \ + decompress/huf_decompress.o \ + decompress/zstd_ddict.o \ + decompress/zstd_decompress.o \ + decompress/zstd_decompress_block.o \ diff --git a/lib/zstd/bitstream.h b/lib/zstd/bitstream.h deleted file mode 100644 index 5d6343c1a909..000000000000 --- a/lib/zstd/bitstream.h +++ /dev/null @@ -1,380 +0,0 @@ -/* - * bitstream - * Part of FSE library - * header file (to include) - * Copyright (C) 2013-2016, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ -#ifndef BITSTREAM_H_MODULE -#define BITSTREAM_H_MODULE - -/* -* This API consists of small unitary functions, which must be inlined for best performance. -* Since link-time-optimization is not available for all compilers, -* these functions are defined into a .h to be included. -*/ - -/*-**************************************** -* Dependencies -******************************************/ -#include "error_private.h" /* error codes and messages */ -#include "mem.h" /* unaligned access routines */ - -/*========================================= -* Target specific -=========================================*/ -#define STREAM_ACCUMULATOR_MIN_32 25 -#define STREAM_ACCUMULATOR_MIN_64 57 -#define STREAM_ACCUMULATOR_MIN ((U32)(ZSTD_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64)) - -/*-****************************************** -* bitStream encoding API (write forward) -********************************************/ -/* bitStream can mix input from multiple sources. -* A critical property of these streams is that they encode and decode in **reverse** direction. -* So the first bit sequence you add will be the last to be read, like a LIFO stack. -*/ -typedef struct { - size_t bitContainer; - int bitPos; - char *startPtr; - char *ptr; - char *endPtr; -} BIT_CStream_t; - -ZSTD_STATIC size_t BIT_initCStream(BIT_CStream_t *bitC, void *dstBuffer, size_t dstCapacity); -ZSTD_STATIC void BIT_addBits(BIT_CStream_t *bitC, size_t value, unsigned nbBits); -ZSTD_STATIC void BIT_flushBits(BIT_CStream_t *bitC); -ZSTD_STATIC size_t BIT_closeCStream(BIT_CStream_t *bitC); - -/* Start with initCStream, providing the size of buffer to write into. -* bitStream will never write outside of this buffer. -* `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code. -* -* bits are first added to a local register. -* Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems. -* Writing data into memory is an explicit operation, performed by the flushBits function. -* Hence keep track how many bits are potentially stored into local register to avoid register overflow. -* After a flushBits, a maximum of 7 bits might still be stored into local register. -* -* Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers. -* -* Last operation is to close the bitStream. -* The function returns the final size of CStream in bytes. -* If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable) -*/ - -/*-******************************************** -* bitStream decoding API (read backward) -**********************************************/ -typedef struct { - size_t bitContainer; - unsigned bitsConsumed; - const char *ptr; - const char *start; -} BIT_DStream_t; - -typedef enum { - BIT_DStream_unfinished = 0, - BIT_DStream_endOfBuffer = 1, - BIT_DStream_completed = 2, - BIT_DStream_overflow = 3 -} BIT_DStream_status; /* result of BIT_reloadDStream() */ -/* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */ - -ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, size_t srcSize); -ZSTD_STATIC size_t BIT_readBits(BIT_DStream_t *bitD, unsigned nbBits); -ZSTD_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t *bitD); -ZSTD_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t *bitD); - -/* Start by invoking BIT_initDStream(). -* A chunk of the bitStream is then stored into a local register. -* Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t). -* You can then retrieve bitFields stored into the local register, **in reverse order**. -* Local register is explicitly reloaded from memory by the BIT_reloadDStream() method. -* A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished. -* Otherwise, it can be less than that, so proceed accordingly. -* Checking if DStream has reached its end can be performed with BIT_endOfDStream(). -*/ - -/*-**************************************** -* unsafe API -******************************************/ -ZSTD_STATIC void BIT_addBitsFast(BIT_CStream_t *bitC, size_t value, unsigned nbBits); -/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */ - -ZSTD_STATIC void BIT_flushBitsFast(BIT_CStream_t *bitC); -/* unsafe version; does not check buffer overflow */ - -ZSTD_STATIC size_t BIT_readBitsFast(BIT_DStream_t *bitD, unsigned nbBits); -/* faster, but works only if nbBits >= 1 */ - -/*-************************************************************** -* Internal functions -****************************************************************/ -ZSTD_STATIC unsigned BIT_highbit32(register U32 val) { return 31 - __builtin_clz(val); } - -/*===== Local Constants =====*/ -static const unsigned BIT_mask[] = {0, 1, 3, 7, 0xF, 0x1F, 0x3F, 0x7F, 0xFF, - 0x1FF, 0x3FF, 0x7FF, 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF, - 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF}; /* up to 26 bits */ - -/*-************************************************************** -* bitStream encoding -****************************************************************/ -/*! BIT_initCStream() : - * `dstCapacity` must be > sizeof(void*) - * @return : 0 if success, - otherwise an error code (can be tested using ERR_isError() ) */ -ZSTD_STATIC size_t BIT_initCStream(BIT_CStream_t *bitC, void *startPtr, size_t dstCapacity) -{ - bitC->bitContainer = 0; - bitC->bitPos = 0; - bitC->startPtr = (char *)startPtr; - bitC->ptr = bitC->startPtr; - bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->ptr); - if (dstCapacity <= sizeof(bitC->ptr)) - return ERROR(dstSize_tooSmall); - return 0; -} - -/*! BIT_addBits() : - can add up to 26 bits into `bitC`. - Does not check for register overflow ! */ -ZSTD_STATIC void BIT_addBits(BIT_CStream_t *bitC, size_t value, unsigned nbBits) -{ - bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos; - bitC->bitPos += nbBits; -} - -/*! BIT_addBitsFast() : - * works only if `value` is _clean_, meaning all high bits above nbBits are 0 */ -ZSTD_STATIC void BIT_addBitsFast(BIT_CStream_t *bitC, size_t value, unsigned nbBits) -{ - bitC->bitContainer |= value << bitC->bitPos; - bitC->bitPos += nbBits; -} - -/*! BIT_flushBitsFast() : - * unsafe version; does not check buffer overflow */ -ZSTD_STATIC void BIT_flushBitsFast(BIT_CStream_t *bitC) -{ - size_t const nbBytes = bitC->bitPos >> 3; - ZSTD_writeLEST(bitC->ptr, bitC->bitContainer); - bitC->ptr += nbBytes; - bitC->bitPos &= 7; - bitC->bitContainer >>= nbBytes * 8; /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */ -} - -/*! BIT_flushBits() : - * safe version; check for buffer overflow, and prevents it. - * note : does not signal buffer overflow. This will be revealed later on using BIT_closeCStream() */ -ZSTD_STATIC void BIT_flushBits(BIT_CStream_t *bitC) -{ - size_t const nbBytes = bitC->bitPos >> 3; - ZSTD_writeLEST(bitC->ptr, bitC->bitContainer); - bitC->ptr += nbBytes; - if (bitC->ptr > bitC->endPtr) - bitC->ptr = bitC->endPtr; - bitC->bitPos &= 7; - bitC->bitContainer >>= nbBytes * 8; /* if bitPos >= sizeof(bitContainer)*8 --> undefined behavior */ -} - -/*! BIT_closeCStream() : - * @return : size of CStream, in bytes, - or 0 if it could not fit into dstBuffer */ -ZSTD_STATIC size_t BIT_closeCStream(BIT_CStream_t *bitC) -{ - BIT_addBitsFast(bitC, 1, 1); /* endMark */ - BIT_flushBits(bitC); - - if (bitC->ptr >= bitC->endPtr) - return 0; /* doesn't fit within authorized budget : cancel */ - - return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0); -} - -/*-******************************************************** -* bitStream decoding -**********************************************************/ -/*! BIT_initDStream() : -* Initialize a BIT_DStream_t. -* `bitD` : a pointer to an already allocated BIT_DStream_t structure. -* `srcSize` must be the *exact* size of the bitStream, in bytes. -* @return : size of stream (== srcSize) or an errorCode if a problem is detected -*/ -ZSTD_STATIC size_t BIT_initDStream(BIT_DStream_t *bitD, const void *srcBuffer, size_t srcSize) -{ - if (srcSize < 1) { - memset(bitD, 0, sizeof(*bitD)); - return ERROR(srcSize_wrong); - } - - if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */ - bitD->start = (const char *)srcBuffer; - bitD->ptr = (const char *)srcBuffer + srcSize - sizeof(bitD->bitContainer); - bitD->bitContainer = ZSTD_readLEST(bitD->ptr); - { - BYTE const lastByte = ((const BYTE *)srcBuffer)[srcSize - 1]; - bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; /* ensures bitsConsumed is always set */ - if (lastByte == 0) - return ERROR(GENERIC); /* endMark not present */ - } - } else { - bitD->start = (const char *)srcBuffer; - bitD->ptr = bitD->start; - bitD->bitContainer = *(const BYTE *)(bitD->start); - switch (srcSize) { - case 7: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[6]) << (sizeof(bitD->bitContainer) * 8 - 16); - fallthrough; - case 6: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[5]) << (sizeof(bitD->bitContainer) * 8 - 24); - fallthrough; - case 5: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[4]) << (sizeof(bitD->bitContainer) * 8 - 32); - fallthrough; - case 4: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[3]) << 24; - fallthrough; - case 3: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[2]) << 16; - fallthrough; - case 2: bitD->bitContainer += (size_t)(((const BYTE *)(srcBuffer))[1]) << 8; - fallthrough; - default:; - } - { - BYTE const lastByte = ((const BYTE *)srcBuffer)[srcSize - 1]; - bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; - if (lastByte == 0) - return ERROR(GENERIC); /* endMark not present */ - } - bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize) * 8; - } - - return srcSize; -} - -ZSTD_STATIC size_t BIT_getUpperBits(size_t bitContainer, U32 const start) { return bitContainer >> start; } - -ZSTD_STATIC size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits) { return (bitContainer >> start) & BIT_mask[nbBits]; } - -ZSTD_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits) { return bitContainer & BIT_mask[nbBits]; } - -/*! BIT_lookBits() : - * Provides next n bits from local register. - * local register is not modified. - * On 32-bits, maxNbBits==24. - * On 64-bits, maxNbBits==56. - * @return : value extracted - */ -ZSTD_STATIC size_t BIT_lookBits(const BIT_DStream_t *bitD, U32 nbBits) -{ - U32 const bitMask = sizeof(bitD->bitContainer) * 8 - 1; - return ((bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> 1) >> ((bitMask - nbBits) & bitMask); -} - -/*! BIT_lookBitsFast() : -* unsafe version; only works only if nbBits >= 1 */ -ZSTD_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t *bitD, U32 nbBits) -{ - U32 const bitMask = sizeof(bitD->bitContainer) * 8 - 1; - return (bitD->bitContainer << (bitD->bitsConsumed & bitMask)) >> (((bitMask + 1) - nbBits) & bitMask); -} - -ZSTD_STATIC void BIT_skipBits(BIT_DStream_t *bitD, U32 nbBits) { bitD->bitsConsumed += nbBits; } - -/*! BIT_readBits() : - * Read (consume) next n bits from local register and update. - * Pay attention to not read more than nbBits contained into local register. - * @return : extracted value. - */ -ZSTD_STATIC size_t BIT_readBits(BIT_DStream_t *bitD, U32 nbBits) -{ - size_t const value = BIT_lookBits(bitD, nbBits); - BIT_skipBits(bitD, nbBits); - return value; -} - -/*! BIT_readBitsFast() : -* unsafe version; only works only if nbBits >= 1 */ -ZSTD_STATIC size_t BIT_readBitsFast(BIT_DStream_t *bitD, U32 nbBits) -{ - size_t const value = BIT_lookBitsFast(bitD, nbBits); - BIT_skipBits(bitD, nbBits); - return value; -} - -/*! BIT_reloadDStream() : -* Refill `bitD` from buffer previously set in BIT_initDStream() . -* This function is safe, it guarantees it will not read beyond src buffer. -* @return : status of `BIT_DStream_t` internal register. - if status == BIT_DStream_unfinished, internal register is filled with >= (sizeof(bitD->bitContainer)*8 - 7) bits */ -ZSTD_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t *bitD) -{ - if (bitD->bitsConsumed > (sizeof(bitD->bitContainer) * 8)) /* should not happen => corruption detected */ - return BIT_DStream_overflow; - - if (bitD->ptr >= bitD->start + sizeof(bitD->bitContainer)) { - bitD->ptr -= bitD->bitsConsumed >> 3; - bitD->bitsConsumed &= 7; - bitD->bitContainer = ZSTD_readLEST(bitD->ptr); - return BIT_DStream_unfinished; - } - if (bitD->ptr == bitD->start) { - if (bitD->bitsConsumed < sizeof(bitD->bitContainer) * 8) - return BIT_DStream_endOfBuffer; - return BIT_DStream_completed; - } - { - U32 nbBytes = bitD->bitsConsumed >> 3; - BIT_DStream_status result = BIT_DStream_unfinished; - if (bitD->ptr - nbBytes < bitD->start) { - nbBytes = (U32)(bitD->ptr - bitD->start); /* ptr > start */ - result = BIT_DStream_endOfBuffer; - } - bitD->ptr -= nbBytes; - bitD->bitsConsumed -= nbBytes * 8; - bitD->bitContainer = ZSTD_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD) */ - return result; - } -} - -/*! BIT_endOfDStream() : -* @return Tells if DStream has exactly reached its end (all bits consumed). -*/ -ZSTD_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t *DStream) -{ - return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer) * 8)); -} - -#endif /* BITSTREAM_H_MODULE */ diff --git a/lib/zstd/common/bitstream.h b/lib/zstd/common/bitstream.h new file mode 100644 index 000000000000..28248abe8612 --- /dev/null +++ b/lib/zstd/common/bitstream.h @@ -0,0 +1,437 @@ +/* ****************************************************************** + * bitstream + * Part of FSE library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ +#ifndef BITSTREAM_H_MODULE +#define BITSTREAM_H_MODULE + +/* +* This API consists of small unitary functions, which must be inlined for best performance. +* Since link-time-optimization is not available for all compilers, +* these functions are defined into a .h to be included. +*/ + +/*-**************************************** +* Dependencies +******************************************/ +#include "mem.h" /* unaligned access routines */ +#include "compiler.h" /* UNLIKELY() */ +#include "debug.h" /* assert(), DEBUGLOG(), RAWLOG() */ +#include "error_private.h" /* error codes and messages */ + + +/*========================================= +* Target specific +=========================================*/ + +#define STREAM_ACCUMULATOR_MIN_32 25 +#define STREAM_ACCUMULATOR_MIN_64 57 +#define STREAM_ACCUMULATOR_MIN ((U32)(MEM_32bits() ? STREAM_ACCUMULATOR_MIN_32 : STREAM_ACCUMULATOR_MIN_64)) + + +/*-****************************************** +* bitStream encoding API (write forward) +********************************************/ +/* bitStream can mix input from multiple sources. + * A critical property of these streams is that they encode and decode in **reverse** direction. + * So the first bit sequence you add will be the last to be read, like a LIFO stack. + */ +typedef struct { + size_t bitContainer; + unsigned bitPos; + char* startPtr; + char* ptr; + char* endPtr; +} BIT_CStream_t; + +MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, void* dstBuffer, size_t dstCapacity); +MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, size_t value, unsigned nbBits); +MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC); +MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC); + +/* Start with initCStream, providing the size of buffer to write into. +* bitStream will never write outside of this buffer. +* `dstCapacity` must be >= sizeof(bitD->bitContainer), otherwise @return will be an error code. +* +* bits are first added to a local register. +* Local register is size_t, hence 64-bits on 64-bits systems, or 32-bits on 32-bits systems. +* Writing data into memory is an explicit operation, performed by the flushBits function. +* Hence keep track how many bits are potentially stored into local register to avoid register overflow. +* After a flushBits, a maximum of 7 bits might still be stored into local register. +* +* Avoid storing elements of more than 24 bits if you want compatibility with 32-bits bitstream readers. +* +* Last operation is to close the bitStream. +* The function returns the final size of CStream in bytes. +* If data couldn't fit into `dstBuffer`, it will return a 0 ( == not storable) +*/ + + +/*-******************************************** +* bitStream decoding API (read backward) +**********************************************/ +typedef struct { + size_t bitContainer; + unsigned bitsConsumed; + const char* ptr; + const char* start; + const char* limitPtr; +} BIT_DStream_t; + +typedef enum { BIT_DStream_unfinished = 0, + BIT_DStream_endOfBuffer = 1, + BIT_DStream_completed = 2, + BIT_DStream_overflow = 3 } BIT_DStream_status; /* result of BIT_reloadDStream() */ + /* 1,2,4,8 would be better for bitmap combinations, but slows down performance a bit ... :( */ + +MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize); +MEM_STATIC size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits); +MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD); +MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* bitD); + + +/* Start by invoking BIT_initDStream(). +* A chunk of the bitStream is then stored into a local register. +* Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t). +* You can then retrieve bitFields stored into the local register, **in reverse order**. +* Local register is explicitly reloaded from memory by the BIT_reloadDStream() method. +* A reload guarantee a minimum of ((8*sizeof(bitD->bitContainer))-7) bits when its result is BIT_DStream_unfinished. +* Otherwise, it can be less than that, so proceed accordingly. +* Checking if DStream has reached its end can be performed with BIT_endOfDStream(). +*/ + + +/*-**************************************** +* unsafe API +******************************************/ +MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, size_t value, unsigned nbBits); +/* faster, but works only if value is "clean", meaning all high bits above nbBits are 0 */ + +MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC); +/* unsafe version; does not check buffer overflow */ + +MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits); +/* faster, but works only if nbBits >= 1 */ + + + +/*-************************************************************** +* Internal functions +****************************************************************/ +MEM_STATIC unsigned BIT_highbit32 (U32 val) +{ + assert(val != 0); + { +# if (__GNUC__ >= 3) /* Use GCC Intrinsic */ + return __builtin_clz (val) ^ 31; +# else /* Software version */ + static const unsigned DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, + 11, 14, 16, 18, 22, 25, 3, 30, + 8, 12, 20, 28, 15, 17, 24, 7, + 19, 27, 23, 6, 26, 5, 4, 31 }; + U32 v = val; + v |= v >> 1; + v |= v >> 2; + v |= v >> 4; + v |= v >> 8; + v |= v >> 16; + return DeBruijnClz[ (U32) (v * 0x07C4ACDDU) >> 27]; +# endif + } +} + +/*===== Local Constants =====*/ +static const unsigned BIT_mask[] = { + 0, 1, 3, 7, 0xF, 0x1F, + 0x3F, 0x7F, 0xFF, 0x1FF, 0x3FF, 0x7FF, + 0xFFF, 0x1FFF, 0x3FFF, 0x7FFF, 0xFFFF, 0x1FFFF, + 0x3FFFF, 0x7FFFF, 0xFFFFF, 0x1FFFFF, 0x3FFFFF, 0x7FFFFF, + 0xFFFFFF, 0x1FFFFFF, 0x3FFFFFF, 0x7FFFFFF, 0xFFFFFFF, 0x1FFFFFFF, + 0x3FFFFFFF, 0x7FFFFFFF}; /* up to 31 bits */ +#define BIT_MASK_SIZE (sizeof(BIT_mask) / sizeof(BIT_mask[0])) + +/*-************************************************************** +* bitStream encoding +****************************************************************/ +/*! BIT_initCStream() : + * `dstCapacity` must be > sizeof(size_t) + * @return : 0 if success, + * otherwise an error code (can be tested using ERR_isError()) */ +MEM_STATIC size_t BIT_initCStream(BIT_CStream_t* bitC, + void* startPtr, size_t dstCapacity) +{ + bitC->bitContainer = 0; + bitC->bitPos = 0; + bitC->startPtr = (char*)startPtr; + bitC->ptr = bitC->startPtr; + bitC->endPtr = bitC->startPtr + dstCapacity - sizeof(bitC->bitContainer); + if (dstCapacity <= sizeof(bitC->bitContainer)) return ERROR(dstSize_tooSmall); + return 0; +} + +/*! BIT_addBits() : + * can add up to 31 bits into `bitC`. + * Note : does not check for register overflow ! */ +MEM_STATIC void BIT_addBits(BIT_CStream_t* bitC, + size_t value, unsigned nbBits) +{ + DEBUG_STATIC_ASSERT(BIT_MASK_SIZE == 32); + assert(nbBits < BIT_MASK_SIZE); + assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); + bitC->bitContainer |= (value & BIT_mask[nbBits]) << bitC->bitPos; + bitC->bitPos += nbBits; +} + +/*! BIT_addBitsFast() : + * works only if `value` is _clean_, + * meaning all high bits above nbBits are 0 */ +MEM_STATIC void BIT_addBitsFast(BIT_CStream_t* bitC, + size_t value, unsigned nbBits) +{ + assert((value>>nbBits) == 0); + assert(nbBits + bitC->bitPos < sizeof(bitC->bitContainer) * 8); + bitC->bitContainer |= value << bitC->bitPos; + bitC->bitPos += nbBits; +} + +/*! BIT_flushBitsFast() : + * assumption : bitContainer has not overflowed + * unsafe version; does not check buffer overflow */ +MEM_STATIC void BIT_flushBitsFast(BIT_CStream_t* bitC) +{ + size_t const nbBytes = bitC->bitPos >> 3; + assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); + assert(bitC->ptr <= bitC->endPtr); + MEM_writeLEST(bitC->ptr, bitC->bitContainer); + bitC->ptr += nbBytes; + bitC->bitPos &= 7; + bitC->bitContainer >>= nbBytes*8; +} + +/*! BIT_flushBits() : + * assumption : bitContainer has not overflowed + * safe version; check for buffer overflow, and prevents it. + * note : does not signal buffer overflow. + * overflow will be revealed later on using BIT_closeCStream() */ +MEM_STATIC void BIT_flushBits(BIT_CStream_t* bitC) +{ + size_t const nbBytes = bitC->bitPos >> 3; + assert(bitC->bitPos < sizeof(bitC->bitContainer) * 8); + assert(bitC->ptr <= bitC->endPtr); + MEM_writeLEST(bitC->ptr, bitC->bitContainer); + bitC->ptr += nbBytes; + if (bitC->ptr > bitC->endPtr) bitC->ptr = bitC->endPtr; + bitC->bitPos &= 7; + bitC->bitContainer >>= nbBytes*8; +} + +/*! BIT_closeCStream() : + * @return : size of CStream, in bytes, + * or 0 if it could not fit into dstBuffer */ +MEM_STATIC size_t BIT_closeCStream(BIT_CStream_t* bitC) +{ + BIT_addBitsFast(bitC, 1, 1); /* endMark */ + BIT_flushBits(bitC); + if (bitC->ptr >= bitC->endPtr) return 0; /* overflow detected */ + return (bitC->ptr - bitC->startPtr) + (bitC->bitPos > 0); +} + + +/*-******************************************************** +* bitStream decoding +**********************************************************/ +/*! BIT_initDStream() : + * Initialize a BIT_DStream_t. + * `bitD` : a pointer to an already allocated BIT_DStream_t structure. + * `srcSize` must be the *exact* size of the bitStream, in bytes. + * @return : size of stream (== srcSize), or an errorCode if a problem is detected + */ +MEM_STATIC size_t BIT_initDStream(BIT_DStream_t* bitD, const void* srcBuffer, size_t srcSize) +{ + if (srcSize < 1) { ZSTD_memset(bitD, 0, sizeof(*bitD)); return ERROR(srcSize_wrong); } + + bitD->start = (const char*)srcBuffer; + bitD->limitPtr = bitD->start + sizeof(bitD->bitContainer); + + if (srcSize >= sizeof(bitD->bitContainer)) { /* normal case */ + bitD->ptr = (const char*)srcBuffer + srcSize - sizeof(bitD->bitContainer); + bitD->bitContainer = MEM_readLEST(bitD->ptr); + { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; + bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; /* ensures bitsConsumed is always set */ + if (lastByte == 0) return ERROR(GENERIC); /* endMark not present */ } + } else { + bitD->ptr = bitD->start; + bitD->bitContainer = *(const BYTE*)(bitD->start); + switch(srcSize) + { + case 7: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[6]) << (sizeof(bitD->bitContainer)*8 - 16); + ZSTD_FALLTHROUGH; + + case 6: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[5]) << (sizeof(bitD->bitContainer)*8 - 24); + ZSTD_FALLTHROUGH; + + case 5: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[4]) << (sizeof(bitD->bitContainer)*8 - 32); + ZSTD_FALLTHROUGH; + + case 4: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[3]) << 24; + ZSTD_FALLTHROUGH; + + case 3: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[2]) << 16; + ZSTD_FALLTHROUGH; + + case 2: bitD->bitContainer += (size_t)(((const BYTE*)(srcBuffer))[1]) << 8; + ZSTD_FALLTHROUGH; + + default: break; + } + { BYTE const lastByte = ((const BYTE*)srcBuffer)[srcSize-1]; + bitD->bitsConsumed = lastByte ? 8 - BIT_highbit32(lastByte) : 0; + if (lastByte == 0) return ERROR(corruption_detected); /* endMark not present */ + } + bitD->bitsConsumed += (U32)(sizeof(bitD->bitContainer) - srcSize)*8; + } + + return srcSize; +} + +MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getUpperBits(size_t bitContainer, U32 const start) +{ + return bitContainer >> start; +} + +MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits) +{ + U32 const regMask = sizeof(bitContainer)*8 - 1; + /* if start > regMask, bitstream is corrupted, and result is undefined */ + assert(nbBits < BIT_MASK_SIZE); + return (bitContainer >> (start & regMask)) & BIT_mask[nbBits]; +} + +MEM_STATIC FORCE_INLINE_ATTR size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits) +{ + assert(nbBits < BIT_MASK_SIZE); + return bitContainer & BIT_mask[nbBits]; +} + +/*! BIT_lookBits() : + * Provides next n bits from local register. + * local register is not modified. + * On 32-bits, maxNbBits==24. + * On 64-bits, maxNbBits==56. + * @return : value extracted */ +MEM_STATIC FORCE_INLINE_ATTR size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits) +{ + /* arbitrate between double-shift and shift+mask */ +#if 1 + /* if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8, + * bitstream is likely corrupted, and result is undefined */ + return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits); +#else + /* this code path is slower on my os-x laptop */ + U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; + return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask); +#endif +} + +/*! BIT_lookBitsFast() : + * unsafe version; only works if nbBits >= 1 */ +MEM_STATIC size_t BIT_lookBitsFast(const BIT_DStream_t* bitD, U32 nbBits) +{ + U32 const regMask = sizeof(bitD->bitContainer)*8 - 1; + assert(nbBits >= 1); + return (bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> (((regMask+1)-nbBits) & regMask); +} + +MEM_STATIC FORCE_INLINE_ATTR void BIT_skipBits(BIT_DStream_t* bitD, U32 nbBits) +{ + bitD->bitsConsumed += nbBits; +} + +/*! BIT_readBits() : + * Read (consume) next n bits from local register and update. + * Pay attention to not read more than nbBits contained into local register. + * @return : extracted value. */ +MEM_STATIC FORCE_INLINE_ATTR size_t BIT_readBits(BIT_DStream_t* bitD, unsigned nbBits) +{ + size_t const value = BIT_lookBits(bitD, nbBits); + BIT_skipBits(bitD, nbBits); + return value; +} + +/*! BIT_readBitsFast() : + * unsafe version; only works only if nbBits >= 1 */ +MEM_STATIC size_t BIT_readBitsFast(BIT_DStream_t* bitD, unsigned nbBits) +{ + size_t const value = BIT_lookBitsFast(bitD, nbBits); + assert(nbBits >= 1); + BIT_skipBits(bitD, nbBits); + return value; +} + +/*! BIT_reloadDStreamFast() : + * Similar to BIT_reloadDStream(), but with two differences: + * 1. bitsConsumed <= sizeof(bitD->bitContainer)*8 must hold! + * 2. Returns BIT_DStream_overflow when bitD->ptr < bitD->limitPtr, at this + * point you must use BIT_reloadDStream() to reload. + */ +MEM_STATIC BIT_DStream_status BIT_reloadDStreamFast(BIT_DStream_t* bitD) +{ + if (UNLIKELY(bitD->ptr < bitD->limitPtr)) + return BIT_DStream_overflow; + assert(bitD->bitsConsumed <= sizeof(bitD->bitContainer)*8); + bitD->ptr -= bitD->bitsConsumed >> 3; + bitD->bitsConsumed &= 7; + bitD->bitContainer = MEM_readLEST(bitD->ptr); + return BIT_DStream_unfinished; +} + +/*! BIT_reloadDStream() : + * Refill `bitD` from buffer previously set in BIT_initDStream() . + * This function is safe, it guarantees it will not read beyond src buffer. + * @return : status of `BIT_DStream_t` internal register. + * when status == BIT_DStream_unfinished, internal register is filled with at least 25 or 57 bits */ +MEM_STATIC BIT_DStream_status BIT_reloadDStream(BIT_DStream_t* bitD) +{ + if (bitD->bitsConsumed > (sizeof(bitD->bitContainer)*8)) /* overflow detected, like end of stream */ + return BIT_DStream_overflow; + + if (bitD->ptr >= bitD->limitPtr) { + return BIT_reloadDStreamFast(bitD); + } + if (bitD->ptr == bitD->start) { + if (bitD->bitsConsumed < sizeof(bitD->bitContainer)*8) return BIT_DStream_endOfBuffer; + return BIT_DStream_completed; + } + /* start < ptr < limitPtr */ + { U32 nbBytes = bitD->bitsConsumed >> 3; + BIT_DStream_status result = BIT_DStream_unfinished; + if (bitD->ptr - nbBytes < bitD->start) { + nbBytes = (U32)(bitD->ptr - bitD->start); /* ptr > start */ + result = BIT_DStream_endOfBuffer; + } + bitD->ptr -= nbBytes; + bitD->bitsConsumed -= nbBytes*8; + bitD->bitContainer = MEM_readLEST(bitD->ptr); /* reminder : srcSize > sizeof(bitD->bitContainer), otherwise bitD->ptr == bitD->start */ + return result; + } +} + +/*! BIT_endOfDStream() : + * @return : 1 if DStream has _exactly_ reached its end (all bits consumed). + */ +MEM_STATIC unsigned BIT_endOfDStream(const BIT_DStream_t* DStream) +{ + return ((DStream->ptr == DStream->start) && (DStream->bitsConsumed == sizeof(DStream->bitContainer)*8)); +} + + +#endif /* BITSTREAM_H_MODULE */ diff --git a/lib/zstd/common/compiler.h b/lib/zstd/common/compiler.h new file mode 100644 index 000000000000..a1a051e4bce6 --- /dev/null +++ b/lib/zstd/common/compiler.h @@ -0,0 +1,170 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_COMPILER_H +#define ZSTD_COMPILER_H + +/*-******************************************************* +* Compiler specifics +*********************************************************/ +/* force inlining */ + +#if (defined(__GNUC__) && !defined(__STRICT_ANSI__)) || defined(__cplusplus) || defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# define INLINE_KEYWORD inline +#else +# define INLINE_KEYWORD +#endif + +#define FORCE_INLINE_ATTR __attribute__((always_inline)) + + +/* + On MSVC qsort requires that functions passed into it use the __cdecl calling conversion(CC). + This explictly marks such functions as __cdecl so that the code will still compile + if a CC other than __cdecl has been made the default. +*/ +#define WIN_CDECL + +/* + * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant + * parameters. They must be inlined for the compiler to eliminate the constant + * branches. + */ +#define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR +/* + * HINT_INLINE is used to help the compiler generate better code. It is *not* + * used for "templates", so it can be tweaked based on the compilers + * performance. + * + * gcc-4.8 and gcc-4.9 have been shown to benefit from leaving off the + * always_inline attribute. + * + * clang up to 5.0.0 (trunk) benefit tremendously from the always_inline + * attribute. + */ +#if !defined(__clang__) && defined(__GNUC__) && __GNUC__ >= 4 && __GNUC_MINOR__ >= 8 && __GNUC__ < 5 +# define HINT_INLINE static INLINE_KEYWORD +#else +# define HINT_INLINE static INLINE_KEYWORD FORCE_INLINE_ATTR +#endif + +/* UNUSED_ATTR tells the compiler it is okay if the function is unused. */ +#define UNUSED_ATTR __attribute__((unused)) + +/* force no inlining */ +#define FORCE_NOINLINE static __attribute__((__noinline__)) + + +/* target attribute */ +#ifndef __has_attribute + #define __has_attribute(x) 0 /* Compatibility with non-clang compilers. */ +#endif +#define TARGET_ATTRIBUTE(target) __attribute__((__target__(target))) + +/* Enable runtime BMI2 dispatch based on the CPU. + * Enabled for clang & gcc >=4.8 on x86 when BMI2 isn't enabled by default. + */ +#ifndef DYNAMIC_BMI2 + #if ((defined(__clang__) && __has_attribute(__target__)) \ + || (defined(__GNUC__) \ + && (__GNUC__ >= 5 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 8)))) \ + && (defined(__x86_64__) || defined(_M_X86)) \ + && !defined(__BMI2__) + # define DYNAMIC_BMI2 1 + #else + # define DYNAMIC_BMI2 0 + #endif +#endif + +/* prefetch + * can be disabled, by declaring NO_PREFETCH build macro */ +#if ( (__GNUC__ >= 4) || ( (__GNUC__ == 3) && (__GNUC_MINOR__ >= 1) ) ) +# define PREFETCH_L1(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 3 /* locality */) +# define PREFETCH_L2(ptr) __builtin_prefetch((ptr), 0 /* rw==read */, 2 /* locality */) +#elif defined(__aarch64__) +# define PREFETCH_L1(ptr) __asm__ __volatile__("prfm pldl1keep, %0" ::"Q"(*(ptr))) +# define PREFETCH_L2(ptr) __asm__ __volatile__("prfm pldl2keep, %0" ::"Q"(*(ptr))) +#else +# define PREFETCH_L1(ptr) (void)(ptr) /* disabled */ +# define PREFETCH_L2(ptr) (void)(ptr) /* disabled */ +#endif /* NO_PREFETCH */ + +#define CACHELINE_SIZE 64 + +#define PREFETCH_AREA(p, s) { \ + const char* const _ptr = (const char*)(p); \ + size_t const _size = (size_t)(s); \ + size_t _pos; \ + for (_pos=0; _pos<_size; _pos+=CACHELINE_SIZE) { \ + PREFETCH_L2(_ptr + _pos); \ + } \ +} + +/* vectorization + * older GCC (pre gcc-4.3 picked as the cutoff) uses a different syntax */ +#if !defined(__INTEL_COMPILER) && !defined(__clang__) && defined(__GNUC__) +# if (__GNUC__ == 4 && __GNUC_MINOR__ > 3) || (__GNUC__ >= 5) +# define DONT_VECTORIZE __attribute__((optimize("no-tree-vectorize"))) +# else +# define DONT_VECTORIZE _Pragma("GCC optimize(\"no-tree-vectorize\")") +# endif +#else +# define DONT_VECTORIZE +#endif + +/* Tell the compiler that a branch is likely or unlikely. + * Only use these macros if it causes the compiler to generate better code. + * If you can remove a LIKELY/UNLIKELY annotation without speed changes in gcc + * and clang, please do. + */ +#define LIKELY(x) (__builtin_expect((x), 1)) +#define UNLIKELY(x) (__builtin_expect((x), 0)) + +/* disable warnings */ + +/*Like DYNAMIC_BMI2 but for compile time determination of BMI2 support*/ + + +/* compat. with non-clang compilers */ +#ifndef __has_builtin +# define __has_builtin(x) 0 +#endif + +/* compat. with non-clang compilers */ +#ifndef __has_feature +# define __has_feature(x) 0 +#endif + +/* C-language Attributes are added in C23. */ +#if defined(__STDC_VERSION__) && (__STDC_VERSION__ > 201710L) && defined(__has_c_attribute) +# define ZSTD_HAS_C_ATTRIBUTE(x) __has_c_attribute(x) +#else +# define ZSTD_HAS_C_ATTRIBUTE(x) 0 +#endif + +/* Only use C++ attributes in C++. Some compilers report support for C++ + * attributes when compiling with C. + */ +#define ZSTD_HAS_CPP_ATTRIBUTE(x) 0 + +/* Define ZSTD_FALLTHROUGH macro for annotating switch case with the 'fallthrough' attribute. + * - C23: https://en.cppreference.com/w/c/language/attributes/fallthrough + * - CPP17: https://en.cppreference.com/w/cpp/language/attributes/fallthrough + * - Else: __attribute__((__fallthrough__)) + */ +#define ZSTD_FALLTHROUGH fallthrough + +/* detects whether we are being compiled under msan */ + + +/* detects whether we are being compiled under asan */ + + +#endif /* ZSTD_COMPILER_H */ diff --git a/lib/zstd/common/cpu.h b/lib/zstd/common/cpu.h new file mode 100644 index 000000000000..0db7b42407ee --- /dev/null +++ b/lib/zstd/common/cpu.h @@ -0,0 +1,194 @@ +/* + * Copyright (c) Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_COMMON_CPU_H +#define ZSTD_COMMON_CPU_H + +/* + * Implementation taken from folly/CpuId.h + * https://github.com/facebook/folly/blob/master/folly/CpuId.h + */ + +#include "mem.h" + + +typedef struct { + U32 f1c; + U32 f1d; + U32 f7b; + U32 f7c; +} ZSTD_cpuid_t; + +MEM_STATIC ZSTD_cpuid_t ZSTD_cpuid(void) { + U32 f1c = 0; + U32 f1d = 0; + U32 f7b = 0; + U32 f7c = 0; +#if defined(__i386__) && defined(__PIC__) && !defined(__clang__) && defined(__GNUC__) + /* The following block like the normal cpuid branch below, but gcc + * reserves ebx for use of its pic register so we must specially + * handle the save and restore to avoid clobbering the register + */ + U32 n; + __asm__( + "pushl %%ebx\n\t" + "cpuid\n\t" + "popl %%ebx\n\t" + : "=a"(n) + : "a"(0) + : "ecx", "edx"); + if (n >= 1) { + U32 f1a; + __asm__( + "pushl %%ebx\n\t" + "cpuid\n\t" + "popl %%ebx\n\t" + : "=a"(f1a), "=c"(f1c), "=d"(f1d) + : "a"(1)); + } + if (n >= 7) { + __asm__( + "pushl %%ebx\n\t" + "cpuid\n\t" + "movl %%ebx, %%eax\n\t" + "popl %%ebx" + : "=a"(f7b), "=c"(f7c) + : "a"(7), "c"(0) + : "edx"); + } +#elif defined(__x86_64__) || defined(_M_X64) || defined(__i386__) + U32 n; + __asm__("cpuid" : "=a"(n) : "a"(0) : "ebx", "ecx", "edx"); + if (n >= 1) { + U32 f1a; + __asm__("cpuid" : "=a"(f1a), "=c"(f1c), "=d"(f1d) : "a"(1) : "ebx"); + } + if (n >= 7) { + U32 f7a; + __asm__("cpuid" + : "=a"(f7a), "=b"(f7b), "=c"(f7c) + : "a"(7), "c"(0) + : "edx"); + } +#endif + { + ZSTD_cpuid_t cpuid; + cpuid.f1c = f1c; + cpuid.f1d = f1d; + cpuid.f7b = f7b; + cpuid.f7c = f7c; + return cpuid; + } +} + +#define X(name, r, bit) \ + MEM_STATIC int ZSTD_cpuid_##name(ZSTD_cpuid_t const cpuid) { \ + return ((cpuid.r) & (1U << bit)) != 0; \ + } + +/* cpuid(1): Processor Info and Feature Bits. */ +#define C(name, bit) X(name, f1c, bit) + C(sse3, 0) + C(pclmuldq, 1) + C(dtes64, 2) + C(monitor, 3) + C(dscpl, 4) + C(vmx, 5) + C(smx, 6) + C(eist, 7) + C(tm2, 8) + C(ssse3, 9) + C(cnxtid, 10) + C(fma, 12) + C(cx16, 13) + C(xtpr, 14) + C(pdcm, 15) + C(pcid, 17) + C(dca, 18) + C(sse41, 19) + C(sse42, 20) + C(x2apic, 21) + C(movbe, 22) + C(popcnt, 23) + C(tscdeadline, 24) + C(aes, 25) + C(xsave, 26) + C(osxsave, 27) + C(avx, 28) + C(f16c, 29) + C(rdrand, 30) +#undef C +#define D(name, bit) X(name, f1d, bit) + D(fpu, 0) + D(vme, 1) + D(de, 2) + D(pse, 3) + D(tsc, 4) + D(msr, 5) + D(pae, 6) + D(mce, 7) + D(cx8, 8) + D(apic, 9) + D(sep, 11) + D(mtrr, 12) + D(pge, 13) + D(mca, 14) + D(cmov, 15) + D(pat, 16) + D(pse36, 17) + D(psn, 18) + D(clfsh, 19) + D(ds, 21) + D(acpi, 22) + D(mmx, 23) + D(fxsr, 24) + D(sse, 25) + D(sse2, 26) + D(ss, 27) + D(htt, 28) + D(tm, 29) + D(pbe, 31) +#undef D + +/* cpuid(7): Extended Features. */ +#define B(name, bit) X(name, f7b, bit) + B(bmi1, 3) + B(hle, 4) + B(avx2, 5) + B(smep, 7) + B(bmi2, 8) + B(erms, 9) + B(invpcid, 10) + B(rtm, 11) + B(mpx, 14) + B(avx512f, 16) + B(avx512dq, 17) + B(rdseed, 18) + B(adx, 19) + B(smap, 20) + B(avx512ifma, 21) + B(pcommit, 22) + B(clflushopt, 23) + B(clwb, 24) + B(avx512pf, 26) + B(avx512er, 27) + B(avx512cd, 28) + B(sha, 29) + B(avx512bw, 30) + B(avx512vl, 31) +#undef B +#define C(name, bit) X(name, f7c, bit) + C(prefetchwt1, 0) + C(avx512vbmi, 1) +#undef C + +#undef X + +#endif /* ZSTD_COMMON_CPU_H */ diff --git a/lib/zstd/common/debug.c b/lib/zstd/common/debug.c new file mode 100644 index 000000000000..bb863c9ea616 --- /dev/null +++ b/lib/zstd/common/debug.c @@ -0,0 +1,24 @@ +/* ****************************************************************** + * debug + * Part of FSE library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + + +/* + * This module only hosts one global variable + * which can be used to dynamically influence the verbosity of traces, + * such as DEBUGLOG and RAWLOG + */ + +#include "debug.h" + +int g_debuglevel = DEBUGLEVEL; diff --git a/lib/zstd/common/debug.h b/lib/zstd/common/debug.h new file mode 100644 index 000000000000..6dd88d1fbd02 --- /dev/null +++ b/lib/zstd/common/debug.h @@ -0,0 +1,101 @@ +/* ****************************************************************** + * debug + * Part of FSE library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + + +/* + * The purpose of this header is to enable debug functions. + * They regroup assert(), DEBUGLOG() and RAWLOG() for run-time, + * and DEBUG_STATIC_ASSERT() for compile-time. + * + * By default, DEBUGLEVEL==0, which means run-time debug is disabled. + * + * Level 1 enables assert() only. + * Starting level 2, traces can be generated and pushed to stderr. + * The higher the level, the more verbose the traces. + * + * It's possible to dynamically adjust level using variable g_debug_level, + * which is only declared if DEBUGLEVEL>=2, + * and is a global variable, not multi-thread protected (use with care) + */ + +#ifndef DEBUG_H_12987983217 +#define DEBUG_H_12987983217 + + + +/* static assert is triggered at compile time, leaving no runtime artefact. + * static assert only works with compile-time constants. + * Also, this variant can only be used inside a function. */ +#define DEBUG_STATIC_ASSERT(c) (void)sizeof(char[(c) ? 1 : -1]) + + +/* DEBUGLEVEL is expected to be defined externally, + * typically through compiler command line. + * Value must be a number. */ +#ifndef DEBUGLEVEL +# define DEBUGLEVEL 0 +#endif + + +/* recommended values for DEBUGLEVEL : + * 0 : release mode, no debug, all run-time checks disabled + * 1 : enables assert() only, no display + * 2 : reserved, for currently active debug path + * 3 : events once per object lifetime (CCtx, CDict, etc.) + * 4 : events once per frame + * 5 : events once per block + * 6 : events once per sequence (verbose) + * 7+: events at every position (*very* verbose) + * + * It's generally inconvenient to output traces > 5. + * In which case, it's possible to selectively trigger high verbosity levels + * by modifying g_debug_level. + */ + +#if (DEBUGLEVEL>=1) +# define ZSTD_DEPS_NEED_ASSERT +# include "zstd_deps.h" +#else +# ifndef assert /* assert may be already defined, due to prior #include */ +# define assert(condition) ((void)0) /* disable assert (default) */ +# endif +#endif + +#if (DEBUGLEVEL>=2) +# define ZSTD_DEPS_NEED_IO +# include "zstd_deps.h" +extern int g_debuglevel; /* the variable is only declared, + it actually lives in debug.c, + and is shared by the whole process. + It's not thread-safe. + It's useful when enabling very verbose levels + on selective conditions (such as position in src) */ + +# define RAWLOG(l, ...) { \ + if (l<=g_debuglevel) { \ + ZSTD_DEBUG_PRINT(__VA_ARGS__); \ + } } +# define DEBUGLOG(l, ...) { \ + if (l<=g_debuglevel) { \ + ZSTD_DEBUG_PRINT(__FILE__ ": " __VA_ARGS__); \ + ZSTD_DEBUG_PRINT(" \n"); \ + } } +#else +# define RAWLOG(l, ...) {} /* disabled */ +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif + + + +#endif /* DEBUG_H_12987983217 */ diff --git a/lib/zstd/common/entropy_common.c b/lib/zstd/common/entropy_common.c new file mode 100644 index 000000000000..53b47a2b52ff --- /dev/null +++ b/lib/zstd/common/entropy_common.c @@ -0,0 +1,357 @@ +/* ****************************************************************** + * Common functions of New Generation Entropy library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy + * - Public forum : https://groups.google.com/forum/#!forum/lz4c + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + +/* ************************************* +* Dependencies +***************************************/ +#include "mem.h" +#include "error_private.h" /* ERR_*, ERROR */ +#define FSE_STATIC_LINKING_ONLY /* FSE_MIN_TABLELOG */ +#include "fse.h" +#define HUF_STATIC_LINKING_ONLY /* HUF_TABLELOG_ABSOLUTEMAX */ +#include "huf.h" + + +/*=== Version ===*/ +unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; } + + +/*=== Error Management ===*/ +unsigned FSE_isError(size_t code) { return ERR_isError(code); } +const char* FSE_getErrorName(size_t code) { return ERR_getErrorName(code); } + +unsigned HUF_isError(size_t code) { return ERR_isError(code); } +const char* HUF_getErrorName(size_t code) { return ERR_getErrorName(code); } + + +/*-************************************************************** +* FSE NCount encoding-decoding +****************************************************************/ +static U32 FSE_ctz(U32 val) +{ + assert(val != 0); + { +# if (__GNUC__ >= 3) /* GCC Intrinsic */ + return __builtin_ctz(val); +# else /* Software version */ + U32 count = 0; + while ((val & 1) == 0) { + val >>= 1; + ++count; + } + return count; +# endif + } +} + +FORCE_INLINE_TEMPLATE +size_t FSE_readNCount_body(short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr, + const void* headerBuffer, size_t hbSize) +{ + const BYTE* const istart = (const BYTE*) headerBuffer; + const BYTE* const iend = istart + hbSize; + const BYTE* ip = istart; + int nbBits; + int remaining; + int threshold; + U32 bitStream; + int bitCount; + unsigned charnum = 0; + unsigned const maxSV1 = *maxSVPtr + 1; + int previous0 = 0; + + if (hbSize < 8) { + /* This function only works when hbSize >= 8 */ + char buffer[8] = {0}; + ZSTD_memcpy(buffer, headerBuffer, hbSize); + { size_t const countSize = FSE_readNCount(normalizedCounter, maxSVPtr, tableLogPtr, + buffer, sizeof(buffer)); + if (FSE_isError(countSize)) return countSize; + if (countSize > hbSize) return ERROR(corruption_detected); + return countSize; + } } + assert(hbSize >= 8); + + /* init */ + ZSTD_memset(normalizedCounter, 0, (*maxSVPtr+1) * sizeof(normalizedCounter[0])); /* all symbols not present in NCount have a frequency of 0 */ + bitStream = MEM_readLE32(ip); + nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG; /* extract tableLog */ + if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX) return ERROR(tableLog_tooLarge); + bitStream >>= 4; + bitCount = 4; + *tableLogPtr = nbBits; + remaining = (1<> 1; + while (repeats >= 12) { + charnum += 3 * 12; + if (LIKELY(ip <= iend-7)) { + ip += 3; + } else { + bitCount -= (int)(8 * (iend - 7 - ip)); + bitCount &= 31; + ip = iend - 4; + } + bitStream = MEM_readLE32(ip) >> bitCount; + repeats = FSE_ctz(~bitStream | 0x80000000) >> 1; + } + charnum += 3 * repeats; + bitStream >>= 2 * repeats; + bitCount += 2 * repeats; + + /* Add the final repeat which isn't 0b11. */ + assert((bitStream & 3) < 3); + charnum += bitStream & 3; + bitCount += 2; + + /* This is an error, but break and return an error + * at the end, because returning out of a loop makes + * it harder for the compiler to optimize. + */ + if (charnum >= maxSV1) break; + + /* We don't need to set the normalized count to 0 + * because we already memset the whole buffer to 0. + */ + + if (LIKELY(ip <= iend-7) || (ip + (bitCount>>3) <= iend-4)) { + assert((bitCount >> 3) <= 3); /* For first condition to work */ + ip += bitCount>>3; + bitCount &= 7; + } else { + bitCount -= (int)(8 * (iend - 4 - ip)); + bitCount &= 31; + ip = iend - 4; + } + bitStream = MEM_readLE32(ip) >> bitCount; + } + { + int const max = (2*threshold-1) - remaining; + int count; + + if ((bitStream & (threshold-1)) < (U32)max) { + count = bitStream & (threshold-1); + bitCount += nbBits-1; + } else { + count = bitStream & (2*threshold-1); + if (count >= threshold) count -= max; + bitCount += nbBits; + } + + count--; /* extra accuracy */ + /* When it matters (small blocks), this is a + * predictable branch, because we don't use -1. + */ + if (count >= 0) { + remaining -= count; + } else { + assert(count == -1); + remaining += count; + } + normalizedCounter[charnum++] = (short)count; + previous0 = !count; + + assert(threshold > 1); + if (remaining < threshold) { + /* This branch can be folded into the + * threshold update condition because we + * know that threshold > 1. + */ + if (remaining <= 1) break; + nbBits = BIT_highbit32(remaining) + 1; + threshold = 1 << (nbBits - 1); + } + if (charnum >= maxSV1) break; + + if (LIKELY(ip <= iend-7) || (ip + (bitCount>>3) <= iend-4)) { + ip += bitCount>>3; + bitCount &= 7; + } else { + bitCount -= (int)(8 * (iend - 4 - ip)); + bitCount &= 31; + ip = iend - 4; + } + bitStream = MEM_readLE32(ip) >> bitCount; + } } + if (remaining != 1) return ERROR(corruption_detected); + /* Only possible when there are too many zeros. */ + if (charnum > maxSV1) return ERROR(maxSymbolValue_tooSmall); + if (bitCount > 32) return ERROR(corruption_detected); + *maxSVPtr = charnum-1; + + ip += (bitCount+7)>>3; + return ip-istart; +} + +/* Avoids the FORCE_INLINE of the _body() function. */ +static size_t FSE_readNCount_body_default( + short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr, + const void* headerBuffer, size_t hbSize) +{ + return FSE_readNCount_body(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize); +} + +#if DYNAMIC_BMI2 +TARGET_ATTRIBUTE("bmi2") static size_t FSE_readNCount_body_bmi2( + short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr, + const void* headerBuffer, size_t hbSize) +{ + return FSE_readNCount_body(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize); +} +#endif + +size_t FSE_readNCount_bmi2( + short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr, + const void* headerBuffer, size_t hbSize, int bmi2) +{ +#if DYNAMIC_BMI2 + if (bmi2) { + return FSE_readNCount_body_bmi2(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize); + } +#endif + (void)bmi2; + return FSE_readNCount_body_default(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize); +} + +size_t FSE_readNCount( + short* normalizedCounter, unsigned* maxSVPtr, unsigned* tableLogPtr, + const void* headerBuffer, size_t hbSize) +{ + return FSE_readNCount_bmi2(normalizedCounter, maxSVPtr, tableLogPtr, headerBuffer, hbSize, /* bmi2 */ 0); +} + + +/*! HUF_readStats() : + Read compact Huffman tree, saved by HUF_writeCTable(). + `huffWeight` is destination buffer. + `rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32. + @return : size read from `src` , or an error Code . + Note : Needed by HUF_readCTable() and HUF_readDTableX?() . +*/ +size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, U32* rankStats, + U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize) +{ + U32 wksp[HUF_READ_STATS_WORKSPACE_SIZE_U32]; + return HUF_readStats_wksp(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, wksp, sizeof(wksp), /* bmi2 */ 0); +} + +FORCE_INLINE_TEMPLATE size_t +HUF_readStats_body(BYTE* huffWeight, size_t hwSize, U32* rankStats, + U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize, + void* workSpace, size_t wkspSize, + int bmi2) +{ + U32 weightTotal; + const BYTE* ip = (const BYTE*) src; + size_t iSize; + size_t oSize; + + if (!srcSize) return ERROR(srcSize_wrong); + iSize = ip[0]; + /* ZSTD_memset(huffWeight, 0, hwSize); *//* is not necessary, even though some analyzer complain ... */ + + if (iSize >= 128) { /* special header */ + oSize = iSize - 127; + iSize = ((oSize+1)/2); + if (iSize+1 > srcSize) return ERROR(srcSize_wrong); + if (oSize >= hwSize) return ERROR(corruption_detected); + ip += 1; + { U32 n; + for (n=0; n> 4; + huffWeight[n+1] = ip[n/2] & 15; + } } } + else { /* header compressed with FSE (normal case) */ + if (iSize+1 > srcSize) return ERROR(srcSize_wrong); + /* max (hwSize-1) values decoded, as last one is implied */ + oSize = FSE_decompress_wksp_bmi2(huffWeight, hwSize-1, ip+1, iSize, 6, workSpace, wkspSize, bmi2); + if (FSE_isError(oSize)) return oSize; + } + + /* collect weight stats */ + ZSTD_memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32)); + weightTotal = 0; + { U32 n; for (n=0; n= HUF_TABLELOG_MAX) return ERROR(corruption_detected); + rankStats[huffWeight[n]]++; + weightTotal += (1 << huffWeight[n]) >> 1; + } } + if (weightTotal == 0) return ERROR(corruption_detected); + + /* get last non-null symbol weight (implied, total must be 2^n) */ + { U32 const tableLog = BIT_highbit32(weightTotal) + 1; + if (tableLog > HUF_TABLELOG_MAX) return ERROR(corruption_detected); + *tableLogPtr = tableLog; + /* determine last weight */ + { U32 const total = 1 << tableLog; + U32 const rest = total - weightTotal; + U32 const verif = 1 << BIT_highbit32(rest); + U32 const lastWeight = BIT_highbit32(rest) + 1; + if (verif != rest) return ERROR(corruption_detected); /* last value must be a clean power of 2 */ + huffWeight[oSize] = (BYTE)lastWeight; + rankStats[lastWeight]++; + } } + + /* check tree construction validity */ + if ((rankStats[1] < 2) || (rankStats[1] & 1)) return ERROR(corruption_detected); /* by construction : at least 2 elts of rank 1, must be even */ + + /* results */ + *nbSymbolsPtr = (U32)(oSize+1); + return iSize+1; +} + +/* Avoids the FORCE_INLINE of the _body() function. */ +static size_t HUF_readStats_body_default(BYTE* huffWeight, size_t hwSize, U32* rankStats, + U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize, + void* workSpace, size_t wkspSize) +{ + return HUF_readStats_body(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize, 0); +} + +#if DYNAMIC_BMI2 +static TARGET_ATTRIBUTE("bmi2") size_t HUF_readStats_body_bmi2(BYTE* huffWeight, size_t hwSize, U32* rankStats, + U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize, + void* workSpace, size_t wkspSize) +{ + return HUF_readStats_body(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize, 1); +} +#endif + +size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize, U32* rankStats, + U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize, + void* workSpace, size_t wkspSize, + int bmi2) +{ +#if DYNAMIC_BMI2 + if (bmi2) { + return HUF_readStats_body_bmi2(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize); + } +#endif + (void)bmi2; + return HUF_readStats_body_default(huffWeight, hwSize, rankStats, nbSymbolsPtr, tableLogPtr, src, srcSize, workSpace, wkspSize); +} diff --git a/lib/zstd/common/error_private.c b/lib/zstd/common/error_private.c new file mode 100644 index 000000000000..6d1135f8c373 --- /dev/null +++ b/lib/zstd/common/error_private.c @@ -0,0 +1,56 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* The purpose of this file is to have a single list of error strings embedded in binary */ + +#include "error_private.h" + +const char* ERR_getErrorString(ERR_enum code) +{ +#ifdef ZSTD_STRIP_ERROR_STRINGS + (void)code; + return "Error strings stripped"; +#else + static const char* const notErrorCode = "Unspecified error code"; + switch( code ) + { + case PREFIX(no_error): return "No error detected"; + case PREFIX(GENERIC): return "Error (generic)"; + case PREFIX(prefix_unknown): return "Unknown frame descriptor"; + case PREFIX(version_unsupported): return "Version not supported"; + case PREFIX(frameParameter_unsupported): return "Unsupported frame parameter"; + case PREFIX(frameParameter_windowTooLarge): return "Frame requires too much memory for decoding"; + case PREFIX(corruption_detected): return "Corrupted block detected"; + case PREFIX(checksum_wrong): return "Restored data doesn't match checksum"; + case PREFIX(parameter_unsupported): return "Unsupported parameter"; + case PREFIX(parameter_outOfBound): return "Parameter is out of bound"; + case PREFIX(init_missing): return "Context should be init first"; + case PREFIX(memory_allocation): return "Allocation error : not enough memory"; + case PREFIX(workSpace_tooSmall): return "workSpace buffer is not large enough"; + case PREFIX(stage_wrong): return "Operation not authorized at current processing stage"; + case PREFIX(tableLog_tooLarge): return "tableLog requires too much memory : unsupported"; + case PREFIX(maxSymbolValue_tooLarge): return "Unsupported max Symbol Value : too large"; + case PREFIX(maxSymbolValue_tooSmall): return "Specified maxSymbolValue is too small"; + case PREFIX(dictionary_corrupted): return "Dictionary is corrupted"; + case PREFIX(dictionary_wrong): return "Dictionary mismatch"; + case PREFIX(dictionaryCreation_failed): return "Cannot create Dictionary from provided samples"; + case PREFIX(dstSize_tooSmall): return "Destination buffer is too small"; + case PREFIX(srcSize_wrong): return "Src size is incorrect"; + case PREFIX(dstBuffer_null): return "Operation on NULL destination buffer"; + /* following error codes are not stable and may be removed or changed in a future version */ + case PREFIX(frameIndex_tooLarge): return "Frame index is too large"; + case PREFIX(seekableIO): return "An I/O error occurred when reading/seeking"; + case PREFIX(dstBuffer_wrong): return "Destination buffer is wrong"; + case PREFIX(srcBuffer_wrong): return "Source buffer is wrong"; + case PREFIX(maxCode): + default: return notErrorCode; + } +#endif +} diff --git a/lib/zstd/common/error_private.h b/lib/zstd/common/error_private.h new file mode 100644 index 000000000000..d14e686adf95 --- /dev/null +++ b/lib/zstd/common/error_private.h @@ -0,0 +1,66 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* Note : this module is expected to remain private, do not expose it */ + +#ifndef ERROR_H_MODULE +#define ERROR_H_MODULE + + + +/* **************************************** +* Dependencies +******************************************/ +#include "zstd_deps.h" /* size_t */ +#include /* enum list */ + + +/* **************************************** +* Compiler-specific +******************************************/ +#define ERR_STATIC static __attribute__((unused)) + + +/*-**************************************** +* Customization (error_public.h) +******************************************/ +typedef ZSTD_ErrorCode ERR_enum; +#define PREFIX(name) ZSTD_error_##name + + +/*-**************************************** +* Error codes handling +******************************************/ +#undef ERROR /* already defined on Visual Studio */ +#define ERROR(name) ZSTD_ERROR(name) +#define ZSTD_ERROR(name) ((size_t)-PREFIX(name)) + +ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); } + +ERR_STATIC ERR_enum ERR_getErrorCode(size_t code) { if (!ERR_isError(code)) return (ERR_enum)0; return (ERR_enum) (0-code); } + +/* check and forward error code */ +#define CHECK_V_F(e, f) size_t const e = f; if (ERR_isError(e)) return e +#define CHECK_F(f) { CHECK_V_F(_var_err__, f); } + + +/*-**************************************** +* Error Strings +******************************************/ + +const char* ERR_getErrorString(ERR_enum code); /* error_private.c */ + +ERR_STATIC const char* ERR_getErrorName(size_t code) +{ + return ERR_getErrorString(ERR_getErrorCode(code)); +} + + +#endif /* ERROR_H_MODULE */ diff --git a/lib/zstd/common/fse.h b/lib/zstd/common/fse.h new file mode 100644 index 000000000000..0bb174c2c367 --- /dev/null +++ b/lib/zstd/common/fse.h @@ -0,0 +1,710 @@ +/* ****************************************************************** + * FSE : Finite State Entropy codec + * Public Prototypes declaration + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + + +#ifndef FSE_H +#define FSE_H + + +/*-***************************************** +* Dependencies +******************************************/ +#include "zstd_deps.h" /* size_t, ptrdiff_t */ + + +/*-***************************************** +* FSE_PUBLIC_API : control library symbols visibility +******************************************/ +#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4) +# define FSE_PUBLIC_API __attribute__ ((visibility ("default"))) +#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */ +# define FSE_PUBLIC_API __declspec(dllexport) +#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1) +# define FSE_PUBLIC_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#else +# define FSE_PUBLIC_API +#endif + +/*------ Version ------*/ +#define FSE_VERSION_MAJOR 0 +#define FSE_VERSION_MINOR 9 +#define FSE_VERSION_RELEASE 0 + +#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE +#define FSE_QUOTE(str) #str +#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str) +#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION) + +#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR *100*100 + FSE_VERSION_MINOR *100 + FSE_VERSION_RELEASE) +FSE_PUBLIC_API unsigned FSE_versionNumber(void); /*< library version number; to be used when checking dll version */ + + +/*-**************************************** +* FSE simple functions +******************************************/ +/*! FSE_compress() : + Compress content of buffer 'src', of size 'srcSize', into destination buffer 'dst'. + 'dst' buffer must be already allocated. Compression runs faster is dstCapacity >= FSE_compressBound(srcSize). + @return : size of compressed data (<= dstCapacity). + Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!! + if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression instead. + if FSE_isError(return), compression failed (more details using FSE_getErrorName()) +*/ +FSE_PUBLIC_API size_t FSE_compress(void* dst, size_t dstCapacity, + const void* src, size_t srcSize); + +/*! FSE_decompress(): + Decompress FSE data from buffer 'cSrc', of size 'cSrcSize', + into already allocated destination buffer 'dst', of size 'dstCapacity'. + @return : size of regenerated data (<= maxDstSize), + or an error code, which can be tested using FSE_isError() . + + ** Important ** : FSE_decompress() does not decompress non-compressible nor RLE data !!! + Why ? : making this distinction requires a header. + Header management is intentionally delegated to the user layer, which can better manage special cases. +*/ +FSE_PUBLIC_API size_t FSE_decompress(void* dst, size_t dstCapacity, + const void* cSrc, size_t cSrcSize); + + +/*-***************************************** +* Tool functions +******************************************/ +FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */ + +/* Error Management */ +FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */ +FSE_PUBLIC_API const char* FSE_getErrorName(size_t code); /* provides error code string (useful for debugging) */ + + +/*-***************************************** +* FSE advanced functions +******************************************/ +/*! FSE_compress2() : + Same as FSE_compress(), but allows the selection of 'maxSymbolValue' and 'tableLog' + Both parameters can be defined as '0' to mean : use default value + @return : size of compressed data + Special values : if return == 0, srcData is not compressible => Nothing is stored within cSrc !!! + if return == 1, srcData is a single byte symbol * srcSize times. Use RLE compression. + if FSE_isError(return), it's an error code. +*/ +FSE_PUBLIC_API size_t FSE_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog); + + +/*-***************************************** +* FSE detailed API +******************************************/ +/*! +FSE_compress() does the following: +1. count symbol occurrence from source[] into table count[] (see hist.h) +2. normalize counters so that sum(count[]) == Power_of_2 (2^tableLog) +3. save normalized counters to memory buffer using writeNCount() +4. build encoding table 'CTable' from normalized counters +5. encode the data stream using encoding table 'CTable' + +FSE_decompress() does the following: +1. read normalized counters with readNCount() +2. build decoding table 'DTable' from normalized counters +3. decode the data stream using decoding table 'DTable' + +The following API allows targeting specific sub-functions for advanced tasks. +For example, it's possible to compress several blocks using the same 'CTable', +or to save and provide normalized distribution using external method. +*/ + +/* *** COMPRESSION *** */ + +/*! FSE_optimalTableLog(): + dynamically downsize 'tableLog' when conditions are met. + It saves CPU time, by using smaller tables, while preserving or even improving compression ratio. + @return : recommended tableLog (necessarily <= 'maxTableLog') */ +FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); + +/*! FSE_normalizeCount(): + normalize counts so that sum(count[]) == Power_of_2 (2^tableLog) + 'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1). + useLowProbCount is a boolean parameter which trades off compressed size for + faster header decoding. When it is set to 1, the compressed data will be slightly + smaller. And when it is set to 0, FSE_readNCount() and FSE_buildDTable() will be + faster. If you are compressing a small amount of data (< 2 KB) then useLowProbCount=0 + is a good default, since header deserialization makes a big speed difference. + Otherwise, useLowProbCount=1 is a good default, since the speed difference is small. + @return : tableLog, + or an errorCode, which can be tested using FSE_isError() */ +FSE_PUBLIC_API size_t FSE_normalizeCount(short* normalizedCounter, unsigned tableLog, + const unsigned* count, size_t srcSize, unsigned maxSymbolValue, unsigned useLowProbCount); + +/*! FSE_NCountWriteBound(): + Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'. + Typically useful for allocation purpose. */ +FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog); + +/*! FSE_writeNCount(): + Compactly save 'normalizedCounter' into 'buffer'. + @return : size of the compressed table, + or an errorCode, which can be tested using FSE_isError(). */ +FSE_PUBLIC_API size_t FSE_writeNCount (void* buffer, size_t bufferSize, + const short* normalizedCounter, + unsigned maxSymbolValue, unsigned tableLog); + +/*! Constructor and Destructor of FSE_CTable. + Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */ +typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */ +FSE_PUBLIC_API FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog); +FSE_PUBLIC_API void FSE_freeCTable (FSE_CTable* ct); + +/*! FSE_buildCTable(): + Builds `ct`, which must be already allocated, using FSE_createCTable(). + @return : 0, or an errorCode, which can be tested using FSE_isError() */ +FSE_PUBLIC_API size_t FSE_buildCTable(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); + +/*! FSE_compress_usingCTable(): + Compress `src` using `ct` into `dst` which must be already allocated. + @return : size of compressed data (<= `dstCapacity`), + or 0 if compressed data could not fit into `dst`, + or an errorCode, which can be tested using FSE_isError() */ +FSE_PUBLIC_API size_t FSE_compress_usingCTable (void* dst, size_t dstCapacity, const void* src, size_t srcSize, const FSE_CTable* ct); + +/*! +Tutorial : +---------- +The first step is to count all symbols. FSE_count() does this job very fast. +Result will be saved into 'count', a table of unsigned int, which must be already allocated, and have 'maxSymbolValuePtr[0]+1' cells. +'src' is a table of bytes of size 'srcSize'. All values within 'src' MUST be <= maxSymbolValuePtr[0] +maxSymbolValuePtr[0] will be updated, with its real value (necessarily <= original value) +FSE_count() will return the number of occurrence of the most frequent symbol. +This can be used to know if there is a single symbol within 'src', and to quickly evaluate its compressibility. +If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()). + +The next step is to normalize the frequencies. +FSE_normalizeCount() will ensure that sum of frequencies is == 2 ^'tableLog'. +It also guarantees a minimum of 1 to any Symbol with frequency >= 1. +You can use 'tableLog'==0 to mean "use default tableLog value". +If you are unsure of which tableLog value to use, you can ask FSE_optimalTableLog(), +which will provide the optimal valid tableLog given sourceSize, maxSymbolValue, and a user-defined maximum (0 means "default"). + +The result of FSE_normalizeCount() will be saved into a table, +called 'normalizedCounter', which is a table of signed short. +'normalizedCounter' must be already allocated, and have at least 'maxSymbolValue+1' cells. +The return value is tableLog if everything proceeded as expected. +It is 0 if there is a single symbol within distribution. +If there is an error (ex: invalid tableLog value), the function will return an ErrorCode (which can be tested using FSE_isError()). + +'normalizedCounter' can be saved in a compact manner to a memory area using FSE_writeNCount(). +'buffer' must be already allocated. +For guaranteed success, buffer size must be at least FSE_headerBound(). +The result of the function is the number of bytes written into 'buffer'. +If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError(); ex : buffer size too small). + +'normalizedCounter' can then be used to create the compression table 'CTable'. +The space required by 'CTable' must be already allocated, using FSE_createCTable(). +You can then use FSE_buildCTable() to fill 'CTable'. +If there is an error, both functions will return an ErrorCode (which can be tested using FSE_isError()). + +'CTable' can then be used to compress 'src', with FSE_compress_usingCTable(). +Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize' +The function returns the size of compressed data (without header), necessarily <= `dstCapacity`. +If it returns '0', compressed data could not fit into 'dst'. +If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()). +*/ + + +/* *** DECOMPRESSION *** */ + +/*! FSE_readNCount(): + Read compactly saved 'normalizedCounter' from 'rBuffer'. + @return : size read from 'rBuffer', + or an errorCode, which can be tested using FSE_isError(). + maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */ +FSE_PUBLIC_API size_t FSE_readNCount (short* normalizedCounter, + unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, + const void* rBuffer, size_t rBuffSize); + +/*! FSE_readNCount_bmi2(): + * Same as FSE_readNCount() but pass bmi2=1 when your CPU supports BMI2 and 0 otherwise. + */ +FSE_PUBLIC_API size_t FSE_readNCount_bmi2(short* normalizedCounter, + unsigned* maxSymbolValuePtr, unsigned* tableLogPtr, + const void* rBuffer, size_t rBuffSize, int bmi2); + +/*! Constructor and Destructor of FSE_DTable. + Note that its size depends on 'tableLog' */ +typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */ +FSE_PUBLIC_API FSE_DTable* FSE_createDTable(unsigned tableLog); +FSE_PUBLIC_API void FSE_freeDTable(FSE_DTable* dt); + +/*! FSE_buildDTable(): + Builds 'dt', which must be already allocated, using FSE_createDTable(). + return : 0, or an errorCode, which can be tested using FSE_isError() */ +FSE_PUBLIC_API size_t FSE_buildDTable (FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); + +/*! FSE_decompress_usingDTable(): + Decompress compressed source `cSrc` of size `cSrcSize` using `dt` + into `dst` which must be already allocated. + @return : size of regenerated data (necessarily <= `dstCapacity`), + or an errorCode, which can be tested using FSE_isError() */ +FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, const FSE_DTable* dt); + +/*! +Tutorial : +---------- +(Note : these functions only decompress FSE-compressed blocks. + If block is uncompressed, use memcpy() instead + If block is a single repeated byte, use memset() instead ) + +The first step is to obtain the normalized frequencies of symbols. +This can be performed by FSE_readNCount() if it was saved using FSE_writeNCount(). +'normalizedCounter' must be already allocated, and have at least 'maxSymbolValuePtr[0]+1' cells of signed short. +In practice, that means it's necessary to know 'maxSymbolValue' beforehand, +or size the table to handle worst case situations (typically 256). +FSE_readNCount() will provide 'tableLog' and 'maxSymbolValue'. +The result of FSE_readNCount() is the number of bytes read from 'rBuffer'. +Note that 'rBufferSize' must be at least 4 bytes, even if useful information is less than that. +If there is an error, the function will return an error code, which can be tested using FSE_isError(). + +The next step is to build the decompression tables 'FSE_DTable' from 'normalizedCounter'. +This is performed by the function FSE_buildDTable(). +The space required by 'FSE_DTable' must be already allocated using FSE_createDTable(). +If there is an error, the function will return an error code, which can be tested using FSE_isError(). + +`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable(). +`cSrcSize` must be strictly correct, otherwise decompression will fail. +FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`). +If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small) +*/ + +#endif /* FSE_H */ + +#if !defined(FSE_H_FSE_STATIC_LINKING_ONLY) +#define FSE_H_FSE_STATIC_LINKING_ONLY + +/* *** Dependency *** */ +#include "bitstream.h" + + +/* ***************************************** +* Static allocation +*******************************************/ +/* FSE buffer bounds */ +#define FSE_NCOUNTBOUND 512 +#define FSE_BLOCKBOUND(size) ((size) + ((size)>>7) + 4 /* fse states */ + sizeof(size_t) /* bitContainer */) +#define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size)) /* Macro version, useful for static allocation */ + +/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */ +#define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) (1 + (1<<((maxTableLog)-1)) + (((maxSymbolValue)+1)*2)) +#define FSE_DTABLE_SIZE_U32(maxTableLog) (1 + (1<<(maxTableLog))) + +/* or use the size to malloc() space directly. Pay attention to alignment restrictions though */ +#define FSE_CTABLE_SIZE(maxTableLog, maxSymbolValue) (FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(FSE_CTable)) +#define FSE_DTABLE_SIZE(maxTableLog) (FSE_DTABLE_SIZE_U32(maxTableLog) * sizeof(FSE_DTable)) + + +/* ***************************************** + * FSE advanced API + ***************************************** */ + +unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus); +/*< same as FSE_optimalTableLog(), which used `minus==2` */ + +/* FSE_compress_wksp() : + * Same as FSE_compress2(), but using an externally allocated scratch buffer (`workSpace`). + * FSE_COMPRESS_WKSP_SIZE_U32() provides the minimum size required for `workSpace` as a table of FSE_CTable. + */ +#define FSE_COMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) ( FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) + ((maxTableLog > 12) ? (1 << (maxTableLog - 2)) : 1024) ) +size_t FSE_compress_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); + +size_t FSE_buildCTable_raw (FSE_CTable* ct, unsigned nbBits); +/*< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */ + +size_t FSE_buildCTable_rle (FSE_CTable* ct, unsigned char symbolValue); +/*< build a fake FSE_CTable, designed to compress always the same symbolValue */ + +/* FSE_buildCTable_wksp() : + * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`). + * `wkspSize` must be >= `FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog)` of `unsigned`. + */ +#define FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog) (maxSymbolValue + 2 + (1ull << (tableLog - 2))) +#define FSE_BUILD_CTABLE_WORKSPACE_SIZE(maxSymbolValue, tableLog) (sizeof(unsigned) * FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(maxSymbolValue, tableLog)) +size_t FSE_buildCTable_wksp(FSE_CTable* ct, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); + +#define FSE_BUILD_DTABLE_WKSP_SIZE(maxTableLog, maxSymbolValue) (sizeof(short) * (maxSymbolValue + 1) + (1ULL << maxTableLog) + 8) +#define FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) ((FSE_BUILD_DTABLE_WKSP_SIZE(maxTableLog, maxSymbolValue) + sizeof(unsigned) - 1) / sizeof(unsigned)) +FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); +/*< Same as FSE_buildDTable(), using an externally allocated `workspace` produced with `FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxSymbolValue)` */ + +size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits); +/*< build a fake FSE_DTable, designed to read a flat distribution where each symbol uses nbBits */ + +size_t FSE_buildDTable_rle (FSE_DTable* dt, unsigned char symbolValue); +/*< build a fake FSE_DTable, designed to always generate the same symbolValue */ + +#define FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) (FSE_DTABLE_SIZE_U32(maxTableLog) + FSE_BUILD_DTABLE_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) + (FSE_MAX_SYMBOL_VALUE + 1) / 2 + 1) +#define FSE_DECOMPRESS_WKSP_SIZE(maxTableLog, maxSymbolValue) (FSE_DECOMPRESS_WKSP_SIZE_U32(maxTableLog, maxSymbolValue) * sizeof(unsigned)) +size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize); +/*< same as FSE_decompress(), using an externally allocated `workSpace` produced with `FSE_DECOMPRESS_WKSP_SIZE_U32(maxLog, maxSymbolValue)` */ + +size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2); +/*< Same as FSE_decompress_wksp() but with dynamic BMI2 support. Pass 1 if your CPU supports BMI2 or 0 if it doesn't. */ + +typedef enum { + FSE_repeat_none, /*< Cannot use the previous table */ + FSE_repeat_check, /*< Can use the previous table but it must be checked */ + FSE_repeat_valid /*< Can use the previous table and it is assumed to be valid */ + } FSE_repeat; + +/* ***************************************** +* FSE symbol compression API +*******************************************/ +/*! + This API consists of small unitary functions, which highly benefit from being inlined. + Hence their body are included in next section. +*/ +typedef struct { + ptrdiff_t value; + const void* stateTable; + const void* symbolTT; + unsigned stateLog; +} FSE_CState_t; + +static void FSE_initCState(FSE_CState_t* CStatePtr, const FSE_CTable* ct); + +static void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* CStatePtr, unsigned symbol); + +static void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* CStatePtr); + +/*< +These functions are inner components of FSE_compress_usingCTable(). +They allow the creation of custom streams, mixing multiple tables and bit sources. + +A key property to keep in mind is that encoding and decoding are done **in reverse direction**. +So the first symbol you will encode is the last you will decode, like a LIFO stack. + +You will need a few variables to track your CStream. They are : + +FSE_CTable ct; // Provided by FSE_buildCTable() +BIT_CStream_t bitStream; // bitStream tracking structure +FSE_CState_t state; // State tracking structure (can have several) + + +The first thing to do is to init bitStream and state. + size_t errorCode = BIT_initCStream(&bitStream, dstBuffer, maxDstSize); + FSE_initCState(&state, ct); + +Note that BIT_initCStream() can produce an error code, so its result should be tested, using FSE_isError(); +You can then encode your input data, byte after byte. +FSE_encodeSymbol() outputs a maximum of 'tableLog' bits at a time. +Remember decoding will be done in reverse direction. + FSE_encodeByte(&bitStream, &state, symbol); + +At any time, you can also add any bit sequence. +Note : maximum allowed nbBits is 25, for compatibility with 32-bits decoders + BIT_addBits(&bitStream, bitField, nbBits); + +The above methods don't commit data to memory, they just store it into local register, for speed. +Local register size is 64-bits on 64-bits systems, 32-bits on 32-bits systems (size_t). +Writing data to memory is a manual operation, performed by the flushBits function. + BIT_flushBits(&bitStream); + +Your last FSE encoding operation shall be to flush your last state value(s). + FSE_flushState(&bitStream, &state); + +Finally, you must close the bitStream. +The function returns the size of CStream in bytes. +If data couldn't fit into dstBuffer, it will return a 0 ( == not compressible) +If there is an error, it returns an errorCode (which can be tested using FSE_isError()). + size_t size = BIT_closeCStream(&bitStream); +*/ + + +/* ***************************************** +* FSE symbol decompression API +*******************************************/ +typedef struct { + size_t state; + const void* table; /* precise table may vary, depending on U16 */ +} FSE_DState_t; + + +static void FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt); + +static unsigned char FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD); + +static unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr); + +/*< +Let's now decompose FSE_decompress_usingDTable() into its unitary components. +You will decode FSE-encoded symbols from the bitStream, +and also any other bitFields you put in, **in reverse order**. + +You will need a few variables to track your bitStream. They are : + +BIT_DStream_t DStream; // Stream context +FSE_DState_t DState; // State context. Multiple ones are possible +FSE_DTable* DTablePtr; // Decoding table, provided by FSE_buildDTable() + +The first thing to do is to init the bitStream. + errorCode = BIT_initDStream(&DStream, srcBuffer, srcSize); + +You should then retrieve your initial state(s) +(in reverse flushing order if you have several ones) : + errorCode = FSE_initDState(&DState, &DStream, DTablePtr); + +You can then decode your data, symbol after symbol. +For information the maximum number of bits read by FSE_decodeSymbol() is 'tableLog'. +Keep in mind that symbols are decoded in reverse order, like a LIFO stack (last in, first out). + unsigned char symbol = FSE_decodeSymbol(&DState, &DStream); + +You can retrieve any bitfield you eventually stored into the bitStream (in reverse order) +Note : maximum allowed nbBits is 25, for 32-bits compatibility + size_t bitField = BIT_readBits(&DStream, nbBits); + +All above operations only read from local register (which size depends on size_t). +Refueling the register from memory is manually performed by the reload method. + endSignal = FSE_reloadDStream(&DStream); + +BIT_reloadDStream() result tells if there is still some more data to read from DStream. +BIT_DStream_unfinished : there is still some data left into the DStream. +BIT_DStream_endOfBuffer : Dstream reached end of buffer. Its container may no longer be completely filled. +BIT_DStream_completed : Dstream reached its exact end, corresponding in general to decompression completed. +BIT_DStream_tooFar : Dstream went too far. Decompression result is corrupted. + +When reaching end of buffer (BIT_DStream_endOfBuffer), progress slowly, notably if you decode multiple symbols per loop, +to properly detect the exact end of stream. +After each decoded symbol, check if DStream is fully consumed using this simple test : + BIT_reloadDStream(&DStream) >= BIT_DStream_completed + +When it's done, verify decompression is fully completed, by checking both DStream and the relevant states. +Checking if DStream has reached its end is performed by : + BIT_endOfDStream(&DStream); +Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible. + FSE_endOfDState(&DState); +*/ + + +/* ***************************************** +* FSE unsafe API +*******************************************/ +static unsigned char FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD); +/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */ + + +/* ***************************************** +* Implementation of inlined functions +*******************************************/ +typedef struct { + int deltaFindState; + U32 deltaNbBits; +} FSE_symbolCompressionTransform; /* total 8 bytes */ + +MEM_STATIC void FSE_initCState(FSE_CState_t* statePtr, const FSE_CTable* ct) +{ + const void* ptr = ct; + const U16* u16ptr = (const U16*) ptr; + const U32 tableLog = MEM_read16(ptr); + statePtr->value = (ptrdiff_t)1<stateTable = u16ptr+2; + statePtr->symbolTT = ct + 1 + (tableLog ? (1<<(tableLog-1)) : 1); + statePtr->stateLog = tableLog; +} + + +/*! FSE_initCState2() : +* Same as FSE_initCState(), but the first symbol to include (which will be the last to be read) +* uses the smallest state value possible, saving the cost of this symbol */ +MEM_STATIC void FSE_initCState2(FSE_CState_t* statePtr, const FSE_CTable* ct, U32 symbol) +{ + FSE_initCState(statePtr, ct); + { const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol]; + const U16* stateTable = (const U16*)(statePtr->stateTable); + U32 nbBitsOut = (U32)((symbolTT.deltaNbBits + (1<<15)) >> 16); + statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits; + statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState]; + } +} + +MEM_STATIC void FSE_encodeSymbol(BIT_CStream_t* bitC, FSE_CState_t* statePtr, unsigned symbol) +{ + FSE_symbolCompressionTransform const symbolTT = ((const FSE_symbolCompressionTransform*)(statePtr->symbolTT))[symbol]; + const U16* const stateTable = (const U16*)(statePtr->stateTable); + U32 const nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16); + BIT_addBits(bitC, statePtr->value, nbBitsOut); + statePtr->value = stateTable[ (statePtr->value >> nbBitsOut) + symbolTT.deltaFindState]; +} + +MEM_STATIC void FSE_flushCState(BIT_CStream_t* bitC, const FSE_CState_t* statePtr) +{ + BIT_addBits(bitC, statePtr->value, statePtr->stateLog); + BIT_flushBits(bitC); +} + + +/* FSE_getMaxNbBits() : + * Approximate maximum cost of a symbol, in bits. + * Fractional get rounded up (i.e : a symbol with a normalized frequency of 3 gives the same result as a frequency of 2) + * note 1 : assume symbolValue is valid (<= maxSymbolValue) + * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */ +MEM_STATIC U32 FSE_getMaxNbBits(const void* symbolTTPtr, U32 symbolValue) +{ + const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr; + return (symbolTT[symbolValue].deltaNbBits + ((1<<16)-1)) >> 16; +} + +/* FSE_bitCost() : + * Approximate symbol cost, as fractional value, using fixed-point format (accuracyLog fractional bits) + * note 1 : assume symbolValue is valid (<= maxSymbolValue) + * note 2 : if freq[symbolValue]==0, @return a fake cost of tableLog+1 bits */ +MEM_STATIC U32 FSE_bitCost(const void* symbolTTPtr, U32 tableLog, U32 symbolValue, U32 accuracyLog) +{ + const FSE_symbolCompressionTransform* symbolTT = (const FSE_symbolCompressionTransform*) symbolTTPtr; + U32 const minNbBits = symbolTT[symbolValue].deltaNbBits >> 16; + U32 const threshold = (minNbBits+1) << 16; + assert(tableLog < 16); + assert(accuracyLog < 31-tableLog); /* ensure enough room for renormalization double shift */ + { U32 const tableSize = 1 << tableLog; + U32 const deltaFromThreshold = threshold - (symbolTT[symbolValue].deltaNbBits + tableSize); + U32 const normalizedDeltaFromThreshold = (deltaFromThreshold << accuracyLog) >> tableLog; /* linear interpolation (very approximate) */ + U32 const bitMultiplier = 1 << accuracyLog; + assert(symbolTT[symbolValue].deltaNbBits + tableSize <= threshold); + assert(normalizedDeltaFromThreshold <= bitMultiplier); + return (minNbBits+1)*bitMultiplier - normalizedDeltaFromThreshold; + } +} + + +/* ====== Decompression ====== */ + +typedef struct { + U16 tableLog; + U16 fastMode; +} FSE_DTableHeader; /* sizeof U32 */ + +typedef struct +{ + unsigned short newState; + unsigned char symbol; + unsigned char nbBits; +} FSE_decode_t; /* size == U32 */ + +MEM_STATIC void FSE_initDState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD, const FSE_DTable* dt) +{ + const void* ptr = dt; + const FSE_DTableHeader* const DTableH = (const FSE_DTableHeader*)ptr; + DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog); + BIT_reloadDStream(bitD); + DStatePtr->table = dt + 1; +} + +MEM_STATIC BYTE FSE_peekSymbol(const FSE_DState_t* DStatePtr) +{ + FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state]; + return DInfo.symbol; +} + +MEM_STATIC void FSE_updateState(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD) +{ + FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state]; + U32 const nbBits = DInfo.nbBits; + size_t const lowBits = BIT_readBits(bitD, nbBits); + DStatePtr->state = DInfo.newState + lowBits; +} + +MEM_STATIC BYTE FSE_decodeSymbol(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD) +{ + FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state]; + U32 const nbBits = DInfo.nbBits; + BYTE const symbol = DInfo.symbol; + size_t const lowBits = BIT_readBits(bitD, nbBits); + + DStatePtr->state = DInfo.newState + lowBits; + return symbol; +} + +/*! FSE_decodeSymbolFast() : + unsafe, only works if no symbol has a probability > 50% */ +MEM_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t* DStatePtr, BIT_DStream_t* bitD) +{ + FSE_decode_t const DInfo = ((const FSE_decode_t*)(DStatePtr->table))[DStatePtr->state]; + U32 const nbBits = DInfo.nbBits; + BYTE const symbol = DInfo.symbol; + size_t const lowBits = BIT_readBitsFast(bitD, nbBits); + + DStatePtr->state = DInfo.newState + lowBits; + return symbol; +} + +MEM_STATIC unsigned FSE_endOfDState(const FSE_DState_t* DStatePtr) +{ + return DStatePtr->state == 0; +} + + + +#ifndef FSE_COMMONDEFS_ONLY + +/* ************************************************************** +* Tuning parameters +****************************************************************/ +/*!MEMORY_USAGE : +* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) +* Increasing memory usage improves compression ratio +* Reduced memory usage can improve speed, due to cache effect +* Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ +#ifndef FSE_MAX_MEMORY_USAGE +# define FSE_MAX_MEMORY_USAGE 14 +#endif +#ifndef FSE_DEFAULT_MEMORY_USAGE +# define FSE_DEFAULT_MEMORY_USAGE 13 +#endif +#if (FSE_DEFAULT_MEMORY_USAGE > FSE_MAX_MEMORY_USAGE) +# error "FSE_DEFAULT_MEMORY_USAGE must be <= FSE_MAX_MEMORY_USAGE" +#endif + +/*!FSE_MAX_SYMBOL_VALUE : +* Maximum symbol value authorized. +* Required for proper stack allocation */ +#ifndef FSE_MAX_SYMBOL_VALUE +# define FSE_MAX_SYMBOL_VALUE 255 +#endif + +/* ************************************************************** +* template functions type & suffix +****************************************************************/ +#define FSE_FUNCTION_TYPE BYTE +#define FSE_FUNCTION_EXTENSION +#define FSE_DECODE_TYPE FSE_decode_t + + +#endif /* !FSE_COMMONDEFS_ONLY */ + + +/* *************************************************************** +* Constants +*****************************************************************/ +#define FSE_MAX_TABLELOG (FSE_MAX_MEMORY_USAGE-2) +#define FSE_MAX_TABLESIZE (1U< FSE_TABLELOG_ABSOLUTE_MAX +# error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported" +#endif + +#define FSE_TABLESTEP(tableSize) (((tableSize)>>1) + ((tableSize)>>3) + 3) + + +#endif /* FSE_STATIC_LINKING_ONLY */ + + diff --git a/lib/zstd/common/fse_decompress.c b/lib/zstd/common/fse_decompress.c new file mode 100644 index 000000000000..2c8bbe3e4c14 --- /dev/null +++ b/lib/zstd/common/fse_decompress.c @@ -0,0 +1,390 @@ +/* ****************************************************************** + * FSE : Finite State Entropy decoder + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy + * - Public forum : https://groups.google.com/forum/#!forum/lz4c + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + + +/* ************************************************************** +* Includes +****************************************************************/ +#include "debug.h" /* assert */ +#include "bitstream.h" +#include "compiler.h" +#define FSE_STATIC_LINKING_ONLY +#include "fse.h" +#include "error_private.h" +#define ZSTD_DEPS_NEED_MALLOC +#include "zstd_deps.h" + + +/* ************************************************************** +* Error Management +****************************************************************/ +#define FSE_isError ERR_isError +#define FSE_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) /* use only *after* variable declarations */ + + +/* ************************************************************** +* Templates +****************************************************************/ +/* + designed to be included + for type-specific functions (template emulation in C) + Objective is to write these functions only once, for improved maintenance +*/ + +/* safety checks */ +#ifndef FSE_FUNCTION_EXTENSION +# error "FSE_FUNCTION_EXTENSION must be defined" +#endif +#ifndef FSE_FUNCTION_TYPE +# error "FSE_FUNCTION_TYPE must be defined" +#endif + +/* Function names */ +#define FSE_CAT(X,Y) X##Y +#define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y) +#define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y) + + +/* Function templates */ +FSE_DTable* FSE_createDTable (unsigned tableLog) +{ + if (tableLog > FSE_TABLELOG_ABSOLUTE_MAX) tableLog = FSE_TABLELOG_ABSOLUTE_MAX; + return (FSE_DTable*)ZSTD_malloc( FSE_DTABLE_SIZE_U32(tableLog) * sizeof (U32) ); +} + +void FSE_freeDTable (FSE_DTable* dt) +{ + ZSTD_free(dt); +} + +static size_t FSE_buildDTable_internal(FSE_DTable* dt, const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize) +{ + void* const tdPtr = dt+1; /* because *dt is unsigned, 32-bits aligned on 32-bits */ + FSE_DECODE_TYPE* const tableDecode = (FSE_DECODE_TYPE*) (tdPtr); + U16* symbolNext = (U16*)workSpace; + BYTE* spread = (BYTE*)(symbolNext + maxSymbolValue + 1); + + U32 const maxSV1 = maxSymbolValue + 1; + U32 const tableSize = 1 << tableLog; + U32 highThreshold = tableSize-1; + + /* Sanity Checks */ + if (FSE_BUILD_DTABLE_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(maxSymbolValue_tooLarge); + if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE) return ERROR(maxSymbolValue_tooLarge); + if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); + + /* Init, lay down lowprob symbols */ + { FSE_DTableHeader DTableH; + DTableH.tableLog = (U16)tableLog; + DTableH.fastMode = 1; + { S16 const largeLimit= (S16)(1 << (tableLog-1)); + U32 s; + for (s=0; s= largeLimit) DTableH.fastMode=0; + symbolNext[s] = normalizedCounter[s]; + } } } + ZSTD_memcpy(dt, &DTableH, sizeof(DTableH)); + } + + /* Spread symbols */ + if (highThreshold == tableSize - 1) { + size_t const tableMask = tableSize-1; + size_t const step = FSE_TABLESTEP(tableSize); + /* First lay down the symbols in order. + * We use a uint64_t to lay down 8 bytes at a time. This reduces branch + * misses since small blocks generally have small table logs, so nearly + * all symbols have counts <= 8. We ensure we have 8 bytes at the end of + * our buffer to handle the over-write. + */ + { + U64 const add = 0x0101010101010101ull; + size_t pos = 0; + U64 sv = 0; + U32 s; + for (s=0; s highThreshold) position = (position + step) & tableMask; /* lowprob area */ + } } + if (position!=0) return ERROR(GENERIC); /* position must reach all cells once, otherwise normalizedCounter is incorrect */ + } + + /* Build Decoding table */ + { U32 u; + for (u=0; utableLog = 0; + DTableH->fastMode = 0; + + cell->newState = 0; + cell->symbol = symbolValue; + cell->nbBits = 0; + + return 0; +} + + +size_t FSE_buildDTable_raw (FSE_DTable* dt, unsigned nbBits) +{ + void* ptr = dt; + FSE_DTableHeader* const DTableH = (FSE_DTableHeader*)ptr; + void* dPtr = dt + 1; + FSE_decode_t* const dinfo = (FSE_decode_t*)dPtr; + const unsigned tableSize = 1 << nbBits; + const unsigned tableMask = tableSize - 1; + const unsigned maxSV1 = tableMask+1; + unsigned s; + + /* Sanity checks */ + if (nbBits < 1) return ERROR(GENERIC); /* min size */ + + /* Build Decoding Table */ + DTableH->tableLog = (U16)nbBits; + DTableH->fastMode = 1; + for (s=0; s sizeof(bitD.bitContainer)*8) /* This test must be static */ + BIT_reloadDStream(&bitD); + + op[1] = FSE_GETSYMBOL(&state2); + + if (FSE_MAX_TABLELOG*4+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */ + { if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) { op+=2; break; } } + + op[2] = FSE_GETSYMBOL(&state1); + + if (FSE_MAX_TABLELOG*2+7 > sizeof(bitD.bitContainer)*8) /* This test must be static */ + BIT_reloadDStream(&bitD); + + op[3] = FSE_GETSYMBOL(&state2); + } + + /* tail */ + /* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */ + while (1) { + if (op>(omax-2)) return ERROR(dstSize_tooSmall); + *op++ = FSE_GETSYMBOL(&state1); + if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) { + *op++ = FSE_GETSYMBOL(&state2); + break; + } + + if (op>(omax-2)) return ERROR(dstSize_tooSmall); + *op++ = FSE_GETSYMBOL(&state2); + if (BIT_reloadDStream(&bitD)==BIT_DStream_overflow) { + *op++ = FSE_GETSYMBOL(&state1); + break; + } } + + return op-ostart; +} + + +size_t FSE_decompress_usingDTable(void* dst, size_t originalSize, + const void* cSrc, size_t cSrcSize, + const FSE_DTable* dt) +{ + const void* ptr = dt; + const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr; + const U32 fastMode = DTableH->fastMode; + + /* select fast mode (static) */ + if (fastMode) return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1); + return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0); +} + + +size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize) +{ + return FSE_decompress_wksp_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, /* bmi2 */ 0); +} + +typedef struct { + short ncount[FSE_MAX_SYMBOL_VALUE + 1]; + FSE_DTable dtable[1]; /* Dynamically sized */ +} FSE_DecompressWksp; + + +FORCE_INLINE_TEMPLATE size_t FSE_decompress_wksp_body( + void* dst, size_t dstCapacity, + const void* cSrc, size_t cSrcSize, + unsigned maxLog, void* workSpace, size_t wkspSize, + int bmi2) +{ + const BYTE* const istart = (const BYTE*)cSrc; + const BYTE* ip = istart; + unsigned tableLog; + unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE; + FSE_DecompressWksp* const wksp = (FSE_DecompressWksp*)workSpace; + + DEBUG_STATIC_ASSERT((FSE_MAX_SYMBOL_VALUE + 1) % 2 == 0); + if (wkspSize < sizeof(*wksp)) return ERROR(GENERIC); + + /* normal FSE decoding mode */ + { + size_t const NCountLength = FSE_readNCount_bmi2(wksp->ncount, &maxSymbolValue, &tableLog, istart, cSrcSize, bmi2); + if (FSE_isError(NCountLength)) return NCountLength; + if (tableLog > maxLog) return ERROR(tableLog_tooLarge); + assert(NCountLength <= cSrcSize); + ip += NCountLength; + cSrcSize -= NCountLength; + } + + if (FSE_DECOMPRESS_WKSP_SIZE(tableLog, maxSymbolValue) > wkspSize) return ERROR(tableLog_tooLarge); + workSpace = wksp->dtable + FSE_DTABLE_SIZE_U32(tableLog); + wkspSize -= sizeof(*wksp) + FSE_DTABLE_SIZE(tableLog); + + CHECK_F( FSE_buildDTable_internal(wksp->dtable, wksp->ncount, maxSymbolValue, tableLog, workSpace, wkspSize) ); + + { + const void* ptr = wksp->dtable; + const FSE_DTableHeader* DTableH = (const FSE_DTableHeader*)ptr; + const U32 fastMode = DTableH->fastMode; + + /* select fast mode (static) */ + if (fastMode) return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 1); + return FSE_decompress_usingDTable_generic(dst, dstCapacity, ip, cSrcSize, wksp->dtable, 0); + } +} + +/* Avoids the FORCE_INLINE of the _body() function. */ +static size_t FSE_decompress_wksp_body_default(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize) +{ + return FSE_decompress_wksp_body(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, 0); +} + +#if DYNAMIC_BMI2 +TARGET_ATTRIBUTE("bmi2") static size_t FSE_decompress_wksp_body_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize) +{ + return FSE_decompress_wksp_body(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize, 1); +} +#endif + +size_t FSE_decompress_wksp_bmi2(void* dst, size_t dstCapacity, const void* cSrc, size_t cSrcSize, unsigned maxLog, void* workSpace, size_t wkspSize, int bmi2) +{ +#if DYNAMIC_BMI2 + if (bmi2) { + return FSE_decompress_wksp_body_bmi2(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize); + } +#endif + (void)bmi2; + return FSE_decompress_wksp_body_default(dst, dstCapacity, cSrc, cSrcSize, maxLog, workSpace, wkspSize); +} + + +typedef FSE_DTable DTable_max_t[FSE_DTABLE_SIZE_U32(FSE_MAX_TABLELOG)]; + + + +#endif /* FSE_COMMONDEFS_ONLY */ diff --git a/lib/zstd/common/huf.h b/lib/zstd/common/huf.h new file mode 100644 index 000000000000..88c5586646aa --- /dev/null +++ b/lib/zstd/common/huf.h @@ -0,0 +1,356 @@ +/* ****************************************************************** + * huff0 huffman codec, + * part of Finite State Entropy library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + + +#ifndef HUF_H_298734234 +#define HUF_H_298734234 + +/* *** Dependencies *** */ +#include "zstd_deps.h" /* size_t */ + + +/* *** library symbols visibility *** */ +/* Note : when linking with -fvisibility=hidden on gcc, or by default on Visual, + * HUF symbols remain "private" (internal symbols for library only). + * Set macro FSE_DLL_EXPORT to 1 if you want HUF symbols visible on DLL interface */ +#if defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) && defined(__GNUC__) && (__GNUC__ >= 4) +# define HUF_PUBLIC_API __attribute__ ((visibility ("default"))) +#elif defined(FSE_DLL_EXPORT) && (FSE_DLL_EXPORT==1) /* Visual expected */ +# define HUF_PUBLIC_API __declspec(dllexport) +#elif defined(FSE_DLL_IMPORT) && (FSE_DLL_IMPORT==1) +# define HUF_PUBLIC_API __declspec(dllimport) /* not required, just to generate faster code (saves a function pointer load from IAT and an indirect jump) */ +#else +# define HUF_PUBLIC_API +#endif + + +/* ========================== */ +/* *** simple functions *** */ +/* ========================== */ + +/* HUF_compress() : + * Compress content from buffer 'src', of size 'srcSize', into buffer 'dst'. + * 'dst' buffer must be already allocated. + * Compression runs faster if `dstCapacity` >= HUF_compressBound(srcSize). + * `srcSize` must be <= `HUF_BLOCKSIZE_MAX` == 128 KB. + * @return : size of compressed data (<= `dstCapacity`). + * Special values : if return == 0, srcData is not compressible => Nothing is stored within dst !!! + * if HUF_isError(return), compression failed (more details using HUF_getErrorName()) + */ +HUF_PUBLIC_API size_t HUF_compress(void* dst, size_t dstCapacity, + const void* src, size_t srcSize); + +/* HUF_decompress() : + * Decompress HUF data from buffer 'cSrc', of size 'cSrcSize', + * into already allocated buffer 'dst', of minimum size 'dstSize'. + * `originalSize` : **must** be the ***exact*** size of original (uncompressed) data. + * Note : in contrast with FSE, HUF_decompress can regenerate + * RLE (cSrcSize==1) and uncompressed (cSrcSize==dstSize) data, + * because it knows size to regenerate (originalSize). + * @return : size of regenerated data (== originalSize), + * or an error code, which can be tested using HUF_isError() + */ +HUF_PUBLIC_API size_t HUF_decompress(void* dst, size_t originalSize, + const void* cSrc, size_t cSrcSize); + + +/* *** Tool functions *** */ +#define HUF_BLOCKSIZE_MAX (128 * 1024) /*< maximum input size for a single block compressed with HUF_compress */ +HUF_PUBLIC_API size_t HUF_compressBound(size_t size); /*< maximum compressed size (worst case) */ + +/* Error Management */ +HUF_PUBLIC_API unsigned HUF_isError(size_t code); /*< tells if a return value is an error code */ +HUF_PUBLIC_API const char* HUF_getErrorName(size_t code); /*< provides error code string (useful for debugging) */ + + +/* *** Advanced function *** */ + +/* HUF_compress2() : + * Same as HUF_compress(), but offers control over `maxSymbolValue` and `tableLog`. + * `maxSymbolValue` must be <= HUF_SYMBOLVALUE_MAX . + * `tableLog` must be `<= HUF_TABLELOG_MAX` . */ +HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned tableLog); + +/* HUF_compress4X_wksp() : + * Same as HUF_compress2(), but uses externally allocated `workSpace`. + * `workspace` must have minimum alignment of 4, and be at least as large as HUF_WORKSPACE_SIZE */ +#define HUF_WORKSPACE_SIZE ((6 << 10) + 256) +#define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32)) +HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned tableLog, + void* workSpace, size_t wkspSize); + +#endif /* HUF_H_298734234 */ + +/* ****************************************************************** + * WARNING !! + * The following section contains advanced and experimental definitions + * which shall never be used in the context of a dynamic library, + * because they are not guaranteed to remain stable in the future. + * Only consider them in association with static linking. + * *****************************************************************/ +#if !defined(HUF_H_HUF_STATIC_LINKING_ONLY) +#define HUF_H_HUF_STATIC_LINKING_ONLY + +/* *** Dependencies *** */ +#include "mem.h" /* U32 */ +#define FSE_STATIC_LINKING_ONLY +#include "fse.h" + + +/* *** Constants *** */ +#define HUF_TABLELOG_MAX 12 /* max runtime value of tableLog (due to static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */ +#define HUF_TABLELOG_DEFAULT 11 /* default tableLog value when none specified */ +#define HUF_SYMBOLVALUE_MAX 255 + +#define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */ +#if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX) +# error "HUF_TABLELOG_MAX is too large !" +#endif + + +/* **************************************** +* Static allocation +******************************************/ +/* HUF buffer bounds */ +#define HUF_CTABLEBOUND 129 +#define HUF_BLOCKBOUND(size) (size + (size>>8) + 8) /* only true when incompressible is pre-filtered with fast heuristic */ +#define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */ + +/* static allocation of HUF's Compression Table */ +/* this is a private definition, just exposed for allocation and strict aliasing purpose. never EVER access its members directly */ +struct HUF_CElt_s { + U16 val; + BYTE nbBits; +}; /* typedef'd to HUF_CElt */ +typedef struct HUF_CElt_s HUF_CElt; /* consider it an incomplete type */ +#define HUF_CTABLE_SIZE_U32(maxSymbolValue) ((maxSymbolValue)+1) /* Use tables of U32, for proper alignment */ +#define HUF_CTABLE_SIZE(maxSymbolValue) (HUF_CTABLE_SIZE_U32(maxSymbolValue) * sizeof(U32)) +#define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \ + HUF_CElt name[HUF_CTABLE_SIZE_U32(maxSymbolValue)] /* no final ; */ + +/* static allocation of HUF's DTable */ +typedef U32 HUF_DTable; +#define HUF_DTABLE_SIZE(maxTableLog) (1 + (1<<(maxTableLog))) +#define HUF_CREATE_STATIC_DTABLEX1(DTable, maxTableLog) \ + HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = { ((U32)((maxTableLog)-1) * 0x01000001) } +#define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) \ + HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = { ((U32)(maxTableLog) * 0x01000001) } + + +/* **************************************** +* Advanced decompression functions +******************************************/ +size_t HUF_decompress4X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< single-symbol decoder */ +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< double-symbols decoder */ +#endif + +size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< decodes RLE and uncompressed */ +size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< considers RLE and uncompressed as errors */ +size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< considers RLE and uncompressed as errors */ +size_t HUF_decompress4X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< single-symbol decoder */ +size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< single-symbol decoder */ +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< double-symbols decoder */ +size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< double-symbols decoder */ +#endif + + +/* **************************************** + * HUF detailed API + * ****************************************/ + +/*! HUF_compress() does the following: + * 1. count symbol occurrence from source[] into table count[] using FSE_count() (exposed within "fse.h") + * 2. (optional) refine tableLog using HUF_optimalTableLog() + * 3. build Huffman table from count using HUF_buildCTable() + * 4. save Huffman table to memory buffer using HUF_writeCTable() + * 5. encode the data stream using HUF_compress4X_usingCTable() + * + * The following API allows targeting specific sub-functions for advanced tasks. + * For example, it's possible to compress several blocks using the same 'CTable', + * or to save and regenerate 'CTable' using external methods. + */ +unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); +size_t HUF_buildCTable (HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue, unsigned maxNbBits); /* @return : maxNbBits; CTable and count can overlap. In which case, CTable will overwrite count content */ +size_t HUF_writeCTable (void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog); +size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize, const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog, void* workspace, size_t workspaceSize); +size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable); +size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue); +int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue); + +typedef enum { + HUF_repeat_none, /*< Cannot use the previous table */ + HUF_repeat_check, /*< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, 4}X_repeat */ + HUF_repeat_valid /*< Can use the previous table and it is assumed to be valid */ + } HUF_repeat; +/* HUF_compress4X_repeat() : + * Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. + * If it uses hufTable it does not modify hufTable or repeat. + * If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. + * If preferRepeat then the old table will always be used if valid. */ +size_t HUF_compress4X_repeat(void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned tableLog, + void* workSpace, size_t wkspSize, /*< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */ + HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2); + +/* HUF_buildCTable_wksp() : + * Same as HUF_buildCTable(), but using externally allocated scratch buffer. + * `workSpace` must be aligned on 4-bytes boundaries, and its size must be >= HUF_CTABLE_WORKSPACE_SIZE. + */ +#define HUF_CTABLE_WORKSPACE_SIZE_U32 (2*HUF_SYMBOLVALUE_MAX +1 +1) +#define HUF_CTABLE_WORKSPACE_SIZE (HUF_CTABLE_WORKSPACE_SIZE_U32 * sizeof(unsigned)) +size_t HUF_buildCTable_wksp (HUF_CElt* tree, + const unsigned* count, U32 maxSymbolValue, U32 maxNbBits, + void* workSpace, size_t wkspSize); + +/*! HUF_readStats() : + * Read compact Huffman tree, saved by HUF_writeCTable(). + * `huffWeight` is destination buffer. + * @return : size read from `src` , or an error Code . + * Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */ +size_t HUF_readStats(BYTE* huffWeight, size_t hwSize, + U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize); + +/*! HUF_readStats_wksp() : + * Same as HUF_readStats() but takes an external workspace which must be + * 4-byte aligned and its size must be >= HUF_READ_STATS_WORKSPACE_SIZE. + * If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0. + */ +#define HUF_READ_STATS_WORKSPACE_SIZE_U32 FSE_DECOMPRESS_WKSP_SIZE_U32(6, HUF_TABLELOG_MAX-1) +#define HUF_READ_STATS_WORKSPACE_SIZE (HUF_READ_STATS_WORKSPACE_SIZE_U32 * sizeof(unsigned)) +size_t HUF_readStats_wksp(BYTE* huffWeight, size_t hwSize, + U32* rankStats, U32* nbSymbolsPtr, U32* tableLogPtr, + const void* src, size_t srcSize, + void* workspace, size_t wkspSize, + int bmi2); + +/* HUF_readCTable() : + * Loading a CTable saved with HUF_writeCTable() */ +size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned *hasZeroWeights); + +/* HUF_getNbBits() : + * Read nbBits from CTable symbolTable, for symbol `symbolValue` presumed <= HUF_SYMBOLVALUE_MAX + * Note 1 : is not inlined, as HUF_CElt definition is private + * Note 2 : const void* used, so that it can provide a statically allocated table as argument (which uses type U32) */ +U32 HUF_getNbBits(const void* symbolTable, U32 symbolValue); + +/* + * HUF_decompress() does the following: + * 1. select the decompression algorithm (X1, X2) based on pre-computed heuristics + * 2. build Huffman table from save, using HUF_readDTableX?() + * 3. decode 1 or 4 segments in parallel using HUF_decompress?X?_usingDTable() + */ + +/* HUF_selectDecoder() : + * Tells which decoder is likely to decode faster, + * based on a set of pre-computed metrics. + * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 . + * Assumption : 0 < dstSize <= 128 KB */ +U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize); + +/* + * The minimum workspace size for the `workSpace` used in + * HUF_readDTableX1_wksp() and HUF_readDTableX2_wksp(). + * + * The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when + * HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15. + * Buffer overflow errors may potentially occur if code modifications result in + * a required workspace size greater than that specified in the following + * macro. + */ +#define HUF_DECOMPRESS_WORKSPACE_SIZE ((2 << 10) + (1 << 9)) +#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32)) + +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_readDTableX1 (HUF_DTable* DTable, const void* src, size_t srcSize); +size_t HUF_readDTableX1_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize); +#endif +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize); +size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize); +#endif + +size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_decompress4X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); +#endif +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); +#endif + + +/* ====================== */ +/* single stream variants */ +/* ====================== */ + +size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog); +size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize); /*< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */ +size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable); +/* HUF_compress1X_repeat() : + * Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. + * If it uses hufTable it does not modify hufTable or repeat. + * If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. + * If preferRepeat then the old table will always be used if valid. */ +size_t HUF_compress1X_repeat(void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned tableLog, + void* workSpace, size_t wkspSize, /*< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */ + HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2); + +size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* single-symbol decoder */ +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* double-symbol decoder */ +#endif + +size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); +size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_decompress1X1_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< single-symbol decoder */ +size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< single-symbol decoder */ +#endif +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /*< double-symbols decoder */ +size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /*< double-symbols decoder */ +#endif + +size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); /*< automatic selection of sing or double symbol decoder, based on DTable */ +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_decompress1X1_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); +#endif +#ifndef HUF_FORCE_DECOMPRESS_X1 +size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable); +#endif + +/* BMI2 variants. + * If the CPU has BMI2 support, pass bmi2=1, otherwise pass bmi2=0. + */ +size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2); +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2); +#endif +size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2); +size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2); +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2); +#endif + +#endif /* HUF_STATIC_LINKING_ONLY */ + diff --git a/lib/zstd/common/mem.h b/lib/zstd/common/mem.h new file mode 100644 index 000000000000..dcdd586a9fd9 --- /dev/null +++ b/lib/zstd/common/mem.h @@ -0,0 +1,259 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef MEM_H_MODULE +#define MEM_H_MODULE + +/*-**************************************** +* Dependencies +******************************************/ +#include /* get_unaligned, put_unaligned* */ +#include /* inline */ +#include /* swab32, swab64 */ +#include /* size_t, ptrdiff_t */ +#include "debug.h" /* DEBUG_STATIC_ASSERT */ + +/*-**************************************** +* Compiler specifics +******************************************/ +#define MEM_STATIC static inline + +/*-************************************************************** +* Basic Types +*****************************************************************/ +typedef uint8_t BYTE; +typedef uint16_t U16; +typedef int16_t S16; +typedef uint32_t U32; +typedef int32_t S32; +typedef uint64_t U64; +typedef int64_t S64; + +/*-************************************************************** +* Memory I/O API +*****************************************************************/ +/*=== Static platform detection ===*/ +MEM_STATIC unsigned MEM_32bits(void); +MEM_STATIC unsigned MEM_64bits(void); +MEM_STATIC unsigned MEM_isLittleEndian(void); + +/*=== Native unaligned read/write ===*/ +MEM_STATIC U16 MEM_read16(const void* memPtr); +MEM_STATIC U32 MEM_read32(const void* memPtr); +MEM_STATIC U64 MEM_read64(const void* memPtr); +MEM_STATIC size_t MEM_readST(const void* memPtr); + +MEM_STATIC void MEM_write16(void* memPtr, U16 value); +MEM_STATIC void MEM_write32(void* memPtr, U32 value); +MEM_STATIC void MEM_write64(void* memPtr, U64 value); + +/*=== Little endian unaligned read/write ===*/ +MEM_STATIC U16 MEM_readLE16(const void* memPtr); +MEM_STATIC U32 MEM_readLE24(const void* memPtr); +MEM_STATIC U32 MEM_readLE32(const void* memPtr); +MEM_STATIC U64 MEM_readLE64(const void* memPtr); +MEM_STATIC size_t MEM_readLEST(const void* memPtr); + +MEM_STATIC void MEM_writeLE16(void* memPtr, U16 val); +MEM_STATIC void MEM_writeLE24(void* memPtr, U32 val); +MEM_STATIC void MEM_writeLE32(void* memPtr, U32 val32); +MEM_STATIC void MEM_writeLE64(void* memPtr, U64 val64); +MEM_STATIC void MEM_writeLEST(void* memPtr, size_t val); + +/*=== Big endian unaligned read/write ===*/ +MEM_STATIC U32 MEM_readBE32(const void* memPtr); +MEM_STATIC U64 MEM_readBE64(const void* memPtr); +MEM_STATIC size_t MEM_readBEST(const void* memPtr); + +MEM_STATIC void MEM_writeBE32(void* memPtr, U32 val32); +MEM_STATIC void MEM_writeBE64(void* memPtr, U64 val64); +MEM_STATIC void MEM_writeBEST(void* memPtr, size_t val); + +/*=== Byteswap ===*/ +MEM_STATIC U32 MEM_swap32(U32 in); +MEM_STATIC U64 MEM_swap64(U64 in); +MEM_STATIC size_t MEM_swapST(size_t in); + +/*-************************************************************** +* Memory I/O Implementation +*****************************************************************/ +MEM_STATIC unsigned MEM_32bits(void) +{ + return sizeof(size_t) == 4; +} + +MEM_STATIC unsigned MEM_64bits(void) +{ + return sizeof(size_t) == 8; +} + +#if defined(__LITTLE_ENDIAN) +#define MEM_LITTLE_ENDIAN 1 +#else +#define MEM_LITTLE_ENDIAN 0 +#endif + +MEM_STATIC unsigned MEM_isLittleEndian(void) +{ + return MEM_LITTLE_ENDIAN; +} + +MEM_STATIC U16 MEM_read16(const void *memPtr) +{ + return get_unaligned((const U16 *)memPtr); +} + +MEM_STATIC U32 MEM_read32(const void *memPtr) +{ + return get_unaligned((const U32 *)memPtr); +} + +MEM_STATIC U64 MEM_read64(const void *memPtr) +{ + return get_unaligned((const U64 *)memPtr); +} + +MEM_STATIC size_t MEM_readST(const void *memPtr) +{ + return get_unaligned((const size_t *)memPtr); +} + +MEM_STATIC void MEM_write16(void *memPtr, U16 value) +{ + put_unaligned(value, (U16 *)memPtr); +} + +MEM_STATIC void MEM_write32(void *memPtr, U32 value) +{ + put_unaligned(value, (U32 *)memPtr); +} + +MEM_STATIC void MEM_write64(void *memPtr, U64 value) +{ + put_unaligned(value, (U64 *)memPtr); +} + +/*=== Little endian r/w ===*/ + +MEM_STATIC U16 MEM_readLE16(const void *memPtr) +{ + return get_unaligned_le16(memPtr); +} + +MEM_STATIC void MEM_writeLE16(void *memPtr, U16 val) +{ + put_unaligned_le16(val, memPtr); +} + +MEM_STATIC U32 MEM_readLE24(const void *memPtr) +{ + return MEM_readLE16(memPtr) + (((const BYTE *)memPtr)[2] << 16); +} + +MEM_STATIC void MEM_writeLE24(void *memPtr, U32 val) +{ + MEM_writeLE16(memPtr, (U16)val); + ((BYTE *)memPtr)[2] = (BYTE)(val >> 16); +} + +MEM_STATIC U32 MEM_readLE32(const void *memPtr) +{ + return get_unaligned_le32(memPtr); +} + +MEM_STATIC void MEM_writeLE32(void *memPtr, U32 val32) +{ + put_unaligned_le32(val32, memPtr); +} + +MEM_STATIC U64 MEM_readLE64(const void *memPtr) +{ + return get_unaligned_le64(memPtr); +} + +MEM_STATIC void MEM_writeLE64(void *memPtr, U64 val64) +{ + put_unaligned_le64(val64, memPtr); +} + +MEM_STATIC size_t MEM_readLEST(const void *memPtr) +{ + if (MEM_32bits()) + return (size_t)MEM_readLE32(memPtr); + else + return (size_t)MEM_readLE64(memPtr); +} + +MEM_STATIC void MEM_writeLEST(void *memPtr, size_t val) +{ + if (MEM_32bits()) + MEM_writeLE32(memPtr, (U32)val); + else + MEM_writeLE64(memPtr, (U64)val); +} + +/*=== Big endian r/w ===*/ + +MEM_STATIC U32 MEM_readBE32(const void *memPtr) +{ + return get_unaligned_be32(memPtr); +} + +MEM_STATIC void MEM_writeBE32(void *memPtr, U32 val32) +{ + put_unaligned_be32(val32, memPtr); +} + +MEM_STATIC U64 MEM_readBE64(const void *memPtr) +{ + return get_unaligned_be64(memPtr); +} + +MEM_STATIC void MEM_writeBE64(void *memPtr, U64 val64) +{ + put_unaligned_be64(val64, memPtr); +} + +MEM_STATIC size_t MEM_readBEST(const void *memPtr) +{ + if (MEM_32bits()) + return (size_t)MEM_readBE32(memPtr); + else + return (size_t)MEM_readBE64(memPtr); +} + +MEM_STATIC void MEM_writeBEST(void *memPtr, size_t val) +{ + if (MEM_32bits()) + MEM_writeBE32(memPtr, (U32)val); + else + MEM_writeBE64(memPtr, (U64)val); +} + +MEM_STATIC U32 MEM_swap32(U32 in) +{ + return swab32(in); +} + +MEM_STATIC U64 MEM_swap64(U64 in) +{ + return swab64(in); +} + +MEM_STATIC size_t MEM_swapST(size_t in) +{ + if (MEM_32bits()) + return (size_t)MEM_swap32((U32)in); + else + return (size_t)MEM_swap64((U64)in); +} + +#endif /* MEM_H_MODULE */ diff --git a/lib/zstd/common/zstd_common.c b/lib/zstd/common/zstd_common.c new file mode 100644 index 000000000000..3d7e35b309b5 --- /dev/null +++ b/lib/zstd/common/zstd_common.c @@ -0,0 +1,83 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + + +/*-************************************* +* Dependencies +***************************************/ +#define ZSTD_DEPS_NEED_MALLOC +#include "zstd_deps.h" /* ZSTD_malloc, ZSTD_calloc, ZSTD_free, ZSTD_memset */ +#include "error_private.h" +#include "zstd_internal.h" + + +/*-**************************************** +* Version +******************************************/ +unsigned ZSTD_versionNumber(void) { return ZSTD_VERSION_NUMBER; } + +const char* ZSTD_versionString(void) { return ZSTD_VERSION_STRING; } + + +/*-**************************************** +* ZSTD Error Management +******************************************/ +#undef ZSTD_isError /* defined within zstd_internal.h */ +/*! ZSTD_isError() : + * tells if a return value is an error code + * symbol is required for external callers */ +unsigned ZSTD_isError(size_t code) { return ERR_isError(code); } + +/*! ZSTD_getErrorName() : + * provides error code string from function result (useful for debugging) */ +const char* ZSTD_getErrorName(size_t code) { return ERR_getErrorName(code); } + +/*! ZSTD_getError() : + * convert a `size_t` function result into a proper ZSTD_errorCode enum */ +ZSTD_ErrorCode ZSTD_getErrorCode(size_t code) { return ERR_getErrorCode(code); } + +/*! ZSTD_getErrorString() : + * provides error code string from enum */ +const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorString(code); } + + + +/*=************************************************************** +* Custom allocator +****************************************************************/ +void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem) +{ + if (customMem.customAlloc) + return customMem.customAlloc(customMem.opaque, size); + return ZSTD_malloc(size); +} + +void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem) +{ + if (customMem.customAlloc) { + /* calloc implemented as malloc+memset; + * not as efficient as calloc, but next best guess for custom malloc */ + void* const ptr = customMem.customAlloc(customMem.opaque, size); + ZSTD_memset(ptr, 0, size); + return ptr; + } + return ZSTD_calloc(1, size); +} + +void ZSTD_customFree(void* ptr, ZSTD_customMem customMem) +{ + if (ptr!=NULL) { + if (customMem.customFree) + customMem.customFree(customMem.opaque, ptr); + else + ZSTD_free(ptr); + } +} diff --git a/lib/zstd/common/zstd_deps.h b/lib/zstd/common/zstd_deps.h new file mode 100644 index 000000000000..7a5bf44839c9 --- /dev/null +++ b/lib/zstd/common/zstd_deps.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause */ +/* + * Copyright (c) Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* + * This file provides common libc dependencies that zstd requires. + * The purpose is to allow replacing this file with a custom implementation + * to compile zstd without libc support. + */ + +/* Need: + * NULL + * INT_MAX + * UINT_MAX + * ZSTD_memcpy() + * ZSTD_memset() + * ZSTD_memmove() + */ +#ifndef ZSTD_DEPS_COMMON +#define ZSTD_DEPS_COMMON + +#include +#include + +#define ZSTD_memcpy(d,s,n) __builtin_memcpy((d),(s),(n)) +#define ZSTD_memmove(d,s,n) __builtin_memmove((d),(s),(n)) +#define ZSTD_memset(d,s,n) __builtin_memset((d),(s),(n)) + +#endif /* ZSTD_DEPS_COMMON */ + +/* + * Define malloc as always failing. That means the user must + * either use ZSTD_customMem or statically allocate memory. + * Need: + * ZSTD_malloc() + * ZSTD_free() + * ZSTD_calloc() + */ +#ifdef ZSTD_DEPS_NEED_MALLOC +#ifndef ZSTD_DEPS_MALLOC +#define ZSTD_DEPS_MALLOC + +#define ZSTD_malloc(s) ({ (void)(s); NULL; }) +#define ZSTD_free(p) ((void)(p)) +#define ZSTD_calloc(n,s) ({ (void)(n); (void)(s); NULL; }) + +#endif /* ZSTD_DEPS_MALLOC */ +#endif /* ZSTD_DEPS_NEED_MALLOC */ + +/* + * Provides 64-bit math support. + * Need: + * U64 ZSTD_div64(U64 dividend, U32 divisor) + */ +#ifdef ZSTD_DEPS_NEED_MATH64 +#ifndef ZSTD_DEPS_MATH64 +#define ZSTD_DEPS_MATH64 + +#include + +static uint64_t ZSTD_div64(uint64_t dividend, uint32_t divisor) { + return div_u64(dividend, divisor); +} + +#endif /* ZSTD_DEPS_MATH64 */ +#endif /* ZSTD_DEPS_NEED_MATH64 */ + +/* + * This is only requested when DEBUGLEVEL >= 1, meaning + * it is disabled in production. + * Need: + * assert() + */ +#ifdef ZSTD_DEPS_NEED_ASSERT +#ifndef ZSTD_DEPS_ASSERT +#define ZSTD_DEPS_ASSERT + +#include + +#define assert(x) WARN_ON((x)) + +#endif /* ZSTD_DEPS_ASSERT */ +#endif /* ZSTD_DEPS_NEED_ASSERT */ + +/* + * This is only requested when DEBUGLEVEL >= 2, meaning + * it is disabled in production. + * Need: + * ZSTD_DEBUG_PRINT() + */ +#ifdef ZSTD_DEPS_NEED_IO +#ifndef ZSTD_DEPS_IO +#define ZSTD_DEPS_IO + +#include + +#define ZSTD_DEBUG_PRINT(...) pr_debug(__VA_ARGS__) + +#endif /* ZSTD_DEPS_IO */ +#endif /* ZSTD_DEPS_NEED_IO */ + +/* + * Only requested when MSAN is enabled. + * Need: + * intptr_t + */ +#ifdef ZSTD_DEPS_NEED_STDINT +#ifndef ZSTD_DEPS_STDINT +#define ZSTD_DEPS_STDINT + +/* + * The Linux Kernel doesn't provide intptr_t, only uintptr_t, which + * is an unsigned long. + */ +typedef long intptr_t; + +#endif /* ZSTD_DEPS_STDINT */ +#endif /* ZSTD_DEPS_NEED_STDINT */ diff --git a/lib/zstd/common/zstd_internal.h b/lib/zstd/common/zstd_internal.h new file mode 100644 index 000000000000..fc6f3a9b40c0 --- /dev/null +++ b/lib/zstd/common/zstd_internal.h @@ -0,0 +1,450 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_CCOMMON_H_MODULE +#define ZSTD_CCOMMON_H_MODULE + +/* this module contains definitions which must be identical + * across compression, decompression and dictBuilder. + * It also contains a few functions useful to at least 2 of them + * and which benefit from being inlined */ + +/*-************************************* +* Dependencies +***************************************/ +#include "compiler.h" +#include "mem.h" +#include "debug.h" /* assert, DEBUGLOG, RAWLOG, g_debuglevel */ +#include "error_private.h" +#define ZSTD_STATIC_LINKING_ONLY +#include +#define FSE_STATIC_LINKING_ONLY +#include "fse.h" +#define HUF_STATIC_LINKING_ONLY +#include "huf.h" +#include /* XXH_reset, update, digest */ +#define ZSTD_TRACE 0 + + +/* ---- static assert (debug) --- */ +#define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) +#define ZSTD_isError ERR_isError /* for inlining */ +#define FSE_isError ERR_isError +#define HUF_isError ERR_isError + + +/*-************************************* +* shared macros +***************************************/ +#undef MIN +#undef MAX +#define MIN(a,b) ((a)<(b) ? (a) : (b)) +#define MAX(a,b) ((a)>(b) ? (a) : (b)) + +/* + * Ignore: this is an internal helper. + * + * This is a helper function to help force C99-correctness during compilation. + * Under strict compilation modes, variadic macro arguments can't be empty. + * However, variadic function arguments can be. Using a function therefore lets + * us statically check that at least one (string) argument was passed, + * independent of the compilation flags. + */ +static INLINE_KEYWORD UNUSED_ATTR +void _force_has_format_string(const char *format, ...) { + (void)format; +} + +/* + * Ignore: this is an internal helper. + * + * We want to force this function invocation to be syntactically correct, but + * we don't want to force runtime evaluation of its arguments. + */ +#define _FORCE_HAS_FORMAT_STRING(...) \ + if (0) { \ + _force_has_format_string(__VA_ARGS__); \ + } + +/* + * Return the specified error if the condition evaluates to true. + * + * In debug modes, prints additional information. + * In order to do that (particularly, printing the conditional that failed), + * this can't just wrap RETURN_ERROR(). + */ +#define RETURN_ERROR_IF(cond, err, ...) \ + if (cond) { \ + RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", \ + __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \ + _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \ + RAWLOG(3, ": " __VA_ARGS__); \ + RAWLOG(3, "\n"); \ + return ERROR(err); \ + } + +/* + * Unconditionally return the specified error. + * + * In debug modes, prints additional information. + */ +#define RETURN_ERROR(err, ...) \ + do { \ + RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", \ + __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \ + _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \ + RAWLOG(3, ": " __VA_ARGS__); \ + RAWLOG(3, "\n"); \ + return ERROR(err); \ + } while(0); + +/* + * If the provided expression evaluates to an error code, returns that error code. + * + * In debug modes, prints additional information. + */ +#define FORWARD_IF_ERROR(err, ...) \ + do { \ + size_t const err_code = (err); \ + if (ERR_isError(err_code)) { \ + RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", \ + __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \ + _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \ + RAWLOG(3, ": " __VA_ARGS__); \ + RAWLOG(3, "\n"); \ + return err_code; \ + } \ + } while(0); + + +/*-************************************* +* Common constants +***************************************/ +#define ZSTD_OPT_NUM (1<<12) + +#define ZSTD_REP_NUM 3 /* number of repcodes */ +#define ZSTD_REP_MOVE (ZSTD_REP_NUM-1) +static UNUSED_ATTR const U32 repStartValue[ZSTD_REP_NUM] = { 1, 4, 8 }; + +#define KB *(1 <<10) +#define MB *(1 <<20) +#define GB *(1U<<30) + +#define BIT7 128 +#define BIT6 64 +#define BIT5 32 +#define BIT4 16 +#define BIT1 2 +#define BIT0 1 + +#define ZSTD_WINDOWLOG_ABSOLUTEMIN 10 +static UNUSED_ATTR const size_t ZSTD_fcs_fieldSize[4] = { 0, 2, 4, 8 }; +static UNUSED_ATTR const size_t ZSTD_did_fieldSize[4] = { 0, 1, 2, 4 }; + +#define ZSTD_FRAMEIDSIZE 4 /* magic number size */ + +#define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */ +static UNUSED_ATTR const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE; +typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e; + +#define ZSTD_FRAMECHECKSUMSIZE 4 + +#define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */ +#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */) /* for a non-null block */ + +#define HufLog 12 +typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e; + +#define LONGNBSEQ 0x7F00 + +#define MINMATCH 3 + +#define Litbits 8 +#define MaxLit ((1<= 8 || (ovtype == ZSTD_no_overlap && diff <= -WILDCOPY_VECLEN)); + + if (ovtype == ZSTD_overlap_src_before_dst && diff < WILDCOPY_VECLEN) { + /* Handle short offset copies. */ + do { + COPY8(op, ip) + } while (op < oend); + } else { + assert(diff >= WILDCOPY_VECLEN || diff <= -WILDCOPY_VECLEN); + /* Separate out the first COPY16() call because the copy length is + * almost certain to be short, so the branches have different + * probabilities. Since it is almost certain to be short, only do + * one COPY16() in the first call. Then, do two calls per loop since + * at that point it is more likely to have a high trip count. + */ +#ifdef __aarch64__ + do { + COPY16(op, ip); + } + while (op < oend); +#else + ZSTD_copy16(op, ip); + if (16 >= length) return; + op += 16; + ip += 16; + do { + COPY16(op, ip); + COPY16(op, ip); + } + while (op < oend); +#endif + } +} + +MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + size_t const length = MIN(dstCapacity, srcSize); + if (length > 0) { + ZSTD_memcpy(dst, src, length); + } + return length; +} + +/* define "workspace is too large" as this number of times larger than needed */ +#define ZSTD_WORKSPACETOOLARGE_FACTOR 3 + +/* when workspace is continuously too large + * during at least this number of times, + * context's memory usage is considered wasteful, + * because it's sized to handle a worst case scenario which rarely happens. + * In which case, resize it down to free some memory */ +#define ZSTD_WORKSPACETOOLARGE_MAXDURATION 128 + +/* Controls whether the input/output buffer is buffered or stable. */ +typedef enum { + ZSTD_bm_buffered = 0, /* Buffer the input/output */ + ZSTD_bm_stable = 1 /* ZSTD_inBuffer/ZSTD_outBuffer is stable */ +} ZSTD_bufferMode_e; + + +/*-******************************************* +* Private declarations +*********************************************/ +typedef struct seqDef_s { + U32 offset; /* Offset code of the sequence */ + U16 litLength; + U16 matchLength; +} seqDef; + +typedef struct { + seqDef* sequencesStart; + seqDef* sequences; /* ptr to end of sequences */ + BYTE* litStart; + BYTE* lit; /* ptr to end of literals */ + BYTE* llCode; + BYTE* mlCode; + BYTE* ofCode; + size_t maxNbSeq; + size_t maxNbLit; + + /* longLengthPos and longLengthID to allow us to represent either a single litLength or matchLength + * in the seqStore that has a value larger than U16 (if it exists). To do so, we increment + * the existing value of the litLength or matchLength by 0x10000. + */ + U32 longLengthID; /* 0 == no longLength; 1 == Represent the long literal; 2 == Represent the long match; */ + U32 longLengthPos; /* Index of the sequence to apply long length modification to */ +} seqStore_t; + +typedef struct { + U32 litLength; + U32 matchLength; +} ZSTD_sequenceLength; + +/* + * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences + * indicated by longLengthPos and longLengthID, and adds MINMATCH back to matchLength. + */ +MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq) +{ + ZSTD_sequenceLength seqLen; + seqLen.litLength = seq->litLength; + seqLen.matchLength = seq->matchLength + MINMATCH; + if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) { + if (seqStore->longLengthID == 1) { + seqLen.litLength += 0xFFFF; + } + if (seqStore->longLengthID == 2) { + seqLen.matchLength += 0xFFFF; + } + } + return seqLen; +} + +/* + * Contains the compressed frame size and an upper-bound for the decompressed frame size. + * Note: before using `compressedSize`, check for errors using ZSTD_isError(). + * similarly, before using `decompressedBound`, check for errors using: + * `decompressedBound != ZSTD_CONTENTSIZE_ERROR` + */ +typedef struct { + size_t compressedSize; + unsigned long long decompressedBound; +} ZSTD_frameSizeInfo; /* decompress & legacy */ + +const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */ +void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */ + +/* custom memory allocation functions */ +void* ZSTD_customMalloc(size_t size, ZSTD_customMem customMem); +void* ZSTD_customCalloc(size_t size, ZSTD_customMem customMem); +void ZSTD_customFree(void* ptr, ZSTD_customMem customMem); + + +MEM_STATIC U32 ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus */ +{ + assert(val != 0); + { +# if (__GNUC__ >= 3) /* GCC Intrinsic */ + return __builtin_clz (val) ^ 31; +# else /* Software version */ + static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 }; + U32 v = val; + v |= v >> 1; + v |= v >> 2; + v |= v >> 4; + v |= v >> 8; + v |= v >> 16; + return DeBruijnClz[(v * 0x07C4ACDDU) >> 27]; +# endif + } +} + + +/* ZSTD_invalidateRepCodes() : + * ensures next compression will not use repcodes from previous block. + * Note : only works with regular variant; + * do not use with extDict variant ! */ +void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx); /* zstdmt, adaptive_compression (shouldn't get this definition from here) */ + + +typedef struct { + blockType_e blockType; + U32 lastBlock; + U32 origSize; +} blockProperties_t; /* declared here for decompress and fullbench */ + +/*! ZSTD_getcBlockSize() : + * Provides the size of compressed block from block header `src` */ +/* Used by: decompress, fullbench (does not get its definition from here) */ +size_t ZSTD_getcBlockSize(const void* src, size_t srcSize, + blockProperties_t* bpPtr); + +/*! ZSTD_decodeSeqHeaders() : + * decode sequence header from src */ +/* Used by: decompress, fullbench (does not get its definition from here) */ +size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, + const void* src, size_t srcSize); + + + +#endif /* ZSTD_CCOMMON_H_MODULE */ diff --git a/lib/zstd/compress.c b/lib/zstd/compress.c deleted file mode 100644 index 57aaa64306a0..000000000000 --- a/lib/zstd/compress.c +++ /dev/null @@ -1,3534 +0,0 @@ -/** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -/*-************************************* -* Dependencies -***************************************/ -#include "fse.h" -#include "huf.h" -#include "mem.h" -#include "zstd_internal.h" /* includes zstd.h */ -#include -#include -#include /* memset */ - -/*-************************************* -* Constants -***************************************/ -static const U32 g_searchStrength = 8; /* control skip over incompressible data */ -#define HASH_READ_SIZE 8 -typedef enum { ZSTDcs_created = 0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e; - -/*-************************************* -* Helper functions -***************************************/ -size_t ZSTD_compressBound(size_t srcSize) { return FSE_compressBound(srcSize) + 12; } - -/*-************************************* -* Sequence storage -***************************************/ -static void ZSTD_resetSeqStore(seqStore_t *ssPtr) -{ - ssPtr->lit = ssPtr->litStart; - ssPtr->sequences = ssPtr->sequencesStart; - ssPtr->longLengthID = 0; -} - -/*-************************************* -* Context memory management -***************************************/ -struct ZSTD_CCtx_s { - const BYTE *nextSrc; /* next block here to continue on curr prefix */ - const BYTE *base; /* All regular indexes relative to this position */ - const BYTE *dictBase; /* extDict indexes relative to this position */ - U32 dictLimit; /* below that point, need extDict */ - U32 lowLimit; /* below that point, no more data */ - U32 nextToUpdate; /* index from which to continue dictionary update */ - U32 nextToUpdate3; /* index from which to continue dictionary update */ - U32 hashLog3; /* dispatch table : larger == faster, more memory */ - U32 loadedDictEnd; /* index of end of dictionary */ - U32 forceWindow; /* force back-references to respect limit of 1< 3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, cParams.windowLog); - size_t const h3Size = ((size_t)1) << hashLog3; - size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32); - size_t const optSpace = - ((MaxML + 1) + (MaxLL + 1) + (MaxOff + 1) + (1 << Litbits)) * sizeof(U32) + (ZSTD_OPT_NUM + 1) * (sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t)); - size_t const workspaceSize = tableSpace + (256 * sizeof(U32)) /* huffTable */ + tokenSpace + - (((cParams.strategy == ZSTD_btopt) || (cParams.strategy == ZSTD_btopt2)) ? optSpace : 0); - - return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_CCtx)) + ZSTD_ALIGN(workspaceSize); -} - -static ZSTD_CCtx *ZSTD_createCCtx_advanced(ZSTD_customMem customMem) -{ - ZSTD_CCtx *cctx; - if (!customMem.customAlloc || !customMem.customFree) - return NULL; - cctx = (ZSTD_CCtx *)ZSTD_malloc(sizeof(ZSTD_CCtx), customMem); - if (!cctx) - return NULL; - memset(cctx, 0, sizeof(ZSTD_CCtx)); - cctx->customMem = customMem; - return cctx; -} - -ZSTD_CCtx *ZSTD_initCCtx(void *workspace, size_t workspaceSize) -{ - ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize); - ZSTD_CCtx *cctx = ZSTD_createCCtx_advanced(stackMem); - if (cctx) { - cctx->workSpace = ZSTD_stackAllocAll(cctx->customMem.opaque, &cctx->workSpaceSize); - } - return cctx; -} - -size_t ZSTD_freeCCtx(ZSTD_CCtx *cctx) -{ - if (cctx == NULL) - return 0; /* support free on NULL */ - ZSTD_free(cctx->workSpace, cctx->customMem); - ZSTD_free(cctx, cctx->customMem); - return 0; /* reserved as a potential error code in the future */ -} - -const seqStore_t *ZSTD_getSeqStore(const ZSTD_CCtx *ctx) /* hidden interface */ { return &(ctx->seqStore); } - -static ZSTD_parameters ZSTD_getParamsFromCCtx(const ZSTD_CCtx *cctx) { return cctx->params; } - -/** ZSTD_checkParams() : - ensure param values remain within authorized range. - @return : 0, or an error code if one value is beyond authorized range */ -size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams) -{ -#define CLAMPCHECK(val, min, max) \ - { \ - if ((val < min) | (val > max)) \ - return ERROR(compressionParameter_unsupported); \ - } - CLAMPCHECK(cParams.windowLog, ZSTD_WINDOWLOG_MIN, ZSTD_WINDOWLOG_MAX); - CLAMPCHECK(cParams.chainLog, ZSTD_CHAINLOG_MIN, ZSTD_CHAINLOG_MAX); - CLAMPCHECK(cParams.hashLog, ZSTD_HASHLOG_MIN, ZSTD_HASHLOG_MAX); - CLAMPCHECK(cParams.searchLog, ZSTD_SEARCHLOG_MIN, ZSTD_SEARCHLOG_MAX); - CLAMPCHECK(cParams.searchLength, ZSTD_SEARCHLENGTH_MIN, ZSTD_SEARCHLENGTH_MAX); - CLAMPCHECK(cParams.targetLength, ZSTD_TARGETLENGTH_MIN, ZSTD_TARGETLENGTH_MAX); - if ((U32)(cParams.strategy) > (U32)ZSTD_btopt2) - return ERROR(compressionParameter_unsupported); - return 0; -} - -/** ZSTD_cycleLog() : - * condition for correct operation : hashLog > 1 */ -static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat) -{ - U32 const btScale = ((U32)strat >= (U32)ZSTD_btlazy2); - return hashLog - btScale; -} - -/** ZSTD_adjustCParams() : - optimize `cPar` for a given input (`srcSize` and `dictSize`). - mostly downsizing to reduce memory consumption and initialization. - Both `srcSize` and `dictSize` are optional (use 0 if unknown), - but if both are 0, no optimization can be done. - Note : cPar is considered validated at this stage. Use ZSTD_checkParams() to ensure that. */ -ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize) -{ - if (srcSize + dictSize == 0) - return cPar; /* no size information available : no adjustment */ - - /* resize params, to use less memory when necessary */ - { - U32 const minSrcSize = (srcSize == 0) ? 500 : 0; - U64 const rSize = srcSize + dictSize + minSrcSize; - if (rSize < ((U64)1 << ZSTD_WINDOWLOG_MAX)) { - U32 const srcLog = MAX(ZSTD_HASHLOG_MIN, ZSTD_highbit32((U32)(rSize)-1) + 1); - if (cPar.windowLog > srcLog) - cPar.windowLog = srcLog; - } - } - if (cPar.hashLog > cPar.windowLog) - cPar.hashLog = cPar.windowLog; - { - U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy); - if (cycleLog > cPar.windowLog) - cPar.chainLog -= (cycleLog - cPar.windowLog); - } - - if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN) - cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* required for frame header */ - - return cPar; -} - -static U32 ZSTD_equivalentParams(ZSTD_parameters param1, ZSTD_parameters param2) -{ - return (param1.cParams.hashLog == param2.cParams.hashLog) & (param1.cParams.chainLog == param2.cParams.chainLog) & - (param1.cParams.strategy == param2.cParams.strategy) & ((param1.cParams.searchLength == 3) == (param2.cParams.searchLength == 3)); -} - -/*! ZSTD_continueCCtx() : - reuse CCtx without reset (note : requires no dictionary) */ -static size_t ZSTD_continueCCtx(ZSTD_CCtx *cctx, ZSTD_parameters params, U64 frameContentSize) -{ - U32 const end = (U32)(cctx->nextSrc - cctx->base); - cctx->params = params; - cctx->frameContentSize = frameContentSize; - cctx->lowLimit = end; - cctx->dictLimit = end; - cctx->nextToUpdate = end + 1; - cctx->stage = ZSTDcs_init; - cctx->dictID = 0; - cctx->loadedDictEnd = 0; - { - int i; - for (i = 0; i < ZSTD_REP_NUM; i++) - cctx->rep[i] = repStartValue[i]; - } - cctx->seqStore.litLengthSum = 0; /* force reset of btopt stats */ - xxh64_reset(&cctx->xxhState, 0); - return 0; -} - -typedef enum { ZSTDcrp_continue, ZSTDcrp_noMemset, ZSTDcrp_fullReset } ZSTD_compResetPolicy_e; - -/*! ZSTD_resetCCtx_advanced() : - note : `params` must be validated */ -static size_t ZSTD_resetCCtx_advanced(ZSTD_CCtx *zc, ZSTD_parameters params, U64 frameContentSize, ZSTD_compResetPolicy_e const crp) -{ - if (crp == ZSTDcrp_continue) - if (ZSTD_equivalentParams(params, zc->params)) { - zc->flagStaticTables = 0; - zc->flagStaticHufTable = HUF_repeat_none; - return ZSTD_continueCCtx(zc, params, frameContentSize); - } - - { - size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, (size_t)1 << params.cParams.windowLog); - U32 const divider = (params.cParams.searchLength == 3) ? 3 : 4; - size_t const maxNbSeq = blockSize / divider; - size_t const tokenSpace = blockSize + 11 * maxNbSeq; - size_t const chainSize = (params.cParams.strategy == ZSTD_fast) ? 0 : (1 << params.cParams.chainLog); - size_t const hSize = ((size_t)1) << params.cParams.hashLog; - U32 const hashLog3 = (params.cParams.searchLength > 3) ? 0 : MIN(ZSTD_HASHLOG3_MAX, params.cParams.windowLog); - size_t const h3Size = ((size_t)1) << hashLog3; - size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32); - void *ptr; - - /* Check if workSpace is large enough, alloc a new one if needed */ - { - size_t const optSpace = ((MaxML + 1) + (MaxLL + 1) + (MaxOff + 1) + (1 << Litbits)) * sizeof(U32) + - (ZSTD_OPT_NUM + 1) * (sizeof(ZSTD_match_t) + sizeof(ZSTD_optimal_t)); - size_t const neededSpace = tableSpace + (256 * sizeof(U32)) /* huffTable */ + tokenSpace + - (((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) ? optSpace : 0); - if (zc->workSpaceSize < neededSpace) { - ZSTD_free(zc->workSpace, zc->customMem); - zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem); - if (zc->workSpace == NULL) - return ERROR(memory_allocation); - zc->workSpaceSize = neededSpace; - } - } - - if (crp != ZSTDcrp_noMemset) - memset(zc->workSpace, 0, tableSpace); /* reset tables only */ - xxh64_reset(&zc->xxhState, 0); - zc->hashLog3 = hashLog3; - zc->hashTable = (U32 *)(zc->workSpace); - zc->chainTable = zc->hashTable + hSize; - zc->hashTable3 = zc->chainTable + chainSize; - ptr = zc->hashTable3 + h3Size; - zc->hufTable = (HUF_CElt *)ptr; - zc->flagStaticTables = 0; - zc->flagStaticHufTable = HUF_repeat_none; - ptr = ((U32 *)ptr) + 256; /* note : HUF_CElt* is incomplete type, size is simulated using U32 */ - - zc->nextToUpdate = 1; - zc->nextSrc = NULL; - zc->base = NULL; - zc->dictBase = NULL; - zc->dictLimit = 0; - zc->lowLimit = 0; - zc->params = params; - zc->blockSize = blockSize; - zc->frameContentSize = frameContentSize; - { - int i; - for (i = 0; i < ZSTD_REP_NUM; i++) - zc->rep[i] = repStartValue[i]; - } - - if ((params.cParams.strategy == ZSTD_btopt) || (params.cParams.strategy == ZSTD_btopt2)) { - zc->seqStore.litFreq = (U32 *)ptr; - zc->seqStore.litLengthFreq = zc->seqStore.litFreq + (1 << Litbits); - zc->seqStore.matchLengthFreq = zc->seqStore.litLengthFreq + (MaxLL + 1); - zc->seqStore.offCodeFreq = zc->seqStore.matchLengthFreq + (MaxML + 1); - ptr = zc->seqStore.offCodeFreq + (MaxOff + 1); - zc->seqStore.matchTable = (ZSTD_match_t *)ptr; - ptr = zc->seqStore.matchTable + ZSTD_OPT_NUM + 1; - zc->seqStore.priceTable = (ZSTD_optimal_t *)ptr; - ptr = zc->seqStore.priceTable + ZSTD_OPT_NUM + 1; - zc->seqStore.litLengthSum = 0; - } - zc->seqStore.sequencesStart = (seqDef *)ptr; - ptr = zc->seqStore.sequencesStart + maxNbSeq; - zc->seqStore.llCode = (BYTE *)ptr; - zc->seqStore.mlCode = zc->seqStore.llCode + maxNbSeq; - zc->seqStore.ofCode = zc->seqStore.mlCode + maxNbSeq; - zc->seqStore.litStart = zc->seqStore.ofCode + maxNbSeq; - - zc->stage = ZSTDcs_init; - zc->dictID = 0; - zc->loadedDictEnd = 0; - - return 0; - } -} - -/* ZSTD_invalidateRepCodes() : - * ensures next compression will not use repcodes from previous block. - * Note : only works with regular variant; - * do not use with extDict variant ! */ -void ZSTD_invalidateRepCodes(ZSTD_CCtx *cctx) -{ - int i; - for (i = 0; i < ZSTD_REP_NUM; i++) - cctx->rep[i] = 0; -} - -/*! ZSTD_copyCCtx() : -* Duplicate an existing context `srcCCtx` into another one `dstCCtx`. -* Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). -* @return : 0, or an error code */ -size_t ZSTD_copyCCtx(ZSTD_CCtx *dstCCtx, const ZSTD_CCtx *srcCCtx, unsigned long long pledgedSrcSize) -{ - if (srcCCtx->stage != ZSTDcs_init) - return ERROR(stage_wrong); - - memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem)); - { - ZSTD_parameters params = srcCCtx->params; - params.fParams.contentSizeFlag = (pledgedSrcSize > 0); - ZSTD_resetCCtx_advanced(dstCCtx, params, pledgedSrcSize, ZSTDcrp_noMemset); - } - - /* copy tables */ - { - size_t const chainSize = (srcCCtx->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << srcCCtx->params.cParams.chainLog); - size_t const hSize = ((size_t)1) << srcCCtx->params.cParams.hashLog; - size_t const h3Size = (size_t)1 << srcCCtx->hashLog3; - size_t const tableSpace = (chainSize + hSize + h3Size) * sizeof(U32); - memcpy(dstCCtx->workSpace, srcCCtx->workSpace, tableSpace); - } - - /* copy dictionary offsets */ - dstCCtx->nextToUpdate = srcCCtx->nextToUpdate; - dstCCtx->nextToUpdate3 = srcCCtx->nextToUpdate3; - dstCCtx->nextSrc = srcCCtx->nextSrc; - dstCCtx->base = srcCCtx->base; - dstCCtx->dictBase = srcCCtx->dictBase; - dstCCtx->dictLimit = srcCCtx->dictLimit; - dstCCtx->lowLimit = srcCCtx->lowLimit; - dstCCtx->loadedDictEnd = srcCCtx->loadedDictEnd; - dstCCtx->dictID = srcCCtx->dictID; - - /* copy entropy tables */ - dstCCtx->flagStaticTables = srcCCtx->flagStaticTables; - dstCCtx->flagStaticHufTable = srcCCtx->flagStaticHufTable; - if (srcCCtx->flagStaticTables) { - memcpy(dstCCtx->litlengthCTable, srcCCtx->litlengthCTable, sizeof(dstCCtx->litlengthCTable)); - memcpy(dstCCtx->matchlengthCTable, srcCCtx->matchlengthCTable, sizeof(dstCCtx->matchlengthCTable)); - memcpy(dstCCtx->offcodeCTable, srcCCtx->offcodeCTable, sizeof(dstCCtx->offcodeCTable)); - } - if (srcCCtx->flagStaticHufTable) { - memcpy(dstCCtx->hufTable, srcCCtx->hufTable, 256 * 4); - } - - return 0; -} - -/*! ZSTD_reduceTable() : -* reduce table indexes by `reducerValue` */ -static void ZSTD_reduceTable(U32 *const table, U32 const size, U32 const reducerValue) -{ - U32 u; - for (u = 0; u < size; u++) { - if (table[u] < reducerValue) - table[u] = 0; - else - table[u] -= reducerValue; - } -} - -/*! ZSTD_reduceIndex() : -* rescale all indexes to avoid future overflow (indexes are U32) */ -static void ZSTD_reduceIndex(ZSTD_CCtx *zc, const U32 reducerValue) -{ - { - U32 const hSize = 1 << zc->params.cParams.hashLog; - ZSTD_reduceTable(zc->hashTable, hSize, reducerValue); - } - - { - U32 const chainSize = (zc->params.cParams.strategy == ZSTD_fast) ? 0 : (1 << zc->params.cParams.chainLog); - ZSTD_reduceTable(zc->chainTable, chainSize, reducerValue); - } - - { - U32 const h3Size = (zc->hashLog3) ? 1 << zc->hashLog3 : 0; - ZSTD_reduceTable(zc->hashTable3, h3Size, reducerValue); - } -} - -/*-******************************************************* -* Block entropic compression -*********************************************************/ - -/* See doc/zstd_compression_format.md for detailed format description */ - -size_t ZSTD_noCompressBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - if (srcSize + ZSTD_blockHeaderSize > dstCapacity) - return ERROR(dstSize_tooSmall); - memcpy((BYTE *)dst + ZSTD_blockHeaderSize, src, srcSize); - ZSTD_writeLE24(dst, (U32)(srcSize << 2) + (U32)bt_raw); - return ZSTD_blockHeaderSize + srcSize; -} - -static size_t ZSTD_noCompressLiterals(void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - BYTE *const ostart = (BYTE * const)dst; - U32 const flSize = 1 + (srcSize > 31) + (srcSize > 4095); - - if (srcSize + flSize > dstCapacity) - return ERROR(dstSize_tooSmall); - - switch (flSize) { - case 1: /* 2 - 1 - 5 */ ostart[0] = (BYTE)((U32)set_basic + (srcSize << 3)); break; - case 2: /* 2 - 2 - 12 */ ZSTD_writeLE16(ostart, (U16)((U32)set_basic + (1 << 2) + (srcSize << 4))); break; - default: /*note : should not be necessary : flSize is within {1,2,3} */ - case 3: /* 2 - 2 - 20 */ ZSTD_writeLE32(ostart, (U32)((U32)set_basic + (3 << 2) + (srcSize << 4))); break; - } - - memcpy(ostart + flSize, src, srcSize); - return srcSize + flSize; -} - -static size_t ZSTD_compressRleLiteralsBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - BYTE *const ostart = (BYTE * const)dst; - U32 const flSize = 1 + (srcSize > 31) + (srcSize > 4095); - - (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */ - - switch (flSize) { - case 1: /* 2 - 1 - 5 */ ostart[0] = (BYTE)((U32)set_rle + (srcSize << 3)); break; - case 2: /* 2 - 2 - 12 */ ZSTD_writeLE16(ostart, (U16)((U32)set_rle + (1 << 2) + (srcSize << 4))); break; - default: /*note : should not be necessary : flSize is necessarily within {1,2,3} */ - case 3: /* 2 - 2 - 20 */ ZSTD_writeLE32(ostart, (U32)((U32)set_rle + (3 << 2) + (srcSize << 4))); break; - } - - ostart[flSize] = *(const BYTE *)src; - return flSize + 1; -} - -static size_t ZSTD_minGain(size_t srcSize) { return (srcSize >> 6) + 2; } - -static size_t ZSTD_compressLiterals(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - size_t const minGain = ZSTD_minGain(srcSize); - size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB); - BYTE *const ostart = (BYTE *)dst; - U32 singleStream = srcSize < 256; - symbolEncodingType_e hType = set_compressed; - size_t cLitSize; - -/* small ? don't even attempt compression (speed opt) */ -#define LITERAL_NOENTROPY 63 - { - size_t const minLitSize = zc->flagStaticHufTable == HUF_repeat_valid ? 6 : LITERAL_NOENTROPY; - if (srcSize <= minLitSize) - return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); - } - - if (dstCapacity < lhSize + 1) - return ERROR(dstSize_tooSmall); /* not enough space for compression */ - { - HUF_repeat repeat = zc->flagStaticHufTable; - int const preferRepeat = zc->params.cParams.strategy < ZSTD_lazy ? srcSize <= 1024 : 0; - if (repeat == HUF_repeat_valid && lhSize == 3) - singleStream = 1; - cLitSize = singleStream ? HUF_compress1X_repeat(ostart + lhSize, dstCapacity - lhSize, src, srcSize, 255, 11, zc->tmpCounters, - sizeof(zc->tmpCounters), zc->hufTable, &repeat, preferRepeat) - : HUF_compress4X_repeat(ostart + lhSize, dstCapacity - lhSize, src, srcSize, 255, 11, zc->tmpCounters, - sizeof(zc->tmpCounters), zc->hufTable, &repeat, preferRepeat); - if (repeat != HUF_repeat_none) { - hType = set_repeat; - } /* reused the existing table */ - else { - zc->flagStaticHufTable = HUF_repeat_check; - } /* now have a table to reuse */ - } - - if ((cLitSize == 0) | (cLitSize >= srcSize - minGain)) { - zc->flagStaticHufTable = HUF_repeat_none; - return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); - } - if (cLitSize == 1) { - zc->flagStaticHufTable = HUF_repeat_none; - return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize); - } - - /* Build header */ - switch (lhSize) { - case 3: /* 2 - 2 - 10 - 10 */ - { - U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 14); - ZSTD_writeLE24(ostart, lhc); - break; - } - case 4: /* 2 - 2 - 14 - 14 */ - { - U32 const lhc = hType + (2 << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 18); - ZSTD_writeLE32(ostart, lhc); - break; - } - default: /* should not be necessary, lhSize is only {3,4,5} */ - case 5: /* 2 - 2 - 18 - 18 */ - { - U32 const lhc = hType + (3 << 2) + ((U32)srcSize << 4) + ((U32)cLitSize << 22); - ZSTD_writeLE32(ostart, lhc); - ostart[4] = (BYTE)(cLitSize >> 10); - break; - } - } - return lhSize + cLitSize; -} - -static const BYTE LL_Code[64] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 16, 17, 17, 18, 18, - 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 22, 22, 22, 22, 22, 22, 22, 22, 23, 23, 23, 23, - 23, 23, 23, 23, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24}; - -static const BYTE ML_Code[128] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, - 26, 27, 28, 29, 30, 31, 32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37, 38, 38, 38, 38, - 38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, - 40, 40, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 42, 42, 42, 42, 42, 42, 42, 42, - 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42}; - -void ZSTD_seqToCodes(const seqStore_t *seqStorePtr) -{ - BYTE const LL_deltaCode = 19; - BYTE const ML_deltaCode = 36; - const seqDef *const sequences = seqStorePtr->sequencesStart; - BYTE *const llCodeTable = seqStorePtr->llCode; - BYTE *const ofCodeTable = seqStorePtr->ofCode; - BYTE *const mlCodeTable = seqStorePtr->mlCode; - U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); - U32 u; - for (u = 0; u < nbSeq; u++) { - U32 const llv = sequences[u].litLength; - U32 const mlv = sequences[u].matchLength; - llCodeTable[u] = (llv > 63) ? (BYTE)ZSTD_highbit32(llv) + LL_deltaCode : LL_Code[llv]; - ofCodeTable[u] = (BYTE)ZSTD_highbit32(sequences[u].offset); - mlCodeTable[u] = (mlv > 127) ? (BYTE)ZSTD_highbit32(mlv) + ML_deltaCode : ML_Code[mlv]; - } - if (seqStorePtr->longLengthID == 1) - llCodeTable[seqStorePtr->longLengthPos] = MaxLL; - if (seqStorePtr->longLengthID == 2) - mlCodeTable[seqStorePtr->longLengthPos] = MaxML; -} - -ZSTD_STATIC size_t ZSTD_compressSequences_internal(ZSTD_CCtx *zc, void *dst, size_t dstCapacity) -{ - const int longOffsets = zc->params.cParams.windowLog > STREAM_ACCUMULATOR_MIN; - const seqStore_t *seqStorePtr = &(zc->seqStore); - FSE_CTable *CTable_LitLength = zc->litlengthCTable; - FSE_CTable *CTable_OffsetBits = zc->offcodeCTable; - FSE_CTable *CTable_MatchLength = zc->matchlengthCTable; - U32 LLtype, Offtype, MLtype; /* compressed, raw or rle */ - const seqDef *const sequences = seqStorePtr->sequencesStart; - const BYTE *const ofCodeTable = seqStorePtr->ofCode; - const BYTE *const llCodeTable = seqStorePtr->llCode; - const BYTE *const mlCodeTable = seqStorePtr->mlCode; - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstCapacity; - BYTE *op = ostart; - size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart; - BYTE *seqHead; - - U32 *count; - S16 *norm; - U32 *workspace; - size_t workspaceSize = sizeof(zc->tmpCounters); - { - size_t spaceUsed32 = 0; - count = (U32 *)zc->tmpCounters + spaceUsed32; - spaceUsed32 += MaxSeq + 1; - norm = (S16 *)((U32 *)zc->tmpCounters + spaceUsed32); - spaceUsed32 += ALIGN(sizeof(S16) * (MaxSeq + 1), sizeof(U32)) >> 2; - - workspace = (U32 *)zc->tmpCounters + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - } - - /* Compress literals */ - { - const BYTE *const literals = seqStorePtr->litStart; - size_t const litSize = seqStorePtr->lit - literals; - size_t const cSize = ZSTD_compressLiterals(zc, op, dstCapacity, literals, litSize); - if (ZSTD_isError(cSize)) - return cSize; - op += cSize; - } - - /* Sequences Header */ - if ((oend - op) < 3 /*max nbSeq Size*/ + 1 /*seqHead */) - return ERROR(dstSize_tooSmall); - if (nbSeq < 0x7F) - *op++ = (BYTE)nbSeq; - else if (nbSeq < LONGNBSEQ) - op[0] = (BYTE)((nbSeq >> 8) + 0x80), op[1] = (BYTE)nbSeq, op += 2; - else - op[0] = 0xFF, ZSTD_writeLE16(op + 1, (U16)(nbSeq - LONGNBSEQ)), op += 3; - if (nbSeq == 0) - return op - ostart; - - /* seqHead : flags for FSE encoding type */ - seqHead = op++; - -#define MIN_SEQ_FOR_DYNAMIC_FSE 64 -#define MAX_SEQ_FOR_STATIC_FSE 1000 - - /* convert length/distances into codes */ - ZSTD_seqToCodes(seqStorePtr); - - /* CTable for Literal Lengths */ - { - U32 max = MaxLL; - size_t const mostFrequent = FSE_countFast_wksp(count, &max, llCodeTable, nbSeq, workspace); - if ((mostFrequent == nbSeq) && (nbSeq > 2)) { - *op++ = llCodeTable[0]; - FSE_buildCTable_rle(CTable_LitLength, (BYTE)max); - LLtype = set_rle; - } else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) { - LLtype = set_repeat; - } else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (LL_defaultNormLog - 1)))) { - FSE_buildCTable_wksp(CTable_LitLength, LL_defaultNorm, MaxLL, LL_defaultNormLog, workspace, workspaceSize); - LLtype = set_basic; - } else { - size_t nbSeq_1 = nbSeq; - const U32 tableLog = FSE_optimalTableLog(LLFSELog, nbSeq, max); - if (count[llCodeTable[nbSeq - 1]] > 1) { - count[llCodeTable[nbSeq - 1]]--; - nbSeq_1--; - } - FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max); - { - size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */ - if (FSE_isError(NCountSize)) - return NCountSize; - op += NCountSize; - } - FSE_buildCTable_wksp(CTable_LitLength, norm, max, tableLog, workspace, workspaceSize); - LLtype = set_compressed; - } - } - - /* CTable for Offsets */ - { - U32 max = MaxOff; - size_t const mostFrequent = FSE_countFast_wksp(count, &max, ofCodeTable, nbSeq, workspace); - if ((mostFrequent == nbSeq) && (nbSeq > 2)) { - *op++ = ofCodeTable[0]; - FSE_buildCTable_rle(CTable_OffsetBits, (BYTE)max); - Offtype = set_rle; - } else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) { - Offtype = set_repeat; - } else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (OF_defaultNormLog - 1)))) { - FSE_buildCTable_wksp(CTable_OffsetBits, OF_defaultNorm, MaxOff, OF_defaultNormLog, workspace, workspaceSize); - Offtype = set_basic; - } else { - size_t nbSeq_1 = nbSeq; - const U32 tableLog = FSE_optimalTableLog(OffFSELog, nbSeq, max); - if (count[ofCodeTable[nbSeq - 1]] > 1) { - count[ofCodeTable[nbSeq - 1]]--; - nbSeq_1--; - } - FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max); - { - size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */ - if (FSE_isError(NCountSize)) - return NCountSize; - op += NCountSize; - } - FSE_buildCTable_wksp(CTable_OffsetBits, norm, max, tableLog, workspace, workspaceSize); - Offtype = set_compressed; - } - } - - /* CTable for MatchLengths */ - { - U32 max = MaxML; - size_t const mostFrequent = FSE_countFast_wksp(count, &max, mlCodeTable, nbSeq, workspace); - if ((mostFrequent == nbSeq) && (nbSeq > 2)) { - *op++ = *mlCodeTable; - FSE_buildCTable_rle(CTable_MatchLength, (BYTE)max); - MLtype = set_rle; - } else if ((zc->flagStaticTables) && (nbSeq < MAX_SEQ_FOR_STATIC_FSE)) { - MLtype = set_repeat; - } else if ((nbSeq < MIN_SEQ_FOR_DYNAMIC_FSE) || (mostFrequent < (nbSeq >> (ML_defaultNormLog - 1)))) { - FSE_buildCTable_wksp(CTable_MatchLength, ML_defaultNorm, MaxML, ML_defaultNormLog, workspace, workspaceSize); - MLtype = set_basic; - } else { - size_t nbSeq_1 = nbSeq; - const U32 tableLog = FSE_optimalTableLog(MLFSELog, nbSeq, max); - if (count[mlCodeTable[nbSeq - 1]] > 1) { - count[mlCodeTable[nbSeq - 1]]--; - nbSeq_1--; - } - FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max); - { - size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */ - if (FSE_isError(NCountSize)) - return NCountSize; - op += NCountSize; - } - FSE_buildCTable_wksp(CTable_MatchLength, norm, max, tableLog, workspace, workspaceSize); - MLtype = set_compressed; - } - } - - *seqHead = (BYTE)((LLtype << 6) + (Offtype << 4) + (MLtype << 2)); - zc->flagStaticTables = 0; - - /* Encoding Sequences */ - { - BIT_CStream_t blockStream; - FSE_CState_t stateMatchLength; - FSE_CState_t stateOffsetBits; - FSE_CState_t stateLitLength; - - CHECK_E(BIT_initCStream(&blockStream, op, oend - op), dstSize_tooSmall); /* not enough space remaining */ - - /* first symbols */ - FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq - 1]); - FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq - 1]); - FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq - 1]); - BIT_addBits(&blockStream, sequences[nbSeq - 1].litLength, LL_bits[llCodeTable[nbSeq - 1]]); - if (ZSTD_32bits()) - BIT_flushBits(&blockStream); - BIT_addBits(&blockStream, sequences[nbSeq - 1].matchLength, ML_bits[mlCodeTable[nbSeq - 1]]); - if (ZSTD_32bits()) - BIT_flushBits(&blockStream); - if (longOffsets) { - U32 const ofBits = ofCodeTable[nbSeq - 1]; - int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN - 1); - if (extraBits) { - BIT_addBits(&blockStream, sequences[nbSeq - 1].offset, extraBits); - BIT_flushBits(&blockStream); - } - BIT_addBits(&blockStream, sequences[nbSeq - 1].offset >> extraBits, ofBits - extraBits); - } else { - BIT_addBits(&blockStream, sequences[nbSeq - 1].offset, ofCodeTable[nbSeq - 1]); - } - BIT_flushBits(&blockStream); - - { - size_t n; - for (n = nbSeq - 2; n < nbSeq; n--) { /* intentional underflow */ - BYTE const llCode = llCodeTable[n]; - BYTE const ofCode = ofCodeTable[n]; - BYTE const mlCode = mlCodeTable[n]; - U32 const llBits = LL_bits[llCode]; - U32 const ofBits = ofCode; /* 32b*/ /* 64b*/ - U32 const mlBits = ML_bits[mlCode]; - /* (7)*/ /* (7)*/ - FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode); /* 15 */ /* 15 */ - FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode); /* 24 */ /* 24 */ - if (ZSTD_32bits()) - BIT_flushBits(&blockStream); /* (7)*/ - FSE_encodeSymbol(&blockStream, &stateLitLength, llCode); /* 16 */ /* 33 */ - if (ZSTD_32bits() || (ofBits + mlBits + llBits >= 64 - 7 - (LLFSELog + MLFSELog + OffFSELog))) - BIT_flushBits(&blockStream); /* (7)*/ - BIT_addBits(&blockStream, sequences[n].litLength, llBits); - if (ZSTD_32bits() && ((llBits + mlBits) > 24)) - BIT_flushBits(&blockStream); - BIT_addBits(&blockStream, sequences[n].matchLength, mlBits); - if (ZSTD_32bits()) - BIT_flushBits(&blockStream); /* (7)*/ - if (longOffsets) { - int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN - 1); - if (extraBits) { - BIT_addBits(&blockStream, sequences[n].offset, extraBits); - BIT_flushBits(&blockStream); /* (7)*/ - } - BIT_addBits(&blockStream, sequences[n].offset >> extraBits, ofBits - extraBits); /* 31 */ - } else { - BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */ - } - BIT_flushBits(&blockStream); /* (7)*/ - } - } - - FSE_flushCState(&blockStream, &stateMatchLength); - FSE_flushCState(&blockStream, &stateOffsetBits); - FSE_flushCState(&blockStream, &stateLitLength); - - { - size_t const streamSize = BIT_closeCStream(&blockStream); - if (streamSize == 0) - return ERROR(dstSize_tooSmall); /* not enough space */ - op += streamSize; - } - } - return op - ostart; -} - -ZSTD_STATIC size_t ZSTD_compressSequences(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, size_t srcSize) -{ - size_t const cSize = ZSTD_compressSequences_internal(zc, dst, dstCapacity); - size_t const minGain = ZSTD_minGain(srcSize); - size_t const maxCSize = srcSize - minGain; - /* If the srcSize <= dstCapacity, then there is enough space to write a - * raw uncompressed block. Since we ran out of space, the block must not - * be compressible, so fall back to a raw uncompressed block. - */ - int const uncompressibleError = cSize == ERROR(dstSize_tooSmall) && srcSize <= dstCapacity; - int i; - - if (ZSTD_isError(cSize) && !uncompressibleError) - return cSize; - if (cSize >= maxCSize || uncompressibleError) { - zc->flagStaticHufTable = HUF_repeat_none; - return 0; - } - /* confirm repcodes */ - for (i = 0; i < ZSTD_REP_NUM; i++) - zc->rep[i] = zc->repToConfirm[i]; - return cSize; -} - -/*! ZSTD_storeSeq() : - Store a sequence (literal length, literals, offset code and match length code) into seqStore_t. - `offsetCode` : distance to match, or 0 == repCode. - `matchCode` : matchLength - MINMATCH -*/ -ZSTD_STATIC void ZSTD_storeSeq(seqStore_t *seqStorePtr, size_t litLength, const void *literals, U32 offsetCode, size_t matchCode) -{ - /* copy Literals */ - ZSTD_wildcopy(seqStorePtr->lit, literals, litLength); - seqStorePtr->lit += litLength; - - /* literal Length */ - if (litLength > 0xFFFF) { - seqStorePtr->longLengthID = 1; - seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); - } - seqStorePtr->sequences[0].litLength = (U16)litLength; - - /* match offset */ - seqStorePtr->sequences[0].offset = offsetCode + 1; - - /* match Length */ - if (matchCode > 0xFFFF) { - seqStorePtr->longLengthID = 2; - seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); - } - seqStorePtr->sequences[0].matchLength = (U16)matchCode; - - seqStorePtr->sequences++; -} - -/*-************************************* -* Match length counter -***************************************/ -static unsigned ZSTD_NbCommonBytes(register size_t val) -{ - if (ZSTD_isLittleEndian()) { - if (ZSTD_64bits()) { - return (__builtin_ctzll((U64)val) >> 3); - } else { /* 32 bits */ - return (__builtin_ctz((U32)val) >> 3); - } - } else { /* Big Endian CPU */ - if (ZSTD_64bits()) { - return (__builtin_clzll(val) >> 3); - } else { /* 32 bits */ - return (__builtin_clz((U32)val) >> 3); - } - } -} - -static size_t ZSTD_count(const BYTE *pIn, const BYTE *pMatch, const BYTE *const pInLimit) -{ - const BYTE *const pStart = pIn; - const BYTE *const pInLoopLimit = pInLimit - (sizeof(size_t) - 1); - - while (pIn < pInLoopLimit) { - size_t const diff = ZSTD_readST(pMatch) ^ ZSTD_readST(pIn); - if (!diff) { - pIn += sizeof(size_t); - pMatch += sizeof(size_t); - continue; - } - pIn += ZSTD_NbCommonBytes(diff); - return (size_t)(pIn - pStart); - } - if (ZSTD_64bits()) - if ((pIn < (pInLimit - 3)) && (ZSTD_read32(pMatch) == ZSTD_read32(pIn))) { - pIn += 4; - pMatch += 4; - } - if ((pIn < (pInLimit - 1)) && (ZSTD_read16(pMatch) == ZSTD_read16(pIn))) { - pIn += 2; - pMatch += 2; - } - if ((pIn < pInLimit) && (*pMatch == *pIn)) - pIn++; - return (size_t)(pIn - pStart); -} - -/** ZSTD_count_2segments() : -* can count match length with `ip` & `match` in 2 different segments. -* convention : on reaching mEnd, match count continue starting from iStart -*/ -static size_t ZSTD_count_2segments(const BYTE *ip, const BYTE *match, const BYTE *iEnd, const BYTE *mEnd, const BYTE *iStart) -{ - const BYTE *const vEnd = MIN(ip + (mEnd - match), iEnd); - size_t const matchLength = ZSTD_count(ip, match, vEnd); - if (match + matchLength != mEnd) - return matchLength; - return matchLength + ZSTD_count(ip + matchLength, iStart, iEnd); -} - -/*-************************************* -* Hashes -***************************************/ -static const U32 prime3bytes = 506832829U; -static U32 ZSTD_hash3(U32 u, U32 h) { return ((u << (32 - 24)) * prime3bytes) >> (32 - h); } -ZSTD_STATIC size_t ZSTD_hash3Ptr(const void *ptr, U32 h) { return ZSTD_hash3(ZSTD_readLE32(ptr), h); } /* only in zstd_opt.h */ - -static const U32 prime4bytes = 2654435761U; -static U32 ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32 - h); } -static size_t ZSTD_hash4Ptr(const void *ptr, U32 h) { return ZSTD_hash4(ZSTD_read32(ptr), h); } - -static const U64 prime5bytes = 889523592379ULL; -static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u << (64 - 40)) * prime5bytes) >> (64 - h)); } -static size_t ZSTD_hash5Ptr(const void *p, U32 h) { return ZSTD_hash5(ZSTD_readLE64(p), h); } - -static const U64 prime6bytes = 227718039650203ULL; -static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64 - 48)) * prime6bytes) >> (64 - h)); } -static size_t ZSTD_hash6Ptr(const void *p, U32 h) { return ZSTD_hash6(ZSTD_readLE64(p), h); } - -static const U64 prime7bytes = 58295818150454627ULL; -static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u << (64 - 56)) * prime7bytes) >> (64 - h)); } -static size_t ZSTD_hash7Ptr(const void *p, U32 h) { return ZSTD_hash7(ZSTD_readLE64(p), h); } - -static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL; -static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u)*prime8bytes) >> (64 - h)); } -static size_t ZSTD_hash8Ptr(const void *p, U32 h) { return ZSTD_hash8(ZSTD_readLE64(p), h); } - -static size_t ZSTD_hashPtr(const void *p, U32 hBits, U32 mls) -{ - switch (mls) { - // case 3: return ZSTD_hash3Ptr(p, hBits); - default: - case 4: return ZSTD_hash4Ptr(p, hBits); - case 5: return ZSTD_hash5Ptr(p, hBits); - case 6: return ZSTD_hash6Ptr(p, hBits); - case 7: return ZSTD_hash7Ptr(p, hBits); - case 8: return ZSTD_hash8Ptr(p, hBits); - } -} - -/*-************************************* -* Fast Scan -***************************************/ -static void ZSTD_fillHashTable(ZSTD_CCtx *zc, const void *end, const U32 mls) -{ - U32 *const hashTable = zc->hashTable; - U32 const hBits = zc->params.cParams.hashLog; - const BYTE *const base = zc->base; - const BYTE *ip = base + zc->nextToUpdate; - const BYTE *const iend = ((const BYTE *)end) - HASH_READ_SIZE; - const size_t fastHashFillStep = 3; - - while (ip <= iend) { - hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base); - ip += fastHashFillStep; - } -} - -FORCE_INLINE -void ZSTD_compressBlock_fast_generic(ZSTD_CCtx *cctx, const void *src, size_t srcSize, const U32 mls) -{ - U32 *const hashTable = cctx->hashTable; - U32 const hBits = cctx->params.cParams.hashLog; - seqStore_t *seqStorePtr = &(cctx->seqStore); - const BYTE *const base = cctx->base; - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const U32 lowestIndex = cctx->dictLimit; - const BYTE *const lowest = base + lowestIndex; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - HASH_READ_SIZE; - U32 offset_1 = cctx->rep[0], offset_2 = cctx->rep[1]; - U32 offsetSaved = 0; - - /* init */ - ip += (ip == lowest); - { - U32 const maxRep = (U32)(ip - lowest); - if (offset_2 > maxRep) - offsetSaved = offset_2, offset_2 = 0; - if (offset_1 > maxRep) - offsetSaved = offset_1, offset_1 = 0; - } - - /* Main Search Loop */ - while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ - size_t mLength; - size_t const h = ZSTD_hashPtr(ip, hBits, mls); - U32 const curr = (U32)(ip - base); - U32 const matchIndex = hashTable[h]; - const BYTE *match = base + matchIndex; - hashTable[h] = curr; /* update hash table */ - - if ((offset_1 > 0) & (ZSTD_read32(ip + 1 - offset_1) == ZSTD_read32(ip + 1))) { - mLength = ZSTD_count(ip + 1 + 4, ip + 1 + 4 - offset_1, iend) + 4; - ip++; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH); - } else { - U32 offset; - if ((matchIndex <= lowestIndex) || (ZSTD_read32(match) != ZSTD_read32(ip))) { - ip += ((ip - anchor) >> g_searchStrength) + 1; - continue; - } - mLength = ZSTD_count(ip + 4, match + 4, iend) + 4; - offset = (U32)(ip - match); - while (((ip > anchor) & (match > lowest)) && (ip[-1] == match[-1])) { - ip--; - match--; - mLength++; - } /* catch up */ - offset_2 = offset_1; - offset_1 = offset; - - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH); - } - - /* match found */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { - /* Fill Table */ - hashTable[ZSTD_hashPtr(base + curr + 2, hBits, mls)] = curr + 2; /* here because curr+2 could be > iend-8 */ - hashTable[ZSTD_hashPtr(ip - 2, hBits, mls)] = (U32)(ip - 2 - base); - /* check immediate repcode */ - while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) { - /* store sequence */ - size_t const rLength = ZSTD_count(ip + 4, ip + 4 - offset_2, iend) + 4; - { - U32 const tmpOff = offset_2; - offset_2 = offset_1; - offset_1 = tmpOff; - } /* swap offset_2 <=> offset_1 */ - hashTable[ZSTD_hashPtr(ip, hBits, mls)] = (U32)(ip - base); - ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, rLength - MINMATCH); - ip += rLength; - anchor = ip; - continue; /* faster when present ... (?) */ - } - } - } - - /* save reps for next block */ - cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved; - cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved; - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -static void ZSTD_compressBlock_fast(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - const U32 mls = ctx->params.cParams.searchLength; - switch (mls) { - default: /* includes case 3 */ - case 4: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 4); return; - case 5: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 5); return; - case 6: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 6); return; - case 7: ZSTD_compressBlock_fast_generic(ctx, src, srcSize, 7); return; - } -} - -static void ZSTD_compressBlock_fast_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 mls) -{ - U32 *hashTable = ctx->hashTable; - const U32 hBits = ctx->params.cParams.hashLog; - seqStore_t *seqStorePtr = &(ctx->seqStore); - const BYTE *const base = ctx->base; - const BYTE *const dictBase = ctx->dictBase; - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const U32 lowestIndex = ctx->lowLimit; - const BYTE *const dictStart = dictBase + lowestIndex; - const U32 dictLimit = ctx->dictLimit; - const BYTE *const lowPrefixPtr = base + dictLimit; - const BYTE *const dictEnd = dictBase + dictLimit; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - 8; - U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1]; - - /* Search Loop */ - while (ip < ilimit) { /* < instead of <=, because (ip+1) */ - const size_t h = ZSTD_hashPtr(ip, hBits, mls); - const U32 matchIndex = hashTable[h]; - const BYTE *matchBase = matchIndex < dictLimit ? dictBase : base; - const BYTE *match = matchBase + matchIndex; - const U32 curr = (U32)(ip - base); - const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */ - const BYTE *repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *repMatch = repBase + repIndex; - size_t mLength; - hashTable[h] = curr; /* update hash table */ - - if ((((U32)((dictLimit - 1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex)) && - (ZSTD_read32(repMatch) == ZSTD_read32(ip + 1))) { - const BYTE *repMatchEnd = repIndex < dictLimit ? dictEnd : iend; - mLength = ZSTD_count_2segments(ip + 1 + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repMatchEnd, lowPrefixPtr) + EQUAL_READ32; - ip++; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH); - } else { - if ((matchIndex < lowestIndex) || (ZSTD_read32(match) != ZSTD_read32(ip))) { - ip += ((ip - anchor) >> g_searchStrength) + 1; - continue; - } - { - const BYTE *matchEnd = matchIndex < dictLimit ? dictEnd : iend; - const BYTE *lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr; - U32 offset; - mLength = ZSTD_count_2segments(ip + EQUAL_READ32, match + EQUAL_READ32, iend, matchEnd, lowPrefixPtr) + EQUAL_READ32; - while (((ip > anchor) & (match > lowMatchPtr)) && (ip[-1] == match[-1])) { - ip--; - match--; - mLength++; - } /* catch up */ - offset = curr - matchIndex; - offset_2 = offset_1; - offset_1 = offset; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH); - } - } - - /* found a match : store it */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { - /* Fill Table */ - hashTable[ZSTD_hashPtr(base + curr + 2, hBits, mls)] = curr + 2; - hashTable[ZSTD_hashPtr(ip - 2, hBits, mls)] = (U32)(ip - 2 - base); - /* check immediate repcode */ - while (ip <= ilimit) { - U32 const curr2 = (U32)(ip - base); - U32 const repIndex2 = curr2 - offset_2; - const BYTE *repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2; - if ((((U32)((dictLimit - 1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */ - && (ZSTD_read32(repMatch2) == ZSTD_read32(ip))) { - const BYTE *const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend; - size_t repLength2 = - ZSTD_count_2segments(ip + EQUAL_READ32, repMatch2 + EQUAL_READ32, iend, repEnd2, lowPrefixPtr) + EQUAL_READ32; - U32 tmpOffset = offset_2; - offset_2 = offset_1; - offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ - ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, repLength2 - MINMATCH); - hashTable[ZSTD_hashPtr(ip, hBits, mls)] = curr2; - ip += repLength2; - anchor = ip; - continue; - } - break; - } - } - } - - /* save reps for next block */ - ctx->repToConfirm[0] = offset_1; - ctx->repToConfirm[1] = offset_2; - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -static void ZSTD_compressBlock_fast_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - U32 const mls = ctx->params.cParams.searchLength; - switch (mls) { - default: /* includes case 3 */ - case 4: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 4); return; - case 5: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 5); return; - case 6: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 6); return; - case 7: ZSTD_compressBlock_fast_extDict_generic(ctx, src, srcSize, 7); return; - } -} - -/*-************************************* -* Double Fast -***************************************/ -static void ZSTD_fillDoubleHashTable(ZSTD_CCtx *cctx, const void *end, const U32 mls) -{ - U32 *const hashLarge = cctx->hashTable; - U32 const hBitsL = cctx->params.cParams.hashLog; - U32 *const hashSmall = cctx->chainTable; - U32 const hBitsS = cctx->params.cParams.chainLog; - const BYTE *const base = cctx->base; - const BYTE *ip = base + cctx->nextToUpdate; - const BYTE *const iend = ((const BYTE *)end) - HASH_READ_SIZE; - const size_t fastHashFillStep = 3; - - while (ip <= iend) { - hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base); - hashLarge[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base); - ip += fastHashFillStep; - } -} - -FORCE_INLINE -void ZSTD_compressBlock_doubleFast_generic(ZSTD_CCtx *cctx, const void *src, size_t srcSize, const U32 mls) -{ - U32 *const hashLong = cctx->hashTable; - const U32 hBitsL = cctx->params.cParams.hashLog; - U32 *const hashSmall = cctx->chainTable; - const U32 hBitsS = cctx->params.cParams.chainLog; - seqStore_t *seqStorePtr = &(cctx->seqStore); - const BYTE *const base = cctx->base; - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const U32 lowestIndex = cctx->dictLimit; - const BYTE *const lowest = base + lowestIndex; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - HASH_READ_SIZE; - U32 offset_1 = cctx->rep[0], offset_2 = cctx->rep[1]; - U32 offsetSaved = 0; - - /* init */ - ip += (ip == lowest); - { - U32 const maxRep = (U32)(ip - lowest); - if (offset_2 > maxRep) - offsetSaved = offset_2, offset_2 = 0; - if (offset_1 > maxRep) - offsetSaved = offset_1, offset_1 = 0; - } - - /* Main Search Loop */ - while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ - size_t mLength; - size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8); - size_t const h = ZSTD_hashPtr(ip, hBitsS, mls); - U32 const curr = (U32)(ip - base); - U32 const matchIndexL = hashLong[h2]; - U32 const matchIndexS = hashSmall[h]; - const BYTE *matchLong = base + matchIndexL; - const BYTE *match = base + matchIndexS; - hashLong[h2] = hashSmall[h] = curr; /* update hash tables */ - - if ((offset_1 > 0) & (ZSTD_read32(ip + 1 - offset_1) == ZSTD_read32(ip + 1))) { /* note : by construction, offset_1 <= curr */ - mLength = ZSTD_count(ip + 1 + 4, ip + 1 + 4 - offset_1, iend) + 4; - ip++; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH); - } else { - U32 offset; - if ((matchIndexL > lowestIndex) && (ZSTD_read64(matchLong) == ZSTD_read64(ip))) { - mLength = ZSTD_count(ip + 8, matchLong + 8, iend) + 8; - offset = (U32)(ip - matchLong); - while (((ip > anchor) & (matchLong > lowest)) && (ip[-1] == matchLong[-1])) { - ip--; - matchLong--; - mLength++; - } /* catch up */ - } else if ((matchIndexS > lowestIndex) && (ZSTD_read32(match) == ZSTD_read32(ip))) { - size_t const h3 = ZSTD_hashPtr(ip + 1, hBitsL, 8); - U32 const matchIndex3 = hashLong[h3]; - const BYTE *match3 = base + matchIndex3; - hashLong[h3] = curr + 1; - if ((matchIndex3 > lowestIndex) && (ZSTD_read64(match3) == ZSTD_read64(ip + 1))) { - mLength = ZSTD_count(ip + 9, match3 + 8, iend) + 8; - ip++; - offset = (U32)(ip - match3); - while (((ip > anchor) & (match3 > lowest)) && (ip[-1] == match3[-1])) { - ip--; - match3--; - mLength++; - } /* catch up */ - } else { - mLength = ZSTD_count(ip + 4, match + 4, iend) + 4; - offset = (U32)(ip - match); - while (((ip > anchor) & (match > lowest)) && (ip[-1] == match[-1])) { - ip--; - match--; - mLength++; - } /* catch up */ - } - } else { - ip += ((ip - anchor) >> g_searchStrength) + 1; - continue; - } - - offset_2 = offset_1; - offset_1 = offset; - - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH); - } - - /* match found */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { - /* Fill Table */ - hashLong[ZSTD_hashPtr(base + curr + 2, hBitsL, 8)] = hashSmall[ZSTD_hashPtr(base + curr + 2, hBitsS, mls)] = - curr + 2; /* here because curr+2 could be > iend-8 */ - hashLong[ZSTD_hashPtr(ip - 2, hBitsL, 8)] = hashSmall[ZSTD_hashPtr(ip - 2, hBitsS, mls)] = (U32)(ip - 2 - base); - - /* check immediate repcode */ - while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) { - /* store sequence */ - size_t const rLength = ZSTD_count(ip + 4, ip + 4 - offset_2, iend) + 4; - { - U32 const tmpOff = offset_2; - offset_2 = offset_1; - offset_1 = tmpOff; - } /* swap offset_2 <=> offset_1 */ - hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip - base); - hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip - base); - ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, rLength - MINMATCH); - ip += rLength; - anchor = ip; - continue; /* faster when present ... (?) */ - } - } - } - - /* save reps for next block */ - cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved; - cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved; - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -static void ZSTD_compressBlock_doubleFast(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - const U32 mls = ctx->params.cParams.searchLength; - switch (mls) { - default: /* includes case 3 */ - case 4: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 4); return; - case 5: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 5); return; - case 6: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 6); return; - case 7: ZSTD_compressBlock_doubleFast_generic(ctx, src, srcSize, 7); return; - } -} - -static void ZSTD_compressBlock_doubleFast_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 mls) -{ - U32 *const hashLong = ctx->hashTable; - U32 const hBitsL = ctx->params.cParams.hashLog; - U32 *const hashSmall = ctx->chainTable; - U32 const hBitsS = ctx->params.cParams.chainLog; - seqStore_t *seqStorePtr = &(ctx->seqStore); - const BYTE *const base = ctx->base; - const BYTE *const dictBase = ctx->dictBase; - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const U32 lowestIndex = ctx->lowLimit; - const BYTE *const dictStart = dictBase + lowestIndex; - const U32 dictLimit = ctx->dictLimit; - const BYTE *const lowPrefixPtr = base + dictLimit; - const BYTE *const dictEnd = dictBase + dictLimit; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - 8; - U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1]; - - /* Search Loop */ - while (ip < ilimit) { /* < instead of <=, because (ip+1) */ - const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls); - const U32 matchIndex = hashSmall[hSmall]; - const BYTE *matchBase = matchIndex < dictLimit ? dictBase : base; - const BYTE *match = matchBase + matchIndex; - - const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8); - const U32 matchLongIndex = hashLong[hLong]; - const BYTE *matchLongBase = matchLongIndex < dictLimit ? dictBase : base; - const BYTE *matchLong = matchLongBase + matchLongIndex; - - const U32 curr = (U32)(ip - base); - const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */ - const BYTE *repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *repMatch = repBase + repIndex; - size_t mLength; - hashSmall[hSmall] = hashLong[hLong] = curr; /* update hash table */ - - if ((((U32)((dictLimit - 1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex)) && - (ZSTD_read32(repMatch) == ZSTD_read32(ip + 1))) { - const BYTE *repMatchEnd = repIndex < dictLimit ? dictEnd : iend; - mLength = ZSTD_count_2segments(ip + 1 + 4, repMatch + 4, iend, repMatchEnd, lowPrefixPtr) + 4; - ip++; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, 0, mLength - MINMATCH); - } else { - if ((matchLongIndex > lowestIndex) && (ZSTD_read64(matchLong) == ZSTD_read64(ip))) { - const BYTE *matchEnd = matchLongIndex < dictLimit ? dictEnd : iend; - const BYTE *lowMatchPtr = matchLongIndex < dictLimit ? dictStart : lowPrefixPtr; - U32 offset; - mLength = ZSTD_count_2segments(ip + 8, matchLong + 8, iend, matchEnd, lowPrefixPtr) + 8; - offset = curr - matchLongIndex; - while (((ip > anchor) & (matchLong > lowMatchPtr)) && (ip[-1] == matchLong[-1])) { - ip--; - matchLong--; - mLength++; - } /* catch up */ - offset_2 = offset_1; - offset_1 = offset; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH); - - } else if ((matchIndex > lowestIndex) && (ZSTD_read32(match) == ZSTD_read32(ip))) { - size_t const h3 = ZSTD_hashPtr(ip + 1, hBitsL, 8); - U32 const matchIndex3 = hashLong[h3]; - const BYTE *const match3Base = matchIndex3 < dictLimit ? dictBase : base; - const BYTE *match3 = match3Base + matchIndex3; - U32 offset; - hashLong[h3] = curr + 1; - if ((matchIndex3 > lowestIndex) && (ZSTD_read64(match3) == ZSTD_read64(ip + 1))) { - const BYTE *matchEnd = matchIndex3 < dictLimit ? dictEnd : iend; - const BYTE *lowMatchPtr = matchIndex3 < dictLimit ? dictStart : lowPrefixPtr; - mLength = ZSTD_count_2segments(ip + 9, match3 + 8, iend, matchEnd, lowPrefixPtr) + 8; - ip++; - offset = curr + 1 - matchIndex3; - while (((ip > anchor) & (match3 > lowMatchPtr)) && (ip[-1] == match3[-1])) { - ip--; - match3--; - mLength++; - } /* catch up */ - } else { - const BYTE *matchEnd = matchIndex < dictLimit ? dictEnd : iend; - const BYTE *lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr; - mLength = ZSTD_count_2segments(ip + 4, match + 4, iend, matchEnd, lowPrefixPtr) + 4; - offset = curr - matchIndex; - while (((ip > anchor) & (match > lowMatchPtr)) && (ip[-1] == match[-1])) { - ip--; - match--; - mLength++; - } /* catch up */ - } - offset_2 = offset_1; - offset_1 = offset; - ZSTD_storeSeq(seqStorePtr, ip - anchor, anchor, offset + ZSTD_REP_MOVE, mLength - MINMATCH); - - } else { - ip += ((ip - anchor) >> g_searchStrength) + 1; - continue; - } - } - - /* found a match : store it */ - ip += mLength; - anchor = ip; - - if (ip <= ilimit) { - /* Fill Table */ - hashSmall[ZSTD_hashPtr(base + curr + 2, hBitsS, mls)] = curr + 2; - hashLong[ZSTD_hashPtr(base + curr + 2, hBitsL, 8)] = curr + 2; - hashSmall[ZSTD_hashPtr(ip - 2, hBitsS, mls)] = (U32)(ip - 2 - base); - hashLong[ZSTD_hashPtr(ip - 2, hBitsL, 8)] = (U32)(ip - 2 - base); - /* check immediate repcode */ - while (ip <= ilimit) { - U32 const curr2 = (U32)(ip - base); - U32 const repIndex2 = curr2 - offset_2; - const BYTE *repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2; - if ((((U32)((dictLimit - 1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */ - && (ZSTD_read32(repMatch2) == ZSTD_read32(ip))) { - const BYTE *const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend; - size_t const repLength2 = - ZSTD_count_2segments(ip + EQUAL_READ32, repMatch2 + EQUAL_READ32, iend, repEnd2, lowPrefixPtr) + EQUAL_READ32; - U32 tmpOffset = offset_2; - offset_2 = offset_1; - offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ - ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, repLength2 - MINMATCH); - hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = curr2; - hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = curr2; - ip += repLength2; - anchor = ip; - continue; - } - break; - } - } - } - - /* save reps for next block */ - ctx->repToConfirm[0] = offset_1; - ctx->repToConfirm[1] = offset_2; - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -static void ZSTD_compressBlock_doubleFast_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - U32 const mls = ctx->params.cParams.searchLength; - switch (mls) { - default: /* includes case 3 */ - case 4: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 4); return; - case 5: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 5); return; - case 6: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 6); return; - case 7: ZSTD_compressBlock_doubleFast_extDict_generic(ctx, src, srcSize, 7); return; - } -} - -/*-************************************* -* Binary Tree search -***************************************/ -/** ZSTD_insertBt1() : add one or multiple positions to tree. -* ip : assumed <= iend-8 . -* @return : nb of positions added */ -static U32 ZSTD_insertBt1(ZSTD_CCtx *zc, const BYTE *const ip, const U32 mls, const BYTE *const iend, U32 nbCompares, U32 extDict) -{ - U32 *const hashTable = zc->hashTable; - U32 const hashLog = zc->params.cParams.hashLog; - size_t const h = ZSTD_hashPtr(ip, hashLog, mls); - U32 *const bt = zc->chainTable; - U32 const btLog = zc->params.cParams.chainLog - 1; - U32 const btMask = (1 << btLog) - 1; - U32 matchIndex = hashTable[h]; - size_t commonLengthSmaller = 0, commonLengthLarger = 0; - const BYTE *const base = zc->base; - const BYTE *const dictBase = zc->dictBase; - const U32 dictLimit = zc->dictLimit; - const BYTE *const dictEnd = dictBase + dictLimit; - const BYTE *const prefixStart = base + dictLimit; - const BYTE *match; - const U32 curr = (U32)(ip - base); - const U32 btLow = btMask >= curr ? 0 : curr - btMask; - U32 *smallerPtr = bt + 2 * (curr & btMask); - U32 *largerPtr = smallerPtr + 1; - U32 dummy32; /* to be nullified at the end */ - U32 const windowLow = zc->lowLimit; - U32 matchEndIdx = curr + 8; - size_t bestLength = 8; - - hashTable[h] = curr; /* Update Hash Table */ - - while (nbCompares-- && (matchIndex > windowLow)) { - U32 *const nextPtr = bt + 2 * (matchIndex & btMask); - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ - - if ((!extDict) || (matchIndex + matchLength >= dictLimit)) { - match = base + matchIndex; - if (match[matchLength] == ip[matchLength]) - matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iend) + 1; - } else { - match = dictBase + matchIndex; - matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iend, dictEnd, prefixStart); - if (matchIndex + matchLength >= dictLimit) - match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ - } - - if (matchLength > bestLength) { - bestLength = matchLength; - if (matchLength > matchEndIdx - matchIndex) - matchEndIdx = matchIndex + (U32)matchLength; - } - - if (ip + matchLength == iend) /* equal : no way to know if inf or sup */ - break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt the tree */ - - if (match[matchLength] < ip[matchLength]) { /* necessarily within correct buffer */ - /* match is smaller than curr */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { - smallerPtr = &dummy32; - break; - } /* beyond tree size, stop the search */ - smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */ - matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to curr) */ - } else { - /* match is larger than curr */ - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { - largerPtr = &dummy32; - break; - } /* beyond tree size, stop the search */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } - } - - *smallerPtr = *largerPtr = 0; - if (bestLength > 384) - return MIN(192, (U32)(bestLength - 384)); /* speed optimization */ - if (matchEndIdx > curr + 8) - return matchEndIdx - curr - 8; - return 1; -} - -static size_t ZSTD_insertBtAndFindBestMatch(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, size_t *offsetPtr, U32 nbCompares, const U32 mls, - U32 extDict) -{ - U32 *const hashTable = zc->hashTable; - U32 const hashLog = zc->params.cParams.hashLog; - size_t const h = ZSTD_hashPtr(ip, hashLog, mls); - U32 *const bt = zc->chainTable; - U32 const btLog = zc->params.cParams.chainLog - 1; - U32 const btMask = (1 << btLog) - 1; - U32 matchIndex = hashTable[h]; - size_t commonLengthSmaller = 0, commonLengthLarger = 0; - const BYTE *const base = zc->base; - const BYTE *const dictBase = zc->dictBase; - const U32 dictLimit = zc->dictLimit; - const BYTE *const dictEnd = dictBase + dictLimit; - const BYTE *const prefixStart = base + dictLimit; - const U32 curr = (U32)(ip - base); - const U32 btLow = btMask >= curr ? 0 : curr - btMask; - const U32 windowLow = zc->lowLimit; - U32 *smallerPtr = bt + 2 * (curr & btMask); - U32 *largerPtr = bt + 2 * (curr & btMask) + 1; - U32 matchEndIdx = curr + 8; - U32 dummy32; /* to be nullified at the end */ - size_t bestLength = 0; - - hashTable[h] = curr; /* Update Hash Table */ - - while (nbCompares-- && (matchIndex > windowLow)) { - U32 *const nextPtr = bt + 2 * (matchIndex & btMask); - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ - const BYTE *match; - - if ((!extDict) || (matchIndex + matchLength >= dictLimit)) { - match = base + matchIndex; - if (match[matchLength] == ip[matchLength]) - matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iend) + 1; - } else { - match = dictBase + matchIndex; - matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iend, dictEnd, prefixStart); - if (matchIndex + matchLength >= dictLimit) - match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ - } - - if (matchLength > bestLength) { - if (matchLength > matchEndIdx - matchIndex) - matchEndIdx = matchIndex + (U32)matchLength; - if ((4 * (int)(matchLength - bestLength)) > (int)(ZSTD_highbit32(curr - matchIndex + 1) - ZSTD_highbit32((U32)offsetPtr[0] + 1))) - bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex; - if (ip + matchLength == iend) /* equal : no way to know if inf or sup */ - break; /* drop, to guarantee consistency (miss a little bit of compression) */ - } - - if (match[matchLength] < ip[matchLength]) { - /* match is smaller than curr */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { - smallerPtr = &dummy32; - break; - } /* beyond tree size, stop the search */ - smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */ - matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to curr) */ - } else { - /* match is larger than curr */ - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { - largerPtr = &dummy32; - break; - } /* beyond tree size, stop the search */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } - } - - *smallerPtr = *largerPtr = 0; - - zc->nextToUpdate = (matchEndIdx > curr + 8) ? matchEndIdx - 8 : curr + 1; - return bestLength; -} - -static void ZSTD_updateTree(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, const U32 nbCompares, const U32 mls) -{ - const BYTE *const base = zc->base; - const U32 target = (U32)(ip - base); - U32 idx = zc->nextToUpdate; - - while (idx < target) - idx += ZSTD_insertBt1(zc, base + idx, mls, iend, nbCompares, 0); -} - -/** ZSTD_BtFindBestMatch() : Tree updater, providing best match */ -static size_t ZSTD_BtFindBestMatch(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 mls) -{ - if (ip < zc->base + zc->nextToUpdate) - return 0; /* skipped area */ - ZSTD_updateTree(zc, ip, iLimit, maxNbAttempts, mls); - return ZSTD_insertBtAndFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, mls, 0); -} - -static size_t ZSTD_BtFindBestMatch_selectMLS(ZSTD_CCtx *zc, /* Index table will be updated */ - const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 matchLengthSearch) -{ - switch (matchLengthSearch) { - default: /* includes case 3 */ - case 4: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4); - case 5: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5); - case 7: - case 6: return ZSTD_BtFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6); - } -} - -static void ZSTD_updateTree_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iend, const U32 nbCompares, const U32 mls) -{ - const BYTE *const base = zc->base; - const U32 target = (U32)(ip - base); - U32 idx = zc->nextToUpdate; - - while (idx < target) - idx += ZSTD_insertBt1(zc, base + idx, mls, iend, nbCompares, 1); -} - -/** Tree updater, providing best match */ -static size_t ZSTD_BtFindBestMatch_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, - const U32 mls) -{ - if (ip < zc->base + zc->nextToUpdate) - return 0; /* skipped area */ - ZSTD_updateTree_extDict(zc, ip, iLimit, maxNbAttempts, mls); - return ZSTD_insertBtAndFindBestMatch(zc, ip, iLimit, offsetPtr, maxNbAttempts, mls, 1); -} - -static size_t ZSTD_BtFindBestMatch_selectMLS_extDict(ZSTD_CCtx *zc, /* Index table will be updated */ - const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, - const U32 matchLengthSearch) -{ - switch (matchLengthSearch) { - default: /* includes case 3 */ - case 4: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4); - case 5: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5); - case 7: - case 6: return ZSTD_BtFindBestMatch_extDict(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6); - } -} - -/* ********************************* -* Hash Chain -***********************************/ -#define NEXT_IN_CHAIN(d, mask) chainTable[(d)&mask] - -/* Update chains up to ip (excluded) - Assumption : always within prefix (i.e. not within extDict) */ -FORCE_INLINE -U32 ZSTD_insertAndFindFirstIndex(ZSTD_CCtx *zc, const BYTE *ip, U32 mls) -{ - U32 *const hashTable = zc->hashTable; - const U32 hashLog = zc->params.cParams.hashLog; - U32 *const chainTable = zc->chainTable; - const U32 chainMask = (1 << zc->params.cParams.chainLog) - 1; - const BYTE *const base = zc->base; - const U32 target = (U32)(ip - base); - U32 idx = zc->nextToUpdate; - - while (idx < target) { /* catch up */ - size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls); - NEXT_IN_CHAIN(idx, chainMask) = hashTable[h]; - hashTable[h] = idx; - idx++; - } - - zc->nextToUpdate = target; - return hashTable[ZSTD_hashPtr(ip, hashLog, mls)]; -} - -/* inlining is important to hardwire a hot branch (template emulation) */ -FORCE_INLINE -size_t ZSTD_HcFindBestMatch_generic(ZSTD_CCtx *zc, /* Index table will be updated */ - const BYTE *const ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, const U32 mls, - const U32 extDict) -{ - U32 *const chainTable = zc->chainTable; - const U32 chainSize = (1 << zc->params.cParams.chainLog); - const U32 chainMask = chainSize - 1; - const BYTE *const base = zc->base; - const BYTE *const dictBase = zc->dictBase; - const U32 dictLimit = zc->dictLimit; - const BYTE *const prefixStart = base + dictLimit; - const BYTE *const dictEnd = dictBase + dictLimit; - const U32 lowLimit = zc->lowLimit; - const U32 curr = (U32)(ip - base); - const U32 minChain = curr > chainSize ? curr - chainSize : 0; - int nbAttempts = maxNbAttempts; - size_t ml = EQUAL_READ32 - 1; - - /* HC4 match finder */ - U32 matchIndex = ZSTD_insertAndFindFirstIndex(zc, ip, mls); - - for (; (matchIndex > lowLimit) & (nbAttempts > 0); nbAttempts--) { - const BYTE *match; - size_t currMl = 0; - if ((!extDict) || matchIndex >= dictLimit) { - match = base + matchIndex; - if (match[ml] == ip[ml]) /* potentially better */ - currMl = ZSTD_count(ip, match, iLimit); - } else { - match = dictBase + matchIndex; - if (ZSTD_read32(match) == ZSTD_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */ - currMl = ZSTD_count_2segments(ip + EQUAL_READ32, match + EQUAL_READ32, iLimit, dictEnd, prefixStart) + EQUAL_READ32; - } - - /* save best solution */ - if (currMl > ml) { - ml = currMl; - *offsetPtr = curr - matchIndex + ZSTD_REP_MOVE; - if (ip + currMl == iLimit) - break; /* best possible, and avoid read overflow*/ - } - - if (matchIndex <= minChain) - break; - matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask); - } - - return ml; -} - -FORCE_INLINE size_t ZSTD_HcFindBestMatch_selectMLS(ZSTD_CCtx *zc, const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, - const U32 matchLengthSearch) -{ - switch (matchLengthSearch) { - default: /* includes case 3 */ - case 4: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4, 0); - case 5: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5, 0); - case 7: - case 6: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6, 0); - } -} - -FORCE_INLINE size_t ZSTD_HcFindBestMatch_extDict_selectMLS(ZSTD_CCtx *zc, const BYTE *ip, const BYTE *const iLimit, size_t *offsetPtr, const U32 maxNbAttempts, - const U32 matchLengthSearch) -{ - switch (matchLengthSearch) { - default: /* includes case 3 */ - case 4: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 4, 1); - case 5: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 5, 1); - case 7: - case 6: return ZSTD_HcFindBestMatch_generic(zc, ip, iLimit, offsetPtr, maxNbAttempts, 6, 1); - } -} - -/* ******************************* -* Common parser - lazy strategy -*********************************/ -FORCE_INLINE -void ZSTD_compressBlock_lazy_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 searchMethod, const U32 depth) -{ - seqStore_t *seqStorePtr = &(ctx->seqStore); - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - 8; - const BYTE *const base = ctx->base + ctx->dictLimit; - - U32 const maxSearches = 1 << ctx->params.cParams.searchLog; - U32 const mls = ctx->params.cParams.searchLength; - - typedef size_t (*searchMax_f)(ZSTD_CCtx * zc, const BYTE *ip, const BYTE *iLimit, size_t *offsetPtr, U32 maxNbAttempts, U32 matchLengthSearch); - searchMax_f const searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS : ZSTD_HcFindBestMatch_selectMLS; - U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1], savedOffset = 0; - - /* init */ - ip += (ip == base); - ctx->nextToUpdate3 = ctx->nextToUpdate; - { - U32 const maxRep = (U32)(ip - base); - if (offset_2 > maxRep) - savedOffset = offset_2, offset_2 = 0; - if (offset_1 > maxRep) - savedOffset = offset_1, offset_1 = 0; - } - - /* Match Loop */ - while (ip < ilimit) { - size_t matchLength = 0; - size_t offset = 0; - const BYTE *start = ip + 1; - - /* check repCode */ - if ((offset_1 > 0) & (ZSTD_read32(ip + 1) == ZSTD_read32(ip + 1 - offset_1))) { - /* repcode : we take it */ - matchLength = ZSTD_count(ip + 1 + EQUAL_READ32, ip + 1 + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32; - if (depth == 0) - goto _storeSequence; - } - - /* first search (depth 0) */ - { - size_t offsetFound = 99999999; - size_t const ml2 = searchMax(ctx, ip, iend, &offsetFound, maxSearches, mls); - if (ml2 > matchLength) - matchLength = ml2, start = ip, offset = offsetFound; - } - - if (matchLength < EQUAL_READ32) { - ip += ((ip - anchor) >> g_searchStrength) + 1; /* jump faster over incompressible sections */ - continue; - } - - /* let's try to find a better solution */ - if (depth >= 1) - while (ip < ilimit) { - ip++; - if ((offset) && ((offset_1 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_1)))) { - size_t const mlRep = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32; - int const gain2 = (int)(mlRep * 3); - int const gain1 = (int)(matchLength * 3 - ZSTD_highbit32((U32)offset + 1) + 1); - if ((mlRep >= EQUAL_READ32) && (gain2 > gain1)) - matchLength = mlRep, offset = 0, start = ip; - } - { - size_t offset2 = 99999999; - size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls); - int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */ - int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 4); - if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) { - matchLength = ml2, offset = offset2, start = ip; - continue; /* search a better one */ - } - } - - /* let's find an even better one */ - if ((depth == 2) && (ip < ilimit)) { - ip++; - if ((offset) && ((offset_1 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_1)))) { - size_t const ml2 = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_1, iend) + EQUAL_READ32; - int const gain2 = (int)(ml2 * 4); - int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 1); - if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) - matchLength = ml2, offset = 0, start = ip; - } - { - size_t offset2 = 99999999; - size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls); - int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */ - int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 7); - if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) { - matchLength = ml2, offset = offset2, start = ip; - continue; - } - } - } - break; /* nothing found : store previous solution */ - } - - /* NOTE: - * start[-offset+ZSTD_REP_MOVE-1] is undefined behavior. - * (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which - * overflows the pointer, which is undefined behavior. - */ - /* catch up */ - if (offset) { - while ((start > anchor) && (start > base + offset - ZSTD_REP_MOVE) && - (start[-1] == (start-offset+ZSTD_REP_MOVE)[-1])) /* only search for offset within prefix */ - { - start--; - matchLength++; - } - offset_2 = offset_1; - offset_1 = (U32)(offset - ZSTD_REP_MOVE); - } - - /* store sequence */ -_storeSequence: - { - size_t const litLength = start - anchor; - ZSTD_storeSeq(seqStorePtr, litLength, anchor, (U32)offset, matchLength - MINMATCH); - anchor = ip = start + matchLength; - } - - /* check immediate repcode */ - while ((ip <= ilimit) && ((offset_2 > 0) & (ZSTD_read32(ip) == ZSTD_read32(ip - offset_2)))) { - /* store sequence */ - matchLength = ZSTD_count(ip + EQUAL_READ32, ip + EQUAL_READ32 - offset_2, iend) + EQUAL_READ32; - offset = offset_2; - offset_2 = offset_1; - offset_1 = (U32)offset; /* swap repcodes */ - ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, matchLength - MINMATCH); - ip += matchLength; - anchor = ip; - continue; /* faster when present ... (?) */ - } - } - - /* Save reps for next block */ - ctx->repToConfirm[0] = offset_1 ? offset_1 : savedOffset; - ctx->repToConfirm[1] = offset_2 ? offset_2 : savedOffset; - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -static void ZSTD_compressBlock_btlazy2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 1, 2); } - -static void ZSTD_compressBlock_lazy2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 2); } - -static void ZSTD_compressBlock_lazy(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 1); } - -static void ZSTD_compressBlock_greedy(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_generic(ctx, src, srcSize, 0, 0); } - -FORCE_INLINE -void ZSTD_compressBlock_lazy_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const U32 searchMethod, const U32 depth) -{ - seqStore_t *seqStorePtr = &(ctx->seqStore); - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - 8; - const BYTE *const base = ctx->base; - const U32 dictLimit = ctx->dictLimit; - const U32 lowestIndex = ctx->lowLimit; - const BYTE *const prefixStart = base + dictLimit; - const BYTE *const dictBase = ctx->dictBase; - const BYTE *const dictEnd = dictBase + dictLimit; - const BYTE *const dictStart = dictBase + ctx->lowLimit; - - const U32 maxSearches = 1 << ctx->params.cParams.searchLog; - const U32 mls = ctx->params.cParams.searchLength; - - typedef size_t (*searchMax_f)(ZSTD_CCtx * zc, const BYTE *ip, const BYTE *iLimit, size_t *offsetPtr, U32 maxNbAttempts, U32 matchLengthSearch); - searchMax_f searchMax = searchMethod ? ZSTD_BtFindBestMatch_selectMLS_extDict : ZSTD_HcFindBestMatch_extDict_selectMLS; - - U32 offset_1 = ctx->rep[0], offset_2 = ctx->rep[1]; - - /* init */ - ctx->nextToUpdate3 = ctx->nextToUpdate; - ip += (ip == prefixStart); - - /* Match Loop */ - while (ip < ilimit) { - size_t matchLength = 0; - size_t offset = 0; - const BYTE *start = ip + 1; - U32 curr = (U32)(ip - base); - - /* check repCode */ - { - const U32 repIndex = (U32)(curr + 1 - offset_1); - const BYTE *const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *const repMatch = repBase + repIndex; - if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */ - if (ZSTD_read32(ip + 1) == ZSTD_read32(repMatch)) { - /* repcode detected we should take it */ - const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend; - matchLength = - ZSTD_count_2segments(ip + 1 + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + EQUAL_READ32; - if (depth == 0) - goto _storeSequence; - } - } - - /* first search (depth 0) */ - { - size_t offsetFound = 99999999; - size_t const ml2 = searchMax(ctx, ip, iend, &offsetFound, maxSearches, mls); - if (ml2 > matchLength) - matchLength = ml2, start = ip, offset = offsetFound; - } - - if (matchLength < EQUAL_READ32) { - ip += ((ip - anchor) >> g_searchStrength) + 1; /* jump faster over incompressible sections */ - continue; - } - - /* let's try to find a better solution */ - if (depth >= 1) - while (ip < ilimit) { - ip++; - curr++; - /* check repCode */ - if (offset) { - const U32 repIndex = (U32)(curr - offset_1); - const BYTE *const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *const repMatch = repBase + repIndex; - if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */ - if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) { - /* repcode detected */ - const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend; - size_t const repLength = - ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + - EQUAL_READ32; - int const gain2 = (int)(repLength * 3); - int const gain1 = (int)(matchLength * 3 - ZSTD_highbit32((U32)offset + 1) + 1); - if ((repLength >= EQUAL_READ32) && (gain2 > gain1)) - matchLength = repLength, offset = 0, start = ip; - } - } - - /* search match, depth 1 */ - { - size_t offset2 = 99999999; - size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls); - int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */ - int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 4); - if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) { - matchLength = ml2, offset = offset2, start = ip; - continue; /* search a better one */ - } - } - - /* let's find an even better one */ - if ((depth == 2) && (ip < ilimit)) { - ip++; - curr++; - /* check repCode */ - if (offset) { - const U32 repIndex = (U32)(curr - offset_1); - const BYTE *const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *const repMatch = repBase + repIndex; - if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */ - if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) { - /* repcode detected */ - const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend; - size_t repLength = ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, - repEnd, prefixStart) + - EQUAL_READ32; - int gain2 = (int)(repLength * 4); - int gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 1); - if ((repLength >= EQUAL_READ32) && (gain2 > gain1)) - matchLength = repLength, offset = 0, start = ip; - } - } - - /* search match, depth 2 */ - { - size_t offset2 = 99999999; - size_t const ml2 = searchMax(ctx, ip, iend, &offset2, maxSearches, mls); - int const gain2 = (int)(ml2 * 4 - ZSTD_highbit32((U32)offset2 + 1)); /* raw approx */ - int const gain1 = (int)(matchLength * 4 - ZSTD_highbit32((U32)offset + 1) + 7); - if ((ml2 >= EQUAL_READ32) && (gain2 > gain1)) { - matchLength = ml2, offset = offset2, start = ip; - continue; - } - } - } - break; /* nothing found : store previous solution */ - } - - /* catch up */ - if (offset) { - U32 const matchIndex = (U32)((start - base) - (offset - ZSTD_REP_MOVE)); - const BYTE *match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex; - const BYTE *const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart; - while ((start > anchor) && (match > mStart) && (start[-1] == match[-1])) { - start--; - match--; - matchLength++; - } /* catch up */ - offset_2 = offset_1; - offset_1 = (U32)(offset - ZSTD_REP_MOVE); - } - - /* store sequence */ - _storeSequence : { - size_t const litLength = start - anchor; - ZSTD_storeSeq(seqStorePtr, litLength, anchor, (U32)offset, matchLength - MINMATCH); - anchor = ip = start + matchLength; - } - - /* check immediate repcode */ - while (ip <= ilimit) { - const U32 repIndex = (U32)((ip - base) - offset_2); - const BYTE *const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *const repMatch = repBase + repIndex; - if (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */ - if (ZSTD_read32(ip) == ZSTD_read32(repMatch)) { - /* repcode detected we should take it */ - const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend; - matchLength = - ZSTD_count_2segments(ip + EQUAL_READ32, repMatch + EQUAL_READ32, iend, repEnd, prefixStart) + EQUAL_READ32; - offset = offset_2; - offset_2 = offset_1; - offset_1 = (U32)offset; /* swap offset history */ - ZSTD_storeSeq(seqStorePtr, 0, anchor, 0, matchLength - MINMATCH); - ip += matchLength; - anchor = ip; - continue; /* faster when present ... (?) */ - } - break; - } - } - - /* Save reps for next block */ - ctx->repToConfirm[0] = offset_1; - ctx->repToConfirm[1] = offset_2; - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -void ZSTD_compressBlock_greedy_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) { ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 0); } - -static void ZSTD_compressBlock_lazy_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 1); -} - -static void ZSTD_compressBlock_lazy2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 0, 2); -} - -static void ZSTD_compressBlock_btlazy2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ - ZSTD_compressBlock_lazy_extDict_generic(ctx, src, srcSize, 1, 2); -} - -/* The optimal parser */ -#include "zstd_opt.h" - -static void ZSTD_compressBlock_btopt(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ -#ifdef ZSTD_OPT_H_91842398743 - ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 0); -#else - (void)ctx; - (void)src; - (void)srcSize; - return; -#endif -} - -static void ZSTD_compressBlock_btopt2(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ -#ifdef ZSTD_OPT_H_91842398743 - ZSTD_compressBlock_opt_generic(ctx, src, srcSize, 1); -#else - (void)ctx; - (void)src; - (void)srcSize; - return; -#endif -} - -static void ZSTD_compressBlock_btopt_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ -#ifdef ZSTD_OPT_H_91842398743 - ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 0); -#else - (void)ctx; - (void)src; - (void)srcSize; - return; -#endif -} - -static void ZSTD_compressBlock_btopt2_extDict(ZSTD_CCtx *ctx, const void *src, size_t srcSize) -{ -#ifdef ZSTD_OPT_H_91842398743 - ZSTD_compressBlock_opt_extDict_generic(ctx, src, srcSize, 1); -#else - (void)ctx; - (void)src; - (void)srcSize; - return; -#endif -} - -typedef void (*ZSTD_blockCompressor)(ZSTD_CCtx *ctx, const void *src, size_t srcSize); - -static ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, int extDict) -{ - static const ZSTD_blockCompressor blockCompressor[2][8] = { - {ZSTD_compressBlock_fast, ZSTD_compressBlock_doubleFast, ZSTD_compressBlock_greedy, ZSTD_compressBlock_lazy, ZSTD_compressBlock_lazy2, - ZSTD_compressBlock_btlazy2, ZSTD_compressBlock_btopt, ZSTD_compressBlock_btopt2}, - {ZSTD_compressBlock_fast_extDict, ZSTD_compressBlock_doubleFast_extDict, ZSTD_compressBlock_greedy_extDict, ZSTD_compressBlock_lazy_extDict, - ZSTD_compressBlock_lazy2_extDict, ZSTD_compressBlock_btlazy2_extDict, ZSTD_compressBlock_btopt_extDict, ZSTD_compressBlock_btopt2_extDict}}; - - return blockCompressor[extDict][(U32)strat]; -} - -static size_t ZSTD_compressBlock_internal(ZSTD_CCtx *zc, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->params.cParams.strategy, zc->lowLimit < zc->dictLimit); - const BYTE *const base = zc->base; - const BYTE *const istart = (const BYTE *)src; - const U32 curr = (U32)(istart - base); - if (srcSize < MIN_CBLOCK_SIZE + ZSTD_blockHeaderSize + 1) - return 0; /* don't even attempt compression below a certain srcSize */ - ZSTD_resetSeqStore(&(zc->seqStore)); - if (curr > zc->nextToUpdate + 384) - zc->nextToUpdate = curr - MIN(192, (U32)(curr - zc->nextToUpdate - 384)); /* update tree not updated after finding very long rep matches */ - blockCompressor(zc, src, srcSize); - return ZSTD_compressSequences(zc, dst, dstCapacity, srcSize); -} - -/*! ZSTD_compress_generic() : -* Compress a chunk of data into one or multiple blocks. -* All blocks will be terminated, all input will be consumed. -* Function will issue an error if there is not enough `dstCapacity` to hold the compressed content. -* Frame is supposed already started (header already produced) -* @return : compressed size, or an error code -*/ -static size_t ZSTD_compress_generic(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, U32 lastFrameChunk) -{ - size_t blockSize = cctx->blockSize; - size_t remaining = srcSize; - const BYTE *ip = (const BYTE *)src; - BYTE *const ostart = (BYTE *)dst; - BYTE *op = ostart; - U32 const maxDist = 1 << cctx->params.cParams.windowLog; - - if (cctx->params.fParams.checksumFlag && srcSize) - xxh64_update(&cctx->xxhState, src, srcSize); - - while (remaining) { - U32 const lastBlock = lastFrameChunk & (blockSize >= remaining); - size_t cSize; - - if (dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE) - return ERROR(dstSize_tooSmall); /* not enough space to store compressed block */ - if (remaining < blockSize) - blockSize = remaining; - - /* preemptive overflow correction */ - if (cctx->lowLimit > (3U << 29)) { - U32 const cycleMask = (1 << ZSTD_cycleLog(cctx->params.cParams.hashLog, cctx->params.cParams.strategy)) - 1; - U32 const curr = (U32)(ip - cctx->base); - U32 const newCurr = (curr & cycleMask) + (1 << cctx->params.cParams.windowLog); - U32 const correction = curr - newCurr; - ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_64 <= 30); - ZSTD_reduceIndex(cctx, correction); - cctx->base += correction; - cctx->dictBase += correction; - cctx->lowLimit -= correction; - cctx->dictLimit -= correction; - if (cctx->nextToUpdate < correction) - cctx->nextToUpdate = 0; - else - cctx->nextToUpdate -= correction; - } - - if ((U32)(ip + blockSize - cctx->base) > cctx->loadedDictEnd + maxDist) { - /* enforce maxDist */ - U32 const newLowLimit = (U32)(ip + blockSize - cctx->base) - maxDist; - if (cctx->lowLimit < newLowLimit) - cctx->lowLimit = newLowLimit; - if (cctx->dictLimit < cctx->lowLimit) - cctx->dictLimit = cctx->lowLimit; - } - - cSize = ZSTD_compressBlock_internal(cctx, op + ZSTD_blockHeaderSize, dstCapacity - ZSTD_blockHeaderSize, ip, blockSize); - if (ZSTD_isError(cSize)) - return cSize; - - if (cSize == 0) { /* block is not compressible */ - U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw) << 1) + (U32)(blockSize << 3); - if (blockSize + ZSTD_blockHeaderSize > dstCapacity) - return ERROR(dstSize_tooSmall); - ZSTD_writeLE32(op, cBlockHeader24); /* no pb, 4th byte will be overwritten */ - memcpy(op + ZSTD_blockHeaderSize, ip, blockSize); - cSize = ZSTD_blockHeaderSize + blockSize; - } else { - U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed) << 1) + (U32)(cSize << 3); - ZSTD_writeLE24(op, cBlockHeader24); - cSize += ZSTD_blockHeaderSize; - } - - remaining -= blockSize; - dstCapacity -= cSize; - ip += blockSize; - op += cSize; - } - - if (lastFrameChunk && (op > ostart)) - cctx->stage = ZSTDcs_ending; - return op - ostart; -} - -static size_t ZSTD_writeFrameHeader(void *dst, size_t dstCapacity, ZSTD_parameters params, U64 pledgedSrcSize, U32 dictID) -{ - BYTE *const op = (BYTE *)dst; - U32 const dictIDSizeCode = (dictID > 0) + (dictID >= 256) + (dictID >= 65536); /* 0-3 */ - U32 const checksumFlag = params.fParams.checksumFlag > 0; - U32 const windowSize = 1U << params.cParams.windowLog; - U32 const singleSegment = params.fParams.contentSizeFlag && (windowSize >= pledgedSrcSize); - BYTE const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3); - U32 const fcsCode = - params.fParams.contentSizeFlag ? (pledgedSrcSize >= 256) + (pledgedSrcSize >= 65536 + 256) + (pledgedSrcSize >= 0xFFFFFFFFU) : 0; /* 0-3 */ - BYTE const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag << 2) + (singleSegment << 5) + (fcsCode << 6)); - size_t pos; - - if (dstCapacity < ZSTD_frameHeaderSize_max) - return ERROR(dstSize_tooSmall); - - ZSTD_writeLE32(dst, ZSTD_MAGICNUMBER); - op[4] = frameHeaderDecriptionByte; - pos = 5; - if (!singleSegment) - op[pos++] = windowLogByte; - switch (dictIDSizeCode) { - default: /* impossible */ - case 0: break; - case 1: - op[pos] = (BYTE)(dictID); - pos++; - break; - case 2: - ZSTD_writeLE16(op + pos, (U16)dictID); - pos += 2; - break; - case 3: - ZSTD_writeLE32(op + pos, dictID); - pos += 4; - break; - } - switch (fcsCode) { - default: /* impossible */ - case 0: - if (singleSegment) - op[pos++] = (BYTE)(pledgedSrcSize); - break; - case 1: - ZSTD_writeLE16(op + pos, (U16)(pledgedSrcSize - 256)); - pos += 2; - break; - case 2: - ZSTD_writeLE32(op + pos, (U32)(pledgedSrcSize)); - pos += 4; - break; - case 3: - ZSTD_writeLE64(op + pos, (U64)(pledgedSrcSize)); - pos += 8; - break; - } - return pos; -} - -static size_t ZSTD_compressContinue_internal(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, U32 frame, U32 lastFrameChunk) -{ - const BYTE *const ip = (const BYTE *)src; - size_t fhSize = 0; - - if (cctx->stage == ZSTDcs_created) - return ERROR(stage_wrong); /* missing init (ZSTD_compressBegin) */ - - if (frame && (cctx->stage == ZSTDcs_init)) { - fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, cctx->frameContentSize, cctx->dictID); - if (ZSTD_isError(fhSize)) - return fhSize; - dstCapacity -= fhSize; - dst = (char *)dst + fhSize; - cctx->stage = ZSTDcs_ongoing; - } - - /* Check if blocks follow each other */ - if (src != cctx->nextSrc) { - /* not contiguous */ - ptrdiff_t const delta = cctx->nextSrc - ip; - cctx->lowLimit = cctx->dictLimit; - cctx->dictLimit = (U32)(cctx->nextSrc - cctx->base); - cctx->dictBase = cctx->base; - cctx->base -= delta; - cctx->nextToUpdate = cctx->dictLimit; - if (cctx->dictLimit - cctx->lowLimit < HASH_READ_SIZE) - cctx->lowLimit = cctx->dictLimit; /* too small extDict */ - } - - /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */ - if ((ip + srcSize > cctx->dictBase + cctx->lowLimit) & (ip < cctx->dictBase + cctx->dictLimit)) { - ptrdiff_t const highInputIdx = (ip + srcSize) - cctx->dictBase; - U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)cctx->dictLimit) ? cctx->dictLimit : (U32)highInputIdx; - cctx->lowLimit = lowLimitMax; - } - - cctx->nextSrc = ip + srcSize; - - if (srcSize) { - size_t const cSize = frame ? ZSTD_compress_generic(cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) - : ZSTD_compressBlock_internal(cctx, dst, dstCapacity, src, srcSize); - if (ZSTD_isError(cSize)) - return cSize; - return cSize + fhSize; - } else - return fhSize; -} - -size_t ZSTD_compressContinue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1, 0); -} - -size_t ZSTD_getBlockSizeMax(ZSTD_CCtx *cctx) { return MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, 1 << cctx->params.cParams.windowLog); } - -size_t ZSTD_compressBlock(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - size_t const blockSizeMax = ZSTD_getBlockSizeMax(cctx); - if (srcSize > blockSizeMax) - return ERROR(srcSize_wrong); - return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0, 0); -} - -/*! ZSTD_loadDictionaryContent() : - * @return : 0, or an error code - */ -static size_t ZSTD_loadDictionaryContent(ZSTD_CCtx *zc, const void *src, size_t srcSize) -{ - const BYTE *const ip = (const BYTE *)src; - const BYTE *const iend = ip + srcSize; - - /* input becomes curr prefix */ - zc->lowLimit = zc->dictLimit; - zc->dictLimit = (U32)(zc->nextSrc - zc->base); - zc->dictBase = zc->base; - zc->base += ip - zc->nextSrc; - zc->nextToUpdate = zc->dictLimit; - zc->loadedDictEnd = zc->forceWindow ? 0 : (U32)(iend - zc->base); - - zc->nextSrc = iend; - if (srcSize <= HASH_READ_SIZE) - return 0; - - switch (zc->params.cParams.strategy) { - case ZSTD_fast: ZSTD_fillHashTable(zc, iend, zc->params.cParams.searchLength); break; - - case ZSTD_dfast: ZSTD_fillDoubleHashTable(zc, iend, zc->params.cParams.searchLength); break; - - case ZSTD_greedy: - case ZSTD_lazy: - case ZSTD_lazy2: - if (srcSize >= HASH_READ_SIZE) - ZSTD_insertAndFindFirstIndex(zc, iend - HASH_READ_SIZE, zc->params.cParams.searchLength); - break; - - case ZSTD_btlazy2: - case ZSTD_btopt: - case ZSTD_btopt2: - if (srcSize >= HASH_READ_SIZE) - ZSTD_updateTree(zc, iend - HASH_READ_SIZE, iend, 1 << zc->params.cParams.searchLog, zc->params.cParams.searchLength); - break; - - default: - return ERROR(GENERIC); /* strategy doesn't exist; impossible */ - } - - zc->nextToUpdate = (U32)(iend - zc->base); - return 0; -} - -/* Dictionaries that assign zero probability to symbols that show up causes problems - when FSE encoding. Refuse dictionaries that assign zero probability to symbols - that we may encounter during compression. - NOTE: This behavior is not standard and could be improved in the future. */ -static size_t ZSTD_checkDictNCount(short *normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue) -{ - U32 s; - if (dictMaxSymbolValue < maxSymbolValue) - return ERROR(dictionary_corrupted); - for (s = 0; s <= maxSymbolValue; ++s) { - if (normalizedCounter[s] == 0) - return ERROR(dictionary_corrupted); - } - return 0; -} - -/* Dictionary format : - * See : - * https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md#dictionary-format - */ -/*! ZSTD_loadZstdDictionary() : - * @return : 0, or an error code - * assumptions : magic number supposed already checked - * dictSize supposed > 8 - */ -static size_t ZSTD_loadZstdDictionary(ZSTD_CCtx *cctx, const void *dict, size_t dictSize) -{ - const BYTE *dictPtr = (const BYTE *)dict; - const BYTE *const dictEnd = dictPtr + dictSize; - short offcodeNCount[MaxOff + 1]; - unsigned offcodeMaxValue = MaxOff; - - dictPtr += 4; /* skip magic number */ - cctx->dictID = cctx->params.fParams.noDictIDFlag ? 0 : ZSTD_readLE32(dictPtr); - dictPtr += 4; - - { - size_t const hufHeaderSize = HUF_readCTable_wksp(cctx->hufTable, 255, dictPtr, dictEnd - dictPtr, cctx->tmpCounters, sizeof(cctx->tmpCounters)); - if (HUF_isError(hufHeaderSize)) - return ERROR(dictionary_corrupted); - dictPtr += hufHeaderSize; - } - - { - unsigned offcodeLog; - size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd - dictPtr); - if (FSE_isError(offcodeHeaderSize)) - return ERROR(dictionary_corrupted); - if (offcodeLog > OffFSELog) - return ERROR(dictionary_corrupted); - /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */ - CHECK_E(FSE_buildCTable_wksp(cctx->offcodeCTable, offcodeNCount, offcodeMaxValue, offcodeLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)), - dictionary_corrupted); - dictPtr += offcodeHeaderSize; - } - - { - short matchlengthNCount[MaxML + 1]; - unsigned matchlengthMaxValue = MaxML, matchlengthLog; - size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd - dictPtr); - if (FSE_isError(matchlengthHeaderSize)) - return ERROR(dictionary_corrupted); - if (matchlengthLog > MLFSELog) - return ERROR(dictionary_corrupted); - /* Every match length code must have non-zero probability */ - CHECK_F(ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML)); - CHECK_E( - FSE_buildCTable_wksp(cctx->matchlengthCTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)), - dictionary_corrupted); - dictPtr += matchlengthHeaderSize; - } - - { - short litlengthNCount[MaxLL + 1]; - unsigned litlengthMaxValue = MaxLL, litlengthLog; - size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd - dictPtr); - if (FSE_isError(litlengthHeaderSize)) - return ERROR(dictionary_corrupted); - if (litlengthLog > LLFSELog) - return ERROR(dictionary_corrupted); - /* Every literal length code must have non-zero probability */ - CHECK_F(ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL)); - CHECK_E(FSE_buildCTable_wksp(cctx->litlengthCTable, litlengthNCount, litlengthMaxValue, litlengthLog, cctx->tmpCounters, sizeof(cctx->tmpCounters)), - dictionary_corrupted); - dictPtr += litlengthHeaderSize; - } - - if (dictPtr + 12 > dictEnd) - return ERROR(dictionary_corrupted); - cctx->rep[0] = ZSTD_readLE32(dictPtr + 0); - cctx->rep[1] = ZSTD_readLE32(dictPtr + 4); - cctx->rep[2] = ZSTD_readLE32(dictPtr + 8); - dictPtr += 12; - - { - size_t const dictContentSize = (size_t)(dictEnd - dictPtr); - U32 offcodeMax = MaxOff; - if (dictContentSize <= ((U32)-1) - 128 KB) { - U32 const maxOffset = (U32)dictContentSize + 128 KB; /* The maximum offset that must be supported */ - offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */ - } - /* All offset values <= dictContentSize + 128 KB must be representable */ - CHECK_F(ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff))); - /* All repCodes must be <= dictContentSize and != 0*/ - { - U32 u; - for (u = 0; u < 3; u++) { - if (cctx->rep[u] == 0) - return ERROR(dictionary_corrupted); - if (cctx->rep[u] > dictContentSize) - return ERROR(dictionary_corrupted); - } - } - - cctx->flagStaticTables = 1; - cctx->flagStaticHufTable = HUF_repeat_valid; - return ZSTD_loadDictionaryContent(cctx, dictPtr, dictContentSize); - } -} - -/** ZSTD_compress_insertDictionary() : -* @return : 0, or an error code */ -static size_t ZSTD_compress_insertDictionary(ZSTD_CCtx *cctx, const void *dict, size_t dictSize) -{ - if ((dict == NULL) || (dictSize <= 8)) - return 0; - - /* dict as pure content */ - if ((ZSTD_readLE32(dict) != ZSTD_DICT_MAGIC) || (cctx->forceRawDict)) - return ZSTD_loadDictionaryContent(cctx, dict, dictSize); - - /* dict as zstd dictionary */ - return ZSTD_loadZstdDictionary(cctx, dict, dictSize); -} - -/*! ZSTD_compressBegin_internal() : -* @return : 0, or an error code */ -static size_t ZSTD_compressBegin_internal(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, ZSTD_parameters params, U64 pledgedSrcSize) -{ - ZSTD_compResetPolicy_e const crp = dictSize ? ZSTDcrp_fullReset : ZSTDcrp_continue; - CHECK_F(ZSTD_resetCCtx_advanced(cctx, params, pledgedSrcSize, crp)); - return ZSTD_compress_insertDictionary(cctx, dict, dictSize); -} - -/*! ZSTD_compressBegin_advanced() : -* @return : 0, or an error code */ -size_t ZSTD_compressBegin_advanced(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize) -{ - /* compression parameters verification and optimization */ - CHECK_F(ZSTD_checkCParams(params.cParams)); - return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, pledgedSrcSize); -} - -size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx *cctx, const void *dict, size_t dictSize, int compressionLevel) -{ - ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, dictSize); - return ZSTD_compressBegin_internal(cctx, dict, dictSize, params, 0); -} - -size_t ZSTD_compressBegin(ZSTD_CCtx *cctx, int compressionLevel) { return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); } - -/*! ZSTD_writeEpilogue() : -* Ends a frame. -* @return : nb of bytes written into dst (or an error code) */ -static size_t ZSTD_writeEpilogue(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity) -{ - BYTE *const ostart = (BYTE *)dst; - BYTE *op = ostart; - size_t fhSize = 0; - - if (cctx->stage == ZSTDcs_created) - return ERROR(stage_wrong); /* init missing */ - - /* special case : empty frame */ - if (cctx->stage == ZSTDcs_init) { - fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->params, 0, 0); - if (ZSTD_isError(fhSize)) - return fhSize; - dstCapacity -= fhSize; - op += fhSize; - cctx->stage = ZSTDcs_ongoing; - } - - if (cctx->stage != ZSTDcs_ending) { - /* write one last empty block, make it the "last" block */ - U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw) << 1) + 0; - if (dstCapacity < 4) - return ERROR(dstSize_tooSmall); - ZSTD_writeLE32(op, cBlockHeader24); - op += ZSTD_blockHeaderSize; - dstCapacity -= ZSTD_blockHeaderSize; - } - - if (cctx->params.fParams.checksumFlag) { - U32 const checksum = (U32)xxh64_digest(&cctx->xxhState); - if (dstCapacity < 4) - return ERROR(dstSize_tooSmall); - ZSTD_writeLE32(op, checksum); - op += 4; - } - - cctx->stage = ZSTDcs_created; /* return to "created but no init" status */ - return op - ostart; -} - -size_t ZSTD_compressEnd(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - size_t endResult; - size_t const cSize = ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1, 1); - if (ZSTD_isError(cSize)) - return cSize; - endResult = ZSTD_writeEpilogue(cctx, (char *)dst + cSize, dstCapacity - cSize); - if (ZSTD_isError(endResult)) - return endResult; - return cSize + endResult; -} - -static size_t ZSTD_compress_internal(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize, - ZSTD_parameters params) -{ - CHECK_F(ZSTD_compressBegin_internal(cctx, dict, dictSize, params, srcSize)); - return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); -} - -size_t ZSTD_compress_usingDict(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize, - ZSTD_parameters params) -{ - return ZSTD_compress_internal(ctx, dst, dstCapacity, src, srcSize, dict, dictSize, params); -} - -size_t ZSTD_compressCCtx(ZSTD_CCtx *ctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, ZSTD_parameters params) -{ - return ZSTD_compress_internal(ctx, dst, dstCapacity, src, srcSize, NULL, 0, params); -} - -/* ===== Dictionary API ===== */ - -struct ZSTD_CDict_s { - void *dictBuffer; - const void *dictContent; - size_t dictContentSize; - ZSTD_CCtx *refContext; -}; /* typedef'd tp ZSTD_CDict within "zstd.h" */ - -size_t ZSTD_CDictWorkspaceBound(ZSTD_compressionParameters cParams) { return ZSTD_CCtxWorkspaceBound(cParams) + ZSTD_ALIGN(sizeof(ZSTD_CDict)); } - -static ZSTD_CDict *ZSTD_createCDict_advanced(const void *dictBuffer, size_t dictSize, unsigned byReference, ZSTD_parameters params, ZSTD_customMem customMem) -{ - if (!customMem.customAlloc || !customMem.customFree) - return NULL; - - { - ZSTD_CDict *const cdict = (ZSTD_CDict *)ZSTD_malloc(sizeof(ZSTD_CDict), customMem); - ZSTD_CCtx *const cctx = ZSTD_createCCtx_advanced(customMem); - - if (!cdict || !cctx) { - ZSTD_free(cdict, customMem); - ZSTD_freeCCtx(cctx); - return NULL; - } - - if ((byReference) || (!dictBuffer) || (!dictSize)) { - cdict->dictBuffer = NULL; - cdict->dictContent = dictBuffer; - } else { - void *const internalBuffer = ZSTD_malloc(dictSize, customMem); - if (!internalBuffer) { - ZSTD_free(cctx, customMem); - ZSTD_free(cdict, customMem); - return NULL; - } - memcpy(internalBuffer, dictBuffer, dictSize); - cdict->dictBuffer = internalBuffer; - cdict->dictContent = internalBuffer; - } - - { - size_t const errorCode = ZSTD_compressBegin_advanced(cctx, cdict->dictContent, dictSize, params, 0); - if (ZSTD_isError(errorCode)) { - ZSTD_free(cdict->dictBuffer, customMem); - ZSTD_free(cdict, customMem); - ZSTD_freeCCtx(cctx); - return NULL; - } - } - - cdict->refContext = cctx; - cdict->dictContentSize = dictSize; - return cdict; - } -} - -ZSTD_CDict *ZSTD_initCDict(const void *dict, size_t dictSize, ZSTD_parameters params, void *workspace, size_t workspaceSize) -{ - ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize); - return ZSTD_createCDict_advanced(dict, dictSize, 1, params, stackMem); -} - -size_t ZSTD_freeCDict(ZSTD_CDict *cdict) -{ - if (cdict == NULL) - return 0; /* support free on NULL */ - { - ZSTD_customMem const cMem = cdict->refContext->customMem; - ZSTD_freeCCtx(cdict->refContext); - ZSTD_free(cdict->dictBuffer, cMem); - ZSTD_free(cdict, cMem); - return 0; - } -} - -static ZSTD_parameters ZSTD_getParamsFromCDict(const ZSTD_CDict *cdict) { return ZSTD_getParamsFromCCtx(cdict->refContext); } - -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx *cctx, const ZSTD_CDict *cdict, unsigned long long pledgedSrcSize) -{ - if (cdict->dictContentSize) - CHECK_F(ZSTD_copyCCtx(cctx, cdict->refContext, pledgedSrcSize)) - else { - ZSTD_parameters params = cdict->refContext->params; - params.fParams.contentSizeFlag = (pledgedSrcSize > 0); - CHECK_F(ZSTD_compressBegin_advanced(cctx, NULL, 0, params, pledgedSrcSize)); - } - return 0; -} - -/*! ZSTD_compress_usingCDict() : -* Compression using a digested Dictionary. -* Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times. -* Note that compression level is decided during dictionary creation */ -size_t ZSTD_compress_usingCDict(ZSTD_CCtx *cctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const ZSTD_CDict *cdict) -{ - CHECK_F(ZSTD_compressBegin_usingCDict(cctx, cdict, srcSize)); - - if (cdict->refContext->params.fParams.contentSizeFlag == 1) { - cctx->params.fParams.contentSizeFlag = 1; - cctx->frameContentSize = srcSize; - } else { - cctx->params.fParams.contentSizeFlag = 0; - } - - return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); -} - -/* ****************************************************************** -* Streaming -********************************************************************/ - -typedef enum { zcss_init, zcss_load, zcss_flush, zcss_final } ZSTD_cStreamStage; - -struct ZSTD_CStream_s { - ZSTD_CCtx *cctx; - ZSTD_CDict *cdictLocal; - const ZSTD_CDict *cdict; - char *inBuff; - size_t inBuffSize; - size_t inToCompress; - size_t inBuffPos; - size_t inBuffTarget; - size_t blockSize; - char *outBuff; - size_t outBuffSize; - size_t outBuffContentSize; - size_t outBuffFlushedSize; - ZSTD_cStreamStage stage; - U32 checksum; - U32 frameEnded; - U64 pledgedSrcSize; - U64 inputProcessed; - ZSTD_parameters params; - ZSTD_customMem customMem; -}; /* typedef'd to ZSTD_CStream within "zstd.h" */ - -size_t ZSTD_CStreamWorkspaceBound(ZSTD_compressionParameters cParams) -{ - size_t const inBuffSize = (size_t)1 << cParams.windowLog; - size_t const blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, inBuffSize); - size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1; - - return ZSTD_CCtxWorkspaceBound(cParams) + ZSTD_ALIGN(sizeof(ZSTD_CStream)) + ZSTD_ALIGN(inBuffSize) + ZSTD_ALIGN(outBuffSize); -} - -ZSTD_CStream *ZSTD_createCStream_advanced(ZSTD_customMem customMem) -{ - ZSTD_CStream *zcs; - - if (!customMem.customAlloc || !customMem.customFree) - return NULL; - - zcs = (ZSTD_CStream *)ZSTD_malloc(sizeof(ZSTD_CStream), customMem); - if (zcs == NULL) - return NULL; - memset(zcs, 0, sizeof(ZSTD_CStream)); - memcpy(&zcs->customMem, &customMem, sizeof(ZSTD_customMem)); - zcs->cctx = ZSTD_createCCtx_advanced(customMem); - if (zcs->cctx == NULL) { - ZSTD_freeCStream(zcs); - return NULL; - } - return zcs; -} - -size_t ZSTD_freeCStream(ZSTD_CStream *zcs) -{ - if (zcs == NULL) - return 0; /* support free on NULL */ - { - ZSTD_customMem const cMem = zcs->customMem; - ZSTD_freeCCtx(zcs->cctx); - zcs->cctx = NULL; - ZSTD_freeCDict(zcs->cdictLocal); - zcs->cdictLocal = NULL; - ZSTD_free(zcs->inBuff, cMem); - zcs->inBuff = NULL; - ZSTD_free(zcs->outBuff, cMem); - zcs->outBuff = NULL; - ZSTD_free(zcs, cMem); - return 0; - } -} - -/*====== Initialization ======*/ - -size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; } -size_t ZSTD_CStreamOutSize(void) { return ZSTD_compressBound(ZSTD_BLOCKSIZE_ABSOLUTEMAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */; } - -static size_t ZSTD_resetCStream_internal(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize) -{ - if (zcs->inBuffSize == 0) - return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */ - - if (zcs->cdict) - CHECK_F(ZSTD_compressBegin_usingCDict(zcs->cctx, zcs->cdict, pledgedSrcSize)) - else - CHECK_F(ZSTD_compressBegin_advanced(zcs->cctx, NULL, 0, zcs->params, pledgedSrcSize)); - - zcs->inToCompress = 0; - zcs->inBuffPos = 0; - zcs->inBuffTarget = zcs->blockSize; - zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0; - zcs->stage = zcss_load; - zcs->frameEnded = 0; - zcs->pledgedSrcSize = pledgedSrcSize; - zcs->inputProcessed = 0; - return 0; /* ready to go */ -} - -size_t ZSTD_resetCStream(ZSTD_CStream *zcs, unsigned long long pledgedSrcSize) -{ - - zcs->params.fParams.contentSizeFlag = (pledgedSrcSize > 0); - - return ZSTD_resetCStream_internal(zcs, pledgedSrcSize); -} - -static size_t ZSTD_initCStream_advanced(ZSTD_CStream *zcs, const void *dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize) -{ - /* allocate buffers */ - { - size_t const neededInBuffSize = (size_t)1 << params.cParams.windowLog; - if (zcs->inBuffSize < neededInBuffSize) { - zcs->inBuffSize = neededInBuffSize; - ZSTD_free(zcs->inBuff, zcs->customMem); - zcs->inBuff = (char *)ZSTD_malloc(neededInBuffSize, zcs->customMem); - if (zcs->inBuff == NULL) - return ERROR(memory_allocation); - } - zcs->blockSize = MIN(ZSTD_BLOCKSIZE_ABSOLUTEMAX, neededInBuffSize); - } - if (zcs->outBuffSize < ZSTD_compressBound(zcs->blockSize) + 1) { - zcs->outBuffSize = ZSTD_compressBound(zcs->blockSize) + 1; - ZSTD_free(zcs->outBuff, zcs->customMem); - zcs->outBuff = (char *)ZSTD_malloc(zcs->outBuffSize, zcs->customMem); - if (zcs->outBuff == NULL) - return ERROR(memory_allocation); - } - - if (dict && dictSize >= 8) { - ZSTD_freeCDict(zcs->cdictLocal); - zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, 0, params, zcs->customMem); - if (zcs->cdictLocal == NULL) - return ERROR(memory_allocation); - zcs->cdict = zcs->cdictLocal; - } else - zcs->cdict = NULL; - - zcs->checksum = params.fParams.checksumFlag > 0; - zcs->params = params; - - return ZSTD_resetCStream_internal(zcs, pledgedSrcSize); -} - -ZSTD_CStream *ZSTD_initCStream(ZSTD_parameters params, unsigned long long pledgedSrcSize, void *workspace, size_t workspaceSize) -{ - ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize); - ZSTD_CStream *const zcs = ZSTD_createCStream_advanced(stackMem); - if (zcs) { - size_t const code = ZSTD_initCStream_advanced(zcs, NULL, 0, params, pledgedSrcSize); - if (ZSTD_isError(code)) { - return NULL; - } - } - return zcs; -} - -ZSTD_CStream *ZSTD_initCStream_usingCDict(const ZSTD_CDict *cdict, unsigned long long pledgedSrcSize, void *workspace, size_t workspaceSize) -{ - ZSTD_parameters const params = ZSTD_getParamsFromCDict(cdict); - ZSTD_CStream *const zcs = ZSTD_initCStream(params, pledgedSrcSize, workspace, workspaceSize); - if (zcs) { - zcs->cdict = cdict; - if (ZSTD_isError(ZSTD_resetCStream_internal(zcs, pledgedSrcSize))) { - return NULL; - } - } - return zcs; -} - -/*====== Compression ======*/ - -typedef enum { zsf_gather, zsf_flush, zsf_end } ZSTD_flush_e; - -ZSTD_STATIC size_t ZSTD_limitCopy(void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - size_t const length = MIN(dstCapacity, srcSize); - memcpy(dst, src, length); - return length; -} - -static size_t ZSTD_compressStream_generic(ZSTD_CStream *zcs, void *dst, size_t *dstCapacityPtr, const void *src, size_t *srcSizePtr, ZSTD_flush_e const flush) -{ - U32 someMoreWork = 1; - const char *const istart = (const char *)src; - const char *const iend = istart + *srcSizePtr; - const char *ip = istart; - char *const ostart = (char *)dst; - char *const oend = ostart + *dstCapacityPtr; - char *op = ostart; - - while (someMoreWork) { - switch (zcs->stage) { - case zcss_init: - return ERROR(init_missing); /* call ZBUFF_compressInit() first ! */ - - case zcss_load: - /* complete inBuffer */ - { - size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos; - size_t const loaded = ZSTD_limitCopy(zcs->inBuff + zcs->inBuffPos, toLoad, ip, iend - ip); - zcs->inBuffPos += loaded; - ip += loaded; - if ((zcs->inBuffPos == zcs->inToCompress) || (!flush && (toLoad != loaded))) { - someMoreWork = 0; - break; /* not enough input to get a full block : stop there, wait for more */ - } - } - /* compress curr block (note : this stage cannot be stopped in the middle) */ - { - void *cDst; - size_t cSize; - size_t const iSize = zcs->inBuffPos - zcs->inToCompress; - size_t oSize = oend - op; - if (oSize >= ZSTD_compressBound(iSize)) - cDst = op; /* compress directly into output buffer (avoid flush stage) */ - else - cDst = zcs->outBuff, oSize = zcs->outBuffSize; - cSize = (flush == zsf_end) ? ZSTD_compressEnd(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize) - : ZSTD_compressContinue(zcs->cctx, cDst, oSize, zcs->inBuff + zcs->inToCompress, iSize); - if (ZSTD_isError(cSize)) - return cSize; - if (flush == zsf_end) - zcs->frameEnded = 1; - /* prepare next block */ - zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize; - if (zcs->inBuffTarget > zcs->inBuffSize) - zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize; /* note : inBuffSize >= blockSize */ - zcs->inToCompress = zcs->inBuffPos; - if (cDst == op) { - op += cSize; - break; - } /* no need to flush */ - zcs->outBuffContentSize = cSize; - zcs->outBuffFlushedSize = 0; - zcs->stage = zcss_flush; /* pass-through to flush stage */ - } - fallthrough; - - case zcss_flush: { - size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize; - size_t const flushed = ZSTD_limitCopy(op, oend - op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush); - op += flushed; - zcs->outBuffFlushedSize += flushed; - if (toFlush != flushed) { - someMoreWork = 0; - break; - } /* dst too small to store flushed data : stop there */ - zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0; - zcs->stage = zcss_load; - break; - } - - case zcss_final: - someMoreWork = 0; /* do nothing */ - break; - - default: - return ERROR(GENERIC); /* impossible */ - } - } - - *srcSizePtr = ip - istart; - *dstCapacityPtr = op - ostart; - zcs->inputProcessed += *srcSizePtr; - if (zcs->frameEnded) - return 0; - { - size_t hintInSize = zcs->inBuffTarget - zcs->inBuffPos; - if (hintInSize == 0) - hintInSize = zcs->blockSize; - return hintInSize; - } -} - -size_t ZSTD_compressStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output, ZSTD_inBuffer *input) -{ - size_t sizeRead = input->size - input->pos; - size_t sizeWritten = output->size - output->pos; - size_t const result = - ZSTD_compressStream_generic(zcs, (char *)(output->dst) + output->pos, &sizeWritten, (const char *)(input->src) + input->pos, &sizeRead, zsf_gather); - input->pos += sizeRead; - output->pos += sizeWritten; - return result; -} - -/*====== Finalize ======*/ - -/*! ZSTD_flushStream() : -* @return : amount of data remaining to flush */ -size_t ZSTD_flushStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output) -{ - size_t srcSize = 0; - size_t sizeWritten = output->size - output->pos; - size_t const result = ZSTD_compressStream_generic(zcs, (char *)(output->dst) + output->pos, &sizeWritten, &srcSize, - &srcSize, /* use a valid src address instead of NULL */ - zsf_flush); - output->pos += sizeWritten; - if (ZSTD_isError(result)) - return result; - return zcs->outBuffContentSize - zcs->outBuffFlushedSize; /* remaining to flush */ -} - -size_t ZSTD_endStream(ZSTD_CStream *zcs, ZSTD_outBuffer *output) -{ - BYTE *const ostart = (BYTE *)(output->dst) + output->pos; - BYTE *const oend = (BYTE *)(output->dst) + output->size; - BYTE *op = ostart; - - if ((zcs->pledgedSrcSize) && (zcs->inputProcessed != zcs->pledgedSrcSize)) - return ERROR(srcSize_wrong); /* pledgedSrcSize not respected */ - - if (zcs->stage != zcss_final) { - /* flush whatever remains */ - size_t srcSize = 0; - size_t sizeWritten = output->size - output->pos; - size_t const notEnded = - ZSTD_compressStream_generic(zcs, ostart, &sizeWritten, &srcSize, &srcSize, zsf_end); /* use a valid src address instead of NULL */ - size_t const remainingToFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize; - op += sizeWritten; - if (remainingToFlush) { - output->pos += sizeWritten; - return remainingToFlush + ZSTD_BLOCKHEADERSIZE /* final empty block */ + (zcs->checksum * 4); - } - /* create epilogue */ - zcs->stage = zcss_final; - zcs->outBuffContentSize = !notEnded ? 0 : ZSTD_compressEnd(zcs->cctx, zcs->outBuff, zcs->outBuffSize, NULL, - 0); /* write epilogue, including final empty block, into outBuff */ - } - - /* flush epilogue */ - { - size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize; - size_t const flushed = ZSTD_limitCopy(op, oend - op, zcs->outBuff + zcs->outBuffFlushedSize, toFlush); - op += flushed; - zcs->outBuffFlushedSize += flushed; - output->pos += op - ostart; - if (toFlush == flushed) - zcs->stage = zcss_init; /* end reached */ - return toFlush - flushed; - } -} - -/*-===== Pre-defined compression levels =====-*/ - -#define ZSTD_DEFAULT_CLEVEL 1 -#define ZSTD_MAX_CLEVEL 22 -int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; } - -static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL + 1] = { - { - /* "default" */ - /* W, C, H, S, L, TL, strat */ - {18, 12, 12, 1, 7, 16, ZSTD_fast}, /* level 0 - never used */ - {19, 13, 14, 1, 7, 16, ZSTD_fast}, /* level 1 */ - {19, 15, 16, 1, 6, 16, ZSTD_fast}, /* level 2 */ - {20, 16, 17, 1, 5, 16, ZSTD_dfast}, /* level 3.*/ - {20, 18, 18, 1, 5, 16, ZSTD_dfast}, /* level 4.*/ - {20, 15, 18, 3, 5, 16, ZSTD_greedy}, /* level 5 */ - {21, 16, 19, 2, 5, 16, ZSTD_lazy}, /* level 6 */ - {21, 17, 20, 3, 5, 16, ZSTD_lazy}, /* level 7 */ - {21, 18, 20, 3, 5, 16, ZSTD_lazy2}, /* level 8 */ - {21, 20, 20, 3, 5, 16, ZSTD_lazy2}, /* level 9 */ - {21, 19, 21, 4, 5, 16, ZSTD_lazy2}, /* level 10 */ - {22, 20, 22, 4, 5, 16, ZSTD_lazy2}, /* level 11 */ - {22, 20, 22, 5, 5, 16, ZSTD_lazy2}, /* level 12 */ - {22, 21, 22, 5, 5, 16, ZSTD_lazy2}, /* level 13 */ - {22, 21, 22, 6, 5, 16, ZSTD_lazy2}, /* level 14 */ - {22, 21, 21, 5, 5, 16, ZSTD_btlazy2}, /* level 15 */ - {23, 22, 22, 5, 5, 16, ZSTD_btlazy2}, /* level 16 */ - {23, 21, 22, 4, 5, 24, ZSTD_btopt}, /* level 17 */ - {23, 23, 22, 6, 5, 32, ZSTD_btopt}, /* level 18 */ - {23, 23, 22, 6, 3, 48, ZSTD_btopt}, /* level 19 */ - {25, 25, 23, 7, 3, 64, ZSTD_btopt2}, /* level 20 */ - {26, 26, 23, 7, 3, 256, ZSTD_btopt2}, /* level 21 */ - {27, 27, 25, 9, 3, 512, ZSTD_btopt2}, /* level 22 */ - }, - { - /* for srcSize <= 256 KB */ - /* W, C, H, S, L, T, strat */ - {0, 0, 0, 0, 0, 0, ZSTD_fast}, /* level 0 - not used */ - {18, 13, 14, 1, 6, 8, ZSTD_fast}, /* level 1 */ - {18, 14, 13, 1, 5, 8, ZSTD_dfast}, /* level 2 */ - {18, 16, 15, 1, 5, 8, ZSTD_dfast}, /* level 3 */ - {18, 15, 17, 1, 5, 8, ZSTD_greedy}, /* level 4.*/ - {18, 16, 17, 4, 5, 8, ZSTD_greedy}, /* level 5.*/ - {18, 16, 17, 3, 5, 8, ZSTD_lazy}, /* level 6.*/ - {18, 17, 17, 4, 4, 8, ZSTD_lazy}, /* level 7 */ - {18, 17, 17, 4, 4, 8, ZSTD_lazy2}, /* level 8 */ - {18, 17, 17, 5, 4, 8, ZSTD_lazy2}, /* level 9 */ - {18, 17, 17, 6, 4, 8, ZSTD_lazy2}, /* level 10 */ - {18, 18, 17, 6, 4, 8, ZSTD_lazy2}, /* level 11.*/ - {18, 18, 17, 7, 4, 8, ZSTD_lazy2}, /* level 12.*/ - {18, 19, 17, 6, 4, 8, ZSTD_btlazy2}, /* level 13 */ - {18, 18, 18, 4, 4, 16, ZSTD_btopt}, /* level 14.*/ - {18, 18, 18, 4, 3, 16, ZSTD_btopt}, /* level 15.*/ - {18, 19, 18, 6, 3, 32, ZSTD_btopt}, /* level 16.*/ - {18, 19, 18, 8, 3, 64, ZSTD_btopt}, /* level 17.*/ - {18, 19, 18, 9, 3, 128, ZSTD_btopt}, /* level 18.*/ - {18, 19, 18, 10, 3, 256, ZSTD_btopt}, /* level 19.*/ - {18, 19, 18, 11, 3, 512, ZSTD_btopt2}, /* level 20.*/ - {18, 19, 18, 12, 3, 512, ZSTD_btopt2}, /* level 21.*/ - {18, 19, 18, 13, 3, 512, ZSTD_btopt2}, /* level 22.*/ - }, - { - /* for srcSize <= 128 KB */ - /* W, C, H, S, L, T, strat */ - {17, 12, 12, 1, 7, 8, ZSTD_fast}, /* level 0 - not used */ - {17, 12, 13, 1, 6, 8, ZSTD_fast}, /* level 1 */ - {17, 13, 16, 1, 5, 8, ZSTD_fast}, /* level 2 */ - {17, 16, 16, 2, 5, 8, ZSTD_dfast}, /* level 3 */ - {17, 13, 15, 3, 4, 8, ZSTD_greedy}, /* level 4 */ - {17, 15, 17, 4, 4, 8, ZSTD_greedy}, /* level 5 */ - {17, 16, 17, 3, 4, 8, ZSTD_lazy}, /* level 6 */ - {17, 15, 17, 4, 4, 8, ZSTD_lazy2}, /* level 7 */ - {17, 17, 17, 4, 4, 8, ZSTD_lazy2}, /* level 8 */ - {17, 17, 17, 5, 4, 8, ZSTD_lazy2}, /* level 9 */ - {17, 17, 17, 6, 4, 8, ZSTD_lazy2}, /* level 10 */ - {17, 17, 17, 7, 4, 8, ZSTD_lazy2}, /* level 11 */ - {17, 17, 17, 8, 4, 8, ZSTD_lazy2}, /* level 12 */ - {17, 18, 17, 6, 4, 8, ZSTD_btlazy2}, /* level 13.*/ - {17, 17, 17, 7, 3, 8, ZSTD_btopt}, /* level 14.*/ - {17, 17, 17, 7, 3, 16, ZSTD_btopt}, /* level 15.*/ - {17, 18, 17, 7, 3, 32, ZSTD_btopt}, /* level 16.*/ - {17, 18, 17, 7, 3, 64, ZSTD_btopt}, /* level 17.*/ - {17, 18, 17, 7, 3, 256, ZSTD_btopt}, /* level 18.*/ - {17, 18, 17, 8, 3, 256, ZSTD_btopt}, /* level 19.*/ - {17, 18, 17, 9, 3, 256, ZSTD_btopt2}, /* level 20.*/ - {17, 18, 17, 10, 3, 256, ZSTD_btopt2}, /* level 21.*/ - {17, 18, 17, 11, 3, 512, ZSTD_btopt2}, /* level 22.*/ - }, - { - /* for srcSize <= 16 KB */ - /* W, C, H, S, L, T, strat */ - {14, 12, 12, 1, 7, 6, ZSTD_fast}, /* level 0 - not used */ - {14, 14, 14, 1, 6, 6, ZSTD_fast}, /* level 1 */ - {14, 14, 14, 1, 4, 6, ZSTD_fast}, /* level 2 */ - {14, 14, 14, 1, 4, 6, ZSTD_dfast}, /* level 3.*/ - {14, 14, 14, 4, 4, 6, ZSTD_greedy}, /* level 4.*/ - {14, 14, 14, 3, 4, 6, ZSTD_lazy}, /* level 5.*/ - {14, 14, 14, 4, 4, 6, ZSTD_lazy2}, /* level 6 */ - {14, 14, 14, 5, 4, 6, ZSTD_lazy2}, /* level 7 */ - {14, 14, 14, 6, 4, 6, ZSTD_lazy2}, /* level 8.*/ - {14, 15, 14, 6, 4, 6, ZSTD_btlazy2}, /* level 9.*/ - {14, 15, 14, 3, 3, 6, ZSTD_btopt}, /* level 10.*/ - {14, 15, 14, 6, 3, 8, ZSTD_btopt}, /* level 11.*/ - {14, 15, 14, 6, 3, 16, ZSTD_btopt}, /* level 12.*/ - {14, 15, 14, 6, 3, 24, ZSTD_btopt}, /* level 13.*/ - {14, 15, 15, 6, 3, 48, ZSTD_btopt}, /* level 14.*/ - {14, 15, 15, 6, 3, 64, ZSTD_btopt}, /* level 15.*/ - {14, 15, 15, 6, 3, 96, ZSTD_btopt}, /* level 16.*/ - {14, 15, 15, 6, 3, 128, ZSTD_btopt}, /* level 17.*/ - {14, 15, 15, 6, 3, 256, ZSTD_btopt}, /* level 18.*/ - {14, 15, 15, 7, 3, 256, ZSTD_btopt}, /* level 19.*/ - {14, 15, 15, 8, 3, 256, ZSTD_btopt2}, /* level 20.*/ - {14, 15, 15, 9, 3, 256, ZSTD_btopt2}, /* level 21.*/ - {14, 15, 15, 10, 3, 256, ZSTD_btopt2}, /* level 22.*/ - }, -}; - -/*! ZSTD_getCParams() : -* @return ZSTD_compressionParameters structure for a selected compression level, `srcSize` and `dictSize`. -* Size values are optional, provide 0 if not known or unused */ -ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSize, size_t dictSize) -{ - ZSTD_compressionParameters cp; - size_t const addedSize = srcSize ? 0 : 500; - U64 const rSize = srcSize + dictSize ? srcSize + dictSize + addedSize : (U64)-1; - U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); /* intentional underflow for srcSizeHint == 0 */ - if (compressionLevel <= 0) - compressionLevel = ZSTD_DEFAULT_CLEVEL; /* 0 == default; no negative compressionLevel yet */ - if (compressionLevel > ZSTD_MAX_CLEVEL) - compressionLevel = ZSTD_MAX_CLEVEL; - cp = ZSTD_defaultCParameters[tableID][compressionLevel]; - if (ZSTD_32bits()) { /* auto-correction, for 32-bits mode */ - if (cp.windowLog > ZSTD_WINDOWLOG_MAX) - cp.windowLog = ZSTD_WINDOWLOG_MAX; - if (cp.chainLog > ZSTD_CHAINLOG_MAX) - cp.chainLog = ZSTD_CHAINLOG_MAX; - if (cp.hashLog > ZSTD_HASHLOG_MAX) - cp.hashLog = ZSTD_HASHLOG_MAX; - } - cp = ZSTD_adjustCParams(cp, srcSize, dictSize); - return cp; -} - -/*! ZSTD_getParams() : -* same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`). -* All fields of `ZSTD_frameParameters` are set to default (0) */ -ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSize, size_t dictSize) -{ - ZSTD_parameters params; - ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSize, dictSize); - memset(¶ms, 0, sizeof(params)); - params.cParams = cParams; - return params; -} - -size_t zstd_compress_bound(size_t src_size) -{ - return ZSTD_compressBound(src_size); -} -EXPORT_SYMBOL(zstd_compress_bound); - -int zstd_min_clevel(void) -{ - /* - * zstd-1.3.1 doesn't implement ZSTD_minCLevel(). - * Return 0 (default level). - */ - return 0; -} -EXPORT_SYMBOL(zstd_min_clevel); - -int zstd_max_clevel(void) -{ - return ZSTD_maxCLevel(); -} -EXPORT_SYMBOL(zstd_max_clevel); - -zstd_parameters zstd_get_params(int level, - unsigned long long estimated_src_size) -{ - return ZSTD_getParams(level, estimated_src_size, 0); -} -EXPORT_SYMBOL(zstd_get_params); - -size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams) -{ - return ZSTD_CCtxWorkspaceBound(*cparams); -} -EXPORT_SYMBOL(zstd_cctx_workspace_bound); - -zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size) -{ - return ZSTD_initCCtx(workspace, workspace_size); -} -EXPORT_SYMBOL(zstd_init_cctx); - -size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, - const void *src, size_t src_size, const zstd_parameters *parameters) -{ - return ZSTD_compressCCtx(cctx, dst, dst_capacity, src, src_size, *parameters); -} -EXPORT_SYMBOL(zstd_compress_cctx); - -size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams) -{ - return ZSTD_CStreamWorkspaceBound(*cparams); -} -EXPORT_SYMBOL(zstd_cstream_workspace_bound); - -zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters, - unsigned long long pledged_src_size, void *workspace, size_t workspace_size) -{ - return ZSTD_initCStream(*parameters, pledged_src_size, workspace, workspace_size); -} -EXPORT_SYMBOL(zstd_init_cstream); - -size_t zstd_reset_cstream(zstd_cstream *cstream, - unsigned long long pledged_src_size) -{ - return ZSTD_resetCStream(cstream, pledged_src_size); -} -EXPORT_SYMBOL(zstd_reset_cstream); - -size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output, - zstd_in_buffer *input) -{ - return ZSTD_compressStream(cstream, output, input); -} -EXPORT_SYMBOL(zstd_compress_stream); - -size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output) -{ - return ZSTD_flushStream(cstream, output); -} -EXPORT_SYMBOL(zstd_flush_stream); - -size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output) -{ - return ZSTD_endStream(cstream, output); -} -EXPORT_SYMBOL(zstd_end_stream); - -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_DESCRIPTION("Zstd Compressor"); diff --git a/lib/zstd/compress/fse_compress.c b/lib/zstd/compress/fse_compress.c new file mode 100644 index 000000000000..436985b620e5 --- /dev/null +++ b/lib/zstd/compress/fse_compress.c @@ -0,0 +1,625 @@ +/* ****************************************************************** + * FSE : Finite State Entropy encoder + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy + * - Public forum : https://groups.google.com/forum/#!forum/lz4c + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + +/* ************************************************************** +* Includes +****************************************************************/ +#include "../common/compiler.h" +#include "../common/mem.h" /* U32, U16, etc. */ +#include "../common/debug.h" /* assert, DEBUGLOG */ +#include "hist.h" /* HIST_count_wksp */ +#include "../common/bitstream.h" +#define FSE_STATIC_LINKING_ONLY +#include "../common/fse.h" +#include "../common/error_private.h" +#define ZSTD_DEPS_NEED_MALLOC +#define ZSTD_DEPS_NEED_MATH64 +#include "../common/zstd_deps.h" /* ZSTD_malloc, ZSTD_free, ZSTD_memcpy, ZSTD_memset */ + + +/* ************************************************************** +* Error Management +****************************************************************/ +#define FSE_isError ERR_isError + + +/* ************************************************************** +* Templates +****************************************************************/ +/* + designed to be included + for type-specific functions (template emulation in C) + Objective is to write these functions only once, for improved maintenance +*/ + +/* safety checks */ +#ifndef FSE_FUNCTION_EXTENSION +# error "FSE_FUNCTION_EXTENSION must be defined" +#endif +#ifndef FSE_FUNCTION_TYPE +# error "FSE_FUNCTION_TYPE must be defined" +#endif + +/* Function names */ +#define FSE_CAT(X,Y) X##Y +#define FSE_FUNCTION_NAME(X,Y) FSE_CAT(X,Y) +#define FSE_TYPE_NAME(X,Y) FSE_CAT(X,Y) + + +/* Function templates */ + +/* FSE_buildCTable_wksp() : + * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`). + * wkspSize should be sized to handle worst case situation, which is `1<>1 : 1) ; + FSE_symbolCompressionTransform* const symbolTT = (FSE_symbolCompressionTransform*) (FSCT); + U32 const step = FSE_TABLESTEP(tableSize); + + U32* cumul = (U32*)workSpace; + FSE_FUNCTION_TYPE* tableSymbol = (FSE_FUNCTION_TYPE*)(cumul + (maxSymbolValue + 2)); + + U32 highThreshold = tableSize-1; + + if ((size_t)workSpace & 3) return ERROR(GENERIC); /* Must be 4 byte aligned */ + if (FSE_BUILD_CTABLE_WORKSPACE_SIZE(maxSymbolValue, tableLog) > wkspSize) return ERROR(tableLog_tooLarge); + /* CTable header */ + tableU16[-2] = (U16) tableLog; + tableU16[-1] = (U16) maxSymbolValue; + assert(tableLog < 16); /* required for threshold strategy to work */ + + /* For explanations on how to distribute symbol values over the table : + * http://fastcompression.blogspot.fr/2014/02/fse-distributing-symbol-values.html */ + + #ifdef __clang_analyzer__ + ZSTD_memset(tableSymbol, 0, sizeof(*tableSymbol) * tableSize); /* useless initialization, just to keep scan-build happy */ + #endif + + /* symbol start positions */ + { U32 u; + cumul[0] = 0; + for (u=1; u <= maxSymbolValue+1; u++) { + if (normalizedCounter[u-1]==-1) { /* Low proba symbol */ + cumul[u] = cumul[u-1] + 1; + tableSymbol[highThreshold--] = (FSE_FUNCTION_TYPE)(u-1); + } else { + cumul[u] = cumul[u-1] + normalizedCounter[u-1]; + } } + cumul[maxSymbolValue+1] = tableSize+1; + } + + /* Spread symbols */ + { U32 position = 0; + U32 symbol; + for (symbol=0; symbol<=maxSymbolValue; symbol++) { + int nbOccurrences; + int const freq = normalizedCounter[symbol]; + for (nbOccurrences=0; nbOccurrences highThreshold) + position = (position + step) & tableMask; /* Low proba area */ + } } + + assert(position==0); /* Must have initialized all positions */ + } + + /* Build table */ + { U32 u; for (u=0; u> 3) + 3; + return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND; /* maxSymbolValue==0 ? use default */ +} + +static size_t +FSE_writeNCount_generic (void* header, size_t headerBufferSize, + const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, + unsigned writeIsSafe) +{ + BYTE* const ostart = (BYTE*) header; + BYTE* out = ostart; + BYTE* const oend = ostart + headerBufferSize; + int nbBits; + const int tableSize = 1 << tableLog; + int remaining; + int threshold; + U32 bitStream = 0; + int bitCount = 0; + unsigned symbol = 0; + unsigned const alphabetSize = maxSymbolValue + 1; + int previousIs0 = 0; + + /* Table Size */ + bitStream += (tableLog-FSE_MIN_TABLELOG) << bitCount; + bitCount += 4; + + /* Init */ + remaining = tableSize+1; /* +1 for extra accuracy */ + threshold = tableSize; + nbBits = tableLog+1; + + while ((symbol < alphabetSize) && (remaining>1)) { /* stops at 1 */ + if (previousIs0) { + unsigned start = symbol; + while ((symbol < alphabetSize) && !normalizedCounter[symbol]) symbol++; + if (symbol == alphabetSize) break; /* incorrect distribution */ + while (symbol >= start+24) { + start+=24; + bitStream += 0xFFFFU << bitCount; + if ((!writeIsSafe) && (out > oend-2)) + return ERROR(dstSize_tooSmall); /* Buffer overflow */ + out[0] = (BYTE) bitStream; + out[1] = (BYTE)(bitStream>>8); + out+=2; + bitStream>>=16; + } + while (symbol >= start+3) { + start+=3; + bitStream += 3 << bitCount; + bitCount += 2; + } + bitStream += (symbol-start) << bitCount; + bitCount += 2; + if (bitCount>16) { + if ((!writeIsSafe) && (out > oend - 2)) + return ERROR(dstSize_tooSmall); /* Buffer overflow */ + out[0] = (BYTE)bitStream; + out[1] = (BYTE)(bitStream>>8); + out += 2; + bitStream >>= 16; + bitCount -= 16; + } } + { int count = normalizedCounter[symbol++]; + int const max = (2*threshold-1) - remaining; + remaining -= count < 0 ? -count : count; + count++; /* +1 for extra accuracy */ + if (count>=threshold) + count += max; /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */ + bitStream += count << bitCount; + bitCount += nbBits; + bitCount -= (count>=1; } + } + if (bitCount>16) { + if ((!writeIsSafe) && (out > oend - 2)) + return ERROR(dstSize_tooSmall); /* Buffer overflow */ + out[0] = (BYTE)bitStream; + out[1] = (BYTE)(bitStream>>8); + out += 2; + bitStream >>= 16; + bitCount -= 16; + } } + + if (remaining != 1) + return ERROR(GENERIC); /* incorrect normalized distribution */ + assert(symbol <= alphabetSize); + + /* flush remaining bitStream */ + if ((!writeIsSafe) && (out > oend - 2)) + return ERROR(dstSize_tooSmall); /* Buffer overflow */ + out[0] = (BYTE)bitStream; + out[1] = (BYTE)(bitStream>>8); + out+= (bitCount+7) /8; + + return (out-ostart); +} + + +size_t FSE_writeNCount (void* buffer, size_t bufferSize, + const short* normalizedCounter, unsigned maxSymbolValue, unsigned tableLog) +{ + if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported */ + if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC); /* Unsupported */ + + if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog)) + return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 0); + + return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 1 /* write in buffer is safe */); +} + + +/*-************************************************************** +* FSE Compression Code +****************************************************************/ + +FSE_CTable* FSE_createCTable (unsigned maxSymbolValue, unsigned tableLog) +{ + size_t size; + if (tableLog > FSE_TABLELOG_ABSOLUTE_MAX) tableLog = FSE_TABLELOG_ABSOLUTE_MAX; + size = FSE_CTABLE_SIZE_U32 (tableLog, maxSymbolValue) * sizeof(U32); + return (FSE_CTable*)ZSTD_malloc(size); +} + +void FSE_freeCTable (FSE_CTable* ct) { ZSTD_free(ct); } + +/* provides the minimum logSize to safely represent a distribution */ +static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue) +{ + U32 minBitsSrc = BIT_highbit32((U32)(srcSize)) + 1; + U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2; + U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols; + assert(srcSize > 1); /* Not supported, RLE should be used instead */ + return minBits; +} + +unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus) +{ + U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus; + U32 tableLog = maxTableLog; + U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue); + assert(srcSize > 1); /* Not supported, RLE should be used instead */ + if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG; + if (maxBitsSrc < tableLog) tableLog = maxBitsSrc; /* Accuracy can be reduced */ + if (minBits > tableLog) tableLog = minBits; /* Need a minimum to safely represent all symbol values */ + if (tableLog < FSE_MIN_TABLELOG) tableLog = FSE_MIN_TABLELOG; + if (tableLog > FSE_MAX_TABLELOG) tableLog = FSE_MAX_TABLELOG; + return tableLog; +} + +unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue) +{ + return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 2); +} + +/* Secondary normalization method. + To be used when primary method fails. */ + +static size_t FSE_normalizeM2(short* norm, U32 tableLog, const unsigned* count, size_t total, U32 maxSymbolValue, short lowProbCount) +{ + short const NOT_YET_ASSIGNED = -2; + U32 s; + U32 distributed = 0; + U32 ToDistribute; + + /* Init */ + U32 const lowThreshold = (U32)(total >> tableLog); + U32 lowOne = (U32)((total * 3) >> (tableLog + 1)); + + for (s=0; s<=maxSymbolValue; s++) { + if (count[s] == 0) { + norm[s]=0; + continue; + } + if (count[s] <= lowThreshold) { + norm[s] = lowProbCount; + distributed++; + total -= count[s]; + continue; + } + if (count[s] <= lowOne) { + norm[s] = 1; + distributed++; + total -= count[s]; + continue; + } + + norm[s]=NOT_YET_ASSIGNED; + } + ToDistribute = (1 << tableLog) - distributed; + + if (ToDistribute == 0) + return 0; + + if ((total / ToDistribute) > lowOne) { + /* risk of rounding to zero */ + lowOne = (U32)((total * 3) / (ToDistribute * 2)); + for (s=0; s<=maxSymbolValue; s++) { + if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) { + norm[s] = 1; + distributed++; + total -= count[s]; + continue; + } } + ToDistribute = (1 << tableLog) - distributed; + } + + if (distributed == maxSymbolValue+1) { + /* all values are pretty poor; + probably incompressible data (should have already been detected); + find max, then give all remaining points to max */ + U32 maxV = 0, maxC = 0; + for (s=0; s<=maxSymbolValue; s++) + if (count[s] > maxC) { maxV=s; maxC=count[s]; } + norm[maxV] += (short)ToDistribute; + return 0; + } + + if (total == 0) { + /* all of the symbols were low enough for the lowOne or lowThreshold */ + for (s=0; ToDistribute > 0; s = (s+1)%(maxSymbolValue+1)) + if (norm[s] > 0) { ToDistribute--; norm[s]++; } + return 0; + } + + { U64 const vStepLog = 62 - tableLog; + U64 const mid = (1ULL << (vStepLog-1)) - 1; + U64 const rStep = ZSTD_div64((((U64)1<> vStepLog); + U32 const sEnd = (U32)(end >> vStepLog); + U32 const weight = sEnd - sStart; + if (weight < 1) + return ERROR(GENERIC); + norm[s] = (short)weight; + tmpTotal = end; + } } } + + return 0; +} + +size_t FSE_normalizeCount (short* normalizedCounter, unsigned tableLog, + const unsigned* count, size_t total, + unsigned maxSymbolValue, unsigned useLowProbCount) +{ + /* Sanity checks */ + if (tableLog==0) tableLog = FSE_DEFAULT_TABLELOG; + if (tableLog < FSE_MIN_TABLELOG) return ERROR(GENERIC); /* Unsupported size */ + if (tableLog > FSE_MAX_TABLELOG) return ERROR(tableLog_tooLarge); /* Unsupported size */ + if (tableLog < FSE_minTableLog(total, maxSymbolValue)) return ERROR(GENERIC); /* Too small tableLog, compression potentially impossible */ + + { static U32 const rtbTable[] = { 0, 473195, 504333, 520860, 550000, 700000, 750000, 830000 }; + short const lowProbCount = useLowProbCount ? -1 : 1; + U64 const scale = 62 - tableLog; + U64 const step = ZSTD_div64((U64)1<<62, (U32)total); /* <== here, one division ! */ + U64 const vStep = 1ULL<<(scale-20); + int stillToDistribute = 1<> tableLog); + + for (s=0; s<=maxSymbolValue; s++) { + if (count[s] == total) return 0; /* rle special case */ + if (count[s] == 0) { normalizedCounter[s]=0; continue; } + if (count[s] <= lowThreshold) { + normalizedCounter[s] = lowProbCount; + stillToDistribute--; + } else { + short proba = (short)((count[s]*step) >> scale); + if (proba<8) { + U64 restToBeat = vStep * rtbTable[proba]; + proba += (count[s]*step) - ((U64)proba< restToBeat; + } + if (proba > largestP) { largestP=proba; largest=s; } + normalizedCounter[s] = proba; + stillToDistribute -= proba; + } } + if (-stillToDistribute >= (normalizedCounter[largest] >> 1)) { + /* corner case, need another normalization method */ + size_t const errorCode = FSE_normalizeM2(normalizedCounter, tableLog, count, total, maxSymbolValue, lowProbCount); + if (FSE_isError(errorCode)) return errorCode; + } + else normalizedCounter[largest] += (short)stillToDistribute; + } + +#if 0 + { /* Print Table (debug) */ + U32 s; + U32 nTotal = 0; + for (s=0; s<=maxSymbolValue; s++) + RAWLOG(2, "%3i: %4i \n", s, normalizedCounter[s]); + for (s=0; s<=maxSymbolValue; s++) + nTotal += abs(normalizedCounter[s]); + if (nTotal != (1U<>1); /* assumption : tableLog >= 1 */ + FSE_symbolCompressionTransform* const symbolTT = (FSE_symbolCompressionTransform*) (FSCT); + unsigned s; + + /* Sanity checks */ + if (nbBits < 1) return ERROR(GENERIC); /* min size */ + + /* header */ + tableU16[-2] = (U16) nbBits; + tableU16[-1] = (U16) maxSymbolValue; + + /* Build table */ + for (s=0; s FSE_MAX_TABLELOG*4+7 ) && (srcSize & 2)) { /* test bit 2 */ + FSE_encodeSymbol(&bitC, &CState2, *--ip); + FSE_encodeSymbol(&bitC, &CState1, *--ip); + FSE_FLUSHBITS(&bitC); + } + + /* 2 or 4 encoding per loop */ + while ( ip>istart ) { + + FSE_encodeSymbol(&bitC, &CState2, *--ip); + + if (sizeof(bitC.bitContainer)*8 < FSE_MAX_TABLELOG*2+7 ) /* this test must be static */ + FSE_FLUSHBITS(&bitC); + + FSE_encodeSymbol(&bitC, &CState1, *--ip); + + if (sizeof(bitC.bitContainer)*8 > FSE_MAX_TABLELOG*4+7 ) { /* this test must be static */ + FSE_encodeSymbol(&bitC, &CState2, *--ip); + FSE_encodeSymbol(&bitC, &CState1, *--ip); + } + + FSE_FLUSHBITS(&bitC); + } + + FSE_flushCState(&bitC, &CState2); + FSE_flushCState(&bitC, &CState1); + return BIT_closeCStream(&bitC); +} + +size_t FSE_compress_usingCTable (void* dst, size_t dstSize, + const void* src, size_t srcSize, + const FSE_CTable* ct) +{ + unsigned const fast = (dstSize >= FSE_BLOCKBOUND(srcSize)); + + if (fast) + return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 1); + else + return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 0); +} + + +size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); } + + +#endif /* FSE_COMMONDEFS_ONLY */ diff --git a/lib/zstd/compress/hist.c b/lib/zstd/compress/hist.c new file mode 100644 index 000000000000..3ddc6dfb6894 --- /dev/null +++ b/lib/zstd/compress/hist.c @@ -0,0 +1,165 @@ +/* ****************************************************************** + * hist : Histogram functions + * part of Finite State Entropy project + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy + * - Public forum : https://groups.google.com/forum/#!forum/lz4c + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + +/* --- dependencies --- */ +#include "../common/mem.h" /* U32, BYTE, etc. */ +#include "../common/debug.h" /* assert, DEBUGLOG */ +#include "../common/error_private.h" /* ERROR */ +#include "hist.h" + + +/* --- Error management --- */ +unsigned HIST_isError(size_t code) { return ERR_isError(code); } + +/*-************************************************************** + * Histogram functions + ****************************************************************/ +unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr, + const void* src, size_t srcSize) +{ + const BYTE* ip = (const BYTE*)src; + const BYTE* const end = ip + srcSize; + unsigned maxSymbolValue = *maxSymbolValuePtr; + unsigned largestCount=0; + + ZSTD_memset(count, 0, (maxSymbolValue+1) * sizeof(*count)); + if (srcSize==0) { *maxSymbolValuePtr = 0; return 0; } + + while (ip largestCount) largestCount = count[s]; + } + + return largestCount; +} + +typedef enum { trustInput, checkMaxSymbolValue } HIST_checkInput_e; + +/* HIST_count_parallel_wksp() : + * store histogram into 4 intermediate tables, recombined at the end. + * this design makes better use of OoO cpus, + * and is noticeably faster when some values are heavily repeated. + * But it needs some additional workspace for intermediate tables. + * `workSpace` must be a U32 table of size >= HIST_WKSP_SIZE_U32. + * @return : largest histogram frequency, + * or an error code (notably when histogram's alphabet is larger than *maxSymbolValuePtr) */ +static size_t HIST_count_parallel_wksp( + unsigned* count, unsigned* maxSymbolValuePtr, + const void* source, size_t sourceSize, + HIST_checkInput_e check, + U32* const workSpace) +{ + const BYTE* ip = (const BYTE*)source; + const BYTE* const iend = ip+sourceSize; + size_t const countSize = (*maxSymbolValuePtr + 1) * sizeof(*count); + unsigned max=0; + U32* const Counting1 = workSpace; + U32* const Counting2 = Counting1 + 256; + U32* const Counting3 = Counting2 + 256; + U32* const Counting4 = Counting3 + 256; + + /* safety checks */ + assert(*maxSymbolValuePtr <= 255); + if (!sourceSize) { + ZSTD_memset(count, 0, countSize); + *maxSymbolValuePtr = 0; + return 0; + } + ZSTD_memset(workSpace, 0, 4*256*sizeof(unsigned)); + + /* by stripes of 16 bytes */ + { U32 cached = MEM_read32(ip); ip += 4; + while (ip < iend-15) { + U32 c = cached; cached = MEM_read32(ip); ip += 4; + Counting1[(BYTE) c ]++; + Counting2[(BYTE)(c>>8) ]++; + Counting3[(BYTE)(c>>16)]++; + Counting4[ c>>24 ]++; + c = cached; cached = MEM_read32(ip); ip += 4; + Counting1[(BYTE) c ]++; + Counting2[(BYTE)(c>>8) ]++; + Counting3[(BYTE)(c>>16)]++; + Counting4[ c>>24 ]++; + c = cached; cached = MEM_read32(ip); ip += 4; + Counting1[(BYTE) c ]++; + Counting2[(BYTE)(c>>8) ]++; + Counting3[(BYTE)(c>>16)]++; + Counting4[ c>>24 ]++; + c = cached; cached = MEM_read32(ip); ip += 4; + Counting1[(BYTE) c ]++; + Counting2[(BYTE)(c>>8) ]++; + Counting3[(BYTE)(c>>16)]++; + Counting4[ c>>24 ]++; + } + ip-=4; + } + + /* finish last symbols */ + while (ip max) max = Counting1[s]; + } } + + { unsigned maxSymbolValue = 255; + while (!Counting1[maxSymbolValue]) maxSymbolValue--; + if (check && maxSymbolValue > *maxSymbolValuePtr) return ERROR(maxSymbolValue_tooSmall); + *maxSymbolValuePtr = maxSymbolValue; + ZSTD_memmove(count, Counting1, countSize); /* in case count & Counting1 are overlapping */ + } + return (size_t)max; +} + +/* HIST_countFast_wksp() : + * Same as HIST_countFast(), but using an externally provided scratch buffer. + * `workSpace` is a writable buffer which must be 4-bytes aligned, + * `workSpaceSize` must be >= HIST_WKSP_SIZE + */ +size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, + const void* source, size_t sourceSize, + void* workSpace, size_t workSpaceSize) +{ + if (sourceSize < 1500) /* heuristic threshold */ + return HIST_count_simple(count, maxSymbolValuePtr, source, sourceSize); + if ((size_t)workSpace & 3) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */ + if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall); + return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, trustInput, (U32*)workSpace); +} + +/* HIST_count_wksp() : + * Same as HIST_count(), but using an externally provided scratch buffer. + * `workSpace` size must be table of >= HIST_WKSP_SIZE_U32 unsigned */ +size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr, + const void* source, size_t sourceSize, + void* workSpace, size_t workSpaceSize) +{ + if ((size_t)workSpace & 3) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */ + if (workSpaceSize < HIST_WKSP_SIZE) return ERROR(workSpace_tooSmall); + if (*maxSymbolValuePtr < 255) + return HIST_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, checkMaxSymbolValue, (U32*)workSpace); + *maxSymbolValuePtr = 255; + return HIST_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace, workSpaceSize); +} + diff --git a/lib/zstd/compress/hist.h b/lib/zstd/compress/hist.h new file mode 100644 index 000000000000..fc1830abc9c6 --- /dev/null +++ b/lib/zstd/compress/hist.h @@ -0,0 +1,75 @@ +/* ****************************************************************** + * hist : Histogram functions + * part of Finite State Entropy project + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE source repository : https://github.com/Cyan4973/FiniteStateEntropy + * - Public forum : https://groups.google.com/forum/#!forum/lz4c + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + +/* --- dependencies --- */ +#include "../common/zstd_deps.h" /* size_t */ + + +/* --- simple histogram functions --- */ + +/*! HIST_count(): + * Provides the precise count of each byte within a table 'count'. + * 'count' is a table of unsigned int, of minimum size (*maxSymbolValuePtr+1). + * Updates *maxSymbolValuePtr with actual largest symbol value detected. + * @return : count of the most frequent symbol (which isn't identified). + * or an error code, which can be tested using HIST_isError(). + * note : if return == srcSize, there is only one symbol. + */ +size_t HIST_count(unsigned* count, unsigned* maxSymbolValuePtr, + const void* src, size_t srcSize); + +unsigned HIST_isError(size_t code); /*< tells if a return value is an error code */ + + +/* --- advanced histogram functions --- */ + +#define HIST_WKSP_SIZE_U32 1024 +#define HIST_WKSP_SIZE (HIST_WKSP_SIZE_U32 * sizeof(unsigned)) +/* HIST_count_wksp() : + * Same as HIST_count(), but using an externally provided scratch buffer. + * Benefit is this function will use very little stack space. + * `workSpace` is a writable buffer which must be 4-bytes aligned, + * `workSpaceSize` must be >= HIST_WKSP_SIZE + */ +size_t HIST_count_wksp(unsigned* count, unsigned* maxSymbolValuePtr, + const void* src, size_t srcSize, + void* workSpace, size_t workSpaceSize); + +/* HIST_countFast() : + * same as HIST_count(), but blindly trusts that all byte values within src are <= *maxSymbolValuePtr. + * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` + */ +size_t HIST_countFast(unsigned* count, unsigned* maxSymbolValuePtr, + const void* src, size_t srcSize); + +/* HIST_countFast_wksp() : + * Same as HIST_countFast(), but using an externally provided scratch buffer. + * `workSpace` is a writable buffer which must be 4-bytes aligned, + * `workSpaceSize` must be >= HIST_WKSP_SIZE + */ +size_t HIST_countFast_wksp(unsigned* count, unsigned* maxSymbolValuePtr, + const void* src, size_t srcSize, + void* workSpace, size_t workSpaceSize); + +/*! HIST_count_simple() : + * Same as HIST_countFast(), this function is unsafe, + * and will segfault if any value within `src` is `> *maxSymbolValuePtr`. + * It is also a bit slower for large inputs. + * However, it does not need any additional memory (not even on stack). + * @return : count of the most frequent symbol. + * Note this function doesn't produce any error (i.e. it must succeed). + */ +unsigned HIST_count_simple(unsigned* count, unsigned* maxSymbolValuePtr, + const void* src, size_t srcSize); diff --git a/lib/zstd/compress/huf_compress.c b/lib/zstd/compress/huf_compress.c new file mode 100644 index 000000000000..f76a526bfa54 --- /dev/null +++ b/lib/zstd/compress/huf_compress.c @@ -0,0 +1,905 @@ +/* ****************************************************************** + * Huffman encoder, part of New Generation Entropy library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy + * - Public forum : https://groups.google.com/forum/#!forum/lz4c + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + +/* ************************************************************** +* Compiler specifics +****************************************************************/ + + +/* ************************************************************** +* Includes +****************************************************************/ +#include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memset */ +#include "../common/compiler.h" +#include "../common/bitstream.h" +#include "hist.h" +#define FSE_STATIC_LINKING_ONLY /* FSE_optimalTableLog_internal */ +#include "../common/fse.h" /* header compression */ +#define HUF_STATIC_LINKING_ONLY +#include "../common/huf.h" +#include "../common/error_private.h" + + +/* ************************************************************** +* Error Management +****************************************************************/ +#define HUF_isError ERR_isError +#define HUF_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) /* use only *after* variable declarations */ + + +/* ************************************************************** +* Utils +****************************************************************/ +unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue) +{ + return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 1); +} + + +/* ******************************************************* +* HUF : Huffman block compression +*********************************************************/ +/* HUF_compressWeights() : + * Same as FSE_compress(), but dedicated to huff0's weights compression. + * The use case needs much less stack memory. + * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX. + */ +#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6 + +typedef struct { + FSE_CTable CTable[FSE_CTABLE_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX)]; + U32 scratchBuffer[FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(HUF_TABLELOG_MAX, MAX_FSE_TABLELOG_FOR_HUFF_HEADER)]; + unsigned count[HUF_TABLELOG_MAX+1]; + S16 norm[HUF_TABLELOG_MAX+1]; +} HUF_CompressWeightsWksp; + +static size_t HUF_compressWeights(void* dst, size_t dstSize, const void* weightTable, size_t wtSize, void* workspace, size_t workspaceSize) +{ + BYTE* const ostart = (BYTE*) dst; + BYTE* op = ostart; + BYTE* const oend = ostart + dstSize; + + unsigned maxSymbolValue = HUF_TABLELOG_MAX; + U32 tableLog = MAX_FSE_TABLELOG_FOR_HUFF_HEADER; + HUF_CompressWeightsWksp* wksp = (HUF_CompressWeightsWksp*)workspace; + + if (workspaceSize < sizeof(HUF_CompressWeightsWksp)) return ERROR(GENERIC); + + /* init conditions */ + if (wtSize <= 1) return 0; /* Not compressible */ + + /* Scan input and build symbol stats */ + { unsigned const maxCount = HIST_count_simple(wksp->count, &maxSymbolValue, weightTable, wtSize); /* never fails */ + if (maxCount == wtSize) return 1; /* only a single symbol in src : rle */ + if (maxCount == 1) return 0; /* each symbol present maximum once => not compressible */ + } + + tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue); + CHECK_F( FSE_normalizeCount(wksp->norm, tableLog, wksp->count, wtSize, maxSymbolValue, /* useLowProbCount */ 0) ); + + /* Write table description header */ + { CHECK_V_F(hSize, FSE_writeNCount(op, (size_t)(oend-op), wksp->norm, maxSymbolValue, tableLog) ); + op += hSize; + } + + /* Compress */ + CHECK_F( FSE_buildCTable_wksp(wksp->CTable, wksp->norm, maxSymbolValue, tableLog, wksp->scratchBuffer, sizeof(wksp->scratchBuffer)) ); + { CHECK_V_F(cSize, FSE_compress_usingCTable(op, (size_t)(oend - op), weightTable, wtSize, wksp->CTable) ); + if (cSize == 0) return 0; /* not enough space for compressed data */ + op += cSize; + } + + return (size_t)(op-ostart); +} + + +typedef struct { + HUF_CompressWeightsWksp wksp; + BYTE bitsToWeight[HUF_TABLELOG_MAX + 1]; /* precomputed conversion table */ + BYTE huffWeight[HUF_SYMBOLVALUE_MAX]; +} HUF_WriteCTableWksp; + +size_t HUF_writeCTable_wksp(void* dst, size_t maxDstSize, + const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog, + void* workspace, size_t workspaceSize) +{ + BYTE* op = (BYTE*)dst; + U32 n; + HUF_WriteCTableWksp* wksp = (HUF_WriteCTableWksp*)workspace; + + /* check conditions */ + if (workspaceSize < sizeof(HUF_WriteCTableWksp)) return ERROR(GENERIC); + if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge); + + /* convert to weight */ + wksp->bitsToWeight[0] = 0; + for (n=1; nbitsToWeight[n] = (BYTE)(huffLog + 1 - n); + for (n=0; nhuffWeight[n] = wksp->bitsToWeight[CTable[n].nbBits]; + + /* attempt weights compression by FSE */ + { CHECK_V_F(hSize, HUF_compressWeights(op+1, maxDstSize-1, wksp->huffWeight, maxSymbolValue, &wksp->wksp, sizeof(wksp->wksp)) ); + if ((hSize>1) & (hSize < maxSymbolValue/2)) { /* FSE compressed */ + op[0] = (BYTE)hSize; + return hSize+1; + } } + + /* write raw values as 4-bits (max : 15) */ + if (maxSymbolValue > (256-128)) return ERROR(GENERIC); /* should not happen : likely means source cannot be compressed */ + if (((maxSymbolValue+1)/2) + 1 > maxDstSize) return ERROR(dstSize_tooSmall); /* not enough space within dst buffer */ + op[0] = (BYTE)(128 /*special case*/ + (maxSymbolValue-1)); + wksp->huffWeight[maxSymbolValue] = 0; /* to be sure it doesn't cause msan issue in final combination */ + for (n=0; nhuffWeight[n] << 4) + wksp->huffWeight[n+1]); + return ((maxSymbolValue+1)/2) + 1; +} + +/*! HUF_writeCTable() : + `CTable` : Huffman tree to save, using huf representation. + @return : size of saved CTable */ +size_t HUF_writeCTable (void* dst, size_t maxDstSize, + const HUF_CElt* CTable, unsigned maxSymbolValue, unsigned huffLog) +{ + HUF_WriteCTableWksp wksp; + return HUF_writeCTable_wksp(dst, maxDstSize, CTable, maxSymbolValue, huffLog, &wksp, sizeof(wksp)); +} + + +size_t HUF_readCTable (HUF_CElt* CTable, unsigned* maxSymbolValuePtr, const void* src, size_t srcSize, unsigned* hasZeroWeights) +{ + BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1]; /* init not required, even though some static analyzer may complain */ + U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1]; /* large enough for values from 0 to 16 */ + U32 tableLog = 0; + U32 nbSymbols = 0; + + /* get symbol weights */ + CHECK_V_F(readSize, HUF_readStats(huffWeight, HUF_SYMBOLVALUE_MAX+1, rankVal, &nbSymbols, &tableLog, src, srcSize)); + *hasZeroWeights = (rankVal[0] > 0); + + /* check result */ + if (tableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); + if (nbSymbols > *maxSymbolValuePtr+1) return ERROR(maxSymbolValue_tooSmall); + + /* Prepare base value per rank */ + { U32 n, nextRankStart = 0; + for (n=1; n<=tableLog; n++) { + U32 curr = nextRankStart; + nextRankStart += (rankVal[n] << (n-1)); + rankVal[n] = curr; + } } + + /* fill nbBits */ + { U32 n; for (n=0; nn=tableLog+1 */ + U16 valPerRank[HUF_TABLELOG_MAX+2] = {0}; + { U32 n; for (n=0; n0; n--) { /* start at n=tablelog <-> w=1 */ + valPerRank[n] = min; /* get starting value within each rank */ + min += nbPerRank[n]; + min >>= 1; + } } + /* assign value within rank, symbol order */ + { U32 n; for (n=0; n maxNbBits to be maxNbBits. Then it adjusts + * the tree to so that it is a valid canonical Huffman tree. + * + * @pre The sum of the ranks of each symbol == 2^largestBits, + * where largestBits == huffNode[lastNonNull].nbBits. + * @post The sum of the ranks of each symbol == 2^largestBits, + * where largestBits is the return value <= maxNbBits. + * + * @param huffNode The Huffman tree modified in place to enforce maxNbBits. + * @param lastNonNull The symbol with the lowest count in the Huffman tree. + * @param maxNbBits The maximum allowed number of bits, which the Huffman tree + * may not respect. After this function the Huffman tree will + * respect maxNbBits. + * @return The maximum number of bits of the Huffman tree after adjustment, + * necessarily no more than maxNbBits. + */ +static U32 HUF_setMaxHeight(nodeElt* huffNode, U32 lastNonNull, U32 maxNbBits) +{ + const U32 largestBits = huffNode[lastNonNull].nbBits; + /* early exit : no elt > maxNbBits, so the tree is already valid. */ + if (largestBits <= maxNbBits) return largestBits; + + /* there are several too large elements (at least >= 2) */ + { int totalCost = 0; + const U32 baseCost = 1 << (largestBits - maxNbBits); + int n = (int)lastNonNull; + + /* Adjust any ranks > maxNbBits to maxNbBits. + * Compute totalCost, which is how far the sum of the ranks is + * we are over 2^largestBits after adjust the offending ranks. + */ + while (huffNode[n].nbBits > maxNbBits) { + totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits)); + huffNode[n].nbBits = (BYTE)maxNbBits; + n--; + } + /* n stops at huffNode[n].nbBits <= maxNbBits */ + assert(huffNode[n].nbBits <= maxNbBits); + /* n end at index of smallest symbol using < maxNbBits */ + while (huffNode[n].nbBits == maxNbBits) --n; + + /* renorm totalCost from 2^largestBits to 2^maxNbBits + * note : totalCost is necessarily a multiple of baseCost */ + assert((totalCost & (baseCost - 1)) == 0); + totalCost >>= (largestBits - maxNbBits); + assert(totalCost > 0); + + /* repay normalized cost */ + { U32 const noSymbol = 0xF0F0F0F0; + U32 rankLast[HUF_TABLELOG_MAX+2]; + + /* Get pos of last (smallest = lowest cum. count) symbol per rank */ + ZSTD_memset(rankLast, 0xF0, sizeof(rankLast)); + { U32 currentNbBits = maxNbBits; + int pos; + for (pos=n ; pos >= 0; pos--) { + if (huffNode[pos].nbBits >= currentNbBits) continue; + currentNbBits = huffNode[pos].nbBits; /* < maxNbBits */ + rankLast[maxNbBits-currentNbBits] = (U32)pos; + } } + + while (totalCost > 0) { + /* Try to reduce the next power of 2 above totalCost because we + * gain back half the rank. + */ + U32 nBitsToDecrease = BIT_highbit32((U32)totalCost) + 1; + for ( ; nBitsToDecrease > 1; nBitsToDecrease--) { + U32 const highPos = rankLast[nBitsToDecrease]; + U32 const lowPos = rankLast[nBitsToDecrease-1]; + if (highPos == noSymbol) continue; + /* Decrease highPos if no symbols of lowPos or if it is + * not cheaper to remove 2 lowPos than highPos. + */ + if (lowPos == noSymbol) break; + { U32 const highTotal = huffNode[highPos].count; + U32 const lowTotal = 2 * huffNode[lowPos].count; + if (highTotal <= lowTotal) break; + } } + /* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */ + assert(rankLast[nBitsToDecrease] != noSymbol || nBitsToDecrease == 1); + /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */ + while ((nBitsToDecrease<=HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol)) + nBitsToDecrease++; + assert(rankLast[nBitsToDecrease] != noSymbol); + /* Increase the number of bits to gain back half the rank cost. */ + totalCost -= 1 << (nBitsToDecrease-1); + huffNode[rankLast[nBitsToDecrease]].nbBits++; + + /* Fix up the new rank. + * If the new rank was empty, this symbol is now its smallest. + * Otherwise, this symbol will be the largest in the new rank so no adjustment. + */ + if (rankLast[nBitsToDecrease-1] == noSymbol) + rankLast[nBitsToDecrease-1] = rankLast[nBitsToDecrease]; + /* Fix up the old rank. + * If the symbol was at position 0, meaning it was the highest weight symbol in the tree, + * it must be the only symbol in its rank, so the old rank now has no symbols. + * Otherwise, since the Huffman nodes are sorted by count, the previous position is now + * the smallest node in the rank. If the previous position belongs to a different rank, + * then the rank is now empty. + */ + if (rankLast[nBitsToDecrease] == 0) /* special case, reached largest symbol */ + rankLast[nBitsToDecrease] = noSymbol; + else { + rankLast[nBitsToDecrease]--; + if (huffNode[rankLast[nBitsToDecrease]].nbBits != maxNbBits-nBitsToDecrease) + rankLast[nBitsToDecrease] = noSymbol; /* this rank is now empty */ + } + } /* while (totalCost > 0) */ + + /* If we've removed too much weight, then we have to add it back. + * To avoid overshooting again, we only adjust the smallest rank. + * We take the largest nodes from the lowest rank 0 and move them + * to rank 1. There's guaranteed to be enough rank 0 symbols because + * TODO. + */ + while (totalCost < 0) { /* Sometimes, cost correction overshoot */ + /* special case : no rank 1 symbol (using maxNbBits-1); + * let's create one from largest rank 0 (using maxNbBits). + */ + if (rankLast[1] == noSymbol) { + while (huffNode[n].nbBits == maxNbBits) n--; + huffNode[n+1].nbBits--; + assert(n >= 0); + rankLast[1] = (U32)(n+1); + totalCost++; + continue; + } + huffNode[ rankLast[1] + 1 ].nbBits--; + rankLast[1]++; + totalCost ++; + } + } /* repay normalized cost */ + } /* there are several too large elements (at least >= 2) */ + + return maxNbBits; +} + +typedef struct { + U32 base; + U32 curr; +} rankPos; + +typedef nodeElt huffNodeTable[HUF_CTABLE_WORKSPACE_SIZE_U32]; + +#define RANK_POSITION_TABLE_SIZE 32 + +typedef struct { + huffNodeTable huffNodeTbl; + rankPos rankPosition[RANK_POSITION_TABLE_SIZE]; +} HUF_buildCTable_wksp_tables; + +/* + * HUF_sort(): + * Sorts the symbols [0, maxSymbolValue] by count[symbol] in decreasing order. + * + * @param[out] huffNode Sorted symbols by decreasing count. Only members `.count` and `.byte` are filled. + * Must have (maxSymbolValue + 1) entries. + * @param[in] count Histogram of the symbols. + * @param[in] maxSymbolValue Maximum symbol value. + * @param rankPosition This is a scratch workspace. Must have RANK_POSITION_TABLE_SIZE entries. + */ +static void HUF_sort(nodeElt* huffNode, const unsigned* count, U32 maxSymbolValue, rankPos* rankPosition) +{ + int n; + int const maxSymbolValue1 = (int)maxSymbolValue + 1; + + /* Compute base and set curr to base. + * For symbol s let lowerRank = BIT_highbit32(count[n]+1) and rank = lowerRank + 1. + * Then 2^lowerRank <= count[n]+1 <= 2^rank. + * We attribute each symbol to lowerRank's base value, because we want to know where + * each rank begins in the output, so for rank R we want to count ranks R+1 and above. + */ + ZSTD_memset(rankPosition, 0, sizeof(*rankPosition) * RANK_POSITION_TABLE_SIZE); + for (n = 0; n < maxSymbolValue1; ++n) { + U32 lowerRank = BIT_highbit32(count[n] + 1); + rankPosition[lowerRank].base++; + } + assert(rankPosition[RANK_POSITION_TABLE_SIZE - 1].base == 0); + for (n = RANK_POSITION_TABLE_SIZE - 1; n > 0; --n) { + rankPosition[n-1].base += rankPosition[n].base; + rankPosition[n-1].curr = rankPosition[n-1].base; + } + /* Sort */ + for (n = 0; n < maxSymbolValue1; ++n) { + U32 const c = count[n]; + U32 const r = BIT_highbit32(c+1) + 1; + U32 pos = rankPosition[r].curr++; + /* Insert into the correct position in the rank. + * We have at most 256 symbols, so this insertion should be fine. + */ + while ((pos > rankPosition[r].base) && (c > huffNode[pos-1].count)) { + huffNode[pos] = huffNode[pos-1]; + pos--; + } + huffNode[pos].count = c; + huffNode[pos].byte = (BYTE)n; + } +} + + +/* HUF_buildCTable_wksp() : + * Same as HUF_buildCTable(), but using externally allocated scratch buffer. + * `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as sizeof(HUF_buildCTable_wksp_tables). + */ +#define STARTNODE (HUF_SYMBOLVALUE_MAX+1) + +/* HUF_buildTree(): + * Takes the huffNode array sorted by HUF_sort() and builds an unlimited-depth Huffman tree. + * + * @param huffNode The array sorted by HUF_sort(). Builds the Huffman tree in this array. + * @param maxSymbolValue The maximum symbol value. + * @return The smallest node in the Huffman tree (by count). + */ +static int HUF_buildTree(nodeElt* huffNode, U32 maxSymbolValue) +{ + nodeElt* const huffNode0 = huffNode - 1; + int nonNullRank; + int lowS, lowN; + int nodeNb = STARTNODE; + int n, nodeRoot; + /* init for parents */ + nonNullRank = (int)maxSymbolValue; + while(huffNode[nonNullRank].count == 0) nonNullRank--; + lowS = nonNullRank; nodeRoot = nodeNb + lowS - 1; lowN = nodeNb; + huffNode[nodeNb].count = huffNode[lowS].count + huffNode[lowS-1].count; + huffNode[lowS].parent = huffNode[lowS-1].parent = (U16)nodeNb; + nodeNb++; lowS-=2; + for (n=nodeNb; n<=nodeRoot; n++) huffNode[n].count = (U32)(1U<<30); + huffNode0[0].count = (U32)(1U<<31); /* fake entry, strong barrier */ + + /* create parents */ + while (nodeNb <= nodeRoot) { + int const n1 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++; + int const n2 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++; + huffNode[nodeNb].count = huffNode[n1].count + huffNode[n2].count; + huffNode[n1].parent = huffNode[n2].parent = (U16)nodeNb; + nodeNb++; + } + + /* distribute weights (unlimited tree height) */ + huffNode[nodeRoot].nbBits = 0; + for (n=nodeRoot-1; n>=STARTNODE; n--) + huffNode[n].nbBits = huffNode[ huffNode[n].parent ].nbBits + 1; + for (n=0; n<=nonNullRank; n++) + huffNode[n].nbBits = huffNode[ huffNode[n].parent ].nbBits + 1; + + return nonNullRank; +} + +/* + * HUF_buildCTableFromTree(): + * Build the CTable given the Huffman tree in huffNode. + * + * @param[out] CTable The output Huffman CTable. + * @param huffNode The Huffman tree. + * @param nonNullRank The last and smallest node in the Huffman tree. + * @param maxSymbolValue The maximum symbol value. + * @param maxNbBits The exact maximum number of bits used in the Huffman tree. + */ +static void HUF_buildCTableFromTree(HUF_CElt* CTable, nodeElt const* huffNode, int nonNullRank, U32 maxSymbolValue, U32 maxNbBits) +{ + /* fill result into ctable (val, nbBits) */ + int n; + U16 nbPerRank[HUF_TABLELOG_MAX+1] = {0}; + U16 valPerRank[HUF_TABLELOG_MAX+1] = {0}; + int const alphabetSize = (int)(maxSymbolValue + 1); + for (n=0; n<=nonNullRank; n++) + nbPerRank[huffNode[n].nbBits]++; + /* determine starting value per rank */ + { U16 min = 0; + for (n=(int)maxNbBits; n>0; n--) { + valPerRank[n] = min; /* get starting value within each rank */ + min += nbPerRank[n]; + min >>= 1; + } } + for (n=0; nhuffNodeTbl; + nodeElt* const huffNode = huffNode0+1; + int nonNullRank; + + /* safety checks */ + if (((size_t)workSpace & 3) != 0) return ERROR(GENERIC); /* must be aligned on 4-bytes boundaries */ + if (wkspSize < sizeof(HUF_buildCTable_wksp_tables)) + return ERROR(workSpace_tooSmall); + if (maxNbBits == 0) maxNbBits = HUF_TABLELOG_DEFAULT; + if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) + return ERROR(maxSymbolValue_tooLarge); + ZSTD_memset(huffNode0, 0, sizeof(huffNodeTable)); + + /* sort, decreasing order */ + HUF_sort(huffNode, count, maxSymbolValue, wksp_tables->rankPosition); + + /* build tree */ + nonNullRank = HUF_buildTree(huffNode, maxSymbolValue); + + /* enforce maxTableLog */ + maxNbBits = HUF_setMaxHeight(huffNode, (U32)nonNullRank, maxNbBits); + if (maxNbBits > HUF_TABLELOG_MAX) return ERROR(GENERIC); /* check fit into table */ + + HUF_buildCTableFromTree(tree, huffNode, nonNullRank, maxSymbolValue, maxNbBits); + + return maxNbBits; +} + +size_t HUF_estimateCompressedSize(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue) +{ + size_t nbBits = 0; + int s; + for (s = 0; s <= (int)maxSymbolValue; ++s) { + nbBits += CTable[s].nbBits * count[s]; + } + return nbBits >> 3; +} + +int HUF_validateCTable(const HUF_CElt* CTable, const unsigned* count, unsigned maxSymbolValue) { + int bad = 0; + int s; + for (s = 0; s <= (int)maxSymbolValue; ++s) { + bad |= (count[s] != 0) & (CTable[s].nbBits == 0); + } + return !bad; +} + +size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); } + +FORCE_INLINE_TEMPLATE void +HUF_encodeSymbol(BIT_CStream_t* bitCPtr, U32 symbol, const HUF_CElt* CTable) +{ + BIT_addBitsFast(bitCPtr, CTable[symbol].val, CTable[symbol].nbBits); +} + +#define HUF_FLUSHBITS(s) BIT_flushBits(s) + +#define HUF_FLUSHBITS_1(stream) \ + if (sizeof((stream)->bitContainer)*8 < HUF_TABLELOG_MAX*2+7) HUF_FLUSHBITS(stream) + +#define HUF_FLUSHBITS_2(stream) \ + if (sizeof((stream)->bitContainer)*8 < HUF_TABLELOG_MAX*4+7) HUF_FLUSHBITS(stream) + +FORCE_INLINE_TEMPLATE size_t +HUF_compress1X_usingCTable_internal_body(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable) +{ + const BYTE* ip = (const BYTE*) src; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstSize; + BYTE* op = ostart; + size_t n; + BIT_CStream_t bitC; + + /* init */ + if (dstSize < 8) return 0; /* not enough space to compress */ + { size_t const initErr = BIT_initCStream(&bitC, op, (size_t)(oend-op)); + if (HUF_isError(initErr)) return 0; } + + n = srcSize & ~3; /* join to mod 4 */ + switch (srcSize & 3) + { + case 3: + HUF_encodeSymbol(&bitC, ip[n+ 2], CTable); + HUF_FLUSHBITS_2(&bitC); + ZSTD_FALLTHROUGH; + case 2: + HUF_encodeSymbol(&bitC, ip[n+ 1], CTable); + HUF_FLUSHBITS_1(&bitC); + ZSTD_FALLTHROUGH; + case 1: + HUF_encodeSymbol(&bitC, ip[n+ 0], CTable); + HUF_FLUSHBITS(&bitC); + ZSTD_FALLTHROUGH; + case 0: ZSTD_FALLTHROUGH; + default: break; + } + + for (; n>0; n-=4) { /* note : n&3==0 at this stage */ + HUF_encodeSymbol(&bitC, ip[n- 1], CTable); + HUF_FLUSHBITS_1(&bitC); + HUF_encodeSymbol(&bitC, ip[n- 2], CTable); + HUF_FLUSHBITS_2(&bitC); + HUF_encodeSymbol(&bitC, ip[n- 3], CTable); + HUF_FLUSHBITS_1(&bitC); + HUF_encodeSymbol(&bitC, ip[n- 4], CTable); + HUF_FLUSHBITS(&bitC); + } + + return BIT_closeCStream(&bitC); +} + +#if DYNAMIC_BMI2 + +static TARGET_ATTRIBUTE("bmi2") size_t +HUF_compress1X_usingCTable_internal_bmi2(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable) +{ + return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); +} + +static size_t +HUF_compress1X_usingCTable_internal_default(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable) +{ + return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); +} + +static size_t +HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable, const int bmi2) +{ + if (bmi2) { + return HUF_compress1X_usingCTable_internal_bmi2(dst, dstSize, src, srcSize, CTable); + } + return HUF_compress1X_usingCTable_internal_default(dst, dstSize, src, srcSize, CTable); +} + +#else + +static size_t +HUF_compress1X_usingCTable_internal(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable, const int bmi2) +{ + (void)bmi2; + return HUF_compress1X_usingCTable_internal_body(dst, dstSize, src, srcSize, CTable); +} + +#endif + +size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable) +{ + return HUF_compress1X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0); +} + + +static size_t +HUF_compress4X_usingCTable_internal(void* dst, size_t dstSize, + const void* src, size_t srcSize, + const HUF_CElt* CTable, int bmi2) +{ + size_t const segmentSize = (srcSize+3)/4; /* first 3 segments */ + const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; + BYTE* const ostart = (BYTE*) dst; + BYTE* const oend = ostart + dstSize; + BYTE* op = ostart; + + if (dstSize < 6 + 1 + 1 + 1 + 8) return 0; /* minimum space to compress successfully */ + if (srcSize < 12) return 0; /* no saving possible : too small input */ + op += 6; /* jumpTable */ + + assert(op <= oend); + { CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, segmentSize, CTable, bmi2) ); + if (cSize==0) return 0; + assert(cSize <= 65535); + MEM_writeLE16(ostart, (U16)cSize); + op += cSize; + } + + ip += segmentSize; + assert(op <= oend); + { CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, segmentSize, CTable, bmi2) ); + if (cSize==0) return 0; + assert(cSize <= 65535); + MEM_writeLE16(ostart+2, (U16)cSize); + op += cSize; + } + + ip += segmentSize; + assert(op <= oend); + { CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, segmentSize, CTable, bmi2) ); + if (cSize==0) return 0; + assert(cSize <= 65535); + MEM_writeLE16(ostart+4, (U16)cSize); + op += cSize; + } + + ip += segmentSize; + assert(op <= oend); + assert(ip <= iend); + { CHECK_V_F(cSize, HUF_compress1X_usingCTable_internal(op, (size_t)(oend-op), ip, (size_t)(iend-ip), CTable, bmi2) ); + if (cSize==0) return 0; + op += cSize; + } + + return (size_t)(op-ostart); +} + +size_t HUF_compress4X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable) +{ + return HUF_compress4X_usingCTable_internal(dst, dstSize, src, srcSize, CTable, /* bmi2 */ 0); +} + +typedef enum { HUF_singleStream, HUF_fourStreams } HUF_nbStreams_e; + +static size_t HUF_compressCTable_internal( + BYTE* const ostart, BYTE* op, BYTE* const oend, + const void* src, size_t srcSize, + HUF_nbStreams_e nbStreams, const HUF_CElt* CTable, const int bmi2) +{ + size_t const cSize = (nbStreams==HUF_singleStream) ? + HUF_compress1X_usingCTable_internal(op, (size_t)(oend - op), src, srcSize, CTable, bmi2) : + HUF_compress4X_usingCTable_internal(op, (size_t)(oend - op), src, srcSize, CTable, bmi2); + if (HUF_isError(cSize)) { return cSize; } + if (cSize==0) { return 0; } /* uncompressible */ + op += cSize; + /* check compressibility */ + assert(op >= ostart); + if ((size_t)(op-ostart) >= srcSize-1) { return 0; } + return (size_t)(op-ostart); +} + +typedef struct { + unsigned count[HUF_SYMBOLVALUE_MAX + 1]; + HUF_CElt CTable[HUF_SYMBOLVALUE_MAX + 1]; + union { + HUF_buildCTable_wksp_tables buildCTable_wksp; + HUF_WriteCTableWksp writeCTable_wksp; + } wksps; +} HUF_compress_tables_t; + +/* HUF_compress_internal() : + * `workSpace_align4` must be aligned on 4-bytes boundaries, + * and occupies the same space as a table of HUF_WORKSPACE_SIZE_U32 unsigned */ +static size_t +HUF_compress_internal (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + HUF_nbStreams_e nbStreams, + void* workSpace_align4, size_t wkspSize, + HUF_CElt* oldHufTable, HUF_repeat* repeat, int preferRepeat, + const int bmi2) +{ + HUF_compress_tables_t* const table = (HUF_compress_tables_t*)workSpace_align4; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstSize; + BYTE* op = ostart; + + HUF_STATIC_ASSERT(sizeof(*table) <= HUF_WORKSPACE_SIZE); + assert(((size_t)workSpace_align4 & 3) == 0); /* must be aligned on 4-bytes boundaries */ + + /* checks & inits */ + if (wkspSize < HUF_WORKSPACE_SIZE) return ERROR(workSpace_tooSmall); + if (!srcSize) return 0; /* Uncompressed */ + if (!dstSize) return 0; /* cannot fit anything within dst budget */ + if (srcSize > HUF_BLOCKSIZE_MAX) return ERROR(srcSize_wrong); /* current block size limit */ + if (huffLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); + if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) return ERROR(maxSymbolValue_tooLarge); + if (!maxSymbolValue) maxSymbolValue = HUF_SYMBOLVALUE_MAX; + if (!huffLog) huffLog = HUF_TABLELOG_DEFAULT; + + /* Heuristic : If old table is valid, use it for small inputs */ + if (preferRepeat && repeat && *repeat == HUF_repeat_valid) { + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, + nbStreams, oldHufTable, bmi2); + } + + /* Scan input and build symbol stats */ + { CHECK_V_F(largest, HIST_count_wksp (table->count, &maxSymbolValue, (const BYTE*)src, srcSize, workSpace_align4, wkspSize) ); + if (largest == srcSize) { *ostart = ((const BYTE*)src)[0]; return 1; } /* single symbol, rle */ + if (largest <= (srcSize >> 7)+4) return 0; /* heuristic : probably not compressible enough */ + } + + /* Check validity of previous table */ + if ( repeat + && *repeat == HUF_repeat_check + && !HUF_validateCTable(oldHufTable, table->count, maxSymbolValue)) { + *repeat = HUF_repeat_none; + } + /* Heuristic : use existing table for small inputs */ + if (preferRepeat && repeat && *repeat != HUF_repeat_none) { + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, + nbStreams, oldHufTable, bmi2); + } + + /* Build Huffman Tree */ + huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue); + { size_t const maxBits = HUF_buildCTable_wksp(table->CTable, table->count, + maxSymbolValue, huffLog, + &table->wksps.buildCTable_wksp, sizeof(table->wksps.buildCTable_wksp)); + CHECK_F(maxBits); + huffLog = (U32)maxBits; + /* Zero unused symbols in CTable, so we can check it for validity */ + ZSTD_memset(table->CTable + (maxSymbolValue + 1), 0, + sizeof(table->CTable) - ((maxSymbolValue + 1) * sizeof(HUF_CElt))); + } + + /* Write table description header */ + { CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, table->CTable, maxSymbolValue, huffLog, + &table->wksps.writeCTable_wksp, sizeof(table->wksps.writeCTable_wksp)) ); + /* Check if using previous huffman table is beneficial */ + if (repeat && *repeat != HUF_repeat_none) { + size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, table->count, maxSymbolValue); + size_t const newSize = HUF_estimateCompressedSize(table->CTable, table->count, maxSymbolValue); + if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) { + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, + nbStreams, oldHufTable, bmi2); + } } + + /* Use the new huffman table */ + if (hSize + 12ul >= srcSize) { return 0; } + op += hSize; + if (repeat) { *repeat = HUF_repeat_none; } + if (oldHufTable) + ZSTD_memcpy(oldHufTable, table->CTable, sizeof(table->CTable)); /* Save new table */ + } + return HUF_compressCTable_internal(ostart, op, oend, + src, srcSize, + nbStreams, table->CTable, bmi2); +} + + +size_t HUF_compress1X_wksp (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + void* workSpace, size_t wkspSize) +{ + return HUF_compress_internal(dst, dstSize, src, srcSize, + maxSymbolValue, huffLog, HUF_singleStream, + workSpace, wkspSize, + NULL, NULL, 0, 0 /*bmi2*/); +} + +size_t HUF_compress1X_repeat (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + void* workSpace, size_t wkspSize, + HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2) +{ + return HUF_compress_internal(dst, dstSize, src, srcSize, + maxSymbolValue, huffLog, HUF_singleStream, + workSpace, wkspSize, hufTable, + repeat, preferRepeat, bmi2); +} + +/* HUF_compress4X_repeat(): + * compress input using 4 streams. + * provide workspace to generate compression tables */ +size_t HUF_compress4X_wksp (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + void* workSpace, size_t wkspSize) +{ + return HUF_compress_internal(dst, dstSize, src, srcSize, + maxSymbolValue, huffLog, HUF_fourStreams, + workSpace, wkspSize, + NULL, NULL, 0, 0 /*bmi2*/); +} + +/* HUF_compress4X_repeat(): + * compress input using 4 streams. + * re-use an existing huffman compression table */ +size_t HUF_compress4X_repeat (void* dst, size_t dstSize, + const void* src, size_t srcSize, + unsigned maxSymbolValue, unsigned huffLog, + void* workSpace, size_t wkspSize, + HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2) +{ + return HUF_compress_internal(dst, dstSize, src, srcSize, + maxSymbolValue, huffLog, HUF_fourStreams, + workSpace, wkspSize, + hufTable, repeat, preferRepeat, bmi2); +} + diff --git a/lib/zstd/compress/zstd_compress.c b/lib/zstd/compress/zstd_compress.c new file mode 100644 index 000000000000..a4e916008b3a --- /dev/null +++ b/lib/zstd/compress/zstd_compress.c @@ -0,0 +1,5109 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/*-************************************* +* Dependencies +***************************************/ +#include "../common/zstd_deps.h" /* INT_MAX, ZSTD_memset, ZSTD_memcpy */ +#include "../common/cpu.h" +#include "../common/mem.h" +#include "hist.h" /* HIST_countFast_wksp */ +#define FSE_STATIC_LINKING_ONLY /* FSE_encodeSymbol */ +#include "../common/fse.h" +#define HUF_STATIC_LINKING_ONLY +#include "../common/huf.h" +#include "zstd_compress_internal.h" +#include "zstd_compress_sequences.h" +#include "zstd_compress_literals.h" +#include "zstd_fast.h" +#include "zstd_double_fast.h" +#include "zstd_lazy.h" +#include "zstd_opt.h" +#include "zstd_ldm.h" +#include "zstd_compress_superblock.h" + +/* *************************************************************** +* Tuning parameters +*****************************************************************/ +/*! + * COMPRESS_HEAPMODE : + * Select how default decompression function ZSTD_compress() allocates its context, + * on stack (0, default), or into heap (1). + * Note that functions with explicit context such as ZSTD_compressCCtx() are unaffected. + */ + + +/*-************************************* +* Helper functions +***************************************/ +/* ZSTD_compressBound() + * Note that the result from this function is only compatible with the "normal" + * full-block strategy. + * When there are a lot of small blocks due to frequent flush in streaming mode + * the overhead of headers can make the compressed data to be larger than the + * return value of ZSTD_compressBound(). + */ +size_t ZSTD_compressBound(size_t srcSize) { + return ZSTD_COMPRESSBOUND(srcSize); +} + + +/*-************************************* +* Context memory management +***************************************/ +struct ZSTD_CDict_s { + const void* dictContent; + size_t dictContentSize; + ZSTD_dictContentType_e dictContentType; /* The dictContentType the CDict was created with */ + U32* entropyWorkspace; /* entropy workspace of HUF_WORKSPACE_SIZE bytes */ + ZSTD_cwksp workspace; + ZSTD_matchState_t matchState; + ZSTD_compressedBlockState_t cBlockState; + ZSTD_customMem customMem; + U32 dictID; + int compressionLevel; /* 0 indicates that advanced API was used to select CDict params */ +}; /* typedef'd to ZSTD_CDict within "zstd.h" */ + +ZSTD_CCtx* ZSTD_createCCtx(void) +{ + return ZSTD_createCCtx_advanced(ZSTD_defaultCMem); +} + +static void ZSTD_initCCtx(ZSTD_CCtx* cctx, ZSTD_customMem memManager) +{ + assert(cctx != NULL); + ZSTD_memset(cctx, 0, sizeof(*cctx)); + cctx->customMem = memManager; + cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid()); + { size_t const err = ZSTD_CCtx_reset(cctx, ZSTD_reset_parameters); + assert(!ZSTD_isError(err)); + (void)err; + } +} + +ZSTD_CCtx* ZSTD_createCCtx_advanced(ZSTD_customMem customMem) +{ + ZSTD_STATIC_ASSERT(zcss_init==0); + ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN==(0ULL - 1)); + if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; + { ZSTD_CCtx* const cctx = (ZSTD_CCtx*)ZSTD_customMalloc(sizeof(ZSTD_CCtx), customMem); + if (!cctx) return NULL; + ZSTD_initCCtx(cctx, customMem); + return cctx; + } +} + +ZSTD_CCtx* ZSTD_initStaticCCtx(void* workspace, size_t workspaceSize) +{ + ZSTD_cwksp ws; + ZSTD_CCtx* cctx; + if (workspaceSize <= sizeof(ZSTD_CCtx)) return NULL; /* minimum size */ + if ((size_t)workspace & 7) return NULL; /* must be 8-aligned */ + ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_static_alloc); + + cctx = (ZSTD_CCtx*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CCtx)); + if (cctx == NULL) return NULL; + + ZSTD_memset(cctx, 0, sizeof(ZSTD_CCtx)); + ZSTD_cwksp_move(&cctx->workspace, &ws); + cctx->staticSize = workspaceSize; + + /* statically sized space. entropyWorkspace never moves (but prev/next block swap places) */ + if (!ZSTD_cwksp_check_available(&cctx->workspace, ENTROPY_WORKSPACE_SIZE + 2 * sizeof(ZSTD_compressedBlockState_t))) return NULL; + cctx->blockState.prevCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t)); + cctx->blockState.nextCBlock = (ZSTD_compressedBlockState_t*)ZSTD_cwksp_reserve_object(&cctx->workspace, sizeof(ZSTD_compressedBlockState_t)); + cctx->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cctx->workspace, ENTROPY_WORKSPACE_SIZE); + cctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid()); + return cctx; +} + +/* + * Clears and frees all of the dictionaries in the CCtx. + */ +static void ZSTD_clearAllDicts(ZSTD_CCtx* cctx) +{ + ZSTD_customFree(cctx->localDict.dictBuffer, cctx->customMem); + ZSTD_freeCDict(cctx->localDict.cdict); + ZSTD_memset(&cctx->localDict, 0, sizeof(cctx->localDict)); + ZSTD_memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict)); + cctx->cdict = NULL; +} + +static size_t ZSTD_sizeof_localDict(ZSTD_localDict dict) +{ + size_t const bufferSize = dict.dictBuffer != NULL ? dict.dictSize : 0; + size_t const cdictSize = ZSTD_sizeof_CDict(dict.cdict); + return bufferSize + cdictSize; +} + +static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx) +{ + assert(cctx != NULL); + assert(cctx->staticSize == 0); + ZSTD_clearAllDicts(cctx); + ZSTD_cwksp_free(&cctx->workspace, cctx->customMem); +} + +size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx) +{ + if (cctx==NULL) return 0; /* support free on NULL */ + RETURN_ERROR_IF(cctx->staticSize, memory_allocation, + "not compatible with static CCtx"); + { + int cctxInWorkspace = ZSTD_cwksp_owns_buffer(&cctx->workspace, cctx); + ZSTD_freeCCtxContent(cctx); + if (!cctxInWorkspace) { + ZSTD_customFree(cctx, cctx->customMem); + } + } + return 0; +} + + +static size_t ZSTD_sizeof_mtctx(const ZSTD_CCtx* cctx) +{ + (void)cctx; + return 0; +} + + +size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx) +{ + if (cctx==NULL) return 0; /* support sizeof on NULL */ + /* cctx may be in the workspace */ + return (cctx->workspace.workspace == cctx ? 0 : sizeof(*cctx)) + + ZSTD_cwksp_sizeof(&cctx->workspace) + + ZSTD_sizeof_localDict(cctx->localDict) + + ZSTD_sizeof_mtctx(cctx); +} + +size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs) +{ + return ZSTD_sizeof_CCtx(zcs); /* same object */ +} + +/* private API call, for dictBuilder only */ +const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) { return &(ctx->seqStore); } + +/* Returns 1 if compression parameters are such that we should + * enable long distance matching (wlog >= 27, strategy >= btopt). + * Returns 0 otherwise. + */ +static U32 ZSTD_CParams_shouldEnableLdm(const ZSTD_compressionParameters* const cParams) { + return cParams->strategy >= ZSTD_btopt && cParams->windowLog >= 27; +} + +static ZSTD_CCtx_params ZSTD_makeCCtxParamsFromCParams( + ZSTD_compressionParameters cParams) +{ + ZSTD_CCtx_params cctxParams; + /* should not matter, as all cParams are presumed properly defined */ + ZSTD_CCtxParams_init(&cctxParams, ZSTD_CLEVEL_DEFAULT); + cctxParams.cParams = cParams; + + if (ZSTD_CParams_shouldEnableLdm(&cParams)) { + DEBUGLOG(4, "ZSTD_makeCCtxParamsFromCParams(): Including LDM into cctx params"); + cctxParams.ldmParams.enableLdm = 1; + /* LDM is enabled by default for optimal parser and window size >= 128MB */ + ZSTD_ldm_adjustParameters(&cctxParams.ldmParams, &cParams); + assert(cctxParams.ldmParams.hashLog >= cctxParams.ldmParams.bucketSizeLog); + assert(cctxParams.ldmParams.hashRateLog < 32); + } + + assert(!ZSTD_checkCParams(cParams)); + return cctxParams; +} + +static ZSTD_CCtx_params* ZSTD_createCCtxParams_advanced( + ZSTD_customMem customMem) +{ + ZSTD_CCtx_params* params; + if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; + params = (ZSTD_CCtx_params*)ZSTD_customCalloc( + sizeof(ZSTD_CCtx_params), customMem); + if (!params) { return NULL; } + ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); + params->customMem = customMem; + return params; +} + +ZSTD_CCtx_params* ZSTD_createCCtxParams(void) +{ + return ZSTD_createCCtxParams_advanced(ZSTD_defaultCMem); +} + +size_t ZSTD_freeCCtxParams(ZSTD_CCtx_params* params) +{ + if (params == NULL) { return 0; } + ZSTD_customFree(params, params->customMem); + return 0; +} + +size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params) +{ + return ZSTD_CCtxParams_init(params, ZSTD_CLEVEL_DEFAULT); +} + +size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) { + RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!"); + ZSTD_memset(cctxParams, 0, sizeof(*cctxParams)); + cctxParams->compressionLevel = compressionLevel; + cctxParams->fParams.contentSizeFlag = 1; + return 0; +} + +#define ZSTD_NO_CLEVEL 0 + +/* + * Initializes the cctxParams from params and compressionLevel. + * @param compressionLevel If params are derived from a compression level then that compression level, otherwise ZSTD_NO_CLEVEL. + */ +static void ZSTD_CCtxParams_init_internal(ZSTD_CCtx_params* cctxParams, ZSTD_parameters const* params, int compressionLevel) +{ + assert(!ZSTD_checkCParams(params->cParams)); + ZSTD_memset(cctxParams, 0, sizeof(*cctxParams)); + cctxParams->cParams = params->cParams; + cctxParams->fParams = params->fParams; + /* Should not matter, as all cParams are presumed properly defined. + * But, set it for tracing anyway. + */ + cctxParams->compressionLevel = compressionLevel; +} + +size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params) +{ + RETURN_ERROR_IF(!cctxParams, GENERIC, "NULL pointer!"); + FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) , ""); + ZSTD_CCtxParams_init_internal(cctxParams, ¶ms, ZSTD_NO_CLEVEL); + return 0; +} + +/* + * Sets cctxParams' cParams and fParams from params, but otherwise leaves them alone. + * @param param Validated zstd parameters. + */ +static void ZSTD_CCtxParams_setZstdParams( + ZSTD_CCtx_params* cctxParams, const ZSTD_parameters* params) +{ + assert(!ZSTD_checkCParams(params->cParams)); + cctxParams->cParams = params->cParams; + cctxParams->fParams = params->fParams; + /* Should not matter, as all cParams are presumed properly defined. + * But, set it for tracing anyway. + */ + cctxParams->compressionLevel = ZSTD_NO_CLEVEL; +} + +ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param) +{ + ZSTD_bounds bounds = { 0, 0, 0 }; + + switch(param) + { + case ZSTD_c_compressionLevel: + bounds.lowerBound = ZSTD_minCLevel(); + bounds.upperBound = ZSTD_maxCLevel(); + return bounds; + + case ZSTD_c_windowLog: + bounds.lowerBound = ZSTD_WINDOWLOG_MIN; + bounds.upperBound = ZSTD_WINDOWLOG_MAX; + return bounds; + + case ZSTD_c_hashLog: + bounds.lowerBound = ZSTD_HASHLOG_MIN; + bounds.upperBound = ZSTD_HASHLOG_MAX; + return bounds; + + case ZSTD_c_chainLog: + bounds.lowerBound = ZSTD_CHAINLOG_MIN; + bounds.upperBound = ZSTD_CHAINLOG_MAX; + return bounds; + + case ZSTD_c_searchLog: + bounds.lowerBound = ZSTD_SEARCHLOG_MIN; + bounds.upperBound = ZSTD_SEARCHLOG_MAX; + return bounds; + + case ZSTD_c_minMatch: + bounds.lowerBound = ZSTD_MINMATCH_MIN; + bounds.upperBound = ZSTD_MINMATCH_MAX; + return bounds; + + case ZSTD_c_targetLength: + bounds.lowerBound = ZSTD_TARGETLENGTH_MIN; + bounds.upperBound = ZSTD_TARGETLENGTH_MAX; + return bounds; + + case ZSTD_c_strategy: + bounds.lowerBound = ZSTD_STRATEGY_MIN; + bounds.upperBound = ZSTD_STRATEGY_MAX; + return bounds; + + case ZSTD_c_contentSizeFlag: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_checksumFlag: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_dictIDFlag: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_nbWorkers: + bounds.lowerBound = 0; + bounds.upperBound = 0; + return bounds; + + case ZSTD_c_jobSize: + bounds.lowerBound = 0; + bounds.upperBound = 0; + return bounds; + + case ZSTD_c_overlapLog: + bounds.lowerBound = 0; + bounds.upperBound = 0; + return bounds; + + case ZSTD_c_enableDedicatedDictSearch: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_enableLongDistanceMatching: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_ldmHashLog: + bounds.lowerBound = ZSTD_LDM_HASHLOG_MIN; + bounds.upperBound = ZSTD_LDM_HASHLOG_MAX; + return bounds; + + case ZSTD_c_ldmMinMatch: + bounds.lowerBound = ZSTD_LDM_MINMATCH_MIN; + bounds.upperBound = ZSTD_LDM_MINMATCH_MAX; + return bounds; + + case ZSTD_c_ldmBucketSizeLog: + bounds.lowerBound = ZSTD_LDM_BUCKETSIZELOG_MIN; + bounds.upperBound = ZSTD_LDM_BUCKETSIZELOG_MAX; + return bounds; + + case ZSTD_c_ldmHashRateLog: + bounds.lowerBound = ZSTD_LDM_HASHRATELOG_MIN; + bounds.upperBound = ZSTD_LDM_HASHRATELOG_MAX; + return bounds; + + /* experimental parameters */ + case ZSTD_c_rsyncable: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_forceMaxWindow : + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + case ZSTD_c_format: + ZSTD_STATIC_ASSERT(ZSTD_f_zstd1 < ZSTD_f_zstd1_magicless); + bounds.lowerBound = ZSTD_f_zstd1; + bounds.upperBound = ZSTD_f_zstd1_magicless; /* note : how to ensure at compile time that this is the highest value enum ? */ + return bounds; + + case ZSTD_c_forceAttachDict: + ZSTD_STATIC_ASSERT(ZSTD_dictDefaultAttach < ZSTD_dictForceLoad); + bounds.lowerBound = ZSTD_dictDefaultAttach; + bounds.upperBound = ZSTD_dictForceLoad; /* note : how to ensure at compile time that this is the highest value enum ? */ + return bounds; + + case ZSTD_c_literalCompressionMode: + ZSTD_STATIC_ASSERT(ZSTD_lcm_auto < ZSTD_lcm_huffman && ZSTD_lcm_huffman < ZSTD_lcm_uncompressed); + bounds.lowerBound = ZSTD_lcm_auto; + bounds.upperBound = ZSTD_lcm_uncompressed; + return bounds; + + case ZSTD_c_targetCBlockSize: + bounds.lowerBound = ZSTD_TARGETCBLOCKSIZE_MIN; + bounds.upperBound = ZSTD_TARGETCBLOCKSIZE_MAX; + return bounds; + + case ZSTD_c_srcSizeHint: + bounds.lowerBound = ZSTD_SRCSIZEHINT_MIN; + bounds.upperBound = ZSTD_SRCSIZEHINT_MAX; + return bounds; + + case ZSTD_c_stableInBuffer: + case ZSTD_c_stableOutBuffer: + bounds.lowerBound = (int)ZSTD_bm_buffered; + bounds.upperBound = (int)ZSTD_bm_stable; + return bounds; + + case ZSTD_c_blockDelimiters: + bounds.lowerBound = (int)ZSTD_sf_noBlockDelimiters; + bounds.upperBound = (int)ZSTD_sf_explicitBlockDelimiters; + return bounds; + + case ZSTD_c_validateSequences: + bounds.lowerBound = 0; + bounds.upperBound = 1; + return bounds; + + default: + bounds.error = ERROR(parameter_unsupported); + return bounds; + } +} + +/* ZSTD_cParam_clampBounds: + * Clamps the value into the bounded range. + */ +static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value) +{ + ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); + if (ZSTD_isError(bounds.error)) return bounds.error; + if (*value < bounds.lowerBound) *value = bounds.lowerBound; + if (*value > bounds.upperBound) *value = bounds.upperBound; + return 0; +} + +#define BOUNDCHECK(cParam, val) { \ + RETURN_ERROR_IF(!ZSTD_cParam_withinBounds(cParam,val), \ + parameter_outOfBound, "Param out of bounds"); \ +} + + +static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param) +{ + switch(param) + { + case ZSTD_c_compressionLevel: + case ZSTD_c_hashLog: + case ZSTD_c_chainLog: + case ZSTD_c_searchLog: + case ZSTD_c_minMatch: + case ZSTD_c_targetLength: + case ZSTD_c_strategy: + return 1; + + case ZSTD_c_format: + case ZSTD_c_windowLog: + case ZSTD_c_contentSizeFlag: + case ZSTD_c_checksumFlag: + case ZSTD_c_dictIDFlag: + case ZSTD_c_forceMaxWindow : + case ZSTD_c_nbWorkers: + case ZSTD_c_jobSize: + case ZSTD_c_overlapLog: + case ZSTD_c_rsyncable: + case ZSTD_c_enableDedicatedDictSearch: + case ZSTD_c_enableLongDistanceMatching: + case ZSTD_c_ldmHashLog: + case ZSTD_c_ldmMinMatch: + case ZSTD_c_ldmBucketSizeLog: + case ZSTD_c_ldmHashRateLog: + case ZSTD_c_forceAttachDict: + case ZSTD_c_literalCompressionMode: + case ZSTD_c_targetCBlockSize: + case ZSTD_c_srcSizeHint: + case ZSTD_c_stableInBuffer: + case ZSTD_c_stableOutBuffer: + case ZSTD_c_blockDelimiters: + case ZSTD_c_validateSequences: + default: + return 0; + } +} + +size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value) +{ + DEBUGLOG(4, "ZSTD_CCtx_setParameter (%i, %i)", (int)param, value); + if (cctx->streamStage != zcss_init) { + if (ZSTD_isUpdateAuthorized(param)) { + cctx->cParamsChanged = 1; + } else { + RETURN_ERROR(stage_wrong, "can only set params in ctx init stage"); + } } + + switch(param) + { + case ZSTD_c_nbWorkers: + RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported, + "MT not compatible with static alloc"); + break; + + case ZSTD_c_compressionLevel: + case ZSTD_c_windowLog: + case ZSTD_c_hashLog: + case ZSTD_c_chainLog: + case ZSTD_c_searchLog: + case ZSTD_c_minMatch: + case ZSTD_c_targetLength: + case ZSTD_c_strategy: + case ZSTD_c_ldmHashRateLog: + case ZSTD_c_format: + case ZSTD_c_contentSizeFlag: + case ZSTD_c_checksumFlag: + case ZSTD_c_dictIDFlag: + case ZSTD_c_forceMaxWindow: + case ZSTD_c_forceAttachDict: + case ZSTD_c_literalCompressionMode: + case ZSTD_c_jobSize: + case ZSTD_c_overlapLog: + case ZSTD_c_rsyncable: + case ZSTD_c_enableDedicatedDictSearch: + case ZSTD_c_enableLongDistanceMatching: + case ZSTD_c_ldmHashLog: + case ZSTD_c_ldmMinMatch: + case ZSTD_c_ldmBucketSizeLog: + case ZSTD_c_targetCBlockSize: + case ZSTD_c_srcSizeHint: + case ZSTD_c_stableInBuffer: + case ZSTD_c_stableOutBuffer: + case ZSTD_c_blockDelimiters: + case ZSTD_c_validateSequences: + break; + + default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); + } + return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value); +} + +size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams, + ZSTD_cParameter param, int value) +{ + DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value); + switch(param) + { + case ZSTD_c_format : + BOUNDCHECK(ZSTD_c_format, value); + CCtxParams->format = (ZSTD_format_e)value; + return (size_t)CCtxParams->format; + + case ZSTD_c_compressionLevel : { + FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value), ""); + if (value == 0) + CCtxParams->compressionLevel = ZSTD_CLEVEL_DEFAULT; /* 0 == default */ + else + CCtxParams->compressionLevel = value; + if (CCtxParams->compressionLevel >= 0) return (size_t)CCtxParams->compressionLevel; + return 0; /* return type (size_t) cannot represent negative values */ + } + + case ZSTD_c_windowLog : + if (value!=0) /* 0 => use default */ + BOUNDCHECK(ZSTD_c_windowLog, value); + CCtxParams->cParams.windowLog = (U32)value; + return CCtxParams->cParams.windowLog; + + case ZSTD_c_hashLog : + if (value!=0) /* 0 => use default */ + BOUNDCHECK(ZSTD_c_hashLog, value); + CCtxParams->cParams.hashLog = (U32)value; + return CCtxParams->cParams.hashLog; + + case ZSTD_c_chainLog : + if (value!=0) /* 0 => use default */ + BOUNDCHECK(ZSTD_c_chainLog, value); + CCtxParams->cParams.chainLog = (U32)value; + return CCtxParams->cParams.chainLog; + + case ZSTD_c_searchLog : + if (value!=0) /* 0 => use default */ + BOUNDCHECK(ZSTD_c_searchLog, value); + CCtxParams->cParams.searchLog = (U32)value; + return (size_t)value; + + case ZSTD_c_minMatch : + if (value!=0) /* 0 => use default */ + BOUNDCHECK(ZSTD_c_minMatch, value); + CCtxParams->cParams.minMatch = value; + return CCtxParams->cParams.minMatch; + + case ZSTD_c_targetLength : + BOUNDCHECK(ZSTD_c_targetLength, value); + CCtxParams->cParams.targetLength = value; + return CCtxParams->cParams.targetLength; + + case ZSTD_c_strategy : + if (value!=0) /* 0 => use default */ + BOUNDCHECK(ZSTD_c_strategy, value); + CCtxParams->cParams.strategy = (ZSTD_strategy)value; + return (size_t)CCtxParams->cParams.strategy; + + case ZSTD_c_contentSizeFlag : + /* Content size written in frame header _when known_ (default:1) */ + DEBUGLOG(4, "set content size flag = %u", (value!=0)); + CCtxParams->fParams.contentSizeFlag = value != 0; + return CCtxParams->fParams.contentSizeFlag; + + case ZSTD_c_checksumFlag : + /* A 32-bits content checksum will be calculated and written at end of frame (default:0) */ + CCtxParams->fParams.checksumFlag = value != 0; + return CCtxParams->fParams.checksumFlag; + + case ZSTD_c_dictIDFlag : /* When applicable, dictionary's dictID is provided in frame header (default:1) */ + DEBUGLOG(4, "set dictIDFlag = %u", (value!=0)); + CCtxParams->fParams.noDictIDFlag = !value; + return !CCtxParams->fParams.noDictIDFlag; + + case ZSTD_c_forceMaxWindow : + CCtxParams->forceWindow = (value != 0); + return CCtxParams->forceWindow; + + case ZSTD_c_forceAttachDict : { + const ZSTD_dictAttachPref_e pref = (ZSTD_dictAttachPref_e)value; + BOUNDCHECK(ZSTD_c_forceAttachDict, pref); + CCtxParams->attachDictPref = pref; + return CCtxParams->attachDictPref; + } + + case ZSTD_c_literalCompressionMode : { + const ZSTD_literalCompressionMode_e lcm = (ZSTD_literalCompressionMode_e)value; + BOUNDCHECK(ZSTD_c_literalCompressionMode, lcm); + CCtxParams->literalCompressionMode = lcm; + return CCtxParams->literalCompressionMode; + } + + case ZSTD_c_nbWorkers : + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; + + case ZSTD_c_jobSize : + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; + + case ZSTD_c_overlapLog : + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; + + case ZSTD_c_rsyncable : + RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading"); + return 0; + + case ZSTD_c_enableDedicatedDictSearch : + CCtxParams->enableDedicatedDictSearch = (value!=0); + return CCtxParams->enableDedicatedDictSearch; + + case ZSTD_c_enableLongDistanceMatching : + CCtxParams->ldmParams.enableLdm = (value!=0); + return CCtxParams->ldmParams.enableLdm; + + case ZSTD_c_ldmHashLog : + if (value!=0) /* 0 ==> auto */ + BOUNDCHECK(ZSTD_c_ldmHashLog, value); + CCtxParams->ldmParams.hashLog = value; + return CCtxParams->ldmParams.hashLog; + + case ZSTD_c_ldmMinMatch : + if (value!=0) /* 0 ==> default */ + BOUNDCHECK(ZSTD_c_ldmMinMatch, value); + CCtxParams->ldmParams.minMatchLength = value; + return CCtxParams->ldmParams.minMatchLength; + + case ZSTD_c_ldmBucketSizeLog : + if (value!=0) /* 0 ==> default */ + BOUNDCHECK(ZSTD_c_ldmBucketSizeLog, value); + CCtxParams->ldmParams.bucketSizeLog = value; + return CCtxParams->ldmParams.bucketSizeLog; + + case ZSTD_c_ldmHashRateLog : + if (value!=0) /* 0 ==> default */ + BOUNDCHECK(ZSTD_c_ldmHashRateLog, value); + CCtxParams->ldmParams.hashRateLog = value; + return CCtxParams->ldmParams.hashRateLog; + + case ZSTD_c_targetCBlockSize : + if (value!=0) /* 0 ==> default */ + BOUNDCHECK(ZSTD_c_targetCBlockSize, value); + CCtxParams->targetCBlockSize = value; + return CCtxParams->targetCBlockSize; + + case ZSTD_c_srcSizeHint : + if (value!=0) /* 0 ==> default */ + BOUNDCHECK(ZSTD_c_srcSizeHint, value); + CCtxParams->srcSizeHint = value; + return CCtxParams->srcSizeHint; + + case ZSTD_c_stableInBuffer: + BOUNDCHECK(ZSTD_c_stableInBuffer, value); + CCtxParams->inBufferMode = (ZSTD_bufferMode_e)value; + return CCtxParams->inBufferMode; + + case ZSTD_c_stableOutBuffer: + BOUNDCHECK(ZSTD_c_stableOutBuffer, value); + CCtxParams->outBufferMode = (ZSTD_bufferMode_e)value; + return CCtxParams->outBufferMode; + + case ZSTD_c_blockDelimiters: + BOUNDCHECK(ZSTD_c_blockDelimiters, value); + CCtxParams->blockDelimiters = (ZSTD_sequenceFormat_e)value; + return CCtxParams->blockDelimiters; + + case ZSTD_c_validateSequences: + BOUNDCHECK(ZSTD_c_validateSequences, value); + CCtxParams->validateSequences = value; + return CCtxParams->validateSequences; + + default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); + } +} + +size_t ZSTD_CCtx_getParameter(ZSTD_CCtx const* cctx, ZSTD_cParameter param, int* value) +{ + return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value); +} + +size_t ZSTD_CCtxParams_getParameter( + ZSTD_CCtx_params const* CCtxParams, ZSTD_cParameter param, int* value) +{ + switch(param) + { + case ZSTD_c_format : + *value = CCtxParams->format; + break; + case ZSTD_c_compressionLevel : + *value = CCtxParams->compressionLevel; + break; + case ZSTD_c_windowLog : + *value = (int)CCtxParams->cParams.windowLog; + break; + case ZSTD_c_hashLog : + *value = (int)CCtxParams->cParams.hashLog; + break; + case ZSTD_c_chainLog : + *value = (int)CCtxParams->cParams.chainLog; + break; + case ZSTD_c_searchLog : + *value = CCtxParams->cParams.searchLog; + break; + case ZSTD_c_minMatch : + *value = CCtxParams->cParams.minMatch; + break; + case ZSTD_c_targetLength : + *value = CCtxParams->cParams.targetLength; + break; + case ZSTD_c_strategy : + *value = (unsigned)CCtxParams->cParams.strategy; + break; + case ZSTD_c_contentSizeFlag : + *value = CCtxParams->fParams.contentSizeFlag; + break; + case ZSTD_c_checksumFlag : + *value = CCtxParams->fParams.checksumFlag; + break; + case ZSTD_c_dictIDFlag : + *value = !CCtxParams->fParams.noDictIDFlag; + break; + case ZSTD_c_forceMaxWindow : + *value = CCtxParams->forceWindow; + break; + case ZSTD_c_forceAttachDict : + *value = CCtxParams->attachDictPref; + break; + case ZSTD_c_literalCompressionMode : + *value = CCtxParams->literalCompressionMode; + break; + case ZSTD_c_nbWorkers : + assert(CCtxParams->nbWorkers == 0); + *value = CCtxParams->nbWorkers; + break; + case ZSTD_c_jobSize : + RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); + case ZSTD_c_overlapLog : + RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); + case ZSTD_c_rsyncable : + RETURN_ERROR(parameter_unsupported, "not compiled with multithreading"); + case ZSTD_c_enableDedicatedDictSearch : + *value = CCtxParams->enableDedicatedDictSearch; + break; + case ZSTD_c_enableLongDistanceMatching : + *value = CCtxParams->ldmParams.enableLdm; + break; + case ZSTD_c_ldmHashLog : + *value = CCtxParams->ldmParams.hashLog; + break; + case ZSTD_c_ldmMinMatch : + *value = CCtxParams->ldmParams.minMatchLength; + break; + case ZSTD_c_ldmBucketSizeLog : + *value = CCtxParams->ldmParams.bucketSizeLog; + break; + case ZSTD_c_ldmHashRateLog : + *value = CCtxParams->ldmParams.hashRateLog; + break; + case ZSTD_c_targetCBlockSize : + *value = (int)CCtxParams->targetCBlockSize; + break; + case ZSTD_c_srcSizeHint : + *value = (int)CCtxParams->srcSizeHint; + break; + case ZSTD_c_stableInBuffer : + *value = (int)CCtxParams->inBufferMode; + break; + case ZSTD_c_stableOutBuffer : + *value = (int)CCtxParams->outBufferMode; + break; + case ZSTD_c_blockDelimiters : + *value = (int)CCtxParams->blockDelimiters; + break; + case ZSTD_c_validateSequences : + *value = (int)CCtxParams->validateSequences; + break; + default: RETURN_ERROR(parameter_unsupported, "unknown parameter"); + } + return 0; +} + +/* ZSTD_CCtx_setParametersUsingCCtxParams() : + * just applies `params` into `cctx` + * no action is performed, parameters are merely stored. + * If ZSTDMT is enabled, parameters are pushed to cctx->mtctx. + * This is possible even if a compression is ongoing. + * In which case, new parameters will be applied on the fly, starting with next compression job. + */ +size_t ZSTD_CCtx_setParametersUsingCCtxParams( + ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params) +{ + DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams"); + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "The context is in the wrong stage!"); + RETURN_ERROR_IF(cctx->cdict, stage_wrong, + "Can't override parameters with cdict attached (some must " + "be inherited from the cdict)."); + + cctx->requestedParams = *params; + return 0; +} + +ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize) +{ + DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize); + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "Can't set pledgedSrcSize when not in init stage."); + cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1; + return 0; +} + +static ZSTD_compressionParameters ZSTD_dedicatedDictSearch_getCParams( + int const compressionLevel, + size_t const dictSize); +static int ZSTD_dedicatedDictSearch_isSupported( + const ZSTD_compressionParameters* cParams); +static void ZSTD_dedicatedDictSearch_revertCParams( + ZSTD_compressionParameters* cParams); + +/* + * Initializes the local dict using the requested parameters. + * NOTE: This does not use the pledged src size, because it may be used for more + * than one compression. + */ +static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx) +{ + ZSTD_localDict* const dl = &cctx->localDict; + if (dl->dict == NULL) { + /* No local dictionary. */ + assert(dl->dictBuffer == NULL); + assert(dl->cdict == NULL); + assert(dl->dictSize == 0); + return 0; + } + if (dl->cdict != NULL) { + assert(cctx->cdict == dl->cdict); + /* Local dictionary already initialized. */ + return 0; + } + assert(dl->dictSize > 0); + assert(cctx->cdict == NULL); + assert(cctx->prefixDict.dict == NULL); + + dl->cdict = ZSTD_createCDict_advanced2( + dl->dict, + dl->dictSize, + ZSTD_dlm_byRef, + dl->dictContentType, + &cctx->requestedParams, + cctx->customMem); + RETURN_ERROR_IF(!dl->cdict, memory_allocation, "ZSTD_createCDict_advanced failed"); + cctx->cdict = dl->cdict; + return 0; +} + +size_t ZSTD_CCtx_loadDictionary_advanced( + ZSTD_CCtx* cctx, const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType) +{ + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "Can't load a dictionary when ctx is not in init stage."); + DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize); + ZSTD_clearAllDicts(cctx); /* in case one already exists */ + if (dict == NULL || dictSize == 0) /* no dictionary mode */ + return 0; + if (dictLoadMethod == ZSTD_dlm_byRef) { + cctx->localDict.dict = dict; + } else { + void* dictBuffer; + RETURN_ERROR_IF(cctx->staticSize, memory_allocation, + "no malloc for static CCtx"); + dictBuffer = ZSTD_customMalloc(dictSize, cctx->customMem); + RETURN_ERROR_IF(!dictBuffer, memory_allocation, "NULL pointer!"); + ZSTD_memcpy(dictBuffer, dict, dictSize); + cctx->localDict.dictBuffer = dictBuffer; + cctx->localDict.dict = dictBuffer; + } + cctx->localDict.dictSize = dictSize; + cctx->localDict.dictContentType = dictContentType; + return 0; +} + +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary_byReference( + ZSTD_CCtx* cctx, const void* dict, size_t dictSize) +{ + return ZSTD_CCtx_loadDictionary_advanced( + cctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); +} + +ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize) +{ + return ZSTD_CCtx_loadDictionary_advanced( + cctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); +} + + +size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) +{ + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "Can't ref a dict when ctx not in init stage."); + /* Free the existing local cdict (if any) to save memory. */ + ZSTD_clearAllDicts(cctx); + cctx->cdict = cdict; + return 0; +} + +size_t ZSTD_CCtx_refThreadPool(ZSTD_CCtx* cctx, ZSTD_threadPool* pool) +{ + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "Can't ref a pool when ctx not in init stage."); + cctx->pool = pool; + return 0; +} + +size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize) +{ + return ZSTD_CCtx_refPrefix_advanced(cctx, prefix, prefixSize, ZSTD_dct_rawContent); +} + +size_t ZSTD_CCtx_refPrefix_advanced( + ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) +{ + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "Can't ref a prefix when ctx not in init stage."); + ZSTD_clearAllDicts(cctx); + if (prefix != NULL && prefixSize > 0) { + cctx->prefixDict.dict = prefix; + cctx->prefixDict.dictSize = prefixSize; + cctx->prefixDict.dictContentType = dictContentType; + } + return 0; +} + +/*! ZSTD_CCtx_reset() : + * Also dumps dictionary */ +size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset) +{ + if ( (reset == ZSTD_reset_session_only) + || (reset == ZSTD_reset_session_and_parameters) ) { + cctx->streamStage = zcss_init; + cctx->pledgedSrcSizePlusOne = 0; + } + if ( (reset == ZSTD_reset_parameters) + || (reset == ZSTD_reset_session_and_parameters) ) { + RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong, + "Can't reset parameters only when not in init stage."); + ZSTD_clearAllDicts(cctx); + return ZSTD_CCtxParams_reset(&cctx->requestedParams); + } + return 0; +} + + +/* ZSTD_checkCParams() : + control CParam values remain within authorized range. + @return : 0, or an error code if one value is beyond authorized range */ +size_t ZSTD_checkCParams(ZSTD_compressionParameters cParams) +{ + BOUNDCHECK(ZSTD_c_windowLog, (int)cParams.windowLog); + BOUNDCHECK(ZSTD_c_chainLog, (int)cParams.chainLog); + BOUNDCHECK(ZSTD_c_hashLog, (int)cParams.hashLog); + BOUNDCHECK(ZSTD_c_searchLog, (int)cParams.searchLog); + BOUNDCHECK(ZSTD_c_minMatch, (int)cParams.minMatch); + BOUNDCHECK(ZSTD_c_targetLength,(int)cParams.targetLength); + BOUNDCHECK(ZSTD_c_strategy, cParams.strategy); + return 0; +} + +/* ZSTD_clampCParams() : + * make CParam values within valid range. + * @return : valid CParams */ +static ZSTD_compressionParameters +ZSTD_clampCParams(ZSTD_compressionParameters cParams) +{ +# define CLAMP_TYPE(cParam, val, type) { \ + ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); \ + if ((int)valbounds.upperBound) val=(type)bounds.upperBound; \ + } +# define CLAMP(cParam, val) CLAMP_TYPE(cParam, val, unsigned) + CLAMP(ZSTD_c_windowLog, cParams.windowLog); + CLAMP(ZSTD_c_chainLog, cParams.chainLog); + CLAMP(ZSTD_c_hashLog, cParams.hashLog); + CLAMP(ZSTD_c_searchLog, cParams.searchLog); + CLAMP(ZSTD_c_minMatch, cParams.minMatch); + CLAMP(ZSTD_c_targetLength,cParams.targetLength); + CLAMP_TYPE(ZSTD_c_strategy,cParams.strategy, ZSTD_strategy); + return cParams; +} + +/* ZSTD_cycleLog() : + * condition for correct operation : hashLog > 1 */ +U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat) +{ + U32 const btScale = ((U32)strat >= (U32)ZSTD_btlazy2); + return hashLog - btScale; +} + +/* ZSTD_dictAndWindowLog() : + * Returns an adjusted window log that is large enough to fit the source and the dictionary. + * The zstd format says that the entire dictionary is valid if one byte of the dictionary + * is within the window. So the hashLog and chainLog should be large enough to reference both + * the dictionary and the window. So we must use this adjusted dictAndWindowLog when downsizing + * the hashLog and windowLog. + * NOTE: srcSize must not be ZSTD_CONTENTSIZE_UNKNOWN. + */ +static U32 ZSTD_dictAndWindowLog(U32 windowLog, U64 srcSize, U64 dictSize) +{ + const U64 maxWindowSize = 1ULL << ZSTD_WINDOWLOG_MAX; + /* No dictionary ==> No change */ + if (dictSize == 0) { + return windowLog; + } + assert(windowLog <= ZSTD_WINDOWLOG_MAX); + assert(srcSize != ZSTD_CONTENTSIZE_UNKNOWN); /* Handled in ZSTD_adjustCParams_internal() */ + { + U64 const windowSize = 1ULL << windowLog; + U64 const dictAndWindowSize = dictSize + windowSize; + /* If the window size is already large enough to fit both the source and the dictionary + * then just use the window size. Otherwise adjust so that it fits the dictionary and + * the window. + */ + if (windowSize >= dictSize + srcSize) { + return windowLog; /* Window size large enough already */ + } else if (dictAndWindowSize >= maxWindowSize) { + return ZSTD_WINDOWLOG_MAX; /* Larger than max window log */ + } else { + return ZSTD_highbit32((U32)dictAndWindowSize - 1) + 1; + } + } +} + +/* ZSTD_adjustCParams_internal() : + * optimize `cPar` for a specified input (`srcSize` and `dictSize`). + * mostly downsize to reduce memory consumption and initialization latency. + * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known. + * `mode` is the mode for parameter adjustment. See docs for `ZSTD_cParamMode_e`. + * note : `srcSize==0` means 0! + * condition : cPar is presumed validated (can be checked using ZSTD_checkCParams()). */ +static ZSTD_compressionParameters +ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar, + unsigned long long srcSize, + size_t dictSize, + ZSTD_cParamMode_e mode) +{ + const U64 minSrcSize = 513; /* (1<<9) + 1 */ + const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1); + assert(ZSTD_checkCParams(cPar)==0); + + switch (mode) { + case ZSTD_cpm_unknown: + case ZSTD_cpm_noAttachDict: + /* If we don't know the source size, don't make any + * assumptions about it. We will already have selected + * smaller parameters if a dictionary is in use. + */ + break; + case ZSTD_cpm_createCDict: + /* Assume a small source size when creating a dictionary + * with an unkown source size. + */ + if (dictSize && srcSize == ZSTD_CONTENTSIZE_UNKNOWN) + srcSize = minSrcSize; + break; + case ZSTD_cpm_attachDict: + /* Dictionary has its own dedicated parameters which have + * already been selected. We are selecting parameters + * for only the source. + */ + dictSize = 0; + break; + default: + assert(0); + break; + } + + /* resize windowLog if input is small enough, to use less memory */ + if ( (srcSize < maxWindowResize) + && (dictSize < maxWindowResize) ) { + U32 const tSize = (U32)(srcSize + dictSize); + static U32 const hashSizeMin = 1 << ZSTD_HASHLOG_MIN; + U32 const srcLog = (tSize < hashSizeMin) ? ZSTD_HASHLOG_MIN : + ZSTD_highbit32(tSize-1) + 1; + if (cPar.windowLog > srcLog) cPar.windowLog = srcLog; + } + if (srcSize != ZSTD_CONTENTSIZE_UNKNOWN) { + U32 const dictAndWindowLog = ZSTD_dictAndWindowLog(cPar.windowLog, (U64)srcSize, (U64)dictSize); + U32 const cycleLog = ZSTD_cycleLog(cPar.chainLog, cPar.strategy); + if (cPar.hashLog > dictAndWindowLog+1) cPar.hashLog = dictAndWindowLog+1; + if (cycleLog > dictAndWindowLog) + cPar.chainLog -= (cycleLog - dictAndWindowLog); + } + + if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN) + cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN; /* minimum wlog required for valid frame header */ + + return cPar; +} + +ZSTD_compressionParameters +ZSTD_adjustCParams(ZSTD_compressionParameters cPar, + unsigned long long srcSize, + size_t dictSize) +{ + cPar = ZSTD_clampCParams(cPar); /* resulting cPar is necessarily valid (all parameters within range) */ + if (srcSize == 0) srcSize = ZSTD_CONTENTSIZE_UNKNOWN; + return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize, ZSTD_cpm_unknown); +} + +static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode); +static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode); + +static void ZSTD_overrideCParams( + ZSTD_compressionParameters* cParams, + const ZSTD_compressionParameters* overrides) +{ + if (overrides->windowLog) cParams->windowLog = overrides->windowLog; + if (overrides->hashLog) cParams->hashLog = overrides->hashLog; + if (overrides->chainLog) cParams->chainLog = overrides->chainLog; + if (overrides->searchLog) cParams->searchLog = overrides->searchLog; + if (overrides->minMatch) cParams->minMatch = overrides->minMatch; + if (overrides->targetLength) cParams->targetLength = overrides->targetLength; + if (overrides->strategy) cParams->strategy = overrides->strategy; +} + +ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams( + const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) +{ + ZSTD_compressionParameters cParams; + if (srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN && CCtxParams->srcSizeHint > 0) { + srcSizeHint = CCtxParams->srcSizeHint; + } + cParams = ZSTD_getCParams_internal(CCtxParams->compressionLevel, srcSizeHint, dictSize, mode); + if (CCtxParams->ldmParams.enableLdm) cParams.windowLog = ZSTD_LDM_DEFAULT_WINDOW_LOG; + ZSTD_overrideCParams(&cParams, &CCtxParams->cParams); + assert(!ZSTD_checkCParams(cParams)); + /* srcSizeHint == 0 means 0 */ + return ZSTD_adjustCParams_internal(cParams, srcSizeHint, dictSize, mode); +} + +static size_t +ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams, + const U32 forCCtx) +{ + size_t const chainSize = (cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cParams->chainLog); + size_t const hSize = ((size_t)1) << cParams->hashLog; + U32 const hashLog3 = (forCCtx && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0; + size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0; + /* We don't use ZSTD_cwksp_alloc_size() here because the tables aren't + * surrounded by redzones in ASAN. */ + size_t const tableSpace = chainSize * sizeof(U32) + + hSize * sizeof(U32) + + h3Size * sizeof(U32); + size_t const optPotentialSpace = + ZSTD_cwksp_alloc_size((MaxML+1) * sizeof(U32)) + + ZSTD_cwksp_alloc_size((MaxLL+1) * sizeof(U32)) + + ZSTD_cwksp_alloc_size((MaxOff+1) * sizeof(U32)) + + ZSTD_cwksp_alloc_size((1<strategy >= ZSTD_btopt)) + ? optPotentialSpace + : 0; + DEBUGLOG(4, "chainSize: %u - hSize: %u - h3Size: %u", + (U32)chainSize, (U32)hSize, (U32)h3Size); + return tableSpace + optSpace; +} + +static size_t ZSTD_estimateCCtxSize_usingCCtxParams_internal( + const ZSTD_compressionParameters* cParams, + const ldmParams_t* ldmParams, + const int isStatic, + const size_t buffInSize, + const size_t buffOutSize, + const U64 pledgedSrcSize) +{ + size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << cParams->windowLog), pledgedSrcSize)); + size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize); + U32 const divider = (cParams->minMatch==3) ? 3 : 4; + size_t const maxNbSeq = blockSize / divider; + size_t const tokenSpace = ZSTD_cwksp_alloc_size(WILDCOPY_OVERLENGTH + blockSize) + + ZSTD_cwksp_alloc_size(maxNbSeq * sizeof(seqDef)) + + 3 * ZSTD_cwksp_alloc_size(maxNbSeq * sizeof(BYTE)); + size_t const entropySpace = ZSTD_cwksp_alloc_size(ENTROPY_WORKSPACE_SIZE); + size_t const blockStateSpace = 2 * ZSTD_cwksp_alloc_size(sizeof(ZSTD_compressedBlockState_t)); + size_t const matchStateSize = ZSTD_sizeof_matchState(cParams, /* forCCtx */ 1); + + size_t const ldmSpace = ZSTD_ldm_getTableSize(*ldmParams); + size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(*ldmParams, blockSize); + size_t const ldmSeqSpace = ldmParams->enableLdm ? + ZSTD_cwksp_alloc_size(maxNbLdmSeq * sizeof(rawSeq)) : 0; + + + size_t const bufferSpace = ZSTD_cwksp_alloc_size(buffInSize) + + ZSTD_cwksp_alloc_size(buffOutSize); + + size_t const cctxSpace = isStatic ? ZSTD_cwksp_alloc_size(sizeof(ZSTD_CCtx)) : 0; + + size_t const neededSpace = + cctxSpace + + entropySpace + + blockStateSpace + + ldmSpace + + ldmSeqSpace + + matchStateSize + + tokenSpace + + bufferSpace; + + DEBUGLOG(5, "estimate workspace : %u", (U32)neededSpace); + return neededSpace; +} + +size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params) +{ + ZSTD_compressionParameters const cParams = + ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); + + RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); + /* estimateCCtxSize is for one-shot compression. So no buffers should + * be needed. However, we still allocate two 0-sized buffers, which can + * take space under ASAN. */ + return ZSTD_estimateCCtxSize_usingCCtxParams_internal( + &cParams, ¶ms->ldmParams, 1, 0, 0, ZSTD_CONTENTSIZE_UNKNOWN); +} + +size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams) +{ + ZSTD_CCtx_params const params = ZSTD_makeCCtxParamsFromCParams(cParams); + return ZSTD_estimateCCtxSize_usingCCtxParams(¶ms); +} + +static size_t ZSTD_estimateCCtxSize_internal(int compressionLevel) +{ + int tier = 0; + size_t largestSize = 0; + static const unsigned long long srcSizeTiers[4] = {16 KB, 128 KB, 256 KB, ZSTD_CONTENTSIZE_UNKNOWN}; + for (; tier < 4; ++tier) { + /* Choose the set of cParams for a given level across all srcSizes that give the largest cctxSize */ + ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, srcSizeTiers[tier], 0, ZSTD_cpm_noAttachDict); + largestSize = MAX(ZSTD_estimateCCtxSize_usingCParams(cParams), largestSize); + } + return largestSize; +} + +size_t ZSTD_estimateCCtxSize(int compressionLevel) +{ + int level; + size_t memBudget = 0; + for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) { + /* Ensure monotonically increasing memory usage as compression level increases */ + size_t const newMB = ZSTD_estimateCCtxSize_internal(level); + if (newMB > memBudget) memBudget = newMB; + } + return memBudget; +} + +size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params) +{ + RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only."); + { ZSTD_compressionParameters const cParams = + ZSTD_getCParamsFromCCtxParams(params, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); + size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog); + size_t const inBuffSize = (params->inBufferMode == ZSTD_bm_buffered) + ? ((size_t)1 << cParams.windowLog) + blockSize + : 0; + size_t const outBuffSize = (params->outBufferMode == ZSTD_bm_buffered) + ? ZSTD_compressBound(blockSize) + 1 + : 0; + + return ZSTD_estimateCCtxSize_usingCCtxParams_internal( + &cParams, ¶ms->ldmParams, 1, inBuffSize, outBuffSize, + ZSTD_CONTENTSIZE_UNKNOWN); + } +} + +size_t ZSTD_estimateCStreamSize_usingCParams(ZSTD_compressionParameters cParams) +{ + ZSTD_CCtx_params const params = ZSTD_makeCCtxParamsFromCParams(cParams); + return ZSTD_estimateCStreamSize_usingCCtxParams(¶ms); +} + +static size_t ZSTD_estimateCStreamSize_internal(int compressionLevel) +{ + ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, 0, ZSTD_cpm_noAttachDict); + return ZSTD_estimateCStreamSize_usingCParams(cParams); +} + +size_t ZSTD_estimateCStreamSize(int compressionLevel) +{ + int level; + size_t memBudget = 0; + for (level=MIN(compressionLevel, 1); level<=compressionLevel; level++) { + size_t const newMB = ZSTD_estimateCStreamSize_internal(level); + if (newMB > memBudget) memBudget = newMB; + } + return memBudget; +} + +/* ZSTD_getFrameProgression(): + * tells how much data has been consumed (input) and produced (output) for current frame. + * able to count progression inside worker threads (non-blocking mode). + */ +ZSTD_frameProgression ZSTD_getFrameProgression(const ZSTD_CCtx* cctx) +{ + { ZSTD_frameProgression fp; + size_t const buffered = (cctx->inBuff == NULL) ? 0 : + cctx->inBuffPos - cctx->inToCompress; + if (buffered) assert(cctx->inBuffPos >= cctx->inToCompress); + assert(buffered <= ZSTD_BLOCKSIZE_MAX); + fp.ingested = cctx->consumedSrcSize + buffered; + fp.consumed = cctx->consumedSrcSize; + fp.produced = cctx->producedCSize; + fp.flushed = cctx->producedCSize; /* simplified; some data might still be left within streaming output buffer */ + fp.currentJobID = 0; + fp.nbActiveWorkers = 0; + return fp; +} } + +/*! ZSTD_toFlushNow() + * Only useful for multithreading scenarios currently (nbWorkers >= 1). + */ +size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx) +{ + (void)cctx; + return 0; /* over-simplification; could also check if context is currently running in streaming mode, and in which case, report how many bytes are left to be flushed within output buffer */ +} + +static void ZSTD_assertEqualCParams(ZSTD_compressionParameters cParams1, + ZSTD_compressionParameters cParams2) +{ + (void)cParams1; + (void)cParams2; + assert(cParams1.windowLog == cParams2.windowLog); + assert(cParams1.chainLog == cParams2.chainLog); + assert(cParams1.hashLog == cParams2.hashLog); + assert(cParams1.searchLog == cParams2.searchLog); + assert(cParams1.minMatch == cParams2.minMatch); + assert(cParams1.targetLength == cParams2.targetLength); + assert(cParams1.strategy == cParams2.strategy); +} + +void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs) +{ + int i; + for (i = 0; i < ZSTD_REP_NUM; ++i) + bs->rep[i] = repStartValue[i]; + bs->entropy.huf.repeatMode = HUF_repeat_none; + bs->entropy.fse.offcode_repeatMode = FSE_repeat_none; + bs->entropy.fse.matchlength_repeatMode = FSE_repeat_none; + bs->entropy.fse.litlength_repeatMode = FSE_repeat_none; +} + +/*! ZSTD_invalidateMatchState() + * Invalidate all the matches in the match finder tables. + * Requires nextSrc and base to be set (can be NULL). + */ +static void ZSTD_invalidateMatchState(ZSTD_matchState_t* ms) +{ + ZSTD_window_clear(&ms->window); + + ms->nextToUpdate = ms->window.dictLimit; + ms->loadedDictEnd = 0; + ms->opt.litLengthSum = 0; /* force reset of btopt stats */ + ms->dictMatchState = NULL; +} + +/* + * Controls, for this matchState reset, whether the tables need to be cleared / + * prepared for the coming compression (ZSTDcrp_makeClean), or whether the + * tables can be left unclean (ZSTDcrp_leaveDirty), because we know that a + * subsequent operation will overwrite the table space anyways (e.g., copying + * the matchState contents in from a CDict). + */ +typedef enum { + ZSTDcrp_makeClean, + ZSTDcrp_leaveDirty +} ZSTD_compResetPolicy_e; + +/* + * Controls, for this matchState reset, whether indexing can continue where it + * left off (ZSTDirp_continue), or whether it needs to be restarted from zero + * (ZSTDirp_reset). + */ +typedef enum { + ZSTDirp_continue, + ZSTDirp_reset +} ZSTD_indexResetPolicy_e; + +typedef enum { + ZSTD_resetTarget_CDict, + ZSTD_resetTarget_CCtx +} ZSTD_resetTarget_e; + +static size_t +ZSTD_reset_matchState(ZSTD_matchState_t* ms, + ZSTD_cwksp* ws, + const ZSTD_compressionParameters* cParams, + const ZSTD_compResetPolicy_e crp, + const ZSTD_indexResetPolicy_e forceResetIndex, + const ZSTD_resetTarget_e forWho) +{ + size_t const chainSize = (cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cParams->chainLog); + size_t const hSize = ((size_t)1) << cParams->hashLog; + U32 const hashLog3 = ((forWho == ZSTD_resetTarget_CCtx) && cParams->minMatch==3) ? MIN(ZSTD_HASHLOG3_MAX, cParams->windowLog) : 0; + size_t const h3Size = hashLog3 ? ((size_t)1) << hashLog3 : 0; + + DEBUGLOG(4, "reset indices : %u", forceResetIndex == ZSTDirp_reset); + if (forceResetIndex == ZSTDirp_reset) { + ZSTD_window_init(&ms->window); + ZSTD_cwksp_mark_tables_dirty(ws); + } + + ms->hashLog3 = hashLog3; + + ZSTD_invalidateMatchState(ms); + + assert(!ZSTD_cwksp_reserve_failed(ws)); /* check that allocation hasn't already failed */ + + ZSTD_cwksp_clear_tables(ws); + + DEBUGLOG(5, "reserving table space"); + /* table Space */ + ms->hashTable = (U32*)ZSTD_cwksp_reserve_table(ws, hSize * sizeof(U32)); + ms->chainTable = (U32*)ZSTD_cwksp_reserve_table(ws, chainSize * sizeof(U32)); + ms->hashTable3 = (U32*)ZSTD_cwksp_reserve_table(ws, h3Size * sizeof(U32)); + RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation, + "failed a workspace allocation in ZSTD_reset_matchState"); + + DEBUGLOG(4, "reset table : %u", crp!=ZSTDcrp_leaveDirty); + if (crp!=ZSTDcrp_leaveDirty) { + /* reset tables only */ + ZSTD_cwksp_clean_tables(ws); + } + + /* opt parser space */ + if ((forWho == ZSTD_resetTarget_CCtx) && (cParams->strategy >= ZSTD_btopt)) { + DEBUGLOG(4, "reserving optimal parser space"); + ms->opt.litFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (1<opt.litLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxLL+1) * sizeof(unsigned)); + ms->opt.matchLengthFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxML+1) * sizeof(unsigned)); + ms->opt.offCodeFreq = (unsigned*)ZSTD_cwksp_reserve_aligned(ws, (MaxOff+1) * sizeof(unsigned)); + ms->opt.matchTable = (ZSTD_match_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_match_t)); + ms->opt.priceTable = (ZSTD_optimal_t*)ZSTD_cwksp_reserve_aligned(ws, (ZSTD_OPT_NUM+1) * sizeof(ZSTD_optimal_t)); + } + + ms->cParams = *cParams; + + RETURN_ERROR_IF(ZSTD_cwksp_reserve_failed(ws), memory_allocation, + "failed a workspace allocation in ZSTD_reset_matchState"); + + return 0; +} + +/* ZSTD_indexTooCloseToMax() : + * minor optimization : prefer memset() rather than reduceIndex() + * which is measurably slow in some circumstances (reported for Visual Studio). + * Works when re-using a context for a lot of smallish inputs : + * if all inputs are smaller than ZSTD_INDEXOVERFLOW_MARGIN, + * memset() will be triggered before reduceIndex(). + */ +#define ZSTD_INDEXOVERFLOW_MARGIN (16 MB) +static int ZSTD_indexTooCloseToMax(ZSTD_window_t w) +{ + return (size_t)(w.nextSrc - w.base) > (ZSTD_CURRENT_MAX - ZSTD_INDEXOVERFLOW_MARGIN); +} + +/*! ZSTD_resetCCtx_internal() : + note : `params` are assumed fully validated at this stage */ +static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc, + ZSTD_CCtx_params params, + U64 const pledgedSrcSize, + ZSTD_compResetPolicy_e const crp, + ZSTD_buffered_policy_e const zbuff) +{ + ZSTD_cwksp* const ws = &zc->workspace; + DEBUGLOG(4, "ZSTD_resetCCtx_internal: pledgedSrcSize=%u, wlog=%u", + (U32)pledgedSrcSize, params.cParams.windowLog); + assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams))); + + zc->isFirstBlock = 1; + + if (params.ldmParams.enableLdm) { + /* Adjust long distance matching parameters */ + ZSTD_ldm_adjustParameters(¶ms.ldmParams, ¶ms.cParams); + assert(params.ldmParams.hashLog >= params.ldmParams.bucketSizeLog); + assert(params.ldmParams.hashRateLog < 32); + } + + { size_t const windowSize = MAX(1, (size_t)MIN(((U64)1 << params.cParams.windowLog), pledgedSrcSize)); + size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, windowSize); + U32 const divider = (params.cParams.minMatch==3) ? 3 : 4; + size_t const maxNbSeq = blockSize / divider; + size_t const buffOutSize = (zbuff == ZSTDb_buffered && params.outBufferMode == ZSTD_bm_buffered) + ? ZSTD_compressBound(blockSize) + 1 + : 0; + size_t const buffInSize = (zbuff == ZSTDb_buffered && params.inBufferMode == ZSTD_bm_buffered) + ? windowSize + blockSize + : 0; + size_t const maxNbLdmSeq = ZSTD_ldm_getMaxNbSeq(params.ldmParams, blockSize); + + int const indexTooClose = ZSTD_indexTooCloseToMax(zc->blockState.matchState.window); + ZSTD_indexResetPolicy_e needsIndexReset = + (!indexTooClose && zc->initialized) ? ZSTDirp_continue : ZSTDirp_reset; + + size_t const neededSpace = + ZSTD_estimateCCtxSize_usingCCtxParams_internal( + ¶ms.cParams, ¶ms.ldmParams, zc->staticSize != 0, + buffInSize, buffOutSize, pledgedSrcSize); + FORWARD_IF_ERROR(neededSpace, "cctx size estimate failed!"); + + if (!zc->staticSize) ZSTD_cwksp_bump_oversized_duration(ws, 0); + + /* Check if workspace is large enough, alloc a new one if needed */ + { + int const workspaceTooSmall = ZSTD_cwksp_sizeof(ws) < neededSpace; + int const workspaceWasteful = ZSTD_cwksp_check_wasteful(ws, neededSpace); + + DEBUGLOG(4, "Need %zu B workspace", neededSpace); + DEBUGLOG(4, "windowSize: %zu - blockSize: %zu", windowSize, blockSize); + + if (workspaceTooSmall || workspaceWasteful) { + DEBUGLOG(4, "Resize workspaceSize from %zuKB to %zuKB", + ZSTD_cwksp_sizeof(ws) >> 10, + neededSpace >> 10); + + RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize"); + + needsIndexReset = ZSTDirp_reset; + + ZSTD_cwksp_free(ws, zc->customMem); + FORWARD_IF_ERROR(ZSTD_cwksp_create(ws, neededSpace, zc->customMem), ""); + + DEBUGLOG(5, "reserving object space"); + /* Statically sized space. + * entropyWorkspace never moves, + * though prev/next block swap places */ + assert(ZSTD_cwksp_check_available(ws, 2 * sizeof(ZSTD_compressedBlockState_t))); + zc->blockState.prevCBlock = (ZSTD_compressedBlockState_t*) ZSTD_cwksp_reserve_object(ws, sizeof(ZSTD_compressedBlockState_t)); + RETURN_ERROR_IF(zc->blockState.prevCBlock == NULL, memory_allocation, "couldn't allocate prevCBlock"); + zc->blockState.nextCBlock = (ZSTD_compressedBlockState_t*) ZSTD_cwksp_reserve_object(ws, sizeof(ZSTD_compressedBlockState_t)); + RETURN_ERROR_IF(zc->blockState.nextCBlock == NULL, memory_allocation, "couldn't allocate nextCBlock"); + zc->entropyWorkspace = (U32*) ZSTD_cwksp_reserve_object(ws, ENTROPY_WORKSPACE_SIZE); + RETURN_ERROR_IF(zc->blockState.nextCBlock == NULL, memory_allocation, "couldn't allocate entropyWorkspace"); + } } + + ZSTD_cwksp_clear(ws); + + /* init params */ + zc->appliedParams = params; + zc->blockState.matchState.cParams = params.cParams; + zc->pledgedSrcSizePlusOne = pledgedSrcSize+1; + zc->consumedSrcSize = 0; + zc->producedCSize = 0; + if (pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN) + zc->appliedParams.fParams.contentSizeFlag = 0; + DEBUGLOG(4, "pledged content size : %u ; flag : %u", + (unsigned)pledgedSrcSize, zc->appliedParams.fParams.contentSizeFlag); + zc->blockSize = blockSize; + + xxh64_reset(&zc->xxhState, 0); + zc->stage = ZSTDcs_init; + zc->dictID = 0; + zc->dictContentSize = 0; + + ZSTD_reset_compressedBlockState(zc->blockState.prevCBlock); + + /* ZSTD_wildcopy() is used to copy into the literals buffer, + * so we have to oversize the buffer by WILDCOPY_OVERLENGTH bytes. + */ + zc->seqStore.litStart = ZSTD_cwksp_reserve_buffer(ws, blockSize + WILDCOPY_OVERLENGTH); + zc->seqStore.maxNbLit = blockSize; + + /* buffers */ + zc->bufferedPolicy = zbuff; + zc->inBuffSize = buffInSize; + zc->inBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffInSize); + zc->outBuffSize = buffOutSize; + zc->outBuff = (char*)ZSTD_cwksp_reserve_buffer(ws, buffOutSize); + + /* ldm bucketOffsets table */ + if (params.ldmParams.enableLdm) { + /* TODO: avoid memset? */ + size_t const numBuckets = + ((size_t)1) << (params.ldmParams.hashLog - + params.ldmParams.bucketSizeLog); + zc->ldmState.bucketOffsets = ZSTD_cwksp_reserve_buffer(ws, numBuckets); + ZSTD_memset(zc->ldmState.bucketOffsets, 0, numBuckets); + } + + /* sequences storage */ + ZSTD_referenceExternalSequences(zc, NULL, 0); + zc->seqStore.maxNbSeq = maxNbSeq; + zc->seqStore.llCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); + zc->seqStore.mlCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); + zc->seqStore.ofCode = ZSTD_cwksp_reserve_buffer(ws, maxNbSeq * sizeof(BYTE)); + zc->seqStore.sequencesStart = (seqDef*)ZSTD_cwksp_reserve_aligned(ws, maxNbSeq * sizeof(seqDef)); + + FORWARD_IF_ERROR(ZSTD_reset_matchState( + &zc->blockState.matchState, + ws, + ¶ms.cParams, + crp, + needsIndexReset, + ZSTD_resetTarget_CCtx), ""); + + /* ldm hash table */ + if (params.ldmParams.enableLdm) { + /* TODO: avoid memset? */ + size_t const ldmHSize = ((size_t)1) << params.ldmParams.hashLog; + zc->ldmState.hashTable = (ldmEntry_t*)ZSTD_cwksp_reserve_aligned(ws, ldmHSize * sizeof(ldmEntry_t)); + ZSTD_memset(zc->ldmState.hashTable, 0, ldmHSize * sizeof(ldmEntry_t)); + zc->ldmSequences = (rawSeq*)ZSTD_cwksp_reserve_aligned(ws, maxNbLdmSeq * sizeof(rawSeq)); + zc->maxNbLdmSequences = maxNbLdmSeq; + + ZSTD_window_init(&zc->ldmState.window); + ZSTD_window_clear(&zc->ldmState.window); + zc->ldmState.loadedDictEnd = 0; + } + + /* Due to alignment, when reusing a workspace, we can actually consume + * up to 3 extra bytes for alignment. See the comments in zstd_cwksp.h + */ + assert(ZSTD_cwksp_used(ws) >= neededSpace && + ZSTD_cwksp_used(ws) <= neededSpace + 3); + + DEBUGLOG(3, "wksp: finished allocating, %zd bytes remain available", ZSTD_cwksp_available_space(ws)); + zc->initialized = 1; + + return 0; + } +} + +/* ZSTD_invalidateRepCodes() : + * ensures next compression will not use repcodes from previous block. + * Note : only works with regular variant; + * do not use with extDict variant ! */ +void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) { + int i; + for (i=0; iblockState.prevCBlock->rep[i] = 0; + assert(!ZSTD_window_hasExtDict(cctx->blockState.matchState.window)); +} + +/* These are the approximate sizes for each strategy past which copying the + * dictionary tables into the working context is faster than using them + * in-place. + */ +static const size_t attachDictSizeCutoffs[ZSTD_STRATEGY_MAX+1] = { + 8 KB, /* unused */ + 8 KB, /* ZSTD_fast */ + 16 KB, /* ZSTD_dfast */ + 32 KB, /* ZSTD_greedy */ + 32 KB, /* ZSTD_lazy */ + 32 KB, /* ZSTD_lazy2 */ + 32 KB, /* ZSTD_btlazy2 */ + 32 KB, /* ZSTD_btopt */ + 8 KB, /* ZSTD_btultra */ + 8 KB /* ZSTD_btultra2 */ +}; + +static int ZSTD_shouldAttachDict(const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, + U64 pledgedSrcSize) +{ + size_t cutoff = attachDictSizeCutoffs[cdict->matchState.cParams.strategy]; + int const dedicatedDictSearch = cdict->matchState.dedicatedDictSearch; + return dedicatedDictSearch + || ( ( pledgedSrcSize <= cutoff + || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN + || params->attachDictPref == ZSTD_dictForceAttach ) + && params->attachDictPref != ZSTD_dictForceCopy + && !params->forceWindow ); /* dictMatchState isn't correctly + * handled in _enforceMaxDist */ +} + +static size_t +ZSTD_resetCCtx_byAttachingCDict(ZSTD_CCtx* cctx, + const ZSTD_CDict* cdict, + ZSTD_CCtx_params params, + U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) +{ + { + ZSTD_compressionParameters adjusted_cdict_cParams = cdict->matchState.cParams; + unsigned const windowLog = params.cParams.windowLog; + assert(windowLog != 0); + /* Resize working context table params for input only, since the dict + * has its own tables. */ + /* pledgedSrcSize == 0 means 0! */ + + if (cdict->matchState.dedicatedDictSearch) { + ZSTD_dedicatedDictSearch_revertCParams(&adjusted_cdict_cParams); + } + + params.cParams = ZSTD_adjustCParams_internal(adjusted_cdict_cParams, pledgedSrcSize, + cdict->dictContentSize, ZSTD_cpm_attachDict); + params.cParams.windowLog = windowLog; + FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, + ZSTDcrp_makeClean, zbuff), ""); + assert(cctx->appliedParams.cParams.strategy == adjusted_cdict_cParams.strategy); + } + + { const U32 cdictEnd = (U32)( cdict->matchState.window.nextSrc + - cdict->matchState.window.base); + const U32 cdictLen = cdictEnd - cdict->matchState.window.dictLimit; + if (cdictLen == 0) { + /* don't even attach dictionaries with no contents */ + DEBUGLOG(4, "skipping attaching empty dictionary"); + } else { + DEBUGLOG(4, "attaching dictionary into context"); + cctx->blockState.matchState.dictMatchState = &cdict->matchState; + + /* prep working match state so dict matches never have negative indices + * when they are translated to the working context's index space. */ + if (cctx->blockState.matchState.window.dictLimit < cdictEnd) { + cctx->blockState.matchState.window.nextSrc = + cctx->blockState.matchState.window.base + cdictEnd; + ZSTD_window_clear(&cctx->blockState.matchState.window); + } + /* loadedDictEnd is expressed within the referential of the active context */ + cctx->blockState.matchState.loadedDictEnd = cctx->blockState.matchState.window.dictLimit; + } } + + cctx->dictID = cdict->dictID; + cctx->dictContentSize = cdict->dictContentSize; + + /* copy block state */ + ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState)); + + return 0; +} + +static size_t ZSTD_resetCCtx_byCopyingCDict(ZSTD_CCtx* cctx, + const ZSTD_CDict* cdict, + ZSTD_CCtx_params params, + U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) +{ + const ZSTD_compressionParameters *cdict_cParams = &cdict->matchState.cParams; + + assert(!cdict->matchState.dedicatedDictSearch); + + DEBUGLOG(4, "copying dictionary into context"); + + { unsigned const windowLog = params.cParams.windowLog; + assert(windowLog != 0); + /* Copy only compression parameters related to tables. */ + params.cParams = *cdict_cParams; + params.cParams.windowLog = windowLog; + FORWARD_IF_ERROR(ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize, + ZSTDcrp_leaveDirty, zbuff), ""); + assert(cctx->appliedParams.cParams.strategy == cdict_cParams->strategy); + assert(cctx->appliedParams.cParams.hashLog == cdict_cParams->hashLog); + assert(cctx->appliedParams.cParams.chainLog == cdict_cParams->chainLog); + } + + ZSTD_cwksp_mark_tables_dirty(&cctx->workspace); + + /* copy tables */ + { size_t const chainSize = (cdict_cParams->strategy == ZSTD_fast) ? 0 : ((size_t)1 << cdict_cParams->chainLog); + size_t const hSize = (size_t)1 << cdict_cParams->hashLog; + + ZSTD_memcpy(cctx->blockState.matchState.hashTable, + cdict->matchState.hashTable, + hSize * sizeof(U32)); + ZSTD_memcpy(cctx->blockState.matchState.chainTable, + cdict->matchState.chainTable, + chainSize * sizeof(U32)); + } + + /* Zero the hashTable3, since the cdict never fills it */ + { int const h3log = cctx->blockState.matchState.hashLog3; + size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0; + assert(cdict->matchState.hashLog3 == 0); + ZSTD_memset(cctx->blockState.matchState.hashTable3, 0, h3Size * sizeof(U32)); + } + + ZSTD_cwksp_mark_tables_clean(&cctx->workspace); + + /* copy dictionary offsets */ + { ZSTD_matchState_t const* srcMatchState = &cdict->matchState; + ZSTD_matchState_t* dstMatchState = &cctx->blockState.matchState; + dstMatchState->window = srcMatchState->window; + dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; + dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; + } + + cctx->dictID = cdict->dictID; + cctx->dictContentSize = cdict->dictContentSize; + + /* copy block state */ + ZSTD_memcpy(cctx->blockState.prevCBlock, &cdict->cBlockState, sizeof(cdict->cBlockState)); + + return 0; +} + +/* We have a choice between copying the dictionary context into the working + * context, or referencing the dictionary context from the working context + * in-place. We decide here which strategy to use. */ +static size_t ZSTD_resetCCtx_usingCDict(ZSTD_CCtx* cctx, + const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, + U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) +{ + + DEBUGLOG(4, "ZSTD_resetCCtx_usingCDict (pledgedSrcSize=%u)", + (unsigned)pledgedSrcSize); + + if (ZSTD_shouldAttachDict(cdict, params, pledgedSrcSize)) { + return ZSTD_resetCCtx_byAttachingCDict( + cctx, cdict, *params, pledgedSrcSize, zbuff); + } else { + return ZSTD_resetCCtx_byCopyingCDict( + cctx, cdict, *params, pledgedSrcSize, zbuff); + } +} + +/*! ZSTD_copyCCtx_internal() : + * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. + * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). + * The "context", in this case, refers to the hash and chain tables, + * entropy tables, and dictionary references. + * `windowLog` value is enforced if != 0, otherwise value is copied from srcCCtx. + * @return : 0, or an error code */ +static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx, + const ZSTD_CCtx* srcCCtx, + ZSTD_frameParameters fParams, + U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) +{ + DEBUGLOG(5, "ZSTD_copyCCtx_internal"); + RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong, + "Can't copy a ctx that's not in init stage."); + + ZSTD_memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem)); + { ZSTD_CCtx_params params = dstCCtx->requestedParams; + /* Copy only compression parameters related to tables. */ + params.cParams = srcCCtx->appliedParams.cParams; + params.fParams = fParams; + ZSTD_resetCCtx_internal(dstCCtx, params, pledgedSrcSize, + ZSTDcrp_leaveDirty, zbuff); + assert(dstCCtx->appliedParams.cParams.windowLog == srcCCtx->appliedParams.cParams.windowLog); + assert(dstCCtx->appliedParams.cParams.strategy == srcCCtx->appliedParams.cParams.strategy); + assert(dstCCtx->appliedParams.cParams.hashLog == srcCCtx->appliedParams.cParams.hashLog); + assert(dstCCtx->appliedParams.cParams.chainLog == srcCCtx->appliedParams.cParams.chainLog); + assert(dstCCtx->blockState.matchState.hashLog3 == srcCCtx->blockState.matchState.hashLog3); + } + + ZSTD_cwksp_mark_tables_dirty(&dstCCtx->workspace); + + /* copy tables */ + { size_t const chainSize = (srcCCtx->appliedParams.cParams.strategy == ZSTD_fast) ? 0 : ((size_t)1 << srcCCtx->appliedParams.cParams.chainLog); + size_t const hSize = (size_t)1 << srcCCtx->appliedParams.cParams.hashLog; + int const h3log = srcCCtx->blockState.matchState.hashLog3; + size_t const h3Size = h3log ? ((size_t)1 << h3log) : 0; + + ZSTD_memcpy(dstCCtx->blockState.matchState.hashTable, + srcCCtx->blockState.matchState.hashTable, + hSize * sizeof(U32)); + ZSTD_memcpy(dstCCtx->blockState.matchState.chainTable, + srcCCtx->blockState.matchState.chainTable, + chainSize * sizeof(U32)); + ZSTD_memcpy(dstCCtx->blockState.matchState.hashTable3, + srcCCtx->blockState.matchState.hashTable3, + h3Size * sizeof(U32)); + } + + ZSTD_cwksp_mark_tables_clean(&dstCCtx->workspace); + + /* copy dictionary offsets */ + { + const ZSTD_matchState_t* srcMatchState = &srcCCtx->blockState.matchState; + ZSTD_matchState_t* dstMatchState = &dstCCtx->blockState.matchState; + dstMatchState->window = srcMatchState->window; + dstMatchState->nextToUpdate = srcMatchState->nextToUpdate; + dstMatchState->loadedDictEnd= srcMatchState->loadedDictEnd; + } + dstCCtx->dictID = srcCCtx->dictID; + dstCCtx->dictContentSize = srcCCtx->dictContentSize; + + /* copy block state */ + ZSTD_memcpy(dstCCtx->blockState.prevCBlock, srcCCtx->blockState.prevCBlock, sizeof(*srcCCtx->blockState.prevCBlock)); + + return 0; +} + +/*! ZSTD_copyCCtx() : + * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. + * Only works during stage ZSTDcs_init (i.e. after creation, but before first call to ZSTD_compressContinue()). + * pledgedSrcSize==0 means "unknown". +* @return : 0, or an error code */ +size_t ZSTD_copyCCtx(ZSTD_CCtx* dstCCtx, const ZSTD_CCtx* srcCCtx, unsigned long long pledgedSrcSize) +{ + ZSTD_frameParameters fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; + ZSTD_buffered_policy_e const zbuff = srcCCtx->bufferedPolicy; + ZSTD_STATIC_ASSERT((U32)ZSTDb_buffered==1); + if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN; + fParams.contentSizeFlag = (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN); + + return ZSTD_copyCCtx_internal(dstCCtx, srcCCtx, + fParams, pledgedSrcSize, + zbuff); +} + + +#define ZSTD_ROWSIZE 16 +/*! ZSTD_reduceTable() : + * reduce table indexes by `reducerValue`, or squash to zero. + * PreserveMark preserves "unsorted mark" for btlazy2 strategy. + * It must be set to a clear 0/1 value, to remove branch during inlining. + * Presume table size is a multiple of ZSTD_ROWSIZE + * to help auto-vectorization */ +FORCE_INLINE_TEMPLATE void +ZSTD_reduceTable_internal (U32* const table, U32 const size, U32 const reducerValue, int const preserveMark) +{ + int const nbRows = (int)size / ZSTD_ROWSIZE; + int cellNb = 0; + int rowNb; + assert((size & (ZSTD_ROWSIZE-1)) == 0); /* multiple of ZSTD_ROWSIZE */ + assert(size < (1U<<31)); /* can be casted to int */ + + + for (rowNb=0 ; rowNb < nbRows ; rowNb++) { + int column; + for (column=0; columncParams.hashLog; + ZSTD_reduceTable(ms->hashTable, hSize, reducerValue); + } + + if (params->cParams.strategy != ZSTD_fast) { + U32 const chainSize = (U32)1 << params->cParams.chainLog; + if (params->cParams.strategy == ZSTD_btlazy2) + ZSTD_reduceTable_btlazy2(ms->chainTable, chainSize, reducerValue); + else + ZSTD_reduceTable(ms->chainTable, chainSize, reducerValue); + } + + if (ms->hashLog3) { + U32 const h3Size = (U32)1 << ms->hashLog3; + ZSTD_reduceTable(ms->hashTable3, h3Size, reducerValue); + } +} + + +/*-******************************************************* +* Block entropic compression +*********************************************************/ + +/* See doc/zstd_compression_format.md for detailed format description */ + +void ZSTD_seqToCodes(const seqStore_t* seqStorePtr) +{ + const seqDef* const sequences = seqStorePtr->sequencesStart; + BYTE* const llCodeTable = seqStorePtr->llCode; + BYTE* const ofCodeTable = seqStorePtr->ofCode; + BYTE* const mlCodeTable = seqStorePtr->mlCode; + U32 const nbSeq = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); + U32 u; + assert(nbSeq <= seqStorePtr->maxNbSeq); + for (u=0; ulongLengthID==1) + llCodeTable[seqStorePtr->longLengthPos] = MaxLL; + if (seqStorePtr->longLengthID==2) + mlCodeTable[seqStorePtr->longLengthPos] = MaxML; +} + +/* ZSTD_useTargetCBlockSize(): + * Returns if target compressed block size param is being used. + * If used, compression will do best effort to make a compressed block size to be around targetCBlockSize. + * Returns 1 if true, 0 otherwise. */ +static int ZSTD_useTargetCBlockSize(const ZSTD_CCtx_params* cctxParams) +{ + DEBUGLOG(5, "ZSTD_useTargetCBlockSize (targetCBlockSize=%zu)", cctxParams->targetCBlockSize); + return (cctxParams->targetCBlockSize != 0); +} + +/* ZSTD_entropyCompressSequences_internal(): + * actually compresses both literals and sequences */ +MEM_STATIC size_t +ZSTD_entropyCompressSequences_internal(seqStore_t* seqStorePtr, + const ZSTD_entropyCTables_t* prevEntropy, + ZSTD_entropyCTables_t* nextEntropy, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + void* entropyWorkspace, size_t entropyWkspSize, + const int bmi2) +{ + const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; + ZSTD_strategy const strategy = cctxParams->cParams.strategy; + unsigned* count = (unsigned*)entropyWorkspace; + FSE_CTable* CTable_LitLength = nextEntropy->fse.litlengthCTable; + FSE_CTable* CTable_OffsetBits = nextEntropy->fse.offcodeCTable; + FSE_CTable* CTable_MatchLength = nextEntropy->fse.matchlengthCTable; + U32 LLtype, Offtype, MLtype; /* compressed, raw or rle */ + const seqDef* const sequences = seqStorePtr->sequencesStart; + const BYTE* const ofCodeTable = seqStorePtr->ofCode; + const BYTE* const llCodeTable = seqStorePtr->llCode; + const BYTE* const mlCodeTable = seqStorePtr->mlCode; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart; + size_t const nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart); + BYTE* seqHead; + BYTE* lastNCount = NULL; + + entropyWorkspace = count + (MaxSeq + 1); + entropyWkspSize -= (MaxSeq + 1) * sizeof(*count); + + DEBUGLOG(4, "ZSTD_entropyCompressSequences_internal (nbSeq=%zu)", nbSeq); + ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<= HUF_WORKSPACE_SIZE); + + /* Compress literals */ + { const BYTE* const literals = seqStorePtr->litStart; + size_t const litSize = (size_t)(seqStorePtr->lit - literals); + size_t const cSize = ZSTD_compressLiterals( + &prevEntropy->huf, &nextEntropy->huf, + cctxParams->cParams.strategy, + ZSTD_disableLiteralsCompression(cctxParams), + op, dstCapacity, + literals, litSize, + entropyWorkspace, entropyWkspSize, + bmi2); + FORWARD_IF_ERROR(cSize, "ZSTD_compressLiterals failed"); + assert(cSize <= dstCapacity); + op += cSize; + } + + /* Sequences Header */ + RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/, + dstSize_tooSmall, "Can't fit seq hdr in output buf!"); + if (nbSeq < 128) { + *op++ = (BYTE)nbSeq; + } else if (nbSeq < LONGNBSEQ) { + op[0] = (BYTE)((nbSeq>>8) + 0x80); + op[1] = (BYTE)nbSeq; + op+=2; + } else { + op[0]=0xFF; + MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)); + op+=3; + } + assert(op <= oend); + if (nbSeq==0) { + /* Copy the old tables over as if we repeated them */ + ZSTD_memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse)); + return (size_t)(op - ostart); + } + + /* seqHead : flags for FSE encoding type */ + seqHead = op++; + assert(op <= oend); + + /* convert length/distances into codes */ + ZSTD_seqToCodes(seqStorePtr); + /* build CTable for Literal Lengths */ + { unsigned max = MaxLL; + size_t const mostFrequent = HIST_countFast_wksp(count, &max, llCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */ + DEBUGLOG(5, "Building LL table"); + nextEntropy->fse.litlength_repeatMode = prevEntropy->fse.litlength_repeatMode; + LLtype = ZSTD_selectEncodingType(&nextEntropy->fse.litlength_repeatMode, + count, max, mostFrequent, nbSeq, + LLFSELog, prevEntropy->fse.litlengthCTable, + LL_defaultNorm, LL_defaultNormLog, + ZSTD_defaultAllowed, strategy); + assert(set_basic < set_compressed && set_rle < set_compressed); + assert(!(LLtype < set_compressed && nextEntropy->fse.litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ + { size_t const countSize = ZSTD_buildCTable( + op, (size_t)(oend - op), + CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype, + count, max, llCodeTable, nbSeq, + LL_defaultNorm, LL_defaultNormLog, MaxLL, + prevEntropy->fse.litlengthCTable, + sizeof(prevEntropy->fse.litlengthCTable), + entropyWorkspace, entropyWkspSize); + FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for LitLens failed"); + if (LLtype == set_compressed) + lastNCount = op; + op += countSize; + assert(op <= oend); + } } + /* build CTable for Offsets */ + { unsigned max = MaxOff; + size_t const mostFrequent = HIST_countFast_wksp( + count, &max, ofCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */ + /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */ + ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed; + DEBUGLOG(5, "Building OF table"); + nextEntropy->fse.offcode_repeatMode = prevEntropy->fse.offcode_repeatMode; + Offtype = ZSTD_selectEncodingType(&nextEntropy->fse.offcode_repeatMode, + count, max, mostFrequent, nbSeq, + OffFSELog, prevEntropy->fse.offcodeCTable, + OF_defaultNorm, OF_defaultNormLog, + defaultPolicy, strategy); + assert(!(Offtype < set_compressed && nextEntropy->fse.offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */ + { size_t const countSize = ZSTD_buildCTable( + op, (size_t)(oend - op), + CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype, + count, max, ofCodeTable, nbSeq, + OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, + prevEntropy->fse.offcodeCTable, + sizeof(prevEntropy->fse.offcodeCTable), + entropyWorkspace, entropyWkspSize); + FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for Offsets failed"); + if (Offtype == set_compressed) + lastNCount = op; + op += countSize; + assert(op <= oend); + } } + /* build CTable for MatchLengths */ + { unsigned max = MaxML; + size_t const mostFrequent = HIST_countFast_wksp( + count, &max, mlCodeTable, nbSeq, entropyWorkspace, entropyWkspSize); /* can't fail */ + DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op)); + nextEntropy->fse.matchlength_repeatMode = prevEntropy->fse.matchlength_repeatMode; + MLtype = ZSTD_selectEncodingType(&nextEntropy->fse.matchlength_repeatMode, + count, max, mostFrequent, nbSeq, + MLFSELog, prevEntropy->fse.matchlengthCTable, + ML_defaultNorm, ML_defaultNormLog, + ZSTD_defaultAllowed, strategy); + assert(!(MLtype < set_compressed && nextEntropy->fse.matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ + { size_t const countSize = ZSTD_buildCTable( + op, (size_t)(oend - op), + CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype, + count, max, mlCodeTable, nbSeq, + ML_defaultNorm, ML_defaultNormLog, MaxML, + prevEntropy->fse.matchlengthCTable, + sizeof(prevEntropy->fse.matchlengthCTable), + entropyWorkspace, entropyWkspSize); + FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for MatchLengths failed"); + if (MLtype == set_compressed) + lastNCount = op; + op += countSize; + assert(op <= oend); + } } + + *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2)); + + { size_t const bitstreamSize = ZSTD_encodeSequences( + op, (size_t)(oend - op), + CTable_MatchLength, mlCodeTable, + CTable_OffsetBits, ofCodeTable, + CTable_LitLength, llCodeTable, + sequences, nbSeq, + longOffsets, bmi2); + FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed"); + op += bitstreamSize; + assert(op <= oend); + /* zstd versions <= 1.3.4 mistakenly report corruption when + * FSE_readNCount() receives a buffer < 4 bytes. + * Fixed by https://github.com/facebook/zstd/pull/1146. + * This can happen when the last set_compressed table present is 2 + * bytes and the bitstream is only one byte. + * In this exceedingly rare case, we will simply emit an uncompressed + * block, since it isn't worth optimizing. + */ + if (lastNCount && (op - lastNCount) < 4) { + /* NCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */ + assert(op - lastNCount == 3); + DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by " + "emitting an uncompressed block."); + return 0; + } + } + + DEBUGLOG(5, "compressed block size : %u", (unsigned)(op - ostart)); + return (size_t)(op - ostart); +} + +MEM_STATIC size_t +ZSTD_entropyCompressSequences(seqStore_t* seqStorePtr, + const ZSTD_entropyCTables_t* prevEntropy, + ZSTD_entropyCTables_t* nextEntropy, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + size_t srcSize, + void* entropyWorkspace, size_t entropyWkspSize, + int bmi2) +{ + size_t const cSize = ZSTD_entropyCompressSequences_internal( + seqStorePtr, prevEntropy, nextEntropy, cctxParams, + dst, dstCapacity, + entropyWorkspace, entropyWkspSize, bmi2); + if (cSize == 0) return 0; + /* When srcSize <= dstCapacity, there is enough space to write a raw uncompressed block. + * Since we ran out of space, block must be not compressible, so fall back to raw uncompressed block. + */ + if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity)) + return 0; /* block not compressed */ + FORWARD_IF_ERROR(cSize, "ZSTD_entropyCompressSequences_internal failed"); + + /* Check compressibility */ + { size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, cctxParams->cParams.strategy); + if (cSize >= maxCSize) return 0; /* block not compressed */ + } + DEBUGLOG(4, "ZSTD_entropyCompressSequences() cSize: %zu\n", cSize); + return cSize; +} + +/* ZSTD_selectBlockCompressor() : + * Not static, but internal use only (used by long distance matcher) + * assumption : strat is a valid strategy */ +ZSTD_blockCompressor ZSTD_selectBlockCompressor(ZSTD_strategy strat, ZSTD_dictMode_e dictMode) +{ + static const ZSTD_blockCompressor blockCompressor[4][ZSTD_STRATEGY_MAX+1] = { + { ZSTD_compressBlock_fast /* default for 0 */, + ZSTD_compressBlock_fast, + ZSTD_compressBlock_doubleFast, + ZSTD_compressBlock_greedy, + ZSTD_compressBlock_lazy, + ZSTD_compressBlock_lazy2, + ZSTD_compressBlock_btlazy2, + ZSTD_compressBlock_btopt, + ZSTD_compressBlock_btultra, + ZSTD_compressBlock_btultra2 }, + { ZSTD_compressBlock_fast_extDict /* default for 0 */, + ZSTD_compressBlock_fast_extDict, + ZSTD_compressBlock_doubleFast_extDict, + ZSTD_compressBlock_greedy_extDict, + ZSTD_compressBlock_lazy_extDict, + ZSTD_compressBlock_lazy2_extDict, + ZSTD_compressBlock_btlazy2_extDict, + ZSTD_compressBlock_btopt_extDict, + ZSTD_compressBlock_btultra_extDict, + ZSTD_compressBlock_btultra_extDict }, + { ZSTD_compressBlock_fast_dictMatchState /* default for 0 */, + ZSTD_compressBlock_fast_dictMatchState, + ZSTD_compressBlock_doubleFast_dictMatchState, + ZSTD_compressBlock_greedy_dictMatchState, + ZSTD_compressBlock_lazy_dictMatchState, + ZSTD_compressBlock_lazy2_dictMatchState, + ZSTD_compressBlock_btlazy2_dictMatchState, + ZSTD_compressBlock_btopt_dictMatchState, + ZSTD_compressBlock_btultra_dictMatchState, + ZSTD_compressBlock_btultra_dictMatchState }, + { NULL /* default for 0 */, + NULL, + NULL, + ZSTD_compressBlock_greedy_dedicatedDictSearch, + ZSTD_compressBlock_lazy_dedicatedDictSearch, + ZSTD_compressBlock_lazy2_dedicatedDictSearch, + NULL, + NULL, + NULL, + NULL } + }; + ZSTD_blockCompressor selectedCompressor; + ZSTD_STATIC_ASSERT((unsigned)ZSTD_fast == 1); + + assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat)); + selectedCompressor = blockCompressor[(int)dictMode][(int)strat]; + assert(selectedCompressor != NULL); + return selectedCompressor; +} + +static void ZSTD_storeLastLiterals(seqStore_t* seqStorePtr, + const BYTE* anchor, size_t lastLLSize) +{ + ZSTD_memcpy(seqStorePtr->lit, anchor, lastLLSize); + seqStorePtr->lit += lastLLSize; +} + +void ZSTD_resetSeqStore(seqStore_t* ssPtr) +{ + ssPtr->lit = ssPtr->litStart; + ssPtr->sequences = ssPtr->sequencesStart; + ssPtr->longLengthID = 0; +} + +typedef enum { ZSTDbss_compress, ZSTDbss_noCompress } ZSTD_buildSeqStore_e; + +static size_t ZSTD_buildSeqStore(ZSTD_CCtx* zc, const void* src, size_t srcSize) +{ + ZSTD_matchState_t* const ms = &zc->blockState.matchState; + DEBUGLOG(5, "ZSTD_buildSeqStore (srcSize=%zu)", srcSize); + assert(srcSize <= ZSTD_BLOCKSIZE_MAX); + /* Assert that we have correctly flushed the ctx params into the ms's copy */ + ZSTD_assertEqualCParams(zc->appliedParams.cParams, ms->cParams); + if (srcSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) { + if (zc->appliedParams.cParams.strategy >= ZSTD_btopt) { + ZSTD_ldm_skipRawSeqStoreBytes(&zc->externSeqStore, srcSize); + } else { + ZSTD_ldm_skipSequences(&zc->externSeqStore, srcSize, zc->appliedParams.cParams.minMatch); + } + return ZSTDbss_noCompress; /* don't even attempt compression below a certain srcSize */ + } + ZSTD_resetSeqStore(&(zc->seqStore)); + /* required for optimal parser to read stats from dictionary */ + ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy; + /* tell the optimal parser how we expect to compress literals */ + ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode; + /* a gap between an attached dict and the current window is not safe, + * they must remain adjacent, + * and when that stops being the case, the dict must be unset */ + assert(ms->dictMatchState == NULL || ms->loadedDictEnd == ms->window.dictLimit); + + /* limited update after a very long match */ + { const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; + const U32 curr = (U32)(istart-base); + if (sizeof(ptrdiff_t)==8) assert(istart - base < (ptrdiff_t)(U32)(-1)); /* ensure no overflow */ + if (curr > ms->nextToUpdate + 384) + ms->nextToUpdate = curr - MIN(192, (U32)(curr - ms->nextToUpdate - 384)); + } + + /* select and store sequences */ + { ZSTD_dictMode_e const dictMode = ZSTD_matchState_dictMode(ms); + size_t lastLLSize; + { int i; + for (i = 0; i < ZSTD_REP_NUM; ++i) + zc->blockState.nextCBlock->rep[i] = zc->blockState.prevCBlock->rep[i]; + } + if (zc->externSeqStore.pos < zc->externSeqStore.size) { + assert(!zc->appliedParams.ldmParams.enableLdm); + /* Updates ldmSeqStore.pos */ + lastLLSize = + ZSTD_ldm_blockCompress(&zc->externSeqStore, + ms, &zc->seqStore, + zc->blockState.nextCBlock->rep, + src, srcSize); + assert(zc->externSeqStore.pos <= zc->externSeqStore.size); + } else if (zc->appliedParams.ldmParams.enableLdm) { + rawSeqStore_t ldmSeqStore = kNullRawSeqStore; + + ldmSeqStore.seq = zc->ldmSequences; + ldmSeqStore.capacity = zc->maxNbLdmSequences; + /* Updates ldmSeqStore.size */ + FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore, + &zc->appliedParams.ldmParams, + src, srcSize), ""); + /* Updates ldmSeqStore.pos */ + lastLLSize = + ZSTD_ldm_blockCompress(&ldmSeqStore, + ms, &zc->seqStore, + zc->blockState.nextCBlock->rep, + src, srcSize); + assert(ldmSeqStore.pos == ldmSeqStore.size); + } else { /* not long range mode */ + ZSTD_blockCompressor const blockCompressor = ZSTD_selectBlockCompressor(zc->appliedParams.cParams.strategy, dictMode); + ms->ldmSeqStore = NULL; + lastLLSize = blockCompressor(ms, &zc->seqStore, zc->blockState.nextCBlock->rep, src, srcSize); + } + { const BYTE* const lastLiterals = (const BYTE*)src + srcSize - lastLLSize; + ZSTD_storeLastLiterals(&zc->seqStore, lastLiterals, lastLLSize); + } } + return ZSTDbss_compress; +} + +static void ZSTD_copyBlockSequences(ZSTD_CCtx* zc) +{ + const seqStore_t* seqStore = ZSTD_getSeqStore(zc); + const seqDef* seqStoreSeqs = seqStore->sequencesStart; + size_t seqStoreSeqSize = seqStore->sequences - seqStoreSeqs; + size_t seqStoreLiteralsSize = (size_t)(seqStore->lit - seqStore->litStart); + size_t literalsRead = 0; + size_t lastLLSize; + + ZSTD_Sequence* outSeqs = &zc->seqCollector.seqStart[zc->seqCollector.seqIndex]; + size_t i; + repcodes_t updatedRepcodes; + + assert(zc->seqCollector.seqIndex + 1 < zc->seqCollector.maxSequences); + /* Ensure we have enough space for last literals "sequence" */ + assert(zc->seqCollector.maxSequences >= seqStoreSeqSize + 1); + ZSTD_memcpy(updatedRepcodes.rep, zc->blockState.prevCBlock->rep, sizeof(repcodes_t)); + for (i = 0; i < seqStoreSeqSize; ++i) { + U32 rawOffset = seqStoreSeqs[i].offset - ZSTD_REP_NUM; + outSeqs[i].litLength = seqStoreSeqs[i].litLength; + outSeqs[i].matchLength = seqStoreSeqs[i].matchLength + MINMATCH; + outSeqs[i].rep = 0; + + if (i == seqStore->longLengthPos) { + if (seqStore->longLengthID == 1) { + outSeqs[i].litLength += 0x10000; + } else if (seqStore->longLengthID == 2) { + outSeqs[i].matchLength += 0x10000; + } + } + + if (seqStoreSeqs[i].offset <= ZSTD_REP_NUM) { + /* Derive the correct offset corresponding to a repcode */ + outSeqs[i].rep = seqStoreSeqs[i].offset; + if (outSeqs[i].litLength != 0) { + rawOffset = updatedRepcodes.rep[outSeqs[i].rep - 1]; + } else { + if (outSeqs[i].rep == 3) { + rawOffset = updatedRepcodes.rep[0] - 1; + } else { + rawOffset = updatedRepcodes.rep[outSeqs[i].rep]; + } + } + } + outSeqs[i].offset = rawOffset; + /* seqStoreSeqs[i].offset == offCode+1, and ZSTD_updateRep() expects offCode + so we provide seqStoreSeqs[i].offset - 1 */ + updatedRepcodes = ZSTD_updateRep(updatedRepcodes.rep, + seqStoreSeqs[i].offset - 1, + seqStoreSeqs[i].litLength == 0); + literalsRead += outSeqs[i].litLength; + } + /* Insert last literals (if any exist) in the block as a sequence with ml == off == 0. + * If there are no last literals, then we'll emit (of: 0, ml: 0, ll: 0), which is a marker + * for the block boundary, according to the API. + */ + assert(seqStoreLiteralsSize >= literalsRead); + lastLLSize = seqStoreLiteralsSize - literalsRead; + outSeqs[i].litLength = (U32)lastLLSize; + outSeqs[i].matchLength = outSeqs[i].offset = outSeqs[i].rep = 0; + seqStoreSeqSize++; + zc->seqCollector.seqIndex += seqStoreSeqSize; +} + +size_t ZSTD_generateSequences(ZSTD_CCtx* zc, ZSTD_Sequence* outSeqs, + size_t outSeqsSize, const void* src, size_t srcSize) +{ + const size_t dstCapacity = ZSTD_compressBound(srcSize); + void* dst = ZSTD_customMalloc(dstCapacity, ZSTD_defaultCMem); + SeqCollector seqCollector; + + RETURN_ERROR_IF(dst == NULL, memory_allocation, "NULL pointer!"); + + seqCollector.collectSequences = 1; + seqCollector.seqStart = outSeqs; + seqCollector.seqIndex = 0; + seqCollector.maxSequences = outSeqsSize; + zc->seqCollector = seqCollector; + + ZSTD_compress2(zc, dst, dstCapacity, src, srcSize); + ZSTD_customFree(dst, ZSTD_defaultCMem); + return zc->seqCollector.seqIndex; +} + +size_t ZSTD_mergeBlockDelimiters(ZSTD_Sequence* sequences, size_t seqsSize) { + size_t in = 0; + size_t out = 0; + for (; in < seqsSize; ++in) { + if (sequences[in].offset == 0 && sequences[in].matchLength == 0) { + if (in != seqsSize - 1) { + sequences[in+1].litLength += sequences[in].litLength; + } + } else { + sequences[out] = sequences[in]; + ++out; + } + } + return out; +} + +/* Unrolled loop to read four size_ts of input at a time. Returns 1 if is RLE, 0 if not. */ +static int ZSTD_isRLE(const BYTE* src, size_t length) { + const BYTE* ip = src; + const BYTE value = ip[0]; + const size_t valueST = (size_t)((U64)value * 0x0101010101010101ULL); + const size_t unrollSize = sizeof(size_t) * 4; + const size_t unrollMask = unrollSize - 1; + const size_t prefixLength = length & unrollMask; + size_t i; + size_t u; + if (length == 1) return 1; + /* Check if prefix is RLE first before using unrolled loop */ + if (prefixLength && ZSTD_count(ip+1, ip, ip+prefixLength) != prefixLength-1) { + return 0; + } + for (i = prefixLength; i != length; i += unrollSize) { + for (u = 0; u < unrollSize; u += sizeof(size_t)) { + if (MEM_readST(ip + i + u) != valueST) { + return 0; + } + } + } + return 1; +} + +/* Returns true if the given block may be RLE. + * This is just a heuristic based on the compressibility. + * It may return both false positives and false negatives. + */ +static int ZSTD_maybeRLE(seqStore_t const* seqStore) +{ + size_t const nbSeqs = (size_t)(seqStore->sequences - seqStore->sequencesStart); + size_t const nbLits = (size_t)(seqStore->lit - seqStore->litStart); + + return nbSeqs < 4 && nbLits < 10; +} + +static void ZSTD_confirmRepcodesAndEntropyTables(ZSTD_CCtx* zc) +{ + ZSTD_compressedBlockState_t* const tmp = zc->blockState.prevCBlock; + zc->blockState.prevCBlock = zc->blockState.nextCBlock; + zc->blockState.nextCBlock = tmp; +} + +static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, U32 frame) +{ + /* This the upper bound for the length of an rle block. + * This isn't the actual upper bound. Finding the real threshold + * needs further investigation. + */ + const U32 rleMaxLength = 25; + size_t cSize; + const BYTE* ip = (const BYTE*)src; + BYTE* op = (BYTE*)dst; + DEBUGLOG(5, "ZSTD_compressBlock_internal (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u)", + (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit, + (unsigned)zc->blockState.matchState.nextToUpdate); + + { const size_t bss = ZSTD_buildSeqStore(zc, src, srcSize); + FORWARD_IF_ERROR(bss, "ZSTD_buildSeqStore failed"); + if (bss == ZSTDbss_noCompress) { cSize = 0; goto out; } + } + + if (zc->seqCollector.collectSequences) { + ZSTD_copyBlockSequences(zc); + ZSTD_confirmRepcodesAndEntropyTables(zc); + return 0; + } + + /* encode sequences and literals */ + cSize = ZSTD_entropyCompressSequences(&zc->seqStore, + &zc->blockState.prevCBlock->entropy, &zc->blockState.nextCBlock->entropy, + &zc->appliedParams, + dst, dstCapacity, + srcSize, + zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */, + zc->bmi2); + + if (zc->seqCollector.collectSequences) { + ZSTD_copyBlockSequences(zc); + return 0; + } + + + if (frame && + /* We don't want to emit our first block as a RLE even if it qualifies because + * doing so will cause the decoder (cli only) to throw a "should consume all input error." + * This is only an issue for zstd <= v1.4.3 + */ + !zc->isFirstBlock && + cSize < rleMaxLength && + ZSTD_isRLE(ip, srcSize)) + { + cSize = 1; + op[0] = ip[0]; + } + +out: + if (!ZSTD_isError(cSize) && cSize > 1) { + ZSTD_confirmRepcodesAndEntropyTables(zc); + } + /* We check that dictionaries have offset codes available for the first + * block. After the first block, the offcode table might not have large + * enough codes to represent the offsets in the data. + */ + if (zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode == FSE_repeat_valid) + zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode = FSE_repeat_check; + + return cSize; +} + +static size_t ZSTD_compressBlock_targetCBlockSize_body(ZSTD_CCtx* zc, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const size_t bss, U32 lastBlock) +{ + DEBUGLOG(6, "Attempting ZSTD_compressSuperBlock()"); + if (bss == ZSTDbss_compress) { + if (/* We don't want to emit our first block as a RLE even if it qualifies because + * doing so will cause the decoder (cli only) to throw a "should consume all input error." + * This is only an issue for zstd <= v1.4.3 + */ + !zc->isFirstBlock && + ZSTD_maybeRLE(&zc->seqStore) && + ZSTD_isRLE((BYTE const*)src, srcSize)) + { + return ZSTD_rleCompressBlock(dst, dstCapacity, *(BYTE const*)src, srcSize, lastBlock); + } + /* Attempt superblock compression. + * + * Note that compressed size of ZSTD_compressSuperBlock() is not bound by the + * standard ZSTD_compressBound(). This is a problem, because even if we have + * space now, taking an extra byte now could cause us to run out of space later + * and violate ZSTD_compressBound(). + * + * Define blockBound(blockSize) = blockSize + ZSTD_blockHeaderSize. + * + * In order to respect ZSTD_compressBound() we must attempt to emit a raw + * uncompressed block in these cases: + * * cSize == 0: Return code for an uncompressed block. + * * cSize == dstSize_tooSmall: We may have expanded beyond blockBound(srcSize). + * ZSTD_noCompressBlock() will return dstSize_tooSmall if we are really out of + * output space. + * * cSize >= blockBound(srcSize): We have expanded the block too much so + * emit an uncompressed block. + */ + { + size_t const cSize = ZSTD_compressSuperBlock(zc, dst, dstCapacity, src, srcSize, lastBlock); + if (cSize != ERROR(dstSize_tooSmall)) { + size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, zc->appliedParams.cParams.strategy); + FORWARD_IF_ERROR(cSize, "ZSTD_compressSuperBlock failed"); + if (cSize != 0 && cSize < maxCSize + ZSTD_blockHeaderSize) { + ZSTD_confirmRepcodesAndEntropyTables(zc); + return cSize; + } + } + } + } + + DEBUGLOG(6, "Resorting to ZSTD_noCompressBlock()"); + /* Superblock compression failed, attempt to emit a single no compress block. + * The decoder will be able to stream this block since it is uncompressed. + */ + return ZSTD_noCompressBlock(dst, dstCapacity, src, srcSize, lastBlock); +} + +static size_t ZSTD_compressBlock_targetCBlockSize(ZSTD_CCtx* zc, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + U32 lastBlock) +{ + size_t cSize = 0; + const size_t bss = ZSTD_buildSeqStore(zc, src, srcSize); + DEBUGLOG(5, "ZSTD_compressBlock_targetCBlockSize (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u, srcSize=%zu)", + (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit, (unsigned)zc->blockState.matchState.nextToUpdate, srcSize); + FORWARD_IF_ERROR(bss, "ZSTD_buildSeqStore failed"); + + cSize = ZSTD_compressBlock_targetCBlockSize_body(zc, dst, dstCapacity, src, srcSize, bss, lastBlock); + FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_targetCBlockSize_body failed"); + + if (zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode == FSE_repeat_valid) + zc->blockState.prevCBlock->entropy.fse.offcode_repeatMode = FSE_repeat_check; + + return cSize; +} + +static void ZSTD_overflowCorrectIfNeeded(ZSTD_matchState_t* ms, + ZSTD_cwksp* ws, + ZSTD_CCtx_params const* params, + void const* ip, + void const* iend) +{ + if (ZSTD_window_needOverflowCorrection(ms->window, iend)) { + U32 const maxDist = (U32)1 << params->cParams.windowLog; + U32 const cycleLog = ZSTD_cycleLog(params->cParams.chainLog, params->cParams.strategy); + U32 const correction = ZSTD_window_correctOverflow(&ms->window, cycleLog, maxDist, ip); + ZSTD_STATIC_ASSERT(ZSTD_CHAINLOG_MAX <= 30); + ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX_32 <= 30); + ZSTD_STATIC_ASSERT(ZSTD_WINDOWLOG_MAX <= 31); + ZSTD_cwksp_mark_tables_dirty(ws); + ZSTD_reduceIndex(ms, params, correction); + ZSTD_cwksp_mark_tables_clean(ws); + if (ms->nextToUpdate < correction) ms->nextToUpdate = 0; + else ms->nextToUpdate -= correction; + /* invalidate dictionaries on overflow correction */ + ms->loadedDictEnd = 0; + ms->dictMatchState = NULL; + } +} + +/*! ZSTD_compress_frameChunk() : +* Compress a chunk of data into one or multiple blocks. +* All blocks will be terminated, all input will be consumed. +* Function will issue an error if there is not enough `dstCapacity` to hold the compressed content. +* Frame is supposed already started (header already produced) +* @return : compressed size, or an error code +*/ +static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + U32 lastFrameChunk) +{ + size_t blockSize = cctx->blockSize; + size_t remaining = srcSize; + const BYTE* ip = (const BYTE*)src; + BYTE* const ostart = (BYTE*)dst; + BYTE* op = ostart; + U32 const maxDist = (U32)1 << cctx->appliedParams.cParams.windowLog; + + assert(cctx->appliedParams.cParams.windowLog <= ZSTD_WINDOWLOG_MAX); + + DEBUGLOG(4, "ZSTD_compress_frameChunk (blockSize=%u)", (unsigned)blockSize); + if (cctx->appliedParams.fParams.checksumFlag && srcSize) + xxh64_update(&cctx->xxhState, src, srcSize); + + while (remaining) { + ZSTD_matchState_t* const ms = &cctx->blockState.matchState; + U32 const lastBlock = lastFrameChunk & (blockSize >= remaining); + + RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE, + dstSize_tooSmall, + "not enough space to store compressed block"); + if (remaining < blockSize) blockSize = remaining; + + ZSTD_overflowCorrectIfNeeded( + ms, &cctx->workspace, &cctx->appliedParams, ip, ip + blockSize); + ZSTD_checkDictValidity(&ms->window, ip + blockSize, maxDist, &ms->loadedDictEnd, &ms->dictMatchState); + + /* Ensure hash/chain table insertion resumes no sooner than lowlimit */ + if (ms->nextToUpdate < ms->window.lowLimit) ms->nextToUpdate = ms->window.lowLimit; + + { size_t cSize; + if (ZSTD_useTargetCBlockSize(&cctx->appliedParams)) { + cSize = ZSTD_compressBlock_targetCBlockSize(cctx, op, dstCapacity, ip, blockSize, lastBlock); + FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_targetCBlockSize failed"); + assert(cSize > 0); + assert(cSize <= blockSize + ZSTD_blockHeaderSize); + } else { + cSize = ZSTD_compressBlock_internal(cctx, + op+ZSTD_blockHeaderSize, dstCapacity-ZSTD_blockHeaderSize, + ip, blockSize, 1 /* frame */); + FORWARD_IF_ERROR(cSize, "ZSTD_compressBlock_internal failed"); + + if (cSize == 0) { /* block is not compressible */ + cSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock); + FORWARD_IF_ERROR(cSize, "ZSTD_noCompressBlock failed"); + } else { + U32 const cBlockHeader = cSize == 1 ? + lastBlock + (((U32)bt_rle)<<1) + (U32)(blockSize << 3) : + lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3); + MEM_writeLE24(op, cBlockHeader); + cSize += ZSTD_blockHeaderSize; + } + } + + + ip += blockSize; + assert(remaining >= blockSize); + remaining -= blockSize; + op += cSize; + assert(dstCapacity >= cSize); + dstCapacity -= cSize; + cctx->isFirstBlock = 0; + DEBUGLOG(5, "ZSTD_compress_frameChunk: adding a block of size %u", + (unsigned)cSize); + } } + + if (lastFrameChunk && (op>ostart)) cctx->stage = ZSTDcs_ending; + return (size_t)(op-ostart); +} + + +static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity, + const ZSTD_CCtx_params* params, U64 pledgedSrcSize, U32 dictID) +{ BYTE* const op = (BYTE*)dst; + U32 const dictIDSizeCodeLength = (dictID>0) + (dictID>=256) + (dictID>=65536); /* 0-3 */ + U32 const dictIDSizeCode = params->fParams.noDictIDFlag ? 0 : dictIDSizeCodeLength; /* 0-3 */ + U32 const checksumFlag = params->fParams.checksumFlag>0; + U32 const windowSize = (U32)1 << params->cParams.windowLog; + U32 const singleSegment = params->fParams.contentSizeFlag && (windowSize >= pledgedSrcSize); + BYTE const windowLogByte = (BYTE)((params->cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3); + U32 const fcsCode = params->fParams.contentSizeFlag ? + (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0; /* 0-3 */ + BYTE const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) ); + size_t pos=0; + + assert(!(params->fParams.contentSizeFlag && pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN)); + RETURN_ERROR_IF(dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX, dstSize_tooSmall, + "dst buf is too small to fit worst-case frame header size."); + DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u", + !params->fParams.noDictIDFlag, (unsigned)dictID, (unsigned)dictIDSizeCode); + if (params->format == ZSTD_f_zstd1) { + MEM_writeLE32(dst, ZSTD_MAGICNUMBER); + pos = 4; + } + op[pos++] = frameHeaderDescriptionByte; + if (!singleSegment) op[pos++] = windowLogByte; + switch(dictIDSizeCode) + { + default: + assert(0); /* impossible */ + ZSTD_FALLTHROUGH; + case 0 : break; + case 1 : op[pos] = (BYTE)(dictID); pos++; break; + case 2 : MEM_writeLE16(op+pos, (U16)dictID); pos+=2; break; + case 3 : MEM_writeLE32(op+pos, dictID); pos+=4; break; + } + switch(fcsCode) + { + default: + assert(0); /* impossible */ + ZSTD_FALLTHROUGH; + case 0 : if (singleSegment) op[pos++] = (BYTE)(pledgedSrcSize); break; + case 1 : MEM_writeLE16(op+pos, (U16)(pledgedSrcSize-256)); pos+=2; break; + case 2 : MEM_writeLE32(op+pos, (U32)(pledgedSrcSize)); pos+=4; break; + case 3 : MEM_writeLE64(op+pos, (U64)(pledgedSrcSize)); pos+=8; break; + } + return pos; +} + +/* ZSTD_writeSkippableFrame_advanced() : + * Writes out a skippable frame with the specified magic number variant (16 are supported), + * from ZSTD_MAGIC_SKIPPABLE_START to ZSTD_MAGIC_SKIPPABLE_START+15, and the desired source data. + * + * Returns the total number of bytes written, or a ZSTD error code. + */ +size_t ZSTD_writeSkippableFrame(void* dst, size_t dstCapacity, + const void* src, size_t srcSize, unsigned magicVariant) { + BYTE* op = (BYTE*)dst; + RETURN_ERROR_IF(dstCapacity < srcSize + ZSTD_SKIPPABLEHEADERSIZE /* Skippable frame overhead */, + dstSize_tooSmall, "Not enough room for skippable frame"); + RETURN_ERROR_IF(srcSize > (unsigned)0xFFFFFFFF, srcSize_wrong, "Src size too large for skippable frame"); + RETURN_ERROR_IF(magicVariant > 15, parameter_outOfBound, "Skippable frame magic number variant not supported"); + + MEM_writeLE32(op, (U32)(ZSTD_MAGIC_SKIPPABLE_START + magicVariant)); + MEM_writeLE32(op+4, (U32)srcSize); + ZSTD_memcpy(op+8, src, srcSize); + return srcSize + ZSTD_SKIPPABLEHEADERSIZE; +} + +/* ZSTD_writeLastEmptyBlock() : + * output an empty Block with end-of-frame mark to complete a frame + * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) + * or an error code if `dstCapacity` is too small (stage != ZSTDcs_init, stage_wrong, + "wrong cctx stage"); + RETURN_ERROR_IF(cctx->appliedParams.ldmParams.enableLdm, + parameter_unsupported, + "incompatible with ldm"); + cctx->externSeqStore.seq = seq; + cctx->externSeqStore.size = nbSeq; + cctx->externSeqStore.capacity = nbSeq; + cctx->externSeqStore.pos = 0; + cctx->externSeqStore.posInSequence = 0; + return 0; +} + + +static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + U32 frame, U32 lastFrameChunk) +{ + ZSTD_matchState_t* const ms = &cctx->blockState.matchState; + size_t fhSize = 0; + + DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u", + cctx->stage, (unsigned)srcSize); + RETURN_ERROR_IF(cctx->stage==ZSTDcs_created, stage_wrong, + "missing init (ZSTD_compressBegin)"); + + if (frame && (cctx->stage==ZSTDcs_init)) { + fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, &cctx->appliedParams, + cctx->pledgedSrcSizePlusOne-1, cctx->dictID); + FORWARD_IF_ERROR(fhSize, "ZSTD_writeFrameHeader failed"); + assert(fhSize <= dstCapacity); + dstCapacity -= fhSize; + dst = (char*)dst + fhSize; + cctx->stage = ZSTDcs_ongoing; + } + + if (!srcSize) return fhSize; /* do not generate an empty block if no input */ + + if (!ZSTD_window_update(&ms->window, src, srcSize)) { + ms->nextToUpdate = ms->window.dictLimit; + } + if (cctx->appliedParams.ldmParams.enableLdm) { + ZSTD_window_update(&cctx->ldmState.window, src, srcSize); + } + + if (!frame) { + /* overflow check and correction for block mode */ + ZSTD_overflowCorrectIfNeeded( + ms, &cctx->workspace, &cctx->appliedParams, + src, (BYTE const*)src + srcSize); + } + + DEBUGLOG(5, "ZSTD_compressContinue_internal (blockSize=%u)", (unsigned)cctx->blockSize); + { size_t const cSize = frame ? + ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) : + ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize, 0 /* frame */); + FORWARD_IF_ERROR(cSize, "%s", frame ? "ZSTD_compress_frameChunk failed" : "ZSTD_compressBlock_internal failed"); + cctx->consumedSrcSize += srcSize; + cctx->producedCSize += (cSize + fhSize); + assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0)); + if (cctx->pledgedSrcSizePlusOne != 0) { /* control src size */ + ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1); + RETURN_ERROR_IF( + cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne, + srcSize_wrong, + "error : pledgedSrcSize = %u, while realSrcSize >= %u", + (unsigned)cctx->pledgedSrcSizePlusOne-1, + (unsigned)cctx->consumedSrcSize); + } + return cSize + fhSize; + } +} + +size_t ZSTD_compressContinue (ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize) +{ + DEBUGLOG(5, "ZSTD_compressContinue (srcSize=%u)", (unsigned)srcSize); + return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 1 /* frame mode */, 0 /* last chunk */); +} + + +size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx) +{ + ZSTD_compressionParameters const cParams = cctx->appliedParams.cParams; + assert(!ZSTD_checkCParams(cParams)); + return MIN (ZSTD_BLOCKSIZE_MAX, (U32)1 << cParams.windowLog); +} + +size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + DEBUGLOG(5, "ZSTD_compressBlock: srcSize = %u", (unsigned)srcSize); + { size_t const blockSizeMax = ZSTD_getBlockSize(cctx); + RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong, "input is larger than a block"); } + + return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */); +} + +/*! ZSTD_loadDictionaryContent() : + * @return : 0, or an error code + */ +static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms, + ldmState_t* ls, + ZSTD_cwksp* ws, + ZSTD_CCtx_params const* params, + const void* src, size_t srcSize, + ZSTD_dictTableLoadMethod_e dtlm) +{ + const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; + + ZSTD_window_update(&ms->window, src, srcSize); + ms->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ms->window.base); + + if (params->ldmParams.enableLdm && ls != NULL) { + ZSTD_window_update(&ls->window, src, srcSize); + ls->loadedDictEnd = params->forceWindow ? 0 : (U32)(iend - ls->window.base); + } + + /* Assert that we the ms params match the params we're being given */ + ZSTD_assertEqualCParams(params->cParams, ms->cParams); + + if (srcSize <= HASH_READ_SIZE) return 0; + + while (iend - ip > HASH_READ_SIZE) { + size_t const remaining = (size_t)(iend - ip); + size_t const chunk = MIN(remaining, ZSTD_CHUNKSIZE_MAX); + const BYTE* const ichunk = ip + chunk; + + ZSTD_overflowCorrectIfNeeded(ms, ws, params, ip, ichunk); + + if (params->ldmParams.enableLdm && ls != NULL) + ZSTD_ldm_fillHashTable(ls, (const BYTE*)src, (const BYTE*)src + srcSize, ¶ms->ldmParams); + + switch(params->cParams.strategy) + { + case ZSTD_fast: + ZSTD_fillHashTable(ms, ichunk, dtlm); + break; + case ZSTD_dfast: + ZSTD_fillDoubleHashTable(ms, ichunk, dtlm); + break; + + case ZSTD_greedy: + case ZSTD_lazy: + case ZSTD_lazy2: + if (chunk >= HASH_READ_SIZE && ms->dedicatedDictSearch) { + assert(chunk == remaining); /* must load everything in one go */ + ZSTD_dedicatedDictSearch_lazy_loadDictionary(ms, ichunk-HASH_READ_SIZE); + } else if (chunk >= HASH_READ_SIZE) { + ZSTD_insertAndFindFirstIndex(ms, ichunk-HASH_READ_SIZE); + } + break; + + case ZSTD_btlazy2: /* we want the dictionary table fully sorted */ + case ZSTD_btopt: + case ZSTD_btultra: + case ZSTD_btultra2: + if (chunk >= HASH_READ_SIZE) + ZSTD_updateTree(ms, ichunk-HASH_READ_SIZE, ichunk); + break; + + default: + assert(0); /* not possible : not a valid strategy id */ + } + + ip = ichunk; + } + + ms->nextToUpdate = (U32)(iend - ms->window.base); + return 0; +} + + +/* Dictionaries that assign zero probability to symbols that show up causes problems + * when FSE encoding. Mark dictionaries with zero probability symbols as FSE_repeat_check + * and only dictionaries with 100% valid symbols can be assumed valid. + */ +static FSE_repeat ZSTD_dictNCountRepeat(short* normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue) +{ + U32 s; + if (dictMaxSymbolValue < maxSymbolValue) { + return FSE_repeat_check; + } + for (s = 0; s <= maxSymbolValue; ++s) { + if (normalizedCounter[s] == 0) { + return FSE_repeat_check; + } + } + return FSE_repeat_valid; +} + +size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace, + const void* const dict, size_t dictSize) +{ + short offcodeNCount[MaxOff+1]; + unsigned offcodeMaxValue = MaxOff; + const BYTE* dictPtr = (const BYTE*)dict; /* skip magic num and dict ID */ + const BYTE* const dictEnd = dictPtr + dictSize; + dictPtr += 8; + bs->entropy.huf.repeatMode = HUF_repeat_check; + + { unsigned maxSymbolValue = 255; + unsigned hasZeroWeights = 1; + size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr, + dictEnd-dictPtr, &hasZeroWeights); + + /* We only set the loaded table as valid if it contains all non-zero + * weights. Otherwise, we set it to check */ + if (!hasZeroWeights) + bs->entropy.huf.repeatMode = HUF_repeat_valid; + + RETURN_ERROR_IF(HUF_isError(hufHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(maxSymbolValue < 255, dictionary_corrupted, ""); + dictPtr += hufHeaderSize; + } + + { unsigned offcodeLog; + size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr); + RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted, ""); + /* fill all offset symbols to avoid garbage at end of table */ + RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp( + bs->entropy.fse.offcodeCTable, + offcodeNCount, MaxOff, offcodeLog, + workspace, HUF_WORKSPACE_SIZE)), + dictionary_corrupted, ""); + /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */ + dictPtr += offcodeHeaderSize; + } + + { short matchlengthNCount[MaxML+1]; + unsigned matchlengthMaxValue = MaxML, matchlengthLog; + size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr); + RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted, ""); + RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp( + bs->entropy.fse.matchlengthCTable, + matchlengthNCount, matchlengthMaxValue, matchlengthLog, + workspace, HUF_WORKSPACE_SIZE)), + dictionary_corrupted, ""); + bs->entropy.fse.matchlength_repeatMode = ZSTD_dictNCountRepeat(matchlengthNCount, matchlengthMaxValue, MaxML); + dictPtr += matchlengthHeaderSize; + } + + { short litlengthNCount[MaxLL+1]; + unsigned litlengthMaxValue = MaxLL, litlengthLog; + size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr); + RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted, ""); + RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp( + bs->entropy.fse.litlengthCTable, + litlengthNCount, litlengthMaxValue, litlengthLog, + workspace, HUF_WORKSPACE_SIZE)), + dictionary_corrupted, ""); + bs->entropy.fse.litlength_repeatMode = ZSTD_dictNCountRepeat(litlengthNCount, litlengthMaxValue, MaxLL); + dictPtr += litlengthHeaderSize; + } + + RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted, ""); + bs->rep[0] = MEM_readLE32(dictPtr+0); + bs->rep[1] = MEM_readLE32(dictPtr+4); + bs->rep[2] = MEM_readLE32(dictPtr+8); + dictPtr += 12; + + { size_t const dictContentSize = (size_t)(dictEnd - dictPtr); + U32 offcodeMax = MaxOff; + if (dictContentSize <= ((U32)-1) - 128 KB) { + U32 const maxOffset = (U32)dictContentSize + 128 KB; /* The maximum offset that must be supported */ + offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */ + } + /* All offset values <= dictContentSize + 128 KB must be representable for a valid table */ + bs->entropy.fse.offcode_repeatMode = ZSTD_dictNCountRepeat(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)); + + /* All repCodes must be <= dictContentSize and != 0 */ + { U32 u; + for (u=0; u<3; u++) { + RETURN_ERROR_IF(bs->rep[u] == 0, dictionary_corrupted, ""); + RETURN_ERROR_IF(bs->rep[u] > dictContentSize, dictionary_corrupted, ""); + } } } + + return dictPtr - (const BYTE*)dict; +} + +/* Dictionary format : + * See : + * https://github.com/facebook/zstd/blob/release/doc/zstd_compression_format.md#dictionary-format + */ +/*! ZSTD_loadZstdDictionary() : + * @return : dictID, or an error code + * assumptions : magic number supposed already checked + * dictSize supposed >= 8 + */ +static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs, + ZSTD_matchState_t* ms, + ZSTD_cwksp* ws, + ZSTD_CCtx_params const* params, + const void* dict, size_t dictSize, + ZSTD_dictTableLoadMethod_e dtlm, + void* workspace) +{ + const BYTE* dictPtr = (const BYTE*)dict; + const BYTE* const dictEnd = dictPtr + dictSize; + size_t dictID; + size_t eSize; + + ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<= 8); + assert(MEM_readLE32(dictPtr) == ZSTD_MAGIC_DICTIONARY); + + dictID = params->fParams.noDictIDFlag ? 0 : MEM_readLE32(dictPtr + 4 /* skip magic number */ ); + eSize = ZSTD_loadCEntropy(bs, workspace, dict, dictSize); + FORWARD_IF_ERROR(eSize, "ZSTD_loadCEntropy failed"); + dictPtr += eSize; + + { + size_t const dictContentSize = (size_t)(dictEnd - dictPtr); + FORWARD_IF_ERROR(ZSTD_loadDictionaryContent( + ms, NULL, ws, params, dictPtr, dictContentSize, dtlm), ""); + } + return dictID; +} + +/* ZSTD_compress_insertDictionary() : +* @return : dictID, or an error code */ +static size_t +ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs, + ZSTD_matchState_t* ms, + ldmState_t* ls, + ZSTD_cwksp* ws, + const ZSTD_CCtx_params* params, + const void* dict, size_t dictSize, + ZSTD_dictContentType_e dictContentType, + ZSTD_dictTableLoadMethod_e dtlm, + void* workspace) +{ + DEBUGLOG(4, "ZSTD_compress_insertDictionary (dictSize=%u)", (U32)dictSize); + if ((dict==NULL) || (dictSize<8)) { + RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, ""); + return 0; + } + + ZSTD_reset_compressedBlockState(bs); + + /* dict restricted modes */ + if (dictContentType == ZSTD_dct_rawContent) + return ZSTD_loadDictionaryContent(ms, ls, ws, params, dict, dictSize, dtlm); + + if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) { + if (dictContentType == ZSTD_dct_auto) { + DEBUGLOG(4, "raw content dictionary detected"); + return ZSTD_loadDictionaryContent( + ms, ls, ws, params, dict, dictSize, dtlm); + } + RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong, ""); + assert(0); /* impossible */ + } + + /* dict as full zstd dictionary */ + return ZSTD_loadZstdDictionary( + bs, ms, ws, params, dict, dictSize, dtlm, workspace); +} + +#define ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF (128 KB) +#define ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER (6ULL) + +/*! ZSTD_compressBegin_internal() : + * @return : 0, or an error code */ +static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, + const void* dict, size_t dictSize, + ZSTD_dictContentType_e dictContentType, + ZSTD_dictTableLoadMethod_e dtlm, + const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, U64 pledgedSrcSize, + ZSTD_buffered_policy_e zbuff) +{ + DEBUGLOG(4, "ZSTD_compressBegin_internal: wlog=%u", params->cParams.windowLog); + /* params are supposed to be fully validated at this point */ + assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams))); + assert(!((dict) && (cdict))); /* either dict or cdict, not both */ + if ( (cdict) + && (cdict->dictContentSize > 0) + && ( pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF + || pledgedSrcSize < cdict->dictContentSize * ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER + || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN + || cdict->compressionLevel == 0) + && (params->attachDictPref != ZSTD_dictForceLoad) ) { + return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff); + } + + FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, *params, pledgedSrcSize, + ZSTDcrp_makeClean, zbuff) , ""); + { size_t const dictID = cdict ? + ZSTD_compress_insertDictionary( + cctx->blockState.prevCBlock, &cctx->blockState.matchState, + &cctx->ldmState, &cctx->workspace, &cctx->appliedParams, cdict->dictContent, + cdict->dictContentSize, cdict->dictContentType, dtlm, + cctx->entropyWorkspace) + : ZSTD_compress_insertDictionary( + cctx->blockState.prevCBlock, &cctx->blockState.matchState, + &cctx->ldmState, &cctx->workspace, &cctx->appliedParams, dict, dictSize, + dictContentType, dtlm, cctx->entropyWorkspace); + FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed"); + assert(dictID <= UINT_MAX); + cctx->dictID = (U32)dictID; + cctx->dictContentSize = cdict ? cdict->dictContentSize : dictSize; + } + return 0; +} + +size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, + const void* dict, size_t dictSize, + ZSTD_dictContentType_e dictContentType, + ZSTD_dictTableLoadMethod_e dtlm, + const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, + unsigned long long pledgedSrcSize) +{ + DEBUGLOG(4, "ZSTD_compressBegin_advanced_internal: wlog=%u", params->cParams.windowLog); + /* compression parameters verification and optimization */ + FORWARD_IF_ERROR( ZSTD_checkCParams(params->cParams) , ""); + return ZSTD_compressBegin_internal(cctx, + dict, dictSize, dictContentType, dtlm, + cdict, + params, pledgedSrcSize, + ZSTDb_not_buffered); +} + +/*! ZSTD_compressBegin_advanced() : +* @return : 0, or an error code */ +size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, + const void* dict, size_t dictSize, + ZSTD_parameters params, unsigned long long pledgedSrcSize) +{ + ZSTD_CCtx_params cctxParams; + ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, ZSTD_NO_CLEVEL); + return ZSTD_compressBegin_advanced_internal(cctx, + dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, + NULL /*cdict*/, + &cctxParams, pledgedSrcSize); +} + +size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel) +{ + ZSTD_CCtx_params cctxParams; + { + ZSTD_parameters const params = ZSTD_getParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_noAttachDict); + ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel); + } + DEBUGLOG(4, "ZSTD_compressBegin_usingDict (dictSize=%u)", (unsigned)dictSize); + return ZSTD_compressBegin_internal(cctx, dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL, + &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, ZSTDb_not_buffered); +} + +size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel) +{ + return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); +} + + +/*! ZSTD_writeEpilogue() : +* Ends a frame. +* @return : nb of bytes written into dst (or an error code) */ +static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity) +{ + BYTE* const ostart = (BYTE*)dst; + BYTE* op = ostart; + size_t fhSize = 0; + + DEBUGLOG(4, "ZSTD_writeEpilogue"); + RETURN_ERROR_IF(cctx->stage == ZSTDcs_created, stage_wrong, "init missing"); + + /* special case : empty frame */ + if (cctx->stage == ZSTDcs_init) { + fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, &cctx->appliedParams, 0, 0); + FORWARD_IF_ERROR(fhSize, "ZSTD_writeFrameHeader failed"); + dstCapacity -= fhSize; + op += fhSize; + cctx->stage = ZSTDcs_ongoing; + } + + if (cctx->stage != ZSTDcs_ending) { + /* write one last empty block, make it the "last" block */ + U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1) + 0; + RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for epilogue"); + MEM_writeLE32(op, cBlockHeader24); + op += ZSTD_blockHeaderSize; + dstCapacity -= ZSTD_blockHeaderSize; + } + + if (cctx->appliedParams.fParams.checksumFlag) { + U32 const checksum = (U32) xxh64_digest(&cctx->xxhState); + RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for checksum"); + DEBUGLOG(4, "ZSTD_writeEpilogue: write checksum : %08X", (unsigned)checksum); + MEM_writeLE32(op, checksum); + op += 4; + } + + cctx->stage = ZSTDcs_created; /* return to "created but no init" status */ + return op-ostart; +} + +void ZSTD_CCtx_trace(ZSTD_CCtx* cctx, size_t extraCSize) +{ + (void)cctx; + (void)extraCSize; +} + +size_t ZSTD_compressEnd (ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize) +{ + size_t endResult; + size_t const cSize = ZSTD_compressContinue_internal(cctx, + dst, dstCapacity, src, srcSize, + 1 /* frame mode */, 1 /* last chunk */); + FORWARD_IF_ERROR(cSize, "ZSTD_compressContinue_internal failed"); + endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize); + FORWARD_IF_ERROR(endResult, "ZSTD_writeEpilogue failed"); + assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0)); + if (cctx->pledgedSrcSizePlusOne != 0) { /* control src size */ + ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1); + DEBUGLOG(4, "end of frame : controlling src size"); + RETURN_ERROR_IF( + cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1, + srcSize_wrong, + "error : pledgedSrcSize = %u, while realSrcSize = %u", + (unsigned)cctx->pledgedSrcSizePlusOne-1, + (unsigned)cctx->consumedSrcSize); + } + ZSTD_CCtx_trace(cctx, endResult); + return cSize + endResult; +} + +size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + ZSTD_parameters params) +{ + ZSTD_CCtx_params cctxParams; + DEBUGLOG(4, "ZSTD_compress_advanced"); + FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams), ""); + ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, ZSTD_NO_CLEVEL); + return ZSTD_compress_advanced_internal(cctx, + dst, dstCapacity, + src, srcSize, + dict, dictSize, + &cctxParams); +} + +/* Internal */ +size_t ZSTD_compress_advanced_internal( + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + const ZSTD_CCtx_params* params) +{ + DEBUGLOG(4, "ZSTD_compress_advanced_internal (srcSize:%u)", (unsigned)srcSize); + FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx, + dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL, + params, srcSize, ZSTDb_not_buffered) , ""); + return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); +} + +size_t ZSTD_compress_usingDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict, size_t dictSize, + int compressionLevel) +{ + ZSTD_CCtx_params cctxParams; + { + ZSTD_parameters const params = ZSTD_getParams_internal(compressionLevel, srcSize, dict ? dictSize : 0, ZSTD_cpm_noAttachDict); + assert(params.fParams.contentSizeFlag == 1); + ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT: compressionLevel); + } + DEBUGLOG(4, "ZSTD_compress_usingDict (srcSize=%u)", (unsigned)srcSize); + return ZSTD_compress_advanced_internal(cctx, dst, dstCapacity, src, srcSize, dict, dictSize, &cctxParams); +} + +size_t ZSTD_compressCCtx(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel) +{ + DEBUGLOG(4, "ZSTD_compressCCtx (srcSize=%u)", (unsigned)srcSize); + assert(cctx != NULL); + return ZSTD_compress_usingDict(cctx, dst, dstCapacity, src, srcSize, NULL, 0, compressionLevel); +} + +size_t ZSTD_compress(void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel) +{ + size_t result; + ZSTD_CCtx* cctx = ZSTD_createCCtx(); + RETURN_ERROR_IF(!cctx, memory_allocation, "ZSTD_createCCtx failed"); + result = ZSTD_compressCCtx(cctx, dst, dstCapacity, src, srcSize, compressionLevel); + ZSTD_freeCCtx(cctx); + return result; +} + + +/* ===== Dictionary API ===== */ + +/*! ZSTD_estimateCDictSize_advanced() : + * Estimate amount of memory that will be needed to create a dictionary with following arguments */ +size_t ZSTD_estimateCDictSize_advanced( + size_t dictSize, ZSTD_compressionParameters cParams, + ZSTD_dictLoadMethod_e dictLoadMethod) +{ + DEBUGLOG(5, "sizeof(ZSTD_CDict) : %u", (unsigned)sizeof(ZSTD_CDict)); + return ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict)) + + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE) + + ZSTD_sizeof_matchState(&cParams, /* forCCtx */ 0) + + (dictLoadMethod == ZSTD_dlm_byRef ? 0 + : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void *)))); +} + +size_t ZSTD_estimateCDictSize(size_t dictSize, int compressionLevel) +{ + ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); + return ZSTD_estimateCDictSize_advanced(dictSize, cParams, ZSTD_dlm_byCopy); +} + +size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict) +{ + if (cdict==NULL) return 0; /* support sizeof on NULL */ + DEBUGLOG(5, "sizeof(*cdict) : %u", (unsigned)sizeof(*cdict)); + /* cdict may be in the workspace */ + return (cdict->workspace.workspace == cdict ? 0 : sizeof(*cdict)) + + ZSTD_cwksp_sizeof(&cdict->workspace); +} + +static size_t ZSTD_initCDict_internal( + ZSTD_CDict* cdict, + const void* dictBuffer, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_CCtx_params params) +{ + DEBUGLOG(3, "ZSTD_initCDict_internal (dictContentType:%u)", (unsigned)dictContentType); + assert(!ZSTD_checkCParams(params.cParams)); + cdict->matchState.cParams = params.cParams; + cdict->matchState.dedicatedDictSearch = params.enableDedicatedDictSearch; + if (cdict->matchState.dedicatedDictSearch && dictSize > ZSTD_CHUNKSIZE_MAX) { + cdict->matchState.dedicatedDictSearch = 0; + } + if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dictBuffer) || (!dictSize)) { + cdict->dictContent = dictBuffer; + } else { + void *internalBuffer = ZSTD_cwksp_reserve_object(&cdict->workspace, ZSTD_cwksp_align(dictSize, sizeof(void*))); + RETURN_ERROR_IF(!internalBuffer, memory_allocation, "NULL pointer!"); + cdict->dictContent = internalBuffer; + ZSTD_memcpy(internalBuffer, dictBuffer, dictSize); + } + cdict->dictContentSize = dictSize; + cdict->dictContentType = dictContentType; + + cdict->entropyWorkspace = (U32*)ZSTD_cwksp_reserve_object(&cdict->workspace, HUF_WORKSPACE_SIZE); + + + /* Reset the state to no dictionary */ + ZSTD_reset_compressedBlockState(&cdict->cBlockState); + FORWARD_IF_ERROR(ZSTD_reset_matchState( + &cdict->matchState, + &cdict->workspace, + ¶ms.cParams, + ZSTDcrp_makeClean, + ZSTDirp_reset, + ZSTD_resetTarget_CDict), ""); + /* (Maybe) load the dictionary + * Skips loading the dictionary if it is < 8 bytes. + */ + { params.compressionLevel = ZSTD_CLEVEL_DEFAULT; + params.fParams.contentSizeFlag = 1; + { size_t const dictID = ZSTD_compress_insertDictionary( + &cdict->cBlockState, &cdict->matchState, NULL, &cdict->workspace, + ¶ms, cdict->dictContent, cdict->dictContentSize, + dictContentType, ZSTD_dtlm_full, cdict->entropyWorkspace); + FORWARD_IF_ERROR(dictID, "ZSTD_compress_insertDictionary failed"); + assert(dictID <= (size_t)(U32)-1); + cdict->dictID = (U32)dictID; + } + } + + return 0; +} + +static ZSTD_CDict* ZSTD_createCDict_advanced_internal(size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_compressionParameters cParams, ZSTD_customMem customMem) +{ + if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; + + { size_t const workspaceSize = + ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict)) + + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE) + + ZSTD_sizeof_matchState(&cParams, /* forCCtx */ 0) + + (dictLoadMethod == ZSTD_dlm_byRef ? 0 + : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void*)))); + void* const workspace = ZSTD_customMalloc(workspaceSize, customMem); + ZSTD_cwksp ws; + ZSTD_CDict* cdict; + + if (!workspace) { + ZSTD_customFree(workspace, customMem); + return NULL; + } + + ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_dynamic_alloc); + + cdict = (ZSTD_CDict*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CDict)); + assert(cdict != NULL); + ZSTD_cwksp_move(&cdict->workspace, &ws); + cdict->customMem = customMem; + cdict->compressionLevel = ZSTD_NO_CLEVEL; /* signals advanced API usage */ + + return cdict; + } +} + +ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams, + ZSTD_customMem customMem) +{ + ZSTD_CCtx_params cctxParams; + ZSTD_memset(&cctxParams, 0, sizeof(cctxParams)); + ZSTD_CCtxParams_init(&cctxParams, 0); + cctxParams.cParams = cParams; + cctxParams.customMem = customMem; + return ZSTD_createCDict_advanced2( + dictBuffer, dictSize, + dictLoadMethod, dictContentType, + &cctxParams, customMem); +} + +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced2( + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + const ZSTD_CCtx_params* originalCctxParams, + ZSTD_customMem customMem) +{ + ZSTD_CCtx_params cctxParams = *originalCctxParams; + ZSTD_compressionParameters cParams; + ZSTD_CDict* cdict; + + DEBUGLOG(3, "ZSTD_createCDict_advanced2, mode %u", (unsigned)dictContentType); + if (!customMem.customAlloc ^ !customMem.customFree) return NULL; + + if (cctxParams.enableDedicatedDictSearch) { + cParams = ZSTD_dedicatedDictSearch_getCParams( + cctxParams.compressionLevel, dictSize); + ZSTD_overrideCParams(&cParams, &cctxParams.cParams); + } else { + cParams = ZSTD_getCParamsFromCCtxParams( + &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); + } + + if (!ZSTD_dedicatedDictSearch_isSupported(&cParams)) { + /* Fall back to non-DDSS params */ + cctxParams.enableDedicatedDictSearch = 0; + cParams = ZSTD_getCParamsFromCCtxParams( + &cctxParams, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); + } + + cctxParams.cParams = cParams; + + cdict = ZSTD_createCDict_advanced_internal(dictSize, + dictLoadMethod, cctxParams.cParams, + customMem); + + if (ZSTD_isError( ZSTD_initCDict_internal(cdict, + dict, dictSize, + dictLoadMethod, dictContentType, + cctxParams) )) { + ZSTD_freeCDict(cdict); + return NULL; + } + + return cdict; +} + +ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel) +{ + ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); + ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dict, dictSize, + ZSTD_dlm_byCopy, ZSTD_dct_auto, + cParams, ZSTD_defaultCMem); + if (cdict) + cdict->compressionLevel = (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel; + return cdict; +} + +ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel) +{ + ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN, dictSize, ZSTD_cpm_createCDict); + ZSTD_CDict* const cdict = ZSTD_createCDict_advanced(dict, dictSize, + ZSTD_dlm_byRef, ZSTD_dct_auto, + cParams, ZSTD_defaultCMem); + if (cdict) + cdict->compressionLevel = (compressionLevel == 0) ? ZSTD_CLEVEL_DEFAULT : compressionLevel; + return cdict; +} + +size_t ZSTD_freeCDict(ZSTD_CDict* cdict) +{ + if (cdict==NULL) return 0; /* support free on NULL */ + { ZSTD_customMem const cMem = cdict->customMem; + int cdictInWorkspace = ZSTD_cwksp_owns_buffer(&cdict->workspace, cdict); + ZSTD_cwksp_free(&cdict->workspace, cMem); + if (!cdictInWorkspace) { + ZSTD_customFree(cdict, cMem); + } + return 0; + } +} + +/*! ZSTD_initStaticCDict_advanced() : + * Generate a digested dictionary in provided memory area. + * workspace: The memory area to emplace the dictionary into. + * Provided pointer must 8-bytes aligned. + * It must outlive dictionary usage. + * workspaceSize: Use ZSTD_estimateCDictSize() + * to determine how large workspace must be. + * cParams : use ZSTD_getCParams() to transform a compression level + * into its relevants cParams. + * @return : pointer to ZSTD_CDict*, or NULL if error (size too small) + * Note : there is no corresponding "free" function. + * Since workspace was allocated externally, it must be freed externally. + */ +const ZSTD_CDict* ZSTD_initStaticCDict( + void* workspace, size_t workspaceSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_compressionParameters cParams) +{ + size_t const matchStateSize = ZSTD_sizeof_matchState(&cParams, /* forCCtx */ 0); + size_t const neededSize = ZSTD_cwksp_alloc_size(sizeof(ZSTD_CDict)) + + (dictLoadMethod == ZSTD_dlm_byRef ? 0 + : ZSTD_cwksp_alloc_size(ZSTD_cwksp_align(dictSize, sizeof(void*)))) + + ZSTD_cwksp_alloc_size(HUF_WORKSPACE_SIZE) + + matchStateSize; + ZSTD_CDict* cdict; + ZSTD_CCtx_params params; + + if ((size_t)workspace & 7) return NULL; /* 8-aligned */ + + { + ZSTD_cwksp ws; + ZSTD_cwksp_init(&ws, workspace, workspaceSize, ZSTD_cwksp_static_alloc); + cdict = (ZSTD_CDict*)ZSTD_cwksp_reserve_object(&ws, sizeof(ZSTD_CDict)); + if (cdict == NULL) return NULL; + ZSTD_cwksp_move(&cdict->workspace, &ws); + } + + DEBUGLOG(4, "(workspaceSize < neededSize) : (%u < %u) => %u", + (unsigned)workspaceSize, (unsigned)neededSize, (unsigned)(workspaceSize < neededSize)); + if (workspaceSize < neededSize) return NULL; + + ZSTD_CCtxParams_init(¶ms, 0); + params.cParams = cParams; + + if (ZSTD_isError( ZSTD_initCDict_internal(cdict, + dict, dictSize, + dictLoadMethod, dictContentType, + params) )) + return NULL; + + return cdict; +} + +ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict) +{ + assert(cdict != NULL); + return cdict->matchState.cParams; +} + +/*! ZSTD_getDictID_fromCDict() : + * Provides the dictID of the dictionary loaded into `cdict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +unsigned ZSTD_getDictID_fromCDict(const ZSTD_CDict* cdict) +{ + if (cdict==NULL) return 0; + return cdict->dictID; +} + + +/* ZSTD_compressBegin_usingCDict_advanced() : + * cdict must be != NULL */ +size_t ZSTD_compressBegin_usingCDict_advanced( + ZSTD_CCtx* const cctx, const ZSTD_CDict* const cdict, + ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize) +{ + ZSTD_CCtx_params cctxParams; + DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced"); + RETURN_ERROR_IF(cdict==NULL, dictionary_wrong, "NULL pointer!"); + /* Initialize the cctxParams from the cdict */ + { + ZSTD_parameters params; + params.fParams = fParams; + params.cParams = ( pledgedSrcSize < ZSTD_USE_CDICT_PARAMS_SRCSIZE_CUTOFF + || pledgedSrcSize < cdict->dictContentSize * ZSTD_USE_CDICT_PARAMS_DICTSIZE_MULTIPLIER + || pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN + || cdict->compressionLevel == 0 ) ? + ZSTD_getCParamsFromCDict(cdict) + : ZSTD_getCParams(cdict->compressionLevel, + pledgedSrcSize, + cdict->dictContentSize); + ZSTD_CCtxParams_init_internal(&cctxParams, ¶ms, cdict->compressionLevel); + } + /* Increase window log to fit the entire dictionary and source if the + * source size is known. Limit the increase to 19, which is the + * window log for compression level 1 with the largest source size. + */ + if (pledgedSrcSize != ZSTD_CONTENTSIZE_UNKNOWN) { + U32 const limitedSrcSize = (U32)MIN(pledgedSrcSize, 1U << 19); + U32 const limitedSrcLog = limitedSrcSize > 1 ? ZSTD_highbit32(limitedSrcSize - 1) + 1 : 1; + cctxParams.cParams.windowLog = MAX(cctxParams.cParams.windowLog, limitedSrcLog); + } + return ZSTD_compressBegin_internal(cctx, + NULL, 0, ZSTD_dct_auto, ZSTD_dtlm_fast, + cdict, + &cctxParams, pledgedSrcSize, + ZSTDb_not_buffered); +} + +/* ZSTD_compressBegin_usingCDict() : + * pledgedSrcSize=0 means "unknown" + * if pledgedSrcSize>0, it will enable contentSizeFlag */ +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict) +{ + ZSTD_frameParameters const fParams = { 0 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; + DEBUGLOG(4, "ZSTD_compressBegin_usingCDict : dictIDFlag == %u", !fParams.noDictIDFlag); + return ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN); +} + +size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict, ZSTD_frameParameters fParams) +{ + FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize), ""); /* will check if cdict != NULL */ + return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize); +} + +/*! ZSTD_compress_usingCDict() : + * Compression using a digested Dictionary. + * Faster startup than ZSTD_compress_usingDict(), recommended when same dictionary is used multiple times. + * Note that compression parameters are decided at CDict creation time + * while frame parameters are hardcoded */ +size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_CDict* cdict) +{ + ZSTD_frameParameters const fParams = { 1 /*content*/, 0 /*checksum*/, 0 /*noDictID*/ }; + return ZSTD_compress_usingCDict_advanced(cctx, dst, dstCapacity, src, srcSize, cdict, fParams); +} + + + +/* ****************************************************************** +* Streaming +********************************************************************/ + +ZSTD_CStream* ZSTD_createCStream(void) +{ + DEBUGLOG(3, "ZSTD_createCStream"); + return ZSTD_createCStream_advanced(ZSTD_defaultCMem); +} + +ZSTD_CStream* ZSTD_initStaticCStream(void *workspace, size_t workspaceSize) +{ + return ZSTD_initStaticCCtx(workspace, workspaceSize); +} + +ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem) +{ /* CStream and CCtx are now same object */ + return ZSTD_createCCtx_advanced(customMem); +} + +size_t ZSTD_freeCStream(ZSTD_CStream* zcs) +{ + return ZSTD_freeCCtx(zcs); /* same object */ +} + + + +/*====== Initialization ======*/ + +size_t ZSTD_CStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX; } + +size_t ZSTD_CStreamOutSize(void) +{ + return ZSTD_compressBound(ZSTD_BLOCKSIZE_MAX) + ZSTD_blockHeaderSize + 4 /* 32-bits hash */ ; +} + +static ZSTD_cParamMode_e ZSTD_getCParamMode(ZSTD_CDict const* cdict, ZSTD_CCtx_params const* params, U64 pledgedSrcSize) +{ + if (cdict != NULL && ZSTD_shouldAttachDict(cdict, params, pledgedSrcSize)) + return ZSTD_cpm_attachDict; + else + return ZSTD_cpm_noAttachDict; +} + +/* ZSTD_resetCStream(): + * pledgedSrcSize == 0 means "unknown" */ +size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss) +{ + /* temporary : 0 interpreted as "unknown" during transition period. + * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. + * 0 will be interpreted as "empty" in the future. + */ + U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; + DEBUGLOG(4, "ZSTD_resetCStream: pledgedSrcSize = %u", (unsigned)pledgedSrcSize); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); + return 0; +} + +/*! ZSTD_initCStream_internal() : + * Note : for lib/compress only. Used by zstdmt_compress.c. + * Assumption 1 : params are valid + * Assumption 2 : either dict, or cdict, is defined, not both */ +size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, + unsigned long long pledgedSrcSize) +{ + DEBUGLOG(4, "ZSTD_initCStream_internal"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); + assert(!ZSTD_isError(ZSTD_checkCParams(params->cParams))); + zcs->requestedParams = *params; + assert(!((dict) && (cdict))); /* either dict or cdict, not both */ + if (dict) { + FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , ""); + } else { + /* Dictionary is cleared if !cdict */ + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , ""); + } + return 0; +} + +/* ZSTD_initCStream_usingCDict_advanced() : + * same as ZSTD_initCStream_usingCDict(), with control over frame parameters */ +size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, + const ZSTD_CDict* cdict, + ZSTD_frameParameters fParams, + unsigned long long pledgedSrcSize) +{ + DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); + zcs->requestedParams.fParams = fParams; + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , ""); + return 0; +} + +/* note : cdict must outlive compression session */ +size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict) +{ + DEBUGLOG(4, "ZSTD_initCStream_usingCDict"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) , ""); + return 0; +} + + +/* ZSTD_initCStream_advanced() : + * pledgedSrcSize must be exact. + * if srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. + * dict is loaded with default parameters ZSTD_dct_auto and ZSTD_dlm_byCopy. */ +size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + ZSTD_parameters params, unsigned long long pss) +{ + /* for compatibility with older programs relying on this behavior. + * Users should now specify ZSTD_CONTENTSIZE_UNKNOWN. + * This line will be removed in the future. + */ + U64 const pledgedSrcSize = (pss==0 && params.fParams.contentSizeFlag==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; + DEBUGLOG(4, "ZSTD_initCStream_advanced"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); + FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) , ""); + ZSTD_CCtxParams_setZstdParams(&zcs->requestedParams, ¶ms); + FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , ""); + return 0; +} + +size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel) +{ + DEBUGLOG(4, "ZSTD_initCStream_usingDict"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) , ""); + return 0; +} + +size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss) +{ + /* temporary : 0 interpreted as "unknown" during transition period. + * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. + * 0 will be interpreted as "empty" in the future. + */ + U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss; + DEBUGLOG(4, "ZSTD_initCStream_srcSize"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) , ""); + return 0; +} + +size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel) +{ + DEBUGLOG(4, "ZSTD_initCStream"); + FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) , ""); + FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) , ""); + return 0; +} + +/*====== Compression ======*/ + +static size_t ZSTD_nextInputSizeHint(const ZSTD_CCtx* cctx) +{ + size_t hintInSize = cctx->inBuffTarget - cctx->inBuffPos; + if (hintInSize==0) hintInSize = cctx->blockSize; + return hintInSize; +} + +/* ZSTD_compressStream_generic(): + * internal function for all *compressStream*() variants + * non-static, because can be called from zstdmt_compress.c + * @return : hint size for next input */ +static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective const flushMode) +{ + const char* const istart = (const char*)input->src; + const char* const iend = input->size != 0 ? istart + input->size : istart; + const char* ip = input->pos != 0 ? istart + input->pos : istart; + char* const ostart = (char*)output->dst; + char* const oend = output->size != 0 ? ostart + output->size : ostart; + char* op = output->pos != 0 ? ostart + output->pos : ostart; + U32 someMoreWork = 1; + + /* check expectations */ + DEBUGLOG(5, "ZSTD_compressStream_generic, flush=%u", (unsigned)flushMode); + if (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered) { + assert(zcs->inBuff != NULL); + assert(zcs->inBuffSize > 0); + } + if (zcs->appliedParams.outBufferMode == ZSTD_bm_buffered) { + assert(zcs->outBuff != NULL); + assert(zcs->outBuffSize > 0); + } + assert(output->pos <= output->size); + assert(input->pos <= input->size); + assert((U32)flushMode <= (U32)ZSTD_e_end); + + while (someMoreWork) { + switch(zcs->streamStage) + { + case zcss_init: + RETURN_ERROR(init_missing, "call ZSTD_initCStream() first!"); + + case zcss_load: + if ( (flushMode == ZSTD_e_end) + && ( (size_t)(oend-op) >= ZSTD_compressBound(iend-ip) /* Enough output space */ + || zcs->appliedParams.outBufferMode == ZSTD_bm_stable) /* OR we are allowed to return dstSizeTooSmall */ + && (zcs->inBuffPos == 0) ) { + /* shortcut to compression pass directly into output buffer */ + size_t const cSize = ZSTD_compressEnd(zcs, + op, oend-op, ip, iend-ip); + DEBUGLOG(4, "ZSTD_compressEnd : cSize=%u", (unsigned)cSize); + FORWARD_IF_ERROR(cSize, "ZSTD_compressEnd failed"); + ip = iend; + op += cSize; + zcs->frameEnded = 1; + ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + someMoreWork = 0; break; + } + /* complete loading into inBuffer in buffered mode */ + if (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered) { + size_t const toLoad = zcs->inBuffTarget - zcs->inBuffPos; + size_t const loaded = ZSTD_limitCopy( + zcs->inBuff + zcs->inBuffPos, toLoad, + ip, iend-ip); + zcs->inBuffPos += loaded; + if (loaded != 0) + ip += loaded; + if ( (flushMode == ZSTD_e_continue) + && (zcs->inBuffPos < zcs->inBuffTarget) ) { + /* not enough input to fill full block : stop here */ + someMoreWork = 0; break; + } + if ( (flushMode == ZSTD_e_flush) + && (zcs->inBuffPos == zcs->inToCompress) ) { + /* empty */ + someMoreWork = 0; break; + } + } + /* compress current block (note : this stage cannot be stopped in the middle) */ + DEBUGLOG(5, "stream compression stage (flushMode==%u)", flushMode); + { int const inputBuffered = (zcs->appliedParams.inBufferMode == ZSTD_bm_buffered); + void* cDst; + size_t cSize; + size_t oSize = oend-op; + size_t const iSize = inputBuffered + ? zcs->inBuffPos - zcs->inToCompress + : MIN((size_t)(iend - ip), zcs->blockSize); + if (oSize >= ZSTD_compressBound(iSize) || zcs->appliedParams.outBufferMode == ZSTD_bm_stable) + cDst = op; /* compress into output buffer, to skip flush stage */ + else + cDst = zcs->outBuff, oSize = zcs->outBuffSize; + if (inputBuffered) { + unsigned const lastBlock = (flushMode == ZSTD_e_end) && (ip==iend); + cSize = lastBlock ? + ZSTD_compressEnd(zcs, cDst, oSize, + zcs->inBuff + zcs->inToCompress, iSize) : + ZSTD_compressContinue(zcs, cDst, oSize, + zcs->inBuff + zcs->inToCompress, iSize); + FORWARD_IF_ERROR(cSize, "%s", lastBlock ? "ZSTD_compressEnd failed" : "ZSTD_compressContinue failed"); + zcs->frameEnded = lastBlock; + /* prepare next block */ + zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize; + if (zcs->inBuffTarget > zcs->inBuffSize) + zcs->inBuffPos = 0, zcs->inBuffTarget = zcs->blockSize; + DEBUGLOG(5, "inBuffTarget:%u / inBuffSize:%u", + (unsigned)zcs->inBuffTarget, (unsigned)zcs->inBuffSize); + if (!lastBlock) + assert(zcs->inBuffTarget <= zcs->inBuffSize); + zcs->inToCompress = zcs->inBuffPos; + } else { + unsigned const lastBlock = (ip + iSize == iend); + assert(flushMode == ZSTD_e_end /* Already validated */); + cSize = lastBlock ? + ZSTD_compressEnd(zcs, cDst, oSize, ip, iSize) : + ZSTD_compressContinue(zcs, cDst, oSize, ip, iSize); + /* Consume the input prior to error checking to mirror buffered mode. */ + if (iSize > 0) + ip += iSize; + FORWARD_IF_ERROR(cSize, "%s", lastBlock ? "ZSTD_compressEnd failed" : "ZSTD_compressContinue failed"); + zcs->frameEnded = lastBlock; + if (lastBlock) + assert(ip == iend); + } + if (cDst == op) { /* no need to flush */ + op += cSize; + if (zcs->frameEnded) { + DEBUGLOG(5, "Frame completed directly in outBuffer"); + someMoreWork = 0; + ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + } + break; + } + zcs->outBuffContentSize = cSize; + zcs->outBuffFlushedSize = 0; + zcs->streamStage = zcss_flush; /* pass-through to flush stage */ + } + ZSTD_FALLTHROUGH; + case zcss_flush: + DEBUGLOG(5, "flush stage"); + assert(zcs->appliedParams.outBufferMode == ZSTD_bm_buffered); + { size_t const toFlush = zcs->outBuffContentSize - zcs->outBuffFlushedSize; + size_t const flushed = ZSTD_limitCopy(op, (size_t)(oend-op), + zcs->outBuff + zcs->outBuffFlushedSize, toFlush); + DEBUGLOG(5, "toFlush: %u into %u ==> flushed: %u", + (unsigned)toFlush, (unsigned)(oend-op), (unsigned)flushed); + if (flushed) + op += flushed; + zcs->outBuffFlushedSize += flushed; + if (toFlush!=flushed) { + /* flush not fully completed, presumably because dst is too small */ + assert(op==oend); + someMoreWork = 0; + break; + } + zcs->outBuffContentSize = zcs->outBuffFlushedSize = 0; + if (zcs->frameEnded) { + DEBUGLOG(5, "Frame completed on flush"); + someMoreWork = 0; + ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only); + break; + } + zcs->streamStage = zcss_load; + break; + } + + default: /* impossible */ + assert(0); + } + } + + input->pos = ip - istart; + output->pos = op - ostart; + if (zcs->frameEnded) return 0; + return ZSTD_nextInputSizeHint(zcs); +} + +static size_t ZSTD_nextInputSizeHint_MTorST(const ZSTD_CCtx* cctx) +{ + return ZSTD_nextInputSizeHint(cctx); + +} + +size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input) +{ + FORWARD_IF_ERROR( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) , ""); + return ZSTD_nextInputSizeHint_MTorST(zcs); +} + +/* After a compression call set the expected input/output buffer. + * This is validated at the start of the next compression call. + */ +static void ZSTD_setBufferExpectations(ZSTD_CCtx* cctx, ZSTD_outBuffer const* output, ZSTD_inBuffer const* input) +{ + if (cctx->appliedParams.inBufferMode == ZSTD_bm_stable) { + cctx->expectedInBuffer = *input; + } + if (cctx->appliedParams.outBufferMode == ZSTD_bm_stable) { + cctx->expectedOutBufferSize = output->size - output->pos; + } +} + +/* Validate that the input/output buffers match the expectations set by + * ZSTD_setBufferExpectations. + */ +static size_t ZSTD_checkBufferStability(ZSTD_CCtx const* cctx, + ZSTD_outBuffer const* output, + ZSTD_inBuffer const* input, + ZSTD_EndDirective endOp) +{ + if (cctx->appliedParams.inBufferMode == ZSTD_bm_stable) { + ZSTD_inBuffer const expect = cctx->expectedInBuffer; + if (expect.src != input->src || expect.pos != input->pos || expect.size != input->size) + RETURN_ERROR(srcBuffer_wrong, "ZSTD_c_stableInBuffer enabled but input differs!"); + if (endOp != ZSTD_e_end) + RETURN_ERROR(srcBuffer_wrong, "ZSTD_c_stableInBuffer can only be used with ZSTD_e_end!"); + } + if (cctx->appliedParams.outBufferMode == ZSTD_bm_stable) { + size_t const outBufferSize = output->size - output->pos; + if (cctx->expectedOutBufferSize != outBufferSize) + RETURN_ERROR(dstBuffer_wrong, "ZSTD_c_stableOutBuffer enabled but output size differs!"); + } + return 0; +} + +static size_t ZSTD_CCtx_init_compressStream2(ZSTD_CCtx* cctx, + ZSTD_EndDirective endOp, + size_t inSize) { + ZSTD_CCtx_params params = cctx->requestedParams; + ZSTD_prefixDict const prefixDict = cctx->prefixDict; + FORWARD_IF_ERROR( ZSTD_initLocalDict(cctx) , ""); /* Init the local dict if present. */ + ZSTD_memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict)); /* single usage */ + assert(prefixDict.dict==NULL || cctx->cdict==NULL); /* only one can be set */ + if (cctx->cdict) + params.compressionLevel = cctx->cdict->compressionLevel; /* let cdict take priority in terms of compression level */ + DEBUGLOG(4, "ZSTD_compressStream2 : transparent init stage"); + if (endOp == ZSTD_e_end) cctx->pledgedSrcSizePlusOne = inSize + 1; /* auto-fix pledgedSrcSize */ + { + size_t const dictSize = prefixDict.dict + ? prefixDict.dictSize + : (cctx->cdict ? cctx->cdict->dictContentSize : 0); + ZSTD_cParamMode_e const mode = ZSTD_getCParamMode(cctx->cdict, ¶ms, cctx->pledgedSrcSizePlusOne - 1); + params.cParams = ZSTD_getCParamsFromCCtxParams( + ¶ms, cctx->pledgedSrcSizePlusOne-1, + dictSize, mode); + } + + if (ZSTD_CParams_shouldEnableLdm(¶ms.cParams)) { + /* Enable LDM by default for optimal parser and window size >= 128MB */ + DEBUGLOG(4, "LDM enabled by default (window size >= 128MB, strategy >= btopt)"); + params.ldmParams.enableLdm = 1; + } + + { U64 const pledgedSrcSize = cctx->pledgedSrcSizePlusOne - 1; + assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams))); + FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx, + prefixDict.dict, prefixDict.dictSize, prefixDict.dictContentType, ZSTD_dtlm_fast, + cctx->cdict, + ¶ms, pledgedSrcSize, + ZSTDb_buffered) , ""); + assert(cctx->appliedParams.nbWorkers == 0); + cctx->inToCompress = 0; + cctx->inBuffPos = 0; + if (cctx->appliedParams.inBufferMode == ZSTD_bm_buffered) { + /* for small input: avoid automatic flush on reaching end of block, since + * it would require to add a 3-bytes null block to end frame + */ + cctx->inBuffTarget = cctx->blockSize + (cctx->blockSize == pledgedSrcSize); + } else { + cctx->inBuffTarget = 0; + } + cctx->outBuffContentSize = cctx->outBuffFlushedSize = 0; + cctx->streamStage = zcss_load; + cctx->frameEnded = 0; + } + return 0; +} + +size_t ZSTD_compressStream2( ZSTD_CCtx* cctx, + ZSTD_outBuffer* output, + ZSTD_inBuffer* input, + ZSTD_EndDirective endOp) +{ + DEBUGLOG(5, "ZSTD_compressStream2, endOp=%u ", (unsigned)endOp); + /* check conditions */ + RETURN_ERROR_IF(output->pos > output->size, dstSize_tooSmall, "invalid output buffer"); + RETURN_ERROR_IF(input->pos > input->size, srcSize_wrong, "invalid input buffer"); + RETURN_ERROR_IF((U32)endOp > (U32)ZSTD_e_end, parameter_outOfBound, "invalid endDirective"); + assert(cctx != NULL); + + /* transparent initialization stage */ + if (cctx->streamStage == zcss_init) { + FORWARD_IF_ERROR(ZSTD_CCtx_init_compressStream2(cctx, endOp, input->size), "CompressStream2 initialization failed"); + ZSTD_setBufferExpectations(cctx, output, input); /* Set initial buffer expectations now that we've initialized */ + } + /* end of transparent initialization stage */ + + FORWARD_IF_ERROR(ZSTD_checkBufferStability(cctx, output, input, endOp), "invalid buffers"); + /* compression stage */ + FORWARD_IF_ERROR( ZSTD_compressStream_generic(cctx, output, input, endOp) , ""); + DEBUGLOG(5, "completed ZSTD_compressStream2"); + ZSTD_setBufferExpectations(cctx, output, input); + return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */ +} + +size_t ZSTD_compressStream2_simpleArgs ( + ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos, + ZSTD_EndDirective endOp) +{ + ZSTD_outBuffer output = { dst, dstCapacity, *dstPos }; + ZSTD_inBuffer input = { src, srcSize, *srcPos }; + /* ZSTD_compressStream2() will check validity of dstPos and srcPos */ + size_t const cErr = ZSTD_compressStream2(cctx, &output, &input, endOp); + *dstPos = output.pos; + *srcPos = input.pos; + return cErr; +} + +size_t ZSTD_compress2(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize) +{ + ZSTD_bufferMode_e const originalInBufferMode = cctx->requestedParams.inBufferMode; + ZSTD_bufferMode_e const originalOutBufferMode = cctx->requestedParams.outBufferMode; + DEBUGLOG(4, "ZSTD_compress2 (srcSize=%u)", (unsigned)srcSize); + ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only); + /* Enable stable input/output buffers. */ + cctx->requestedParams.inBufferMode = ZSTD_bm_stable; + cctx->requestedParams.outBufferMode = ZSTD_bm_stable; + { size_t oPos = 0; + size_t iPos = 0; + size_t const result = ZSTD_compressStream2_simpleArgs(cctx, + dst, dstCapacity, &oPos, + src, srcSize, &iPos, + ZSTD_e_end); + /* Reset to the original values. */ + cctx->requestedParams.inBufferMode = originalInBufferMode; + cctx->requestedParams.outBufferMode = originalOutBufferMode; + FORWARD_IF_ERROR(result, "ZSTD_compressStream2_simpleArgs failed"); + if (result != 0) { /* compression not completed, due to lack of output space */ + assert(oPos == dstCapacity); + RETURN_ERROR(dstSize_tooSmall, ""); + } + assert(iPos == srcSize); /* all input is expected consumed */ + return oPos; + } +} + +typedef struct { + U32 idx; /* Index in array of ZSTD_Sequence */ + U32 posInSequence; /* Position within sequence at idx */ + size_t posInSrc; /* Number of bytes given by sequences provided so far */ +} ZSTD_sequencePosition; + +/* Returns a ZSTD error code if sequence is not valid */ +static size_t ZSTD_validateSequence(U32 offCode, U32 matchLength, + size_t posInSrc, U32 windowLog, size_t dictSize, U32 minMatch) { + size_t offsetBound; + U32 windowSize = 1 << windowLog; + /* posInSrc represents the amount of data the the decoder would decode up to this point. + * As long as the amount of data decoded is less than or equal to window size, offsets may be + * larger than the total length of output decoded in order to reference the dict, even larger than + * window size. After output surpasses windowSize, we're limited to windowSize offsets again. + */ + offsetBound = posInSrc > windowSize ? (size_t)windowSize : posInSrc + (size_t)dictSize; + RETURN_ERROR_IF(offCode > offsetBound + ZSTD_REP_MOVE, corruption_detected, "Offset too large!"); + RETURN_ERROR_IF(matchLength < minMatch, corruption_detected, "Matchlength too small"); + return 0; +} + +/* Returns an offset code, given a sequence's raw offset, the ongoing repcode array, and whether litLength == 0 */ +static U32 ZSTD_finalizeOffCode(U32 rawOffset, const U32 rep[ZSTD_REP_NUM], U32 ll0) { + U32 offCode = rawOffset + ZSTD_REP_MOVE; + U32 repCode = 0; + + if (!ll0 && rawOffset == rep[0]) { + repCode = 1; + } else if (rawOffset == rep[1]) { + repCode = 2 - ll0; + } else if (rawOffset == rep[2]) { + repCode = 3 - ll0; + } else if (ll0 && rawOffset == rep[0] - 1) { + repCode = 3; + } + if (repCode) { + /* ZSTD_storeSeq expects a number in the range [0, 2] to represent a repcode */ + offCode = repCode - 1; + } + return offCode; +} + +/* Returns 0 on success, and a ZSTD_error otherwise. This function scans through an array of + * ZSTD_Sequence, storing the sequences it finds, until it reaches a block delimiter. + */ +static size_t ZSTD_copySequencesToSeqStoreExplicitBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos, + const ZSTD_Sequence* const inSeqs, size_t inSeqsSize, + const void* src, size_t blockSize) { + U32 idx = seqPos->idx; + BYTE const* ip = (BYTE const*)(src); + const BYTE* const iend = ip + blockSize; + repcodes_t updatedRepcodes; + U32 dictSize; + U32 litLength; + U32 matchLength; + U32 ll0; + U32 offCode; + + if (cctx->cdict) { + dictSize = (U32)cctx->cdict->dictContentSize; + } else if (cctx->prefixDict.dict) { + dictSize = (U32)cctx->prefixDict.dictSize; + } else { + dictSize = 0; + } + ZSTD_memcpy(updatedRepcodes.rep, cctx->blockState.prevCBlock->rep, sizeof(repcodes_t)); + for (; (inSeqs[idx].matchLength != 0 || inSeqs[idx].offset != 0) && idx < inSeqsSize; ++idx) { + litLength = inSeqs[idx].litLength; + matchLength = inSeqs[idx].matchLength; + ll0 = litLength == 0; + offCode = ZSTD_finalizeOffCode(inSeqs[idx].offset, updatedRepcodes.rep, ll0); + updatedRepcodes = ZSTD_updateRep(updatedRepcodes.rep, offCode, ll0); + + DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offCode, matchLength, litLength); + if (cctx->appliedParams.validateSequences) { + seqPos->posInSrc += litLength + matchLength; + FORWARD_IF_ERROR(ZSTD_validateSequence(offCode, matchLength, seqPos->posInSrc, + cctx->appliedParams.cParams.windowLog, dictSize, + cctx->appliedParams.cParams.minMatch), + "Sequence validation failed"); + } + RETURN_ERROR_IF(idx - seqPos->idx > cctx->seqStore.maxNbSeq, memory_allocation, + "Not enough memory allocated. Try adjusting ZSTD_c_minMatch."); + ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offCode, matchLength - MINMATCH); + ip += matchLength + litLength; + } + ZSTD_memcpy(cctx->blockState.nextCBlock->rep, updatedRepcodes.rep, sizeof(repcodes_t)); + + if (inSeqs[idx].litLength) { + DEBUGLOG(6, "Storing last literals of size: %u", inSeqs[idx].litLength); + ZSTD_storeLastLiterals(&cctx->seqStore, ip, inSeqs[idx].litLength); + ip += inSeqs[idx].litLength; + seqPos->posInSrc += inSeqs[idx].litLength; + } + RETURN_ERROR_IF(ip != iend, corruption_detected, "Blocksize doesn't agree with block delimiter!"); + seqPos->idx = idx+1; + return 0; +} + +/* Returns the number of bytes to move the current read position back by. Only non-zero + * if we ended up splitting a sequence. Otherwise, it may return a ZSTD error if something + * went wrong. + * + * This function will attempt to scan through blockSize bytes represented by the sequences + * in inSeqs, storing any (partial) sequences. + * + * Occasionally, we may want to change the actual number of bytes we consumed from inSeqs to + * avoid splitting a match, or to avoid splitting a match such that it would produce a match + * smaller than MINMATCH. In this case, we return the number of bytes that we didn't read from this block. + */ +static size_t ZSTD_copySequencesToSeqStoreNoBlockDelim(ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos, + const ZSTD_Sequence* const inSeqs, size_t inSeqsSize, + const void* src, size_t blockSize) { + U32 idx = seqPos->idx; + U32 startPosInSequence = seqPos->posInSequence; + U32 endPosInSequence = seqPos->posInSequence + (U32)blockSize; + size_t dictSize; + BYTE const* ip = (BYTE const*)(src); + BYTE const* iend = ip + blockSize; /* May be adjusted if we decide to process fewer than blockSize bytes */ + repcodes_t updatedRepcodes; + U32 bytesAdjustment = 0; + U32 finalMatchSplit = 0; + U32 litLength; + U32 matchLength; + U32 rawOffset; + U32 offCode; + + if (cctx->cdict) { + dictSize = cctx->cdict->dictContentSize; + } else if (cctx->prefixDict.dict) { + dictSize = cctx->prefixDict.dictSize; + } else { + dictSize = 0; + } + DEBUGLOG(5, "ZSTD_copySequencesToSeqStore: idx: %u PIS: %u blockSize: %zu", idx, startPosInSequence, blockSize); + DEBUGLOG(5, "Start seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength); + ZSTD_memcpy(updatedRepcodes.rep, cctx->blockState.prevCBlock->rep, sizeof(repcodes_t)); + while (endPosInSequence && idx < inSeqsSize && !finalMatchSplit) { + const ZSTD_Sequence currSeq = inSeqs[idx]; + litLength = currSeq.litLength; + matchLength = currSeq.matchLength; + rawOffset = currSeq.offset; + + /* Modify the sequence depending on where endPosInSequence lies */ + if (endPosInSequence >= currSeq.litLength + currSeq.matchLength) { + if (startPosInSequence >= litLength) { + startPosInSequence -= litLength; + litLength = 0; + matchLength -= startPosInSequence; + } else { + litLength -= startPosInSequence; + } + /* Move to the next sequence */ + endPosInSequence -= currSeq.litLength + currSeq.matchLength; + startPosInSequence = 0; + idx++; + } else { + /* This is the final (partial) sequence we're adding from inSeqs, and endPosInSequence + does not reach the end of the match. So, we have to split the sequence */ + DEBUGLOG(6, "Require a split: diff: %u, idx: %u PIS: %u", + currSeq.litLength + currSeq.matchLength - endPosInSequence, idx, endPosInSequence); + if (endPosInSequence > litLength) { + U32 firstHalfMatchLength; + litLength = startPosInSequence >= litLength ? 0 : litLength - startPosInSequence; + firstHalfMatchLength = endPosInSequence - startPosInSequence - litLength; + if (matchLength > blockSize && firstHalfMatchLength >= cctx->appliedParams.cParams.minMatch) { + /* Only ever split the match if it is larger than the block size */ + U32 secondHalfMatchLength = currSeq.matchLength + currSeq.litLength - endPosInSequence; + if (secondHalfMatchLength < cctx->appliedParams.cParams.minMatch) { + /* Move the endPosInSequence backward so that it creates match of minMatch length */ + endPosInSequence -= cctx->appliedParams.cParams.minMatch - secondHalfMatchLength; + bytesAdjustment = cctx->appliedParams.cParams.minMatch - secondHalfMatchLength; + firstHalfMatchLength -= bytesAdjustment; + } + matchLength = firstHalfMatchLength; + /* Flag that we split the last match - after storing the sequence, exit the loop, + but keep the value of endPosInSequence */ + finalMatchSplit = 1; + } else { + /* Move the position in sequence backwards so that we don't split match, and break to store + * the last literals. We use the original currSeq.litLength as a marker for where endPosInSequence + * should go. We prefer to do this whenever it is not necessary to split the match, or if doing so + * would cause the first half of the match to be too small + */ + bytesAdjustment = endPosInSequence - currSeq.litLength; + endPosInSequence = currSeq.litLength; + break; + } + } else { + /* This sequence ends inside the literals, break to store the last literals */ + break; + } + } + /* Check if this offset can be represented with a repcode */ + { U32 ll0 = (litLength == 0); + offCode = ZSTD_finalizeOffCode(rawOffset, updatedRepcodes.rep, ll0); + updatedRepcodes = ZSTD_updateRep(updatedRepcodes.rep, offCode, ll0); + } + + if (cctx->appliedParams.validateSequences) { + seqPos->posInSrc += litLength + matchLength; + FORWARD_IF_ERROR(ZSTD_validateSequence(offCode, matchLength, seqPos->posInSrc, + cctx->appliedParams.cParams.windowLog, dictSize, + cctx->appliedParams.cParams.minMatch), + "Sequence validation failed"); + } + DEBUGLOG(6, "Storing sequence: (of: %u, ml: %u, ll: %u)", offCode, matchLength, litLength); + RETURN_ERROR_IF(idx - seqPos->idx > cctx->seqStore.maxNbSeq, memory_allocation, + "Not enough memory allocated. Try adjusting ZSTD_c_minMatch."); + ZSTD_storeSeq(&cctx->seqStore, litLength, ip, iend, offCode, matchLength - MINMATCH); + ip += matchLength + litLength; + } + DEBUGLOG(5, "Ending seq: idx: %u (of: %u ml: %u ll: %u)", idx, inSeqs[idx].offset, inSeqs[idx].matchLength, inSeqs[idx].litLength); + assert(idx == inSeqsSize || endPosInSequence <= inSeqs[idx].litLength + inSeqs[idx].matchLength); + seqPos->idx = idx; + seqPos->posInSequence = endPosInSequence; + ZSTD_memcpy(cctx->blockState.nextCBlock->rep, updatedRepcodes.rep, sizeof(repcodes_t)); + + iend -= bytesAdjustment; + if (ip != iend) { + /* Store any last literals */ + U32 lastLLSize = (U32)(iend - ip); + assert(ip <= iend); + DEBUGLOG(6, "Storing last literals of size: %u", lastLLSize); + ZSTD_storeLastLiterals(&cctx->seqStore, ip, lastLLSize); + seqPos->posInSrc += lastLLSize; + } + + return bytesAdjustment; +} + +typedef size_t (*ZSTD_sequenceCopier) (ZSTD_CCtx* cctx, ZSTD_sequencePosition* seqPos, + const ZSTD_Sequence* const inSeqs, size_t inSeqsSize, + const void* src, size_t blockSize); +static ZSTD_sequenceCopier ZSTD_selectSequenceCopier(ZSTD_sequenceFormat_e mode) { + ZSTD_sequenceCopier sequenceCopier = NULL; + assert(ZSTD_cParam_withinBounds(ZSTD_c_blockDelimiters, mode)); + if (mode == ZSTD_sf_explicitBlockDelimiters) { + return ZSTD_copySequencesToSeqStoreExplicitBlockDelim; + } else if (mode == ZSTD_sf_noBlockDelimiters) { + return ZSTD_copySequencesToSeqStoreNoBlockDelim; + } + assert(sequenceCopier != NULL); + return sequenceCopier; +} + +/* Compress, block-by-block, all of the sequences given. + * + * Returns the cumulative size of all compressed blocks (including their headers), otherwise a ZSTD error. + */ +static size_t ZSTD_compressSequences_internal(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const ZSTD_Sequence* inSeqs, size_t inSeqsSize, + const void* src, size_t srcSize) { + size_t cSize = 0; + U32 lastBlock; + size_t blockSize; + size_t compressedSeqsSize; + size_t remaining = srcSize; + ZSTD_sequencePosition seqPos = {0, 0, 0}; + + BYTE const* ip = (BYTE const*)src; + BYTE* op = (BYTE*)dst; + ZSTD_sequenceCopier sequenceCopier = ZSTD_selectSequenceCopier(cctx->appliedParams.blockDelimiters); + + DEBUGLOG(4, "ZSTD_compressSequences_internal srcSize: %zu, inSeqsSize: %zu", srcSize, inSeqsSize); + /* Special case: empty frame */ + if (remaining == 0) { + U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1); + RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "No room for empty frame block header"); + MEM_writeLE32(op, cBlockHeader24); + op += ZSTD_blockHeaderSize; + dstCapacity -= ZSTD_blockHeaderSize; + cSize += ZSTD_blockHeaderSize; + } + + while (remaining) { + size_t cBlockSize; + size_t additionalByteAdjustment; + lastBlock = remaining <= cctx->blockSize; + blockSize = lastBlock ? (U32)remaining : (U32)cctx->blockSize; + ZSTD_resetSeqStore(&cctx->seqStore); + DEBUGLOG(4, "Working on new block. Blocksize: %zu", blockSize); + + additionalByteAdjustment = sequenceCopier(cctx, &seqPos, inSeqs, inSeqsSize, ip, blockSize); + FORWARD_IF_ERROR(additionalByteAdjustment, "Bad sequence copy"); + blockSize -= additionalByteAdjustment; + + /* If blocks are too small, emit as a nocompress block */ + if (blockSize < MIN_CBLOCK_SIZE+ZSTD_blockHeaderSize+1) { + cBlockSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock); + FORWARD_IF_ERROR(cBlockSize, "Nocompress block failed"); + DEBUGLOG(4, "Block too small, writing out nocompress block: cSize: %zu", cBlockSize); + cSize += cBlockSize; + ip += blockSize; + op += cBlockSize; + remaining -= blockSize; + dstCapacity -= cBlockSize; + continue; + } + + compressedSeqsSize = ZSTD_entropyCompressSequences(&cctx->seqStore, + &cctx->blockState.prevCBlock->entropy, &cctx->blockState.nextCBlock->entropy, + &cctx->appliedParams, + op + ZSTD_blockHeaderSize /* Leave space for block header */, dstCapacity - ZSTD_blockHeaderSize, + blockSize, + cctx->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */, + cctx->bmi2); + FORWARD_IF_ERROR(compressedSeqsSize, "Compressing sequences of block failed"); + DEBUGLOG(4, "Compressed sequences size: %zu", compressedSeqsSize); + + if (!cctx->isFirstBlock && + ZSTD_maybeRLE(&cctx->seqStore) && + ZSTD_isRLE((BYTE const*)src, srcSize)) { + /* We don't want to emit our first block as a RLE even if it qualifies because + * doing so will cause the decoder (cli only) to throw a "should consume all input error." + * This is only an issue for zstd <= v1.4.3 + */ + compressedSeqsSize = 1; + } + + if (compressedSeqsSize == 0) { + /* ZSTD_noCompressBlock writes the block header as well */ + cBlockSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock); + FORWARD_IF_ERROR(cBlockSize, "Nocompress block failed"); + DEBUGLOG(4, "Writing out nocompress block, size: %zu", cBlockSize); + } else if (compressedSeqsSize == 1) { + cBlockSize = ZSTD_rleCompressBlock(op, dstCapacity, *ip, blockSize, lastBlock); + FORWARD_IF_ERROR(cBlockSize, "RLE compress block failed"); + DEBUGLOG(4, "Writing out RLE block, size: %zu", cBlockSize); + } else { + U32 cBlockHeader; + /* Error checking and repcodes update */ + ZSTD_confirmRepcodesAndEntropyTables(cctx); + if (cctx->blockState.prevCBlock->entropy.fse.offcode_repeatMode == FSE_repeat_valid) + cctx->blockState.prevCBlock->entropy.fse.offcode_repeatMode = FSE_repeat_check; + + /* Write block header into beginning of block*/ + cBlockHeader = lastBlock + (((U32)bt_compressed)<<1) + (U32)(compressedSeqsSize << 3); + MEM_writeLE24(op, cBlockHeader); + cBlockSize = ZSTD_blockHeaderSize + compressedSeqsSize; + DEBUGLOG(4, "Writing out compressed block, size: %zu", cBlockSize); + } + + cSize += cBlockSize; + DEBUGLOG(4, "cSize running total: %zu", cSize); + + if (lastBlock) { + break; + } else { + ip += blockSize; + op += cBlockSize; + remaining -= blockSize; + dstCapacity -= cBlockSize; + cctx->isFirstBlock = 0; + } + } + + return cSize; +} + +size_t ZSTD_compressSequences(ZSTD_CCtx* const cctx, void* dst, size_t dstCapacity, + const ZSTD_Sequence* inSeqs, size_t inSeqsSize, + const void* src, size_t srcSize) { + BYTE* op = (BYTE*)dst; + size_t cSize = 0; + size_t compressedBlocksSize = 0; + size_t frameHeaderSize = 0; + + /* Transparent initialization stage, same as compressStream2() */ + DEBUGLOG(3, "ZSTD_compressSequences()"); + assert(cctx != NULL); + FORWARD_IF_ERROR(ZSTD_CCtx_init_compressStream2(cctx, ZSTD_e_end, srcSize), "CCtx initialization failed"); + /* Begin writing output, starting with frame header */ + frameHeaderSize = ZSTD_writeFrameHeader(op, dstCapacity, &cctx->appliedParams, srcSize, cctx->dictID); + op += frameHeaderSize; + dstCapacity -= frameHeaderSize; + cSize += frameHeaderSize; + if (cctx->appliedParams.fParams.checksumFlag && srcSize) { + xxh64_update(&cctx->xxhState, src, srcSize); + } + /* cSize includes block header size and compressed sequences size */ + compressedBlocksSize = ZSTD_compressSequences_internal(cctx, + op, dstCapacity, + inSeqs, inSeqsSize, + src, srcSize); + FORWARD_IF_ERROR(compressedBlocksSize, "Compressing blocks failed!"); + cSize += compressedBlocksSize; + dstCapacity -= compressedBlocksSize; + + if (cctx->appliedParams.fParams.checksumFlag) { + U32 const checksum = (U32) xxh64_digest(&cctx->xxhState); + RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall, "no room for checksum"); + DEBUGLOG(4, "Write checksum : %08X", (unsigned)checksum); + MEM_writeLE32((char*)dst + cSize, checksum); + cSize += 4; + } + + DEBUGLOG(3, "Final compressed size: %zu", cSize); + return cSize; +} + +/*====== Finalize ======*/ + +/*! ZSTD_flushStream() : + * @return : amount of data remaining to flush */ +size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output) +{ + ZSTD_inBuffer input = { NULL, 0, 0 }; + return ZSTD_compressStream2(zcs, output, &input, ZSTD_e_flush); +} + + +size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output) +{ + ZSTD_inBuffer input = { NULL, 0, 0 }; + size_t const remainingToFlush = ZSTD_compressStream2(zcs, output, &input, ZSTD_e_end); + FORWARD_IF_ERROR( remainingToFlush , "ZSTD_compressStream2 failed"); + if (zcs->appliedParams.nbWorkers > 0) return remainingToFlush; /* minimal estimation */ + /* single thread mode : attempt to calculate remaining to flush more precisely */ + { size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE; + size_t const checksumSize = (size_t)(zcs->frameEnded ? 0 : zcs->appliedParams.fParams.checksumFlag * 4); + size_t const toFlush = remainingToFlush + lastBlockSize + checksumSize; + DEBUGLOG(4, "ZSTD_endStream : remaining to flush : %u", (unsigned)toFlush); + return toFlush; + } +} + + +/*-===== Pre-defined compression levels =====-*/ + +#define ZSTD_MAX_CLEVEL 22 +int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; } +int ZSTD_minCLevel(void) { return (int)-ZSTD_TARGETLENGTH_MAX; } + +static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL+1] = { +{ /* "default" - for any srcSize > 256 KB */ + /* W, C, H, S, L, TL, strat */ + { 19, 12, 13, 1, 6, 1, ZSTD_fast }, /* base for negative levels */ + { 19, 13, 14, 1, 7, 0, ZSTD_fast }, /* level 1 */ + { 20, 15, 16, 1, 6, 0, ZSTD_fast }, /* level 2 */ + { 21, 16, 17, 1, 5, 0, ZSTD_dfast }, /* level 3 */ + { 21, 18, 18, 1, 5, 0, ZSTD_dfast }, /* level 4 */ + { 21, 18, 19, 2, 5, 2, ZSTD_greedy }, /* level 5 */ + { 21, 19, 19, 3, 5, 4, ZSTD_greedy }, /* level 6 */ + { 21, 19, 19, 3, 5, 8, ZSTD_lazy }, /* level 7 */ + { 21, 19, 19, 3, 5, 16, ZSTD_lazy2 }, /* level 8 */ + { 21, 19, 20, 4, 5, 16, ZSTD_lazy2 }, /* level 9 */ + { 22, 20, 21, 4, 5, 16, ZSTD_lazy2 }, /* level 10 */ + { 22, 21, 22, 4, 5, 16, ZSTD_lazy2 }, /* level 11 */ + { 22, 21, 22, 5, 5, 16, ZSTD_lazy2 }, /* level 12 */ + { 22, 21, 22, 5, 5, 32, ZSTD_btlazy2 }, /* level 13 */ + { 22, 22, 23, 5, 5, 32, ZSTD_btlazy2 }, /* level 14 */ + { 22, 23, 23, 6, 5, 32, ZSTD_btlazy2 }, /* level 15 */ + { 22, 22, 22, 5, 5, 48, ZSTD_btopt }, /* level 16 */ + { 23, 23, 22, 5, 4, 64, ZSTD_btopt }, /* level 17 */ + { 23, 23, 22, 6, 3, 64, ZSTD_btultra }, /* level 18 */ + { 23, 24, 22, 7, 3,256, ZSTD_btultra2}, /* level 19 */ + { 25, 25, 23, 7, 3,256, ZSTD_btultra2}, /* level 20 */ + { 26, 26, 24, 7, 3,512, ZSTD_btultra2}, /* level 21 */ + { 27, 27, 25, 9, 3,999, ZSTD_btultra2}, /* level 22 */ +}, +{ /* for srcSize <= 256 KB */ + /* W, C, H, S, L, T, strat */ + { 18, 12, 13, 1, 5, 1, ZSTD_fast }, /* base for negative levels */ + { 18, 13, 14, 1, 6, 0, ZSTD_fast }, /* level 1 */ + { 18, 14, 14, 1, 5, 0, ZSTD_dfast }, /* level 2 */ + { 18, 16, 16, 1, 4, 0, ZSTD_dfast }, /* level 3 */ + { 18, 16, 17, 2, 5, 2, ZSTD_greedy }, /* level 4.*/ + { 18, 18, 18, 3, 5, 2, ZSTD_greedy }, /* level 5.*/ + { 18, 18, 19, 3, 5, 4, ZSTD_lazy }, /* level 6.*/ + { 18, 18, 19, 4, 4, 4, ZSTD_lazy }, /* level 7 */ + { 18, 18, 19, 4, 4, 8, ZSTD_lazy2 }, /* level 8 */ + { 18, 18, 19, 5, 4, 8, ZSTD_lazy2 }, /* level 9 */ + { 18, 18, 19, 6, 4, 8, ZSTD_lazy2 }, /* level 10 */ + { 18, 18, 19, 5, 4, 12, ZSTD_btlazy2 }, /* level 11.*/ + { 18, 19, 19, 7, 4, 12, ZSTD_btlazy2 }, /* level 12.*/ + { 18, 18, 19, 4, 4, 16, ZSTD_btopt }, /* level 13 */ + { 18, 18, 19, 4, 3, 32, ZSTD_btopt }, /* level 14.*/ + { 18, 18, 19, 6, 3,128, ZSTD_btopt }, /* level 15.*/ + { 18, 19, 19, 6, 3,128, ZSTD_btultra }, /* level 16.*/ + { 18, 19, 19, 8, 3,256, ZSTD_btultra }, /* level 17.*/ + { 18, 19, 19, 6, 3,128, ZSTD_btultra2}, /* level 18.*/ + { 18, 19, 19, 8, 3,256, ZSTD_btultra2}, /* level 19.*/ + { 18, 19, 19, 10, 3,512, ZSTD_btultra2}, /* level 20.*/ + { 18, 19, 19, 12, 3,512, ZSTD_btultra2}, /* level 21.*/ + { 18, 19, 19, 13, 3,999, ZSTD_btultra2}, /* level 22.*/ +}, +{ /* for srcSize <= 128 KB */ + /* W, C, H, S, L, T, strat */ + { 17, 12, 12, 1, 5, 1, ZSTD_fast }, /* base for negative levels */ + { 17, 12, 13, 1, 6, 0, ZSTD_fast }, /* level 1 */ + { 17, 13, 15, 1, 5, 0, ZSTD_fast }, /* level 2 */ + { 17, 15, 16, 2, 5, 0, ZSTD_dfast }, /* level 3 */ + { 17, 17, 17, 2, 4, 0, ZSTD_dfast }, /* level 4 */ + { 17, 16, 17, 3, 4, 2, ZSTD_greedy }, /* level 5 */ + { 17, 17, 17, 3, 4, 4, ZSTD_lazy }, /* level 6 */ + { 17, 17, 17, 3, 4, 8, ZSTD_lazy2 }, /* level 7 */ + { 17, 17, 17, 4, 4, 8, ZSTD_lazy2 }, /* level 8 */ + { 17, 17, 17, 5, 4, 8, ZSTD_lazy2 }, /* level 9 */ + { 17, 17, 17, 6, 4, 8, ZSTD_lazy2 }, /* level 10 */ + { 17, 17, 17, 5, 4, 8, ZSTD_btlazy2 }, /* level 11 */ + { 17, 18, 17, 7, 4, 12, ZSTD_btlazy2 }, /* level 12 */ + { 17, 18, 17, 3, 4, 12, ZSTD_btopt }, /* level 13.*/ + { 17, 18, 17, 4, 3, 32, ZSTD_btopt }, /* level 14.*/ + { 17, 18, 17, 6, 3,256, ZSTD_btopt }, /* level 15.*/ + { 17, 18, 17, 6, 3,128, ZSTD_btultra }, /* level 16.*/ + { 17, 18, 17, 8, 3,256, ZSTD_btultra }, /* level 17.*/ + { 17, 18, 17, 10, 3,512, ZSTD_btultra }, /* level 18.*/ + { 17, 18, 17, 5, 3,256, ZSTD_btultra2}, /* level 19.*/ + { 17, 18, 17, 7, 3,512, ZSTD_btultra2}, /* level 20.*/ + { 17, 18, 17, 9, 3,512, ZSTD_btultra2}, /* level 21.*/ + { 17, 18, 17, 11, 3,999, ZSTD_btultra2}, /* level 22.*/ +}, +{ /* for srcSize <= 16 KB */ + /* W, C, H, S, L, T, strat */ + { 14, 12, 13, 1, 5, 1, ZSTD_fast }, /* base for negative levels */ + { 14, 14, 15, 1, 5, 0, ZSTD_fast }, /* level 1 */ + { 14, 14, 15, 1, 4, 0, ZSTD_fast }, /* level 2 */ + { 14, 14, 15, 2, 4, 0, ZSTD_dfast }, /* level 3 */ + { 14, 14, 14, 4, 4, 2, ZSTD_greedy }, /* level 4 */ + { 14, 14, 14, 3, 4, 4, ZSTD_lazy }, /* level 5.*/ + { 14, 14, 14, 4, 4, 8, ZSTD_lazy2 }, /* level 6 */ + { 14, 14, 14, 6, 4, 8, ZSTD_lazy2 }, /* level 7 */ + { 14, 14, 14, 8, 4, 8, ZSTD_lazy2 }, /* level 8.*/ + { 14, 15, 14, 5, 4, 8, ZSTD_btlazy2 }, /* level 9.*/ + { 14, 15, 14, 9, 4, 8, ZSTD_btlazy2 }, /* level 10.*/ + { 14, 15, 14, 3, 4, 12, ZSTD_btopt }, /* level 11.*/ + { 14, 15, 14, 4, 3, 24, ZSTD_btopt }, /* level 12.*/ + { 14, 15, 14, 5, 3, 32, ZSTD_btultra }, /* level 13.*/ + { 14, 15, 15, 6, 3, 64, ZSTD_btultra }, /* level 14.*/ + { 14, 15, 15, 7, 3,256, ZSTD_btultra }, /* level 15.*/ + { 14, 15, 15, 5, 3, 48, ZSTD_btultra2}, /* level 16.*/ + { 14, 15, 15, 6, 3,128, ZSTD_btultra2}, /* level 17.*/ + { 14, 15, 15, 7, 3,256, ZSTD_btultra2}, /* level 18.*/ + { 14, 15, 15, 8, 3,256, ZSTD_btultra2}, /* level 19.*/ + { 14, 15, 15, 8, 3,512, ZSTD_btultra2}, /* level 20.*/ + { 14, 15, 15, 9, 3,512, ZSTD_btultra2}, /* level 21.*/ + { 14, 15, 15, 10, 3,999, ZSTD_btultra2}, /* level 22.*/ +}, +}; + +static ZSTD_compressionParameters ZSTD_dedicatedDictSearch_getCParams(int const compressionLevel, size_t const dictSize) +{ + ZSTD_compressionParameters cParams = ZSTD_getCParams_internal(compressionLevel, 0, dictSize, ZSTD_cpm_createCDict); + switch (cParams.strategy) { + case ZSTD_fast: + case ZSTD_dfast: + break; + case ZSTD_greedy: + case ZSTD_lazy: + case ZSTD_lazy2: + cParams.hashLog += ZSTD_LAZY_DDSS_BUCKET_LOG; + break; + case ZSTD_btlazy2: + case ZSTD_btopt: + case ZSTD_btultra: + case ZSTD_btultra2: + break; + } + return cParams; +} + +static int ZSTD_dedicatedDictSearch_isSupported( + ZSTD_compressionParameters const* cParams) +{ + return (cParams->strategy >= ZSTD_greedy) + && (cParams->strategy <= ZSTD_lazy2) + && (cParams->hashLog >= cParams->chainLog) + && (cParams->chainLog <= 24); +} + +/* + * Reverses the adjustment applied to cparams when enabling dedicated dict + * search. This is used to recover the params set to be used in the working + * context. (Otherwise, those tables would also grow.) + */ +static void ZSTD_dedicatedDictSearch_revertCParams( + ZSTD_compressionParameters* cParams) { + switch (cParams->strategy) { + case ZSTD_fast: + case ZSTD_dfast: + break; + case ZSTD_greedy: + case ZSTD_lazy: + case ZSTD_lazy2: + cParams->hashLog -= ZSTD_LAZY_DDSS_BUCKET_LOG; + break; + case ZSTD_btlazy2: + case ZSTD_btopt: + case ZSTD_btultra: + case ZSTD_btultra2: + break; + } +} + +static U64 ZSTD_getCParamRowSize(U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) +{ + switch (mode) { + case ZSTD_cpm_unknown: + case ZSTD_cpm_noAttachDict: + case ZSTD_cpm_createCDict: + break; + case ZSTD_cpm_attachDict: + dictSize = 0; + break; + default: + assert(0); + break; + } + { int const unknown = srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN; + size_t const addedSize = unknown && dictSize > 0 ? 500 : 0; + return unknown && dictSize == 0 ? ZSTD_CONTENTSIZE_UNKNOWN : srcSizeHint+dictSize+addedSize; + } +} + +/*! ZSTD_getCParams_internal() : + * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize. + * Note: srcSizeHint 0 means 0, use ZSTD_CONTENTSIZE_UNKNOWN for unknown. + * Use dictSize == 0 for unknown or unused. + * Note: `mode` controls how we treat the `dictSize`. See docs for `ZSTD_cParamMode_e`. */ +static ZSTD_compressionParameters ZSTD_getCParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) +{ + U64 const rSize = ZSTD_getCParamRowSize(srcSizeHint, dictSize, mode); + U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB); + int row; + DEBUGLOG(5, "ZSTD_getCParams_internal (cLevel=%i)", compressionLevel); + + /* row */ + if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT; /* 0 == default */ + else if (compressionLevel < 0) row = 0; /* entry 0 is baseline for fast mode */ + else if (compressionLevel > ZSTD_MAX_CLEVEL) row = ZSTD_MAX_CLEVEL; + else row = compressionLevel; + + { ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row]; + /* acceleration factor */ + if (compressionLevel < 0) { + int const clampedCompressionLevel = MAX(ZSTD_minCLevel(), compressionLevel); + cp.targetLength = (unsigned)(-clampedCompressionLevel); + } + /* refine parameters based on srcSize & dictSize */ + return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize, mode); + } +} + +/*! ZSTD_getCParams() : + * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize. + * Size values are optional, provide 0 if not known or unused */ +ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) +{ + if (srcSizeHint == 0) srcSizeHint = ZSTD_CONTENTSIZE_UNKNOWN; + return ZSTD_getCParams_internal(compressionLevel, srcSizeHint, dictSize, ZSTD_cpm_unknown); +} + +/*! ZSTD_getParams() : + * same idea as ZSTD_getCParams() + * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`). + * Fields of `ZSTD_frameParameters` are set to default values */ +static ZSTD_parameters ZSTD_getParams_internal(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode) { + ZSTD_parameters params; + ZSTD_compressionParameters const cParams = ZSTD_getCParams_internal(compressionLevel, srcSizeHint, dictSize, mode); + DEBUGLOG(5, "ZSTD_getParams (cLevel=%i)", compressionLevel); + ZSTD_memset(¶ms, 0, sizeof(params)); + params.cParams = cParams; + params.fParams.contentSizeFlag = 1; + return params; +} + +/*! ZSTD_getParams() : + * same idea as ZSTD_getCParams() + * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`). + * Fields of `ZSTD_frameParameters` are set to default values */ +ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) { + if (srcSizeHint == 0) srcSizeHint = ZSTD_CONTENTSIZE_UNKNOWN; + return ZSTD_getParams_internal(compressionLevel, srcSizeHint, dictSize, ZSTD_cpm_unknown); +} diff --git a/lib/zstd/compress/zstd_compress_internal.h b/lib/zstd/compress/zstd_compress_internal.h new file mode 100644 index 000000000000..685d2f996cc2 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_internal.h @@ -0,0 +1,1188 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* This header contains definitions + * that shall **only** be used by modules within lib/compress. + */ + +#ifndef ZSTD_COMPRESS_H +#define ZSTD_COMPRESS_H + +/*-************************************* +* Dependencies +***************************************/ +#include "../common/zstd_internal.h" +#include "zstd_cwksp.h" + + +/*-************************************* +* Constants +***************************************/ +#define kSearchStrength 8 +#define HASH_READ_SIZE 8 +#define ZSTD_DUBT_UNSORTED_MARK 1 /* For btlazy2 strategy, index ZSTD_DUBT_UNSORTED_MARK==1 means "unsorted". + It could be confused for a real successor at index "1", if sorted as larger than its predecessor. + It's not a big deal though : candidate will just be sorted again. + Additionally, candidate position 1 will be lost. + But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss. + The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy. + This constant is required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */ + + +/*-************************************* +* Context memory management +***************************************/ +typedef enum { ZSTDcs_created=0, ZSTDcs_init, ZSTDcs_ongoing, ZSTDcs_ending } ZSTD_compressionStage_e; +typedef enum { zcss_init=0, zcss_load, zcss_flush } ZSTD_cStreamStage; + +typedef struct ZSTD_prefixDict_s { + const void* dict; + size_t dictSize; + ZSTD_dictContentType_e dictContentType; +} ZSTD_prefixDict; + +typedef struct { + void* dictBuffer; + void const* dict; + size_t dictSize; + ZSTD_dictContentType_e dictContentType; + ZSTD_CDict* cdict; +} ZSTD_localDict; + +typedef struct { + HUF_CElt CTable[HUF_CTABLE_SIZE_U32(255)]; + HUF_repeat repeatMode; +} ZSTD_hufCTables_t; + +typedef struct { + FSE_CTable offcodeCTable[FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)]; + FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)]; + FSE_CTable litlengthCTable[FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)]; + FSE_repeat offcode_repeatMode; + FSE_repeat matchlength_repeatMode; + FSE_repeat litlength_repeatMode; +} ZSTD_fseCTables_t; + +typedef struct { + ZSTD_hufCTables_t huf; + ZSTD_fseCTables_t fse; +} ZSTD_entropyCTables_t; + +typedef struct { + U32 off; /* Offset code (offset + ZSTD_REP_MOVE) for the match */ + U32 len; /* Raw length of match */ +} ZSTD_match_t; + +typedef struct { + U32 offset; /* Offset of sequence */ + U32 litLength; /* Length of literals prior to match */ + U32 matchLength; /* Raw length of match */ +} rawSeq; + +typedef struct { + rawSeq* seq; /* The start of the sequences */ + size_t pos; /* The index in seq where reading stopped. pos <= size. */ + size_t posInSequence; /* The position within the sequence at seq[pos] where reading + stopped. posInSequence <= seq[pos].litLength + seq[pos].matchLength */ + size_t size; /* The number of sequences. <= capacity. */ + size_t capacity; /* The capacity starting from `seq` pointer */ +} rawSeqStore_t; + +UNUSED_ATTR static const rawSeqStore_t kNullRawSeqStore = {NULL, 0, 0, 0, 0}; + +typedef struct { + int price; + U32 off; + U32 mlen; + U32 litlen; + U32 rep[ZSTD_REP_NUM]; +} ZSTD_optimal_t; + +typedef enum { zop_dynamic=0, zop_predef } ZSTD_OptPrice_e; + +typedef struct { + /* All tables are allocated inside cctx->workspace by ZSTD_resetCCtx_internal() */ + unsigned* litFreq; /* table of literals statistics, of size 256 */ + unsigned* litLengthFreq; /* table of litLength statistics, of size (MaxLL+1) */ + unsigned* matchLengthFreq; /* table of matchLength statistics, of size (MaxML+1) */ + unsigned* offCodeFreq; /* table of offCode statistics, of size (MaxOff+1) */ + ZSTD_match_t* matchTable; /* list of found matches, of size ZSTD_OPT_NUM+1 */ + ZSTD_optimal_t* priceTable; /* All positions tracked by optimal parser, of size ZSTD_OPT_NUM+1 */ + + U32 litSum; /* nb of literals */ + U32 litLengthSum; /* nb of litLength codes */ + U32 matchLengthSum; /* nb of matchLength codes */ + U32 offCodeSum; /* nb of offset codes */ + U32 litSumBasePrice; /* to compare to log2(litfreq) */ + U32 litLengthSumBasePrice; /* to compare to log2(llfreq) */ + U32 matchLengthSumBasePrice;/* to compare to log2(mlfreq) */ + U32 offCodeSumBasePrice; /* to compare to log2(offreq) */ + ZSTD_OptPrice_e priceType; /* prices can be determined dynamically, or follow a pre-defined cost structure */ + const ZSTD_entropyCTables_t* symbolCosts; /* pre-calculated dictionary statistics */ + ZSTD_literalCompressionMode_e literalCompressionMode; +} optState_t; + +typedef struct { + ZSTD_entropyCTables_t entropy; + U32 rep[ZSTD_REP_NUM]; +} ZSTD_compressedBlockState_t; + +typedef struct { + BYTE const* nextSrc; /* next block here to continue on current prefix */ + BYTE const* base; /* All regular indexes relative to this position */ + BYTE const* dictBase; /* extDict indexes relative to this position */ + U32 dictLimit; /* below that point, need extDict */ + U32 lowLimit; /* below that point, no more valid data */ +} ZSTD_window_t; + +typedef struct ZSTD_matchState_t ZSTD_matchState_t; +struct ZSTD_matchState_t { + ZSTD_window_t window; /* State for window round buffer management */ + U32 loadedDictEnd; /* index of end of dictionary, within context's referential. + * When loadedDictEnd != 0, a dictionary is in use, and still valid. + * This relies on a mechanism to set loadedDictEnd=0 when dictionary is no longer within distance. + * Such mechanism is provided within ZSTD_window_enforceMaxDist() and ZSTD_checkDictValidity(). + * When dict referential is copied into active context (i.e. not attached), + * loadedDictEnd == dictSize, since referential starts from zero. + */ + U32 nextToUpdate; /* index from which to continue table update */ + U32 hashLog3; /* dispatch table for matches of len==3 : larger == faster, more memory */ + U32* hashTable; + U32* hashTable3; + U32* chainTable; + int dedicatedDictSearch; /* Indicates whether this matchState is using the + * dedicated dictionary search structure. + */ + optState_t opt; /* optimal parser state */ + const ZSTD_matchState_t* dictMatchState; + ZSTD_compressionParameters cParams; + const rawSeqStore_t* ldmSeqStore; +}; + +typedef struct { + ZSTD_compressedBlockState_t* prevCBlock; + ZSTD_compressedBlockState_t* nextCBlock; + ZSTD_matchState_t matchState; +} ZSTD_blockState_t; + +typedef struct { + U32 offset; + U32 checksum; +} ldmEntry_t; + +typedef struct { + BYTE const* split; + U32 hash; + U32 checksum; + ldmEntry_t* bucket; +} ldmMatchCandidate_t; + +#define LDM_BATCH_SIZE 64 + +typedef struct { + ZSTD_window_t window; /* State for the window round buffer management */ + ldmEntry_t* hashTable; + U32 loadedDictEnd; + BYTE* bucketOffsets; /* Next position in bucket to insert entry */ + size_t splitIndices[LDM_BATCH_SIZE]; + ldmMatchCandidate_t matchCandidates[LDM_BATCH_SIZE]; +} ldmState_t; + +typedef struct { + U32 enableLdm; /* 1 if enable long distance matching */ + U32 hashLog; /* Log size of hashTable */ + U32 bucketSizeLog; /* Log bucket size for collision resolution, at most 8 */ + U32 minMatchLength; /* Minimum match length */ + U32 hashRateLog; /* Log number of entries to skip */ + U32 windowLog; /* Window log for the LDM */ +} ldmParams_t; + +typedef struct { + int collectSequences; + ZSTD_Sequence* seqStart; + size_t seqIndex; + size_t maxSequences; +} SeqCollector; + +struct ZSTD_CCtx_params_s { + ZSTD_format_e format; + ZSTD_compressionParameters cParams; + ZSTD_frameParameters fParams; + + int compressionLevel; + int forceWindow; /* force back-references to respect limit of + * 1< 63) ? ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength]; +} + +/* ZSTD_MLcode() : + * note : mlBase = matchLength - MINMATCH; + * because it's the format it's stored in seqStore->sequences */ +MEM_STATIC U32 ZSTD_MLcode(U32 mlBase) +{ + static const BYTE ML_Code[128] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, + 32, 32, 33, 33, 34, 34, 35, 35, 36, 36, 36, 36, 37, 37, 37, 37, + 38, 38, 38, 38, 38, 38, 38, 38, 39, 39, 39, 39, 39, 39, 39, 39, + 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, + 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, 41, + 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, + 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42, 42 }; + static const U32 ML_deltaCode = 36; + return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase]; +} + +typedef struct repcodes_s { + U32 rep[3]; +} repcodes_t; + +MEM_STATIC repcodes_t ZSTD_updateRep(U32 const rep[3], U32 const offset, U32 const ll0) +{ + repcodes_t newReps; + if (offset >= ZSTD_REP_NUM) { /* full offset */ + newReps.rep[2] = rep[1]; + newReps.rep[1] = rep[0]; + newReps.rep[0] = offset - ZSTD_REP_MOVE; + } else { /* repcode */ + U32 const repCode = offset + ll0; + if (repCode > 0) { /* note : if repCode==0, no change */ + U32 const currentOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode]; + newReps.rep[2] = (repCode >= 2) ? rep[1] : rep[2]; + newReps.rep[1] = rep[0]; + newReps.rep[0] = currentOffset; + } else { /* repCode == 0 */ + ZSTD_memcpy(&newReps, rep, sizeof(newReps)); + } + } + return newReps; +} + +/* ZSTD_cParam_withinBounds: + * @return 1 if value is within cParam bounds, + * 0 otherwise */ +MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value) +{ + ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); + if (ZSTD_isError(bounds.error)) return 0; + if (value < bounds.lowerBound) return 0; + if (value > bounds.upperBound) return 0; + return 1; +} + +/* ZSTD_noCompressBlock() : + * Writes uncompressed block to dst buffer from given src. + * Returns the size of the block */ +MEM_STATIC size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize, U32 lastBlock) +{ + U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw)<<1) + (U32)(srcSize << 3); + RETURN_ERROR_IF(srcSize + ZSTD_blockHeaderSize > dstCapacity, + dstSize_tooSmall, "dst buf too small for uncompressed block"); + MEM_writeLE24(dst, cBlockHeader24); + ZSTD_memcpy((BYTE*)dst + ZSTD_blockHeaderSize, src, srcSize); + return ZSTD_blockHeaderSize + srcSize; +} + +MEM_STATIC size_t ZSTD_rleCompressBlock (void* dst, size_t dstCapacity, BYTE src, size_t srcSize, U32 lastBlock) +{ + BYTE* const op = (BYTE*)dst; + U32 const cBlockHeader = lastBlock + (((U32)bt_rle)<<1) + (U32)(srcSize << 3); + RETURN_ERROR_IF(dstCapacity < 4, dstSize_tooSmall, ""); + MEM_writeLE24(op, cBlockHeader); + op[3] = src; + return 4; +} + + +/* ZSTD_minGain() : + * minimum compression required + * to generate a compress block or a compressed literals section. + * note : use same formula for both situations */ +MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat) +{ + U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6; + ZSTD_STATIC_ASSERT(ZSTD_btultra == 8); + assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat)); + return (srcSize >> minlog) + 2; +} + +MEM_STATIC int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams) +{ + switch (cctxParams->literalCompressionMode) { + case ZSTD_lcm_huffman: + return 0; + case ZSTD_lcm_uncompressed: + return 1; + default: + assert(0 /* impossible: pre-validated */); + ZSTD_FALLTHROUGH; + case ZSTD_lcm_auto: + return (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0); + } +} + +/*! ZSTD_safecopyLiterals() : + * memcpy() function that won't read beyond more than WILDCOPY_OVERLENGTH bytes past ilimit_w. + * Only called when the sequence ends past ilimit_w, so it only needs to be optimized for single + * large copies. + */ +static void ZSTD_safecopyLiterals(BYTE* op, BYTE const* ip, BYTE const* const iend, BYTE const* ilimit_w) { + assert(iend > ilimit_w); + if (ip <= ilimit_w) { + ZSTD_wildcopy(op, ip, ilimit_w - ip, ZSTD_no_overlap); + op += ilimit_w - ip; + ip = ilimit_w; + } + while (ip < iend) *op++ = *ip++; +} + +/*! ZSTD_storeSeq() : + * Store a sequence (litlen, litPtr, offCode and mlBase) into seqStore_t. + * `offCode` : distance to match + ZSTD_REP_MOVE (values <= ZSTD_REP_MOVE are repCodes). + * `mlBase` : matchLength - MINMATCH + * Allowed to overread literals up to litLimit. +*/ +HINT_INLINE UNUSED_ATTR +void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const BYTE* literals, const BYTE* litLimit, U32 offCode, size_t mlBase) +{ + BYTE const* const litLimit_w = litLimit - WILDCOPY_OVERLENGTH; + BYTE const* const litEnd = literals + litLength; +#if defined(DEBUGLEVEL) && (DEBUGLEVEL >= 6) + static const BYTE* g_start = NULL; + if (g_start==NULL) g_start = (const BYTE*)literals; /* note : index only works for compression within a single segment */ + { U32 const pos = (U32)((const BYTE*)literals - g_start); + DEBUGLOG(6, "Cpos%7u :%3u literals, match%4u bytes at offCode%7u", + pos, (U32)litLength, (U32)mlBase+MINMATCH, (U32)offCode); + } +#endif + assert((size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart) < seqStorePtr->maxNbSeq); + /* copy Literals */ + assert(seqStorePtr->maxNbLit <= 128 KB); + assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + seqStorePtr->maxNbLit); + assert(literals + litLength <= litLimit); + if (litEnd <= litLimit_w) { + /* Common case we can use wildcopy. + * First copy 16 bytes, because literals are likely short. + */ + assert(WILDCOPY_OVERLENGTH >= 16); + ZSTD_copy16(seqStorePtr->lit, literals); + if (litLength > 16) { + ZSTD_wildcopy(seqStorePtr->lit+16, literals+16, (ptrdiff_t)litLength-16, ZSTD_no_overlap); + } + } else { + ZSTD_safecopyLiterals(seqStorePtr->lit, literals, litEnd, litLimit_w); + } + seqStorePtr->lit += litLength; + + /* literal Length */ + if (litLength>0xFFFF) { + assert(seqStorePtr->longLengthID == 0); /* there can only be a single long length */ + seqStorePtr->longLengthID = 1; + seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); + } + seqStorePtr->sequences[0].litLength = (U16)litLength; + + /* match offset */ + seqStorePtr->sequences[0].offset = offCode + 1; + + /* match Length */ + if (mlBase>0xFFFF) { + assert(seqStorePtr->longLengthID == 0); /* there can only be a single long length */ + seqStorePtr->longLengthID = 2; + seqStorePtr->longLengthPos = (U32)(seqStorePtr->sequences - seqStorePtr->sequencesStart); + } + seqStorePtr->sequences[0].matchLength = (U16)mlBase; + + seqStorePtr->sequences++; +} + + +/*-************************************* +* Match length counter +***************************************/ +static unsigned ZSTD_NbCommonBytes (size_t val) +{ + if (MEM_isLittleEndian()) { + if (MEM_64bits()) { +# if (__GNUC__ >= 4) + return (__builtin_ctzll((U64)val) >> 3); +# else + static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, + 0, 3, 1, 3, 1, 4, 2, 7, + 0, 2, 3, 6, 1, 5, 3, 5, + 1, 3, 4, 4, 2, 5, 6, 7, + 7, 0, 1, 2, 3, 3, 4, 6, + 2, 6, 5, 5, 3, 4, 5, 6, + 7, 1, 2, 4, 6, 4, 4, 5, + 7, 2, 6, 5, 7, 6, 7, 7 }; + return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; +# endif + } else { /* 32 bits */ +# if (__GNUC__ >= 3) + return (__builtin_ctz((U32)val) >> 3); +# else + static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, + 3, 2, 2, 1, 3, 2, 0, 1, + 3, 3, 1, 2, 2, 2, 2, 0, + 3, 1, 2, 0, 1, 0, 1, 1 }; + return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; +# endif + } + } else { /* Big Endian CPU */ + if (MEM_64bits()) { +# if (__GNUC__ >= 4) + return (__builtin_clzll(val) >> 3); +# else + unsigned r; + const unsigned n32 = sizeof(size_t)*4; /* calculate this way due to compiler complaining in 32-bits mode */ + if (!(val>>n32)) { r=4; } else { r=0; val>>=n32; } + if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } + r += (!val); + return r; +# endif + } else { /* 32 bits */ +# if (__GNUC__ >= 3) + return (__builtin_clz((U32)val) >> 3); +# else + unsigned r; + if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } + r += (!val); + return r; +# endif + } } +} + + +MEM_STATIC size_t ZSTD_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* const pInLimit) +{ + const BYTE* const pStart = pIn; + const BYTE* const pInLoopLimit = pInLimit - (sizeof(size_t)-1); + + if (pIn < pInLoopLimit) { + { size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn); + if (diff) return ZSTD_NbCommonBytes(diff); } + pIn+=sizeof(size_t); pMatch+=sizeof(size_t); + while (pIn < pInLoopLimit) { + size_t const diff = MEM_readST(pMatch) ^ MEM_readST(pIn); + if (!diff) { pIn+=sizeof(size_t); pMatch+=sizeof(size_t); continue; } + pIn += ZSTD_NbCommonBytes(diff); + return (size_t)(pIn - pStart); + } } + if (MEM_64bits() && (pIn<(pInLimit-3)) && (MEM_read32(pMatch) == MEM_read32(pIn))) { pIn+=4; pMatch+=4; } + if ((pIn<(pInLimit-1)) && (MEM_read16(pMatch) == MEM_read16(pIn))) { pIn+=2; pMatch+=2; } + if ((pIn> (32-h) ; } +MEM_STATIC size_t ZSTD_hash3Ptr(const void* ptr, U32 h) { return ZSTD_hash3(MEM_readLE32(ptr), h); } /* only in zstd_opt.h */ + +static const U32 prime4bytes = 2654435761U; +static U32 ZSTD_hash4(U32 u, U32 h) { return (u * prime4bytes) >> (32-h) ; } +static size_t ZSTD_hash4Ptr(const void* ptr, U32 h) { return ZSTD_hash4(MEM_read32(ptr), h); } + +static const U64 prime5bytes = 889523592379ULL; +static size_t ZSTD_hash5(U64 u, U32 h) { return (size_t)(((u << (64-40)) * prime5bytes) >> (64-h)) ; } +static size_t ZSTD_hash5Ptr(const void* p, U32 h) { return ZSTD_hash5(MEM_readLE64(p), h); } + +static const U64 prime6bytes = 227718039650203ULL; +static size_t ZSTD_hash6(U64 u, U32 h) { return (size_t)(((u << (64-48)) * prime6bytes) >> (64-h)) ; } +static size_t ZSTD_hash6Ptr(const void* p, U32 h) { return ZSTD_hash6(MEM_readLE64(p), h); } + +static const U64 prime7bytes = 58295818150454627ULL; +static size_t ZSTD_hash7(U64 u, U32 h) { return (size_t)(((u << (64-56)) * prime7bytes) >> (64-h)) ; } +static size_t ZSTD_hash7Ptr(const void* p, U32 h) { return ZSTD_hash7(MEM_readLE64(p), h); } + +static const U64 prime8bytes = 0xCF1BBCDCB7A56463ULL; +static size_t ZSTD_hash8(U64 u, U32 h) { return (size_t)(((u) * prime8bytes) >> (64-h)) ; } +static size_t ZSTD_hash8Ptr(const void* p, U32 h) { return ZSTD_hash8(MEM_readLE64(p), h); } + +MEM_STATIC FORCE_INLINE_ATTR +size_t ZSTD_hashPtr(const void* p, U32 hBits, U32 mls) +{ + switch(mls) + { + default: + case 4: return ZSTD_hash4Ptr(p, hBits); + case 5: return ZSTD_hash5Ptr(p, hBits); + case 6: return ZSTD_hash6Ptr(p, hBits); + case 7: return ZSTD_hash7Ptr(p, hBits); + case 8: return ZSTD_hash8Ptr(p, hBits); + } +} + +/* ZSTD_ipow() : + * Return base^exponent. + */ +static U64 ZSTD_ipow(U64 base, U64 exponent) +{ + U64 power = 1; + while (exponent) { + if (exponent & 1) power *= base; + exponent >>= 1; + base *= base; + } + return power; +} + +#define ZSTD_ROLL_HASH_CHAR_OFFSET 10 + +/* ZSTD_rollingHash_append() : + * Add the buffer to the hash value. + */ +static U64 ZSTD_rollingHash_append(U64 hash, void const* buf, size_t size) +{ + BYTE const* istart = (BYTE const*)buf; + size_t pos; + for (pos = 0; pos < size; ++pos) { + hash *= prime8bytes; + hash += istart[pos] + ZSTD_ROLL_HASH_CHAR_OFFSET; + } + return hash; +} + +/* ZSTD_rollingHash_compute() : + * Compute the rolling hash value of the buffer. + */ +MEM_STATIC U64 ZSTD_rollingHash_compute(void const* buf, size_t size) +{ + return ZSTD_rollingHash_append(0, buf, size); +} + +/* ZSTD_rollingHash_primePower() : + * Compute the primePower to be passed to ZSTD_rollingHash_rotate() for a hash + * over a window of length bytes. + */ +MEM_STATIC U64 ZSTD_rollingHash_primePower(U32 length) +{ + return ZSTD_ipow(prime8bytes, length - 1); +} + +/* ZSTD_rollingHash_rotate() : + * Rotate the rolling hash by one byte. + */ +MEM_STATIC U64 ZSTD_rollingHash_rotate(U64 hash, BYTE toRemove, BYTE toAdd, U64 primePower) +{ + hash -= (toRemove + ZSTD_ROLL_HASH_CHAR_OFFSET) * primePower; + hash *= prime8bytes; + hash += toAdd + ZSTD_ROLL_HASH_CHAR_OFFSET; + return hash; +} + +/*-************************************* +* Round buffer management +***************************************/ +#if (ZSTD_WINDOWLOG_MAX_64 > 31) +# error "ZSTD_WINDOWLOG_MAX is too large : would overflow ZSTD_CURRENT_MAX" +#endif +/* Max current allowed */ +#define ZSTD_CURRENT_MAX ((3U << 29) + (1U << ZSTD_WINDOWLOG_MAX)) +/* Maximum chunk size before overflow correction needs to be called again */ +#define ZSTD_CHUNKSIZE_MAX \ + ( ((U32)-1) /* Maximum ending current index */ \ + - ZSTD_CURRENT_MAX) /* Maximum beginning lowLimit */ + +/* + * ZSTD_window_clear(): + * Clears the window containing the history by simply setting it to empty. + */ +MEM_STATIC void ZSTD_window_clear(ZSTD_window_t* window) +{ + size_t const endT = (size_t)(window->nextSrc - window->base); + U32 const end = (U32)endT; + + window->lowLimit = end; + window->dictLimit = end; +} + +/* + * ZSTD_window_hasExtDict(): + * Returns non-zero if the window has a non-empty extDict. + */ +MEM_STATIC U32 ZSTD_window_hasExtDict(ZSTD_window_t const window) +{ + return window.lowLimit < window.dictLimit; +} + +/* + * ZSTD_matchState_dictMode(): + * Inspects the provided matchState and figures out what dictMode should be + * passed to the compressor. + */ +MEM_STATIC ZSTD_dictMode_e ZSTD_matchState_dictMode(const ZSTD_matchState_t *ms) +{ + return ZSTD_window_hasExtDict(ms->window) ? + ZSTD_extDict : + ms->dictMatchState != NULL ? + (ms->dictMatchState->dedicatedDictSearch ? ZSTD_dedicatedDictSearch : ZSTD_dictMatchState) : + ZSTD_noDict; +} + +/* + * ZSTD_window_needOverflowCorrection(): + * Returns non-zero if the indices are getting too large and need overflow + * protection. + */ +MEM_STATIC U32 ZSTD_window_needOverflowCorrection(ZSTD_window_t const window, + void const* srcEnd) +{ + U32 const curr = (U32)((BYTE const*)srcEnd - window.base); + return curr > ZSTD_CURRENT_MAX; +} + +/* + * ZSTD_window_correctOverflow(): + * Reduces the indices to protect from index overflow. + * Returns the correction made to the indices, which must be applied to every + * stored index. + * + * The least significant cycleLog bits of the indices must remain the same, + * which may be 0. Every index up to maxDist in the past must be valid. + * NOTE: (maxDist & cycleMask) must be zero. + */ +MEM_STATIC U32 ZSTD_window_correctOverflow(ZSTD_window_t* window, U32 cycleLog, + U32 maxDist, void const* src) +{ + /* preemptive overflow correction: + * 1. correction is large enough: + * lowLimit > (3<<29) ==> current > 3<<29 + 1< (3<<29 + 1< (3<<29) - (1< (3<<29) - (1<<30) (NOTE: chainLog <= 30) + * > 1<<29 + * + * 2. (ip+ZSTD_CHUNKSIZE_MAX - cctx->base) doesn't overflow: + * After correction, current is less than (1<base < 1<<32. + * 3. (cctx->lowLimit + 1< 3<<29 + 1<base); + U32 const currentCycle0 = curr & cycleMask; + /* Exclude zero so that newCurrent - maxDist >= 1. */ + U32 const currentCycle1 = currentCycle0 == 0 ? (1U << cycleLog) : currentCycle0; + U32 const newCurrent = currentCycle1 + maxDist; + U32 const correction = curr - newCurrent; + assert((maxDist & cycleMask) == 0); + assert(curr > newCurrent); + /* Loose bound, should be around 1<<29 (see above) */ + assert(correction > 1<<28); + + window->base += correction; + window->dictBase += correction; + if (window->lowLimit <= correction) window->lowLimit = 1; + else window->lowLimit -= correction; + if (window->dictLimit <= correction) window->dictLimit = 1; + else window->dictLimit -= correction; + + /* Ensure we can still reference the full window. */ + assert(newCurrent >= maxDist); + assert(newCurrent - maxDist >= 1); + /* Ensure that lowLimit and dictLimit didn't underflow. */ + assert(window->lowLimit <= newCurrent); + assert(window->dictLimit <= newCurrent); + + DEBUGLOG(4, "Correction of 0x%x bytes to lowLimit=0x%x", correction, + window->lowLimit); + return correction; +} + +/* + * ZSTD_window_enforceMaxDist(): + * Updates lowLimit so that: + * (srcEnd - base) - lowLimit == maxDist + loadedDictEnd + * + * It ensures index is valid as long as index >= lowLimit. + * This must be called before a block compression call. + * + * loadedDictEnd is only defined if a dictionary is in use for current compression. + * As the name implies, loadedDictEnd represents the index at end of dictionary. + * The value lies within context's referential, it can be directly compared to blockEndIdx. + * + * If loadedDictEndPtr is NULL, no dictionary is in use, and we use loadedDictEnd == 0. + * If loadedDictEndPtr is not NULL, we set it to zero after updating lowLimit. + * This is because dictionaries are allowed to be referenced fully + * as long as the last byte of the dictionary is in the window. + * Once input has progressed beyond window size, dictionary cannot be referenced anymore. + * + * In normal dict mode, the dictionary lies between lowLimit and dictLimit. + * In dictMatchState mode, lowLimit and dictLimit are the same, + * and the dictionary is below them. + * forceWindow and dictMatchState are therefore incompatible. + */ +MEM_STATIC void +ZSTD_window_enforceMaxDist(ZSTD_window_t* window, + const void* blockEnd, + U32 maxDist, + U32* loadedDictEndPtr, + const ZSTD_matchState_t** dictMatchStatePtr) +{ + U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base); + U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0; + DEBUGLOG(5, "ZSTD_window_enforceMaxDist: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u", + (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd); + + /* - When there is no dictionary : loadedDictEnd == 0. + In which case, the test (blockEndIdx > maxDist) is merely to avoid + overflowing next operation `newLowLimit = blockEndIdx - maxDist`. + - When there is a standard dictionary : + Index referential is copied from the dictionary, + which means it starts from 0. + In which case, loadedDictEnd == dictSize, + and it makes sense to compare `blockEndIdx > maxDist + dictSize` + since `blockEndIdx` also starts from zero. + - When there is an attached dictionary : + loadedDictEnd is expressed within the referential of the context, + so it can be directly compared against blockEndIdx. + */ + if (blockEndIdx > maxDist + loadedDictEnd) { + U32 const newLowLimit = blockEndIdx - maxDist; + if (window->lowLimit < newLowLimit) window->lowLimit = newLowLimit; + if (window->dictLimit < window->lowLimit) { + DEBUGLOG(5, "Update dictLimit to match lowLimit, from %u to %u", + (unsigned)window->dictLimit, (unsigned)window->lowLimit); + window->dictLimit = window->lowLimit; + } + /* On reaching window size, dictionaries are invalidated */ + if (loadedDictEndPtr) *loadedDictEndPtr = 0; + if (dictMatchStatePtr) *dictMatchStatePtr = NULL; + } +} + +/* Similar to ZSTD_window_enforceMaxDist(), + * but only invalidates dictionary + * when input progresses beyond window size. + * assumption : loadedDictEndPtr and dictMatchStatePtr are valid (non NULL) + * loadedDictEnd uses same referential as window->base + * maxDist is the window size */ +MEM_STATIC void +ZSTD_checkDictValidity(const ZSTD_window_t* window, + const void* blockEnd, + U32 maxDist, + U32* loadedDictEndPtr, + const ZSTD_matchState_t** dictMatchStatePtr) +{ + assert(loadedDictEndPtr != NULL); + assert(dictMatchStatePtr != NULL); + { U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base); + U32 const loadedDictEnd = *loadedDictEndPtr; + DEBUGLOG(5, "ZSTD_checkDictValidity: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u", + (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd); + assert(blockEndIdx >= loadedDictEnd); + + if (blockEndIdx > loadedDictEnd + maxDist) { + /* On reaching window size, dictionaries are invalidated. + * For simplification, if window size is reached anywhere within next block, + * the dictionary is invalidated for the full block. + */ + DEBUGLOG(6, "invalidating dictionary for current block (distance > windowSize)"); + *loadedDictEndPtr = 0; + *dictMatchStatePtr = NULL; + } else { + if (*loadedDictEndPtr != 0) { + DEBUGLOG(6, "dictionary considered valid for current block"); + } } } +} + +MEM_STATIC void ZSTD_window_init(ZSTD_window_t* window) { + ZSTD_memset(window, 0, sizeof(*window)); + window->base = (BYTE const*)""; + window->dictBase = (BYTE const*)""; + window->dictLimit = 1; /* start from 1, so that 1st position is valid */ + window->lowLimit = 1; /* it ensures first and later CCtx usages compress the same */ + window->nextSrc = window->base + 1; /* see issue #1241 */ +} + +/* + * ZSTD_window_update(): + * Updates the window by appending [src, src + srcSize) to the window. + * If it is not contiguous, the current prefix becomes the extDict, and we + * forget about the extDict. Handles overlap of the prefix and extDict. + * Returns non-zero if the segment is contiguous. + */ +MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window, + void const* src, size_t srcSize) +{ + BYTE const* const ip = (BYTE const*)src; + U32 contiguous = 1; + DEBUGLOG(5, "ZSTD_window_update"); + if (srcSize == 0) + return contiguous; + assert(window->base != NULL); + assert(window->dictBase != NULL); + /* Check if blocks follow each other */ + if (src != window->nextSrc) { + /* not contiguous */ + size_t const distanceFromBase = (size_t)(window->nextSrc - window->base); + DEBUGLOG(5, "Non contiguous blocks, new segment starts at %u", window->dictLimit); + window->lowLimit = window->dictLimit; + assert(distanceFromBase == (size_t)(U32)distanceFromBase); /* should never overflow */ + window->dictLimit = (U32)distanceFromBase; + window->dictBase = window->base; + window->base = ip - distanceFromBase; + /* ms->nextToUpdate = window->dictLimit; */ + if (window->dictLimit - window->lowLimit < HASH_READ_SIZE) window->lowLimit = window->dictLimit; /* too small extDict */ + contiguous = 0; + } + window->nextSrc = ip + srcSize; + /* if input and dictionary overlap : reduce dictionary (area presumed modified by input) */ + if ( (ip+srcSize > window->dictBase + window->lowLimit) + & (ip < window->dictBase + window->dictLimit)) { + ptrdiff_t const highInputIdx = (ip + srcSize) - window->dictBase; + U32 const lowLimitMax = (highInputIdx > (ptrdiff_t)window->dictLimit) ? window->dictLimit : (U32)highInputIdx; + window->lowLimit = lowLimitMax; + DEBUGLOG(5, "Overlapping extDict and input : new lowLimit = %u", window->lowLimit); + } + return contiguous; +} + +/* + * Returns the lowest allowed match index. It may either be in the ext-dict or the prefix. + */ +MEM_STATIC U32 ZSTD_getLowestMatchIndex(const ZSTD_matchState_t* ms, U32 curr, unsigned windowLog) +{ + U32 const maxDistance = 1U << windowLog; + U32 const lowestValid = ms->window.lowLimit; + U32 const withinWindow = (curr - lowestValid > maxDistance) ? curr - maxDistance : lowestValid; + U32 const isDictionary = (ms->loadedDictEnd != 0); + /* When using a dictionary the entire dictionary is valid if a single byte of the dictionary + * is within the window. We invalidate the dictionary (and set loadedDictEnd to 0) when it isn't + * valid for the entire block. So this check is sufficient to find the lowest valid match index. + */ + U32 const matchLowest = isDictionary ? lowestValid : withinWindow; + return matchLowest; +} + +/* + * Returns the lowest allowed match index in the prefix. + */ +MEM_STATIC U32 ZSTD_getLowestPrefixIndex(const ZSTD_matchState_t* ms, U32 curr, unsigned windowLog) +{ + U32 const maxDistance = 1U << windowLog; + U32 const lowestValid = ms->window.dictLimit; + U32 const withinWindow = (curr - lowestValid > maxDistance) ? curr - maxDistance : lowestValid; + U32 const isDictionary = (ms->loadedDictEnd != 0); + /* When computing the lowest prefix index we need to take the dictionary into account to handle + * the edge case where the dictionary and the source are contiguous in memory. + */ + U32 const matchLowest = isDictionary ? lowestValid : withinWindow; + return matchLowest; +} + + + +/* debug functions */ +#if (DEBUGLEVEL>=2) + +MEM_STATIC double ZSTD_fWeight(U32 rawStat) +{ + U32 const fp_accuracy = 8; + U32 const fp_multiplier = (1 << fp_accuracy); + U32 const newStat = rawStat + 1; + U32 const hb = ZSTD_highbit32(newStat); + U32 const BWeight = hb * fp_multiplier; + U32 const FWeight = (newStat << fp_accuracy) >> hb; + U32 const weight = BWeight + FWeight; + assert(hb + fp_accuracy < 31); + return (double)weight / fp_multiplier; +} + +/* display a table content, + * listing each element, its frequency, and its predicted bit cost */ +MEM_STATIC void ZSTD_debugTable(const U32* table, U32 max) +{ + unsigned u, sum; + for (u=0, sum=0; u<=max; u++) sum += table[u]; + DEBUGLOG(2, "total nb elts: %u", sum); + for (u=0; u<=max; u++) { + DEBUGLOG(2, "%2u: %5u (%.2f)", + u, table[u], ZSTD_fWeight(sum) - ZSTD_fWeight(table[u]) ); + } +} + +#endif + + + +/* =============================================================== + * Shared internal declarations + * These prototypes may be called from sources not in lib/compress + * =============================================================== */ + +/* ZSTD_loadCEntropy() : + * dict : must point at beginning of a valid zstd dictionary. + * return : size of dictionary header (size of magic number + dict ID + entropy tables) + * assumptions : magic number supposed already checked + * and dictSize >= 8 */ +size_t ZSTD_loadCEntropy(ZSTD_compressedBlockState_t* bs, void* workspace, + const void* const dict, size_t dictSize); + +void ZSTD_reset_compressedBlockState(ZSTD_compressedBlockState_t* bs); + +/* ============================================================== + * Private declarations + * These prototypes shall only be called from within lib/compress + * ============================================================== */ + +/* ZSTD_getCParamsFromCCtxParams() : + * cParams are built depending on compressionLevel, src size hints, + * LDM and manually set compression parameters. + * Note: srcSizeHint == 0 means 0! + */ +ZSTD_compressionParameters ZSTD_getCParamsFromCCtxParams( + const ZSTD_CCtx_params* CCtxParams, U64 srcSizeHint, size_t dictSize, ZSTD_cParamMode_e mode); + +/*! ZSTD_initCStream_internal() : + * Private use only. Init streaming operation. + * expects params to be valid. + * must receive dict, or cdict, or none, but not both. + * @return : 0, or an error code */ +size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs, + const void* dict, size_t dictSize, + const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, unsigned long long pledgedSrcSize); + +void ZSTD_resetSeqStore(seqStore_t* ssPtr); + +/*! ZSTD_getCParamsFromCDict() : + * as the name implies */ +ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict); + +/* ZSTD_compressBegin_advanced_internal() : + * Private use only. To be called from zstdmt_compress.c. */ +size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx, + const void* dict, size_t dictSize, + ZSTD_dictContentType_e dictContentType, + ZSTD_dictTableLoadMethod_e dtlm, + const ZSTD_CDict* cdict, + const ZSTD_CCtx_params* params, + unsigned long long pledgedSrcSize); + +/* ZSTD_compress_advanced_internal() : + * Private use only. To be called from zstdmt_compress.c. */ +size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict,size_t dictSize, + const ZSTD_CCtx_params* params); + + +/* ZSTD_writeLastEmptyBlock() : + * output an empty Block with end-of-frame mark to complete a frame + * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h)) + * or an error code if `dstCapacity` is too small ( 1 */ +U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat); + +/* ZSTD_CCtx_trace() : + * Trace the end of a compression call. + */ +void ZSTD_CCtx_trace(ZSTD_CCtx* cctx, size_t extraCSize); + +#endif /* ZSTD_COMPRESS_H */ diff --git a/lib/zstd/compress/zstd_compress_literals.c b/lib/zstd/compress/zstd_compress_literals.c new file mode 100644 index 000000000000..655bcda4d1f1 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_literals.c @@ -0,0 +1,158 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + /*-************************************* + * Dependencies + ***************************************/ +#include "zstd_compress_literals.h" + +size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + BYTE* const ostart = (BYTE*)dst; + U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); + + RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall, ""); + + switch(flSize) + { + case 1: /* 2 - 1 - 5 */ + ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3)); + break; + case 2: /* 2 - 2 - 12 */ + MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4))); + break; + case 3: /* 2 - 2 - 20 */ + MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4))); + break; + default: /* not necessary : flSize is {1,2,3} */ + assert(0); + } + + ZSTD_memcpy(ostart + flSize, src, srcSize); + DEBUGLOG(5, "Raw literals: %u -> %u", (U32)srcSize, (U32)(srcSize + flSize)); + return srcSize + flSize; +} + +size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + BYTE* const ostart = (BYTE*)dst; + U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); + + (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */ + + switch(flSize) + { + case 1: /* 2 - 1 - 5 */ + ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3)); + break; + case 2: /* 2 - 2 - 12 */ + MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4))); + break; + case 3: /* 2 - 2 - 20 */ + MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4))); + break; + default: /* not necessary : flSize is {1,2,3} */ + assert(0); + } + + ostart[flSize] = *(const BYTE*)src; + DEBUGLOG(5, "RLE literals: %u -> %u", (U32)srcSize, (U32)flSize + 1); + return flSize+1; +} + +size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf, + ZSTD_hufCTables_t* nextHuf, + ZSTD_strategy strategy, int disableLiteralCompression, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + void* entropyWorkspace, size_t entropyWorkspaceSize, + const int bmi2) +{ + size_t const minGain = ZSTD_minGain(srcSize, strategy); + size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB); + BYTE* const ostart = (BYTE*)dst; + U32 singleStream = srcSize < 256; + symbolEncodingType_e hType = set_compressed; + size_t cLitSize; + + DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i srcSize=%u)", + disableLiteralCompression, (U32)srcSize); + + /* Prepare nextEntropy assuming reusing the existing table */ + ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + + if (disableLiteralCompression) + return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); + + /* small ? don't even attempt compression (speed opt) */ +# define COMPRESS_LITERALS_SIZE_MIN 63 + { size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN; + if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); + } + + RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression"); + { HUF_repeat repeat = prevHuf->repeatMode; + int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0; + if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1; + cLitSize = singleStream ? + HUF_compress1X_repeat( + ostart+lhSize, dstCapacity-lhSize, src, srcSize, + HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize, + (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) : + HUF_compress4X_repeat( + ostart+lhSize, dstCapacity-lhSize, src, srcSize, + HUF_SYMBOLVALUE_MAX, HUF_TABLELOG_DEFAULT, entropyWorkspace, entropyWorkspaceSize, + (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2); + if (repeat != HUF_repeat_none) { + /* reused the existing table */ + DEBUGLOG(5, "Reusing previous huffman table"); + hType = set_repeat; + } + } + + if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) { + ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); + } + if (cLitSize==1) { + ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize); + } + + if (hType == set_compressed) { + /* using a newly constructed table */ + nextHuf->repeatMode = HUF_repeat_check; + } + + /* Build header */ + switch(lhSize) + { + case 3: /* 2 - 2 - 10 - 10 */ + { U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14); + MEM_writeLE24(ostart, lhc); + break; + } + case 4: /* 2 - 2 - 14 - 14 */ + { U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18); + MEM_writeLE32(ostart, lhc); + break; + } + case 5: /* 2 - 2 - 18 - 18 */ + { U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22); + MEM_writeLE32(ostart, lhc); + ostart[4] = (BYTE)(cLitSize >> 10); + break; + } + default: /* not possible : lhSize is {3,4,5} */ + assert(0); + } + DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)srcSize, (U32)(lhSize+cLitSize)); + return lhSize+cLitSize; +} diff --git a/lib/zstd/compress/zstd_compress_literals.h b/lib/zstd/compress/zstd_compress_literals.h new file mode 100644 index 000000000000..9904c0cd30a0 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_literals.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_COMPRESS_LITERALS_H +#define ZSTD_COMPRESS_LITERALS_H + +#include "zstd_compress_internal.h" /* ZSTD_hufCTables_t, ZSTD_minGain() */ + + +size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize); + +size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize); + +size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf, + ZSTD_hufCTables_t* nextHuf, + ZSTD_strategy strategy, int disableLiteralCompression, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + void* entropyWorkspace, size_t entropyWorkspaceSize, + const int bmi2); + +#endif /* ZSTD_COMPRESS_LITERALS_H */ diff --git a/lib/zstd/compress/zstd_compress_sequences.c b/lib/zstd/compress/zstd_compress_sequences.c new file mode 100644 index 000000000000..dcfcdc9cc5e8 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_sequences.c @@ -0,0 +1,439 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + /*-************************************* + * Dependencies + ***************************************/ +#include "zstd_compress_sequences.h" + +/* + * -log2(x / 256) lookup table for x in [0, 256). + * If x == 0: Return 0 + * Else: Return floor(-log2(x / 256) * 256) + */ +static unsigned const kInverseProbabilityLog256[256] = { + 0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162, + 1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889, + 874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734, + 724, 714, 704, 694, 685, 676, 667, 658, 650, 642, 633, 626, + 618, 610, 603, 595, 588, 581, 574, 567, 561, 554, 548, 542, + 535, 529, 523, 517, 512, 506, 500, 495, 489, 484, 478, 473, + 468, 463, 458, 453, 448, 443, 438, 434, 429, 424, 420, 415, + 411, 407, 402, 398, 394, 390, 386, 382, 377, 373, 370, 366, + 362, 358, 354, 350, 347, 343, 339, 336, 332, 329, 325, 322, + 318, 315, 311, 308, 305, 302, 298, 295, 292, 289, 286, 282, + 279, 276, 273, 270, 267, 264, 261, 258, 256, 253, 250, 247, + 244, 241, 239, 236, 233, 230, 228, 225, 222, 220, 217, 215, + 212, 209, 207, 204, 202, 199, 197, 194, 192, 190, 187, 185, + 182, 180, 178, 175, 173, 171, 168, 166, 164, 162, 159, 157, + 155, 153, 151, 149, 146, 144, 142, 140, 138, 136, 134, 132, + 130, 128, 126, 123, 121, 119, 117, 115, 114, 112, 110, 108, + 106, 104, 102, 100, 98, 96, 94, 93, 91, 89, 87, 85, + 83, 82, 80, 78, 76, 74, 73, 71, 69, 67, 66, 64, + 62, 61, 59, 57, 55, 54, 52, 50, 49, 47, 46, 44, + 42, 41, 39, 37, 36, 34, 33, 31, 30, 28, 26, 25, + 23, 22, 20, 19, 17, 16, 14, 13, 11, 10, 8, 7, + 5, 4, 2, 1, +}; + +static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) { + void const* ptr = ctable; + U16 const* u16ptr = (U16 const*)ptr; + U32 const maxSymbolValue = MEM_read16(u16ptr + 1); + return maxSymbolValue; +} + +/* + * Returns true if we should use ncount=-1 else we should + * use ncount=1 for low probability symbols instead. + */ +static unsigned ZSTD_useLowProbCount(size_t const nbSeq) +{ + /* Heuristic: This should cover most blocks <= 16K and + * start to fade out after 16K to about 32K depending on + * comprssibility. + */ + return nbSeq >= 2048; +} + +/* + * Returns the cost in bytes of encoding the normalized count header. + * Returns an error if any of the helper functions return an error. + */ +static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max, + size_t const nbSeq, unsigned const FSELog) +{ + BYTE wksp[FSE_NCOUNTBOUND]; + S16 norm[MaxSeq + 1]; + const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); + FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max, ZSTD_useLowProbCount(nbSeq)), ""); + return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog); +} + +/* + * Returns the cost in bits of encoding the distribution described by count + * using the entropy bound. + */ +static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total) +{ + unsigned cost = 0; + unsigned s; + for (s = 0; s <= max; ++s) { + unsigned norm = (unsigned)((256 * count[s]) / total); + if (count[s] != 0 && norm == 0) + norm = 1; + assert(count[s] < total); + cost += count[s] * kInverseProbabilityLog256[norm]; + } + return cost >> 8; +} + +/* + * Returns the cost in bits of encoding the distribution in count using ctable. + * Returns an error if ctable cannot represent all the symbols in count. + */ +size_t ZSTD_fseBitCost( + FSE_CTable const* ctable, + unsigned const* count, + unsigned const max) +{ + unsigned const kAccuracyLog = 8; + size_t cost = 0; + unsigned s; + FSE_CState_t cstate; + FSE_initCState(&cstate, ctable); + if (ZSTD_getFSEMaxSymbolValue(ctable) < max) { + DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u", + ZSTD_getFSEMaxSymbolValue(ctable), max); + return ERROR(GENERIC); + } + for (s = 0; s <= max; ++s) { + unsigned const tableLog = cstate.stateLog; + unsigned const badCost = (tableLog + 1) << kAccuracyLog; + unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog); + if (count[s] == 0) + continue; + if (bitCost >= badCost) { + DEBUGLOG(5, "Repeat FSE_CTable has Prob[%u] == 0", s); + return ERROR(GENERIC); + } + cost += (size_t)count[s] * bitCost; + } + return cost >> kAccuracyLog; +} + +/* + * Returns the cost in bits of encoding the distribution in count using the + * table described by norm. The max symbol support by norm is assumed >= max. + * norm must be valid for every symbol with non-zero probability in count. + */ +size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog, + unsigned const* count, unsigned const max) +{ + unsigned const shift = 8 - accuracyLog; + size_t cost = 0; + unsigned s; + assert(accuracyLog <= 8); + for (s = 0; s <= max; ++s) { + unsigned const normAcc = (norm[s] != -1) ? (unsigned)norm[s] : 1; + unsigned const norm256 = normAcc << shift; + assert(norm256 > 0); + assert(norm256 < 256); + cost += count[s] * kInverseProbabilityLog256[norm256]; + } + return cost >> 8; +} + +symbolEncodingType_e +ZSTD_selectEncodingType( + FSE_repeat* repeatMode, unsigned const* count, unsigned const max, + size_t const mostFrequent, size_t nbSeq, unsigned const FSELog, + FSE_CTable const* prevCTable, + short const* defaultNorm, U32 defaultNormLog, + ZSTD_defaultPolicy_e const isDefaultAllowed, + ZSTD_strategy const strategy) +{ + ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0); + if (mostFrequent == nbSeq) { + *repeatMode = FSE_repeat_none; + if (isDefaultAllowed && nbSeq <= 2) { + /* Prefer set_basic over set_rle when there are 2 or less symbols, + * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol. + * If basic encoding isn't possible, always choose RLE. + */ + DEBUGLOG(5, "Selected set_basic"); + return set_basic; + } + DEBUGLOG(5, "Selected set_rle"); + return set_rle; + } + if (strategy < ZSTD_lazy) { + if (isDefaultAllowed) { + size_t const staticFse_nbSeq_max = 1000; + size_t const mult = 10 - strategy; + size_t const baseLog = 3; + size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog; /* 28-36 for offset, 56-72 for lengths */ + assert(defaultNormLog >= 5 && defaultNormLog <= 6); /* xx_DEFAULTNORMLOG */ + assert(mult <= 9 && mult >= 7); + if ( (*repeatMode == FSE_repeat_valid) + && (nbSeq < staticFse_nbSeq_max) ) { + DEBUGLOG(5, "Selected set_repeat"); + return set_repeat; + } + if ( (nbSeq < dynamicFse_nbSeq_min) + || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) { + DEBUGLOG(5, "Selected set_basic"); + /* The format allows default tables to be repeated, but it isn't useful. + * When using simple heuristics to select encoding type, we don't want + * to confuse these tables with dictionaries. When running more careful + * analysis, we don't need to waste time checking both repeating tables + * and default tables. + */ + *repeatMode = FSE_repeat_none; + return set_basic; + } + } + } else { + size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC); + size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC); + size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog); + size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq); + + if (isDefaultAllowed) { + assert(!ZSTD_isError(basicCost)); + assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost))); + } + assert(!ZSTD_isError(NCountCost)); + assert(compressedCost < ERROR(maxCode)); + DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u", + (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost); + if (basicCost <= repeatCost && basicCost <= compressedCost) { + DEBUGLOG(5, "Selected set_basic"); + assert(isDefaultAllowed); + *repeatMode = FSE_repeat_none; + return set_basic; + } + if (repeatCost <= compressedCost) { + DEBUGLOG(5, "Selected set_repeat"); + assert(!ZSTD_isError(repeatCost)); + return set_repeat; + } + assert(compressedCost < basicCost && compressedCost < repeatCost); + } + DEBUGLOG(5, "Selected set_compressed"); + *repeatMode = FSE_repeat_check; + return set_compressed; +} + +typedef struct { + S16 norm[MaxSeq + 1]; + U32 wksp[FSE_BUILD_CTABLE_WORKSPACE_SIZE_U32(MaxSeq, MaxFSELog)]; +} ZSTD_BuildCTableWksp; + +size_t +ZSTD_buildCTable(void* dst, size_t dstCapacity, + FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type, + unsigned* count, U32 max, + const BYTE* codeTable, size_t nbSeq, + const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax, + const FSE_CTable* prevCTable, size_t prevCTableSize, + void* entropyWorkspace, size_t entropyWorkspaceSize) +{ + BYTE* op = (BYTE*)dst; + const BYTE* const oend = op + dstCapacity; + DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity); + + switch (type) { + case set_rle: + FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max), ""); + RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall, "not enough space"); + *op = codeTable[0]; + return 1; + case set_repeat: + ZSTD_memcpy(nextCTable, prevCTable, prevCTableSize); + return 0; + case set_basic: + FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, entropyWorkspace, entropyWorkspaceSize), ""); /* note : could be pre-calculated */ + return 0; + case set_compressed: { + ZSTD_BuildCTableWksp* wksp = (ZSTD_BuildCTableWksp*)entropyWorkspace; + size_t nbSeq_1 = nbSeq; + const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); + if (count[codeTable[nbSeq-1]] > 1) { + count[codeTable[nbSeq-1]]--; + nbSeq_1--; + } + assert(nbSeq_1 > 1); + assert(entropyWorkspaceSize >= sizeof(ZSTD_BuildCTableWksp)); + (void)entropyWorkspaceSize; + FORWARD_IF_ERROR(FSE_normalizeCount(wksp->norm, tableLog, count, nbSeq_1, max, ZSTD_useLowProbCount(nbSeq_1)), ""); + { size_t const NCountSize = FSE_writeNCount(op, oend - op, wksp->norm, max, tableLog); /* overflow protected */ + FORWARD_IF_ERROR(NCountSize, "FSE_writeNCount failed"); + FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, wksp->norm, max, tableLog, wksp->wksp, sizeof(wksp->wksp)), ""); + return NCountSize; + } + } + default: assert(0); RETURN_ERROR(GENERIC, "impossible to reach"); + } +} + +FORCE_INLINE_TEMPLATE size_t +ZSTD_encodeSequences_body( + void* dst, size_t dstCapacity, + FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, + FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, + FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, + seqDef const* sequences, size_t nbSeq, int longOffsets) +{ + BIT_CStream_t blockStream; + FSE_CState_t stateMatchLength; + FSE_CState_t stateOffsetBits; + FSE_CState_t stateLitLength; + + RETURN_ERROR_IF( + ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)), + dstSize_tooSmall, "not enough space remaining"); + DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)", + (int)(blockStream.endPtr - blockStream.startPtr), + (unsigned)dstCapacity); + + /* first symbols */ + FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]); + FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq-1]); + FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq-1]); + BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]); + if (MEM_32bits()) BIT_flushBits(&blockStream); + BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]); + if (MEM_32bits()) BIT_flushBits(&blockStream); + if (longOffsets) { + U32 const ofBits = ofCodeTable[nbSeq-1]; + unsigned const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1); + if (extraBits) { + BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits); + BIT_flushBits(&blockStream); + } + BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits, + ofBits - extraBits); + } else { + BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]); + } + BIT_flushBits(&blockStream); + + { size_t n; + for (n=nbSeq-2 ; n= 64-7-(LLFSELog+MLFSELog+OffFSELog))) + BIT_flushBits(&blockStream); /* (7)*/ + BIT_addBits(&blockStream, sequences[n].litLength, llBits); + if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream); + BIT_addBits(&blockStream, sequences[n].matchLength, mlBits); + if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream); + if (longOffsets) { + unsigned const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1); + if (extraBits) { + BIT_addBits(&blockStream, sequences[n].offset, extraBits); + BIT_flushBits(&blockStream); /* (7)*/ + } + BIT_addBits(&blockStream, sequences[n].offset >> extraBits, + ofBits - extraBits); /* 31 */ + } else { + BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */ + } + BIT_flushBits(&blockStream); /* (7)*/ + DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr)); + } } + + DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog); + FSE_flushCState(&blockStream, &stateMatchLength); + DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog); + FSE_flushCState(&blockStream, &stateOffsetBits); + DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog); + FSE_flushCState(&blockStream, &stateLitLength); + + { size_t const streamSize = BIT_closeCStream(&blockStream); + RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space"); + return streamSize; + } +} + +static size_t +ZSTD_encodeSequences_default( + void* dst, size_t dstCapacity, + FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, + FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, + FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, + seqDef const* sequences, size_t nbSeq, int longOffsets) +{ + return ZSTD_encodeSequences_body(dst, dstCapacity, + CTable_MatchLength, mlCodeTable, + CTable_OffsetBits, ofCodeTable, + CTable_LitLength, llCodeTable, + sequences, nbSeq, longOffsets); +} + + +#if DYNAMIC_BMI2 + +static TARGET_ATTRIBUTE("bmi2") size_t +ZSTD_encodeSequences_bmi2( + void* dst, size_t dstCapacity, + FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, + FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, + FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, + seqDef const* sequences, size_t nbSeq, int longOffsets) +{ + return ZSTD_encodeSequences_body(dst, dstCapacity, + CTable_MatchLength, mlCodeTable, + CTable_OffsetBits, ofCodeTable, + CTable_LitLength, llCodeTable, + sequences, nbSeq, longOffsets); +} + +#endif + +size_t ZSTD_encodeSequences( + void* dst, size_t dstCapacity, + FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, + FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, + FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, + seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2) +{ + DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity); +#if DYNAMIC_BMI2 + if (bmi2) { + return ZSTD_encodeSequences_bmi2(dst, dstCapacity, + CTable_MatchLength, mlCodeTable, + CTable_OffsetBits, ofCodeTable, + CTable_LitLength, llCodeTable, + sequences, nbSeq, longOffsets); + } +#endif + (void)bmi2; + return ZSTD_encodeSequences_default(dst, dstCapacity, + CTable_MatchLength, mlCodeTable, + CTable_OffsetBits, ofCodeTable, + CTable_LitLength, llCodeTable, + sequences, nbSeq, longOffsets); +} diff --git a/lib/zstd/compress/zstd_compress_sequences.h b/lib/zstd/compress/zstd_compress_sequences.h new file mode 100644 index 000000000000..7991364c2f71 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_sequences.h @@ -0,0 +1,54 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_COMPRESS_SEQUENCES_H +#define ZSTD_COMPRESS_SEQUENCES_H + +#include "../common/fse.h" /* FSE_repeat, FSE_CTable */ +#include "../common/zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */ + +typedef enum { + ZSTD_defaultDisallowed = 0, + ZSTD_defaultAllowed = 1 +} ZSTD_defaultPolicy_e; + +symbolEncodingType_e +ZSTD_selectEncodingType( + FSE_repeat* repeatMode, unsigned const* count, unsigned const max, + size_t const mostFrequent, size_t nbSeq, unsigned const FSELog, + FSE_CTable const* prevCTable, + short const* defaultNorm, U32 defaultNormLog, + ZSTD_defaultPolicy_e const isDefaultAllowed, + ZSTD_strategy const strategy); + +size_t +ZSTD_buildCTable(void* dst, size_t dstCapacity, + FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type, + unsigned* count, U32 max, + const BYTE* codeTable, size_t nbSeq, + const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax, + const FSE_CTable* prevCTable, size_t prevCTableSize, + void* entropyWorkspace, size_t entropyWorkspaceSize); + +size_t ZSTD_encodeSequences( + void* dst, size_t dstCapacity, + FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, + FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, + FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, + seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2); + +size_t ZSTD_fseBitCost( + FSE_CTable const* ctable, + unsigned const* count, + unsigned const max); + +size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog, + unsigned const* count, unsigned const max); +#endif /* ZSTD_COMPRESS_SEQUENCES_H */ diff --git a/lib/zstd/compress/zstd_compress_superblock.c b/lib/zstd/compress/zstd_compress_superblock.c new file mode 100644 index 000000000000..ee03e0aedb03 --- /dev/null +++ b/lib/zstd/compress/zstd_compress_superblock.c @@ -0,0 +1,850 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + /*-************************************* + * Dependencies + ***************************************/ +#include "zstd_compress_superblock.h" + +#include "../common/zstd_internal.h" /* ZSTD_getSequenceLength */ +#include "hist.h" /* HIST_countFast_wksp */ +#include "zstd_compress_internal.h" +#include "zstd_compress_sequences.h" +#include "zstd_compress_literals.h" + +/*-************************************* +* Superblock entropy buffer structs +***************************************/ +/* ZSTD_hufCTablesMetadata_t : + * Stores Literals Block Type for a super-block in hType, and + * huffman tree description in hufDesBuffer. + * hufDesSize refers to the size of huffman tree description in bytes. + * This metadata is populated in ZSTD_buildSuperBlockEntropy_literal() */ +typedef struct { + symbolEncodingType_e hType; + BYTE hufDesBuffer[ZSTD_MAX_HUF_HEADER_SIZE]; + size_t hufDesSize; +} ZSTD_hufCTablesMetadata_t; + +/* ZSTD_fseCTablesMetadata_t : + * Stores symbol compression modes for a super-block in {ll, ol, ml}Type, and + * fse tables in fseTablesBuffer. + * fseTablesSize refers to the size of fse tables in bytes. + * This metadata is populated in ZSTD_buildSuperBlockEntropy_sequences() */ +typedef struct { + symbolEncodingType_e llType; + symbolEncodingType_e ofType; + symbolEncodingType_e mlType; + BYTE fseTablesBuffer[ZSTD_MAX_FSE_HEADERS_SIZE]; + size_t fseTablesSize; + size_t lastCountSize; /* This is to account for bug in 1.3.4. More detail in ZSTD_compressSubBlock_sequences() */ +} ZSTD_fseCTablesMetadata_t; + +typedef struct { + ZSTD_hufCTablesMetadata_t hufMetadata; + ZSTD_fseCTablesMetadata_t fseMetadata; +} ZSTD_entropyCTablesMetadata_t; + + +/* ZSTD_buildSuperBlockEntropy_literal() : + * Builds entropy for the super-block literals. + * Stores literals block type (raw, rle, compressed, repeat) and + * huffman description table to hufMetadata. + * @return : size of huffman description table or error code */ +static size_t ZSTD_buildSuperBlockEntropy_literal(void* const src, size_t srcSize, + const ZSTD_hufCTables_t* prevHuf, + ZSTD_hufCTables_t* nextHuf, + ZSTD_hufCTablesMetadata_t* hufMetadata, + const int disableLiteralsCompression, + void* workspace, size_t wkspSize) +{ + BYTE* const wkspStart = (BYTE*)workspace; + BYTE* const wkspEnd = wkspStart + wkspSize; + BYTE* const countWkspStart = wkspStart; + unsigned* const countWksp = (unsigned*)workspace; + const size_t countWkspSize = (HUF_SYMBOLVALUE_MAX + 1) * sizeof(unsigned); + BYTE* const nodeWksp = countWkspStart + countWkspSize; + const size_t nodeWkspSize = wkspEnd-nodeWksp; + unsigned maxSymbolValue = 255; + unsigned huffLog = HUF_TABLELOG_DEFAULT; + HUF_repeat repeat = prevHuf->repeatMode; + + DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy_literal (srcSize=%zu)", srcSize); + + /* Prepare nextEntropy assuming reusing the existing table */ + ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + + if (disableLiteralsCompression) { + DEBUGLOG(5, "set_basic - disabled"); + hufMetadata->hType = set_basic; + return 0; + } + + /* small ? don't even attempt compression (speed opt) */ +# define COMPRESS_LITERALS_SIZE_MIN 63 + { size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN; + if (srcSize <= minLitSize) { + DEBUGLOG(5, "set_basic - too small"); + hufMetadata->hType = set_basic; + return 0; + } + } + + /* Scan input and build symbol stats */ + { size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)src, srcSize, workspace, wkspSize); + FORWARD_IF_ERROR(largest, "HIST_count_wksp failed"); + if (largest == srcSize) { + DEBUGLOG(5, "set_rle"); + hufMetadata->hType = set_rle; + return 0; + } + if (largest <= (srcSize >> 7)+4) { + DEBUGLOG(5, "set_basic - no gain"); + hufMetadata->hType = set_basic; + return 0; + } + } + + /* Validate the previous Huffman table */ + if (repeat == HUF_repeat_check && !HUF_validateCTable((HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue)) { + repeat = HUF_repeat_none; + } + + /* Build Huffman Tree */ + ZSTD_memset(nextHuf->CTable, 0, sizeof(nextHuf->CTable)); + huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue); + { size_t const maxBits = HUF_buildCTable_wksp((HUF_CElt*)nextHuf->CTable, countWksp, + maxSymbolValue, huffLog, + nodeWksp, nodeWkspSize); + FORWARD_IF_ERROR(maxBits, "HUF_buildCTable_wksp"); + huffLog = (U32)maxBits; + { /* Build and write the CTable */ + size_t const newCSize = HUF_estimateCompressedSize( + (HUF_CElt*)nextHuf->CTable, countWksp, maxSymbolValue); + size_t const hSize = HUF_writeCTable_wksp( + hufMetadata->hufDesBuffer, sizeof(hufMetadata->hufDesBuffer), + (HUF_CElt*)nextHuf->CTable, maxSymbolValue, huffLog, + nodeWksp, nodeWkspSize); + /* Check against repeating the previous CTable */ + if (repeat != HUF_repeat_none) { + size_t const oldCSize = HUF_estimateCompressedSize( + (HUF_CElt const*)prevHuf->CTable, countWksp, maxSymbolValue); + if (oldCSize < srcSize && (oldCSize <= hSize + newCSize || hSize + 12 >= srcSize)) { + DEBUGLOG(5, "set_repeat - smaller"); + ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + hufMetadata->hType = set_repeat; + return 0; + } + } + if (newCSize + hSize >= srcSize) { + DEBUGLOG(5, "set_basic - no gains"); + ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + hufMetadata->hType = set_basic; + return 0; + } + DEBUGLOG(5, "set_compressed (hSize=%u)", (U32)hSize); + hufMetadata->hType = set_compressed; + nextHuf->repeatMode = HUF_repeat_check; + return hSize; + } + } +} + +/* ZSTD_buildSuperBlockEntropy_sequences() : + * Builds entropy for the super-block sequences. + * Stores symbol compression modes and fse table to fseMetadata. + * @return : size of fse tables or error code */ +static size_t ZSTD_buildSuperBlockEntropy_sequences(seqStore_t* seqStorePtr, + const ZSTD_fseCTables_t* prevEntropy, + ZSTD_fseCTables_t* nextEntropy, + const ZSTD_CCtx_params* cctxParams, + ZSTD_fseCTablesMetadata_t* fseMetadata, + void* workspace, size_t wkspSize) +{ + BYTE* const wkspStart = (BYTE*)workspace; + BYTE* const wkspEnd = wkspStart + wkspSize; + BYTE* const countWkspStart = wkspStart; + unsigned* const countWksp = (unsigned*)workspace; + const size_t countWkspSize = (MaxSeq + 1) * sizeof(unsigned); + BYTE* const cTableWksp = countWkspStart + countWkspSize; + const size_t cTableWkspSize = wkspEnd-cTableWksp; + ZSTD_strategy const strategy = cctxParams->cParams.strategy; + FSE_CTable* CTable_LitLength = nextEntropy->litlengthCTable; + FSE_CTable* CTable_OffsetBits = nextEntropy->offcodeCTable; + FSE_CTable* CTable_MatchLength = nextEntropy->matchlengthCTable; + const BYTE* const ofCodeTable = seqStorePtr->ofCode; + const BYTE* const llCodeTable = seqStorePtr->llCode; + const BYTE* const mlCodeTable = seqStorePtr->mlCode; + size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart; + BYTE* const ostart = fseMetadata->fseTablesBuffer; + BYTE* const oend = ostart + sizeof(fseMetadata->fseTablesBuffer); + BYTE* op = ostart; + + assert(cTableWkspSize >= (1 << MaxFSELog) * sizeof(FSE_FUNCTION_TYPE)); + DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy_sequences (nbSeq=%zu)", nbSeq); + ZSTD_memset(workspace, 0, wkspSize); + + fseMetadata->lastCountSize = 0; + /* convert length/distances into codes */ + ZSTD_seqToCodes(seqStorePtr); + /* build CTable for Literal Lengths */ + { U32 LLtype; + unsigned max = MaxLL; + size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, llCodeTable, nbSeq, workspace, wkspSize); /* can't fail */ + DEBUGLOG(5, "Building LL table"); + nextEntropy->litlength_repeatMode = prevEntropy->litlength_repeatMode; + LLtype = ZSTD_selectEncodingType(&nextEntropy->litlength_repeatMode, + countWksp, max, mostFrequent, nbSeq, + LLFSELog, prevEntropy->litlengthCTable, + LL_defaultNorm, LL_defaultNormLog, + ZSTD_defaultAllowed, strategy); + assert(set_basic < set_compressed && set_rle < set_compressed); + assert(!(LLtype < set_compressed && nextEntropy->litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ + { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype, + countWksp, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL, + prevEntropy->litlengthCTable, sizeof(prevEntropy->litlengthCTable), + cTableWksp, cTableWkspSize); + FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for LitLens failed"); + if (LLtype == set_compressed) + fseMetadata->lastCountSize = countSize; + op += countSize; + fseMetadata->llType = (symbolEncodingType_e) LLtype; + } } + /* build CTable for Offsets */ + { U32 Offtype; + unsigned max = MaxOff; + size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, ofCodeTable, nbSeq, workspace, wkspSize); /* can't fail */ + /* We can only use the basic table if max <= DefaultMaxOff, otherwise the offsets are too large */ + ZSTD_defaultPolicy_e const defaultPolicy = (max <= DefaultMaxOff) ? ZSTD_defaultAllowed : ZSTD_defaultDisallowed; + DEBUGLOG(5, "Building OF table"); + nextEntropy->offcode_repeatMode = prevEntropy->offcode_repeatMode; + Offtype = ZSTD_selectEncodingType(&nextEntropy->offcode_repeatMode, + countWksp, max, mostFrequent, nbSeq, + OffFSELog, prevEntropy->offcodeCTable, + OF_defaultNorm, OF_defaultNormLog, + defaultPolicy, strategy); + assert(!(Offtype < set_compressed && nextEntropy->offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */ + { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype, + countWksp, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, + prevEntropy->offcodeCTable, sizeof(prevEntropy->offcodeCTable), + cTableWksp, cTableWkspSize); + FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for Offsets failed"); + if (Offtype == set_compressed) + fseMetadata->lastCountSize = countSize; + op += countSize; + fseMetadata->ofType = (symbolEncodingType_e) Offtype; + } } + /* build CTable for MatchLengths */ + { U32 MLtype; + unsigned max = MaxML; + size_t const mostFrequent = HIST_countFast_wksp(countWksp, &max, mlCodeTable, nbSeq, workspace, wkspSize); /* can't fail */ + DEBUGLOG(5, "Building ML table (remaining space : %i)", (int)(oend-op)); + nextEntropy->matchlength_repeatMode = prevEntropy->matchlength_repeatMode; + MLtype = ZSTD_selectEncodingType(&nextEntropy->matchlength_repeatMode, + countWksp, max, mostFrequent, nbSeq, + MLFSELog, prevEntropy->matchlengthCTable, + ML_defaultNorm, ML_defaultNormLog, + ZSTD_defaultAllowed, strategy); + assert(!(MLtype < set_compressed && nextEntropy->matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */ + { size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype, + countWksp, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML, + prevEntropy->matchlengthCTable, sizeof(prevEntropy->matchlengthCTable), + cTableWksp, cTableWkspSize); + FORWARD_IF_ERROR(countSize, "ZSTD_buildCTable for MatchLengths failed"); + if (MLtype == set_compressed) + fseMetadata->lastCountSize = countSize; + op += countSize; + fseMetadata->mlType = (symbolEncodingType_e) MLtype; + } } + assert((size_t) (op-ostart) <= sizeof(fseMetadata->fseTablesBuffer)); + return op-ostart; +} + + +/* ZSTD_buildSuperBlockEntropy() : + * Builds entropy for the super-block. + * @return : 0 on success or error code */ +static size_t +ZSTD_buildSuperBlockEntropy(seqStore_t* seqStorePtr, + const ZSTD_entropyCTables_t* prevEntropy, + ZSTD_entropyCTables_t* nextEntropy, + const ZSTD_CCtx_params* cctxParams, + ZSTD_entropyCTablesMetadata_t* entropyMetadata, + void* workspace, size_t wkspSize) +{ + size_t const litSize = seqStorePtr->lit - seqStorePtr->litStart; + DEBUGLOG(5, "ZSTD_buildSuperBlockEntropy"); + entropyMetadata->hufMetadata.hufDesSize = + ZSTD_buildSuperBlockEntropy_literal(seqStorePtr->litStart, litSize, + &prevEntropy->huf, &nextEntropy->huf, + &entropyMetadata->hufMetadata, + ZSTD_disableLiteralsCompression(cctxParams), + workspace, wkspSize); + FORWARD_IF_ERROR(entropyMetadata->hufMetadata.hufDesSize, "ZSTD_buildSuperBlockEntropy_literal failed"); + entropyMetadata->fseMetadata.fseTablesSize = + ZSTD_buildSuperBlockEntropy_sequences(seqStorePtr, + &prevEntropy->fse, &nextEntropy->fse, + cctxParams, + &entropyMetadata->fseMetadata, + workspace, wkspSize); + FORWARD_IF_ERROR(entropyMetadata->fseMetadata.fseTablesSize, "ZSTD_buildSuperBlockEntropy_sequences failed"); + return 0; +} + +/* ZSTD_compressSubBlock_literal() : + * Compresses literals section for a sub-block. + * When we have to write the Huffman table we will sometimes choose a header + * size larger than necessary. This is because we have to pick the header size + * before we know the table size + compressed size, so we have a bound on the + * table size. If we guessed incorrectly, we fall back to uncompressed literals. + * + * We write the header when writeEntropy=1 and set entropyWritten=1 when we succeeded + * in writing the header, otherwise it is set to 0. + * + * hufMetadata->hType has literals block type info. + * If it is set_basic, all sub-blocks literals section will be Raw_Literals_Block. + * If it is set_rle, all sub-blocks literals section will be RLE_Literals_Block. + * If it is set_compressed, first sub-block's literals section will be Compressed_Literals_Block + * If it is set_compressed, first sub-block's literals section will be Treeless_Literals_Block + * and the following sub-blocks' literals sections will be Treeless_Literals_Block. + * @return : compressed size of literals section of a sub-block + * Or 0 if it unable to compress. + * Or error code */ +static size_t ZSTD_compressSubBlock_literal(const HUF_CElt* hufTable, + const ZSTD_hufCTablesMetadata_t* hufMetadata, + const BYTE* literals, size_t litSize, + void* dst, size_t dstSize, + const int bmi2, int writeEntropy, int* entropyWritten) +{ + size_t const header = writeEntropy ? 200 : 0; + size_t const lhSize = 3 + (litSize >= (1 KB - header)) + (litSize >= (16 KB - header)); + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstSize; + BYTE* op = ostart + lhSize; + U32 const singleStream = lhSize == 3; + symbolEncodingType_e hType = writeEntropy ? hufMetadata->hType : set_repeat; + size_t cLitSize = 0; + + (void)bmi2; /* TODO bmi2... */ + + DEBUGLOG(5, "ZSTD_compressSubBlock_literal (litSize=%zu, lhSize=%zu, writeEntropy=%d)", litSize, lhSize, writeEntropy); + + *entropyWritten = 0; + if (litSize == 0 || hufMetadata->hType == set_basic) { + DEBUGLOG(5, "ZSTD_compressSubBlock_literal using raw literal"); + return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize); + } else if (hufMetadata->hType == set_rle) { + DEBUGLOG(5, "ZSTD_compressSubBlock_literal using rle literal"); + return ZSTD_compressRleLiteralsBlock(dst, dstSize, literals, litSize); + } + + assert(litSize > 0); + assert(hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat); + + if (writeEntropy && hufMetadata->hType == set_compressed) { + ZSTD_memcpy(op, hufMetadata->hufDesBuffer, hufMetadata->hufDesSize); + op += hufMetadata->hufDesSize; + cLitSize += hufMetadata->hufDesSize; + DEBUGLOG(5, "ZSTD_compressSubBlock_literal (hSize=%zu)", hufMetadata->hufDesSize); + } + + /* TODO bmi2 */ + { const size_t cSize = singleStream ? HUF_compress1X_usingCTable(op, oend-op, literals, litSize, hufTable) + : HUF_compress4X_usingCTable(op, oend-op, literals, litSize, hufTable); + op += cSize; + cLitSize += cSize; + if (cSize == 0 || ERR_isError(cSize)) { + DEBUGLOG(5, "Failed to write entropy tables %s", ZSTD_getErrorName(cSize)); + return 0; + } + /* If we expand and we aren't writing a header then emit uncompressed */ + if (!writeEntropy && cLitSize >= litSize) { + DEBUGLOG(5, "ZSTD_compressSubBlock_literal using raw literal because uncompressible"); + return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize); + } + /* If we are writing headers then allow expansion that doesn't change our header size. */ + if (lhSize < (size_t)(3 + (cLitSize >= 1 KB) + (cLitSize >= 16 KB))) { + assert(cLitSize > litSize); + DEBUGLOG(5, "Literals expanded beyond allowed header size"); + return ZSTD_noCompressLiterals(dst, dstSize, literals, litSize); + } + DEBUGLOG(5, "ZSTD_compressSubBlock_literal (cSize=%zu)", cSize); + } + + /* Build header */ + switch(lhSize) + { + case 3: /* 2 - 2 - 10 - 10 */ + { U32 const lhc = hType + ((!singleStream) << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<14); + MEM_writeLE24(ostart, lhc); + break; + } + case 4: /* 2 - 2 - 14 - 14 */ + { U32 const lhc = hType + (2 << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<18); + MEM_writeLE32(ostart, lhc); + break; + } + case 5: /* 2 - 2 - 18 - 18 */ + { U32 const lhc = hType + (3 << 2) + ((U32)litSize<<4) + ((U32)cLitSize<<22); + MEM_writeLE32(ostart, lhc); + ostart[4] = (BYTE)(cLitSize >> 10); + break; + } + default: /* not possible : lhSize is {3,4,5} */ + assert(0); + } + *entropyWritten = 1; + DEBUGLOG(5, "Compressed literals: %u -> %u", (U32)litSize, (U32)(op-ostart)); + return op-ostart; +} + +static size_t ZSTD_seqDecompressedSize(seqStore_t const* seqStore, const seqDef* sequences, size_t nbSeq, size_t litSize, int lastSequence) { + const seqDef* const sstart = sequences; + const seqDef* const send = sequences + nbSeq; + const seqDef* sp = sstart; + size_t matchLengthSum = 0; + size_t litLengthSum = 0; + while (send-sp > 0) { + ZSTD_sequenceLength const seqLen = ZSTD_getSequenceLength(seqStore, sp); + litLengthSum += seqLen.litLength; + matchLengthSum += seqLen.matchLength; + sp++; + } + assert(litLengthSum <= litSize); + if (!lastSequence) { + assert(litLengthSum == litSize); + } + return matchLengthSum + litSize; +} + +/* ZSTD_compressSubBlock_sequences() : + * Compresses sequences section for a sub-block. + * fseMetadata->llType, fseMetadata->ofType, and fseMetadata->mlType have + * symbol compression modes for the super-block. + * The first successfully compressed block will have these in its header. + * We set entropyWritten=1 when we succeed in compressing the sequences. + * The following sub-blocks will always have repeat mode. + * @return : compressed size of sequences section of a sub-block + * Or 0 if it is unable to compress + * Or error code. */ +static size_t ZSTD_compressSubBlock_sequences(const ZSTD_fseCTables_t* fseTables, + const ZSTD_fseCTablesMetadata_t* fseMetadata, + const seqDef* sequences, size_t nbSeq, + const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + const int bmi2, int writeEntropy, int* entropyWritten) +{ + const int longOffsets = cctxParams->cParams.windowLog > STREAM_ACCUMULATOR_MIN; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart; + BYTE* seqHead; + + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (nbSeq=%zu, writeEntropy=%d, longOffsets=%d)", nbSeq, writeEntropy, longOffsets); + + *entropyWritten = 0; + /* Sequences Header */ + RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/, + dstSize_tooSmall, ""); + if (nbSeq < 0x7F) + *op++ = (BYTE)nbSeq; + else if (nbSeq < LONGNBSEQ) + op[0] = (BYTE)((nbSeq>>8) + 0x80), op[1] = (BYTE)nbSeq, op+=2; + else + op[0]=0xFF, MEM_writeLE16(op+1, (U16)(nbSeq - LONGNBSEQ)), op+=3; + if (nbSeq==0) { + return op - ostart; + } + + /* seqHead : flags for FSE encoding type */ + seqHead = op++; + + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (seqHeadSize=%u)", (unsigned)(op-ostart)); + + if (writeEntropy) { + const U32 LLtype = fseMetadata->llType; + const U32 Offtype = fseMetadata->ofType; + const U32 MLtype = fseMetadata->mlType; + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (fseTablesSize=%zu)", fseMetadata->fseTablesSize); + *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2)); + ZSTD_memcpy(op, fseMetadata->fseTablesBuffer, fseMetadata->fseTablesSize); + op += fseMetadata->fseTablesSize; + } else { + const U32 repeat = set_repeat; + *seqHead = (BYTE)((repeat<<6) + (repeat<<4) + (repeat<<2)); + } + + { size_t const bitstreamSize = ZSTD_encodeSequences( + op, oend - op, + fseTables->matchlengthCTable, mlCode, + fseTables->offcodeCTable, ofCode, + fseTables->litlengthCTable, llCode, + sequences, nbSeq, + longOffsets, bmi2); + FORWARD_IF_ERROR(bitstreamSize, "ZSTD_encodeSequences failed"); + op += bitstreamSize; + /* zstd versions <= 1.3.4 mistakenly report corruption when + * FSE_readNCount() receives a buffer < 4 bytes. + * Fixed by https://github.com/facebook/zstd/pull/1146. + * This can happen when the last set_compressed table present is 2 + * bytes and the bitstream is only one byte. + * In this exceedingly rare case, we will simply emit an uncompressed + * block, since it isn't worth optimizing. + */ +#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + if (writeEntropy && fseMetadata->lastCountSize && fseMetadata->lastCountSize + bitstreamSize < 4) { + /* NCountSize >= 2 && bitstreamSize > 0 ==> lastCountSize == 3 */ + assert(fseMetadata->lastCountSize + bitstreamSize == 3); + DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.3.4 by " + "emitting an uncompressed block."); + return 0; + } +#endif + DEBUGLOG(5, "ZSTD_compressSubBlock_sequences (bitstreamSize=%zu)", bitstreamSize); + } + + /* zstd versions <= 1.4.0 mistakenly report error when + * sequences section body size is less than 3 bytes. + * Fixed by https://github.com/facebook/zstd/pull/1664. + * This can happen when the previous sequences section block is compressed + * with rle mode and the current block's sequences section is compressed + * with repeat mode where sequences section body size can be 1 byte. + */ +#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + if (op-seqHead < 4) { + DEBUGLOG(5, "Avoiding bug in zstd decoder in versions <= 1.4.0 by emitting " + "an uncompressed block when sequences are < 4 bytes"); + return 0; + } +#endif + + *entropyWritten = 1; + return op - ostart; +} + +/* ZSTD_compressSubBlock() : + * Compresses a single sub-block. + * @return : compressed size of the sub-block + * Or 0 if it failed to compress. */ +static size_t ZSTD_compressSubBlock(const ZSTD_entropyCTables_t* entropy, + const ZSTD_entropyCTablesMetadata_t* entropyMetadata, + const seqDef* sequences, size_t nbSeq, + const BYTE* literals, size_t litSize, + const BYTE* llCode, const BYTE* mlCode, const BYTE* ofCode, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + const int bmi2, + int writeLitEntropy, int writeSeqEntropy, + int* litEntropyWritten, int* seqEntropyWritten, + U32 lastBlock) +{ + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart + ZSTD_blockHeaderSize; + DEBUGLOG(5, "ZSTD_compressSubBlock (litSize=%zu, nbSeq=%zu, writeLitEntropy=%d, writeSeqEntropy=%d, lastBlock=%d)", + litSize, nbSeq, writeLitEntropy, writeSeqEntropy, lastBlock); + { size_t cLitSize = ZSTD_compressSubBlock_literal((const HUF_CElt*)entropy->huf.CTable, + &entropyMetadata->hufMetadata, literals, litSize, + op, oend-op, bmi2, writeLitEntropy, litEntropyWritten); + FORWARD_IF_ERROR(cLitSize, "ZSTD_compressSubBlock_literal failed"); + if (cLitSize == 0) return 0; + op += cLitSize; + } + { size_t cSeqSize = ZSTD_compressSubBlock_sequences(&entropy->fse, + &entropyMetadata->fseMetadata, + sequences, nbSeq, + llCode, mlCode, ofCode, + cctxParams, + op, oend-op, + bmi2, writeSeqEntropy, seqEntropyWritten); + FORWARD_IF_ERROR(cSeqSize, "ZSTD_compressSubBlock_sequences failed"); + if (cSeqSize == 0) return 0; + op += cSeqSize; + } + /* Write block header */ + { size_t cSize = (op-ostart)-ZSTD_blockHeaderSize; + U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3); + MEM_writeLE24(ostart, cBlockHeader24); + } + return op-ostart; +} + +static size_t ZSTD_estimateSubBlockSize_literal(const BYTE* literals, size_t litSize, + const ZSTD_hufCTables_t* huf, + const ZSTD_hufCTablesMetadata_t* hufMetadata, + void* workspace, size_t wkspSize, + int writeEntropy) +{ + unsigned* const countWksp = (unsigned*)workspace; + unsigned maxSymbolValue = 255; + size_t literalSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */ + + if (hufMetadata->hType == set_basic) return litSize; + else if (hufMetadata->hType == set_rle) return 1; + else if (hufMetadata->hType == set_compressed || hufMetadata->hType == set_repeat) { + size_t const largest = HIST_count_wksp (countWksp, &maxSymbolValue, (const BYTE*)literals, litSize, workspace, wkspSize); + if (ZSTD_isError(largest)) return litSize; + { size_t cLitSizeEstimate = HUF_estimateCompressedSize((const HUF_CElt*)huf->CTable, countWksp, maxSymbolValue); + if (writeEntropy) cLitSizeEstimate += hufMetadata->hufDesSize; + return cLitSizeEstimate + literalSectionHeaderSize; + } } + assert(0); /* impossible */ + return 0; +} + +static size_t ZSTD_estimateSubBlockSize_symbolType(symbolEncodingType_e type, + const BYTE* codeTable, unsigned maxCode, + size_t nbSeq, const FSE_CTable* fseCTable, + const U32* additionalBits, + short const* defaultNorm, U32 defaultNormLog, U32 defaultMax, + void* workspace, size_t wkspSize) +{ + unsigned* const countWksp = (unsigned*)workspace; + const BYTE* ctp = codeTable; + const BYTE* const ctStart = ctp; + const BYTE* const ctEnd = ctStart + nbSeq; + size_t cSymbolTypeSizeEstimateInBits = 0; + unsigned max = maxCode; + + HIST_countFast_wksp(countWksp, &max, codeTable, nbSeq, workspace, wkspSize); /* can't fail */ + if (type == set_basic) { + /* We selected this encoding type, so it must be valid. */ + assert(max <= defaultMax); + cSymbolTypeSizeEstimateInBits = max <= defaultMax + ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, countWksp, max) + : ERROR(GENERIC); + } else if (type == set_rle) { + cSymbolTypeSizeEstimateInBits = 0; + } else if (type == set_compressed || type == set_repeat) { + cSymbolTypeSizeEstimateInBits = ZSTD_fseBitCost(fseCTable, countWksp, max); + } + if (ZSTD_isError(cSymbolTypeSizeEstimateInBits)) return nbSeq * 10; + while (ctp < ctEnd) { + if (additionalBits) cSymbolTypeSizeEstimateInBits += additionalBits[*ctp]; + else cSymbolTypeSizeEstimateInBits += *ctp; /* for offset, offset code is also the number of additional bits */ + ctp++; + } + return cSymbolTypeSizeEstimateInBits / 8; +} + +static size_t ZSTD_estimateSubBlockSize_sequences(const BYTE* ofCodeTable, + const BYTE* llCodeTable, + const BYTE* mlCodeTable, + size_t nbSeq, + const ZSTD_fseCTables_t* fseTables, + const ZSTD_fseCTablesMetadata_t* fseMetadata, + void* workspace, size_t wkspSize, + int writeEntropy) +{ + size_t sequencesSectionHeaderSize = 3; /* Use hard coded size of 3 bytes */ + size_t cSeqSizeEstimate = 0; + cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->ofType, ofCodeTable, MaxOff, + nbSeq, fseTables->offcodeCTable, NULL, + OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff, + workspace, wkspSize); + cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->llType, llCodeTable, MaxLL, + nbSeq, fseTables->litlengthCTable, LL_bits, + LL_defaultNorm, LL_defaultNormLog, MaxLL, + workspace, wkspSize); + cSeqSizeEstimate += ZSTD_estimateSubBlockSize_symbolType(fseMetadata->mlType, mlCodeTable, MaxML, + nbSeq, fseTables->matchlengthCTable, ML_bits, + ML_defaultNorm, ML_defaultNormLog, MaxML, + workspace, wkspSize); + if (writeEntropy) cSeqSizeEstimate += fseMetadata->fseTablesSize; + return cSeqSizeEstimate + sequencesSectionHeaderSize; +} + +static size_t ZSTD_estimateSubBlockSize(const BYTE* literals, size_t litSize, + const BYTE* ofCodeTable, + const BYTE* llCodeTable, + const BYTE* mlCodeTable, + size_t nbSeq, + const ZSTD_entropyCTables_t* entropy, + const ZSTD_entropyCTablesMetadata_t* entropyMetadata, + void* workspace, size_t wkspSize, + int writeLitEntropy, int writeSeqEntropy) { + size_t cSizeEstimate = 0; + cSizeEstimate += ZSTD_estimateSubBlockSize_literal(literals, litSize, + &entropy->huf, &entropyMetadata->hufMetadata, + workspace, wkspSize, writeLitEntropy); + cSizeEstimate += ZSTD_estimateSubBlockSize_sequences(ofCodeTable, llCodeTable, mlCodeTable, + nbSeq, &entropy->fse, &entropyMetadata->fseMetadata, + workspace, wkspSize, writeSeqEntropy); + return cSizeEstimate + ZSTD_blockHeaderSize; +} + +static int ZSTD_needSequenceEntropyTables(ZSTD_fseCTablesMetadata_t const* fseMetadata) +{ + if (fseMetadata->llType == set_compressed || fseMetadata->llType == set_rle) + return 1; + if (fseMetadata->mlType == set_compressed || fseMetadata->mlType == set_rle) + return 1; + if (fseMetadata->ofType == set_compressed || fseMetadata->ofType == set_rle) + return 1; + return 0; +} + +/* ZSTD_compressSubBlock_multi() : + * Breaks super-block into multiple sub-blocks and compresses them. + * Entropy will be written to the first block. + * The following blocks will use repeat mode to compress. + * All sub-blocks are compressed blocks (no raw or rle blocks). + * @return : compressed size of the super block (which is multiple ZSTD blocks) + * Or 0 if it failed to compress. */ +static size_t ZSTD_compressSubBlock_multi(const seqStore_t* seqStorePtr, + const ZSTD_compressedBlockState_t* prevCBlock, + ZSTD_compressedBlockState_t* nextCBlock, + const ZSTD_entropyCTablesMetadata_t* entropyMetadata, + const ZSTD_CCtx_params* cctxParams, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const int bmi2, U32 lastBlock, + void* workspace, size_t wkspSize) +{ + const seqDef* const sstart = seqStorePtr->sequencesStart; + const seqDef* const send = seqStorePtr->sequences; + const seqDef* sp = sstart; + const BYTE* const lstart = seqStorePtr->litStart; + const BYTE* const lend = seqStorePtr->lit; + const BYTE* lp = lstart; + BYTE const* ip = (BYTE const*)src; + BYTE const* const iend = ip + srcSize; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + dstCapacity; + BYTE* op = ostart; + const BYTE* llCodePtr = seqStorePtr->llCode; + const BYTE* mlCodePtr = seqStorePtr->mlCode; + const BYTE* ofCodePtr = seqStorePtr->ofCode; + size_t targetCBlockSize = cctxParams->targetCBlockSize; + size_t litSize, seqCount; + int writeLitEntropy = entropyMetadata->hufMetadata.hType == set_compressed; + int writeSeqEntropy = 1; + int lastSequence = 0; + + DEBUGLOG(5, "ZSTD_compressSubBlock_multi (litSize=%u, nbSeq=%u)", + (unsigned)(lend-lp), (unsigned)(send-sstart)); + + litSize = 0; + seqCount = 0; + do { + size_t cBlockSizeEstimate = 0; + if (sstart == send) { + lastSequence = 1; + } else { + const seqDef* const sequence = sp + seqCount; + lastSequence = sequence == send - 1; + litSize += ZSTD_getSequenceLength(seqStorePtr, sequence).litLength; + seqCount++; + } + if (lastSequence) { + assert(lp <= lend); + assert(litSize <= (size_t)(lend - lp)); + litSize = (size_t)(lend - lp); + } + /* I think there is an optimization opportunity here. + * Calling ZSTD_estimateSubBlockSize for every sequence can be wasteful + * since it recalculates estimate from scratch. + * For example, it would recount literal distribution and symbol codes everytime. + */ + cBlockSizeEstimate = ZSTD_estimateSubBlockSize(lp, litSize, ofCodePtr, llCodePtr, mlCodePtr, seqCount, + &nextCBlock->entropy, entropyMetadata, + workspace, wkspSize, writeLitEntropy, writeSeqEntropy); + if (cBlockSizeEstimate > targetCBlockSize || lastSequence) { + int litEntropyWritten = 0; + int seqEntropyWritten = 0; + const size_t decompressedSize = ZSTD_seqDecompressedSize(seqStorePtr, sp, seqCount, litSize, lastSequence); + const size_t cSize = ZSTD_compressSubBlock(&nextCBlock->entropy, entropyMetadata, + sp, seqCount, + lp, litSize, + llCodePtr, mlCodePtr, ofCodePtr, + cctxParams, + op, oend-op, + bmi2, writeLitEntropy, writeSeqEntropy, + &litEntropyWritten, &seqEntropyWritten, + lastBlock && lastSequence); + FORWARD_IF_ERROR(cSize, "ZSTD_compressSubBlock failed"); + if (cSize > 0 && cSize < decompressedSize) { + DEBUGLOG(5, "Committed the sub-block"); + assert(ip + decompressedSize <= iend); + ip += decompressedSize; + sp += seqCount; + lp += litSize; + op += cSize; + llCodePtr += seqCount; + mlCodePtr += seqCount; + ofCodePtr += seqCount; + litSize = 0; + seqCount = 0; + /* Entropy only needs to be written once */ + if (litEntropyWritten) { + writeLitEntropy = 0; + } + if (seqEntropyWritten) { + writeSeqEntropy = 0; + } + } + } + } while (!lastSequence); + if (writeLitEntropy) { + DEBUGLOG(5, "ZSTD_compressSubBlock_multi has literal entropy tables unwritten"); + ZSTD_memcpy(&nextCBlock->entropy.huf, &prevCBlock->entropy.huf, sizeof(prevCBlock->entropy.huf)); + } + if (writeSeqEntropy && ZSTD_needSequenceEntropyTables(&entropyMetadata->fseMetadata)) { + /* If we haven't written our entropy tables, then we've violated our contract and + * must emit an uncompressed block. + */ + DEBUGLOG(5, "ZSTD_compressSubBlock_multi has sequence entropy tables unwritten"); + return 0; + } + if (ip < iend) { + size_t const cSize = ZSTD_noCompressBlock(op, oend - op, ip, iend - ip, lastBlock); + DEBUGLOG(5, "ZSTD_compressSubBlock_multi last sub-block uncompressed, %zu bytes", (size_t)(iend - ip)); + FORWARD_IF_ERROR(cSize, "ZSTD_noCompressBlock failed"); + assert(cSize != 0); + op += cSize; + /* We have to regenerate the repcodes because we've skipped some sequences */ + if (sp < send) { + seqDef const* seq; + repcodes_t rep; + ZSTD_memcpy(&rep, prevCBlock->rep, sizeof(rep)); + for (seq = sstart; seq < sp; ++seq) { + rep = ZSTD_updateRep(rep.rep, seq->offset - 1, ZSTD_getSequenceLength(seqStorePtr, seq).litLength == 0); + } + ZSTD_memcpy(nextCBlock->rep, &rep, sizeof(rep)); + } + } + DEBUGLOG(5, "ZSTD_compressSubBlock_multi compressed"); + return op-ostart; +} + +size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc, + void* dst, size_t dstCapacity, + void const* src, size_t srcSize, + unsigned lastBlock) { + ZSTD_entropyCTablesMetadata_t entropyMetadata; + + FORWARD_IF_ERROR(ZSTD_buildSuperBlockEntropy(&zc->seqStore, + &zc->blockState.prevCBlock->entropy, + &zc->blockState.nextCBlock->entropy, + &zc->appliedParams, + &entropyMetadata, + zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */), ""); + + return ZSTD_compressSubBlock_multi(&zc->seqStore, + zc->blockState.prevCBlock, + zc->blockState.nextCBlock, + &entropyMetadata, + &zc->appliedParams, + dst, dstCapacity, + src, srcSize, + zc->bmi2, lastBlock, + zc->entropyWorkspace, ENTROPY_WORKSPACE_SIZE /* statically allocated in resetCCtx */); +} diff --git a/lib/zstd/compress/zstd_compress_superblock.h b/lib/zstd/compress/zstd_compress_superblock.h new file mode 100644 index 000000000000..224ece79546e --- /dev/null +++ b/lib/zstd/compress/zstd_compress_superblock.h @@ -0,0 +1,32 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_COMPRESS_ADVANCED_H +#define ZSTD_COMPRESS_ADVANCED_H + +/*-************************************* +* Dependencies +***************************************/ + +#include /* ZSTD_CCtx */ + +/*-************************************* +* Target Compressed Block Size +***************************************/ + +/* ZSTD_compressSuperBlock() : + * Used to compress a super block when targetCBlockSize is being used. + * The given block will be compressed into multiple sub blocks that are around targetCBlockSize. */ +size_t ZSTD_compressSuperBlock(ZSTD_CCtx* zc, + void* dst, size_t dstCapacity, + void const* src, size_t srcSize, + unsigned lastBlock); + +#endif /* ZSTD_COMPRESS_ADVANCED_H */ diff --git a/lib/zstd/compress/zstd_cwksp.h b/lib/zstd/compress/zstd_cwksp.h new file mode 100644 index 000000000000..98e359adf5d4 --- /dev/null +++ b/lib/zstd/compress/zstd_cwksp.h @@ -0,0 +1,482 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_CWKSP_H +#define ZSTD_CWKSP_H + +/*-************************************* +* Dependencies +***************************************/ +#include "../common/zstd_internal.h" + + +/*-************************************* +* Constants +***************************************/ + +/* Since the workspace is effectively its own little malloc implementation / + * arena, when we run under ASAN, we should similarly insert redzones between + * each internal element of the workspace, so ASAN will catch overruns that + * reach outside an object but that stay inside the workspace. + * + * This defines the size of that redzone. + */ +#ifndef ZSTD_CWKSP_ASAN_REDZONE_SIZE +#define ZSTD_CWKSP_ASAN_REDZONE_SIZE 128 +#endif + +/*-************************************* +* Structures +***************************************/ +typedef enum { + ZSTD_cwksp_alloc_objects, + ZSTD_cwksp_alloc_buffers, + ZSTD_cwksp_alloc_aligned +} ZSTD_cwksp_alloc_phase_e; + +/* + * Used to describe whether the workspace is statically allocated (and will not + * necessarily ever be freed), or if it's dynamically allocated and we can + * expect a well-formed caller to free this. + */ +typedef enum { + ZSTD_cwksp_dynamic_alloc, + ZSTD_cwksp_static_alloc +} ZSTD_cwksp_static_alloc_e; + +/* + * Zstd fits all its internal datastructures into a single continuous buffer, + * so that it only needs to perform a single OS allocation (or so that a buffer + * can be provided to it and it can perform no allocations at all). This buffer + * is called the workspace. + * + * Several optimizations complicate that process of allocating memory ranges + * from this workspace for each internal datastructure: + * + * - These different internal datastructures have different setup requirements: + * + * - The static objects need to be cleared once and can then be trivially + * reused for each compression. + * + * - Various buffers don't need to be initialized at all--they are always + * written into before they're read. + * + * - The matchstate tables have a unique requirement that they don't need + * their memory to be totally cleared, but they do need the memory to have + * some bound, i.e., a guarantee that all values in the memory they've been + * allocated is less than some maximum value (which is the starting value + * for the indices that they will then use for compression). When this + * guarantee is provided to them, they can use the memory without any setup + * work. When it can't, they have to clear the area. + * + * - These buffers also have different alignment requirements. + * + * - We would like to reuse the objects in the workspace for multiple + * compressions without having to perform any expensive reallocation or + * reinitialization work. + * + * - We would like to be able to efficiently reuse the workspace across + * multiple compressions **even when the compression parameters change** and + * we need to resize some of the objects (where possible). + * + * To attempt to manage this buffer, given these constraints, the ZSTD_cwksp + * abstraction was created. It works as follows: + * + * Workspace Layout: + * + * [ ... workspace ... ] + * [objects][tables ... ->] free space [<- ... aligned][<- ... buffers] + * + * The various objects that live in the workspace are divided into the + * following categories, and are allocated separately: + * + * - Static objects: this is optionally the enclosing ZSTD_CCtx or ZSTD_CDict, + * so that literally everything fits in a single buffer. Note: if present, + * this must be the first object in the workspace, since ZSTD_customFree{CCtx, + * CDict}() rely on a pointer comparison to see whether one or two frees are + * required. + * + * - Fixed size objects: these are fixed-size, fixed-count objects that are + * nonetheless "dynamically" allocated in the workspace so that we can + * control how they're initialized separately from the broader ZSTD_CCtx. + * Examples: + * - Entropy Workspace + * - 2 x ZSTD_compressedBlockState_t + * - CDict dictionary contents + * + * - Tables: these are any of several different datastructures (hash tables, + * chain tables, binary trees) that all respect a common format: they are + * uint32_t arrays, all of whose values are between 0 and (nextSrc - base). + * Their sizes depend on the cparams. + * + * - Aligned: these buffers are used for various purposes that require 4 byte + * alignment, but don't require any initialization before they're used. + * + * - Buffers: these buffers are used for various purposes that don't require + * any alignment or initialization before they're used. This means they can + * be moved around at no cost for a new compression. + * + * Allocating Memory: + * + * The various types of objects must be allocated in order, so they can be + * correctly packed into the workspace buffer. That order is: + * + * 1. Objects + * 2. Buffers + * 3. Aligned + * 4. Tables + * + * Attempts to reserve objects of different types out of order will fail. + */ +typedef struct { + void* workspace; + void* workspaceEnd; + + void* objectEnd; + void* tableEnd; + void* tableValidEnd; + void* allocStart; + + BYTE allocFailed; + int workspaceOversizedDuration; + ZSTD_cwksp_alloc_phase_e phase; + ZSTD_cwksp_static_alloc_e isStatic; +} ZSTD_cwksp; + +/*-************************************* +* Functions +***************************************/ + +MEM_STATIC size_t ZSTD_cwksp_available_space(ZSTD_cwksp* ws); + +MEM_STATIC void ZSTD_cwksp_assert_internal_consistency(ZSTD_cwksp* ws) { + (void)ws; + assert(ws->workspace <= ws->objectEnd); + assert(ws->objectEnd <= ws->tableEnd); + assert(ws->objectEnd <= ws->tableValidEnd); + assert(ws->tableEnd <= ws->allocStart); + assert(ws->tableValidEnd <= ws->allocStart); + assert(ws->allocStart <= ws->workspaceEnd); +} + +/* + * Align must be a power of 2. + */ +MEM_STATIC size_t ZSTD_cwksp_align(size_t size, size_t const align) { + size_t const mask = align - 1; + assert((align & mask) == 0); + return (size + mask) & ~mask; +} + +/* + * Use this to determine how much space in the workspace we will consume to + * allocate this object. (Normally it should be exactly the size of the object, + * but under special conditions, like ASAN, where we pad each object, it might + * be larger.) + * + * Since tables aren't currently redzoned, you don't need to call through this + * to figure out how much space you need for the matchState tables. Everything + * else is though. + */ +MEM_STATIC size_t ZSTD_cwksp_alloc_size(size_t size) { + if (size == 0) + return 0; + return size; +} + +MEM_STATIC void ZSTD_cwksp_internal_advance_phase( + ZSTD_cwksp* ws, ZSTD_cwksp_alloc_phase_e phase) { + assert(phase >= ws->phase); + if (phase > ws->phase) { + if (ws->phase < ZSTD_cwksp_alloc_buffers && + phase >= ZSTD_cwksp_alloc_buffers) { + ws->tableValidEnd = ws->objectEnd; + } + if (ws->phase < ZSTD_cwksp_alloc_aligned && + phase >= ZSTD_cwksp_alloc_aligned) { + /* If unaligned allocations down from a too-large top have left us + * unaligned, we need to realign our alloc ptr. Technically, this + * can consume space that is unaccounted for in the neededSpace + * calculation. However, I believe this can only happen when the + * workspace is too large, and specifically when it is too large + * by a larger margin than the space that will be consumed. */ + /* TODO: cleaner, compiler warning friendly way to do this??? */ + ws->allocStart = (BYTE*)ws->allocStart - ((size_t)ws->allocStart & (sizeof(U32)-1)); + if (ws->allocStart < ws->tableValidEnd) { + ws->tableValidEnd = ws->allocStart; + } + } + ws->phase = phase; + } +} + +/* + * Returns whether this object/buffer/etc was allocated in this workspace. + */ +MEM_STATIC int ZSTD_cwksp_owns_buffer(const ZSTD_cwksp* ws, const void* ptr) { + return (ptr != NULL) && (ws->workspace <= ptr) && (ptr <= ws->workspaceEnd); +} + +/* + * Internal function. Do not use directly. + */ +MEM_STATIC void* ZSTD_cwksp_reserve_internal( + ZSTD_cwksp* ws, size_t bytes, ZSTD_cwksp_alloc_phase_e phase) { + void* alloc; + void* bottom = ws->tableEnd; + ZSTD_cwksp_internal_advance_phase(ws, phase); + alloc = (BYTE *)ws->allocStart - bytes; + + if (bytes == 0) + return NULL; + + + DEBUGLOG(5, "cwksp: reserving %p %zd bytes, %zd bytes remaining", + alloc, bytes, ZSTD_cwksp_available_space(ws) - bytes); + ZSTD_cwksp_assert_internal_consistency(ws); + assert(alloc >= bottom); + if (alloc < bottom) { + DEBUGLOG(4, "cwksp: alloc failed!"); + ws->allocFailed = 1; + return NULL; + } + if (alloc < ws->tableValidEnd) { + ws->tableValidEnd = alloc; + } + ws->allocStart = alloc; + + + return alloc; +} + +/* + * Reserves and returns unaligned memory. + */ +MEM_STATIC BYTE* ZSTD_cwksp_reserve_buffer(ZSTD_cwksp* ws, size_t bytes) { + return (BYTE*)ZSTD_cwksp_reserve_internal(ws, bytes, ZSTD_cwksp_alloc_buffers); +} + +/* + * Reserves and returns memory sized on and aligned on sizeof(unsigned). + */ +MEM_STATIC void* ZSTD_cwksp_reserve_aligned(ZSTD_cwksp* ws, size_t bytes) { + assert((bytes & (sizeof(U32)-1)) == 0); + return ZSTD_cwksp_reserve_internal(ws, ZSTD_cwksp_align(bytes, sizeof(U32)), ZSTD_cwksp_alloc_aligned); +} + +/* + * Aligned on sizeof(unsigned). These buffers have the special property that + * their values remain constrained, allowing us to re-use them without + * memset()-ing them. + */ +MEM_STATIC void* ZSTD_cwksp_reserve_table(ZSTD_cwksp* ws, size_t bytes) { + const ZSTD_cwksp_alloc_phase_e phase = ZSTD_cwksp_alloc_aligned; + void* alloc = ws->tableEnd; + void* end = (BYTE *)alloc + bytes; + void* top = ws->allocStart; + + DEBUGLOG(5, "cwksp: reserving %p table %zd bytes, %zd bytes remaining", + alloc, bytes, ZSTD_cwksp_available_space(ws) - bytes); + assert((bytes & (sizeof(U32)-1)) == 0); + ZSTD_cwksp_internal_advance_phase(ws, phase); + ZSTD_cwksp_assert_internal_consistency(ws); + assert(end <= top); + if (end > top) { + DEBUGLOG(4, "cwksp: table alloc failed!"); + ws->allocFailed = 1; + return NULL; + } + ws->tableEnd = end; + + + return alloc; +} + +/* + * Aligned on sizeof(void*). + */ +MEM_STATIC void* ZSTD_cwksp_reserve_object(ZSTD_cwksp* ws, size_t bytes) { + size_t roundedBytes = ZSTD_cwksp_align(bytes, sizeof(void*)); + void* alloc = ws->objectEnd; + void* end = (BYTE*)alloc + roundedBytes; + + + DEBUGLOG(5, + "cwksp: reserving %p object %zd bytes (rounded to %zd), %zd bytes remaining", + alloc, bytes, roundedBytes, ZSTD_cwksp_available_space(ws) - roundedBytes); + assert(((size_t)alloc & (sizeof(void*)-1)) == 0); + assert((bytes & (sizeof(void*)-1)) == 0); + ZSTD_cwksp_assert_internal_consistency(ws); + /* we must be in the first phase, no advance is possible */ + if (ws->phase != ZSTD_cwksp_alloc_objects || end > ws->workspaceEnd) { + DEBUGLOG(4, "cwksp: object alloc failed!"); + ws->allocFailed = 1; + return NULL; + } + ws->objectEnd = end; + ws->tableEnd = end; + ws->tableValidEnd = end; + + + return alloc; +} + +MEM_STATIC void ZSTD_cwksp_mark_tables_dirty(ZSTD_cwksp* ws) { + DEBUGLOG(4, "cwksp: ZSTD_cwksp_mark_tables_dirty"); + + + assert(ws->tableValidEnd >= ws->objectEnd); + assert(ws->tableValidEnd <= ws->allocStart); + ws->tableValidEnd = ws->objectEnd; + ZSTD_cwksp_assert_internal_consistency(ws); +} + +MEM_STATIC void ZSTD_cwksp_mark_tables_clean(ZSTD_cwksp* ws) { + DEBUGLOG(4, "cwksp: ZSTD_cwksp_mark_tables_clean"); + assert(ws->tableValidEnd >= ws->objectEnd); + assert(ws->tableValidEnd <= ws->allocStart); + if (ws->tableValidEnd < ws->tableEnd) { + ws->tableValidEnd = ws->tableEnd; + } + ZSTD_cwksp_assert_internal_consistency(ws); +} + +/* + * Zero the part of the allocated tables not already marked clean. + */ +MEM_STATIC void ZSTD_cwksp_clean_tables(ZSTD_cwksp* ws) { + DEBUGLOG(4, "cwksp: ZSTD_cwksp_clean_tables"); + assert(ws->tableValidEnd >= ws->objectEnd); + assert(ws->tableValidEnd <= ws->allocStart); + if (ws->tableValidEnd < ws->tableEnd) { + ZSTD_memset(ws->tableValidEnd, 0, (BYTE*)ws->tableEnd - (BYTE*)ws->tableValidEnd); + } + ZSTD_cwksp_mark_tables_clean(ws); +} + +/* + * Invalidates table allocations. + * All other allocations remain valid. + */ +MEM_STATIC void ZSTD_cwksp_clear_tables(ZSTD_cwksp* ws) { + DEBUGLOG(4, "cwksp: clearing tables!"); + + + ws->tableEnd = ws->objectEnd; + ZSTD_cwksp_assert_internal_consistency(ws); +} + +/* + * Invalidates all buffer, aligned, and table allocations. + * Object allocations remain valid. + */ +MEM_STATIC void ZSTD_cwksp_clear(ZSTD_cwksp* ws) { + DEBUGLOG(4, "cwksp: clearing!"); + + + + ws->tableEnd = ws->objectEnd; + ws->allocStart = ws->workspaceEnd; + ws->allocFailed = 0; + if (ws->phase > ZSTD_cwksp_alloc_buffers) { + ws->phase = ZSTD_cwksp_alloc_buffers; + } + ZSTD_cwksp_assert_internal_consistency(ws); +} + +/* + * The provided workspace takes ownership of the buffer [start, start+size). + * Any existing values in the workspace are ignored (the previously managed + * buffer, if present, must be separately freed). + */ +MEM_STATIC void ZSTD_cwksp_init(ZSTD_cwksp* ws, void* start, size_t size, ZSTD_cwksp_static_alloc_e isStatic) { + DEBUGLOG(4, "cwksp: init'ing workspace with %zd bytes", size); + assert(((size_t)start & (sizeof(void*)-1)) == 0); /* ensure correct alignment */ + ws->workspace = start; + ws->workspaceEnd = (BYTE*)start + size; + ws->objectEnd = ws->workspace; + ws->tableValidEnd = ws->objectEnd; + ws->phase = ZSTD_cwksp_alloc_objects; + ws->isStatic = isStatic; + ZSTD_cwksp_clear(ws); + ws->workspaceOversizedDuration = 0; + ZSTD_cwksp_assert_internal_consistency(ws); +} + +MEM_STATIC size_t ZSTD_cwksp_create(ZSTD_cwksp* ws, size_t size, ZSTD_customMem customMem) { + void* workspace = ZSTD_customMalloc(size, customMem); + DEBUGLOG(4, "cwksp: creating new workspace with %zd bytes", size); + RETURN_ERROR_IF(workspace == NULL, memory_allocation, "NULL pointer!"); + ZSTD_cwksp_init(ws, workspace, size, ZSTD_cwksp_dynamic_alloc); + return 0; +} + +MEM_STATIC void ZSTD_cwksp_free(ZSTD_cwksp* ws, ZSTD_customMem customMem) { + void *ptr = ws->workspace; + DEBUGLOG(4, "cwksp: freeing workspace"); + ZSTD_memset(ws, 0, sizeof(ZSTD_cwksp)); + ZSTD_customFree(ptr, customMem); +} + +/* + * Moves the management of a workspace from one cwksp to another. The src cwksp + * is left in an invalid state (src must be re-init()'ed before it's used again). + */ +MEM_STATIC void ZSTD_cwksp_move(ZSTD_cwksp* dst, ZSTD_cwksp* src) { + *dst = *src; + ZSTD_memset(src, 0, sizeof(ZSTD_cwksp)); +} + +MEM_STATIC size_t ZSTD_cwksp_sizeof(const ZSTD_cwksp* ws) { + return (size_t)((BYTE*)ws->workspaceEnd - (BYTE*)ws->workspace); +} + +MEM_STATIC size_t ZSTD_cwksp_used(const ZSTD_cwksp* ws) { + return (size_t)((BYTE*)ws->tableEnd - (BYTE*)ws->workspace) + + (size_t)((BYTE*)ws->workspaceEnd - (BYTE*)ws->allocStart); +} + +MEM_STATIC int ZSTD_cwksp_reserve_failed(const ZSTD_cwksp* ws) { + return ws->allocFailed; +} + +/*-************************************* +* Functions Checking Free Space +***************************************/ + +MEM_STATIC size_t ZSTD_cwksp_available_space(ZSTD_cwksp* ws) { + return (size_t)((BYTE*)ws->allocStart - (BYTE*)ws->tableEnd); +} + +MEM_STATIC int ZSTD_cwksp_check_available(ZSTD_cwksp* ws, size_t additionalNeededSpace) { + return ZSTD_cwksp_available_space(ws) >= additionalNeededSpace; +} + +MEM_STATIC int ZSTD_cwksp_check_too_large(ZSTD_cwksp* ws, size_t additionalNeededSpace) { + return ZSTD_cwksp_check_available( + ws, additionalNeededSpace * ZSTD_WORKSPACETOOLARGE_FACTOR); +} + +MEM_STATIC int ZSTD_cwksp_check_wasteful(ZSTD_cwksp* ws, size_t additionalNeededSpace) { + return ZSTD_cwksp_check_too_large(ws, additionalNeededSpace) + && ws->workspaceOversizedDuration > ZSTD_WORKSPACETOOLARGE_MAXDURATION; +} + +MEM_STATIC void ZSTD_cwksp_bump_oversized_duration( + ZSTD_cwksp* ws, size_t additionalNeededSpace) { + if (ZSTD_cwksp_check_too_large(ws, additionalNeededSpace)) { + ws->workspaceOversizedDuration++; + } else { + ws->workspaceOversizedDuration = 0; + } +} + + +#endif /* ZSTD_CWKSP_H */ diff --git a/lib/zstd/compress/zstd_double_fast.c b/lib/zstd/compress/zstd_double_fast.c new file mode 100644 index 000000000000..b0424d23ac57 --- /dev/null +++ b/lib/zstd/compress/zstd_double_fast.c @@ -0,0 +1,519 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include "zstd_compress_internal.h" +#include "zstd_double_fast.h" + + +void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms, + void const* end, ZSTD_dictTableLoadMethod_e dtlm) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashLarge = ms->hashTable; + U32 const hBitsL = cParams->hashLog; + U32 const mls = cParams->minMatch; + U32* const hashSmall = ms->chainTable; + U32 const hBitsS = cParams->chainLog; + const BYTE* const base = ms->window.base; + const BYTE* ip = base + ms->nextToUpdate; + const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; + const U32 fastHashFillStep = 3; + + /* Always insert every fastHashFillStep position into the hash tables. + * Insert the other positions into the large hash table if their entry + * is empty. + */ + for (; ip + fastHashFillStep - 1 <= iend; ip += fastHashFillStep) { + U32 const curr = (U32)(ip - base); + U32 i; + for (i = 0; i < fastHashFillStep; ++i) { + size_t const smHash = ZSTD_hashPtr(ip + i, hBitsS, mls); + size_t const lgHash = ZSTD_hashPtr(ip + i, hBitsL, 8); + if (i == 0) + hashSmall[smHash] = curr + i; + if (i == 0 || hashLarge[lgHash] == 0) + hashLarge[lgHash] = curr + i; + /* Only load extra positions for ZSTD_dtlm_full */ + if (dtlm == ZSTD_dtlm_fast) + break; + } } +} + + +FORCE_INLINE_TEMPLATE +size_t ZSTD_compressBlock_doubleFast_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, + U32 const mls /* template */, ZSTD_dictMode_e const dictMode) +{ + ZSTD_compressionParameters const* cParams = &ms->cParams; + U32* const hashLong = ms->hashTable; + const U32 hBitsL = cParams->hashLog; + U32* const hashSmall = ms->chainTable; + const U32 hBitsS = cParams->chainLog; + const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); + /* presumes that, if there is a dictionary, it must be using Attach mode */ + const U32 prefixLowestIndex = ZSTD_getLowestPrefixIndex(ms, endIndex, cParams->windowLog); + const BYTE* const prefixLowest = base + prefixLowestIndex; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - HASH_READ_SIZE; + U32 offset_1=rep[0], offset_2=rep[1]; + U32 offsetSaved = 0; + + const ZSTD_matchState_t* const dms = ms->dictMatchState; + const ZSTD_compressionParameters* const dictCParams = + dictMode == ZSTD_dictMatchState ? + &dms->cParams : NULL; + const U32* const dictHashLong = dictMode == ZSTD_dictMatchState ? + dms->hashTable : NULL; + const U32* const dictHashSmall = dictMode == ZSTD_dictMatchState ? + dms->chainTable : NULL; + const U32 dictStartIndex = dictMode == ZSTD_dictMatchState ? + dms->window.dictLimit : 0; + const BYTE* const dictBase = dictMode == ZSTD_dictMatchState ? + dms->window.base : NULL; + const BYTE* const dictStart = dictMode == ZSTD_dictMatchState ? + dictBase + dictStartIndex : NULL; + const BYTE* const dictEnd = dictMode == ZSTD_dictMatchState ? + dms->window.nextSrc : NULL; + const U32 dictIndexDelta = dictMode == ZSTD_dictMatchState ? + prefixLowestIndex - (U32)(dictEnd - dictBase) : + 0; + const U32 dictHBitsL = dictMode == ZSTD_dictMatchState ? + dictCParams->hashLog : hBitsL; + const U32 dictHBitsS = dictMode == ZSTD_dictMatchState ? + dictCParams->chainLog : hBitsS; + const U32 dictAndPrefixLength = (U32)((ip - prefixLowest) + (dictEnd - dictStart)); + + DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_generic"); + + assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState); + + /* if a dictionary is attached, it must be within window range */ + if (dictMode == ZSTD_dictMatchState) { + assert(ms->window.dictLimit + (1U << cParams->windowLog) >= endIndex); + } + + /* init */ + ip += (dictAndPrefixLength == 0); + if (dictMode == ZSTD_noDict) { + U32 const curr = (U32)(ip - base); + U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, cParams->windowLog); + U32 const maxRep = curr - windowLow; + if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0; + if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0; + } + if (dictMode == ZSTD_dictMatchState) { + /* dictMatchState repCode checks don't currently handle repCode == 0 + * disabling. */ + assert(offset_1 <= dictAndPrefixLength); + assert(offset_2 <= dictAndPrefixLength); + } + + /* Main Search Loop */ + while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ + size_t mLength; + U32 offset; + size_t const h2 = ZSTD_hashPtr(ip, hBitsL, 8); + size_t const h = ZSTD_hashPtr(ip, hBitsS, mls); + size_t const dictHL = ZSTD_hashPtr(ip, dictHBitsL, 8); + size_t const dictHS = ZSTD_hashPtr(ip, dictHBitsS, mls); + U32 const curr = (U32)(ip-base); + U32 const matchIndexL = hashLong[h2]; + U32 matchIndexS = hashSmall[h]; + const BYTE* matchLong = base + matchIndexL; + const BYTE* match = base + matchIndexS; + const U32 repIndex = curr + 1 - offset_1; + const BYTE* repMatch = (dictMode == ZSTD_dictMatchState + && repIndex < prefixLowestIndex) ? + dictBase + (repIndex - dictIndexDelta) : + base + repIndex; + hashLong[h2] = hashSmall[h] = curr; /* update hash tables */ + + /* check dictMatchState repcode */ + if (dictMode == ZSTD_dictMatchState + && ((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */) + && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { + const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend; + mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4; + ip++; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH); + goto _match_stored; + } + + /* check noDict repcode */ + if ( dictMode == ZSTD_noDict + && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) { + mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4; + ip++; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH); + goto _match_stored; + } + + if (matchIndexL > prefixLowestIndex) { + /* check prefix long match */ + if (MEM_read64(matchLong) == MEM_read64(ip)) { + mLength = ZSTD_count(ip+8, matchLong+8, iend) + 8; + offset = (U32)(ip-matchLong); + while (((ip>anchor) & (matchLong>prefixLowest)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ + goto _match_found; + } + } else if (dictMode == ZSTD_dictMatchState) { + /* check dictMatchState long match */ + U32 const dictMatchIndexL = dictHashLong[dictHL]; + const BYTE* dictMatchL = dictBase + dictMatchIndexL; + assert(dictMatchL < dictEnd); + + if (dictMatchL > dictStart && MEM_read64(dictMatchL) == MEM_read64(ip)) { + mLength = ZSTD_count_2segments(ip+8, dictMatchL+8, iend, dictEnd, prefixLowest) + 8; + offset = (U32)(curr - dictMatchIndexL - dictIndexDelta); + while (((ip>anchor) & (dictMatchL>dictStart)) && (ip[-1] == dictMatchL[-1])) { ip--; dictMatchL--; mLength++; } /* catch up */ + goto _match_found; + } } + + if (matchIndexS > prefixLowestIndex) { + /* check prefix short match */ + if (MEM_read32(match) == MEM_read32(ip)) { + goto _search_next_long; + } + } else if (dictMode == ZSTD_dictMatchState) { + /* check dictMatchState short match */ + U32 const dictMatchIndexS = dictHashSmall[dictHS]; + match = dictBase + dictMatchIndexS; + matchIndexS = dictMatchIndexS + dictIndexDelta; + + if (match > dictStart && MEM_read32(match) == MEM_read32(ip)) { + goto _search_next_long; + } } + + ip += ((ip-anchor) >> kSearchStrength) + 1; +#if defined(__aarch64__) + PREFETCH_L1(ip+256); +#endif + continue; + +_search_next_long: + + { size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8); + size_t const dictHLNext = ZSTD_hashPtr(ip+1, dictHBitsL, 8); + U32 const matchIndexL3 = hashLong[hl3]; + const BYTE* matchL3 = base + matchIndexL3; + hashLong[hl3] = curr + 1; + + /* check prefix long +1 match */ + if (matchIndexL3 > prefixLowestIndex) { + if (MEM_read64(matchL3) == MEM_read64(ip+1)) { + mLength = ZSTD_count(ip+9, matchL3+8, iend) + 8; + ip++; + offset = (U32)(ip-matchL3); + while (((ip>anchor) & (matchL3>prefixLowest)) && (ip[-1] == matchL3[-1])) { ip--; matchL3--; mLength++; } /* catch up */ + goto _match_found; + } + } else if (dictMode == ZSTD_dictMatchState) { + /* check dict long +1 match */ + U32 const dictMatchIndexL3 = dictHashLong[dictHLNext]; + const BYTE* dictMatchL3 = dictBase + dictMatchIndexL3; + assert(dictMatchL3 < dictEnd); + if (dictMatchL3 > dictStart && MEM_read64(dictMatchL3) == MEM_read64(ip+1)) { + mLength = ZSTD_count_2segments(ip+1+8, dictMatchL3+8, iend, dictEnd, prefixLowest) + 8; + ip++; + offset = (U32)(curr + 1 - dictMatchIndexL3 - dictIndexDelta); + while (((ip>anchor) & (dictMatchL3>dictStart)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */ + goto _match_found; + } } } + + /* if no long +1 match, explore the short match we found */ + if (dictMode == ZSTD_dictMatchState && matchIndexS < prefixLowestIndex) { + mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, prefixLowest) + 4; + offset = (U32)(curr - matchIndexS); + while (((ip>anchor) & (match>dictStart)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + } else { + mLength = ZSTD_count(ip+4, match+4, iend) + 4; + offset = (U32)(ip - match); + while (((ip>anchor) & (match>prefixLowest)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + } + +_match_found: + offset_2 = offset_1; + offset_1 = offset; + + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); + +_match_stored: + /* match found */ + ip += mLength; + anchor = ip; + + if (ip <= ilimit) { + /* Complementary insertion */ + /* done after iLimit test, as candidates could be > iend-8 */ + { U32 const indexToInsert = curr+2; + hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert; + hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base); + hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert; + hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base); + } + + /* check immediate repcode */ + if (dictMode == ZSTD_dictMatchState) { + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; + const BYTE* repMatch2 = dictMode == ZSTD_dictMatchState + && repIndex2 < prefixLowestIndex ? + dictBase + repIndex2 - dictIndexDelta : + base + repIndex2; + if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */) + && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { + const BYTE* const repEnd2 = repIndex2 < prefixLowestIndex ? dictEnd : iend; + size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixLowest) + 4; + U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH); + hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2; + hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2; + ip += repLength2; + anchor = ip; + continue; + } + break; + } } + + if (dictMode == ZSTD_noDict) { + while ( (ip <= ilimit) + && ( (offset_2>0) + & (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) { + /* store sequence */ + size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4; + U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; /* swap offset_2 <=> offset_1 */ + hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = (U32)(ip-base); + hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = (U32)(ip-base); + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, rLength-MINMATCH); + ip += rLength; + anchor = ip; + continue; /* faster when present ... (?) */ + } } } + } /* while (ip < ilimit) */ + + /* save reps for next block */ + rep[0] = offset_1 ? offset_1 : offsetSaved; + rep[1] = offset_2 ? offset_2 : offsetSaved; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_doubleFast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + const U32 mls = ms->cParams.minMatch; + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_noDict); + case 5 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_noDict); + case 6 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_noDict); + case 7 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_noDict); + } +} + + +size_t ZSTD_compressBlock_doubleFast_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + const U32 mls = ms->cParams.minMatch; + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState); + case 5 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState); + case 6 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState); + case 7 : + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState); + } +} + + +static size_t ZSTD_compressBlock_doubleFast_extDict_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, + U32 const mls /* template */) +{ + ZSTD_compressionParameters const* cParams = &ms->cParams; + U32* const hashLong = ms->hashTable; + U32 const hBitsL = cParams->hashLog; + U32* const hashSmall = ms->chainTable; + U32 const hBitsS = cParams->chainLog; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + const BYTE* const base = ms->window.base; + const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); + const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog); + const U32 dictStartIndex = lowLimit; + const U32 dictLimit = ms->window.dictLimit; + const U32 prefixStartIndex = (dictLimit > lowLimit) ? dictLimit : lowLimit; + const BYTE* const prefixStart = base + prefixStartIndex; + const BYTE* const dictBase = ms->window.dictBase; + const BYTE* const dictStart = dictBase + dictStartIndex; + const BYTE* const dictEnd = dictBase + prefixStartIndex; + U32 offset_1=rep[0], offset_2=rep[1]; + + DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize); + + /* if extDict is invalidated due to maxDistance, switch to "regular" variant */ + if (prefixStartIndex == dictStartIndex) + return ZSTD_compressBlock_doubleFast_generic(ms, seqStore, rep, src, srcSize, mls, ZSTD_noDict); + + /* Search Loop */ + while (ip < ilimit) { /* < instead of <=, because (ip+1) */ + const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls); + const U32 matchIndex = hashSmall[hSmall]; + const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base; + const BYTE* match = matchBase + matchIndex; + + const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8); + const U32 matchLongIndex = hashLong[hLong]; + const BYTE* const matchLongBase = matchLongIndex < prefixStartIndex ? dictBase : base; + const BYTE* matchLong = matchLongBase + matchLongIndex; + + const U32 curr = (U32)(ip-base); + const U32 repIndex = curr + 1 - offset_1; /* offset_1 expected <= curr +1 */ + const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; + size_t mLength; + hashSmall[hSmall] = hashLong[hLong] = curr; /* update hash table */ + + if ((((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex doesn't overlap dict + prefix */ + & (repIndex > dictStartIndex)) + && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { + const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; + mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; + ip++; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH); + } else { + if ((matchLongIndex > dictStartIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) { + const BYTE* const matchEnd = matchLongIndex < prefixStartIndex ? dictEnd : iend; + const BYTE* const lowMatchPtr = matchLongIndex < prefixStartIndex ? dictStart : prefixStart; + U32 offset; + mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, prefixStart) + 8; + offset = curr - matchLongIndex; + while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */ + offset_2 = offset_1; + offset_1 = offset; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); + + } else if ((matchIndex > dictStartIndex) && (MEM_read32(match) == MEM_read32(ip))) { + size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8); + U32 const matchIndex3 = hashLong[h3]; + const BYTE* const match3Base = matchIndex3 < prefixStartIndex ? dictBase : base; + const BYTE* match3 = match3Base + matchIndex3; + U32 offset; + hashLong[h3] = curr + 1; + if ( (matchIndex3 > dictStartIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) { + const BYTE* const matchEnd = matchIndex3 < prefixStartIndex ? dictEnd : iend; + const BYTE* const lowMatchPtr = matchIndex3 < prefixStartIndex ? dictStart : prefixStart; + mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, prefixStart) + 8; + ip++; + offset = curr+1 - matchIndex3; + while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */ + } else { + const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend; + const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart; + mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4; + offset = curr - matchIndex; + while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + } + offset_2 = offset_1; + offset_1 = offset; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); + + } else { + ip += ((ip-anchor) >> kSearchStrength) + 1; + continue; + } } + + /* move to next sequence start */ + ip += mLength; + anchor = ip; + + if (ip <= ilimit) { + /* Complementary insertion */ + /* done after iLimit test, as candidates could be > iend-8 */ + { U32 const indexToInsert = curr+2; + hashLong[ZSTD_hashPtr(base+indexToInsert, hBitsL, 8)] = indexToInsert; + hashLong[ZSTD_hashPtr(ip-2, hBitsL, 8)] = (U32)(ip-2-base); + hashSmall[ZSTD_hashPtr(base+indexToInsert, hBitsS, mls)] = indexToInsert; + hashSmall[ZSTD_hashPtr(ip-1, hBitsS, mls)] = (U32)(ip-1-base); + } + + /* check immediate repcode */ + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; + const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2; + if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) /* intentional overflow : ensure repIndex2 doesn't overlap dict + prefix */ + & (repIndex2 > dictStartIndex)) + && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { + const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; + size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; + U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH); + hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2; + hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2; + ip += repLength2; + anchor = ip; + continue; + } + break; + } } } + + /* save reps for next block */ + rep[0] = offset_1; + rep[1] = offset_2; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_doubleFast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + U32 const mls = ms->cParams.minMatch; + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 4); + case 5 : + return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 5); + case 6 : + return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 6); + case 7 : + return ZSTD_compressBlock_doubleFast_extDict_generic(ms, seqStore, rep, src, srcSize, 7); + } +} diff --git a/lib/zstd/compress/zstd_double_fast.h b/lib/zstd/compress/zstd_double_fast.h new file mode 100644 index 000000000000..6822bde65a1d --- /dev/null +++ b/lib/zstd/compress/zstd_double_fast.h @@ -0,0 +1,32 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_DOUBLE_FAST_H +#define ZSTD_DOUBLE_FAST_H + + +#include "../common/mem.h" /* U32 */ +#include "zstd_compress_internal.h" /* ZSTD_CCtx, size_t */ + +void ZSTD_fillDoubleHashTable(ZSTD_matchState_t* ms, + void const* end, ZSTD_dictTableLoadMethod_e dtlm); +size_t ZSTD_compressBlock_doubleFast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_doubleFast_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_doubleFast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + + + +#endif /* ZSTD_DOUBLE_FAST_H */ diff --git a/lib/zstd/compress/zstd_fast.c b/lib/zstd/compress/zstd_fast.c new file mode 100644 index 000000000000..96b7d48e2868 --- /dev/null +++ b/lib/zstd/compress/zstd_fast.c @@ -0,0 +1,496 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include "zstd_compress_internal.h" /* ZSTD_hashPtr, ZSTD_count, ZSTD_storeSeq */ +#include "zstd_fast.h" + + +void ZSTD_fillHashTable(ZSTD_matchState_t* ms, + const void* const end, + ZSTD_dictTableLoadMethod_e dtlm) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hBits = cParams->hashLog; + U32 const mls = cParams->minMatch; + const BYTE* const base = ms->window.base; + const BYTE* ip = base + ms->nextToUpdate; + const BYTE* const iend = ((const BYTE*)end) - HASH_READ_SIZE; + const U32 fastHashFillStep = 3; + + /* Always insert every fastHashFillStep position into the hash table. + * Insert the other positions if their hash entry is empty. + */ + for ( ; ip + fastHashFillStep < iend + 2; ip += fastHashFillStep) { + U32 const curr = (U32)(ip - base); + size_t const hash0 = ZSTD_hashPtr(ip, hBits, mls); + hashTable[hash0] = curr; + if (dtlm == ZSTD_dtlm_fast) continue; + /* Only load extra positions for ZSTD_dtlm_full */ + { U32 p; + for (p = 1; p < fastHashFillStep; ++p) { + size_t const hash = ZSTD_hashPtr(ip + p, hBits, mls); + if (hashTable[hash] == 0) { /* not yet filled */ + hashTable[hash] = curr + p; + } } } } +} + + +FORCE_INLINE_TEMPLATE size_t +ZSTD_compressBlock_fast_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, + U32 const mls) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hlog = cParams->hashLog; + /* support stepSize of 0 */ + size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1; + const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; + /* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */ + const BYTE* ip0 = istart; + const BYTE* ip1; + const BYTE* anchor = istart; + const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); + const U32 prefixStartIndex = ZSTD_getLowestPrefixIndex(ms, endIndex, cParams->windowLog); + const BYTE* const prefixStart = base + prefixStartIndex; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - HASH_READ_SIZE; + U32 offset_1=rep[0], offset_2=rep[1]; + U32 offsetSaved = 0; + + /* init */ + DEBUGLOG(5, "ZSTD_compressBlock_fast_generic"); + ip0 += (ip0 == prefixStart); + ip1 = ip0 + 1; + { U32 const curr = (U32)(ip0 - base); + U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, cParams->windowLog); + U32 const maxRep = curr - windowLow; + if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0; + if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0; + } + + /* Main Search Loop */ +#ifdef __INTEL_COMPILER + /* From intel 'The vector pragma indicates that the loop should be + * vectorized if it is legal to do so'. Can be used together with + * #pragma ivdep (but have opted to exclude that because intel + * warns against using it).*/ + #pragma vector always +#endif + while (ip1 < ilimit) { /* < instead of <=, because check at ip0+2 */ + size_t mLength; + BYTE const* ip2 = ip0 + 2; + size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls); + U32 const val0 = MEM_read32(ip0); + size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls); + U32 const val1 = MEM_read32(ip1); + U32 const current0 = (U32)(ip0-base); + U32 const current1 = (U32)(ip1-base); + U32 const matchIndex0 = hashTable[h0]; + U32 const matchIndex1 = hashTable[h1]; + BYTE const* repMatch = ip2 - offset_1; + const BYTE* match0 = base + matchIndex0; + const BYTE* match1 = base + matchIndex1; + U32 offcode; + +#if defined(__aarch64__) + PREFETCH_L1(ip0+256); +#endif + + hashTable[h0] = current0; /* update hash table */ + hashTable[h1] = current1; /* update hash table */ + + assert(ip0 + 1 == ip1); + + if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) { + mLength = (ip2[-1] == repMatch[-1]) ? 1 : 0; + ip0 = ip2 - mLength; + match0 = repMatch - mLength; + mLength += 4; + offcode = 0; + goto _match; + } + if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) { + /* found a regular match */ + goto _offset; + } + if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) { + /* found a regular match after one literal */ + ip0 = ip1; + match0 = match1; + goto _offset; + } + { size_t const step = ((size_t)(ip0-anchor) >> (kSearchStrength - 1)) + stepSize; + assert(step >= 2); + ip0 += step; + ip1 += step; + continue; + } +_offset: /* Requires: ip0, match0 */ + /* Compute the offset code */ + offset_2 = offset_1; + offset_1 = (U32)(ip0-match0); + offcode = offset_1 + ZSTD_REP_MOVE; + mLength = 4; + /* Count the backwards match length */ + while (((ip0>anchor) & (match0>prefixStart)) + && (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */ + +_match: /* Requires: ip0, match0, offcode */ + /* Count the forward length */ + mLength += ZSTD_count(ip0+mLength, match0+mLength, iend); + ZSTD_storeSeq(seqStore, (size_t)(ip0-anchor), anchor, iend, offcode, mLength-MINMATCH); + /* match found */ + ip0 += mLength; + anchor = ip0; + + if (ip0 <= ilimit) { + /* Fill Table */ + assert(base+current0+2 > istart); /* check base overflow */ + hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2; /* here because current+2 could be > iend-8 */ + hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base); + + if (offset_2 > 0) { /* offset_2==0 means offset_2 is invalidated */ + while ( (ip0 <= ilimit) && (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) ) { + /* store sequence */ + size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4; + { U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff; } /* swap offset_2 <=> offset_1 */ + hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base); + ip0 += rLength; + ZSTD_storeSeq(seqStore, 0 /*litLen*/, anchor, iend, 0 /*offCode*/, rLength-MINMATCH); + anchor = ip0; + continue; /* faster when present (confirmed on gcc-8) ... (?) */ + } } } + ip1 = ip0 + 1; + } + + /* save reps for next block */ + rep[0] = offset_1 ? offset_1 : offsetSaved; + rep[1] = offset_2 ? offset_2 : offsetSaved; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_fast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + U32 const mls = ms->cParams.minMatch; + assert(ms->dictMatchState == NULL); + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4); + case 5 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5); + case 6 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6); + case 7 : + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7); + } +} + +FORCE_INLINE_TEMPLATE +size_t ZSTD_compressBlock_fast_dictMatchState_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, U32 const mls) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hlog = cParams->hashLog; + /* support stepSize of 0 */ + U32 const stepSize = cParams->targetLength + !(cParams->targetLength); + const BYTE* const base = ms->window.base; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const U32 prefixStartIndex = ms->window.dictLimit; + const BYTE* const prefixStart = base + prefixStartIndex; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - HASH_READ_SIZE; + U32 offset_1=rep[0], offset_2=rep[1]; + U32 offsetSaved = 0; + + const ZSTD_matchState_t* const dms = ms->dictMatchState; + const ZSTD_compressionParameters* const dictCParams = &dms->cParams ; + const U32* const dictHashTable = dms->hashTable; + const U32 dictStartIndex = dms->window.dictLimit; + const BYTE* const dictBase = dms->window.base; + const BYTE* const dictStart = dictBase + dictStartIndex; + const BYTE* const dictEnd = dms->window.nextSrc; + const U32 dictIndexDelta = prefixStartIndex - (U32)(dictEnd - dictBase); + const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart); + const U32 dictHLog = dictCParams->hashLog; + + /* if a dictionary is still attached, it necessarily means that + * it is within window size. So we just check it. */ + const U32 maxDistance = 1U << cParams->windowLog; + const U32 endIndex = (U32)((size_t)(ip - base) + srcSize); + assert(endIndex - prefixStartIndex <= maxDistance); + (void)maxDistance; (void)endIndex; /* these variables are not used when assert() is disabled */ + + /* ensure there will be no underflow + * when translating a dict index into a local index */ + assert(prefixStartIndex >= (U32)(dictEnd - dictBase)); + + /* init */ + DEBUGLOG(5, "ZSTD_compressBlock_fast_dictMatchState_generic"); + ip += (dictAndPrefixLength == 0); + /* dictMatchState repCode checks don't currently handle repCode == 0 + * disabling. */ + assert(offset_1 <= dictAndPrefixLength); + assert(offset_2 <= dictAndPrefixLength); + + /* Main Search Loop */ + while (ip < ilimit) { /* < instead of <=, because repcode check at (ip+1) */ + size_t mLength; + size_t const h = ZSTD_hashPtr(ip, hlog, mls); + U32 const curr = (U32)(ip-base); + U32 const matchIndex = hashTable[h]; + const BYTE* match = base + matchIndex; + const U32 repIndex = curr + 1 - offset_1; + const BYTE* repMatch = (repIndex < prefixStartIndex) ? + dictBase + (repIndex - dictIndexDelta) : + base + repIndex; + hashTable[h] = curr; /* update hash table */ + + if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */ + && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { + const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; + mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4; + ip++; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, mLength-MINMATCH); + } else if ( (matchIndex <= prefixStartIndex) ) { + size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls); + U32 const dictMatchIndex = dictHashTable[dictHash]; + const BYTE* dictMatch = dictBase + dictMatchIndex; + if (dictMatchIndex <= dictStartIndex || + MEM_read32(dictMatch) != MEM_read32(ip)) { + assert(stepSize >= 1); + ip += ((ip-anchor) >> kSearchStrength) + stepSize; + continue; + } else { + /* found a dict match */ + U32 const offset = (U32)(curr-dictMatchIndex-dictIndexDelta); + mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4; + while (((ip>anchor) & (dictMatch>dictStart)) + && (ip[-1] == dictMatch[-1])) { + ip--; dictMatch--; mLength++; + } /* catch up */ + offset_2 = offset_1; + offset_1 = offset; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); + } + } else if (MEM_read32(match) != MEM_read32(ip)) { + /* it's not a match, and we're not going to check the dictionary */ + assert(stepSize >= 1); + ip += ((ip-anchor) >> kSearchStrength) + stepSize; + continue; + } else { + /* found a regular match */ + U32 const offset = (U32)(ip-match); + mLength = ZSTD_count(ip+4, match+4, iend) + 4; + while (((ip>anchor) & (match>prefixStart)) + && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + offset_2 = offset_1; + offset_1 = offset; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); + } + + /* match found */ + ip += mLength; + anchor = ip; + + if (ip <= ilimit) { + /* Fill Table */ + assert(base+curr+2 > istart); /* check base overflow */ + hashTable[ZSTD_hashPtr(base+curr+2, hlog, mls)] = curr+2; /* here because curr+2 could be > iend-8 */ + hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); + + /* check immediate repcode */ + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; + const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? + dictBase - dictIndexDelta + repIndex2 : + base + repIndex2; + if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */) + && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { + const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; + size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; + U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */ + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, repLength2-MINMATCH); + hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; + ip += repLength2; + anchor = ip; + continue; + } + break; + } + } + } + + /* save reps for next block */ + rep[0] = offset_1 ? offset_1 : offsetSaved; + rep[1] = offset_2 ? offset_2 : offsetSaved; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + +size_t ZSTD_compressBlock_fast_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + U32 const mls = ms->cParams.minMatch; + assert(ms->dictMatchState != NULL); + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4); + case 5 : + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5); + case 6 : + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6); + case 7 : + return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7); + } +} + + +static size_t ZSTD_compressBlock_fast_extDict_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize, U32 const mls) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hlog = cParams->hashLog; + /* support stepSize of 0 */ + U32 const stepSize = cParams->targetLength + !(cParams->targetLength); + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const U32 endIndex = (U32)((size_t)(istart - base) + srcSize); + const U32 lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog); + const U32 dictStartIndex = lowLimit; + const BYTE* const dictStart = dictBase + dictStartIndex; + const U32 dictLimit = ms->window.dictLimit; + const U32 prefixStartIndex = dictLimit < lowLimit ? lowLimit : dictLimit; + const BYTE* const prefixStart = base + prefixStartIndex; + const BYTE* const dictEnd = dictBase + prefixStartIndex; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + U32 offset_1=rep[0], offset_2=rep[1]; + + DEBUGLOG(5, "ZSTD_compressBlock_fast_extDict_generic (offset_1=%u)", offset_1); + + /* switch to "regular" variant if extDict is invalidated due to maxDistance */ + if (prefixStartIndex == dictStartIndex) + return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, mls); + + /* Search Loop */ + while (ip < ilimit) { /* < instead of <=, because (ip+1) */ + const size_t h = ZSTD_hashPtr(ip, hlog, mls); + const U32 matchIndex = hashTable[h]; + const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base; + const BYTE* match = matchBase + matchIndex; + const U32 curr = (U32)(ip-base); + const U32 repIndex = curr + 1 - offset_1; + const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; + hashTable[h] = curr; /* update hash table */ + DEBUGLOG(7, "offset_1 = %u , curr = %u", offset_1, curr); + assert(offset_1 <= curr +1); /* check repIndex */ + + if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex)) + && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { + const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend; + size_t const rLength = ZSTD_count_2segments(ip+1 +4, repMatch +4, iend, repMatchEnd, prefixStart) + 4; + ip++; + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, 0, rLength-MINMATCH); + ip += rLength; + anchor = ip; + } else { + if ( (matchIndex < dictStartIndex) || + (MEM_read32(match) != MEM_read32(ip)) ) { + assert(stepSize >= 1); + ip += ((ip-anchor) >> kSearchStrength) + stepSize; + continue; + } + { const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend; + const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart; + U32 const offset = curr - matchIndex; + size_t mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4; + while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */ + offset_2 = offset_1; offset_1 = offset; /* update offset history */ + ZSTD_storeSeq(seqStore, (size_t)(ip-anchor), anchor, iend, offset + ZSTD_REP_MOVE, mLength-MINMATCH); + ip += mLength; + anchor = ip; + } } + + if (ip <= ilimit) { + /* Fill Table */ + hashTable[ZSTD_hashPtr(base+curr+2, hlog, mls)] = curr+2; + hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base); + /* check immediate repcode */ + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex2 = current2 - offset_2; + const BYTE* const repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2; + if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (repIndex2 > dictStartIndex)) /* intentional overflow */ + && (MEM_read32(repMatch2) == MEM_read32(ip)) ) { + const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend; + size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4; + { U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; } /* swap offset_2 <=> offset_1 */ + ZSTD_storeSeq(seqStore, 0 /*litlen*/, anchor, iend, 0 /*offcode*/, repLength2-MINMATCH); + hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2; + ip += repLength2; + anchor = ip; + continue; + } + break; + } } } + + /* save reps for next block */ + rep[0] = offset_1; + rep[1] = offset_2; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_fast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + U32 const mls = ms->cParams.minMatch; + switch(mls) + { + default: /* includes case 3 */ + case 4 : + return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 4); + case 5 : + return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 5); + case 6 : + return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 6); + case 7 : + return ZSTD_compressBlock_fast_extDict_generic(ms, seqStore, rep, src, srcSize, 7); + } +} diff --git a/lib/zstd/compress/zstd_fast.h b/lib/zstd/compress/zstd_fast.h new file mode 100644 index 000000000000..fddc2f532d21 --- /dev/null +++ b/lib/zstd/compress/zstd_fast.h @@ -0,0 +1,31 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_FAST_H +#define ZSTD_FAST_H + + +#include "../common/mem.h" /* U32 */ +#include "zstd_compress_internal.h" + +void ZSTD_fillHashTable(ZSTD_matchState_t* ms, + void const* end, ZSTD_dictTableLoadMethod_e dtlm); +size_t ZSTD_compressBlock_fast( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_fast_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_fast_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + + +#endif /* ZSTD_FAST_H */ diff --git a/lib/zstd/compress/zstd_lazy.c b/lib/zstd/compress/zstd_lazy.c new file mode 100644 index 000000000000..fb54d4e28a2b --- /dev/null +++ b/lib/zstd/compress/zstd_lazy.c @@ -0,0 +1,1414 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include "zstd_compress_internal.h" +#include "zstd_lazy.h" + + +/*-************************************* +* Binary Tree search +***************************************/ + +static void +ZSTD_updateDUBT(ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* iend, + U32 mls) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hashLog = cParams->hashLog; + + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + + const BYTE* const base = ms->window.base; + U32 const target = (U32)(ip - base); + U32 idx = ms->nextToUpdate; + + if (idx != target) + DEBUGLOG(7, "ZSTD_updateDUBT, from %u to %u (dictLimit:%u)", + idx, target, ms->window.dictLimit); + assert(ip + 8 <= iend); /* condition for ZSTD_hashPtr */ + (void)iend; + + assert(idx >= ms->window.dictLimit); /* condition for valid base+idx */ + for ( ; idx < target ; idx++) { + size_t const h = ZSTD_hashPtr(base + idx, hashLog, mls); /* assumption : ip + 8 <= iend */ + U32 const matchIndex = hashTable[h]; + + U32* const nextCandidatePtr = bt + 2*(idx&btMask); + U32* const sortMarkPtr = nextCandidatePtr + 1; + + DEBUGLOG(8, "ZSTD_updateDUBT: insert %u", idx); + hashTable[h] = idx; /* Update Hash Table */ + *nextCandidatePtr = matchIndex; /* update BT like a chain */ + *sortMarkPtr = ZSTD_DUBT_UNSORTED_MARK; + } + ms->nextToUpdate = target; +} + + +/* ZSTD_insertDUBT1() : + * sort one already inserted but unsorted position + * assumption : curr >= btlow == (curr - btmask) + * doesn't fail */ +static void +ZSTD_insertDUBT1(ZSTD_matchState_t* ms, + U32 curr, const BYTE* inputEnd, + U32 nbCompares, U32 btLow, + const ZSTD_dictMode_e dictMode) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + size_t commonLengthSmaller=0, commonLengthLarger=0; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const ip = (curr>=dictLimit) ? base + curr : dictBase + curr; + const BYTE* const iend = (curr>=dictLimit) ? inputEnd : dictBase + dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* match; + U32* smallerPtr = bt + 2*(curr&btMask); + U32* largerPtr = smallerPtr + 1; + U32 matchIndex = *smallerPtr; /* this candidate is unsorted : next sorted candidate is reached through *smallerPtr, while *largerPtr contains previous unsorted candidate (which is already saved and can be overwritten) */ + U32 dummy32; /* to be nullified at the end */ + U32 const windowValid = ms->window.lowLimit; + U32 const maxDistance = 1U << cParams->windowLog; + U32 const windowLow = (curr - windowValid > maxDistance) ? curr - maxDistance : windowValid; + + + DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)", + curr, dictLimit, windowLow); + assert(curr >= btLow); + assert(ip < iend); /* condition for ZSTD_count */ + + for (; nbCompares && (matchIndex > windowLow); --nbCompares) { + U32* const nextPtr = bt + 2*(matchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + assert(matchIndex < curr); + /* note : all candidates are now supposed sorted, + * but it's still possible to have nextPtr[1] == ZSTD_DUBT_UNSORTED_MARK + * when a real index has the same value as ZSTD_DUBT_UNSORTED_MARK */ + + if ( (dictMode != ZSTD_extDict) + || (matchIndex+matchLength >= dictLimit) /* both in current segment*/ + || (curr < dictLimit) /* both in extDict */) { + const BYTE* const mBase = ( (dictMode != ZSTD_extDict) + || (matchIndex+matchLength >= dictLimit)) ? + base : dictBase; + assert( (matchIndex+matchLength >= dictLimit) /* might be wrong if extDict is incorrectly set to 0 */ + || (curr < dictLimit) ); + match = mBase + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); + } else { + match = dictBase + matchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) + match = base + matchIndex; /* preparation for next read of match[matchLength] */ + } + + DEBUGLOG(8, "ZSTD_insertDUBT1: comparing %u with %u : found %u common bytes ", + curr, matchIndex, (U32)matchLength); + + if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ + break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */ + } + + if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */ + /* match is smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is smaller : next => %u", + matchIndex, btLow, nextPtr[1]); + smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */ + matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */ + } else { + /* match is larger than current */ + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + DEBUGLOG(8, "ZSTD_insertDUBT1: %u (>btLow=%u) is larger => %u", + matchIndex, btLow, nextPtr[0]); + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; +} + + +static size_t +ZSTD_DUBT_findBetterDictMatch ( + ZSTD_matchState_t* ms, + const BYTE* const ip, const BYTE* const iend, + size_t* offsetPtr, + size_t bestLength, + U32 nbCompares, + U32 const mls, + const ZSTD_dictMode_e dictMode) +{ + const ZSTD_matchState_t * const dms = ms->dictMatchState; + const ZSTD_compressionParameters* const dmsCParams = &dms->cParams; + const U32 * const dictHashTable = dms->hashTable; + U32 const hashLog = dmsCParams->hashLog; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32 dictMatchIndex = dictHashTable[h]; + + const BYTE* const base = ms->window.base; + const BYTE* const prefixStart = base + ms->window.dictLimit; + U32 const curr = (U32)(ip-base); + const BYTE* const dictBase = dms->window.base; + const BYTE* const dictEnd = dms->window.nextSrc; + U32 const dictHighLimit = (U32)(dms->window.nextSrc - dms->window.base); + U32 const dictLowLimit = dms->window.lowLimit; + U32 const dictIndexDelta = ms->window.lowLimit - dictHighLimit; + + U32* const dictBt = dms->chainTable; + U32 const btLog = dmsCParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + U32 const btLow = (btMask >= dictHighLimit - dictLowLimit) ? dictLowLimit : dictHighLimit - btMask; + + size_t commonLengthSmaller=0, commonLengthLarger=0; + + (void)dictMode; + assert(dictMode == ZSTD_dictMatchState); + + for (; nbCompares && (dictMatchIndex > dictLowLimit); --nbCompares) { + U32* const nextPtr = dictBt + 2*(dictMatchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + const BYTE* match = dictBase + dictMatchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (dictMatchIndex+matchLength >= dictHighLimit) + match = base + dictMatchIndex + dictIndexDelta; /* to prepare for next usage of match[matchLength] */ + + if (matchLength > bestLength) { + U32 matchIndex = dictMatchIndex + dictIndexDelta; + if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(curr-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) ) { + DEBUGLOG(9, "ZSTD_DUBT_findBetterDictMatch(%u) : found better match length %u -> %u and offsetCode %u -> %u (dictMatchIndex %u, matchIndex %u)", + curr, (U32)bestLength, (U32)matchLength, (U32)*offsetPtr, ZSTD_REP_MOVE + curr - matchIndex, dictMatchIndex, matchIndex); + bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex; + } + if (ip+matchLength == iend) { /* reached end of input : ip[matchLength] is not valid, no way to know if it's larger or smaller than match */ + break; /* drop, to guarantee consistency (miss a little bit of compression) */ + } + } + + if (match[matchLength] < ip[matchLength]) { + if (dictMatchIndex <= btLow) { break; } /* beyond tree size, stop the search */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + dictMatchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ + } else { + /* match is larger than current */ + if (dictMatchIndex <= btLow) { break; } /* beyond tree size, stop the search */ + commonLengthLarger = matchLength; + dictMatchIndex = nextPtr[0]; + } + } + + if (bestLength >= MINMATCH) { + U32 const mIndex = curr - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex; + DEBUGLOG(8, "ZSTD_DUBT_findBetterDictMatch(%u) : found match of length %u and offsetCode %u (pos %u)", + curr, (U32)bestLength, (U32)*offsetPtr, mIndex); + } + return bestLength; + +} + + +static size_t +ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms, + const BYTE* const ip, const BYTE* const iend, + size_t* offsetPtr, + U32 const mls, + const ZSTD_dictMode_e dictMode) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hashLog = cParams->hashLog; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32 matchIndex = hashTable[h]; + + const BYTE* const base = ms->window.base; + U32 const curr = (U32)(ip-base); + U32 const windowLow = ZSTD_getLowestMatchIndex(ms, curr, cParams->windowLog); + + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + U32 const btLow = (btMask >= curr) ? 0 : curr - btMask; + U32 const unsortLimit = MAX(btLow, windowLow); + + U32* nextCandidate = bt + 2*(matchIndex&btMask); + U32* unsortedMark = bt + 2*(matchIndex&btMask) + 1; + U32 nbCompares = 1U << cParams->searchLog; + U32 nbCandidates = nbCompares; + U32 previousCandidate = 0; + + DEBUGLOG(7, "ZSTD_DUBT_findBestMatch (%u) ", curr); + assert(ip <= iend-8); /* required for h calculation */ + assert(dictMode != ZSTD_dedicatedDictSearch); + + /* reach end of unsorted candidates list */ + while ( (matchIndex > unsortLimit) + && (*unsortedMark == ZSTD_DUBT_UNSORTED_MARK) + && (nbCandidates > 1) ) { + DEBUGLOG(8, "ZSTD_DUBT_findBestMatch: candidate %u is unsorted", + matchIndex); + *unsortedMark = previousCandidate; /* the unsortedMark becomes a reversed chain, to move up back to original position */ + previousCandidate = matchIndex; + matchIndex = *nextCandidate; + nextCandidate = bt + 2*(matchIndex&btMask); + unsortedMark = bt + 2*(matchIndex&btMask) + 1; + nbCandidates --; + } + + /* nullify last candidate if it's still unsorted + * simplification, detrimental to compression ratio, beneficial for speed */ + if ( (matchIndex > unsortLimit) + && (*unsortedMark==ZSTD_DUBT_UNSORTED_MARK) ) { + DEBUGLOG(7, "ZSTD_DUBT_findBestMatch: nullify last unsorted candidate %u", + matchIndex); + *nextCandidate = *unsortedMark = 0; + } + + /* batch sort stacked candidates */ + matchIndex = previousCandidate; + while (matchIndex) { /* will end on matchIndex == 0 */ + U32* const nextCandidateIdxPtr = bt + 2*(matchIndex&btMask) + 1; + U32 const nextCandidateIdx = *nextCandidateIdxPtr; + ZSTD_insertDUBT1(ms, matchIndex, iend, + nbCandidates, unsortLimit, dictMode); + matchIndex = nextCandidateIdx; + nbCandidates++; + } + + /* find longest match */ + { size_t commonLengthSmaller = 0, commonLengthLarger = 0; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; + U32* smallerPtr = bt + 2*(curr&btMask); + U32* largerPtr = bt + 2*(curr&btMask) + 1; + U32 matchEndIdx = curr + 8 + 1; + U32 dummy32; /* to be nullified at the end */ + size_t bestLength = 0; + + matchIndex = hashTable[h]; + hashTable[h] = curr; /* Update Hash Table */ + + for (; nbCompares && (matchIndex > windowLow); --nbCompares) { + U32* const nextPtr = bt + 2*(matchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + const BYTE* match; + + if ((dictMode != ZSTD_extDict) || (matchIndex+matchLength >= dictLimit)) { + match = base + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); + } else { + match = dictBase + matchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) + match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ + } + + if (matchLength > bestLength) { + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; + if ( (4*(int)(matchLength-bestLength)) > (int)(ZSTD_highbit32(curr-matchIndex+1) - ZSTD_highbit32((U32)offsetPtr[0]+1)) ) + bestLength = matchLength, *offsetPtr = ZSTD_REP_MOVE + curr - matchIndex; + if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ + if (dictMode == ZSTD_dictMatchState) { + nbCompares = 0; /* in addition to avoiding checking any + * further in this loop, make sure we + * skip checking in the dictionary. */ + } + break; /* drop, to guarantee consistency (miss a little bit of compression) */ + } + } + + if (match[matchLength] < ip[matchLength]) { + /* match is smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + smallerPtr = nextPtr+1; /* new "smaller" => larger of match */ + matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ + } else { + /* match is larger than current */ + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; + + assert(nbCompares <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */ + if (dictMode == ZSTD_dictMatchState && nbCompares) { + bestLength = ZSTD_DUBT_findBetterDictMatch( + ms, ip, iend, + offsetPtr, bestLength, nbCompares, + mls, dictMode); + } + + assert(matchEndIdx > curr+8); /* ensure nextToUpdate is increased */ + ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */ + if (bestLength >= MINMATCH) { + U32 const mIndex = curr - ((U32)*offsetPtr - ZSTD_REP_MOVE); (void)mIndex; + DEBUGLOG(8, "ZSTD_DUBT_findBestMatch(%u) : found match of length %u and offsetCode %u (pos %u)", + curr, (U32)bestLength, (U32)*offsetPtr, mIndex); + } + return bestLength; + } +} + + +/* ZSTD_BtFindBestMatch() : Tree updater, providing best match */ +FORCE_INLINE_TEMPLATE size_t +ZSTD_BtFindBestMatch( ZSTD_matchState_t* ms, + const BYTE* const ip, const BYTE* const iLimit, + size_t* offsetPtr, + const U32 mls /* template */, + const ZSTD_dictMode_e dictMode) +{ + DEBUGLOG(7, "ZSTD_BtFindBestMatch"); + if (ip < ms->window.base + ms->nextToUpdate) return 0; /* skipped area */ + ZSTD_updateDUBT(ms, ip, iLimit, mls); + return ZSTD_DUBT_findBestMatch(ms, ip, iLimit, offsetPtr, mls, dictMode); +} + + +static size_t +ZSTD_BtFindBestMatch_selectMLS ( ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 4, ZSTD_noDict); + case 5 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 5, ZSTD_noDict); + case 7 : + case 6 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 6, ZSTD_noDict); + } +} + + +static size_t ZSTD_BtFindBestMatch_dictMatchState_selectMLS ( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 4, ZSTD_dictMatchState); + case 5 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 5, ZSTD_dictMatchState); + case 7 : + case 6 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 6, ZSTD_dictMatchState); + } +} + + +static size_t ZSTD_BtFindBestMatch_extDict_selectMLS ( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 4, ZSTD_extDict); + case 5 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 5, ZSTD_extDict); + case 7 : + case 6 : return ZSTD_BtFindBestMatch(ms, ip, iLimit, offsetPtr, 6, ZSTD_extDict); + } +} + + + +/* ********************************* +* Hash Chain +***********************************/ +#define NEXT_IN_CHAIN(d, mask) chainTable[(d) & (mask)] + +/* Update chains up to ip (excluded) + Assumption : always within prefix (i.e. not within extDict) */ +FORCE_INLINE_TEMPLATE U32 ZSTD_insertAndFindFirstIndex_internal( + ZSTD_matchState_t* ms, + const ZSTD_compressionParameters* const cParams, + const BYTE* ip, U32 const mls) +{ + U32* const hashTable = ms->hashTable; + const U32 hashLog = cParams->hashLog; + U32* const chainTable = ms->chainTable; + const U32 chainMask = (1 << cParams->chainLog) - 1; + const BYTE* const base = ms->window.base; + const U32 target = (U32)(ip - base); + U32 idx = ms->nextToUpdate; + + while(idx < target) { /* catch up */ + size_t const h = ZSTD_hashPtr(base+idx, hashLog, mls); + NEXT_IN_CHAIN(idx, chainMask) = hashTable[h]; + hashTable[h] = idx; + idx++; + } + + ms->nextToUpdate = target; + return hashTable[ZSTD_hashPtr(ip, hashLog, mls)]; +} + +U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip) { + const ZSTD_compressionParameters* const cParams = &ms->cParams; + return ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, ms->cParams.minMatch); +} + +void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip) +{ + const BYTE* const base = ms->window.base; + U32 const target = (U32)(ip - base); + U32* const hashTable = ms->hashTable; + U32* const chainTable = ms->chainTable; + U32 const chainSize = 1 << ms->cParams.chainLog; + U32 idx = ms->nextToUpdate; + U32 const minChain = chainSize < target ? target - chainSize : idx; + U32 const bucketSize = 1 << ZSTD_LAZY_DDSS_BUCKET_LOG; + U32 const cacheSize = bucketSize - 1; + U32 const chainAttempts = (1 << ms->cParams.searchLog) - cacheSize; + U32 const chainLimit = chainAttempts > 255 ? 255 : chainAttempts; + + /* We know the hashtable is oversized by a factor of `bucketSize`. + * We are going to temporarily pretend `bucketSize == 1`, keeping only a + * single entry. We will use the rest of the space to construct a temporary + * chaintable. + */ + U32 const hashLog = ms->cParams.hashLog - ZSTD_LAZY_DDSS_BUCKET_LOG; + U32* const tmpHashTable = hashTable; + U32* const tmpChainTable = hashTable + ((size_t)1 << hashLog); + U32 const tmpChainSize = ((1 << ZSTD_LAZY_DDSS_BUCKET_LOG) - 1) << hashLog; + U32 const tmpMinChain = tmpChainSize < target ? target - tmpChainSize : idx; + + U32 hashIdx; + + assert(ms->cParams.chainLog <= 24); + assert(ms->cParams.hashLog >= ms->cParams.chainLog); + assert(idx != 0); + assert(tmpMinChain <= minChain); + + /* fill conventional hash table and conventional chain table */ + for ( ; idx < target; idx++) { + U32 const h = (U32)ZSTD_hashPtr(base + idx, hashLog, ms->cParams.minMatch); + if (idx >= tmpMinChain) { + tmpChainTable[idx - tmpMinChain] = hashTable[h]; + } + tmpHashTable[h] = idx; + } + + /* sort chains into ddss chain table */ + { + U32 chainPos = 0; + for (hashIdx = 0; hashIdx < (1U << hashLog); hashIdx++) { + U32 count; + U32 countBeyondMinChain = 0; + U32 i = tmpHashTable[hashIdx]; + for (count = 0; i >= tmpMinChain && count < cacheSize; count++) { + /* skip through the chain to the first position that won't be + * in the hash cache bucket */ + if (i < minChain) { + countBeyondMinChain++; + } + i = tmpChainTable[i - tmpMinChain]; + } + if (count == cacheSize) { + for (count = 0; count < chainLimit;) { + if (i < minChain) { + if (!i || countBeyondMinChain++ > cacheSize) { + /* only allow pulling `cacheSize` number of entries + * into the cache or chainTable beyond `minChain`, + * to replace the entries pulled out of the + * chainTable into the cache. This lets us reach + * back further without increasing the total number + * of entries in the chainTable, guaranteeing the + * DDSS chain table will fit into the space + * allocated for the regular one. */ + break; + } + } + chainTable[chainPos++] = i; + count++; + if (i < tmpMinChain) { + break; + } + i = tmpChainTable[i - tmpMinChain]; + } + } else { + count = 0; + } + if (count) { + tmpHashTable[hashIdx] = ((chainPos - count) << 8) + count; + } else { + tmpHashTable[hashIdx] = 0; + } + } + assert(chainPos <= chainSize); /* I believe this is guaranteed... */ + } + + /* move chain pointers into the last entry of each hash bucket */ + for (hashIdx = (1 << hashLog); hashIdx; ) { + U32 const bucketIdx = --hashIdx << ZSTD_LAZY_DDSS_BUCKET_LOG; + U32 const chainPackedPointer = tmpHashTable[hashIdx]; + U32 i; + for (i = 0; i < cacheSize; i++) { + hashTable[bucketIdx + i] = 0; + } + hashTable[bucketIdx + bucketSize - 1] = chainPackedPointer; + } + + /* fill the buckets of the hash table */ + for (idx = ms->nextToUpdate; idx < target; idx++) { + U32 const h = (U32)ZSTD_hashPtr(base + idx, hashLog, ms->cParams.minMatch) + << ZSTD_LAZY_DDSS_BUCKET_LOG; + U32 i; + /* Shift hash cache down 1. */ + for (i = cacheSize - 1; i; i--) + hashTable[h + i] = hashTable[h + i - 1]; + hashTable[h] = idx; + } + + ms->nextToUpdate = target; +} + + +/* inlining is important to hardwire a hot branch (template emulation) */ +FORCE_INLINE_TEMPLATE +size_t ZSTD_HcFindBestMatch_generic ( + ZSTD_matchState_t* ms, + const BYTE* const ip, const BYTE* const iLimit, + size_t* offsetPtr, + const U32 mls, const ZSTD_dictMode_e dictMode) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const chainTable = ms->chainTable; + const U32 chainSize = (1 << cParams->chainLog); + const U32 chainMask = chainSize-1; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const U32 curr = (U32)(ip-base); + const U32 maxDistance = 1U << cParams->windowLog; + const U32 lowestValid = ms->window.lowLimit; + const U32 withinMaxDistance = (curr - lowestValid > maxDistance) ? curr - maxDistance : lowestValid; + const U32 isDictionary = (ms->loadedDictEnd != 0); + const U32 lowLimit = isDictionary ? lowestValid : withinMaxDistance; + const U32 minChain = curr > chainSize ? curr - chainSize : 0; + U32 nbAttempts = 1U << cParams->searchLog; + size_t ml=4-1; + + const ZSTD_matchState_t* const dms = ms->dictMatchState; + const U32 ddsHashLog = dictMode == ZSTD_dedicatedDictSearch + ? dms->cParams.hashLog - ZSTD_LAZY_DDSS_BUCKET_LOG : 0; + const size_t ddsIdx = dictMode == ZSTD_dedicatedDictSearch + ? ZSTD_hashPtr(ip, ddsHashLog, mls) << ZSTD_LAZY_DDSS_BUCKET_LOG : 0; + + U32 matchIndex; + + if (dictMode == ZSTD_dedicatedDictSearch) { + const U32* entry = &dms->hashTable[ddsIdx]; + PREFETCH_L1(entry); + } + + /* HC4 match finder */ + matchIndex = ZSTD_insertAndFindFirstIndex_internal(ms, cParams, ip, mls); + + for ( ; (matchIndex>=lowLimit) & (nbAttempts>0) ; nbAttempts--) { + size_t currentMl=0; + if ((dictMode != ZSTD_extDict) || matchIndex >= dictLimit) { + const BYTE* const match = base + matchIndex; + assert(matchIndex >= dictLimit); /* ensures this is true if dictMode != ZSTD_extDict */ + if (match[ml] == ip[ml]) /* potentially better */ + currentMl = ZSTD_count(ip, match, iLimit); + } else { + const BYTE* const match = dictBase + matchIndex; + assert(match+4 <= dictEnd); + if (MEM_read32(match) == MEM_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */ + currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dictEnd, prefixStart) + 4; + } + + /* save best solution */ + if (currentMl > ml) { + ml = currentMl; + *offsetPtr = curr - matchIndex + ZSTD_REP_MOVE; + if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */ + } + + if (matchIndex <= minChain) break; + matchIndex = NEXT_IN_CHAIN(matchIndex, chainMask); + } + + assert(nbAttempts <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */ + if (dictMode == ZSTD_dedicatedDictSearch) { + const U32 ddsLowestIndex = dms->window.dictLimit; + const BYTE* const ddsBase = dms->window.base; + const BYTE* const ddsEnd = dms->window.nextSrc; + const U32 ddsSize = (U32)(ddsEnd - ddsBase); + const U32 ddsIndexDelta = dictLimit - ddsSize; + const U32 bucketSize = (1 << ZSTD_LAZY_DDSS_BUCKET_LOG); + const U32 bucketLimit = nbAttempts < bucketSize - 1 ? nbAttempts : bucketSize - 1; + U32 ddsAttempt; + + for (ddsAttempt = 0; ddsAttempt < bucketSize - 1; ddsAttempt++) { + PREFETCH_L1(ddsBase + dms->hashTable[ddsIdx + ddsAttempt]); + } + + { + U32 const chainPackedPointer = dms->hashTable[ddsIdx + bucketSize - 1]; + U32 const chainIndex = chainPackedPointer >> 8; + + PREFETCH_L1(&dms->chainTable[chainIndex]); + } + + for (ddsAttempt = 0; ddsAttempt < bucketLimit; ddsAttempt++) { + size_t currentMl=0; + const BYTE* match; + matchIndex = dms->hashTable[ddsIdx + ddsAttempt]; + match = ddsBase + matchIndex; + + if (!matchIndex) { + return ml; + } + + /* guaranteed by table construction */ + (void)ddsLowestIndex; + assert(matchIndex >= ddsLowestIndex); + assert(match+4 <= ddsEnd); + if (MEM_read32(match) == MEM_read32(ip)) { + /* assumption : matchIndex <= dictLimit-4 (by table construction) */ + currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, ddsEnd, prefixStart) + 4; + } + + /* save best solution */ + if (currentMl > ml) { + ml = currentMl; + *offsetPtr = curr - (matchIndex + ddsIndexDelta) + ZSTD_REP_MOVE; + if (ip+currentMl == iLimit) { + /* best possible, avoids read overflow on next attempt */ + return ml; + } + } + } + + { + U32 const chainPackedPointer = dms->hashTable[ddsIdx + bucketSize - 1]; + U32 chainIndex = chainPackedPointer >> 8; + U32 const chainLength = chainPackedPointer & 0xFF; + U32 const chainAttempts = nbAttempts - ddsAttempt; + U32 const chainLimit = chainAttempts > chainLength ? chainLength : chainAttempts; + U32 chainAttempt; + + for (chainAttempt = 0 ; chainAttempt < chainLimit; chainAttempt++) { + PREFETCH_L1(ddsBase + dms->chainTable[chainIndex + chainAttempt]); + } + + for (chainAttempt = 0 ; chainAttempt < chainLimit; chainAttempt++, chainIndex++) { + size_t currentMl=0; + const BYTE* match; + matchIndex = dms->chainTable[chainIndex]; + match = ddsBase + matchIndex; + + /* guaranteed by table construction */ + assert(matchIndex >= ddsLowestIndex); + assert(match+4 <= ddsEnd); + if (MEM_read32(match) == MEM_read32(ip)) { + /* assumption : matchIndex <= dictLimit-4 (by table construction) */ + currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, ddsEnd, prefixStart) + 4; + } + + /* save best solution */ + if (currentMl > ml) { + ml = currentMl; + *offsetPtr = curr - (matchIndex + ddsIndexDelta) + ZSTD_REP_MOVE; + if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */ + } + } + } + } else if (dictMode == ZSTD_dictMatchState) { + const U32* const dmsChainTable = dms->chainTable; + const U32 dmsChainSize = (1 << dms->cParams.chainLog); + const U32 dmsChainMask = dmsChainSize - 1; + const U32 dmsLowestIndex = dms->window.dictLimit; + const BYTE* const dmsBase = dms->window.base; + const BYTE* const dmsEnd = dms->window.nextSrc; + const U32 dmsSize = (U32)(dmsEnd - dmsBase); + const U32 dmsIndexDelta = dictLimit - dmsSize; + const U32 dmsMinChain = dmsSize > dmsChainSize ? dmsSize - dmsChainSize : 0; + + matchIndex = dms->hashTable[ZSTD_hashPtr(ip, dms->cParams.hashLog, mls)]; + + for ( ; (matchIndex>=dmsLowestIndex) & (nbAttempts>0) ; nbAttempts--) { + size_t currentMl=0; + const BYTE* const match = dmsBase + matchIndex; + assert(match+4 <= dmsEnd); + if (MEM_read32(match) == MEM_read32(ip)) /* assumption : matchIndex <= dictLimit-4 (by table construction) */ + currentMl = ZSTD_count_2segments(ip+4, match+4, iLimit, dmsEnd, prefixStart) + 4; + + /* save best solution */ + if (currentMl > ml) { + ml = currentMl; + *offsetPtr = curr - (matchIndex + dmsIndexDelta) + ZSTD_REP_MOVE; + if (ip+currentMl == iLimit) break; /* best possible, avoids read overflow on next attempt */ + } + + if (matchIndex <= dmsMinChain) break; + + matchIndex = dmsChainTable[matchIndex & dmsChainMask]; + } + } + + return ml; +} + + +FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_selectMLS ( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_noDict); + case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_noDict); + case 7 : + case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_noDict); + } +} + + +static size_t ZSTD_HcFindBestMatch_dictMatchState_selectMLS ( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_dictMatchState); + case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_dictMatchState); + case 7 : + case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_dictMatchState); + } +} + + +static size_t ZSTD_HcFindBestMatch_dedicatedDictSearch_selectMLS ( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_dedicatedDictSearch); + case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_dedicatedDictSearch); + case 7 : + case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_dedicatedDictSearch); + } +} + + +FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_extDict_selectMLS ( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* const iLimit, + size_t* offsetPtr) +{ + switch(ms->cParams.minMatch) + { + default : /* includes case 3 */ + case 4 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 4, ZSTD_extDict); + case 5 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 5, ZSTD_extDict); + case 7 : + case 6 : return ZSTD_HcFindBestMatch_generic(ms, ip, iLimit, offsetPtr, 6, ZSTD_extDict); + } +} + + +/* ******************************* +* Common parser - lazy strategy +*********************************/ +typedef enum { search_hashChain, search_binaryTree } searchMethod_e; + +FORCE_INLINE_TEMPLATE size_t +ZSTD_compressBlock_lazy_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, + U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize, + const searchMethod_e searchMethod, const U32 depth, + ZSTD_dictMode_e const dictMode) +{ + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + const BYTE* const base = ms->window.base; + const U32 prefixLowestIndex = ms->window.dictLimit; + const BYTE* const prefixLowest = base + prefixLowestIndex; + + typedef size_t (*searchMax_f)( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr); + + /* + * This table is indexed first by the four ZSTD_dictMode_e values, and then + * by the two searchMethod_e values. NULLs are placed for configurations + * that should never occur (extDict modes go to the other implementation + * below and there is no DDSS for binary tree search yet). + */ + const searchMax_f searchFuncs[4][2] = { + { + ZSTD_HcFindBestMatch_selectMLS, + ZSTD_BtFindBestMatch_selectMLS + }, + { + NULL, + NULL + }, + { + ZSTD_HcFindBestMatch_dictMatchState_selectMLS, + ZSTD_BtFindBestMatch_dictMatchState_selectMLS + }, + { + ZSTD_HcFindBestMatch_dedicatedDictSearch_selectMLS, + NULL + } + }; + + searchMax_f const searchMax = searchFuncs[dictMode][searchMethod == search_binaryTree]; + U32 offset_1 = rep[0], offset_2 = rep[1], savedOffset=0; + + const int isDMS = dictMode == ZSTD_dictMatchState; + const int isDDS = dictMode == ZSTD_dedicatedDictSearch; + const int isDxS = isDMS || isDDS; + const ZSTD_matchState_t* const dms = ms->dictMatchState; + const U32 dictLowestIndex = isDxS ? dms->window.dictLimit : 0; + const BYTE* const dictBase = isDxS ? dms->window.base : NULL; + const BYTE* const dictLowest = isDxS ? dictBase + dictLowestIndex : NULL; + const BYTE* const dictEnd = isDxS ? dms->window.nextSrc : NULL; + const U32 dictIndexDelta = isDxS ? + prefixLowestIndex - (U32)(dictEnd - dictBase) : + 0; + const U32 dictAndPrefixLength = (U32)((ip - prefixLowest) + (dictEnd - dictLowest)); + + assert(searchMax != NULL); + + DEBUGLOG(5, "ZSTD_compressBlock_lazy_generic (dictMode=%u)", (U32)dictMode); + + /* init */ + ip += (dictAndPrefixLength == 0); + if (dictMode == ZSTD_noDict) { + U32 const curr = (U32)(ip - base); + U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, curr, ms->cParams.windowLog); + U32 const maxRep = curr - windowLow; + if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0; + if (offset_1 > maxRep) savedOffset = offset_1, offset_1 = 0; + } + if (isDxS) { + /* dictMatchState repCode checks don't currently handle repCode == 0 + * disabling. */ + assert(offset_1 <= dictAndPrefixLength); + assert(offset_2 <= dictAndPrefixLength); + } + + /* Match Loop */ +#if defined(__x86_64__) + /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the + * code alignment is perturbed. To fix the instability align the loop on 32-bytes. + */ + __asm__(".p2align 5"); +#endif + while (ip < ilimit) { + size_t matchLength=0; + size_t offset=0; + const BYTE* start=ip+1; + + /* check repCode */ + if (isDxS) { + const U32 repIndex = (U32)(ip - base) + 1 - offset_1; + const BYTE* repMatch = ((dictMode == ZSTD_dictMatchState || dictMode == ZSTD_dedicatedDictSearch) + && repIndex < prefixLowestIndex) ? + dictBase + (repIndex - dictIndexDelta) : + base + repIndex; + if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */) + && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) { + const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend; + matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4; + if (depth==0) goto _storeSequence; + } + } + if ( dictMode == ZSTD_noDict + && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) { + matchLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4; + if (depth==0) goto _storeSequence; + } + + /* first search (depth 0) */ + { size_t offsetFound = 999999999; + size_t const ml2 = searchMax(ms, ip, iend, &offsetFound); + if (ml2 > matchLength) + matchLength = ml2, start = ip, offset=offsetFound; + } + + if (matchLength < 4) { + ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */ + continue; + } + + /* let's try to find a better solution */ + if (depth>=1) + while (ip0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) { + size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4; + int const gain2 = (int)(mlRep * 3); + int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1); + if ((mlRep >= 4) && (gain2 > gain1)) + matchLength = mlRep, offset = 0, start = ip; + } + if (isDxS) { + const U32 repIndex = (U32)(ip - base) - offset_1; + const BYTE* repMatch = repIndex < prefixLowestIndex ? + dictBase + (repIndex - dictIndexDelta) : + base + repIndex; + if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */) + && (MEM_read32(repMatch) == MEM_read32(ip)) ) { + const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend; + size_t const mlRep = ZSTD_count_2segments(ip+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4; + int const gain2 = (int)(mlRep * 3); + int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1); + if ((mlRep >= 4) && (gain2 > gain1)) + matchLength = mlRep, offset = 0, start = ip; + } + } + { size_t offset2=999999999; + size_t const ml2 = searchMax(ms, ip, iend, &offset2); + int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */ + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 4); + if ((ml2 >= 4) && (gain2 > gain1)) { + matchLength = ml2, offset = offset2, start = ip; + continue; /* search a better one */ + } } + + /* let's find an even better one */ + if ((depth==2) && (ip0) & (MEM_read32(ip) == MEM_read32(ip - offset_1)))) { + size_t const mlRep = ZSTD_count(ip+4, ip+4-offset_1, iend) + 4; + int const gain2 = (int)(mlRep * 4); + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1); + if ((mlRep >= 4) && (gain2 > gain1)) + matchLength = mlRep, offset = 0, start = ip; + } + if (isDxS) { + const U32 repIndex = (U32)(ip - base) - offset_1; + const BYTE* repMatch = repIndex < prefixLowestIndex ? + dictBase + (repIndex - dictIndexDelta) : + base + repIndex; + if (((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */) + && (MEM_read32(repMatch) == MEM_read32(ip)) ) { + const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend; + size_t const mlRep = ZSTD_count_2segments(ip+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4; + int const gain2 = (int)(mlRep * 4); + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1); + if ((mlRep >= 4) && (gain2 > gain1)) + matchLength = mlRep, offset = 0, start = ip; + } + } + { size_t offset2=999999999; + size_t const ml2 = searchMax(ms, ip, iend, &offset2); + int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */ + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 7); + if ((ml2 >= 4) && (gain2 > gain1)) { + matchLength = ml2, offset = offset2, start = ip; + continue; + } } } + break; /* nothing found : store previous solution */ + } + + /* NOTE: + * start[-offset+ZSTD_REP_MOVE-1] is undefined behavior. + * (-offset+ZSTD_REP_MOVE-1) is unsigned, and is added to start, which + * overflows the pointer, which is undefined behavior. + */ + /* catch up */ + if (offset) { + if (dictMode == ZSTD_noDict) { + while ( ((start > anchor) & (start - (offset-ZSTD_REP_MOVE) > prefixLowest)) + && (start[-1] == (start-(offset-ZSTD_REP_MOVE))[-1]) ) /* only search for offset within prefix */ + { start--; matchLength++; } + } + if (isDxS) { + U32 const matchIndex = (U32)((start-base) - (offset - ZSTD_REP_MOVE)); + const BYTE* match = (matchIndex < prefixLowestIndex) ? dictBase + matchIndex - dictIndexDelta : base + matchIndex; + const BYTE* const mStart = (matchIndex < prefixLowestIndex) ? dictLowest : prefixLowest; + while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; } /* catch up */ + } + offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE); + } + /* store sequence */ +_storeSequence: + { size_t const litLength = start - anchor; + ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offset, matchLength-MINMATCH); + anchor = ip = start + matchLength; + } + + /* check immediate repcode */ + if (isDxS) { + while (ip <= ilimit) { + U32 const current2 = (U32)(ip-base); + U32 const repIndex = current2 - offset_2; + const BYTE* repMatch = repIndex < prefixLowestIndex ? + dictBase - dictIndexDelta + repIndex : + base + repIndex; + if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex) >= 3 /* intentional overflow */) + && (MEM_read32(repMatch) == MEM_read32(ip)) ) { + const BYTE* const repEnd2 = repIndex < prefixLowestIndex ? dictEnd : iend; + matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd2, prefixLowest) + 4; + offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap offset_2 <=> offset_1 */ + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH); + ip += matchLength; + anchor = ip; + continue; + } + break; + } + } + + if (dictMode == ZSTD_noDict) { + while ( ((ip <= ilimit) & (offset_2>0)) + && (MEM_read32(ip) == MEM_read32(ip - offset_2)) ) { + /* store sequence */ + matchLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4; + offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap repcodes */ + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH); + ip += matchLength; + anchor = ip; + continue; /* faster when present ... (?) */ + } } } + + /* Save reps for next block */ + rep[0] = offset_1 ? offset_1 : savedOffset; + rep[1] = offset_2 ? offset_2 : savedOffset; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_btlazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_noDict); +} + +size_t ZSTD_compressBlock_lazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_noDict); +} + +size_t ZSTD_compressBlock_lazy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_noDict); +} + +size_t ZSTD_compressBlock_greedy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_noDict); +} + +size_t ZSTD_compressBlock_btlazy2_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_dictMatchState); +} + +size_t ZSTD_compressBlock_lazy2_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_dictMatchState); +} + +size_t ZSTD_compressBlock_lazy_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_dictMatchState); +} + +size_t ZSTD_compressBlock_greedy_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_dictMatchState); +} + + +size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_dedicatedDictSearch); +} + +size_t ZSTD_compressBlock_lazy_dedicatedDictSearch( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_dedicatedDictSearch); +} + +size_t ZSTD_compressBlock_greedy_dedicatedDictSearch( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_dedicatedDictSearch); +} + + +FORCE_INLINE_TEMPLATE +size_t ZSTD_compressBlock_lazy_extDict_generic( + ZSTD_matchState_t* ms, seqStore_t* seqStore, + U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize, + const searchMethod_e searchMethod, const U32 depth) +{ + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + const BYTE* const base = ms->window.base; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* const dictBase = ms->window.dictBase; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const dictStart = dictBase + ms->window.lowLimit; + const U32 windowLog = ms->cParams.windowLog; + + typedef size_t (*searchMax_f)( + ZSTD_matchState_t* ms, + const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr); + searchMax_f searchMax = searchMethod==search_binaryTree ? ZSTD_BtFindBestMatch_extDict_selectMLS : ZSTD_HcFindBestMatch_extDict_selectMLS; + + U32 offset_1 = rep[0], offset_2 = rep[1]; + + DEBUGLOG(5, "ZSTD_compressBlock_lazy_extDict_generic"); + + /* init */ + ip += (ip == prefixStart); + + /* Match Loop */ +#if defined(__x86_64__) + /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the + * code alignment is perturbed. To fix the instability align the loop on 32-bytes. + */ + __asm__(".p2align 5"); +#endif + while (ip < ilimit) { + size_t matchLength=0; + size_t offset=0; + const BYTE* start=ip+1; + U32 curr = (U32)(ip-base); + + /* check repCode */ + { const U32 windowLow = ZSTD_getLowestMatchIndex(ms, curr+1, windowLog); + const U32 repIndex = (U32)(curr+1 - offset_1); + const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; + if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow)) /* intentional overflow */ + if (MEM_read32(ip+1) == MEM_read32(repMatch)) { + /* repcode detected we should take it */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + matchLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repEnd, prefixStart) + 4; + if (depth==0) goto _storeSequence; + } } + + /* first search (depth 0) */ + { size_t offsetFound = 999999999; + size_t const ml2 = searchMax(ms, ip, iend, &offsetFound); + if (ml2 > matchLength) + matchLength = ml2, start = ip, offset=offsetFound; + } + + if (matchLength < 4) { + ip += ((ip-anchor) >> kSearchStrength) + 1; /* jump faster over incompressible sections */ + continue; + } + + /* let's try to find a better solution */ + if (depth>=1) + while (ip= 3) & (repIndex > windowLow)) /* intentional overflow */ + if (MEM_read32(ip) == MEM_read32(repMatch)) { + /* repcode detected */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; + int const gain2 = (int)(repLength * 3); + int const gain1 = (int)(matchLength*3 - ZSTD_highbit32((U32)offset+1) + 1); + if ((repLength >= 4) && (gain2 > gain1)) + matchLength = repLength, offset = 0, start = ip; + } } + + /* search match, depth 1 */ + { size_t offset2=999999999; + size_t const ml2 = searchMax(ms, ip, iend, &offset2); + int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */ + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 4); + if ((ml2 >= 4) && (gain2 > gain1)) { + matchLength = ml2, offset = offset2, start = ip; + continue; /* search a better one */ + } } + + /* let's find an even better one */ + if ((depth==2) && (ip= 3) & (repIndex > windowLow)) /* intentional overflow */ + if (MEM_read32(ip) == MEM_read32(repMatch)) { + /* repcode detected */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + size_t const repLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; + int const gain2 = (int)(repLength * 4); + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 1); + if ((repLength >= 4) && (gain2 > gain1)) + matchLength = repLength, offset = 0, start = ip; + } } + + /* search match, depth 2 */ + { size_t offset2=999999999; + size_t const ml2 = searchMax(ms, ip, iend, &offset2); + int const gain2 = (int)(ml2*4 - ZSTD_highbit32((U32)offset2+1)); /* raw approx */ + int const gain1 = (int)(matchLength*4 - ZSTD_highbit32((U32)offset+1) + 7); + if ((ml2 >= 4) && (gain2 > gain1)) { + matchLength = ml2, offset = offset2, start = ip; + continue; + } } } + break; /* nothing found : store previous solution */ + } + + /* catch up */ + if (offset) { + U32 const matchIndex = (U32)((start-base) - (offset - ZSTD_REP_MOVE)); + const BYTE* match = (matchIndex < dictLimit) ? dictBase + matchIndex : base + matchIndex; + const BYTE* const mStart = (matchIndex < dictLimit) ? dictStart : prefixStart; + while ((start>anchor) && (match>mStart) && (start[-1] == match[-1])) { start--; match--; matchLength++; } /* catch up */ + offset_2 = offset_1; offset_1 = (U32)(offset - ZSTD_REP_MOVE); + } + + /* store sequence */ +_storeSequence: + { size_t const litLength = start - anchor; + ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offset, matchLength-MINMATCH); + anchor = ip = start + matchLength; + } + + /* check immediate repcode */ + while (ip <= ilimit) { + const U32 repCurrent = (U32)(ip-base); + const U32 windowLow = ZSTD_getLowestMatchIndex(ms, repCurrent, windowLog); + const U32 repIndex = repCurrent - offset_2; + const BYTE* const repBase = repIndex < dictLimit ? dictBase : base; + const BYTE* const repMatch = repBase + repIndex; + if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow)) /* intentional overflow */ + if (MEM_read32(ip) == MEM_read32(repMatch)) { + /* repcode detected we should take it */ + const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend; + matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4; + offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap offset history */ + ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH); + ip += matchLength; + anchor = ip; + continue; /* faster when present ... (?) */ + } + break; + } } + + /* Save reps for next block */ + rep[0] = offset_1; + rep[1] = offset_2; + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_greedy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0); +} + +size_t ZSTD_compressBlock_lazy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) + +{ + return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1); +} + +size_t ZSTD_compressBlock_lazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) + +{ + return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2); +} + +size_t ZSTD_compressBlock_btlazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) + +{ + return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2); +} diff --git a/lib/zstd/compress/zstd_lazy.h b/lib/zstd/compress/zstd_lazy.h new file mode 100644 index 000000000000..2fc5a6182134 --- /dev/null +++ b/lib/zstd/compress/zstd_lazy.h @@ -0,0 +1,81 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_LAZY_H +#define ZSTD_LAZY_H + + +#include "zstd_compress_internal.h" + +/* + * Dedicated Dictionary Search Structure bucket log. In the + * ZSTD_dedicatedDictSearch mode, the hashTable has + * 2 ** ZSTD_LAZY_DDSS_BUCKET_LOG entries in each bucket, rather than just + * one. + */ +#define ZSTD_LAZY_DDSS_BUCKET_LOG 2 + +U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip); + +void ZSTD_dedicatedDictSearch_lazy_loadDictionary(ZSTD_matchState_t* ms, const BYTE* const ip); + +void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue); /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */ + +size_t ZSTD_compressBlock_btlazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_greedy( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + +size_t ZSTD_compressBlock_btlazy2_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy2_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_greedy_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + +size_t ZSTD_compressBlock_lazy2_dedicatedDictSearch( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy_dedicatedDictSearch( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_greedy_dedicatedDictSearch( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + +size_t ZSTD_compressBlock_greedy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_lazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_btlazy2_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + + +#endif /* ZSTD_LAZY_H */ diff --git a/lib/zstd/compress/zstd_ldm.c b/lib/zstd/compress/zstd_ldm.c new file mode 100644 index 000000000000..8ef7e88a5add --- /dev/null +++ b/lib/zstd/compress/zstd_ldm.c @@ -0,0 +1,686 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include "zstd_ldm.h" + +#include "../common/debug.h" +#include +#include "zstd_fast.h" /* ZSTD_fillHashTable() */ +#include "zstd_double_fast.h" /* ZSTD_fillDoubleHashTable() */ +#include "zstd_ldm_geartab.h" + +#define LDM_BUCKET_SIZE_LOG 3 +#define LDM_MIN_MATCH_LENGTH 64 +#define LDM_HASH_RLOG 7 + +typedef struct { + U64 rolling; + U64 stopMask; +} ldmRollingHashState_t; + +/* ZSTD_ldm_gear_init(): + * + * Initializes the rolling hash state such that it will honor the + * settings in params. */ +static void ZSTD_ldm_gear_init(ldmRollingHashState_t* state, ldmParams_t const* params) +{ + unsigned maxBitsInMask = MIN(params->minMatchLength, 64); + unsigned hashRateLog = params->hashRateLog; + + state->rolling = ~(U32)0; + + /* The choice of the splitting criterion is subject to two conditions: + * 1. it has to trigger on average every 2^(hashRateLog) bytes; + * 2. ideally, it has to depend on a window of minMatchLength bytes. + * + * In the gear hash algorithm, bit n depends on the last n bytes; + * so in order to obtain a good quality splitting criterion it is + * preferable to use bits with high weight. + * + * To match condition 1 we use a mask with hashRateLog bits set + * and, because of the previous remark, we make sure these bits + * have the highest possible weight while still respecting + * condition 2. + */ + if (hashRateLog > 0 && hashRateLog <= maxBitsInMask) { + state->stopMask = (((U64)1 << hashRateLog) - 1) << (maxBitsInMask - hashRateLog); + } else { + /* In this degenerate case we simply honor the hash rate. */ + state->stopMask = ((U64)1 << hashRateLog) - 1; + } +} + +/* ZSTD_ldm_gear_feed(): + * + * Registers in the splits array all the split points found in the first + * size bytes following the data pointer. This function terminates when + * either all the data has been processed or LDM_BATCH_SIZE splits are + * present in the splits array. + * + * Precondition: The splits array must not be full. + * Returns: The number of bytes processed. */ +static size_t ZSTD_ldm_gear_feed(ldmRollingHashState_t* state, + BYTE const* data, size_t size, + size_t* splits, unsigned* numSplits) +{ + size_t n; + U64 hash, mask; + + hash = state->rolling; + mask = state->stopMask; + n = 0; + +#define GEAR_ITER_ONCE() do { \ + hash = (hash << 1) + ZSTD_ldm_gearTab[data[n] & 0xff]; \ + n += 1; \ + if (UNLIKELY((hash & mask) == 0)) { \ + splits[*numSplits] = n; \ + *numSplits += 1; \ + if (*numSplits == LDM_BATCH_SIZE) \ + goto done; \ + } \ + } while (0) + + while (n + 3 < size) { + GEAR_ITER_ONCE(); + GEAR_ITER_ONCE(); + GEAR_ITER_ONCE(); + GEAR_ITER_ONCE(); + } + while (n < size) { + GEAR_ITER_ONCE(); + } + +#undef GEAR_ITER_ONCE + +done: + state->rolling = hash; + return n; +} + +void ZSTD_ldm_adjustParameters(ldmParams_t* params, + ZSTD_compressionParameters const* cParams) +{ + params->windowLog = cParams->windowLog; + ZSTD_STATIC_ASSERT(LDM_BUCKET_SIZE_LOG <= ZSTD_LDM_BUCKETSIZELOG_MAX); + DEBUGLOG(4, "ZSTD_ldm_adjustParameters"); + if (!params->bucketSizeLog) params->bucketSizeLog = LDM_BUCKET_SIZE_LOG; + if (!params->minMatchLength) params->minMatchLength = LDM_MIN_MATCH_LENGTH; + if (params->hashLog == 0) { + params->hashLog = MAX(ZSTD_HASHLOG_MIN, params->windowLog - LDM_HASH_RLOG); + assert(params->hashLog <= ZSTD_HASHLOG_MAX); + } + if (params->hashRateLog == 0) { + params->hashRateLog = params->windowLog < params->hashLog + ? 0 + : params->windowLog - params->hashLog; + } + params->bucketSizeLog = MIN(params->bucketSizeLog, params->hashLog); +} + +size_t ZSTD_ldm_getTableSize(ldmParams_t params) +{ + size_t const ldmHSize = ((size_t)1) << params.hashLog; + size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog); + size_t const ldmBucketSize = ((size_t)1) << (params.hashLog - ldmBucketSizeLog); + size_t const totalSize = ZSTD_cwksp_alloc_size(ldmBucketSize) + + ZSTD_cwksp_alloc_size(ldmHSize * sizeof(ldmEntry_t)); + return params.enableLdm ? totalSize : 0; +} + +size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize) +{ + return params.enableLdm ? (maxChunkSize / params.minMatchLength) : 0; +} + +/* ZSTD_ldm_getBucket() : + * Returns a pointer to the start of the bucket associated with hash. */ +static ldmEntry_t* ZSTD_ldm_getBucket( + ldmState_t* ldmState, size_t hash, ldmParams_t const ldmParams) +{ + return ldmState->hashTable + (hash << ldmParams.bucketSizeLog); +} + +/* ZSTD_ldm_insertEntry() : + * Insert the entry with corresponding hash into the hash table */ +static void ZSTD_ldm_insertEntry(ldmState_t* ldmState, + size_t const hash, const ldmEntry_t entry, + ldmParams_t const ldmParams) +{ + BYTE* const pOffset = ldmState->bucketOffsets + hash; + unsigned const offset = *pOffset; + + *(ZSTD_ldm_getBucket(ldmState, hash, ldmParams) + offset) = entry; + *pOffset = (BYTE)((offset + 1) & ((1u << ldmParams.bucketSizeLog) - 1)); + +} + +/* ZSTD_ldm_countBackwardsMatch() : + * Returns the number of bytes that match backwards before pIn and pMatch. + * + * We count only bytes where pMatch >= pBase and pIn >= pAnchor. */ +static size_t ZSTD_ldm_countBackwardsMatch( + const BYTE* pIn, const BYTE* pAnchor, + const BYTE* pMatch, const BYTE* pMatchBase) +{ + size_t matchLength = 0; + while (pIn > pAnchor && pMatch > pMatchBase && pIn[-1] == pMatch[-1]) { + pIn--; + pMatch--; + matchLength++; + } + return matchLength; +} + +/* ZSTD_ldm_countBackwardsMatch_2segments() : + * Returns the number of bytes that match backwards from pMatch, + * even with the backwards match spanning 2 different segments. + * + * On reaching `pMatchBase`, start counting from mEnd */ +static size_t ZSTD_ldm_countBackwardsMatch_2segments( + const BYTE* pIn, const BYTE* pAnchor, + const BYTE* pMatch, const BYTE* pMatchBase, + const BYTE* pExtDictStart, const BYTE* pExtDictEnd) +{ + size_t matchLength = ZSTD_ldm_countBackwardsMatch(pIn, pAnchor, pMatch, pMatchBase); + if (pMatch - matchLength != pMatchBase || pMatchBase == pExtDictStart) { + /* If backwards match is entirely in the extDict or prefix, immediately return */ + return matchLength; + } + DEBUGLOG(7, "ZSTD_ldm_countBackwardsMatch_2segments: found 2-parts backwards match (length in prefix==%zu)", matchLength); + matchLength += ZSTD_ldm_countBackwardsMatch(pIn - matchLength, pAnchor, pExtDictEnd, pExtDictStart); + DEBUGLOG(7, "final backwards match length = %zu", matchLength); + return matchLength; +} + +/* ZSTD_ldm_fillFastTables() : + * + * Fills the relevant tables for the ZSTD_fast and ZSTD_dfast strategies. + * This is similar to ZSTD_loadDictionaryContent. + * + * The tables for the other strategies are filled within their + * block compressors. */ +static size_t ZSTD_ldm_fillFastTables(ZSTD_matchState_t* ms, + void const* end) +{ + const BYTE* const iend = (const BYTE*)end; + + switch(ms->cParams.strategy) + { + case ZSTD_fast: + ZSTD_fillHashTable(ms, iend, ZSTD_dtlm_fast); + break; + + case ZSTD_dfast: + ZSTD_fillDoubleHashTable(ms, iend, ZSTD_dtlm_fast); + break; + + case ZSTD_greedy: + case ZSTD_lazy: + case ZSTD_lazy2: + case ZSTD_btlazy2: + case ZSTD_btopt: + case ZSTD_btultra: + case ZSTD_btultra2: + break; + default: + assert(0); /* not possible : not a valid strategy id */ + } + + return 0; +} + +void ZSTD_ldm_fillHashTable( + ldmState_t* ldmState, const BYTE* ip, + const BYTE* iend, ldmParams_t const* params) +{ + U32 const minMatchLength = params->minMatchLength; + U32 const hBits = params->hashLog - params->bucketSizeLog; + BYTE const* const base = ldmState->window.base; + BYTE const* const istart = ip; + ldmRollingHashState_t hashState; + size_t* const splits = ldmState->splitIndices; + unsigned numSplits; + + DEBUGLOG(5, "ZSTD_ldm_fillHashTable"); + + ZSTD_ldm_gear_init(&hashState, params); + while (ip < iend) { + size_t hashed; + unsigned n; + + numSplits = 0; + hashed = ZSTD_ldm_gear_feed(&hashState, ip, iend - ip, splits, &numSplits); + + for (n = 0; n < numSplits; n++) { + if (ip + splits[n] >= istart + minMatchLength) { + BYTE const* const split = ip + splits[n] - minMatchLength; + U64 const xxhash = xxh64(split, minMatchLength, 0); + U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1)); + ldmEntry_t entry; + + entry.offset = (U32)(split - base); + entry.checksum = (U32)(xxhash >> 32); + ZSTD_ldm_insertEntry(ldmState, hash, entry, *params); + } + } + + ip += hashed; + } +} + + +/* ZSTD_ldm_limitTableUpdate() : + * + * Sets cctx->nextToUpdate to a position corresponding closer to anchor + * if it is far way + * (after a long match, only update tables a limited amount). */ +static void ZSTD_ldm_limitTableUpdate(ZSTD_matchState_t* ms, const BYTE* anchor) +{ + U32 const curr = (U32)(anchor - ms->window.base); + if (curr > ms->nextToUpdate + 1024) { + ms->nextToUpdate = + curr - MIN(512, curr - ms->nextToUpdate - 1024); + } +} + +static size_t ZSTD_ldm_generateSequences_internal( + ldmState_t* ldmState, rawSeqStore_t* rawSeqStore, + ldmParams_t const* params, void const* src, size_t srcSize) +{ + /* LDM parameters */ + int const extDict = ZSTD_window_hasExtDict(ldmState->window); + U32 const minMatchLength = params->minMatchLength; + U32 const entsPerBucket = 1U << params->bucketSizeLog; + U32 const hBits = params->hashLog - params->bucketSizeLog; + /* Prefix and extDict parameters */ + U32 const dictLimit = ldmState->window.dictLimit; + U32 const lowestIndex = extDict ? ldmState->window.lowLimit : dictLimit; + BYTE const* const base = ldmState->window.base; + BYTE const* const dictBase = extDict ? ldmState->window.dictBase : NULL; + BYTE const* const dictStart = extDict ? dictBase + lowestIndex : NULL; + BYTE const* const dictEnd = extDict ? dictBase + dictLimit : NULL; + BYTE const* const lowPrefixPtr = base + dictLimit; + /* Input bounds */ + BYTE const* const istart = (BYTE const*)src; + BYTE const* const iend = istart + srcSize; + BYTE const* const ilimit = iend - HASH_READ_SIZE; + /* Input positions */ + BYTE const* anchor = istart; + BYTE const* ip = istart; + /* Rolling hash state */ + ldmRollingHashState_t hashState; + /* Arrays for staged-processing */ + size_t* const splits = ldmState->splitIndices; + ldmMatchCandidate_t* const candidates = ldmState->matchCandidates; + unsigned numSplits; + + if (srcSize < minMatchLength) + return iend - anchor; + + /* Initialize the rolling hash state with the first minMatchLength bytes */ + ZSTD_ldm_gear_init(&hashState, params); + { + size_t n = 0; + + while (n < minMatchLength) { + numSplits = 0; + n += ZSTD_ldm_gear_feed(&hashState, ip + n, minMatchLength - n, + splits, &numSplits); + } + ip += minMatchLength; + } + + while (ip < ilimit) { + size_t hashed; + unsigned n; + + numSplits = 0; + hashed = ZSTD_ldm_gear_feed(&hashState, ip, ilimit - ip, + splits, &numSplits); + + for (n = 0; n < numSplits; n++) { + BYTE const* const split = ip + splits[n] - minMatchLength; + U64 const xxhash = xxh64(split, minMatchLength, 0); + U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1)); + + candidates[n].split = split; + candidates[n].hash = hash; + candidates[n].checksum = (U32)(xxhash >> 32); + candidates[n].bucket = ZSTD_ldm_getBucket(ldmState, hash, *params); + PREFETCH_L1(candidates[n].bucket); + } + + for (n = 0; n < numSplits; n++) { + size_t forwardMatchLength = 0, backwardMatchLength = 0, + bestMatchLength = 0, mLength; + BYTE const* const split = candidates[n].split; + U32 const checksum = candidates[n].checksum; + U32 const hash = candidates[n].hash; + ldmEntry_t* const bucket = candidates[n].bucket; + ldmEntry_t const* cur; + ldmEntry_t const* bestEntry = NULL; + ldmEntry_t newEntry; + + newEntry.offset = (U32)(split - base); + newEntry.checksum = checksum; + + /* If a split point would generate a sequence overlapping with + * the previous one, we merely register it in the hash table and + * move on */ + if (split < anchor) { + ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params); + continue; + } + + for (cur = bucket; cur < bucket + entsPerBucket; cur++) { + size_t curForwardMatchLength, curBackwardMatchLength, + curTotalMatchLength; + if (cur->checksum != checksum || cur->offset <= lowestIndex) { + continue; + } + if (extDict) { + BYTE const* const curMatchBase = + cur->offset < dictLimit ? dictBase : base; + BYTE const* const pMatch = curMatchBase + cur->offset; + BYTE const* const matchEnd = + cur->offset < dictLimit ? dictEnd : iend; + BYTE const* const lowMatchPtr = + cur->offset < dictLimit ? dictStart : lowPrefixPtr; + curForwardMatchLength = + ZSTD_count_2segments(split, pMatch, iend, matchEnd, lowPrefixPtr); + if (curForwardMatchLength < minMatchLength) { + continue; + } + curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch_2segments( + split, anchor, pMatch, lowMatchPtr, dictStart, dictEnd); + } else { /* !extDict */ + BYTE const* const pMatch = base + cur->offset; + curForwardMatchLength = ZSTD_count(split, pMatch, iend); + if (curForwardMatchLength < minMatchLength) { + continue; + } + curBackwardMatchLength = + ZSTD_ldm_countBackwardsMatch(split, anchor, pMatch, lowPrefixPtr); + } + curTotalMatchLength = curForwardMatchLength + curBackwardMatchLength; + + if (curTotalMatchLength > bestMatchLength) { + bestMatchLength = curTotalMatchLength; + forwardMatchLength = curForwardMatchLength; + backwardMatchLength = curBackwardMatchLength; + bestEntry = cur; + } + } + + /* No match found -- insert an entry into the hash table + * and process the next candidate match */ + if (bestEntry == NULL) { + ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params); + continue; + } + + /* Match found */ + mLength = forwardMatchLength + backwardMatchLength; + { + U32 const offset = (U32)(split - base) - bestEntry->offset; + rawSeq* const seq = rawSeqStore->seq + rawSeqStore->size; + + /* Out of sequence storage */ + if (rawSeqStore->size == rawSeqStore->capacity) + return ERROR(dstSize_tooSmall); + seq->litLength = (U32)(split - backwardMatchLength - anchor); + seq->matchLength = (U32)mLength; + seq->offset = offset; + rawSeqStore->size++; + } + + /* Insert the current entry into the hash table --- it must be + * done after the previous block to avoid clobbering bestEntry */ + ZSTD_ldm_insertEntry(ldmState, hash, newEntry, *params); + + anchor = split + forwardMatchLength; + } + + ip += hashed; + } + + return iend - anchor; +} + +/*! ZSTD_ldm_reduceTable() : + * reduce table indexes by `reducerValue` */ +static void ZSTD_ldm_reduceTable(ldmEntry_t* const table, U32 const size, + U32 const reducerValue) +{ + U32 u; + for (u = 0; u < size; u++) { + if (table[u].offset < reducerValue) table[u].offset = 0; + else table[u].offset -= reducerValue; + } +} + +size_t ZSTD_ldm_generateSequences( + ldmState_t* ldmState, rawSeqStore_t* sequences, + ldmParams_t const* params, void const* src, size_t srcSize) +{ + U32 const maxDist = 1U << params->windowLog; + BYTE const* const istart = (BYTE const*)src; + BYTE const* const iend = istart + srcSize; + size_t const kMaxChunkSize = 1 << 20; + size_t const nbChunks = (srcSize / kMaxChunkSize) + ((srcSize % kMaxChunkSize) != 0); + size_t chunk; + size_t leftoverSize = 0; + + assert(ZSTD_CHUNKSIZE_MAX >= kMaxChunkSize); + /* Check that ZSTD_window_update() has been called for this chunk prior + * to passing it to this function. + */ + assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize); + /* The input could be very large (in zstdmt), so it must be broken up into + * chunks to enforce the maximum distance and handle overflow correction. + */ + assert(sequences->pos <= sequences->size); + assert(sequences->size <= sequences->capacity); + for (chunk = 0; chunk < nbChunks && sequences->size < sequences->capacity; ++chunk) { + BYTE const* const chunkStart = istart + chunk * kMaxChunkSize; + size_t const remaining = (size_t)(iend - chunkStart); + BYTE const *const chunkEnd = + (remaining < kMaxChunkSize) ? iend : chunkStart + kMaxChunkSize; + size_t const chunkSize = chunkEnd - chunkStart; + size_t newLeftoverSize; + size_t const prevSize = sequences->size; + + assert(chunkStart < iend); + /* 1. Perform overflow correction if necessary. */ + if (ZSTD_window_needOverflowCorrection(ldmState->window, chunkEnd)) { + U32 const ldmHSize = 1U << params->hashLog; + U32 const correction = ZSTD_window_correctOverflow( + &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart); + ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction); + /* invalidate dictionaries on overflow correction */ + ldmState->loadedDictEnd = 0; + } + /* 2. We enforce the maximum offset allowed. + * + * kMaxChunkSize should be small enough that we don't lose too much of + * the window through early invalidation. + * TODO: * Test the chunk size. + * * Try invalidation after the sequence generation and test the + * the offset against maxDist directly. + * + * NOTE: Because of dictionaries + sequence splitting we MUST make sure + * that any offset used is valid at the END of the sequence, since it may + * be split into two sequences. This condition holds when using + * ZSTD_window_enforceMaxDist(), but if we move to checking offsets + * against maxDist directly, we'll have to carefully handle that case. + */ + ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, &ldmState->loadedDictEnd, NULL); + /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */ + newLeftoverSize = ZSTD_ldm_generateSequences_internal( + ldmState, sequences, params, chunkStart, chunkSize); + if (ZSTD_isError(newLeftoverSize)) + return newLeftoverSize; + /* 4. We add the leftover literals from previous iterations to the first + * newly generated sequence, or add the `newLeftoverSize` if none are + * generated. + */ + /* Prepend the leftover literals from the last call */ + if (prevSize < sequences->size) { + sequences->seq[prevSize].litLength += (U32)leftoverSize; + leftoverSize = newLeftoverSize; + } else { + assert(newLeftoverSize == chunkSize); + leftoverSize += chunkSize; + } + } + return 0; +} + +void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, U32 const minMatch) { + while (srcSize > 0 && rawSeqStore->pos < rawSeqStore->size) { + rawSeq* seq = rawSeqStore->seq + rawSeqStore->pos; + if (srcSize <= seq->litLength) { + /* Skip past srcSize literals */ + seq->litLength -= (U32)srcSize; + return; + } + srcSize -= seq->litLength; + seq->litLength = 0; + if (srcSize < seq->matchLength) { + /* Skip past the first srcSize of the match */ + seq->matchLength -= (U32)srcSize; + if (seq->matchLength < minMatch) { + /* The match is too short, omit it */ + if (rawSeqStore->pos + 1 < rawSeqStore->size) { + seq[1].litLength += seq[0].matchLength; + } + rawSeqStore->pos++; + } + return; + } + srcSize -= seq->matchLength; + seq->matchLength = 0; + rawSeqStore->pos++; + } +} + +/* + * If the sequence length is longer than remaining then the sequence is split + * between this block and the next. + * + * Returns the current sequence to handle, or if the rest of the block should + * be literals, it returns a sequence with offset == 0. + */ +static rawSeq maybeSplitSequence(rawSeqStore_t* rawSeqStore, + U32 const remaining, U32 const minMatch) +{ + rawSeq sequence = rawSeqStore->seq[rawSeqStore->pos]; + assert(sequence.offset > 0); + /* Likely: No partial sequence */ + if (remaining >= sequence.litLength + sequence.matchLength) { + rawSeqStore->pos++; + return sequence; + } + /* Cut the sequence short (offset == 0 ==> rest is literals). */ + if (remaining <= sequence.litLength) { + sequence.offset = 0; + } else if (remaining < sequence.litLength + sequence.matchLength) { + sequence.matchLength = remaining - sequence.litLength; + if (sequence.matchLength < minMatch) { + sequence.offset = 0; + } + } + /* Skip past `remaining` bytes for the future sequences. */ + ZSTD_ldm_skipSequences(rawSeqStore, remaining, minMatch); + return sequence; +} + +void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes) { + U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes); + while (currPos && rawSeqStore->pos < rawSeqStore->size) { + rawSeq currSeq = rawSeqStore->seq[rawSeqStore->pos]; + if (currPos >= currSeq.litLength + currSeq.matchLength) { + currPos -= currSeq.litLength + currSeq.matchLength; + rawSeqStore->pos++; + } else { + rawSeqStore->posInSequence = currPos; + break; + } + } + if (currPos == 0 || rawSeqStore->pos == rawSeqStore->size) { + rawSeqStore->posInSequence = 0; + } +} + +size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + unsigned const minMatch = cParams->minMatch; + ZSTD_blockCompressor const blockCompressor = + ZSTD_selectBlockCompressor(cParams->strategy, ZSTD_matchState_dictMode(ms)); + /* Input bounds */ + BYTE const* const istart = (BYTE const*)src; + BYTE const* const iend = istart + srcSize; + /* Input positions */ + BYTE const* ip = istart; + + DEBUGLOG(5, "ZSTD_ldm_blockCompress: srcSize=%zu", srcSize); + /* If using opt parser, use LDMs only as candidates rather than always accepting them */ + if (cParams->strategy >= ZSTD_btopt) { + size_t lastLLSize; + ms->ldmSeqStore = rawSeqStore; + lastLLSize = blockCompressor(ms, seqStore, rep, src, srcSize); + ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore, srcSize); + return lastLLSize; + } + + assert(rawSeqStore->pos <= rawSeqStore->size); + assert(rawSeqStore->size <= rawSeqStore->capacity); + /* Loop through each sequence and apply the block compressor to the literals */ + while (rawSeqStore->pos < rawSeqStore->size && ip < iend) { + /* maybeSplitSequence updates rawSeqStore->pos */ + rawSeq const sequence = maybeSplitSequence(rawSeqStore, + (U32)(iend - ip), minMatch); + int i; + /* End signal */ + if (sequence.offset == 0) + break; + + assert(ip + sequence.litLength + sequence.matchLength <= iend); + + /* Fill tables for block compressor */ + ZSTD_ldm_limitTableUpdate(ms, ip); + ZSTD_ldm_fillFastTables(ms, ip); + /* Run the block compressor */ + DEBUGLOG(5, "pos %u : calling block compressor on segment of size %u", (unsigned)(ip-istart), sequence.litLength); + { + size_t const newLitLength = + blockCompressor(ms, seqStore, rep, ip, sequence.litLength); + ip += sequence.litLength; + /* Update the repcodes */ + for (i = ZSTD_REP_NUM - 1; i > 0; i--) + rep[i] = rep[i-1]; + rep[0] = sequence.offset; + /* Store the sequence */ + ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength, iend, + sequence.offset + ZSTD_REP_MOVE, + sequence.matchLength - MINMATCH); + ip += sequence.matchLength; + } + } + /* Fill the tables for the block compressor */ + ZSTD_ldm_limitTableUpdate(ms, ip); + ZSTD_ldm_fillFastTables(ms, ip); + /* Compress the last literals */ + return blockCompressor(ms, seqStore, rep, ip, iend - ip); +} diff --git a/lib/zstd/compress/zstd_ldm.h b/lib/zstd/compress/zstd_ldm.h new file mode 100644 index 000000000000..25b25270b72e --- /dev/null +++ b/lib/zstd/compress/zstd_ldm.h @@ -0,0 +1,110 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_LDM_H +#define ZSTD_LDM_H + + +#include "zstd_compress_internal.h" /* ldmParams_t, U32 */ +#include /* ZSTD_CCtx, size_t */ + +/*-************************************* +* Long distance matching +***************************************/ + +#define ZSTD_LDM_DEFAULT_WINDOW_LOG ZSTD_WINDOWLOG_LIMIT_DEFAULT + +void ZSTD_ldm_fillHashTable( + ldmState_t* state, const BYTE* ip, + const BYTE* iend, ldmParams_t const* params); + +/* + * ZSTD_ldm_generateSequences(): + * + * Generates the sequences using the long distance match finder. + * Generates long range matching sequences in `sequences`, which parse a prefix + * of the source. `sequences` must be large enough to store every sequence, + * which can be checked with `ZSTD_ldm_getMaxNbSeq()`. + * @returns 0 or an error code. + * + * NOTE: The user must have called ZSTD_window_update() for all of the input + * they have, even if they pass it to ZSTD_ldm_generateSequences() in chunks. + * NOTE: This function returns an error if it runs out of space to store + * sequences. + */ +size_t ZSTD_ldm_generateSequences( + ldmState_t* ldms, rawSeqStore_t* sequences, + ldmParams_t const* params, void const* src, size_t srcSize); + +/* + * ZSTD_ldm_blockCompress(): + * + * Compresses a block using the predefined sequences, along with a secondary + * block compressor. The literals section of every sequence is passed to the + * secondary block compressor, and those sequences are interspersed with the + * predefined sequences. Returns the length of the last literals. + * Updates `rawSeqStore.pos` to indicate how many sequences have been consumed. + * `rawSeqStore.seq` may also be updated to split the last sequence between two + * blocks. + * @return The length of the last literals. + * + * NOTE: The source must be at most the maximum block size, but the predefined + * sequences can be any size, and may be longer than the block. In the case that + * they are longer than the block, the last sequences may need to be split into + * two. We handle that case correctly, and update `rawSeqStore` appropriately. + * NOTE: This function does not return any errors. + */ +size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore, + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + +/* + * ZSTD_ldm_skipSequences(): + * + * Skip past `srcSize` bytes worth of sequences in `rawSeqStore`. + * Avoids emitting matches less than `minMatch` bytes. + * Must be called for data that is not passed to ZSTD_ldm_blockCompress(). + */ +void ZSTD_ldm_skipSequences(rawSeqStore_t* rawSeqStore, size_t srcSize, + U32 const minMatch); + +/* ZSTD_ldm_skipRawSeqStoreBytes(): + * Moves forward in rawSeqStore by nbBytes, updating fields 'pos' and 'posInSequence'. + * Not to be used in conjunction with ZSTD_ldm_skipSequences(). + * Must be called for data with is not passed to ZSTD_ldm_blockCompress(). + */ +void ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes); + +/* ZSTD_ldm_getTableSize() : + * Estimate the space needed for long distance matching tables or 0 if LDM is + * disabled. + */ +size_t ZSTD_ldm_getTableSize(ldmParams_t params); + +/* ZSTD_ldm_getSeqSpace() : + * Return an upper bound on the number of sequences that can be produced by + * the long distance matcher, or 0 if LDM is disabled. + */ +size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize); + +/* ZSTD_ldm_adjustParameters() : + * If the params->hashRateLog is not set, set it to its default value based on + * windowLog and params->hashLog. + * + * Ensures that params->bucketSizeLog is <= params->hashLog (setting it to + * params->hashLog if it is not). + * + * Ensures that the minMatchLength >= targetLength during optimal parsing. + */ +void ZSTD_ldm_adjustParameters(ldmParams_t* params, + ZSTD_compressionParameters const* cParams); + + +#endif /* ZSTD_FAST_H */ diff --git a/lib/zstd/compress/zstd_ldm_geartab.h b/lib/zstd/compress/zstd_ldm_geartab.h new file mode 100644 index 000000000000..e5c24d856b0a --- /dev/null +++ b/lib/zstd/compress/zstd_ldm_geartab.h @@ -0,0 +1,103 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_LDM_GEARTAB_H +#define ZSTD_LDM_GEARTAB_H + +static U64 ZSTD_ldm_gearTab[256] = { + 0xf5b8f72c5f77775c, 0x84935f266b7ac412, 0xb647ada9ca730ccc, + 0xb065bb4b114fb1de, 0x34584e7e8c3a9fd0, 0x4e97e17c6ae26b05, + 0x3a03d743bc99a604, 0xcecd042422c4044f, 0x76de76c58524259e, + 0x9c8528f65badeaca, 0x86563706e2097529, 0x2902475fa375d889, + 0xafb32a9739a5ebe6, 0xce2714da3883e639, 0x21eaf821722e69e, + 0x37b628620b628, 0x49a8d455d88caf5, 0x8556d711e6958140, + 0x4f7ae74fc605c1f, 0x829f0c3468bd3a20, 0x4ffdc885c625179e, + 0x8473de048a3daf1b, 0x51008822b05646b2, 0x69d75d12b2d1cc5f, + 0x8c9d4a19159154bc, 0xc3cc10f4abbd4003, 0xd06ddc1cecb97391, + 0xbe48e6e7ed80302e, 0x3481db31cee03547, 0xacc3f67cdaa1d210, + 0x65cb771d8c7f96cc, 0x8eb27177055723dd, 0xc789950d44cd94be, + 0x934feadc3700b12b, 0x5e485f11edbdf182, 0x1e2e2a46fd64767a, + 0x2969ca71d82efa7c, 0x9d46e9935ebbba2e, 0xe056b67e05e6822b, + 0x94d73f55739d03a0, 0xcd7010bdb69b5a03, 0x455ef9fcd79b82f4, + 0x869cb54a8749c161, 0x38d1a4fa6185d225, 0xb475166f94bbe9bb, + 0xa4143548720959f1, 0x7aed4780ba6b26ba, 0xd0ce264439e02312, + 0x84366d746078d508, 0xa8ce973c72ed17be, 0x21c323a29a430b01, + 0x9962d617e3af80ee, 0xab0ce91d9c8cf75b, 0x530e8ee6d19a4dbc, + 0x2ef68c0cf53f5d72, 0xc03a681640a85506, 0x496e4e9f9c310967, + 0x78580472b59b14a0, 0x273824c23b388577, 0x66bf923ad45cb553, + 0x47ae1a5a2492ba86, 0x35e304569e229659, 0x4765182a46870b6f, + 0x6cbab625e9099412, 0xddac9a2e598522c1, 0x7172086e666624f2, + 0xdf5003ca503b7837, 0x88c0c1db78563d09, 0x58d51865acfc289d, + 0x177671aec65224f1, 0xfb79d8a241e967d7, 0x2be1e101cad9a49a, + 0x6625682f6e29186b, 0x399553457ac06e50, 0x35dffb4c23abb74, + 0x429db2591f54aade, 0xc52802a8037d1009, 0x6acb27381f0b25f3, + 0xf45e2551ee4f823b, 0x8b0ea2d99580c2f7, 0x3bed519cbcb4e1e1, + 0xff452823dbb010a, 0x9d42ed614f3dd267, 0x5b9313c06257c57b, + 0xa114b8008b5e1442, 0xc1fe311c11c13d4b, 0x66e8763ea34c5568, + 0x8b982af1c262f05d, 0xee8876faaa75fbb7, 0x8a62a4d0d172bb2a, + 0xc13d94a3b7449a97, 0x6dbbba9dc15d037c, 0xc786101f1d92e0f1, + 0xd78681a907a0b79b, 0xf61aaf2962c9abb9, 0x2cfd16fcd3cb7ad9, + 0x868c5b6744624d21, 0x25e650899c74ddd7, 0xba042af4a7c37463, + 0x4eb1a539465a3eca, 0xbe09dbf03b05d5ca, 0x774e5a362b5472ba, + 0x47a1221229d183cd, 0x504b0ca18ef5a2df, 0xdffbdfbde2456eb9, + 0x46cd2b2fbee34634, 0xf2aef8fe819d98c3, 0x357f5276d4599d61, + 0x24a5483879c453e3, 0x88026889192b4b9, 0x28da96671782dbec, + 0x4ef37c40588e9aaa, 0x8837b90651bc9fb3, 0xc164f741d3f0e5d6, + 0xbc135a0a704b70ba, 0x69cd868f7622ada, 0xbc37ba89e0b9c0ab, + 0x47c14a01323552f6, 0x4f00794bacee98bb, 0x7107de7d637a69d5, + 0x88af793bb6f2255e, 0xf3c6466b8799b598, 0xc288c616aa7f3b59, + 0x81ca63cf42fca3fd, 0x88d85ace36a2674b, 0xd056bd3792389e7, + 0xe55c396c4e9dd32d, 0xbefb504571e6c0a6, 0x96ab32115e91e8cc, + 0xbf8acb18de8f38d1, 0x66dae58801672606, 0x833b6017872317fb, + 0xb87c16f2d1c92864, 0xdb766a74e58b669c, 0x89659f85c61417be, + 0xc8daad856011ea0c, 0x76a4b565b6fe7eae, 0xa469d085f6237312, + 0xaaf0365683a3e96c, 0x4dbb746f8424f7b8, 0x638755af4e4acc1, + 0x3d7807f5bde64486, 0x17be6d8f5bbb7639, 0x903f0cd44dc35dc, + 0x67b672eafdf1196c, 0xa676ff93ed4c82f1, 0x521d1004c5053d9d, + 0x37ba9ad09ccc9202, 0x84e54d297aacfb51, 0xa0b4b776a143445, + 0x820d471e20b348e, 0x1874383cb83d46dc, 0x97edeec7a1efe11c, + 0xb330e50b1bdc42aa, 0x1dd91955ce70e032, 0xa514cdb88f2939d5, + 0x2791233fd90db9d3, 0x7b670a4cc50f7a9b, 0x77c07d2a05c6dfa5, + 0xe3778b6646d0a6fa, 0xb39c8eda47b56749, 0x933ed448addbef28, + 0xaf846af6ab7d0bf4, 0xe5af208eb666e49, 0x5e6622f73534cd6a, + 0x297daeca42ef5b6e, 0x862daef3d35539a6, 0xe68722498f8e1ea9, + 0x981c53093dc0d572, 0xfa09b0bfbf86fbf5, 0x30b1e96166219f15, + 0x70e7d466bdc4fb83, 0x5a66736e35f2a8e9, 0xcddb59d2b7c1baef, + 0xd6c7d247d26d8996, 0xea4e39eac8de1ba3, 0x539c8bb19fa3aff2, + 0x9f90e4c5fd508d8, 0xa34e5956fbaf3385, 0x2e2f8e151d3ef375, + 0x173691e9b83faec1, 0xb85a8d56bf016379, 0x8382381267408ae3, + 0xb90f901bbdc0096d, 0x7c6ad32933bcec65, 0x76bb5e2f2c8ad595, + 0x390f851a6cf46d28, 0xc3e6064da1c2da72, 0xc52a0c101cfa5389, + 0xd78eaf84a3fbc530, 0x3781b9e2288b997e, 0x73c2f6dea83d05c4, + 0x4228e364c5b5ed7, 0x9d7a3edf0da43911, 0x8edcfeda24686756, + 0x5e7667a7b7a9b3a1, 0x4c4f389fa143791d, 0xb08bc1023da7cddc, + 0x7ab4be3ae529b1cc, 0x754e6132dbe74ff9, 0x71635442a839df45, + 0x2f6fb1643fbe52de, 0x961e0a42cf7a8177, 0xf3b45d83d89ef2ea, + 0xee3de4cf4a6e3e9b, 0xcd6848542c3295e7, 0xe4cee1664c78662f, + 0x9947548b474c68c4, 0x25d73777a5ed8b0b, 0xc915b1d636b7fc, + 0x21c2ba75d9b0d2da, 0x5f6b5dcf608a64a1, 0xdcf333255ff9570c, + 0x633b922418ced4ee, 0xc136dde0b004b34a, 0x58cc83b05d4b2f5a, + 0x5eb424dda28e42d2, 0x62df47369739cd98, 0xb4e0b42485e4ce17, + 0x16e1f0c1f9a8d1e7, 0x8ec3916707560ebf, 0x62ba6e2df2cc9db3, + 0xcbf9f4ff77d83a16, 0x78d9d7d07d2bbcc4, 0xef554ce1e02c41f4, + 0x8d7581127eccf94d, 0xa9b53336cb3c8a05, 0x38c42c0bf45c4f91, + 0x640893cdf4488863, 0x80ec34bc575ea568, 0x39f324f5b48eaa40, + 0xe9d9ed1f8eff527f, 0x9224fc058cc5a214, 0xbaba00b04cfe7741, + 0x309a9f120fcf52af, 0xa558f3ec65626212, 0x424bec8b7adabe2f, + 0x41622513a6aea433, 0xb88da2d5324ca798, 0xd287733b245528a4, + 0x9a44697e6d68aec3, 0x7b1093be2f49bb28, 0x50bbec632e3d8aad, + 0x6cd90723e1ea8283, 0x897b9e7431b02bf3, 0x219efdcb338a7047, + 0x3b0311f0a27c0656, 0xdb17bf91c0db96e7, 0x8cd4fd6b4e85a5b2, + 0xfab071054ba6409d, 0x40d6fe831fa9dfd9, 0xaf358debad7d791e, + 0xeb8d0e25a65e3e58, 0xbbcbd3df14e08580, 0xcf751f27ecdab2b, + 0x2b4da14f2613d8f4 +}; + +#endif /* ZSTD_LDM_GEARTAB_H */ diff --git a/lib/zstd/compress/zstd_opt.c b/lib/zstd/compress/zstd_opt.c new file mode 100644 index 000000000000..04337050fe9a --- /dev/null +++ b/lib/zstd/compress/zstd_opt.c @@ -0,0 +1,1346 @@ +/* + * Copyright (c) Przemyslaw Skibinski, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include "zstd_compress_internal.h" +#include "hist.h" +#include "zstd_opt.h" + + +#define ZSTD_LITFREQ_ADD 2 /* scaling factor for litFreq, so that frequencies adapt faster to new stats */ +#define ZSTD_FREQ_DIV 4 /* log factor when using previous stats to init next stats */ +#define ZSTD_MAX_PRICE (1<<30) + +#define ZSTD_PREDEF_THRESHOLD 1024 /* if srcSize < ZSTD_PREDEF_THRESHOLD, symbols' cost is assumed static, directly determined by pre-defined distributions */ + + +/*-************************************* +* Price functions for optimal parser +***************************************/ + +#if 0 /* approximation at bit level */ +# define BITCOST_ACCURACY 0 +# define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY) +# define WEIGHT(stat) ((void)opt, ZSTD_bitWeight(stat)) +#elif 0 /* fractional bit accuracy */ +# define BITCOST_ACCURACY 8 +# define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY) +# define WEIGHT(stat,opt) ((void)opt, ZSTD_fracWeight(stat)) +#else /* opt==approx, ultra==accurate */ +# define BITCOST_ACCURACY 8 +# define BITCOST_MULTIPLIER (1 << BITCOST_ACCURACY) +# define WEIGHT(stat,opt) (opt ? ZSTD_fracWeight(stat) : ZSTD_bitWeight(stat)) +#endif + +MEM_STATIC U32 ZSTD_bitWeight(U32 stat) +{ + return (ZSTD_highbit32(stat+1) * BITCOST_MULTIPLIER); +} + +MEM_STATIC U32 ZSTD_fracWeight(U32 rawStat) +{ + U32 const stat = rawStat + 1; + U32 const hb = ZSTD_highbit32(stat); + U32 const BWeight = hb * BITCOST_MULTIPLIER; + U32 const FWeight = (stat << BITCOST_ACCURACY) >> hb; + U32 const weight = BWeight + FWeight; + assert(hb + BITCOST_ACCURACY < 31); + return weight; +} + +#if (DEBUGLEVEL>=2) +/* debugging function, + * @return price in bytes as fractional value + * for debug messages only */ +MEM_STATIC double ZSTD_fCost(U32 price) +{ + return (double)price / (BITCOST_MULTIPLIER*8); +} +#endif + +static int ZSTD_compressedLiterals(optState_t const* const optPtr) +{ + return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed; +} + +static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel) +{ + if (ZSTD_compressedLiterals(optPtr)) + optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel); + optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel); + optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel); + optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel); +} + + +/* ZSTD_downscaleStat() : + * reduce all elements in table by a factor 2^(ZSTD_FREQ_DIV+malus) + * return the resulting sum of elements */ +static U32 ZSTD_downscaleStat(unsigned* table, U32 lastEltIndex, int malus) +{ + U32 s, sum=0; + DEBUGLOG(5, "ZSTD_downscaleStat (nbElts=%u)", (unsigned)lastEltIndex+1); + assert(ZSTD_FREQ_DIV+malus > 0 && ZSTD_FREQ_DIV+malus < 31); + for (s=0; s> (ZSTD_FREQ_DIV+malus)); + sum += table[s]; + } + return sum; +} + +/* ZSTD_rescaleFreqs() : + * if first block (detected by optPtr->litLengthSum == 0) : init statistics + * take hints from dictionary if there is one + * or init from zero, using src for literals stats, or flat 1 for match symbols + * otherwise downscale existing stats, to be used as seed for next block. + */ +static void +ZSTD_rescaleFreqs(optState_t* const optPtr, + const BYTE* const src, size_t const srcSize, + int const optLevel) +{ + int const compressedLiterals = ZSTD_compressedLiterals(optPtr); + DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize); + optPtr->priceType = zop_dynamic; + + if (optPtr->litLengthSum == 0) { /* first block : init */ + if (srcSize <= ZSTD_PREDEF_THRESHOLD) { /* heuristic */ + DEBUGLOG(5, "(srcSize <= ZSTD_PREDEF_THRESHOLD) => zop_predef"); + optPtr->priceType = zop_predef; + } + + assert(optPtr->symbolCosts != NULL); + if (optPtr->symbolCosts->huf.repeatMode == HUF_repeat_valid) { + /* huffman table presumed generated by dictionary */ + optPtr->priceType = zop_dynamic; + + if (compressedLiterals) { + unsigned lit; + assert(optPtr->litFreq != NULL); + optPtr->litSum = 0; + for (lit=0; lit<=MaxLit; lit++) { + U32 const scaleLog = 11; /* scale to 2K */ + U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit); + assert(bitCost <= scaleLog); + optPtr->litFreq[lit] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/; + optPtr->litSum += optPtr->litFreq[lit]; + } } + + { unsigned ll; + FSE_CState_t llstate; + FSE_initCState(&llstate, optPtr->symbolCosts->fse.litlengthCTable); + optPtr->litLengthSum = 0; + for (ll=0; ll<=MaxLL; ll++) { + U32 const scaleLog = 10; /* scale to 1K */ + U32 const bitCost = FSE_getMaxNbBits(llstate.symbolTT, ll); + assert(bitCost < scaleLog); + optPtr->litLengthFreq[ll] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/; + optPtr->litLengthSum += optPtr->litLengthFreq[ll]; + } } + + { unsigned ml; + FSE_CState_t mlstate; + FSE_initCState(&mlstate, optPtr->symbolCosts->fse.matchlengthCTable); + optPtr->matchLengthSum = 0; + for (ml=0; ml<=MaxML; ml++) { + U32 const scaleLog = 10; + U32 const bitCost = FSE_getMaxNbBits(mlstate.symbolTT, ml); + assert(bitCost < scaleLog); + optPtr->matchLengthFreq[ml] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/; + optPtr->matchLengthSum += optPtr->matchLengthFreq[ml]; + } } + + { unsigned of; + FSE_CState_t ofstate; + FSE_initCState(&ofstate, optPtr->symbolCosts->fse.offcodeCTable); + optPtr->offCodeSum = 0; + for (of=0; of<=MaxOff; of++) { + U32 const scaleLog = 10; + U32 const bitCost = FSE_getMaxNbBits(ofstate.symbolTT, of); + assert(bitCost < scaleLog); + optPtr->offCodeFreq[of] = bitCost ? 1 << (scaleLog-bitCost) : 1 /*minimum to calculate cost*/; + optPtr->offCodeSum += optPtr->offCodeFreq[of]; + } } + + } else { /* not a dictionary */ + + assert(optPtr->litFreq != NULL); + if (compressedLiterals) { + unsigned lit = MaxLit; + HIST_count_simple(optPtr->litFreq, &lit, src, srcSize); /* use raw first block to init statistics */ + optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1); + } + + { unsigned ll; + for (ll=0; ll<=MaxLL; ll++) + optPtr->litLengthFreq[ll] = 1; + } + optPtr->litLengthSum = MaxLL+1; + + { unsigned ml; + for (ml=0; ml<=MaxML; ml++) + optPtr->matchLengthFreq[ml] = 1; + } + optPtr->matchLengthSum = MaxML+1; + + { unsigned of; + for (of=0; of<=MaxOff; of++) + optPtr->offCodeFreq[of] = 1; + } + optPtr->offCodeSum = MaxOff+1; + + } + + } else { /* new block : re-use previous statistics, scaled down */ + + if (compressedLiterals) + optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1); + optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0); + optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0); + optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0); + } + + ZSTD_setBasePrices(optPtr, optLevel); +} + +/* ZSTD_rawLiteralsCost() : + * price of literals (only) in specified segment (which length can be 0). + * does not include price of literalLength symbol */ +static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength, + const optState_t* const optPtr, + int optLevel) +{ + if (litLength == 0) return 0; + + if (!ZSTD_compressedLiterals(optPtr)) + return (litLength << 3) * BITCOST_MULTIPLIER; /* Uncompressed - 8 bytes per literal. */ + + if (optPtr->priceType == zop_predef) + return (litLength*6) * BITCOST_MULTIPLIER; /* 6 bit per literal - no statistic used */ + + /* dynamic statistics */ + { U32 price = litLength * optPtr->litSumBasePrice; + U32 u; + for (u=0; u < litLength; u++) { + assert(WEIGHT(optPtr->litFreq[literals[u]], optLevel) <= optPtr->litSumBasePrice); /* literal cost should never be negative */ + price -= WEIGHT(optPtr->litFreq[literals[u]], optLevel); + } + return price; + } +} + +/* ZSTD_litLengthPrice() : + * cost of literalLength symbol */ +static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optPtr, int optLevel) +{ + if (optPtr->priceType == zop_predef) return WEIGHT(litLength, optLevel); + + /* dynamic statistics */ + { U32 const llCode = ZSTD_LLcode(litLength); + return (LL_bits[llCode] * BITCOST_MULTIPLIER) + + optPtr->litLengthSumBasePrice + - WEIGHT(optPtr->litLengthFreq[llCode], optLevel); + } +} + +/* ZSTD_getMatchPrice() : + * Provides the cost of the match part (offset + matchLength) of a sequence + * Must be combined with ZSTD_fullLiteralsCost() to get the full cost of a sequence. + * optLevel: when <2, favors small offset for decompression speed (improved cache efficiency) */ +FORCE_INLINE_TEMPLATE U32 +ZSTD_getMatchPrice(U32 const offset, + U32 const matchLength, + const optState_t* const optPtr, + int const optLevel) +{ + U32 price; + U32 const offCode = ZSTD_highbit32(offset+1); + U32 const mlBase = matchLength - MINMATCH; + assert(matchLength >= MINMATCH); + + if (optPtr->priceType == zop_predef) /* fixed scheme, do not use statistics */ + return WEIGHT(mlBase, optLevel) + ((16 + offCode) * BITCOST_MULTIPLIER); + + /* dynamic statistics */ + price = (offCode * BITCOST_MULTIPLIER) + (optPtr->offCodeSumBasePrice - WEIGHT(optPtr->offCodeFreq[offCode], optLevel)); + if ((optLevel<2) /*static*/ && offCode >= 20) + price += (offCode-19)*2 * BITCOST_MULTIPLIER; /* handicap for long distance offsets, favor decompression speed */ + + /* match Length */ + { U32 const mlCode = ZSTD_MLcode(mlBase); + price += (ML_bits[mlCode] * BITCOST_MULTIPLIER) + (optPtr->matchLengthSumBasePrice - WEIGHT(optPtr->matchLengthFreq[mlCode], optLevel)); + } + + price += BITCOST_MULTIPLIER / 5; /* heuristic : make matches a bit more costly to favor less sequences -> faster decompression speed */ + + DEBUGLOG(8, "ZSTD_getMatchPrice(ml:%u) = %u", matchLength, price); + return price; +} + +/* ZSTD_updateStats() : + * assumption : literals + litLengtn <= iend */ +static void ZSTD_updateStats(optState_t* const optPtr, + U32 litLength, const BYTE* literals, + U32 offsetCode, U32 matchLength) +{ + /* literals */ + if (ZSTD_compressedLiterals(optPtr)) { + U32 u; + for (u=0; u < litLength; u++) + optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD; + optPtr->litSum += litLength*ZSTD_LITFREQ_ADD; + } + + /* literal Length */ + { U32 const llCode = ZSTD_LLcode(litLength); + optPtr->litLengthFreq[llCode]++; + optPtr->litLengthSum++; + } + + /* match offset code (0-2=>repCode; 3+=>offset+2) */ + { U32 const offCode = ZSTD_highbit32(offsetCode+1); + assert(offCode <= MaxOff); + optPtr->offCodeFreq[offCode]++; + optPtr->offCodeSum++; + } + + /* match Length */ + { U32 const mlBase = matchLength - MINMATCH; + U32 const mlCode = ZSTD_MLcode(mlBase); + optPtr->matchLengthFreq[mlCode]++; + optPtr->matchLengthSum++; + } +} + + +/* ZSTD_readMINMATCH() : + * function safe only for comparisons + * assumption : memPtr must be at least 4 bytes before end of buffer */ +MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length) +{ + switch (length) + { + default : + case 4 : return MEM_read32(memPtr); + case 3 : if (MEM_isLittleEndian()) + return MEM_read32(memPtr)<<8; + else + return MEM_read32(memPtr)>>8; + } +} + + +/* Update hashTable3 up to ip (excluded) + Assumption : always within prefix (i.e. not within extDict) */ +static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, + U32* nextToUpdate3, + const BYTE* const ip) +{ + U32* const hashTable3 = ms->hashTable3; + U32 const hashLog3 = ms->hashLog3; + const BYTE* const base = ms->window.base; + U32 idx = *nextToUpdate3; + U32 const target = (U32)(ip - base); + size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3); + assert(hashLog3 > 0); + + while(idx < target) { + hashTable3[ZSTD_hash3Ptr(base+idx, hashLog3)] = idx; + idx++; + } + + *nextToUpdate3 = target; + return hashTable3[hash3]; +} + + +/*-************************************* +* Binary Tree search +***************************************/ +/* ZSTD_insertBt1() : add one or multiple positions to tree. + * ip : assumed <= iend-8 . + * @return : nb of positions added */ +static U32 ZSTD_insertBt1( + ZSTD_matchState_t* ms, + const BYTE* const ip, const BYTE* const iend, + U32 const mls, const int extDict) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32* const hashTable = ms->hashTable; + U32 const hashLog = cParams->hashLog; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask = (1 << btLog) - 1; + U32 matchIndex = hashTable[h]; + size_t commonLengthSmaller=0, commonLengthLarger=0; + const BYTE* const base = ms->window.base; + const BYTE* const dictBase = ms->window.dictBase; + const U32 dictLimit = ms->window.dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; + const BYTE* match; + const U32 curr = (U32)(ip-base); + const U32 btLow = btMask >= curr ? 0 : curr - btMask; + U32* smallerPtr = bt + 2*(curr&btMask); + U32* largerPtr = smallerPtr + 1; + U32 dummy32; /* to be nullified at the end */ + U32 const windowLow = ms->window.lowLimit; + U32 matchEndIdx = curr+8+1; + size_t bestLength = 8; + U32 nbCompares = 1U << cParams->searchLog; +#ifdef ZSTD_C_PREDICT + U32 predictedSmall = *(bt + 2*((curr-1)&btMask) + 0); + U32 predictedLarge = *(bt + 2*((curr-1)&btMask) + 1); + predictedSmall += (predictedSmall>0); + predictedLarge += (predictedLarge>0); +#endif /* ZSTD_C_PREDICT */ + + DEBUGLOG(8, "ZSTD_insertBt1 (%u)", curr); + + assert(ip <= iend-8); /* required for h calculation */ + hashTable[h] = curr; /* Update Hash Table */ + + assert(windowLow > 0); + for (; nbCompares && (matchIndex >= windowLow); --nbCompares) { + U32* const nextPtr = bt + 2*(matchIndex & btMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + assert(matchIndex < curr); + +#ifdef ZSTD_C_PREDICT /* note : can create issues when hlog small <= 11 */ + const U32* predictPtr = bt + 2*((matchIndex-1) & btMask); /* written this way, as bt is a roll buffer */ + if (matchIndex == predictedSmall) { + /* no need to check length, result known */ + *smallerPtr = matchIndex; + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + smallerPtr = nextPtr+1; /* new "smaller" => larger of match */ + matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ + predictedSmall = predictPtr[1] + (predictPtr[1]>0); + continue; + } + if (matchIndex == predictedLarge) { + *largerPtr = matchIndex; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + predictedLarge = predictPtr[0] + (predictPtr[0]>0); + continue; + } +#endif + + if (!extDict || (matchIndex+matchLength >= dictLimit)) { + assert(matchIndex+matchLength >= dictLimit); /* might be wrong if actually extDict */ + match = base + matchIndex; + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iend); + } else { + match = dictBase + matchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iend, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) + match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ + } + + if (matchLength > bestLength) { + bestLength = matchLength; + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; + } + + if (ip+matchLength == iend) { /* equal : no way to know if inf or sup */ + break; /* drop , to guarantee consistency ; miss a bit of compression, but other solutions can corrupt tree */ + } + + if (match[matchLength] < ip[matchLength]) { /* necessarily within buffer */ + /* match is smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + smallerPtr = nextPtr+1; /* new "candidate" => larger than match, which was smaller than target */ + matchIndex = nextPtr[1]; /* new matchIndex, larger than previous and closer to current */ + } else { + /* match is larger than current */ + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop searching */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; + { U32 positions = 0; + if (bestLength > 384) positions = MIN(192, (U32)(bestLength - 384)); /* speed optimization */ + assert(matchEndIdx > curr + 8); + return MAX(positions, matchEndIdx - (curr + 8)); + } +} + +FORCE_INLINE_TEMPLATE +void ZSTD_updateTree_internal( + ZSTD_matchState_t* ms, + const BYTE* const ip, const BYTE* const iend, + const U32 mls, const ZSTD_dictMode_e dictMode) +{ + const BYTE* const base = ms->window.base; + U32 const target = (U32)(ip - base); + U32 idx = ms->nextToUpdate; + DEBUGLOG(6, "ZSTD_updateTree_internal, from %u to %u (dictMode:%u)", + idx, target, dictMode); + + while(idx < target) { + U32 const forward = ZSTD_insertBt1(ms, base+idx, iend, mls, dictMode == ZSTD_extDict); + assert(idx < (U32)(idx + forward)); + idx += forward; + } + assert((size_t)(ip - base) <= (size_t)(U32)(-1)); + assert((size_t)(iend - base) <= (size_t)(U32)(-1)); + ms->nextToUpdate = target; +} + +void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend) { + ZSTD_updateTree_internal(ms, ip, iend, ms->cParams.minMatch, ZSTD_noDict); +} + +FORCE_INLINE_TEMPLATE +U32 ZSTD_insertBtAndGetAllMatches ( + ZSTD_match_t* matches, /* store result (found matches) in this table (presumed large enough) */ + ZSTD_matchState_t* ms, + U32* nextToUpdate3, + const BYTE* const ip, const BYTE* const iLimit, const ZSTD_dictMode_e dictMode, + const U32 rep[ZSTD_REP_NUM], + U32 const ll0, /* tells if associated literal length is 0 or not. This value must be 0 or 1 */ + const U32 lengthToBeat, + U32 const mls /* template */) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1); + const BYTE* const base = ms->window.base; + U32 const curr = (U32)(ip-base); + U32 const hashLog = cParams->hashLog; + U32 const minMatch = (mls==3) ? 3 : 4; + U32* const hashTable = ms->hashTable; + size_t const h = ZSTD_hashPtr(ip, hashLog, mls); + U32 matchIndex = hashTable[h]; + U32* const bt = ms->chainTable; + U32 const btLog = cParams->chainLog - 1; + U32 const btMask= (1U << btLog) - 1; + size_t commonLengthSmaller=0, commonLengthLarger=0; + const BYTE* const dictBase = ms->window.dictBase; + U32 const dictLimit = ms->window.dictLimit; + const BYTE* const dictEnd = dictBase + dictLimit; + const BYTE* const prefixStart = base + dictLimit; + U32 const btLow = (btMask >= curr) ? 0 : curr - btMask; + U32 const windowLow = ZSTD_getLowestMatchIndex(ms, curr, cParams->windowLog); + U32 const matchLow = windowLow ? windowLow : 1; + U32* smallerPtr = bt + 2*(curr&btMask); + U32* largerPtr = bt + 2*(curr&btMask) + 1; + U32 matchEndIdx = curr+8+1; /* farthest referenced position of any match => detects repetitive patterns */ + U32 dummy32; /* to be nullified at the end */ + U32 mnum = 0; + U32 nbCompares = 1U << cParams->searchLog; + + const ZSTD_matchState_t* dms = dictMode == ZSTD_dictMatchState ? ms->dictMatchState : NULL; + const ZSTD_compressionParameters* const dmsCParams = + dictMode == ZSTD_dictMatchState ? &dms->cParams : NULL; + const BYTE* const dmsBase = dictMode == ZSTD_dictMatchState ? dms->window.base : NULL; + const BYTE* const dmsEnd = dictMode == ZSTD_dictMatchState ? dms->window.nextSrc : NULL; + U32 const dmsHighLimit = dictMode == ZSTD_dictMatchState ? (U32)(dmsEnd - dmsBase) : 0; + U32 const dmsLowLimit = dictMode == ZSTD_dictMatchState ? dms->window.lowLimit : 0; + U32 const dmsIndexDelta = dictMode == ZSTD_dictMatchState ? windowLow - dmsHighLimit : 0; + U32 const dmsHashLog = dictMode == ZSTD_dictMatchState ? dmsCParams->hashLog : hashLog; + U32 const dmsBtLog = dictMode == ZSTD_dictMatchState ? dmsCParams->chainLog - 1 : btLog; + U32 const dmsBtMask = dictMode == ZSTD_dictMatchState ? (1U << dmsBtLog) - 1 : 0; + U32 const dmsBtLow = dictMode == ZSTD_dictMatchState && dmsBtMask < dmsHighLimit - dmsLowLimit ? dmsHighLimit - dmsBtMask : dmsLowLimit; + + size_t bestLength = lengthToBeat-1; + DEBUGLOG(8, "ZSTD_insertBtAndGetAllMatches: current=%u", curr); + + /* check repCode */ + assert(ll0 <= 1); /* necessarily 1 or 0 */ + { U32 const lastR = ZSTD_REP_NUM + ll0; + U32 repCode; + for (repCode = ll0; repCode < lastR; repCode++) { + U32 const repOffset = (repCode==ZSTD_REP_NUM) ? (rep[0] - 1) : rep[repCode]; + U32 const repIndex = curr - repOffset; + U32 repLen = 0; + assert(curr >= dictLimit); + if (repOffset-1 /* intentional overflow, discards 0 and -1 */ < curr-dictLimit) { /* equivalent to `curr > repIndex >= dictLimit` */ + /* We must validate the repcode offset because when we're using a dictionary the + * valid offset range shrinks when the dictionary goes out of bounds. + */ + if ((repIndex >= windowLow) & (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repOffset, minMatch))) { + repLen = (U32)ZSTD_count(ip+minMatch, ip+minMatch-repOffset, iLimit) + minMatch; + } + } else { /* repIndex < dictLimit || repIndex >= curr */ + const BYTE* const repMatch = dictMode == ZSTD_dictMatchState ? + dmsBase + repIndex - dmsIndexDelta : + dictBase + repIndex; + assert(curr >= windowLow); + if ( dictMode == ZSTD_extDict + && ( ((repOffset-1) /*intentional overflow*/ < curr - windowLow) /* equivalent to `curr > repIndex >= windowLow` */ + & (((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */) + && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) { + repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dictEnd, prefixStart) + minMatch; + } + if (dictMode == ZSTD_dictMatchState + && ( ((repOffset-1) /*intentional overflow*/ < curr - (dmsLowLimit + dmsIndexDelta)) /* equivalent to `curr > repIndex >= dmsLowLimit` */ + & ((U32)((dictLimit-1) - repIndex) >= 3) ) /* intentional overflow : do not test positions overlapping 2 memory segments */ + && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch)) ) { + repLen = (U32)ZSTD_count_2segments(ip+minMatch, repMatch+minMatch, iLimit, dmsEnd, prefixStart) + minMatch; + } } + /* save longer solution */ + if (repLen > bestLength) { + DEBUGLOG(8, "found repCode %u (ll0:%u, offset:%u) of length %u", + repCode, ll0, repOffset, repLen); + bestLength = repLen; + matches[mnum].off = repCode - ll0; + matches[mnum].len = (U32)repLen; + mnum++; + if ( (repLen > sufficient_len) + | (ip+repLen == iLimit) ) { /* best possible */ + return mnum; + } } } } + + /* HC3 match finder */ + if ((mls == 3) /*static*/ && (bestLength < mls)) { + U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, nextToUpdate3, ip); + if ((matchIndex3 >= matchLow) + & (curr - matchIndex3 < (1<<18)) /*heuristic : longer distance likely too expensive*/ ) { + size_t mlen; + if ((dictMode == ZSTD_noDict) /*static*/ || (dictMode == ZSTD_dictMatchState) /*static*/ || (matchIndex3 >= dictLimit)) { + const BYTE* const match = base + matchIndex3; + mlen = ZSTD_count(ip, match, iLimit); + } else { + const BYTE* const match = dictBase + matchIndex3; + mlen = ZSTD_count_2segments(ip, match, iLimit, dictEnd, prefixStart); + } + + /* save best solution */ + if (mlen >= mls /* == 3 > bestLength */) { + DEBUGLOG(8, "found small match with hlog3, of length %u", + (U32)mlen); + bestLength = mlen; + assert(curr > matchIndex3); + assert(mnum==0); /* no prior solution */ + matches[0].off = (curr - matchIndex3) + ZSTD_REP_MOVE; + matches[0].len = (U32)mlen; + mnum = 1; + if ( (mlen > sufficient_len) | + (ip+mlen == iLimit) ) { /* best possible length */ + ms->nextToUpdate = curr+1; /* skip insertion */ + return 1; + } } } + /* no dictMatchState lookup: dicts don't have a populated HC3 table */ + } + + hashTable[h] = curr; /* Update Hash Table */ + + for (; nbCompares && (matchIndex >= matchLow); --nbCompares) { + U32* const nextPtr = bt + 2*(matchIndex & btMask); + const BYTE* match; + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + assert(curr > matchIndex); + + if ((dictMode == ZSTD_noDict) || (dictMode == ZSTD_dictMatchState) || (matchIndex+matchLength >= dictLimit)) { + assert(matchIndex+matchLength >= dictLimit); /* ensure the condition is correct when !extDict */ + match = base + matchIndex; + if (matchIndex >= dictLimit) assert(memcmp(match, ip, matchLength) == 0); /* ensure early section of match is equal as expected */ + matchLength += ZSTD_count(ip+matchLength, match+matchLength, iLimit); + } else { + match = dictBase + matchIndex; + assert(memcmp(match, ip, matchLength) == 0); /* ensure early section of match is equal as expected */ + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dictEnd, prefixStart); + if (matchIndex+matchLength >= dictLimit) + match = base + matchIndex; /* prepare for match[matchLength] read */ + } + + if (matchLength > bestLength) { + DEBUGLOG(8, "found match of length %u at distance %u (offCode=%u)", + (U32)matchLength, curr - matchIndex, curr - matchIndex + ZSTD_REP_MOVE); + assert(matchEndIdx > matchIndex); + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; + bestLength = matchLength; + matches[mnum].off = (curr - matchIndex) + ZSTD_REP_MOVE; + matches[mnum].len = (U32)matchLength; + mnum++; + if ( (matchLength > ZSTD_OPT_NUM) + | (ip+matchLength == iLimit) /* equal : no way to know if inf or sup */) { + if (dictMode == ZSTD_dictMatchState) nbCompares = 0; /* break should also skip searching dms */ + break; /* drop, to preserve bt consistency (miss a little bit of compression) */ + } + } + + if (match[matchLength] < ip[matchLength]) { + /* match smaller than current */ + *smallerPtr = matchIndex; /* update smaller idx */ + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + if (matchIndex <= btLow) { smallerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + smallerPtr = nextPtr+1; /* new candidate => larger than match, which was smaller than current */ + matchIndex = nextPtr[1]; /* new matchIndex, larger than previous, closer to current */ + } else { + *largerPtr = matchIndex; + commonLengthLarger = matchLength; + if (matchIndex <= btLow) { largerPtr=&dummy32; break; } /* beyond tree size, stop the search */ + largerPtr = nextPtr; + matchIndex = nextPtr[0]; + } } + + *smallerPtr = *largerPtr = 0; + + assert(nbCompares <= (1U << ZSTD_SEARCHLOG_MAX)); /* Check we haven't underflowed. */ + if (dictMode == ZSTD_dictMatchState && nbCompares) { + size_t const dmsH = ZSTD_hashPtr(ip, dmsHashLog, mls); + U32 dictMatchIndex = dms->hashTable[dmsH]; + const U32* const dmsBt = dms->chainTable; + commonLengthSmaller = commonLengthLarger = 0; + for (; nbCompares && (dictMatchIndex > dmsLowLimit); --nbCompares) { + const U32* const nextPtr = dmsBt + 2*(dictMatchIndex & dmsBtMask); + size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ + const BYTE* match = dmsBase + dictMatchIndex; + matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dmsEnd, prefixStart); + if (dictMatchIndex+matchLength >= dmsHighLimit) + match = base + dictMatchIndex + dmsIndexDelta; /* to prepare for next usage of match[matchLength] */ + + if (matchLength > bestLength) { + matchIndex = dictMatchIndex + dmsIndexDelta; + DEBUGLOG(8, "found dms match of length %u at distance %u (offCode=%u)", + (U32)matchLength, curr - matchIndex, curr - matchIndex + ZSTD_REP_MOVE); + if (matchLength > matchEndIdx - matchIndex) + matchEndIdx = matchIndex + (U32)matchLength; + bestLength = matchLength; + matches[mnum].off = (curr - matchIndex) + ZSTD_REP_MOVE; + matches[mnum].len = (U32)matchLength; + mnum++; + if ( (matchLength > ZSTD_OPT_NUM) + | (ip+matchLength == iLimit) /* equal : no way to know if inf or sup */) { + break; /* drop, to guarantee consistency (miss a little bit of compression) */ + } + } + + if (dictMatchIndex <= dmsBtLow) { break; } /* beyond tree size, stop the search */ + if (match[matchLength] < ip[matchLength]) { + commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ + dictMatchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to current) */ + } else { + /* match is larger than current */ + commonLengthLarger = matchLength; + dictMatchIndex = nextPtr[0]; + } + } + } + + assert(matchEndIdx > curr+8); + ms->nextToUpdate = matchEndIdx - 8; /* skip repetitive patterns */ + return mnum; +} + + +FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches ( + ZSTD_match_t* matches, /* store result (match found, increasing size) in this table */ + ZSTD_matchState_t* ms, + U32* nextToUpdate3, + const BYTE* ip, const BYTE* const iHighLimit, const ZSTD_dictMode_e dictMode, + const U32 rep[ZSTD_REP_NUM], + U32 const ll0, + U32 const lengthToBeat) +{ + const ZSTD_compressionParameters* const cParams = &ms->cParams; + U32 const matchLengthSearch = cParams->minMatch; + DEBUGLOG(8, "ZSTD_BtGetAllMatches"); + if (ip < ms->window.base + ms->nextToUpdate) return 0; /* skipped area */ + ZSTD_updateTree_internal(ms, ip, iHighLimit, matchLengthSearch, dictMode); + switch(matchLengthSearch) + { + case 3 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 3); + default : + case 4 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 4); + case 5 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 5); + case 7 : + case 6 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 6); + } +} + +/* *********************** +* LDM helper functions * +*************************/ + +/* Struct containing info needed to make decision about ldm inclusion */ +typedef struct { + rawSeqStore_t seqStore; /* External match candidates store for this block */ + U32 startPosInBlock; /* Start position of the current match candidate */ + U32 endPosInBlock; /* End position of the current match candidate */ + U32 offset; /* Offset of the match candidate */ +} ZSTD_optLdm_t; + +/* ZSTD_optLdm_skipRawSeqStoreBytes(): + * Moves forward in rawSeqStore by nbBytes, which will update the fields 'pos' and 'posInSequence'. + */ +static void ZSTD_optLdm_skipRawSeqStoreBytes(rawSeqStore_t* rawSeqStore, size_t nbBytes) { + U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes); + while (currPos && rawSeqStore->pos < rawSeqStore->size) { + rawSeq currSeq = rawSeqStore->seq[rawSeqStore->pos]; + if (currPos >= currSeq.litLength + currSeq.matchLength) { + currPos -= currSeq.litLength + currSeq.matchLength; + rawSeqStore->pos++; + } else { + rawSeqStore->posInSequence = currPos; + break; + } + } + if (currPos == 0 || rawSeqStore->pos == rawSeqStore->size) { + rawSeqStore->posInSequence = 0; + } +} + +/* ZSTD_opt_getNextMatchAndUpdateSeqStore(): + * Calculates the beginning and end of the next match in the current block. + * Updates 'pos' and 'posInSequence' of the ldmSeqStore. + */ +static void ZSTD_opt_getNextMatchAndUpdateSeqStore(ZSTD_optLdm_t* optLdm, U32 currPosInBlock, + U32 blockBytesRemaining) { + rawSeq currSeq; + U32 currBlockEndPos; + U32 literalsBytesRemaining; + U32 matchBytesRemaining; + + /* Setting match end position to MAX to ensure we never use an LDM during this block */ + if (optLdm->seqStore.size == 0 || optLdm->seqStore.pos >= optLdm->seqStore.size) { + optLdm->startPosInBlock = UINT_MAX; + optLdm->endPosInBlock = UINT_MAX; + return; + } + /* Calculate appropriate bytes left in matchLength and litLength after adjusting + based on ldmSeqStore->posInSequence */ + currSeq = optLdm->seqStore.seq[optLdm->seqStore.pos]; + assert(optLdm->seqStore.posInSequence <= currSeq.litLength + currSeq.matchLength); + currBlockEndPos = currPosInBlock + blockBytesRemaining; + literalsBytesRemaining = (optLdm->seqStore.posInSequence < currSeq.litLength) ? + currSeq.litLength - (U32)optLdm->seqStore.posInSequence : + 0; + matchBytesRemaining = (literalsBytesRemaining == 0) ? + currSeq.matchLength - ((U32)optLdm->seqStore.posInSequence - currSeq.litLength) : + currSeq.matchLength; + + /* If there are more literal bytes than bytes remaining in block, no ldm is possible */ + if (literalsBytesRemaining >= blockBytesRemaining) { + optLdm->startPosInBlock = UINT_MAX; + optLdm->endPosInBlock = UINT_MAX; + ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, blockBytesRemaining); + return; + } + + /* Matches may be < MINMATCH by this process. In that case, we will reject them + when we are deciding whether or not to add the ldm */ + optLdm->startPosInBlock = currPosInBlock + literalsBytesRemaining; + optLdm->endPosInBlock = optLdm->startPosInBlock + matchBytesRemaining; + optLdm->offset = currSeq.offset; + + if (optLdm->endPosInBlock > currBlockEndPos) { + /* Match ends after the block ends, we can't use the whole match */ + optLdm->endPosInBlock = currBlockEndPos; + ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, currBlockEndPos - currPosInBlock); + } else { + /* Consume nb of bytes equal to size of sequence left */ + ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, literalsBytesRemaining + matchBytesRemaining); + } +} + +/* ZSTD_optLdm_maybeAddMatch(): + * Adds a match if it's long enough, based on it's 'matchStartPosInBlock' + * and 'matchEndPosInBlock', into 'matches'. Maintains the correct ordering of 'matches' + */ +static void ZSTD_optLdm_maybeAddMatch(ZSTD_match_t* matches, U32* nbMatches, + ZSTD_optLdm_t* optLdm, U32 currPosInBlock) { + U32 posDiff = currPosInBlock - optLdm->startPosInBlock; + /* Note: ZSTD_match_t actually contains offCode and matchLength (before subtracting MINMATCH) */ + U32 candidateMatchLength = optLdm->endPosInBlock - optLdm->startPosInBlock - posDiff; + U32 candidateOffCode = optLdm->offset + ZSTD_REP_MOVE; + + /* Ensure that current block position is not outside of the match */ + if (currPosInBlock < optLdm->startPosInBlock + || currPosInBlock >= optLdm->endPosInBlock + || candidateMatchLength < MINMATCH) { + return; + } + + if (*nbMatches == 0 || ((candidateMatchLength > matches[*nbMatches-1].len) && *nbMatches < ZSTD_OPT_NUM)) { + DEBUGLOG(6, "ZSTD_optLdm_maybeAddMatch(): Adding ldm candidate match (offCode: %u matchLength %u) at block position=%u", + candidateOffCode, candidateMatchLength, currPosInBlock); + matches[*nbMatches].len = candidateMatchLength; + matches[*nbMatches].off = candidateOffCode; + (*nbMatches)++; + } +} + +/* ZSTD_optLdm_processMatchCandidate(): + * Wrapper function to update ldm seq store and call ldm functions as necessary. + */ +static void ZSTD_optLdm_processMatchCandidate(ZSTD_optLdm_t* optLdm, ZSTD_match_t* matches, U32* nbMatches, + U32 currPosInBlock, U32 remainingBytes) { + if (optLdm->seqStore.size == 0 || optLdm->seqStore.pos >= optLdm->seqStore.size) { + return; + } + + if (currPosInBlock >= optLdm->endPosInBlock) { + if (currPosInBlock > optLdm->endPosInBlock) { + /* The position at which ZSTD_optLdm_processMatchCandidate() is called is not necessarily + * at the end of a match from the ldm seq store, and will often be some bytes + * over beyond matchEndPosInBlock. As such, we need to correct for these "overshoots" + */ + U32 posOvershoot = currPosInBlock - optLdm->endPosInBlock; + ZSTD_optLdm_skipRawSeqStoreBytes(&optLdm->seqStore, posOvershoot); + } + ZSTD_opt_getNextMatchAndUpdateSeqStore(optLdm, currPosInBlock, remainingBytes); + } + ZSTD_optLdm_maybeAddMatch(matches, nbMatches, optLdm, currPosInBlock); +} + +/*-******************************* +* Optimal parser +*********************************/ + + +static U32 ZSTD_totalLen(ZSTD_optimal_t sol) +{ + return sol.litlen + sol.mlen; +} + +#if 0 /* debug */ + +static void +listStats(const U32* table, int lastEltID) +{ + int const nbElts = lastEltID + 1; + int enb; + for (enb=0; enb < nbElts; enb++) { + (void)table; + /* RAWLOG(2, "%3i:%3i, ", enb, table[enb]); */ + RAWLOG(2, "%4i,", table[enb]); + } + RAWLOG(2, " \n"); +} + +#endif + +FORCE_INLINE_TEMPLATE size_t +ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms, + seqStore_t* seqStore, + U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize, + const int optLevel, + const ZSTD_dictMode_e dictMode) +{ + optState_t* const optStatePtr = &ms->opt; + const BYTE* const istart = (const BYTE*)src; + const BYTE* ip = istart; + const BYTE* anchor = istart; + const BYTE* const iend = istart + srcSize; + const BYTE* const ilimit = iend - 8; + const BYTE* const base = ms->window.base; + const BYTE* const prefixStart = base + ms->window.dictLimit; + const ZSTD_compressionParameters* const cParams = &ms->cParams; + + U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1); + U32 const minMatch = (cParams->minMatch == 3) ? 3 : 4; + U32 nextToUpdate3 = ms->nextToUpdate; + + ZSTD_optimal_t* const opt = optStatePtr->priceTable; + ZSTD_match_t* const matches = optStatePtr->matchTable; + ZSTD_optimal_t lastSequence; + ZSTD_optLdm_t optLdm; + + optLdm.seqStore = ms->ldmSeqStore ? *ms->ldmSeqStore : kNullRawSeqStore; + optLdm.endPosInBlock = optLdm.startPosInBlock = optLdm.offset = 0; + ZSTD_opt_getNextMatchAndUpdateSeqStore(&optLdm, (U32)(ip-istart), (U32)(iend-ip)); + + /* init */ + DEBUGLOG(5, "ZSTD_compressBlock_opt_generic: current=%u, prefix=%u, nextToUpdate=%u", + (U32)(ip - base), ms->window.dictLimit, ms->nextToUpdate); + assert(optLevel <= 2); + ZSTD_rescaleFreqs(optStatePtr, (const BYTE*)src, srcSize, optLevel); + ip += (ip==prefixStart); + + /* Match Loop */ + while (ip < ilimit) { + U32 cur, last_pos = 0; + + /* find first match */ + { U32 const litlen = (U32)(ip - anchor); + U32 const ll0 = !litlen; + U32 nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, ip, iend, dictMode, rep, ll0, minMatch); + ZSTD_optLdm_processMatchCandidate(&optLdm, matches, &nbMatches, + (U32)(ip-istart), (U32)(iend - ip)); + if (!nbMatches) { ip++; continue; } + + /* initialize opt[0] */ + { U32 i ; for (i=0; i immediate encoding */ + { U32 const maxML = matches[nbMatches-1].len; + U32 const maxOffset = matches[nbMatches-1].off; + DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series", + nbMatches, maxML, maxOffset, (U32)(ip-prefixStart)); + + if (maxML > sufficient_len) { + lastSequence.litlen = litlen; + lastSequence.mlen = maxML; + lastSequence.off = maxOffset; + DEBUGLOG(6, "large match (%u>%u), immediate encoding", + maxML, sufficient_len); + cur = 0; + last_pos = ZSTD_totalLen(lastSequence); + goto _shortestPath; + } } + + /* set prices for first matches starting position == 0 */ + { U32 const literalsPrice = opt[0].price + ZSTD_litLengthPrice(0, optStatePtr, optLevel); + U32 pos; + U32 matchNb; + for (pos = 1; pos < minMatch; pos++) { + opt[pos].price = ZSTD_MAX_PRICE; /* mlen, litlen and price will be fixed during forward scanning */ + } + for (matchNb = 0; matchNb < nbMatches; matchNb++) { + U32 const offset = matches[matchNb].off; + U32 const end = matches[matchNb].len; + for ( ; pos <= end ; pos++ ) { + U32 const matchPrice = ZSTD_getMatchPrice(offset, pos, optStatePtr, optLevel); + U32 const sequencePrice = literalsPrice + matchPrice; + DEBUGLOG(7, "rPos:%u => set initial price : %.2f", + pos, ZSTD_fCost(sequencePrice)); + opt[pos].mlen = pos; + opt[pos].off = offset; + opt[pos].litlen = litlen; + opt[pos].price = sequencePrice; + } } + last_pos = pos-1; + } + } + + /* check further positions */ + for (cur = 1; cur <= last_pos; cur++) { + const BYTE* const inr = ip + cur; + assert(cur < ZSTD_OPT_NUM); + DEBUGLOG(7, "cPos:%zi==rPos:%u", inr-istart, cur) + + /* Fix current position with one literal if cheaper */ + { U32 const litlen = (opt[cur-1].mlen == 0) ? opt[cur-1].litlen + 1 : 1; + int const price = opt[cur-1].price + + ZSTD_rawLiteralsCost(ip+cur-1, 1, optStatePtr, optLevel) + + ZSTD_litLengthPrice(litlen, optStatePtr, optLevel) + - ZSTD_litLengthPrice(litlen-1, optStatePtr, optLevel); + assert(price < 1000000000); /* overflow check */ + if (price <= opt[cur].price) { + DEBUGLOG(7, "cPos:%zi==rPos:%u : better price (%.2f<=%.2f) using literal (ll==%u) (hist:%u,%u,%u)", + inr-istart, cur, ZSTD_fCost(price), ZSTD_fCost(opt[cur].price), litlen, + opt[cur-1].rep[0], opt[cur-1].rep[1], opt[cur-1].rep[2]); + opt[cur].mlen = 0; + opt[cur].off = 0; + opt[cur].litlen = litlen; + opt[cur].price = price; + } else { + DEBUGLOG(7, "cPos:%zi==rPos:%u : literal would cost more (%.2f>%.2f) (hist:%u,%u,%u)", + inr-istart, cur, ZSTD_fCost(price), ZSTD_fCost(opt[cur].price), + opt[cur].rep[0], opt[cur].rep[1], opt[cur].rep[2]); + } + } + + /* Set the repcodes of the current position. We must do it here + * because we rely on the repcodes of the 2nd to last sequence being + * correct to set the next chunks repcodes during the backward + * traversal. + */ + ZSTD_STATIC_ASSERT(sizeof(opt[cur].rep) == sizeof(repcodes_t)); + assert(cur >= opt[cur].mlen); + if (opt[cur].mlen != 0) { + U32 const prev = cur - opt[cur].mlen; + repcodes_t newReps = ZSTD_updateRep(opt[prev].rep, opt[cur].off, opt[cur].litlen==0); + ZSTD_memcpy(opt[cur].rep, &newReps, sizeof(repcodes_t)); + } else { + ZSTD_memcpy(opt[cur].rep, opt[cur - 1].rep, sizeof(repcodes_t)); + } + + /* last match must start at a minimum distance of 8 from oend */ + if (inr > ilimit) continue; + + if (cur == last_pos) break; + + if ( (optLevel==0) /*static_test*/ + && (opt[cur+1].price <= opt[cur].price + (BITCOST_MULTIPLIER/2)) ) { + DEBUGLOG(7, "move to next rPos:%u : price is <=", cur+1); + continue; /* skip unpromising positions; about ~+6% speed, -0.01 ratio */ + } + + { U32 const ll0 = (opt[cur].mlen != 0); + U32 const litlen = (opt[cur].mlen == 0) ? opt[cur].litlen : 0; + U32 const previousPrice = opt[cur].price; + U32 const basePrice = previousPrice + ZSTD_litLengthPrice(0, optStatePtr, optLevel); + U32 nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, inr, iend, dictMode, opt[cur].rep, ll0, minMatch); + U32 matchNb; + + ZSTD_optLdm_processMatchCandidate(&optLdm, matches, &nbMatches, + (U32)(inr-istart), (U32)(iend-inr)); + + if (!nbMatches) { + DEBUGLOG(7, "rPos:%u : no match found", cur); + continue; + } + + { U32 const maxML = matches[nbMatches-1].len; + DEBUGLOG(7, "cPos:%zi==rPos:%u, found %u matches, of maxLength=%u", + inr-istart, cur, nbMatches, maxML); + + if ( (maxML > sufficient_len) + || (cur + maxML >= ZSTD_OPT_NUM) ) { + lastSequence.mlen = maxML; + lastSequence.off = matches[nbMatches-1].off; + lastSequence.litlen = litlen; + cur -= (opt[cur].mlen==0) ? opt[cur].litlen : 0; /* last sequence is actually only literals, fix cur to last match - note : may underflow, in which case, it's first sequence, and it's okay */ + last_pos = cur + ZSTD_totalLen(lastSequence); + if (cur > ZSTD_OPT_NUM) cur = 0; /* underflow => first match */ + goto _shortestPath; + } } + + /* set prices using matches found at position == cur */ + for (matchNb = 0; matchNb < nbMatches; matchNb++) { + U32 const offset = matches[matchNb].off; + U32 const lastML = matches[matchNb].len; + U32 const startML = (matchNb>0) ? matches[matchNb-1].len+1 : minMatch; + U32 mlen; + + DEBUGLOG(7, "testing match %u => offCode=%4u, mlen=%2u, llen=%2u", + matchNb, matches[matchNb].off, lastML, litlen); + + for (mlen = lastML; mlen >= startML; mlen--) { /* scan downward */ + U32 const pos = cur + mlen; + int const price = basePrice + ZSTD_getMatchPrice(offset, mlen, optStatePtr, optLevel); + + if ((pos > last_pos) || (price < opt[pos].price)) { + DEBUGLOG(7, "rPos:%u (ml=%2u) => new better price (%.2f<%.2f)", + pos, mlen, ZSTD_fCost(price), ZSTD_fCost(opt[pos].price)); + while (last_pos < pos) { opt[last_pos+1].price = ZSTD_MAX_PRICE; last_pos++; } /* fill empty positions */ + opt[pos].mlen = mlen; + opt[pos].off = offset; + opt[pos].litlen = litlen; + opt[pos].price = price; + } else { + DEBUGLOG(7, "rPos:%u (ml=%2u) => new price is worse (%.2f>=%.2f)", + pos, mlen, ZSTD_fCost(price), ZSTD_fCost(opt[pos].price)); + if (optLevel==0) break; /* early update abort; gets ~+10% speed for about -0.01 ratio loss */ + } + } } } + } /* for (cur = 1; cur <= last_pos; cur++) */ + + lastSequence = opt[last_pos]; + cur = last_pos > ZSTD_totalLen(lastSequence) ? last_pos - ZSTD_totalLen(lastSequence) : 0; /* single sequence, and it starts before `ip` */ + assert(cur < ZSTD_OPT_NUM); /* control overflow*/ + +_shortestPath: /* cur, last_pos, best_mlen, best_off have to be set */ + assert(opt[0].mlen == 0); + + /* Set the next chunk's repcodes based on the repcodes of the beginning + * of the last match, and the last sequence. This avoids us having to + * update them while traversing the sequences. + */ + if (lastSequence.mlen != 0) { + repcodes_t reps = ZSTD_updateRep(opt[cur].rep, lastSequence.off, lastSequence.litlen==0); + ZSTD_memcpy(rep, &reps, sizeof(reps)); + } else { + ZSTD_memcpy(rep, opt[cur].rep, sizeof(repcodes_t)); + } + + { U32 const storeEnd = cur + 1; + U32 storeStart = storeEnd; + U32 seqPos = cur; + + DEBUGLOG(6, "start reverse traversal (last_pos:%u, cur:%u)", + last_pos, cur); (void)last_pos; + assert(storeEnd < ZSTD_OPT_NUM); + DEBUGLOG(6, "last sequence copied into pos=%u (llen=%u,mlen=%u,ofc=%u)", + storeEnd, lastSequence.litlen, lastSequence.mlen, lastSequence.off); + opt[storeEnd] = lastSequence; + while (seqPos > 0) { + U32 const backDist = ZSTD_totalLen(opt[seqPos]); + storeStart--; + DEBUGLOG(6, "sequence from rPos=%u copied into pos=%u (llen=%u,mlen=%u,ofc=%u)", + seqPos, storeStart, opt[seqPos].litlen, opt[seqPos].mlen, opt[seqPos].off); + opt[storeStart] = opt[seqPos]; + seqPos = (seqPos > backDist) ? seqPos - backDist : 0; + } + + /* save sequences */ + DEBUGLOG(6, "sending selected sequences into seqStore") + { U32 storePos; + for (storePos=storeStart; storePos <= storeEnd; storePos++) { + U32 const llen = opt[storePos].litlen; + U32 const mlen = opt[storePos].mlen; + U32 const offCode = opt[storePos].off; + U32 const advance = llen + mlen; + DEBUGLOG(6, "considering seq starting at %zi, llen=%u, mlen=%u", + anchor - istart, (unsigned)llen, (unsigned)mlen); + + if (mlen==0) { /* only literals => must be last "sequence", actually starting a new stream of sequences */ + assert(storePos == storeEnd); /* must be last sequence */ + ip = anchor + llen; /* last "sequence" is a bunch of literals => don't progress anchor */ + continue; /* will finish */ + } + + assert(anchor + llen <= iend); + ZSTD_updateStats(optStatePtr, llen, anchor, offCode, mlen); + ZSTD_storeSeq(seqStore, llen, anchor, iend, offCode, mlen-MINMATCH); + anchor += advance; + ip = anchor; + } } + ZSTD_setBasePrices(optStatePtr, optLevel); + } + } /* while (ip < ilimit) */ + + /* Return the last literals size */ + return (size_t)(iend - anchor); +} + + +size_t ZSTD_compressBlock_btopt( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + DEBUGLOG(5, "ZSTD_compressBlock_btopt"); + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /*optLevel*/, ZSTD_noDict); +} + + +/* used in 2-pass strategy */ +static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus) +{ + U32 s, sum=0; + assert(ZSTD_FREQ_DIV+bonus >= 0); + for (s=0; slitSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0); + optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0); + optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0); + optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0); +} + +/* ZSTD_initStats_ultra(): + * make a first compression pass, just to seed stats with more accurate starting values. + * only works on first block, with no dictionary and no ldm. + * this function cannot error, hence its contract must be respected. + */ +static void +ZSTD_initStats_ultra(ZSTD_matchState_t* ms, + seqStore_t* seqStore, + U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + U32 tmpRep[ZSTD_REP_NUM]; /* updated rep codes will sink here */ + ZSTD_memcpy(tmpRep, rep, sizeof(tmpRep)); + + DEBUGLOG(4, "ZSTD_initStats_ultra (srcSize=%zu)", srcSize); + assert(ms->opt.litLengthSum == 0); /* first block */ + assert(seqStore->sequences == seqStore->sequencesStart); /* no ldm */ + assert(ms->window.dictLimit == ms->window.lowLimit); /* no dictionary */ + assert(ms->window.dictLimit - ms->nextToUpdate <= 1); /* no prefix (note: intentional overflow, defined as 2-complement) */ + + ZSTD_compressBlock_opt_generic(ms, seqStore, tmpRep, src, srcSize, 2 /*optLevel*/, ZSTD_noDict); /* generate stats into ms->opt*/ + + /* invalidate first scan from history */ + ZSTD_resetSeqStore(seqStore); + ms->window.base -= srcSize; + ms->window.dictLimit += (U32)srcSize; + ms->window.lowLimit = ms->window.dictLimit; + ms->nextToUpdate = ms->window.dictLimit; + + /* re-inforce weight of collected statistics */ + ZSTD_upscaleStats(&ms->opt); +} + +size_t ZSTD_compressBlock_btultra( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + DEBUGLOG(5, "ZSTD_compressBlock_btultra (srcSize=%zu)", srcSize); + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_noDict); +} + +size_t ZSTD_compressBlock_btultra2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + U32 const curr = (U32)((const BYTE*)src - ms->window.base); + DEBUGLOG(5, "ZSTD_compressBlock_btultra2 (srcSize=%zu)", srcSize); + + /* 2-pass strategy: + * this strategy makes a first pass over first block to collect statistics + * and seed next round's statistics with it. + * After 1st pass, function forgets everything, and starts a new block. + * Consequently, this can only work if no data has been previously loaded in tables, + * aka, no dictionary, no prefix, no ldm preprocessing. + * The compression ratio gain is generally small (~0.5% on first block), + * the cost is 2x cpu time on first block. */ + assert(srcSize <= ZSTD_BLOCKSIZE_MAX); + if ( (ms->opt.litLengthSum==0) /* first block */ + && (seqStore->sequences == seqStore->sequencesStart) /* no ldm */ + && (ms->window.dictLimit == ms->window.lowLimit) /* no dictionary */ + && (curr == ms->window.dictLimit) /* start of frame, nothing already loaded nor skipped */ + && (srcSize > ZSTD_PREDEF_THRESHOLD) + ) { + ZSTD_initStats_ultra(ms, seqStore, rep, src, srcSize); + } + + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_noDict); +} + +size_t ZSTD_compressBlock_btopt_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /*optLevel*/, ZSTD_dictMatchState); +} + +size_t ZSTD_compressBlock_btultra_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_dictMatchState); +} + +size_t ZSTD_compressBlock_btopt_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 0 /*optLevel*/, ZSTD_extDict); +} + +size_t ZSTD_compressBlock_btultra_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + const void* src, size_t srcSize) +{ + return ZSTD_compressBlock_opt_generic(ms, seqStore, rep, src, srcSize, 2 /*optLevel*/, ZSTD_extDict); +} + +/* note : no btultra2 variant for extDict nor dictMatchState, + * because btultra2 is not meant to work with dictionaries + * and is only specific for the first block (no prefix) */ diff --git a/lib/zstd/compress/zstd_opt.h b/lib/zstd/compress/zstd_opt.h new file mode 100644 index 000000000000..22b862858ba7 --- /dev/null +++ b/lib/zstd/compress/zstd_opt.h @@ -0,0 +1,50 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#ifndef ZSTD_OPT_H +#define ZSTD_OPT_H + + +#include "zstd_compress_internal.h" + +/* used in ZSTD_loadDictionaryContent() */ +void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend); + +size_t ZSTD_compressBlock_btopt( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_btultra( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_btultra2( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + + +size_t ZSTD_compressBlock_btopt_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_btultra_dictMatchState( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + +size_t ZSTD_compressBlock_btopt_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); +size_t ZSTD_compressBlock_btultra_extDict( + ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], + void const* src, size_t srcSize); + + /* note : no btultra2 variant for extDict nor dictMatchState, + * because btultra2 is not meant to work with dictionaries + * and is only specific for the first block (no prefix) */ + + +#endif /* ZSTD_OPT_H */ diff --git a/lib/zstd/decompress.c b/lib/zstd/decompress.c deleted file mode 100644 index 02e92c2cbf4f..000000000000 --- a/lib/zstd/decompress.c +++ /dev/null @@ -1,2571 +0,0 @@ -/** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -/* *************************************************************** -* Tuning parameters -*****************************************************************/ -/*! -* MAXWINDOWSIZE_DEFAULT : -* maximum window size accepted by DStream, by default. -* Frames requiring more memory will be rejected. -*/ -#ifndef ZSTD_MAXWINDOWSIZE_DEFAULT -#define ZSTD_MAXWINDOWSIZE_DEFAULT ((1 << ZSTD_WINDOWLOG_MAX) + 1) /* defined within zstd.h */ -#endif - -/*-******************************************************* -* Dependencies -*********************************************************/ -#include "fse.h" -#include "huf.h" -#include "mem.h" /* low level memory routines */ -#include "zstd_internal.h" -#include -#include -#include /* memcpy, memmove, memset */ - -#define ZSTD_PREFETCH(ptr) __builtin_prefetch(ptr, 0, 0) - -/*-************************************* -* Macros -***************************************/ -#define ZSTD_isError ERR_isError /* for inlining */ -#define FSE_isError ERR_isError -#define HUF_isError ERR_isError - -/*_******************************************************* -* Memory operations -**********************************************************/ -static void ZSTD_copy4(void *dst, const void *src) { memcpy(dst, src, 4); } - -/*-************************************************************* -* Context management -***************************************************************/ -typedef enum { - ZSTDds_getFrameHeaderSize, - ZSTDds_decodeFrameHeader, - ZSTDds_decodeBlockHeader, - ZSTDds_decompressBlock, - ZSTDds_decompressLastBlock, - ZSTDds_checkChecksum, - ZSTDds_decodeSkippableHeader, - ZSTDds_skipFrame -} ZSTD_dStage; - -typedef struct { - FSE_DTable LLTable[FSE_DTABLE_SIZE_U32(LLFSELog)]; - FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)]; - FSE_DTable MLTable[FSE_DTABLE_SIZE_U32(MLFSELog)]; - HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)]; /* can accommodate HUF_decompress4X */ - U64 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32 / 2]; - U32 rep[ZSTD_REP_NUM]; -} ZSTD_entropyTables_t; - -struct ZSTD_DCtx_s { - const FSE_DTable *LLTptr; - const FSE_DTable *MLTptr; - const FSE_DTable *OFTptr; - const HUF_DTable *HUFptr; - ZSTD_entropyTables_t entropy; - const void *previousDstEnd; /* detect continuity */ - const void *base; /* start of curr segment */ - const void *vBase; /* virtual start of previous segment if it was just before curr one */ - const void *dictEnd; /* end of previous segment */ - size_t expected; - ZSTD_frameParams fParams; - blockType_e bType; /* used in ZSTD_decompressContinue(), to transfer blockType between header decoding and block decoding stages */ - ZSTD_dStage stage; - U32 litEntropy; - U32 fseEntropy; - struct xxh64_state xxhState; - size_t headerSize; - U32 dictID; - const BYTE *litPtr; - ZSTD_customMem customMem; - size_t litSize; - size_t rleSize; - BYTE litBuffer[ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH]; - BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; -}; /* typedef'd to ZSTD_DCtx within "zstd.h" */ - -size_t ZSTD_DCtxWorkspaceBound(void) { return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_DCtx)); } - -size_t ZSTD_decompressBegin(ZSTD_DCtx *dctx) -{ - dctx->expected = ZSTD_frameHeaderSize_prefix; - dctx->stage = ZSTDds_getFrameHeaderSize; - dctx->previousDstEnd = NULL; - dctx->base = NULL; - dctx->vBase = NULL; - dctx->dictEnd = NULL; - dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ - dctx->litEntropy = dctx->fseEntropy = 0; - dctx->dictID = 0; - ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue)); - memcpy(dctx->entropy.rep, repStartValue, sizeof(repStartValue)); /* initial repcodes */ - dctx->LLTptr = dctx->entropy.LLTable; - dctx->MLTptr = dctx->entropy.MLTable; - dctx->OFTptr = dctx->entropy.OFTable; - dctx->HUFptr = dctx->entropy.hufTable; - return 0; -} - -ZSTD_DCtx *ZSTD_createDCtx_advanced(ZSTD_customMem customMem) -{ - ZSTD_DCtx *dctx; - - if (!customMem.customAlloc || !customMem.customFree) - return NULL; - - dctx = (ZSTD_DCtx *)ZSTD_malloc(sizeof(ZSTD_DCtx), customMem); - if (!dctx) - return NULL; - memcpy(&dctx->customMem, &customMem, sizeof(customMem)); - ZSTD_decompressBegin(dctx); - return dctx; -} - -ZSTD_DCtx *ZSTD_initDCtx(void *workspace, size_t workspaceSize) -{ - ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize); - return ZSTD_createDCtx_advanced(stackMem); -} - -size_t ZSTD_freeDCtx(ZSTD_DCtx *dctx) -{ - if (dctx == NULL) - return 0; /* support free on NULL */ - ZSTD_free(dctx, dctx->customMem); - return 0; /* reserved as a potential error code in the future */ -} - -void ZSTD_copyDCtx(ZSTD_DCtx *dstDCtx, const ZSTD_DCtx *srcDCtx) -{ - size_t const workSpaceSize = (ZSTD_BLOCKSIZE_ABSOLUTEMAX + WILDCOPY_OVERLENGTH) + ZSTD_frameHeaderSize_max; - memcpy(dstDCtx, srcDCtx, sizeof(ZSTD_DCtx) - workSpaceSize); /* no need to copy workspace */ -} - -static void ZSTD_refDDict(ZSTD_DCtx *dstDCtx, const ZSTD_DDict *ddict); - -/*-************************************************************* -* Decompression section -***************************************************************/ - -/*! ZSTD_isFrame() : - * Tells if the content of `buffer` starts with a valid Frame Identifier. - * Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0. - * Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled. - * Note 3 : Skippable Frame Identifiers are considered valid. */ -unsigned ZSTD_isFrame(const void *buffer, size_t size) -{ - if (size < 4) - return 0; - { - U32 const magic = ZSTD_readLE32(buffer); - if (magic == ZSTD_MAGICNUMBER) - return 1; - if ((magic & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) - return 1; - } - return 0; -} - -/** ZSTD_frameHeaderSize() : -* srcSize must be >= ZSTD_frameHeaderSize_prefix. -* @return : size of the Frame Header */ -static size_t ZSTD_frameHeaderSize(const void *src, size_t srcSize) -{ - if (srcSize < ZSTD_frameHeaderSize_prefix) - return ERROR(srcSize_wrong); - { - BYTE const fhd = ((const BYTE *)src)[4]; - U32 const dictID = fhd & 3; - U32 const singleSegment = (fhd >> 5) & 1; - U32 const fcsId = fhd >> 6; - return ZSTD_frameHeaderSize_prefix + !singleSegment + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId] + (singleSegment && !fcsId); - } -} - -/** ZSTD_getFrameParams() : -* decode Frame Header, or require larger `srcSize`. -* @return : 0, `fparamsPtr` is correctly filled, -* >0, `srcSize` is too small, result is expected `srcSize`, -* or an error code, which can be tested using ZSTD_isError() */ -size_t ZSTD_getFrameParams(ZSTD_frameParams *fparamsPtr, const void *src, size_t srcSize) -{ - const BYTE *ip = (const BYTE *)src; - - if (srcSize < ZSTD_frameHeaderSize_prefix) - return ZSTD_frameHeaderSize_prefix; - if (ZSTD_readLE32(src) != ZSTD_MAGICNUMBER) { - if ((ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { - if (srcSize < ZSTD_skippableHeaderSize) - return ZSTD_skippableHeaderSize; /* magic number + skippable frame length */ - memset(fparamsPtr, 0, sizeof(*fparamsPtr)); - fparamsPtr->frameContentSize = ZSTD_readLE32((const char *)src + 4); - fparamsPtr->windowSize = 0; /* windowSize==0 means a frame is skippable */ - return 0; - } - return ERROR(prefix_unknown); - } - - /* ensure there is enough `srcSize` to fully read/decode frame header */ - { - size_t const fhsize = ZSTD_frameHeaderSize(src, srcSize); - if (srcSize < fhsize) - return fhsize; - } - - { - BYTE const fhdByte = ip[4]; - size_t pos = 5; - U32 const dictIDSizeCode = fhdByte & 3; - U32 const checksumFlag = (fhdByte >> 2) & 1; - U32 const singleSegment = (fhdByte >> 5) & 1; - U32 const fcsID = fhdByte >> 6; - U32 const windowSizeMax = 1U << ZSTD_WINDOWLOG_MAX; - U32 windowSize = 0; - U32 dictID = 0; - U64 frameContentSize = 0; - if ((fhdByte & 0x08) != 0) - return ERROR(frameParameter_unsupported); /* reserved bits, which must be zero */ - if (!singleSegment) { - BYTE const wlByte = ip[pos++]; - U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN; - if (windowLog > ZSTD_WINDOWLOG_MAX) - return ERROR(frameParameter_windowTooLarge); /* avoids issue with 1 << windowLog */ - windowSize = (1U << windowLog); - windowSize += (windowSize >> 3) * (wlByte & 7); - } - - switch (dictIDSizeCode) { - default: /* impossible */ - case 0: break; - case 1: - dictID = ip[pos]; - pos++; - break; - case 2: - dictID = ZSTD_readLE16(ip + pos); - pos += 2; - break; - case 3: - dictID = ZSTD_readLE32(ip + pos); - pos += 4; - break; - } - switch (fcsID) { - default: /* impossible */ - case 0: - if (singleSegment) - frameContentSize = ip[pos]; - break; - case 1: frameContentSize = ZSTD_readLE16(ip + pos) + 256; break; - case 2: frameContentSize = ZSTD_readLE32(ip + pos); break; - case 3: frameContentSize = ZSTD_readLE64(ip + pos); break; - } - if (!windowSize) - windowSize = (U32)frameContentSize; - if (windowSize > windowSizeMax) - return ERROR(frameParameter_windowTooLarge); - fparamsPtr->frameContentSize = frameContentSize; - fparamsPtr->windowSize = windowSize; - fparamsPtr->dictID = dictID; - fparamsPtr->checksumFlag = checksumFlag; - } - return 0; -} - -/** ZSTD_getFrameContentSize() : -* compatible with legacy mode -* @return : decompressed size of the single frame pointed to be `src` if known, otherwise -* - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined -* - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */ -unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize) -{ - { - ZSTD_frameParams fParams; - if (ZSTD_getFrameParams(&fParams, src, srcSize) != 0) - return ZSTD_CONTENTSIZE_ERROR; - if (fParams.windowSize == 0) { - /* Either skippable or empty frame, size == 0 either way */ - return 0; - } else if (fParams.frameContentSize != 0) { - return fParams.frameContentSize; - } else { - return ZSTD_CONTENTSIZE_UNKNOWN; - } - } -} - -/** ZSTD_findDecompressedSize() : - * compatible with legacy mode - * `srcSize` must be the exact length of some number of ZSTD compressed and/or - * skippable frames - * @return : decompressed size of the frames contained */ -unsigned long long ZSTD_findDecompressedSize(const void *src, size_t srcSize) -{ - { - unsigned long long totalDstSize = 0; - while (srcSize >= ZSTD_frameHeaderSize_prefix) { - const U32 magicNumber = ZSTD_readLE32(src); - - if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { - size_t skippableSize; - if (srcSize < ZSTD_skippableHeaderSize) - return ERROR(srcSize_wrong); - skippableSize = ZSTD_readLE32((const BYTE *)src + 4) + ZSTD_skippableHeaderSize; - if (srcSize < skippableSize) { - return ZSTD_CONTENTSIZE_ERROR; - } - - src = (const BYTE *)src + skippableSize; - srcSize -= skippableSize; - continue; - } - - { - unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); - if (ret >= ZSTD_CONTENTSIZE_ERROR) - return ret; - - /* check for overflow */ - if (totalDstSize + ret < totalDstSize) - return ZSTD_CONTENTSIZE_ERROR; - totalDstSize += ret; - } - { - size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize); - if (ZSTD_isError(frameSrcSize)) { - return ZSTD_CONTENTSIZE_ERROR; - } - - src = (const BYTE *)src + frameSrcSize; - srcSize -= frameSrcSize; - } - } - - if (srcSize) { - return ZSTD_CONTENTSIZE_ERROR; - } - - return totalDstSize; - } -} - -/** ZSTD_decodeFrameHeader() : -* `headerSize` must be the size provided by ZSTD_frameHeaderSize(). -* @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */ -static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx *dctx, const void *src, size_t headerSize) -{ - size_t const result = ZSTD_getFrameParams(&(dctx->fParams), src, headerSize); - if (ZSTD_isError(result)) - return result; /* invalid header */ - if (result > 0) - return ERROR(srcSize_wrong); /* headerSize too small */ - if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID)) - return ERROR(dictionary_wrong); - if (dctx->fParams.checksumFlag) - xxh64_reset(&dctx->xxhState, 0); - return 0; -} - -typedef struct { - blockType_e blockType; - U32 lastBlock; - U32 origSize; -} blockProperties_t; - -/*! ZSTD_getcBlockSize() : -* Provides the size of compressed block from block header `src` */ -size_t ZSTD_getcBlockSize(const void *src, size_t srcSize, blockProperties_t *bpPtr) -{ - if (srcSize < ZSTD_blockHeaderSize) - return ERROR(srcSize_wrong); - { - U32 const cBlockHeader = ZSTD_readLE24(src); - U32 const cSize = cBlockHeader >> 3; - bpPtr->lastBlock = cBlockHeader & 1; - bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3); - bpPtr->origSize = cSize; /* only useful for RLE */ - if (bpPtr->blockType == bt_rle) - return 1; - if (bpPtr->blockType == bt_reserved) - return ERROR(corruption_detected); - return cSize; - } -} - -static size_t ZSTD_copyRawBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - if (srcSize > dstCapacity) - return ERROR(dstSize_tooSmall); - memcpy(dst, src, srcSize); - return srcSize; -} - -static size_t ZSTD_setRleBlock(void *dst, size_t dstCapacity, const void *src, size_t srcSize, size_t regenSize) -{ - if (srcSize != 1) - return ERROR(srcSize_wrong); - if (regenSize > dstCapacity) - return ERROR(dstSize_tooSmall); - memset(dst, *(const BYTE *)src, regenSize); - return regenSize; -} - -/*! ZSTD_decodeLiteralsBlock() : - @return : nb of bytes read from src (< srcSize ) */ -size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx *dctx, const void *src, size_t srcSize) /* note : srcSize < BLOCKSIZE */ -{ - if (srcSize < MIN_CBLOCK_SIZE) - return ERROR(corruption_detected); - - { - const BYTE *const istart = (const BYTE *)src; - symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3); - - switch (litEncType) { - case set_repeat: - if (dctx->litEntropy == 0) - return ERROR(dictionary_corrupted); - fallthrough; - case set_compressed: - if (srcSize < 5) - return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */ - { - size_t lhSize, litSize, litCSize; - U32 singleStream = 0; - U32 const lhlCode = (istart[0] >> 2) & 3; - U32 const lhc = ZSTD_readLE32(istart); - switch (lhlCode) { - case 0: - case 1: - default: /* note : default is impossible, since lhlCode into [0..3] */ - /* 2 - 2 - 10 - 10 */ - singleStream = !lhlCode; - lhSize = 3; - litSize = (lhc >> 4) & 0x3FF; - litCSize = (lhc >> 14) & 0x3FF; - break; - case 2: - /* 2 - 2 - 14 - 14 */ - lhSize = 4; - litSize = (lhc >> 4) & 0x3FFF; - litCSize = lhc >> 18; - break; - case 3: - /* 2 - 2 - 18 - 18 */ - lhSize = 5; - litSize = (lhc >> 4) & 0x3FFFF; - litCSize = (lhc >> 22) + (istart[4] << 10); - break; - } - if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) - return ERROR(corruption_detected); - if (litCSize + lhSize > srcSize) - return ERROR(corruption_detected); - - if (HUF_isError( - (litEncType == set_repeat) - ? (singleStream ? HUF_decompress1X_usingDTable(dctx->litBuffer, litSize, istart + lhSize, litCSize, dctx->HUFptr) - : HUF_decompress4X_usingDTable(dctx->litBuffer, litSize, istart + lhSize, litCSize, dctx->HUFptr)) - : (singleStream - ? HUF_decompress1X2_DCtx_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart + lhSize, litCSize, - dctx->entropy.workspace, sizeof(dctx->entropy.workspace)) - : HUF_decompress4X_hufOnly_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart + lhSize, litCSize, - dctx->entropy.workspace, sizeof(dctx->entropy.workspace))))) - return ERROR(corruption_detected); - - dctx->litPtr = dctx->litBuffer; - dctx->litSize = litSize; - dctx->litEntropy = 1; - if (litEncType == set_compressed) - dctx->HUFptr = dctx->entropy.hufTable; - memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH); - return litCSize + lhSize; - } - - case set_basic: { - size_t litSize, lhSize; - U32 const lhlCode = ((istart[0]) >> 2) & 3; - switch (lhlCode) { - case 0: - case 2: - default: /* note : default is impossible, since lhlCode into [0..3] */ - lhSize = 1; - litSize = istart[0] >> 3; - break; - case 1: - lhSize = 2; - litSize = ZSTD_readLE16(istart) >> 4; - break; - case 3: - lhSize = 3; - litSize = ZSTD_readLE24(istart) >> 4; - break; - } - - if (lhSize + litSize + WILDCOPY_OVERLENGTH > srcSize) { /* risk reading beyond src buffer with wildcopy */ - if (litSize + lhSize > srcSize) - return ERROR(corruption_detected); - memcpy(dctx->litBuffer, istart + lhSize, litSize); - dctx->litPtr = dctx->litBuffer; - dctx->litSize = litSize; - memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH); - return lhSize + litSize; - } - /* direct reference into compressed stream */ - dctx->litPtr = istart + lhSize; - dctx->litSize = litSize; - return lhSize + litSize; - } - - case set_rle: { - U32 const lhlCode = ((istart[0]) >> 2) & 3; - size_t litSize, lhSize; - switch (lhlCode) { - case 0: - case 2: - default: /* note : default is impossible, since lhlCode into [0..3] */ - lhSize = 1; - litSize = istart[0] >> 3; - break; - case 1: - lhSize = 2; - litSize = ZSTD_readLE16(istart) >> 4; - break; - case 3: - lhSize = 3; - litSize = ZSTD_readLE24(istart) >> 4; - if (srcSize < 4) - return ERROR(corruption_detected); /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */ - break; - } - if (litSize > ZSTD_BLOCKSIZE_ABSOLUTEMAX) - return ERROR(corruption_detected); - memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH); - dctx->litPtr = dctx->litBuffer; - dctx->litSize = litSize; - return lhSize + 1; - } - default: - return ERROR(corruption_detected); /* impossible */ - } - } -} - -typedef union { - FSE_decode_t realData; - U32 alignedBy4; -} FSE_decode_t4; - -static const FSE_decode_t4 LL_defaultDTable[(1 << LL_DEFAULTNORMLOG) + 1] = { - {{LL_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */ - {{0, 0, 4}}, /* 0 : base, symbol, bits */ - {{16, 0, 4}}, - {{32, 1, 5}}, - {{0, 3, 5}}, - {{0, 4, 5}}, - {{0, 6, 5}}, - {{0, 7, 5}}, - {{0, 9, 5}}, - {{0, 10, 5}}, - {{0, 12, 5}}, - {{0, 14, 6}}, - {{0, 16, 5}}, - {{0, 18, 5}}, - {{0, 19, 5}}, - {{0, 21, 5}}, - {{0, 22, 5}}, - {{0, 24, 5}}, - {{32, 25, 5}}, - {{0, 26, 5}}, - {{0, 27, 6}}, - {{0, 29, 6}}, - {{0, 31, 6}}, - {{32, 0, 4}}, - {{0, 1, 4}}, - {{0, 2, 5}}, - {{32, 4, 5}}, - {{0, 5, 5}}, - {{32, 7, 5}}, - {{0, 8, 5}}, - {{32, 10, 5}}, - {{0, 11, 5}}, - {{0, 13, 6}}, - {{32, 16, 5}}, - {{0, 17, 5}}, - {{32, 19, 5}}, - {{0, 20, 5}}, - {{32, 22, 5}}, - {{0, 23, 5}}, - {{0, 25, 4}}, - {{16, 25, 4}}, - {{32, 26, 5}}, - {{0, 28, 6}}, - {{0, 30, 6}}, - {{48, 0, 4}}, - {{16, 1, 4}}, - {{32, 2, 5}}, - {{32, 3, 5}}, - {{32, 5, 5}}, - {{32, 6, 5}}, - {{32, 8, 5}}, - {{32, 9, 5}}, - {{32, 11, 5}}, - {{32, 12, 5}}, - {{0, 15, 6}}, - {{32, 17, 5}}, - {{32, 18, 5}}, - {{32, 20, 5}}, - {{32, 21, 5}}, - {{32, 23, 5}}, - {{32, 24, 5}}, - {{0, 35, 6}}, - {{0, 34, 6}}, - {{0, 33, 6}}, - {{0, 32, 6}}, -}; /* LL_defaultDTable */ - -static const FSE_decode_t4 ML_defaultDTable[(1 << ML_DEFAULTNORMLOG) + 1] = { - {{ML_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */ - {{0, 0, 6}}, /* 0 : base, symbol, bits */ - {{0, 1, 4}}, - {{32, 2, 5}}, - {{0, 3, 5}}, - {{0, 5, 5}}, - {{0, 6, 5}}, - {{0, 8, 5}}, - {{0, 10, 6}}, - {{0, 13, 6}}, - {{0, 16, 6}}, - {{0, 19, 6}}, - {{0, 22, 6}}, - {{0, 25, 6}}, - {{0, 28, 6}}, - {{0, 31, 6}}, - {{0, 33, 6}}, - {{0, 35, 6}}, - {{0, 37, 6}}, - {{0, 39, 6}}, - {{0, 41, 6}}, - {{0, 43, 6}}, - {{0, 45, 6}}, - {{16, 1, 4}}, - {{0, 2, 4}}, - {{32, 3, 5}}, - {{0, 4, 5}}, - {{32, 6, 5}}, - {{0, 7, 5}}, - {{0, 9, 6}}, - {{0, 12, 6}}, - {{0, 15, 6}}, - {{0, 18, 6}}, - {{0, 21, 6}}, - {{0, 24, 6}}, - {{0, 27, 6}}, - {{0, 30, 6}}, - {{0, 32, 6}}, - {{0, 34, 6}}, - {{0, 36, 6}}, - {{0, 38, 6}}, - {{0, 40, 6}}, - {{0, 42, 6}}, - {{0, 44, 6}}, - {{32, 1, 4}}, - {{48, 1, 4}}, - {{16, 2, 4}}, - {{32, 4, 5}}, - {{32, 5, 5}}, - {{32, 7, 5}}, - {{32, 8, 5}}, - {{0, 11, 6}}, - {{0, 14, 6}}, - {{0, 17, 6}}, - {{0, 20, 6}}, - {{0, 23, 6}}, - {{0, 26, 6}}, - {{0, 29, 6}}, - {{0, 52, 6}}, - {{0, 51, 6}}, - {{0, 50, 6}}, - {{0, 49, 6}}, - {{0, 48, 6}}, - {{0, 47, 6}}, - {{0, 46, 6}}, -}; /* ML_defaultDTable */ - -static const FSE_decode_t4 OF_defaultDTable[(1 << OF_DEFAULTNORMLOG) + 1] = { - {{OF_DEFAULTNORMLOG, 1, 1}}, /* header : tableLog, fastMode, fastMode */ - {{0, 0, 5}}, /* 0 : base, symbol, bits */ - {{0, 6, 4}}, - {{0, 9, 5}}, - {{0, 15, 5}}, - {{0, 21, 5}}, - {{0, 3, 5}}, - {{0, 7, 4}}, - {{0, 12, 5}}, - {{0, 18, 5}}, - {{0, 23, 5}}, - {{0, 5, 5}}, - {{0, 8, 4}}, - {{0, 14, 5}}, - {{0, 20, 5}}, - {{0, 2, 5}}, - {{16, 7, 4}}, - {{0, 11, 5}}, - {{0, 17, 5}}, - {{0, 22, 5}}, - {{0, 4, 5}}, - {{16, 8, 4}}, - {{0, 13, 5}}, - {{0, 19, 5}}, - {{0, 1, 5}}, - {{16, 6, 4}}, - {{0, 10, 5}}, - {{0, 16, 5}}, - {{0, 28, 5}}, - {{0, 27, 5}}, - {{0, 26, 5}}, - {{0, 25, 5}}, - {{0, 24, 5}}, -}; /* OF_defaultDTable */ - -/*! ZSTD_buildSeqTable() : - @return : nb bytes read from src, - or an error code if it fails, testable with ZSTD_isError() -*/ -static size_t ZSTD_buildSeqTable(FSE_DTable *DTableSpace, const FSE_DTable **DTablePtr, symbolEncodingType_e type, U32 max, U32 maxLog, const void *src, - size_t srcSize, const FSE_decode_t4 *defaultTable, U32 flagRepeatTable, void *workspace, size_t workspaceSize) -{ - const void *const tmpPtr = defaultTable; /* bypass strict aliasing */ - switch (type) { - case set_rle: - if (!srcSize) - return ERROR(srcSize_wrong); - if ((*(const BYTE *)src) > max) - return ERROR(corruption_detected); - FSE_buildDTable_rle(DTableSpace, *(const BYTE *)src); - *DTablePtr = DTableSpace; - return 1; - case set_basic: *DTablePtr = (const FSE_DTable *)tmpPtr; return 0; - case set_repeat: - if (!flagRepeatTable) - return ERROR(corruption_detected); - return 0; - default: /* impossible */ - case set_compressed: { - U32 tableLog; - S16 *norm = (S16 *)workspace; - size_t const spaceUsed32 = ALIGN(sizeof(S16) * (MaxSeq + 1), sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(GENERIC); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - { - size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize); - if (FSE_isError(headerSize)) - return ERROR(corruption_detected); - if (tableLog > maxLog) - return ERROR(corruption_detected); - FSE_buildDTable_wksp(DTableSpace, norm, max, tableLog, workspace, workspaceSize); - *DTablePtr = DTableSpace; - return headerSize; - } - } - } -} - -size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx *dctx, int *nbSeqPtr, const void *src, size_t srcSize) -{ - const BYTE *const istart = (const BYTE *const)src; - const BYTE *const iend = istart + srcSize; - const BYTE *ip = istart; - - /* check */ - if (srcSize < MIN_SEQUENCES_SIZE) - return ERROR(srcSize_wrong); - - /* SeqHead */ - { - int nbSeq = *ip++; - if (!nbSeq) { - *nbSeqPtr = 0; - return 1; - } - if (nbSeq > 0x7F) { - if (nbSeq == 0xFF) { - if (ip + 2 > iend) - return ERROR(srcSize_wrong); - nbSeq = ZSTD_readLE16(ip) + LONGNBSEQ, ip += 2; - } else { - if (ip >= iend) - return ERROR(srcSize_wrong); - nbSeq = ((nbSeq - 0x80) << 8) + *ip++; - } - } - *nbSeqPtr = nbSeq; - } - - /* FSE table descriptors */ - if (ip + 4 > iend) - return ERROR(srcSize_wrong); /* minimum possible size */ - { - symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6); - symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3); - symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3); - ip++; - - /* Build DTables */ - { - size_t const llhSize = ZSTD_buildSeqTable(dctx->entropy.LLTable, &dctx->LLTptr, LLtype, MaxLL, LLFSELog, ip, iend - ip, - LL_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace)); - if (ZSTD_isError(llhSize)) - return ERROR(corruption_detected); - ip += llhSize; - } - { - size_t const ofhSize = ZSTD_buildSeqTable(dctx->entropy.OFTable, &dctx->OFTptr, OFtype, MaxOff, OffFSELog, ip, iend - ip, - OF_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace)); - if (ZSTD_isError(ofhSize)) - return ERROR(corruption_detected); - ip += ofhSize; - } - { - size_t const mlhSize = ZSTD_buildSeqTable(dctx->entropy.MLTable, &dctx->MLTptr, MLtype, MaxML, MLFSELog, ip, iend - ip, - ML_defaultDTable, dctx->fseEntropy, dctx->entropy.workspace, sizeof(dctx->entropy.workspace)); - if (ZSTD_isError(mlhSize)) - return ERROR(corruption_detected); - ip += mlhSize; - } - } - - return ip - istart; -} - -typedef struct { - size_t litLength; - size_t matchLength; - size_t offset; - const BYTE *match; -} seq_t; - -typedef struct { - BIT_DStream_t DStream; - FSE_DState_t stateLL; - FSE_DState_t stateOffb; - FSE_DState_t stateML; - size_t prevOffset[ZSTD_REP_NUM]; - const BYTE *base; - size_t pos; - uPtrDiff gotoDict; -} seqState_t; - -FORCE_NOINLINE -size_t ZSTD_execSequenceLast7(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base, - const BYTE *const vBase, const BYTE *const dictEnd) -{ - BYTE *const oLitEnd = op + sequence.litLength; - size_t const sequenceLength = sequence.litLength + sequence.matchLength; - BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */ - BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH; - const BYTE *const iLitEnd = *litPtr + sequence.litLength; - const BYTE *match = oLitEnd - sequence.offset; - - /* check */ - if (oMatchEnd > oend) - return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */ - if (iLitEnd > litLimit) - return ERROR(corruption_detected); /* over-read beyond lit buffer */ - if (oLitEnd <= oend_w) - return ERROR(GENERIC); /* Precondition */ - - /* copy literals */ - if (op < oend_w) { - ZSTD_wildcopy(op, *litPtr, oend_w - op); - *litPtr += oend_w - op; - op = oend_w; - } - while (op < oLitEnd) - *op++ = *(*litPtr)++; - - /* copy Match */ - if (sequence.offset > (size_t)(oLitEnd - base)) { - /* offset beyond prefix */ - if (sequence.offset > (size_t)(oLitEnd - vBase)) - return ERROR(corruption_detected); - match = dictEnd - (base - match); - if (match + sequence.matchLength <= dictEnd) { - memmove(oLitEnd, match, sequence.matchLength); - return sequenceLength; - } - /* span extDict & currPrefixSegment */ - { - size_t const length1 = dictEnd - match; - memmove(oLitEnd, match, length1); - op = oLitEnd + length1; - sequence.matchLength -= length1; - match = base; - } - } - while (op < oMatchEnd) - *op++ = *match++; - return sequenceLength; -} - -static seq_t ZSTD_decodeSequence(seqState_t *seqState) -{ - seq_t seq; - - U32 const llCode = FSE_peekSymbol(&seqState->stateLL); - U32 const mlCode = FSE_peekSymbol(&seqState->stateML); - U32 const ofCode = FSE_peekSymbol(&seqState->stateOffb); /* <= maxOff, by table construction */ - - U32 const llBits = LL_bits[llCode]; - U32 const mlBits = ML_bits[mlCode]; - U32 const ofBits = ofCode; - U32 const totalBits = llBits + mlBits + ofBits; - - static const U32 LL_base[MaxLL + 1] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, - 20, 22, 24, 28, 32, 40, 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, 0x10000}; - - static const U32 ML_base[MaxML + 1] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, - 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 39, 41, - 43, 47, 51, 59, 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, 0x1003, 0x2003, 0x4003, 0x8003, 0x10003}; - - static const U32 OF_base[MaxOff + 1] = {0, 1, 1, 5, 0xD, 0x1D, 0x3D, 0x7D, 0xFD, 0x1FD, - 0x3FD, 0x7FD, 0xFFD, 0x1FFD, 0x3FFD, 0x7FFD, 0xFFFD, 0x1FFFD, 0x3FFFD, 0x7FFFD, - 0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD}; - - /* sequence */ - { - size_t offset; - if (!ofCode) - offset = 0; - else { - offset = OF_base[ofCode] + BIT_readBitsFast(&seqState->DStream, ofBits); /* <= (ZSTD_WINDOWLOG_MAX-1) bits */ - if (ZSTD_32bits()) - BIT_reloadDStream(&seqState->DStream); - } - - if (ofCode <= 1) { - offset += (llCode == 0); - if (offset) { - size_t temp = (offset == 3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset]; - temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */ - if (offset != 1) - seqState->prevOffset[2] = seqState->prevOffset[1]; - seqState->prevOffset[1] = seqState->prevOffset[0]; - seqState->prevOffset[0] = offset = temp; - } else { - offset = seqState->prevOffset[0]; - } - } else { - seqState->prevOffset[2] = seqState->prevOffset[1]; - seqState->prevOffset[1] = seqState->prevOffset[0]; - seqState->prevOffset[0] = offset; - } - seq.offset = offset; - } - - seq.matchLength = ML_base[mlCode] + ((mlCode > 31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <= 16 bits */ - if (ZSTD_32bits() && (mlBits + llBits > 24)) - BIT_reloadDStream(&seqState->DStream); - - seq.litLength = LL_base[llCode] + ((llCode > 15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <= 16 bits */ - if (ZSTD_32bits() || (totalBits > 64 - 7 - (LLFSELog + MLFSELog + OffFSELog))) - BIT_reloadDStream(&seqState->DStream); - - /* ANS state update */ - FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <= 9 bits */ - FSE_updateState(&seqState->stateML, &seqState->DStream); /* <= 9 bits */ - if (ZSTD_32bits()) - BIT_reloadDStream(&seqState->DStream); /* <= 18 bits */ - FSE_updateState(&seqState->stateOffb, &seqState->DStream); /* <= 8 bits */ - - seq.match = NULL; - - return seq; -} - -FORCE_INLINE -size_t ZSTD_execSequence(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base, - const BYTE *const vBase, const BYTE *const dictEnd) -{ - BYTE *const oLitEnd = op + sequence.litLength; - size_t const sequenceLength = sequence.litLength + sequence.matchLength; - BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */ - BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH; - const BYTE *const iLitEnd = *litPtr + sequence.litLength; - const BYTE *match = oLitEnd - sequence.offset; - - /* check */ - if (oMatchEnd > oend) - return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */ - if (iLitEnd > litLimit) - return ERROR(corruption_detected); /* over-read beyond lit buffer */ - if (oLitEnd > oend_w) - return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd); - - /* copy Literals */ - ZSTD_copy8(op, *litPtr); - if (sequence.litLength > 8) - ZSTD_wildcopy(op + 8, (*litPtr) + 8, - sequence.litLength - 8); /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */ - op = oLitEnd; - *litPtr = iLitEnd; /* update for next sequence */ - - /* copy Match */ - if (sequence.offset > (size_t)(oLitEnd - base)) { - /* offset beyond prefix */ - if (sequence.offset > (size_t)(oLitEnd - vBase)) - return ERROR(corruption_detected); - match = dictEnd + (match - base); - if (match + sequence.matchLength <= dictEnd) { - memmove(oLitEnd, match, sequence.matchLength); - return sequenceLength; - } - /* span extDict & currPrefixSegment */ - { - size_t const length1 = dictEnd - match; - memmove(oLitEnd, match, length1); - op = oLitEnd + length1; - sequence.matchLength -= length1; - match = base; - if (op > oend_w || sequence.matchLength < MINMATCH) { - U32 i; - for (i = 0; i < sequence.matchLength; ++i) - op[i] = match[i]; - return sequenceLength; - } - } - } - /* Requirement: op <= oend_w && sequence.matchLength >= MINMATCH */ - - /* match within prefix */ - if (sequence.offset < 8) { - /* close range match, overlap */ - static const U32 dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */ - static const int dec64table[] = {8, 8, 8, 7, 8, 9, 10, 11}; /* subtracted */ - int const sub2 = dec64table[sequence.offset]; - op[0] = match[0]; - op[1] = match[1]; - op[2] = match[2]; - op[3] = match[3]; - match += dec32table[sequence.offset]; - ZSTD_copy4(op + 4, match); - match -= sub2; - } else { - ZSTD_copy8(op, match); - } - op += 8; - match += 8; - - if (oMatchEnd > oend - (16 - MINMATCH)) { - if (op < oend_w) { - ZSTD_wildcopy(op, match, oend_w - op); - match += oend_w - op; - op = oend_w; - } - while (op < oMatchEnd) - *op++ = *match++; - } else { - ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength - 8); /* works even if matchLength < 8 */ - } - return sequenceLength; -} - -static size_t ZSTD_decompressSequences(ZSTD_DCtx *dctx, void *dst, size_t maxDstSize, const void *seqStart, size_t seqSize) -{ - const BYTE *ip = (const BYTE *)seqStart; - const BYTE *const iend = ip + seqSize; - BYTE *const ostart = (BYTE * const)dst; - BYTE *const oend = ostart + maxDstSize; - BYTE *op = ostart; - const BYTE *litPtr = dctx->litPtr; - const BYTE *const litEnd = litPtr + dctx->litSize; - const BYTE *const base = (const BYTE *)(dctx->base); - const BYTE *const vBase = (const BYTE *)(dctx->vBase); - const BYTE *const dictEnd = (const BYTE *)(dctx->dictEnd); - int nbSeq; - - /* Build Decoding Tables */ - { - size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize); - if (ZSTD_isError(seqHSize)) - return seqHSize; - ip += seqHSize; - } - - /* Regen sequences */ - if (nbSeq) { - seqState_t seqState; - dctx->fseEntropy = 1; - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - seqState.prevOffset[i] = dctx->entropy.rep[i]; - } - CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend - ip), corruption_detected); - FSE_initDState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr); - FSE_initDState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr); - FSE_initDState(&seqState.stateML, &seqState.DStream, dctx->MLTptr); - - for (; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && nbSeq;) { - nbSeq--; - { - seq_t const sequence = ZSTD_decodeSequence(&seqState); - size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, base, vBase, dictEnd); - if (ZSTD_isError(oneSeqSize)) - return oneSeqSize; - op += oneSeqSize; - } - } - - /* check if reached exact end */ - if (nbSeq) - return ERROR(corruption_detected); - /* save reps for next block */ - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); - } - } - - /* last literal segment */ - { - size_t const lastLLSize = litEnd - litPtr; - if (lastLLSize > (size_t)(oend - op)) - return ERROR(dstSize_tooSmall); - memcpy(op, litPtr, lastLLSize); - op += lastLLSize; - } - - return op - ostart; -} - -FORCE_INLINE seq_t ZSTD_decodeSequenceLong_generic(seqState_t *seqState, int const longOffsets) -{ - seq_t seq; - - U32 const llCode = FSE_peekSymbol(&seqState->stateLL); - U32 const mlCode = FSE_peekSymbol(&seqState->stateML); - U32 const ofCode = FSE_peekSymbol(&seqState->stateOffb); /* <= maxOff, by table construction */ - - U32 const llBits = LL_bits[llCode]; - U32 const mlBits = ML_bits[mlCode]; - U32 const ofBits = ofCode; - U32 const totalBits = llBits + mlBits + ofBits; - - static const U32 LL_base[MaxLL + 1] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 18, - 20, 22, 24, 28, 32, 40, 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, 0x2000, 0x4000, 0x8000, 0x10000}; - - static const U32 ML_base[MaxML + 1] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, - 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 37, 39, 41, - 43, 47, 51, 59, 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, 0x1003, 0x2003, 0x4003, 0x8003, 0x10003}; - - static const U32 OF_base[MaxOff + 1] = {0, 1, 1, 5, 0xD, 0x1D, 0x3D, 0x7D, 0xFD, 0x1FD, - 0x3FD, 0x7FD, 0xFFD, 0x1FFD, 0x3FFD, 0x7FFD, 0xFFFD, 0x1FFFD, 0x3FFFD, 0x7FFFD, - 0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD}; - - /* sequence */ - { - size_t offset; - if (!ofCode) - offset = 0; - else { - if (longOffsets) { - int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN); - offset = OF_base[ofCode] + (BIT_readBitsFast(&seqState->DStream, ofBits - extraBits) << extraBits); - if (ZSTD_32bits() || extraBits) - BIT_reloadDStream(&seqState->DStream); - if (extraBits) - offset += BIT_readBitsFast(&seqState->DStream, extraBits); - } else { - offset = OF_base[ofCode] + BIT_readBitsFast(&seqState->DStream, ofBits); /* <= (ZSTD_WINDOWLOG_MAX-1) bits */ - if (ZSTD_32bits()) - BIT_reloadDStream(&seqState->DStream); - } - } - - if (ofCode <= 1) { - offset += (llCode == 0); - if (offset) { - size_t temp = (offset == 3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset]; - temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */ - if (offset != 1) - seqState->prevOffset[2] = seqState->prevOffset[1]; - seqState->prevOffset[1] = seqState->prevOffset[0]; - seqState->prevOffset[0] = offset = temp; - } else { - offset = seqState->prevOffset[0]; - } - } else { - seqState->prevOffset[2] = seqState->prevOffset[1]; - seqState->prevOffset[1] = seqState->prevOffset[0]; - seqState->prevOffset[0] = offset; - } - seq.offset = offset; - } - - seq.matchLength = ML_base[mlCode] + ((mlCode > 31) ? BIT_readBitsFast(&seqState->DStream, mlBits) : 0); /* <= 16 bits */ - if (ZSTD_32bits() && (mlBits + llBits > 24)) - BIT_reloadDStream(&seqState->DStream); - - seq.litLength = LL_base[llCode] + ((llCode > 15) ? BIT_readBitsFast(&seqState->DStream, llBits) : 0); /* <= 16 bits */ - if (ZSTD_32bits() || (totalBits > 64 - 7 - (LLFSELog + MLFSELog + OffFSELog))) - BIT_reloadDStream(&seqState->DStream); - - { - size_t const pos = seqState->pos + seq.litLength; - seq.match = seqState->base + pos - seq.offset; /* single memory segment */ - if (seq.offset > pos) - seq.match += seqState->gotoDict; /* separate memory segment */ - seqState->pos = pos + seq.matchLength; - } - - /* ANS state update */ - FSE_updateState(&seqState->stateLL, &seqState->DStream); /* <= 9 bits */ - FSE_updateState(&seqState->stateML, &seqState->DStream); /* <= 9 bits */ - if (ZSTD_32bits()) - BIT_reloadDStream(&seqState->DStream); /* <= 18 bits */ - FSE_updateState(&seqState->stateOffb, &seqState->DStream); /* <= 8 bits */ - - return seq; -} - -static seq_t ZSTD_decodeSequenceLong(seqState_t *seqState, unsigned const windowSize) -{ - if (ZSTD_highbit32(windowSize) > STREAM_ACCUMULATOR_MIN) { - return ZSTD_decodeSequenceLong_generic(seqState, 1); - } else { - return ZSTD_decodeSequenceLong_generic(seqState, 0); - } -} - -FORCE_INLINE -size_t ZSTD_execSequenceLong(BYTE *op, BYTE *const oend, seq_t sequence, const BYTE **litPtr, const BYTE *const litLimit, const BYTE *const base, - const BYTE *const vBase, const BYTE *const dictEnd) -{ - BYTE *const oLitEnd = op + sequence.litLength; - size_t const sequenceLength = sequence.litLength + sequence.matchLength; - BYTE *const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */ - BYTE *const oend_w = oend - WILDCOPY_OVERLENGTH; - const BYTE *const iLitEnd = *litPtr + sequence.litLength; - const BYTE *match = sequence.match; - - /* check */ - if (oMatchEnd > oend) - return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */ - if (iLitEnd > litLimit) - return ERROR(corruption_detected); /* over-read beyond lit buffer */ - if (oLitEnd > oend_w) - return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd); - - /* copy Literals */ - ZSTD_copy8(op, *litPtr); - if (sequence.litLength > 8) - ZSTD_wildcopy(op + 8, (*litPtr) + 8, - sequence.litLength - 8); /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */ - op = oLitEnd; - *litPtr = iLitEnd; /* update for next sequence */ - - /* copy Match */ - if (sequence.offset > (size_t)(oLitEnd - base)) { - /* offset beyond prefix */ - if (sequence.offset > (size_t)(oLitEnd - vBase)) - return ERROR(corruption_detected); - if (match + sequence.matchLength <= dictEnd) { - memmove(oLitEnd, match, sequence.matchLength); - return sequenceLength; - } - /* span extDict & currPrefixSegment */ - { - size_t const length1 = dictEnd - match; - memmove(oLitEnd, match, length1); - op = oLitEnd + length1; - sequence.matchLength -= length1; - match = base; - if (op > oend_w || sequence.matchLength < MINMATCH) { - U32 i; - for (i = 0; i < sequence.matchLength; ++i) - op[i] = match[i]; - return sequenceLength; - } - } - } - /* Requirement: op <= oend_w && sequence.matchLength >= MINMATCH */ - - /* match within prefix */ - if (sequence.offset < 8) { - /* close range match, overlap */ - static const U32 dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; /* added */ - static const int dec64table[] = {8, 8, 8, 7, 8, 9, 10, 11}; /* subtracted */ - int const sub2 = dec64table[sequence.offset]; - op[0] = match[0]; - op[1] = match[1]; - op[2] = match[2]; - op[3] = match[3]; - match += dec32table[sequence.offset]; - ZSTD_copy4(op + 4, match); - match -= sub2; - } else { - ZSTD_copy8(op, match); - } - op += 8; - match += 8; - - if (oMatchEnd > oend - (16 - MINMATCH)) { - if (op < oend_w) { - ZSTD_wildcopy(op, match, oend_w - op); - match += oend_w - op; - op = oend_w; - } - while (op < oMatchEnd) - *op++ = *match++; - } else { - ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength - 8); /* works even if matchLength < 8 */ - } - return sequenceLength; -} - -static size_t ZSTD_decompressSequencesLong(ZSTD_DCtx *dctx, void *dst, size_t maxDstSize, const void *seqStart, size_t seqSize) -{ - const BYTE *ip = (const BYTE *)seqStart; - const BYTE *const iend = ip + seqSize; - BYTE *const ostart = (BYTE * const)dst; - BYTE *const oend = ostart + maxDstSize; - BYTE *op = ostart; - const BYTE *litPtr = dctx->litPtr; - const BYTE *const litEnd = litPtr + dctx->litSize; - const BYTE *const base = (const BYTE *)(dctx->base); - const BYTE *const vBase = (const BYTE *)(dctx->vBase); - const BYTE *const dictEnd = (const BYTE *)(dctx->dictEnd); - unsigned const windowSize = dctx->fParams.windowSize; - int nbSeq; - - /* Build Decoding Tables */ - { - size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, seqSize); - if (ZSTD_isError(seqHSize)) - return seqHSize; - ip += seqHSize; - } - - /* Regen sequences */ - if (nbSeq) { -#define STORED_SEQS 4 -#define STOSEQ_MASK (STORED_SEQS - 1) -#define ADVANCED_SEQS 4 - seq_t *sequences = (seq_t *)dctx->entropy.workspace; - int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS); - seqState_t seqState; - int seqNb; - ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.workspace) >= sizeof(seq_t) * STORED_SEQS); - dctx->fseEntropy = 1; - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - seqState.prevOffset[i] = dctx->entropy.rep[i]; - } - seqState.base = base; - seqState.pos = (size_t)(op - base); - seqState.gotoDict = (uPtrDiff)dictEnd - (uPtrDiff)base; /* cast to avoid undefined behaviour */ - CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend - ip), corruption_detected); - FSE_initDState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr); - FSE_initDState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr); - FSE_initDState(&seqState.stateML, &seqState.DStream, dctx->MLTptr); - - /* prepare in advance */ - for (seqNb = 0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && seqNb < seqAdvance; seqNb++) { - sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, windowSize); - } - if (seqNb < seqAdvance) - return ERROR(corruption_detected); - - /* decode and decompress */ - for (; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && seqNb < nbSeq; seqNb++) { - seq_t const sequence = ZSTD_decodeSequenceLong(&seqState, windowSize); - size_t const oneSeqSize = - ZSTD_execSequenceLong(op, oend, sequences[(seqNb - ADVANCED_SEQS) & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd); - if (ZSTD_isError(oneSeqSize)) - return oneSeqSize; - ZSTD_PREFETCH(sequence.match); - sequences[seqNb & STOSEQ_MASK] = sequence; - op += oneSeqSize; - } - if (seqNb < nbSeq) - return ERROR(corruption_detected); - - /* finish queue */ - seqNb -= seqAdvance; - for (; seqNb < nbSeq; seqNb++) { - size_t const oneSeqSize = ZSTD_execSequenceLong(op, oend, sequences[seqNb & STOSEQ_MASK], &litPtr, litEnd, base, vBase, dictEnd); - if (ZSTD_isError(oneSeqSize)) - return oneSeqSize; - op += oneSeqSize; - } - - /* save reps for next block */ - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); - } - } - - /* last literal segment */ - { - size_t const lastLLSize = litEnd - litPtr; - if (lastLLSize > (size_t)(oend - op)) - return ERROR(dstSize_tooSmall); - memcpy(op, litPtr, lastLLSize); - op += lastLLSize; - } - - return op - ostart; -} - -static size_t ZSTD_decompressBlock_internal(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ /* blockType == blockCompressed */ - const BYTE *ip = (const BYTE *)src; - - if (srcSize >= ZSTD_BLOCKSIZE_ABSOLUTEMAX) - return ERROR(srcSize_wrong); - - /* Decode literals section */ - { - size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize); - if (ZSTD_isError(litCSize)) - return litCSize; - ip += litCSize; - srcSize -= litCSize; - } - if (sizeof(size_t) > 4) /* do not enable prefetching on 32-bits x86, as it's performance detrimental */ - /* likely because of register pressure */ - /* if that's the correct cause, then 32-bits ARM should be affected differently */ - /* it would be good to test this on ARM real hardware, to see if prefetch version improves speed */ - if (dctx->fParams.windowSize > (1 << 23)) - return ZSTD_decompressSequencesLong(dctx, dst, dstCapacity, ip, srcSize); - return ZSTD_decompressSequences(dctx, dst, dstCapacity, ip, srcSize); -} - -static void ZSTD_checkContinuity(ZSTD_DCtx *dctx, const void *dst) -{ - if (dst != dctx->previousDstEnd) { /* not contiguous */ - dctx->dictEnd = dctx->previousDstEnd; - dctx->vBase = (const char *)dst - ((const char *)(dctx->previousDstEnd) - (const char *)(dctx->base)); - dctx->base = dst; - dctx->previousDstEnd = dst; - } -} - -size_t ZSTD_decompressBlock(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - size_t dSize; - ZSTD_checkContinuity(dctx, dst); - dSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize); - dctx->previousDstEnd = (char *)dst + dSize; - return dSize; -} - -/** ZSTD_insertBlock() : - insert `src` block into `dctx` history. Useful to track uncompressed blocks. */ -size_t ZSTD_insertBlock(ZSTD_DCtx *dctx, const void *blockStart, size_t blockSize) -{ - ZSTD_checkContinuity(dctx, blockStart); - dctx->previousDstEnd = (const char *)blockStart + blockSize; - return blockSize; -} - -size_t ZSTD_generateNxBytes(void *dst, size_t dstCapacity, BYTE byte, size_t length) -{ - if (length > dstCapacity) - return ERROR(dstSize_tooSmall); - memset(dst, byte, length); - return length; -} - -/** ZSTD_findFrameCompressedSize() : - * compatible with legacy mode - * `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame - * `srcSize` must be at least as large as the frame contained - * @return : the compressed size of the frame starting at `src` */ -size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize) -{ - if (srcSize >= ZSTD_skippableHeaderSize && (ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { - return ZSTD_skippableHeaderSize + ZSTD_readLE32((const BYTE *)src + 4); - } else { - const BYTE *ip = (const BYTE *)src; - const BYTE *const ipstart = ip; - size_t remainingSize = srcSize; - ZSTD_frameParams fParams; - - size_t const headerSize = ZSTD_frameHeaderSize(ip, remainingSize); - if (ZSTD_isError(headerSize)) - return headerSize; - - /* Frame Header */ - { - size_t const ret = ZSTD_getFrameParams(&fParams, ip, remainingSize); - if (ZSTD_isError(ret)) - return ret; - if (ret > 0) - return ERROR(srcSize_wrong); - } - - ip += headerSize; - remainingSize -= headerSize; - - /* Loop on each block */ - while (1) { - blockProperties_t blockProperties; - size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTD_isError(cBlockSize)) - return cBlockSize; - - if (ZSTD_blockHeaderSize + cBlockSize > remainingSize) - return ERROR(srcSize_wrong); - - ip += ZSTD_blockHeaderSize + cBlockSize; - remainingSize -= ZSTD_blockHeaderSize + cBlockSize; - - if (blockProperties.lastBlock) - break; - } - - if (fParams.checksumFlag) { /* Frame content checksum */ - if (remainingSize < 4) - return ERROR(srcSize_wrong); - ip += 4; - remainingSize -= 4; - } - - return ip - ipstart; - } -} - -/*! ZSTD_decompressFrame() : -* @dctx must be properly initialized */ -static size_t ZSTD_decompressFrame(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void **srcPtr, size_t *srcSizePtr) -{ - const BYTE *ip = (const BYTE *)(*srcPtr); - BYTE *const ostart = (BYTE * const)dst; - BYTE *const oend = ostart + dstCapacity; - BYTE *op = ostart; - size_t remainingSize = *srcSizePtr; - - /* check */ - if (remainingSize < ZSTD_frameHeaderSize_min + ZSTD_blockHeaderSize) - return ERROR(srcSize_wrong); - - /* Frame Header */ - { - size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_frameHeaderSize_prefix); - if (ZSTD_isError(frameHeaderSize)) - return frameHeaderSize; - if (remainingSize < frameHeaderSize + ZSTD_blockHeaderSize) - return ERROR(srcSize_wrong); - CHECK_F(ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize)); - ip += frameHeaderSize; - remainingSize -= frameHeaderSize; - } - - /* Loop on each block */ - while (1) { - size_t decodedSize; - blockProperties_t blockProperties; - size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); - if (ZSTD_isError(cBlockSize)) - return cBlockSize; - - ip += ZSTD_blockHeaderSize; - remainingSize -= ZSTD_blockHeaderSize; - if (cBlockSize > remainingSize) - return ERROR(srcSize_wrong); - - switch (blockProperties.blockType) { - case bt_compressed: decodedSize = ZSTD_decompressBlock_internal(dctx, op, oend - op, ip, cBlockSize); break; - case bt_raw: decodedSize = ZSTD_copyRawBlock(op, oend - op, ip, cBlockSize); break; - case bt_rle: decodedSize = ZSTD_generateNxBytes(op, oend - op, *ip, blockProperties.origSize); break; - case bt_reserved: - default: return ERROR(corruption_detected); - } - - if (ZSTD_isError(decodedSize)) - return decodedSize; - if (dctx->fParams.checksumFlag) - xxh64_update(&dctx->xxhState, op, decodedSize); - op += decodedSize; - ip += cBlockSize; - remainingSize -= cBlockSize; - if (blockProperties.lastBlock) - break; - } - - if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */ - U32 const checkCalc = (U32)xxh64_digest(&dctx->xxhState); - U32 checkRead; - if (remainingSize < 4) - return ERROR(checksum_wrong); - checkRead = ZSTD_readLE32(ip); - if (checkRead != checkCalc) - return ERROR(checksum_wrong); - ip += 4; - remainingSize -= 4; - } - - /* Allow caller to get size read */ - *srcPtr = ip; - *srcSizePtr = remainingSize; - return op - ostart; -} - -static const void *ZSTD_DDictDictContent(const ZSTD_DDict *ddict); -static size_t ZSTD_DDictDictSize(const ZSTD_DDict *ddict); - -static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize, - const ZSTD_DDict *ddict) -{ - void *const dststart = dst; - - if (ddict) { - if (dict) { - /* programmer error, these two cases should be mutually exclusive */ - return ERROR(GENERIC); - } - - dict = ZSTD_DDictDictContent(ddict); - dictSize = ZSTD_DDictDictSize(ddict); - } - - while (srcSize >= ZSTD_frameHeaderSize_prefix) { - U32 magicNumber; - - magicNumber = ZSTD_readLE32(src); - if (magicNumber != ZSTD_MAGICNUMBER) { - if ((magicNumber & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { - size_t skippableSize; - if (srcSize < ZSTD_skippableHeaderSize) - return ERROR(srcSize_wrong); - skippableSize = ZSTD_readLE32((const BYTE *)src + 4) + ZSTD_skippableHeaderSize; - if (srcSize < skippableSize) { - return ERROR(srcSize_wrong); - } - - src = (const BYTE *)src + skippableSize; - srcSize -= skippableSize; - continue; - } else { - return ERROR(prefix_unknown); - } - } - - if (ddict) { - /* we were called from ZSTD_decompress_usingDDict */ - ZSTD_refDDict(dctx, ddict); - } else { - /* this will initialize correctly with no dict if dict == NULL, so - * use this in all cases but ddict */ - CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize)); - } - ZSTD_checkContinuity(dctx, dst); - - { - const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, &src, &srcSize); - if (ZSTD_isError(res)) - return res; - /* don't need to bounds check this, ZSTD_decompressFrame will have - * already */ - dst = (BYTE *)dst + res; - dstCapacity -= res; - } - } - - if (srcSize) - return ERROR(srcSize_wrong); /* input not entirely consumed */ - - return (BYTE *)dst - (BYTE *)dststart; -} - -size_t ZSTD_decompress_usingDict(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const void *dict, size_t dictSize) -{ - return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL); -} - -size_t ZSTD_decompressDCtx(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0); -} - -/*-************************************** -* Advanced Streaming Decompression API -* Bufferless and synchronous -****************************************/ -size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx *dctx) { return dctx->expected; } - -ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx *dctx) -{ - switch (dctx->stage) { - default: /* should not happen */ - case ZSTDds_getFrameHeaderSize: - case ZSTDds_decodeFrameHeader: return ZSTDnit_frameHeader; - case ZSTDds_decodeBlockHeader: return ZSTDnit_blockHeader; - case ZSTDds_decompressBlock: return ZSTDnit_block; - case ZSTDds_decompressLastBlock: return ZSTDnit_lastBlock; - case ZSTDds_checkChecksum: return ZSTDnit_checksum; - case ZSTDds_decodeSkippableHeader: - case ZSTDds_skipFrame: return ZSTDnit_skippableFrame; - } -} - -int ZSTD_isSkipFrame(ZSTD_DCtx *dctx) { return dctx->stage == ZSTDds_skipFrame; } /* for zbuff */ - -/** ZSTD_decompressContinue() : -* @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity) -* or an error code, which can be tested using ZSTD_isError() */ -size_t ZSTD_decompressContinue(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - /* Sanity check */ - if (srcSize != dctx->expected) - return ERROR(srcSize_wrong); - if (dstCapacity) - ZSTD_checkContinuity(dctx, dst); - - switch (dctx->stage) { - case ZSTDds_getFrameHeaderSize: - if (srcSize != ZSTD_frameHeaderSize_prefix) - return ERROR(srcSize_wrong); /* impossible */ - if ((ZSTD_readLE32(src) & 0xFFFFFFF0U) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */ - memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix); - dctx->expected = ZSTD_skippableHeaderSize - ZSTD_frameHeaderSize_prefix; /* magic number + skippable frame length */ - dctx->stage = ZSTDds_decodeSkippableHeader; - return 0; - } - dctx->headerSize = ZSTD_frameHeaderSize(src, ZSTD_frameHeaderSize_prefix); - if (ZSTD_isError(dctx->headerSize)) - return dctx->headerSize; - memcpy(dctx->headerBuffer, src, ZSTD_frameHeaderSize_prefix); - if (dctx->headerSize > ZSTD_frameHeaderSize_prefix) { - dctx->expected = dctx->headerSize - ZSTD_frameHeaderSize_prefix; - dctx->stage = ZSTDds_decodeFrameHeader; - return 0; - } - dctx->expected = 0; /* not necessary to copy more */ - fallthrough; - - case ZSTDds_decodeFrameHeader: - memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected); - CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize)); - dctx->expected = ZSTD_blockHeaderSize; - dctx->stage = ZSTDds_decodeBlockHeader; - return 0; - - case ZSTDds_decodeBlockHeader: { - blockProperties_t bp; - size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp); - if (ZSTD_isError(cBlockSize)) - return cBlockSize; - dctx->expected = cBlockSize; - dctx->bType = bp.blockType; - dctx->rleSize = bp.origSize; - if (cBlockSize) { - dctx->stage = bp.lastBlock ? ZSTDds_decompressLastBlock : ZSTDds_decompressBlock; - return 0; - } - /* empty block */ - if (bp.lastBlock) { - if (dctx->fParams.checksumFlag) { - dctx->expected = 4; - dctx->stage = ZSTDds_checkChecksum; - } else { - dctx->expected = 0; /* end of frame */ - dctx->stage = ZSTDds_getFrameHeaderSize; - } - } else { - dctx->expected = 3; /* go directly to next header */ - dctx->stage = ZSTDds_decodeBlockHeader; - } - return 0; - } - case ZSTDds_decompressLastBlock: - case ZSTDds_decompressBlock: { - size_t rSize; - switch (dctx->bType) { - case bt_compressed: rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize); break; - case bt_raw: rSize = ZSTD_copyRawBlock(dst, dstCapacity, src, srcSize); break; - case bt_rle: rSize = ZSTD_setRleBlock(dst, dstCapacity, src, srcSize, dctx->rleSize); break; - case bt_reserved: /* should never happen */ - default: return ERROR(corruption_detected); - } - if (ZSTD_isError(rSize)) - return rSize; - if (dctx->fParams.checksumFlag) - xxh64_update(&dctx->xxhState, dst, rSize); - - if (dctx->stage == ZSTDds_decompressLastBlock) { /* end of frame */ - if (dctx->fParams.checksumFlag) { /* another round for frame checksum */ - dctx->expected = 4; - dctx->stage = ZSTDds_checkChecksum; - } else { - dctx->expected = 0; /* ends here */ - dctx->stage = ZSTDds_getFrameHeaderSize; - } - } else { - dctx->stage = ZSTDds_decodeBlockHeader; - dctx->expected = ZSTD_blockHeaderSize; - dctx->previousDstEnd = (char *)dst + rSize; - } - return rSize; - } - case ZSTDds_checkChecksum: { - U32 const h32 = (U32)xxh64_digest(&dctx->xxhState); - U32 const check32 = ZSTD_readLE32(src); /* srcSize == 4, guaranteed by dctx->expected */ - if (check32 != h32) - return ERROR(checksum_wrong); - dctx->expected = 0; - dctx->stage = ZSTDds_getFrameHeaderSize; - return 0; - } - case ZSTDds_decodeSkippableHeader: { - memcpy(dctx->headerBuffer + ZSTD_frameHeaderSize_prefix, src, dctx->expected); - dctx->expected = ZSTD_readLE32(dctx->headerBuffer + 4); - dctx->stage = ZSTDds_skipFrame; - return 0; - } - case ZSTDds_skipFrame: { - dctx->expected = 0; - dctx->stage = ZSTDds_getFrameHeaderSize; - return 0; - } - default: - return ERROR(GENERIC); /* impossible */ - } -} - -static size_t ZSTD_refDictContent(ZSTD_DCtx *dctx, const void *dict, size_t dictSize) -{ - dctx->dictEnd = dctx->previousDstEnd; - dctx->vBase = (const char *)dict - ((const char *)(dctx->previousDstEnd) - (const char *)(dctx->base)); - dctx->base = dict; - dctx->previousDstEnd = (const char *)dict + dictSize; - return 0; -} - -/* ZSTD_loadEntropy() : - * dict : must point at beginning of a valid zstd dictionary - * @return : size of entropy tables read */ -static size_t ZSTD_loadEntropy(ZSTD_entropyTables_t *entropy, const void *const dict, size_t const dictSize) -{ - const BYTE *dictPtr = (const BYTE *)dict; - const BYTE *const dictEnd = dictPtr + dictSize; - - if (dictSize <= 8) - return ERROR(dictionary_corrupted); - dictPtr += 8; /* skip header = magic + dictID */ - - { - size_t const hSize = HUF_readDTableX4_wksp(entropy->hufTable, dictPtr, dictEnd - dictPtr, entropy->workspace, sizeof(entropy->workspace)); - if (HUF_isError(hSize)) - return ERROR(dictionary_corrupted); - dictPtr += hSize; - } - - { - short offcodeNCount[MaxOff + 1]; - U32 offcodeMaxValue = MaxOff, offcodeLog; - size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd - dictPtr); - if (FSE_isError(offcodeHeaderSize)) - return ERROR(dictionary_corrupted); - if (offcodeLog > OffFSELog) - return ERROR(dictionary_corrupted); - CHECK_E(FSE_buildDTable_wksp(entropy->OFTable, offcodeNCount, offcodeMaxValue, offcodeLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted); - dictPtr += offcodeHeaderSize; - } - - { - short matchlengthNCount[MaxML + 1]; - unsigned matchlengthMaxValue = MaxML, matchlengthLog; - size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd - dictPtr); - if (FSE_isError(matchlengthHeaderSize)) - return ERROR(dictionary_corrupted); - if (matchlengthLog > MLFSELog) - return ERROR(dictionary_corrupted); - CHECK_E(FSE_buildDTable_wksp(entropy->MLTable, matchlengthNCount, matchlengthMaxValue, matchlengthLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted); - dictPtr += matchlengthHeaderSize; - } - - { - short litlengthNCount[MaxLL + 1]; - unsigned litlengthMaxValue = MaxLL, litlengthLog; - size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd - dictPtr); - if (FSE_isError(litlengthHeaderSize)) - return ERROR(dictionary_corrupted); - if (litlengthLog > LLFSELog) - return ERROR(dictionary_corrupted); - CHECK_E(FSE_buildDTable_wksp(entropy->LLTable, litlengthNCount, litlengthMaxValue, litlengthLog, entropy->workspace, sizeof(entropy->workspace)), dictionary_corrupted); - dictPtr += litlengthHeaderSize; - } - - if (dictPtr + 12 > dictEnd) - return ERROR(dictionary_corrupted); - { - int i; - size_t const dictContentSize = (size_t)(dictEnd - (dictPtr + 12)); - for (i = 0; i < 3; i++) { - U32 const rep = ZSTD_readLE32(dictPtr); - dictPtr += 4; - if (rep == 0 || rep >= dictContentSize) - return ERROR(dictionary_corrupted); - entropy->rep[i] = rep; - } - } - - return dictPtr - (const BYTE *)dict; -} - -static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx *dctx, const void *dict, size_t dictSize) -{ - if (dictSize < 8) - return ZSTD_refDictContent(dctx, dict, dictSize); - { - U32 const magic = ZSTD_readLE32(dict); - if (magic != ZSTD_DICT_MAGIC) { - return ZSTD_refDictContent(dctx, dict, dictSize); /* pure content mode */ - } - } - dctx->dictID = ZSTD_readLE32((const char *)dict + 4); - - /* load entropy tables */ - { - size_t const eSize = ZSTD_loadEntropy(&dctx->entropy, dict, dictSize); - if (ZSTD_isError(eSize)) - return ERROR(dictionary_corrupted); - dict = (const char *)dict + eSize; - dictSize -= eSize; - } - dctx->litEntropy = dctx->fseEntropy = 1; - - /* reference dictionary content */ - return ZSTD_refDictContent(dctx, dict, dictSize); -} - -size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx *dctx, const void *dict, size_t dictSize) -{ - CHECK_F(ZSTD_decompressBegin(dctx)); - if (dict && dictSize) - CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted); - return 0; -} - -/* ====== ZSTD_DDict ====== */ - -struct ZSTD_DDict_s { - void *dictBuffer; - const void *dictContent; - size_t dictSize; - ZSTD_entropyTables_t entropy; - U32 dictID; - U32 entropyPresent; - ZSTD_customMem cMem; -}; /* typedef'd to ZSTD_DDict within "zstd.h" */ - -size_t ZSTD_DDictWorkspaceBound(void) { return ZSTD_ALIGN(sizeof(ZSTD_stack)) + ZSTD_ALIGN(sizeof(ZSTD_DDict)); } - -static const void *ZSTD_DDictDictContent(const ZSTD_DDict *ddict) { return ddict->dictContent; } - -static size_t ZSTD_DDictDictSize(const ZSTD_DDict *ddict) { return ddict->dictSize; } - -static void ZSTD_refDDict(ZSTD_DCtx *dstDCtx, const ZSTD_DDict *ddict) -{ - ZSTD_decompressBegin(dstDCtx); /* init */ - if (ddict) { /* support refDDict on NULL */ - dstDCtx->dictID = ddict->dictID; - dstDCtx->base = ddict->dictContent; - dstDCtx->vBase = ddict->dictContent; - dstDCtx->dictEnd = (const BYTE *)ddict->dictContent + ddict->dictSize; - dstDCtx->previousDstEnd = dstDCtx->dictEnd; - if (ddict->entropyPresent) { - dstDCtx->litEntropy = 1; - dstDCtx->fseEntropy = 1; - dstDCtx->LLTptr = ddict->entropy.LLTable; - dstDCtx->MLTptr = ddict->entropy.MLTable; - dstDCtx->OFTptr = ddict->entropy.OFTable; - dstDCtx->HUFptr = ddict->entropy.hufTable; - dstDCtx->entropy.rep[0] = ddict->entropy.rep[0]; - dstDCtx->entropy.rep[1] = ddict->entropy.rep[1]; - dstDCtx->entropy.rep[2] = ddict->entropy.rep[2]; - } else { - dstDCtx->litEntropy = 0; - dstDCtx->fseEntropy = 0; - } - } -} - -static size_t ZSTD_loadEntropy_inDDict(ZSTD_DDict *ddict) -{ - ddict->dictID = 0; - ddict->entropyPresent = 0; - if (ddict->dictSize < 8) - return 0; - { - U32 const magic = ZSTD_readLE32(ddict->dictContent); - if (magic != ZSTD_DICT_MAGIC) - return 0; /* pure content mode */ - } - ddict->dictID = ZSTD_readLE32((const char *)ddict->dictContent + 4); - - /* load entropy tables */ - CHECK_E(ZSTD_loadEntropy(&ddict->entropy, ddict->dictContent, ddict->dictSize), dictionary_corrupted); - ddict->entropyPresent = 1; - return 0; -} - -static ZSTD_DDict *ZSTD_createDDict_advanced(const void *dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem) -{ - if (!customMem.customAlloc || !customMem.customFree) - return NULL; - - { - ZSTD_DDict *const ddict = (ZSTD_DDict *)ZSTD_malloc(sizeof(ZSTD_DDict), customMem); - if (!ddict) - return NULL; - ddict->cMem = customMem; - - if ((byReference) || (!dict) || (!dictSize)) { - ddict->dictBuffer = NULL; - ddict->dictContent = dict; - } else { - void *const internalBuffer = ZSTD_malloc(dictSize, customMem); - if (!internalBuffer) { - ZSTD_freeDDict(ddict); - return NULL; - } - memcpy(internalBuffer, dict, dictSize); - ddict->dictBuffer = internalBuffer; - ddict->dictContent = internalBuffer; - } - ddict->dictSize = dictSize; - ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ - /* parse dictionary content */ - { - size_t const errorCode = ZSTD_loadEntropy_inDDict(ddict); - if (ZSTD_isError(errorCode)) { - ZSTD_freeDDict(ddict); - return NULL; - } - } - - return ddict; - } -} - -/*! ZSTD_initDDict() : -* Create a digested dictionary, to start decompression without startup delay. -* `dict` content is copied inside DDict. -* Consequently, `dict` can be released after `ZSTD_DDict` creation */ -ZSTD_DDict *ZSTD_initDDict(const void *dict, size_t dictSize, void *workspace, size_t workspaceSize) -{ - ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize); - return ZSTD_createDDict_advanced(dict, dictSize, 1, stackMem); -} - -size_t ZSTD_freeDDict(ZSTD_DDict *ddict) -{ - if (ddict == NULL) - return 0; /* support free on NULL */ - { - ZSTD_customMem const cMem = ddict->cMem; - ZSTD_free(ddict->dictBuffer, cMem); - ZSTD_free(ddict, cMem); - return 0; - } -} - -/*! ZSTD_getDictID_fromDict() : - * Provides the dictID stored within dictionary. - * if @return == 0, the dictionary is not conformant with Zstandard specification. - * It can still be loaded, but as a content-only dictionary. */ -unsigned ZSTD_getDictID_fromDict(const void *dict, size_t dictSize) -{ - if (dictSize < 8) - return 0; - if (ZSTD_readLE32(dict) != ZSTD_DICT_MAGIC) - return 0; - return ZSTD_readLE32((const char *)dict + 4); -} - -/*! ZSTD_getDictID_fromDDict() : - * Provides the dictID of the dictionary loaded into `ddict`. - * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. - * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ -unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict *ddict) -{ - if (ddict == NULL) - return 0; - return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize); -} - -/*! ZSTD_getDictID_fromFrame() : - * Provides the dictID required to decompressed the frame stored within `src`. - * If @return == 0, the dictID could not be decoded. - * This could for one of the following reasons : - * - The frame does not require a dictionary to be decoded (most common case). - * - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information. - * Note : this use case also happens when using a non-conformant dictionary. - * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). - * - This is not a Zstandard frame. - * When identifying the exact failure cause, it's possible to used ZSTD_getFrameParams(), which will provide a more precise error code. */ -unsigned ZSTD_getDictID_fromFrame(const void *src, size_t srcSize) -{ - ZSTD_frameParams zfp = {0, 0, 0, 0}; - size_t const hError = ZSTD_getFrameParams(&zfp, src, srcSize); - if (ZSTD_isError(hError)) - return 0; - return zfp.dictID; -} - -/*! ZSTD_decompress_usingDDict() : -* Decompression using a pre-digested Dictionary -* Use dictionary without significant overhead. */ -size_t ZSTD_decompress_usingDDict(ZSTD_DCtx *dctx, void *dst, size_t dstCapacity, const void *src, size_t srcSize, const ZSTD_DDict *ddict) -{ - /* pass content and size in case legacy frames are encountered */ - return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, NULL, 0, ddict); -} - -/*===================================== -* Streaming decompression -*====================================*/ - -typedef enum { zdss_init, zdss_loadHeader, zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage; - -/* *** Resource management *** */ -struct ZSTD_DStream_s { - ZSTD_DCtx *dctx; - ZSTD_DDict *ddictLocal; - const ZSTD_DDict *ddict; - ZSTD_frameParams fParams; - ZSTD_dStreamStage stage; - char *inBuff; - size_t inBuffSize; - size_t inPos; - size_t maxWindowSize; - char *outBuff; - size_t outBuffSize; - size_t outStart; - size_t outEnd; - size_t blockSize; - BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; /* tmp buffer to store frame header */ - size_t lhSize; - ZSTD_customMem customMem; - void *legacyContext; - U32 previousLegacyVersion; - U32 legacyVersion; - U32 hostageByte; -}; /* typedef'd to ZSTD_DStream within "zstd.h" */ - -size_t ZSTD_DStreamWorkspaceBound(size_t maxWindowSize) -{ - size_t const blockSize = MIN(maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX); - size_t const inBuffSize = blockSize; - size_t const outBuffSize = maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2; - return ZSTD_DCtxWorkspaceBound() + ZSTD_ALIGN(sizeof(ZSTD_DStream)) + ZSTD_ALIGN(inBuffSize) + ZSTD_ALIGN(outBuffSize); -} - -static ZSTD_DStream *ZSTD_createDStream_advanced(ZSTD_customMem customMem) -{ - ZSTD_DStream *zds; - - if (!customMem.customAlloc || !customMem.customFree) - return NULL; - - zds = (ZSTD_DStream *)ZSTD_malloc(sizeof(ZSTD_DStream), customMem); - if (zds == NULL) - return NULL; - memset(zds, 0, sizeof(ZSTD_DStream)); - memcpy(&zds->customMem, &customMem, sizeof(ZSTD_customMem)); - zds->dctx = ZSTD_createDCtx_advanced(customMem); - if (zds->dctx == NULL) { - ZSTD_freeDStream(zds); - return NULL; - } - zds->stage = zdss_init; - zds->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT; - return zds; -} - -ZSTD_DStream *ZSTD_initDStream(size_t maxWindowSize, void *workspace, size_t workspaceSize) -{ - ZSTD_customMem const stackMem = ZSTD_initStack(workspace, workspaceSize); - ZSTD_DStream *zds = ZSTD_createDStream_advanced(stackMem); - if (!zds) { - return NULL; - } - - zds->maxWindowSize = maxWindowSize; - zds->stage = zdss_loadHeader; - zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0; - ZSTD_freeDDict(zds->ddictLocal); - zds->ddictLocal = NULL; - zds->ddict = zds->ddictLocal; - zds->legacyVersion = 0; - zds->hostageByte = 0; - - { - size_t const blockSize = MIN(zds->maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX); - size_t const neededOutSize = zds->maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2; - - zds->inBuff = (char *)ZSTD_malloc(blockSize, zds->customMem); - zds->inBuffSize = blockSize; - zds->outBuff = (char *)ZSTD_malloc(neededOutSize, zds->customMem); - zds->outBuffSize = neededOutSize; - if (zds->inBuff == NULL || zds->outBuff == NULL) { - ZSTD_freeDStream(zds); - return NULL; - } - } - return zds; -} - -ZSTD_DStream *ZSTD_initDStream_usingDDict(size_t maxWindowSize, const ZSTD_DDict *ddict, void *workspace, size_t workspaceSize) -{ - ZSTD_DStream *zds = ZSTD_initDStream(maxWindowSize, workspace, workspaceSize); - if (zds) { - zds->ddict = ddict; - } - return zds; -} - -size_t ZSTD_freeDStream(ZSTD_DStream *zds) -{ - if (zds == NULL) - return 0; /* support free on null */ - { - ZSTD_customMem const cMem = zds->customMem; - ZSTD_freeDCtx(zds->dctx); - zds->dctx = NULL; - ZSTD_freeDDict(zds->ddictLocal); - zds->ddictLocal = NULL; - ZSTD_free(zds->inBuff, cMem); - zds->inBuff = NULL; - ZSTD_free(zds->outBuff, cMem); - zds->outBuff = NULL; - ZSTD_free(zds, cMem); - return 0; - } -} - -/* *** Initialization *** */ - -size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX + ZSTD_blockHeaderSize; } -size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_ABSOLUTEMAX; } - -size_t ZSTD_resetDStream(ZSTD_DStream *zds) -{ - zds->stage = zdss_loadHeader; - zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0; - zds->legacyVersion = 0; - zds->hostageByte = 0; - return ZSTD_frameHeaderSize_prefix; -} - -/* ***** Decompression ***** */ - -ZSTD_STATIC size_t ZSTD_limitCopy(void *dst, size_t dstCapacity, const void *src, size_t srcSize) -{ - size_t const length = MIN(dstCapacity, srcSize); - memcpy(dst, src, length); - return length; -} - -size_t ZSTD_decompressStream(ZSTD_DStream *zds, ZSTD_outBuffer *output, ZSTD_inBuffer *input) -{ - const char *const istart = (const char *)(input->src) + input->pos; - const char *const iend = (const char *)(input->src) + input->size; - const char *ip = istart; - char *const ostart = (char *)(output->dst) + output->pos; - char *const oend = (char *)(output->dst) + output->size; - char *op = ostart; - U32 someMoreWork = 1; - - while (someMoreWork) { - switch (zds->stage) { - case zdss_init: - ZSTD_resetDStream(zds); /* transparent reset on starting decoding a new frame */ - fallthrough; - - case zdss_loadHeader: { - size_t const hSize = ZSTD_getFrameParams(&zds->fParams, zds->headerBuffer, zds->lhSize); - if (ZSTD_isError(hSize)) - return hSize; - if (hSize != 0) { /* need more input */ - size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */ - if (toLoad > (size_t)(iend - ip)) { /* not enough input to load full header */ - memcpy(zds->headerBuffer + zds->lhSize, ip, iend - ip); - zds->lhSize += iend - ip; - input->pos = input->size; - return (MAX(ZSTD_frameHeaderSize_min, hSize) - zds->lhSize) + - ZSTD_blockHeaderSize; /* remaining header bytes + next block header */ - } - memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); - zds->lhSize = hSize; - ip += toLoad; - break; - } - - /* check for single-pass mode opportunity */ - if (zds->fParams.frameContentSize && zds->fParams.windowSize /* skippable frame if == 0 */ - && (U64)(size_t)(oend - op) >= zds->fParams.frameContentSize) { - size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend - istart); - if (cSize <= (size_t)(iend - istart)) { - size_t const decompressedSize = ZSTD_decompress_usingDDict(zds->dctx, op, oend - op, istart, cSize, zds->ddict); - if (ZSTD_isError(decompressedSize)) - return decompressedSize; - ip = istart + cSize; - op += decompressedSize; - zds->dctx->expected = 0; - zds->stage = zdss_init; - someMoreWork = 0; - break; - } - } - - /* Consume header */ - ZSTD_refDDict(zds->dctx, zds->ddict); - { - size_t const h1Size = ZSTD_nextSrcSizeToDecompress(zds->dctx); /* == ZSTD_frameHeaderSize_prefix */ - CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer, h1Size)); - { - size_t const h2Size = ZSTD_nextSrcSizeToDecompress(zds->dctx); - CHECK_F(ZSTD_decompressContinue(zds->dctx, NULL, 0, zds->headerBuffer + h1Size, h2Size)); - } - } - - zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN); - if (zds->fParams.windowSize > zds->maxWindowSize) - return ERROR(frameParameter_windowTooLarge); - - /* Buffers are preallocated, but double check */ - { - size_t const blockSize = MIN(zds->maxWindowSize, ZSTD_BLOCKSIZE_ABSOLUTEMAX); - size_t const neededOutSize = zds->maxWindowSize + blockSize + WILDCOPY_OVERLENGTH * 2; - if (zds->inBuffSize < blockSize) { - return ERROR(GENERIC); - } - if (zds->outBuffSize < neededOutSize) { - return ERROR(GENERIC); - } - zds->blockSize = blockSize; - } - zds->stage = zdss_read; - } - fallthrough; - - case zdss_read: { - size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx); - if (neededInSize == 0) { /* end of frame */ - zds->stage = zdss_init; - someMoreWork = 0; - break; - } - if ((size_t)(iend - ip) >= neededInSize) { /* decode directly from src */ - const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx); - size_t const decodedSize = ZSTD_decompressContinue(zds->dctx, zds->outBuff + zds->outStart, - (isSkipFrame ? 0 : zds->outBuffSize - zds->outStart), ip, neededInSize); - if (ZSTD_isError(decodedSize)) - return decodedSize; - ip += neededInSize; - if (!decodedSize && !isSkipFrame) - break; /* this was just a header */ - zds->outEnd = zds->outStart + decodedSize; - zds->stage = zdss_flush; - break; - } - if (ip == iend) { - someMoreWork = 0; - break; - } /* no more input */ - zds->stage = zdss_load; - /* pass-through */ - } - fallthrough; - - case zdss_load: { - size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds->dctx); - size_t const toLoad = neededInSize - zds->inPos; /* should always be <= remaining space within inBuff */ - size_t loadedSize; - if (toLoad > zds->inBuffSize - zds->inPos) - return ERROR(corruption_detected); /* should never happen */ - loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend - ip); - ip += loadedSize; - zds->inPos += loadedSize; - if (loadedSize < toLoad) { - someMoreWork = 0; - break; - } /* not enough input, wait for more */ - - /* decode loaded input */ - { - const int isSkipFrame = ZSTD_isSkipFrame(zds->dctx); - size_t const decodedSize = ZSTD_decompressContinue(zds->dctx, zds->outBuff + zds->outStart, zds->outBuffSize - zds->outStart, - zds->inBuff, neededInSize); - if (ZSTD_isError(decodedSize)) - return decodedSize; - zds->inPos = 0; /* input is consumed */ - if (!decodedSize && !isSkipFrame) { - zds->stage = zdss_read; - break; - } /* this was just a header */ - zds->outEnd = zds->outStart + decodedSize; - zds->stage = zdss_flush; - /* pass-through */ - } - } - fallthrough; - - case zdss_flush: { - size_t const toFlushSize = zds->outEnd - zds->outStart; - size_t const flushedSize = ZSTD_limitCopy(op, oend - op, zds->outBuff + zds->outStart, toFlushSize); - op += flushedSize; - zds->outStart += flushedSize; - if (flushedSize == toFlushSize) { /* flush completed */ - zds->stage = zdss_read; - if (zds->outStart + zds->blockSize > zds->outBuffSize) - zds->outStart = zds->outEnd = 0; - break; - } - /* cannot complete flush */ - someMoreWork = 0; - break; - } - default: - return ERROR(GENERIC); /* impossible */ - } - } - - /* result */ - input->pos += (size_t)(ip - istart); - output->pos += (size_t)(op - ostart); - { - size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds->dctx); - if (!nextSrcSizeHint) { /* frame fully decoded */ - if (zds->outEnd == zds->outStart) { /* output fully flushed */ - if (zds->hostageByte) { - if (input->pos >= input->size) { - zds->stage = zdss_read; - return 1; - } /* can't release hostage (not present) */ - input->pos++; /* release hostage */ - } - return 0; - } - if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */ - input->pos--; /* note : pos > 0, otherwise, impossible to finish reading last block */ - zds->hostageByte = 1; - } - return 1; - } - nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds->dctx) == ZSTDnit_block); /* preload header of next block */ - if (zds->inPos > nextSrcSizeHint) - return ERROR(GENERIC); /* should never happen */ - nextSrcSizeHint -= zds->inPos; /* already loaded*/ - return nextSrcSizeHint; - } -} - -unsigned int zstd_is_error(size_t code) -{ - return ZSTD_isError(code); -} -EXPORT_SYMBOL(zstd_is_error); - -zstd_error_code zstd_get_error_code(size_t code) -{ - return ZSTD_getErrorCode(code); -} -EXPORT_SYMBOL(zstd_get_error_code); - -const char *zstd_get_error_name(size_t code) -{ - /* Real implementation in zstd-1.4.6. */ - return "GENERIC"; -} -EXPORT_SYMBOL(zstd_get_error_name); - -size_t zstd_dctx_workspace_bound(void) -{ - return ZSTD_DCtxWorkspaceBound(); -} -EXPORT_SYMBOL(zstd_dctx_workspace_bound); - -zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size) -{ - return ZSTD_initDCtx(workspace, workspace_size); -} -EXPORT_SYMBOL(zstd_init_dctx); - -size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, - const void *src, size_t src_size) -{ - return ZSTD_decompressDCtx(dctx, dst, dst_capacity, src, src_size); -} -EXPORT_SYMBOL(zstd_decompress_dctx); - -size_t zstd_dstream_workspace_bound(size_t max_window_size) -{ - return ZSTD_DStreamWorkspaceBound(max_window_size); -} -EXPORT_SYMBOL(zstd_dstream_workspace_bound); - -zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace, - size_t workspace_size) -{ - return ZSTD_initDStream(max_window_size, workspace, workspace_size); -} -EXPORT_SYMBOL(zstd_init_dstream); - -size_t zstd_reset_dstream(zstd_dstream *dstream) -{ - return ZSTD_resetDStream(dstream); -} -EXPORT_SYMBOL(zstd_reset_dstream); - -size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output, - zstd_in_buffer *input) -{ - return ZSTD_decompressStream(dstream, output, input); -} -EXPORT_SYMBOL(zstd_decompress_stream); - -size_t zstd_find_frame_compressed_size(const void *src, size_t src_size) -{ - return ZSTD_findFrameCompressedSize(src, src_size); -} -EXPORT_SYMBOL(zstd_find_frame_compressed_size); - -size_t zstd_get_frame_header(zstd_frame_header *header, const void *src, - size_t src_size) -{ - return ZSTD_getFrameParams(header, src, src_size); -} -EXPORT_SYMBOL(zstd_get_frame_header); - -MODULE_LICENSE("Dual BSD/GPL"); -MODULE_DESCRIPTION("Zstd Decompressor"); diff --git a/lib/zstd/decompress/huf_decompress.c b/lib/zstd/decompress/huf_decompress.c new file mode 100644 index 000000000000..05570ed5f8be --- /dev/null +++ b/lib/zstd/decompress/huf_decompress.c @@ -0,0 +1,1206 @@ +/* ****************************************************************** + * huff0 huffman decoder, + * part of Finite State Entropy library + * Copyright (c) Yann Collet, Facebook, Inc. + * + * You can contact the author at : + * - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. +****************************************************************** */ + +/* ************************************************************** +* Dependencies +****************************************************************/ +#include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memset */ +#include "../common/compiler.h" +#include "../common/bitstream.h" /* BIT_* */ +#include "../common/fse.h" /* to compress headers */ +#define HUF_STATIC_LINKING_ONLY +#include "../common/huf.h" +#include "../common/error_private.h" + +/* ************************************************************** +* Macros +****************************************************************/ + +/* These two optional macros force the use one way or another of the two + * Huffman decompression implementations. You can't force in both directions + * at the same time. + */ +#if defined(HUF_FORCE_DECOMPRESS_X1) && \ + defined(HUF_FORCE_DECOMPRESS_X2) +#error "Cannot force the use of the X1 and X2 decoders at the same time!" +#endif + + +/* ************************************************************** +* Error Management +****************************************************************/ +#define HUF_isError ERR_isError + + +/* ************************************************************** +* Byte alignment for workSpace management +****************************************************************/ +#define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1) +#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask)) + + +/* ************************************************************** +* BMI2 Variant Wrappers +****************************************************************/ +#if DYNAMIC_BMI2 + +#define HUF_DGEN(fn) \ + \ + static size_t fn##_default( \ + void* dst, size_t dstSize, \ + const void* cSrc, size_t cSrcSize, \ + const HUF_DTable* DTable) \ + { \ + return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable); \ + } \ + \ + static TARGET_ATTRIBUTE("bmi2") size_t fn##_bmi2( \ + void* dst, size_t dstSize, \ + const void* cSrc, size_t cSrcSize, \ + const HUF_DTable* DTable) \ + { \ + return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable); \ + } \ + \ + static size_t fn(void* dst, size_t dstSize, void const* cSrc, \ + size_t cSrcSize, HUF_DTable const* DTable, int bmi2) \ + { \ + if (bmi2) { \ + return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable); \ + } \ + return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable); \ + } + +#else + +#define HUF_DGEN(fn) \ + static size_t fn(void* dst, size_t dstSize, void const* cSrc, \ + size_t cSrcSize, HUF_DTable const* DTable, int bmi2) \ + { \ + (void)bmi2; \ + return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable); \ + } + +#endif + + +/*-***************************/ +/* generic DTableDesc */ +/*-***************************/ +typedef struct { BYTE maxTableLog; BYTE tableType; BYTE tableLog; BYTE reserved; } DTableDesc; + +static DTableDesc HUF_getDTableDesc(const HUF_DTable* table) +{ + DTableDesc dtd; + ZSTD_memcpy(&dtd, table, sizeof(dtd)); + return dtd; +} + + +#ifndef HUF_FORCE_DECOMPRESS_X2 + +/*-***************************/ +/* single-symbol decoding */ +/*-***************************/ +typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX1; /* single-symbol decoding */ + +/* + * Packs 4 HUF_DEltX1 structs into a U64. This is used to lay down 4 entries at + * a time. + */ +static U64 HUF_DEltX1_set4(BYTE symbol, BYTE nbBits) { + U64 D4; + if (MEM_isLittleEndian()) { + D4 = symbol + (nbBits << 8); + } else { + D4 = (symbol << 8) + nbBits; + } + D4 *= 0x0001000100010001ULL; + return D4; +} + +typedef struct { + U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1]; + U32 rankStart[HUF_TABLELOG_ABSOLUTEMAX + 1]; + U32 statsWksp[HUF_READ_STATS_WORKSPACE_SIZE_U32]; + BYTE symbols[HUF_SYMBOLVALUE_MAX + 1]; + BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1]; +} HUF_ReadDTableX1_Workspace; + + +size_t HUF_readDTableX1_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize) +{ + return HUF_readDTableX1_wksp_bmi2(DTable, src, srcSize, workSpace, wkspSize, /* bmi2 */ 0); +} + +size_t HUF_readDTableX1_wksp_bmi2(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int bmi2) +{ + U32 tableLog = 0; + U32 nbSymbols = 0; + size_t iSize; + void* const dtPtr = DTable + 1; + HUF_DEltX1* const dt = (HUF_DEltX1*)dtPtr; + HUF_ReadDTableX1_Workspace* wksp = (HUF_ReadDTableX1_Workspace*)workSpace; + + DEBUG_STATIC_ASSERT(HUF_DECOMPRESS_WORKSPACE_SIZE >= sizeof(*wksp)); + if (sizeof(*wksp) > wkspSize) return ERROR(tableLog_tooLarge); + + DEBUG_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable)); + /* ZSTD_memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */ + + iSize = HUF_readStats_wksp(wksp->huffWeight, HUF_SYMBOLVALUE_MAX + 1, wksp->rankVal, &nbSymbols, &tableLog, src, srcSize, wksp->statsWksp, sizeof(wksp->statsWksp), bmi2); + if (HUF_isError(iSize)) return iSize; + + /* Table header */ + { DTableDesc dtd = HUF_getDTableDesc(DTable); + if (tableLog > (U32)(dtd.maxTableLog+1)) return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */ + dtd.tableType = 0; + dtd.tableLog = (BYTE)tableLog; + ZSTD_memcpy(DTable, &dtd, sizeof(dtd)); + } + + /* Compute symbols and rankStart given rankVal: + * + * rankVal already contains the number of values of each weight. + * + * symbols contains the symbols ordered by weight. First are the rankVal[0] + * weight 0 symbols, followed by the rankVal[1] weight 1 symbols, and so on. + * symbols[0] is filled (but unused) to avoid a branch. + * + * rankStart contains the offset where each rank belongs in the DTable. + * rankStart[0] is not filled because there are no entries in the table for + * weight 0. + */ + { + int n; + int nextRankStart = 0; + int const unroll = 4; + int const nLimit = (int)nbSymbols - unroll + 1; + for (n=0; n<(int)tableLog+1; n++) { + U32 const curr = nextRankStart; + nextRankStart += wksp->rankVal[n]; + wksp->rankStart[n] = curr; + } + for (n=0; n < nLimit; n += unroll) { + int u; + for (u=0; u < unroll; ++u) { + size_t const w = wksp->huffWeight[n+u]; + wksp->symbols[wksp->rankStart[w]++] = (BYTE)(n+u); + } + } + for (; n < (int)nbSymbols; ++n) { + size_t const w = wksp->huffWeight[n]; + wksp->symbols[wksp->rankStart[w]++] = (BYTE)n; + } + } + + /* fill DTable + * We fill all entries of each weight in order. + * That way length is a constant for each iteration of the outter loop. + * We can switch based on the length to a different inner loop which is + * optimized for that particular case. + */ + { + U32 w; + int symbol=wksp->rankVal[0]; + int rankStart=0; + for (w=1; wrankVal[w]; + int const length = (1 << w) >> 1; + int uStart = rankStart; + BYTE const nbBits = (BYTE)(tableLog + 1 - w); + int s; + int u; + switch (length) { + case 1: + for (s=0; ssymbols[symbol + s]; + D.nbBits = nbBits; + dt[uStart] = D; + uStart += 1; + } + break; + case 2: + for (s=0; ssymbols[symbol + s]; + D.nbBits = nbBits; + dt[uStart+0] = D; + dt[uStart+1] = D; + uStart += 2; + } + break; + case 4: + for (s=0; ssymbols[symbol + s], nbBits); + MEM_write64(dt + uStart, D4); + uStart += 4; + } + break; + case 8: + for (s=0; ssymbols[symbol + s], nbBits); + MEM_write64(dt + uStart, D4); + MEM_write64(dt + uStart + 4, D4); + uStart += 8; + } + break; + default: + for (s=0; ssymbols[symbol + s], nbBits); + for (u=0; u < length; u += 16) { + MEM_write64(dt + uStart + u + 0, D4); + MEM_write64(dt + uStart + u + 4, D4); + MEM_write64(dt + uStart + u + 8, D4); + MEM_write64(dt + uStart + u + 12, D4); + } + assert(u == length); + uStart += length; + } + break; + } + symbol += symbolCount; + rankStart += symbolCount * length; + } + } + return iSize; +} + +FORCE_INLINE_TEMPLATE BYTE +HUF_decodeSymbolX1(BIT_DStream_t* Dstream, const HUF_DEltX1* dt, const U32 dtLog) +{ + size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */ + BYTE const c = dt[val].byte; + BIT_skipBits(Dstream, dt[val].nbBits); + return c; +} + +#define HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) \ + *ptr++ = HUF_decodeSymbolX1(DStreamPtr, dt, dtLog) + +#define HUF_DECODE_SYMBOLX1_1(ptr, DStreamPtr) \ + if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \ + HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) + +#define HUF_DECODE_SYMBOLX1_2(ptr, DStreamPtr) \ + if (MEM_64bits()) \ + HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) + +HINT_INLINE size_t +HUF_decodeStreamX1(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX1* const dt, const U32 dtLog) +{ + BYTE* const pStart = p; + + /* up to 4 symbols at a time */ + while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-3)) { + HUF_DECODE_SYMBOLX1_2(p, bitDPtr); + HUF_DECODE_SYMBOLX1_1(p, bitDPtr); + HUF_DECODE_SYMBOLX1_2(p, bitDPtr); + HUF_DECODE_SYMBOLX1_0(p, bitDPtr); + } + + /* [0-3] symbols remaining */ + if (MEM_32bits()) + while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd)) + HUF_DECODE_SYMBOLX1_0(p, bitDPtr); + + /* no more data to retrieve from bitstream, no need to reload */ + while (p < pEnd) + HUF_DECODE_SYMBOLX1_0(p, bitDPtr); + + return pEnd-pStart; +} + +FORCE_INLINE_TEMPLATE size_t +HUF_decompress1X1_usingDTable_internal_body( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + BYTE* op = (BYTE*)dst; + BYTE* const oend = op + dstSize; + const void* dtPtr = DTable + 1; + const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr; + BIT_DStream_t bitD; + DTableDesc const dtd = HUF_getDTableDesc(DTable); + U32 const dtLog = dtd.tableLog; + + CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) ); + + HUF_decodeStreamX1(op, &bitD, oend, dt, dtLog); + + if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected); + + return dstSize; +} + +FORCE_INLINE_TEMPLATE size_t +HUF_decompress4X1_usingDTable_internal_body( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + /* Check */ + if (cSrcSize < 10) return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */ + + { const BYTE* const istart = (const BYTE*) cSrc; + BYTE* const ostart = (BYTE*) dst; + BYTE* const oend = ostart + dstSize; + BYTE* const olimit = oend - 3; + const void* const dtPtr = DTable + 1; + const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr; + + /* Init */ + BIT_DStream_t bitD1; + BIT_DStream_t bitD2; + BIT_DStream_t bitD3; + BIT_DStream_t bitD4; + size_t const length1 = MEM_readLE16(istart); + size_t const length2 = MEM_readLE16(istart+2); + size_t const length3 = MEM_readLE16(istart+4); + size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6); + const BYTE* const istart1 = istart + 6; /* jumpTable */ + const BYTE* const istart2 = istart1 + length1; + const BYTE* const istart3 = istart2 + length2; + const BYTE* const istart4 = istart3 + length3; + const size_t segmentSize = (dstSize+3) / 4; + BYTE* const opStart2 = ostart + segmentSize; + BYTE* const opStart3 = opStart2 + segmentSize; + BYTE* const opStart4 = opStart3 + segmentSize; + BYTE* op1 = ostart; + BYTE* op2 = opStart2; + BYTE* op3 = opStart3; + BYTE* op4 = opStart4; + DTableDesc const dtd = HUF_getDTableDesc(DTable); + U32 const dtLog = dtd.tableLog; + U32 endSignal = 1; + + if (length4 > cSrcSize) return ERROR(corruption_detected); /* overflow */ + CHECK_F( BIT_initDStream(&bitD1, istart1, length1) ); + CHECK_F( BIT_initDStream(&bitD2, istart2, length2) ); + CHECK_F( BIT_initDStream(&bitD3, istart3, length3) ); + CHECK_F( BIT_initDStream(&bitD4, istart4, length4) ); + + /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */ + for ( ; (endSignal) & (op4 < olimit) ; ) { + HUF_DECODE_SYMBOLX1_2(op1, &bitD1); + HUF_DECODE_SYMBOLX1_2(op2, &bitD2); + HUF_DECODE_SYMBOLX1_2(op3, &bitD3); + HUF_DECODE_SYMBOLX1_2(op4, &bitD4); + HUF_DECODE_SYMBOLX1_1(op1, &bitD1); + HUF_DECODE_SYMBOLX1_1(op2, &bitD2); + HUF_DECODE_SYMBOLX1_1(op3, &bitD3); + HUF_DECODE_SYMBOLX1_1(op4, &bitD4); + HUF_DECODE_SYMBOLX1_2(op1, &bitD1); + HUF_DECODE_SYMBOLX1_2(op2, &bitD2); + HUF_DECODE_SYMBOLX1_2(op3, &bitD3); + HUF_DECODE_SYMBOLX1_2(op4, &bitD4); + HUF_DECODE_SYMBOLX1_0(op1, &bitD1); + HUF_DECODE_SYMBOLX1_0(op2, &bitD2); + HUF_DECODE_SYMBOLX1_0(op3, &bitD3); + HUF_DECODE_SYMBOLX1_0(op4, &bitD4); + endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished; + endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished; + endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished; + endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished; + } + + /* check corruption */ + /* note : should not be necessary : op# advance in lock step, and we control op4. + * but curiously, binary generated by gcc 7.2 & 7.3 with -mbmi2 runs faster when >=1 test is present */ + if (op1 > opStart2) return ERROR(corruption_detected); + if (op2 > opStart3) return ERROR(corruption_detected); + if (op3 > opStart4) return ERROR(corruption_detected); + /* note : op4 supposed already verified within main loop */ + + /* finish bitStreams one by one */ + HUF_decodeStreamX1(op1, &bitD1, opStart2, dt, dtLog); + HUF_decodeStreamX1(op2, &bitD2, opStart3, dt, dtLog); + HUF_decodeStreamX1(op3, &bitD3, opStart4, dt, dtLog); + HUF_decodeStreamX1(op4, &bitD4, oend, dt, dtLog); + + /* check */ + { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); + if (!endCheck) return ERROR(corruption_detected); } + + /* decoded size */ + return dstSize; + } +} + + +typedef size_t (*HUF_decompress_usingDTable_t)(void *dst, size_t dstSize, + const void *cSrc, + size_t cSrcSize, + const HUF_DTable *DTable); + +HUF_DGEN(HUF_decompress1X1_usingDTable_internal) +HUF_DGEN(HUF_decompress4X1_usingDTable_internal) + + + +size_t HUF_decompress1X1_usingDTable( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc dtd = HUF_getDTableDesc(DTable); + if (dtd.tableType != 0) return ERROR(GENERIC); + return HUF_decompress1X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +} + +size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ + const BYTE* ip = (const BYTE*) cSrc; + + size_t const hSize = HUF_readDTableX1_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize); + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + + return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0); +} + + +size_t HUF_decompress4X1_usingDTable( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc dtd = HUF_getDTableDesc(DTable); + if (dtd.tableType != 0) return ERROR(GENERIC); + return HUF_decompress4X1_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +} + +static size_t HUF_decompress4X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize, int bmi2) +{ + const BYTE* ip = (const BYTE*) cSrc; + + size_t const hSize = HUF_readDTableX1_wksp_bmi2(dctx, cSrc, cSrcSize, workSpace, wkspSize, bmi2); + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + + return HUF_decompress4X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2); +} + +size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ + return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, 0); +} + + +#endif /* HUF_FORCE_DECOMPRESS_X2 */ + + +#ifndef HUF_FORCE_DECOMPRESS_X1 + +/* *************************/ +/* double-symbols decoding */ +/* *************************/ + +typedef struct { U16 sequence; BYTE nbBits; BYTE length; } HUF_DEltX2; /* double-symbols decoding */ +typedef struct { BYTE symbol; BYTE weight; } sortedSymbol_t; +typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1]; +typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX]; + + +/* HUF_fillDTableX2Level2() : + * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */ +static void HUF_fillDTableX2Level2(HUF_DEltX2* DTable, U32 sizeLog, const U32 consumed, + const U32* rankValOrigin, const int minWeight, + const sortedSymbol_t* sortedSymbols, const U32 sortedListSize, + U32 nbBitsBaseline, U16 baseSeq, U32* wksp, size_t wkspSize) +{ + HUF_DEltX2 DElt; + U32* rankVal = wksp; + + assert(wkspSize >= HUF_TABLELOG_MAX + 1); + (void)wkspSize; + /* get pre-calculated rankVal */ + ZSTD_memcpy(rankVal, rankValOrigin, sizeof(U32) * (HUF_TABLELOG_MAX + 1)); + + /* fill skipped values */ + if (minWeight>1) { + U32 i, skipSize = rankVal[minWeight]; + MEM_writeLE16(&(DElt.sequence), baseSeq); + DElt.nbBits = (BYTE)(consumed); + DElt.length = 1; + for (i = 0; i < skipSize; i++) + DTable[i] = DElt; + } + + /* fill DTable */ + { U32 s; for (s=0; s= 1 */ + + rankVal[weight] += length; + } } +} + + +static void HUF_fillDTableX2(HUF_DEltX2* DTable, const U32 targetLog, + const sortedSymbol_t* sortedList, const U32 sortedListSize, + const U32* rankStart, rankVal_t rankValOrigin, const U32 maxWeight, + const U32 nbBitsBaseline, U32* wksp, size_t wkspSize) +{ + U32* rankVal = wksp; + const int scaleLog = nbBitsBaseline - targetLog; /* note : targetLog >= srcLog, hence scaleLog <= 1 */ + const U32 minBits = nbBitsBaseline - maxWeight; + U32 s; + + assert(wkspSize >= HUF_TABLELOG_MAX + 1); + wksp += HUF_TABLELOG_MAX + 1; + wkspSize -= HUF_TABLELOG_MAX + 1; + + ZSTD_memcpy(rankVal, rankValOrigin, sizeof(U32) * (HUF_TABLELOG_MAX + 1)); + + /* fill DTable */ + for (s=0; s= minBits) { /* enough room for a second symbol */ + U32 sortedRank; + int minWeight = nbBits + scaleLog; + if (minWeight < 1) minWeight = 1; + sortedRank = rankStart[minWeight]; + HUF_fillDTableX2Level2(DTable+start, targetLog-nbBits, nbBits, + rankValOrigin[nbBits], minWeight, + sortedList+sortedRank, sortedListSize-sortedRank, + nbBitsBaseline, symbol, wksp, wkspSize); + } else { + HUF_DEltX2 DElt; + MEM_writeLE16(&(DElt.sequence), symbol); + DElt.nbBits = (BYTE)(nbBits); + DElt.length = 1; + { U32 const end = start + length; + U32 u; + for (u = start; u < end; u++) DTable[u] = DElt; + } } + rankVal[weight] += length; + } +} + +typedef struct { + rankValCol_t rankVal[HUF_TABLELOG_MAX]; + U32 rankStats[HUF_TABLELOG_MAX + 1]; + U32 rankStart0[HUF_TABLELOG_MAX + 2]; + sortedSymbol_t sortedSymbol[HUF_SYMBOLVALUE_MAX + 1]; + BYTE weightList[HUF_SYMBOLVALUE_MAX + 1]; + U32 calleeWksp[HUF_READ_STATS_WORKSPACE_SIZE_U32]; +} HUF_ReadDTableX2_Workspace; + +size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, + const void* src, size_t srcSize, + void* workSpace, size_t wkspSize) +{ + U32 tableLog, maxW, sizeOfSort, nbSymbols; + DTableDesc dtd = HUF_getDTableDesc(DTable); + U32 const maxTableLog = dtd.maxTableLog; + size_t iSize; + void* dtPtr = DTable+1; /* force compiler to avoid strict-aliasing */ + HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr; + U32 *rankStart; + + HUF_ReadDTableX2_Workspace* const wksp = (HUF_ReadDTableX2_Workspace*)workSpace; + + if (sizeof(*wksp) > wkspSize) return ERROR(GENERIC); + + rankStart = wksp->rankStart0 + 1; + ZSTD_memset(wksp->rankStats, 0, sizeof(wksp->rankStats)); + ZSTD_memset(wksp->rankStart0, 0, sizeof(wksp->rankStart0)); + + DEBUG_STATIC_ASSERT(sizeof(HUF_DEltX2) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */ + if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); + /* ZSTD_memset(weightList, 0, sizeof(weightList)); */ /* is not necessary, even though some analyzer complain ... */ + + iSize = HUF_readStats_wksp(wksp->weightList, HUF_SYMBOLVALUE_MAX + 1, wksp->rankStats, &nbSymbols, &tableLog, src, srcSize, wksp->calleeWksp, sizeof(wksp->calleeWksp), /* bmi2 */ 0); + if (HUF_isError(iSize)) return iSize; + + /* check result */ + if (tableLog > maxTableLog) return ERROR(tableLog_tooLarge); /* DTable can't fit code depth */ + + /* find maxWeight */ + for (maxW = tableLog; wksp->rankStats[maxW]==0; maxW--) {} /* necessarily finds a solution before 0 */ + + /* Get start index of each weight */ + { U32 w, nextRankStart = 0; + for (w=1; wrankStats[w]; + rankStart[w] = curr; + } + rankStart[0] = nextRankStart; /* put all 0w symbols at the end of sorted list*/ + sizeOfSort = nextRankStart; + } + + /* sort symbols by weight */ + { U32 s; + for (s=0; sweightList[s]; + U32 const r = rankStart[w]++; + wksp->sortedSymbol[r].symbol = (BYTE)s; + wksp->sortedSymbol[r].weight = (BYTE)w; + } + rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */ + } + + /* Build rankVal */ + { U32* const rankVal0 = wksp->rankVal[0]; + { int const rescale = (maxTableLog-tableLog) - 1; /* tableLog <= maxTableLog */ + U32 nextRankVal = 0; + U32 w; + for (w=1; wrankStats[w] << (w+rescale); + rankVal0[w] = curr; + } } + { U32 const minBits = tableLog+1 - maxW; + U32 consumed; + for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) { + U32* const rankValPtr = wksp->rankVal[consumed]; + U32 w; + for (w = 1; w < maxW+1; w++) { + rankValPtr[w] = rankVal0[w] >> consumed; + } } } } + + HUF_fillDTableX2(dt, maxTableLog, + wksp->sortedSymbol, sizeOfSort, + wksp->rankStart0, wksp->rankVal, maxW, + tableLog+1, + wksp->calleeWksp, sizeof(wksp->calleeWksp) / sizeof(U32)); + + dtd.tableLog = (BYTE)maxTableLog; + dtd.tableType = 1; + ZSTD_memcpy(DTable, &dtd, sizeof(dtd)); + return iSize; +} + + +FORCE_INLINE_TEMPLATE U32 +HUF_decodeSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog) +{ + size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */ + ZSTD_memcpy(op, dt+val, 2); + BIT_skipBits(DStream, dt[val].nbBits); + return dt[val].length; +} + +FORCE_INLINE_TEMPLATE U32 +HUF_decodeLastSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog) +{ + size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */ + ZSTD_memcpy(op, dt+val, 1); + if (dt[val].length==1) BIT_skipBits(DStream, dt[val].nbBits); + else { + if (DStream->bitsConsumed < (sizeof(DStream->bitContainer)*8)) { + BIT_skipBits(DStream, dt[val].nbBits); + if (DStream->bitsConsumed > (sizeof(DStream->bitContainer)*8)) + /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */ + DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8); + } } + return 1; +} + +#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) \ + ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog) + +#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr) \ + if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \ + ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog) + +#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \ + if (MEM_64bits()) \ + ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog) + +HINT_INLINE size_t +HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd, + const HUF_DEltX2* const dt, const U32 dtLog) +{ + BYTE* const pStart = p; + + /* up to 8 symbols at a time */ + while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-(sizeof(bitDPtr->bitContainer)-1))) { + HUF_DECODE_SYMBOLX2_2(p, bitDPtr); + HUF_DECODE_SYMBOLX2_1(p, bitDPtr); + HUF_DECODE_SYMBOLX2_2(p, bitDPtr); + HUF_DECODE_SYMBOLX2_0(p, bitDPtr); + } + + /* closer to end : up to 2 symbols at a time */ + while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd-2)) + HUF_DECODE_SYMBOLX2_0(p, bitDPtr); + + while (p <= pEnd-2) + HUF_DECODE_SYMBOLX2_0(p, bitDPtr); /* no need to reload : reached the end of DStream */ + + if (p < pEnd) + p += HUF_decodeLastSymbolX2(p, bitDPtr, dt, dtLog); + + return p-pStart; +} + +FORCE_INLINE_TEMPLATE size_t +HUF_decompress1X2_usingDTable_internal_body( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + BIT_DStream_t bitD; + + /* Init */ + CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) ); + + /* decode */ + { BYTE* const ostart = (BYTE*) dst; + BYTE* const oend = ostart + dstSize; + const void* const dtPtr = DTable+1; /* force compiler to not use strict-aliasing */ + const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr; + DTableDesc const dtd = HUF_getDTableDesc(DTable); + HUF_decodeStreamX2(ostart, &bitD, oend, dt, dtd.tableLog); + } + + /* check */ + if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected); + + /* decoded size */ + return dstSize; +} + +FORCE_INLINE_TEMPLATE size_t +HUF_decompress4X2_usingDTable_internal_body( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + if (cSrcSize < 10) return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */ + + { const BYTE* const istart = (const BYTE*) cSrc; + BYTE* const ostart = (BYTE*) dst; + BYTE* const oend = ostart + dstSize; + BYTE* const olimit = oend - (sizeof(size_t)-1); + const void* const dtPtr = DTable+1; + const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr; + + /* Init */ + BIT_DStream_t bitD1; + BIT_DStream_t bitD2; + BIT_DStream_t bitD3; + BIT_DStream_t bitD4; + size_t const length1 = MEM_readLE16(istart); + size_t const length2 = MEM_readLE16(istart+2); + size_t const length3 = MEM_readLE16(istart+4); + size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6); + const BYTE* const istart1 = istart + 6; /* jumpTable */ + const BYTE* const istart2 = istart1 + length1; + const BYTE* const istart3 = istart2 + length2; + const BYTE* const istart4 = istart3 + length3; + size_t const segmentSize = (dstSize+3) / 4; + BYTE* const opStart2 = ostart + segmentSize; + BYTE* const opStart3 = opStart2 + segmentSize; + BYTE* const opStart4 = opStart3 + segmentSize; + BYTE* op1 = ostart; + BYTE* op2 = opStart2; + BYTE* op3 = opStart3; + BYTE* op4 = opStart4; + U32 endSignal = 1; + DTableDesc const dtd = HUF_getDTableDesc(DTable); + U32 const dtLog = dtd.tableLog; + + if (length4 > cSrcSize) return ERROR(corruption_detected); /* overflow */ + CHECK_F( BIT_initDStream(&bitD1, istart1, length1) ); + CHECK_F( BIT_initDStream(&bitD2, istart2, length2) ); + CHECK_F( BIT_initDStream(&bitD3, istart3, length3) ); + CHECK_F( BIT_initDStream(&bitD4, istart4, length4) ); + + /* 16-32 symbols per loop (4-8 symbols per stream) */ + for ( ; (endSignal) & (op4 < olimit); ) { +#if defined(__clang__) && (defined(__x86_64__) || defined(__i386__)) + HUF_DECODE_SYMBOLX2_2(op1, &bitD1); + HUF_DECODE_SYMBOLX2_1(op1, &bitD1); + HUF_DECODE_SYMBOLX2_2(op1, &bitD1); + HUF_DECODE_SYMBOLX2_0(op1, &bitD1); + HUF_DECODE_SYMBOLX2_2(op2, &bitD2); + HUF_DECODE_SYMBOLX2_1(op2, &bitD2); + HUF_DECODE_SYMBOLX2_2(op2, &bitD2); + HUF_DECODE_SYMBOLX2_0(op2, &bitD2); + endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished; + endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished; + HUF_DECODE_SYMBOLX2_2(op3, &bitD3); + HUF_DECODE_SYMBOLX2_1(op3, &bitD3); + HUF_DECODE_SYMBOLX2_2(op3, &bitD3); + HUF_DECODE_SYMBOLX2_0(op3, &bitD3); + HUF_DECODE_SYMBOLX2_2(op4, &bitD4); + HUF_DECODE_SYMBOLX2_1(op4, &bitD4); + HUF_DECODE_SYMBOLX2_2(op4, &bitD4); + HUF_DECODE_SYMBOLX2_0(op4, &bitD4); + endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished; + endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished; +#else + HUF_DECODE_SYMBOLX2_2(op1, &bitD1); + HUF_DECODE_SYMBOLX2_2(op2, &bitD2); + HUF_DECODE_SYMBOLX2_2(op3, &bitD3); + HUF_DECODE_SYMBOLX2_2(op4, &bitD4); + HUF_DECODE_SYMBOLX2_1(op1, &bitD1); + HUF_DECODE_SYMBOLX2_1(op2, &bitD2); + HUF_DECODE_SYMBOLX2_1(op3, &bitD3); + HUF_DECODE_SYMBOLX2_1(op4, &bitD4); + HUF_DECODE_SYMBOLX2_2(op1, &bitD1); + HUF_DECODE_SYMBOLX2_2(op2, &bitD2); + HUF_DECODE_SYMBOLX2_2(op3, &bitD3); + HUF_DECODE_SYMBOLX2_2(op4, &bitD4); + HUF_DECODE_SYMBOLX2_0(op1, &bitD1); + HUF_DECODE_SYMBOLX2_0(op2, &bitD2); + HUF_DECODE_SYMBOLX2_0(op3, &bitD3); + HUF_DECODE_SYMBOLX2_0(op4, &bitD4); + endSignal = (U32)LIKELY( + (BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished) + & (BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished) + & (BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished) + & (BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished)); +#endif + } + + /* check corruption */ + if (op1 > opStart2) return ERROR(corruption_detected); + if (op2 > opStart3) return ERROR(corruption_detected); + if (op3 > opStart4) return ERROR(corruption_detected); + /* note : op4 already verified within main loop */ + + /* finish bitStreams one by one */ + HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog); + HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog); + HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog); + HUF_decodeStreamX2(op4, &bitD4, oend, dt, dtLog); + + /* check */ + { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); + if (!endCheck) return ERROR(corruption_detected); } + + /* decoded size */ + return dstSize; + } +} + +HUF_DGEN(HUF_decompress1X2_usingDTable_internal) +HUF_DGEN(HUF_decompress4X2_usingDTable_internal) + +size_t HUF_decompress1X2_usingDTable( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc dtd = HUF_getDTableDesc(DTable); + if (dtd.tableType != 1) return ERROR(GENERIC); + return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +} + +size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ + const BYTE* ip = (const BYTE*) cSrc; + + size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, + workSpace, wkspSize); + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + + return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, /* bmi2 */ 0); +} + + +size_t HUF_decompress4X2_usingDTable( + void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc dtd = HUF_getDTableDesc(DTable); + if (dtd.tableType != 1) return ERROR(GENERIC); + return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +} + +static size_t HUF_decompress4X2_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize, int bmi2) +{ + const BYTE* ip = (const BYTE*) cSrc; + + size_t hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize, + workSpace, wkspSize); + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + + return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2); +} + +size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ + return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, /* bmi2 */ 0); +} + + +#endif /* HUF_FORCE_DECOMPRESS_X1 */ + + +/* ***********************************/ +/* Universal decompression selectors */ +/* ***********************************/ + +size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc const dtd = HUF_getDTableDesc(DTable); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)dtd; + assert(dtd.tableType == 0); + return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)dtd; + assert(dtd.tableType == 1); + return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +#else + return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) : + HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +#endif +} + +size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, + const void* cSrc, size_t cSrcSize, + const HUF_DTable* DTable) +{ + DTableDesc const dtd = HUF_getDTableDesc(DTable); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)dtd; + assert(dtd.tableType == 0); + return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)dtd; + assert(dtd.tableType == 1); + return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +#else + return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0) : + HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, /* bmi2 */ 0); +#endif +} + + +#if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2) +typedef struct { U32 tableTime; U32 decode256Time; } algo_time_t; +static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] = +{ + /* single, double, quad */ + {{0,0}, {1,1}, {2,2}}, /* Q==0 : impossible */ + {{0,0}, {1,1}, {2,2}}, /* Q==1 : impossible */ + {{ 38,130}, {1313, 74}, {2151, 38}}, /* Q == 2 : 12-18% */ + {{ 448,128}, {1353, 74}, {2238, 41}}, /* Q == 3 : 18-25% */ + {{ 556,128}, {1353, 74}, {2238, 47}}, /* Q == 4 : 25-32% */ + {{ 714,128}, {1418, 74}, {2436, 53}}, /* Q == 5 : 32-38% */ + {{ 883,128}, {1437, 74}, {2464, 61}}, /* Q == 6 : 38-44% */ + {{ 897,128}, {1515, 75}, {2622, 68}}, /* Q == 7 : 44-50% */ + {{ 926,128}, {1613, 75}, {2730, 75}}, /* Q == 8 : 50-56% */ + {{ 947,128}, {1729, 77}, {3359, 77}}, /* Q == 9 : 56-62% */ + {{1107,128}, {2083, 81}, {4006, 84}}, /* Q ==10 : 62-69% */ + {{1177,128}, {2379, 87}, {4785, 88}}, /* Q ==11 : 69-75% */ + {{1242,128}, {2415, 93}, {5155, 84}}, /* Q ==12 : 75-81% */ + {{1349,128}, {2644,106}, {5260,106}}, /* Q ==13 : 81-87% */ + {{1455,128}, {2422,124}, {4174,124}}, /* Q ==14 : 87-93% */ + {{ 722,128}, {1891,145}, {1936,146}}, /* Q ==15 : 93-99% */ +}; +#endif + +/* HUF_selectDecoder() : + * Tells which decoder is likely to decode faster, + * based on a set of pre-computed metrics. + * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 . + * Assumption : 0 < dstSize <= 128 KB */ +U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize) +{ + assert(dstSize > 0); + assert(dstSize <= 128*1024); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)dstSize; + (void)cSrcSize; + return 0; +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)dstSize; + (void)cSrcSize; + return 1; +#else + /* decoder timing evaluation */ + { U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize); /* Q < 16 */ + U32 const D256 = (U32)(dstSize >> 8); + U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256); + U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256); + DTime1 += DTime1 >> 3; /* advantage to algorithm using less memory, to reduce cache eviction */ + return DTime1 < DTime0; + } +#endif +} + + +size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, + size_t dstSize, const void* cSrc, + size_t cSrcSize, void* workSpace, + size_t wkspSize) +{ + /* validation checks */ + if (dstSize == 0) return ERROR(dstSize_tooSmall); + if (cSrcSize == 0) return ERROR(corruption_detected); + + { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)algoNb; + assert(algoNb == 0); + return HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)algoNb; + assert(algoNb == 1); + return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize); +#else + return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, + cSrcSize, workSpace, wkspSize): + HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize); +#endif + } +} + +size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, + const void* cSrc, size_t cSrcSize, + void* workSpace, size_t wkspSize) +{ + /* validation checks */ + if (dstSize == 0) return ERROR(dstSize_tooSmall); + if (cSrcSize > dstSize) return ERROR(corruption_detected); /* invalid */ + if (cSrcSize == dstSize) { ZSTD_memcpy(dst, cSrc, dstSize); return dstSize; } /* not compressed */ + if (cSrcSize == 1) { ZSTD_memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; } /* RLE */ + + { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)algoNb; + assert(algoNb == 0); + return HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc, + cSrcSize, workSpace, wkspSize); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)algoNb; + assert(algoNb == 1); + return HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, + cSrcSize, workSpace, wkspSize); +#else + return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, + cSrcSize, workSpace, wkspSize): + HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc, + cSrcSize, workSpace, wkspSize); +#endif + } +} + + +size_t HUF_decompress1X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2) +{ + DTableDesc const dtd = HUF_getDTableDesc(DTable); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)dtd; + assert(dtd.tableType == 0); + return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)dtd; + assert(dtd.tableType == 1); + return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); +#else + return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) : + HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); +#endif +} + +#ifndef HUF_FORCE_DECOMPRESS_X2 +size_t HUF_decompress1X1_DCtx_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2) +{ + const BYTE* ip = (const BYTE*) cSrc; + + size_t const hSize = HUF_readDTableX1_wksp_bmi2(dctx, cSrc, cSrcSize, workSpace, wkspSize, bmi2); + if (HUF_isError(hSize)) return hSize; + if (hSize >= cSrcSize) return ERROR(srcSize_wrong); + ip += hSize; cSrcSize -= hSize; + + return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, bmi2); +} +#endif + +size_t HUF_decompress4X_usingDTable_bmi2(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int bmi2) +{ + DTableDesc const dtd = HUF_getDTableDesc(DTable); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)dtd; + assert(dtd.tableType == 0); + return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)dtd; + assert(dtd.tableType == 1); + return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); +#else + return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2) : + HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, bmi2); +#endif +} + +size_t HUF_decompress4X_hufOnly_wksp_bmi2(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int bmi2) +{ + /* validation checks */ + if (dstSize == 0) return ERROR(dstSize_tooSmall); + if (cSrcSize == 0) return ERROR(corruption_detected); + + { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); +#if defined(HUF_FORCE_DECOMPRESS_X1) + (void)algoNb; + assert(algoNb == 0); + return HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2); +#elif defined(HUF_FORCE_DECOMPRESS_X2) + (void)algoNb; + assert(algoNb == 1); + return HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2); +#else + return algoNb ? HUF_decompress4X2_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2) : + HUF_decompress4X1_DCtx_wksp_bmi2(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, bmi2); +#endif + } +} + diff --git a/lib/zstd/decompress/zstd_ddict.c b/lib/zstd/decompress/zstd_ddict.c new file mode 100644 index 000000000000..dbbc7919de53 --- /dev/null +++ b/lib/zstd/decompress/zstd_ddict.c @@ -0,0 +1,241 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* zstd_ddict.c : + * concentrates all logic that needs to know the internals of ZSTD_DDict object */ + +/*-******************************************************* +* Dependencies +*********************************************************/ +#include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */ +#include "../common/cpu.h" /* bmi2 */ +#include "../common/mem.h" /* low level memory routines */ +#define FSE_STATIC_LINKING_ONLY +#include "../common/fse.h" +#define HUF_STATIC_LINKING_ONLY +#include "../common/huf.h" +#include "zstd_decompress_internal.h" +#include "zstd_ddict.h" + + + + +/*-******************************************************* +* Types +*********************************************************/ +struct ZSTD_DDict_s { + void* dictBuffer; + const void* dictContent; + size_t dictSize; + ZSTD_entropyDTables_t entropy; + U32 dictID; + U32 entropyPresent; + ZSTD_customMem cMem; +}; /* typedef'd to ZSTD_DDict within "zstd.h" */ + +const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict) +{ + assert(ddict != NULL); + return ddict->dictContent; +} + +size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict) +{ + assert(ddict != NULL); + return ddict->dictSize; +} + +void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) +{ + DEBUGLOG(4, "ZSTD_copyDDictParameters"); + assert(dctx != NULL); + assert(ddict != NULL); + dctx->dictID = ddict->dictID; + dctx->prefixStart = ddict->dictContent; + dctx->virtualStart = ddict->dictContent; + dctx->dictEnd = (const BYTE*)ddict->dictContent + ddict->dictSize; + dctx->previousDstEnd = dctx->dictEnd; +#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + dctx->dictContentBeginForFuzzing = dctx->prefixStart; + dctx->dictContentEndForFuzzing = dctx->previousDstEnd; +#endif + if (ddict->entropyPresent) { + dctx->litEntropy = 1; + dctx->fseEntropy = 1; + dctx->LLTptr = ddict->entropy.LLTable; + dctx->MLTptr = ddict->entropy.MLTable; + dctx->OFTptr = ddict->entropy.OFTable; + dctx->HUFptr = ddict->entropy.hufTable; + dctx->entropy.rep[0] = ddict->entropy.rep[0]; + dctx->entropy.rep[1] = ddict->entropy.rep[1]; + dctx->entropy.rep[2] = ddict->entropy.rep[2]; + } else { + dctx->litEntropy = 0; + dctx->fseEntropy = 0; + } +} + + +static size_t +ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict, + ZSTD_dictContentType_e dictContentType) +{ + ddict->dictID = 0; + ddict->entropyPresent = 0; + if (dictContentType == ZSTD_dct_rawContent) return 0; + + if (ddict->dictSize < 8) { + if (dictContentType == ZSTD_dct_fullDict) + return ERROR(dictionary_corrupted); /* only accept specified dictionaries */ + return 0; /* pure content mode */ + } + { U32 const magic = MEM_readLE32(ddict->dictContent); + if (magic != ZSTD_MAGIC_DICTIONARY) { + if (dictContentType == ZSTD_dct_fullDict) + return ERROR(dictionary_corrupted); /* only accept specified dictionaries */ + return 0; /* pure content mode */ + } + } + ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE); + + /* load entropy tables */ + RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy( + &ddict->entropy, ddict->dictContent, ddict->dictSize)), + dictionary_corrupted, ""); + ddict->entropyPresent = 1; + return 0; +} + + +static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType) +{ + if ((dictLoadMethod == ZSTD_dlm_byRef) || (!dict) || (!dictSize)) { + ddict->dictBuffer = NULL; + ddict->dictContent = dict; + if (!dict) dictSize = 0; + } else { + void* const internalBuffer = ZSTD_customMalloc(dictSize, ddict->cMem); + ddict->dictBuffer = internalBuffer; + ddict->dictContent = internalBuffer; + if (!internalBuffer) return ERROR(memory_allocation); + ZSTD_memcpy(internalBuffer, dict, dictSize); + } + ddict->dictSize = dictSize; + ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ + + /* parse dictionary content */ + FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) , ""); + + return 0; +} + +ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType, + ZSTD_customMem customMem) +{ + if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; + + { ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_customMalloc(sizeof(ZSTD_DDict), customMem); + if (ddict == NULL) return NULL; + ddict->cMem = customMem; + { size_t const initResult = ZSTD_initDDict_internal(ddict, + dict, dictSize, + dictLoadMethod, dictContentType); + if (ZSTD_isError(initResult)) { + ZSTD_freeDDict(ddict); + return NULL; + } } + return ddict; + } +} + +/*! ZSTD_createDDict() : +* Create a digested dictionary, to start decompression without startup delay. +* `dict` content is copied inside DDict. +* Consequently, `dict` can be released after `ZSTD_DDict` creation */ +ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize) +{ + ZSTD_customMem const allocator = { NULL, NULL, NULL }; + return ZSTD_createDDict_advanced(dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto, allocator); +} + +/*! ZSTD_createDDict_byReference() : + * Create a digested dictionary, to start decompression without startup delay. + * Dictionary content is simply referenced, it will be accessed during decompression. + * Warning : dictBuffer must outlive DDict (DDict must be freed before dictBuffer) */ +ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize) +{ + ZSTD_customMem const allocator = { NULL, NULL, NULL }; + return ZSTD_createDDict_advanced(dictBuffer, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto, allocator); +} + + +const ZSTD_DDict* ZSTD_initStaticDDict( + void* sBuffer, size_t sBufferSize, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType) +{ + size_t const neededSpace = sizeof(ZSTD_DDict) + + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize); + ZSTD_DDict* const ddict = (ZSTD_DDict*)sBuffer; + assert(sBuffer != NULL); + assert(dict != NULL); + if ((size_t)sBuffer & 7) return NULL; /* 8-aligned */ + if (sBufferSize < neededSpace) return NULL; + if (dictLoadMethod == ZSTD_dlm_byCopy) { + ZSTD_memcpy(ddict+1, dict, dictSize); /* local copy */ + dict = ddict+1; + } + if (ZSTD_isError( ZSTD_initDDict_internal(ddict, + dict, dictSize, + ZSTD_dlm_byRef, dictContentType) )) + return NULL; + return ddict; +} + + +size_t ZSTD_freeDDict(ZSTD_DDict* ddict) +{ + if (ddict==NULL) return 0; /* support free on NULL */ + { ZSTD_customMem const cMem = ddict->cMem; + ZSTD_customFree(ddict->dictBuffer, cMem); + ZSTD_customFree(ddict, cMem); + return 0; + } +} + +/*! ZSTD_estimateDDictSize() : + * Estimate amount of memory that will be needed to create a dictionary for decompression. + * Note : dictionary created by reference using ZSTD_dlm_byRef are smaller */ +size_t ZSTD_estimateDDictSize(size_t dictSize, ZSTD_dictLoadMethod_e dictLoadMethod) +{ + return sizeof(ZSTD_DDict) + (dictLoadMethod == ZSTD_dlm_byRef ? 0 : dictSize); +} + +size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict) +{ + if (ddict==NULL) return 0; /* support sizeof on NULL */ + return sizeof(*ddict) + (ddict->dictBuffer ? ddict->dictSize : 0) ; +} + +/*! ZSTD_getDictID_fromDDict() : + * Provides the dictID of the dictionary loaded into `ddict`. + * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. + * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ +unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict) +{ + if (ddict==NULL) return 0; + return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize); +} diff --git a/lib/zstd/decompress/zstd_ddict.h b/lib/zstd/decompress/zstd_ddict.h new file mode 100644 index 000000000000..8c1a79d666f8 --- /dev/null +++ b/lib/zstd/decompress/zstd_ddict.h @@ -0,0 +1,44 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +#ifndef ZSTD_DDICT_H +#define ZSTD_DDICT_H + +/*-******************************************************* + * Dependencies + *********************************************************/ +#include "../common/zstd_deps.h" /* size_t */ +#include /* ZSTD_DDict, and several public functions */ + + +/*-******************************************************* + * Interface + *********************************************************/ + +/* note: several prototypes are already published in `zstd.h` : + * ZSTD_createDDict() + * ZSTD_createDDict_byReference() + * ZSTD_createDDict_advanced() + * ZSTD_freeDDict() + * ZSTD_initStaticDDict() + * ZSTD_sizeof_DDict() + * ZSTD_estimateDDictSize() + * ZSTD_getDictID_fromDict() + */ + +const void* ZSTD_DDict_dictContent(const ZSTD_DDict* ddict); +size_t ZSTD_DDict_dictSize(const ZSTD_DDict* ddict); + +void ZSTD_copyDDictParameters(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict); + + + +#endif /* ZSTD_DDICT_H */ diff --git a/lib/zstd/decompress/zstd_decompress.c b/lib/zstd/decompress/zstd_decompress.c new file mode 100644 index 000000000000..b4d81d84479a --- /dev/null +++ b/lib/zstd/decompress/zstd_decompress.c @@ -0,0 +1,2085 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +/* *************************************************************** +* Tuning parameters +*****************************************************************/ +/*! + * HEAPMODE : + * Select how default decompression function ZSTD_decompress() allocates its context, + * on stack (0), or into heap (1, default; requires malloc()). + * Note that functions with explicit context such as ZSTD_decompressDCtx() are unaffected. + */ +#ifndef ZSTD_HEAPMODE +# define ZSTD_HEAPMODE 1 +#endif + +/*! +* LEGACY_SUPPORT : +* if set to 1+, ZSTD_decompress() can decode older formats (v0.1+) +*/ + +/*! + * MAXWINDOWSIZE_DEFAULT : + * maximum window size accepted by DStream __by default__. + * Frames requiring more memory will be rejected. + * It's possible to set a different limit using ZSTD_DCtx_setMaxWindowSize(). + */ +#ifndef ZSTD_MAXWINDOWSIZE_DEFAULT +# define ZSTD_MAXWINDOWSIZE_DEFAULT (((U32)1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) + 1) +#endif + +/*! + * NO_FORWARD_PROGRESS_MAX : + * maximum allowed nb of calls to ZSTD_decompressStream() + * without any forward progress + * (defined as: no byte read from input, and no byte flushed to output) + * before triggering an error. + */ +#ifndef ZSTD_NO_FORWARD_PROGRESS_MAX +# define ZSTD_NO_FORWARD_PROGRESS_MAX 16 +#endif + + +/*-******************************************************* +* Dependencies +*********************************************************/ +#include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */ +#include "../common/cpu.h" /* bmi2 */ +#include "../common/mem.h" /* low level memory routines */ +#define FSE_STATIC_LINKING_ONLY +#include "../common/fse.h" +#define HUF_STATIC_LINKING_ONLY +#include "../common/huf.h" +#include /* xxh64_reset, xxh64_update, xxh64_digest, XXH64 */ +#include "../common/zstd_internal.h" /* blockProperties_t */ +#include "zstd_decompress_internal.h" /* ZSTD_DCtx */ +#include "zstd_ddict.h" /* ZSTD_DDictDictContent */ +#include "zstd_decompress_block.h" /* ZSTD_decompressBlock_internal */ + + + + +/* *********************************** + * Multiple DDicts Hashset internals * + *************************************/ + +#define DDICT_HASHSET_MAX_LOAD_FACTOR_COUNT_MULT 4 +#define DDICT_HASHSET_MAX_LOAD_FACTOR_SIZE_MULT 3 /* These two constants represent SIZE_MULT/COUNT_MULT load factor without using a float. + * Currently, that means a 0.75 load factor. + * So, if count * COUNT_MULT / size * SIZE_MULT != 0, then we've exceeded + * the load factor of the ddict hash set. + */ + +#define DDICT_HASHSET_TABLE_BASE_SIZE 64 +#define DDICT_HASHSET_RESIZE_FACTOR 2 + +/* Hash function to determine starting position of dict insertion within the table + * Returns an index between [0, hashSet->ddictPtrTableSize] + */ +static size_t ZSTD_DDictHashSet_getIndex(const ZSTD_DDictHashSet* hashSet, U32 dictID) { + const U64 hash = xxh64(&dictID, sizeof(U32), 0); + /* DDict ptr table size is a multiple of 2, use size - 1 as mask to get index within [0, hashSet->ddictPtrTableSize) */ + return hash & (hashSet->ddictPtrTableSize - 1); +} + +/* Adds DDict to a hashset without resizing it. + * If inserting a DDict with a dictID that already exists in the set, replaces the one in the set. + * Returns 0 if successful, or a zstd error code if something went wrong. + */ +static size_t ZSTD_DDictHashSet_emplaceDDict(ZSTD_DDictHashSet* hashSet, const ZSTD_DDict* ddict) { + const U32 dictID = ZSTD_getDictID_fromDDict(ddict); + size_t idx = ZSTD_DDictHashSet_getIndex(hashSet, dictID); + const size_t idxRangeMask = hashSet->ddictPtrTableSize - 1; + RETURN_ERROR_IF(hashSet->ddictPtrCount == hashSet->ddictPtrTableSize, GENERIC, "Hash set is full!"); + DEBUGLOG(4, "Hashed index: for dictID: %u is %zu", dictID, idx); + while (hashSet->ddictPtrTable[idx] != NULL) { + /* Replace existing ddict if inserting ddict with same dictID */ + if (ZSTD_getDictID_fromDDict(hashSet->ddictPtrTable[idx]) == dictID) { + DEBUGLOG(4, "DictID already exists, replacing rather than adding"); + hashSet->ddictPtrTable[idx] = ddict; + return 0; + } + idx &= idxRangeMask; + idx++; + } + DEBUGLOG(4, "Final idx after probing for dictID %u is: %zu", dictID, idx); + hashSet->ddictPtrTable[idx] = ddict; + hashSet->ddictPtrCount++; + return 0; +} + +/* Expands hash table by factor of DDICT_HASHSET_RESIZE_FACTOR and + * rehashes all values, allocates new table, frees old table. + * Returns 0 on success, otherwise a zstd error code. + */ +static size_t ZSTD_DDictHashSet_expand(ZSTD_DDictHashSet* hashSet, ZSTD_customMem customMem) { + size_t newTableSize = hashSet->ddictPtrTableSize * DDICT_HASHSET_RESIZE_FACTOR; + const ZSTD_DDict** newTable = (const ZSTD_DDict**)ZSTD_customCalloc(sizeof(ZSTD_DDict*) * newTableSize, customMem); + const ZSTD_DDict** oldTable = hashSet->ddictPtrTable; + size_t oldTableSize = hashSet->ddictPtrTableSize; + size_t i; + + DEBUGLOG(4, "Expanding DDict hash table! Old size: %zu new size: %zu", oldTableSize, newTableSize); + RETURN_ERROR_IF(!newTable, memory_allocation, "Expanded hashset allocation failed!"); + hashSet->ddictPtrTable = newTable; + hashSet->ddictPtrTableSize = newTableSize; + hashSet->ddictPtrCount = 0; + for (i = 0; i < oldTableSize; ++i) { + if (oldTable[i] != NULL) { + FORWARD_IF_ERROR(ZSTD_DDictHashSet_emplaceDDict(hashSet, oldTable[i]), ""); + } + } + ZSTD_customFree((void*)oldTable, customMem); + DEBUGLOG(4, "Finished re-hash"); + return 0; +} + +/* Fetches a DDict with the given dictID + * Returns the ZSTD_DDict* with the requested dictID. If it doesn't exist, then returns NULL. + */ +static const ZSTD_DDict* ZSTD_DDictHashSet_getDDict(ZSTD_DDictHashSet* hashSet, U32 dictID) { + size_t idx = ZSTD_DDictHashSet_getIndex(hashSet, dictID); + const size_t idxRangeMask = hashSet->ddictPtrTableSize - 1; + DEBUGLOG(4, "Hashed index: for dictID: %u is %zu", dictID, idx); + for (;;) { + size_t currDictID = ZSTD_getDictID_fromDDict(hashSet->ddictPtrTable[idx]); + if (currDictID == dictID || currDictID == 0) { + /* currDictID == 0 implies a NULL ddict entry */ + break; + } else { + idx &= idxRangeMask; /* Goes to start of table when we reach the end */ + idx++; + } + } + DEBUGLOG(4, "Final idx after probing for dictID %u is: %zu", dictID, idx); + return hashSet->ddictPtrTable[idx]; +} + +/* Allocates space for and returns a ddict hash set + * The hash set's ZSTD_DDict* table has all values automatically set to NULL to begin with. + * Returns NULL if allocation failed. + */ +static ZSTD_DDictHashSet* ZSTD_createDDictHashSet(ZSTD_customMem customMem) { + ZSTD_DDictHashSet* ret = (ZSTD_DDictHashSet*)ZSTD_customMalloc(sizeof(ZSTD_DDictHashSet), customMem); + DEBUGLOG(4, "Allocating new hash set"); + if (!ret) + return NULL; + ret->ddictPtrTable = (const ZSTD_DDict**)ZSTD_customCalloc(DDICT_HASHSET_TABLE_BASE_SIZE * sizeof(ZSTD_DDict*), customMem); + if (!ret->ddictPtrTable) { + ZSTD_customFree(ret, customMem); + return NULL; + } + ret->ddictPtrTableSize = DDICT_HASHSET_TABLE_BASE_SIZE; + ret->ddictPtrCount = 0; + return ret; +} + +/* Frees the table of ZSTD_DDict* within a hashset, then frees the hashset itself. + * Note: The ZSTD_DDict* within the table are NOT freed. + */ +static void ZSTD_freeDDictHashSet(ZSTD_DDictHashSet* hashSet, ZSTD_customMem customMem) { + DEBUGLOG(4, "Freeing ddict hash set"); + if (hashSet && hashSet->ddictPtrTable) { + ZSTD_customFree((void*)hashSet->ddictPtrTable, customMem); + } + if (hashSet) { + ZSTD_customFree(hashSet, customMem); + } +} + +/* Public function: Adds a DDict into the ZSTD_DDictHashSet, possibly triggering a resize of the hash set. + * Returns 0 on success, or a ZSTD error. + */ +static size_t ZSTD_DDictHashSet_addDDict(ZSTD_DDictHashSet* hashSet, const ZSTD_DDict* ddict, ZSTD_customMem customMem) { + DEBUGLOG(4, "Adding dict ID: %u to hashset with - Count: %zu Tablesize: %zu", ZSTD_getDictID_fromDDict(ddict), hashSet->ddictPtrCount, hashSet->ddictPtrTableSize); + if (hashSet->ddictPtrCount * DDICT_HASHSET_MAX_LOAD_FACTOR_COUNT_MULT / hashSet->ddictPtrTableSize * DDICT_HASHSET_MAX_LOAD_FACTOR_SIZE_MULT != 0) { + FORWARD_IF_ERROR(ZSTD_DDictHashSet_expand(hashSet, customMem), ""); + } + FORWARD_IF_ERROR(ZSTD_DDictHashSet_emplaceDDict(hashSet, ddict), ""); + return 0; +} + +/*-************************************************************* +* Context management +***************************************************************/ +size_t ZSTD_sizeof_DCtx (const ZSTD_DCtx* dctx) +{ + if (dctx==NULL) return 0; /* support sizeof NULL */ + return sizeof(*dctx) + + ZSTD_sizeof_DDict(dctx->ddictLocal) + + dctx->inBuffSize + dctx->outBuffSize; +} + +size_t ZSTD_estimateDCtxSize(void) { return sizeof(ZSTD_DCtx); } + + +static size_t ZSTD_startingInputLength(ZSTD_format_e format) +{ + size_t const startingInputLength = ZSTD_FRAMEHEADERSIZE_PREFIX(format); + /* only supports formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless */ + assert( (format == ZSTD_f_zstd1) || (format == ZSTD_f_zstd1_magicless) ); + return startingInputLength; +} + +static void ZSTD_DCtx_resetParameters(ZSTD_DCtx* dctx) +{ + assert(dctx->streamStage == zdss_init); + dctx->format = ZSTD_f_zstd1; + dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT; + dctx->outBufferMode = ZSTD_bm_buffered; + dctx->forceIgnoreChecksum = ZSTD_d_validateChecksum; + dctx->refMultipleDDicts = ZSTD_rmd_refSingleDDict; +} + +static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx) +{ + dctx->staticSize = 0; + dctx->ddict = NULL; + dctx->ddictLocal = NULL; + dctx->dictEnd = NULL; + dctx->ddictIsCold = 0; + dctx->dictUses = ZSTD_dont_use; + dctx->inBuff = NULL; + dctx->inBuffSize = 0; + dctx->outBuffSize = 0; + dctx->streamStage = zdss_init; + dctx->legacyContext = NULL; + dctx->previousLegacyVersion = 0; + dctx->noForwardProgress = 0; + dctx->oversizedDuration = 0; + dctx->bmi2 = ZSTD_cpuid_bmi2(ZSTD_cpuid()); + dctx->ddictSet = NULL; + ZSTD_DCtx_resetParameters(dctx); +#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + dctx->dictContentEndForFuzzing = NULL; +#endif +} + +ZSTD_DCtx* ZSTD_initStaticDCtx(void *workspace, size_t workspaceSize) +{ + ZSTD_DCtx* const dctx = (ZSTD_DCtx*) workspace; + + if ((size_t)workspace & 7) return NULL; /* 8-aligned */ + if (workspaceSize < sizeof(ZSTD_DCtx)) return NULL; /* minimum size */ + + ZSTD_initDCtx_internal(dctx); + dctx->staticSize = workspaceSize; + dctx->inBuff = (char*)(dctx+1); + return dctx; +} + +ZSTD_DCtx* ZSTD_createDCtx_advanced(ZSTD_customMem customMem) +{ + if ((!customMem.customAlloc) ^ (!customMem.customFree)) return NULL; + + { ZSTD_DCtx* const dctx = (ZSTD_DCtx*)ZSTD_customMalloc(sizeof(*dctx), customMem); + if (!dctx) return NULL; + dctx->customMem = customMem; + ZSTD_initDCtx_internal(dctx); + return dctx; + } +} + +ZSTD_DCtx* ZSTD_createDCtx(void) +{ + DEBUGLOG(3, "ZSTD_createDCtx"); + return ZSTD_createDCtx_advanced(ZSTD_defaultCMem); +} + +static void ZSTD_clearDict(ZSTD_DCtx* dctx) +{ + ZSTD_freeDDict(dctx->ddictLocal); + dctx->ddictLocal = NULL; + dctx->ddict = NULL; + dctx->dictUses = ZSTD_dont_use; +} + +size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx) +{ + if (dctx==NULL) return 0; /* support free on NULL */ + RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx"); + { ZSTD_customMem const cMem = dctx->customMem; + ZSTD_clearDict(dctx); + ZSTD_customFree(dctx->inBuff, cMem); + dctx->inBuff = NULL; + if (dctx->ddictSet) { + ZSTD_freeDDictHashSet(dctx->ddictSet, cMem); + dctx->ddictSet = NULL; + } + ZSTD_customFree(dctx, cMem); + return 0; + } +} + +/* no longer useful */ +void ZSTD_copyDCtx(ZSTD_DCtx* dstDCtx, const ZSTD_DCtx* srcDCtx) +{ + size_t const toCopy = (size_t)((char*)(&dstDCtx->inBuff) - (char*)dstDCtx); + ZSTD_memcpy(dstDCtx, srcDCtx, toCopy); /* no need to copy workspace */ +} + +/* Given a dctx with a digested frame params, re-selects the correct ZSTD_DDict based on + * the requested dict ID from the frame. If there exists a reference to the correct ZSTD_DDict, then + * accordingly sets the ddict to be used to decompress the frame. + * + * If no DDict is found, then no action is taken, and the ZSTD_DCtx::ddict remains as-is. + * + * ZSTD_d_refMultipleDDicts must be enabled for this function to be called. + */ +static void ZSTD_DCtx_selectFrameDDict(ZSTD_DCtx* dctx) { + assert(dctx->refMultipleDDicts && dctx->ddictSet); + DEBUGLOG(4, "Adjusting DDict based on requested dict ID from frame"); + if (dctx->ddict) { + const ZSTD_DDict* frameDDict = ZSTD_DDictHashSet_getDDict(dctx->ddictSet, dctx->fParams.dictID); + if (frameDDict) { + DEBUGLOG(4, "DDict found!"); + ZSTD_clearDict(dctx); + dctx->dictID = dctx->fParams.dictID; + dctx->ddict = frameDDict; + dctx->dictUses = ZSTD_use_indefinitely; + } + } +} + + +/*-************************************************************* + * Frame header decoding + ***************************************************************/ + +/*! ZSTD_isFrame() : + * Tells if the content of `buffer` starts with a valid Frame Identifier. + * Note : Frame Identifier is 4 bytes. If `size < 4`, @return will always be 0. + * Note 2 : Legacy Frame Identifiers are considered valid only if Legacy Support is enabled. + * Note 3 : Skippable Frame Identifiers are considered valid. */ +unsigned ZSTD_isFrame(const void* buffer, size_t size) +{ + if (size < ZSTD_FRAMEIDSIZE) return 0; + { U32 const magic = MEM_readLE32(buffer); + if (magic == ZSTD_MAGICNUMBER) return 1; + if ((magic & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) return 1; + } + return 0; +} + +/* ZSTD_frameHeaderSize_internal() : + * srcSize must be large enough to reach header size fields. + * note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless. + * @return : size of the Frame Header + * or an error code, which can be tested with ZSTD_isError() */ +static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format) +{ + size_t const minInputSize = ZSTD_startingInputLength(format); + RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong, ""); + + { BYTE const fhd = ((const BYTE*)src)[minInputSize-1]; + U32 const dictID= fhd & 3; + U32 const singleSegment = (fhd >> 5) & 1; + U32 const fcsId = fhd >> 6; + return minInputSize + !singleSegment + + ZSTD_did_fieldSize[dictID] + ZSTD_fcs_fieldSize[fcsId] + + (singleSegment && !fcsId); + } +} + +/* ZSTD_frameHeaderSize() : + * srcSize must be >= ZSTD_frameHeaderSize_prefix. + * @return : size of the Frame Header, + * or an error code (if srcSize is too small) */ +size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize) +{ + return ZSTD_frameHeaderSize_internal(src, srcSize, ZSTD_f_zstd1); +} + + +/* ZSTD_getFrameHeader_advanced() : + * decode Frame Header, or require larger `srcSize`. + * note : only works for formats ZSTD_f_zstd1 and ZSTD_f_zstd1_magicless + * @return : 0, `zfhPtr` is correctly filled, + * >0, `srcSize` is too small, value is wanted `srcSize` amount, + * or an error code, which can be tested using ZSTD_isError() */ +size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize, ZSTD_format_e format) +{ + const BYTE* ip = (const BYTE*)src; + size_t const minInputSize = ZSTD_startingInputLength(format); + + ZSTD_memset(zfhPtr, 0, sizeof(*zfhPtr)); /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */ + if (srcSize < minInputSize) return minInputSize; + RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter"); + + if ( (format != ZSTD_f_zstd1_magicless) + && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) { + if ((MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { + /* skippable frame */ + if (srcSize < ZSTD_SKIPPABLEHEADERSIZE) + return ZSTD_SKIPPABLEHEADERSIZE; /* magic number + frame length */ + ZSTD_memset(zfhPtr, 0, sizeof(*zfhPtr)); + zfhPtr->frameContentSize = MEM_readLE32((const char *)src + ZSTD_FRAMEIDSIZE); + zfhPtr->frameType = ZSTD_skippableFrame; + return 0; + } + RETURN_ERROR(prefix_unknown, ""); + } + + /* ensure there is enough `srcSize` to fully read/decode frame header */ + { size_t const fhsize = ZSTD_frameHeaderSize_internal(src, srcSize, format); + if (srcSize < fhsize) return fhsize; + zfhPtr->headerSize = (U32)fhsize; + } + + { BYTE const fhdByte = ip[minInputSize-1]; + size_t pos = minInputSize; + U32 const dictIDSizeCode = fhdByte&3; + U32 const checksumFlag = (fhdByte>>2)&1; + U32 const singleSegment = (fhdByte>>5)&1; + U32 const fcsID = fhdByte>>6; + U64 windowSize = 0; + U32 dictID = 0; + U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN; + RETURN_ERROR_IF((fhdByte & 0x08) != 0, frameParameter_unsupported, + "reserved bits, must be zero"); + + if (!singleSegment) { + BYTE const wlByte = ip[pos++]; + U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN; + RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge, ""); + windowSize = (1ULL << windowLog); + windowSize += (windowSize >> 3) * (wlByte&7); + } + switch(dictIDSizeCode) + { + default: + assert(0); /* impossible */ + ZSTD_FALLTHROUGH; + case 0 : break; + case 1 : dictID = ip[pos]; pos++; break; + case 2 : dictID = MEM_readLE16(ip+pos); pos+=2; break; + case 3 : dictID = MEM_readLE32(ip+pos); pos+=4; break; + } + switch(fcsID) + { + default: + assert(0); /* impossible */ + ZSTD_FALLTHROUGH; + case 0 : if (singleSegment) frameContentSize = ip[pos]; break; + case 1 : frameContentSize = MEM_readLE16(ip+pos)+256; break; + case 2 : frameContentSize = MEM_readLE32(ip+pos); break; + case 3 : frameContentSize = MEM_readLE64(ip+pos); break; + } + if (singleSegment) windowSize = frameContentSize; + + zfhPtr->frameType = ZSTD_frame; + zfhPtr->frameContentSize = frameContentSize; + zfhPtr->windowSize = windowSize; + zfhPtr->blockSizeMax = (unsigned) MIN(windowSize, ZSTD_BLOCKSIZE_MAX); + zfhPtr->dictID = dictID; + zfhPtr->checksumFlag = checksumFlag; + } + return 0; +} + +/* ZSTD_getFrameHeader() : + * decode Frame Header, or require larger `srcSize`. + * note : this function does not consume input, it only reads it. + * @return : 0, `zfhPtr` is correctly filled, + * >0, `srcSize` is too small, value is wanted `srcSize` amount, + * or an error code, which can be tested using ZSTD_isError() */ +size_t ZSTD_getFrameHeader(ZSTD_frameHeader* zfhPtr, const void* src, size_t srcSize) +{ + return ZSTD_getFrameHeader_advanced(zfhPtr, src, srcSize, ZSTD_f_zstd1); +} + + +/* ZSTD_getFrameContentSize() : + * compatible with legacy mode + * @return : decompressed size of the single frame pointed to be `src` if known, otherwise + * - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined + * - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */ +unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize) +{ + { ZSTD_frameHeader zfh; + if (ZSTD_getFrameHeader(&zfh, src, srcSize) != 0) + return ZSTD_CONTENTSIZE_ERROR; + if (zfh.frameType == ZSTD_skippableFrame) { + return 0; + } else { + return zfh.frameContentSize; + } } +} + +static size_t readSkippableFrameSize(void const* src, size_t srcSize) +{ + size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE; + U32 sizeU32; + + RETURN_ERROR_IF(srcSize < ZSTD_SKIPPABLEHEADERSIZE, srcSize_wrong, ""); + + sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE); + RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32, + frameParameter_unsupported, ""); + { + size_t const skippableSize = skippableHeaderSize + sizeU32; + RETURN_ERROR_IF(skippableSize > srcSize, srcSize_wrong, ""); + return skippableSize; + } +} + +/* ZSTD_findDecompressedSize() : + * compatible with legacy mode + * `srcSize` must be the exact length of some number of ZSTD compressed and/or + * skippable frames + * @return : decompressed size of the frames contained */ +unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize) +{ + unsigned long long totalDstSize = 0; + + while (srcSize >= ZSTD_startingInputLength(ZSTD_f_zstd1)) { + U32 const magicNumber = MEM_readLE32(src); + + if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { + size_t const skippableSize = readSkippableFrameSize(src, srcSize); + if (ZSTD_isError(skippableSize)) { + return ZSTD_CONTENTSIZE_ERROR; + } + assert(skippableSize <= srcSize); + + src = (const BYTE *)src + skippableSize; + srcSize -= skippableSize; + continue; + } + + { unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); + if (ret >= ZSTD_CONTENTSIZE_ERROR) return ret; + + /* check for overflow */ + if (totalDstSize + ret < totalDstSize) return ZSTD_CONTENTSIZE_ERROR; + totalDstSize += ret; + } + { size_t const frameSrcSize = ZSTD_findFrameCompressedSize(src, srcSize); + if (ZSTD_isError(frameSrcSize)) { + return ZSTD_CONTENTSIZE_ERROR; + } + + src = (const BYTE *)src + frameSrcSize; + srcSize -= frameSrcSize; + } + } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ + + if (srcSize) return ZSTD_CONTENTSIZE_ERROR; + + return totalDstSize; +} + +/* ZSTD_getDecompressedSize() : + * compatible with legacy mode + * @return : decompressed size if known, 0 otherwise + note : 0 can mean any of the following : + - frame content is empty + - decompressed size field is not present in frame header + - frame header unknown / not supported + - frame header not complete (`srcSize` too small) */ +unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize) +{ + unsigned long long const ret = ZSTD_getFrameContentSize(src, srcSize); + ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_ERROR < ZSTD_CONTENTSIZE_UNKNOWN); + return (ret >= ZSTD_CONTENTSIZE_ERROR) ? 0 : ret; +} + + +/* ZSTD_decodeFrameHeader() : + * `headerSize` must be the size provided by ZSTD_frameHeaderSize(). + * If multiple DDict references are enabled, also will choose the correct DDict to use. + * @return : 0 if success, or an error code, which can be tested using ZSTD_isError() */ +static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t headerSize) +{ + size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format); + if (ZSTD_isError(result)) return result; /* invalid header */ + RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small"); + + /* Reference DDict requested by frame if dctx references multiple ddicts */ + if (dctx->refMultipleDDicts == ZSTD_rmd_refMultipleDDicts && dctx->ddictSet) { + ZSTD_DCtx_selectFrameDDict(dctx); + } + +#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + /* Skip the dictID check in fuzzing mode, because it makes the search + * harder. + */ + RETURN_ERROR_IF(dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID), + dictionary_wrong, ""); +#endif + dctx->validateChecksum = (dctx->fParams.checksumFlag && !dctx->forceIgnoreChecksum) ? 1 : 0; + if (dctx->validateChecksum) xxh64_reset(&dctx->xxhState, 0); + dctx->processedCSize += headerSize; + return 0; +} + +static ZSTD_frameSizeInfo ZSTD_errorFrameSizeInfo(size_t ret) +{ + ZSTD_frameSizeInfo frameSizeInfo; + frameSizeInfo.compressedSize = ret; + frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR; + return frameSizeInfo; +} + +static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize) +{ + ZSTD_frameSizeInfo frameSizeInfo; + ZSTD_memset(&frameSizeInfo, 0, sizeof(ZSTD_frameSizeInfo)); + + + if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE) + && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { + frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize); + assert(ZSTD_isError(frameSizeInfo.compressedSize) || + frameSizeInfo.compressedSize <= srcSize); + return frameSizeInfo; + } else { + const BYTE* ip = (const BYTE*)src; + const BYTE* const ipstart = ip; + size_t remainingSize = srcSize; + size_t nbBlocks = 0; + ZSTD_frameHeader zfh; + + /* Extract Frame Header */ + { size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize); + if (ZSTD_isError(ret)) + return ZSTD_errorFrameSizeInfo(ret); + if (ret > 0) + return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); + } + + ip += zfh.headerSize; + remainingSize -= zfh.headerSize; + + /* Iterate over each block */ + while (1) { + blockProperties_t blockProperties; + size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties); + if (ZSTD_isError(cBlockSize)) + return ZSTD_errorFrameSizeInfo(cBlockSize); + + if (ZSTD_blockHeaderSize + cBlockSize > remainingSize) + return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); + + ip += ZSTD_blockHeaderSize + cBlockSize; + remainingSize -= ZSTD_blockHeaderSize + cBlockSize; + nbBlocks++; + + if (blockProperties.lastBlock) break; + } + + /* Final frame content checksum */ + if (zfh.checksumFlag) { + if (remainingSize < 4) + return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong)); + ip += 4; + } + + frameSizeInfo.compressedSize = (size_t)(ip - ipstart); + frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) + ? zfh.frameContentSize + : nbBlocks * zfh.blockSizeMax; + return frameSizeInfo; + } +} + +/* ZSTD_findFrameCompressedSize() : + * compatible with legacy mode + * `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame + * `srcSize` must be at least as large as the frame contained + * @return : the compressed size of the frame starting at `src` */ +size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize) +{ + ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize); + return frameSizeInfo.compressedSize; +} + +/* ZSTD_decompressBound() : + * compatible with legacy mode + * `src` must point to the start of a ZSTD frame or a skippeable frame + * `srcSize` must be at least as large as the frame contained + * @return : the maximum decompressed size of the compressed source + */ +unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize) +{ + unsigned long long bound = 0; + /* Iterate over each frame */ + while (srcSize > 0) { + ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize); + size_t const compressedSize = frameSizeInfo.compressedSize; + unsigned long long const decompressedBound = frameSizeInfo.decompressedBound; + if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR) + return ZSTD_CONTENTSIZE_ERROR; + assert(srcSize >= compressedSize); + src = (const BYTE*)src + compressedSize; + srcSize -= compressedSize; + bound += decompressedBound; + } + return bound; +} + + +/*-************************************************************* + * Frame decoding + ***************************************************************/ + +/* ZSTD_insertBlock() : + * insert `src` block into `dctx` history. Useful to track uncompressed blocks. */ +size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize) +{ + DEBUGLOG(5, "ZSTD_insertBlock: %u bytes", (unsigned)blockSize); + ZSTD_checkContinuity(dctx, blockStart, blockSize); + dctx->previousDstEnd = (const char*)blockStart + blockSize; + return blockSize; +} + + +static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity, + const void* src, size_t srcSize) +{ + DEBUGLOG(5, "ZSTD_copyRawBlock"); + RETURN_ERROR_IF(srcSize > dstCapacity, dstSize_tooSmall, ""); + if (dst == NULL) { + if (srcSize == 0) return 0; + RETURN_ERROR(dstBuffer_null, ""); + } + ZSTD_memcpy(dst, src, srcSize); + return srcSize; +} + +static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity, + BYTE b, + size_t regenSize) +{ + RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall, ""); + if (dst == NULL) { + if (regenSize == 0) return 0; + RETURN_ERROR(dstBuffer_null, ""); + } + ZSTD_memset(dst, b, regenSize); + return regenSize; +} + +static void ZSTD_DCtx_trace_end(ZSTD_DCtx const* dctx, U64 uncompressedSize, U64 compressedSize, unsigned streaming) +{ + (void)dctx; + (void)uncompressedSize; + (void)compressedSize; + (void)streaming; +} + + +/*! ZSTD_decompressFrame() : + * @dctx must be properly initialized + * will update *srcPtr and *srcSizePtr, + * to make *srcPtr progress by one frame. */ +static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void** srcPtr, size_t *srcSizePtr) +{ + const BYTE* const istart = (const BYTE*)(*srcPtr); + const BYTE* ip = istart; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = dstCapacity != 0 ? ostart + dstCapacity : ostart; + BYTE* op = ostart; + size_t remainingSrcSize = *srcSizePtr; + + DEBUGLOG(4, "ZSTD_decompressFrame (srcSize:%i)", (int)*srcSizePtr); + + /* check */ + RETURN_ERROR_IF( + remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN(dctx->format)+ZSTD_blockHeaderSize, + srcSize_wrong, ""); + + /* Frame Header */ + { size_t const frameHeaderSize = ZSTD_frameHeaderSize_internal( + ip, ZSTD_FRAMEHEADERSIZE_PREFIX(dctx->format), dctx->format); + if (ZSTD_isError(frameHeaderSize)) return frameHeaderSize; + RETURN_ERROR_IF(remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize, + srcSize_wrong, ""); + FORWARD_IF_ERROR( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) , ""); + ip += frameHeaderSize; remainingSrcSize -= frameHeaderSize; + } + + /* Loop on each block */ + while (1) { + size_t decodedSize; + blockProperties_t blockProperties; + size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSrcSize, &blockProperties); + if (ZSTD_isError(cBlockSize)) return cBlockSize; + + ip += ZSTD_blockHeaderSize; + remainingSrcSize -= ZSTD_blockHeaderSize; + RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong, ""); + + switch(blockProperties.blockType) + { + case bt_compressed: + decodedSize = ZSTD_decompressBlock_internal(dctx, op, (size_t)(oend-op), ip, cBlockSize, /* frame */ 1); + break; + case bt_raw : + decodedSize = ZSTD_copyRawBlock(op, (size_t)(oend-op), ip, cBlockSize); + break; + case bt_rle : + decodedSize = ZSTD_setRleBlock(op, (size_t)(oend-op), *ip, blockProperties.origSize); + break; + case bt_reserved : + default: + RETURN_ERROR(corruption_detected, "invalid block type"); + } + + if (ZSTD_isError(decodedSize)) return decodedSize; + if (dctx->validateChecksum) + xxh64_update(&dctx->xxhState, op, decodedSize); + if (decodedSize != 0) + op += decodedSize; + assert(ip != NULL); + ip += cBlockSize; + remainingSrcSize -= cBlockSize; + if (blockProperties.lastBlock) break; + } + + if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) { + RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize, + corruption_detected, ""); + } + if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */ + RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong, ""); + if (!dctx->forceIgnoreChecksum) { + U32 const checkCalc = (U32)xxh64_digest(&dctx->xxhState); + U32 checkRead; + checkRead = MEM_readLE32(ip); + RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong, ""); + } + ip += 4; + remainingSrcSize -= 4; + } + ZSTD_DCtx_trace_end(dctx, (U64)(op-ostart), (U64)(ip-istart), /* streaming */ 0); + /* Allow caller to get size read */ + *srcPtr = ip; + *srcSizePtr = remainingSrcSize; + return (size_t)(op-ostart); +} + +static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict, size_t dictSize, + const ZSTD_DDict* ddict) +{ + void* const dststart = dst; + int moreThan1Frame = 0; + + DEBUGLOG(5, "ZSTD_decompressMultiFrame"); + assert(dict==NULL || ddict==NULL); /* either dict or ddict set, not both */ + + if (ddict) { + dict = ZSTD_DDict_dictContent(ddict); + dictSize = ZSTD_DDict_dictSize(ddict); + } + + while (srcSize >= ZSTD_startingInputLength(dctx->format)) { + + + { U32 const magicNumber = MEM_readLE32(src); + DEBUGLOG(4, "reading magic number %08X (expecting %08X)", + (unsigned)magicNumber, ZSTD_MAGICNUMBER); + if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { + size_t const skippableSize = readSkippableFrameSize(src, srcSize); + FORWARD_IF_ERROR(skippableSize, "readSkippableFrameSize failed"); + assert(skippableSize <= srcSize); + + src = (const BYTE *)src + skippableSize; + srcSize -= skippableSize; + continue; + } } + + if (ddict) { + /* we were called from ZSTD_decompress_usingDDict */ + FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict), ""); + } else { + /* this will initialize correctly with no dict if dict == NULL, so + * use this in all cases but ddict */ + FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize), ""); + } + ZSTD_checkContinuity(dctx, dst, dstCapacity); + + { const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity, + &src, &srcSize); + RETURN_ERROR_IF( + (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown) + && (moreThan1Frame==1), + srcSize_wrong, + "At least one frame successfully completed, " + "but following bytes are garbage: " + "it's more likely to be a srcSize error, " + "specifying more input bytes than size of frame(s). " + "Note: one could be unlucky, it might be a corruption error instead, " + "happening right at the place where we expect zstd magic bytes. " + "But this is _much_ less likely than a srcSize field error."); + if (ZSTD_isError(res)) return res; + assert(res <= dstCapacity); + if (res != 0) + dst = (BYTE*)dst + res; + dstCapacity -= res; + } + moreThan1Frame = 1; + } /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */ + + RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed"); + + return (size_t)((BYTE*)dst - (BYTE*)dststart); +} + +size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const void* dict, size_t dictSize) +{ + return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, dict, dictSize, NULL); +} + + +static ZSTD_DDict const* ZSTD_getDDict(ZSTD_DCtx* dctx) +{ + switch (dctx->dictUses) { + default: + assert(0 /* Impossible */); + ZSTD_FALLTHROUGH; + case ZSTD_dont_use: + ZSTD_clearDict(dctx); + return NULL; + case ZSTD_use_indefinitely: + return dctx->ddict; + case ZSTD_use_once: + dctx->dictUses = ZSTD_dont_use; + return dctx->ddict; + } +} + +size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + return ZSTD_decompress_usingDDict(dctx, dst, dstCapacity, src, srcSize, ZSTD_getDDict(dctx)); +} + + +size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ +#if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1) + size_t regenSize; + ZSTD_DCtx* const dctx = ZSTD_createDCtx(); + RETURN_ERROR_IF(dctx==NULL, memory_allocation, "NULL pointer!"); + regenSize = ZSTD_decompressDCtx(dctx, dst, dstCapacity, src, srcSize); + ZSTD_freeDCtx(dctx); + return regenSize; +#else /* stack mode */ + ZSTD_DCtx dctx; + ZSTD_initDCtx_internal(&dctx); + return ZSTD_decompressDCtx(&dctx, dst, dstCapacity, src, srcSize); +#endif +} + + +/*-************************************** +* Advanced Streaming Decompression API +* Bufferless and synchronous +****************************************/ +size_t ZSTD_nextSrcSizeToDecompress(ZSTD_DCtx* dctx) { return dctx->expected; } + +/* + * Similar to ZSTD_nextSrcSizeToDecompress(), but when when a block input can be streamed, + * we allow taking a partial block as the input. Currently only raw uncompressed blocks can + * be streamed. + * + * For blocks that can be streamed, this allows us to reduce the latency until we produce + * output, and avoid copying the input. + * + * @param inputSize - The total amount of input that the caller currently has. + */ +static size_t ZSTD_nextSrcSizeToDecompressWithInputSize(ZSTD_DCtx* dctx, size_t inputSize) { + if (!(dctx->stage == ZSTDds_decompressBlock || dctx->stage == ZSTDds_decompressLastBlock)) + return dctx->expected; + if (dctx->bType != bt_raw) + return dctx->expected; + return MIN(MAX(inputSize, 1), dctx->expected); +} + +ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx) { + switch(dctx->stage) + { + default: /* should not happen */ + assert(0); + ZSTD_FALLTHROUGH; + case ZSTDds_getFrameHeaderSize: + ZSTD_FALLTHROUGH; + case ZSTDds_decodeFrameHeader: + return ZSTDnit_frameHeader; + case ZSTDds_decodeBlockHeader: + return ZSTDnit_blockHeader; + case ZSTDds_decompressBlock: + return ZSTDnit_block; + case ZSTDds_decompressLastBlock: + return ZSTDnit_lastBlock; + case ZSTDds_checkChecksum: + return ZSTDnit_checksum; + case ZSTDds_decodeSkippableHeader: + ZSTD_FALLTHROUGH; + case ZSTDds_skipFrame: + return ZSTDnit_skippableFrame; + } +} + +static int ZSTD_isSkipFrame(ZSTD_DCtx* dctx) { return dctx->stage == ZSTDds_skipFrame; } + +/* ZSTD_decompressContinue() : + * srcSize : must be the exact nb of bytes expected (see ZSTD_nextSrcSizeToDecompress()) + * @return : nb of bytes generated into `dst` (necessarily <= `dstCapacity) + * or an error code, which can be tested using ZSTD_isError() */ +size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize); + /* Sanity check */ + RETURN_ERROR_IF(srcSize != ZSTD_nextSrcSizeToDecompressWithInputSize(dctx, srcSize), srcSize_wrong, "not allowed"); + ZSTD_checkContinuity(dctx, dst, dstCapacity); + + dctx->processedCSize += srcSize; + + switch (dctx->stage) + { + case ZSTDds_getFrameHeaderSize : + assert(src != NULL); + if (dctx->format == ZSTD_f_zstd1) { /* allows header */ + assert(srcSize >= ZSTD_FRAMEIDSIZE); /* to read skippable magic number */ + if ((MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */ + ZSTD_memcpy(dctx->headerBuffer, src, srcSize); + dctx->expected = ZSTD_SKIPPABLEHEADERSIZE - srcSize; /* remaining to load to get full skippable frame header */ + dctx->stage = ZSTDds_decodeSkippableHeader; + return 0; + } } + dctx->headerSize = ZSTD_frameHeaderSize_internal(src, srcSize, dctx->format); + if (ZSTD_isError(dctx->headerSize)) return dctx->headerSize; + ZSTD_memcpy(dctx->headerBuffer, src, srcSize); + dctx->expected = dctx->headerSize - srcSize; + dctx->stage = ZSTDds_decodeFrameHeader; + return 0; + + case ZSTDds_decodeFrameHeader: + assert(src != NULL); + ZSTD_memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize); + FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize), ""); + dctx->expected = ZSTD_blockHeaderSize; + dctx->stage = ZSTDds_decodeBlockHeader; + return 0; + + case ZSTDds_decodeBlockHeader: + { blockProperties_t bp; + size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp); + if (ZSTD_isError(cBlockSize)) return cBlockSize; + RETURN_ERROR_IF(cBlockSize > dctx->fParams.blockSizeMax, corruption_detected, "Block Size Exceeds Maximum"); + dctx->expected = cBlockSize; + dctx->bType = bp.blockType; + dctx->rleSize = bp.origSize; + if (cBlockSize) { + dctx->stage = bp.lastBlock ? ZSTDds_decompressLastBlock : ZSTDds_decompressBlock; + return 0; + } + /* empty block */ + if (bp.lastBlock) { + if (dctx->fParams.checksumFlag) { + dctx->expected = 4; + dctx->stage = ZSTDds_checkChecksum; + } else { + dctx->expected = 0; /* end of frame */ + dctx->stage = ZSTDds_getFrameHeaderSize; + } + } else { + dctx->expected = ZSTD_blockHeaderSize; /* jump to next header */ + dctx->stage = ZSTDds_decodeBlockHeader; + } + return 0; + } + + case ZSTDds_decompressLastBlock: + case ZSTDds_decompressBlock: + DEBUGLOG(5, "ZSTD_decompressContinue: case ZSTDds_decompressBlock"); + { size_t rSize; + switch(dctx->bType) + { + case bt_compressed: + DEBUGLOG(5, "ZSTD_decompressContinue: case bt_compressed"); + rSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize, /* frame */ 1); + dctx->expected = 0; /* Streaming not supported */ + break; + case bt_raw : + assert(srcSize <= dctx->expected); + rSize = ZSTD_copyRawBlock(dst, dstCapacity, src, srcSize); + FORWARD_IF_ERROR(rSize, "ZSTD_copyRawBlock failed"); + assert(rSize == srcSize); + dctx->expected -= rSize; + break; + case bt_rle : + rSize = ZSTD_setRleBlock(dst, dstCapacity, *(const BYTE*)src, dctx->rleSize); + dctx->expected = 0; /* Streaming not supported */ + break; + case bt_reserved : /* should never happen */ + default: + RETURN_ERROR(corruption_detected, "invalid block type"); + } + FORWARD_IF_ERROR(rSize, ""); + RETURN_ERROR_IF(rSize > dctx->fParams.blockSizeMax, corruption_detected, "Decompressed Block Size Exceeds Maximum"); + DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize); + dctx->decodedSize += rSize; + if (dctx->validateChecksum) xxh64_update(&dctx->xxhState, dst, rSize); + dctx->previousDstEnd = (char*)dst + rSize; + + /* Stay on the same stage until we are finished streaming the block. */ + if (dctx->expected > 0) { + return rSize; + } + + if (dctx->stage == ZSTDds_decompressLastBlock) { /* end of frame */ + DEBUGLOG(4, "ZSTD_decompressContinue: decoded size from frame : %u", (unsigned)dctx->decodedSize); + RETURN_ERROR_IF( + dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN + && dctx->decodedSize != dctx->fParams.frameContentSize, + corruption_detected, ""); + if (dctx->fParams.checksumFlag) { /* another round for frame checksum */ + dctx->expected = 4; + dctx->stage = ZSTDds_checkChecksum; + } else { + ZSTD_DCtx_trace_end(dctx, dctx->decodedSize, dctx->processedCSize, /* streaming */ 1); + dctx->expected = 0; /* ends here */ + dctx->stage = ZSTDds_getFrameHeaderSize; + } + } else { + dctx->stage = ZSTDds_decodeBlockHeader; + dctx->expected = ZSTD_blockHeaderSize; + } + return rSize; + } + + case ZSTDds_checkChecksum: + assert(srcSize == 4); /* guaranteed by dctx->expected */ + { + if (dctx->validateChecksum) { + U32 const h32 = (U32)xxh64_digest(&dctx->xxhState); + U32 const check32 = MEM_readLE32(src); + DEBUGLOG(4, "ZSTD_decompressContinue: checksum : calculated %08X :: %08X read", (unsigned)h32, (unsigned)check32); + RETURN_ERROR_IF(check32 != h32, checksum_wrong, ""); + } + ZSTD_DCtx_trace_end(dctx, dctx->decodedSize, dctx->processedCSize, /* streaming */ 1); + dctx->expected = 0; + dctx->stage = ZSTDds_getFrameHeaderSize; + return 0; + } + + case ZSTDds_decodeSkippableHeader: + assert(src != NULL); + assert(srcSize <= ZSTD_SKIPPABLEHEADERSIZE); + ZSTD_memcpy(dctx->headerBuffer + (ZSTD_SKIPPABLEHEADERSIZE - srcSize), src, srcSize); /* complete skippable header */ + dctx->expected = MEM_readLE32(dctx->headerBuffer + ZSTD_FRAMEIDSIZE); /* note : dctx->expected can grow seriously large, beyond local buffer size */ + dctx->stage = ZSTDds_skipFrame; + return 0; + + case ZSTDds_skipFrame: + dctx->expected = 0; + dctx->stage = ZSTDds_getFrameHeaderSize; + return 0; + + default: + assert(0); /* impossible */ + RETURN_ERROR(GENERIC, "impossible to reach"); /* some compiler require default to do something */ + } +} + + +static size_t ZSTD_refDictContent(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + dctx->dictEnd = dctx->previousDstEnd; + dctx->virtualStart = (const char*)dict - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->prefixStart)); + dctx->prefixStart = dict; + dctx->previousDstEnd = (const char*)dict + dictSize; +#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + dctx->dictContentBeginForFuzzing = dctx->prefixStart; + dctx->dictContentEndForFuzzing = dctx->previousDstEnd; +#endif + return 0; +} + +/*! ZSTD_loadDEntropy() : + * dict : must point at beginning of a valid zstd dictionary. + * @return : size of entropy tables read */ +size_t +ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, + const void* const dict, size_t const dictSize) +{ + const BYTE* dictPtr = (const BYTE*)dict; + const BYTE* const dictEnd = dictPtr + dictSize; + + RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted, "dict is too small"); + assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY); /* dict must be valid */ + dictPtr += 8; /* skip header = magic + dictID */ + + ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyDTables_t, OFTable) == offsetof(ZSTD_entropyDTables_t, LLTable) + sizeof(entropy->LLTable)); + ZSTD_STATIC_ASSERT(offsetof(ZSTD_entropyDTables_t, MLTable) == offsetof(ZSTD_entropyDTables_t, OFTable) + sizeof(entropy->OFTable)); + ZSTD_STATIC_ASSERT(sizeof(entropy->LLTable) + sizeof(entropy->OFTable) + sizeof(entropy->MLTable) >= HUF_DECOMPRESS_WORKSPACE_SIZE); + { void* const workspace = &entropy->LLTable; /* use fse tables as temporary workspace; implies fse tables are grouped together */ + size_t const workspaceSize = sizeof(entropy->LLTable) + sizeof(entropy->OFTable) + sizeof(entropy->MLTable); +#ifdef HUF_FORCE_DECOMPRESS_X1 + /* in minimal huffman, we always use X1 variants */ + size_t const hSize = HUF_readDTableX1_wksp(entropy->hufTable, + dictPtr, dictEnd - dictPtr, + workspace, workspaceSize); +#else + size_t const hSize = HUF_readDTableX2_wksp(entropy->hufTable, + dictPtr, (size_t)(dictEnd - dictPtr), + workspace, workspaceSize); +#endif + RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted, ""); + dictPtr += hSize; + } + + { short offcodeNCount[MaxOff+1]; + unsigned offcodeMaxValue = MaxOff, offcodeLog; + size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, (size_t)(dictEnd-dictPtr)); + RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted, ""); + RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted, ""); + ZSTD_buildFSETable( entropy->OFTable, + offcodeNCount, offcodeMaxValue, + OF_base, OF_bits, + offcodeLog, + entropy->workspace, sizeof(entropy->workspace), + /* bmi2 */0); + dictPtr += offcodeHeaderSize; + } + + { short matchlengthNCount[MaxML+1]; + unsigned matchlengthMaxValue = MaxML, matchlengthLog; + size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, (size_t)(dictEnd-dictPtr)); + RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted, ""); + RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted, ""); + ZSTD_buildFSETable( entropy->MLTable, + matchlengthNCount, matchlengthMaxValue, + ML_base, ML_bits, + matchlengthLog, + entropy->workspace, sizeof(entropy->workspace), + /* bmi2 */ 0); + dictPtr += matchlengthHeaderSize; + } + + { short litlengthNCount[MaxLL+1]; + unsigned litlengthMaxValue = MaxLL, litlengthLog; + size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, (size_t)(dictEnd-dictPtr)); + RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted, ""); + RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted, ""); + RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted, ""); + ZSTD_buildFSETable( entropy->LLTable, + litlengthNCount, litlengthMaxValue, + LL_base, LL_bits, + litlengthLog, + entropy->workspace, sizeof(entropy->workspace), + /* bmi2 */ 0); + dictPtr += litlengthHeaderSize; + } + + RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted, ""); + { int i; + size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12)); + for (i=0; i<3; i++) { + U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4; + RETURN_ERROR_IF(rep==0 || rep > dictContentSize, + dictionary_corrupted, ""); + entropy->rep[i] = rep; + } } + + return (size_t)(dictPtr - (const BYTE*)dict); +} + +static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + if (dictSize < 8) return ZSTD_refDictContent(dctx, dict, dictSize); + { U32 const magic = MEM_readLE32(dict); + if (magic != ZSTD_MAGIC_DICTIONARY) { + return ZSTD_refDictContent(dctx, dict, dictSize); /* pure content mode */ + } } + dctx->dictID = MEM_readLE32((const char*)dict + ZSTD_FRAMEIDSIZE); + + /* load entropy tables */ + { size_t const eSize = ZSTD_loadDEntropy(&dctx->entropy, dict, dictSize); + RETURN_ERROR_IF(ZSTD_isError(eSize), dictionary_corrupted, ""); + dict = (const char*)dict + eSize; + dictSize -= eSize; + } + dctx->litEntropy = dctx->fseEntropy = 1; + + /* reference dictionary content */ + return ZSTD_refDictContent(dctx, dict, dictSize); +} + +size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx) +{ + assert(dctx != NULL); + dctx->expected = ZSTD_startingInputLength(dctx->format); /* dctx->format must be properly set */ + dctx->stage = ZSTDds_getFrameHeaderSize; + dctx->processedCSize = 0; + dctx->decodedSize = 0; + dctx->previousDstEnd = NULL; + dctx->prefixStart = NULL; + dctx->virtualStart = NULL; + dctx->dictEnd = NULL; + dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */ + dctx->litEntropy = dctx->fseEntropy = 0; + dctx->dictID = 0; + dctx->bType = bt_reserved; + ZSTD_STATIC_ASSERT(sizeof(dctx->entropy.rep) == sizeof(repStartValue)); + ZSTD_memcpy(dctx->entropy.rep, repStartValue, sizeof(repStartValue)); /* initial repcodes */ + dctx->LLTptr = dctx->entropy.LLTable; + dctx->MLTptr = dctx->entropy.MLTable; + dctx->OFTptr = dctx->entropy.OFTable; + dctx->HUFptr = dctx->entropy.hufTable; + return 0; +} + +size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) , ""); + if (dict && dictSize) + RETURN_ERROR_IF( + ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)), + dictionary_corrupted, ""); + return 0; +} + + +/* ====== ZSTD_DDict ====== */ + +size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) +{ + DEBUGLOG(4, "ZSTD_decompressBegin_usingDDict"); + assert(dctx != NULL); + if (ddict) { + const char* const dictStart = (const char*)ZSTD_DDict_dictContent(ddict); + size_t const dictSize = ZSTD_DDict_dictSize(ddict); + const void* const dictEnd = dictStart + dictSize; + dctx->ddictIsCold = (dctx->dictEnd != dictEnd); + DEBUGLOG(4, "DDict is %s", + dctx->ddictIsCold ? "~cold~" : "hot!"); + } + FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) , ""); + if (ddict) { /* NULL ddict is equivalent to no dictionary */ + ZSTD_copyDDictParameters(dctx, ddict); + } + return 0; +} + +/*! ZSTD_getDictID_fromDict() : + * Provides the dictID stored within dictionary. + * if @return == 0, the dictionary is not conformant with Zstandard specification. + * It can still be loaded, but as a content-only dictionary. */ +unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize) +{ + if (dictSize < 8) return 0; + if (MEM_readLE32(dict) != ZSTD_MAGIC_DICTIONARY) return 0; + return MEM_readLE32((const char*)dict + ZSTD_FRAMEIDSIZE); +} + +/*! ZSTD_getDictID_fromFrame() : + * Provides the dictID required to decompress frame stored within `src`. + * If @return == 0, the dictID could not be decoded. + * This could for one of the following reasons : + * - The frame does not require a dictionary (most common case). + * - The frame was built with dictID intentionally removed. + * Needed dictionary is a hidden information. + * Note : this use case also happens when using a non-conformant dictionary. + * - `srcSize` is too small, and as a result, frame header could not be decoded. + * Note : possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`. + * - This is not a Zstandard frame. + * When identifying the exact failure cause, it's possible to use + * ZSTD_getFrameHeader(), which will provide a more precise error code. */ +unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize) +{ + ZSTD_frameHeader zfp = { 0, 0, 0, ZSTD_frame, 0, 0, 0 }; + size_t const hError = ZSTD_getFrameHeader(&zfp, src, srcSize); + if (ZSTD_isError(hError)) return 0; + return zfp.dictID; +} + + +/*! ZSTD_decompress_usingDDict() : +* Decompression using a pre-digested Dictionary +* Use dictionary without significant overhead. */ +size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + const ZSTD_DDict* ddict) +{ + /* pass content and size in case legacy frames are encountered */ + return ZSTD_decompressMultiFrame(dctx, dst, dstCapacity, src, srcSize, + NULL, 0, + ddict); +} + + +/*===================================== +* Streaming decompression +*====================================*/ + +ZSTD_DStream* ZSTD_createDStream(void) +{ + DEBUGLOG(3, "ZSTD_createDStream"); + return ZSTD_createDStream_advanced(ZSTD_defaultCMem); +} + +ZSTD_DStream* ZSTD_initStaticDStream(void *workspace, size_t workspaceSize) +{ + return ZSTD_initStaticDCtx(workspace, workspaceSize); +} + +ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem) +{ + return ZSTD_createDCtx_advanced(customMem); +} + +size_t ZSTD_freeDStream(ZSTD_DStream* zds) +{ + return ZSTD_freeDCtx(zds); +} + + +/* *** Initialization *** */ + +size_t ZSTD_DStreamInSize(void) { return ZSTD_BLOCKSIZE_MAX + ZSTD_blockHeaderSize; } +size_t ZSTD_DStreamOutSize(void) { return ZSTD_BLOCKSIZE_MAX; } + +size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx, + const void* dict, size_t dictSize, + ZSTD_dictLoadMethod_e dictLoadMethod, + ZSTD_dictContentType_e dictContentType) +{ + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); + ZSTD_clearDict(dctx); + if (dict && dictSize != 0) { + dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem); + RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation, "NULL pointer!"); + dctx->ddict = dctx->ddictLocal; + dctx->dictUses = ZSTD_use_indefinitely; + } + return 0; +} + +size_t ZSTD_DCtx_loadDictionary_byReference(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byRef, ZSTD_dct_auto); +} + +size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSize) +{ + return ZSTD_DCtx_loadDictionary_advanced(dctx, dict, dictSize, ZSTD_dlm_byCopy, ZSTD_dct_auto); +} + +size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType) +{ + FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType), ""); + dctx->dictUses = ZSTD_use_once; + return 0; +} + +size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize) +{ + return ZSTD_DCtx_refPrefix_advanced(dctx, prefix, prefixSize, ZSTD_dct_rawContent); +} + + +/* ZSTD_initDStream_usingDict() : + * return : expected size, aka ZSTD_startingInputLength(). + * this function cannot fail */ +size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize) +{ + DEBUGLOG(4, "ZSTD_initDStream_usingDict"); + FORWARD_IF_ERROR( ZSTD_DCtx_reset(zds, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) , ""); + return ZSTD_startingInputLength(zds->format); +} + +/* note : this variant can't fail */ +size_t ZSTD_initDStream(ZSTD_DStream* zds) +{ + DEBUGLOG(4, "ZSTD_initDStream"); + return ZSTD_initDStream_usingDDict(zds, NULL); +} + +/* ZSTD_initDStream_usingDDict() : + * ddict will just be referenced, and must outlive decompression session + * this function cannot fail */ +size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict) +{ + FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) , ""); + FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) , ""); + return ZSTD_startingInputLength(dctx->format); +} + +/* ZSTD_resetDStream() : + * return : expected size, aka ZSTD_startingInputLength(). + * this function cannot fail */ +size_t ZSTD_resetDStream(ZSTD_DStream* dctx) +{ + FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only), ""); + return ZSTD_startingInputLength(dctx->format); +} + + +size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict) +{ + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); + ZSTD_clearDict(dctx); + if (ddict) { + dctx->ddict = ddict; + dctx->dictUses = ZSTD_use_indefinitely; + if (dctx->refMultipleDDicts == ZSTD_rmd_refMultipleDDicts) { + if (dctx->ddictSet == NULL) { + dctx->ddictSet = ZSTD_createDDictHashSet(dctx->customMem); + if (!dctx->ddictSet) { + RETURN_ERROR(memory_allocation, "Failed to allocate memory for hash set!"); + } + } + assert(!dctx->staticSize); /* Impossible: ddictSet cannot have been allocated if static dctx */ + FORWARD_IF_ERROR(ZSTD_DDictHashSet_addDDict(dctx->ddictSet, ddict, dctx->customMem), ""); + } + } + return 0; +} + +/* ZSTD_DCtx_setMaxWindowSize() : + * note : no direct equivalence in ZSTD_DCtx_setParameter, + * since this version sets windowSize, and the other sets windowLog */ +size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize) +{ + ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax); + size_t const min = (size_t)1 << bounds.lowerBound; + size_t const max = (size_t)1 << bounds.upperBound; + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); + RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound, ""); + RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound, ""); + dctx->maxWindowSize = maxWindowSize; + return 0; +} + +size_t ZSTD_DCtx_setFormat(ZSTD_DCtx* dctx, ZSTD_format_e format) +{ + return ZSTD_DCtx_setParameter(dctx, ZSTD_d_format, (int)format); +} + +ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam) +{ + ZSTD_bounds bounds = { 0, 0, 0 }; + switch(dParam) { + case ZSTD_d_windowLogMax: + bounds.lowerBound = ZSTD_WINDOWLOG_ABSOLUTEMIN; + bounds.upperBound = ZSTD_WINDOWLOG_MAX; + return bounds; + case ZSTD_d_format: + bounds.lowerBound = (int)ZSTD_f_zstd1; + bounds.upperBound = (int)ZSTD_f_zstd1_magicless; + ZSTD_STATIC_ASSERT(ZSTD_f_zstd1 < ZSTD_f_zstd1_magicless); + return bounds; + case ZSTD_d_stableOutBuffer: + bounds.lowerBound = (int)ZSTD_bm_buffered; + bounds.upperBound = (int)ZSTD_bm_stable; + return bounds; + case ZSTD_d_forceIgnoreChecksum: + bounds.lowerBound = (int)ZSTD_d_validateChecksum; + bounds.upperBound = (int)ZSTD_d_ignoreChecksum; + return bounds; + case ZSTD_d_refMultipleDDicts: + bounds.lowerBound = (int)ZSTD_rmd_refSingleDDict; + bounds.upperBound = (int)ZSTD_rmd_refMultipleDDicts; + return bounds; + default:; + } + bounds.error = ERROR(parameter_unsupported); + return bounds; +} + +/* ZSTD_dParam_withinBounds: + * @return 1 if value is within dParam bounds, + * 0 otherwise */ +static int ZSTD_dParam_withinBounds(ZSTD_dParameter dParam, int value) +{ + ZSTD_bounds const bounds = ZSTD_dParam_getBounds(dParam); + if (ZSTD_isError(bounds.error)) return 0; + if (value < bounds.lowerBound) return 0; + if (value > bounds.upperBound) return 0; + return 1; +} + +#define CHECK_DBOUNDS(p,v) { \ + RETURN_ERROR_IF(!ZSTD_dParam_withinBounds(p, v), parameter_outOfBound, ""); \ +} + +size_t ZSTD_DCtx_getParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int* value) +{ + switch (param) { + case ZSTD_d_windowLogMax: + *value = (int)ZSTD_highbit32((U32)dctx->maxWindowSize); + return 0; + case ZSTD_d_format: + *value = (int)dctx->format; + return 0; + case ZSTD_d_stableOutBuffer: + *value = (int)dctx->outBufferMode; + return 0; + case ZSTD_d_forceIgnoreChecksum: + *value = (int)dctx->forceIgnoreChecksum; + return 0; + case ZSTD_d_refMultipleDDicts: + *value = (int)dctx->refMultipleDDicts; + return 0; + default:; + } + RETURN_ERROR(parameter_unsupported, ""); +} + +size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value) +{ + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); + switch(dParam) { + case ZSTD_d_windowLogMax: + if (value == 0) value = ZSTD_WINDOWLOG_LIMIT_DEFAULT; + CHECK_DBOUNDS(ZSTD_d_windowLogMax, value); + dctx->maxWindowSize = ((size_t)1) << value; + return 0; + case ZSTD_d_format: + CHECK_DBOUNDS(ZSTD_d_format, value); + dctx->format = (ZSTD_format_e)value; + return 0; + case ZSTD_d_stableOutBuffer: + CHECK_DBOUNDS(ZSTD_d_stableOutBuffer, value); + dctx->outBufferMode = (ZSTD_bufferMode_e)value; + return 0; + case ZSTD_d_forceIgnoreChecksum: + CHECK_DBOUNDS(ZSTD_d_forceIgnoreChecksum, value); + dctx->forceIgnoreChecksum = (ZSTD_forceIgnoreChecksum_e)value; + return 0; + case ZSTD_d_refMultipleDDicts: + CHECK_DBOUNDS(ZSTD_d_refMultipleDDicts, value); + if (dctx->staticSize != 0) { + RETURN_ERROR(parameter_unsupported, "Static dctx does not support multiple DDicts!"); + } + dctx->refMultipleDDicts = (ZSTD_refMultipleDDicts_e)value; + return 0; + default:; + } + RETURN_ERROR(parameter_unsupported, ""); +} + +size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset) +{ + if ( (reset == ZSTD_reset_session_only) + || (reset == ZSTD_reset_session_and_parameters) ) { + dctx->streamStage = zdss_init; + dctx->noForwardProgress = 0; + } + if ( (reset == ZSTD_reset_parameters) + || (reset == ZSTD_reset_session_and_parameters) ) { + RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong, ""); + ZSTD_clearDict(dctx); + ZSTD_DCtx_resetParameters(dctx); + } + return 0; +} + + +size_t ZSTD_sizeof_DStream(const ZSTD_DStream* dctx) +{ + return ZSTD_sizeof_DCtx(dctx); +} + +size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long long frameContentSize) +{ + size_t const blockSize = (size_t) MIN(windowSize, ZSTD_BLOCKSIZE_MAX); + unsigned long long const neededRBSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2); + unsigned long long const neededSize = MIN(frameContentSize, neededRBSize); + size_t const minRBSize = (size_t) neededSize; + RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize, + frameParameter_windowTooLarge, ""); + return minRBSize; +} + +size_t ZSTD_estimateDStreamSize(size_t windowSize) +{ + size_t const blockSize = MIN(windowSize, ZSTD_BLOCKSIZE_MAX); + size_t const inBuffSize = blockSize; /* no block can be larger */ + size_t const outBuffSize = ZSTD_decodingBufferSize_min(windowSize, ZSTD_CONTENTSIZE_UNKNOWN); + return ZSTD_estimateDCtxSize() + inBuffSize + outBuffSize; +} + +size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize) +{ + U32 const windowSizeMax = 1U << ZSTD_WINDOWLOG_MAX; /* note : should be user-selectable, but requires an additional parameter (or a dctx) */ + ZSTD_frameHeader zfh; + size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize); + if (ZSTD_isError(err)) return err; + RETURN_ERROR_IF(err>0, srcSize_wrong, ""); + RETURN_ERROR_IF(zfh.windowSize > windowSizeMax, + frameParameter_windowTooLarge, ""); + return ZSTD_estimateDStreamSize((size_t)zfh.windowSize); +} + + +/* ***** Decompression ***** */ + +static int ZSTD_DCtx_isOverflow(ZSTD_DStream* zds, size_t const neededInBuffSize, size_t const neededOutBuffSize) +{ + return (zds->inBuffSize + zds->outBuffSize) >= (neededInBuffSize + neededOutBuffSize) * ZSTD_WORKSPACETOOLARGE_FACTOR; +} + +static void ZSTD_DCtx_updateOversizedDuration(ZSTD_DStream* zds, size_t const neededInBuffSize, size_t const neededOutBuffSize) +{ + if (ZSTD_DCtx_isOverflow(zds, neededInBuffSize, neededOutBuffSize)) + zds->oversizedDuration++; + else + zds->oversizedDuration = 0; +} + +static int ZSTD_DCtx_isOversizedTooLong(ZSTD_DStream* zds) +{ + return zds->oversizedDuration >= ZSTD_WORKSPACETOOLARGE_MAXDURATION; +} + +/* Checks that the output buffer hasn't changed if ZSTD_obm_stable is used. */ +static size_t ZSTD_checkOutBuffer(ZSTD_DStream const* zds, ZSTD_outBuffer const* output) +{ + ZSTD_outBuffer const expect = zds->expectedOutBuffer; + /* No requirement when ZSTD_obm_stable is not enabled. */ + if (zds->outBufferMode != ZSTD_bm_stable) + return 0; + /* Any buffer is allowed in zdss_init, this must be the same for every other call until + * the context is reset. + */ + if (zds->streamStage == zdss_init) + return 0; + /* The buffer must match our expectation exactly. */ + if (expect.dst == output->dst && expect.pos == output->pos && expect.size == output->size) + return 0; + RETURN_ERROR(dstBuffer_wrong, "ZSTD_d_stableOutBuffer enabled but output differs!"); +} + +/* Calls ZSTD_decompressContinue() with the right parameters for ZSTD_decompressStream() + * and updates the stage and the output buffer state. This call is extracted so it can be + * used both when reading directly from the ZSTD_inBuffer, and in buffered input mode. + * NOTE: You must break after calling this function since the streamStage is modified. + */ +static size_t ZSTD_decompressContinueStream( + ZSTD_DStream* zds, char** op, char* oend, + void const* src, size_t srcSize) { + int const isSkipFrame = ZSTD_isSkipFrame(zds); + if (zds->outBufferMode == ZSTD_bm_buffered) { + size_t const dstSize = isSkipFrame ? 0 : zds->outBuffSize - zds->outStart; + size_t const decodedSize = ZSTD_decompressContinue(zds, + zds->outBuff + zds->outStart, dstSize, src, srcSize); + FORWARD_IF_ERROR(decodedSize, ""); + if (!decodedSize && !isSkipFrame) { + zds->streamStage = zdss_read; + } else { + zds->outEnd = zds->outStart + decodedSize; + zds->streamStage = zdss_flush; + } + } else { + /* Write directly into the output buffer */ + size_t const dstSize = isSkipFrame ? 0 : (size_t)(oend - *op); + size_t const decodedSize = ZSTD_decompressContinue(zds, *op, dstSize, src, srcSize); + FORWARD_IF_ERROR(decodedSize, ""); + *op += decodedSize; + /* Flushing is not needed. */ + zds->streamStage = zdss_read; + assert(*op <= oend); + assert(zds->outBufferMode == ZSTD_bm_stable); + } + return 0; +} + +size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input) +{ + const char* const src = (const char*)input->src; + const char* const istart = input->pos != 0 ? src + input->pos : src; + const char* const iend = input->size != 0 ? src + input->size : src; + const char* ip = istart; + char* const dst = (char*)output->dst; + char* const ostart = output->pos != 0 ? dst + output->pos : dst; + char* const oend = output->size != 0 ? dst + output->size : dst; + char* op = ostart; + U32 someMoreWork = 1; + + DEBUGLOG(5, "ZSTD_decompressStream"); + RETURN_ERROR_IF( + input->pos > input->size, + srcSize_wrong, + "forbidden. in: pos: %u vs size: %u", + (U32)input->pos, (U32)input->size); + RETURN_ERROR_IF( + output->pos > output->size, + dstSize_tooSmall, + "forbidden. out: pos: %u vs size: %u", + (U32)output->pos, (U32)output->size); + DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos)); + FORWARD_IF_ERROR(ZSTD_checkOutBuffer(zds, output), ""); + + while (someMoreWork) { + switch(zds->streamStage) + { + case zdss_init : + DEBUGLOG(5, "stage zdss_init => transparent reset "); + zds->streamStage = zdss_loadHeader; + zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0; + zds->legacyVersion = 0; + zds->hostageByte = 0; + zds->expectedOutBuffer = *output; + ZSTD_FALLTHROUGH; + + case zdss_loadHeader : + DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip)); + { size_t const hSize = ZSTD_getFrameHeader_advanced(&zds->fParams, zds->headerBuffer, zds->lhSize, zds->format); + if (zds->refMultipleDDicts && zds->ddictSet) { + ZSTD_DCtx_selectFrameDDict(zds); + } + DEBUGLOG(5, "header size : %u", (U32)hSize); + if (ZSTD_isError(hSize)) { + return hSize; /* error */ + } + if (hSize != 0) { /* need more input */ + size_t const toLoad = hSize - zds->lhSize; /* if hSize!=0, hSize > zds->lhSize */ + size_t const remainingInput = (size_t)(iend-ip); + assert(iend >= ip); + if (toLoad > remainingInput) { /* not enough input to load full header */ + if (remainingInput > 0) { + ZSTD_memcpy(zds->headerBuffer + zds->lhSize, ip, remainingInput); + zds->lhSize += remainingInput; + } + input->pos = input->size; + return (MAX((size_t)ZSTD_FRAMEHEADERSIZE_MIN(zds->format), hSize) - zds->lhSize) + ZSTD_blockHeaderSize; /* remaining header bytes + next block header */ + } + assert(ip != NULL); + ZSTD_memcpy(zds->headerBuffer + zds->lhSize, ip, toLoad); zds->lhSize = hSize; ip += toLoad; + break; + } } + + /* check for single-pass mode opportunity */ + if (zds->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN + && zds->fParams.frameType != ZSTD_skippableFrame + && (U64)(size_t)(oend-op) >= zds->fParams.frameContentSize) { + size_t const cSize = ZSTD_findFrameCompressedSize(istart, (size_t)(iend-istart)); + if (cSize <= (size_t)(iend-istart)) { + /* shortcut : using single-pass mode */ + size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, (size_t)(oend-op), istart, cSize, ZSTD_getDDict(zds)); + if (ZSTD_isError(decompressedSize)) return decompressedSize; + DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()") + ip = istart + cSize; + op += decompressedSize; + zds->expected = 0; + zds->streamStage = zdss_init; + someMoreWork = 0; + break; + } } + + /* Check output buffer is large enough for ZSTD_odm_stable. */ + if (zds->outBufferMode == ZSTD_bm_stable + && zds->fParams.frameType != ZSTD_skippableFrame + && zds->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN + && (U64)(size_t)(oend-op) < zds->fParams.frameContentSize) { + RETURN_ERROR(dstSize_tooSmall, "ZSTD_obm_stable passed but ZSTD_outBuffer is too small"); + } + + /* Consume header (see ZSTDds_decodeFrameHeader) */ + DEBUGLOG(4, "Consume header"); + FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, ZSTD_getDDict(zds)), ""); + + if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) { /* skippable frame */ + zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE); + zds->stage = ZSTDds_skipFrame; + } else { + FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize), ""); + zds->expected = ZSTD_blockHeaderSize; + zds->stage = ZSTDds_decodeBlockHeader; + } + + /* control buffer memory usage */ + DEBUGLOG(4, "Control max memory usage (%u KB <= max %u KB)", + (U32)(zds->fParams.windowSize >>10), + (U32)(zds->maxWindowSize >> 10) ); + zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN); + RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize, + frameParameter_windowTooLarge, ""); + + /* Adapt buffer sizes to frame header instructions */ + { size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */); + size_t const neededOutBuffSize = zds->outBufferMode == ZSTD_bm_buffered + ? ZSTD_decodingBufferSize_min(zds->fParams.windowSize, zds->fParams.frameContentSize) + : 0; + + ZSTD_DCtx_updateOversizedDuration(zds, neededInBuffSize, neededOutBuffSize); + + { int const tooSmall = (zds->inBuffSize < neededInBuffSize) || (zds->outBuffSize < neededOutBuffSize); + int const tooLarge = ZSTD_DCtx_isOversizedTooLong(zds); + + if (tooSmall || tooLarge) { + size_t const bufferSize = neededInBuffSize + neededOutBuffSize; + DEBUGLOG(4, "inBuff : from %u to %u", + (U32)zds->inBuffSize, (U32)neededInBuffSize); + DEBUGLOG(4, "outBuff : from %u to %u", + (U32)zds->outBuffSize, (U32)neededOutBuffSize); + if (zds->staticSize) { /* static DCtx */ + DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize); + assert(zds->staticSize >= sizeof(ZSTD_DCtx)); /* controlled at init */ + RETURN_ERROR_IF( + bufferSize > zds->staticSize - sizeof(ZSTD_DCtx), + memory_allocation, ""); + } else { + ZSTD_customFree(zds->inBuff, zds->customMem); + zds->inBuffSize = 0; + zds->outBuffSize = 0; + zds->inBuff = (char*)ZSTD_customMalloc(bufferSize, zds->customMem); + RETURN_ERROR_IF(zds->inBuff == NULL, memory_allocation, ""); + } + zds->inBuffSize = neededInBuffSize; + zds->outBuff = zds->inBuff + zds->inBuffSize; + zds->outBuffSize = neededOutBuffSize; + } } } + zds->streamStage = zdss_read; + ZSTD_FALLTHROUGH; + + case zdss_read: + DEBUGLOG(5, "stage zdss_read"); + { size_t const neededInSize = ZSTD_nextSrcSizeToDecompressWithInputSize(zds, (size_t)(iend - ip)); + DEBUGLOG(5, "neededInSize = %u", (U32)neededInSize); + if (neededInSize==0) { /* end of frame */ + zds->streamStage = zdss_init; + someMoreWork = 0; + break; + } + if ((size_t)(iend-ip) >= neededInSize) { /* decode directly from src */ + FORWARD_IF_ERROR(ZSTD_decompressContinueStream(zds, &op, oend, ip, neededInSize), ""); + ip += neededInSize; + /* Function modifies the stage so we must break */ + break; + } } + if (ip==iend) { someMoreWork = 0; break; } /* no more input */ + zds->streamStage = zdss_load; + ZSTD_FALLTHROUGH; + + case zdss_load: + { size_t const neededInSize = ZSTD_nextSrcSizeToDecompress(zds); + size_t const toLoad = neededInSize - zds->inPos; + int const isSkipFrame = ZSTD_isSkipFrame(zds); + size_t loadedSize; + /* At this point we shouldn't be decompressing a block that we can stream. */ + assert(neededInSize == ZSTD_nextSrcSizeToDecompressWithInputSize(zds, iend - ip)); + if (isSkipFrame) { + loadedSize = MIN(toLoad, (size_t)(iend-ip)); + } else { + RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos, + corruption_detected, + "should never happen"); + loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, (size_t)(iend-ip)); + } + ip += loadedSize; + zds->inPos += loadedSize; + if (loadedSize < toLoad) { someMoreWork = 0; break; } /* not enough input, wait for more */ + + /* decode loaded input */ + zds->inPos = 0; /* input is consumed */ + FORWARD_IF_ERROR(ZSTD_decompressContinueStream(zds, &op, oend, zds->inBuff, neededInSize), ""); + /* Function modifies the stage so we must break */ + break; + } + case zdss_flush: + { size_t const toFlushSize = zds->outEnd - zds->outStart; + size_t const flushedSize = ZSTD_limitCopy(op, (size_t)(oend-op), zds->outBuff + zds->outStart, toFlushSize); + op += flushedSize; + zds->outStart += flushedSize; + if (flushedSize == toFlushSize) { /* flush completed */ + zds->streamStage = zdss_read; + if ( (zds->outBuffSize < zds->fParams.frameContentSize) + && (zds->outStart + zds->fParams.blockSizeMax > zds->outBuffSize) ) { + DEBUGLOG(5, "restart filling outBuff from beginning (left:%i, needed:%u)", + (int)(zds->outBuffSize - zds->outStart), + (U32)zds->fParams.blockSizeMax); + zds->outStart = zds->outEnd = 0; + } + break; + } } + /* cannot complete flush */ + someMoreWork = 0; + break; + + default: + assert(0); /* impossible */ + RETURN_ERROR(GENERIC, "impossible to reach"); /* some compiler require default to do something */ + } } + + /* result */ + input->pos = (size_t)(ip - (const char*)(input->src)); + output->pos = (size_t)(op - (char*)(output->dst)); + + /* Update the expected output buffer for ZSTD_obm_stable. */ + zds->expectedOutBuffer = *output; + + if ((ip==istart) && (op==ostart)) { /* no forward progress */ + zds->noForwardProgress ++; + if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) { + RETURN_ERROR_IF(op==oend, dstSize_tooSmall, ""); + RETURN_ERROR_IF(ip==iend, srcSize_wrong, ""); + assert(0); + } + } else { + zds->noForwardProgress = 0; + } + { size_t nextSrcSizeHint = ZSTD_nextSrcSizeToDecompress(zds); + if (!nextSrcSizeHint) { /* frame fully decoded */ + if (zds->outEnd == zds->outStart) { /* output fully flushed */ + if (zds->hostageByte) { + if (input->pos >= input->size) { + /* can't release hostage (not present) */ + zds->streamStage = zdss_read; + return 1; + } + input->pos++; /* release hostage */ + } /* zds->hostageByte */ + return 0; + } /* zds->outEnd == zds->outStart */ + if (!zds->hostageByte) { /* output not fully flushed; keep last byte as hostage; will be released when all output is flushed */ + input->pos--; /* note : pos > 0, otherwise, impossible to finish reading last block */ + zds->hostageByte=1; + } + return 1; + } /* nextSrcSizeHint==0 */ + nextSrcSizeHint += ZSTD_blockHeaderSize * (ZSTD_nextInputType(zds) == ZSTDnit_block); /* preload header of next block */ + assert(zds->inPos <= nextSrcSizeHint); + nextSrcSizeHint -= zds->inPos; /* part already loaded*/ + return nextSrcSizeHint; + } +} + +size_t ZSTD_decompressStream_simpleArgs ( + ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, size_t* dstPos, + const void* src, size_t srcSize, size_t* srcPos) +{ + ZSTD_outBuffer output = { dst, dstCapacity, *dstPos }; + ZSTD_inBuffer input = { src, srcSize, *srcPos }; + /* ZSTD_compress_generic() will check validity of dstPos and srcPos */ + size_t const cErr = ZSTD_decompressStream(dctx, &output, &input); + *dstPos = output.pos; + *srcPos = input.pos; + return cErr; +} diff --git a/lib/zstd/decompress/zstd_decompress_block.c b/lib/zstd/decompress/zstd_decompress_block.c new file mode 100644 index 000000000000..2d101d9a842e --- /dev/null +++ b/lib/zstd/decompress/zstd_decompress_block.c @@ -0,0 +1,1540 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +/* zstd_decompress_block : + * this module takes care of decompressing _compressed_ block */ + +/*-******************************************************* +* Dependencies +*********************************************************/ +#include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memmove, ZSTD_memset */ +#include "../common/compiler.h" /* prefetch */ +#include "../common/cpu.h" /* bmi2 */ +#include "../common/mem.h" /* low level memory routines */ +#define FSE_STATIC_LINKING_ONLY +#include "../common/fse.h" +#define HUF_STATIC_LINKING_ONLY +#include "../common/huf.h" +#include "../common/zstd_internal.h" +#include "zstd_decompress_internal.h" /* ZSTD_DCtx */ +#include "zstd_ddict.h" /* ZSTD_DDictDictContent */ +#include "zstd_decompress_block.h" + +/*_******************************************************* +* Macros +**********************************************************/ + +/* These two optional macros force the use one way or another of the two + * ZSTD_decompressSequences implementations. You can't force in both directions + * at the same time. + */ +#if defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \ + defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG) +#error "Cannot force the use of the short and the long ZSTD_decompressSequences variants!" +#endif + + +/*_******************************************************* +* Memory operations +**********************************************************/ +static void ZSTD_copy4(void* dst, const void* src) { ZSTD_memcpy(dst, src, 4); } + + +/*-************************************************************* + * Block decoding + ***************************************************************/ + +/*! ZSTD_getcBlockSize() : + * Provides the size of compressed block from block header `src` */ +size_t ZSTD_getcBlockSize(const void* src, size_t srcSize, + blockProperties_t* bpPtr) +{ + RETURN_ERROR_IF(srcSize < ZSTD_blockHeaderSize, srcSize_wrong, ""); + + { U32 const cBlockHeader = MEM_readLE24(src); + U32 const cSize = cBlockHeader >> 3; + bpPtr->lastBlock = cBlockHeader & 1; + bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3); + bpPtr->origSize = cSize; /* only useful for RLE */ + if (bpPtr->blockType == bt_rle) return 1; + RETURN_ERROR_IF(bpPtr->blockType == bt_reserved, corruption_detected, ""); + return cSize; + } +} + + +/* Hidden declaration for fullbench */ +size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, + const void* src, size_t srcSize); +/*! ZSTD_decodeLiteralsBlock() : + * @return : nb of bytes read from src (< srcSize ) + * note : symbol not declared but exposed for fullbench */ +size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx, + const void* src, size_t srcSize) /* note : srcSize < BLOCKSIZE */ +{ + DEBUGLOG(5, "ZSTD_decodeLiteralsBlock"); + RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected, ""); + + { const BYTE* const istart = (const BYTE*) src; + symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3); + + switch(litEncType) + { + case set_repeat: + DEBUGLOG(5, "set_repeat flag : re-using stats from previous compressed literals block"); + RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted, ""); + ZSTD_FALLTHROUGH; + + case set_compressed: + RETURN_ERROR_IF(srcSize < 5, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3"); + { size_t lhSize, litSize, litCSize; + U32 singleStream=0; + U32 const lhlCode = (istart[0] >> 2) & 3; + U32 const lhc = MEM_readLE32(istart); + size_t hufSuccess; + switch(lhlCode) + { + case 0: case 1: default: /* note : default is impossible, since lhlCode into [0..3] */ + /* 2 - 2 - 10 - 10 */ + singleStream = !lhlCode; + lhSize = 3; + litSize = (lhc >> 4) & 0x3FF; + litCSize = (lhc >> 14) & 0x3FF; + break; + case 2: + /* 2 - 2 - 14 - 14 */ + lhSize = 4; + litSize = (lhc >> 4) & 0x3FFF; + litCSize = lhc >> 18; + break; + case 3: + /* 2 - 2 - 18 - 18 */ + lhSize = 5; + litSize = (lhc >> 4) & 0x3FFFF; + litCSize = (lhc >> 22) + ((size_t)istart[4] << 10); + break; + } + RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected, ""); + RETURN_ERROR_IF(litCSize + lhSize > srcSize, corruption_detected, ""); + + /* prefetch huffman table if cold */ + if (dctx->ddictIsCold && (litSize > 768 /* heuristic */)) { + PREFETCH_AREA(dctx->HUFptr, sizeof(dctx->entropy.hufTable)); + } + + if (litEncType==set_repeat) { + if (singleStream) { + hufSuccess = HUF_decompress1X_usingDTable_bmi2( + dctx->litBuffer, litSize, istart+lhSize, litCSize, + dctx->HUFptr, dctx->bmi2); + } else { + hufSuccess = HUF_decompress4X_usingDTable_bmi2( + dctx->litBuffer, litSize, istart+lhSize, litCSize, + dctx->HUFptr, dctx->bmi2); + } + } else { + if (singleStream) { +#if defined(HUF_FORCE_DECOMPRESS_X2) + hufSuccess = HUF_decompress1X_DCtx_wksp( + dctx->entropy.hufTable, dctx->litBuffer, litSize, + istart+lhSize, litCSize, dctx->workspace, + sizeof(dctx->workspace)); +#else + hufSuccess = HUF_decompress1X1_DCtx_wksp_bmi2( + dctx->entropy.hufTable, dctx->litBuffer, litSize, + istart+lhSize, litCSize, dctx->workspace, + sizeof(dctx->workspace), dctx->bmi2); +#endif + } else { + hufSuccess = HUF_decompress4X_hufOnly_wksp_bmi2( + dctx->entropy.hufTable, dctx->litBuffer, litSize, + istart+lhSize, litCSize, dctx->workspace, + sizeof(dctx->workspace), dctx->bmi2); + } + } + + RETURN_ERROR_IF(HUF_isError(hufSuccess), corruption_detected, ""); + + dctx->litPtr = dctx->litBuffer; + dctx->litSize = litSize; + dctx->litEntropy = 1; + if (litEncType==set_compressed) dctx->HUFptr = dctx->entropy.hufTable; + ZSTD_memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH); + return litCSize + lhSize; + } + + case set_basic: + { size_t litSize, lhSize; + U32 const lhlCode = ((istart[0]) >> 2) & 3; + switch(lhlCode) + { + case 0: case 2: default: /* note : default is impossible, since lhlCode into [0..3] */ + lhSize = 1; + litSize = istart[0] >> 3; + break; + case 1: + lhSize = 2; + litSize = MEM_readLE16(istart) >> 4; + break; + case 3: + lhSize = 3; + litSize = MEM_readLE24(istart) >> 4; + break; + } + + if (lhSize+litSize+WILDCOPY_OVERLENGTH > srcSize) { /* risk reading beyond src buffer with wildcopy */ + RETURN_ERROR_IF(litSize+lhSize > srcSize, corruption_detected, ""); + ZSTD_memcpy(dctx->litBuffer, istart+lhSize, litSize); + dctx->litPtr = dctx->litBuffer; + dctx->litSize = litSize; + ZSTD_memset(dctx->litBuffer + dctx->litSize, 0, WILDCOPY_OVERLENGTH); + return lhSize+litSize; + } + /* direct reference into compressed stream */ + dctx->litPtr = istart+lhSize; + dctx->litSize = litSize; + return lhSize+litSize; + } + + case set_rle: + { U32 const lhlCode = ((istart[0]) >> 2) & 3; + size_t litSize, lhSize; + switch(lhlCode) + { + case 0: case 2: default: /* note : default is impossible, since lhlCode into [0..3] */ + lhSize = 1; + litSize = istart[0] >> 3; + break; + case 1: + lhSize = 2; + litSize = MEM_readLE16(istart) >> 4; + break; + case 3: + lhSize = 3; + litSize = MEM_readLE24(istart) >> 4; + RETURN_ERROR_IF(srcSize<4, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4"); + break; + } + RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected, ""); + ZSTD_memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH); + dctx->litPtr = dctx->litBuffer; + dctx->litSize = litSize; + return lhSize+1; + } + default: + RETURN_ERROR(corruption_detected, "impossible"); + } + } +} + +/* Default FSE distribution tables. + * These are pre-calculated FSE decoding tables using default distributions as defined in specification : + * https://github.com/facebook/zstd/blob/release/doc/zstd_compression_format.md#default-distributions + * They were generated programmatically with following method : + * - start from default distributions, present in /lib/common/zstd_internal.h + * - generate tables normally, using ZSTD_buildFSETable() + * - printout the content of tables + * - pretify output, report below, test with fuzzer to ensure it's correct */ + +/* Default FSE distribution table for Literal Lengths */ +static const ZSTD_seqSymbol LL_defaultDTable[(1<tableLog = 0; + DTableH->fastMode = 0; + + cell->nbBits = 0; + cell->nextState = 0; + assert(nbAddBits < 255); + cell->nbAdditionalBits = (BYTE)nbAddBits; + cell->baseValue = baseValue; +} + + +/* ZSTD_buildFSETable() : + * generate FSE decoding table for one symbol (ll, ml or off) + * cannot fail if input is valid => + * all inputs are presumed validated at this stage */ +FORCE_INLINE_TEMPLATE +void ZSTD_buildFSETable_body(ZSTD_seqSymbol* dt, + const short* normalizedCounter, unsigned maxSymbolValue, + const U32* baseValue, const U32* nbAdditionalBits, + unsigned tableLog, void* wksp, size_t wkspSize) +{ + ZSTD_seqSymbol* const tableDecode = dt+1; + U32 const maxSV1 = maxSymbolValue + 1; + U32 const tableSize = 1 << tableLog; + + U16* symbolNext = (U16*)wksp; + BYTE* spread = (BYTE*)(symbolNext + MaxSeq + 1); + U32 highThreshold = tableSize - 1; + + + /* Sanity Checks */ + assert(maxSymbolValue <= MaxSeq); + assert(tableLog <= MaxFSELog); + assert(wkspSize >= ZSTD_BUILD_FSE_TABLE_WKSP_SIZE); + (void)wkspSize; + /* Init, lay down lowprob symbols */ + { ZSTD_seqSymbol_header DTableH; + DTableH.tableLog = tableLog; + DTableH.fastMode = 1; + { S16 const largeLimit= (S16)(1 << (tableLog-1)); + U32 s; + for (s=0; s= largeLimit) DTableH.fastMode=0; + assert(normalizedCounter[s]>=0); + symbolNext[s] = (U16)normalizedCounter[s]; + } } } + ZSTD_memcpy(dt, &DTableH, sizeof(DTableH)); + } + + /* Spread symbols */ + assert(tableSize <= 512); + /* Specialized symbol spreading for the case when there are + * no low probability (-1 count) symbols. When compressing + * small blocks we avoid low probability symbols to hit this + * case, since header decoding speed matters more. + */ + if (highThreshold == tableSize - 1) { + size_t const tableMask = tableSize-1; + size_t const step = FSE_TABLESTEP(tableSize); + /* First lay down the symbols in order. + * We use a uint64_t to lay down 8 bytes at a time. This reduces branch + * misses since small blocks generally have small table logs, so nearly + * all symbols have counts <= 8. We ensure we have 8 bytes at the end of + * our buffer to handle the over-write. + */ + { + U64 const add = 0x0101010101010101ull; + size_t pos = 0; + U64 sv = 0; + U32 s; + for (s=0; s highThreshold) position = (position + step) & tableMask; /* lowprob area */ + } } + assert(position == 0); /* position must reach all cells once, otherwise normalizedCounter is incorrect */ + } + + /* Build Decoding table */ + { + U32 u; + for (u=0; u max, corruption_detected, ""); + { U32 const symbol = *(const BYTE*)src; + U32 const baseline = baseValue[symbol]; + U32 const nbBits = nbAdditionalBits[symbol]; + ZSTD_buildSeqTable_rle(DTableSpace, baseline, nbBits); + } + *DTablePtr = DTableSpace; + return 1; + case set_basic : + *DTablePtr = defaultTable; + return 0; + case set_repeat: + RETURN_ERROR_IF(!flagRepeatTable, corruption_detected, ""); + /* prefetch FSE table if used */ + if (ddictIsCold && (nbSeq > 24 /* heuristic */)) { + const void* const pStart = *DTablePtr; + size_t const pSize = sizeof(ZSTD_seqSymbol) * (SEQSYMBOL_TABLE_SIZE(maxLog)); + PREFETCH_AREA(pStart, pSize); + } + return 0; + case set_compressed : + { unsigned tableLog; + S16 norm[MaxSeq+1]; + size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize); + RETURN_ERROR_IF(FSE_isError(headerSize), corruption_detected, ""); + RETURN_ERROR_IF(tableLog > maxLog, corruption_detected, ""); + ZSTD_buildFSETable(DTableSpace, norm, max, baseValue, nbAdditionalBits, tableLog, wksp, wkspSize, bmi2); + *DTablePtr = DTableSpace; + return headerSize; + } + default : + assert(0); + RETURN_ERROR(GENERIC, "impossible"); + } +} + +size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, + const void* src, size_t srcSize) +{ + const BYTE* const istart = (const BYTE*)src; + const BYTE* const iend = istart + srcSize; + const BYTE* ip = istart; + int nbSeq; + DEBUGLOG(5, "ZSTD_decodeSeqHeaders"); + + /* check */ + RETURN_ERROR_IF(srcSize < MIN_SEQUENCES_SIZE, srcSize_wrong, ""); + + /* SeqHead */ + nbSeq = *ip++; + if (!nbSeq) { + *nbSeqPtr=0; + RETURN_ERROR_IF(srcSize != 1, srcSize_wrong, ""); + return 1; + } + if (nbSeq > 0x7F) { + if (nbSeq == 0xFF) { + RETURN_ERROR_IF(ip+2 > iend, srcSize_wrong, ""); + nbSeq = MEM_readLE16(ip) + LONGNBSEQ; + ip+=2; + } else { + RETURN_ERROR_IF(ip >= iend, srcSize_wrong, ""); + nbSeq = ((nbSeq-0x80)<<8) + *ip++; + } + } + *nbSeqPtr = nbSeq; + + /* FSE table descriptors */ + RETURN_ERROR_IF(ip+1 > iend, srcSize_wrong, ""); /* minimum possible size: 1 byte for symbol encoding types */ + { symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6); + symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3); + symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3); + ip++; + + /* Build DTables */ + { size_t const llhSize = ZSTD_buildSeqTable(dctx->entropy.LLTable, &dctx->LLTptr, + LLtype, MaxLL, LLFSELog, + ip, iend-ip, + LL_base, LL_bits, + LL_defaultDTable, dctx->fseEntropy, + dctx->ddictIsCold, nbSeq, + dctx->workspace, sizeof(dctx->workspace), + dctx->bmi2); + RETURN_ERROR_IF(ZSTD_isError(llhSize), corruption_detected, "ZSTD_buildSeqTable failed"); + ip += llhSize; + } + + { size_t const ofhSize = ZSTD_buildSeqTable(dctx->entropy.OFTable, &dctx->OFTptr, + OFtype, MaxOff, OffFSELog, + ip, iend-ip, + OF_base, OF_bits, + OF_defaultDTable, dctx->fseEntropy, + dctx->ddictIsCold, nbSeq, + dctx->workspace, sizeof(dctx->workspace), + dctx->bmi2); + RETURN_ERROR_IF(ZSTD_isError(ofhSize), corruption_detected, "ZSTD_buildSeqTable failed"); + ip += ofhSize; + } + + { size_t const mlhSize = ZSTD_buildSeqTable(dctx->entropy.MLTable, &dctx->MLTptr, + MLtype, MaxML, MLFSELog, + ip, iend-ip, + ML_base, ML_bits, + ML_defaultDTable, dctx->fseEntropy, + dctx->ddictIsCold, nbSeq, + dctx->workspace, sizeof(dctx->workspace), + dctx->bmi2); + RETURN_ERROR_IF(ZSTD_isError(mlhSize), corruption_detected, "ZSTD_buildSeqTable failed"); + ip += mlhSize; + } + } + + return ip-istart; +} + + +typedef struct { + size_t litLength; + size_t matchLength; + size_t offset; + const BYTE* match; +} seq_t; + +typedef struct { + size_t state; + const ZSTD_seqSymbol* table; +} ZSTD_fseState; + +typedef struct { + BIT_DStream_t DStream; + ZSTD_fseState stateLL; + ZSTD_fseState stateOffb; + ZSTD_fseState stateML; + size_t prevOffset[ZSTD_REP_NUM]; + const BYTE* prefixStart; + const BYTE* dictEnd; + size_t pos; +} seqState_t; + +/*! ZSTD_overlapCopy8() : + * Copies 8 bytes from ip to op and updates op and ip where ip <= op. + * If the offset is < 8 then the offset is spread to at least 8 bytes. + * + * Precondition: *ip <= *op + * Postcondition: *op - *op >= 8 + */ +HINT_INLINE void ZSTD_overlapCopy8(BYTE** op, BYTE const** ip, size_t offset) { + assert(*ip <= *op); + if (offset < 8) { + /* close range match, overlap */ + static const U32 dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 }; /* added */ + static const int dec64table[] = { 8, 8, 8, 7, 8, 9,10,11 }; /* subtracted */ + int const sub2 = dec64table[offset]; + (*op)[0] = (*ip)[0]; + (*op)[1] = (*ip)[1]; + (*op)[2] = (*ip)[2]; + (*op)[3] = (*ip)[3]; + *ip += dec32table[offset]; + ZSTD_copy4(*op+4, *ip); + *ip -= sub2; + } else { + ZSTD_copy8(*op, *ip); + } + *ip += 8; + *op += 8; + assert(*op - *ip >= 8); +} + +/*! ZSTD_safecopy() : + * Specialized version of memcpy() that is allowed to READ up to WILDCOPY_OVERLENGTH past the input buffer + * and write up to 16 bytes past oend_w (op >= oend_w is allowed). + * This function is only called in the uncommon case where the sequence is near the end of the block. It + * should be fast for a single long sequence, but can be slow for several short sequences. + * + * @param ovtype controls the overlap detection + * - ZSTD_no_overlap: The source and destination are guaranteed to be at least WILDCOPY_VECLEN bytes apart. + * - ZSTD_overlap_src_before_dst: The src and dst may overlap and may be any distance apart. + * The src buffer must be before the dst buffer. + */ +static void ZSTD_safecopy(BYTE* op, BYTE* const oend_w, BYTE const* ip, ptrdiff_t length, ZSTD_overlap_e ovtype) { + ptrdiff_t const diff = op - ip; + BYTE* const oend = op + length; + + assert((ovtype == ZSTD_no_overlap && (diff <= -8 || diff >= 8 || op >= oend_w)) || + (ovtype == ZSTD_overlap_src_before_dst && diff >= 0)); + + if (length < 8) { + /* Handle short lengths. */ + while (op < oend) *op++ = *ip++; + return; + } + if (ovtype == ZSTD_overlap_src_before_dst) { + /* Copy 8 bytes and ensure the offset >= 8 when there can be overlap. */ + assert(length >= 8); + ZSTD_overlapCopy8(&op, &ip, diff); + assert(op - ip >= 8); + assert(op <= oend); + } + + if (oend <= oend_w) { + /* No risk of overwrite. */ + ZSTD_wildcopy(op, ip, length, ovtype); + return; + } + if (op <= oend_w) { + /* Wildcopy until we get close to the end. */ + assert(oend > oend_w); + ZSTD_wildcopy(op, ip, oend_w - op, ovtype); + ip += oend_w - op; + op = oend_w; + } + /* Handle the leftovers. */ + while (op < oend) *op++ = *ip++; +} + +/* ZSTD_execSequenceEnd(): + * This version handles cases that are near the end of the output buffer. It requires + * more careful checks to make sure there is no overflow. By separating out these hard + * and unlikely cases, we can speed up the common cases. + * + * NOTE: This function needs to be fast for a single long sequence, but doesn't need + * to be optimized for many small sequences, since those fall into ZSTD_execSequence(). + */ +FORCE_NOINLINE +size_t ZSTD_execSequenceEnd(BYTE* op, + BYTE* const oend, seq_t sequence, + const BYTE** litPtr, const BYTE* const litLimit, + const BYTE* const prefixStart, const BYTE* const virtualStart, const BYTE* const dictEnd) +{ + BYTE* const oLitEnd = op + sequence.litLength; + size_t const sequenceLength = sequence.litLength + sequence.matchLength; + const BYTE* const iLitEnd = *litPtr + sequence.litLength; + const BYTE* match = oLitEnd - sequence.offset; + BYTE* const oend_w = oend - WILDCOPY_OVERLENGTH; + + /* bounds checks : careful of address space overflow in 32-bit mode */ + RETURN_ERROR_IF(sequenceLength > (size_t)(oend - op), dstSize_tooSmall, "last match must fit within dstBuffer"); + RETURN_ERROR_IF(sequence.litLength > (size_t)(litLimit - *litPtr), corruption_detected, "try to read beyond literal buffer"); + assert(op < op + sequenceLength); + assert(oLitEnd < op + sequenceLength); + + /* copy literals */ + ZSTD_safecopy(op, oend_w, *litPtr, sequence.litLength, ZSTD_no_overlap); + op = oLitEnd; + *litPtr = iLitEnd; + + /* copy Match */ + if (sequence.offset > (size_t)(oLitEnd - prefixStart)) { + /* offset beyond prefix */ + RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - virtualStart), corruption_detected, ""); + match = dictEnd - (prefixStart-match); + if (match + sequence.matchLength <= dictEnd) { + ZSTD_memmove(oLitEnd, match, sequence.matchLength); + return sequenceLength; + } + /* span extDict & currentPrefixSegment */ + { size_t const length1 = dictEnd - match; + ZSTD_memmove(oLitEnd, match, length1); + op = oLitEnd + length1; + sequence.matchLength -= length1; + match = prefixStart; + } } + ZSTD_safecopy(op, oend_w, match, sequence.matchLength, ZSTD_overlap_src_before_dst); + return sequenceLength; +} + +HINT_INLINE +size_t ZSTD_execSequence(BYTE* op, + BYTE* const oend, seq_t sequence, + const BYTE** litPtr, const BYTE* const litLimit, + const BYTE* const prefixStart, const BYTE* const virtualStart, const BYTE* const dictEnd) +{ + BYTE* const oLitEnd = op + sequence.litLength; + size_t const sequenceLength = sequence.litLength + sequence.matchLength; + BYTE* const oMatchEnd = op + sequenceLength; /* risk : address space overflow (32-bits) */ + BYTE* const oend_w = oend - WILDCOPY_OVERLENGTH; /* risk : address space underflow on oend=NULL */ + const BYTE* const iLitEnd = *litPtr + sequence.litLength; + const BYTE* match = oLitEnd - sequence.offset; + + assert(op != NULL /* Precondition */); + assert(oend_w < oend /* No underflow */); + /* Handle edge cases in a slow path: + * - Read beyond end of literals + * - Match end is within WILDCOPY_OVERLIMIT of oend + * - 32-bit mode and the match length overflows + */ + if (UNLIKELY( + iLitEnd > litLimit || + oMatchEnd > oend_w || + (MEM_32bits() && (size_t)(oend - op) < sequenceLength + WILDCOPY_OVERLENGTH))) + return ZSTD_execSequenceEnd(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd); + + /* Assumptions (everything else goes into ZSTD_execSequenceEnd()) */ + assert(op <= oLitEnd /* No overflow */); + assert(oLitEnd < oMatchEnd /* Non-zero match & no overflow */); + assert(oMatchEnd <= oend /* No underflow */); + assert(iLitEnd <= litLimit /* Literal length is in bounds */); + assert(oLitEnd <= oend_w /* Can wildcopy literals */); + assert(oMatchEnd <= oend_w /* Can wildcopy matches */); + + /* Copy Literals: + * Split out litLength <= 16 since it is nearly always true. +1.6% on gcc-9. + * We likely don't need the full 32-byte wildcopy. + */ + assert(WILDCOPY_OVERLENGTH >= 16); + ZSTD_copy16(op, (*litPtr)); + if (UNLIKELY(sequence.litLength > 16)) { + ZSTD_wildcopy(op+16, (*litPtr)+16, sequence.litLength-16, ZSTD_no_overlap); + } + op = oLitEnd; + *litPtr = iLitEnd; /* update for next sequence */ + + /* Copy Match */ + if (sequence.offset > (size_t)(oLitEnd - prefixStart)) { + /* offset beyond prefix -> go into extDict */ + RETURN_ERROR_IF(UNLIKELY(sequence.offset > (size_t)(oLitEnd - virtualStart)), corruption_detected, ""); + match = dictEnd + (match - prefixStart); + if (match + sequence.matchLength <= dictEnd) { + ZSTD_memmove(oLitEnd, match, sequence.matchLength); + return sequenceLength; + } + /* span extDict & currentPrefixSegment */ + { size_t const length1 = dictEnd - match; + ZSTD_memmove(oLitEnd, match, length1); + op = oLitEnd + length1; + sequence.matchLength -= length1; + match = prefixStart; + } } + /* Match within prefix of 1 or more bytes */ + assert(op <= oMatchEnd); + assert(oMatchEnd <= oend_w); + assert(match >= prefixStart); + assert(sequence.matchLength >= 1); + + /* Nearly all offsets are >= WILDCOPY_VECLEN bytes, which means we can use wildcopy + * without overlap checking. + */ + if (LIKELY(sequence.offset >= WILDCOPY_VECLEN)) { + /* We bet on a full wildcopy for matches, since we expect matches to be + * longer than literals (in general). In silesia, ~10% of matches are longer + * than 16 bytes. + */ + ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength, ZSTD_no_overlap); + return sequenceLength; + } + assert(sequence.offset < WILDCOPY_VECLEN); + + /* Copy 8 bytes and spread the offset to be >= 8. */ + ZSTD_overlapCopy8(&op, &match, sequence.offset); + + /* If the match length is > 8 bytes, then continue with the wildcopy. */ + if (sequence.matchLength > 8) { + assert(op < oMatchEnd); + ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8, ZSTD_overlap_src_before_dst); + } + return sequenceLength; +} + +static void +ZSTD_initFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD, const ZSTD_seqSymbol* dt) +{ + const void* ptr = dt; + const ZSTD_seqSymbol_header* const DTableH = (const ZSTD_seqSymbol_header*)ptr; + DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog); + DEBUGLOG(6, "ZSTD_initFseState : val=%u using %u bits", + (U32)DStatePtr->state, DTableH->tableLog); + BIT_reloadDStream(bitD); + DStatePtr->table = dt + 1; +} + +FORCE_INLINE_TEMPLATE void +ZSTD_updateFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD) +{ + ZSTD_seqSymbol const DInfo = DStatePtr->table[DStatePtr->state]; + U32 const nbBits = DInfo.nbBits; + size_t const lowBits = BIT_readBits(bitD, nbBits); + DStatePtr->state = DInfo.nextState + lowBits; +} + +FORCE_INLINE_TEMPLATE void +ZSTD_updateFseStateWithDInfo(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD, ZSTD_seqSymbol const DInfo) +{ + U32 const nbBits = DInfo.nbBits; + size_t const lowBits = BIT_readBits(bitD, nbBits); + DStatePtr->state = DInfo.nextState + lowBits; +} + +/* We need to add at most (ZSTD_WINDOWLOG_MAX_32 - 1) bits to read the maximum + * offset bits. But we can only read at most (STREAM_ACCUMULATOR_MIN_32 - 1) + * bits before reloading. This value is the maximum number of bytes we read + * after reloading when we are decoding long offsets. + */ +#define LONG_OFFSETS_MAX_EXTRA_BITS_32 \ + (ZSTD_WINDOWLOG_MAX_32 > STREAM_ACCUMULATOR_MIN_32 \ + ? ZSTD_WINDOWLOG_MAX_32 - STREAM_ACCUMULATOR_MIN_32 \ + : 0) + +typedef enum { ZSTD_lo_isRegularOffset, ZSTD_lo_isLongOffset=1 } ZSTD_longOffset_e; +typedef enum { ZSTD_p_noPrefetch=0, ZSTD_p_prefetch=1 } ZSTD_prefetch_e; + +FORCE_INLINE_TEMPLATE seq_t +ZSTD_decodeSequence(seqState_t* seqState, const ZSTD_longOffset_e longOffsets, const ZSTD_prefetch_e prefetch) +{ + seq_t seq; + ZSTD_seqSymbol const llDInfo = seqState->stateLL.table[seqState->stateLL.state]; + ZSTD_seqSymbol const mlDInfo = seqState->stateML.table[seqState->stateML.state]; + ZSTD_seqSymbol const ofDInfo = seqState->stateOffb.table[seqState->stateOffb.state]; + U32 const llBase = llDInfo.baseValue; + U32 const mlBase = mlDInfo.baseValue; + U32 const ofBase = ofDInfo.baseValue; + BYTE const llBits = llDInfo.nbAdditionalBits; + BYTE const mlBits = mlDInfo.nbAdditionalBits; + BYTE const ofBits = ofDInfo.nbAdditionalBits; + BYTE const totalBits = llBits+mlBits+ofBits; + + /* sequence */ + { size_t offset; + if (ofBits > 1) { + ZSTD_STATIC_ASSERT(ZSTD_lo_isLongOffset == 1); + ZSTD_STATIC_ASSERT(LONG_OFFSETS_MAX_EXTRA_BITS_32 == 5); + assert(ofBits <= MaxOff); + if (MEM_32bits() && longOffsets && (ofBits >= STREAM_ACCUMULATOR_MIN_32)) { + U32 const extraBits = ofBits - MIN(ofBits, 32 - seqState->DStream.bitsConsumed); + offset = ofBase + (BIT_readBitsFast(&seqState->DStream, ofBits - extraBits) << extraBits); + BIT_reloadDStream(&seqState->DStream); + if (extraBits) offset += BIT_readBitsFast(&seqState->DStream, extraBits); + assert(extraBits <= LONG_OFFSETS_MAX_EXTRA_BITS_32); /* to avoid another reload */ + } else { + offset = ofBase + BIT_readBitsFast(&seqState->DStream, ofBits/*>0*/); /* <= (ZSTD_WINDOWLOG_MAX-1) bits */ + if (MEM_32bits()) BIT_reloadDStream(&seqState->DStream); + } + seqState->prevOffset[2] = seqState->prevOffset[1]; + seqState->prevOffset[1] = seqState->prevOffset[0]; + seqState->prevOffset[0] = offset; + } else { + U32 const ll0 = (llBase == 0); + if (LIKELY((ofBits == 0))) { + if (LIKELY(!ll0)) + offset = seqState->prevOffset[0]; + else { + offset = seqState->prevOffset[1]; + seqState->prevOffset[1] = seqState->prevOffset[0]; + seqState->prevOffset[0] = offset; + } + } else { + offset = ofBase + ll0 + BIT_readBitsFast(&seqState->DStream, 1); + { size_t temp = (offset==3) ? seqState->prevOffset[0] - 1 : seqState->prevOffset[offset]; + temp += !temp; /* 0 is not valid; input is corrupted; force offset to 1 */ + if (offset != 1) seqState->prevOffset[2] = seqState->prevOffset[1]; + seqState->prevOffset[1] = seqState->prevOffset[0]; + seqState->prevOffset[0] = offset = temp; + } } } + seq.offset = offset; + } + + seq.matchLength = mlBase; + if (mlBits > 0) + seq.matchLength += BIT_readBitsFast(&seqState->DStream, mlBits/*>0*/); + + if (MEM_32bits() && (mlBits+llBits >= STREAM_ACCUMULATOR_MIN_32-LONG_OFFSETS_MAX_EXTRA_BITS_32)) + BIT_reloadDStream(&seqState->DStream); + if (MEM_64bits() && UNLIKELY(totalBits >= STREAM_ACCUMULATOR_MIN_64-(LLFSELog+MLFSELog+OffFSELog))) + BIT_reloadDStream(&seqState->DStream); + /* Ensure there are enough bits to read the rest of data in 64-bit mode. */ + ZSTD_STATIC_ASSERT(16+LLFSELog+MLFSELog+OffFSELog < STREAM_ACCUMULATOR_MIN_64); + + seq.litLength = llBase; + if (llBits > 0) + seq.litLength += BIT_readBitsFast(&seqState->DStream, llBits/*>0*/); + + if (MEM_32bits()) + BIT_reloadDStream(&seqState->DStream); + + DEBUGLOG(6, "seq: litL=%u, matchL=%u, offset=%u", + (U32)seq.litLength, (U32)seq.matchLength, (U32)seq.offset); + + if (prefetch == ZSTD_p_prefetch) { + size_t const pos = seqState->pos + seq.litLength; + const BYTE* const matchBase = (seq.offset > pos) ? seqState->dictEnd : seqState->prefixStart; + seq.match = matchBase + pos - seq.offset; /* note : this operation can overflow when seq.offset is really too large, which can only happen when input is corrupted. + * No consequence though : no memory access will occur, offset is only used for prefetching */ + seqState->pos = pos + seq.matchLength; + } + + /* ANS state update + * gcc-9.0.0 does 2.5% worse with ZSTD_updateFseStateWithDInfo(). + * clang-9.2.0 does 7% worse with ZSTD_updateFseState(). + * Naturally it seems like ZSTD_updateFseStateWithDInfo() should be the + * better option, so it is the default for other compilers. But, if you + * measure that it is worse, please put up a pull request. + */ + { +#if !defined(__clang__) + const int kUseUpdateFseState = 1; +#else + const int kUseUpdateFseState = 0; +#endif + if (kUseUpdateFseState) { + ZSTD_updateFseState(&seqState->stateLL, &seqState->DStream); /* <= 9 bits */ + ZSTD_updateFseState(&seqState->stateML, &seqState->DStream); /* <= 9 bits */ + if (MEM_32bits()) BIT_reloadDStream(&seqState->DStream); /* <= 18 bits */ + ZSTD_updateFseState(&seqState->stateOffb, &seqState->DStream); /* <= 8 bits */ + } else { + ZSTD_updateFseStateWithDInfo(&seqState->stateLL, &seqState->DStream, llDInfo); /* <= 9 bits */ + ZSTD_updateFseStateWithDInfo(&seqState->stateML, &seqState->DStream, mlDInfo); /* <= 9 bits */ + if (MEM_32bits()) BIT_reloadDStream(&seqState->DStream); /* <= 18 bits */ + ZSTD_updateFseStateWithDInfo(&seqState->stateOffb, &seqState->DStream, ofDInfo); /* <= 8 bits */ + } + } + + return seq; +} + +#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION +MEM_STATIC int ZSTD_dictionaryIsActive(ZSTD_DCtx const* dctx, BYTE const* prefixStart, BYTE const* oLitEnd) +{ + size_t const windowSize = dctx->fParams.windowSize; + /* No dictionary used. */ + if (dctx->dictContentEndForFuzzing == NULL) return 0; + /* Dictionary is our prefix. */ + if (prefixStart == dctx->dictContentBeginForFuzzing) return 1; + /* Dictionary is not our ext-dict. */ + if (dctx->dictEnd != dctx->dictContentEndForFuzzing) return 0; + /* Dictionary is not within our window size. */ + if ((size_t)(oLitEnd - prefixStart) >= windowSize) return 0; + /* Dictionary is active. */ + return 1; +} + +MEM_STATIC void ZSTD_assertValidSequence( + ZSTD_DCtx const* dctx, + BYTE const* op, BYTE const* oend, + seq_t const seq, + BYTE const* prefixStart, BYTE const* virtualStart) +{ +#if DEBUGLEVEL >= 1 + size_t const windowSize = dctx->fParams.windowSize; + size_t const sequenceSize = seq.litLength + seq.matchLength; + BYTE const* const oLitEnd = op + seq.litLength; + DEBUGLOG(6, "Checking sequence: litL=%u matchL=%u offset=%u", + (U32)seq.litLength, (U32)seq.matchLength, (U32)seq.offset); + assert(op <= oend); + assert((size_t)(oend - op) >= sequenceSize); + assert(sequenceSize <= ZSTD_BLOCKSIZE_MAX); + if (ZSTD_dictionaryIsActive(dctx, prefixStart, oLitEnd)) { + size_t const dictSize = (size_t)((char const*)dctx->dictContentEndForFuzzing - (char const*)dctx->dictContentBeginForFuzzing); + /* Offset must be within the dictionary. */ + assert(seq.offset <= (size_t)(oLitEnd - virtualStart)); + assert(seq.offset <= windowSize + dictSize); + } else { + /* Offset must be within our window. */ + assert(seq.offset <= windowSize); + } +#else + (void)dctx, (void)op, (void)oend, (void)seq, (void)prefixStart, (void)virtualStart; +#endif +} +#endif + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG +FORCE_INLINE_TEMPLATE size_t +DONT_VECTORIZE +ZSTD_decompressSequences_body( ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + const BYTE* ip = (const BYTE*)seqStart; + const BYTE* const iend = ip + seqSize; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + maxDstSize; + BYTE* op = ostart; + const BYTE* litPtr = dctx->litPtr; + const BYTE* const litEnd = litPtr + dctx->litSize; + const BYTE* const prefixStart = (const BYTE*) (dctx->prefixStart); + const BYTE* const vBase = (const BYTE*) (dctx->virtualStart); + const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd); + DEBUGLOG(5, "ZSTD_decompressSequences_body"); + (void)frame; + + /* Regen sequences */ + if (nbSeq) { + seqState_t seqState; + size_t error = 0; + dctx->fseEntropy = 1; + { U32 i; for (i=0; ientropy.rep[i]; } + RETURN_ERROR_IF( + ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)), + corruption_detected, ""); + ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr); + ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr); + ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr); + assert(dst != NULL); + + ZSTD_STATIC_ASSERT( + BIT_DStream_unfinished < BIT_DStream_completed && + BIT_DStream_endOfBuffer < BIT_DStream_completed && + BIT_DStream_completed < BIT_DStream_overflow); + +#if defined(__x86_64__) + /* Align the decompression loop to 32 + 16 bytes. + * + * zstd compiled with gcc-9 on an Intel i9-9900k shows 10% decompression + * speed swings based on the alignment of the decompression loop. This + * performance swing is caused by parts of the decompression loop falling + * out of the DSB. The entire decompression loop should fit in the DSB, + * when it can't we get much worse performance. You can measure if you've + * hit the good case or the bad case with this perf command for some + * compressed file test.zst: + * + * perf stat -e cycles -e instructions -e idq.all_dsb_cycles_any_uops \ + * -e idq.all_mite_cycles_any_uops -- ./zstd -tq test.zst + * + * If you see most cycles served out of the MITE you've hit the bad case. + * If you see most cycles served out of the DSB you've hit the good case. + * If it is pretty even then you may be in an okay case. + * + * I've been able to reproduce this issue on the following CPUs: + * - Kabylake: Macbook Pro (15-inch, 2019) 2.4 GHz Intel Core i9 + * Use Instruments->Counters to get DSB/MITE cycles. + * I never got performance swings, but I was able to + * go from the good case of mostly DSB to half of the + * cycles served from MITE. + * - Coffeelake: Intel i9-9900k + * + * I haven't been able to reproduce the instability or DSB misses on any + * of the following CPUS: + * - Haswell + * - Broadwell: Intel(R) Xeon(R) CPU E5-2680 v4 @ 2.40GH + * - Skylake + * + * If you are seeing performance stability this script can help test. + * It tests on 4 commits in zstd where I saw performance change. + * + * https://gist.github.com/terrelln/9889fc06a423fd5ca6e99351564473f4 + */ + __asm__(".p2align 5"); + __asm__("nop"); + __asm__(".p2align 4"); +#endif + for ( ; ; ) { + seq_t const sequence = ZSTD_decodeSequence(&seqState, isLongOffset, ZSTD_p_noPrefetch); + size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, prefixStart, vBase, dictEnd); +#if defined(FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION) && defined(FUZZING_ASSERT_VALID_SEQUENCE) + assert(!ZSTD_isError(oneSeqSize)); + if (frame) ZSTD_assertValidSequence(dctx, op, oend, sequence, prefixStart, vBase); +#endif + DEBUGLOG(6, "regenerated sequence size : %u", (U32)oneSeqSize); + BIT_reloadDStream(&(seqState.DStream)); + op += oneSeqSize; + /* gcc and clang both don't like early returns in this loop. + * Instead break and check for an error at the end of the loop. + */ + if (UNLIKELY(ZSTD_isError(oneSeqSize))) { + error = oneSeqSize; + break; + } + if (UNLIKELY(!--nbSeq)) break; + } + + /* check if reached exact end */ + DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq); + if (ZSTD_isError(error)) return error; + RETURN_ERROR_IF(nbSeq, corruption_detected, ""); + RETURN_ERROR_IF(BIT_reloadDStream(&seqState.DStream) < BIT_DStream_completed, corruption_detected, ""); + /* save reps for next block */ + { U32 i; for (i=0; ientropy.rep[i] = (U32)(seqState.prevOffset[i]); } + } + + /* last literal segment */ + { size_t const lastLLSize = litEnd - litPtr; + RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall, ""); + if (op != NULL) { + ZSTD_memcpy(op, litPtr, lastLLSize); + op += lastLLSize; + } + } + + return op-ostart; +} + +static size_t +ZSTD_decompressSequences_default(ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + return ZSTD_decompressSequences_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); +} +#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */ + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT +FORCE_INLINE_TEMPLATE size_t +ZSTD_decompressSequencesLong_body( + ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + const BYTE* ip = (const BYTE*)seqStart; + const BYTE* const iend = ip + seqSize; + BYTE* const ostart = (BYTE*)dst; + BYTE* const oend = ostart + maxDstSize; + BYTE* op = ostart; + const BYTE* litPtr = dctx->litPtr; + const BYTE* const litEnd = litPtr + dctx->litSize; + const BYTE* const prefixStart = (const BYTE*) (dctx->prefixStart); + const BYTE* const dictStart = (const BYTE*) (dctx->virtualStart); + const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd); + (void)frame; + + /* Regen sequences */ + if (nbSeq) { +#define STORED_SEQS 4 +#define STORED_SEQS_MASK (STORED_SEQS-1) +#define ADVANCED_SEQS 4 + seq_t sequences[STORED_SEQS]; + int const seqAdvance = MIN(nbSeq, ADVANCED_SEQS); + seqState_t seqState; + int seqNb; + dctx->fseEntropy = 1; + { int i; for (i=0; ientropy.rep[i]; } + seqState.prefixStart = prefixStart; + seqState.pos = (size_t)(op-prefixStart); + seqState.dictEnd = dictEnd; + assert(dst != NULL); + assert(iend >= ip); + RETURN_ERROR_IF( + ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)), + corruption_detected, ""); + ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr); + ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr); + ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr); + + /* prepare in advance */ + for (seqNb=0; (BIT_reloadDStream(&seqState.DStream) <= BIT_DStream_completed) && (seqNbentropy.rep[i] = (U32)(seqState.prevOffset[i]); } + } + + /* last literal segment */ + { size_t const lastLLSize = litEnd - litPtr; + RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall, ""); + if (op != NULL) { + ZSTD_memcpy(op, litPtr, lastLLSize); + op += lastLLSize; + } + } + + return op-ostart; +} + +static size_t +ZSTD_decompressSequencesLong_default(ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + return ZSTD_decompressSequencesLong_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); +} +#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */ + + + +#if DYNAMIC_BMI2 + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG +static TARGET_ATTRIBUTE("bmi2") size_t +DONT_VECTORIZE +ZSTD_decompressSequences_bmi2(ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + return ZSTD_decompressSequences_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); +} +#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */ + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT +static TARGET_ATTRIBUTE("bmi2") size_t +ZSTD_decompressSequencesLong_bmi2(ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + return ZSTD_decompressSequencesLong_body(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); +} +#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */ + +#endif /* DYNAMIC_BMI2 */ + +typedef size_t (*ZSTD_decompressSequences_t)( + ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame); + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG +static size_t +ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + DEBUGLOG(5, "ZSTD_decompressSequences"); +#if DYNAMIC_BMI2 + if (dctx->bmi2) { + return ZSTD_decompressSequences_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); + } +#endif + return ZSTD_decompressSequences_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); +} +#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG */ + + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT +/* ZSTD_decompressSequencesLong() : + * decompression function triggered when a minimum share of offsets is considered "long", + * aka out of cache. + * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes meaning "farther than memory cache distance". + * This function will try to mitigate main memory latency through the use of prefetching */ +static size_t +ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx, + void* dst, size_t maxDstSize, + const void* seqStart, size_t seqSize, int nbSeq, + const ZSTD_longOffset_e isLongOffset, + const int frame) +{ + DEBUGLOG(5, "ZSTD_decompressSequencesLong"); +#if DYNAMIC_BMI2 + if (dctx->bmi2) { + return ZSTD_decompressSequencesLong_bmi2(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); + } +#endif + return ZSTD_decompressSequencesLong_default(dctx, dst, maxDstSize, seqStart, seqSize, nbSeq, isLongOffset, frame); +} +#endif /* ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT */ + + + +#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \ + !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG) +/* ZSTD_getLongOffsetsShare() : + * condition : offTable must be valid + * @return : "share" of long offsets (arbitrarily defined as > (1<<23)) + * compared to maximum possible of (1< 22) total += 1; + } + + assert(tableLog <= OffFSELog); + total <<= (OffFSELog - tableLog); /* scale to OffFSELog */ + + return total; +} +#endif + +size_t +ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, const int frame) +{ /* blockType == blockCompressed */ + const BYTE* ip = (const BYTE*)src; + /* isLongOffset must be true if there are long offsets. + * Offsets are long if they are larger than 2^STREAM_ACCUMULATOR_MIN. + * We don't expect that to be the case in 64-bit mode. + * In block mode, window size is not known, so we have to be conservative. + * (note: but it could be evaluated from current-lowLimit) + */ + ZSTD_longOffset_e const isLongOffset = (ZSTD_longOffset_e)(MEM_32bits() && (!frame || (dctx->fParams.windowSize > (1ULL << STREAM_ACCUMULATOR_MIN)))); + DEBUGLOG(5, "ZSTD_decompressBlock_internal (size : %u)", (U32)srcSize); + + RETURN_ERROR_IF(srcSize >= ZSTD_BLOCKSIZE_MAX, srcSize_wrong, ""); + + /* Decode literals section */ + { size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize); + DEBUGLOG(5, "ZSTD_decodeLiteralsBlock : %u", (U32)litCSize); + if (ZSTD_isError(litCSize)) return litCSize; + ip += litCSize; + srcSize -= litCSize; + } + + /* Build Decoding Tables */ + { + /* These macros control at build-time which decompressor implementation + * we use. If neither is defined, we do some inspection and dispatch at + * runtime. + */ +#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \ + !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG) + int usePrefetchDecoder = dctx->ddictIsCold; +#endif + int nbSeq; + size_t const seqHSize = ZSTD_decodeSeqHeaders(dctx, &nbSeq, ip, srcSize); + if (ZSTD_isError(seqHSize)) return seqHSize; + ip += seqHSize; + srcSize -= seqHSize; + + RETURN_ERROR_IF(dst == NULL && nbSeq > 0, dstSize_tooSmall, "NULL not handled"); + +#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \ + !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG) + if ( !usePrefetchDecoder + && (!frame || (dctx->fParams.windowSize > (1<<24))) + && (nbSeq>ADVANCED_SEQS) ) { /* could probably use a larger nbSeq limit */ + U32 const shareLongOffsets = ZSTD_getLongOffsetsShare(dctx->OFTptr); + U32 const minShare = MEM_64bits() ? 7 : 20; /* heuristic values, correspond to 2.73% and 7.81% */ + usePrefetchDecoder = (shareLongOffsets >= minShare); + } +#endif + + dctx->ddictIsCold = 0; + +#if !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT) && \ + !defined(ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG) + if (usePrefetchDecoder) +#endif +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_SHORT + return ZSTD_decompressSequencesLong(dctx, dst, dstCapacity, ip, srcSize, nbSeq, isLongOffset, frame); +#endif + +#ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG + /* else */ + return ZSTD_decompressSequences(dctx, dst, dstCapacity, ip, srcSize, nbSeq, isLongOffset, frame); +#endif + } +} + + +void ZSTD_checkContinuity(ZSTD_DCtx* dctx, const void* dst, size_t dstSize) +{ + if (dst != dctx->previousDstEnd && dstSize > 0) { /* not contiguous */ + dctx->dictEnd = dctx->previousDstEnd; + dctx->virtualStart = (const char*)dst - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->prefixStart)); + dctx->prefixStart = dst; + dctx->previousDstEnd = dst; + } +} + + +size_t ZSTD_decompressBlock(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize) +{ + size_t dSize; + ZSTD_checkContinuity(dctx, dst, dstCapacity); + dSize = ZSTD_decompressBlock_internal(dctx, dst, dstCapacity, src, srcSize, /* frame */ 0); + dctx->previousDstEnd = (char*)dst + dSize; + return dSize; +} diff --git a/lib/zstd/decompress/zstd_decompress_block.h b/lib/zstd/decompress/zstd_decompress_block.h new file mode 100644 index 000000000000..e7f5f6689459 --- /dev/null +++ b/lib/zstd/decompress/zstd_decompress_block.h @@ -0,0 +1,62 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +#ifndef ZSTD_DEC_BLOCK_H +#define ZSTD_DEC_BLOCK_H + +/*-******************************************************* + * Dependencies + *********************************************************/ +#include "../common/zstd_deps.h" /* size_t */ +#include /* DCtx, and some public functions */ +#include "../common/zstd_internal.h" /* blockProperties_t, and some public functions */ +#include "zstd_decompress_internal.h" /* ZSTD_seqSymbol */ + + +/* === Prototypes === */ + +/* note: prototypes already published within `zstd.h` : + * ZSTD_decompressBlock() + */ + +/* note: prototypes already published within `zstd_internal.h` : + * ZSTD_getcBlockSize() + * ZSTD_decodeSeqHeaders() + */ + + +/* ZSTD_decompressBlock_internal() : + * decompress block, starting at `src`, + * into destination buffer `dst`. + * @return : decompressed block size, + * or an error code (which can be tested using ZSTD_isError()) + */ +size_t ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, const int frame); + +/* ZSTD_buildFSETable() : + * generate FSE decoding table for one symbol (ll, ml or off) + * this function must be called with valid parameters only + * (dt is large enough, normalizedCounter distribution total is a power of 2, max is within range, etc.) + * in which case it cannot fail. + * The workspace must be 4-byte aligned and at least ZSTD_BUILD_FSE_TABLE_WKSP_SIZE bytes, which is + * defined in zstd_decompress_internal.h. + * Internal use only. + */ +void ZSTD_buildFSETable(ZSTD_seqSymbol* dt, + const short* normalizedCounter, unsigned maxSymbolValue, + const U32* baseValue, const U32* nbAdditionalBits, + unsigned tableLog, void* wksp, size_t wkspSize, + int bmi2); + + +#endif /* ZSTD_DEC_BLOCK_H */ diff --git a/lib/zstd/decompress/zstd_decompress_internal.h b/lib/zstd/decompress/zstd_decompress_internal.h new file mode 100644 index 000000000000..4b9052f68755 --- /dev/null +++ b/lib/zstd/decompress/zstd_decompress_internal.h @@ -0,0 +1,202 @@ +/* + * Copyright (c) Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + + +/* zstd_decompress_internal: + * objects and definitions shared within lib/decompress modules */ + + #ifndef ZSTD_DECOMPRESS_INTERNAL_H + #define ZSTD_DECOMPRESS_INTERNAL_H + + +/*-******************************************************* + * Dependencies + *********************************************************/ +#include "../common/mem.h" /* BYTE, U16, U32 */ +#include "../common/zstd_internal.h" /* ZSTD_seqSymbol */ + + + +/*-******************************************************* + * Constants + *********************************************************/ +static UNUSED_ATTR const U32 LL_base[MaxLL+1] = { + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 18, 20, 22, 24, 28, 32, 40, + 48, 64, 0x80, 0x100, 0x200, 0x400, 0x800, 0x1000, + 0x2000, 0x4000, 0x8000, 0x10000 }; + +static UNUSED_ATTR const U32 OF_base[MaxOff+1] = { + 0, 1, 1, 5, 0xD, 0x1D, 0x3D, 0x7D, + 0xFD, 0x1FD, 0x3FD, 0x7FD, 0xFFD, 0x1FFD, 0x3FFD, 0x7FFD, + 0xFFFD, 0x1FFFD, 0x3FFFD, 0x7FFFD, 0xFFFFD, 0x1FFFFD, 0x3FFFFD, 0x7FFFFD, + 0xFFFFFD, 0x1FFFFFD, 0x3FFFFFD, 0x7FFFFFD, 0xFFFFFFD, 0x1FFFFFFD, 0x3FFFFFFD, 0x7FFFFFFD }; + +static UNUSED_ATTR const U32 OF_bits[MaxOff+1] = { + 0, 1, 2, 3, 4, 5, 6, 7, + 8, 9, 10, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 20, 21, 22, 23, + 24, 25, 26, 27, 28, 29, 30, 31 }; + +static UNUSED_ATTR const U32 ML_base[MaxML+1] = { + 3, 4, 5, 6, 7, 8, 9, 10, + 11, 12, 13, 14, 15, 16, 17, 18, + 19, 20, 21, 22, 23, 24, 25, 26, + 27, 28, 29, 30, 31, 32, 33, 34, + 35, 37, 39, 41, 43, 47, 51, 59, + 67, 83, 99, 0x83, 0x103, 0x203, 0x403, 0x803, + 0x1003, 0x2003, 0x4003, 0x8003, 0x10003 }; + + +/*-******************************************************* + * Decompression types + *********************************************************/ + typedef struct { + U32 fastMode; + U32 tableLog; + } ZSTD_seqSymbol_header; + + typedef struct { + U16 nextState; + BYTE nbAdditionalBits; + BYTE nbBits; + U32 baseValue; + } ZSTD_seqSymbol; + + #define SEQSYMBOL_TABLE_SIZE(log) (1 + (1 << (log))) + +#define ZSTD_BUILD_FSE_TABLE_WKSP_SIZE (sizeof(S16) * (MaxSeq + 1) + (1u << MaxFSELog) + sizeof(U64)) +#define ZSTD_BUILD_FSE_TABLE_WKSP_SIZE_U32 ((ZSTD_BUILD_FSE_TABLE_WKSP_SIZE + sizeof(U32) - 1) / sizeof(U32)) + +typedef struct { + ZSTD_seqSymbol LLTable[SEQSYMBOL_TABLE_SIZE(LLFSELog)]; /* Note : Space reserved for FSE Tables */ + ZSTD_seqSymbol OFTable[SEQSYMBOL_TABLE_SIZE(OffFSELog)]; /* is also used as temporary workspace while building hufTable during DDict creation */ + ZSTD_seqSymbol MLTable[SEQSYMBOL_TABLE_SIZE(MLFSELog)]; /* and therefore must be at least HUF_DECOMPRESS_WORKSPACE_SIZE large */ + HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)]; /* can accommodate HUF_decompress4X */ + U32 rep[ZSTD_REP_NUM]; + U32 workspace[ZSTD_BUILD_FSE_TABLE_WKSP_SIZE_U32]; +} ZSTD_entropyDTables_t; + +typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader, + ZSTDds_decodeBlockHeader, ZSTDds_decompressBlock, + ZSTDds_decompressLastBlock, ZSTDds_checkChecksum, + ZSTDds_decodeSkippableHeader, ZSTDds_skipFrame } ZSTD_dStage; + +typedef enum { zdss_init=0, zdss_loadHeader, + zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage; + +typedef enum { + ZSTD_use_indefinitely = -1, /* Use the dictionary indefinitely */ + ZSTD_dont_use = 0, /* Do not use the dictionary (if one exists free it) */ + ZSTD_use_once = 1 /* Use the dictionary once and set to ZSTD_dont_use */ +} ZSTD_dictUses_e; + +/* Hashset for storing references to multiple ZSTD_DDict within ZSTD_DCtx */ +typedef struct { + const ZSTD_DDict** ddictPtrTable; + size_t ddictPtrTableSize; + size_t ddictPtrCount; +} ZSTD_DDictHashSet; + +struct ZSTD_DCtx_s +{ + const ZSTD_seqSymbol* LLTptr; + const ZSTD_seqSymbol* MLTptr; + const ZSTD_seqSymbol* OFTptr; + const HUF_DTable* HUFptr; + ZSTD_entropyDTables_t entropy; + U32 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32]; /* space needed when building huffman tables */ + const void* previousDstEnd; /* detect continuity */ + const void* prefixStart; /* start of current segment */ + const void* virtualStart; /* virtual start of previous segment if it was just before current one */ + const void* dictEnd; /* end of previous segment */ + size_t expected; + ZSTD_frameHeader fParams; + U64 processedCSize; + U64 decodedSize; + blockType_e bType; /* used in ZSTD_decompressContinue(), store blockType between block header decoding and block decompression stages */ + ZSTD_dStage stage; + U32 litEntropy; + U32 fseEntropy; + struct xxh64_state xxhState; + size_t headerSize; + ZSTD_format_e format; + ZSTD_forceIgnoreChecksum_e forceIgnoreChecksum; /* User specified: if == 1, will ignore checksums in compressed frame. Default == 0 */ + U32 validateChecksum; /* if == 1, will validate checksum. Is == 1 if (fParams.checksumFlag == 1) and (forceIgnoreChecksum == 0). */ + const BYTE* litPtr; + ZSTD_customMem customMem; + size_t litSize; + size_t rleSize; + size_t staticSize; + int bmi2; /* == 1 if the CPU supports BMI2 and 0 otherwise. CPU support is determined dynamically once per context lifetime. */ + + /* dictionary */ + ZSTD_DDict* ddictLocal; + const ZSTD_DDict* ddict; /* set by ZSTD_initDStream_usingDDict(), or ZSTD_DCtx_refDDict() */ + U32 dictID; + int ddictIsCold; /* if == 1 : dictionary is "new" for working context, and presumed "cold" (not in cpu cache) */ + ZSTD_dictUses_e dictUses; + ZSTD_DDictHashSet* ddictSet; /* Hash set for multiple ddicts */ + ZSTD_refMultipleDDicts_e refMultipleDDicts; /* User specified: if == 1, will allow references to multiple DDicts. Default == 0 (disabled) */ + + /* streaming */ + ZSTD_dStreamStage streamStage; + char* inBuff; + size_t inBuffSize; + size_t inPos; + size_t maxWindowSize; + char* outBuff; + size_t outBuffSize; + size_t outStart; + size_t outEnd; + size_t lhSize; + void* legacyContext; + U32 previousLegacyVersion; + U32 legacyVersion; + U32 hostageByte; + int noForwardProgress; + ZSTD_bufferMode_e outBufferMode; + ZSTD_outBuffer expectedOutBuffer; + + /* workspace */ + BYTE litBuffer[ZSTD_BLOCKSIZE_MAX + WILDCOPY_OVERLENGTH]; + BYTE headerBuffer[ZSTD_FRAMEHEADERSIZE_MAX]; + + size_t oversizedDuration; + +#ifdef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION + void const* dictContentBeginForFuzzing; + void const* dictContentEndForFuzzing; +#endif + + /* Tracing */ +}; /* typedef'd to ZSTD_DCtx within "zstd.h" */ + + +/*-******************************************************* + * Shared internal functions + *********************************************************/ + +/*! ZSTD_loadDEntropy() : + * dict : must point at beginning of a valid zstd dictionary. + * @return : size of dictionary header (size of magic number + dict ID + entropy tables) */ +size_t ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy, + const void* const dict, size_t const dictSize); + +/*! ZSTD_checkContinuity() : + * check if next `dst` follows previous position, where decompression ended. + * If yes, do nothing (continue on current segment). + * If not, classify previous segment as "external dictionary", and start a new segment. + * This function cannot fail. */ +void ZSTD_checkContinuity(ZSTD_DCtx* dctx, const void* dst, size_t dstSize); + + +#endif /* ZSTD_DECOMPRESS_INTERNAL_H */ diff --git a/lib/zstd/decompress_sources.h b/lib/zstd/decompress_sources.h index 9ba367b44149..0fbec508f285 100644 --- a/lib/zstd/decompress_sources.h +++ b/lib/zstd/decompress_sources.h @@ -16,8 +16,13 @@ * decompression. */ -#include "entropy_common.c" -#include "fse_decompress.c" -#include "huf_decompress.c" -#include "zstd_common.c" -#include "decompress.c" +#include "common/debug.c" +#include "common/entropy_common.c" +#include "common/error_private.c" +#include "common/fse_decompress.c" +#include "common/zstd_common.c" +#include "decompress/huf_decompress.c" +#include "decompress/zstd_ddict.c" +#include "decompress/zstd_decompress.c" +#include "decompress/zstd_decompress_block.c" +#include "zstd_decompress_module.c" diff --git a/lib/zstd/entropy_common.c b/lib/zstd/entropy_common.c deleted file mode 100644 index 2b0a643c32c4..000000000000 --- a/lib/zstd/entropy_common.c +++ /dev/null @@ -1,243 +0,0 @@ -/* - * Common functions of New Generation Entropy library - * Copyright (C) 2016, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ - -/* ************************************* -* Dependencies -***************************************/ -#include "error_private.h" /* ERR_*, ERROR */ -#include "fse.h" -#include "huf.h" -#include "mem.h" - -/*=== Version ===*/ -unsigned FSE_versionNumber(void) { return FSE_VERSION_NUMBER; } - -/*=== Error Management ===*/ -unsigned FSE_isError(size_t code) { return ERR_isError(code); } - -unsigned HUF_isError(size_t code) { return ERR_isError(code); } - -/*-************************************************************** -* FSE NCount encoding-decoding -****************************************************************/ -size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSVPtr, unsigned *tableLogPtr, const void *headerBuffer, size_t hbSize) -{ - const BYTE *const istart = (const BYTE *)headerBuffer; - const BYTE *const iend = istart + hbSize; - const BYTE *ip = istart; - int nbBits; - int remaining; - int threshold; - U32 bitStream; - int bitCount; - unsigned charnum = 0; - int previous0 = 0; - - if (hbSize < 4) - return ERROR(srcSize_wrong); - bitStream = ZSTD_readLE32(ip); - nbBits = (bitStream & 0xF) + FSE_MIN_TABLELOG; /* extract tableLog */ - if (nbBits > FSE_TABLELOG_ABSOLUTE_MAX) - return ERROR(tableLog_tooLarge); - bitStream >>= 4; - bitCount = 4; - *tableLogPtr = nbBits; - remaining = (1 << nbBits) + 1; - threshold = 1 << nbBits; - nbBits++; - - while ((remaining > 1) & (charnum <= *maxSVPtr)) { - if (previous0) { - unsigned n0 = charnum; - while ((bitStream & 0xFFFF) == 0xFFFF) { - n0 += 24; - if (ip < iend - 5) { - ip += 2; - bitStream = ZSTD_readLE32(ip) >> bitCount; - } else { - bitStream >>= 16; - bitCount += 16; - } - } - while ((bitStream & 3) == 3) { - n0 += 3; - bitStream >>= 2; - bitCount += 2; - } - n0 += bitStream & 3; - bitCount += 2; - if (n0 > *maxSVPtr) - return ERROR(maxSymbolValue_tooSmall); - while (charnum < n0) - normalizedCounter[charnum++] = 0; - if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) { - ip += bitCount >> 3; - bitCount &= 7; - bitStream = ZSTD_readLE32(ip) >> bitCount; - } else { - bitStream >>= 2; - } - } - { - int const max = (2 * threshold - 1) - remaining; - int count; - - if ((bitStream & (threshold - 1)) < (U32)max) { - count = bitStream & (threshold - 1); - bitCount += nbBits - 1; - } else { - count = bitStream & (2 * threshold - 1); - if (count >= threshold) - count -= max; - bitCount += nbBits; - } - - count--; /* extra accuracy */ - remaining -= count < 0 ? -count : count; /* -1 means +1 */ - normalizedCounter[charnum++] = (short)count; - previous0 = !count; - while (remaining < threshold) { - nbBits--; - threshold >>= 1; - } - - if ((ip <= iend - 7) || (ip + (bitCount >> 3) <= iend - 4)) { - ip += bitCount >> 3; - bitCount &= 7; - } else { - bitCount -= (int)(8 * (iend - 4 - ip)); - ip = iend - 4; - } - bitStream = ZSTD_readLE32(ip) >> (bitCount & 31); - } - } /* while ((remaining>1) & (charnum<=*maxSVPtr)) */ - if (remaining != 1) - return ERROR(corruption_detected); - if (bitCount > 32) - return ERROR(corruption_detected); - *maxSVPtr = charnum - 1; - - ip += (bitCount + 7) >> 3; - return ip - istart; -} - -/*! HUF_readStats() : - Read compact Huffman tree, saved by HUF_writeCTable(). - `huffWeight` is destination buffer. - `rankStats` is assumed to be a table of at least HUF_TABLELOG_MAX U32. - @return : size read from `src` , or an error Code . - Note : Needed by HUF_readCTable() and HUF_readDTableX?() . -*/ -size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize, void *workspace, size_t workspaceSize) -{ - U32 weightTotal; - const BYTE *ip = (const BYTE *)src; - size_t iSize; - size_t oSize; - - if (!srcSize) - return ERROR(srcSize_wrong); - iSize = ip[0]; - /* memset(huffWeight, 0, hwSize); */ /* is not necessary, even though some analyzer complain ... */ - - if (iSize >= 128) { /* special header */ - oSize = iSize - 127; - iSize = ((oSize + 1) / 2); - if (iSize + 1 > srcSize) - return ERROR(srcSize_wrong); - if (oSize >= hwSize) - return ERROR(corruption_detected); - ip += 1; - { - U32 n; - for (n = 0; n < oSize; n += 2) { - huffWeight[n] = ip[n / 2] >> 4; - huffWeight[n + 1] = ip[n / 2] & 15; - } - } - } else { /* header compressed with FSE (normal case) */ - if (iSize + 1 > srcSize) - return ERROR(srcSize_wrong); - oSize = FSE_decompress_wksp(huffWeight, hwSize - 1, ip + 1, iSize, 6, workspace, workspaceSize); /* max (hwSize-1) values decoded, as last one is implied */ - if (FSE_isError(oSize)) - return oSize; - } - - /* collect weight stats */ - memset(rankStats, 0, (HUF_TABLELOG_MAX + 1) * sizeof(U32)); - weightTotal = 0; - { - U32 n; - for (n = 0; n < oSize; n++) { - if (huffWeight[n] >= HUF_TABLELOG_MAX) - return ERROR(corruption_detected); - rankStats[huffWeight[n]]++; - weightTotal += (1 << huffWeight[n]) >> 1; - } - } - if (weightTotal == 0) - return ERROR(corruption_detected); - - /* get last non-null symbol weight (implied, total must be 2^n) */ - { - U32 const tableLog = BIT_highbit32(weightTotal) + 1; - if (tableLog > HUF_TABLELOG_MAX) - return ERROR(corruption_detected); - *tableLogPtr = tableLog; - /* determine last weight */ - { - U32 const total = 1 << tableLog; - U32 const rest = total - weightTotal; - U32 const verif = 1 << BIT_highbit32(rest); - U32 const lastWeight = BIT_highbit32(rest) + 1; - if (verif != rest) - return ERROR(corruption_detected); /* last value must be a clean power of 2 */ - huffWeight[oSize] = (BYTE)lastWeight; - rankStats[lastWeight]++; - } - } - - /* check tree construction validity */ - if ((rankStats[1] < 2) || (rankStats[1] & 1)) - return ERROR(corruption_detected); /* by construction : at least 2 elts of rank 1, must be even */ - - /* results */ - *nbSymbolsPtr = (U32)(oSize + 1); - return iSize + 1; -} diff --git a/lib/zstd/error_private.h b/lib/zstd/error_private.h deleted file mode 100644 index 1a60b31f706c..000000000000 --- a/lib/zstd/error_private.h +++ /dev/null @@ -1,53 +0,0 @@ -/** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -/* Note : this module is expected to remain private, do not expose it */ - -#ifndef ERROR_H_MODULE -#define ERROR_H_MODULE - -/* **************************************** -* Dependencies -******************************************/ -#include /* size_t */ -#include /* enum list */ - -/* **************************************** -* Compiler-specific -******************************************/ -#define ERR_STATIC static __attribute__((unused)) - -/*-**************************************** -* Customization (error_public.h) -******************************************/ -typedef ZSTD_ErrorCode ERR_enum; -#define PREFIX(name) ZSTD_error_##name - -/*-**************************************** -* Error codes handling -******************************************/ -#define ERROR(name) ((size_t)-PREFIX(name)) - -ERR_STATIC unsigned ERR_isError(size_t code) { return (code > ERROR(maxCode)); } - -ERR_STATIC ERR_enum ERR_getErrorCode(size_t code) -{ - if (!ERR_isError(code)) - return (ERR_enum)0; - return (ERR_enum)(0 - code); -} - -#endif /* ERROR_H_MODULE */ diff --git a/lib/zstd/fse.h b/lib/zstd/fse.h deleted file mode 100644 index 7460ab04b191..000000000000 --- a/lib/zstd/fse.h +++ /dev/null @@ -1,575 +0,0 @@ -/* - * FSE : Finite State Entropy codec - * Public Prototypes declaration - * Copyright (C) 2013-2016, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ -#ifndef FSE_H -#define FSE_H - -/*-***************************************** -* Dependencies -******************************************/ -#include /* size_t, ptrdiff_t */ - -/*-***************************************** -* FSE_PUBLIC_API : control library symbols visibility -******************************************/ -#define FSE_PUBLIC_API - -/*------ Version ------*/ -#define FSE_VERSION_MAJOR 0 -#define FSE_VERSION_MINOR 9 -#define FSE_VERSION_RELEASE 0 - -#define FSE_LIB_VERSION FSE_VERSION_MAJOR.FSE_VERSION_MINOR.FSE_VERSION_RELEASE -#define FSE_QUOTE(str) #str -#define FSE_EXPAND_AND_QUOTE(str) FSE_QUOTE(str) -#define FSE_VERSION_STRING FSE_EXPAND_AND_QUOTE(FSE_LIB_VERSION) - -#define FSE_VERSION_NUMBER (FSE_VERSION_MAJOR * 100 * 100 + FSE_VERSION_MINOR * 100 + FSE_VERSION_RELEASE) -FSE_PUBLIC_API unsigned FSE_versionNumber(void); /**< library version number; to be used when checking dll version */ - -/*-***************************************** -* Tool functions -******************************************/ -FSE_PUBLIC_API size_t FSE_compressBound(size_t size); /* maximum compressed size */ - -/* Error Management */ -FSE_PUBLIC_API unsigned FSE_isError(size_t code); /* tells if a return value is an error code */ - -/*-***************************************** -* FSE detailed API -******************************************/ -/*! -FSE_compress() does the following: -1. count symbol occurrence from source[] into table count[] -2. normalize counters so that sum(count[]) == Power_of_2 (2^tableLog) -3. save normalized counters to memory buffer using writeNCount() -4. build encoding table 'CTable' from normalized counters -5. encode the data stream using encoding table 'CTable' - -FSE_decompress() does the following: -1. read normalized counters with readNCount() -2. build decoding table 'DTable' from normalized counters -3. decode the data stream using decoding table 'DTable' - -The following API allows targeting specific sub-functions for advanced tasks. -For example, it's possible to compress several blocks using the same 'CTable', -or to save and provide normalized distribution using external method. -*/ - -/* *** COMPRESSION *** */ -/*! FSE_optimalTableLog(): - dynamically downsize 'tableLog' when conditions are met. - It saves CPU time, by using smaller tables, while preserving or even improving compression ratio. - @return : recommended tableLog (necessarily <= 'maxTableLog') */ -FSE_PUBLIC_API unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); - -/*! FSE_normalizeCount(): - normalize counts so that sum(count[]) == Power_of_2 (2^tableLog) - 'normalizedCounter' is a table of short, of minimum size (maxSymbolValue+1). - @return : tableLog, - or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_normalizeCount(short *normalizedCounter, unsigned tableLog, const unsigned *count, size_t srcSize, unsigned maxSymbolValue); - -/*! FSE_NCountWriteBound(): - Provides the maximum possible size of an FSE normalized table, given 'maxSymbolValue' and 'tableLog'. - Typically useful for allocation purpose. */ -FSE_PUBLIC_API size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog); - -/*! FSE_writeNCount(): - Compactly save 'normalizedCounter' into 'buffer'. - @return : size of the compressed table, - or an errorCode, which can be tested using FSE_isError(). */ -FSE_PUBLIC_API size_t FSE_writeNCount(void *buffer, size_t bufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog); - -/*! Constructor and Destructor of FSE_CTable. - Note that FSE_CTable size depends on 'tableLog' and 'maxSymbolValue' */ -typedef unsigned FSE_CTable; /* don't allocate that. It's only meant to be more restrictive than void* */ - -/*! FSE_compress_usingCTable(): - Compress `src` using `ct` into `dst` which must be already allocated. - @return : size of compressed data (<= `dstCapacity`), - or 0 if compressed data could not fit into `dst`, - or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_compress_usingCTable(void *dst, size_t dstCapacity, const void *src, size_t srcSize, const FSE_CTable *ct); - -/*! -Tutorial : ----------- -The first step is to count all symbols. FSE_count() does this job very fast. -Result will be saved into 'count', a table of unsigned int, which must be already allocated, and have 'maxSymbolValuePtr[0]+1' cells. -'src' is a table of bytes of size 'srcSize'. All values within 'src' MUST be <= maxSymbolValuePtr[0] -maxSymbolValuePtr[0] will be updated, with its real value (necessarily <= original value) -FSE_count() will return the number of occurrence of the most frequent symbol. -This can be used to know if there is a single symbol within 'src', and to quickly evaluate its compressibility. -If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()). - -The next step is to normalize the frequencies. -FSE_normalizeCount() will ensure that sum of frequencies is == 2 ^'tableLog'. -It also guarantees a minimum of 1 to any Symbol with frequency >= 1. -You can use 'tableLog'==0 to mean "use default tableLog value". -If you are unsure of which tableLog value to use, you can ask FSE_optimalTableLog(), -which will provide the optimal valid tableLog given sourceSize, maxSymbolValue, and a user-defined maximum (0 means "default"). - -The result of FSE_normalizeCount() will be saved into a table, -called 'normalizedCounter', which is a table of signed short. -'normalizedCounter' must be already allocated, and have at least 'maxSymbolValue+1' cells. -The return value is tableLog if everything proceeded as expected. -It is 0 if there is a single symbol within distribution. -If there is an error (ex: invalid tableLog value), the function will return an ErrorCode (which can be tested using FSE_isError()). - -'normalizedCounter' can be saved in a compact manner to a memory area using FSE_writeNCount(). -'buffer' must be already allocated. -For guaranteed success, buffer size must be at least FSE_headerBound(). -The result of the function is the number of bytes written into 'buffer'. -If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError(); ex : buffer size too small). - -'normalizedCounter' can then be used to create the compression table 'CTable'. -The space required by 'CTable' must be already allocated, using FSE_createCTable(). -You can then use FSE_buildCTable() to fill 'CTable'. -If there is an error, both functions will return an ErrorCode (which can be tested using FSE_isError()). - -'CTable' can then be used to compress 'src', with FSE_compress_usingCTable(). -Similar to FSE_count(), the convention is that 'src' is assumed to be a table of char of size 'srcSize' -The function returns the size of compressed data (without header), necessarily <= `dstCapacity`. -If it returns '0', compressed data could not fit into 'dst'. -If there is an error, the function will return an ErrorCode (which can be tested using FSE_isError()). -*/ - -/* *** DECOMPRESSION *** */ - -/*! FSE_readNCount(): - Read compactly saved 'normalizedCounter' from 'rBuffer'. - @return : size read from 'rBuffer', - or an errorCode, which can be tested using FSE_isError(). - maxSymbolValuePtr[0] and tableLogPtr[0] will also be updated with their respective values */ -FSE_PUBLIC_API size_t FSE_readNCount(short *normalizedCounter, unsigned *maxSymbolValuePtr, unsigned *tableLogPtr, const void *rBuffer, size_t rBuffSize); - -/*! Constructor and Destructor of FSE_DTable. - Note that its size depends on 'tableLog' */ -typedef unsigned FSE_DTable; /* don't allocate that. It's just a way to be more restrictive than void* */ - -/*! FSE_buildDTable(): - Builds 'dt', which must be already allocated, using FSE_createDTable(). - return : 0, or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_buildDTable_wksp(FSE_DTable *dt, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize); - -/*! FSE_decompress_usingDTable(): - Decompress compressed source `cSrc` of size `cSrcSize` using `dt` - into `dst` which must be already allocated. - @return : size of regenerated data (necessarily <= `dstCapacity`), - or an errorCode, which can be tested using FSE_isError() */ -FSE_PUBLIC_API size_t FSE_decompress_usingDTable(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt); - -/*! -Tutorial : ----------- -(Note : these functions only decompress FSE-compressed blocks. - If block is uncompressed, use memcpy() instead - If block is a single repeated byte, use memset() instead ) - -The first step is to obtain the normalized frequencies of symbols. -This can be performed by FSE_readNCount() if it was saved using FSE_writeNCount(). -'normalizedCounter' must be already allocated, and have at least 'maxSymbolValuePtr[0]+1' cells of signed short. -In practice, that means it's necessary to know 'maxSymbolValue' beforehand, -or size the table to handle worst case situations (typically 256). -FSE_readNCount() will provide 'tableLog' and 'maxSymbolValue'. -The result of FSE_readNCount() is the number of bytes read from 'rBuffer'. -Note that 'rBufferSize' must be at least 4 bytes, even if useful information is less than that. -If there is an error, the function will return an error code, which can be tested using FSE_isError(). - -The next step is to build the decompression tables 'FSE_DTable' from 'normalizedCounter'. -This is performed by the function FSE_buildDTable(). -The space required by 'FSE_DTable' must be already allocated using FSE_createDTable(). -If there is an error, the function will return an error code, which can be tested using FSE_isError(). - -`FSE_DTable` can then be used to decompress `cSrc`, with FSE_decompress_usingDTable(). -`cSrcSize` must be strictly correct, otherwise decompression will fail. -FSE_decompress_usingDTable() result will tell how many bytes were regenerated (<=`dstCapacity`). -If there is an error, the function will return an error code, which can be tested using FSE_isError(). (ex: dst buffer too small) -*/ - -/* *** Dependency *** */ -#include "bitstream.h" - -/* ***************************************** -* Static allocation -*******************************************/ -/* FSE buffer bounds */ -#define FSE_NCOUNTBOUND 512 -#define FSE_BLOCKBOUND(size) (size + (size >> 7)) -#define FSE_COMPRESSBOUND(size) (FSE_NCOUNTBOUND + FSE_BLOCKBOUND(size)) /* Macro version, useful for static allocation */ - -/* It is possible to statically allocate FSE CTable/DTable as a table of FSE_CTable/FSE_DTable using below macros */ -#define FSE_CTABLE_SIZE_U32(maxTableLog, maxSymbolValue) (1 + (1 << (maxTableLog - 1)) + ((maxSymbolValue + 1) * 2)) -#define FSE_DTABLE_SIZE_U32(maxTableLog) (1 + (1 << maxTableLog)) - -/* ***************************************** -* FSE advanced API -*******************************************/ -/* FSE_count_wksp() : - * Same as FSE_count(), but using an externally provided scratch buffer. - * `workSpace` size must be table of >= `1024` unsigned - */ -size_t FSE_count_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace); - -/* FSE_countFast_wksp() : - * Same as FSE_countFast(), but using an externally provided scratch buffer. - * `workSpace` must be a table of minimum `1024` unsigned - */ -size_t FSE_countFast_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize, unsigned *workSpace); - -/*! FSE_count_simple - * Same as FSE_countFast(), but does not use any additional memory (not even on stack). - * This function is unsafe, and will segfault if any value within `src` is `> *maxSymbolValuePtr` (presuming it's also the size of `count`). -*/ -size_t FSE_count_simple(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize); - -unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus); -/**< same as FSE_optimalTableLog(), which used `minus==2` */ - -size_t FSE_buildCTable_raw(FSE_CTable *ct, unsigned nbBits); -/**< build a fake FSE_CTable, designed for a flat distribution, where each symbol uses nbBits */ - -size_t FSE_buildCTable_rle(FSE_CTable *ct, unsigned char symbolValue); -/**< build a fake FSE_CTable, designed to compress always the same symbolValue */ - -/* FSE_buildCTable_wksp() : - * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`). - * `wkspSize` must be >= `(1<= BIT_DStream_completed - -When it's done, verify decompression is fully completed, by checking both DStream and the relevant states. -Checking if DStream has reached its end is performed by : - BIT_endOfDStream(&DStream); -Check also the states. There might be some symbols left there, if some high probability ones (>50%) are possible. - FSE_endOfDState(&DState); -*/ - -/* ***************************************** -* FSE unsafe API -*******************************************/ -static unsigned char FSE_decodeSymbolFast(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD); -/* faster, but works only if nbBits is always >= 1 (otherwise, result will be corrupted) */ - -/* ***************************************** -* Implementation of inlined functions -*******************************************/ -typedef struct { - int deltaFindState; - U32 deltaNbBits; -} FSE_symbolCompressionTransform; /* total 8 bytes */ - -ZSTD_STATIC void FSE_initCState(FSE_CState_t *statePtr, const FSE_CTable *ct) -{ - const void *ptr = ct; - const U16 *u16ptr = (const U16 *)ptr; - const U32 tableLog = ZSTD_read16(ptr); - statePtr->value = (ptrdiff_t)1 << tableLog; - statePtr->stateTable = u16ptr + 2; - statePtr->symbolTT = ((const U32 *)ct + 1 + (tableLog ? (1 << (tableLog - 1)) : 1)); - statePtr->stateLog = tableLog; -} - -/*! FSE_initCState2() : -* Same as FSE_initCState(), but the first symbol to include (which will be the last to be read) -* uses the smallest state value possible, saving the cost of this symbol */ -ZSTD_STATIC void FSE_initCState2(FSE_CState_t *statePtr, const FSE_CTable *ct, U32 symbol) -{ - FSE_initCState(statePtr, ct); - { - const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform *)(statePtr->symbolTT))[symbol]; - const U16 *stateTable = (const U16 *)(statePtr->stateTable); - U32 nbBitsOut = (U32)((symbolTT.deltaNbBits + (1 << 15)) >> 16); - statePtr->value = (nbBitsOut << 16) - symbolTT.deltaNbBits; - statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState]; - } -} - -ZSTD_STATIC void FSE_encodeSymbol(BIT_CStream_t *bitC, FSE_CState_t *statePtr, U32 symbol) -{ - const FSE_symbolCompressionTransform symbolTT = ((const FSE_symbolCompressionTransform *)(statePtr->symbolTT))[symbol]; - const U16 *const stateTable = (const U16 *)(statePtr->stateTable); - U32 nbBitsOut = (U32)((statePtr->value + symbolTT.deltaNbBits) >> 16); - BIT_addBits(bitC, statePtr->value, nbBitsOut); - statePtr->value = stateTable[(statePtr->value >> nbBitsOut) + symbolTT.deltaFindState]; -} - -ZSTD_STATIC void FSE_flushCState(BIT_CStream_t *bitC, const FSE_CState_t *statePtr) -{ - BIT_addBits(bitC, statePtr->value, statePtr->stateLog); - BIT_flushBits(bitC); -} - -/* ====== Decompression ====== */ - -typedef struct { - U16 tableLog; - U16 fastMode; -} FSE_DTableHeader; /* sizeof U32 */ - -typedef struct { - unsigned short newState; - unsigned char symbol; - unsigned char nbBits; -} FSE_decode_t; /* size == U32 */ - -ZSTD_STATIC void FSE_initDState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD, const FSE_DTable *dt) -{ - const void *ptr = dt; - const FSE_DTableHeader *const DTableH = (const FSE_DTableHeader *)ptr; - DStatePtr->state = BIT_readBits(bitD, DTableH->tableLog); - BIT_reloadDStream(bitD); - DStatePtr->table = dt + 1; -} - -ZSTD_STATIC BYTE FSE_peekSymbol(const FSE_DState_t *DStatePtr) -{ - FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state]; - return DInfo.symbol; -} - -ZSTD_STATIC void FSE_updateState(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD) -{ - FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state]; - U32 const nbBits = DInfo.nbBits; - size_t const lowBits = BIT_readBits(bitD, nbBits); - DStatePtr->state = DInfo.newState + lowBits; -} - -ZSTD_STATIC BYTE FSE_decodeSymbol(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD) -{ - FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state]; - U32 const nbBits = DInfo.nbBits; - BYTE const symbol = DInfo.symbol; - size_t const lowBits = BIT_readBits(bitD, nbBits); - - DStatePtr->state = DInfo.newState + lowBits; - return symbol; -} - -/*! FSE_decodeSymbolFast() : - unsafe, only works if no symbol has a probability > 50% */ -ZSTD_STATIC BYTE FSE_decodeSymbolFast(FSE_DState_t *DStatePtr, BIT_DStream_t *bitD) -{ - FSE_decode_t const DInfo = ((const FSE_decode_t *)(DStatePtr->table))[DStatePtr->state]; - U32 const nbBits = DInfo.nbBits; - BYTE const symbol = DInfo.symbol; - size_t const lowBits = BIT_readBitsFast(bitD, nbBits); - - DStatePtr->state = DInfo.newState + lowBits; - return symbol; -} - -ZSTD_STATIC unsigned FSE_endOfDState(const FSE_DState_t *DStatePtr) { return DStatePtr->state == 0; } - -/* ************************************************************** -* Tuning parameters -****************************************************************/ -/*!MEMORY_USAGE : -* Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) -* Increasing memory usage improves compression ratio -* Reduced memory usage can improve speed, due to cache effect -* Recommended max value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ -#ifndef FSE_MAX_MEMORY_USAGE -#define FSE_MAX_MEMORY_USAGE 14 -#endif -#ifndef FSE_DEFAULT_MEMORY_USAGE -#define FSE_DEFAULT_MEMORY_USAGE 13 -#endif - -/*!FSE_MAX_SYMBOL_VALUE : -* Maximum symbol value authorized. -* Required for proper stack allocation */ -#ifndef FSE_MAX_SYMBOL_VALUE -#define FSE_MAX_SYMBOL_VALUE 255 -#endif - -/* ************************************************************** -* template functions type & suffix -****************************************************************/ -#define FSE_FUNCTION_TYPE BYTE -#define FSE_FUNCTION_EXTENSION -#define FSE_DECODE_TYPE FSE_decode_t - -/* *************************************************************** -* Constants -*****************************************************************/ -#define FSE_MAX_TABLELOG (FSE_MAX_MEMORY_USAGE - 2) -#define FSE_MAX_TABLESIZE (1U << FSE_MAX_TABLELOG) -#define FSE_MAXTABLESIZE_MASK (FSE_MAX_TABLESIZE - 1) -#define FSE_DEFAULT_TABLELOG (FSE_DEFAULT_MEMORY_USAGE - 2) -#define FSE_MIN_TABLELOG 5 - -#define FSE_TABLELOG_ABSOLUTE_MAX 15 -#if FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX -#error "FSE_MAX_TABLELOG > FSE_TABLELOG_ABSOLUTE_MAX is not supported" -#endif - -#define FSE_TABLESTEP(tableSize) ((tableSize >> 1) + (tableSize >> 3) + 3) - -#endif /* FSE_H */ diff --git a/lib/zstd/fse_compress.c b/lib/zstd/fse_compress.c deleted file mode 100644 index ef3d1741d532..000000000000 --- a/lib/zstd/fse_compress.c +++ /dev/null @@ -1,795 +0,0 @@ -/* - * FSE : Finite State Entropy encoder - * Copyright (C) 2013-2015, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ - -/* ************************************************************** -* Compiler specifics -****************************************************************/ -#define FORCE_INLINE static __always_inline - -/* ************************************************************** -* Includes -****************************************************************/ -#include "bitstream.h" -#include "fse.h" -#include -#include -#include -#include /* memcpy, memset */ - -/* ************************************************************** -* Error Management -****************************************************************/ -#define FSE_STATIC_ASSERT(c) \ - { \ - enum { FSE_static_assert = 1 / (int)(!!(c)) }; \ - } /* use only *after* variable declarations */ - -/* ************************************************************** -* Templates -****************************************************************/ -/* - designed to be included - for type-specific functions (template emulation in C) - Objective is to write these functions only once, for improved maintenance -*/ - -/* safety checks */ -#ifndef FSE_FUNCTION_EXTENSION -#error "FSE_FUNCTION_EXTENSION must be defined" -#endif -#ifndef FSE_FUNCTION_TYPE -#error "FSE_FUNCTION_TYPE must be defined" -#endif - -/* Function names */ -#define FSE_CAT(X, Y) X##Y -#define FSE_FUNCTION_NAME(X, Y) FSE_CAT(X, Y) -#define FSE_TYPE_NAME(X, Y) FSE_CAT(X, Y) - -/* Function templates */ - -/* FSE_buildCTable_wksp() : - * Same as FSE_buildCTable(), but using an externally allocated scratch buffer (`workSpace`). - * wkspSize should be sized to handle worst case situation, which is `1<> 1 : 1); - FSE_symbolCompressionTransform *const symbolTT = (FSE_symbolCompressionTransform *)(FSCT); - U32 const step = FSE_TABLESTEP(tableSize); - U32 highThreshold = tableSize - 1; - - U32 *cumul; - FSE_FUNCTION_TYPE *tableSymbol; - size_t spaceUsed32 = 0; - - cumul = (U32 *)workspace + spaceUsed32; - spaceUsed32 += FSE_MAX_SYMBOL_VALUE + 2; - tableSymbol = (FSE_FUNCTION_TYPE *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(sizeof(FSE_FUNCTION_TYPE) * ((size_t)1 << tableLog), sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - /* CTable header */ - tableU16[-2] = (U16)tableLog; - tableU16[-1] = (U16)maxSymbolValue; - - /* For explanations on how to distribute symbol values over the table : - * http://fastcompression.blogspot.fr/2014/02/fse-distributing-symbol-values.html */ - - /* symbol start positions */ - { - U32 u; - cumul[0] = 0; - for (u = 1; u <= maxSymbolValue + 1; u++) { - if (normalizedCounter[u - 1] == -1) { /* Low proba symbol */ - cumul[u] = cumul[u - 1] + 1; - tableSymbol[highThreshold--] = (FSE_FUNCTION_TYPE)(u - 1); - } else { - cumul[u] = cumul[u - 1] + normalizedCounter[u - 1]; - } - } - cumul[maxSymbolValue + 1] = tableSize + 1; - } - - /* Spread symbols */ - { - U32 position = 0; - U32 symbol; - for (symbol = 0; symbol <= maxSymbolValue; symbol++) { - int nbOccurences; - for (nbOccurences = 0; nbOccurences < normalizedCounter[symbol]; nbOccurences++) { - tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol; - position = (position + step) & tableMask; - while (position > highThreshold) - position = (position + step) & tableMask; /* Low proba area */ - } - } - - if (position != 0) - return ERROR(GENERIC); /* Must have gone through all positions */ - } - - /* Build table */ - { - U32 u; - for (u = 0; u < tableSize; u++) { - FSE_FUNCTION_TYPE s = tableSymbol[u]; /* note : static analyzer may not understand tableSymbol is properly initialized */ - tableU16[cumul[s]++] = (U16)(tableSize + u); /* TableU16 : sorted by symbol order; gives next state value */ - } - } - - /* Build Symbol Transformation Table */ - { - unsigned total = 0; - unsigned s; - for (s = 0; s <= maxSymbolValue; s++) { - switch (normalizedCounter[s]) { - case 0: break; - - case -1: - case 1: - symbolTT[s].deltaNbBits = (tableLog << 16) - (1 << tableLog); - symbolTT[s].deltaFindState = total - 1; - total++; - break; - default: { - U32 const maxBitsOut = tableLog - BIT_highbit32(normalizedCounter[s] - 1); - U32 const minStatePlus = normalizedCounter[s] << maxBitsOut; - symbolTT[s].deltaNbBits = (maxBitsOut << 16) - minStatePlus; - symbolTT[s].deltaFindState = total - normalizedCounter[s]; - total += normalizedCounter[s]; - } - } - } - } - - return 0; -} - -/*-************************************************************** -* FSE NCount encoding-decoding -****************************************************************/ -size_t FSE_NCountWriteBound(unsigned maxSymbolValue, unsigned tableLog) -{ - size_t const maxHeaderSize = (((maxSymbolValue + 1) * tableLog) >> 3) + 3; - return maxSymbolValue ? maxHeaderSize : FSE_NCOUNTBOUND; /* maxSymbolValue==0 ? use default */ -} - -static size_t FSE_writeNCount_generic(void *header, size_t headerBufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, - unsigned writeIsSafe) -{ - BYTE *const ostart = (BYTE *)header; - BYTE *out = ostart; - BYTE *const oend = ostart + headerBufferSize; - int nbBits; - const int tableSize = 1 << tableLog; - int remaining; - int threshold; - U32 bitStream; - int bitCount; - unsigned charnum = 0; - int previous0 = 0; - - bitStream = 0; - bitCount = 0; - /* Table Size */ - bitStream += (tableLog - FSE_MIN_TABLELOG) << bitCount; - bitCount += 4; - - /* Init */ - remaining = tableSize + 1; /* +1 for extra accuracy */ - threshold = tableSize; - nbBits = tableLog + 1; - - while (remaining > 1) { /* stops at 1 */ - if (previous0) { - unsigned start = charnum; - while (!normalizedCounter[charnum]) - charnum++; - while (charnum >= start + 24) { - start += 24; - bitStream += 0xFFFFU << bitCount; - if ((!writeIsSafe) && (out > oend - 2)) - return ERROR(dstSize_tooSmall); /* Buffer overflow */ - out[0] = (BYTE)bitStream; - out[1] = (BYTE)(bitStream >> 8); - out += 2; - bitStream >>= 16; - } - while (charnum >= start + 3) { - start += 3; - bitStream += 3 << bitCount; - bitCount += 2; - } - bitStream += (charnum - start) << bitCount; - bitCount += 2; - if (bitCount > 16) { - if ((!writeIsSafe) && (out > oend - 2)) - return ERROR(dstSize_tooSmall); /* Buffer overflow */ - out[0] = (BYTE)bitStream; - out[1] = (BYTE)(bitStream >> 8); - out += 2; - bitStream >>= 16; - bitCount -= 16; - } - } - { - int count = normalizedCounter[charnum++]; - int const max = (2 * threshold - 1) - remaining; - remaining -= count < 0 ? -count : count; - count++; /* +1 for extra accuracy */ - if (count >= threshold) - count += max; /* [0..max[ [max..threshold[ (...) [threshold+max 2*threshold[ */ - bitStream += count << bitCount; - bitCount += nbBits; - bitCount -= (count < max); - previous0 = (count == 1); - if (remaining < 1) - return ERROR(GENERIC); - while (remaining < threshold) - nbBits--, threshold >>= 1; - } - if (bitCount > 16) { - if ((!writeIsSafe) && (out > oend - 2)) - return ERROR(dstSize_tooSmall); /* Buffer overflow */ - out[0] = (BYTE)bitStream; - out[1] = (BYTE)(bitStream >> 8); - out += 2; - bitStream >>= 16; - bitCount -= 16; - } - } - - /* flush remaining bitStream */ - if ((!writeIsSafe) && (out > oend - 2)) - return ERROR(dstSize_tooSmall); /* Buffer overflow */ - out[0] = (BYTE)bitStream; - out[1] = (BYTE)(bitStream >> 8); - out += (bitCount + 7) / 8; - - if (charnum > maxSymbolValue + 1) - return ERROR(GENERIC); - - return (out - ostart); -} - -size_t FSE_writeNCount(void *buffer, size_t bufferSize, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog) -{ - if (tableLog > FSE_MAX_TABLELOG) - return ERROR(tableLog_tooLarge); /* Unsupported */ - if (tableLog < FSE_MIN_TABLELOG) - return ERROR(GENERIC); /* Unsupported */ - - if (bufferSize < FSE_NCountWriteBound(maxSymbolValue, tableLog)) - return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 0); - - return FSE_writeNCount_generic(buffer, bufferSize, normalizedCounter, maxSymbolValue, tableLog, 1); -} - -/*-************************************************************** -* Counting histogram -****************************************************************/ -/*! FSE_count_simple - This function counts byte values within `src`, and store the histogram into table `count`. - It doesn't use any additional memory. - But this function is unsafe : it doesn't check that all values within `src` can fit into `count`. - For this reason, prefer using a table `count` with 256 elements. - @return : count of most numerous element -*/ -size_t FSE_count_simple(unsigned *count, unsigned *maxSymbolValuePtr, const void *src, size_t srcSize) -{ - const BYTE *ip = (const BYTE *)src; - const BYTE *const end = ip + srcSize; - unsigned maxSymbolValue = *maxSymbolValuePtr; - unsigned max = 0; - - memset(count, 0, (maxSymbolValue + 1) * sizeof(*count)); - if (srcSize == 0) { - *maxSymbolValuePtr = 0; - return 0; - } - - while (ip < end) - count[*ip++]++; - - while (!count[maxSymbolValue]) - maxSymbolValue--; - *maxSymbolValuePtr = maxSymbolValue; - - { - U32 s; - for (s = 0; s <= maxSymbolValue; s++) - if (count[s] > max) - max = count[s]; - } - - return (size_t)max; -} - -/* FSE_count_parallel_wksp() : - * Same as FSE_count_parallel(), but using an externally provided scratch buffer. - * `workSpace` size must be a minimum of `1024 * sizeof(unsigned)`` */ -static size_t FSE_count_parallel_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned checkMax, - unsigned *const workSpace) -{ - const BYTE *ip = (const BYTE *)source; - const BYTE *const iend = ip + sourceSize; - unsigned maxSymbolValue = *maxSymbolValuePtr; - unsigned max = 0; - U32 *const Counting1 = workSpace; - U32 *const Counting2 = Counting1 + 256; - U32 *const Counting3 = Counting2 + 256; - U32 *const Counting4 = Counting3 + 256; - - memset(Counting1, 0, 4 * 256 * sizeof(unsigned)); - - /* safety checks */ - if (!sourceSize) { - memset(count, 0, maxSymbolValue + 1); - *maxSymbolValuePtr = 0; - return 0; - } - if (!maxSymbolValue) - maxSymbolValue = 255; /* 0 == default */ - - /* by stripes of 16 bytes */ - { - U32 cached = ZSTD_read32(ip); - ip += 4; - while (ip < iend - 15) { - U32 c = cached; - cached = ZSTD_read32(ip); - ip += 4; - Counting1[(BYTE)c]++; - Counting2[(BYTE)(c >> 8)]++; - Counting3[(BYTE)(c >> 16)]++; - Counting4[c >> 24]++; - c = cached; - cached = ZSTD_read32(ip); - ip += 4; - Counting1[(BYTE)c]++; - Counting2[(BYTE)(c >> 8)]++; - Counting3[(BYTE)(c >> 16)]++; - Counting4[c >> 24]++; - c = cached; - cached = ZSTD_read32(ip); - ip += 4; - Counting1[(BYTE)c]++; - Counting2[(BYTE)(c >> 8)]++; - Counting3[(BYTE)(c >> 16)]++; - Counting4[c >> 24]++; - c = cached; - cached = ZSTD_read32(ip); - ip += 4; - Counting1[(BYTE)c]++; - Counting2[(BYTE)(c >> 8)]++; - Counting3[(BYTE)(c >> 16)]++; - Counting4[c >> 24]++; - } - ip -= 4; - } - - /* finish last symbols */ - while (ip < iend) - Counting1[*ip++]++; - - if (checkMax) { /* verify stats will fit into destination table */ - U32 s; - for (s = 255; s > maxSymbolValue; s--) { - Counting1[s] += Counting2[s] + Counting3[s] + Counting4[s]; - if (Counting1[s]) - return ERROR(maxSymbolValue_tooSmall); - } - } - - { - U32 s; - for (s = 0; s <= maxSymbolValue; s++) { - count[s] = Counting1[s] + Counting2[s] + Counting3[s] + Counting4[s]; - if (count[s] > max) - max = count[s]; - } - } - - while (!count[maxSymbolValue]) - maxSymbolValue--; - *maxSymbolValuePtr = maxSymbolValue; - return (size_t)max; -} - -/* FSE_countFast_wksp() : - * Same as FSE_countFast(), but using an externally provided scratch buffer. - * `workSpace` size must be table of >= `1024` unsigned */ -size_t FSE_countFast_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace) -{ - if (sourceSize < 1500) - return FSE_count_simple(count, maxSymbolValuePtr, source, sourceSize); - return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 0, workSpace); -} - -/* FSE_count_wksp() : - * Same as FSE_count(), but using an externally provided scratch buffer. - * `workSpace` size must be table of >= `1024` unsigned */ -size_t FSE_count_wksp(unsigned *count, unsigned *maxSymbolValuePtr, const void *source, size_t sourceSize, unsigned *workSpace) -{ - if (*maxSymbolValuePtr < 255) - return FSE_count_parallel_wksp(count, maxSymbolValuePtr, source, sourceSize, 1, workSpace); - *maxSymbolValuePtr = 255; - return FSE_countFast_wksp(count, maxSymbolValuePtr, source, sourceSize, workSpace); -} - -/*-************************************************************** -* FSE Compression Code -****************************************************************/ -/*! FSE_sizeof_CTable() : - FSE_CTable is a variable size structure which contains : - `U16 tableLog;` - `U16 maxSymbolValue;` - `U16 nextStateNumber[1 << tableLog];` // This size is variable - `FSE_symbolCompressionTransform symbolTT[maxSymbolValue+1];` // This size is variable -Allocation is manual (C standard does not support variable-size structures). -*/ -size_t FSE_sizeof_CTable(unsigned maxSymbolValue, unsigned tableLog) -{ - if (tableLog > FSE_MAX_TABLELOG) - return ERROR(tableLog_tooLarge); - return FSE_CTABLE_SIZE_U32(tableLog, maxSymbolValue) * sizeof(U32); -} - -/* provides the minimum logSize to safely represent a distribution */ -static unsigned FSE_minTableLog(size_t srcSize, unsigned maxSymbolValue) -{ - U32 minBitsSrc = BIT_highbit32((U32)(srcSize - 1)) + 1; - U32 minBitsSymbols = BIT_highbit32(maxSymbolValue) + 2; - U32 minBits = minBitsSrc < minBitsSymbols ? minBitsSrc : minBitsSymbols; - return minBits; -} - -unsigned FSE_optimalTableLog_internal(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue, unsigned minus) -{ - U32 maxBitsSrc = BIT_highbit32((U32)(srcSize - 1)) - minus; - U32 tableLog = maxTableLog; - U32 minBits = FSE_minTableLog(srcSize, maxSymbolValue); - if (tableLog == 0) - tableLog = FSE_DEFAULT_TABLELOG; - if (maxBitsSrc < tableLog) - tableLog = maxBitsSrc; /* Accuracy can be reduced */ - if (minBits > tableLog) - tableLog = minBits; /* Need a minimum to safely represent all symbol values */ - if (tableLog < FSE_MIN_TABLELOG) - tableLog = FSE_MIN_TABLELOG; - if (tableLog > FSE_MAX_TABLELOG) - tableLog = FSE_MAX_TABLELOG; - return tableLog; -} - -unsigned FSE_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue) -{ - return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 2); -} - -/* Secondary normalization method. - To be used when primary method fails. */ - -static size_t FSE_normalizeM2(short *norm, U32 tableLog, const unsigned *count, size_t total, U32 maxSymbolValue) -{ - short const NOT_YET_ASSIGNED = -2; - U32 s; - U32 distributed = 0; - U32 ToDistribute; - - /* Init */ - U32 const lowThreshold = (U32)(total >> tableLog); - U32 lowOne = (U32)((total * 3) >> (tableLog + 1)); - - for (s = 0; s <= maxSymbolValue; s++) { - if (count[s] == 0) { - norm[s] = 0; - continue; - } - if (count[s] <= lowThreshold) { - norm[s] = -1; - distributed++; - total -= count[s]; - continue; - } - if (count[s] <= lowOne) { - norm[s] = 1; - distributed++; - total -= count[s]; - continue; - } - - norm[s] = NOT_YET_ASSIGNED; - } - ToDistribute = (1 << tableLog) - distributed; - - if ((total / ToDistribute) > lowOne) { - /* risk of rounding to zero */ - lowOne = (U32)((total * 3) / (ToDistribute * 2)); - for (s = 0; s <= maxSymbolValue; s++) { - if ((norm[s] == NOT_YET_ASSIGNED) && (count[s] <= lowOne)) { - norm[s] = 1; - distributed++; - total -= count[s]; - continue; - } - } - ToDistribute = (1 << tableLog) - distributed; - } - - if (distributed == maxSymbolValue + 1) { - /* all values are pretty poor; - probably incompressible data (should have already been detected); - find max, then give all remaining points to max */ - U32 maxV = 0, maxC = 0; - for (s = 0; s <= maxSymbolValue; s++) - if (count[s] > maxC) - maxV = s, maxC = count[s]; - norm[maxV] += (short)ToDistribute; - return 0; - } - - if (total == 0) { - /* all of the symbols were low enough for the lowOne or lowThreshold */ - for (s = 0; ToDistribute > 0; s = (s + 1) % (maxSymbolValue + 1)) - if (norm[s] > 0) - ToDistribute--, norm[s]++; - return 0; - } - - { - U64 const vStepLog = 62 - tableLog; - U64 const mid = (1ULL << (vStepLog - 1)) - 1; - U64 const rStep = div_u64((((U64)1 << vStepLog) * ToDistribute) + mid, (U32)total); /* scale on remaining */ - U64 tmpTotal = mid; - for (s = 0; s <= maxSymbolValue; s++) { - if (norm[s] == NOT_YET_ASSIGNED) { - U64 const end = tmpTotal + (count[s] * rStep); - U32 const sStart = (U32)(tmpTotal >> vStepLog); - U32 const sEnd = (U32)(end >> vStepLog); - U32 const weight = sEnd - sStart; - if (weight < 1) - return ERROR(GENERIC); - norm[s] = (short)weight; - tmpTotal = end; - } - } - } - - return 0; -} - -size_t FSE_normalizeCount(short *normalizedCounter, unsigned tableLog, const unsigned *count, size_t total, unsigned maxSymbolValue) -{ - /* Sanity checks */ - if (tableLog == 0) - tableLog = FSE_DEFAULT_TABLELOG; - if (tableLog < FSE_MIN_TABLELOG) - return ERROR(GENERIC); /* Unsupported size */ - if (tableLog > FSE_MAX_TABLELOG) - return ERROR(tableLog_tooLarge); /* Unsupported size */ - if (tableLog < FSE_minTableLog(total, maxSymbolValue)) - return ERROR(GENERIC); /* Too small tableLog, compression potentially impossible */ - - { - U32 const rtbTable[] = {0, 473195, 504333, 520860, 550000, 700000, 750000, 830000}; - U64 const scale = 62 - tableLog; - U64 const step = div_u64((U64)1 << 62, (U32)total); /* <== here, one division ! */ - U64 const vStep = 1ULL << (scale - 20); - int stillToDistribute = 1 << tableLog; - unsigned s; - unsigned largest = 0; - short largestP = 0; - U32 lowThreshold = (U32)(total >> tableLog); - - for (s = 0; s <= maxSymbolValue; s++) { - if (count[s] == total) - return 0; /* rle special case */ - if (count[s] == 0) { - normalizedCounter[s] = 0; - continue; - } - if (count[s] <= lowThreshold) { - normalizedCounter[s] = -1; - stillToDistribute--; - } else { - short proba = (short)((count[s] * step) >> scale); - if (proba < 8) { - U64 restToBeat = vStep * rtbTable[proba]; - proba += (count[s] * step) - ((U64)proba << scale) > restToBeat; - } - if (proba > largestP) - largestP = proba, largest = s; - normalizedCounter[s] = proba; - stillToDistribute -= proba; - } - } - if (-stillToDistribute >= (normalizedCounter[largest] >> 1)) { - /* corner case, need another normalization method */ - size_t const errorCode = FSE_normalizeM2(normalizedCounter, tableLog, count, total, maxSymbolValue); - if (FSE_isError(errorCode)) - return errorCode; - } else - normalizedCounter[largest] += (short)stillToDistribute; - } - - return tableLog; -} - -/* fake FSE_CTable, for raw (uncompressed) input */ -size_t FSE_buildCTable_raw(FSE_CTable *ct, unsigned nbBits) -{ - const unsigned tableSize = 1 << nbBits; - const unsigned tableMask = tableSize - 1; - const unsigned maxSymbolValue = tableMask; - void *const ptr = ct; - U16 *const tableU16 = ((U16 *)ptr) + 2; - void *const FSCT = ((U32 *)ptr) + 1 /* header */ + (tableSize >> 1); /* assumption : tableLog >= 1 */ - FSE_symbolCompressionTransform *const symbolTT = (FSE_symbolCompressionTransform *)(FSCT); - unsigned s; - - /* Sanity checks */ - if (nbBits < 1) - return ERROR(GENERIC); /* min size */ - - /* header */ - tableU16[-2] = (U16)nbBits; - tableU16[-1] = (U16)maxSymbolValue; - - /* Build table */ - for (s = 0; s < tableSize; s++) - tableU16[s] = (U16)(tableSize + s); - - /* Build Symbol Transformation Table */ - { - const U32 deltaNbBits = (nbBits << 16) - (1 << nbBits); - for (s = 0; s <= maxSymbolValue; s++) { - symbolTT[s].deltaNbBits = deltaNbBits; - symbolTT[s].deltaFindState = s - 1; - } - } - - return 0; -} - -/* fake FSE_CTable, for rle input (always same symbol) */ -size_t FSE_buildCTable_rle(FSE_CTable *ct, BYTE symbolValue) -{ - void *ptr = ct; - U16 *tableU16 = ((U16 *)ptr) + 2; - void *FSCTptr = (U32 *)ptr + 2; - FSE_symbolCompressionTransform *symbolTT = (FSE_symbolCompressionTransform *)FSCTptr; - - /* header */ - tableU16[-2] = (U16)0; - tableU16[-1] = (U16)symbolValue; - - /* Build table */ - tableU16[0] = 0; - tableU16[1] = 0; /* just in case */ - - /* Build Symbol Transformation Table */ - symbolTT[symbolValue].deltaNbBits = 0; - symbolTT[symbolValue].deltaFindState = 0; - - return 0; -} - -static size_t FSE_compress_usingCTable_generic(void *dst, size_t dstSize, const void *src, size_t srcSize, const FSE_CTable *ct, const unsigned fast) -{ - const BYTE *const istart = (const BYTE *)src; - const BYTE *const iend = istart + srcSize; - const BYTE *ip = iend; - - BIT_CStream_t bitC; - FSE_CState_t CState1, CState2; - - /* init */ - if (srcSize <= 2) - return 0; - { - size_t const initError = BIT_initCStream(&bitC, dst, dstSize); - if (FSE_isError(initError)) - return 0; /* not enough space available to write a bitstream */ - } - -#define FSE_FLUSHBITS(s) (fast ? BIT_flushBitsFast(s) : BIT_flushBits(s)) - - if (srcSize & 1) { - FSE_initCState2(&CState1, ct, *--ip); - FSE_initCState2(&CState2, ct, *--ip); - FSE_encodeSymbol(&bitC, &CState1, *--ip); - FSE_FLUSHBITS(&bitC); - } else { - FSE_initCState2(&CState2, ct, *--ip); - FSE_initCState2(&CState1, ct, *--ip); - } - - /* join to mod 4 */ - srcSize -= 2; - if ((sizeof(bitC.bitContainer) * 8 > FSE_MAX_TABLELOG * 4 + 7) && (srcSize & 2)) { /* test bit 2 */ - FSE_encodeSymbol(&bitC, &CState2, *--ip); - FSE_encodeSymbol(&bitC, &CState1, *--ip); - FSE_FLUSHBITS(&bitC); - } - - /* 2 or 4 encoding per loop */ - while (ip > istart) { - - FSE_encodeSymbol(&bitC, &CState2, *--ip); - - if (sizeof(bitC.bitContainer) * 8 < FSE_MAX_TABLELOG * 2 + 7) /* this test must be static */ - FSE_FLUSHBITS(&bitC); - - FSE_encodeSymbol(&bitC, &CState1, *--ip); - - if (sizeof(bitC.bitContainer) * 8 > FSE_MAX_TABLELOG * 4 + 7) { /* this test must be static */ - FSE_encodeSymbol(&bitC, &CState2, *--ip); - FSE_encodeSymbol(&bitC, &CState1, *--ip); - } - - FSE_FLUSHBITS(&bitC); - } - - FSE_flushCState(&bitC, &CState2); - FSE_flushCState(&bitC, &CState1); - return BIT_closeCStream(&bitC); -} - -size_t FSE_compress_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const FSE_CTable *ct) -{ - unsigned const fast = (dstSize >= FSE_BLOCKBOUND(srcSize)); - - if (fast) - return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 1); - else - return FSE_compress_usingCTable_generic(dst, dstSize, src, srcSize, ct, 0); -} - -size_t FSE_compressBound(size_t size) { return FSE_COMPRESSBOUND(size); } diff --git a/lib/zstd/fse_decompress.c b/lib/zstd/fse_decompress.c deleted file mode 100644 index 0b353530fb3f..000000000000 --- a/lib/zstd/fse_decompress.c +++ /dev/null @@ -1,325 +0,0 @@ -/* - * FSE : Finite State Entropy decoder - * Copyright (C) 2013-2015, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ - -/* ************************************************************** -* Compiler specifics -****************************************************************/ -#define FORCE_INLINE static __always_inline - -/* ************************************************************** -* Includes -****************************************************************/ -#include "bitstream.h" -#include "fse.h" -#include "zstd_internal.h" -#include -#include -#include /* memcpy, memset */ - -/* ************************************************************** -* Error Management -****************************************************************/ -#define FSE_isError ERR_isError -#define FSE_STATIC_ASSERT(c) \ - { \ - enum { FSE_static_assert = 1 / (int)(!!(c)) }; \ - } /* use only *after* variable declarations */ - -/* ************************************************************** -* Templates -****************************************************************/ -/* - designed to be included - for type-specific functions (template emulation in C) - Objective is to write these functions only once, for improved maintenance -*/ - -/* safety checks */ -#ifndef FSE_FUNCTION_EXTENSION -#error "FSE_FUNCTION_EXTENSION must be defined" -#endif -#ifndef FSE_FUNCTION_TYPE -#error "FSE_FUNCTION_TYPE must be defined" -#endif - -/* Function names */ -#define FSE_CAT(X, Y) X##Y -#define FSE_FUNCTION_NAME(X, Y) FSE_CAT(X, Y) -#define FSE_TYPE_NAME(X, Y) FSE_CAT(X, Y) - -/* Function templates */ - -size_t FSE_buildDTable_wksp(FSE_DTable *dt, const short *normalizedCounter, unsigned maxSymbolValue, unsigned tableLog, void *workspace, size_t workspaceSize) -{ - void *const tdPtr = dt + 1; /* because *dt is unsigned, 32-bits aligned on 32-bits */ - FSE_DECODE_TYPE *const tableDecode = (FSE_DECODE_TYPE *)(tdPtr); - U16 *symbolNext = (U16 *)workspace; - - U32 const maxSV1 = maxSymbolValue + 1; - U32 const tableSize = 1 << tableLog; - U32 highThreshold = tableSize - 1; - - /* Sanity Checks */ - if (workspaceSize < sizeof(U16) * (FSE_MAX_SYMBOL_VALUE + 1)) - return ERROR(tableLog_tooLarge); - if (maxSymbolValue > FSE_MAX_SYMBOL_VALUE) - return ERROR(maxSymbolValue_tooLarge); - if (tableLog > FSE_MAX_TABLELOG) - return ERROR(tableLog_tooLarge); - - /* Init, lay down lowprob symbols */ - { - FSE_DTableHeader DTableH; - DTableH.tableLog = (U16)tableLog; - DTableH.fastMode = 1; - { - S16 const largeLimit = (S16)(1 << (tableLog - 1)); - U32 s; - for (s = 0; s < maxSV1; s++) { - if (normalizedCounter[s] == -1) { - tableDecode[highThreshold--].symbol = (FSE_FUNCTION_TYPE)s; - symbolNext[s] = 1; - } else { - if (normalizedCounter[s] >= largeLimit) - DTableH.fastMode = 0; - symbolNext[s] = normalizedCounter[s]; - } - } - } - memcpy(dt, &DTableH, sizeof(DTableH)); - } - - /* Spread symbols */ - { - U32 const tableMask = tableSize - 1; - U32 const step = FSE_TABLESTEP(tableSize); - U32 s, position = 0; - for (s = 0; s < maxSV1; s++) { - int i; - for (i = 0; i < normalizedCounter[s]; i++) { - tableDecode[position].symbol = (FSE_FUNCTION_TYPE)s; - position = (position + step) & tableMask; - while (position > highThreshold) - position = (position + step) & tableMask; /* lowprob area */ - } - } - if (position != 0) - return ERROR(GENERIC); /* position must reach all cells once, otherwise normalizedCounter is incorrect */ - } - - /* Build Decoding table */ - { - U32 u; - for (u = 0; u < tableSize; u++) { - FSE_FUNCTION_TYPE const symbol = (FSE_FUNCTION_TYPE)(tableDecode[u].symbol); - U16 nextState = symbolNext[symbol]++; - tableDecode[u].nbBits = (BYTE)(tableLog - BIT_highbit32((U32)nextState)); - tableDecode[u].newState = (U16)((nextState << tableDecode[u].nbBits) - tableSize); - } - } - - return 0; -} - -/*-******************************************************* -* Decompression (Byte symbols) -*********************************************************/ -size_t FSE_buildDTable_rle(FSE_DTable *dt, BYTE symbolValue) -{ - void *ptr = dt; - FSE_DTableHeader *const DTableH = (FSE_DTableHeader *)ptr; - void *dPtr = dt + 1; - FSE_decode_t *const cell = (FSE_decode_t *)dPtr; - - DTableH->tableLog = 0; - DTableH->fastMode = 0; - - cell->newState = 0; - cell->symbol = symbolValue; - cell->nbBits = 0; - - return 0; -} - -size_t FSE_buildDTable_raw(FSE_DTable *dt, unsigned nbBits) -{ - void *ptr = dt; - FSE_DTableHeader *const DTableH = (FSE_DTableHeader *)ptr; - void *dPtr = dt + 1; - FSE_decode_t *const dinfo = (FSE_decode_t *)dPtr; - const unsigned tableSize = 1 << nbBits; - const unsigned tableMask = tableSize - 1; - const unsigned maxSV1 = tableMask + 1; - unsigned s; - - /* Sanity checks */ - if (nbBits < 1) - return ERROR(GENERIC); /* min size */ - - /* Build Decoding Table */ - DTableH->tableLog = (U16)nbBits; - DTableH->fastMode = 1; - for (s = 0; s < maxSV1; s++) { - dinfo[s].newState = 0; - dinfo[s].symbol = (BYTE)s; - dinfo[s].nbBits = (BYTE)nbBits; - } - - return 0; -} - -FORCE_INLINE size_t FSE_decompress_usingDTable_generic(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt, - const unsigned fast) -{ - BYTE *const ostart = (BYTE *)dst; - BYTE *op = ostart; - BYTE *const omax = op + maxDstSize; - BYTE *const olimit = omax - 3; - - BIT_DStream_t bitD; - FSE_DState_t state1; - FSE_DState_t state2; - - /* Init */ - CHECK_F(BIT_initDStream(&bitD, cSrc, cSrcSize)); - - FSE_initDState(&state1, &bitD, dt); - FSE_initDState(&state2, &bitD, dt); - -#define FSE_GETSYMBOL(statePtr) fast ? FSE_decodeSymbolFast(statePtr, &bitD) : FSE_decodeSymbol(statePtr, &bitD) - - /* 4 symbols per loop */ - for (; (BIT_reloadDStream(&bitD) == BIT_DStream_unfinished) & (op < olimit); op += 4) { - op[0] = FSE_GETSYMBOL(&state1); - - if (FSE_MAX_TABLELOG * 2 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */ - BIT_reloadDStream(&bitD); - - op[1] = FSE_GETSYMBOL(&state2); - - if (FSE_MAX_TABLELOG * 4 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */ - { - if (BIT_reloadDStream(&bitD) > BIT_DStream_unfinished) { - op += 2; - break; - } - } - - op[2] = FSE_GETSYMBOL(&state1); - - if (FSE_MAX_TABLELOG * 2 + 7 > sizeof(bitD.bitContainer) * 8) /* This test must be static */ - BIT_reloadDStream(&bitD); - - op[3] = FSE_GETSYMBOL(&state2); - } - - /* tail */ - /* note : BIT_reloadDStream(&bitD) >= FSE_DStream_partiallyFilled; Ends at exactly BIT_DStream_completed */ - while (1) { - if (op > (omax - 2)) - return ERROR(dstSize_tooSmall); - *op++ = FSE_GETSYMBOL(&state1); - if (BIT_reloadDStream(&bitD) == BIT_DStream_overflow) { - *op++ = FSE_GETSYMBOL(&state2); - break; - } - - if (op > (omax - 2)) - return ERROR(dstSize_tooSmall); - *op++ = FSE_GETSYMBOL(&state2); - if (BIT_reloadDStream(&bitD) == BIT_DStream_overflow) { - *op++ = FSE_GETSYMBOL(&state1); - break; - } - } - - return op - ostart; -} - -size_t FSE_decompress_usingDTable(void *dst, size_t originalSize, const void *cSrc, size_t cSrcSize, const FSE_DTable *dt) -{ - const void *ptr = dt; - const FSE_DTableHeader *DTableH = (const FSE_DTableHeader *)ptr; - const U32 fastMode = DTableH->fastMode; - - /* select fast mode (static) */ - if (fastMode) - return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 1); - return FSE_decompress_usingDTable_generic(dst, originalSize, cSrc, cSrcSize, dt, 0); -} - -size_t FSE_decompress_wksp(void *dst, size_t dstCapacity, const void *cSrc, size_t cSrcSize, unsigned maxLog, void *workspace, size_t workspaceSize) -{ - const BYTE *const istart = (const BYTE *)cSrc; - const BYTE *ip = istart; - unsigned tableLog; - unsigned maxSymbolValue = FSE_MAX_SYMBOL_VALUE; - size_t NCountLength; - - FSE_DTable *dt; - short *counting; - size_t spaceUsed32 = 0; - - FSE_STATIC_ASSERT(sizeof(FSE_DTable) == sizeof(U32)); - - dt = (FSE_DTable *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += FSE_DTABLE_SIZE_U32(maxLog); - counting = (short *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(sizeof(short) * (FSE_MAX_SYMBOL_VALUE + 1), sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - /* normal FSE decoding mode */ - NCountLength = FSE_readNCount(counting, &maxSymbolValue, &tableLog, istart, cSrcSize); - if (FSE_isError(NCountLength)) - return NCountLength; - // if (NCountLength >= cSrcSize) return ERROR(srcSize_wrong); /* too small input size; supposed to be already checked in NCountLength, only remaining - // case : NCountLength==cSrcSize */ - if (tableLog > maxLog) - return ERROR(tableLog_tooLarge); - ip += NCountLength; - cSrcSize -= NCountLength; - - CHECK_F(FSE_buildDTable_wksp(dt, counting, maxSymbolValue, tableLog, workspace, workspaceSize)); - - return FSE_decompress_usingDTable(dst, dstCapacity, ip, cSrcSize, dt); /* always return, even if it is an error code */ -} diff --git a/lib/zstd/huf.h b/lib/zstd/huf.h deleted file mode 100644 index 923218d12e28..000000000000 --- a/lib/zstd/huf.h +++ /dev/null @@ -1,212 +0,0 @@ -/* - * Huffman coder, part of New Generation Entropy library - * header file - * Copyright (C) 2013-2016, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ -#ifndef HUF_H_298734234 -#define HUF_H_298734234 - -/* *** Dependencies *** */ -#include /* size_t */ - -/* *** Tool functions *** */ -#define HUF_BLOCKSIZE_MAX (128 * 1024) /**< maximum input size for a single block compressed with HUF_compress */ -size_t HUF_compressBound(size_t size); /**< maximum compressed size (worst case) */ - -/* Error Management */ -unsigned HUF_isError(size_t code); /**< tells if a return value is an error code */ - -/* *** Advanced function *** */ - -/** HUF_compress4X_wksp() : -* Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of >= 1024 unsigned */ -size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace, - size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */ - -/* *** Dependencies *** */ -#include "mem.h" /* U32 */ - -/* *** Constants *** */ -#define HUF_TABLELOG_MAX 12 /* max configured tableLog (for static allocation); can be modified up to HUF_ABSOLUTEMAX_TABLELOG */ -#define HUF_TABLELOG_DEFAULT 11 /* tableLog by default, when not specified */ -#define HUF_SYMBOLVALUE_MAX 255 - -#define HUF_TABLELOG_ABSOLUTEMAX 15 /* absolute limit of HUF_MAX_TABLELOG. Beyond that value, code does not work */ -#if (HUF_TABLELOG_MAX > HUF_TABLELOG_ABSOLUTEMAX) -#error "HUF_TABLELOG_MAX is too large !" -#endif - -/* **************************************** -* Static allocation -******************************************/ -/* HUF buffer bounds */ -#define HUF_CTABLEBOUND 129 -#define HUF_BLOCKBOUND(size) (size + (size >> 8) + 8) /* only true if incompressible pre-filtered with fast heuristic */ -#define HUF_COMPRESSBOUND(size) (HUF_CTABLEBOUND + HUF_BLOCKBOUND(size)) /* Macro version, useful for static allocation */ - -/* static allocation of HUF's Compression Table */ -#define HUF_CREATE_STATIC_CTABLE(name, maxSymbolValue) \ - U32 name##hb[maxSymbolValue + 1]; \ - void *name##hv = &(name##hb); \ - HUF_CElt *name = (HUF_CElt *)(name##hv) /* no final ; */ - -/* static allocation of HUF's DTable */ -typedef U32 HUF_DTable; -#define HUF_DTABLE_SIZE(maxTableLog) (1 + (1 << (maxTableLog))) -#define HUF_CREATE_STATIC_DTABLEX2(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE((maxTableLog)-1)] = {((U32)((maxTableLog)-1) * 0x01000001)} -#define HUF_CREATE_STATIC_DTABLEX4(DTable, maxTableLog) HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = {((U32)(maxTableLog)*0x01000001)} - -/* The workspace must have alignment at least 4 and be at least this large */ -#define HUF_COMPRESS_WORKSPACE_SIZE (6 << 10) -#define HUF_COMPRESS_WORKSPACE_SIZE_U32 (HUF_COMPRESS_WORKSPACE_SIZE / sizeof(U32)) - -/* The workspace must have alignment at least 4 and be at least this large */ -#define HUF_DECOMPRESS_WORKSPACE_SIZE (3 << 10) -#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32)) - -/* **************************************** -* Advanced decompression functions -******************************************/ -size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize); /**< decodes RLE and uncompressed */ -size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, - size_t workspaceSize); /**< considers RLE and uncompressed as errors */ -size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, - size_t workspaceSize); /**< single-symbol decoder */ -size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, - size_t workspaceSize); /**< double-symbols decoder */ - -/* **************************************** -* HUF detailed API -******************************************/ -/*! -HUF_compress() does the following: -1. count symbol occurrence from source[] into table count[] using FSE_count() -2. (optional) refine tableLog using HUF_optimalTableLog() -3. build Huffman table from count using HUF_buildCTable() -4. save Huffman table to memory buffer using HUF_writeCTable_wksp() -5. encode the data stream using HUF_compress4X_usingCTable() - -The following API allows targeting specific sub-functions for advanced tasks. -For example, it's possible to compress several blocks using the same 'CTable', -or to save and regenerate 'CTable' using external methods. -*/ -/* FSE_count() : find it within "fse.h" */ -unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue); -typedef struct HUF_CElt_s HUF_CElt; /* incomplete type */ -size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, unsigned maxSymbolValue, unsigned huffLog, void *workspace, size_t workspaceSize); -size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable); - -typedef enum { - HUF_repeat_none, /**< Cannot use the previous table */ - HUF_repeat_check, /**< Can use the previous table but it must be checked. Note : The previous table must have been constructed by HUF_compress{1, - 4}X_repeat */ - HUF_repeat_valid /**< Can use the previous table and it is assumed to be valid */ -} HUF_repeat; -/** HUF_compress4X_repeat() : -* Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. -* If it uses hufTable it does not modify hufTable or repeat. -* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. -* If preferRepeat then the old table will always be used if valid. */ -size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace, - size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, - int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */ - -/** HUF_buildCTable_wksp() : - * Same as HUF_buildCTable(), but using externally allocated scratch buffer. - * `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned. - */ -size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize); - -/*! HUF_readStats() : - Read compact Huffman tree, saved by HUF_writeCTable(). - `huffWeight` is destination buffer. - @return : size read from `src` , or an error Code . - Note : Needed by HUF_readCTable() and HUF_readDTableXn() . */ -size_t HUF_readStats_wksp(BYTE *huffWeight, size_t hwSize, U32 *rankStats, U32 *nbSymbolsPtr, U32 *tableLogPtr, const void *src, size_t srcSize, - void *workspace, size_t workspaceSize); - -/** HUF_readCTable() : -* Loading a CTable saved with HUF_writeCTable() */ -size_t HUF_readCTable_wksp(HUF_CElt *CTable, unsigned maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize); - -/* -HUF_decompress() does the following: -1. select the decompression algorithm (X2, X4) based on pre-computed heuristics -2. build Huffman table from save, using HUF_readDTableXn() -3. decode 1 or 4 segments in parallel using HUF_decompressSXn_usingDTable -*/ - -/** HUF_selectDecoder() : -* Tells which decoder is likely to decode faster, -* based on a set of pre-determined metrics. -* @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 . -* Assumption : 0 < cSrcSize < dstSize <= 128 KB */ -U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize); - -size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize); -size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize); - -size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable); -size_t HUF_decompress4X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable); -size_t HUF_decompress4X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable); - -/* single stream variants */ - -size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace, - size_t wkspSize); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */ -size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable); -/** HUF_compress1X_repeat() : -* Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none. -* If it uses hufTable it does not modify hufTable or repeat. -* If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. -* If preferRepeat then the old table will always be used if valid. */ -size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void *workSpace, - size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, - int preferRepeat); /**< `workSpace` must be a table of at least HUF_COMPRESS_WORKSPACE_SIZE_U32 unsigned */ - -size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize); -size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, - size_t workspaceSize); /**< single-symbol decoder */ -size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, - size_t workspaceSize); /**< double-symbols decoder */ - -size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, - const HUF_DTable *DTable); /**< automatic selection of sing or double symbol decoder, based on DTable */ -size_t HUF_decompress1X2_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable); -size_t HUF_decompress1X4_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable); - -#endif /* HUF_H_298734234 */ diff --git a/lib/zstd/huf_compress.c b/lib/zstd/huf_compress.c deleted file mode 100644 index fd32838c185f..000000000000 --- a/lib/zstd/huf_compress.c +++ /dev/null @@ -1,773 +0,0 @@ -/* - * Huffman encoder, part of New Generation Entropy library - * Copyright (C) 2013-2016, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ - -/* ************************************************************** -* Includes -****************************************************************/ -#include "bitstream.h" -#include "fse.h" /* header compression */ -#include "huf.h" -#include -#include /* memcpy, memset */ - -/* ************************************************************** -* Error Management -****************************************************************/ -#define HUF_STATIC_ASSERT(c) \ - { \ - enum { HUF_static_assert = 1 / (int)(!!(c)) }; \ - } /* use only *after* variable declarations */ -#define CHECK_V_F(e, f) \ - size_t const e = f; \ - if (ERR_isError(e)) \ - return f -#define CHECK_F(f) \ - { \ - CHECK_V_F(_var_err__, f); \ - } - -/* ************************************************************** -* Utils -****************************************************************/ -unsigned HUF_optimalTableLog(unsigned maxTableLog, size_t srcSize, unsigned maxSymbolValue) -{ - return FSE_optimalTableLog_internal(maxTableLog, srcSize, maxSymbolValue, 1); -} - -/* ******************************************************* -* HUF : Huffman block compression -*********************************************************/ -/* HUF_compressWeights() : - * Same as FSE_compress(), but dedicated to huff0's weights compression. - * The use case needs much less stack memory. - * Note : all elements within weightTable are supposed to be <= HUF_TABLELOG_MAX. - */ -#define MAX_FSE_TABLELOG_FOR_HUFF_HEADER 6 -size_t HUF_compressWeights_wksp(void *dst, size_t dstSize, const void *weightTable, size_t wtSize, void *workspace, size_t workspaceSize) -{ - BYTE *const ostart = (BYTE *)dst; - BYTE *op = ostart; - BYTE *const oend = ostart + dstSize; - - U32 maxSymbolValue = HUF_TABLELOG_MAX; - U32 tableLog = MAX_FSE_TABLELOG_FOR_HUFF_HEADER; - - FSE_CTable *CTable; - U32 *count; - S16 *norm; - size_t spaceUsed32 = 0; - - HUF_STATIC_ASSERT(sizeof(FSE_CTable) == sizeof(U32)); - - CTable = (FSE_CTable *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += FSE_CTABLE_SIZE_U32(MAX_FSE_TABLELOG_FOR_HUFF_HEADER, HUF_TABLELOG_MAX); - count = (U32 *)workspace + spaceUsed32; - spaceUsed32 += HUF_TABLELOG_MAX + 1; - norm = (S16 *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(sizeof(S16) * (HUF_TABLELOG_MAX + 1), sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - /* init conditions */ - if (wtSize <= 1) - return 0; /* Not compressible */ - - /* Scan input and build symbol stats */ - { - CHECK_V_F(maxCount, FSE_count_simple(count, &maxSymbolValue, weightTable, wtSize)); - if (maxCount == wtSize) - return 1; /* only a single symbol in src : rle */ - if (maxCount == 1) - return 0; /* each symbol present maximum once => not compressible */ - } - - tableLog = FSE_optimalTableLog(tableLog, wtSize, maxSymbolValue); - CHECK_F(FSE_normalizeCount(norm, tableLog, count, wtSize, maxSymbolValue)); - - /* Write table description header */ - { - CHECK_V_F(hSize, FSE_writeNCount(op, oend - op, norm, maxSymbolValue, tableLog)); - op += hSize; - } - - /* Compress */ - CHECK_F(FSE_buildCTable_wksp(CTable, norm, maxSymbolValue, tableLog, workspace, workspaceSize)); - { - CHECK_V_F(cSize, FSE_compress_usingCTable(op, oend - op, weightTable, wtSize, CTable)); - if (cSize == 0) - return 0; /* not enough space for compressed data */ - op += cSize; - } - - return op - ostart; -} - -struct HUF_CElt_s { - U16 val; - BYTE nbBits; -}; /* typedef'd to HUF_CElt within "huf.h" */ - -/*! HUF_writeCTable_wksp() : - `CTable` : Huffman tree to save, using huf representation. - @return : size of saved CTable */ -size_t HUF_writeCTable_wksp(void *dst, size_t maxDstSize, const HUF_CElt *CTable, U32 maxSymbolValue, U32 huffLog, void *workspace, size_t workspaceSize) -{ - BYTE *op = (BYTE *)dst; - U32 n; - - BYTE *bitsToWeight; - BYTE *huffWeight; - size_t spaceUsed32 = 0; - - bitsToWeight = (BYTE *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(HUF_TABLELOG_MAX + 1, sizeof(U32)) >> 2; - huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX, sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - /* check conditions */ - if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) - return ERROR(maxSymbolValue_tooLarge); - - /* convert to weight */ - bitsToWeight[0] = 0; - for (n = 1; n < huffLog + 1; n++) - bitsToWeight[n] = (BYTE)(huffLog + 1 - n); - for (n = 0; n < maxSymbolValue; n++) - huffWeight[n] = bitsToWeight[CTable[n].nbBits]; - - /* attempt weights compression by FSE */ - { - CHECK_V_F(hSize, HUF_compressWeights_wksp(op + 1, maxDstSize - 1, huffWeight, maxSymbolValue, workspace, workspaceSize)); - if ((hSize > 1) & (hSize < maxSymbolValue / 2)) { /* FSE compressed */ - op[0] = (BYTE)hSize; - return hSize + 1; - } - } - - /* write raw values as 4-bits (max : 15) */ - if (maxSymbolValue > (256 - 128)) - return ERROR(GENERIC); /* should not happen : likely means source cannot be compressed */ - if (((maxSymbolValue + 1) / 2) + 1 > maxDstSize) - return ERROR(dstSize_tooSmall); /* not enough space within dst buffer */ - op[0] = (BYTE)(128 /*special case*/ + (maxSymbolValue - 1)); - huffWeight[maxSymbolValue] = 0; /* to be sure it doesn't cause msan issue in final combination */ - for (n = 0; n < maxSymbolValue; n += 2) - op[(n / 2) + 1] = (BYTE)((huffWeight[n] << 4) + huffWeight[n + 1]); - return ((maxSymbolValue + 1) / 2) + 1; -} - -size_t HUF_readCTable_wksp(HUF_CElt *CTable, U32 maxSymbolValue, const void *src, size_t srcSize, void *workspace, size_t workspaceSize) -{ - U32 *rankVal; - BYTE *huffWeight; - U32 tableLog = 0; - U32 nbSymbols = 0; - size_t readSize; - size_t spaceUsed32 = 0; - - rankVal = (U32 *)workspace + spaceUsed32; - spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1; - huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - /* get symbol weights */ - readSize = HUF_readStats_wksp(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize); - if (ERR_isError(readSize)) - return readSize; - - /* check result */ - if (tableLog > HUF_TABLELOG_MAX) - return ERROR(tableLog_tooLarge); - if (nbSymbols > maxSymbolValue + 1) - return ERROR(maxSymbolValue_tooSmall); - - /* Prepare base value per rank */ - { - U32 n, nextRankStart = 0; - for (n = 1; n <= tableLog; n++) { - U32 curr = nextRankStart; - nextRankStart += (rankVal[n] << (n - 1)); - rankVal[n] = curr; - } - } - - /* fill nbBits */ - { - U32 n; - for (n = 0; n < nbSymbols; n++) { - const U32 w = huffWeight[n]; - CTable[n].nbBits = (BYTE)(tableLog + 1 - w); - } - } - - /* fill val */ - { - U16 nbPerRank[HUF_TABLELOG_MAX + 2] = {0}; /* support w=0=>n=tableLog+1 */ - U16 valPerRank[HUF_TABLELOG_MAX + 2] = {0}; - { - U32 n; - for (n = 0; n < nbSymbols; n++) - nbPerRank[CTable[n].nbBits]++; - } - /* determine stating value per rank */ - valPerRank[tableLog + 1] = 0; /* for w==0 */ - { - U16 min = 0; - U32 n; - for (n = tableLog; n > 0; n--) { /* start at n=tablelog <-> w=1 */ - valPerRank[n] = min; /* get starting value within each rank */ - min += nbPerRank[n]; - min >>= 1; - } - } - /* assign value within rank, symbol order */ - { - U32 n; - for (n = 0; n <= maxSymbolValue; n++) - CTable[n].val = valPerRank[CTable[n].nbBits]++; - } - } - - return readSize; -} - -typedef struct nodeElt_s { - U32 count; - U16 parent; - BYTE byte; - BYTE nbBits; -} nodeElt; - -static U32 HUF_setMaxHeight(nodeElt *huffNode, U32 lastNonNull, U32 maxNbBits) -{ - const U32 largestBits = huffNode[lastNonNull].nbBits; - if (largestBits <= maxNbBits) - return largestBits; /* early exit : no elt > maxNbBits */ - - /* there are several too large elements (at least >= 2) */ - { - int totalCost = 0; - const U32 baseCost = 1 << (largestBits - maxNbBits); - U32 n = lastNonNull; - - while (huffNode[n].nbBits > maxNbBits) { - totalCost += baseCost - (1 << (largestBits - huffNode[n].nbBits)); - huffNode[n].nbBits = (BYTE)maxNbBits; - n--; - } /* n stops at huffNode[n].nbBits <= maxNbBits */ - while (huffNode[n].nbBits == maxNbBits) - n--; /* n end at index of smallest symbol using < maxNbBits */ - - /* renorm totalCost */ - totalCost >>= (largestBits - maxNbBits); /* note : totalCost is necessarily a multiple of baseCost */ - - /* repay normalized cost */ - { - U32 const noSymbol = 0xF0F0F0F0; - U32 rankLast[HUF_TABLELOG_MAX + 2]; - int pos; - - /* Get pos of last (smallest) symbol per rank */ - memset(rankLast, 0xF0, sizeof(rankLast)); - { - U32 currNbBits = maxNbBits; - for (pos = n; pos >= 0; pos--) { - if (huffNode[pos].nbBits >= currNbBits) - continue; - currNbBits = huffNode[pos].nbBits; /* < maxNbBits */ - rankLast[maxNbBits - currNbBits] = pos; - } - } - - while (totalCost > 0) { - U32 nBitsToDecrease = BIT_highbit32(totalCost) + 1; - for (; nBitsToDecrease > 1; nBitsToDecrease--) { - U32 highPos = rankLast[nBitsToDecrease]; - U32 lowPos = rankLast[nBitsToDecrease - 1]; - if (highPos == noSymbol) - continue; - if (lowPos == noSymbol) - break; - { - U32 const highTotal = huffNode[highPos].count; - U32 const lowTotal = 2 * huffNode[lowPos].count; - if (highTotal <= lowTotal) - break; - } - } - /* only triggered when no more rank 1 symbol left => find closest one (note : there is necessarily at least one !) */ - /* HUF_MAX_TABLELOG test just to please gcc 5+; but it should not be necessary */ - while ((nBitsToDecrease <= HUF_TABLELOG_MAX) && (rankLast[nBitsToDecrease] == noSymbol)) - nBitsToDecrease++; - totalCost -= 1 << (nBitsToDecrease - 1); - if (rankLast[nBitsToDecrease - 1] == noSymbol) - rankLast[nBitsToDecrease - 1] = rankLast[nBitsToDecrease]; /* this rank is no longer empty */ - huffNode[rankLast[nBitsToDecrease]].nbBits++; - if (rankLast[nBitsToDecrease] == 0) /* special case, reached largest symbol */ - rankLast[nBitsToDecrease] = noSymbol; - else { - rankLast[nBitsToDecrease]--; - if (huffNode[rankLast[nBitsToDecrease]].nbBits != maxNbBits - nBitsToDecrease) - rankLast[nBitsToDecrease] = noSymbol; /* this rank is now empty */ - } - } /* while (totalCost > 0) */ - - while (totalCost < 0) { /* Sometimes, cost correction overshoot */ - if (rankLast[1] == noSymbol) { /* special case : no rank 1 symbol (using maxNbBits-1); let's create one from largest rank 0 - (using maxNbBits) */ - while (huffNode[n].nbBits == maxNbBits) - n--; - huffNode[n + 1].nbBits--; - rankLast[1] = n + 1; - totalCost++; - continue; - } - huffNode[rankLast[1] + 1].nbBits--; - rankLast[1]++; - totalCost++; - } - } - } /* there are several too large elements (at least >= 2) */ - - return maxNbBits; -} - -typedef struct { - U32 base; - U32 curr; -} rankPos; - -static void HUF_sort(nodeElt *huffNode, const U32 *count, U32 maxSymbolValue) -{ - rankPos rank[32]; - U32 n; - - memset(rank, 0, sizeof(rank)); - for (n = 0; n <= maxSymbolValue; n++) { - U32 r = BIT_highbit32(count[n] + 1); - rank[r].base++; - } - for (n = 30; n > 0; n--) - rank[n - 1].base += rank[n].base; - for (n = 0; n < 32; n++) - rank[n].curr = rank[n].base; - for (n = 0; n <= maxSymbolValue; n++) { - U32 const c = count[n]; - U32 const r = BIT_highbit32(c + 1) + 1; - U32 pos = rank[r].curr++; - while ((pos > rank[r].base) && (c > huffNode[pos - 1].count)) - huffNode[pos] = huffNode[pos - 1], pos--; - huffNode[pos].count = c; - huffNode[pos].byte = (BYTE)n; - } -} - -/** HUF_buildCTable_wksp() : - * Same as HUF_buildCTable(), but using externally allocated scratch buffer. - * `workSpace` must be aligned on 4-bytes boundaries, and be at least as large as a table of 1024 unsigned. - */ -#define STARTNODE (HUF_SYMBOLVALUE_MAX + 1) -typedef nodeElt huffNodeTable[2 * HUF_SYMBOLVALUE_MAX + 1 + 1]; -size_t HUF_buildCTable_wksp(HUF_CElt *tree, const U32 *count, U32 maxSymbolValue, U32 maxNbBits, void *workSpace, size_t wkspSize) -{ - nodeElt *const huffNode0 = (nodeElt *)workSpace; - nodeElt *const huffNode = huffNode0 + 1; - U32 n, nonNullRank; - int lowS, lowN; - U16 nodeNb = STARTNODE; - U32 nodeRoot; - - /* safety checks */ - if (wkspSize < sizeof(huffNodeTable)) - return ERROR(GENERIC); /* workSpace is not large enough */ - if (maxNbBits == 0) - maxNbBits = HUF_TABLELOG_DEFAULT; - if (maxSymbolValue > HUF_SYMBOLVALUE_MAX) - return ERROR(GENERIC); - memset(huffNode0, 0, sizeof(huffNodeTable)); - - /* sort, decreasing order */ - HUF_sort(huffNode, count, maxSymbolValue); - - /* init for parents */ - nonNullRank = maxSymbolValue; - while (huffNode[nonNullRank].count == 0) - nonNullRank--; - lowS = nonNullRank; - nodeRoot = nodeNb + lowS - 1; - lowN = nodeNb; - huffNode[nodeNb].count = huffNode[lowS].count + huffNode[lowS - 1].count; - huffNode[lowS].parent = huffNode[lowS - 1].parent = nodeNb; - nodeNb++; - lowS -= 2; - for (n = nodeNb; n <= nodeRoot; n++) - huffNode[n].count = (U32)(1U << 30); - huffNode0[0].count = (U32)(1U << 31); /* fake entry, strong barrier */ - - /* create parents */ - while (nodeNb <= nodeRoot) { - U32 n1 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++; - U32 n2 = (huffNode[lowS].count < huffNode[lowN].count) ? lowS-- : lowN++; - huffNode[nodeNb].count = huffNode[n1].count + huffNode[n2].count; - huffNode[n1].parent = huffNode[n2].parent = nodeNb; - nodeNb++; - } - - /* distribute weights (unlimited tree height) */ - huffNode[nodeRoot].nbBits = 0; - for (n = nodeRoot - 1; n >= STARTNODE; n--) - huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1; - for (n = 0; n <= nonNullRank; n++) - huffNode[n].nbBits = huffNode[huffNode[n].parent].nbBits + 1; - - /* enforce maxTableLog */ - maxNbBits = HUF_setMaxHeight(huffNode, nonNullRank, maxNbBits); - - /* fill result into tree (val, nbBits) */ - { - U16 nbPerRank[HUF_TABLELOG_MAX + 1] = {0}; - U16 valPerRank[HUF_TABLELOG_MAX + 1] = {0}; - if (maxNbBits > HUF_TABLELOG_MAX) - return ERROR(GENERIC); /* check fit into table */ - for (n = 0; n <= nonNullRank; n++) - nbPerRank[huffNode[n].nbBits]++; - /* determine stating value per rank */ - { - U16 min = 0; - for (n = maxNbBits; n > 0; n--) { - valPerRank[n] = min; /* get starting value within each rank */ - min += nbPerRank[n]; - min >>= 1; - } - } - for (n = 0; n <= maxSymbolValue; n++) - tree[huffNode[n].byte].nbBits = huffNode[n].nbBits; /* push nbBits per symbol, symbol order */ - for (n = 0; n <= maxSymbolValue; n++) - tree[n].val = valPerRank[tree[n].nbBits]++; /* assign value within rank, symbol order */ - } - - return maxNbBits; -} - -static size_t HUF_estimateCompressedSize(HUF_CElt *CTable, const unsigned *count, unsigned maxSymbolValue) -{ - size_t nbBits = 0; - int s; - for (s = 0; s <= (int)maxSymbolValue; ++s) { - nbBits += CTable[s].nbBits * count[s]; - } - return nbBits >> 3; -} - -static int HUF_validateCTable(const HUF_CElt *CTable, const unsigned *count, unsigned maxSymbolValue) -{ - int bad = 0; - int s; - for (s = 0; s <= (int)maxSymbolValue; ++s) { - bad |= (count[s] != 0) & (CTable[s].nbBits == 0); - } - return !bad; -} - -static void HUF_encodeSymbol(BIT_CStream_t *bitCPtr, U32 symbol, const HUF_CElt *CTable) -{ - BIT_addBitsFast(bitCPtr, CTable[symbol].val, CTable[symbol].nbBits); -} - -size_t HUF_compressBound(size_t size) { return HUF_COMPRESSBOUND(size); } - -#define HUF_FLUSHBITS(s) BIT_flushBits(s) - -#define HUF_FLUSHBITS_1(stream) \ - if (sizeof((stream)->bitContainer) * 8 < HUF_TABLELOG_MAX * 2 + 7) \ - HUF_FLUSHBITS(stream) - -#define HUF_FLUSHBITS_2(stream) \ - if (sizeof((stream)->bitContainer) * 8 < HUF_TABLELOG_MAX * 4 + 7) \ - HUF_FLUSHBITS(stream) - -size_t HUF_compress1X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable) -{ - const BYTE *ip = (const BYTE *)src; - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstSize; - BYTE *op = ostart; - size_t n; - BIT_CStream_t bitC; - - /* init */ - if (dstSize < 8) - return 0; /* not enough space to compress */ - { - size_t const initErr = BIT_initCStream(&bitC, op, oend - op); - if (HUF_isError(initErr)) - return 0; - } - - n = srcSize & ~3; /* join to mod 4 */ - switch (srcSize & 3) { - case 3: HUF_encodeSymbol(&bitC, ip[n + 2], CTable); HUF_FLUSHBITS_2(&bitC); - fallthrough; - case 2: HUF_encodeSymbol(&bitC, ip[n + 1], CTable); HUF_FLUSHBITS_1(&bitC); - fallthrough; - case 1: HUF_encodeSymbol(&bitC, ip[n + 0], CTable); HUF_FLUSHBITS(&bitC); - fallthrough; - case 0: - default:; - } - - for (; n > 0; n -= 4) { /* note : n&3==0 at this stage */ - HUF_encodeSymbol(&bitC, ip[n - 1], CTable); - HUF_FLUSHBITS_1(&bitC); - HUF_encodeSymbol(&bitC, ip[n - 2], CTable); - HUF_FLUSHBITS_2(&bitC); - HUF_encodeSymbol(&bitC, ip[n - 3], CTable); - HUF_FLUSHBITS_1(&bitC); - HUF_encodeSymbol(&bitC, ip[n - 4], CTable); - HUF_FLUSHBITS(&bitC); - } - - return BIT_closeCStream(&bitC); -} - -size_t HUF_compress4X_usingCTable(void *dst, size_t dstSize, const void *src, size_t srcSize, const HUF_CElt *CTable) -{ - size_t const segmentSize = (srcSize + 3) / 4; /* first 3 segments */ - const BYTE *ip = (const BYTE *)src; - const BYTE *const iend = ip + srcSize; - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstSize; - BYTE *op = ostart; - - if (dstSize < 6 + 1 + 1 + 1 + 8) - return 0; /* minimum space to compress successfully */ - if (srcSize < 12) - return 0; /* no saving possible : too small input */ - op += 6; /* jumpTable */ - - { - CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable)); - if (cSize == 0) - return 0; - ZSTD_writeLE16(ostart, (U16)cSize); - op += cSize; - } - - ip += segmentSize; - { - CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable)); - if (cSize == 0) - return 0; - ZSTD_writeLE16(ostart + 2, (U16)cSize); - op += cSize; - } - - ip += segmentSize; - { - CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, segmentSize, CTable)); - if (cSize == 0) - return 0; - ZSTD_writeLE16(ostart + 4, (U16)cSize); - op += cSize; - } - - ip += segmentSize; - { - CHECK_V_F(cSize, HUF_compress1X_usingCTable(op, oend - op, ip, iend - ip, CTable)); - if (cSize == 0) - return 0; - op += cSize; - } - - return op - ostart; -} - -static size_t HUF_compressCTable_internal(BYTE *const ostart, BYTE *op, BYTE *const oend, const void *src, size_t srcSize, unsigned singleStream, - const HUF_CElt *CTable) -{ - size_t const cSize = - singleStream ? HUF_compress1X_usingCTable(op, oend - op, src, srcSize, CTable) : HUF_compress4X_usingCTable(op, oend - op, src, srcSize, CTable); - if (HUF_isError(cSize)) { - return cSize; - } - if (cSize == 0) { - return 0; - } /* uncompressible */ - op += cSize; - /* check compressibility */ - if ((size_t)(op - ostart) >= srcSize - 1) { - return 0; - } - return op - ostart; -} - -/* `workSpace` must a table of at least 1024 unsigned */ -static size_t HUF_compress_internal(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, - unsigned singleStream, void *workSpace, size_t wkspSize, HUF_CElt *oldHufTable, HUF_repeat *repeat, int preferRepeat) -{ - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstSize; - BYTE *op = ostart; - - U32 *count; - size_t const countSize = sizeof(U32) * (HUF_SYMBOLVALUE_MAX + 1); - HUF_CElt *CTable; - size_t const CTableSize = sizeof(HUF_CElt) * (HUF_SYMBOLVALUE_MAX + 1); - - /* checks & inits */ - if (wkspSize < sizeof(huffNodeTable) + countSize + CTableSize) - return ERROR(GENERIC); - if (!srcSize) - return 0; /* Uncompressed (note : 1 means rle, so first byte must be correct) */ - if (!dstSize) - return 0; /* cannot fit within dst budget */ - if (srcSize > HUF_BLOCKSIZE_MAX) - return ERROR(srcSize_wrong); /* curr block size limit */ - if (huffLog > HUF_TABLELOG_MAX) - return ERROR(tableLog_tooLarge); - if (!maxSymbolValue) - maxSymbolValue = HUF_SYMBOLVALUE_MAX; - if (!huffLog) - huffLog = HUF_TABLELOG_DEFAULT; - - count = (U32 *)workSpace; - workSpace = (BYTE *)workSpace + countSize; - wkspSize -= countSize; - CTable = (HUF_CElt *)workSpace; - workSpace = (BYTE *)workSpace + CTableSize; - wkspSize -= CTableSize; - - /* Heuristic : If we don't need to check the validity of the old table use the old table for small inputs */ - if (preferRepeat && repeat && *repeat == HUF_repeat_valid) { - return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable); - } - - /* Scan input and build symbol stats */ - { - CHECK_V_F(largest, FSE_count_wksp(count, &maxSymbolValue, (const BYTE *)src, srcSize, (U32 *)workSpace)); - if (largest == srcSize) { - *ostart = ((const BYTE *)src)[0]; - return 1; - } /* single symbol, rle */ - if (largest <= (srcSize >> 7) + 1) - return 0; /* Fast heuristic : not compressible enough */ - } - - /* Check validity of previous table */ - if (repeat && *repeat == HUF_repeat_check && !HUF_validateCTable(oldHufTable, count, maxSymbolValue)) { - *repeat = HUF_repeat_none; - } - /* Heuristic : use existing table for small inputs */ - if (preferRepeat && repeat && *repeat != HUF_repeat_none) { - return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable); - } - - /* Build Huffman Tree */ - huffLog = HUF_optimalTableLog(huffLog, srcSize, maxSymbolValue); - { - CHECK_V_F(maxBits, HUF_buildCTable_wksp(CTable, count, maxSymbolValue, huffLog, workSpace, wkspSize)); - huffLog = (U32)maxBits; - /* Zero the unused symbols so we can check it for validity */ - memset(CTable + maxSymbolValue + 1, 0, CTableSize - (maxSymbolValue + 1) * sizeof(HUF_CElt)); - } - - /* Write table description header */ - { - CHECK_V_F(hSize, HUF_writeCTable_wksp(op, dstSize, CTable, maxSymbolValue, huffLog, workSpace, wkspSize)); - /* Check if using the previous table will be beneficial */ - if (repeat && *repeat != HUF_repeat_none) { - size_t const oldSize = HUF_estimateCompressedSize(oldHufTable, count, maxSymbolValue); - size_t const newSize = HUF_estimateCompressedSize(CTable, count, maxSymbolValue); - if (oldSize <= hSize + newSize || hSize + 12 >= srcSize) { - return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable); - } - } - /* Use the new table */ - if (hSize + 12ul >= srcSize) { - return 0; - } - op += hSize; - if (repeat) { - *repeat = HUF_repeat_none; - } - if (oldHufTable) { - memcpy(oldHufTable, CTable, CTableSize); - } /* Save the new table */ - } - return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, CTable); -} - -size_t HUF_compress1X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace, - size_t wkspSize) -{ - return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace, wkspSize, NULL, NULL, 0); -} - -size_t HUF_compress1X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace, - size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, int preferRepeat) -{ - return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 1 /* single stream */, workSpace, wkspSize, hufTable, repeat, - preferRepeat); -} - -size_t HUF_compress4X_wksp(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace, - size_t wkspSize) -{ - return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace, wkspSize, NULL, NULL, 0); -} - -size_t HUF_compress4X_repeat(void *dst, size_t dstSize, const void *src, size_t srcSize, unsigned maxSymbolValue, unsigned huffLog, void *workSpace, - size_t wkspSize, HUF_CElt *hufTable, HUF_repeat *repeat, int preferRepeat) -{ - return HUF_compress_internal(dst, dstSize, src, srcSize, maxSymbolValue, huffLog, 0 /* 4 streams */, workSpace, wkspSize, hufTable, repeat, - preferRepeat); -} diff --git a/lib/zstd/huf_decompress.c b/lib/zstd/huf_decompress.c deleted file mode 100644 index 6526482047dc..000000000000 --- a/lib/zstd/huf_decompress.c +++ /dev/null @@ -1,960 +0,0 @@ -/* - * Huffman decoder, part of New Generation Entropy library - * Copyright (C) 2013-2016, Yann Collet. - * - * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - * - * You can contact the author at : - * - Source repository : https://github.com/Cyan4973/FiniteStateEntropy - */ - -/* ************************************************************** -* Compiler specifics -****************************************************************/ -#define FORCE_INLINE static __always_inline - -/* ************************************************************** -* Dependencies -****************************************************************/ -#include "bitstream.h" /* BIT_* */ -#include "fse.h" /* header compression */ -#include "huf.h" -#include -#include -#include /* memcpy, memset */ - -/* ************************************************************** -* Error Management -****************************************************************/ -#define HUF_STATIC_ASSERT(c) \ - { \ - enum { HUF_static_assert = 1 / (int)(!!(c)) }; \ - } /* use only *after* variable declarations */ - -/*-***************************/ -/* generic DTableDesc */ -/*-***************************/ - -typedef struct { - BYTE maxTableLog; - BYTE tableType; - BYTE tableLog; - BYTE reserved; -} DTableDesc; - -static DTableDesc HUF_getDTableDesc(const HUF_DTable *table) -{ - DTableDesc dtd; - memcpy(&dtd, table, sizeof(dtd)); - return dtd; -} - -/*-***************************/ -/* single-symbol decoding */ -/*-***************************/ - -typedef struct { - BYTE byte; - BYTE nbBits; -} HUF_DEltX2; /* single-symbol decoding */ - -size_t HUF_readDTableX2_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize) -{ - U32 tableLog = 0; - U32 nbSymbols = 0; - size_t iSize; - void *const dtPtr = DTable + 1; - HUF_DEltX2 *const dt = (HUF_DEltX2 *)dtPtr; - - U32 *rankVal; - BYTE *huffWeight; - size_t spaceUsed32 = 0; - - rankVal = (U32 *)workspace + spaceUsed32; - spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1; - huffWeight = (BYTE *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable)); - /* memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */ - - iSize = HUF_readStats_wksp(huffWeight, HUF_SYMBOLVALUE_MAX + 1, rankVal, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize); - if (HUF_isError(iSize)) - return iSize; - - /* Table header */ - { - DTableDesc dtd = HUF_getDTableDesc(DTable); - if (tableLog > (U32)(dtd.maxTableLog + 1)) - return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */ - dtd.tableType = 0; - dtd.tableLog = (BYTE)tableLog; - memcpy(DTable, &dtd, sizeof(dtd)); - } - - /* Calculate starting value for each rank */ - { - U32 n, nextRankStart = 0; - for (n = 1; n < tableLog + 1; n++) { - U32 const curr = nextRankStart; - nextRankStart += (rankVal[n] << (n - 1)); - rankVal[n] = curr; - } - } - - /* fill DTable */ - { - U32 n; - for (n = 0; n < nbSymbols; n++) { - U32 const w = huffWeight[n]; - U32 const length = (1 << w) >> 1; - U32 u; - HUF_DEltX2 D; - D.byte = (BYTE)n; - D.nbBits = (BYTE)(tableLog + 1 - w); - for (u = rankVal[w]; u < rankVal[w] + length; u++) - dt[u] = D; - rankVal[w] += length; - } - } - - return iSize; -} - -static BYTE HUF_decodeSymbolX2(BIT_DStream_t *Dstream, const HUF_DEltX2 *dt, const U32 dtLog) -{ - size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */ - BYTE const c = dt[val].byte; - BIT_skipBits(Dstream, dt[val].nbBits); - return c; -} - -#define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) *ptr++ = HUF_decodeSymbolX2(DStreamPtr, dt, dtLog) - -#define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr) \ - if (ZSTD_64bits() || (HUF_TABLELOG_MAX <= 12)) \ - HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) - -#define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \ - if (ZSTD_64bits()) \ - HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) - -FORCE_INLINE size_t HUF_decodeStreamX2(BYTE *p, BIT_DStream_t *const bitDPtr, BYTE *const pEnd, const HUF_DEltX2 *const dt, const U32 dtLog) -{ - BYTE *const pStart = p; - - /* up to 4 symbols at a time */ - while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) && (p <= pEnd - 4)) { - HUF_DECODE_SYMBOLX2_2(p, bitDPtr); - HUF_DECODE_SYMBOLX2_1(p, bitDPtr); - HUF_DECODE_SYMBOLX2_2(p, bitDPtr); - HUF_DECODE_SYMBOLX2_0(p, bitDPtr); - } - - /* closer to the end */ - while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) && (p < pEnd)) - HUF_DECODE_SYMBOLX2_0(p, bitDPtr); - - /* no more data to retrieve from bitstream, hence no need to reload */ - while (p < pEnd) - HUF_DECODE_SYMBOLX2_0(p, bitDPtr); - - return pEnd - pStart; -} - -static size_t HUF_decompress1X2_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - BYTE *op = (BYTE *)dst; - BYTE *const oend = op + dstSize; - const void *dtPtr = DTable + 1; - const HUF_DEltX2 *const dt = (const HUF_DEltX2 *)dtPtr; - BIT_DStream_t bitD; - DTableDesc const dtd = HUF_getDTableDesc(DTable); - U32 const dtLog = dtd.tableLog; - - { - size_t const errorCode = BIT_initDStream(&bitD, cSrc, cSrcSize); - if (HUF_isError(errorCode)) - return errorCode; - } - - HUF_decodeStreamX2(op, &bitD, oend, dt, dtLog); - - /* check */ - if (!BIT_endOfDStream(&bitD)) - return ERROR(corruption_detected); - - return dstSize; -} - -size_t HUF_decompress1X2_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - DTableDesc dtd = HUF_getDTableDesc(DTable); - if (dtd.tableType != 0) - return ERROR(GENERIC); - return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable); -} - -size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable *DCtx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - const BYTE *ip = (const BYTE *)cSrc; - - size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workspace, workspaceSize); - if (HUF_isError(hSize)) - return hSize; - if (hSize >= cSrcSize) - return ERROR(srcSize_wrong); - ip += hSize; - cSrcSize -= hSize; - - return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx); -} - -static size_t HUF_decompress4X2_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - /* Check */ - if (cSrcSize < 10) - return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */ - - { - const BYTE *const istart = (const BYTE *)cSrc; - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstSize; - const void *const dtPtr = DTable + 1; - const HUF_DEltX2 *const dt = (const HUF_DEltX2 *)dtPtr; - - /* Init */ - BIT_DStream_t bitD1; - BIT_DStream_t bitD2; - BIT_DStream_t bitD3; - BIT_DStream_t bitD4; - size_t const length1 = ZSTD_readLE16(istart); - size_t const length2 = ZSTD_readLE16(istart + 2); - size_t const length3 = ZSTD_readLE16(istart + 4); - size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6); - const BYTE *const istart1 = istart + 6; /* jumpTable */ - const BYTE *const istart2 = istart1 + length1; - const BYTE *const istart3 = istart2 + length2; - const BYTE *const istart4 = istart3 + length3; - const size_t segmentSize = (dstSize + 3) / 4; - BYTE *const opStart2 = ostart + segmentSize; - BYTE *const opStart3 = opStart2 + segmentSize; - BYTE *const opStart4 = opStart3 + segmentSize; - BYTE *op1 = ostart; - BYTE *op2 = opStart2; - BYTE *op3 = opStart3; - BYTE *op4 = opStart4; - U32 endSignal; - DTableDesc const dtd = HUF_getDTableDesc(DTable); - U32 const dtLog = dtd.tableLog; - - if (length4 > cSrcSize) - return ERROR(corruption_detected); /* overflow */ - { - size_t const errorCode = BIT_initDStream(&bitD1, istart1, length1); - if (HUF_isError(errorCode)) - return errorCode; - } - { - size_t const errorCode = BIT_initDStream(&bitD2, istart2, length2); - if (HUF_isError(errorCode)) - return errorCode; - } - { - size_t const errorCode = BIT_initDStream(&bitD3, istart3, length3); - if (HUF_isError(errorCode)) - return errorCode; - } - { - size_t const errorCode = BIT_initDStream(&bitD4, istart4, length4); - if (HUF_isError(errorCode)) - return errorCode; - } - - /* 16-32 symbols per loop (4-8 symbols per stream) */ - endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4); - for (; (endSignal == BIT_DStream_unfinished) && (op4 < (oend - 7));) { - HUF_DECODE_SYMBOLX2_2(op1, &bitD1); - HUF_DECODE_SYMBOLX2_2(op2, &bitD2); - HUF_DECODE_SYMBOLX2_2(op3, &bitD3); - HUF_DECODE_SYMBOLX2_2(op4, &bitD4); - HUF_DECODE_SYMBOLX2_1(op1, &bitD1); - HUF_DECODE_SYMBOLX2_1(op2, &bitD2); - HUF_DECODE_SYMBOLX2_1(op3, &bitD3); - HUF_DECODE_SYMBOLX2_1(op4, &bitD4); - HUF_DECODE_SYMBOLX2_2(op1, &bitD1); - HUF_DECODE_SYMBOLX2_2(op2, &bitD2); - HUF_DECODE_SYMBOLX2_2(op3, &bitD3); - HUF_DECODE_SYMBOLX2_2(op4, &bitD4); - HUF_DECODE_SYMBOLX2_0(op1, &bitD1); - HUF_DECODE_SYMBOLX2_0(op2, &bitD2); - HUF_DECODE_SYMBOLX2_0(op3, &bitD3); - HUF_DECODE_SYMBOLX2_0(op4, &bitD4); - endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4); - } - - /* check corruption */ - if (op1 > opStart2) - return ERROR(corruption_detected); - if (op2 > opStart3) - return ERROR(corruption_detected); - if (op3 > opStart4) - return ERROR(corruption_detected); - /* note : op4 supposed already verified within main loop */ - - /* finish bitStreams one by one */ - HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog); - HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog); - HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog); - HUF_decodeStreamX2(op4, &bitD4, oend, dt, dtLog); - - /* check */ - endSignal = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); - if (!endSignal) - return ERROR(corruption_detected); - - /* decoded size */ - return dstSize; - } -} - -size_t HUF_decompress4X2_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - DTableDesc dtd = HUF_getDTableDesc(DTable); - if (dtd.tableType != 0) - return ERROR(GENERIC); - return HUF_decompress4X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable); -} - -size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - const BYTE *ip = (const BYTE *)cSrc; - - size_t const hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize, workspace, workspaceSize); - if (HUF_isError(hSize)) - return hSize; - if (hSize >= cSrcSize) - return ERROR(srcSize_wrong); - ip += hSize; - cSrcSize -= hSize; - - return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx); -} - -/* *************************/ -/* double-symbols decoding */ -/* *************************/ -typedef struct { - U16 sequence; - BYTE nbBits; - BYTE length; -} HUF_DEltX4; /* double-symbols decoding */ - -typedef struct { - BYTE symbol; - BYTE weight; -} sortedSymbol_t; - -/* HUF_fillDTableX4Level2() : - * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */ -static void HUF_fillDTableX4Level2(HUF_DEltX4 *DTable, U32 sizeLog, const U32 consumed, const U32 *rankValOrigin, const int minWeight, - const sortedSymbol_t *sortedSymbols, const U32 sortedListSize, U32 nbBitsBaseline, U16 baseSeq) -{ - HUF_DEltX4 DElt; - U32 rankVal[HUF_TABLELOG_MAX + 1]; - - /* get pre-calculated rankVal */ - memcpy(rankVal, rankValOrigin, sizeof(rankVal)); - - /* fill skipped values */ - if (minWeight > 1) { - U32 i, skipSize = rankVal[minWeight]; - ZSTD_writeLE16(&(DElt.sequence), baseSeq); - DElt.nbBits = (BYTE)(consumed); - DElt.length = 1; - for (i = 0; i < skipSize; i++) - DTable[i] = DElt; - } - - /* fill DTable */ - { - U32 s; - for (s = 0; s < sortedListSize; s++) { /* note : sortedSymbols already skipped */ - const U32 symbol = sortedSymbols[s].symbol; - const U32 weight = sortedSymbols[s].weight; - const U32 nbBits = nbBitsBaseline - weight; - const U32 length = 1 << (sizeLog - nbBits); - const U32 start = rankVal[weight]; - U32 i = start; - const U32 end = start + length; - - ZSTD_writeLE16(&(DElt.sequence), (U16)(baseSeq + (symbol << 8))); - DElt.nbBits = (BYTE)(nbBits + consumed); - DElt.length = 2; - do { - DTable[i++] = DElt; - } while (i < end); /* since length >= 1 */ - - rankVal[weight] += length; - } - } -} - -typedef U32 rankVal_t[HUF_TABLELOG_MAX][HUF_TABLELOG_MAX + 1]; -typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1]; - -static void HUF_fillDTableX4(HUF_DEltX4 *DTable, const U32 targetLog, const sortedSymbol_t *sortedList, const U32 sortedListSize, const U32 *rankStart, - rankVal_t rankValOrigin, const U32 maxWeight, const U32 nbBitsBaseline) -{ - U32 rankVal[HUF_TABLELOG_MAX + 1]; - const int scaleLog = nbBitsBaseline - targetLog; /* note : targetLog >= srcLog, hence scaleLog <= 1 */ - const U32 minBits = nbBitsBaseline - maxWeight; - U32 s; - - memcpy(rankVal, rankValOrigin, sizeof(rankVal)); - - /* fill DTable */ - for (s = 0; s < sortedListSize; s++) { - const U16 symbol = sortedList[s].symbol; - const U32 weight = sortedList[s].weight; - const U32 nbBits = nbBitsBaseline - weight; - const U32 start = rankVal[weight]; - const U32 length = 1 << (targetLog - nbBits); - - if (targetLog - nbBits >= minBits) { /* enough room for a second symbol */ - U32 sortedRank; - int minWeight = nbBits + scaleLog; - if (minWeight < 1) - minWeight = 1; - sortedRank = rankStart[minWeight]; - HUF_fillDTableX4Level2(DTable + start, targetLog - nbBits, nbBits, rankValOrigin[nbBits], minWeight, sortedList + sortedRank, - sortedListSize - sortedRank, nbBitsBaseline, symbol); - } else { - HUF_DEltX4 DElt; - ZSTD_writeLE16(&(DElt.sequence), symbol); - DElt.nbBits = (BYTE)(nbBits); - DElt.length = 1; - { - U32 const end = start + length; - U32 u; - for (u = start; u < end; u++) - DTable[u] = DElt; - } - } - rankVal[weight] += length; - } -} - -size_t HUF_readDTableX4_wksp(HUF_DTable *DTable, const void *src, size_t srcSize, void *workspace, size_t workspaceSize) -{ - U32 tableLog, maxW, sizeOfSort, nbSymbols; - DTableDesc dtd = HUF_getDTableDesc(DTable); - U32 const maxTableLog = dtd.maxTableLog; - size_t iSize; - void *dtPtr = DTable + 1; /* force compiler to avoid strict-aliasing */ - HUF_DEltX4 *const dt = (HUF_DEltX4 *)dtPtr; - U32 *rankStart; - - rankValCol_t *rankVal; - U32 *rankStats; - U32 *rankStart0; - sortedSymbol_t *sortedSymbol; - BYTE *weightList; - size_t spaceUsed32 = 0; - - HUF_STATIC_ASSERT((sizeof(rankValCol_t) & 3) == 0); - - rankVal = (rankValCol_t *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2; - rankStats = (U32 *)workspace + spaceUsed32; - spaceUsed32 += HUF_TABLELOG_MAX + 1; - rankStart0 = (U32 *)workspace + spaceUsed32; - spaceUsed32 += HUF_TABLELOG_MAX + 2; - sortedSymbol = (sortedSymbol_t *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2; - weightList = (BYTE *)((U32 *)workspace + spaceUsed32); - spaceUsed32 += ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2; - - if ((spaceUsed32 << 2) > workspaceSize) - return ERROR(tableLog_tooLarge); - workspace = (U32 *)workspace + spaceUsed32; - workspaceSize -= (spaceUsed32 << 2); - - rankStart = rankStart0 + 1; - memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1)); - - HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */ - if (maxTableLog > HUF_TABLELOG_MAX) - return ERROR(tableLog_tooLarge); - /* memset(weightList, 0, sizeof(weightList)); */ /* is not necessary, even though some analyzer complain ... */ - - iSize = HUF_readStats_wksp(weightList, HUF_SYMBOLVALUE_MAX + 1, rankStats, &nbSymbols, &tableLog, src, srcSize, workspace, workspaceSize); - if (HUF_isError(iSize)) - return iSize; - - /* check result */ - if (tableLog > maxTableLog) - return ERROR(tableLog_tooLarge); /* DTable can't fit code depth */ - - /* find maxWeight */ - for (maxW = tableLog; rankStats[maxW] == 0; maxW--) { - } /* necessarily finds a solution before 0 */ - - /* Get start index of each weight */ - { - U32 w, nextRankStart = 0; - for (w = 1; w < maxW + 1; w++) { - U32 curr = nextRankStart; - nextRankStart += rankStats[w]; - rankStart[w] = curr; - } - rankStart[0] = nextRankStart; /* put all 0w symbols at the end of sorted list*/ - sizeOfSort = nextRankStart; - } - - /* sort symbols by weight */ - { - U32 s; - for (s = 0; s < nbSymbols; s++) { - U32 const w = weightList[s]; - U32 const r = rankStart[w]++; - sortedSymbol[r].symbol = (BYTE)s; - sortedSymbol[r].weight = (BYTE)w; - } - rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */ - } - - /* Build rankVal */ - { - U32 *const rankVal0 = rankVal[0]; - { - int const rescale = (maxTableLog - tableLog) - 1; /* tableLog <= maxTableLog */ - U32 nextRankVal = 0; - U32 w; - for (w = 1; w < maxW + 1; w++) { - U32 curr = nextRankVal; - nextRankVal += rankStats[w] << (w + rescale); - rankVal0[w] = curr; - } - } - { - U32 const minBits = tableLog + 1 - maxW; - U32 consumed; - for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) { - U32 *const rankValPtr = rankVal[consumed]; - U32 w; - for (w = 1; w < maxW + 1; w++) { - rankValPtr[w] = rankVal0[w] >> consumed; - } - } - } - } - - HUF_fillDTableX4(dt, maxTableLog, sortedSymbol, sizeOfSort, rankStart0, rankVal, maxW, tableLog + 1); - - dtd.tableLog = (BYTE)maxTableLog; - dtd.tableType = 1; - memcpy(DTable, &dtd, sizeof(dtd)); - return iSize; -} - -static U32 HUF_decodeSymbolX4(void *op, BIT_DStream_t *DStream, const HUF_DEltX4 *dt, const U32 dtLog) -{ - size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */ - memcpy(op, dt + val, 2); - BIT_skipBits(DStream, dt[val].nbBits); - return dt[val].length; -} - -static U32 HUF_decodeLastSymbolX4(void *op, BIT_DStream_t *DStream, const HUF_DEltX4 *dt, const U32 dtLog) -{ - size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */ - memcpy(op, dt + val, 1); - if (dt[val].length == 1) - BIT_skipBits(DStream, dt[val].nbBits); - else { - if (DStream->bitsConsumed < (sizeof(DStream->bitContainer) * 8)) { - BIT_skipBits(DStream, dt[val].nbBits); - if (DStream->bitsConsumed > (sizeof(DStream->bitContainer) * 8)) - /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */ - DStream->bitsConsumed = (sizeof(DStream->bitContainer) * 8); - } - } - return 1; -} - -#define HUF_DECODE_SYMBOLX4_0(ptr, DStreamPtr) ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog) - -#define HUF_DECODE_SYMBOLX4_1(ptr, DStreamPtr) \ - if (ZSTD_64bits() || (HUF_TABLELOG_MAX <= 12)) \ - ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog) - -#define HUF_DECODE_SYMBOLX4_2(ptr, DStreamPtr) \ - if (ZSTD_64bits()) \ - ptr += HUF_decodeSymbolX4(ptr, DStreamPtr, dt, dtLog) - -FORCE_INLINE size_t HUF_decodeStreamX4(BYTE *p, BIT_DStream_t *bitDPtr, BYTE *const pEnd, const HUF_DEltX4 *const dt, const U32 dtLog) -{ - BYTE *const pStart = p; - - /* up to 8 symbols at a time */ - while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd - (sizeof(bitDPtr->bitContainer) - 1))) { - HUF_DECODE_SYMBOLX4_2(p, bitDPtr); - HUF_DECODE_SYMBOLX4_1(p, bitDPtr); - HUF_DECODE_SYMBOLX4_2(p, bitDPtr); - HUF_DECODE_SYMBOLX4_0(p, bitDPtr); - } - - /* closer to end : up to 2 symbols at a time */ - while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd - 2)) - HUF_DECODE_SYMBOLX4_0(p, bitDPtr); - - while (p <= pEnd - 2) - HUF_DECODE_SYMBOLX4_0(p, bitDPtr); /* no need to reload : reached the end of DStream */ - - if (p < pEnd) - p += HUF_decodeLastSymbolX4(p, bitDPtr, dt, dtLog); - - return p - pStart; -} - -static size_t HUF_decompress1X4_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - BIT_DStream_t bitD; - - /* Init */ - { - size_t const errorCode = BIT_initDStream(&bitD, cSrc, cSrcSize); - if (HUF_isError(errorCode)) - return errorCode; - } - - /* decode */ - { - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstSize; - const void *const dtPtr = DTable + 1; /* force compiler to not use strict-aliasing */ - const HUF_DEltX4 *const dt = (const HUF_DEltX4 *)dtPtr; - DTableDesc const dtd = HUF_getDTableDesc(DTable); - HUF_decodeStreamX4(ostart, &bitD, oend, dt, dtd.tableLog); - } - - /* check */ - if (!BIT_endOfDStream(&bitD)) - return ERROR(corruption_detected); - - /* decoded size */ - return dstSize; -} - -size_t HUF_decompress1X4_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - DTableDesc dtd = HUF_getDTableDesc(DTable); - if (dtd.tableType != 1) - return ERROR(GENERIC); - return HUF_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable); -} - -size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable *DCtx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - const BYTE *ip = (const BYTE *)cSrc; - - size_t const hSize = HUF_readDTableX4_wksp(DCtx, cSrc, cSrcSize, workspace, workspaceSize); - if (HUF_isError(hSize)) - return hSize; - if (hSize >= cSrcSize) - return ERROR(srcSize_wrong); - ip += hSize; - cSrcSize -= hSize; - - return HUF_decompress1X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx); -} - -static size_t HUF_decompress4X4_usingDTable_internal(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - if (cSrcSize < 10) - return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */ - - { - const BYTE *const istart = (const BYTE *)cSrc; - BYTE *const ostart = (BYTE *)dst; - BYTE *const oend = ostart + dstSize; - const void *const dtPtr = DTable + 1; - const HUF_DEltX4 *const dt = (const HUF_DEltX4 *)dtPtr; - - /* Init */ - BIT_DStream_t bitD1; - BIT_DStream_t bitD2; - BIT_DStream_t bitD3; - BIT_DStream_t bitD4; - size_t const length1 = ZSTD_readLE16(istart); - size_t const length2 = ZSTD_readLE16(istart + 2); - size_t const length3 = ZSTD_readLE16(istart + 4); - size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6); - const BYTE *const istart1 = istart + 6; /* jumpTable */ - const BYTE *const istart2 = istart1 + length1; - const BYTE *const istart3 = istart2 + length2; - const BYTE *const istart4 = istart3 + length3; - size_t const segmentSize = (dstSize + 3) / 4; - BYTE *const opStart2 = ostart + segmentSize; - BYTE *const opStart3 = opStart2 + segmentSize; - BYTE *const opStart4 = opStart3 + segmentSize; - BYTE *op1 = ostart; - BYTE *op2 = opStart2; - BYTE *op3 = opStart3; - BYTE *op4 = opStart4; - U32 endSignal; - DTableDesc const dtd = HUF_getDTableDesc(DTable); - U32 const dtLog = dtd.tableLog; - - if (length4 > cSrcSize) - return ERROR(corruption_detected); /* overflow */ - { - size_t const errorCode = BIT_initDStream(&bitD1, istart1, length1); - if (HUF_isError(errorCode)) - return errorCode; - } - { - size_t const errorCode = BIT_initDStream(&bitD2, istart2, length2); - if (HUF_isError(errorCode)) - return errorCode; - } - { - size_t const errorCode = BIT_initDStream(&bitD3, istart3, length3); - if (HUF_isError(errorCode)) - return errorCode; - } - { - size_t const errorCode = BIT_initDStream(&bitD4, istart4, length4); - if (HUF_isError(errorCode)) - return errorCode; - } - - /* 16-32 symbols per loop (4-8 symbols per stream) */ - endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4); - for (; (endSignal == BIT_DStream_unfinished) & (op4 < (oend - (sizeof(bitD4.bitContainer) - 1)));) { - HUF_DECODE_SYMBOLX4_2(op1, &bitD1); - HUF_DECODE_SYMBOLX4_2(op2, &bitD2); - HUF_DECODE_SYMBOLX4_2(op3, &bitD3); - HUF_DECODE_SYMBOLX4_2(op4, &bitD4); - HUF_DECODE_SYMBOLX4_1(op1, &bitD1); - HUF_DECODE_SYMBOLX4_1(op2, &bitD2); - HUF_DECODE_SYMBOLX4_1(op3, &bitD3); - HUF_DECODE_SYMBOLX4_1(op4, &bitD4); - HUF_DECODE_SYMBOLX4_2(op1, &bitD1); - HUF_DECODE_SYMBOLX4_2(op2, &bitD2); - HUF_DECODE_SYMBOLX4_2(op3, &bitD3); - HUF_DECODE_SYMBOLX4_2(op4, &bitD4); - HUF_DECODE_SYMBOLX4_0(op1, &bitD1); - HUF_DECODE_SYMBOLX4_0(op2, &bitD2); - HUF_DECODE_SYMBOLX4_0(op3, &bitD3); - HUF_DECODE_SYMBOLX4_0(op4, &bitD4); - - endSignal = BIT_reloadDStream(&bitD1) | BIT_reloadDStream(&bitD2) | BIT_reloadDStream(&bitD3) | BIT_reloadDStream(&bitD4); - } - - /* check corruption */ - if (op1 > opStart2) - return ERROR(corruption_detected); - if (op2 > opStart3) - return ERROR(corruption_detected); - if (op3 > opStart4) - return ERROR(corruption_detected); - /* note : op4 already verified within main loop */ - - /* finish bitStreams one by one */ - HUF_decodeStreamX4(op1, &bitD1, opStart2, dt, dtLog); - HUF_decodeStreamX4(op2, &bitD2, opStart3, dt, dtLog); - HUF_decodeStreamX4(op3, &bitD3, opStart4, dt, dtLog); - HUF_decodeStreamX4(op4, &bitD4, oend, dt, dtLog); - - /* check */ - { - U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); - if (!endCheck) - return ERROR(corruption_detected); - } - - /* decoded size */ - return dstSize; - } -} - -size_t HUF_decompress4X4_usingDTable(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - DTableDesc dtd = HUF_getDTableDesc(DTable); - if (dtd.tableType != 1) - return ERROR(GENERIC); - return HUF_decompress4X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable); -} - -size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - const BYTE *ip = (const BYTE *)cSrc; - - size_t hSize = HUF_readDTableX4_wksp(dctx, cSrc, cSrcSize, workspace, workspaceSize); - if (HUF_isError(hSize)) - return hSize; - if (hSize >= cSrcSize) - return ERROR(srcSize_wrong); - ip += hSize; - cSrcSize -= hSize; - - return HUF_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx); -} - -/* ********************************/ -/* Generic decompression selector */ -/* ********************************/ - -size_t HUF_decompress1X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - DTableDesc const dtd = HUF_getDTableDesc(DTable); - return dtd.tableType ? HUF_decompress1X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable) - : HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable); -} - -size_t HUF_decompress4X_usingDTable(void *dst, size_t maxDstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable) -{ - DTableDesc const dtd = HUF_getDTableDesc(DTable); - return dtd.tableType ? HUF_decompress4X4_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable) - : HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable); -} - -typedef struct { - U32 tableTime; - U32 decode256Time; -} algo_time_t; -static const algo_time_t algoTime[16 /* Quantization */][3 /* single, double, quad */] = { - /* single, double, quad */ - {{0, 0}, {1, 1}, {2, 2}}, /* Q==0 : impossible */ - {{0, 0}, {1, 1}, {2, 2}}, /* Q==1 : impossible */ - {{38, 130}, {1313, 74}, {2151, 38}}, /* Q == 2 : 12-18% */ - {{448, 128}, {1353, 74}, {2238, 41}}, /* Q == 3 : 18-25% */ - {{556, 128}, {1353, 74}, {2238, 47}}, /* Q == 4 : 25-32% */ - {{714, 128}, {1418, 74}, {2436, 53}}, /* Q == 5 : 32-38% */ - {{883, 128}, {1437, 74}, {2464, 61}}, /* Q == 6 : 38-44% */ - {{897, 128}, {1515, 75}, {2622, 68}}, /* Q == 7 : 44-50% */ - {{926, 128}, {1613, 75}, {2730, 75}}, /* Q == 8 : 50-56% */ - {{947, 128}, {1729, 77}, {3359, 77}}, /* Q == 9 : 56-62% */ - {{1107, 128}, {2083, 81}, {4006, 84}}, /* Q ==10 : 62-69% */ - {{1177, 128}, {2379, 87}, {4785, 88}}, /* Q ==11 : 69-75% */ - {{1242, 128}, {2415, 93}, {5155, 84}}, /* Q ==12 : 75-81% */ - {{1349, 128}, {2644, 106}, {5260, 106}}, /* Q ==13 : 81-87% */ - {{1455, 128}, {2422, 124}, {4174, 124}}, /* Q ==14 : 87-93% */ - {{722, 128}, {1891, 145}, {1936, 146}}, /* Q ==15 : 93-99% */ -}; - -/** HUF_selectDecoder() : -* Tells which decoder is likely to decode faster, -* based on a set of pre-determined metrics. -* @return : 0==HUF_decompress4X2, 1==HUF_decompress4X4 . -* Assumption : 0 < cSrcSize < dstSize <= 128 KB */ -U32 HUF_selectDecoder(size_t dstSize, size_t cSrcSize) -{ - /* decoder timing evaluation */ - U32 const Q = (U32)(cSrcSize * 16 / dstSize); /* Q < 16 since dstSize > cSrcSize */ - U32 const D256 = (U32)(dstSize >> 8); - U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256); - U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256); - DTime1 += DTime1 >> 3; /* advantage to algorithm using less memory, for cache eviction */ - - return DTime1 < DTime0; -} - -typedef size_t (*decompressionAlgo)(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize); - -size_t HUF_decompress4X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - /* validation checks */ - if (dstSize == 0) - return ERROR(dstSize_tooSmall); - if (cSrcSize > dstSize) - return ERROR(corruption_detected); /* invalid */ - if (cSrcSize == dstSize) { - memcpy(dst, cSrc, dstSize); - return dstSize; - } /* not compressed */ - if (cSrcSize == 1) { - memset(dst, *(const BYTE *)cSrc, dstSize); - return dstSize; - } /* RLE */ - - { - U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); - return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize) - : HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize); - } -} - -size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - /* validation checks */ - if (dstSize == 0) - return ERROR(dstSize_tooSmall); - if ((cSrcSize >= dstSize) || (cSrcSize <= 1)) - return ERROR(corruption_detected); /* invalid */ - - { - U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); - return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize) - : HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize); - } -} - -size_t HUF_decompress1X_DCtx_wksp(HUF_DTable *dctx, void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, void *workspace, size_t workspaceSize) -{ - /* validation checks */ - if (dstSize == 0) - return ERROR(dstSize_tooSmall); - if (cSrcSize > dstSize) - return ERROR(corruption_detected); /* invalid */ - if (cSrcSize == dstSize) { - memcpy(dst, cSrc, dstSize); - return dstSize; - } /* not compressed */ - if (cSrcSize == 1) { - memset(dst, *(const BYTE *)cSrc, dstSize); - return dstSize; - } /* RLE */ - - { - U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); - return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize) - : HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workspace, workspaceSize); - } -} diff --git a/lib/zstd/mem.h b/lib/zstd/mem.h deleted file mode 100644 index 93d7a2c377fe..000000000000 --- a/lib/zstd/mem.h +++ /dev/null @@ -1,151 +0,0 @@ -/** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -#ifndef MEM_H_MODULE -#define MEM_H_MODULE - -/*-**************************************** -* Dependencies -******************************************/ -#include -#include /* memcpy */ -#include /* size_t, ptrdiff_t */ - -/*-**************************************** -* Compiler specifics -******************************************/ -#define ZSTD_STATIC static inline - -/*-************************************************************** -* Basic Types -*****************************************************************/ -typedef uint8_t BYTE; -typedef uint16_t U16; -typedef int16_t S16; -typedef uint32_t U32; -typedef int32_t S32; -typedef uint64_t U64; -typedef int64_t S64; -typedef ptrdiff_t iPtrDiff; -typedef uintptr_t uPtrDiff; - -/*-************************************************************** -* Memory I/O -*****************************************************************/ -ZSTD_STATIC unsigned ZSTD_32bits(void) { return sizeof(size_t) == 4; } -ZSTD_STATIC unsigned ZSTD_64bits(void) { return sizeof(size_t) == 8; } - -#if defined(__LITTLE_ENDIAN) -#define ZSTD_LITTLE_ENDIAN 1 -#else -#define ZSTD_LITTLE_ENDIAN 0 -#endif - -ZSTD_STATIC unsigned ZSTD_isLittleEndian(void) { return ZSTD_LITTLE_ENDIAN; } - -ZSTD_STATIC U16 ZSTD_read16(const void *memPtr) { return get_unaligned((const U16 *)memPtr); } - -ZSTD_STATIC U32 ZSTD_read32(const void *memPtr) { return get_unaligned((const U32 *)memPtr); } - -ZSTD_STATIC U64 ZSTD_read64(const void *memPtr) { return get_unaligned((const U64 *)memPtr); } - -ZSTD_STATIC size_t ZSTD_readST(const void *memPtr) { return get_unaligned((const size_t *)memPtr); } - -ZSTD_STATIC void ZSTD_write16(void *memPtr, U16 value) { put_unaligned(value, (U16 *)memPtr); } - -ZSTD_STATIC void ZSTD_write32(void *memPtr, U32 value) { put_unaligned(value, (U32 *)memPtr); } - -ZSTD_STATIC void ZSTD_write64(void *memPtr, U64 value) { put_unaligned(value, (U64 *)memPtr); } - -/*=== Little endian r/w ===*/ - -ZSTD_STATIC U16 ZSTD_readLE16(const void *memPtr) { return get_unaligned_le16(memPtr); } - -ZSTD_STATIC void ZSTD_writeLE16(void *memPtr, U16 val) { put_unaligned_le16(val, memPtr); } - -ZSTD_STATIC U32 ZSTD_readLE24(const void *memPtr) { return ZSTD_readLE16(memPtr) + (((const BYTE *)memPtr)[2] << 16); } - -ZSTD_STATIC void ZSTD_writeLE24(void *memPtr, U32 val) -{ - ZSTD_writeLE16(memPtr, (U16)val); - ((BYTE *)memPtr)[2] = (BYTE)(val >> 16); -} - -ZSTD_STATIC U32 ZSTD_readLE32(const void *memPtr) { return get_unaligned_le32(memPtr); } - -ZSTD_STATIC void ZSTD_writeLE32(void *memPtr, U32 val32) { put_unaligned_le32(val32, memPtr); } - -ZSTD_STATIC U64 ZSTD_readLE64(const void *memPtr) { return get_unaligned_le64(memPtr); } - -ZSTD_STATIC void ZSTD_writeLE64(void *memPtr, U64 val64) { put_unaligned_le64(val64, memPtr); } - -ZSTD_STATIC size_t ZSTD_readLEST(const void *memPtr) -{ - if (ZSTD_32bits()) - return (size_t)ZSTD_readLE32(memPtr); - else - return (size_t)ZSTD_readLE64(memPtr); -} - -ZSTD_STATIC void ZSTD_writeLEST(void *memPtr, size_t val) -{ - if (ZSTD_32bits()) - ZSTD_writeLE32(memPtr, (U32)val); - else - ZSTD_writeLE64(memPtr, (U64)val); -} - -/*=== Big endian r/w ===*/ - -ZSTD_STATIC U32 ZSTD_readBE32(const void *memPtr) { return get_unaligned_be32(memPtr); } - -ZSTD_STATIC void ZSTD_writeBE32(void *memPtr, U32 val32) { put_unaligned_be32(val32, memPtr); } - -ZSTD_STATIC U64 ZSTD_readBE64(const void *memPtr) { return get_unaligned_be64(memPtr); } - -ZSTD_STATIC void ZSTD_writeBE64(void *memPtr, U64 val64) { put_unaligned_be64(val64, memPtr); } - -ZSTD_STATIC size_t ZSTD_readBEST(const void *memPtr) -{ - if (ZSTD_32bits()) - return (size_t)ZSTD_readBE32(memPtr); - else - return (size_t)ZSTD_readBE64(memPtr); -} - -ZSTD_STATIC void ZSTD_writeBEST(void *memPtr, size_t val) -{ - if (ZSTD_32bits()) - ZSTD_writeBE32(memPtr, (U32)val); - else - ZSTD_writeBE64(memPtr, (U64)val); -} - -/* function safe only for comparisons */ -ZSTD_STATIC U32 ZSTD_readMINMATCH(const void *memPtr, U32 length) -{ - switch (length) { - default: - case 4: return ZSTD_read32(memPtr); - case 3: - if (ZSTD_isLittleEndian()) - return ZSTD_read32(memPtr) << 8; - else - return ZSTD_read32(memPtr) >> 8; - } -} - -#endif /* MEM_H_MODULE */ diff --git a/lib/zstd/zstd_common.c b/lib/zstd/zstd_common.c deleted file mode 100644 index a282624ee155..000000000000 --- a/lib/zstd/zstd_common.c +++ /dev/null @@ -1,75 +0,0 @@ -/** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -/*-************************************* -* Dependencies -***************************************/ -#include "error_private.h" -#include "zstd_internal.h" /* declaration of ZSTD_isError, ZSTD_getErrorName, ZSTD_getErrorCode, ZSTD_getErrorString, ZSTD_versionNumber */ -#include - -/*=************************************************************** -* Custom allocator -****************************************************************/ - -#define stack_push(stack, size) \ - ({ \ - void *const ptr = ZSTD_PTR_ALIGN((stack)->ptr); \ - (stack)->ptr = (char *)ptr + (size); \ - (stack)->ptr <= (stack)->end ? ptr : NULL; \ - }) - -ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize) -{ - ZSTD_customMem stackMem = {ZSTD_stackAlloc, ZSTD_stackFree, workspace}; - ZSTD_stack *stack = (ZSTD_stack *)workspace; - /* Verify preconditions */ - if (!workspace || workspaceSize < sizeof(ZSTD_stack) || workspace != ZSTD_PTR_ALIGN(workspace)) { - ZSTD_customMem error = {NULL, NULL, NULL}; - return error; - } - /* Initialize the stack */ - stack->ptr = workspace; - stack->end = (char *)workspace + workspaceSize; - stack_push(stack, sizeof(ZSTD_stack)); - return stackMem; -} - -void *ZSTD_stackAllocAll(void *opaque, size_t *size) -{ - ZSTD_stack *stack = (ZSTD_stack *)opaque; - *size = (BYTE const *)stack->end - (BYTE *)ZSTD_PTR_ALIGN(stack->ptr); - return stack_push(stack, *size); -} - -void *ZSTD_stackAlloc(void *opaque, size_t size) -{ - ZSTD_stack *stack = (ZSTD_stack *)opaque; - return stack_push(stack, size); -} -void ZSTD_stackFree(void *opaque, void *address) -{ - (void)opaque; - (void)address; -} - -void *ZSTD_malloc(size_t size, ZSTD_customMem customMem) { return customMem.customAlloc(customMem.opaque, size); } - -void ZSTD_free(void *ptr, ZSTD_customMem customMem) -{ - if (ptr != NULL) - customMem.customFree(customMem.opaque, ptr); -} diff --git a/lib/zstd/zstd_compress_module.c b/lib/zstd/zstd_compress_module.c new file mode 100644 index 000000000000..65548a4bb934 --- /dev/null +++ b/lib/zstd/zstd_compress_module.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause +/* + * Copyright (c) Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include +#include +#include +#include + +#include "common/zstd_deps.h" +#include "common/zstd_internal.h" + +#define ZSTD_FORWARD_IF_ERR(ret) \ + do { \ + size_t const __ret = (ret); \ + if (ZSTD_isError(__ret)) \ + return __ret; \ + } while (0) + +static size_t zstd_cctx_init(zstd_cctx *cctx, const zstd_parameters *parameters, + unsigned long long pledged_src_size) +{ + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_reset( + cctx, ZSTD_reset_session_and_parameters)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setPledgedSrcSize( + cctx, pledged_src_size)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_windowLog, parameters->cParams.windowLog)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_hashLog, parameters->cParams.hashLog)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_chainLog, parameters->cParams.chainLog)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_searchLog, parameters->cParams.searchLog)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_minMatch, parameters->cParams.minMatch)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_targetLength, parameters->cParams.targetLength)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_strategy, parameters->cParams.strategy)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_contentSizeFlag, parameters->fParams.contentSizeFlag)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_checksumFlag, parameters->fParams.checksumFlag)); + ZSTD_FORWARD_IF_ERR(ZSTD_CCtx_setParameter( + cctx, ZSTD_c_dictIDFlag, !parameters->fParams.noDictIDFlag)); + return 0; +} + +int zstd_min_clevel(void) +{ + return ZSTD_minCLevel(); +} +EXPORT_SYMBOL(zstd_min_clevel); + +int zstd_max_clevel(void) +{ + return ZSTD_maxCLevel(); +} +EXPORT_SYMBOL(zstd_max_clevel); + +size_t zstd_compress_bound(size_t src_size) +{ + return ZSTD_compressBound(src_size); +} +EXPORT_SYMBOL(zstd_compress_bound); + +zstd_parameters zstd_get_params(int level, + unsigned long long estimated_src_size) +{ + return ZSTD_getParams(level, estimated_src_size, 0); +} +EXPORT_SYMBOL(zstd_get_params); + +size_t zstd_cctx_workspace_bound(const zstd_compression_parameters *cparams) +{ + return ZSTD_estimateCCtxSize_usingCParams(*cparams); +} +EXPORT_SYMBOL(zstd_cctx_workspace_bound); + +zstd_cctx *zstd_init_cctx(void *workspace, size_t workspace_size) +{ + if (workspace == NULL) + return NULL; + return ZSTD_initStaticCCtx(workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_cctx); + +size_t zstd_compress_cctx(zstd_cctx *cctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size, const zstd_parameters *parameters) +{ + ZSTD_FORWARD_IF_ERR(zstd_cctx_init(cctx, parameters, src_size)); + return ZSTD_compress2(cctx, dst, dst_capacity, src, src_size); +} +EXPORT_SYMBOL(zstd_compress_cctx); + +size_t zstd_cstream_workspace_bound(const zstd_compression_parameters *cparams) +{ + return ZSTD_estimateCStreamSize_usingCParams(*cparams); +} +EXPORT_SYMBOL(zstd_cstream_workspace_bound); + +zstd_cstream *zstd_init_cstream(const zstd_parameters *parameters, + unsigned long long pledged_src_size, void *workspace, size_t workspace_size) +{ + zstd_cstream *cstream; + + if (workspace == NULL) + return NULL; + + cstream = ZSTD_initStaticCStream(workspace, workspace_size); + if (cstream == NULL) + return NULL; + + /* 0 means unknown in linux zstd API but means 0 in new zstd API */ + if (pledged_src_size == 0) + pledged_src_size = ZSTD_CONTENTSIZE_UNKNOWN; + + if (ZSTD_isError(zstd_cctx_init(cstream, parameters, pledged_src_size))) + return NULL; + + return cstream; +} +EXPORT_SYMBOL(zstd_init_cstream); + +size_t zstd_reset_cstream(zstd_cstream *cstream, + unsigned long long pledged_src_size) +{ + return ZSTD_resetCStream(cstream, pledged_src_size); +} +EXPORT_SYMBOL(zstd_reset_cstream); + +size_t zstd_compress_stream(zstd_cstream *cstream, zstd_out_buffer *output, + zstd_in_buffer *input) +{ + return ZSTD_compressStream(cstream, output, input); +} +EXPORT_SYMBOL(zstd_compress_stream); + +size_t zstd_flush_stream(zstd_cstream *cstream, zstd_out_buffer *output) +{ + return ZSTD_flushStream(cstream, output); +} +EXPORT_SYMBOL(zstd_flush_stream); + +size_t zstd_end_stream(zstd_cstream *cstream, zstd_out_buffer *output) +{ + return ZSTD_endStream(cstream, output); +} +EXPORT_SYMBOL(zstd_end_stream); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("Zstd Compressor"); diff --git a/lib/zstd/zstd_decompress_module.c b/lib/zstd/zstd_decompress_module.c new file mode 100644 index 000000000000..f4ed952ed485 --- /dev/null +++ b/lib/zstd/zstd_decompress_module.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause +/* + * Copyright (c) Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under both the BSD-style license (found in the + * LICENSE file in the root directory of this source tree) and the GPLv2 (found + * in the COPYING file in the root directory of this source tree). + * You may select, at your option, one of the above-listed licenses. + */ + +#include +#include +#include +#include + +#include "common/zstd_deps.h" + +/* Common symbols. zstd_compress must depend on zstd_decompress. */ + +unsigned int zstd_is_error(size_t code) +{ + return ZSTD_isError(code); +} +EXPORT_SYMBOL(zstd_is_error); + +zstd_error_code zstd_get_error_code(size_t code) +{ + return ZSTD_getErrorCode(code); +} +EXPORT_SYMBOL(zstd_get_error_code); + +const char *zstd_get_error_name(size_t code) +{ + return ZSTD_getErrorName(code); +} +EXPORT_SYMBOL(zstd_get_error_name); + +/* Decompression symbols. */ + +size_t zstd_dctx_workspace_bound(void) +{ + return ZSTD_estimateDCtxSize(); +} +EXPORT_SYMBOL(zstd_dctx_workspace_bound); + +zstd_dctx *zstd_init_dctx(void *workspace, size_t workspace_size) +{ + if (workspace == NULL) + return NULL; + return ZSTD_initStaticDCtx(workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_dctx); + +size_t zstd_decompress_dctx(zstd_dctx *dctx, void *dst, size_t dst_capacity, + const void *src, size_t src_size) +{ + return ZSTD_decompressDCtx(dctx, dst, dst_capacity, src, src_size); +} +EXPORT_SYMBOL(zstd_decompress_dctx); + +size_t zstd_dstream_workspace_bound(size_t max_window_size) +{ + return ZSTD_estimateDStreamSize(max_window_size); +} +EXPORT_SYMBOL(zstd_dstream_workspace_bound); + +zstd_dstream *zstd_init_dstream(size_t max_window_size, void *workspace, + size_t workspace_size) +{ + if (workspace == NULL) + return NULL; + (void)max_window_size; + return ZSTD_initStaticDStream(workspace, workspace_size); +} +EXPORT_SYMBOL(zstd_init_dstream); + +size_t zstd_reset_dstream(zstd_dstream *dstream) +{ + return ZSTD_resetDStream(dstream); +} +EXPORT_SYMBOL(zstd_reset_dstream); + +size_t zstd_decompress_stream(zstd_dstream *dstream, zstd_out_buffer *output, + zstd_in_buffer *input) +{ + return ZSTD_decompressStream(dstream, output, input); +} +EXPORT_SYMBOL(zstd_decompress_stream); + +size_t zstd_find_frame_compressed_size(const void *src, size_t src_size) +{ + return ZSTD_findFrameCompressedSize(src, src_size); +} +EXPORT_SYMBOL(zstd_find_frame_compressed_size); + +size_t zstd_get_frame_header(zstd_frame_header *header, const void *src, + size_t src_size) +{ + return ZSTD_getFrameHeader(header, src, src_size); +} +EXPORT_SYMBOL(zstd_get_frame_header); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("Zstd Decompressor"); diff --git a/lib/zstd/zstd_internal.h b/lib/zstd/zstd_internal.h deleted file mode 100644 index dac753397f86..000000000000 --- a/lib/zstd/zstd_internal.h +++ /dev/null @@ -1,273 +0,0 @@ -/** - * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -#ifndef ZSTD_CCOMMON_H_MODULE -#define ZSTD_CCOMMON_H_MODULE - -/*-******************************************************* -* Compiler specifics -*********************************************************/ -#define FORCE_INLINE static __always_inline -#define FORCE_NOINLINE static noinline - -/*-************************************* -* Dependencies -***************************************/ -#include "error_private.h" -#include "mem.h" -#include -#include -#include -#include - -/*-************************************* -* shared macros -***************************************/ -#define MIN(a, b) ((a) < (b) ? (a) : (b)) -#define MAX(a, b) ((a) > (b) ? (a) : (b)) -#define CHECK_F(f) \ - { \ - size_t const errcod = f; \ - if (ERR_isError(errcod)) \ - return errcod; \ - } /* check and Forward error code */ -#define CHECK_E(f, e) \ - { \ - size_t const errcod = f; \ - if (ERR_isError(errcod)) \ - return ERROR(e); \ - } /* check and send Error code */ -#define ZSTD_STATIC_ASSERT(c) \ - { \ - enum { ZSTD_static_assert = 1 / (int)(!!(c)) }; \ - } - -/*-************************************* -* Common constants -***************************************/ -#define ZSTD_OPT_NUM (1 << 12) -#define ZSTD_DICT_MAGIC 0xEC30A437 /* v0.7+ */ - -#define ZSTD_REP_NUM 3 /* number of repcodes */ -#define ZSTD_REP_CHECK (ZSTD_REP_NUM) /* number of repcodes to check by the optimal parser */ -#define ZSTD_REP_MOVE (ZSTD_REP_NUM - 1) -#define ZSTD_REP_MOVE_OPT (ZSTD_REP_NUM) -static const U32 repStartValue[ZSTD_REP_NUM] = {1, 4, 8}; - -#define KB *(1 << 10) -#define MB *(1 << 20) -#define GB *(1U << 30) - -#define BIT7 128 -#define BIT6 64 -#define BIT5 32 -#define BIT4 16 -#define BIT1 2 -#define BIT0 1 - -#define ZSTD_WINDOWLOG_ABSOLUTEMIN 10 -static const size_t ZSTD_fcs_fieldSize[4] = {0, 2, 4, 8}; -static const size_t ZSTD_did_fieldSize[4] = {0, 1, 2, 4}; - -#define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */ -static const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE; -typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e; - -#define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */ -#define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */) /* for a non-null block */ - -#define HufLog 12 -typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e; - -#define LONGNBSEQ 0x7F00 - -#define MINMATCH 3 -#define EQUAL_READ32 4 - -#define Litbits 8 -#define MaxLit ((1 << Litbits) - 1) -#define MaxML 52 -#define MaxLL 35 -#define MaxOff 28 -#define MaxSeq MAX(MaxLL, MaxML) /* Assumption : MaxOff < MaxLL,MaxML */ -#define MLFSELog 9 -#define LLFSELog 9 -#define OffFSELog 8 - -static const U32 LL_bits[MaxLL + 1] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}; -static const S16 LL_defaultNorm[MaxLL + 1] = {4, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 2, 1, 1, 1, 1, 1, -1, -1, -1, -1}; -#define LL_DEFAULTNORMLOG 6 /* for static allocation */ -static const U32 LL_defaultNormLog = LL_DEFAULTNORMLOG; - -static const U32 ML_bits[MaxML + 1] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 3, 4, 4, 5, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16}; -static const S16 ML_defaultNorm[MaxML + 1] = {1, 4, 3, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, - 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1, -1, -1}; -#define ML_DEFAULTNORMLOG 6 /* for static allocation */ -static const U32 ML_defaultNormLog = ML_DEFAULTNORMLOG; - -static const S16 OF_defaultNorm[MaxOff + 1] = {1, 1, 1, 1, 1, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1}; -#define OF_DEFAULTNORMLOG 5 /* for static allocation */ -static const U32 OF_defaultNormLog = OF_DEFAULTNORMLOG; - -/*-******************************************* -* Shared functions to include for inlining -*********************************************/ -ZSTD_STATIC void ZSTD_copy8(void *dst, const void *src) { - /* - * zstd relies heavily on gcc being able to analyze and inline this - * memcpy() call, since it is called in a tight loop. Preboot mode - * is compiled in freestanding mode, which stops gcc from analyzing - * memcpy(). Use __builtin_memcpy() to tell gcc to analyze this as a - * regular memcpy(). - */ - __builtin_memcpy(dst, src, 8); -} -/*! ZSTD_wildcopy() : -* custom version of memcpy(), can copy up to 7 bytes too many (8 bytes if length==0) */ -#define WILDCOPY_OVERLENGTH 8 -ZSTD_STATIC void ZSTD_wildcopy(void *dst, const void *src, ptrdiff_t length) -{ - const BYTE* ip = (const BYTE*)src; - BYTE* op = (BYTE*)dst; - BYTE* const oend = op + length; -#if defined(GCC_VERSION) && GCC_VERSION >= 70000 && GCC_VERSION < 70200 - /* - * Work around https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81388. - * Avoid the bad case where the loop only runs once by handling the - * special case separately. This doesn't trigger the bug because it - * doesn't involve pointer/integer overflow. - */ - if (length <= 8) - return ZSTD_copy8(dst, src); -#endif - do { - ZSTD_copy8(op, ip); - op += 8; - ip += 8; - } while (op < oend); -} - -/*-******************************************* -* Private interfaces -*********************************************/ -typedef struct ZSTD_stats_s ZSTD_stats_t; - -typedef struct { - U32 off; - U32 len; -} ZSTD_match_t; - -typedef struct { - U32 price; - U32 off; - U32 mlen; - U32 litlen; - U32 rep[ZSTD_REP_NUM]; -} ZSTD_optimal_t; - -typedef struct seqDef_s { - U32 offset; - U16 litLength; - U16 matchLength; -} seqDef; - -typedef struct { - seqDef *sequencesStart; - seqDef *sequences; - BYTE *litStart; - BYTE *lit; - BYTE *llCode; - BYTE *mlCode; - BYTE *ofCode; - U32 longLengthID; /* 0 == no longLength; 1 == Lit.longLength; 2 == Match.longLength; */ - U32 longLengthPos; - /* opt */ - ZSTD_optimal_t *priceTable; - ZSTD_match_t *matchTable; - U32 *matchLengthFreq; - U32 *litLengthFreq; - U32 *litFreq; - U32 *offCodeFreq; - U32 matchLengthSum; - U32 matchSum; - U32 litLengthSum; - U32 litSum; - U32 offCodeSum; - U32 log2matchLengthSum; - U32 log2matchSum; - U32 log2litLengthSum; - U32 log2litSum; - U32 log2offCodeSum; - U32 factor; - U32 staticPrices; - U32 cachedPrice; - U32 cachedLitLength; - const BYTE *cachedLiterals; -} seqStore_t; - -const seqStore_t *ZSTD_getSeqStore(const ZSTD_CCtx *ctx); -void ZSTD_seqToCodes(const seqStore_t *seqStorePtr); -int ZSTD_isSkipFrame(ZSTD_DCtx *dctx); - -/*= Custom memory allocation functions */ -typedef void *(*ZSTD_allocFunction)(void *opaque, size_t size); -typedef void (*ZSTD_freeFunction)(void *opaque, void *address); -typedef struct { - ZSTD_allocFunction customAlloc; - ZSTD_freeFunction customFree; - void *opaque; -} ZSTD_customMem; - -void *ZSTD_malloc(size_t size, ZSTD_customMem customMem); -void ZSTD_free(void *ptr, ZSTD_customMem customMem); - -/*====== stack allocation ======*/ - -typedef struct { - void *ptr; - const void *end; -} ZSTD_stack; - -#define ZSTD_ALIGN(x) ALIGN(x, sizeof(size_t)) -#define ZSTD_PTR_ALIGN(p) PTR_ALIGN(p, sizeof(size_t)) - -ZSTD_customMem ZSTD_initStack(void *workspace, size_t workspaceSize); - -void *ZSTD_stackAllocAll(void *opaque, size_t *size); -void *ZSTD_stackAlloc(void *opaque, size_t size); -void ZSTD_stackFree(void *opaque, void *address); - -/*====== common function ======*/ - -ZSTD_STATIC U32 ZSTD_highbit32(U32 val) { return 31 - __builtin_clz(val); } - -/* hidden functions */ - -/* ZSTD_invalidateRepCodes() : - * ensures next compression will not use repcodes from previous block. - * Note : only works with regular variant; - * do not use with extDict variant ! */ -void ZSTD_invalidateRepCodes(ZSTD_CCtx *cctx); - -size_t ZSTD_freeCCtx(ZSTD_CCtx *cctx); -size_t ZSTD_freeDCtx(ZSTD_DCtx *dctx); -size_t ZSTD_freeCDict(ZSTD_CDict *cdict); -size_t ZSTD_freeDDict(ZSTD_DDict *cdict); -size_t ZSTD_freeCStream(ZSTD_CStream *zcs); -size_t ZSTD_freeDStream(ZSTD_DStream *zds); - -#endif /* ZSTD_CCOMMON_H_MODULE */ diff --git a/lib/zstd/zstd_opt.h b/lib/zstd/zstd_opt.h deleted file mode 100644 index 55e1b4cba808..000000000000 --- a/lib/zstd/zstd_opt.h +++ /dev/null @@ -1,1014 +0,0 @@ -/** - * Copyright (c) 2016-present, Przemyslaw Skibinski, Yann Collet, Facebook, Inc. - * All rights reserved. - * - * This source code is licensed under the BSD-style license found in the - * LICENSE file in the root directory of https://github.com/facebook/zstd. - * An additional grant of patent rights can be found in the PATENTS file in the - * same directory. - * - * This program is free software; you can redistribute it and/or modify it under - * the terms of the GNU General Public License version 2 as published by the - * Free Software Foundation. This program is dual-licensed; you may select - * either version 2 of the GNU General Public License ("GPL") or BSD license - * ("BSD"). - */ - -/* Note : this file is intended to be included within zstd_compress.c */ - -#ifndef ZSTD_OPT_H_91842398743 -#define ZSTD_OPT_H_91842398743 - -#define ZSTD_LITFREQ_ADD 2 -#define ZSTD_FREQ_DIV 4 -#define ZSTD_MAX_PRICE (1 << 30) - -/*-************************************* -* Price functions for optimal parser -***************************************/ -FORCE_INLINE void ZSTD_setLog2Prices(seqStore_t *ssPtr) -{ - ssPtr->log2matchLengthSum = ZSTD_highbit32(ssPtr->matchLengthSum + 1); - ssPtr->log2litLengthSum = ZSTD_highbit32(ssPtr->litLengthSum + 1); - ssPtr->log2litSum = ZSTD_highbit32(ssPtr->litSum + 1); - ssPtr->log2offCodeSum = ZSTD_highbit32(ssPtr->offCodeSum + 1); - ssPtr->factor = 1 + ((ssPtr->litSum >> 5) / ssPtr->litLengthSum) + ((ssPtr->litSum << 1) / (ssPtr->litSum + ssPtr->matchSum)); -} - -ZSTD_STATIC void ZSTD_rescaleFreqs(seqStore_t *ssPtr, const BYTE *src, size_t srcSize) -{ - unsigned u; - - ssPtr->cachedLiterals = NULL; - ssPtr->cachedPrice = ssPtr->cachedLitLength = 0; - ssPtr->staticPrices = 0; - - if (ssPtr->litLengthSum == 0) { - if (srcSize <= 1024) - ssPtr->staticPrices = 1; - - for (u = 0; u <= MaxLit; u++) - ssPtr->litFreq[u] = 0; - for (u = 0; u < srcSize; u++) - ssPtr->litFreq[src[u]]++; - - ssPtr->litSum = 0; - ssPtr->litLengthSum = MaxLL + 1; - ssPtr->matchLengthSum = MaxML + 1; - ssPtr->offCodeSum = (MaxOff + 1); - ssPtr->matchSum = (ZSTD_LITFREQ_ADD << Litbits); - - for (u = 0; u <= MaxLit; u++) { - ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u] >> ZSTD_FREQ_DIV); - ssPtr->litSum += ssPtr->litFreq[u]; - } - for (u = 0; u <= MaxLL; u++) - ssPtr->litLengthFreq[u] = 1; - for (u = 0; u <= MaxML; u++) - ssPtr->matchLengthFreq[u] = 1; - for (u = 0; u <= MaxOff; u++) - ssPtr->offCodeFreq[u] = 1; - } else { - ssPtr->matchLengthSum = 0; - ssPtr->litLengthSum = 0; - ssPtr->offCodeSum = 0; - ssPtr->matchSum = 0; - ssPtr->litSum = 0; - - for (u = 0; u <= MaxLit; u++) { - ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u] >> (ZSTD_FREQ_DIV + 1)); - ssPtr->litSum += ssPtr->litFreq[u]; - } - for (u = 0; u <= MaxLL; u++) { - ssPtr->litLengthFreq[u] = 1 + (ssPtr->litLengthFreq[u] >> (ZSTD_FREQ_DIV + 1)); - ssPtr->litLengthSum += ssPtr->litLengthFreq[u]; - } - for (u = 0; u <= MaxML; u++) { - ssPtr->matchLengthFreq[u] = 1 + (ssPtr->matchLengthFreq[u] >> ZSTD_FREQ_DIV); - ssPtr->matchLengthSum += ssPtr->matchLengthFreq[u]; - ssPtr->matchSum += ssPtr->matchLengthFreq[u] * (u + 3); - } - ssPtr->matchSum *= ZSTD_LITFREQ_ADD; - for (u = 0; u <= MaxOff; u++) { - ssPtr->offCodeFreq[u] = 1 + (ssPtr->offCodeFreq[u] >> ZSTD_FREQ_DIV); - ssPtr->offCodeSum += ssPtr->offCodeFreq[u]; - } - } - - ZSTD_setLog2Prices(ssPtr); -} - -FORCE_INLINE U32 ZSTD_getLiteralPrice(seqStore_t *ssPtr, U32 litLength, const BYTE *literals) -{ - U32 price, u; - - if (ssPtr->staticPrices) - return ZSTD_highbit32((U32)litLength + 1) + (litLength * 6); - - if (litLength == 0) - return ssPtr->log2litLengthSum - ZSTD_highbit32(ssPtr->litLengthFreq[0] + 1); - - /* literals */ - if (ssPtr->cachedLiterals == literals) { - U32 const additional = litLength - ssPtr->cachedLitLength; - const BYTE *literals2 = ssPtr->cachedLiterals + ssPtr->cachedLitLength; - price = ssPtr->cachedPrice + additional * ssPtr->log2litSum; - for (u = 0; u < additional; u++) - price -= ZSTD_highbit32(ssPtr->litFreq[literals2[u]] + 1); - ssPtr->cachedPrice = price; - ssPtr->cachedLitLength = litLength; - } else { - price = litLength * ssPtr->log2litSum; - for (u = 0; u < litLength; u++) - price -= ZSTD_highbit32(ssPtr->litFreq[literals[u]] + 1); - - if (litLength >= 12) { - ssPtr->cachedLiterals = literals; - ssPtr->cachedPrice = price; - ssPtr->cachedLitLength = litLength; - } - } - - /* literal Length */ - { - const BYTE LL_deltaCode = 19; - const BYTE llCode = (litLength > 63) ? (BYTE)ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength]; - price += LL_bits[llCode] + ssPtr->log2litLengthSum - ZSTD_highbit32(ssPtr->litLengthFreq[llCode] + 1); - } - - return price; -} - -FORCE_INLINE U32 ZSTD_getPrice(seqStore_t *seqStorePtr, U32 litLength, const BYTE *literals, U32 offset, U32 matchLength, const int ultra) -{ - /* offset */ - U32 price; - BYTE const offCode = (BYTE)ZSTD_highbit32(offset + 1); - - if (seqStorePtr->staticPrices) - return ZSTD_getLiteralPrice(seqStorePtr, litLength, literals) + ZSTD_highbit32((U32)matchLength + 1) + 16 + offCode; - - price = offCode + seqStorePtr->log2offCodeSum - ZSTD_highbit32(seqStorePtr->offCodeFreq[offCode] + 1); - if (!ultra && offCode >= 20) - price += (offCode - 19) * 2; - - /* match Length */ - { - const BYTE ML_deltaCode = 36; - const BYTE mlCode = (matchLength > 127) ? (BYTE)ZSTD_highbit32(matchLength) + ML_deltaCode : ML_Code[matchLength]; - price += ML_bits[mlCode] + seqStorePtr->log2matchLengthSum - ZSTD_highbit32(seqStorePtr->matchLengthFreq[mlCode] + 1); - } - - return price + ZSTD_getLiteralPrice(seqStorePtr, litLength, literals) + seqStorePtr->factor; -} - -ZSTD_STATIC void ZSTD_updatePrice(seqStore_t *seqStorePtr, U32 litLength, const BYTE *literals, U32 offset, U32 matchLength) -{ - U32 u; - - /* literals */ - seqStorePtr->litSum += litLength * ZSTD_LITFREQ_ADD; - for (u = 0; u < litLength; u++) - seqStorePtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD; - - /* literal Length */ - { - const BYTE LL_deltaCode = 19; - const BYTE llCode = (litLength > 63) ? (BYTE)ZSTD_highbit32(litLength) + LL_deltaCode : LL_Code[litLength]; - seqStorePtr->litLengthFreq[llCode]++; - seqStorePtr->litLengthSum++; - } - - /* match offset */ - { - BYTE const offCode = (BYTE)ZSTD_highbit32(offset + 1); - seqStorePtr->offCodeSum++; - seqStorePtr->offCodeFreq[offCode]++; - } - - /* match Length */ - { - const BYTE ML_deltaCode = 36; - const BYTE mlCode = (matchLength > 127) ? (BYTE)ZSTD_highbit32(matchLength) + ML_deltaCode : ML_Code[matchLength]; - seqStorePtr->matchLengthFreq[mlCode]++; - seqStorePtr->matchLengthSum++; - } - - ZSTD_setLog2Prices(seqStorePtr); -} - -#define SET_PRICE(pos, mlen_, offset_, litlen_, price_) \ - { \ - while (last_pos < pos) { \ - opt[last_pos + 1].price = ZSTD_MAX_PRICE; \ - last_pos++; \ - } \ - opt[pos].mlen = mlen_; \ - opt[pos].off = offset_; \ - opt[pos].litlen = litlen_; \ - opt[pos].price = price_; \ - } - -/* Update hashTable3 up to ip (excluded) - Assumption : always within prefix (i.e. not within extDict) */ -FORCE_INLINE -U32 ZSTD_insertAndFindFirstIndexHash3(ZSTD_CCtx *zc, const BYTE *ip) -{ - U32 *const hashTable3 = zc->hashTable3; - U32 const hashLog3 = zc->hashLog3; - const BYTE *const base = zc->base; - U32 idx = zc->nextToUpdate3; - const U32 target = zc->nextToUpdate3 = (U32)(ip - base); - const size_t hash3 = ZSTD_hash3Ptr(ip, hashLog3); - - while (idx < target) { - hashTable3[ZSTD_hash3Ptr(base + idx, hashLog3)] = idx; - idx++; - } - - return hashTable3[hash3]; -} - -/*-************************************* -* Binary Tree search -***************************************/ -static U32 ZSTD_insertBtAndGetAllMatches(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, U32 nbCompares, const U32 mls, U32 extDict, - ZSTD_match_t *matches, const U32 minMatchLen) -{ - const BYTE *const base = zc->base; - const U32 curr = (U32)(ip - base); - const U32 hashLog = zc->params.cParams.hashLog; - const size_t h = ZSTD_hashPtr(ip, hashLog, mls); - U32 *const hashTable = zc->hashTable; - U32 matchIndex = hashTable[h]; - U32 *const bt = zc->chainTable; - const U32 btLog = zc->params.cParams.chainLog - 1; - const U32 btMask = (1U << btLog) - 1; - size_t commonLengthSmaller = 0, commonLengthLarger = 0; - const BYTE *const dictBase = zc->dictBase; - const U32 dictLimit = zc->dictLimit; - const BYTE *const dictEnd = dictBase + dictLimit; - const BYTE *const prefixStart = base + dictLimit; - const U32 btLow = btMask >= curr ? 0 : curr - btMask; - const U32 windowLow = zc->lowLimit; - U32 *smallerPtr = bt + 2 * (curr & btMask); - U32 *largerPtr = bt + 2 * (curr & btMask) + 1; - U32 matchEndIdx = curr + 8; - U32 dummy32; /* to be nullified at the end */ - U32 mnum = 0; - - const U32 minMatch = (mls == 3) ? 3 : 4; - size_t bestLength = minMatchLen - 1; - - if (minMatch == 3) { /* HC3 match finder */ - U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(zc, ip); - if (matchIndex3 > windowLow && (curr - matchIndex3 < (1 << 18))) { - const BYTE *match; - size_t currMl = 0; - if ((!extDict) || matchIndex3 >= dictLimit) { - match = base + matchIndex3; - if (match[bestLength] == ip[bestLength]) - currMl = ZSTD_count(ip, match, iLimit); - } else { - match = dictBase + matchIndex3; - if (ZSTD_readMINMATCH(match, MINMATCH) == - ZSTD_readMINMATCH(ip, MINMATCH)) /* assumption : matchIndex3 <= dictLimit-4 (by table construction) */ - currMl = ZSTD_count_2segments(ip + MINMATCH, match + MINMATCH, iLimit, dictEnd, prefixStart) + MINMATCH; - } - - /* save best solution */ - if (currMl > bestLength) { - bestLength = currMl; - matches[mnum].off = ZSTD_REP_MOVE_OPT + curr - matchIndex3; - matches[mnum].len = (U32)currMl; - mnum++; - if (currMl > ZSTD_OPT_NUM) - goto update; - if (ip + currMl == iLimit) - goto update; /* best possible, and avoid read overflow*/ - } - } - } - - hashTable[h] = curr; /* Update Hash Table */ - - while (nbCompares-- && (matchIndex > windowLow)) { - U32 *nextPtr = bt + 2 * (matchIndex & btMask); - size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger); /* guaranteed minimum nb of common bytes */ - const BYTE *match; - - if ((!extDict) || (matchIndex + matchLength >= dictLimit)) { - match = base + matchIndex; - if (match[matchLength] == ip[matchLength]) { - matchLength += ZSTD_count(ip + matchLength + 1, match + matchLength + 1, iLimit) + 1; - } - } else { - match = dictBase + matchIndex; - matchLength += ZSTD_count_2segments(ip + matchLength, match + matchLength, iLimit, dictEnd, prefixStart); - if (matchIndex + matchLength >= dictLimit) - match = base + matchIndex; /* to prepare for next usage of match[matchLength] */ - } - - if (matchLength > bestLength) { - if (matchLength > matchEndIdx - matchIndex) - matchEndIdx = matchIndex + (U32)matchLength; - bestLength = matchLength; - matches[mnum].off = ZSTD_REP_MOVE_OPT + curr - matchIndex; - matches[mnum].len = (U32)matchLength; - mnum++; - if (matchLength > ZSTD_OPT_NUM) - break; - if (ip + matchLength == iLimit) /* equal : no way to know if inf or sup */ - break; /* drop, to guarantee consistency (miss a little bit of compression) */ - } - - if (match[matchLength] < ip[matchLength]) { - /* match is smaller than curr */ - *smallerPtr = matchIndex; /* update smaller idx */ - commonLengthSmaller = matchLength; /* all smaller will now have at least this guaranteed common length */ - if (matchIndex <= btLow) { - smallerPtr = &dummy32; - break; - } /* beyond tree size, stop the search */ - smallerPtr = nextPtr + 1; /* new "smaller" => larger of match */ - matchIndex = nextPtr[1]; /* new matchIndex larger than previous (closer to curr) */ - } else { - /* match is larger than curr */ - *largerPtr = matchIndex; - commonLengthLarger = matchLength; - if (matchIndex <= btLow) { - largerPtr = &dummy32; - break; - } /* beyond tree size, stop the search */ - largerPtr = nextPtr; - matchIndex = nextPtr[0]; - } - } - - *smallerPtr = *largerPtr = 0; - -update: - zc->nextToUpdate = (matchEndIdx > curr + 8) ? matchEndIdx - 8 : curr + 1; - return mnum; -} - -/** Tree updater, providing best match */ -static U32 ZSTD_BtGetAllMatches(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, const U32 maxNbAttempts, const U32 mls, ZSTD_match_t *matches, - const U32 minMatchLen) -{ - if (ip < zc->base + zc->nextToUpdate) - return 0; /* skipped area */ - ZSTD_updateTree(zc, ip, iLimit, maxNbAttempts, mls); - return ZSTD_insertBtAndGetAllMatches(zc, ip, iLimit, maxNbAttempts, mls, 0, matches, minMatchLen); -} - -static U32 ZSTD_BtGetAllMatches_selectMLS(ZSTD_CCtx *zc, /* Index table will be updated */ - const BYTE *ip, const BYTE *const iHighLimit, const U32 maxNbAttempts, const U32 matchLengthSearch, - ZSTD_match_t *matches, const U32 minMatchLen) -{ - switch (matchLengthSearch) { - case 3: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 3, matches, minMatchLen); - default: - case 4: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 4, matches, minMatchLen); - case 5: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 5, matches, minMatchLen); - case 7: - case 6: return ZSTD_BtGetAllMatches(zc, ip, iHighLimit, maxNbAttempts, 6, matches, minMatchLen); - } -} - -/** Tree updater, providing best match */ -static U32 ZSTD_BtGetAllMatches_extDict(ZSTD_CCtx *zc, const BYTE *const ip, const BYTE *const iLimit, const U32 maxNbAttempts, const U32 mls, - ZSTD_match_t *matches, const U32 minMatchLen) -{ - if (ip < zc->base + zc->nextToUpdate) - return 0; /* skipped area */ - ZSTD_updateTree_extDict(zc, ip, iLimit, maxNbAttempts, mls); - return ZSTD_insertBtAndGetAllMatches(zc, ip, iLimit, maxNbAttempts, mls, 1, matches, minMatchLen); -} - -static U32 ZSTD_BtGetAllMatches_selectMLS_extDict(ZSTD_CCtx *zc, /* Index table will be updated */ - const BYTE *ip, const BYTE *const iHighLimit, const U32 maxNbAttempts, const U32 matchLengthSearch, - ZSTD_match_t *matches, const U32 minMatchLen) -{ - switch (matchLengthSearch) { - case 3: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 3, matches, minMatchLen); - default: - case 4: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 4, matches, minMatchLen); - case 5: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 5, matches, minMatchLen); - case 7: - case 6: return ZSTD_BtGetAllMatches_extDict(zc, ip, iHighLimit, maxNbAttempts, 6, matches, minMatchLen); - } -} - -/*-******************************* -* Optimal parser -*********************************/ -FORCE_INLINE -void ZSTD_compressBlock_opt_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const int ultra) -{ - seqStore_t *seqStorePtr = &(ctx->seqStore); - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - 8; - const BYTE *const base = ctx->base; - const BYTE *const prefixStart = base + ctx->dictLimit; - - const U32 maxSearches = 1U << ctx->params.cParams.searchLog; - const U32 sufficient_len = ctx->params.cParams.targetLength; - const U32 mls = ctx->params.cParams.searchLength; - const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4; - - ZSTD_optimal_t *opt = seqStorePtr->priceTable; - ZSTD_match_t *matches = seqStorePtr->matchTable; - const BYTE *inr; - U32 offset, rep[ZSTD_REP_NUM]; - - /* init */ - ctx->nextToUpdate3 = ctx->nextToUpdate; - ZSTD_rescaleFreqs(seqStorePtr, (const BYTE *)src, srcSize); - ip += (ip == prefixStart); - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - rep[i] = ctx->rep[i]; - } - - /* Match Loop */ - while (ip < ilimit) { - U32 cur, match_num, last_pos, litlen, price; - U32 u, mlen, best_mlen, best_off, litLength; - memset(opt, 0, sizeof(ZSTD_optimal_t)); - last_pos = 0; - litlen = (U32)(ip - anchor); - - /* check repCode */ - { - U32 i, last_i = ZSTD_REP_CHECK + (ip == anchor); - for (i = (ip == anchor); i < last_i; i++) { - const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i]; - if ((repCur > 0) && (repCur < (S32)(ip - prefixStart)) && - (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(ip - repCur, minMatch))) { - mlen = (U32)ZSTD_count(ip + minMatch, ip + minMatch - repCur, iend) + minMatch; - if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) { - best_mlen = mlen; - best_off = i; - cur = 0; - last_pos = 1; - goto _storeSequence; - } - best_off = i - (ip == anchor); - do { - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra); - if (mlen > last_pos || price < opt[mlen].price) - SET_PRICE(mlen, mlen, i, litlen, price); /* note : macro modifies last_pos */ - mlen--; - } while (mlen >= minMatch); - } - } - } - - match_num = ZSTD_BtGetAllMatches_selectMLS(ctx, ip, iend, maxSearches, mls, matches, minMatch); - - if (!last_pos && !match_num) { - ip++; - continue; - } - - if (match_num && (matches[match_num - 1].len > sufficient_len || matches[match_num - 1].len >= ZSTD_OPT_NUM)) { - best_mlen = matches[match_num - 1].len; - best_off = matches[match_num - 1].off; - cur = 0; - last_pos = 1; - goto _storeSequence; - } - - /* set prices using matches at position = 0 */ - best_mlen = (last_pos) ? last_pos : minMatch; - for (u = 0; u < match_num; u++) { - mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen; - best_mlen = matches[u].len; - while (mlen <= best_mlen) { - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra); - if (mlen > last_pos || price < opt[mlen].price) - SET_PRICE(mlen, mlen, matches[u].off, litlen, price); /* note : macro modifies last_pos */ - mlen++; - } - } - - if (last_pos < minMatch) { - ip++; - continue; - } - - /* initialize opt[0] */ - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - opt[0].rep[i] = rep[i]; - } - opt[0].mlen = 1; - opt[0].litlen = litlen; - - /* check further positions */ - for (cur = 1; cur <= last_pos; cur++) { - inr = ip + cur; - - if (opt[cur - 1].mlen == 1) { - litlen = opt[cur - 1].litlen + 1; - if (cur > litlen) { - price = opt[cur - litlen].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - litlen); - } else - price = ZSTD_getLiteralPrice(seqStorePtr, litlen, anchor); - } else { - litlen = 1; - price = opt[cur - 1].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - 1); - } - - if (cur > last_pos || price <= opt[cur].price) - SET_PRICE(cur, 1, 0, litlen, price); - - if (cur == last_pos) - break; - - if (inr > ilimit) /* last match must start at a minimum distance of 8 from oend */ - continue; - - mlen = opt[cur].mlen; - if (opt[cur].off > ZSTD_REP_MOVE_OPT) { - opt[cur].rep[2] = opt[cur - mlen].rep[1]; - opt[cur].rep[1] = opt[cur - mlen].rep[0]; - opt[cur].rep[0] = opt[cur].off - ZSTD_REP_MOVE_OPT; - } else { - opt[cur].rep[2] = (opt[cur].off > 1) ? opt[cur - mlen].rep[1] : opt[cur - mlen].rep[2]; - opt[cur].rep[1] = (opt[cur].off > 0) ? opt[cur - mlen].rep[0] : opt[cur - mlen].rep[1]; - opt[cur].rep[0] = - ((opt[cur].off == ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur - mlen].rep[0] - 1) : (opt[cur - mlen].rep[opt[cur].off]); - } - - best_mlen = minMatch; - { - U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1); - for (i = (opt[cur].mlen != 1); i < last_i; i++) { /* check rep */ - const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i]; - if ((repCur > 0) && (repCur < (S32)(inr - prefixStart)) && - (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(inr - repCur, minMatch))) { - mlen = (U32)ZSTD_count(inr + minMatch, inr + minMatch - repCur, iend) + minMatch; - - if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) { - best_mlen = mlen; - best_off = i; - last_pos = cur + 1; - goto _storeSequence; - } - - best_off = i - (opt[cur].mlen != 1); - if (mlen > best_mlen) - best_mlen = mlen; - - do { - if (opt[cur].mlen == 1) { - litlen = opt[cur].litlen; - if (cur > litlen) { - price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr - litlen, - best_off, mlen - MINMATCH, ultra); - } else - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra); - } else { - litlen = 0; - price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH, ultra); - } - - if (cur + mlen > last_pos || price <= opt[cur + mlen].price) - SET_PRICE(cur + mlen, mlen, i, litlen, price); - mlen--; - } while (mlen >= minMatch); - } - } - } - - match_num = ZSTD_BtGetAllMatches_selectMLS(ctx, inr, iend, maxSearches, mls, matches, best_mlen); - - if (match_num > 0 && (matches[match_num - 1].len > sufficient_len || cur + matches[match_num - 1].len >= ZSTD_OPT_NUM)) { - best_mlen = matches[match_num - 1].len; - best_off = matches[match_num - 1].off; - last_pos = cur + 1; - goto _storeSequence; - } - - /* set prices using matches at position = cur */ - for (u = 0; u < match_num; u++) { - mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen; - best_mlen = matches[u].len; - - while (mlen <= best_mlen) { - if (opt[cur].mlen == 1) { - litlen = opt[cur].litlen; - if (cur > litlen) - price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, ip + cur - litlen, - matches[u].off - 1, mlen - MINMATCH, ultra); - else - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra); - } else { - litlen = 0; - price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, matches[u].off - 1, mlen - MINMATCH, ultra); - } - - if (cur + mlen > last_pos || (price < opt[cur + mlen].price)) - SET_PRICE(cur + mlen, mlen, matches[u].off, litlen, price); - - mlen++; - } - } - } - - best_mlen = opt[last_pos].mlen; - best_off = opt[last_pos].off; - cur = last_pos - best_mlen; - - /* store sequence */ -_storeSequence: /* cur, last_pos, best_mlen, best_off have to be set */ - opt[0].mlen = 1; - - while (1) { - mlen = opt[cur].mlen; - offset = opt[cur].off; - opt[cur].mlen = best_mlen; - opt[cur].off = best_off; - best_mlen = mlen; - best_off = offset; - if (mlen > cur) - break; - cur -= mlen; - } - - for (u = 0; u <= last_pos;) { - u += opt[u].mlen; - } - - for (cur = 0; cur < last_pos;) { - mlen = opt[cur].mlen; - if (mlen == 1) { - ip++; - cur++; - continue; - } - offset = opt[cur].off; - cur += mlen; - litLength = (U32)(ip - anchor); - - if (offset > ZSTD_REP_MOVE_OPT) { - rep[2] = rep[1]; - rep[1] = rep[0]; - rep[0] = offset - ZSTD_REP_MOVE_OPT; - offset--; - } else { - if (offset != 0) { - best_off = (offset == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : (rep[offset]); - if (offset != 1) - rep[2] = rep[1]; - rep[1] = rep[0]; - rep[0] = best_off; - } - if (litLength == 0) - offset--; - } - - ZSTD_updatePrice(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH); - ZSTD_storeSeq(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH); - anchor = ip = ip + mlen; - } - } /* for (cur=0; cur < last_pos; ) */ - - /* Save reps for next block */ - { - int i; - for (i = 0; i < ZSTD_REP_NUM; i++) - ctx->repToConfirm[i] = rep[i]; - } - - /* Last Literals */ - { - size_t const lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -FORCE_INLINE -void ZSTD_compressBlock_opt_extDict_generic(ZSTD_CCtx *ctx, const void *src, size_t srcSize, const int ultra) -{ - seqStore_t *seqStorePtr = &(ctx->seqStore); - const BYTE *const istart = (const BYTE *)src; - const BYTE *ip = istart; - const BYTE *anchor = istart; - const BYTE *const iend = istart + srcSize; - const BYTE *const ilimit = iend - 8; - const BYTE *const base = ctx->base; - const U32 lowestIndex = ctx->lowLimit; - const U32 dictLimit = ctx->dictLimit; - const BYTE *const prefixStart = base + dictLimit; - const BYTE *const dictBase = ctx->dictBase; - const BYTE *const dictEnd = dictBase + dictLimit; - - const U32 maxSearches = 1U << ctx->params.cParams.searchLog; - const U32 sufficient_len = ctx->params.cParams.targetLength; - const U32 mls = ctx->params.cParams.searchLength; - const U32 minMatch = (ctx->params.cParams.searchLength == 3) ? 3 : 4; - - ZSTD_optimal_t *opt = seqStorePtr->priceTable; - ZSTD_match_t *matches = seqStorePtr->matchTable; - const BYTE *inr; - - /* init */ - U32 offset, rep[ZSTD_REP_NUM]; - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - rep[i] = ctx->rep[i]; - } - - ctx->nextToUpdate3 = ctx->nextToUpdate; - ZSTD_rescaleFreqs(seqStorePtr, (const BYTE *)src, srcSize); - ip += (ip == prefixStart); - - /* Match Loop */ - while (ip < ilimit) { - U32 cur, match_num, last_pos, litlen, price; - U32 u, mlen, best_mlen, best_off, litLength; - U32 curr = (U32)(ip - base); - memset(opt, 0, sizeof(ZSTD_optimal_t)); - last_pos = 0; - opt[0].litlen = (U32)(ip - anchor); - - /* check repCode */ - { - U32 i, last_i = ZSTD_REP_CHECK + (ip == anchor); - for (i = (ip == anchor); i < last_i; i++) { - const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : rep[i]; - const U32 repIndex = (U32)(curr - repCur); - const BYTE *const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *const repMatch = repBase + repIndex; - if ((repCur > 0 && repCur <= (S32)curr) && - (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */ - && (ZSTD_readMINMATCH(ip, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch))) { - /* repcode detected we should take it */ - const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend; - mlen = (U32)ZSTD_count_2segments(ip + minMatch, repMatch + minMatch, iend, repEnd, prefixStart) + minMatch; - - if (mlen > sufficient_len || mlen >= ZSTD_OPT_NUM) { - best_mlen = mlen; - best_off = i; - cur = 0; - last_pos = 1; - goto _storeSequence; - } - - best_off = i - (ip == anchor); - litlen = opt[0].litlen; - do { - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra); - if (mlen > last_pos || price < opt[mlen].price) - SET_PRICE(mlen, mlen, i, litlen, price); /* note : macro modifies last_pos */ - mlen--; - } while (mlen >= minMatch); - } - } - } - - match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, ip, iend, maxSearches, mls, matches, minMatch); /* first search (depth 0) */ - - if (!last_pos && !match_num) { - ip++; - continue; - } - - { - U32 i; - for (i = 0; i < ZSTD_REP_NUM; i++) - opt[0].rep[i] = rep[i]; - } - opt[0].mlen = 1; - - if (match_num && (matches[match_num - 1].len > sufficient_len || matches[match_num - 1].len >= ZSTD_OPT_NUM)) { - best_mlen = matches[match_num - 1].len; - best_off = matches[match_num - 1].off; - cur = 0; - last_pos = 1; - goto _storeSequence; - } - - best_mlen = (last_pos) ? last_pos : minMatch; - - /* set prices using matches at position = 0 */ - for (u = 0; u < match_num; u++) { - mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen; - best_mlen = matches[u].len; - litlen = opt[0].litlen; - while (mlen <= best_mlen) { - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra); - if (mlen > last_pos || price < opt[mlen].price) - SET_PRICE(mlen, mlen, matches[u].off, litlen, price); - mlen++; - } - } - - if (last_pos < minMatch) { - ip++; - continue; - } - - /* check further positions */ - for (cur = 1; cur <= last_pos; cur++) { - inr = ip + cur; - - if (opt[cur - 1].mlen == 1) { - litlen = opt[cur - 1].litlen + 1; - if (cur > litlen) { - price = opt[cur - litlen].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - litlen); - } else - price = ZSTD_getLiteralPrice(seqStorePtr, litlen, anchor); - } else { - litlen = 1; - price = opt[cur - 1].price + ZSTD_getLiteralPrice(seqStorePtr, litlen, inr - 1); - } - - if (cur > last_pos || price <= opt[cur].price) - SET_PRICE(cur, 1, 0, litlen, price); - - if (cur == last_pos) - break; - - if (inr > ilimit) /* last match must start at a minimum distance of 8 from oend */ - continue; - - mlen = opt[cur].mlen; - if (opt[cur].off > ZSTD_REP_MOVE_OPT) { - opt[cur].rep[2] = opt[cur - mlen].rep[1]; - opt[cur].rep[1] = opt[cur - mlen].rep[0]; - opt[cur].rep[0] = opt[cur].off - ZSTD_REP_MOVE_OPT; - } else { - opt[cur].rep[2] = (opt[cur].off > 1) ? opt[cur - mlen].rep[1] : opt[cur - mlen].rep[2]; - opt[cur].rep[1] = (opt[cur].off > 0) ? opt[cur - mlen].rep[0] : opt[cur - mlen].rep[1]; - opt[cur].rep[0] = - ((opt[cur].off == ZSTD_REP_MOVE_OPT) && (mlen != 1)) ? (opt[cur - mlen].rep[0] - 1) : (opt[cur - mlen].rep[opt[cur].off]); - } - - best_mlen = minMatch; - { - U32 i, last_i = ZSTD_REP_CHECK + (mlen != 1); - for (i = (mlen != 1); i < last_i; i++) { - const S32 repCur = (i == ZSTD_REP_MOVE_OPT) ? (opt[cur].rep[0] - 1) : opt[cur].rep[i]; - const U32 repIndex = (U32)(curr + cur - repCur); - const BYTE *const repBase = repIndex < dictLimit ? dictBase : base; - const BYTE *const repMatch = repBase + repIndex; - if ((repCur > 0 && repCur <= (S32)(curr + cur)) && - (((U32)((dictLimit - 1) - repIndex) >= 3) & (repIndex > lowestIndex)) /* intentional overflow */ - && (ZSTD_readMINMATCH(inr, minMatch) == ZSTD_readMINMATCH(repMatch, minMatch))) { - /* repcode detected */ - const BYTE *const repEnd = repIndex < dictLimit ? dictEnd : iend; - mlen = (U32)ZSTD_count_2segments(inr + minMatch, repMatch + minMatch, iend, repEnd, prefixStart) + minMatch; - - if (mlen > sufficient_len || cur + mlen >= ZSTD_OPT_NUM) { - best_mlen = mlen; - best_off = i; - last_pos = cur + 1; - goto _storeSequence; - } - - best_off = i - (opt[cur].mlen != 1); - if (mlen > best_mlen) - best_mlen = mlen; - - do { - if (opt[cur].mlen == 1) { - litlen = opt[cur].litlen; - if (cur > litlen) { - price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, inr - litlen, - best_off, mlen - MINMATCH, ultra); - } else - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, best_off, mlen - MINMATCH, ultra); - } else { - litlen = 0; - price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, best_off, mlen - MINMATCH, ultra); - } - - if (cur + mlen > last_pos || price <= opt[cur + mlen].price) - SET_PRICE(cur + mlen, mlen, i, litlen, price); - mlen--; - } while (mlen >= minMatch); - } - } - } - - match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, inr, iend, maxSearches, mls, matches, minMatch); - - if (match_num > 0 && (matches[match_num - 1].len > sufficient_len || cur + matches[match_num - 1].len >= ZSTD_OPT_NUM)) { - best_mlen = matches[match_num - 1].len; - best_off = matches[match_num - 1].off; - last_pos = cur + 1; - goto _storeSequence; - } - - /* set prices using matches at position = cur */ - for (u = 0; u < match_num; u++) { - mlen = (u > 0) ? matches[u - 1].len + 1 : best_mlen; - best_mlen = matches[u].len; - - while (mlen <= best_mlen) { - if (opt[cur].mlen == 1) { - litlen = opt[cur].litlen; - if (cur > litlen) - price = opt[cur - litlen].price + ZSTD_getPrice(seqStorePtr, litlen, ip + cur - litlen, - matches[u].off - 1, mlen - MINMATCH, ultra); - else - price = ZSTD_getPrice(seqStorePtr, litlen, anchor, matches[u].off - 1, mlen - MINMATCH, ultra); - } else { - litlen = 0; - price = opt[cur].price + ZSTD_getPrice(seqStorePtr, 0, NULL, matches[u].off - 1, mlen - MINMATCH, ultra); - } - - if (cur + mlen > last_pos || (price < opt[cur + mlen].price)) - SET_PRICE(cur + mlen, mlen, matches[u].off, litlen, price); - - mlen++; - } - } - } /* for (cur = 1; cur <= last_pos; cur++) */ - - best_mlen = opt[last_pos].mlen; - best_off = opt[last_pos].off; - cur = last_pos - best_mlen; - - /* store sequence */ -_storeSequence: /* cur, last_pos, best_mlen, best_off have to be set */ - opt[0].mlen = 1; - - while (1) { - mlen = opt[cur].mlen; - offset = opt[cur].off; - opt[cur].mlen = best_mlen; - opt[cur].off = best_off; - best_mlen = mlen; - best_off = offset; - if (mlen > cur) - break; - cur -= mlen; - } - - for (u = 0; u <= last_pos;) { - u += opt[u].mlen; - } - - for (cur = 0; cur < last_pos;) { - mlen = opt[cur].mlen; - if (mlen == 1) { - ip++; - cur++; - continue; - } - offset = opt[cur].off; - cur += mlen; - litLength = (U32)(ip - anchor); - - if (offset > ZSTD_REP_MOVE_OPT) { - rep[2] = rep[1]; - rep[1] = rep[0]; - rep[0] = offset - ZSTD_REP_MOVE_OPT; - offset--; - } else { - if (offset != 0) { - best_off = (offset == ZSTD_REP_MOVE_OPT) ? (rep[0] - 1) : (rep[offset]); - if (offset != 1) - rep[2] = rep[1]; - rep[1] = rep[0]; - rep[0] = best_off; - } - - if (litLength == 0) - offset--; - } - - ZSTD_updatePrice(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH); - ZSTD_storeSeq(seqStorePtr, litLength, anchor, offset, mlen - MINMATCH); - anchor = ip = ip + mlen; - } - } /* for (cur=0; cur < last_pos; ) */ - - /* Save reps for next block */ - { - int i; - for (i = 0; i < ZSTD_REP_NUM; i++) - ctx->repToConfirm[i] = rep[i]; - } - - /* Last Literals */ - { - size_t lastLLSize = iend - anchor; - memcpy(seqStorePtr->lit, anchor, lastLLSize); - seqStorePtr->lit += lastLLSize; - } -} - -#endif /* ZSTD_OPT_H_91842398743 */ -- cgit v1.2.3 From fa443bc3c1e4b28d9315dea882e8358ba6e26f8b Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Fri, 29 Oct 2021 17:28:56 +0200 Subject: HID: intel-ish-hid: add support for MODULE_DEVICE_TABLE() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This allows to selectively autoload drivers for ISH devices. Currently all ISH drivers are loaded for all systems having any ISH device. Signed-off-by: Thomas Weißschuh Acked-by: Srinivas Pandruvada Acked-by: Hans de Goede Signed-off-by: Jiri Kosina --- include/linux/mod_devicetable.h | 13 +++++++++++++ scripts/mod/devicetable-offsets.c | 3 +++ scripts/mod/file2alias.c | 24 ++++++++++++++++++++++++ 3 files changed, 40 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index ae2e75d15b21..befbf53c4b7c 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -895,4 +895,17 @@ struct dfl_device_id { kernel_ulong_t driver_data; }; +/* ISHTP (Integrated Sensor Hub Transport Protocol) */ + +#define ISHTP_MODULE_PREFIX "ishtp:" + +/** + * struct ishtp_device_id - ISHTP device identifier + * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba + * @context: pointer to driver specific data + */ +struct ishtp_device_id { + guid_t guid; +}; + #endif /* LINUX_MOD_DEVICETABLE_H */ diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c index cc3625617a0e..c0d3bcb99138 100644 --- a/scripts/mod/devicetable-offsets.c +++ b/scripts/mod/devicetable-offsets.c @@ -259,5 +259,8 @@ int main(void) DEVID_FIELD(dfl_device_id, type); DEVID_FIELD(dfl_device_id, feature_id); + DEVID(ishtp_device_id); + DEVID_FIELD(ishtp_device_id, guid); + return 0; } diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 49aba862073e..5258247d78ac 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -115,6 +115,17 @@ static inline void add_uuid(char *str, uuid_le uuid) uuid.b[12], uuid.b[13], uuid.b[14], uuid.b[15]); } +static inline void add_guid(char *str, guid_t guid) +{ + int len = strlen(str); + + sprintf(str + len, "%02X%02X%02X%02X-%02X%02X-%02X%02X-%02X%02X-%02X%02X%02X%02X%02X%02X", + guid.b[3], guid.b[2], guid.b[1], guid.b[0], + guid.b[5], guid.b[4], guid.b[7], guid.b[6], + guid.b[8], guid.b[9], guid.b[10], guid.b[11], + guid.b[12], guid.b[13], guid.b[14], guid.b[15]); +} + /** * Check that sizeof(device_id type) are consistent with size of section * in .o file. If in-consistent then userspace and kernel does not agree @@ -1380,6 +1391,18 @@ static int do_mhi_entry(const char *filename, void *symval, char *alias) return 1; } +/* Looks like: ishtp:{guid} */ +static int do_ishtp_entry(const char *filename, void *symval, char *alias) +{ + DEF_FIELD(symval, ishtp_device_id, guid); + + strcpy(alias, ISHTP_MODULE_PREFIX "{"); + add_guid(alias, guid); + strcat(alias, "}"); + + return 1; +} + static int do_auxiliary_entry(const char *filename, void *symval, char *alias) { DEF_FIELD_ADDR(symval, auxiliary_device_id, name); @@ -1499,6 +1522,7 @@ static const struct devtable devtable[] = { {"auxiliary", SIZE_auxiliary_device_id, do_auxiliary_entry}, {"ssam", SIZE_ssam_device_id, do_ssam_entry}, {"dfl", SIZE_dfl_device_id, do_dfl_entry}, + {"ishtp", SIZE_ishtp_device_id, do_ishtp_entry}, }; /* Create MODULE_ALIAS() statements. -- cgit v1.2.3 From 9ef4d0209cbadb63656a7aa29fde49c27ab2b9bf Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 9 Nov 2021 15:11:41 +0800 Subject: blk-mq: add one API for waiting until quiesce is done Some drivers(NVMe, SCSI) need to call quiesce and unquiesce in pair, but it is hard to switch to this style, so these drivers need one atomic flag for helping to balance quiesce and unquiesce. When quiesce is in-progress, the driver still needs to wait until the quiesce is done, so add API of blk_mq_wait_quiesce_done() for these drivers. Signed-off-by: Ming Lei Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20211109071144.181581-2-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/blk-mq.c | 28 ++++++++++++++++++++-------- include/linux/blk-mq.h | 1 + 2 files changed, 21 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 5a9cd9fe8da3..d3e5fcbc943b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -251,22 +251,18 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q) EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); /** - * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished + * blk_mq_wait_quiesce_done() - wait until in-progress quiesce is done * @q: request queue. * - * Note: this function does not prevent that the struct request end_io() - * callback function is invoked. Once this function is returned, we make - * sure no dispatch can happen until the queue is unquiesced via - * blk_mq_unquiesce_queue(). + * Note: it is driver's responsibility for making sure that quiesce has + * been started. */ -void blk_mq_quiesce_queue(struct request_queue *q) +void blk_mq_wait_quiesce_done(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned int i; bool rcu = false; - blk_mq_quiesce_queue_nowait(q); - queue_for_each_hw_ctx(q, hctx, i) { if (hctx->flags & BLK_MQ_F_BLOCKING) synchronize_srcu(hctx->srcu); @@ -276,6 +272,22 @@ void blk_mq_quiesce_queue(struct request_queue *q) if (rcu) synchronize_rcu(); } +EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done); + +/** + * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished + * @q: request queue. + * + * Note: this function does not prevent that the struct request end_io() + * callback function is invoked. Once this function is returned, we make + * sure no dispatch can happen until the queue is unquiesced via + * blk_mq_unquiesce_queue(). + */ +void blk_mq_quiesce_queue(struct request_queue *q) +{ + blk_mq_quiesce_queue_nowait(q); + blk_mq_wait_quiesce_done(q); +} EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue); /* diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index b4039fdf1b04..d53ee59ba131 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -803,6 +803,7 @@ void blk_mq_start_hw_queues(struct request_queue *q); void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async); void blk_mq_quiesce_queue(struct request_queue *q); +void blk_mq_wait_quiesce_done(struct request_queue *q); void blk_mq_unquiesce_queue(struct request_queue *q); void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); -- cgit v1.2.3 From 51b8c1fe250d1bd70c1722dc3c414f5cff2d7cca Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Mon, 8 Nov 2021 18:31:24 -0800 Subject: vfs: keep inodes with page cache off the inode shrinker LRU Historically (pre-2.5), the inode shrinker used to reclaim only empty inodes and skip over those that still contained page cache. This caused problems on highmem hosts: struct inode could put fill lowmem zones before the cache was getting reclaimed in the highmem zones. To address this, the inode shrinker started to strip page cache to facilitate reclaiming lowmem. However, this comes with its own set of problems: the shrinkers may drop actively used page cache just because the inodes are not currently open or dirty - think working with a large git tree. It further doesn't respect cgroup memory protection settings and can cause priority inversions between containers. Nowadays, the page cache also holds non-resident info for evicted cache pages in order to detect refaults. We've come to rely heavily on this data inside reclaim for protecting the cache workingset and driving swap behavior. We also use it to quantify and report workload health through psi. The latter in turn is used for fleet health monitoring, as well as driving automated memory sizing of workloads and containers, proactive reclaim and memory offloading schemes. The consequences of dropping page cache prematurely is that we're seeing subtle and not-so-subtle failures in all of the above-mentioned scenarios, with the workload generally entering unexpected thrashing states while losing the ability to reliably detect it. To fix this on non-highmem systems at least, going back to rotating inodes on the LRU isn't feasible. We've tried (commit a76cf1a474d7 ("mm: don't reclaim inodes with many attached pages")) and failed (commit 69056ee6a8a3 ("Revert "mm: don't reclaim inodes with many attached pages"")). The issue is mostly that shrinker pools attract pressure based on their size, and when objects get skipped the shrinkers remember this as deferred reclaim work. This accumulates excessive pressure on the remaining inodes, and we can quickly eat into heavily used ones, or dirty ones that require IO to reclaim, when there potentially is plenty of cold, clean cache around still. Instead, this patch keeps populated inodes off the inode LRU in the first place - just like an open file or dirty state would. An otherwise clean and unused inode then gets queued when the last cache entry disappears. This solves the problem without reintroducing the reclaim issues, and generally is a bit more scalable than having to wade through potentially hundreds of thousands of busy inodes. Locking is a bit tricky because the locks protecting the inode state (i_lock) and the inode LRU (lru_list.lock) don't nest inside the irq-safe page cache lock (i_pages.xa_lock). Page cache deletions are serialized through i_lock, taken before the i_pages lock, to make sure depopulated inodes are queued reliably. Additions may race with deletions, but we'll check again in the shrinker. If additions race with the shrinker itself, we're protected by the i_lock: if find_inode() or iput() win, the shrinker will bail on the elevated i_count or I_REFERENCED; if the shrinker wins and goes ahead with the inode, it will set I_FREEING and inhibit further igets(), which will cause the other side to create a new instance of the inode instead. Link: https://lkml.kernel.org/r/20210614211904.14420-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Roman Gushchin Cc: Tejun Heo Cc: Dave Chinner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 46 ++++++++++++++++++++++++++------------------- fs/internal.h | 1 - include/linux/fs.h | 1 + include/linux/pagemap.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/filemap.c | 8 ++++++++ mm/truncate.c | 19 +++++++++++++++++-- mm/vmscan.c | 7 +++++++ mm/workingset.c | 10 ++++++++++ 8 files changed, 120 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index ed0cab8a32db..a49695f57e1e 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -428,11 +428,20 @@ void ihold(struct inode *inode) } EXPORT_SYMBOL(ihold); -static void inode_lru_list_add(struct inode *inode) +static void __inode_add_lru(struct inode *inode, bool rotate) { + if (inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) + return; + if (atomic_read(&inode->i_count)) + return; + if (!(inode->i_sb->s_flags & SB_ACTIVE)) + return; + if (!mapping_shrinkable(&inode->i_data)) + return; + if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); - else + else if (rotate) inode->i_state |= I_REFERENCED; } @@ -443,16 +452,11 @@ static void inode_lru_list_add(struct inode *inode) */ void inode_add_lru(struct inode *inode) { - if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | - I_FREEING | I_WILL_FREE)) && - !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE) - inode_lru_list_add(inode); + __inode_add_lru(inode, false); } - static void inode_lru_list_del(struct inode *inode) { - if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } @@ -728,10 +732,6 @@ again: /* * Isolate the inode from the LRU in preparation for freeing it. * - * Any inodes which are pinned purely because of attached pagecache have their - * pagecache removed. If the inode has metadata buffers attached to - * mapping->private_list then try to remove them. - * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another @@ -747,31 +747,39 @@ static enum lru_status inode_lru_isolate(struct list_head *item, struct inode *inode = container_of(item, struct inode, i_lru); /* - * we are inverting the lru lock/inode->i_lock here, so use a trylock. - * If we fail to get the lock, just skip it. + * We are inverting the lru lock/inode->i_lock here, so use a + * trylock. If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* - * Referenced or dirty inodes are still in use. Give them another pass - * through the LRU as we canot reclaim them now. + * Inodes can get referenced, redirtied, or repopulated while + * they're already on the LRU, and this can make them + * unreclaimable for a while. Remove them lazily here; iput, + * sync, or the last page cache deletion will requeue them. */ if (atomic_read(&inode->i_count) || - (inode->i_state & ~I_REFERENCED)) { + (inode->i_state & ~I_REFERENCED) || + !mapping_shrinkable(&inode->i_data)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } - /* recently referenced inodes get one more pass */ + /* Recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } + /* + * On highmem systems, mapping_shrinkable() permits dropping + * page cache in order to free up struct inodes: lowmem might + * be under pressure before the cache inside the highmem zone. + */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { __iget(inode); spin_unlock(&inode->i_lock); @@ -1638,7 +1646,7 @@ static void iput_final(struct inode *inode) if (!drop && !(inode->i_state & I_DONTCACHE) && (sb->s_flags & SB_ACTIVE)) { - inode_add_lru(inode); + __inode_add_lru(inode, true); spin_unlock(&inode->i_lock); return; } diff --git a/fs/internal.h b/fs/internal.h index 3cd065c8a66b..2854ff29f116 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -149,7 +149,6 @@ extern int vfs_open(const struct path *, struct file *); * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); -extern void inode_add_lru(struct inode *inode); extern int dentry_needs_remove_privs(struct dentry *dentry); /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 226de651f52e..de35a2640e70 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3193,6 +3193,7 @@ static inline void remove_inode_hash(struct inode *inode) } extern void inode_sb_list_add(struct inode *inode); +extern void inode_add_lru(struct inode *inode); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 62db6b0176b9..5c74a45ff97a 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -23,6 +23,56 @@ static inline bool mapping_empty(struct address_space *mapping) return xa_empty(&mapping->i_pages); } +/* + * mapping_shrinkable - test if page cache state allows inode reclaim + * @mapping: the page cache mapping + * + * This checks the mapping's cache state for the pupose of inode + * reclaim and LRU management. + * + * The caller is expected to hold the i_lock, but is not required to + * hold the i_pages lock, which usually protects cache state. That's + * because the i_lock and the list_lru lock that protect the inode and + * its LRU state don't nest inside the irq-safe i_pages lock. + * + * Cache deletions are performed under the i_lock, which ensures that + * when an inode goes empty, it will reliably get queued on the LRU. + * + * Cache additions do not acquire the i_lock and may race with this + * check, in which case we'll report the inode as shrinkable when it + * has cache pages. This is okay: the shrinker also checks the + * refcount and the referenced bit, which will be elevated or set in + * the process of adding new cache pages to an inode. + */ +static inline bool mapping_shrinkable(struct address_space *mapping) +{ + void *head; + + /* + * On highmem systems, there could be lowmem pressure from the + * inodes before there is highmem pressure from the page + * cache. Make inodes shrinkable regardless of cache state. + */ + if (IS_ENABLED(CONFIG_HIGHMEM)) + return true; + + /* Cache completely empty? Shrink away. */ + head = rcu_access_pointer(mapping->i_pages.xa_head); + if (!head) + return true; + + /* + * The xarray stores single offset-0 entries directly in the + * head pointer, which allows non-resident page cache entries + * to escape the shadow shrinker's list of xarray nodes. The + * inode shrinker needs to pick them up under memory pressure. + */ + if (!xa_is_node(head) && xa_is_value(head)) + return true; + + return false; +} + /* * Bits in mapping->flags. */ diff --git a/mm/filemap.c b/mm/filemap.c index b6140debc2da..06de9a17499f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -262,9 +262,13 @@ void delete_from_page_cache(struct page *page) struct address_space *mapping = page_mapping(page); BUG_ON(!PageLocked(page)); + spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __delete_from_page_cache(page, NULL); xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); page_cache_free_page(mapping, page); } @@ -340,6 +344,7 @@ void delete_from_page_cache_batch(struct address_space *mapping, if (!pagevec_count(pvec)) return; + spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); @@ -348,6 +353,9 @@ void delete_from_page_cache_batch(struct address_space *mapping, } page_cache_delete_batch(mapping, pvec); xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); for (i = 0; i < pagevec_count(pvec); i++) page_cache_free_page(mapping, pvec->pages[i]); diff --git a/mm/truncate.c b/mm/truncate.c index 714eaf19821d..cc83a3f7c1ad 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -45,9 +45,13 @@ static inline void __clear_shadow_entry(struct address_space *mapping, static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { + spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __clear_shadow_entry(mapping, index, entry); xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); } /* @@ -73,8 +77,10 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, return; dax = dax_mapping(mapping); - if (!dax) + if (!dax) { + spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); + } for (i = j; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; @@ -93,8 +99,12 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, __clear_shadow_entry(mapping, index, page); } - if (!dax) + if (!dax) { xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); + } pvec->nr = j; } @@ -567,6 +577,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; + spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); if (PageDirty(page)) goto failed; @@ -574,6 +585,9 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) BUG_ON(page_has_private(page)); __delete_from_page_cache(page, NULL); xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); @@ -582,6 +596,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) return 1; failed: xa_unlock_irq(&mapping->i_pages); + spin_unlock(&mapping->host->i_lock); return 0; } diff --git a/mm/vmscan.c b/mm/vmscan.c index 41f5f6007c30..26f07518d7a4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1190,6 +1190,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); + if (!PageSwapCache(page)) + spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); /* * The non racy check for a busy page. @@ -1258,6 +1260,9 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, shadow = workingset_eviction(page, target_memcg); __delete_from_page_cache(page, shadow); xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); if (freepage != NULL) freepage(page); @@ -1267,6 +1272,8 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, cannot_free: xa_unlock_irq(&mapping->i_pages); + if (!PageSwapCache(page)) + spin_unlock(&mapping->host->i_lock); return 0; } diff --git a/mm/workingset.c b/mm/workingset.c index d5b81e4f4cbe..23df60ce2e10 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -543,6 +543,13 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out; } + if (!spin_trylock(&mapping->host->i_lock)) { + xa_unlock(&mapping->i_pages); + spin_unlock_irq(lru_lock); + ret = LRU_RETRY; + goto out; + } + list_lru_isolate(lru, item); __dec_lruvec_kmem_state(node, WORKINGSET_NODES); @@ -562,6 +569,9 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, out_invalid: xa_unlock_irq(&mapping->i_pages); + if (mapping_shrinkable(mapping)) + inode_add_lru(mapping->host); + spin_unlock(&mapping->host->i_lock); ret = LRU_REMOVED_RETRY; out: cond_resched(); -- cgit v1.2.3 From 83c1fd763b3220458652f7d656d5047292ebcde4 Mon Sep 17 00:00:00 2001 From: zhangyiru Date: Mon, 8 Nov 2021 18:31:27 -0800 Subject: mm,hugetlb: remove mlock ulimit for SHM_HUGETLB Commit 21a3c273f88c ("mm, hugetlb: add thread name and pid to SHM_HUGETLB mlock rlimit warning") marked this as deprecated in 2012, but it is not deleted yet. Mike says he still sees that message in log files on occasion, so maybe we should preserve this warning. Also remove hugetlbfs related user_shm_unlock in ipc/shm.c and remove the user_shm_unlock after out. Link: https://lkml.kernel.org/r/20211103105857.25041-1-zhangyiru3@huawei.com Signed-off-by: zhangyiru Reviewed-by: Mike Kravetz Cc: Hugh Dickins Cc: Liu Zixian Cc: Michal Hocko Cc: wuxu.wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/hugetlbfs/inode.c | 23 ++++++++--------------- include/linux/hugetlb.h | 6 ++---- ipc/shm.c | 8 +------- mm/memfd.c | 4 +--- mm/mmap.c | 3 +-- 5 files changed, 13 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index cdfb1ae78a3f..49d2e686be74 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -1446,8 +1446,8 @@ static int get_hstate_idx(int page_size_log) * otherwise hugetlb_reserve_pages reserves one less hugepages than intended. */ struct file *hugetlb_file_setup(const char *name, size_t size, - vm_flags_t acctflag, struct ucounts **ucounts, - int creat_flags, int page_size_log) + vm_flags_t acctflag, int creat_flags, + int page_size_log) { struct inode *inode; struct vfsmount *mnt; @@ -1458,22 +1458,19 @@ struct file *hugetlb_file_setup(const char *name, size_t size, if (hstate_idx < 0) return ERR_PTR(-ENODEV); - *ucounts = NULL; mnt = hugetlbfs_vfsmount[hstate_idx]; if (!mnt) return ERR_PTR(-ENOENT); if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) { - *ucounts = current_ucounts(); - if (user_shm_lock(size, *ucounts)) { - task_lock(current); - pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is deprecated\n", + struct ucounts *ucounts = current_ucounts(); + + if (user_shm_lock(size, ucounts)) { + pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n", current->comm, current->pid); - task_unlock(current); - } else { - *ucounts = NULL; - return ERR_PTR(-EPERM); + user_shm_unlock(size, ucounts); } + return ERR_PTR(-EPERM); } file = ERR_PTR(-ENOSPC); @@ -1498,10 +1495,6 @@ struct file *hugetlb_file_setup(const char *name, size_t size, iput(inode); out: - if (*ucounts) { - user_shm_unlock(size, *ucounts); - *ucounts = NULL; - } return file; } diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 44c2ab0dfa59..00351ccb49a3 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -477,8 +477,7 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) extern const struct file_operations hugetlbfs_file_operations; extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct, - struct ucounts **ucounts, int creat_flags, - int page_size_log); + int creat_flags, int page_size_log); static inline bool is_file_hugepages(struct file *file) { @@ -497,8 +496,7 @@ static inline struct hstate *hstate_inode(struct inode *i) #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, - struct ucounts **ucounts, int creat_flags, - int page_size_log) + int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } diff --git a/ipc/shm.c b/ipc/shm.c index ab749be6d8b7..4942bdd65748 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -287,9 +287,6 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_ucounts); - else if (shp->mlock_ucounts) - user_shm_unlock(i_size_read(file_inode(shm_file)), - shp->mlock_ucounts); fput(shm_file); ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); @@ -650,8 +647,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (shmflg & SHM_NORESERVE) acctflag = VM_NORESERVE; file = hugetlb_file_setup(name, hugesize, acctflag, - &shp->mlock_ucounts, HUGETLB_SHMFS_INODE, - (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); + HUGETLB_SHMFS_INODE, (shmflg >> SHM_HUGE_SHIFT) & SHM_HUGE_MASK); } else { /* * Do not allow no accounting for OVERCOMMIT_NEVER, even @@ -698,8 +694,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) no_id: ipc_update_pid(&shp->shm_cprid, NULL); ipc_update_pid(&shp->shm_lprid, NULL); - if (is_file_hugepages(file) && shp->mlock_ucounts) - user_shm_unlock(size, shp->mlock_ucounts); fput(file); ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); return error; diff --git a/mm/memfd.c b/mm/memfd.c index 081dd33e6a61..9f80f162791a 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -297,9 +297,7 @@ SYSCALL_DEFINE2(memfd_create, } if (flags & MFD_HUGETLB) { - struct ucounts *ucounts = NULL; - - file = hugetlb_file_setup(name, 0, VM_NORESERVE, &ucounts, + file = hugetlb_file_setup(name, 0, VM_NORESERVE, HUGETLB_ANONHUGE_INODE, (flags >> MFD_HUGE_SHIFT) & MFD_HUGE_MASK); diff --git a/mm/mmap.c b/mm/mmap.c index b22a07f5e761..bfb0ea164a90 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1599,7 +1599,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, goto out_fput; } } else if (flags & MAP_HUGETLB) { - struct ucounts *ucounts = NULL; struct hstate *hs; hs = hstate_sizelog((flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); @@ -1615,7 +1614,7 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len, */ file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, - &ucounts, HUGETLB_ANONHUGE_INODE, + HUGETLB_ANONHUGE_INODE, (flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK); if (IS_ERR(file)) return PTR_ERR(file); -- cgit v1.2.3 From cc5f2704c93456e6f1c671c5cf7b582a55df5484 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 8 Nov 2021 18:31:48 -0800 Subject: proc/vmcore: convert oldmem_pfn_is_ram callback to more generic vmcore callbacks Let's support multiple registered callbacks, making sure that registering vmcore callbacks cannot fail. Make the callback return a bool instead of an int, handling how to deal with errors internally. Drop unused HAVE_OLDMEM_PFN_IS_RAM. We soon want to make use of this infrastructure from other drivers: virtio-mem, registering one callback for each virtio-mem device, to prevent reading unplugged virtio-mem memory. Handle it via a generic vmcore_cb structure, prepared for future extensions: for example, once we support virtio-mem on s390x where the vmcore is completely constructed in the second kernel, we want to detect and add plugged virtio-mem memory ranges to the vmcore in order for them to get dumped properly. Handle corner cases that are unexpected and shouldn't happen in sane setups: registering a callback after the vmcore has already been opened (warn only) and unregistering a callback after the vmcore has already been opened (warn and essentially read only zeroes from that point on). Link: https://lkml.kernel.org/r/20211005121430.30136-6-david@redhat.com Signed-off-by: David Hildenbrand Cc: Baoquan He Cc: Borislav Petkov Cc: Boris Ostrovsky Cc: Dave Young Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Juergen Gross Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: Stefano Stabellini Cc: Thomas Gleixner Cc: Vivek Goyal Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/aperture_64.c | 13 +++++- arch/x86/xen/mmu_hvm.c | 11 +++-- fs/proc/vmcore.c | 99 ++++++++++++++++++++++++++++++------------- include/linux/crash_dump.h | 26 ++++++++++-- 4 files changed, 111 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 10562885f5fc..af3ba08b684b 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -73,12 +73,23 @@ static int gart_mem_pfn_is_ram(unsigned long pfn) (pfn >= aperture_pfn_start + aperture_page_count)); } +#ifdef CONFIG_PROC_VMCORE +static bool gart_oldmem_pfn_is_ram(struct vmcore_cb *cb, unsigned long pfn) +{ + return !!gart_mem_pfn_is_ram(pfn); +} + +static struct vmcore_cb gart_vmcore_cb = { + .pfn_is_ram = gart_oldmem_pfn_is_ram, +}; +#endif + static void __init exclude_from_core(u64 aper_base, u32 aper_order) { aperture_pfn_start = aper_base >> PAGE_SHIFT; aperture_page_count = (32 * 1024 * 1024) << aper_order >> PAGE_SHIFT; #ifdef CONFIG_PROC_VMCORE - WARN_ON(register_oldmem_pfn_is_ram(&gart_mem_pfn_is_ram)); + register_vmcore_cb(&gart_vmcore_cb); #endif #ifdef CONFIG_PROC_KCORE WARN_ON(register_mem_pfn_is_ram(&gart_mem_pfn_is_ram)); diff --git a/arch/x86/xen/mmu_hvm.c b/arch/x86/xen/mmu_hvm.c index 6ba8826dcdcc..509bdee3ab90 100644 --- a/arch/x86/xen/mmu_hvm.c +++ b/arch/x86/xen/mmu_hvm.c @@ -12,10 +12,10 @@ * The kdump kernel has to check whether a pfn of the crashed kernel * was a ballooned page. vmcore is using this function to decide * whether to access a pfn of the crashed kernel. - * Returns 0 if the pfn is not backed by a RAM page, the caller may + * Returns "false" if the pfn is not backed by a RAM page, the caller may * handle the pfn special in this case. */ -static int xen_oldmem_pfn_is_ram(unsigned long pfn) +static bool xen_vmcore_pfn_is_ram(struct vmcore_cb *cb, unsigned long pfn) { struct xen_hvm_get_mem_type a = { .domid = DOMID_SELF, @@ -24,10 +24,13 @@ static int xen_oldmem_pfn_is_ram(unsigned long pfn) if (HYPERVISOR_hvm_op(HVMOP_get_mem_type, &a)) { pr_warn_once("Unexpected HVMOP_get_mem_type failure\n"); - return -ENXIO; + return true; } return a.mem_type != HVMMEM_mmio_dm; } +static struct vmcore_cb xen_vmcore_cb = { + .pfn_is_ram = xen_vmcore_pfn_is_ram, +}; #endif static void xen_hvm_exit_mmap(struct mm_struct *mm) @@ -61,6 +64,6 @@ void __init xen_hvm_init_mmu_ops(void) if (is_pagetable_dying_supported()) pv_ops.mmu.exit_mmap = xen_hvm_exit_mmap; #ifdef CONFIG_PROC_VMCORE - WARN_ON(register_oldmem_pfn_is_ram(&xen_oldmem_pfn_is_ram)); + register_vmcore_cb(&xen_vmcore_cb); #endif } diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index a9bd80ab670e..7a04b2eca287 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -62,46 +62,75 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0); /* Device Dump Size */ static size_t vmcoredd_orig_sz; -/* - * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error - * The called function has to take care of module refcounting. - */ -static int (*oldmem_pfn_is_ram)(unsigned long pfn); - -int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)) +static DECLARE_RWSEM(vmcore_cb_rwsem); +/* List of registered vmcore callbacks. */ +static LIST_HEAD(vmcore_cb_list); +/* Whether we had a surprise unregistration of a callback. */ +static bool vmcore_cb_unstable; +/* Whether the vmcore has been opened once. */ +static bool vmcore_opened; + +void register_vmcore_cb(struct vmcore_cb *cb) { - if (oldmem_pfn_is_ram) - return -EBUSY; - oldmem_pfn_is_ram = fn; - return 0; + down_write(&vmcore_cb_rwsem); + INIT_LIST_HEAD(&cb->next); + list_add_tail(&cb->next, &vmcore_cb_list); + /* + * Registering a vmcore callback after the vmcore was opened is + * very unusual (e.g., manual driver loading). + */ + if (vmcore_opened) + pr_warn_once("Unexpected vmcore callback registration\n"); + up_write(&vmcore_cb_rwsem); } -EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram); +EXPORT_SYMBOL_GPL(register_vmcore_cb); -void unregister_oldmem_pfn_is_ram(void) +void unregister_vmcore_cb(struct vmcore_cb *cb) { - oldmem_pfn_is_ram = NULL; - wmb(); + down_write(&vmcore_cb_rwsem); + list_del(&cb->next); + /* + * Unregistering a vmcore callback after the vmcore was opened is + * very unusual (e.g., forced driver removal), but we cannot stop + * unregistering. + */ + if (vmcore_opened) { + pr_warn_once("Unexpected vmcore callback unregistration\n"); + vmcore_cb_unstable = true; + } + up_write(&vmcore_cb_rwsem); } -EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram); +EXPORT_SYMBOL_GPL(unregister_vmcore_cb); static bool pfn_is_ram(unsigned long pfn) { - int (*fn)(unsigned long pfn); - /* pfn is ram unless fn() checks pagetype */ + struct vmcore_cb *cb; bool ret = true; - /* - * Ask hypervisor if the pfn is really ram. - * A ballooned page contains no data and reading from such a page - * will cause high load in the hypervisor. - */ - fn = oldmem_pfn_is_ram; - if (fn) - ret = !!fn(pfn); + lockdep_assert_held_read(&vmcore_cb_rwsem); + if (unlikely(vmcore_cb_unstable)) + return false; + + list_for_each_entry(cb, &vmcore_cb_list, next) { + if (unlikely(!cb->pfn_is_ram)) + continue; + ret = cb->pfn_is_ram(cb, pfn); + if (!ret) + break; + } return ret; } +static int open_vmcore(struct inode *inode, struct file *file) +{ + down_read(&vmcore_cb_rwsem); + vmcore_opened = true; + up_read(&vmcore_cb_rwsem); + + return 0; +} + /* Reads a page from the oldmem device from given offset. */ ssize_t read_from_oldmem(char *buf, size_t count, u64 *ppos, int userbuf, @@ -117,6 +146,7 @@ ssize_t read_from_oldmem(char *buf, size_t count, offset = (unsigned long)(*ppos % PAGE_SIZE); pfn = (unsigned long)(*ppos / PAGE_SIZE); + down_read(&vmcore_cb_rwsem); do { if (count > (PAGE_SIZE - offset)) nr_bytes = PAGE_SIZE - offset; @@ -136,8 +166,10 @@ ssize_t read_from_oldmem(char *buf, size_t count, tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf); - if (tmp < 0) + if (tmp < 0) { + up_read(&vmcore_cb_rwsem); return tmp; + } } *ppos += nr_bytes; count -= nr_bytes; @@ -147,6 +179,7 @@ ssize_t read_from_oldmem(char *buf, size_t count, offset = 0; } while (count); + up_read(&vmcore_cb_rwsem); return read; } @@ -537,14 +570,19 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma, unsigned long from, unsigned long pfn, unsigned long size, pgprot_t prot) { + int ret; + /* * Check if oldmem_pfn_is_ram was registered to avoid * looping over all pages without a reason. */ - if (oldmem_pfn_is_ram) - return remap_oldmem_pfn_checked(vma, from, pfn, size, prot); + down_read(&vmcore_cb_rwsem); + if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable) + ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot); else - return remap_oldmem_pfn_range(vma, from, pfn, size, prot); + ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot); + up_read(&vmcore_cb_rwsem); + return ret; } static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) @@ -668,6 +706,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma) #endif static const struct proc_ops vmcore_proc_ops = { + .proc_open = open_vmcore, .proc_read = read_vmcore, .proc_lseek = default_llseek, .proc_mmap = mmap_vmcore, diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 2618577a4d6d..0c547d866f1e 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -91,9 +91,29 @@ static inline void vmcore_unusable(void) elfcorehdr_addr = ELFCORE_ADDR_ERR; } -#define HAVE_OLDMEM_PFN_IS_RAM 1 -extern int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)); -extern void unregister_oldmem_pfn_is_ram(void); +/** + * struct vmcore_cb - driver callbacks for /proc/vmcore handling + * @pfn_is_ram: check whether a PFN really is RAM and should be accessed when + * reading the vmcore. Will return "true" if it is RAM or if the + * callback cannot tell. If any callback returns "false", it's not + * RAM and the page must not be accessed; zeroes should be + * indicated in the vmcore instead. For example, a ballooned page + * contains no data and reading from such a page will cause high + * load in the hypervisor. + * @next: List head to manage registered callbacks internally; initialized by + * register_vmcore_cb(). + * + * vmcore callbacks allow drivers managing physical memory ranges to + * coordinate with vmcore handling code, for example, to prevent accessing + * physical memory ranges that should not be accessed when reading the vmcore, + * although included in the vmcore header as memory ranges to dump. + */ +struct vmcore_cb { + bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn); + struct list_head next; +}; +extern void register_vmcore_cb(struct vmcore_cb *cb); +extern void unregister_vmcore_cb(struct vmcore_cb *cb); #else /* !CONFIG_CRASH_DUMP */ static inline bool is_kdump_kernel(void) { return 0; } -- cgit v1.2.3 From f5d80614844a725cbf66fd6524e01c218ede2141 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:08 -0800 Subject: kernel.h: drop unneeded inclusion from other headers Patch series "kernel.h further split", v5. kernel.h is a set of something which is not related to each other and often used in non-crossed compilation units, especially when drivers need only one or two macro definitions from it. This patch (of 7): There is no evidence we need kernel.h inclusion in certain headers. Drop unneeded inclusion from other headers. [sfr@canb.auug.org.au: bottom_half.h needs kernel] Link: https://lkml.kernel.org/r/20211015202908.1c417ae2@canb.auug.org.au Link: https://lkml.kernel.org/r/20211013170417.87909-1-andriy.shevchenko@linux.intel.com Link: https://lkml.kernel.org/r/20211013170417.87909-2-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Stephen Rothwell Cc: Thomas Gleixner Cc: Brendan Higgins Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Will Deacon Cc: Waiman Long Cc: Boqun Feng Cc: Sakari Ailus Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Jonathan Cameron Cc: Rasmus Villemoes Cc: Thorsten Leemhuis Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bottom_half.h | 1 + include/linux/rwsem.h | 1 - include/linux/smp.h | 1 - include/linux/spinlock.h | 1 - 4 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index eed86eb0a1de..11d107d88d03 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,6 +2,7 @@ #ifndef _LINUX_BH_H #define _LINUX_BH_H +#include #include #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 352c6127cb90..f9348769e558 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -11,7 +11,6 @@ #include #include -#include #include #include #include diff --git a/include/linux/smp.h b/include/linux/smp.h index 510519e8a1eb..a80ab58ae3f1 100644 --- a/include/linux/smp.h +++ b/include/linux/smp.h @@ -108,7 +108,6 @@ static inline void on_each_cpu_cond(smp_cond_func_t cond_func, #ifdef CONFIG_SMP #include -#include #include #include #include diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 45310ea1b1d7..22d672f81705 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From d2a8ebbf8192b84b11f1b204c4f7c602df32aeac Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:12 -0800 Subject: kernel.h: split out container_of() and typeof_member() macros kernel.h is being used as a dump for all kinds of stuff for a long time. Here is the attempt cleaning it up by splitting out container_of() and typeof_member() macros. For time being include new header back to kernel.h to avoid twisted indirected includes for existing users. Note, there are _a lot_ of headers and modules that include kernel.h solely for one of these macros and this allows to unburden compiler for the twisted inclusion paths and to make new code cleaner in the future. Link: https://lkml.kernel.org/r/20211013170417.87909-3-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/container_of.h | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/kernel.h | 33 +-------------------------------- 2 files changed, 41 insertions(+), 32 deletions(-) create mode 100644 include/linux/container_of.h (limited to 'include/linux') diff --git a/include/linux/container_of.h b/include/linux/container_of.h new file mode 100644 index 000000000000..dd56019838c6 --- /dev/null +++ b/include/linux/container_of.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CONTAINER_OF_H +#define _LINUX_CONTAINER_OF_H + +#include +#include + +#define typeof_member(T, m) typeof(((T*)0)->m) + +/** + * container_of - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + */ +#define container_of(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + ((type *)(__mptr - offsetof(type, member))); }) + +/** + * container_of_safe - cast a member of a structure out to the containing structure + * @ptr: the pointer to the member. + * @type: the type of the container struct this is embedded in. + * @member: the name of the member within the struct. + * + * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. + */ +#define container_of_safe(ptr, type, member) ({ \ + void *__mptr = (void *)(ptr); \ + BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ + !__same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ + IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ + ((type *)(__mptr - offsetof(type, member))); }) + +#endif /* _LINUX_CONTAINER_OF_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 471bc0593679..ed4465757cec 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -52,8 +53,6 @@ } \ ) -#define typeof_member(T, m) typeof(((T*)0)->m) - #define _RET_IP_ (unsigned long)__builtin_return_address(0) #define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) @@ -484,36 +483,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } #define __CONCAT(a, b) a ## b #define CONCATENATE(a, b) __CONCAT(a, b) -/** - * container_of - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - */ -#define container_of(ptr, type, member) ({ \ - void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ - ((type *)(__mptr - offsetof(type, member))); }) - -/** - * container_of_safe - cast a member of a structure out to the containing structure - * @ptr: the pointer to the member. - * @type: the type of the container struct this is embedded in. - * @member: the name of the member within the struct. - * - * If IS_ERR_OR_NULL(ptr), ptr is returned unchanged. - */ -#define container_of_safe(ptr, type, member) ({ \ - void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ - IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ - ((type *)(__mptr - offsetof(type, member))); }) - /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.2.3 From cd7187e112c91186185c0553b1f9d033ed399d3a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:19 -0800 Subject: include/linux/list.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211013170417.87909-5-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index f2af4b4aa4e9..6636fc07f918 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -2,11 +2,13 @@ #ifndef _LINUX_LIST_H #define _LINUX_LIST_H +#include #include #include #include #include -#include + +#include /* * Circular doubly linked list implementation. -- cgit v1.2.3 From 50b09d6145da04e19fa448670e4918ce496f1c77 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:22 -0800 Subject: include/linux/llist.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211013170417.87909-6-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/llist.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/llist.h b/include/linux/llist.h index 24f207b0190b..85bda2d02d65 100644 --- a/include/linux/llist.h +++ b/include/linux/llist.h @@ -49,7 +49,9 @@ */ #include -#include +#include +#include +#include struct llist_head { struct llist_node *first; -- cgit v1.2.3 From c540f9595956ff3c4b2cca1145c893941f921bcd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:25 -0800 Subject: include/linux/plist.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211013170417.87909-7-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Boqun Feng Cc: Brendan Higgins Cc: Ingo Molnar Cc: Jonathan Cameron Cc: Laurent Pinchart Cc: Mauro Carvalho Chehab Cc: Miguel Ojeda Cc: Peter Zijlstra Cc: Rasmus Villemoes Cc: Sakari Ailus Cc: Thomas Gleixner Cc: Thorsten Leemhuis Cc: Waiman Long Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/plist.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/plist.h b/include/linux/plist.h index 66bab1bca35c..0f352c1d3c80 100644 --- a/include/linux/plist.h +++ b/include/linux/plist.h @@ -73,8 +73,11 @@ #ifndef _LINUX_PLIST_H_ #define _LINUX_PLIST_H_ -#include +#include #include +#include + +#include struct plist_head { struct list_head node_list; -- cgit v1.2.3 From 5f6286a608107a68646241b57d2bd2a4fc139ef9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:32 -0800 Subject: include/linux/delay.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. [akpm@linux-foundation.org: cxd2880_common.h needs bits.h for GENMASK()] [andriy.shevchenko@linux.intel.com: delay.h: fix for removed kernel.h] Link: https://lkml.kernel.org/r/20211028170143.56523-1-andriy.shevchenko@linux.intel.com [akpm@linux-foundation.org: include/linux/fwnode.h needs bits.h for BIT()] Link: https://lkml.kernel.org/r/20211027150324.79827-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/riscv/lib/delay.c | 4 ++++ arch/s390/include/asm/facility.h | 4 ++++ drivers/media/dvb-frontends/cxd2880/cxd2880_common.h | 1 + include/linux/delay.h | 2 +- include/linux/fwnode.h | 1 + 5 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c index f51c9a03bca1..49d510ba75fd 100644 --- a/arch/riscv/lib/delay.c +++ b/arch/riscv/lib/delay.c @@ -4,10 +4,14 @@ */ #include +#include #include #include +#include #include +#include + /* * This is copies from arch/arm/include/asm/delay.h * diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index e3aa354ab9f4..94b6919026df 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -9,8 +9,12 @@ #define __ASM_FACILITY_H #include + +#include #include +#include #include + #include #define MAX_FACILITY_BIT (sizeof(stfle_fac_list) * 8) diff --git a/drivers/media/dvb-frontends/cxd2880/cxd2880_common.h b/drivers/media/dvb-frontends/cxd2880/cxd2880_common.h index b05bce71ab35..9dc15a5a9683 100644 --- a/drivers/media/dvb-frontends/cxd2880/cxd2880_common.h +++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_common.h @@ -12,6 +12,7 @@ #include #include #include +#include #include int cxd2880_convert2s_complement(u32 value, u32 bitlen); diff --git a/include/linux/delay.h b/include/linux/delay.h index 1d0e2ce6b6d9..8eacf67eb212 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -19,7 +19,7 @@ * https://lists.openwall.net/linux-kernel/2011/01/09/56 */ -#include +#include extern unsigned long loops_per_jiffy; diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 9f4ad719bfe3..3a532ba66f6c 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -11,6 +11,7 @@ #include #include +#include #include struct fwnode_operations; -- cgit v1.2.3 From 1fcbd5deac51f30a7ed3f10bea422d08a2b3aba6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:35 -0800 Subject: include/linux/sbitmap.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211027150437.79921-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sbitmap.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 2713e689ad66..8121034d1f13 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -9,8 +9,17 @@ #ifndef __LINUX_SCALE_BITMAP_H #define __LINUX_SCALE_BITMAP_H -#include +#include +#include +#include +#include +#include +#include +#include #include +#include +#include +#include struct seq_file; -- cgit v1.2.3 From 98e1385ef24bd607586fbf44e73decd5112d3d4a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:38 -0800 Subject: include/linux/radix-tree.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Link: https://lkml.kernel.org/r/20211027150528.80003-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/radix-tree.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 64ad900ac742..f7c1d21c2f39 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -9,8 +9,10 @@ #define _LINUX_RADIX_TREE_H #include -#include +#include #include +#include +#include #include #include #include -- cgit v1.2.3 From b4b87651104dd32ab258d097d47b97e243a95222 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:32:41 -0800 Subject: include/linux/generic-radix-tree.h: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. [akpm@linux-foundation.org: include math.h for round_up()] Link: https://lkml.kernel.org/r/20211027150548.80042-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/generic-radix-tree.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h index bfd00320c7f3..107613f7d792 100644 --- a/include/linux/generic-radix-tree.h +++ b/include/linux/generic-radix-tree.h @@ -38,8 +38,9 @@ #include #include -#include #include +#include +#include struct genradix_root; -- cgit v1.2.3 From e52340de11d8bca3ba35e5a72fea4f2a5b6abbbb Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Mon, 8 Nov 2021 18:32:43 -0800 Subject: kernel.h: split out instruction pointer accessors bottom_half.h needs _THIS_IP_ to be standalone, so split that and _RET_IP_ out from kernel.h into the new instruction_pointer.h. kernel.h directly needs them, so include it there and replace the include of kernel.h with this new file in bottom_half.h. Link: https://lkml.kernel.org/r/20211028161248.45232-1-andriy.shevchenko@linux.intel.com Signed-off-by: Stephen Rothwell Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bottom_half.h | 2 +- include/linux/instruction_pointer.h | 8 ++++++++ include/linux/kernel.h | 4 +--- 3 files changed, 10 insertions(+), 4 deletions(-) create mode 100644 include/linux/instruction_pointer.h (limited to 'include/linux') diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h index 11d107d88d03..fc53e0ad56d9 100644 --- a/include/linux/bottom_half.h +++ b/include/linux/bottom_half.h @@ -2,7 +2,7 @@ #ifndef _LINUX_BH_H #define _LINUX_BH_H -#include +#include #include #if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS) diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h new file mode 100644 index 000000000000..cda1f706eaeb --- /dev/null +++ b/include/linux/instruction_pointer.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_INSTRUCTION_POINTER_H +#define _LINUX_INSTRUCTION_POINTER_H + +#define _RET_IP_ (unsigned long)__builtin_return_address(0) +#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) + +#endif /* _LINUX_INSTRUCTION_POINTER_H */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index ed4465757cec..46ca4404fb93 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -53,9 +54,6 @@ } \ ) -#define _RET_IP_ (unsigned long)__builtin_return_address(0) -#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; }) - /** * upper_32_bits - return bits 32-63 of a number * @n: the number we're accessing -- cgit v1.2.3 From e1edc277e6f6dfb372216522dfc57f9381c39e35 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 8 Nov 2021 18:32:46 -0800 Subject: linux/container_of.h: switch to static_assert _Static_assert() is evaluated already in the compiler's frontend, and gives a somehat more to-the-point error, compared to the BUILD_BUG_ON macro, which only fires after the optimizer has had a chance to eliminate calls to functions marked with __attribute__((error)). In theory, this might make builds a tiny bit faster. There's also a little less gunk in the error message emitted: lib/sort.c: In function `foo': include/linux/build_bug.h:78:41: error: static assertion failed: "pointer type mismatch in container_of()" 78 | #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) compared to lib/sort.c: In function `foo': include/linux/compiler_types.h:322:38: error: call to `__compiletime_assert_2' declared with attribute error: pointer type mismatch in container_of() 322 | _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) While at it, fix the copy-pasto in container_of_safe(). Link: https://lkml.kernel.org/r/20211015090530.2774079-1-linux@rasmusvillemoes.dk Link: https://lore.kernel.org/lkml/20211014132331.GA4811@kernel.org/T/ Signed-off-by: Rasmus Villemoes Reviewed-by: Miguel Ojeda Acked-by: Andy Shevchenko Reviewed-by: Nick Desaulniers Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/container_of.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/container_of.h b/include/linux/container_of.h index dd56019838c6..2f4944b791b8 100644 --- a/include/linux/container_of.h +++ b/include/linux/container_of.h @@ -16,9 +16,9 @@ */ #define container_of(ptr, type, member) ({ \ void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ + static_assert(__same_type(*(ptr), ((type *)0)->member) || \ + __same_type(*(ptr), void), \ + "pointer type mismatch in container_of()"); \ ((type *)(__mptr - offsetof(type, member))); }) /** @@ -31,9 +31,9 @@ */ #define container_of_safe(ptr, type, member) ({ \ void *__mptr = (void *)(ptr); \ - BUILD_BUG_ON_MSG(!__same_type(*(ptr), ((type *)0)->member) && \ - !__same_type(*(ptr), void), \ - "pointer type mismatch in container_of()"); \ + static_assert(__same_type(*(ptr), ((type *)0)->member) || \ + __same_type(*(ptr), void), \ + "pointer type mismatch in container_of_safe()"); \ IS_ERR_OR_NULL(__mptr) ? ERR_CAST(__mptr) : \ ((type *)(__mptr - offsetof(type, member))); }) -- cgit v1.2.3 From 505be48165fa2f2cb795659b4fc61f35563d105e Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Mon, 8 Nov 2021 18:33:12 -0800 Subject: lib, stackdepot: add helper to print stack entries To print a stack entries, users of stackdepot, first use stack_depot_fetch to get a list of stack entries and then use stack_trace_print to print this list. Provide a helper in stackdepot to print stack entries based on stackdepot handle. Also change above mentioned users to use this helper. Link: https://lkml.kernel.org/r/20210915014806.3206938-3-imran.f.khan@oracle.com Signed-off-by: Imran Khan Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Reviewed-by: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Daniel Vetter Cc: David Airlie Cc: Dmitry Vyukov Cc: Geert Uytterhoeven Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackdepot.h | 2 ++ lib/stackdepot.c | 18 ++++++++++++++++++ mm/kasan/report.c | 15 +++------------ mm/page_owner.c | 13 ++++--------- 4 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index d29860966bc9..8ab37500fcba 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,6 +25,8 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +void stack_depot_print(depot_stack_handle_t stack); + #ifdef CONFIG_STACKDEPOT int stack_depot_init(void); #else diff --git a/lib/stackdepot.c b/lib/stackdepot.c index f034f095c627..4e1f2982d0fa 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -213,6 +213,24 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } +/** + * stack_depot_print - print stack entries from a depot + * + * @stack: Stack depot handle which was returned from + * stack_depot_save(). + * + */ +void stack_depot_print(depot_stack_handle_t stack) +{ + unsigned long *entries; + unsigned int nr_entries; + + nr_entries = stack_depot_fetch(stack, &entries); + if (nr_entries > 0) + stack_trace_print(entries, nr_entries, 0); +} +EXPORT_SYMBOL_GPL(stack_depot_print); + /** * stack_depot_fetch - Fetch stack entries from a depot * diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 884a950c7026..3239fd8f8747 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -132,20 +132,11 @@ static void end_report(unsigned long *flags, unsigned long addr) kasan_enable_current(); } -static void print_stack(depot_stack_handle_t stack) -{ - unsigned long *entries; - unsigned int nr_entries; - - nr_entries = stack_depot_fetch(stack, &entries); - stack_trace_print(entries, nr_entries, 0); -} - static void print_track(struct kasan_track *track, const char *prefix) { pr_err("%s by task %u:\n", prefix, track->pid); if (track->stack) { - print_stack(track->stack); + stack_depot_print(track->stack); } else { pr_err("(stack is not available)\n"); } @@ -214,12 +205,12 @@ static void describe_object_stacks(struct kmem_cache *cache, void *object, return; if (alloc_meta->aux_stack[0]) { pr_err("Last potentially related work creation:\n"); - print_stack(alloc_meta->aux_stack[0]); + stack_depot_print(alloc_meta->aux_stack[0]); pr_err("\n"); } if (alloc_meta->aux_stack[1]) { pr_err("Second to last potentially related work creation:\n"); - print_stack(alloc_meta->aux_stack[1]); + stack_depot_print(alloc_meta->aux_stack[1]); pr_err("\n"); } #endif diff --git a/mm/page_owner.c b/mm/page_owner.c index 62402d22539b..eff29be1218b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -394,8 +394,6 @@ void __dump_page_owner(const struct page *page) struct page_ext *page_ext = lookup_page_ext(page); struct page_owner *page_owner; depot_stack_handle_t handle; - unsigned long *entries; - unsigned int nr_entries; gfp_t gfp_mask; int mt; @@ -423,20 +421,17 @@ void __dump_page_owner(const struct page *page) page_owner->pid, page_owner->ts_nsec, page_owner->free_ts_nsec); handle = READ_ONCE(page_owner->handle); - if (!handle) { + if (!handle) pr_alert("page_owner allocation stack trace missing\n"); - } else { - nr_entries = stack_depot_fetch(handle, &entries); - stack_trace_print(entries, nr_entries, 0); - } + else + stack_depot_print(handle); handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); } else { - nr_entries = stack_depot_fetch(handle, &entries); pr_alert("page last free stack trace:\n"); - stack_trace_print(entries, nr_entries, 0); + stack_depot_print(handle); } if (page_owner->last_migrate_reason != -1) -- cgit v1.2.3 From 0f68d45ef41abb618a9ca33996348ae73800a106 Mon Sep 17 00:00:00 2001 From: Imran Khan Date: Mon, 8 Nov 2021 18:33:16 -0800 Subject: lib, stackdepot: add helper to print stack entries into buffer To print stack entries into a buffer, users of stackdepot, first get a list of stack entries using stack_depot_fetch and then print this list into a buffer using stack_trace_snprint. Provide a helper in stackdepot for this purpose. Also change above mentioned users to use this helper. [imran.f.khan@oracle.com: fix build error] Link: https://lkml.kernel.org/r/20210915175321.3472770-4-imran.f.khan@oracle.com [imran.f.khan@oracle.com: export stack_depot_snprint() to modules] Link: https://lkml.kernel.org/r/20210916133535.3592491-4-imran.f.khan@oracle.com Link: https://lkml.kernel.org/r/20210915014806.3206938-4-imran.f.khan@oracle.com Signed-off-by: Imran Khan Suggested-by: Vlastimil Babka Acked-by: Vlastimil Babka Acked-by: Jani Nikula [i915] Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Daniel Vetter Cc: David Airlie Cc: Dmitry Vyukov Cc: Geert Uytterhoeven Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_dp_mst_topology.c | 5 +---- drivers/gpu/drm/drm_mm.c | 5 +---- drivers/gpu/drm/i915/i915_vma.c | 5 +---- drivers/gpu/drm/i915/intel_runtime_pm.c | 20 +++++--------------- include/linux/stackdepot.h | 3 +++ lib/stackdepot.c | 25 +++++++++++++++++++++++++ mm/page_owner.c | 5 +---- 7 files changed, 37 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 86d13d6bc463..2d1adab9e360 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1668,13 +1668,10 @@ __dump_topology_ref_history(struct drm_dp_mst_topology_ref_history *history, for (i = 0; i < history->len; i++) { const struct drm_dp_mst_topology_ref_entry *entry = &history->entries[i]; - ulong *entries; - uint nr_entries; u64 ts_nsec = entry->ts_nsec; u32 rem_nsec = do_div(ts_nsec, 1000000000); - nr_entries = stack_depot_fetch(entry->backtrace, &entries); - stack_trace_snprint(buf, PAGE_SIZE, entries, nr_entries, 4); + stack_depot_snprint(entry->backtrace, buf, PAGE_SIZE, 4); drm_printf(&p, " %d %ss (last at %5llu.%06u):\n%s", entry->count, diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 93d48a6f04ab..7d1c578388d3 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -118,8 +118,6 @@ static noinline void save_stack(struct drm_mm_node *node) static void show_leaks(struct drm_mm *mm) { struct drm_mm_node *node; - unsigned long *entries; - unsigned int nr_entries; char *buf; buf = kmalloc(BUFSZ, GFP_KERNEL); @@ -133,8 +131,7 @@ static void show_leaks(struct drm_mm *mm) continue; } - nr_entries = stack_depot_fetch(node->stack, &entries); - stack_trace_snprint(buf, BUFSZ, entries, nr_entries, 0); + stack_depot_snprint(node->stack, buf, BUFSZ, 0); DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s", node->start, node->size, buf); } diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 4b7fc4647e46..f2d9ed375109 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -56,8 +56,6 @@ void i915_vma_free(struct i915_vma *vma) static void vma_print_allocator(struct i915_vma *vma, const char *reason) { - unsigned long *entries; - unsigned int nr_entries; char buf[512]; if (!vma->node.stack) { @@ -66,8 +64,7 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason) return; } - nr_entries = stack_depot_fetch(vma->node.stack, &entries); - stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0); + stack_depot_snprint(vma->node.stack, buf, sizeof(buf), 0); DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n", vma->node.start, vma->node.size, reason, buf); } diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index eaf7688f517d..0d85f3c5c526 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -65,16 +65,6 @@ static noinline depot_stack_handle_t __save_depot_stack(void) return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN); } -static void __print_depot_stack(depot_stack_handle_t stack, - char *buf, int sz, int indent) -{ - unsigned long *entries; - unsigned int nr_entries; - - nr_entries = stack_depot_fetch(stack, &entries); - stack_trace_snprint(buf, sz, entries, nr_entries, indent); -} - static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm) { spin_lock_init(&rpm->debug.lock); @@ -146,12 +136,12 @@ static void untrack_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm, if (!buf) return; - __print_depot_stack(stack, buf, PAGE_SIZE, 2); + stack_depot_snprint(stack, buf, PAGE_SIZE, 2); DRM_DEBUG_DRIVER("wakeref %x from\n%s", stack, buf); stack = READ_ONCE(rpm->debug.last_release); if (stack) { - __print_depot_stack(stack, buf, PAGE_SIZE, 2); + stack_depot_snprint(stack, buf, PAGE_SIZE, 2); DRM_DEBUG_DRIVER("wakeref last released at\n%s", buf); } @@ -183,12 +173,12 @@ __print_intel_runtime_pm_wakeref(struct drm_printer *p, return; if (dbg->last_acquire) { - __print_depot_stack(dbg->last_acquire, buf, PAGE_SIZE, 2); + stack_depot_snprint(dbg->last_acquire, buf, PAGE_SIZE, 2); drm_printf(p, "Wakeref last acquired:\n%s", buf); } if (dbg->last_release) { - __print_depot_stack(dbg->last_release, buf, PAGE_SIZE, 2); + stack_depot_snprint(dbg->last_release, buf, PAGE_SIZE, 2); drm_printf(p, "Wakeref last released:\n%s", buf); } @@ -203,7 +193,7 @@ __print_intel_runtime_pm_wakeref(struct drm_printer *p, rep = 1; while (i + 1 < dbg->count && dbg->owners[i + 1] == stack) rep++, i++; - __print_depot_stack(stack, buf, PAGE_SIZE, 2); + stack_depot_snprint(stack, buf, PAGE_SIZE, 2); drm_printf(p, "Wakeref x%lu taken at:\n%s", rep, buf); } diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 8ab37500fcba..c34b55a6e554 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -25,6 +25,9 @@ depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); +int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, + int spaces); + void stack_depot_print(depot_stack_handle_t stack); #ifdef CONFIG_STACKDEPOT diff --git a/lib/stackdepot.c b/lib/stackdepot.c index 4e1f2982d0fa..b437ae79aca1 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -213,6 +213,31 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } +/** + * stack_depot_snprint - print stack entries from a depot into a buffer + * + * @handle: Stack depot handle which was returned from + * stack_depot_save(). + * @buf: Pointer to the print buffer + * + * @size: Size of the print buffer + * + * @spaces: Number of leading spaces to print + * + * Return: Number of bytes printed. + */ +int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, + int spaces) +{ + unsigned long *entries; + unsigned int nr_entries; + + nr_entries = stack_depot_fetch(handle, &entries); + return nr_entries ? stack_trace_snprint(buf, size, entries, nr_entries, + spaces) : 0; +} +EXPORT_SYMBOL_GPL(stack_depot_snprint); + /** * stack_depot_print - print stack entries from a depot * diff --git a/mm/page_owner.c b/mm/page_owner.c index eff29be1218b..1653040d1133 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -329,8 +329,6 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, depot_stack_handle_t handle) { int ret, pageblock_mt, page_mt; - unsigned long *entries; - unsigned int nr_entries; char *kbuf; count = min_t(size_t, count, PAGE_SIZE); @@ -361,8 +359,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, if (ret >= count) goto err; - nr_entries = stack_depot_fetch(handle, &entries); - ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0); + ret += stack_depot_snprint(handle, kbuf + ret, count - ret, 0); if (ret >= count) goto err; -- cgit v1.2.3 From bfb3ba32061da1a9217ef6d02fbcffb528e4c8df Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Mon, 8 Nov 2021 18:33:19 -0800 Subject: include/linux/string_helpers.h: add linux/string.h for strlen() linux/string_helpers.h uses strlen(), so include the correponding header. Otherwise we get a compilation error if it's not also included by whoever included the helper. Link: https://lkml.kernel.org/r/20211005212634.3223113-1-lucas.demarchi@intel.com Signed-off-by: Lucas De Marchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string_helpers.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 68189c4a2eb1..4ba39e1403b2 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -4,6 +4,7 @@ #include #include +#include #include struct file; -- cgit v1.2.3 From 1b1ad288b8f1b11f83396e537003722897ecc12b Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:43 -0800 Subject: kallsyms: remove arch specific text and data check Patch series "sections: Unify kernel sections range check and use", v4. There are three head files(kallsyms.h, kernel.h and sections.h) which include the kernel sections range check, let's make some cleanup and unify them. 1. cleanup arch specific text/data check and fix address boundary check in kallsyms.h 2. make all the basic/core kernel range check function into sections.h 3. update all the callers, and use the helper in sections.h to simplify the code After this series, we have 5 APIs about kernel sections range check in sections.h * is_kernel_rodata() --- already in sections.h * is_kernel_core_data() --- come from core_kernel_data() in kernel.h * is_kernel_inittext() --- come from kernel.h and kallsyms.h * __is_kernel_text() --- add new internal helper * __is_kernel() --- add new internal helper Note: For the last two helpers, people should not use directly, consider to use corresponding function in kallsyms.h. This patch (of 11): Remove arch specific text and data check after commit 4ba66a976072 ("arch: remove blackfin port"), no need arch-specific text/data check. Link: https://lkml.kernel.org/r/20210930071143.63410-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20210930071143.63410-2-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Steven Rostedt Cc: Ingo Molnar Cc: David S. Miller Cc: Alexei Starovoitov Cc: Andrey Ryabinin Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Christophe Leroy Cc: Kefeng Wang Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Borislav Petkov Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michal Simek Cc: Petr Mladek Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/sections.h | 16 ---------------- include/linux/kallsyms.h | 3 +-- kernel/locking/lockdep.c | 3 --- 3 files changed, 1 insertion(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 596ab2092289..614fc809de34 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -64,22 +64,6 @@ extern __visible const void __nosave_begin, __nosave_end; #define dereference_kernel_function_descriptor(p) ((void *)(p)) #endif -/* random extra sections (if any). Override - * in asm/sections.h */ -#ifndef arch_is_kernel_text -static inline int arch_is_kernel_text(unsigned long addr) -{ - return 0; -} -#endif - -#ifndef arch_is_kernel_data -static inline int arch_is_kernel_data(unsigned long addr) -{ - return 0; -} -#endif - /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index a1d6fc82d7f0..bac340972670 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -34,8 +34,7 @@ static inline int is_kernel_inittext(unsigned long addr) static inline int is_kernel_text(unsigned long addr) { - if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext) || - arch_is_kernel_text(addr)) + if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)) return 1; return in_gate_area_no_mm(addr); } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 8e118caf835e..f2d3bf4960f4 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -818,9 +818,6 @@ static int static_obj(const void *obj) if ((addr >= start) && (addr < end)) return 1; - if (arch_is_kernel_data(addr)) - return 1; - /* * in-kernel percpu var? */ -- cgit v1.2.3 From e7d5c4b0eb9be6ea5c2cfb510a9d6f56925118eb Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:47 -0800 Subject: kallsyms: fix address-checks for kernel related range The is_kernel_inittext/is_kernel_text/is_kernel function should not include the end address(the labels _einittext, _etext and _end) when check the address range, the issue exists since Linux v2.6.12. Link: https://lkml.kernel.org/r/20210930071143.63410-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Petr Mladek Reviewed-by: Steven Rostedt (VMware) Acked-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kallsyms.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index bac340972670..62ce22b27ea8 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -27,21 +27,21 @@ struct module; static inline int is_kernel_inittext(unsigned long addr) { if (addr >= (unsigned long)_sinittext - && addr <= (unsigned long)_einittext) + && addr < (unsigned long)_einittext) return 1; return 0; } static inline int is_kernel_text(unsigned long addr) { - if ((addr >= (unsigned long)_stext && addr <= (unsigned long)_etext)) + if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { - if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) + if (addr >= (unsigned long)_stext && addr < (unsigned long)_end) return 1; return in_gate_area_no_mm(addr); } -- cgit v1.2.3 From a20deb3a348719adaf8c12e1bf4b599bfc51836e Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:51 -0800 Subject: sections: move and rename core_kernel_data() to is_kernel_core_data() Move core_kernel_data() into sections.h and rename it to is_kernel_core_data(), also make it return bool value, then update all the callers. Link: https://lkml.kernel.org/r/20210930071143.63410-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Arnd Bergmann Cc: Steven Rostedt Cc: Ingo Molnar Cc: "David S. Miller" Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/sections.h | 16 ++++++++++++++++ include/linux/kernel.h | 1 - kernel/extable.c | 18 ------------------ kernel/trace/ftrace.c | 2 +- net/sysctl_net.c | 2 +- 5 files changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 614fc809de34..7cba8ff10d3a 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -128,6 +128,22 @@ static inline bool init_section_intersects(void *virt, size_t size) return memory_intersects(__init_begin, __init_end, virt, size); } +/** + * is_kernel_core_data - checks if the pointer address is located in the + * .data section + * + * @addr: address to check + * + * Returns: true if the address is located in .data, false otherwise. + * Note: On some archs it may return true for core RODATA, and false + * for others. But will always be true for core RW data. + */ +static inline bool is_kernel_core_data(unsigned long addr) +{ + return addr >= (unsigned long)_sdata && + addr < (unsigned long)_edata; +} + /** * is_kernel_rodata - checks if the pointer address is located in the * .rodata section diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 46ca4404fb93..23f57a2d5a13 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -227,7 +227,6 @@ extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); extern int init_kernel_text(unsigned long addr); -extern int core_kernel_data(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); diff --git a/kernel/extable.c b/kernel/extable.c index 290661f68e6b..0e3412b48bba 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -82,24 +82,6 @@ int notrace core_kernel_text(unsigned long addr) return 0; } -/** - * core_kernel_data - tell if addr points to kernel data - * @addr: address to test - * - * Returns true if @addr passed in is from the core kernel data - * section. - * - * Note: On some archs it may return true for core RODATA, and false - * for others. But will always be true for core RW data. - */ -int core_kernel_data(unsigned long addr) -{ - if (addr >= (unsigned long)_sdata && - addr < (unsigned long)_edata) - return 1; - return 0; -} - int __kernel_text_address(unsigned long addr) { if (kernel_text_address(addr)) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index feebf57c6458..7aaef2b78760 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -323,7 +323,7 @@ int __register_ftrace_function(struct ftrace_ops *ops) if (!ftrace_enabled && (ops->flags & FTRACE_OPS_FL_PERMANENT)) return -EBUSY; - if (!core_kernel_data((unsigned long)ops)) + if (!is_kernel_core_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; add_ftrace_ops(&ftrace_ops_list, ops); diff --git a/net/sysctl_net.c b/net/sysctl_net.c index f6cb0d4d114c..4b45ed631eb8 100644 --- a/net/sysctl_net.c +++ b/net/sysctl_net.c @@ -144,7 +144,7 @@ static void ensure_safe_net_sysctl(struct net *net, const char *path, addr = (unsigned long)ent->data; if (is_module_address(addr)) where = "module"; - else if (core_kernel_data(addr)) + else if (is_kernel_core_data(addr)) where = "kernel"; else continue; -- cgit v1.2.3 From b9ad8fe7b8cab3814d1de41e8ddca602b2646f4b Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:33:54 -0800 Subject: sections: move is_kernel_inittext() into sections.h The is_kernel_inittext() and init_kernel_text() are with same functionality, let's just keep is_kernel_inittext() and move it into sections.h, then update all the callers. Link: https://lkml.kernel.org/r/20210930071143.63410-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Arnd Bergmann Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/unwind_orc.c | 2 +- include/asm-generic/sections.h | 14 ++++++++++++++ include/linux/kallsyms.h | 8 -------- include/linux/kernel.h | 1 - kernel/extable.c | 12 ++---------- 5 files changed, 17 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index a1202536fc57..d92ec2ced059 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -175,7 +175,7 @@ static struct orc_entry *orc_find(unsigned long ip) } /* vmlinux .init slow lookup: */ - if (init_kernel_text(ip)) + if (is_kernel_inittext(ip)) return __orc_find(__start_orc_unwind_ip, __start_orc_unwind, __stop_orc_unwind_ip - __start_orc_unwind_ip, ip); diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 7cba8ff10d3a..f82806ca8756 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -158,4 +158,18 @@ static inline bool is_kernel_rodata(unsigned long addr) addr < (unsigned long)__end_rodata; } +/** + * is_kernel_inittext - checks if the pointer address is located in the + * .init.text section + * + * @addr: address to check + * + * Returns: true if the address is located in .init.text, false otherwise. + */ +static inline bool is_kernel_inittext(unsigned long addr) +{ + return addr >= (unsigned long)_sinittext && + addr < (unsigned long)_einittext; +} + #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index 62ce22b27ea8..bb5d9ec78e13 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -24,14 +24,6 @@ struct cred; struct module; -static inline int is_kernel_inittext(unsigned long addr) -{ - if (addr >= (unsigned long)_sinittext - && addr < (unsigned long)_einittext) - return 1; - return 0; -} - static inline int is_kernel_text(unsigned long addr) { if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 23f57a2d5a13..be84ab369650 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -226,7 +226,6 @@ extern bool parse_option_str(const char *str, const char *option); extern char *next_arg(char *args, char **param, char **val); extern int core_kernel_text(unsigned long addr); -extern int init_kernel_text(unsigned long addr); extern int __kernel_text_address(unsigned long addr); extern int kernel_text_address(unsigned long addr); extern int func_ptr_is_kernel_text(void *ptr); diff --git a/kernel/extable.c b/kernel/extable.c index 0e3412b48bba..6505207aa7e6 100644 --- a/kernel/extable.c +++ b/kernel/extable.c @@ -62,14 +62,6 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr) return e; } -int init_kernel_text(unsigned long addr) -{ - if (addr >= (unsigned long)_sinittext && - addr < (unsigned long)_einittext) - return 1; - return 0; -} - int notrace core_kernel_text(unsigned long addr) { if (addr >= (unsigned long)_stext && @@ -77,7 +69,7 @@ int notrace core_kernel_text(unsigned long addr) return 1; if (system_state < SYSTEM_FREEING_INITMEM && - init_kernel_text(addr)) + is_kernel_inittext(addr)) return 1; return 0; } @@ -94,7 +86,7 @@ int __kernel_text_address(unsigned long addr) * Since we are after the module-symbols check, there's * no danger of address overlap: */ - if (init_kernel_text(addr)) + if (is_kernel_inittext(addr)) return 1; return 0; } -- cgit v1.2.3 From 8f6e42e83362650007ed298070a69d084f2c8baf Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Mon, 8 Nov 2021 18:34:02 -0800 Subject: sections: provide internal __is_kernel() and __is_kernel_text() helper An internal __is_kernel() helper which only check the kernel address ranges, and an internal __is_kernel_text() helper which only check text section ranges. Link: https://lkml.kernel.org/r/20210930071143.63410-7-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Reviewed-by: Sergey Senozhatsky Cc: Alexander Potapenko Cc: Alexei Starovoitov Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Christophe Leroy Cc: "David S. Miller" Cc: Dmitry Vyukov Cc: Ingo Molnar Cc: Ivan Kokshaysky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Paul Mackerras Cc: Petr Mladek Cc: Richard Henderson Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/asm-generic/sections.h | 29 +++++++++++++++++++++++++++++ include/linux/kallsyms.h | 4 ++-- 2 files changed, 31 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index f82806ca8756..1dfadb2e878d 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -172,4 +172,33 @@ static inline bool is_kernel_inittext(unsigned long addr) addr < (unsigned long)_einittext; } +/** + * __is_kernel_text - checks if the pointer address is located in the + * .text section + * + * @addr: address to check + * + * Returns: true if the address is located in .text, false otherwise. + * Note: an internal helper, only check the range of _stext to _etext. + */ +static inline bool __is_kernel_text(unsigned long addr) +{ + return addr >= (unsigned long)_stext && + addr < (unsigned long)_etext; +} + +/** + * __is_kernel - checks if the pointer address is located in the kernel range + * + * @addr: address to check + * + * Returns: true if the address is located in the kernel range, false otherwise. + * Note: an internal helper, only check the range of _stext to _end. + */ +static inline bool __is_kernel(unsigned long addr) +{ + return addr >= (unsigned long)_stext && + addr < (unsigned long)_end; +} + #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index bb5d9ec78e13..4176c7eca7b5 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -26,14 +26,14 @@ struct module; static inline int is_kernel_text(unsigned long addr) { - if ((addr >= (unsigned long)_stext && addr < (unsigned long)_etext)) + if (__is_kernel_text(addr)) return 1; return in_gate_area_no_mm(addr); } static inline int is_kernel(unsigned long addr) { - if (addr >= (unsigned long)_stext && addr < (unsigned long)_end) + if (__is_kernel(addr)) return 1; return in_gate_area_no_mm(addr); } -- cgit v1.2.3 From 5605f41917c6ad766814a8e417a4481e9157c991 Mon Sep 17 00:00:00 2001 From: Changcheng Deng Date: Mon, 8 Nov 2021 18:35:07 -0800 Subject: crash_dump: fix boolreturn.cocci warning ./include/linux/crash_dump.h: 119: 50-51: WARNING: return of 0/1 in function 'is_kdump_kernel' with return type bool Return statements in functions returning bool should use true/false instead of 1/0. Link: https://lkml.kernel.org/r/20211020083905.1037952-1-deng.changcheng@zte.com.cn Signed-off-by: Changcheng Deng Reported-by: Zeal Robot Reviewed-by: Simon Horman Acked-by: Baoquan He Cc: Dave Young Cc: Mike Rapoport Cc: Vivek Goyal Cc: Ye Guojin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 0c547d866f1e..979c26176c1d 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -116,7 +116,7 @@ extern void register_vmcore_cb(struct vmcore_cb *cb); extern void unregister_vmcore_cb(struct vmcore_cb *cb); #else /* !CONFIG_CRASH_DUMP */ -static inline bool is_kdump_kernel(void) { return 0; } +static inline bool is_kdump_kernel(void) { return false; } #endif /* CONFIG_CRASH_DUMP */ /* Device Dump information to be filled by drivers */ -- cgit v1.2.3 From a10677a028b853c25054a4b8be04013ccb55682f Mon Sep 17 00:00:00 2001 From: Ye Guojin Date: Mon, 8 Nov 2021 18:35:10 -0800 Subject: crash_dump: remove duplicate include in crash_dump.h In crash_dump.h, header file is included twice. This duplication was introduced in commit 65fddcfca8ad("mm: reorder includes after introduction of linux/pgtable.h") where the order of the header files is adjusted, while the old one was not removed. Clean it up here. Link: https://lkml.kernel.org/r/20211020090659.1038877-1-ye.guojin@zte.com.cn Signed-off-by: Ye Guojin Reported-by: Zeal Robot Acked-by: Baoquan He Cc: Dave Young Cc: Mike Rapoport Cc: Vivek Goyal Cc: Changcheng Deng Cc: Simon Horman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/crash_dump.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 979c26176c1d..620821549b23 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -8,8 +8,6 @@ #include #include -#include /* for pgprot_t */ - /* For IS_ENABLED(CONFIG_CRASH_DUMP) */ #define ELFCORE_ADDR_MAX (-1ULL) #define ELFCORE_ADDR_ERR (-2ULL) -- cgit v1.2.3 From f26663684e76773ea86e2df13fb18f9d66c91151 Mon Sep 17 00:00:00 2001 From: Ye Guojin Date: Mon, 8 Nov 2021 18:35:13 -0800 Subject: signal: remove duplicate include in signal.h 'linux/string.h' included in 'signal.h' is duplicated. it's also included at line 7. Link: https://lkml.kernel.org/r/20211019024934.973008-1-ye.guojin@zte.com.cn Signed-off-by: Ye Guojin Reported-by: Zeal Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/signal.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/signal.h b/include/linux/signal.h index 3f96a6374e4f..37f5080c070a 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -126,7 +126,6 @@ static inline int sigequalsets(const sigset_t *set1, const sigset_t *set2) #define sigmask(sig) (1UL << ((sig) - 1)) #ifndef __HAVE_ARCH_SIG_SETOPS -#include #define _SIG_SET_BINOP(name, op) \ static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \ -- cgit v1.2.3 From 372904c080be44629d84bb15ed5e12eed44b5f9f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 8 Nov 2021 18:35:16 -0800 Subject: seq_file: move seq_escape() to a header Move seq_escape() to the header as inliner, for a small kernel text size reduction. Link: https://lkml.kernel.org/r/20211001122917.67228-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/seq_file.c | 16 ---------------- include/linux/seq_file.h | 17 ++++++++++++++++- 2 files changed, 16 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/fs/seq_file.c b/fs/seq_file.c index 4a2cda04d3e2..f8e1f4ee87ff 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -383,22 +383,6 @@ void seq_escape_mem(struct seq_file *m, const char *src, size_t len, } EXPORT_SYMBOL(seq_escape_mem); -/** - * seq_escape - print string into buffer, escaping some characters - * @m: target buffer - * @s: string - * @esc: set of characters that need escaping - * - * Puts string into buffer, replacing each occurrence of character from - * @esc with usual octal escape. - * Use seq_has_overflowed() to check for errors. - */ -void seq_escape(struct seq_file *m, const char *s, const char *esc) -{ - seq_escape_str(m, s, ESCAPE_OCTAL, esc); -} -EXPORT_SYMBOL(seq_escape); - void seq_vprintf(struct seq_file *m, const char *f, va_list args) { int len; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index dd99569595fd..103776e18555 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -4,6 +4,7 @@ #include #include +#include #include #include #include @@ -135,7 +136,21 @@ static inline void seq_escape_str(struct seq_file *m, const char *src, seq_escape_mem(m, src, strlen(src), flags, esc); } -void seq_escape(struct seq_file *m, const char *s, const char *esc); +/** + * seq_escape - print string into buffer, escaping some characters + * @m: target buffer + * @s: NULL-terminated string + * @esc: set of characters that need escaping + * + * Puts string into buffer, replacing each occurrence of character from + * @esc with usual octal escape. + * + * Use seq_has_overflowed() to check for errors. + */ +static inline void seq_escape(struct seq_file *m, const char *s, const char *esc) +{ + seq_escape_str(m, s, ESCAPE_OCTAL, esc); +} void seq_hex_dump(struct seq_file *m, const char *prefix_str, int prefix_type, int rowsize, int groupsize, const void *buf, size_t len, -- cgit v1.2.3 From 10a6de19cad6efb9b49883513afb810dc265fca2 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Mon, 8 Nov 2021 18:35:19 -0800 Subject: seq_file: fix passing wrong private data DEFINE_PROC_SHOW_ATTRIBUTE() is supposed to be used to define a series of functions and variables to register proc file easily. And the users can use proc_create_data() to pass their own private data and get it via seq->private in the callback. Unfortunately, the proc file system use PDE_DATA() to get private data instead of inode->i_private. So fix it. Fortunately, there only one user of it which does not pass any private data, so this bug does not break any in-tree codes. Link: https://lkml.kernel.org/r/20211029032638.84884-1-songmuchun@bytedance.com Fixes: 97a32539b956 ("proc: convert everything to "struct proc_ops"") Signed-off-by: Muchun Song Cc: Andy Shevchenko Cc: Stephen Rothwell Cc: Florent Revest Cc: Alexey Dobriyan Cc: Christian Brauner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/seq_file.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 103776e18555..72dbb44a4573 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -209,7 +209,7 @@ static const struct file_operations __name ## _fops = { \ #define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ - return single_open(file, __name ## _show, inode->i_private); \ + return single_open(file, __name ## _show, PDE_DATA(inode)); \ } \ \ static const struct proc_ops __name ## _proc_ops = { \ -- cgit v1.2.3 From 278167fd2f8ffe679351605fe03e29ff3ab8db18 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Tue, 9 Nov 2021 16:29:49 -0800 Subject: block: add __must_check for *add_disk*() callers Now that we have done a spring cleaning on all drivers and added error checking / handling, let's keep it that way and ensure no new drivers fail to stick with it. Reviewed-by: Christoph Hellwig Signed-off-by: Luis Chamberlain Reviewed-by: Bart Van Assche Link: https://lore.kernel.org/r/20211110002949.999380-1-mcgrof@kernel.org Signed-off-by: Jens Axboe --- block/genhd.c | 6 +++--- include/linux/genhd.h | 6 +++--- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index ca2fbab1d425..c5392cc24d37 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -394,8 +394,8 @@ static void disk_scan_partitions(struct gendisk *disk) * This function registers the partitioning information in @disk * with the kernel. */ -int device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups) { struct device *ddev = disk_to_dev(disk); @@ -544,7 +544,7 @@ out_disk_release_events: out_free_ext_minor: if (disk->major == BLOCK_EXT_MAJOR) blk_free_ext_minor(disk->first_minor); - return WARN_ON_ONCE(ret); /* keep until all callers handle errors */ + return ret; } EXPORT_SYMBOL(device_add_disk); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 462634b4b48f..74c410263113 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -205,9 +205,9 @@ static inline dev_t disk_devt(struct gendisk *disk) void disk_uevent(struct gendisk *disk, enum kobject_action action); /* block/genhd.c */ -int device_add_disk(struct device *parent, struct gendisk *disk, - const struct attribute_group **groups); -static inline int add_disk(struct gendisk *disk) +int __must_check device_add_disk(struct device *parent, struct gendisk *disk, + const struct attribute_group **groups); +static inline int __must_check add_disk(struct gendisk *disk) { return device_add_disk(NULL, disk, NULL); } -- cgit v1.2.3 From 64355db3caf6468dc711995239efe0cbcd7d0091 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Wed, 10 Nov 2021 13:16:55 +0100 Subject: mod_devicetable: fix kdocs for ishtp_device_id MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The kdocs were copied from another device_id struct and not adapted. Fixes: fa443bc3c1e4 ("HID: intel-ish-hid: add support for MODULE_DEVICE_TABLE()") Signed-off-by: Thomas Weißschuh Reported-by: Stephen Rothwell Signed-off-by: Jiri Kosina --- include/linux/mod_devicetable.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index befbf53c4b7c..c70abe7aaef2 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -901,8 +901,7 @@ struct dfl_device_id { /** * struct ishtp_device_id - ISHTP device identifier - * @guid_string: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba - * @context: pointer to driver specific data + * @guid: GUID of the device. */ struct ishtp_device_id { guid_t guid; -- cgit v1.2.3 From 5d5e4522a7f404d1a96fd6c703989d32a9c9568d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sun, 7 Nov 2021 14:51:16 +1000 Subject: printk: restore flushing of NMI buffers on remote CPUs after NMI backtraces printk from NMI context relies on irq work being raised on the local CPU to print to console. This can be a problem if the NMI was raised by a lockup detector to print lockup stack and regs, because the CPU may not enable irqs (because it is locked up). Introduce printk_trigger_flush() that can be called another CPU to try to get those messages to the console, call that where printk_safe_flush was previously called. Fixes: 93d102f094be ("printk: remove safe buffers") Cc: stable@vger.kernel.org # 5.15 Signed-off-by: Nicholas Piggin Reviewed-by: Petr Mladek Reviewed-by: John Ogness Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20211107045116.1754411-1-npiggin@gmail.com --- arch/powerpc/kernel/watchdog.c | 6 ++++++ include/linux/printk.h | 4 ++++ kernel/printk/printk.c | 5 +++++ lib/nmi_backtrace.c | 6 ++++++ 4 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c index dc17d8903d4f..6b7a83d5e03e 100644 --- a/arch/powerpc/kernel/watchdog.c +++ b/arch/powerpc/kernel/watchdog.c @@ -186,6 +186,12 @@ static void watchdog_smp_panic(int cpu, u64 tb) if (sysctl_hardlockup_all_cpu_backtrace) trigger_allbutself_cpu_backtrace(); + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_trigger_flush(); + if (hardlockup_panic) nmi_panic(NULL, "Hard LOCKUP"); diff --git a/include/linux/printk.h b/include/linux/printk.h index a1379df43251..596ad6fa0336 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -206,6 +206,7 @@ void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; +void printk_trigger_flush(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -282,6 +283,9 @@ static inline void dump_stack_lvl(const char *log_lvl) static inline void dump_stack(void) { } +static inline void printk_trigger_flush(void) +{ +} #endif #ifdef CONFIG_SMP diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 65fffa6368c9..eabe23b0a982 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -3261,6 +3261,11 @@ void defer_console_output(void) preempt_enable(); } +void printk_trigger_flush(void) +{ + defer_console_output(); +} + int vprintk_deferred(const char *fmt, va_list args) { int r; diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index f9e89001b52e..199ab201d501 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -75,6 +75,12 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask, touch_softlockup_watchdog(); } + /* + * Force flush any remote buffers that might be stuck in IRQ context + * and therefore could not run their irq_work. + */ + printk_trigger_flush(); + clear_bit_unlock(0, &backtrace_flag); put_cpu(); } -- cgit v1.2.3 From a19672f6b9718df247a9087a266150dbe833022e Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Aug 2021 21:54:58 +0100 Subject: folio: Add a function to change the private data attached to a folio Add a function, folio_change_private(), that will change the private data attached to a folio, without the need to twiddle the private bit or the refcount. It assumes that folio_add_private() has already been called on the page. Signed-off-by: David Howells Reviewed-by: Matthew Wilcox (Oracle) Tested-by: Jeff Layton Tested-by: Dominique Martinet Tested-by: kafs-testing@auristor.com Link: https://lore.kernel.org/r/162981149911.1901565.17776700811659843340.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005743485.2472992.5100702469503007023.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584180781.4023316.5037526301198034310.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649324326.309189.17817587229450840783.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657848531.834781.14269656212269187893.stgit@warthog.procyon.org.uk/ # v5 --- include/linux/pagemap.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6a30916b76e5..1f560aecd9b5 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -279,6 +279,25 @@ static inline void folio_attach_private(struct folio *folio, void *data) folio_set_private(folio); } +/** + * folio_change_private - Change private data on a folio. + * @folio: Folio to change the data on. + * @data: Data to set on the folio. + * + * Change the private data attached to a folio and return the old + * data. The page must previously have had data attached and the data + * must be detached before the folio will be freed. + * + * Return: Data that was previously attached to the folio. + */ +static inline void *folio_change_private(struct folio *folio, void *data) +{ + void *old = folio_get_private(folio); + + folio->private = data; + return old; +} + /** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. -- cgit v1.2.3 From 452c472e26348df1e7052544130aa98eebbd2331 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 12 Aug 2021 22:09:57 +0100 Subject: folio: Add a function to get the host inode for a folio Add a convenience function, folio_inode() that will get the host inode from a folio's mapping. Changes: ver #3: - Fix mistake in function description[2]. ver #2: - Fix contradiction between doc and implementation by disallowing use with swap caches[1]. Signed-off-by: David Howells Reviewed-by: Matthew Wilcox (Oracle) Tested-by: Jeff Layton Tested-by: Dominique Martinet Tested-by: kafs-testing@auristor.com Link: https://lore.kernel.org/r/YST8OcVNy02Rivbm@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/YYKLkBwQdtn4ja+i@casper.infradead.org/ [2] Link: https://lore.kernel.org/r/162880453171.3369675.3704943108660112470.stgit@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162981151155.1901565.7010079316994382707.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005744370.2472992.18324470937328925723.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584184628.4023316.9386282630968981869.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649325519.309189.15072332908703129455.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657850401.834781.1031963517399283294.stgit@warthog.procyon.org.uk/ # v5 --- include/linux/pagemap.h | 14 ++++++++++++++ mm/page-writeback.c | 2 +- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1f560aecd9b5..1a0c646eb6ff 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -253,6 +253,20 @@ static inline struct address_space *page_mapping_file(struct page *page) return folio_mapping(folio); } +/** + * folio_inode - Get the host inode for this folio. + * @folio: The folio. + * + * For folios which are in the page cache, return the inode that this folio + * belongs to. + * + * Do not call this for folios which aren't in the page cache. + */ +static inline struct inode *folio_inode(struct folio *folio) +{ + return folio->mapping->host; +} + static inline bool page_cache_add_speculative(struct page *page, int count) { VM_BUG_ON_PAGE(PageTail(page), page); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2d498bb62248..a613f8ef6a02 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2967,7 +2967,7 @@ EXPORT_SYMBOL_GPL(folio_wait_writeback_killable); */ void folio_wait_stable(struct folio *folio) { - if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES) + if (folio_inode(folio)->i_sb->s_iflags & SB_I_STABLE_WRITES) folio_wait_writeback(folio); } EXPORT_SYMBOL_GPL(folio_wait_stable); -- cgit v1.2.3 From 78525c74d9e7d1a6ce69bd4388f045f6e474a20b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 11 Aug 2021 09:49:13 +0100 Subject: netfs, 9p, afs, ceph: Use folios Convert the netfs helper library to use folios throughout, convert the 9p and afs filesystems to use folios in their file I/O paths and convert the ceph filesystem to use just enough folios to compile. With these changes, afs passes -g quick xfstests. Changes ======= ver #5: - Got rid of folio_end{io,_read,_write}() and inlined the stuff it does instead (Willy decided he didn't want this after all). ver #4: - Fixed a bug in afs_redirty_page() whereby it didn't set the next page index in the loop and returned too early. - Simplified a check in v9fs_vfs_write_folio_locked()[1]. - Undid a change to afs_symlink_readpage()[1]. - Used offset_in_folio() in afs_write_end()[1]. - Changed from using page_endio() to folio_end{io,_read,_write}()[1]. ver #2: - Add 9p foliation. Signed-off-by: David Howells Reviewed-by: Jeff Layton Tested-by: Jeff Layton Tested-by: Dominique Martinet Tested-by: kafs-testing@auristor.com cc: Matthew Wilcox (Oracle) cc: Marc Dionne cc: Ilya Dryomov cc: Dominique Martinet cc: v9fs-developer@lists.sourceforge.net cc: linux-afs@lists.infradead.org cc: ceph-devel@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YYKa3bfQZxK5/wDN@casper.infradead.org/ [1] Link: https://lore.kernel.org/r/2408234.1628687271@warthog.procyon.org.uk/ # rfc Link: https://lore.kernel.org/r/162877311459.3085614.10601478228012245108.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/162981153551.1901565.3124454657133703341.stgit@warthog.procyon.org.uk/ Link: https://lore.kernel.org/r/163005745264.2472992.9852048135392188995.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163584187452.4023316.500389675405550116.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/163649328026.309189.1124218109373941936.stgit@warthog.procyon.org.uk/ # v4 Link: https://lore.kernel.org/r/163657852454.834781.9265101983152100556.stgit@warthog.procyon.org.uk/ # v5 --- fs/9p/vfs_addr.c | 83 ++++++----- fs/9p/vfs_file.c | 20 +-- fs/afs/file.c | 70 +++++---- fs/afs/internal.h | 46 +++--- fs/afs/write.c | 347 ++++++++++++++++++++++----------------------- fs/ceph/addr.c | 80 ++++++----- fs/netfs/read_helper.c | 165 ++++++++++----------- include/linux/netfs.h | 12 +- include/trace/events/afs.h | 21 +-- 9 files changed, 428 insertions(+), 416 deletions(-) (limited to 'include/linux') diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index adafdf86f42f..fac918ccb305 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -108,7 +108,9 @@ static const struct netfs_read_request_ops v9fs_req_ops = { */ static int v9fs_vfs_readpage(struct file *file, struct page *page) { - return netfs_readpage(file, page, &v9fs_req_ops, NULL); + struct folio *folio = page_folio(page); + + return netfs_readpage(file, folio, &v9fs_req_ops, NULL); } /** @@ -130,13 +132,15 @@ static void v9fs_vfs_readahead(struct readahead_control *ractl) static int v9fs_release_page(struct page *page, gfp_t gfp) { - if (PagePrivate(page)) + struct folio *folio = page_folio(page); + + if (folio_test_private(folio)) return 0; #ifdef CONFIG_9P_FSCACHE - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) return 0; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } #endif return 1; @@ -152,55 +156,58 @@ static int v9fs_release_page(struct page *page, gfp_t gfp) static void v9fs_invalidate_page(struct page *page, unsigned int offset, unsigned int length) { - wait_on_page_fscache(page); + struct folio *folio = page_folio(page); + + folio_wait_fscache(folio); } -static int v9fs_vfs_writepage_locked(struct page *page) +static int v9fs_vfs_write_folio_locked(struct folio *folio) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio_inode(folio); struct v9fs_inode *v9inode = V9FS_I(inode); - loff_t start = page_offset(page); - loff_t size = i_size_read(inode); + loff_t start = folio_pos(folio); + loff_t i_size = i_size_read(inode); struct iov_iter from; - int err, len; + size_t len = folio_size(folio); + int err; + + if (start >= i_size) + return 0; /* Simultaneous truncation occurred */ - if (page->index == size >> PAGE_SHIFT) - len = size & ~PAGE_MASK; - else - len = PAGE_SIZE; + len = min_t(loff_t, i_size - start, len); - iov_iter_xarray(&from, WRITE, &page->mapping->i_pages, start, len); + iov_iter_xarray(&from, WRITE, &folio_mapping(folio)->i_pages, start, len); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); - set_page_writeback(page); + folio_start_writeback(folio); p9_client_write(v9inode->writeback_fid, start, &from, &err); - end_page_writeback(page); + folio_end_writeback(folio); return err; } static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) { + struct folio *folio = page_folio(page); int retval; - p9_debug(P9_DEBUG_VFS, "page %p\n", page); + p9_debug(P9_DEBUG_VFS, "folio %p\n", folio); - retval = v9fs_vfs_writepage_locked(page); + retval = v9fs_vfs_write_folio_locked(folio); if (retval < 0) { if (retval == -EAGAIN) { - redirty_page_for_writepage(wbc, page); + folio_redirty_for_writepage(wbc, folio); retval = 0; } else { - SetPageError(page); - mapping_set_error(page->mapping, retval); + mapping_set_error(folio_mapping(folio), retval); } } else retval = 0; - unlock_page(page); + folio_unlock(folio); return retval; } @@ -213,14 +220,15 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc) static int v9fs_launder_page(struct page *page) { + struct folio *folio = page_folio(page); int retval; - if (clear_page_dirty_for_io(page)) { - retval = v9fs_vfs_writepage_locked(page); + if (folio_clear_dirty_for_io(folio)) { + retval = v9fs_vfs_write_folio_locked(folio); if (retval) return retval; } - wait_on_page_fscache(page); + folio_wait_fscache(folio); return 0; } @@ -265,10 +273,10 @@ v9fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) static int v9fs_write_begin(struct file *filp, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int flags, - struct page **pagep, void **fsdata) + struct page **subpagep, void **fsdata) { int retval; - struct page *page; + struct folio *folio; struct v9fs_inode *v9inode = V9FS_I(mapping->host); p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); @@ -279,31 +287,32 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - retval = netfs_write_begin(filp, mapping, pos, len, flags, &page, fsdata, + retval = netfs_write_begin(filp, mapping, pos, len, flags, &folio, fsdata, &v9fs_req_ops, NULL); if (retval < 0) return retval; - *pagep = find_subpage(page, pos / PAGE_SIZE); + *subpagep = &folio->page; return retval; } static int v9fs_write_end(struct file *filp, struct address_space *mapping, loff_t pos, unsigned int len, unsigned int copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { loff_t last_pos = pos + copied; - struct inode *inode = page->mapping->host; + struct folio *folio = page_folio(subpage); + struct inode *inode = mapping->host; p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (unlikely(copied < len)) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* @@ -314,10 +323,10 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping, inode_add_bytes(inode, last_pos - inode->i_size); i_size_write(inode, last_pos); } - set_page_dirty(page); + folio_mark_dirty(folio); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 4244d48398ef..612e297f3763 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -528,13 +528,13 @@ static vm_fault_t v9fs_vm_page_mkwrite(struct vm_fault *vmf) { struct v9fs_inode *v9inode; - struct page *page = vmf->page; + struct folio *folio = page_folio(vmf->page); struct file *filp = vmf->vma->vm_file; struct inode *inode = file_inode(filp); - p9_debug(P9_DEBUG_VFS, "page %p fid %lx\n", - page, (unsigned long)filp->private_data); + p9_debug(P9_DEBUG_VFS, "folio %p fid %lx\n", + folio, (unsigned long)filp->private_data); v9inode = V9FS_I(inode); @@ -542,24 +542,24 @@ v9fs_vm_page_mkwrite(struct vm_fault *vmf) * be modified. We then assume the entire page will need writing back. */ #ifdef CONFIG_9P_FSCACHE - if (PageFsCache(page) && - wait_on_page_fscache_killable(page) < 0) - return VM_FAULT_RETRY; + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) + return VM_FAULT_NOPAGE; #endif /* Update file times before taking page lock */ file_update_time(filp); BUG_ON(!v9inode->writeback_fid); - if (lock_page_killable(page) < 0) + if (folio_lock_killable(folio) < 0) return VM_FAULT_RETRY; - if (page->mapping != inode->i_mapping) + if (folio_mapping(folio) != inode->i_mapping) goto out_unlock; - wait_for_stable_page(page); + folio_wait_stable(folio); return VM_FAULT_LOCKED; out_unlock: - unlock_page(page); + folio_unlock(folio); return VM_FAULT_NOPAGE; } diff --git a/fs/afs/file.c b/fs/afs/file.c index eb11d047c0ae..cb6ad61eec3b 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -324,21 +324,24 @@ static int afs_symlink_readpage(struct file *file, struct page *page) { struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); struct afs_read *fsreq; + struct folio *folio = page_folio(page); int ret; fsreq = afs_alloc_read(GFP_NOFS); if (!fsreq) return -ENOMEM; - fsreq->pos = page->index * PAGE_SIZE; - fsreq->len = PAGE_SIZE; + fsreq->pos = folio_pos(folio); + fsreq->len = folio_size(folio); fsreq->vnode = vnode; fsreq->iter = &fsreq->def_iter; iov_iter_xarray(&fsreq->def_iter, READ, &page->mapping->i_pages, fsreq->pos, fsreq->len); ret = afs_fetch_data(fsreq->vnode, fsreq); - page_endio(page, false, ret); + if (ret == 0) + SetPageUptodate(page); + unlock_page(page); return ret; } @@ -362,7 +365,7 @@ static int afs_begin_cache_operation(struct netfs_read_request *rreq) } static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata) + struct folio *folio, void **_fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); @@ -385,7 +388,9 @@ const struct netfs_read_request_ops afs_req_ops = { static int afs_readpage(struct file *file, struct page *page) { - return netfs_readpage(file, page, &afs_req_ops, NULL); + struct folio *folio = page_folio(page); + + return netfs_readpage(file, folio, &afs_req_ops, NULL); } static void afs_readahead(struct readahead_control *ractl) @@ -397,29 +402,29 @@ static void afs_readahead(struct readahead_control *ractl) * Adjust the dirty region of the page on truncation or full invalidation, * getting rid of the markers altogether if the region is entirely invalidated. */ -static void afs_invalidate_dirty(struct page *page, unsigned int offset, +static void afs_invalidate_dirty(struct folio *folio, unsigned int offset, unsigned int length) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); unsigned long priv; unsigned int f, t, end = offset + length; - priv = page_private(page); + priv = (unsigned long)folio_get_private(folio); /* we clean up only if the entire page is being invalidated */ - if (offset == 0 && length == thp_size(page)) + if (offset == 0 && length == folio_size(folio)) goto full_invalidate; /* If the page was dirtied by page_mkwrite(), the PTE stays writable * and we don't get another notification to tell us to expand it * again. */ - if (afs_is_page_dirty_mmapped(priv)) + if (afs_is_folio_dirty_mmapped(priv)) return; /* We may need to shorten the dirty region */ - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (t <= offset || f >= end) return; /* Doesn't overlap */ @@ -437,17 +442,17 @@ static void afs_invalidate_dirty(struct page *page, unsigned int offset, if (f == t) goto undirty; - priv = afs_page_dirty(page, f, t); - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("trunc"), page); + priv = afs_folio_dirty(folio, f, t); + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("trunc"), folio); return; undirty: - trace_afs_page_dirty(vnode, tracepoint_string("undirty"), page); - clear_page_dirty_for_io(page); + trace_afs_folio_dirty(vnode, tracepoint_string("undirty"), folio); + folio_clear_dirty_for_io(folio); full_invalidate: - trace_afs_page_dirty(vnode, tracepoint_string("inval"), page); - detach_page_private(page); + trace_afs_folio_dirty(vnode, tracepoint_string("inval"), folio); + folio_detach_private(folio); } /* @@ -458,14 +463,16 @@ full_invalidate: static void afs_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { - _enter("{%lu},%u,%u", page->index, offset, length); + struct folio *folio = page_folio(page); + + _enter("{%lu},%u,%u", folio_index(folio), offset, length); BUG_ON(!PageLocked(page)); if (PagePrivate(page)) - afs_invalidate_dirty(page, offset, length); + afs_invalidate_dirty(folio, offset, length); - wait_on_page_fscache(page); + folio_wait_fscache(folio); _leave(""); } @@ -475,30 +482,31 @@ static void afs_invalidatepage(struct page *page, unsigned int offset, */ static int afs_releasepage(struct page *page, gfp_t gfp_flags) { - struct afs_vnode *vnode = AFS_FS_I(page->mapping->host); + struct folio *folio = page_folio(page); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); _enter("{{%llx:%llu}[%lu],%lx},%x", - vnode->fid.vid, vnode->fid.vnode, page->index, page->flags, + vnode->fid.vid, vnode->fid.vnode, folio_index(folio), folio->flags, gfp_flags); /* deny if page is being written to the cache and the caller hasn't * elected to wait */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page)) { + if (folio_test_fscache(folio)) { if (!(gfp_flags & __GFP_DIRECT_RECLAIM) || !(gfp_flags & __GFP_FS)) return false; - wait_on_page_fscache(page); + folio_wait_fscache(folio); } #endif - if (PagePrivate(page)) { - trace_afs_page_dirty(vnode, tracepoint_string("rel"), page); - detach_page_private(page); + if (folio_test_private(folio)) { + trace_afs_folio_dirty(vnode, tracepoint_string("rel"), folio); + folio_detach_private(folio); } - /* indicate that the page can be released */ + /* Indicate that the folio can be released */ _leave(" = T"); - return 1; + return true; } static void afs_add_open_mmap(struct afs_vnode *vnode) diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 9357c53faa69..aa4c0d6c9780 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -876,59 +876,59 @@ struct afs_vnode_cache_aux { } __packed; /* - * We use page->private to hold the amount of the page that we've written to, + * We use folio->private to hold the amount of the folio that we've written to, * splitting the field into two parts. However, we need to represent a range - * 0...PAGE_SIZE, so we reduce the resolution if the size of the page + * 0...FOLIO_SIZE, so we reduce the resolution if the size of the folio * exceeds what we can encode. */ #ifdef CONFIG_64BIT -#define __AFS_PAGE_PRIV_MASK 0x7fffffffUL -#define __AFS_PAGE_PRIV_SHIFT 32 -#define __AFS_PAGE_PRIV_MMAPPED 0x80000000UL +#define __AFS_FOLIO_PRIV_MASK 0x7fffffffUL +#define __AFS_FOLIO_PRIV_SHIFT 32 +#define __AFS_FOLIO_PRIV_MMAPPED 0x80000000UL #else -#define __AFS_PAGE_PRIV_MASK 0x7fffUL -#define __AFS_PAGE_PRIV_SHIFT 16 -#define __AFS_PAGE_PRIV_MMAPPED 0x8000UL +#define __AFS_FOLIO_PRIV_MASK 0x7fffUL +#define __AFS_FOLIO_PRIV_SHIFT 16 +#define __AFS_FOLIO_PRIV_MMAPPED 0x8000UL #endif -static inline unsigned int afs_page_dirty_resolution(struct page *page) +static inline unsigned int afs_folio_dirty_resolution(struct folio *folio) { - int shift = thp_order(page) + PAGE_SHIFT - (__AFS_PAGE_PRIV_SHIFT - 1); + int shift = folio_shift(folio) - (__AFS_FOLIO_PRIV_SHIFT - 1); return (shift > 0) ? shift : 0; } -static inline size_t afs_page_dirty_from(struct page *page, unsigned long priv) +static inline size_t afs_folio_dirty_from(struct folio *folio, unsigned long priv) { - unsigned long x = priv & __AFS_PAGE_PRIV_MASK; + unsigned long x = priv & __AFS_FOLIO_PRIV_MASK; /* The lower bound is inclusive */ - return x << afs_page_dirty_resolution(page); + return x << afs_folio_dirty_resolution(folio); } -static inline size_t afs_page_dirty_to(struct page *page, unsigned long priv) +static inline size_t afs_folio_dirty_to(struct folio *folio, unsigned long priv) { - unsigned long x = (priv >> __AFS_PAGE_PRIV_SHIFT) & __AFS_PAGE_PRIV_MASK; + unsigned long x = (priv >> __AFS_FOLIO_PRIV_SHIFT) & __AFS_FOLIO_PRIV_MASK; /* The upper bound is immediately beyond the region */ - return (x + 1) << afs_page_dirty_resolution(page); + return (x + 1) << afs_folio_dirty_resolution(folio); } -static inline unsigned long afs_page_dirty(struct page *page, size_t from, size_t to) +static inline unsigned long afs_folio_dirty(struct folio *folio, size_t from, size_t to) { - unsigned int res = afs_page_dirty_resolution(page); + unsigned int res = afs_folio_dirty_resolution(folio); from >>= res; to = (to - 1) >> res; - return (to << __AFS_PAGE_PRIV_SHIFT) | from; + return (to << __AFS_FOLIO_PRIV_SHIFT) | from; } -static inline unsigned long afs_page_dirty_mmapped(unsigned long priv) +static inline unsigned long afs_folio_dirty_mmapped(unsigned long priv) { - return priv | __AFS_PAGE_PRIV_MMAPPED; + return priv | __AFS_FOLIO_PRIV_MMAPPED; } -static inline bool afs_is_page_dirty_mmapped(unsigned long priv) +static inline bool afs_is_folio_dirty_mmapped(unsigned long priv) { - return priv & __AFS_PAGE_PRIV_MMAPPED; + return priv & __AFS_FOLIO_PRIV_MMAPPED; } #include diff --git a/fs/afs/write.c b/fs/afs/write.c index 8b1d9c2f6bec..ca4909baf5e6 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -32,7 +32,7 @@ int afs_write_begin(struct file *file, struct address_space *mapping, struct page **_page, void **fsdata) { struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); - struct page *page; + struct folio *folio; unsigned long priv; unsigned f, from; unsigned t, to; @@ -46,12 +46,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping, * file. We need to do this before we get a lock on the page in case * there's more than one writer competing for the same cache block. */ - ret = netfs_write_begin(file, mapping, pos, len, flags, &page, fsdata, + ret = netfs_write_begin(file, mapping, pos, len, flags, &folio, fsdata, &afs_req_ops, NULL); if (ret < 0) return ret; - index = page->index; + index = folio_index(folio); from = pos - index * PAGE_SIZE; to = from + len; @@ -59,14 +59,14 @@ try_again: /* See if this page is already partially written in a way that we can * merge the new write with. */ - if (PagePrivate(page)) { - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + if (folio_test_private(folio)) { + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); ASSERTCMP(f, <=, t); - if (PageWriteback(page)) { - trace_afs_page_dirty(vnode, tracepoint_string("alrdy"), page); + if (folio_test_writeback(folio)) { + trace_afs_folio_dirty(vnode, tracepoint_string("alrdy"), folio); goto flush_conflicting_write; } /* If the file is being filled locally, allow inter-write @@ -78,7 +78,7 @@ try_again: goto flush_conflicting_write; } - *_page = page; + *_page = &folio->page; _leave(" = 0"); return 0; @@ -87,17 +87,17 @@ try_again: */ flush_conflicting_write: _debug("flush conflict"); - ret = write_one_page(page); + ret = folio_write_one(folio); if (ret < 0) goto error; - ret = lock_page_killable(page); + ret = folio_lock_killable(folio); if (ret < 0) goto error; goto try_again; error: - put_page(page); + folio_put(folio); _leave(" = %d", ret); return ret; } @@ -107,24 +107,25 @@ error: */ int afs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { + struct folio *folio = page_folio(subpage); struct afs_vnode *vnode = AFS_FS_I(file_inode(file)); unsigned long priv; - unsigned int f, from = pos & (thp_size(page) - 1); + unsigned int f, from = offset_in_folio(folio, pos); unsigned int t, to = from + copied; loff_t i_size, maybe_i_size; _enter("{%llx:%llu},{%lx}", - vnode->fid.vid, vnode->fid.vnode, page->index); + vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { if (copied < len) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } if (copied == 0) @@ -141,29 +142,29 @@ int afs_write_end(struct file *file, struct address_space *mapping, write_sequnlock(&vnode->cb_lock); } - if (PagePrivate(page)) { - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + if (folio_test_private(folio)) { + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (from < f) f = from; if (to > t) t = to; - priv = afs_page_dirty(page, f, t); - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("dirty+"), page); + priv = afs_folio_dirty(folio, f, t); + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("dirty+"), folio); } else { - priv = afs_page_dirty(page, from, to); - attach_page_private(page, (void *)priv); - trace_afs_page_dirty(vnode, tracepoint_string("dirty"), page); + priv = afs_folio_dirty(folio, from, to); + folio_attach_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("dirty"), folio); } - if (set_page_dirty(page)) - _debug("dirtied %lx", page->index); + if (folio_mark_dirty(folio)) + _debug("dirtied %lx", folio_index(folio)); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); return copied; } @@ -174,40 +175,32 @@ static void afs_kill_pages(struct address_space *mapping, loff_t start, loff_t len) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct pagevec pv; - unsigned int loop, psize; + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; _enter("{%llx:%llu},%llx @%llx", vnode->fid.vid, vnode->fid.vnode, len, start); - pagevec_init(&pv); - do { - _debug("kill %llx @%llx", len, start); - - pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE, - PAGEVEC_SIZE, pv.pages); - if (pv.nr == 0) - break; + _debug("kill %lx (to %lx)", index, last); - for (loop = 0; loop < pv.nr; loop++) { - struct page *page = pv.pages[loop]; + folio = filemap_get_folio(mapping, index); + if (!folio) { + next = index + 1; + continue; + } - if (page->index * PAGE_SIZE >= start + len) - break; + next = folio_next_index(folio); - psize = thp_size(page); - start += psize; - len -= psize; - ClearPageUptodate(page); - end_page_writeback(page); - lock_page(page); - generic_error_remove_page(mapping, page); - unlock_page(page); - } + folio_clear_uptodate(folio); + folio_end_writeback(folio); + folio_lock(folio); + generic_error_remove_page(mapping, &folio->page); + folio_unlock(folio); + folio_put(folio); - __pagevec_release(&pv); - } while (len > 0); + } while (index = next, index <= last); _leave(""); } @@ -220,37 +213,27 @@ static void afs_redirty_pages(struct writeback_control *wbc, loff_t start, loff_t len) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); - struct pagevec pv; - unsigned int loop, psize; + struct folio *folio; + pgoff_t index = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE, next; _enter("{%llx:%llu},%llx @%llx", vnode->fid.vid, vnode->fid.vnode, len, start); - pagevec_init(&pv); - do { _debug("redirty %llx @%llx", len, start); - pv.nr = find_get_pages_contig(mapping, start / PAGE_SIZE, - PAGEVEC_SIZE, pv.pages); - if (pv.nr == 0) - break; - - for (loop = 0; loop < pv.nr; loop++) { - struct page *page = pv.pages[loop]; - - if (page->index * PAGE_SIZE >= start + len) - break; - - psize = thp_size(page); - start += psize; - len -= psize; - redirty_page_for_writepage(wbc, page); - end_page_writeback(page); + folio = filemap_get_folio(mapping, index); + if (!folio) { + next = index + 1; + continue; } - __pagevec_release(&pv); - } while (len > 0); + next = index + folio_nr_pages(folio); + folio_redirty_for_writepage(wbc, folio); + folio_end_writeback(folio); + folio_put(folio); + } while (index = next, index <= last); _leave(""); } @@ -261,7 +244,7 @@ static void afs_redirty_pages(struct writeback_control *wbc, static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsigned int len) { struct address_space *mapping = vnode->vfs_inode.i_mapping; - struct page *page; + struct folio *folio; pgoff_t end; XA_STATE(xas, &mapping->i_pages, start / PAGE_SIZE); @@ -272,15 +255,16 @@ static void afs_pages_written_back(struct afs_vnode *vnode, loff_t start, unsign rcu_read_lock(); end = (start + len - 1) / PAGE_SIZE; - xas_for_each(&xas, page, end) { - if (!PageWriteback(page)) { - kdebug("bad %x @%llx page %lx %lx", len, start, page->index, end); - ASSERT(PageWriteback(page)); + xas_for_each(&xas, folio, end) { + if (!folio_test_writeback(folio)) { + kdebug("bad %x @%llx page %lx %lx", + len, start, folio_index(folio), end); + ASSERT(folio_test_writeback(folio)); } - trace_afs_page_dirty(vnode, tracepoint_string("clear"), page); - detach_page_private(page); - page_endio(page, true, 0); + trace_afs_folio_dirty(vnode, tracepoint_string("clear"), folio); + folio_detach_private(folio); + folio_end_writeback(folio); } rcu_read_unlock(); @@ -437,7 +421,7 @@ static void afs_extend_writeback(struct address_space *mapping, unsigned int *_len) { struct pagevec pvec; - struct page *page; + struct folio *folio; unsigned long priv; unsigned int psize, filler = 0; unsigned int f, t; @@ -456,43 +440,43 @@ static void afs_extend_writeback(struct address_space *mapping, */ rcu_read_lock(); - xas_for_each(&xas, page, ULONG_MAX) { + xas_for_each(&xas, folio, ULONG_MAX) { stop = true; - if (xas_retry(&xas, page)) + if (xas_retry(&xas, folio)) continue; - if (xa_is_value(page)) + if (xa_is_value(folio)) break; - if (page->index != index) + if (folio_index(folio) != index) break; - if (!page_cache_get_speculative(page)) { + if (!folio_try_get_rcu(folio)) { xas_reset(&xas); continue; } /* Has the page moved or been split? */ - if (unlikely(page != xas_reload(&xas))) { - put_page(page); + if (unlikely(folio != xas_reload(&xas))) { + folio_put(folio); break; } - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); break; } - if (!PageDirty(page) || PageWriteback(page)) { - unlock_page(page); - put_page(page); + if (!folio_test_dirty(folio) || folio_test_writeback(folio)) { + folio_unlock(folio); + folio_put(folio); break; } - psize = thp_size(page); - priv = page_private(page); - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + psize = folio_size(folio); + priv = (unsigned long)folio_get_private(folio); + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); if (f != 0 && !new_content) { - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); break; } @@ -503,8 +487,8 @@ static void afs_extend_writeback(struct address_space *mapping, else if (t == psize || new_content) stop = false; - index += thp_nr_pages(page); - if (!pagevec_add(&pvec, page)) + index += folio_nr_pages(folio); + if (!pagevec_add(&pvec, &folio->page)) break; if (stop) break; @@ -521,16 +505,16 @@ static void afs_extend_writeback(struct address_space *mapping, break; for (i = 0; i < pagevec_count(&pvec); i++) { - page = pvec.pages[i]; - trace_afs_page_dirty(vnode, tracepoint_string("store+"), page); + folio = page_folio(pvec.pages[i]); + trace_afs_folio_dirty(vnode, tracepoint_string("store+"), folio); - if (!clear_page_dirty_for_io(page)) + if (!folio_clear_dirty_for_io(folio)) BUG(); - if (test_set_page_writeback(page)) + if (folio_start_writeback(folio)) BUG(); - *_count -= thp_nr_pages(page); - unlock_page(page); + *_count -= folio_nr_pages(folio); + folio_unlock(folio); } pagevec_release(&pvec); @@ -544,10 +528,10 @@ static void afs_extend_writeback(struct address_space *mapping, * Synchronously write back the locked page and any subsequent non-locked dirty * pages. */ -static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, - struct writeback_control *wbc, - struct page *page, - loff_t start, loff_t end) +static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, + struct writeback_control *wbc, + struct folio *folio, + loff_t start, loff_t end) { struct afs_vnode *vnode = AFS_FS_I(mapping->host); struct iov_iter iter; @@ -558,22 +542,22 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, long count = wbc->nr_to_write; int ret; - _enter(",%lx,%llx-%llx", page->index, start, end); + _enter(",%lx,%llx-%llx", folio_index(folio), start, end); - if (test_set_page_writeback(page)) + if (folio_start_writeback(folio)) BUG(); - count -= thp_nr_pages(page); + count -= folio_nr_pages(folio); /* Find all consecutive lockable dirty pages that have contiguous * written regions, stopping when we find a page that is not * immediately lockable, is not dirty or is missing, or we reach the * end of the range. */ - priv = page_private(page); - offset = afs_page_dirty_from(page, priv); - to = afs_page_dirty_to(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("store"), page); + priv = (unsigned long)folio_get_private(folio); + offset = afs_folio_dirty_from(folio, priv); + to = afs_folio_dirty_to(folio, priv); + trace_afs_folio_dirty(vnode, tracepoint_string("store"), folio); len = to - offset; start += offset; @@ -586,7 +570,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, max_len = min_t(unsigned long long, max_len, i_size - start); if (len < max_len && - (to == thp_size(page) || new_content)) + (to == folio_size(folio) || new_content)) afs_extend_writeback(mapping, vnode, &count, start, max_len, new_content, &len); len = min_t(loff_t, len, max_len); @@ -596,7 +580,7 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, * set; the first page is still locked at this point, but all the rest * have been unlocked. */ - unlock_page(page); + folio_unlock(folio); if (start < i_size) { _debug("write back %x @%llx [%llx]", len, start, i_size); @@ -657,16 +641,17 @@ static ssize_t afs_write_back_from_locked_page(struct address_space *mapping, * write a page back to the server * - the caller locked the page for us */ -int afs_writepage(struct page *page, struct writeback_control *wbc) +int afs_writepage(struct page *subpage, struct writeback_control *wbc) { + struct folio *folio = page_folio(subpage); ssize_t ret; loff_t start; - _enter("{%lx},", page->index); + _enter("{%lx},", folio_index(folio)); - start = page->index * PAGE_SIZE; - ret = afs_write_back_from_locked_page(page->mapping, wbc, page, - start, LLONG_MAX - start); + start = folio_index(folio) * PAGE_SIZE; + ret = afs_write_back_from_locked_folio(folio_mapping(folio), wbc, + folio, start, LLONG_MAX - start); if (ret < 0) { _leave(" = %zd", ret); return ret; @@ -683,7 +668,8 @@ static int afs_writepages_region(struct address_space *mapping, struct writeback_control *wbc, loff_t start, loff_t end, loff_t *_next) { - struct page *page; + struct folio *folio; + struct page *head_page; ssize_t ret; int n; @@ -693,13 +679,14 @@ static int afs_writepages_region(struct address_space *mapping, pgoff_t index = start / PAGE_SIZE; n = find_get_pages_range_tag(mapping, &index, end / PAGE_SIZE, - PAGECACHE_TAG_DIRTY, 1, &page); + PAGECACHE_TAG_DIRTY, 1, &head_page); if (!n) break; - start = (loff_t)page->index * PAGE_SIZE; /* May regress with THPs */ + folio = page_folio(head_page); + start = folio_pos(folio); /* May regress with THPs */ - _debug("wback %lx", page->index); + _debug("wback %lx", folio_index(folio)); /* At this point we hold neither the i_pages lock nor the * page lock: the page may be truncated or invalidated @@ -707,37 +694,38 @@ static int afs_writepages_region(struct address_space *mapping, * back from swapper_space to tmpfs file mapping */ if (wbc->sync_mode != WB_SYNC_NONE) { - ret = lock_page_killable(page); + ret = folio_lock_killable(folio); if (ret < 0) { - put_page(page); + folio_put(folio); return ret; } } else { - if (!trylock_page(page)) { - put_page(page); + if (!folio_trylock(folio)) { + folio_put(folio); return 0; } } - if (page->mapping != mapping || !PageDirty(page)) { - start += thp_size(page); - unlock_page(page); - put_page(page); + if (folio_mapping(folio) != mapping || + !folio_test_dirty(folio)) { + start += folio_size(folio); + folio_unlock(folio); + folio_put(folio); continue; } - if (PageWriteback(page)) { - unlock_page(page); + if (folio_test_writeback(folio)) { + folio_unlock(folio); if (wbc->sync_mode != WB_SYNC_NONE) - wait_on_page_writeback(page); - put_page(page); + folio_wait_writeback(folio); + folio_put(folio); continue; } - if (!clear_page_dirty_for_io(page)) + if (!folio_clear_dirty_for_io(folio)) BUG(); - ret = afs_write_back_from_locked_page(mapping, wbc, page, start, end); - put_page(page); + ret = afs_write_back_from_locked_folio(mapping, wbc, folio, start, end); + folio_put(folio); if (ret < 0) { _leave(" = %zd", ret); return ret; @@ -862,7 +850,6 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync) vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) { struct folio *folio = page_folio(vmf->page); - struct page *page = &folio->page; struct file *file = vmf->vma->vm_file; struct inode *inode = file_inode(file); struct afs_vnode *vnode = AFS_FS_I(inode); @@ -870,7 +857,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) unsigned long priv; vm_fault_t ret = VM_FAULT_RETRY; - _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, page->index); + _enter("{{%llx:%llu}},{%lx}", vnode->fid.vid, vnode->fid.vnode, folio_index(folio)); afs_validate(vnode, af->key); @@ -880,18 +867,18 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) * be modified. We then assume the entire page will need writing back. */ #ifdef CONFIG_AFS_FSCACHE - if (PageFsCache(page) && - wait_on_page_fscache_killable(page) < 0) + if (folio_test_fscache(folio) && + folio_wait_fscache_killable(folio) < 0) goto out; #endif if (folio_wait_writeback_killable(folio)) goto out; - if (lock_page_killable(page) < 0) + if (folio_lock_killable(folio) < 0) goto out; - /* We mustn't change page->private until writeback is complete as that + /* We mustn't change folio->private until writeback is complete as that * details the portion of the page we need to write back and we might * need to redirty the page if there's a problem. */ @@ -900,14 +887,14 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) goto out; } - priv = afs_page_dirty(page, 0, thp_size(page)); - priv = afs_page_dirty_mmapped(priv); - if (PagePrivate(page)) { - set_page_private(page, priv); - trace_afs_page_dirty(vnode, tracepoint_string("mkwrite+"), page); + priv = afs_folio_dirty(folio, 0, folio_size(folio)); + priv = afs_folio_dirty_mmapped(priv); + if (folio_test_private(folio)) { + folio_change_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite+"), folio); } else { - attach_page_private(page, (void *)priv); - trace_afs_page_dirty(vnode, tracepoint_string("mkwrite"), page); + folio_attach_private(folio, (void *)priv); + trace_afs_folio_dirty(vnode, tracepoint_string("mkwrite"), folio); } file_update_time(file); @@ -948,38 +935,38 @@ void afs_prune_wb_keys(struct afs_vnode *vnode) /* * Clean up a page during invalidation. */ -int afs_launder_page(struct page *page) +int afs_launder_page(struct page *subpage) { - struct address_space *mapping = page->mapping; - struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct folio *folio = page_folio(subpage); + struct afs_vnode *vnode = AFS_FS_I(folio_inode(folio)); struct iov_iter iter; struct bio_vec bv[1]; unsigned long priv; unsigned int f, t; int ret = 0; - _enter("{%lx}", page->index); + _enter("{%lx}", folio_index(folio)); - priv = page_private(page); - if (clear_page_dirty_for_io(page)) { + priv = (unsigned long)folio_get_private(folio); + if (folio_clear_dirty_for_io(folio)) { f = 0; - t = thp_size(page); - if (PagePrivate(page)) { - f = afs_page_dirty_from(page, priv); - t = afs_page_dirty_to(page, priv); + t = folio_size(folio); + if (folio_test_private(folio)) { + f = afs_folio_dirty_from(folio, priv); + t = afs_folio_dirty_to(folio, priv); } - bv[0].bv_page = page; + bv[0].bv_page = &folio->page; bv[0].bv_offset = f; bv[0].bv_len = t - f; iov_iter_bvec(&iter, WRITE, bv, 1, bv[0].bv_len); - trace_afs_page_dirty(vnode, tracepoint_string("launder"), page); - ret = afs_store_data(vnode, &iter, page_offset(page) + f, true); + trace_afs_folio_dirty(vnode, tracepoint_string("launder"), folio); + ret = afs_store_data(vnode, &iter, folio_pos(folio) + f, true); } - trace_afs_page_dirty(vnode, tracepoint_string("laundered"), page); - detach_page_private(page); - wait_on_page_fscache(page); + trace_afs_folio_dirty(vnode, tracepoint_string("laundered"), folio); + folio_detach_private(folio); + folio_wait_fscache(folio); return ret; } diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 99b80b5c7a93..04bbe853bcb1 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -63,7 +63,7 @@ (CONGESTION_ON_THRESH(congestion_kb) >> 2)) static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); static inline struct ceph_snap_context *page_snap_context(struct page *page) { @@ -317,13 +317,14 @@ static const struct netfs_read_request_ops ceph_netfs_read_ops = { }; /* read a single page, without unlocking it. */ -static int ceph_readpage(struct file *file, struct page *page) +static int ceph_readpage(struct file *file, struct page *subpage) { + struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_vino vino = ceph_vino(inode); - u64 off = page_offset(page); - u64 len = thp_size(page); + size_t len = folio_size(folio); + u64 off = folio_file_pos(folio); if (ci->i_inline_version != CEPH_INLINE_NONE) { /* @@ -331,19 +332,19 @@ static int ceph_readpage(struct file *file, struct page *page) * into page cache while getting Fcr caps. */ if (off == 0) { - unlock_page(page); + folio_unlock(folio); return -EINVAL; } - zero_user_segment(page, 0, thp_size(page)); - SetPageUptodate(page); - unlock_page(page); + zero_user_segment(&folio->page, 0, folio_size(folio)); + folio_mark_uptodate(folio); + folio_unlock(folio); return 0; } - dout("readpage ino %llx.%llx file %p off %llu len %llu page %p index %lu\n", - vino.ino, vino.snap, file, off, len, page, page->index); + dout("readpage ino %llx.%llx file %p off %llu len %zu folio %p index %lu\n", + vino.ino, vino.snap, file, off, len, folio, folio_index(folio)); - return netfs_readpage(file, page, &ceph_netfs_read_ops, NULL); + return netfs_readpage(file, folio, &ceph_netfs_read_ops, NULL); } static void ceph_readahead(struct readahead_control *ractl) @@ -1187,18 +1188,18 @@ ceph_find_incompatible(struct page *page) } static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned int len, - struct page *page, void **_fsdata) + struct folio *folio, void **_fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_snap_context *snapc; - snapc = ceph_find_incompatible(page); + snapc = ceph_find_incompatible(folio_page(folio, 0)); if (snapc) { int r; - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (IS_ERR(snapc)) return PTR_ERR(snapc); @@ -1216,12 +1217,12 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned * clean, or already dirty within the same snap context. */ static int ceph_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, + loff_t pos, unsigned len, unsigned aop_flags, struct page **pagep, void **fsdata) { struct inode *inode = file_inode(file); struct ceph_inode_info *ci = ceph_inode(inode); - struct page *page = NULL; + struct folio *folio = NULL; pgoff_t index = pos >> PAGE_SHIFT; int r; @@ -1230,39 +1231,43 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, * for inline_version sent to the MDS. */ if (ci->i_inline_version != CEPH_INLINE_NONE) { - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) + unsigned int fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) return -ENOMEM; /* * The inline_version on a new inode is set to 1. If that's the - * case, then the page is brand new and isn't yet Uptodate. + * case, then the folio is brand new and isn't yet Uptodate. */ r = 0; if (index == 0 && ci->i_inline_version != 1) { - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { WARN_ONCE(1, "ceph: write_begin called on still-inlined inode (inline_version %llu)!\n", ci->i_inline_version); r = -EINVAL; } goto out; } - zero_user_segment(page, 0, thp_size(page)); - SetPageUptodate(page); + zero_user_segment(&folio->page, 0, folio_size(folio)); + folio_mark_uptodate(folio); goto out; } - r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &page, NULL, + r = netfs_write_begin(file, inode->i_mapping, pos, len, 0, &folio, NULL, &ceph_netfs_read_ops, NULL); out: if (r == 0) - wait_on_page_fscache(page); + folio_wait_fscache(folio); if (r < 0) { - if (page) - put_page(page); + if (folio) + folio_put(folio); } else { - WARN_ON_ONCE(!PageLocked(page)); - *pagep = page; + WARN_ON_ONCE(!folio_test_locked(folio)); + *pagep = &folio->page; } return r; } @@ -1273,32 +1278,33 @@ out: */ static int ceph_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata) + struct page *subpage, void *fsdata) { + struct folio *folio = page_folio(subpage); struct inode *inode = file_inode(file); bool check_cap = false; - dout("write_end file %p inode %p page %p %d~%d (%d)\n", file, - inode, page, (int)pos, (int)copied, (int)len); + dout("write_end file %p inode %p folio %p %d~%d (%d)\n", file, + inode, folio, (int)pos, (int)copied, (int)len); - if (!PageUptodate(page)) { + if (!folio_test_uptodate(folio)) { /* just return that nothing was copied on a short copy */ if (copied < len) { copied = 0; goto out; } - SetPageUptodate(page); + folio_mark_uptodate(folio); } /* did file size increase? */ if (pos+copied > i_size_read(inode)) check_cap = ceph_inode_set_size(inode, pos+copied); - set_page_dirty(page); + folio_mark_dirty(folio); out: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (check_cap) ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL); diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 994ec22d4040..9320a42dfaf9 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -230,7 +230,7 @@ static void netfs_rreq_completed(struct netfs_read_request *rreq, bool was_async /* * Deal with the completion of writing the data to the cache. We have to clear - * the PG_fscache bits on the pages involved and release the caller's ref. + * the PG_fscache bits on the folios involved and release the caller's ref. * * May be called in softirq mode and we inherit a ref from the caller. */ @@ -238,7 +238,7 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, bool was_async) { struct netfs_read_subrequest *subreq; - struct page *page; + struct folio *folio; pgoff_t unlocked = 0; bool have_unlocked = false; @@ -247,14 +247,14 @@ static void netfs_rreq_unmark_after_write(struct netfs_read_request *rreq, list_for_each_entry(subreq, &rreq->subrequests, rreq_link) { XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE); - xas_for_each(&xas, page, (subreq->start + subreq->len - 1) / PAGE_SIZE) { + xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) { /* We might have multiple writes from the same huge - * page, but we mustn't unlock a page more than once. + * folio, but we mustn't unlock a folio more than once. */ - if (have_unlocked && page->index <= unlocked) + if (have_unlocked && folio_index(folio) <= unlocked) continue; - unlocked = page->index; - end_page_fscache(page); + unlocked = folio_index(folio); + folio_end_fscache(folio); have_unlocked = true; } } @@ -367,18 +367,17 @@ static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq, } /* - * Unlock the pages in a read operation. We need to set PG_fscache on any - * pages we're going to write back before we unlock them. + * Unlock the folios in a read operation. We need to set PG_fscache on any + * folios we're going to write back before we unlock them. */ static void netfs_rreq_unlock(struct netfs_read_request *rreq) { struct netfs_read_subrequest *subreq; - struct page *page; + struct folio *folio; unsigned int iopos, account = 0; pgoff_t start_page = rreq->start / PAGE_SIZE; pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1; bool subreq_failed = false; - int i; XA_STATE(xas, &rreq->mapping->i_pages, start_page); @@ -403,9 +402,9 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) trace_netfs_rreq(rreq, netfs_rreq_trace_unlock); rcu_read_lock(); - xas_for_each(&xas, page, last_page) { - unsigned int pgpos = (page->index - start_page) * PAGE_SIZE; - unsigned int pgend = pgpos + thp_size(page); + xas_for_each(&xas, folio, last_page) { + unsigned int pgpos = (folio_index(folio) - start_page) * PAGE_SIZE; + unsigned int pgend = pgpos + folio_size(folio); bool pg_failed = false; for (;;) { @@ -414,7 +413,7 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) break; } if (test_bit(NETFS_SREQ_WRITE_TO_CACHE, &subreq->flags)) - set_page_fscache(page); + folio_start_fscache(folio); pg_failed |= subreq_failed; if (pgend < iopos + subreq->len) break; @@ -433,17 +432,16 @@ static void netfs_rreq_unlock(struct netfs_read_request *rreq) } if (!pg_failed) { - for (i = 0; i < thp_nr_pages(page); i++) - flush_dcache_page(page); - SetPageUptodate(page); + flush_dcache_folio(folio); + folio_mark_uptodate(folio); } - if (!test_bit(NETFS_RREQ_DONT_UNLOCK_PAGES, &rreq->flags)) { - if (page->index == rreq->no_unlock_page && - test_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags)) + if (!test_bit(NETFS_RREQ_DONT_UNLOCK_FOLIOS, &rreq->flags)) { + if (folio_index(folio) == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) _debug("no unlock"); else - unlock_page(page); + folio_unlock(folio); } } rcu_read_unlock(); @@ -876,7 +874,6 @@ void netfs_readahead(struct readahead_control *ractl, void *netfs_priv) { struct netfs_read_request *rreq; - struct page *page; unsigned int debug_index = 0; int ret; @@ -911,11 +908,11 @@ void netfs_readahead(struct readahead_control *ractl, } while (rreq->submitted < rreq->len); - /* Drop the refs on the pages here rather than in the cache or + /* Drop the refs on the folios here rather than in the cache or * filesystem. The locks will be dropped in netfs_rreq_unlock(). */ - while ((page = readahead_page(ractl))) - put_page(page); + while (readahead_folio(ractl)) + ; /* If we decrement nr_rd_ops to 0, the ref belongs to us. */ if (atomic_dec_and_test(&rreq->nr_rd_ops)) @@ -935,7 +932,7 @@ EXPORT_SYMBOL(netfs_readahead); /** * netfs_readpage - Helper to manage a readpage request * @file: The file to read from - * @page: The page to read + * @folio: The folio to read * @ops: The network filesystem's operations for the helper to use * @netfs_priv: Private netfs data to be retained in the request * @@ -950,7 +947,7 @@ EXPORT_SYMBOL(netfs_readahead); * This is usable whether or not caching is enabled. */ int netfs_readpage(struct file *file, - struct page *page, + struct folio *folio, const struct netfs_read_request_ops *ops, void *netfs_priv) { @@ -958,23 +955,23 @@ int netfs_readpage(struct file *file, unsigned int debug_index = 0; int ret; - _enter("%lx", page_index(page)); + _enter("%lx", folio_index(folio)); rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) { if (netfs_priv) - ops->cleanup(netfs_priv, page_file_mapping(page)); - unlock_page(page); + ops->cleanup(netfs_priv, folio_file_mapping(folio)); + folio_unlock(folio); return -ENOMEM; } - rreq->mapping = page_file_mapping(page); - rreq->start = page_file_offset(page); - rreq->len = thp_size(page); + rreq->mapping = folio_file_mapping(folio); + rreq->start = folio_file_pos(folio); + rreq->len = folio_size(folio); if (ops->begin_cache_operation) { ret = ops->begin_cache_operation(rreq); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) { - unlock_page(page); + folio_unlock(folio); goto out; } } @@ -1012,40 +1009,40 @@ out: EXPORT_SYMBOL(netfs_readpage); /** - * netfs_skip_page_read - prep a page for writing without reading first - * @page: page being prepared + * netfs_skip_folio_read - prep a folio for writing without reading first + * @folio: The folio being prepared * @pos: starting position for the write * @len: length of write * * In some cases, write_begin doesn't need to read at all: - * - full page write - * - write that lies in a page that is completely beyond EOF - * - write that covers the the page from start to EOF or beyond it + * - full folio write + * - write that lies in a folio that is completely beyond EOF + * - write that covers the folio from start to EOF or beyond it * * If any of these criteria are met, then zero out the unwritten parts - * of the page and return true. Otherwise, return false. + * of the folio and return true. Otherwise, return false. */ -static bool netfs_skip_page_read(struct page *page, loff_t pos, size_t len) +static bool netfs_skip_folio_read(struct folio *folio, loff_t pos, size_t len) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio_inode(folio); loff_t i_size = i_size_read(inode); - size_t offset = offset_in_thp(page, pos); + size_t offset = offset_in_folio(folio, pos); - /* Full page write */ - if (offset == 0 && len >= thp_size(page)) + /* Full folio write */ + if (offset == 0 && len >= folio_size(folio)) return true; - /* pos beyond last page in the file */ + /* pos beyond last folio in the file */ if (pos - offset >= i_size) goto zero_out; - /* Write that covers from the start of the page to EOF or beyond */ + /* Write that covers from the start of the folio to EOF or beyond */ if (offset == 0 && (pos + len) >= i_size) goto zero_out; return false; zero_out: - zero_user_segments(page, 0, offset, offset + len, thp_size(page)); + zero_user_segments(&folio->page, 0, offset, offset + len, folio_size(folio)); return true; } @@ -1054,9 +1051,9 @@ zero_out: * @file: The file to read from * @mapping: The mapping to read from * @pos: File position at which the write will begin - * @len: The length of the write (may extend beyond the end of the page chosen) - * @flags: AOP_* flags - * @_page: Where to put the resultant page + * @len: The length of the write (may extend beyond the end of the folio chosen) + * @aop_flags: AOP_* flags + * @_folio: Where to put the resultant folio * @_fsdata: Place for the netfs to store a cookie * @ops: The network filesystem's operations for the helper to use * @netfs_priv: Private netfs data to be retained in the request @@ -1072,37 +1069,41 @@ zero_out: * issue_op, is mandatory. * * The check_write_begin() operation can be provided to check for and flush - * conflicting writes once the page is grabbed and locked. It is passed a + * conflicting writes once the folio is grabbed and locked. It is passed a * pointer to the fsdata cookie that gets returned to the VM to be passed to * write_end. It is permitted to sleep. It should return 0 if the request - * should go ahead; unlock the page and return -EAGAIN to cause the page to be - * regot; or return an error. + * should go ahead; unlock the folio and return -EAGAIN to cause the folio to + * be regot; or return an error. * * This is usable whether or not caching is enabled. */ int netfs_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned int len, unsigned int flags, - struct page **_page, void **_fsdata, + loff_t pos, unsigned int len, unsigned int aop_flags, + struct folio **_folio, void **_fsdata, const struct netfs_read_request_ops *ops, void *netfs_priv) { struct netfs_read_request *rreq; - struct page *page, *xpage; + struct folio *folio; struct inode *inode = file_inode(file); - unsigned int debug_index = 0; + unsigned int debug_index = 0, fgp_flags; pgoff_t index = pos >> PAGE_SHIFT; int ret; DEFINE_READAHEAD(ractl, file, NULL, mapping, index); retry: - page = grab_cache_page_write_begin(mapping, index, flags); - if (!page) + fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE; + if (aop_flags & AOP_FLAG_NOFS) + fgp_flags |= FGP_NOFS; + folio = __filemap_get_folio(mapping, index, fgp_flags, + mapping_gfp_mask(mapping)); + if (!folio) return -ENOMEM; if (ops->check_write_begin) { /* Allow the netfs (eg. ceph) to flush conflicts. */ - ret = ops->check_write_begin(file, pos, len, page, _fsdata); + ret = ops->check_write_begin(file, pos, len, folio, _fsdata); if (ret < 0) { trace_netfs_failure(NULL, NULL, ret, netfs_fail_check_write_begin); if (ret == -EAGAIN) @@ -1111,28 +1112,28 @@ retry: } } - if (PageUptodate(page)) - goto have_page; + if (folio_test_uptodate(folio)) + goto have_folio; /* If the page is beyond the EOF, we want to clear it - unless it's * within the cache granule containing the EOF, in which case we need * to preload the granule. */ if (!ops->is_cache_enabled(inode) && - netfs_skip_page_read(page, pos, len)) { + netfs_skip_folio_read(folio, pos, len)) { netfs_stat(&netfs_n_rh_write_zskip); - goto have_page_no_wait; + goto have_folio_no_wait; } ret = -ENOMEM; rreq = netfs_alloc_read_request(ops, netfs_priv, file); if (!rreq) goto error; - rreq->mapping = page->mapping; - rreq->start = page_offset(page); - rreq->len = thp_size(page); - rreq->no_unlock_page = page->index; - __set_bit(NETFS_RREQ_NO_UNLOCK_PAGE, &rreq->flags); + rreq->mapping = folio_file_mapping(folio); + rreq->start = folio_file_pos(folio); + rreq->len = folio_size(folio); + rreq->no_unlock_folio = folio_index(folio); + __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); netfs_priv = NULL; if (ops->begin_cache_operation) { @@ -1147,14 +1148,14 @@ retry: /* Expand the request to meet caching requirements and download * preferences. */ - ractl._nr_pages = thp_nr_pages(page); + ractl._nr_pages = folio_nr_pages(folio); netfs_rreq_expand(rreq, &ractl); netfs_get_read_request(rreq); - /* We hold the page locks, so we can drop the references */ - while ((xpage = readahead_page(&ractl))) - if (xpage != page) - put_page(xpage); + /* We hold the folio locks, so we can drop the references */ + folio_get(folio); + while (readahead_folio(&ractl)) + ; atomic_set(&rreq->nr_rd_ops, 1); do { @@ -1184,22 +1185,22 @@ retry: if (ret < 0) goto error; -have_page: - ret = wait_on_page_fscache_killable(page); +have_folio: + ret = folio_wait_fscache_killable(folio); if (ret < 0) goto error; -have_page_no_wait: +have_folio_no_wait: if (netfs_priv) ops->cleanup(netfs_priv, mapping); - *_page = page; + *_folio = folio; _leave(" = 0"); return 0; error_put: netfs_put_read_request(rreq, false); error: - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); if (netfs_priv) ops->cleanup(netfs_priv, mapping); _leave(" = %d", ret); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 12c4177f7703..ca0683b9e3d1 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -166,13 +166,13 @@ struct netfs_read_request { short error; /* 0 or error that occurred */ loff_t i_size; /* Size of the file */ loff_t start; /* Start position */ - pgoff_t no_unlock_page; /* Don't unlock this page after read */ + pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ refcount_t usage; unsigned long flags; #define NETFS_RREQ_INCOMPLETE_IO 0 /* Some ioreqs terminated short or with error */ #define NETFS_RREQ_WRITE_TO_CACHE 1 /* Need to write to the cache */ -#define NETFS_RREQ_NO_UNLOCK_PAGE 2 /* Don't unlock no_unlock_page on completion */ -#define NETFS_RREQ_DONT_UNLOCK_PAGES 3 /* Don't unlock the pages on completion */ +#define NETFS_RREQ_NO_UNLOCK_FOLIO 2 /* Don't unlock no_unlock_folio on completion */ +#define NETFS_RREQ_DONT_UNLOCK_FOLIOS 3 /* Don't unlock the folios on completion */ #define NETFS_RREQ_FAILED 4 /* The request failed */ #define NETFS_RREQ_IN_PROGRESS 5 /* Unlocked when the request completes */ const struct netfs_read_request_ops *netfs_ops; @@ -190,7 +190,7 @@ struct netfs_read_request_ops { void (*issue_op)(struct netfs_read_subrequest *subreq); bool (*is_still_valid)(struct netfs_read_request *rreq); int (*check_write_begin)(struct file *file, loff_t pos, unsigned len, - struct page *page, void **_fsdata); + struct folio *folio, void **_fsdata); void (*done)(struct netfs_read_request *rreq); void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; @@ -240,11 +240,11 @@ extern void netfs_readahead(struct readahead_control *, const struct netfs_read_request_ops *, void *); extern int netfs_readpage(struct file *, - struct page *, + struct folio *, const struct netfs_read_request_ops *, void *); extern int netfs_write_begin(struct file *, struct address_space *, - loff_t, unsigned int, unsigned int, struct page **, + loff_t, unsigned int, unsigned int, struct folio **, void **, const struct netfs_read_request_ops *, void *); diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index bca73e8c8cde..499f5fabd20f 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -1016,31 +1016,32 @@ TRACE_EVENT(afs_dir_check_failed, __entry->vnode, __entry->off, __entry->i_size) ); -TRACE_EVENT(afs_page_dirty, - TP_PROTO(struct afs_vnode *vnode, const char *where, struct page *page), +TRACE_EVENT(afs_folio_dirty, + TP_PROTO(struct afs_vnode *vnode, const char *where, struct folio *folio), - TP_ARGS(vnode, where, page), + TP_ARGS(vnode, where, folio), TP_STRUCT__entry( __field(struct afs_vnode *, vnode ) __field(const char *, where ) - __field(pgoff_t, page ) + __field(pgoff_t, index ) __field(unsigned long, from ) __field(unsigned long, to ) ), TP_fast_assign( + unsigned long priv = (unsigned long)folio_get_private(folio); __entry->vnode = vnode; __entry->where = where; - __entry->page = page->index; - __entry->from = afs_page_dirty_from(page, page->private); - __entry->to = afs_page_dirty_to(page, page->private); - __entry->to |= (afs_is_page_dirty_mmapped(page->private) ? - (1UL << (BITS_PER_LONG - 1)) : 0); + __entry->index = folio_index(folio); + __entry->from = afs_folio_dirty_from(folio, priv); + __entry->to = afs_folio_dirty_to(folio, priv); + __entry->to |= (afs_is_folio_dirty_mmapped(priv) ? + (1UL << (BITS_PER_LONG - 1)) : 0); ), TP_printk("vn=%p %lx %s %lx-%lx%s", - __entry->vnode, __entry->page, __entry->where, + __entry->vnode, __entry->index, __entry->where, __entry->from, __entry->to & ~(1UL << (BITS_PER_LONG - 1)), __entry->to & (1UL << (BITS_PER_LONG - 1)) ? " M" : "") -- cgit v1.2.3 From f89315650ba34ec6c91a8bded72796980bee2a4d Mon Sep 17 00:00:00 2001 From: Mark Pashmfouroush Date: Wed, 10 Nov 2021 11:10:15 +0000 Subject: bpf: Add ingress_ifindex to bpf_sk_lookup It may be helpful to have access to the ifindex during bpf socket lookup. An example may be to scope certain socket lookup logic to specific interfaces, i.e. an interface may be made exempt from custom lookup code. Add the ifindex of the arriving connection to the bpf_sk_lookup API. Signed-off-by: Mark Pashmfouroush Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211110111016.5670-2-markpash@cloudflare.com --- include/linux/filter.h | 7 +++++-- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 7 +++++++ net/ipv4/inet_hashtables.c | 8 ++++---- net/ipv4/udp.c | 8 ++++---- net/ipv6/inet6_hashtables.c | 8 ++++---- net/ipv6/udp.c | 8 ++++---- tools/include/uapi/linux/bpf.h | 1 + 8 files changed, 30 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 24b7ed2677af..b6a216eb217a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1374,6 +1374,7 @@ struct bpf_sk_lookup_kern { const struct in6_addr *daddr; } v6; struct sock *selected_sk; + u32 ingress_ifindex; bool no_reuseport; }; @@ -1436,7 +1437,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1452,6 +1453,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, .v4.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; @@ -1474,7 +1476,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const __be16 sport, const struct in6_addr *daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1490,6 +1492,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, .v6.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 509eee5f0393..6297eafdc40f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6316,6 +6316,7 @@ struct bpf_sk_lookup { __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* diff --git a/net/core/filter.c b/net/core/filter.c index 8e8d3b49c297..315a58466fc9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10491,6 +10491,7 @@ static bool sk_lookup_is_valid_access(int off, int size, case bpf_ctx_range_till(struct bpf_sk_lookup, local_ip6[0], local_ip6[3]): case bpf_ctx_range(struct bpf_sk_lookup, remote_port): case bpf_ctx_range(struct bpf_sk_lookup, local_port): + case bpf_ctx_range(struct bpf_sk_lookup, ingress_ifindex): bpf_ctx_record_field_size(info, sizeof(__u32)); return bpf_ctx_narrow_access_ok(off, size, sizeof(__u32)); @@ -10580,6 +10581,12 @@ static u32 sk_lookup_convert_ctx_access(enum bpf_access_type type, bpf_target_off(struct bpf_sk_lookup_kern, dport, 2, target_size)); break; + + case offsetof(struct bpf_sk_lookup, ingress_ifindex): + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + bpf_target_off(struct bpf_sk_lookup_kern, + ingress_ifindex, 4, target_size)); + break; } return insn - insn_buf; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 75737267746f..30ab717ff1b8 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -307,7 +307,7 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum) + __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -315,8 +315,8 @@ static inline struct sock *inet_lookup_run_bpf(struct net *net, if (hashinfo != &tcp_hashinfo) return NULL; /* only TCP is supported */ - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_TCP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -340,7 +340,7 @@ struct sock *__inet_lookup_listener(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (result) goto done; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 2fffcf2b54f3..5fceee3de65d 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -460,7 +460,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, struct udp_table *udptable, struct sk_buff *skb, __be32 saddr, __be16 sport, - __be32 daddr, u16 hnum) + __be32 daddr, u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -468,8 +468,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net, if (udptable != &udp_table) return NULL; /* only UDP is supported */ - no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -505,7 +505,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp4_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (sk) { result = sk; goto done; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 67c9114835c8..4514444e96c8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -165,7 +165,7 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, - const u16 hnum) + const u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -173,8 +173,8 @@ static inline struct sock *inet6_lookup_run_bpf(struct net *net, if (hashinfo != &tcp_hashinfo) return NULL; /* only TCP is supported */ - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_TCP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -198,7 +198,7 @@ struct sock *inet6_lookup_listener(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { result = inet6_lookup_run_bpf(net, hashinfo, skb, doff, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (result) goto done; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 12c12619ee35..ea4ea525f94a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -195,7 +195,7 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, - u16 hnum) + u16 hnum, const int dif) { struct sock *sk, *reuse_sk; bool no_reuseport; @@ -203,8 +203,8 @@ static inline struct sock *udp6_lookup_run_bpf(struct net *net, if (udptable != &udp_table) return NULL; /* only UDP is supported */ - no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, - saddr, sport, daddr, hnum, &sk); + no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport, + daddr, hnum, dif, &sk); if (no_reuseport || IS_ERR_OR_NULL(sk)) return sk; @@ -240,7 +240,7 @@ struct sock *__udp6_lib_lookup(struct net *net, /* Lookup redirect from BPF */ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) { sk = udp6_lookup_run_bpf(net, udptable, skb, - saddr, sport, daddr, hnum); + saddr, sport, daddr, hnum, dif); if (sk) { result = sk; goto done; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 509eee5f0393..6297eafdc40f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6316,6 +6316,7 @@ struct bpf_sk_lookup { __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* -- cgit v1.2.3 From 68dbbe7d5b4fde736d104cbbc9a2fce875562012 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 4 Nov 2021 17:31:58 +0900 Subject: libata: fix read log timeout value Some ATA drives are very slow to respond to READ_LOG_EXT and READ_LOG_DMA_EXT commands issued from ata_dev_configure() when the device is revalidated right after resuming a system or inserting the ATA adapter driver (e.g. ahci). The default 5s timeout (ATA_EH_CMD_DFL_TIMEOUT) used for these commands is too short, causing errors during the device configuration. Ex: ... ata9: SATA max UDMA/133 abar m524288@0x9d200000 port 0x9d200400 irq 209 ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300) ata9.00: ATA-9: XXX XXXXXXXXXXXXXXX, XXXXXXXX, max UDMA/133 ata9.00: qc timeout (cmd 0x2f) ata9.00: Read log page 0x00 failed, Emask 0x4 ata9.00: Read log page 0x00 failed, Emask 0x40 ata9.00: NCQ Send/Recv Log not supported ata9.00: Read log page 0x08 failed, Emask 0x40 ata9.00: 27344764928 sectors, multi 16: LBA48 NCQ (depth 32), AA ata9.00: Read log page 0x00 failed, Emask 0x40 ata9.00: ATA Identify Device Log not supported ata9.00: failed to set xfermode (err_mask=0x40) ata9: SATA link up 6.0 Gbps (SStatus 133 SControl 300) ata9.00: configured for UDMA/133 ... The timeout error causes a soft reset of the drive link, followed in most cases by a successful revalidation as that give enough time to the drive to become fully ready to quickly process the read log commands. However, in some cases, this also fails resulting in the device being dropped. Fix this by using adding the ata_eh_revalidate_timeouts entries for the READ_LOG_EXT and READ_LOG_DMA_EXT commands. This defines a timeout increased to 15s, retriable one time. Reported-by: Geert Uytterhoeven Tested-by: Geert Uytterhoeven Cc: stable@vger.kernel.org Signed-off-by: Damien Le Moal --- drivers/ata/libata-eh.c | 8 ++++++++ include/linux/libata.h | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index bf9c4b6c5c3d..1d4a6f1e88cd 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -93,6 +93,12 @@ static const unsigned long ata_eh_identify_timeouts[] = { ULONG_MAX, }; +static const unsigned long ata_eh_revalidate_timeouts[] = { + 15000, /* Some drives are slow to read log pages when waking-up */ + 15000, /* combined time till here is enough even for media access */ + ULONG_MAX, +}; + static const unsigned long ata_eh_flush_timeouts[] = { 15000, /* be generous with flush */ 15000, /* ditto */ @@ -129,6 +135,8 @@ static const struct ata_eh_cmd_timeout_ent ata_eh_cmd_timeout_table[ATA_EH_CMD_TIMEOUT_TABLE_SIZE] = { { .commands = CMDS(ATA_CMD_ID_ATA, ATA_CMD_ID_ATAPI), .timeouts = ata_eh_identify_timeouts, }, + { .commands = CMDS(ATA_CMD_READ_LOG_EXT, ATA_CMD_READ_LOG_DMA_EXT), + .timeouts = ata_eh_revalidate_timeouts, }, { .commands = CMDS(ATA_CMD_READ_NATIVE_MAX, ATA_CMD_READ_NATIVE_MAX_EXT), .timeouts = ata_eh_other_timeouts, }, { .commands = CMDS(ATA_CMD_SET_MAX, ATA_CMD_SET_MAX_EXT), diff --git a/include/linux/libata.h b/include/linux/libata.h index 2884383f1718..5331557316e8 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -394,7 +394,7 @@ enum { /* This should match the actual table size of * ata_eh_cmd_timeout_table in libata-eh.c. */ - ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 6, + ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7, /* Horkage types. May be set by libata or controller on drives (some horkage may be drive/controller pair dependent */ -- cgit v1.2.3 From a25efb3863d068929f0bbeb87a995df11507e691 Mon Sep 17 00:00:00 2001 From: Christian König Date: Thu, 23 Sep 2021 13:57:42 +0200 Subject: dma-buf: add dma_fence_describe and dma_resv_describe v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add functions to dump dma_fence and dma_resv objects into a seq_file and use them for printing the debugfs information. v2: fix missing include reported by test robot. Signed-off-by: Christian König Reviewed-by: Rob Clark Link: https://patchwork.freedesktop.org/patch/msgid/20211103081231.18578-2-christian.koenig@amd.com --- drivers/dma-buf/dma-buf.c | 11 +---------- drivers/dma-buf/dma-fence.c | 17 +++++++++++++++++ drivers/dma-buf/dma-resv.c | 23 +++++++++++++++++++++++ include/linux/dma-fence.h | 1 + include/linux/dma-resv.h | 1 + 5 files changed, 43 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 3f63d58bf68a..385cd037325e 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -1321,8 +1321,6 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) { struct dma_buf *buf_obj; struct dma_buf_attachment *attach_obj; - struct dma_resv_iter cursor; - struct dma_fence *fence; int count = 0, attach_count; size_t size = 0; int ret; @@ -1350,14 +1348,7 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused) file_inode(buf_obj->file)->i_ino, buf_obj->name ?: ""); - dma_resv_for_each_fence(&cursor, buf_obj->resv, true, fence) { - seq_printf(s, "\t%s fence: %s %s %ssignalled\n", - dma_resv_iter_is_exclusive(&cursor) ? - "Exclusive" : "Shared", - fence->ops->get_driver_name(fence), - fence->ops->get_timeline_name(fence), - dma_fence_is_signaled(fence) ? "" : "un"); - } + dma_resv_describe(buf_obj->resv, s); seq_puts(s, "\tAttached Devices:\n"); attach_count = 0; diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 1e82ecd443fa..066400ed8841 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -15,6 +15,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -907,6 +908,22 @@ err_free_cb: } EXPORT_SYMBOL(dma_fence_wait_any_timeout); +/** + * dma_fence_describe - Dump fence describtion into seq_file + * @fence: the 6fence to describe + * @seq: the seq_file to put the textual description into + * + * Dump a textual description of the fence and it's state into the seq_file. + */ +void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq) +{ + seq_printf(seq, "%s %s seq %llu %ssignalled\n", + fence->ops->get_driver_name(fence), + fence->ops->get_timeline_name(fence), fence->seqno, + dma_fence_is_signaled(fence) ? "" : "un"); +} +EXPORT_SYMBOL(dma_fence_describe); + /** * dma_fence_init - Initialize a custom fence. * @fence: the fence to initialize diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c index 9eb2baa387d4..ff3c0558b3b8 100644 --- a/drivers/dma-buf/dma-resv.c +++ b/drivers/dma-buf/dma-resv.c @@ -38,6 +38,7 @@ #include #include #include +#include /** * DOC: Reservation Object Overview @@ -666,6 +667,28 @@ bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all) } EXPORT_SYMBOL_GPL(dma_resv_test_signaled); +/** + * dma_resv_describe - Dump description of the resv object into seq_file + * @obj: the reservation object + * @seq: the seq_file to dump the description into + * + * Dump a textual description of the fences inside an dma_resv object into the + * seq_file. + */ +void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq) +{ + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_for_each_fence(&cursor, obj, true, fence) { + seq_printf(seq, "\t%s fence:", + dma_resv_iter_is_exclusive(&cursor) ? + "Exclusive" : "Shared"); + dma_fence_describe(fence, seq); + } +} +EXPORT_SYMBOL_GPL(dma_resv_describe); + #if IS_ENABLED(CONFIG_LOCKDEP) static int __init dma_resv_lockdep(void) { diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index a706b7bf51d7..1ea691753bd3 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -264,6 +264,7 @@ void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops, void dma_fence_release(struct kref *kref); void dma_fence_free(struct dma_fence *fence); +void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq); /** * dma_fence_put - decreases refcount of the fence diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index dbd235ab447f..09c6063b199a 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -490,5 +490,6 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src); long dma_resv_wait_timeout(struct dma_resv *obj, bool wait_all, bool intr, unsigned long timeout); bool dma_resv_test_signaled(struct dma_resv *obj, bool test_all); +void dma_resv_describe(struct dma_resv *obj, struct seq_file *seq); #endif /* _LINUX_RESERVATION_H */ -- cgit v1.2.3 From 9c8e9c9681a0f3f1ae90a90230d059c7a1dece5a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 4 Nov 2021 00:27:29 +0100 Subject: PCI/MSI: Move non-mask check back into low level accessors The recent rework of PCI/MSI[X] masking moved the non-mask checks from the low level accessors into the higher level mask/unmask functions. This missed the fact that these accessors can be invoked from other places as well. The missing checks break XEN-PV which sets pci_msi_ignore_mask and also violates the virtual MSIX and the msi_attrib.maskbit protections. Instead of sprinkling checks all over the place, lift them back into the low level accessor functions. To avoid checking three different conditions combine them into one property of msi_desc::msi_attrib. [ josef: Fixed the missed conversion in the core code ] Fixes: fcacdfbef5a1 ("PCI/MSI: Provide a new set of mask and unmask functions") Reported-by: Josef Johansson Signed-off-by: Thomas Gleixner Tested-by: Josef Johansson Cc: Bjorn Helgaas Cc: stable@vger.kernel.org --- drivers/pci/msi.c | 26 ++++++++++++++------------ include/linux/msi.h | 2 +- kernel/irq/msi.c | 4 ++-- 3 files changed, 17 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 12e296d634eb..6da791022d2e 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -148,6 +148,9 @@ static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 s raw_spinlock_t *lock = &desc->dev->msi_lock; unsigned long flags; + if (!desc->msi_attrib.can_mask) + return; + raw_spin_lock_irqsave(lock, flags); desc->msi_mask &= ~clear; desc->msi_mask |= set; @@ -181,7 +184,8 @@ static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl) { void __iomem *desc_addr = pci_msix_desc_addr(desc); - writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + if (desc->msi_attrib.can_mask) + writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } static inline void pci_msix_mask(struct msi_desc *desc) @@ -200,23 +204,17 @@ static inline void pci_msix_unmask(struct msi_desc *desc) static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) { - if (pci_msi_ignore_mask || desc->msi_attrib.is_virtual) - return; - if (desc->msi_attrib.is_msix) pci_msix_mask(desc); - else if (desc->msi_attrib.maskbit) + else pci_msi_mask(desc, mask); } static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask) { - if (pci_msi_ignore_mask || desc->msi_attrib.is_virtual) - return; - if (desc->msi_attrib.is_msix) pci_msix_unmask(desc); - else if (desc->msi_attrib.maskbit) + else pci_msi_unmask(desc, mask); } @@ -484,7 +482,8 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); entry->msi_attrib.is_virtual = 0; entry->msi_attrib.entry_nr = 0; - entry->msi_attrib.maskbit = !!(control & PCI_MSI_FLAGS_MASKBIT); + entry->msi_attrib.can_mask = !pci_msi_ignore_mask && + !!(control & PCI_MSI_FLAGS_MASKBIT); entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ entry->msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1; entry->msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec)); @@ -495,7 +494,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32; /* Save the initial mask status */ - if (entry->msi_attrib.maskbit) + if (entry->msi_attrib.can_mask) pci_read_config_dword(dev, entry->mask_pos, &entry->msi_mask); out: @@ -639,10 +638,13 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.is_virtual = entry->msi_attrib.entry_nr >= vec_count; + entry->msi_attrib.can_mask = !pci_msi_ignore_mask && + !entry->msi_attrib.is_virtual; + entry->msi_attrib.default_irq = dev->irq; entry->mask_base = base; - if (!entry->msi_attrib.is_virtual) { + if (entry->msi_attrib.can_mask) { addr = pci_msix_desc_addr(entry); entry->msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } diff --git a/include/linux/msi.h b/include/linux/msi.h index 49cf6eb222e7..e616f94c7c58 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -148,7 +148,7 @@ struct msi_desc { u8 is_msix : 1; u8 multiple : 3; u8 multi_cap : 3; - u8 maskbit : 1; + u8 can_mask : 1; u8 is_64 : 1; u8 is_virtual : 1; u16 entry_nr; diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 6a5ecee6e567..7f350ae59c5f 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -529,10 +529,10 @@ static bool msi_check_reservation_mode(struct irq_domain *domain, /* * Checking the first MSI descriptor is sufficient. MSIX supports - * masking and MSI does so when the maskbit is set. + * masking and MSI does so when the can_mask attribute is set. */ desc = first_msi_entry(dev); - return desc->msi_attrib.is_msix || desc->msi_attrib.maskbit; + return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask; } int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, -- cgit v1.2.3 From 2226667a145db2e1f314d7f57fd644fe69863ab9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 4 Nov 2021 18:01:29 +0000 Subject: PCI/MSI: Deal with devices lying about their MSI mask capability It appears that some devices are lying about their mask capability, pretending that they don't have it, while they actually do. The net result is that now that we don't enable MSIs on such endpoint. Add a new per-device flag to deal with this. Further patches will make use of it, sadly. Signed-off-by: Marc Zyngier Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Link: https://lore.kernel.org/r/20211104180130.3825416-2-maz@kernel.org Cc: Bjorn Helgaas --- drivers/pci/msi.c | 3 +++ include/linux/pci.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 6da791022d2e..70433013897b 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -477,6 +477,9 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) goto out; pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); + /* Lies, damned lies, and MSIs */ + if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING) + control |= PCI_MSI_FLAGS_MASKBIT; entry->msi_attrib.is_msix = 0; entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); diff --git a/include/linux/pci.h b/include/linux/pci.h index c8afbee5da4b..d0dba7fd9848 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -233,6 +233,8 @@ enum pci_dev_flags { PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10), /* Don't use Relaxed Ordering for TLPs directed at this device */ PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 11), + /* Device does honor MSI masking despite saying otherwise */ + PCI_DEV_FLAGS_HAS_MSI_MASKING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { -- cgit v1.2.3 From a8b76910e465d718effce0cad306a21fa4f3526b Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 10 Nov 2021 20:24:44 +0000 Subject: preempt: Restore preemption model selection configs Commit c597bfddc9e9 ("sched: Provide Kconfig support for default dynamic preempt mode") changed the selectable config names for the preemption model. This means a config file must now select CONFIG_PREEMPT_BEHAVIOUR=y rather than CONFIG_PREEMPT=y to get a preemptible kernel. This means all arch config files would need to be updated - right now they'll all end up with the default CONFIG_PREEMPT_NONE_BEHAVIOUR. Rather than touch a good hundred of config files, restore usage of CONFIG_PREEMPT{_NONE, _VOLUNTARY}. Make them configure: o The build-time preemption model when !PREEMPT_DYNAMIC o The default boot-time preemption model when PREEMPT_DYNAMIC Add siblings of those configs with the _BUILD suffix to unconditionally designate the build-time preemption model (PREEMPT_DYNAMIC is built with the "highest" preemption model it supports, aka PREEMPT). Downstream configs should by now all be depending / selected by CONFIG_PREEMPTION rather than CONFIG_PREEMPT, so only a few sites need patching up. Signed-off-by: Valentin Schneider Signed-off-by: Peter Zijlstra (Intel) Acked-by: Marco Elver Link: https://lore.kernel.org/r/20211110202448.4054153-2-valentin.schneider@arm.com --- include/linux/kernel.h | 2 +- include/linux/vermagic.h | 2 +- init/Makefile | 2 +- kernel/Kconfig.preempt | 42 +++++++++++++++++++++--------------------- kernel/sched/core.c | 6 +++--- 5 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 968b4c4fe65b..77755ac3e189 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -85,7 +85,7 @@ struct completion; struct user; -#ifdef CONFIG_PREEMPT_VOLUNTARY +#ifdef CONFIG_PREEMPT_VOLUNTARY_BUILD extern int __cond_resched(void); # define might_resched() __cond_resched() diff --git a/include/linux/vermagic.h b/include/linux/vermagic.h index 1eaaa93c37bf..329d63babaeb 100644 --- a/include/linux/vermagic.h +++ b/include/linux/vermagic.h @@ -15,7 +15,7 @@ #else #define MODULE_VERMAGIC_SMP "" #endif -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPT_BUILD #define MODULE_VERMAGIC_PREEMPT "preempt " #elif defined(CONFIG_PREEMPT_RT) #define MODULE_VERMAGIC_PREEMPT "preempt_rt " diff --git a/init/Makefile b/init/Makefile index 2846113677ee..04eeee12c076 100644 --- a/init/Makefile +++ b/init/Makefile @@ -30,7 +30,7 @@ $(obj)/version.o: include/generated/compile.h quiet_cmd_compile.h = CHK $@ cmd_compile.h = \ $(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ - "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" \ + "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT_BUILD)" \ "$(CONFIG_PREEMPT_RT)" $(CONFIG_CC_VERSION_TEXT) "$(LD)" include/generated/compile.h: FORCE diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index 60f1bfc3c7b2..ce77f0265660 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -1,12 +1,23 @@ # SPDX-License-Identifier: GPL-2.0-only +config PREEMPT_NONE_BUILD + bool + +config PREEMPT_VOLUNTARY_BUILD + bool + +config PREEMPT_BUILD + bool + select PREEMPTION + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + choice prompt "Preemption Model" - default PREEMPT_NONE_BEHAVIOUR + default PREEMPT_NONE -config PREEMPT_NONE_BEHAVIOUR +config PREEMPT_NONE bool "No Forced Preemption (Server)" - select PREEMPT_NONE if !PREEMPT_DYNAMIC + select PREEMPT_NONE_BUILD if !PREEMPT_DYNAMIC help This is the traditional Linux preemption model, geared towards throughput. It will still provide good latencies most of the @@ -18,10 +29,10 @@ config PREEMPT_NONE_BEHAVIOUR raw processing power of the kernel, irrespective of scheduling latencies. -config PREEMPT_VOLUNTARY_BEHAVIOUR +config PREEMPT_VOLUNTARY bool "Voluntary Kernel Preemption (Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT_VOLUNTARY if !PREEMPT_DYNAMIC + select PREEMPT_VOLUNTARY_BUILD if !PREEMPT_DYNAMIC help This option reduces the latency of the kernel by adding more "explicit preemption points" to the kernel code. These new @@ -37,10 +48,10 @@ config PREEMPT_VOLUNTARY_BEHAVIOUR Select this if you are building a kernel for a desktop system. -config PREEMPT_BEHAVIOUR +config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT + select PREEMPT_BUILD help This option reduces the latency of the kernel by making all kernel code (that is not executing in a critical section) @@ -58,7 +69,7 @@ config PREEMPT_BEHAVIOUR config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" - depends on EXPERT && ARCH_SUPPORTS_RT && !PREEMPT_DYNAMIC + depends on EXPERT && ARCH_SUPPORTS_RT select PREEMPTION help This option turns the kernel into a real-time kernel by replacing @@ -75,17 +86,6 @@ config PREEMPT_RT endchoice -config PREEMPT_NONE - bool - -config PREEMPT_VOLUNTARY - bool - -config PREEMPT - bool - select PREEMPTION - select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK - config PREEMPT_COUNT bool @@ -95,8 +95,8 @@ config PREEMPTION config PREEMPT_DYNAMIC bool "Preemption behaviour defined on boot" - depends on HAVE_PREEMPT_DYNAMIC - select PREEMPT + depends on HAVE_PREEMPT_DYNAMIC && !PREEMPT_RT + select PREEMPT_BUILD default y help This option allows to define the preemption model on the kernel diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 862af1db22ab..3c9b0fda64ac 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6628,13 +6628,13 @@ __setup("preempt=", setup_preempt_mode); static void __init preempt_dynamic_init(void) { if (preempt_dynamic_mode == preempt_dynamic_undefined) { - if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) { + if (IS_ENABLED(CONFIG_PREEMPT_NONE)) { sched_dynamic_update(preempt_dynamic_none); - } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) { + } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { sched_dynamic_update(preempt_dynamic_voluntary); } else { /* Default static call setting, nothing to do */ - WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR)); + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); preempt_dynamic_mode = preempt_dynamic_full; pr_info("Dynamic Preempt: full\n"); } -- cgit v1.2.3 From 2f70ddb1f71814aae525c58086fcb2f6974e6591 Mon Sep 17 00:00:00 2001 From: Ashish Kalra Date: Tue, 24 Aug 2021 11:06:40 +0000 Subject: EFI: Introduce the new AMD Memory Encryption GUID. Introduce a new AMD Memory Encryption GUID which is currently used for defining a new UEFI environment variable which indicates UEFI/OVMF support for the SEV live migration feature. This variable is setup when UEFI/OVMF detects host/hypervisor support for SEV live migration and later this variable is read by the kernel using EFI runtime services to verify if OVMF supports the live migration feature. Signed-off-by: Ashish Kalra Acked-by: Ard Biesheuvel Message-Id: <1cea22976d2208f34d47e0c1ce0ecac816c13111.1629726117.git.ashish.kalra@amd.com> Signed-off-by: Paolo Bonzini --- include/linux/efi.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index 6b5d36babfcc..dbd39b20e034 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -362,6 +362,7 @@ void efi_native_runtime_setup(void); /* OEM GUIDs */ #define DELLEMC_EFI_RCI2_TABLE_GUID EFI_GUID(0x2d9f28a2, 0xa886, 0x456a, 0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55) +#define AMD_SEV_MEM_ENCRYPT_GUID EFI_GUID(0x0cf29b71, 0x9e51, 0x433a, 0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75) typedef struct { efi_guid_t guid; -- cgit v1.2.3 From f4d316537059b274452727e86f46ff3bdefdde4d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Nov 2021 10:13:38 -0500 Subject: KVM: generalize "bugged" VM to "dead" VM Generalize KVM_REQ_VM_BUGGED so that it can be called even in cases where it is by design that the VM cannot be operated upon. In this case any KVM_BUG_ON should still warn, so introduce a new flag kvm->vm_dead that is separate from kvm->vm_bugged. Suggested-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 12 ++++++++++-- virt/kvm/kvm_main.c | 10 +++++----- 3 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ac83d873d65b..622cb75f5e75 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9654,7 +9654,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_request_pending(vcpu)) { - if (kvm_check_request(KVM_REQ_VM_BUGGED, vcpu)) { + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 60a35d9fe259..9e0667e3723e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -150,7 +150,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_MMU_RELOAD (1 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 -#define KVM_REQ_VM_BUGGED (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -617,6 +617,7 @@ struct kvm { unsigned int max_halt_poll_ns; u32 dirty_ring_size; bool vm_bugged; + bool vm_dead; #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; @@ -650,12 +651,19 @@ struct kvm { #define vcpu_err(vcpu, fmt, ...) \ kvm_err("vcpu%i " fmt, (vcpu)->vcpu_id, ## __VA_ARGS__) +static inline void kvm_vm_dead(struct kvm *kvm) +{ + kvm->vm_dead = true; + kvm_make_all_cpus_request(kvm, KVM_REQ_VM_DEAD); +} + static inline void kvm_vm_bugged(struct kvm *kvm) { kvm->vm_bugged = true; - kvm_make_all_cpus_request(kvm, KVM_REQ_VM_BUGGED); + kvm_vm_dead(kvm); } + #define KVM_BUG(cond, kvm, fmt...) \ ({ \ int __ret = (cond); \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3f6d450355f0..d31724500501 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3747,7 +3747,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; - if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) @@ -3957,7 +3957,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, void __user *argp = compat_ptr(arg); int r; - if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -4023,7 +4023,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; - if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged) + if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -4345,7 +4345,7 @@ static long kvm_vm_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; - if (kvm->mm != current->mm || kvm->vm_bugged) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: @@ -4556,7 +4556,7 @@ static long kvm_vm_compat_ioctl(struct file *filp, struct kvm *kvm = filp->private_data; int r; - if (kvm->mm != current->mm || kvm->vm_bugged) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT -- cgit v1.2.3 From 0093de693fe7baf31641d1863793e6db93a43b6e Mon Sep 17 00:00:00 2001 From: Yixuan Cao Date: Wed, 10 Nov 2021 20:32:30 -0800 Subject: mm/page_owner.c: modify the type of argument "order" in some functions The type of "order" in struct page_owner is unsigned short. However, it is unsigned int in the following 3 functions: __reset_page_owner __set_page_owner_handle __set_page_owner_handle The type of "order" in argument list is unsigned int, which is inconsistent. [akpm@linux-foundation.org: update include/linux/page_owner.h] Link: https://lkml.kernel.org/r/20211020125945.47792-1-caoyixuan2019@email.szu.edu.cn Signed-off-by: Yixuan Cao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_owner.h | 12 ++++++------ mm/page_owner.c | 6 +++--- 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h index 43c638c51c1f..119a0c9d2a8b 100644 --- a/include/linux/page_owner.h +++ b/include/linux/page_owner.h @@ -8,9 +8,9 @@ extern struct static_key_false page_owner_inited; extern struct page_ext_operations page_owner_ops; -extern void __reset_page_owner(struct page *page, unsigned int order); +extern void __reset_page_owner(struct page *page, unsigned short order); extern void __set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask); + unsigned short order, gfp_t gfp_mask); extern void __split_page_owner(struct page *page, unsigned int nr); extern void __folio_copy_owner(struct folio *newfolio, struct folio *old); extern void __set_page_owner_migrate_reason(struct page *page, int reason); @@ -18,14 +18,14 @@ extern void __dump_page_owner(const struct page *page); extern void pagetypeinfo_showmixedcount_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone); -static inline void reset_page_owner(struct page *page, unsigned int order) +static inline void reset_page_owner(struct page *page, unsigned short order) { if (static_branch_unlikely(&page_owner_inited)) __reset_page_owner(page, order); } static inline void set_page_owner(struct page *page, - unsigned int order, gfp_t gfp_mask) + unsigned short order, gfp_t gfp_mask) { if (static_branch_unlikely(&page_owner_inited)) __set_page_owner(page, order, gfp_mask); @@ -52,7 +52,7 @@ static inline void dump_page_owner(const struct page *page) __dump_page_owner(page); } #else -static inline void reset_page_owner(struct page *page, unsigned int order) +static inline void reset_page_owner(struct page *page, unsigned short order) { } static inline void set_page_owner(struct page *page, @@ -60,7 +60,7 @@ static inline void set_page_owner(struct page *page, { } static inline void split_page_owner(struct page *page, - unsigned int order) + unsigned short order) { } static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio) diff --git a/mm/page_owner.c b/mm/page_owner.c index 79936db59859..4f924957ce7a 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -125,7 +125,7 @@ static noinline depot_stack_handle_t save_stack(gfp_t flags) return handle; } -void __reset_page_owner(struct page *page, unsigned int order) +void __reset_page_owner(struct page *page, unsigned short order) { int i; struct page_ext *page_ext; @@ -149,7 +149,7 @@ void __reset_page_owner(struct page *page, unsigned int order) static inline void __set_page_owner_handle(struct page_ext *page_ext, depot_stack_handle_t handle, - unsigned int order, gfp_t gfp_mask) + unsigned short order, gfp_t gfp_mask) { struct page_owner *page_owner; int i; @@ -169,7 +169,7 @@ static inline void __set_page_owner_handle(struct page_ext *page_ext, } } -noinline void __set_page_owner(struct page *page, unsigned int order, +noinline void __set_page_owner(struct page *page, unsigned short order, gfp_t gfp_mask) { struct page_ext *page_ext = lookup_page_ext(page); -- cgit v1.2.3 From ab09243aa95a72bac5c71e852773de34116f8d0f Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Wed, 10 Nov 2021 20:32:40 -0800 Subject: mm/migrate.c: remove MIGRATE_PFN_LOCKED MIGRATE_PFN_LOCKED is used to indicate to migrate_vma_prepare() that a source page was already locked during migrate_vma_collect(). If it wasn't then the a second attempt is made to lock the page. However if the first attempt failed it's unlikely a second attempt will succeed, and the retry adds complexity. So clean this up by removing the retry and MIGRATE_PFN_LOCKED flag. Destination pages are also meant to have the MIGRATE_PFN_LOCKED flag set, but nothing actually checks that. Link: https://lkml.kernel.org/r/20211025041608.289017-1-apopple@nvidia.com Signed-off-by: Alistair Popple Reviewed-by: Ralph Campbell Acked-by: Felix Kuehling Cc: Alex Deucher Cc: Jerome Glisse Cc: John Hubbard Cc: Zi Yan Cc: Christoph Hellwig Cc: Ben Skeggs Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/hmm.rst | 2 +- arch/powerpc/kvm/book3s_hv_uvmem.c | 4 +- drivers/gpu/drm/amd/amdkfd/kfd_migrate.c | 2 - drivers/gpu/drm/nouveau/nouveau_dmem.c | 4 +- include/linux/migrate.h | 1 - lib/test_hmm.c | 5 +- mm/migrate.c | 145 ++++++------------------------- 7 files changed, 35 insertions(+), 128 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/hmm.rst b/Documentation/vm/hmm.rst index a14c2938e7af..f2a59ed82ed3 100644 --- a/Documentation/vm/hmm.rst +++ b/Documentation/vm/hmm.rst @@ -360,7 +360,7 @@ between device driver specific code and shared common code: system memory page, locks the page with ``lock_page()``, and fills in the ``dst`` array entry with:: - dst[i] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + dst[i] = migrate_pfn(page_to_pfn(dpage)); Now that the driver knows that this page is being migrated, it can invalidate device private MMU mappings and copy device private memory diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index a7061ee3b157..28c436df9935 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -560,7 +560,7 @@ static int __kvmppc_svm_page_out(struct vm_area_struct *vma, gpa, 0, page_shift); if (ret == U_SUCCESS) - *mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED; + *mig.dst = migrate_pfn(pfn); else { unlock_page(dpage); __free_page(dpage); @@ -774,7 +774,7 @@ static int kvmppc_svm_page_in(struct vm_area_struct *vma, } } - *mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + *mig.dst = migrate_pfn(page_to_pfn(dpage)); migrate_vma_pages(&mig); out_finalize: migrate_vma_finalize(&mig); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 6d8634e40b3b..d43bfd8b35ae 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -317,7 +317,6 @@ svm_migrate_copy_to_vram(struct amdgpu_device *adev, struct svm_range *prange, migrate->dst[i] = svm_migrate_addr_to_pfn(adev, dst[i]); svm_migrate_get_vram_page(prange, migrate->dst[i]); migrate->dst[i] = migrate_pfn(migrate->dst[i]); - migrate->dst[i] |= MIGRATE_PFN_LOCKED; src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, DMA_TO_DEVICE); r = dma_mapping_error(dev, src[i]); @@ -610,7 +609,6 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, dst[i] >> PAGE_SHIFT, page_to_pfn(dpage)); migrate->dst[i] = migrate_pfn(page_to_pfn(dpage)); - migrate->dst[i] |= MIGRATE_PFN_LOCKED; j++; } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 92987daa5e17..3828aafd3ac4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -166,7 +166,7 @@ static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, goto error_dma_unmap; mutex_unlock(&svmm->mutex); - args->dst[0] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + args->dst[0] = migrate_pfn(page_to_pfn(dpage)); return 0; error_dma_unmap: @@ -602,7 +602,7 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, ((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT); if (src & MIGRATE_PFN_WRITE) *pfn |= NVIF_VMM_PFNMAP_V0_W; - return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + return migrate_pfn(page_to_pfn(dpage)); out_dma_unmap: dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); diff --git a/include/linux/migrate.h b/include/linux/migrate.h index eeb818c4fc78..4850cc5bf813 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -110,7 +110,6 @@ static inline int migrate_misplaced_page(struct page *page, */ #define MIGRATE_PFN_VALID (1UL << 0) #define MIGRATE_PFN_MIGRATE (1UL << 1) -#define MIGRATE_PFN_LOCKED (1UL << 2) #define MIGRATE_PFN_WRITE (1UL << 3) #define MIGRATE_PFN_SHIFT 6 diff --git a/lib/test_hmm.c b/lib/test_hmm.c index c259842f6d44..e2ce8f9b7605 100644 --- a/lib/test_hmm.c +++ b/lib/test_hmm.c @@ -613,8 +613,7 @@ static void dmirror_migrate_alloc_and_copy(struct migrate_vma *args, */ rpage->zone_device_data = dmirror; - *dst = migrate_pfn(page_to_pfn(dpage)) | - MIGRATE_PFN_LOCKED; + *dst = migrate_pfn(page_to_pfn(dpage)); if ((*src & MIGRATE_PFN_WRITE) || (!spage && args->vma->vm_flags & VM_WRITE)) *dst |= MIGRATE_PFN_WRITE; @@ -1137,7 +1136,7 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args, lock_page(dpage); xa_erase(&dmirror->pt, addr >> PAGE_SHIFT); copy_highpage(dpage, spage); - *dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + *dst = migrate_pfn(page_to_pfn(dpage)); if (*src & MIGRATE_PFN_WRITE) *dst |= MIGRATE_PFN_WRITE; } diff --git a/mm/migrate.c b/mm/migrate.c index 43dd88c7fcdc..cf25b00f03c8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2362,7 +2362,6 @@ again: * can't be dropped from it). */ get_page(page); - migrate->cpages++; /* * Optimize for the common case where page is only mapped once @@ -2372,7 +2371,7 @@ again: if (trylock_page(page)) { pte_t swp_pte; - mpfn |= MIGRATE_PFN_LOCKED; + migrate->cpages++; ptep_get_and_clear(mm, addr, ptep); /* Setup special migration page table entry */ @@ -2406,6 +2405,9 @@ again: if (pte_present(pte)) unmapped++; + } else { + put_page(page); + mpfn = 0; } next: @@ -2510,15 +2512,17 @@ static bool migrate_vma_check_page(struct page *page) } /* - * migrate_vma_prepare() - lock pages and isolate them from the lru + * migrate_vma_unmap() - replace page mapping with special migration pte entry * @migrate: migrate struct containing all migration information * - * This locks pages that have been collected by migrate_vma_collect(). Once each - * page is locked it is isolated from the lru (for non-device pages). Finally, - * the ref taken by migrate_vma_collect() is dropped, as locked pages cannot be - * migrated by concurrent kernel threads. + * Isolate pages from the LRU and replace mappings (CPU page table pte) with a + * special migration pte entry and check if it has been pinned. Pinned pages are + * restored because we cannot migrate them. + * + * This is the last step before we call the device driver callback to allocate + * destination memory and copy contents of original page over to new page. */ -static void migrate_vma_prepare(struct migrate_vma *migrate) +static void migrate_vma_unmap(struct migrate_vma *migrate) { const unsigned long npages = migrate->npages; const unsigned long start = migrate->start; @@ -2527,32 +2531,12 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) lru_add_drain(); - for (i = 0; (i < npages) && migrate->cpages; i++) { + for (i = 0; i < npages; i++) { struct page *page = migrate_pfn_to_page(migrate->src[i]); - bool remap = true; if (!page) continue; - if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) { - /* - * Because we are migrating several pages there can be - * a deadlock between 2 concurrent migration where each - * are waiting on each other page lock. - * - * Make migrate_vma() a best effort thing and backoff - * for any page we can not lock right away. - */ - if (!trylock_page(page)) { - migrate->src[i] = 0; - migrate->cpages--; - put_page(page); - continue; - } - remap = false; - migrate->src[i] |= MIGRATE_PFN_LOCKED; - } - /* ZONE_DEVICE pages are not on LRU */ if (!is_zone_device_page(page)) { if (!PageLRU(page) && allow_drain) { @@ -2562,16 +2546,9 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) } if (isolate_lru_page(page)) { - if (remap) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; - } else { - migrate->src[i] = 0; - unlock_page(page); - migrate->cpages--; - put_page(page); - } + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; continue; } @@ -2579,80 +2556,20 @@ static void migrate_vma_prepare(struct migrate_vma *migrate) put_page(page); } - if (!migrate_vma_check_page(page)) { - if (remap) { - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; - - if (!is_zone_device_page(page)) { - get_page(page); - putback_lru_page(page); - } - } else { - migrate->src[i] = 0; - unlock_page(page); - migrate->cpages--; + if (page_mapped(page)) + try_to_migrate(page, 0); - if (!is_zone_device_page(page)) - putback_lru_page(page); - else - put_page(page); + if (page_mapped(page) || !migrate_vma_check_page(page)) { + if (!is_zone_device_page(page)) { + get_page(page); + putback_lru_page(page); } - } - } - - for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); - - if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE)) - continue; - remove_migration_pte(page, migrate->vma, addr, page); - - migrate->src[i] = 0; - unlock_page(page); - put_page(page); - restore--; - } -} - -/* - * migrate_vma_unmap() - replace page mapping with special migration pte entry - * @migrate: migrate struct containing all migration information - * - * Replace page mapping (CPU page table pte) with a special migration pte entry - * and check again if it has been pinned. Pinned pages are restored because we - * cannot migrate them. - * - * This is the last step before we call the device driver callback to allocate - * destination memory and copy contents of original page over to new page. - */ -static void migrate_vma_unmap(struct migrate_vma *migrate) -{ - const unsigned long npages = migrate->npages; - const unsigned long start = migrate->start; - unsigned long addr, i, restore = 0; - - for (i = 0; i < npages; i++) { - struct page *page = migrate_pfn_to_page(migrate->src[i]); - - if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE)) + migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; + migrate->cpages--; + restore++; continue; - - if (page_mapped(page)) { - try_to_migrate(page, 0); - if (page_mapped(page)) - goto restore; } - - if (migrate_vma_check_page(page)) - continue; - -restore: - migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; - migrate->cpages--; - restore++; } for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) { @@ -2665,12 +2582,8 @@ restore: migrate->src[i] = 0; unlock_page(page); + put_page(page); restore--; - - if (is_zone_device_page(page)) - put_page(page); - else - putback_lru_page(page); } } @@ -2693,8 +2606,8 @@ restore: * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE * flag set). Once these are allocated and copied, the caller must update each * corresponding entry in the dst array with the pfn value of the destination - * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set - * (destination pages must have their struct pages locked, via lock_page()). + * page and with MIGRATE_PFN_VALID. Destination pages must be locked via + * lock_page(). * * Note that the caller does not have to migrate all the pages that are marked * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from @@ -2763,8 +2676,6 @@ int migrate_vma_setup(struct migrate_vma *args) migrate_vma_collect(args); - if (args->cpages) - migrate_vma_prepare(args); if (args->cpages) migrate_vma_unmap(args); -- cgit v1.2.3 From 68da4e0eaaab421f228eac57cbe7505b136464af Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 10 Nov 2021 12:01:14 -0600 Subject: Revert "PCI: Remove struct pci_dev->driver" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This reverts commit b5f9c644eb1baafcd349ad134e2110773f8d0a38. Revert b5f9c644eb1b ("PCI: Remove struct pci_dev->driver"), which is needed to revert 2a4d9408c9e8 ("PCI: Use to_pci_driver() instead of pci_dev->driver"). 2a4d9408c9e8 caused a NULL pointer dereference reported by Robert Święcki. Details in the revert of that commit. Fixes: 2a4d9408c9e8 ("PCI: Use to_pci_driver() instead of pci_dev->driver") Link: https://lore.kernel.org/linux-i2c/CAP145pgdrdiMAT7=-iB1DMgA7t_bMqTcJL4N0=6u8kNY3EU0dw@mail.gmail.com/ Reported-by: Robert Święcki Tested-by: Robert Święcki Signed-off-by: Bjorn Helgaas --- drivers/pci/pci-driver.c | 4 ++++ include/linux/pci.h | 1 + 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 1d98c974381c..4c1f46dbfa87 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -319,10 +319,12 @@ static long local_pci_probe(void *_ddi) * its remove routine. */ pm_runtime_get_sync(dev); + pci_dev->driver = pci_drv; rc = pci_drv->probe(pci_dev, ddi->id); if (!rc) return rc; if (rc < 0) { + pci_dev->driver = NULL; pm_runtime_put_sync(dev); return rc; } @@ -388,6 +390,7 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, * @pci_dev: PCI device being probed * * returns 0 on success, else error. + * side-effect: pci_dev->driver is set to drv when drv claims pci_dev. */ static int __pci_device_probe(struct pci_driver *drv, struct pci_dev *pci_dev) { @@ -462,6 +465,7 @@ static void pci_device_remove(struct device *dev) pm_runtime_put_noidle(dev); } pcibios_free_irq(pci_dev); + pci_dev->driver = NULL; pci_iov_remove(pci_dev); /* Undo the runtime PM settings in local_pci_probe() */ diff --git a/include/linux/pci.h b/include/linux/pci.h index b4dbcc86b3f1..e58888e21ab7 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -342,6 +342,7 @@ struct pci_dev { u16 pcie_flags_reg; /* Cached PCIe Capabilities Register */ unsigned long *dma_alias_mask;/* Mask of enabled devfn aliases */ + struct pci_driver *driver; /* Driver bound to this device */ u64 dma_mask; /* Mask of the bits of bus address this device implements. Normally this is 0xffffffff. You only need to change -- cgit v1.2.3 From bf9167a8b40c9cf463521da05342db81808c1b6e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 11 Nov 2021 09:56:33 +0100 Subject: HID: intel-ish-hid: fix module device-id handling A late addititon to the intel-ish-hid framework caused a build failure with clang, and introduced an ABI to the module loader that stops working if any driver ever needs to bind to more than one UUID: drivers/hid/intel-ish-hid/ishtp-fw-loader.c:1067:4: error: initializer element is not a compile-time constant Change the ishtp_device_id to have correct documentation and a driver_data field like all the other ones, and change the drivers to use the ID table as the primary identification in a way that works with all compilers and avoids duplciating the identifiers. Fixes: f155dfeaa4ee ("platform/x86: isthp_eclite: only load for matching devices") Fixes: facfe0a4fdce ("platform/chrome: chros_ec_ishtp: only load for matching devices") Fixes: 0d0cccc0fd83 ("HID: intel-ish-hid: hid-client: only load for matching devices") Fixes: 44e2a58cb880 ("HID: intel-ish-hid: fw-loader: only load for matching devices") Fixes: cb1a2c6847f7 ("HID: intel-ish-hid: use constants for modaliases") Fixes: fa443bc3c1e4 ("HID: intel-ish-hid: add support for MODULE_DEVICE_TABLE()") Signed-off-by: Arnd Bergmann Reviewed-by: Hans de Goede [jkosina@suse.cz: fix ecl_ishtp_cl_driver.id initialization] [jkosina@suse.cz: fix conflict with already fixed kerneldoc] Signed-off-by: Jiri Kosina --- drivers/hid/intel-ish-hid/ishtp-fw-loader.c | 19 ++++++++----------- drivers/hid/intel-ish-hid/ishtp-hid-client.c | 19 ++++++++----------- drivers/hid/intel-ish-hid/ishtp/bus.c | 2 +- drivers/platform/chrome/cros_ec_ishtp.c | 19 ++++++++----------- drivers/platform/x86/intel/ishtp_eclite.c | 19 ++++++++----------- include/linux/intel-ish-client-if.h | 4 ++-- include/linux/mod_devicetable.h | 2 ++ 7 files changed, 37 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c index 945a9d0b68cd..0e1183e96147 100644 --- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c +++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c @@ -76,9 +76,12 @@ enum ish_loader_commands { #define LOADER_XFER_MODE_ISHTP BIT(1) /* ISH Transport Loader client unique GUID */ -static const guid_t loader_ishtp_guid = - GUID_INIT(0xc804d06a, 0x55bd, 0x4ea7, - 0xad, 0xed, 0x1e, 0x31, 0x22, 0x8c, 0x76, 0xdc); +static const struct ishtp_device_id loader_ishtp_id_table[] = { + { .guid = GUID_INIT(0xc804d06a, 0x55bd, 0x4ea7, + 0xad, 0xed, 0x1e, 0x31, 0x22, 0x8c, 0x76, 0xdc) }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, loader_ishtp_id_table); #define FILENAME_SIZE 256 @@ -880,7 +883,7 @@ static int loader_init(struct ishtp_cl *loader_ishtp_cl, int reset) fw_client = ishtp_fw_cl_get_client(ishtp_get_ishtp_device(loader_ishtp_cl), - &loader_ishtp_guid); + &loader_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(client_data), "ISH client uuid not found\n"); @@ -1057,18 +1060,12 @@ static int loader_ishtp_cl_reset(struct ishtp_cl_device *cl_device) static struct ishtp_cl_driver loader_ishtp_cl_driver = { .name = "ish-loader", - .guid = &loader_ishtp_guid, + .id = loader_ishtp_id_table, .probe = loader_ishtp_cl_probe, .remove = loader_ishtp_cl_remove, .reset = loader_ishtp_cl_reset, }; -static const struct ishtp_device_id loader_ishtp_id_table[] = { - { loader_ishtp_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, loader_ishtp_id_table); - static int __init ish_loader_init(void) { return ishtp_cl_driver_register(&loader_ishtp_cl_driver, THIS_MODULE); diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index fb47d38d1e87..4338c9b68a43 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -12,9 +12,12 @@ #include "ishtp-hid.h" /* ISH Transport protocol (ISHTP in short) GUID */ -static const guid_t hid_ishtp_guid = - GUID_INIT(0x33AECD58, 0xB679, 0x4E54, - 0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26); +static const struct ishtp_device_id hid_ishtp_id_table[] = { + { .guid = GUID_INIT(0x33AECD58, 0xB679, 0x4E54, + 0x9B, 0xD9, 0xA0, 0x4D, 0x34, 0xF0, 0xC2, 0x26), }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, hid_ishtp_id_table); /* Rx ring buffer pool size */ #define HID_CL_RX_RING_SIZE 32 @@ -662,7 +665,7 @@ static int hid_ishtp_cl_init(struct ishtp_cl *hid_ishtp_cl, int reset) ishtp_set_tx_ring_size(hid_ishtp_cl, HID_CL_TX_RING_SIZE); ishtp_set_rx_ring_size(hid_ishtp_cl, HID_CL_RX_RING_SIZE); - fw_client = ishtp_fw_cl_get_client(dev, &hid_ishtp_guid); + fw_client = ishtp_fw_cl_get_client(dev, &hid_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(client_data), "ish client uuid not found\n"); @@ -945,19 +948,13 @@ static const struct dev_pm_ops hid_ishtp_pm_ops = { static struct ishtp_cl_driver hid_ishtp_cl_driver = { .name = "ish-hid", - .guid = &hid_ishtp_guid, + .id = hid_ishtp_id_table, .probe = hid_ishtp_cl_probe, .remove = hid_ishtp_cl_remove, .reset = hid_ishtp_cl_reset, .driver.pm = &hid_ishtp_pm_ops, }; -static const struct ishtp_device_id hid_ishtp_id_table[] = { - { hid_ishtp_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, hid_ishtp_id_table); - static int __init ish_hid_init(void) { int rv; diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index e159cd1c5f37..f68aba8794fe 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -241,7 +241,7 @@ static int ishtp_cl_bus_match(struct device *dev, struct device_driver *drv) struct ishtp_cl_device *device = to_ishtp_cl_device(dev); struct ishtp_cl_driver *driver = to_ishtp_cl_driver(drv); - return guid_equal(driver->guid, + return guid_equal(&driver->id[0].guid, &device->fw_client->props.protocol_name); } diff --git a/drivers/platform/chrome/cros_ec_ishtp.c b/drivers/platform/chrome/cros_ec_ishtp.c index 8c17358e84c1..4020b8354bae 100644 --- a/drivers/platform/chrome/cros_ec_ishtp.c +++ b/drivers/platform/chrome/cros_ec_ishtp.c @@ -41,9 +41,12 @@ enum cros_ec_ish_channel { #define ISHTP_SEND_TIMEOUT (3 * HZ) /* ISH Transport CrOS EC ISH client unique GUID */ -static const guid_t cros_ish_guid = - GUID_INIT(0x7b7154d0, 0x56f4, 0x4bdc, - 0xb0, 0xd8, 0x9e, 0x7c, 0xda, 0xe0, 0xd6, 0xa0); +static const struct ishtp_device_id cros_ec_ishtp_id_table[] = { + { .guid = GUID_INIT(0x7b7154d0, 0x56f4, 0x4bdc, + 0xb0, 0xd8, 0x9e, 0x7c, 0xda, 0xe0, 0xd6, 0xa0), }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, cros_ec_ishtp_id_table); struct header { u8 channel; @@ -389,7 +392,7 @@ static int cros_ish_init(struct ishtp_cl *cros_ish_cl) ishtp_set_tx_ring_size(cros_ish_cl, CROS_ISH_CL_TX_RING_SIZE); ishtp_set_rx_ring_size(cros_ish_cl, CROS_ISH_CL_RX_RING_SIZE); - fw_client = ishtp_fw_cl_get_client(dev, &cros_ish_guid); + fw_client = ishtp_fw_cl_get_client(dev, &cros_ec_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(client_data), "ish client uuid not found\n"); @@ -765,7 +768,7 @@ static SIMPLE_DEV_PM_OPS(cros_ec_ishtp_pm_ops, cros_ec_ishtp_suspend, static struct ishtp_cl_driver cros_ec_ishtp_driver = { .name = "cros_ec_ishtp", - .guid = &cros_ish_guid, + .id = cros_ec_ishtp_id_table, .probe = cros_ec_ishtp_probe, .remove = cros_ec_ishtp_remove, .reset = cros_ec_ishtp_reset, @@ -774,12 +777,6 @@ static struct ishtp_cl_driver cros_ec_ishtp_driver = { }, }; -static const struct ishtp_device_id cros_ec_ishtp_id_table[] = { - { cros_ish_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, cros_ec_ishtp_id_table); - static int __init cros_ec_ishtp_mod_init(void) { return ishtp_cl_driver_register(&cros_ec_ishtp_driver, THIS_MODULE); diff --git a/drivers/platform/x86/intel/ishtp_eclite.c b/drivers/platform/x86/intel/ishtp_eclite.c index b9fb8f28fd63..93ac8b2dbf38 100644 --- a/drivers/platform/x86/intel/ishtp_eclite.c +++ b/drivers/platform/x86/intel/ishtp_eclite.c @@ -93,9 +93,12 @@ struct ishtp_opregion_dev { }; /* eclite ishtp client UUID: 6a19cc4b-d760-4de3-b14d-f25ebd0fbcd9 */ -static const guid_t ecl_ishtp_guid = - GUID_INIT(0x6a19cc4b, 0xd760, 0x4de3, - 0xb1, 0x4d, 0xf2, 0x5e, 0xbd, 0xf, 0xbc, 0xd9); +static const struct ishtp_device_id ecl_ishtp_id_table[] = { + { .guid = GUID_INIT(0x6a19cc4b, 0xd760, 0x4de3, + 0xb1, 0x4d, 0xf2, 0x5e, 0xbd, 0xf, 0xbc, 0xd9), }, + { } +}; +MODULE_DEVICE_TABLE(ishtp, ecl_ishtp_id_table); /* ACPI DSM UUID: 91d936a7-1f01-49c6-a6b4-72f00ad8d8a5 */ static const guid_t ecl_acpi_guid = @@ -462,7 +465,7 @@ static int ecl_ishtp_cl_init(struct ishtp_cl *ecl_ishtp_cl) ishtp_set_tx_ring_size(ecl_ishtp_cl, ECL_CL_TX_RING_SIZE); ishtp_set_rx_ring_size(ecl_ishtp_cl, ECL_CL_RX_RING_SIZE); - fw_client = ishtp_fw_cl_get_client(dev, &ecl_ishtp_guid); + fw_client = ishtp_fw_cl_get_client(dev, &ecl_ishtp_id_table[0].guid); if (!fw_client) { dev_err(cl_data_to_dev(opr_dev), "fw client not found\n"); return -ENOENT; @@ -674,19 +677,13 @@ static const struct dev_pm_ops ecl_ishtp_pm_ops = { static struct ishtp_cl_driver ecl_ishtp_cl_driver = { .name = "ishtp-eclite", - .guid = &ecl_ishtp_guid, + .id = ecl_ishtp_id_table, .probe = ecl_ishtp_cl_probe, .remove = ecl_ishtp_cl_remove, .reset = ecl_ishtp_cl_reset, .driver.pm = &ecl_ishtp_pm_ops, }; -static const struct ishtp_device_id ecl_ishtp_id_table[] = { - { ecl_ishtp_guid }, - { } -}; -MODULE_DEVICE_TABLE(ishtp, ecl_ishtp_id_table); - static int __init ecl_ishtp_init(void) { return ishtp_cl_driver_register(&ecl_ishtp_cl_driver, THIS_MODULE); diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index aee8ff4739b1..f45f13304add 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -9,7 +9,7 @@ #define _INTEL_ISH_CLIENT_IF_H_ #include -#include +#include struct ishtp_cl_device; struct ishtp_device; @@ -40,7 +40,7 @@ enum cl_state { struct ishtp_cl_driver { struct device_driver driver; const char *name; - const guid_t *guid; + const struct ishtp_device_id *id; int (*probe)(struct ishtp_cl_device *dev); void (*remove)(struct ishtp_cl_device *dev); int (*reset)(struct ishtp_cl_device *dev); diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index c70abe7aaef2..4bb71979a8fd 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -902,9 +902,11 @@ struct dfl_device_id { /** * struct ishtp_device_id - ISHTP device identifier * @guid: GUID of the device. + * @driver_data: pointer to driver specific data */ struct ishtp_device_id { guid_t guid; + kernel_ulong_t driver_data; }; #endif /* LINUX_MOD_DEVICETABLE_H */ -- cgit v1.2.3 From 636f6e2af4fb916b9f1b432964294b6979c34002 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 9 Nov 2021 08:45:25 +0900 Subject: libata: add horkage for missing Identify Device log ACS-3 introduced the ATA Identify Device Data log as mandatory. A warning message currently signals to the user if a device does not report supporting this log page in the log directory page, regardless of the ATA version of the device. Furthermore, this warning will appear for all attempts at accessing this missing log page during device revalidation. Since it is useless to constantly access the log directory and warn about this lack of support once we have discovered that the device does not support this log page, introduce the horkage flag ATA_HORKAGE_NO_ID_DEV_LOG to mark a device as lacking support for the Identify Device Data log page. Set this flag when ata_log_supported() returns false in ata_identify_page_supported(). The warning is printed only if the device ATA level is 10 or above (ACS-3 or above), and only once on device scan. With this flag set, the log directory page is not accessed again to test for Identify Device Data log page support. Signed-off-by: Damien Le Moal Reviewed-by: Christoph Hellwig Reviewed-by: Martin K. Petersen --- drivers/ata/libata-core.c | 13 ++++++++++++- include/linux/libata.h | 1 + 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 3018ca84a3d8..8a0ccb190d76 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2052,8 +2052,19 @@ static bool ata_identify_page_supported(struct ata_device *dev, u8 page) struct ata_port *ap = dev->link->ap; unsigned int err, i; + if (dev->horkage & ATA_HORKAGE_NO_ID_DEV_LOG) + return false; + if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE)) { - ata_dev_warn(dev, "ATA Identify Device Log not supported\n"); + /* + * IDENTIFY DEVICE data log is defined as mandatory starting + * with ACS-3 (ATA version 10). Warn about the missing log + * for drives which implement this ATA level or above. + */ + if (ata_id_major_version(dev->id) >= 10) + ata_dev_warn(dev, + "ATA Identify Device Log not supported\n"); + dev->horkage |= ATA_HORKAGE_NO_ID_DEV_LOG; return false; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 5331557316e8..2a8404b26083 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -427,6 +427,7 @@ enum { ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ + ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 32a370abf12f82c8383e430c21365f5355d8b288 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 12 Nov 2021 12:07:02 -0500 Subject: net,lsm,selinux: revert the security_sctp_assoc_established() hook This patch reverts two prior patches, e7310c94024c ("security: implement sctp_assoc_established hook in selinux") and 7c2ef0240e6a ("security: add sctp_assoc_established hook"), which create the security_sctp_assoc_established() LSM hook and provide a SELinux implementation. Unfortunately these two patches were merged without proper review (the Reviewed-by and Tested-by tags from Richard Haines were for previous revisions of these patches that were significantly different) and there are outstanding objections from the SELinux maintainers regarding these patches. Work is currently ongoing to correct the problems identified in the reverted patches, as well as others that have come up during review, but it is unclear at this point in time when that work will be ready for inclusion in the mainline kernel. In the interest of not keeping objectionable code in the kernel for multiple weeks, and potentially a kernel release, we are reverting the two problematic patches. Signed-off-by: Paul Moore --- Documentation/security/SCTP.rst | 22 ++++++++++++---------- include/linux/lsm_hook_defs.h | 2 -- include/linux/lsm_hooks.h | 5 ----- include/linux/security.h | 7 ------- net/sctp/sm_statefuns.c | 2 +- security/security.c | 7 ------- security/selinux/hooks.c | 14 +------------- 7 files changed, 14 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/Documentation/security/SCTP.rst b/Documentation/security/SCTP.rst index 406cc68b8808..d5fd6ccc3dcb 100644 --- a/Documentation/security/SCTP.rst +++ b/Documentation/security/SCTP.rst @@ -15,7 +15,10 @@ For security module support, three SCTP specific hooks have been implemented:: security_sctp_assoc_request() security_sctp_bind_connect() security_sctp_sk_clone() - security_sctp_assoc_established() + +Also the following security hook has been utilised:: + + security_inet_conn_established() The usage of these hooks are described below with the SELinux implementation described in the `SCTP SELinux Support`_ chapter. @@ -119,12 +122,11 @@ calls **sctp_peeloff**\(3). @newsk - pointer to new sock structure. -security_sctp_assoc_established() +security_inet_conn_established() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Called when a COOKIE ACK is received, and the peer secid will be -saved into ``@asoc->peer_secid`` for client:: +Called when a COOKIE ACK is received:: - @asoc - pointer to sctp association structure. + @sk - pointer to sock structure. @skb - pointer to skbuff of the COOKIE ACK packet. @@ -132,7 +134,7 @@ Security Hooks used for Association Establishment ------------------------------------------------- The following diagram shows the use of ``security_sctp_bind_connect()``, -``security_sctp_assoc_request()``, ``security_sctp_assoc_established()`` when +``security_sctp_assoc_request()``, ``security_inet_conn_established()`` when establishing an association. :: @@ -170,7 +172,7 @@ establishing an association. <------------------------------------------- COOKIE ACK | | sctp_sf_do_5_1E_ca | - Call security_sctp_assoc_established() | + Call security_inet_conn_established() | to set the peer label. | | | | If SCTP_SOCKET_TCP or peeled off @@ -196,7 +198,7 @@ hooks with the SELinux specifics expanded below:: security_sctp_assoc_request() security_sctp_bind_connect() security_sctp_sk_clone() - security_sctp_assoc_established() + security_inet_conn_established() security_sctp_assoc_request() @@ -269,12 +271,12 @@ sockets sid and peer sid to that contained in the ``@asoc sid`` and @newsk - pointer to new sock structure. -security_sctp_assoc_established() +security_inet_conn_established() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Called when a COOKIE ACK is received where it sets the connection's peer sid to that in ``@skb``:: - @asoc - pointer to sctp association structure. + @sk - pointer to sock structure. @skb - pointer to skbuff of the COOKIE ACK packet. diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 442a611fa0fb..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -335,8 +335,6 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) -LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc, - struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d6823214d5c1..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1050,11 +1050,6 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. - * @sctp_assoc_established: - * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet - * to the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 06eac4e61a13..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1430,8 +1430,6 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); -void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1651,11 +1649,6 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } - -static inline void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ -} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 39ba82ee87ce..354c1c4de19b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -946,7 +946,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); /* Set peer label for connection. */ - security_sctp_assoc_established((struct sctp_association *)asoc, chunk->skb); + security_inet_conn_established(ep->base.sk, chunk->skb); /* RFC 2960 5.1 Normal Establishment of an Association * diff --git a/security/security.c b/security/security.c index 779a9edea0a0..c88167a414b4 100644 --- a/security/security.c +++ b/security/security.c @@ -2388,13 +2388,6 @@ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, } EXPORT_SYMBOL(security_sctp_sk_clone); -void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ - call_void_hook(sctp_assoc_established, asoc, skb); -} -EXPORT_SYMBOL(security_sctp_assoc_established); - #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 5e5215fe2e83..62d30c0a30c2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5502,8 +5502,7 @@ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); - if (asoc->secid != SECSID_WILD) - newsksec->sid = asoc->secid; + newsksec->sid = asoc->secid; newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); @@ -5559,16 +5558,6 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } -static void selinux_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ - struct sk_security_struct *sksec = asoc->base.sk->sk_security; - - selinux_inet_conn_established(asoc->base.sk, skb); - asoc->peer_secid = sksec->peer_sid; - asoc->secid = SECSID_WILD; -} - static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; @@ -7239,7 +7228,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), - LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), -- cgit v1.2.3 From 9e2ad638ae3632ef916ceb39f70e3104bf8fdc97 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 12 Nov 2021 07:02:42 -0800 Subject: bpf: Extend BTF_ID_LIST_GLOBAL with parameter for number of IDs syzbot reported the following BUG w/o CONFIG_DEBUG_INFO_BTF BUG: KASAN: global-out-of-bounds in task_iter_init+0x212/0x2e7 kernel/bpf/task_iter.c:661 Read of size 4 at addr ffffffff90297404 by task swapper/0/1 CPU: 1 PID: 1 Comm: swapper/0 Not tainted 5.15.0-syzkaller #0 Hardware name: ... Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_address_description.constprop.0.cold+0xf/0x309 mm/kasan/report.c:256 __kasan_report mm/kasan/report.c:442 [inline] kasan_report.cold+0x83/0xdf mm/kasan/report.c:459 task_iter_init+0x212/0x2e7 kernel/bpf/task_iter.c:661 do_one_initcall+0x103/0x650 init/main.c:1295 do_initcall_level init/main.c:1368 [inline] do_initcalls init/main.c:1384 [inline] do_basic_setup init/main.c:1403 [inline] kernel_init_freeable+0x6b1/0x73a init/main.c:1606 kernel_init+0x1a/0x1d0 init/main.c:1497 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:295 This is caused by hard-coded name[1] in BTF_ID_LIST_GLOBAL (w/o CONFIG_DEBUG_INFO_BTF). Fix this by adding a parameter n to BTF_ID_LIST_GLOBAL. This avoids ifdef CONFIG_DEBUG_INFO_BTF in btf.c and filter.c. Fixes: 7c7e3d31e785 ("bpf: Introduce helper bpf_find_vma") Reported-by: syzbot+e0d81ec552a21d9071aa@syzkaller.appspotmail.com Reported-by: Eric Dumazet Suggested-by: Eric Dumazet Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211112150243.1270987-2-songliubraving@fb.com --- include/linux/btf_ids.h | 6 +++--- kernel/bpf/btf.c | 2 +- net/core/filter.c | 6 +----- 3 files changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 47d9abfbdb55..6bb42b785293 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -73,7 +73,7 @@ asm( \ __BTF_ID_LIST(name, local) \ extern u32 name[]; -#define BTF_ID_LIST_GLOBAL(name) \ +#define BTF_ID_LIST_GLOBAL(name, n) \ __BTF_ID_LIST(name, globl) /* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with @@ -83,7 +83,7 @@ __BTF_ID_LIST(name, globl) BTF_ID_LIST(name) \ BTF_ID(prefix, typename) #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \ - BTF_ID_LIST_GLOBAL(name) \ + BTF_ID_LIST_GLOBAL(name, 1) \ BTF_ID(prefix, typename) /* @@ -149,7 +149,7 @@ extern struct btf_id_set name; #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; #define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; #define BTF_SET_START(name) static struct btf_id_set name = { 0 }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 1dd9ba82da1e..2a9d8a1fee1d 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6354,7 +6354,7 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .arg4_type = ARG_ANYTHING, }; -BTF_ID_LIST_GLOBAL(btf_task_struct_ids) +BTF_ID_LIST_GLOBAL(btf_task_struct_ids, 3) BTF_ID(struct, task_struct) BTF_ID(struct, file) BTF_ID(struct, vm_area_struct) diff --git a/net/core/filter.c b/net/core/filter.c index 315a58466fc9..46f09a8fba20 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10611,14 +10611,10 @@ void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog) bpf_dispatcher_change_prog(BPF_DISPATCHER_PTR(xdp), prev_prog, prog); } -#ifdef CONFIG_DEBUG_INFO_BTF -BTF_ID_LIST_GLOBAL(btf_sock_ids) +BTF_ID_LIST_GLOBAL(btf_sock_ids, MAX_BTF_SOCK_TYPE) #define BTF_SOCK_TYPE(name, type) BTF_ID(struct, type) BTF_SOCK_TYPE_xxx #undef BTF_SOCK_TYPE -#else -u32 btf_sock_ids[MAX_BTF_SOCK_TYPE]; -#endif BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { -- cgit v1.2.3 From d19ddb476a539fd78ad1028ae13bb38506286931 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 12 Nov 2021 07:02:43 -0800 Subject: bpf: Introduce btf_tracing_ids Similar to btf_sock_ids, btf_tracing_ids provides btf ID for task_struct, file, and vm_area_struct via easy to understand format like btf_tracing_ids[BTF_TRACING_TYPE_[TASK|file|VMA]]. Suggested-by: Alexei Starovoitov Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211112150243.1270987-3-songliubraving@fb.com --- include/linux/btf_ids.h | 14 +++++++++++++- kernel/bpf/bpf_task_storage.c | 4 ++-- kernel/bpf/btf.c | 8 ++++---- kernel/bpf/stackmap.c | 2 +- kernel/bpf/task_iter.c | 12 ++++++------ kernel/bpf/verifier.c | 2 +- kernel/trace/bpf_trace.c | 4 ++-- 7 files changed, 29 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 6bb42b785293..919c0fde1c51 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -189,6 +189,18 @@ MAX_BTF_SOCK_TYPE, extern u32 btf_sock_ids[]; #endif -extern u32 btf_task_struct_ids[]; +#define BTF_TRACING_TYPE_xxx \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct) + +enum { +#define BTF_TRACING_TYPE(name, type) name, +BTF_TRACING_TYPE_xxx +#undef BTF_TRACING_TYPE +MAX_BTF_TRACING_TYPE, +}; + +extern u32 btf_tracing_ids[]; #endif diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index ebfa8bc90892..bb69aea1a777 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -323,7 +323,7 @@ const struct bpf_func_proto bpf_task_storage_get_proto = { .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_task_struct_ids[0], + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -334,5 +334,5 @@ const struct bpf_func_proto bpf_task_storage_delete_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID, - .arg2_btf_id = &btf_task_struct_ids[0], + .arg2_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2a9d8a1fee1d..6b9d23be1e99 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6354,10 +6354,10 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .arg4_type = ARG_ANYTHING, }; -BTF_ID_LIST_GLOBAL(btf_task_struct_ids, 3) -BTF_ID(struct, task_struct) -BTF_ID(struct, file) -BTF_ID(struct, vm_area_struct) +BTF_ID_LIST_GLOBAL(btf_tracing_ids, MAX_BTF_TRACING_TYPE) +#define BTF_TRACING_TYPE(name, type) BTF_ID(struct, type) +BTF_TRACING_TYPE_xxx +#undef BTF_TRACING_TYPE /* BTF ID set registration API for modules */ diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 1de0a1b03636..49e567209c6b 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -489,7 +489,7 @@ const struct bpf_func_proto bpf_get_task_stack_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &btf_task_struct_ids[0], + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index f171479f7dd6..d94696198ef8 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -622,7 +622,7 @@ const struct bpf_func_proto bpf_find_vma_proto = { .func = bpf_find_vma, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &btf_task_struct_ids[0], + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_FUNC, .arg4_type = ARG_PTR_TO_STACK_OR_NULL, @@ -652,19 +652,19 @@ static int __init task_iter_init(void) init_irq_work(&work->irq_work, do_mmap_read_unlock); } - task_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; + task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; ret = bpf_iter_reg_target(&task_reg_info); if (ret) return ret; - task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_struct_ids[1]; + task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE]; ret = bpf_iter_reg_target(&task_file_reg_info); if (ret) return ret; - task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_struct_ids[0]; - task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_struct_ids[2]; + task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; return bpf_iter_reg_target(&task_vma_reg_info); } late_initcall(task_iter_init); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1aafb43f61d1..d31a031ab377 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6147,7 +6147,7 @@ static int set_find_vma_callback_state(struct bpf_verifier_env *env, callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID; __mark_reg_known_zero(&callee->regs[BPF_REG_2]); callee->regs[BPF_REG_2].btf = btf_vmlinux; - callee->regs[BPF_REG_2].btf_id = btf_task_struct_ids[2]; + callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA], /* pointer to stack or null */ callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4]; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 390176a3031a..25ea521fb8f1 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -764,7 +764,7 @@ const struct bpf_func_proto bpf_get_current_task_btf_proto = { .func = bpf_get_current_task_btf, .gpl_only = true, .ret_type = RET_PTR_TO_BTF_ID, - .ret_btf_id = &btf_task_struct_ids[0], + .ret_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], }; BPF_CALL_1(bpf_task_pt_regs, struct task_struct *, task) @@ -779,7 +779,7 @@ const struct bpf_func_proto bpf_task_pt_regs_proto = { .func = bpf_task_pt_regs, .gpl_only = true, .arg1_type = ARG_PTR_TO_BTF_ID, - .arg1_btf_id = &btf_task_struct_ids[0], + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], .ret_type = RET_PTR_TO_BTF_ID, .ret_btf_id = &bpf_task_pt_regs_ids[0], }; -- cgit v1.2.3 From 1aa3b2207e889a948049c9a8016cedb0218c2389 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Fri, 12 Nov 2021 18:18:10 -0500 Subject: net,lsm,selinux: revert the security_sctp_assoc_established() hook This patch reverts two prior patches, e7310c94024c ("security: implement sctp_assoc_established hook in selinux") and 7c2ef0240e6a ("security: add sctp_assoc_established hook"), which create the security_sctp_assoc_established() LSM hook and provide a SELinux implementation. Unfortunately these two patches were merged without proper review (the Reviewed-by and Tested-by tags from Richard Haines were for previous revisions of these patches that were significantly different) and there are outstanding objections from the SELinux maintainers regarding these patches. Work is currently ongoing to correct the problems identified in the reverted patches, as well as others that have come up during review, but it is unclear at this point in time when that work will be ready for inclusion in the mainline kernel. In the interest of not keeping objectionable code in the kernel for multiple weeks, and potentially a kernel release, we are reverting the two problematic patches. Signed-off-by: Paul Moore Signed-off-by: David S. Miller --- Documentation/security/SCTP.rst | 22 ++++++++++++---------- include/linux/lsm_hook_defs.h | 2 -- include/linux/lsm_hooks.h | 5 ----- include/linux/security.h | 7 ------- net/sctp/sm_statefuns.c | 2 +- security/security.c | 7 ------- security/selinux/hooks.c | 14 +------------- 7 files changed, 14 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/Documentation/security/SCTP.rst b/Documentation/security/SCTP.rst index 406cc68b8808..d5fd6ccc3dcb 100644 --- a/Documentation/security/SCTP.rst +++ b/Documentation/security/SCTP.rst @@ -15,7 +15,10 @@ For security module support, three SCTP specific hooks have been implemented:: security_sctp_assoc_request() security_sctp_bind_connect() security_sctp_sk_clone() - security_sctp_assoc_established() + +Also the following security hook has been utilised:: + + security_inet_conn_established() The usage of these hooks are described below with the SELinux implementation described in the `SCTP SELinux Support`_ chapter. @@ -119,12 +122,11 @@ calls **sctp_peeloff**\(3). @newsk - pointer to new sock structure. -security_sctp_assoc_established() +security_inet_conn_established() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Called when a COOKIE ACK is received, and the peer secid will be -saved into ``@asoc->peer_secid`` for client:: +Called when a COOKIE ACK is received:: - @asoc - pointer to sctp association structure. + @sk - pointer to sock structure. @skb - pointer to skbuff of the COOKIE ACK packet. @@ -132,7 +134,7 @@ Security Hooks used for Association Establishment ------------------------------------------------- The following diagram shows the use of ``security_sctp_bind_connect()``, -``security_sctp_assoc_request()``, ``security_sctp_assoc_established()`` when +``security_sctp_assoc_request()``, ``security_inet_conn_established()`` when establishing an association. :: @@ -170,7 +172,7 @@ establishing an association. <------------------------------------------- COOKIE ACK | | sctp_sf_do_5_1E_ca | - Call security_sctp_assoc_established() | + Call security_inet_conn_established() | to set the peer label. | | | | If SCTP_SOCKET_TCP or peeled off @@ -196,7 +198,7 @@ hooks with the SELinux specifics expanded below:: security_sctp_assoc_request() security_sctp_bind_connect() security_sctp_sk_clone() - security_sctp_assoc_established() + security_inet_conn_established() security_sctp_assoc_request() @@ -269,12 +271,12 @@ sockets sid and peer sid to that contained in the ``@asoc sid`` and @newsk - pointer to new sock structure. -security_sctp_assoc_established() +security_inet_conn_established() ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Called when a COOKIE ACK is received where it sets the connection's peer sid to that in ``@skb``:: - @asoc - pointer to sctp association structure. + @sk - pointer to sock structure. @skb - pointer to skbuff of the COOKIE ACK packet. diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 442a611fa0fb..df8de62f4710 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -335,8 +335,6 @@ LSM_HOOK(int, 0, sctp_bind_connect, struct sock *sk, int optname, struct sockaddr *address, int addrlen) LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc, struct sock *sk, struct sock *newsk) -LSM_HOOK(void, LSM_RET_VOID, sctp_assoc_established, struct sctp_association *asoc, - struct sk_buff *skb) #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d6823214d5c1..d45b6f6e27fd 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -1050,11 +1050,6 @@ * @asoc pointer to current sctp association structure. * @sk pointer to current sock structure. * @newsk pointer to new sock structure. - * @sctp_assoc_established: - * Passes the @asoc and @chunk->skb of the association COOKIE_ACK packet - * to the security module. - * @asoc pointer to sctp association structure. - * @skb pointer to skbuff of association packet. * * Security hooks for Infiniband * diff --git a/include/linux/security.h b/include/linux/security.h index 06eac4e61a13..bbf44a466832 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1430,8 +1430,6 @@ int security_sctp_bind_connect(struct sock *sk, int optname, struct sockaddr *address, int addrlen); void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, struct sock *newsk); -void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb); #else /* CONFIG_SECURITY_NETWORK */ static inline int security_unix_stream_connect(struct sock *sock, @@ -1651,11 +1649,6 @@ static inline void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *newsk) { } - -static inline void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ -} #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 39ba82ee87ce..354c1c4de19b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -946,7 +946,7 @@ enum sctp_disposition sctp_sf_do_5_1E_ca(struct net *net, sctp_add_cmd_sf(commands, SCTP_CMD_INIT_COUNTER_RESET, SCTP_NULL()); /* Set peer label for connection. */ - security_sctp_assoc_established((struct sctp_association *)asoc, chunk->skb); + security_inet_conn_established(ep->base.sk, chunk->skb); /* RFC 2960 5.1 Normal Establishment of an Association * diff --git a/security/security.c b/security/security.c index 779a9edea0a0..c88167a414b4 100644 --- a/security/security.c +++ b/security/security.c @@ -2388,13 +2388,6 @@ void security_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk, } EXPORT_SYMBOL(security_sctp_sk_clone); -void security_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ - call_void_hook(sctp_assoc_established, asoc, skb); -} -EXPORT_SYMBOL(security_sctp_assoc_established); - #endif /* CONFIG_SECURITY_NETWORK */ #ifdef CONFIG_SECURITY_INFINIBAND diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 5e5215fe2e83..62d30c0a30c2 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -5502,8 +5502,7 @@ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk if (!selinux_policycap_extsockclass()) return selinux_sk_clone_security(sk, newsk); - if (asoc->secid != SECSID_WILD) - newsksec->sid = asoc->secid; + newsksec->sid = asoc->secid; newsksec->peer_sid = asoc->peer_secid; newsksec->sclass = sksec->sclass; selinux_netlbl_sctp_sk_clone(sk, newsk); @@ -5559,16 +5558,6 @@ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); } -static void selinux_sctp_assoc_established(struct sctp_association *asoc, - struct sk_buff *skb) -{ - struct sk_security_struct *sksec = asoc->base.sk->sk_security; - - selinux_inet_conn_established(asoc->base.sk, skb); - asoc->peer_secid = sksec->peer_sid; - asoc->secid = SECSID_WILD; -} - static int selinux_secmark_relabel_packet(u32 sid) { const struct task_security_struct *__tsec; @@ -7239,7 +7228,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(sctp_assoc_request, selinux_sctp_assoc_request), LSM_HOOK_INIT(sctp_sk_clone, selinux_sctp_sk_clone), LSM_HOOK_INIT(sctp_bind_connect, selinux_sctp_bind_connect), - LSM_HOOK_INIT(sctp_assoc_established, selinux_sctp_assoc_established), LSM_HOOK_INIT(inet_conn_request, selinux_inet_conn_request), LSM_HOOK_INIT(inet_csk_clone, selinux_inet_csk_clone), LSM_HOOK_INIT(inet_conn_established, selinux_inet_conn_established), -- cgit v1.2.3 From 938aa33f14657c9ed9deea348b7d6f14b6d69cb7 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Sun, 14 Nov 2021 13:28:34 -0500 Subject: tracing: Add length protection to histogram string copies The string copies to the histogram storage has a max size of 256 bytes (defined by MAX_FILTER_STR_VAL). Only the string size of the event field needs to be copied to the event storage, but no more than what is in the event storage. Although nothing should be bigger than 256 bytes, there's no protection against overwriting of the storage if one day there is. Copy no more than the destination size, and enforce it. Also had to turn MAX_FILTER_STR_VAL into an unsigned int, to keep the min() comparison of the string sizes of comparable types. Link: https://lore.kernel.org/all/CAHk-=wjREUihCGrtRBwfX47y_KrLCGjiq3t6QtoNJpmVrAEb1w@mail.gmail.com/ Link: https://lkml.kernel.org/r/20211114132834.183429a4@rorschach.local.home Cc: Ingo Molnar Cc: Andrew Morton Cc: Tom Zanussi Reported-by: Linus Torvalds Reviewed-by: Masami Hiramatsu Fixes: 63f84ae6b82b ("tracing/histogram: Do not copy the fixed-size char array field over the field size") Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 2 +- kernel/trace/trace_events_hist.c | 9 +++++++-- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 50453b287615..2d167ac3452c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -673,7 +673,7 @@ struct trace_event_file { #define PERF_MAX_TRACE_SIZE 8192 -#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ +#define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */ enum event_trigger_type { ETT_NONE = (0), diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 1475d7347fe0..34afcaebd0e5 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3026,8 +3026,10 @@ static inline void __update_field_vars(struct tracing_map_elt *elt, if (val->flags & HIST_FIELD_FL_STRING) { char *str = elt_data->field_var_str[j++]; char *val_str = (char *)(uintptr_t)var_val; + unsigned int size; - strscpy(str, val_str, val->size); + size = min(val->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); var_val = (u64)(uintptr_t)str; } tracing_map_set_var(elt, var_idx, var_val); @@ -4914,6 +4916,7 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, if (hist_field->flags & HIST_FIELD_FL_STRING) { unsigned int str_start, var_str_idx, idx; char *str, *val_str; + unsigned int size; str_start = hist_data->n_field_var_str + hist_data->n_save_var_str; @@ -4922,7 +4925,9 @@ static void hist_trigger_elt_update(struct hist_trigger_data *hist_data, str = elt_data->field_var_str[idx]; val_str = (char *)(uintptr_t)hist_val; - strscpy(str, val_str, hist_field->size); + + size = min(hist_field->size, STR_VAR_LEN_MAX); + strscpy(str, val_str, size); hist_val = (u64)(uintptr_t)str; } -- cgit v1.2.3 From 4c7924fb905b02323ff6d9d20f370892615dccfa Mon Sep 17 00:00:00 2001 From: Julien Massot Date: Fri, 22 Oct 2021 14:21:01 +0200 Subject: soc: renesas: rcar-rst: Add support to set rproc boot address R-Car Gen3 SoC series has a realtime processor, the boot address of this processor can be set thanks to CR7BAR register of the reset module. Export this function so that it's possible to set the boot address from a remoteproc driver. Also drop the __initdata qualifier on rcar_rst_base, since we will use this address later than init time. Signed-off-by: Julien Massot Link: https://lore.kernel.org/r/20211022122101.66998-1-julien.massot@iot.bzh Signed-off-by: Geert Uytterhoeven --- drivers/soc/renesas/rcar-rst.c | 43 +++++++++++++++++++++++++++++++++--- include/linux/soc/renesas/rcar-rst.h | 2 ++ 2 files changed, 42 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/renesas/rcar-rst.c b/drivers/soc/renesas/rcar-rst.c index 8a1e402ea799..1ad54e0c32e1 100644 --- a/drivers/soc/renesas/rcar-rst.c +++ b/drivers/soc/renesas/rcar-rst.c @@ -13,15 +13,43 @@ #define WDTRSTCR_RESET 0xA55A0002 #define WDTRSTCR 0x0054 +#define CR7BAR 0x0070 +#define CR7BAREN BIT(4) +#define CR7BAR_MASK 0xFFFC0000 + +static void __iomem *rcar_rst_base; +static u32 saved_mode __initdata; +static int (*rcar_rst_set_rproc_boot_addr_func)(u64 boot_addr); + static int rcar_rst_enable_wdt_reset(void __iomem *base) { iowrite32(WDTRSTCR_RESET, base + WDTRSTCR); return 0; } +/* + * Most of the R-Car Gen3 SoCs have an ARM Realtime Core. + * Firmware boot address has to be set in CR7BAR before + * starting the realtime core. + * Boot address must be aligned on a 256k boundary. + */ +static int rcar_rst_set_gen3_rproc_boot_addr(u64 boot_addr) +{ + if (boot_addr & ~(u64)CR7BAR_MASK) { + pr_err("Invalid boot address got %llx\n", boot_addr); + return -EINVAL; + } + + iowrite32(boot_addr, rcar_rst_base + CR7BAR); + iowrite32(boot_addr | CR7BAREN, rcar_rst_base + CR7BAR); + + return 0; +} + struct rst_config { unsigned int modemr; /* Mode Monitoring Register Offset */ int (*configure)(void __iomem *base); /* Platform specific config */ + int (*set_rproc_boot_addr)(u64 boot_addr); }; static const struct rst_config rcar_rst_gen1 __initconst = { @@ -35,6 +63,7 @@ static const struct rst_config rcar_rst_gen2 __initconst = { static const struct rst_config rcar_rst_gen3 __initconst = { .modemr = 0x60, + .set_rproc_boot_addr = rcar_rst_set_gen3_rproc_boot_addr, }; static const struct rst_config rcar_rst_r8a779a0 __initconst = { @@ -76,9 +105,6 @@ static const struct of_device_id rcar_rst_matches[] __initconst = { { /* sentinel */ } }; -static void __iomem *rcar_rst_base __initdata; -static u32 saved_mode __initdata; - static int __init rcar_rst_init(void) { const struct of_device_id *match; @@ -100,6 +126,8 @@ static int __init rcar_rst_init(void) rcar_rst_base = base; cfg = match->data; + rcar_rst_set_rproc_boot_addr_func = cfg->set_rproc_boot_addr; + saved_mode = ioread32(base + cfg->modemr); if (cfg->configure) { error = cfg->configure(base); @@ -130,3 +158,12 @@ int __init rcar_rst_read_mode_pins(u32 *mode) *mode = saved_mode; return 0; } + +int rcar_rst_set_rproc_boot_addr(u64 boot_addr) +{ + if (!rcar_rst_set_rproc_boot_addr_func) + return -EIO; + + return rcar_rst_set_rproc_boot_addr_func(boot_addr); +} +EXPORT_SYMBOL_GPL(rcar_rst_set_rproc_boot_addr); diff --git a/include/linux/soc/renesas/rcar-rst.h b/include/linux/soc/renesas/rcar-rst.h index 7899a5b8c247..1f1fe8bfaa76 100644 --- a/include/linux/soc/renesas/rcar-rst.h +++ b/include/linux/soc/renesas/rcar-rst.h @@ -4,8 +4,10 @@ #ifdef CONFIG_RST_RCAR int rcar_rst_read_mode_pins(u32 *mode); +int rcar_rst_set_rproc_boot_addr(u64 boot_addr); #else static inline int rcar_rst_read_mode_pins(u32 *mode) { return -ENODEV; } +static inline int rcar_rst_set_rproc_boot_addr(u64 boot_addr) { return -ENODEV; } #endif #endif /* __LINUX_SOC_RENESAS_RCAR_RST_H__ */ -- cgit v1.2.3 From 032816fbbfafe3198bb5c71fbbe4e8e5be33b352 Mon Sep 17 00:00:00 2001 From: Lad Prabhakar Date: Wed, 27 Oct 2021 14:45:07 +0100 Subject: pinctrl: pinconf-generic: Add support for "output-impedance-ohms" to be extracted from DT files Add "output-impedance-ohms" property to generic options used for DT parsing files. This enables drivers, which use generic pin configurations, to get the value passed to this property. Signed-off-by: Lad Prabhakar Reviewed-by: Biju Das Reviewed-by: Linus Walleij Link: https://lore.kernel.org/r/20211027134509.5036-3-prabhakar.mahadev-lad.rj@bp.renesas.com Signed-off-by: Geert Uytterhoeven --- drivers/pinctrl/pinconf-generic.c | 2 ++ include/linux/pinctrl/pinconf-generic.h | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 22e8d4c4040e..f8edcc88ac01 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -46,6 +46,7 @@ static const struct pin_config_item conf_items[] = { PCONFDUMP(PIN_CONFIG_MODE_LOW_POWER, "pin low power", "mode", true), PCONFDUMP(PIN_CONFIG_OUTPUT_ENABLE, "output enabled", NULL, false), PCONFDUMP(PIN_CONFIG_OUTPUT, "pin output", "level", true), + PCONFDUMP(PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS, "output impedance", "ohms", true), PCONFDUMP(PIN_CONFIG_POWER_SOURCE, "pin power source", "selector", true), PCONFDUMP(PIN_CONFIG_SLEEP_HARDWARE_STATE, "sleep hardware state", NULL, false), PCONFDUMP(PIN_CONFIG_SLEW_RATE, "slew rate", NULL, true), @@ -179,6 +180,7 @@ static const struct pinconf_generic_params dt_params[] = { { "output-disable", PIN_CONFIG_OUTPUT_ENABLE, 0 }, { "output-enable", PIN_CONFIG_OUTPUT_ENABLE, 1 }, { "output-high", PIN_CONFIG_OUTPUT, 1, }, + { "output-impedance-ohms", PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS, 0 }, { "output-low", PIN_CONFIG_OUTPUT, 0, }, { "power-source", PIN_CONFIG_POWER_SOURCE, 0 }, { "sleep-hardware-state", PIN_CONFIG_SLEEP_HARDWARE_STATE, 0 }, diff --git a/include/linux/pinctrl/pinconf-generic.h b/include/linux/pinctrl/pinconf-generic.h index eee0e3948537..2422211d6a5a 100644 --- a/include/linux/pinctrl/pinconf-generic.h +++ b/include/linux/pinctrl/pinconf-generic.h @@ -91,6 +91,8 @@ struct pinctrl_map; * configuration (eg. the currently selected mux function) drive values on * the line. Use argument 1 to enable output mode, argument 0 to disable * it. + * @PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS: this will configure the output impedance + * of the pin with the value passed as argument. The argument is in ohms. * @PIN_CONFIG_PERSIST_STATE: retain pin state across sleep or controller reset * @PIN_CONFIG_POWER_SOURCE: if the pin can select between different power * supplies, the argument to this parameter (on a custom format) tells @@ -129,6 +131,7 @@ enum pin_config_param { PIN_CONFIG_MODE_PWM, PIN_CONFIG_OUTPUT, PIN_CONFIG_OUTPUT_ENABLE, + PIN_CONFIG_OUTPUT_IMPEDANCE_OHMS, PIN_CONFIG_PERSIST_STATE, PIN_CONFIG_POWER_SOURCE, PIN_CONFIG_SKEW_DELAY, -- cgit v1.2.3 From 507805b83ff108473dba9d4909e41abd50cf07f5 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 10 Nov 2021 15:47:42 +0200 Subject: gpiolib: acpi: Remove never used devm_acpi_dev_remove_driver_gpios() Remove never used devm_acpi_dev_remove_driver_gpios(). Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg --- drivers/gpio/gpiolib-acpi.c | 6 ------ include/linux/gpio/consumer.h | 2 -- 2 files changed, 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index 985e8589c58b..25ecc0a37054 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -604,12 +604,6 @@ int devm_acpi_dev_add_driver_gpios(struct device *dev, } EXPORT_SYMBOL_GPL(devm_acpi_dev_add_driver_gpios); -void devm_acpi_dev_remove_driver_gpios(struct device *dev) -{ - WARN_ON(devres_release(dev, devm_acpi_dev_release_driver_gpios, NULL, NULL)); -} -EXPORT_SYMBOL_GPL(devm_acpi_dev_remove_driver_gpios); - static bool acpi_get_driver_gpio_data(struct acpi_device *adev, const char *name, int index, struct fwnode_reference_args *args, diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h index 97a28ad3393b..3ad67b4a72be 100644 --- a/include/linux/gpio/consumer.h +++ b/include/linux/gpio/consumer.h @@ -690,7 +690,6 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev); int devm_acpi_dev_add_driver_gpios(struct device *dev, const struct acpi_gpio_mapping *gpios); -void devm_acpi_dev_remove_driver_gpios(struct device *dev); struct gpio_desc *acpi_get_and_request_gpiod(char *path, int pin, char *label); @@ -708,7 +707,6 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev, { return -ENXIO; } -static inline void devm_acpi_dev_remove_driver_gpios(struct device *dev) {} #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */ -- cgit v1.2.3 From 10a2308ffb8cf262e473eb324fde42ae31b6da04 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Fri, 12 Nov 2021 18:16:34 +0800 Subject: net: Clean up some inconsistent indenting Eliminate the follow smatch warning: ./include/linux/skbuff.h:4229 skb_remcsum_process() warn: inconsistent indenting. Reported-by: Abaci Robot Signed-off-by: Jiapeng Chong Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 686a666d073d..c8cb7e697d47 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4226,7 +4226,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, return; } - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } -- cgit v1.2.3 From 02d6fdecb9c38de19065f6bed8d5214556fd061d Mon Sep 17 00:00:00 2001 From: Ansuel Smith Date: Thu, 4 Nov 2021 16:00:40 +0100 Subject: regmap: allow to define reg_update_bits for no bus configuration Some device requires a special handling for reg_update_bits and can't use the normal regmap read write logic. An example is when locking is handled by the device and rmw operations requires to do atomic operations. Allow to declare a dedicated function in regmap_config for reg_update_bits in no bus configuration. Signed-off-by: Ansuel Smith Link: https://lore.kernel.org/r/20211104150040.1260-1-ansuelsmth@gmail.com Signed-off-by: Mark Brown --- drivers/base/regmap/regmap.c | 1 + include/linux/regmap.h | 7 +++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 21a0c2562ec0..2d74f9f82aa9 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -876,6 +876,7 @@ struct regmap *__regmap_init(struct device *dev, if (!bus) { map->reg_read = config->reg_read; map->reg_write = config->reg_write; + map->reg_update_bits = config->reg_update_bits; map->defer_caching = false; goto skip_format_initialization; diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e3c9a25a853a..22652e5fbc38 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -290,6 +290,11 @@ typedef void (*regmap_unlock)(void *); * read operation on a bus such as SPI, I2C, etc. Most of the * devices do not need this. * @reg_write: Same as above for writing. + * @reg_update_bits: Optional callback that if filled will be used to perform + * all the update_bits(rmw) operation. Should only be provided + * if the function require special handling with lock and reg + * handling and the operation cannot be represented as a simple + * update_bits operation on a bus such as SPI, I2C, etc. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -372,6 +377,8 @@ struct regmap_config { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); + int (*reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); bool fast_io; -- cgit v1.2.3 From 45971bdd8ca8b5a99a49f4db86737401c45e246f Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:02:02 -0600 Subject: spi: remove unused header file Commit 6acaadc852f1 ("spi: clps711x: Driver refactor") removed the only use of , but left the header file behind. This file is unused, delete it. Cc: Signed-off-by: Arnd Bergmann Cc: Signed-off-by: Mark Brown Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Jonathan Corbet Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20211102220203.940290-9-corbet@lwn.net Signed-off-by: Mark Brown --- include/linux/platform_data/spi-clps711x.h | 17 ----------------- 1 file changed, 17 deletions(-) delete mode 100644 include/linux/platform_data/spi-clps711x.h (limited to 'include/linux') diff --git a/include/linux/platform_data/spi-clps711x.h b/include/linux/platform_data/spi-clps711x.h deleted file mode 100644 index efaa596848c9..000000000000 --- a/include/linux/platform_data/spi-clps711x.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * CLPS711X SPI bus driver definitions - * - * Copyright (C) 2012 Alexander Shiyan - */ - -#ifndef ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H -#define ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H - -/* Board specific platform_data */ -struct spi_clps711x_pdata { - int *chipselect; /* Array of GPIO-numbers */ - int num_chipselect; /* Total count of GPIOs */ -}; - -#endif -- cgit v1.2.3 From a0ddee65c527d877e798205c1391c6170e580c66 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 12 Nov 2021 16:07:49 +0200 Subject: printk: Remove printk.h inclusion in percpu.h After the commit 42a0bb3f7138 ("printk/nmi: generic solution for safe printk in NMI") the printk.h is not needed anymore in percpu.h. Moreover `make headerdep` complains (an excerpt) In file included from linux/printk.h, from linux/dynamic_debug.h:188 from linux/printk.h:559 <-- here from linux/percpu.h:9 from linux/idr.h:17 include/net/9p/client.h:13: warning: recursive header inclusion Yeah, it's not a root cause of this, but removing will help to reduce the noise. Fixes: 42a0bb3f7138 ("printk/nmi: generic solution for safe printk in NMI") Signed-off-by: Andy Shevchenko Acked-by: Dennis Zhou Reviewed-by: Petr Mladek Signed-off-by: Petr Mladek Link: https://lore.kernel.org/r/20211112140749.80042-1-andriy.shevchenko@linux.intel.com --- include/linux/percpu.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 5e76af742c80..4fa3000f9c22 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -6,7 +6,6 @@ #include #include #include -#include #include #include -- cgit v1.2.3 From 13cae4a104d2b7205696229ba85d34cc035f8c84 Mon Sep 17 00:00:00 2001 From: Matt Johnston Date: Mon, 15 Nov 2021 10:49:21 +0800 Subject: i2c: core: Allow 255 byte transfers for SMBus 3.x SMBus 3.0 increased the maximum block transfer size from 32 bytes to 255 bytes. We increase the size of struct i2c_smbus_data's block[] member. i2c_smbus_xfer() and i2c_smbus_xfer_emulated() now support 255 byte block operations, other block functions remain limited to 32 bytes for compatibility with existing callers. We allow adapters to indicate support for the larger size with I2C_FUNC_SMBUS_V3_BLOCK. Most emulated drivers should be able to use 255 byte blocks by replacing I2C_SMBUS_BLOCK_MAX with I2C_SMBUS_V3_BLOCK_MAX though some will have hardware limitations that need testing. Signed-off-by: Matt Johnston Signed-off-by: David S. Miller --- drivers/i2c/i2c-core-smbus.c | 20 +++++++++++++------- include/linux/i2c.h | 13 +++++++++++++ include/uapi/linux/i2c.h | 5 ++++- 3 files changed, 30 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index e5b2d1465e7e..743415584aba 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -303,7 +303,8 @@ static void i2c_smbus_try_get_dmabuf(struct i2c_msg *msg, u8 init_val) bool is_read = msg->flags & I2C_M_RD; unsigned char *dma_buf; - dma_buf = kzalloc(I2C_SMBUS_BLOCK_MAX + (is_read ? 2 : 3), GFP_KERNEL); + dma_buf = kzalloc(I2C_SMBUS_V3_BLOCK_MAX + (is_read ? 2 : 3), + GFP_KERNEL); if (!dma_buf) return; @@ -329,9 +330,10 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, * initialize most things with sane defaults, to keep the code below * somewhat simpler. */ - unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3]; - unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2]; + unsigned char msgbuf0[I2C_SMBUS_V3_BLOCK_MAX+3]; + unsigned char msgbuf1[I2C_SMBUS_V3_BLOCK_MAX+2]; int nmsgs = read_write == I2C_SMBUS_READ ? 2 : 1; + u16 block_max; u8 partial_pec = 0; int status; struct i2c_msg msg[2] = { @@ -350,6 +352,10 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, bool wants_pec = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA); + /* Drivers must opt in to 255 byte max block size */ + block_max = i2c_check_functionality(adapter, I2C_FUNC_SMBUS_V3_BLOCK) + ? I2C_SMBUS_V3_BLOCK_MAX : I2C_SMBUS_BLOCK_MAX; + msgbuf0[0] = command; switch (size) { case I2C_SMBUS_QUICK: @@ -399,7 +405,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); } else { msg[0].len = data->block[0] + 2; - if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) { + if (msg[0].len > block_max + 2) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -413,7 +419,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, case I2C_SMBUS_BLOCK_PROC_CALL: nmsgs = 2; /* Another special case */ read_write = I2C_SMBUS_READ; - if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { + if (data->block[0] > block_max) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -430,7 +436,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); break; case I2C_SMBUS_I2C_BLOCK_DATA: - if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { + if (data->block[0] > block_max) { dev_err(&adapter->dev, "Invalid block %s size %d\n", read_write == I2C_SMBUS_READ ? "read" : "write", data->block[0]); @@ -498,7 +504,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_BLOCK_PROC_CALL: - if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) { + if (msg[1].buf[0] > block_max) { dev_err(&adapter->dev, "Invalid block size returned: %d\n", msg[1].buf[0]); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 16119ac1aa97..353d6b4e7a53 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -52,6 +52,19 @@ typedef int (*i2c_slave_cb_t)(struct i2c_client *client, struct module; struct property_entry; +/* SMBus 3.0 extends the maximum block read/write size to 255 (from 32). + * The larger size is only supported by some drivers, indicated by + * the I2C_FUNC_SMBUS_V3_BLOCK functionality bit. + */ +#define I2C_SMBUS_V3_BLOCK_MAX 255 /* As specified in SMBus 3.0 standard */ + +/* Note compatibility definition in uapi header with 32 byte block */ +union i2c_smbus_data { + __u8 byte; + __u16 word; + __u8 block[I2C_SMBUS_V3_BLOCK_MAX + 1]; /* block[0] is used for length */ +}; + #if IS_ENABLED(CONFIG_I2C) /* Return the Frequency mode string based on the bus frequency */ const char *i2c_freq_mode_string(u32 bus_freq_hz); diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index 92326ebde350..7b7d90b50cf0 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -108,6 +108,7 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ #define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ +#define I2C_FUNC_SMBUS_V3_BLOCK 0x20000000 /* Device supports 255 byte block */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) @@ -137,13 +138,15 @@ struct i2c_msg { /* * Data for SMBus Messages */ -#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus standard */ +#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus 2.0 standard */ +#ifndef __KERNEL__ union i2c_smbus_data { __u8 byte; __u16 word; __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ /* and one more for user-space compatibility */ }; +#endif /* i2c_smbus_xfer read or write markers */ #define I2C_SMBUS_READ 1 -- cgit v1.2.3 From 34ae2c09d46a2d0abd907e139b466f798e4095a8 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 15 Nov 2021 10:00:27 +0000 Subject: net: phylink: add generic validate implementation Add a generic validate() implementation using the supported_interfaces and a bitmask of MAC pause/speed/duplex capabilities. This allows us to entirely eliminate many driver private validate() implementations. We expose the underlying phylink_get_linkmodes() function so that drivers which have special needs can still benefit from conversion. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 252 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/phylink.h | 31 ++++++ 2 files changed, 283 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 3ad7397b8119..33462fdc7add 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -166,6 +166,258 @@ static const char *phylink_an_mode_str(unsigned int mode) return mode < ARRAY_SIZE(modestr) ? modestr[mode] : "unknown"; } +static void phylink_caps_to_linkmodes(unsigned long *linkmodes, + unsigned long caps) +{ + if (caps & MAC_SYM_PAUSE) + __set_bit(ETHTOOL_LINK_MODE_Pause_BIT, linkmodes); + + if (caps & MAC_ASYM_PAUSE) + __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, linkmodes); + + if (caps & MAC_10HD) + __set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, linkmodes); + + if (caps & MAC_10FD) + __set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, linkmodes); + + if (caps & MAC_100HD) { + __set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100baseFX_Half_BIT, linkmodes); + } + + if (caps & MAC_100FD) { + __set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100baseFX_Full_BIT, linkmodes); + } + + if (caps & MAC_1000HD) + __set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, linkmodes); + + if (caps & MAC_1000FD) { + __set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT, linkmodes); + } + + if (caps & MAC_2500FD) { + __set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT, linkmodes); + } + + if (caps & MAC_5000FD) + __set_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, linkmodes); + + if (caps & MAC_10000FD) { + __set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseR_FEC_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_10000baseER_Full_BIT, linkmodes); + } + + if (caps & MAC_25000FD) { + __set_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, linkmodes); + } + + if (caps & MAC_40000FD) { + __set_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, linkmodes); + } + + if (caps & MAC_50000FD) { + __set_bit(ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_50000baseDR_Full_BIT, linkmodes); + } + + if (caps & MAC_56000FD) { + __set_bit(ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, linkmodes); + } + + if (caps & MAC_100000FD) { + __set_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseKR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseSR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseCR_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_100000baseDR_Full_BIT, linkmodes); + } + + if (caps & MAC_200000FD) { + __set_bit(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT, linkmodes); + } + + if (caps & MAC_400000FD) { + __set_bit(ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT, + linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT, linkmodes); + __set_bit(ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT, linkmodes); + } +} + +/** + * phylink_get_linkmodes() - get acceptable link modes + * @linkmodes: ethtool linkmode mask (must be already initialised) + * @interface: phy interface mode defined by &typedef phy_interface_t + * @mac_capabilities: bitmask of MAC capabilities + * + * Set all possible pause, speed and duplex linkmodes in @linkmodes that + * are supported by the @interface mode and @mac_capabilities. @linkmodes + * must have been initialised previously. + */ +void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, + unsigned long mac_capabilities) +{ + unsigned long caps = MAC_SYM_PAUSE | MAC_ASYM_PAUSE; + + switch (interface) { + case PHY_INTERFACE_MODE_USXGMII: + caps |= MAC_10000FD | MAC_5000FD | MAC_2500FD; + fallthrough; + + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_GMII: + caps |= MAC_1000HD | MAC_1000FD; + fallthrough; + + case PHY_INTERFACE_MODE_REVRMII: + case PHY_INTERFACE_MODE_RMII: + case PHY_INTERFACE_MODE_REVMII: + case PHY_INTERFACE_MODE_MII: + caps |= MAC_10HD | MAC_10FD; + fallthrough; + + case PHY_INTERFACE_MODE_100BASEX: + caps |= MAC_100HD | MAC_100FD; + break; + + case PHY_INTERFACE_MODE_TBI: + case PHY_INTERFACE_MODE_MOCA: + case PHY_INTERFACE_MODE_RTBI: + case PHY_INTERFACE_MODE_1000BASEX: + caps |= MAC_1000HD; + fallthrough; + case PHY_INTERFACE_MODE_TRGMII: + caps |= MAC_1000FD; + break; + + case PHY_INTERFACE_MODE_2500BASEX: + caps |= MAC_2500FD; + break; + + case PHY_INTERFACE_MODE_5GBASER: + caps |= MAC_5000FD; + break; + + case PHY_INTERFACE_MODE_XGMII: + case PHY_INTERFACE_MODE_RXAUI: + case PHY_INTERFACE_MODE_XAUI: + case PHY_INTERFACE_MODE_10GBASER: + case PHY_INTERFACE_MODE_10GKR: + caps |= MAC_10000FD; + break; + + case PHY_INTERFACE_MODE_25GBASER: + caps |= MAC_25000FD; + break; + + case PHY_INTERFACE_MODE_XLGMII: + caps |= MAC_40000FD; + break; + + case PHY_INTERFACE_MODE_INTERNAL: + caps |= ~0; + break; + + case PHY_INTERFACE_MODE_NA: + case PHY_INTERFACE_MODE_MAX: + case PHY_INTERFACE_MODE_SMII: + break; + } + + phylink_caps_to_linkmodes(linkmodes, caps & mac_capabilities); +} +EXPORT_SYMBOL_GPL(phylink_get_linkmodes); + +/** + * phylink_generic_validate() - generic validate() callback implementation + * @config: a pointer to a &struct phylink_config. + * @supported: ethtool bitmask for supported link modes. + * @state: a pointer to a &struct phylink_link_state. + * + * Generic implementation of the validate() callback that MAC drivers can + * use when they pass the range of supported interfaces and MAC capabilities. + * This makes use of phylink_get_linkmodes(). + */ +void phylink_generic_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + phylink_set_port_modes(mask); + phylink_set(mask, Autoneg); + phylink_get_linkmodes(mask, state->interface, config->mac_capabilities); + + linkmode_and(supported, supported, mask); + linkmode_and(state->advertising, state->advertising, mask); +} +EXPORT_SYMBOL_GPL(phylink_generic_validate); + static int phylink_validate_any(struct phylink *pl, unsigned long *supported, struct phylink_link_state *state) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index f037470b6fb3..3563820a1765 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -20,6 +20,29 @@ enum { MLO_AN_PHY = 0, /* Conventional PHY */ MLO_AN_FIXED, /* Fixed-link mode */ MLO_AN_INBAND, /* In-band protocol */ + + MAC_SYM_PAUSE = BIT(0), + MAC_ASYM_PAUSE = BIT(1), + MAC_10HD = BIT(2), + MAC_10FD = BIT(3), + MAC_10 = MAC_10HD | MAC_10FD, + MAC_100HD = BIT(4), + MAC_100FD = BIT(5), + MAC_100 = MAC_100HD | MAC_100FD, + MAC_1000HD = BIT(6), + MAC_1000FD = BIT(7), + MAC_1000 = MAC_1000HD | MAC_1000FD, + MAC_2500FD = BIT(8), + MAC_5000FD = BIT(9), + MAC_10000FD = BIT(10), + MAC_20000FD = BIT(11), + MAC_25000FD = BIT(12), + MAC_40000FD = BIT(13), + MAC_50000FD = BIT(14), + MAC_56000FD = BIT(15), + MAC_100000FD = BIT(16), + MAC_200000FD = BIT(17), + MAC_400000FD = BIT(18), }; static inline bool phylink_autoneg_inband(unsigned int mode) @@ -69,6 +92,7 @@ enum phylink_op_type { * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx * are supported by the MAC/PCS. + * @mac_capabilities: MAC pause/speed/duplex capabilities. */ struct phylink_config { struct device *dev; @@ -79,6 +103,7 @@ struct phylink_config { void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + unsigned long mac_capabilities; }; /** @@ -442,6 +467,12 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); #endif +void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, + unsigned long mac_capabilities); +void phylink_generic_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state); + struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); -- cgit v1.2.3 From 2f6a470d6545841cf1891b87e360d3998ef024c8 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 15 Nov 2021 07:49:46 -0800 Subject: Revert "Merge branch 'mctp-i2c-driver'" This reverts commit 71812af7234f30362b43ccff33f93890ae4c0655, reversing changes made to cc0be1ad686fb29a4d127948486f40b17fb34b50. Wolfram Sang says: Please revert. Besides the driver in net, it modifies the I2C core code. This has not been acked by the I2C maintainer (in this case me). So, please don't pull this in via the net tree. The question raised here (extending SMBus calls to 255 byte) is complicated because we need ABI backwards compatibility. Link: https://lore.kernel.org/all/YZJ9H4eM%2FM7OXVN0@shikoro/ Signed-off-by: Jakub Kicinski --- Documentation/devicetree/bindings/i2c/i2c.txt | 4 - .../bindings/net/mctp-i2c-controller.yaml | 92 -- drivers/i2c/busses/i2c-aspeed.c | 5 +- drivers/i2c/busses/i2c-npcm7xx.c | 3 +- drivers/i2c/i2c-core-smbus.c | 20 +- drivers/i2c/i2c-dev.c | 93 +- drivers/net/mctp/Kconfig | 12 - drivers/net/mctp/Makefile | 1 - drivers/net/mctp/mctp-i2c.c | 982 --------------------- include/linux/i2c.h | 13 - include/uapi/linux/i2c-dev.h | 2 - include/uapi/linux/i2c.h | 7 +- 12 files changed, 25 insertions(+), 1209 deletions(-) delete mode 100644 Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml delete mode 100644 drivers/net/mctp/mctp-i2c.c (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/i2c/i2c.txt b/Documentation/devicetree/bindings/i2c/i2c.txt index fc3dd7ec0445..b864916e087f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c.txt @@ -95,10 +95,6 @@ wants to support one of the below features, it should adapt these bindings. - smbus-alert states that the optional SMBus-Alert feature apply to this bus. -- mctp-controller - indicates that the system is accessible via this bus as an endpoint for - MCTP over I2C transport. - Required properties (per child device) -------------------------------------- diff --git a/Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml b/Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml deleted file mode 100644 index afd11c9422fa..000000000000 --- a/Documentation/devicetree/bindings/net/mctp-i2c-controller.yaml +++ /dev/null @@ -1,92 +0,0 @@ -# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) -%YAML 1.2 ---- -$id: http://devicetree.org/schemas/net/mctp-i2c-controller.yaml# -$schema: http://devicetree.org/meta-schemas/core.yaml# - -title: MCTP I2C transport binding - -maintainers: - - Matt Johnston - -description: | - An mctp-i2c-controller defines a local MCTP endpoint on an I2C controller. - MCTP I2C is specified by DMTF DSP0237. - - An mctp-i2c-controller must be attached to an I2C adapter which supports - slave functionality. I2C busses (either directly or as subordinate mux - busses) are attached to the mctp-i2c-controller with a 'mctp-controller' - property on each used bus. Each mctp-controller I2C bus will be presented - to the host system as a separate MCTP I2C instance. - -properties: - compatible: - const: mctp-i2c-controller - - reg: - minimum: 0x40000000 - maximum: 0x4000007f - description: | - 7 bit I2C address of the local endpoint. - I2C_OWN_SLAVE_ADDRESS (1<<30) flag must be set. - -additionalProperties: false - -required: - - compatible - - reg - -examples: - - | - // Basic case of a single I2C bus - #include - - i2c { - #address-cells = <1>; - #size-cells = <0>; - mctp-controller; - - mctp@30 { - compatible = "mctp-i2c-controller"; - reg = <(0x30 | I2C_OWN_SLAVE_ADDRESS)>; - }; - }; - - - | - // Mux topology with multiple MCTP-handling busses under - // a single mctp-i2c-controller. - // i2c1 and i2c6 can have MCTP devices, i2c5 does not. - #include - - i2c1: i2c { - #address-cells = <1>; - #size-cells = <0>; - mctp-controller; - - mctp@50 { - compatible = "mctp-i2c-controller"; - reg = <(0x50 | I2C_OWN_SLAVE_ADDRESS)>; - }; - }; - - i2c-mux { - #address-cells = <1>; - #size-cells = <0>; - i2c-parent = <&i2c1>; - - i2c5: i2c@0 { - #address-cells = <1>; - #size-cells = <0>; - reg = <0>; - eeprom@33 { - reg = <0x33>; - }; - }; - - i2c6: i2c@1 { - #address-cells = <1>; - #size-cells = <0>; - reg = <1>; - mctp-controller; - }; - }; diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index 7395f3702fae..67e8b97c0c95 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -533,7 +533,7 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status) msg->buf[bus->buf_index++] = recv_byte; if (msg->flags & I2C_M_RECV_LEN) { - if (unlikely(recv_byte > I2C_SMBUS_V3_BLOCK_MAX)) { + if (unlikely(recv_byte > I2C_SMBUS_BLOCK_MAX)) { bus->cmd_err = -EPROTO; aspeed_i2c_do_stop(bus); goto out_no_complete; @@ -718,8 +718,7 @@ static int aspeed_i2c_master_xfer(struct i2c_adapter *adap, static u32 aspeed_i2c_functionality(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | - I2C_FUNC_SMBUS_BLOCK_DATA | I2C_FUNC_SMBUS_V3_BLOCK; + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SMBUS_BLOCK_DATA; } #if IS_ENABLED(CONFIG_I2C_SLAVE) diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index 6d60f65add85..2ad166355ec9 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -1399,7 +1399,7 @@ static void npcm_i2c_irq_master_handler_read(struct npcm_i2c *bus) if (bus->read_block_use) { /* first byte in block protocol is the size: */ data = npcm_i2c_rd_byte(bus); - data = clamp_val(data, 1, I2C_SMBUS_V3_BLOCK_MAX); + data = clamp_val(data, 1, I2C_SMBUS_BLOCK_MAX); bus->rd_size = data + block_extra_bytes_size; bus->rd_buf[bus->rd_ind++] = data; @@ -2187,7 +2187,6 @@ static u32 npcm_i2c_functionality(struct i2c_adapter *adap) I2C_FUNC_SMBUS_EMUL | I2C_FUNC_SMBUS_BLOCK_DATA | I2C_FUNC_SMBUS_PEC | - I2C_FUNC_SMBUS_V3_BLOCK | I2C_FUNC_SLAVE; } diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c index 743415584aba..e5b2d1465e7e 100644 --- a/drivers/i2c/i2c-core-smbus.c +++ b/drivers/i2c/i2c-core-smbus.c @@ -303,8 +303,7 @@ static void i2c_smbus_try_get_dmabuf(struct i2c_msg *msg, u8 init_val) bool is_read = msg->flags & I2C_M_RD; unsigned char *dma_buf; - dma_buf = kzalloc(I2C_SMBUS_V3_BLOCK_MAX + (is_read ? 2 : 3), - GFP_KERNEL); + dma_buf = kzalloc(I2C_SMBUS_BLOCK_MAX + (is_read ? 2 : 3), GFP_KERNEL); if (!dma_buf) return; @@ -330,10 +329,9 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, * initialize most things with sane defaults, to keep the code below * somewhat simpler. */ - unsigned char msgbuf0[I2C_SMBUS_V3_BLOCK_MAX+3]; - unsigned char msgbuf1[I2C_SMBUS_V3_BLOCK_MAX+2]; + unsigned char msgbuf0[I2C_SMBUS_BLOCK_MAX+3]; + unsigned char msgbuf1[I2C_SMBUS_BLOCK_MAX+2]; int nmsgs = read_write == I2C_SMBUS_READ ? 2 : 1; - u16 block_max; u8 partial_pec = 0; int status; struct i2c_msg msg[2] = { @@ -352,10 +350,6 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, bool wants_pec = ((flags & I2C_CLIENT_PEC) && size != I2C_SMBUS_QUICK && size != I2C_SMBUS_I2C_BLOCK_DATA); - /* Drivers must opt in to 255 byte max block size */ - block_max = i2c_check_functionality(adapter, I2C_FUNC_SMBUS_V3_BLOCK) - ? I2C_SMBUS_V3_BLOCK_MAX : I2C_SMBUS_BLOCK_MAX; - msgbuf0[0] = command; switch (size) { case I2C_SMBUS_QUICK: @@ -405,7 +399,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); } else { msg[0].len = data->block[0] + 2; - if (msg[0].len > block_max + 2) { + if (msg[0].len > I2C_SMBUS_BLOCK_MAX + 2) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -419,7 +413,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, case I2C_SMBUS_BLOCK_PROC_CALL: nmsgs = 2; /* Another special case */ read_write = I2C_SMBUS_READ; - if (data->block[0] > block_max) { + if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block write size %d\n", data->block[0]); @@ -436,7 +430,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, i2c_smbus_try_get_dmabuf(&msg[1], 0); break; case I2C_SMBUS_I2C_BLOCK_DATA: - if (data->block[0] > block_max) { + if (data->block[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block %s size %d\n", read_write == I2C_SMBUS_READ ? "read" : "write", data->block[0]); @@ -504,7 +498,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr, break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_BLOCK_PROC_CALL: - if (msg[1].buf[0] > block_max) { + if (msg[1].buf[0] > I2C_SMBUS_BLOCK_MAX) { dev_err(&adapter->dev, "Invalid block size returned: %d\n", msg[1].buf[0]); diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 5ee9118c0407..bce0e8bb7852 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -46,24 +46,6 @@ struct i2c_dev { struct cdev cdev; }; -/* The userspace union i2c_smbus_data for I2C_SMBUS ioctl is limited - * to 32 bytes (I2C_SMBUS_BLOCK_MAX) for compatibility. - */ -union compat_i2c_smbus_data { - __u8 byte; - __u16 word; - __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ - /* and one more for user-space compatibility */ -}; - -/* Must match i2c-dev.h definition with compat .data member */ -struct i2c_smbus_ioctl_data { - __u8 read_write; - __u8 command; - __u32 size; - union compat_i2c_smbus_data __user *data; -}; - #define I2C_MINORS (MINORMASK + 1) static LIST_HEAD(i2c_dev_list); static DEFINE_SPINLOCK(i2c_dev_list_lock); @@ -253,17 +235,14 @@ static int i2cdev_check_addr(struct i2c_adapter *adapter, unsigned int addr) static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, unsigned nmsgs, struct i2c_msg *msgs) { - u8 __user **data_ptrs = NULL; - u16 *orig_lens = NULL; + u8 __user **data_ptrs; int i, res; - res = -ENOMEM; data_ptrs = kmalloc_array(nmsgs, sizeof(u8 __user *), GFP_KERNEL); - if (data_ptrs == NULL) - goto out; - orig_lens = kmalloc_array(nmsgs, sizeof(u16), GFP_KERNEL); - if (orig_lens == NULL) - goto out; + if (data_ptrs == NULL) { + kfree(msgs); + return -ENOMEM; + } res = 0; for (i = 0; i < nmsgs; i++) { @@ -274,30 +253,12 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, } data_ptrs[i] = (u8 __user *)msgs[i].buf; - msgs[i].buf = NULL; - if (msgs[i].len < 1) { - /* Sanity check */ - res = -EINVAL; - break; - - } - /* Allocate a larger buffer to accommodate possible 255 byte - * blocks. Read results will be dropped later - * if they are too large for the original length. - */ - orig_lens[i] = msgs[i].len; - msgs[i].buf = kmalloc(msgs[i].len + I2C_SMBUS_V3_BLOCK_MAX, - GFP_USER | __GFP_NOWARN); + msgs[i].buf = memdup_user(data_ptrs[i], msgs[i].len); if (IS_ERR(msgs[i].buf)) { res = PTR_ERR(msgs[i].buf); break; } - if (copy_from_user(msgs[i].buf, data_ptrs[i], msgs[i].len)) { - kfree(msgs[i].buf); - res = -EFAULT; - break; - } - /* Buffer from kmalloc, so DMA is ok */ + /* memdup_user allocates with GFP_KERNEL, so DMA is ok */ msgs[i].flags |= I2C_M_DMA_SAFE; /* @@ -313,7 +274,7 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, */ if (msgs[i].flags & I2C_M_RECV_LEN) { if (!(msgs[i].flags & I2C_M_RD) || - msgs[i].buf[0] < 1 || + msgs[i].len < 1 || msgs[i].buf[0] < 1 || msgs[i].len < msgs[i].buf[0] + I2C_SMBUS_BLOCK_MAX) { i++; @@ -336,16 +297,12 @@ static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, res = i2c_transfer(client->adapter, msgs, nmsgs); while (i-- > 0) { if (res >= 0 && (msgs[i].flags & I2C_M_RD)) { - if (orig_lens[i] < msgs[i].len) - res = -EINVAL; - else if (copy_to_user(data_ptrs[i], msgs[i].buf, - msgs[i].len)) + if (copy_to_user(data_ptrs[i], msgs[i].buf, + msgs[i].len)) res = -EFAULT; } kfree(msgs[i].buf); } -out: - kfree(orig_lens); kfree(data_ptrs); kfree(msgs); return res; @@ -353,7 +310,7 @@ out: static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, u8 read_write, u8 command, u32 size, - union compat_i2c_smbus_data __user *data) + union i2c_smbus_data __user *data) { union i2c_smbus_data temp = {}; int datasize, res; @@ -414,16 +371,6 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, if (copy_from_user(&temp, data, datasize)) return -EFAULT; } - if ((size == I2C_SMBUS_BLOCK_PROC_CALL || - size == I2C_SMBUS_I2C_BLOCK_DATA || - size == I2C_SMBUS_BLOCK_DATA) && - read_write == I2C_SMBUS_WRITE && - temp.block[0] > I2C_SMBUS_BLOCK_MAX) { - /* Don't accept writes larger than the buffer size */ - dev_dbg(&client->adapter->dev, "block write is too large"); - return -EINVAL; - - } if (size == I2C_SMBUS_I2C_BLOCK_BROKEN) { /* Convert old I2C block commands to the new convention. This preserves binary compatibility. */ @@ -433,21 +380,9 @@ static noinline int i2cdev_ioctl_smbus(struct i2c_client *client, } res = i2c_smbus_xfer(client->adapter, client->addr, client->flags, read_write, command, size, &temp); - if (res) - return res; - if ((size == I2C_SMBUS_BLOCK_PROC_CALL || - size == I2C_SMBUS_I2C_BLOCK_DATA || - size == I2C_SMBUS_BLOCK_DATA) && - read_write == I2C_SMBUS_READ && - temp.block[0] > I2C_SMBUS_BLOCK_MAX) { - /* Don't accept reads larger than the buffer size */ - dev_dbg(&client->adapter->dev, "block read is too large"); - return -EINVAL; - - } - if ((size == I2C_SMBUS_PROC_CALL) || - (size == I2C_SMBUS_BLOCK_PROC_CALL) || - (read_write == I2C_SMBUS_READ)) { + if (!res && ((size == I2C_SMBUS_PROC_CALL) || + (size == I2C_SMBUS_BLOCK_PROC_CALL) || + (read_write == I2C_SMBUS_READ))) { if (copy_to_user(data, &temp, datasize)) return -EFAULT; } diff --git a/drivers/net/mctp/Kconfig b/drivers/net/mctp/Kconfig index b758b29c2ddf..d8f966cedc89 100644 --- a/drivers/net/mctp/Kconfig +++ b/drivers/net/mctp/Kconfig @@ -3,18 +3,6 @@ if MCTP menu "MCTP Device Drivers" -config MCTP_TRANSPORT_I2C - tristate "MCTP SMBus/I2C transport" - # i2c-mux is optional, but we must build as a module if i2c-mux is a module - depends on I2C_MUX || !I2C_MUX - depends on I2C - depends on I2C_SLAVE - select MCTP_FLOWS - help - Provides a driver to access MCTP devices over SMBus/I2C transport, - from DMTF specification DSP0237. A MCTP protocol network device is - created for each I2C bus that has been assigned a mctp-i2c device. - endmenu endif diff --git a/drivers/net/mctp/Makefile b/drivers/net/mctp/Makefile index 73dc411986a6..e69de29bb2d1 100644 --- a/drivers/net/mctp/Makefile +++ b/drivers/net/mctp/Makefile @@ -1 +0,0 @@ -obj-$(CONFIG_MCTP_TRANSPORT_I2C) += mctp-i2c.o diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c deleted file mode 100644 index ed213b4765a1..000000000000 --- a/drivers/net/mctp/mctp-i2c.c +++ /dev/null @@ -1,982 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Management Controller Transport Protocol (MCTP) - * - * Copyright (c) 2021 Code Construct - * Copyright (c) 2021 Google - */ - -#include -#include -#include -#include -#include -#include -#include - -/* SMBus 3.0 allows 255 data bytes (plus PEC), but the - * first byte is taken for source slave address. - */ -#define MCTP_I2C_MAXBLOCK 255 -#define MCTP_I2C_MAXMTU (MCTP_I2C_MAXBLOCK - 1) -#define MCTP_I2C_MINMTU (64 + 4) -/* Allow space for address, command, byte_count, databytes, PEC */ -#define MCTP_I2C_RXBUFSZ (3 + MCTP_I2C_MAXBLOCK + 1) -#define MCTP_I2C_MINLEN 8 -#define MCTP_I2C_COMMANDCODE 0x0f -#define MCTP_I2C_TX_WORK_LEN 100 -// sufficient for 64kB at min mtu -#define MCTP_I2C_TX_QUEUE_LEN 1100 - -#define MCTP_I2C_OF_PROP "mctp-controller" - -enum { - MCTP_I2C_FLOW_STATE_NEW = 0, - MCTP_I2C_FLOW_STATE_ACTIVE, -}; - -static struct { - /* lock protects clients and also prevents adding/removing adapters - * during mctp_i2c_client probe/remove. - */ - struct mutex lock; - // list of struct mctp_i2c_client - struct list_head clients; -} mi_driver_state; - -struct mctp_i2c_client; - -// The netdev structure. One of these per I2C adapter. -struct mctp_i2c_dev { - struct net_device *ndev; - struct i2c_adapter *adapter; - struct mctp_i2c_client *client; - struct list_head list; // for mctp_i2c_client.devs - - size_t pos; - u8 buffer[MCTP_I2C_RXBUFSZ]; - - struct task_struct *tx_thread; - wait_queue_head_t tx_wq; - struct sk_buff_head tx_queue; - - // a fake entry in our tx queue to perform an unlock operation - struct sk_buff unlock_marker; - - spinlock_t flow_lock; // protects i2c_lock_count and release_count - int i2c_lock_count; - int release_count; -}; - -/* The i2c client structure. One per hardware i2c bus at the top of the - * mux tree, shared by multiple netdevs - */ -struct mctp_i2c_client { - struct i2c_client *client; - u8 lladdr; - - struct mctp_i2c_dev *sel; - struct list_head devs; - spinlock_t curr_lock; // protects sel - - struct list_head list; // for mi_driver_state.clients -}; - -// Header on the wire -struct mctp_i2c_hdr { - u8 dest_slave; - u8 command; - u8 byte_count; - u8 source_slave; -}; - -static int mctp_i2c_recv(struct mctp_i2c_dev *midev); -static int mctp_i2c_slave_cb(struct i2c_client *client, - enum i2c_slave_event event, u8 *val); - -static struct i2c_adapter *mux_root_adapter(struct i2c_adapter *adap) -{ -#if IS_ENABLED(CONFIG_I2C_MUX) - return i2c_root_adapter(&adap->dev); -#else - /* In non-mux config all i2c adapters are root adapters */ - return adap; -#endif -} - -static ssize_t mctp_current_mux_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct mctp_i2c_client *mcli = i2c_get_clientdata(to_i2c_client(dev)); - struct net_device *ndev = NULL; - unsigned long flags; - ssize_t l; - - spin_lock_irqsave(&mcli->curr_lock, flags); - if (mcli->sel) { - ndev = mcli->sel->ndev; - dev_hold(ndev); - } - spin_unlock_irqrestore(&mcli->curr_lock, flags); - l = scnprintf(buf, PAGE_SIZE, "%s\n", ndev ? ndev->name : "(none)"); - if (ndev) - dev_put(ndev); - return l; -} -static DEVICE_ATTR_RO(mctp_current_mux); - -/* Creates a new i2c slave device attached to the root adapter. - * Sets up the slave callback. - * Must be called with a client on a root adapter. - */ -static struct mctp_i2c_client *mctp_i2c_new_client(struct i2c_client *client) -{ - struct mctp_i2c_client *mcli = NULL; - struct i2c_adapter *root = NULL; - int rc; - - if (client->flags & I2C_CLIENT_TEN) { - dev_err(&client->dev, "%s failed, MCTP requires a 7-bit I2C address, addr=0x%x", - __func__, client->addr); - rc = -EINVAL; - goto err; - } - - root = mux_root_adapter(client->adapter); - if (!root) { - dev_err(&client->dev, "%s failed to find root adapter\n", __func__); - rc = -ENOENT; - goto err; - } - if (root != client->adapter) { - dev_err(&client->dev, - "A mctp-i2c-controller client cannot be placed on an I2C mux adapter.\n" - " It should be placed on the mux tree root adapter\n" - " then set mctp-controller property on adapters to attach\n"); - rc = -EINVAL; - goto err; - } - - mcli = kzalloc(sizeof(*mcli), GFP_KERNEL); - if (!mcli) { - rc = -ENOMEM; - goto err; - } - spin_lock_init(&mcli->curr_lock); - INIT_LIST_HEAD(&mcli->devs); - INIT_LIST_HEAD(&mcli->list); - mcli->lladdr = client->addr & 0xff; - mcli->client = client; - i2c_set_clientdata(client, mcli); - - rc = i2c_slave_register(mcli->client, mctp_i2c_slave_cb); - if (rc) { - dev_err(&client->dev, "%s i2c register failed %d\n", __func__, rc); - mcli->client = NULL; - i2c_set_clientdata(client, NULL); - goto err; - } - - rc = device_create_file(&client->dev, &dev_attr_mctp_current_mux); - if (rc) { - dev_err(&client->dev, "%s adding sysfs \"%s\" failed %d\n", __func__, - dev_attr_mctp_current_mux.attr.name, rc); - // continue anyway - } - - return mcli; -err: - if (mcli) { - if (mcli->client) { - device_remove_file(&mcli->client->dev, &dev_attr_mctp_current_mux); - i2c_unregister_device(mcli->client); - } - kfree(mcli); - } - return ERR_PTR(rc); -} - -static void mctp_i2c_free_client(struct mctp_i2c_client *mcli) -{ - int rc; - - WARN_ON(!mutex_is_locked(&mi_driver_state.lock)); - WARN_ON(!list_empty(&mcli->devs)); - WARN_ON(mcli->sel); // sanity check, no locking - - device_remove_file(&mcli->client->dev, &dev_attr_mctp_current_mux); - rc = i2c_slave_unregister(mcli->client); - // leak if it fails, we can't propagate errors upwards - if (rc) - dev_err(&mcli->client->dev, "%s i2c unregister failed %d\n", __func__, rc); - else - kfree(mcli); -} - -/* Switch the mctp i2c device to receive responses. - * Call with curr_lock held - */ -static void __mctp_i2c_device_select(struct mctp_i2c_client *mcli, - struct mctp_i2c_dev *midev) -{ - assert_spin_locked(&mcli->curr_lock); - if (midev) - dev_hold(midev->ndev); - if (mcli->sel) - dev_put(mcli->sel->ndev); - mcli->sel = midev; -} - -// Switch the mctp i2c device to receive responses -static void mctp_i2c_device_select(struct mctp_i2c_client *mcli, - struct mctp_i2c_dev *midev) -{ - unsigned long flags; - - spin_lock_irqsave(&mcli->curr_lock, flags); - __mctp_i2c_device_select(mcli, midev); - spin_unlock_irqrestore(&mcli->curr_lock, flags); -} - -static int mctp_i2c_slave_cb(struct i2c_client *client, - enum i2c_slave_event event, u8 *val) -{ - struct mctp_i2c_client *mcli = i2c_get_clientdata(client); - struct mctp_i2c_dev *midev = NULL; - unsigned long flags; - int rc = 0; - - spin_lock_irqsave(&mcli->curr_lock, flags); - midev = mcli->sel; - if (midev) - dev_hold(midev->ndev); - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - if (!midev) - return 0; - - switch (event) { - case I2C_SLAVE_WRITE_RECEIVED: - if (midev->pos < MCTP_I2C_RXBUFSZ) { - midev->buffer[midev->pos] = *val; - midev->pos++; - } else { - midev->ndev->stats.rx_over_errors++; - } - - break; - case I2C_SLAVE_WRITE_REQUESTED: - /* dest_slave as first byte */ - midev->buffer[0] = mcli->lladdr << 1; - midev->pos = 1; - break; - case I2C_SLAVE_STOP: - rc = mctp_i2c_recv(midev); - break; - default: - break; - } - - dev_put(midev->ndev); - return rc; -} - -// Processes incoming data that has been accumulated by the slave cb -static int mctp_i2c_recv(struct mctp_i2c_dev *midev) -{ - struct net_device *ndev = midev->ndev; - struct mctp_i2c_hdr *hdr; - struct mctp_skb_cb *cb; - struct sk_buff *skb; - u8 pec, calc_pec; - size_t recvlen; - - /* + 1 for the PEC */ - if (midev->pos < MCTP_I2C_MINLEN + 1) { - ndev->stats.rx_length_errors++; - return -EINVAL; - } - recvlen = midev->pos - 1; - - hdr = (void *)midev->buffer; - if (hdr->command != MCTP_I2C_COMMANDCODE) { - ndev->stats.rx_dropped++; - return -EINVAL; - } - - pec = midev->buffer[midev->pos - 1]; - calc_pec = i2c_smbus_pec(0, midev->buffer, recvlen); - if (pec != calc_pec) { - ndev->stats.rx_crc_errors++; - return -EINVAL; - } - - skb = netdev_alloc_skb(ndev, recvlen); - if (!skb) { - ndev->stats.rx_dropped++; - return -ENOMEM; - } - - skb->protocol = htons(ETH_P_MCTP); - skb_put_data(skb, midev->buffer, recvlen); - skb_reset_mac_header(skb); - skb_pull(skb, sizeof(struct mctp_i2c_hdr)); - skb_reset_network_header(skb); - - cb = __mctp_cb(skb); - cb->halen = 1; - cb->haddr[0] = hdr->source_slave; - - if (netif_rx(skb) == NET_RX_SUCCESS) { - ndev->stats.rx_packets++; - ndev->stats.rx_bytes += skb->len; - } else { - ndev->stats.rx_dropped++; - } - return 0; -} - -enum mctp_i2c_flow_state { - MCTP_I2C_TX_FLOW_INVALID, - MCTP_I2C_TX_FLOW_NONE, - MCTP_I2C_TX_FLOW_NEW, - MCTP_I2C_TX_FLOW_EXISTING, -}; - -static enum mctp_i2c_flow_state -mctp_i2c_get_tx_flow_state(struct mctp_i2c_dev *midev, struct sk_buff *skb) -{ - enum mctp_i2c_flow_state state; - struct mctp_sk_key *key; - struct mctp_flow *flow; - unsigned long flags; - - flow = skb_ext_find(skb, SKB_EXT_MCTP); - if (!flow) - return MCTP_I2C_TX_FLOW_NONE; - - key = flow->key; - if (!key) - return MCTP_I2C_TX_FLOW_NONE; - - spin_lock_irqsave(&key->lock, flags); - /* if the key is present but invalid, we're unlikely to be able - * to handle the flow at all; just drop now - */ - if (!key->valid) { - state = MCTP_I2C_TX_FLOW_INVALID; - - } else if (key->dev_flow_state == MCTP_I2C_FLOW_STATE_NEW) { - key->dev_flow_state = MCTP_I2C_FLOW_STATE_ACTIVE; - state = MCTP_I2C_TX_FLOW_NEW; - } else { - state = MCTP_I2C_TX_FLOW_EXISTING; - } - - spin_unlock_irqrestore(&key->lock, flags); - - return state; -} - -/* We're not contending with ourselves here; we only need to exclude other - * i2c clients from using the bus. refcounts are simply to prevent - * recursive locking. - */ -static void mctp_i2c_lock_nest(struct mctp_i2c_dev *midev) -{ - unsigned long flags; - bool lock; - - spin_lock_irqsave(&midev->flow_lock, flags); - lock = midev->i2c_lock_count == 0; - midev->i2c_lock_count++; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - if (lock) - i2c_lock_bus(midev->adapter, I2C_LOCK_SEGMENT); -} - -static void mctp_i2c_unlock_nest(struct mctp_i2c_dev *midev) -{ - unsigned long flags; - bool unlock; - - spin_lock_irqsave(&midev->flow_lock, flags); - if (!WARN_ONCE(midev->i2c_lock_count == 0, "lock count underflow!")) - midev->i2c_lock_count--; - unlock = midev->i2c_lock_count == 0; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - if (unlock) - i2c_unlock_bus(midev->adapter, I2C_LOCK_SEGMENT); -} - -static void mctp_i2c_xmit(struct mctp_i2c_dev *midev, struct sk_buff *skb) -{ - struct net_device_stats *stats = &midev->ndev->stats; - enum mctp_i2c_flow_state fs; - union i2c_smbus_data *data; - struct mctp_i2c_hdr *hdr; - unsigned int len; - u16 daddr; - int rc; - - fs = mctp_i2c_get_tx_flow_state(midev, skb); - - len = skb->len; - hdr = (void *)skb_mac_header(skb); - data = (void *)&hdr->byte_count; - daddr = hdr->dest_slave >> 1; - - switch (fs) { - case MCTP_I2C_TX_FLOW_NONE: - /* no flow: full lock & unlock */ - mctp_i2c_lock_nest(midev); - mctp_i2c_device_select(midev->client, midev); - rc = __i2c_smbus_xfer(midev->adapter, daddr, I2C_CLIENT_PEC, - I2C_SMBUS_WRITE, hdr->command, - I2C_SMBUS_BLOCK_DATA, data); - mctp_i2c_unlock_nest(midev); - break; - - case MCTP_I2C_TX_FLOW_NEW: - /* new flow: lock, tx, but don't unlock; that will happen - * on flow release - */ - mctp_i2c_lock_nest(midev); - mctp_i2c_device_select(midev->client, midev); - fallthrough; - - case MCTP_I2C_TX_FLOW_EXISTING: - /* existing flow: we already have the lock; just tx */ - rc = __i2c_smbus_xfer(midev->adapter, daddr, I2C_CLIENT_PEC, - I2C_SMBUS_WRITE, hdr->command, - I2C_SMBUS_BLOCK_DATA, data); - break; - - case MCTP_I2C_TX_FLOW_INVALID: - return; - } - - if (rc) { - dev_warn_ratelimited(&midev->adapter->dev, - "%s i2c_smbus_xfer failed %d", __func__, rc); - stats->tx_errors++; - } else { - stats->tx_bytes += len; - stats->tx_packets++; - } -} - -static void mctp_i2c_flow_release(struct mctp_i2c_dev *midev) -{ - unsigned long flags; - bool unlock; - - spin_lock_irqsave(&midev->flow_lock, flags); - if (midev->release_count > midev->i2c_lock_count) { - WARN_ONCE(1, "release count overflow"); - midev->release_count = midev->i2c_lock_count; - } - - midev->i2c_lock_count -= midev->release_count; - unlock = midev->i2c_lock_count == 0 && midev->release_count > 0; - midev->release_count = 0; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - if (unlock) - i2c_unlock_bus(midev->adapter, I2C_LOCK_SEGMENT); -} - -static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev, - unsigned short type, const void *daddr, - const void *saddr, unsigned int len) -{ - struct mctp_i2c_hdr *hdr; - struct mctp_hdr *mhdr; - u8 lldst, llsrc; - - lldst = *((u8 *)daddr); - llsrc = *((u8 *)saddr); - - skb_push(skb, sizeof(struct mctp_i2c_hdr)); - skb_reset_mac_header(skb); - hdr = (void *)skb_mac_header(skb); - mhdr = mctp_hdr(skb); - hdr->dest_slave = (lldst << 1) & 0xff; - hdr->command = MCTP_I2C_COMMANDCODE; - hdr->byte_count = len + 1; - if (hdr->byte_count > MCTP_I2C_MAXBLOCK) - return -EMSGSIZE; - hdr->source_slave = ((llsrc << 1) & 0xff) | 0x01; - mhdr->ver = 0x01; - - return 0; -} - -static int mctp_i2c_tx_thread(void *data) -{ - struct mctp_i2c_dev *midev = data; - struct sk_buff *skb; - unsigned long flags; - - for (;;) { - if (kthread_should_stop()) - break; - - spin_lock_irqsave(&midev->tx_queue.lock, flags); - skb = __skb_dequeue(&midev->tx_queue); - if (netif_queue_stopped(midev->ndev)) - netif_wake_queue(midev->ndev); - spin_unlock_irqrestore(&midev->tx_queue.lock, flags); - - if (skb == &midev->unlock_marker) { - mctp_i2c_flow_release(midev); - - } else if (skb) { - mctp_i2c_xmit(midev, skb); - kfree_skb(skb); - - } else { - wait_event(midev->tx_wq, - !skb_queue_empty(&midev->tx_queue) || - kthread_should_stop()); - } - } - - return 0; -} - -static netdev_tx_t mctp_i2c_start_xmit(struct sk_buff *skb, - struct net_device *dev) -{ - struct mctp_i2c_dev *midev = netdev_priv(dev); - unsigned long flags; - - spin_lock_irqsave(&midev->tx_queue.lock, flags); - if (skb_queue_len(&midev->tx_queue) >= MCTP_I2C_TX_WORK_LEN) { - netif_stop_queue(dev); - spin_unlock_irqrestore(&midev->tx_queue.lock, flags); - netdev_err(dev, "BUG! Tx Ring full when queue awake!\n"); - return NETDEV_TX_BUSY; - } - - __skb_queue_tail(&midev->tx_queue, skb); - if (skb_queue_len(&midev->tx_queue) == MCTP_I2C_TX_WORK_LEN) - netif_stop_queue(dev); - spin_unlock_irqrestore(&midev->tx_queue.lock, flags); - - wake_up(&midev->tx_wq); - return NETDEV_TX_OK; -} - -static void mctp_i2c_release_flow(struct mctp_dev *mdev, - struct mctp_sk_key *key) - -{ - struct mctp_i2c_dev *midev = netdev_priv(mdev->dev); - unsigned long flags; - - spin_lock_irqsave(&midev->flow_lock, flags); - midev->release_count++; - spin_unlock_irqrestore(&midev->flow_lock, flags); - - /* Ensure we have a release operation queued, through the fake - * marker skb - */ - spin_lock(&midev->tx_queue.lock); - if (!midev->unlock_marker.next) - __skb_queue_tail(&midev->tx_queue, &midev->unlock_marker); - spin_unlock(&midev->tx_queue.lock); - - wake_up(&midev->tx_wq); -} - -static const struct net_device_ops mctp_i2c_ops = { - .ndo_start_xmit = mctp_i2c_start_xmit, -}; - -static const struct header_ops mctp_i2c_headops = { - .create = mctp_i2c_header_create, -}; - -static const struct mctp_netdev_ops mctp_i2c_mctp_ops = { - .release_flow = mctp_i2c_release_flow, -}; - -static void mctp_i2c_net_setup(struct net_device *dev) -{ - dev->type = ARPHRD_MCTP; - - dev->mtu = MCTP_I2C_MAXMTU; - dev->min_mtu = MCTP_I2C_MINMTU; - dev->max_mtu = MCTP_I2C_MAXMTU; - dev->tx_queue_len = MCTP_I2C_TX_QUEUE_LEN; - - dev->hard_header_len = sizeof(struct mctp_i2c_hdr); - dev->addr_len = 1; - - dev->netdev_ops = &mctp_i2c_ops; - dev->header_ops = &mctp_i2c_headops; - dev->needs_free_netdev = true; -} - -static int mctp_i2c_add_netdev(struct mctp_i2c_client *mcli, - struct i2c_adapter *adap) -{ - unsigned long flags; - struct mctp_i2c_dev *midev = NULL; - struct net_device *ndev = NULL; - struct i2c_adapter *root; - char namebuf[30]; - int rc; - - root = mux_root_adapter(adap); - if (root != mcli->client->adapter) { - dev_err(&mcli->client->dev, - "I2C adapter %s is not a child bus of %s", - mcli->client->adapter->name, root->name); - return -EINVAL; - } - - WARN_ON(!mutex_is_locked(&mi_driver_state.lock)); - snprintf(namebuf, sizeof(namebuf), "mctpi2c%d", adap->nr); - ndev = alloc_netdev(sizeof(*midev), namebuf, NET_NAME_ENUM, mctp_i2c_net_setup); - if (!ndev) { - dev_err(&mcli->client->dev, "%s alloc netdev failed\n", __func__); - rc = -ENOMEM; - goto err; - } - dev_net_set(ndev, current->nsproxy->net_ns); - SET_NETDEV_DEV(ndev, &adap->dev); - ndev->dev_addr = &mcli->lladdr; - - midev = netdev_priv(ndev); - skb_queue_head_init(&midev->tx_queue); - INIT_LIST_HEAD(&midev->list); - midev->adapter = adap; - midev->client = mcli; - spin_lock_init(&midev->flow_lock); - midev->i2c_lock_count = 0; - midev->release_count = 0; - /* Hold references */ - get_device(&midev->adapter->dev); - get_device(&midev->client->client->dev); - midev->ndev = ndev; - init_waitqueue_head(&midev->tx_wq); - midev->tx_thread = kthread_create(mctp_i2c_tx_thread, midev, - "%s/tx", namebuf); - if (IS_ERR_OR_NULL(midev->tx_thread)) { - rc = -ENOMEM; - goto err_free; - } - - rc = mctp_register_netdev(ndev, &mctp_i2c_mctp_ops); - if (rc) { - dev_err(&mcli->client->dev, - "%s register netdev \"%s\" failed %d\n", __func__, - ndev->name, rc); - goto err_stop_kthread; - } - spin_lock_irqsave(&mcli->curr_lock, flags); - list_add(&midev->list, &mcli->devs); - // Select a device by default - if (!mcli->sel) - __mctp_i2c_device_select(mcli, midev); - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - wake_up_process(midev->tx_thread); - - return 0; - -err_stop_kthread: - kthread_stop(midev->tx_thread); - -err_free: - free_netdev(ndev); - -err: - return rc; -} - -// Removes and unregisters a mctp-i2c netdev -static void mctp_i2c_free_netdev(struct mctp_i2c_dev *midev) -{ - struct mctp_i2c_client *mcli = midev->client; - unsigned long flags; - - netif_stop_queue(midev->ndev); - kthread_stop(midev->tx_thread); - skb_queue_purge(&midev->tx_queue); - - /* Release references, used only for TX which has stopped */ - put_device(&midev->adapter->dev); - put_device(&mcli->client->dev); - - /* Remove it from the parent mcli */ - spin_lock_irqsave(&mcli->curr_lock, flags); - list_del(&midev->list); - if (mcli->sel == midev) { - struct mctp_i2c_dev *first; - - first = list_first_entry_or_null(&mcli->devs, struct mctp_i2c_dev, list); - __mctp_i2c_device_select(mcli, first); - } - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - /* Remove netdev. mctp_i2c_slave_cb() takes a dev_hold() so removing - * it now is safe. unregister_netdev() frees ndev and midev. - */ - mctp_unregister_netdev(midev->ndev); -} - -// Removes any netdev for adap. mcli is the parent root i2c client -static void mctp_i2c_remove_netdev(struct mctp_i2c_client *mcli, - struct i2c_adapter *adap) -{ - unsigned long flags; - struct mctp_i2c_dev *midev = NULL, *m = NULL; - - WARN_ON(!mutex_is_locked(&mi_driver_state.lock)); - spin_lock_irqsave(&mcli->curr_lock, flags); - // list size is limited by number of MCTP netdevs on a single hardware bus - list_for_each_entry(m, &mcli->devs, list) - if (m->adapter == adap) { - midev = m; - break; - } - spin_unlock_irqrestore(&mcli->curr_lock, flags); - - if (midev) - mctp_i2c_free_netdev(midev); -} - -/* Determines whether a device is an i2c adapter. - * Optionally returns the root i2c_adapter - */ -static struct i2c_adapter *mctp_i2c_get_adapter(struct device *dev, - struct i2c_adapter **ret_root) -{ - struct i2c_adapter *root, *adap; - - if (dev->type != &i2c_adapter_type) - return NULL; - adap = to_i2c_adapter(dev); - root = mux_root_adapter(adap); - WARN_ONCE(!root, "%s failed to find root adapter for %s\n", - __func__, dev_name(dev)); - if (!root) - return NULL; - if (ret_root) - *ret_root = root; - return adap; -} - -/* Determines whether a device is an i2c adapter with the "mctp-controller" - * devicetree property set. If adap is not an OF node, returns match_no_of - */ -static bool mctp_i2c_adapter_match(struct i2c_adapter *adap, bool match_no_of) -{ - if (!adap->dev.of_node) - return match_no_of; - return of_property_read_bool(adap->dev.of_node, MCTP_I2C_OF_PROP); -} - -/* Called for each existing i2c device (adapter or client) when a - * new mctp-i2c client is probed. - */ -static int mctp_i2c_client_try_attach(struct device *dev, void *data) -{ - struct i2c_adapter *adap = NULL, *root = NULL; - struct mctp_i2c_client *mcli = data; - - adap = mctp_i2c_get_adapter(dev, &root); - if (!adap) - return 0; - if (mcli->client->adapter != root) - return 0; - // Must either have mctp-controller property on the adapter, or - // be a root adapter if it's non-devicetree - if (!mctp_i2c_adapter_match(adap, adap == root)) - return 0; - - return mctp_i2c_add_netdev(mcli, adap); -} - -static void mctp_i2c_notify_add(struct device *dev) -{ - struct mctp_i2c_client *mcli = NULL, *m = NULL; - struct i2c_adapter *root = NULL, *adap = NULL; - int rc; - - adap = mctp_i2c_get_adapter(dev, &root); - if (!adap) - return; - // Check for mctp-controller property on the adapter - if (!mctp_i2c_adapter_match(adap, false)) - return; - - /* Find an existing mcli for adap's root */ - mutex_lock(&mi_driver_state.lock); - list_for_each_entry(m, &mi_driver_state.clients, list) { - if (m->client->adapter == root) { - mcli = m; - break; - } - } - - if (mcli) { - rc = mctp_i2c_add_netdev(mcli, adap); - if (rc) - dev_warn(dev, "%s Failed adding mctp-i2c device", - __func__); - } - mutex_unlock(&mi_driver_state.lock); -} - -static void mctp_i2c_notify_del(struct device *dev) -{ - struct i2c_adapter *root = NULL, *adap = NULL; - struct mctp_i2c_client *mcli = NULL; - - adap = mctp_i2c_get_adapter(dev, &root); - if (!adap) - return; - - mutex_lock(&mi_driver_state.lock); - list_for_each_entry(mcli, &mi_driver_state.clients, list) { - if (mcli->client->adapter == root) { - mctp_i2c_remove_netdev(mcli, adap); - break; - } - } - mutex_unlock(&mi_driver_state.lock); -} - -static int mctp_i2c_probe(struct i2c_client *client) -{ - struct mctp_i2c_client *mcli = NULL; - int rc; - - /* Check for >32 byte block support required for MCTP */ - if (!i2c_check_functionality(client->adapter, I2C_FUNC_SMBUS_V3_BLOCK)) { - dev_err(&client->dev, - "%s failed, I2C bus driver does not support 255 byte block transfer\n", - __func__); - return -EOPNOTSUPP; - } - - mutex_lock(&mi_driver_state.lock); - mcli = mctp_i2c_new_client(client); - if (IS_ERR(mcli)) { - rc = PTR_ERR(mcli); - mcli = NULL; - goto out; - } else { - list_add(&mcli->list, &mi_driver_state.clients); - } - - // Add a netdev for adapters that have a 'mctp-controller' property - i2c_for_each_dev(mcli, mctp_i2c_client_try_attach); - rc = 0; -out: - mutex_unlock(&mi_driver_state.lock); - return rc; -} - -static int mctp_i2c_remove(struct i2c_client *client) -{ - struct mctp_i2c_client *mcli = i2c_get_clientdata(client); - struct mctp_i2c_dev *midev = NULL, *tmp = NULL; - - mutex_lock(&mi_driver_state.lock); - list_del(&mcli->list); - // Remove all child adapter netdevs - list_for_each_entry_safe(midev, tmp, &mcli->devs, list) - mctp_i2c_free_netdev(midev); - - mctp_i2c_free_client(mcli); - mutex_unlock(&mi_driver_state.lock); - // Callers ignore return code - return 0; -} - -/* We look for a 'mctp-controller' property on I2C busses as they are - * added/deleted, creating/removing netdevs as required. - */ -static int mctp_i2c_notifier_call(struct notifier_block *nb, - unsigned long action, void *data) -{ - struct device *dev = data; - - switch (action) { - case BUS_NOTIFY_ADD_DEVICE: - mctp_i2c_notify_add(dev); - break; - case BUS_NOTIFY_DEL_DEVICE: - mctp_i2c_notify_del(dev); - break; - } - return NOTIFY_DONE; -} - -static struct notifier_block mctp_i2c_notifier = { - .notifier_call = mctp_i2c_notifier_call, -}; - -static const struct i2c_device_id mctp_i2c_id[] = { - { "mctp-i2c", 0 }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, mctp_i2c_id); - -static const struct of_device_id mctp_i2c_of_match[] = { - { .compatible = "mctp-i2c-controller" }, - {}, -}; -MODULE_DEVICE_TABLE(of, mctp_i2c_of_match); - -static struct i2c_driver mctp_i2c_driver = { - .driver = { - .name = "mctp-i2c", - .of_match_table = mctp_i2c_of_match, - }, - .probe_new = mctp_i2c_probe, - .remove = mctp_i2c_remove, - .id_table = mctp_i2c_id, -}; - -static __init int mctp_i2c_init(void) -{ - int rc; - - INIT_LIST_HEAD(&mi_driver_state.clients); - mutex_init(&mi_driver_state.lock); - pr_info("MCTP SMBus/I2C transport driver\n"); - rc = i2c_add_driver(&mctp_i2c_driver); - if (rc) - return rc; - rc = bus_register_notifier(&i2c_bus_type, &mctp_i2c_notifier); - if (rc) { - i2c_del_driver(&mctp_i2c_driver); - return rc; - } - return 0; -} - -static __exit void mctp_i2c_exit(void) -{ - int rc; - - rc = bus_unregister_notifier(&i2c_bus_type, &mctp_i2c_notifier); - if (rc) - pr_warn("%s Could not unregister notifier, %d", __func__, rc); - i2c_del_driver(&mctp_i2c_driver); -} - -module_init(mctp_i2c_init); -module_exit(mctp_i2c_exit); - -MODULE_DESCRIPTION("MCTP SMBus/I2C device"); -MODULE_LICENSE("GPL v2"); -MODULE_AUTHOR("Matt Johnston "); diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 353d6b4e7a53..16119ac1aa97 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -52,19 +52,6 @@ typedef int (*i2c_slave_cb_t)(struct i2c_client *client, struct module; struct property_entry; -/* SMBus 3.0 extends the maximum block read/write size to 255 (from 32). - * The larger size is only supported by some drivers, indicated by - * the I2C_FUNC_SMBUS_V3_BLOCK functionality bit. - */ -#define I2C_SMBUS_V3_BLOCK_MAX 255 /* As specified in SMBus 3.0 standard */ - -/* Note compatibility definition in uapi header with 32 byte block */ -union i2c_smbus_data { - __u8 byte; - __u16 word; - __u8 block[I2C_SMBUS_V3_BLOCK_MAX + 1]; /* block[0] is used for length */ -}; - #if IS_ENABLED(CONFIG_I2C) /* Return the Frequency mode string based on the bus frequency */ const char *i2c_freq_mode_string(u32 bus_freq_hz); diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 46ce31d42f7d..1c4cec4ddd84 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -39,14 +39,12 @@ /* This is the structure as used in the I2C_SMBUS ioctl call */ -#ifndef __KERNEL__ struct i2c_smbus_ioctl_data { __u8 read_write; __u8 command; __u32 size; union i2c_smbus_data __user *data; }; -#endif /* This is the structure as used in the I2C_RDWR ioctl call */ struct i2c_rdwr_ioctl_data { diff --git a/include/uapi/linux/i2c.h b/include/uapi/linux/i2c.h index c3534ab1ae53..92326ebde350 100644 --- a/include/uapi/linux/i2c.h +++ b/include/uapi/linux/i2c.h @@ -108,9 +108,6 @@ struct i2c_msg { #define I2C_FUNC_SMBUS_READ_I2C_BLOCK 0x04000000 /* I2C-like block xfer */ #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK 0x08000000 /* w/ 1-byte reg. addr. */ #define I2C_FUNC_SMBUS_HOST_NOTIFY 0x10000000 /* SMBus 2.0 or later */ -#define I2C_FUNC_SMBUS_V3_BLOCK 0x20000000 /* Device supports 255 byte block */ - /* Note that I2C_SMBUS ioctl only */ - /* supports a 32 byte block */ #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \ I2C_FUNC_SMBUS_WRITE_BYTE) @@ -140,15 +137,13 @@ struct i2c_msg { /* * Data for SMBus Messages */ -#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus 2.0 standard */ -#ifndef __KERNEL__ +#define I2C_SMBUS_BLOCK_MAX 32 /* As specified in SMBus standard */ union i2c_smbus_data { __u8 byte; __u16 word; __u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */ /* and one more for user-space compatibility */ }; -#endif /* i2c_smbus_xfer read or write markers */ #define I2C_SMBUS_READ 1 -- cgit v1.2.3 From f64bd790b750dd281406964af40d16adfc88a074 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 29 Oct 2021 12:51:32 -0700 Subject: ACPI: Keep sub-table parsing infrastructure available for modules The NFIT driver and now the CXL ACPI driver have both open-coded ACPI table parsing. Before another instance is added arrange for the core ACPI sub-table parsing to be optionally available to drivers via the CONFIG_ACPI_TABLE_LIB symbol. If no drivers select the symbol then the infrastructure reverts back to being tagged __init via the __init_or_acpilib annotation. For now, only tag the core sub-table routines and data that the CEDT parsing in the cxl_acpi driver would want to reuse, a CEDT parsing helper is added in a later change. Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Alison Schofield Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/163553709227.2509508.8215196520233473814.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/acpi/Kconfig | 3 +++ drivers/acpi/tables.c | 27 +++++++++++++-------------- include/linux/acpi.h | 22 +++++++++++++++------- 3 files changed, 31 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index cdbdf68bd98f..c97ee0cfe26e 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -59,6 +59,9 @@ config ACPI_SYSTEM_POWER_STATES_SUPPORT config ACPI_CCA_REQUIRED bool +config ACPI_TABLE_LIB + bool + config ACPI_DEBUGGER bool "AML debugger interface" select ACPI_DEBUG diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 71419eb16e09..b80a3de655d7 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -35,7 +35,7 @@ static char *mps_inti_flags_trigger[] = { "dfl", "edge", "res", "level" }; static struct acpi_table_desc initial_tables[ACPI_MAX_TABLES] __initdata; -static int acpi_apic_instance __initdata; +static int acpi_apic_instance __initdata_or_acpilib; enum acpi_subtable_type { ACPI_SUBTABLE_COMMON, @@ -52,7 +52,7 @@ struct acpi_subtable_entry { * Disable table checksum verification for the early stage due to the size * limitation of the current x86 early mapping implementation. */ -static bool acpi_verify_table_checksum __initdata = false; +static bool acpi_verify_table_checksum __initdata_or_acpilib = false; void acpi_table_print_madt_entry(struct acpi_subtable_header *header) { @@ -216,7 +216,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header) } } -static unsigned long __init +static unsigned long __init_or_acpilib acpi_get_entry_type(struct acpi_subtable_entry *entry) { switch (entry->type) { @@ -230,7 +230,7 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry) return 0; } -static unsigned long __init +static unsigned long __init_or_acpilib acpi_get_entry_length(struct acpi_subtable_entry *entry) { switch (entry->type) { @@ -244,7 +244,7 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry) return 0; } -static unsigned long __init +static unsigned long __init_or_acpilib acpi_get_subtable_header_length(struct acpi_subtable_entry *entry) { switch (entry->type) { @@ -258,7 +258,7 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry) return 0; } -static enum acpi_subtable_type __init +static enum acpi_subtable_type __init_or_acpilib acpi_get_subtable_type(char *id) { if (strncmp(id, ACPI_SIG_HMAT, 4) == 0) @@ -291,10 +291,10 @@ acpi_get_subtable_type(char *id) * On success returns sum of all matching entries for all proc handlers. * Otherwise, -ENODEV or -EINVAL is returned. */ -static int __init acpi_parse_entries_array(char *id, unsigned long table_size, - struct acpi_table_header *table_header, - struct acpi_subtable_proc *proc, int proc_num, - unsigned int max_entries) +static int __init_or_acpilib acpi_parse_entries_array( + char *id, unsigned long table_size, + struct acpi_table_header *table_header, struct acpi_subtable_proc *proc, + int proc_num, unsigned int max_entries) { struct acpi_subtable_entry entry; unsigned long table_end, subtable_len, entry_len; @@ -352,10 +352,9 @@ static int __init acpi_parse_entries_array(char *id, unsigned long table_size, return errs ? -EINVAL : count; } -int __init acpi_table_parse_entries_array(char *id, - unsigned long table_size, - struct acpi_subtable_proc *proc, int proc_num, - unsigned int max_entries) +int __init_or_acpilib acpi_table_parse_entries_array( + char *id, unsigned long table_size, struct acpi_subtable_proc *proc, + int proc_num, unsigned int max_entries) { struct acpi_table_header *table_header = NULL; int count; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 143ce7e0bee1..edfa3c8f3562 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -232,14 +232,22 @@ int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); + +#ifdef CONFIG_ACPI_TABLE_LIB +#define __init_or_acpilib +#define __initdata_or_acpilib +#else +#define __init_or_acpilib __init +#define __initdata_or_acpilib __initdata +#endif + int acpi_table_parse(char *id, acpi_tbl_table_handler handler); -int __init acpi_table_parse_entries(char *id, unsigned long table_size, - int entry_id, - acpi_tbl_entry_handler handler, - unsigned int max_entries); -int __init acpi_table_parse_entries_array(char *id, unsigned long table_size, - struct acpi_subtable_proc *proc, int proc_num, - unsigned int max_entries); +int __init_or_acpilib acpi_table_parse_entries(char *id, + unsigned long table_size, int entry_id, + acpi_tbl_entry_handler handler, unsigned int max_entries); +int __init_or_acpilib acpi_table_parse_entries_array(char *id, + unsigned long table_size, struct acpi_subtable_proc *proc, + int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); -- cgit v1.2.3 From ad2f63971e9655e3987db32dac85aa50658790eb Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 29 Oct 2021 12:51:37 -0700 Subject: ACPI: Teach ACPI table parsing about the CEDT header format The CEDT adds yet one more unique subtable header type where the length is a 16-bit value. Extend the subtable helpers to detect this scenario. Cc: "Rafael J. Wysocki" Cc: Len Brown Tested-by: Alison Schofield Reviewed-by: Alison Schofield Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/163553709742.2509508.5177761945441327574.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/acpi/tables.c | 9 +++++++++ include/linux/acpi.h | 1 + 2 files changed, 10 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index b80a3de655d7..8d052b65f6bc 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -41,6 +41,7 @@ enum acpi_subtable_type { ACPI_SUBTABLE_COMMON, ACPI_SUBTABLE_HMAT, ACPI_SUBTABLE_PRMT, + ACPI_SUBTABLE_CEDT, }; struct acpi_subtable_entry { @@ -226,6 +227,8 @@ acpi_get_entry_type(struct acpi_subtable_entry *entry) return entry->hdr->hmat.type; case ACPI_SUBTABLE_PRMT: return 0; + case ACPI_SUBTABLE_CEDT: + return entry->hdr->cedt.type; } return 0; } @@ -240,6 +243,8 @@ acpi_get_entry_length(struct acpi_subtable_entry *entry) return entry->hdr->hmat.length; case ACPI_SUBTABLE_PRMT: return entry->hdr->prmt.length; + case ACPI_SUBTABLE_CEDT: + return entry->hdr->cedt.length; } return 0; } @@ -254,6 +259,8 @@ acpi_get_subtable_header_length(struct acpi_subtable_entry *entry) return sizeof(entry->hdr->hmat); case ACPI_SUBTABLE_PRMT: return sizeof(entry->hdr->prmt); + case ACPI_SUBTABLE_CEDT: + return sizeof(entry->hdr->cedt); } return 0; } @@ -265,6 +272,8 @@ acpi_get_subtable_type(char *id) return ACPI_SUBTABLE_HMAT; if (strncmp(id, ACPI_SIG_PRMT, 4) == 0) return ACPI_SUBTABLE_PRMT; + if (strncmp(id, ACPI_SIG_CEDT, 4) == 0) + return ACPI_SUBTABLE_CEDT; return ACPI_SUBTABLE_COMMON; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index edfa3c8f3562..6b7f181d51e2 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -133,6 +133,7 @@ union acpi_subtable_headers { struct acpi_subtable_header common; struct acpi_hmat_structure hmat; struct acpi_prmt_module_header prmt; + struct acpi_cedt_header cedt; }; typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); -- cgit v1.2.3 From 2d03e46a4bad20191d07b83ec1242d5f002577be Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 29 Oct 2021 12:51:42 -0700 Subject: ACPI: Add a context argument for table parsing handlers In preparation for drivers reusing the core table parsing infrastructure, arrange for handlers to take a context argument. This allows driver table parsing to wrap ACPI table entries in driver-specific data. The first consumer of this infrastructure is the CEDT parsing that happens in the cxl_acpi driver, add a conditional (CONFIG_ACPI_TABLE_LIB=y) export of a acpi_table_parse_cedt() helper for this case. Cc: "Rafael J. Wysocki" Cc: Len Brown Tested-by: Alison Schofield Reviewed-by: Alison Schofield Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/163553710257.2509508.14310494417463866020.stgit@dwillia2-desk3.amr.corp.intel.com Signed-off-by: Dan Williams --- drivers/acpi/tables.c | 51 ++++++++++++++++++++++++++++++++++++++++++++------- include/linux/acpi.h | 11 +++++++++++ 2 files changed, 55 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 8d052b65f6bc..e9bdbb6fbc36 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -277,6 +277,22 @@ acpi_get_subtable_type(char *id) return ACPI_SUBTABLE_COMMON; } +static __init_or_acpilib bool has_handler(struct acpi_subtable_proc *proc) +{ + return proc->handler || proc->handler_arg; +} + +static __init_or_acpilib int call_handler(struct acpi_subtable_proc *proc, + union acpi_subtable_headers *hdr, + unsigned long end) +{ + if (proc->handler) + return proc->handler(hdr, end); + if (proc->handler_arg) + return proc->handler_arg(hdr, proc->arg, end); + return -EINVAL; +} + /** * acpi_parse_entries_array - for each proc_num find a suitable subtable * @@ -327,8 +343,9 @@ static int __init_or_acpilib acpi_parse_entries_array( for (i = 0; i < proc_num; i++) { if (acpi_get_entry_type(&entry) != proc[i].id) continue; - if (!proc[i].handler || - (!errs && proc[i].handler(entry.hdr, table_end))) { + if (!has_handler(&proc[i]) || + (!errs && + call_handler(&proc[i], entry.hdr, table_end))) { errs++; continue; } @@ -394,21 +411,41 @@ int __init_or_acpilib acpi_table_parse_entries_array( return count; } -int __init acpi_table_parse_entries(char *id, - unsigned long table_size, - int entry_id, - acpi_tbl_entry_handler handler, - unsigned int max_entries) +static int __init_or_acpilib __acpi_table_parse_entries( + char *id, unsigned long table_size, int entry_id, + acpi_tbl_entry_handler handler, acpi_tbl_entry_handler_arg handler_arg, + void *arg, unsigned int max_entries) { struct acpi_subtable_proc proc = { .id = entry_id, .handler = handler, + .handler_arg = handler_arg, + .arg = arg, }; return acpi_table_parse_entries_array(id, table_size, &proc, 1, max_entries); } +int __init_or_acpilib +acpi_table_parse_cedt(enum acpi_cedt_type id, + acpi_tbl_entry_handler_arg handler_arg, void *arg) +{ + return __acpi_table_parse_entries(ACPI_SIG_CEDT, + sizeof(struct acpi_table_cedt), id, + NULL, handler_arg, arg, 0); +} +EXPORT_SYMBOL_ACPI_LIB(acpi_table_parse_cedt); + +int __init acpi_table_parse_entries(char *id, unsigned long table_size, + int entry_id, + acpi_tbl_entry_handler handler, + unsigned int max_entries) +{ + return __acpi_table_parse_entries(id, table_size, entry_id, handler, + NULL, NULL, max_entries); +} + int __init acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries) { diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 6b7f181d51e2..95f88108f664 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -141,6 +141,9 @@ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header, const unsigned long end); +typedef int (*acpi_tbl_entry_handler_arg)(union acpi_subtable_headers *header, + void *arg, const unsigned long end); + /* Debugger support */ struct acpi_debugger_ops { @@ -217,6 +220,8 @@ static inline int acpi_debugger_notify_command_complete(void) struct acpi_subtable_proc { int id; acpi_tbl_entry_handler handler; + acpi_tbl_entry_handler_arg handler_arg; + void *arg; int count; }; @@ -235,9 +240,11 @@ void acpi_table_init_complete (void); int acpi_table_init (void); #ifdef CONFIG_ACPI_TABLE_LIB +#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) #define __init_or_acpilib #define __initdata_or_acpilib #else +#define EXPORT_SYMBOL_ACPI_LIB(x) #define __init_or_acpilib __init #define __initdata_or_acpilib __initdata #endif @@ -252,6 +259,10 @@ int __init_or_acpilib acpi_table_parse_entries_array(char *id, int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); +int __init_or_acpilib +acpi_table_parse_cedt(enum acpi_cedt_type id, + acpi_tbl_entry_handler_arg handler_arg, void *arg); + int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); -- cgit v1.2.3 From 03b122da74b22fbe7cd98184fa5657a9ce13970c Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Tue, 26 Oct 2021 15:00:48 -0700 Subject: x86/sgx: Hook arch_memory_failure() into mainline code Add a call inside memory_failure() to call the arch specific code to check if the address is an SGX EPC page and handle it. Note the SGX EPC pages do not have a "struct page" entry, so the hook goes in at the same point as the device mapping hook. Pull the call to acquire the mutex earlier so the SGX errors are also protected. Make set_mce_nospec() skip SGX pages when trying to adjust the 1:1 map. Signed-off-by: Tony Luck Signed-off-by: Dave Hansen Reviewed-by: Jarkko Sakkinen Reviewed-by: Naoya Horiguchi Tested-by: Reinette Chatre Link: https://lkml.kernel.org/r/20211026220050.697075-6-tony.luck@intel.com --- arch/x86/include/asm/processor.h | 8 ++++++++ arch/x86/include/asm/set_memory.h | 4 ++++ include/linux/mm.h | 13 +++++++++++++ mm/memory-failure.c | 19 +++++++++++++------ 4 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 355d38c0cf60..2c5f12ae7d04 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -855,4 +855,12 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; +#ifdef CONFIG_X86_SGX +int arch_memory_failure(unsigned long pfn, int flags); +#define arch_memory_failure arch_memory_failure + +bool arch_is_platform_page(u64 paddr); +#define arch_is_platform_page arch_is_platform_page +#endif + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 872617542bbc..ff0f2d90338a 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_SET_MEMORY_H #define _ASM_X86_SET_MEMORY_H +#include #include #include @@ -99,6 +100,9 @@ static inline int set_mce_nospec(unsigned long pfn, bool unmap) unsigned long decoy_addr; int rc; + /* SGX pages are not in the 1:1 map */ + if (arch_is_platform_page(pfn << PAGE_SHIFT)) + return 0; /* * We would like to just call: * set_memory_XX((unsigned long)pfn_to_kaddr(pfn), 1); diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..57f1aa2a33b6 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3231,6 +3231,19 @@ extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); +#ifndef arch_memory_failure +static inline int arch_memory_failure(unsigned long pfn, int flags) +{ + return -ENXIO; +} +#endif + +#ifndef arch_is_platform_page +static inline bool arch_is_platform_page(u64 paddr) +{ + return false; +} +#endif /* * Error handlers for various types of pages. diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 07c875fdeaf0..fddee33bc6cb 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1651,21 +1651,28 @@ int memory_failure(unsigned long pfn, int flags) if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); + mutex_lock(&mf_mutex); + p = pfn_to_online_page(pfn); if (!p) { + res = arch_memory_failure(pfn, flags); + if (res == 0) + goto unlock_mutex; + if (pfn_valid(pfn)) { pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, - pgmap); + if (pgmap) { + res = memory_failure_dev_pagemap(pfn, flags, + pgmap); + goto unlock_mutex; + } } pr_err("Memory failure: %#lx: memory outside kernel control\n", pfn); - return -ENXIO; + res = -ENXIO; + goto unlock_mutex; } - mutex_lock(&mf_mutex); - try_again: if (PageHuge(p)) { res = memory_failure_hugetlb(pfn, flags); -- cgit v1.2.3 From 749303055b78bc38ec0790ccc596cae235446367 Mon Sep 17 00:00:00 2001 From: Simon Trimmer Date: Mon, 15 Nov 2021 12:02:15 +0000 Subject: firmware: cs_dsp: tidy includes in cs_dsp.c and cs_dsp.h This patch removes unused included header files and moves others into cs_dsp.h to ensure that types referenced in the header file are properly described to prevent compiler warnings. Signed-off-by: Simon Trimmer Acked-by: Charles Keepax Link: https://lore.kernel.org/r/20211115120215.56824-1-simont@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 6 ------ include/linux/firmware/cirrus/cs_dsp.h | 5 +++++ 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 948dd8382686..1a0c6c793f6a 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -12,16 +12,10 @@ #include #include #include -#include -#include -#include -#include #include #include -#include #include #include -#include #include #include diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 9ad9eaaaa552..3a54b1afc48f 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -11,6 +11,11 @@ #ifndef __CS_DSP_H #define __CS_DSP_H +#include +#include +#include +#include + #define CS_ADSP2_REGION_0 BIT(0) #define CS_ADSP2_REGION_1 BIT(1) #define CS_ADSP2_REGION_2 BIT(2) -- cgit v1.2.3 From e9380df851878cee71df5a1c7611584421527f7e Mon Sep 17 00:00:00 2001 From: Mario Limonciello Date: Sun, 31 Oct 2021 20:48:52 -0500 Subject: ACPI: Add stubs for wakeup handler functions The commit ddfd9dcf270c ("ACPI: PM: Add acpi_[un]register_wakeup_handler()") added new functions for drivers to use during the s2idle wakeup path, but didn't add stubs for when CONFIG_ACPI wasn't set. Add those stubs in for other drivers to be able to use. Fixes: ddfd9dcf270c ("ACPI: PM: Add acpi_[un]register_wakeup_handler()") Acked-by: Rafael J. Wysocki Signed-off-by: Mario Limonciello Link: https://lore.kernel.org/r/20211101014853.6177-1-mario.limonciello@amd.com Signed-off-by: Linus Walleij --- include/linux/acpi.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 143ce7e0bee1..668d007f0917 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -974,6 +974,15 @@ static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) return -ENODEV; } +static inline int acpi_register_wakeup_handler(int wake_irq, + bool (*wakeup)(void *context), void *context) +{ + return -ENXIO; +} + +static inline void acpi_unregister_wakeup_handler( + bool (*wakeup)(void *context), void *context) { } + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC -- cgit v1.2.3 From a3143f7822a9eeb38f0e046080ae8f79f6c7122d Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:01:58 -0600 Subject: Remove unused header Commit 6a80b30086b8 ("fmc: Delete the FMC subsystem") removed the last user of , but left the header file behind. Nothing uses this file, delete it now. Cc: Linus Walleij Cc: Alessandro Rubini Signed-off-by: Jonathan Corbet Acked-by: Alessandro Rubini Link: https://lore.kernel.org/r/20211102220203.940290-5-corbet@lwn.net Signed-off-by: Linus Walleij --- include/linux/sdb.h | 160 ---------------------------------------------------- 1 file changed, 160 deletions(-) delete mode 100644 include/linux/sdb.h (limited to 'include/linux') diff --git a/include/linux/sdb.h b/include/linux/sdb.h deleted file mode 100644 index a2404a2bbd10..000000000000 --- a/include/linux/sdb.h +++ /dev/null @@ -1,160 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * This is the official version 1.1 of sdb.h - */ -#ifndef __SDB_H__ -#define __SDB_H__ -#ifdef __KERNEL__ -#include -#else -#include -#endif - -/* - * All structures are 64 bytes long and are expected - * to live in an array, one for each interconnect. - * Most fields of the structures are shared among the - * various types, and most-specific fields are at the - * beginning (for alignment reasons, and to keep the - * magic number at the head of the interconnect record - */ - -/* Product, 40 bytes at offset 24, 8-byte aligned - * - * device_id is vendor-assigned; version is device-specific, - * date is hex (e.g 0x20120501), name is UTF-8, blank-filled - * and not terminated with a 0 byte. - */ -struct sdb_product { - uint64_t vendor_id; /* 0x18..0x1f */ - uint32_t device_id; /* 0x20..0x23 */ - uint32_t version; /* 0x24..0x27 */ - uint32_t date; /* 0x28..0x2b */ - uint8_t name[19]; /* 0x2c..0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* - * Component, 56 bytes at offset 8, 8-byte aligned - * - * The address range is first to last, inclusive - * (for example 0x100000 - 0x10ffff) - */ -struct sdb_component { - uint64_t addr_first; /* 0x08..0x0f */ - uint64_t addr_last; /* 0x10..0x17 */ - struct sdb_product product; /* 0x18..0x3f */ -}; - -/* Type of the SDB record */ -enum sdb_record_type { - sdb_type_interconnect = 0x00, - sdb_type_device = 0x01, - sdb_type_bridge = 0x02, - sdb_type_integration = 0x80, - sdb_type_repo_url = 0x81, - sdb_type_synthesis = 0x82, - sdb_type_empty = 0xFF, -}; - -/* Type 0: interconnect (first of the array) - * - * sdb_records is the length of the table including this first - * record, version is 1. The bus type is enumerated later. - */ -#define SDB_MAGIC 0x5344422d /* "SDB-" */ -struct sdb_interconnect { - uint32_t sdb_magic; /* 0x00-0x03 */ - uint16_t sdb_records; /* 0x04-0x05 */ - uint8_t sdb_version; /* 0x06 */ - uint8_t sdb_bus_type; /* 0x07 */ - struct sdb_component sdb_component; /* 0x08-0x3f */ -}; - -/* Type 1: device - * - * class is 0 for "custom device", other values are - * to be standardized; ABI version is for the driver, - * bus-specific bits are defined by each bus (see below) - */ -struct sdb_device { - uint16_t abi_class; /* 0x00-0x01 */ - uint8_t abi_ver_major; /* 0x02 */ - uint8_t abi_ver_minor; /* 0x03 */ - uint32_t bus_specific; /* 0x04-0x07 */ - struct sdb_component sdb_component; /* 0x08-0x3f */ -}; - -/* Type 2: bridge - * - * child is the address of the nested SDB table - */ -struct sdb_bridge { - uint64_t sdb_child; /* 0x00-0x07 */ - struct sdb_component sdb_component; /* 0x08-0x3f */ -}; - -/* Type 0x80: integration - * - * all types with bit 7 set are meta-information, so - * software can ignore the types it doesn't know. Here we - * just provide product information for an aggregate device - */ -struct sdb_integration { - uint8_t reserved[24]; /* 0x00-0x17 */ - struct sdb_product product; /* 0x08-0x3f */ -}; - -/* Type 0x81: Top module repository url - * - * again, an informative field that software can ignore - */ -struct sdb_repo_url { - uint8_t repo_url[63]; /* 0x00-0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* Type 0x82: Synthesis tool information - * - * this informative record - */ -struct sdb_synthesis { - uint8_t syn_name[16]; /* 0x00-0x0f */ - uint8_t commit_id[16]; /* 0x10-0x1f */ - uint8_t tool_name[8]; /* 0x20-0x27 */ - uint32_t tool_version; /* 0x28-0x2b */ - uint32_t date; /* 0x2c-0x2f */ - uint8_t user_name[15]; /* 0x30-0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* Type 0xff: empty - * - * this allows keeping empty slots during development, - * so they can be filled later with minimal efforts and - * no misleading description is ever shipped -- hopefully. - * It can also be used to pad a table to a desired length. - */ -struct sdb_empty { - uint8_t reserved[63]; /* 0x00-0x3e */ - uint8_t record_type; /* 0x3f */ -}; - -/* The type of bus, for bus-specific flags */ -enum sdb_bus_type { - sdb_wishbone = 0x00, - sdb_data = 0x01, -}; - -#define SDB_WB_WIDTH_MASK 0x0f -#define SDB_WB_ACCESS8 0x01 -#define SDB_WB_ACCESS16 0x02 -#define SDB_WB_ACCESS32 0x04 -#define SDB_WB_ACCESS64 0x08 -#define SDB_WB_LITTLE_ENDIAN 0x80 - -#define SDB_DATA_READ 0x04 -#define SDB_DATA_WRITE 0x02 -#define SDB_DATA_EXEC 0x01 - -#endif /* __SDB_H__ */ -- cgit v1.2.3 From 353050be4c19e102178ccc05988101887c25ae53 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 9 Nov 2021 18:48:08 +0000 Subject: bpf: Fix toctou on read-only map's constant scalar tracking Commit a23740ec43ba ("bpf: Track contents of read-only maps as scalars") is checking whether maps are read-only both from BPF program side and user space side, and then, given their content is constant, reading out their data via map->ops->map_direct_value_addr() which is then subsequently used as known scalar value for the register, that is, it is marked as __mark_reg_known() with the read value at verification time. Before a23740ec43ba, the register content was marked as an unknown scalar so the verifier could not make any assumptions about the map content. The current implementation however is prone to a TOCTOU race, meaning, the value read as known scalar for the register is not guaranteed to be exactly the same at a later point when the program is executed, and as such, the prior made assumptions of the verifier with regards to the program will be invalid which can cause issues such as OOB access, etc. While the BPF_F_RDONLY_PROG map flag is always fixed and required to be specified at map creation time, the map->frozen property is initially set to false for the map given the map value needs to be populated, e.g. for global data sections. Once complete, the loader "freezes" the map from user space such that no subsequent updates/deletes are possible anymore. For the rest of the lifetime of the map, this freeze one-time trigger cannot be undone anymore after a successful BPF_MAP_FREEZE cmd return. Meaning, any new BPF_* cmd calls which would update/delete map entries will be rejected with -EPERM since map_get_sys_perms() removes the FMODE_CAN_WRITE permission. This also means that pending update/delete map entries must still complete before this guarantee is given. This corner case is not an issue for loaders since they create and prepare such program private map in successive steps. However, a malicious user is able to trigger this TOCTOU race in two different ways: i) via userfaultfd, and ii) via batched updates. For i) userfaultfd is used to expand the competition interval, so that map_update_elem() can modify the contents of the map after map_freeze() and bpf_prog_load() were executed. This works, because userfaultfd halts the parallel thread which triggered a map_update_elem() at the time where we copy key/value from the user buffer and this already passed the FMODE_CAN_WRITE capability test given at that time the map was not "frozen". Then, the main thread performs the map_freeze() and bpf_prog_load(), and once that had completed successfully, the other thread is woken up to complete the pending map_update_elem() which then changes the map content. For ii) the idea of the batched update is similar, meaning, when there are a large number of updates to be processed, it can increase the competition interval between the two. It is therefore possible in practice to modify the contents of the map after executing map_freeze() and bpf_prog_load(). One way to fix both i) and ii) at the same time is to expand the use of the map's map->writecnt. The latter was introduced in fc9702273e2e ("bpf: Add mmap() support for BPF_MAP_TYPE_ARRAY") and further refined in 1f6cb19be2e2 ("bpf: Prevent re-mmap()'ing BPF map as writable for initially r/o mapping") with the rationale to make a writable mmap()'ing of a map mutually exclusive with read-only freezing. The counter indicates writable mmap() mappings and then prevents/fails the freeze operation. Its semantics can be expanded beyond just mmap() by generally indicating ongoing write phases. This would essentially span any parallel regular and batched flavor of update/delete operation and then also have map_freeze() fail with -EBUSY. For the check_mem_access() in the verifier we expand upon the bpf_map_is_rdonly() check ensuring that all last pending writes have completed via bpf_map_write_active() test. Once the map->frozen is set and bpf_map_write_active() indicates a map->writecnt of 0 only then we are really guaranteed to use the map's data as known constants. For map->frozen being set and pending writes in process of still being completed we fall back to marking that register as unknown scalar so we don't end up making assumptions about it. With this, both TOCTOU reproducers from i) and ii) are fixed. Note that the map->writecnt has been converted into a atomic64 in the fix in order to avoid a double freeze_mutex mutex_{un,}lock() pair when updating map->writecnt in the various map update/delete BPF_* cmd flavors. Spanning the freeze_mutex over entire map update/delete operations in syscall side would not be possible due to then causing everything to be serialized. Similarly, something like synchronize_rcu() after setting map->frozen to wait for update/deletes to complete is not possible either since it would also have to span the user copy which can sleep. On the libbpf side, this won't break d66562fba1ce ("libbpf: Add BPF object skeleton support") as the anonymous mmap()-ed "map initialization image" is remapped as a BPF map-backed mmap()-ed memory where for .rodata it's non-writable. Fixes: a23740ec43ba ("bpf: Track contents of read-only maps as scalars") Reported-by: w1tcher.bupt@gmail.com Signed-off-by: Daniel Borkmann Acked-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 ++- kernel/bpf/syscall.c | 57 ++++++++++++++++++++++++++++++++------------------- kernel/bpf/verifier.c | 17 ++++++++++++++- 3 files changed, 54 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f715e8863f4d..e7a163a3146b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,7 @@ struct bpf_map { atomic64_t usercnt; struct work_struct work; struct mutex freeze_mutex; - u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ + atomic64_t writecnt; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -1419,6 +1419,7 @@ void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); +bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 50f96ea4452a..1033ee8c0caf 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -132,6 +132,21 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } +static void bpf_map_write_active_inc(struct bpf_map *map) +{ + atomic64_inc(&map->writecnt); +} + +static void bpf_map_write_active_dec(struct bpf_map *map) +{ + atomic64_dec(&map->writecnt); +} + +bool bpf_map_write_active(const struct bpf_map *map) +{ + return atomic64_read(&map->writecnt) != 0; +} + static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -601,11 +616,8 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt++; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ @@ -613,11 +625,8 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; - if (vma->vm_flags & VM_MAYWRITE) { - mutex_lock(&map->freeze_mutex); - map->writecnt--; - mutex_unlock(&map->freeze_mutex); - } + if (vma->vm_flags & VM_MAYWRITE) + bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { @@ -668,7 +677,7 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) goto out; if (vma->vm_flags & VM_MAYWRITE) - map->writecnt++; + bpf_map_write_active_inc(map); out: mutex_unlock(&map->freeze_mutex); return err; @@ -1139,6 +1148,7 @@ static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1174,6 +1184,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1196,6 +1207,7 @@ static int map_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; @@ -1226,6 +1238,7 @@ static int map_delete_elem(union bpf_attr *attr) out: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1533,6 +1546,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); + bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; @@ -1597,6 +1611,7 @@ free_value: free_key: kvfree(key); err_put: + bpf_map_write_active_dec(map); fdput(f); return err; } @@ -1624,8 +1639,7 @@ static int map_freeze(const union bpf_attr *attr) } mutex_lock(&map->freeze_mutex); - - if (map->writecnt) { + if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } @@ -4171,6 +4185,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { + bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || + cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; + bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err, ufd; struct fd f; @@ -4183,16 +4200,13 @@ static int bpf_map_do_batch(const union bpf_attr *attr, map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - - if ((cmd == BPF_MAP_LOOKUP_BATCH || - cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) && - !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { + if (has_write) + bpf_map_write_active_inc(map); + if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } - - if (cmd != BPF_MAP_LOOKUP_BATCH && - !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { + if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } @@ -4205,8 +4219,9 @@ static int bpf_map_do_batch(const union bpf_attr *attr, BPF_DO_BATCH(map->ops->map_update_batch); else BPF_DO_BATCH(map->ops->map_delete_batch); - err_put: + if (has_write) + bpf_map_write_active_dec(map); fdput(f); return err; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65d2f93b7030..50efda51515b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4056,7 +4056,22 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) static bool bpf_map_is_rdonly(const struct bpf_map *map) { - return (map->map_flags & BPF_F_RDONLY_PROG) && map->frozen; + /* A map is considered read-only if the following condition are true: + * + * 1) BPF program side cannot change any of the map content. The + * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map + * and was set at map creation time. + * 2) The map value(s) have been initialized from user space by a + * loader and then "frozen", such that no new map update/delete + * operations from syscall side are possible for the rest of + * the map's lifetime from that point onwards. + * 3) Any parallel/pending map update/delete operations from syscall + * side have been completed. Only after that point, it's safe to + * assume that map value(s) are immutable. + */ + return (map->map_flags & BPF_F_RDONLY_PROG) && + READ_ONCE(map->frozen) && + !bpf_map_write_active(map); } static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val) -- cgit v1.2.3 From 0f0ac158d28ff78e75c334e869b1cb8e69372a1f Mon Sep 17 00:00:00 2001 From: "Luke D. Jones" Date: Sun, 24 Oct 2021 16:37:05 +1300 Subject: platform/x86: asus-wmi: Add support for custom fan curves Add support for custom fan curves found on some ASUS ROG laptops. These laptops have the ability to set a custom curve for the CPU and GPU fans via two ACPI methods. This patch adds two pwm attributes to the hwmon sysfs, pwm1 for CPU fan, pwm2 for GPU fan. Both are under the hwmon of the name `asus_custom_fan_curve`. There is no safety check of the set fan curves - this must be done in userspace. The fans have settings [1,2,3] under pwm_enable: 1. Enable and write settings out 2. Disable and use factory fan mode 3. Same as 2, additionally restoring default factory curve. Use of 2 means that the curve the user has set is still stored and won't be erased, but the laptop will be using its default auto-fan mode. Re-enabling the manual mode then activates the curves again. Notes: - pwm_enable = 0 is an invalid setting. - pwm is actually a percentage and is scaled on writing to device. Signed-off-by: Luke D. Jones Link: https://lore.kernel.org/r/20211024033705.5595-2-luke@ljones.dev Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/asus-wmi.c | 567 ++++++++++++++++++++++++++++- include/linux/platform_data/x86/asus-wmi.h | 2 + 2 files changed, 564 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 8f067ac4e952..ab0c087d40cf 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -106,8 +106,17 @@ module_param(fnlock_default, bool, 0444); #define WMI_EVENT_MASK 0xFFFF +#define FAN_CURVE_POINTS 8 +#define FAN_CURVE_BUF_LEN (FAN_CURVE_POINTS * 2) +#define FAN_CURVE_DEV_CPU 0x00 +#define FAN_CURVE_DEV_GPU 0x01 +/* Mask to determine if setting temperature or percentage */ +#define FAN_CURVE_PWM_MASK 0x04 + static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL }; +static int throttle_thermal_policy_write(struct asus_wmi *); + static bool ashs_present(void) { int i = 0; @@ -122,7 +131,8 @@ struct bios_args { u32 arg0; u32 arg1; u32 arg2; /* At least TUF Gaming series uses 3 dword input buffer. */ - u32 arg4; + u32 arg3; + u32 arg4; /* Some ROG laptops require a full 5 input args */ u32 arg5; } __packed; @@ -173,6 +183,13 @@ enum fan_type { FAN_TYPE_SPEC83, /* starting in Spec 8.3, use CPU_FAN_CTRL */ }; +struct fan_curve_data { + bool enabled; + u32 device_id; + u8 temps[FAN_CURVE_POINTS]; + u8 percents[FAN_CURVE_POINTS]; +}; + struct asus_wmi { int dsts_id; int spec; @@ -220,6 +237,10 @@ struct asus_wmi { bool throttle_thermal_policy_available; u8 throttle_thermal_policy_mode; + bool cpu_fan_curve_available; + bool gpu_fan_curve_available; + struct fan_curve_data custom_fan_curves[2]; + struct platform_profile_handler platform_profile_handler; bool platform_profile_support; @@ -285,6 +306,103 @@ int asus_wmi_evaluate_method(u32 method_id, u32 arg0, u32 arg1, u32 *retval) } EXPORT_SYMBOL_GPL(asus_wmi_evaluate_method); +static int asus_wmi_evaluate_method5(u32 method_id, + u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4, u32 *retval) +{ + struct bios_args args = { + .arg0 = arg0, + .arg1 = arg1, + .arg2 = arg2, + .arg3 = arg3, + .arg4 = arg4, + }; + struct acpi_buffer input = { (acpi_size) sizeof(args), &args }; + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_status status; + union acpi_object *obj; + u32 tmp = 0; + + status = wmi_evaluate_method(ASUS_WMI_MGMT_GUID, 0, method_id, + &input, &output); + + if (ACPI_FAILURE(status)) + return -EIO; + + obj = (union acpi_object *)output.pointer; + if (obj && obj->type == ACPI_TYPE_INTEGER) + tmp = (u32) obj->integer.value; + + if (retval) + *retval = tmp; + + kfree(obj); + + if (tmp == ASUS_WMI_UNSUPPORTED_METHOD) + return -ENODEV; + + return 0; +} + +/* + * Returns as an error if the method output is not a buffer. Typically this + * means that the method called is unsupported. + */ +static int asus_wmi_evaluate_method_buf(u32 method_id, + u32 arg0, u32 arg1, u8 *ret_buffer, size_t size) +{ + struct bios_args args = { + .arg0 = arg0, + .arg1 = arg1, + .arg2 = 0, + }; + struct acpi_buffer input = { (acpi_size) sizeof(args), &args }; + struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL }; + acpi_status status; + union acpi_object *obj; + int err = 0; + + status = wmi_evaluate_method(ASUS_WMI_MGMT_GUID, 0, method_id, + &input, &output); + + if (ACPI_FAILURE(status)) + return -EIO; + + obj = (union acpi_object *)output.pointer; + + switch (obj->type) { + case ACPI_TYPE_BUFFER: + if (obj->buffer.length > size) + err = -ENOSPC; + if (obj->buffer.length == 0) + err = -ENODATA; + + memcpy(ret_buffer, obj->buffer.pointer, obj->buffer.length); + break; + case ACPI_TYPE_INTEGER: + err = (u32)obj->integer.value; + + if (err == ASUS_WMI_UNSUPPORTED_METHOD) + err = -ENODEV; + /* + * At least one method returns a 0 with no buffer if no arg + * is provided, such as ASUS_WMI_DEVID_CPU_FAN_CURVE + */ + if (err == 0) + err = -ENODATA; + break; + default: + err = -ENODATA; + break; + } + + kfree(obj); + + if (err) + return err; + + return 0; +} + static int asus_wmi_evaluate_method_agfn(const struct acpi_buffer args) { struct acpi_buffer input; @@ -1806,6 +1924,13 @@ static ssize_t pwm1_enable_store(struct device *dev, } asus->fan_pwm_mode = state; + + /* Must set to disabled if mode is toggled */ + if (asus->cpu_fan_curve_available) + asus->custom_fan_curves[FAN_CURVE_DEV_CPU].enabled = false; + if (asus->gpu_fan_curve_available) + asus->custom_fan_curves[FAN_CURVE_DEV_GPU].enabled = false; + return count; } @@ -1953,9 +2078,9 @@ static int fan_boost_mode_check_present(struct asus_wmi *asus) static int fan_boost_mode_write(struct asus_wmi *asus) { - int err; - u8 value; u32 retval; + u8 value; + int err; value = asus->fan_boost_mode; @@ -2013,10 +2138,10 @@ static ssize_t fan_boost_mode_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - int result; - u8 new_mode; struct asus_wmi *asus = dev_get_drvdata(dev); u8 mask = asus->fan_boost_mode_mask; + u8 new_mode; + int result; result = kstrtou8(buf, 10, &new_mode); if (result < 0) { @@ -2043,6 +2168,426 @@ static ssize_t fan_boost_mode_store(struct device *dev, // Fan boost mode: 0 - normal, 1 - overboost, 2 - silent static DEVICE_ATTR_RW(fan_boost_mode); +/* Custom fan curves **********************************************************/ + +static void fan_curve_copy_from_buf(struct fan_curve_data *data, u8 *buf) +{ + int i; + + for (i = 0; i < FAN_CURVE_POINTS; i++) { + data->temps[i] = buf[i]; + } + + for (i = 0; i < FAN_CURVE_POINTS; i++) { + data->percents[i] = + 255 * buf[i + FAN_CURVE_POINTS] / 100; + } +} + +static int fan_curve_get_factory_default(struct asus_wmi *asus, u32 fan_dev) +{ + struct fan_curve_data *curves; + u8 buf[FAN_CURVE_BUF_LEN]; + int fan_idx = 0; + u8 mode = 0; + int err; + + if (asus->throttle_thermal_policy_available) + mode = asus->throttle_thermal_policy_mode; + /* DEVID_PU_FAN_CURVE is switched for OVERBOOST vs SILENT */ + if (mode == 2) + mode = 1; + else if (mode == 1) + mode = 2; + + if (fan_dev == ASUS_WMI_DEVID_GPU_FAN_CURVE) + fan_idx = FAN_CURVE_DEV_GPU; + + curves = &asus->custom_fan_curves[fan_idx]; + err = asus_wmi_evaluate_method_buf(asus->dsts_id, fan_dev, mode, buf, + FAN_CURVE_BUF_LEN); + if (err) + return err; + + fan_curve_copy_from_buf(curves, buf); + curves->device_id = fan_dev; + + return 0; +} + +/* Check if capability exists, and populate defaults */ +static int fan_curve_check_present(struct asus_wmi *asus, bool *available, + u32 fan_dev) +{ + int err; + + *available = false; + + err = fan_curve_get_factory_default(asus, fan_dev); + if (err) { + if (err == -ENODEV) + return 0; + return err; + } + + *available = true; + return 0; +} + +/* Determine which fan the attribute is for if SENSOR_ATTR */ +static struct fan_curve_data *fan_curve_attr_select(struct asus_wmi *asus, + struct device_attribute *attr) +{ + int index = to_sensor_dev_attr(attr)->index; + + return &asus->custom_fan_curves[index & FAN_CURVE_DEV_GPU]; +} + +/* Determine which fan the attribute is for if SENSOR_ATTR_2 */ +static struct fan_curve_data *fan_curve_attr_2_select(struct asus_wmi *asus, + struct device_attribute *attr) +{ + int nr = to_sensor_dev_attr_2(attr)->nr; + + return &asus->custom_fan_curves[nr & FAN_CURVE_DEV_GPU]; +} + +static ssize_t fan_curve_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct sensor_device_attribute_2 *dev_attr = to_sensor_dev_attr_2(attr); + struct asus_wmi *asus = dev_get_drvdata(dev); + struct fan_curve_data *data; + int value, index, nr; + + data = fan_curve_attr_2_select(asus, attr); + index = dev_attr->index; + nr = dev_attr->nr; + + if (nr & FAN_CURVE_PWM_MASK) + value = data->percents[index]; + else + value = data->temps[index]; + + return sysfs_emit(buf, "%d\n", value); +} + +/* + * "fan_dev" is the related WMI method such as ASUS_WMI_DEVID_CPU_FAN_CURVE. + */ +static int fan_curve_write(struct asus_wmi *asus, + struct fan_curve_data *data) +{ + u32 arg1 = 0, arg2 = 0, arg3 = 0, arg4 = 0; + u8 *percents = data->percents; + u8 *temps = data->temps; + int ret, i, shift = 0; + + if (!data->enabled) + return 0; + + for (i = 0; i < FAN_CURVE_POINTS / 2; i++) { + arg1 += (temps[i]) << shift; + arg2 += (temps[i + 4]) << shift; + /* Scale to percentage for device */ + arg3 += (100 * percents[i] / 255) << shift; + arg4 += (100 * percents[i + 4] / 255) << shift; + shift += 8; + } + + return asus_wmi_evaluate_method5(ASUS_WMI_METHODID_DEVS, + data->device_id, + arg1, arg2, arg3, arg4, &ret); +} + +static ssize_t fan_curve_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct sensor_device_attribute_2 *dev_attr = to_sensor_dev_attr_2(attr); + struct asus_wmi *asus = dev_get_drvdata(dev); + struct fan_curve_data *data; + u8 value; + int err; + + int pwm = dev_attr->nr & FAN_CURVE_PWM_MASK; + int index = dev_attr->index; + + data = fan_curve_attr_2_select(asus, attr); + + err = kstrtou8(buf, 10, &value); + if (err < 0) + return err; + + if (pwm) { + data->percents[index] = value; + } else { + data->temps[index] = value; + } + + /* + * Mark as disabled so the user has to explicitly enable to apply a + * changed fan curve. This prevents potential lockups from writing out + * many changes as one-write-per-change. + */ + data->enabled = false; + + return count; +} + +static ssize_t fan_curve_enable_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct asus_wmi *asus = dev_get_drvdata(dev); + struct fan_curve_data *data; + int out = 2; + + data = fan_curve_attr_select(asus, attr); + + if (data->enabled) + out = 1; + + return sysfs_emit(buf, "%d\n", out); +} + +static ssize_t fan_curve_enable_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct asus_wmi *asus = dev_get_drvdata(dev); + struct fan_curve_data *data; + int value, err; + + data = fan_curve_attr_select(asus, attr); + + err = kstrtoint(buf, 10, &value); + if (err < 0) + return err; + + switch (value) { + case 1: + data->enabled = true; + break; + case 2: + data->enabled = false; + break; + /* + * Auto + reset the fan curve data to defaults. Make it an explicit + * option so that users don't accidentally overwrite a set fan curve. + */ + case 3: + err = fan_curve_get_factory_default(asus, data->device_id); + if (err) + return err; + data->enabled = false; + break; + default: + return -EINVAL; + }; + + if (data->enabled) { + err = fan_curve_write(asus, data); + if (err) + return err; + } else { + /* + * For machines with throttle this is the only way to reset fans + * to default mode of operation (does not erase curve data). + */ + if (asus->throttle_thermal_policy_available) { + err = throttle_thermal_policy_write(asus); + if (err) + return err; + /* Similar is true for laptops with this fan */ + } else if (asus->fan_type == FAN_TYPE_SPEC83) { + err = asus_fan_set_auto(asus); + if (err) + return err; + } else { + /* Safeguard against fautly ACPI tables */ + err = fan_curve_get_factory_default(asus, data->device_id); + if (err) + return err; + err = fan_curve_write(asus, data); + if (err) + return err; + } + } + return count; +} + +/* CPU */ +static SENSOR_DEVICE_ATTR_RW(pwm1_enable, fan_curve_enable, FAN_CURVE_DEV_CPU); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point1_temp, fan_curve, + FAN_CURVE_DEV_CPU, 0); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point2_temp, fan_curve, + FAN_CURVE_DEV_CPU, 1); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point3_temp, fan_curve, + FAN_CURVE_DEV_CPU, 2); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point4_temp, fan_curve, + FAN_CURVE_DEV_CPU, 3); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point5_temp, fan_curve, + FAN_CURVE_DEV_CPU, 4); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point6_temp, fan_curve, + FAN_CURVE_DEV_CPU, 5); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point7_temp, fan_curve, + FAN_CURVE_DEV_CPU, 6); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point8_temp, fan_curve, + FAN_CURVE_DEV_CPU, 7); + +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point1_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 0); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point2_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 1); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point3_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 2); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point4_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 3); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point5_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 4); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point6_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 5); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point7_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 6); +static SENSOR_DEVICE_ATTR_2_RW(pwm1_auto_point8_pwm, fan_curve, + FAN_CURVE_DEV_CPU | FAN_CURVE_PWM_MASK, 7); + +/* GPU */ +static SENSOR_DEVICE_ATTR_RW(pwm2_enable, fan_curve_enable, FAN_CURVE_DEV_GPU); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point1_temp, fan_curve, + FAN_CURVE_DEV_GPU, 0); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point2_temp, fan_curve, + FAN_CURVE_DEV_GPU, 1); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point3_temp, fan_curve, + FAN_CURVE_DEV_GPU, 2); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point4_temp, fan_curve, + FAN_CURVE_DEV_GPU, 3); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point5_temp, fan_curve, + FAN_CURVE_DEV_GPU, 4); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point6_temp, fan_curve, + FAN_CURVE_DEV_GPU, 5); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point7_temp, fan_curve, + FAN_CURVE_DEV_GPU, 6); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point8_temp, fan_curve, + FAN_CURVE_DEV_GPU, 7); + +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point1_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 0); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point2_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 1); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point3_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 2); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point4_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 3); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point5_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 4); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point6_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 5); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point7_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 6); +static SENSOR_DEVICE_ATTR_2_RW(pwm2_auto_point8_pwm, fan_curve, + FAN_CURVE_DEV_GPU | FAN_CURVE_PWM_MASK, 7); + +static struct attribute *asus_fan_curve_attr[] = { + /* CPU */ + &sensor_dev_attr_pwm1_enable.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point1_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point2_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point3_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point4_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point5_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point6_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point7_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point8_temp.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point1_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point2_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point3_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point4_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point5_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point6_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point7_pwm.dev_attr.attr, + &sensor_dev_attr_pwm1_auto_point8_pwm.dev_attr.attr, + /* GPU */ + &sensor_dev_attr_pwm2_enable.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point1_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point2_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point3_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point4_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point5_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point6_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point7_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point8_temp.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point1_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point2_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point3_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point4_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point5_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point6_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point7_pwm.dev_attr.attr, + &sensor_dev_attr_pwm2_auto_point8_pwm.dev_attr.attr, + NULL +}; + +static umode_t asus_fan_curve_is_visible(struct kobject *kobj, + struct attribute *attr, int idx) +{ + struct device *dev = container_of(kobj, struct device, kobj); + struct asus_wmi *asus = dev_get_drvdata(dev->parent); + + /* + * Check the char instead of casting attr as there are two attr types + * involved here (attr1 and attr2) + */ + if (asus->cpu_fan_curve_available && attr->name[3] == '1') + return 0644; + + if (asus->gpu_fan_curve_available && attr->name[3] == '2') + return 0644; + + return 0; +} + +static const struct attribute_group asus_fan_curve_attr_group = { + .is_visible = asus_fan_curve_is_visible, + .attrs = asus_fan_curve_attr, +}; +__ATTRIBUTE_GROUPS(asus_fan_curve_attr); + +/* + * Must be initialised after throttle_thermal_policy_check_present() as + * we check the status of throttle_thermal_policy_available during init. + */ +static int asus_wmi_custom_fan_curve_init(struct asus_wmi *asus) +{ + struct device *dev = &asus->platform_device->dev; + struct device *hwmon; + int err; + + err = fan_curve_check_present(asus, &asus->cpu_fan_curve_available, + ASUS_WMI_DEVID_CPU_FAN_CURVE); + if (err) + return err; + + err = fan_curve_check_present(asus, &asus->gpu_fan_curve_available, + ASUS_WMI_DEVID_GPU_FAN_CURVE); + if (err) + return err; + + if (!asus->cpu_fan_curve_available && !asus->gpu_fan_curve_available) + return 0; + + hwmon = devm_hwmon_device_register_with_groups( + dev, "asus_custom_fan_curve", asus, asus_fan_curve_attr_groups); + + if (IS_ERR(hwmon)) { + dev_err(dev, + "Could not register asus_custom_fan_curve device\n"); + return PTR_ERR(hwmon); + } + + return 0; +} + /* Throttle thermal policy ****************************************************/ static int throttle_thermal_policy_check_present(struct asus_wmi *asus) @@ -2092,6 +2637,12 @@ static int throttle_thermal_policy_write(struct asus_wmi *asus) return -EIO; } + /* Must set to disabled if mode is toggled */ + if (asus->cpu_fan_curve_available) + asus->custom_fan_curves[FAN_CURVE_DEV_CPU].enabled = false; + if (asus->gpu_fan_curve_available) + asus->custom_fan_curves[FAN_CURVE_DEV_GPU].enabled = false; + return 0; } @@ -3035,6 +3586,10 @@ static int asus_wmi_add(struct platform_device *pdev) if (err) goto fail_hwmon; + err = asus_wmi_custom_fan_curve_init(asus); + if (err) + goto fail_custom_fan_curve; + err = asus_wmi_led_init(asus); if (err) goto fail_leds; @@ -3106,6 +3661,7 @@ fail_input: asus_wmi_sysfs_exit(asus->platform_device); fail_sysfs: fail_throttle_thermal_policy: +fail_custom_fan_curve: fail_platform_profile_setup: if (asus->platform_profile_support) platform_profile_remove(); @@ -3131,6 +3687,7 @@ static int asus_wmi_remove(struct platform_device *device) asus_wmi_debugfs_exit(asus); asus_wmi_sysfs_exit(asus->platform_device); asus_fan_set_auto(asus); + throttle_thermal_policy_set_default(asus); asus_wmi_battery_exit(asus); if (asus->platform_profile_support) diff --git a/include/linux/platform_data/x86/asus-wmi.h b/include/linux/platform_data/x86/asus-wmi.h index 17dc5cb6f3f2..a571b47ff362 100644 --- a/include/linux/platform_data/x86/asus-wmi.h +++ b/include/linux/platform_data/x86/asus-wmi.h @@ -77,6 +77,8 @@ #define ASUS_WMI_DEVID_THERMAL_CTRL 0x00110011 #define ASUS_WMI_DEVID_FAN_CTRL 0x00110012 /* deprecated */ #define ASUS_WMI_DEVID_CPU_FAN_CTRL 0x00110013 +#define ASUS_WMI_DEVID_CPU_FAN_CURVE 0x00110024 +#define ASUS_WMI_DEVID_GPU_FAN_CURVE 0x00110025 /* Power */ #define ASUS_WMI_DEVID_PROCESSOR_STATE 0x00120012 -- cgit v1.2.3 From 38543b72fbe52b7eec0dedd420d80a06c652d8e4 Mon Sep 17 00:00:00 2001 From: Maximilian Luz Date: Thu, 28 Oct 2021 02:22:41 +0200 Subject: platform/surface: aggregator: Make client device removal more generic Currently, there are similar functions defined in the Aggregator Registry and the controller core. Make client device removal more generic and export it. We can then use this function later on to remove client devices from device hubs as well as the controller and avoid re-defining similar things. Signed-off-by: Maximilian Luz Link: https://lore.kernel.org/r/20211028002243.1586083-2-luzmaximilian@gmail.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/surface/aggregator/bus.c | 24 ++++++++---------------- drivers/platform/surface/aggregator/bus.h | 3 --- drivers/platform/surface/aggregator/core.c | 3 ++- include/linux/surface_aggregator/device.h | 9 +++++++++ 4 files changed, 19 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/surface/aggregator/bus.c b/drivers/platform/surface/aggregator/bus.c index 0a40dd9c94ed..abbbb5b08b07 100644 --- a/drivers/platform/surface/aggregator/bus.c +++ b/drivers/platform/surface/aggregator/bus.c @@ -374,27 +374,19 @@ static int ssam_remove_device(struct device *dev, void *_data) } /** - * ssam_controller_remove_clients() - Remove SSAM client devices registered as - * direct children under the given controller. - * @ctrl: The controller to remove all direct clients for. + * ssam_remove_clients() - Remove SSAM client devices registered as direct + * children under the given parent device. + * @dev: The (parent) device to remove all direct clients for. * - * Remove all SSAM client devices registered as direct children under the - * given controller. Note that this only accounts for direct children of the - * controller device. This does not take care of any client devices where the - * parent device has been manually set before calling ssam_device_add. Refer - * to ssam_device_add()/ssam_device_remove() for more details on those cases. - * - * To avoid new devices being added in parallel to this call, the main - * controller lock (not statelock) must be held during this (and if - * necessary, any subsequent deinitialization) call. + * Remove all SSAM client devices registered as direct children under the given + * device. Note that this only accounts for direct children of the device. + * Refer to ssam_device_add()/ssam_device_remove() for more details. */ -void ssam_controller_remove_clients(struct ssam_controller *ctrl) +void ssam_remove_clients(struct device *dev) { - struct device *dev; - - dev = ssam_controller_device(ctrl); device_for_each_child_reverse(dev, NULL, ssam_remove_device); } +EXPORT_SYMBOL_GPL(ssam_remove_clients); /** * ssam_bus_register() - Register and set-up the SSAM client device bus. diff --git a/drivers/platform/surface/aggregator/bus.h b/drivers/platform/surface/aggregator/bus.h index ed032c2cbdb2..6964ee84e79c 100644 --- a/drivers/platform/surface/aggregator/bus.h +++ b/drivers/platform/surface/aggregator/bus.h @@ -12,14 +12,11 @@ #ifdef CONFIG_SURFACE_AGGREGATOR_BUS -void ssam_controller_remove_clients(struct ssam_controller *ctrl); - int ssam_bus_register(void); void ssam_bus_unregister(void); #else /* CONFIG_SURFACE_AGGREGATOR_BUS */ -static inline void ssam_controller_remove_clients(struct ssam_controller *ctrl) {} static inline int ssam_bus_register(void) { return 0; } static inline void ssam_bus_unregister(void) {} diff --git a/drivers/platform/surface/aggregator/core.c b/drivers/platform/surface/aggregator/core.c index c61bbeeec2df..d384d36098c2 100644 --- a/drivers/platform/surface/aggregator/core.c +++ b/drivers/platform/surface/aggregator/core.c @@ -22,6 +22,7 @@ #include #include +#include #include "bus.h" #include "controller.h" @@ -735,7 +736,7 @@ static void ssam_serial_hub_remove(struct serdev_device *serdev) ssam_controller_lock(ctrl); /* Remove all client devices. */ - ssam_controller_remove_clients(ctrl); + ssam_remove_clients(&serdev->dev); /* Act as if suspending to silence events. */ status = ssam_ctrl_notif_display_off(ctrl); diff --git a/include/linux/surface_aggregator/device.h b/include/linux/surface_aggregator/device.h index f636c5310321..cc257097eb05 100644 --- a/include/linux/surface_aggregator/device.h +++ b/include/linux/surface_aggregator/device.h @@ -319,6 +319,15 @@ void ssam_device_driver_unregister(struct ssam_device_driver *d); ssam_device_driver_unregister) +/* -- Helpers for controller and hub devices. ------------------------------- */ + +#ifdef CONFIG_SURFACE_AGGREGATOR_BUS +void ssam_remove_clients(struct device *dev); +#else /* CONFIG_SURFACE_AGGREGATOR_BUS */ +static inline void ssam_remove_clients(struct device *dev) {} +#endif /* CONFIG_SURFACE_AGGREGATOR_BUS */ + + /* -- Helpers for client-device requests. ----------------------------------- */ /** -- cgit v1.2.3 From ebf7f6f0a6cdcc17a3da52b81e4b3a98c4005028 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Fri, 5 Nov 2021 09:30:00 +0800 Subject: bpf: Change value of MAX_TAIL_CALL_CNT from 32 to 33 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the current code, the actual max tail call count is 33 which is greater than MAX_TAIL_CALL_CNT (defined as 32). The actual limit is not consistent with the meaning of MAX_TAIL_CALL_CNT and thus confusing at first glance. We can see the historical evolution from commit 04fd61ab36ec ("bpf: allow bpf programs to tail-call other bpf programs") and commit f9dabe016b63 ("bpf: Undo off-by-one in interpreter tail call count limit"). In order to avoid changing existing behavior, the actual limit is 33 now, this is reasonable. After commit 874be05f525e ("bpf, tests: Add tail call test suite"), we can see there exists failed testcase. On all archs when CONFIG_BPF_JIT_ALWAYS_ON is not set: # echo 0 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf # dmesg | grep -w FAIL Tail call error path, max count reached jited:0 ret 34 != 33 FAIL On some archs: # echo 1 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf # dmesg | grep -w FAIL Tail call error path, max count reached jited:1 ret 34 != 33 FAIL Although the above failed testcase has been fixed in commit 18935a72eb25 ("bpf/tests: Fix error in tail call limit tests"), it would still be good to change the value of MAX_TAIL_CALL_CNT from 32 to 33 to make the code more readable. The 32-bit x86 JIT was using a limit of 32, just fix the wrong comments and limit to 33 tail calls as the constant MAX_TAIL_CALL_CNT updated. For the mips64 JIT, use "ori" instead of "addiu" as suggested by Johan Almbladh. For the riscv JIT, use RV_REG_TCC directly to save one register move as suggested by Björn Töpel. For the other implementations, no function changes, it does not change the current limit 33, the new value of MAX_TAIL_CALL_CNT can reflect the actual max tail call count, the related tail call testcases in test_bpf module and selftests can work well for the interpreter and the JIT. Here are the test results on x86_64: # uname -m x86_64 # echo 0 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf test_suite=test_tail_calls # dmesg | tail -1 test_bpf: test_tail_calls: Summary: 8 PASSED, 0 FAILED, [0/8 JIT'ed] # rmmod test_bpf # echo 1 > /proc/sys/net/core/bpf_jit_enable # modprobe test_bpf test_suite=test_tail_calls # dmesg | tail -1 test_bpf: test_tail_calls: Summary: 8 PASSED, 0 FAILED, [8/8 JIT'ed] # rmmod test_bpf # ./test_progs -t tailcalls #142 tailcalls:OK Summary: 1/11 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Tiezhu Yang Signed-off-by: Daniel Borkmann Tested-by: Johan Almbladh Tested-by: Ilya Leoshkevich Acked-by: Björn Töpel Acked-by: Johan Almbladh Acked-by: Ilya Leoshkevich Link: https://lore.kernel.org/bpf/1636075800-3264-1-git-send-email-yangtiezhu@loongson.cn --- arch/arm/net/bpf_jit_32.c | 5 +++-- arch/arm64/net/bpf_jit_comp.c | 5 +++-- arch/mips/net/bpf_jit_comp32.c | 3 +-- arch/mips/net/bpf_jit_comp64.c | 2 +- arch/powerpc/net/bpf_jit_comp32.c | 4 ++-- arch/powerpc/net/bpf_jit_comp64.c | 4 ++-- arch/riscv/net/bpf_jit_comp32.c | 6 ++---- arch/riscv/net/bpf_jit_comp64.c | 7 +++---- arch/s390/net/bpf_jit_comp.c | 6 +++--- arch/sparc/net/bpf_jit_comp_64.c | 2 +- arch/x86/net/bpf_jit_comp.c | 10 +++++----- arch/x86/net/bpf_jit_comp32.c | 4 ++-- include/linux/bpf.h | 2 +- include/uapi/linux/bpf.h | 2 +- kernel/bpf/core.c | 3 ++- lib/test_bpf.c | 4 ++-- tools/include/uapi/linux/bpf.h | 2 +- 17 files changed, 35 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index eeb6dc0ecf46..e59b41e9ab0c 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1199,7 +1199,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) /* tmp2[0] = array, tmp2[1] = index */ - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + /* + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ @@ -1208,7 +1209,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) tc = arm_bpf_get_reg64(tcc, tmp, ctx); emit(ARM_CMP_I(tc[0], hi), ctx); _emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx); - _emit(ARM_COND_HI, ARM_B(jmp_offset), ctx); + _emit(ARM_COND_CS, ARM_B(jmp_offset), ctx); emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx); emit(ARM_ADC_I(tc[0], tc[0], 0), ctx); arm_bpf_put_reg64(tcc, tmp, ctx); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 86c9dc0681cc..07c12c42b751 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -287,13 +287,14 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx) emit(A64_CMP(0, r3, tmp), ctx); emit(A64_B_(A64_COND_CS, jmp_offset), ctx); - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) + /* + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; * tail_call_cnt++; */ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx); emit(A64_CMP(1, tcc, tmp), ctx); - emit(A64_B_(A64_COND_HI, jmp_offset), ctx); + emit(A64_B_(A64_COND_CS, jmp_offset), ctx); emit(A64_ADD_I(1, tcc, tcc, 1), ctx); /* prog = array->ptrs[index]; diff --git a/arch/mips/net/bpf_jit_comp32.c b/arch/mips/net/bpf_jit_comp32.c index bd996ede12f8..044b11b65bca 100644 --- a/arch/mips/net/bpf_jit_comp32.c +++ b/arch/mips/net/bpf_jit_comp32.c @@ -1381,8 +1381,7 @@ void build_prologue(struct jit_context *ctx) * 16-byte area in the parent's stack frame. On a tail call, the * calling function jumps into the prologue after these instructions. */ - emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, - min(MAX_TAIL_CALL_CNT + 1, 0xffff)); + emit(ctx, ori, MIPS_R_T9, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff)); emit(ctx, sw, MIPS_R_T9, 0, MIPS_R_SP); /* diff --git a/arch/mips/net/bpf_jit_comp64.c b/arch/mips/net/bpf_jit_comp64.c index 815ade724227..6475828ffb36 100644 --- a/arch/mips/net/bpf_jit_comp64.c +++ b/arch/mips/net/bpf_jit_comp64.c @@ -552,7 +552,7 @@ void build_prologue(struct jit_context *ctx) * On a tail call, the calling function jumps into the prologue * after this instruction. */ - emit(ctx, addiu, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT + 1, 0xffff)); + emit(ctx, ori, tc, MIPS_R_ZERO, min(MAX_TAIL_CALL_CNT, 0xffff)); /* === Entry-point for tail calls === */ diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c index 0da31d41d413..8a4faa05f9e4 100644 --- a/arch/powerpc/net/bpf_jit_comp32.c +++ b/arch/powerpc/net/bpf_jit_comp32.c @@ -221,13 +221,13 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC(COND_GE, out); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT(PPC_RAW_CMPLWI(_R0, MAX_TAIL_CALL_CNT)); /* tail_call_cnt++; */ EMIT(PPC_RAW_ADDIC(_R0, _R0, 1)); - PPC_BCC(COND_GT, out); + PPC_BCC(COND_GE, out); /* prog = array->ptrs[index]; */ EMIT(PPC_RAW_RLWINM(_R3, b2p_index, 2, 0, 29)); diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 8b5157ccfeba..8571aafcc9e1 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -228,12 +228,12 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o PPC_BCC(COND_GE, out); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt >= MAX_TAIL_CALL_CNT) * goto out; */ PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx)); EMIT(PPC_RAW_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT)); - PPC_BCC(COND_GT, out); + PPC_BCC(COND_GE, out); /* * tail_call_cnt++; diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c index e6497424cbf6..529a83b85c1c 100644 --- a/arch/riscv/net/bpf_jit_comp32.c +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -799,11 +799,10 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); /* - * temp_tcc = tcc - 1; - * if (tcc < 0) + * if (--tcc < 0) * goto out; */ - emit(rv_addi(RV_REG_T1, RV_REG_TCC, -1), ctx); + emit(rv_addi(RV_REG_TCC, RV_REG_TCC, -1), ctx); off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); @@ -829,7 +828,6 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) if (is_12b_check(off, insn)) return -1; emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); - emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx); /* Epilogue jumps to *(t0 + 4). */ __build_epilogue(true, ctx); return 0; diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index f2a779c7e225..603630b6f3c5 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -327,12 +327,12 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); emit_branch(BPF_JGE, RV_REG_A2, RV_REG_T1, off, ctx); - /* if (TCC-- < 0) + /* if (--TCC < 0) * goto out; */ - emit_addi(RV_REG_T1, tcc, -1, ctx); + emit_addi(RV_REG_TCC, tcc, -1, ctx); off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); - emit_branch(BPF_JSLT, tcc, RV_REG_ZERO, off, ctx); + emit_branch(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); /* prog = array->ptrs[index]; * if (!prog) @@ -352,7 +352,6 @@ static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) if (is_12b_check(off, insn)) return -1; emit_ld(RV_REG_T3, off, RV_REG_T2, ctx); - emit_mv(RV_REG_TCC, RV_REG_T1, ctx); __build_epilogue(true, ctx); return 0; } diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 233cc9bcd652..9ff2bd83aad7 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1369,7 +1369,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, jit->prg); /* - * if (tail_call_cnt++ > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ @@ -1381,9 +1381,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, EMIT4_IMM(0xa7080000, REG_W0, 1); /* laal %w1,%w0,off(%r15) */ EMIT6_DISP_LH(0xeb000000, 0x00fa, REG_W1, REG_W0, REG_15, off); - /* clij %w1,MAX_TAIL_CALL_CNT,0x2,out */ + /* clij %w1,MAX_TAIL_CALL_CNT-1,0x2,out */ patch_2_clij = jit->prg; - EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT, + EMIT6_PCREL_RIEC(0xec000000, 0x007f, REG_W1, MAX_TAIL_CALL_CNT - 1, 2, jit->prg); /* diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 9a2f20cbd48b..0bfe1c72a0c9 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -867,7 +867,7 @@ static void emit_tail_call(struct jit_ctx *ctx) emit(LD32 | IMMED | RS1(SP) | S13(off) | RD(tmp), ctx); emit_cmpi(tmp, MAX_TAIL_CALL_CNT, ctx); #define OFFSET2 13 - emit_branch(BGU, ctx->idx, ctx->idx + OFFSET2, ctx); + emit_branch(BGEU, ctx->idx, ctx->idx + OFFSET2, ctx); emit_nop(ctx); emit_alu_K(ADD, tmp, 1, ctx); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 726700fabca6..631847907786 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -412,7 +412,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... * if (index >= array->map.max_entries) * goto out; - * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; * prog = array->ptrs[index]; * if (prog == NULL) @@ -446,14 +446,14 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, EMIT2(X86_JBE, offset); /* jbe out */ /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_indirect_label - (prog + 2 - start); - EMIT2(X86_JA, offset); /* ja out */ + EMIT2(X86_JAE, offset); /* jae out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ @@ -504,14 +504,14 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, int offset; /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ offset = ctx->tail_call_direct_label - (prog + 2 - start); - EMIT2(X86_JA, offset); /* ja out */ + EMIT2(X86_JAE, offset); /* jae out */ EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */ diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index da9b7cfa4632..429a89c5468b 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1323,7 +1323,7 @@ static void emit_bpf_tail_call(u8 **pprog, u8 *ip) EMIT2(IA32_JBE, jmp_label(jmp_label1, 2)); /* - * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT) * goto out; */ lo = (u32)MAX_TAIL_CALL_CNT; @@ -1337,7 +1337,7 @@ static void emit_bpf_tail_call(u8 **pprog, u8 *ip) /* cmp ecx,lo */ EMIT3(0x83, add_1reg(0xF8, IA32_ECX), lo); - /* ja out */ + /* jae out */ EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); /* add eax,0x1 */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 56098c866704..cc7a0c36e7df 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1081,7 +1081,7 @@ struct bpf_array { }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ -#define MAX_TAIL_CALL_CNT 32 +#define MAX_TAIL_CALL_CNT 33 #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6297eafdc40f..a69e4b04ffeb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1744,7 +1744,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2405e39d800f..b52dc845ecea 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1574,7 +1574,8 @@ select_insn: if (unlikely(index >= array->map.max_entries)) goto out; - if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT)) + + if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT)) goto out; tail_call_cnt++; diff --git a/lib/test_bpf.c b/lib/test_bpf.c index adae39567264..0c5cb2d6436a 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -14683,7 +14683,7 @@ static struct tail_call_test tail_call_tests[] = { BPF_EXIT_INSN(), }, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, - .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, }, { "Tail call count preserved across function calls", @@ -14705,7 +14705,7 @@ static struct tail_call_test tail_call_tests[] = { }, .stack_depth = 8, .flags = FLAG_NEED_STATE | FLAG_RESULT_IN_STATE, - .result = (MAX_TAIL_CALL_CNT + 1 + 1) * MAX_TESTRUNS, + .result = (MAX_TAIL_CALL_CNT + 1) * MAX_TESTRUNS, }, { "Tail call error path, NULL target", diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6297eafdc40f..a69e4b04ffeb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1744,7 +1744,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * -- cgit v1.2.3 From 42f67eea3ba36cef2dce2e853de6ddcb2e89eb39 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 11:02:33 -0800 Subject: net: use sk_is_tcp() in more places Move sk_is_tcp() to include/net/sock.h and use it where we can. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skmsg.h | 6 ------ include/net/sock.h | 5 +++++ net/core/skbuff.c | 6 ++---- net/core/sock.c | 6 ++---- 4 files changed, 9 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 584d94be9c8b..18a717fe62eb 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -507,12 +507,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } -static inline bool sk_is_tcp(const struct sock *sk) -{ - return sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP; -} - static inline bool sk_is_udp(const struct sock *sk) { return sk->sk_type == SOCK_DGRAM && diff --git a/include/net/sock.h b/include/net/sock.h index b32906e1ab55..5bdeffdea5ec 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2638,6 +2638,11 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +static inline bool sk_is_tcp(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ba2f38246f07..d57796f38a0b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4849,8 +4849,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0; if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) + if (sk_is_tcp(sk)) serr->ee.ee_data -= sk->sk_tskey; } @@ -4919,8 +4918,7 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb, if (tsonly) { #ifdef CONFIG_INET if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) && - sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) { + sk_is_tcp(sk)) { skb = tcp_get_timestamping_opt_stats(sk, orig_skb, ack_skb); opt_stats = true; diff --git a/net/core/sock.c b/net/core/sock.c index 8f2b2f2c0e7b..0be8e43f44b9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -872,8 +872,7 @@ int sock_set_timestamping(struct sock *sk, int optname, if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { - if (sk->sk_protocol == IPPROTO_TCP && - sk->sk_type == SOCK_STREAM) { + if (sk_is_tcp(sk)) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; @@ -1370,8 +1369,7 @@ set_sndbuf: case SO_ZEROCOPY: if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6) { - if (!((sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP) || + if (!(sk_is_tcp(sk) || (sk->sk_type == SOCK_DGRAM && sk->sk_protocol == IPPROTO_UDP))) ret = -ENOTSUPP; -- cgit v1.2.3 From f35f821935d8df76f9c92e2431a225bdff938169 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 11:02:46 -0800 Subject: tcp: defer skb freeing after socket lock is released tcp recvmsg() (or rx zerocopy) spends a fair amount of time freeing skbs after their payload has been consumed. A typical ~64KB GRO packet has to release ~45 page references, eventually going to page allocator for each of them. Currently, this freeing is performed while socket lock is held, meaning that there is a high chance that BH handler has to queue incoming packets to tcp socket backlog. This can cause additional latencies, because the user thread has to process the backlog at release_sock() time, and while doing so, additional frames can be added by BH handler. This patch adds logic to defer these frees after socket lock is released, or directly from BH handler if possible. Being able to free these skbs from BH handler helps a lot, because this avoids the usual alloc/free assymetry, when BH handler and user thread do not run on same cpu or NUMA node. One cpu can now be fully utilized for the kernel->user copy, and another cpu is handling BH processing and skb/page allocs/frees (assuming RFS is not forcing use of a single CPU) Tested: 100Gbit NIC Max throughput for one TCP_STREAM flow, over 10 runs MTU : 1500 Before: 55 Gbit After: 66 Gbit MTU : 4096+(headers) Before: 82 Gbit After: 95 Gbit Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/skbuff.h | 2 ++ include/net/sock.h | 3 +++ include/net/tcp.h | 10 ++++++++++ net/ipv4/tcp.c | 27 +++++++++++++++++++++++++-- net/ipv4/tcp_ipv4.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 6 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 686a666d073d..b8b806512e16 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #if IS_ENABLED(CONFIG_NF_CONNTRACK) @@ -743,6 +744,7 @@ struct sk_buff { }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; + struct llist_node ll_node; }; union { diff --git a/include/net/sock.h b/include/net/sock.h index 2d40fe4c7718..2578d1f455a7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -408,6 +409,8 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; + struct llist_head defer_list; + #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; diff --git a/include/net/tcp.h b/include/net/tcp.h index 05c81677aaf7..44e442bf23f9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1368,6 +1368,16 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); + +void __sk_defer_free_flush(struct sock *sk); + +static inline void sk_defer_free_flush(struct sock *sk) +{ + if (llist_empty(&sk->defer_list)) + return; + __sk_defer_free_flush(sk); +} + int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4e7011672aa9..33cd9a1c199c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1580,14 +1580,34 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) tcp_send_ack(sk); } +void __sk_defer_free_flush(struct sock *sk) +{ + struct llist_node *head; + struct sk_buff *skb, *n; + + head = llist_del_all(&sk->defer_list); + llist_for_each_entry_safe(skb, n, head, ll_node) { + prefetch(n); + skb_mark_not_on_list(skb); + __kfree_skb(skb); + } +} +EXPORT_SYMBOL(__sk_defer_free_flush); + static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb) { + __skb_unlink(skb, &sk->sk_receive_queue); if (likely(skb->destructor == sock_rfree)) { sock_rfree(skb); skb->destructor = NULL; skb->sk = NULL; + if (!skb_queue_empty(&sk->sk_receive_queue) || + !llist_empty(&sk->defer_list)) { + llist_add(&skb->ll_node, &sk->defer_list); + return; + } } - sk_eat_skb(sk, skb); + __kfree_skb(skb); } static struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off) @@ -2422,6 +2442,7 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, /* Do not sleep, just process backlog. */ __sk_flush_backlog(sk); } else { + sk_defer_free_flush(sk); sk_wait_data(sk, &timeo, last); } @@ -2540,6 +2561,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss, &cmsg_flags); release_sock(sk); + sk_defer_free_flush(sk); if (cmsg_flags && ret >= 0) { if (cmsg_flags & TCP_CMSG_TS) @@ -3065,7 +3087,7 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_frag.page = NULL; sk->sk_frag.offset = 0; } - + sk_defer_free_flush(sk); sk_error_report(sk); return 0; } @@ -4194,6 +4216,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname, &zc, &len, err); release_sock(sk); + sk_defer_free_flush(sk); if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags)) goto zerocopy_rcv_cmsg; switch (len) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5ad81bfb27b2..3dd19a2bf06c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2102,6 +2102,7 @@ process: sk_incoming_cpu_update(sk); + sk_defer_free_flush(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f41f14b70123..3b7d6ede1364 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1758,6 +1758,7 @@ process: sk_incoming_cpu_update(sk); + sk_defer_free_flush(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; -- cgit v1.2.3 From 4721031c3559db8eae61df305f10c00099a7c1d0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:05:51 -0800 Subject: net: move gro definitions to include/net/gro.h include/linux/netdevice.h became too big, move gro stuff into include/net/gro.h Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 + drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 + drivers/net/ethernet/qlogic/qede/qede_fp.c | 1 + drivers/net/geneve.c | 1 + drivers/net/vxlan.c | 1 + include/linux/netdevice.h | 348 --------------------- include/net/gro.h | 396 +++++++++++++++++++++++- include/net/ip.h | 8 - include/net/ip6_checksum.h | 8 - include/net/udp.h | 24 -- net/core/skbuff.c | 1 + net/ipv4/af_inet.c | 1 + net/ipv4/esp4_offload.c | 1 + net/ipv4/fou.c | 1 + net/ipv4/gre_offload.c | 1 + net/ipv4/tcp_offload.c | 1 + net/ipv4/udp_offload.c | 1 + net/ipv6/esp6_offload.c | 1 + net/ipv6/tcpv6_offload.c | 1 + net/ipv6/udp_offload.c | 1 + 22 files changed, 411 insertions(+), 390 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index e8e8c2d593c5..54a2334dee56 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index c04ea83188e2..c057b1df86a9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 9ccebbaa0d69..13835a37b3a2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 96967b0a2441..e384f6458c06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -37,6 +37,7 @@ #include #include #include +#include #include #include #include "en.h" diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 065e9004598e..e113fbd56e86 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 1ab94b5f9bbf..9d26d1b965d2 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #define GENEVE_NETDEV_VER "0.6" diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 141635a35c28..563f86de0e0d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec42495a43a..d95c9839ce90 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2520,109 +2520,6 @@ static inline void netif_napi_del(struct napi_struct *napi) synchronize_net(); } -struct napi_gro_cb { - /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; - - /* Length of frag0. */ - unsigned int frag0_len; - - /* This indicates where we are processing relative to skb->data. */ - int data_offset; - - /* This is non-zero if the packet cannot be merged with the new skb. */ - u16 flush; - - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - - /* Number of segments aggregated. */ - u16 count; - - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; - - /* jiffies when first packet was created/queued */ - unsigned long age; - - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; - - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; - - /* Used in tunnel GRO receive */ - u8 encap_mark:1; - - /* GRO checksum is valid */ - u8 csum_valid:1; - - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; - - /* Free the skb? */ - u8 free:2; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 - - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; - - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; - - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; - - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; - - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; - - /* used to support CHECKSUM_COMPLETE for tunneling protocols */ - __wsum csum; - - /* used in skb_gro_receive() slow path */ - struct sk_buff *last; -}; - -#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) - -#define GRO_RECURSION_LIMIT 15 -static inline int gro_recursion_inc_test(struct sk_buff *skb) -{ - return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; -} - -typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); -static inline struct sk_buff *call_gro_receive(gro_receive_t cb, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(head, skb); -} - -typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, - struct sk_buff *); -static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(sk, head, skb); -} - struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; @@ -3008,251 +2905,6 @@ int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); -static inline unsigned int skb_gro_offset(const struct sk_buff *skb) -{ - return NAPI_GRO_CB(skb)->data_offset; -} - -static inline unsigned int skb_gro_len(const struct sk_buff *skb) -{ - return skb->len - NAPI_GRO_CB(skb)->data_offset; -} - -static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) -{ - NAPI_GRO_CB(skb)->data_offset += len; -} - -static inline void *skb_gro_header_fast(struct sk_buff *skb, - unsigned int offset) -{ - return NAPI_GRO_CB(skb)->frag0 + offset; -} - -static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) -{ - return NAPI_GRO_CB(skb)->frag0_len < hlen; -} - -static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; -} - -static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, - unsigned int offset) -{ - if (!pskb_may_pull(skb, hlen)) - return NULL; - - skb_gro_frag0_invalidate(skb); - return skb->data + offset; -} - -static inline void *skb_gro_network_header(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + - skb_network_offset(skb); -} - -static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) -{ - if (NAPI_GRO_CB(skb)->csum_valid) - NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, - csum_partial(start, len, 0)); -} - -/* GRO checksum functions. These are logical equivalents of the normal - * checksum functions (in skbuff.h) except that they operate on the GRO - * offsets and fields in sk_buff. - */ - -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); - -static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); -} - -static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, - bool zero_okay, - __sum16 check) -{ - return ((skb->ip_summed != CHECKSUM_PARTIAL || - skb_checksum_start_offset(skb) < - skb_gro_offset(skb)) && - !skb_at_gro_remcsum_start(skb) && - NAPI_GRO_CB(skb)->csum_cnt == 0 && - (!zero_okay || check)); -} - -static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, - __wsum psum) -{ - if (NAPI_GRO_CB(skb)->csum_valid && - !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) - return 0; - - NAPI_GRO_CB(skb)->csum = psum; - - return __skb_gro_checksum_complete(skb); -} - -static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) -{ - if (NAPI_GRO_CB(skb)->csum_cnt > 0) { - /* Consume a checksum from CHECKSUM_UNNECESSARY */ - NAPI_GRO_CB(skb)->csum_cnt--; - } else { - /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we - * verified a new top level checksum or an encapsulated one - * during GRO. This saves work if we fallback to normal path. - */ - __skb_incr_checksum_unnecessary(skb); - } -} - -#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ - compute_pseudo) \ -({ \ - __sum16 __ret = 0; \ - if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ - __ret = __skb_gro_checksum_validate_complete(skb, \ - compute_pseudo(skb, proto)); \ - if (!__ret) \ - skb_gro_incr_csum_unnecessary(skb); \ - __ret; \ -}) - -#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) - -#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ - compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) - -#define skb_gro_checksum_simple_validate(skb) \ - __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) - -static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->csum_cnt == 0 && - !NAPI_GRO_CB(skb)->csum_valid); -} - -static inline void __skb_gro_checksum_convert(struct sk_buff *skb, - __wsum pseudo) -{ - NAPI_GRO_CB(skb)->csum = ~pseudo; - NAPI_GRO_CB(skb)->csum_valid = 1; -} - -#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ -do { \ - if (__skb_gro_checksum_convert_check(skb)) \ - __skb_gro_checksum_convert(skb, \ - compute_pseudo(skb, proto)); \ -} while (0) - -struct gro_remcsum { - int offset; - __wsum delta; -}; - -static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) -{ - grc->offset = 0; - grc->delta = 0; -} - -static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - unsigned int off, size_t hdrlen, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) -{ - __wsum delta; - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - - BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); - - if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; - return ptr; - } - - ptr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, off + plen)) { - ptr = skb_gro_header_slow(skb, off + plen, off); - if (!ptr) - return NULL; - } - - delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, - start, offset); - - /* Adjust skb->csum since we changed the packet */ - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - - grc->offset = off + hdrlen + offset; - grc->delta = delta; - - return ptr; -} - -static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, - struct gro_remcsum *grc) -{ - void *ptr; - size_t plen = grc->offset + sizeof(u16); - - if (!grc->delta) - return; - - ptr = skb_gro_header_fast(skb, grc->offset); - if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { - ptr = skb_gro_header_slow(skb, plen, grc->offset); - if (!ptr) - return; - } - - remcsum_unadjust((__sum16 *)ptr, grc->delta); -} - -#ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - if (PTR_ERR(pp) != -EINPROGRESS) - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - if (PTR_ERR(pp) != -EINPROGRESS) { - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; - } -} -#else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; -} -#endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, diff --git a/include/net/gro.h b/include/net/gro.h index 01edaf3fdda0..1ffbe74b2e35 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -4,9 +4,367 @@ #define _NET_IPV6_GRO_H #include +#include +#include +#include +#include -struct list_head; -struct sk_buff; +struct napi_gro_cb { + /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ + void *frag0; + + /* Length of frag0. */ + unsigned int frag0_len; + + /* This indicates where we are processing relative to skb->data. */ + int data_offset; + + /* This is non-zero if the packet cannot be merged with the new skb. */ + u16 flush; + + /* Save the IP ID here and check when we get to the transport layer */ + u16 flush_id; + + /* Number of segments aggregated. */ + u16 count; + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; + + /* jiffies when first packet was created/queued */ + unsigned long age; + + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; + + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; + + /* Used in tunnel GRO receive */ + u8 encap_mark:1; + + /* GRO checksum is valid */ + u8 csum_valid:1; + + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; + + /* Free the skb? */ + u8 free:2; +#define NAPI_GRO_FREE 1 +#define NAPI_GRO_FREE_STOLEN_HEAD 2 + + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; + + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; + + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; + + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; + + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ + __wsum csum; + + /* used in skb_gro_receive() slow path */ + struct sk_buff *last; +}; + +#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) + +#define GRO_RECURSION_LIMIT 15 +static inline int gro_recursion_inc_test(struct sk_buff *skb) +{ + return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; +} + +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb); +} + +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(sk, head, skb); +} + +static inline unsigned int skb_gro_offset(const struct sk_buff *skb) +{ + return NAPI_GRO_CB(skb)->data_offset; +} + +static inline unsigned int skb_gro_len(const struct sk_buff *skb) +{ + return skb->len - NAPI_GRO_CB(skb)->data_offset; +} + +static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) +{ + NAPI_GRO_CB(skb)->data_offset += len; +} + +static inline void *skb_gro_header_fast(struct sk_buff *skb, + unsigned int offset) +{ + return NAPI_GRO_CB(skb)->frag0 + offset; +} + +static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) +{ + return NAPI_GRO_CB(skb)->frag0_len < hlen; +} + +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; +} + +static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, + unsigned int offset) +{ + if (!pskb_may_pull(skb, hlen)) + return NULL; + + skb_gro_frag0_invalidate(skb); + return skb->data + offset; +} + +static inline void *skb_gro_network_header(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + + skb_network_offset(skb); +} + +static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb_gro_len(skb), proto, 0); +} + +static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + if (NAPI_GRO_CB(skb)->csum_valid) + NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, + csum_partial(start, len, 0)); +} + +/* GRO checksum functions. These are logical equivalents of the normal + * checksum functions (in skbuff.h) except that they operate on the GRO + * offsets and fields in sk_buff. + */ + +__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); + +static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); +} + +static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, + bool zero_okay, + __sum16 check) +{ + return ((skb->ip_summed != CHECKSUM_PARTIAL || + skb_checksum_start_offset(skb) < + skb_gro_offset(skb)) && + !skb_at_gro_remcsum_start(skb) && + NAPI_GRO_CB(skb)->csum_cnt == 0 && + (!zero_okay || check)); +} + +static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, + __wsum psum) +{ + if (NAPI_GRO_CB(skb)->csum_valid && + !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) + return 0; + + NAPI_GRO_CB(skb)->csum = psum; + + return __skb_gro_checksum_complete(skb); +} + +static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->csum_cnt > 0) { + /* Consume a checksum from CHECKSUM_UNNECESSARY */ + NAPI_GRO_CB(skb)->csum_cnt--; + } else { + /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we + * verified a new top level checksum or an encapsulated one + * during GRO. This saves work if we fallback to normal path. + */ + __skb_incr_checksum_unnecessary(skb); + } +} + +#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ + compute_pseudo) \ +({ \ + __sum16 __ret = 0; \ + if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ + __ret = __skb_gro_checksum_validate_complete(skb, \ + compute_pseudo(skb, proto)); \ + if (!__ret) \ + skb_gro_incr_csum_unnecessary(skb); \ + __ret; \ +}) + +#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) + +#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ + compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) + +#define skb_gro_checksum_simple_validate(skb) \ + __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) + +static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->csum_cnt == 0 && + !NAPI_GRO_CB(skb)->csum_valid); +} + +static inline void __skb_gro_checksum_convert(struct sk_buff *skb, + __wsum pseudo) +{ + NAPI_GRO_CB(skb)->csum = ~pseudo; + NAPI_GRO_CB(skb)->csum_valid = 1; +} + +#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ +do { \ + if (__skb_gro_checksum_convert_check(skb)) \ + __skb_gro_checksum_convert(skb, \ + compute_pseudo(skb, proto)); \ +} while (0) + +struct gro_remcsum { + int offset; + __wsum delta; +}; + +static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) +{ + grc->offset = 0; + grc->delta = 0; +} + +static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + unsigned int off, size_t hdrlen, + int start, int offset, + struct gro_remcsum *grc, + bool nopartial) +{ + __wsum delta; + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + + BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); + + if (!nopartial) { + NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; + return ptr; + } + + ptr = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, off + plen)) { + ptr = skb_gro_header_slow(skb, off + plen, off); + if (!ptr) + return NULL; + } + + delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, + start, offset); + + /* Adjust skb->csum since we changed the packet */ + NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + + grc->offset = off + hdrlen + offset; + grc->delta = delta; + + return ptr; +} + +static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, + struct gro_remcsum *grc) +{ + void *ptr; + size_t plen = grc->offset + sizeof(u16); + + if (!grc->delta) + return; + + ptr = skb_gro_header_fast(skb, grc->offset); + if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { + ptr = skb_gro_header_slow(skb, plen, grc->offset); + if (!ptr) + return; + } + + remcsum_unadjust((__sum16 *)ptr, grc->delta); +} + +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) +{ + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; +} +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} +#else +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) +{ + NAPI_GRO_CB(skb)->flush |= flush; +} +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} +#endif INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, struct sk_buff *)); @@ -15,6 +373,14 @@ INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); +INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); + +INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); + #define indirect_call_gro_receive_inet(cb, f2, f1, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ @@ -22,4 +388,30 @@ INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALL_INET(cb, f2, f1, head, skb); \ }) +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, struct sock *sk); +int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); + +static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) +{ + struct udphdr *uh; + unsigned int hlen, off; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*uh); + uh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) + uh = skb_gro_header_slow(skb, hlen, off); + + return uh; +} + +static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), proto, 0)); +} + #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/ip.h b/include/net/ip.h index b71e88507c4a..7d1088888c10 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -568,14 +568,6 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } -static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) -{ - const struct iphdr *iph = skb_gro_network_header(skb); - - return csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb_gro_len(skb), proto, 0); -} - /* * Map a multicast IP onto multicast MAC for type ethernet. */ diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index ea681910b7a3..c8a96b888277 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -43,14 +43,6 @@ static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) skb->len, proto, 0)); } -static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) -{ - const struct ipv6hdr *iph = skb_gro_network_header(skb); - - return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), proto, 0)); -} - static __inline__ __sum16 tcp_v6_check(int len, const struct in6_addr *saddr, const struct in6_addr *daddr, diff --git a/include/net/udp.h b/include/net/udp.h index 909ecf447e0f..f1c2a88c9005 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -167,36 +167,12 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); -struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, - struct udphdr *uh, struct sock *sk); -int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); - struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); -static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) -{ - struct udphdr *uh; - unsigned int hlen, off; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*uh); - uh = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) - uh = skb_gro_header_slow(skb, hlen, off); - - return uh; -} - /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d57796f38a0b..5b9472bdceff 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -64,6 +64,7 @@ #include #include +#include #include #include #include diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0189e3cd4a7d..6d52b6491255 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -99,6 +99,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 8e4e9aa12130..d87f02a6e934 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 8fcbc6258ec5..b56d6b40c0a2 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1121a9d5fed9..740298dac7d3 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -10,6 +10,7 @@ #include #include #include +#include static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index fc61cd3fea65..30abde86db45 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -8,6 +8,7 @@ #include #include +#include #include #include diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 86d32a1e62ac..7fbf9975e8c0 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index a349d4798077..ba5e81cd569c 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c index 1796856bc24f..39db5a226855 100644 --- a/net/ipv6/tcpv6_offload.c +++ b/net/ipv6/tcpv6_offload.c @@ -7,6 +7,7 @@ */ #include #include +#include #include #include #include diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index b3d9ed96e5ea..50a8a65fad23 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -13,6 +13,7 @@ #include #include #include "ip6_offload.h" +#include static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, netdev_features_t features) -- cgit v1.2.3 From 0b935d7f8c07bf0a192712bdbf76dbf45ef8b115 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:05:52 -0800 Subject: net: gro: move skb_gro_receive_list to udp_offload.c This helper is used once, no need to keep it in fat net/core/skbuff.c Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - net/core/skbuff.c | 26 -------------------------- net/ipv4/udp_offload.c | 27 +++++++++++++++++++++++++++ 3 files changed, 27 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d95c9839ce90..ce6ee1453dbc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2903,7 +2903,6 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); -int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5b9472bdceff..8560d50c960b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3920,32 +3920,6 @@ err_linearize: } EXPORT_SYMBOL_GPL(skb_segment_list); -int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) -{ - if (unlikely(p->len + skb->len >= 65536)) - return -E2BIG; - - if (NAPI_GRO_CB(p)->last == p) - skb_shinfo(p)->frag_list = skb; - else - NAPI_GRO_CB(p)->last->next = skb; - - skb_pull(skb, skb_gro_offset(skb)); - - NAPI_GRO_CB(p)->last = skb; - NAPI_GRO_CB(p)->count++; - p->data_len += skb->len; - - /* sk owenrship - if any - completely transferred to the aggregated packet */ - skb->destructor = NULL; - p->truesize += skb->truesize; - p->len += skb->len; - - NAPI_GRO_CB(skb)->same_flow = 1; - - return 0; -} - /** * skb_segment - Perform protocol segmentation on skb. * @head_skb: buffer to segment diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 7fbf9975e8c0..cbeb8965d1b7 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -425,6 +425,33 @@ out: return segs; } +static int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) +{ + if (unlikely(p->len + skb->len >= 65536)) + return -E2BIG; + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + + skb_pull(skb, skb_gro_offset(skb)); + + NAPI_GRO_CB(p)->last = skb; + NAPI_GRO_CB(p)->count++; + p->data_len += skb->len; + + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; + p->truesize += skb->truesize; + p->len += skb->len; + + NAPI_GRO_CB(skb)->same_flow = 1; + + return 0; +} + + #define UDP_GRO_CNT_MAX 64 static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct sk_buff *skb) -- cgit v1.2.3 From e456a18a390b96f22b0de2acd4d0f49c72ed2280 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:05:53 -0800 Subject: net: gro: move skb_gro_receive into net/core/gro.c net/core/gro.c will contain all core gro functions, to shrink net/core/skbuff.c and net/core/dev.c Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - include/net/gro.h | 2 + net/core/Makefile | 2 +- net/core/gro.c | 118 ++++++++++++++++++++++++++++++++++++++++++++++ net/core/skbuff.c | 117 --------------------------------------------- 5 files changed, 121 insertions(+), 119 deletions(-) create mode 100644 net/core/gro.c (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ce6ee1453dbc..93d397db9ec4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2902,7 +2902,6 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, diff --git a/include/net/gro.h b/include/net/gro.h index 1ffbe74b2e35..f988bf3440f8 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -414,4 +414,6 @@ static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) skb_gro_len(skb), proto, 0)); } +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); + #endif /* _NET_IPV6_GRO_H */ diff --git a/net/core/Makefile b/net/core/Makefile index 4268846f2f47..6bdcb2cafed8 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o flow_offload.o + fib_notifier.o xdp.o flow_offload.o gro.o obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o diff --git a/net/core/gro.c b/net/core/gro.c new file mode 100644 index 000000000000..91a74c4da9ff --- /dev/null +++ b/net/core/gro.c @@ -0,0 +1,118 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include + +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) +{ + struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); + unsigned int offset = skb_gro_offset(skb); + unsigned int headlen = skb_headlen(skb); + unsigned int len = skb_gro_len(skb); + unsigned int delta_truesize; + unsigned int new_truesize; + struct sk_buff *lp; + + if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) + return -E2BIG; + + lp = NAPI_GRO_CB(p)->last; + pinfo = skb_shinfo(lp); + + if (headlen <= offset) { + skb_frag_t *frag; + skb_frag_t *frag2; + int i = skbinfo->nr_frags; + int nr_frags = pinfo->nr_frags + i; + + if (nr_frags > MAX_SKB_FRAGS) + goto merge; + + offset -= headlen; + pinfo->nr_frags = nr_frags; + skbinfo->nr_frags = 0; + + frag = pinfo->frags + nr_frags; + frag2 = skbinfo->frags + i; + do { + *--frag = *--frag2; + } while (--i); + + skb_frag_off_add(frag, offset); + skb_frag_size_sub(frag, offset); + + /* all fragments truesize : remove (head size + sk_buff) */ + new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); + delta_truesize = skb->truesize - new_truesize; + + skb->truesize = new_truesize; + skb->len -= skb->data_len; + skb->data_len = 0; + + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; + goto done; + } else if (skb->head_frag) { + int nr_frags = pinfo->nr_frags; + skb_frag_t *frag = pinfo->frags + nr_frags; + struct page *page = virt_to_head_page(skb->head); + unsigned int first_size = headlen - offset; + unsigned int first_offset; + + if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) + goto merge; + + first_offset = skb->data - + (unsigned char *)page_address(page) + + offset; + + pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; + + __skb_frag_set_page(frag, page); + skb_frag_off_set(frag, first_offset); + skb_frag_size_set(frag, first_size); + + memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); + /* We dont need to clear skbinfo->nr_frags here */ + + new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); + delta_truesize = skb->truesize - new_truesize; + skb->truesize = new_truesize; + NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; + goto done; + } + +merge: + /* sk owenrship - if any - completely transferred to the aggregated packet */ + skb->destructor = NULL; + delta_truesize = skb->truesize; + if (offset > headlen) { + unsigned int eat = offset - headlen; + + skb_frag_off_add(&skbinfo->frags[0], eat); + skb_frag_size_sub(&skbinfo->frags[0], eat); + skb->data_len -= eat; + skb->len -= eat; + offset = headlen; + } + + __skb_pull(skb, offset); + + if (NAPI_GRO_CB(p)->last == p) + skb_shinfo(p)->frag_list = skb; + else + NAPI_GRO_CB(p)->last->next = skb; + NAPI_GRO_CB(p)->last = skb; + __skb_header_release(skb); + lp = p; + +done: + NAPI_GRO_CB(p)->count++; + p->data_len += len; + p->truesize += delta_truesize; + p->len += len; + if (lp != p) { + lp->data_len += len; + lp->truesize += delta_truesize; + lp->len += len; + } + NAPI_GRO_CB(skb)->same_flow = 1; + return 0; +} diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8560d50c960b..73720bc1daa3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -64,7 +64,6 @@ #include #include -#include #include #include #include @@ -4272,122 +4271,6 @@ err: } EXPORT_SYMBOL_GPL(skb_segment); -int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) -{ - struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb); - unsigned int offset = skb_gro_offset(skb); - unsigned int headlen = skb_headlen(skb); - unsigned int len = skb_gro_len(skb); - unsigned int delta_truesize; - unsigned int new_truesize; - struct sk_buff *lp; - - if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) - return -E2BIG; - - lp = NAPI_GRO_CB(p)->last; - pinfo = skb_shinfo(lp); - - if (headlen <= offset) { - skb_frag_t *frag; - skb_frag_t *frag2; - int i = skbinfo->nr_frags; - int nr_frags = pinfo->nr_frags + i; - - if (nr_frags > MAX_SKB_FRAGS) - goto merge; - - offset -= headlen; - pinfo->nr_frags = nr_frags; - skbinfo->nr_frags = 0; - - frag = pinfo->frags + nr_frags; - frag2 = skbinfo->frags + i; - do { - *--frag = *--frag2; - } while (--i); - - skb_frag_off_add(frag, offset); - skb_frag_size_sub(frag, offset); - - /* all fragments truesize : remove (head size + sk_buff) */ - new_truesize = SKB_TRUESIZE(skb_end_offset(skb)); - delta_truesize = skb->truesize - new_truesize; - - skb->truesize = new_truesize; - skb->len -= skb->data_len; - skb->data_len = 0; - - NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE; - goto done; - } else if (skb->head_frag) { - int nr_frags = pinfo->nr_frags; - skb_frag_t *frag = pinfo->frags + nr_frags; - struct page *page = virt_to_head_page(skb->head); - unsigned int first_size = headlen - offset; - unsigned int first_offset; - - if (nr_frags + 1 + skbinfo->nr_frags > MAX_SKB_FRAGS) - goto merge; - - first_offset = skb->data - - (unsigned char *)page_address(page) + - offset; - - pinfo->nr_frags = nr_frags + 1 + skbinfo->nr_frags; - - __skb_frag_set_page(frag, page); - skb_frag_off_set(frag, first_offset); - skb_frag_size_set(frag, first_size); - - memcpy(frag + 1, skbinfo->frags, sizeof(*frag) * skbinfo->nr_frags); - /* We dont need to clear skbinfo->nr_frags here */ - - new_truesize = SKB_DATA_ALIGN(sizeof(struct sk_buff)); - delta_truesize = skb->truesize - new_truesize; - skb->truesize = new_truesize; - NAPI_GRO_CB(skb)->free = NAPI_GRO_FREE_STOLEN_HEAD; - goto done; - } - -merge: - /* sk owenrship - if any - completely transferred to the aggregated packet */ - skb->destructor = NULL; - delta_truesize = skb->truesize; - if (offset > headlen) { - unsigned int eat = offset - headlen; - - skb_frag_off_add(&skbinfo->frags[0], eat); - skb_frag_size_sub(&skbinfo->frags[0], eat); - skb->data_len -= eat; - skb->len -= eat; - offset = headlen; - } - - __skb_pull(skb, offset); - - if (NAPI_GRO_CB(p)->last == p) - skb_shinfo(p)->frag_list = skb; - else - NAPI_GRO_CB(p)->last->next = skb; - NAPI_GRO_CB(p)->last = skb; - __skb_header_release(skb); - lp = p; - -done: - NAPI_GRO_CB(p)->count++; - p->data_len += len; - p->truesize += delta_truesize; - p->len += len; - if (lp != p) { - lp->data_len += len; - lp->truesize += delta_truesize; - lp->len += len; - } - NAPI_GRO_CB(skb)->same_flow = 1; - return 0; -} - #ifdef CONFIG_SKB_EXTENSIONS #define SKB_EXT_ALIGN_VALUE 8 #define SKB_EXT_CHUNKSIZEOF(x) (ALIGN((sizeof(x)), SKB_EXT_ALIGN_VALUE) / SKB_EXT_ALIGN_VALUE) -- cgit v1.2.3 From 587652bbdd06ab38a4c1b85e40f933d2cf4a1147 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:05:54 -0800 Subject: net: gro: populate net/core/gro.c Move gro code and data from net/core/dev.c to net/core/gro.c to ease maintenance. gro_normal_list() and gro_normal_one() are inlined because they are called from both files. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/gro.h | 22 ++ net/core/dev.c | 668 +--------------------------------------------- net/core/gro.c | 648 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 672 insertions(+), 667 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 93d397db9ec4..31a7e6b27681 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3657,6 +3657,7 @@ int netif_rx_ni(struct sk_buff *skb); int netif_rx_any_context(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); diff --git a/include/net/gro.h b/include/net/gro.h index f988bf3440f8..d0e7df691a80 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -416,4 +416,26 @@ static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static inline void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) +{ + list_add_tail(&skb->list, &napi->rx_list); + napi->rx_count += segs; + if (napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + + #endif /* _NET_IPV6_GRO_H */ diff --git a/net/core/dev.c b/net/core/dev.c index 15ac064b5562..92c9258cbf28 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -153,16 +153,10 @@ #include "net-sysfs.h" -#define MAX_GRO_SKBS 8 - -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) static DEFINE_SPINLOCK(ptype_lock); -static DEFINE_SPINLOCK(offload_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; struct list_head ptype_all __read_mostly; /* Taps */ -static struct list_head offload_base __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_info(unsigned long val, @@ -604,84 +598,6 @@ void dev_remove_pack(struct packet_type *pt) EXPORT_SYMBOL(dev_remove_pack); -/** - * dev_add_offload - register offload handlers - * @po: protocol offload declaration - * - * Add protocol offload handlers to the networking stack. The passed - * &proto_offload is linked into kernel lists and may not be freed until - * it has been removed from the kernel lists. - * - * This call does not sleep therefore it can not - * guarantee all CPU's that are in middle of receiving packets - * will see the new offload handlers (until the next received packet). - */ -void dev_add_offload(struct packet_offload *po) -{ - struct packet_offload *elem; - - spin_lock(&offload_lock); - list_for_each_entry(elem, &offload_base, list) { - if (po->priority < elem->priority) - break; - } - list_add_rcu(&po->list, elem->list.prev); - spin_unlock(&offload_lock); -} -EXPORT_SYMBOL(dev_add_offload); - -/** - * __dev_remove_offload - remove offload handler - * @po: packet offload declaration - * - * Remove a protocol offload handler that was previously added to the - * kernel offload handlers by dev_add_offload(). The passed &offload_type - * is removed from the kernel lists and can be freed or reused once this - * function returns. - * - * The packet type might still be in use by receivers - * and must not be freed until after all the CPU's have gone - * through a quiescent state. - */ -static void __dev_remove_offload(struct packet_offload *po) -{ - struct list_head *head = &offload_base; - struct packet_offload *po1; - - spin_lock(&offload_lock); - - list_for_each_entry(po1, head, list) { - if (po == po1) { - list_del_rcu(&po->list); - goto out; - } - } - - pr_warn("dev_remove_offload: %p not found\n", po); -out: - spin_unlock(&offload_lock); -} - -/** - * dev_remove_offload - remove packet offload handler - * @po: packet offload declaration - * - * Remove a packet offload handler that was previously added to the kernel - * offload handlers by dev_add_offload(). The passed &offload_type is - * removed from the kernel lists and can be freed or reused once this - * function returns. - * - * This call sleeps to guarantee that no CPU is looking at the packet - * type after return. - */ -void dev_remove_offload(struct packet_offload *po) -{ - __dev_remove_offload(po); - - synchronize_net(); -} -EXPORT_SYMBOL(dev_remove_offload); - /******************************************************************************* * * Device Interface Subroutines @@ -3315,40 +3231,6 @@ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) return __vlan_get_protocol(skb, type, depth); } -/** - * skb_mac_gso_segment - mac layer segmentation handler. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - */ -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features) -{ - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_offload *ptype; - int vlan_depth = skb->mac_len; - __be16 type = skb_network_protocol(skb, &vlan_depth); - - if (unlikely(!type)) - return ERR_PTR(-EINVAL); - - __skb_pull(skb, vlan_depth); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &offload_base, list) { - if (ptype->type == type && ptype->callbacks.gso_segment) { - segs = ptype->callbacks.gso_segment(skb, features); - break; - } - } - rcu_read_unlock(); - - __skb_push(skb, skb->data - skb_mac_header(skb)); - - return segs; -} -EXPORT_SYMBOL(skb_mac_gso_segment); - - /* openvswitch calls this on rx path, so we need a different check. */ static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) @@ -4320,8 +4202,6 @@ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ int dev_rx_weight __read_mostly = 64; int dev_tx_weight __read_mostly = 64; -/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ -int gro_normal_batch __read_mostly = 8; /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, @@ -5664,7 +5544,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) return ret; } -static void netif_receive_skb_list_internal(struct list_head *head) +void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; struct list_head sublist; @@ -5842,550 +5722,6 @@ static void flush_all_backlogs(void) cpus_read_unlock(); } -/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) -{ - list_add_tail(&skb->list, &napi->rx_list); - napi->rx_count += segs; - if (napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - -static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) -{ - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct list_head *head = &offload_base; - int err = -ENOENT; - - BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); - - if (NAPI_GRO_CB(skb)->count == 1) { - skb_shinfo(skb)->gso_size = 0; - goto out; - } - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - - err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, - ipv6_gro_complete, inet_gro_complete, - skb, 0); - break; - } - rcu_read_unlock(); - - if (err) { - WARN_ON(&ptype->list == head); - kfree_skb(skb); - return; - } - -out: - gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); -} - -static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, - bool flush_old) -{ - struct list_head *head = &napi->gro_hash[index].list; - struct sk_buff *skb, *p; - - list_for_each_entry_safe_reverse(skb, p, head, list) { - if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) - return; - skb_list_del_init(skb); - napi_gro_complete(napi, skb); - napi->gro_hash[index].count--; - } - - if (!napi->gro_hash[index].count) - __clear_bit(index, &napi->gro_bitmask); -} - -/* napi->gro_hash[].list contains packets ordered by age. - * youngest packets at the head of it. - * Complete skbs in reverse order to reduce latencies. - */ -void napi_gro_flush(struct napi_struct *napi, bool flush_old) -{ - unsigned long bitmask = napi->gro_bitmask; - unsigned int i, base = ~0U; - - while ((i = ffs(bitmask)) != 0) { - bitmask >>= i; - base += i; - __napi_gro_flush_chain(napi, base, flush_old); - } -} -EXPORT_SYMBOL(napi_gro_flush); - -static void gro_list_prepare(const struct list_head *head, - const struct sk_buff *skb) -{ - unsigned int maclen = skb->dev->hard_header_len; - u32 hash = skb_get_hash_raw(skb); - struct sk_buff *p; - - list_for_each_entry(p, head, list) { - unsigned long diffs; - - NAPI_GRO_CB(p)->flush = 0; - - if (hash != skb_get_hash_raw(p)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - - diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; - diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); - if (skb_vlan_tag_present(p)) - diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); - diffs |= skb_metadata_differs(p, skb); - if (maclen == ETH_HLEN) - diffs |= compare_ether_header(skb_mac_header(p), - skb_mac_header(skb)); - else if (!diffs) - diffs = memcmp(skb_mac_header(p), - skb_mac_header(skb), - maclen); - - /* in most common scenarions 'slow_gro' is 0 - * otherwise we are already on some slower paths - * either skip all the infrequent tests altogether or - * avoid trying too hard to skip each of them individually - */ - if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { -#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - struct tc_skb_ext *skb_ext; - struct tc_skb_ext *p_ext; -#endif - - diffs |= p->sk != skb->sk; - diffs |= skb_metadata_dst_cmp(p, skb); - diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); - -#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) - skb_ext = skb_ext_find(skb, TC_SKB_EXT); - p_ext = skb_ext_find(p, TC_SKB_EXT); - - diffs |= (!!p_ext) ^ (!!skb_ext); - if (!diffs && unlikely(skb_ext)) - diffs |= p_ext->chain ^ skb_ext->chain; -#endif - } - - NAPI_GRO_CB(p)->same_flow = !diffs; - } -} - -static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) -{ - const struct skb_shared_info *pinfo = skb_shinfo(skb); - const skb_frag_t *frag0 = &pinfo->frags[0]; - - NAPI_GRO_CB(skb)->data_offset = 0; - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; - - if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0)) && - (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { - NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); - NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, - skb_frag_size(frag0), - skb->end - skb->tail); - } -} - -static void gro_pull_from_frag0(struct sk_buff *skb, int grow) -{ - struct skb_shared_info *pinfo = skb_shinfo(skb); - - BUG_ON(skb->end - skb->tail < grow); - - memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); - - skb->data_len -= grow; - skb->tail += grow; - - skb_frag_off_add(&pinfo->frags[0], grow); - skb_frag_size_sub(&pinfo->frags[0], grow); - - if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { - skb_frag_unref(skb, 0); - memmove(pinfo->frags, pinfo->frags + 1, - --pinfo->nr_frags * sizeof(pinfo->frags[0])); - } -} - -static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) -{ - struct sk_buff *oldest; - - oldest = list_last_entry(head, struct sk_buff, list); - - /* We are called with head length >= MAX_GRO_SKBS, so this is - * impossible. - */ - if (WARN_ON_ONCE(!oldest)) - return; - - /* Do not adjust napi->gro_hash[].count, caller is adding a new - * SKB to the chain. - */ - skb_list_del_init(oldest); - napi_gro_complete(napi, oldest); -} - -static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); - struct gro_list *gro_list = &napi->gro_hash[bucket]; - struct list_head *head = &offload_base; - struct packet_offload *ptype; - __be16 type = skb->protocol; - struct sk_buff *pp = NULL; - enum gro_result ret; - int same_flow; - int grow; - - if (netif_elide_gro(skb->dev)) - goto normal; - - gro_list_prepare(&gro_list->list, skb); - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - - skb_set_network_header(skb, skb_gro_offset(skb)); - skb_reset_mac_len(skb); - NAPI_GRO_CB(skb)->same_flow = 0; - NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); - NAPI_GRO_CB(skb)->free = 0; - NAPI_GRO_CB(skb)->encap_mark = 0; - NAPI_GRO_CB(skb)->recursion_counter = 0; - NAPI_GRO_CB(skb)->is_fou = 0; - NAPI_GRO_CB(skb)->is_atomic = 1; - NAPI_GRO_CB(skb)->gro_remcsum_start = 0; - - /* Setup for GRO checksum validation */ - switch (skb->ip_summed) { - case CHECKSUM_COMPLETE: - NAPI_GRO_CB(skb)->csum = skb->csum; - NAPI_GRO_CB(skb)->csum_valid = 1; - NAPI_GRO_CB(skb)->csum_cnt = 0; - break; - case CHECKSUM_UNNECESSARY: - NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; - NAPI_GRO_CB(skb)->csum_valid = 0; - break; - default: - NAPI_GRO_CB(skb)->csum_cnt = 0; - NAPI_GRO_CB(skb)->csum_valid = 0; - } - - pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, - ipv6_gro_receive, inet_gro_receive, - &gro_list->list, skb); - break; - } - rcu_read_unlock(); - - if (&ptype->list == head) - goto normal; - - if (PTR_ERR(pp) == -EINPROGRESS) { - ret = GRO_CONSUMED; - goto ok; - } - - same_flow = NAPI_GRO_CB(skb)->same_flow; - ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; - - if (pp) { - skb_list_del_init(pp); - napi_gro_complete(napi, pp); - gro_list->count--; - } - - if (same_flow) - goto ok; - - if (NAPI_GRO_CB(skb)->flush) - goto normal; - - if (unlikely(gro_list->count >= MAX_GRO_SKBS)) - gro_flush_oldest(napi, &gro_list->list); - else - gro_list->count++; - - NAPI_GRO_CB(skb)->count = 1; - NAPI_GRO_CB(skb)->age = jiffies; - NAPI_GRO_CB(skb)->last = skb; - skb_shinfo(skb)->gso_size = skb_gro_len(skb); - list_add(&skb->list, &gro_list->list); - ret = GRO_HELD; - -pull: - grow = skb_gro_offset(skb) - skb_headlen(skb); - if (grow > 0) - gro_pull_from_frag0(skb, grow); -ok: - if (gro_list->count) { - if (!test_bit(bucket, &napi->gro_bitmask)) - __set_bit(bucket, &napi->gro_bitmask); - } else if (test_bit(bucket, &napi->gro_bitmask)) { - __clear_bit(bucket, &napi->gro_bitmask); - } - - return ret; - -normal: - ret = GRO_NORMAL; - goto pull; -} - -struct packet_offload *gro_find_receive_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_receive) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_receive_by_type); - -struct packet_offload *gro_find_complete_by_type(__be16 type) -{ - struct list_head *offload_head = &offload_base; - struct packet_offload *ptype; - - list_for_each_entry_rcu(ptype, offload_head, list) { - if (ptype->type != type || !ptype->callbacks.gro_complete) - continue; - return ptype; - } - return NULL; -} -EXPORT_SYMBOL(gro_find_complete_by_type); - -static gro_result_t napi_skb_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) -{ - switch (ret) { - case GRO_NORMAL: - gro_normal_one(napi, skb, 1); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) - __kfree_skb(skb); - else - __kfree_skb_defer(skb); - break; - - case GRO_HELD: - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) -{ - gro_result_t ret; - - skb_mark_napi_id(skb, napi); - trace_napi_gro_receive_entry(skb); - - skb_gro_reset_offset(skb, 0); - - ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_receive_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_receive); - -static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) -{ - if (unlikely(skb->pfmemalloc)) { - consume_skb(skb); - return; - } - __skb_pull(skb, skb_headlen(skb)); - /* restore the reserve we had after netdev_alloc_skb_ip_align() */ - skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); - __vlan_hwaccel_clear_tag(skb); - skb->dev = napi->dev; - skb->skb_iif = 0; - - /* eth_type_trans() assumes pkt_type is PACKET_HOST */ - skb->pkt_type = PACKET_HOST; - - skb->encapsulation = 0; - skb_shinfo(skb)->gso_type = 0; - skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); - if (unlikely(skb->slow_gro)) { - skb_orphan(skb); - skb_ext_reset(skb); - nf_reset_ct(skb); - skb->slow_gro = 0; - } - - napi->skb = skb; -} - -struct sk_buff *napi_get_frags(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - - if (!skb) { - skb = napi_alloc_skb(napi, GRO_MAX_HEAD); - if (skb) { - napi->skb = skb; - skb_mark_napi_id(skb, napi); - } - } - return skb; -} -EXPORT_SYMBOL(napi_get_frags); - -static gro_result_t napi_frags_finish(struct napi_struct *napi, - struct sk_buff *skb, - gro_result_t ret) -{ - switch (ret) { - case GRO_NORMAL: - case GRO_HELD: - __skb_push(skb, ETH_HLEN); - skb->protocol = eth_type_trans(skb, skb->dev); - if (ret == GRO_NORMAL) - gro_normal_one(napi, skb, 1); - break; - - case GRO_MERGED_FREE: - if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) - napi_skb_free_stolen_head(skb); - else - napi_reuse_skb(napi, skb); - break; - - case GRO_MERGED: - case GRO_CONSUMED: - break; - } - - return ret; -} - -/* Upper GRO stack assumes network header starts at gro_offset=0 - * Drivers could call both napi_gro_frags() and napi_gro_receive() - * We copy ethernet header into skb->data to have a common layout. - */ -static struct sk_buff *napi_frags_skb(struct napi_struct *napi) -{ - struct sk_buff *skb = napi->skb; - const struct ethhdr *eth; - unsigned int hlen = sizeof(*eth); - - napi->skb = NULL; - - skb_reset_mac_header(skb); - skb_gro_reset_offset(skb, hlen); - - if (unlikely(skb_gro_header_hard(skb, hlen))) { - eth = skb_gro_header_slow(skb, hlen, 0); - if (unlikely(!eth)) { - net_warn_ratelimited("%s: dropping impossible skb from %s\n", - __func__, napi->dev->name); - napi_reuse_skb(napi, skb); - return NULL; - } - } else { - eth = (const struct ethhdr *)skb->data; - gro_pull_from_frag0(skb, hlen); - NAPI_GRO_CB(skb)->frag0 += hlen; - NAPI_GRO_CB(skb)->frag0_len -= hlen; - } - __skb_pull(skb, hlen); - - /* - * This works because the only protocols we care about don't require - * special handling. - * We'll fix it up properly in napi_frags_finish() - */ - skb->protocol = eth->h_proto; - - return skb; -} - -gro_result_t napi_gro_frags(struct napi_struct *napi) -{ - gro_result_t ret; - struct sk_buff *skb = napi_frags_skb(napi); - - trace_napi_gro_frags_entry(skb); - - ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); - trace_napi_gro_frags_exit(ret); - - return ret; -} -EXPORT_SYMBOL(napi_gro_frags); - -/* Compute the checksum from gro_offset and return the folded value - * after adding in any pseudo checksum. - */ -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb) -{ - __wsum wsum; - __sum16 sum; - - wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); - - /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ - sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); - /* See comments in __skb_checksum_complete(). */ - if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && - !skb->csum_complete_sw) - netdev_rx_csum_fault(skb->dev, skb); - } - - NAPI_GRO_CB(skb)->csum = wsum; - NAPI_GRO_CB(skb)->csum_valid = 1; - - return sum; -} -EXPORT_SYMBOL(__skb_gro_checksum_complete); - static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS @@ -11640,8 +10976,6 @@ static int __init net_dev_init(void) for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); - INIT_LIST_HEAD(&offload_base); - if (register_pernet_subsys(&netdev_net_ops)) goto out; diff --git a/net/core/gro.c b/net/core/gro.c index 91a74c4da9ff..8ec8b44596da 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -1,5 +1,129 @@ // SPDX-License-Identifier: GPL-2.0-or-later #include +#include +#include +#include + +#define MAX_GRO_SKBS 8 + +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) + +static DEFINE_SPINLOCK(offload_lock); +static struct list_head offload_base __read_mostly = LIST_HEAD_INIT(offload_base); +/* Maximum number of GRO_NORMAL skbs to batch up for list-RX */ +int gro_normal_batch __read_mostly = 8; + +/** + * dev_add_offload - register offload handlers + * @po: protocol offload declaration + * + * Add protocol offload handlers to the networking stack. The passed + * &proto_offload is linked into kernel lists and may not be freed until + * it has been removed from the kernel lists. + * + * This call does not sleep therefore it can not + * guarantee all CPU's that are in middle of receiving packets + * will see the new offload handlers (until the next received packet). + */ +void dev_add_offload(struct packet_offload *po) +{ + struct packet_offload *elem; + + spin_lock(&offload_lock); + list_for_each_entry(elem, &offload_base, list) { + if (po->priority < elem->priority) + break; + } + list_add_rcu(&po->list, elem->list.prev); + spin_unlock(&offload_lock); +} +EXPORT_SYMBOL(dev_add_offload); + +/** + * __dev_remove_offload - remove offload handler + * @po: packet offload declaration + * + * Remove a protocol offload handler that was previously added to the + * kernel offload handlers by dev_add_offload(). The passed &offload_type + * is removed from the kernel lists and can be freed or reused once this + * function returns. + * + * The packet type might still be in use by receivers + * and must not be freed until after all the CPU's have gone + * through a quiescent state. + */ +static void __dev_remove_offload(struct packet_offload *po) +{ + struct list_head *head = &offload_base; + struct packet_offload *po1; + + spin_lock(&offload_lock); + + list_for_each_entry(po1, head, list) { + if (po == po1) { + list_del_rcu(&po->list); + goto out; + } + } + + pr_warn("dev_remove_offload: %p not found\n", po); +out: + spin_unlock(&offload_lock); +} + +/** + * dev_remove_offload - remove packet offload handler + * @po: packet offload declaration + * + * Remove a packet offload handler that was previously added to the kernel + * offload handlers by dev_add_offload(). The passed &offload_type is + * removed from the kernel lists and can be freed or reused once this + * function returns. + * + * This call sleeps to guarantee that no CPU is looking at the packet + * type after return. + */ +void dev_remove_offload(struct packet_offload *po) +{ + __dev_remove_offload(po); + + synchronize_net(); +} +EXPORT_SYMBOL(dev_remove_offload); + +/** + * skb_mac_gso_segment - mac layer segmentation handler. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + */ +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_offload *ptype; + int vlan_depth = skb->mac_len; + __be16 type = skb_network_protocol(skb, &vlan_depth); + + if (unlikely(!type)) + return ERR_PTR(-EINVAL); + + __skb_pull(skb, vlan_depth); + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { + segs = ptype->callbacks.gso_segment(skb, features); + break; + } + } + rcu_read_unlock(); + + __skb_push(skb, skb->data - skb_mac_header(skb)); + + return segs; +} +EXPORT_SYMBOL(skb_mac_gso_segment); int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) { @@ -116,3 +240,527 @@ done: NAPI_GRO_CB(skb)->same_flow = 1; return 0; } + + +static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) +{ + struct packet_offload *ptype; + __be16 type = skb->protocol; + struct list_head *head = &offload_base; + int err = -ENOENT; + + BUILD_BUG_ON(sizeof(struct napi_gro_cb) > sizeof(skb->cb)); + + if (NAPI_GRO_CB(skb)->count == 1) { + skb_shinfo(skb)->gso_size = 0; + goto out; + } + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + + err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete, + ipv6_gro_complete, inet_gro_complete, + skb, 0); + break; + } + rcu_read_unlock(); + + if (err) { + WARN_ON(&ptype->list == head); + kfree_skb(skb); + return; + } + +out: + gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); +} + +static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, + bool flush_old) +{ + struct list_head *head = &napi->gro_hash[index].list; + struct sk_buff *skb, *p; + + list_for_each_entry_safe_reverse(skb, p, head, list) { + if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) + return; + skb_list_del_init(skb); + napi_gro_complete(napi, skb); + napi->gro_hash[index].count--; + } + + if (!napi->gro_hash[index].count) + __clear_bit(index, &napi->gro_bitmask); +} + +/* napi->gro_hash[].list contains packets ordered by age. + * youngest packets at the head of it. + * Complete skbs in reverse order to reduce latencies. + */ +void napi_gro_flush(struct napi_struct *napi, bool flush_old) +{ + unsigned long bitmask = napi->gro_bitmask; + unsigned int i, base = ~0U; + + while ((i = ffs(bitmask)) != 0) { + bitmask >>= i; + base += i; + __napi_gro_flush_chain(napi, base, flush_old); + } +} +EXPORT_SYMBOL(napi_gro_flush); + +static void gro_list_prepare(const struct list_head *head, + const struct sk_buff *skb) +{ + unsigned int maclen = skb->dev->hard_header_len; + u32 hash = skb_get_hash_raw(skb); + struct sk_buff *p; + + list_for_each_entry(p, head, list) { + unsigned long diffs; + + NAPI_GRO_CB(p)->flush = 0; + + if (hash != skb_get_hash_raw(p)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= skb_vlan_tag_present(p) ^ skb_vlan_tag_present(skb); + if (skb_vlan_tag_present(p)) + diffs |= skb_vlan_tag_get(p) ^ skb_vlan_tag_get(skb); + diffs |= skb_metadata_differs(p, skb); + if (maclen == ETH_HLEN) + diffs |= compare_ether_header(skb_mac_header(p), + skb_mac_header(skb)); + else if (!diffs) + diffs = memcmp(skb_mac_header(p), + skb_mac_header(skb), + maclen); + + /* in most common scenarions 'slow_gro' is 0 + * otherwise we are already on some slower paths + * either skip all the infrequent tests altogether or + * avoid trying too hard to skip each of them individually + */ + if (!diffs && unlikely(skb->slow_gro | p->slow_gro)) { +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + struct tc_skb_ext *skb_ext; + struct tc_skb_ext *p_ext; +#endif + + diffs |= p->sk != skb->sk; + diffs |= skb_metadata_dst_cmp(p, skb); + diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb); + +#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT) + skb_ext = skb_ext_find(skb, TC_SKB_EXT); + p_ext = skb_ext_find(p, TC_SKB_EXT); + + diffs |= (!!p_ext) ^ (!!skb_ext); + if (!diffs && unlikely(skb_ext)) + diffs |= p_ext->chain ^ skb_ext->chain; +#endif + } + + NAPI_GRO_CB(p)->same_flow = !diffs; + } +} + +static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff) +{ + const struct skb_shared_info *pinfo = skb_shinfo(skb); + const skb_frag_t *frag0 = &pinfo->frags[0]; + + NAPI_GRO_CB(skb)->data_offset = 0; + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; + + if (!skb_headlen(skb) && pinfo->nr_frags && + !PageHighMem(skb_frag_page(frag0)) && + (!NET_IP_ALIGN || !((skb_frag_off(frag0) + nhoff) & 3))) { + NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); + NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, + skb_frag_size(frag0), + skb->end - skb->tail); + } +} + +static void gro_pull_from_frag0(struct sk_buff *skb, int grow) +{ + struct skb_shared_info *pinfo = skb_shinfo(skb); + + BUG_ON(skb->end - skb->tail < grow); + + memcpy(skb_tail_pointer(skb), NAPI_GRO_CB(skb)->frag0, grow); + + skb->data_len -= grow; + skb->tail += grow; + + skb_frag_off_add(&pinfo->frags[0], grow); + skb_frag_size_sub(&pinfo->frags[0], grow); + + if (unlikely(!skb_frag_size(&pinfo->frags[0]))) { + skb_frag_unref(skb, 0); + memmove(pinfo->frags, pinfo->frags + 1, + --pinfo->nr_frags * sizeof(pinfo->frags[0])); + } +} + +static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head) +{ + struct sk_buff *oldest; + + oldest = list_last_entry(head, struct sk_buff, list); + + /* We are called with head length >= MAX_GRO_SKBS, so this is + * impossible. + */ + if (WARN_ON_ONCE(!oldest)) + return; + + /* Do not adjust napi->gro_hash[].count, caller is adding a new + * SKB to the chain. + */ + skb_list_del_init(oldest); + napi_gro_complete(napi, oldest); +} + +static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +{ + u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1); + struct gro_list *gro_list = &napi->gro_hash[bucket]; + struct list_head *head = &offload_base; + struct packet_offload *ptype; + __be16 type = skb->protocol; + struct sk_buff *pp = NULL; + enum gro_result ret; + int same_flow; + int grow; + + if (netif_elide_gro(skb->dev)) + goto normal; + + gro_list_prepare(&gro_list->list, skb); + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + + skb_set_network_header(skb, skb_gro_offset(skb)); + skb_reset_mac_len(skb); + NAPI_GRO_CB(skb)->same_flow = 0; + NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb); + NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; + NAPI_GRO_CB(skb)->recursion_counter = 0; + NAPI_GRO_CB(skb)->is_fou = 0; + NAPI_GRO_CB(skb)->is_atomic = 1; + NAPI_GRO_CB(skb)->gro_remcsum_start = 0; + + /* Setup for GRO checksum validation */ + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + NAPI_GRO_CB(skb)->csum = skb->csum; + NAPI_GRO_CB(skb)->csum_valid = 1; + NAPI_GRO_CB(skb)->csum_cnt = 0; + break; + case CHECKSUM_UNNECESSARY: + NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1; + NAPI_GRO_CB(skb)->csum_valid = 0; + break; + default: + NAPI_GRO_CB(skb)->csum_cnt = 0; + NAPI_GRO_CB(skb)->csum_valid = 0; + } + + pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive, + ipv6_gro_receive, inet_gro_receive, + &gro_list->list, skb); + break; + } + rcu_read_unlock(); + + if (&ptype->list == head) + goto normal; + + if (PTR_ERR(pp) == -EINPROGRESS) { + ret = GRO_CONSUMED; + goto ok; + } + + same_flow = NAPI_GRO_CB(skb)->same_flow; + ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; + + if (pp) { + skb_list_del_init(pp); + napi_gro_complete(napi, pp); + gro_list->count--; + } + + if (same_flow) + goto ok; + + if (NAPI_GRO_CB(skb)->flush) + goto normal; + + if (unlikely(gro_list->count >= MAX_GRO_SKBS)) + gro_flush_oldest(napi, &gro_list->list); + else + gro_list->count++; + + NAPI_GRO_CB(skb)->count = 1; + NAPI_GRO_CB(skb)->age = jiffies; + NAPI_GRO_CB(skb)->last = skb; + skb_shinfo(skb)->gso_size = skb_gro_len(skb); + list_add(&skb->list, &gro_list->list); + ret = GRO_HELD; + +pull: + grow = skb_gro_offset(skb) - skb_headlen(skb); + if (grow > 0) + gro_pull_from_frag0(skb, grow); +ok: + if (gro_list->count) { + if (!test_bit(bucket, &napi->gro_bitmask)) + __set_bit(bucket, &napi->gro_bitmask); + } else if (test_bit(bucket, &napi->gro_bitmask)) { + __clear_bit(bucket, &napi->gro_bitmask); + } + + return ret; + +normal: + ret = GRO_NORMAL; + goto pull; +} + +struct packet_offload *gro_find_receive_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_receive) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_receive_by_type); + +struct packet_offload *gro_find_complete_by_type(__be16 type) +{ + struct list_head *offload_head = &offload_base; + struct packet_offload *ptype; + + list_for_each_entry_rcu(ptype, offload_head, list) { + if (ptype->type != type || !ptype->callbacks.gro_complete) + continue; + return ptype; + } + return NULL; +} +EXPORT_SYMBOL(gro_find_complete_by_type); + +static gro_result_t napi_skb_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) +{ + switch (ret) { + case GRO_NORMAL: + gro_normal_one(napi, skb, 1); + break; + + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else if (skb->fclone != SKB_FCLONE_UNAVAILABLE) + __kfree_skb(skb); + else + __kfree_skb_defer(skb); + break; + + case GRO_HELD: + case GRO_MERGED: + case GRO_CONSUMED: + break; + } + + return ret; +} + +gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +{ + gro_result_t ret; + + skb_mark_napi_id(skb, napi); + trace_napi_gro_receive_entry(skb); + + skb_gro_reset_offset(skb, 0); + + ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); + trace_napi_gro_receive_exit(ret); + + return ret; +} +EXPORT_SYMBOL(napi_gro_receive); + +static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) +{ + if (unlikely(skb->pfmemalloc)) { + consume_skb(skb); + return; + } + __skb_pull(skb, skb_headlen(skb)); + /* restore the reserve we had after netdev_alloc_skb_ip_align() */ + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN - skb_headroom(skb)); + __vlan_hwaccel_clear_tag(skb); + skb->dev = napi->dev; + skb->skb_iif = 0; + + /* eth_type_trans() assumes pkt_type is PACKET_HOST */ + skb->pkt_type = PACKET_HOST; + + skb->encapsulation = 0; + skb_shinfo(skb)->gso_type = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); + if (unlikely(skb->slow_gro)) { + skb_orphan(skb); + skb_ext_reset(skb); + nf_reset_ct(skb); + skb->slow_gro = 0; + } + + napi->skb = skb; +} + +struct sk_buff *napi_get_frags(struct napi_struct *napi) +{ + struct sk_buff *skb = napi->skb; + + if (!skb) { + skb = napi_alloc_skb(napi, GRO_MAX_HEAD); + if (skb) { + napi->skb = skb; + skb_mark_napi_id(skb, napi); + } + } + return skb; +} +EXPORT_SYMBOL(napi_get_frags); + +static gro_result_t napi_frags_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) +{ + switch (ret) { + case GRO_NORMAL: + case GRO_HELD: + __skb_push(skb, ETH_HLEN); + skb->protocol = eth_type_trans(skb, skb->dev); + if (ret == GRO_NORMAL) + gro_normal_one(napi, skb, 1); + break; + + case GRO_MERGED_FREE: + if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD) + napi_skb_free_stolen_head(skb); + else + napi_reuse_skb(napi, skb); + break; + + case GRO_MERGED: + case GRO_CONSUMED: + break; + } + + return ret; +} + +/* Upper GRO stack assumes network header starts at gro_offset=0 + * Drivers could call both napi_gro_frags() and napi_gro_receive() + * We copy ethernet header into skb->data to have a common layout. + */ +static struct sk_buff *napi_frags_skb(struct napi_struct *napi) +{ + struct sk_buff *skb = napi->skb; + const struct ethhdr *eth; + unsigned int hlen = sizeof(*eth); + + napi->skb = NULL; + + skb_reset_mac_header(skb); + skb_gro_reset_offset(skb, hlen); + + if (unlikely(skb_gro_header_hard(skb, hlen))) { + eth = skb_gro_header_slow(skb, hlen, 0); + if (unlikely(!eth)) { + net_warn_ratelimited("%s: dropping impossible skb from %s\n", + __func__, napi->dev->name); + napi_reuse_skb(napi, skb); + return NULL; + } + } else { + eth = (const struct ethhdr *)skb->data; + gro_pull_from_frag0(skb, hlen); + NAPI_GRO_CB(skb)->frag0 += hlen; + NAPI_GRO_CB(skb)->frag0_len -= hlen; + } + __skb_pull(skb, hlen); + + /* + * This works because the only protocols we care about don't require + * special handling. + * We'll fix it up properly in napi_frags_finish() + */ + skb->protocol = eth->h_proto; + + return skb; +} + +gro_result_t napi_gro_frags(struct napi_struct *napi) +{ + gro_result_t ret; + struct sk_buff *skb = napi_frags_skb(napi); + + trace_napi_gro_frags_entry(skb); + + ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb)); + trace_napi_gro_frags_exit(ret); + + return ret; +} +EXPORT_SYMBOL(napi_gro_frags); + +/* Compute the checksum from gro_offset and return the folded value + * after adding in any pseudo checksum. + */ +__sum16 __skb_gro_checksum_complete(struct sk_buff *skb) +{ + __wsum wsum; + __sum16 sum; + + wsum = skb_checksum(skb, skb_gro_offset(skb), skb_gro_len(skb), 0); + + /* NAPI_GRO_CB(skb)->csum holds pseudo checksum */ + sum = csum_fold(csum_add(NAPI_GRO_CB(skb)->csum, wsum)); + /* See comments in __skb_checksum_complete(). */ + if (likely(!sum)) { + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) && + !skb->csum_complete_sw) + netdev_rx_csum_fault(skb->dev, skb); + } + + NAPI_GRO_CB(skb)->csum = wsum; + NAPI_GRO_CB(skb)->csum_valid = 1; + + return sum; +} +EXPORT_SYMBOL(__skb_gro_checksum_complete); -- cgit v1.2.3 From 77d641baa3c8e18a1056bec6c64c6103c1a17b1e Mon Sep 17 00:00:00 2001 From: Luca Ceresoli Date: Mon, 8 Nov 2021 17:27:05 +0100 Subject: power: supply: core: add POWER_SUPPLY_HEALTH_NO_BATTERY Some chargers can keep the system powered from the mains even when no battery is present. It this case none of the currently defined health statuses applies. Add a new status to report that no battery is present. Suggested-by: Sebastian Reichel Signed-off-by: Luca Ceresoli Signed-off-by: Sebastian Reichel --- Documentation/ABI/testing/sysfs-class-power | 2 +- drivers/power/supply/power_supply_sysfs.c | 1 + include/linux/power_supply.h | 1 + 3 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power index f7904efc4cfa..a0b2a4280e38 100644 --- a/Documentation/ABI/testing/sysfs-class-power +++ b/Documentation/ABI/testing/sysfs-class-power @@ -413,7 +413,7 @@ Description: "Over voltage", "Unspecified failure", "Cold", "Watchdog timer expire", "Safety timer expire", "Over current", "Calibration required", "Warm", - "Cool", "Hot" + "Cool", "Hot", "No battery" What: /sys/class/power_supply//precharge_current Date: June 2017 diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index c3d7cbcd4fad..6ac88fbee3cb 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -106,6 +106,7 @@ static const char * const POWER_SUPPLY_HEALTH_TEXT[] = { [POWER_SUPPLY_HEALTH_WARM] = "Warm", [POWER_SUPPLY_HEALTH_COOL] = "Cool", [POWER_SUPPLY_HEALTH_HOT] = "Hot", + [POWER_SUPPLY_HEALTH_NO_BATTERY] = "No battery", }; static const char * const POWER_SUPPLY_TECHNOLOGY_TEXT[] = { diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 9ca1f120a211..2d1318fe2455 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -66,6 +66,7 @@ enum { POWER_SUPPLY_HEALTH_WARM, POWER_SUPPLY_HEALTH_COOL, POWER_SUPPLY_HEALTH_HOT, + POWER_SUPPLY_HEALTH_NO_BATTERY, }; enum { -- cgit v1.2.3 From d7751d6476185ff754b9dad2cba0c0a6e43ecadc Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 20 May 2021 17:09:58 +0300 Subject: net/mlx5: E-Switch, Fix resetting of encap mode when entering switchdev E-Switch encap mode is relevant only when in switchdev mode. The RDMA driver can query the encap configuration via mlx5_eswitch_get_encap_mode(). Make sure it returns the currently used mode and not the set one. This reverts the cited commit which reset the encap mode on entering switchdev and fixes the original issue properly. Fixes: 9a64144d683a ("net/mlx5: E-Switch, Fix default encap mode") Signed-off-by: Paul Blakey Reviewed-by: Mark Bloch Reviewed-by: Maor Dickman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 9 +++++++-- drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 7 ------- include/linux/mlx5/eswitch.h | 4 ++-- 3 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index ec136b499204..5872cc8bf953 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1572,6 +1572,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) esw->enabled_vports = 0; esw->mode = MLX5_ESWITCH_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) && + MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap)) + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; + else + esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; dev->priv.eswitch = esw; BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head); @@ -1934,7 +1939,7 @@ free_out: return err; } -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { struct mlx5_eswitch *esw = dev->priv.eswitch; @@ -1948,7 +1953,7 @@ mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev) struct mlx5_eswitch *esw; esw = dev->priv.eswitch; - return mlx5_esw_allowed(esw) ? esw->offloads.encap : + return (mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS) ? esw->offloads.encap : DEVLINK_ESWITCH_ENCAP_MODE_NONE; } EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f4eaa5893886..80fa76f60e1e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -3183,12 +3183,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) u64 mapping_id; int err; - if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) && - MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap)) - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC; - else - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; - mutex_init(&esw->offloads.termtbl_mutex); mlx5_rdma_enable_roce(esw->dev); @@ -3286,7 +3280,6 @@ void esw_offloads_disable(struct mlx5_eswitch *esw) esw_offloads_metadata_uninit(esw); mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); - esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 97afcea39a7b..8b18fe9771f9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } -- cgit v1.2.3 From c2c60ea37e5b6be58c9dd7aff0b2e86ba0f18e0b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:23:01 -0800 Subject: once: use __section(".data.once") .data.once contains nicely packed bool variables. It is used already by DO_ONCE_LITE(). Using it also in DO_ONCE() removes holes in .data section. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/once.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/once.h b/include/linux/once.h index d361fb14ac3a..f54523052bbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -38,7 +38,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, #define DO_ONCE(func, ...) \ ({ \ bool ___ret = false; \ - static bool ___done = false; \ + static bool __section(".data.once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ -- cgit v1.2.3 From 7071732c26fe2cf141185ed16a8a85d02495ae8c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:23:02 -0800 Subject: net: use .data.once section in netdev_level_once() Same rationale than prior patch : using the dedicated section avoid holes and pack all these bool values. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 31a7e6b27681..dd328364dfe9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4942,7 +4942,7 @@ void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ do { \ - static bool __print_once __read_mostly; \ + static bool __section(".data.once") __print_once; \ \ if (!__print_once) { \ __print_once = true; \ -- cgit v1.2.3 From 49ecc2e9c3abd269951972fa8b23a4d081111b80 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 15 Nov 2021 09:23:03 -0800 Subject: net: align static siphash keys siphash keys use 16 bytes. Define siphash_aligned_key_t macro so that we can make sure they are not crossing a cache line boundary. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/siphash.h | 2 ++ net/core/flow_dissector.c | 2 +- net/core/secure_seq.c | 4 ++-- net/ipv4/route.c | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv6/route.c | 2 +- net/ipv6/syncookies.c | 2 +- net/netfilter/nf_conntrack_core.c | 4 ++-- net/netfilter/nf_conntrack_expect.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 2 +- net/netfilter/nf_nat_core.c | 2 +- 11 files changed, 14 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/siphash.h b/include/linux/siphash.h index bf21591a9e5e..3f7427b9e935 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -21,6 +21,8 @@ typedef struct { u64 key[2]; } siphash_key_t; +#define siphash_aligned_key_t siphash_key_t __aligned(16) + static inline bool siphash_key_is_zero(const siphash_key_t *key) { return !(key->key[0] | key->key[1]); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3255f57f5131..257976cb55ce 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1460,7 +1460,7 @@ out_bad: } EXPORT_SYMBOL(__skb_flow_dissect); -static siphash_key_t hashrnd __read_mostly; +static siphash_aligned_key_t hashrnd; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index b5bc680d4755..9b8443774449 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -19,8 +19,8 @@ #include #include -static siphash_key_t net_secret __read_mostly; -static siphash_key_t ts_secret __read_mostly; +static siphash_aligned_key_t net_secret; +static siphash_aligned_key_t ts_secret; static __always_inline void net_secret_init(void) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0b4103b1e622..243a0c52be42 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -602,7 +602,7 @@ static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) static u32 fnhe_hashfun(__be32 daddr) { - static siphash_key_t fnhe_hash_key __read_mostly; + static siphash_aligned_key_t fnhe_hash_key; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 8696dc343ad2..2cb3b852d148 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -14,7 +14,7 @@ #include #include -static siphash_key_t syncookie_secret[2] __read_mostly; +static siphash_aligned_key_t syncookie_secret[2]; #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3ae25b8ffbd6..5e8f2f15607d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1485,7 +1485,7 @@ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { - static siphash_key_t rt6_exception_key __read_mostly; + static siphash_aligned_key_t rt6_exception_key; struct { struct in6_addr dst; struct in6_addr src; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index e8cfb9e997bf..d1b61d00368e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -20,7 +20,7 @@ #define COOKIEBITS 24 /* Upper bits store count */ #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1) -static siphash_key_t syncookie6_secret[2] __read_mostly; +static siphash_aligned_key_t syncookie6_secret[2]; /* RFC 2460, Section 8.3: * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..] diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 770a63103c7a..054ee9d25efe 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -189,7 +189,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); seqcount_spinlock_t nf_conntrack_generation __read_mostly; -static siphash_key_t nf_conntrack_hash_rnd __read_mostly; +static siphash_aligned_key_t nf_conntrack_hash_rnd; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, unsigned int zoneid, @@ -482,7 +482,7 @@ EXPORT_SYMBOL_GPL(nf_ct_invert_tuple); */ u32 nf_ct_get_id(const struct nf_conn *ct) { - static __read_mostly siphash_key_t ct_id_seed; + static siphash_aligned_key_t ct_id_seed; unsigned long a, b, c, d; net_get_random_once(&ct_id_seed, sizeof(ct_id_seed)); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index f562eeef4234..1e89b595ecd0 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(nf_ct_expect_hash); unsigned int nf_ct_expect_max __read_mostly; static struct kmem_cache *nf_ct_expect_cachep __read_mostly; -static siphash_key_t nf_ct_expect_hashrnd __read_mostly; +static siphash_aligned_key_t nf_ct_expect_hashrnd; /* nf_conntrack_expect helper functions */ void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index f1e5443fe7c7..3d6c8da3de1f 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2997,7 +2997,7 @@ static const union nf_inet_addr any_addr; static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp) { - static __read_mostly siphash_key_t exp_id_seed; + static siphash_aligned_key_t exp_id_seed; unsigned long a, b, c, d; net_get_random_once(&exp_id_seed, sizeof(exp_id_seed)); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 4d50d51db796..ab9f6c75524d 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -34,7 +34,7 @@ static unsigned int nat_net_id __read_mostly; static struct hlist_head *nf_nat_bysource __read_mostly; static unsigned int nf_nat_htable_size __read_mostly; -static siphash_key_t nf_nat_hash_rnd __read_mostly; +static siphash_aligned_key_t nf_nat_hash_rnd; struct nf_nat_lookup_hook_priv { struct nf_hook_entries __rcu *entries; -- cgit v1.2.3 From b9241f54138ca5af4d3c5ca6db56be83d7491508 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 15 Nov 2021 17:11:17 +0000 Subject: net: document SMII and correct phylink's new validation mechanism SMII has not been documented in the kernel, but information on this PHY interface mode has been recently found. Document it, and correct the recently introduced phylink handling for this interface mode. Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/E1mmfVl-0075nP-14@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- Documentation/networking/phy.rst | 5 +++++ drivers/net/phy/phylink.c | 2 +- include/linux/phy.h | 2 +- 3 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst index 571ba08386e7..d43da709bf40 100644 --- a/Documentation/networking/phy.rst +++ b/Documentation/networking/phy.rst @@ -237,6 +237,11 @@ negotiation results. Some of the interface modes are described below: +``PHY_INTERFACE_MODE_SMII`` + This is serial MII, clocked at 125MHz, supporting 100M and 10M speeds. + Some details can be found in + https://opencores.org/ocsvn/smii/smii/trunk/doc/SMII.pdf + ``PHY_INTERFACE_MODE_1000BASEX`` This defines the 1000BASE-X single-lane serdes link as defined by the 802.3 standard section 36. The link operates at a fixed bit rate of diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 33462fdc7add..f7156b6868e7 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -336,6 +336,7 @@ void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, case PHY_INTERFACE_MODE_REVRMII: case PHY_INTERFACE_MODE_RMII: + case PHY_INTERFACE_MODE_SMII: case PHY_INTERFACE_MODE_REVMII: case PHY_INTERFACE_MODE_MII: caps |= MAC_10HD | MAC_10FD; @@ -385,7 +386,6 @@ void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, case PHY_INTERFACE_MODE_NA: case PHY_INTERFACE_MODE_MAX: - case PHY_INTERFACE_MODE_SMII: break; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 96e43fbb2dd8..1e57cdd95da3 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -99,7 +99,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI - * @PHY_INTERFACE_MODE_SMII: ??? MII + * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax -- cgit v1.2.3 From 5854d4a6cc356ba3e16d8593ac1c089a32d1759c Mon Sep 17 00:00:00 2001 From: Tudor Ambarus Date: Fri, 29 Oct 2021 20:26:12 +0300 Subject: mtd: spi-nor: Get rid of nor->page_size nor->page_size duplicated what nor->params->page_size indicates for no good reason. page_size is a flash parameter of fixed value and it is better suited to be found in nor->params->page_size. Signed-off-by: Tudor Ambarus Reviewed-by: Pratyush Yadav Reviewed-by: Michael Walle Link: https://lore.kernel.org/r/20211029172633.886453-5-tudor.ambarus@microchip.com --- drivers/mtd/spi-nor/core.c | 19 +++++++++---------- drivers/mtd/spi-nor/xilinx.c | 17 ++++++++++------- include/linux/mtd/spi-nor.h | 2 -- 3 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index 277d1fde84c8..3ec0959ffc20 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -1952,6 +1952,7 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len, struct spi_nor *nor = mtd_to_spi_nor(mtd); size_t page_offset, page_remain, i; ssize_t ret; + u32 page_size = nor->params->page_size; dev_dbg(nor->dev, "to 0x%08x, len %zd\n", (u32)to, len); @@ -1968,16 +1969,15 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len, * calculated with an AND operation. On the other cases we * need to do a modulus operation (more expensive). */ - if (is_power_of_2(nor->page_size)) { - page_offset = addr & (nor->page_size - 1); + if (is_power_of_2(page_size)) { + page_offset = addr & (page_size - 1); } else { uint64_t aux = addr; - page_offset = do_div(aux, nor->page_size); + page_offset = do_div(aux, page_size); } /* the size of data remaining on the first page */ - page_remain = min_t(size_t, - nor->page_size - page_offset, len - i); + page_remain = min_t(size_t, page_size - page_offset, len - i); addr = spi_nor_convert_addr(nor, addr); @@ -3094,7 +3094,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, * We need the bounce buffer early to read/write registers when going * through the spi-mem layer (buffers have to be DMA-able). * For spi-mem drivers, we'll reallocate a new buffer if - * nor->page_size turns out to be greater than PAGE_SIZE (which + * nor->params->page_size turns out to be greater than PAGE_SIZE (which * shouldn't happen before long since NOR pages are usually less * than 1KB) after spi_nor_scan() returns. */ @@ -3170,8 +3170,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, mtd->flags |= MTD_NO_ERASE; mtd->dev.parent = dev; - nor->page_size = nor->params->page_size; - mtd->writebufsize = nor->page_size; + mtd->writebufsize = nor->params->page_size; if (of_property_read_bool(np, "broken-flash-reset")) nor->flags |= SNOR_F_BROKEN_RESET; @@ -3340,8 +3339,8 @@ static int spi_nor_probe(struct spi_mem *spimem) * and add this logic so that if anyone ever adds support for such * a NOR we don't end up with buffer overflows. */ - if (nor->page_size > PAGE_SIZE) { - nor->bouncebuf_size = nor->page_size; + if (nor->params->page_size > PAGE_SIZE) { + nor->bouncebuf_size = nor->params->page_size; devm_kfree(nor->dev, nor->bouncebuf); nor->bouncebuf = devm_kmalloc(nor->dev, nor->bouncebuf_size, diff --git a/drivers/mtd/spi-nor/xilinx.c b/drivers/mtd/spi-nor/xilinx.c index 1138bdbf4199..0658e47564ba 100644 --- a/drivers/mtd/spi-nor/xilinx.c +++ b/drivers/mtd/spi-nor/xilinx.c @@ -28,11 +28,12 @@ static const struct flash_info xilinx_parts[] = { */ static u32 s3an_convert_addr(struct spi_nor *nor, u32 addr) { + u32 page_size = nor->params->page_size; u32 offset, page; - offset = addr % nor->page_size; - page = addr / nor->page_size; - page <<= (nor->page_size > 512) ? 10 : 9; + offset = addr % page_size; + page = addr / page_size; + page <<= (page_size > 512) ? 10 : 9; return page | offset; } @@ -40,6 +41,7 @@ static u32 s3an_convert_addr(struct spi_nor *nor, u32 addr) static int xilinx_nor_setup(struct spi_nor *nor, const struct spi_nor_hwcaps *hwcaps) { + u32 page_size; int ret; ret = spi_nor_xread_sr(nor, nor->bouncebuf); @@ -64,10 +66,11 @@ static int xilinx_nor_setup(struct spi_nor *nor, */ if (nor->bouncebuf[0] & XSR_PAGESIZE) { /* Flash in Power of 2 mode */ - nor->page_size = (nor->page_size == 264) ? 256 : 512; - nor->mtd.writebufsize = nor->page_size; - nor->mtd.size = 8 * nor->page_size * nor->info->n_sectors; - nor->mtd.erasesize = 8 * nor->page_size; + page_size = (nor->params->page_size == 264) ? 256 : 512; + nor->params->page_size = page_size; + nor->mtd.writebufsize = page_size; + nor->mtd.size = 8 * page_size * nor->info->n_sectors; + nor->mtd.erasesize = 8 * page_size; } else { /* Flash in Default addressing mode */ nor->params->convert_addr = s3an_convert_addr; diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index f67457748ed8..fc90fce26e33 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -371,7 +371,6 @@ struct spi_nor_flash_parameter; * @bouncebuf_size: size of the bounce buffer * @info: SPI NOR part JEDEC MFR ID and other info * @manufacturer: SPI NOR manufacturer - * @page_size: the page size of the SPI NOR * @addr_width: number of address bytes * @erase_opcode: the opcode for erasing a sector * @read_opcode: the read opcode @@ -401,7 +400,6 @@ struct spi_nor { size_t bouncebuf_size; const struct flash_info *info; const struct spi_nor_manufacturer *manufacturer; - u32 page_size; u8 addr_width; u8 erase_opcode; u8 read_opcode; -- cgit v1.2.3 From 1e2c3ef0496e72ba9001da5fd1b7ed56ccb30597 Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Mon, 4 Oct 2021 16:11:52 +0200 Subject: tee: export teedev_open() and teedev_close_context() Exports the two functions teedev_open() and teedev_close_context() in order to make it easier to create a driver internal struct tee_context. Reviewed-by: Sumit Garg Signed-off-by: Jens Wiklander --- drivers/tee/tee_core.c | 6 ++++-- include/linux/tee_drv.h | 14 ++++++++++++++ 2 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/tee/tee_core.c b/drivers/tee/tee_core.c index 85102d12d716..3fc426dad2df 100644 --- a/drivers/tee/tee_core.c +++ b/drivers/tee/tee_core.c @@ -43,7 +43,7 @@ static DEFINE_SPINLOCK(driver_lock); static struct class *tee_class; static dev_t tee_devt; -static struct tee_context *teedev_open(struct tee_device *teedev) +struct tee_context *teedev_open(struct tee_device *teedev) { int rc; struct tee_context *ctx; @@ -70,6 +70,7 @@ err: return ERR_PTR(rc); } +EXPORT_SYMBOL_GPL(teedev_open); void teedev_ctx_get(struct tee_context *ctx) { @@ -96,13 +97,14 @@ void teedev_ctx_put(struct tee_context *ctx) kref_put(&ctx->refcount, teedev_ctx_release); } -static void teedev_close_context(struct tee_context *ctx) +void teedev_close_context(struct tee_context *ctx) { struct tee_device *teedev = ctx->teedev; teedev_ctx_put(ctx); tee_device_put(teedev); } +EXPORT_SYMBOL_GPL(teedev_close_context); static int tee_open(struct inode *inode, struct file *filp) { diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a1f03461369b..468a7d83dc6c 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -587,4 +587,18 @@ struct tee_client_driver { #define to_tee_client_driver(d) \ container_of(d, struct tee_client_driver, driver) +/** + * teedev_open() - Open a struct tee_device + * @teedev: Device to open + * + * @return a pointer to struct tee_context on success or an ERR_PTR on failure. + */ +struct tee_context *teedev_open(struct tee_device *teedev); + +/** + * teedev_close_context() - closes a struct tee_context + * @ctx: The struct tee_context to close + */ +void teedev_close_context(struct tee_context *ctx); + #endif /*__TEE_DRV_H*/ -- cgit v1.2.3 From 49c39ec4670a8f045729e3717af2e1a74caf89a5 Mon Sep 17 00:00:00 2001 From: Christian König Date: Mon, 13 Sep 2021 14:21:25 +0200 Subject: dma-buf: nuke dma_resv_get_excl_unlocked MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Heureka, that's finally not used any more. Signed-off-by: Christian König Reviewed-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20210917123513.1106-27-christian.koenig@amd.com --- include/linux/dma-resv.h | 26 -------------------------- 1 file changed, 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h index 09c6063b199a..eebf04325b34 100644 --- a/include/linux/dma-resv.h +++ b/include/linux/dma-resv.h @@ -440,32 +440,6 @@ dma_resv_excl_fence(struct dma_resv *obj) return rcu_dereference_check(obj->fence_excl, dma_resv_held(obj)); } -/** - * dma_resv_get_excl_unlocked - get the reservation object's - * exclusive fence, without lock held. - * @obj: the reservation object - * - * If there is an exclusive fence, this atomically increments it's - * reference count and returns it. - * - * RETURNS - * The exclusive fence or NULL if none - */ -static inline struct dma_fence * -dma_resv_get_excl_unlocked(struct dma_resv *obj) -{ - struct dma_fence *fence; - - if (!rcu_access_pointer(obj->fence_excl)) - return NULL; - - rcu_read_lock(); - fence = dma_fence_get_rcu_safe(&obj->fence_excl); - rcu_read_unlock(); - - return fence; -} - /** * dma_resv_shared_list - get the reservation object's shared fence list * @obj: the reservation object -- cgit v1.2.3 From 2fb75e1b642f49253d8848c9e47e8942f5366221 Mon Sep 17 00:00:00 2001 From: Liu Xinpeng Date: Mon, 25 Oct 2021 11:46:26 +0800 Subject: psi: Add a missing SPDX license header Add the missing SPDX license header to include/linux/psi.h include/linux/psi_types.h kernel/sched/psi.c Signed-off-by: Liu Xinpeng Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/1635133586-84611-2-git-send-email-liuxp11@chinatelecom.cn --- include/linux/psi.h | 1 + include/linux/psi_types.h | 1 + kernel/sched/psi.c | 1 + 3 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index 65eb1476ac70..a70ca833c6d7 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_H #define _LINUX_PSI_H diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 0a23300d49af..bf50068d5d4b 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PSI_TYPES_H #define _LINUX_PSI_TYPES_H diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 526af84ab852..3397fa001157 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Pressure stall information for CPU, memory and IO * -- cgit v1.2.3 From 4feee7d12603deca8775f9f9ae5e121093837444 Mon Sep 17 00:00:00 2001 From: Josh Don Date: Mon, 18 Oct 2021 13:34:28 -0700 Subject: sched/core: Forced idle accounting Adds accounting for "forced idle" time, which is time where a cookie'd task forces its SMT sibling to idle, despite the presence of runnable tasks. Forced idle time is one means to measure the cost of enabling core scheduling (ie. the capacity lost due to the need to force idle). Forced idle time is attributed to the thread responsible for causing the forced idle. A few details: - Forced idle time is displayed via /proc/PID/sched. It also requires that schedstats is enabled. - Forced idle is only accounted when a sibling hyperthread is held idle despite the presence of runnable tasks. No time is charged if a sibling is idle but has no runnable tasks. - Tasks with 0 cookie are never charged forced idle. - For SMT > 2, we scale the amount of forced idle charged based on the number of forced idle siblings. Additionally, we split the time up and evenly charge it to all running tasks, as each is equally responsible for the forced idle. Signed-off-by: Josh Don Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211018203428.2025792-1-joshdon@google.com --- include/linux/sched.h | 4 +++ kernel/sched/core.c | 82 +++++++++++++++++++++++++++++++++++------------ kernel/sched/core_sched.c | 66 +++++++++++++++++++++++++++++++++++++- kernel/sched/debug.c | 4 +++ kernel/sched/fair.c | 2 +- kernel/sched/sched.h | 32 ++++++++++++++++-- 6 files changed, 166 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..d2e261adb8ea 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -523,7 +523,11 @@ struct sched_statistics { u64 nr_wakeups_affine_attempts; u64 nr_wakeups_passive; u64 nr_wakeups_idle; + +#ifdef CONFIG_SCHED_CORE + u64 core_forceidle_sum; #endif +#endif /* CONFIG_SCHEDSTATS */ } ____cacheline_aligned; struct sched_entity { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c9b0fda64ac..beaa8be6241e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -144,7 +144,7 @@ static inline bool __sched_core_less(struct task_struct *a, struct task_struct * return false; /* flip prio, so high prio is leftmost */ - if (prio_less(b, a, task_rq(a)->core->core_forceidle)) + if (prio_less(b, a, !!task_rq(a)->core->core_forceidle_count)) return true; return false; @@ -181,15 +181,23 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p) rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less); } -void sched_core_dequeue(struct rq *rq, struct task_struct *p) +void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { rq->core->core_task_seq++; - if (!sched_core_enqueued(p)) - return; + if (sched_core_enqueued(p)) { + rb_erase(&p->core_node, &rq->core_tree); + RB_CLEAR_NODE(&p->core_node); + } - rb_erase(&p->core_node, &rq->core_tree); - RB_CLEAR_NODE(&p->core_node); + /* + * Migrating the last task off the cpu, with the cpu in forced idle + * state. Reschedule to create an accounting edge for forced idle, + * and re-examine whether the core is still in forced idle state. + */ + if (!(flags & DEQUEUE_SAVE) && rq->nr_running == 1 && + rq->core->core_forceidle_count && rq->curr == rq->idle) + resched_curr(rq); } /* @@ -280,6 +288,8 @@ static void __sched_core_flip(bool enabled) for_each_cpu(t, smt_mask) cpu_rq(t)->core_enabled = enabled; + cpu_rq(cpu)->core->core_forceidle_start = 0; + sched_core_unlock(cpu, &flags); cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask); @@ -364,7 +374,8 @@ void sched_core_put(void) #else /* !CONFIG_SCHED_CORE */ static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { } -static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p) { } +static inline void +sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } #endif /* CONFIG_SCHED_CORE */ @@ -2005,7 +2016,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) { if (sched_core_enabled(rq)) - sched_core_dequeue(rq, p); + sched_core_dequeue(rq, p, flags); if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); @@ -5244,6 +5255,7 @@ void scheduler_tick(void) if (sched_feat(LATENCY_WARN)) resched_latency = cpu_resched_latency(rq); calc_global_load_tick(rq); + sched_core_tick(rq); rq_unlock(rq, &rf); @@ -5656,6 +5668,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *next, *p, *max = NULL; const struct cpumask *smt_mask; bool fi_before = false; + bool core_clock_updated = (rq == rq->core); unsigned long cookie; int i, cpu, occ = 0; struct rq *rq_i; @@ -5708,10 +5721,18 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* reset state */ rq->core->core_cookie = 0UL; - if (rq->core->core_forceidle) { + if (rq->core->core_forceidle_count) { + if (!core_clock_updated) { + update_rq_clock(rq->core); + core_clock_updated = true; + } + sched_core_account_forceidle(rq); + /* reset after accounting force idle */ + rq->core->core_forceidle_start = 0; + rq->core->core_forceidle_count = 0; + rq->core->core_forceidle_occupation = 0; need_sync = true; fi_before = true; - rq->core->core_forceidle = false; } /* @@ -5753,7 +5774,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) for_each_cpu_wrap(i, smt_mask, cpu) { rq_i = cpu_rq(i); - if (i != cpu) + /* + * Current cpu always has its clock updated on entrance to + * pick_next_task(). If the current cpu is not the core, + * the core may also have been updated above. + */ + if (i != cpu && (rq_i != rq->core || !core_clock_updated)) update_rq_clock(rq_i); p = rq_i->core_pick = pick_task(rq_i); @@ -5783,7 +5809,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) if (p == rq_i->idle) { if (rq_i->nr_running) { - rq->core->core_forceidle = true; + rq->core->core_forceidle_count++; if (!fi_before) rq->core->core_forceidle_seq++; } @@ -5792,6 +5818,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } } + if (schedstat_enabled() && rq->core->core_forceidle_count) { + if (cookie) + rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_occupation = occ; + } + rq->core->core_pick_seq = rq->core->core_task_seq; next = rq->core_pick; rq->core_sched_seq = rq->core->core_pick_seq; @@ -5828,8 +5860,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * 1 0 1 * 1 1 0 */ - if (!(fi_before && rq->core->core_forceidle)) - task_vruntime_update(rq_i, rq_i->core_pick, rq->core->core_forceidle); + if (!(fi_before && rq->core->core_forceidle_count)) + task_vruntime_update(rq_i, rq_i->core_pick, !!rq->core->core_forceidle_count); rq_i->core_pick->core_occupation = occ; @@ -6033,11 +6065,19 @@ static void sched_core_cpu_deactivate(unsigned int cpu) goto unlock; /* copy the shared state to the new leader */ - core_rq->core_task_seq = rq->core_task_seq; - core_rq->core_pick_seq = rq->core_pick_seq; - core_rq->core_cookie = rq->core_cookie; - core_rq->core_forceidle = rq->core_forceidle; - core_rq->core_forceidle_seq = rq->core_forceidle_seq; + core_rq->core_task_seq = rq->core_task_seq; + core_rq->core_pick_seq = rq->core_pick_seq; + core_rq->core_cookie = rq->core_cookie; + core_rq->core_forceidle_count = rq->core_forceidle_count; + core_rq->core_forceidle_seq = rq->core_forceidle_seq; + core_rq->core_forceidle_occupation = rq->core_forceidle_occupation; + + /* + * Accounting edge for forced idle is handled in pick_next_task(). + * Don't need another one here, since the hotplug thread shouldn't + * have a cookie. + */ + core_rq->core_forceidle_start = 0; /* install new leader */ for_each_cpu(t, smt_mask) { @@ -9413,7 +9453,9 @@ void __init sched_init(void) rq->core_pick = NULL; rq->core_enabled = 0; rq->core_tree = RB_ROOT; - rq->core_forceidle = false; + rq->core_forceidle_count = 0; + rq->core_forceidle_occupation = 0; + rq->core_forceidle_start = 0; rq->core_cookie = 0UL; #endif diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 517f72b008f5..1fb45672ec85 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -73,7 +73,7 @@ static unsigned long sched_core_update_cookie(struct task_struct *p, enqueued = sched_core_enqueued(p); if (enqueued) - sched_core_dequeue(rq, p); + sched_core_dequeue(rq, p, DEQUEUE_SAVE); old_cookie = p->core_cookie; p->core_cookie = cookie; @@ -85,6 +85,10 @@ static unsigned long sched_core_update_cookie(struct task_struct *p, * If task is currently running, it may not be compatible anymore after * the cookie change, so enter the scheduler on its CPU to schedule it * away. + * + * Note that it is possible that as a result of this cookie change, the + * core has now entered/left forced idle state. Defer accounting to the + * next scheduling edge, rather than always forcing a reschedule here. */ if (task_running(rq, p)) resched_curr(rq); @@ -232,3 +236,63 @@ out: return err; } +#ifdef CONFIG_SCHEDSTATS + +/* REQUIRES: rq->core's clock recently updated. */ +void __sched_core_account_forceidle(struct rq *rq) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu_of(rq)); + u64 delta, now = rq_clock(rq->core); + struct rq *rq_i; + struct task_struct *p; + int i; + + lockdep_assert_rq_held(rq); + + WARN_ON_ONCE(!rq->core->core_forceidle_count); + + if (rq->core->core_forceidle_start == 0) + return; + + delta = now - rq->core->core_forceidle_start; + if (unlikely((s64)delta <= 0)) + return; + + rq->core->core_forceidle_start = now; + + if (WARN_ON_ONCE(!rq->core->core_forceidle_occupation)) { + /* can't be forced idle without a running task */ + } else if (rq->core->core_forceidle_count > 1 || + rq->core->core_forceidle_occupation > 1) { + /* + * For larger SMT configurations, we need to scale the charged + * forced idle amount since there can be more than one forced + * idle sibling and more than one running cookied task. + */ + delta *= rq->core->core_forceidle_count; + delta = div_u64(delta, rq->core->core_forceidle_occupation); + } + + for_each_cpu(i, smt_mask) { + rq_i = cpu_rq(i); + p = rq_i->core_pick ?: rq_i->curr; + + if (!p->core_cookie) + continue; + + __schedstat_add(p->stats.core_forceidle_sum, delta); + } +} + +void __sched_core_tick(struct rq *rq) +{ + if (!rq->core->core_forceidle_count) + return; + + if (rq != rq->core) + update_rq_clock(rq->core); + + __sched_core_account_forceidle(rq); +} + +#endif /* CONFIG_SCHEDSTATS */ diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 7dcbaa31c5d9..aa29211de1bf 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -1023,6 +1023,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, __PN(avg_atom); __PN(avg_per_cpu); + +#ifdef CONFIG_SCHED_CORE + PN_SCHEDSTAT(core_forceidle_sum); +#endif } __P(nr_switches); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6e476f6d9435..884f29d07963 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -11068,7 +11068,7 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr) * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check * if we need to give up the CPU. */ - if (rq->core->core_forceidle && rq->cfs.nr_running == 1 && + if (rq->core->core_forceidle_count && rq->cfs.nr_running == 1 && __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE)) resched_curr(rq); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0e66749486e7..eb971151e7e4 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1111,8 +1111,10 @@ struct rq { unsigned int core_task_seq; unsigned int core_pick_seq; unsigned long core_cookie; - unsigned char core_forceidle; + unsigned int core_forceidle_count; unsigned int core_forceidle_seq; + unsigned int core_forceidle_occupation; + u64 core_forceidle_start; #endif }; @@ -1253,7 +1255,7 @@ static inline bool sched_core_enqueued(struct task_struct *p) } extern void sched_core_enqueue(struct rq *rq, struct task_struct *p); -extern void sched_core_dequeue(struct rq *rq, struct task_struct *p); +extern void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags); extern void sched_core_get(void); extern void sched_core_put(void); @@ -1854,6 +1856,32 @@ static inline void flush_smp_call_function_from_idle(void) { } #include "stats.h" #include "autogroup.h" +#if defined(CONFIG_SCHED_CORE) && defined(CONFIG_SCHEDSTATS) + +extern void __sched_core_account_forceidle(struct rq *rq); + +static inline void sched_core_account_forceidle(struct rq *rq) +{ + if (schedstat_enabled()) + __sched_core_account_forceidle(rq); +} + +extern void __sched_core_tick(struct rq *rq); + +static inline void sched_core_tick(struct rq *rq) +{ + if (sched_core_enabled(rq) && schedstat_enabled()) + __sched_core_tick(rq); +} + +#else + +static inline void sched_core_account_forceidle(struct rq *rq) {} + +static inline void sched_core_tick(struct rq *rq) {} + +#endif /* CONFIG_SCHED_CORE && CONFIG_SCHEDSTATS */ + #ifdef CONFIG_CGROUP_SCHED /* -- cgit v1.2.3 From cb0e52b7748737b2cf6481fdd9b920ce7e1ebbdf Mon Sep 17 00:00:00 2001 From: Brian Chen Date: Wed, 10 Nov 2021 21:33:12 +0000 Subject: psi: Fix PSI_MEM_FULL state when tasks are in memstall and doing reclaim We've noticed cases where tasks in a cgroup are stalled on memory but there is little memory FULL pressure since tasks stay on the runqueue in reclaim. A simple example involves a single threaded program that keeps leaking and touching large amounts of memory. It runs in a cgroup with swap enabled, memory.high set at 10M and cpu.max ratio set at 5%. Though there is significant CPU pressure and memory SOME, there is barely any memory FULL since the task enters reclaim and stays on the runqueue. However, this memory-bound task is effectively stalled on memory and we expect memory FULL to match memory SOME in this scenario. The code is confused about memstall && running, thinking there is a stalled task and a productive task when there's only one task: a reclaimer that's counted as both. To fix this, we redefine the condition for PSI_MEM_FULL to check that all running tasks are in an active memstall instead of checking that there are no running tasks. case PSI_MEM_FULL: - return unlikely(tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]); + return unlikely(tasks[NR_MEMSTALL] && + tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); This will capture reclaimers. It will also capture tasks that called psi_memstall_enter() and are about to sleep, but this should be negligible noise. Signed-off-by: Brian Chen Signed-off-by: Peter Zijlstra (Intel) Acked-by: Johannes Weiner Link: https://lore.kernel.org/r/20211110213312.310243-1-brianchen118@gmail.com --- include/linux/psi_types.h | 13 ++++++++++++- kernel/sched/psi.c | 45 ++++++++++++++++++++++++++++----------------- kernel/sched/stats.h | 5 ++++- 3 files changed, 44 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index bf50068d5d4b..516c0fe836fd 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -22,7 +22,17 @@ enum psi_task_count { * don't have to special case any state tracking for it. */ NR_ONCPU, - NR_PSI_TASK_COUNTS = 4, + /* + * For IO and CPU stalls the presence of running/oncpu tasks + * in the domain means a partial rather than a full stall. + * For memory it's not so simple because of page reclaimers: + * they are running/oncpu while representing a stall. To tell + * whether a domain has productivity left or not, we need to + * distinguish between regular running (i.e. productive) + * threads and memstall ones. + */ + NR_MEMSTALL_RUNNING, + NR_PSI_TASK_COUNTS = 5, }; /* Task state bitmasks */ @@ -30,6 +40,7 @@ enum psi_task_count { #define TSK_MEMSTALL (1 << NR_MEMSTALL) #define TSK_RUNNING (1 << NR_RUNNING) #define TSK_ONCPU (1 << NR_ONCPU) +#define TSK_MEMSTALL_RUNNING (1 << NR_MEMSTALL_RUNNING) /* Resources that workloads could be stalled on */ enum psi_res { diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 3397fa001157..a679613a7cb7 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -35,13 +35,19 @@ * delayed on that resource such that nobody is advancing and the CPU * goes idle. This leaves both workload and CPU unproductive. * - * Naturally, the FULL state doesn't exist for the CPU resource at the - * system level, but exist at the cgroup level, means all non-idle tasks - * in a cgroup are delayed on the CPU resource which used by others outside - * of the cgroup or throttled by the cgroup cpu.max configuration. - * * SOME = nr_delayed_tasks != 0 - * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * FULL = nr_delayed_tasks != 0 && nr_productive_tasks == 0 + * + * What it means for a task to be productive is defined differently + * for each resource. For IO, productive means a running task. For + * memory, productive means a running task that isn't a reclaimer. For + * CPU, productive means an oncpu task. + * + * Naturally, the FULL state doesn't exist for the CPU resource at the + * system level, but exist at the cgroup level. At the cgroup level, + * FULL means all non-idle tasks in the cgroup are delayed on the CPU + * resource which is being used by others outside of the cgroup or + * throttled by the cgroup cpu.max configuration. * * The percentage of wallclock time spent in those compound stall * states gives pressure numbers between 0 and 100 for each resource, @@ -82,13 +88,13 @@ * * threads = min(nr_nonidle_tasks, nr_cpus) * SOME = min(nr_delayed_tasks / threads, 1) - * FULL = (threads - min(nr_running_tasks, threads)) / threads + * FULL = (threads - min(nr_productive_tasks, threads)) / threads * * For the 257 number crunchers on 256 CPUs, this yields: * * threads = min(257, 256) * SOME = min(1 / 256, 1) = 0.4% - * FULL = (256 - min(257, 256)) / 256 = 0% + * FULL = (256 - min(256, 256)) / 256 = 0% * * For the 1 out of 4 memory-delayed tasks, this yields: * @@ -113,7 +119,7 @@ * For each runqueue, we track: * * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) - * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_productive_tasks[cpu]) * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) * * and then periodically aggregate: @@ -234,7 +240,8 @@ static bool test_state(unsigned int *tasks, enum psi_states state) case PSI_MEM_SOME: return unlikely(tasks[NR_MEMSTALL]); case PSI_MEM_FULL: - return unlikely(tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]); + return unlikely(tasks[NR_MEMSTALL] && + tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]); case PSI_CPU_SOME: return unlikely(tasks[NR_RUNNING] > tasks[NR_ONCPU]); case PSI_CPU_FULL: @@ -711,10 +718,11 @@ static void psi_group_change(struct psi_group *group, int cpu, if (groupc->tasks[t]) { groupc->tasks[t]--; } else if (!psi_bug) { - printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u] clear=%x set=%x\n", + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u %u %u] clear=%x set=%x\n", cpu, t, groupc->tasks[0], groupc->tasks[1], groupc->tasks[2], - groupc->tasks[3], clear, set); + groupc->tasks[3], groupc->tasks[4], + clear, set); psi_bug = 1; } } @@ -854,12 +862,15 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next, int clear = TSK_ONCPU, set = 0; /* - * When we're going to sleep, psi_dequeue() lets us handle - * TSK_RUNNING and TSK_IOWAIT here, where we can combine it - * with TSK_ONCPU and save walking common ancestors twice. + * When we're going to sleep, psi_dequeue() lets us + * handle TSK_RUNNING, TSK_MEMSTALL_RUNNING and + * TSK_IOWAIT here, where we can combine it with + * TSK_ONCPU and save walking common ancestors twice. */ if (sleep) { clear |= TSK_RUNNING; + if (prev->in_memstall) + clear |= TSK_MEMSTALL_RUNNING; if (prev->in_iowait) set |= TSK_IOWAIT; } @@ -908,7 +919,7 @@ void psi_memstall_enter(unsigned long *flags) rq = this_rq_lock_irq(&rf); current->in_memstall = 1; - psi_task_change(current, 0, TSK_MEMSTALL); + psi_task_change(current, 0, TSK_MEMSTALL | TSK_MEMSTALL_RUNNING); rq_unlock_irq(rq, &rf); } @@ -937,7 +948,7 @@ void psi_memstall_leave(unsigned long *flags) rq = this_rq_lock_irq(&rf); current->in_memstall = 0; - psi_task_change(current, TSK_MEMSTALL, 0); + psi_task_change(current, TSK_MEMSTALL | TSK_MEMSTALL_RUNNING, 0); rq_unlock_irq(rq, &rf); } diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index cfb0893a83d4..3a3c826dd83a 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -118,6 +118,9 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup) if (static_branch_likely(&psi_disabled)) return; + if (p->in_memstall) + set |= TSK_MEMSTALL_RUNNING; + if (!wakeup || p->sched_psi_wake_requeue) { if (p->in_memstall) set |= TSK_MEMSTALL; @@ -148,7 +151,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep) return; if (p->in_memstall) - clear |= TSK_MEMSTALL; + clear |= (TSK_MEMSTALL | TSK_MEMSTALL_RUNNING); psi_task_change(p, clear, 0); } -- cgit v1.2.3 From ff083a2d972f56bebfd82409ca62e5dfce950961 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:22 +0000 Subject: perf: Protect perf_guest_cbs with RCU Protect perf_guest_cbs with RCU to fix multiple possible errors. Luckily, all paths that read perf_guest_cbs already require RCU protection, e.g. to protect the callback chains, so only the direct perf_guest_cbs touchpoints need to be modified. Bug #1 is a simple lack of WRITE_ONCE/READ_ONCE behavior to ensure perf_guest_cbs isn't reloaded between a !NULL check and a dereference. Fixed via the READ_ONCE() in rcu_dereference(). Bug #2 is that on weakly-ordered architectures, updates to the callbacks themselves are not guaranteed to be visible before the pointer is made visible to readers. Fixed by the smp_store_release() in rcu_assign_pointer() when the new pointer is non-NULL. Bug #3 is that, because the callbacks are global, it's possible for readers to run in parallel with an unregisters, and thus a module implementing the callbacks can be unloaded while readers are in flight, resulting in a use-after-free. Fixed by a synchronize_rcu() call when unregistering callbacks. Bug #1 escaped notice because it's extremely unlikely a compiler will reload perf_guest_cbs in this sequence. perf_guest_cbs does get reloaded for future derefs, e.g. for ->is_user_mode(), but the ->is_in_guest() guard all but guarantees the consumer will win the race, e.g. to nullify perf_guest_cbs, KVM has to completely exit the guest and teardown down all VMs before KVM start its module unload / unregister sequence. This also makes it all but impossible to encounter bug #3. Bug #2 has not been a problem because all architectures that register callbacks are strongly ordered and/or have a static set of callbacks. But with help, unloading kvm_intel can trigger bug #1 e.g. wrapping perf_guest_cbs with READ_ONCE in perf_misc_flags() while spamming kvm_intel module load/unload leads to: BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP CPU: 6 PID: 1825 Comm: stress Not tainted 5.14.0-rc2+ #459 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:perf_misc_flags+0x1c/0x70 Call Trace: perf_prepare_sample+0x53/0x6b0 perf_event_output_forward+0x67/0x160 __perf_event_overflow+0x52/0xf0 handle_pmi_common+0x207/0x300 intel_pmu_handle_irq+0xcf/0x410 perf_event_nmi_handler+0x28/0x50 nmi_handle+0xc7/0x260 default_do_nmi+0x6b/0x170 exc_nmi+0x103/0x130 asm_exc_nmi+0x76/0xbf Fixes: 39447b386c84 ("perf: Enhance perf to allow for guest statistic collection from host") Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211111020738.2512932-2-seanjc@google.com --- arch/arm/kernel/perf_callchain.c | 17 +++++++++++------ arch/arm64/kernel/perf_callchain.c | 18 ++++++++++++------ arch/csky/kernel/perf_callchain.c | 6 ++++-- arch/nds32/kernel/perf_event_cpu.c | 17 +++++++++++------ arch/riscv/kernel/perf_callchain.c | 7 +++++-- arch/x86/events/core.c | 17 +++++++++++------ arch/x86/events/intel/core.c | 9 ++++++--- include/linux/perf_event.h | 13 ++++++++++++- kernel/events/core.c | 13 ++++++++++--- 9 files changed, 82 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c index 3b69a76d341e..1626dfc6f6ce 100644 --- a/arch/arm/kernel/perf_callchain.c +++ b/arch/arm/kernel/perf_callchain.c @@ -62,9 +62,10 @@ user_backtrace(struct frame_tail __user *tail, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct frame_tail __user *tail; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* We don't support guest os callchain now */ return; } @@ -98,9 +99,10 @@ callchain_trace(struct stackframe *fr, void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stackframe fr; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* We don't support guest os callchain now */ return; } @@ -111,18 +113,21 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re unsigned long perf_instruction_pointer(struct pt_regs *regs) { - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - return perf_guest_cbs->get_guest_ip(); + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + if (guest_cbs && guest_cbs->is_in_guest()) + return guest_cbs->get_guest_ip(); return instruction_pointer(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); int misc = 0; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - if (perf_guest_cbs->is_user_mode()) + if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs->is_user_mode()) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 4a72c2727309..86d9f2013172 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -102,7 +102,9 @@ compat_user_backtrace(struct compat_frame_tail __user *tail, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + if (guest_cbs && guest_cbs->is_in_guest()) { /* We don't support guest os callchain now */ return; } @@ -147,9 +149,10 @@ static bool callchain_trace(void *data, unsigned long pc) void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stackframe frame; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* We don't support guest os callchain now */ return; } @@ -160,18 +163,21 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, unsigned long perf_instruction_pointer(struct pt_regs *regs) { - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - return perf_guest_cbs->get_guest_ip(); + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + if (guest_cbs && guest_cbs->is_in_guest()) + return guest_cbs->get_guest_ip(); return instruction_pointer(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); int misc = 0; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - if (perf_guest_cbs->is_user_mode()) + if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs->is_user_mode()) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; diff --git a/arch/csky/kernel/perf_callchain.c b/arch/csky/kernel/perf_callchain.c index ab55e98ee8f6..35318a635a5f 100644 --- a/arch/csky/kernel/perf_callchain.c +++ b/arch/csky/kernel/perf_callchain.c @@ -86,10 +86,11 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); unsigned long fp = 0; /* C-SKY does not support virtualization. */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + if (guest_cbs && guest_cbs->is_in_guest()) return; fp = regs->regs[4]; @@ -110,10 +111,11 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stackframe fr; /* C-SKY does not support virtualization. */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { pr_warn("C-SKY does not support perf in guest mode!"); return; } diff --git a/arch/nds32/kernel/perf_event_cpu.c b/arch/nds32/kernel/perf_event_cpu.c index 0ce6f9f307e6..f38791960781 100644 --- a/arch/nds32/kernel/perf_event_cpu.c +++ b/arch/nds32/kernel/perf_event_cpu.c @@ -1363,6 +1363,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); unsigned long fp = 0; unsigned long gp = 0; unsigned long lp = 0; @@ -1371,7 +1372,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, leaf_fp = 0; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* We don't support guest os callchain now */ return; } @@ -1479,9 +1480,10 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stackframe fr; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* We don't support guest os callchain now */ return; } @@ -1493,20 +1495,23 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, unsigned long perf_instruction_pointer(struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + /* However, NDS32 does not support virtualization */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - return perf_guest_cbs->get_guest_ip(); + if (guest_cbs && guest_cbs->is_in_guest()) + return guest_cbs->get_guest_ip(); return instruction_pointer(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); int misc = 0; /* However, NDS32 does not support virtualization */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - if (perf_guest_cbs->is_user_mode()) + if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs->is_user_mode()) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index 0bb1854dce83..8ecfc4c128bc 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -56,10 +56,11 @@ static unsigned long user_backtrace(struct perf_callchain_entry_ctx *entry, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); unsigned long fp = 0; /* RISC-V does not support perf in guest mode. */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) + if (guest_cbs && guest_cbs->is_in_guest()) return; fp = regs->s0; @@ -78,8 +79,10 @@ static bool fill_callchain(void *entry, unsigned long pc) void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + /* RISC-V does not support perf in guest mode. */ - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { pr_warn("RISC-V does not support perf in guest mode!"); return; } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 38b2c779146f..32cec290d3ad 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2768,10 +2768,11 @@ static bool perf_hw_regs(struct pt_regs *regs) void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct unwind_state state; unsigned long addr; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ return; } @@ -2871,10 +2872,11 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stack_frame frame; const struct stack_frame __user *fp; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->is_in_guest()) { /* TODO: We don't support guest os callchain now */ return; } @@ -2951,18 +2953,21 @@ static unsigned long code_segment_base(struct pt_regs *regs) unsigned long perf_instruction_pointer(struct pt_regs *regs) { - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) - return perf_guest_cbs->get_guest_ip(); + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + if (guest_cbs && guest_cbs->is_in_guest()) + return guest_cbs->get_guest_ip(); return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); int misc = 0; - if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) { - if (perf_guest_cbs->is_user_mode()) + if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs->is_user_mode()) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 42cf01ecdd13..2258e02ca350 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2837,6 +2837,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) { struct perf_sample_data data; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_guest_info_callbacks *guest_cbs; int bit; int handled = 0; u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl); @@ -2903,9 +2904,11 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) { handled++; - if (unlikely(perf_guest_cbs && perf_guest_cbs->is_in_guest() && - perf_guest_cbs->handle_intel_pt_intr)) - perf_guest_cbs->handle_intel_pt_intr(); + + guest_cbs = perf_get_guest_cbs(); + if (unlikely(guest_cbs && guest_cbs->is_in_guest() && + guest_cbs->handle_intel_pt_intr)) + guest_cbs->handle_intel_pt_intr(); else intel_pt_interrupt(); } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0dcfd265beed..318c489b735b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1240,7 +1240,18 @@ extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); -extern struct perf_guest_info_callbacks *perf_guest_cbs; +extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; +static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) +{ + /* + * Callbacks are RCU-protected and must be READ_ONCE to avoid reloading + * the callbacks between a !NULL check and dereferences, to ensure + * pending stores/changes to the callback pointers are visible before a + * non-NULL perf_guest_cbs is visible to readers, and to prevent a + * module from unloading callbacks while readers are active. + */ + return rcu_dereference(perf_guest_cbs); +} extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); diff --git a/kernel/events/core.c b/kernel/events/core.c index 523106a506ee..c552e1bfcaea 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6526,18 +6526,25 @@ static void perf_pending_event(struct irq_work *entry) * Later on, we might change it to a list if there is * another virtualization implementation supporting the callbacks. */ -struct perf_guest_info_callbacks *perf_guest_cbs; +struct perf_guest_info_callbacks __rcu *perf_guest_cbs; int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) { - perf_guest_cbs = cbs; + if (WARN_ON_ONCE(rcu_access_pointer(perf_guest_cbs))) + return -EBUSY; + + rcu_assign_pointer(perf_guest_cbs, cbs); return 0; } EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) { - perf_guest_cbs = NULL; + if (WARN_ON_ONCE(rcu_access_pointer(perf_guest_cbs) != cbs)) + return -EINVAL; + + rcu_assign_pointer(perf_guest_cbs, NULL); + synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); -- cgit v1.2.3 From 2934e3d09350c1a7ca2433fbeabfcd831e48a575 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:25 +0000 Subject: perf: Stop pretending that perf can handle multiple guest callbacks Drop the 'int' return value from the perf (un)register callbacks helpers and stop pretending perf can support multiple callbacks. The 'int' returns are not future proofing anything as none of the callers take action on an error. It's also not obvious that there will ever be co-tenant hypervisors, and if there are, that allowing multiple callbacks to be registered is desirable or even correct. Opportunistically rename callbacks=>cbs in the affected declarations to match their definitions. No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-5-seanjc@google.com --- arch/arm64/include/asm/kvm_host.h | 4 ++-- arch/arm64/kvm/perf.c | 8 ++++---- include/linux/perf_event.h | 12 ++++++------ kernel/events/core.c | 15 ++++----------- 4 files changed, 16 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 2a5f7f38006f..f680f303ba7c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -675,8 +675,8 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); int kvm_handle_mmio_return(struct kvm_vcpu *vcpu); int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa); -int kvm_perf_init(void); -int kvm_perf_teardown(void); +void kvm_perf_init(void); +void kvm_perf_teardown(void); long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index c84fe24b2ea1..a0d660cf889e 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -48,12 +48,12 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { .get_guest_ip = kvm_get_guest_ip, }; -int kvm_perf_init(void) +void kvm_perf_init(void) { - return perf_register_guest_info_callbacks(&kvm_guest_cbs); + perf_register_guest_info_callbacks(&kvm_guest_cbs); } -int kvm_perf_teardown(void) +void kvm_perf_teardown(void) { - return perf_unregister_guest_info_callbacks(&kvm_guest_cbs); + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 318c489b735b..98c204488496 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1252,8 +1252,8 @@ static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) */ return rcu_dereference(perf_guest_cbs); } -extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); -extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks); +extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); +extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); @@ -1497,10 +1497,10 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } -static inline int perf_register_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } -static inline int perf_unregister_guest_info_callbacks -(struct perf_guest_info_callbacks *callbacks) { return 0; } +static inline void perf_register_guest_info_callbacks +(struct perf_guest_info_callbacks *cbs) { } +static inline void perf_unregister_guest_info_callbacks +(struct perf_guest_info_callbacks *cbs) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } diff --git a/kernel/events/core.c b/kernel/events/core.c index c552e1bfcaea..17e5b20762c5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6521,31 +6521,24 @@ static void perf_pending_event(struct irq_work *entry) perf_swevent_put_recursion_context(rctx); } -/* - * We assume there is only KVM supporting the callbacks. - * Later on, we might change it to a list if there is - * another virtualization implementation supporting the callbacks. - */ struct perf_guest_info_callbacks __rcu *perf_guest_cbs; -int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) { if (WARN_ON_ONCE(rcu_access_pointer(perf_guest_cbs))) - return -EBUSY; + return; rcu_assign_pointer(perf_guest_cbs, cbs); - return 0; } EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); -int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) +void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) { if (WARN_ON_ONCE(rcu_access_pointer(perf_guest_cbs) != cbs)) - return -EINVAL; + return; rcu_assign_pointer(perf_guest_cbs, NULL); synchronize_rcu(); - return 0; } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); -- cgit v1.2.3 From b9f5621c9547dd787900f005a9e1c3d5712de512 Mon Sep 17 00:00:00 2001 From: Like Xu Date: Thu, 11 Nov 2021 02:07:27 +0000 Subject: perf/core: Rework guest callbacks to prepare for static_call support To prepare for using static_calls to optimize perf's guest callbacks, replace ->is_in_guest and ->is_user_mode with a new multiplexed hook ->state, tweak ->handle_intel_pt_intr to play nice with being called when there is no active guest, and drop "guest" from ->get_guest_ip. Return '0' from ->state and ->handle_intel_pt_intr to indicate "not in guest" so that DEFINE_STATIC_CALL_RET0 can be used to define the static calls, i.e. no callback == !guest. [sean: extracted from static_call patch, fixed get_ip() bug, wrote changelog] Suggested-by: Peter Zijlstra (Intel) Originally-by: Peter Zijlstra (Intel) Signed-off-by: Like Xu Signed-off-by: Zhu Lingshan Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Boris Ostrovsky Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-7-seanjc@google.com --- arch/arm64/kernel/perf_callchain.c | 13 +++++++------ arch/arm64/kvm/perf.c | 35 ++++++++++++++------------------- arch/x86/events/core.c | 13 +++++++------ arch/x86/events/intel/core.c | 5 +---- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/pmu.c | 2 +- arch/x86/kvm/x86.c | 40 +++++++++++++++++++++----------------- arch/x86/xen/pmu.c | 32 +++++++++++++----------------- include/linux/perf_event.h | 10 ++++++---- 9 files changed, 73 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 86d9f2013172..274dc3e11b6d 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -104,7 +104,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->state()) { /* We don't support guest os callchain now */ return; } @@ -152,7 +152,7 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stackframe frame; - if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->state()) { /* We don't support guest os callchain now */ return; } @@ -165,8 +165,8 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - if (guest_cbs && guest_cbs->is_in_guest()) - return guest_cbs->get_guest_ip(); + if (guest_cbs && guest_cbs->state()) + return guest_cbs->get_ip(); return instruction_pointer(regs); } @@ -174,10 +174,11 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs) unsigned long perf_misc_flags(struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0; int misc = 0; - if (guest_cbs && guest_cbs->is_in_guest()) { - if (guest_cbs->is_user_mode()) + if (guest_state) { + if (guest_state & PERF_GUEST_USER) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index a0d660cf889e..dfa9bce8559e 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -13,39 +13,34 @@ DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available); -static int kvm_is_in_guest(void) +static unsigned int kvm_guest_state(void) { - return kvm_get_running_vcpu() != NULL; -} - -static int kvm_is_user_mode(void) -{ - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + unsigned int state; - vcpu = kvm_get_running_vcpu(); + if (!vcpu) + return 0; - if (vcpu) - return !vcpu_mode_priv(vcpu); + state = PERF_GUEST_ACTIVE; + if (!vcpu_mode_priv(vcpu)) + state |= PERF_GUEST_USER; - return 0; + return state; } static unsigned long kvm_get_guest_ip(void) { - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_running_vcpu(); + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); - if (vcpu) - return *vcpu_pc(vcpu); + if (WARN_ON_ONCE(!vcpu)) + return 0; - return 0; + return *vcpu_pc(vcpu); } static struct perf_guest_info_callbacks kvm_guest_cbs = { - .is_in_guest = kvm_is_in_guest, - .is_user_mode = kvm_is_user_mode, - .get_guest_ip = kvm_get_guest_ip, + .state = kvm_guest_state, + .get_ip = kvm_get_guest_ip, }; void kvm_perf_init(void) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 32cec290d3ad..e29312a1003a 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2772,7 +2772,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re struct unwind_state state; unsigned long addr; - if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->state()) { /* TODO: We don't support guest os callchain now */ return; } @@ -2876,7 +2876,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs struct stack_frame frame; const struct stack_frame __user *fp; - if (guest_cbs && guest_cbs->is_in_guest()) { + if (guest_cbs && guest_cbs->state()) { /* TODO: We don't support guest os callchain now */ return; } @@ -2955,8 +2955,8 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - if (guest_cbs && guest_cbs->is_in_guest()) - return guest_cbs->get_guest_ip(); + if (guest_cbs && guest_cbs->state()) + return guest_cbs->get_ip(); return regs->ip + code_segment_base(regs); } @@ -2964,10 +2964,11 @@ unsigned long perf_instruction_pointer(struct pt_regs *regs) unsigned long perf_misc_flags(struct pt_regs *regs) { struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0; int misc = 0; - if (guest_cbs && guest_cbs->is_in_guest()) { - if (guest_cbs->is_user_mode()) + if (guest_state) { + if (guest_state & PERF_GUEST_USER) misc |= PERF_RECORD_MISC_GUEST_USER; else misc |= PERF_RECORD_MISC_GUEST_KERNEL; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2258e02ca350..7ff24d1ecdb7 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2906,10 +2906,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) handled++; guest_cbs = perf_get_guest_cbs(); - if (unlikely(guest_cbs && guest_cbs->is_in_guest() && - guest_cbs->handle_intel_pt_intr)) - guest_cbs->handle_intel_pt_intr(); - else + if (likely(!guest_cbs || !guest_cbs->handle_intel_pt_intr())) intel_pt_interrupt(); } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 41e858df5795..fa1b1a209945 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1895,7 +1895,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); -int kvm_is_in_guest(void); +unsigned int kvm_guest_state(void); void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 09873f6488f7..b2520b3e9e89 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -87,7 +87,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, * woken up. So we should wake it, but this is impossible from * NMI context. Do it from irq work instead. */ - if (!kvm_is_in_guest()) + if (!kvm_guest_state()) irq_work_queue(&pmc_to_pmu(pmc)->irq_work); else kvm_make_request(KVM_REQ_PMI, pmc->vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 760c4e3a8326..2011a1cfb42d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8472,44 +8472,48 @@ static void kvm_timer_init(void) DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); EXPORT_PER_CPU_SYMBOL_GPL(current_vcpu); -int kvm_is_in_guest(void) +unsigned int kvm_guest_state(void) { - return __this_cpu_read(current_vcpu) != NULL; -} + struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu); + unsigned int state; -static int kvm_is_user_mode(void) -{ - int user_mode = 3; + if (!vcpu) + return 0; - if (__this_cpu_read(current_vcpu)) - user_mode = static_call(kvm_x86_get_cpl)(__this_cpu_read(current_vcpu)); + state = PERF_GUEST_ACTIVE; + if (static_call(kvm_x86_get_cpl)(vcpu)) + state |= PERF_GUEST_USER; - return user_mode != 0; + return state; } -static unsigned long kvm_get_guest_ip(void) +static unsigned long kvm_guest_get_ip(void) { - unsigned long ip = 0; + struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu); - if (__this_cpu_read(current_vcpu)) - ip = kvm_rip_read(__this_cpu_read(current_vcpu)); + if (WARN_ON_ONCE(!vcpu)) + return 0; - return ip; + return kvm_rip_read(vcpu); } -static void kvm_handle_intel_pt_intr(void) +static unsigned int kvm_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu); + /* '0' on failure so that the !PT case can use a RET0 static call. */ + if (!vcpu) + return 0; + kvm_make_request(KVM_REQ_PMI, vcpu); __set_bit(MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT, (unsigned long *)&vcpu->arch.pmu.global_status); + return 1; } static struct perf_guest_info_callbacks kvm_guest_cbs = { - .is_in_guest = kvm_is_in_guest, - .is_user_mode = kvm_is_user_mode, - .get_guest_ip = kvm_get_guest_ip, + .state = kvm_guest_state, + .get_ip = kvm_guest_get_ip, .handle_intel_pt_intr = NULL, }; diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index e13b0b49fcdf..89dd6b1708b0 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -413,34 +413,29 @@ int pmu_apic_update(uint32_t val) } /* perf callbacks */ -static int xen_is_in_guest(void) +static unsigned int xen_guest_state(void) { const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + unsigned int state = 0; if (!xenpmu_data) { pr_warn_once("%s: pmudata not initialized\n", __func__); - return 0; + return state; } if (!xen_initial_domain() || (xenpmu_data->domain_id >= DOMID_SELF)) - return 0; + return state; - return 1; -} - -static int xen_is_user_mode(void) -{ - const struct xen_pmu_data *xenpmu_data = get_xenpmu_data(); + state |= PERF_GUEST_ACTIVE; - if (!xenpmu_data) { - pr_warn_once("%s: pmudata not initialized\n", __func__); - return 0; + if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV) { + if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER) + state |= PERF_GUEST_USER; + } else if (xenpmu_data->pmu.r.regs.cpl & 3) { + state |= PERF_GUEST_USER; } - if (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_PV) - return (xenpmu_data->pmu.pmu_flags & PMU_SAMPLE_USER); - else - return !!(xenpmu_data->pmu.r.regs.cpl & 3); + return state; } static unsigned long xen_get_guest_ip(void) @@ -456,9 +451,8 @@ static unsigned long xen_get_guest_ip(void) } static struct perf_guest_info_callbacks xen_guest_cbs = { - .is_in_guest = xen_is_in_guest, - .is_user_mode = xen_is_user_mode, - .get_guest_ip = xen_get_guest_ip, + .state = xen_guest_state, + .get_ip = xen_get_guest_ip, }; /* Convert registers from Xen's format to Linux' */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 98c204488496..5e6b346d62a7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -26,11 +26,13 @@ # include #endif +#define PERF_GUEST_ACTIVE 0x01 +#define PERF_GUEST_USER 0x02 + struct perf_guest_info_callbacks { - int (*is_in_guest)(void); - int (*is_user_mode)(void); - unsigned long (*get_guest_ip)(void); - void (*handle_intel_pt_intr)(void); + unsigned int (*state)(void); + unsigned long (*get_ip)(void); + unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_HAVE_HW_BREAKPOINT -- cgit v1.2.3 From 1c3430516b0732d923de9fd3bfb3e2e537eeb235 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:28 +0000 Subject: perf: Add wrappers for invoking guest callbacks Add helpers for the guest callbacks to prepare for burying the callbacks behind a Kconfig (it's a lot easier to provide a few stubs than to #ifdef piles of code), and also to prepare for converting the callbacks to static_call(). perf_instruction_pointer() in particular will have subtle semantics with static_call(), as the "no callbacks" case will return 0 if the callbacks are unregistered between querying guest state and getting the IP. Implement the change now to avoid a functional change when adding static_call() support, and because the new helper needs to return _something_ in this case. Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-8-seanjc@google.com --- arch/arm64/kernel/perf_callchain.c | 16 +++++----------- arch/x86/events/core.c | 15 +++++---------- arch/x86/events/intel/core.c | 5 +---- include/linux/perf_event.h | 24 ++++++++++++++++++++++++ 4 files changed, 35 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 274dc3e11b6d..db04a55cee7e 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -102,9 +102,7 @@ compat_user_backtrace(struct compat_frame_tail __user *tail, void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - - if (guest_cbs && guest_cbs->state()) { + if (perf_guest_state()) { /* We don't support guest os callchain now */ return; } @@ -149,10 +147,9 @@ static bool callchain_trace(void *data, unsigned long pc) void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stackframe frame; - if (guest_cbs && guest_cbs->state()) { + if (perf_guest_state()) { /* We don't support guest os callchain now */ return; } @@ -163,18 +160,15 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, unsigned long perf_instruction_pointer(struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - - if (guest_cbs && guest_cbs->state()) - return guest_cbs->get_ip(); + if (perf_guest_state()) + return perf_guest_get_ip(); return instruction_pointer(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0; + unsigned int guest_state = perf_guest_state(); int misc = 0; if (guest_state) { diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index e29312a1003a..620347398027 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2768,11 +2768,10 @@ static bool perf_hw_regs(struct pt_regs *regs) void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct unwind_state state; unsigned long addr; - if (guest_cbs && guest_cbs->state()) { + if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ return; } @@ -2872,11 +2871,10 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); struct stack_frame frame; const struct stack_frame __user *fp; - if (guest_cbs && guest_cbs->state()) { + if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ return; } @@ -2953,18 +2951,15 @@ static unsigned long code_segment_base(struct pt_regs *regs) unsigned long perf_instruction_pointer(struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - - if (guest_cbs && guest_cbs->state()) - return guest_cbs->get_ip(); + if (perf_guest_state()) + return perf_guest_get_ip(); return regs->ip + code_segment_base(regs); } unsigned long perf_misc_flags(struct pt_regs *regs) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - unsigned int guest_state = guest_cbs ? guest_cbs->state() : 0; + unsigned int guest_state = perf_guest_state(); int misc = 0; if (guest_state) { diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7ff24d1ecdb7..f7af8029664f 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2837,7 +2837,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) { struct perf_sample_data data; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct perf_guest_info_callbacks *guest_cbs; int bit; int handled = 0; u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl); @@ -2904,9 +2903,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (__test_and_clear_bit(GLOBAL_STATUS_TRACE_TOPAPMI_BIT, (unsigned long *)&status)) { handled++; - - guest_cbs = perf_get_guest_cbs(); - if (likely(!guest_cbs || !guest_cbs->handle_intel_pt_intr())) + if (!perf_guest_handle_intel_pt_intr()) intel_pt_interrupt(); } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5e6b346d62a7..346d5aff5804 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1254,6 +1254,30 @@ static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) */ return rcu_dereference(perf_guest_cbs); } +static inline unsigned int perf_guest_state(void) +{ + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + return guest_cbs ? guest_cbs->state() : 0; +} +static inline unsigned long perf_guest_get_ip(void) +{ + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + /* + * Arbitrarily return '0' in the unlikely scenario that the callbacks + * are unregistered between checking guest state and getting the IP. + */ + return guest_cbs ? guest_cbs->get_ip() : 0; +} +static inline unsigned int perf_guest_handle_intel_pt_intr(void) +{ + struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); + + if (guest_cbs && guest_cbs->handle_intel_pt_intr) + return guest_cbs->handle_intel_pt_intr(); + return 0; +} extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); -- cgit v1.2.3 From 2aef6f306b39bbe74e2287d6e2ee07c4867d87d0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:29 +0000 Subject: perf: Force architectures to opt-in to guest callbacks Introduce GUEST_PERF_EVENTS and require architectures to select it to allow registering and using guest callbacks in perf. This will hopefully make it more difficult for new architectures to add useless "support" for guest callbacks, e.g. via copy+paste. Stubbing out the helpers has the happy bonus of avoiding a load of perf_guest_cbs when GUEST_PERF_EVENTS=n on arm64/x86. Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-9-seanjc@google.com --- arch/arm64/kvm/Kconfig | 1 + arch/x86/kvm/Kconfig | 1 + arch/x86/xen/Kconfig | 1 + include/linux/perf_event.h | 6 ++++++ init/Kconfig | 4 ++++ kernel/events/core.c | 2 ++ 6 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ffcbe29395e..e9761d84f982 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ menuconfig KVM select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE select SCHED_INFO + select GUEST_PERF_EVENTS if PERF_EVENTS help Support hosting virtualized guest machines. diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 619186138176..47bdbe705a76 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -36,6 +36,7 @@ config KVM select KVM_MMIO select SCHED_INFO select PERF_EVENTS + select GUEST_PERF_EVENTS select HAVE_KVM_MSI select HAVE_KVM_CPU_RELAX_INTERCEPT select HAVE_KVM_NO_POLL diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 6bcd3d8ca6ac..85246dd9faa1 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -23,6 +23,7 @@ config XEN_PV select PARAVIRT_XXL select XEN_HAVE_PVMMU select XEN_HAVE_VPMU + select GUEST_PERF_EVENTS help Support running as a Xen PV guest. diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 346d5aff5804..ea47ef616ee0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1242,6 +1242,7 @@ extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); +#ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) { @@ -1280,6 +1281,11 @@ static inline unsigned int perf_guest_handle_intel_pt_intr(void) } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); +#else +static inline unsigned int perf_guest_state(void) { return 0; } +static inline unsigned long perf_guest_get_ip(void) { return 0; } +static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } +#endif /* CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); diff --git a/init/Kconfig b/init/Kconfig index 036b750e8d8a..72d40b3b5805 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1804,6 +1804,10 @@ config HAVE_PERF_EVENTS help See tools/perf/design.txt for details. +config GUEST_PERF_EVENTS + bool + depends on HAVE_PERF_EVENTS + config PERF_USE_VMALLOC bool help diff --git a/kernel/events/core.c b/kernel/events/core.c index 17e5b20762c5..5a3502cd5362 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6521,6 +6521,7 @@ static void perf_pending_event(struct irq_work *entry) perf_swevent_put_recursion_context(rctx); } +#ifdef CONFIG_GUEST_PERF_EVENTS struct perf_guest_info_callbacks __rcu *perf_guest_cbs; void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) @@ -6541,6 +6542,7 @@ void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) synchronize_rcu(); } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); +#endif static void perf_output_sample_regs(struct perf_output_handle *handle, -- cgit v1.2.3 From 87b940a0675e25261f022ac3e53e0dfff9cdb995 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:30 +0000 Subject: perf/core: Use static_call to optimize perf_guest_info_callbacks Use static_call to optimize perf's guest callbacks on arm64 and x86, which are now the only architectures that define the callbacks. Use DEFINE_STATIC_CALL_RET0 as the default/NULL for all guest callbacks, as the callback semantics are that a return value '0' means "not in guest". static_call obviously avoids the overhead of CONFIG_RETPOLINE=y, but is also advantageous versus other solutions, e.g. per-cpu callbacks, in that a per-cpu memory load is not needed to detect the !guest case. Based on code from Peter and Like. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-10-seanjc@google.com --- include/linux/perf_event.h | 34 ++++++++-------------------------- kernel/events/core.c | 15 +++++++++++++++ 2 files changed, 23 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ea47ef616ee0..0ac7d867ca0c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1244,40 +1244,22 @@ extern void perf_event_bpf_event(struct bpf_prog *prog, #ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; -static inline struct perf_guest_info_callbacks *perf_get_guest_cbs(void) -{ - /* - * Callbacks are RCU-protected and must be READ_ONCE to avoid reloading - * the callbacks between a !NULL check and dereferences, to ensure - * pending stores/changes to the callback pointers are visible before a - * non-NULL perf_guest_cbs is visible to readers, and to prevent a - * module from unloading callbacks while readers are active. - */ - return rcu_dereference(perf_guest_cbs); -} + +DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); +DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); +DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); + static inline unsigned int perf_guest_state(void) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - - return guest_cbs ? guest_cbs->state() : 0; + return static_call(__perf_guest_state)(); } static inline unsigned long perf_guest_get_ip(void) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - - /* - * Arbitrarily return '0' in the unlikely scenario that the callbacks - * are unregistered between checking guest state and getting the IP. - */ - return guest_cbs ? guest_cbs->get_ip() : 0; + return static_call(__perf_guest_get_ip)(); } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { - struct perf_guest_info_callbacks *guest_cbs = perf_get_guest_cbs(); - - if (guest_cbs && guest_cbs->handle_intel_pt_intr) - return guest_cbs->handle_intel_pt_intr(); - return 0; + return static_call(__perf_guest_handle_intel_pt_intr)(); } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); diff --git a/kernel/events/core.c b/kernel/events/core.c index 5a3502cd5362..3b3297a57228 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -6524,12 +6524,23 @@ static void perf_pending_event(struct irq_work *entry) #ifdef CONFIG_GUEST_PERF_EVENTS struct perf_guest_info_callbacks __rcu *perf_guest_cbs; +DEFINE_STATIC_CALL_RET0(__perf_guest_state, *perf_guest_cbs->state); +DEFINE_STATIC_CALL_RET0(__perf_guest_get_ip, *perf_guest_cbs->get_ip); +DEFINE_STATIC_CALL_RET0(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); + void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) { if (WARN_ON_ONCE(rcu_access_pointer(perf_guest_cbs))) return; rcu_assign_pointer(perf_guest_cbs, cbs); + static_call_update(__perf_guest_state, cbs->state); + static_call_update(__perf_guest_get_ip, cbs->get_ip); + + /* Implementing ->handle_intel_pt_intr is optional. */ + if (cbs->handle_intel_pt_intr) + static_call_update(__perf_guest_handle_intel_pt_intr, + cbs->handle_intel_pt_intr); } EXPORT_SYMBOL_GPL(perf_register_guest_info_callbacks); @@ -6539,6 +6550,10 @@ void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) return; rcu_assign_pointer(perf_guest_cbs, NULL); + static_call_update(__perf_guest_state, (void *)&__static_call_return0); + static_call_update(__perf_guest_get_ip, (void *)&__static_call_return0); + static_call_update(__perf_guest_handle_intel_pt_intr, + (void *)&__static_call_return0); synchronize_rcu(); } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); -- cgit v1.2.3 From e1bfc24577cc65c95dc519d7621a9c985b97e567 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:33 +0000 Subject: KVM: Move x86's perf guest info callbacks to generic KVM Move x86's perf guest callbacks into common KVM, as they are semantically identical to arm64's callbacks (the only other such KVM callbacks). arm64 will convert to the common versions in a future patch. Implement the necessary arm64 arch hooks now to avoid having to provide stubs or a temporary #define (from x86) to avoid arm64 compilation errors when CONFIG_GUEST_PERF_EVENTS=y. Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Acked-by: Marc Zyngier Link: https://lore.kernel.org/r/20211111020738.2512932-13-seanjc@google.com --- arch/arm64/include/asm/kvm_host.h | 10 ++++++++ arch/arm64/kvm/arm.c | 5 ++++ arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/x86.c | 53 ++++++++------------------------------- include/linux/kvm_host.h | 10 ++++++++ virt/kvm/kvm_main.c | 44 ++++++++++++++++++++++++++++++++ 6 files changed, 83 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f680f303ba7c..aa28b8e0e5d0 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -678,6 +678,16 @@ int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa); void kvm_perf_init(void); void kvm_perf_teardown(void); +/* + * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, + * arrived in guest context. For arm64, any event that arrives while a vCPU is + * loaded is considered to be "in guest". + */ +static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) +{ + return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; +} + long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); void kvm_update_stolen_time(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 2f03cbfefe67..b400be996040 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -496,6 +496,11 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) return vcpu_mode_priv(vcpu); } +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) +{ + return *vcpu_pc(vcpu); +} + /* Just ensure a guest exit from a particular CPU */ static void exit_vm_noop(void *info) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 38f01b00d82a..89576549b1d5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1567,6 +1567,9 @@ static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm) return -ENOTSUPP; } +#define kvm_arch_pmi_in_guest(vcpu) \ + ((vcpu) && (vcpu)->arch.handling_intr_from_guest) + int kvm_mmu_module_init(void); void kvm_mmu_module_exit(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ab032ef7879f..32cb6f9ca077 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8469,43 +8469,12 @@ static void kvm_timer_init(void) kvmclock_cpu_online, kvmclock_cpu_down_prep); } -static inline bool kvm_pmi_in_guest(struct kvm_vcpu *vcpu) -{ - return vcpu && vcpu->arch.handling_intr_from_guest; -} - -static unsigned int kvm_guest_state(void) -{ - struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); - unsigned int state; - - if (!kvm_pmi_in_guest(vcpu)) - return 0; - - state = PERF_GUEST_ACTIVE; - if (static_call(kvm_x86_get_cpl)(vcpu)) - state |= PERF_GUEST_USER; - - return state; -} - -static unsigned long kvm_guest_get_ip(void) -{ - struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); - - /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ - if (WARN_ON_ONCE(!kvm_pmi_in_guest(vcpu))) - return 0; - - return kvm_rip_read(vcpu); -} - static unsigned int kvm_handle_intel_pt_intr(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* '0' on failure so that the !PT case can use a RET0 static call. */ - if (!kvm_pmi_in_guest(vcpu)) + if (!kvm_arch_pmi_in_guest(vcpu)) return 0; kvm_make_request(KVM_REQ_PMI, vcpu); @@ -8514,12 +8483,6 @@ static unsigned int kvm_handle_intel_pt_intr(void) return 1; } -static struct perf_guest_info_callbacks kvm_guest_cbs = { - .state = kvm_guest_state, - .get_ip = kvm_guest_get_ip, - .handle_intel_pt_intr = NULL, -}; - #ifdef CONFIG_X86_64 static void pvclock_gtod_update_fn(struct work_struct *work) { @@ -11229,9 +11192,11 @@ int kvm_arch_hardware_setup(void *opaque) memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); kvm_ops_static_call_update(); + /* Temporary ugliness. */ if (ops->intel_pt_intr_in_guest && ops->intel_pt_intr_in_guest()) - kvm_guest_cbs.handle_intel_pt_intr = kvm_handle_intel_pt_intr; - perf_register_guest_info_callbacks(&kvm_guest_cbs); + kvm_register_perf_callbacks(kvm_handle_intel_pt_intr); + else + kvm_register_perf_callbacks(NULL); if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; @@ -11260,8 +11225,7 @@ int kvm_arch_hardware_setup(void *opaque) void kvm_arch_hardware_unsetup(void) { - perf_unregister_guest_info_callbacks(&kvm_guest_cbs); - kvm_guest_cbs.handle_intel_pt_intr = NULL; + kvm_unregister_perf_callbacks(); static_call(kvm_x86_hardware_unsetup)(); } @@ -11852,6 +11816,11 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) return vcpu->arch.preempted_in_kernel; } +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) +{ + return kvm_rip_read(vcpu); +} + int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9e0667e3723e..9df7ab2d7530 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1170,6 +1170,16 @@ static inline bool kvm_arch_intc_initialized(struct kvm *kvm) } #endif +#ifdef CONFIG_GUEST_PERF_EVENTS +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu); + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)); +void kvm_unregister_perf_callbacks(void); +#else +static inline void kvm_register_perf_callbacks(void *ign) {} +static inline void kvm_unregister_perf_callbacks(void) {} +#endif /* CONFIG_GUEST_PERF_EVENTS */ + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type); void kvm_arch_destroy_vm(struct kvm *kvm); void kvm_arch_sync_events(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index d31724500501..76778dd2351f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5479,6 +5479,50 @@ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) return &kvm_running_vcpu; } +#ifdef CONFIG_GUEST_PERF_EVENTS +static unsigned int kvm_guest_state(void) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + unsigned int state; + + if (!kvm_arch_pmi_in_guest(vcpu)) + return 0; + + state = PERF_GUEST_ACTIVE; + if (!kvm_arch_vcpu_in_kernel(vcpu)) + state |= PERF_GUEST_USER; + + return state; +} + +static unsigned long kvm_guest_get_ip(void) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + + /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ + if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu))) + return 0; + + return kvm_arch_vcpu_get_ip(vcpu); +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .state = kvm_guest_state, + .get_ip = kvm_guest_get_ip, + .handle_intel_pt_intr = NULL, +}; + +void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)) +{ + kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler; + perf_register_guest_info_callbacks(&kvm_guest_cbs); +} +void kvm_unregister_perf_callbacks(void) +{ + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); +} +#endif + struct kvm_cpu_compat_check { void *opaque; int *ret; -- cgit v1.2.3 From a9f4a6e92b3b319296fb078da2615f618f6cd80c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 11 Nov 2021 02:07:38 +0000 Subject: perf: Drop guest callback (un)register stubs Drop perf's stubs for (un)registering guest callbacks now that KVM registration of callbacks is hidden behind GUEST_PERF_EVENTS=y. The only other user is x86 XEN_PV, and x86 unconditionally selects PERF_EVENTS. No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paolo Bonzini Link: https://lore.kernel.org/r/20211111020738.2512932-18-seanjc@google.com --- include/linux/perf_event.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0ac7d867ca0c..7b7525e9155f 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1511,11 +1511,6 @@ perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } -static inline void perf_register_guest_info_callbacks -(struct perf_guest_info_callbacks *cbs) { } -static inline void perf_unregister_guest_info_callbacks -(struct perf_guest_info_callbacks *cbs) { } - static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); -- cgit v1.2.3 From f45b2974cc0ae959a4c503a071e38a56bd64372f Mon Sep 17 00:00:00 2001 From: Björn Töpel Date: Wed, 17 Nov 2021 13:57:08 +0100 Subject: bpf, x86: Fix "no previous prototype" warning MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The arch_prepare_bpf_dispatcher function does not have a prototype, and yields the following warning when W=1 is enabled for the kernel build. >> arch/x86/net/bpf_jit_comp.c:2188:5: warning: no previous \ prototype for 'arch_prepare_bpf_dispatcher' [-Wmissing-prototypes] 2188 | int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, \ int num_funcs) | ^~~~~~~~~~~~~~~~~~~~~~~~~~~ Remove the warning by adding a function declaration to include/linux/bpf.h. Fixes: 75ccbef6369e ("bpf: Introduce BPF dispatcher") Reported-by: kernel test robot Signed-off-by: Björn Töpel Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211117125708.769168-1-bjorn@kernel.org --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index e7a163a3146b..84ff6ef49462 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -732,6 +732,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); +int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs); #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ -- cgit v1.2.3 From cf9acc90c80ecbee00334aa85d92f4e74014bcff Mon Sep 17 00:00:00 2001 From: Jonathan Davies Date: Tue, 16 Nov 2021 17:42:42 +0000 Subject: net: virtio_net_hdr_to_skb: count transport header in UFO virtio_net_hdr_to_skb does not set the skb's gso_size and gso_type correctly for UFO packets received via virtio-net that are a little over the GSO size. This can lead to problems elsewhere in the networking stack, e.g. ovs_vport_send dropping over-sized packets if gso_size is not set. This is due to the comparison if (skb->len - p_off > gso_size) not properly accounting for the transport layer header. p_off includes the size of the transport layer header (thlen), so skb->len - p_off is the size of the TCP/UDP payload. gso_size is read from the virtio-net header. For UFO, fragmentation happens at the IP level so does not need to include the UDP header. Hence the calculation could be comparing a TCP/UDP payload length with an IP payload length, causing legitimate virtio-net packets to have lack gso_type/gso_size information. Example: a UDP packet with payload size 1473 has IP payload size 1481. If the guest used UFO, it is not fragmented and the virtio-net header's flags indicate that it is a GSO frame (VIRTIO_NET_HDR_GSO_UDP), with gso_size = 1480 for an MTU of 1500. skb->len will be 1515 and p_off will be 42, so skb->len - p_off = 1473. Hence the comparison fails, and shinfo->gso_size and gso_type are not set as they should be. Instead, add the UDP header length before comparing to gso_size when using UFO. In this way, it is the size of the IP payload that is compared to gso_size. Fixes: 6dd912f82680 ("net: check untrusted gso_size at kernel entry") Signed-off-by: Jonathan Davies Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/virtio_net.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b465f8f3e554..04e87f4b9417 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -120,10 +120,15 @@ retry: if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); + /* UFO may not include transport header in gso_size. */ + if (gso_type & SKB_GSO_UDP) + nh_off -= thlen; + /* Too small packets are not really GSO ones. */ - if (skb->len - p_off > gso_size) { + if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; -- cgit v1.2.3 From 8160fb43d55d26d64607fd32fe69185a5f5fe41f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Nov 2021 19:29:21 -0800 Subject: net: use an atomic_long_t for queue->trans_timeout tx_timeout_show() assumed dev_watchdog() would stop all the queues, to fetch queue->trans_timeout under protection of the queue->_xmit_lock. As we want to no longer disrupt transmits, we use an atomic_long_t instead. Signed-off-by: Eric Dumazet Cc: david decotigny Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/net-sysfs.c | 6 +----- net/sched/sch_generic.c | 2 +- 3 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dd328364dfe9..1d22483cf78c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -592,7 +592,7 @@ struct netdev_queue { * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ - unsigned long trans_timeout; + atomic_long_t trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 9c01c642cf9e..addbef5419fb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1201,11 +1201,7 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = { static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) { - unsigned long trans_timeout; - - spin_lock_irq(&queue->_xmit_lock); - trans_timeout = queue->trans_timeout; - spin_unlock_irq(&queue->_xmit_lock); + unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout); return sprintf(buf, fmt_ulong, trans_timeout); } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 3b0f62095803..1b4328bd495d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -467,7 +467,7 @@ static void dev_watchdog(struct timer_list *t) time_after(jiffies, (trans_start + dev->watchdog_timeo))) { some_queue_timedout = 1; - txq->trans_timeout++; + atomic_long_inc(&txq->trans_timeout); break; } } -- cgit v1.2.3 From 5337824f4dc4bb26f38fbbba4ffb425a92803f15 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Nov 2021 19:29:22 -0800 Subject: net: annotate accesses to queue->trans_start In following patches, dev_watchdog() will no longer stop all queues. It will read queue->trans_start locklessly. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/apm/xgene/xgene_enet_main.c | 2 +- drivers/net/ethernet/atheros/ag71xx.c | 2 +- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 4 ++-- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +- drivers/net/ethernet/ibm/ibmvnic.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 4 ++-- drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++--- drivers/net/ethernet/ti/am65-cpsw-nuss.c | 2 +- drivers/net/virtio_net.c | 2 +- drivers/net/wireless/marvell/mwifiex/init.c | 2 +- drivers/staging/rtl8192e/rtllib_softmac.c | 2 +- include/linux/netdevice.h | 16 +++++++++++++--- net/sched/sch_generic.c | 8 ++++---- 14 files changed, 33 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 220dc42af31a..ff2d099aab21 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -869,7 +869,7 @@ static void xgene_enet_timeout(struct net_device *ndev, unsigned int txqueue) for (i = 0; i < pdata->txq_cnt; i++) { txq = netdev_get_tx_queue(ndev, i); - txq->trans_start = jiffies; + txq_trans_cond_update(txq); netif_tx_start_queue(txq); } } diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 88d2ab748399..e4f30bb7498f 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -766,7 +766,7 @@ static bool ag71xx_check_dma_stuck(struct ag71xx *ag) unsigned long timestamp; u32 rx_sm, tx_sm, rx_fd; - timestamp = netdev_get_tx_queue(ag->ndev, 0)->trans_start; + timestamp = READ_ONCE(netdev_get_tx_queue(ag->ndev, 0)->trans_start); if (likely(time_before(jiffies, timestamp + HZ / 10))) return false; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 6b2927d863e2..d6871437d951 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2325,7 +2325,7 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev) txq = netdev_get_tx_queue(net_dev, queue_mapping); /* LLTX requires to do our own update of trans_start */ - txq->trans_start = jiffies; + txq_trans_cond_update(txq); if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) { fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD); @@ -2531,7 +2531,7 @@ static int dpaa_xdp_xmit_frame(struct net_device *net_dev, /* Bump the trans_start */ txq = netdev_get_tx_queue(net_dev, smp_processor_id()); - txq->trans_start = jiffies; + txq_trans_cond_update(txq); err = dpaa_xmit(priv, percpu_stats, smp_processor_id(), &fd); if (err) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 13835a37b3a2..d5100179f8d5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2679,7 +2679,7 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev) unsigned long trans_start; q = netdev_get_tx_queue(ndev, i); - trans_start = q->trans_start; + trans_start = READ_ONCE(q->trans_start); if (netif_xmit_stopped(q) && time_after(jiffies, (trans_start + ndev->watchdog_timeo))) { diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 3cca51735421..c327fc8860da 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2058,7 +2058,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_packets++; tx_bytes += skb->len; - txq->trans_start = jiffies; + txq_trans_cond_update(txq); ret = NETDEV_TX_OK; goto out; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 836be0d3b291..18a019a47182 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2927,7 +2927,7 @@ static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); /* Avoid transmit queue timeout since we share it with the slow path */ - nq->trans_start = jiffies; + txq_trans_cond_update(nq); ret = igb_xmit_xdp_ring(adapter, tx_ring, xdpf); __netif_tx_unlock(nq); @@ -2961,7 +2961,7 @@ static int igb_xdp_xmit(struct net_device *dev, int n, __netif_tx_lock(nq, cpu); /* Avoid transmit queue timeout since we share it with the slow path */ - nq->trans_start = jiffies; + txq_trans_cond_update(nq); for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 4f4bc8726ec4..860605133287 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -565,7 +565,7 @@ int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) snprintf(err_str, sizeof(err_str), "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u", sq->ch_ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - sq->txq->trans_start)); + jiffies_to_usecs(jiffies - READ_ONCE(sq->txq->trans_start))); mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); return to_ctx.status; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 033c35c09a54..389d125310c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2356,7 +2356,7 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget) bool work_done = true; /* Avoids TX time-out as we are sharing with slow path */ - nq->trans_start = jiffies; + txq_trans_cond_update(nq->trans_start); budget = min(budget, stmmac_tx_avail(priv, queue)); @@ -4657,7 +4657,7 @@ static int stmmac_xdp_xmit_back(struct stmmac_priv *priv, __netif_tx_lock(nq, cpu); /* Avoids TX time-out as we are sharing with slow path */ - nq->trans_start = jiffies; + txq_trans_cond_update(nq->trans_start); res = stmmac_xdp_xmit_xdpf(priv, queue, xdpf, false); if (res == STMMAC_XDP_TX) @@ -6293,7 +6293,7 @@ static int stmmac_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_lock(nq, cpu); /* Avoids TX time-out as we are sharing with slow path */ - nq->trans_start = jiffies; + txq_trans_cond_update(nq); for (i = 0; i < num_frames; i++) { int res; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index c092cb61416a..750cea23e9cd 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -345,7 +345,7 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev, netif_txq = netdev_get_tx_queue(ndev, txqueue); tx_chn = &common->tx_chns[txqueue]; - trans_start = netif_txq->trans_start; + trans_start = READ_ONCE(netif_txq->trans_start); netdev_err(ndev, "txq:%d DRV_XOFF:%d tmo:%u dql_avail:%d free_desc:%zu\n", txqueue, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 1771d6e5224f..03e38e38ee4b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2694,7 +2694,7 @@ static void virtnet_tx_timeout(struct net_device *dev, unsigned int txqueue) netdev_err(dev, "TX timeout on queue: %u, sq: %s, vq: 0x%x, name: %s, %u usecs ago\n", txqueue, sq->name, sq->vq->index, sq->vq->name, - jiffies_to_usecs(jiffies - txq->trans_start)); + jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start))); } static const struct net_device_ops virtnet_netdev = { diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c index f006a3d72b40..88c72d1827a0 100644 --- a/drivers/net/wireless/marvell/mwifiex/init.c +++ b/drivers/net/wireless/marvell/mwifiex/init.c @@ -332,7 +332,7 @@ void mwifiex_set_trans_start(struct net_device *dev) int i; for (i = 0; i < dev->num_tx_queues; i++) - netdev_get_tx_queue(dev, i)->trans_start = jiffies; + txq_trans_cond_update(netdev_get_tx_queue(dev, i)); netif_trans_update(dev); } diff --git a/drivers/staging/rtl8192e/rtllib_softmac.c b/drivers/staging/rtl8192e/rtllib_softmac.c index d2726d01c757..aabbea48223d 100644 --- a/drivers/staging/rtl8192e/rtllib_softmac.c +++ b/drivers/staging/rtl8192e/rtllib_softmac.c @@ -2515,7 +2515,7 @@ void rtllib_stop_all_queues(struct rtllib_device *ieee) unsigned int i; for (i = 0; i < ieee->dev->num_tx_queues; i++) - netdev_get_tx_queue(ieee->dev, i)->trans_start = jiffies; + txq_trans_cond_update(netdev_get_tx_queue(ieee->dev, i)); netif_tx_stop_all_queues(ieee->dev); } diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1d22483cf78c..279409ef2b18 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4095,10 +4095,21 @@ static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) spin_unlock_bh(&txq->_xmit_lock); } +/* + * txq->trans_start can be read locklessly from dev_watchdog() + */ static inline void txq_trans_update(struct netdev_queue *txq) { if (txq->xmit_lock_owner != -1) - txq->trans_start = jiffies; + WRITE_ONCE(txq->trans_start, jiffies); +} + +static inline void txq_trans_cond_update(struct netdev_queue *txq) +{ + unsigned long now = jiffies; + + if (READ_ONCE(txq->trans_start) != now) + WRITE_ONCE(txq->trans_start, now); } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ @@ -4106,8 +4117,7 @@ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); - if (txq->trans_start != jiffies) - txq->trans_start = jiffies; + txq_trans_cond_update(txq); } /** diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 1b4328bd495d..02c46041f76e 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -434,9 +434,9 @@ unsigned long dev_trans_start(struct net_device *dev) dev = vlan_dev_real_dev(dev); else if (netif_is_macvlan(dev)) dev = macvlan_dev_real_dev(dev); - res = netdev_get_tx_queue(dev, 0)->trans_start; + res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start); for (i = 1; i < dev->num_tx_queues; i++) { - val = netdev_get_tx_queue(dev, i)->trans_start; + val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start); if (val && time_after(val, res)) res = val; } @@ -462,7 +462,7 @@ static void dev_watchdog(struct timer_list *t) struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); - trans_start = txq->trans_start; + trans_start = READ_ONCE(txq->trans_start); if (netif_xmit_stopped(txq) && time_after(jiffies, (trans_start + dev->watchdog_timeo))) { @@ -1148,7 +1148,7 @@ static void transition_one_qdisc(struct net_device *dev, rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { - dev_queue->trans_start = 0; + WRITE_ONCE(dev_queue->trans_start, 0); *need_watchdog_p = 1; } } -- cgit v1.2.3 From dab8fe320726b38a6b1dc6a7ca6e386c5f7779e8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 16 Nov 2021 19:29:23 -0800 Subject: net: do not inline netif_tx_lock()/netif_tx_unlock() These are not fast path, there is no point in inlining them. Also provide netif_freeze_queues()/netif_unfreeze_queues() so that we can use them from dev_watchdog() in the following patch. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 39 ++---------------------------------- net/sched/sch_generic.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 53 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 279409ef2b18..4f4a299e92de 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4126,27 +4126,7 @@ static inline void netif_trans_update(struct net_device *dev) * * Get network device transmit lock */ -static inline void netif_tx_lock(struct net_device *dev) -{ - unsigned int i; - int cpu; - - spin_lock(&dev->tx_global_lock); - cpu = smp_processor_id(); - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* We are the only thread of execution doing a - * freeze, but we have to grab the _xmit_lock in - * order to synchronize with threads which are in - * the ->hard_start_xmit() handler and already - * checked the frozen bit. - */ - __netif_tx_lock(txq, cpu); - set_bit(__QUEUE_STATE_FROZEN, &txq->state); - __netif_tx_unlock(txq); - } -} +void netif_tx_lock(struct net_device *dev); static inline void netif_tx_lock_bh(struct net_device *dev) { @@ -4154,22 +4134,7 @@ static inline void netif_tx_lock_bh(struct net_device *dev) netif_tx_lock(dev); } -static inline void netif_tx_unlock(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* No need to grab the _xmit_lock here. If the - * queue is not stopped for another reason, we - * force a schedule. - */ - clear_bit(__QUEUE_STATE_FROZEN, &txq->state); - netif_schedule_queue(txq); - } - spin_unlock(&dev->tx_global_lock); -} +void netif_tx_unlock(struct net_device *dev); static inline void netif_tx_unlock_bh(struct net_device *dev) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 02c46041f76e..389e0d8fc68d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -445,6 +445,57 @@ unsigned long dev_trans_start(struct net_device *dev) } EXPORT_SYMBOL(dev_trans_start); +static void netif_freeze_queues(struct net_device *dev) +{ + unsigned int i; + int cpu; + + cpu = smp_processor_id(); + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* We are the only thread of execution doing a + * freeze, but we have to grab the _xmit_lock in + * order to synchronize with threads which are in + * the ->hard_start_xmit() handler and already + * checked the frozen bit. + */ + __netif_tx_lock(txq, cpu); + set_bit(__QUEUE_STATE_FROZEN, &txq->state); + __netif_tx_unlock(txq); + } +} + +void netif_tx_lock(struct net_device *dev) +{ + spin_lock(&dev->tx_global_lock); + netif_freeze_queues(dev); +} +EXPORT_SYMBOL(netif_tx_lock); + +static void netif_unfreeze_queues(struct net_device *dev) +{ + unsigned int i; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *txq = netdev_get_tx_queue(dev, i); + + /* No need to grab the _xmit_lock here. If the + * queue is not stopped for another reason, we + * force a schedule. + */ + clear_bit(__QUEUE_STATE_FROZEN, &txq->state); + netif_schedule_queue(txq); + } +} + +void netif_tx_unlock(struct net_device *dev) +{ + netif_unfreeze_queues(dev); + spin_unlock(&dev->tx_global_lock); +} +EXPORT_SYMBOL(netif_tx_unlock); + static void dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); -- cgit v1.2.3 From 1881eadb2041889d74d60c074eb04189c4a07dad Mon Sep 17 00:00:00 2001 From: Abhyuday Godhasara Date: Mon, 25 Oct 2021 21:25:20 -0700 Subject: firmware: xilinx: add register notifier in zynqmp firmware In zynqmp-firmware, register notifier is not supported, add support of register notifier in zynqmp-firmware. Acked-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Abhyuday Godhasara Link: https://lore.kernel.org/r/20211026042525.26612-2-abhyuday.godhasara@xilinx.com Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/xilinx/zynqmp.c | 23 +++++++++++++++++++++++ include/linux/firmware/xlnx-zynqmp.h | 11 ++++++++++- 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 3dd45a7420dc..30edcd233786 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -1116,6 +1116,29 @@ int zynqmp_pm_aes_engine(const u64 address, u32 *out) } EXPORT_SYMBOL_GPL(zynqmp_pm_aes_engine); +/** + * zynqmp_pm_register_notifier() - PM API for register a subsystem + * to be notified about specific + * event/error. + * @node: Node ID to which the event is related. + * @event: Event Mask of Error events for which wants to get notified. + * @wake: Wake subsystem upon capturing the event if value 1 + * @enable: Enable the registration for value 1, disable for value 0 + * + * This function is used to register/un-register for particular node-event + * combination in firmware. + * + * Return: Returns status, either success or error+reason + */ + +int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable) +{ + return zynqmp_pm_invoke_fn(PM_REGISTER_NOTIFIER, node, event, + wake, enable, NULL); +} +EXPORT_SYMBOL_GPL(zynqmp_pm_register_notifier); + /** * zynqmp_pm_system_shutdown - PM call to request a system shutdown or restart * @type: Shutdown or restart? 0 for shutdown, 1 for restart diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 47fd4e52a423..d30d39dc8cb4 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -2,7 +2,7 @@ /* * Xilinx Zynq MPSoC Firmware layer * - * Copyright (C) 2014-2019 Xilinx + * Copyright (C) 2014-2021 Xilinx * * Michal Simek * Davorin Mista @@ -66,6 +66,7 @@ enum pm_api_id { PM_GET_API_VERSION = 1, + PM_REGISTER_NOTIFIER = 5, PM_SYSTEM_SHUTDOWN = 12, PM_REQUEST_NODE = 13, PM_RELEASE_NODE = 14, @@ -427,6 +428,8 @@ int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param, int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, u32 value); int zynqmp_pm_load_pdi(const u32 src, const u64 address); +int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -658,6 +661,12 @@ static inline int zynqmp_pm_load_pdi(const u32 src, const u64 address) { return -ENODEV; } + +static inline int zynqmp_pm_register_notifier(const u32 node, const u32 event, + const u32 wake, const u32 enable) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From fbce9f14055e547d270046f61758c29c957e675d Mon Sep 17 00:00:00 2001 From: Abhyuday Godhasara Date: Mon, 25 Oct 2021 21:25:21 -0700 Subject: firmware: xilinx: add macros of node ids for error event Add macros for the Node-Id of Error events. Move supported api callback ids from zynqmp-power to zynqmp-firmware. Acked-by: Michal Simek Signed-off-by: Rajan Vaja Signed-off-by: Abhyuday Godhasara Link: https://lore.kernel.org/r/20211026042525.26612-3-abhyuday.godhasara@xilinx.com Signed-off-by: Greg Kroah-Hartman --- drivers/soc/xilinx/zynqmp_power.c | 6 ------ include/linux/firmware/xlnx-zynqmp.h | 14 ++++++++++++++ 2 files changed, 14 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c index c556623dae02..76478fe2301f 100644 --- a/drivers/soc/xilinx/zynqmp_power.c +++ b/drivers/soc/xilinx/zynqmp_power.c @@ -46,12 +46,6 @@ static const char *const suspend_modes[] = { static enum pm_suspend_mode suspend_mode = PM_SUSPEND_MODE_STD; -enum pm_api_cb_id { - PM_INIT_SUSPEND_CB = 30, - PM_ACKNOWLEDGE_CB, - PM_NOTIFY_CB, -}; - static void zynqmp_pm_get_callback_data(u32 *buf) { zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf); diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index d30d39dc8cb4..b0a38091db71 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -64,6 +64,20 @@ #define XILINX_ZYNQMP_PM_FPGA_FULL 0x0U #define XILINX_ZYNQMP_PM_FPGA_PARTIAL BIT(0) +/* + * Node IDs for the Error Events. + */ +#define EVENT_ERROR_PMC_ERR1 (0x28100000U) +#define EVENT_ERROR_PMC_ERR2 (0x28104000U) +#define EVENT_ERROR_PSM_ERR1 (0x28108000U) +#define EVENT_ERROR_PSM_ERR2 (0x2810C000U) + +enum pm_api_cb_id { + PM_INIT_SUSPEND_CB = 30, + PM_ACKNOWLEDGE_CB = 31, + PM_NOTIFY_CB = 32, +}; + enum pm_api_id { PM_GET_API_VERSION = 1, PM_REGISTER_NOTIFIER = 5, -- cgit v1.2.3 From f4d77525679e289d4976ca03b620ac4cc5403205 Mon Sep 17 00:00:00 2001 From: Abhyuday Godhasara Date: Mon, 25 Oct 2021 21:25:22 -0700 Subject: firmware: xilinx: export the feature check of zynqmp firmware Export the zynqmp_pm_feature(), so it can be use by other as to get API version available in firmware. Acked-by: Michal Simek Signed-off-by: Rajan Vaja Signed-off-by: Abhyuday Godhasara Link: https://lore.kernel.org/r/20211026042525.26612-4-abhyuday.godhasara@xilinx.com Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/xilinx/zynqmp.c | 3 ++- include/linux/firmware/xlnx-zynqmp.h | 6 ++++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c index 30edcd233786..c2828ee6d4cf 100644 --- a/drivers/firmware/xilinx/zynqmp.c +++ b/drivers/firmware/xilinx/zynqmp.c @@ -160,7 +160,7 @@ static noinline int do_fw_call_hvc(u64 arg0, u64 arg1, u64 arg2, * * Return: Returns status, either success or error+reason */ -static int zynqmp_pm_feature(u32 api_id) +int zynqmp_pm_feature(const u32 api_id) { int ret; u32 ret_payload[PAYLOAD_ARG_CNT]; @@ -197,6 +197,7 @@ static int zynqmp_pm_feature(u32 api_id) return ret; } +EXPORT_SYMBOL_GPL(zynqmp_pm_feature); /** * zynqmp_pm_invoke_fn() - Invoke the system-level platform management layer diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index b0a38091db71..077e894bb340 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -444,6 +444,7 @@ int zynqmp_pm_pinctrl_set_config(const u32 pin, const u32 param, int zynqmp_pm_load_pdi(const u32 src, const u64 address); int zynqmp_pm_register_notifier(const u32 node, const u32 event, const u32 wake, const u32 enable); +int zynqmp_pm_feature(const u32 api_id); #else static inline int zynqmp_pm_get_api_version(u32 *version) { @@ -681,6 +682,11 @@ static inline int zynqmp_pm_register_notifier(const u32 node, const u32 event, { return -ENODEV; } + +static inline int zynqmp_pm_feature(const u32 api_id) +{ + return -ENODEV; +} #endif #endif /* __FIRMWARE_ZYNQMP_H__ */ -- cgit v1.2.3 From 522a0032af005502507f5f81ae64fdcc82b5d068 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 6 Nov 2021 17:13:35 -0400 Subject: Add linux/cacheflush.h Many architectures do not include asm-generic/cacheflush.h, so turn the includes on their head and add linux/cacheflush.h which includes asm/cacheflush.h. Move the flush_dcache_folio() declaration from asm-generic/cacheflush.h to linux/cacheflush.h and change linux/highmem.h to include linux/cacheflush.h instead of asm/cacheflush.h so that all necessary places will see flush_dcache_folio(). More functions should have their default implementations moved in the future, but those are for follow-on patches. This fixes csky, sparc and sparc64 which were missed in the commit which added flush_dcache_folio(). Fixes: 08b0b0059bf1 ("mm: Add flush_dcache_folio()") Suggested-by: Christoph Hellwig Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Geert Uytterhoeven --- arch/arc/include/asm/cacheflush.h | 1 - arch/arm/include/asm/cacheflush.h | 1 - arch/m68k/include/asm/cacheflush_mm.h | 1 - arch/mips/include/asm/cacheflush.h | 2 -- arch/nds32/include/asm/cacheflush.h | 1 - arch/nios2/include/asm/cacheflush.h | 1 - arch/parisc/include/asm/cacheflush.h | 1 - arch/sh/include/asm/cacheflush.h | 1 - arch/xtensa/include/asm/cacheflush.h | 3 --- include/asm-generic/cacheflush.h | 6 ------ include/linux/cacheflush.h | 18 ++++++++++++++++++ include/linux/highmem.h | 3 +-- 12 files changed, 19 insertions(+), 20 deletions(-) create mode 100644 include/linux/cacheflush.h (limited to 'include/linux') diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index e8c2c7469e10..e201b4b1655a 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -36,7 +36,6 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void dma_cache_wback_inv(phys_addr_t start, unsigned long sz); void dma_cache_inv(phys_addr_t start, unsigned long sz); diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h index e68fb879e4f9..5e56288e343b 100644 --- a/arch/arm/include/asm/cacheflush.h +++ b/arch/arm/include/asm/cacheflush.h @@ -290,7 +290,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr */ #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 extern void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *folio); #define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1 static inline void flush_kernel_vmap_range(void *addr, int size) diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h index 8ab46625ddd3..1ac55e7b47f0 100644 --- a/arch/m68k/include/asm/cacheflush_mm.h +++ b/arch/m68k/include/asm/cacheflush_mm.h @@ -250,7 +250,6 @@ static inline void __flush_page_to_ram(void *vaddr) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 #define flush_dcache_page(page) __flush_page_to_ram(page_address(page)) -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) #define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page)) diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h index f207388541d5..b3dc9c589442 100644 --- a/arch/mips/include/asm/cacheflush.h +++ b/arch/mips/include/asm/cacheflush.h @@ -61,8 +61,6 @@ static inline void flush_dcache_page(struct page *page) SetPageDcacheDirty(page); } -void flush_dcache_folio(struct folio *folio); - #define flush_dcache_mmap_lock(mapping) do { } while (0) #define flush_dcache_mmap_unlock(mapping) do { } while (0) diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h index 3fc0bb7d6487..c2a222ebfa2a 100644 --- a/arch/nds32/include/asm/cacheflush.h +++ b/arch/nds32/include/asm/cacheflush.h @@ -27,7 +27,6 @@ void flush_cache_vunmap(unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long vaddr, void *dst, void *src, int len); void copy_from_user_page(struct vm_area_struct *vma, struct page *page, diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h index 1999561b22aa..d0b71dd71287 100644 --- a/arch/nios2/include/asm/cacheflush.h +++ b/arch/nios2/include/asm/cacheflush.h @@ -29,7 +29,6 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); extern void flush_icache_page(struct vm_area_struct *vma, struct page *page); diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h index da0cd4b3a28f..859b8a34adcf 100644 --- a/arch/parisc/include/asm/cacheflush.h +++ b/arch/parisc/include/asm/cacheflush.h @@ -50,7 +50,6 @@ void invalidate_kernel_vmap_range(void *vaddr, int size); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); #define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages) #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages) diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h index c7a97f32432f..481a664287e2 100644 --- a/arch/sh/include/asm/cacheflush.h +++ b/arch/sh/include/asm/cacheflush.h @@ -43,7 +43,6 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *page); -void flush_dcache_folio(struct folio *folio); extern void flush_icache_range(unsigned long start, unsigned long end); #define flush_icache_user_range flush_icache_range extern void flush_icache_page(struct vm_area_struct *vma, diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h index a8a041609c5d..7b4359312c25 100644 --- a/arch/xtensa/include/asm/cacheflush.h +++ b/arch/xtensa/include/asm/cacheflush.h @@ -121,7 +121,6 @@ void flush_cache_page(struct vm_area_struct*, #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 void flush_dcache_page(struct page *); -void flush_dcache_folio(struct folio *); void local_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); @@ -138,9 +137,7 @@ void local_flush_cache_page(struct vm_area_struct *vma, #define flush_cache_vunmap(start,end) do { } while (0) #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO #define flush_dcache_page(page) do { } while (0) -static inline void flush_dcache_folio(struct folio *folio) { } #define flush_icache_range local_flush_icache_range #define flush_cache_page(vma, addr, pfn) do { } while (0) diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index fedc0dfa4877..4f07afacbc23 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -50,13 +50,7 @@ static inline void flush_dcache_page(struct page *page) { } -static inline void flush_dcache_folio(struct folio *folio) { } #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0 -#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO -#endif - -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO -void flush_dcache_folio(struct folio *folio); #endif #ifndef flush_dcache_mmap_lock diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h new file mode 100644 index 000000000000..fef8b607f97e --- /dev/null +++ b/include/linux/cacheflush.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CACHEFLUSH_H +#define _LINUX_CACHEFLUSH_H + +#include + +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO +void flush_dcache_folio(struct folio *folio); +#endif +#else +static inline void flush_dcache_folio(struct folio *folio) +{ +} +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO 0 +#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ + +#endif /* _LINUX_CACHEFLUSH_H */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 25aff0f2ed0b..c944b3b70ee7 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -5,12 +5,11 @@ #include #include #include +#include #include #include #include -#include - #include "highmem-internal.h" /** -- cgit v1.2.3 From 9c3252152e8a6401c2b9e32490a5a16ec4472778 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 16 Nov 2021 21:17:14 -0500 Subject: mm: Rename folio_test_multi to folio_test_large This is a better name. Also add kernel-doc. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/page-flags.h | 8 +++++++- mm/memcontrol.c | 2 +- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 52ec4b5e5615..05510118fbb8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -692,7 +692,13 @@ static inline bool folio_test_single(struct folio *folio) return !folio_test_head(folio); } -static inline bool folio_test_multi(struct folio *folio) +/** + * folio_test_large() - Does this folio contain more than one page? + * @folio: The folio to test. + * + * Return: True if the folio is larger than one page. + */ +static inline bool folio_test_large(struct folio *folio) { return folio_test_head(folio); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 781605e92015..6863a834ed42 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5558,7 +5558,7 @@ static int mem_cgroup_move_account(struct page *page, VM_BUG_ON(from == to); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); - VM_BUG_ON(compound && !folio_test_multi(folio)); + VM_BUG_ON(compound && !folio_test_large(folio)); /* * Prevent mem_cgroup_migrate() from looking at -- cgit v1.2.3 From a1efe484dd8c04c4c2d4eb1ee6b04d01cfc07ccc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 16 Nov 2021 21:18:52 -0500 Subject: mm: Remove folio_test_single There's no need for this predicate; callers can just use !folio_test_large(). Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/page-flags.h | 6 ------ mm/util.c | 2 +- 2 files changed, 1 insertion(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 05510118fbb8..b5f14d581113 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -686,12 +686,6 @@ static inline bool test_set_page_writeback(struct page *page) __PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY) -/* Whether there are one or multiple pages in a folio */ -static inline bool folio_test_single(struct folio *folio) -{ - return !folio_test_head(folio); -} - /** * folio_test_large() - Does this folio contain more than one page? * @folio: The folio to test. diff --git a/mm/util.c b/mm/util.c index e58151a61255..741ba32a43ac 100644 --- a/mm/util.c +++ b/mm/util.c @@ -670,7 +670,7 @@ bool folio_mapped(struct folio *folio) { long i, nr; - if (folio_test_single(folio)) + if (!folio_test_large(folio)) return atomic_read(&folio->_mapcount) >= 0; if (atomic_read(folio_mapcount_ptr(folio)) >= 0) return true; -- cgit v1.2.3 From ff36da69bc90d80b0c73f47f4b2e270b3ff6da99 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 29 Aug 2021 06:07:03 -0400 Subject: fs: Remove FS_THP_SUPPORT Instead of setting a bit in the fs_flags to set a bit in the address_space, set the bit in the address_space directly. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/inode.c | 2 -- include/linux/fs.h | 1 - include/linux/pagemap.h | 16 ++++++++++++++++ mm/shmem.c | 3 ++- 4 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 3eba0940ffcf..6b80a51129d5 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -180,8 +180,6 @@ int inode_init_always(struct super_block *sb, struct inode *inode) mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; - if (sb->s_type->fs_flags & FS_THP_SUPPORT) - __set_bit(AS_THP_SUPPORT, &mapping->flags); mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS diff --git a/include/linux/fs.h b/include/linux/fs.h index 1cb616fc1105..bbf812ce89a8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2518,7 +2518,6 @@ struct file_system_type { #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_DISALLOW_NOTIFY_PERM 16 /* Disable fanotify permission events */ #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ -#define FS_THP_SUPPORT 8192 /* Remove once all fs converted */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 1a0c646eb6ff..9e33878bf23b 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -176,6 +176,22 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) m->gfp_mask = mask; } +/** + * mapping_set_large_folios() - Indicate the file supports large folios. + * @mapping: The file. + * + * The filesystem should call this function in its inode constructor to + * indicate that the VFS can use large folios to cache the contents of + * the file. + * + * Context: This should not be called while the inode is active as it + * is non-atomic. + */ +static inline void mapping_set_large_folios(struct address_space *mapping) +{ + __set_bit(AS_THP_SUPPORT, &mapping->flags); +} + static inline bool mapping_thp_support(struct address_space *mapping) { return test_bit(AS_THP_SUPPORT, &mapping->flags); diff --git a/mm/shmem.c b/mm/shmem.c index dc038ce78700..18f93c2d68f1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2303,6 +2303,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode INIT_LIST_HEAD(&info->swaplist); simple_xattrs_init(&info->xattrs); cache_no_acl(inode); + mapping_set_large_folios(inode->i_mapping); switch (mode & S_IFMT) { default: @@ -3870,7 +3871,7 @@ static struct file_system_type shmem_fs_type = { .parameters = shmem_fs_parameters, #endif .kill_sb = kill_litter_super, - .fs_flags = FS_USERNS_MOUNT | FS_THP_SUPPORT, + .fs_flags = FS_USERNS_MOUNT, }; int __init shmem_init(void) -- cgit v1.2.3 From ed2145c474c9015bc634e35f6d1a9b7767f3fbfc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 29 Aug 2021 06:28:19 -0400 Subject: fs: Rename AS_THP_SUPPORT and mapping_thp_support These are now indicators of large folio support, not THP support. Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagemap.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 9e33878bf23b..605246452305 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -84,7 +84,7 @@ enum mapping_flags { AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, - AS_THP_SUPPORT = 6, /* THPs supported */ + AS_LARGE_FOLIO_SUPPORT = 6, }; /** @@ -189,12 +189,12 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) */ static inline void mapping_set_large_folios(struct address_space *mapping) { - __set_bit(AS_THP_SUPPORT, &mapping->flags); + __set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } -static inline bool mapping_thp_support(struct address_space *mapping) +static inline bool mapping_large_folio_support(struct address_space *mapping) { - return test_bit(AS_THP_SUPPORT, &mapping->flags); + return test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags); } static inline int filemap_nr_thps(struct address_space *mapping) @@ -209,7 +209,7 @@ static inline int filemap_nr_thps(struct address_space *mapping) static inline void filemap_nr_thps_inc(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_thp_support(mapping)) + if (!mapping_large_folio_support(mapping)) atomic_inc(&mapping->nr_thps); #else WARN_ON_ONCE(1); @@ -219,7 +219,7 @@ static inline void filemap_nr_thps_inc(struct address_space *mapping) static inline void filemap_nr_thps_dec(struct address_space *mapping) { #ifdef CONFIG_READ_ONLY_THP_FOR_FS - if (!mapping_thp_support(mapping)) + if (!mapping_large_folio_support(mapping)) atomic_dec(&mapping->nr_thps); #else WARN_ON_ONCE(1); -- cgit v1.2.3 From 5768d8906bc23d512b1a736c1e198aa833a6daa4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 15 Nov 2021 13:47:13 -0600 Subject: signal: Requeue signals in the appropriate queue In the event that a tracer changes which signal needs to be delivered and that signal is currently blocked then the signal needs to be requeued for later delivery. With the advent of CLONE_THREAD the kernel has 2 signal queues per task. The per process queue and the per task queue. Update the code so that if the signal is removed from the per process queue it is requeued on the per process queue. This is necessary to make it appear the signal was never dequeued. The rr debugger reasonably believes that the state of the process from the last ptrace_stop it observed until PTRACE_EVENT_EXIT can be recreated by simply letting a process run. If a SIGKILL interrupts a ptrace_stop this is not true today. So return signals to their original queue in ptrace_signal so that signals that are not delivered appear like they were never dequeued. Fixes: 794aa320b79d ("[PATCH] sigfix-2.5.40-D6") History Tree: https://git.kernel.org/pub/scm/linux/kernel/git/tglx/history.gi Reviewed-by: Kees Cook Link: https://lkml.kernel.org/r/87zgq4d5r4.fsf_-_@email.froward.int.ebiederm.org Signed-off-by: "Eric W. Biederman" --- fs/signalfd.c | 5 +++-- include/linux/sched/signal.h | 7 ++++--- kernel/signal.c | 21 ++++++++++++++------- 3 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/signalfd.c b/fs/signalfd.c index 040e1cf90528..74f134cd1ff6 100644 --- a/fs/signalfd.c +++ b/fs/signalfd.c @@ -165,11 +165,12 @@ static int signalfd_copyinfo(struct signalfd_siginfo __user *uinfo, static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info, int nonblock) { + enum pid_type type; ssize_t ret; DECLARE_WAITQUEUE(wait, current); spin_lock_irq(¤t->sighand->siglock); - ret = dequeue_signal(current, &ctx->sigmask, info); + ret = dequeue_signal(current, &ctx->sigmask, info, &type); switch (ret) { case 0: if (!nonblock) @@ -184,7 +185,7 @@ static ssize_t signalfd_dequeue(struct signalfd_ctx *ctx, kernel_siginfo_t *info add_wait_queue(¤t->sighand->signalfd_wqh, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); - ret = dequeue_signal(current, &ctx->sigmask, info); + ret = dequeue_signal(current, &ctx->sigmask, info, &type); if (ret != 0) break; if (signal_pending(current)) { diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 23505394ef70..167995d471da 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -286,17 +286,18 @@ static inline int signal_group_exit(const struct signal_struct *sig) extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); -extern int dequeue_signal(struct task_struct *task, - sigset_t *mask, kernel_siginfo_t *info); +extern int dequeue_signal(struct task_struct *task, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; + enum pid_type __type; int ret; spin_lock_irq(&task->sighand->siglock); - ret = dequeue_signal(task, &task->blocked, &__info); + ret = dequeue_signal(task, &task->blocked, &__info, &__type); spin_unlock_irq(&task->sighand->siglock); return ret; diff --git a/kernel/signal.c b/kernel/signal.c index 986fa69c15c5..43e8b7e362b0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -626,7 +626,8 @@ static int __dequeue_signal(struct sigpending *pending, sigset_t *mask, * * All callers have to hold the siglock. */ -int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *info) +int dequeue_signal(struct task_struct *tsk, sigset_t *mask, + kernel_siginfo_t *info, enum pid_type *type) { bool resched_timer = false; int signr; @@ -634,8 +635,10 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in /* We only dequeue private signals from ourselves, we don't let * signalfd steal them */ + *type = PIDTYPE_PID; signr = __dequeue_signal(&tsk->pending, mask, info, &resched_timer); if (!signr) { + *type = PIDTYPE_TGID; signr = __dequeue_signal(&tsk->signal->shared_pending, mask, info, &resched_timer); #ifdef CONFIG_POSIX_TIMERS @@ -2522,7 +2525,7 @@ static void do_freezer_trap(void) freezable_schedule(); } -static int ptrace_signal(int signr, kernel_siginfo_t *info) +static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type) { /* * We do not check sig_kernel_stop(signr) but set this marker @@ -2563,7 +2566,7 @@ static int ptrace_signal(int signr, kernel_siginfo_t *info) /* If the (new) signal is now blocked, requeue it. */ if (sigismember(¤t->blocked, signr)) { - send_signal(signr, info, current, PIDTYPE_PID); + send_signal(signr, info, current, type); signr = 0; } @@ -2664,6 +2667,7 @@ relock: for (;;) { struct k_sigaction *ka; + enum pid_type type; /* Has this task already been marked for death? */ if (signal_group_exit(signal)) { @@ -2706,16 +2710,18 @@ relock: * so that the instruction pointer in the signal stack * frame points to the faulting instruction. */ + type = PIDTYPE_PID; signr = dequeue_synchronous_signal(&ksig->info); if (!signr) - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + signr = dequeue_signal(current, ¤t->blocked, + &ksig->info, &type); if (!signr) break; /* will return 0 */ if (unlikely(current->ptrace) && (signr != SIGKILL) && !(sighand->action[signr -1].sa.sa_flags & SA_IMMUTABLE)) { - signr = ptrace_signal(signr, &ksig->info); + signr = ptrace_signal(signr, &ksig->info, type); if (!signr) continue; } @@ -3540,6 +3546,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, ktime_t *to = NULL, timeout = KTIME_MAX; struct task_struct *tsk = current; sigset_t mask = *which; + enum pid_type type; int sig, ret = 0; if (ts) { @@ -3556,7 +3563,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, signotset(&mask); spin_lock_irq(&tsk->sighand->siglock); - sig = dequeue_signal(tsk, &mask, info); + sig = dequeue_signal(tsk, &mask, info, &type); if (!sig && timeout) { /* * None ready, temporarily unblock those we're interested @@ -3575,7 +3582,7 @@ static int do_sigtimedwait(const sigset_t *which, kernel_siginfo_t *info, spin_lock_irq(&tsk->sighand->siglock); __set_task_blocked(tsk, &tsk->real_blocked); sigemptyset(&tsk->real_blocked); - sig = dequeue_signal(tsk, &mask, info); + sig = dequeue_signal(tsk, &mask, info, &type); } spin_unlock_irq(&tsk->sighand->siglock); -- cgit v1.2.3 From e0dbd7b0ed021fb9250f7ba4d759325678efefb5 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Tue, 16 Nov 2021 23:44:28 +0100 Subject: power: supply: core: Add kerneldoc to battery struct This complements the struct power_supply_battery_info with extensive kerneldoc explaining the different semantics of the fields, including an overview of the CC/CV charging concepts implicit in some of the struct members. This is done to first establish semantics before I can add more charging methods by breaking out the CC/CV parameters to its own struct. Tested-by: Randy Dunlap Acked-by: Randy Dunlap Reviewed-by: Matti Vaittinen Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- include/linux/power_supply.h | 215 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 192 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 2d1318fe2455..f6e94eae4f28 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -343,37 +343,206 @@ struct power_supply_resistance_temp_table { #define POWER_SUPPLY_OCV_TEMP_MAX 20 -/* +/** + * struct power_supply_battery_info - information about batteries + * @technology: from the POWER_SUPPLY_TECHNOLOGY_* enum + * @energy_full_design_uwh: energy content when fully charged in microwatt + * hours + * @charge_full_design_uah: charge content when fully charged in microampere + * hours + * @voltage_min_design_uv: minimum voltage across the poles when the battery + * is at minimum voltage level in microvolts. If the voltage drops below this + * level the battery will need precharging when using CC/CV charging. + * @voltage_max_design_uv: voltage across the poles when the battery is fully + * charged in microvolts. This is the "nominal voltage" i.e. the voltage + * printed on the label of the battery. + * @tricklecharge_current_ua: the tricklecharge current used when trickle + * charging the battery in microamperes. This is the charging phase when the + * battery is completely empty and we need to carefully trickle in some + * charge until we reach the precharging voltage. + * @precharge_current_ua: current to use in the precharge phase in microamperes, + * the precharge rate is limited by limiting the current to this value. + * @precharge_voltage_max_uv: the maximum voltage allowed when precharging in + * microvolts. When we pass this voltage we will nominally switch over to the + * CC (constant current) charging phase defined by constant_charge_current_ua + * and constant_charge_voltage_max_uv. + * @charge_term_current_ua: when the current in the CV (constant voltage) + * charging phase drops below this value in microamperes the charging will + * terminate completely and not restart until the voltage over the battery + * poles reach charge_restart_voltage_uv unless we use maintenance charging. + * @charge_restart_voltage_uv: when the battery has been fully charged by + * CC/CV charging and charging has been disabled, and the voltage subsequently + * drops below this value in microvolts, the charging will be restarted + * (typically using CV charging). + * @overvoltage_limit_uv: If the voltage exceeds the nominal voltage + * voltage_max_design_uv and we reach this voltage level, all charging must + * stop and emergency procedures take place, such as shutting down the system + * in some cases. + * @constant_charge_current_max_ua: current in microamperes to use in the CC + * (constant current) charging phase. The charging rate is limited + * by this current. This is the main charging phase and as the current is + * constant into the battery the voltage slowly ascends to + * constant_charge_voltage_max_uv. + * @constant_charge_voltage_max_uv: voltage in microvolts signifying the end of + * the CC (constant current) charging phase and the beginning of the CV + * (constant voltage) charging phase. + * @factory_internal_resistance_uohm: the internal resistance of the battery + * at fabrication time, expressed in microohms. This resistance will vary + * depending on the lifetime and charge of the battery, so this is just a + * nominal ballpark figure. + * @ocv_temp: array indicating the open circuit voltage (OCV) capacity + * temperature indices. This is an array of temperatures in degrees Celsius + * indicating which capacity table to use for a certain temperature, since + * the capacity for reasons of chemistry will be different at different + * temperatures. Determining capacity is a multivariate problem and the + * temperature is the first variable we determine. + * @temp_ambient_alert_min: the battery will go outside of operating conditions + * when the ambient temperature goes below this temperature in degrees + * Celsius. + * @temp_ambient_alert_max: the battery will go outside of operating conditions + * when the ambient temperature goes above this temperature in degrees + * Celsius. + * @temp_alert_min: the battery should issue an alert if the internal + * temperature goes below this temperature in degrees Celsius. + * @temp_alert_max: the battery should issue an alert if the internal + * temperature goes above this temperature in degrees Celsius. + * @temp_min: the battery will go outside of operating conditions when + * the internal temperature goes below this temperature in degrees Celsius. + * Normally this means the system should shut down. + * @temp_max: the battery will go outside of operating conditions when + * the internal temperature goes above this temperature in degrees Celsius. + * Normally this means the system should shut down. + * @ocv_table: for each entry in ocv_temp there is a corresponding entry in + * ocv_table and a size for each entry in ocv_table_size. These arrays + * determine the capacity in percent in relation to the voltage in microvolts + * at the indexed temperature. + * @ocv_table_size: for each entry in ocv_temp this array is giving the size of + * each entry in the array of capacity arrays in ocv_table. + * @resist_table: this is a table that correlates a battery temperature to the + * expected internal resistance at this temperature. The resistance is given + * as a percentage of factory_internal_resistance_uohm. Knowing the + * resistance of the battery is usually necessary for calculating the open + * circuit voltage (OCV) that is then used with the ocv_table to calculate + * the capacity of the battery. The resist_table must be ordered descending + * by temperature: highest temperature with lowest resistance first, lowest + * temperature with highest resistance last. + * @resist_table_size: the number of items in the resist_table. + * * This is the recommended struct to manage static battery parameters, * populated by power_supply_get_battery_info(). Most platform drivers should * use these for consistency. + * * Its field names must correspond to elements in enum power_supply_property. * The default field value is -EINVAL. - * Power supply class itself doesn't use this. + * + * The charging parameters here assume a CC/CV charging scheme. This method + * is most common with Lithium Ion batteries (other methods are possible) and + * looks as follows: + * + * ^ Battery voltage + * | --- overvoltage_limit_uv + * | + * | ................................................... + * | .. constant_charge_voltage_max_uv + * | .. + * | . + * | . + * | . + * | . + * | . + * | .. precharge_voltage_max_uv + * | .. + * |. (trickle charging) + * +------------------------------------------------------------------> time + * + * ^ Current into the battery + * | + * | ............. constant_charge_current_max_ua + * | . . + * | . . + * | . . + * | . . + * | . .. + * | . .... + * | . ..... + * | ... precharge_current_ua ....... charge_term_current_ua + * | . . + * | . . + * |.... tricklecharge_current_ua . + * | . + * +-----------------------------------------------------------------> time + * + * These diagrams are synchronized on time and the voltage and current + * follow each other. + * + * With CC/CV charging commence over time like this for an empty battery: + * + * 1. When the battery is completely empty it may need to be charged with + * an especially small current so that electrons just "trickle in", + * this is the tricklecharge_current_ua. + * + * 2. Next a small initial pre-charge current (precharge_current_ua) + * is applied if the voltage is below precharge_voltage_max_uv until we + * reach precharge_voltage_max_uv. CAUTION: in some texts this is referred + * to as "trickle charging" but the use in the Linux kernel is different + * see below! + * + * 3. Then the main charging current is applied, which is called the constant + * current (CC) phase. A current regulator is set up to allow + * constant_charge_current_max_ua of current to flow into the battery. + * The chemical reaction in the battery will make the voltage go up as + * charge goes into the battery. This current is applied until we reach + * the constant_charge_voltage_max_uv voltage. + * + * 4. At this voltage we switch over to the constant voltage (CV) phase. This + * means we allow current to go into the battery, but we keep the voltage + * fixed. This current will continue to charge the battery while keeping + * the voltage the same. A chemical reaction in the battery goes on + * storing energy without affecting the voltage. Over time the current + * will slowly drop and when we reach charge_term_current_ua we will + * end the constant voltage phase. + * + * After this the battery is fully charged, and if we do not support maintenance + * charging, the charging will not restart until power dissipation makes the + * voltage fall so that we reach charge_restart_voltage_uv and at this point + * we restart charging at the appropriate phase, usually this will be inside + * the CV phase. + * + * If we support maintenance charging the voltage is however kept high after + * the CV phase with a very low current. This is meant to let the same charge + * go in for usage while the charger is still connected, mainly for + * dissipation for the power consuming entity while connected to the + * charger. + * + * All charging MUST terminate if the overvoltage_limit_uv is ever reached. + * Overcharging Lithium Ion cells can be DANGEROUS and lead to fire or + * explosions. + * + * The power supply class itself doesn't use this struct as of now. */ struct power_supply_battery_info { - unsigned int technology; /* from the enum above */ - int energy_full_design_uwh; /* microWatt-hours */ - int charge_full_design_uah; /* microAmp-hours */ - int voltage_min_design_uv; /* microVolts */ - int voltage_max_design_uv; /* microVolts */ - int tricklecharge_current_ua; /* microAmps */ - int precharge_current_ua; /* microAmps */ - int precharge_voltage_max_uv; /* microVolts */ - int charge_term_current_ua; /* microAmps */ - int charge_restart_voltage_uv; /* microVolts */ - int overvoltage_limit_uv; /* microVolts */ - int constant_charge_current_max_ua; /* microAmps */ - int constant_charge_voltage_max_uv; /* microVolts */ - int factory_internal_resistance_uohm; /* microOhms */ - int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX];/* celsius */ - int temp_ambient_alert_min; /* celsius */ - int temp_ambient_alert_max; /* celsius */ - int temp_alert_min; /* celsius */ - int temp_alert_max; /* celsius */ - int temp_min; /* celsius */ - int temp_max; /* celsius */ + unsigned int technology; + int energy_full_design_uwh; + int charge_full_design_uah; + int voltage_min_design_uv; + int voltage_max_design_uv; + int tricklecharge_current_ua; + int precharge_current_ua; + int precharge_voltage_max_uv; + int charge_term_current_ua; + int charge_restart_voltage_uv; + int overvoltage_limit_uv; + int constant_charge_current_max_ua; + int constant_charge_voltage_max_uv; + int factory_internal_resistance_uohm; + int ocv_temp[POWER_SUPPLY_OCV_TEMP_MAX]; + int temp_ambient_alert_min; + int temp_ambient_alert_max; + int temp_alert_min; + int temp_alert_max; + int temp_min; + int temp_max; struct power_supply_battery_ocv_table *ocv_table[POWER_SUPPLY_OCV_TEMP_MAX]; int ocv_table_size[POWER_SUPPLY_OCV_TEMP_MAX]; struct power_supply_resistance_temp_table *resist_table; -- cgit v1.2.3 From 6bb835f3d00467c9a5e35f4955afa29df96a404e Mon Sep 17 00:00:00 2001 From: Andriy Tryshnivskyy Date: Sun, 24 Oct 2021 12:16:26 +0300 Subject: iio: core: Introduce IIO_VAL_INT_64. Introduce IIO_VAL_INT_64 to read 64-bit value for channel attribute. Val is used as lower 32 bits. Signed-off-by: Andriy Tryshnivskyy Link: https://lore.kernel.org/r/20211024091627.28031-2-andriy.tryshnivskyy@opensynergy.com Signed-off-by: Jonathan Cameron --- drivers/iio/industrialio-core.c | 3 +++ include/linux/iio/types.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index 463a63d5bf56..d94d26b11473 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -702,6 +702,9 @@ static ssize_t __iio_format_value(char *buf, size_t offset, unsigned int type, } case IIO_VAL_CHAR: return sysfs_emit_at(buf, offset, "%c", (char)vals[0]); + case IIO_VAL_INT_64: + tmp2 = (s64)((((u64)vals[1]) << 32) | (u32)vals[0]); + return sysfs_emit_at(buf, offset, "%lld", tmp2); default: return 0; } diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h index 84b3f8175cc6..a7aa91f3a8dc 100644 --- a/include/linux/iio/types.h +++ b/include/linux/iio/types.h @@ -24,6 +24,7 @@ enum iio_event_info { #define IIO_VAL_INT_PLUS_NANO 3 #define IIO_VAL_INT_PLUS_MICRO_DB 4 #define IIO_VAL_INT_MULTIPLE 5 +#define IIO_VAL_INT_64 6 /* 64-bit data, val is lower 32 bits */ #define IIO_VAL_FRACTIONAL 10 #define IIO_VAL_FRACTIONAL_LOG2 11 #define IIO_VAL_CHAR 12 -- cgit v1.2.3 From 2925748eadc33cba3bded7b69475a1b002b124ac Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 17 Nov 2021 13:22:53 +0000 Subject: firmware: cs_dsp: Add version checks on coefficient loading The firmware coefficient files contain version information that is currently ignored by the cs_dsp code. This information specifies which version of the firmware the coefficient were generated for. Add a check into the code which prints a warning in the case the coefficient and firmware differ in version, in many cases this will be ok but it is not always, so best to let the user know there is a potential issue. Co-authored-by: Simon Trimmer Signed-off-by: Simon Trimmer Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20211117132300.1290-3-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 49 +++++++++++++++++++++++++--------- include/linux/firmware/cirrus/cs_dsp.h | 2 ++ 2 files changed, 38 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 0d1ba7d8efa4..0da454a8498d 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1569,7 +1569,7 @@ EXPORT_SYMBOL_GPL(cs_dsp_find_alg_region); static struct cs_dsp_alg_region *cs_dsp_create_region(struct cs_dsp *dsp, int type, __be32 id, - __be32 base) + __be32 ver, __be32 base) { struct cs_dsp_alg_region *alg_region; @@ -1579,6 +1579,7 @@ static struct cs_dsp_alg_region *cs_dsp_create_region(struct cs_dsp *dsp, alg_region->type = type; alg_region->alg = be32_to_cpu(id); + alg_region->ver = be32_to_cpu(ver); alg_region->base = be32_to_cpu(base); list_add_tail(&alg_region->list, &dsp->alg_regions); @@ -1628,14 +1629,14 @@ static void cs_dsp_parse_wmfw_v3_id_header(struct cs_dsp *dsp, nalgs); } -static int cs_dsp_create_regions(struct cs_dsp *dsp, __be32 id, int nregions, - const int *type, __be32 *base) +static int cs_dsp_create_regions(struct cs_dsp *dsp, __be32 id, __be32 ver, + int nregions, const int *type, __be32 *base) { struct cs_dsp_alg_region *alg_region; int i; for (i = 0; i < nregions; i++) { - alg_region = cs_dsp_create_region(dsp, type[i], id, base[i]); + alg_region = cs_dsp_create_region(dsp, type[i], id, ver, base[i]); if (IS_ERR(alg_region)) return PTR_ERR(alg_region); } @@ -1670,12 +1671,14 @@ static int cs_dsp_adsp1_setup_algs(struct cs_dsp *dsp) cs_dsp_parse_wmfw_id_header(dsp, &adsp1_id.fw, n_algs); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_ZM, - adsp1_id.fw.id, adsp1_id.zm); + adsp1_id.fw.id, adsp1_id.fw.ver, + adsp1_id.zm); if (IS_ERR(alg_region)) return PTR_ERR(alg_region); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_DM, - adsp1_id.fw.id, adsp1_id.dm); + adsp1_id.fw.id, adsp1_id.fw.ver, + adsp1_id.dm); if (IS_ERR(alg_region)) return PTR_ERR(alg_region); @@ -1698,6 +1701,7 @@ static int cs_dsp_adsp1_setup_algs(struct cs_dsp *dsp) alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_DM, adsp1_alg[i].alg.id, + adsp1_alg[i].alg.ver, adsp1_alg[i].dm); if (IS_ERR(alg_region)) { ret = PTR_ERR(alg_region); @@ -1719,6 +1723,7 @@ static int cs_dsp_adsp1_setup_algs(struct cs_dsp *dsp) alg_region = cs_dsp_create_region(dsp, WMFW_ADSP1_ZM, adsp1_alg[i].alg.id, + adsp1_alg[i].alg.ver, adsp1_alg[i].zm); if (IS_ERR(alg_region)) { ret = PTR_ERR(alg_region); @@ -1771,17 +1776,20 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) cs_dsp_parse_wmfw_id_header(dsp, &adsp2_id.fw, n_algs); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, - adsp2_id.fw.id, adsp2_id.xm); + adsp2_id.fw.id, adsp2_id.fw.ver, + adsp2_id.xm); if (IS_ERR(alg_region)) return PTR_ERR(alg_region); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_YM, - adsp2_id.fw.id, adsp2_id.ym); + adsp2_id.fw.id, adsp2_id.fw.ver, + adsp2_id.ym); if (IS_ERR(alg_region)) return PTR_ERR(alg_region); alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_ZM, - adsp2_id.fw.id, adsp2_id.zm); + adsp2_id.fw.id, adsp2_id.fw.ver, + adsp2_id.zm); if (IS_ERR(alg_region)) return PTR_ERR(alg_region); @@ -1806,6 +1814,7 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_XM, adsp2_alg[i].alg.id, + adsp2_alg[i].alg.ver, adsp2_alg[i].xm); if (IS_ERR(alg_region)) { ret = PTR_ERR(alg_region); @@ -1827,6 +1836,7 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_YM, adsp2_alg[i].alg.id, + adsp2_alg[i].alg.ver, adsp2_alg[i].ym); if (IS_ERR(alg_region)) { ret = PTR_ERR(alg_region); @@ -1848,6 +1858,7 @@ static int cs_dsp_adsp2_setup_algs(struct cs_dsp *dsp) alg_region = cs_dsp_create_region(dsp, WMFW_ADSP2_ZM, adsp2_alg[i].alg.id, + adsp2_alg[i].alg.ver, adsp2_alg[i].zm); if (IS_ERR(alg_region)) { ret = PTR_ERR(alg_region); @@ -1873,7 +1884,7 @@ out: return ret; } -static int cs_dsp_halo_create_regions(struct cs_dsp *dsp, __be32 id, +static int cs_dsp_halo_create_regions(struct cs_dsp *dsp, __be32 id, __be32 ver, __be32 xm_base, __be32 ym_base) { static const int types[] = { @@ -1882,7 +1893,7 @@ static int cs_dsp_halo_create_regions(struct cs_dsp *dsp, __be32 id, }; __be32 bases[] = { xm_base, xm_base, ym_base, ym_base }; - return cs_dsp_create_regions(dsp, id, ARRAY_SIZE(types), types, bases); + return cs_dsp_create_regions(dsp, id, ver, ARRAY_SIZE(types), types, bases); } static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) @@ -1910,7 +1921,7 @@ static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) cs_dsp_parse_wmfw_v3_id_header(dsp, &halo_id.fw, n_algs); - ret = cs_dsp_halo_create_regions(dsp, halo_id.fw.id, + ret = cs_dsp_halo_create_regions(dsp, halo_id.fw.id, halo_id.fw.ver, halo_id.xm_base, halo_id.ym_base); if (ret) return ret; @@ -1934,6 +1945,7 @@ static int cs_dsp_halo_setup_algs(struct cs_dsp *dsp) be32_to_cpu(halo_alg[i].ym_base)); ret = cs_dsp_halo_create_regions(dsp, halo_alg[i].alg.id, + halo_alg[i].alg.ver, halo_alg[i].xm_base, halo_alg[i].ym_base); if (ret) @@ -1955,7 +1967,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware const struct cs_dsp_region *mem; struct cs_dsp_alg_region *alg_region; const char *region_name; - int ret, pos, blocks, type, offset, reg; + int ret, pos, blocks, type, offset, reg, version; struct cs_dsp_buf *buf; if (!firmware) @@ -1999,6 +2011,7 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware type = le16_to_cpu(blk->type); offset = le16_to_cpu(blk->offset); + version = le32_to_cpu(blk->ver) >> 8; cs_dsp_dbg(dsp, "%s.%d: %x v%d.%d.%d\n", file, blocks, le32_to_cpu(blk->id), @@ -2056,6 +2069,16 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware alg_region = cs_dsp_find_alg_region(dsp, type, le32_to_cpu(blk->id)); if (alg_region) { + if (version != alg_region->ver) + cs_dsp_warn(dsp, + "Algorithm coefficient version %d.%d.%d but expected %d.%d.%d\n", + (version >> 16) & 0xFF, + (version >> 8) & 0xFF, + version & 0xFF, + (alg_region->ver >> 16) & 0xFF, + (alg_region->ver >> 8) & 0xFF, + alg_region->ver & 0xFF); + reg = alg_region->base; reg = dsp->ops->region_to_reg(mem, reg); reg += offset; diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 3a54b1afc48f..ce54705e2bec 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -54,12 +54,14 @@ struct cs_dsp_region { * struct cs_dsp_alg_region - Describes a logical algorithm region in DSP address space * @list: List node for internal use * @alg: Algorithm id + * @ver: Expected algorithm version * @type: Memory region type * @base: Address of region */ struct cs_dsp_alg_region { struct list_head list; unsigned int alg; + unsigned int ver; int type; unsigned int base; }; -- cgit v1.2.3 From 14055b5a3a23204c4702ae5d3f2a819ee081ce33 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 17 Nov 2021 13:22:54 +0000 Subject: firmware: cs_dsp: Add pre_run callback The code already has a post_run callback, add a matching pre_run callback to the client_ops that is called before execution is started. This callback provides a convenient place for the client code to set DSP controls or hardware that requires configuration before the DSP core actually starts execution. Note that placing this callback before cs_dsp_coeff_sync_controls is important to ensure that any control values are then correctly synced out to the chip. Co-authored-by: Simon Trimmer Signed-off-by: Simon Trimmer Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20211117132300.1290-4-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 6 ++++++ include/linux/firmware/cirrus/cs_dsp.h | 4 +++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 0da454a8498d..ef7afadea42d 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -2627,6 +2627,12 @@ int cs_dsp_run(struct cs_dsp *dsp) goto err; } + if (dsp->client_ops->pre_run) { + ret = dsp->client_ops->pre_run(dsp); + if (ret) + goto err; + } + /* Sync set controls */ ret = cs_dsp_coeff_sync_controls(dsp); if (ret != 0) diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index ce54705e2bec..0bf849baeaa5 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -187,7 +187,8 @@ struct cs_dsp { * struct cs_dsp_client_ops - client callbacks * @control_add: Called under the pwr_lock when a control is created * @control_remove: Called under the pwr_lock when a control is destroyed - * @post_run: Called under the pwr_lock by cs_dsp_run() + * @pre_run: Called under the pwr_lock by cs_dsp_run() before the core is started + * @post_run: Called under the pwr_lock by cs_dsp_run() after the core is started * @post_stop: Called under the pwr_lock by cs_dsp_stop() * @watchdog_expired: Called when a watchdog expiry is detected * @@ -197,6 +198,7 @@ struct cs_dsp { struct cs_dsp_client_ops { int (*control_add)(struct cs_dsp_coeff_ctl *ctl); void (*control_remove)(struct cs_dsp_coeff_ctl *ctl); + int (*pre_run)(struct cs_dsp *dsp); int (*post_run)(struct cs_dsp *dsp); void (*post_stop)(struct cs_dsp *dsp); void (*watchdog_expired)(struct cs_dsp *dsp); -- cgit v1.2.3 From b329b3d39497a9fdb175d7e4fd77ae7170d5d26c Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 17 Nov 2021 13:22:58 +0000 Subject: firmware: cs_dsp: Clarify some kernel doc comments Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20211117132300.1290-8-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 4 ++-- include/linux/firmware/cirrus/cs_dsp.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 9eecd1626537..d1bcade2efe2 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -746,7 +746,7 @@ static int cs_dsp_coeff_write_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, * cs_dsp_coeff_write_ctrl() - Writes the given buffer to the given coefficient control * @ctl: pointer to coefficient control * @buf: the buffer to write to the given control - * @len: the length of the buffer + * @len: the length of the buffer in bytes * * Must be called with pwr_lock held. * @@ -808,7 +808,7 @@ static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, void *buf, s * cs_dsp_coeff_read_ctrl() - Reads the given coefficient control into the given buffer * @ctl: pointer to coefficient control * @buf: the buffer to store to the given control - * @len: the length of the buffer + * @len: the length of the buffer in bytes * * Must be called with pwr_lock held. * diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 0bf849baeaa5..1ad1b173417a 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -76,8 +76,8 @@ struct cs_dsp_alg_region { * @enabled: Flag indicating whether control is enabled * @list: List node for internal use * @cache: Cached value of the control - * @offset: Offset of control within alg_region - * @len: Length of the cached value + * @offset: Offset of control within alg_region in words + * @len: Length of the cached value in bytes * @set: Flag indicating the value has been written by the user * @flags: Bitfield of WMFW_CTL_FLAG_ control flags defined in wmfw.h * @type: One of the WMFW_CTL_TYPE_ control types defined in wmfw.h -- cgit v1.2.3 From f444da38ac924748de696c393327a44c4b8d727e Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 17 Nov 2021 13:22:59 +0000 Subject: firmware: cs_dsp: Add offset to cs_dsp read/write Provide a mechanism to access only part of a control through the cs_dsp interface. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20211117132300.1290-9-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 44 +++++++++++++++++++++------------- include/linux/firmware/cirrus/cs_dsp.h | 6 +++-- sound/soc/codecs/wm_adsp.c | 14 +++++------ 3 files changed, 39 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index d1bcade2efe2..5fe08de91ecd 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -616,7 +616,8 @@ static void cs_dsp_halo_show_fw_status(struct cs_dsp *dsp) offs[0], offs[1], offs[2], offs[3]); } -static int cs_dsp_coeff_base_reg(struct cs_dsp_coeff_ctl *ctl, unsigned int *reg) +static int cs_dsp_coeff_base_reg(struct cs_dsp_coeff_ctl *ctl, unsigned int *reg, + unsigned int off) { const struct cs_dsp_alg_region *alg_region = &ctl->alg_region; struct cs_dsp *dsp = ctl->dsp; @@ -629,7 +630,7 @@ static int cs_dsp_coeff_base_reg(struct cs_dsp_coeff_ctl *ctl, unsigned int *reg return -EINVAL; } - *reg = dsp->ops->region_to_reg(mem, ctl->alg_region.base + ctl->offset); + *reg = dsp->ops->region_to_reg(mem, ctl->alg_region.base + ctl->offset + off); return 0; } @@ -658,7 +659,7 @@ int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int if (!dsp->running) return -EPERM; - ret = cs_dsp_coeff_base_reg(ctl, ®); + ret = cs_dsp_coeff_base_reg(ctl, ®, 0); if (ret) return ret; @@ -712,14 +713,14 @@ int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int EXPORT_SYMBOL_GPL(cs_dsp_coeff_write_acked_control); static int cs_dsp_coeff_write_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, - const void *buf, size_t len) + unsigned int off, const void *buf, size_t len) { struct cs_dsp *dsp = ctl->dsp; void *scratch; int ret; unsigned int reg; - ret = cs_dsp_coeff_base_reg(ctl, ®); + ret = cs_dsp_coeff_base_reg(ctl, ®, off); if (ret) return ret; @@ -745,6 +746,7 @@ static int cs_dsp_coeff_write_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, /** * cs_dsp_coeff_write_ctrl() - Writes the given buffer to the given coefficient control * @ctl: pointer to coefficient control + * @off: word offset at which data should be written * @buf: the buffer to write to the given control * @len: the length of the buffer in bytes * @@ -752,7 +754,8 @@ static int cs_dsp_coeff_write_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, * * Return: Zero for success, a negative number on error. */ -int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_t len) +int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, + unsigned int off, const void *buf, size_t len) { int ret = 0; @@ -761,27 +764,31 @@ int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_ if (!ctl) return -ENOENT; + if (len + off * sizeof(u32) > ctl->len) + return -EINVAL; + if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) ret = -EPERM; else if (buf != ctl->cache) - memcpy(ctl->cache, buf, len); + memcpy(ctl->cache + off * sizeof(u32), buf, len); ctl->set = 1; if (ctl->enabled && ctl->dsp->running) - ret = cs_dsp_coeff_write_ctrl_raw(ctl, buf, len); + ret = cs_dsp_coeff_write_ctrl_raw(ctl, off, buf, len); return ret; } EXPORT_SYMBOL_GPL(cs_dsp_coeff_write_ctrl); -static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len) +static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, + unsigned int off, void *buf, size_t len) { struct cs_dsp *dsp = ctl->dsp; void *scratch; int ret; unsigned int reg; - ret = cs_dsp_coeff_base_reg(ctl, ®); + ret = cs_dsp_coeff_base_reg(ctl, ®, off); if (ret) return ret; @@ -807,6 +814,7 @@ static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, void *buf, s /** * cs_dsp_coeff_read_ctrl() - Reads the given coefficient control into the given buffer * @ctl: pointer to coefficient control + * @off: word offset at which data should be read * @buf: the buffer to store to the given control * @len: the length of the buffer in bytes * @@ -814,7 +822,8 @@ static int cs_dsp_coeff_read_ctrl_raw(struct cs_dsp_coeff_ctl *ctl, void *buf, s * * Return: Zero for success, a negative number on error. */ -int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len) +int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, + unsigned int off, void *buf, size_t len) { int ret = 0; @@ -823,17 +832,20 @@ int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len) if (!ctl) return -ENOENT; + if (len + off * sizeof(u32) > ctl->len) + return -EINVAL; + if (ctl->flags & WMFW_CTL_FLAG_VOLATILE) { if (ctl->enabled && ctl->dsp->running) - return cs_dsp_coeff_read_ctrl_raw(ctl, buf, len); + return cs_dsp_coeff_read_ctrl_raw(ctl, off, buf, len); else return -EPERM; } else { if (!ctl->flags && ctl->enabled && ctl->dsp->running) - ret = cs_dsp_coeff_read_ctrl_raw(ctl, ctl->cache, ctl->len); + ret = cs_dsp_coeff_read_ctrl_raw(ctl, 0, ctl->cache, ctl->len); if (buf != ctl->cache) - memcpy(buf, ctl->cache, len); + memcpy(buf, ctl->cache + off * sizeof(u32), len); } return ret; @@ -857,7 +869,7 @@ static int cs_dsp_coeff_init_control_caches(struct cs_dsp *dsp) * created so we don't need to do anything. */ if (!ctl->flags || (ctl->flags & WMFW_CTL_FLAG_READABLE)) { - ret = cs_dsp_coeff_read_ctrl_raw(ctl, ctl->cache, ctl->len); + ret = cs_dsp_coeff_read_ctrl_raw(ctl, 0, ctl->cache, ctl->len); if (ret < 0) return ret; } @@ -875,7 +887,7 @@ static int cs_dsp_coeff_sync_controls(struct cs_dsp *dsp) if (!ctl->enabled) continue; if (ctl->set && !(ctl->flags & WMFW_CTL_FLAG_VOLATILE)) { - ret = cs_dsp_coeff_write_ctrl_raw(ctl, ctl->cache, + ret = cs_dsp_coeff_write_ctrl_raw(ctl, 0, ctl->cache, ctl->len); if (ret < 0) return ret; diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h index 1ad1b173417a..38b4da3ddfe4 100644 --- a/include/linux/firmware/cirrus/cs_dsp.h +++ b/include/linux/firmware/cirrus/cs_dsp.h @@ -232,8 +232,10 @@ void cs_dsp_init_debugfs(struct cs_dsp *dsp, struct dentry *debugfs_root); void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp); int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id); -int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, const void *buf, size_t len); -int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, void *buf, size_t len); +int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + const void *buf, size_t len); +int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off, + void *buf, size_t len); struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type, unsigned int alg); diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c index 404717e30f44..f084b093cff6 100644 --- a/sound/soc/codecs/wm_adsp.c +++ b/sound/soc/codecs/wm_adsp.c @@ -401,7 +401,7 @@ static int wm_coeff_put(struct snd_kcontrol *kctl, int ret = 0; mutex_lock(&cs_ctl->dsp->pwr_lock); - ret = cs_dsp_coeff_write_ctrl(cs_ctl, p, cs_ctl->len); + ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, p, cs_ctl->len); mutex_unlock(&cs_ctl->dsp->pwr_lock); return ret; @@ -421,7 +421,7 @@ static int wm_coeff_tlv_put(struct snd_kcontrol *kctl, if (copy_from_user(cs_ctl->cache, bytes, size)) ret = -EFAULT; else - ret = cs_dsp_coeff_write_ctrl(cs_ctl, cs_ctl->cache, size); + ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, cs_ctl->cache, size); mutex_unlock(&cs_ctl->dsp->pwr_lock); @@ -464,7 +464,7 @@ static int wm_coeff_get(struct snd_kcontrol *kctl, int ret; mutex_lock(&cs_ctl->dsp->pwr_lock); - ret = cs_dsp_coeff_read_ctrl(cs_ctl, p, cs_ctl->len); + ret = cs_dsp_coeff_read_ctrl(cs_ctl, 0, p, cs_ctl->len); mutex_unlock(&cs_ctl->dsp->pwr_lock); return ret; @@ -481,7 +481,7 @@ static int wm_coeff_tlv_get(struct snd_kcontrol *kctl, mutex_lock(&cs_ctl->dsp->pwr_lock); - ret = cs_dsp_coeff_read_ctrl(cs_ctl, cs_ctl->cache, size); + ret = cs_dsp_coeff_read_ctrl(cs_ctl, 0, cs_ctl->cache, size); if (!ret && copy_to_user(bytes, cs_ctl->cache, size)) ret = -EFAULT; @@ -684,7 +684,7 @@ int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type, if (len > cs_ctl->len) return -EINVAL; - ret = cs_dsp_coeff_write_ctrl(cs_ctl, buf, len); + ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len); if (ret) return ret; @@ -723,7 +723,7 @@ int wm_adsp_read_ctl(struct wm_adsp *dsp, const char *name, int type, if (len > cs_ctl->len) return -EINVAL; - return cs_dsp_coeff_read_ctrl(cs_ctl, buf, len); + return cs_dsp_coeff_read_ctrl(cs_ctl, 0, buf, len); } EXPORT_SYMBOL_GPL(wm_adsp_read_ctl); @@ -1432,7 +1432,7 @@ static int wm_adsp_buffer_parse_coeff(struct cs_dsp_coeff_ctl *cs_ctl) int ret, i; for (i = 0; i < 5; ++i) { - ret = cs_dsp_coeff_read_ctrl(cs_ctl, &coeff_v1, sizeof(coeff_v1)); + ret = cs_dsp_coeff_read_ctrl(cs_ctl, 0, &coeff_v1, sizeof(coeff_v1)); if (ret < 0) return ret; -- cgit v1.2.3 From 5c903f64ce97172d63f7591cfa9e37cba58867b2 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Wed, 17 Nov 2021 13:23:00 +0000 Subject: firmware: cs_dsp: Allow creation of event controls Some firmwares contain controls intended to convey firmware state back to the host. Whilst more infrastructure will probably be needed for these in time, as a first step allow creation of the controls, so said firmwares arn't completely rejected. Signed-off-by: Charles Keepax Link: https://lore.kernel.org/r/20211117132300.1290-10-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown --- drivers/firmware/cirrus/cs_dsp.c | 1 + include/linux/firmware/cirrus/wmfw.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 5fe08de91ecd..3814cbba0a54 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -1177,6 +1177,7 @@ static int cs_dsp_parse_coeff(struct cs_dsp *dsp, return -EINVAL; break; case WMFW_CTL_TYPE_HOSTEVENT: + case WMFW_CTL_TYPE_FWEVENT: ret = cs_dsp_check_coeff_flags(dsp, &coeff_blk, WMFW_CTL_FLAG_SYS | WMFW_CTL_FLAG_VOLATILE | diff --git a/include/linux/firmware/cirrus/wmfw.h b/include/linux/firmware/cirrus/wmfw.h index a19bf7c6fc8b..74e5a4f6c13a 100644 --- a/include/linux/firmware/cirrus/wmfw.h +++ b/include/linux/firmware/cirrus/wmfw.h @@ -29,6 +29,7 @@ #define WMFW_CTL_TYPE_ACKED 0x1000 /* acked control */ #define WMFW_CTL_TYPE_HOSTEVENT 0x1001 /* event control */ #define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */ +#define WMFW_CTL_TYPE_FWEVENT 0x1004 /* firmware event control */ struct wmfw_header { char magic[4]; -- cgit v1.2.3 From 357a18ad230f0867791b788d2b1d6f280f6f6e61 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 15 Nov 2021 16:50:27 +0000 Subject: KVM: Kill kvm_map_gfn() / kvm_unmap_gfn() and gfn_to_pfn_cache In commit 7e2175ebd695 ("KVM: x86: Fix recording of guest steal time / preempted status") I removed the only user of these functions because it was basically impossible to use them safely. There are two stages to the GFN->PFN mapping; first through the KVM memslots to a userspace HVA and then through the page tables to translate that HVA to an underlying PFN. Invalidations of the former were being handled correctly, but no attempt was made to use the MMU notifiers to invalidate the cache when the HVA->GFN mapping changed. As a prelude to reinventing the gfn_to_pfn_cache with more usable semantics, rip it out entirely and untangle the implementation of the unsafe kvm_vcpu_map()/kvm_vcpu_unmap() functions from it. All current users of kvm_vcpu_map() also look broken right now, and will be dealt with separately. They broadly fall into two classes: * Those which map, access the data and immediately unmap. This is mostly gratuitous and could just as well use the existing user HVA, and could probably benefit from a gfn_to_hva_cache as they do so. * Those which keep the mapping around for a longer time, perhaps even using the PFN directly from the guest. These will need to be converted to the new gfn_to_pfn_cache and then kvm_vcpu_map() can be removed too. Signed-off-by: David Woodhouse Message-Id: <20211115165030.7422-8-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 6 +-- include/linux/kvm_types.h | 7 ---- virt/kvm/kvm_main.c | 100 +++++----------------------------------------- 3 files changed, 12 insertions(+), 101 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 60a35d9fe259..eb625af4fc5e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -866,7 +866,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -942,12 +942,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2237abb93ccd..234eab059839 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,13 +53,6 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; -struct gfn_to_pfn_cache { - u64 generation; - gfn_t gfn; - kvm_pfn_t pfn; - bool dirty; -}; - #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 3f6d450355f0..7a28c29dca8a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2548,72 +2548,36 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_page); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache) +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty) { if (pfn == 0) return; - if (cache) - cache->pfn = cache->gfn = 0; - if (dirty) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); } -static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn, - struct gfn_to_pfn_cache *cache, u64 gen) -{ - kvm_release_pfn(cache->pfn, cache->dirty, cache); - - cache->pfn = gfn_to_pfn_memslot(slot, gfn); - cache->gfn = gfn; - cache->dirty = false; - cache->generation = gen; -} - -static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool atomic) +int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) { kvm_pfn_t pfn; void *hva = NULL; struct page *page = KVM_UNMAPPED_PAGE; - struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn); - u64 gen = slots->generation; if (!map) return -EINVAL; - if (cache) { - if (!cache->pfn || cache->gfn != gfn || - cache->generation != gen) { - if (atomic) - return -EAGAIN; - kvm_cache_gfn_to_pfn(slot, gfn, cache, gen); - } - pfn = cache->pfn; - } else { - if (atomic) - return -EAGAIN; - pfn = gfn_to_pfn_memslot(slot, gfn); - } + pfn = gfn_to_pfn(vcpu->kvm, gfn); if (is_error_noslot_pfn(pfn)) return -EINVAL; if (pfn_valid(pfn)) { page = pfn_to_page(pfn); - if (atomic) - hva = kmap_atomic(page); - else - hva = kmap(page); + hva = kmap(page); #ifdef CONFIG_HAS_IOMEM - } else if (!atomic) { - hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); } else { - return -EINVAL; + hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #endif } @@ -2627,27 +2591,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, return 0; } - -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic) -{ - return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map, - cache, atomic); -} -EXPORT_SYMBOL_GPL(kvm_map_gfn); - -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) -{ - return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map, - NULL, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_map); -static void __kvm_unmap_gfn(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool dirty, bool atomic) +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) { if (!map) return; @@ -2655,45 +2601,21 @@ static void __kvm_unmap_gfn(struct kvm *kvm, if (!map->hva) return; - if (map->page != KVM_UNMAPPED_PAGE) { - if (atomic) - kunmap_atomic(map->hva); - else - kunmap(map->page); - } + if (map->page != KVM_UNMAPPED_PAGE) + kunmap(map->page); #ifdef CONFIG_HAS_IOMEM - else if (!atomic) - memunmap(map->hva); else - WARN_ONCE(1, "Unexpected unmapping in atomic context"); + memunmap(map->hva); #endif if (dirty) - mark_page_dirty_in_slot(kvm, memslot, map->gfn); + kvm_vcpu_mark_page_dirty(vcpu, map->gfn); - if (cache) - cache->dirty |= dirty; - else - kvm_release_pfn(map->pfn, dirty, NULL); + kvm_release_pfn(map->pfn, dirty); map->hva = NULL; map->page = NULL; } - -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic) -{ - __kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map, - cache, dirty, atomic); - return 0; -} -EXPORT_SYMBOL_GPL(kvm_unmap_gfn); - -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) -{ - __kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), - map, NULL, dirty, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) -- cgit v1.2.3 From f915b75bffb7257bd8d26376b8e1cc67771927f8 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 17 Nov 2021 15:56:52 +0800 Subject: page_pool: Revert "page_pool: disable dma mapping support..." This reverts commit d00e60ee54b12de945b8493cf18c1ada9e422514. As reported by Guillaume in [1]: Enabling LPAE always enables CONFIG_ARCH_DMA_ADDR_T_64BIT in 32-bit systems, which breaks the bootup proceess when a ethernet driver is using page pool with PP_FLAG_DMA_MAP flag. As we were hoping we had no active consumers for such system when we removed the dma mapping support, and LPAE seems like a common feature for 32 bits system, so revert it. 1. https://www.spinics.net/lists/netdev/msg779890.html Fixes: d00e60ee54b1 ("page_pool: disable dma mapping support for 32-bit arch with 64-bit DMA") Signed-off-by: Yunsheng Lin Reported-by: "kernelci.org bot" Tested-by: "kernelci.org bot" Acked-by: Jesper Dangaard Brouer Acked-by: Ilias Apalodimas Signed-off-by: David S. Miller --- include/linux/mm_types.h | 13 ++++++++++++- include/net/page_pool.h | 12 +++++++++++- net/core/page_pool.c | 10 ++++------ 3 files changed, 27 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb8c6f5f19bc..c3a6e6209600 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -105,7 +105,18 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3855f069627f..a4082406a003 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,14 +216,24 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 9b60e4301a44..1a6978427d6c 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -49,12 +49,6 @@ static int page_pool_init(struct page_pool *pool, * which is the XDP_TX use-case. */ if (pool->p.flags & PP_FLAG_DMA_MAP) { - /* DMA-mapping is not supported on 32-bit systems with - * 64-bit DMA mapping. - */ - if (sizeof(dma_addr_t) > sizeof(unsigned long)) - return -EOPNOTSUPP; - if ((pool->p.dma_dir != DMA_FROM_DEVICE) && (pool->p.dma_dir != DMA_BIDIRECTIONAL)) return -EINVAL; @@ -75,6 +69,10 @@ static int page_pool_init(struct page_pool *pool, */ } + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT && + pool->p.flags & PP_FLAG_PAGE_FRAG) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; -- cgit v1.2.3 From df6160deb3debe6f964c16349f9431157ff67dda Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 17 Nov 2021 17:57:29 -0800 Subject: tcp: add missing htmldocs for skb->ll_node and sk->defer_list Add missing entries to fix these "make htmldocs" warnings. ./include/linux/skbuff.h:953: warning: Function parameter or member 'll_node' not described in 'sk_buff' ./include/net/sock.h:540: warning: Function parameter or member 'defer_list' not described in 'sock' Fixes: f35f821935d8 ("tcp: defer skb freeing after socket lock is released") Signed-off-by: Eric Dumazet Reported-by: Stephen Rothwell Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/net/sock.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b8b806512e16..100fd604fbc9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -627,6 +627,7 @@ typedef unsigned char *sk_buff_data_t; * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head + * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in * fragmentation management diff --git a/include/net/sock.h b/include/net/sock.h index f09c0c4736c4..a79fc772324e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -292,6 +292,7 @@ struct bpf_local_storage; * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held + * @defer_list: head of llist storing skbs to be freed * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, -- cgit v1.2.3 From 6966df483d7b5b218aeb0e13e7e334a8fc3c1744 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 18 Nov 2021 13:49:51 +0200 Subject: regulator: Update protection IRQ helper docs The documentation of IRQ notification helper had still references to first RFC implementation which called BUG() while trying to protect the hardware. Behaviour was improved as calling the BUG() was not a proper solution. Current implementation attempts to call poweroff if handling of potentially damaging error notification fails. Update the documentation to reflect the actual behaviour. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/0c9cc4bcf20c3da66fd5a85c97ee4288e5727538.1637233864.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index bd7a73db2e66..54cf566616ae 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -499,7 +499,8 @@ struct regulator_irq_data { * best to shut-down regulator(s) or reboot the SOC if error * handling is repeatedly failing. If fatal_cnt is given the IRQ * handling is aborted if it fails for fatal_cnt times and die() - * callback (if populated) or BUG() is called to try to prevent + * callback (if populated) is called. If die() is not populated + * poweroff for the system is attempted in order to prevent any * further damage. * @reread_ms: The time which is waited before attempting to re-read status * at the worker if IC reading fails. Immediate re-read is done @@ -516,11 +517,12 @@ struct regulator_irq_data { * @data: Driver private data pointer which will be passed as such to * the renable, map_event and die callbacks in regulator_irq_data. * @die: Protection callback. If IC status reading or recovery actions - * fail fatal_cnt times this callback or BUG() is called. This - * callback should implement a final protection attempt like - * disabling the regulator. If protection succeeded this may - * return 0. If anything else is returned the core assumes final - * protection failed and calls BUG() as a last resort. + * fail fatal_cnt times this callback is called or system is + * powered off. This callback should implement a final protection + * attempt like disabling the regulator. If protection succeeded + * die() may return 0. If anything else is returned the core + * assumes final protection failed and attempts to perform a + * poweroff as a last resort. * @map_event: Driver callback to map IRQ status into regulator devices with * events / errors. NOTE: callback MUST initialize both the * errors and notifs for all rdevs which it signals having -- cgit v1.2.3 From 8b6e88555971eac384b89fb0bd6c72ee4e1e6a6a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 18 Nov 2021 13:48:47 +0200 Subject: regulator: rohm-regulator: add helper for restricted voltage setting Few ROHM PMICs have regulators where voltage setting can be done only when regulator is disabled. Add helper for those PMICs. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/6f51871e9fea611d133b5dd2560f4a7ee1ede9cd.1637233864.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- drivers/regulator/rohm-regulator.c | 16 ++++++++++++++++ include/linux/mfd/rohm-generic.h | 7 +++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/drivers/regulator/rohm-regulator.c b/drivers/regulator/rohm-regulator.c index 6e0d9c08ec1c..f97a9a51ee76 100644 --- a/drivers/regulator/rohm-regulator.c +++ b/drivers/regulator/rohm-regulator.c @@ -112,6 +112,22 @@ int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, } EXPORT_SYMBOL(rohm_regulator_set_dvs_levels); +/* + * Few ROHM PMIC ICs have constrains on voltage changing: + * BD71837 - only buck 1-4 voltages can be changed when they are enabled. + * Other bucks and all LDOs must be disabled when voltage is changed. + * BD96801 - LDO voltage levels can be changed when LDOs are disabled. + */ +int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, + unsigned int sel) +{ + if (rdev->desc->ops->is_enabled(rdev)) + return -EBUSY; + + return regulator_set_voltage_sel_regmap(rdev, sel); +} +EXPORT_SYMBOL_GPL(rohm_regulator_set_voltage_sel_restricted); + MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Matti Vaittinen "); MODULE_DESCRIPTION("Generic helpers for ROHM PMIC regulator drivers"); diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 35b392a0d73a..35c5866f48b7 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -80,6 +80,8 @@ int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, const struct regulator_desc *desc, struct regmap *regmap); +int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, + unsigned int sel); #else static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, struct device_node *np, @@ -88,6 +90,11 @@ static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dv { return 0; } +static int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, + unsigned int sel) +{ + return 0; +} #endif #endif -- cgit v1.2.3 From 92b1348277f8893671e5354adde64fe3cf462821 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Thu, 18 Nov 2021 13:49:30 +0200 Subject: regulator: Add units to limit documentation The documentation for limits used at protection level setting did not mention the units. Fix the units in documentation to match values passed in from device-tree (uV, uA, Kelvin) to avoid confusion. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/111114aca991e41e49a32f89b74e95285f07c1e3.1637233864.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index bd7a73db2e66..1cb8071fee34 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -101,11 +101,13 @@ enum regulator_detection_severity { * is requested. * @set_over_voltage_protection: Support enabling of and setting limits for over * voltage situation detection. Detection can be configured for same - * severities as over current protection. + * severities as over current protection. Units of uV. * @set_under_voltage_protection: Support enabling of and setting limits for - * under situation detection. + * under voltage situation detection. Detection can be configured for same + * severities as over current protection. Units of uV. * @set_thermal_protection: Support enabling of and setting limits for over - * temperature situation detection. + * temperature situation detection.Detection can be configured for same + * severities as over current protection. Units of degree Kelvin. * * @set_active_discharge: Set active discharge enable/disable of regulators. * -- cgit v1.2.3 From 418e0a3551bbef5b221705b0e5b8412cdc0afd39 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 5 Nov 2021 14:42:24 +0200 Subject: lib/string_helpers: Introduce kasprintf_strarray() We have a few users already that basically want to have array of sequential strings to be allocated and filled. Provide a helper for them (basically adjusted version from gpio-mockup.c). Signed-off-by: Andy Shevchenko Reviewed-by: Linus Walleij --- include/linux/string_helpers.h | 1 + lib/string_helpers.c | 33 +++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index 4ba39e1403b2..f67a94013c87 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -100,6 +100,7 @@ char *kstrdup_quotable(const char *src, gfp_t gfp); char *kstrdup_quotable_cmdline(struct task_struct *task, gfp_t gfp); char *kstrdup_quotable_file(struct file *file, gfp_t gfp); +char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n); void kfree_strarray(char **array, size_t n); #endif diff --git a/lib/string_helpers.c b/lib/string_helpers.c index d5d008f5b1d9..9758997c465e 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -674,6 +674,39 @@ char *kstrdup_quotable_file(struct file *file, gfp_t gfp) } EXPORT_SYMBOL_GPL(kstrdup_quotable_file); +/** + * kasprintf_strarray - allocate and fill array of sequential strings + * @gfp: flags for the slab allocator + * @prefix: prefix to be used + * @n: amount of lines to be allocated and filled + * + * Allocates and fills @n strings using pattern "%s-%zu", where prefix + * is provided by caller. The caller is responsible to free them with + * kfree_strarray() after use. + * + * Returns array of strings or NULL when memory can't be allocated. + */ +char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n) +{ + char **names; + size_t i; + + names = kcalloc(n + 1, sizeof(char *), gfp); + if (!names) + return NULL; + + for (i = 0; i < n; i++) { + names[i] = kasprintf(gfp, "%s-%zu", prefix, i); + if (!names[i]) { + kfree_strarray(names, i); + return NULL; + } + } + + return names; +} +EXPORT_SYMBOL_GPL(kasprintf_strarray); + /** * kfree_strarray - free a number of dynamically allocated strings contained * in an array and the array itself -- cgit v1.2.3 From acdb89b6c87a2d7b5c48a82756e6f5c6f599f60a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 5 Nov 2021 14:42:25 +0200 Subject: lib/string_helpers: Introduce managed variant of kasprintf_strarray() Some of the users want to have easy way to allocate array of strings that will be automatically cleaned when associated device is gone. Introduce managed variant of kasprintf_strarray() for such use cases. Signed-off-by: Andy Shevchenko --- include/linux/string_helpers.h | 3 +++ lib/string_helpers.c | 31 +++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string_helpers.h b/include/linux/string_helpers.h index f67a94013c87..7a22921c9db7 100644 --- a/include/linux/string_helpers.h +++ b/include/linux/string_helpers.h @@ -7,6 +7,7 @@ #include #include +struct device; struct file; struct task_struct; @@ -103,4 +104,6 @@ char *kstrdup_quotable_file(struct file *file, gfp_t gfp); char **kasprintf_strarray(gfp_t gfp, const char *prefix, size_t n); void kfree_strarray(char **array, size_t n); +char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n); + #endif diff --git a/lib/string_helpers.c b/lib/string_helpers.c index 9758997c465e..90f9f1b7afec 100644 --- a/lib/string_helpers.c +++ b/lib/string_helpers.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -730,6 +731,36 @@ void kfree_strarray(char **array, size_t n) } EXPORT_SYMBOL_GPL(kfree_strarray); +struct strarray { + char **array; + size_t n; +}; + +static void devm_kfree_strarray(struct device *dev, void *res) +{ + struct strarray *array = res; + + kfree_strarray(array->array, array->n); +} + +char **devm_kasprintf_strarray(struct device *dev, const char *prefix, size_t n) +{ + struct strarray *ptr; + + ptr = devres_alloc(devm_kfree_strarray, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + ptr->array = kasprintf_strarray(GFP_KERNEL, prefix, n); + if (!ptr->array) { + devres_free(ptr); + return ERR_PTR(-ENOMEM); + } + + return ptr->array; +} +EXPORT_SYMBOL_GPL(devm_kasprintf_strarray); + /** * strscpy_pad() - Copy a C-string into a sized buffer * @dest: Where to copy the string to -- cgit v1.2.3 From 57bdeef4716689d9b0e3571034d65cf420f6efcd Mon Sep 17 00:00:00 2001 From: Naveen Naidu Date: Thu, 18 Nov 2021 19:33:11 +0530 Subject: PCI: Add PCI_ERROR_RESPONSE and related definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A config or MMIO read from a PCI device that doesn't exist or doesn't respond causes a PCI error. There's no real data to return to satisfy the CPU read, so most hardware fabricates ~0 data. Add a PCI_ERROR_RESPONSE definition for that and use it where appropriate to make these checks consistent and easier to find. Also add helper definitions PCI_SET_ERROR_RESPONSE() and PCI_POSSIBLE_ERROR() to make the code more readable. Suggested-by: Bjorn Helgaas Link: https://lore.kernel.org/r/55563bf4dfc5d3fdc96695373c659d099bf175b1.1637243717.git.naveennaidu479@gmail.com Signed-off-by: Naveen Naidu Signed-off-by: Bjorn Helgaas Reviewed-by: Pali Rohár --- include/linux/pci.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 18a75c8e615c..0ce26850470e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -154,6 +154,15 @@ enum pci_interrupt_pin { /* The number of legacy PCI INTx interrupts */ #define PCI_NUM_INTX 4 +/* + * Reading from a device that doesn't respond typically returns ~0. A + * successful read from a device may also return ~0, so you need additional + * information to reliably identify errors. + */ +#define PCI_ERROR_RESPONSE (~0ULL) +#define PCI_SET_ERROR_RESPONSE(val) (*(val) = ((typeof(*(val))) PCI_ERROR_RESPONSE)) +#define PCI_POSSIBLE_ERROR(val) ((val) == ((typeof(val)) PCI_ERROR_RESPONSE)) + /* * pci_power_t values must match the bits in the Capabilities PME_Support * and Control/Status PowerState fields in the Power Management capability. -- cgit v1.2.3 From c035713998700e8843c7d087f55bce3c54c0e3ec Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 5 Nov 2021 10:19:05 -0400 Subject: mm: Add functions to zero portions of a folio These functions are wrappers around zero_user_segments(), which means that zero_user_segments() can now be called for compound pages even when CONFIG_TRANSPARENT_HUGEPAGE is disabled. Use 'xend' as the name of the parameter to indicate that this is an excluded end, not the more usual included end. Excluding the end makes more sense to the callers, but can cause confusion to readers who are more used to seeing included ends. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- include/linux/highmem.h | 44 +++++++++++++++++++++++++++++++++++++++++--- mm/highmem.c | 2 -- 2 files changed, 41 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index c944b3b70ee7..39bb9b47fa9c 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -230,10 +230,10 @@ static inline void tag_clear_highpage(struct page *page) * If we pass in a base or tail page, we can zero up to PAGE_SIZE. * If we pass in a head page, we can zero up to the size of the compound page. */ -#if defined(CONFIG_HIGHMEM) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +#ifdef CONFIG_HIGHMEM void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2); -#else /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ +#else static inline void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) @@ -253,7 +253,7 @@ static inline void zero_user_segments(struct page *page, for (i = 0; i < compound_nr(page); i++) flush_dcache_page(page + i); } -#endif /* !HIGHMEM || !TRANSPARENT_HUGEPAGE */ +#endif static inline void zero_user_segment(struct page *page, unsigned start, unsigned end) @@ -363,4 +363,42 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len) kunmap_local(addr); } +/** + * folio_zero_segments() - Zero two byte ranges in a folio. + * @folio: The folio to write to. + * @start1: The first byte to zero. + * @xend1: One more than the last byte in the first range. + * @start2: The first byte to zero in the second range. + * @xend2: One more than the last byte in the second range. + */ +static inline void folio_zero_segments(struct folio *folio, + size_t start1, size_t xend1, size_t start2, size_t xend2) +{ + zero_user_segments(&folio->page, start1, xend1, start2, xend2); +} + +/** + * folio_zero_segment() - Zero a byte range in a folio. + * @folio: The folio to write to. + * @start: The first byte to zero. + * @xend: One more than the last byte to zero. + */ +static inline void folio_zero_segment(struct folio *folio, + size_t start, size_t xend) +{ + zero_user_segments(&folio->page, start, xend, 0, 0); +} + +/** + * folio_zero_range() - Zero a byte range in a folio. + * @folio: The folio to write to. + * @start: The first byte to zero. + * @length: The number of bytes to zero. + */ +static inline void folio_zero_range(struct folio *folio, + size_t start, size_t length) +{ + zero_user_segments(&folio->page, start, start + length, 0, 0); +} + #endif /* _LINUX_HIGHMEM_H */ diff --git a/mm/highmem.c b/mm/highmem.c index 88f65f155845..819d41140e5b 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -359,7 +359,6 @@ void kunmap_high(struct page *page) } EXPORT_SYMBOL(kunmap_high); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE void zero_user_segments(struct page *page, unsigned start1, unsigned end1, unsigned start2, unsigned end2) { @@ -416,7 +415,6 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1, BUG_ON((start1 | start2 | end1 | end2) != 0); } EXPORT_SYMBOL(zero_user_segments); -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* CONFIG_HIGHMEM */ #ifdef CONFIG_KMAP_LOCAL -- cgit v1.2.3 From c4f5b30dda01f2f6979a9681142de454991182ee Mon Sep 17 00:00:00 2001 From: Biju Das Date: Fri, 12 Nov 2021 18:44:10 +0000 Subject: reset: Add of_reset_control_get_optional_exclusive() Add optional variant of of_reset_control_get_exclusive(). If the requested reset is not specified in the device tree, this function returns NULL instead of an error. Suggested-by: Philipp Zabel Signed-off-by: Biju Das Reviewed-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20211112184413.4391-2-biju.das.jz@bp.renesas.com Signed-off-by: Philipp Zabel --- include/linux/reset.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/reset.h b/include/linux/reset.h index db0e6115a2f6..8a21b5756c3e 100644 --- a/include/linux/reset.h +++ b/include/linux/reset.h @@ -454,6 +454,26 @@ static inline struct reset_control *of_reset_control_get_exclusive( return __of_reset_control_get(node, id, 0, false, false, true); } +/** + * of_reset_control_get_optional_exclusive - Lookup and obtain an optional exclusive + * reference to a reset controller. + * @node: device to be reset by the controller + * @id: reset line name + * + * Optional variant of of_reset_control_get_exclusive(). If the requested reset + * is not specified in the device tree, this function returns NULL instead of + * an error. + * + * Returns a struct reset_control or IS_ERR() condition containing errno. + * + * Use of id names is optional. + */ +static inline struct reset_control *of_reset_control_get_optional_exclusive( + struct device_node *node, const char *id) +{ + return __of_reset_control_get(node, id, 0, false, true, true); +} + /** * of_reset_control_get_shared - Lookup and obtain a shared reference * to a reset controller. -- cgit v1.2.3 From fcb116bc43c8c37c052530ead79872f8b2615711 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 18 Nov 2021 14:23:21 -0600 Subject: signal: Replace force_fatal_sig with force_exit_sig when in doubt Recently to prevent issues with SECCOMP_RET_KILL and similar signals being changed before they are delivered SA_IMMUTABLE was added. Unfortunately this broke debuggers[1][2] which reasonably expect to be able to trap synchronous SIGTRAP and SIGSEGV even when the target process is not configured to handle those signals. Add force_exit_sig and use it instead of force_fatal_sig where historically the code has directly called do_exit. This has the implementation benefits of going through the signal exit path (including generating core dumps) without the danger of allowing userspace to ignore or change these signals. This avoids userspace regressions as older kernels exited with do_exit which debuggers also can not intercept. In the future is should be possible to improve the quality of implementation of the kernel by changing some of these force_exit_sig calls to force_fatal_sig. That can be done where it matters on a case-by-case basis with careful analysis. Reported-by: Kyle Huey Reported-by: kernel test robot [1] https://lkml.kernel.org/r/CAP045AoMY4xf8aC_4QU_-j7obuEPYgTcnQQP3Yxk=2X90jtpjw@mail.gmail.com [2] https://lkml.kernel.org/r/20211117150258.GB5403@xsang-OptiPlex-9020 Fixes: 00b06da29cf9 ("signal: Add SA_IMMUTABLE to ensure forced siganls do not get changed") Fixes: a3616a3c0272 ("signal/m68k: Use force_sigsegv(SIGSEGV) in fpsp040_die") Fixes: 83a1f27ad773 ("signal/powerpc: On swapcontext failure force SIGSEGV") Fixes: 9bc508cf0791 ("signal/s390: Use force_sigsegv in default_trap_handler") Fixes: 086ec444f866 ("signal/sparc32: In setup_rt_frame and setup_fram use force_fatal_sig") Fixes: c317d306d550 ("signal/sparc32: Exit with a fatal signal when try_to_clear_window_buffer fails") Fixes: 695dd0d634df ("signal/x86: In emulate_vsyscall force a signal instead of calling do_exit") Fixes: 1fbd60df8a85 ("signal/vm86_32: Properly send SIGSEGV when the vm86 state cannot be saved.") Fixes: 941edc5bf174 ("exit/syscall_user_dispatch: Send ordinary signals on failure") Link: https://lkml.kernel.org/r/871r3dqfv8.fsf_-_@email.froward.int.ebiederm.org Reviewed-by: Kees Cook Tested-by: Kees Cook Tested-by: Kyle Huey Signed-off-by: "Eric W. Biederman" --- arch/m68k/kernel/traps.c | 2 +- arch/powerpc/kernel/signal_32.c | 2 +- arch/powerpc/kernel/signal_64.c | 4 ++-- arch/s390/kernel/traps.c | 2 +- arch/sparc/kernel/signal_32.c | 4 ++-- arch/sparc/kernel/windows.c | 2 +- arch/x86/entry/vsyscall/vsyscall_64.c | 2 +- arch/x86/kernel/vm86_32.c | 2 +- include/linux/sched/signal.h | 1 + kernel/entry/syscall_user_dispatch.c | 4 ++-- kernel/signal.c | 13 +++++++++++++ 11 files changed, 26 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 99058a6da956..34d6458340b0 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1145,7 +1145,7 @@ asmlinkage void set_esp0(unsigned long ssp) */ asmlinkage void fpsp040_die(void) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); } #ifdef CONFIG_M68KFPU_EMU diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 00a9c9cd6d42..3e053e2fd6b6 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -1063,7 +1063,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, * We kill the task with a SIGSEGV in this situation. */ if (do_setcontext(new_ctx, regs, 0)) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return -EFAULT; } diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c index ef518535d436..d1e1fc0acbea 100644 --- a/arch/powerpc/kernel/signal_64.c +++ b/arch/powerpc/kernel/signal_64.c @@ -704,7 +704,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, */ if (__get_user_sigset(&set, &new_ctx->uc_sigmask)) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return -EFAULT; } set_current_blocked(&set); @@ -713,7 +713,7 @@ SYSCALL_DEFINE3(swapcontext, struct ucontext __user *, old_ctx, return -EFAULT; if (__unsafe_restore_sigcontext(current, NULL, 0, &new_ctx->uc_mcontext)) { user_read_access_end(); - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return -EFAULT; } user_read_access_end(); diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c index 035705c9f23e..2b780786fc68 100644 --- a/arch/s390/kernel/traps.c +++ b/arch/s390/kernel/traps.c @@ -84,7 +84,7 @@ static void default_trap_handler(struct pt_regs *regs) { if (user_mode(regs)) { report_user_fault(regs, SIGSEGV, 0); - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); } else die(regs, "Unknown program exception"); } diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c index cd677bc564a7..ffab16369bea 100644 --- a/arch/sparc/kernel/signal_32.c +++ b/arch/sparc/kernel/signal_32.c @@ -244,7 +244,7 @@ static int setup_frame(struct ksignal *ksig, struct pt_regs *regs, get_sigframe(ksig, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) { - force_fatal_sig(SIGILL); + force_exit_sig(SIGILL); return -EINVAL; } @@ -336,7 +336,7 @@ static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs, sf = (struct rt_signal_frame __user *) get_sigframe(ksig, regs, sigframe_size); if (invalid_frame_pointer(sf, sigframe_size)) { - force_fatal_sig(SIGILL); + force_exit_sig(SIGILL); return -EINVAL; } diff --git a/arch/sparc/kernel/windows.c b/arch/sparc/kernel/windows.c index bbbd40cc6b28..8f20862ccc83 100644 --- a/arch/sparc/kernel/windows.c +++ b/arch/sparc/kernel/windows.c @@ -122,7 +122,7 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who) if ((sp & 7) || copy_to_user((char __user *) sp, &tp->reg_window[window], sizeof(struct reg_window32))) { - force_fatal_sig(SIGILL); + force_exit_sig(SIGILL); return; } } diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 0b6b277ee050..fd2ee9408e91 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -226,7 +226,7 @@ bool emulate_vsyscall(unsigned long error_code, if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); - force_fatal_sig(SIGSYS); + force_exit_sig(SIGSYS); return true; } regs->orig_ax = -1; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index cce1c89cb7df..c21bcd668284 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -160,7 +160,7 @@ Efault_end: user_access_end(); Efault: pr_alert("could not access userspace vm86 info\n"); - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); goto exit_vm86; } diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index 23505394ef70..33a50642cf41 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -352,6 +352,7 @@ extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern void force_fatal_sig(int); +extern void force_exit_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); diff --git a/kernel/entry/syscall_user_dispatch.c b/kernel/entry/syscall_user_dispatch.c index 4508201847d2..0b6379adff6b 100644 --- a/kernel/entry/syscall_user_dispatch.c +++ b/kernel/entry/syscall_user_dispatch.c @@ -48,7 +48,7 @@ bool syscall_user_dispatch(struct pt_regs *regs) * the selector is loaded by userspace. */ if (unlikely(__get_user(state, sd->selector))) { - force_fatal_sig(SIGSEGV); + force_exit_sig(SIGSEGV); return true; } @@ -56,7 +56,7 @@ bool syscall_user_dispatch(struct pt_regs *regs) return false; if (state != SYSCALL_DISPATCH_FILTER_BLOCK) { - force_fatal_sig(SIGSYS); + force_exit_sig(SIGSYS); return true; } } diff --git a/kernel/signal.c b/kernel/signal.c index 7815e1bbeddc..a629b11bf3e0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1671,6 +1671,19 @@ void force_fatal_sig(int sig) force_sig_info_to_task(&info, current, HANDLER_SIG_DFL); } +void force_exit_sig(int sig) +{ + struct kernel_siginfo info; + + clear_siginfo(&info); + info.si_signo = sig; + info.si_errno = 0; + info.si_code = SI_KERNEL; + info.si_pid = 0; + info.si_uid = 0; + force_sig_info_to_task(&info, current, HANDLER_EXIT); +} + /* * When things go south during signal handling, we * will force a SIGSEGV. And if the signal that caused -- cgit v1.2.3 From d8466f73010faf71effb21228ae1cbf577dab130 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Sat, 16 Oct 2021 14:22:27 +0100 Subject: mtd: rawnand: Export nand_read_page_hwecc_oob_first() Move the function nand_read_page_hwecc_oob_first() (previously nand_davinci_read_page_hwecc_oob_first()) to nand_base.c, and export it as a GPL symbol, so that it can be used by more modules. Cc: # v5.2 Fixes: a0ac778eb82c ("mtd: rawnand: ingenic: Add support for the JZ4740") Signed-off-by: Paul Cercueil Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211016132228.40254-4-paul@crapouillou.net --- drivers/mtd/nand/raw/davinci_nand.c | 69 +------------------------------------ drivers/mtd/nand/raw/nand_base.c | 67 +++++++++++++++++++++++++++++++++++ include/linux/mtd/rawnand.h | 2 ++ 3 files changed, 70 insertions(+), 68 deletions(-) (limited to 'include/linux') diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c index fe2511cdcae3..45fec8c192ab 100644 --- a/drivers/mtd/nand/raw/davinci_nand.c +++ b/drivers/mtd/nand/raw/davinci_nand.c @@ -371,73 +371,6 @@ correct: return corrected; } -/** - * nand_davinci_read_page_hwecc_oob_first - Hardware ECC page read with ECC - * data read from OOB area - * @chip: nand chip info structure - * @buf: buffer to store read data - * @oob_required: caller requires OOB data read to chip->oob_poi - * @page: page number to read - * - * Hardware ECC for large page chips, which requires the ECC data to be - * extracted from the OOB before the actual data is read. - */ -static int nand_davinci_read_page_hwecc_oob_first(struct nand_chip *chip, - uint8_t *buf, - int oob_required, int page) -{ - struct mtd_info *mtd = nand_to_mtd(chip); - int i, eccsize = chip->ecc.size, ret; - int eccbytes = chip->ecc.bytes; - int eccsteps = chip->ecc.steps; - uint8_t *p = buf; - uint8_t *ecc_code = chip->ecc.code_buf; - unsigned int max_bitflips = 0; - - /* Read the OOB area first */ - ret = nand_read_oob_op(chip, page, 0, chip->oob_poi, mtd->oobsize); - if (ret) - return ret; - - /* Move read cursor to start of page */ - ret = nand_change_read_column_op(chip, 0, NULL, 0, false); - if (ret) - return ret; - - ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0, - chip->ecc.total); - if (ret) - return ret; - - for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) { - int stat; - - chip->ecc.hwctl(chip, NAND_ECC_READ); - - ret = nand_read_data_op(chip, p, eccsize, false, false); - if (ret) - return ret; - - stat = chip->ecc.correct(chip, p, &ecc_code[i], NULL); - if (stat == -EBADMSG && - (chip->ecc.options & NAND_ECC_GENERIC_ERASED_CHECK)) { - /* check for empty pages with bitflips */ - stat = nand_check_erased_ecc_chunk(p, eccsize, - &ecc_code[i], - eccbytes, NULL, 0, - chip->ecc.strength); - } - - if (stat < 0) { - mtd->ecc_stats.failed++; - } else { - mtd->ecc_stats.corrected += stat; - max_bitflips = max_t(unsigned int, max_bitflips, stat); - } - } - return max_bitflips; -} - /*----------------------------------------------------------------------*/ /* An ECC layout for using 4-bit ECC with small-page flash, storing @@ -647,7 +580,7 @@ static int davinci_nand_attach_chip(struct nand_chip *chip) } else if (chunks == 4 || chunks == 8) { mtd_set_ooblayout(mtd, nand_get_large_page_ooblayout()); - chip->ecc.read_page = nand_davinci_read_page_hwecc_oob_first; + chip->ecc.read_page = nand_read_page_hwecc_oob_first; } else { return -EIO; } diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 3d6c6e880520..113a2e9f43b1 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -3160,6 +3160,73 @@ static int nand_read_page_hwecc(struct nand_chip *chip, uint8_t *buf, return max_bitflips; } +/** + * nand_read_page_hwecc_oob_first - Hardware ECC page read with ECC + * data read from OOB area + * @chip: nand chip info structure + * @buf: buffer to store read data + * @oob_required: caller requires OOB data read to chip->oob_poi + * @page: page number to read + * + * Hardware ECC for large page chips, which requires the ECC data to be + * extracted from the OOB before the actual data is read. + */ +int nand_read_page_hwecc_oob_first(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page) +{ + struct mtd_info *mtd = nand_to_mtd(chip); + int i, eccsize = chip->ecc.size, ret; + int eccbytes = chip->ecc.bytes; + int eccsteps = chip->ecc.steps; + uint8_t *p = buf; + uint8_t *ecc_code = chip->ecc.code_buf; + unsigned int max_bitflips = 0; + + /* Read the OOB area first */ + ret = nand_read_oob_op(chip, page, 0, chip->oob_poi, mtd->oobsize); + if (ret) + return ret; + + /* Move read cursor to start of page */ + ret = nand_change_read_column_op(chip, 0, NULL, 0, false); + if (ret) + return ret; + + ret = mtd_ooblayout_get_eccbytes(mtd, ecc_code, chip->oob_poi, 0, + chip->ecc.total); + if (ret) + return ret; + + for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) { + int stat; + + chip->ecc.hwctl(chip, NAND_ECC_READ); + + ret = nand_read_data_op(chip, p, eccsize, false, false); + if (ret) + return ret; + + stat = chip->ecc.correct(chip, p, &ecc_code[i], NULL); + if (stat == -EBADMSG && + (chip->ecc.options & NAND_ECC_GENERIC_ERASED_CHECK)) { + /* check for empty pages with bitflips */ + stat = nand_check_erased_ecc_chunk(p, eccsize, + &ecc_code[i], + eccbytes, NULL, 0, + chip->ecc.strength); + } + + if (stat < 0) { + mtd->ecc_stats.failed++; + } else { + mtd->ecc_stats.corrected += stat; + max_bitflips = max_t(unsigned int, max_bitflips, stat); + } + } + return max_bitflips; +} +EXPORT_SYMBOL_GPL(nand_read_page_hwecc_oob_first); + /** * nand_read_page_syndrome - [REPLACEABLE] hardware ECC syndrome based page read * @chip: nand chip info structure diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index b2f9dd3cbd69..5b88cd51fadb 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -1539,6 +1539,8 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len, bool force_8bit, bool check_only); int nand_write_data_op(struct nand_chip *chip, const void *buf, unsigned int len, bool force_8bit); +int nand_read_page_hwecc_oob_first(struct nand_chip *chip, uint8_t *buf, + int oob_required, int page); /* Scan and identify a NAND device */ int nand_scan_with_ids(struct nand_chip *chip, unsigned int max_chips, -- cgit v1.2.3 From adeef3e32146a8d2a73c399dc6f5d76a449131b1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Nov 2021 06:21:51 -0800 Subject: net: constify netdev->dev_addr Commit 406f42fa0d3c ("net-next: When a bond have a massive amount of VLANs...") introduced a rbtree for faster Ethernet address look up. We converted all users to make modifications via appropriate helpers, make netdev->dev_addr const. The update helpers need to upcast from the buffer to struct netdev_hw_addr. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 14 +++++--------- net/core/dev_addr_lists.c | 10 ++++++++++ 2 files changed, 15 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4f4a299e92de..2462195784a9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2117,7 +2117,7 @@ struct net_device { * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ - unsigned char *dev_addr; + const unsigned char *dev_addr; struct netdev_rx_queue *_rx; unsigned int num_rx_queues; @@ -4268,10 +4268,13 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ +void dev_addr_mod(struct net_device *dev, unsigned int offset, + const void *addr, size_t len); + static inline void __dev_addr_set(struct net_device *dev, const void *addr, size_t len) { - memcpy(dev->dev_addr, addr, len); + dev_addr_mod(dev, 0, addr, len); } static inline void dev_addr_set(struct net_device *dev, const u8 *addr) @@ -4279,13 +4282,6 @@ static inline void dev_addr_set(struct net_device *dev, const u8 *addr) __dev_addr_set(dev, addr, dev->addr_len); } -static inline void -dev_addr_mod(struct net_device *dev, unsigned int offset, - const void *addr, size_t len) -{ - memcpy(&dev->dev_addr[offset], addr, len); -} - int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index f0cb38344126..ae8b1ef00fec 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -549,6 +549,16 @@ int dev_addr_init(struct net_device *dev) } EXPORT_SYMBOL(dev_addr_init); +void dev_addr_mod(struct net_device *dev, unsigned int offset, + const void *addr, size_t len) +{ + struct netdev_hw_addr *ha; + + ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); + memcpy(&ha->addr[offset], addr, len); +} +EXPORT_SYMBOL(dev_addr_mod); + /** * dev_addr_add - Add a device address * @dev: device -- cgit v1.2.3 From d07b26f5bbea9ade34dfd6abea7b3ca056c03cd1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 19 Nov 2021 06:21:53 -0800 Subject: dev_addr: add a modification check netdev->dev_addr should only be modified via helpers, but someone may be casting off the const. Add a runtime check to catch abuses. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/netdevice.h | 5 +++++ net/core/dev.c | 1 + net/core/dev_addr_lists.c | 19 +++++++++++++++++++ 3 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2462195784a9..cb7f2661d187 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1942,6 +1942,8 @@ enum netdev_ml_priv_type { * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. * + * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2268,6 +2270,8 @@ struct net_device { /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; + + u8 dev_addr_shadow[MAX_ADDR_LEN]; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -4288,6 +4292,7 @@ int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); void dev_addr_flush(struct net_device *dev); int dev_addr_init(struct net_device *dev); +void dev_addr_check(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); diff --git a/net/core/dev.c b/net/core/dev.c index 92c9258cbf28..9219e319e901 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1377,6 +1377,7 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) int ret; ASSERT_RTNL(); + dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index a23a83ac18e5..969942734951 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -498,6 +498,21 @@ EXPORT_SYMBOL(__hw_addr_init); * Device addresses handling functions */ +/* Check that netdev->dev_addr is not written to directly as this would + * break the rbtree layout. All changes should go thru dev_addr_set() and co. + * Remove this check in mid-2024. + */ +void dev_addr_check(struct net_device *dev) +{ + if (!memcmp(dev->dev_addr, dev->dev_addr_shadow, MAX_ADDR_LEN)) + return; + + netdev_warn(dev, "Current addr: %*ph\n", MAX_ADDR_LEN, dev->dev_addr); + netdev_warn(dev, "Expected addr: %*ph\n", + MAX_ADDR_LEN, dev->dev_addr_shadow); + netdev_WARN(dev, "Incorrect netdev->dev_addr\n"); +} + /** * dev_addr_flush - Flush device address list * @dev: device @@ -509,6 +524,7 @@ EXPORT_SYMBOL(__hw_addr_init); void dev_addr_flush(struct net_device *dev) { /* rtnl_mutex must be held here */ + dev_addr_check(dev); __hw_addr_flush(&dev->dev_addrs); dev->dev_addr = NULL; @@ -552,8 +568,11 @@ void dev_addr_mod(struct net_device *dev, unsigned int offset, { struct netdev_hw_addr *ha; + dev_addr_check(dev); + ha = container_of(dev->dev_addr, struct netdev_hw_addr, addr[0]); memcpy(&ha->addr[offset], addr, len); + memcpy(&dev->dev_addr_shadow[offset], addr, len); } EXPORT_SYMBOL(dev_addr_mod); -- cgit v1.2.3 From 85b6d24646e4125c591639841169baa98a2da503 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 19 Nov 2021 16:43:21 -0800 Subject: shm: extend forced shm destroy to support objects from several IPC nses Currently, the exit_shm() function not designed to work properly when task->sysvshm.shm_clist holds shm objects from different IPC namespaces. This is a real pain when sysctl kernel.shm_rmid_forced = 1, because it leads to use-after-free (reproducer exists). This is an attempt to fix the problem by extending exit_shm mechanism to handle shm's destroy from several IPC ns'es. To achieve that we do several things: 1. add a namespace (non-refcounted) pointer to the struct shmid_kernel 2. during new shm object creation (newseg()/shmget syscall) we initialize this pointer by current task IPC ns 3. exit_shm() fully reworked such that it traverses over all shp's in task->sysvshm.shm_clist and gets IPC namespace not from current task as it was before but from shp's object itself, then call shm_destroy(shp, ns). Note: We need to be really careful here, because as it was said before (1), our pointer to IPC ns non-refcnt'ed. To be on the safe side we using special helper get_ipc_ns_not_zero() which allows to get IPC ns refcounter only if IPC ns not in the "state of destruction". Q/A Q: Why can we access shp->ns memory using non-refcounted pointer? A: Because shp object lifetime is always shorther than IPC namespace lifetime, so, if we get shp object from the task->sysvshm.shm_clist while holding task_lock(task) nobody can steal our namespace. Q: Does this patch change semantics of unshare/setns/clone syscalls? A: No. It's just fixes non-covered case when process may leave IPC namespace without getting task->sysvshm.shm_clist list cleaned up. Link: https://lkml.kernel.org/r/67bb03e5-f79c-1815-e2bf-949c67047418@colorfullife.com Link: https://lkml.kernel.org/r/20211109151501.4921-1-manfred@colorfullife.com Fixes: ab602f79915 ("shm: make exit_shm work proportional to task activity") Co-developed-by: Manfred Spraul Signed-off-by: Manfred Spraul Signed-off-by: Alexander Mikhalitsyn Cc: "Eric W. Biederman" Cc: Davidlohr Bueso Cc: Greg KH Cc: Andrei Vagin Cc: Pavel Tikhomirov Cc: Vasily Averin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 15 ++++ include/linux/sched/task.h | 2 +- ipc/shm.c | 189 ++++++++++++++++++++++++++++++++---------- 3 files changed, 159 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 05e22770af51..b75395ec8d52 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -131,6 +131,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + if (ns) { + if (refcount_inc_not_zero(&ns->ns.count)) + return ns; + } + + return NULL; +} + extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, @@ -147,6 +157,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + return ns; +} + static inline void put_ipc_ns(struct ipc_namespace *ns) { } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ba88a6987400..058d7f371e25 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -158,7 +158,7 @@ static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. And ->vfork_done. + * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), diff --git a/ipc/shm.c b/ipc/shm.c index 4942bdd65748..b3048ebd5c31 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -62,9 +62,18 @@ struct shmid_kernel /* private to the kernel */ struct pid *shm_lprid; struct ucounts *mlock_ucounts; - /* The task created the shm object. NULL if the task is dead. */ + /* + * The task created the shm object, for + * task_lock(shp->shm_creator) + */ struct task_struct *shm_creator; - struct list_head shm_clist; /* list by creator */ + + /* + * List by creator. task_lock(->shm_creator) required for read/write. + * If list_empty(), then the creator is dead already. + */ + struct list_head shm_clist; + struct ipc_namespace *ns; } __randomize_layout; /* shm_mode upper byte flags */ @@ -115,6 +124,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp) struct shmid_kernel *shp; shp = container_of(ipcp, struct shmid_kernel, shm_perm); + WARN_ON(ns != shp->ns); if (shp->shm_nattch) { shp->shm_perm.mode |= SHM_DEST; @@ -225,10 +235,43 @@ static void shm_rcu_free(struct rcu_head *head) kfree(shp); } -static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) +/* + * It has to be called with shp locked. + * It must be called before ipc_rmid() + */ +static inline void shm_clist_rm(struct shmid_kernel *shp) { - list_del(&s->shm_clist); - ipc_rmid(&shm_ids(ns), &s->shm_perm); + struct task_struct *creator; + + /* ensure that shm_creator does not disappear */ + rcu_read_lock(); + + /* + * A concurrent exit_shm may do a list_del_init() as well. + * Just do nothing if exit_shm already did the work + */ + if (!list_empty(&shp->shm_clist)) { + /* + * shp->shm_creator is guaranteed to be valid *only* + * if shp->shm_clist is not empty. + */ + creator = shp->shm_creator; + + task_lock(creator); + /* + * list_del_init() is a nop if the entry was already removed + * from the list. + */ + list_del_init(&shp->shm_clist); + task_unlock(creator); + } + rcu_read_unlock(); +} + +static inline void shm_rmid(struct shmid_kernel *s) +{ + shm_clist_rm(s); + ipc_rmid(&shm_ids(s->ns), &s->shm_perm); } @@ -283,7 +326,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_file = shp->shm_file; shp->shm_file = NULL; ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT; - shm_rmid(ns, shp); + shm_rmid(shp); shm_unlock(shp); if (!is_file_hugepages(shm_file)) shmem_lock(shm_file, 0, shp->mlock_ucounts); @@ -303,10 +346,10 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) * * 2) sysctl kernel.shm_rmid_forced is set to 1. */ -static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) +static bool shm_may_destroy(struct shmid_kernel *shp) { return (shp->shm_nattch == 0) && - (ns->shm_rmid_forced || + (shp->ns->shm_rmid_forced || (shp->shm_perm.mode & SHM_DEST)); } @@ -337,7 +380,7 @@ static void shm_close(struct vm_area_struct *vma) ipc_update_pid(&shp->shm_lprid, task_tgid(current)); shp->shm_dtim = ktime_get_real_seconds(); shp->shm_nattch--; - if (shm_may_destroy(ns, shp)) + if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); @@ -358,10 +401,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data) * * As shp->* are changed under rwsem, it's safe to skip shp locking. */ - if (shp->shm_creator != NULL) + if (!list_empty(&shp->shm_clist)) return 0; - if (shm_may_destroy(ns, shp)) { + if (shm_may_destroy(shp)) { shm_lock_by_ptr(shp); shm_destroy(ns, shp); } @@ -379,48 +422,97 @@ void shm_destroy_orphaned(struct ipc_namespace *ns) /* Locking assumes this will only be called with task == current */ void exit_shm(struct task_struct *task) { - struct ipc_namespace *ns = task->nsproxy->ipc_ns; - struct shmid_kernel *shp, *n; + for (;;) { + struct shmid_kernel *shp; + struct ipc_namespace *ns; - if (list_empty(&task->sysvshm.shm_clist)) - return; + task_lock(task); + + if (list_empty(&task->sysvshm.shm_clist)) { + task_unlock(task); + break; + } + + shp = list_first_entry(&task->sysvshm.shm_clist, struct shmid_kernel, + shm_clist); - /* - * If kernel.shm_rmid_forced is not set then only keep track of - * which shmids are orphaned, so that a later set of the sysctl - * can clean them up. - */ - if (!ns->shm_rmid_forced) { - down_read(&shm_ids(ns).rwsem); - list_for_each_entry(shp, &task->sysvshm.shm_clist, shm_clist) - shp->shm_creator = NULL; /* - * Only under read lock but we are only called on current - * so no entry on the list will be shared. + * 1) Get pointer to the ipc namespace. It is worth to say + * that this pointer is guaranteed to be valid because + * shp lifetime is always shorter than namespace lifetime + * in which shp lives. + * We taken task_lock it means that shp won't be freed. */ - list_del(&task->sysvshm.shm_clist); - up_read(&shm_ids(ns).rwsem); - return; - } + ns = shp->ns; - /* - * Destroy all already created segments, that were not yet mapped, - * and mark any mapped as orphan to cover the sysctl toggling. - * Destroy is skipped if shm_may_destroy() returns false. - */ - down_write(&shm_ids(ns).rwsem); - list_for_each_entry_safe(shp, n, &task->sysvshm.shm_clist, shm_clist) { - shp->shm_creator = NULL; + /* + * 2) If kernel.shm_rmid_forced is not set then only keep track of + * which shmids are orphaned, so that a later set of the sysctl + * can clean them up. + */ + if (!ns->shm_rmid_forced) + goto unlink_continue; - if (shm_may_destroy(ns, shp)) { - shm_lock_by_ptr(shp); - shm_destroy(ns, shp); + /* + * 3) get a reference to the namespace. + * The refcount could be already 0. If it is 0, then + * the shm objects will be free by free_ipc_work(). + */ + ns = get_ipc_ns_not_zero(ns); + if (!ns) { +unlink_continue: + list_del_init(&shp->shm_clist); + task_unlock(task); + continue; } - } - /* Remove the list head from any segments still attached. */ - list_del(&task->sysvshm.shm_clist); - up_write(&shm_ids(ns).rwsem); + /* + * 4) get a reference to shp. + * This cannot fail: shm_clist_rm() is called before + * ipc_rmid(), thus the refcount cannot be 0. + */ + WARN_ON(!ipc_rcu_getref(&shp->shm_perm)); + + /* + * 5) unlink the shm segment from the list of segments + * created by current. + * This must be done last. After unlinking, + * only the refcounts obtained above prevent IPC_RMID + * from destroying the segment or the namespace. + */ + list_del_init(&shp->shm_clist); + + task_unlock(task); + + /* + * 6) we have all references + * Thus lock & if needed destroy shp. + */ + down_write(&shm_ids(ns).rwsem); + shm_lock_by_ptr(shp); + /* + * rcu_read_lock was implicitly taken in shm_lock_by_ptr, it's + * safe to call ipc_rcu_putref here + */ + ipc_rcu_putref(&shp->shm_perm, shm_rcu_free); + + if (ipc_valid_object(&shp->shm_perm)) { + if (shm_may_destroy(shp)) + shm_destroy(ns, shp); + else + shm_unlock(shp); + } else { + /* + * Someone else deleted the shp from namespace + * idr/kht while we have waited. + * Just unlock and continue. + */ + shm_unlock(shp); + } + + up_write(&shm_ids(ns).rwsem); + put_ipc_ns(ns); /* paired with get_ipc_ns_not_zero */ + } } static vm_fault_t shm_fault(struct vm_fault *vmf) @@ -676,7 +768,11 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (error < 0) goto no_id; + shp->ns = ns; + + task_lock(current); list_add(&shp->shm_clist, ¤t->sysvshm.shm_clist); + task_unlock(current); /* * shmid gets reported as "inode#" in /proc/pid/maps. @@ -1567,7 +1663,8 @@ out_nattch: down_write(&shm_ids(ns).rwsem); shp = shm_lock(ns, shmid); shp->shm_nattch--; - if (shm_may_destroy(ns, shp)) + + if (shm_may_destroy(shp)) shm_destroy(ns, shp); else shm_unlock(shp); -- cgit v1.2.3 From afe041c2d0febd83698b8b0164e6b3b1dfae0b66 Mon Sep 17 00:00:00 2001 From: Bui Quang Minh Date: Fri, 19 Nov 2021 16:43:40 -0800 Subject: hugetlb: fix hugetlb cgroup refcounting during mremap When hugetlb_vm_op_open() is called during copy_vma(), we may take the reference to resv_map->css. Later, when clearing the reservation pointer of old_vma after transferring it to new_vma, we forget to drop the reference to resv_map->css. This leads to a reference leak of css. Fixes this by adding a check to drop reservation css reference in clear_vma_resv_huge_pages() Link: https://lkml.kernel.org/r/20211113154412.91134-1-minhquangbui99@gmail.com Fixes: 550a7d60bd5e35 ("mm, hugepages: add mremap() support for hugepage backed vma") Signed-off-by: Bui Quang Minh Reviewed-by: Mike Kravetz Reviewed-by: Mina Almasry Cc: Miaohe Lin Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb_cgroup.h | 12 ++++++++++++ mm/hugetlb.c | 4 +++- 2 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index c137396129db..ba025ae27882 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -128,6 +128,13 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( css_get(resv_map->css); } +static inline void resv_map_put_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ + if (resv_map->css) + css_put(resv_map->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -211,6 +218,11 @@ static inline void resv_map_dup_hugetlb_cgroup_uncharge_info( { } +static inline void resv_map_put_hugetlb_cgroup_uncharge_info( + struct resv_map *resv_map) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e09159c957e3..3a2479003ddf 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1037,8 +1037,10 @@ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) */ struct resv_map *reservations = vma_resv_map(vma); - if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { + resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); + } reset_vma_resv_huge_pages(vma); } -- cgit v1.2.3 From f65b8132092699e4f672111836f3f51c00c354f2 Mon Sep 17 00:00:00 2001 From: Elyes HAOUAS Date: Thu, 28 Oct 2021 23:05:17 +0200 Subject: include/linux/efi.h: Remove unneeded whitespaces before tabs Signed-off-by: Elyes HAOUAS Signed-off-by: Ard Biesheuvel --- include/linux/efi.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index dbd39b20e034..de36fb547602 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -570,8 +570,8 @@ extern struct efi { unsigned long flags; } efi; -#define EFI_RT_SUPPORTED_GET_TIME 0x0001 -#define EFI_RT_SUPPORTED_SET_TIME 0x0002 +#define EFI_RT_SUPPORTED_GET_TIME 0x0001 +#define EFI_RT_SUPPORTED_SET_TIME 0x0002 #define EFI_RT_SUPPORTED_GET_WAKEUP_TIME 0x0004 #define EFI_RT_SUPPORTED_SET_WAKEUP_TIME 0x0008 #define EFI_RT_SUPPORTED_GET_VARIABLE 0x0010 @@ -838,7 +838,7 @@ extern int efi_status_to_err(efi_status_t status); #define EFI_VARIABLE_TIME_BASED_AUTHENTICATED_WRITE_ACCESS 0x0000000000000020 #define EFI_VARIABLE_APPEND_WRITE 0x0000000000000040 -#define EFI_VARIABLE_MASK (EFI_VARIABLE_NON_VOLATILE | \ +#define EFI_VARIABLE_MASK (EFI_VARIABLE_NON_VOLATILE | \ EFI_VARIABLE_BOOTSERVICE_ACCESS | \ EFI_VARIABLE_RUNTIME_ACCESS | \ EFI_VARIABLE_HARDWARE_ERROR_RECORD | \ -- cgit v1.2.3 From 3218910fd5858842a1dd98ce92b602f0878f8210 Mon Sep 17 00:00:00 2001 From: Adrian Larumbe Date: Mon, 1 Nov 2021 18:08:24 +0000 Subject: dmaengine: Add core function and capability check for DMA_MEMCPY_SG This is the old DMA_SG interface that was removed in commit c678fa66341c ("dmaengine: remove DMA_SG as it is dead code in kernel"). It has been renamed to DMA_MEMCPY_SG to better match the MEMSET and MEMSET_SG naming convention. It should only be used for mem2mem copies, either main system memory or CPU-addressable device memory (like video memory on a PCI graphics card). Bringing back this interface was prompted by the need to use the Xilinx CDMA device for mem2mem SG transfers. Signed-off-by: Adrian Larumbe Link: https://lore.kernel.org/r/20211101180825.241048-3-adrianml@alumnos.upm.es Signed-off-by: Vinod Koul --- drivers/dma/dmaengine.c | 7 +++++++ include/linux/dmaengine.h | 20 ++++++++++++++++++++ 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index d9f7c097cfd6..2cfa8458b51b 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1159,6 +1159,13 @@ int dma_async_device_register(struct dma_device *device) return -EIO; } + if (dma_has_cap(DMA_MEMCPY_SG, device->cap_mask) && !device->device_prep_dma_memcpy_sg) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_MEMCPY_SG"); + return -EIO; + } + if (dma_has_cap(DMA_XOR, device->cap_mask) && !device->device_prep_dma_xor) { dev_err(device->dev, "Device claims capability %s, but op is not defined\n", diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9000f3ffce8b..554a86665de9 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -50,6 +50,7 @@ enum dma_status { */ enum dma_transaction_type { DMA_MEMCPY, + DMA_MEMCPY_SG, DMA_XOR, DMA_PQ, DMA_XOR_VAL, @@ -891,6 +892,11 @@ struct dma_device { struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)( struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memcpy_sg)( + struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags); struct dma_async_tx_descriptor *(*device_prep_dma_xor)( struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, unsigned int src_cnt, size_t len, unsigned long flags); @@ -1051,6 +1057,20 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( len, flags); } +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy_sg( + struct dma_chan *chan, + struct scatterlist *dst_sg, unsigned int dst_nents, + struct scatterlist *src_sg, unsigned int src_nents, + unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy_sg) + return NULL; + + return chan->device->device_prep_dma_memcpy_sg(chan, dst_sg, dst_nents, + src_sg, src_nents, + flags); +} + static inline bool dmaengine_is_metadata_mode_supported(struct dma_chan *chan, enum dma_desc_metadata_mode mode) { -- cgit v1.2.3 From 0b70c256eba8448b072d25c95ee65e59da8970de Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Thu, 18 Nov 2021 20:12:42 +0800 Subject: ethtool: add support to set/get rx buf len via ethtool Add support to set rx buf len via ethtool -G parameter and get rx buf len via ethtool -g parameter. Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- Documentation/networking/ethtool-netlink.rst | 10 ++++++---- include/linux/ethtool.h | 18 ++++++++++++++++++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/netlink.h | 2 +- net/ethtool/rings.c | 23 +++++++++++++++++++++-- 5 files changed, 47 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 7b598c7e3912..9d98e0511249 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -849,7 +849,7 @@ Request contents: Kernel response contents: - ==================================== ====== ========================== + ==================================== ====== =========================== ``ETHTOOL_A_RINGS_HEADER`` nested reply header ``ETHTOOL_A_RINGS_RX_MAX`` u32 max size of RX ring ``ETHTOOL_A_RINGS_RX_MINI_MAX`` u32 max size of RX mini ring @@ -859,7 +859,8 @@ Kernel response contents: ``ETHTOOL_A_RINGS_RX_MINI`` u32 size of RX mini ring ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring - ==================================== ====== ========================== + ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ==================================== ====== =========================== RINGS_SET @@ -869,13 +870,14 @@ Sets ring sizes like ``ETHTOOL_SRINGPARAM`` ioctl request. Request contents: - ==================================== ====== ========================== + ==================================== ====== =========================== ``ETHTOOL_A_RINGS_HEADER`` nested reply header ``ETHTOOL_A_RINGS_RX`` u32 size of RX ring ``ETHTOOL_A_RINGS_RX_MINI`` u32 size of RX mini ring ``ETHTOOL_A_RINGS_RX_JUMBO`` u32 size of RX jumbo ring ``ETHTOOL_A_RINGS_TX`` u32 size of TX ring - ==================================== ====== ========================== + ``ETHTOOL_A_RINGS_RX_BUF_LEN`` u32 size of buffers on the ring + ==================================== ====== =========================== Kernel checks that requested ring sizes do not exceed limits reported by driver. Driver may impose additional constraints and may not suspport all diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 845a0ffc16ee..0b252b82988b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -67,6 +67,22 @@ enum { ETH_RSS_HASH_FUNCS_COUNT }; +/** + * struct kernel_ethtool_ringparam - RX/TX ring configuration + * @rx_buf_len: Current length of buffers on the rx ring. + */ +struct kernel_ethtool_ringparam { + u32 rx_buf_len; +}; + +/** + * enum ethtool_supported_ring_param - indicator caps for setting ring params + * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + */ +enum ethtool_supported_ring_param { + ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), +}; + #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) #define __ETH_RSS_HASH(name) __ETH_RSS_HASH_BIT(ETH_RSS_HASH_##name##_BIT) @@ -432,6 +448,7 @@ struct ethtool_module_power_mode_params { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. + * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -613,6 +630,7 @@ struct ethtool_module_power_mode_params { struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; + u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 999777d32dcf..cca6e474a085 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -329,6 +329,7 @@ enum { ETHTOOL_A_RINGS_RX_MINI, /* u32 */ ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ + ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 836ee7157848..490598e5eedd 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -356,7 +356,7 @@ extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANT extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1]; extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1]; extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1]; -extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX + 1]; +extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_RX_BUF_LEN + 1]; extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1]; extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1]; extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1]; diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index 4e097812a967..bd8e9a7530eb 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -10,6 +10,7 @@ struct rings_req_info { struct rings_reply_data { struct ethnl_reply_data base; struct ethtool_ringparam ringparam; + struct kernel_ethtool_ringparam kernel_ringparam; }; #define RINGS_REPDATA(__reply_base) \ @@ -49,7 +50,8 @@ static int rings_reply_size(const struct ethnl_req_info *req_base, nla_total_size(sizeof(u32)) + /* _RINGS_RX */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_MINI */ nla_total_size(sizeof(u32)) + /* _RINGS_RX_JUMBO */ - nla_total_size(sizeof(u32)); /* _RINGS_TX */ + nla_total_size(sizeof(u32)) + /* _RINGS_TX */ + nla_total_size(sizeof(u32)); /* _RINGS_RX_BUF_LEN */ } static int rings_fill_reply(struct sk_buff *skb, @@ -57,6 +59,7 @@ static int rings_fill_reply(struct sk_buff *skb, const struct ethnl_reply_data *reply_base) { const struct rings_reply_data *data = RINGS_REPDATA(reply_base); + const struct kernel_ethtool_ringparam *kernel_ringparam = &data->kernel_ringparam; const struct ethtool_ringparam *ringparam = &data->ringparam; if ((ringparam->rx_max_pending && @@ -78,7 +81,10 @@ static int rings_fill_reply(struct sk_buff *skb, (nla_put_u32(skb, ETHTOOL_A_RINGS_TX_MAX, ringparam->tx_max_pending) || nla_put_u32(skb, ETHTOOL_A_RINGS_TX, - ringparam->tx_pending)))) + ringparam->tx_pending))) || + (kernel_ringparam->rx_buf_len && + (nla_put_u32(skb, ETHTOOL_A_RINGS_RX_BUF_LEN, + kernel_ringparam->rx_buf_len)))) return -EMSGSIZE; return 0; @@ -105,10 +111,12 @@ const struct nla_policy ethnl_rings_set_policy[] = { [ETHTOOL_A_RINGS_RX_MINI] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_RX_JUMBO] = { .type = NLA_U32 }, [ETHTOOL_A_RINGS_TX] = { .type = NLA_U32 }, + [ETHTOOL_A_RINGS_RX_BUF_LEN] = NLA_POLICY_MIN(NLA_U32, 1), }; int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) { + struct kernel_ethtool_ringparam kernel_ringparam = {}; struct ethtool_ringparam ringparam = {}; struct ethnl_req_info req_info = {}; struct nlattr **tb = info->attrs; @@ -142,6 +150,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) ethnl_update_u32(&ringparam.rx_jumbo_pending, tb[ETHTOOL_A_RINGS_RX_JUMBO], &mod); ethnl_update_u32(&ringparam.tx_pending, tb[ETHTOOL_A_RINGS_TX], &mod); + ethnl_update_u32(&kernel_ringparam.rx_buf_len, + tb[ETHTOOL_A_RINGS_RX_BUF_LEN], &mod); ret = 0; if (!mod) goto out_ops; @@ -164,6 +174,15 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) goto out_ops; } + if (kernel_ringparam.rx_buf_len != 0 && + !(ops->supported_ring_params & ETHTOOL_RING_USE_RX_BUF_LEN)) { + ret = -EOPNOTSUPP; + NL_SET_ERR_MSG_ATTR(info->extack, + tb[ETHTOOL_A_RINGS_RX_BUF_LEN], + "setting rx buf len not supported"); + goto out_ops; + } + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam); if (ret < 0) goto out_ops; -- cgit v1.2.3 From 7462494408cd3de8b0bc1e79670bf213288501d0 Mon Sep 17 00:00:00 2001 From: Hao Chen Date: Thu, 18 Nov 2021 20:12:43 +0800 Subject: ethtool: extend ringparam setting/getting API with rx_buf_len Add two new parameters kernel_ringparam and extack for .get_ringparam and .set_ringparam to extend more ring params through netlink. Signed-off-by: Hao Chen Signed-off-by: Guangbin Huang Signed-off-by: David S. Miller --- arch/um/drivers/vector_kern.c | 4 +++- drivers/net/can/c_can/c_can_ethtool.c | 4 +++- drivers/net/ethernet/3com/typhoon.c | 4 +++- drivers/net/ethernet/amazon/ena/ena_ethtool.c | 8 +++++-- drivers/net/ethernet/amd/pcnet32.c | 8 +++++-- drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 11 +++++++--- .../net/ethernet/aquantia/atlantic/aq_ethtool.c | 8 +++++-- drivers/net/ethernet/atheros/atlx/atl1.c | 8 +++++-- drivers/net/ethernet/broadcom/b44.c | 8 +++++-- drivers/net/ethernet/broadcom/bcm63xx_enet.c | 25 ++++++++++++++++------ drivers/net/ethernet/broadcom/bnx2.c | 8 +++++-- .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 8 +++++-- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 8 +++++-- drivers/net/ethernet/broadcom/tg3.c | 10 +++++++-- drivers/net/ethernet/brocade/bna/bnad_ethtool.c | 8 +++++-- drivers/net/ethernet/cadence/macb_main.c | 8 +++++-- drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 11 +++++++--- .../net/ethernet/cavium/thunder/nicvf_ethtool.c | 8 +++++-- drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 8 +++++-- drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c | 8 +++++-- drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 8 +++++-- .../net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 8 +++++-- drivers/net/ethernet/cisco/enic/enic_ethtool.c | 8 +++++-- drivers/net/ethernet/cortina/gemini.c | 8 +++++-- drivers/net/ethernet/emulex/benet/be_ethtool.c | 4 +++- drivers/net/ethernet/ethoc.c | 8 +++++-- drivers/net/ethernet/faraday/ftgmac100.c | 14 ++++++++---- .../net/ethernet/freescale/enetc/enetc_ethtool.c | 4 +++- drivers/net/ethernet/freescale/gianfar_ethtool.c | 8 +++++-- drivers/net/ethernet/freescale/ucc_geth_ethtool.c | 8 +++++-- drivers/net/ethernet/google/gve/gve_ethtool.c | 4 +++- drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 6 +++++- drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 8 +++++-- drivers/net/ethernet/huawei/hinic/hinic_ethtool.c | 8 +++++-- drivers/net/ethernet/ibm/emac/core.c | 7 ++++-- drivers/net/ethernet/ibm/ibmvnic.c | 8 +++++-- drivers/net/ethernet/intel/e100.c | 8 +++++-- drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/e1000e/ethtool.c | 8 +++++-- drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 12 +++++++++-- drivers/net/ethernet/intel/ice/ice_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/igb/igb_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/igbvf/ethtool.c | 8 +++++-- drivers/net/ethernet/intel/igc/igc_ethtool.c | 14 ++++++++---- drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 8 +++++-- drivers/net/ethernet/intel/ixgbevf/ethtool.c | 8 +++++-- drivers/net/ethernet/marvell/mv643xx_eth.c | 8 +++++-- drivers/net/ethernet/marvell/mvneta.c | 14 ++++++++---- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 14 ++++++++---- .../ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 8 +++++-- drivers/net/ethernet/marvell/skge.c | 8 +++++-- drivers/net/ethernet/marvell/sky2.c | 8 +++++-- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 8 +++++-- .../net/ethernet/mellanox/mlx5/core/en_ethtool.c | 8 +++++-- drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 14 ++++++++---- .../ethernet/mellanox/mlx5/core/ipoib/ethtool.c | 8 +++++-- .../mellanox/mlxbf_gige/mlxbf_gige_ethtool.c | 7 ++++-- drivers/net/ethernet/micrel/ksz884x.c | 6 +++++- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 4 +++- drivers/net/ethernet/neterion/s2io.c | 7 ++++-- .../net/ethernet/netronome/nfp/nfp_net_ethtool.c | 8 +++++-- drivers/net/ethernet/nvidia/forcedeth.c | 10 +++++++-- .../ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c | 12 +++++++++-- drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c | 4 +++- .../net/ethernet/pensando/ionic/ionic_ethtool.c | 8 +++++-- .../ethernet/qlogic/netxen/netxen_nic_ethtool.c | 8 +++++-- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 8 +++++-- .../net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c | 8 +++++-- drivers/net/ethernet/qualcomm/emac/emac-ethtool.c | 8 +++++-- drivers/net/ethernet/qualcomm/qca_debug.c | 8 +++++-- drivers/net/ethernet/realtek/8139cp.c | 4 +++- drivers/net/ethernet/realtek/r8169_main.c | 4 +++- drivers/net/ethernet/renesas/ravb_main.c | 8 +++++-- drivers/net/ethernet/renesas/sh_eth.c | 8 +++++-- drivers/net/ethernet/sfc/ef100_ethtool.c | 7 ++++-- drivers/net/ethernet/sfc/ethtool.c | 14 ++++++++---- drivers/net/ethernet/sfc/falcon/ethtool.c | 14 ++++++++---- .../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 8 +++++-- drivers/net/ethernet/tehuti/tehuti.c | 12 +++++++++-- drivers/net/ethernet/ti/am65-cpsw-ethtool.c | 7 ++++-- drivers/net/ethernet/ti/cpmac.c | 8 +++++-- drivers/net/ethernet/ti/cpsw_ethtool.c | 8 +++++-- drivers/net/ethernet/ti/cpsw_priv.h | 8 +++++-- drivers/net/ethernet/toshiba/spider_net_ethtool.c | 4 +++- drivers/net/ethernet/xilinx/ll_temac_main.c | 14 ++++++++---- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 14 ++++++++---- drivers/net/hyperv/netvsc_drv.c | 8 +++++-- drivers/net/netdevsim/ethtool.c | 8 +++++-- drivers/net/usb/r8152.c | 8 +++++-- drivers/net/virtio_net.c | 4 +++- drivers/net/vmxnet3/vmxnet3_ethtool.c | 10 +++++---- drivers/s390/net/qeth_ethtool.c | 4 +++- include/linux/ethtool.h | 8 +++++-- net/ethtool/ioctl.c | 10 ++++++--- net/ethtool/rings.c | 9 +++++--- net/mac80211/ethtool.c | 8 +++++-- 99 files changed, 617 insertions(+), 212 deletions(-) (limited to 'include/linux') diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index cde6db184c26..4fc1a5d70dcf 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1441,7 +1441,9 @@ flash_fail: } static void vector_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct vector_private *vp = netdev_priv(netdev); diff --git a/drivers/net/can/c_can/c_can_ethtool.c b/drivers/net/can/c_can/c_can_ethtool.c index 377c7d2e7612..6655146294fc 100644 --- a/drivers/net/can/c_can/c_can_ethtool.c +++ b/drivers/net/can/c_can/c_can_ethtool.c @@ -20,7 +20,9 @@ static void c_can_get_drvinfo(struct net_device *netdev, } static void c_can_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct c_can_priv *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c index 05e15b6e5e2c..481f1df3106c 100644 --- a/drivers/net/ethernet/3com/typhoon.c +++ b/drivers/net/ethernet/3com/typhoon.c @@ -1138,7 +1138,9 @@ typhoon_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) } static void -typhoon_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering) +typhoon_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { ering->rx_max_pending = RXENT_ENTRIES; ering->tx_max_pending = TXLO_ENTRIES - 1; diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index 13e745cf3781..6b9b43e422c1 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -465,7 +465,9 @@ static void ena_get_drvinfo(struct net_device *dev, } static void ena_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ena_adapter *adapter = netdev_priv(netdev); @@ -476,7 +478,9 @@ static void ena_get_ringparam(struct net_device *netdev, } static int ena_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ena_adapter *adapter = netdev_priv(netdev); u32 new_tx_size, new_rx_size; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index f5c50ff377ff..c20c369c7eb8 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -860,7 +860,9 @@ static int pcnet32_nway_reset(struct net_device *dev) } static void pcnet32_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct pcnet32_private *lp = netdev_priv(dev); @@ -871,7 +873,9 @@ static void pcnet32_get_ringparam(struct net_device *dev, } static int pcnet32_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct pcnet32_private *lp = netdev_priv(dev); unsigned long flags; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 94879cf8b420..6ceb1cdf6eba 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -619,8 +619,11 @@ static int xgbe_get_module_eeprom(struct net_device *netdev, return pdata->phy_if.module_eeprom(pdata, eeprom, data); } -static void xgbe_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ringparam) +static void +xgbe_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ringparam, + struct kernel_ethtool_ringparam *kernel_ringparam, + struct netlink_ext_ack *extack) { struct xgbe_prv_data *pdata = netdev_priv(netdev); @@ -631,7 +634,9 @@ static void xgbe_get_ringparam(struct net_device *netdev, } static int xgbe_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ringparam) + struct ethtool_ringparam *ringparam, + struct kernel_ethtool_ringparam *kernel_ringparam, + struct netlink_ext_ack *extack) { struct xgbe_prv_data *pdata = netdev_priv(netdev); unsigned int rx, tx; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a9ef0544e30f..a418238f6309 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -812,7 +812,9 @@ static int aq_ethtool_set_pauseparam(struct net_device *ndev, } static void aq_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *cfg; @@ -827,7 +829,9 @@ static void aq_get_ringparam(struct net_device *ndev, } static int aq_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct aq_nic_s *aq_nic = netdev_priv(ndev); const struct aq_hw_caps_s *hw_caps; diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b4c9e805e981..6a969969d221 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -3438,7 +3438,9 @@ static void atl1_get_regs(struct net_device *netdev, struct ethtool_regs *regs, } static void atl1_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct atl1_adapter *adapter = netdev_priv(netdev); struct atl1_tpd_ring *txdr = &adapter->tpd_ring; @@ -3451,7 +3453,9 @@ static void atl1_get_ringparam(struct net_device *netdev, } static int atl1_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct atl1_adapter *adapter = netdev_priv(netdev); struct atl1_tpd_ring *tpdr = &adapter->tpd_ring; diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 969591bbc066..e5857e88c207 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -1961,7 +1961,9 @@ static int b44_set_link_ksettings(struct net_device *dev, } static void b44_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct b44 *bp = netdev_priv(dev); @@ -1972,7 +1974,9 @@ static void b44_get_ringparam(struct net_device *dev, } static int b44_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct b44 *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index a568994a03a6..b04e423c446a 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1497,8 +1497,11 @@ static int bcm_enet_set_link_ksettings(struct net_device *dev, } } -static void bcm_enet_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) +static void +bcm_enet_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bcm_enet_priv *priv; @@ -1512,7 +1515,9 @@ static void bcm_enet_get_ringparam(struct net_device *dev, } static int bcm_enet_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bcm_enet_priv *priv; int was_running; @@ -2579,8 +2584,11 @@ static void bcm_enetsw_get_ethtool_stats(struct net_device *netdev, } } -static void bcm_enetsw_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) +static void +bcm_enetsw_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bcm_enet_priv *priv; @@ -2595,8 +2603,11 @@ static void bcm_enetsw_get_ringparam(struct net_device *dev, ering->tx_pending = priv->tx_ring_size; } -static int bcm_enetsw_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) +static int +bcm_enetsw_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bcm_enet_priv *priv; int was_running; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index babc955ba64e..e20aafeb4ca9 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -7318,7 +7318,9 @@ static int bnx2_set_coalesce(struct net_device *dev, } static void -bnx2_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering) +bnx2_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bnx2 *bp = netdev_priv(dev); @@ -7389,7 +7391,9 @@ bnx2_change_ring_size(struct bnx2 *bp, u32 rx, u32 tx, bool reset_irq) } static int -bnx2_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ering) +bnx2_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bnx2 *bp = netdev_priv(dev); int rc; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 472a3a478038..0e319ac7799f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -1914,7 +1914,9 @@ static int bnx2x_set_coalesce(struct net_device *dev, } static void bnx2x_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bnx2x *bp = netdev_priv(dev); @@ -1938,7 +1940,9 @@ static void bnx2x_get_ringparam(struct net_device *dev, } static int bnx2x_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bnx2x *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 8188d55722e4..15253396096a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -775,7 +775,9 @@ skip_tpa_stats: } static void bnxt_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bnxt *bp = netdev_priv(dev); @@ -794,7 +796,9 @@ static void bnxt_get_ringparam(struct net_device *dev, } static int bnxt_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct bnxt *bp = netdev_priv(dev); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 85ca3909859d..283f3c1f1195 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12390,7 +12390,10 @@ static int tg3_nway_reset(struct net_device *dev) return r; } -static void tg3_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ering) +static void tg3_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct tg3 *tp = netdev_priv(dev); @@ -12411,7 +12414,10 @@ static void tg3_get_ringparam(struct net_device *dev, struct ethtool_ringparam * ering->tx_pending = tp->napi[0].tx_pending; } -static int tg3_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ering) +static int tg3_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct tg3 *tp = netdev_priv(dev); int i, irq_sync = 0, err = 0; diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c index 391b85f25141..4b4ad731897f 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c +++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c @@ -405,7 +405,9 @@ static int bnad_set_coalesce(struct net_device *netdev, static void bnad_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ringparam) + struct ethtool_ringparam *ringparam, + struct kernel_ethtool_ringparam *kernel_ringparam, + struct netlink_ext_ack *extack) { struct bnad *bnad = netdev_priv(netdev); @@ -418,7 +420,9 @@ bnad_get_ringparam(struct net_device *netdev, static int bnad_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ringparam) + struct ethtool_ringparam *ringparam, + struct kernel_ethtool_ringparam *kernel_ringparam, + struct netlink_ext_ack *extack) { int i, current_err, err = 0; struct bnad *bnad = netdev_priv(netdev); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 57c5f48d19a4..7b68f5a1720c 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3135,7 +3135,9 @@ static int macb_set_link_ksettings(struct net_device *netdev, } static void macb_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct macb *bp = netdev_priv(netdev); @@ -3147,7 +3149,9 @@ static void macb_get_ringparam(struct net_device *netdev, } static int macb_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct macb *bp = netdev_priv(netdev); u32 new_rx_size, new_tx_size; diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 2b9747867d4c..2c10ae3f7fc1 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -947,7 +947,9 @@ static int lio_set_phys_id(struct net_device *netdev, static void lio_ethtool_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; @@ -1252,8 +1254,11 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) return 0; } -static int lio_ethtool_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) +static int +lio_ethtool_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { u32 rx_count, tx_count, rx_count_old, tx_count_old; struct lio *lio = GET_LIO(netdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c index 7f2882109b16..5a9fad61e9ea 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c @@ -467,7 +467,9 @@ static int nicvf_get_coalesce(struct net_device *netdev, } static void nicvf_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; @@ -479,7 +481,9 @@ static void nicvf_get_ringparam(struct net_device *netdev, } static int nicvf_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c index 609820e214a3..18acd7cf3d6d 100644 --- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c +++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c @@ -710,7 +710,9 @@ static int set_pauseparam(struct net_device *dev, return 0; } -static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e) +static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e, + struct kernel_ethtool_ringparam *kernel_e, + struct netlink_ext_ack *extack) { struct adapter *adapter = dev->ml_priv; int jumbo_fl = t1_is_T1B(adapter) ? 1 : 0; @@ -724,7 +726,9 @@ static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e) e->tx_pending = adapter->params.sge.cmdQ_size[0]; } -static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e) +static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e, + struct kernel_ethtool_ringparam *kernel_e, + struct netlink_ext_ack *extack) { struct adapter *adapter = dev->ml_priv; int jumbo_fl = t1_is_T1B(adapter) ? 1 : 0; diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index bfffcaeee624..e2637bd2f423 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -1948,7 +1948,9 @@ static int set_pauseparam(struct net_device *dev, return 0; } -static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e) +static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e, + struct kernel_ethtool_ringparam *kernel_e, + struct netlink_ext_ack *extack) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; @@ -1964,7 +1966,9 @@ static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e) e->tx_pending = q->txq_size[0]; } -static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e) +static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e, + struct kernel_ethtool_ringparam *kernel_e, + struct netlink_ext_ack *extack) { struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 129352bbe114..0e4ec4079741 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -890,7 +890,9 @@ static int set_pauseparam(struct net_device *dev, return 0; } -static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e) +static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e, + struct kernel_ethtool_ringparam *kernel_e, + struct netlink_ext_ack *extack) { const struct port_info *pi = netdev_priv(dev); const struct sge *s = &pi->adapter->sge; @@ -906,7 +908,9 @@ static void get_sge_param(struct net_device *dev, struct ethtool_ringparam *e) e->tx_pending = s->ethtxq[pi->first_qset].q.size; } -static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e) +static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e, + struct kernel_ethtool_ringparam *kernel_e, + struct netlink_ext_ack *extack) { int i; const struct port_info *pi = netdev_priv(dev); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 64479c464b4e..61808c2c26a6 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1591,7 +1591,9 @@ static void cxgb4vf_set_msglevel(struct net_device *dev, u32 msglevel) * first Queue Set. */ static void cxgb4vf_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *rp) + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { const struct port_info *pi = netdev_priv(dev); const struct sge *s = &pi->adapter->sge; @@ -1614,7 +1616,9 @@ static void cxgb4vf_get_ringparam(struct net_device *dev, * device -- after vetting them of course! */ static int cxgb4vf_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *rp) + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { const struct port_info *pi = netdev_priv(dev); struct adapter *adapter = pi->adapter; diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c index 6ded4d9fa32a..6c11f9d62526 100644 --- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -177,7 +177,9 @@ static void enic_get_strings(struct net_device *netdev, u32 stringset, } static void enic_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct enic *enic = netdev_priv(netdev); struct vnic_enet_config *c = &enic->config; @@ -189,7 +191,9 @@ static void enic_get_ringparam(struct net_device *netdev, } static int enic_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct enic *enic = netdev_priv(netdev); struct vnic_enet_config *c = &enic->config; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 941f175fb911..07add311f65d 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2105,7 +2105,9 @@ static void gmac_get_pauseparam(struct net_device *netdev, } static void gmac_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *rp) + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { struct gemini_ethernet_port *port = netdev_priv(netdev); @@ -2123,7 +2125,9 @@ static void gmac_get_ringparam(struct net_device *netdev, } static int gmac_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *rp) + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { struct gemini_ethernet_port *port = netdev_priv(netdev); int err = 0; diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index f9955308b93d..dfa784339781 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -683,7 +683,9 @@ static int be_get_link_ksettings(struct net_device *netdev, } static void be_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct be_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index b1c8ffea6ad2..d618a8b785b0 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -945,7 +945,9 @@ static void ethoc_get_regs(struct net_device *dev, struct ethtool_regs *regs, } static void ethoc_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ethoc *priv = netdev_priv(dev); @@ -961,7 +963,9 @@ static void ethoc_get_ringparam(struct net_device *dev, } static int ethoc_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ethoc *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 97c5d70de76e..691605c15265 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1178,8 +1178,11 @@ static void ftgmac100_get_drvinfo(struct net_device *netdev, strlcpy(info->bus_info, dev_name(&netdev->dev), sizeof(info->bus_info)); } -static void ftgmac100_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) +static void +ftgmac100_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct ftgmac100 *priv = netdev_priv(netdev); @@ -1190,8 +1193,11 @@ static void ftgmac100_get_ringparam(struct net_device *netdev, ering->tx_pending = priv->tx_q_entries; } -static int ftgmac100_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) +static int +ftgmac100_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct ftgmac100 *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 910b9f722504..fa5b4f885b17 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -562,7 +562,9 @@ static int enetc_set_rxfh(struct net_device *ndev, const u32 *indir, } static void enetc_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct enetc_ndev_priv *priv = netdev_priv(ndev); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 7b32ed29bf4c..ff756265d58f 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -372,7 +372,9 @@ static int gfar_scoalesce(struct net_device *dev, * rx, rx_mini, and rx_jumbo rings are the same size, as mini and * jumbo are ignored by the driver */ static void gfar_gringparam(struct net_device *dev, - struct ethtool_ringparam *rvals) + struct ethtool_ringparam *rvals, + struct kernel_ethtool_ringparam *kernel_rvals, + struct netlink_ext_ack *extack) { struct gfar_private *priv = netdev_priv(dev); struct gfar_priv_tx_q *tx_queue = NULL; @@ -399,7 +401,9 @@ static void gfar_gringparam(struct net_device *dev, * necessary so that we don't mess things up while we're in motion. */ static int gfar_sringparam(struct net_device *dev, - struct ethtool_ringparam *rvals) + struct ethtool_ringparam *rvals, + struct kernel_ethtool_ringparam *kernel_rvals, + struct netlink_ext_ack *extack) { struct gfar_private *priv = netdev_priv(dev); int err = 0, i; diff --git a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c index 14c08a868190..69b2b98b1525 100644 --- a/drivers/net/ethernet/freescale/ucc_geth_ethtool.c +++ b/drivers/net/ethernet/freescale/ucc_geth_ethtool.c @@ -207,7 +207,9 @@ uec_get_regs(struct net_device *netdev, static void uec_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ucc_geth_private *ugeth = netdev_priv(netdev); struct ucc_geth_info *ug_info = ugeth->ug_info; @@ -226,7 +228,9 @@ uec_get_ringparam(struct net_device *netdev, static int uec_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ucc_geth_private *ugeth = netdev_priv(netdev); struct ucc_geth_info *ug_info = ugeth->ug_info; diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index c8df47a97fa4..fd2d2c705391 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -419,7 +419,9 @@ static int gve_set_channels(struct net_device *netdev, } static void gve_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *cmd) + struct ethtool_ringparam *cmd, + struct kernel_ethtool_ringparam *kernel_cmd, + struct netlink_ext_ack *extack) { struct gve_priv *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index ab7390225942..d7a27c244d48 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -663,9 +663,13 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, * hns_get_ringparam - get ring parameter * @net_dev: net device * @param: ethtool parameter + * @kernel_param: ethtool external parameter + * @extack: netlink extended ACK report struct */ static void hns_get_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct hns_nic_priv *priv = netdev_priv(net_dev); struct hnae_ae_ops *ops; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 9a816dbec613..e35a2661b45d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -643,7 +643,9 @@ static u32 hns3_get_link(struct net_device *netdev) } static void hns3_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; @@ -1081,7 +1083,9 @@ static int hns3_check_ringparam(struct net_device *ndev, } static int hns3_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct hns3_nic_priv *priv = netdev_priv(ndev); struct hnae3_handle *h = priv->ae_handle; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index a35a80f9a234..93192f58ac88 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -547,7 +547,9 @@ static void hinic_get_drvinfo(struct net_device *netdev, } static void hinic_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct hinic_dev *nic_dev = netdev_priv(netdev); @@ -580,7 +582,9 @@ static int check_ringparam_valid(struct hinic_dev *nic_dev, } static int hinic_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct hinic_dev *nic_dev = netdev_priv(netdev); u16 new_sq_depth, new_rq_depth; diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 6b3fc8823c54..fbea9f7efe8c 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -2137,8 +2137,11 @@ emac_ethtool_set_link_ksettings(struct net_device *ndev, return 0; } -static void emac_ethtool_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *rp) +static void +emac_ethtool_get_ringparam(struct net_device *ndev, + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { rp->rx_max_pending = rp->rx_pending = NUM_RX_BUFF; rp->tx_max_pending = rp->tx_pending = NUM_TX_BUFF; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c327fc8860da..ad9a2819e202 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3088,7 +3088,9 @@ static u32 ibmvnic_get_link(struct net_device *netdev) } static void ibmvnic_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); @@ -3108,7 +3110,9 @@ static void ibmvnic_get_ringparam(struct net_device *netdev, } static int ibmvnic_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); int ret; diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 0bf3d47bb90d..4a8013f20152 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2557,7 +2557,9 @@ static int e100_set_eeprom(struct net_device *netdev, } static void e100_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct nic *nic = netdev_priv(netdev); struct param_range *rfds = &nic->params.rfds; @@ -2570,7 +2572,9 @@ static void e100_get_ringparam(struct net_device *netdev, } static int e100_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct nic *nic = netdev_priv(netdev); struct param_range *rfds = &nic->params.rfds; diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 0a57172dfcbc..32803b0cf1e8 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -539,7 +539,9 @@ static void e1000_get_drvinfo(struct net_device *netdev, } static void e1000_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -556,7 +558,9 @@ static void e1000_get_ringparam(struct net_device *netdev, } static int e1000_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 8515e00d1b40..b80ae9a82224 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -655,7 +655,9 @@ static void e1000_get_drvinfo(struct net_device *netdev, } static void e1000_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); @@ -666,7 +668,9 @@ static void e1000_get_ringparam(struct net_device *netdev, } static int e1000_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_ring *temp_tx = NULL, *temp_rx = NULL; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 0d37f011d0ce..d53369e30040 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -502,7 +502,9 @@ static void fm10k_set_msglevel(struct net_device *netdev, u32 data) } static void fm10k_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct fm10k_intfc *interface = netdev_priv(netdev); @@ -517,7 +519,9 @@ static void fm10k_get_ringparam(struct net_device *netdev, } static int fm10k_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_ring *temp_ring; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 513ba6974355..091f36adbbe1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1916,7 +1916,9 @@ static void i40e_get_drvinfo(struct net_device *netdev, } static void i40e_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; @@ -1944,7 +1946,9 @@ static bool i40e_active_tx_ring_index(struct i40e_vsi *vsi, u16 index) } static int i40e_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct i40e_ring *tx_rings = NULL, *rx_rings = NULL; struct i40e_netdev_priv *np = netdev_priv(netdev); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 144a77679359..d327f576136f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -580,12 +580,16 @@ static void iavf_get_drvinfo(struct net_device *netdev, * iavf_get_ringparam - Get ring parameters * @netdev: network interface device structure * @ring: ethtool ringparam structure + * @kernel_ring: ethtool extenal ringparam structure + * @extack: netlink extended ACK report struct * * Returns current ring parameters. TX and RX rings are reported separately, * but the number of rings is not reported. **/ static void iavf_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct iavf_adapter *adapter = netdev_priv(netdev); @@ -599,12 +603,16 @@ static void iavf_get_ringparam(struct net_device *netdev, * iavf_set_ringparam - Set ring parameters * @netdev: network interface device structure * @ring: ethtool ringparam structure + * @kernel_ring: ethtool external ringparam structure + * @extack: netlink extended ACK report struct * * Sets ring parameters. TX and RX rings are controlled separately, but the * number of rings is not specified, so all rings get the same settings. **/ static int iavf_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct iavf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 572519e402f4..5af2faaa21e1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2686,7 +2686,9 @@ ice_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, } static void -ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) +ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; @@ -2704,7 +2706,9 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) } static int -ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) +ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_tx_ring *xdp_rings = NULL; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index fb1029352c3e..51a2dcaf553d 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -864,7 +864,9 @@ static void igb_get_drvinfo(struct net_device *netdev, } static void igb_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -875,7 +877,9 @@ static void igb_get_ringparam(struct net_device *netdev, } static int igb_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct igb_adapter *adapter = netdev_priv(netdev); struct igb_ring *temp_ring; diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index 06e5bd646a0e..9d4322b74163 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -175,7 +175,9 @@ static void igbvf_get_drvinfo(struct net_device *netdev, } static void igbvf_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct igbvf_adapter *adapter = netdev_priv(netdev); struct igbvf_ring *tx_ring = adapter->tx_ring; @@ -188,7 +190,9 @@ static void igbvf_get_ringparam(struct net_device *netdev, } static int igbvf_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct igbvf_adapter *adapter = netdev_priv(netdev); struct igbvf_ring *temp_ring; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index e0a76ac1bbbc..8cc077b712ad 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -567,8 +567,11 @@ static int igc_ethtool_set_eeprom(struct net_device *netdev, return ret_val; } -static void igc_ethtool_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) +static void +igc_ethtool_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct igc_adapter *adapter = netdev_priv(netdev); @@ -578,8 +581,11 @@ static void igc_ethtool_get_ringparam(struct net_device *netdev, ring->tx_pending = adapter->tx_ring_count; } -static int igc_ethtool_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) +static int +igc_ethtool_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct igc_adapter *adapter = netdev_priv(netdev); struct igc_ring *temp_ring; diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index 582099a5ad41..46efcfab7234 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -464,7 +464,9 @@ ixgb_get_drvinfo(struct net_device *netdev, static void ixgb_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ixgb_adapter *adapter = netdev_priv(netdev); struct ixgb_desc_ring *txdr = &adapter->tx_ring; @@ -478,7 +480,9 @@ ixgb_get_ringparam(struct net_device *netdev, static int ixgb_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ixgb_adapter *adapter = netdev_priv(netdev); struct ixgb_desc_ring *txdr = &adapter->tx_ring; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 8362822316a9..f70967c32116 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1118,7 +1118,9 @@ static void ixgbe_get_drvinfo(struct net_device *netdev, } static void ixgbe_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *tx_ring = adapter->tx_ring[0]; @@ -1131,7 +1133,9 @@ static void ixgbe_get_ringparam(struct net_device *netdev, } static int ixgbe_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *temp_ring; diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 8380f905e708..3b41f83c8dff 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -225,7 +225,9 @@ static void ixgbevf_get_drvinfo(struct net_device *netdev, } static void ixgbevf_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); @@ -236,7 +238,9 @@ static void ixgbevf_get_ringparam(struct net_device *netdev, } static int ixgbevf_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); struct ixgbevf_ring *tx_ring = NULL, *rx_ring = NULL; diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index bb14fa2241a3..116919730237 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1638,7 +1638,9 @@ static int mv643xx_eth_set_coalesce(struct net_device *dev, } static void -mv643xx_eth_get_ringparam(struct net_device *dev, struct ethtool_ringparam *er) +mv643xx_eth_get_ringparam(struct net_device *dev, struct ethtool_ringparam *er, + struct kernel_ethtool_ringparam *kernel_er, + struct netlink_ext_ack *extack) { struct mv643xx_eth_private *mp = netdev_priv(dev); @@ -1650,7 +1652,9 @@ mv643xx_eth_get_ringparam(struct net_device *dev, struct ethtool_ringparam *er) } static int -mv643xx_eth_set_ringparam(struct net_device *dev, struct ethtool_ringparam *er) +mv643xx_eth_set_ringparam(struct net_device *dev, struct ethtool_ringparam *er, + struct kernel_ethtool_ringparam *kernel_er, + struct netlink_ext_ack *extack) { struct mv643xx_eth_private *mp = netdev_priv(dev); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 67a644177880..350d24d7ead0 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -4510,8 +4510,11 @@ static void mvneta_ethtool_get_drvinfo(struct net_device *dev, } -static void mvneta_ethtool_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) +static void +mvneta_ethtool_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct mvneta_port *pp = netdev_priv(netdev); @@ -4521,8 +4524,11 @@ static void mvneta_ethtool_get_ringparam(struct net_device *netdev, ring->tx_pending = pp->tx_ring_size; } -static int mvneta_ethtool_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) +static int +mvneta_ethtool_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct mvneta_port *pp = netdev_priv(dev); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index df6c793f4b1b..8b1ca0b13e88 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -5431,8 +5431,11 @@ static void mvpp2_ethtool_get_drvinfo(struct net_device *dev, sizeof(drvinfo->bus_info)); } -static void mvpp2_ethtool_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) +static void +mvpp2_ethtool_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct mvpp2_port *port = netdev_priv(dev); @@ -5442,8 +5445,11 @@ static void mvpp2_ethtool_get_ringparam(struct net_device *dev, ring->tx_pending = port->tx_ring_size; } -static int mvpp2_ethtool_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) +static int +mvpp2_ethtool_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct mvpp2_port *port = netdev_priv(dev); u16 prev_rx_ring_size = port->rx_ring_size; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c index 80d4ce61f442..d85db90632d6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c @@ -360,7 +360,9 @@ static int otx2_set_pauseparam(struct net_device *netdev, } static void otx2_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); struct otx2_qset *qs = &pfvf->qset; @@ -372,7 +374,9 @@ static void otx2_get_ringparam(struct net_device *netdev, } static int otx2_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); bool if_up = netif_running(netdev); diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 0c864e5bf0a6..cf03c67fbf40 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -492,7 +492,9 @@ static void skge_get_strings(struct net_device *dev, u32 stringset, u8 *data) } static void skge_get_ring_param(struct net_device *dev, - struct ethtool_ringparam *p) + struct ethtool_ringparam *p, + struct kernel_ethtool_ringparam *kernel_p, + struct netlink_ext_ack *extack) { struct skge_port *skge = netdev_priv(dev); @@ -504,7 +506,9 @@ static void skge_get_ring_param(struct net_device *dev, } static int skge_set_ring_param(struct net_device *dev, - struct ethtool_ringparam *p) + struct ethtool_ringparam *p, + struct kernel_ethtool_ringparam *kernel_p, + struct netlink_ext_ack *extack) { struct skge_port *skge = netdev_priv(dev); int err = 0; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index d53ce826befd..ea16b1dd6a98 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4149,7 +4149,9 @@ static unsigned long roundup_ring_size(unsigned long pending) } static void sky2_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct sky2_port *sky2 = netdev_priv(dev); @@ -4161,7 +4163,9 @@ static void sky2_get_ringparam(struct net_device *dev, } static int sky2_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct sky2_port *sky2 = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 066d79e4ecfc..e97d97e94231 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1141,7 +1141,9 @@ static void mlx4_en_get_pauseparam(struct net_device *dev, } static int mlx4_en_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; @@ -1208,7 +1210,9 @@ out: } static void mlx4_en_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 45bdfcb3dcc7..c8757c5a812b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -314,7 +314,9 @@ void mlx5e_ethtool_get_ringparam(struct mlx5e_priv *priv, } static void mlx5e_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(dev); @@ -380,7 +382,9 @@ unlock: } static int mlx5e_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 8c81aeba07db..87c762066adb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -219,16 +219,22 @@ static int mlx5e_rep_get_sset_count(struct net_device *dev, int sset) } } -static void mlx5e_rep_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) +static void +mlx5e_rep_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(dev); mlx5e_ethtool_get_ringparam(priv, param); } -static int mlx5e_rep_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) +static int +mlx5e_rep_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index f23e33ac9c6b..f4f7eaf16446 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -67,7 +67,9 @@ static void mlx5i_get_ethtool_stats(struct net_device *dev, } static int mlx5i_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = mlx5i_epriv(dev); @@ -75,7 +77,9 @@ static int mlx5i_set_ringparam(struct net_device *dev, } static void mlx5i_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = mlx5i_epriv(dev); diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c index 92b798f8e73a..ceeb7f4c3f6c 100644 --- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_ethtool.c @@ -33,8 +33,11 @@ static void mlxbf_gige_get_regs(struct net_device *netdev, memcpy_fromio(p, priv->base, MLXBF_GIGE_MMIO_REG_SZ); } -static void mlxbf_gige_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) +static void +mlxbf_gige_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct mlxbf_gige *priv = netdev_priv(netdev); diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 99c0c1491af2..d024983815da 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -6317,11 +6317,15 @@ static int netdev_set_pauseparam(struct net_device *dev, * netdev_get_ringparam - get tx/rx ring parameters * @dev: Network device. * @ring: Ethtool RING settings data structure. + * @kernel_ring: Ethtool external RING settings data structure. + * @extack: Netlink handle. * * This procedure returns the TX/RX ring settings. */ static void netdev_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct dev_priv *priv = netdev_priv(dev); struct dev_info *hw_priv = priv->adapter; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 5736fcdafd7a..83a5e29c836a 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1704,7 +1704,9 @@ myri10ge_set_pauseparam(struct net_device *netdev, static void myri10ge_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct myri10ge_priv *mgp = netdev_priv(netdev); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index d1c32c65db05..d6ae44f164a9 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -5461,8 +5461,11 @@ static int s2io_ethtool_set_led(struct net_device *dev, return 0; } -static void s2io_ethtool_gringparam(struct net_device *dev, - struct ethtool_ringparam *ering) +static void +s2io_ethtool_gringparam(struct net_device *dev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct s2io_nic *sp = netdev_priv(dev); int i, tx_desc_count = 0, rx_desc_count = 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 1de076f55740..93fa8e677e05 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -381,7 +381,9 @@ err_bad_set: } static void nfp_net_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct nfp_net *nn = netdev_priv(netdev); @@ -406,7 +408,9 @@ static int nfp_net_set_ring_size(struct nfp_net *nn, u32 rxd_cnt, u32 txd_cnt) } static int nfp_net_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct nfp_net *nn = netdev_priv(netdev); u32 rxd_cnt, txd_cnt; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 9b530d7509a4..660013f716d4 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -4651,7 +4651,10 @@ static int nv_nway_reset(struct net_device *dev) return ret; } -static void nv_get_ringparam(struct net_device *dev, struct ethtool_ringparam* ring) +static void nv_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct fe_priv *np = netdev_priv(dev); @@ -4662,7 +4665,10 @@ static void nv_get_ringparam(struct net_device *dev, struct ethtool_ringparam* r ring->tx_pending = np->tx_ring_size; } -static int nv_set_ringparam(struct net_device *dev, struct ethtool_ringparam* ring) +static int nv_set_ringparam(struct net_device *dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c index 660b07cb5b92..84cc79e928c8 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c @@ -270,9 +270,13 @@ static int pch_gbe_nway_reset(struct net_device *netdev) * pch_gbe_get_ringparam - Report ring sizes * @netdev: Network interface device structure * @ring: Ring param structure + * @kernel_ring: Ring external param structure + * @extack: netlink handle */ static void pch_gbe_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct pch_gbe_adapter *adapter = netdev_priv(netdev); struct pch_gbe_tx_ring *txdr = adapter->tx_ring; @@ -288,12 +292,16 @@ static void pch_gbe_get_ringparam(struct net_device *netdev, * pch_gbe_set_ringparam - Set ring sizes * @netdev: Network interface device structure * @ring: Ring param structure + * @kernel_ring: Ring external param structure + * @extack: netlink handle * Returns * 0: Successful. * Negative value: Failed. */ static int pch_gbe_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct pch_gbe_adapter *adapter = netdev_priv(netdev); struct pch_gbe_tx_ring *txdr, *tx_old; diff --git a/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c b/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c index e1a304886a3c..4c7e0c991105 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac_ethtool.c @@ -69,7 +69,9 @@ pasemi_mac_ethtool_set_msglevel(struct net_device *netdev, static void pasemi_mac_ethtool_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct pasemi_mac *mac = netdev_priv(netdev); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c index c54d735b9e2e..386a5cf1e224 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -512,7 +512,9 @@ static int ionic_set_coalesce(struct net_device *netdev, } static void ionic_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ionic_lif *lif = netdev_priv(netdev); @@ -523,7 +525,9 @@ static void ionic_get_ringparam(struct net_device *netdev, } static int ionic_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ionic_lif *lif = netdev_priv(netdev); struct ionic_queue_params qparam; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c index a075643f5826..3c4a84ea6321 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c @@ -392,7 +392,9 @@ netxen_nic_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, static void netxen_nic_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct netxen_adapter *adapter = netdev_priv(dev); @@ -430,7 +432,9 @@ netxen_validate_ringparam(u32 val, u32 min, u32 max, char *r_name) static int netxen_nic_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct netxen_adapter *adapter = netdev_priv(dev); u16 max_rcv_desc = MAX_RCV_DESCRIPTORS_10G; diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 8284c4c1528f..100c9c52c20b 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -888,7 +888,9 @@ int qede_set_coalesce(struct net_device *dev, struct ethtool_coalesce *coal, } static void qede_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct qede_dev *edev = netdev_priv(dev); @@ -899,7 +901,9 @@ static void qede_get_ringparam(struct net_device *dev, } static int qede_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct qede_dev *edev = netdev_priv(dev); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index fc364b4ab6eb..e10fe071a40f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -632,7 +632,9 @@ qlcnic_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, static void qlcnic_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct qlcnic_adapter *adapter = netdev_priv(dev); @@ -663,7 +665,9 @@ qlcnic_validate_ringparam(u32 val, u32 min, u32 max, char *r_name) static int qlcnic_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct qlcnic_adapter *adapter = netdev_priv(dev); u16 num_rxd, num_jumbo_rxd, num_txd; diff --git a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c index f72e13b83869..f502db9cdea9 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-ethtool.c @@ -133,7 +133,9 @@ static int emac_nway_reset(struct net_device *netdev) } static void emac_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct emac_adapter *adpt = netdev_priv(netdev); @@ -144,7 +146,9 @@ static void emac_get_ringparam(struct net_device *netdev, } static int emac_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct emac_adapter *adpt = netdev_priv(netdev); diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index d59fff2fbcc6..792ce9a323cd 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -246,7 +246,9 @@ qcaspi_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *p) } static void -qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring) +qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct qcaspi *qca = netdev_priv(dev); @@ -257,7 +259,9 @@ qcaspi_get_ringparam(struct net_device *dev, struct ethtool_ringparam *ring) } static int -qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring) +qcaspi_set_ringparam(struct net_device *dev, struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct qcaspi *qca = netdev_priv(dev); diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 4f39f843bb3a..ad7b9e9d7f95 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -1388,7 +1388,9 @@ static void cp_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *info } static void cp_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { ring->rx_max_pending = CP_RX_RING_SIZE; ring->tx_max_pending = CP_TX_RING_SIZE; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index e896e5eca804..14dd04b2fbed 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1873,7 +1873,9 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) } static void rtl8169_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *data) + struct ethtool_ringparam *data, + struct kernel_ethtool_ringparam *kernel_data, + struct netlink_ext_ack *extack) { data->rx_max_pending = NUM_RX_DESC; data->rx_pending = NUM_RX_DESC; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 151cce2fe36d..ce09bd45527e 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1604,7 +1604,9 @@ static void ravb_get_strings(struct net_device *ndev, u32 stringset, u8 *data) } static void ravb_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ravb_private *priv = netdev_priv(ndev); @@ -1615,7 +1617,9 @@ static void ravb_get_ringparam(struct net_device *ndev, } static int ravb_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ravb_private *priv = netdev_priv(ndev); const struct ravb_hw_info *info = priv->info; diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index a3fbb2221c9a..223626290ce0 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2296,7 +2296,9 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) } static void sh_eth_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct sh_eth_private *mdp = netdev_priv(ndev); @@ -2307,7 +2309,9 @@ static void sh_eth_get_ringparam(struct net_device *ndev, } static int sh_eth_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct sh_eth_private *mdp = netdev_priv(ndev); int ret; diff --git a/drivers/net/ethernet/sfc/ef100_ethtool.c b/drivers/net/ethernet/sfc/ef100_ethtool.c index 835c838b7dfa..5dba4125d953 100644 --- a/drivers/net/ethernet/sfc/ef100_ethtool.c +++ b/drivers/net/ethernet/sfc/ef100_ethtool.c @@ -20,8 +20,11 @@ /* This is the maximum number of descriptor rings supported by the QDMA */ #define EFX_EF100_MAX_DMAQ_SIZE 16384UL -static void ef100_ethtool_get_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *ring) +static void +ef100_ethtool_get_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct efx_nic *efx = netdev_priv(net_dev); diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index e002ce21788d..48506373721a 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -157,8 +157,11 @@ static int efx_ethtool_set_coalesce(struct net_device *net_dev, return 0; } -static void efx_ethtool_get_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *ring) +static void +efx_ethtool_get_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct efx_nic *efx = netdev_priv(net_dev); @@ -168,8 +171,11 @@ static void efx_ethtool_get_ringparam(struct net_device *net_dev, ring->tx_pending = efx->txq_entries; } -static int efx_ethtool_set_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *ring) +static int +efx_ethtool_set_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct efx_nic *efx = netdev_priv(net_dev); u32 txq_entries; diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c index 137e8a7aeaa1..907254b36663 100644 --- a/drivers/net/ethernet/sfc/falcon/ethtool.c +++ b/drivers/net/ethernet/sfc/falcon/ethtool.c @@ -637,8 +637,11 @@ static int ef4_ethtool_set_coalesce(struct net_device *net_dev, return 0; } -static void ef4_ethtool_get_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *ring) +static void +ef4_ethtool_get_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ef4_nic *efx = netdev_priv(net_dev); @@ -648,8 +651,11 @@ static void ef4_ethtool_get_ringparam(struct net_device *net_dev, ring->tx_pending = efx->txq_entries; } -static int ef4_ethtool_set_ringparam(struct net_device *net_dev, - struct ethtool_ringparam *ring) +static int +ef4_ethtool_set_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct ef4_nic *efx = netdev_priv(net_dev); u32 txq_entries; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d89455803bed..eead45369eb9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -463,7 +463,9 @@ static int stmmac_nway_reset(struct net_device *dev) } static void stmmac_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct stmmac_priv *priv = netdev_priv(netdev); @@ -474,7 +476,9 @@ static void stmmac_get_ringparam(struct net_device *netdev, } static int stmmac_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { if (ring->rx_mini_pending || ring->rx_jumbo_pending || ring->rx_pending < DMA_MIN_RX_SIZE || diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 0775a5542f2f..89bc1602661c 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -2245,9 +2245,13 @@ static inline int bdx_tx_fifo_size_to_packets(int tx_size) * bdx_get_ringparam - report ring sizes * @netdev * @ring + * @kernel_ring + * @extack */ static void -bdx_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) +bdx_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct bdx_priv *priv = netdev_priv(netdev); @@ -2262,9 +2266,13 @@ bdx_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) * bdx_set_ringparam - set ring sizes * @netdev * @ring + * @kernel_ring + * @extack */ static int -bdx_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) +bdx_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct bdx_priv *priv = netdev_priv(netdev); int rx_size = 0; diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c index b05de9b61ad6..d45b6bb86f0b 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c +++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c @@ -453,8 +453,11 @@ static int am65_cpsw_set_channels(struct net_device *ndev, return am65_cpsw_nuss_update_tx_chns(common, chs->tx_count); } -static void am65_cpsw_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) +static void +am65_cpsw_get_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct am65_cpsw_common *common = am65_ndev_to_common(ndev); diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 7449436fc87c..bef5e68dac31 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -817,7 +817,9 @@ static void cpmac_tx_timeout(struct net_device *dev, unsigned int txqueue) } static void cpmac_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct cpmac_priv *priv = netdev_priv(dev); @@ -833,7 +835,9 @@ static void cpmac_get_ringparam(struct net_device *dev, } static int cpmac_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct cpmac_priv *priv = netdev_priv(dev); diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c index 158c8d3793f4..aa42141be3c0 100644 --- a/drivers/net/ethernet/ti/cpsw_ethtool.c +++ b/drivers/net/ethernet/ti/cpsw_ethtool.c @@ -658,7 +658,9 @@ err: } void cpsw_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct cpsw_priv *priv = netdev_priv(ndev); struct cpsw_common *cpsw = priv->cpsw; @@ -671,7 +673,9 @@ void cpsw_get_ringparam(struct net_device *ndev, } int cpsw_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct cpsw_common *cpsw = ndev_to_cpsw(ndev); int descs_num, ret; diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h index 435668ee542d..f33c882eb70e 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.h +++ b/drivers/net/ethernet/ti/cpsw_priv.h @@ -491,9 +491,13 @@ int cpsw_get_eee(struct net_device *ndev, struct ethtool_eee *edata); int cpsw_set_eee(struct net_device *ndev, struct ethtool_eee *edata); int cpsw_nway_reset(struct net_device *ndev); void cpsw_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering); + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack); int cpsw_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering); + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack); int cpsw_set_channels_common(struct net_device *ndev, struct ethtool_channels *chs, cpdma_handler_fn rx_handler); diff --git a/drivers/net/ethernet/toshiba/spider_net_ethtool.c b/drivers/net/ethernet/toshiba/spider_net_ethtool.c index 54f655a68148..93110dba0bfa 100644 --- a/drivers/net/ethernet/toshiba/spider_net_ethtool.c +++ b/drivers/net/ethernet/toshiba/spider_net_ethtool.c @@ -110,7 +110,9 @@ spider_net_ethtool_nway_reset(struct net_device *netdev) static void spider_net_ethtool_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ering) + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct spider_net_card *card = netdev_priv(netdev); diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index e7065c9a8e38..b900ab5aef2a 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1276,8 +1276,11 @@ static const struct attribute_group temac_attr_group = { * ethtool support */ -static void ll_temac_ethtools_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) +static void +ll_temac_ethtools_get_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct temac_local *lp = netdev_priv(ndev); @@ -1291,8 +1294,11 @@ static void ll_temac_ethtools_get_ringparam(struct net_device *ndev, ering->tx_pending = lp->tx_bd_num; } -static int ll_temac_ethtools_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) +static int +ll_temac_ethtools_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct temac_local *lp = netdev_priv(ndev); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 3dabc1901416..e39356364f33 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1323,8 +1323,11 @@ static void axienet_ethtools_get_regs(struct net_device *ndev, data[39] = axienet_dma_in32(lp, XAXIDMA_RX_TDESC_OFFSET); } -static void axienet_ethtools_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) +static void +axienet_ethtools_get_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct axienet_local *lp = netdev_priv(ndev); @@ -1338,8 +1341,11 @@ static void axienet_ethtools_get_ringparam(struct net_device *ndev, ering->tx_pending = lp->tx_bd_num; } -static int axienet_ethtools_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ering) +static int +axienet_ethtools_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *ering, + struct kernel_ethtool_ringparam *kernel_ering, + struct netlink_ext_ack *extack) { struct axienet_local *lp = netdev_priv(ndev); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 7e66ae1d2a59..efa963b7af54 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1858,7 +1858,9 @@ static void __netvsc_get_ringparam(struct netvsc_device *nvdev, } static void netvsc_get_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct net_device_context *ndevctx = netdev_priv(ndev); struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); @@ -1870,7 +1872,9 @@ static void netvsc_get_ringparam(struct net_device *ndev, } static int netvsc_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct net_device_context *ndevctx = netdev_priv(ndev); struct netvsc_device *nvdev = rtnl_dereference(ndevctx->nvdev); diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c index 0ab6a40be611..2b84169bf3a2 100644 --- a/drivers/net/netdevsim/ethtool.c +++ b/drivers/net/netdevsim/ethtool.c @@ -65,7 +65,9 @@ static int nsim_set_coalesce(struct net_device *dev, } static void nsim_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); @@ -73,7 +75,9 @@ static void nsim_get_ringparam(struct net_device *dev, } static int nsim_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct netdevsim *ns = netdev_priv(dev); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index f9877a3e83ac..b88f07c77a6b 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -8983,7 +8983,9 @@ static int rtl8152_set_tunable(struct net_device *netdev, } static void rtl8152_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct r8152 *tp = netdev_priv(netdev); @@ -8992,7 +8994,9 @@ static void rtl8152_get_ringparam(struct net_device *netdev, } static int rtl8152_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct r8152 *tp = netdev_priv(netdev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 03e38e38ee4b..c74af526d79b 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2174,7 +2174,9 @@ static void virtnet_cpu_notif_remove(struct virtnet_info *vi) } static void virtnet_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) { struct virtnet_info *vi = netdev_priv(dev); diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index 16f3a2057b90..3172d46c0335 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -575,10 +575,11 @@ vmxnet3_get_link_ksettings(struct net_device *netdev, return 0; } - static void vmxnet3_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); @@ -595,10 +596,11 @@ vmxnet3_get_ringparam(struct net_device *netdev, param->rx_jumbo_pending = adapter->rx_ring2_size; } - static int vmxnet3_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); u32 new_tx_ring_size, new_rx_ring_size, new_rx_ring2_size; diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index 46d0fe0d0e8a..b0b36b2132fe 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -144,7 +144,9 @@ static int qeth_set_coalesce(struct net_device *dev, } static void qeth_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *param) + struct ethtool_ringparam *param, + struct kernel_ethtool_ringparam *kernel_param, + struct netlink_ext_ack *extack) { struct qeth_card *card = dev->ml_priv; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 0b252b82988b..a26f37a27167 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -656,9 +656,13 @@ struct ethtool_ops { struct kernel_ethtool_coalesce *, struct netlink_ext_ack *); void (*get_ringparam)(struct net_device *, - struct ethtool_ringparam *); + struct ethtool_ringparam *, + struct kernel_ethtool_ringparam *, + struct netlink_ext_ack *); int (*set_ringparam)(struct net_device *, - struct ethtool_ringparam *); + struct ethtool_ringparam *, + struct kernel_ethtool_ringparam *, + struct netlink_ext_ack *); void (*get_pause_stats)(struct net_device *dev, struct ethtool_pause_stats *pause_stats); void (*get_pauseparam)(struct net_device *, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 5c5f170a9851..af2d4e022076 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -1743,11 +1743,13 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) { struct ethtool_ringparam ringparam = { .cmd = ETHTOOL_GRINGPARAM }; + struct kernel_ethtool_ringparam kernel_ringparam = {}; if (!dev->ethtool_ops->get_ringparam) return -EOPNOTSUPP; - dev->ethtool_ops->get_ringparam(dev, &ringparam); + dev->ethtool_ops->get_ringparam(dev, &ringparam, + &kernel_ringparam, NULL); if (copy_to_user(useraddr, &ringparam, sizeof(ringparam))) return -EFAULT; @@ -1757,6 +1759,7 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) { struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM }; + struct kernel_ethtool_ringparam kernel_ringparam; int ret; if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam) @@ -1765,7 +1768,7 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) if (copy_from_user(&ringparam, useraddr, sizeof(ringparam))) return -EFAULT; - dev->ethtool_ops->get_ringparam(dev, &max); + dev->ethtool_ops->get_ringparam(dev, &max, &kernel_ringparam, NULL); /* ensure new ring parameters are within the maximums */ if (ringparam.rx_pending > max.rx_max_pending || @@ -1774,7 +1777,8 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) ringparam.tx_pending > max.tx_max_pending) return -EINVAL; - ret = dev->ethtool_ops->set_ringparam(dev, &ringparam); + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam, + &kernel_ringparam, NULL); if (!ret) ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF, NULL); return ret; diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c index bd8e9a7530eb..450b8866373d 100644 --- a/net/ethtool/rings.c +++ b/net/ethtool/rings.c @@ -26,6 +26,7 @@ static int rings_prepare_data(const struct ethnl_req_info *req_base, struct genl_info *info) { struct rings_reply_data *data = RINGS_REPDATA(reply_base); + struct netlink_ext_ack *extack = info ? info->extack : NULL; struct net_device *dev = reply_base->dev; int ret; @@ -34,7 +35,8 @@ static int rings_prepare_data(const struct ethnl_req_info *req_base, ret = ethnl_ops_begin(dev); if (ret < 0) return ret; - dev->ethtool_ops->get_ringparam(dev, &data->ringparam); + dev->ethtool_ops->get_ringparam(dev, &data->ringparam, + &data->kernel_ringparam, extack); ethnl_ops_complete(dev); return 0; @@ -142,7 +144,7 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) ret = ethnl_ops_begin(dev); if (ret < 0) goto out_rtnl; - ops->get_ringparam(dev, &ringparam); + ops->get_ringparam(dev, &ringparam, &kernel_ringparam, info->extack); ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod); ethnl_update_u32(&ringparam.rx_mini_pending, @@ -183,7 +185,8 @@ int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info) goto out_ops; } - ret = dev->ethtool_ops->set_ringparam(dev, &ringparam); + ret = dev->ethtool_ops->set_ringparam(dev, &ringparam, + &kernel_ringparam, info->extack); if (ret < 0) goto out_ops; ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF, NULL); diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c index 99a2e30b3833..b2253df54413 100644 --- a/net/mac80211/ethtool.c +++ b/net/mac80211/ethtool.c @@ -14,7 +14,9 @@ #include "driver-ops.h" static int ieee80211_set_ringparam(struct net_device *dev, - struct ethtool_ringparam *rp) + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); @@ -25,7 +27,9 @@ static int ieee80211_set_ringparam(struct net_device *dev, } static void ieee80211_get_ringparam(struct net_device *dev, - struct ethtool_ringparam *rp) + struct ethtool_ringparam *rp, + struct kernel_ethtool_ringparam *kernel_rp, + struct netlink_ext_ack *extack) { struct ieee80211_local *local = wiphy_priv(dev->ieee80211_ptr->wiphy); -- cgit v1.2.3 From 4b66d2161b8125b6caa6971815e85631cf3cf36f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Nov 2021 07:43:31 -0800 Subject: net: annotate accesses to dev->gso_max_size dev->gso_max_size is written under RTNL protection, or when the device is not yet visible, but is read locklessly. Add the READ_ONCE()/WRITE_ONCE() pairs, and use netif_set_gso_max_size() where we can to better document what is going on. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 2 +- drivers/net/ethernet/realtek/r8169_main.c | 4 ++-- drivers/net/ethernet/sfc/ef100_nic.c | 2 +- drivers/net/ipvlan/ipvlan_main.c | 4 ++-- drivers/net/macvlan.c | 4 ++-- drivers/net/veth.c | 2 +- drivers/net/vxlan.c | 2 +- include/linux/netdevice.h | 3 ++- net/8021q/vlan.c | 2 +- net/8021q/vlan_dev.c | 2 +- net/bridge/br_if.c | 2 +- net/core/sock.c | 3 ++- net/sctp/output.c | 2 +- 13 files changed, 18 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 369f6ae700c7..927ddbdf650b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -286,7 +286,7 @@ nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower) if (repr->dst->u.port_info.lower_dev != lower) return; - netdev->gso_max_size = lower->gso_max_size; + netif_set_gso_max_size(netdev, lower->gso_max_size); netdev->gso_max_segs = lower->gso_max_segs; netdev_update_features(netdev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 14dd04b2fbed..ff222c54299d 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5390,11 +5390,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ if (rtl_chip_supports_csum_v2(tp)) { dev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6; - dev->gso_max_size = RTL_GSO_MAX_SIZE_V2; + netif_set_gso_max_size(dev, RTL_GSO_MAX_SIZE_V2); dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2; } else { dev->hw_features |= NETIF_F_SG | NETIF_F_TSO; - dev->gso_max_size = RTL_GSO_MAX_SIZE_V1; + netif_set_gso_max_size(dev, RTL_GSO_MAX_SIZE_V1); dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1; } diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 6aa81229b68a..d9015a77a6b8 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -993,7 +993,7 @@ static int ef100_process_design_param(struct efx_nic *efx, return 0; case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN: nic_data->tso_max_payload_len = min_t(u64, reader->value, GSO_MAX_SIZE); - efx->net_dev->gso_max_size = nic_data->tso_max_payload_len; + netif_set_gso_max_size(efx->net_dev, nic_data->tso_max_payload_len); return 0; case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS: nic_data->tso_max_payload_num_segs = min_t(u64, reader->value, 0xffff); diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 1d2f4e7d7324..0ba63eccefa5 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -140,7 +140,7 @@ static int ipvlan_init(struct net_device *dev) dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; - dev->gso_max_size = phy_dev->gso_max_size; + netif_set_gso_max_size(dev, phy_dev->gso_max_size); dev->gso_max_segs = phy_dev->gso_max_segs; dev->hard_header_len = phy_dev->hard_header_len; @@ -763,7 +763,7 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - ipvlan->dev->gso_max_size = dev->gso_max_size; + netif_set_gso_max_size(ipvlan->dev, dev->gso_max_size); ipvlan->dev->gso_max_segs = dev->gso_max_segs; netdev_update_features(ipvlan->dev); } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index d2f830ec2969..506e9559df80 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -900,7 +900,7 @@ static int macvlan_init(struct net_device *dev) dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; - dev->gso_max_size = lowerdev->gso_max_size; + netif_set_gso_max_size(dev, lowerdev->gso_max_size); dev->gso_max_segs = lowerdev->gso_max_segs; dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); @@ -1748,7 +1748,7 @@ static int macvlan_device_event(struct notifier_block *unused, break; case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { - vlan->dev->gso_max_size = dev->gso_max_size; + netif_set_gso_max_size(vlan->dev, dev->gso_max_size); vlan->dev->gso_max_segs = dev->gso_max_segs; netdev_update_features(vlan->dev); } diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 50eb43e5bf45..f2f66fb293fd 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1689,7 +1689,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, if (ifmp && (dev->ifindex != 0)) peer->ifindex = ifmp->ifi_index; - peer->gso_max_size = dev->gso_max_size; + netif_set_gso_max_size(peer, dev->gso_max_size); peer->gso_max_segs = dev->gso_max_segs; err = register_netdevice(peer); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 563f86de0e0d..df4f1712be95 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3811,7 +3811,7 @@ static void vxlan_config_apply(struct net_device *dev, if (lowerdev) { dst->remote_ifindex = conf->remote_ifindex; - dev->gso_max_size = lowerdev->gso_max_size; + netif_set_gso_max_size(dev, lowerdev->gso_max_size); dev->gso_max_segs = lowerdev->gso_max_segs; needed_headroom = lowerdev->hard_header_len; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cb7f2661d187..14eeb58ed197 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4731,7 +4731,8 @@ static inline bool netif_needs_gso(struct sk_buff *skb, static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { - dev->gso_max_size = size; + /* dev->gso_max_size is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_max_size, size); } static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index a3a0a5e994f5..34c0ffa81e5f 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -322,7 +322,7 @@ static void vlan_transfer_features(struct net_device *dev, { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); - vlandev->gso_max_size = dev->gso_max_size; + netif_set_gso_max_size(vlandev, dev->gso_max_size); vlandev->gso_max_segs = dev->gso_max_segs; if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index ab6dee28536d..208f6845f6dd 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -573,7 +573,7 @@ static int vlan_dev_init(struct net_device *dev) NETIF_F_ALL_FCOE; dev->features |= dev->hw_features | NETIF_F_LLTX; - dev->gso_max_size = real_dev->gso_max_size; + netif_set_gso_max_size(dev, real_dev->gso_max_size); dev->gso_max_segs = real_dev->gso_max_segs; if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 64b2d4fb50f5..d3e1c2276551 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -525,7 +525,7 @@ static void br_set_gso_limits(struct net_bridge *br) gso_max_size = min(gso_max_size, p->dev->gso_max_size); gso_max_segs = min(gso_max_segs, p->dev->gso_max_segs); } - br->dev->gso_max_size = gso_max_size; + netif_set_gso_max_size(br->dev, gso_max_size); br->dev->gso_max_segs = gso_max_segs; } diff --git a/net/core/sock.c b/net/core/sock.c index 1f9be266e586..4418e2a07c34 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2257,7 +2257,8 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } else { sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; - sk->sk_gso_max_size = dst->dev->gso_max_size; + /* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ + sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size); max_segs = max_t(u32, dst->dev->gso_max_segs, 1); } } diff --git a/net/sctp/output.c b/net/sctp/output.c index cdfdbd353c67..72fe6669c50d 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -134,7 +134,7 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, dst_hold(tp->dst); sk_setup_caps(sk, tp->dst); } - packet->max_size = sk_can_gso(sk) ? tp->dst->dev->gso_max_size + packet->max_size = sk_can_gso(sk) ? READ_ONCE(tp->dst->dev->gso_max_size) : asoc->pathmtu; rcu_read_unlock(); } -- cgit v1.2.3 From 6d872df3e3b91532b142de9044e5b4984017a55f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 19 Nov 2021 07:43:32 -0800 Subject: net: annotate accesses to dev->gso_max_segs dev->gso_max_segs is written under RTNL protection, or when the device is not yet visible, but is read locklessly. Add netif_set_gso_max_segs() helper. Add the READ_ONCE()/WRITE_ONCE() pairs, and use netif_set_gso_max_segs() where we can to better document what is going on. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ethernet/freescale/fec_main.c | 2 +- drivers/net/ethernet/marvell/mv643xx_eth.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 +- drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_net_repr.c | 4 ++-- drivers/net/ethernet/realtek/r8169_main.c | 4 ++-- drivers/net/ethernet/sfc/ef100_nic.c | 4 ++-- drivers/net/ethernet/sfc/efx.c | 2 +- drivers/net/ethernet/sfc/falcon/efx.c | 2 +- drivers/net/ipvlan/ipvlan_main.c | 4 ++-- drivers/net/macvlan.c | 4 ++-- drivers/net/veth.c | 2 +- drivers/net/vxlan.c | 2 +- include/linux/netdevice.h | 7 +++++++ net/8021q/vlan.c | 2 +- net/8021q/vlan_dev.c | 2 +- net/bridge/br_if.c | 2 +- net/core/dev.c | 2 +- net/core/rtnetlink.c | 4 ++-- net/core/sock.c | 3 ++- 24 files changed, 37 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ff8da720a33a..cf73eacdda91 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1460,7 +1460,7 @@ done: bond_dev->hw_enc_features |= xfrm_features; #endif /* CONFIG_XFRM_OFFLOAD */ bond_dev->mpls_features = mpls_features; - bond_dev->gso_max_segs = gso_max_segs; + netif_set_gso_max_segs(bond_dev, gso_max_segs); netif_set_gso_max_size(bond_dev, gso_max_size); bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index bc418b910999..f38e70692514 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3558,7 +3558,7 @@ static int fec_enet_init(struct net_device *ndev) ndev->features |= NETIF_F_HW_VLAN_CTAG_RX; if (fep->quirks & FEC_QUIRK_HAS_CSUM) { - ndev->gso_max_segs = FEC_MAX_TSO_SEGS; + netif_set_gso_max_segs(ndev, FEC_MAX_TSO_SEGS); /* enable hw accelerator */ ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 116919730237..105247582684 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -3201,7 +3201,7 @@ static int mv643xx_eth_probe(struct platform_device *pdev) dev->hw_features = dev->features; dev->priv_flags |= IFF_UNICAST_FLT; - dev->gso_max_segs = MV643XX_MAX_TSO_SEGS; + netif_set_gso_max_segs(dev, MV643XX_MAX_TSO_SEGS); /* MTU range: 64 - 9500 */ dev->min_mtu = 64; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 350d24d7ead0..80e4b500695e 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -5335,7 +5335,7 @@ static int mvneta_probe(struct platform_device *pdev) dev->hw_features |= dev->features; dev->vlan_features |= dev->features; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - dev->gso_max_segs = MVNETA_MAX_TSO_SEGS; + netif_set_gso_max_segs(dev, MVNETA_MAX_TSO_SEGS); /* MTU range: 68 - 9676 */ dev->min_mtu = ETH_MIN_MTU; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 8b1ca0b13e88..49fc31fe0db8 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6857,7 +6857,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, mvpp2_set_hw_csum(port, port->pool_long->id); dev->vlan_features |= features; - dev->gso_max_segs = MVPP2_MAX_TSO_SEGS; + netif_set_gso_max_segs(dev, MVPP2_MAX_TSO_SEGS); dev->priv_flags |= IFF_UNICAST_FLT; /* MTU range: 68 - 9704 */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 1e0d0c9c1dac..1333edf1c361 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -2741,7 +2741,7 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->hw_features |= NETIF_F_LOOPBACK | NETIF_F_RXALL; - netdev->gso_max_segs = OTX2_MAX_GSO_SEGS; + netif_set_gso_max_segs(netdev, OTX2_MAX_GSO_SEGS); netdev->watchdog_timeo = OTX2_TX_TIMEOUT; netdev->netdev_ops = &otx2_netdev_ops; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 78944ad3492f..254bebffe8c1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -663,7 +663,7 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->hw_features |= NETIF_F_NTUPLE; netdev->hw_features |= NETIF_F_RXALL; - netdev->gso_max_segs = OTX2_MAX_GSO_SEGS; + netif_set_gso_max_segs(netdev, OTX2_MAX_GSO_SEGS); netdev->watchdog_timeo = OTX2_TX_TIMEOUT; netdev->netdev_ops = &otx2vf_netdev_ops; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 850bfdf83d0a..6e38da4ad554 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -4097,7 +4097,7 @@ static void nfp_net_netdev_init(struct nfp_net *nn) netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = nn->max_mtu; - netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS; + netif_set_gso_max_segs(netdev, NFP_NET_LSO_MAX_SEGS); netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 927ddbdf650b..181ac8e789a3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -287,7 +287,7 @@ nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower) return; netif_set_gso_max_size(netdev, lower->gso_max_size); - netdev->gso_max_segs = lower->gso_max_segs; + netif_set_gso_max_segs(netdev, lower->gso_max_segs); netdev_update_features(netdev); } @@ -381,7 +381,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, /* Advertise but disable TSO by default. */ netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6); - netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS; + netif_set_gso_max_segs(netdev, NFP_NET_LSO_MAX_SEGS); netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; netdev->features |= NETIF_F_LLTX; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index ff222c54299d..1f6313c8d308 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -5391,11 +5391,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rtl_chip_supports_csum_v2(tp)) { dev->hw_features |= NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6; netif_set_gso_max_size(dev, RTL_GSO_MAX_SIZE_V2); - dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2; + netif_set_gso_max_segs(dev, RTL_GSO_MAX_SEGS_V2); } else { dev->hw_features |= NETIF_F_SG | NETIF_F_TSO; netif_set_gso_max_size(dev, RTL_GSO_MAX_SIZE_V1); - dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1; + netif_set_gso_max_segs(dev, RTL_GSO_MAX_SEGS_V1); } dev->hw_features |= NETIF_F_RXALL; diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index d9015a77a6b8..5a6fed33a1d7 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -997,7 +997,7 @@ static int ef100_process_design_param(struct efx_nic *efx, return 0; case ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS: nic_data->tso_max_payload_num_segs = min_t(u64, reader->value, 0xffff); - efx->net_dev->gso_max_segs = nic_data->tso_max_payload_num_segs; + netif_set_gso_max_segs(efx->net_dev, nic_data->tso_max_payload_num_segs); return 0; case ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES: nic_data->tso_max_frames = min_t(u64, reader->value, 0xffff); @@ -1122,7 +1122,7 @@ static int ef100_probe_main(struct efx_nic *efx) nic_data->tso_max_frames = ESE_EF100_DP_GZ_TSO_MAX_NUM_FRAMES_DEFAULT; nic_data->tso_max_payload_num_segs = ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_NUM_SEGS_DEFAULT; nic_data->tso_max_payload_len = ESE_EF100_DP_GZ_TSO_MAX_PAYLOAD_LEN_DEFAULT; - net_dev->gso_max_segs = ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT; + netif_set_gso_max_segs(net_dev, ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT); /* Read design parameters */ rc = ef100_check_design_params(efx); if (rc) { diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 6960a2fe2b53..a8c252e2b252 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -709,7 +709,7 @@ static int efx_register_netdev(struct efx_nic *efx) if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) net_dev->priv_flags |= IFF_UNICAST_FLT; net_dev->ethtool_ops = &efx_ethtool_ops; - net_dev->gso_max_segs = EFX_TSO_MAX_SEGS; + netif_set_gso_max_segs(net_dev, EFX_TSO_MAX_SEGS); net_dev->min_mtu = EFX_MIN_MTU; net_dev->max_mtu = EFX_MAX_MTU; diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 314c9c69eb0e..60c595ef7589 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2267,7 +2267,7 @@ static int ef4_register_netdev(struct ef4_nic *efx) net_dev->irq = efx->pci_dev->irq; net_dev->netdev_ops = &ef4_netdev_ops; net_dev->ethtool_ops = &ef4_ethtool_ops; - net_dev->gso_max_segs = EF4_TSO_MAX_SEGS; + netif_set_gso_max_segs(net_dev, EF4_TSO_MAX_SEGS); net_dev->min_mtu = EF4_MIN_MTU; net_dev->max_mtu = EF4_MAX_MTU; diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 0ba63eccefa5..20da0b2bd246 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -141,7 +141,7 @@ static int ipvlan_init(struct net_device *dev) dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; netif_set_gso_max_size(dev, phy_dev->gso_max_size); - dev->gso_max_segs = phy_dev->gso_max_segs; + netif_set_gso_max_segs(dev, phy_dev->gso_max_segs); dev->hard_header_len = phy_dev->hard_header_len; netdev_lockdep_set_classes(dev); @@ -764,7 +764,7 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { netif_set_gso_max_size(ipvlan->dev, dev->gso_max_size); - ipvlan->dev->gso_max_segs = dev->gso_max_segs; + netif_set_gso_max_segs(ipvlan->dev, dev->gso_max_segs); netdev_update_features(ipvlan->dev); } break; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 506e9559df80..75b453acd778 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -901,7 +901,7 @@ static int macvlan_init(struct net_device *dev) dev->vlan_features |= ALWAYS_ON_OFFLOADS; dev->hw_enc_features |= dev->features; netif_set_gso_max_size(dev, lowerdev->gso_max_size); - dev->gso_max_segs = lowerdev->gso_max_segs; + netif_set_gso_max_segs(dev, lowerdev->gso_max_segs); dev->hard_header_len = lowerdev->hard_header_len; macvlan_set_lockdep_class(dev); @@ -1749,7 +1749,7 @@ static int macvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(vlan, &port->vlans, list) { netif_set_gso_max_size(vlan->dev, dev->gso_max_size); - vlan->dev->gso_max_segs = dev->gso_max_segs; + netif_set_gso_max_segs(vlan->dev, dev->gso_max_segs); netdev_update_features(vlan->dev); } break; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index f2f66fb293fd..5ca0a899101d 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1690,7 +1690,7 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, peer->ifindex = ifmp->ifi_index; netif_set_gso_max_size(peer, dev->gso_max_size); - peer->gso_max_segs = dev->gso_max_segs; + netif_set_gso_max_segs(peer, dev->gso_max_segs); err = register_netdevice(peer); put_net(net); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index df4f1712be95..82bd794fceb3 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3812,7 +3812,7 @@ static void vxlan_config_apply(struct net_device *dev, dst->remote_ifindex = conf->remote_ifindex; netif_set_gso_max_size(dev, lowerdev->gso_max_size); - dev->gso_max_segs = lowerdev->gso_max_segs; + netif_set_gso_max_segs(dev, lowerdev->gso_max_segs); needed_headroom = lowerdev->hard_header_len; needed_headroom += lowerdev->needed_headroom; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 14eeb58ed197..df049864661d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4735,6 +4735,13 @@ static inline void netif_set_gso_max_size(struct net_device *dev, WRITE_ONCE(dev->gso_max_size, size); } +static inline void netif_set_gso_max_segs(struct net_device *dev, + unsigned int segs) +{ + /* dev->gso_max_segs is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_max_segs, segs); +} + static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 34c0ffa81e5f..0c00200c9cb2 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -323,7 +323,7 @@ static void vlan_transfer_features(struct net_device *dev, struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); netif_set_gso_max_size(vlandev, dev->gso_max_size); - vlandev->gso_max_segs = dev->gso_max_segs; + netif_set_gso_max_segs(vlandev, dev->gso_max_segs); if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 208f6845f6dd..e9499a7c19fe 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -574,7 +574,7 @@ static int vlan_dev_init(struct net_device *dev) dev->features |= dev->hw_features | NETIF_F_LLTX; netif_set_gso_max_size(dev, real_dev->gso_max_size); - dev->gso_max_segs = real_dev->gso_max_segs; + netif_set_gso_max_segs(dev, real_dev->gso_max_segs); if (dev->features & NETIF_F_VLAN_FEATURES) netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n"); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index d3e1c2276551..3915832a03c2 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -526,7 +526,7 @@ static void br_set_gso_limits(struct net_bridge *br) gso_max_segs = min(gso_max_segs, p->dev->gso_max_segs); } netif_set_gso_max_size(br->dev, gso_max_size); - br->dev->gso_max_segs = gso_max_segs; + netif_set_gso_max_segs(br->dev, gso_max_segs); } /* diff --git a/net/core/dev.c b/net/core/dev.c index 9219e319e901..9c4fc8c3f981 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3396,7 +3396,7 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb, { u16 gso_segs = skb_shinfo(skb)->gso_segs; - if (gso_segs > dev->gso_max_segs) + if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2af8aeeadadf..fd030e02f16d 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2768,7 +2768,7 @@ static int do_setlink(const struct sk_buff *skb, } if (dev->gso_max_segs ^ max_segs) { - dev->gso_max_segs = max_segs; + netif_set_gso_max_segs(dev, max_segs); status |= DO_SETLINK_MODIFIED; } } @@ -3222,7 +3222,7 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, if (tb[IFLA_GSO_MAX_SIZE]) netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE])); if (tb[IFLA_GSO_MAX_SEGS]) - dev->gso_max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); + netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS])); return dev; } diff --git a/net/core/sock.c b/net/core/sock.c index 4418e2a07c34..31a2b79c9b38 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2259,7 +2259,8 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; /* pairs with the WRITE_ONCE() in netif_set_gso_max_size() */ sk->sk_gso_max_size = READ_ONCE(dst->dev->gso_max_size); - max_segs = max_t(u32, dst->dev->gso_max_segs, 1); + /* pairs with the WRITE_ONCE() in netif_set_gso_max_segs() */ + max_segs = max_t(u32, READ_ONCE(dst->dev->gso_max_segs), 1); } } sk->sk_gso_max_segs = max_segs; -- cgit v1.2.3 From 291dcae39bc482f7edc91a50d97027327e0cf5f9 Mon Sep 17 00:00:00 2001 From: Sean Anderson Date: Fri, 19 Nov 2021 10:58:09 -0500 Subject: net: phylink: Add helpers for c22 registers without MDIO Some devices expose memory-mapped c22-compliant PHYs. Because these devices do not have an MDIO bus, we cannot use the existing helpers. Refactor the existing helpers to allow supplying the values for c22 registers directly, instead of using MDIO to access them. Only get_state and set_advertisement are converted, since they contain the most complex logic. Because set_advertisement is never actually used outside phylink_mii_c22_pcs_config, move the MDIO-writing part into that function. Because some modes do not need the advertisement register set at all, we use -EINVAL for this purpose. Additionally, a new function phylink_pcs_enable_an is provided to determine whether to enable autonegotiation. Signed-off-by: Sean Anderson Reviewed-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 104 ++++++++++++++++++++++++++-------------------- include/linux/phylink.h | 7 ++-- 2 files changed, 64 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index da17b874a5e7..2d201a795775 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2815,31 +2815,22 @@ void phylink_decode_usxgmii_word(struct phylink_link_state *state, EXPORT_SYMBOL_GPL(phylink_decode_usxgmii_word); /** - * phylink_mii_c22_pcs_get_state() - read the MAC PCS state - * @pcs: a pointer to a &struct mdio_device. + * phylink_mii_c22_pcs_decode_state() - Decode MAC PCS state from MII registers * @state: a pointer to a &struct phylink_link_state. + * @bmsr: The value of the %MII_BMSR register + * @lpa: The value of the %MII_LPA register * * Helper for MAC PCS supporting the 802.3 clause 22 register set for * clause 37 negotiation and/or SGMII control. * - * Read the MAC PCS state from the MII device configured in @config and - * parse the Clause 37 or Cisco SGMII link partner negotiation word into - * the phylink @state structure. This is suitable to be directly plugged - * into the mac_pcs_get_state() member of the struct phylink_mac_ops - * structure. + * Parse the Clause 37 or Cisco SGMII link partner negotiation word into + * the phylink @state structure. This is suitable to be used for implementing + * the mac_pcs_get_state() member of the struct phylink_mac_ops structure if + * accessing @bmsr and @lpa cannot be done with MDIO directly. */ -void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, - struct phylink_link_state *state) +void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, + u16 bmsr, u16 lpa) { - int bmsr, lpa; - - bmsr = mdiodev_read(pcs, MII_BMSR); - lpa = mdiodev_read(pcs, MII_LPA); - if (bmsr < 0 || lpa < 0) { - state->link = false; - return; - } - state->link = !!(bmsr & BMSR_LSTATUS); state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); /* If there is no link or autonegotiation is disabled, the LP advertisement @@ -2867,28 +2858,54 @@ void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, break; } } +EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_decode_state); + +/** + * phylink_mii_c22_pcs_get_state() - read the MAC PCS state + * @pcs: a pointer to a &struct mdio_device. + * @state: a pointer to a &struct phylink_link_state. + * + * Helper for MAC PCS supporting the 802.3 clause 22 register set for + * clause 37 negotiation and/or SGMII control. + * + * Read the MAC PCS state from the MII device configured in @config and + * parse the Clause 37 or Cisco SGMII link partner negotiation word into + * the phylink @state structure. This is suitable to be directly plugged + * into the mac_pcs_get_state() member of the struct phylink_mac_ops + * structure. + */ +void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, + struct phylink_link_state *state) +{ + int bmsr, lpa; + + bmsr = mdiodev_read(pcs, MII_BMSR); + lpa = mdiodev_read(pcs, MII_LPA); + if (bmsr < 0 || lpa < 0) { + state->link = false; + return; + } + + phylink_mii_c22_pcs_decode_state(state, bmsr, lpa); +} EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_get_state); /** - * phylink_mii_c22_pcs_set_advertisement() - configure the clause 37 PCS + * phylink_mii_c22_pcs_encode_advertisement() - configure the clause 37 PCS * advertisement - * @pcs: a pointer to a &struct mdio_device. * @interface: the PHY interface mode being configured * @advertising: the ethtool advertisement mask * * Helper for MAC PCS supporting the 802.3 clause 22 register set for * clause 37 negotiation and/or SGMII control. * - * Configure the clause 37 PCS advertisement as specified by @state. This - * does not trigger a renegotiation; phylink will do that via the - * mac_an_restart() method of the struct phylink_mac_ops structure. + * Encode the clause 37 PCS advertisement as specified by @interface and + * @advertising. * - * Returns negative error code on failure to configure the advertisement, - * zero if no change has been made, or one if the advertisement has changed. + * Return: The new value for @adv, or ``-EINVAL`` if it should not be changed. */ -int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, - phy_interface_t interface, - const unsigned long *advertising) +int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, + const unsigned long *advertising) { u16 adv; @@ -2902,18 +2919,15 @@ int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) adv |= ADVERTISE_1000XPSE_ASYM; - - return mdiodev_modify_changed(pcs, MII_ADVERTISE, 0xffff, adv); - + return adv; case PHY_INTERFACE_MODE_SGMII: - return mdiodev_modify_changed(pcs, MII_ADVERTISE, 0xffff, 0x0001); - + return 0x0001; default: /* Nothing to do for other modes */ - return 0; + return -EINVAL; } } -EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_set_advertisement); +EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_encode_advertisement); /** * phylink_mii_c22_pcs_config() - configure clause 22 PCS @@ -2931,16 +2945,18 @@ int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising) { - bool changed; + bool changed = 0; u16 bmcr; - int ret; + int ret, adv; - ret = phylink_mii_c22_pcs_set_advertisement(pcs, interface, - advertising); - if (ret < 0) - return ret; - - changed = ret > 0; + adv = phylink_mii_c22_pcs_encode_advertisement(interface, advertising); + if (adv >= 0) { + ret = mdiobus_modify_changed(pcs->bus, pcs->addr, + MII_ADVERTISE, 0xffff, adv); + if (ret < 0) + return ret; + changed = ret; + } /* Ensure ISOLATE bit is disabled */ if (mode == MLO_AN_INBAND && @@ -2953,7 +2969,7 @@ int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, if (ret < 0) return ret; - return changed ? 1 : 0; + return changed; } EXPORT_SYMBOL_GPL(phylink_mii_c22_pcs_config); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 3563820a1765..01224235df0f 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -527,11 +527,12 @@ void phylink_set_port_modes(unsigned long *bits); void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); +void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, + u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); -int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, - phy_interface_t interface, - const unsigned long *advertising); +int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, + const unsigned long *advertising); int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising); -- cgit v1.2.3 From c4804670026b93f4ebddda30af89fd737bf93931 Mon Sep 17 00:00:00 2001 From: M Chetan Kumar Date: Sat, 20 Nov 2021 21:51:54 +0530 Subject: net: wwan: common debugfs base dir for wwan device This patch set brings in a common debugfs base directory i.e. /sys/kernel/debugfs/wwan/ in WWAN Subsystem for a WWAN device instance. So that it avoids driver polluting debugfs root with unrelated directories & possible name collusion. Having a common debugfs base directory for WWAN drivers eases user to match control devices with debugfs entries. WWAN Subsystem creates dentry (/sys/kernel/debugfs/wwan) on module load & removes dentry on module unload. When driver registers a new wwan device, dentry (wwanX) is created for WWAN device instance & on driver unregister dentry is removed. New API is introduced to return the wwan device instance dentry so that driver can create debugfs entries under it. Signed-off-by: M Chetan Kumar Reviewed-by: Loic Poulain Signed-off-by: David S. Miller --- drivers/net/wwan/wwan_core.c | 30 ++++++++++++++++++++++++++++-- include/linux/wwan.h | 2 ++ 2 files changed, 30 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index d293ab688044..5bf62dc35ac7 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -3,6 +3,7 @@ #include #include +#include #include #include #include @@ -25,6 +26,7 @@ static DEFINE_IDA(minors); /* minors for WWAN port chardevs */ static DEFINE_IDA(wwan_dev_ids); /* for unique WWAN device IDs */ static struct class *wwan_class; static int wwan_major; +static struct dentry *wwan_debugfs_dir; #define to_wwan_dev(d) container_of(d, struct wwan_device, dev) #define to_wwan_port(d) container_of(d, struct wwan_port, dev) @@ -40,6 +42,7 @@ static int wwan_major; * @port_id: Current available port ID to pick. * @ops: wwan device ops * @ops_ctxt: context to pass to ops + * @debugfs_dir: WWAN device debugfs dir */ struct wwan_device { unsigned int id; @@ -47,6 +50,7 @@ struct wwan_device { atomic_t port_id; const struct wwan_ops *ops; void *ops_ctxt; + struct dentry *debugfs_dir; }; /** @@ -142,6 +146,18 @@ static struct wwan_device *wwan_dev_get_by_name(const char *name) return to_wwan_dev(dev); } +struct dentry *wwan_get_debugfs_dir(struct device *parent) +{ + struct wwan_device *wwandev; + + wwandev = wwan_dev_get_by_parent(parent); + if (IS_ERR(wwandev)) + return ERR_CAST(wwandev); + + return wwandev->debugfs_dir; +} +EXPORT_SYMBOL_GPL(wwan_get_debugfs_dir); + /* This function allocates and registers a new WWAN device OR if a WWAN device * already exist for the given parent, it gets a reference and return it. * This function is not exported (for now), it is called indirectly via @@ -150,6 +166,7 @@ static struct wwan_device *wwan_dev_get_by_name(const char *name) static struct wwan_device *wwan_create_dev(struct device *parent) { struct wwan_device *wwandev; + const char *wwandev_name; int err, id; /* The 'find-alloc-register' operation must be protected against @@ -189,6 +206,10 @@ static struct wwan_device *wwan_create_dev(struct device *parent) goto done_unlock; } + wwandev_name = kobject_name(&wwandev->dev.kobj); + wwandev->debugfs_dir = debugfs_create_dir(wwandev_name, + wwan_debugfs_dir); + done_unlock: mutex_unlock(&wwan_register_lock); @@ -218,10 +239,12 @@ static void wwan_remove_dev(struct wwan_device *wwandev) else ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); - if (!ret) + if (!ret) { + debugfs_remove_recursive(wwandev->debugfs_dir); device_unregister(&wwandev->dev); - else + } else { put_device(&wwandev->dev); + } mutex_unlock(&wwan_register_lock); } @@ -1117,6 +1140,8 @@ static int __init wwan_init(void) goto destroy; } + wwan_debugfs_dir = debugfs_create_dir("wwan", NULL); + return 0; destroy: @@ -1128,6 +1153,7 @@ unregister: static void __exit wwan_exit(void) { + debugfs_remove_recursive(wwan_debugfs_dir); __unregister_chrdev(wwan_major, 0, WWAN_MAX_MINORS, "wwan_port"); rtnl_link_unregister(&wwan_rtnl_link_ops); class_destroy(wwan_class); diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 9fac819f92e3..1646aa3e6779 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -171,4 +171,6 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, void wwan_unregister_ops(struct device *parent); +struct dentry *wwan_get_debugfs_dir(struct device *parent); + #endif /* __WWAN_H */ -- cgit v1.2.3 From fba84957e2e2e201cf4e352efe0c7cac0fbb5d5d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 20 Nov 2021 16:31:48 -0800 Subject: skbuff: Move conditional preprocessor directives out of struct sk_buff In preparation for using the struct_group() macro in struct sk_buff, move the conditional preprocessor directives out of the region of struct sk_buff that will be enclosed by struct_group(). While GCC and Clang are happy with conditional preprocessor directives here, sparse is not, even under -Wno-directive-within-macro[1], as would be seen under a C=1 build: net/core/filter.c: note: in included file (through include/linux/netlink.h, include/linux/sock_diag.h): ./include/linux/skbuff.h:820:1: warning: directive in macro's argument list ./include/linux/skbuff.h:822:1: warning: directive in macro's argument list ./include/linux/skbuff.h:846:1: warning: directive in macro's argument list ./include/linux/skbuff.h:848:1: warning: directive in macro's argument list Additionally remove empty macro argument definitions and usage. "objdump -d" shows no object code differences. [1] https://www.spinics.net/lists/linux-sparse/msg10857.html Signed-off-by: Kees Cook Signed-off-by: David S. Miller --- include/linux/skbuff.h | 36 +++++++++++++++++++----------------- net/core/filter.c | 10 +++++----- 2 files changed, 24 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 059b6266dcd7..c7889afe0d0d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -795,7 +795,7 @@ struct sk_buff { #else #define CLONED_MASK 1 #endif -#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) +#define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; @@ -818,18 +818,10 @@ struct sk_buff { __u32 headers_start[0]; /* public: */ -/* if you move pkt_type around you also must adapt those constants */ -#ifdef __BIG_ENDIAN_BITFIELD -#define PKT_TYPE_MAX (7 << 5) -#else -#define PKT_TYPE_MAX 7 -#endif -#define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) - /* private: */ __u8 __pkt_type_offset[0]; /* public: */ - __u8 pkt_type:3; + __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 nf_trace:1; __u8 ip_summed:2; @@ -845,16 +837,10 @@ struct sk_buff { __u8 encap_hdr_csum:1; __u8 csum_valid:1; -#ifdef __BIG_ENDIAN_BITFIELD -#define PKT_VLAN_PRESENT_BIT 7 -#else -#define PKT_VLAN_PRESENT_BIT 0 -#endif -#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) /* private: */ __u8 __pkt_vlan_present_offset[0]; /* public: */ - __u8 vlan_present:1; + __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; @@ -953,6 +939,22 @@ struct sk_buff { #endif }; +/* if you move pkt_type around you also must adapt those constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_TYPE_MAX (7 << 5) +#else +#define PKT_TYPE_MAX 7 +#endif +#define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) + +/* if you move pkt_vlan_present around you also must adapt these constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_VLAN_PRESENT_BIT 7 +#else +#define PKT_VLAN_PRESENT_BIT 0 +#endif +#define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) + #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel diff --git a/net/core/filter.c b/net/core/filter.c index efebbaf4e00b..8271624a19aa 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -301,7 +301,7 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, break; case SKF_AD_PKTTYPE: - *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET()); + *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, 5); @@ -323,7 +323,7 @@ static u32 convert_skb_access(int skb_field, int dst_reg, int src_reg, offsetof(struct sk_buff, vlan_tci)); break; case SKF_AD_VLAN_TAG_PRESENT: - *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET()); + *insn++ = BPF_LDX_MEM(BPF_B, dst_reg, src_reg, PKT_VLAN_PRESENT_OFFSET); if (PKT_VLAN_PRESENT_BIT) *insn++ = BPF_ALU32_IMM(BPF_RSH, dst_reg, PKT_VLAN_PRESENT_BIT); if (PKT_VLAN_PRESENT_BIT < 7) @@ -8029,7 +8029,7 @@ static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, * (Fast-path, otherwise approximation that we might be * a clone, do the rest in helper.) */ - *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET()); + *insn++ = BPF_LDX_MEM(BPF_B, BPF_REG_6, BPF_REG_1, CLONED_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_6, CLONED_MASK); *insn++ = BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 7); @@ -8617,7 +8617,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, pkt_type): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, - PKT_TYPE_OFFSET()); + PKT_TYPE_OFFSET); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, PKT_TYPE_MAX); #ifdef __BIG_ENDIAN_BITFIELD *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, 5); @@ -8642,7 +8642,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, case offsetof(struct __sk_buff, vlan_present): *target_size = 1; *insn++ = BPF_LDX_MEM(BPF_B, si->dst_reg, si->src_reg, - PKT_VLAN_PRESENT_OFFSET()); + PKT_VLAN_PRESENT_OFFSET); if (PKT_VLAN_PRESENT_BIT) *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, PKT_VLAN_PRESENT_BIT); if (PKT_VLAN_PRESENT_BIT < 7) -- cgit v1.2.3 From 03f61041c17914355dde7261be9ccdc821ddd454 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Sat, 20 Nov 2021 16:31:49 -0800 Subject: skbuff: Switch structure bounds to struct_group() In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Replace the existing empty member position markers "headers_start" and "headers_end" with a struct_group(). This will allow memcpy() and sizeof() to more easily reason about sizes, and improve readability. "pahole" shows no size nor member offset changes to struct sk_buff. "objdump -d" shows no object code changes (outside of WARNs affected by source line number changes). Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Jason A. Donenfeld # drivers/net/wireguard/* Link: https://lore.kernel.org/lkml/20210728035006.GD35706@embeddedor Signed-off-by: David S. Miller --- drivers/net/wireguard/queueing.h | 4 +--- include/linux/skbuff.h | 10 +++------- net/core/skbuff.c | 14 +++++--------- 3 files changed, 9 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireguard/queueing.h b/drivers/net/wireguard/queueing.h index 4ef2944a68bc..52da5e963003 100644 --- a/drivers/net/wireguard/queueing.h +++ b/drivers/net/wireguard/queueing.h @@ -79,9 +79,7 @@ static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating) u8 sw_hash = skb->sw_hash; u32 hash = skb->hash; skb_scrub_packet(skb, true); - memset(&skb->headers_start, 0, - offsetof(struct sk_buff, headers_end) - - offsetof(struct sk_buff, headers_start)); + memset(&skb->headers, 0, sizeof(skb->headers)); if (encapsulating) { skb->l4_hash = l4_hash; skb->sw_hash = sw_hash; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c7889afe0d0d..eba256af64a5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -811,12 +811,10 @@ struct sk_buff { __u8 active_extensions; #endif - /* fields enclosed in headers_start/headers_end are copied + /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ - /* private: */ - __u32 headers_start[0]; - /* public: */ + struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; @@ -921,9 +919,7 @@ struct sk_buff { u64 kcov_handle; #endif - /* private: */ - __u32 headers_end[0]; - /* public: */ + ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 73720bc1daa3..a33247fdb8f5 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -992,12 +992,10 @@ void napi_consume_skb(struct sk_buff *skb, int budget) } EXPORT_SYMBOL(napi_consume_skb); -/* Make sure a field is enclosed inside headers_start/headers_end section */ +/* Make sure a field is contained by headers group */ #define CHECK_SKB_FIELD(field) \ - BUILD_BUG_ON(offsetof(struct sk_buff, field) < \ - offsetof(struct sk_buff, headers_start)); \ - BUILD_BUG_ON(offsetof(struct sk_buff, field) > \ - offsetof(struct sk_buff, headers_end)); \ + BUILD_BUG_ON(offsetof(struct sk_buff, field) != \ + offsetof(struct sk_buff, headers.field)); \ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) { @@ -1009,14 +1007,12 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) __skb_ext_copy(new, old); __nf_copy(new, old, false); - /* Note : this field could be in headers_start/headers_end section + /* Note : this field could be in the headers group. * It is not yet because we do not want to have a 16 bit hole */ new->queue_mapping = old->queue_mapping; - memcpy(&new->headers_start, &old->headers_start, - offsetof(struct sk_buff, headers_end) - - offsetof(struct sk_buff, headers_start)); + memcpy(&new->headers, &old->headers, sizeof(new->headers)); CHECK_SKB_FIELD(protocol); CHECK_SKB_FIELD(csum); CHECK_SKB_FIELD(hash); -- cgit v1.2.3 From e523af4ee56090fbdd9cf474752448d35930bcd4 Mon Sep 17 00:00:00 2001 From: Shiraz Saleem Date: Mon, 18 Oct 2021 18:16:02 -0500 Subject: net/ice: Add support for enable_iwarp and enable_roce devlink param Allow support for 'enable_iwarp' and 'enable_roce' devlink params to turn on/off iWARP or RoCE protocol support for E800 devices. For example, a user can turn on iWARP functionality with, devlink dev param set pci/0000:07:00.0 name enable_iwarp value true cmode runtime This add an iWARP auxiliary rdma device, ice.iwarp.<>, under this PF. A user request to enable both iWARP and RoCE under the same PF is rejected since this device does not support both protocols simultaneously on the same port. Signed-off-by: Shiraz Saleem Tested-by: Leszek Kaliszczuk Signed-off-by: Tony Nguyen --- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_devlink.c | 144 +++++++++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_devlink.h | 6 ++ drivers/net/ethernet/intel/ice/ice_idc.c | 4 +- drivers/net/ethernet/intel/ice/ice_main.c | 9 +- include/linux/net/intel/iidc.h | 7 +- 6 files changed, 166 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index b2db39ee5f85..b67ad51cbcc9 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -576,6 +576,7 @@ struct ice_pf { struct ice_hw_port_stats stats_prev; struct ice_hw hw; u8 stat_prev_loaded:1; /* has previous stats been loaded */ + u8 rdma_mode; u16 dcbx_cap; u32 tx_timeout_count; unsigned long tx_timeout_last_recovery; diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index b9bd9f9472f6..478412b28a76 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -430,6 +430,120 @@ static const struct devlink_ops ice_devlink_ops = { .flash_update = ice_devlink_flash_update, }; +static int +ice_devlink_enable_roce_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + + ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2; + + return 0; +} + +static int +ice_devlink_enable_roce_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool roce_ena = ctx->val.vbool; + int ret; + + if (!roce_ena) { + ice_unplug_aux_dev(pf); + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + return 0; + } + + pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; + ret = ice_plug_aux_dev(pf); + if (ret) + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_ROCEV2; + + return ret; +} + +static int +ice_devlink_enable_roce_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP) { + NL_SET_ERR_MSG_MOD(extack, "iWARP is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); + return -EOPNOTSUPP; + } + + return 0; +} + +static int +ice_devlink_enable_iw_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + + ctx->val.vbool = pf->rdma_mode & IIDC_RDMA_PROTOCOL_IWARP; + + return 0; +} + +static int +ice_devlink_enable_iw_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool iw_ena = ctx->val.vbool; + int ret; + + if (!iw_ena) { + ice_unplug_aux_dev(pf); + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + return 0; + } + + pf->rdma_mode |= IIDC_RDMA_PROTOCOL_IWARP; + ret = ice_plug_aux_dev(pf); + if (ret) + pf->rdma_mode &= ~IIDC_RDMA_PROTOCOL_IWARP; + + return ret; +} + +static int +ice_devlink_enable_iw_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (!test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + if (pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2) { + NL_SET_ERR_MSG_MOD(extack, "RoCEv2 is currently enabled. This device cannot enable iWARP and RoCEv2 simultaneously"); + return -EOPNOTSUPP; + } + + return 0; +} + +static const struct devlink_param ice_devlink_params[] = { + DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_enable_roce_get, + ice_devlink_enable_roce_set, + ice_devlink_enable_roce_validate), + DEVLINK_PARAM_GENERIC(ENABLE_IWARP, BIT(DEVLINK_PARAM_CMODE_RUNTIME), + ice_devlink_enable_iw_get, + ice_devlink_enable_iw_set, + ice_devlink_enable_iw_validate), + +}; + static void ice_devlink_free(void *devlink_ptr) { devlink_free((struct devlink *)devlink_ptr); @@ -484,6 +598,36 @@ void ice_devlink_unregister(struct ice_pf *pf) devlink_unregister(priv_to_devlink(pf)); } +int ice_devlink_register_params(struct ice_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value value; + int err; + + err = devlink_params_register(devlink, ice_devlink_params, + ARRAY_SIZE(ice_devlink_params)); + if (err) + return err; + + value.vbool = false; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP, + value); + + value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags) ? true : false; + devlink_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + value); + + return 0; +} + +void ice_devlink_unregister_params(struct ice_pf *pf) +{ + devlink_params_unregister(priv_to_devlink(pf), ice_devlink_params, + ARRAY_SIZE(ice_devlink_params)); +} + /** * ice_devlink_create_pf_port - Create a devlink port for this PF * @pf: the PF to create a devlink port for diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.h b/drivers/net/ethernet/intel/ice/ice_devlink.h index b7f9551e4fc4..faea757fcf5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.h +++ b/drivers/net/ethernet/intel/ice/ice_devlink.h @@ -4,10 +4,16 @@ #ifndef _ICE_DEVLINK_H_ #define _ICE_DEVLINK_H_ +enum ice_devlink_param_id { + ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, +}; + struct ice_pf *ice_allocate_pf(struct device *dev); void ice_devlink_register(struct ice_pf *pf); void ice_devlink_unregister(struct ice_pf *pf); +int ice_devlink_register_params(struct ice_pf *pf); +void ice_devlink_unregister_params(struct ice_pf *pf); int ice_devlink_create_pf_port(struct ice_pf *pf); void ice_devlink_destroy_pf_port(struct ice_pf *pf); int ice_devlink_create_vf_port(struct ice_vf *vf); diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index adcc9a251595..fc3580167e7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -288,7 +288,7 @@ int ice_plug_aux_dev(struct ice_pf *pf) adev->id = pf->aux_idx; adev->dev.release = ice_adev_release; adev->dev.parent = &pf->pdev->dev; - adev->name = IIDC_RDMA_ROCE_NAME; + adev->name = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ? "roce" : "iwarp"; ret = auxiliary_device_init(adev); if (ret) { @@ -335,6 +335,6 @@ int ice_init_rdma(struct ice_pf *pf) dev_err(dev, "failed to reserve vectors for RDMA\n"); return ret; } - + pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; return ice_plug_aux_dev(pf); } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index f099797f35e3..f2a5f2f965d1 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4705,6 +4705,10 @@ probe_done: if (err) goto err_netdev_reg; + err = ice_devlink_register_params(pf); + if (err) + goto err_netdev_reg; + /* ready to go, so clear down state bit */ clear_bit(ICE_DOWN, pf->state); if (ice_is_aux_ena(pf)) { @@ -4712,7 +4716,7 @@ probe_done: if (pf->aux_idx < 0) { dev_err(dev, "Failed to allocate device ID for AUX driver\n"); err = -ENOMEM; - goto err_netdev_reg; + goto err_devlink_reg_param; } err = ice_init_rdma(pf); @@ -4731,6 +4735,8 @@ probe_done: err_init_aux_unroll: pf->adev = NULL; ida_free(&ice_aux_ida, pf->aux_idx); +err_devlink_reg_param: + ice_devlink_unregister_params(pf); err_netdev_reg: err_send_version_unroll: ice_vsi_release_all(pf); @@ -4845,6 +4851,7 @@ static void ice_remove(struct pci_dev *pdev) ice_unplug_aux_dev(pf); if (pf->aux_idx >= 0) ida_free(&ice_aux_ida, pf->aux_idx); + ice_devlink_unregister_params(pf); set_bit(ICE_DOWN, pf->state); mutex_destroy(&(&pf->hw)->fdir_fltr_lock); diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index e32f6712aee0..1289593411d3 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -26,6 +26,11 @@ enum iidc_reset_type { IIDC_GLOBR, }; +enum iidc_rdma_protocol { + IIDC_RDMA_PROTOCOL_IWARP = BIT(0), + IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1), +}; + #define IIDC_MAX_USER_PRIORITY 8 /* Struct to hold per RDMA Qset info */ @@ -70,8 +75,6 @@ int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); -#define IIDC_RDMA_ROCE_NAME "roce" - /* Structure representing auxiliary driver tailored information about the core * PCI dev, each auxiliary driver using the IIDC interface will have an * instance of this struct dedicated to it. -- cgit v1.2.3 From 6326948f940dc3f77066d5cdc44ba6afe67830c0 Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Wed, 29 Sep 2021 11:01:21 -0400 Subject: lsm: security_task_getsecid_subj() -> security_current_getsecid_subj() The security_task_getsecid_subj() LSM hook invites misuse by allowing callers to specify a task even though the hook is only safe when the current task is referenced. Fix this by removing the task_struct argument to the hook, requiring LSM implementations to use the current task. While we are changing the hook declaration we also rename the function to security_current_getsecid_subj() in an effort to reinforce that the hook captures the subjective credentials of the current task and not an arbitrary task on the system. Reviewed-by: Serge Hallyn Reviewed-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 3 +-- include/linux/lsm_hooks.h | 8 +++----- include/linux/security.h | 4 ++-- kernel/audit.c | 4 ++-- kernel/auditfilter.c | 3 +-- kernel/auditsc.c | 11 ++++++++++- net/netlabel/netlabel_unlabeled.c | 2 +- net/netlabel/netlabel_user.h | 2 +- security/apparmor/lsm.c | 13 ++++++++++--- security/integrity/ima/ima_appraise.c | 2 +- security/integrity/ima/ima_main.c | 14 +++++++------- security/security.c | 6 +++--- security/selinux/hooks.c | 19 +++---------------- security/smack/smack.h | 16 ---------------- security/smack/smack_lsm.c | 9 ++++----- 15 files changed, 49 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index df8de62f4710..ae2228f0711d 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -206,8 +206,7 @@ LSM_HOOK(int, 0, task_fix_setgid, struct cred *new, const struct cred * old, LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid) LSM_HOOK(int, 0, task_getpgid, struct task_struct *p) LSM_HOOK(int, 0, task_getsid, struct task_struct *p) -LSM_HOOK(void, LSM_RET_VOID, task_getsecid_subj, - struct task_struct *p, u32 *secid) +LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj, struct task_struct *p, u32 *secid) LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice) diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index d45b6f6e27fd..52c1990644b9 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -719,11 +719,9 @@ * @p. * @p contains the task_struct for the process. * Return 0 if permission is granted. - * @task_getsecid_subj: - * Retrieve the subjective security identifier of the task_struct in @p - * and return it in @secid. Special care must be taken to ensure that @p - * is the either the "current" task, or the caller has exclusive access - * to @p. + * @current_getsecid_subj: + * Retrieve the subjective security identifier of the current task and + * return it in @secid. * In case of failure, @secid will be set to zero. * @task_getsecid_obj: * Retrieve the objective security identifier of the task_struct in @p diff --git a/include/linux/security.h b/include/linux/security.h index bbf44a466832..bb301963e333 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -418,7 +418,7 @@ int security_task_fix_setgid(struct cred *new, const struct cred *old, int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); int security_task_getsid(struct task_struct *p); -void security_task_getsecid_subj(struct task_struct *p, u32 *secid); +void security_current_getsecid_subj(u32 *secid); void security_task_getsecid_obj(struct task_struct *p, u32 *secid); int security_task_setnice(struct task_struct *p, int nice); int security_task_setioprio(struct task_struct *p, int ioprio); @@ -1119,7 +1119,7 @@ static inline int security_task_getsid(struct task_struct *p) return 0; } -static inline void security_task_getsecid_subj(struct task_struct *p, u32 *secid) +static inline void security_current_getsecid_subj(u32 *secid) { *secid = 0; } diff --git a/kernel/audit.c b/kernel/audit.c index 121d37e700a6..d4084751cfe6 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2132,7 +2132,7 @@ int audit_log_task_context(struct audit_buffer *ab) int error; u32 sid; - security_task_getsecid_subj(current, &sid); + security_current_getsecid_subj(&sid); if (!sid) return 0; @@ -2353,7 +2353,7 @@ int audit_signal_info(int sig, struct task_struct *t) audit_sig_uid = auid; else audit_sig_uid = uid; - security_task_getsecid_subj(current, &audit_sig_sid); + security_current_getsecid_subj(&audit_sig_sid); } return audit_signal_info_syscall(t); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index d75acb014ccd..4173e771650c 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1368,8 +1368,7 @@ int audit_filter(int msgtype, unsigned int listtype) case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { - security_task_getsecid_subj(current, - &sid); + security_current_getsecid_subj(&sid); result = security_audit_rule_match(sid, f->type, f->op, f->lsm_rule); } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b517947bfa48..fce5d43a933f 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -666,7 +666,16 @@ static int audit_filter_rules(struct task_struct *tsk, logged upon error */ if (f->lsm_rule) { if (need_sid) { - security_task_getsecid_subj(tsk, &sid); + /* @tsk should always be equal to + * @current with the exception of + * fork()/copy_process() in which case + * the new @tsk creds are still a dup + * of @current's creds so we can still + * use security_current_getsecid_subj() + * here even though it always refs + * @current's creds + */ + security_current_getsecid_subj(&sid); need_sid = 0; } result = security_audit_rule_match(sid, f->type, diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 566ba4397ee4..8490e46359ae 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1537,7 +1537,7 @@ int __init netlbl_unlabel_defconf(void) /* Only the kernel is allowed to call this function and the only time * it is called is at bootup before the audit subsystem is reporting * messages so don't worry to much about these values. */ - security_task_getsecid_subj(current, &audit_info.secid); + security_current_getsecid_subj(&audit_info.secid); audit_info.loginuid = GLOBAL_ROOT_UID; audit_info.sessionid = 0; diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index 6190cbf94bf0..d6c5b31eb4eb 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -32,7 +32,7 @@ */ static inline void netlbl_netlink_auditinfo(struct netlbl_audit *audit_info) { - security_task_getsecid_subj(current, &audit_info->secid); + security_current_getsecid_subj(&audit_info->secid); audit_info->loginuid = audit_get_loginuid(current); audit_info->sessionid = audit_get_sessionid(current); } diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 0d6585056f3d..4f0eecb67dde 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -728,7 +728,14 @@ static void apparmor_bprm_committed_creds(struct linux_binprm *bprm) return; } -static void apparmor_task_getsecid(struct task_struct *p, u32 *secid) +static void apparmor_current_getsecid_subj(u32 *secid) +{ + struct aa_label *label = aa_get_current_label(); + *secid = label->secid; + aa_put_label(label); +} + +static void apparmor_task_getsecid_obj(struct task_struct *p, u32 *secid) { struct aa_label *label = aa_get_task_label(p); *secid = label->secid; @@ -1252,8 +1259,8 @@ static struct security_hook_list apparmor_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(task_free, apparmor_task_free), LSM_HOOK_INIT(task_alloc, apparmor_task_alloc), - LSM_HOOK_INIT(task_getsecid_subj, apparmor_task_getsecid), - LSM_HOOK_INIT(task_getsecid_obj, apparmor_task_getsecid), + LSM_HOOK_INIT(current_getsecid_subj, apparmor_current_getsecid_subj), + LSM_HOOK_INIT(task_getsecid_obj, apparmor_task_getsecid_obj), LSM_HOOK_INIT(task_setrlimit, apparmor_task_setrlimit), LSM_HOOK_INIT(task_kill, apparmor_task_kill), diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index dbba51583e7c..17232bbfb9f9 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -76,7 +76,7 @@ int ima_must_appraise(struct user_namespace *mnt_userns, struct inode *inode, if (!ima_appraise) return 0; - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); return ima_match_policy(mnt_userns, inode, current_cred(), secid, func, mask, IMA_APPRAISE | IMA_HASH, NULL, NULL, NULL, NULL); diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 465865412100..8c6e4514d494 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -408,7 +408,7 @@ int ima_file_mmap(struct file *file, unsigned long prot) u32 secid; if (file && (prot & PROT_EXEC)) { - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK); } @@ -446,7 +446,7 @@ int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot) !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_user_ns(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK, @@ -487,7 +487,7 @@ int ima_bprm_check(struct linux_binprm *bprm) int ret; u32 secid; - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) @@ -512,7 +512,7 @@ int ima_file_check(struct file *file, int mask) { u32 secid; - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); @@ -709,7 +709,7 @@ int ima_read_file(struct file *file, enum kernel_read_file_id read_id, /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, MAY_READ, func); } @@ -752,7 +752,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size, } func = read_idmap[read_id] ?: FILE_CHECK; - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, buf, size, MAY_READ, func); } @@ -905,7 +905,7 @@ int process_buffer_measurement(struct user_namespace *mnt_userns, * buffer measurements. */ if (func) { - security_task_getsecid_subj(current, &secid); + security_current_getsecid_subj(&secid); action = ima_get_action(mnt_userns, inode, current_cred(), secid, 0, func, &pcr, &template, func_data, NULL); diff --git a/security/security.c b/security/security.c index c88167a414b4..edb922b8bf4a 100644 --- a/security/security.c +++ b/security/security.c @@ -1808,12 +1808,12 @@ int security_task_getsid(struct task_struct *p) return call_int_hook(task_getsid, 0, p); } -void security_task_getsecid_subj(struct task_struct *p, u32 *secid) +void security_current_getsecid_subj(u32 *secid) { *secid = 0; - call_void_hook(task_getsecid_subj, p, secid); + call_void_hook(current_getsecid_subj, secid); } -EXPORT_SYMBOL(security_task_getsecid_subj); +EXPORT_SYMBOL(security_current_getsecid_subj); void security_task_getsecid_obj(struct task_struct *p, u32 *secid) { diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 62d30c0a30c2..726175254f60 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -229,19 +229,6 @@ static inline u32 cred_sid(const struct cred *cred) return tsec->sid; } -/* - * get the subjective security ID of a task - */ -static inline u32 task_sid_subj(const struct task_struct *task) -{ - u32 sid; - - rcu_read_lock(); - sid = cred_sid(rcu_dereference(task->cred)); - rcu_read_unlock(); - return sid; -} - /* * get the objective security ID of a task */ @@ -4205,9 +4192,9 @@ static int selinux_task_getsid(struct task_struct *p) PROCESS__GETSESSION, NULL); } -static void selinux_task_getsecid_subj(struct task_struct *p, u32 *secid) +static void selinux_current_getsecid_subj(u32 *secid) { - *secid = task_sid_subj(p); + *secid = current_sid(); } static void selinux_task_getsecid_obj(struct task_struct *p, u32 *secid) @@ -7159,7 +7146,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid), LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid), LSM_HOOK_INIT(task_getsid, selinux_task_getsid), - LSM_HOOK_INIT(task_getsecid_subj, selinux_task_getsecid_subj), + LSM_HOOK_INIT(current_getsecid_subj, selinux_current_getsecid_subj), LSM_HOOK_INIT(task_getsecid_obj, selinux_task_getsecid_obj), LSM_HOOK_INIT(task_setnice, selinux_task_setnice), LSM_HOOK_INIT(task_setioprio, selinux_task_setioprio), diff --git a/security/smack/smack.h b/security/smack/smack.h index 99c3422596ab..fc837dcebf96 100644 --- a/security/smack/smack.h +++ b/security/smack/smack.h @@ -389,22 +389,6 @@ static inline struct smack_known *smk_of_task(const struct task_smack *tsp) return tsp->smk_task; } -static inline struct smack_known *smk_of_task_struct_subj( - const struct task_struct *t) -{ - struct smack_known *skp; - const struct cred *cred; - - rcu_read_lock(); - - cred = rcu_dereference(t->cred); - skp = smk_of_task(smack_cred(cred)); - - rcu_read_unlock(); - - return skp; -} - static inline struct smack_known *smk_of_task_struct_obj( const struct task_struct *t) { diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index efd35b07c7f8..14b279cc75c9 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -2067,15 +2067,14 @@ static int smack_task_getsid(struct task_struct *p) } /** - * smack_task_getsecid_subj - get the subjective secid of the task - * @p: the task + * smack_current_getsecid_subj - get the subjective secid of the current task * @secid: where to put the result * * Sets the secid to contain a u32 version of the task's subjective smack label. */ -static void smack_task_getsecid_subj(struct task_struct *p, u32 *secid) +static void smack_current_getsecid_subj(u32 *secid) { - struct smack_known *skp = smk_of_task_struct_subj(p); + struct smack_known *skp = smk_of_current(); *secid = skp->smk_secid; } @@ -4807,7 +4806,7 @@ static struct security_hook_list smack_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(task_setpgid, smack_task_setpgid), LSM_HOOK_INIT(task_getpgid, smack_task_getpgid), LSM_HOOK_INIT(task_getsid, smack_task_getsid), - LSM_HOOK_INIT(task_getsecid_subj, smack_task_getsecid_subj), + LSM_HOOK_INIT(current_getsecid_subj, smack_current_getsecid_subj), LSM_HOOK_INIT(task_getsecid_obj, smack_task_getsecid_obj), LSM_HOOK_INIT(task_setnice, smack_task_setnice), LSM_HOOK_INIT(task_setioprio, smack_task_setioprio), -- cgit v1.2.3 From 91389c390521a02ecfb91270f5b9d7fae4312ae5 Mon Sep 17 00:00:00 2001 From: Samuel Holland Date: Thu, 18 Nov 2021 21:33:37 -0600 Subject: clk: sunxi-ng: Allow the CCU core to be built as a module Like the individual CCU drivers, it can be beneficial for memory consumption of cross-platform configurations to only load the CCU core on the relevant platform. For example, a generic arm64 kernel sees the following improvement when building the CCU core and drivers as modules: before: text data bss dec hex filename 13882360 5251670 360800 19494830 12977ae vmlinux after: text data bss dec hex filename 13734787 5086442 360800 19182029 124b1cd vmlinux So the result is a 390KB total reduction in kernel image size. The one early clock provider (sun5i) requires the core to be built in. Now that loading the MMC driver will trigger loading the CCU core, the MMC timing mode functions do not need a compile-time fallback. Signed-off-by: Samuel Holland Signed-off-by: Maxime Ripard Link: https://lore.kernel.org/r/20211119033338.25486-5-samuel@sholland.org --- drivers/clk/Makefile | 2 +- drivers/clk/sunxi-ng/Kconfig | 3 ++- drivers/clk/sunxi-ng/Makefile | 33 ++++++++++++++++++--------------- drivers/clk/sunxi-ng/ccu_common.c | 3 +++ drivers/mmc/host/Kconfig | 1 + include/linux/clk/sunxi-ng.h | 15 --------------- 6 files changed, 25 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index e42312121e51..6afe36bd2c0a 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -110,7 +110,7 @@ obj-$(CONFIG_PLAT_SPEAR) += spear/ obj-y += sprd/ obj-$(CONFIG_ARCH_STI) += st/ obj-$(CONFIG_ARCH_SUNXI) += sunxi/ -obj-$(CONFIG_SUNXI_CCU) += sunxi-ng/ +obj-y += sunxi-ng/ obj-$(CONFIG_ARCH_TEGRA) += tegra/ obj-y += ti/ obj-$(CONFIG_CLK_UNIPHIER) += uniphier/ diff --git a/drivers/clk/sunxi-ng/Kconfig b/drivers/clk/sunxi-ng/Kconfig index de88b6e0ec69..727ff755eca4 100644 --- a/drivers/clk/sunxi-ng/Kconfig +++ b/drivers/clk/sunxi-ng/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only config SUNXI_CCU - bool "Clock support for Allwinner SoCs" + tristate "Clock support for Allwinner SoCs" depends on ARCH_SUNXI || COMPILE_TEST select RESET_CONTROLLER default ARCH_SUNXI @@ -52,6 +52,7 @@ config SUN5I_CCU bool "Support for the Allwinner sun5i family CCM" default MACH_SUN5I depends on MACH_SUN5I || COMPILE_TEST + depends on SUNXI_CCU=y config SUN6I_A31_CCU tristate "Support for the Allwinner A31/A31s CCU" diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile index 1020ed49a588..659d55150c32 100644 --- a/drivers/clk/sunxi-ng/Makefile +++ b/drivers/clk/sunxi-ng/Makefile @@ -1,24 +1,27 @@ # SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SUNXI_CCU) += sunxi-ccu.o + # Common objects -obj-y += ccu_common.o -obj-y += ccu_mmc_timing.o -obj-y += ccu_reset.o +sunxi-ccu-y += ccu_common.o +sunxi-ccu-y += ccu_mmc_timing.o +sunxi-ccu-y += ccu_reset.o # Base clock types -obj-y += ccu_div.o -obj-y += ccu_frac.o -obj-y += ccu_gate.o -obj-y += ccu_mux.o -obj-y += ccu_mult.o -obj-y += ccu_phase.o -obj-y += ccu_sdm.o +sunxi-ccu-y += ccu_div.o +sunxi-ccu-y += ccu_frac.o +sunxi-ccu-y += ccu_gate.o +sunxi-ccu-y += ccu_mux.o +sunxi-ccu-y += ccu_mult.o +sunxi-ccu-y += ccu_phase.o +sunxi-ccu-y += ccu_sdm.o # Multi-factor clocks -obj-y += ccu_nk.o -obj-y += ccu_nkm.o -obj-y += ccu_nkmp.o -obj-y += ccu_nm.o -obj-y += ccu_mp.o +sunxi-ccu-y += ccu_nk.o +sunxi-ccu-y += ccu_nkm.o +sunxi-ccu-y += ccu_nkmp.o +sunxi-ccu-y += ccu_nm.o +sunxi-ccu-y += ccu_mp.o # SoC support obj-$(CONFIG_SUNIV_F1C100S_CCU) += suniv-f1c100s-ccu.o diff --git a/drivers/clk/sunxi-ng/ccu_common.c b/drivers/clk/sunxi-ng/ccu_common.c index 6afdedbce6a2..8d28a7a079d0 100644 --- a/drivers/clk/sunxi-ng/ccu_common.c +++ b/drivers/clk/sunxi-ng/ccu_common.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include "ccu_common.h" @@ -214,3 +215,5 @@ void of_sunxi_ccu_probe(struct device_node *node, void __iomem *reg, kfree(ccu); } } + +MODULE_LICENSE("GPL"); diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 5af8494c31b5..52b0b27a6839 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -966,6 +966,7 @@ config MMC_REALTEK_USB config MMC_SUNXI tristate "Allwinner sunxi SD/MMC Host Controller support" depends on ARCH_SUNXI || COMPILE_TEST + depends on SUNXI_CCU help This selects support for the SD/MMC Host Controller on Allwinner sunxi SoCs. diff --git a/include/linux/clk/sunxi-ng.h b/include/linux/clk/sunxi-ng.h index 3cd14acde0a1..cf32123b39f5 100644 --- a/include/linux/clk/sunxi-ng.h +++ b/include/linux/clk/sunxi-ng.h @@ -6,22 +6,7 @@ #ifndef _LINUX_CLK_SUNXI_NG_H_ #define _LINUX_CLK_SUNXI_NG_H_ -#include - -#ifdef CONFIG_SUNXI_CCU int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, bool new_mode); int sunxi_ccu_get_mmc_timing_mode(struct clk *clk); -#else -static inline int sunxi_ccu_set_mmc_timing_mode(struct clk *clk, - bool new_mode) -{ - return -ENOTSUPP; -} - -static inline int sunxi_ccu_get_mmc_timing_mode(struct clk *clk) -{ - return -ENOTSUPP; -} -#endif #endif -- cgit v1.2.3 From c214f124161d446b340597e7c968e0a2dc149142 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 9 Nov 2021 19:57:10 +0000 Subject: arch_topology: Introduce thermal pressure update function The thermal pressure is a mechanism which is used for providing information about reduced CPU performance to the scheduler. Usually code has to convert the value from frequency units into capacity units, which are understandable by the scheduler. Create a common conversion code which can be just used via a handy API. Internally, the topology_update_thermal_pressure() operates on frequency in MHz and max CPU frequency is taken from 'freq_factor' (per-cpu). Signed-off-by: Lukasz Luba Reviewed-by: Thara Gopinath Signed-off-by: Viresh Kumar --- arch/arm/include/asm/topology.h | 1 + arch/arm64/include/asm/topology.h | 1 + drivers/base/arch_topology.c | 43 ++++++++++++++++++++++++++++++++++++++- include/linux/arch_topology.h | 3 +++ include/linux/sched/topology.h | 7 +++++++ 5 files changed, 54 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 470299ee2fba..f1eafacc9a30 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -24,6 +24,7 @@ /* Replace task scheduler's default thermal pressure API */ #define arch_scale_thermal_pressure topology_get_thermal_pressure #define arch_set_thermal_pressure topology_set_thermal_pressure +#define arch_update_thermal_pressure topology_update_thermal_pressure #else diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index ec2db3419c41..7a421cbc99ed 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -33,6 +33,7 @@ void update_freq_counters_refs(void); /* Replace task scheduler's default thermal pressure API */ #define arch_scale_thermal_pressure topology_get_thermal_pressure #define arch_set_thermal_pressure topology_set_thermal_pressure +#define arch_update_thermal_pressure topology_update_thermal_pressure #include diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index ff16a36a908b..a3ae0b4eea09 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -22,6 +22,7 @@ static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; +static DEFINE_PER_CPU(u32, freq_factor) = 1; static bool supports_scale_freq_counters(const struct cpumask *cpus) { @@ -165,6 +166,47 @@ void topology_set_thermal_pressure(const struct cpumask *cpus, } EXPORT_SYMBOL_GPL(topology_set_thermal_pressure); +/** + * topology_update_thermal_pressure() - Update thermal pressure for CPUs + * @cpus : The related CPUs for which capacity has been reduced + * @capped_freq : The maximum allowed frequency that CPUs can run at + * + * Update the value of thermal pressure for all @cpus in the mask. The + * cpumask should include all (online+offline) affected CPUs, to avoid + * operating on stale data when hot-plug is used for some CPUs. The + * @capped_freq reflects the currently allowed max CPUs frequency due to + * thermal capping. It might be also a boost frequency value, which is bigger + * than the internal 'freq_factor' max frequency. In such case the pressure + * value should simply be removed, since this is an indication that there is + * no thermal throttling. The @capped_freq must be provided in kHz. + */ +void topology_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_freq) +{ + unsigned long max_capacity, capacity; + u32 max_freq; + int cpu; + + cpu = cpumask_first(cpus); + max_capacity = arch_scale_cpu_capacity(cpu); + max_freq = per_cpu(freq_factor, cpu); + + /* Convert to MHz scale which is used in 'freq_factor' */ + capped_freq /= 1000; + + /* + * Handle properly the boost frequencies, which should simply clean + * the thermal pressure value. + */ + if (max_freq <= capped_freq) + capacity = max_capacity; + else + capacity = mult_frac(max_capacity, capped_freq, max_freq); + + arch_set_thermal_pressure(cpus, max_capacity - capacity); +} +EXPORT_SYMBOL_GPL(topology_update_thermal_pressure); + static ssize_t cpu_capacity_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -217,7 +259,6 @@ static void update_topology_flags_workfn(struct work_struct *work) update_topology = 0; } -static DEFINE_PER_CPU(u32, freq_factor) = 1; static u32 *raw_capacity; static int free_raw_capacity(void) diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index b97cea83b25e..ace1e5dcf773 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -59,6 +59,9 @@ static inline unsigned long topology_get_thermal_pressure(int cpu) void topology_set_thermal_pressure(const struct cpumask *cpus, unsigned long th_pressure); +void topology_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_freq); + struct cpu_topology { int thread_id; int core_id; diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index c07bfa2d80f2..6e89a8e43aa7 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -273,6 +273,13 @@ void arch_set_thermal_pressure(const struct cpumask *cpus, { } #endif +#ifndef arch_update_thermal_pressure +static __always_inline +void arch_update_thermal_pressure(const struct cpumask *cpus, + unsigned long capped_frequency) +{ } +#endif + static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p)); -- cgit v1.2.3 From 7e97b3dc2556743dd02612c92a8de7026e8d7dc9 Mon Sep 17 00:00:00 2001 From: Lukasz Luba Date: Tue, 9 Nov 2021 19:57:14 +0000 Subject: arch_topology: Remove unused topology_set_thermal_pressure() and related There is no need of this function (and related) since code has been converted to use the new arch_update_thermal_pressure() API. The old code can be removed. Signed-off-by: Lukasz Luba Signed-off-by: Viresh Kumar --- arch/arm/include/asm/topology.h | 1 - arch/arm64/include/asm/topology.h | 1 - drivers/base/arch_topology.c | 17 +++++------------ include/linux/arch_topology.h | 3 --- include/linux/sched/topology.h | 7 ------- init/Kconfig | 2 +- 6 files changed, 6 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index f1eafacc9a30..c7d2510e5a78 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -23,7 +23,6 @@ /* Replace task scheduler's default thermal pressure API */ #define arch_scale_thermal_pressure topology_get_thermal_pressure -#define arch_set_thermal_pressure topology_set_thermal_pressure #define arch_update_thermal_pressure topology_update_thermal_pressure #else diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 7a421cbc99ed..f386b90a79c8 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -32,7 +32,6 @@ void update_freq_counters_refs(void); /* Replace task scheduler's default thermal pressure API */ #define arch_scale_thermal_pressure topology_get_thermal_pressure -#define arch_set_thermal_pressure topology_set_thermal_pressure #define arch_update_thermal_pressure topology_update_thermal_pressure #include diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index a3ae0b4eea09..976154140f0b 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -156,16 +156,6 @@ void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity) DEFINE_PER_CPU(unsigned long, thermal_pressure); -void topology_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure) -{ - int cpu; - - for_each_cpu(cpu, cpus) - WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure); -} -EXPORT_SYMBOL_GPL(topology_set_thermal_pressure); - /** * topology_update_thermal_pressure() - Update thermal pressure for CPUs * @cpus : The related CPUs for which capacity has been reduced @@ -183,7 +173,7 @@ EXPORT_SYMBOL_GPL(topology_set_thermal_pressure); void topology_update_thermal_pressure(const struct cpumask *cpus, unsigned long capped_freq) { - unsigned long max_capacity, capacity; + unsigned long max_capacity, capacity, th_pressure; u32 max_freq; int cpu; @@ -203,7 +193,10 @@ void topology_update_thermal_pressure(const struct cpumask *cpus, else capacity = mult_frac(max_capacity, capped_freq, max_freq); - arch_set_thermal_pressure(cpus, max_capacity - capacity); + th_pressure = max_capacity - capacity; + + for_each_cpu(cpu, cpus) + WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure); } EXPORT_SYMBOL_GPL(topology_update_thermal_pressure); diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index ace1e5dcf773..cce6136b300a 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -56,9 +56,6 @@ static inline unsigned long topology_get_thermal_pressure(int cpu) return per_cpu(thermal_pressure, cpu); } -void topology_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure); - void topology_update_thermal_pressure(const struct cpumask *cpus, unsigned long capped_freq); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 6e89a8e43aa7..8054641c0a7b 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -266,13 +266,6 @@ unsigned long arch_scale_thermal_pressure(int cpu) } #endif -#ifndef arch_set_thermal_pressure -static __always_inline -void arch_set_thermal_pressure(const struct cpumask *cpus, - unsigned long th_pressure) -{ } -#endif - #ifndef arch_update_thermal_pressure static __always_inline void arch_update_thermal_pressure(const struct cpumask *cpus, diff --git a/init/Kconfig b/init/Kconfig index 036b750e8d8a..086fd11348e0 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -550,7 +550,7 @@ config SCHED_THERMAL_PRESSURE i.e. put less load on throttled CPUs than on non/less throttled ones. This requires the architecture to implement - arch_set_thermal_pressure() and arch_scale_thermal_pressure(). + arch_update_thermal_pressure() and arch_scale_thermal_pressure(). config BSD_PROCESS_ACCT bool "BSD Process Accounting" -- cgit v1.2.3 From cff6f593251cdf5398dc3c57f7032b8e9dcb633e Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Tue, 23 Nov 2021 12:36:47 +0200 Subject: regulator: rohm-generic: iniline stub function The function rohm_regulator_set_voltage_sel_restricted() has a stub implementation. Linux-next testing spot following: include/linux/mfd/rohm-generic.h:93:12: error: 'rohm_regulator_set_voltage_sel_restricted' defined but not used Fix this by inlining the stub. Fixes: 8b6e88555971 ("regulator: rohm-regulator: add helper for restricted voltage setting") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/YZzEP3S7U15bTDAI@fedora Signed-off-by: Mark Brown --- include/linux/mfd/rohm-generic.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 35c5866f48b7..080d60adcd5f 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -90,7 +90,8 @@ static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dv { return 0; } -static int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, + +static inline int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, unsigned int sel) { return 0; -- cgit v1.2.3 From 2106efda785b55a8957efed9a52dfa28ee0d7280 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 22 Nov 2021 17:24:47 -0800 Subject: net: remove .ndo_change_proto_down .ndo_change_proto_down was added seemingly to enable out-of-tree implementations. Over 2.5yrs later we still have no real users upstream. Hardwire the generic implementation for now, we can revert once real users materialize. (rocker is a test vehicle, not a user.) We need to drop the optimization on the sysfs side, because unlike ndos priv_flags will be changed at runtime, so we'd need READ_ONCE/WRITE_ONCE everywhere.. Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/rocker/rocker_main.c | 12 ------------ drivers/net/macvlan.c | 3 +-- drivers/net/vxlan.c | 3 +-- include/linux/netdevice.h | 12 +++--------- net/8021q/vlanproc.c | 2 +- net/core/dev.c | 26 ++++---------------------- net/core/net-sysfs.c | 8 -------- net/core/rtnetlink.c | 3 +-- 8 files changed, 11 insertions(+), 58 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index ba4062881eed..b620470c7905 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1995,17 +1995,6 @@ static int rocker_port_get_phys_port_name(struct net_device *dev, return err ? -EOPNOTSUPP : 0; } -static int rocker_port_change_proto_down(struct net_device *dev, - bool proto_down) -{ - struct rocker_port *rocker_port = netdev_priv(dev); - - if (rocker_port->dev->flags & IFF_UP) - rocker_port_set_enable(rocker_port, !proto_down); - rocker_port->dev->proto_down = proto_down; - return 0; -} - static void rocker_port_neigh_destroy(struct net_device *dev, struct neighbour *n) { @@ -2037,7 +2026,6 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_set_mac_address = rocker_port_set_mac_address, .ndo_change_mtu = rocker_port_change_mtu, .ndo_get_phys_port_name = rocker_port_get_phys_port_name, - .ndo_change_proto_down = rocker_port_change_proto_down, .ndo_neigh_destroy = rocker_port_neigh_destroy, .ndo_get_port_parent_id = rocker_port_get_port_parent_id, }; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 75b453acd778..6ef5f77be4d0 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1171,7 +1171,6 @@ static const struct net_device_ops macvlan_netdev_ops = { #endif .ndo_get_iflink = macvlan_dev_get_iflink, .ndo_features_check = passthru_features_check, - .ndo_change_proto_down = dev_change_proto_down_generic, }; void macvlan_common_setup(struct net_device *dev) @@ -1182,7 +1181,7 @@ void macvlan_common_setup(struct net_device *dev) dev->max_mtu = ETH_MAX_MTU; dev->priv_flags &= ~IFF_TX_SKB_SHARING; netif_keep_dst(dev); - dev->priv_flags |= IFF_UNICAST_FLT; + dev->priv_flags |= IFF_UNICAST_FLT | IFF_CHANGE_PROTO_DOWN; dev->netdev_ops = &macvlan_netdev_ops; dev->needs_free_netdev = true; dev->header_ops = &macvlan_hard_header_ops; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 82bd794fceb3..fecff0a46612 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -3234,7 +3234,6 @@ static const struct net_device_ops vxlan_netdev_ether_ops = { .ndo_fdb_dump = vxlan_fdb_dump, .ndo_fdb_get = vxlan_fdb_get, .ndo_fill_metadata_dst = vxlan_fill_metadata_dst, - .ndo_change_proto_down = dev_change_proto_down_generic, }; static const struct net_device_ops vxlan_netdev_raw_ops = { @@ -3305,7 +3304,7 @@ static void vxlan_setup(struct net_device *dev) dev->hw_features |= NETIF_F_RXCSUM; dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); - dev->priv_flags |= IFF_NO_QUEUE; + dev->priv_flags |= IFF_NO_QUEUE | IFF_CHANGE_PROTO_DOWN; /* MTU range: 68 - 65535 */ dev->min_mtu = ETH_MIN_MTU; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index df049864661d..db3bff1ae7fd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1297,11 +1297,6 @@ struct netdev_net_notifier { * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. - * void (*ndo_change_proto_down)(struct net_device *dev, - * bool proto_down); - * This function is used to pass protocol port error state information - * to the switch driver. The switch driver can react to the proto_down - * by doing a phys down on the associated switch port. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while @@ -1542,8 +1537,6 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); - int (*ndo_change_proto_down)(struct net_device *dev, - bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, @@ -1612,6 +1605,7 @@ struct net_device_ops { * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) + * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1646,6 +1640,7 @@ enum netdev_priv_flags { IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, IFF_TX_SKB_NO_LINEAR = 1<<31, + IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1982,7 +1977,7 @@ struct net_device { /* Read-mostly cache-line for fast-path access */ unsigned int flags; - unsigned int priv_flags; + unsigned long long priv_flags; const struct net_device_ops *netdev_ops; int ifindex; unsigned short gflags; @@ -3735,7 +3730,6 @@ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index ec87dea23719..08bf6c839e25 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -252,7 +252,7 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset) stats = dev_get_stats(vlandev, &temp); seq_printf(seq, - "%s VID: %d REORDER_HDR: %i dev->priv_flags: %hx\n", + "%s VID: %d REORDER_HDR: %i dev->priv_flags: %llx\n", vlandev->name, vlan->vlan_id, (int)(vlan->flags & 1), vlandev->priv_flags); diff --git a/net/core/dev.c b/net/core/dev.c index 9c4fc8c3f981..823917de0d2b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8558,35 +8558,17 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) EXPORT_SYMBOL(netdev_port_same_parent_id); /** - * dev_change_proto_down - update protocol port state information + * dev_change_proto_down - set carrier according to proto_down. + * * @dev: device * @proto_down: new value - * - * This info can be used by switch drivers to set the phys state of the - * port. */ int dev_change_proto_down(struct net_device *dev, bool proto_down) { - const struct net_device_ops *ops = dev->netdev_ops; - - if (!ops->ndo_change_proto_down) + if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; - return ops->ndo_change_proto_down(dev, proto_down); -} -EXPORT_SYMBOL(dev_change_proto_down); - -/** - * dev_change_proto_down_generic - generic implementation for - * ndo_change_proto_down that sets carrier according to - * proto_down. - * - * @dev: device - * @proto_down: new value - */ -int dev_change_proto_down_generic(struct net_device *dev, bool proto_down) -{ if (proto_down) netif_carrier_off(dev); else @@ -8594,7 +8576,7 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down) dev->proto_down = proto_down; return 0; } -EXPORT_SYMBOL(dev_change_proto_down_generic); +EXPORT_SYMBOL(dev_change_proto_down); /** * dev_change_proto_down_reason - proto down reason diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4edd58d34f16..affe34d71d31 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -488,14 +488,6 @@ static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { - struct net_device *netdev = to_net_dev(dev); - - /* The check is also done in change_proto_down; this helps returning - * early without hitting the trylock/restart in netdev_store. - */ - if (!netdev->netdev_ops->ndo_change_proto_down) - return -EOPNOTSUPP; - return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index fd030e02f16d..6f25c0a8aebe 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2539,13 +2539,12 @@ static int do_set_proto_down(struct net_device *dev, struct netlink_ext_ack *extack) { struct nlattr *pdreason[IFLA_PROTO_DOWN_REASON_MAX + 1]; - const struct net_device_ops *ops = dev->netdev_ops; unsigned long mask = 0; u32 value; bool proto_down; int err; - if (!ops->ndo_change_proto_down) { + if (!(dev->priv_flags & IFF_CHANGE_PROTO_DOWN)) { NL_SET_ERR_MSG(extack, "Protodown not supported by device"); return -EOPNOTSUPP; } -- cgit v1.2.3 From 985e9ece1e55a94da842f6c1f9ff84d587b26267 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 17 Nov 2021 20:07:35 +0200 Subject: ACPI: Make acpi_node_get_parent() local acpi_node_get_parent() isn't used outside drivers/acpi/property.c. Make it local. Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/acpi/property.c | 3 ++- include/linux/acpi.h | 7 ------- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 781e312f4534..2366f54d8e9c 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1084,7 +1084,8 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, * Returns parent node of an ACPI device or data firmware node or %NULL if * not available. */ -struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode) +static struct fwnode_handle * +acpi_node_get_parent(const struct fwnode_handle *fwnode) { if (is_acpi_data_node(fwnode)) { /* All data nodes have parent pointer so just return that */ diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 668d007f0917..b28f8790192a 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1182,7 +1182,6 @@ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); -struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, @@ -1287,12 +1286,6 @@ acpi_get_next_subnode(const struct fwnode_handle *fwnode, return NULL; } -static inline struct fwnode_handle * -acpi_node_get_parent(const struct fwnode_handle *fwnode) -{ - return NULL; -} - static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) -- cgit v1.2.3 From c6d5f1933085f9a92ed5c256a859ab31c7a35f88 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 22 Nov 2021 12:19:31 +0100 Subject: net: stmmac: Calculate CDC error only once The clock domain crossing error (CDC) is calculated at every fetch of Tx or Rx timestamps. It includes a division. Especially on arm32 based systems it is expensive. It also requires two conditionals in the hotpath. Add a compensation value cache to struct plat_stmmacenet_data and subtract it unconditionally in the RX/TX functions which spares the conditionals. The value is initialized to 0 and if supported calculated in the PTP initialization code. Suggested-by: Thomas Gleixner Signed-off-by: Kurt Kanzenbach Link: https://lore.kernel.org/r/20211122111931.135135-1-kurt@linutronix.de Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ++---------- drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 5 +++++ include/linux/stmmac.h | 1 + 3 files changed, 8 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 21111df73719..340076b5bb38 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -511,14 +511,6 @@ bool stmmac_eee_init(struct stmmac_priv *priv) return true; } -static inline u32 stmmac_cdc_adjust(struct stmmac_priv *priv) -{ - /* Correct the clk domain crossing(CDC) error */ - if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) - return (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate; - return 0; -} - /* stmmac_get_tx_hwtstamp - get HW TX timestamps * @priv: driver private structure * @p : descriptor pointer @@ -550,7 +542,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, } if (found) { - ns -= stmmac_cdc_adjust(priv); + ns -= priv->plat->cdc_error_adj; memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); @@ -587,7 +579,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, if (stmmac_get_rx_timestamp_status(priv, p, np, priv->adv_ts)) { stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns); - ns -= stmmac_cdc_adjust(priv); + ns -= priv->plat->cdc_error_adj; netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 580cc035536b..e14c97c04317 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -309,6 +309,11 @@ void stmmac_ptp_register(struct stmmac_priv *priv) if (priv->plat->ptp_max_adj) stmmac_ptp_clock_ops.max_adj = priv->plat->ptp_max_adj; + /* Calculate the clock domain crossing (CDC) error if necessary */ + priv->plat->cdc_error_adj = 0; + if (priv->plat->has_gmac4 && priv->plat->clk_ptp_rate) + priv->plat->cdc_error_adj = (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate; + stmmac_ptp_clock_ops.n_per_out = priv->dma_cap.pps_out_num; stmmac_ptp_clock_ops.n_ext_ts = priv->dma_cap.aux_snapshot_n; diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a6f03b36fc4f..89b8e208cd7b 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -241,6 +241,7 @@ struct plat_stmmacenet_data { unsigned int clk_ref_rate; unsigned int mult_fact_100ns; s32 ptp_max_adj; + u32 cdc_error_adj; struct reset_control *stmmac_rst; struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; -- cgit v1.2.3 From 393c3714081a53795bbff0e985d24146def6f57f Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 18 Nov 2021 15:00:08 -0800 Subject: kernfs: switch global kernfs_rwsem lock to per-fs lock The kernfs implementation has big lock granularity(kernfs_rwsem) so every kernfs-based(e.g., sysfs, cgroup) fs are able to compete the lock. It makes trouble for some cases to wait the global lock for a long time even though they are totally independent contexts each other. A general example is process A goes under direct reclaim with holding the lock when it accessed the file in sysfs and process B is waiting the lock with exclusive mode and then process C is waiting the lock until process B could finish the job after it gets the lock from process A. This patch switches the global kernfs_rwsem to per-fs lock, which put the rwsem into kernfs_root. Suggested-by: Tejun Heo Acked-by: Tejun Heo Signed-off-by: Minchan Kim Link: https://lore.kernel.org/r/20211118230008.2679780-1-minchan@kernel.org Signed-off-by: Greg Kroah-Hartman --- fs/kernfs/dir.c | 110 +++++++++++++++++++++++++++++-------------------- fs/kernfs/file.c | 6 ++- fs/kernfs/inode.c | 22 ++++++---- fs/kernfs/mount.c | 15 ++++--- fs/kernfs/symlink.c | 5 ++- include/linux/kernfs.h | 2 + 6 files changed, 97 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 8e0a1378a4b1..13cae0ccce74 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -17,7 +17,6 @@ #include "kernfs-internal.h" -DECLARE_RWSEM(kernfs_rwsem); static DEFINE_SPINLOCK(kernfs_rename_lock); /* kn->parent and ->name */ static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by rename_lock */ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ @@ -26,7 +25,7 @@ static DEFINE_SPINLOCK(kernfs_idr_lock); /* root->ino_idr */ static bool kernfs_active(struct kernfs_node *kn) { - lockdep_assert_held(&kernfs_rwsem); + lockdep_assert_held(&kernfs_root(kn)->kernfs_rwsem); return atomic_read(&kn->active) >= 0; } @@ -457,14 +456,15 @@ void kernfs_put_active(struct kernfs_node *kn) * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn) - __releases(&kernfs_rwsem) __acquires(&kernfs_rwsem) + __releases(&kernfs_root(kn)->kernfs_rwsem) + __acquires(&kernfs_root(kn)->kernfs_rwsem) { struct kernfs_root *root = kernfs_root(kn); - lockdep_assert_held_write(&kernfs_rwsem); + lockdep_assert_held_write(&root->kernfs_rwsem); WARN_ON_ONCE(kernfs_active(kn)); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); @@ -483,7 +483,7 @@ static void kernfs_drain(struct kernfs_node *kn) kernfs_drain_open_files(kn); - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); } /** @@ -718,11 +718,12 @@ err_unlock: int kernfs_add_one(struct kernfs_node *kn) { struct kernfs_node *parent = kn->parent; + struct kernfs_root *root = kernfs_root(parent); struct kernfs_iattrs *ps_iattr; bool has_ns; int ret; - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); @@ -753,7 +754,7 @@ int kernfs_add_one(struct kernfs_node *kn) ps_iattr->ia_mtime = ps_iattr->ia_ctime; } - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); /* * Activate the new node unless CREATE_DEACTIVATED is requested. @@ -767,7 +768,7 @@ int kernfs_add_one(struct kernfs_node *kn) return 0; out_unlock: - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); return ret; } @@ -788,7 +789,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; - lockdep_assert_held(&kernfs_rwsem); + lockdep_assert_held(&kernfs_root(parent)->kernfs_rwsem); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", @@ -820,7 +821,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, size_t len; char *p, *name; - lockdep_assert_held_read(&kernfs_rwsem); + lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem); /* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */ spin_lock_irq(&kernfs_rename_lock); @@ -859,11 +860,12 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; + struct kernfs_root *root = kernfs_root(parent); - down_read(&kernfs_rwsem); + down_read(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return kn; } @@ -883,11 +885,12 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const void *ns) { struct kernfs_node *kn; + struct kernfs_root *root = kernfs_root(parent); - down_read(&kernfs_rwsem); + down_read(&root->kernfs_rwsem); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return kn; } @@ -912,6 +915,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, return ERR_PTR(-ENOMEM); idr_init(&root->ino_idr); + init_rwsem(&root->kernfs_rwsem); INIT_LIST_HEAD(&root->supers); /* @@ -1035,6 +1039,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn; + struct kernfs_root *root; if (flags & LOOKUP_RCU) return -ECHILD; @@ -1046,18 +1051,19 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) /* If the kernfs parent node has changed discard and * proceed to ->lookup. */ - down_read(&kernfs_rwsem); spin_lock(&dentry->d_lock); parent = kernfs_dentry_node(dentry->d_parent); if (parent) { + spin_unlock(&dentry->d_lock); + root = kernfs_root(parent); + down_read(&root->kernfs_rwsem); if (kernfs_dir_changed(parent, dentry)) { - spin_unlock(&dentry->d_lock); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return 0; } - } - spin_unlock(&dentry->d_lock); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); + } else + spin_unlock(&dentry->d_lock); /* The kernfs parent node hasn't changed, leave the * dentry negative and return success. @@ -1066,7 +1072,8 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) } kn = kernfs_dentry_node(dentry); - down_read(&kernfs_rwsem); + root = kernfs_root(kn); + down_read(&root->kernfs_rwsem); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) @@ -1085,10 +1092,10 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags) kernfs_info(dentry->d_sb)->ns != kn->ns) goto out_bad; - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return 1; out_bad: - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return 0; } @@ -1102,10 +1109,12 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, { struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; + struct kernfs_root *root; struct inode *inode = NULL; const void *ns = NULL; - down_read(&kernfs_rwsem); + root = kernfs_root(parent); + down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; @@ -1116,7 +1125,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, * create a negative. */ if (!kernfs_active(kn)) { - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return NULL; } inode = kernfs_get_inode(dir->i_sb, kn); @@ -1131,7 +1140,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir, */ if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); /* instantiate and hash (possibly negative) dentry */ return d_splice_alias(inode, dentry); @@ -1254,7 +1263,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, { struct rb_node *rbn; - lockdep_assert_held_write(&kernfs_rwsem); + lockdep_assert_held_write(&kernfs_root(root)->kernfs_rwsem); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) @@ -1289,8 +1298,9 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; + struct kernfs_root *root = kernfs_root(kn); - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { @@ -1304,14 +1314,14 @@ void kernfs_activate(struct kernfs_node *kn) pos->flags |= KERNFS_ACTIVATED; } - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos; - lockdep_assert_held_write(&kernfs_rwsem); + lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); /* * Short-circuit if non-root @kn has already finished removal. @@ -1381,9 +1391,11 @@ static void __kernfs_remove(struct kernfs_node *kn) */ void kernfs_remove(struct kernfs_node *kn) { - down_write(&kernfs_rwsem); + struct kernfs_root *root = kernfs_root(kn); + + down_write(&root->kernfs_rwsem); __kernfs_remove(kn); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); } /** @@ -1469,8 +1481,9 @@ void kernfs_unbreak_active_protection(struct kernfs_node *kn) bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; + struct kernfs_root *root = kernfs_root(kn); - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); kernfs_break_active_protection(kn); /* @@ -1498,9 +1511,9 @@ bool kernfs_remove_self(struct kernfs_node *kn) atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); schedule(); - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); @@ -1513,7 +1526,7 @@ bool kernfs_remove_self(struct kernfs_node *kn) */ kernfs_unbreak_active_protection(kn); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); return ret; } @@ -1530,6 +1543,7 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const void *ns) { struct kernfs_node *kn; + struct kernfs_root *root; if (!parent) { WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n", @@ -1537,13 +1551,14 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, return -ENOENT; } - down_write(&kernfs_rwsem); + root = kernfs_root(parent); + down_write(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); if (kn) __kernfs_remove(kn); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); if (kn) return 0; @@ -1562,6 +1577,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const void *new_ns) { struct kernfs_node *old_parent; + struct kernfs_root *root; const char *old_name = NULL; int error; @@ -1569,7 +1585,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, if (!kn->parent) return -EINVAL; - down_write(&kernfs_rwsem); + root = kernfs_root(kn); + down_write(&root->kernfs_rwsem); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || @@ -1623,7 +1640,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, error = 0; out: - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); return error; } @@ -1694,11 +1711,14 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) struct dentry *dentry = file->f_path.dentry; struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; + struct kernfs_root *root; const void *ns = NULL; if (!dir_emit_dots(file, ctx)) return 0; - down_read(&kernfs_rwsem); + + root = kernfs_root(parent); + down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; @@ -1715,12 +1735,12 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) file->private_data = pos; kernfs_get(pos); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); if (!dir_emit(ctx, name, len, ino, type)) return 0; - down_read(&kernfs_rwsem); + down_read(&root->kernfs_rwsem); } - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); file->private_data = NULL; ctx->pos = INT_MAX; return 0; diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 60e2a86c535e..9414a7a60a9f 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -847,6 +847,7 @@ static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; + struct kernfs_root *root; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); @@ -859,8 +860,9 @@ repeat: kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); + root = kernfs_root(kn); /* kick fsnotify */ - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; @@ -898,7 +900,7 @@ repeat: iput(inode); } - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); kernfs_put(kn); goto repeat; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index c0eae1725435..3d783d80f5da 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -99,10 +99,11 @@ int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) int kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr) { int ret; + struct kernfs_root *root = kernfs_root(kn); - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); ret = __kernfs_setattr(kn, iattr); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); return ret; } @@ -111,12 +112,14 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct kernfs_node *kn = inode->i_private; + struct kernfs_root *root; int error; if (!kn) return -EINVAL; - down_write(&kernfs_rwsem); + root = kernfs_root(kn); + down_write(&root->kernfs_rwsem); error = setattr_prepare(&init_user_ns, dentry, iattr); if (error) goto out; @@ -129,7 +132,7 @@ int kernfs_iop_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, setattr_copy(&init_user_ns, inode, iattr); out: - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); return error; } @@ -184,13 +187,14 @@ int kernfs_iop_getattr(struct user_namespace *mnt_userns, { struct inode *inode = d_inode(path->dentry); struct kernfs_node *kn = inode->i_private; + struct kernfs_root *root = kernfs_root(kn); - down_read(&kernfs_rwsem); + down_read(&root->kernfs_rwsem); spin_lock(&inode->i_lock); kernfs_refresh_inode(kn, inode); generic_fillattr(&init_user_ns, inode, stat); spin_unlock(&inode->i_lock); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return 0; } @@ -274,19 +278,21 @@ int kernfs_iop_permission(struct user_namespace *mnt_userns, struct inode *inode, int mask) { struct kernfs_node *kn; + struct kernfs_root *root; int ret; if (mask & MAY_NOT_BLOCK) return -ECHILD; kn = inode->i_private; + root = kernfs_root(kn); - down_read(&kernfs_rwsem); + down_read(&root->kernfs_rwsem); spin_lock(&inode->i_lock); kernfs_refresh_inode(kn, inode); ret = generic_permission(&init_user_ns, inode, mask); spin_unlock(&inode->i_lock); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return ret; } diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index f2f909d09f52..cfa79715fc1a 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -236,6 +236,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn, static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc) { struct kernfs_super_info *info = kernfs_info(sb); + struct kernfs_root *kf_root = kfc->root; struct inode *inode; struct dentry *root; @@ -255,9 +256,9 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k sb->s_shrink.seeks = 0; /* get root inode, initialize and unlock it */ - down_read(&kernfs_rwsem); + down_read(&kf_root->kernfs_rwsem); inode = kernfs_get_inode(sb, info->root->kn); - up_read(&kernfs_rwsem); + up_read(&kf_root->kernfs_rwsem); if (!inode) { pr_debug("kernfs: could not get root inode\n"); return -ENOMEM; @@ -334,6 +335,7 @@ int kernfs_get_tree(struct fs_context *fc) if (!sb->s_root) { struct kernfs_super_info *info = kernfs_info(sb); + struct kernfs_root *root = kfc->root; kfc->new_sb_created = true; @@ -344,9 +346,9 @@ int kernfs_get_tree(struct fs_context *fc) } sb->s_flags |= SB_ACTIVE; - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); list_add(&info->node, &info->root->supers); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); } fc->root = dget(sb->s_root); @@ -371,10 +373,11 @@ void kernfs_free_fs_context(struct fs_context *fc) void kernfs_kill_sb(struct super_block *sb) { struct kernfs_super_info *info = kernfs_info(sb); + struct kernfs_root *root = info->root; - down_write(&kernfs_rwsem); + down_write(&root->kernfs_rwsem); list_del(&info->node); - up_write(&kernfs_rwsem); + up_write(&root->kernfs_rwsem); /* * Remove the superblock from fs_supers/s_instances diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c index 19a6c71c6ff5..0ab13824822f 100644 --- a/fs/kernfs/symlink.c +++ b/fs/kernfs/symlink.c @@ -113,11 +113,12 @@ static int kernfs_getlink(struct inode *inode, char *path) struct kernfs_node *kn = inode->i_private; struct kernfs_node *parent = kn->parent; struct kernfs_node *target = kn->symlink.target_kn; + struct kernfs_root *root = kernfs_root(parent); int error; - down_read(&kernfs_rwsem); + down_read(&root->kernfs_rwsem); error = kernfs_get_target_path(parent, target, path); - up_read(&kernfs_rwsem); + up_read(&root->kernfs_rwsem); return error; } diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 3ccce6f24548..9f650986a81b 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -16,6 +16,7 @@ #include #include #include +#include struct file; struct dentry; @@ -197,6 +198,7 @@ struct kernfs_root { struct list_head supers; wait_queue_head_t deactivate_waitq; + struct rw_semaphore kernfs_rwsem; }; struct kernfs_open_file { -- cgit v1.2.3 From 1b6ed6bf32fb22ef8e3572fc9c0f6454adf1ca40 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 24 Nov 2021 09:17:37 +0200 Subject: regulator: Drop unnecessary struct member The irq_flags from the regulator IRQ helper description struct was never used. The IRQ flags are passed as parameters to helper registration instead. Remove the unnecessary struct field. Fixes: 7111c6d1b31b ("regulator: IRQ based event/error notification helpers") Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/5f6371e178453fa2b165da50452f7db4e986debb.1637736436.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 1cb8071fee34..53b25cd7ead0 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -554,7 +554,6 @@ struct regulator_irq_data { */ struct regulator_irq_desc { const char *name; - int irq_flags; int fatal_cnt; int reread_ms; int irq_off_ms; -- cgit v1.2.3 From 6fadec4c5561e2fbe1dfa8a7da9bc58d094a8f04 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 24 Nov 2021 09:16:45 +0200 Subject: regulator: Add regulator_err2notif() helper Help drivers avoid storing both supported notification and supported error flags by supporting conversion from regulator error to notification. This may help saving some bytes. Add helper for finding the regulator notification corresponding to a regulator error. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/eb1755ac0569ff07ffa466cf8912c6fd50e7c7c6.1637736436.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 53b25cd7ead0..6c6ec9658c30 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -645,6 +645,40 @@ struct regulator_dev { spinlock_t err_lock; }; +/* + * Convert error flags to corresponding notifications. + * + * Can be used by drivers which use the notification helpers to + * find out correct notification flags based on the error flags. Drivers + * can avoid storing both supported notification and error flags which + * may save few bytes. + */ +static inline int regulator_err2notif(int err) +{ + switch (err) { + case REGULATOR_ERROR_UNDER_VOLTAGE: + return REGULATOR_EVENT_UNDER_VOLTAGE; + case REGULATOR_ERROR_OVER_CURRENT: + return REGULATOR_EVENT_OVER_CURRENT; + case REGULATOR_ERROR_REGULATION_OUT: + return REGULATOR_EVENT_REGULATION_OUT; + case REGULATOR_ERROR_FAIL: + return REGULATOR_EVENT_FAIL; + case REGULATOR_ERROR_OVER_TEMP: + return REGULATOR_EVENT_OVER_TEMP; + case REGULATOR_ERROR_UNDER_VOLTAGE_WARN: + return REGULATOR_EVENT_UNDER_VOLTAGE_WARN; + case REGULATOR_ERROR_OVER_CURRENT_WARN: + return REGULATOR_EVENT_OVER_CURRENT_WARN; + case REGULATOR_ERROR_OVER_VOLTAGE_WARN: + return REGULATOR_EVENT_OVER_VOLTAGE_WARN; + case REGULATOR_ERROR_OVER_TEMP_WARN: + return REGULATOR_EVENT_OVER_TEMP_WARN; + } + return 0; +} + + struct regulator_dev * regulator_register(const struct regulator_desc *regulator_desc, const struct regulator_config *config); -- cgit v1.2.3 From a764ff77d697a4a13e69b3379cc613f7409c6b9a Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 24 Nov 2021 09:17:13 +0200 Subject: regulator: irq_helper: Provide helper for trivial IRQ notifications Provide a generic map_event helper for regulators which have a notification IRQ with single, well defined purpose. Eg, IRQ always indicates exactly one event for exactly one regulator device. For such IRQs the mapping is trivial. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/603b7ed1938013a00371c1e7ccc63dfb16982b87.1637736436.git.matti.vaittinen@fi.rohmeurope.com Signed-off-by: Mark Brown --- drivers/regulator/irq_helpers.c | 41 +++++++++++++++++++++++++++++++++++++++- include/linux/regulator/driver.h | 2 ++ 2 files changed, 42 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/regulator/irq_helpers.c b/drivers/regulator/irq_helpers.c index 522764435575..fe7ae0f3f46a 100644 --- a/drivers/regulator/irq_helpers.c +++ b/drivers/regulator/irq_helpers.c @@ -320,7 +320,9 @@ static void init_rdev_errors(struct regulator_irq *h) * IRQF_ONESHOT when requesting the (threaded) irq. * @common_errs: Errors which can be flagged by this IRQ for all rdevs. * When IRQ is re-enabled these errors will be cleared - * from all associated regulators + * from all associated regulators. Use this instead of the + * per_rdev_errs if you use + * regulator_irq_map_event_simple() for event mapping. * @per_rdev_errs: Optional error flag array describing errors specific * for only some of the regulators. These errors will be * or'ed with common errors. If this is given the array @@ -395,3 +397,40 @@ void regulator_irq_helper_cancel(void **handle) } } EXPORT_SYMBOL_GPL(regulator_irq_helper_cancel); + +/** + * regulator_irq_map_event_simple - regulator IRQ notification for trivial IRQs + * + * @irq: Number of IRQ that occurred + * @rid: Information about the event IRQ indicates + * @dev_mask: mask indicating the regulator originating the IRQ + * + * Regulators whose IRQ has single, well defined purpose (always indicate + * exactly one event, and are relevant to exactly one regulator device) can + * use this function as their map_event callbac for their regulator IRQ + * notification helperk. Exactly one rdev and exactly one error (in + * "common_errs"-field) can be given at IRQ helper registration for + * regulator_irq_map_event_simple() to be viable. + */ +int regulator_irq_map_event_simple(int irq, struct regulator_irq_data *rid, + unsigned long *dev_mask) +{ + int err = rid->states[0].possible_errs; + + *dev_mask = 1; + /* + * This helper should only be used in a situation where the IRQ + * can indicate only one type of problem for one specific rdev. + * Something fishy is going on if we are having multiple rdevs or ERROR + * flags here. + */ + if (WARN_ON(rid->num_states != 1 || hweight32(err) != 1)) + return 0; + + rid->states[0].errors = err; + rid->states[0].notifs = regulator_err2notif(err); + + return 0; +} +EXPORT_SYMBOL_GPL(regulator_irq_map_event_simple); + diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 6c6ec9658c30..4078c7776453 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -700,6 +700,8 @@ void *regulator_irq_helper(struct device *dev, int irq_flags, int common_errs, int *per_rdev_errs, struct regulator_dev **rdev, int rdev_amount); void regulator_irq_helper_cancel(void **handle); +int regulator_irq_map_event_simple(int irq, struct regulator_irq_data *rid, + unsigned long *dev_mask); void *rdev_get_drvdata(struct regulator_dev *rdev); struct device *rdev_get_dev(struct regulator_dev *rdev); -- cgit v1.2.3 From 432dd1fc134ef902b049b26839edfd3fdc1f8dc0 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Wed, 24 Nov 2021 07:57:49 +0200 Subject: regulator: rohm-generic: remove unused dummies Function rohm_regulator_set_voltage_sel_restricted() and rohm_regulator_set_dvs_levels() had inlined dummy implementations for cases when the real implementation was not configured in. All of the drivers who issue the call to these functions do SELECT the real implementation from the Kconfig. There should be no cases where the real implementation was not selected by the drivers using these functions - such a situation is likely to be an error which deserves to be noticed at compile-time. These dummies could in theory be used for compile-testing the drivers only (without the generic rohm regulator pieces). However, for such compile testing we should manually drop the selection from KConfig - and I guess that if it does not work out-of-the-box, then it is not going to happen. Especially when there should be no reason to omit compile-testing the generic rohm_regulator part. Crash test dummies. Signed-off-by: Matti Vaittinen Link: https://lore.kernel.org/r/YZ3UXXrk/Efe7Scj@fedora Signed-off-by: Mark Brown --- include/linux/mfd/rohm-generic.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 080d60adcd5f..5ed97a1d0908 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -82,20 +82,6 @@ int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, unsigned int sel); -#else -static inline int rohm_regulator_set_dvs_levels(const struct rohm_dvs_config *dvs, - struct device_node *np, - const struct regulator_desc *desc, - struct regmap *regmap) -{ - return 0; -} - -static inline int rohm_regulator_set_voltage_sel_restricted(struct regulator_dev *rdev, - unsigned int sel) -{ - return 0; -} #endif #endif -- cgit v1.2.3 From 2338e7bcef445059a99848a3eddde0b556277663 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Mon, 15 Nov 2021 15:10:01 +0300 Subject: device property: Remove device_add_properties() API There are no more users for it. Reviewed-by: Andy Shevchenko Signed-off-by: Heikki Krogerus Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 48 ------------------------------------------------ include/linux/property.h | 4 ---- 2 files changed, 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index f1f35b48ab8b..d0960a9e8974 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -507,54 +507,6 @@ struct fwnode_handle *fwnode_find_reference(const struct fwnode_handle *fwnode, } EXPORT_SYMBOL_GPL(fwnode_find_reference); -/** - * device_remove_properties - Remove properties from a device object. - * @dev: Device whose properties to remove. - * - * The function removes properties previously associated to the device - * firmware node with device_add_properties(). Memory allocated to the - * properties will also be released. - */ -void device_remove_properties(struct device *dev) -{ - struct fwnode_handle *fwnode = dev_fwnode(dev); - - if (!fwnode) - return; - - if (is_software_node(fwnode->secondary)) { - fwnode_remove_software_node(fwnode->secondary); - set_secondary_fwnode(dev, NULL); - } -} -EXPORT_SYMBOL_GPL(device_remove_properties); - -/** - * device_add_properties - Add a collection of properties to a device object. - * @dev: Device to add properties to. - * @properties: Collection of properties to add. - * - * Associate a collection of device properties represented by @properties with - * @dev. The function takes a copy of @properties. - * - * WARNING: The callers should not use this function if it is known that there - * is no real firmware node associated with @dev! In that case the callers - * should create a software node and assign it to @dev directly. - */ -int device_add_properties(struct device *dev, - const struct property_entry *properties) -{ - struct fwnode_handle *fwnode; - - fwnode = fwnode_create_software_node(properties, NULL); - if (IS_ERR(fwnode)) - return PTR_ERR(fwnode); - - set_secondary_fwnode(dev, fwnode); - return 0; -} -EXPORT_SYMBOL_GPL(device_add_properties); - /** * fwnode_get_name - Return the name of a node * @fwnode: The firmware node diff --git a/include/linux/property.h b/include/linux/property.h index 88fa726a76df..16f736c698a2 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -378,10 +378,6 @@ property_entries_dup(const struct property_entry *properties); void property_entries_free(const struct property_entry *properties); -int device_add_properties(struct device *dev, - const struct property_entry *properties); -void device_remove_properties(struct device *dev); - bool device_dma_supported(struct device *dev); enum dev_dma_attr device_get_dma_attr(struct device *dev); -- cgit v1.2.3 From f124034faa911ed534bf8c4881ad98dbbde2a966 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 24 Nov 2021 18:44:17 -0500 Subject: Revert "virtio_ring: validate used buffer length" This reverts commit 939779f5152d161b34f612af29e7dc1ac4472fcf. Attempts to validate length in the core did not work out: there turn out to exist multiple broken devices, and in particular legacy devices are known to be broken in this respect. We have ideas for handling this better in the next version but for now let's revert to a known good state to make sure drivers work for people. Signed-off-by: Michael S. Tsirkin --- drivers/virtio/virtio_ring.c | 60 -------------------------------------------- include/linux/virtio.h | 2 -- 2 files changed, 62 deletions(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 00f64f2f8b72..6d2614e34470 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -14,9 +14,6 @@ #include #include -static bool force_used_validation = false; -module_param(force_used_validation, bool, 0444); - #ifdef DEBUG /* For development, we want to crash whenever the ring is screwed. */ #define BAD_RING(_vq, fmt, args...) \ @@ -185,9 +182,6 @@ struct vring_virtqueue { } packed; }; - /* Per-descriptor in buffer length */ - u32 *buflen; - /* How to notify other side. FIXME: commonalize hcalls! */ bool (*notify)(struct virtqueue *vq); @@ -496,7 +490,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, unsigned int i, n, avail, descs_used, prev, err_idx; int head; bool indirect; - u32 buflen = 0; START_USE(vq); @@ -578,7 +571,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, VRING_DESC_F_NEXT | VRING_DESC_F_WRITE, indirect); - buflen += sg->length; } } /* Last one doesn't continue. */ @@ -618,10 +610,6 @@ static inline int virtqueue_add_split(struct virtqueue *_vq, else vq->split.desc_state[head].indir_desc = ctx; - /* Store in buffer length if necessary */ - if (vq->buflen) - vq->buflen[head] = buflen; - /* Put entry in available array (but don't update avail->idx until they * do sync). */ avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1); @@ -796,11 +784,6 @@ static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq, BAD_RING(vq, "id %u is not a head!\n", i); return NULL; } - if (vq->buflen && unlikely(*len > vq->buflen[i])) { - BAD_RING(vq, "used len %d is larger than in buflen %u\n", - *len, vq->buflen[i]); - return NULL; - } /* detach_buf_split clears data, so grab it now. */ ret = vq->split.desc_state[i].data; @@ -1079,7 +1062,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, unsigned int i, n, err_idx; u16 head, id; dma_addr_t addr; - u32 buflen = 0; head = vq->packed.next_avail_idx; desc = alloc_indirect_packed(total_sg, gfp); @@ -1109,8 +1091,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, desc[i].addr = cpu_to_le64(addr); desc[i].len = cpu_to_le32(sg->length); i++; - if (n >= out_sgs) - buflen += sg->length; } } @@ -1164,10 +1144,6 @@ static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq, vq->packed.desc_state[id].indir_desc = desc; vq->packed.desc_state[id].last = id; - /* Store in buffer length if necessary */ - if (vq->buflen) - vq->buflen[id] = buflen; - vq->num_added += 1; pr_debug("Added buffer head %i to %p\n", head, vq); @@ -1203,7 +1179,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, __le16 head_flags, flags; u16 head, id, prev, curr, avail_used_flags; int err; - u32 buflen = 0; START_USE(vq); @@ -1283,8 +1258,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, 1 << VRING_PACKED_DESC_F_AVAIL | 1 << VRING_PACKED_DESC_F_USED; } - if (n >= out_sgs) - buflen += sg->length; } } @@ -1304,10 +1277,6 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq, vq->packed.desc_state[id].indir_desc = ctx; vq->packed.desc_state[id].last = prev; - /* Store in buffer length if necessary */ - if (vq->buflen) - vq->buflen[id] = buflen; - /* * A driver MUST NOT make the first descriptor in the list * available before all subsequent descriptors comprising @@ -1494,11 +1463,6 @@ static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq, BAD_RING(vq, "id %u is not a head!\n", id); return NULL; } - if (vq->buflen && unlikely(*len > vq->buflen[id])) { - BAD_RING(vq, "used len %d is larger than in buflen %u\n", - *len, vq->buflen[id]); - return NULL; - } /* detach_buf_packed clears data, so grab it now. */ ret = vq->packed.desc_state[id].data; @@ -1704,7 +1668,6 @@ static struct virtqueue *vring_create_virtqueue_packed( struct vring_virtqueue *vq; struct vring_packed_desc *ring; struct vring_packed_desc_event *driver, *device; - struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver); dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr; size_t ring_size_in_bytes, event_size_in_bytes; @@ -1794,15 +1757,6 @@ static struct virtqueue *vring_create_virtqueue_packed( if (!vq->packed.desc_extra) goto err_desc_extra; - if (!drv->suppress_used_validation || force_used_validation) { - vq->buflen = kmalloc_array(num, sizeof(*vq->buflen), - GFP_KERNEL); - if (!vq->buflen) - goto err_buflen; - } else { - vq->buflen = NULL; - } - /* No callback? Tell other side not to bother us. */ if (!callback) { vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE; @@ -1815,8 +1769,6 @@ static struct virtqueue *vring_create_virtqueue_packed( spin_unlock(&vdev->vqs_list_lock); return &vq->vq; -err_buflen: - kfree(vq->packed.desc_extra); err_desc_extra: kfree(vq->packed.desc_state); err_desc_state: @@ -2224,7 +2176,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, void (*callback)(struct virtqueue *), const char *name) { - struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver); struct vring_virtqueue *vq; if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED)) @@ -2284,15 +2235,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, if (!vq->split.desc_extra) goto err_extra; - if (!drv->suppress_used_validation || force_used_validation) { - vq->buflen = kmalloc_array(vring.num, sizeof(*vq->buflen), - GFP_KERNEL); - if (!vq->buflen) - goto err_buflen; - } else { - vq->buflen = NULL; - } - /* Put everything in free lists. */ vq->free_head = 0; memset(vq->split.desc_state, 0, vring.num * @@ -2303,8 +2245,6 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, spin_unlock(&vdev->vqs_list_lock); return &vq->vq; -err_buflen: - kfree(vq->split.desc_extra); err_extra: kfree(vq->split.desc_state); err_state: diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 44d0e09da2d9..41edbc01ffa4 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -152,7 +152,6 @@ size_t virtio_max_dma_size(struct virtio_device *vdev); * @feature_table_size: number of entries in the feature table array. * @feature_table_legacy: same as feature_table but when working in legacy mode. * @feature_table_size_legacy: number of entries in feature table legacy array. - * @suppress_used_validation: set to not have core validate used length * @probe: the function to call when a device is found. Returns 0 or -errno. * @scan: optional function to call after successful probe; intended * for virtio-scsi to invoke a scan. @@ -169,7 +168,6 @@ struct virtio_driver { unsigned int feature_table_size; const unsigned int *feature_table_legacy; unsigned int feature_table_size_legacy; - bool suppress_used_validation; int (*validate)(struct virtio_device *dev); int (*probe)(struct virtio_device *dev); void (*scan)(struct virtio_device *dev); -- cgit v1.2.3 From 635e4172bd0a43af943fb164799965fc9a9a705d Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Tue, 2 Nov 2021 07:38:10 +0100 Subject: arm: remove zte zx platform left-over Commit 89d4f98ae90d ("ARM: remove zte zx platform") missed to remove some definitions for this platform's debug and serial, e.g., code dependent on the config DEBUG_ZTE_ZX. Fortunately, ./scripts/checkkconfigsymbols.py detects this and warns: DEBUG_ZTE_ZX Referencing files: arch/arm/include/debug/pl01x.S Further review by Arnd Bergmann identified even more dead code in the amba serial driver. Remove all this left-over from the zte zx platform. Reviewed-by: Arnd Bergmann Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20211102063810.932-1-lukas.bulwahn@gmail.com Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/debug/pl01x.S | 7 ------- drivers/tty/serial/amba-pl011.c | 37 ------------------------------------- include/linux/amba/bus.h | 6 ------ 3 files changed, 50 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/debug/pl01x.S b/arch/arm/include/debug/pl01x.S index 0c7bfa4c10db..c7e02d0628bf 100644 --- a/arch/arm/include/debug/pl01x.S +++ b/arch/arm/include/debug/pl01x.S @@ -8,13 +8,6 @@ */ #include -#ifdef CONFIG_DEBUG_ZTE_ZX -#undef UART01x_DR -#undef UART01x_FR -#define UART01x_DR 0x04 -#define UART01x_FR 0x14 -#endif - #ifdef CONFIG_DEBUG_UART_PHYS .macro addruart, rp, rv, tmp ldr \rp, =CONFIG_DEBUG_UART_PHYS diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index d361cd84ff8c..c9534e229166 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -188,38 +188,6 @@ static struct vendor_data vendor_st = { .get_fifosize = get_fifosize_st, }; -static const u16 pl011_zte_offsets[REG_ARRAY_SIZE] = { - [REG_DR] = ZX_UART011_DR, - [REG_FR] = ZX_UART011_FR, - [REG_LCRH_RX] = ZX_UART011_LCRH, - [REG_LCRH_TX] = ZX_UART011_LCRH, - [REG_IBRD] = ZX_UART011_IBRD, - [REG_FBRD] = ZX_UART011_FBRD, - [REG_CR] = ZX_UART011_CR, - [REG_IFLS] = ZX_UART011_IFLS, - [REG_IMSC] = ZX_UART011_IMSC, - [REG_RIS] = ZX_UART011_RIS, - [REG_MIS] = ZX_UART011_MIS, - [REG_ICR] = ZX_UART011_ICR, - [REG_DMACR] = ZX_UART011_DMACR, -}; - -static unsigned int get_fifosize_zte(struct amba_device *dev) -{ - return 16; -} - -static struct vendor_data vendor_zte = { - .reg_offset = pl011_zte_offsets, - .access_32b = true, - .ifls = UART011_IFLS_RX4_8|UART011_IFLS_TX4_8, - .fr_busy = ZX_UART01x_FR_BUSY, - .fr_dsr = ZX_UART01x_FR_DSR, - .fr_cts = ZX_UART01x_FR_CTS, - .fr_ri = ZX_UART011_FR_RI, - .get_fifosize = get_fifosize_zte, -}; - /* Deals with DMA transactions */ struct pl011_sgbuf { @@ -2974,11 +2942,6 @@ static const struct amba_id pl011_ids[] = { .mask = 0x00ffffff, .data = &vendor_st, }, - { - .id = AMBA_LINUX_ID(0x00, 0x1, 0xffe), - .mask = 0x00ffffff, - .data = &vendor_zte, - }, { 0, 0 }, }; diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index edfcf7a14dcd..6c7f47846971 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -90,14 +90,8 @@ enum amba_vendor { AMBA_VENDOR_ST = 0x80, AMBA_VENDOR_QCOM = 0x51, AMBA_VENDOR_LSI = 0xb6, - AMBA_VENDOR_LINUX = 0xfe, /* This value is not official */ }; -/* This is used to generate pseudo-ID for AMBA device */ -#define AMBA_LINUX_ID(conf, rev, part) \ - (((conf) & 0xff) << 24 | ((rev) & 0xf) << 20 | \ - AMBA_VENDOR_LINUX << 12 | ((part) & 0xfff)) - extern struct bus_type amba_bustype; #define to_amba_device(d) container_of(d, struct amba_device, dev) -- cgit v1.2.3 From 4167bd25ec3bc221387ec6811c05eadfe3cf1d3e Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 18 Nov 2021 08:31:24 +0100 Subject: mxser: move ids from pci_ids.h here There is no point having MOXA PCI device IDs in include/linux/pci_ids.h. Move them to the driver and sort them all by the ID. Cc: Bjorn Helgaas Cc: linux-pci@vger.kernel.org Acked-by: Bjorn Helgaas Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211118073125.12283-19-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/tty/mxser.c | 20 +++++++++++++++++++- include/linux/pci_ids.h | 18 ------------------ 2 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c index f6842089459a..ba96ffed193a 100644 --- a/drivers/tty/mxser.c +++ b/drivers/tty/mxser.c @@ -159,14 +159,32 @@ #define MXSER_BAUD_BASE 921600 #define MXSER_CUSTOM_DIVISOR (MXSER_BAUD_BASE * 16) +#define PCI_DEVICE_ID_MOXA_RC7000 0x0001 +#define PCI_DEVICE_ID_MOXA_CP102 0x1020 +#define PCI_DEVICE_ID_MOXA_CP102UL 0x1021 +#define PCI_DEVICE_ID_MOXA_CP102U 0x1022 +#define PCI_DEVICE_ID_MOXA_CP102UF 0x1023 +#define PCI_DEVICE_ID_MOXA_C104 0x1040 +#define PCI_DEVICE_ID_MOXA_CP104U 0x1041 +#define PCI_DEVICE_ID_MOXA_CP104JU 0x1042 +#define PCI_DEVICE_ID_MOXA_CP104EL 0x1043 #define PCI_DEVICE_ID_MOXA_POS104UL 0x1044 #define PCI_DEVICE_ID_MOXA_CB108 0x1080 -#define PCI_DEVICE_ID_MOXA_CP102UF 0x1023 #define PCI_DEVICE_ID_MOXA_CP112UL 0x1120 +#define PCI_DEVICE_ID_MOXA_CT114 0x1140 +#define PCI_DEVICE_ID_MOXA_CP114 0x1141 #define PCI_DEVICE_ID_MOXA_CB114 0x1142 #define PCI_DEVICE_ID_MOXA_CP114UL 0x1143 +#define PCI_DEVICE_ID_MOXA_CP118U 0x1180 +#define PCI_DEVICE_ID_MOXA_CP118EL 0x1181 +#define PCI_DEVICE_ID_MOXA_CP132 0x1320 +#define PCI_DEVICE_ID_MOXA_CP132U 0x1321 +#define PCI_DEVICE_ID_MOXA_CP134U 0x1340 #define PCI_DEVICE_ID_MOXA_CB134I 0x1341 #define PCI_DEVICE_ID_MOXA_CP138U 0x1380 +#define PCI_DEVICE_ID_MOXA_C168 0x1680 +#define PCI_DEVICE_ID_MOXA_CP168U 0x1681 +#define PCI_DEVICE_ID_MOXA_CP168EL 0x1682 #define MXSER_NPORTS(ddata) ((ddata) & 0xffU) #define MXSER_HIGHBAUD 0x0100 diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 011f2f1ea5bb..c389a9c0f290 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1964,24 +1964,6 @@ #define PCI_DEVICE_ID_APPLICOM_PCI2000PFB 0x0003 #define PCI_VENDOR_ID_MOXA 0x1393 -#define PCI_DEVICE_ID_MOXA_RC7000 0x0001 -#define PCI_DEVICE_ID_MOXA_CP102 0x1020 -#define PCI_DEVICE_ID_MOXA_CP102UL 0x1021 -#define PCI_DEVICE_ID_MOXA_CP102U 0x1022 -#define PCI_DEVICE_ID_MOXA_C104 0x1040 -#define PCI_DEVICE_ID_MOXA_CP104U 0x1041 -#define PCI_DEVICE_ID_MOXA_CP104JU 0x1042 -#define PCI_DEVICE_ID_MOXA_CP104EL 0x1043 -#define PCI_DEVICE_ID_MOXA_CT114 0x1140 -#define PCI_DEVICE_ID_MOXA_CP114 0x1141 -#define PCI_DEVICE_ID_MOXA_CP118U 0x1180 -#define PCI_DEVICE_ID_MOXA_CP118EL 0x1181 -#define PCI_DEVICE_ID_MOXA_CP132 0x1320 -#define PCI_DEVICE_ID_MOXA_CP132U 0x1321 -#define PCI_DEVICE_ID_MOXA_CP134U 0x1340 -#define PCI_DEVICE_ID_MOXA_C168 0x1680 -#define PCI_DEVICE_ID_MOXA_CP168U 0x1681 -#define PCI_DEVICE_ID_MOXA_CP168EL 0x1682 #define PCI_DEVICE_ID_MOXA_CP204J 0x2040 #define PCI_DEVICE_ID_MOXA_C218 0x2180 #define PCI_DEVICE_ID_MOXA_C320 0x3200 -- cgit v1.2.3 From 5db96ef23bda6c2a61a51693c85b78b52d03f654 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 22 Nov 2021 12:16:48 +0100 Subject: tty: drop tty_schedule_flip() Since commit a9c3f68f3cd8d (tty: Fix low_latency BUG) in 2014, tty_flip_buffer_push() is only a wrapper to tty_schedule_flip(). All users were converted in the previous patches, so remove tty_schedule_flip() completely while inlining its body into tty_flip_buffer_push(). One less exported function. Reviewed-by: Johan Hovold Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211122111648.30379-4-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_buffer.c | 30 ++++++++---------------------- include/linux/tty_flip.h | 1 - 2 files changed, 8 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c index 6c7e65b1d9a1..5b6875057ce2 100644 --- a/drivers/tty/tty_buffer.c +++ b/drivers/tty/tty_buffer.c @@ -401,27 +401,6 @@ int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag) } EXPORT_SYMBOL(__tty_insert_flip_char); -/** - * tty_schedule_flip - push characters to ldisc - * @port: tty port to push from - * - * Takes any pending buffers and transfers their ownership to the - * ldisc side of the queue. It then schedules those characters for - * processing by the line discipline. - */ - -void tty_schedule_flip(struct tty_port *port) -{ - struct tty_bufhead *buf = &port->buf; - - /* paired w/ acquire in flush_to_ldisc(); ensures - * flush_to_ldisc() sees buffer data. - */ - smp_store_release(&buf->tail->commit, buf->tail->used); - queue_work(system_unbound_wq, &buf->work); -} -EXPORT_SYMBOL(tty_schedule_flip); - /** * tty_prepare_flip_string - make room for characters * @port: tty port @@ -566,7 +545,14 @@ static void flush_to_ldisc(struct work_struct *work) void tty_flip_buffer_push(struct tty_port *port) { - tty_schedule_flip(port); + struct tty_bufhead *buf = &port->buf; + + /* + * Paired w/ acquire in flush_to_ldisc(); ensures flush_to_ldisc() sees + * buffer data. + */ + smp_store_release(&buf->tail->commit, buf->tail->used); + queue_work(system_unbound_wq, &buf->work); } EXPORT_SYMBOL(tty_flip_buffer_push); diff --git a/include/linux/tty_flip.h b/include/linux/tty_flip.h index 9916acb5de49..483d41cbcbb7 100644 --- a/include/linux/tty_flip.h +++ b/include/linux/tty_flip.h @@ -17,7 +17,6 @@ int tty_insert_flip_string_fixed_flag(struct tty_port *port, int tty_prepare_flip_string(struct tty_port *port, unsigned char **chars, size_t size); void tty_flip_buffer_push(struct tty_port *port); -void tty_schedule_flip(struct tty_port *port); int __tty_insert_flip_char(struct tty_port *port, unsigned char ch, char flag); static inline int tty_insert_flip_char(struct tty_port *port, -- cgit v1.2.3 From d78328bcc4d0e677f2ff83f4ae1f43c933fbd143 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Mon, 22 Nov 2021 10:45:29 +0100 Subject: tty: remove file from tty_ldisc_ops::ioctl and compat_ioctl After the previous patches, noone needs 'file' parameter in neither ioctl hook from tty_ldisc_ops. So remove 'file' from both of them. Cc: Marcel Holtmann Cc: Johan Hedberg Cc: Luiz Augusto von Dentz Cc: Wolfgang Grandegger Cc: Marc Kleine-Budde Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Andreas Koensgen Cc: Paul Mackerras Acked-by: Krzysztof Kozlowski [NFC] Acked-by: Dmitry Torokhov Acked-by: Marc Kleine-Budde Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211122094529.24171-1-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- drivers/bluetooth/hci_ldisc.c | 5 ++--- drivers/input/serio/serport.c | 5 ++--- drivers/net/can/slcan.c | 4 ++-- drivers/net/hamradio/6pack.c | 4 ++-- drivers/net/hamradio/mkiss.c | 4 ++-- drivers/net/ppp/ppp_async.c | 3 +-- drivers/net/ppp/ppp_synctty.c | 3 +-- drivers/net/slip/slip.c | 4 ++-- drivers/tty/n_gsm.c | 4 ++-- drivers/tty/n_hdlc.c | 5 ++--- drivers/tty/n_tty.c | 4 ++-- drivers/tty/tty_io.c | 8 ++++---- include/linux/tty_ldisc.h | 15 +++++++-------- net/nfc/nci/uart.c | 5 ++--- 14 files changed, 33 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index ecdf8e034351..f537673ede17 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -739,14 +739,13 @@ static int hci_uart_set_flags(struct hci_uart *hu, unsigned long flags) * Arguments: * * tty pointer to tty instance data - * file pointer to open file object for device * cmd IOCTL command code * arg argument for IOCTL call (cmd dependent) * * Return Value: Command dependent */ -static int hci_uart_tty_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int hci_uart_tty_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct hci_uart *hu = tty->disc_data; int err = 0; diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c index 17eb8f2aa48d..669a728095b8 100644 --- a/drivers/input/serio/serport.c +++ b/drivers/input/serio/serport.c @@ -207,8 +207,8 @@ static void serport_set_type(struct tty_struct *tty, unsigned long type) * serport_ldisc_ioctl() allows to set the port protocol, and device ID */ -static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int serport_ldisc_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { if (cmd == SPIOCSTYPE) { unsigned long type; @@ -226,7 +226,6 @@ static int serport_ldisc_ioctl(struct tty_struct *tty, struct file *file, #ifdef CONFIG_COMPAT #define COMPAT_SPIOCSTYPE _IOW('q', 0x01, compat_ulong_t) static int serport_ldisc_compat_ioctl(struct tty_struct *tty, - struct file *file, unsigned int cmd, unsigned long arg) { if (cmd == COMPAT_SPIOCSTYPE) { diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 9a4ebda30510..113763790ac9 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -670,8 +670,8 @@ static void slcan_hangup(struct tty_struct *tty) } /* Perform I/O control on an active SLCAN channel. */ -static int slcan_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int slcan_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct slcan *sl = (struct slcan *) tty->disc_data; unsigned int tmp; diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 8a19a06b505d..b1fc153125d9 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -681,8 +681,8 @@ static void sixpack_close(struct tty_struct *tty) } /* Perform I/O control on an active 6pack channel. */ -static int sixpack_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int sixpack_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct sixpack *sp = sp_get(tty); struct net_device *dev; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index e2b332b54f06..894b5f92b85f 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -804,8 +804,8 @@ static void mkiss_close(struct tty_struct *tty) } /* Perform I/O control on an active ax25 channel. */ -static int mkiss_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int mkiss_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct mkiss *ax = mkiss_get(tty); struct net_device *dev; diff --git a/drivers/net/ppp/ppp_async.c b/drivers/net/ppp/ppp_async.c index f4429b93a9c8..15a179631903 100644 --- a/drivers/net/ppp/ppp_async.c +++ b/drivers/net/ppp/ppp_async.c @@ -281,8 +281,7 @@ ppp_asynctty_write(struct tty_struct *tty, struct file *file, */ static int -ppp_asynctty_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +ppp_asynctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct asyncppp *ap = ap_get(tty); int err, val; diff --git a/drivers/net/ppp/ppp_synctty.c b/drivers/net/ppp/ppp_synctty.c index b3a71b409a80..18283b7b94bc 100644 --- a/drivers/net/ppp/ppp_synctty.c +++ b/drivers/net/ppp/ppp_synctty.c @@ -274,8 +274,7 @@ ppp_sync_write(struct tty_struct *tty, struct file *file, } static int -ppp_synctty_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +ppp_synctty_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct syncppp *ap = sp_get(tty); int __user *p = (int __user *)arg; diff --git a/drivers/net/slip/slip.c b/drivers/net/slip/slip.c index 9f3b4c1aa5ce..98f586f910fb 100644 --- a/drivers/net/slip/slip.c +++ b/drivers/net/slip/slip.c @@ -1072,8 +1072,8 @@ static void slip_unesc6(struct slip *sl, unsigned char s) #endif /* CONFIG_SLIP_MODE_SLIP6 */ /* Perform I/O control on an active SLIP channel. */ -static int slip_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int slip_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct slip *sl = tty->disc_data; unsigned int tmp; diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c index 68e6df27d2e3..ba27b274c967 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -2687,8 +2687,8 @@ static __poll_t gsmld_poll(struct tty_struct *tty, struct file *file, return mask; } -static int gsmld_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int gsmld_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct gsm_config c; struct gsm_mux *gsm = tty->disc_data; diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c index 7e0884ecc74f..a66915032e7e 100644 --- a/drivers/tty/n_hdlc.c +++ b/drivers/tty/n_hdlc.c @@ -572,14 +572,13 @@ static ssize_t n_hdlc_tty_write(struct tty_struct *tty, struct file *file, /** * n_hdlc_tty_ioctl - process IOCTL system call for the tty device. * @tty: pointer to tty instance data - * @file: pointer to open file object for device * @cmd: IOCTL command code * @arg: argument for IOCTL call (cmd dependent) * * Returns command dependent result. */ -static int n_hdlc_tty_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int n_hdlc_tty_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct n_hdlc *n_hdlc = tty->disc_data; int error = 0; diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c index 5be6d02dc690..5b0f50373fc6 100644 --- a/drivers/tty/n_tty.c +++ b/drivers/tty/n_tty.c @@ -2400,8 +2400,8 @@ static unsigned long inq_canon(struct n_tty_data *ldata) return nr; } -static int n_tty_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int n_tty_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct n_tty_data *ldata = tty->disc_data; int retval; diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 99cad1560876..3c2349b2089c 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2811,7 +2811,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return hung_up_tty_ioctl(file, cmd, arg); retval = -EINVAL; if (ld->ops->ioctl) { - retval = ld->ops->ioctl(tty, file, cmd, arg); + retval = ld->ops->ioctl(tty, cmd, arg); if (retval == -ENOIOCTLCMD) retval = -ENOTTY; } @@ -2990,10 +2990,10 @@ static long tty_compat_ioctl(struct file *file, unsigned int cmd, if (!ld) return hung_up_tty_compat_ioctl(file, cmd, arg); if (ld->ops->compat_ioctl) - retval = ld->ops->compat_ioctl(tty, file, cmd, arg); + retval = ld->ops->compat_ioctl(tty, cmd, arg); if (retval == -ENOIOCTLCMD && ld->ops->ioctl) - retval = ld->ops->ioctl(tty, file, - (unsigned long)compat_ptr(cmd), arg); + retval = ld->ops->ioctl(tty, (unsigned long)compat_ptr(cmd), + arg); tty_ldisc_deref(ld); return retval; diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index b85d84fb5f49..25f07017bbad 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -45,8 +45,7 @@ struct tty_struct; * some processing on the characters first. If this function is * not defined, the user will receive an EIO error. * - * int (*ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); + * int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); * * This function is called when the user requests an ioctl which * is not handled by the tty layer or the low-level tty driver. @@ -56,8 +55,8 @@ struct tty_struct; * low-level driver can "grab" an ioctl request before the line * discpline has a chance to see it. * - * int (*compat_ioctl)(struct tty_struct * tty, struct file * file, - * unsigned int cmd, unsigned long arg); + * int (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg); * * Process ioctl calls from 32-bit process on 64-bit system * @@ -192,10 +191,10 @@ struct tty_ldisc_ops { void **cookie, unsigned long offset); ssize_t (*write)(struct tty_struct *tty, struct file *file, const unsigned char *buf, size_t nr); - int (*ioctl)(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); - int (*compat_ioctl)(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg); + int (*ioctl)(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); + int (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, + unsigned long arg); void (*set_termios)(struct tty_struct *tty, struct ktermios *old); __poll_t (*poll)(struct tty_struct *, struct file *, struct poll_table_struct *); diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index c027c76d493c..cc8fa9e36159 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -317,14 +317,13 @@ static void nci_uart_tty_receive(struct tty_struct *tty, const u8 *data, * Arguments: * * tty pointer to tty instance data - * file pointer to open file object for device * cmd IOCTL command code * arg argument for IOCTL call (cmd dependent) * * Return Value: Command dependent */ -static int nci_uart_tty_ioctl(struct tty_struct *tty, struct file *file, - unsigned int cmd, unsigned long arg) +static int nci_uart_tty_ioctl(struct tty_struct *tty, unsigned int cmd, + unsigned long arg) { struct nci_uart *nu = (void *)tty->disc_data; int err = 0; -- cgit v1.2.3 From 29c3002644bdd653f6ec6407d25135d0a4f7cefb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 24 Nov 2021 12:24:46 -0800 Subject: net: optimize skb_postpull_rcsum() Remove one pair of add/adc instructions and their dependency against carry flag. We can leverage third argument to csum_partial(): X = csum_block_sub(X, csum_partial(start, len, 0), 0); --> X = csum_block_add(X, ~csum_partial(start, len, 0), 0); --> X = ~csum_partial(start, len, ~X); Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eba256af64a5..eae4bd3237a4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3485,7 +3485,11 @@ __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - __skb_postpull_rcsum(skb, start, len, 0); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = ~csum_partial(start, len, ~skb->csum); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; } static __always_inline void -- cgit v1.2.3 From b4c80629c5c9d48880c5ad99943374f9ab72432e Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Sun, 23 May 2021 22:49:57 +0200 Subject: include/linux/byteorder/generic.h: fix index variables In cpu_to_be32_array() and be32_to_cpu_array() the length of the array is given by variable len of type size_t. An index variable of type int is used to iterate over the array. This is bound to fail for len > INT_MAX and lets GCC add instructions for sign extension. Correct the type of the index variable. Signed-off-by: Heinrich Schuchardt Link: https://lore.kernel.org/r/20210523204958.64575-1-xypron.glpk@gmx.de Signed-off-by: Greg Kroah-Hartman --- include/linux/byteorder/generic.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 4b13e0a3e15b..c9a4c96c9943 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -190,7 +190,7 @@ static inline void be64_add_cpu(__be64 *var, u64 val) static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) { - int i; + size_t i; for (i = 0; i < len; i++) dst[i] = cpu_to_be32(src[i]); @@ -198,7 +198,7 @@ static inline void cpu_to_be32_array(__be32 *dst, const u32 *src, size_t len) static inline void be32_to_cpu_array(u32 *dst, const __be32 *src, size_t len) { - int i; + size_t i; for (i = 0; i < len; i++) dst[i] = be32_to_cpu(src[i]); -- cgit v1.2.3 From 18e6c0751cf9ae0631a2623e31af2bf504f72c30 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:49 +0100 Subject: tty: finish kernel-doc of tty_struct members There are already pieces of kernel-doc documentation for struct tty_struct in tty.h. Finish the documentation for the members which were undocumented yet. It also includes tuning the already existing pieces like flow and ctrl, especially adding highlights to them. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-2-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty.h | 79 +++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 64 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty.h b/include/linux/tty.h index 5dbd7c5afac7..da49ad9be281 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -122,33 +122,84 @@ struct tty_operations; /** * struct tty_struct - state associated with a tty while open * - * @flow.lock: lock for flow members - * @flow.stopped: tty stopped/started by tty_stop/tty_start - * @flow.tco_stopped: tty stopped/started by TCOOFF/TCOON ioctls (it has - * precedense over @flow.stopped) + * @magic: magic value set early in @alloc_tty_struct to %TTY_MAGIC, for + * debugging purposes + * @kref: reference counting by tty_kref_get() and tty_kref_put(), reaching zero + * frees the structure + * @dev: class device or %NULL (e.g. ptys, serdev) + * @driver: &struct tty_driver operating this tty + * @ops: &struct tty_operations of @driver for this tty (open, close, etc.) + * @index: index of this tty (e.g. to construct @name like tty12) + * @ldisc_sem: protects line discipline changes (@ldisc) -- lock tty not pty + * @ldisc: the current line discipline for this tty (n_tty by default) + * @atomic_write_lock: protects against concurrent writers, i.e. locks + * @write_cnt, @write_buf and similar + * @legacy_mutex: leftover from history (BKL -> BTM -> @legacy_mutex), + * protecting several operations on this tty + * @throttle_mutex: protects against concurrent tty_throttle_safe() and + * tty_unthrottle_safe() (but not tty_unthrottle()) + * @termios_rwsem: protects @termios and @termios_locked + * @winsize_mutex: protects @winsize + * @termios: termios for the current tty, copied from/to @driver.termios + * @termios_locked: locked termios (by %TIOCGLCKTRMIOS and %TIOCSLCKTRMIOS + * ioctls) + * @name: name of the tty constructed by tty_line_name() (e.g. ttyS3) + * @flags: bitwise OR of %TTY_THROTTLED, %TTY_IO_ERROR, ... + * @count: count of open processes, reaching zero cancels all the work for + * this tty and drops a @kref too (but does not free this tty) + * @winsize: size of the terminal "window" (cf. @winsize_mutex) + * @flow: flow settings grouped together, see also @flow.unused + * @flow.lock: lock for @flow members + * @flow.stopped: tty stopped/started by stop_tty()/start_tty() + * @flow.tco_stopped: tty stopped/started by %TCOOFF/%TCOON ioctls (it has + * precedence over @flow.stopped) * @flow.unused: alignment for Alpha, so that no members other than @flow.* are * modified by the same 64b word store. The @flow's __aligned is * there for the very same reason. - * @ctrl.lock: lock for ctrl members + * @ctrl: control settings grouped together, see also @ctrl.unused + * @ctrl.lock: lock for @ctrl members * @ctrl.pgrp: process group of this tty (setpgrp(2)) * @ctrl.session: session of this tty (setsid(2)). Writes are protected by both - * @ctrl.lock and legacy mutex, readers must use at least one of + * @ctrl.lock and @legacy_mutex, readers must use at least one of * them. - * @ctrl.pktstatus: packet mode status (bitwise OR of TIOCPKT_* constants) + * @ctrl.pktstatus: packet mode status (bitwise OR of %TIOCPKT_ constants) * @ctrl.packet: packet mode enabled + * @ctrl.unused: alignment for Alpha, see @flow.unused for explanation + * @hw_stopped: not controlled by the tty layer, under @driver's control for CTS + * handling + * @receive_room: bytes permitted to feed to @ldisc without any being lost + * @flow_change: controls behavior of throttling, see tty_throttle_safe() and + * tty_unthrottle_safe() + * @link: link to another pty (master -> slave and vice versa) + * @fasync: state for %O_ASYNC (for %SIGIO); managed by fasync_helper() + * @write_wait: concurrent writers are waiting in this queue until they are + * allowed to write + * @read_wait: readers wait for data in this queue + * @hangup_work: normally a work to perform a hangup (do_tty_hangup()); while + * freeing the tty, (re)used to release_one_tty() + * @disc_data: pointer to @ldisc's private data (e.g. to &struct n_tty_data) + * @driver_data: pointer to @driver's private data (e.g. &struct uart_state) + * @files_lock: protects @tty_files list + * @tty_files: list of (re)openers of this tty (i.e. linked &struct + * tty_file_private) + * @closing: when set during close, n_tty processes only START & STOP chars + * @write_buf: temporary buffer used during tty_write() to copy user data to + * @write_cnt: count of bytes written in tty_write() to @write_buf + * @SAK_work: if the tty has a pending do_SAK, it is queued here + * @port: persistent storage for this device (i.e. &struct tty_port) * * All of the state associated with a tty while the tty is open. Persistent - * storage for tty devices is referenced here as @port in struct tty_port. + * storage for tty devices is referenced here as @port and is documented in + * &struct tty_port. */ struct tty_struct { int magic; struct kref kref; - struct device *dev; /* class device or NULL (e.g. ptys, serdev) */ + struct device *dev; struct tty_driver *driver; const struct tty_operations *ops; int index; - /* Protects ldisc changes: Lock tty not pty */ struct ld_semaphore ldisc_sem; struct tty_ldisc *ldisc; @@ -157,12 +208,11 @@ struct tty_struct { struct mutex throttle_mutex; struct rw_semaphore termios_rwsem; struct mutex winsize_mutex; - /* Termios values are protected by the termios rwsem */ struct ktermios termios, termios_locked; char name[64]; unsigned long flags; int count; - struct winsize winsize; /* winsize_mutex */ + struct winsize winsize; struct { spinlock_t lock; @@ -181,7 +231,7 @@ struct tty_struct { } __aligned(sizeof(unsigned long)) ctrl; int hw_stopped; - unsigned int receive_room; /* Bytes free for queue */ + unsigned int receive_room; int flow_change; struct tty_struct *link; @@ -191,7 +241,7 @@ struct tty_struct { struct work_struct hangup_work; void *disc_data; void *driver_data; - spinlock_t files_lock; /* protects tty_files list */ + spinlock_t files_lock; struct list_head tty_files; #define N_TTY_BUF_SIZE 4096 @@ -199,7 +249,6 @@ struct tty_struct { int closing; unsigned char *write_buf; int write_cnt; - /* If the tty has a pending do_SAK, queue it here - akpm */ struct work_struct SAK_work; struct tty_port *port; } __randomize_layout; -- cgit v1.2.3 From 61c83addb77c65f498a8db0e7113dc3acf753c45 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:50 +0100 Subject: tty: add kernel-doc for tty_port tty_port used to have only short comments along its members. Convert them into proper kernel-doc comments in front of the structure. And add some more explanation to them where needed. The whole structure purpose and handling is documented at the end too -- some pieces of preexisting text moved to this place. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-3-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_port.h | 104 +++++++++++++++++++++++++++++++---------------- 1 file changed, 70 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index 6e86e9e118b6..9091e1c8de4c 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -7,17 +7,6 @@ #include #include -/* - * Port level information. Each device keeps its own port level information - * so provide a common structure for those ports wanting to use common support - * routines. - * - * The tty port has a different lifetime to the tty so must be kept apart. - * In addition be careful as tty -> port mappings are valid for the life - * of the tty object but in many cases port -> tty mappings are valid only - * until a hangup so don't use the wrong path. - */ - struct attribute_group; struct tty_driver; struct tty_port; @@ -48,30 +37,77 @@ struct tty_port_client_operations { extern const struct tty_port_client_operations tty_port_default_client_ops; +/** + * struct tty_port -- port level information + * + * @buf: buffer for this port, locked internally + * @tty: back pointer to &struct tty_struct, valid only if the tty is open. Use + * tty_port_tty_get() to obtain it (and tty_kref_put() to release). + * @itty: internal back pointer to &struct tty_struct. Avoid this. It should be + * eliminated in the long term. + * @ops: tty port operations (like activate, shutdown), see &struct + * tty_port_operations + * @client_ops: tty port client operations (like receive_buf, write_wakeup). + * By default, tty_port_default_client_ops is used. + * @lock: lock protecting @tty + * @blocked_open: # of procs waiting for open in tty_port_block_til_ready() + * @count: usage count + * @open_wait: open waiters queue (waiting e.g. for a carrier) + * @delta_msr_wait: modem status change queue (waiting for MSR changes) + * @flags: user TTY flags (%ASYNC_) + * @iflags: internal flags (%TTY_PORT_) + * @console: when set, the port is a console + * @mutex: locking, for open, shutdown and other port operations + * @buf_mutex: @xmit_buf alloc lock + * @xmit_buf: optional xmit buffer used by some drivers + * @close_delay: delay in jiffies to wait when closing the port + * @closing_wait: delay in jiffies for output to be sent before closing + * @drain_delay: set to zero if no pure time based drain is needed else set to + * size of fifo + * @kref: references counter. Reaching zero calls @ops->destruct() if non-%NULL + * or frees the port otherwise. + * @client_data: pointer to private data, for @client_ops + * + * Each device keeps its own port level information. &struct tty_port was + * introduced as a common structure for such information. As every TTY device + * shall have a backing tty_port structure, every driver can use these members. + * + * The tty port has a different lifetime to the tty so must be kept apart. + * In addition be careful as tty -> port mappings are valid for the life + * of the tty object but in many cases port -> tty mappings are valid only + * until a hangup so don't use the wrong path. + * + * Tty port shall be initialized by tty_port_init() and shut down either by + * tty_port_destroy() (refcounting not used), or tty_port_put() (refcounting). + * + * There is a lot of helpers around &struct tty_port too. To name the most + * significant ones: tty_port_open(), tty_port_close() (or + * tty_port_close_start() and tty_port_close_end() separately if need be), and + * tty_port_hangup(). These call @ops->activate() and @ops->shutdown() as + * needed. + */ struct tty_port { - struct tty_bufhead buf; /* Locked internally */ - struct tty_struct *tty; /* Back pointer */ - struct tty_struct *itty; /* internal back ptr */ - const struct tty_port_operations *ops; /* Port operations */ - const struct tty_port_client_operations *client_ops; /* Port client operations */ - spinlock_t lock; /* Lock protecting tty field */ - int blocked_open; /* Waiting to open */ - int count; /* Usage count */ - wait_queue_head_t open_wait; /* Open waiters */ - wait_queue_head_t delta_msr_wait; /* Modem status change */ - unsigned long flags; /* User TTY flags ASYNC_ */ - unsigned long iflags; /* Internal flags TTY_PORT_ */ - unsigned char console:1; /* port is a console */ - struct mutex mutex; /* Locking */ - struct mutex buf_mutex; /* Buffer alloc lock */ - unsigned char *xmit_buf; /* Optional buffer */ - unsigned int close_delay; /* Close port delay */ - unsigned int closing_wait; /* Delay for output */ - int drain_delay; /* Set to zero if no pure time - based drain is needed else - set to size of fifo */ - struct kref kref; /* Ref counter */ - void *client_data; + struct tty_bufhead buf; + struct tty_struct *tty; + struct tty_struct *itty; + const struct tty_port_operations *ops; + const struct tty_port_client_operations *client_ops; + spinlock_t lock; + int blocked_open; + int count; + wait_queue_head_t open_wait; + wait_queue_head_t delta_msr_wait; + unsigned long flags; + unsigned long iflags; + unsigned char console:1; + struct mutex mutex; + struct mutex buf_mutex; + unsigned char *xmit_buf; + unsigned int close_delay; + unsigned int closing_wait; + int drain_delay; + struct kref kref; + void *client_data; }; /* tty_port::iflags bits -- use atomic bit ops */ -- cgit v1.2.3 From a6563830215226aae0e7e6802955c77a6a7b7547 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:51 +0100 Subject: tty: add kernel-doc for tty_driver tty_driver used to have only short comments along its members. Convert them into proper kernel-doc comments in front of the structure. And add some more explanation to them where needed. The whole structure handling is documented at the end too. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-4-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 62 +++++++++++++++++++++++++++++++++++++--------- 1 file changed, 50 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 795b94ccdeb6..3622404a678d 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -291,23 +291,61 @@ struct tty_operations { int (*proc_show)(struct seq_file *, void *); } __randomize_layout; +/** + * struct tty_driver -- driver for TTY devices + * + * @magic: set to %TTY_DRIVER_MAGIC in __tty_alloc_driver() + * @kref: reference counting. Reaching zero frees all the internals and the + * driver. + * @cdevs: allocated/registered character /dev devices + * @owner: modules owning this driver. Used drivers cannot be rmmod'ed. + * Automatically set by tty_alloc_driver(). + * @driver_name: name of the driver used in /proc/tty + * @name: used for constructing /dev node name + * @name_base: used as a number base for constructing /dev node name + * @major: major /dev device number (zero for autoassignment) + * @minor_start: the first minor /dev device number + * @num: number of devices allocated + * @type: type of tty driver (%TTY_DRIVER_TYPE_) + * @subtype: subtype of tty driver (%SYSTEM_TYPE_, %PTY_TYPE_, %SERIAL_TYPE_) + * @init_termios: termios to set to each tty initially (e.g. %tty_std_termios) + * @flags: tty driver flags (%TTY_DRIVER_) + * @proc_entry: proc fs entry, used internally + * @other: driver of the linked tty; only used for the PTY driver + * @ttys: array of active &struct tty_struct, set by tty_standard_install() + * @ports: array of &struct tty_port; can be set during initialization by + * tty_port_link_device() and similar + * @termios: storage for termios at each TTY close for the next open + * @driver_state: pointer to driver's arbitrary data + * @ops: driver hooks for TTYs. Set them using tty_set_operations(). Use &struct + * tty_port helpers in them as much as possible. + * @tty_drivers: used internally to link tty_drivers together + * + * The usual handling of &struct tty_driver is to allocate it by + * tty_alloc_driver(), set up all the necessary members, and register it by + * tty_register_driver(). At last, the driver is torn down by calling + * tty_unregister_driver() followed by tty_driver_kref_put(). + * + * The fields required to be set before calling tty_register_driver() include + * @driver_name, @name, @type, @subtype, @init_termios, and @ops. + */ struct tty_driver { - int magic; /* magic number for this structure */ - struct kref kref; /* Reference management */ + int magic; + struct kref kref; struct cdev **cdevs; struct module *owner; const char *driver_name; const char *name; - int name_base; /* offset of printed name */ - int major; /* major device number */ - int minor_start; /* start of minor device number */ - unsigned int num; /* number of devices allocated */ - short type; /* type of tty driver */ - short subtype; /* subtype of tty driver */ - struct ktermios init_termios; /* Initial termios */ - unsigned long flags; /* tty driver flags */ - struct proc_dir_entry *proc_entry; /* /proc fs entry */ - struct tty_driver *other; /* only used for the PTY driver */ + int name_base; + int major; + int minor_start; + unsigned int num; + short type; + short subtype; + struct ktermios init_termios; + unsigned long flags; + struct proc_dir_entry *proc_entry; + struct tty_driver *other; /* * Pointer to the tty data structures -- cgit v1.2.3 From 1fe183091753b1d7f11e70593700c0c0ef268db7 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:52 +0100 Subject: tty: add kernel-doc for tty_operations tty_operations structure was already documented in a standalone comment in the header beginning. Move it right before the structure and reformat it so it complies to kernel-doc. That way, we can include it in Documentation/ later in this series. Note that we named proc_show's parameters, so that we can reference them in the text. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-5-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 398 +++++++++++++++++++++++++++------------------ 1 file changed, 241 insertions(+), 157 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 3622404a678d..5611992ab26a 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -2,248 +2,332 @@ #ifndef _LINUX_TTY_DRIVER_H #define _LINUX_TTY_DRIVER_H -/* - * This structure defines the interface between the low-level tty - * driver and the tty routines. The following routines can be - * defined; unless noted otherwise, they are optional, and can be - * filled in with a null pointer. +#include +#include +#include +#include +#include +#include +#include + +struct tty_struct; +struct tty_driver; +struct serial_icounter_struct; +struct serial_struct; + +/** + * struct tty_operations -- interface between driver and tty * - * struct tty_struct * (*lookup)(struct tty_driver *self, struct file *, int idx) + * @lookup: ``struct tty_struct *()(struct tty_driver *self, struct file *, + * int idx)`` * - * Return the tty device corresponding to idx, NULL if there is not - * one currently in use and an ERR_PTR value on error. Called under - * tty_mutex (for now!) + * Return the tty device corresponding to @idx, %NULL if there is not + * one currently in use and an %ERR_PTR value on error. Called under + * %tty_mutex (for now!) * - * Optional method. Default behaviour is to use the ttys array + * Optional method. Default behaviour is to use the @self->ttys array. * - * int (*install)(struct tty_driver *self, struct tty_struct *tty) + * @install: ``int ()(struct tty_driver *self, struct tty_struct *tty)`` * - * Install a new tty into the tty driver internal tables. Used in - * conjunction with lookup and remove methods. + * Install a new @tty into the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. * - * Optional method. Default behaviour is to use the ttys array + * Optional method. Default behaviour is to use the @self->ttys array. * - * void (*remove)(struct tty_driver *self, struct tty_struct *tty) + * @remove: ``void ()(struct tty_driver *self, struct tty_struct *tty)`` * - * Remove a closed tty from the tty driver internal tables. Used in - * conjunction with lookup and remove methods. + * Remove a closed @tty from the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. * - * Optional method. Default behaviour is to use the ttys array + * Optional method. Default behaviour is to use the @self->ttys array. * - * int (*open)(struct tty_struct * tty, struct file * filp); + * @open: ``int ()(struct tty_struct *tty, struct file *)`` * - * This routine is called when a particular tty device is opened. - * This routine is mandatory; if this routine is not filled in, - * the attempted open will fail with ENODEV. + * This routine is called when a particular @tty device is opened. This + * routine is mandatory; if this routine is not filled in, the attempted + * open will fail with %ENODEV. * * Required method. Called with tty lock held. * - * void (*close)(struct tty_struct * tty, struct file * filp); + * @close: ``void ()(struct tty_struct *tty, struct file *)`` * - * This routine is called when a particular tty device is closed. - * Note: called even if the corresponding open() failed. + * This routine is called when a particular @tty device is closed. + * + * Remark: called even if the corresponding @open() failed. * * Required method. Called with tty lock held. * - * void (*shutdown)(struct tty_struct * tty); + * @shutdown: ``void ()(struct tty_struct *tty)`` * - * This routine is called under the tty lock when a particular tty device - * is closed for the last time. It executes before the tty resources - * are freed so may execute while another function holds a tty kref. + * This routine is called under the tty lock when a particular @tty device + * is closed for the last time. It executes before the @tty resources + * are freed so may execute while another function holds a @tty kref. * - * void (*cleanup)(struct tty_struct * tty); + * @cleanup: ``void ()(struct tty_struct *tty)`` * - * This routine is called asynchronously when a particular tty device + * This routine is called asynchronously when a particular @tty device * is closed for the last time freeing up the resources. This is * actually the second part of shutdown for routines that might sleep. * + * @write: ``int ()(struct tty_struct *tty, const unsigned char *buf, + * int count)`` * - * int (*write)(struct tty_struct * tty, - * const unsigned char *buf, int count); - * - * This routine is called by the kernel to write a series of - * characters to the tty device. The characters may come from - * user space or kernel space. This routine will return the + * This routine is called by the kernel to write a series (@count) of + * characters (@buf) to the @tty device. The characters may come from + * user space or kernel space. This routine will return the * number of characters actually accepted for writing. * * Optional: Required for writable devices. * - * int (*put_char)(struct tty_struct *tty, unsigned char ch); + * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)`` * - * This routine is called by the kernel to write a single - * character to the tty device. If the kernel uses this routine, - * it must call the flush_chars() routine (if defined) when it is - * done stuffing characters into the driver. If there is no room - * in the queue, the character is ignored. + * This routine is called by the kernel to write a single character @ch to + * the @tty device. If the kernel uses this routine, it must call the + * @flush_chars() routine (if defined) when it is done stuffing characters + * into the driver. If there is no room in the queue, the character is + * ignored. * - * Optional: Kernel will use the write method if not provided. + * Optional: Kernel will use the @write method if not provided. Do not + * call this function directly, call tty_put_char(). * - * Note: Do not call this function directly, call tty_put_char + * @flush_chars: ``void ()(struct tty_struct *tty)`` * - * void (*flush_chars)(struct tty_struct *tty); + * This routine is called by the kernel after it has written a + * series of characters to the tty device using @put_char(). * - * This routine is called by the kernel after it has written a - * series of characters to the tty device using put_char(). + * Optional. Do not call this function directly, call + * tty_driver_flush_chars(). * - * Optional: + * @write_room: ``unsigned int ()(struct tty_struct *tty)`` * - * Note: Do not call this function directly, call tty_driver_flush_chars - * - * unsigned int (*write_room)(struct tty_struct *tty); - * - * This routine returns the numbers of characters the tty driver - * will accept for queuing to be written. This number is subject - * to change as output buffers get emptied, or if the output flow + * This routine returns the numbers of characters the @tty driver + * will accept for queuing to be written. This number is subject + * to change as output buffers get emptied, or if the output flow * control is acted. * - * Required if write method is provided else not needed. + * Required if @write method is provided else not needed. Do not call this + * function directly, call tty_write_room() * - * Note: Do not call this function directly, call tty_write_room - * - * int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); + * @chars_in_buffer: ``unsigned int ()(struct tty_struct *tty)`` * - * This routine allows the tty driver to implement - * device-specific ioctls. If the ioctl number passed in cmd - * is not recognized by the driver, it should return ENOIOCTLCMD. + * This routine returns the number of characters in the device private + * output queue. Used in tty_wait_until_sent() and for poll() + * implementation. * - * Optional + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call tty_chars_in_buffer(). * - * long (*compat_ioctl)(struct tty_struct *tty,, - * unsigned int cmd, unsigned long arg); + * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` * - * implement ioctl processing for 32 bit process on 64 bit system + * This routine allows the @tty driver to implement device-specific + * ioctls. If the ioctl number passed in @cmd is not recognized by the + * driver, it should return %ENOIOCTLCMD. * - * Optional - * - * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); + * Optional. * - * This routine allows the tty driver to be notified when - * device's termios settings have changed. + * @compat_ioctl: ``long ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` * - * Optional: Called under the termios lock + * Implement ioctl processing for 32 bit process on 64 bit system. * + * Optional. * - * void (*set_ldisc)(struct tty_struct *tty); + * @set_termios: ``void ()(struct tty_struct *tty, struct ktermios *old)`` * - * This routine allows the tty driver to be notified when the - * device's termios settings have changed. + * This routine allows the @tty driver to be notified when device's + * termios settings have changed. * - * Optional: Called under BKL (currently) - * - * void (*throttle)(struct tty_struct * tty); + * Optional: Called under the @tty->termios_rwsem. * - * This routine notifies the tty driver that input buffers for - * the line discipline are close to full, and it should somehow - * signal that no more characters should be sent to the tty. + * @set_ldisc: ``void ()(struct tty_struct *tty)`` * - * Optional: Always invoke via tty_throttle_safe(), called under the - * termios lock. - * - * void (*unthrottle)(struct tty_struct * tty); + * This routine allows the @tty driver to be notified when the device's + * line discipline is being changed. * - * This routine notifies the tty drivers that it should signals - * that characters can now be sent to the tty without fear of - * overrunning the input buffers of the line disciplines. - * - * Optional: Always invoke via tty_unthrottle(), called under the - * termios lock. + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. * - * void (*stop)(struct tty_struct *tty); + * @throttle: ``void ()(struct tty_struct *tty)`` * - * This routine notifies the tty driver that it should stop - * outputting characters to the tty device. + * This routine notifies the @tty driver that input buffers for the line + * discipline are close to full, and it should somehow signal that no more + * characters should be sent to the @tty. * - * Called with ->flow.lock held. Serialized with start() method. + * Optional: Always invoke via tty_throttle_safe(). Called under the + * @tty->termios_rwsem. * - * Optional: + * @unthrottle: ``void ()(struct tty_struct *tty)`` * - * Note: Call stop_tty not this method. - * - * void (*start)(struct tty_struct *tty); + * This routine notifies the @tty driver that it should signal that + * characters can now be sent to the @tty without fear of overrunning the + * input buffers of the line disciplines. * - * This routine notifies the tty driver that it resume sending + * Optional. Always invoke via tty_unthrottle(). Called under the + * @tty->termios_rwsem. + * + * @stop: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should stop outputting * characters to the tty device. * - * Called with ->flow.lock held. Serialized with stop() method. + * Called with @tty->flow.lock held. Serialized with @start() method. * - * Optional: + * Optional. Always invoke via stop_tty(). * - * Note: Call start_tty not this method. - * - * void (*hangup)(struct tty_struct *tty); + * @start: ``void ()(struct tty_struct *tty)`` * - * This routine notifies the tty driver that it should hang up the - * tty device. + * This routine notifies the @tty driver that it resumed sending + * characters to the @tty device. * - * Optional: + * Called with @tty->flow.lock held. Serialized with stop() method. * - * Called with tty lock held. + * Optional. Always invoke via start_tty(). * - * int (*break_ctl)(struct tty_struct *tty, int state); + * @hangup: ``void ()(struct tty_struct *tty)`` * - * This optional routine requests the tty driver to turn on or - * off BREAK status on the RS-232 port. If state is -1, - * then the BREAK status should be turned on; if state is 0, then - * BREAK should be turned off. + * This routine notifies the @tty driver that it should hang up the @tty + * device. * - * If this routine is implemented, the high-level tty driver will - * handle the following ioctls: TCSBRK, TCSBRKP, TIOCSBRK, - * TIOCCBRK. + * Optional. Called with tty lock held. * - * If the driver sets TTY_DRIVER_HARDWARE_BREAK then the interface - * will also be called with actual times and the hardware is expected - * to do the delay work itself. 0 and -1 are still used for on/off. + * @break_ctl: ``int ()(struct tty_struct *tty, int state)`` * - * Optional: Required for TCSBRK/BRKP/etc handling. + * This optional routine requests the @tty driver to turn on or off BREAK + * status on the RS-232 port. If @state is -1, then the BREAK status + * should be turned on; if @state is 0, then BREAK should be turned off. * - * void (*wait_until_sent)(struct tty_struct *tty, int timeout); - * - * This routine waits until the device has written out all of the - * characters in its transmitter FIFO. + * If this routine is implemented, the high-level tty driver will handle + * the following ioctls: %TCSBRK, %TCSBRKP, %TIOCSBRK, %TIOCCBRK. + * + * If the driver sets %TTY_DRIVER_HARDWARE_BREAK in tty_alloc_driver(), + * then the interface will also be called with actual times and the + * hardware is expected to do the delay work itself. 0 and -1 are still + * used for on/off. + * + * Optional: Required for %TCSBRK/%BRKP/etc. handling. + * + * @flush_buffer: ``void ()(struct tty_struct *tty)`` + * + * This routine discards device private output buffer. Invoked on close, + * hangup, to implement %TCOFLUSH ioctl and similar. + * + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call + * tty_driver_flush_buffer(). + * + * @wait_until_sent: ``void ()(struct tty_struct *tty, int timeout)`` + * + * This routine waits until the device has written out all of the + * characters in its transmitter FIFO. Or until @timeout (in jiffies) is + * reached. + * + * Optional: If not provided, the device is assumed to have no FIFO. + * Usually correct to invoke via tty_wait_until_sent(). + * + * @send_xchar: ``void ()(struct tty_struct *tty, char ch)`` + * + * This routine is used to send a high-priority XON/XOFF character (@ch) + * to the @tty device. * - * Optional: If not provided the device is assumed to have no FIFO + * Optional: If not provided, then the @write method is called under + * the @tty->atomic_write_lock to keep it serialized with the ldisc. * - * Note: Usually correct to call tty_wait_until_sent + * @tiocmget: ``int ()(struct tty_struct *tty)`` * - * void (*send_xchar)(struct tty_struct *tty, char ch); + * This routine is used to obtain the modem status bits from the @tty + * driver. * - * This routine is used to send a high-priority XON/XOFF - * character to the device. + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMGET + * ioctl. Do not call this function directly, call tty_tiocmget(). * - * Optional: If not provided then the write method is called under - * the atomic write lock to keep it serialized with the ldisc. + * @tiocmset: ``int ()(struct tty_struct *tty, + * unsigned int set, unsigned int clear)`` * - * int (*resize)(struct tty_struct *tty, struct winsize *ws) + * This routine is used to set the modem status bits to the @tty driver. + * First, @clear bits should be cleared, then @set bits set. * - * Called when a termios request is issued which changes the - * requested terminal geometry. + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMSET + * ioctl. Do not call this function directly, call tty_tiocmset(). + * + * @resize: ``int ()(struct tty_struct *tty, struct winsize *ws)`` + * + * Called when a termios request is issued which changes the requested + * terminal geometry to @ws. * * Optional: the default action is to update the termios structure * without error. This is usually the correct behaviour. Drivers should - * not force errors here if they are not resizable objects (eg a serial + * not force errors here if they are not resizable objects (e.g. a serial * line). See tty_do_resize() if you need to wrap the standard method - * in your own logic - the usual case. + * in your own logic -- the usual case. + * + * @get_icount: ``int ()(struct tty_struct *tty, + * struct serial_icounter *icount)`` + * + * Called when the @tty device receives a %TIOCGICOUNT ioctl. Passed a + * kernel structure @icount to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * + * @get_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` + * + * Called when the @tty device receives a %TIOCGSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocgserial(). + * + * @set_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` + * + * Called when the @tty device receives a %TIOCSSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to set the values from. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocsserial(). + * + * @show_fdinfo: ``void ()(struct tty_struct *tty, struct seq_file *m)`` + * + * Called when the @tty device file descriptor receives a fdinfo request + * from VFS (to show in /proc//fdinfo/). @m should be filled with + * information. + * + * Optional: called only if provided, otherwise nothing is written to @m. + * Do not call this function directly, call tty_show_fdinfo(). + * + * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` + * + * kgdboc support (Documentation/dev-tools/kgdb.rst). This routine is + * called to initialize the HW for later use by calling @poll_get_char or + * @poll_put_char. + * + * Optional: called only if provided, otherwise skipped as a non-polling + * driver. + * + * @poll_get_char: ``int ()(struct tty_driver *driver, int line)`` + * + * kgdboc support (see @poll_init). @driver should read a character from a + * tty identified by @line and return it. + * + * Optional: called only if @poll_init provided. * - * int (*get_icount)(struct tty_struct *tty, struct serial_icounter *icount); + * @poll_put_char: ``void ()(struct tty_driver *driver, int line, char ch)`` * - * Called when the device receives a TIOCGICOUNT ioctl. Passed a kernel - * structure to complete. This method is optional and will only be called - * if provided (otherwise ENOTTY will be returned). + * kgdboc support (see @poll_init). @driver should write character @ch to + * a tty identified by @line. + * + * Optional: called only if @poll_init provided. + * + * @proc_show: ``int ()(struct seq_file *m, void *driver)`` + * + * Driver @driver (cast to &struct tty_driver) can show additional info in + * /proc/tty/driver/. It is enough to fill in the information + * into @m. + * + * Optional: called only if provided, otherwise no /proc entry created. + * + * This structure defines the interface between the low-level tty driver and + * the tty routines. These routines can be defined. Unless noted otherwise, + * they are optional, and can be filled in with a %NULL pointer. */ - -#include -#include -#include -#include -#include -#include -#include - -struct tty_struct; -struct tty_driver; -struct serial_icounter_struct; -struct serial_struct; - struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, struct file *filp, int idx); @@ -288,7 +372,7 @@ struct tty_operations { int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif - int (*proc_show)(struct seq_file *, void *); + int (*proc_show)(struct seq_file *m, void *driver); } __randomize_layout; /** -- cgit v1.2.3 From 630bf86d15778fd3e5df17cb6e00839d0f44a707 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:53 +0100 Subject: tty: add kernel-doc for tty_port_operations tty_port_operations used to have only comments along its members. Convert them into proper kernel-doc comments in front of the structure. And add some more explanation to them where needed. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-6-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_port.h | 27 +++++++++++++++++---------- 1 file changed, 17 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h index 9091e1c8de4c..d3ea9ed0b98e 100644 --- a/include/linux/tty_port.h +++ b/include/linux/tty_port.h @@ -12,21 +12,28 @@ struct tty_driver; struct tty_port; struct tty_struct; +/** + * struct tty_port_operations -- operations on tty_port + * @carrier_raised: return 1 if the carrier is raised on @port + * @dtr_rts: raise the DTR line if @raise is nonzero, otherwise lower DTR + * @shutdown: called when the last close completes or a hangup finishes IFF the + * port was initialized. Do not use to free resources. Turn off the device + * only. Called under the port mutex to serialize against @activate and + * @shutdown. + * @activate: called under the port mutex from tty_port_open(), serialized using + * the port mutex. Supposed to turn on the device. + * + * FIXME: long term getting the tty argument *out* of this would be good + * for consoles. + * + * @destruct: called on the final put of a port. Free resources, possibly incl. + * the port itself. + */ struct tty_port_operations { - /* Return 1 if the carrier is raised */ int (*carrier_raised)(struct tty_port *port); - /* Control the DTR line */ void (*dtr_rts)(struct tty_port *port, int raise); - /* Called when the last close completes or a hangup finishes - IFF the port was initialized. Do not use to free resources. Called - under the port mutex to serialize against activate/shutdowns */ void (*shutdown)(struct tty_port *port); - /* Called under the port mutex from tty_port_open, serialized using - the port mutex */ - /* FIXME: long term getting the tty argument *out* of this would be - good for consoles */ int (*activate)(struct tty_port *port, struct tty_struct *tty); - /* Called on the final put of a port */ void (*destruct)(struct tty_port *port); }; -- cgit v1.2.3 From 0c6119f9f7dc03a53bd35ca5a77926eef3c33d10 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:54 +0100 Subject: tty: add kernel-doc for tty_ldisc_ops tty_ldisc_ops structure was already partially documented in a standalone comment in the header beginning. Move it right before the structure and reformat it so it complies to kernel-doc. That way, we can include it in Documentation/ later in this series. And add the documentation for the members where missing too. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-7-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_ldisc.h | 259 +++++++++++++++++++++++----------------------- 1 file changed, 130 insertions(+), 129 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index 25f07017bbad..e0da0ba02de9 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -4,126 +4,6 @@ struct tty_struct; -/* - * This structure defines the interface between the tty line discipline - * implementation and the tty routines. The following routines can be - * defined; unless noted otherwise, they are optional, and can be - * filled in with a null pointer. - * - * int (*open)(struct tty_struct *); - * - * This function is called when the line discipline is associated - * with the tty. The line discipline can use this as an - * opportunity to initialize any state needed by the ldisc routines. - * - * void (*close)(struct tty_struct *); - * - * This function is called when the line discipline is being - * shutdown, either because the tty is being closed or because - * the tty is being changed to use a new line discipline - * - * void (*flush_buffer)(struct tty_struct *tty); - * - * This function instructs the line discipline to clear its - * buffers of any input characters it may have queued to be - * delivered to the user mode process. - * - * ssize_t (*read)(struct tty_struct * tty, struct file * file, - * unsigned char * buf, size_t nr); - * - * This function is called when the user requests to read from - * the tty. The line discipline will return whatever characters - * it has buffered up for the user. If this function is not - * defined, the user will receive an EIO error. - * - * ssize_t (*write)(struct tty_struct * tty, struct file * file, - * const unsigned char * buf, size_t nr); - * - * This function is called when the user requests to write to the - * tty. The line discipline will deliver the characters to the - * low-level tty device for transmission, optionally performing - * some processing on the characters first. If this function is - * not defined, the user will receive an EIO error. - * - * int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); - * - * This function is called when the user requests an ioctl which - * is not handled by the tty layer or the low-level tty driver. - * It is intended for ioctls which affect line discpline - * operation. Note that the search order for ioctls is (1) tty - * layer, (2) tty low-level driver, (3) line discpline. So a - * low-level driver can "grab" an ioctl request before the line - * discpline has a chance to see it. - * - * int (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, - * unsigned long arg); - * - * Process ioctl calls from 32-bit process on 64-bit system - * - * NOTE: only ioctls that are neither "pointer to compatible - * structure" nor tty-generic. Something private that takes - * an integer or a pointer to wordsize-sensitive structure - * belongs here, but most of ldiscs will happily leave - * it NULL. - * - * void (*set_termios)(struct tty_struct *tty, struct ktermios * old); - * - * This function notifies the line discpline that a change has - * been made to the termios structure. - * - * int (*poll)(struct tty_struct * tty, struct file * file, - * poll_table *wait); - * - * This function is called when a user attempts to select/poll on a - * tty device. It is solely the responsibility of the line - * discipline to handle poll requests. - * - * void (*receive_buf)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. is a pointer to the buffer of input - * character received by the device. is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. may be NULL to indicate - * all data received is TTY_NORMAL. - * - * void (*write_wakeup)(struct tty_struct *); - * - * This function is called by the low-level tty driver to signal - * that line discpline should try to send more characters to the - * low-level driver for transmission. If the line discpline does - * not have any more data to send, it can just return. If the line - * discipline does have some data to send, please arise a tasklet - * or workqueue to do the real data transfer. Do not send data in - * this hook, it may leads to a deadlock. - * - * int (*hangup)(struct tty_struct *) - * - * Called on a hangup. Tells the discipline that it should - * cease I/O to the tty driver. Can sleep. The driver should - * seek to perform this action quickly but should wait until - * any pending driver I/O is completed. - * - * void (*dcd_change)(struct tty_struct *tty, unsigned int status) - * - * Tells the discipline that the DCD pin has changed its status. - * Used exclusively by the N_PPS (Pulse-Per-Second) line discipline. - * - * int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, - * char *fp, int count); - * - * This function is called by the low-level tty driver to send - * characters received by the hardware to the line discpline for - * processing. is a pointer to the buffer of input - * character received by the device. is a pointer to a - * pointer of flag bytes which indicate whether a character was - * received with a parity error, etc. may be NULL to indicate - * all data received is TTY_NORMAL. - * If assigned, prefer this function for automatic flow control. - */ - #include #include #include @@ -175,7 +55,128 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, ldsem_down_write(sem, timeout) #endif - +/** + * struct tty_ldisc_ops - ldisc operations + * + * @name: name of this ldisc rendered in /proc/tty/ldiscs + * @num: ``N_*`` number (%N_TTY, %N_HDLC, ...) reserved to this ldisc + * + * @open: ``int ()(struct tty_struct *tty)`` + * + * This function is called when the line discipline is associated with the + * @tty. The line discipline can use this as an opportunity to initialize + * any state needed by the ldisc routines. + * + * @close: ``void ()(struct tty_struct *tty)`` + * + * This function is called when the line discipline is being shutdown, + * either because the @tty is being closed or because the @tty is being + * changed to use a new line discipline + * + * @flush_buffer: ``void ()(struct tty_struct *tty)`` + * + * This function instructs the line discipline to clear its buffers of any + * input characters it may have queued to be delivered to the user mode + * process. + * + * @read: ``ssize_t ()(struct tty_struct *tty, struct file *file, + * unsigned char *buf, size_t nr)`` + * + * This function is called when the user requests to read from the @tty. + * The line discipline will return whatever characters it has buffered up + * for the user. If this function is not defined, the user will receive + * an %EIO error. + * + * @write: ``ssize_t ()(struct tty_struct *tty, struct file *file, + * const unsigned char *buf, size_t nr)`` + * + * This function is called when the user requests to write to the @tty. + * The line discipline will deliver the characters to the low-level tty + * device for transmission, optionally performing some processing on the + * characters first. If this function is not defined, the user will + * receive an %EIO error. + * + * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * This function is called when the user requests an ioctl which is not + * handled by the tty layer or the low-level tty driver. It is intended + * for ioctls which affect line discpline operation. Note that the search + * order for ioctls is (1) tty layer, (2) tty low-level driver, (3) line + * discpline. So a low-level driver can "grab" an ioctl request before + * the line discpline has a chance to see it. + * + * @compat_ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * Process ioctl calls from 32-bit process on 64-bit system. + * + * Note that only ioctls that are neither "pointer to compatible + * structure" nor tty-generic. Something private that takes an integer or + * a pointer to wordsize-sensitive structure belongs here, but most of + * ldiscs will happily leave it %NULL. + * + * @set_termios: ``void ()(struct tty_struct *tty, struct ktermios *old)`` + * + * This function notifies the line discpline that a change has been made + * to the termios structure. + * + * @poll: ``int ()(struct tty_struct *tty, struct file *file, + * struct poll_table_struct *wait)`` + * + * This function is called when a user attempts to select/poll on a @tty + * device. It is solely the responsibility of the line discipline to + * handle poll requests. + * + * @hangup: ``void ()(struct tty_struct *tty)`` + * + * Called on a hangup. Tells the discipline that it should cease I/O to + * the tty driver. Can sleep. The driver should seek to perform this + * action quickly but should wait until any pending driver I/O is + * completed. + * + * @receive_buf: ``void ()(struct tty_struct *tty, const unsigned char *cp, + * const char *fp, int count)`` + * + * This function is called by the low-level tty driver to send characters + * received by the hardware to the line discpline for processing. @cp is + * a pointer to the buffer of input character received by the device. @fp + * is a pointer to an array of flag bytes which indicate whether a + * character was received with a parity error, etc. @fp may be %NULL to + * indicate all data received is %TTY_NORMAL. + * + * @write_wakeup: ``void ()(struct tty_struct *tty)`` + * + * This function is called by the low-level tty driver to signal that line + * discpline should try to send more characters to the low-level driver + * for transmission. If the line discpline does not have any more data to + * send, it can just return. If the line discipline does have some data to + * send, please arise a tasklet or workqueue to do the real data transfer. + * Do not send data in this hook, it may lead to a deadlock. + * + * @dcd_change: ``void ()(struct tty_struct *tty, unsigned int status)`` + * + * Tells the discipline that the DCD pin has changed its status. Used + * exclusively by the %N_PPS (Pulse-Per-Second) line discipline. + * + * @receive_buf2: ``int ()(struct tty_struct *tty, const unsigned char *cp, + * const char *fp, int count)`` + * + * This function is called by the low-level tty driver to send characters + * received by the hardware to the line discpline for processing. @cp is a + * pointer to the buffer of input character received by the device. @fp + * is a pointer to an array of flag bytes which indicate whether a + * character was received with a parity error, etc. @fp may be %NULL to + * indicate all data received is %TTY_NORMAL. If assigned, prefer this + * function for automatic flow control. + * + * @owner: module containting this ldisc (for reference counting) + * + * This structure defines the interface between the tty line discipline + * implementation and the tty routines. The above routines can be defined. + * Unless noted otherwise, they are optional, and can be filled in with a %NULL + * pointer. + */ struct tty_ldisc_ops { char *name; int num; @@ -183,8 +184,8 @@ struct tty_ldisc_ops { /* * The following routines are called from above. */ - int (*open)(struct tty_struct *); - void (*close)(struct tty_struct *); + int (*open)(struct tty_struct *tty); + void (*close)(struct tty_struct *tty); void (*flush_buffer)(struct tty_struct *tty); ssize_t (*read)(struct tty_struct *tty, struct file *file, unsigned char *buf, size_t nr, @@ -196,18 +197,18 @@ struct tty_ldisc_ops { int (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); void (*set_termios)(struct tty_struct *tty, struct ktermios *old); - __poll_t (*poll)(struct tty_struct *, struct file *, - struct poll_table_struct *); + __poll_t (*poll)(struct tty_struct *tty, struct file *file, + struct poll_table_struct *wait); void (*hangup)(struct tty_struct *tty); /* * The following routines are called from below. */ - void (*receive_buf)(struct tty_struct *, const unsigned char *cp, + void (*receive_buf)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); - void (*write_wakeup)(struct tty_struct *); - void (*dcd_change)(struct tty_struct *, unsigned int); - int (*receive_buf2)(struct tty_struct *, const unsigned char *cp, + void (*write_wakeup)(struct tty_struct *tty); + void (*dcd_change)(struct tty_struct *tty, unsigned int status); + int (*receive_buf2)(struct tty_struct *tty, const unsigned char *cp, const char *fp, int count); struct module *owner; -- cgit v1.2.3 From 29d5ef685948369602ccd5c04d2a215449c4b943 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:55 +0100 Subject: tty: combine tty_operations triple docs into kernel-doc In Documentation/driver-api/serial/tty.rst, there are triplicated texts about some struct tty_operations' hooks. Combine them into existing kernel-doc comments of struct tty_operations and drop them from the Documentation/. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-8-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/serial/tty.rst | 134 +------------------------------- include/linux/tty_driver.h | 36 ++++++--- 2 files changed, 29 insertions(+), 141 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/serial/tty.rst b/Documentation/driver-api/serial/tty.rst index 4b709f392713..f7ef10c6f458 100644 --- a/Documentation/driver-api/serial/tty.rst +++ b/Documentation/driver-api/serial/tty.rst @@ -132,74 +132,8 @@ dcd_change() Report to the tty line the current DCD pin status Driver Access ^^^^^^^^^^^^^ -Line discipline methods can call the following methods of the underlying -hardware driver through the function pointers within the tty->driver -structure: - -======================= ======================================================= -write() Write a block of characters to the tty device. - Returns the number of characters accepted. The - character buffer passed to this method is already - in kernel space. - -put_char() Queues a character for writing to the tty device. - If there is no room in the queue, the character is - ignored. - -flush_chars() (Optional) If defined, must be called after - queueing characters with put_char() in order to - start transmission. - -write_room() Returns the numbers of characters the tty driver - will accept for queueing to be written. - -ioctl() Invoke device specific ioctl. - Expects data pointers to refer to userspace. - Returns ENOIOCTLCMD for unrecognized ioctl numbers. - -set_termios() Notify the tty driver that the device's termios - settings have changed. New settings are in - tty->termios. Previous settings should be passed in - the "old" argument. - - The API is defined such that the driver should return - the actual modes selected. This means that the - driver function is responsible for modifying any - bits in the request it cannot fulfill to indicate - the actual modes being used. A device with no - hardware capability for change (e.g. a USB dongle or - virtual port) can provide NULL for this method. - -throttle() Notify the tty driver that input buffers for the - line discipline are close to full, and it should - somehow signal that no more characters should be - sent to the tty. - -unthrottle() Notify the tty driver that characters can now be - sent to the tty without fear of overrunning the - input buffers of the line disciplines. - -stop() Ask the tty driver to stop outputting characters - to the tty device. - -start() Ask the tty driver to resume sending characters - to the tty device. - -hangup() Ask the tty driver to hang up the tty device. - -break_ctl() (Optional) Ask the tty driver to turn on or off - BREAK status on the RS-232 port. If state is -1, - then the BREAK status should be turned on; if - state is 0, then BREAK should be turned off. - If this routine is not implemented, use ioctls - TIOCSBRK / TIOCCBRK instead. - -wait_until_sent() Waits until the device has written out all of the - characters in its transmitter FIFO. - -send_xchar() Send a high-priority XON/XOFF character to the device. -======================= ======================================================= - +Line discipline methods can call the methods of the underlying hardware driver. +These are documented as a part of struct tty_operations. Flags ^^^^^ @@ -262,67 +196,3 @@ A caution: The ldisc->open(), ldisc->close() and driver->set_ldisc functions are called with the ldisc unavailable. Thus tty_ldisc_ref will fail in this situation if used within these functions. Ldisc and driver code calling its own functions must be careful in this case. - - -Driver Interface ----------------- - -======================= ======================================================= -open() Called when a device is opened. May sleep - -close() Called when a device is closed. At the point of - return from this call the driver must make no - further ldisc calls of any kind. May sleep - -write() Called to write bytes to the device. May not - sleep. May occur in parallel in special cases. - Because this includes panic paths drivers generally - shouldn't try and do clever locking here. - -put_char() Stuff a single character onto the queue. The - driver is guaranteed following up calls to - flush_chars. - -flush_chars() Ask the kernel to write put_char queue - -write_room() Return the number of characters that can be stuffed - into the port buffers without overflow (or less). - The ldisc is responsible for being intelligent - about multi-threading of write_room/write calls - -ioctl() Called when an ioctl may be for the driver - -set_termios() Called on termios change, serialized against - itself by a semaphore. May sleep. - -set_ldisc() Notifier for discipline change. At the point this - is done the discipline is not yet usable. Can now - sleep (I think) - -throttle() Called by the ldisc to ask the driver to do flow - control. Serialization including with unthrottle - is the job of the ldisc layer. - -unthrottle() Called by the ldisc to ask the driver to stop flow - control. - -stop() Ldisc notifier to the driver to stop output. As with - throttle the serializations with start() are down - to the ldisc layer. - -start() Ldisc notifier to the driver to start output. - -hangup() Ask the tty driver to cause a hangup initiated - from the host side. [Can sleep ??] - -break_ctl() Send RS232 break. Can sleep. Can get called in - parallel, driver must serialize (for now), and - with write calls. - -wait_until_sent() Wait for characters to exit the hardware queue - of the driver. Can sleep - -send_xchar() Send XON/XOFF and if possible jump the queue with - it in order to get fast flow control responses. - Cannot sleep ?? -======================= ======================================================= diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 5611992ab26a..41274d551e28 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -47,15 +47,17 @@ struct serial_struct; * routine is mandatory; if this routine is not filled in, the attempted * open will fail with %ENODEV. * - * Required method. Called with tty lock held. + * Required method. Called with tty lock held. May sleep. * * @close: ``void ()(struct tty_struct *tty, struct file *)`` * - * This routine is called when a particular @tty device is closed. + * This routine is called when a particular @tty device is closed. At the + * point of return from this call the driver must make no further ldisc + * calls of any kind. * * Remark: called even if the corresponding @open() failed. * - * Required method. Called with tty lock held. + * Required method. Called with tty lock held. May sleep. * * @shutdown: ``void ()(struct tty_struct *tty)`` * @@ -77,7 +79,10 @@ struct serial_struct; * user space or kernel space. This routine will return the * number of characters actually accepted for writing. * - * Optional: Required for writable devices. + * May occur in parallel in special cases. Because this includes panic + * paths drivers generally shouldn't try and do clever locking here. + * + * Optional: Required for writable devices. May not sleep. * * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)`` * @@ -105,6 +110,9 @@ struct serial_struct; * to change as output buffers get emptied, or if the output flow * control is acted. * + * The ldisc is responsible for being intelligent about multi-threading of + * write_room/write calls + * * Required if @write method is provided else not needed. Do not call this * function directly, call tty_write_room() * @@ -136,14 +144,21 @@ struct serial_struct; * @set_termios: ``void ()(struct tty_struct *tty, struct ktermios *old)`` * * This routine allows the @tty driver to be notified when device's - * termios settings have changed. + * termios settings have changed. New settings are in @tty->termios. + * Previous settings are passed in the @old argument. * - * Optional: Called under the @tty->termios_rwsem. + * The API is defined such that the driver should return the actual modes + * selected. This means that the driver is responsible for modifying any + * bits in @tty->termios it cannot fulfill to indicate the actual modes + * being used. + * + * Optional. Called under the @tty->termios_rwsem. May sleep. * * @set_ldisc: ``void ()(struct tty_struct *tty)`` * * This routine allows the @tty driver to be notified when the device's - * line discipline is being changed. + * line discipline is being changed. At the point this is done the + * discipline is not yet usable. * * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. * @@ -153,6 +168,9 @@ struct serial_struct; * discipline are close to full, and it should somehow signal that no more * characters should be sent to the @tty. * + * Serialization including with @unthrottle() is the job of the ldisc + * layer. + * * Optional: Always invoke via tty_throttle_safe(). Called under the * @tty->termios_rwsem. * @@ -204,7 +222,7 @@ struct serial_struct; * hardware is expected to do the delay work itself. 0 and -1 are still * used for on/off. * - * Optional: Required for %TCSBRK/%BRKP/etc. handling. + * Optional: Required for %TCSBRK/%BRKP/etc. handling. May sleep. * * @flush_buffer: ``void ()(struct tty_struct *tty)`` * @@ -222,7 +240,7 @@ struct serial_struct; * reached. * * Optional: If not provided, the device is assumed to have no FIFO. - * Usually correct to invoke via tty_wait_until_sent(). + * Usually correct to invoke via tty_wait_until_sent(). May sleep. * * @send_xchar: ``void ()(struct tty_struct *tty, char ch)`` * -- cgit v1.2.3 From 40f4268cddb93d17a11579920d940c2dca8b9445 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:56 +0100 Subject: tty: combine tty_ldisc_ops docs into kernel-doc In Documentation/driver-api/serial/tty.rst, there are duplicated texts about some struct tty_ldisc_ops' hooks. Combine them into existing kernel-doc comments of struct tty_ldisc_ops and drop them from the Documentation/. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-9-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/serial/tty.rst | 95 +-------------------------------- include/linux/tty_ldisc.h | 67 ++++++++++++++--------- 2 files changed, 45 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/serial/tty.rst b/Documentation/driver-api/serial/tty.rst index f7ef10c6f458..333a5923f6e1 100644 --- a/Documentation/driver-api/serial/tty.rst +++ b/Documentation/driver-api/serial/tty.rst @@ -35,99 +35,8 @@ about to enter and exit although this detail matters not). Line Discipline Methods ----------------------- -TTY side interfaces -^^^^^^^^^^^^^^^^^^^ - -======================= ======================================================= -open() Called when the line discipline is attached to - the terminal. No other call into the line - discipline for this tty will occur until it - completes successfully. Should initialize any - state needed by the ldisc, and set receive_room - in the tty_struct to the maximum amount of data - the line discipline is willing to accept from the - driver with a single call to receive_buf(). - Returning an error will prevent the ldisc from - being attached. Can sleep. - -close() This is called on a terminal when the line - discipline is being unplugged. At the point of - execution no further users will enter the - ldisc code for this tty. Can sleep. - -hangup() Called when the tty line is hung up. - The line discipline should cease I/O to the tty. - No further calls into the ldisc code will occur. - Can sleep. - -read() (optional) A process requests reading data from - the line. Multiple read calls may occur in parallel - and the ldisc must deal with serialization issues. - If not defined, the process will receive an EIO - error. May sleep. - -write() (optional) A process requests writing data to the - line. Multiple write calls are serialized by the - tty layer for the ldisc. If not defined, the - process will receive an EIO error. May sleep. - -flush_buffer() (optional) May be called at any point between - open and close, and instructs the line discipline - to empty its input buffer. - -set_termios() (optional) Called on termios structure changes. - The caller passes the old termios data and the - current data is in the tty. Called under the - termios semaphore so allowed to sleep. Serialized - against itself only. - -poll() (optional) Check the status for the poll/select - calls. Multiple poll calls may occur in parallel. - May sleep. - -ioctl() (optional) Called when an ioctl is handed to the - tty layer that might be for the ldisc. Multiple - ioctl calls may occur in parallel. May sleep. - -compat_ioctl() (optional) Called when a 32 bit ioctl is handed - to the tty layer that might be for the ldisc. - Multiple ioctl calls may occur in parallel. - May sleep. -======================= ======================================================= - -Driver Side Interfaces -^^^^^^^^^^^^^^^^^^^^^^ - -======================= ======================================================= -receive_buf() (optional) Called by the low-level driver to hand - a buffer of received bytes to the ldisc for - processing. The number of bytes is guaranteed not - to exceed the current value of tty->receive_room. - All bytes must be processed. - -receive_buf2() (optional) Called by the low-level driver to hand - a buffer of received bytes to the ldisc for - processing. Returns the number of bytes processed. - - If both receive_buf() and receive_buf2() are - defined, receive_buf2() should be preferred. - -write_wakeup() May be called at any point between open and close. - The TTY_DO_WRITE_WAKEUP flag indicates if a call - is needed but always races versus calls. Thus the - ldisc must be careful about setting order and to - handle unexpected calls. Must not sleep. - - The driver is forbidden from calling this directly - from the ->write call from the ldisc as the ldisc - is permitted to call the driver write method from - this function. In such a situation defer it. - -dcd_change() Report to the tty line the current DCD pin status - changes and the relative timestamp. The timestamp - cannot be NULL. -======================= ======================================================= - +.. kernel-doc:: include/linux/tty_ldisc.h + :identifiers: tty_ldisc_ops Driver Access ^^^^^^^^^^^^^ diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h index e0da0ba02de9..e85002b56752 100644 --- a/include/linux/tty_ldisc.h +++ b/include/linux/tty_ldisc.h @@ -61,33 +61,45 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * @name: name of this ldisc rendered in /proc/tty/ldiscs * @num: ``N_*`` number (%N_TTY, %N_HDLC, ...) reserved to this ldisc * - * @open: ``int ()(struct tty_struct *tty)`` + * @open: [TTY] ``int ()(struct tty_struct *tty)`` * * This function is called when the line discipline is associated with the - * @tty. The line discipline can use this as an opportunity to initialize - * any state needed by the ldisc routines. + * @tty. No other call into the line discipline for this tty will occur + * until it completes successfully. It should initialize any state needed + * by the ldisc, and set @tty->receive_room to the maximum amount of data + * the line discipline is willing to accept from the driver with a single + * call to @receive_buf(). Returning an error will prevent the ldisc from + * being attached. * - * @close: ``void ()(struct tty_struct *tty)`` + * Can sleep. + * + * @close: [TTY] ``void ()(struct tty_struct *tty)`` * * This function is called when the line discipline is being shutdown, * either because the @tty is being closed or because the @tty is being - * changed to use a new line discipline + * changed to use a new line discipline. At the point of execution no + * further users will enter the ldisc code for this tty. + * + * Can sleep. * - * @flush_buffer: ``void ()(struct tty_struct *tty)`` + * @flush_buffer: [TTY] ``void ()(struct tty_struct *tty)`` * * This function instructs the line discipline to clear its buffers of any * input characters it may have queued to be delivered to the user mode - * process. + * process. It may be called at any point between open and close. * - * @read: ``ssize_t ()(struct tty_struct *tty, struct file *file, + * @read: [TTY] ``ssize_t ()(struct tty_struct *tty, struct file *file, * unsigned char *buf, size_t nr)`` * * This function is called when the user requests to read from the @tty. * The line discipline will return whatever characters it has buffered up * for the user. If this function is not defined, the user will receive - * an %EIO error. + * an %EIO error. Multiple read calls may occur in parallel and the ldisc + * must deal with serialization issues. + * + * Can sleep. * - * @write: ``ssize_t ()(struct tty_struct *tty, struct file *file, + * @write: [TTY] ``ssize_t ()(struct tty_struct *tty, struct file *file, * const unsigned char *buf, size_t nr)`` * * This function is called when the user requests to write to the @tty. @@ -96,7 +108,9 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * characters first. If this function is not defined, the user will * receive an %EIO error. * - * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * Can sleep. + * + * @ioctl: [TTY] ``int ()(struct tty_struct *tty, unsigned int cmd, * unsigned long arg)`` * * This function is called when the user requests an ioctl which is not @@ -106,7 +120,7 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * discpline. So a low-level driver can "grab" an ioctl request before * the line discpline has a chance to see it. * - * @compat_ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * @compat_ioctl: [TTY] ``int ()(struct tty_struct *tty, unsigned int cmd, * unsigned long arg)`` * * Process ioctl calls from 32-bit process on 64-bit system. @@ -116,27 +130,29 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * a pointer to wordsize-sensitive structure belongs here, but most of * ldiscs will happily leave it %NULL. * - * @set_termios: ``void ()(struct tty_struct *tty, struct ktermios *old)`` + * @set_termios: [TTY] ``void ()(struct tty_struct *tty, struct ktermios *old)`` * * This function notifies the line discpline that a change has been made * to the termios structure. * - * @poll: ``int ()(struct tty_struct *tty, struct file *file, + * @poll: [TTY] ``int ()(struct tty_struct *tty, struct file *file, * struct poll_table_struct *wait)`` * * This function is called when a user attempts to select/poll on a @tty * device. It is solely the responsibility of the line discipline to * handle poll requests. * - * @hangup: ``void ()(struct tty_struct *tty)`` + * @hangup: [TTY] ``void ()(struct tty_struct *tty)`` * * Called on a hangup. Tells the discipline that it should cease I/O to - * the tty driver. Can sleep. The driver should seek to perform this - * action quickly but should wait until any pending driver I/O is - * completed. + * the tty driver. The driver should seek to perform this action quickly + * but should wait until any pending driver I/O is completed. No further + * calls into the ldisc code will occur. + * + * Can sleep. * - * @receive_buf: ``void ()(struct tty_struct *tty, const unsigned char *cp, - * const char *fp, int count)`` + * @receive_buf: [DRV] ``void ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` * * This function is called by the low-level tty driver to send characters * received by the hardware to the line discpline for processing. @cp is @@ -145,7 +161,7 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * character was received with a parity error, etc. @fp may be %NULL to * indicate all data received is %TTY_NORMAL. * - * @write_wakeup: ``void ()(struct tty_struct *tty)`` + * @write_wakeup: [DRV] ``void ()(struct tty_struct *tty)`` * * This function is called by the low-level tty driver to signal that line * discpline should try to send more characters to the low-level driver @@ -154,13 +170,13 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * send, please arise a tasklet or workqueue to do the real data transfer. * Do not send data in this hook, it may lead to a deadlock. * - * @dcd_change: ``void ()(struct tty_struct *tty, unsigned int status)`` + * @dcd_change: [DRV] ``void ()(struct tty_struct *tty, unsigned int status)`` * * Tells the discipline that the DCD pin has changed its status. Used * exclusively by the %N_PPS (Pulse-Per-Second) line discipline. * - * @receive_buf2: ``int ()(struct tty_struct *tty, const unsigned char *cp, - * const char *fp, int count)`` + * @receive_buf2: [DRV] ``int ()(struct tty_struct *tty, + * const unsigned char *cp, const char *fp, int count)`` * * This function is called by the low-level tty driver to send characters * received by the hardware to the line discpline for processing. @cp is a @@ -176,6 +192,9 @@ int ldsem_down_write_nested(struct ld_semaphore *sem, int subclass, * implementation and the tty routines. The above routines can be defined. * Unless noted otherwise, they are optional, and can be filled in with a %NULL * pointer. + * + * Hooks marked [TTY] are invoked from the TTY core, the [DRV] ones from the + * tty_driver side. */ struct tty_ldisc_ops { char *name; -- cgit v1.2.3 From 4072254f96f954ec0d34899f15d987803b6d76a2 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:57 +0100 Subject: tty: reformat tty_struct::flags into kernel-doc Move the partial tty_struct::flags documentation from tty_ldisc to the tty.h header and combine it with the one-liners present there. Convert all those to kernel-doc. This way, we can simply reference the documentation in Documentation while the text is still along the definitions. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-10-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/serial/tty.rst | 24 +---------- include/linux/tty.h | 74 ++++++++++++++++++++++++++------- 2 files changed, 62 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/serial/tty.rst b/Documentation/driver-api/serial/tty.rst index 333a5923f6e1..65f971e3aada 100644 --- a/Documentation/driver-api/serial/tty.rst +++ b/Documentation/driver-api/serial/tty.rst @@ -47,28 +47,8 @@ These are documented as a part of struct tty_operations. Flags ^^^^^ -Line discipline methods have access to tty->flags field containing the -following interesting flags: - -======================= ======================================================= -TTY_THROTTLED Driver input is throttled. The ldisc should call - tty->driver->unthrottle() in order to resume - reception when it is ready to process more data. - -TTY_DO_WRITE_WAKEUP If set, causes the driver to call the ldisc's - write_wakeup() method in order to resume - transmission when it can accept more data - to transmit. - -TTY_IO_ERROR If set, causes all subsequent userspace read/write - calls on the tty to fail, returning -EIO. - -TTY_OTHER_CLOSED Device is a pty and the other side has closed. - -TTY_NO_WRITE_SPLIT Prevent driver from splitting up writes into - smaller chunks. -======================= ======================================================= - +Line discipline methods have access to :c:member:`tty_struct.flags` field. See +:doc:`tty_struct`. Locking ^^^^^^^ diff --git a/include/linux/tty.h b/include/linux/tty.h index da49ad9be281..7b0a5d478ef6 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -263,26 +263,72 @@ struct tty_file_private { /* tty magic number */ #define TTY_MAGIC 0x5401 -/* - * These bits are used in the flags field of the tty structure. +/** + * DOC: TTY Struct Flags + * + * These bits are used in the :c:member:`tty_struct.flags` field. * * So that interrupts won't be able to mess up the queues, * copy_to_cooked must be atomic with respect to itself, as must * tty->write. Thus, you must use the inline functions set_bit() and * clear_bit() to make things atomic. + * + * TTY_THROTTLED + * Driver input is throttled. The ldisc should call + * :c:member:`tty_driver.unthrottle()` in order to resume reception when + * it is ready to process more data (at threshold min). + * + * TTY_IO_ERROR + * If set, causes all subsequent userspace read/write calls on the tty to + * fail, returning -%EIO. (May be no ldisc too.) + * + * TTY_OTHER_CLOSED + * Device is a pty and the other side has closed. + * + * TTY_EXCLUSIVE + * Exclusive open mode (a single opener). + * + * TTY_DO_WRITE_WAKEUP + * If set, causes the driver to call the + * :c:member:`tty_ldisc_ops.write_wakeup()` method in order to resume + * transmission when it can accept more data to transmit. + * + * TTY_LDISC_OPEN + * Indicates that a line discipline is open. For debugging purposes only. + * + * TTY_PTY_LOCK + * A flag private to pty code to implement %TIOCSPTLCK/%TIOCGPTLCK logic. + * + * TTY_NO_WRITE_SPLIT + * Prevent driver from splitting up writes into smaller chunks (preserve + * write boundaries to driver). + * + * TTY_HUPPED + * The TTY was hung up. This is set post :c:member:`tty_driver.hangup()`. + * + * TTY_HUPPING + * The TTY is in the process of hanging up to abort potential readers. + * + * TTY_LDISC_CHANGING + * Line discipline for this TTY is being changed. I/O should not block + * when this is set. Use tty_io_nonblock() to check. + * + * TTY_LDISC_HALTED + * Line discipline for this TTY was stopped. No work should be queued to + * this ldisc. */ -#define TTY_THROTTLED 0 /* Call unthrottle() at threshold min */ -#define TTY_IO_ERROR 1 /* Cause an I/O error (may be no ldisc too) */ -#define TTY_OTHER_CLOSED 2 /* Other side (if any) has closed */ -#define TTY_EXCLUSIVE 3 /* Exclusive open mode */ -#define TTY_DO_WRITE_WAKEUP 5 /* Call write_wakeup after queuing new */ -#define TTY_LDISC_OPEN 11 /* Line discipline is open */ -#define TTY_PTY_LOCK 16 /* pty private */ -#define TTY_NO_WRITE_SPLIT 17 /* Preserve write boundaries to driver */ -#define TTY_HUPPED 18 /* Post driver->hangup() */ -#define TTY_HUPPING 19 /* Hangup in progress */ -#define TTY_LDISC_CHANGING 20 /* Change pending - non-block IO */ -#define TTY_LDISC_HALTED 22 /* Line discipline is halted */ +#define TTY_THROTTLED 0 +#define TTY_IO_ERROR 1 +#define TTY_OTHER_CLOSED 2 +#define TTY_EXCLUSIVE 3 +#define TTY_DO_WRITE_WAKEUP 5 +#define TTY_LDISC_OPEN 11 +#define TTY_PTY_LOCK 16 +#define TTY_NO_WRITE_SPLIT 17 +#define TTY_HUPPED 18 +#define TTY_HUPPING 19 +#define TTY_LDISC_CHANGING 20 +#define TTY_LDISC_HALTED 22 static inline bool tty_io_nonblock(struct tty_struct *tty, struct file *file) { -- cgit v1.2.3 From 34d809f8b4ff68f63e8d7f71d93d150382c6bb8b Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Fri, 26 Nov 2021 09:15:58 +0100 Subject: tty: reformat TTY_DRIVER_ flags into kernel-doc We want to reference TTY_DRIVER_* flags in Documentation/ later in this series. But the current documentation in the TTY_DRIVER_*'s header does not allow that. Reformat it to kernel-doc using "DOC" directive and line-feeds, so that we can include it as it is. Signed-off-by: Jiri Slaby Link: https://lore.kernel.org/r/20211126081611.11001-11-jslaby@suse.cz Signed-off-by: Greg Kroah-Hartman --- include/linux/tty_driver.h | 90 ++++++++++++++++++++++++---------------------- 1 file changed, 47 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index 41274d551e28..4841d8069c07 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -492,49 +492,53 @@ static inline void tty_set_operations(struct tty_driver *driver, /* tty driver magic number */ #define TTY_DRIVER_MAGIC 0x5402 -/* - * tty driver flags - * - * TTY_DRIVER_RESET_TERMIOS --- requests the tty layer to reset the - * termios setting when the last process has closed the device. - * Used for PTY's, in particular. - * - * TTY_DRIVER_REAL_RAW --- if set, indicates that the driver will - * guarantee never to set any special character handling - * flags if ((IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || - * !INPCK)). That is, if there is no reason for the driver to - * send notifications of parity and break characters up to the - * line driver, it won't do so. This allows the line driver to - * optimize for this case if this flag is set. (Note that there - * is also a promise, if the above case is true, not to signal - * overruns, either.) - * - * TTY_DRIVER_DYNAMIC_DEV --- if set, the individual tty devices need - * to be registered with a call to tty_register_device() when the - * device is found in the system and unregistered with a call to - * tty_unregister_device() so the devices will be show up - * properly in sysfs. If not set, driver->num entries will be - * created by the tty core in sysfs when tty_register_driver() is - * called. This is to be used by drivers that have tty devices - * that can appear and disappear while the main tty driver is - * registered with the tty core. - * - * TTY_DRIVER_DEVPTS_MEM -- don't use the standard arrays, instead - * use dynamic memory keyed through the devpts filesystem. This - * is only applicable to the pty driver. - * - * TTY_DRIVER_HARDWARE_BREAK -- hardware handles break signals. Pass - * the requested timeout to the caller instead of using a simple - * on/off interface. - * - * TTY_DRIVER_DYNAMIC_ALLOC -- do not allocate structures which are - * needed per line for this driver as it would waste memory. - * The driver will take care. - * - * TTY_DRIVER_UNNUMBERED_NODE -- do not create numbered /dev nodes. In - * other words create /dev/ttyprintk and not /dev/ttyprintk0. - * Applicable only when a driver for a single tty device is - * being allocated. +/** + * DOC: TTY Driver Flags + * + * TTY_DRIVER_RESET_TERMIOS + * Requests the tty layer to reset the termios setting when the last + * process has closed the device. Used for PTYs, in particular. + * + * TTY_DRIVER_REAL_RAW + * Indicates that the driver will guarantee not to set any special + * character handling flags if this is set for the tty: + * + * ``(IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || !INPCK)`` + * + * That is, if there is no reason for the driver to + * send notifications of parity and break characters up to the line + * driver, it won't do so. This allows the line driver to optimize for + * this case if this flag is set. (Note that there is also a promise, if + * the above case is true, not to signal overruns, either.) + * + * TTY_DRIVER_DYNAMIC_DEV + * The individual tty devices need to be registered with a call to + * tty_register_device() when the device is found in the system and + * unregistered with a call to tty_unregister_device() so the devices will + * be show up properly in sysfs. If not set, all &tty_driver.num entries + * will be created by the tty core in sysfs when tty_register_driver() is + * called. This is to be used by drivers that have tty devices that can + * appear and disappear while the main tty driver is registered with the + * tty core. + * + * TTY_DRIVER_DEVPTS_MEM + * Don't use the standard arrays (&tty_driver.ttys and + * &tty_driver.termios), instead use dynamic memory keyed through the + * devpts filesystem. This is only applicable to the PTY driver. + * + * TTY_DRIVER_HARDWARE_BREAK + * Hardware handles break signals. Pass the requested timeout to the + * &tty_operations.break_ctl instead of using a simple on/off interface. + * + * TTY_DRIVER_DYNAMIC_ALLOC + * Do not allocate structures which are needed per line for this driver + * (&tty_driver.ports) as it would waste memory. The driver will take + * care. This is only applicable to the PTY driver. + * + * TTY_DRIVER_UNNUMBERED_NODE + * Do not create numbered ``/dev`` nodes. For example, create + * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a + * driver for a single tty device is being allocated. */ #define TTY_DRIVER_INSTALLED 0x0001 #define TTY_DRIVER_RESET_TERMIOS 0x0002 -- cgit v1.2.3 From df0e68c1e9945e2ee86d266ce45597bbd8299b06 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 17 Nov 2021 12:05:59 +0000 Subject: comedi: Move the main COMEDI headers Move the main COMEDI driver headers out of "drivers/comedi/" into new directory "include/linux/comedi/". These are "comedidev.h", "comedilib.h", "comedi_pci.h", "comedi_pcmcia.h", and "comedi_usb.h". Additionally, move the user-space API header "comedi.h" into "include/uapi/linux/" and add "WITH Linux-syscall-note" to its SPDX-License-Identifier. Update the "COMEDI DRIVERS" section of the MAINTAINERS file to account for these changes. Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20211117120604.117740-2-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 2 + drivers/comedi/comedi.h | 1528 -------------------- drivers/comedi/comedi_buf.c | 3 +- drivers/comedi/comedi_fops.c | 2 +- drivers/comedi/comedi_pci.c | 3 +- drivers/comedi/comedi_pci.h | 57 - drivers/comedi/comedi_pcmcia.c | 3 +- drivers/comedi/comedi_pcmcia.h | 49 - drivers/comedi/comedi_usb.c | 3 +- drivers/comedi/comedi_usb.h | 42 - drivers/comedi/comedidev.h | 1054 -------------- drivers/comedi/comedilib.h | 26 - drivers/comedi/drivers.c | 3 +- drivers/comedi/drivers/8255.c | 2 +- drivers/comedi/drivers/8255_pci.c | 3 +- drivers/comedi/drivers/addi_apci_1032.c | 2 +- drivers/comedi/drivers/addi_apci_1500.c | 2 +- drivers/comedi/drivers/addi_apci_1516.c | 2 +- drivers/comedi/drivers/addi_apci_1564.c | 2 +- drivers/comedi/drivers/addi_apci_16xx.c | 3 +- drivers/comedi/drivers/addi_apci_2032.c | 2 +- drivers/comedi/drivers/addi_apci_2200.c | 2 +- drivers/comedi/drivers/addi_apci_3120.c | 2 +- drivers/comedi/drivers/addi_apci_3501.c | 2 +- drivers/comedi/drivers/addi_apci_3xxx.c | 3 +- drivers/comedi/drivers/addi_watchdog.c | 2 +- drivers/comedi/drivers/adl_pci6208.c | 3 +- drivers/comedi/drivers/adl_pci7x3x.c | 3 +- drivers/comedi/drivers/adl_pci8164.c | 3 +- drivers/comedi/drivers/adl_pci9111.c | 3 +- drivers/comedi/drivers/adl_pci9118.c | 3 +- drivers/comedi/drivers/adq12b.c | 3 +- drivers/comedi/drivers/adv_pci1710.c | 3 +- drivers/comedi/drivers/adv_pci1720.c | 3 +- drivers/comedi/drivers/adv_pci1723.c | 3 +- drivers/comedi/drivers/adv_pci1724.c | 3 +- drivers/comedi/drivers/adv_pci1760.c | 3 +- drivers/comedi/drivers/adv_pci_dio.c | 3 +- drivers/comedi/drivers/aio_aio12_8.c | 2 +- drivers/comedi/drivers/aio_iiro_16.c | 3 +- drivers/comedi/drivers/amplc_dio200.c | 2 +- drivers/comedi/drivers/amplc_dio200_common.c | 3 +- drivers/comedi/drivers/amplc_dio200_pci.c | 3 +- drivers/comedi/drivers/amplc_pc236.c | 3 +- drivers/comedi/drivers/amplc_pc236_common.c | 3 +- drivers/comedi/drivers/amplc_pc263.c | 2 +- drivers/comedi/drivers/amplc_pci224.c | 3 +- drivers/comedi/drivers/amplc_pci230.c | 3 +- drivers/comedi/drivers/amplc_pci236.c | 3 +- drivers/comedi/drivers/amplc_pci263.c | 3 +- drivers/comedi/drivers/c6xdigio.c | 3 +- drivers/comedi/drivers/cb_das16_cs.c | 3 +- drivers/comedi/drivers/cb_pcidas.c | 3 +- drivers/comedi/drivers/cb_pcidas64.c | 3 +- drivers/comedi/drivers/cb_pcidda.c | 3 +- drivers/comedi/drivers/cb_pcimdas.c | 3 +- drivers/comedi/drivers/cb_pcimdda.c | 3 +- drivers/comedi/drivers/comedi_8254.c | 3 +- drivers/comedi/drivers/comedi_8255.c | 2 +- drivers/comedi/drivers/comedi_bond.c | 6 +- drivers/comedi/drivers/comedi_isadma.c | 3 +- drivers/comedi/drivers/comedi_parport.c | 3 +- drivers/comedi/drivers/comedi_test.c | 4 +- drivers/comedi/drivers/contec_pci_dio.c | 3 +- drivers/comedi/drivers/dac02.c | 3 +- drivers/comedi/drivers/daqboard2000.c | 3 +- drivers/comedi/drivers/das08.c | 3 +- drivers/comedi/drivers/das08_cs.c | 3 +- drivers/comedi/drivers/das08_isa.c | 2 +- drivers/comedi/drivers/das08_pci.c | 3 +- drivers/comedi/drivers/das16.c | 3 +- drivers/comedi/drivers/das16m1.c | 2 +- drivers/comedi/drivers/das1800.c | 3 +- drivers/comedi/drivers/das6402.c | 3 +- drivers/comedi/drivers/das800.c | 3 +- drivers/comedi/drivers/dmm32at.c | 2 +- drivers/comedi/drivers/dt2801.c | 2 +- drivers/comedi/drivers/dt2811.c | 3 +- drivers/comedi/drivers/dt2814.c | 3 +- drivers/comedi/drivers/dt2815.c | 3 +- drivers/comedi/drivers/dt2817.c | 2 +- drivers/comedi/drivers/dt282x.c | 3 +- drivers/comedi/drivers/dt3000.c | 3 +- drivers/comedi/drivers/dt9812.c | 3 +- drivers/comedi/drivers/dyna_pci10xx.c | 3 +- drivers/comedi/drivers/fl512.c | 3 +- drivers/comedi/drivers/gsc_hpdi.c | 3 +- drivers/comedi/drivers/icp_multi.c | 3 +- drivers/comedi/drivers/ii_pci20kc.c | 2 +- drivers/comedi/drivers/jr3_pci.c | 3 +- drivers/comedi/drivers/ke_counter.c | 3 +- drivers/comedi/drivers/me4000.c | 3 +- drivers/comedi/drivers/me_daq.c | 3 +- drivers/comedi/drivers/mf6x4.c | 3 +- drivers/comedi/drivers/mite.c | 3 +- drivers/comedi/drivers/mpc624.c | 3 +- drivers/comedi/drivers/multiq3.c | 3 +- drivers/comedi/drivers/ni_6527.c | 3 +- drivers/comedi/drivers/ni_65xx.c | 3 +- drivers/comedi/drivers/ni_660x.c | 3 +- drivers/comedi/drivers/ni_670x.c | 3 +- drivers/comedi/drivers/ni_at_a2150.c | 3 +- drivers/comedi/drivers/ni_at_ao.c | 3 +- drivers/comedi/drivers/ni_atmio.c | 3 +- drivers/comedi/drivers/ni_atmio16d.c | 2 +- drivers/comedi/drivers/ni_daq_700.c | 3 +- drivers/comedi/drivers/ni_daq_dio24.c | 2 +- drivers/comedi/drivers/ni_labpc.c | 3 +- drivers/comedi/drivers/ni_labpc_common.c | 3 +- drivers/comedi/drivers/ni_labpc_cs.c | 3 +- drivers/comedi/drivers/ni_labpc_isadma.c | 3 +- drivers/comedi/drivers/ni_labpc_pci.c | 3 +- drivers/comedi/drivers/ni_mio_cs.c | 2 +- drivers/comedi/drivers/ni_pcidio.c | 3 +- drivers/comedi/drivers/ni_pcimio.c | 4 +- drivers/comedi/drivers/ni_routes.c | 3 +- drivers/comedi/drivers/ni_routes.h | 2 +- .../comedi/drivers/ni_routing/ni_route_values.h | 2 +- drivers/comedi/drivers/ni_tio.h | 2 +- drivers/comedi/drivers/ni_usb6501.c | 3 +- drivers/comedi/drivers/pcl711.c | 3 +- drivers/comedi/drivers/pcl724.c | 2 +- drivers/comedi/drivers/pcl726.c | 3 +- drivers/comedi/drivers/pcl730.c | 2 +- drivers/comedi/drivers/pcl812.c | 3 +- drivers/comedi/drivers/pcl816.c | 3 +- drivers/comedi/drivers/pcl818.c | 3 +- drivers/comedi/drivers/pcm3724.c | 2 +- drivers/comedi/drivers/pcmad.c | 2 +- drivers/comedi/drivers/pcmda12.c | 2 +- drivers/comedi/drivers/pcmmio.c | 3 +- drivers/comedi/drivers/pcmuio.c | 3 +- drivers/comedi/drivers/quatech_daqp_cs.c | 3 +- drivers/comedi/drivers/rtd520.c | 3 +- drivers/comedi/drivers/rti800.c | 2 +- drivers/comedi/drivers/rti802.c | 2 +- drivers/comedi/drivers/s526.c | 2 +- drivers/comedi/drivers/s626.c | 3 +- drivers/comedi/drivers/ssv_dnp.c | 2 +- drivers/comedi/drivers/usbdux.c | 3 +- drivers/comedi/drivers/usbduxfast.c | 2 +- drivers/comedi/drivers/usbduxsigma.c | 3 +- drivers/comedi/drivers/vmk80xx.c | 3 +- drivers/comedi/kcomedilib/kcomedilib_main.c | 6 +- drivers/comedi/proc.c | 2 +- drivers/comedi/range.c | 2 +- include/linux/comedi/comedi_pci.h | 56 + include/linux/comedi/comedi_pcmcia.h | 48 + include/linux/comedi/comedi_usb.h | 41 + include/linux/comedi/comedidev.h | 1053 ++++++++++++++ include/linux/comedi/comedilib.h | 26 + include/uapi/linux/comedi.h | 1528 ++++++++++++++++++++ 152 files changed, 2897 insertions(+), 2999 deletions(-) delete mode 100644 drivers/comedi/comedi.h delete mode 100644 drivers/comedi/comedi_pci.h delete mode 100644 drivers/comedi/comedi_pcmcia.h delete mode 100644 drivers/comedi/comedi_usb.h delete mode 100644 drivers/comedi/comedidev.h delete mode 100644 drivers/comedi/comedilib.h create mode 100644 include/linux/comedi/comedi_pci.h create mode 100644 include/linux/comedi/comedi_pcmcia.h create mode 100644 include/linux/comedi/comedi_usb.h create mode 100644 include/linux/comedi/comedidev.h create mode 100644 include/linux/comedi/comedilib.h create mode 100644 include/uapi/linux/comedi.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..f9b50d136c90 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4713,6 +4713,8 @@ M: Ian Abbott M: H Hartley Sweeten S: Odd Fixes F: drivers/comedi/ +F: include/linux/comedi/ +F: include/uapi/linux/comedi.h COMMON CLK FRAMEWORK M: Michael Turquette diff --git a/drivers/comedi/comedi.h b/drivers/comedi/comedi.h deleted file mode 100644 index b5d00a006dbb..000000000000 --- a/drivers/comedi/comedi.h +++ /dev/null @@ -1,1528 +0,0 @@ -/* SPDX-License-Identifier: LGPL-2.0+ */ -/* - * comedi.h - * header file for COMEDI user API - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1998-2001 David A. Schleef - */ - -#ifndef _COMEDI_H -#define _COMEDI_H - -#define COMEDI_MAJORVERSION 0 -#define COMEDI_MINORVERSION 7 -#define COMEDI_MICROVERSION 76 -#define VERSION "0.7.76" - -/* comedi's major device number */ -#define COMEDI_MAJOR 98 - -/* - * maximum number of minor devices. This can be increased, although - * kernel structures are currently statically allocated, thus you - * don't want this to be much more than you actually use. - */ -#define COMEDI_NDEVICES 16 - -/* number of config options in the config structure */ -#define COMEDI_NDEVCONFOPTS 32 - -/* - * NOTE: 'comedi_config --init-data' is deprecated - * - * The following indexes in the config options were used by - * comedi_config to pass firmware blobs from user space to the - * comedi drivers. The request_firmware() hotplug interface is - * now used by all comedi drivers instead. - */ - -/* length of nth chunk of firmware data -*/ -#define COMEDI_DEVCONF_AUX_DATA3_LENGTH 25 -#define COMEDI_DEVCONF_AUX_DATA2_LENGTH 26 -#define COMEDI_DEVCONF_AUX_DATA1_LENGTH 27 -#define COMEDI_DEVCONF_AUX_DATA0_LENGTH 28 -/* most significant 32 bits of pointer address (if needed) */ -#define COMEDI_DEVCONF_AUX_DATA_HI 29 -/* least significant 32 bits of pointer address */ -#define COMEDI_DEVCONF_AUX_DATA_LO 30 -#define COMEDI_DEVCONF_AUX_DATA_LENGTH 31 /* total data length */ - -/* max length of device and driver names */ -#define COMEDI_NAMELEN 20 - -/* packs and unpacks a channel/range number */ - -#define CR_PACK(chan, rng, aref) \ - ((((aref) & 0x3) << 24) | (((rng) & 0xff) << 16) | (chan)) -#define CR_PACK_FLAGS(chan, range, aref, flags) \ - (CR_PACK(chan, range, aref) | ((flags) & CR_FLAGS_MASK)) - -#define CR_CHAN(a) ((a) & 0xffff) -#define CR_RANGE(a) (((a) >> 16) & 0xff) -#define CR_AREF(a) (((a) >> 24) & 0x03) - -#define CR_FLAGS_MASK 0xfc000000 -#define CR_ALT_FILTER 0x04000000 -#define CR_DITHER CR_ALT_FILTER -#define CR_DEGLITCH CR_ALT_FILTER -#define CR_ALT_SOURCE 0x08000000 -#define CR_EDGE 0x40000000 -#define CR_INVERT 0x80000000 - -#define AREF_GROUND 0x00 /* analog ref = analog ground */ -#define AREF_COMMON 0x01 /* analog ref = analog common */ -#define AREF_DIFF 0x02 /* analog ref = differential */ -#define AREF_OTHER 0x03 /* analog ref = other (undefined) */ - -/* counters -- these are arbitrary values */ -#define GPCT_RESET 0x0001 -#define GPCT_SET_SOURCE 0x0002 -#define GPCT_SET_GATE 0x0004 -#define GPCT_SET_DIRECTION 0x0008 -#define GPCT_SET_OPERATION 0x0010 -#define GPCT_ARM 0x0020 -#define GPCT_DISARM 0x0040 -#define GPCT_GET_INT_CLK_FRQ 0x0080 - -#define GPCT_INT_CLOCK 0x0001 -#define GPCT_EXT_PIN 0x0002 -#define GPCT_NO_GATE 0x0004 -#define GPCT_UP 0x0008 -#define GPCT_DOWN 0x0010 -#define GPCT_HWUD 0x0020 -#define GPCT_SIMPLE_EVENT 0x0040 -#define GPCT_SINGLE_PERIOD 0x0080 -#define GPCT_SINGLE_PW 0x0100 -#define GPCT_CONT_PULSE_OUT 0x0200 -#define GPCT_SINGLE_PULSE_OUT 0x0400 - -/* instructions */ - -#define INSN_MASK_WRITE 0x8000000 -#define INSN_MASK_READ 0x4000000 -#define INSN_MASK_SPECIAL 0x2000000 - -#define INSN_READ (0 | INSN_MASK_READ) -#define INSN_WRITE (1 | INSN_MASK_WRITE) -#define INSN_BITS (2 | INSN_MASK_READ | INSN_MASK_WRITE) -#define INSN_CONFIG (3 | INSN_MASK_READ | INSN_MASK_WRITE) -#define INSN_DEVICE_CONFIG (INSN_CONFIG | INSN_MASK_SPECIAL) -#define INSN_GTOD (4 | INSN_MASK_READ | INSN_MASK_SPECIAL) -#define INSN_WAIT (5 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) -#define INSN_INTTRIG (6 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) - -/* command flags */ -/* These flags are used in comedi_cmd structures */ - -#define CMDF_BOGUS 0x00000001 /* do the motions */ - -/* try to use a real-time interrupt while performing command */ -#define CMDF_PRIORITY 0x00000008 - -/* wake up on end-of-scan events */ -#define CMDF_WAKE_EOS 0x00000020 - -#define CMDF_WRITE 0x00000040 - -#define CMDF_RAWDATA 0x00000080 - -/* timer rounding definitions */ -#define CMDF_ROUND_MASK 0x00030000 -#define CMDF_ROUND_NEAREST 0x00000000 -#define CMDF_ROUND_DOWN 0x00010000 -#define CMDF_ROUND_UP 0x00020000 -#define CMDF_ROUND_UP_NEXT 0x00030000 - -#define COMEDI_EV_START 0x00040000 -#define COMEDI_EV_SCAN_BEGIN 0x00080000 -#define COMEDI_EV_CONVERT 0x00100000 -#define COMEDI_EV_SCAN_END 0x00200000 -#define COMEDI_EV_STOP 0x00400000 - -/* compatibility definitions */ -#define TRIG_BOGUS CMDF_BOGUS -#define TRIG_RT CMDF_PRIORITY -#define TRIG_WAKE_EOS CMDF_WAKE_EOS -#define TRIG_WRITE CMDF_WRITE -#define TRIG_ROUND_MASK CMDF_ROUND_MASK -#define TRIG_ROUND_NEAREST CMDF_ROUND_NEAREST -#define TRIG_ROUND_DOWN CMDF_ROUND_DOWN -#define TRIG_ROUND_UP CMDF_ROUND_UP -#define TRIG_ROUND_UP_NEXT CMDF_ROUND_UP_NEXT - -/* trigger sources */ - -#define TRIG_ANY 0xffffffff -#define TRIG_INVALID 0x00000000 - -#define TRIG_NONE 0x00000001 /* never trigger */ -#define TRIG_NOW 0x00000002 /* trigger now + N ns */ -#define TRIG_FOLLOW 0x00000004 /* trigger on next lower level trig */ -#define TRIG_TIME 0x00000008 /* trigger at time N ns */ -#define TRIG_TIMER 0x00000010 /* trigger at rate N ns */ -#define TRIG_COUNT 0x00000020 /* trigger when count reaches N */ -#define TRIG_EXT 0x00000040 /* trigger on external signal N */ -#define TRIG_INT 0x00000080 /* trigger on comedi-internal signal N */ -#define TRIG_OTHER 0x00000100 /* driver defined */ - -/* subdevice flags */ - -#define SDF_BUSY 0x0001 /* device is busy */ -#define SDF_BUSY_OWNER 0x0002 /* device is busy with your job */ -#define SDF_LOCKED 0x0004 /* subdevice is locked */ -#define SDF_LOCK_OWNER 0x0008 /* you own lock */ -#define SDF_MAXDATA 0x0010 /* maxdata depends on channel */ -#define SDF_FLAGS 0x0020 /* flags depend on channel */ -#define SDF_RANGETYPE 0x0040 /* range type depends on channel */ -#define SDF_PWM_COUNTER 0x0080 /* PWM can automatically switch off */ -#define SDF_PWM_HBRIDGE 0x0100 /* PWM is signed (H-bridge) */ -#define SDF_CMD 0x1000 /* can do commands (deprecated) */ -#define SDF_SOFT_CALIBRATED 0x2000 /* subdevice uses software calibration */ -#define SDF_CMD_WRITE 0x4000 /* can do output commands */ -#define SDF_CMD_READ 0x8000 /* can do input commands */ - -/* subdevice can be read (e.g. analog input) */ -#define SDF_READABLE 0x00010000 -/* subdevice can be written (e.g. analog output) */ -#define SDF_WRITABLE 0x00020000 -#define SDF_WRITEABLE SDF_WRITABLE /* spelling error in API */ -/* subdevice does not have externally visible lines */ -#define SDF_INTERNAL 0x00040000 -#define SDF_GROUND 0x00100000 /* can do aref=ground */ -#define SDF_COMMON 0x00200000 /* can do aref=common */ -#define SDF_DIFF 0x00400000 /* can do aref=diff */ -#define SDF_OTHER 0x00800000 /* can do aref=other */ -#define SDF_DITHER 0x01000000 /* can do dithering */ -#define SDF_DEGLITCH 0x02000000 /* can do deglitching */ -#define SDF_MMAP 0x04000000 /* can do mmap() */ -#define SDF_RUNNING 0x08000000 /* subdevice is acquiring data */ -#define SDF_LSAMPL 0x10000000 /* subdevice uses 32-bit samples */ -#define SDF_PACKED 0x20000000 /* subdevice can do packed DIO */ - -/* subdevice types */ - -/** - * enum comedi_subdevice_type - COMEDI subdevice types - * @COMEDI_SUBD_UNUSED: Unused subdevice. - * @COMEDI_SUBD_AI: Analog input. - * @COMEDI_SUBD_AO: Analog output. - * @COMEDI_SUBD_DI: Digital input. - * @COMEDI_SUBD_DO: Digital output. - * @COMEDI_SUBD_DIO: Digital input/output. - * @COMEDI_SUBD_COUNTER: Counter. - * @COMEDI_SUBD_TIMER: Timer. - * @COMEDI_SUBD_MEMORY: Memory, EEPROM, DPRAM. - * @COMEDI_SUBD_CALIB: Calibration DACs. - * @COMEDI_SUBD_PROC: Processor, DSP. - * @COMEDI_SUBD_SERIAL: Serial I/O. - * @COMEDI_SUBD_PWM: Pulse-Width Modulation output. - */ -enum comedi_subdevice_type { - COMEDI_SUBD_UNUSED, - COMEDI_SUBD_AI, - COMEDI_SUBD_AO, - COMEDI_SUBD_DI, - COMEDI_SUBD_DO, - COMEDI_SUBD_DIO, - COMEDI_SUBD_COUNTER, - COMEDI_SUBD_TIMER, - COMEDI_SUBD_MEMORY, - COMEDI_SUBD_CALIB, - COMEDI_SUBD_PROC, - COMEDI_SUBD_SERIAL, - COMEDI_SUBD_PWM -}; - -/* configuration instructions */ - -/** - * enum comedi_io_direction - COMEDI I/O directions - * @COMEDI_INPUT: Input. - * @COMEDI_OUTPUT: Output. - * @COMEDI_OPENDRAIN: Open-drain (or open-collector) output. - * - * These are used by the %INSN_CONFIG_DIO_QUERY configuration instruction to - * report a direction. They may also be used in other places where a direction - * needs to be specified. - */ -enum comedi_io_direction { - COMEDI_INPUT = 0, - COMEDI_OUTPUT = 1, - COMEDI_OPENDRAIN = 2 -}; - -/** - * enum configuration_ids - COMEDI configuration instruction codes - * @INSN_CONFIG_DIO_INPUT: Configure digital I/O as input. - * @INSN_CONFIG_DIO_OUTPUT: Configure digital I/O as output. - * @INSN_CONFIG_DIO_OPENDRAIN: Configure digital I/O as open-drain (or open - * collector) output. - * @INSN_CONFIG_ANALOG_TRIG: Configure analog trigger. - * @INSN_CONFIG_ALT_SOURCE: Configure alternate input source. - * @INSN_CONFIG_DIGITAL_TRIG: Configure digital trigger. - * @INSN_CONFIG_BLOCK_SIZE: Configure block size for DMA transfers. - * @INSN_CONFIG_TIMER_1: Configure divisor for external clock. - * @INSN_CONFIG_FILTER: Configure a filter. - * @INSN_CONFIG_CHANGE_NOTIFY: Configure change notification for digital - * inputs. (New drivers should use - * %INSN_CONFIG_DIGITAL_TRIG instead.) - * @INSN_CONFIG_SERIAL_CLOCK: Configure clock for serial I/O. - * @INSN_CONFIG_BIDIRECTIONAL_DATA: Send and receive byte over serial I/O. - * @INSN_CONFIG_DIO_QUERY: Query direction of digital I/O channel. - * @INSN_CONFIG_PWM_OUTPUT: Configure pulse-width modulator output. - * @INSN_CONFIG_GET_PWM_OUTPUT: Get pulse-width modulator output configuration. - * @INSN_CONFIG_ARM: Arm a subdevice or channel. - * @INSN_CONFIG_DISARM: Disarm a subdevice or channel. - * @INSN_CONFIG_GET_COUNTER_STATUS: Get counter status. - * @INSN_CONFIG_RESET: Reset a subdevice or channel. - * @INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR: Configure counter/timer as - * single pulse generator. - * @INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR: Configure counter/timer as - * pulse train generator. - * @INSN_CONFIG_GPCT_QUADRATURE_ENCODER: Configure counter as a quadrature - * encoder. - * @INSN_CONFIG_SET_GATE_SRC: Set counter/timer gate source. - * @INSN_CONFIG_GET_GATE_SRC: Get counter/timer gate source. - * @INSN_CONFIG_SET_CLOCK_SRC: Set counter/timer master clock source. - * @INSN_CONFIG_GET_CLOCK_SRC: Get counter/timer master clock source. - * @INSN_CONFIG_SET_OTHER_SRC: Set counter/timer "other" source. - * @INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE: Get size (in bytes) of subdevice's - * on-board FIFOs used during streaming - * input/output. - * @INSN_CONFIG_SET_COUNTER_MODE: Set counter/timer mode. - * @INSN_CONFIG_8254_SET_MODE: (Deprecated) Same as - * %INSN_CONFIG_SET_COUNTER_MODE. - * @INSN_CONFIG_8254_READ_STATUS: Read status of 8254 counter channel. - * @INSN_CONFIG_SET_ROUTING: Set routing for a channel. - * @INSN_CONFIG_GET_ROUTING: Get routing for a channel. - * @INSN_CONFIG_PWM_SET_PERIOD: Set PWM period in nanoseconds. - * @INSN_CONFIG_PWM_GET_PERIOD: Get PWM period in nanoseconds. - * @INSN_CONFIG_GET_PWM_STATUS: Get PWM status. - * @INSN_CONFIG_PWM_SET_H_BRIDGE: Set PWM H bridge duty cycle and polarity for - * a relay simultaneously. - * @INSN_CONFIG_PWM_GET_H_BRIDGE: Get PWM H bridge duty cycle and polarity. - * @INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS: Get the hardware timing restraints, - * regardless of trigger sources. - */ -enum configuration_ids { - INSN_CONFIG_DIO_INPUT = COMEDI_INPUT, - INSN_CONFIG_DIO_OUTPUT = COMEDI_OUTPUT, - INSN_CONFIG_DIO_OPENDRAIN = COMEDI_OPENDRAIN, - INSN_CONFIG_ANALOG_TRIG = 16, -/* INSN_CONFIG_WAVEFORM = 17, */ -/* INSN_CONFIG_TRIG = 18, */ -/* INSN_CONFIG_COUNTER = 19, */ - INSN_CONFIG_ALT_SOURCE = 20, - INSN_CONFIG_DIGITAL_TRIG = 21, - INSN_CONFIG_BLOCK_SIZE = 22, - INSN_CONFIG_TIMER_1 = 23, - INSN_CONFIG_FILTER = 24, - INSN_CONFIG_CHANGE_NOTIFY = 25, - - INSN_CONFIG_SERIAL_CLOCK = 26, /*ALPHA*/ - INSN_CONFIG_BIDIRECTIONAL_DATA = 27, - INSN_CONFIG_DIO_QUERY = 28, - INSN_CONFIG_PWM_OUTPUT = 29, - INSN_CONFIG_GET_PWM_OUTPUT = 30, - INSN_CONFIG_ARM = 31, - INSN_CONFIG_DISARM = 32, - INSN_CONFIG_GET_COUNTER_STATUS = 33, - INSN_CONFIG_RESET = 34, - INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR = 1001, - INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR = 1002, - INSN_CONFIG_GPCT_QUADRATURE_ENCODER = 1003, - INSN_CONFIG_SET_GATE_SRC = 2001, - INSN_CONFIG_GET_GATE_SRC = 2002, - INSN_CONFIG_SET_CLOCK_SRC = 2003, - INSN_CONFIG_GET_CLOCK_SRC = 2004, - INSN_CONFIG_SET_OTHER_SRC = 2005, - INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE = 2006, - INSN_CONFIG_SET_COUNTER_MODE = 4097, - INSN_CONFIG_8254_SET_MODE = INSN_CONFIG_SET_COUNTER_MODE, - INSN_CONFIG_8254_READ_STATUS = 4098, - INSN_CONFIG_SET_ROUTING = 4099, - INSN_CONFIG_GET_ROUTING = 4109, - INSN_CONFIG_PWM_SET_PERIOD = 5000, - INSN_CONFIG_PWM_GET_PERIOD = 5001, - INSN_CONFIG_GET_PWM_STATUS = 5002, - INSN_CONFIG_PWM_SET_H_BRIDGE = 5003, - INSN_CONFIG_PWM_GET_H_BRIDGE = 5004, - INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS = 5005, -}; - -/** - * enum device_configuration_ids - COMEDI configuration instruction codes global - * to an entire device. - * @INSN_DEVICE_CONFIG_TEST_ROUTE: Validate the possibility of a - * globally-named route - * @INSN_DEVICE_CONFIG_CONNECT_ROUTE: Connect a globally-named route - * @INSN_DEVICE_CONFIG_DISCONNECT_ROUTE:Disconnect a globally-named route - * @INSN_DEVICE_CONFIG_GET_ROUTES: Get a list of all globally-named routes - * that are valid for a particular device. - */ -enum device_config_route_ids { - INSN_DEVICE_CONFIG_TEST_ROUTE = 0, - INSN_DEVICE_CONFIG_CONNECT_ROUTE = 1, - INSN_DEVICE_CONFIG_DISCONNECT_ROUTE = 2, - INSN_DEVICE_CONFIG_GET_ROUTES = 3, -}; - -/** - * enum comedi_digital_trig_op - operations for configuring a digital trigger - * @COMEDI_DIGITAL_TRIG_DISABLE: Return digital trigger to its default, - * inactive, unconfigured state. - * @COMEDI_DIGITAL_TRIG_ENABLE_EDGES: Set rising and/or falling edge inputs - * that each can fire the trigger. - * @COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: Set a combination of high and/or low - * level inputs that can fire the trigger. - * - * These are used with the %INSN_CONFIG_DIGITAL_TRIG configuration instruction. - * The data for the configuration instruction is as follows... - * - * data[%0] = %INSN_CONFIG_DIGITAL_TRIG - * - * data[%1] = trigger ID - * - * data[%2] = configuration operation - * - * data[%3] = configuration parameter 1 - * - * data[%4] = configuration parameter 2 - * - * data[%5] = configuration parameter 3 - * - * The trigger ID (data[%1]) is used to differentiate multiple digital triggers - * belonging to the same subdevice. The configuration operation (data[%2]) is - * one of the enum comedi_digital_trig_op values. The configuration - * parameters (data[%3], data[%4], and data[%5]) depend on the operation; they - * are not used with %COMEDI_DIGITAL_TRIG_DISABLE. - * - * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES and %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, - * configuration parameter 1 (data[%3]) contains a "left-shift" value that - * specifies the input corresponding to bit 0 of configuration parameters 2 - * and 3. This is useful if the trigger has more than 32 inputs. - * - * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES, configuration parameter 2 (data[%4]) - * specifies which of up to 32 inputs have rising-edge sensitivity, and - * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs - * have falling-edge sensitivity that can fire the trigger. - * - * For %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, configuration parameter 2 (data[%4]) - * specifies which of up to 32 inputs must be at a high level, and - * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs - * must be at a low level for the trigger to fire. - * - * Some sequences of %INSN_CONFIG_DIGITAL_TRIG instructions may have a (partly) - * accumulative effect, depending on the low-level driver. This is useful - * when setting up a trigger that has more than 32 inputs, or has a combination - * of edge- and level-triggered inputs. - */ -enum comedi_digital_trig_op { - COMEDI_DIGITAL_TRIG_DISABLE = 0, - COMEDI_DIGITAL_TRIG_ENABLE_EDGES = 1, - COMEDI_DIGITAL_TRIG_ENABLE_LEVELS = 2 -}; - -/** - * enum comedi_support_level - support level for a COMEDI feature - * @COMEDI_UNKNOWN_SUPPORT: Unspecified support for feature. - * @COMEDI_SUPPORTED: Feature is supported. - * @COMEDI_UNSUPPORTED: Feature is unsupported. - */ -enum comedi_support_level { - COMEDI_UNKNOWN_SUPPORT = 0, - COMEDI_SUPPORTED, - COMEDI_UNSUPPORTED -}; - -/** - * enum comedi_counter_status_flags - counter status bits - * @COMEDI_COUNTER_ARMED: Counter is armed. - * @COMEDI_COUNTER_COUNTING: Counter is counting. - * @COMEDI_COUNTER_TERMINAL_COUNT: Counter reached terminal count. - * - * These bitwise values are used by the %INSN_CONFIG_GET_COUNTER_STATUS - * configuration instruction to report the status of a counter. - */ -enum comedi_counter_status_flags { - COMEDI_COUNTER_ARMED = 0x1, - COMEDI_COUNTER_COUNTING = 0x2, - COMEDI_COUNTER_TERMINAL_COUNT = 0x4, -}; - -/* ioctls */ - -#define CIO 'd' -#define COMEDI_DEVCONFIG _IOW(CIO, 0, struct comedi_devconfig) -#define COMEDI_DEVINFO _IOR(CIO, 1, struct comedi_devinfo) -#define COMEDI_SUBDINFO _IOR(CIO, 2, struct comedi_subdinfo) -#define COMEDI_CHANINFO _IOR(CIO, 3, struct comedi_chaninfo) -/* _IOWR(CIO, 4, ...) is reserved */ -#define COMEDI_LOCK _IO(CIO, 5) -#define COMEDI_UNLOCK _IO(CIO, 6) -#define COMEDI_CANCEL _IO(CIO, 7) -#define COMEDI_RANGEINFO _IOR(CIO, 8, struct comedi_rangeinfo) -#define COMEDI_CMD _IOR(CIO, 9, struct comedi_cmd) -#define COMEDI_CMDTEST _IOR(CIO, 10, struct comedi_cmd) -#define COMEDI_INSNLIST _IOR(CIO, 11, struct comedi_insnlist) -#define COMEDI_INSN _IOR(CIO, 12, struct comedi_insn) -#define COMEDI_BUFCONFIG _IOR(CIO, 13, struct comedi_bufconfig) -#define COMEDI_BUFINFO _IOWR(CIO, 14, struct comedi_bufinfo) -#define COMEDI_POLL _IO(CIO, 15) -#define COMEDI_SETRSUBD _IO(CIO, 16) -#define COMEDI_SETWSUBD _IO(CIO, 17) - -/* structures */ - -/** - * struct comedi_insn - COMEDI instruction - * @insn: COMEDI instruction type (%INSN_xxx). - * @n: Length of @data[]. - * @data: Pointer to data array operated on by the instruction. - * @subdev: Subdevice index. - * @chanspec: A packed "chanspec" value consisting of channel number, - * analog range index, analog reference type, and flags. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_INSN ioctl, and indirectly with the - * %COMEDI_INSNLIST ioctl. - */ -struct comedi_insn { - unsigned int insn; - unsigned int n; - unsigned int __user *data; - unsigned int subdev; - unsigned int chanspec; - unsigned int unused[3]; -}; - -/** - * struct comedi_insnlist - list of COMEDI instructions - * @n_insns: Number of COMEDI instructions. - * @insns: Pointer to array COMEDI instructions. - * - * This is used with the %COMEDI_INSNLIST ioctl. - */ -struct comedi_insnlist { - unsigned int n_insns; - struct comedi_insn __user *insns; -}; - -/** - * struct comedi_cmd - COMEDI asynchronous acquisition command details - * @subdev: Subdevice index. - * @flags: Command flags (%CMDF_xxx). - * @start_src: "Start acquisition" trigger source (%TRIG_xxx). - * @start_arg: "Start acquisition" trigger argument. - * @scan_begin_src: "Scan begin" trigger source. - * @scan_begin_arg: "Scan begin" trigger argument. - * @convert_src: "Convert" trigger source. - * @convert_arg: "Convert" trigger argument. - * @scan_end_src: "Scan end" trigger source. - * @scan_end_arg: "Scan end" trigger argument. - * @stop_src: "Stop acquisition" trigger source. - * @stop_arg: "Stop acquisition" trigger argument. - * @chanlist: Pointer to array of "chanspec" values, containing a - * sequence of channel numbers packed with analog range - * index, etc. - * @chanlist_len: Number of channels in sequence. - * @data: Pointer to miscellaneous set-up data (not used). - * @data_len: Length of miscellaneous set-up data. - * - * This is used with the %COMEDI_CMD or %COMEDI_CMDTEST ioctl to set-up - * or validate an asynchronous acquisition command. The ioctl may modify - * the &struct comedi_cmd and copy it back to the caller. - * - * Optional command @flags values that can be ORed together... - * - * %CMDF_BOGUS - makes %COMEDI_CMD ioctl return error %EAGAIN instead of - * starting the command. - * - * %CMDF_PRIORITY - requests "hard real-time" processing (which is not - * supported in this version of COMEDI). - * - * %CMDF_WAKE_EOS - requests the command makes data available for reading - * after every "scan" period. - * - * %CMDF_WRITE - marks the command as being in the "write" (to device) - * direction. This does not need to be specified by the caller unless the - * subdevice supports commands in either direction. - * - * %CMDF_RAWDATA - prevents the command from "munging" the data between the - * COMEDI sample format and the raw hardware sample format. - * - * %CMDF_ROUND_NEAREST - requests timing periods to be rounded to nearest - * supported values. - * - * %CMDF_ROUND_DOWN - requests timing periods to be rounded down to supported - * values (frequencies rounded up). - * - * %CMDF_ROUND_UP - requests timing periods to be rounded up to supported - * values (frequencies rounded down). - * - * Trigger source values for @start_src, @scan_begin_src, @convert_src, - * @scan_end_src, and @stop_src... - * - * %TRIG_ANY - "all ones" value used to test which trigger sources are - * supported. - * - * %TRIG_INVALID - "all zeroes" value used to indicate that all requested - * trigger sources are invalid. - * - * %TRIG_NONE - never trigger (often used as a @stop_src value). - * - * %TRIG_NOW - trigger after '_arg' nanoseconds. - * - * %TRIG_FOLLOW - trigger follows another event. - * - * %TRIG_TIMER - trigger every '_arg' nanoseconds. - * - * %TRIG_COUNT - trigger when count '_arg' is reached. - * - * %TRIG_EXT - trigger on external signal specified by '_arg'. - * - * %TRIG_INT - trigger on internal, software trigger specified by '_arg'. - * - * %TRIG_OTHER - trigger on other, driver-defined signal specified by '_arg'. - */ -struct comedi_cmd { - unsigned int subdev; - unsigned int flags; - - unsigned int start_src; - unsigned int start_arg; - - unsigned int scan_begin_src; - unsigned int scan_begin_arg; - - unsigned int convert_src; - unsigned int convert_arg; - - unsigned int scan_end_src; - unsigned int scan_end_arg; - - unsigned int stop_src; - unsigned int stop_arg; - - unsigned int *chanlist; - unsigned int chanlist_len; - - short __user *data; - unsigned int data_len; -}; - -/** - * struct comedi_chaninfo - used to retrieve per-channel information - * @subdev: Subdevice index. - * @maxdata_list: Optional pointer to per-channel maximum data values. - * @flaglist: Optional pointer to per-channel flags. - * @rangelist: Optional pointer to per-channel range types. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_CHANINFO ioctl to get per-channel information - * for the subdevice. Use of this requires knowledge of the number of channels - * and subdevice flags obtained using the %COMEDI_SUBDINFO ioctl. - * - * The @maxdata_list member must be %NULL unless the %SDF_MAXDATA subdevice - * flag is set. The @flaglist member must be %NULL unless the %SDF_FLAGS - * subdevice flag is set. The @rangelist member must be %NULL unless the - * %SDF_RANGETYPE subdevice flag is set. Otherwise, the arrays they point to - * must be at least as long as the number of channels. - */ -struct comedi_chaninfo { - unsigned int subdev; - unsigned int __user *maxdata_list; - unsigned int __user *flaglist; - unsigned int __user *rangelist; - unsigned int unused[4]; -}; - -/** - * struct comedi_rangeinfo - used to retrieve the range table for a channel - * @range_type: Encodes subdevice index (bits 27:24), channel index - * (bits 23:16) and range table length (bits 15:0). - * @range_ptr: Pointer to array of @struct comedi_krange to be filled - * in with the range table for the channel or subdevice. - * - * This is used with the %COMEDI_RANGEINFO ioctl to retrieve the range table - * for a specific channel (if the subdevice has the %SDF_RANGETYPE flag set to - * indicate that the range table depends on the channel), or for the subdevice - * as a whole (if the %SDF_RANGETYPE flag is clear, indicating the range table - * is shared by all channels). - * - * The @range_type value is an input to the ioctl and comes from a previous - * use of the %COMEDI_SUBDINFO ioctl (if the %SDF_RANGETYPE flag is clear), - * or the %COMEDI_CHANINFO ioctl (if the %SDF_RANGETYPE flag is set). - */ -struct comedi_rangeinfo { - unsigned int range_type; - void __user *range_ptr; -}; - -/** - * struct comedi_krange - describes a range in a range table - * @min: Minimum value in millionths (1e-6) of a unit. - * @max: Maximum value in millionths (1e-6) of a unit. - * @flags: Indicates the units (in bits 7:0) OR'ed with optional flags. - * - * A range table is associated with a single channel, or with all channels in a - * subdevice, and a list of one or more ranges. A %struct comedi_krange - * describes the physical range of units for one of those ranges. Sample - * values in COMEDI are unsigned from %0 up to some 'maxdata' value. The - * mapping from sample values to physical units is assumed to be nomimally - * linear (for the purpose of describing the range), with sample value %0 - * mapping to @min, and the 'maxdata' sample value mapping to @max. - * - * The currently defined units are %UNIT_volt (%0), %UNIT_mA (%1), and - * %UNIT_none (%2). The @min and @max values are the physical range multiplied - * by 1e6, so a @max value of %1000000 (with %UNIT_volt) represents a maximal - * value of 1 volt. - * - * The only defined flag value is %RF_EXTERNAL (%0x100), indicating that the - * range needs to be multiplied by an external reference. - */ -struct comedi_krange { - int min; - int max; - unsigned int flags; -}; - -/** - * struct comedi_subdinfo - used to retrieve information about a subdevice - * @type: Type of subdevice from &enum comedi_subdevice_type. - * @n_chan: Number of channels the subdevice supports. - * @subd_flags: A mixture of static and dynamic flags describing - * aspects of the subdevice and its current state. - * @timer_type: Timer type. Always set to %5 ("nanosecond timer"). - * @len_chanlist: Maximum length of a channel list if the subdevice - * supports asynchronous acquisition commands. - * @maxdata: Maximum sample value for all channels if the - * %SDF_MAXDATA subdevice flag is clear. - * @flags: Channel flags for all channels if the %SDF_FLAGS - * subdevice flag is clear. - * @range_type: The range type for all channels if the %SDF_RANGETYPE - * subdevice flag is clear. Encodes the subdevice index - * (bits 27:24), a dummy channel index %0 (bits 23:16), - * and the range table length (bits 15:0). - * @settling_time_0: Not used. - * @insn_bits_support: Set to %COMEDI_SUPPORTED if the subdevice supports the - * %INSN_BITS instruction, or to %COMEDI_UNSUPPORTED if it - * does not. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_SUBDINFO ioctl which copies an array of - * &struct comedi_subdinfo back to user space, with one element per subdevice. - * Use of this requires knowledge of the number of subdevices obtained from - * the %COMEDI_DEVINFO ioctl. - * - * These are the @subd_flags values that may be ORed together... - * - * %SDF_BUSY - the subdevice is busy processing an asynchronous command or a - * synchronous instruction. - * - * %SDF_BUSY_OWNER - the subdevice is busy processing an asynchronous - * acquisition command started on the current file object (the file object - * issuing the %COMEDI_SUBDINFO ioctl). - * - * %SDF_LOCKED - the subdevice is locked by a %COMEDI_LOCK ioctl. - * - * %SDF_LOCK_OWNER - the subdevice is locked by a %COMEDI_LOCK ioctl from the - * current file object. - * - * %SDF_MAXDATA - maximum sample values are channel-specific. - * - * %SDF_FLAGS - channel flags are channel-specific. - * - * %SDF_RANGETYPE - range types are channel-specific. - * - * %SDF_PWM_COUNTER - PWM can switch off automatically. - * - * %SDF_PWM_HBRIDGE - or PWM is signed (H-bridge). - * - * %SDF_CMD - the subdevice supports asynchronous commands. - * - * %SDF_SOFT_CALIBRATED - the subdevice uses software calibration. - * - * %SDF_CMD_WRITE - the subdevice supports asynchronous commands in the output - * ("write") direction. - * - * %SDF_CMD_READ - the subdevice supports asynchronous commands in the input - * ("read") direction. - * - * %SDF_READABLE - the subdevice is readable (e.g. analog input). - * - * %SDF_WRITABLE (aliased as %SDF_WRITEABLE) - the subdevice is writable (e.g. - * analog output). - * - * %SDF_INTERNAL - the subdevice has no externally visible lines. - * - * %SDF_GROUND - the subdevice can use ground as an analog reference. - * - * %SDF_COMMON - the subdevice can use a common analog reference. - * - * %SDF_DIFF - the subdevice can use differential inputs (or outputs). - * - * %SDF_OTHER - the subdevice can use some other analog reference. - * - * %SDF_DITHER - the subdevice can do dithering. - * - * %SDF_DEGLITCH - the subdevice can do deglitching. - * - * %SDF_MMAP - this is never set. - * - * %SDF_RUNNING - an asynchronous command is still running. - * - * %SDF_LSAMPL - the subdevice uses "long" (32-bit) samples (for asynchronous - * command data). - * - * %SDF_PACKED - the subdevice packs several DIO samples into a single sample - * (for asynchronous command data). - * - * No "channel flags" (@flags) values are currently defined. - */ -struct comedi_subdinfo { - unsigned int type; - unsigned int n_chan; - unsigned int subd_flags; - unsigned int timer_type; - unsigned int len_chanlist; - unsigned int maxdata; - unsigned int flags; - unsigned int range_type; - unsigned int settling_time_0; - unsigned int insn_bits_support; - unsigned int unused[8]; -}; - -/** - * struct comedi_devinfo - used to retrieve information about a COMEDI device - * @version_code: COMEDI version code. - * @n_subdevs: Number of subdevices the device has. - * @driver_name: Null-terminated COMEDI driver name. - * @board_name: Null-terminated COMEDI board name. - * @read_subdevice: Index of the current "read" subdevice (%-1 if none). - * @write_subdevice: Index of the current "write" subdevice (%-1 if none). - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_DEVINFO ioctl to get basic information about - * the device. - */ -struct comedi_devinfo { - unsigned int version_code; - unsigned int n_subdevs; - char driver_name[COMEDI_NAMELEN]; - char board_name[COMEDI_NAMELEN]; - int read_subdevice; - int write_subdevice; - int unused[30]; -}; - -/** - * struct comedi_devconfig - used to configure a legacy COMEDI device - * @board_name: Null-terminated string specifying the type of board - * to configure. - * @options: An array of integer configuration options. - * - * This is used with the %COMEDI_DEVCONFIG ioctl to configure a "legacy" COMEDI - * device, such as an ISA card. Not all COMEDI drivers support this. Those - * that do either expect the specified board name to match one of a list of - * names registered with the COMEDI core, or expect the specified board name - * to match the COMEDI driver name itself. The configuration options are - * handled in a driver-specific manner. - */ -struct comedi_devconfig { - char board_name[COMEDI_NAMELEN]; - int options[COMEDI_NDEVCONFOPTS]; -}; - -/** - * struct comedi_bufconfig - used to set or get buffer size for a subdevice - * @subdevice: Subdevice index. - * @flags: Not used. - * @maximum_size: Maximum allowed buffer size. - * @size: Buffer size. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_BUFCONFIG ioctl to get or configure the - * maximum buffer size and current buffer size for a COMEDI subdevice that - * supports asynchronous commands. If the subdevice does not support - * asynchronous commands, @maximum_size and @size are ignored and set to 0. - * - * On ioctl input, non-zero values of @maximum_size and @size specify a - * new maximum size and new current size (in bytes), respectively. These - * will by rounded up to a multiple of %PAGE_SIZE. Specifying a new maximum - * size requires admin capabilities. - * - * On ioctl output, @maximum_size and @size and set to the current maximum - * buffer size and current buffer size, respectively. - */ -struct comedi_bufconfig { - unsigned int subdevice; - unsigned int flags; - - unsigned int maximum_size; - unsigned int size; - - unsigned int unused[4]; -}; - -/** - * struct comedi_bufinfo - used to manipulate buffer position for a subdevice - * @subdevice: Subdevice index. - * @bytes_read: Specify amount to advance read position for an - * asynchronous command in the input ("read") direction. - * @buf_write_ptr: Current write position (index) within the buffer. - * @buf_read_ptr: Current read position (index) within the buffer. - * @buf_write_count: Total amount written, modulo 2^32. - * @buf_read_count: Total amount read, modulo 2^32. - * @bytes_written: Specify amount to advance write position for an - * asynchronous command in the output ("write") direction. - * @unused: Reserved for future use. - * - * This is used with the %COMEDI_BUFINFO ioctl to optionally advance the - * current read or write position in an asynchronous acquisition data buffer, - * and to get the current read and write positions in the buffer. - */ -struct comedi_bufinfo { - unsigned int subdevice; - unsigned int bytes_read; - - unsigned int buf_write_ptr; - unsigned int buf_read_ptr; - unsigned int buf_write_count; - unsigned int buf_read_count; - - unsigned int bytes_written; - - unsigned int unused[4]; -}; - -/* range stuff */ - -#define __RANGE(a, b) ((((a) & 0xffff) << 16) | ((b) & 0xffff)) - -#define RANGE_OFFSET(a) (((a) >> 16) & 0xffff) -#define RANGE_LENGTH(b) ((b) & 0xffff) - -#define RF_UNIT(flags) ((flags) & 0xff) -#define RF_EXTERNAL 0x100 - -#define UNIT_volt 0 -#define UNIT_mA 1 -#define UNIT_none 2 - -#define COMEDI_MIN_SPEED 0xffffffffu - -/**********************************************************/ -/* everything after this line is ALPHA */ -/**********************************************************/ - -/* - * 8254 specific configuration. - * - * It supports two config commands: - * - * 0 ID: INSN_CONFIG_SET_COUNTER_MODE - * 1 8254 Mode - * I8254_MODE0, I8254_MODE1, ..., I8254_MODE5 - * OR'ed with: - * I8254_BCD, I8254_BINARY - * - * 0 ID: INSN_CONFIG_8254_READ_STATUS - * 1 <-- Status byte returned here. - * B7 = Output - * B6 = NULL Count - * B5 - B0 Current mode. - */ - -enum i8254_mode { - I8254_MODE0 = (0 << 1), /* Interrupt on terminal count */ - I8254_MODE1 = (1 << 1), /* Hardware retriggerable one-shot */ - I8254_MODE2 = (2 << 1), /* Rate generator */ - I8254_MODE3 = (3 << 1), /* Square wave mode */ - I8254_MODE4 = (4 << 1), /* Software triggered strobe */ - /* Hardware triggered strobe (retriggerable) */ - I8254_MODE5 = (5 << 1), - /* Use binary-coded decimal instead of binary (pretty useless) */ - I8254_BCD = 1, - I8254_BINARY = 0 -}; - -/* *** BEGIN GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ - -/* - * Common National Instruments Terminal/Signal names. - * Some of these have no NI_ prefix as they are useful for non-NI hardware, such - * as those that utilize the PXI/RTSI trigger lines. - * - * NOTE ABOUT THE CHOICE OF NAMES HERE AND THE CAMELSCRIPT: - * The choice to use CamelScript and the exact names below is for - * maintainability, clarity, similarity to manufacturer's documentation, - * _and_ a mitigation for confusion that has plagued the use of these drivers - * for years! - * - * More detail: - * There have been significant confusions over the past many years for users - * when trying to understand how to connect to/from signals and terminals on - * NI hardware using comedi. The major reason for this is that the actual - * register values were exposed and required to be used by users. Several - * major reasons exist why this caused major confusion for users: - * 1) The register values are _NOT_ in user documentation, but rather in - * arcane locations, such as a few register programming manuals that are - * increasingly hard to find and the NI MHDDK (comments in example code). - * There is no one place to find the various valid values of the registers. - * 2) The register values are _NOT_ completely consistent. There is no way to - * gain any sense of intuition of which values, or even enums one should use - * for various registers. There was some attempt in prior use of comedi to - * name enums such that a user might know which enums should be used for - * varying purposes, but the end-user had to gain a knowledge of register - * values to correctly wield this approach. - * 3) The names for signals and registers found in the various register level - * programming manuals and vendor-provided documentation are _not_ even - * close to the same names that are in the end-user documentation. - * - * Similar, albeit less, confusion plagued NI's previous version of their own - * drivers. Earlier than 2003, NI greatly simplified the situation for users - * by releasing a new API that abstracted the names of signals/terminals to a - * common and intuitive set of names. - * - * The names below mirror the names chosen and well documented by NI. These - * names are exposed to the user via the comedilib user library. By keeping - * the names below, in spite of the use of CamelScript, maintenance will be - * greatly eased and confusion for users _and_ comedi developers will be - * greatly reduced. - */ - -/* - * Base of abstracted NI names. - * The first 16 bits of *_arg are reserved for channel selection. - * Since we only actually need the first 4 or 5 bits for all register values on - * NI select registers anyways, we'll identify all values >= (1<<15) as being an - * abstracted NI signal/terminal name. - * These values are also used/returned by INSN_DEVICE_CONFIG_TEST_ROUTE, - * INSN_DEVICE_CONFIG_CONNECT_ROUTE, INSN_DEVICE_CONFIG_DISCONNECT_ROUTE, - * and INSN_DEVICE_CONFIG_GET_ROUTES. - */ -#define NI_NAMES_BASE 0x8000u - -#define _TERM_N(base, n, x) ((base) + ((x) & ((n) - 1))) - -/* - * not necessarily all allowed 64 PFIs are valid--certainly not for all devices - */ -#define NI_PFI(x) _TERM_N(NI_NAMES_BASE, 64, x) -/* 8 trigger lines by standard, Some devices cannot talk to all eight. */ -#define TRIGGER_LINE(x) _TERM_N(NI_PFI(-1) + 1, 8, x) -/* 4 RTSI shared MUXes to route signals to/from TRIGGER_LINES on NI hardware */ -#define NI_RTSI_BRD(x) _TERM_N(TRIGGER_LINE(-1) + 1, 4, x) - -/* *** Counter/timer names : 8 counters max *** */ -#define NI_MAX_COUNTERS 8 -#define NI_COUNTER_NAMES_BASE (NI_RTSI_BRD(-1) + 1) -#define NI_CtrSource(x) _TERM_N(NI_COUNTER_NAMES_BASE, NI_MAX_COUNTERS, x) -/* Gate, Aux, A,B,Z are all treated, at times as gates */ -#define NI_GATES_NAMES_BASE (NI_CtrSource(-1) + 1) -#define NI_CtrGate(x) _TERM_N(NI_GATES_NAMES_BASE, NI_MAX_COUNTERS, x) -#define NI_CtrAux(x) _TERM_N(NI_CtrGate(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrA(x) _TERM_N(NI_CtrAux(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrB(x) _TERM_N(NI_CtrA(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrZ(x) _TERM_N(NI_CtrB(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_GATES_NAMES_MAX NI_CtrZ(-1) -#define NI_CtrArmStartTrigger(x) _TERM_N(NI_CtrZ(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_CtrInternalOutput(x) \ - _TERM_N(NI_CtrArmStartTrigger(-1) + 1, NI_MAX_COUNTERS, x) -/** external pin(s) labeled conveniently as CtrOut. */ -#define NI_CtrOut(x) _TERM_N(NI_CtrInternalOutput(-1) + 1, NI_MAX_COUNTERS, x) -/** For Buffered sampling of ctr -- x series capability. */ -#define NI_CtrSampleClock(x) _TERM_N(NI_CtrOut(-1) + 1, NI_MAX_COUNTERS, x) -#define NI_COUNTER_NAMES_MAX NI_CtrSampleClock(-1) - -enum ni_common_signal_names { - /* PXI_Star: this is a non-NI-specific signal */ - PXI_Star = NI_COUNTER_NAMES_MAX + 1, - PXI_Clk10, - PXIe_Clk100, - NI_AI_SampleClock, - NI_AI_SampleClockTimebase, - NI_AI_StartTrigger, - NI_AI_ReferenceTrigger, - NI_AI_ConvertClock, - NI_AI_ConvertClockTimebase, - NI_AI_PauseTrigger, - NI_AI_HoldCompleteEvent, - NI_AI_HoldComplete, - NI_AI_ExternalMUXClock, - NI_AI_STOP, /* pulse signal that occurs when a update is finished(?) */ - NI_AO_SampleClock, - NI_AO_SampleClockTimebase, - NI_AO_StartTrigger, - NI_AO_PauseTrigger, - NI_DI_SampleClock, - NI_DI_SampleClockTimebase, - NI_DI_StartTrigger, - NI_DI_ReferenceTrigger, - NI_DI_PauseTrigger, - NI_DI_InputBufferFull, - NI_DI_ReadyForStartEvent, - NI_DI_ReadyForTransferEventBurst, - NI_DI_ReadyForTransferEventPipelined, - NI_DO_SampleClock, - NI_DO_SampleClockTimebase, - NI_DO_StartTrigger, - NI_DO_PauseTrigger, - NI_DO_OutputBufferFull, - NI_DO_DataActiveEvent, - NI_DO_ReadyForStartEvent, - NI_DO_ReadyForTransferEvent, - NI_MasterTimebase, - NI_20MHzTimebase, - NI_80MHzTimebase, - NI_100MHzTimebase, - NI_200MHzTimebase, - NI_100kHzTimebase, - NI_10MHzRefClock, - NI_FrequencyOutput, - NI_ChangeDetectionEvent, - NI_AnalogComparisonEvent, - NI_WatchdogExpiredEvent, - NI_WatchdogExpirationTrigger, - NI_SCXI_Trig1, - NI_LogicLow, - NI_LogicHigh, - NI_ExternalStrobe, - NI_PFI_DO, - NI_CaseGround, - /* special internal signal used as variable source for RTSI bus: */ - NI_RGOUT0, - - /* just a name to make the next more convenient, regardless of above */ - _NI_NAMES_MAX_PLUS_1, - NI_NUM_NAMES = _NI_NAMES_MAX_PLUS_1 - NI_NAMES_BASE, -}; - -/* *** END GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ - -#define NI_USUAL_PFI_SELECT(x) (((x) < 10) ? (0x1 + (x)) : (0xb + (x))) -#define NI_USUAL_RTSI_SELECT(x) (((x) < 7) ? (0xb + (x)) : 0x1b) - -/* - * mode bits for NI general-purpose counters, set with - * INSN_CONFIG_SET_COUNTER_MODE - */ -#define NI_GPCT_COUNTING_MODE_SHIFT 16 -#define NI_GPCT_INDEX_PHASE_BITSHIFT 20 -#define NI_GPCT_COUNTING_DIRECTION_SHIFT 24 -enum ni_gpct_mode_bits { - NI_GPCT_GATE_ON_BOTH_EDGES_BIT = 0x4, - NI_GPCT_EDGE_GATE_MODE_MASK = 0x18, - NI_GPCT_EDGE_GATE_STARTS_STOPS_BITS = 0x0, - NI_GPCT_EDGE_GATE_STOPS_STARTS_BITS = 0x8, - NI_GPCT_EDGE_GATE_STARTS_BITS = 0x10, - NI_GPCT_EDGE_GATE_NO_STARTS_NO_STOPS_BITS = 0x18, - NI_GPCT_STOP_MODE_MASK = 0x60, - NI_GPCT_STOP_ON_GATE_BITS = 0x00, - NI_GPCT_STOP_ON_GATE_OR_TC_BITS = 0x20, - NI_GPCT_STOP_ON_GATE_OR_SECOND_TC_BITS = 0x40, - NI_GPCT_LOAD_B_SELECT_BIT = 0x80, - NI_GPCT_OUTPUT_MODE_MASK = 0x300, - NI_GPCT_OUTPUT_TC_PULSE_BITS = 0x100, - NI_GPCT_OUTPUT_TC_TOGGLE_BITS = 0x200, - NI_GPCT_OUTPUT_TC_OR_GATE_TOGGLE_BITS = 0x300, - NI_GPCT_HARDWARE_DISARM_MASK = 0xc00, - NI_GPCT_NO_HARDWARE_DISARM_BITS = 0x000, - NI_GPCT_DISARM_AT_TC_BITS = 0x400, - NI_GPCT_DISARM_AT_GATE_BITS = 0x800, - NI_GPCT_DISARM_AT_TC_OR_GATE_BITS = 0xc00, - NI_GPCT_LOADING_ON_TC_BIT = 0x1000, - NI_GPCT_LOADING_ON_GATE_BIT = 0x4000, - NI_GPCT_COUNTING_MODE_MASK = 0x7 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_NORMAL_BITS = - 0x0 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_QUADRATURE_X1_BITS = - 0x1 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_QUADRATURE_X2_BITS = - 0x2 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_QUADRATURE_X4_BITS = - 0x3 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_TWO_PULSE_BITS = - 0x4 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_COUNTING_MODE_SYNC_SOURCE_BITS = - 0x6 << NI_GPCT_COUNTING_MODE_SHIFT, - NI_GPCT_INDEX_PHASE_MASK = 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_LOW_A_LOW_B_BITS = - 0x0 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_LOW_A_HIGH_B_BITS = - 0x1 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_HIGH_A_LOW_B_BITS = - 0x2 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_PHASE_HIGH_A_HIGH_B_BITS = - 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, - NI_GPCT_INDEX_ENABLE_BIT = 0x400000, - NI_GPCT_COUNTING_DIRECTION_MASK = - 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_DOWN_BITS = - 0x00 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_UP_BITS = - 0x1 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_HW_UP_DOWN_BITS = - 0x2 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_COUNTING_DIRECTION_HW_GATE_BITS = - 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, - NI_GPCT_RELOAD_SOURCE_MASK = 0xc000000, - NI_GPCT_RELOAD_SOURCE_FIXED_BITS = 0x0, - NI_GPCT_RELOAD_SOURCE_SWITCHING_BITS = 0x4000000, - NI_GPCT_RELOAD_SOURCE_GATE_SELECT_BITS = 0x8000000, - NI_GPCT_OR_GATE_BIT = 0x10000000, - NI_GPCT_INVERT_OUTPUT_BIT = 0x20000000 -}; - -/* - * Bits for setting a clock source with - * INSN_CONFIG_SET_CLOCK_SRC when using NI general-purpose counters. - */ -enum ni_gpct_clock_source_bits { - NI_GPCT_CLOCK_SRC_SELECT_MASK = 0x3f, - NI_GPCT_TIMEBASE_1_CLOCK_SRC_BITS = 0x0, - NI_GPCT_TIMEBASE_2_CLOCK_SRC_BITS = 0x1, - NI_GPCT_TIMEBASE_3_CLOCK_SRC_BITS = 0x2, - NI_GPCT_LOGIC_LOW_CLOCK_SRC_BITS = 0x3, - NI_GPCT_NEXT_GATE_CLOCK_SRC_BITS = 0x4, - NI_GPCT_NEXT_TC_CLOCK_SRC_BITS = 0x5, - /* NI 660x-specific */ - NI_GPCT_SOURCE_PIN_i_CLOCK_SRC_BITS = 0x6, - NI_GPCT_PXI10_CLOCK_SRC_BITS = 0x7, - NI_GPCT_PXI_STAR_TRIGGER_CLOCK_SRC_BITS = 0x8, - NI_GPCT_ANALOG_TRIGGER_OUT_CLOCK_SRC_BITS = 0x9, - NI_GPCT_PRESCALE_MODE_CLOCK_SRC_MASK = 0x30000000, - NI_GPCT_NO_PRESCALE_CLOCK_SRC_BITS = 0x0, - /* divide source by 2 */ - NI_GPCT_PRESCALE_X2_CLOCK_SRC_BITS = 0x10000000, - /* divide source by 8 */ - NI_GPCT_PRESCALE_X8_CLOCK_SRC_BITS = 0x20000000, - NI_GPCT_INVERT_CLOCK_SRC_BIT = 0x80000000 -}; - -/* NI 660x-specific */ -#define NI_GPCT_SOURCE_PIN_CLOCK_SRC_BITS(x) (0x10 + (x)) - -#define NI_GPCT_RTSI_CLOCK_SRC_BITS(x) (0x18 + (x)) - -/* no pfi on NI 660x */ -#define NI_GPCT_PFI_CLOCK_SRC_BITS(x) (0x20 + (x)) - -/* - * Possibilities for setting a gate source with - * INSN_CONFIG_SET_GATE_SRC when using NI general-purpose counters. - * May be bitwise-or'd with CR_EDGE or CR_INVERT. - */ -enum ni_gpct_gate_select { - /* m-series gates */ - NI_GPCT_TIMESTAMP_MUX_GATE_SELECT = 0x0, - NI_GPCT_AI_START2_GATE_SELECT = 0x12, - NI_GPCT_PXI_STAR_TRIGGER_GATE_SELECT = 0x13, - NI_GPCT_NEXT_OUT_GATE_SELECT = 0x14, - NI_GPCT_AI_START1_GATE_SELECT = 0x1c, - NI_GPCT_NEXT_SOURCE_GATE_SELECT = 0x1d, - NI_GPCT_ANALOG_TRIGGER_OUT_GATE_SELECT = 0x1e, - NI_GPCT_LOGIC_LOW_GATE_SELECT = 0x1f, - /* more gates for 660x */ - NI_GPCT_SOURCE_PIN_i_GATE_SELECT = 0x100, - NI_GPCT_GATE_PIN_i_GATE_SELECT = 0x101, - /* more gates for 660x "second gate" */ - NI_GPCT_UP_DOWN_PIN_i_GATE_SELECT = 0x201, - NI_GPCT_SELECTED_GATE_GATE_SELECT = 0x21e, - /* - * m-series "second gate" sources are unknown, - * we should add them here with an offset of 0x300 when - * known. - */ - NI_GPCT_DISABLED_GATE_SELECT = 0x8000, -}; - -#define NI_GPCT_GATE_PIN_GATE_SELECT(x) (0x102 + (x)) -#define NI_GPCT_RTSI_GATE_SELECT(x) NI_USUAL_RTSI_SELECT(x) -#define NI_GPCT_PFI_GATE_SELECT(x) NI_USUAL_PFI_SELECT(x) -#define NI_GPCT_UP_DOWN_PIN_GATE_SELECT(x) (0x202 + (x)) - -/* - * Possibilities for setting a source with - * INSN_CONFIG_SET_OTHER_SRC when using NI general-purpose counters. - */ -enum ni_gpct_other_index { - NI_GPCT_SOURCE_ENCODER_A, - NI_GPCT_SOURCE_ENCODER_B, - NI_GPCT_SOURCE_ENCODER_Z -}; - -enum ni_gpct_other_select { - /* m-series gates */ - /* Still unknown, probably only need NI_GPCT_PFI_OTHER_SELECT */ - NI_GPCT_DISABLED_OTHER_SELECT = 0x8000, -}; - -#define NI_GPCT_PFI_OTHER_SELECT(x) NI_USUAL_PFI_SELECT(x) - -/* - * start sources for ni general-purpose counters for use with - * INSN_CONFIG_ARM - */ -enum ni_gpct_arm_source { - NI_GPCT_ARM_IMMEDIATE = 0x0, - /* - * Start both the counter and the adjacent paired counter simultaneously - */ - NI_GPCT_ARM_PAIRED_IMMEDIATE = 0x1, - /* - * If the NI_GPCT_HW_ARM bit is set, we will pass the least significant - * bits (3 bits for 660x or 5 bits for m-series) through to the - * hardware. To select a hardware trigger, pass the appropriate select - * bit, e.g., - * NI_GPCT_HW_ARM | NI_GPCT_AI_START1_GATE_SELECT or - * NI_GPCT_HW_ARM | NI_GPCT_PFI_GATE_SELECT(pfi_number) - */ - NI_GPCT_HW_ARM = 0x1000, - NI_GPCT_ARM_UNKNOWN = NI_GPCT_HW_ARM, /* for backward compatibility */ -}; - -/* digital filtering options for ni 660x for use with INSN_CONFIG_FILTER. */ -enum ni_gpct_filter_select { - NI_GPCT_FILTER_OFF = 0x0, - NI_GPCT_FILTER_TIMEBASE_3_SYNC = 0x1, - NI_GPCT_FILTER_100x_TIMEBASE_1 = 0x2, - NI_GPCT_FILTER_20x_TIMEBASE_1 = 0x3, - NI_GPCT_FILTER_10x_TIMEBASE_1 = 0x4, - NI_GPCT_FILTER_2x_TIMEBASE_1 = 0x5, - NI_GPCT_FILTER_2x_TIMEBASE_3 = 0x6 -}; - -/* - * PFI digital filtering options for ni m-series for use with - * INSN_CONFIG_FILTER. - */ -enum ni_pfi_filter_select { - NI_PFI_FILTER_OFF = 0x0, - NI_PFI_FILTER_125ns = 0x1, - NI_PFI_FILTER_6425ns = 0x2, - NI_PFI_FILTER_2550us = 0x3 -}; - -/* master clock sources for ni mio boards and INSN_CONFIG_SET_CLOCK_SRC */ -enum ni_mio_clock_source { - NI_MIO_INTERNAL_CLOCK = 0, - /* - * Doesn't work for m-series, use NI_MIO_PLL_RTSI_CLOCK() - * the NI_MIO_PLL_* sources are m-series only - */ - NI_MIO_RTSI_CLOCK = 1, - NI_MIO_PLL_PXI_STAR_TRIGGER_CLOCK = 2, - NI_MIO_PLL_PXI10_CLOCK = 3, - NI_MIO_PLL_RTSI0_CLOCK = 4 -}; - -#define NI_MIO_PLL_RTSI_CLOCK(x) (NI_MIO_PLL_RTSI0_CLOCK + (x)) - -/* - * Signals which can be routed to an NI RTSI pin with INSN_CONFIG_SET_ROUTING. - * The numbers assigned are not arbitrary, they correspond to the bits required - * to program the board. - */ -enum ni_rtsi_routing { - NI_RTSI_OUTPUT_ADR_START1 = 0, - NI_RTSI_OUTPUT_ADR_START2 = 1, - NI_RTSI_OUTPUT_SCLKG = 2, - NI_RTSI_OUTPUT_DACUPDN = 3, - NI_RTSI_OUTPUT_DA_START1 = 4, - NI_RTSI_OUTPUT_G_SRC0 = 5, - NI_RTSI_OUTPUT_G_GATE0 = 6, - NI_RTSI_OUTPUT_RGOUT0 = 7, - NI_RTSI_OUTPUT_RTSI_BRD_0 = 8, - /* Pre-m-series always have RTSI clock on line 7 */ - NI_RTSI_OUTPUT_RTSI_OSC = 12 -}; - -#define NI_RTSI_OUTPUT_RTSI_BRD(x) (NI_RTSI_OUTPUT_RTSI_BRD_0 + (x)) - -/* - * Signals which can be routed to an NI PFI pin on an m-series board with - * INSN_CONFIG_SET_ROUTING. These numbers are also returned by - * INSN_CONFIG_GET_ROUTING on pre-m-series boards, even though their routing - * cannot be changed. The numbers assigned are not arbitrary, they correspond - * to the bits required to program the board. - */ -enum ni_pfi_routing { - NI_PFI_OUTPUT_PFI_DEFAULT = 0, - NI_PFI_OUTPUT_AI_START1 = 1, - NI_PFI_OUTPUT_AI_START2 = 2, - NI_PFI_OUTPUT_AI_CONVERT = 3, - NI_PFI_OUTPUT_G_SRC1 = 4, - NI_PFI_OUTPUT_G_GATE1 = 5, - NI_PFI_OUTPUT_AO_UPDATE_N = 6, - NI_PFI_OUTPUT_AO_START1 = 7, - NI_PFI_OUTPUT_AI_START_PULSE = 8, - NI_PFI_OUTPUT_G_SRC0 = 9, - NI_PFI_OUTPUT_G_GATE0 = 10, - NI_PFI_OUTPUT_EXT_STROBE = 11, - NI_PFI_OUTPUT_AI_EXT_MUX_CLK = 12, - NI_PFI_OUTPUT_GOUT0 = 13, - NI_PFI_OUTPUT_GOUT1 = 14, - NI_PFI_OUTPUT_FREQ_OUT = 15, - NI_PFI_OUTPUT_PFI_DO = 16, - NI_PFI_OUTPUT_I_ATRIG = 17, - NI_PFI_OUTPUT_RTSI0 = 18, - NI_PFI_OUTPUT_PXI_STAR_TRIGGER_IN = 26, - NI_PFI_OUTPUT_SCXI_TRIG1 = 27, - NI_PFI_OUTPUT_DIO_CHANGE_DETECT_RTSI = 28, - NI_PFI_OUTPUT_CDI_SAMPLE = 29, - NI_PFI_OUTPUT_CDO_UPDATE = 30 -}; - -#define NI_PFI_OUTPUT_RTSI(x) (NI_PFI_OUTPUT_RTSI0 + (x)) - -/* - * Signals which can be routed to output on a NI PFI pin on a 660x board - * with INSN_CONFIG_SET_ROUTING. The numbers assigned are - * not arbitrary, they correspond to the bits required - * to program the board. Lines 0 to 7 can only be set to - * NI_660X_PFI_OUTPUT_DIO. Lines 32 to 39 can only be set to - * NI_660X_PFI_OUTPUT_COUNTER. - */ -enum ni_660x_pfi_routing { - NI_660X_PFI_OUTPUT_COUNTER = 1, /* counter */ - NI_660X_PFI_OUTPUT_DIO = 2, /* static digital output */ -}; - -/* - * NI External Trigger lines. These values are not arbitrary, but are related - * to the bits required to program the board (offset by 1 for historical - * reasons). - */ -#define NI_EXT_PFI(x) (NI_USUAL_PFI_SELECT(x) - 1) -#define NI_EXT_RTSI(x) (NI_USUAL_RTSI_SELECT(x) - 1) - -/* - * Clock sources for CDIO subdevice on NI m-series boards. Used as the - * scan_begin_arg for a comedi_command. These sources may also be bitwise-or'd - * with CR_INVERT to change polarity. - */ -enum ni_m_series_cdio_scan_begin_src { - NI_CDIO_SCAN_BEGIN_SRC_GROUND = 0, - NI_CDIO_SCAN_BEGIN_SRC_AI_START = 18, - NI_CDIO_SCAN_BEGIN_SRC_AI_CONVERT = 19, - NI_CDIO_SCAN_BEGIN_SRC_PXI_STAR_TRIGGER = 20, - NI_CDIO_SCAN_BEGIN_SRC_G0_OUT = 28, - NI_CDIO_SCAN_BEGIN_SRC_G1_OUT = 29, - NI_CDIO_SCAN_BEGIN_SRC_ANALOG_TRIGGER = 30, - NI_CDIO_SCAN_BEGIN_SRC_AO_UPDATE = 31, - NI_CDIO_SCAN_BEGIN_SRC_FREQ_OUT = 32, - NI_CDIO_SCAN_BEGIN_SRC_DIO_CHANGE_DETECT_IRQ = 33 -}; - -#define NI_CDIO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) -#define NI_CDIO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) - -/* - * scan_begin_src for scan_begin_arg==TRIG_EXT with analog output command on NI - * boards. These scan begin sources can also be bitwise-or'd with CR_INVERT to - * change polarity. - */ -#define NI_AO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) -#define NI_AO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) - -/* - * Bits for setting a clock source with - * INSN_CONFIG_SET_CLOCK_SRC when using NI frequency output subdevice. - */ -enum ni_freq_out_clock_source_bits { - NI_FREQ_OUT_TIMEBASE_1_DIV_2_CLOCK_SRC, /* 10 MHz */ - NI_FREQ_OUT_TIMEBASE_2_CLOCK_SRC /* 100 KHz */ -}; - -/* - * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for - * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). - */ -enum amplc_dio_clock_source { - /* - * Per channel external clock - * input/output pin (pin is only an - * input when clock source set to this value, - * otherwise it is an output) - */ - AMPLC_DIO_CLK_CLKN, - AMPLC_DIO_CLK_10MHZ, /* 10 MHz internal clock */ - AMPLC_DIO_CLK_1MHZ, /* 1 MHz internal clock */ - AMPLC_DIO_CLK_100KHZ, /* 100 kHz internal clock */ - AMPLC_DIO_CLK_10KHZ, /* 10 kHz internal clock */ - AMPLC_DIO_CLK_1KHZ, /* 1 kHz internal clock */ - /* - * Output of preceding counter channel - * (for channel 0, preceding counter - * channel is channel 2 on preceding - * counter subdevice, for first counter - * subdevice, preceding counter - * subdevice is the last counter - * subdevice) - */ - AMPLC_DIO_CLK_OUTNM1, - AMPLC_DIO_CLK_EXT, /* per chip external input pin */ - /* the following are "enhanced" clock sources for PCIe models */ - AMPLC_DIO_CLK_VCC, /* clock input HIGH */ - AMPLC_DIO_CLK_GND, /* clock input LOW */ - AMPLC_DIO_CLK_PAT_PRESENT, /* "pattern present" signal */ - AMPLC_DIO_CLK_20MHZ /* 20 MHz internal clock */ -}; - -/* - * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for - * timer subdevice on some Amplicon DIO PCIe boards (amplc_dio200 driver). - */ -enum amplc_dio_ts_clock_src { - AMPLC_DIO_TS_CLK_1GHZ, /* 1 ns period with 20 ns granularity */ - AMPLC_DIO_TS_CLK_1MHZ, /* 1 us period */ - AMPLC_DIO_TS_CLK_1KHZ /* 1 ms period */ -}; - -/* - * Values for setting a gate source with INSN_CONFIG_SET_GATE_SRC for - * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). - */ -enum amplc_dio_gate_source { - AMPLC_DIO_GAT_VCC, /* internal high logic level */ - AMPLC_DIO_GAT_GND, /* internal low logic level */ - AMPLC_DIO_GAT_GATN, /* per channel external gate input */ - /* - * negated output of counter channel minus 2 - * (for channels 0 or 1, channel minus 2 is channel 1 or 2 on - * the preceding counter subdevice, for the first counter subdevice - * the preceding counter subdevice is the last counter subdevice) - */ - AMPLC_DIO_GAT_NOUTNM2, - AMPLC_DIO_GAT_RESERVED4, - AMPLC_DIO_GAT_RESERVED5, - AMPLC_DIO_GAT_RESERVED6, - AMPLC_DIO_GAT_RESERVED7, - /* the following are "enhanced" gate sources for PCIe models */ - AMPLC_DIO_GAT_NGATN = 6, /* negated per channel gate input */ - /* non-negated output of counter channel minus 2 */ - AMPLC_DIO_GAT_OUTNM2, - AMPLC_DIO_GAT_PAT_PRESENT, /* "pattern present" signal */ - AMPLC_DIO_GAT_PAT_OCCURRED, /* "pattern occurred" latched */ - AMPLC_DIO_GAT_PAT_GONE, /* "pattern gone away" latched */ - AMPLC_DIO_GAT_NPAT_PRESENT, /* negated "pattern present" */ - AMPLC_DIO_GAT_NPAT_OCCURRED, /* negated "pattern occurred" */ - AMPLC_DIO_GAT_NPAT_GONE /* negated "pattern gone away" */ -}; - -/* - * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for - * the counter subdevice on the Kolter Electronic PCI-Counter board - * (ke_counter driver). - */ -enum ke_counter_clock_source { - KE_CLK_20MHZ, /* internal 20MHz (default) */ - KE_CLK_4MHZ, /* internal 4MHz (option) */ - KE_CLK_EXT /* external clock on pin 21 of D-Sub */ -}; - -#endif /* _COMEDI_H */ diff --git a/drivers/comedi/comedi_buf.c b/drivers/comedi/comedi_buf.c index 06bfc859ab31..393966c09740 100644 --- a/drivers/comedi/comedi_buf.c +++ b/drivers/comedi/comedi_buf.c @@ -9,8 +9,7 @@ #include #include - -#include "comedidev.h" +#include #include "comedi_internal.h" #ifdef PAGE_KERNEL_NOCACHE diff --git a/drivers/comedi/comedi_fops.c b/drivers/comedi/comedi_fops.c index 763cea8418f8..55a0cae04b8d 100644 --- a/drivers/comedi/comedi_fops.c +++ b/drivers/comedi/comedi_fops.c @@ -23,7 +23,7 @@ #include #include #include -#include "comedidev.h" +#include #include #include diff --git a/drivers/comedi/comedi_pci.c b/drivers/comedi/comedi_pci.c index 54739af7eb71..cc2581902195 100644 --- a/drivers/comedi/comedi_pci.c +++ b/drivers/comedi/comedi_pci.c @@ -9,8 +9,7 @@ #include #include - -#include "comedi_pci.h" +#include /** * comedi_to_pci_dev() - Return PCI device attached to COMEDI device diff --git a/drivers/comedi/comedi_pci.h b/drivers/comedi/comedi_pci.h deleted file mode 100644 index 4e069440cbdc..000000000000 --- a/drivers/comedi/comedi_pci.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedi_pci.h - * header file for Comedi PCI drivers - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDI_PCI_H -#define _COMEDI_PCI_H - -#include - -#include "comedidev.h" - -/* - * PCI Vendor IDs not in - */ -#define PCI_VENDOR_ID_KOLTER 0x1001 -#define PCI_VENDOR_ID_ICP 0x104c -#define PCI_VENDOR_ID_DT 0x1116 -#define PCI_VENDOR_ID_IOTECH 0x1616 -#define PCI_VENDOR_ID_CONTEC 0x1221 -#define PCI_VENDOR_ID_RTD 0x1435 -#define PCI_VENDOR_ID_HUMUSOFT 0x186c - -struct pci_dev *comedi_to_pci_dev(struct comedi_device *dev); - -int comedi_pci_enable(struct comedi_device *dev); -void comedi_pci_disable(struct comedi_device *dev); -void comedi_pci_detach(struct comedi_device *dev); - -int comedi_pci_auto_config(struct pci_dev *pcidev, struct comedi_driver *driver, - unsigned long context); -void comedi_pci_auto_unconfig(struct pci_dev *pcidev); - -int comedi_pci_driver_register(struct comedi_driver *comedi_driver, - struct pci_driver *pci_driver); -void comedi_pci_driver_unregister(struct comedi_driver *comedi_driver, - struct pci_driver *pci_driver); - -/** - * module_comedi_pci_driver() - Helper macro for registering a comedi PCI driver - * @__comedi_driver: comedi_driver struct - * @__pci_driver: pci_driver struct - * - * Helper macro for comedi PCI drivers which do not do anything special - * in module init/exit. This eliminates a lot of boilerplate. Each - * module may only use this macro once, and calling it replaces - * module_init() and module_exit() - */ -#define module_comedi_pci_driver(__comedi_driver, __pci_driver) \ - module_driver(__comedi_driver, comedi_pci_driver_register, \ - comedi_pci_driver_unregister, &(__pci_driver)) - -#endif /* _COMEDI_PCI_H */ diff --git a/drivers/comedi/comedi_pcmcia.c b/drivers/comedi/comedi_pcmcia.c index bb273bb202e6..c53aad0fc2ce 100644 --- a/drivers/comedi/comedi_pcmcia.c +++ b/drivers/comedi/comedi_pcmcia.c @@ -9,8 +9,7 @@ #include #include - -#include "comedi_pcmcia.h" +#include /** * comedi_to_pcmcia_dev() - Return PCMCIA device attached to COMEDI device diff --git a/drivers/comedi/comedi_pcmcia.h b/drivers/comedi/comedi_pcmcia.h deleted file mode 100644 index f2f6e779645b..000000000000 --- a/drivers/comedi/comedi_pcmcia.h +++ /dev/null @@ -1,49 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedi_pcmcia.h - * header file for Comedi PCMCIA drivers - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDI_PCMCIA_H -#define _COMEDI_PCMCIA_H - -#include -#include - -#include "comedidev.h" - -struct pcmcia_device *comedi_to_pcmcia_dev(struct comedi_device *dev); - -int comedi_pcmcia_enable(struct comedi_device *dev, - int (*conf_check)(struct pcmcia_device *p_dev, - void *priv_data)); -void comedi_pcmcia_disable(struct comedi_device *dev); - -int comedi_pcmcia_auto_config(struct pcmcia_device *link, - struct comedi_driver *driver); -void comedi_pcmcia_auto_unconfig(struct pcmcia_device *link); - -int comedi_pcmcia_driver_register(struct comedi_driver *comedi_driver, - struct pcmcia_driver *pcmcia_driver); -void comedi_pcmcia_driver_unregister(struct comedi_driver *comedi_driver, - struct pcmcia_driver *pcmcia_driver); - -/** - * module_comedi_pcmcia_driver() - Helper macro for registering a comedi - * PCMCIA driver - * @__comedi_driver: comedi_driver struct - * @__pcmcia_driver: pcmcia_driver struct - * - * Helper macro for comedi PCMCIA drivers which do not do anything special - * in module init/exit. This eliminates a lot of boilerplate. Each - * module may only use this macro once, and calling it replaces - * module_init() and module_exit() - */ -#define module_comedi_pcmcia_driver(__comedi_driver, __pcmcia_driver) \ - module_driver(__comedi_driver, comedi_pcmcia_driver_register, \ - comedi_pcmcia_driver_unregister, &(__pcmcia_driver)) - -#endif /* _COMEDI_PCMCIA_H */ diff --git a/drivers/comedi/comedi_usb.c b/drivers/comedi/comedi_usb.c index eea8ebf32ed0..d11ea148ebf8 100644 --- a/drivers/comedi/comedi_usb.c +++ b/drivers/comedi/comedi_usb.c @@ -8,8 +8,7 @@ */ #include - -#include "comedi_usb.h" +#include /** * comedi_to_usb_interface() - Return USB interface attached to COMEDI device diff --git a/drivers/comedi/comedi_usb.h b/drivers/comedi/comedi_usb.h deleted file mode 100644 index 601e29d3891c..000000000000 --- a/drivers/comedi/comedi_usb.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* comedi_usb.h - * header file for USB Comedi drivers - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDI_USB_H -#define _COMEDI_USB_H - -#include - -#include "comedidev.h" - -struct usb_interface *comedi_to_usb_interface(struct comedi_device *dev); -struct usb_device *comedi_to_usb_dev(struct comedi_device *dev); - -int comedi_usb_auto_config(struct usb_interface *intf, - struct comedi_driver *driver, unsigned long context); -void comedi_usb_auto_unconfig(struct usb_interface *intf); - -int comedi_usb_driver_register(struct comedi_driver *comedi_driver, - struct usb_driver *usb_driver); -void comedi_usb_driver_unregister(struct comedi_driver *comedi_driver, - struct usb_driver *usb_driver); - -/** - * module_comedi_usb_driver() - Helper macro for registering a comedi USB driver - * @__comedi_driver: comedi_driver struct - * @__usb_driver: usb_driver struct - * - * Helper macro for comedi USB drivers which do not do anything special - * in module init/exit. This eliminates a lot of boilerplate. Each - * module may only use this macro once, and calling it replaces - * module_init() and module_exit() - */ -#define module_comedi_usb_driver(__comedi_driver, __usb_driver) \ - module_driver(__comedi_driver, comedi_usb_driver_register, \ - comedi_usb_driver_unregister, &(__usb_driver)) - -#endif /* _COMEDI_USB_H */ diff --git a/drivers/comedi/comedidev.h b/drivers/comedi/comedidev.h deleted file mode 100644 index 0e1b95ef9a4d..000000000000 --- a/drivers/comedi/comedidev.h +++ /dev/null @@ -1,1054 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedidev.h - * header file for kernel-only structures, variables, and constants - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1997-2000 David A. Schleef - */ - -#ifndef _COMEDIDEV_H -#define _COMEDIDEV_H - -#include -#include -#include -#include -#include - -#include "comedi.h" - -#define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) -#define COMEDI_VERSION_CODE COMEDI_VERSION(COMEDI_MAJORVERSION, \ - COMEDI_MINORVERSION, COMEDI_MICROVERSION) -#define COMEDI_RELEASE VERSION - -#define COMEDI_NUM_BOARD_MINORS 0x30 - -/** - * struct comedi_subdevice - Working data for a COMEDI subdevice - * @device: COMEDI device to which this subdevice belongs. (Initialized by - * comedi_alloc_subdevices().) - * @index: Index of this subdevice within device's array of subdevices. - * (Initialized by comedi_alloc_subdevices().) - * @type: Type of subdevice from &enum comedi_subdevice_type. (Initialized by - * the low-level driver.) - * @n_chan: Number of channels the subdevice supports. (Initialized by the - * low-level driver.) - * @subdev_flags: Various "SDF" flags indicating aspects of the subdevice to - * the COMEDI core and user application. (Initialized by the low-level - * driver.) - * @len_chanlist: Maximum length of a channel list if the subdevice supports - * asynchronous acquisition commands. (Optionally initialized by the - * low-level driver, or changed from 0 to 1 during post-configuration.) - * @private: Private data pointer which is either set by the low-level driver - * itself, or by a call to comedi_alloc_spriv() which allocates storage. - * In the latter case, the storage is automatically freed after the - * low-level driver's "detach" handler is called for the device. - * (Initialized by the low-level driver.) - * @async: Pointer to &struct comedi_async id the subdevice supports - * asynchronous acquisition commands. (Allocated and initialized during - * post-configuration if needed.) - * @lock: Pointer to a file object that performed a %COMEDI_LOCK ioctl on the - * subdevice. (Initially NULL.) - * @busy: Pointer to a file object that is performing an asynchronous - * acquisition command on the subdevice. (Initially NULL.) - * @runflags: Internal flags for use by COMEDI core, mostly indicating whether - * an asynchronous acquisition command is running. - * @spin_lock: Generic spin-lock for use by the COMEDI core and the low-level - * driver. (Initialized by comedi_alloc_subdevices().) - * @io_bits: Bit-mask indicating the channel directions for a DIO subdevice - * with no more than 32 channels. A '1' at a bit position indicates the - * corresponding channel is configured as an output. (Initialized by the - * low-level driver for a DIO subdevice. Forced to all-outputs during - * post-configuration for a digital output subdevice.) - * @maxdata: If non-zero, this is the maximum raw data value of each channel. - * If zero, the maximum data value is channel-specific. (Initialized by - * the low-level driver.) - * @maxdata_list: If the maximum data value is channel-specific, this points - * to an array of maximum data values indexed by channel index. - * (Initialized by the low-level driver.) - * @range_table: If non-NULL, this points to a COMEDI range table for the - * subdevice. If NULL, the range table is channel-specific. (Initialized - * by the low-level driver, will be set to an "invalid" range table during - * post-configuration if @range_table and @range_table_list are both - * NULL.) - * @range_table_list: If the COMEDI range table is channel-specific, this - * points to an array of pointers to COMEDI range tables indexed by - * channel number. (Initialized by the low-level driver.) - * @chanlist: Not used. - * @insn_read: Optional pointer to a handler for the %INSN_READ instruction. - * (Initialized by the low-level driver, or set to a default handler - * during post-configuration.) - * @insn_write: Optional pointer to a handler for the %INSN_WRITE instruction. - * (Initialized by the low-level driver, or set to a default handler - * during post-configuration.) - * @insn_bits: Optional pointer to a handler for the %INSN_BITS instruction - * for a digital input, digital output or digital input/output subdevice. - * (Initialized by the low-level driver, or set to a default handler - * during post-configuration.) - * @insn_config: Optional pointer to a handler for the %INSN_CONFIG - * instruction. (Initialized by the low-level driver, or set to a default - * handler during post-configuration.) - * @do_cmd: If the subdevice supports asynchronous acquisition commands, this - * points to a handler to set it up in hardware. (Initialized by the - * low-level driver.) - * @do_cmdtest: If the subdevice supports asynchronous acquisition commands, - * this points to a handler used to check and possibly tweak a prospective - * acquisition command without setting it up in hardware. (Initialized by - * the low-level driver.) - * @poll: If the subdevice supports asynchronous acquisition commands, this - * is an optional pointer to a handler for the %COMEDI_POLL ioctl which - * instructs the low-level driver to synchronize buffers. (Initialized by - * the low-level driver if needed.) - * @cancel: If the subdevice supports asynchronous acquisition commands, this - * points to a handler used to terminate a running command. (Initialized - * by the low-level driver.) - * @buf_change: If the subdevice supports asynchronous acquisition commands, - * this is an optional pointer to a handler that is called when the data - * buffer for handling asynchronous commands is allocated or reallocated. - * (Initialized by the low-level driver if needed.) - * @munge: If the subdevice supports asynchronous acquisition commands and - * uses DMA to transfer data from the hardware to the acquisition buffer, - * this points to a function used to "munge" the data values from the - * hardware into the format expected by COMEDI. (Initialized by the - * low-level driver if needed.) - * @async_dma_dir: If the subdevice supports asynchronous acquisition commands - * and uses DMA to transfer data from the hardware to the acquisition - * buffer, this sets the DMA direction for the buffer. (initialized to - * %DMA_NONE by comedi_alloc_subdevices() and changed by the low-level - * driver if necessary.) - * @state: Handy bit-mask indicating the output states for a DIO or digital - * output subdevice with no more than 32 channels. (Initialized by the - * low-level driver.) - * @class_dev: If the subdevice supports asynchronous acquisition commands, - * this points to a sysfs comediX_subdY device where X is the minor device - * number of the COMEDI device and Y is the subdevice number. The minor - * device number for the sysfs device is allocated dynamically in the - * range 48 to 255. This is used to allow the COMEDI device to be opened - * with a different default read or write subdevice. (Allocated during - * post-configuration if needed.) - * @minor: If @class_dev is set, this is its dynamically allocated minor - * device number. (Set during post-configuration if necessary.) - * @readback: Optional pointer to memory allocated by - * comedi_alloc_subdev_readback() used to hold the values written to - * analog output channels so they can be read back. The storage is - * automatically freed after the low-level driver's "detach" handler is - * called for the device. (Initialized by the low-level driver.) - * - * This is the main control structure for a COMEDI subdevice. If the subdevice - * supports asynchronous acquisition commands, additional information is stored - * in the &struct comedi_async pointed to by @async. - * - * Most of the subdevice is initialized by the low-level driver's "attach" or - * "auto_attach" handlers but parts of it are initialized by - * comedi_alloc_subdevices(), and other parts are initialized during - * post-configuration on return from that handler. - * - * A low-level driver that sets @insn_bits for a digital input, digital output, - * or DIO subdevice may leave @insn_read and @insn_write uninitialized, in - * which case they will be set to a default handler during post-configuration - * that uses @insn_bits to emulate the %INSN_READ and %INSN_WRITE instructions. - */ -struct comedi_subdevice { - struct comedi_device *device; - int index; - int type; - int n_chan; - int subdev_flags; - int len_chanlist; /* maximum length of channel/gain list */ - - void *private; - - struct comedi_async *async; - - void *lock; - void *busy; - unsigned int runflags; - spinlock_t spin_lock; /* generic spin-lock for COMEDI and drivers */ - - unsigned int io_bits; - - unsigned int maxdata; /* if maxdata==0, use list */ - const unsigned int *maxdata_list; /* list is channel specific */ - - const struct comedi_lrange *range_table; - const struct comedi_lrange *const *range_table_list; - - unsigned int *chanlist; /* driver-owned chanlist (not used) */ - - int (*insn_read)(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - int (*insn_write)(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - int (*insn_bits)(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - int (*insn_config)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, - unsigned int *data); - - int (*do_cmd)(struct comedi_device *dev, struct comedi_subdevice *s); - int (*do_cmdtest)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_cmd *cmd); - int (*poll)(struct comedi_device *dev, struct comedi_subdevice *s); - int (*cancel)(struct comedi_device *dev, struct comedi_subdevice *s); - - /* called when the buffer changes */ - int (*buf_change)(struct comedi_device *dev, - struct comedi_subdevice *s); - - void (*munge)(struct comedi_device *dev, struct comedi_subdevice *s, - void *data, unsigned int num_bytes, - unsigned int start_chan_index); - enum dma_data_direction async_dma_dir; - - unsigned int state; - - struct device *class_dev; - int minor; - - unsigned int *readback; -}; - -/** - * struct comedi_buf_page - Describe a page of a COMEDI buffer - * @virt_addr: Kernel address of page. - * @dma_addr: DMA address of page if in DMA coherent memory. - */ -struct comedi_buf_page { - void *virt_addr; - dma_addr_t dma_addr; -}; - -/** - * struct comedi_buf_map - Describe pages in a COMEDI buffer - * @dma_hw_dev: Low-level hardware &struct device pointer copied from the - * COMEDI device's hw_dev member. - * @page_list: Pointer to array of &struct comedi_buf_page, one for each - * page in the buffer. - * @n_pages: Number of pages in the buffer. - * @dma_dir: DMA direction used to allocate pages of DMA coherent memory, - * or %DMA_NONE if pages allocated from regular memory. - * @refcount: &struct kref reference counter used to free the buffer. - * - * A COMEDI data buffer is allocated as individual pages, either in - * conventional memory or DMA coherent memory, depending on the attached, - * low-level hardware device. (The buffer pages also get mapped into the - * kernel's contiguous virtual address space pointed to by the 'prealloc_buf' - * member of &struct comedi_async.) - * - * The buffer is normally freed when the COMEDI device is detached from the - * low-level driver (which may happen due to device removal), but if it happens - * to be mmapped at the time, the pages cannot be freed until the buffer has - * been munmapped. That is what the reference counter is for. (The virtual - * address space pointed by 'prealloc_buf' is freed when the COMEDI device is - * detached.) - */ -struct comedi_buf_map { - struct device *dma_hw_dev; - struct comedi_buf_page *page_list; - unsigned int n_pages; - enum dma_data_direction dma_dir; - struct kref refcount; -}; - -/** - * struct comedi_async - Control data for asynchronous COMEDI commands - * @prealloc_buf: Kernel virtual address of allocated acquisition buffer. - * @prealloc_bufsz: Buffer size (in bytes). - * @buf_map: Map of buffer pages. - * @max_bufsize: Maximum allowed buffer size (in bytes). - * @buf_write_count: "Write completed" count (in bytes, modulo 2**32). - * @buf_write_alloc_count: "Allocated for writing" count (in bytes, - * modulo 2**32). - * @buf_read_count: "Read completed" count (in bytes, modulo 2**32). - * @buf_read_alloc_count: "Allocated for reading" count (in bytes, - * modulo 2**32). - * @buf_write_ptr: Buffer position for writer. - * @buf_read_ptr: Buffer position for reader. - * @cur_chan: Current position in chanlist for scan (for those drivers that - * use it). - * @scans_done: The number of scans completed. - * @scan_progress: Amount received or sent for current scan (in bytes). - * @munge_chan: Current position in chanlist for "munging". - * @munge_count: "Munge" count (in bytes, modulo 2**32). - * @munge_ptr: Buffer position for "munging". - * @events: Bit-vector of events that have occurred. - * @cmd: Details of comedi command in progress. - * @wait_head: Task wait queue for file reader or writer. - * @cb_mask: Bit-vector of events that should wake waiting tasks. - * @inttrig: Software trigger function for command, or NULL. - * - * Note about the ..._count and ..._ptr members: - * - * Think of the _Count values being integers of unlimited size, indexing - * into a buffer of infinite length (though only an advancing portion - * of the buffer of fixed length prealloc_bufsz is accessible at any - * time). Then: - * - * Buf_Read_Count <= Buf_Read_Alloc_Count <= Munge_Count <= - * Buf_Write_Count <= Buf_Write_Alloc_Count <= - * (Buf_Read_Count + prealloc_bufsz) - * - * (Those aren't the actual members, apart from prealloc_bufsz.) When the - * buffer is reset, those _Count values start at 0 and only increase in value, - * maintaining the above inequalities until the next time the buffer is - * reset. The buffer is divided into the following regions by the inequalities: - * - * [0, Buf_Read_Count): - * old region no longer accessible - * - * [Buf_Read_Count, Buf_Read_Alloc_Count): - * filled and munged region allocated for reading but not yet read - * - * [Buf_Read_Alloc_Count, Munge_Count): - * filled and munged region not yet allocated for reading - * - * [Munge_Count, Buf_Write_Count): - * filled region not yet munged - * - * [Buf_Write_Count, Buf_Write_Alloc_Count): - * unfilled region allocated for writing but not yet written - * - * [Buf_Write_Alloc_Count, Buf_Read_Count + prealloc_bufsz): - * unfilled region not yet allocated for writing - * - * [Buf_Read_Count + prealloc_bufsz, infinity): - * unfilled region not yet accessible - * - * Data needs to be written into the buffer before it can be read out, - * and may need to be converted (or "munged") between the two - * operations. Extra unfilled buffer space may need to allocated for - * writing (advancing Buf_Write_Alloc_Count) before new data is written. - * After writing new data, the newly filled space needs to be released - * (advancing Buf_Write_Count). This also results in the new data being - * "munged" (advancing Munge_Count). Before data is read out of the - * buffer, extra space may need to be allocated for reading (advancing - * Buf_Read_Alloc_Count). After the data has been read out, the space - * needs to be released (advancing Buf_Read_Count). - * - * The actual members, buf_read_count, buf_read_alloc_count, - * munge_count, buf_write_count, and buf_write_alloc_count take the - * value of the corresponding capitalized _Count values modulo 2^32 - * (UINT_MAX+1). Subtracting a "higher" _count value from a "lower" - * _count value gives the same answer as subtracting a "higher" _Count - * value from a lower _Count value because prealloc_bufsz < UINT_MAX+1. - * The modulo operation is done implicitly. - * - * The buf_read_ptr, munge_ptr, and buf_write_ptr members take the value - * of the corresponding capitalized _Count values modulo prealloc_bufsz. - * These correspond to byte indices in the physical buffer. The modulo - * operation is done by subtracting prealloc_bufsz when the value - * exceeds prealloc_bufsz (assuming prealloc_bufsz plus the increment is - * less than or equal to UINT_MAX). - */ -struct comedi_async { - void *prealloc_buf; - unsigned int prealloc_bufsz; - struct comedi_buf_map *buf_map; - unsigned int max_bufsize; - unsigned int buf_write_count; - unsigned int buf_write_alloc_count; - unsigned int buf_read_count; - unsigned int buf_read_alloc_count; - unsigned int buf_write_ptr; - unsigned int buf_read_ptr; - unsigned int cur_chan; - unsigned int scans_done; - unsigned int scan_progress; - unsigned int munge_chan; - unsigned int munge_count; - unsigned int munge_ptr; - unsigned int events; - struct comedi_cmd cmd; - wait_queue_head_t wait_head; - unsigned int cb_mask; - int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s, - unsigned int x); -}; - -/** - * enum comedi_cb - &struct comedi_async callback "events" - * @COMEDI_CB_EOS: end-of-scan - * @COMEDI_CB_EOA: end-of-acquisition/output - * @COMEDI_CB_BLOCK: data has arrived, wakes up read() / write() - * @COMEDI_CB_EOBUF: DEPRECATED: end of buffer - * @COMEDI_CB_ERROR: card error during acquisition - * @COMEDI_CB_OVERFLOW: buffer overflow/underflow - * @COMEDI_CB_ERROR_MASK: events that indicate an error has occurred - * @COMEDI_CB_CANCEL_MASK: events that will cancel an async command - */ -enum comedi_cb { - COMEDI_CB_EOS = BIT(0), - COMEDI_CB_EOA = BIT(1), - COMEDI_CB_BLOCK = BIT(2), - COMEDI_CB_EOBUF = BIT(3), - COMEDI_CB_ERROR = BIT(4), - COMEDI_CB_OVERFLOW = BIT(5), - /* masks */ - COMEDI_CB_ERROR_MASK = (COMEDI_CB_ERROR | COMEDI_CB_OVERFLOW), - COMEDI_CB_CANCEL_MASK = (COMEDI_CB_EOA | COMEDI_CB_ERROR_MASK) -}; - -/** - * struct comedi_driver - COMEDI driver registration - * @driver_name: Name of driver. - * @module: Owning module. - * @attach: The optional "attach" handler for manually configured COMEDI - * devices. - * @detach: The "detach" handler for deconfiguring COMEDI devices. - * @auto_attach: The optional "auto_attach" handler for automatically - * configured COMEDI devices. - * @num_names: Optional number of "board names" supported. - * @board_name: Optional pointer to a pointer to a board name. The pointer - * to a board name is embedded in an element of a driver-defined array - * of static, read-only board type information. - * @offset: Optional size of each element of the driver-defined array of - * static, read-only board type information, i.e. the offset between each - * pointer to a board name. - * - * This is used with comedi_driver_register() and comedi_driver_unregister() to - * register and unregister a low-level COMEDI driver with the COMEDI core. - * - * If @num_names is non-zero, @board_name should be non-NULL, and @offset - * should be at least sizeof(*board_name). These are used by the handler for - * the %COMEDI_DEVCONFIG ioctl to match a hardware device and its driver by - * board name. If @num_names is zero, the %COMEDI_DEVCONFIG ioctl matches a - * hardware device and its driver by driver name. This is only useful if the - * @attach handler is set. If @num_names is non-zero, the driver's @attach - * handler will be called with the COMEDI device structure's board_ptr member - * pointing to the matched pointer to a board name within the driver's private - * array of static, read-only board type information. - * - * The @detach handler has two roles. If a COMEDI device was successfully - * configured by the @attach or @auto_attach handler, it is called when the - * device is being deconfigured (by the %COMEDI_DEVCONFIG ioctl, or due to - * unloading of the driver, or due to device removal). It is also called when - * the @attach or @auto_attach handler returns an error. Therefore, the - * @attach or @auto_attach handlers can defer clean-up on error until the - * @detach handler is called. If the @attach or @auto_attach handlers free - * any resources themselves, they must prevent the @detach handler from - * freeing the same resources. The @detach handler must not assume that all - * resources requested by the @attach or @auto_attach handler were - * successfully allocated. - */ -struct comedi_driver { - /* private: */ - struct comedi_driver *next; /* Next in list of COMEDI drivers. */ - /* public: */ - const char *driver_name; - struct module *module; - int (*attach)(struct comedi_device *dev, struct comedi_devconfig *it); - void (*detach)(struct comedi_device *dev); - int (*auto_attach)(struct comedi_device *dev, unsigned long context); - unsigned int num_names; - const char *const *board_name; - int offset; -}; - -/** - * struct comedi_device - Working data for a COMEDI device - * @use_count: Number of open file objects. - * @driver: Low-level COMEDI driver attached to this COMEDI device. - * @pacer: Optional pointer to a dynamically allocated acquisition pacer - * control. It is freed automatically after the COMEDI device is - * detached from the low-level driver. - * @private: Optional pointer to private data allocated by the low-level - * driver. It is freed automatically after the COMEDI device is - * detached from the low-level driver. - * @class_dev: Sysfs comediX device. - * @minor: Minor device number of COMEDI char device (0-47). - * @detach_count: Counter incremented every time the COMEDI device is detached. - * Used for checking a previous attachment is still valid. - * @hw_dev: Optional pointer to the low-level hardware &struct device. It is - * required for automatically configured COMEDI devices and optional for - * COMEDI devices configured by the %COMEDI_DEVCONFIG ioctl, although - * the bus-specific COMEDI functions only work if it is set correctly. - * It is also passed to dma_alloc_coherent() for COMEDI subdevices that - * have their 'async_dma_dir' member set to something other than - * %DMA_NONE. - * @board_name: Pointer to a COMEDI board name or a COMEDI driver name. When - * the low-level driver's "attach" handler is called by the handler for - * the %COMEDI_DEVCONFIG ioctl, it either points to a matched board name - * string if the 'num_names' member of the &struct comedi_driver is - * non-zero, otherwise it points to the low-level driver name string. - * When the low-lever driver's "auto_attach" handler is called for an - * automatically configured COMEDI device, it points to the low-level - * driver name string. The low-level driver is free to change it in its - * "attach" or "auto_attach" handler if it wishes. - * @board_ptr: Optional pointer to private, read-only board type information in - * the low-level driver. If the 'num_names' member of the &struct - * comedi_driver is non-zero, the handler for the %COMEDI_DEVCONFIG ioctl - * will point it to a pointer to a matched board name string within the - * driver's private array of static, read-only board type information when - * calling the driver's "attach" handler. The low-level driver is free to - * change it. - * @attached: Flag indicating that the COMEDI device is attached to a low-level - * driver. - * @ioenabled: Flag used to indicate that a PCI device has been enabled and - * its regions requested. - * @spinlock: Generic spin-lock for use by the low-level driver. - * @mutex: Generic mutex for use by the COMEDI core module. - * @attach_lock: &struct rw_semaphore used to guard against the COMEDI device - * being detached while an operation is in progress. The down_write() - * operation is only allowed while @mutex is held and is used when - * changing @attached and @detach_count and calling the low-level driver's - * "detach" handler. The down_read() operation is generally used without - * holding @mutex. - * @refcount: &struct kref reference counter for freeing COMEDI device. - * @n_subdevices: Number of COMEDI subdevices allocated by the low-level - * driver for this device. - * @subdevices: Dynamically allocated array of COMEDI subdevices. - * @mmio: Optional pointer to a remapped MMIO region set by the low-level - * driver. - * @iobase: Optional base of an I/O port region requested by the low-level - * driver. - * @iolen: Length of I/O port region requested at @iobase. - * @irq: Optional IRQ number requested by the low-level driver. - * @read_subdev: Optional pointer to a default COMEDI subdevice operated on by - * the read() file operation. Set by the low-level driver. - * @write_subdev: Optional pointer to a default COMEDI subdevice operated on by - * the write() file operation. Set by the low-level driver. - * @async_queue: Storage for fasync_helper(). - * @open: Optional pointer to a function set by the low-level driver to be - * called when @use_count changes from 0 to 1. - * @close: Optional pointer to a function set by the low-level driver to be - * called when @use_count changed from 1 to 0. - * @insn_device_config: Optional pointer to a handler for all sub-instructions - * except %INSN_DEVICE_CONFIG_GET_ROUTES of the %INSN_DEVICE_CONFIG - * instruction. If this is not initialized by the low-level driver, a - * default handler will be set during post-configuration. - * @get_valid_routes: Optional pointer to a handler for the - * %INSN_DEVICE_CONFIG_GET_ROUTES sub-instruction of the - * %INSN_DEVICE_CONFIG instruction set. If this is not initialized by the - * low-level driver, a default handler that copies zero routes back to the - * user will be used. - * - * This is the main control data structure for a COMEDI device (as far as the - * COMEDI core is concerned). There are two groups of COMEDI devices - - * "legacy" devices that are configured by the handler for the - * %COMEDI_DEVCONFIG ioctl, and automatically configured devices resulting - * from a call to comedi_auto_config() as a result of a bus driver probe in - * a low-level COMEDI driver. The "legacy" COMEDI devices are allocated - * during module initialization if the "comedi_num_legacy_minors" module - * parameter is non-zero and use minor device numbers from 0 to - * comedi_num_legacy_minors minus one. The automatically configured COMEDI - * devices are allocated on demand and use minor device numbers from - * comedi_num_legacy_minors to 47. - */ -struct comedi_device { - int use_count; - struct comedi_driver *driver; - struct comedi_8254 *pacer; - void *private; - - struct device *class_dev; - int minor; - unsigned int detach_count; - struct device *hw_dev; - - const char *board_name; - const void *board_ptr; - unsigned int attached:1; - unsigned int ioenabled:1; - spinlock_t spinlock; /* generic spin-lock for low-level driver */ - struct mutex mutex; /* generic mutex for COMEDI core */ - struct rw_semaphore attach_lock; - struct kref refcount; - - int n_subdevices; - struct comedi_subdevice *subdevices; - - /* dumb */ - void __iomem *mmio; - unsigned long iobase; - unsigned long iolen; - unsigned int irq; - - struct comedi_subdevice *read_subdev; - struct comedi_subdevice *write_subdev; - - struct fasync_struct *async_queue; - - int (*open)(struct comedi_device *dev); - void (*close)(struct comedi_device *dev); - int (*insn_device_config)(struct comedi_device *dev, - struct comedi_insn *insn, unsigned int *data); - unsigned int (*get_valid_routes)(struct comedi_device *dev, - unsigned int n_pairs, - unsigned int *pair_data); -}; - -/* - * function prototypes - */ - -void comedi_event(struct comedi_device *dev, struct comedi_subdevice *s); - -struct comedi_device *comedi_dev_get_from_minor(unsigned int minor); -int comedi_dev_put(struct comedi_device *dev); - -bool comedi_is_subdevice_running(struct comedi_subdevice *s); - -void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size); -void comedi_set_spriv_auto_free(struct comedi_subdevice *s); - -int comedi_check_chanlist(struct comedi_subdevice *s, - int n, - unsigned int *chanlist); - -/* range stuff */ - -#define RANGE(a, b) {(a) * 1e6, (b) * 1e6, 0} -#define RANGE_ext(a, b) {(a) * 1e6, (b) * 1e6, RF_EXTERNAL} -#define RANGE_mA(a, b) {(a) * 1e6, (b) * 1e6, UNIT_mA} -#define RANGE_unitless(a, b) {(a) * 1e6, (b) * 1e6, 0} -#define BIP_RANGE(a) {-(a) * 1e6, (a) * 1e6, 0} -#define UNI_RANGE(a) {0, (a) * 1e6, 0} - -extern const struct comedi_lrange range_bipolar10; -extern const struct comedi_lrange range_bipolar5; -extern const struct comedi_lrange range_bipolar2_5; -extern const struct comedi_lrange range_unipolar10; -extern const struct comedi_lrange range_unipolar5; -extern const struct comedi_lrange range_unipolar2_5; -extern const struct comedi_lrange range_0_20mA; -extern const struct comedi_lrange range_4_20mA; -extern const struct comedi_lrange range_0_32mA; -extern const struct comedi_lrange range_unknown; - -#define range_digital range_unipolar5 - -/** - * struct comedi_lrange - Describes a COMEDI range table - * @length: Number of entries in the range table. - * @range: Array of &struct comedi_krange, one for each range. - * - * Each element of @range[] describes the minimum and maximum physical range - * and the type of units. Typically, the type of unit is %UNIT_volt - * (i.e. volts) and the minimum and maximum are in millionths of a volt. - * There may also be a flag that indicates the minimum and maximum are merely - * scale factors for an unknown, external reference. - */ -struct comedi_lrange { - int length; - struct comedi_krange range[]; -}; - -/** - * comedi_range_is_bipolar() - Test if subdevice range is bipolar - * @s: COMEDI subdevice. - * @range: Index of range within a range table. - * - * Tests whether a range is bipolar by checking whether its minimum value - * is negative. - * - * Assumes @range is valid. Does not work for subdevices using a - * channel-specific range table list. - * - * Return: - * %true if the range is bipolar. - * %false if the range is unipolar. - */ -static inline bool comedi_range_is_bipolar(struct comedi_subdevice *s, - unsigned int range) -{ - return s->range_table->range[range].min < 0; -} - -/** - * comedi_range_is_unipolar() - Test if subdevice range is unipolar - * @s: COMEDI subdevice. - * @range: Index of range within a range table. - * - * Tests whether a range is unipolar by checking whether its minimum value - * is at least 0. - * - * Assumes @range is valid. Does not work for subdevices using a - * channel-specific range table list. - * - * Return: - * %true if the range is unipolar. - * %false if the range is bipolar. - */ -static inline bool comedi_range_is_unipolar(struct comedi_subdevice *s, - unsigned int range) -{ - return s->range_table->range[range].min >= 0; -} - -/** - * comedi_range_is_external() - Test if subdevice range is external - * @s: COMEDI subdevice. - * @range: Index of range within a range table. - * - * Tests whether a range is externally reference by checking whether its - * %RF_EXTERNAL flag is set. - * - * Assumes @range is valid. Does not work for subdevices using a - * channel-specific range table list. - * - * Return: - * %true if the range is external. - * %false if the range is internal. - */ -static inline bool comedi_range_is_external(struct comedi_subdevice *s, - unsigned int range) -{ - return !!(s->range_table->range[range].flags & RF_EXTERNAL); -} - -/** - * comedi_chan_range_is_bipolar() - Test if channel-specific range is bipolar - * @s: COMEDI subdevice. - * @chan: The channel number. - * @range: Index of range within a range table. - * - * Tests whether a range is bipolar by checking whether its minimum value - * is negative. - * - * Assumes @chan and @range are valid. Only works for subdevices with a - * channel-specific range table list. - * - * Return: - * %true if the range is bipolar. - * %false if the range is unipolar. - */ -static inline bool comedi_chan_range_is_bipolar(struct comedi_subdevice *s, - unsigned int chan, - unsigned int range) -{ - return s->range_table_list[chan]->range[range].min < 0; -} - -/** - * comedi_chan_range_is_unipolar() - Test if channel-specific range is unipolar - * @s: COMEDI subdevice. - * @chan: The channel number. - * @range: Index of range within a range table. - * - * Tests whether a range is unipolar by checking whether its minimum value - * is at least 0. - * - * Assumes @chan and @range are valid. Only works for subdevices with a - * channel-specific range table list. - * - * Return: - * %true if the range is unipolar. - * %false if the range is bipolar. - */ -static inline bool comedi_chan_range_is_unipolar(struct comedi_subdevice *s, - unsigned int chan, - unsigned int range) -{ - return s->range_table_list[chan]->range[range].min >= 0; -} - -/** - * comedi_chan_range_is_external() - Test if channel-specific range is external - * @s: COMEDI subdevice. - * @chan: The channel number. - * @range: Index of range within a range table. - * - * Tests whether a range is externally reference by checking whether its - * %RF_EXTERNAL flag is set. - * - * Assumes @chan and @range are valid. Only works for subdevices with a - * channel-specific range table list. - * - * Return: - * %true if the range is bipolar. - * %false if the range is unipolar. - */ -static inline bool comedi_chan_range_is_external(struct comedi_subdevice *s, - unsigned int chan, - unsigned int range) -{ - return !!(s->range_table_list[chan]->range[range].flags & RF_EXTERNAL); -} - -/** - * comedi_offset_munge() - Convert between offset binary and 2's complement - * @s: COMEDI subdevice. - * @val: Value to be converted. - * - * Toggles the highest bit of a sample value to toggle between offset binary - * and 2's complement. Assumes that @s->maxdata is a power of 2 minus 1. - * - * Return: The converted value. - */ -static inline unsigned int comedi_offset_munge(struct comedi_subdevice *s, - unsigned int val) -{ - return val ^ s->maxdata ^ (s->maxdata >> 1); -} - -/** - * comedi_bytes_per_sample() - Determine subdevice sample size - * @s: COMEDI subdevice. - * - * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on - * whether the %SDF_LSAMPL subdevice flag is set or not. - * - * Return: The subdevice sample size. - */ -static inline unsigned int comedi_bytes_per_sample(struct comedi_subdevice *s) -{ - return s->subdev_flags & SDF_LSAMPL ? sizeof(int) : sizeof(short); -} - -/** - * comedi_sample_shift() - Determine log2 of subdevice sample size - * @s: COMEDI subdevice. - * - * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on - * whether the %SDF_LSAMPL subdevice flag is set or not. The log2 of the - * sample size will be 2 or 1 and can be used as the right operand of a - * bit-shift operator to multiply or divide something by the sample size. - * - * Return: log2 of the subdevice sample size. - */ -static inline unsigned int comedi_sample_shift(struct comedi_subdevice *s) -{ - return s->subdev_flags & SDF_LSAMPL ? 2 : 1; -} - -/** - * comedi_bytes_to_samples() - Convert a number of bytes to a number of samples - * @s: COMEDI subdevice. - * @nbytes: Number of bytes - * - * Return: The number of bytes divided by the subdevice sample size. - */ -static inline unsigned int comedi_bytes_to_samples(struct comedi_subdevice *s, - unsigned int nbytes) -{ - return nbytes >> comedi_sample_shift(s); -} - -/** - * comedi_samples_to_bytes() - Convert a number of samples to a number of bytes - * @s: COMEDI subdevice. - * @nsamples: Number of samples. - * - * Return: The number of samples multiplied by the subdevice sample size. - * (Does not check for arithmetic overflow.) - */ -static inline unsigned int comedi_samples_to_bytes(struct comedi_subdevice *s, - unsigned int nsamples) -{ - return nsamples << comedi_sample_shift(s); -} - -/** - * comedi_check_trigger_src() - Trivially validate a comedi_cmd trigger source - * @src: Pointer to the trigger source to validate. - * @flags: Bitmask of valid %TRIG_* for the trigger. - * - * This is used in "step 1" of the do_cmdtest functions of comedi drivers - * to validate the comedi_cmd triggers. The mask of the @src against the - * @flags allows the userspace comedilib to pass all the comedi_cmd - * triggers as %TRIG_ANY and get back a bitmask of the valid trigger sources. - * - * Return: - * 0 if trigger sources in *@src are all supported. - * -EINVAL if any trigger source in *@src is unsupported. - */ -static inline int comedi_check_trigger_src(unsigned int *src, - unsigned int flags) -{ - unsigned int orig_src = *src; - - *src = orig_src & flags; - if (*src == TRIG_INVALID || *src != orig_src) - return -EINVAL; - return 0; -} - -/** - * comedi_check_trigger_is_unique() - Make sure a trigger source is unique - * @src: The trigger source to check. - * - * Return: - * 0 if no more than one trigger source is set. - * -EINVAL if more than one trigger source is set. - */ -static inline int comedi_check_trigger_is_unique(unsigned int src) -{ - /* this test is true if more than one _src bit is set */ - if ((src & (src - 1)) != 0) - return -EINVAL; - return 0; -} - -/** - * comedi_check_trigger_arg_is() - Trivially validate a trigger argument - * @arg: Pointer to the trigger arg to validate. - * @val: The value the argument should be. - * - * Forces *@arg to be @val. - * - * Return: - * 0 if *@arg was already @val. - * -EINVAL if *@arg differed from @val. - */ -static inline int comedi_check_trigger_arg_is(unsigned int *arg, - unsigned int val) -{ - if (*arg != val) { - *arg = val; - return -EINVAL; - } - return 0; -} - -/** - * comedi_check_trigger_arg_min() - Trivially validate a trigger argument min - * @arg: Pointer to the trigger arg to validate. - * @val: The minimum value the argument should be. - * - * Forces *@arg to be at least @val, setting it to @val if necessary. - * - * Return: - * 0 if *@arg was already at least @val. - * -EINVAL if *@arg was less than @val. - */ -static inline int comedi_check_trigger_arg_min(unsigned int *arg, - unsigned int val) -{ - if (*arg < val) { - *arg = val; - return -EINVAL; - } - return 0; -} - -/** - * comedi_check_trigger_arg_max() - Trivially validate a trigger argument max - * @arg: Pointer to the trigger arg to validate. - * @val: The maximum value the argument should be. - * - * Forces *@arg to be no more than @val, setting it to @val if necessary. - * - * Return: - * 0 if*@arg was already no more than @val. - * -EINVAL if *@arg was greater than @val. - */ -static inline int comedi_check_trigger_arg_max(unsigned int *arg, - unsigned int val) -{ - if (*arg > val) { - *arg = val; - return -EINVAL; - } - return 0; -} - -/* - * Must set dev->hw_dev if you wish to dma directly into comedi's buffer. - * Also useful for retrieving a previously configured hardware device of - * known bus type. Set automatically for auto-configured devices. - * Automatically set to NULL when detaching hardware device. - */ -int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev); - -/** - * comedi_buf_n_bytes_ready - Determine amount of unread data in buffer - * @s: COMEDI subdevice. - * - * Determines the number of bytes of unread data in the asynchronous - * acquisition data buffer for a subdevice. The data in question might not - * have been fully "munged" yet. - * - * Returns: The amount of unread data in bytes. - */ -static inline unsigned int comedi_buf_n_bytes_ready(struct comedi_subdevice *s) -{ - return s->async->buf_write_count - s->async->buf_read_count; -} - -unsigned int comedi_buf_write_alloc(struct comedi_subdevice *s, unsigned int n); -unsigned int comedi_buf_write_free(struct comedi_subdevice *s, unsigned int n); - -unsigned int comedi_buf_read_n_available(struct comedi_subdevice *s); -unsigned int comedi_buf_read_alloc(struct comedi_subdevice *s, unsigned int n); -unsigned int comedi_buf_read_free(struct comedi_subdevice *s, unsigned int n); - -unsigned int comedi_buf_write_samples(struct comedi_subdevice *s, - const void *data, unsigned int nsamples); -unsigned int comedi_buf_read_samples(struct comedi_subdevice *s, - void *data, unsigned int nsamples); - -/* drivers.c - general comedi driver functions */ - -#define COMEDI_TIMEOUT_MS 1000 - -int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, - struct comedi_insn *insn, - int (*cb)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned long context), - unsigned long context); - -unsigned int comedi_handle_events(struct comedi_device *dev, - struct comedi_subdevice *s); - -int comedi_dio_insn_config(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data, - unsigned int mask); -unsigned int comedi_dio_update_state(struct comedi_subdevice *s, - unsigned int *data); -unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, - struct comedi_cmd *cmd); -unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); -unsigned int comedi_nscans_left(struct comedi_subdevice *s, - unsigned int nscans); -unsigned int comedi_nsamples_left(struct comedi_subdevice *s, - unsigned int nsamples); -void comedi_inc_scan_progress(struct comedi_subdevice *s, - unsigned int num_bytes); - -void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size); -int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices); -int comedi_alloc_subdev_readback(struct comedi_subdevice *s); - -int comedi_readback_insn_read(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); - -int comedi_load_firmware(struct comedi_device *dev, struct device *hw_dev, - const char *name, - int (*cb)(struct comedi_device *dev, - const u8 *data, size_t size, - unsigned long context), - unsigned long context); - -int __comedi_request_region(struct comedi_device *dev, - unsigned long start, unsigned long len); -int comedi_request_region(struct comedi_device *dev, - unsigned long start, unsigned long len); -void comedi_legacy_detach(struct comedi_device *dev); - -int comedi_auto_config(struct device *hardware_device, - struct comedi_driver *driver, unsigned long context); -void comedi_auto_unconfig(struct device *hardware_device); - -int comedi_driver_register(struct comedi_driver *driver); -void comedi_driver_unregister(struct comedi_driver *driver); - -/** - * module_comedi_driver() - Helper macro for registering a comedi driver - * @__comedi_driver: comedi_driver struct - * - * Helper macro for comedi drivers which do not do anything special in module - * init/exit. This eliminates a lot of boilerplate. Each module may only use - * this macro once, and calling it replaces module_init() and module_exit(). - */ -#define module_comedi_driver(__comedi_driver) \ - module_driver(__comedi_driver, comedi_driver_register, \ - comedi_driver_unregister) - -#endif /* _COMEDIDEV_H */ diff --git a/drivers/comedi/comedilib.h b/drivers/comedi/comedilib.h deleted file mode 100644 index 0223c9cd9215..000000000000 --- a/drivers/comedi/comedilib.h +++ /dev/null @@ -1,26 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedilib.h - * Header file for kcomedilib - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1998-2001 David A. Schleef - */ - -#ifndef _LINUX_COMEDILIB_H -#define _LINUX_COMEDILIB_H - -struct comedi_device *comedi_open(const char *path); -int comedi_close(struct comedi_device *dev); -int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev, - unsigned int chan, unsigned int *io); -int comedi_dio_config(struct comedi_device *dev, unsigned int subdev, - unsigned int chan, unsigned int io); -int comedi_dio_bitfield2(struct comedi_device *dev, unsigned int subdev, - unsigned int mask, unsigned int *bits, - unsigned int base_channel); -int comedi_find_subdevice_by_type(struct comedi_device *dev, int type, - unsigned int subd); -int comedi_get_n_channels(struct comedi_device *dev, unsigned int subdevice); - -#endif diff --git a/drivers/comedi/drivers.c b/drivers/comedi/drivers.c index 750a6ff3c03c..8eb1f699a857 100644 --- a/drivers/comedi/drivers.c +++ b/drivers/comedi/drivers.c @@ -17,8 +17,7 @@ #include #include #include - -#include "comedidev.h" +#include #include "comedi_internal.h" struct comedi_driver *comedi_drivers; diff --git a/drivers/comedi/drivers/8255.c b/drivers/comedi/drivers/8255.c index e23335c75867..f23a52b7c919 100644 --- a/drivers/comedi/drivers/8255.c +++ b/drivers/comedi/drivers/8255.c @@ -40,7 +40,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/8255_pci.c b/drivers/comedi/drivers/8255_pci.c index 5a810f0e532a..76b8b4762bae 100644 --- a/drivers/comedi/drivers/8255_pci.c +++ b/drivers/comedi/drivers/8255_pci.c @@ -53,8 +53,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/addi_apci_1032.c b/drivers/comedi/drivers/addi_apci_1032.c index 81a246fbcc01..8eec6d9402de 100644 --- a/drivers/comedi/drivers/addi_apci_1032.c +++ b/drivers/comedi/drivers/addi_apci_1032.c @@ -63,8 +63,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/addi_apci_1500.c b/drivers/comedi/drivers/addi_apci_1500.c index b04c15dcfb57..c94c78588889 100644 --- a/drivers/comedi/drivers/addi_apci_1500.c +++ b/drivers/comedi/drivers/addi_apci_1500.c @@ -14,8 +14,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" #include "z8536.h" diff --git a/drivers/comedi/drivers/addi_apci_1516.c b/drivers/comedi/drivers/addi_apci_1516.c index 274ec9fb030c..3c48b72dad9d 100644 --- a/drivers/comedi/drivers/addi_apci_1516.c +++ b/drivers/comedi/drivers/addi_apci_1516.c @@ -14,8 +14,8 @@ */ #include +#include -#include "../comedi_pci.h" #include "addi_watchdog.h" /* diff --git a/drivers/comedi/drivers/addi_apci_1564.c b/drivers/comedi/drivers/addi_apci_1564.c index 06fc7ed96200..0cd40948bee7 100644 --- a/drivers/comedi/drivers/addi_apci_1564.c +++ b/drivers/comedi/drivers/addi_apci_1564.c @@ -68,8 +68,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "addi_tcw.h" #include "addi_watchdog.h" diff --git a/drivers/comedi/drivers/addi_apci_16xx.c b/drivers/comedi/drivers/addi_apci_16xx.c index c306aa41df97..ec2c321d2431 100644 --- a/drivers/comedi/drivers/addi_apci_16xx.c +++ b/drivers/comedi/drivers/addi_apci_16xx.c @@ -14,8 +14,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/addi_apci_2032.c b/drivers/comedi/drivers/addi_apci_2032.c index e9a2b37a4ae0..e048dfc3ec77 100644 --- a/drivers/comedi/drivers/addi_apci_2032.c +++ b/drivers/comedi/drivers/addi_apci_2032.c @@ -16,8 +16,8 @@ #include #include #include +#include -#include "../comedi_pci.h" #include "addi_watchdog.h" /* diff --git a/drivers/comedi/drivers/addi_apci_2200.c b/drivers/comedi/drivers/addi_apci_2200.c index 4c5aee784bd9..00378c9dddc8 100644 --- a/drivers/comedi/drivers/addi_apci_2200.c +++ b/drivers/comedi/drivers/addi_apci_2200.c @@ -14,8 +14,8 @@ */ #include +#include -#include "../comedi_pci.h" #include "addi_watchdog.h" /* diff --git a/drivers/comedi/drivers/addi_apci_3120.c b/drivers/comedi/drivers/addi_apci_3120.c index 1ed3b33d1a30..28a242e69721 100644 --- a/drivers/comedi/drivers/addi_apci_3120.c +++ b/drivers/comedi/drivers/addi_apci_3120.c @@ -14,8 +14,8 @@ #include #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/addi_apci_3501.c b/drivers/comedi/drivers/addi_apci_3501.c index f0c9642f3f1a..ecb5552f1785 100644 --- a/drivers/comedi/drivers/addi_apci_3501.c +++ b/drivers/comedi/drivers/addi_apci_3501.c @@ -41,8 +41,8 @@ */ #include +#include -#include "../comedi_pci.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/addi_apci_3xxx.c b/drivers/comedi/drivers/addi_apci_3xxx.c index a90d59377e18..bc72273e6a29 100644 --- a/drivers/comedi/drivers/addi_apci_3xxx.c +++ b/drivers/comedi/drivers/addi_apci_3xxx.c @@ -15,8 +15,7 @@ #include #include - -#include "../comedi_pci.h" +#include #define CONV_UNIT_NS BIT(0) #define CONV_UNIT_US BIT(1) diff --git a/drivers/comedi/drivers/addi_watchdog.c b/drivers/comedi/drivers/addi_watchdog.c index 69b323fb869f..ed87ab432020 100644 --- a/drivers/comedi/drivers/addi_watchdog.c +++ b/drivers/comedi/drivers/addi_watchdog.c @@ -10,7 +10,7 @@ */ #include -#include "../comedidev.h" +#include #include "addi_tcw.h" #include "addi_watchdog.h" diff --git a/drivers/comedi/drivers/adl_pci6208.c b/drivers/comedi/drivers/adl_pci6208.c index 9ae4cc523dd4..b27354a51f5c 100644 --- a/drivers/comedi/drivers/adl_pci6208.c +++ b/drivers/comedi/drivers/adl_pci6208.c @@ -24,8 +24,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI-6208/6216-GL register map diff --git a/drivers/comedi/drivers/adl_pci7x3x.c b/drivers/comedi/drivers/adl_pci7x3x.c index 8fc45638ff59..e9f22de9b6f1 100644 --- a/drivers/comedi/drivers/adl_pci7x3x.c +++ b/drivers/comedi/drivers/adl_pci7x3x.c @@ -46,8 +46,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "plx9052.h" diff --git a/drivers/comedi/drivers/adl_pci8164.c b/drivers/comedi/drivers/adl_pci8164.c index d5e1bda81557..0c513a67a264 100644 --- a/drivers/comedi/drivers/adl_pci8164.c +++ b/drivers/comedi/drivers/adl_pci8164.c @@ -19,8 +19,7 @@ #include #include - -#include "../comedi_pci.h" +#include #define PCI8164_AXIS(x) ((x) * 0x08) #define PCI8164_CMD_MSTS_REG 0x00 diff --git a/drivers/comedi/drivers/adl_pci9111.c b/drivers/comedi/drivers/adl_pci9111.c index a062c5ab20e9..65454f3ecc91 100644 --- a/drivers/comedi/drivers/adl_pci9111.c +++ b/drivers/comedi/drivers/adl_pci9111.c @@ -42,8 +42,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "plx9052.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/adl_pci9118.c b/drivers/comedi/drivers/adl_pci9118.c index cda3a4267dca..248cec3d894f 100644 --- a/drivers/comedi/drivers/adl_pci9118.c +++ b/drivers/comedi/drivers/adl_pci9118.c @@ -78,8 +78,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "amcc_s5933.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/adq12b.c b/drivers/comedi/drivers/adq12b.c index d719f76709ef..19d765182006 100644 --- a/drivers/comedi/drivers/adq12b.c +++ b/drivers/comedi/drivers/adq12b.c @@ -48,8 +48,7 @@ #include #include - -#include "../comedidev.h" +#include /* address scheme (page 2.17 of the manual) */ #define ADQ12B_CTREG 0x00 diff --git a/drivers/comedi/drivers/adv_pci1710.c b/drivers/comedi/drivers/adv_pci1710.c index 090607760be6..47a800d72e58 100644 --- a/drivers/comedi/drivers/adv_pci1710.c +++ b/drivers/comedi/drivers/adv_pci1710.c @@ -30,8 +30,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "amcc_s5933.h" diff --git a/drivers/comedi/drivers/adv_pci1720.c b/drivers/comedi/drivers/adv_pci1720.c index 2fcd7e8e7d85..2619591ba301 100644 --- a/drivers/comedi/drivers/adv_pci1720.c +++ b/drivers/comedi/drivers/adv_pci1720.c @@ -42,8 +42,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR2 Register map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1723.c b/drivers/comedi/drivers/adv_pci1723.c index 23660a9fdb9c..e2aedb152068 100644 --- a/drivers/comedi/drivers/adv_pci1723.c +++ b/drivers/comedi/drivers/adv_pci1723.c @@ -32,8 +32,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI Bar 2 I/O Register map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1724.c b/drivers/comedi/drivers/adv_pci1724.c index e8ab573c839f..bb43b7deeb56 100644 --- a/drivers/comedi/drivers/adv_pci1724.c +++ b/drivers/comedi/drivers/adv_pci1724.c @@ -38,8 +38,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI bar 2 Register I/O map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1760.c b/drivers/comedi/drivers/adv_pci1760.c index 6de8ab97d346..fcfc2e299110 100644 --- a/drivers/comedi/drivers/adv_pci1760.c +++ b/drivers/comedi/drivers/adv_pci1760.c @@ -22,8 +22,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI-1760 Register Map diff --git a/drivers/comedi/drivers/adv_pci_dio.c b/drivers/comedi/drivers/adv_pci_dio.c index 54c7419c8ca6..5947f08b9a1e 100644 --- a/drivers/comedi/drivers/adv_pci_dio.c +++ b/drivers/comedi/drivers/adv_pci_dio.c @@ -23,8 +23,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "8255.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/aio_aio12_8.c b/drivers/comedi/drivers/aio_aio12_8.c index 4829115921a3..36c3a2d8a352 100644 --- a/drivers/comedi/drivers/aio_aio12_8.c +++ b/drivers/comedi/drivers/aio_aio12_8.c @@ -22,7 +22,7 @@ */ #include -#include "../comedidev.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/aio_iiro_16.c b/drivers/comedi/drivers/aio_iiro_16.c index fe3876235075..b00fab0b89d4 100644 --- a/drivers/comedi/drivers/aio_iiro_16.c +++ b/drivers/comedi/drivers/aio_iiro_16.c @@ -30,8 +30,7 @@ #include #include - -#include "../comedidev.h" +#include #define AIO_IIRO_16_RELAY_0_7 0x00 #define AIO_IIRO_16_INPUT_0_7 0x01 diff --git a/drivers/comedi/drivers/amplc_dio200.c b/drivers/comedi/drivers/amplc_dio200.c index fa19c9e7c56b..4544bcdd8a70 100644 --- a/drivers/comedi/drivers/amplc_dio200.c +++ b/drivers/comedi/drivers/amplc_dio200.c @@ -185,7 +185,7 @@ */ #include -#include "../comedidev.h" +#include #include "amplc_dio200.h" diff --git a/drivers/comedi/drivers/amplc_dio200_common.c b/drivers/comedi/drivers/amplc_dio200_common.c index a3454130d5f8..950c50be4ff3 100644 --- a/drivers/comedi/drivers/amplc_dio200_common.c +++ b/drivers/comedi/drivers/amplc_dio200_common.c @@ -12,8 +12,7 @@ #include #include - -#include "../comedidev.h" +#include #include "amplc_dio200.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/amplc_dio200_pci.c b/drivers/comedi/drivers/amplc_dio200_pci.c index 1bd7a42c8464..527994d82a1f 100644 --- a/drivers/comedi/drivers/amplc_dio200_pci.c +++ b/drivers/comedi/drivers/amplc_dio200_pci.c @@ -214,8 +214,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "amplc_dio200.h" diff --git a/drivers/comedi/drivers/amplc_pc236.c b/drivers/comedi/drivers/amplc_pc236.c index c377af1d5246..b21e0c906aab 100644 --- a/drivers/comedi/drivers/amplc_pc236.c +++ b/drivers/comedi/drivers/amplc_pc236.c @@ -32,8 +32,7 @@ */ #include - -#include "../comedidev.h" +#include #include "amplc_pc236.h" diff --git a/drivers/comedi/drivers/amplc_pc236_common.c b/drivers/comedi/drivers/amplc_pc236_common.c index 981d281e87a1..b8b0a624f72b 100644 --- a/drivers/comedi/drivers/amplc_pc236_common.c +++ b/drivers/comedi/drivers/amplc_pc236_common.c @@ -11,8 +11,7 @@ #include #include - -#include "../comedidev.h" +#include #include "amplc_pc236.h" #include "8255.h" diff --git a/drivers/comedi/drivers/amplc_pc263.c b/drivers/comedi/drivers/amplc_pc263.c index 68da6098ee84..d7f088a8a5e3 100644 --- a/drivers/comedi/drivers/amplc_pc263.c +++ b/drivers/comedi/drivers/amplc_pc263.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include /* PC263 registers */ #define PC263_DO_0_7_REG 0x00 diff --git a/drivers/comedi/drivers/amplc_pci224.c b/drivers/comedi/drivers/amplc_pci224.c index bcf6d61af863..3cf1b7fa565d 100644 --- a/drivers/comedi/drivers/amplc_pci224.c +++ b/drivers/comedi/drivers/amplc_pci224.c @@ -96,8 +96,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/amplc_pci230.c b/drivers/comedi/drivers/amplc_pci230.c index 8911dc2bd2c6..554ee40e321f 100644 --- a/drivers/comedi/drivers/amplc_pci230.c +++ b/drivers/comedi/drivers/amplc_pci230.c @@ -174,8 +174,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/amplc_pci236.c b/drivers/comedi/drivers/amplc_pci236.c index e7f6fa4d101a..482eb261c333 100644 --- a/drivers/comedi/drivers/amplc_pci236.c +++ b/drivers/comedi/drivers/amplc_pci236.c @@ -34,8 +34,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "amplc_pc236.h" #include "plx9052.h" diff --git a/drivers/comedi/drivers/amplc_pci263.c b/drivers/comedi/drivers/amplc_pci263.c index 9217973f1141..1609665c4b18 100644 --- a/drivers/comedi/drivers/amplc_pci263.c +++ b/drivers/comedi/drivers/amplc_pci263.c @@ -24,8 +24,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* PCI263 registers */ #define PCI263_DO_0_7_REG 0x00 diff --git a/drivers/comedi/drivers/c6xdigio.c b/drivers/comedi/drivers/c6xdigio.c index 786fd15698df..14b90d1c64dc 100644 --- a/drivers/comedi/drivers/c6xdigio.c +++ b/drivers/comedi/drivers/c6xdigio.c @@ -30,8 +30,7 @@ #include #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/cb_das16_cs.c b/drivers/comedi/drivers/cb_das16_cs.c index a5d171e71c33..190d73a7d12c 100644 --- a/drivers/comedi/drivers/cb_das16_cs.c +++ b/drivers/comedi/drivers/cb_das16_cs.c @@ -27,8 +27,7 @@ #include #include #include - -#include "../comedi_pcmcia.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/cb_pcidas.c b/drivers/comedi/drivers/cb_pcidas.c index 2f20bd56ec6c..9b603532a4e7 100644 --- a/drivers/comedi/drivers/cb_pcidas.c +++ b/drivers/comedi/drivers/cb_pcidas.c @@ -54,8 +54,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/cb_pcidas64.c b/drivers/comedi/drivers/cb_pcidas64.c index 41a8fea7f48a..7d4808faa1fb 100644 --- a/drivers/comedi/drivers/cb_pcidas64.c +++ b/drivers/comedi/drivers/cb_pcidas64.c @@ -73,8 +73,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "8255.h" #include "plx9080.h" diff --git a/drivers/comedi/drivers/cb_pcidda.c b/drivers/comedi/drivers/cb_pcidda.c index 78cf1603638c..4ed3bcf47973 100644 --- a/drivers/comedi/drivers/cb_pcidda.c +++ b/drivers/comedi/drivers/cb_pcidda.c @@ -27,8 +27,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/cb_pcimdas.c b/drivers/comedi/drivers/cb_pcimdas.c index 2292f69da4f4..64c7d72c7956 100644 --- a/drivers/comedi/drivers/cb_pcimdas.c +++ b/drivers/comedi/drivers/cb_pcimdas.c @@ -34,8 +34,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "plx9052.h" diff --git a/drivers/comedi/drivers/cb_pcimdda.c b/drivers/comedi/drivers/cb_pcimdda.c index 21fc7b3c5f60..69d7803b0e58 100644 --- a/drivers/comedi/drivers/cb_pcimdda.c +++ b/drivers/comedi/drivers/cb_pcimdda.c @@ -67,8 +67,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/comedi_8254.c b/drivers/comedi/drivers/comedi_8254.c index 4bf5daa9e885..fac81567133d 100644 --- a/drivers/comedi/drivers/comedi_8254.c +++ b/drivers/comedi/drivers/comedi_8254.c @@ -116,8 +116,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c index b7ca465933ee..10614603d677 100644 --- a/drivers/comedi/drivers/comedi_8255.c +++ b/drivers/comedi/drivers/comedi_8255.c @@ -29,7 +29,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/comedi_bond.c b/drivers/comedi/drivers/comedi_bond.c index 4392b5927a99..78c39fa84177 100644 --- a/drivers/comedi/drivers/comedi_bond.c +++ b/drivers/comedi/drivers/comedi_bond.c @@ -40,9 +40,9 @@ #include #include #include -#include "../comedi.h" -#include "../comedilib.h" -#include "../comedidev.h" +#include +#include +#include struct bonded_device { struct comedi_device *dev; diff --git a/drivers/comedi/drivers/comedi_isadma.c b/drivers/comedi/drivers/comedi_isadma.c index 479b58e209ba..63457bd4ff78 100644 --- a/drivers/comedi/drivers/comedi_isadma.c +++ b/drivers/comedi/drivers/comedi_isadma.c @@ -9,8 +9,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" diff --git a/drivers/comedi/drivers/comedi_parport.c b/drivers/comedi/drivers/comedi_parport.c index 5338b5eea440..098738a688fe 100644 --- a/drivers/comedi/drivers/comedi_parport.c +++ b/drivers/comedi/drivers/comedi_parport.c @@ -57,8 +57,7 @@ #include #include - -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/comedi_test.c b/drivers/comedi/drivers/comedi_test.c index cbc225eb1991..0b5c0af1cebf 100644 --- a/drivers/comedi/drivers/comedi_test.c +++ b/drivers/comedi/drivers/comedi_test.c @@ -45,10 +45,8 @@ */ #include -#include "../comedidev.h" - +#include #include - #include #include #include diff --git a/drivers/comedi/drivers/contec_pci_dio.c b/drivers/comedi/drivers/contec_pci_dio.c index b8fdd9c1f166..41d42ff14144 100644 --- a/drivers/comedi/drivers/contec_pci_dio.c +++ b/drivers/comedi/drivers/contec_pci_dio.c @@ -18,8 +18,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/dac02.c b/drivers/comedi/drivers/dac02.c index 5ef8114c2c85..4b011d66d7b0 100644 --- a/drivers/comedi/drivers/dac02.c +++ b/drivers/comedi/drivers/dac02.c @@ -25,8 +25,7 @@ */ #include - -#include "../comedidev.h" +#include /* * The output range is selected by jumpering pins on the I/O connector. diff --git a/drivers/comedi/drivers/daqboard2000.c b/drivers/comedi/drivers/daqboard2000.c index f64e747078bd..52e4bf16cbda 100644 --- a/drivers/comedi/drivers/daqboard2000.c +++ b/drivers/comedi/drivers/daqboard2000.c @@ -96,8 +96,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "8255.h" #include "plx9080.h" diff --git a/drivers/comedi/drivers/das08.c b/drivers/comedi/drivers/das08.c index b50743c5b822..c146a168f43b 100644 --- a/drivers/comedi/drivers/das08.c +++ b/drivers/comedi/drivers/das08.c @@ -10,8 +10,7 @@ */ #include - -#include "../comedidev.h" +#include #include "8255.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das08_cs.c b/drivers/comedi/drivers/das08_cs.c index 223479f9ea3c..6075efcf10d6 100644 --- a/drivers/comedi/drivers/das08_cs.c +++ b/drivers/comedi/drivers/das08_cs.c @@ -30,8 +30,7 @@ */ #include - -#include "../comedi_pcmcia.h" +#include #include "das08.h" diff --git a/drivers/comedi/drivers/das08_isa.c b/drivers/comedi/drivers/das08_isa.c index 8c4cfa821423..3d43b77cc9f4 100644 --- a/drivers/comedi/drivers/das08_isa.c +++ b/drivers/comedi/drivers/das08_isa.c @@ -29,7 +29,7 @@ */ #include -#include "../comedidev.h" +#include #include "das08.h" diff --git a/drivers/comedi/drivers/das08_pci.c b/drivers/comedi/drivers/das08_pci.c index 1cd903336a4c..982f3ab0ccbd 100644 --- a/drivers/comedi/drivers/das08_pci.c +++ b/drivers/comedi/drivers/das08_pci.c @@ -23,8 +23,7 @@ */ #include - -#include "../comedi_pci.h" +#include #include "das08.h" diff --git a/drivers/comedi/drivers/das16.c b/drivers/comedi/drivers/das16.c index 4ac2622b0fac..362232ad4409 100644 --- a/drivers/comedi/drivers/das16.c +++ b/drivers/comedi/drivers/das16.c @@ -63,8 +63,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c index 75f3dbbe97ac..cc79e318cb2d 100644 --- a/drivers/comedi/drivers/das16m1.c +++ b/drivers/comedi/drivers/das16m1.c @@ -42,7 +42,7 @@ #include #include #include -#include "../comedidev.h" +#include #include "8255.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das1800.c b/drivers/comedi/drivers/das1800.c index f50891a6ee7d..768803742350 100644 --- a/drivers/comedi/drivers/das1800.c +++ b/drivers/comedi/drivers/das1800.c @@ -73,8 +73,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das6402.c b/drivers/comedi/drivers/das6402.c index 96f4107b8054..d411ab7cf37c 100644 --- a/drivers/comedi/drivers/das6402.c +++ b/drivers/comedi/drivers/das6402.c @@ -24,8 +24,7 @@ #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/das800.c b/drivers/comedi/drivers/das800.c index bc08324f422f..c95e0fcb94a4 100644 --- a/drivers/comedi/drivers/das800.c +++ b/drivers/comedi/drivers/das800.c @@ -46,8 +46,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/dmm32at.c b/drivers/comedi/drivers/dmm32at.c index 56682f01242f..0f2bea88b8a7 100644 --- a/drivers/comedi/drivers/dmm32at.c +++ b/drivers/comedi/drivers/dmm32at.c @@ -29,7 +29,7 @@ #include #include #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/dt2801.c b/drivers/comedi/drivers/dt2801.c index 0d571d817b4e..230d25010f58 100644 --- a/drivers/comedi/drivers/dt2801.c +++ b/drivers/comedi/drivers/dt2801.c @@ -31,7 +31,7 @@ */ #include -#include "../comedidev.h" +#include #include #define DT2801_TIMEOUT 1000 diff --git a/drivers/comedi/drivers/dt2811.c b/drivers/comedi/drivers/dt2811.c index 0eb5e6ba6916..dbb9f38da289 100644 --- a/drivers/comedi/drivers/dt2811.c +++ b/drivers/comedi/drivers/dt2811.c @@ -40,8 +40,7 @@ #include #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/dt2814.c b/drivers/comedi/drivers/dt2814.c index ed44ce0d151b..c98a5a4a7aec 100644 --- a/drivers/comedi/drivers/dt2814.c +++ b/drivers/comedi/drivers/dt2814.c @@ -27,8 +27,7 @@ #include #include -#include "../comedidev.h" - +#include #include #define DT2814_CSR 0 diff --git a/drivers/comedi/drivers/dt2815.c b/drivers/comedi/drivers/dt2815.c index 5906f32aa01f..03ba2fd18a21 100644 --- a/drivers/comedi/drivers/dt2815.c +++ b/drivers/comedi/drivers/dt2815.c @@ -43,8 +43,7 @@ */ #include -#include "../comedidev.h" - +#include #include #define DT2815_DATA 0 diff --git a/drivers/comedi/drivers/dt2817.c b/drivers/comedi/drivers/dt2817.c index 7c1463e835d3..6738045c7531 100644 --- a/drivers/comedi/drivers/dt2817.c +++ b/drivers/comedi/drivers/dt2817.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include #define DT2817_CR 0 #define DT2817_DATA 1 diff --git a/drivers/comedi/drivers/dt282x.c b/drivers/comedi/drivers/dt282x.c index 2656b4b0e3d0..078f8fba7183 100644 --- a/drivers/comedi/drivers/dt282x.c +++ b/drivers/comedi/drivers/dt282x.c @@ -51,8 +51,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" diff --git a/drivers/comedi/drivers/dt3000.c b/drivers/comedi/drivers/dt3000.c index ec27aa4730d4..fc6e9c30e522 100644 --- a/drivers/comedi/drivers/dt3000.c +++ b/drivers/comedi/drivers/dt3000.c @@ -43,8 +43,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR0 - dual-ported RAM location definitions (dev->mmio) diff --git a/drivers/comedi/drivers/dt9812.c b/drivers/comedi/drivers/dt9812.c index 704b04d2980d..b37b9d8eca0d 100644 --- a/drivers/comedi/drivers/dt9812.c +++ b/drivers/comedi/drivers/dt9812.c @@ -34,8 +34,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include #define DT9812_DIAGS_BOARD_INFO_ADDR 0xFBFF #define DT9812_MAX_WRITE_CMD_PIPE_SIZE 32 diff --git a/drivers/comedi/drivers/dyna_pci10xx.c b/drivers/comedi/drivers/dyna_pci10xx.c index c224422bb126..407a038fb3e0 100644 --- a/drivers/comedi/drivers/dyna_pci10xx.c +++ b/drivers/comedi/drivers/dyna_pci10xx.c @@ -26,8 +26,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #define READ_TIMEOUT 50 diff --git a/drivers/comedi/drivers/fl512.c b/drivers/comedi/drivers/fl512.c index b715f30659fa..139e801fc358 100644 --- a/drivers/comedi/drivers/fl512.c +++ b/drivers/comedi/drivers/fl512.c @@ -21,8 +21,7 @@ */ #include -#include "../comedidev.h" - +#include #include /* diff --git a/drivers/comedi/drivers/gsc_hpdi.c b/drivers/comedi/drivers/gsc_hpdi.c index e35e4a743714..c09d135df38d 100644 --- a/drivers/comedi/drivers/gsc_hpdi.c +++ b/drivers/comedi/drivers/gsc_hpdi.c @@ -34,8 +34,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "plx9080.h" diff --git a/drivers/comedi/drivers/icp_multi.c b/drivers/comedi/drivers/icp_multi.c index 16d2b78de83c..ac4b11dbd741 100644 --- a/drivers/comedi/drivers/icp_multi.c +++ b/drivers/comedi/drivers/icp_multi.c @@ -36,8 +36,7 @@ #include #include - -#include "../comedi_pci.h" +#include #define ICP_MULTI_ADC_CSR 0x00 /* R/W: ADC command/status register */ #define ICP_MULTI_ADC_CSR_ST BIT(0) /* Start ADC */ diff --git a/drivers/comedi/drivers/ii_pci20kc.c b/drivers/comedi/drivers/ii_pci20kc.c index 399255dbe388..4a19bf8462be 100644 --- a/drivers/comedi/drivers/ii_pci20kc.c +++ b/drivers/comedi/drivers/ii_pci20kc.c @@ -30,7 +30,7 @@ #include #include -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/jr3_pci.c b/drivers/comedi/drivers/jr3_pci.c index f963080dd61f..951c23fa0369 100644 --- a/drivers/comedi/drivers/jr3_pci.c +++ b/drivers/comedi/drivers/jr3_pci.c @@ -35,8 +35,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "jr3_pci.h" diff --git a/drivers/comedi/drivers/ke_counter.c b/drivers/comedi/drivers/ke_counter.c index bef1b20c1c8d..b825cf60e1e0 100644 --- a/drivers/comedi/drivers/ke_counter.c +++ b/drivers/comedi/drivers/ke_counter.c @@ -19,8 +19,7 @@ */ #include - -#include "../comedi_pci.h" +#include /* * PCI BAR 0 Register I/O map diff --git a/drivers/comedi/drivers/me4000.c b/drivers/comedi/drivers/me4000.c index 0d3d4cafce2e..c5dc8199771f 100644 --- a/drivers/comedi/drivers/me4000.c +++ b/drivers/comedi/drivers/me4000.c @@ -32,8 +32,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "plx9052.h" diff --git a/drivers/comedi/drivers/me_daq.c b/drivers/comedi/drivers/me_daq.c index ef18e387471b..076b15097afd 100644 --- a/drivers/comedi/drivers/me_daq.c +++ b/drivers/comedi/drivers/me_daq.c @@ -23,8 +23,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "plx9052.h" diff --git a/drivers/comedi/drivers/mf6x4.c b/drivers/comedi/drivers/mf6x4.c index 9da8dd748078..14f1d5e9cd59 100644 --- a/drivers/comedi/drivers/mf6x4.c +++ b/drivers/comedi/drivers/mf6x4.c @@ -18,8 +18,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* Registers present in BAR0 memory region */ #define MF624_GPIOC_REG 0x54 diff --git a/drivers/comedi/drivers/mite.c b/drivers/comedi/drivers/mite.c index 70960e3ba878..88f3cd6f54f1 100644 --- a/drivers/comedi/drivers/mite.c +++ b/drivers/comedi/drivers/mite.c @@ -38,8 +38,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "mite.h" diff --git a/drivers/comedi/drivers/mpc624.c b/drivers/comedi/drivers/mpc624.c index 646f4c086204..9e51ff528ed1 100644 --- a/drivers/comedi/drivers/mpc624.c +++ b/drivers/comedi/drivers/mpc624.c @@ -44,8 +44,7 @@ */ #include -#include "../comedidev.h" - +#include #include /* Offsets of different ports */ diff --git a/drivers/comedi/drivers/multiq3.c b/drivers/comedi/drivers/multiq3.c index c1897aee9a9a..07ff5383da99 100644 --- a/drivers/comedi/drivers/multiq3.c +++ b/drivers/comedi/drivers/multiq3.c @@ -26,8 +26,7 @@ */ #include - -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/ni_6527.c b/drivers/comedi/drivers/ni_6527.c index f1a45cf7342a..ac5820085231 100644 --- a/drivers/comedi/drivers/ni_6527.c +++ b/drivers/comedi/drivers/ni_6527.c @@ -20,8 +20,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR1 - Register memory map diff --git a/drivers/comedi/drivers/ni_65xx.c b/drivers/comedi/drivers/ni_65xx.c index 7cd8497420f2..58334de3b253 100644 --- a/drivers/comedi/drivers/ni_65xx.c +++ b/drivers/comedi/drivers/ni_65xx.c @@ -49,8 +49,7 @@ #include #include - -#include "../comedi_pci.h" +#include /* * PCI BAR1 Register Map diff --git a/drivers/comedi/drivers/ni_660x.c b/drivers/comedi/drivers/ni_660x.c index e60d0125bcb2..0679bc39e0bc 100644 --- a/drivers/comedi/drivers/ni_660x.c +++ b/drivers/comedi/drivers/ni_660x.c @@ -26,8 +26,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "mite.h" #include "ni_tio.h" diff --git a/drivers/comedi/drivers/ni_670x.c b/drivers/comedi/drivers/ni_670x.c index c197e47486be..c875d251c230 100644 --- a/drivers/comedi/drivers/ni_670x.c +++ b/drivers/comedi/drivers/ni_670x.c @@ -24,8 +24,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #define AO_VALUE_OFFSET 0x00 #define AO_CHAN_OFFSET 0x0c diff --git a/drivers/comedi/drivers/ni_at_a2150.c b/drivers/comedi/drivers/ni_at_a2150.c index 10ad7b88713e..ce5de58c499f 100644 --- a/drivers/comedi/drivers/ni_at_a2150.c +++ b/drivers/comedi/drivers/ni_at_a2150.c @@ -39,8 +39,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/ni_at_ao.c b/drivers/comedi/drivers/ni_at_ao.c index 2a0fb4d460db..a06dfb9da329 100644 --- a/drivers/comedi/drivers/ni_at_ao.c +++ b/drivers/comedi/drivers/ni_at_ao.c @@ -25,8 +25,7 @@ */ #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/ni_atmio.c b/drivers/comedi/drivers/ni_atmio.c index 56c78da475e7..f60a4e459a98 100644 --- a/drivers/comedi/drivers/ni_atmio.c +++ b/drivers/comedi/drivers/ni_atmio.c @@ -73,8 +73,7 @@ #include #include -#include "../comedidev.h" - +#include #include #include "ni_stc.h" diff --git a/drivers/comedi/drivers/ni_atmio16d.c b/drivers/comedi/drivers/ni_atmio16d.c index dffce1aa3e69..0bd4f88a2ac8 100644 --- a/drivers/comedi/drivers/ni_atmio16d.c +++ b/drivers/comedi/drivers/ni_atmio16d.c @@ -39,7 +39,7 @@ #include #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/ni_daq_700.c b/drivers/comedi/drivers/ni_daq_700.c index d40fc89f9cef..0ef20e9a8bc4 100644 --- a/drivers/comedi/drivers/ni_daq_700.c +++ b/drivers/comedi/drivers/ni_daq_700.c @@ -41,8 +41,7 @@ #include #include #include - -#include "../comedi_pcmcia.h" +#include /* daqcard700 registers */ #define DIO_W 0x04 /* WO 8bit */ diff --git a/drivers/comedi/drivers/ni_daq_dio24.c b/drivers/comedi/drivers/ni_daq_dio24.c index 44fb65afc218..84d78f2ee5ac 100644 --- a/drivers/comedi/drivers/ni_daq_dio24.c +++ b/drivers/comedi/drivers/ni_daq_dio24.c @@ -23,7 +23,7 @@ */ #include -#include "../comedi_pcmcia.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/ni_labpc.c b/drivers/comedi/drivers/ni_labpc.c index 1f4a07bd1d26..b25a8e117072 100644 --- a/drivers/comedi/drivers/ni_labpc.c +++ b/drivers/comedi/drivers/ni_labpc.c @@ -48,8 +48,7 @@ */ #include - -#include "../comedidev.h" +#include #include "ni_labpc.h" #include "ni_labpc_isadma.h" diff --git a/drivers/comedi/drivers/ni_labpc_common.c b/drivers/comedi/drivers/ni_labpc_common.c index dd97946eacaf..7c4687226450 100644 --- a/drivers/comedi/drivers/ni_labpc_common.c +++ b/drivers/comedi/drivers/ni_labpc_common.c @@ -12,8 +12,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" #include "8255.h" diff --git a/drivers/comedi/drivers/ni_labpc_cs.c b/drivers/comedi/drivers/ni_labpc_cs.c index 4f7e2fe21254..62fecb50ec6e 100644 --- a/drivers/comedi/drivers/ni_labpc_cs.c +++ b/drivers/comedi/drivers/ni_labpc_cs.c @@ -38,8 +38,7 @@ */ #include - -#include "../comedi_pcmcia.h" +#include #include "ni_labpc.h" diff --git a/drivers/comedi/drivers/ni_labpc_isadma.c b/drivers/comedi/drivers/ni_labpc_isadma.c index a551aca6e615..dd37ec0d9b15 100644 --- a/drivers/comedi/drivers/ni_labpc_isadma.c +++ b/drivers/comedi/drivers/ni_labpc_isadma.c @@ -10,8 +10,7 @@ #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "ni_labpc.h" diff --git a/drivers/comedi/drivers/ni_labpc_pci.c b/drivers/comedi/drivers/ni_labpc_pci.c index ec180b0fedf7..e2a44bbd9fa6 100644 --- a/drivers/comedi/drivers/ni_labpc_pci.c +++ b/drivers/comedi/drivers/ni_labpc_pci.c @@ -22,8 +22,7 @@ #include #include - -#include "../comedi_pci.h" +#include #include "ni_labpc.h" diff --git a/drivers/comedi/drivers/ni_mio_cs.c b/drivers/comedi/drivers/ni_mio_cs.c index 4f37b4e58f09..bd967cdb2036 100644 --- a/drivers/comedi/drivers/ni_mio_cs.c +++ b/drivers/comedi/drivers/ni_mio_cs.c @@ -28,8 +28,8 @@ #include #include +#include -#include "../comedi_pcmcia.h" #include "ni_stc.h" #include "8255.h" diff --git a/drivers/comedi/drivers/ni_pcidio.c b/drivers/comedi/drivers/ni_pcidio.c index 623f8d08d13a..2d58e83420e8 100644 --- a/drivers/comedi/drivers/ni_pcidio.c +++ b/drivers/comedi/drivers/ni_pcidio.c @@ -42,8 +42,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "mite.h" diff --git a/drivers/comedi/drivers/ni_pcimio.c b/drivers/comedi/drivers/ni_pcimio.c index 6c813a490ba5..0b055321023d 100644 --- a/drivers/comedi/drivers/ni_pcimio.c +++ b/drivers/comedi/drivers/ni_pcimio.c @@ -94,9 +94,7 @@ #include #include - -#include "../comedi_pci.h" - +#include #include #include "ni_stc.h" diff --git a/drivers/comedi/drivers/ni_routes.c b/drivers/comedi/drivers/ni_routes.c index f0f8cd424b30..f24eeb464eba 100644 --- a/drivers/comedi/drivers/ni_routes.c +++ b/drivers/comedi/drivers/ni_routes.c @@ -21,8 +21,7 @@ #include #include #include - -#include "../comedi.h" +#include #include "ni_routes.h" #include "ni_routing/ni_route_values.h" diff --git a/drivers/comedi/drivers/ni_routes.h b/drivers/comedi/drivers/ni_routes.h index 036982315584..cff8a463a03f 100644 --- a/drivers/comedi/drivers/ni_routes.h +++ b/drivers/comedi/drivers/ni_routes.h @@ -27,7 +27,7 @@ #include #endif -#include "../comedi.h" +#include /** * struct ni_route_set - Set of destinations with a common source. diff --git a/drivers/comedi/drivers/ni_routing/ni_route_values.h b/drivers/comedi/drivers/ni_routing/ni_route_values.h index 6e358efa6f7f..80880083ea41 100644 --- a/drivers/comedi/drivers/ni_routing/ni_route_values.h +++ b/drivers/comedi/drivers/ni_routing/ni_route_values.h @@ -20,7 +20,7 @@ #ifndef _COMEDI_DRIVERS_NI_ROUTINT_NI_ROUTE_VALUES_H #define _COMEDI_DRIVERS_NI_ROUTINT_NI_ROUTE_VALUES_H -#include "../../comedi.h" +#include #include /* diff --git a/drivers/comedi/drivers/ni_tio.h b/drivers/comedi/drivers/ni_tio.h index e7b05718df9b..9ae2221c3c18 100644 --- a/drivers/comedi/drivers/ni_tio.h +++ b/drivers/comedi/drivers/ni_tio.h @@ -8,7 +8,7 @@ #ifndef _COMEDI_NI_TIO_H #define _COMEDI_NI_TIO_H -#include "../comedidev.h" +#include enum ni_gpct_register { NITIO_G0_AUTO_INC, diff --git a/drivers/comedi/drivers/ni_usb6501.c b/drivers/comedi/drivers/ni_usb6501.c index c42987b74b1d..0dd9edf7bced 100644 --- a/drivers/comedi/drivers/ni_usb6501.c +++ b/drivers/comedi/drivers/ni_usb6501.c @@ -87,8 +87,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include #define NI6501_TIMEOUT 1000 diff --git a/drivers/comedi/drivers/pcl711.c b/drivers/comedi/drivers/pcl711.c index bd6f42fe9e3c..f1c383bd9d87 100644 --- a/drivers/comedi/drivers/pcl711.c +++ b/drivers/comedi/drivers/pcl711.c @@ -29,8 +29,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcl724.c b/drivers/comedi/drivers/pcl724.c index 1a5799278a7a..b3f472c93e80 100644 --- a/drivers/comedi/drivers/pcl724.c +++ b/drivers/comedi/drivers/pcl724.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/pcl726.c b/drivers/comedi/drivers/pcl726.c index 88f25d7e76f7..0430630e6ebb 100644 --- a/drivers/comedi/drivers/pcl726.c +++ b/drivers/comedi/drivers/pcl726.c @@ -50,8 +50,7 @@ #include #include - -#include "../comedidev.h" +#include #define PCL726_AO_MSB_REG(x) (0x00 + ((x) * 2)) #define PCL726_AO_LSB_REG(x) (0x01 + ((x) * 2)) diff --git a/drivers/comedi/drivers/pcl730.c b/drivers/comedi/drivers/pcl730.c index 32a29129e6e8..d2733cd5383d 100644 --- a/drivers/comedi/drivers/pcl730.c +++ b/drivers/comedi/drivers/pcl730.c @@ -25,7 +25,7 @@ */ #include -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c index b87ab3840eee..f00976ddfc2a 100644 --- a/drivers/comedi/drivers/pcl812.c +++ b/drivers/comedi/drivers/pcl812.c @@ -114,8 +114,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcl816.c b/drivers/comedi/drivers/pcl816.c index c368a337a0ae..c5acdc8913f8 100644 --- a/drivers/comedi/drivers/pcl816.c +++ b/drivers/comedi/drivers/pcl816.c @@ -35,8 +35,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcl818.c b/drivers/comedi/drivers/pcl818.c index f4b4a686c710..20fcd6d588f8 100644 --- a/drivers/comedi/drivers/pcl818.c +++ b/drivers/comedi/drivers/pcl818.c @@ -97,8 +97,7 @@ #include #include #include - -#include "../comedidev.h" +#include #include "comedi_isadma.h" #include "comedi_8254.h" diff --git a/drivers/comedi/drivers/pcm3724.c b/drivers/comedi/drivers/pcm3724.c index 0cb1ad060402..93ae6cffed44 100644 --- a/drivers/comedi/drivers/pcm3724.c +++ b/drivers/comedi/drivers/pcm3724.c @@ -24,7 +24,7 @@ */ #include -#include "../comedidev.h" +#include #include "8255.h" diff --git a/drivers/comedi/drivers/pcmad.c b/drivers/comedi/drivers/pcmad.c index eec89a0afb2f..976eda43881b 100644 --- a/drivers/comedi/drivers/pcmad.c +++ b/drivers/comedi/drivers/pcmad.c @@ -29,7 +29,7 @@ */ #include -#include "../comedidev.h" +#include #define PCMAD_STATUS 0 #define PCMAD_LSB 1 diff --git a/drivers/comedi/drivers/pcmda12.c b/drivers/comedi/drivers/pcmda12.c index 14ab1f0d1e9f..611f13bedca0 100644 --- a/drivers/comedi/drivers/pcmda12.c +++ b/drivers/comedi/drivers/pcmda12.c @@ -40,7 +40,7 @@ */ #include -#include "../comedidev.h" +#include /* AI range is not configurable, it's set by jumpers on the board */ static const struct comedi_lrange pcmda12_ranges = { diff --git a/drivers/comedi/drivers/pcmmio.c b/drivers/comedi/drivers/pcmmio.c index 24a9568d3378..c2402239d551 100644 --- a/drivers/comedi/drivers/pcmmio.c +++ b/drivers/comedi/drivers/pcmmio.c @@ -66,8 +66,7 @@ #include #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/pcmuio.c b/drivers/comedi/drivers/pcmuio.c index b299d648a0eb..33b24dbbb919 100644 --- a/drivers/comedi/drivers/pcmuio.c +++ b/drivers/comedi/drivers/pcmuio.c @@ -65,8 +65,7 @@ #include #include - -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/quatech_daqp_cs.c b/drivers/comedi/drivers/quatech_daqp_cs.c index fe4408ebf6b3..2a76c75c513b 100644 --- a/drivers/comedi/drivers/quatech_daqp_cs.c +++ b/drivers/comedi/drivers/quatech_daqp_cs.c @@ -41,8 +41,7 @@ */ #include - -#include "../comedi_pcmcia.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/rtd520.c b/drivers/comedi/drivers/rtd520.c index 2d99a648b054..ee5bca2b1c09 100644 --- a/drivers/comedi/drivers/rtd520.c +++ b/drivers/comedi/drivers/rtd520.c @@ -85,8 +85,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "comedi_8254.h" #include "plx9080.h" diff --git a/drivers/comedi/drivers/rti800.c b/drivers/comedi/drivers/rti800.c index 327fd93b8b12..1b02e47bdb4c 100644 --- a/drivers/comedi/drivers/rti800.c +++ b/drivers/comedi/drivers/rti800.c @@ -42,7 +42,7 @@ #include #include #include -#include "../comedidev.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/rti802.c b/drivers/comedi/drivers/rti802.c index 195e2b1ac4c1..d66762a22258 100644 --- a/drivers/comedi/drivers/rti802.c +++ b/drivers/comedi/drivers/rti802.c @@ -22,7 +22,7 @@ */ #include -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/s526.c b/drivers/comedi/drivers/s526.c index 085cf5b449e5..9245c679a3c4 100644 --- a/drivers/comedi/drivers/s526.c +++ b/drivers/comedi/drivers/s526.c @@ -27,7 +27,7 @@ */ #include -#include "../comedidev.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/s626.c b/drivers/comedi/drivers/s626.c index e7aba937d896..0e5f9a9a7fd3 100644 --- a/drivers/comedi/drivers/s626.c +++ b/drivers/comedi/drivers/s626.c @@ -55,8 +55,7 @@ #include #include #include - -#include "../comedi_pci.h" +#include #include "s626.h" diff --git a/drivers/comedi/drivers/ssv_dnp.c b/drivers/comedi/drivers/ssv_dnp.c index 016d315aa584..813bd0853b0b 100644 --- a/drivers/comedi/drivers/ssv_dnp.c +++ b/drivers/comedi/drivers/ssv_dnp.c @@ -19,7 +19,7 @@ /* include files ----------------------------------------------------------- */ #include -#include "../comedidev.h" +#include /* Some global definitions: the registers of the DNP ----------------------- */ /* */ diff --git a/drivers/comedi/drivers/usbdux.c b/drivers/comedi/drivers/usbdux.c index 0350f303d557..92d514b3c1c3 100644 --- a/drivers/comedi/drivers/usbdux.c +++ b/drivers/comedi/drivers/usbdux.c @@ -73,8 +73,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include /* constants for firmware upload and download */ #define USBDUX_FIRMWARE "usbdux_firmware.bin" diff --git a/drivers/comedi/drivers/usbduxfast.c b/drivers/comedi/drivers/usbduxfast.c index 4af012968cb6..39faae0ecb19 100644 --- a/drivers/comedi/drivers/usbduxfast.c +++ b/drivers/comedi/drivers/usbduxfast.c @@ -40,7 +40,7 @@ #include #include #include -#include "../comedi_usb.h" +#include /* * timeout for the USB-transfer diff --git a/drivers/comedi/drivers/usbduxsigma.c b/drivers/comedi/drivers/usbduxsigma.c index 54d7605e909f..2aaeaf44fbe5 100644 --- a/drivers/comedi/drivers/usbduxsigma.c +++ b/drivers/comedi/drivers/usbduxsigma.c @@ -40,8 +40,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include /* timeout for the USB-transfer in ms*/ #define BULK_TIMEOUT 1000 diff --git a/drivers/comedi/drivers/vmk80xx.c b/drivers/comedi/drivers/vmk80xx.c index 4b00a9ea611a..46023adc5395 100644 --- a/drivers/comedi/drivers/vmk80xx.c +++ b/drivers/comedi/drivers/vmk80xx.c @@ -35,8 +35,7 @@ #include #include #include - -#include "../comedi_usb.h" +#include enum { DEVICE_VMK8055, diff --git a/drivers/comedi/kcomedilib/kcomedilib_main.c b/drivers/comedi/kcomedilib/kcomedilib_main.c index df9bba1b69ed..43fbe1a63b14 100644 --- a/drivers/comedi/kcomedilib/kcomedilib_main.c +++ b/drivers/comedi/kcomedilib/kcomedilib_main.c @@ -16,9 +16,9 @@ #include #include -#include "../comedi.h" -#include "../comedilib.h" -#include "../comedidev.h" +#include +#include +#include MODULE_AUTHOR("David Schleef "); MODULE_DESCRIPTION("Comedi kernel library"); diff --git a/drivers/comedi/proc.c b/drivers/comedi/proc.c index 8bc8e42beb90..2e4496633d3d 100644 --- a/drivers/comedi/proc.c +++ b/drivers/comedi/proc.c @@ -13,7 +13,7 @@ * was cool. */ -#include "comedidev.h" +#include #include "comedi_internal.h" #include #include diff --git a/drivers/comedi/range.c b/drivers/comedi/range.c index a4e6fe0fb729..8f43cf88d784 100644 --- a/drivers/comedi/range.c +++ b/drivers/comedi/range.c @@ -8,7 +8,7 @@ */ #include -#include "comedidev.h" +#include #include "comedi_internal.h" const struct comedi_lrange range_bipolar10 = { 1, {BIP_RANGE(10)} }; diff --git a/include/linux/comedi/comedi_pci.h b/include/linux/comedi/comedi_pci.h new file mode 100644 index 000000000000..2fb50663e3ed --- /dev/null +++ b/include/linux/comedi/comedi_pci.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pci.h + * header file for Comedi PCI drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDI_PCI_H +#define _COMEDI_PCI_H + +#include +#include + +/* + * PCI Vendor IDs not in + */ +#define PCI_VENDOR_ID_KOLTER 0x1001 +#define PCI_VENDOR_ID_ICP 0x104c +#define PCI_VENDOR_ID_DT 0x1116 +#define PCI_VENDOR_ID_IOTECH 0x1616 +#define PCI_VENDOR_ID_CONTEC 0x1221 +#define PCI_VENDOR_ID_RTD 0x1435 +#define PCI_VENDOR_ID_HUMUSOFT 0x186c + +struct pci_dev *comedi_to_pci_dev(struct comedi_device *dev); + +int comedi_pci_enable(struct comedi_device *dev); +void comedi_pci_disable(struct comedi_device *dev); +void comedi_pci_detach(struct comedi_device *dev); + +int comedi_pci_auto_config(struct pci_dev *pcidev, struct comedi_driver *driver, + unsigned long context); +void comedi_pci_auto_unconfig(struct pci_dev *pcidev); + +int comedi_pci_driver_register(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); +void comedi_pci_driver_unregister(struct comedi_driver *comedi_driver, + struct pci_driver *pci_driver); + +/** + * module_comedi_pci_driver() - Helper macro for registering a comedi PCI driver + * @__comedi_driver: comedi_driver struct + * @__pci_driver: pci_driver struct + * + * Helper macro for comedi PCI drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pci_driver(__comedi_driver, __pci_driver) \ + module_driver(__comedi_driver, comedi_pci_driver_register, \ + comedi_pci_driver_unregister, &(__pci_driver)) + +#endif /* _COMEDI_PCI_H */ diff --git a/include/linux/comedi/comedi_pcmcia.h b/include/linux/comedi/comedi_pcmcia.h new file mode 100644 index 000000000000..a33dfb65b869 --- /dev/null +++ b/include/linux/comedi/comedi_pcmcia.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_pcmcia.h + * header file for Comedi PCMCIA drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDI_PCMCIA_H +#define _COMEDI_PCMCIA_H + +#include +#include +#include + +struct pcmcia_device *comedi_to_pcmcia_dev(struct comedi_device *dev); + +int comedi_pcmcia_enable(struct comedi_device *dev, + int (*conf_check)(struct pcmcia_device *p_dev, + void *priv_data)); +void comedi_pcmcia_disable(struct comedi_device *dev); + +int comedi_pcmcia_auto_config(struct pcmcia_device *link, + struct comedi_driver *driver); +void comedi_pcmcia_auto_unconfig(struct pcmcia_device *link); + +int comedi_pcmcia_driver_register(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); +void comedi_pcmcia_driver_unregister(struct comedi_driver *comedi_driver, + struct pcmcia_driver *pcmcia_driver); + +/** + * module_comedi_pcmcia_driver() - Helper macro for registering a comedi + * PCMCIA driver + * @__comedi_driver: comedi_driver struct + * @__pcmcia_driver: pcmcia_driver struct + * + * Helper macro for comedi PCMCIA drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_pcmcia_driver(__comedi_driver, __pcmcia_driver) \ + module_driver(__comedi_driver, comedi_pcmcia_driver_register, \ + comedi_pcmcia_driver_unregister, &(__pcmcia_driver)) + +#endif /* _COMEDI_PCMCIA_H */ diff --git a/include/linux/comedi/comedi_usb.h b/include/linux/comedi/comedi_usb.h new file mode 100644 index 000000000000..5d17dd425bd2 --- /dev/null +++ b/include/linux/comedi/comedi_usb.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* comedi_usb.h + * header file for USB Comedi drivers + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDI_USB_H +#define _COMEDI_USB_H + +#include +#include + +struct usb_interface *comedi_to_usb_interface(struct comedi_device *dev); +struct usb_device *comedi_to_usb_dev(struct comedi_device *dev); + +int comedi_usb_auto_config(struct usb_interface *intf, + struct comedi_driver *driver, unsigned long context); +void comedi_usb_auto_unconfig(struct usb_interface *intf); + +int comedi_usb_driver_register(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); +void comedi_usb_driver_unregister(struct comedi_driver *comedi_driver, + struct usb_driver *usb_driver); + +/** + * module_comedi_usb_driver() - Helper macro for registering a comedi USB driver + * @__comedi_driver: comedi_driver struct + * @__usb_driver: usb_driver struct + * + * Helper macro for comedi USB drivers which do not do anything special + * in module init/exit. This eliminates a lot of boilerplate. Each + * module may only use this macro once, and calling it replaces + * module_init() and module_exit() + */ +#define module_comedi_usb_driver(__comedi_driver, __usb_driver) \ + module_driver(__comedi_driver, comedi_usb_driver_register, \ + comedi_usb_driver_unregister, &(__usb_driver)) + +#endif /* _COMEDI_USB_H */ diff --git a/include/linux/comedi/comedidev.h b/include/linux/comedi/comedidev.h new file mode 100644 index 000000000000..0a1150900ef3 --- /dev/null +++ b/include/linux/comedi/comedidev.h @@ -0,0 +1,1053 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedidev.h + * header file for kernel-only structures, variables, and constants + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1997-2000 David A. Schleef + */ + +#ifndef _COMEDIDEV_H +#define _COMEDIDEV_H + +#include +#include +#include +#include +#include +#include + +#define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c)) +#define COMEDI_VERSION_CODE COMEDI_VERSION(COMEDI_MAJORVERSION, \ + COMEDI_MINORVERSION, COMEDI_MICROVERSION) +#define COMEDI_RELEASE VERSION + +#define COMEDI_NUM_BOARD_MINORS 0x30 + +/** + * struct comedi_subdevice - Working data for a COMEDI subdevice + * @device: COMEDI device to which this subdevice belongs. (Initialized by + * comedi_alloc_subdevices().) + * @index: Index of this subdevice within device's array of subdevices. + * (Initialized by comedi_alloc_subdevices().) + * @type: Type of subdevice from &enum comedi_subdevice_type. (Initialized by + * the low-level driver.) + * @n_chan: Number of channels the subdevice supports. (Initialized by the + * low-level driver.) + * @subdev_flags: Various "SDF" flags indicating aspects of the subdevice to + * the COMEDI core and user application. (Initialized by the low-level + * driver.) + * @len_chanlist: Maximum length of a channel list if the subdevice supports + * asynchronous acquisition commands. (Optionally initialized by the + * low-level driver, or changed from 0 to 1 during post-configuration.) + * @private: Private data pointer which is either set by the low-level driver + * itself, or by a call to comedi_alloc_spriv() which allocates storage. + * In the latter case, the storage is automatically freed after the + * low-level driver's "detach" handler is called for the device. + * (Initialized by the low-level driver.) + * @async: Pointer to &struct comedi_async id the subdevice supports + * asynchronous acquisition commands. (Allocated and initialized during + * post-configuration if needed.) + * @lock: Pointer to a file object that performed a %COMEDI_LOCK ioctl on the + * subdevice. (Initially NULL.) + * @busy: Pointer to a file object that is performing an asynchronous + * acquisition command on the subdevice. (Initially NULL.) + * @runflags: Internal flags for use by COMEDI core, mostly indicating whether + * an asynchronous acquisition command is running. + * @spin_lock: Generic spin-lock for use by the COMEDI core and the low-level + * driver. (Initialized by comedi_alloc_subdevices().) + * @io_bits: Bit-mask indicating the channel directions for a DIO subdevice + * with no more than 32 channels. A '1' at a bit position indicates the + * corresponding channel is configured as an output. (Initialized by the + * low-level driver for a DIO subdevice. Forced to all-outputs during + * post-configuration for a digital output subdevice.) + * @maxdata: If non-zero, this is the maximum raw data value of each channel. + * If zero, the maximum data value is channel-specific. (Initialized by + * the low-level driver.) + * @maxdata_list: If the maximum data value is channel-specific, this points + * to an array of maximum data values indexed by channel index. + * (Initialized by the low-level driver.) + * @range_table: If non-NULL, this points to a COMEDI range table for the + * subdevice. If NULL, the range table is channel-specific. (Initialized + * by the low-level driver, will be set to an "invalid" range table during + * post-configuration if @range_table and @range_table_list are both + * NULL.) + * @range_table_list: If the COMEDI range table is channel-specific, this + * points to an array of pointers to COMEDI range tables indexed by + * channel number. (Initialized by the low-level driver.) + * @chanlist: Not used. + * @insn_read: Optional pointer to a handler for the %INSN_READ instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_write: Optional pointer to a handler for the %INSN_WRITE instruction. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_bits: Optional pointer to a handler for the %INSN_BITS instruction + * for a digital input, digital output or digital input/output subdevice. + * (Initialized by the low-level driver, or set to a default handler + * during post-configuration.) + * @insn_config: Optional pointer to a handler for the %INSN_CONFIG + * instruction. (Initialized by the low-level driver, or set to a default + * handler during post-configuration.) + * @do_cmd: If the subdevice supports asynchronous acquisition commands, this + * points to a handler to set it up in hardware. (Initialized by the + * low-level driver.) + * @do_cmdtest: If the subdevice supports asynchronous acquisition commands, + * this points to a handler used to check and possibly tweak a prospective + * acquisition command without setting it up in hardware. (Initialized by + * the low-level driver.) + * @poll: If the subdevice supports asynchronous acquisition commands, this + * is an optional pointer to a handler for the %COMEDI_POLL ioctl which + * instructs the low-level driver to synchronize buffers. (Initialized by + * the low-level driver if needed.) + * @cancel: If the subdevice supports asynchronous acquisition commands, this + * points to a handler used to terminate a running command. (Initialized + * by the low-level driver.) + * @buf_change: If the subdevice supports asynchronous acquisition commands, + * this is an optional pointer to a handler that is called when the data + * buffer for handling asynchronous commands is allocated or reallocated. + * (Initialized by the low-level driver if needed.) + * @munge: If the subdevice supports asynchronous acquisition commands and + * uses DMA to transfer data from the hardware to the acquisition buffer, + * this points to a function used to "munge" the data values from the + * hardware into the format expected by COMEDI. (Initialized by the + * low-level driver if needed.) + * @async_dma_dir: If the subdevice supports asynchronous acquisition commands + * and uses DMA to transfer data from the hardware to the acquisition + * buffer, this sets the DMA direction for the buffer. (initialized to + * %DMA_NONE by comedi_alloc_subdevices() and changed by the low-level + * driver if necessary.) + * @state: Handy bit-mask indicating the output states for a DIO or digital + * output subdevice with no more than 32 channels. (Initialized by the + * low-level driver.) + * @class_dev: If the subdevice supports asynchronous acquisition commands, + * this points to a sysfs comediX_subdY device where X is the minor device + * number of the COMEDI device and Y is the subdevice number. The minor + * device number for the sysfs device is allocated dynamically in the + * range 48 to 255. This is used to allow the COMEDI device to be opened + * with a different default read or write subdevice. (Allocated during + * post-configuration if needed.) + * @minor: If @class_dev is set, this is its dynamically allocated minor + * device number. (Set during post-configuration if necessary.) + * @readback: Optional pointer to memory allocated by + * comedi_alloc_subdev_readback() used to hold the values written to + * analog output channels so they can be read back. The storage is + * automatically freed after the low-level driver's "detach" handler is + * called for the device. (Initialized by the low-level driver.) + * + * This is the main control structure for a COMEDI subdevice. If the subdevice + * supports asynchronous acquisition commands, additional information is stored + * in the &struct comedi_async pointed to by @async. + * + * Most of the subdevice is initialized by the low-level driver's "attach" or + * "auto_attach" handlers but parts of it are initialized by + * comedi_alloc_subdevices(), and other parts are initialized during + * post-configuration on return from that handler. + * + * A low-level driver that sets @insn_bits for a digital input, digital output, + * or DIO subdevice may leave @insn_read and @insn_write uninitialized, in + * which case they will be set to a default handler during post-configuration + * that uses @insn_bits to emulate the %INSN_READ and %INSN_WRITE instructions. + */ +struct comedi_subdevice { + struct comedi_device *device; + int index; + int type; + int n_chan; + int subdev_flags; + int len_chanlist; /* maximum length of channel/gain list */ + + void *private; + + struct comedi_async *async; + + void *lock; + void *busy; + unsigned int runflags; + spinlock_t spin_lock; /* generic spin-lock for COMEDI and drivers */ + + unsigned int io_bits; + + unsigned int maxdata; /* if maxdata==0, use list */ + const unsigned int *maxdata_list; /* list is channel specific */ + + const struct comedi_lrange *range_table; + const struct comedi_lrange *const *range_table_list; + + unsigned int *chanlist; /* driver-owned chanlist (not used) */ + + int (*insn_read)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_write)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_bits)(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, + unsigned int *data); + + int (*do_cmd)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*do_cmdtest)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_cmd *cmd); + int (*poll)(struct comedi_device *dev, struct comedi_subdevice *s); + int (*cancel)(struct comedi_device *dev, struct comedi_subdevice *s); + + /* called when the buffer changes */ + int (*buf_change)(struct comedi_device *dev, + struct comedi_subdevice *s); + + void (*munge)(struct comedi_device *dev, struct comedi_subdevice *s, + void *data, unsigned int num_bytes, + unsigned int start_chan_index); + enum dma_data_direction async_dma_dir; + + unsigned int state; + + struct device *class_dev; + int minor; + + unsigned int *readback; +}; + +/** + * struct comedi_buf_page - Describe a page of a COMEDI buffer + * @virt_addr: Kernel address of page. + * @dma_addr: DMA address of page if in DMA coherent memory. + */ +struct comedi_buf_page { + void *virt_addr; + dma_addr_t dma_addr; +}; + +/** + * struct comedi_buf_map - Describe pages in a COMEDI buffer + * @dma_hw_dev: Low-level hardware &struct device pointer copied from the + * COMEDI device's hw_dev member. + * @page_list: Pointer to array of &struct comedi_buf_page, one for each + * page in the buffer. + * @n_pages: Number of pages in the buffer. + * @dma_dir: DMA direction used to allocate pages of DMA coherent memory, + * or %DMA_NONE if pages allocated from regular memory. + * @refcount: &struct kref reference counter used to free the buffer. + * + * A COMEDI data buffer is allocated as individual pages, either in + * conventional memory or DMA coherent memory, depending on the attached, + * low-level hardware device. (The buffer pages also get mapped into the + * kernel's contiguous virtual address space pointed to by the 'prealloc_buf' + * member of &struct comedi_async.) + * + * The buffer is normally freed when the COMEDI device is detached from the + * low-level driver (which may happen due to device removal), but if it happens + * to be mmapped at the time, the pages cannot be freed until the buffer has + * been munmapped. That is what the reference counter is for. (The virtual + * address space pointed by 'prealloc_buf' is freed when the COMEDI device is + * detached.) + */ +struct comedi_buf_map { + struct device *dma_hw_dev; + struct comedi_buf_page *page_list; + unsigned int n_pages; + enum dma_data_direction dma_dir; + struct kref refcount; +}; + +/** + * struct comedi_async - Control data for asynchronous COMEDI commands + * @prealloc_buf: Kernel virtual address of allocated acquisition buffer. + * @prealloc_bufsz: Buffer size (in bytes). + * @buf_map: Map of buffer pages. + * @max_bufsize: Maximum allowed buffer size (in bytes). + * @buf_write_count: "Write completed" count (in bytes, modulo 2**32). + * @buf_write_alloc_count: "Allocated for writing" count (in bytes, + * modulo 2**32). + * @buf_read_count: "Read completed" count (in bytes, modulo 2**32). + * @buf_read_alloc_count: "Allocated for reading" count (in bytes, + * modulo 2**32). + * @buf_write_ptr: Buffer position for writer. + * @buf_read_ptr: Buffer position for reader. + * @cur_chan: Current position in chanlist for scan (for those drivers that + * use it). + * @scans_done: The number of scans completed. + * @scan_progress: Amount received or sent for current scan (in bytes). + * @munge_chan: Current position in chanlist for "munging". + * @munge_count: "Munge" count (in bytes, modulo 2**32). + * @munge_ptr: Buffer position for "munging". + * @events: Bit-vector of events that have occurred. + * @cmd: Details of comedi command in progress. + * @wait_head: Task wait queue for file reader or writer. + * @cb_mask: Bit-vector of events that should wake waiting tasks. + * @inttrig: Software trigger function for command, or NULL. + * + * Note about the ..._count and ..._ptr members: + * + * Think of the _Count values being integers of unlimited size, indexing + * into a buffer of infinite length (though only an advancing portion + * of the buffer of fixed length prealloc_bufsz is accessible at any + * time). Then: + * + * Buf_Read_Count <= Buf_Read_Alloc_Count <= Munge_Count <= + * Buf_Write_Count <= Buf_Write_Alloc_Count <= + * (Buf_Read_Count + prealloc_bufsz) + * + * (Those aren't the actual members, apart from prealloc_bufsz.) When the + * buffer is reset, those _Count values start at 0 and only increase in value, + * maintaining the above inequalities until the next time the buffer is + * reset. The buffer is divided into the following regions by the inequalities: + * + * [0, Buf_Read_Count): + * old region no longer accessible + * + * [Buf_Read_Count, Buf_Read_Alloc_Count): + * filled and munged region allocated for reading but not yet read + * + * [Buf_Read_Alloc_Count, Munge_Count): + * filled and munged region not yet allocated for reading + * + * [Munge_Count, Buf_Write_Count): + * filled region not yet munged + * + * [Buf_Write_Count, Buf_Write_Alloc_Count): + * unfilled region allocated for writing but not yet written + * + * [Buf_Write_Alloc_Count, Buf_Read_Count + prealloc_bufsz): + * unfilled region not yet allocated for writing + * + * [Buf_Read_Count + prealloc_bufsz, infinity): + * unfilled region not yet accessible + * + * Data needs to be written into the buffer before it can be read out, + * and may need to be converted (or "munged") between the two + * operations. Extra unfilled buffer space may need to allocated for + * writing (advancing Buf_Write_Alloc_Count) before new data is written. + * After writing new data, the newly filled space needs to be released + * (advancing Buf_Write_Count). This also results in the new data being + * "munged" (advancing Munge_Count). Before data is read out of the + * buffer, extra space may need to be allocated for reading (advancing + * Buf_Read_Alloc_Count). After the data has been read out, the space + * needs to be released (advancing Buf_Read_Count). + * + * The actual members, buf_read_count, buf_read_alloc_count, + * munge_count, buf_write_count, and buf_write_alloc_count take the + * value of the corresponding capitalized _Count values modulo 2^32 + * (UINT_MAX+1). Subtracting a "higher" _count value from a "lower" + * _count value gives the same answer as subtracting a "higher" _Count + * value from a lower _Count value because prealloc_bufsz < UINT_MAX+1. + * The modulo operation is done implicitly. + * + * The buf_read_ptr, munge_ptr, and buf_write_ptr members take the value + * of the corresponding capitalized _Count values modulo prealloc_bufsz. + * These correspond to byte indices in the physical buffer. The modulo + * operation is done by subtracting prealloc_bufsz when the value + * exceeds prealloc_bufsz (assuming prealloc_bufsz plus the increment is + * less than or equal to UINT_MAX). + */ +struct comedi_async { + void *prealloc_buf; + unsigned int prealloc_bufsz; + struct comedi_buf_map *buf_map; + unsigned int max_bufsize; + unsigned int buf_write_count; + unsigned int buf_write_alloc_count; + unsigned int buf_read_count; + unsigned int buf_read_alloc_count; + unsigned int buf_write_ptr; + unsigned int buf_read_ptr; + unsigned int cur_chan; + unsigned int scans_done; + unsigned int scan_progress; + unsigned int munge_chan; + unsigned int munge_count; + unsigned int munge_ptr; + unsigned int events; + struct comedi_cmd cmd; + wait_queue_head_t wait_head; + unsigned int cb_mask; + int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s, + unsigned int x); +}; + +/** + * enum comedi_cb - &struct comedi_async callback "events" + * @COMEDI_CB_EOS: end-of-scan + * @COMEDI_CB_EOA: end-of-acquisition/output + * @COMEDI_CB_BLOCK: data has arrived, wakes up read() / write() + * @COMEDI_CB_EOBUF: DEPRECATED: end of buffer + * @COMEDI_CB_ERROR: card error during acquisition + * @COMEDI_CB_OVERFLOW: buffer overflow/underflow + * @COMEDI_CB_ERROR_MASK: events that indicate an error has occurred + * @COMEDI_CB_CANCEL_MASK: events that will cancel an async command + */ +enum comedi_cb { + COMEDI_CB_EOS = BIT(0), + COMEDI_CB_EOA = BIT(1), + COMEDI_CB_BLOCK = BIT(2), + COMEDI_CB_EOBUF = BIT(3), + COMEDI_CB_ERROR = BIT(4), + COMEDI_CB_OVERFLOW = BIT(5), + /* masks */ + COMEDI_CB_ERROR_MASK = (COMEDI_CB_ERROR | COMEDI_CB_OVERFLOW), + COMEDI_CB_CANCEL_MASK = (COMEDI_CB_EOA | COMEDI_CB_ERROR_MASK) +}; + +/** + * struct comedi_driver - COMEDI driver registration + * @driver_name: Name of driver. + * @module: Owning module. + * @attach: The optional "attach" handler for manually configured COMEDI + * devices. + * @detach: The "detach" handler for deconfiguring COMEDI devices. + * @auto_attach: The optional "auto_attach" handler for automatically + * configured COMEDI devices. + * @num_names: Optional number of "board names" supported. + * @board_name: Optional pointer to a pointer to a board name. The pointer + * to a board name is embedded in an element of a driver-defined array + * of static, read-only board type information. + * @offset: Optional size of each element of the driver-defined array of + * static, read-only board type information, i.e. the offset between each + * pointer to a board name. + * + * This is used with comedi_driver_register() and comedi_driver_unregister() to + * register and unregister a low-level COMEDI driver with the COMEDI core. + * + * If @num_names is non-zero, @board_name should be non-NULL, and @offset + * should be at least sizeof(*board_name). These are used by the handler for + * the %COMEDI_DEVCONFIG ioctl to match a hardware device and its driver by + * board name. If @num_names is zero, the %COMEDI_DEVCONFIG ioctl matches a + * hardware device and its driver by driver name. This is only useful if the + * @attach handler is set. If @num_names is non-zero, the driver's @attach + * handler will be called with the COMEDI device structure's board_ptr member + * pointing to the matched pointer to a board name within the driver's private + * array of static, read-only board type information. + * + * The @detach handler has two roles. If a COMEDI device was successfully + * configured by the @attach or @auto_attach handler, it is called when the + * device is being deconfigured (by the %COMEDI_DEVCONFIG ioctl, or due to + * unloading of the driver, or due to device removal). It is also called when + * the @attach or @auto_attach handler returns an error. Therefore, the + * @attach or @auto_attach handlers can defer clean-up on error until the + * @detach handler is called. If the @attach or @auto_attach handlers free + * any resources themselves, they must prevent the @detach handler from + * freeing the same resources. The @detach handler must not assume that all + * resources requested by the @attach or @auto_attach handler were + * successfully allocated. + */ +struct comedi_driver { + /* private: */ + struct comedi_driver *next; /* Next in list of COMEDI drivers. */ + /* public: */ + const char *driver_name; + struct module *module; + int (*attach)(struct comedi_device *dev, struct comedi_devconfig *it); + void (*detach)(struct comedi_device *dev); + int (*auto_attach)(struct comedi_device *dev, unsigned long context); + unsigned int num_names; + const char *const *board_name; + int offset; +}; + +/** + * struct comedi_device - Working data for a COMEDI device + * @use_count: Number of open file objects. + * @driver: Low-level COMEDI driver attached to this COMEDI device. + * @pacer: Optional pointer to a dynamically allocated acquisition pacer + * control. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @private: Optional pointer to private data allocated by the low-level + * driver. It is freed automatically after the COMEDI device is + * detached from the low-level driver. + * @class_dev: Sysfs comediX device. + * @minor: Minor device number of COMEDI char device (0-47). + * @detach_count: Counter incremented every time the COMEDI device is detached. + * Used for checking a previous attachment is still valid. + * @hw_dev: Optional pointer to the low-level hardware &struct device. It is + * required for automatically configured COMEDI devices and optional for + * COMEDI devices configured by the %COMEDI_DEVCONFIG ioctl, although + * the bus-specific COMEDI functions only work if it is set correctly. + * It is also passed to dma_alloc_coherent() for COMEDI subdevices that + * have their 'async_dma_dir' member set to something other than + * %DMA_NONE. + * @board_name: Pointer to a COMEDI board name or a COMEDI driver name. When + * the low-level driver's "attach" handler is called by the handler for + * the %COMEDI_DEVCONFIG ioctl, it either points to a matched board name + * string if the 'num_names' member of the &struct comedi_driver is + * non-zero, otherwise it points to the low-level driver name string. + * When the low-lever driver's "auto_attach" handler is called for an + * automatically configured COMEDI device, it points to the low-level + * driver name string. The low-level driver is free to change it in its + * "attach" or "auto_attach" handler if it wishes. + * @board_ptr: Optional pointer to private, read-only board type information in + * the low-level driver. If the 'num_names' member of the &struct + * comedi_driver is non-zero, the handler for the %COMEDI_DEVCONFIG ioctl + * will point it to a pointer to a matched board name string within the + * driver's private array of static, read-only board type information when + * calling the driver's "attach" handler. The low-level driver is free to + * change it. + * @attached: Flag indicating that the COMEDI device is attached to a low-level + * driver. + * @ioenabled: Flag used to indicate that a PCI device has been enabled and + * its regions requested. + * @spinlock: Generic spin-lock for use by the low-level driver. + * @mutex: Generic mutex for use by the COMEDI core module. + * @attach_lock: &struct rw_semaphore used to guard against the COMEDI device + * being detached while an operation is in progress. The down_write() + * operation is only allowed while @mutex is held and is used when + * changing @attached and @detach_count and calling the low-level driver's + * "detach" handler. The down_read() operation is generally used without + * holding @mutex. + * @refcount: &struct kref reference counter for freeing COMEDI device. + * @n_subdevices: Number of COMEDI subdevices allocated by the low-level + * driver for this device. + * @subdevices: Dynamically allocated array of COMEDI subdevices. + * @mmio: Optional pointer to a remapped MMIO region set by the low-level + * driver. + * @iobase: Optional base of an I/O port region requested by the low-level + * driver. + * @iolen: Length of I/O port region requested at @iobase. + * @irq: Optional IRQ number requested by the low-level driver. + * @read_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the read() file operation. Set by the low-level driver. + * @write_subdev: Optional pointer to a default COMEDI subdevice operated on by + * the write() file operation. Set by the low-level driver. + * @async_queue: Storage for fasync_helper(). + * @open: Optional pointer to a function set by the low-level driver to be + * called when @use_count changes from 0 to 1. + * @close: Optional pointer to a function set by the low-level driver to be + * called when @use_count changed from 1 to 0. + * @insn_device_config: Optional pointer to a handler for all sub-instructions + * except %INSN_DEVICE_CONFIG_GET_ROUTES of the %INSN_DEVICE_CONFIG + * instruction. If this is not initialized by the low-level driver, a + * default handler will be set during post-configuration. + * @get_valid_routes: Optional pointer to a handler for the + * %INSN_DEVICE_CONFIG_GET_ROUTES sub-instruction of the + * %INSN_DEVICE_CONFIG instruction set. If this is not initialized by the + * low-level driver, a default handler that copies zero routes back to the + * user will be used. + * + * This is the main control data structure for a COMEDI device (as far as the + * COMEDI core is concerned). There are two groups of COMEDI devices - + * "legacy" devices that are configured by the handler for the + * %COMEDI_DEVCONFIG ioctl, and automatically configured devices resulting + * from a call to comedi_auto_config() as a result of a bus driver probe in + * a low-level COMEDI driver. The "legacy" COMEDI devices are allocated + * during module initialization if the "comedi_num_legacy_minors" module + * parameter is non-zero and use minor device numbers from 0 to + * comedi_num_legacy_minors minus one. The automatically configured COMEDI + * devices are allocated on demand and use minor device numbers from + * comedi_num_legacy_minors to 47. + */ +struct comedi_device { + int use_count; + struct comedi_driver *driver; + struct comedi_8254 *pacer; + void *private; + + struct device *class_dev; + int minor; + unsigned int detach_count; + struct device *hw_dev; + + const char *board_name; + const void *board_ptr; + unsigned int attached:1; + unsigned int ioenabled:1; + spinlock_t spinlock; /* generic spin-lock for low-level driver */ + struct mutex mutex; /* generic mutex for COMEDI core */ + struct rw_semaphore attach_lock; + struct kref refcount; + + int n_subdevices; + struct comedi_subdevice *subdevices; + + /* dumb */ + void __iomem *mmio; + unsigned long iobase; + unsigned long iolen; + unsigned int irq; + + struct comedi_subdevice *read_subdev; + struct comedi_subdevice *write_subdev; + + struct fasync_struct *async_queue; + + int (*open)(struct comedi_device *dev); + void (*close)(struct comedi_device *dev); + int (*insn_device_config)(struct comedi_device *dev, + struct comedi_insn *insn, unsigned int *data); + unsigned int (*get_valid_routes)(struct comedi_device *dev, + unsigned int n_pairs, + unsigned int *pair_data); +}; + +/* + * function prototypes + */ + +void comedi_event(struct comedi_device *dev, struct comedi_subdevice *s); + +struct comedi_device *comedi_dev_get_from_minor(unsigned int minor); +int comedi_dev_put(struct comedi_device *dev); + +bool comedi_is_subdevice_running(struct comedi_subdevice *s); + +void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size); +void comedi_set_spriv_auto_free(struct comedi_subdevice *s); + +int comedi_check_chanlist(struct comedi_subdevice *s, + int n, + unsigned int *chanlist); + +/* range stuff */ + +#define RANGE(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define RANGE_ext(a, b) {(a) * 1e6, (b) * 1e6, RF_EXTERNAL} +#define RANGE_mA(a, b) {(a) * 1e6, (b) * 1e6, UNIT_mA} +#define RANGE_unitless(a, b) {(a) * 1e6, (b) * 1e6, 0} +#define BIP_RANGE(a) {-(a) * 1e6, (a) * 1e6, 0} +#define UNI_RANGE(a) {0, (a) * 1e6, 0} + +extern const struct comedi_lrange range_bipolar10; +extern const struct comedi_lrange range_bipolar5; +extern const struct comedi_lrange range_bipolar2_5; +extern const struct comedi_lrange range_unipolar10; +extern const struct comedi_lrange range_unipolar5; +extern const struct comedi_lrange range_unipolar2_5; +extern const struct comedi_lrange range_0_20mA; +extern const struct comedi_lrange range_4_20mA; +extern const struct comedi_lrange range_0_32mA; +extern const struct comedi_lrange range_unknown; + +#define range_digital range_unipolar5 + +/** + * struct comedi_lrange - Describes a COMEDI range table + * @length: Number of entries in the range table. + * @range: Array of &struct comedi_krange, one for each range. + * + * Each element of @range[] describes the minimum and maximum physical range + * and the type of units. Typically, the type of unit is %UNIT_volt + * (i.e. volts) and the minimum and maximum are in millionths of a volt. + * There may also be a flag that indicates the minimum and maximum are merely + * scale factors for an unknown, external reference. + */ +struct comedi_lrange { + int length; + struct comedi_krange range[]; +}; + +/** + * comedi_range_is_bipolar() - Test if subdevice range is bipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_range_is_bipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min < 0; +} + +/** + * comedi_range_is_unipolar() - Test if subdevice range is unipolar + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_range_is_unipolar(struct comedi_subdevice *s, + unsigned int range) +{ + return s->range_table->range[range].min >= 0; +} + +/** + * comedi_range_is_external() - Test if subdevice range is external + * @s: COMEDI subdevice. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @range is valid. Does not work for subdevices using a + * channel-specific range table list. + * + * Return: + * %true if the range is external. + * %false if the range is internal. + */ +static inline bool comedi_range_is_external(struct comedi_subdevice *s, + unsigned int range) +{ + return !!(s->range_table->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_chan_range_is_bipolar() - Test if channel-specific range is bipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is bipolar by checking whether its minimum value + * is negative. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_bipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min < 0; +} + +/** + * comedi_chan_range_is_unipolar() - Test if channel-specific range is unipolar + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is unipolar by checking whether its minimum value + * is at least 0. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is unipolar. + * %false if the range is bipolar. + */ +static inline bool comedi_chan_range_is_unipolar(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return s->range_table_list[chan]->range[range].min >= 0; +} + +/** + * comedi_chan_range_is_external() - Test if channel-specific range is external + * @s: COMEDI subdevice. + * @chan: The channel number. + * @range: Index of range within a range table. + * + * Tests whether a range is externally reference by checking whether its + * %RF_EXTERNAL flag is set. + * + * Assumes @chan and @range are valid. Only works for subdevices with a + * channel-specific range table list. + * + * Return: + * %true if the range is bipolar. + * %false if the range is unipolar. + */ +static inline bool comedi_chan_range_is_external(struct comedi_subdevice *s, + unsigned int chan, + unsigned int range) +{ + return !!(s->range_table_list[chan]->range[range].flags & RF_EXTERNAL); +} + +/** + * comedi_offset_munge() - Convert between offset binary and 2's complement + * @s: COMEDI subdevice. + * @val: Value to be converted. + * + * Toggles the highest bit of a sample value to toggle between offset binary + * and 2's complement. Assumes that @s->maxdata is a power of 2 minus 1. + * + * Return: The converted value. + */ +static inline unsigned int comedi_offset_munge(struct comedi_subdevice *s, + unsigned int val) +{ + return val ^ s->maxdata ^ (s->maxdata >> 1); +} + +/** + * comedi_bytes_per_sample() - Determine subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. + * + * Return: The subdevice sample size. + */ +static inline unsigned int comedi_bytes_per_sample(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? sizeof(int) : sizeof(short); +} + +/** + * comedi_sample_shift() - Determine log2 of subdevice sample size + * @s: COMEDI subdevice. + * + * The sample size will be 4 (sizeof int) or 2 (sizeof short) depending on + * whether the %SDF_LSAMPL subdevice flag is set or not. The log2 of the + * sample size will be 2 or 1 and can be used as the right operand of a + * bit-shift operator to multiply or divide something by the sample size. + * + * Return: log2 of the subdevice sample size. + */ +static inline unsigned int comedi_sample_shift(struct comedi_subdevice *s) +{ + return s->subdev_flags & SDF_LSAMPL ? 2 : 1; +} + +/** + * comedi_bytes_to_samples() - Convert a number of bytes to a number of samples + * @s: COMEDI subdevice. + * @nbytes: Number of bytes + * + * Return: The number of bytes divided by the subdevice sample size. + */ +static inline unsigned int comedi_bytes_to_samples(struct comedi_subdevice *s, + unsigned int nbytes) +{ + return nbytes >> comedi_sample_shift(s); +} + +/** + * comedi_samples_to_bytes() - Convert a number of samples to a number of bytes + * @s: COMEDI subdevice. + * @nsamples: Number of samples. + * + * Return: The number of samples multiplied by the subdevice sample size. + * (Does not check for arithmetic overflow.) + */ +static inline unsigned int comedi_samples_to_bytes(struct comedi_subdevice *s, + unsigned int nsamples) +{ + return nsamples << comedi_sample_shift(s); +} + +/** + * comedi_check_trigger_src() - Trivially validate a comedi_cmd trigger source + * @src: Pointer to the trigger source to validate. + * @flags: Bitmask of valid %TRIG_* for the trigger. + * + * This is used in "step 1" of the do_cmdtest functions of comedi drivers + * to validate the comedi_cmd triggers. The mask of the @src against the + * @flags allows the userspace comedilib to pass all the comedi_cmd + * triggers as %TRIG_ANY and get back a bitmask of the valid trigger sources. + * + * Return: + * 0 if trigger sources in *@src are all supported. + * -EINVAL if any trigger source in *@src is unsupported. + */ +static inline int comedi_check_trigger_src(unsigned int *src, + unsigned int flags) +{ + unsigned int orig_src = *src; + + *src = orig_src & flags; + if (*src == TRIG_INVALID || *src != orig_src) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_is_unique() - Make sure a trigger source is unique + * @src: The trigger source to check. + * + * Return: + * 0 if no more than one trigger source is set. + * -EINVAL if more than one trigger source is set. + */ +static inline int comedi_check_trigger_is_unique(unsigned int src) +{ + /* this test is true if more than one _src bit is set */ + if ((src & (src - 1)) != 0) + return -EINVAL; + return 0; +} + +/** + * comedi_check_trigger_arg_is() - Trivially validate a trigger argument + * @arg: Pointer to the trigger arg to validate. + * @val: The value the argument should be. + * + * Forces *@arg to be @val. + * + * Return: + * 0 if *@arg was already @val. + * -EINVAL if *@arg differed from @val. + */ +static inline int comedi_check_trigger_arg_is(unsigned int *arg, + unsigned int val) +{ + if (*arg != val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_min() - Trivially validate a trigger argument min + * @arg: Pointer to the trigger arg to validate. + * @val: The minimum value the argument should be. + * + * Forces *@arg to be at least @val, setting it to @val if necessary. + * + * Return: + * 0 if *@arg was already at least @val. + * -EINVAL if *@arg was less than @val. + */ +static inline int comedi_check_trigger_arg_min(unsigned int *arg, + unsigned int val) +{ + if (*arg < val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/** + * comedi_check_trigger_arg_max() - Trivially validate a trigger argument max + * @arg: Pointer to the trigger arg to validate. + * @val: The maximum value the argument should be. + * + * Forces *@arg to be no more than @val, setting it to @val if necessary. + * + * Return: + * 0 if*@arg was already no more than @val. + * -EINVAL if *@arg was greater than @val. + */ +static inline int comedi_check_trigger_arg_max(unsigned int *arg, + unsigned int val) +{ + if (*arg > val) { + *arg = val; + return -EINVAL; + } + return 0; +} + +/* + * Must set dev->hw_dev if you wish to dma directly into comedi's buffer. + * Also useful for retrieving a previously configured hardware device of + * known bus type. Set automatically for auto-configured devices. + * Automatically set to NULL when detaching hardware device. + */ +int comedi_set_hw_dev(struct comedi_device *dev, struct device *hw_dev); + +/** + * comedi_buf_n_bytes_ready - Determine amount of unread data in buffer + * @s: COMEDI subdevice. + * + * Determines the number of bytes of unread data in the asynchronous + * acquisition data buffer for a subdevice. The data in question might not + * have been fully "munged" yet. + * + * Returns: The amount of unread data in bytes. + */ +static inline unsigned int comedi_buf_n_bytes_ready(struct comedi_subdevice *s) +{ + return s->async->buf_write_count - s->async->buf_read_count; +} + +unsigned int comedi_buf_write_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_write_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_read_n_available(struct comedi_subdevice *s); +unsigned int comedi_buf_read_alloc(struct comedi_subdevice *s, unsigned int n); +unsigned int comedi_buf_read_free(struct comedi_subdevice *s, unsigned int n); + +unsigned int comedi_buf_write_samples(struct comedi_subdevice *s, + const void *data, unsigned int nsamples); +unsigned int comedi_buf_read_samples(struct comedi_subdevice *s, + void *data, unsigned int nsamples); + +/* drivers.c - general comedi driver functions */ + +#define COMEDI_TIMEOUT_MS 1000 + +int comedi_timeout(struct comedi_device *dev, struct comedi_subdevice *s, + struct comedi_insn *insn, + int (*cb)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned long context), + unsigned long context); + +unsigned int comedi_handle_events(struct comedi_device *dev, + struct comedi_subdevice *s); + +int comedi_dio_insn_config(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data, + unsigned int mask); +unsigned int comedi_dio_update_state(struct comedi_subdevice *s, + unsigned int *data); +unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s, + struct comedi_cmd *cmd); +unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s); +unsigned int comedi_nscans_left(struct comedi_subdevice *s, + unsigned int nscans); +unsigned int comedi_nsamples_left(struct comedi_subdevice *s, + unsigned int nsamples); +void comedi_inc_scan_progress(struct comedi_subdevice *s, + unsigned int num_bytes); + +void *comedi_alloc_devpriv(struct comedi_device *dev, size_t size); +int comedi_alloc_subdevices(struct comedi_device *dev, int num_subdevices); +int comedi_alloc_subdev_readback(struct comedi_subdevice *s); + +int comedi_readback_insn_read(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); + +int comedi_load_firmware(struct comedi_device *dev, struct device *hw_dev, + const char *name, + int (*cb)(struct comedi_device *dev, + const u8 *data, size_t size, + unsigned long context), + unsigned long context); + +int __comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +int comedi_request_region(struct comedi_device *dev, + unsigned long start, unsigned long len); +void comedi_legacy_detach(struct comedi_device *dev); + +int comedi_auto_config(struct device *hardware_device, + struct comedi_driver *driver, unsigned long context); +void comedi_auto_unconfig(struct device *hardware_device); + +int comedi_driver_register(struct comedi_driver *driver); +void comedi_driver_unregister(struct comedi_driver *driver); + +/** + * module_comedi_driver() - Helper macro for registering a comedi driver + * @__comedi_driver: comedi_driver struct + * + * Helper macro for comedi drivers which do not do anything special in module + * init/exit. This eliminates a lot of boilerplate. Each module may only use + * this macro once, and calling it replaces module_init() and module_exit(). + */ +#define module_comedi_driver(__comedi_driver) \ + module_driver(__comedi_driver, comedi_driver_register, \ + comedi_driver_unregister) + +#endif /* _COMEDIDEV_H */ diff --git a/include/linux/comedi/comedilib.h b/include/linux/comedi/comedilib.h new file mode 100644 index 000000000000..0223c9cd9215 --- /dev/null +++ b/include/linux/comedi/comedilib.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedilib.h + * Header file for kcomedilib + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998-2001 David A. Schleef + */ + +#ifndef _LINUX_COMEDILIB_H +#define _LINUX_COMEDILIB_H + +struct comedi_device *comedi_open(const char *path); +int comedi_close(struct comedi_device *dev); +int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int *io); +int comedi_dio_config(struct comedi_device *dev, unsigned int subdev, + unsigned int chan, unsigned int io); +int comedi_dio_bitfield2(struct comedi_device *dev, unsigned int subdev, + unsigned int mask, unsigned int *bits, + unsigned int base_channel); +int comedi_find_subdevice_by_type(struct comedi_device *dev, int type, + unsigned int subd); +int comedi_get_n_channels(struct comedi_device *dev, unsigned int subdevice); + +#endif diff --git a/include/uapi/linux/comedi.h b/include/uapi/linux/comedi.h new file mode 100644 index 000000000000..7314e5ee0a1e --- /dev/null +++ b/include/uapi/linux/comedi.h @@ -0,0 +1,1528 @@ +/* SPDX-License-Identifier: LGPL-2.0+ WITH Linux-syscall-note */ +/* + * comedi.h + * header file for COMEDI user API + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998-2001 David A. Schleef + */ + +#ifndef _COMEDI_H +#define _COMEDI_H + +#define COMEDI_MAJORVERSION 0 +#define COMEDI_MINORVERSION 7 +#define COMEDI_MICROVERSION 76 +#define VERSION "0.7.76" + +/* comedi's major device number */ +#define COMEDI_MAJOR 98 + +/* + * maximum number of minor devices. This can be increased, although + * kernel structures are currently statically allocated, thus you + * don't want this to be much more than you actually use. + */ +#define COMEDI_NDEVICES 16 + +/* number of config options in the config structure */ +#define COMEDI_NDEVCONFOPTS 32 + +/* + * NOTE: 'comedi_config --init-data' is deprecated + * + * The following indexes in the config options were used by + * comedi_config to pass firmware blobs from user space to the + * comedi drivers. The request_firmware() hotplug interface is + * now used by all comedi drivers instead. + */ + +/* length of nth chunk of firmware data -*/ +#define COMEDI_DEVCONF_AUX_DATA3_LENGTH 25 +#define COMEDI_DEVCONF_AUX_DATA2_LENGTH 26 +#define COMEDI_DEVCONF_AUX_DATA1_LENGTH 27 +#define COMEDI_DEVCONF_AUX_DATA0_LENGTH 28 +/* most significant 32 bits of pointer address (if needed) */ +#define COMEDI_DEVCONF_AUX_DATA_HI 29 +/* least significant 32 bits of pointer address */ +#define COMEDI_DEVCONF_AUX_DATA_LO 30 +#define COMEDI_DEVCONF_AUX_DATA_LENGTH 31 /* total data length */ + +/* max length of device and driver names */ +#define COMEDI_NAMELEN 20 + +/* packs and unpacks a channel/range number */ + +#define CR_PACK(chan, rng, aref) \ + ((((aref) & 0x3) << 24) | (((rng) & 0xff) << 16) | (chan)) +#define CR_PACK_FLAGS(chan, range, aref, flags) \ + (CR_PACK(chan, range, aref) | ((flags) & CR_FLAGS_MASK)) + +#define CR_CHAN(a) ((a) & 0xffff) +#define CR_RANGE(a) (((a) >> 16) & 0xff) +#define CR_AREF(a) (((a) >> 24) & 0x03) + +#define CR_FLAGS_MASK 0xfc000000 +#define CR_ALT_FILTER 0x04000000 +#define CR_DITHER CR_ALT_FILTER +#define CR_DEGLITCH CR_ALT_FILTER +#define CR_ALT_SOURCE 0x08000000 +#define CR_EDGE 0x40000000 +#define CR_INVERT 0x80000000 + +#define AREF_GROUND 0x00 /* analog ref = analog ground */ +#define AREF_COMMON 0x01 /* analog ref = analog common */ +#define AREF_DIFF 0x02 /* analog ref = differential */ +#define AREF_OTHER 0x03 /* analog ref = other (undefined) */ + +/* counters -- these are arbitrary values */ +#define GPCT_RESET 0x0001 +#define GPCT_SET_SOURCE 0x0002 +#define GPCT_SET_GATE 0x0004 +#define GPCT_SET_DIRECTION 0x0008 +#define GPCT_SET_OPERATION 0x0010 +#define GPCT_ARM 0x0020 +#define GPCT_DISARM 0x0040 +#define GPCT_GET_INT_CLK_FRQ 0x0080 + +#define GPCT_INT_CLOCK 0x0001 +#define GPCT_EXT_PIN 0x0002 +#define GPCT_NO_GATE 0x0004 +#define GPCT_UP 0x0008 +#define GPCT_DOWN 0x0010 +#define GPCT_HWUD 0x0020 +#define GPCT_SIMPLE_EVENT 0x0040 +#define GPCT_SINGLE_PERIOD 0x0080 +#define GPCT_SINGLE_PW 0x0100 +#define GPCT_CONT_PULSE_OUT 0x0200 +#define GPCT_SINGLE_PULSE_OUT 0x0400 + +/* instructions */ + +#define INSN_MASK_WRITE 0x8000000 +#define INSN_MASK_READ 0x4000000 +#define INSN_MASK_SPECIAL 0x2000000 + +#define INSN_READ (0 | INSN_MASK_READ) +#define INSN_WRITE (1 | INSN_MASK_WRITE) +#define INSN_BITS (2 | INSN_MASK_READ | INSN_MASK_WRITE) +#define INSN_CONFIG (3 | INSN_MASK_READ | INSN_MASK_WRITE) +#define INSN_DEVICE_CONFIG (INSN_CONFIG | INSN_MASK_SPECIAL) +#define INSN_GTOD (4 | INSN_MASK_READ | INSN_MASK_SPECIAL) +#define INSN_WAIT (5 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) +#define INSN_INTTRIG (6 | INSN_MASK_WRITE | INSN_MASK_SPECIAL) + +/* command flags */ +/* These flags are used in comedi_cmd structures */ + +#define CMDF_BOGUS 0x00000001 /* do the motions */ + +/* try to use a real-time interrupt while performing command */ +#define CMDF_PRIORITY 0x00000008 + +/* wake up on end-of-scan events */ +#define CMDF_WAKE_EOS 0x00000020 + +#define CMDF_WRITE 0x00000040 + +#define CMDF_RAWDATA 0x00000080 + +/* timer rounding definitions */ +#define CMDF_ROUND_MASK 0x00030000 +#define CMDF_ROUND_NEAREST 0x00000000 +#define CMDF_ROUND_DOWN 0x00010000 +#define CMDF_ROUND_UP 0x00020000 +#define CMDF_ROUND_UP_NEXT 0x00030000 + +#define COMEDI_EV_START 0x00040000 +#define COMEDI_EV_SCAN_BEGIN 0x00080000 +#define COMEDI_EV_CONVERT 0x00100000 +#define COMEDI_EV_SCAN_END 0x00200000 +#define COMEDI_EV_STOP 0x00400000 + +/* compatibility definitions */ +#define TRIG_BOGUS CMDF_BOGUS +#define TRIG_RT CMDF_PRIORITY +#define TRIG_WAKE_EOS CMDF_WAKE_EOS +#define TRIG_WRITE CMDF_WRITE +#define TRIG_ROUND_MASK CMDF_ROUND_MASK +#define TRIG_ROUND_NEAREST CMDF_ROUND_NEAREST +#define TRIG_ROUND_DOWN CMDF_ROUND_DOWN +#define TRIG_ROUND_UP CMDF_ROUND_UP +#define TRIG_ROUND_UP_NEXT CMDF_ROUND_UP_NEXT + +/* trigger sources */ + +#define TRIG_ANY 0xffffffff +#define TRIG_INVALID 0x00000000 + +#define TRIG_NONE 0x00000001 /* never trigger */ +#define TRIG_NOW 0x00000002 /* trigger now + N ns */ +#define TRIG_FOLLOW 0x00000004 /* trigger on next lower level trig */ +#define TRIG_TIME 0x00000008 /* trigger at time N ns */ +#define TRIG_TIMER 0x00000010 /* trigger at rate N ns */ +#define TRIG_COUNT 0x00000020 /* trigger when count reaches N */ +#define TRIG_EXT 0x00000040 /* trigger on external signal N */ +#define TRIG_INT 0x00000080 /* trigger on comedi-internal signal N */ +#define TRIG_OTHER 0x00000100 /* driver defined */ + +/* subdevice flags */ + +#define SDF_BUSY 0x0001 /* device is busy */ +#define SDF_BUSY_OWNER 0x0002 /* device is busy with your job */ +#define SDF_LOCKED 0x0004 /* subdevice is locked */ +#define SDF_LOCK_OWNER 0x0008 /* you own lock */ +#define SDF_MAXDATA 0x0010 /* maxdata depends on channel */ +#define SDF_FLAGS 0x0020 /* flags depend on channel */ +#define SDF_RANGETYPE 0x0040 /* range type depends on channel */ +#define SDF_PWM_COUNTER 0x0080 /* PWM can automatically switch off */ +#define SDF_PWM_HBRIDGE 0x0100 /* PWM is signed (H-bridge) */ +#define SDF_CMD 0x1000 /* can do commands (deprecated) */ +#define SDF_SOFT_CALIBRATED 0x2000 /* subdevice uses software calibration */ +#define SDF_CMD_WRITE 0x4000 /* can do output commands */ +#define SDF_CMD_READ 0x8000 /* can do input commands */ + +/* subdevice can be read (e.g. analog input) */ +#define SDF_READABLE 0x00010000 +/* subdevice can be written (e.g. analog output) */ +#define SDF_WRITABLE 0x00020000 +#define SDF_WRITEABLE SDF_WRITABLE /* spelling error in API */ +/* subdevice does not have externally visible lines */ +#define SDF_INTERNAL 0x00040000 +#define SDF_GROUND 0x00100000 /* can do aref=ground */ +#define SDF_COMMON 0x00200000 /* can do aref=common */ +#define SDF_DIFF 0x00400000 /* can do aref=diff */ +#define SDF_OTHER 0x00800000 /* can do aref=other */ +#define SDF_DITHER 0x01000000 /* can do dithering */ +#define SDF_DEGLITCH 0x02000000 /* can do deglitching */ +#define SDF_MMAP 0x04000000 /* can do mmap() */ +#define SDF_RUNNING 0x08000000 /* subdevice is acquiring data */ +#define SDF_LSAMPL 0x10000000 /* subdevice uses 32-bit samples */ +#define SDF_PACKED 0x20000000 /* subdevice can do packed DIO */ + +/* subdevice types */ + +/** + * enum comedi_subdevice_type - COMEDI subdevice types + * @COMEDI_SUBD_UNUSED: Unused subdevice. + * @COMEDI_SUBD_AI: Analog input. + * @COMEDI_SUBD_AO: Analog output. + * @COMEDI_SUBD_DI: Digital input. + * @COMEDI_SUBD_DO: Digital output. + * @COMEDI_SUBD_DIO: Digital input/output. + * @COMEDI_SUBD_COUNTER: Counter. + * @COMEDI_SUBD_TIMER: Timer. + * @COMEDI_SUBD_MEMORY: Memory, EEPROM, DPRAM. + * @COMEDI_SUBD_CALIB: Calibration DACs. + * @COMEDI_SUBD_PROC: Processor, DSP. + * @COMEDI_SUBD_SERIAL: Serial I/O. + * @COMEDI_SUBD_PWM: Pulse-Width Modulation output. + */ +enum comedi_subdevice_type { + COMEDI_SUBD_UNUSED, + COMEDI_SUBD_AI, + COMEDI_SUBD_AO, + COMEDI_SUBD_DI, + COMEDI_SUBD_DO, + COMEDI_SUBD_DIO, + COMEDI_SUBD_COUNTER, + COMEDI_SUBD_TIMER, + COMEDI_SUBD_MEMORY, + COMEDI_SUBD_CALIB, + COMEDI_SUBD_PROC, + COMEDI_SUBD_SERIAL, + COMEDI_SUBD_PWM +}; + +/* configuration instructions */ + +/** + * enum comedi_io_direction - COMEDI I/O directions + * @COMEDI_INPUT: Input. + * @COMEDI_OUTPUT: Output. + * @COMEDI_OPENDRAIN: Open-drain (or open-collector) output. + * + * These are used by the %INSN_CONFIG_DIO_QUERY configuration instruction to + * report a direction. They may also be used in other places where a direction + * needs to be specified. + */ +enum comedi_io_direction { + COMEDI_INPUT = 0, + COMEDI_OUTPUT = 1, + COMEDI_OPENDRAIN = 2 +}; + +/** + * enum configuration_ids - COMEDI configuration instruction codes + * @INSN_CONFIG_DIO_INPUT: Configure digital I/O as input. + * @INSN_CONFIG_DIO_OUTPUT: Configure digital I/O as output. + * @INSN_CONFIG_DIO_OPENDRAIN: Configure digital I/O as open-drain (or open + * collector) output. + * @INSN_CONFIG_ANALOG_TRIG: Configure analog trigger. + * @INSN_CONFIG_ALT_SOURCE: Configure alternate input source. + * @INSN_CONFIG_DIGITAL_TRIG: Configure digital trigger. + * @INSN_CONFIG_BLOCK_SIZE: Configure block size for DMA transfers. + * @INSN_CONFIG_TIMER_1: Configure divisor for external clock. + * @INSN_CONFIG_FILTER: Configure a filter. + * @INSN_CONFIG_CHANGE_NOTIFY: Configure change notification for digital + * inputs. (New drivers should use + * %INSN_CONFIG_DIGITAL_TRIG instead.) + * @INSN_CONFIG_SERIAL_CLOCK: Configure clock for serial I/O. + * @INSN_CONFIG_BIDIRECTIONAL_DATA: Send and receive byte over serial I/O. + * @INSN_CONFIG_DIO_QUERY: Query direction of digital I/O channel. + * @INSN_CONFIG_PWM_OUTPUT: Configure pulse-width modulator output. + * @INSN_CONFIG_GET_PWM_OUTPUT: Get pulse-width modulator output configuration. + * @INSN_CONFIG_ARM: Arm a subdevice or channel. + * @INSN_CONFIG_DISARM: Disarm a subdevice or channel. + * @INSN_CONFIG_GET_COUNTER_STATUS: Get counter status. + * @INSN_CONFIG_RESET: Reset a subdevice or channel. + * @INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR: Configure counter/timer as + * single pulse generator. + * @INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR: Configure counter/timer as + * pulse train generator. + * @INSN_CONFIG_GPCT_QUADRATURE_ENCODER: Configure counter as a quadrature + * encoder. + * @INSN_CONFIG_SET_GATE_SRC: Set counter/timer gate source. + * @INSN_CONFIG_GET_GATE_SRC: Get counter/timer gate source. + * @INSN_CONFIG_SET_CLOCK_SRC: Set counter/timer master clock source. + * @INSN_CONFIG_GET_CLOCK_SRC: Get counter/timer master clock source. + * @INSN_CONFIG_SET_OTHER_SRC: Set counter/timer "other" source. + * @INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE: Get size (in bytes) of subdevice's + * on-board FIFOs used during streaming + * input/output. + * @INSN_CONFIG_SET_COUNTER_MODE: Set counter/timer mode. + * @INSN_CONFIG_8254_SET_MODE: (Deprecated) Same as + * %INSN_CONFIG_SET_COUNTER_MODE. + * @INSN_CONFIG_8254_READ_STATUS: Read status of 8254 counter channel. + * @INSN_CONFIG_SET_ROUTING: Set routing for a channel. + * @INSN_CONFIG_GET_ROUTING: Get routing for a channel. + * @INSN_CONFIG_PWM_SET_PERIOD: Set PWM period in nanoseconds. + * @INSN_CONFIG_PWM_GET_PERIOD: Get PWM period in nanoseconds. + * @INSN_CONFIG_GET_PWM_STATUS: Get PWM status. + * @INSN_CONFIG_PWM_SET_H_BRIDGE: Set PWM H bridge duty cycle and polarity for + * a relay simultaneously. + * @INSN_CONFIG_PWM_GET_H_BRIDGE: Get PWM H bridge duty cycle and polarity. + * @INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS: Get the hardware timing restraints, + * regardless of trigger sources. + */ +enum configuration_ids { + INSN_CONFIG_DIO_INPUT = COMEDI_INPUT, + INSN_CONFIG_DIO_OUTPUT = COMEDI_OUTPUT, + INSN_CONFIG_DIO_OPENDRAIN = COMEDI_OPENDRAIN, + INSN_CONFIG_ANALOG_TRIG = 16, +/* INSN_CONFIG_WAVEFORM = 17, */ +/* INSN_CONFIG_TRIG = 18, */ +/* INSN_CONFIG_COUNTER = 19, */ + INSN_CONFIG_ALT_SOURCE = 20, + INSN_CONFIG_DIGITAL_TRIG = 21, + INSN_CONFIG_BLOCK_SIZE = 22, + INSN_CONFIG_TIMER_1 = 23, + INSN_CONFIG_FILTER = 24, + INSN_CONFIG_CHANGE_NOTIFY = 25, + + INSN_CONFIG_SERIAL_CLOCK = 26, /*ALPHA*/ + INSN_CONFIG_BIDIRECTIONAL_DATA = 27, + INSN_CONFIG_DIO_QUERY = 28, + INSN_CONFIG_PWM_OUTPUT = 29, + INSN_CONFIG_GET_PWM_OUTPUT = 30, + INSN_CONFIG_ARM = 31, + INSN_CONFIG_DISARM = 32, + INSN_CONFIG_GET_COUNTER_STATUS = 33, + INSN_CONFIG_RESET = 34, + INSN_CONFIG_GPCT_SINGLE_PULSE_GENERATOR = 1001, + INSN_CONFIG_GPCT_PULSE_TRAIN_GENERATOR = 1002, + INSN_CONFIG_GPCT_QUADRATURE_ENCODER = 1003, + INSN_CONFIG_SET_GATE_SRC = 2001, + INSN_CONFIG_GET_GATE_SRC = 2002, + INSN_CONFIG_SET_CLOCK_SRC = 2003, + INSN_CONFIG_GET_CLOCK_SRC = 2004, + INSN_CONFIG_SET_OTHER_SRC = 2005, + INSN_CONFIG_GET_HARDWARE_BUFFER_SIZE = 2006, + INSN_CONFIG_SET_COUNTER_MODE = 4097, + INSN_CONFIG_8254_SET_MODE = INSN_CONFIG_SET_COUNTER_MODE, + INSN_CONFIG_8254_READ_STATUS = 4098, + INSN_CONFIG_SET_ROUTING = 4099, + INSN_CONFIG_GET_ROUTING = 4109, + INSN_CONFIG_PWM_SET_PERIOD = 5000, + INSN_CONFIG_PWM_GET_PERIOD = 5001, + INSN_CONFIG_GET_PWM_STATUS = 5002, + INSN_CONFIG_PWM_SET_H_BRIDGE = 5003, + INSN_CONFIG_PWM_GET_H_BRIDGE = 5004, + INSN_CONFIG_GET_CMD_TIMING_CONSTRAINTS = 5005, +}; + +/** + * enum device_configuration_ids - COMEDI configuration instruction codes global + * to an entire device. + * @INSN_DEVICE_CONFIG_TEST_ROUTE: Validate the possibility of a + * globally-named route + * @INSN_DEVICE_CONFIG_CONNECT_ROUTE: Connect a globally-named route + * @INSN_DEVICE_CONFIG_DISCONNECT_ROUTE:Disconnect a globally-named route + * @INSN_DEVICE_CONFIG_GET_ROUTES: Get a list of all globally-named routes + * that are valid for a particular device. + */ +enum device_config_route_ids { + INSN_DEVICE_CONFIG_TEST_ROUTE = 0, + INSN_DEVICE_CONFIG_CONNECT_ROUTE = 1, + INSN_DEVICE_CONFIG_DISCONNECT_ROUTE = 2, + INSN_DEVICE_CONFIG_GET_ROUTES = 3, +}; + +/** + * enum comedi_digital_trig_op - operations for configuring a digital trigger + * @COMEDI_DIGITAL_TRIG_DISABLE: Return digital trigger to its default, + * inactive, unconfigured state. + * @COMEDI_DIGITAL_TRIG_ENABLE_EDGES: Set rising and/or falling edge inputs + * that each can fire the trigger. + * @COMEDI_DIGITAL_TRIG_ENABLE_LEVELS: Set a combination of high and/or low + * level inputs that can fire the trigger. + * + * These are used with the %INSN_CONFIG_DIGITAL_TRIG configuration instruction. + * The data for the configuration instruction is as follows... + * + * data[%0] = %INSN_CONFIG_DIGITAL_TRIG + * + * data[%1] = trigger ID + * + * data[%2] = configuration operation + * + * data[%3] = configuration parameter 1 + * + * data[%4] = configuration parameter 2 + * + * data[%5] = configuration parameter 3 + * + * The trigger ID (data[%1]) is used to differentiate multiple digital triggers + * belonging to the same subdevice. The configuration operation (data[%2]) is + * one of the enum comedi_digital_trig_op values. The configuration + * parameters (data[%3], data[%4], and data[%5]) depend on the operation; they + * are not used with %COMEDI_DIGITAL_TRIG_DISABLE. + * + * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES and %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, + * configuration parameter 1 (data[%3]) contains a "left-shift" value that + * specifies the input corresponding to bit 0 of configuration parameters 2 + * and 3. This is useful if the trigger has more than 32 inputs. + * + * For %COMEDI_DIGITAL_TRIG_ENABLE_EDGES, configuration parameter 2 (data[%4]) + * specifies which of up to 32 inputs have rising-edge sensitivity, and + * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs + * have falling-edge sensitivity that can fire the trigger. + * + * For %COMEDI_DIGITAL_TRIG_ENABLE_LEVELS, configuration parameter 2 (data[%4]) + * specifies which of up to 32 inputs must be at a high level, and + * configuration parameter 3 (data[%5]) specifies which of up to 32 inputs + * must be at a low level for the trigger to fire. + * + * Some sequences of %INSN_CONFIG_DIGITAL_TRIG instructions may have a (partly) + * accumulative effect, depending on the low-level driver. This is useful + * when setting up a trigger that has more than 32 inputs, or has a combination + * of edge- and level-triggered inputs. + */ +enum comedi_digital_trig_op { + COMEDI_DIGITAL_TRIG_DISABLE = 0, + COMEDI_DIGITAL_TRIG_ENABLE_EDGES = 1, + COMEDI_DIGITAL_TRIG_ENABLE_LEVELS = 2 +}; + +/** + * enum comedi_support_level - support level for a COMEDI feature + * @COMEDI_UNKNOWN_SUPPORT: Unspecified support for feature. + * @COMEDI_SUPPORTED: Feature is supported. + * @COMEDI_UNSUPPORTED: Feature is unsupported. + */ +enum comedi_support_level { + COMEDI_UNKNOWN_SUPPORT = 0, + COMEDI_SUPPORTED, + COMEDI_UNSUPPORTED +}; + +/** + * enum comedi_counter_status_flags - counter status bits + * @COMEDI_COUNTER_ARMED: Counter is armed. + * @COMEDI_COUNTER_COUNTING: Counter is counting. + * @COMEDI_COUNTER_TERMINAL_COUNT: Counter reached terminal count. + * + * These bitwise values are used by the %INSN_CONFIG_GET_COUNTER_STATUS + * configuration instruction to report the status of a counter. + */ +enum comedi_counter_status_flags { + COMEDI_COUNTER_ARMED = 0x1, + COMEDI_COUNTER_COUNTING = 0x2, + COMEDI_COUNTER_TERMINAL_COUNT = 0x4, +}; + +/* ioctls */ + +#define CIO 'd' +#define COMEDI_DEVCONFIG _IOW(CIO, 0, struct comedi_devconfig) +#define COMEDI_DEVINFO _IOR(CIO, 1, struct comedi_devinfo) +#define COMEDI_SUBDINFO _IOR(CIO, 2, struct comedi_subdinfo) +#define COMEDI_CHANINFO _IOR(CIO, 3, struct comedi_chaninfo) +/* _IOWR(CIO, 4, ...) is reserved */ +#define COMEDI_LOCK _IO(CIO, 5) +#define COMEDI_UNLOCK _IO(CIO, 6) +#define COMEDI_CANCEL _IO(CIO, 7) +#define COMEDI_RANGEINFO _IOR(CIO, 8, struct comedi_rangeinfo) +#define COMEDI_CMD _IOR(CIO, 9, struct comedi_cmd) +#define COMEDI_CMDTEST _IOR(CIO, 10, struct comedi_cmd) +#define COMEDI_INSNLIST _IOR(CIO, 11, struct comedi_insnlist) +#define COMEDI_INSN _IOR(CIO, 12, struct comedi_insn) +#define COMEDI_BUFCONFIG _IOR(CIO, 13, struct comedi_bufconfig) +#define COMEDI_BUFINFO _IOWR(CIO, 14, struct comedi_bufinfo) +#define COMEDI_POLL _IO(CIO, 15) +#define COMEDI_SETRSUBD _IO(CIO, 16) +#define COMEDI_SETWSUBD _IO(CIO, 17) + +/* structures */ + +/** + * struct comedi_insn - COMEDI instruction + * @insn: COMEDI instruction type (%INSN_xxx). + * @n: Length of @data[]. + * @data: Pointer to data array operated on by the instruction. + * @subdev: Subdevice index. + * @chanspec: A packed "chanspec" value consisting of channel number, + * analog range index, analog reference type, and flags. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_INSN ioctl, and indirectly with the + * %COMEDI_INSNLIST ioctl. + */ +struct comedi_insn { + unsigned int insn; + unsigned int n; + unsigned int __user *data; + unsigned int subdev; + unsigned int chanspec; + unsigned int unused[3]; +}; + +/** + * struct comedi_insnlist - list of COMEDI instructions + * @n_insns: Number of COMEDI instructions. + * @insns: Pointer to array COMEDI instructions. + * + * This is used with the %COMEDI_INSNLIST ioctl. + */ +struct comedi_insnlist { + unsigned int n_insns; + struct comedi_insn __user *insns; +}; + +/** + * struct comedi_cmd - COMEDI asynchronous acquisition command details + * @subdev: Subdevice index. + * @flags: Command flags (%CMDF_xxx). + * @start_src: "Start acquisition" trigger source (%TRIG_xxx). + * @start_arg: "Start acquisition" trigger argument. + * @scan_begin_src: "Scan begin" trigger source. + * @scan_begin_arg: "Scan begin" trigger argument. + * @convert_src: "Convert" trigger source. + * @convert_arg: "Convert" trigger argument. + * @scan_end_src: "Scan end" trigger source. + * @scan_end_arg: "Scan end" trigger argument. + * @stop_src: "Stop acquisition" trigger source. + * @stop_arg: "Stop acquisition" trigger argument. + * @chanlist: Pointer to array of "chanspec" values, containing a + * sequence of channel numbers packed with analog range + * index, etc. + * @chanlist_len: Number of channels in sequence. + * @data: Pointer to miscellaneous set-up data (not used). + * @data_len: Length of miscellaneous set-up data. + * + * This is used with the %COMEDI_CMD or %COMEDI_CMDTEST ioctl to set-up + * or validate an asynchronous acquisition command. The ioctl may modify + * the &struct comedi_cmd and copy it back to the caller. + * + * Optional command @flags values that can be ORed together... + * + * %CMDF_BOGUS - makes %COMEDI_CMD ioctl return error %EAGAIN instead of + * starting the command. + * + * %CMDF_PRIORITY - requests "hard real-time" processing (which is not + * supported in this version of COMEDI). + * + * %CMDF_WAKE_EOS - requests the command makes data available for reading + * after every "scan" period. + * + * %CMDF_WRITE - marks the command as being in the "write" (to device) + * direction. This does not need to be specified by the caller unless the + * subdevice supports commands in either direction. + * + * %CMDF_RAWDATA - prevents the command from "munging" the data between the + * COMEDI sample format and the raw hardware sample format. + * + * %CMDF_ROUND_NEAREST - requests timing periods to be rounded to nearest + * supported values. + * + * %CMDF_ROUND_DOWN - requests timing periods to be rounded down to supported + * values (frequencies rounded up). + * + * %CMDF_ROUND_UP - requests timing periods to be rounded up to supported + * values (frequencies rounded down). + * + * Trigger source values for @start_src, @scan_begin_src, @convert_src, + * @scan_end_src, and @stop_src... + * + * %TRIG_ANY - "all ones" value used to test which trigger sources are + * supported. + * + * %TRIG_INVALID - "all zeroes" value used to indicate that all requested + * trigger sources are invalid. + * + * %TRIG_NONE - never trigger (often used as a @stop_src value). + * + * %TRIG_NOW - trigger after '_arg' nanoseconds. + * + * %TRIG_FOLLOW - trigger follows another event. + * + * %TRIG_TIMER - trigger every '_arg' nanoseconds. + * + * %TRIG_COUNT - trigger when count '_arg' is reached. + * + * %TRIG_EXT - trigger on external signal specified by '_arg'. + * + * %TRIG_INT - trigger on internal, software trigger specified by '_arg'. + * + * %TRIG_OTHER - trigger on other, driver-defined signal specified by '_arg'. + */ +struct comedi_cmd { + unsigned int subdev; + unsigned int flags; + + unsigned int start_src; + unsigned int start_arg; + + unsigned int scan_begin_src; + unsigned int scan_begin_arg; + + unsigned int convert_src; + unsigned int convert_arg; + + unsigned int scan_end_src; + unsigned int scan_end_arg; + + unsigned int stop_src; + unsigned int stop_arg; + + unsigned int *chanlist; + unsigned int chanlist_len; + + short __user *data; + unsigned int data_len; +}; + +/** + * struct comedi_chaninfo - used to retrieve per-channel information + * @subdev: Subdevice index. + * @maxdata_list: Optional pointer to per-channel maximum data values. + * @flaglist: Optional pointer to per-channel flags. + * @rangelist: Optional pointer to per-channel range types. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_CHANINFO ioctl to get per-channel information + * for the subdevice. Use of this requires knowledge of the number of channels + * and subdevice flags obtained using the %COMEDI_SUBDINFO ioctl. + * + * The @maxdata_list member must be %NULL unless the %SDF_MAXDATA subdevice + * flag is set. The @flaglist member must be %NULL unless the %SDF_FLAGS + * subdevice flag is set. The @rangelist member must be %NULL unless the + * %SDF_RANGETYPE subdevice flag is set. Otherwise, the arrays they point to + * must be at least as long as the number of channels. + */ +struct comedi_chaninfo { + unsigned int subdev; + unsigned int __user *maxdata_list; + unsigned int __user *flaglist; + unsigned int __user *rangelist; + unsigned int unused[4]; +}; + +/** + * struct comedi_rangeinfo - used to retrieve the range table for a channel + * @range_type: Encodes subdevice index (bits 27:24), channel index + * (bits 23:16) and range table length (bits 15:0). + * @range_ptr: Pointer to array of @struct comedi_krange to be filled + * in with the range table for the channel or subdevice. + * + * This is used with the %COMEDI_RANGEINFO ioctl to retrieve the range table + * for a specific channel (if the subdevice has the %SDF_RANGETYPE flag set to + * indicate that the range table depends on the channel), or for the subdevice + * as a whole (if the %SDF_RANGETYPE flag is clear, indicating the range table + * is shared by all channels). + * + * The @range_type value is an input to the ioctl and comes from a previous + * use of the %COMEDI_SUBDINFO ioctl (if the %SDF_RANGETYPE flag is clear), + * or the %COMEDI_CHANINFO ioctl (if the %SDF_RANGETYPE flag is set). + */ +struct comedi_rangeinfo { + unsigned int range_type; + void __user *range_ptr; +}; + +/** + * struct comedi_krange - describes a range in a range table + * @min: Minimum value in millionths (1e-6) of a unit. + * @max: Maximum value in millionths (1e-6) of a unit. + * @flags: Indicates the units (in bits 7:0) OR'ed with optional flags. + * + * A range table is associated with a single channel, or with all channels in a + * subdevice, and a list of one or more ranges. A %struct comedi_krange + * describes the physical range of units for one of those ranges. Sample + * values in COMEDI are unsigned from %0 up to some 'maxdata' value. The + * mapping from sample values to physical units is assumed to be nomimally + * linear (for the purpose of describing the range), with sample value %0 + * mapping to @min, and the 'maxdata' sample value mapping to @max. + * + * The currently defined units are %UNIT_volt (%0), %UNIT_mA (%1), and + * %UNIT_none (%2). The @min and @max values are the physical range multiplied + * by 1e6, so a @max value of %1000000 (with %UNIT_volt) represents a maximal + * value of 1 volt. + * + * The only defined flag value is %RF_EXTERNAL (%0x100), indicating that the + * range needs to be multiplied by an external reference. + */ +struct comedi_krange { + int min; + int max; + unsigned int flags; +}; + +/** + * struct comedi_subdinfo - used to retrieve information about a subdevice + * @type: Type of subdevice from &enum comedi_subdevice_type. + * @n_chan: Number of channels the subdevice supports. + * @subd_flags: A mixture of static and dynamic flags describing + * aspects of the subdevice and its current state. + * @timer_type: Timer type. Always set to %5 ("nanosecond timer"). + * @len_chanlist: Maximum length of a channel list if the subdevice + * supports asynchronous acquisition commands. + * @maxdata: Maximum sample value for all channels if the + * %SDF_MAXDATA subdevice flag is clear. + * @flags: Channel flags for all channels if the %SDF_FLAGS + * subdevice flag is clear. + * @range_type: The range type for all channels if the %SDF_RANGETYPE + * subdevice flag is clear. Encodes the subdevice index + * (bits 27:24), a dummy channel index %0 (bits 23:16), + * and the range table length (bits 15:0). + * @settling_time_0: Not used. + * @insn_bits_support: Set to %COMEDI_SUPPORTED if the subdevice supports the + * %INSN_BITS instruction, or to %COMEDI_UNSUPPORTED if it + * does not. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_SUBDINFO ioctl which copies an array of + * &struct comedi_subdinfo back to user space, with one element per subdevice. + * Use of this requires knowledge of the number of subdevices obtained from + * the %COMEDI_DEVINFO ioctl. + * + * These are the @subd_flags values that may be ORed together... + * + * %SDF_BUSY - the subdevice is busy processing an asynchronous command or a + * synchronous instruction. + * + * %SDF_BUSY_OWNER - the subdevice is busy processing an asynchronous + * acquisition command started on the current file object (the file object + * issuing the %COMEDI_SUBDINFO ioctl). + * + * %SDF_LOCKED - the subdevice is locked by a %COMEDI_LOCK ioctl. + * + * %SDF_LOCK_OWNER - the subdevice is locked by a %COMEDI_LOCK ioctl from the + * current file object. + * + * %SDF_MAXDATA - maximum sample values are channel-specific. + * + * %SDF_FLAGS - channel flags are channel-specific. + * + * %SDF_RANGETYPE - range types are channel-specific. + * + * %SDF_PWM_COUNTER - PWM can switch off automatically. + * + * %SDF_PWM_HBRIDGE - or PWM is signed (H-bridge). + * + * %SDF_CMD - the subdevice supports asynchronous commands. + * + * %SDF_SOFT_CALIBRATED - the subdevice uses software calibration. + * + * %SDF_CMD_WRITE - the subdevice supports asynchronous commands in the output + * ("write") direction. + * + * %SDF_CMD_READ - the subdevice supports asynchronous commands in the input + * ("read") direction. + * + * %SDF_READABLE - the subdevice is readable (e.g. analog input). + * + * %SDF_WRITABLE (aliased as %SDF_WRITEABLE) - the subdevice is writable (e.g. + * analog output). + * + * %SDF_INTERNAL - the subdevice has no externally visible lines. + * + * %SDF_GROUND - the subdevice can use ground as an analog reference. + * + * %SDF_COMMON - the subdevice can use a common analog reference. + * + * %SDF_DIFF - the subdevice can use differential inputs (or outputs). + * + * %SDF_OTHER - the subdevice can use some other analog reference. + * + * %SDF_DITHER - the subdevice can do dithering. + * + * %SDF_DEGLITCH - the subdevice can do deglitching. + * + * %SDF_MMAP - this is never set. + * + * %SDF_RUNNING - an asynchronous command is still running. + * + * %SDF_LSAMPL - the subdevice uses "long" (32-bit) samples (for asynchronous + * command data). + * + * %SDF_PACKED - the subdevice packs several DIO samples into a single sample + * (for asynchronous command data). + * + * No "channel flags" (@flags) values are currently defined. + */ +struct comedi_subdinfo { + unsigned int type; + unsigned int n_chan; + unsigned int subd_flags; + unsigned int timer_type; + unsigned int len_chanlist; + unsigned int maxdata; + unsigned int flags; + unsigned int range_type; + unsigned int settling_time_0; + unsigned int insn_bits_support; + unsigned int unused[8]; +}; + +/** + * struct comedi_devinfo - used to retrieve information about a COMEDI device + * @version_code: COMEDI version code. + * @n_subdevs: Number of subdevices the device has. + * @driver_name: Null-terminated COMEDI driver name. + * @board_name: Null-terminated COMEDI board name. + * @read_subdevice: Index of the current "read" subdevice (%-1 if none). + * @write_subdevice: Index of the current "write" subdevice (%-1 if none). + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_DEVINFO ioctl to get basic information about + * the device. + */ +struct comedi_devinfo { + unsigned int version_code; + unsigned int n_subdevs; + char driver_name[COMEDI_NAMELEN]; + char board_name[COMEDI_NAMELEN]; + int read_subdevice; + int write_subdevice; + int unused[30]; +}; + +/** + * struct comedi_devconfig - used to configure a legacy COMEDI device + * @board_name: Null-terminated string specifying the type of board + * to configure. + * @options: An array of integer configuration options. + * + * This is used with the %COMEDI_DEVCONFIG ioctl to configure a "legacy" COMEDI + * device, such as an ISA card. Not all COMEDI drivers support this. Those + * that do either expect the specified board name to match one of a list of + * names registered with the COMEDI core, or expect the specified board name + * to match the COMEDI driver name itself. The configuration options are + * handled in a driver-specific manner. + */ +struct comedi_devconfig { + char board_name[COMEDI_NAMELEN]; + int options[COMEDI_NDEVCONFOPTS]; +}; + +/** + * struct comedi_bufconfig - used to set or get buffer size for a subdevice + * @subdevice: Subdevice index. + * @flags: Not used. + * @maximum_size: Maximum allowed buffer size. + * @size: Buffer size. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_BUFCONFIG ioctl to get or configure the + * maximum buffer size and current buffer size for a COMEDI subdevice that + * supports asynchronous commands. If the subdevice does not support + * asynchronous commands, @maximum_size and @size are ignored and set to 0. + * + * On ioctl input, non-zero values of @maximum_size and @size specify a + * new maximum size and new current size (in bytes), respectively. These + * will by rounded up to a multiple of %PAGE_SIZE. Specifying a new maximum + * size requires admin capabilities. + * + * On ioctl output, @maximum_size and @size and set to the current maximum + * buffer size and current buffer size, respectively. + */ +struct comedi_bufconfig { + unsigned int subdevice; + unsigned int flags; + + unsigned int maximum_size; + unsigned int size; + + unsigned int unused[4]; +}; + +/** + * struct comedi_bufinfo - used to manipulate buffer position for a subdevice + * @subdevice: Subdevice index. + * @bytes_read: Specify amount to advance read position for an + * asynchronous command in the input ("read") direction. + * @buf_write_ptr: Current write position (index) within the buffer. + * @buf_read_ptr: Current read position (index) within the buffer. + * @buf_write_count: Total amount written, modulo 2^32. + * @buf_read_count: Total amount read, modulo 2^32. + * @bytes_written: Specify amount to advance write position for an + * asynchronous command in the output ("write") direction. + * @unused: Reserved for future use. + * + * This is used with the %COMEDI_BUFINFO ioctl to optionally advance the + * current read or write position in an asynchronous acquisition data buffer, + * and to get the current read and write positions in the buffer. + */ +struct comedi_bufinfo { + unsigned int subdevice; + unsigned int bytes_read; + + unsigned int buf_write_ptr; + unsigned int buf_read_ptr; + unsigned int buf_write_count; + unsigned int buf_read_count; + + unsigned int bytes_written; + + unsigned int unused[4]; +}; + +/* range stuff */ + +#define __RANGE(a, b) ((((a) & 0xffff) << 16) | ((b) & 0xffff)) + +#define RANGE_OFFSET(a) (((a) >> 16) & 0xffff) +#define RANGE_LENGTH(b) ((b) & 0xffff) + +#define RF_UNIT(flags) ((flags) & 0xff) +#define RF_EXTERNAL 0x100 + +#define UNIT_volt 0 +#define UNIT_mA 1 +#define UNIT_none 2 + +#define COMEDI_MIN_SPEED 0xffffffffu + +/**********************************************************/ +/* everything after this line is ALPHA */ +/**********************************************************/ + +/* + * 8254 specific configuration. + * + * It supports two config commands: + * + * 0 ID: INSN_CONFIG_SET_COUNTER_MODE + * 1 8254 Mode + * I8254_MODE0, I8254_MODE1, ..., I8254_MODE5 + * OR'ed with: + * I8254_BCD, I8254_BINARY + * + * 0 ID: INSN_CONFIG_8254_READ_STATUS + * 1 <-- Status byte returned here. + * B7 = Output + * B6 = NULL Count + * B5 - B0 Current mode. + */ + +enum i8254_mode { + I8254_MODE0 = (0 << 1), /* Interrupt on terminal count */ + I8254_MODE1 = (1 << 1), /* Hardware retriggerable one-shot */ + I8254_MODE2 = (2 << 1), /* Rate generator */ + I8254_MODE3 = (3 << 1), /* Square wave mode */ + I8254_MODE4 = (4 << 1), /* Software triggered strobe */ + /* Hardware triggered strobe (retriggerable) */ + I8254_MODE5 = (5 << 1), + /* Use binary-coded decimal instead of binary (pretty useless) */ + I8254_BCD = 1, + I8254_BINARY = 0 +}; + +/* *** BEGIN GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ + +/* + * Common National Instruments Terminal/Signal names. + * Some of these have no NI_ prefix as they are useful for non-NI hardware, such + * as those that utilize the PXI/RTSI trigger lines. + * + * NOTE ABOUT THE CHOICE OF NAMES HERE AND THE CAMELSCRIPT: + * The choice to use CamelScript and the exact names below is for + * maintainability, clarity, similarity to manufacturer's documentation, + * _and_ a mitigation for confusion that has plagued the use of these drivers + * for years! + * + * More detail: + * There have been significant confusions over the past many years for users + * when trying to understand how to connect to/from signals and terminals on + * NI hardware using comedi. The major reason for this is that the actual + * register values were exposed and required to be used by users. Several + * major reasons exist why this caused major confusion for users: + * 1) The register values are _NOT_ in user documentation, but rather in + * arcane locations, such as a few register programming manuals that are + * increasingly hard to find and the NI MHDDK (comments in example code). + * There is no one place to find the various valid values of the registers. + * 2) The register values are _NOT_ completely consistent. There is no way to + * gain any sense of intuition of which values, or even enums one should use + * for various registers. There was some attempt in prior use of comedi to + * name enums such that a user might know which enums should be used for + * varying purposes, but the end-user had to gain a knowledge of register + * values to correctly wield this approach. + * 3) The names for signals and registers found in the various register level + * programming manuals and vendor-provided documentation are _not_ even + * close to the same names that are in the end-user documentation. + * + * Similar, albeit less, confusion plagued NI's previous version of their own + * drivers. Earlier than 2003, NI greatly simplified the situation for users + * by releasing a new API that abstracted the names of signals/terminals to a + * common and intuitive set of names. + * + * The names below mirror the names chosen and well documented by NI. These + * names are exposed to the user via the comedilib user library. By keeping + * the names below, in spite of the use of CamelScript, maintenance will be + * greatly eased and confusion for users _and_ comedi developers will be + * greatly reduced. + */ + +/* + * Base of abstracted NI names. + * The first 16 bits of *_arg are reserved for channel selection. + * Since we only actually need the first 4 or 5 bits for all register values on + * NI select registers anyways, we'll identify all values >= (1<<15) as being an + * abstracted NI signal/terminal name. + * These values are also used/returned by INSN_DEVICE_CONFIG_TEST_ROUTE, + * INSN_DEVICE_CONFIG_CONNECT_ROUTE, INSN_DEVICE_CONFIG_DISCONNECT_ROUTE, + * and INSN_DEVICE_CONFIG_GET_ROUTES. + */ +#define NI_NAMES_BASE 0x8000u + +#define _TERM_N(base, n, x) ((base) + ((x) & ((n) - 1))) + +/* + * not necessarily all allowed 64 PFIs are valid--certainly not for all devices + */ +#define NI_PFI(x) _TERM_N(NI_NAMES_BASE, 64, x) +/* 8 trigger lines by standard, Some devices cannot talk to all eight. */ +#define TRIGGER_LINE(x) _TERM_N(NI_PFI(-1) + 1, 8, x) +/* 4 RTSI shared MUXes to route signals to/from TRIGGER_LINES on NI hardware */ +#define NI_RTSI_BRD(x) _TERM_N(TRIGGER_LINE(-1) + 1, 4, x) + +/* *** Counter/timer names : 8 counters max *** */ +#define NI_MAX_COUNTERS 8 +#define NI_COUNTER_NAMES_BASE (NI_RTSI_BRD(-1) + 1) +#define NI_CtrSource(x) _TERM_N(NI_COUNTER_NAMES_BASE, NI_MAX_COUNTERS, x) +/* Gate, Aux, A,B,Z are all treated, at times as gates */ +#define NI_GATES_NAMES_BASE (NI_CtrSource(-1) + 1) +#define NI_CtrGate(x) _TERM_N(NI_GATES_NAMES_BASE, NI_MAX_COUNTERS, x) +#define NI_CtrAux(x) _TERM_N(NI_CtrGate(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrA(x) _TERM_N(NI_CtrAux(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrB(x) _TERM_N(NI_CtrA(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrZ(x) _TERM_N(NI_CtrB(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_GATES_NAMES_MAX NI_CtrZ(-1) +#define NI_CtrArmStartTrigger(x) _TERM_N(NI_CtrZ(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_CtrInternalOutput(x) \ + _TERM_N(NI_CtrArmStartTrigger(-1) + 1, NI_MAX_COUNTERS, x) +/** external pin(s) labeled conveniently as CtrOut. */ +#define NI_CtrOut(x) _TERM_N(NI_CtrInternalOutput(-1) + 1, NI_MAX_COUNTERS, x) +/** For Buffered sampling of ctr -- x series capability. */ +#define NI_CtrSampleClock(x) _TERM_N(NI_CtrOut(-1) + 1, NI_MAX_COUNTERS, x) +#define NI_COUNTER_NAMES_MAX NI_CtrSampleClock(-1) + +enum ni_common_signal_names { + /* PXI_Star: this is a non-NI-specific signal */ + PXI_Star = NI_COUNTER_NAMES_MAX + 1, + PXI_Clk10, + PXIe_Clk100, + NI_AI_SampleClock, + NI_AI_SampleClockTimebase, + NI_AI_StartTrigger, + NI_AI_ReferenceTrigger, + NI_AI_ConvertClock, + NI_AI_ConvertClockTimebase, + NI_AI_PauseTrigger, + NI_AI_HoldCompleteEvent, + NI_AI_HoldComplete, + NI_AI_ExternalMUXClock, + NI_AI_STOP, /* pulse signal that occurs when a update is finished(?) */ + NI_AO_SampleClock, + NI_AO_SampleClockTimebase, + NI_AO_StartTrigger, + NI_AO_PauseTrigger, + NI_DI_SampleClock, + NI_DI_SampleClockTimebase, + NI_DI_StartTrigger, + NI_DI_ReferenceTrigger, + NI_DI_PauseTrigger, + NI_DI_InputBufferFull, + NI_DI_ReadyForStartEvent, + NI_DI_ReadyForTransferEventBurst, + NI_DI_ReadyForTransferEventPipelined, + NI_DO_SampleClock, + NI_DO_SampleClockTimebase, + NI_DO_StartTrigger, + NI_DO_PauseTrigger, + NI_DO_OutputBufferFull, + NI_DO_DataActiveEvent, + NI_DO_ReadyForStartEvent, + NI_DO_ReadyForTransferEvent, + NI_MasterTimebase, + NI_20MHzTimebase, + NI_80MHzTimebase, + NI_100MHzTimebase, + NI_200MHzTimebase, + NI_100kHzTimebase, + NI_10MHzRefClock, + NI_FrequencyOutput, + NI_ChangeDetectionEvent, + NI_AnalogComparisonEvent, + NI_WatchdogExpiredEvent, + NI_WatchdogExpirationTrigger, + NI_SCXI_Trig1, + NI_LogicLow, + NI_LogicHigh, + NI_ExternalStrobe, + NI_PFI_DO, + NI_CaseGround, + /* special internal signal used as variable source for RTSI bus: */ + NI_RGOUT0, + + /* just a name to make the next more convenient, regardless of above */ + _NI_NAMES_MAX_PLUS_1, + NI_NUM_NAMES = _NI_NAMES_MAX_PLUS_1 - NI_NAMES_BASE, +}; + +/* *** END GLOBALLY-NAMED NI TERMINALS/SIGNALS *** */ + +#define NI_USUAL_PFI_SELECT(x) (((x) < 10) ? (0x1 + (x)) : (0xb + (x))) +#define NI_USUAL_RTSI_SELECT(x) (((x) < 7) ? (0xb + (x)) : 0x1b) + +/* + * mode bits for NI general-purpose counters, set with + * INSN_CONFIG_SET_COUNTER_MODE + */ +#define NI_GPCT_COUNTING_MODE_SHIFT 16 +#define NI_GPCT_INDEX_PHASE_BITSHIFT 20 +#define NI_GPCT_COUNTING_DIRECTION_SHIFT 24 +enum ni_gpct_mode_bits { + NI_GPCT_GATE_ON_BOTH_EDGES_BIT = 0x4, + NI_GPCT_EDGE_GATE_MODE_MASK = 0x18, + NI_GPCT_EDGE_GATE_STARTS_STOPS_BITS = 0x0, + NI_GPCT_EDGE_GATE_STOPS_STARTS_BITS = 0x8, + NI_GPCT_EDGE_GATE_STARTS_BITS = 0x10, + NI_GPCT_EDGE_GATE_NO_STARTS_NO_STOPS_BITS = 0x18, + NI_GPCT_STOP_MODE_MASK = 0x60, + NI_GPCT_STOP_ON_GATE_BITS = 0x00, + NI_GPCT_STOP_ON_GATE_OR_TC_BITS = 0x20, + NI_GPCT_STOP_ON_GATE_OR_SECOND_TC_BITS = 0x40, + NI_GPCT_LOAD_B_SELECT_BIT = 0x80, + NI_GPCT_OUTPUT_MODE_MASK = 0x300, + NI_GPCT_OUTPUT_TC_PULSE_BITS = 0x100, + NI_GPCT_OUTPUT_TC_TOGGLE_BITS = 0x200, + NI_GPCT_OUTPUT_TC_OR_GATE_TOGGLE_BITS = 0x300, + NI_GPCT_HARDWARE_DISARM_MASK = 0xc00, + NI_GPCT_NO_HARDWARE_DISARM_BITS = 0x000, + NI_GPCT_DISARM_AT_TC_BITS = 0x400, + NI_GPCT_DISARM_AT_GATE_BITS = 0x800, + NI_GPCT_DISARM_AT_TC_OR_GATE_BITS = 0xc00, + NI_GPCT_LOADING_ON_TC_BIT = 0x1000, + NI_GPCT_LOADING_ON_GATE_BIT = 0x4000, + NI_GPCT_COUNTING_MODE_MASK = 0x7 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_NORMAL_BITS = + 0x0 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_QUADRATURE_X1_BITS = + 0x1 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_QUADRATURE_X2_BITS = + 0x2 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_QUADRATURE_X4_BITS = + 0x3 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_TWO_PULSE_BITS = + 0x4 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_COUNTING_MODE_SYNC_SOURCE_BITS = + 0x6 << NI_GPCT_COUNTING_MODE_SHIFT, + NI_GPCT_INDEX_PHASE_MASK = 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_LOW_A_LOW_B_BITS = + 0x0 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_LOW_A_HIGH_B_BITS = + 0x1 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_HIGH_A_LOW_B_BITS = + 0x2 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_PHASE_HIGH_A_HIGH_B_BITS = + 0x3 << NI_GPCT_INDEX_PHASE_BITSHIFT, + NI_GPCT_INDEX_ENABLE_BIT = 0x400000, + NI_GPCT_COUNTING_DIRECTION_MASK = + 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_DOWN_BITS = + 0x00 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_UP_BITS = + 0x1 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_HW_UP_DOWN_BITS = + 0x2 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_COUNTING_DIRECTION_HW_GATE_BITS = + 0x3 << NI_GPCT_COUNTING_DIRECTION_SHIFT, + NI_GPCT_RELOAD_SOURCE_MASK = 0xc000000, + NI_GPCT_RELOAD_SOURCE_FIXED_BITS = 0x0, + NI_GPCT_RELOAD_SOURCE_SWITCHING_BITS = 0x4000000, + NI_GPCT_RELOAD_SOURCE_GATE_SELECT_BITS = 0x8000000, + NI_GPCT_OR_GATE_BIT = 0x10000000, + NI_GPCT_INVERT_OUTPUT_BIT = 0x20000000 +}; + +/* + * Bits for setting a clock source with + * INSN_CONFIG_SET_CLOCK_SRC when using NI general-purpose counters. + */ +enum ni_gpct_clock_source_bits { + NI_GPCT_CLOCK_SRC_SELECT_MASK = 0x3f, + NI_GPCT_TIMEBASE_1_CLOCK_SRC_BITS = 0x0, + NI_GPCT_TIMEBASE_2_CLOCK_SRC_BITS = 0x1, + NI_GPCT_TIMEBASE_3_CLOCK_SRC_BITS = 0x2, + NI_GPCT_LOGIC_LOW_CLOCK_SRC_BITS = 0x3, + NI_GPCT_NEXT_GATE_CLOCK_SRC_BITS = 0x4, + NI_GPCT_NEXT_TC_CLOCK_SRC_BITS = 0x5, + /* NI 660x-specific */ + NI_GPCT_SOURCE_PIN_i_CLOCK_SRC_BITS = 0x6, + NI_GPCT_PXI10_CLOCK_SRC_BITS = 0x7, + NI_GPCT_PXI_STAR_TRIGGER_CLOCK_SRC_BITS = 0x8, + NI_GPCT_ANALOG_TRIGGER_OUT_CLOCK_SRC_BITS = 0x9, + NI_GPCT_PRESCALE_MODE_CLOCK_SRC_MASK = 0x30000000, + NI_GPCT_NO_PRESCALE_CLOCK_SRC_BITS = 0x0, + /* divide source by 2 */ + NI_GPCT_PRESCALE_X2_CLOCK_SRC_BITS = 0x10000000, + /* divide source by 8 */ + NI_GPCT_PRESCALE_X8_CLOCK_SRC_BITS = 0x20000000, + NI_GPCT_INVERT_CLOCK_SRC_BIT = 0x80000000 +}; + +/* NI 660x-specific */ +#define NI_GPCT_SOURCE_PIN_CLOCK_SRC_BITS(x) (0x10 + (x)) + +#define NI_GPCT_RTSI_CLOCK_SRC_BITS(x) (0x18 + (x)) + +/* no pfi on NI 660x */ +#define NI_GPCT_PFI_CLOCK_SRC_BITS(x) (0x20 + (x)) + +/* + * Possibilities for setting a gate source with + * INSN_CONFIG_SET_GATE_SRC when using NI general-purpose counters. + * May be bitwise-or'd with CR_EDGE or CR_INVERT. + */ +enum ni_gpct_gate_select { + /* m-series gates */ + NI_GPCT_TIMESTAMP_MUX_GATE_SELECT = 0x0, + NI_GPCT_AI_START2_GATE_SELECT = 0x12, + NI_GPCT_PXI_STAR_TRIGGER_GATE_SELECT = 0x13, + NI_GPCT_NEXT_OUT_GATE_SELECT = 0x14, + NI_GPCT_AI_START1_GATE_SELECT = 0x1c, + NI_GPCT_NEXT_SOURCE_GATE_SELECT = 0x1d, + NI_GPCT_ANALOG_TRIGGER_OUT_GATE_SELECT = 0x1e, + NI_GPCT_LOGIC_LOW_GATE_SELECT = 0x1f, + /* more gates for 660x */ + NI_GPCT_SOURCE_PIN_i_GATE_SELECT = 0x100, + NI_GPCT_GATE_PIN_i_GATE_SELECT = 0x101, + /* more gates for 660x "second gate" */ + NI_GPCT_UP_DOWN_PIN_i_GATE_SELECT = 0x201, + NI_GPCT_SELECTED_GATE_GATE_SELECT = 0x21e, + /* + * m-series "second gate" sources are unknown, + * we should add them here with an offset of 0x300 when + * known. + */ + NI_GPCT_DISABLED_GATE_SELECT = 0x8000, +}; + +#define NI_GPCT_GATE_PIN_GATE_SELECT(x) (0x102 + (x)) +#define NI_GPCT_RTSI_GATE_SELECT(x) NI_USUAL_RTSI_SELECT(x) +#define NI_GPCT_PFI_GATE_SELECT(x) NI_USUAL_PFI_SELECT(x) +#define NI_GPCT_UP_DOWN_PIN_GATE_SELECT(x) (0x202 + (x)) + +/* + * Possibilities for setting a source with + * INSN_CONFIG_SET_OTHER_SRC when using NI general-purpose counters. + */ +enum ni_gpct_other_index { + NI_GPCT_SOURCE_ENCODER_A, + NI_GPCT_SOURCE_ENCODER_B, + NI_GPCT_SOURCE_ENCODER_Z +}; + +enum ni_gpct_other_select { + /* m-series gates */ + /* Still unknown, probably only need NI_GPCT_PFI_OTHER_SELECT */ + NI_GPCT_DISABLED_OTHER_SELECT = 0x8000, +}; + +#define NI_GPCT_PFI_OTHER_SELECT(x) NI_USUAL_PFI_SELECT(x) + +/* + * start sources for ni general-purpose counters for use with + * INSN_CONFIG_ARM + */ +enum ni_gpct_arm_source { + NI_GPCT_ARM_IMMEDIATE = 0x0, + /* + * Start both the counter and the adjacent paired counter simultaneously + */ + NI_GPCT_ARM_PAIRED_IMMEDIATE = 0x1, + /* + * If the NI_GPCT_HW_ARM bit is set, we will pass the least significant + * bits (3 bits for 660x or 5 bits for m-series) through to the + * hardware. To select a hardware trigger, pass the appropriate select + * bit, e.g., + * NI_GPCT_HW_ARM | NI_GPCT_AI_START1_GATE_SELECT or + * NI_GPCT_HW_ARM | NI_GPCT_PFI_GATE_SELECT(pfi_number) + */ + NI_GPCT_HW_ARM = 0x1000, + NI_GPCT_ARM_UNKNOWN = NI_GPCT_HW_ARM, /* for backward compatibility */ +}; + +/* digital filtering options for ni 660x for use with INSN_CONFIG_FILTER. */ +enum ni_gpct_filter_select { + NI_GPCT_FILTER_OFF = 0x0, + NI_GPCT_FILTER_TIMEBASE_3_SYNC = 0x1, + NI_GPCT_FILTER_100x_TIMEBASE_1 = 0x2, + NI_GPCT_FILTER_20x_TIMEBASE_1 = 0x3, + NI_GPCT_FILTER_10x_TIMEBASE_1 = 0x4, + NI_GPCT_FILTER_2x_TIMEBASE_1 = 0x5, + NI_GPCT_FILTER_2x_TIMEBASE_3 = 0x6 +}; + +/* + * PFI digital filtering options for ni m-series for use with + * INSN_CONFIG_FILTER. + */ +enum ni_pfi_filter_select { + NI_PFI_FILTER_OFF = 0x0, + NI_PFI_FILTER_125ns = 0x1, + NI_PFI_FILTER_6425ns = 0x2, + NI_PFI_FILTER_2550us = 0x3 +}; + +/* master clock sources for ni mio boards and INSN_CONFIG_SET_CLOCK_SRC */ +enum ni_mio_clock_source { + NI_MIO_INTERNAL_CLOCK = 0, + /* + * Doesn't work for m-series, use NI_MIO_PLL_RTSI_CLOCK() + * the NI_MIO_PLL_* sources are m-series only + */ + NI_MIO_RTSI_CLOCK = 1, + NI_MIO_PLL_PXI_STAR_TRIGGER_CLOCK = 2, + NI_MIO_PLL_PXI10_CLOCK = 3, + NI_MIO_PLL_RTSI0_CLOCK = 4 +}; + +#define NI_MIO_PLL_RTSI_CLOCK(x) (NI_MIO_PLL_RTSI0_CLOCK + (x)) + +/* + * Signals which can be routed to an NI RTSI pin with INSN_CONFIG_SET_ROUTING. + * The numbers assigned are not arbitrary, they correspond to the bits required + * to program the board. + */ +enum ni_rtsi_routing { + NI_RTSI_OUTPUT_ADR_START1 = 0, + NI_RTSI_OUTPUT_ADR_START2 = 1, + NI_RTSI_OUTPUT_SCLKG = 2, + NI_RTSI_OUTPUT_DACUPDN = 3, + NI_RTSI_OUTPUT_DA_START1 = 4, + NI_RTSI_OUTPUT_G_SRC0 = 5, + NI_RTSI_OUTPUT_G_GATE0 = 6, + NI_RTSI_OUTPUT_RGOUT0 = 7, + NI_RTSI_OUTPUT_RTSI_BRD_0 = 8, + /* Pre-m-series always have RTSI clock on line 7 */ + NI_RTSI_OUTPUT_RTSI_OSC = 12 +}; + +#define NI_RTSI_OUTPUT_RTSI_BRD(x) (NI_RTSI_OUTPUT_RTSI_BRD_0 + (x)) + +/* + * Signals which can be routed to an NI PFI pin on an m-series board with + * INSN_CONFIG_SET_ROUTING. These numbers are also returned by + * INSN_CONFIG_GET_ROUTING on pre-m-series boards, even though their routing + * cannot be changed. The numbers assigned are not arbitrary, they correspond + * to the bits required to program the board. + */ +enum ni_pfi_routing { + NI_PFI_OUTPUT_PFI_DEFAULT = 0, + NI_PFI_OUTPUT_AI_START1 = 1, + NI_PFI_OUTPUT_AI_START2 = 2, + NI_PFI_OUTPUT_AI_CONVERT = 3, + NI_PFI_OUTPUT_G_SRC1 = 4, + NI_PFI_OUTPUT_G_GATE1 = 5, + NI_PFI_OUTPUT_AO_UPDATE_N = 6, + NI_PFI_OUTPUT_AO_START1 = 7, + NI_PFI_OUTPUT_AI_START_PULSE = 8, + NI_PFI_OUTPUT_G_SRC0 = 9, + NI_PFI_OUTPUT_G_GATE0 = 10, + NI_PFI_OUTPUT_EXT_STROBE = 11, + NI_PFI_OUTPUT_AI_EXT_MUX_CLK = 12, + NI_PFI_OUTPUT_GOUT0 = 13, + NI_PFI_OUTPUT_GOUT1 = 14, + NI_PFI_OUTPUT_FREQ_OUT = 15, + NI_PFI_OUTPUT_PFI_DO = 16, + NI_PFI_OUTPUT_I_ATRIG = 17, + NI_PFI_OUTPUT_RTSI0 = 18, + NI_PFI_OUTPUT_PXI_STAR_TRIGGER_IN = 26, + NI_PFI_OUTPUT_SCXI_TRIG1 = 27, + NI_PFI_OUTPUT_DIO_CHANGE_DETECT_RTSI = 28, + NI_PFI_OUTPUT_CDI_SAMPLE = 29, + NI_PFI_OUTPUT_CDO_UPDATE = 30 +}; + +#define NI_PFI_OUTPUT_RTSI(x) (NI_PFI_OUTPUT_RTSI0 + (x)) + +/* + * Signals which can be routed to output on a NI PFI pin on a 660x board + * with INSN_CONFIG_SET_ROUTING. The numbers assigned are + * not arbitrary, they correspond to the bits required + * to program the board. Lines 0 to 7 can only be set to + * NI_660X_PFI_OUTPUT_DIO. Lines 32 to 39 can only be set to + * NI_660X_PFI_OUTPUT_COUNTER. + */ +enum ni_660x_pfi_routing { + NI_660X_PFI_OUTPUT_COUNTER = 1, /* counter */ + NI_660X_PFI_OUTPUT_DIO = 2, /* static digital output */ +}; + +/* + * NI External Trigger lines. These values are not arbitrary, but are related + * to the bits required to program the board (offset by 1 for historical + * reasons). + */ +#define NI_EXT_PFI(x) (NI_USUAL_PFI_SELECT(x) - 1) +#define NI_EXT_RTSI(x) (NI_USUAL_RTSI_SELECT(x) - 1) + +/* + * Clock sources for CDIO subdevice on NI m-series boards. Used as the + * scan_begin_arg for a comedi_command. These sources may also be bitwise-or'd + * with CR_INVERT to change polarity. + */ +enum ni_m_series_cdio_scan_begin_src { + NI_CDIO_SCAN_BEGIN_SRC_GROUND = 0, + NI_CDIO_SCAN_BEGIN_SRC_AI_START = 18, + NI_CDIO_SCAN_BEGIN_SRC_AI_CONVERT = 19, + NI_CDIO_SCAN_BEGIN_SRC_PXI_STAR_TRIGGER = 20, + NI_CDIO_SCAN_BEGIN_SRC_G0_OUT = 28, + NI_CDIO_SCAN_BEGIN_SRC_G1_OUT = 29, + NI_CDIO_SCAN_BEGIN_SRC_ANALOG_TRIGGER = 30, + NI_CDIO_SCAN_BEGIN_SRC_AO_UPDATE = 31, + NI_CDIO_SCAN_BEGIN_SRC_FREQ_OUT = 32, + NI_CDIO_SCAN_BEGIN_SRC_DIO_CHANGE_DETECT_IRQ = 33 +}; + +#define NI_CDIO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) +#define NI_CDIO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) + +/* + * scan_begin_src for scan_begin_arg==TRIG_EXT with analog output command on NI + * boards. These scan begin sources can also be bitwise-or'd with CR_INVERT to + * change polarity. + */ +#define NI_AO_SCAN_BEGIN_SRC_PFI(x) NI_USUAL_PFI_SELECT(x) +#define NI_AO_SCAN_BEGIN_SRC_RTSI(x) NI_USUAL_RTSI_SELECT(x) + +/* + * Bits for setting a clock source with + * INSN_CONFIG_SET_CLOCK_SRC when using NI frequency output subdevice. + */ +enum ni_freq_out_clock_source_bits { + NI_FREQ_OUT_TIMEBASE_1_DIV_2_CLOCK_SRC, /* 10 MHz */ + NI_FREQ_OUT_TIMEBASE_2_CLOCK_SRC /* 100 KHz */ +}; + +/* + * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for + * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). + */ +enum amplc_dio_clock_source { + /* + * Per channel external clock + * input/output pin (pin is only an + * input when clock source set to this value, + * otherwise it is an output) + */ + AMPLC_DIO_CLK_CLKN, + AMPLC_DIO_CLK_10MHZ, /* 10 MHz internal clock */ + AMPLC_DIO_CLK_1MHZ, /* 1 MHz internal clock */ + AMPLC_DIO_CLK_100KHZ, /* 100 kHz internal clock */ + AMPLC_DIO_CLK_10KHZ, /* 10 kHz internal clock */ + AMPLC_DIO_CLK_1KHZ, /* 1 kHz internal clock */ + /* + * Output of preceding counter channel + * (for channel 0, preceding counter + * channel is channel 2 on preceding + * counter subdevice, for first counter + * subdevice, preceding counter + * subdevice is the last counter + * subdevice) + */ + AMPLC_DIO_CLK_OUTNM1, + AMPLC_DIO_CLK_EXT, /* per chip external input pin */ + /* the following are "enhanced" clock sources for PCIe models */ + AMPLC_DIO_CLK_VCC, /* clock input HIGH */ + AMPLC_DIO_CLK_GND, /* clock input LOW */ + AMPLC_DIO_CLK_PAT_PRESENT, /* "pattern present" signal */ + AMPLC_DIO_CLK_20MHZ /* 20 MHz internal clock */ +}; + +/* + * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for + * timer subdevice on some Amplicon DIO PCIe boards (amplc_dio200 driver). + */ +enum amplc_dio_ts_clock_src { + AMPLC_DIO_TS_CLK_1GHZ, /* 1 ns period with 20 ns granularity */ + AMPLC_DIO_TS_CLK_1MHZ, /* 1 us period */ + AMPLC_DIO_TS_CLK_1KHZ /* 1 ms period */ +}; + +/* + * Values for setting a gate source with INSN_CONFIG_SET_GATE_SRC for + * 8254 counter subdevices on Amplicon DIO boards (amplc_dio200 driver). + */ +enum amplc_dio_gate_source { + AMPLC_DIO_GAT_VCC, /* internal high logic level */ + AMPLC_DIO_GAT_GND, /* internal low logic level */ + AMPLC_DIO_GAT_GATN, /* per channel external gate input */ + /* + * negated output of counter channel minus 2 + * (for channels 0 or 1, channel minus 2 is channel 1 or 2 on + * the preceding counter subdevice, for the first counter subdevice + * the preceding counter subdevice is the last counter subdevice) + */ + AMPLC_DIO_GAT_NOUTNM2, + AMPLC_DIO_GAT_RESERVED4, + AMPLC_DIO_GAT_RESERVED5, + AMPLC_DIO_GAT_RESERVED6, + AMPLC_DIO_GAT_RESERVED7, + /* the following are "enhanced" gate sources for PCIe models */ + AMPLC_DIO_GAT_NGATN = 6, /* negated per channel gate input */ + /* non-negated output of counter channel minus 2 */ + AMPLC_DIO_GAT_OUTNM2, + AMPLC_DIO_GAT_PAT_PRESENT, /* "pattern present" signal */ + AMPLC_DIO_GAT_PAT_OCCURRED, /* "pattern occurred" latched */ + AMPLC_DIO_GAT_PAT_GONE, /* "pattern gone away" latched */ + AMPLC_DIO_GAT_NPAT_PRESENT, /* negated "pattern present" */ + AMPLC_DIO_GAT_NPAT_OCCURRED, /* negated "pattern occurred" */ + AMPLC_DIO_GAT_NPAT_GONE /* negated "pattern gone away" */ +}; + +/* + * Values for setting a clock source with INSN_CONFIG_SET_CLOCK_SRC for + * the counter subdevice on the Kolter Electronic PCI-Counter board + * (ke_counter driver). + */ +enum ke_counter_clock_source { + KE_CLK_20MHZ, /* internal 20MHz (default) */ + KE_CLK_4MHZ, /* internal 4MHz (option) */ + KE_CLK_EXT /* external clock on pin 21 of D-Sub */ +}; + +#endif /* _COMEDI_H */ -- cgit v1.2.3 From 631e272b12075b60f7c7fc4f84f937d78a699844 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 17 Nov 2021 12:06:01 +0000 Subject: comedi: Move and rename "8255.h" to Some of the header files in "drivers/comedi/drivers/" are common enough to be useful to out-of-tree comedi driver modules. Using them for out-of-tree module builds is hampered by the headers being outside the "include/" directory so it is desirable to move them. There are about a couple of dozen Comedi device drivers that use the "comedi_8255" module to add digital I/O subdevices based on the venerable 8255 Programmable Peripheral Interface chip. The macros and declarations to use that module are in the "8255.h" header file in the comedi "drivers" directory. Move it into "include/linux/comedi/" and rename it to "comedi_8255.h" for naming consistency reasons. Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20211117120604.117740-4-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/comedi/drivers/8255.c | 3 +- drivers/comedi/drivers/8255.h | 42 ---------------------------- drivers/comedi/drivers/8255_pci.c | 3 +- drivers/comedi/drivers/adv_pci_dio.c | 2 +- drivers/comedi/drivers/aio_aio12_8.c | 2 +- drivers/comedi/drivers/amplc_dio200_common.c | 2 +- drivers/comedi/drivers/amplc_pc236_common.c | 2 +- drivers/comedi/drivers/amplc_pci230.c | 2 +- drivers/comedi/drivers/cb_pcidas.c | 2 +- drivers/comedi/drivers/cb_pcidas64.c | 2 +- drivers/comedi/drivers/cb_pcidda.c | 3 +- drivers/comedi/drivers/cb_pcimdas.c | 2 +- drivers/comedi/drivers/cb_pcimdda.c | 3 +- drivers/comedi/drivers/comedi_8255.c | 3 +- drivers/comedi/drivers/daqboard2000.c | 2 +- drivers/comedi/drivers/das08.c | 2 +- drivers/comedi/drivers/das16.c | 2 +- drivers/comedi/drivers/das16m1.c | 2 +- drivers/comedi/drivers/dmm32at.c | 3 +- drivers/comedi/drivers/ni_atmio.c | 2 +- drivers/comedi/drivers/ni_atmio16d.c | 3 +- drivers/comedi/drivers/ni_daq_dio24.c | 3 +- drivers/comedi/drivers/ni_labpc_common.c | 2 +- drivers/comedi/drivers/ni_mio_common.c | 2 +- drivers/comedi/drivers/ni_mio_cs.c | 2 +- drivers/comedi/drivers/pcl724.c | 3 +- drivers/comedi/drivers/pcm3724.c | 3 +- include/linux/comedi/comedi_8255.h | 42 ++++++++++++++++++++++++++++ 28 files changed, 68 insertions(+), 78 deletions(-) delete mode 100644 drivers/comedi/drivers/8255.h create mode 100644 include/linux/comedi/comedi_8255.h (limited to 'include/linux') diff --git a/drivers/comedi/drivers/8255.c b/drivers/comedi/drivers/8255.c index f23a52b7c919..ced8ea09d4fa 100644 --- a/drivers/comedi/drivers/8255.c +++ b/drivers/comedi/drivers/8255.c @@ -41,8 +41,7 @@ #include #include - -#include "8255.h" +#include static int dev_8255_attach(struct comedi_device *dev, struct comedi_devconfig *it) diff --git a/drivers/comedi/drivers/8255.h b/drivers/comedi/drivers/8255.h deleted file mode 100644 index ceae3ca52e60..000000000000 --- a/drivers/comedi/drivers/8255.h +++ /dev/null @@ -1,42 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * module/8255.h - * Header file for 8255 - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 1998 David A. Schleef - */ - -#ifndef _8255_H -#define _8255_H - -#define I8255_SIZE 0x04 - -#define I8255_DATA_A_REG 0x00 -#define I8255_DATA_B_REG 0x01 -#define I8255_DATA_C_REG 0x02 -#define I8255_CTRL_REG 0x03 -#define I8255_CTRL_C_LO_IO BIT(0) -#define I8255_CTRL_B_IO BIT(1) -#define I8255_CTRL_B_MODE BIT(2) -#define I8255_CTRL_C_HI_IO BIT(3) -#define I8255_CTRL_A_IO BIT(4) -#define I8255_CTRL_A_MODE(x) ((x) << 5) -#define I8255_CTRL_CW BIT(7) - -struct comedi_device; -struct comedi_subdevice; - -int subdev_8255_init(struct comedi_device *dev, struct comedi_subdevice *s, - int (*io)(struct comedi_device *dev, int dir, int port, - int data, unsigned long regbase), - unsigned long regbase); - -int subdev_8255_mm_init(struct comedi_device *dev, struct comedi_subdevice *s, - int (*io)(struct comedi_device *dev, int dir, int port, - int data, unsigned long regbase), - unsigned long regbase); - -unsigned long subdev_8255_regbase(struct comedi_subdevice *s); - -#endif diff --git a/drivers/comedi/drivers/8255_pci.c b/drivers/comedi/drivers/8255_pci.c index 76b8b4762bae..0fec048e3a53 100644 --- a/drivers/comedi/drivers/8255_pci.c +++ b/drivers/comedi/drivers/8255_pci.c @@ -54,8 +54,7 @@ #include #include - -#include "8255.h" +#include enum pci_8255_boardid { BOARD_ADLINK_PCI7224, diff --git a/drivers/comedi/drivers/adv_pci_dio.c b/drivers/comedi/drivers/adv_pci_dio.c index 5947f08b9a1e..1ec602f8c6e1 100644 --- a/drivers/comedi/drivers/adv_pci_dio.c +++ b/drivers/comedi/drivers/adv_pci_dio.c @@ -24,8 +24,8 @@ #include #include #include +#include -#include "8255.h" #include "comedi_8254.h" /* diff --git a/drivers/comedi/drivers/aio_aio12_8.c b/drivers/comedi/drivers/aio_aio12_8.c index 36c3a2d8a352..cd797dc0f828 100644 --- a/drivers/comedi/drivers/aio_aio12_8.c +++ b/drivers/comedi/drivers/aio_aio12_8.c @@ -23,9 +23,9 @@ #include #include +#include #include "comedi_8254.h" -#include "8255.h" /* * Register map diff --git a/drivers/comedi/drivers/amplc_dio200_common.c b/drivers/comedi/drivers/amplc_dio200_common.c index 950c50be4ff3..26b4049b366c 100644 --- a/drivers/comedi/drivers/amplc_dio200_common.c +++ b/drivers/comedi/drivers/amplc_dio200_common.c @@ -13,10 +13,10 @@ #include #include #include +#include /* only for register defines */ #include "amplc_dio200.h" #include "comedi_8254.h" -#include "8255.h" /* only for register defines */ /* 200 series registers */ #define DIO200_IO_SIZE 0x20 diff --git a/drivers/comedi/drivers/amplc_pc236_common.c b/drivers/comedi/drivers/amplc_pc236_common.c index b8b0a624f72b..9f4f89b1ef23 100644 --- a/drivers/comedi/drivers/amplc_pc236_common.c +++ b/drivers/comedi/drivers/amplc_pc236_common.c @@ -12,9 +12,9 @@ #include #include #include +#include #include "amplc_pc236.h" -#include "8255.h" static void pc236_intr_update(struct comedi_device *dev, bool enable) { diff --git a/drivers/comedi/drivers/amplc_pci230.c b/drivers/comedi/drivers/amplc_pci230.c index 554ee40e321f..93f7057d5b3f 100644 --- a/drivers/comedi/drivers/amplc_pci230.c +++ b/drivers/comedi/drivers/amplc_pci230.c @@ -175,9 +175,9 @@ #include #include #include +#include #include "comedi_8254.h" -#include "8255.h" /* * PCI230 PCI configuration register information diff --git a/drivers/comedi/drivers/cb_pcidas.c b/drivers/comedi/drivers/cb_pcidas.c index 9b603532a4e7..75ff02b47959 100644 --- a/drivers/comedi/drivers/cb_pcidas.c +++ b/drivers/comedi/drivers/cb_pcidas.c @@ -55,9 +55,9 @@ #include #include #include +#include #include "comedi_8254.h" -#include "8255.h" #include "amcc_s5933.h" #define AI_BUFFER_SIZE 1024 /* max ai fifo size */ diff --git a/drivers/comedi/drivers/cb_pcidas64.c b/drivers/comedi/drivers/cb_pcidas64.c index 7d4808faa1fb..ca6038a25f26 100644 --- a/drivers/comedi/drivers/cb_pcidas64.c +++ b/drivers/comedi/drivers/cb_pcidas64.c @@ -74,8 +74,8 @@ #include #include #include +#include -#include "8255.h" #include "plx9080.h" #define TIMER_BASE 25 /* 40MHz master clock */ diff --git a/drivers/comedi/drivers/cb_pcidda.c b/drivers/comedi/drivers/cb_pcidda.c index 4ed3bcf47973..c52204a6bda4 100644 --- a/drivers/comedi/drivers/cb_pcidda.c +++ b/drivers/comedi/drivers/cb_pcidda.c @@ -28,8 +28,7 @@ #include #include - -#include "8255.h" +#include #define EEPROM_SIZE 128 /* number of entries in eeprom */ /* maximum number of ao channels for supported boards */ diff --git a/drivers/comedi/drivers/cb_pcimdas.c b/drivers/comedi/drivers/cb_pcimdas.c index 64c7d72c7956..7bc0805c69e2 100644 --- a/drivers/comedi/drivers/cb_pcimdas.c +++ b/drivers/comedi/drivers/cb_pcimdas.c @@ -35,10 +35,10 @@ #include #include #include +#include #include "comedi_8254.h" #include "plx9052.h" -#include "8255.h" /* * PCI Bar 1 Register map diff --git a/drivers/comedi/drivers/cb_pcimdda.c b/drivers/comedi/drivers/cb_pcimdda.c index 69d7803b0e58..bf8093a10315 100644 --- a/drivers/comedi/drivers/cb_pcimdda.c +++ b/drivers/comedi/drivers/cb_pcimdda.c @@ -68,8 +68,7 @@ #include #include - -#include "8255.h" +#include /* device ids of the cards we support -- currently only 1 card supported */ #define PCI_ID_PCIM_DDA06_16 0x0053 diff --git a/drivers/comedi/drivers/comedi_8255.c b/drivers/comedi/drivers/comedi_8255.c index 10614603d677..5562b9cd0a17 100644 --- a/drivers/comedi/drivers/comedi_8255.c +++ b/drivers/comedi/drivers/comedi_8255.c @@ -30,8 +30,7 @@ #include #include - -#include "8255.h" +#include struct subdev_8255_private { unsigned long regbase; diff --git a/drivers/comedi/drivers/daqboard2000.c b/drivers/comedi/drivers/daqboard2000.c index 52e4bf16cbda..c0a4e1b06fb3 100644 --- a/drivers/comedi/drivers/daqboard2000.c +++ b/drivers/comedi/drivers/daqboard2000.c @@ -97,8 +97,8 @@ #include #include #include +#include -#include "8255.h" #include "plx9080.h" #define DB2K_FIRMWARE "daqboard2000_firmware.bin" diff --git a/drivers/comedi/drivers/das08.c b/drivers/comedi/drivers/das08.c index c146a168f43b..bab868de2967 100644 --- a/drivers/comedi/drivers/das08.c +++ b/drivers/comedi/drivers/das08.c @@ -11,8 +11,8 @@ #include #include +#include -#include "8255.h" #include "comedi_8254.h" #include "das08.h" diff --git a/drivers/comedi/drivers/das16.c b/drivers/comedi/drivers/das16.c index 362232ad4409..338396736936 100644 --- a/drivers/comedi/drivers/das16.c +++ b/drivers/comedi/drivers/das16.c @@ -64,10 +64,10 @@ #include #include #include +#include #include "comedi_isadma.h" #include "comedi_8254.h" -#include "8255.h" #define DAS16_DMA_SIZE 0xff00 /* size in bytes of allocated dma buffer */ diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c index cc79e318cb2d..ea55024d8c5a 100644 --- a/drivers/comedi/drivers/das16m1.c +++ b/drivers/comedi/drivers/das16m1.c @@ -43,8 +43,8 @@ #include #include #include +#include -#include "8255.h" #include "comedi_8254.h" /* diff --git a/drivers/comedi/drivers/dmm32at.c b/drivers/comedi/drivers/dmm32at.c index 0f2bea88b8a7..fe023c722aa3 100644 --- a/drivers/comedi/drivers/dmm32at.c +++ b/drivers/comedi/drivers/dmm32at.c @@ -30,8 +30,7 @@ #include #include #include - -#include "8255.h" +#include /* Board register addresses */ #define DMM32AT_AI_START_CONV_REG 0x00 diff --git a/drivers/comedi/drivers/ni_atmio.c b/drivers/comedi/drivers/ni_atmio.c index f60a4e459a98..8876a1d24c56 100644 --- a/drivers/comedi/drivers/ni_atmio.c +++ b/drivers/comedi/drivers/ni_atmio.c @@ -75,9 +75,9 @@ #include #include #include +#include #include "ni_stc.h" -#include "8255.h" /* AT specific setup */ static const struct ni_board_struct ni_boards[] = { diff --git a/drivers/comedi/drivers/ni_atmio16d.c b/drivers/comedi/drivers/ni_atmio16d.c index 0bd4f88a2ac8..9fa902529a8e 100644 --- a/drivers/comedi/drivers/ni_atmio16d.c +++ b/drivers/comedi/drivers/ni_atmio16d.c @@ -40,8 +40,7 @@ #include #include #include - -#include "8255.h" +#include /* Configuration and Status Registers */ #define COM_REG_1 0x00 /* wo 16 */ diff --git a/drivers/comedi/drivers/ni_daq_dio24.c b/drivers/comedi/drivers/ni_daq_dio24.c index 84d78f2ee5ac..487733111023 100644 --- a/drivers/comedi/drivers/ni_daq_dio24.c +++ b/drivers/comedi/drivers/ni_daq_dio24.c @@ -24,8 +24,7 @@ #include #include - -#include "8255.h" +#include static int dio24_auto_attach(struct comedi_device *dev, unsigned long context) diff --git a/drivers/comedi/drivers/ni_labpc_common.c b/drivers/comedi/drivers/ni_labpc_common.c index 7c4687226450..4a1269aeb371 100644 --- a/drivers/comedi/drivers/ni_labpc_common.c +++ b/drivers/comedi/drivers/ni_labpc_common.c @@ -13,9 +13,9 @@ #include #include #include +#include #include "comedi_8254.h" -#include "8255.h" #include "ni_labpc.h" #include "ni_labpc_regs.h" #include "ni_labpc_isadma.h" diff --git a/drivers/comedi/drivers/ni_mio_common.c b/drivers/comedi/drivers/ni_mio_common.c index 4f80a4991f95..d39998565808 100644 --- a/drivers/comedi/drivers/ni_mio_common.c +++ b/drivers/comedi/drivers/ni_mio_common.c @@ -43,7 +43,7 @@ #include #include #include -#include "8255.h" +#include #include "mite.h" /* A timeout count */ diff --git a/drivers/comedi/drivers/ni_mio_cs.c b/drivers/comedi/drivers/ni_mio_cs.c index bd967cdb2036..796f0b743772 100644 --- a/drivers/comedi/drivers/ni_mio_cs.c +++ b/drivers/comedi/drivers/ni_mio_cs.c @@ -29,9 +29,9 @@ #include #include #include +#include #include "ni_stc.h" -#include "8255.h" /* * AT specific setup diff --git a/drivers/comedi/drivers/pcl724.c b/drivers/comedi/drivers/pcl724.c index b3f472c93e80..948a0576c9ef 100644 --- a/drivers/comedi/drivers/pcl724.c +++ b/drivers/comedi/drivers/pcl724.c @@ -26,8 +26,7 @@ #include #include - -#include "8255.h" +#include struct pcl724_board { const char *name; diff --git a/drivers/comedi/drivers/pcm3724.c b/drivers/comedi/drivers/pcm3724.c index 93ae6cffed44..e4103f9eeced 100644 --- a/drivers/comedi/drivers/pcm3724.c +++ b/drivers/comedi/drivers/pcm3724.c @@ -25,8 +25,7 @@ #include #include - -#include "8255.h" +#include /* * Register I/O Map diff --git a/include/linux/comedi/comedi_8255.h b/include/linux/comedi/comedi_8255.h new file mode 100644 index 000000000000..b2a5bc6b3a49 --- /dev/null +++ b/include/linux/comedi/comedi_8255.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_8255.h + * Generic 8255 digital I/O subdevice support + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 1998 David A. Schleef + */ + +#ifndef _COMEDI_8255_H +#define _COMEDI_8255_H + +#define I8255_SIZE 0x04 + +#define I8255_DATA_A_REG 0x00 +#define I8255_DATA_B_REG 0x01 +#define I8255_DATA_C_REG 0x02 +#define I8255_CTRL_REG 0x03 +#define I8255_CTRL_C_LO_IO BIT(0) +#define I8255_CTRL_B_IO BIT(1) +#define I8255_CTRL_B_MODE BIT(2) +#define I8255_CTRL_C_HI_IO BIT(3) +#define I8255_CTRL_A_IO BIT(4) +#define I8255_CTRL_A_MODE(x) ((x) << 5) +#define I8255_CTRL_CW BIT(7) + +struct comedi_device; +struct comedi_subdevice; + +int subdev_8255_init(struct comedi_device *dev, struct comedi_subdevice *s, + int (*io)(struct comedi_device *dev, int dir, int port, + int data, unsigned long regbase), + unsigned long regbase); + +int subdev_8255_mm_init(struct comedi_device *dev, struct comedi_subdevice *s, + int (*io)(struct comedi_device *dev, int dir, int port, + int data, unsigned long regbase), + unsigned long regbase); + +unsigned long subdev_8255_regbase(struct comedi_subdevice *s); + +#endif -- cgit v1.2.3 From 44fb7affcfa4e968e9c2ede023ef0e15f06d8209 Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 17 Nov 2021 12:06:02 +0000 Subject: comedi: Move "comedi_8254.h" to Some of the header files in "drivers/comedi/drivers/" are common enough to be useful to out-of-tree comedi driver modules. Using them for out-of-tree module builds is hampered by the headers being outside the "include/" directory so it is desirable to move them. There are about a couple of dozen or so Comedi device drivers that use the "comedi_8254" module to add timers based on the venerable 8254 Programmable Interval Timer chip. The macros and declarations to use that module are in the "comedi_8254.h" header file in the comedi "drivers" directory. Move it into "include/linux/comedi/". Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20211117120604.117740-5-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/comedi/drivers/adl_pci9111.c | 2 +- drivers/comedi/drivers/adl_pci9118.c | 2 +- drivers/comedi/drivers/adv_pci1710.c | 2 +- drivers/comedi/drivers/adv_pci_dio.c | 3 +- drivers/comedi/drivers/aio_aio12_8.c | 3 +- drivers/comedi/drivers/amplc_dio200_common.c | 2 +- drivers/comedi/drivers/amplc_pci224.c | 3 +- drivers/comedi/drivers/amplc_pci230.c | 3 +- drivers/comedi/drivers/cb_das16_cs.c | 3 +- drivers/comedi/drivers/cb_pcidas.c | 2 +- drivers/comedi/drivers/cb_pcimdas.c | 2 +- drivers/comedi/drivers/comedi_8254.c | 3 +- drivers/comedi/drivers/comedi_8254.h | 134 --------------------------- drivers/comedi/drivers/das08.c | 2 +- drivers/comedi/drivers/das16.c | 2 +- drivers/comedi/drivers/das16m1.c | 3 +- drivers/comedi/drivers/das1800.c | 2 +- drivers/comedi/drivers/das6402.c | 3 +- drivers/comedi/drivers/das800.c | 3 +- drivers/comedi/drivers/me4000.c | 2 +- drivers/comedi/drivers/ni_at_a2150.c | 2 +- drivers/comedi/drivers/ni_at_ao.c | 3 +- drivers/comedi/drivers/ni_labpc_common.c | 2 +- drivers/comedi/drivers/pcl711.c | 3 +- drivers/comedi/drivers/pcl812.c | 2 +- drivers/comedi/drivers/pcl816.c | 2 +- drivers/comedi/drivers/pcl818.c | 2 +- drivers/comedi/drivers/rtd520.c | 2 +- include/linux/comedi/comedi_8254.h | 134 +++++++++++++++++++++++++++ 29 files changed, 161 insertions(+), 172 deletions(-) delete mode 100644 drivers/comedi/drivers/comedi_8254.h create mode 100644 include/linux/comedi/comedi_8254.h (limited to 'include/linux') diff --git a/drivers/comedi/drivers/adl_pci9111.c b/drivers/comedi/drivers/adl_pci9111.c index 65454f3ecc91..c50f94272a74 100644 --- a/drivers/comedi/drivers/adl_pci9111.c +++ b/drivers/comedi/drivers/adl_pci9111.c @@ -43,9 +43,9 @@ #include #include #include +#include #include "plx9052.h" -#include "comedi_8254.h" #define PCI9111_FIFO_HALF_SIZE 512 diff --git a/drivers/comedi/drivers/adl_pci9118.c b/drivers/comedi/drivers/adl_pci9118.c index 248cec3d894f..9a816c718303 100644 --- a/drivers/comedi/drivers/adl_pci9118.c +++ b/drivers/comedi/drivers/adl_pci9118.c @@ -79,9 +79,9 @@ #include #include #include +#include #include "amcc_s5933.h" -#include "comedi_8254.h" /* * PCI BAR2 Register map (dev->iobase) diff --git a/drivers/comedi/drivers/adv_pci1710.c b/drivers/comedi/drivers/adv_pci1710.c index 47a800d72e58..4f2639968260 100644 --- a/drivers/comedi/drivers/adv_pci1710.c +++ b/drivers/comedi/drivers/adv_pci1710.c @@ -31,8 +31,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "amcc_s5933.h" /* diff --git a/drivers/comedi/drivers/adv_pci_dio.c b/drivers/comedi/drivers/adv_pci_dio.c index 1ec602f8c6e1..efa3e46b554b 100644 --- a/drivers/comedi/drivers/adv_pci_dio.c +++ b/drivers/comedi/drivers/adv_pci_dio.c @@ -25,8 +25,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * Register offset definitions diff --git a/drivers/comedi/drivers/aio_aio12_8.c b/drivers/comedi/drivers/aio_aio12_8.c index cd797dc0f828..30b8a32204d8 100644 --- a/drivers/comedi/drivers/aio_aio12_8.c +++ b/drivers/comedi/drivers/aio_aio12_8.c @@ -24,8 +24,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/amplc_dio200_common.c b/drivers/comedi/drivers/amplc_dio200_common.c index 26b4049b366c..ff651f2eb86c 100644 --- a/drivers/comedi/drivers/amplc_dio200_common.c +++ b/drivers/comedi/drivers/amplc_dio200_common.c @@ -14,9 +14,9 @@ #include #include #include /* only for register defines */ +#include #include "amplc_dio200.h" -#include "comedi_8254.h" /* 200 series registers */ #define DIO200_IO_SIZE 0x20 diff --git a/drivers/comedi/drivers/amplc_pci224.c b/drivers/comedi/drivers/amplc_pci224.c index 3cf1b7fa565d..5a04e55daeea 100644 --- a/drivers/comedi/drivers/amplc_pci224.c +++ b/drivers/comedi/drivers/amplc_pci224.c @@ -97,8 +97,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * PCI224/234 i/o space 1 (PCIBAR2) registers. diff --git a/drivers/comedi/drivers/amplc_pci230.c b/drivers/comedi/drivers/amplc_pci230.c index 93f7057d5b3f..92ba8b8c0172 100644 --- a/drivers/comedi/drivers/amplc_pci230.c +++ b/drivers/comedi/drivers/amplc_pci230.c @@ -176,8 +176,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * PCI230 PCI configuration register information diff --git a/drivers/comedi/drivers/cb_das16_cs.c b/drivers/comedi/drivers/cb_das16_cs.c index 190d73a7d12c..8e0d2fa5f95d 100644 --- a/drivers/comedi/drivers/cb_das16_cs.c +++ b/drivers/comedi/drivers/cb_das16_cs.c @@ -28,8 +28,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/cb_pcidas.c b/drivers/comedi/drivers/cb_pcidas.c index 75ff02b47959..0c7576b967fc 100644 --- a/drivers/comedi/drivers/cb_pcidas.c +++ b/drivers/comedi/drivers/cb_pcidas.c @@ -56,8 +56,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "amcc_s5933.h" #define AI_BUFFER_SIZE 1024 /* max ai fifo size */ diff --git a/drivers/comedi/drivers/cb_pcimdas.c b/drivers/comedi/drivers/cb_pcimdas.c index 7bc0805c69e2..8bdb00774f11 100644 --- a/drivers/comedi/drivers/cb_pcimdas.c +++ b/drivers/comedi/drivers/cb_pcimdas.c @@ -36,8 +36,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "plx9052.h" /* diff --git a/drivers/comedi/drivers/comedi_8254.c b/drivers/comedi/drivers/comedi_8254.c index fac81567133d..b4185c1b2695 100644 --- a/drivers/comedi/drivers/comedi_8254.c +++ b/drivers/comedi/drivers/comedi_8254.c @@ -117,8 +117,7 @@ #include #include #include - -#include "comedi_8254.h" +#include static unsigned int __i8254_read(struct comedi_8254 *i8254, unsigned int reg) { diff --git a/drivers/comedi/drivers/comedi_8254.h b/drivers/comedi/drivers/comedi_8254.h deleted file mode 100644 index d8264417e53c..000000000000 --- a/drivers/comedi/drivers/comedi_8254.h +++ /dev/null @@ -1,134 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * comedi_8254.h - * Generic 8254 timer/counter support - * Copyright (C) 2014 H Hartley Sweeten - * - * COMEDI - Linux Control and Measurement Device Interface - * Copyright (C) 2000 David A. Schleef - */ - -#ifndef _COMEDI_8254_H -#define _COMEDI_8254_H - -#include - -struct comedi_device; -struct comedi_insn; -struct comedi_subdevice; - -/* - * Common oscillator base values in nanoseconds - */ -#define I8254_OSC_BASE_10MHZ 100 -#define I8254_OSC_BASE_5MHZ 200 -#define I8254_OSC_BASE_4MHZ 250 -#define I8254_OSC_BASE_2MHZ 500 -#define I8254_OSC_BASE_1MHZ 1000 -#define I8254_OSC_BASE_100KHZ 10000 -#define I8254_OSC_BASE_10KHZ 100000 -#define I8254_OSC_BASE_1KHZ 1000000 - -/* - * I/O access size used to read/write registers - */ -#define I8254_IO8 1 -#define I8254_IO16 2 -#define I8254_IO32 4 - -/* - * Register map for generic 8254 timer (I8254_IO8 with 0 regshift) - */ -#define I8254_COUNTER0_REG 0x00 -#define I8254_COUNTER1_REG 0x01 -#define I8254_COUNTER2_REG 0x02 -#define I8254_CTRL_REG 0x03 -#define I8254_CTRL_SEL_CTR(x) ((x) << 6) -#define I8254_CTRL_READBACK(x) (I8254_CTRL_SEL_CTR(3) | BIT(x)) -#define I8254_CTRL_READBACK_COUNT I8254_CTRL_READBACK(4) -#define I8254_CTRL_READBACK_STATUS I8254_CTRL_READBACK(5) -#define I8254_CTRL_READBACK_SEL_CTR(x) (2 << (x)) -#define I8254_CTRL_RW(x) (((x) & 0x3) << 4) -#define I8254_CTRL_LATCH I8254_CTRL_RW(0) -#define I8254_CTRL_LSB_ONLY I8254_CTRL_RW(1) -#define I8254_CTRL_MSB_ONLY I8254_CTRL_RW(2) -#define I8254_CTRL_LSB_MSB I8254_CTRL_RW(3) - -/* counter maps zero to 0x10000 */ -#define I8254_MAX_COUNT 0x10000 - -/** - * struct comedi_8254 - private data used by this module - * @iobase: PIO base address of the registers (in/out) - * @mmio: MMIO base address of the registers (read/write) - * @iosize: I/O size used to access the registers (b/w/l) - * @regshift: register gap shift - * @osc_base: cascaded oscillator speed in ns - * @divisor: divisor for single counter - * @divisor1: divisor loaded into first cascaded counter - * @divisor2: divisor loaded into second cascaded counter - * #next_div: next divisor for single counter - * @next_div1: next divisor to use for first cascaded counter - * @next_div2: next divisor to use for second cascaded counter - * @clock_src; current clock source for each counter (driver specific) - * @gate_src; current gate source for each counter (driver specific) - * @busy: flags used to indicate that a counter is "busy" - * @insn_config: driver specific (*insn_config) callback - */ -struct comedi_8254 { - unsigned long iobase; - void __iomem *mmio; - unsigned int iosize; - unsigned int regshift; - unsigned int osc_base; - unsigned int divisor; - unsigned int divisor1; - unsigned int divisor2; - unsigned int next_div; - unsigned int next_div1; - unsigned int next_div2; - unsigned int clock_src[3]; - unsigned int gate_src[3]; - bool busy[3]; - - int (*insn_config)(struct comedi_device *dev, - struct comedi_subdevice *s, - struct comedi_insn *insn, unsigned int *data); -}; - -unsigned int comedi_8254_status(struct comedi_8254 *i8254, - unsigned int counter); -unsigned int comedi_8254_read(struct comedi_8254 *i8254, unsigned int counter); -void comedi_8254_write(struct comedi_8254 *i8254, - unsigned int counter, unsigned int val); - -int comedi_8254_set_mode(struct comedi_8254 *i8254, - unsigned int counter, unsigned int mode); -int comedi_8254_load(struct comedi_8254 *i8254, - unsigned int counter, unsigned int val, unsigned int mode); - -void comedi_8254_pacer_enable(struct comedi_8254 *i8254, - unsigned int counter1, unsigned int counter2, - bool enable); -void comedi_8254_update_divisors(struct comedi_8254 *i8254); -void comedi_8254_cascade_ns_to_timer(struct comedi_8254 *i8254, - unsigned int *nanosec, unsigned int flags); -void comedi_8254_ns_to_timer(struct comedi_8254 *i8254, - unsigned int *nanosec, unsigned int flags); - -void comedi_8254_set_busy(struct comedi_8254 *i8254, - unsigned int counter, bool busy); - -void comedi_8254_subdevice_init(struct comedi_subdevice *s, - struct comedi_8254 *i8254); - -struct comedi_8254 *comedi_8254_init(unsigned long iobase, - unsigned int osc_base, - unsigned int iosize, - unsigned int regshift); -struct comedi_8254 *comedi_8254_mm_init(void __iomem *mmio, - unsigned int osc_base, - unsigned int iosize, - unsigned int regshift); - -#endif /* _COMEDI_8254_H */ diff --git a/drivers/comedi/drivers/das08.c b/drivers/comedi/drivers/das08.c index bab868de2967..f8ab3af2e391 100644 --- a/drivers/comedi/drivers/das08.c +++ b/drivers/comedi/drivers/das08.c @@ -12,8 +12,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "das08.h" /* diff --git a/drivers/comedi/drivers/das16.c b/drivers/comedi/drivers/das16.c index 338396736936..f6649ffa9670 100644 --- a/drivers/comedi/drivers/das16.c +++ b/drivers/comedi/drivers/das16.c @@ -65,9 +65,9 @@ #include #include #include +#include #include "comedi_isadma.h" -#include "comedi_8254.h" #define DAS16_DMA_SIZE 0xff00 /* size in bytes of allocated dma buffer */ diff --git a/drivers/comedi/drivers/das16m1.c b/drivers/comedi/drivers/das16m1.c index ea55024d8c5a..275effb77746 100644 --- a/drivers/comedi/drivers/das16m1.c +++ b/drivers/comedi/drivers/das16m1.c @@ -44,8 +44,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * Register map (dev->iobase) diff --git a/drivers/comedi/drivers/das1800.c b/drivers/comedi/drivers/das1800.c index 768803742350..a43d3414a122 100644 --- a/drivers/comedi/drivers/das1800.c +++ b/drivers/comedi/drivers/das1800.c @@ -74,9 +74,9 @@ #include #include #include +#include #include "comedi_isadma.h" -#include "comedi_8254.h" /* misc. defines */ #define DAS1800_SIZE 16 /* uses 16 io addresses */ diff --git a/drivers/comedi/drivers/das6402.c b/drivers/comedi/drivers/das6402.c index d411ab7cf37c..1af394591e74 100644 --- a/drivers/comedi/drivers/das6402.c +++ b/drivers/comedi/drivers/das6402.c @@ -25,8 +25,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/das800.c b/drivers/comedi/drivers/das800.c index c95e0fcb94a4..4ca33f46eaa7 100644 --- a/drivers/comedi/drivers/das800.c +++ b/drivers/comedi/drivers/das800.c @@ -47,8 +47,7 @@ #include #include #include - -#include "comedi_8254.h" +#include #define N_CHAN_AI 8 /* number of analog input channels */ diff --git a/drivers/comedi/drivers/me4000.c b/drivers/comedi/drivers/me4000.c index c5dc8199771f..9aea02b86ed9 100644 --- a/drivers/comedi/drivers/me4000.c +++ b/drivers/comedi/drivers/me4000.c @@ -33,8 +33,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "plx9052.h" #define ME4000_FIRMWARE "me4000_firmware.bin" diff --git a/drivers/comedi/drivers/ni_at_a2150.c b/drivers/comedi/drivers/ni_at_a2150.c index ce5de58c499f..9942d770add8 100644 --- a/drivers/comedi/drivers/ni_at_a2150.c +++ b/drivers/comedi/drivers/ni_at_a2150.c @@ -40,9 +40,9 @@ #include #include #include +#include #include "comedi_isadma.h" -#include "comedi_8254.h" #define A2150_DMA_BUFFER_SIZE 0xff00 /* size in bytes of dma buffer */ diff --git a/drivers/comedi/drivers/ni_at_ao.c b/drivers/comedi/drivers/ni_at_ao.c index a06dfb9da329..9f3147b72aa8 100644 --- a/drivers/comedi/drivers/ni_at_ao.c +++ b/drivers/comedi/drivers/ni_at_ao.c @@ -26,8 +26,7 @@ #include #include - -#include "comedi_8254.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/ni_labpc_common.c b/drivers/comedi/drivers/ni_labpc_common.c index 4a1269aeb371..763249653228 100644 --- a/drivers/comedi/drivers/ni_labpc_common.c +++ b/drivers/comedi/drivers/ni_labpc_common.c @@ -14,8 +14,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "ni_labpc.h" #include "ni_labpc_regs.h" #include "ni_labpc_isadma.h" diff --git a/drivers/comedi/drivers/pcl711.c b/drivers/comedi/drivers/pcl711.c index f1c383bd9d87..05172c553c8a 100644 --- a/drivers/comedi/drivers/pcl711.c +++ b/drivers/comedi/drivers/pcl711.c @@ -30,8 +30,7 @@ #include #include #include - -#include "comedi_8254.h" +#include /* * I/O port register map diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c index f00976ddfc2a..790f54476a91 100644 --- a/drivers/comedi/drivers/pcl812.c +++ b/drivers/comedi/drivers/pcl812.c @@ -115,9 +115,9 @@ #include #include #include +#include #include "comedi_isadma.h" -#include "comedi_8254.h" /* * Register I/O map diff --git a/drivers/comedi/drivers/pcl816.c b/drivers/comedi/drivers/pcl816.c index c5acdc8913f8..77b30246d966 100644 --- a/drivers/comedi/drivers/pcl816.c +++ b/drivers/comedi/drivers/pcl816.c @@ -36,9 +36,9 @@ #include #include #include +#include #include "comedi_isadma.h" -#include "comedi_8254.h" /* * Register I/O map diff --git a/drivers/comedi/drivers/pcl818.c b/drivers/comedi/drivers/pcl818.c index 20fcd6d588f8..e5b7793cce05 100644 --- a/drivers/comedi/drivers/pcl818.c +++ b/drivers/comedi/drivers/pcl818.c @@ -98,9 +98,9 @@ #include #include #include +#include #include "comedi_isadma.h" -#include "comedi_8254.h" /* * Register I/O map diff --git a/drivers/comedi/drivers/rtd520.c b/drivers/comedi/drivers/rtd520.c index ee5bca2b1c09..7e0ec1a2a2ca 100644 --- a/drivers/comedi/drivers/rtd520.c +++ b/drivers/comedi/drivers/rtd520.c @@ -86,8 +86,8 @@ #include #include #include +#include -#include "comedi_8254.h" #include "plx9080.h" /* diff --git a/include/linux/comedi/comedi_8254.h b/include/linux/comedi/comedi_8254.h new file mode 100644 index 000000000000..d8264417e53c --- /dev/null +++ b/include/linux/comedi/comedi_8254.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * comedi_8254.h + * Generic 8254 timer/counter support + * Copyright (C) 2014 H Hartley Sweeten + * + * COMEDI - Linux Control and Measurement Device Interface + * Copyright (C) 2000 David A. Schleef + */ + +#ifndef _COMEDI_8254_H +#define _COMEDI_8254_H + +#include + +struct comedi_device; +struct comedi_insn; +struct comedi_subdevice; + +/* + * Common oscillator base values in nanoseconds + */ +#define I8254_OSC_BASE_10MHZ 100 +#define I8254_OSC_BASE_5MHZ 200 +#define I8254_OSC_BASE_4MHZ 250 +#define I8254_OSC_BASE_2MHZ 500 +#define I8254_OSC_BASE_1MHZ 1000 +#define I8254_OSC_BASE_100KHZ 10000 +#define I8254_OSC_BASE_10KHZ 100000 +#define I8254_OSC_BASE_1KHZ 1000000 + +/* + * I/O access size used to read/write registers + */ +#define I8254_IO8 1 +#define I8254_IO16 2 +#define I8254_IO32 4 + +/* + * Register map for generic 8254 timer (I8254_IO8 with 0 regshift) + */ +#define I8254_COUNTER0_REG 0x00 +#define I8254_COUNTER1_REG 0x01 +#define I8254_COUNTER2_REG 0x02 +#define I8254_CTRL_REG 0x03 +#define I8254_CTRL_SEL_CTR(x) ((x) << 6) +#define I8254_CTRL_READBACK(x) (I8254_CTRL_SEL_CTR(3) | BIT(x)) +#define I8254_CTRL_READBACK_COUNT I8254_CTRL_READBACK(4) +#define I8254_CTRL_READBACK_STATUS I8254_CTRL_READBACK(5) +#define I8254_CTRL_READBACK_SEL_CTR(x) (2 << (x)) +#define I8254_CTRL_RW(x) (((x) & 0x3) << 4) +#define I8254_CTRL_LATCH I8254_CTRL_RW(0) +#define I8254_CTRL_LSB_ONLY I8254_CTRL_RW(1) +#define I8254_CTRL_MSB_ONLY I8254_CTRL_RW(2) +#define I8254_CTRL_LSB_MSB I8254_CTRL_RW(3) + +/* counter maps zero to 0x10000 */ +#define I8254_MAX_COUNT 0x10000 + +/** + * struct comedi_8254 - private data used by this module + * @iobase: PIO base address of the registers (in/out) + * @mmio: MMIO base address of the registers (read/write) + * @iosize: I/O size used to access the registers (b/w/l) + * @regshift: register gap shift + * @osc_base: cascaded oscillator speed in ns + * @divisor: divisor for single counter + * @divisor1: divisor loaded into first cascaded counter + * @divisor2: divisor loaded into second cascaded counter + * #next_div: next divisor for single counter + * @next_div1: next divisor to use for first cascaded counter + * @next_div2: next divisor to use for second cascaded counter + * @clock_src; current clock source for each counter (driver specific) + * @gate_src; current gate source for each counter (driver specific) + * @busy: flags used to indicate that a counter is "busy" + * @insn_config: driver specific (*insn_config) callback + */ +struct comedi_8254 { + unsigned long iobase; + void __iomem *mmio; + unsigned int iosize; + unsigned int regshift; + unsigned int osc_base; + unsigned int divisor; + unsigned int divisor1; + unsigned int divisor2; + unsigned int next_div; + unsigned int next_div1; + unsigned int next_div2; + unsigned int clock_src[3]; + unsigned int gate_src[3]; + bool busy[3]; + + int (*insn_config)(struct comedi_device *dev, + struct comedi_subdevice *s, + struct comedi_insn *insn, unsigned int *data); +}; + +unsigned int comedi_8254_status(struct comedi_8254 *i8254, + unsigned int counter); +unsigned int comedi_8254_read(struct comedi_8254 *i8254, unsigned int counter); +void comedi_8254_write(struct comedi_8254 *i8254, + unsigned int counter, unsigned int val); + +int comedi_8254_set_mode(struct comedi_8254 *i8254, + unsigned int counter, unsigned int mode); +int comedi_8254_load(struct comedi_8254 *i8254, + unsigned int counter, unsigned int val, unsigned int mode); + +void comedi_8254_pacer_enable(struct comedi_8254 *i8254, + unsigned int counter1, unsigned int counter2, + bool enable); +void comedi_8254_update_divisors(struct comedi_8254 *i8254); +void comedi_8254_cascade_ns_to_timer(struct comedi_8254 *i8254, + unsigned int *nanosec, unsigned int flags); +void comedi_8254_ns_to_timer(struct comedi_8254 *i8254, + unsigned int *nanosec, unsigned int flags); + +void comedi_8254_set_busy(struct comedi_8254 *i8254, + unsigned int counter, bool busy); + +void comedi_8254_subdevice_init(struct comedi_subdevice *s, + struct comedi_8254 *i8254); + +struct comedi_8254 *comedi_8254_init(unsigned long iobase, + unsigned int osc_base, + unsigned int iosize, + unsigned int regshift); +struct comedi_8254 *comedi_8254_mm_init(void __iomem *mmio, + unsigned int osc_base, + unsigned int iosize, + unsigned int regshift); + +#endif /* _COMEDI_8254_H */ -- cgit v1.2.3 From fe7a4f5b9548456246ffda143bab59922acda9fd Mon Sep 17 00:00:00 2001 From: Ian Abbott Date: Wed, 17 Nov 2021 12:06:03 +0000 Subject: comedi: Move "comedi_isadma.h" to Some of the header files in "drivers/comedi/drivers/" are common enough to be useful to out-of-tree comedi driver modules. Using them for out-of-tree module builds is hampered by the headers being outside the "include/" directory so it is desirable to move them. There are about a half a dozen or so Comedi device drivers that use the "comedi_isadma" module to add ISA DMA support. The macros and declarations to use that module are in the "comedi_isadma.h" header file in the comedi "drivers" directory. Move it into "include/linux/comedi/". Signed-off-by: Ian Abbott Link: https://lore.kernel.org/r/20211117120604.117740-6-abbotti@mev.co.uk Signed-off-by: Greg Kroah-Hartman --- drivers/comedi/drivers/comedi_isadma.c | 3 +- drivers/comedi/drivers/comedi_isadma.h | 114 ------------------------------- drivers/comedi/drivers/das16.c | 3 +- drivers/comedi/drivers/das1800.c | 3 +- drivers/comedi/drivers/dt282x.c | 3 +- drivers/comedi/drivers/ni_at_a2150.c | 3 +- drivers/comedi/drivers/ni_labpc_isadma.c | 2 +- drivers/comedi/drivers/pcl812.c | 3 +- drivers/comedi/drivers/pcl816.c | 3 +- drivers/comedi/drivers/pcl818.c | 3 +- include/linux/comedi/comedi_isadma.h | 114 +++++++++++++++++++++++++++++++ 11 files changed, 123 insertions(+), 131 deletions(-) delete mode 100644 drivers/comedi/drivers/comedi_isadma.h create mode 100644 include/linux/comedi/comedi_isadma.h (limited to 'include/linux') diff --git a/drivers/comedi/drivers/comedi_isadma.c b/drivers/comedi/drivers/comedi_isadma.c index 63457bd4ff78..700982464c53 100644 --- a/drivers/comedi/drivers/comedi_isadma.c +++ b/drivers/comedi/drivers/comedi_isadma.c @@ -10,8 +10,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include /** * comedi_isadma_program - program and enable an ISA DMA transfer diff --git a/drivers/comedi/drivers/comedi_isadma.h b/drivers/comedi/drivers/comedi_isadma.h deleted file mode 100644 index 9d2b12db7e6e..000000000000 --- a/drivers/comedi/drivers/comedi_isadma.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0+ */ -/* - * COMEDI ISA DMA support functions - * Copyright (c) 2014 H Hartley Sweeten - */ - -#ifndef _COMEDI_ISADMA_H -#define _COMEDI_ISADMA_H - -#include - -struct comedi_device; -struct device; - -/* - * These are used to avoid issues when and the DMA_MODE_ - * defines are not available. - */ -#define COMEDI_ISADMA_READ 0 -#define COMEDI_ISADMA_WRITE 1 - -/** - * struct comedi_isadma_desc - cookie for ISA DMA - * @virt_addr: virtual address of buffer - * @hw_addr: hardware (bus) address of buffer - * @chan: DMA channel - * @maxsize: allocated size of buffer (in bytes) - * @size: transfer size (in bytes) - * @mode: DMA_MODE_READ or DMA_MODE_WRITE - */ -struct comedi_isadma_desc { - void *virt_addr; - dma_addr_t hw_addr; - unsigned int chan; - unsigned int maxsize; - unsigned int size; - char mode; -}; - -/** - * struct comedi_isadma - ISA DMA data - * @dev: device to allocate non-coherent memory for - * @desc: cookie for each DMA buffer - * @n_desc: the number of cookies - * @cur_dma: the current cookie in use - * @chan: the first DMA channel requested - * @chan2: the second DMA channel requested - */ -struct comedi_isadma { - struct device *dev; - struct comedi_isadma_desc *desc; - int n_desc; - int cur_dma; - unsigned int chan; - unsigned int chan2; -}; - -#if IS_ENABLED(CONFIG_ISA_DMA_API) - -void comedi_isadma_program(struct comedi_isadma_desc *desc); -unsigned int comedi_isadma_disable(unsigned int dma_chan); -unsigned int comedi_isadma_disable_on_sample(unsigned int dma_chan, - unsigned int size); -unsigned int comedi_isadma_poll(struct comedi_isadma *dma); -void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, char dma_dir); - -struct comedi_isadma *comedi_isadma_alloc(struct comedi_device *dev, - int n_desc, unsigned int dma_chan1, - unsigned int dma_chan2, - unsigned int maxsize, char dma_dir); -void comedi_isadma_free(struct comedi_isadma *dma); - -#else /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ - -static inline void comedi_isadma_program(struct comedi_isadma_desc *desc) -{ -} - -static inline unsigned int comedi_isadma_disable(unsigned int dma_chan) -{ - return 0; -} - -static inline unsigned int -comedi_isadma_disable_on_sample(unsigned int dma_chan, unsigned int size) -{ - return 0; -} - -static inline unsigned int comedi_isadma_poll(struct comedi_isadma *dma) -{ - return 0; -} - -static inline void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, - char dma_dir) -{ -} - -static inline struct comedi_isadma * -comedi_isadma_alloc(struct comedi_device *dev, int n_desc, - unsigned int dma_chan1, unsigned int dma_chan2, - unsigned int maxsize, char dma_dir) -{ - return NULL; -} - -static inline void comedi_isadma_free(struct comedi_isadma *dma) -{ -} - -#endif /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ - -#endif /* #ifndef _COMEDI_ISADMA_H */ diff --git a/drivers/comedi/drivers/das16.c b/drivers/comedi/drivers/das16.c index f6649ffa9670..937a69ce0977 100644 --- a/drivers/comedi/drivers/das16.c +++ b/drivers/comedi/drivers/das16.c @@ -66,8 +66,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include #define DAS16_DMA_SIZE 0xff00 /* size in bytes of allocated dma buffer */ diff --git a/drivers/comedi/drivers/das1800.c b/drivers/comedi/drivers/das1800.c index a43d3414a122..f09608c0f4ff 100644 --- a/drivers/comedi/drivers/das1800.c +++ b/drivers/comedi/drivers/das1800.c @@ -75,8 +75,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include /* misc. defines */ #define DAS1800_SIZE 16 /* uses 16 io addresses */ diff --git a/drivers/comedi/drivers/dt282x.c b/drivers/comedi/drivers/dt282x.c index 078f8fba7183..4ae80e6c7266 100644 --- a/drivers/comedi/drivers/dt282x.c +++ b/drivers/comedi/drivers/dt282x.c @@ -52,8 +52,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include /* * Register map diff --git a/drivers/comedi/drivers/ni_at_a2150.c b/drivers/comedi/drivers/ni_at_a2150.c index 9942d770add8..df8d219e6723 100644 --- a/drivers/comedi/drivers/ni_at_a2150.c +++ b/drivers/comedi/drivers/ni_at_a2150.c @@ -41,8 +41,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include #define A2150_DMA_BUFFER_SIZE 0xff00 /* size in bytes of dma buffer */ diff --git a/drivers/comedi/drivers/ni_labpc_isadma.c b/drivers/comedi/drivers/ni_labpc_isadma.c index dd37ec0d9b15..0652ca8345b6 100644 --- a/drivers/comedi/drivers/ni_labpc_isadma.c +++ b/drivers/comedi/drivers/ni_labpc_isadma.c @@ -11,8 +11,8 @@ #include #include #include +#include -#include "comedi_isadma.h" #include "ni_labpc.h" #include "ni_labpc_regs.h" #include "ni_labpc_isadma.h" diff --git a/drivers/comedi/drivers/pcl812.c b/drivers/comedi/drivers/pcl812.c index 790f54476a91..70dbc129fcf5 100644 --- a/drivers/comedi/drivers/pcl812.c +++ b/drivers/comedi/drivers/pcl812.c @@ -116,8 +116,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/pcl816.c b/drivers/comedi/drivers/pcl816.c index 77b30246d966..a5e5320be648 100644 --- a/drivers/comedi/drivers/pcl816.c +++ b/drivers/comedi/drivers/pcl816.c @@ -37,8 +37,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include /* * Register I/O map diff --git a/drivers/comedi/drivers/pcl818.c b/drivers/comedi/drivers/pcl818.c index e5b7793cce05..29e503de8267 100644 --- a/drivers/comedi/drivers/pcl818.c +++ b/drivers/comedi/drivers/pcl818.c @@ -99,8 +99,7 @@ #include #include #include - -#include "comedi_isadma.h" +#include /* * Register I/O map diff --git a/include/linux/comedi/comedi_isadma.h b/include/linux/comedi/comedi_isadma.h new file mode 100644 index 000000000000..9d2b12db7e6e --- /dev/null +++ b/include/linux/comedi/comedi_isadma.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * COMEDI ISA DMA support functions + * Copyright (c) 2014 H Hartley Sweeten + */ + +#ifndef _COMEDI_ISADMA_H +#define _COMEDI_ISADMA_H + +#include + +struct comedi_device; +struct device; + +/* + * These are used to avoid issues when and the DMA_MODE_ + * defines are not available. + */ +#define COMEDI_ISADMA_READ 0 +#define COMEDI_ISADMA_WRITE 1 + +/** + * struct comedi_isadma_desc - cookie for ISA DMA + * @virt_addr: virtual address of buffer + * @hw_addr: hardware (bus) address of buffer + * @chan: DMA channel + * @maxsize: allocated size of buffer (in bytes) + * @size: transfer size (in bytes) + * @mode: DMA_MODE_READ or DMA_MODE_WRITE + */ +struct comedi_isadma_desc { + void *virt_addr; + dma_addr_t hw_addr; + unsigned int chan; + unsigned int maxsize; + unsigned int size; + char mode; +}; + +/** + * struct comedi_isadma - ISA DMA data + * @dev: device to allocate non-coherent memory for + * @desc: cookie for each DMA buffer + * @n_desc: the number of cookies + * @cur_dma: the current cookie in use + * @chan: the first DMA channel requested + * @chan2: the second DMA channel requested + */ +struct comedi_isadma { + struct device *dev; + struct comedi_isadma_desc *desc; + int n_desc; + int cur_dma; + unsigned int chan; + unsigned int chan2; +}; + +#if IS_ENABLED(CONFIG_ISA_DMA_API) + +void comedi_isadma_program(struct comedi_isadma_desc *desc); +unsigned int comedi_isadma_disable(unsigned int dma_chan); +unsigned int comedi_isadma_disable_on_sample(unsigned int dma_chan, + unsigned int size); +unsigned int comedi_isadma_poll(struct comedi_isadma *dma); +void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, char dma_dir); + +struct comedi_isadma *comedi_isadma_alloc(struct comedi_device *dev, + int n_desc, unsigned int dma_chan1, + unsigned int dma_chan2, + unsigned int maxsize, char dma_dir); +void comedi_isadma_free(struct comedi_isadma *dma); + +#else /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ + +static inline void comedi_isadma_program(struct comedi_isadma_desc *desc) +{ +} + +static inline unsigned int comedi_isadma_disable(unsigned int dma_chan) +{ + return 0; +} + +static inline unsigned int +comedi_isadma_disable_on_sample(unsigned int dma_chan, unsigned int size) +{ + return 0; +} + +static inline unsigned int comedi_isadma_poll(struct comedi_isadma *dma) +{ + return 0; +} + +static inline void comedi_isadma_set_mode(struct comedi_isadma_desc *desc, + char dma_dir) +{ +} + +static inline struct comedi_isadma * +comedi_isadma_alloc(struct comedi_device *dev, int n_desc, + unsigned int dma_chan1, unsigned int dma_chan2, + unsigned int maxsize, char dma_dir) +{ + return NULL; +} + +static inline void comedi_isadma_free(struct comedi_isadma *dma) +{ +} + +#endif /* !IS_ENABLED(CONFIG_ISA_DMA_API) */ + +#endif /* #ifndef _COMEDI_ISADMA_H */ -- cgit v1.2.3 From 2cca3465147d650be3de04927a99784b30251ade Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Fri, 12 Nov 2021 08:28:09 +0200 Subject: mei: bus: add client dma interface Expose the client dma mapping via mei client bus interface. The client dma has to be mapped before the device is enabled, therefore we need to create device linking already during mapping and we need to unmap after the client is disable hence we need to postpone the unlink and flush till unmapping or when destroying the device. Signed-off-by: Alexander Usyskin Co-developed-by: Tomas Winkler Signed-off-by: Tomas Winkler Signed-off-by: Emmanuel Grumbach Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210420172755.12178-1-emmanuel.grumbach@intel.com Signed-off-by: Kalle Valo Link: https://lore.kernel.org/r/20211112062814.7502-1-emmanuel.grumbach@intel.com --- drivers/misc/mei/bus.c | 67 +++++++++++++++++++++++++++++++++++++++++++--- drivers/misc/mei/client.c | 3 +++ drivers/misc/mei/hw.h | 5 ++++ include/linux/mei_cl_bus.h | 3 +++ 4 files changed, 75 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 44bac4ad687c..46aa3554e97b 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -643,6 +643,64 @@ static void mei_cl_bus_vtag_free(struct mei_cl_device *cldev) kfree(cl_vtag); } +void *mei_cldev_dma_map(struct mei_cl_device *cldev, u8 buffer_id, size_t size) +{ + struct mei_device *bus; + struct mei_cl *cl; + int ret; + + if (!cldev || !buffer_id || !size) + return ERR_PTR(-EINVAL); + + if (!IS_ALIGNED(size, MEI_FW_PAGE_SIZE)) { + dev_err(&cldev->dev, "Map size should be aligned to %lu\n", + MEI_FW_PAGE_SIZE); + return ERR_PTR(-EINVAL); + } + + cl = cldev->cl; + bus = cldev->bus; + + mutex_lock(&bus->device_lock); + if (cl->state == MEI_FILE_UNINITIALIZED) { + ret = mei_cl_link(cl); + if (ret) + goto out; + /* update pointers */ + cl->cldev = cldev; + } + + ret = mei_cl_dma_alloc_and_map(cl, NULL, buffer_id, size); +out: + mutex_unlock(&bus->device_lock); + if (ret) + return ERR_PTR(ret); + return cl->dma.vaddr; +} +EXPORT_SYMBOL_GPL(mei_cldev_dma_map); + +int mei_cldev_dma_unmap(struct mei_cl_device *cldev) +{ + struct mei_device *bus; + struct mei_cl *cl; + int ret; + + if (!cldev) + return -EINVAL; + + cl = cldev->cl; + bus = cldev->bus; + + mutex_lock(&bus->device_lock); + ret = mei_cl_dma_unmap(cl, NULL); + + mei_cl_flush_queues(cl, NULL); + mei_cl_unlink(cl); + mutex_unlock(&bus->device_lock); + return ret; +} +EXPORT_SYMBOL_GPL(mei_cldev_dma_unmap); + /** * mei_cldev_enable - enable me client device * create connection with me client @@ -753,9 +811,11 @@ int mei_cldev_disable(struct mei_cl_device *cldev) dev_err(bus->dev, "Could not disconnect from the ME client\n"); out: - /* Flush queues and remove any pending read */ - mei_cl_flush_queues(cl, NULL); - mei_cl_unlink(cl); + /* Flush queues and remove any pending read unless we have mapped DMA */ + if (!cl->dma_mapped) { + mei_cl_flush_queues(cl, NULL); + mei_cl_unlink(cl); + } mutex_unlock(&bus->device_lock); return err; @@ -1052,6 +1112,7 @@ static void mei_cl_bus_dev_release(struct device *dev) if (!cldev) return; + mei_cl_flush_queues(cldev->cl, NULL); mei_me_cl_put(cldev->me_cl); mei_dev_bus_put(cldev->bus); mei_cl_unlink(cldev->cl); diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 96f4e59c32a5..0e90591235a6 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -700,6 +700,9 @@ int mei_cl_unlink(struct mei_cl *cl) cl_dbg(dev, cl, "unlink client"); + if (cl->state == MEI_FILE_UNINITIALIZED) + return 0; + if (dev->open_handle_count > 0) dev->open_handle_count--; diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h index dfd60c916da0..b46077b17114 100644 --- a/drivers/misc/mei/hw.h +++ b/drivers/misc/mei/hw.h @@ -22,6 +22,11 @@ #define MEI_D0I3_TIMEOUT 5 /* D0i3 set/unset max response time */ #define MEI_HBM_TIMEOUT 1 /* 1 second */ +/* + * FW page size for DMA allocations + */ +#define MEI_FW_PAGE_SIZE 4096UL + /* * MEI Version */ diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index c6786c12b207..df1fab44ea5c 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -117,4 +117,7 @@ int mei_cldev_enable(struct mei_cl_device *cldev); int mei_cldev_disable(struct mei_cl_device *cldev); bool mei_cldev_enabled(const struct mei_cl_device *cldev); +void *mei_cldev_dma_map(struct mei_cl_device *cldev, u8 buffer_id, size_t size); +int mei_cldev_dma_unmap(struct mei_cl_device *cldev); + #endif /* _LINUX_MEI_CL_BUS_H */ -- cgit v1.2.3 From ec15baec3272bbec576f2ce7ce47765a8e9b7b1c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 26 Nov 2021 19:28:43 +0200 Subject: net: ptp: add a definition for the UDP port for IEEE 1588 general messages As opposed to event messages (Sync, PdelayReq etc) which require timestamping, general messages (Announce, FollowUp etc) do not. In PTP they are part of different streams of data. IEEE 1588-2008 Annex D.2 "UDP port numbers" states that the UDP destination port assigned by IANA is 319 for event messages, and 320 for general messages. Yet the kernel seems to be missing the definition for general messages. This patch adds it. Signed-off-by: Vladimir Oltean Acked-by: Richard Cochran Signed-off-by: Jakub Kicinski --- include/linux/ptp_classify.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h index ae04968a3a47..9afd34a2d36c 100644 --- a/include/linux/ptp_classify.h +++ b/include/linux/ptp_classify.h @@ -37,6 +37,7 @@ #define PTP_MSGTYPE_PDELAY_RESP 0x3 #define PTP_EV_PORT 319 +#define PTP_GEN_PORT 320 #define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */ #define OFF_PTP_SOURCE_UUID 22 /* PTPv1 only */ -- cgit v1.2.3 From a6914afcdf0e3fb853fce0e0c04710be7427b62f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 10 Nov 2021 12:31:28 +0200 Subject: kobject: Replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211110103128.59888-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/kobject.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kobject.h b/include/linux/kobject.h index efd56f990a46..c740062b4b1a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -19,10 +19,10 @@ #include #include #include +#include #include #include #include -#include #include #include #include -- cgit v1.2.3 From 6a2d2ddf2c345e0149bfbffdddc4768a9ab0a741 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Fri, 12 Nov 2021 14:32:27 +0100 Subject: drm: Move nomodeset kernel parameter to the DRM subsystem The "nomodeset" kernel cmdline parameter is handled by the vgacon driver but the exported vgacon_text_force() symbol is only used by DRM drivers. It makes much more sense for the parameter logic to be in the subsystem of the drivers that are making use of it. Let's move the vgacon_text_force() function and related logic to the DRM subsystem. While doing that, rename it to drm_firmware_drivers_only() and make it return true if "nomodeset" was used and false otherwise. This is a better description of the condition that the drivers are testing for. Suggested-by: Daniel Vetter Signed-off-by: Javier Martinez Canillas Acked-by: Thomas Zimmermann Acked-by: Jani Nikula Acked-by: Pekka Paalanen Acked-by: Greg Kroah-Hartman Link: https://patchwork.freedesktop.org/patch/msgid/20211112133230.1595307-4-javierm@redhat.com --- drivers/gpu/drm/Makefile | 2 ++ drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 3 +-- drivers/gpu/drm/ast/ast_drv.c | 3 +-- drivers/gpu/drm/i915/i915_module.c | 4 ++-- drivers/gpu/drm/mgag200/mgag200_drv.c | 3 +-- drivers/gpu/drm/nouveau/nouveau_drm.c | 4 ++-- drivers/gpu/drm/qxl/qxl_drv.c | 3 +-- drivers/gpu/drm/radeon/radeon_drv.c | 3 +-- drivers/gpu/drm/tiny/bochs.c | 3 +-- drivers/gpu/drm/tiny/cirrus.c | 4 ++-- drivers/gpu/drm/vboxvideo/vbox_drv.c | 3 +-- drivers/gpu/drm/virtio/virtgpu_drv.c | 3 +-- drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 3 +-- drivers/video/console/vgacon.c | 21 --------------------- gpu/drm/drm_nomodeset.c | 26 ++++++++++++++++++++++++++ include/drm/drm_drv.h | 5 +++++ include/linux/console.h | 6 ------ 17 files changed, 48 insertions(+), 51 deletions(-) create mode 100644 gpu/drm/drm_nomodeset.c (limited to 'include/linux') diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 1c41156deb5f..c74810c285af 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -33,6 +33,8 @@ drm-$(CONFIG_DRM_PRIVACY_SCREEN) += drm_privacy_screen.o drm_privacy_screen_x86. obj-$(CONFIG_DRM_DP_AUX_BUS) += drm_dp_aux_bus.o +obj-$(CONFIG_VGA_CONSOLE) += drm_nomodeset.o + drm_cma_helper-y := drm_gem_cma_helper.o obj-$(CONFIG_DRM_GEM_CMA_HELPER) += drm_cma_helper.o diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index e8c23e37c83c..438468b82eb6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -31,7 +31,6 @@ #include "amdgpu_drv.h" #include -#include #include #include #include @@ -2516,7 +2515,7 @@ static int __init amdgpu_init(void) { int r; - if (vgacon_text_force()) + if (drm_firmware_drivers_only()) return -EINVAL; r = amdgpu_sync_init(); diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c index 86d5cd7b6318..6d8613f6fe1c 100644 --- a/drivers/gpu/drm/ast/ast_drv.c +++ b/drivers/gpu/drm/ast/ast_drv.c @@ -26,7 +26,6 @@ * Authors: Dave Airlie */ -#include #include #include @@ -233,7 +232,7 @@ static struct pci_driver ast_pci_driver = { static int __init ast_init(void) { - if (vgacon_text_force() && ast_modeset == -1) + if (drm_firmware_drivers_only() && ast_modeset == -1) return -EINVAL; if (ast_modeset == 0) diff --git a/drivers/gpu/drm/i915/i915_module.c b/drivers/gpu/drm/i915/i915_module.c index ab2295dd4500..1df66bf276ce 100644 --- a/drivers/gpu/drm/i915/i915_module.c +++ b/drivers/gpu/drm/i915/i915_module.c @@ -4,7 +4,7 @@ * Copyright © 2021 Intel Corporation */ -#include +#include #include "gem/i915_gem_context.h" #include "gem/i915_gem_object.h" @@ -31,7 +31,7 @@ static int i915_check_nomodeset(void) if (i915_modparams.modeset == 0) use_kms = false; - if (vgacon_text_force() && i915_modparams.modeset == -1) + if (drm_firmware_drivers_only() && i915_modparams.modeset == -1) use_kms = false; if (!use_kms) { diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index 6b9243713b3c..740108a006ba 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -6,7 +6,6 @@ * Dave Airlie */ -#include #include #include #include @@ -378,7 +377,7 @@ static struct pci_driver mgag200_pci_driver = { static int __init mgag200_init(void) { - if (vgacon_text_force() && mgag200_modeset == -1) + if (drm_firmware_drivers_only() && mgag200_modeset == -1) return -EINVAL; if (mgag200_modeset == 0) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index e7efd9ede8e4..561309d447e0 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -22,7 +22,6 @@ * Authors: Ben Skeggs */ -#include #include #include #include @@ -32,6 +31,7 @@ #include #include +#include #include #include #include @@ -1358,7 +1358,7 @@ nouveau_drm_init(void) nouveau_display_options(); if (nouveau_modeset == -1) { - if (vgacon_text_force()) + if (drm_firmware_drivers_only()) nouveau_modeset = 0; } diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c index fc47b0deb021..e4b16421500b 100644 --- a/drivers/gpu/drm/qxl/qxl_drv.c +++ b/drivers/gpu/drm/qxl/qxl_drv.c @@ -29,7 +29,6 @@ #include "qxl_drv.h" -#include #include #include #include @@ -295,7 +294,7 @@ static struct drm_driver qxl_driver = { static int __init qxl_init(void) { - if (vgacon_text_force() && qxl_modeset == -1) + if (drm_firmware_drivers_only() && qxl_modeset == -1) return -EINVAL; if (qxl_modeset == 0) diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index 380adc61e71c..956c72b5aa33 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -31,7 +31,6 @@ #include -#include #include #include #include @@ -637,7 +636,7 @@ static struct pci_driver radeon_kms_pci_driver = { static int __init radeon_module_init(void) { - if (vgacon_text_force() && radeon_modeset == -1) + if (drm_firmware_drivers_only() && radeon_modeset == -1) radeon_modeset = 0; if (radeon_modeset == 0) diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c index 2ce3bd903b70..fc26a1ce11ee 100644 --- a/drivers/gpu/drm/tiny/bochs.c +++ b/drivers/gpu/drm/tiny/bochs.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -#include #include #include @@ -719,7 +718,7 @@ static struct pci_driver bochs_pci_driver = { static int __init bochs_init(void) { - if (vgacon_text_force() && bochs_modeset == -1) + if (drm_firmware_drivers_only() && bochs_modeset == -1) return -EINVAL; if (bochs_modeset == 0) diff --git a/drivers/gpu/drm/tiny/cirrus.c b/drivers/gpu/drm/tiny/cirrus.c index 9327001d35dd..c95d9ff7d600 100644 --- a/drivers/gpu/drm/tiny/cirrus.c +++ b/drivers/gpu/drm/tiny/cirrus.c @@ -16,7 +16,6 @@ * Copyright 1999-2001 Jeff Garzik */ -#include #include #include #include @@ -636,8 +635,9 @@ static struct pci_driver cirrus_pci_driver = { static int __init cirrus_init(void) { - if (vgacon_text_force()) + if (drm_firmware_drivers_only()) return -EINVAL; + return pci_register_driver(&cirrus_pci_driver); } diff --git a/drivers/gpu/drm/vboxvideo/vbox_drv.c b/drivers/gpu/drm/vboxvideo/vbox_drv.c index fd7abb029c65..f35d9e44c6b7 100644 --- a/drivers/gpu/drm/vboxvideo/vbox_drv.c +++ b/drivers/gpu/drm/vboxvideo/vbox_drv.c @@ -7,7 +7,6 @@ * Michael Thayer */ -#include #include #include #include @@ -193,7 +192,7 @@ static const struct drm_driver driver = { static int __init vbox_init(void) { - if (vgacon_text_force() && vbox_modeset == -1) + if (drm_firmware_drivers_only() && vbox_modeset == -1) return -EINVAL; if (vbox_modeset == 0) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index d86e1ad4a972..c20c96a97a6c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -27,7 +27,6 @@ */ #include -#include #include #include #include @@ -104,7 +103,7 @@ static int virtio_gpu_probe(struct virtio_device *vdev) struct drm_device *dev; int ret; - if (vgacon_text_force() && virtio_gpu_modeset == -1) + if (drm_firmware_drivers_only() && virtio_gpu_modeset == -1) return -EINVAL; if (virtio_gpu_modeset == 0) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index bfd71c86faa5..75d1e032cf16 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -25,7 +25,6 @@ * **************************************************************************/ -#include #include #include #include @@ -1651,7 +1650,7 @@ static int __init vmwgfx_init(void) { int ret; - if (vgacon_text_force()) + if (drm_firmware_drivers_only()) return -EINVAL; ret = pci_register_driver(&vmw_pci_driver); diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c index ef9c57ce0906..d4320b147956 100644 --- a/drivers/video/console/vgacon.c +++ b/drivers/video/console/vgacon.c @@ -97,30 +97,9 @@ static int vga_video_font_height; static int vga_scan_lines __read_mostly; static unsigned int vga_rolled_over; /* last vc_origin offset before wrap */ -static bool vgacon_text_mode_force; static bool vga_hardscroll_enabled; static bool vga_hardscroll_user_enable = true; -bool vgacon_text_force(void) -{ - return vgacon_text_mode_force; -} -EXPORT_SYMBOL(vgacon_text_force); - -static int __init text_mode(char *str) -{ - vgacon_text_mode_force = true; - - pr_warn("You have booted with nomodeset. This means your GPU drivers are DISABLED\n"); - pr_warn("Any video related functionality will be severely degraded, and you may not even be able to suspend the system properly\n"); - pr_warn("Unless you actually understand what nomodeset does, you should reboot without enabling it\n"); - - return 1; -} - -/* force text mode - used by kernel modesetting */ -__setup("nomodeset", text_mode); - static int __init no_scroll(char *str) { /* diff --git a/gpu/drm/drm_nomodeset.c b/gpu/drm/drm_nomodeset.c new file mode 100644 index 000000000000..287edfb18b5d --- /dev/null +++ b/gpu/drm/drm_nomodeset.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +static bool drm_nomodeset; + +bool drm_firmware_drivers_only(void) +{ + return drm_nomodeset; +} +EXPORT_SYMBOL(drm_firmware_drivers_only); + +static int __init disable_modeset(char *str) +{ + drm_nomodeset = true; + + pr_warn("You have booted with nomodeset. This means your GPU drivers are DISABLED\n"); + pr_warn("Any video related functionality will be severely degraded, and you may not even be able to suspend the system properly\n"); + pr_warn("Unless you actually understand what nomodeset does, you should reboot without enabling it\n"); + + return 1; +} + +/* Disable kernel modesetting */ +__setup("nomodeset", disable_modeset); diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h index a84eb4028e5b..89e26a732175 100644 --- a/include/drm/drm_drv.h +++ b/include/drm/drm_drv.h @@ -601,5 +601,10 @@ static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev) int drm_dev_set_unique(struct drm_device *dev, const char *name); +#ifdef CONFIG_VGA_CONSOLE +extern bool drm_firmware_drivers_only(void); +#else +static inline bool drm_firmware_drivers_only(void) { return false; } +#endif #endif diff --git a/include/linux/console.h b/include/linux/console.h index a97f277cfdfa..7cd758a4f44e 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -219,12 +219,6 @@ extern atomic_t ignore_console_lock_warning; #define VESA_HSYNC_SUSPEND 2 #define VESA_POWERDOWN 3 -#ifdef CONFIG_VGA_CONSOLE -extern bool vgacon_text_force(void); -#else -static inline bool vgacon_text_force(void) { return false; } -#endif - extern void console_init(void); /* For deferred console takeover */ -- cgit v1.2.3 From ed14e769f64311769dcf20dde544b82c158d01b1 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Mon, 15 Nov 2021 14:19:12 +0000 Subject: iio: buffer-dma: Remove unused iio_buffer_block struct This structure was never used anywhere, so it can safely be dropped. It will later be re-introduced as a different structure in a different header. Signed-off-by: Paul Cercueil Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20211115141925.60164-3-paul@crapouillou.net Signed-off-by: Jonathan Cameron --- include/linux/iio/buffer-dma.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index ff15c61bf319..6564bdcdac66 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -17,11 +17,6 @@ struct iio_dma_buffer_queue; struct iio_dma_buffer_ops; struct device; -struct iio_buffer_block { - u32 size; - u32 bytes_used; -}; - /** * enum iio_block_state - State of a struct iio_dma_buffer_block * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued -- cgit v1.2.3 From ffc7c5172a6d1f7ec468066a7172ce65baf1e3e1 Mon Sep 17 00:00:00 2001 From: Antoniu Miclaus Date: Fri, 19 Nov 2021 10:56:27 +0200 Subject: iio: expose shared parameter in IIO_ENUM_AVAILABLE The shared parameter should be configurable based on its usage, and not constrained to IIO_SHARED_BY_TYPE. This patch aims to improve the flexibility in using the IIO_ENUM_AVAILABLE define and avoid redefining custom iio enums that expose the shared parameter. An example is the ad5766.c driver where IIO_ENUM_AVAILABLE_SHARED was defined in order to achieve `shared` parameter customization. The current state of the IIO_ENUM_AVAILABLE implementation will imply similar redefinitions each time a driver will require access to the `shared` parameter. An example would be admv1013 driver which will require custom device attribute for the frequency translation modes: Quadrature I/Q mode and Intermediate Frequency mode. Signed-off-by: Antoniu Miclaus Reviewed-by: Alexandru Ardelean Link: https://lore.kernel.org/r/20211119085627.6348-1-antoniu.miclaus@analog.com Signed-off-by: Jonathan Cameron --- drivers/iio/accel/bma180.c | 2 +- drivers/iio/accel/mma9553.c | 2 +- drivers/iio/adc/ad7192.c | 3 ++- drivers/iio/adc/hi8435.c | 2 +- drivers/iio/dac/ad5064.c | 4 ++-- drivers/iio/dac/ad5380.c | 2 +- drivers/iio/dac/ad5446.c | 2 +- drivers/iio/dac/ad5504.c | 2 +- drivers/iio/dac/ad5624r_spi.c | 2 +- drivers/iio/dac/ad5686.c | 2 +- drivers/iio/dac/ad5766.c | 13 ++----------- drivers/iio/dac/ad5791.c | 2 +- drivers/iio/dac/max5821.c | 2 +- drivers/iio/dac/mcp4725.c | 8 ++++---- drivers/iio/dac/stm32-dac.c | 2 +- drivers/iio/dac/ti-dac082s085.c | 2 +- drivers/iio/dac/ti-dac5571.c | 2 +- drivers/iio/dac/ti-dac7311.c | 2 +- drivers/iio/magnetometer/hmc5843_core.c | 4 ++-- drivers/iio/trigger/stm32-timer-trigger.c | 4 ++-- include/linux/iio/iio.h | 5 +++-- 21 files changed, 31 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/accel/bma180.c b/drivers/iio/accel/bma180.c index 2edfcb4819b7..09496f358ad9 100644 --- a/drivers/iio/accel/bma180.c +++ b/drivers/iio/accel/bma180.c @@ -658,7 +658,7 @@ static const struct iio_chan_spec_ext_info bma023_ext_info[] = { static const struct iio_chan_spec_ext_info bma180_ext_info[] = { IIO_ENUM("power_mode", IIO_SHARED_BY_TYPE, &bma180_power_mode_enum), - IIO_ENUM_AVAILABLE("power_mode", &bma180_power_mode_enum), + IIO_ENUM_AVAILABLE("power_mode", IIO_SHARED_BY_TYPE, &bma180_power_mode_enum), IIO_MOUNT_MATRIX(IIO_SHARED_BY_DIR, bma180_accel_get_mount_matrix), { } }; diff --git a/drivers/iio/accel/mma9553.c b/drivers/iio/accel/mma9553.c index ba3ecb3b57dc..0570ab1cc064 100644 --- a/drivers/iio/accel/mma9553.c +++ b/drivers/iio/accel/mma9553.c @@ -917,7 +917,7 @@ static const struct iio_enum mma9553_calibgender_enum = { static const struct iio_chan_spec_ext_info mma9553_ext_info[] = { IIO_ENUM("calibgender", IIO_SHARED_BY_TYPE, &mma9553_calibgender_enum), - IIO_ENUM_AVAILABLE("calibgender", &mma9553_calibgender_enum), + IIO_ENUM_AVAILABLE("calibgender", IIO_SHARED_BY_TYPE, &mma9553_calibgender_enum), {}, }; diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 2121a812b0c3..cc990205f306 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -257,7 +257,8 @@ static const struct iio_chan_spec_ext_info ad7192_calibsys_ext_info[] = { }, IIO_ENUM("sys_calibration_mode", IIO_SEPARATE, &ad7192_syscalib_mode_enum), - IIO_ENUM_AVAILABLE("sys_calibration_mode", &ad7192_syscalib_mode_enum), + IIO_ENUM_AVAILABLE("sys_calibration_mode", IIO_SHARED_BY_TYPE, + &ad7192_syscalib_mode_enum), {} }; diff --git a/drivers/iio/adc/hi8435.c b/drivers/iio/adc/hi8435.c index 8b353e26668e..e665e14c6e54 100644 --- a/drivers/iio/adc/hi8435.c +++ b/drivers/iio/adc/hi8435.c @@ -350,7 +350,7 @@ static const struct iio_enum hi8435_sensing_mode = { static const struct iio_chan_spec_ext_info hi8435_ext_info[] = { IIO_ENUM("sensing_mode", IIO_SEPARATE, &hi8435_sensing_mode), - IIO_ENUM_AVAILABLE("sensing_mode", &hi8435_sensing_mode), + IIO_ENUM_AVAILABLE("sensing_mode", IIO_SHARED_BY_TYPE, &hi8435_sensing_mode), {}, }; diff --git a/drivers/iio/dac/ad5064.c b/drivers/iio/dac/ad5064.c index fd9cac4f6321..27ee2c63c5d4 100644 --- a/drivers/iio/dac/ad5064.c +++ b/drivers/iio/dac/ad5064.c @@ -377,7 +377,7 @@ static const struct iio_chan_spec_ext_info ad5064_ext_info[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &ad5064_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5064_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5064_powerdown_mode_enum), { }, }; @@ -389,7 +389,7 @@ static const struct iio_chan_spec_ext_info ltc2617_ext_info[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, <c2617_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", <c2617_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, <c2617_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/ad5380.c b/drivers/iio/dac/ad5380.c index 8ca26bb4b62f..e38860a6a9f3 100644 --- a/drivers/iio/dac/ad5380.c +++ b/drivers/iio/dac/ad5380.c @@ -249,7 +249,7 @@ static const struct iio_chan_spec_ext_info ad5380_ext_info[] = { }, IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5380_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5380_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5380_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/ad5446.c b/drivers/iio/dac/ad5446.c index 3cc5513a6cbf..1c9b54c012a7 100644 --- a/drivers/iio/dac/ad5446.c +++ b/drivers/iio/dac/ad5446.c @@ -142,7 +142,7 @@ static const struct iio_chan_spec_ext_info ad5446_ext_info_powerdown[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &ad5446_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5446_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5446_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/ad5504.c b/drivers/iio/dac/ad5504.c index 19cdf9890d02..b631261efa97 100644 --- a/drivers/iio/dac/ad5504.c +++ b/drivers/iio/dac/ad5504.c @@ -241,7 +241,7 @@ static const struct iio_chan_spec_ext_info ad5504_ext_info[] = { }, IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5504_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5504_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5504_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/ad5624r_spi.c b/drivers/iio/dac/ad5624r_spi.c index 530529feebb5..3c98941b9f99 100644 --- a/drivers/iio/dac/ad5624r_spi.c +++ b/drivers/iio/dac/ad5624r_spi.c @@ -159,7 +159,7 @@ static const struct iio_chan_spec_ext_info ad5624r_ext_info[] = { }, IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5624r_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5624r_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5624r_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/ad5686.c b/drivers/iio/dac/ad5686.c index 8f001db775f4..e592a995f404 100644 --- a/drivers/iio/dac/ad5686.c +++ b/drivers/iio/dac/ad5686.c @@ -184,7 +184,7 @@ static const struct iio_chan_spec_ext_info ad5686_ext_info[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &ad5686_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5686_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5686_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/ad5766.c b/drivers/iio/dac/ad5766.c index b0d220c3a126..43189af2fb1f 100644 --- a/drivers/iio/dac/ad5766.c +++ b/drivers/iio/dac/ad5766.c @@ -426,14 +426,6 @@ static ssize_t ad5766_write_ext(struct iio_dev *indio_dev, .shared = _shared, \ } -#define IIO_ENUM_AVAILABLE_SHARED(_name, _shared, _e) \ -{ \ - .name = (_name "_available"), \ - .shared = _shared, \ - .read = iio_enum_available_read, \ - .private = (uintptr_t)(_e), \ -} - static const struct iio_chan_spec_ext_info ad5766_ext_info[] = { _AD5766_CHAN_EXT_INFO("dither_enable", AD5766_DITHER_ENABLE, @@ -443,9 +435,8 @@ static const struct iio_chan_spec_ext_info ad5766_ext_info[] = { _AD5766_CHAN_EXT_INFO("dither_source", AD5766_DITHER_SOURCE, IIO_SEPARATE), IIO_ENUM("dither_scale", IIO_SEPARATE, &ad5766_dither_scale_enum), - IIO_ENUM_AVAILABLE_SHARED("dither_scale", - IIO_SEPARATE, - &ad5766_dither_scale_enum), + IIO_ENUM_AVAILABLE("dither_scale", IIO_SEPARATE, + &ad5766_dither_scale_enum), {} }; diff --git a/drivers/iio/dac/ad5791.c b/drivers/iio/dac/ad5791.c index a0923b76e8b6..7b4579d73d18 100644 --- a/drivers/iio/dac/ad5791.c +++ b/drivers/iio/dac/ad5791.c @@ -285,7 +285,7 @@ static const struct iio_chan_spec_ext_info ad5791_ext_info[] = { }, IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5791_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &ad5791_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ad5791_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/max5821.c b/drivers/iio/dac/max5821.c index 7da4710a6408..fce640b7f1c8 100644 --- a/drivers/iio/dac/max5821.c +++ b/drivers/iio/dac/max5821.c @@ -137,7 +137,7 @@ static const struct iio_chan_spec_ext_info max5821_ext_info[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &max5821_powerdown_mode_enum), - IIO_ENUM_AVAILABLE("powerdown_mode", &max5821_powerdown_mode_enum), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &max5821_powerdown_mode_enum), { }, }; diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c index 34b14aafb630..98b2c2f10bf3 100644 --- a/drivers/iio/dac/mcp4725.c +++ b/drivers/iio/dac/mcp4725.c @@ -221,8 +221,8 @@ static const struct iio_chan_spec_ext_info mcp4725_ext_info[] = { }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &mcp472x_powerdown_mode_enum[MCP4725]), - IIO_ENUM_AVAILABLE("powerdown_mode", - &mcp472x_powerdown_mode_enum[MCP4725]), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, + &mcp472x_powerdown_mode_enum[MCP4725]), { }, }; @@ -235,8 +235,8 @@ static const struct iio_chan_spec_ext_info mcp4726_ext_info[] = { }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &mcp472x_powerdown_mode_enum[MCP4726]), - IIO_ENUM_AVAILABLE("powerdown_mode", - &mcp472x_powerdown_mode_enum[MCP4726]), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, + &mcp472x_powerdown_mode_enum[MCP4726]), { }, }; diff --git a/drivers/iio/dac/stm32-dac.c b/drivers/iio/dac/stm32-dac.c index dd2e306824e7..cd71cc4553a7 100644 --- a/drivers/iio/dac/stm32-dac.c +++ b/drivers/iio/dac/stm32-dac.c @@ -246,7 +246,7 @@ static const struct iio_chan_spec_ext_info stm32_dac_ext_info[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &stm32_dac_powerdown_mode_en), - IIO_ENUM_AVAILABLE("powerdown_mode", &stm32_dac_powerdown_mode_en), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &stm32_dac_powerdown_mode_en), {}, }; diff --git a/drivers/iio/dac/ti-dac082s085.c b/drivers/iio/dac/ti-dac082s085.c index 5c14bfb16521..6beda2193683 100644 --- a/drivers/iio/dac/ti-dac082s085.c +++ b/drivers/iio/dac/ti-dac082s085.c @@ -160,7 +160,7 @@ static const struct iio_chan_spec_ext_info ti_dac_ext_info[] = { .shared = IIO_SHARED_BY_TYPE, }, IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE, &ti_dac_powerdown_mode), - IIO_ENUM_AVAILABLE("powerdown_mode", &ti_dac_powerdown_mode), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ti_dac_powerdown_mode), { }, }; diff --git a/drivers/iio/dac/ti-dac5571.c b/drivers/iio/dac/ti-dac5571.c index 546a4cf6c5ef..4a3b8d875518 100644 --- a/drivers/iio/dac/ti-dac5571.c +++ b/drivers/iio/dac/ti-dac5571.c @@ -212,7 +212,7 @@ static const struct iio_chan_spec_ext_info dac5571_ext_info[] = { .shared = IIO_SEPARATE, }, IIO_ENUM("powerdown_mode", IIO_SEPARATE, &dac5571_powerdown_mode), - IIO_ENUM_AVAILABLE("powerdown_mode", &dac5571_powerdown_mode), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &dac5571_powerdown_mode), {}, }; diff --git a/drivers/iio/dac/ti-dac7311.c b/drivers/iio/dac/ti-dac7311.c index 09218c3029f0..99f275829ec2 100644 --- a/drivers/iio/dac/ti-dac7311.c +++ b/drivers/iio/dac/ti-dac7311.c @@ -146,7 +146,7 @@ static const struct iio_chan_spec_ext_info ti_dac_ext_info[] = { .shared = IIO_SHARED_BY_TYPE, }, IIO_ENUM("powerdown_mode", IIO_SHARED_BY_TYPE, &ti_dac_powerdown_mode), - IIO_ENUM_AVAILABLE("powerdown_mode", &ti_dac_powerdown_mode), + IIO_ENUM_AVAILABLE("powerdown_mode", IIO_SHARED_BY_TYPE, &ti_dac_powerdown_mode), { }, }; diff --git a/drivers/iio/magnetometer/hmc5843_core.c b/drivers/iio/magnetometer/hmc5843_core.c index f08726bf5ec3..5a730d9bdbb0 100644 --- a/drivers/iio/magnetometer/hmc5843_core.c +++ b/drivers/iio/magnetometer/hmc5843_core.c @@ -246,7 +246,7 @@ static const struct iio_enum hmc5843_meas_conf_enum = { static const struct iio_chan_spec_ext_info hmc5843_ext_info[] = { IIO_ENUM("meas_conf", IIO_SHARED_BY_TYPE, &hmc5843_meas_conf_enum), - IIO_ENUM_AVAILABLE("meas_conf", &hmc5843_meas_conf_enum), + IIO_ENUM_AVAILABLE("meas_conf", IIO_SHARED_BY_TYPE, &hmc5843_meas_conf_enum), IIO_MOUNT_MATRIX(IIO_SHARED_BY_DIR, hmc5843_get_mount_matrix), { } }; @@ -260,7 +260,7 @@ static const struct iio_enum hmc5983_meas_conf_enum = { static const struct iio_chan_spec_ext_info hmc5983_ext_info[] = { IIO_ENUM("meas_conf", IIO_SHARED_BY_TYPE, &hmc5983_meas_conf_enum), - IIO_ENUM_AVAILABLE("meas_conf", &hmc5983_meas_conf_enum), + IIO_ENUM_AVAILABLE("meas_conf", IIO_SHARED_BY_TYPE, &hmc5983_meas_conf_enum), IIO_MOUNT_MATRIX(IIO_SHARED_BY_DIR, hmc5843_get_mount_matrix), { } }; diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index 33083877cd19..02b87b0f9d70 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -696,9 +696,9 @@ static const struct iio_chan_spec_ext_info stm32_trigger_count_info[] = { .write = stm32_count_set_preset }, IIO_ENUM("enable_mode", IIO_SEPARATE, &stm32_enable_mode_enum), - IIO_ENUM_AVAILABLE("enable_mode", &stm32_enable_mode_enum), + IIO_ENUM_AVAILABLE("enable_mode", IIO_SHARED_BY_TYPE, &stm32_enable_mode_enum), IIO_ENUM("trigger_mode", IIO_SEPARATE, &stm32_trigger_mode_enum), - IIO_ENUM_AVAILABLE("trigger_mode", &stm32_trigger_mode_enum), + IIO_ENUM_AVAILABLE("trigger_mode", IIO_SHARED_BY_TYPE, &stm32_trigger_mode_enum), {} }; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index 324561b7a5e8..07025d6b3de1 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -103,15 +103,16 @@ ssize_t iio_enum_write(struct iio_dev *indio_dev, /** * IIO_ENUM_AVAILABLE() - Initialize enum available extended channel attribute * @_name: Attribute name ("_available" will be appended to the name) + * @_shared: Whether the attribute is shared between all channels * @_e: Pointer to an iio_enum struct * * Creates a read only attribute which lists all the available enum items in a * space separated list. This should usually be used together with IIO_ENUM() */ -#define IIO_ENUM_AVAILABLE(_name, _e) \ +#define IIO_ENUM_AVAILABLE(_name, _shared, _e) \ { \ .name = (_name "_available"), \ - .shared = IIO_SHARED_BY_TYPE, \ + .shared = _shared, \ .read = iio_enum_available_read, \ .private = (uintptr_t)(_e), \ } -- cgit v1.2.3 From 75c5bd68b699bbcb6d25879644d62de4da14ab92 Mon Sep 17 00:00:00 2001 From: Miri Korenblit Date: Fri, 26 Nov 2021 10:48:19 +0100 Subject: ieee80211: change HE nominal packet padding value defines It's easier to use and understand, and to extend for EHT later, if we use the values here instead of the shifted values. Unfortunately, we need to add _POS so that we can use it in places like iwlwifi/mvm where constants are needed. While at it, fix the typo ("NOMIMAL") which also helps catch any conflicts. Signed-off-by: Miri Korenblit Link: https://lore.kernel.org/r/20211126104817.7c29a05b8eb5.I2ca9faf06e177e3035bec91e2ae53c2f91d41774@changeid Signed-off-by: Johannes Berg --- drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 6 ++++-- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 16 ++++++++-------- drivers/net/wireless/mediatek/mt76/mt7915/init.c | 3 ++- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 3 ++- drivers/net/wireless/realtek/rtw89/core.c | 3 ++- drivers/net/wireless/realtek/rtw89/fw.c | 2 +- include/linux/ieee80211.h | 11 ++++++----- net/mac80211/debugfs_sta.c | 9 +++++---- 8 files changed, 30 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index f470f9aea50f..881ede4a4aa2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -607,7 +607,8 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { .phy_cap_info[9] = IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB | - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED, + (IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED << + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS), .phy_cap_info[10] = IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF, }, @@ -664,7 +665,8 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI | IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242, .phy_cap_info[9] = - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED, + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED + << IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS, }, /* * Set default Tx/Rx HE MCS NSS Support field. diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 9fb9c7dad314..b96ccabd1596 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2126,24 +2126,24 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm, } flags |= STA_CTXT_HE_PACKET_EXT; - } else if ((sta->he_cap.he_cap_elem.phy_cap_info[9] & - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK) != - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED) { + } else if (u8_get_bits(sta->he_cap.he_cap_elem.phy_cap_info[9], + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK) + != IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED) { int low_th = -1; int high_th = -1; /* Take the PPE thresholds from the nominal padding info */ - switch (sta->he_cap.he_cap_elem.phy_cap_info[9] & - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK) { - case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US: + switch (u8_get_bits(sta->he_cap.he_cap_elem.phy_cap_info[9], + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK)) { + case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US: low_th = IWL_HE_PKT_EXT_NONE; high_th = IWL_HE_PKT_EXT_NONE; break; - case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US: + case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US: low_th = IWL_HE_PKT_EXT_BPSK; high_th = IWL_HE_PKT_EXT_NONE; break; - case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US: + case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US: low_th = IWL_HE_PKT_EXT_NONE; high_th = IWL_HE_PKT_EXT_BPSK; break; diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index 4fa8e7ba93e6..d054cdecd5f7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -853,7 +853,8 @@ mt7915_init_he_caps(struct mt7915_phy *phy, enum nl80211_band band, mt7915_gen_ppe_thresh(he_cap->ppe_thres, nss); } else { he_cap_elem->phy_cap_info[9] |= - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US; + u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK); } idx++; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 633c6d2a57ac..e2eef9b5f63b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -140,7 +140,8 @@ mt7921_init_he_caps(struct mt7921_phy *phy, enum nl80211_band band, mt7921_gen_ppe_thresh(he_cap->ppe_thres, nss); } else { he_cap_elem->phy_cap_info[9] |= - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US; + u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK); } if (band == NL80211_BAND_6GHZ) { diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index d02ec5a735cb..2bbe77ae7713 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -2115,7 +2115,8 @@ static void rtw89_init_he_cap(struct rtw89_dev *rtwdev, IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU | IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB | - IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US; + u8_encode_bits(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US, + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK); if (i == NL80211_IFTYPE_STATION) phy_cap_info[9] |= IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU; he_cap->he_mcs_nss_supp.rx_mcs_80 = cpu_to_le16(mcs_map); diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c index 212aaf577d3c..460d63dd6779 100644 --- a/drivers/net/wireless/realtek/rtw89/fw.c +++ b/drivers/net/wireless/realtek/rtw89/fw.c @@ -780,7 +780,7 @@ static void __get_sta_he_pkt_padding(struct rtw89_dev *rtwdev, if (!ppe_th) { u8 pad; - pad = FIELD_GET(IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK, + pad = FIELD_GET(IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK, sta->he_cap.he_cap_elem.phy_cap_info[9]); for (i = 0; i < RTW89_PPE_BW_NUM; i++) diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 11d7af260f20..559b6c644938 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2258,11 +2258,12 @@ enum ieee80211_client_reg_power { #define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US 0x00 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US 0x40 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US 0x80 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 #define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 481f01b0f65c..9479f2787ea7 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -936,14 +936,15 @@ static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, "RX-FULL-BW-SU-USING-MU-WITH-NON-COMP-SIGB"); - switch (cap[9] & IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK) { - case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US: + switch (u8_get_bits(cap[9], + IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK)) { + case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US: PRINT("NOMINAL-PACKET-PADDING-0US"); break; - case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US: + case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US: PRINT("NOMINAL-PACKET-PADDING-8US"); break; - case IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US: + case IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US: PRINT("NOMINAL-PACKET-PADDING-16US"); break; } -- cgit v1.2.3 From 4ba0b2c294fe691921271372f7b59e5cc2ce4b0f Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 18 Nov 2021 17:55:51 -0800 Subject: fpga: mgr: Use standard dev_release for class driver The FPGA manager class driver data structure is being treated as a managed resource instead of using the standard dev_release call-back function to release the class data structure. This change removes the managed resource code for the freeing of the class data structure and combines the create() and register() functions into a single register() or register_full() function. The register_full() function accepts an info data structure to provide flexibility in passing optional parameters. The register() function supports the current parameter list for users that don't require the use of optional parameters. The devm_fpga_mgr_register() function is retained, and the devm_fpga_mgr_register_full() function is added. Signed-off-by: Russ Weight Reviewed-by: Xu Yilun Acked-by: Xu Yilun Signed-off-by: Moritz Fischer --- Documentation/driver-api/fpga/fpga-mgr.rst | 38 +++-- drivers/fpga/altera-cvp.c | 12 +- drivers/fpga/altera-pr-ip-core.c | 7 +- drivers/fpga/altera-ps-spi.c | 9 +- drivers/fpga/dfl-fme-mgr.c | 22 ++- drivers/fpga/fpga-mgr.c | 215 ++++++++++++----------------- drivers/fpga/ice40-spi.c | 9 +- drivers/fpga/machxo2-spi.c | 9 +- drivers/fpga/socfpga-a10.c | 16 +-- drivers/fpga/socfpga.c | 9 +- drivers/fpga/stratix10-soc.c | 16 +-- drivers/fpga/ts73xx-fpga.c | 9 +- drivers/fpga/versal-fpga.c | 9 +- drivers/fpga/xilinx-spi.c | 11 +- drivers/fpga/zynq-fpga.c | 16 +-- drivers/fpga/zynqmp-fpga.c | 9 +- include/linux/fpga/fpga-mgr.h | 62 ++++++--- 17 files changed, 217 insertions(+), 261 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/fpga/fpga-mgr.rst b/Documentation/driver-api/fpga/fpga-mgr.rst index 4d926b452cb3..42c01f396dce 100644 --- a/Documentation/driver-api/fpga/fpga-mgr.rst +++ b/Documentation/driver-api/fpga/fpga-mgr.rst @@ -24,7 +24,7 @@ How to support a new FPGA device -------------------------------- To add another FPGA manager, write a driver that implements a set of ops. The -probe function calls fpga_mgr_register(), such as:: +probe function calls fpga_mgr_register() or fpga_mgr_register_full(), such as:: static const struct fpga_manager_ops socfpga_fpga_ops = { .write_init = socfpga_fpga_ops_configure_init, @@ -49,14 +49,14 @@ probe function calls fpga_mgr_register(), such as:: * them in priv */ - mgr = devm_fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager", - &socfpga_fpga_ops, priv); - if (!mgr) - return -ENOMEM; + mgr = fpga_mgr_register(dev, "Altera SOCFPGA FPGA Manager", + &socfpga_fpga_ops, priv); + if (IS_ERR(mgr)) + return PTR_ERR(mgr); platform_set_drvdata(pdev, mgr); - return fpga_mgr_register(mgr); + return 0; } static int socfpga_fpga_remove(struct platform_device *pdev) @@ -68,6 +68,11 @@ probe function calls fpga_mgr_register(), such as:: return 0; } +Alternatively, the probe function could call one of the resource managed +register functions, devm_fpga_mgr_register() or devm_fpga_mgr_register_full(). +When these functions are used, the parameter syntax is the same, but the call +to fpga_mgr_unregister() should be removed. In the above example, the +socfpga_fpga_remove() function would not be required. The ops will implement whatever device specific register writes are needed to do the programming sequence for this particular FPGA. These ops return 0 for @@ -104,8 +109,14 @@ API for implementing a new FPGA Manager driver * ``fpga_mgr_states`` - Values for :c:expr:`fpga_manager->state`. * struct fpga_manager - the FPGA manager struct * struct fpga_manager_ops - Low level FPGA manager driver ops -* devm_fpga_mgr_create() - Allocate and init a manager struct -* fpga_mgr_register() - Register an FPGA manager +* struct fpga_manager_info - Parameter structure for fpga_mgr_register_full() +* fpga_mgr_register_full() - Create and register an FPGA manager using the + fpga_mgr_info structure to provide the full flexibility of options +* fpga_mgr_register() - Create and register an FPGA manager using standard + arguments +* devm_fpga_mgr_register_full() - Resource managed version of + fpga_mgr_register_full() +* devm_fpga_mgr_register() - Resource managed version of fpga_mgr_register() * fpga_mgr_unregister() - Unregister an FPGA manager .. kernel-doc:: include/linux/fpga/fpga-mgr.h @@ -117,11 +128,20 @@ API for implementing a new FPGA Manager driver .. kernel-doc:: include/linux/fpga/fpga-mgr.h :functions: fpga_manager_ops +.. kernel-doc:: include/linux/fpga/fpga-mgr.h + :functions: fpga_manager_info + .. kernel-doc:: drivers/fpga/fpga-mgr.c - :functions: devm_fpga_mgr_create + :functions: fpga_mgr_register_full .. kernel-doc:: drivers/fpga/fpga-mgr.c :functions: fpga_mgr_register +.. kernel-doc:: drivers/fpga/fpga-mgr.c + :functions: devm_fpga_mgr_register_full + +.. kernel-doc:: drivers/fpga/fpga-mgr.c + :functions: devm_fpga_mgr_register + .. kernel-doc:: drivers/fpga/fpga-mgr.c :functions: fpga_mgr_unregister diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c index ccf4546eff29..4ffb9da537d8 100644 --- a/drivers/fpga/altera-cvp.c +++ b/drivers/fpga/altera-cvp.c @@ -652,19 +652,15 @@ static int altera_cvp_probe(struct pci_dev *pdev, snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s @%s", ALTERA_CVP_MGR_NAME, pci_name(pdev)); - mgr = devm_fpga_mgr_create(&pdev->dev, conf->mgr_name, - &altera_cvp_ops, conf); - if (!mgr) { - ret = -ENOMEM; + mgr = fpga_mgr_register(&pdev->dev, conf->mgr_name, + &altera_cvp_ops, conf); + if (IS_ERR(mgr)) { + ret = PTR_ERR(mgr); goto err_unmap; } pci_set_drvdata(pdev, mgr); - ret = fpga_mgr_register(mgr); - if (ret) - goto err_unmap; - return 0; err_unmap: diff --git a/drivers/fpga/altera-pr-ip-core.c b/drivers/fpga/altera-pr-ip-core.c index dfdf21ed34c4..be0667968d33 100644 --- a/drivers/fpga/altera-pr-ip-core.c +++ b/drivers/fpga/altera-pr-ip-core.c @@ -191,11 +191,8 @@ int alt_pr_register(struct device *dev, void __iomem *reg_base) (val & ALT_PR_CSR_STATUS_MSK) >> ALT_PR_CSR_STATUS_SFT, (int)(val & ALT_PR_CSR_PR_START)); - mgr = devm_fpga_mgr_create(dev, dev_name(dev), &alt_pr_ops, priv); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(dev, mgr); + mgr = devm_fpga_mgr_register(dev, dev_name(dev), &alt_pr_ops, priv); + return PTR_ERR_OR_ZERO(mgr); } EXPORT_SYMBOL_GPL(alt_pr_register); diff --git a/drivers/fpga/altera-ps-spi.c b/drivers/fpga/altera-ps-spi.c index 23bfd4d1ad0f..5e1e009dba89 100644 --- a/drivers/fpga/altera-ps-spi.c +++ b/drivers/fpga/altera-ps-spi.c @@ -302,12 +302,9 @@ static int altera_ps_probe(struct spi_device *spi) snprintf(conf->mgr_name, sizeof(conf->mgr_name), "%s %s", dev_driver_string(&spi->dev), dev_name(&spi->dev)); - mgr = devm_fpga_mgr_create(&spi->dev, conf->mgr_name, - &altera_ps_ops, conf); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(&spi->dev, mgr); + mgr = devm_fpga_mgr_register(&spi->dev, conf->mgr_name, + &altera_ps_ops, conf); + return PTR_ERR_OR_ZERO(mgr); } static const struct spi_device_id altera_ps_spi_ids[] = { diff --git a/drivers/fpga/dfl-fme-mgr.c b/drivers/fpga/dfl-fme-mgr.c index 313420405d5e..af0785783b52 100644 --- a/drivers/fpga/dfl-fme-mgr.c +++ b/drivers/fpga/dfl-fme-mgr.c @@ -276,7 +276,7 @@ static void fme_mgr_get_compat_id(void __iomem *fme_pr, static int fme_mgr_probe(struct platform_device *pdev) { struct dfl_fme_mgr_pdata *pdata = dev_get_platdata(&pdev->dev); - struct fpga_compat_id *compat_id; + struct fpga_manager_info info = { 0 }; struct device *dev = &pdev->dev; struct fme_mgr_priv *priv; struct fpga_manager *mgr; @@ -296,20 +296,16 @@ static int fme_mgr_probe(struct platform_device *pdev) return PTR_ERR(priv->ioaddr); } - compat_id = devm_kzalloc(dev, sizeof(*compat_id), GFP_KERNEL); - if (!compat_id) + info.name = "DFL FME FPGA Manager"; + info.mops = &fme_mgr_ops; + info.priv = priv; + info.compat_id = devm_kzalloc(dev, sizeof(*info.compat_id), GFP_KERNEL); + if (!info.compat_id) return -ENOMEM; - fme_mgr_get_compat_id(priv->ioaddr, compat_id); - - mgr = devm_fpga_mgr_create(dev, "DFL FME FPGA Manager", - &fme_mgr_ops, priv); - if (!mgr) - return -ENOMEM; - - mgr->compat_id = compat_id; - - return devm_fpga_mgr_register(dev, mgr); + fme_mgr_get_compat_id(priv->ioaddr, info.compat_id); + mgr = devm_fpga_mgr_register_full(dev, &info); + return PTR_ERR_OR_ZERO(mgr); } static struct platform_driver fme_mgr_driver = { diff --git a/drivers/fpga/fpga-mgr.c b/drivers/fpga/fpga-mgr.c index aa30889e2320..d49a9ce34568 100644 --- a/drivers/fpga/fpga-mgr.c +++ b/drivers/fpga/fpga-mgr.c @@ -592,49 +592,49 @@ void fpga_mgr_unlock(struct fpga_manager *mgr) EXPORT_SYMBOL_GPL(fpga_mgr_unlock); /** - * fpga_mgr_create - create and initialize an FPGA manager struct + * fpga_mgr_register_full - create and register an FPGA Manager device * @parent: fpga manager device from pdev - * @name: fpga manager name - * @mops: pointer to structure of fpga manager ops - * @priv: fpga manager private data + * @info: parameters for fpga manager * - * The caller of this function is responsible for freeing the struct with - * fpga_mgr_free(). Using devm_fpga_mgr_create() instead is recommended. + * The caller of this function is responsible for calling fpga_mgr_unregister(). + * Using devm_fpga_mgr_register_full() instead is recommended. * - * Return: pointer to struct fpga_manager or NULL + * Return: pointer to struct fpga_manager pointer or ERR_PTR() */ -struct fpga_manager *fpga_mgr_create(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, - void *priv) +struct fpga_manager * +fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info) { + const struct fpga_manager_ops *mops = info->mops; struct fpga_manager *mgr; int id, ret; if (!mops) { dev_err(parent, "Attempt to register without fpga_manager_ops\n"); - return NULL; + return ERR_PTR(-EINVAL); } - if (!name || !strlen(name)) { + if (!info->name || !strlen(info->name)) { dev_err(parent, "Attempt to register with no name!\n"); - return NULL; + return ERR_PTR(-EINVAL); } mgr = kzalloc(sizeof(*mgr), GFP_KERNEL); if (!mgr) - return NULL; + return ERR_PTR(-ENOMEM); id = ida_simple_get(&fpga_mgr_ida, 0, 0, GFP_KERNEL); - if (id < 0) + if (id < 0) { + ret = id; goto error_kfree; + } mutex_init(&mgr->ref_mutex); - mgr->name = name; - mgr->mops = mops; - mgr->priv = priv; + mgr->name = info->name; + mgr->mops = info->mops; + mgr->priv = info->priv; + mgr->compat_id = info->compat_id; - device_initialize(&mgr->dev); mgr->dev.class = fpga_mgr_class; mgr->dev.groups = mops->groups; mgr->dev.parent = parent; @@ -645,6 +645,19 @@ struct fpga_manager *fpga_mgr_create(struct device *parent, const char *name, if (ret) goto error_device; + /* + * Initialize framework state by requesting low level driver read state + * from device. FPGA may be in reset mode or may have been programmed + * by bootloader or EEPROM. + */ + mgr->state = fpga_mgr_state(mgr); + + ret = device_register(&mgr->dev); + if (ret) { + put_device(&mgr->dev); + return ERR_PTR(ret); + } + return mgr; error_device: @@ -652,96 +665,36 @@ error_device: error_kfree: kfree(mgr); - return NULL; + return ERR_PTR(ret); } -EXPORT_SYMBOL_GPL(fpga_mgr_create); +EXPORT_SYMBOL_GPL(fpga_mgr_register_full); /** - * fpga_mgr_free - free an FPGA manager created with fpga_mgr_create() - * @mgr: fpga manager struct - */ -void fpga_mgr_free(struct fpga_manager *mgr) -{ - ida_simple_remove(&fpga_mgr_ida, mgr->dev.id); - kfree(mgr); -} -EXPORT_SYMBOL_GPL(fpga_mgr_free); - -static void devm_fpga_mgr_release(struct device *dev, void *res) -{ - struct fpga_mgr_devres *dr = res; - - fpga_mgr_free(dr->mgr); -} - -/** - * devm_fpga_mgr_create - create and initialize a managed FPGA manager struct + * fpga_mgr_register - create and register an FPGA Manager device * @parent: fpga manager device from pdev * @name: fpga manager name * @mops: pointer to structure of fpga manager ops * @priv: fpga manager private data * - * This function is intended for use in an FPGA manager driver's probe function. - * After the manager driver creates the manager struct with - * devm_fpga_mgr_create(), it should register it with fpga_mgr_register(). The - * manager driver's remove function should call fpga_mgr_unregister(). The - * manager struct allocated with this function will be freed automatically on - * driver detach. This includes the case of a probe function returning error - * before calling fpga_mgr_register(), the struct will still get cleaned up. + * The caller of this function is responsible for calling fpga_mgr_unregister(). + * Using devm_fpga_mgr_register() instead is recommended. This simple + * version of the register function should be sufficient for most users. The + * fpga_mgr_register_full() function is available for users that need to pass + * additional, optional parameters. * - * Return: pointer to struct fpga_manager or NULL + * Return: pointer to struct fpga_manager pointer or ERR_PTR() */ -struct fpga_manager *devm_fpga_mgr_create(struct device *parent, const char *name, - const struct fpga_manager_ops *mops, - void *priv) +struct fpga_manager * +fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv) { - struct fpga_mgr_devres *dr; + struct fpga_manager_info info = { 0 }; - dr = devres_alloc(devm_fpga_mgr_release, sizeof(*dr), GFP_KERNEL); - if (!dr) - return NULL; + info.name = name; + info.mops = mops; + info.priv = priv; - dr->mgr = fpga_mgr_create(parent, name, mops, priv); - if (!dr->mgr) { - devres_free(dr); - return NULL; - } - - devres_add(parent, dr); - - return dr->mgr; -} -EXPORT_SYMBOL_GPL(devm_fpga_mgr_create); - -/** - * fpga_mgr_register - register an FPGA manager - * @mgr: fpga manager struct - * - * Return: 0 on success, negative error code otherwise. - */ -int fpga_mgr_register(struct fpga_manager *mgr) -{ - int ret; - - /* - * Initialize framework state by requesting low level driver read state - * from device. FPGA may be in reset mode or may have been programmed - * by bootloader or EEPROM. - */ - mgr->state = fpga_mgr_state(mgr); - - ret = device_add(&mgr->dev); - if (ret) - goto error_device; - - dev_info(&mgr->dev, "%s registered\n", mgr->name); - - return 0; - -error_device: - ida_simple_remove(&fpga_mgr_ida, mgr->dev.id); - - return ret; + return fpga_mgr_register_full(parent, &info); } EXPORT_SYMBOL_GPL(fpga_mgr_register); @@ -765,14 +718,6 @@ void fpga_mgr_unregister(struct fpga_manager *mgr) } EXPORT_SYMBOL_GPL(fpga_mgr_unregister); -static int fpga_mgr_devres_match(struct device *dev, void *res, - void *match_data) -{ - struct fpga_mgr_devres *dr = res; - - return match_data == dr->mgr; -} - static void devm_fpga_mgr_unregister(struct device *dev, void *res) { struct fpga_mgr_devres *dr = res; @@ -781,45 +726,67 @@ static void devm_fpga_mgr_unregister(struct device *dev, void *res) } /** - * devm_fpga_mgr_register - resource managed variant of fpga_mgr_register() - * @dev: managing device for this FPGA manager - * @mgr: fpga manager struct + * devm_fpga_mgr_register_full - resource managed variant of fpga_mgr_register() + * @parent: fpga manager device from pdev + * @info: parameters for fpga manager * - * This is the devres variant of fpga_mgr_register() for which the unregister + * This is the devres variant of fpga_mgr_register_full() for which the unregister * function will be called automatically when the managing device is detached. */ -int devm_fpga_mgr_register(struct device *dev, struct fpga_manager *mgr) +struct fpga_manager * +devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info) { struct fpga_mgr_devres *dr; - int ret; - - /* - * Make sure that the struct fpga_manager * that is passed in is - * managed itself. - */ - if (WARN_ON(!devres_find(dev, devm_fpga_mgr_release, - fpga_mgr_devres_match, mgr))) - return -EINVAL; + struct fpga_manager *mgr; dr = devres_alloc(devm_fpga_mgr_unregister, sizeof(*dr), GFP_KERNEL); if (!dr) - return -ENOMEM; + return ERR_PTR(-ENOMEM); - ret = fpga_mgr_register(mgr); - if (ret) { + mgr = fpga_mgr_register_full(parent, info); + if (IS_ERR(mgr)) { devres_free(dr); - return ret; + return mgr; } dr->mgr = mgr; - devres_add(dev, dr); + devres_add(parent, dr); - return 0; + return mgr; +} +EXPORT_SYMBOL_GPL(devm_fpga_mgr_register_full); + +/** + * devm_fpga_mgr_register - resource managed variant of fpga_mgr_register() + * @parent: fpga manager device from pdev + * @name: fpga manager name + * @mops: pointer to structure of fpga manager ops + * @priv: fpga manager private data + * + * This is the devres variant of fpga_mgr_register() for which the + * unregister function will be called automatically when the managing + * device is detached. + */ +struct fpga_manager * +devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv) +{ + struct fpga_manager_info info = { 0 }; + + info.name = name; + info.mops = mops; + info.priv = priv; + + return devm_fpga_mgr_register_full(parent, &info); } EXPORT_SYMBOL_GPL(devm_fpga_mgr_register); static void fpga_mgr_dev_release(struct device *dev) { + struct fpga_manager *mgr = to_fpga_manager(dev); + + ida_simple_remove(&fpga_mgr_ida, mgr->dev.id); + kfree(mgr); } static int __init fpga_mgr_class_init(void) diff --git a/drivers/fpga/ice40-spi.c b/drivers/fpga/ice40-spi.c index 029d3cdb918d..7cbb3558b844 100644 --- a/drivers/fpga/ice40-spi.c +++ b/drivers/fpga/ice40-spi.c @@ -178,12 +178,9 @@ static int ice40_fpga_probe(struct spi_device *spi) return ret; } - mgr = devm_fpga_mgr_create(dev, "Lattice iCE40 FPGA Manager", - &ice40_fpga_ops, priv); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(dev, mgr); + mgr = devm_fpga_mgr_register(dev, "Lattice iCE40 FPGA Manager", + &ice40_fpga_ops, priv); + return PTR_ERR_OR_ZERO(mgr); } static const struct of_device_id ice40_fpga_of_match[] = { diff --git a/drivers/fpga/machxo2-spi.c b/drivers/fpga/machxo2-spi.c index ea2ec3c6815c..905607992a12 100644 --- a/drivers/fpga/machxo2-spi.c +++ b/drivers/fpga/machxo2-spi.c @@ -370,12 +370,9 @@ static int machxo2_spi_probe(struct spi_device *spi) return -EINVAL; } - mgr = devm_fpga_mgr_create(dev, "Lattice MachXO2 SPI FPGA Manager", - &machxo2_ops, spi); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(dev, mgr); + mgr = devm_fpga_mgr_register(dev, "Lattice MachXO2 SPI FPGA Manager", + &machxo2_ops, spi); + return PTR_ERR_OR_ZERO(mgr); } #ifdef CONFIG_OF diff --git a/drivers/fpga/socfpga-a10.c b/drivers/fpga/socfpga-a10.c index 573d88bdf730..ac8e89b8a5cc 100644 --- a/drivers/fpga/socfpga-a10.c +++ b/drivers/fpga/socfpga-a10.c @@ -508,19 +508,15 @@ static int socfpga_a10_fpga_probe(struct platform_device *pdev) return -EBUSY; } - mgr = devm_fpga_mgr_create(dev, "SoCFPGA Arria10 FPGA Manager", - &socfpga_a10_fpga_mgr_ops, priv); - if (!mgr) - return -ENOMEM; - - platform_set_drvdata(pdev, mgr); - - ret = fpga_mgr_register(mgr); - if (ret) { + mgr = fpga_mgr_register(dev, "SoCFPGA Arria10 FPGA Manager", + &socfpga_a10_fpga_mgr_ops, priv); + if (IS_ERR(mgr)) { clk_disable_unprepare(priv->clk); - return ret; + return PTR_ERR(mgr); } + platform_set_drvdata(pdev, mgr); + return 0; } diff --git a/drivers/fpga/socfpga.c b/drivers/fpga/socfpga.c index 1f467173fc1f..7e0741f99696 100644 --- a/drivers/fpga/socfpga.c +++ b/drivers/fpga/socfpga.c @@ -571,12 +571,9 @@ static int socfpga_fpga_probe(struct platform_device *pdev) if (ret) return ret; - mgr = devm_fpga_mgr_create(dev, "Altera SOCFPGA FPGA Manager", - &socfpga_fpga_ops, priv); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(dev, mgr); + mgr = devm_fpga_mgr_register(dev, "Altera SOCFPGA FPGA Manager", + &socfpga_fpga_ops, priv); + return PTR_ERR_OR_ZERO(mgr); } #ifdef CONFIG_OF diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 047fd7f23706..737d14c6e0de 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -419,18 +419,11 @@ static int s10_probe(struct platform_device *pdev) init_completion(&priv->status_return_completion); - mgr = fpga_mgr_create(dev, "Stratix10 SOC FPGA Manager", - &s10_ops, priv); - if (!mgr) { - dev_err(dev, "unable to create FPGA manager\n"); - ret = -ENOMEM; - goto probe_err; - } - - ret = fpga_mgr_register(mgr); - if (ret) { + mgr = fpga_mgr_register(dev, "Stratix10 SOC FPGA Manager", + &s10_ops, priv); + if (IS_ERR(mgr)) { dev_err(dev, "unable to register FPGA manager\n"); - fpga_mgr_free(mgr); + ret = PTR_ERR(mgr); goto probe_err; } @@ -448,7 +441,6 @@ static int s10_remove(struct platform_device *pdev) struct s10_priv *priv = mgr->priv; fpga_mgr_unregister(mgr); - fpga_mgr_free(mgr); stratix10_svc_free_channel(priv->chan); return 0; diff --git a/drivers/fpga/ts73xx-fpga.c b/drivers/fpga/ts73xx-fpga.c index 167abb0b08d4..8e6e9c840d9d 100644 --- a/drivers/fpga/ts73xx-fpga.c +++ b/drivers/fpga/ts73xx-fpga.c @@ -116,12 +116,9 @@ static int ts73xx_fpga_probe(struct platform_device *pdev) if (IS_ERR(priv->io_base)) return PTR_ERR(priv->io_base); - mgr = devm_fpga_mgr_create(kdev, "TS-73xx FPGA Manager", - &ts73xx_fpga_ops, priv); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(kdev, mgr); + mgr = devm_fpga_mgr_register(kdev, "TS-73xx FPGA Manager", + &ts73xx_fpga_ops, priv); + return PTR_ERR_OR_ZERO(mgr); } static struct platform_driver ts73xx_fpga_driver = { diff --git a/drivers/fpga/versal-fpga.c b/drivers/fpga/versal-fpga.c index 5b0dda304bd2..e1601b3a345b 100644 --- a/drivers/fpga/versal-fpga.c +++ b/drivers/fpga/versal-fpga.c @@ -54,12 +54,9 @@ static int versal_fpga_probe(struct platform_device *pdev) return ret; } - mgr = devm_fpga_mgr_create(dev, "Xilinx Versal FPGA Manager", - &versal_fpga_ops, NULL); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(dev, mgr); + mgr = devm_fpga_mgr_register(dev, "Xilinx Versal FPGA Manager", + &versal_fpga_ops, NULL); + return PTR_ERR_OR_ZERO(mgr); } static const struct of_device_id versal_fpga_of_match[] = { diff --git a/drivers/fpga/xilinx-spi.c b/drivers/fpga/xilinx-spi.c index b6bcf1d9233d..e1a227e7ff2a 100644 --- a/drivers/fpga/xilinx-spi.c +++ b/drivers/fpga/xilinx-spi.c @@ -247,13 +247,10 @@ static int xilinx_spi_probe(struct spi_device *spi) return dev_err_probe(&spi->dev, PTR_ERR(conf->done), "Failed to get DONE gpio\n"); - mgr = devm_fpga_mgr_create(&spi->dev, - "Xilinx Slave Serial FPGA Manager", - &xilinx_spi_ops, conf); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(&spi->dev, mgr); + mgr = devm_fpga_mgr_register(&spi->dev, + "Xilinx Slave Serial FPGA Manager", + &xilinx_spi_ops, conf); + return PTR_ERR_OR_ZERO(mgr); } #ifdef CONFIG_OF diff --git a/drivers/fpga/zynq-fpga.c b/drivers/fpga/zynq-fpga.c index 9b75bd4f93d8..426aa34c6a0d 100644 --- a/drivers/fpga/zynq-fpga.c +++ b/drivers/fpga/zynq-fpga.c @@ -609,20 +609,16 @@ static int zynq_fpga_probe(struct platform_device *pdev) clk_disable(priv->clk); - mgr = devm_fpga_mgr_create(dev, "Xilinx Zynq FPGA Manager", - &zynq_fpga_ops, priv); - if (!mgr) - return -ENOMEM; - - platform_set_drvdata(pdev, mgr); - - err = fpga_mgr_register(mgr); - if (err) { + mgr = fpga_mgr_register(dev, "Xilinx Zynq FPGA Manager", + &zynq_fpga_ops, priv); + if (IS_ERR(mgr)) { dev_err(dev, "unable to register FPGA manager\n"); clk_unprepare(priv->clk); - return err; + return PTR_ERR(mgr); } + platform_set_drvdata(pdev, mgr); + return 0; } diff --git a/drivers/fpga/zynqmp-fpga.c b/drivers/fpga/zynqmp-fpga.c index 7d3d5650c322..c60f20949c47 100644 --- a/drivers/fpga/zynqmp-fpga.c +++ b/drivers/fpga/zynqmp-fpga.c @@ -95,12 +95,9 @@ static int zynqmp_fpga_probe(struct platform_device *pdev) priv->dev = dev; - mgr = devm_fpga_mgr_create(dev, "Xilinx ZynqMP FPGA Manager", - &zynqmp_fpga_ops, priv); - if (!mgr) - return -ENOMEM; - - return devm_fpga_mgr_register(dev, mgr); + mgr = devm_fpga_mgr_register(dev, "Xilinx ZynqMP FPGA Manager", + &zynqmp_fpga_ops, priv); + return PTR_ERR_OR_ZERO(mgr); } #ifdef CONFIG_OF diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h index 474c1f506307..0f9468771bb9 100644 --- a/include/linux/fpga/fpga-mgr.h +++ b/include/linux/fpga/fpga-mgr.h @@ -105,6 +105,36 @@ struct fpga_image_info { #endif }; +/** + * struct fpga_compat_id - id for compatibility check + * + * @id_h: high 64bit of the compat_id + * @id_l: low 64bit of the compat_id + */ +struct fpga_compat_id { + u64 id_h; + u64 id_l; +}; + +/** + * struct fpga_manager_info - collection of parameters for an FPGA Manager + * @name: fpga manager name + * @compat_id: FPGA manager id for compatibility check. + * @mops: pointer to structure of fpga manager ops + * @priv: fpga manager private data + * + * fpga_manager_info contains parameters for the register_full function. + * These are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_manager_info { + const char *name; + struct fpga_compat_id *compat_id; + const struct fpga_manager_ops *mops; + void *priv; +}; + /** * struct fpga_manager_ops - ops for low level fpga manager drivers * @initial_header_size: Maximum number of bytes that should be passed into write_init @@ -143,17 +173,6 @@ struct fpga_manager_ops { #define FPGA_MGR_STATUS_IP_PROTOCOL_ERR BIT(3) #define FPGA_MGR_STATUS_FIFO_OVERFLOW_ERR BIT(4) -/** - * struct fpga_compat_id - id for compatibility check - * - * @id_h: high 64bit of the compat_id - * @id_l: low 64bit of the compat_id - */ -struct fpga_compat_id { - u64 id_h; - u64 id_l; -}; - /** * struct fpga_manager - fpga manager structure * @name: name of low level fpga manager @@ -191,17 +210,18 @@ struct fpga_manager *fpga_mgr_get(struct device *dev); void fpga_mgr_put(struct fpga_manager *mgr); -struct fpga_manager *fpga_mgr_create(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, - void *priv); -void fpga_mgr_free(struct fpga_manager *mgr); -int fpga_mgr_register(struct fpga_manager *mgr); -void fpga_mgr_unregister(struct fpga_manager *mgr); +struct fpga_manager * +fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); -int devm_fpga_mgr_register(struct device *dev, struct fpga_manager *mgr); +struct fpga_manager * +fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv); +void fpga_mgr_unregister(struct fpga_manager *mgr); -struct fpga_manager *devm_fpga_mgr_create(struct device *dev, const char *name, - const struct fpga_manager_ops *mops, - void *priv); +struct fpga_manager * +devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info); +struct fpga_manager * +devm_fpga_mgr_register(struct device *parent, const char *name, + const struct fpga_manager_ops *mops, void *priv); #endif /*_LINUX_FPGA_MGR_H */ -- cgit v1.2.3 From 0d70af3c2530a70f1b2c197feaa63fbd3548ce34 Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 18 Nov 2021 17:55:52 -0800 Subject: fpga: bridge: Use standard dev_release for class driver The FPGA bridge class driver data structure is being treated as a managed resource instead of using the standard dev_release call-back function to release the class data structure. This change removes the managed resource code and combines the create() and register() functions into a single register() function. Signed-off-by: Russ Weight Reviewed-by: Xu Yilun Acked-by: Xu Yilun Signed-off-by: Moritz Fischer --- Documentation/driver-api/fpga/fpga-bridge.rst | 6 +- drivers/fpga/altera-fpga2sdram.c | 12 +-- drivers/fpga/altera-freeze-bridge.c | 10 +-- drivers/fpga/altera-hps2fpga.c | 12 +-- drivers/fpga/dfl-fme-br.c | 10 +-- drivers/fpga/fpga-bridge.c | 122 ++++++-------------------- drivers/fpga/xilinx-pr-decoupler.c | 17 ++-- include/linux/fpga/fpga-bridge.h | 30 +++++-- 8 files changed, 74 insertions(+), 145 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/fpga/fpga-bridge.rst b/Documentation/driver-api/fpga/fpga-bridge.rst index 8d650b4e2ce6..604208534095 100644 --- a/Documentation/driver-api/fpga/fpga-bridge.rst +++ b/Documentation/driver-api/fpga/fpga-bridge.rst @@ -6,8 +6,7 @@ API to implement a new FPGA bridge * struct fpga_bridge - The FPGA Bridge structure * struct fpga_bridge_ops - Low level Bridge driver ops -* devm_fpga_bridge_create() - Allocate and init a bridge struct -* fpga_bridge_register() - Register a bridge +* fpga_bridge_register() - Create and register a bridge * fpga_bridge_unregister() - Unregister a bridge .. kernel-doc:: include/linux/fpga/fpga-bridge.h @@ -16,9 +15,6 @@ API to implement a new FPGA bridge .. kernel-doc:: include/linux/fpga/fpga-bridge.h :functions: fpga_bridge_ops -.. kernel-doc:: drivers/fpga/fpga-bridge.c - :functions: devm_fpga_bridge_create - .. kernel-doc:: drivers/fpga/fpga-bridge.c :functions: fpga_bridge_register diff --git a/drivers/fpga/altera-fpga2sdram.c b/drivers/fpga/altera-fpga2sdram.c index a78e49c63c64..ff3a646fd9e3 100644 --- a/drivers/fpga/altera-fpga2sdram.c +++ b/drivers/fpga/altera-fpga2sdram.c @@ -121,17 +121,13 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) /* Get f2s bridge configuration saved in handoff register */ regmap_read(sysmgr, SYSMGR_ISWGRP_HANDOFF3, &priv->mask); - br = devm_fpga_bridge_create(dev, F2S_BRIDGE_NAME, - &altera_fpga2sdram_br_ops, priv); - if (!br) - return -ENOMEM; + br = fpga_bridge_register(dev, F2S_BRIDGE_NAME, + &altera_fpga2sdram_br_ops, priv); + if (IS_ERR(br)) + return PTR_ERR(br); platform_set_drvdata(pdev, br); - ret = fpga_bridge_register(br); - if (ret) - return ret; - dev_info(dev, "driver initialized with handoff %08x\n", priv->mask); if (!of_property_read_u32(dev->of_node, "bridge-enable", &enable)) { diff --git a/drivers/fpga/altera-freeze-bridge.c b/drivers/fpga/altera-freeze-bridge.c index 7d22a44d652e..445f4b011167 100644 --- a/drivers/fpga/altera-freeze-bridge.c +++ b/drivers/fpga/altera-freeze-bridge.c @@ -246,14 +246,14 @@ static int altera_freeze_br_probe(struct platform_device *pdev) priv->base_addr = base_addr; - br = devm_fpga_bridge_create(dev, FREEZE_BRIDGE_NAME, - &altera_freeze_br_br_ops, priv); - if (!br) - return -ENOMEM; + br = fpga_bridge_register(dev, FREEZE_BRIDGE_NAME, + &altera_freeze_br_br_ops, priv); + if (IS_ERR(br)) + return PTR_ERR(br); platform_set_drvdata(pdev, br); - return fpga_bridge_register(br); + return 0; } static int altera_freeze_br_remove(struct platform_device *pdev) diff --git a/drivers/fpga/altera-hps2fpga.c b/drivers/fpga/altera-hps2fpga.c index 77b95f251821..aa758426c22b 100644 --- a/drivers/fpga/altera-hps2fpga.c +++ b/drivers/fpga/altera-hps2fpga.c @@ -180,19 +180,15 @@ static int alt_fpga_bridge_probe(struct platform_device *pdev) } } - br = devm_fpga_bridge_create(dev, priv->name, - &altera_hps2fpga_br_ops, priv); - if (!br) { - ret = -ENOMEM; + br = fpga_bridge_register(dev, priv->name, + &altera_hps2fpga_br_ops, priv); + if (IS_ERR(br)) { + ret = PTR_ERR(br); goto err; } platform_set_drvdata(pdev, br); - ret = fpga_bridge_register(br); - if (ret) - goto err; - return 0; err: diff --git a/drivers/fpga/dfl-fme-br.c b/drivers/fpga/dfl-fme-br.c index 3ff9f3a687ce..808d1f4d76df 100644 --- a/drivers/fpga/dfl-fme-br.c +++ b/drivers/fpga/dfl-fme-br.c @@ -68,14 +68,14 @@ static int fme_br_probe(struct platform_device *pdev) priv->pdata = dev_get_platdata(dev); - br = devm_fpga_bridge_create(dev, "DFL FPGA FME Bridge", - &fme_bridge_ops, priv); - if (!br) - return -ENOMEM; + br = fpga_bridge_register(dev, "DFL FPGA FME Bridge", + &fme_bridge_ops, priv); + if (IS_ERR(br)) + return PTR_ERR(br); platform_set_drvdata(pdev, br); - return fpga_bridge_register(br); + return 0; } static int fme_br_remove(struct platform_device *pdev) diff --git a/drivers/fpga/fpga-bridge.c b/drivers/fpga/fpga-bridge.c index 798f55670646..16f2b164a178 100644 --- a/drivers/fpga/fpga-bridge.c +++ b/drivers/fpga/fpga-bridge.c @@ -312,36 +312,41 @@ static struct attribute *fpga_bridge_attrs[] = { ATTRIBUTE_GROUPS(fpga_bridge); /** - * fpga_bridge_create - create and initialize a struct fpga_bridge + * fpga_bridge_register - create and register an FPGA Bridge device * @parent: FPGA bridge device from pdev * @name: FPGA bridge name * @br_ops: pointer to structure of fpga bridge ops * @priv: FPGA bridge private data * - * The caller of this function is responsible for freeing the bridge with - * fpga_bridge_free(). Using devm_fpga_bridge_create() instead is recommended. - * - * Return: struct fpga_bridge or NULL + * Return: struct fpga_bridge pointer or ERR_PTR() */ -struct fpga_bridge *fpga_bridge_create(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv) +struct fpga_bridge * +fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv) { struct fpga_bridge *bridge; int id, ret; + if (!br_ops) { + dev_err(parent, "Attempt to register without fpga_bridge_ops\n"); + return ERR_PTR(-EINVAL); + } + if (!name || !strlen(name)) { dev_err(parent, "Attempt to register with no name!\n"); - return NULL; + return ERR_PTR(-EINVAL); } bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); if (!bridge) - return NULL; + return ERR_PTR(-ENOMEM); id = ida_simple_get(&fpga_bridge_ida, 0, 0, GFP_KERNEL); - if (id < 0) + if (id < 0) { + ret = id; goto error_kfree; + } mutex_init(&bridge->mutex); INIT_LIST_HEAD(&bridge->node); @@ -350,17 +355,23 @@ struct fpga_bridge *fpga_bridge_create(struct device *parent, const char *name, bridge->br_ops = br_ops; bridge->priv = priv; - device_initialize(&bridge->dev); bridge->dev.groups = br_ops->groups; bridge->dev.class = fpga_bridge_class; bridge->dev.parent = parent; bridge->dev.of_node = parent->of_node; bridge->dev.id = id; + of_platform_populate(bridge->dev.of_node, NULL, NULL, &bridge->dev); ret = dev_set_name(&bridge->dev, "br%d", id); if (ret) goto error_device; + ret = device_register(&bridge->dev); + if (ret) { + put_device(&bridge->dev); + return ERR_PTR(ret); + } + return bridge; error_device: @@ -368,88 +379,7 @@ error_device: error_kfree: kfree(bridge); - return NULL; -} -EXPORT_SYMBOL_GPL(fpga_bridge_create); - -/** - * fpga_bridge_free - free an fpga bridge created by fpga_bridge_create() - * @bridge: FPGA bridge struct - */ -void fpga_bridge_free(struct fpga_bridge *bridge) -{ - ida_simple_remove(&fpga_bridge_ida, bridge->dev.id); - kfree(bridge); -} -EXPORT_SYMBOL_GPL(fpga_bridge_free); - -static void devm_fpga_bridge_release(struct device *dev, void *res) -{ - struct fpga_bridge *bridge = *(struct fpga_bridge **)res; - - fpga_bridge_free(bridge); -} - -/** - * devm_fpga_bridge_create - create and init a managed struct fpga_bridge - * @parent: FPGA bridge device from pdev - * @name: FPGA bridge name - * @br_ops: pointer to structure of fpga bridge ops - * @priv: FPGA bridge private data - * - * This function is intended for use in an FPGA bridge driver's probe function. - * After the bridge driver creates the struct with devm_fpga_bridge_create(), it - * should register the bridge with fpga_bridge_register(). The bridge driver's - * remove function should call fpga_bridge_unregister(). The bridge struct - * allocated with this function will be freed automatically on driver detach. - * This includes the case of a probe function returning error before calling - * fpga_bridge_register(), the struct will still get cleaned up. - * - * Return: struct fpga_bridge or NULL - */ -struct fpga_bridge -*devm_fpga_bridge_create(struct device *parent, const char *name, - const struct fpga_bridge_ops *br_ops, void *priv) -{ - struct fpga_bridge **ptr, *bridge; - - ptr = devres_alloc(devm_fpga_bridge_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return NULL; - - bridge = fpga_bridge_create(parent, name, br_ops, priv); - if (!bridge) { - devres_free(ptr); - } else { - *ptr = bridge; - devres_add(parent, ptr); - } - - return bridge; -} -EXPORT_SYMBOL_GPL(devm_fpga_bridge_create); - -/** - * fpga_bridge_register - register an FPGA bridge - * - * @bridge: FPGA bridge struct - * - * Return: 0 for success, error code otherwise. - */ -int fpga_bridge_register(struct fpga_bridge *bridge) -{ - struct device *dev = &bridge->dev; - int ret; - - ret = device_add(dev); - if (ret) - return ret; - - of_platform_populate(dev->of_node, NULL, NULL, dev); - - dev_info(dev->parent, "fpga bridge [%s] registered\n", bridge->name); - - return 0; + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(fpga_bridge_register); @@ -475,6 +405,10 @@ EXPORT_SYMBOL_GPL(fpga_bridge_unregister); static void fpga_bridge_dev_release(struct device *dev) { + struct fpga_bridge *bridge = to_fpga_bridge(dev); + + ida_simple_remove(&fpga_bridge_ida, bridge->dev.id); + kfree(bridge); } static int __init fpga_bridge_dev_init(void) diff --git a/drivers/fpga/xilinx-pr-decoupler.c b/drivers/fpga/xilinx-pr-decoupler.c index e986ed47c4ed..2d9c491f7be9 100644 --- a/drivers/fpga/xilinx-pr-decoupler.c +++ b/drivers/fpga/xilinx-pr-decoupler.c @@ -140,22 +140,17 @@ static int xlnx_pr_decoupler_probe(struct platform_device *pdev) clk_disable(priv->clk); - br = devm_fpga_bridge_create(&pdev->dev, priv->ipconfig->name, - &xlnx_pr_decoupler_br_ops, priv); - if (!br) { - err = -ENOMEM; - goto err_clk; - } - - platform_set_drvdata(pdev, br); - - err = fpga_bridge_register(br); - if (err) { + br = fpga_bridge_register(&pdev->dev, priv->ipconfig->name, + &xlnx_pr_decoupler_br_ops, priv); + if (IS_ERR(br)) { + err = PTR_ERR(br); dev_err(&pdev->dev, "unable to register %s", priv->ipconfig->name); goto err_clk; } + platform_set_drvdata(pdev, br); + return 0; err_clk: diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h index 6c3c28806ff1..223da48a6d18 100644 --- a/include/linux/fpga/fpga-bridge.h +++ b/include/linux/fpga/fpga-bridge.h @@ -22,6 +22,23 @@ struct fpga_bridge_ops { const struct attribute_group **groups; }; +/** + * struct fpga_bridge_info - collection of parameters an FPGA Bridge + * @name: fpga bridge name + * @br_ops: pointer to structure of fpga bridge ops + * @priv: fpga bridge private data + * + * fpga_bridge_info contains parameters for the register function. These + * are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_bridge_info { + const char *name; + const struct fpga_bridge_ops *br_ops; + void *priv; +}; + /** * struct fpga_bridge - FPGA bridge structure * @name: name of low level FPGA bridge @@ -62,15 +79,10 @@ int of_fpga_bridge_get_to_list(struct device_node *np, struct fpga_image_info *info, struct list_head *bridge_list); -struct fpga_bridge *fpga_bridge_create(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, - void *priv); -void fpga_bridge_free(struct fpga_bridge *br); -int fpga_bridge_register(struct fpga_bridge *br); +struct fpga_bridge * +fpga_bridge_register(struct device *parent, const char *name, + const struct fpga_bridge_ops *br_ops, + void *priv); void fpga_bridge_unregister(struct fpga_bridge *br); -struct fpga_bridge -*devm_fpga_bridge_create(struct device *dev, const char *name, - const struct fpga_bridge_ops *br_ops, void *priv); - #endif /* _LINUX_FPGA_BRIDGE_H */ -- cgit v1.2.3 From 8886a579744fbfa53e69aa453ed10ae3b1f9abac Mon Sep 17 00:00:00 2001 From: Russ Weight Date: Thu, 18 Nov 2021 17:55:53 -0800 Subject: fpga: region: Use standard dev_release for class driver The FPGA region class driver data structure is being treated as a managed resource instead of using the standard dev_release call-back function to release the class data structure. This change removes the managed resource code and combines the create() and register() functions into a single register() or register_full() function. The register_full() function accepts an info data structure to provide flexibility in passing optional parameters. The register() function supports the current parameter list for users that don't require the use of optional parameters. Signed-off-by: Russ Weight Reviewed-by: Xu Yilun Acked-by: Xu Yilun Signed-off-by: Moritz Fischer --- Documentation/driver-api/fpga/fpga-region.rst | 12 ++- drivers/fpga/dfl-fme-region.c | 17 ++-- drivers/fpga/dfl.c | 12 +-- drivers/fpga/fpga-region.c | 119 ++++++++++---------------- drivers/fpga/of-fpga-region.c | 10 +-- include/linux/fpga/fpga-region.h | 36 ++++++-- 6 files changed, 95 insertions(+), 111 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/fpga/fpga-region.rst b/Documentation/driver-api/fpga/fpga-region.rst index 2636a27c11b2..dc55d60a0b4a 100644 --- a/Documentation/driver-api/fpga/fpga-region.rst +++ b/Documentation/driver-api/fpga/fpga-region.rst @@ -46,8 +46,11 @@ API to add a new FPGA region ---------------------------- * struct fpga_region - The FPGA region struct -* devm_fpga_region_create() - Allocate and init a region struct -* fpga_region_register() - Register an FPGA region +* struct fpga_region_info - Parameter structure for fpga_region_register_full() +* fpga_region_register_full() - Create and register an FPGA region using the + fpga_region_info structure to provide the full flexibility of options +* fpga_region_register() - Create and register an FPGA region using standard + arguments * fpga_region_unregister() - Unregister an FPGA region The FPGA region's probe function will need to get a reference to the FPGA @@ -75,8 +78,11 @@ following APIs to handle building or tearing down that list. .. kernel-doc:: include/linux/fpga/fpga-region.h :functions: fpga_region +.. kernel-doc:: include/linux/fpga/fpga-region.h + :functions: fpga_region_info + .. kernel-doc:: drivers/fpga/fpga-region.c - :functions: devm_fpga_region_create + :functions: fpga_region_register_full .. kernel-doc:: drivers/fpga/fpga-region.c :functions: fpga_region_register diff --git a/drivers/fpga/dfl-fme-region.c b/drivers/fpga/dfl-fme-region.c index 1eeb42af1012..4aebde0a7f1c 100644 --- a/drivers/fpga/dfl-fme-region.c +++ b/drivers/fpga/dfl-fme-region.c @@ -30,6 +30,7 @@ static int fme_region_get_bridges(struct fpga_region *region) static int fme_region_probe(struct platform_device *pdev) { struct dfl_fme_region_pdata *pdata = dev_get_platdata(&pdev->dev); + struct fpga_region_info info = { 0 }; struct device *dev = &pdev->dev; struct fpga_region *region; struct fpga_manager *mgr; @@ -39,20 +40,18 @@ static int fme_region_probe(struct platform_device *pdev) if (IS_ERR(mgr)) return -EPROBE_DEFER; - region = devm_fpga_region_create(dev, mgr, fme_region_get_bridges); - if (!region) { - ret = -ENOMEM; + info.mgr = mgr; + info.compat_id = mgr->compat_id; + info.get_bridges = fme_region_get_bridges; + info.priv = pdata; + region = fpga_region_register_full(dev, &info); + if (IS_ERR(region)) { + ret = PTR_ERR(region); goto eprobe_mgr_put; } - region->priv = pdata; - region->compat_id = mgr->compat_id; platform_set_drvdata(pdev, region); - ret = fpga_region_register(region); - if (ret) - goto eprobe_mgr_put; - dev_dbg(dev, "DFL FME FPGA Region probed\n"); return 0; diff --git a/drivers/fpga/dfl.c b/drivers/fpga/dfl.c index f86666cf2c6a..599bb21d86af 100644 --- a/drivers/fpga/dfl.c +++ b/drivers/fpga/dfl.c @@ -1407,19 +1407,15 @@ dfl_fpga_feature_devs_enumerate(struct dfl_fpga_enum_info *info) if (!cdev) return ERR_PTR(-ENOMEM); - cdev->region = devm_fpga_region_create(info->dev, NULL, NULL); - if (!cdev->region) { - ret = -ENOMEM; - goto free_cdev_exit; - } - cdev->parent = info->dev; mutex_init(&cdev->lock); INIT_LIST_HEAD(&cdev->port_dev_list); - ret = fpga_region_register(cdev->region); - if (ret) + cdev->region = fpga_region_register(info->dev, NULL, NULL); + if (IS_ERR(cdev->region)) { + ret = PTR_ERR(cdev->region); goto free_cdev_exit; + } /* create and init build info for enumeration */ binfo = devm_kzalloc(info->dev, sizeof(*binfo), GFP_KERNEL); diff --git a/drivers/fpga/fpga-region.c b/drivers/fpga/fpga-region.c index a4838715221f..b0ac18de4885 100644 --- a/drivers/fpga/fpga-region.c +++ b/drivers/fpga/fpga-region.c @@ -180,39 +180,42 @@ static struct attribute *fpga_region_attrs[] = { ATTRIBUTE_GROUPS(fpga_region); /** - * fpga_region_create - alloc and init a struct fpga_region + * fpga_region_register_full - create and register an FPGA Region device * @parent: device parent - * @mgr: manager that programs this region - * @get_bridges: optional function to get bridges to a list - * - * The caller of this function is responsible for freeing the resulting region - * struct with fpga_region_free(). Using devm_fpga_region_create() instead is - * recommended. + * @info: parameters for FPGA Region * - * Return: struct fpga_region or NULL + * Return: struct fpga_region or ERR_PTR() */ -struct fpga_region -*fpga_region_create(struct device *parent, - struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)) +struct fpga_region * +fpga_region_register_full(struct device *parent, const struct fpga_region_info *info) { struct fpga_region *region; int id, ret = 0; + if (!info) { + dev_err(parent, + "Attempt to register without required info structure\n"); + return ERR_PTR(-EINVAL); + } + region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) - return NULL; + return ERR_PTR(-ENOMEM); id = ida_simple_get(&fpga_region_ida, 0, 0, GFP_KERNEL); - if (id < 0) + if (id < 0) { + ret = id; goto err_free; + } + + region->mgr = info->mgr; + region->compat_id = info->compat_id; + region->priv = info->priv; + region->get_bridges = info->get_bridges; - region->mgr = mgr; - region->get_bridges = get_bridges; mutex_init(®ion->mutex); INIT_LIST_HEAD(®ion->bridge_list); - device_initialize(®ion->dev); region->dev.class = fpga_region_class; region->dev.parent = parent; region->dev.of_node = parent->of_node; @@ -222,6 +225,12 @@ struct fpga_region if (ret) goto err_remove; + ret = device_register(®ion->dev); + if (ret) { + put_device(®ion->dev); + return ERR_PTR(ret); + } + return region; err_remove: @@ -229,76 +238,32 @@ err_remove: err_free: kfree(region); - return NULL; -} -EXPORT_SYMBOL_GPL(fpga_region_create); - -/** - * fpga_region_free - free an FPGA region created by fpga_region_create() - * @region: FPGA region - */ -void fpga_region_free(struct fpga_region *region) -{ - ida_simple_remove(&fpga_region_ida, region->dev.id); - kfree(region); -} -EXPORT_SYMBOL_GPL(fpga_region_free); - -static void devm_fpga_region_release(struct device *dev, void *res) -{ - struct fpga_region *region = *(struct fpga_region **)res; - - fpga_region_free(region); + return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(fpga_region_register_full); /** - * devm_fpga_region_create - create and initialize a managed FPGA region struct + * fpga_region_register - create and register an FPGA Region device * @parent: device parent * @mgr: manager that programs this region * @get_bridges: optional function to get bridges to a list * - * This function is intended for use in an FPGA region driver's probe function. - * After the region driver creates the region struct with - * devm_fpga_region_create(), it should register it with fpga_region_register(). - * The region driver's remove function should call fpga_region_unregister(). - * The region struct allocated with this function will be freed automatically on - * driver detach. This includes the case of a probe function returning error - * before calling fpga_region_register(), the struct will still get cleaned up. + * This simple version of the register function should be sufficient for most users. + * The fpga_region_register_full() function is available for users that need to + * pass additional, optional parameters. * - * Return: struct fpga_region or NULL + * Return: struct fpga_region or ERR_PTR() */ -struct fpga_region -*devm_fpga_region_create(struct device *parent, - struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)) +struct fpga_region * +fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)) { - struct fpga_region **ptr, *region; - - ptr = devres_alloc(devm_fpga_region_release, sizeof(*ptr), GFP_KERNEL); - if (!ptr) - return NULL; + struct fpga_region_info info = { 0 }; - region = fpga_region_create(parent, mgr, get_bridges); - if (!region) { - devres_free(ptr); - } else { - *ptr = region; - devres_add(parent, ptr); - } + info.mgr = mgr; + info.get_bridges = get_bridges; - return region; -} -EXPORT_SYMBOL_GPL(devm_fpga_region_create); - -/** - * fpga_region_register - register an FPGA region - * @region: FPGA region - * - * Return: 0 or -errno - */ -int fpga_region_register(struct fpga_region *region) -{ - return device_add(®ion->dev); + return fpga_region_register_full(parent, &info); } EXPORT_SYMBOL_GPL(fpga_region_register); @@ -316,6 +281,10 @@ EXPORT_SYMBOL_GPL(fpga_region_unregister); static void fpga_region_dev_release(struct device *dev) { + struct fpga_region *region = to_fpga_region(dev); + + ida_simple_remove(&fpga_region_ida, region->dev.id); + kfree(region); } /** diff --git a/drivers/fpga/of-fpga-region.c b/drivers/fpga/of-fpga-region.c index e3c25576b6b9..9c662db1c508 100644 --- a/drivers/fpga/of-fpga-region.c +++ b/drivers/fpga/of-fpga-region.c @@ -405,16 +405,12 @@ static int of_fpga_region_probe(struct platform_device *pdev) if (IS_ERR(mgr)) return -EPROBE_DEFER; - region = devm_fpga_region_create(dev, mgr, of_fpga_region_get_bridges); - if (!region) { - ret = -ENOMEM; + region = fpga_region_register(dev, mgr, of_fpga_region_get_bridges); + if (IS_ERR(region)) { + ret = PTR_ERR(region); goto eprobe_mgr_put; } - ret = fpga_region_register(region); - if (ret) - goto eprobe_mgr_put; - of_platform_populate(np, fpga_region_of_match, NULL, ®ion->dev); platform_set_drvdata(pdev, region); diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h index 27cb706275db..3b87f232425c 100644 --- a/include/linux/fpga/fpga-region.h +++ b/include/linux/fpga/fpga-region.h @@ -7,6 +7,27 @@ #include #include +struct fpga_region; + +/** + * struct fpga_region_info - collection of parameters an FPGA Region + * @mgr: fpga region manager + * @compat_id: FPGA region id for compatibility check. + * @priv: fpga region private data + * @get_bridges: optional function to get bridges to a list + * + * fpga_region_info contains parameters for the register_full function. + * These are separated into an info structure because they some are optional + * others could be added to in the future. The info structure facilitates + * maintaining a stable API. + */ +struct fpga_region_info { + struct fpga_manager *mgr; + struct fpga_compat_id *compat_id; + void *priv; + int (*get_bridges)(struct fpga_region *region); +}; + /** * struct fpga_region - FPGA Region structure * @dev: FPGA Region device @@ -37,15 +58,12 @@ struct fpga_region *fpga_region_class_find( int fpga_region_program_fpga(struct fpga_region *region); -struct fpga_region -*fpga_region_create(struct device *dev, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); -void fpga_region_free(struct fpga_region *region); -int fpga_region_register(struct fpga_region *region); -void fpga_region_unregister(struct fpga_region *region); +struct fpga_region * +fpga_region_register_full(struct device *parent, const struct fpga_region_info *info); -struct fpga_region -*devm_fpga_region_create(struct device *dev, struct fpga_manager *mgr, - int (*get_bridges)(struct fpga_region *)); +struct fpga_region * +fpga_region_register(struct device *parent, struct fpga_manager *mgr, + int (*get_bridges)(struct fpga_region *)); +void fpga_region_unregister(struct fpga_region *region); #endif /* _FPGA_REGION_H */ -- cgit v1.2.3 From 306456c21c792ac633e660bc45f0854b612a0e98 Mon Sep 17 00:00:00 2001 From: Matti Vaittinen Date: Tue, 16 Nov 2021 14:54:35 +0200 Subject: mfd: bd70528: Drop BD70528 support The only known BD70528 use-cases are such that the PMIC is controlled from separate MCU which is not running Linux. I am not aware of any Linux driver users. Furthermore, it seems there is no demand for this IC. Let's ease the maintenance burden and drop the driver. We can always add it back if there is sudden need for it. Signed-off-by: Matti Vaittinen Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/cf7dfd98b3403ad363b2b48b57bdbfd57a6416cb.1637066805.git.matti.vaittinen@fi.rohmeurope.com --- drivers/mfd/Kconfig | 17 -- drivers/mfd/Makefile | 1 - drivers/mfd/rohm-bd70528.c | 314 ------------------------------- include/linux/mfd/rohm-bd70528.h | 389 --------------------------------------- include/linux/mfd/rohm-generic.h | 1 - 5 files changed, 722 deletions(-) delete mode 100644 drivers/mfd/rohm-bd70528.c delete mode 100644 include/linux/mfd/rohm-bd70528.h (limited to 'include/linux') diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index 3fb480818599..34c7d9d6b580 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1945,23 +1945,6 @@ config MFD_ROHM_BD718XX NXP i.MX8. It contains 8 BUCK outputs and 7 LDOs, voltage monitoring and emergency shut down as well as 32,768KHz clock output. -config MFD_ROHM_BD70528 - tristate "ROHM BD70528 Power Management IC" - depends on I2C=y - depends on OF - select REGMAP_I2C - select REGMAP_IRQ - select MFD_CORE - help - Select this option to get support for the ROHM BD70528 Power - Management IC. BD71837 is general purpose single-chip power - management IC for battery-powered portable devices. It contains - 3 ultra-low current consumption buck converters, 3 LDOs and 2 LED - drivers. Also included are 4 GPIOs, a real-time clock (RTC), a 32kHz - crystal oscillator, high-accuracy VREF for use with an external ADC, - 10 bits SAR ADC for battery temperature monitor and 1S battery - charger. - config MFD_ROHM_BD71828 tristate "ROHM BD71828 and BD71815 Power Management IC" depends on I2C=y diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile index 0b1b629aef3e..4d53e951a92d 100644 --- a/drivers/mfd/Makefile +++ b/drivers/mfd/Makefile @@ -257,7 +257,6 @@ obj-$(CONFIG_MFD_STM32_TIMERS) += stm32-timers.o obj-$(CONFIG_MFD_MXS_LRADC) += mxs-lradc.o obj-$(CONFIG_MFD_SC27XX_PMIC) += sprd-sc27xx-spi.o obj-$(CONFIG_RAVE_SP_CORE) += rave-sp.o -obj-$(CONFIG_MFD_ROHM_BD70528) += rohm-bd70528.o obj-$(CONFIG_MFD_ROHM_BD71828) += rohm-bd71828.o obj-$(CONFIG_MFD_ROHM_BD718XX) += rohm-bd718x7.o obj-$(CONFIG_MFD_ROHM_BD957XMUF) += rohm-bd9576.o diff --git a/drivers/mfd/rohm-bd70528.c b/drivers/mfd/rohm-bd70528.c deleted file mode 100644 index 5c44d3b77b3e..000000000000 --- a/drivers/mfd/rohm-bd70528.c +++ /dev/null @@ -1,314 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -// -// Copyright (C) 2019 ROHM Semiconductors -// -// ROHM BD70528 PMIC driver - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define BD70528_NUM_OF_GPIOS 4 - -static const struct resource rtc_irqs[] = { - DEFINE_RES_IRQ_NAMED(BD70528_INT_RTC_ALARM, "bd70528-rtc-alm"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_ELPS_TIM, "bd70528-elapsed-timer"), -}; - -static const struct resource charger_irqs[] = { - DEFINE_RES_IRQ_NAMED(BD70528_INT_BAT_OV_RES, "bd70528-bat-ov-res"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BAT_OV_DET, "bd70528-bat-ov-det"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DBAT_DET, "bd70528-bat-dead"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BATTSD_COLD_RES, "bd70528-bat-warmed"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BATTSD_COLD_DET, "bd70528-bat-cold"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BATTSD_HOT_RES, "bd70528-bat-cooled"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BATTSD_HOT_DET, "bd70528-bat-hot"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_CHG_TSD, "bd70528-chg-tshd"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BAT_RMV, "bd70528-bat-removed"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_BAT_DET, "bd70528-bat-detected"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DCIN2_OV_RES, "bd70528-dcin2-ov-res"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DCIN2_OV_DET, "bd70528-dcin2-ov-det"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DCIN2_RMV, "bd70528-dcin2-removed"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DCIN2_DET, "bd70528-dcin2-detected"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DCIN1_RMV, "bd70528-dcin1-removed"), - DEFINE_RES_IRQ_NAMED(BD70528_INT_DCIN1_DET, "bd70528-dcin1-detected"), -}; - -static struct mfd_cell bd70528_mfd_cells[] = { - { .name = "bd70528-pmic", }, - { .name = "bd70528-gpio", }, - /* - * We use BD71837 driver to drive the clock block. Only differences to - * BD70528 clock gate are the register address and mask. - */ - { .name = "bd70528-clk", }, - { .name = "bd70528-wdt", }, - { - .name = "bd70528-power", - .resources = charger_irqs, - .num_resources = ARRAY_SIZE(charger_irqs), - }, { - .name = "bd70528-rtc", - .resources = rtc_irqs, - .num_resources = ARRAY_SIZE(rtc_irqs), - }, -}; - -static const struct regmap_range volatile_ranges[] = { - { - .range_min = BD70528_REG_INT_MAIN, - .range_max = BD70528_REG_INT_OP_FAIL, - }, { - .range_min = BD70528_REG_RTC_COUNT_H, - .range_max = BD70528_REG_RTC_ALM_REPEAT, - }, { - /* - * WDT control reg is special. Magic values must be written to - * it in order to change the control. Should not be cached. - */ - .range_min = BD70528_REG_WDT_CTRL, - .range_max = BD70528_REG_WDT_CTRL, - }, { - /* - * BD70528 also contains a few other registers which require - * magic sequences to be written in order to update the value. - * At least SHIPMODE, HWRESET, WARMRESET,and STANDBY - */ - .range_min = BD70528_REG_SHIPMODE, - .range_max = BD70528_REG_STANDBY, - }, -}; - -static const struct regmap_access_table volatile_regs = { - .yes_ranges = &volatile_ranges[0], - .n_yes_ranges = ARRAY_SIZE(volatile_ranges), -}; - -static struct regmap_config bd70528_regmap = { - .reg_bits = 8, - .val_bits = 8, - .volatile_table = &volatile_regs, - .max_register = BD70528_MAX_REGISTER, - .cache_type = REGCACHE_RBTREE, -}; - -/* - * Mapping of main IRQ register bits to sub-IRQ register offsets so that we can - * access corect sub-IRQ registers based on bits that are set in main IRQ - * register. - */ - -static unsigned int bit0_offsets[] = {0}; /* Shutdown */ -static unsigned int bit1_offsets[] = {1}; /* Power failure */ -static unsigned int bit2_offsets[] = {2}; /* VR FAULT */ -static unsigned int bit3_offsets[] = {3}; /* PMU interrupts */ -static unsigned int bit4_offsets[] = {4, 5}; /* Charger 1 and Charger 2 */ -static unsigned int bit5_offsets[] = {6}; /* RTC */ -static unsigned int bit6_offsets[] = {7}; /* GPIO */ -static unsigned int bit7_offsets[] = {8}; /* Invalid operation */ - -static struct regmap_irq_sub_irq_map bd70528_sub_irq_offsets[] = { - REGMAP_IRQ_MAIN_REG_OFFSET(bit0_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit1_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit2_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit3_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit4_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit5_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit6_offsets), - REGMAP_IRQ_MAIN_REG_OFFSET(bit7_offsets), -}; - -static struct regmap_irq bd70528_irqs[] = { - REGMAP_IRQ_REG(BD70528_INT_LONGPUSH, 0, BD70528_INT_LONGPUSH_MASK), - REGMAP_IRQ_REG(BD70528_INT_WDT, 0, BD70528_INT_WDT_MASK), - REGMAP_IRQ_REG(BD70528_INT_HWRESET, 0, BD70528_INT_HWRESET_MASK), - REGMAP_IRQ_REG(BD70528_INT_RSTB_FAULT, 0, BD70528_INT_RSTB_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_VBAT_UVLO, 0, BD70528_INT_VBAT_UVLO_MASK), - REGMAP_IRQ_REG(BD70528_INT_TSD, 0, BD70528_INT_TSD_MASK), - REGMAP_IRQ_REG(BD70528_INT_RSTIN, 0, BD70528_INT_RSTIN_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK1_FAULT, 1, - BD70528_INT_BUCK1_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK2_FAULT, 1, - BD70528_INT_BUCK2_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK3_FAULT, 1, - BD70528_INT_BUCK3_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_LDO1_FAULT, 1, BD70528_INT_LDO1_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_LDO2_FAULT, 1, BD70528_INT_LDO2_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_LDO3_FAULT, 1, BD70528_INT_LDO3_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_LED1_FAULT, 1, BD70528_INT_LED1_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_LED2_FAULT, 1, BD70528_INT_LED2_FAULT_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK1_OCP, 2, BD70528_INT_BUCK1_OCP_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK2_OCP, 2, BD70528_INT_BUCK2_OCP_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK3_OCP, 2, BD70528_INT_BUCK3_OCP_MASK), - REGMAP_IRQ_REG(BD70528_INT_LED1_OCP, 2, BD70528_INT_LED1_OCP_MASK), - REGMAP_IRQ_REG(BD70528_INT_LED2_OCP, 2, BD70528_INT_LED2_OCP_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK1_FULLON, 2, - BD70528_INT_BUCK1_FULLON_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK2_FULLON, 2, - BD70528_INT_BUCK2_FULLON_MASK), - REGMAP_IRQ_REG(BD70528_INT_SHORTPUSH, 3, BD70528_INT_SHORTPUSH_MASK), - REGMAP_IRQ_REG(BD70528_INT_AUTO_WAKEUP, 3, - BD70528_INT_AUTO_WAKEUP_MASK), - REGMAP_IRQ_REG(BD70528_INT_STATE_CHANGE, 3, - BD70528_INT_STATE_CHANGE_MASK), - REGMAP_IRQ_REG(BD70528_INT_BAT_OV_RES, 4, BD70528_INT_BAT_OV_RES_MASK), - REGMAP_IRQ_REG(BD70528_INT_BAT_OV_DET, 4, BD70528_INT_BAT_OV_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_DBAT_DET, 4, BD70528_INT_DBAT_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_BATTSD_COLD_RES, 4, - BD70528_INT_BATTSD_COLD_RES_MASK), - REGMAP_IRQ_REG(BD70528_INT_BATTSD_COLD_DET, 4, - BD70528_INT_BATTSD_COLD_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_BATTSD_HOT_RES, 4, - BD70528_INT_BATTSD_HOT_RES_MASK), - REGMAP_IRQ_REG(BD70528_INT_BATTSD_HOT_DET, 4, - BD70528_INT_BATTSD_HOT_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_CHG_TSD, 4, BD70528_INT_CHG_TSD_MASK), - REGMAP_IRQ_REG(BD70528_INT_BAT_RMV, 5, BD70528_INT_BAT_RMV_MASK), - REGMAP_IRQ_REG(BD70528_INT_BAT_DET, 5, BD70528_INT_BAT_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_DCIN2_OV_RES, 5, - BD70528_INT_DCIN2_OV_RES_MASK), - REGMAP_IRQ_REG(BD70528_INT_DCIN2_OV_DET, 5, - BD70528_INT_DCIN2_OV_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_DCIN2_RMV, 5, BD70528_INT_DCIN2_RMV_MASK), - REGMAP_IRQ_REG(BD70528_INT_DCIN2_DET, 5, BD70528_INT_DCIN2_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_DCIN1_RMV, 5, BD70528_INT_DCIN1_RMV_MASK), - REGMAP_IRQ_REG(BD70528_INT_DCIN1_DET, 5, BD70528_INT_DCIN1_DET_MASK), - REGMAP_IRQ_REG(BD70528_INT_RTC_ALARM, 6, BD70528_INT_RTC_ALARM_MASK), - REGMAP_IRQ_REG(BD70528_INT_ELPS_TIM, 6, BD70528_INT_ELPS_TIM_MASK), - REGMAP_IRQ_REG(BD70528_INT_GPIO0, 7, BD70528_INT_GPIO0_MASK), - REGMAP_IRQ_REG(BD70528_INT_GPIO1, 7, BD70528_INT_GPIO1_MASK), - REGMAP_IRQ_REG(BD70528_INT_GPIO2, 7, BD70528_INT_GPIO2_MASK), - REGMAP_IRQ_REG(BD70528_INT_GPIO3, 7, BD70528_INT_GPIO3_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK1_DVS_OPFAIL, 8, - BD70528_INT_BUCK1_DVS_OPFAIL_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK2_DVS_OPFAIL, 8, - BD70528_INT_BUCK2_DVS_OPFAIL_MASK), - REGMAP_IRQ_REG(BD70528_INT_BUCK3_DVS_OPFAIL, 8, - BD70528_INT_BUCK3_DVS_OPFAIL_MASK), - REGMAP_IRQ_REG(BD70528_INT_LED1_VOLT_OPFAIL, 8, - BD70528_INT_LED1_VOLT_OPFAIL_MASK), - REGMAP_IRQ_REG(BD70528_INT_LED2_VOLT_OPFAIL, 8, - BD70528_INT_LED2_VOLT_OPFAIL_MASK), -}; - -static struct regmap_irq_chip bd70528_irq_chip = { - .name = "bd70528_irq", - .main_status = BD70528_REG_INT_MAIN, - .irqs = &bd70528_irqs[0], - .num_irqs = ARRAY_SIZE(bd70528_irqs), - .status_base = BD70528_REG_INT_SHDN, - .mask_base = BD70528_REG_INT_SHDN_MASK, - .ack_base = BD70528_REG_INT_SHDN, - .type_base = BD70528_REG_GPIO1_IN, - .init_ack_masked = true, - .num_regs = 9, - .num_main_regs = 1, - .num_type_reg = 4, - .sub_reg_offsets = &bd70528_sub_irq_offsets[0], - .num_main_status_bits = 8, - .irq_reg_stride = 1, -}; - -static int bd70528_i2c_probe(struct i2c_client *i2c, - const struct i2c_device_id *id) -{ - struct bd70528_data *bd70528; - struct regmap_irq_chip_data *irq_data; - int ret, i; - - if (!i2c->irq) { - dev_err(&i2c->dev, "No IRQ configured\n"); - return -EINVAL; - } - - bd70528 = devm_kzalloc(&i2c->dev, sizeof(*bd70528), GFP_KERNEL); - if (!bd70528) - return -ENOMEM; - - mutex_init(&bd70528->rtc_timer_lock); - - dev_set_drvdata(&i2c->dev, &bd70528->chip); - - bd70528->chip.regmap = devm_regmap_init_i2c(i2c, &bd70528_regmap); - if (IS_ERR(bd70528->chip.regmap)) { - dev_err(&i2c->dev, "Failed to initialize Regmap\n"); - return PTR_ERR(bd70528->chip.regmap); - } - - /* - * Disallow type setting for all IRQs by default as most of them do not - * support setting type. - */ - for (i = 0; i < ARRAY_SIZE(bd70528_irqs); i++) - bd70528_irqs[i].type.types_supported = 0; - - /* Set IRQ typesetting information for GPIO pins 0 - 3 */ - for (i = 0; i < BD70528_NUM_OF_GPIOS; i++) { - struct regmap_irq_type *type; - - type = &bd70528_irqs[BD70528_INT_GPIO0 + i].type; - type->type_reg_offset = 2 * i; - type->type_rising_val = 0x20; - type->type_falling_val = 0x10; - type->type_level_high_val = 0x40; - type->type_level_low_val = 0x50; - type->types_supported = (IRQ_TYPE_EDGE_BOTH | - IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW); - } - - ret = devm_regmap_add_irq_chip(&i2c->dev, bd70528->chip.regmap, - i2c->irq, IRQF_ONESHOT, 0, - &bd70528_irq_chip, &irq_data); - if (ret) { - dev_err(&i2c->dev, "Failed to add IRQ chip\n"); - return ret; - } - dev_dbg(&i2c->dev, "Registered %d IRQs for chip\n", - bd70528_irq_chip.num_irqs); - - /* - * BD70528 IRQ controller is not touching the main mask register. - * So enable the GPIO block interrupts at main level. We can just leave - * them enabled as the IRQ controller should disable IRQs from - * sub-registers when IRQ is disabled or freed. - */ - ret = regmap_update_bits(bd70528->chip.regmap, - BD70528_REG_INT_MAIN_MASK, - BD70528_INT_GPIO_MASK, 0); - - ret = devm_mfd_add_devices(&i2c->dev, PLATFORM_DEVID_AUTO, - bd70528_mfd_cells, - ARRAY_SIZE(bd70528_mfd_cells), NULL, 0, - regmap_irq_get_domain(irq_data)); - if (ret) - dev_err(&i2c->dev, "Failed to create subdevices\n"); - - return ret; -} - -static const struct of_device_id bd70528_of_match[] = { - { .compatible = "rohm,bd70528", }, - { }, -}; -MODULE_DEVICE_TABLE(of, bd70528_of_match); - -static struct i2c_driver bd70528_drv = { - .driver = { - .name = "rohm-bd70528", - .of_match_table = bd70528_of_match, - }, - .probe = &bd70528_i2c_probe, -}; - -module_i2c_driver(bd70528_drv); - -MODULE_AUTHOR("Matti Vaittinen "); -MODULE_DESCRIPTION("ROHM BD70528 Power Management IC driver"); -MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/rohm-bd70528.h b/include/linux/mfd/rohm-bd70528.h deleted file mode 100644 index 4a5966475a35..000000000000 --- a/include/linux/mfd/rohm-bd70528.h +++ /dev/null @@ -1,389 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Copyright (C) 2018 ROHM Semiconductors */ - -#ifndef __LINUX_MFD_BD70528_H__ -#define __LINUX_MFD_BD70528_H__ - -#include -#include -#include -#include -#include - -enum { - BD70528_BUCK1, - BD70528_BUCK2, - BD70528_BUCK3, - BD70528_LDO1, - BD70528_LDO2, - BD70528_LDO3, - BD70528_LED1, - BD70528_LED2, -}; - -struct bd70528_data { - struct rohm_regmap_dev chip; - struct mutex rtc_timer_lock; -}; - -#define BD70528_BUCK_VOLTS 0x10 -#define BD70528_LDO_VOLTS 0x20 - -#define BD70528_REG_BUCK1_EN 0x0F -#define BD70528_REG_BUCK1_VOLT 0x15 -#define BD70528_REG_BUCK2_EN 0x10 -#define BD70528_REG_BUCK2_VOLT 0x16 -#define BD70528_REG_BUCK3_EN 0x11 -#define BD70528_REG_BUCK3_VOLT 0x17 -#define BD70528_REG_LDO1_EN 0x1b -#define BD70528_REG_LDO1_VOLT 0x1e -#define BD70528_REG_LDO2_EN 0x1c -#define BD70528_REG_LDO2_VOLT 0x1f -#define BD70528_REG_LDO3_EN 0x1d -#define BD70528_REG_LDO3_VOLT 0x20 -#define BD70528_REG_LED_CTRL 0x2b -#define BD70528_REG_LED_VOLT 0x29 -#define BD70528_REG_LED_EN 0x2a - -/* main irq registers */ -#define BD70528_REG_INT_MAIN 0x7E -#define BD70528_REG_INT_MAIN_MASK 0x74 - -/* 'sub irq' registers */ -#define BD70528_REG_INT_SHDN 0x7F -#define BD70528_REG_INT_PWR_FLT 0x80 -#define BD70528_REG_INT_VR_FLT 0x81 -#define BD70528_REG_INT_MISC 0x82 -#define BD70528_REG_INT_BAT1 0x83 -#define BD70528_REG_INT_BAT2 0x84 -#define BD70528_REG_INT_RTC 0x85 -#define BD70528_REG_INT_GPIO 0x86 -#define BD70528_REG_INT_OP_FAIL 0x87 - -#define BD70528_REG_INT_SHDN_MASK 0x75 -#define BD70528_REG_INT_PWR_FLT_MASK 0x76 -#define BD70528_REG_INT_VR_FLT_MASK 0x77 -#define BD70528_REG_INT_MISC_MASK 0x78 -#define BD70528_REG_INT_BAT1_MASK 0x79 -#define BD70528_REG_INT_BAT2_MASK 0x7a -#define BD70528_REG_INT_RTC_MASK 0x7b -#define BD70528_REG_INT_GPIO_MASK 0x7c -#define BD70528_REG_INT_OP_FAIL_MASK 0x7d - -/* Reset related 'magic' registers */ -#define BD70528_REG_SHIPMODE 0x03 -#define BD70528_REG_HWRESET 0x04 -#define BD70528_REG_WARMRESET 0x05 -#define BD70528_REG_STANDBY 0x06 - -/* GPIO registers */ -#define BD70528_REG_GPIO_STATE 0x8F - -#define BD70528_REG_GPIO1_IN 0x4d -#define BD70528_REG_GPIO2_IN 0x4f -#define BD70528_REG_GPIO3_IN 0x51 -#define BD70528_REG_GPIO4_IN 0x53 -#define BD70528_REG_GPIO1_OUT 0x4e -#define BD70528_REG_GPIO2_OUT 0x50 -#define BD70528_REG_GPIO3_OUT 0x52 -#define BD70528_REG_GPIO4_OUT 0x54 - -/* RTC */ - -#define BD70528_REG_RTC_COUNT_H 0x2d -#define BD70528_REG_RTC_COUNT_L 0x2e -#define BD70528_REG_RTC_SEC 0x2f -#define BD70528_REG_RTC_MINUTE 0x30 -#define BD70528_REG_RTC_HOUR 0x31 -#define BD70528_REG_RTC_WEEK 0x32 -#define BD70528_REG_RTC_DAY 0x33 -#define BD70528_REG_RTC_MONTH 0x34 -#define BD70528_REG_RTC_YEAR 0x35 - -#define BD70528_REG_RTC_ALM_SEC 0x36 -#define BD70528_REG_RTC_ALM_START BD70528_REG_RTC_ALM_SEC -#define BD70528_REG_RTC_ALM_MINUTE 0x37 -#define BD70528_REG_RTC_ALM_HOUR 0x38 -#define BD70528_REG_RTC_ALM_WEEK 0x39 -#define BD70528_REG_RTC_ALM_DAY 0x3a -#define BD70528_REG_RTC_ALM_MONTH 0x3b -#define BD70528_REG_RTC_ALM_YEAR 0x3c -#define BD70528_REG_RTC_ALM_MASK 0x3d -#define BD70528_REG_RTC_ALM_REPEAT 0x3e -#define BD70528_REG_RTC_START BD70528_REG_RTC_SEC - -#define BD70528_REG_RTC_WAKE_SEC 0x43 -#define BD70528_REG_RTC_WAKE_START BD70528_REG_RTC_WAKE_SEC -#define BD70528_REG_RTC_WAKE_MIN 0x44 -#define BD70528_REG_RTC_WAKE_HOUR 0x45 -#define BD70528_REG_RTC_WAKE_CTRL 0x46 - -#define BD70528_REG_ELAPSED_TIMER_EN 0x42 -#define BD70528_REG_WAKE_EN 0x46 - -/* WDT registers */ -#define BD70528_REG_WDT_CTRL 0x4A -#define BD70528_REG_WDT_HOUR 0x49 -#define BD70528_REG_WDT_MINUTE 0x48 -#define BD70528_REG_WDT_SEC 0x47 - -/* Charger / Battery */ -#define BD70528_REG_CHG_CURR_STAT 0x59 -#define BD70528_REG_CHG_BAT_STAT 0x57 -#define BD70528_REG_CHG_BAT_TEMP 0x58 -#define BD70528_REG_CHG_IN_STAT 0x56 -#define BD70528_REG_CHG_DCIN_ILIM 0x5d -#define BD70528_REG_CHG_CHG_CURR_WARM 0x61 -#define BD70528_REG_CHG_CHG_CURR_COLD 0x62 - -/* Masks for main IRQ register bits */ -enum { - BD70528_INT_SHDN, -#define BD70528_INT_SHDN_MASK BIT(BD70528_INT_SHDN) - BD70528_INT_PWR_FLT, -#define BD70528_INT_PWR_FLT_MASK BIT(BD70528_INT_PWR_FLT) - BD70528_INT_VR_FLT, -#define BD70528_INT_VR_FLT_MASK BIT(BD70528_INT_VR_FLT) - BD70528_INT_MISC, -#define BD70528_INT_MISC_MASK BIT(BD70528_INT_MISC) - BD70528_INT_BAT1, -#define BD70528_INT_BAT1_MASK BIT(BD70528_INT_BAT1) - BD70528_INT_RTC, -#define BD70528_INT_RTC_MASK BIT(BD70528_INT_RTC) - BD70528_INT_GPIO, -#define BD70528_INT_GPIO_MASK BIT(BD70528_INT_GPIO) - BD70528_INT_OP_FAIL, -#define BD70528_INT_OP_FAIL_MASK BIT(BD70528_INT_OP_FAIL) -}; - -/* IRQs */ -enum { - /* Shutdown register IRQs */ - BD70528_INT_LONGPUSH, - BD70528_INT_WDT, - BD70528_INT_HWRESET, - BD70528_INT_RSTB_FAULT, - BD70528_INT_VBAT_UVLO, - BD70528_INT_TSD, - BD70528_INT_RSTIN, - /* Power failure register IRQs */ - BD70528_INT_BUCK1_FAULT, - BD70528_INT_BUCK2_FAULT, - BD70528_INT_BUCK3_FAULT, - BD70528_INT_LDO1_FAULT, - BD70528_INT_LDO2_FAULT, - BD70528_INT_LDO3_FAULT, - BD70528_INT_LED1_FAULT, - BD70528_INT_LED2_FAULT, - /* VR FAULT register IRQs */ - BD70528_INT_BUCK1_OCP, - BD70528_INT_BUCK2_OCP, - BD70528_INT_BUCK3_OCP, - BD70528_INT_LED1_OCP, - BD70528_INT_LED2_OCP, - BD70528_INT_BUCK1_FULLON, - BD70528_INT_BUCK2_FULLON, - /* PMU register interrupts */ - BD70528_INT_SHORTPUSH, - BD70528_INT_AUTO_WAKEUP, - BD70528_INT_STATE_CHANGE, - /* Charger 1 register IRQs */ - BD70528_INT_BAT_OV_RES, - BD70528_INT_BAT_OV_DET, - BD70528_INT_DBAT_DET, - BD70528_INT_BATTSD_COLD_RES, - BD70528_INT_BATTSD_COLD_DET, - BD70528_INT_BATTSD_HOT_RES, - BD70528_INT_BATTSD_HOT_DET, - BD70528_INT_CHG_TSD, - /* Charger 2 register IRQs */ - BD70528_INT_BAT_RMV, - BD70528_INT_BAT_DET, - BD70528_INT_DCIN2_OV_RES, - BD70528_INT_DCIN2_OV_DET, - BD70528_INT_DCIN2_RMV, - BD70528_INT_DCIN2_DET, - BD70528_INT_DCIN1_RMV, - BD70528_INT_DCIN1_DET, - /* RTC register IRQs */ - BD70528_INT_RTC_ALARM, - BD70528_INT_ELPS_TIM, - /* GPIO register IRQs */ - BD70528_INT_GPIO0, - BD70528_INT_GPIO1, - BD70528_INT_GPIO2, - BD70528_INT_GPIO3, - /* Invalid operation register IRQs */ - BD70528_INT_BUCK1_DVS_OPFAIL, - BD70528_INT_BUCK2_DVS_OPFAIL, - BD70528_INT_BUCK3_DVS_OPFAIL, - BD70528_INT_LED1_VOLT_OPFAIL, - BD70528_INT_LED2_VOLT_OPFAIL, -}; - -/* Masks */ -#define BD70528_INT_LONGPUSH_MASK 0x1 -#define BD70528_INT_WDT_MASK 0x2 -#define BD70528_INT_HWRESET_MASK 0x4 -#define BD70528_INT_RSTB_FAULT_MASK 0x8 -#define BD70528_INT_VBAT_UVLO_MASK 0x10 -#define BD70528_INT_TSD_MASK 0x20 -#define BD70528_INT_RSTIN_MASK 0x40 - -#define BD70528_INT_BUCK1_FAULT_MASK 0x1 -#define BD70528_INT_BUCK2_FAULT_MASK 0x2 -#define BD70528_INT_BUCK3_FAULT_MASK 0x4 -#define BD70528_INT_LDO1_FAULT_MASK 0x8 -#define BD70528_INT_LDO2_FAULT_MASK 0x10 -#define BD70528_INT_LDO3_FAULT_MASK 0x20 -#define BD70528_INT_LED1_FAULT_MASK 0x40 -#define BD70528_INT_LED2_FAULT_MASK 0x80 - -#define BD70528_INT_BUCK1_OCP_MASK 0x1 -#define BD70528_INT_BUCK2_OCP_MASK 0x2 -#define BD70528_INT_BUCK3_OCP_MASK 0x4 -#define BD70528_INT_LED1_OCP_MASK 0x8 -#define BD70528_INT_LED2_OCP_MASK 0x10 -#define BD70528_INT_BUCK1_FULLON_MASK 0x20 -#define BD70528_INT_BUCK2_FULLON_MASK 0x40 - -#define BD70528_INT_SHORTPUSH_MASK 0x1 -#define BD70528_INT_AUTO_WAKEUP_MASK 0x2 -#define BD70528_INT_STATE_CHANGE_MASK 0x10 - -#define BD70528_INT_BAT_OV_RES_MASK 0x1 -#define BD70528_INT_BAT_OV_DET_MASK 0x2 -#define BD70528_INT_DBAT_DET_MASK 0x4 -#define BD70528_INT_BATTSD_COLD_RES_MASK 0x8 -#define BD70528_INT_BATTSD_COLD_DET_MASK 0x10 -#define BD70528_INT_BATTSD_HOT_RES_MASK 0x20 -#define BD70528_INT_BATTSD_HOT_DET_MASK 0x40 -#define BD70528_INT_CHG_TSD_MASK 0x80 - -#define BD70528_INT_BAT_RMV_MASK 0x1 -#define BD70528_INT_BAT_DET_MASK 0x2 -#define BD70528_INT_DCIN2_OV_RES_MASK 0x4 -#define BD70528_INT_DCIN2_OV_DET_MASK 0x8 -#define BD70528_INT_DCIN2_RMV_MASK 0x10 -#define BD70528_INT_DCIN2_DET_MASK 0x20 -#define BD70528_INT_DCIN1_RMV_MASK 0x40 -#define BD70528_INT_DCIN1_DET_MASK 0x80 - -#define BD70528_INT_RTC_ALARM_MASK 0x1 -#define BD70528_INT_ELPS_TIM_MASK 0x2 - -#define BD70528_INT_GPIO0_MASK 0x1 -#define BD70528_INT_GPIO1_MASK 0x2 -#define BD70528_INT_GPIO2_MASK 0x4 -#define BD70528_INT_GPIO3_MASK 0x8 - -#define BD70528_INT_BUCK1_DVS_OPFAIL_MASK 0x1 -#define BD70528_INT_BUCK2_DVS_OPFAIL_MASK 0x2 -#define BD70528_INT_BUCK3_DVS_OPFAIL_MASK 0x4 -#define BD70528_INT_LED1_VOLT_OPFAIL_MASK 0x10 -#define BD70528_INT_LED2_VOLT_OPFAIL_MASK 0x20 - -#define BD70528_DEBOUNCE_MASK 0x3 - -#define BD70528_DEBOUNCE_DISABLE 0 -#define BD70528_DEBOUNCE_15MS 1 -#define BD70528_DEBOUNCE_30MS 2 -#define BD70528_DEBOUNCE_50MS 3 - -#define BD70528_GPIO_DRIVE_MASK 0x2 -#define BD70528_GPIO_PUSH_PULL 0x0 -#define BD70528_GPIO_OPEN_DRAIN 0x2 - -#define BD70528_GPIO_OUT_EN_MASK 0x80 -#define BD70528_GPIO_OUT_ENABLE 0x80 -#define BD70528_GPIO_OUT_DISABLE 0x0 - -#define BD70528_GPIO_OUT_HI 0x1 -#define BD70528_GPIO_OUT_LO 0x0 -#define BD70528_GPIO_OUT_MASK 0x1 - -#define BD70528_GPIO_IN_STATE_BASE 1 - -/* RTC masks to mask out reserved bits */ - -#define BD70528_MASK_ELAPSED_TIMER_EN 0x1 -/* Mask second, min and hour fields - * HW would support ALM irq for over 24h - * (by setting day, month and year too) - * but as we wish to keep this same as for - * wake-up we limit ALM to 24H and only - * unmask sec, min and hour - */ -#define BD70528_MASK_WAKE_EN 0x1 - -/* WDT masks */ -#define BD70528_MASK_WDT_EN 0x1 -#define BD70528_MASK_WDT_HOUR 0x1 -#define BD70528_MASK_WDT_MINUTE 0x7f -#define BD70528_MASK_WDT_SEC 0x7f - -#define BD70528_WDT_STATE_BIT 0x1 -#define BD70528_ELAPSED_STATE_BIT 0x2 -#define BD70528_WAKE_STATE_BIT 0x4 - -/* Charger masks */ -#define BD70528_MASK_CHG_STAT 0x7f -#define BD70528_MASK_CHG_BAT_TIMER 0x20 -#define BD70528_MASK_CHG_BAT_OVERVOLT 0x10 -#define BD70528_MASK_CHG_BAT_DETECT 0x1 -#define BD70528_MASK_CHG_DCIN1_UVLO 0x1 -#define BD70528_MASK_CHG_DCIN_ILIM 0x3f -#define BD70528_MASK_CHG_CHG_CURR 0x1f -#define BD70528_MASK_CHG_TRICKLE_CURR 0x10 - -/* - * Note, external battery register is the lonely rider at - * address 0xc5. See how to stuff that in the regmap - */ -#define BD70528_MAX_REGISTER 0x94 - -/* Buck control masks */ -#define BD70528_MASK_RUN_EN 0x4 -#define BD70528_MASK_STBY_EN 0x2 -#define BD70528_MASK_IDLE_EN 0x1 -#define BD70528_MASK_LED1_EN 0x1 -#define BD70528_MASK_LED2_EN 0x10 - -#define BD70528_MASK_BUCK_VOLT 0xf -#define BD70528_MASK_LDO_VOLT 0x1f -#define BD70528_MASK_LED1_VOLT 0x1 -#define BD70528_MASK_LED2_VOLT 0x10 - -/* Misc irq masks */ -#define BD70528_INT_MASK_SHORT_PUSH 1 -#define BD70528_INT_MASK_AUTO_WAKE 2 -#define BD70528_INT_MASK_POWER_STATE 4 - -#define BD70528_MASK_BUCK_RAMP 0x10 -#define BD70528_SIFT_BUCK_RAMP 4 - -#if IS_ENABLED(CONFIG_BD70528_WATCHDOG) - -int bd70528_wdt_set(struct rohm_regmap_dev *data, int enable, int *old_state); -void bd70528_wdt_lock(struct rohm_regmap_dev *data); -void bd70528_wdt_unlock(struct rohm_regmap_dev *data); - -#else /* CONFIG_BD70528_WATCHDOG */ - -static inline int bd70528_wdt_set(struct rohm_regmap_dev *data, int enable, - int *old_state) -{ - return 0; -} - -static inline void bd70528_wdt_lock(struct rohm_regmap_dev *data) -{ -} - -static inline void bd70528_wdt_unlock(struct rohm_regmap_dev *data) -{ -} - -#endif /* CONFIG_BD70528_WATCHDOG */ - -#endif /* __LINUX_MFD_BD70528_H__ */ diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h index 35b392a0d73a..8fb763a2265a 100644 --- a/include/linux/mfd/rohm-generic.h +++ b/include/linux/mfd/rohm-generic.h @@ -12,7 +12,6 @@ enum rohm_chip_type { ROHM_CHIP_TYPE_BD9573, ROHM_CHIP_TYPE_BD9574, ROHM_CHIP_TYPE_BD9576, - ROHM_CHIP_TYPE_BD70528, ROHM_CHIP_TYPE_BD71815, ROHM_CHIP_TYPE_BD71828, ROHM_CHIP_TYPE_BD71837, -- cgit v1.2.3 From a9c8f68ce2c37ced2f7a8667eda71b7753ede398 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 23 Nov 2021 21:27:22 +0200 Subject: spi: pxa2xx: Get rid of unused ->cs_control() Since the last user of the custom ->cs_control() gone, we may get rid of this legacy API completely. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211123192723.44537-2-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- Documentation/spi/pxa2xx.rst | 29 +++-------------------------- arch/arm/mach-pxa/stargate2.c | 2 +- drivers/spi/spi-pxa2xx.c | 18 ------------------ drivers/spi/spi-pxa2xx.h | 3 --- include/linux/spi/pxa2xx_spi.h | 4 ---- 5 files changed, 4 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/Documentation/spi/pxa2xx.rst b/Documentation/spi/pxa2xx.rst index 6312968acfe9..dfc7673ed15d 100644 --- a/Documentation/spi/pxa2xx.rst +++ b/Documentation/spi/pxa2xx.rst @@ -102,7 +102,7 @@ device. All fields are optional. u8 dma_burst_size; u32 timeout; u8 enable_loopback; - void (*cs_control)(u32 command); + int gpio_cs; }; The "pxa2xx_spi_chip.tx_threshold" and "pxa2xx_spi_chip.rx_threshold" fields are @@ -133,11 +133,6 @@ into internal loopback mode. In this mode the SSP controller internally connects the SSPTX pin to the SSPRX pin. This is useful for initial setup testing. -The "pxa2xx_spi_chip.cs_control" field is used to point to a board specific -function for asserting/deasserting a slave device chip select. If the field is -NULL, the pxa2xx_spi master controller driver assumes that the SSP port is -configured to use GPIO or SSPFRM instead. - NOTE: the SPI driver cannot control the chip select if SSPFRM is used, so the chipselect is dropped after each spi_transfer. Most devices need chip select asserted around the complete message. Use SSPFRM as a GPIO (through a descriptor) @@ -152,30 +147,12 @@ field. Below is a sample configuration using the PXA255 NSSP. :: - /* Chip Select control for the CS8415A SPI slave device */ - static void cs8415a_cs_control(u32 command) - { - if (command & PXA2XX_CS_ASSERT) - GPCR(2) = GPIO_bit(2); - else - GPSR(2) = GPIO_bit(2); - } - - /* Chip Select control for the CS8405A SPI slave device */ - static void cs8405a_cs_control(u32 command) - { - if (command & PXA2XX_CS_ASSERT) - GPCR(3) = GPIO_bit(3); - else - GPSR(3) = GPIO_bit(3); - } - static struct pxa2xx_spi_chip cs8415a_chip_info = { .tx_threshold = 8, /* SSP hardward FIFO threshold */ .rx_threshold = 8, /* SSP hardward FIFO threshold */ .dma_burst_size = 8, /* Byte wide transfers used so 8 byte bursts */ .timeout = 235, /* See Intel documentation */ - .cs_control = cs8415a_cs_control, /* Use external chip select */ + .gpio_cs = 2, /* Use external chip select */ }; static struct pxa2xx_spi_chip cs8405a_chip_info = { @@ -183,7 +160,7 @@ field. Below is a sample configuration using the PXA255 NSSP. .rx_threshold = 8, /* SSP hardward FIFO threshold */ .dma_burst_size = 8, /* Byte wide transfers used so 8 byte bursts */ .timeout = 235, /* See Intel documentation */ - .cs_control = cs8405a_cs_control, /* Use external chip select */ + .gpio_cs = 3, /* Use external chip select */ }; static struct spi_board_info streetracer_spi_board_info[] __initdata = { diff --git a/arch/arm/mach-pxa/stargate2.c b/arch/arm/mach-pxa/stargate2.c index 7ad627465768..8ca02ec1d44c 100644 --- a/arch/arm/mach-pxa/stargate2.c +++ b/arch/arm/mach-pxa/stargate2.c @@ -347,7 +347,7 @@ static struct pxa2xx_spi_controller pxa_ssp_master_2_info = { }; /* An upcoming kernel change will scrap SFRM usage so these - * drivers have been moved to use gpio's via cs_control */ + * drivers have been moved to use GPIOs */ static struct pxa2xx_spi_chip staccel_chip_info = { .tx_threshold = 8, .rx_threshold = 8, diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index ee3297dd532e..24196156c609 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -427,7 +427,6 @@ static void lpss_ssp_cs_control(struct spi_device *spi, bool enable) static void cs_assert(struct spi_device *spi) { - struct chip_data *chip = spi_get_ctldata(spi); struct driver_data *drv_data = spi_controller_get_devdata(spi->controller); @@ -436,18 +435,12 @@ static void cs_assert(struct spi_device *spi) return; } - if (chip->cs_control) { - chip->cs_control(PXA2XX_CS_ASSERT); - return; - } - if (is_lpss_ssp(drv_data)) lpss_ssp_cs_control(spi, true); } static void cs_deassert(struct spi_device *spi) { - struct chip_data *chip = spi_get_ctldata(spi); struct driver_data *drv_data = spi_controller_get_devdata(spi->controller); unsigned long timeout; @@ -461,11 +454,6 @@ static void cs_deassert(struct spi_device *spi) !time_after(jiffies, timeout)) cpu_relax(); - if (chip->cs_control) { - chip->cs_control(PXA2XX_CS_DEASSERT); - return; - } - if (is_lpss_ssp(drv_data)) lpss_ssp_cs_control(spi, false); } @@ -1204,12 +1192,6 @@ static int setup_cs(struct spi_device *spi, struct chip_data *chip, */ cleanup_cs(spi); - /* If ->cs_control() is provided, ignore GPIO chip select */ - if (chip_info->cs_control) { - chip->cs_control = chip_info->cs_control; - return 0; - } - if (gpio_is_valid(chip_info->gpio_cs)) { int gpio = chip_info->gpio_cs; int err; diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h index 4d77f4de6eda..45cdbbc71c4b 100644 --- a/drivers/spi/spi-pxa2xx.h +++ b/drivers/spi/spi-pxa2xx.h @@ -49,7 +49,6 @@ struct driver_data { int (*write)(struct driver_data *drv_data); int (*read)(struct driver_data *drv_data); irqreturn_t (*transfer_handler)(struct driver_data *drv_data); - void (*cs_control)(u32 command); void __iomem *lpss_base; @@ -67,8 +66,6 @@ struct chip_data { u32 threshold; u16 lpss_rx_threshold; u16 lpss_tx_threshold; - - void (*cs_control)(u32 command); }; static inline u32 pxa2xx_spi_read(const struct driver_data *drv_data, u32 reg) diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index eaab121ee575..42e06bfbc2a4 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -9,9 +9,6 @@ #include -#define PXA2XX_CS_ASSERT (0x01) -#define PXA2XX_CS_DEASSERT (0x02) - struct dma_chan; /* @@ -47,7 +44,6 @@ struct pxa2xx_spi_chip { u32 timeout; u8 enable_loopback; int gpio_cs; - void (*cs_control)(u32 command); }; #if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP) -- cgit v1.2.3 From 8393961c53b31078cfc877bc00eb0f67e1474edd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 23 Nov 2021 21:27:23 +0200 Subject: spi: pxa2xx: Get rid of unused enable_loopback member There is no user of the enable_loopback member in the struct pxa2xx_spi_chip. Remote this legacy member completely. The mentioned in the documentation the testing phase can be performed with spidev_test tool. Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211123192723.44537-3-andriy.shevchenko@linux.intel.com Signed-off-by: Mark Brown --- Documentation/spi/pxa2xx.rst | 6 ------ drivers/spi/spi-pxa2xx.c | 5 ++--- include/linux/spi/pxa2xx_spi.h | 1 - 3 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/Documentation/spi/pxa2xx.rst b/Documentation/spi/pxa2xx.rst index dfc7673ed15d..6347580826be 100644 --- a/Documentation/spi/pxa2xx.rst +++ b/Documentation/spi/pxa2xx.rst @@ -101,7 +101,6 @@ device. All fields are optional. u8 rx_threshold; u8 dma_burst_size; u32 timeout; - u8 enable_loopback; int gpio_cs; }; @@ -128,11 +127,6 @@ dependent on the SPI bus speed ("spi_board_info.max_speed_hz") and the specific slave device. Please note that the PXA2xx SSP 1 does not support trailing byte timeouts and must busy-wait any trailing bytes. -The "pxa2xx_spi_chip.enable_loopback" field is used to place the SSP porting -into internal loopback mode. In this mode the SSP controller internally -connects the SSPTX pin to the SSPRX pin. This is useful for initial setup -testing. - NOTE: the SPI driver cannot control the chip select if SSPFRM is used, so the chipselect is dropped after each spi_transfer. Most devices need chip select asserted around the complete message. Use SSPFRM as a GPIO (through a descriptor) diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c index 24196156c609..b3186bd0c2a8 100644 --- a/drivers/spi/spi-pxa2xx.c +++ b/drivers/spi/spi-pxa2xx.c @@ -1289,7 +1289,6 @@ static int setup(struct spi_device *spi) chip_info = spi->controller_data; /* chip_info isn't always needed */ - chip->cr1 = 0; if (chip_info) { if (chip_info->timeout) chip->timeout = chip_info->timeout; @@ -1300,9 +1299,9 @@ static int setup(struct spi_device *spi) if (chip_info->rx_threshold) rx_thres = chip_info->rx_threshold; chip->dma_threshold = 0; - if (chip_info->enable_loopback) - chip->cr1 = SSCR1_LBM; } + + chip->cr1 = 0; if (spi_controller_is_slave(drv_data->controller)) { chip->cr1 |= SSCR1_SCFR; chip->cr1 |= SSCR1_SCLKDIR; diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h index 42e06bfbc2a4..ca74dce36706 100644 --- a/include/linux/spi/pxa2xx_spi.h +++ b/include/linux/spi/pxa2xx_spi.h @@ -42,7 +42,6 @@ struct pxa2xx_spi_chip { u8 rx_threshold; u8 dma_burst_size; u32 timeout; - u8 enable_loopback; int gpio_cs; }; -- cgit v1.2.3 From b99658452355d316debee11079e8f1c6c1029355 Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Sun, 28 Nov 2021 17:57:37 -0800 Subject: net: dsa: ocelot: felix: utilize shared mscc-miim driver for indirect MDIO access Switch to a shared MDIO access implementation by way of the mdio-mscc-miim driver. Signed-off-by: Colin Foster Tested-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/Kconfig | 1 + drivers/net/dsa/ocelot/seville_vsc9953.c | 102 +++---------------------------- drivers/net/mdio/mdio-mscc-miim.c | 38 ++++++++---- include/linux/mdio/mdio-mscc-miim.h | 19 ++++++ 4 files changed, 56 insertions(+), 104 deletions(-) create mode 100644 include/linux/mdio/mdio-mscc-miim.h (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 9948544ba1c4..220b0b027b55 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -21,6 +21,7 @@ config NET_DSA_MSCC_SEVILLE depends on NET_VENDOR_MICROSEMI depends on HAS_IOMEM depends on PTP_1588_CLOCK_OPTIONAL + select MDIO_MSCC_MIIM select MSCC_OCELOT_SWITCH_LIB select NET_DSA_TAG_OCELOT_8021Q select NET_DSA_TAG_OCELOT diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index db124922c374..b9be889016ce 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -6,19 +6,14 @@ #include #include #include +#include +#include #include #include #include #include -#include #include "felix.h" -#define MSCC_MIIM_CMD_OPR_WRITE BIT(1) -#define MSCC_MIIM_CMD_OPR_READ BIT(2) -#define MSCC_MIIM_CMD_WRDATA_SHIFT 4 -#define MSCC_MIIM_CMD_REGAD_SHIFT 20 -#define MSCC_MIIM_CMD_PHYAD_SHIFT 25 -#define MSCC_MIIM_CMD_VLD BIT(31) #define VSC9953_VCAP_POLICER_BASE 11 #define VSC9953_VCAP_POLICER_MAX 31 #define VSC9953_VCAP_POLICER_BASE2 120 @@ -862,7 +857,6 @@ static struct vcap_props vsc9953_vcap_props[] = { #define VSC9953_INIT_TIMEOUT 50000 #define VSC9953_GCB_RST_SLEEP 100 #define VSC9953_SYS_RAMINIT_SLEEP 80 -#define VCS9953_MII_TIMEOUT 10000 static int vsc9953_gcb_soft_rst_status(struct ocelot *ocelot) { @@ -882,82 +876,6 @@ static int vsc9953_sys_ram_init_status(struct ocelot *ocelot) return val; } -static int vsc9953_gcb_miim_pending_status(struct ocelot *ocelot) -{ - int val; - - ocelot_field_read(ocelot, GCB_MIIM_MII_STATUS_PENDING, &val); - - return val; -} - -static int vsc9953_gcb_miim_busy_status(struct ocelot *ocelot) -{ - int val; - - ocelot_field_read(ocelot, GCB_MIIM_MII_STATUS_BUSY, &val); - - return val; -} - -static int vsc9953_mdio_write(struct mii_bus *bus, int phy_id, int regnum, - u16 value) -{ - struct ocelot *ocelot = bus->priv; - int err, cmd, val; - - /* Wait while MIIM controller becomes idle */ - err = readx_poll_timeout(vsc9953_gcb_miim_pending_status, ocelot, - val, !val, 10, VCS9953_MII_TIMEOUT); - if (err) { - dev_err(ocelot->dev, "MDIO write: pending timeout\n"); - goto out; - } - - cmd = MSCC_MIIM_CMD_VLD | (phy_id << MSCC_MIIM_CMD_PHYAD_SHIFT) | - (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | - (value << MSCC_MIIM_CMD_WRDATA_SHIFT) | - MSCC_MIIM_CMD_OPR_WRITE; - - ocelot_write(ocelot, cmd, GCB_MIIM_MII_CMD); - -out: - return err; -} - -static int vsc9953_mdio_read(struct mii_bus *bus, int phy_id, int regnum) -{ - struct ocelot *ocelot = bus->priv; - int err, cmd, val; - - /* Wait until MIIM controller becomes idle */ - err = readx_poll_timeout(vsc9953_gcb_miim_pending_status, ocelot, - val, !val, 10, VCS9953_MII_TIMEOUT); - if (err) { - dev_err(ocelot->dev, "MDIO read: pending timeout\n"); - goto out; - } - - /* Write the MIIM COMMAND register */ - cmd = MSCC_MIIM_CMD_VLD | (phy_id << MSCC_MIIM_CMD_PHYAD_SHIFT) | - (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | MSCC_MIIM_CMD_OPR_READ; - - ocelot_write(ocelot, cmd, GCB_MIIM_MII_CMD); - - /* Wait while read operation via the MIIM controller is in progress */ - err = readx_poll_timeout(vsc9953_gcb_miim_busy_status, ocelot, - val, !val, 10, VCS9953_MII_TIMEOUT); - if (err) { - dev_err(ocelot->dev, "MDIO read: busy timeout\n"); - goto out; - } - - val = ocelot_read(ocelot, GCB_MIIM_MII_DATA); - - err = val & 0xFFFF; -out: - return err; -} /* CORE_ENA is in SYS:SYSTEM:RESET_CFG * MEM_INIT is in SYS:SYSTEM:RESET_CFG @@ -1101,16 +1019,14 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) return -ENOMEM; } - bus = devm_mdiobus_alloc(dev); - if (!bus) - return -ENOMEM; + rc = mscc_miim_setup(dev, &bus, "VSC9953 internal MDIO bus", + ocelot->targets[GCB], + ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK]); - bus->name = "VSC9953 internal MDIO bus"; - bus->read = vsc9953_mdio_read; - bus->write = vsc9953_mdio_write; - bus->parent = dev; - bus->priv = ocelot; - snprintf(bus->id, MII_BUS_ID_SIZE, "%s-imdio", dev_name(dev)); + if (rc) { + dev_err(dev, "failed to setup MDIO bus\n"); + return rc; + } /* Needed in order to initialize the bus mutex lock */ rc = of_mdiobus_register(bus, NULL); diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index e016b32ad208..2d420c9d7520 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include @@ -37,7 +38,9 @@ struct mscc_miim_dev { struct regmap *regs; + int mii_status_offset; struct regmap *phy_regs; + int phy_reset_offset; }; /* When high resolution timers aren't built-in: we can't use usleep_range() as @@ -56,7 +59,8 @@ static int mscc_miim_status(struct mii_bus *bus) struct mscc_miim_dev *miim = bus->priv; int val, ret; - ret = regmap_read(miim->regs, MSCC_MIIM_REG_STATUS, &val); + ret = regmap_read(miim->regs, + MSCC_MIIM_REG_STATUS + miim->mii_status_offset, &val); if (ret < 0) { WARN_ONCE(1, "mscc miim status read error %d\n", ret); return ret; @@ -93,7 +97,9 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) if (ret) goto out; - ret = regmap_write(miim->regs, MSCC_MIIM_REG_CMD, MSCC_MIIM_CMD_VLD | + ret = regmap_write(miim->regs, + MSCC_MIIM_REG_CMD + miim->mii_status_offset, + MSCC_MIIM_CMD_VLD | (mii_id << MSCC_MIIM_CMD_PHYAD_SHIFT) | (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | MSCC_MIIM_CMD_OPR_READ); @@ -107,8 +113,8 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) if (ret) goto out; - ret = regmap_read(miim->regs, MSCC_MIIM_REG_DATA, &val); - + ret = regmap_read(miim->regs, + MSCC_MIIM_REG_DATA + miim->mii_status_offset, &val); if (ret < 0) { WARN_ONCE(1, "mscc miim read data reg error %d\n", ret); goto out; @@ -134,7 +140,9 @@ static int mscc_miim_write(struct mii_bus *bus, int mii_id, if (ret < 0) goto out; - ret = regmap_write(miim->regs, MSCC_MIIM_REG_CMD, MSCC_MIIM_CMD_VLD | + ret = regmap_write(miim->regs, + MSCC_MIIM_REG_CMD + miim->mii_status_offset, + MSCC_MIIM_CMD_VLD | (mii_id << MSCC_MIIM_CMD_PHYAD_SHIFT) | (regnum << MSCC_MIIM_CMD_REGAD_SHIFT) | (value << MSCC_MIIM_CMD_WRDATA_SHIFT) | @@ -149,16 +157,19 @@ out: static int mscc_miim_reset(struct mii_bus *bus) { struct mscc_miim_dev *miim = bus->priv; + int offset = miim->phy_reset_offset; int ret; if (miim->phy_regs) { - ret = regmap_write(miim->phy_regs, MSCC_PHY_REG_PHY_CFG, 0); + ret = regmap_write(miim->phy_regs, + MSCC_PHY_REG_PHY_CFG + offset, 0); if (ret < 0) { WARN_ONCE(1, "mscc reset set error %d\n", ret); return ret; } - ret = regmap_write(miim->phy_regs, MSCC_PHY_REG_PHY_CFG, 0x1ff); + ret = regmap_write(miim->phy_regs, + MSCC_PHY_REG_PHY_CFG + offset, 0x1ff); if (ret < 0) { WARN_ONCE(1, "mscc reset clear error %d\n", ret); return ret; @@ -176,8 +187,8 @@ static const struct regmap_config mscc_miim_regmap_config = { .reg_stride = 4, }; -static int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, - struct regmap *mii_regmap) +int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name, + struct regmap *mii_regmap, int status_offset) { struct mscc_miim_dev *miim; struct mii_bus *bus; @@ -186,7 +197,7 @@ static int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, if (!bus) return -ENOMEM; - bus->name = "mscc_miim"; + bus->name = name; bus->read = mscc_miim_read; bus->write = mscc_miim_write; bus->reset = mscc_miim_reset; @@ -198,9 +209,13 @@ static int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, *pbus = bus; miim->regs = mii_regmap; + miim->mii_status_offset = status_offset; + + *pbus = bus; return 0; } +EXPORT_SYMBOL(mscc_miim_setup); static int mscc_miim_probe(struct platform_device *pdev) { @@ -237,7 +252,7 @@ static int mscc_miim_probe(struct platform_device *pdev) return PTR_ERR(phy_regmap); } - ret = mscc_miim_setup(&pdev->dev, &bus, mii_regmap); + ret = mscc_miim_setup(&pdev->dev, &bus, "mscc_miim", mii_regmap, 0); if (ret < 0) { dev_err(&pdev->dev, "Unable to setup the MDIO bus\n"); return ret; @@ -245,6 +260,7 @@ static int mscc_miim_probe(struct platform_device *pdev) miim = bus->priv; miim->phy_regs = phy_regmap; + miim->phy_reset_offset = 0; ret = of_mdiobus_register(bus, pdev->dev.of_node); if (ret < 0) { diff --git a/include/linux/mdio/mdio-mscc-miim.h b/include/linux/mdio/mdio-mscc-miim.h new file mode 100644 index 000000000000..5b4ed2c3cbb9 --- /dev/null +++ b/include/linux/mdio/mdio-mscc-miim.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Driver for the MDIO interface of Microsemi network switches. + * + * Author: Colin Foster + * Copyright (C) 2021 Innovative Advantage + */ +#ifndef MDIO_MSCC_MIIM_H +#define MDIO_MSCC_MIIM_H + +#include +#include +#include + +int mscc_miim_setup(struct device *device, struct mii_bus **bus, + const char *name, struct regmap *mii_regmap, + int status_offset); + +#endif -- cgit v1.2.3 From 17247821ae9b40ea6df8d771cfca97d91675be93 Mon Sep 17 00:00:00 2001 From: Dario Binacchi Date: Thu, 25 Nov 2021 23:46:42 +0100 Subject: mfd: ti_am335x_tscadc: Drop the CNTRLREG_TSC_8WIRE macro In TI's reference manual description for the `AFE_Pen_Ctrl' bit-field of the TSC's CTRL register, there is no mention of 8-wire touchscreens. Even commit f0933a60d190 ("mfd: ti_am335x_tscadc: Update logic in CTRL register for 5-wire TS") says that the value of this bit-field must be the same for 4-wire and 8-wire touchscreens. So let's remove the CNTRLREG_TSC_8WIRE macro to avoid misunderstandings. Signed-off-by: Dario Binacchi Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211125224642.21011-5-dariobin@libero.it --- include/linux/mfd/ti_am335x_tscadc.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index ba13e043d910..4063b0614d90 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -103,7 +103,6 @@ #define CNTRLREG_TSC_AFE_CTRL(val) FIELD_PREP(GENMASK(6, 5), (val)) #define CNTRLREG_TSC_4WIRE CNTRLREG_TSC_AFE_CTRL(1) #define CNTRLREG_TSC_5WIRE CNTRLREG_TSC_AFE_CTRL(2) -#define CNTRLREG_TSC_8WIRE CNTRLREG_TSC_AFE_CTRL(3) #define CNTRLREG_TSC_ENB BIT(7) /*Control registers bitfields for MAGADC IP */ -- cgit v1.2.3 From 79478bf9ea9fa48d30836afa796ac13d8a0f320b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Nov 2021 07:13:54 +0100 Subject: block: move blk_rq_err_bytes to scsi blk_rq_err_bytes is only used by the scsi midlayer, so move it there. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20211117061404.331732-2-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 41 ----------------------------------------- drivers/scsi/scsi_lib.c | 42 +++++++++++++++++++++++++++++++++++++++++- include/linux/blk-mq.h | 3 --- 3 files changed, 41 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 1378d084c770..682b112f513f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1176,47 +1176,6 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); -/** - * blk_rq_err_bytes - determine number of bytes till the next failure boundary - * @rq: request to examine - * - * Description: - * A request could be merge of IOs which require different failure - * handling. This function determines the number of bytes which - * can be failed from the beginning of the request without - * crossing into area which need to be retried further. - * - * Return: - * The number of bytes to fail. - */ -unsigned int blk_rq_err_bytes(const struct request *rq) -{ - unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; - unsigned int bytes = 0; - struct bio *bio; - - if (!(rq->rq_flags & RQF_MIXED_MERGE)) - return blk_rq_bytes(rq); - - /* - * Currently the only 'mixing' which can happen is between - * different fastfail types. We can safely fail portions - * which have all the failfast bits that the first one has - - * the ones which are at least as eager to fail as the first - * one. - */ - for (bio = rq->bio; bio; bio = bio->bi_next) { - if ((bio->bi_opf & ff) != ff) - break; - bytes += bio->bi_iter.bi_size; - } - - /* this could lead to infinite loop */ - BUG_ON(blk_rq_bytes(rq) && !bytes); - return bytes; -} -EXPORT_SYMBOL_GPL(blk_rq_err_bytes); - static void update_io_ticks(struct block_device *part, unsigned long now, bool end) { diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 621d841d819a..5e8b5ecb3245 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -617,6 +617,46 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result) } } +/** + * scsi_rq_err_bytes - determine number of bytes till the next failure boundary + * @rq: request to examine + * + * Description: + * A request could be merge of IOs which require different failure + * handling. This function determines the number of bytes which + * can be failed from the beginning of the request without + * crossing into area which need to be retried further. + * + * Return: + * The number of bytes to fail. + */ +static unsigned int scsi_rq_err_bytes(const struct request *rq) +{ + unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + unsigned int bytes = 0; + struct bio *bio; + + if (!(rq->rq_flags & RQF_MIXED_MERGE)) + return blk_rq_bytes(rq); + + /* + * Currently the only 'mixing' which can happen is between + * different fastfail types. We can safely fail portions + * which have all the failfast bits that the first one has - + * the ones which are at least as eager to fail as the first + * one. + */ + for (bio = rq->bio; bio; bio = bio->bi_next) { + if ((bio->bi_opf & ff) != ff) + break; + bytes += bio->bi_iter.bi_size; + } + + /* this could lead to infinite loop */ + BUG_ON(blk_rq_bytes(rq) && !bytes); + return bytes; +} + /* Helper for scsi_io_completion() when "reprep" action required. */ static void scsi_io_completion_reprep(struct scsi_cmnd *cmd, struct request_queue *q) @@ -794,7 +834,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result) scsi_print_command(cmd); } } - if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req))) + if (!scsi_end_request(req, blk_stat, scsi_rq_err_bytes(req))) return; fallthrough; case ACTION_REPREP: diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2949d9ac7484..a78d9a0f2a1b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -947,7 +947,6 @@ struct req_iterator { * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment - * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats @@ -971,8 +970,6 @@ static inline int blk_rq_cur_bytes(const struct request *rq) return bio_iovec(rq->bio).bv_len; } -unsigned int blk_rq_err_bytes(const struct request *rq); - static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; -- cgit v1.2.3 From 786d4e01c550e8bb7c9f9f23bca0596a2a33483c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Nov 2021 07:13:55 +0100 Subject: block: remove rq_flush_dcache_pages This function is trivial, and flush_dcache_page is always defined, so just open code it in the 2.5 callers. Signed-off-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20211117061404.331732-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-core.c | 19 ------------------- drivers/mtd/mtd_blkdevs.c | 10 ++++++++-- drivers/mtd/ubi/block.c | 6 +++++- include/linux/blk-mq.h | 10 ---------- 4 files changed, 13 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 682b112f513f..039e28509f59 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1300,25 +1300,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq) } EXPORT_SYMBOL_GPL(blk_steal_bios); -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -/** - * rq_flush_dcache_pages - Helper function to flush all pages in a request - * @rq: the request to be flushed - * - * Description: - * Flush all pages in @rq. - */ -void rq_flush_dcache_pages(struct request *rq) -{ - struct req_iterator iter; - struct bio_vec bvec; - - rq_for_each_segment(bvec, rq, iter) - flush_dcache_page(bvec.bv_page); -} -EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); -#endif - /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index 4eaba6f4ec68..66f81d42fe77 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -46,6 +46,8 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr, struct mtd_blktrans_dev *dev, struct request *req) { + struct req_iterator iter; + struct bio_vec bvec; unsigned long block, nsect; char *buf; @@ -76,13 +78,17 @@ static blk_status_t do_blktrans_request(struct mtd_blktrans_ops *tr, } } kunmap(bio_page(req->bio)); - rq_flush_dcache_pages(req); + + rq_for_each_segment(bvec, req, iter) + flush_dcache_page(bvec.bv_page); return BLK_STS_OK; case REQ_OP_WRITE: if (!tr->writesect) return BLK_STS_IOERR; - rq_flush_dcache_pages(req); + rq_for_each_segment(bvec, req, iter) + flush_dcache_page(bvec.bv_page); + buf = kmap(bio_page(req->bio)) + bio_offset(req->bio); for (; nsect > 0; nsect--, block++, buf += tr->blksize) { if (tr->writesect(dev, block, buf)) { diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 062e6c2c45f5..302426ab30f8 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -294,6 +294,8 @@ static void ubiblock_do_work(struct work_struct *work) int ret; struct ubiblock_pdu *pdu = container_of(work, struct ubiblock_pdu, work); struct request *req = blk_mq_rq_from_pdu(pdu); + struct req_iterator iter; + struct bio_vec bvec; blk_mq_start_request(req); @@ -305,7 +307,9 @@ static void ubiblock_do_work(struct work_struct *work) blk_rq_map_sg(req->q, req, pdu->usgl.sg); ret = ubiblock_read(pdu); - rq_flush_dcache_pages(req); + + rq_for_each_segment(bvec, req, iter) + flush_dcache_page(bvec.bv_page); blk_mq_end_request(req, errno_to_blk_status(ret)); } diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index a78d9a0f2a1b..308edc2a4925 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -1132,14 +1132,4 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) } #endif /* CONFIG_BLK_DEV_ZONED */ -#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" -#endif -#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE -void rq_flush_dcache_pages(struct request *rq); -#else -static inline void rq_flush_dcache_pages(struct request *rq) -{ -} -#endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */ #endif /* BLK_MQ_H */ -- cgit v1.2.3 From 86416916466514e4ae0b7296d20133b6427c4c1f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:12 +0100 Subject: block: move GENHD_FL_NATIVE_CAPACITY to disk->state The flag to indicate an unlocked native capacity is dynamic state, not a driver capability flag, so move it to disk->state. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211122130625.1136848-2-hch@lst.de Signed-off-by: Jens Axboe --- block/partitions/core.c | 15 ++++++--------- include/linux/genhd.h | 8 +------- 2 files changed, 7 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/block/partitions/core.c b/block/partitions/core.c index 334b72ef1d73..520292fee933 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -527,18 +527,15 @@ out_unlock: static bool disk_unlock_native_capacity(struct gendisk *disk) { - const struct block_device_operations *bdops = disk->fops; - - if (bdops->unlock_native_capacity && - !(disk->flags & GENHD_FL_NATIVE_CAPACITY)) { - printk(KERN_CONT "enabling native capacity\n"); - bdops->unlock_native_capacity(disk); - disk->flags |= GENHD_FL_NATIVE_CAPACITY; - return true; - } else { + if (!disk->fops->unlock_native_capacity || + test_and_set_bit(GD_NATIVE_CAPACITY, &disk->state)) { printk(KERN_CONT "truncated\n"); return false; } + + printk(KERN_CONT "enabling native capacity\n"); + disk->fops->unlock_native_capacity(disk); + return true; } void blk_drop_partitions(struct gendisk *disk) diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 74c410263113..e490a71e5e9d 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -60,12 +60,6 @@ struct partition_meta_info { * (``BLOCK_EXT_MAJOR``). * This affects the maximum number of partitions. * - * ``GENHD_FL_NATIVE_CAPACITY`` (0x0080): based on information in the - * partition table, the device's capacity has been extended to its - * native capacity; i.e. the device has hidden capacity used by one - * of the partitions (this is a flag used so that native capacity is - * only ever unlocked once). - * * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is * blocked whenever a writer holds an exclusive lock. * @@ -86,7 +80,6 @@ struct partition_meta_info { #define GENHD_FL_CD 0x0008 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 -#define GENHD_FL_NATIVE_CAPACITY 0x0080 #define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100 #define GENHD_FL_NO_PART_SCAN 0x0200 #define GENHD_FL_HIDDEN 0x0400 @@ -140,6 +133,7 @@ struct gendisk { #define GD_NEED_PART_SCAN 0 #define GD_READ_ONLY 1 #define GD_DEAD 2 +#define GD_NATIVE_CAPACITY 3 struct mutex open_mutex; /* open/close mutex */ unsigned open_partitions; /* number of open partitions */ -- cgit v1.2.3 From 1545e0b419ba1d9b9bee4061d4826340afe6b0aa Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:13 +0100 Subject: block: move GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE to disk->event_flags GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE is all about the event reporting mechanism, so move it to the event_flags field. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211122130625.1136848-3-hch@lst.de Signed-off-by: Jens Axboe --- block/bdev.c | 2 +- drivers/block/paride/pcd.c | 2 +- drivers/scsi/sr.c | 5 +++-- include/linux/genhd.h | 6 ++---- 4 files changed, 7 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/block/bdev.c b/block/bdev.c index b1d087e5e205..dd84961bed7e 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -837,7 +837,7 @@ struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder) * used in blkdev_get/put(). */ if ((mode & FMODE_WRITE) && !bdev->bd_write_holder && - (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { + (disk->event_flags & DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE)) { bdev->bd_write_holder = true; unblock_events = false; } diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index f6b1d63e96e1..430ee8004a51 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -928,8 +928,8 @@ static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port, disk->minors = 1; strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; - disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; disk->events = DISK_EVENT_MEDIA_CHANGE; + disk->event_flags = DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE; if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay, pcd_buffer, PI_PCD, verbose, cd->name)) { diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 8e4af111c078..be445dc35f2c 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -684,9 +684,10 @@ static int sr_probe(struct device *dev) disk->minors = 1; sprintf(disk->disk_name, "sr%d", minor); disk->fops = &sr_bdops; - disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; + disk->flags = GENHD_FL_CD; disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST; - disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; + disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT | + DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE; blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index e490a71e5e9d..c1136ff3c91f 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -60,9 +60,6 @@ struct partition_meta_info { * (``BLOCK_EXT_MAJOR``). * This affects the maximum number of partitions. * - * ``GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE`` (0x0100): event polling is - * blocked whenever a writer holds an exclusive lock. - * * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled. * Used for loop devices in their default settings and some MMC * devices. @@ -80,7 +77,6 @@ struct partition_meta_info { #define GENHD_FL_CD 0x0008 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 -#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 0x0100 #define GENHD_FL_NO_PART_SCAN 0x0200 #define GENHD_FL_HIDDEN 0x0400 @@ -94,6 +90,8 @@ enum { DISK_EVENT_FLAG_POLL = 1 << 0, /* Forward events to udev */ DISK_EVENT_FLAG_UEVENT = 1 << 1, + /* Block event polling when open for exclusive write */ + DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE = 1 << 2, }; struct disk_events; -- cgit v1.2.3 From 1a827ce1b9f2c740d2c6a228afd972970c18bc21 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:14 +0100 Subject: block: remove GENHD_FL_CD GENHD_FL_CD marks a gendisk as a vaguely CD-ROM like device. Besides being used internally inside of sunvdc.c an xen-blkfront it is used by xen-blkback as a hint to claim a device exported to a guest is a CD-ROM like device. Just check for disk->cdi instead which is the right indicator for "real" CD-ROM or DVD drivers. This will miss the paravirtualized guest drivers, but those make little sense to report anyway. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211122130625.1136848-4-hch@lst.de Signed-off-by: Jens Axboe --- drivers/block/sunvdc.c | 17 +++++++++-------- drivers/block/xen-blkback/xenbus.c | 2 +- drivers/block/xen-blkfront.c | 26 +++++++++++--------------- drivers/scsi/sr.c | 1 - include/linux/genhd.h | 5 ----- 5 files changed, 21 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 6f45a53f7cbf..2157936de623 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -143,8 +143,8 @@ static int vdc_getgeo(struct block_device *bdev, struct hd_geometry *geo) static int vdc_ioctl(struct block_device *bdev, fmode_t mode, unsigned command, unsigned long argument) { + struct vdc_port *port = bdev->bd_disk->private_data; int i; - struct gendisk *disk; switch (command) { case CDROMMULTISESSION: @@ -155,12 +155,15 @@ static int vdc_ioctl(struct block_device *bdev, fmode_t mode, return 0; case CDROM_GET_CAPABILITY: - disk = bdev->bd_disk; - - if (bdev->bd_disk && (disk->flags & GENHD_FL_CD)) + if (!vdc_version_supported(port, 1, 1)) + return -EINVAL; + switch (port->vdisk_mtype) { + case VD_MEDIA_TYPE_CD: + case VD_MEDIA_TYPE_DVD: return 0; - return -EINVAL; - + default: + return -EINVAL; + } default: pr_debug(PFX "ioctl %08x not supported\n", command); return -EINVAL; @@ -854,14 +857,12 @@ static int probe_disk(struct vdc_port *port) switch (port->vdisk_mtype) { case VD_MEDIA_TYPE_CD: pr_info(PFX "Virtual CDROM %s\n", port->disk_name); - g->flags |= GENHD_FL_CD; g->flags |= GENHD_FL_REMOVABLE; set_disk_ro(g, 1); break; case VD_MEDIA_TYPE_DVD: pr_info(PFX "Virtual DVD %s\n", port->disk_name); - g->flags |= GENHD_FL_CD; g->flags |= GENHD_FL_REMOVABLE; set_disk_ro(g, 1); break; diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 914587aabca0..62125fd4af4a 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -510,7 +510,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, } vbd->size = vbd_sz(vbd); - if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom) + if (cdrom || disk_to_cdi(vbd->bdev->bd_disk)) vbd->type |= VDISK_CDROM; if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE) vbd->type |= VDISK_REMOVABLE; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8e3983e456f3..700c765a759a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -198,6 +198,7 @@ struct blkfront_info struct gendisk *gd; u16 sector_size; unsigned int physical_sector_size; + unsigned long vdisk_info; int vdevice; blkif_vdev_t handle; enum blkif_state connected; @@ -505,6 +506,7 @@ static int blkif_getgeo(struct block_device *bd, struct hd_geometry *hg) static int blkif_ioctl(struct block_device *bdev, fmode_t mode, unsigned command, unsigned long argument) { + struct blkfront_info *info = bdev->bd_disk->private_data; int i; switch (command) { @@ -514,9 +516,9 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode, return -EFAULT; return 0; case CDROM_GET_CAPABILITY: - if (bdev->bd_disk->flags & GENHD_FL_CD) - return 0; - return -EINVAL; + if (!(info->vdisk_info & VDISK_CDROM)) + return -EINVAL; + return 0; default: return -EINVAL; } @@ -1057,9 +1059,8 @@ static char *encode_disk_name(char *ptr, unsigned int n) } static int xlvbd_alloc_gendisk(blkif_sector_t capacity, - struct blkfront_info *info, - u16 vdisk_info, u16 sector_size, - unsigned int physical_sector_size) + struct blkfront_info *info, u16 sector_size, + unsigned int physical_sector_size) { struct gendisk *gd; int nr_minors = 1; @@ -1157,15 +1158,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, xlvbd_flush(info); - if (vdisk_info & VDISK_READONLY) + if (info->vdisk_info & VDISK_READONLY) set_disk_ro(gd, 1); - - if (vdisk_info & VDISK_REMOVABLE) + if (info->vdisk_info & VDISK_REMOVABLE) gd->flags |= GENHD_FL_REMOVABLE; - if (vdisk_info & VDISK_CDROM) - gd->flags |= GENHD_FL_CD; - return 0; out_free_tag_set: @@ -2304,7 +2301,6 @@ static void blkfront_connect(struct blkfront_info *info) unsigned long long sectors; unsigned long sector_size; unsigned int physical_sector_size; - unsigned int binfo; int err, i; struct blkfront_ring_info *rinfo; @@ -2342,7 +2338,7 @@ static void blkfront_connect(struct blkfront_info *info) err = xenbus_gather(XBT_NIL, info->xbdev->otherend, "sectors", "%llu", §ors, - "info", "%u", &binfo, + "info", "%u", &info->vdisk_info, "sector-size", "%lu", §or_size, NULL); if (err) { @@ -2371,7 +2367,7 @@ static void blkfront_connect(struct blkfront_info *info) } } - err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size, + err = xlvbd_alloc_gendisk(sectors, info, sector_size, physical_sector_size); if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index be445dc35f2c..6646797a7756 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -684,7 +684,6 @@ static int sr_probe(struct device *dev) disk->minors = 1; sprintf(disk->disk_name, "sr%d", minor); disk->fops = &sr_bdops; - disk->flags = GENHD_FL_CD; disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST; disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT | DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index c1136ff3c91f..74518c576fbb 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -46,10 +46,6 @@ struct partition_meta_info { * Must not be set for devices which are removed entirely when the * media is removed. * - * ``GENHD_FL_CD`` (0x0008): the block device is a CD-ROM-style - * device. - * Affects responses to the ``CDROM_GET_CAPABILITY`` ioctl. - * * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include * partition information in ``/proc/partitions`` or in the output of * printk_all_partitions(). @@ -74,7 +70,6 @@ struct partition_meta_info { #define GENHD_FL_REMOVABLE 0x0001 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ -#define GENHD_FL_CD 0x0008 #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NO_PART_SCAN 0x0200 -- cgit v1.2.3 From 46e7eac647b34ed4106a8262f8bedbb90801fadd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:17 +0100 Subject: block: rename GENHD_FL_NO_PART_SCAN to GENHD_FL_NO_PART The GENHD_FL_NO_PART_SCAN controls more than just partitions canning, so rename it to GENHD_FL_NO_PART. Signed-off-by: Christoph Hellwig Acked-by: Ulf Hansson Link: https://lore.kernel.org/r/20211122130625.1136848-7-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 2 +- drivers/block/loop.c | 8 ++++---- drivers/block/n64cart.c | 2 +- drivers/mmc/core/block.c | 4 ++-- include/linux/genhd.h | 13 ++++++------- 5 files changed, 14 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 94f39c4333b8..685794a2ebb0 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -500,7 +500,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, * and don't bother scanning for partitions either. */ disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; - disk->flags |= GENHD_FL_NO_PART_SCAN; + disk->flags |= GENHD_FL_NO_PART; } else { ret = bdi_register(disk->bdi, "%u:%u", disk->major, disk->first_minor); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a154cab6cd98..7219d98c6fb8 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1061,7 +1061,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, lo->lo_flags |= LO_FLAGS_PARTSCAN; partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; if (partscan) - lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; + lo->lo_disk->flags &= ~GENHD_FL_NO_PART; loop_global_unlock(lo, is_loop); if (partscan) @@ -1191,7 +1191,7 @@ out_unlock: mutex_lock(&lo->lo_mutex); lo->lo_flags = 0; if (!part_shift) - lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; + lo->lo_disk->flags |= GENHD_FL_NO_PART; lo->lo_state = Lo_unbound; mutex_unlock(&lo->lo_mutex); @@ -1301,7 +1301,7 @@ out_unfreeze: if (!err && (lo->lo_flags & LO_FLAGS_PARTSCAN) && !(prev_lo_flags & LO_FLAGS_PARTSCAN)) { - lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN; + lo->lo_disk->flags &= ~GENHD_FL_NO_PART; partscan = true; } out_unlock: @@ -2032,7 +2032,7 @@ static int loop_add(int i) * userspace tools. Parameters like this in general should be avoided. */ if (!part_shift) - disk->flags |= GENHD_FL_NO_PART_SCAN; + disk->flags |= GENHD_FL_NO_PART; disk->flags |= GENHD_FL_EXT_DEVT; atomic_set(&lo->lo_refcnt, 0); mutex_init(&lo->lo_mutex); diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index 78282f01f581..4db9a8c244af 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -136,7 +136,7 @@ static int __init n64cart_probe(struct platform_device *pdev) goto out; disk->first_minor = 0; - disk->flags = GENHD_FL_NO_PART_SCAN; + disk->flags = GENHD_FL_NO_PART; disk->fops = &n64cart_fops; disk->private_data = &pdev->dev; strcpy(disk->disk_name, "n64cart"); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 90e1bcd03b46..a71b3512c877 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2397,8 +2397,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, set_disk_ro(md->disk, md->read_only || default_ro); md->disk->flags = GENHD_FL_EXT_DEVT; if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT)) - md->disk->flags |= GENHD_FL_NO_PART_SCAN - | GENHD_FL_SUPPRESS_PARTITION_INFO; + md->disk->flags |= GENHD_FL_NO_PART | + GENHD_FL_SUPPRESS_PARTITION_INFO; /* * As discussed on lkml, GENHD_FL_REMOVABLE should: diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 74518c576fbb..0b9be3df9489 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -56,15 +56,15 @@ struct partition_meta_info { * (``BLOCK_EXT_MAJOR``). * This affects the maximum number of partitions. * - * ``GENHD_FL_NO_PART_SCAN`` (0x0200): partition scanning is disabled. - * Used for loop devices in their default settings and some MMC - * devices. + * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled. + * The kernel will not scan for partitions from add_disk, and users + * can't add partitions manually. * * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it * doesn't produce events, doesn't appear in sysfs, and doesn't have * an associated ``bdev``. * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and - * ``GENHD_FL_NO_PART_SCAN``. + * ``GENHD_FL_NO_PART``. * Used for multipath devices. */ #define GENHD_FL_REMOVABLE 0x0001 @@ -72,7 +72,7 @@ struct partition_meta_info { /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ #define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 -#define GENHD_FL_NO_PART_SCAN 0x0200 +#define GENHD_FL_NO_PART 0x0200 #define GENHD_FL_HIDDEN 0x0400 enum { @@ -180,8 +180,7 @@ static inline int disk_max_parts(struct gendisk *disk) static inline bool disk_part_scan_enabled(struct gendisk *disk) { - return disk_max_parts(disk) > 1 && - !(disk->flags & GENHD_FL_NO_PART_SCAN); + return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART); } static inline dev_t disk_devt(struct gendisk *disk) -- cgit v1.2.3 From 3b5149ac50970669ee0ddb9629ec77ffd5c0622d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:21 +0100 Subject: block: remove GENHD_FL_SUPPRESS_PARTITION_INFO This flag is not set directly anywhere and only inherited from GENHD_FL_HIDDEN. Just check for GENHD_FL_HIDDEN instead. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211122130625.1136848-11-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 11 +++-------- include/linux/genhd.h | 9 +-------- 2 files changed, 4 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 685794a2ebb0..50a843ee18f6 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -496,10 +496,8 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, if (disk->flags & GENHD_FL_HIDDEN) { /* - * Don't let hidden disks show up in /proc/partitions, - * and don't bother scanning for partitions either. + * Don't bother scanning for partitions. */ - disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO; disk->flags |= GENHD_FL_NO_PART; } else { ret = bdi_register(disk->bdi, "%u:%u", @@ -725,8 +723,7 @@ void __init printk_all_partitions(void) * Don't show empty devices or things that have been * suppressed */ - if (get_capacity(disk) == 0 || - (disk->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)) + if (get_capacity(disk) == 0 || (disk->flags & GENHD_FL_HIDDEN)) continue; /* @@ -819,9 +816,7 @@ static int show_partition(struct seq_file *seqf, void *v) struct block_device *part; unsigned long idx; - if (!get_capacity(sgp)) - return 0; - if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO) + if (!get_capacity(sgp) || (sgp->flags & GENHD_FL_HIDDEN)) return 0; rcu_read_lock(); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0b9be3df9489..64a2f33ae9ea 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -46,11 +46,6 @@ struct partition_meta_info { * Must not be set for devices which are removed entirely when the * media is removed. * - * ``GENHD_FL_SUPPRESS_PARTITION_INFO`` (0x0020): don't include - * partition information in ``/proc/partitions`` or in the output of - * printk_all_partitions(). - * Used for the null block device and some MMC devices. - * * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended * dynamic ``dev_t``, i.e. it wants extended device numbers * (``BLOCK_EXT_MAJOR``). @@ -63,14 +58,12 @@ struct partition_meta_info { * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it * doesn't produce events, doesn't appear in sysfs, and doesn't have * an associated ``bdev``. - * Implies ``GENHD_FL_SUPPRESS_PARTITION_INFO`` and - * ``GENHD_FL_NO_PART``. + * Implies ``GENHD_FL_NO_PART``. * Used for multipath devices. */ #define GENHD_FL_REMOVABLE 0x0001 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ -#define GENHD_FL_SUPPRESS_PARTITION_INFO 0x0020 #define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NO_PART 0x0200 #define GENHD_FL_HIDDEN 0x0400 -- cgit v1.2.3 From 1ebe2e5f9d68e94c524aba876f27b945669a7879 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:22 +0100 Subject: block: remove GENHD_FL_EXT_DEVT All modern drivers can support extra partitions using the extended dev_t. In fact except for the ioctl method drivers never even see partitions in normal operation. So remove the GENHD_FL_EXT_DEVT and allow extra partitions for all block devices that do support partitions, and require those that do not support partitions to explicit disallow them using GENHD_FL_NO_PART. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211122130625.1136848-12-hch@lst.de Signed-off-by: Jens Axboe --- block/genhd.c | 6 +++--- block/partitions/core.c | 9 ++++----- drivers/block/amiflop.c | 1 + drivers/block/ataflop.c | 1 + drivers/block/brd.c | 1 - drivers/block/drbd/drbd_main.c | 1 + drivers/block/floppy.c | 1 + drivers/block/loop.c | 1 - drivers/block/null_blk/main.c | 1 - drivers/block/paride/pcd.c | 1 + drivers/block/paride/pf.c | 1 + drivers/block/pktcdvd.c | 2 +- drivers/block/ps3vram.c | 1 + drivers/block/rbd.c | 6 ++---- drivers/block/swim.c | 1 + drivers/block/swim3.c | 2 +- drivers/block/virtio_blk.c | 1 - drivers/block/z2ram.c | 1 + drivers/block/zram/zram_drv.c | 1 + drivers/cdrom/gdrom.c | 1 + drivers/md/dm.c | 1 + drivers/md/md.c | 5 ----- drivers/mmc/core/block.c | 1 - drivers/mtd/ubi/block.c | 1 + drivers/scsi/sd.c | 1 - drivers/scsi/sr.c | 1 + include/linux/genhd.h | 28 +++++----------------------- 27 files changed, 30 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/block/genhd.c b/block/genhd.c index 50a843ee18f6..628632537129 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -376,7 +376,7 @@ int disk_scan_partitions(struct gendisk *disk, fmode_t mode) { struct block_device *bdev; - if (!disk_part_scan_enabled(disk)) + if (disk->flags & GENHD_FL_NO_PART) return -EINVAL; if (disk->open_partitions) return -EBUSY; @@ -438,7 +438,6 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, return ret; disk->major = BLOCK_EXT_MAJOR; disk->first_minor = ret; - disk->flags |= GENHD_FL_EXT_DEVT; } ret = disk_alloc_events(disk); @@ -872,7 +871,8 @@ static ssize_t disk_ext_range_show(struct device *dev, { struct gendisk *disk = dev_to_disk(dev); - return sprintf(buf, "%d\n", disk_max_parts(disk)); + return sprintf(buf, "%d\n", + (disk->flags & GENHD_FL_NO_PART) ? 1 : DISK_MAX_PARTS); } static ssize_t disk_removable_show(struct device *dev, diff --git a/block/partitions/core.c b/block/partitions/core.c index 520292fee933..c2a1635922b1 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -98,13 +98,12 @@ static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) static struct parsed_partitions *allocate_partitions(struct gendisk *hd) { struct parsed_partitions *state; - int nr; + int nr = DISK_MAX_PARTS; state = kzalloc(sizeof(*state), GFP_KERNEL); if (!state) return NULL; - nr = disk_max_parts(hd); state->parts = vzalloc(array_size(nr, sizeof(state->parts[0]))); if (!state->parts) { kfree(state); @@ -326,7 +325,7 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, lockdep_assert_held(&disk->open_mutex); - if (partno >= disk_max_parts(disk)) + if (partno >= DISK_MAX_PARTS) return ERR_PTR(-EINVAL); /* @@ -604,7 +603,7 @@ static int blk_add_partitions(struct gendisk *disk) struct parsed_partitions *state; int ret = -EAGAIN, p; - if (!disk_part_scan_enabled(disk)) + if (disk->flags & GENHD_FL_NO_PART) return 0; state = check_partition(disk); @@ -687,7 +686,7 @@ rescan: * userspace for this particular setup. */ if (invalidate) { - if (disk_part_scan_enabled(disk) || + if (!(disk->flags & GENHD_FL_NO_PART) || !(disk->flags & GENHD_FL_REMOVABLE)) set_capacity(disk, 0); } diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index bf5c124c5452..1eec5113d0b5 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1790,6 +1790,7 @@ static int fd_alloc_disk(int drive, int system) disk->first_minor = drive + system; disk->minors = 1; disk->fops = &floppy_fops; + disk->flags |= GENHD_FL_NO_PART; disk->events = DISK_EVENT_MEDIA_CHANGE; if (system) sprintf(disk->disk_name, "fd%d_msdos", drive); diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index bf769e6e32fe..f3ff9babdb5c 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -2000,6 +2000,7 @@ static int ataflop_alloc_disk(unsigned int drive, unsigned int type) disk->minors = 1; sprintf(disk->disk_name, "fd%d", drive); disk->fops = &floppy_fops; + disk->flags |= GENHD_FL_NO_PART; disk->events = DISK_EVENT_MEDIA_CHANGE; disk->private_data = &unit[drive]; set_capacity(disk, MAX_DISK_SIZE * 2); diff --git a/drivers/block/brd.c b/drivers/block/brd.c index a896ee175d86..8fe2e4289dae 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -405,7 +405,6 @@ static int brd_alloc(int i) disk->minors = max_part; disk->fops = &brd_fops; disk->private_data = brd; - disk->flags = GENHD_FL_EXT_DEVT; strlcpy(disk->disk_name, buf, DISK_NAME_LEN); set_capacity(disk, rd_size * 2); diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 53ba2dddba6e..07b3c6093e7d 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2734,6 +2734,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig disk->first_minor = minor; disk->minors = 1; disk->fops = &drbd_ops; + disk->flags |= GENHD_FL_NO_PART; sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index c4267da716fe..7f0a60c4079f 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4503,6 +4503,7 @@ static int floppy_alloc_disk(unsigned int drive, unsigned int type) disk->first_minor = TOMINOR(drive) | (type << 2); disk->minors = 1; disk->fops = &floppy_fops; + disk->flags |= GENHD_FL_NO_PART; disk->events = DISK_EVENT_MEDIA_CHANGE; if (type) sprintf(disk->disk_name, "fd%d_type%d", drive, type); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 7219d98c6fb8..0954ea8cf9e3 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -2033,7 +2033,6 @@ static int loop_add(int i) */ if (!part_shift) disk->flags |= GENHD_FL_NO_PART; - disk->flags |= GENHD_FL_EXT_DEVT; atomic_set(&lo->lo_refcnt, 0); mutex_init(&lo->lo_mutex); lo->lo_number = i; diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index eb17def1f265..54f7d490f8eb 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1850,7 +1850,6 @@ static int null_gendisk_register(struct nullb *nullb) set_capacity(disk, size); - disk->flags |= GENHD_FL_EXT_DEVT; disk->major = null_major; disk->first_minor = nullb->index; disk->minors = 1; diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 430ee8004a51..255fd3d4b8a8 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -928,6 +928,7 @@ static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port, disk->minors = 1; strcpy(disk->disk_name, cd->name); /* umm... */ disk->fops = &pcd_bdops; + disk->flags |= GENHD_FL_NO_PART; disk->events = DISK_EVENT_MEDIA_CHANGE; disk->event_flags = DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE; diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index bf8d0ef41a0a..b84a6448a4f7 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -942,6 +942,7 @@ static int __init pf_init_unit(struct pf_unit *pf, bool autoprobe, int port, disk->minors = 1; strcpy(disk->disk_name, pf->name); disk->fops = &pf_fops; + disk->flags |= GENHD_FL_NO_PART; disk->events = DISK_EVENT_MEDIA_CHANGE; disk->private_data = pf; diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index b53f648302c1..3af0499857ec 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2719,7 +2719,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) disk->first_minor = idx; disk->minors = 1; disk->fops = &pktcdvd_ops; - disk->flags = GENHD_FL_REMOVABLE; + disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; strcpy(disk->disk_name, pd->name); disk->private_data = pd; diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index c1876646a4cb..4f90819e245e 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -742,6 +742,7 @@ static int ps3vram_probe(struct ps3_system_bus_device *dev) priv->gendisk = gendisk; gendisk->major = ps3vram_major; gendisk->minors = 1; + gendisk->flags |= GENHD_FL_NO_PART; gendisk->fops = &ps3vram_fops; gendisk->private_data = dev; strlcpy(gendisk->disk_name, DEVICE_NAME, sizeof(gendisk->disk_name)); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 953fa134cd3d..8f140da1efe3 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4924,12 +4924,10 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) rbd_dev->dev_id); disk->major = rbd_dev->major; disk->first_minor = rbd_dev->minor; - if (single_major) { + if (single_major) disk->minors = (1 << RBD_SINGLE_MAJOR_PART_SHIFT); - disk->flags |= GENHD_FL_EXT_DEVT; - } else { + else disk->minors = RBD_MINORS_PER_MAJOR; - } disk->fops = &rbd_bd_ops; disk->private_data = rbd_dev; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 821594cd1315..fef65a18d56f 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -840,6 +840,7 @@ static int swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->minors = 1; sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive); swd->unit[drive].disk->fops = &floppy_fops; + swd->unit[drive].disk->flags |= GENHD_FL_NO_PART; swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE; swd->unit[drive].disk->private_data = &swd->unit[drive]; set_capacity(swd->unit[drive].disk, 2880); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 4b91c9aa5892..6c39f2c9f806 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1227,7 +1227,7 @@ static int swim3_attach(struct macio_dev *mdev, disk->fops = &floppy_fops; disk->private_data = fs; disk->events = DISK_EVENT_MEDIA_CHANGE; - disk->flags |= GENHD_FL_REMOVABLE; + disk->flags |= GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; sprintf(disk->disk_name, "fd%d", floppy_count); set_capacity(disk, 2880); rc = add_disk(disk); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6ae38776e30e..cfa303fa7318 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -843,7 +843,6 @@ static int virtblk_probe(struct virtio_device *vdev) vblk->disk->minors = 1 << PART_BITS; vblk->disk->private_data = vblk; vblk->disk->fops = &virtblk_fops; - vblk->disk->flags |= GENHD_FL_EXT_DEVT; vblk->index = index; /* configure queue flush support */ diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index ccc52c935faf..7a6ed83481b8 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -327,6 +327,7 @@ static int z2ram_register_disk(int minor) disk->major = Z2RAM_MAJOR; disk->first_minor = minor; disk->minors = 1; + disk->flags |= GENHD_FL_NO_PART; disk->fops = &z2_fops; if (minor) sprintf(disk->disk_name, "z2ram%d", minor); diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 25071126995b..f6da5293b913 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1947,6 +1947,7 @@ static int zram_add(void) zram->disk->major = zram_major; zram->disk->first_minor = device_id; zram->disk->minors = 1; + zram->disk->flags |= GENHD_FL_NO_PART; zram->disk->fops = &zram_devops; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index d50cc1fd34d5..faead41709bc 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -719,6 +719,7 @@ static void probe_gdrom_setupdisk(void) gd.disk->major = gdrom_major; gd.disk->first_minor = 1; gd.disk->minors = 1; + gd.disk->flags |= GENHD_FL_NO_PART; strcpy(gd.disk->disk_name, GDROM_DEV_NAME); } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 662742a310cb..280918cdcabd 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1778,6 +1778,7 @@ static struct mapped_device *alloc_dev(int minor) md->disk->major = _major; md->disk->first_minor = minor; md->disk->minors = 1; + md->disk->flags |= GENHD_FL_NO_PART; md->disk->fops = &dm_blk_dops; md->disk->queue = md->queue; md->disk->private_data = md; diff --git a/drivers/md/md.c b/drivers/md/md.c index 5111ed966947..7fbf6f0ac01b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -5707,11 +5707,6 @@ static int md_alloc(dev_t dev, char *name) mddev->queue = disk->queue; blk_set_stacking_limits(&mddev->queue->limits); blk_queue_write_cache(mddev->queue, true, true); - /* Allow extended partitions. This makes the - * 'mdp' device redundant, but we can't really - * remove it now. - */ - disk->flags |= GENHD_FL_EXT_DEVT; disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; error = add_disk(disk); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 2dd93d49d822..5e0960560eab 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2395,7 +2395,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, md->disk->private_data = md; md->parent = parent; set_disk_ro(md->disk, md->read_only || default_ro); - md->disk->flags = GENHD_FL_EXT_DEVT; if (area_type & (MMC_BLK_DATA_AREA_RPMB | MMC_BLK_DATA_AREA_BOOT)) md->disk->flags |= GENHD_FL_NO_PART; diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c index 302426ab30f8..a78fdf3b30f7 100644 --- a/drivers/mtd/ubi/block.c +++ b/drivers/mtd/ubi/block.c @@ -430,6 +430,7 @@ int ubiblock_create(struct ubi_volume_info *vi) ret = -ENODEV; goto out_cleanup_disk; } + gd->flags |= GENHD_FL_NO_PART; gd->private_data = dev; sprintf(gd->disk_name, "ubiblock%d_%d", dev->ubi_num, dev->vol_id); set_capacity(gd, disk_capacity); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 65875a598d62..bba1f5dafd38 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3566,7 +3566,6 @@ static int sd_probe(struct device *dev) sd_revalidate_disk(gd); - gd->flags = GENHD_FL_EXT_DEVT; if (sdp->removable) { gd->flags |= GENHD_FL_REMOVABLE; gd->events |= DISK_EVENT_MEDIA_CHANGE; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 6646797a7756..cf093387e42a 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -684,6 +684,7 @@ static int sr_probe(struct device *dev) disk->minors = 1; sprintf(disk->disk_name, "sr%d", minor); disk->fops = &sr_bdops; + disk->flags |= GENHD_FL_NO_PART; disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST; disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT | DISK_EVENT_FLAG_BLOCK_ON_EXCL_WRITE; diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 64a2f33ae9ea..b8ced80178d6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -46,11 +46,6 @@ struct partition_meta_info { * Must not be set for devices which are removed entirely when the * media is removed. * - * ``GENHD_FL_EXT_DEVT`` (0x0040): the driver supports extended - * dynamic ``dev_t``, i.e. it wants extended device numbers - * (``BLOCK_EXT_MAJOR``). - * This affects the maximum number of partitions. - * * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled. * The kernel will not scan for partitions from add_disk, and users * can't add partitions manually. @@ -64,7 +59,6 @@ struct partition_meta_info { #define GENHD_FL_REMOVABLE 0x0001 /* 2 is unused (used to be GENHD_FL_DRIVERFS) */ /* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ -#define GENHD_FL_EXT_DEVT 0x0040 #define GENHD_FL_NO_PART 0x0200 #define GENHD_FL_HIDDEN 0x0400 @@ -94,13 +88,13 @@ struct blk_integrity { }; struct gendisk { - /* major, first_minor and minors are input parameters only, - * don't use directly. Use disk_devt() and disk_max_parts(). + /* + * major/first_minor/minors should not be set by any new driver, the + * block core will take care of allocating them automatically. */ - int major; /* major number of driver */ + int major; int first_minor; - int minors; /* maximum number of minors, =1 for - * disks that can't be partitioned. */ + int minors; char disk_name[DISK_NAME_LEN]; /* name of major driver */ @@ -164,18 +158,6 @@ static inline bool disk_live(struct gendisk *disk) #define disk_to_cdi(disk) NULL #endif -static inline int disk_max_parts(struct gendisk *disk) -{ - if (disk->flags & GENHD_FL_EXT_DEVT) - return DISK_MAX_PARTS; - return disk->minors; -} - -static inline bool disk_part_scan_enabled(struct gendisk *disk) -{ - return disk_max_parts(disk) > 1 && !(disk->flags & GENHD_FL_NO_PART); -} - static inline dev_t disk_devt(struct gendisk *disk) { return MKDEV(disk->major, disk->first_minor); -- cgit v1.2.3 From 430cc5d3ab4d0ba0bd011cfbb0035e46ba92920c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 22 Nov 2021 14:06:24 +0100 Subject: block: cleanup the GENHD_FL_* definitions Switch to an enum and tidy up the documentation. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211122130625.1136848-14-hch@lst.de Signed-off-by: Jens Axboe --- include/linux/genhd.h | 32 ++++++++++++++------------------ 1 file changed, 14 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index b8ced80178d6..6906a45bc761 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -39,28 +39,24 @@ struct partition_meta_info { /** * DOC: genhd capability flags * - * ``GENHD_FL_REMOVABLE`` (0x0001): indicates that the block device - * gives access to removable media. - * When set, the device remains present even when media is not - * inserted. - * Must not be set for devices which are removed entirely when the + * ``GENHD_FL_REMOVABLE``: indicates that the block device gives access to + * removable media. When set, the device remains present even when media is not + * inserted. Shall not be set for devices which are removed entirely when the * media is removed. * - * ``GENHD_FL_NO_PART`` (0x0200): partition support is disabled. - * The kernel will not scan for partitions from add_disk, and users - * can't add partitions manually. + * ``GENHD_FL_HIDDEN``: the block device is hidden; it doesn't produce events, + * doesn't appear in sysfs, and can't be opened from userspace or using + * blkdev_get*. Used for the underlying components of multipath devices. + * + * ``GENHD_FL_NO_PART``: partition support is disabled. The kernel will not + * scan for partitions from add_disk, and users can't add partitions manually. * - * ``GENHD_FL_HIDDEN`` (0x0400): the block device is hidden; it - * doesn't produce events, doesn't appear in sysfs, and doesn't have - * an associated ``bdev``. - * Implies ``GENHD_FL_NO_PART``. - * Used for multipath devices. */ -#define GENHD_FL_REMOVABLE 0x0001 -/* 2 is unused (used to be GENHD_FL_DRIVERFS) */ -/* 4 is unused (used to be GENHD_FL_MEDIA_CHANGE_NOTIFY) */ -#define GENHD_FL_NO_PART 0x0200 -#define GENHD_FL_HIDDEN 0x0400 +enum { + GENHD_FL_REMOVABLE = 1 << 0, + GENHD_FL_HIDDEN = 1 << 1, + GENHD_FL_NO_PART = 1 << 2, +}; enum { DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */ -- cgit v1.2.3 From 48b5c1fbcd8c5bc6b91a56399a5257b801391dd8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 13 Nov 2021 14:03:26 -0700 Subject: block: only allocate poll_stats if there's a user of them This is essentially never used, yet it's about 1/3rd of the total queue size. Allocate it when needed, and don't embed it in the queue. Kill the queue flag for this while at it, since we can just check the assigned pointer now. Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 1 - block/blk-mq.c | 10 ++++------ block/blk-stat.c | 18 ++++++++++++++++++ block/blk-stat.h | 1 + block/blk-sysfs.c | 3 ++- include/linux/blkdev.h | 3 +-- 6 files changed, 26 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 4f2cf8399f3d..f4022b198580 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -122,7 +122,6 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(FUA), QUEUE_FLAG_NAME(DAX), QUEUE_FLAG_NAME(STATS), - QUEUE_FLAG_NAME(POLL_STATS), QUEUE_FLAG_NAME(REGISTERED), QUEUE_FLAG_NAME(QUIESCED), QUEUE_FLAG_NAME(PCI_P2PDMA), diff --git a/block/blk-mq.c b/block/blk-mq.c index 3af88ffc9e2c..7cd408408a37 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4581,11 +4581,10 @@ EXPORT_SYMBOL_GPL(blk_mq_update_nr_hw_queues); /* Enable polling stats and return whether they were already enabled. */ static bool blk_poll_stats_enable(struct request_queue *q) { - if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) || - blk_queue_flag_test_and_set(QUEUE_FLAG_POLL_STATS, q)) + if (q->poll_stat) return true; - blk_stat_add_callback(q, q->poll_cb); - return false; + + return blk_stats_alloc_enable(q); } static void blk_mq_poll_stats_start(struct request_queue *q) @@ -4594,8 +4593,7 @@ static void blk_mq_poll_stats_start(struct request_queue *q) * We don't arm the callback if polling stats are not enabled or the * callback is already active. */ - if (!test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags) || - blk_stat_is_active(q->poll_cb)) + if (!q->poll_stat || blk_stat_is_active(q->poll_cb)) return; blk_stat_activate_msecs(q->poll_cb, 100); diff --git a/block/blk-stat.c b/block/blk-stat.c index ae3dd1fb8e61..efb2a80db906 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -219,3 +219,21 @@ void blk_free_queue_stats(struct blk_queue_stats *stats) kfree(stats); } + +bool blk_stats_alloc_enable(struct request_queue *q) +{ + struct blk_rq_stat *poll_stat; + + poll_stat = kcalloc(BLK_MQ_POLL_STATS_BKTS, sizeof(*poll_stat), + GFP_ATOMIC); + if (!poll_stat) + return false; + + if (cmpxchg(&q->poll_stat, NULL, poll_stat) != NULL) { + kfree(poll_stat); + return true; + } + + blk_stat_add_callback(q, q->poll_cb); + return false; +} diff --git a/block/blk-stat.h b/block/blk-stat.h index 17b47a86eefb..58f029af49e5 100644 --- a/block/blk-stat.h +++ b/block/blk-stat.h @@ -64,6 +64,7 @@ struct blk_stat_callback { struct blk_queue_stats *blk_alloc_queue_stats(void); void blk_free_queue_stats(struct blk_queue_stats *); +bool blk_stats_alloc_enable(struct request_queue *q); void blk_stat_add(struct request *rq, u64 now); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index cd75b0f73dc6..c079be1c58a3 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -785,11 +785,12 @@ static void blk_release_queue(struct kobject *kobj) might_sleep(); - if (test_bit(QUEUE_FLAG_POLL_STATS, &q->queue_flags)) + if (q->poll_stat) blk_stat_remove_callback(q, q->poll_cb); blk_stat_free_callback(q->poll_cb); blk_free_queue_stats(q->stats); + kfree(q->poll_stat); blk_exit_queue(q); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bd4370baccca..74118e67f649 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -267,7 +267,7 @@ struct request_queue { int poll_nsec; struct blk_stat_callback *poll_cb; - struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; + struct blk_rq_stat *poll_stat; struct timer_list timeout; struct work_struct timeout_work; @@ -397,7 +397,6 @@ struct request_queue { #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ -#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ -- cgit v1.2.3 From 72cd9df2ef788d88c138d51223a01ca6281f232d Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 23 Nov 2021 17:37:33 -0800 Subject: blk-crypto: remove blk_crypto_unregister() This function is trivial and is only used in one place. Having this function is misleading because it implies that blk_crypto_register() needs to be paired with blk_crypto_unregister(), which is not the case. Just set disk->queue->crypto_profile to NULL directly. Signed-off-by: Eric Biggers Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211124013733.347612-1-ebiggers@kernel.org Signed-off-by: Jens Axboe --- block/blk-crypto-profile.c | 5 ----- block/blk-integrity.c | 2 +- include/linux/blkdev.h | 4 ---- 3 files changed, 1 insertion(+), 10 deletions(-) (limited to 'include/linux') diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c index 605ba0626a5c..96c511967386 100644 --- a/block/blk-crypto-profile.c +++ b/block/blk-crypto-profile.c @@ -463,11 +463,6 @@ bool blk_crypto_register(struct blk_crypto_profile *profile, } EXPORT_SYMBOL_GPL(blk_crypto_register); -void blk_crypto_unregister(struct request_queue *q) -{ - q->crypto_profile = NULL; -} - /** * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities * by child device diff --git a/block/blk-integrity.c b/block/blk-integrity.c index d670d54e5f7a..69eed260a823 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -411,7 +411,7 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template #ifdef CONFIG_BLK_INLINE_ENCRYPTION if (disk->queue->crypto_profile) { pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n"); - blk_crypto_unregister(disk->queue); + disk->queue->crypto_profile = NULL; } #endif } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 74118e67f649..0a4416ef4fbf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1170,8 +1170,6 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo bool blk_crypto_register(struct blk_crypto_profile *profile, struct request_queue *q); -void blk_crypto_unregister(struct request_queue *q); - #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, @@ -1180,8 +1178,6 @@ static inline bool blk_crypto_register(struct blk_crypto_profile *profile, return true; } -static inline void blk_crypto_unregister(struct request_queue *q) { } - #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ enum blk_unique_id { -- cgit v1.2.3 From e8dc17e2893b4107366004810ca2a4acf1fc8563 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 25 Oct 2021 09:06:57 +0200 Subject: blk-mq: Add blk_mq_complete_request_direct() Add blk_mq_complete_request_direct() which completes the block request directly instead deferring it to softirq for single queue devices. This is useful for devices which complete the requests in preemptible context and raising softirq from means scheduling ksoftirqd. Signed-off-by: Sebastian Andrzej Siewior Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211025070658.1565848-2-bigeasy@linutronix.de Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 308edc2a4925..d952c3442261 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -752,6 +752,17 @@ static inline void blk_mq_set_request_complete(struct request *rq) WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); } +/* + * Complete the request directly instead of deferring it to softirq or + * completing it another CPU. Useful in preemptible instead of an interrupt. + */ +static inline void blk_mq_complete_request_direct(struct request *rq, + void (*complete)(struct request *rq)) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); + complete(rq); +} + void blk_mq_start_request(struct request *rq); void blk_mq_end_request(struct request *rq, blk_status_t error); void __blk_mq_end_request(struct request *rq, blk_status_t error); -- cgit v1.2.3 From 88c9a2ce520ba381bb70658c80ec704f4d60f728 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Nov 2021 12:58:05 +0100 Subject: fork: move copy_io to block/blk-ioc.c Move the copying of the I/O context to the block layer as that is where we can use the proper low-level interfaces. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211126115817.2087431-3-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-ioc.c | 27 +++++++++++++++++++++++++++ include/linux/iocontext.h | 23 +++++++++++++---------- kernel/fork.c | 26 -------------------------- 3 files changed, 40 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 70c99e85aee5..3b31cfad4b75 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -322,6 +322,33 @@ struct io_context *get_task_io_context(struct task_struct *task, return NULL; } +int __copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + struct io_context *ioc = current->io_context; + struct io_context *new_ioc; + + /* + * Share io context with parent, if CLONE_IO is set + */ + if (clone_flags & CLONE_IO) { + get_io_context_active(ioc); + + WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); + atomic_inc(&ioc->nr_tasks); + + tsk->io_context = ioc; + } else if (ioprio_valid(ioc->ioprio)) { + new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); + if (unlikely(!new_ioc)) + return -ENOMEM; + + new_ioc->ioprio = ioc->ioprio; + put_io_context(new_ioc); + } + + return 0; +} + /** * ioc_lookup_icq - lookup io_cq from ioc * @ioc: the associated io_context diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 0a9dc40b7be8..bcd47d104d8e 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -129,14 +129,6 @@ static inline void get_io_context_active(struct io_context *ioc) atomic_inc(&ioc->active_ref); } -static inline void ioc_task_link(struct io_context *ioc) -{ - get_io_context_active(ioc); - - WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); - atomic_inc(&ioc->nr_tasks); -} - struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); @@ -144,10 +136,21 @@ void put_io_context_active(struct io_context *ioc); void exit_io_context(struct task_struct *task); struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); +int __copy_io(unsigned long clone_flags, struct task_struct *tsk); +static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + if (!current->io_context) + return 0; + return __copy_io(clone_flags, tsk); +} #else struct io_context; static inline void put_io_context(struct io_context *ioc) { } static inline void exit_io_context(struct task_struct *task) { } -#endif +static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) +{ + return 0; +} +#endif /* CONFIG_BLOCK */ -#endif +#endif /* IOCONTEXT_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 3244cc56b697..3161d7980155 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1556,32 +1556,6 @@ out: return error; } -static int copy_io(unsigned long clone_flags, struct task_struct *tsk) -{ -#ifdef CONFIG_BLOCK - struct io_context *ioc = current->io_context; - struct io_context *new_ioc; - - if (!ioc) - return 0; - /* - * Share io context with parent, if CLONE_IO is set - */ - if (clone_flags & CLONE_IO) { - ioc_task_link(ioc); - tsk->io_context = ioc; - } else if (ioprio_valid(ioc->ioprio)) { - new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); - if (unlikely(!new_ioc)) - return -ENOMEM; - - new_ioc->ioprio = ioc->ioprio; - put_io_context(new_ioc); - } -#endif - return 0; -} - static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; -- cgit v1.2.3 From 3304742562d27fb87a6d8291cc48824dd20f6964 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Nov 2021 12:58:09 +0100 Subject: block: mark put_io_context_active static Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211126115817.2087431-7-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-ioc.c | 2 +- include/linux/iocontext.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 3b31cfad4b75..f3ff495756cb 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -175,7 +175,7 @@ void put_io_context(struct io_context *ioc) * Undo get_io_context_active(). If active reference reaches zero after * put, @ioc can never issue further IOs and ioscheds are notified. */ -void put_io_context_active(struct io_context *ioc) +static void put_io_context_active(struct io_context *ioc) { struct io_cq *icq; diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index bcd47d104d8e..3ba45953d522 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -132,7 +132,6 @@ static inline void get_io_context_active(struct io_context *ioc) struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); -void put_io_context_active(struct io_context *ioc); void exit_io_context(struct task_struct *task); struct io_context *get_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node); -- cgit v1.2.3 From 50569c24be61eafb3efa06e2a3ccd447f75ae1b0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Nov 2021 12:58:12 +0100 Subject: block: remove get_io_context_active Fold it into it's only caller, and remove a lof of the debug checks that are not needed. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211126115817.2087431-10-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-ioc.c | 8 +++----- include/linux/iocontext.h | 16 ---------------- 2 files changed, 3 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 3ba15c867dfa..cc4eb2ba87f7 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -173,7 +173,7 @@ EXPORT_SYMBOL_GPL(put_io_context); * put_io_context_active - put active reference on ioc * @ioc: ioc of interest * - * Undo get_io_context_active(). If active reference reaches zero after + * Put an active reference to an ioc. If active reference reaches zero after * put, @ioc can never issue further IOs and ioscheds are notified. */ static void put_io_context_active(struct io_context *ioc) @@ -333,11 +333,9 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk) * Share io context with parent, if CLONE_IO is set */ if (clone_flags & CLONE_IO) { - get_io_context_active(ioc); - - WARN_ON_ONCE(atomic_read(&ioc->nr_tasks) <= 0); + atomic_long_inc(&ioc->refcount); + atomic_inc(&ioc->active_ref); atomic_inc(&ioc->nr_tasks); - tsk->io_context = ioc; } else if (ioprio_valid(ioc->ioprio)) { new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 3ba45953d522..c1229fbd6691 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -113,22 +113,6 @@ struct io_context { struct work_struct release_work; }; -/** - * get_io_context_active - get active reference on ioc - * @ioc: ioc of interest - * - * Only iocs with active reference can issue new IOs. This function - * acquires an active reference on @ioc. The caller must already have an - * active reference on @ioc. - */ -static inline void get_io_context_active(struct io_context *ioc) -{ - WARN_ON_ONCE(atomic_long_read(&ioc->refcount) <= 0); - WARN_ON_ONCE(atomic_read(&ioc->active_ref) <= 0); - atomic_long_inc(&ioc->refcount); - atomic_inc(&ioc->active_ref); -} - struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); -- cgit v1.2.3 From f3fa33acca9f0058157214800f68b10d8e71ab7a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Nov 2021 13:18:00 +0100 Subject: block: remove the ->rq_disk field in struct request Just use the disk attached to the request_queue instead. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20211126121802.2090656-4-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-flush.c | 3 +-- block/blk-mq.c | 14 ++++++-------- block/blk.h | 2 +- drivers/block/amiflop.c | 2 +- drivers/block/ataflop.c | 6 +++--- drivers/block/floppy.c | 6 +++--- drivers/block/null_blk/trace.h | 2 +- drivers/block/paride/pcd.c | 2 +- drivers/block/paride/pd.c | 4 ++-- drivers/block/paride/pf.c | 4 ++-- drivers/block/rnbd/rnbd-clt.c | 4 ++-- drivers/block/sunvdc.c | 2 +- drivers/md/dm-mpath.c | 1 - drivers/mmc/core/block.c | 2 +- drivers/nvme/host/fault_inject.c | 2 +- drivers/nvme/host/trace.h | 6 +++--- drivers/scsi/scsi_lib.c | 3 ++- drivers/scsi/scsi_logging.c | 4 +++- drivers/scsi/sd.c | 24 ++++++++++++------------ drivers/scsi/sd_zbc.c | 8 ++++---- drivers/scsi/sr.c | 4 ++-- drivers/scsi/virtio_scsi.c | 2 +- drivers/usb/storage/transport.c | 2 +- include/linux/blk-mq.h | 4 ---- include/scsi/scsi_cmnd.h | 2 +- include/scsi/scsi_device.h | 4 ++-- include/trace/events/block.h | 8 ++++---- kernel/trace/blktrace.c | 2 +- 28 files changed, 62 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/block/blk-flush.c b/block/blk-flush.c index 902e80e48e4a..fd5187a0898d 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -145,7 +145,7 @@ static void blk_flush_queue_rq(struct request *rq, bool add_front) static void blk_account_io_flush(struct request *rq) { - struct block_device *part = rq->rq_disk->part0; + struct block_device *part = rq->q->disk->part0; part_stat_lock(); part_stat_inc(part, ios[STAT_FLUSH]); @@ -339,7 +339,6 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH; flush_rq->cmd_flags |= (flags & REQ_DRV) | (flags & REQ_FAILFAST_MASK); flush_rq->rq_flags |= RQF_FLUSH_SEQ; - flush_rq->rq_disk = first_rq->rq_disk; flush_rq->end_io = flush_end_io; /* * Order WRITE ->end_io and WRITE rq->ref, and its pair is the one diff --git a/block/blk-mq.c b/block/blk-mq.c index 3e67662f7801..f1abfd2e24f7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -377,7 +377,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->start_time_ns = ktime_get_ns(); else rq->start_time_ns = 0; - rq->rq_disk = NULL; rq->part = NULL; #ifdef CONFIG_BLK_RQ_ALLOC_TIME rq->alloc_time_ns = alloc_time_ns; @@ -659,7 +658,7 @@ void blk_mq_free_plug_rqs(struct blk_plug *plug) void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, - rq->rq_disk ? rq->rq_disk->disk_name : "?", + rq->q->disk ? rq->q->disk->disk_name : "?", (unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", @@ -712,7 +711,7 @@ static void blk_print_req_error(struct request *req, blk_status_t status) "%s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", blk_status_to_str(status), - req->rq_disk ? req->rq_disk->disk_name : "?", + req->q->disk ? req->q->disk->disk_name : "?", blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)), req->cmd_flags & ~REQ_OP_MASK, req->nr_phys_segments, @@ -853,8 +852,8 @@ static void __blk_account_io_start(struct request *rq) /* passthrough requests can hold bios that do not have ->bi_bdev set */ if (rq->bio && rq->bio->bi_bdev) rq->part = rq->bio->bi_bdev; - else - rq->part = rq->rq_disk->part0; + else if (rq->q->disk) + rq->part = rq->q->disk->part0; part_stat_lock(); update_io_ticks(rq->part, jiffies, false); @@ -1172,7 +1171,6 @@ void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq, WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); - rq->rq_disk = bd_disk; rq->end_io = done; blk_account_io_start(rq); @@ -2902,8 +2900,8 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * if (ret != BLK_STS_OK) return ret; - if (rq->rq_disk && - should_fail_request(rq->rq_disk->part0, blk_rq_bytes(rq))) + if (rq->q->disk && + should_fail_request(rq->q->disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) diff --git a/block/blk.h b/block/blk.h index 3be0fdf76c9a..a55d82c3d1c2 100644 --- a/block/blk.h +++ b/block/blk.h @@ -324,7 +324,7 @@ int blk_dev_init(void); */ static inline bool blk_do_io_stat(struct request *rq) { - return (rq->rq_flags & RQF_IO_STAT) && rq->rq_disk; + return (rq->rq_flags & RQF_IO_STAT) && rq->q->disk; } void update_io_ticks(struct block_device *part, unsigned long now, bool end); diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 1eec5113d0b5..5a566f2fd533 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1505,7 +1505,7 @@ static blk_status_t amiflop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; - struct amiga_floppy_struct *floppy = rq->rq_disk->private_data; + struct amiga_floppy_struct *floppy = rq->q->disk->private_data; blk_status_t err; if (!spin_trylock_irq(&amiflop_lock)) diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index f3ff9babdb5c..5d819a466e2f 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -1502,7 +1502,7 @@ static void setup_req_params( int drive ) static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { - struct atari_floppy_struct *floppy = bd->rq->rq_disk->private_data; + struct atari_floppy_struct *floppy = bd->rq->q->disk->private_data; int drive = floppy - unit; int type = floppy->type; @@ -1538,7 +1538,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, if (!UDT) { Probing = 1; UDT = atari_disk_type + StartDiskType[DriveType]; - set_capacity(bd->rq->rq_disk, UDT->blocks); + set_capacity(bd->rq->q->disk, UDT->blocks); UD.autoprobe = 1; } } @@ -1558,7 +1558,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, } type = minor2disktype[type].index; UDT = &atari_disk_type[type]; - set_capacity(bd->rq->rq_disk, UDT->blocks); + set_capacity(bd->rq->q->disk, UDT->blocks); UD.autoprobe = 0; } diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 7f0a60c4079f..0c638de25023 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2259,7 +2259,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req) static void floppy_end_request(struct request *req, blk_status_t error) { unsigned int nr_sectors = current_count_sectors; - unsigned int drive = (unsigned long)req->rq_disk->private_data; + unsigned int drive = (unsigned long)req->q->disk->private_data; /* current_count_sectors can be zero if transfer failed */ if (error) @@ -2550,7 +2550,7 @@ static int make_raw_rw_request(void) if (WARN(max_buffer_sectors == 0, "VFS: Block I/O scheduled on unopened device\n")) return 0; - set_fdc((long)current_req->rq_disk->private_data); + set_fdc((long)current_req->q->disk->private_data); raw_cmd = &default_raw_cmd; raw_cmd->flags = FD_RAW_SPIN | FD_RAW_NEED_DISK | FD_RAW_NEED_SEEK; @@ -2792,7 +2792,7 @@ do_request: return; } } - drive = (long)current_req->rq_disk->private_data; + drive = (long)current_req->q->disk->private_data; set_fdc(drive); reschedule_timeout(current_drive, "redo fd request"); diff --git a/drivers/block/null_blk/trace.h b/drivers/block/null_blk/trace.h index ce3b430e88c5..86d6c12c603c 100644 --- a/drivers/block/null_blk/trace.h +++ b/drivers/block/null_blk/trace.h @@ -44,7 +44,7 @@ TRACE_EVENT(nullb_zone_op, __entry->op = req_op(cmd->rq); __entry->zone_no = zone_no; __entry->zone_cond = zone_cond; - __assign_disk_name(__entry->disk, cmd->rq->rq_disk); + __assign_disk_name(__entry->disk, cmd->rq->q->disk); ), TP_printk("%s req=%-15s zone_no=%u zone_cond=%-10s", __print_disk_name(__entry->disk), diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 255fd3d4b8a8..f462ad67931a 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -690,7 +690,7 @@ static void pcd_request(void) if (!pcd_req && !set_next_request()) return; - cd = pcd_req->rq_disk->private_data; + cd = pcd_req->q->disk->private_data; if (cd != pcd_current) pcd_bufblk = -1; pcd_current = cd; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index fba865058a17..4f8cce510562 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -430,7 +430,7 @@ static void run_fsm(void) int stop = 0; if (!phase) { - pd_current = pd_req->rq_disk->private_data; + pd_current = pd_req->q->disk->private_data; pi_current = pd_current->pi; phase = do_pd_io_start; } @@ -492,7 +492,7 @@ static enum action do_pd_io_start(void) case REQ_OP_WRITE: pd_block = blk_rq_pos(pd_req); pd_count = blk_rq_cur_sectors(pd_req); - if (pd_block + pd_count > get_capacity(pd_req->rq_disk)) + if (pd_block + pd_count > get_capacity(pd_req->q->disk)) return Fail; pd_run = blk_rq_sectors(pd_req); pd_buf = bio_data(pd_req->bio); diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index b84a6448a4f7..292e9a4ce1b9 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -746,12 +746,12 @@ repeat: if (!pf_req && !set_next_request()) return; - pf_current = pf_req->rq_disk->private_data; + pf_current = pf_req->q->disk->private_data; pf_block = blk_rq_pos(pf_req); pf_run = blk_rq_sectors(pf_req); pf_count = blk_rq_cur_sectors(pf_req); - if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) { + if (pf_block + pf_count > get_capacity(pf_req->q->disk)) { pf_end_request(BLK_STS_IOERR); goto repeat; } diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 2df0657cdf00..67a8edbaa1fd 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -393,7 +393,7 @@ static void rnbd_put_iu(struct rnbd_clt_session *sess, struct rnbd_iu *iu) static void rnbd_softirq_done_fn(struct request *rq) { - struct rnbd_clt_dev *dev = rq->rq_disk->private_data; + struct rnbd_clt_dev *dev = rq->q->disk->private_data; struct rnbd_clt_session *sess = dev->sess; struct rnbd_iu *iu; @@ -1133,7 +1133,7 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; - struct rnbd_clt_dev *dev = rq->rq_disk->private_data; + struct rnbd_clt_dev *dev = rq->q->disk->private_data; struct rnbd_iu *iu = blk_mq_rq_to_pdu(rq); int err; blk_status_t ret = BLK_STS_IOERR; diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 2157936de623..146d85d80e0e 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -462,7 +462,7 @@ static int __vdc_tx_trigger(struct vdc_port *port) static int __send_request(struct request *req) { - struct vdc_port *port = req->rq_disk->private_data; + struct vdc_port *port = req->q->disk->private_data; struct vio_dring_state *dr = &port->vio.drings[VIO_DRIVER_TX_RING]; struct scatterlist sg[MAX_RING_COOKIES]; struct vdc_req_entry *rqe; diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 90dc9cc48881..f4719b65e5e3 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -550,7 +550,6 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, return DM_MAPIO_REQUEUE; } clone->bio = clone->biotail = NULL; - clone->rq_disk = bdev->bd_disk; clone->cmd_flags |= REQ_FAILFAST_TRANSPORT; *__clone = clone; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 635b79899b9f..dc094f73d335 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1837,7 +1837,7 @@ static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req) /* Reset if the card is in a bad state */ if (!mmc_host_is_spi(mq->card->host) && err && mmc_blk_reset(md, card->host, type)) { - pr_err("%s: recovery failed!\n", req->rq_disk->disk_name); + pr_err("%s: recovery failed!\n", req->q->disk->disk_name); mqrq->retries = MMC_NO_RETRIES; return; } diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 1352159733b0..83d2e6860d38 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -56,7 +56,7 @@ void nvme_fault_inject_fini(struct nvme_fault_inject *fault_inject) void nvme_should_fail(struct request *req) { - struct gendisk *disk = req->rq_disk; + struct gendisk *disk = req->q->disk; struct nvme_fault_inject *fault_inject = NULL; u16 status; diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index 35bac7a25422..b5f85259461a 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -68,7 +68,7 @@ TRACE_EVENT(nvme_setup_cmd, __entry->nsid = le32_to_cpu(cmd->common.nsid); __entry->metadata = !!blk_integrity_rq(req); __entry->fctype = cmd->fabrics.fctype; - __assign_disk_name(__entry->disk, req->rq_disk); + __assign_disk_name(__entry->disk, req->q->disk); memcpy(__entry->cdw10, &cmd->common.cdw10, sizeof(__entry->cdw10)); ), @@ -103,7 +103,7 @@ TRACE_EVENT(nvme_complete_rq, __entry->retries = nvme_req(req)->retries; __entry->flags = nvme_req(req)->flags; __entry->status = nvme_req(req)->status; - __assign_disk_name(__entry->disk, req->rq_disk); + __assign_disk_name(__entry->disk, req->q->disk); ), TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%#llx, retries=%u, flags=0x%x, status=%#x", __entry->ctrl_id, __print_disk_name(__entry->disk), @@ -153,7 +153,7 @@ TRACE_EVENT(nvme_sq, ), TP_fast_assign( __entry->ctrl_id = nvme_req(req)->ctrl->instance; - __assign_disk_name(__entry->disk, req->rq_disk); + __assign_disk_name(__entry->disk, req->q->disk); __entry->qid = nvme_req_qid(req); __entry->sq_head = le16_to_cpu(sq_head); __entry->sq_tail = sq_tail; diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 5e8b5ecb3245..c23cf8e7b3c3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -543,8 +543,9 @@ static bool scsi_end_request(struct request *req, blk_status_t error, if (blk_update_request(req, error, bytes)) return true; + // XXX: if (blk_queue_add_random(q)) - add_disk_randomness(req->rq_disk); + add_disk_randomness(req->q->disk); if (!blk_rq_is_passthrough(req)) { WARN_ON_ONCE(!(cmd->flags & SCMD_INITIALIZED)); diff --git a/drivers/scsi/scsi_logging.c b/drivers/scsi/scsi_logging.c index ed9572252a42..1f8f80b2dbfc 100644 --- a/drivers/scsi/scsi_logging.c +++ b/drivers/scsi/scsi_logging.c @@ -30,7 +30,9 @@ static inline const char *scmd_name(const struct scsi_cmnd *scmd) { struct request *rq = scsi_cmd_to_rq((struct scsi_cmnd *)scmd); - return rq->rq_disk ? rq->rq_disk->disk_name : NULL; + if (!rq->q->disk) + return NULL; + return rq->q->disk->disk_name; } static size_t sdev_format_header(char *logbuf, size_t logbuf_len, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bba1f5dafd38..8181857ddf53 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -872,7 +872,7 @@ static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) { struct scsi_device *sdp = cmd->device; struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); unsigned int data_len = 24; @@ -908,7 +908,7 @@ static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, { struct scsi_device *sdp = cmd->device; struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; @@ -940,7 +940,7 @@ static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, { struct scsi_device *sdp = cmd->device; struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; @@ -971,7 +971,7 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); struct scsi_device *sdp = cmd->device; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); @@ -1068,7 +1068,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); struct scsi_device *sdp = cmd->device; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); struct bio *bio = rq->bio; u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); @@ -1116,7 +1116,7 @@ static blk_status_t sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) static blk_status_t sd_setup_flush_cmnd(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); /* flush requests don't perform I/O, zero the S/G table */ memset(&cmd->sdb, 0, sizeof(cmd->sdb)); @@ -1215,7 +1215,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); struct scsi_device *sdp = cmd->device; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); sector_t lba = sectors_to_logical(sdp, blk_rq_pos(rq)); sector_t threshold; unsigned int nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); @@ -1236,7 +1236,7 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) goto fail; } - if (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->rq_disk)) { + if (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->q->disk)) { scmd_printk(KERN_ERR, cmd, "access beyond end of device\n"); goto fail; } @@ -1331,7 +1331,7 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd) switch (req_op(rq)) { case REQ_OP_DISCARD: - switch (scsi_disk(rq->rq_disk)->provisioning_mode) { + switch (scsi_disk(rq->q->disk)->provisioning_mode) { case SD_LBP_UNMAP: return sd_setup_unmap_cmnd(cmd); case SD_LBP_WS16: @@ -1917,7 +1917,7 @@ static const struct block_device_operations sd_fops = { **/ static void sd_eh_reset(struct scsi_cmnd *scmd) { - struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->rq_disk); + struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->q->disk); /* New SCSI EH run, reset gate variable */ sdkp->ignore_medium_access_errors = false; @@ -1937,7 +1937,7 @@ static void sd_eh_reset(struct scsi_cmnd *scmd) **/ static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) { - struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->rq_disk); + struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->q->disk); struct scsi_device *sdev = scmd->device; if (!scsi_device_online(sdev) || @@ -2034,7 +2034,7 @@ static int sd_done(struct scsi_cmnd *SCpnt) unsigned int resid; struct scsi_sense_hdr sshdr; struct request *req = scsi_cmd_to_rq(SCpnt); - struct scsi_disk *sdkp = scsi_disk(req->rq_disk); + struct scsi_disk *sdkp = scsi_disk(req->q->disk); int sense_valid = 0; int sense_deferred = 0; diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index ed06798983f8..65bfd1e170da 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -244,7 +244,7 @@ out: static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); sector_t sector = blk_rq_pos(rq); if (!sd_is_zoned(sdkp)) @@ -322,7 +322,7 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, unsigned int nr_blocks) { struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); unsigned int wp_offset, zno = blk_rq_zone_no(rq); unsigned long flags; blk_status_t ret; @@ -388,7 +388,7 @@ blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, { struct request *rq = scsi_cmd_to_rq(cmd); sector_t sector = blk_rq_pos(rq); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); sector_t block = sectors_to_logical(sdkp->device, sector); blk_status_t ret; @@ -443,7 +443,7 @@ static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd, { int result = cmd->result; struct request *rq = scsi_cmd_to_rq(cmd); - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); unsigned int zno = blk_rq_zone_no(rq); enum req_opf op = req_op(rq); unsigned long flags; diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 411e2b01966e..7db595c08b20 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -335,7 +335,7 @@ static int sr_done(struct scsi_cmnd *SCpnt) int block_sectors = 0; long error_sector; struct request *rq = scsi_cmd_to_rq(SCpnt); - struct scsi_cd *cd = scsi_cd(rq->rq_disk); + struct scsi_cd *cd = scsi_cd(rq->q->disk); #ifdef DEBUG scmd_printk(KERN_INFO, SCpnt, "done: %x\n", result); @@ -402,7 +402,7 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt) ret = scsi_alloc_sgtables(SCpnt); if (ret != BLK_STS_OK) return ret; - cd = scsi_cd(rq->rq_disk); + cd = scsi_cd(rq->q->disk); SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt, "Doing sr request, block = %d\n", block)); diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 28e1d98ae102..65c642b24ecf 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -528,7 +528,7 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev, if (!rq || !scsi_prot_sg_count(sc)) return; - bi = blk_get_integrity(rq->rq_disk); + bi = blk_get_integrity(rq->q->disk); if (sc->sc_data_direction == DMA_TO_DEVICE) cmd_pi->pi_bytesout = cpu_to_virtio32(vdev, diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c index 4c5a0a49035f..1928b3918242 100644 --- a/drivers/usb/storage/transport.c +++ b/drivers/usb/storage/transport.c @@ -551,7 +551,7 @@ static void last_sector_hacks(struct us_data *us, struct scsi_cmnd *srb) /* Did this command access the last sector? */ sector = (srb->cmnd[2] << 24) | (srb->cmnd[3] << 16) | (srb->cmnd[4] << 8) | (srb->cmnd[5]); - disk = scsi_cmd_to_rq(srb)->rq_disk; + disk = scsi_cmd_to_rq(srb)->q->disk; if (!disk) goto done; sdkp = scsi_disk(disk); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d952c3442261..ede7bef8880a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -100,7 +100,6 @@ struct request { struct request *rq_next; }; - struct gendisk *rq_disk; struct block_device *part; #ifdef CONFIG_BLK_RQ_ALLOC_TIME /* Time that the first bio started allocating this request. */ @@ -890,9 +889,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; rq->ioprio = bio_prio(bio); - - if (bio->bi_bdev) - rq->rq_disk = bio->bi_bdev->bd_disk; } void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx, diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index 477a800a9543..6794d7322cbd 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -164,7 +164,7 @@ static inline struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd) { struct request *rq = scsi_cmd_to_rq(cmd); - return *(struct scsi_driver **)rq->rq_disk->private_data; + return *(struct scsi_driver **)rq->q->disk->private_data; } void scsi_done(struct scsi_cmnd *cmd); diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index d1c6fc83b1e3..ab7557d84f75 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -275,9 +275,9 @@ scmd_printk(const char *, const struct scsi_cmnd *, const char *, ...); do { \ struct request *__rq = scsi_cmd_to_rq((scmd)); \ \ - if (__rq->rq_disk) \ + if (__rq->q->disk) \ sdev_dbg((scmd)->device, "[%s] " fmt, \ - __rq->rq_disk->disk_name, ##a); \ + __rq->q->disk->disk_name, ##a); \ else \ sdev_dbg((scmd)->device, fmt, ##a); \ } while (0) diff --git a/include/trace/events/block.h b/include/trace/events/block.h index a95daa4d4caa..27170e40e8c9 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -85,7 +85,7 @@ TRACE_EVENT(block_rq_requeue, ), TP_fast_assign( - __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; + __entry->dev = rq->q->disk ? disk_devt(rq->q->disk) : 0; __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); @@ -128,7 +128,7 @@ TRACE_EVENT(block_rq_complete, ), TP_fast_assign( - __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; + __entry->dev = rq->q->disk ? disk_devt(rq->q->disk) : 0; __entry->sector = blk_rq_pos(rq); __entry->nr_sector = nr_bytes >> 9; __entry->error = blk_status_to_errno(error); @@ -161,7 +161,7 @@ DECLARE_EVENT_CLASS(block_rq, ), TP_fast_assign( - __entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0; + __entry->dev = rq->q->disk ? disk_devt(rq->q->disk) : 0; __entry->sector = blk_rq_trace_sector(rq); __entry->nr_sector = blk_rq_trace_nr_sectors(rq); __entry->bytes = blk_rq_bytes(rq); @@ -512,7 +512,7 @@ TRACE_EVENT(block_rq_remap, ), TP_fast_assign( - __entry->dev = disk_devt(rq->rq_disk); + __entry->dev = disk_devt(rq->q->disk); __entry->sector = blk_rq_pos(rq); __entry->nr_sector = blk_rq_sectors(rq); __entry->old_dev = dev; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 1183c88634aa..431e41bc4c23 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1045,7 +1045,7 @@ static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev, } r.device_from = cpu_to_be32(dev); - r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); + r.device_to = cpu_to_be32(disk_devt(rq->q->disk)); r.sector_from = cpu_to_be64(from); __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), -- cgit v1.2.3 From b84ba30b6c7a75babdf73b83bc3c7b59b944501a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Nov 2021 13:18:01 +0100 Subject: block: remove the gendisk argument to blk_execute_rq Remove the gendisk aregument to blk_execute_rq and blk_execute_rq_nowait given that it is unused now. Also convert the boolean at_head parameter to actually use the bool type while touching the prototype. Signed-off-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20211126121802.2090656-5-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-mq.c | 10 +++------- block/bsg-lib.c | 2 +- drivers/block/mtip32xx/mtip32xx.c | 2 +- drivers/block/paride/pd.c | 2 +- drivers/block/pktcdvd.c | 2 +- drivers/block/sx8.c | 4 ++-- drivers/block/virtio_blk.c | 2 +- drivers/mmc/core/block.c | 10 +++++----- drivers/nvme/host/core.c | 4 ++-- drivers/nvme/host/pci.c | 7 +++---- drivers/nvme/target/passthru.c | 3 +-- drivers/scsi/scsi_bsg.c | 2 +- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/scsi_ioctl.c | 4 ++-- drivers/scsi/scsi_lib.c | 2 +- drivers/scsi/sg.c | 2 +- drivers/scsi/sr.c | 2 +- drivers/scsi/st.c | 2 +- drivers/scsi/ufs/ufshpb.c | 4 ++-- drivers/target/target_core_pscsi.c | 2 +- include/linux/blk-mq.h | 7 +++---- 21 files changed, 35 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index f1abfd2e24f7..ecfc47fad236 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1153,7 +1153,6 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error) /** * blk_execute_rq_nowait - insert a request to I/O scheduler for execution - * @bd_disk: matching gendisk * @rq: request to insert * @at_head: insert request at head or tail of queue * @done: I/O completion handler @@ -1165,8 +1164,7 @@ static void blk_end_sync_rq(struct request *rq, blk_status_t error) * Note: * This function will invoke @done directly if the queue is dead. */ -void blk_execute_rq_nowait(struct gendisk *bd_disk, struct request *rq, - int at_head, rq_end_io_fn *done) +void blk_execute_rq_nowait(struct request *rq, bool at_head, rq_end_io_fn *done) { WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); @@ -1204,7 +1202,6 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait) /** * blk_execute_rq - insert a request into queue for execution - * @bd_disk: matching gendisk * @rq: request to insert * @at_head: insert request at head or tail of queue * @@ -1213,14 +1210,13 @@ static void blk_rq_poll_completion(struct request *rq, struct completion *wait) * for execution and wait for completion. * Return: The blk_status_t result provided to blk_mq_end_request(). */ -blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, - int at_head) +blk_status_t blk_execute_rq(struct request *rq, bool at_head) { DECLARE_COMPLETION_ONSTACK(wait); unsigned long hang_check; rq->end_io_data = &wait; - blk_execute_rq_nowait(bd_disk, rq, at_head, blk_end_sync_rq); + blk_execute_rq_nowait(rq, at_head, blk_end_sync_rq); /* Prevent hang_check timer from firing at us during very long I/O */ hang_check = sysctl_hung_task_timeout_secs; diff --git a/block/bsg-lib.c b/block/bsg-lib.c index 10aa378702fa..acfe1357bf6c 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -92,7 +92,7 @@ static int bsg_transport_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, goto out_unmap_bidi_rq; bio = rq->bio; - blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL)); + blk_execute_rq(rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL)); /* * The assignments below don't make much sense, but are kept for diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index c91b9010c1a6..30f471021a40 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -1015,7 +1015,7 @@ static int mtip_exec_internal_command(struct mtip_port *port, rq->timeout = timeout; /* insert request and run queue */ - blk_execute_rq(NULL, rq, true); + blk_execute_rq(rq, true); if (int_cmd->status) { dev_err(&dd->pdev->dev, "Internal command [%02X] failed %d\n", diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 4f8cce510562..3637c38c72f9 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -781,7 +781,7 @@ static int pd_special_command(struct pd_unit *disk, req = blk_mq_rq_to_pdu(rq); req->func = func; - blk_execute_rq(disk->gd, rq, 0); + blk_execute_rq(rq, false); blk_mq_free_request(rq); return 0; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 3af0499857ec..887c98d61684 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -722,7 +722,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * if (cgc->quiet) rq->rq_flags |= RQF_QUIET; - blk_execute_rq(pd->bdev->bd_disk, rq, 0); + blk_execute_rq(rq, false); if (scsi_req(rq)->result) ret = -EIO; out: diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index d1676fe0da1a..b361583944b9 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -540,7 +540,7 @@ static int carm_array_info (struct carm_host *host, unsigned int array_idx) spin_unlock_irq(&host->lock); DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag); - blk_execute_rq_nowait(NULL, rq, true, NULL); + blk_execute_rq_nowait(rq, true, NULL); return 0; @@ -579,7 +579,7 @@ static int carm_send_special (struct carm_host *host, carm_sspc_t func) crq->msg_bucket = (u32) rc; DPRINTK("blk_execute_rq_nowait, tag == %u\n", rq->tag); - blk_execute_rq_nowait(NULL, rq, true, NULL); + blk_execute_rq_nowait(rq, true, NULL); return 0; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index cfa303fa7318..c3dc3cd7a779 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -384,7 +384,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) if (err) goto out; - blk_execute_rq(vblk->disk, req, false); + blk_execute_rq(req, false); err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req))); out: blk_mq_free_request(req); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index dc094f73d335..ef8f45fa2cee 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -264,7 +264,7 @@ static ssize_t power_ro_lock_store(struct device *dev, goto out_put; } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_BOOT_WP; - blk_execute_rq(NULL, req, 0); + blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; blk_mq_free_request(req); @@ -657,7 +657,7 @@ static int mmc_blk_ioctl_cmd(struct mmc_blk_data *md, rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; req_to_mmc_queue_req(req)->drv_op_data = idatas; req_to_mmc_queue_req(req)->ioc_count = 1; - blk_execute_rq(NULL, req, 0); + blk_execute_rq(req, false); ioc_err = req_to_mmc_queue_req(req)->drv_op_result; err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata); blk_mq_free_request(req); @@ -726,7 +726,7 @@ static int mmc_blk_ioctl_multi_cmd(struct mmc_blk_data *md, rpmb ? MMC_DRV_OP_IOCTL_RPMB : MMC_DRV_OP_IOCTL; req_to_mmc_queue_req(req)->drv_op_data = idata; req_to_mmc_queue_req(req)->ioc_count = num_of_cmds; - blk_execute_rq(NULL, req, 0); + blk_execute_rq(req, false); ioc_err = req_to_mmc_queue_req(req)->drv_op_result; /* copy to user if data and response */ @@ -2743,7 +2743,7 @@ static int mmc_dbg_card_status_get(void *data, u64 *val) if (IS_ERR(req)) return PTR_ERR(req); req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_CARD_STATUS; - blk_execute_rq(NULL, req, 0); + blk_execute_rq(req, false); ret = req_to_mmc_queue_req(req)->drv_op_result; if (ret >= 0) { *val = ret; @@ -2782,7 +2782,7 @@ static int mmc_ext_csd_open(struct inode *inode, struct file *filp) } req_to_mmc_queue_req(req)->drv_op = MMC_DRV_OP_GET_EXT_CSD; req_to_mmc_queue_req(req)->drv_op_data = &ext_csd; - blk_execute_rq(NULL, req, 0); + blk_execute_rq(req, false); err = req_to_mmc_queue_req(req)->drv_op_result; blk_mq_free_request(req); if (err) { diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 4c63564adeaa..f82c098b1a61 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1056,7 +1056,7 @@ static int nvme_execute_rq(struct gendisk *disk, struct request *rq, { blk_status_t status; - status = blk_execute_rq(disk, rq, at_head); + status = blk_execute_rq(rq, at_head); if (nvme_req(rq)->flags & NVME_REQ_CANCELLED) return -EINTR; if (nvme_req(rq)->status) @@ -1283,7 +1283,7 @@ static void nvme_keep_alive_work(struct work_struct *work) rq->timeout = ctrl->kato * HZ; rq->end_io_data = ctrl; - blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io); + blk_execute_rq_nowait(rq, false, nvme_keep_alive_end_io); } static void nvme_start_keep_alive(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index ca2ee806d74b..8637538f3fd5 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1371,7 +1371,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) } abort_req->end_io_data = NULL; - blk_execute_rq_nowait(NULL, abort_req, 0, abort_endio); + blk_execute_rq_nowait(abort_req, false, abort_endio); /* * The aborted req will be completed on receiving the abort req. @@ -2416,9 +2416,8 @@ static int nvme_delete_queue(struct nvme_queue *nvmeq, u8 opcode) req->end_io_data = nvmeq; init_completion(&nvmeq->delete_done); - blk_execute_rq_nowait(NULL, req, false, - opcode == nvme_admin_delete_cq ? - nvme_del_cq_end : nvme_del_queue_end); + blk_execute_rq_nowait(req, false, opcode == nvme_admin_delete_cq ? + nvme_del_cq_end : nvme_del_queue_end); return 0; } diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index f0efb3537989..9e5b89ae29df 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -284,8 +284,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req) schedule_work(&req->p.work); } else { rq->end_io_data = req; - blk_execute_rq_nowait(ns ? ns->disk : NULL, rq, 0, - nvmet_passthru_req_done); + blk_execute_rq_nowait(rq, false, nvmet_passthru_req_done); } if (ns) diff --git a/drivers/scsi/scsi_bsg.c b/drivers/scsi/scsi_bsg.c index 081b84bb7985..b7a464383cc0 100644 --- a/drivers/scsi/scsi_bsg.c +++ b/drivers/scsi/scsi_bsg.c @@ -60,7 +60,7 @@ static int scsi_bsg_sg_io_fn(struct request_queue *q, struct sg_io_v4 *hdr, goto out_free_cmd; bio = rq->bio; - blk_execute_rq(NULL, rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL)); + blk_execute_rq(rq, !(hdr->flags & BSG_FLAG_Q_AT_TAIL)); /* * fill in all the output members diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index 2371edbc3af4..3eae2392ef15 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -2040,7 +2040,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev) req->timeout = 10 * HZ; rq->retries = 5; - blk_execute_rq_nowait(NULL, req, 1, eh_lock_door_done); + blk_execute_rq_nowait(req, true, eh_lock_door_done); } /** diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c index 400df3354cd6..340ba0ad6e70 100644 --- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -483,7 +483,7 @@ static int sg_io(struct scsi_device *sdev, struct gendisk *disk, start_time = jiffies; - blk_execute_rq(disk, rq, at_head); + blk_execute_rq(rq, at_head); hdr->duration = jiffies_to_msecs(jiffies - start_time); @@ -620,7 +620,7 @@ static int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, goto error; } - blk_execute_rq(disk, rq, 0); + blk_execute_rq(rq, false); err = req->result & 0xff; /* only 8 bit SCSI status */ if (err) { diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index c23cf8e7b3c3..35e381f6d371 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -241,7 +241,7 @@ int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd, /* * head injection *required* here otherwise quiesce won't work */ - blk_execute_rq(NULL, req, 1); + blk_execute_rq(req, true); /* * Some devices (USB mass-storage in particular) may transfer diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index 141099ab9092..6c8ffad88f9e 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -833,7 +833,7 @@ sg_common_write(Sg_fd * sfp, Sg_request * srp, srp->rq->timeout = timeout; kref_get(&sfp->f_ref); /* sg_rq_end_io() does kref_put(). */ - blk_execute_rq_nowait(NULL, srp->rq, at_head, sg_rq_end_io); + blk_execute_rq_nowait(srp->rq, at_head, sg_rq_end_io); return 0; } diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 7db595c08b20..c29589815468 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -994,7 +994,7 @@ static int sr_read_cdda_bpc(struct cdrom_device_info *cdi, void __user *ubuf, rq->timeout = 60 * HZ; bio = rq->bio; - blk_execute_rq(disk, rq, 0); + blk_execute_rq(rq, false); if (scsi_req(rq)->result) { struct scsi_sense_hdr sshdr; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index c2d5608f6b1a..06acc7db7755 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -581,7 +581,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, rq->retries = retries; req->end_io_data = SRpnt; - blk_execute_rq_nowait(NULL, req, 1, st_scsi_execute_end); + blk_execute_rq_nowait(req, true, st_scsi_execute_end); return 0; } diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c index ded5ba9b1466..13cd21204bf9 100644 --- a/drivers/scsi/ufs/ufshpb.c +++ b/drivers/scsi/ufs/ufshpb.c @@ -677,7 +677,7 @@ static void ufshpb_execute_umap_req(struct ufshpb_lu *hpb, ufshpb_set_unmap_cmd(rq->cmd, rgn); rq->cmd_len = HPB_WRITE_BUFFER_CMD_LENGTH; - blk_execute_rq_nowait(NULL, req, 1, ufshpb_umap_req_compl_fn); + blk_execute_rq_nowait(req, true, ufshpb_umap_req_compl_fn); hpb->stats.umap_req_cnt++; } @@ -719,7 +719,7 @@ static int ufshpb_execute_map_req(struct ufshpb_lu *hpb, map_req->rb.srgn_idx, mem_size); rq->cmd_len = HPB_READ_BUFFER_CMD_LENGTH; - blk_execute_rq_nowait(NULL, req, 1, ufshpb_map_req_compl_fn); + blk_execute_rq_nowait(req, true, ufshpb_map_req_compl_fn); hpb->stats.map_req_cnt++; return 0; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 7fa57fb57bf2..807d06ecadee 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1005,7 +1005,7 @@ pscsi_execute_cmd(struct se_cmd *cmd) req->timeout = PS_TIMEOUT_OTHER; scsi_req(req)->retries = PS_RETRY; - blk_execute_rq_nowait(NULL, req, (cmd->sam_task_attr == TCM_HEAD_TAG), + blk_execute_rq_nowait(req, cmd->sam_task_attr == TCM_HEAD_TAG, pscsi_req_done); return 0; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ede7bef8880a..1b87b7c8bbff 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -924,10 +924,9 @@ int blk_rq_unmap_user(struct bio *); int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); int blk_rq_append_bio(struct request *rq, struct bio *bio); -void blk_execute_rq_nowait(struct gendisk *, struct request *, int, - rq_end_io_fn *); -blk_status_t blk_execute_rq(struct gendisk *bd_disk, struct request *rq, - int at_head); +void blk_execute_rq_nowait(struct request *rq, bool at_head, + rq_end_io_fn *end_io); +blk_status_t blk_execute_rq(struct request *rq, bool at_head); struct req_iterator { struct bvec_iter iter; -- cgit v1.2.3 From f7e5b9bfa6c8820407b64eabc1f29c9a87e8993d Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 29 Nov 2021 10:39:29 -0500 Subject: siphash: use _unaligned version by default On ARM v6 and later, we define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS because the ordinary load/store instructions (ldr, ldrh, ldrb) can tolerate any misalignment of the memory address. However, load/store double and load/store multiple instructions (ldrd, ldm) may still only be used on memory addresses that are 32-bit aligned, and so we have to use the CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS macro with care, or we may end up with a severe performance hit due to alignment traps that require fixups by the kernel. Testing shows that this currently happens with clang-13 but not gcc-11. In theory, any compiler version can produce this bug or other problems, as we are dealing with undefined behavior in C99 even on architectures that support this in hardware, see also https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100363. Fortunately, the get_unaligned() accessors do the right thing: when building for ARMv6 or later, the compiler will emit unaligned accesses using the ordinary load/store instructions (but avoid the ones that require 32-bit alignment). When building for older ARM, those accessors will emit the appropriate sequence of ldrb/mov/orr instructions. And on architectures that can truly tolerate any kind of misalignment, the get_unaligned() accessors resolve to the leXX_to_cpup accessors that operate on aligned addresses. Since the compiler will in fact emit ldrd or ldm instructions when building this code for ARM v6 or later, the solution is to use the unaligned accessors unconditionally on architectures where this is known to be fast. The _aligned version of the hash function is however still needed to get the best performance on architectures that cannot do any unaligned access in hardware. This new version avoids the undefined behavior and should produce the fastest hash on all architectures we support. Link: https://lore.kernel.org/linux-arm-kernel/20181008211554.5355-4-ard.biesheuvel@linaro.org/ Link: https://lore.kernel.org/linux-crypto/CAK8P3a2KfmmGDbVHULWevB0hv71P2oi2ZCHEAqT=8dQfa0=cqQ@mail.gmail.com/ Reported-by: Ard Biesheuvel Fixes: 2c956a60778c ("siphash: add cryptographically secure PRF") Signed-off-by: Arnd Bergmann Reviewed-by: Jason A. Donenfeld Acked-by: Ard Biesheuvel Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski --- include/linux/siphash.h | 14 ++++---------- lib/siphash.c | 12 ++++++------ 2 files changed, 10 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/siphash.h b/include/linux/siphash.h index bf21591a9e5e..0cda61855d90 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key) } u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); -#endif u64 siphash_1u64(const u64 a, const siphash_key_t *key); u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key); @@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len, static inline u64 siphash(const void *data, size_t len, const siphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) return __siphash_unaligned(data, len, key); -#endif return ___siphash_aligned(data, len, key); } @@ -96,10 +93,8 @@ typedef struct { u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key); -#endif u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key); u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key); @@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, static inline u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) return __hsiphash_unaligned(data, len, key); -#endif return ___hsiphash_aligned(data, len, key); } diff --git a/lib/siphash.c b/lib/siphash.c index a90112ee72a1..72b9068ab57b 100644 --- a/lib/siphash.c +++ b/lib/siphash.c @@ -49,6 +49,7 @@ SIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); @@ -80,8 +81,8 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) POSTAMBLE } EXPORT_SYMBOL(__siphash_aligned); +#endif -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); @@ -113,7 +114,6 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) POSTAMBLE } EXPORT_SYMBOL(__siphash_unaligned); -#endif /** * siphash_1u64 - compute 64-bit siphash PRF value of a u64 @@ -250,6 +250,7 @@ EXPORT_SYMBOL(siphash_3u32); HSIPROUND; \ return (v0 ^ v1) ^ (v2 ^ v3); +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u64)); @@ -280,8 +281,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); +#endif -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { @@ -313,7 +314,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len, HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); -#endif /** * hsiphash_1u32 - compute 64-bit hsiphash PRF value of a u32 @@ -418,6 +418,7 @@ EXPORT_SYMBOL(hsiphash_4u32); HSIPROUND; \ return v1 ^ v3; +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) { const u8 *end = data + len - (len % sizeof(u32)); @@ -438,8 +439,8 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_aligned); +#endif -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key) { @@ -461,7 +462,6 @@ u32 __hsiphash_unaligned(const void *data, size_t len, HPOSTAMBLE } EXPORT_SYMBOL(__hsiphash_unaligned); -#endif /** * hsiphash_1u32 - compute 32-bit hsiphash PRF value of a u32 -- cgit v1.2.3 From 4047b9db1aa7512a10ba3560a3f63821c8c40235 Mon Sep 17 00:00:00 2001 From: Bhupesh Sharma Date: Mon, 29 Nov 2021 01:28:54 +0530 Subject: net: stmmac: Add platform level debug register dump feature dwmac-qcom-ethqos currently exposes a mechanism to dump rgmii registers after the 'stmmac_dvr_probe()' returns. However with commit 5ec55823438e ("net: stmmac: add clocks management for gmac driver"), we now let 'pm_runtime_put()' disable the clocks before returning from 'stmmac_dvr_probe()'. This causes a crash when 'rgmii_dump()' register dumps are enabled, as the clocks are already off. Since other dwmac drivers (possible future users as well) might require a similar register dump feature, introduce a platform level callback to allow the same. This fixes the crash noticed while enabling rgmii_dump() dumps in dwmac-qcom-ethqos driver as well. It also allows future changes to keep a invoking the register dump callback from the correct place inside 'stmmac_dvr_probe()'. Fixes: 5ec55823438e ("net: stmmac: add clocks management for gmac driver") Cc: Joakim Zhang Cc: David S. Miller Signed-off-by: Bhupesh Sharma Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 7 ++++--- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 +++ include/linux/stmmac.h | 1 + 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 8fea48e477e6..2ffa0a11eea5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -113,8 +113,10 @@ static void rgmii_updatel(struct qcom_ethqos *ethqos, rgmii_writel(ethqos, temp, offset); } -static void rgmii_dump(struct qcom_ethqos *ethqos) +static void rgmii_dump(void *priv) { + struct qcom_ethqos *ethqos = priv; + dev_dbg(ðqos->pdev->dev, "Rgmii register dump\n"); dev_dbg(ðqos->pdev->dev, "RGMII_IO_MACRO_CONFIG: %x\n", rgmii_readl(ethqos, RGMII_IO_MACRO_CONFIG)); @@ -519,6 +521,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->bsp_priv = ethqos; plat_dat->fix_mac_speed = ethqos_fix_mac_speed; + plat_dat->dump_debug_regs = rgmii_dump; plat_dat->has_gmac4 = 1; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); @@ -527,8 +530,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev) if (ret) goto err_clk; - rgmii_dump(ethqos); - return ret; err_clk: diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 89a6c35e2546..cc1075c08996 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -7211,6 +7211,9 @@ int stmmac_dvr_probe(struct device *device, stmmac_init_fs(ndev); #endif + if (priv->plat->dump_debug_regs) + priv->plat->dump_debug_regs(priv->plat->bsp_priv); + /* Let pm_runtime_put() disable the clocks. * If CONFIG_PM is not enabled, the clocks will stay powered. */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 89b8e208cd7b..24eea1b05ca2 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -233,6 +233,7 @@ struct plat_stmmacenet_data { int (*clks_config)(void *priv, bool enabled); int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); + void (*dump_debug_regs)(void *priv); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; -- cgit v1.2.3 From 79364031c5b4365ca28ac0fa00acfab5bf465be1 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Sat, 27 Nov 2021 17:32:00 +0100 Subject: bpf: Make sure bpf_disable_instrumentation() is safe vs preemption. The initial implementation of migrate_disable() for mainline was a wrapper around preempt_disable(). RT kernels substituted this with a real migrate disable implementation. Later on mainline gained true migrate disable support, but neither documentation nor affected code were updated. Remove stale comments claiming that migrate_disable() is PREEMPT_RT only. Don't use __this_cpu_inc() in the !PREEMPT_RT path because preemption is not disabled and the RMW operation can be preempted. Fixes: 74d862b682f51 ("sched: Make migrate_disable/enable() independent of RT") Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211127163200.10466-3-bigeasy@linutronix.de --- include/linux/bpf.h | 16 ++-------------- include/linux/filter.h | 3 --- 2 files changed, 2 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 84ff6ef49462..755f38e893be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1353,28 +1353,16 @@ extern struct mutex bpf_stats_enabled_mutex; * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. - * - * Use the preemption safe inc/dec variants on RT because migrate disable - * is preemptible on RT and preemption in the middle of the RMW operation - * might lead to inconsistent state. Use the raw variants for non RT - * kernels as migrate_disable() maps to preempt_disable() so the slightly - * more expensive save operation can be avoided. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_inc(bpf_prog_active); - else - __this_cpu_inc(bpf_prog_active); + this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { - if (IS_ENABLED(CONFIG_PREEMPT_RT)) - this_cpu_dec(bpf_prog_active); - else - __this_cpu_dec(bpf_prog_active); + this_cpu_dec(bpf_prog_active); migrate_enable(); } diff --git a/include/linux/filter.h b/include/linux/filter.h index 24b7ed2677af..534f678ca50f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -640,9 +640,6 @@ static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. - * - * For non RT enabled kernels migrate_disable/enable() maps to - * preempt_disable/enable(), i.e. it disables also preemption. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) -- cgit v1.2.3 From e6f2dd0f80674e9d5960337b3e9c2a242441b326 Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Mon, 29 Nov 2021 19:06:19 -0800 Subject: bpf: Add bpf_loop helper This patch adds the kernel-side and API changes for a new helper function, bpf_loop: long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags); where long (*callback_fn)(u32 index, void *ctx); bpf_loop invokes the "callback_fn" **nr_loops** times or until the callback_fn returns 1. The callback_fn can only return 0 or 1, and this is enforced by the verifier. The callback_fn index is zero-indexed. A few things to please note: ~ The "u64 flags" parameter is currently unused but is included in case a future use case for it arises. ~ In the kernel-side implementation of bpf_loop (kernel/bpf/bpf_iter.c), bpf_callback_t is used as the callback function cast. ~ A program can have nested bpf_loop calls but the program must still adhere to the verifier constraint of its stack depth (the stack depth cannot exceed MAX_BPF_STACK)) ~ Recursive callback_fns do not pass the verifier, due to the call stack for these being too deep. ~ The next patch will include the tests and benchmark Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211130030622.4131246-2-joannekoong@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 25 ++++++++++++ kernel/bpf/bpf_iter.c | 35 +++++++++++++++++ kernel/bpf/helpers.c | 2 + kernel/bpf/verifier.c | 88 ++++++++++++++++++++++++++---------------- tools/include/uapi/linux/bpf.h | 25 ++++++++++++ 6 files changed, 142 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cc7a0c36e7df..cad0829710be 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2164,6 +2164,7 @@ extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; +extern const struct bpf_func_proto bpf_loop_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index a69e4b04ffeb..211b43afd0fb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4957,6 +4957,30 @@ union bpf_attr { * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. * **-EBUSY** if failed to try lock mmap_lock. * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5140,6 +5164,7 @@ union bpf_attr { FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ FN(find_vma), \ + FN(loop), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b2ee45064e06..b7aef5b3416d 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -714,3 +714,38 @@ const struct bpf_func_proto bpf_for_each_map_elem_proto = { .arg3_type = ARG_PTR_TO_STACK_OR_NULL, .arg4_type = ARG_ANYTHING, }; + +/* maximum number of loops */ +#define MAX_LOOPS BIT(23) + +BPF_CALL_4(bpf_loop, u32, nr_loops, void *, callback_fn, void *, callback_ctx, + u64, flags) +{ + bpf_callback_t callback = (bpf_callback_t)callback_fn; + u64 ret; + u32 i; + + if (flags) + return -EINVAL; + if (nr_loops > MAX_LOOPS) + return -E2BIG; + + for (i = 0; i < nr_loops; i++) { + ret = callback((u64)i, (u64)(long)callback_ctx, 0, 0, 0); + /* return value: 0 - continue, 1 - stop and return */ + if (ret) + return i + 1; + } + + return i; +} + +const struct bpf_func_proto bpf_loop_proto = { + .func = bpf_loop, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_PTR_TO_FUNC, + .arg3_type = ARG_PTR_TO_STACK_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 1ffd469c217f..52188004a9c3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1378,6 +1378,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ringbuf_query_proto; case BPF_FUNC_for_each_map_elem: return &bpf_for_each_map_elem_proto; + case BPF_FUNC_loop: + return &bpf_loop_proto; default: break; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0763cca139a7..d7678d8a925c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6085,6 +6085,27 @@ static int set_map_elem_callback_state(struct bpf_verifier_env *env, return 0; } +static int set_loop_callback_state(struct bpf_verifier_env *env, + struct bpf_func_state *caller, + struct bpf_func_state *callee, + int insn_idx) +{ + /* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, + * u64 flags); + * callback_fn(u32 index, void *callback_ctx); + */ + callee->regs[BPF_REG_1].type = SCALAR_VALUE; + callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; + + /* unused */ + __mark_reg_not_init(env, &callee->regs[BPF_REG_3]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_4]); + __mark_reg_not_init(env, &callee->regs[BPF_REG_5]); + + callee->in_callback_fn = true; + return 0; +} + static int set_timer_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -6458,13 +6479,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return err; } - if (func_id == BPF_FUNC_tail_call) { - err = check_reference_leak(env); - if (err) { - verbose(env, "tail_call would lead to reference leak\n"); - return err; - } - } else if (is_release_function(func_id)) { + if (is_release_function(func_id)) { err = release_reference(env, meta.ref_obj_id); if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", @@ -6475,42 +6490,47 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); - /* check that flags argument in get_local_storage(map, flags) is 0, - * this is required because get_local_storage() can't return an error. - */ - if (func_id == BPF_FUNC_get_local_storage && - !register_is_null(®s[BPF_REG_2])) { - verbose(env, "get_local_storage() doesn't support non-zero flags\n"); - return -EINVAL; - } - - if (func_id == BPF_FUNC_for_each_map_elem) { + switch (func_id) { + case BPF_FUNC_tail_call: + err = check_reference_leak(env); + if (err) { + verbose(env, "tail_call would lead to reference leak\n"); + return err; + } + break; + case BPF_FUNC_get_local_storage: + /* check that flags argument in get_local_storage(map, flags) is 0, + * this is required because get_local_storage() can't return an error. + */ + if (!register_is_null(®s[BPF_REG_2])) { + verbose(env, "get_local_storage() doesn't support non-zero flags\n"); + return -EINVAL; + } + break; + case BPF_FUNC_for_each_map_elem: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_map_elem_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_timer_set_callback) { + break; + case BPF_FUNC_timer_set_callback: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_timer_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_find_vma) { + break; + case BPF_FUNC_find_vma: err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, set_find_vma_callback_state); - if (err < 0) - return -EINVAL; - } - - if (func_id == BPF_FUNC_snprintf) { + break; + case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); - if (err < 0) - return err; + break; + case BPF_FUNC_loop: + err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, + set_loop_callback_state); + break; } + if (err) + return err; + /* reset caller saved regs */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index a69e4b04ffeb..211b43afd0fb 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4957,6 +4957,30 @@ union bpf_attr { * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. * **-EBUSY** if failed to try lock mmap_lock. * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5140,6 +5164,7 @@ union bpf_attr { FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ FN(find_vma), \ + FN(loop), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 7ad639840acf2800b5f387c495795f995a67a329 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 29 Nov 2021 13:06:43 +0000 Subject: thread_info: Add helpers to snapshot thread flags In there are helpers to manipulate individual thread flags, but where code wants to check several flags at once, it must open code reading current_thread_info()->flags and operating on a snapshot. As some flags can be set remotely it's necessary to use READ_ONCE() to get a consistent snapshot even when IRQs are disabled, but some code forgets to do this. Generally this is unlike to cause a problem in practice, but it is somewhat unsound, and KCSAN will legitimately warn that there is a data race. To make it easier to do the right thing, and to highlight that concurrent modification is possible, add new helpers to snapshot the flags, which should be used in preference to plain reads. Subsequent patches will move existing code to use the new helpers. Signed-off-by: Mark Rutland Signed-off-by: Thomas Gleixner Reviewed-by: Thomas Gleixner Acked-by: Marco Elver Acked-by: Paul E. McKenney Cc: Boqun Feng Cc: Dmitry Vyukov Cc: Peter Zijlstra Cc: Will Deacon Link: https://lore.kernel.org/r/20211129130653.2037928-2-mark.rutland@arm.com --- include/linux/thread_info.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index ad0c4e041030..73a6f34b3847 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -118,6 +118,15 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) return test_bit(flag, (unsigned long *)&ti->flags); } +/* + * This may be used in noinstr code, and needs to be __always_inline to prevent + * inadvertent instrumentation. + */ +static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) +{ + return READ_ONCE(ti->flags); +} + #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ @@ -130,6 +139,11 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) +#define read_thread_flags() \ + read_ti_thread_flags(current_thread_info()) + +#define read_task_thread_flags(t) \ + read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ -- cgit v1.2.3 From 6ce895128b3bff738fe8d9dd74747a03e319e466 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Mon, 29 Nov 2021 13:06:44 +0000 Subject: entry: Snapshot thread flags Some thread flags can be set remotely, and so even when IRQs are disabled, the flags can change under our feet. Generally this is unlikely to cause a problem in practice, but it is somewhat unsound, and KCSAN will legitimately warn that there is a data race. To avoid such issues, a snapshot of the flags has to be taken prior to using them. Some places already use READ_ONCE() for that, others do not. Convert them all to the new flag accessor helpers. Signed-off-by: Mark Rutland Signed-off-by: Thomas Gleixner Acked-by: Paul E. McKenney Link: https://lore.kernel.org/r/20211129130653.2037928-3-mark.rutland@arm.com --- include/linux/entry-kvm.h | 2 +- kernel/entry/common.c | 4 ++-- kernel/entry/kvm.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h index 0d7865a0731c..07c878d6e323 100644 --- a/include/linux/entry-kvm.h +++ b/include/linux/entry-kvm.h @@ -75,7 +75,7 @@ static inline void xfer_to_guest_mode_prepare(void) */ static inline bool __xfer_to_guest_mode_work_pending(void) { - unsigned long ti_work = READ_ONCE(current_thread_info()->flags); + unsigned long ti_work = read_thread_flags(); return !!(ti_work & XFER_TO_GUEST_MODE_WORK); } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index d5a61d565ad5..bad713684c2e 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -187,7 +187,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, /* Check if any of the above work has queued a deferred wakeup */ tick_nohz_user_enter_prepare(); - ti_work = READ_ONCE(current_thread_info()->flags); + ti_work = read_thread_flags(); } /* Return the latest work state for arch_exit_to_user_mode() */ @@ -196,7 +196,7 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs, static void exit_to_user_mode_prepare(struct pt_regs *regs) { - unsigned long ti_work = READ_ONCE(current_thread_info()->flags); + unsigned long ti_work = read_thread_flags(); lockdep_assert_irqs_disabled(); diff --git a/kernel/entry/kvm.c b/kernel/entry/kvm.c index 49972ee99aff..96d476e06c77 100644 --- a/kernel/entry/kvm.c +++ b/kernel/entry/kvm.c @@ -26,7 +26,7 @@ static int xfer_to_guest_mode_work(struct kvm_vcpu *vcpu, unsigned long ti_work) if (ret) return ret; - ti_work = READ_ONCE(current_thread_info()->flags); + ti_work = read_thread_flags(); } while (ti_work & XFER_TO_GUEST_MODE_WORK || need_resched()); return 0; } @@ -43,7 +43,7 @@ int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu) * disabled in the inner loop before going into guest mode. No need * to disable interrupts here. */ - ti_work = READ_ONCE(current_thread_info()->flags); + ti_work = read_thread_flags(); if (!(ti_work & XFER_TO_GUEST_MODE_WORK)) return 0; -- cgit v1.2.3 From 4946f15e8c334840bf277a0bf924371eae120fcd Mon Sep 17 00:00:00 2001 From: Rikard Falkeborn Date: Tue, 30 Nov 2021 22:40:43 +0100 Subject: genirq/generic_chip: Constify irq_generic_chip_ops The only usage of irq_generic_chip_ops is to pass its address to irq_domain_add_linear() which takes a pointer to const struct irq_domain_ops. Make it const to allow the compiler to put it in read-only memory. [ tglx: Fixed subject prefix ] Signed-off-by: Rikard Falkeborn Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/20211130214043.1257585-1-rikard.falkeborn@gmail.com --- include/linux/irqdomain.h | 2 +- kernel/irq/generic-chip.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 553da4899f55..d476405802e9 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -131,7 +131,7 @@ struct irq_domain_ops { #endif }; -extern struct irq_domain_ops irq_generic_chip_ops; +extern const struct irq_domain_ops irq_generic_chip_ops; struct irq_domain_chip_generic; diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c index 6f29bf4c8515..f0862eb6b506 100644 --- a/kernel/irq/generic-chip.c +++ b/kernel/irq/generic-chip.c @@ -451,7 +451,7 @@ static void irq_unmap_generic_chip(struct irq_domain *d, unsigned int virq) } -struct irq_domain_ops irq_generic_chip_ops = { +const struct irq_domain_ops irq_generic_chip_ops = { .map = irq_map_generic_chip, .unmap = irq_unmap_generic_chip, .xlate = irq_domain_xlate_onetwocell, -- cgit v1.2.3 From 24ba53017e188e031f9cb8b290286fad52d2af00 Mon Sep 17 00:00:00 2001 From: Chun-Hung Tseng Date: Wed, 15 Sep 2021 17:02:18 +0800 Subject: rcu: Replace ________p1 and _________p1 with __UNIQUE_ID(rcu) This commit replaces both ________p1 and _________p1 with __UNIQUE_ID(rcu), and also adjusts the callers of the affected macros. __UNIQUE_ID(rcu) will generate unique variable names during compilation, which eliminates the need of ________p1 and _________p1 (both having 4 occurrences prior to the code change). This also avoids the variable name shadowing issue, or at least makes those wishing to cause shadowing problems work much harder to do so. The same idea is used for the min/max macros (commit 589a978 and commit e9092d0). Signed-off-by: Jim Huang Signed-off-by: Chun-Hung Tseng Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 50 +++++++++++++++++++++++++++--------------------- include/linux/srcu.h | 3 ++- 2 files changed, 30 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 5e0beb5c5659..88b42eb46406 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -364,6 +364,12 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ +#define __unrcu_pointer(p, local) \ +({ \ + typeof(*p) *local = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(local)); \ +}) /** * unrcu_pointer - mark a pointer as not being RCU protected * @p: pointer needing to lose its __rcu property @@ -371,39 +377,35 @@ static inline void rcu_preempt_sleep_check(void) { } * Converts @p from an __rcu pointer to a __kernel pointer. * This allows an __rcu pointer to be used with xchg() and friends. */ -#define unrcu_pointer(p) \ -({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)(p); \ - rcu_check_sparse(p, __rcu); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ -}) +#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) -#define __rcu_access_pointer(p, space) \ +#define __rcu_access_pointer(p, local, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ + typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ + ((typeof(*p) __force __kernel *)(local)); \ }) -#define __rcu_dereference_check(p, c, space) \ +#define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ + typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(________p1)); \ + ((typeof(*p) __force __kernel *)(local)); \ }) -#define __rcu_dereference_protected(p, c, space) \ +#define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) -#define rcu_dereference_raw(p) \ +#define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(p) ________p1 = READ_ONCE(p); \ - ((typeof(*p) __force __kernel *)(________p1)); \ + typeof(p) local = READ_ONCE(p); \ + ((typeof(*p) __force __kernel *)(local)); \ }) +#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable @@ -490,7 +492,7 @@ do { \ * when tearing down multi-linked structures after a grace period * has elapsed. */ -#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) +#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking @@ -526,7 +528,8 @@ do { \ * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking @@ -541,7 +544,8 @@ do { \ * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking @@ -556,7 +560,8 @@ do { \ * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_sched_held(), \ __rcu) /* @@ -566,7 +571,8 @@ do { \ * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ -#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) +#define rcu_dereference_raw_check(p) \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented @@ -585,7 +591,7 @@ do { \ * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) + __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** diff --git a/include/linux/srcu.h b/include/linux/srcu.h index e6011a9975af..01226e4d960a 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -117,7 +117,8 @@ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ - __rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing -- cgit v1.2.3 From 2407a64f8045552203ee5cb9904ce75ce2fceef4 Mon Sep 17 00:00:00 2001 From: Changbin Du Date: Tue, 28 Sep 2021 08:21:28 +0800 Subject: rcu: in_irq() cleanup This commit replaces the obsolete and ambiguous macro in_irq() with its shiny new in_hardirq() equivalent. Signed-off-by: Changbin Du Signed-off-by: Paul E. McKenney --- include/linux/rcutiny.h | 2 +- kernel/rcu/tree.c | 2 +- kernel/rcu/tree_plugin.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 9be015305f9f..858f4d429946 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -85,7 +85,7 @@ static inline void rcu_irq_enter_irqson(void) { } static inline void rcu_irq_exit(void) { } static inline void rcu_irq_exit_check_preempt(void) { } #define rcu_is_idle_cpu(cpu) \ - (is_idle_task(current) && !in_nmi() && !in_irq() && !in_serving_softirq()) + (is_idle_task(current) && !in_nmi() && !in_hardirq() && !in_serving_softirq()) static inline void exit_rcu(void) { } static inline bool rcu_preempt_need_deferred_qs(struct task_struct *t) { diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index ef8d36f580fc..f0f19dc7f19e 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1467,7 +1467,7 @@ static void rcu_gp_kthread_wake(void) { struct task_struct *t = READ_ONCE(rcu_state.gp_kthread); - if ((current == t && !in_irq() && !in_serving_softirq()) || + if ((current == t && !in_hardirq() && !in_serving_softirq()) || !READ_ONCE(rcu_state.gp_flags) || !t) return; WRITE_ONCE(rcu_state.gp_wake_time, jiffies); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 5199559fbbf0..599084c4c21f 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -642,7 +642,7 @@ static void rcu_read_unlock_special(struct task_struct *t) (IS_ENABLED(CONFIG_RCU_BOOST) && irqs_were_disabled && t->rcu_blocked_node); // Need to defer quiescent state until everything is enabled. - if (use_softirq && (in_irq() || (expboost && !irqs_were_disabled))) { + if (use_softirq && (in_hardirq() || (expboost && !irqs_were_disabled))) { // Using softirq, safe to awaken, and either the // wakeup is free or there is either an expedited // GP in flight or a potential need to deboost. -- cgit v1.2.3 From 502e82b91361955c66c8453b5b7a905b0b5bd5a1 Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Sun, 7 Nov 2021 17:21:45 +0200 Subject: net/mlx5: Fix access to a non-supported register Validate MRTC register is supported before triggering a delayed work which accesses it. Fixes: 5a1023deeed0 ("net/mlx5: Add periodic update of host time to firmware") Signed-off-by: Aya Levin Reviewed-by: Gal Pressman Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/main.c | 8 +++----- include/linux/mlx5/mlx5_ifc.h | 5 ++++- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 380f50d5462d..3ca998874c50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -836,7 +836,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) health->timer.expires = jiffies + msecs_to_jiffies(poll_interval_ms); add_timer(&health->timer); - if (mlx5_core_is_pf(dev)) + if (mlx5_core_is_pf(dev) && MLX5_CAP_MCAM_REG(dev, mrtc)) queue_delayed_work(health->wq, &health->update_fw_log_ts_work, 0); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e127c0530b3a..7df9c7f8d9c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1071,18 +1071,16 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) mlx5_set_driver_version(dev); - mlx5_start_health_poll(dev); - err = mlx5_query_hca_caps(dev); if (err) { mlx5_core_err(dev, "query hca failed\n"); - goto stop_health; + goto reclaim_boot_pages; } + mlx5_start_health_poll(dev); + return 0; -stop_health: - mlx5_stop_health_poll(dev, boot); reclaim_boot_pages: mlx5_reclaim_startup_pages(dev); err_disable_hca: diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3636df90899a..fbaab440a484 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -9698,7 +9698,10 @@ struct mlx5_ifc_mcam_access_reg_bits { u8 regs_84_to_68[0x11]; u8 tracer_registers[0x4]; - u8 regs_63_to_32[0x20]; + u8 regs_63_to_46[0x12]; + u8 mrtc[0x1]; + u8 regs_44_to_32[0xd]; + u8 regs_31_to_0[0x20]; }; -- cgit v1.2.3 From af3bf054661fb11497a7f712ece8b838521227a4 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Wed, 1 Dec 2021 01:17:36 +0000 Subject: cgroup: fix a typo in comment In commit 8699b7762a62 ("cgroup: s/child_subsys_mask/subtree_ss_mask/"), we rename child_subsys_mask to subtree_ss_mask. While it missed to rename this in comment. Signed-off-by: Wei Yang Signed-off-by: Tejun Heo --- include/linux/cgroup-defs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index db2e147e069f..bb1e79791ed5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -413,7 +413,7 @@ struct cgroup { /* * The bitmask of subsystems enabled on the child cgroups. * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_ss_mask is the effective + * "cgroup.subtree_control" while ->subtree_ss_mask is the effective * one which may have more subsystems enabled. Controller knobs * are made available iff it's enabled in ->subtree_control. */ -- cgit v1.2.3 From 6bbfa44116689469267f1a6e3d233b52114139d2 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 1 Dec 2021 23:45:50 +0900 Subject: kprobes: Limit max data_size of the kretprobe instances The 'kprobe::data_size' is unsigned, thus it can not be negative. But if user sets it enough big number (e.g. (size_t)-8), the result of 'data_size + sizeof(struct kretprobe_instance)' becomes smaller than sizeof(struct kretprobe_instance) or zero. In result, the kretprobe_instance are allocated without enough memory, and kretprobe accesses outside of allocated memory. To avoid this issue, introduce a max limitation of the kretprobe::data_size. 4KB per instance should be OK. Link: https://lkml.kernel.org/r/163836995040.432120.10322772773821182925.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: f47cd9b553aa ("kprobes: kretprobe user entry-handler") Reported-by: zhangyue Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/kprobes.h | 2 ++ kernel/kprobes.c | 3 +++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index e974caf39d3e..8c8f7a4d93af 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -153,6 +153,8 @@ struct kretprobe { struct kretprobe_holder *rph; }; +#define KRETPROBE_MAX_DATA_SIZE 4096 + struct kretprobe_instance { union { struct freelist_node freelist; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e9db0c810554..21eccc961bba 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp) } } + if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) + return -E2BIG; + rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; -- cgit v1.2.3 From 7a10d8c810cfad3e79372d7d1c77899d86cd6662 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 30 Nov 2021 09:01:55 -0800 Subject: net: annotate data-races on txq->xmit_lock_owner syzbot found that __dev_queue_xmit() is reading txq->xmit_lock_owner without annotations. No serious issue there, let's document what is happening there. BUG: KCSAN: data-race in __dev_queue_xmit / __dev_queue_xmit write to 0xffff888139d09484 of 4 bytes by interrupt on cpu 0: __netif_tx_unlock include/linux/netdevice.h:4437 [inline] __dev_queue_xmit+0x948/0xf70 net/core/dev.c:4229 dev_queue_xmit_accel+0x19/0x20 net/core/dev.c:4265 macvlan_queue_xmit drivers/net/macvlan.c:543 [inline] macvlan_start_xmit+0x2b3/0x3d0 drivers/net/macvlan.c:567 __netdev_start_xmit include/linux/netdevice.h:4987 [inline] netdev_start_xmit include/linux/netdevice.h:5001 [inline] xmit_one+0x105/0x2f0 net/core/dev.c:3590 dev_hard_start_xmit+0x72/0x120 net/core/dev.c:3606 sch_direct_xmit+0x1b2/0x7c0 net/sched/sch_generic.c:342 __dev_xmit_skb+0x83d/0x1370 net/core/dev.c:3817 __dev_queue_xmit+0x590/0xf70 net/core/dev.c:4194 dev_queue_xmit+0x13/0x20 net/core/dev.c:4259 neigh_hh_output include/net/neighbour.h:511 [inline] neigh_output include/net/neighbour.h:525 [inline] ip6_finish_output2+0x995/0xbb0 net/ipv6/ip6_output.c:126 __ip6_finish_output net/ipv6/ip6_output.c:191 [inline] ip6_finish_output+0x444/0x4c0 net/ipv6/ip6_output.c:201 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip6_output+0x10e/0x210 net/ipv6/ip6_output.c:224 dst_output include/net/dst.h:450 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ndisc_send_skb+0x486/0x610 net/ipv6/ndisc.c:508 ndisc_send_rs+0x3b0/0x3e0 net/ipv6/ndisc.c:702 addrconf_rs_timer+0x370/0x540 net/ipv6/addrconf.c:3898 call_timer_fn+0x2e/0x240 kernel/time/timer.c:1421 expire_timers+0x116/0x240 kernel/time/timer.c:1466 __run_timers+0x368/0x410 kernel/time/timer.c:1734 run_timer_softirq+0x2e/0x60 kernel/time/timer.c:1747 __do_softirq+0x158/0x2de kernel/softirq.c:558 __irq_exit_rcu kernel/softirq.c:636 [inline] irq_exit_rcu+0x37/0x70 kernel/softirq.c:648 sysvec_apic_timer_interrupt+0x3e/0xb0 arch/x86/kernel/apic/apic.c:1097 asm_sysvec_apic_timer_interrupt+0x12/0x20 read to 0xffff888139d09484 of 4 bytes by interrupt on cpu 1: __dev_queue_xmit+0x5e3/0xf70 net/core/dev.c:4213 dev_queue_xmit_accel+0x19/0x20 net/core/dev.c:4265 macvlan_queue_xmit drivers/net/macvlan.c:543 [inline] macvlan_start_xmit+0x2b3/0x3d0 drivers/net/macvlan.c:567 __netdev_start_xmit include/linux/netdevice.h:4987 [inline] netdev_start_xmit include/linux/netdevice.h:5001 [inline] xmit_one+0x105/0x2f0 net/core/dev.c:3590 dev_hard_start_xmit+0x72/0x120 net/core/dev.c:3606 sch_direct_xmit+0x1b2/0x7c0 net/sched/sch_generic.c:342 __dev_xmit_skb+0x83d/0x1370 net/core/dev.c:3817 __dev_queue_xmit+0x590/0xf70 net/core/dev.c:4194 dev_queue_xmit+0x13/0x20 net/core/dev.c:4259 neigh_resolve_output+0x3db/0x410 net/core/neighbour.c:1523 neigh_output include/net/neighbour.h:527 [inline] ip6_finish_output2+0x9be/0xbb0 net/ipv6/ip6_output.c:126 __ip6_finish_output net/ipv6/ip6_output.c:191 [inline] ip6_finish_output+0x444/0x4c0 net/ipv6/ip6_output.c:201 NF_HOOK_COND include/linux/netfilter.h:296 [inline] ip6_output+0x10e/0x210 net/ipv6/ip6_output.c:224 dst_output include/net/dst.h:450 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] ndisc_send_skb+0x486/0x610 net/ipv6/ndisc.c:508 ndisc_send_rs+0x3b0/0x3e0 net/ipv6/ndisc.c:702 addrconf_rs_timer+0x370/0x540 net/ipv6/addrconf.c:3898 call_timer_fn+0x2e/0x240 kernel/time/timer.c:1421 expire_timers+0x116/0x240 kernel/time/timer.c:1466 __run_timers+0x368/0x410 kernel/time/timer.c:1734 run_timer_softirq+0x2e/0x60 kernel/time/timer.c:1747 __do_softirq+0x158/0x2de kernel/softirq.c:558 __irq_exit_rcu kernel/softirq.c:636 [inline] irq_exit_rcu+0x37/0x70 kernel/softirq.c:648 sysvec_apic_timer_interrupt+0x8d/0xb0 arch/x86/kernel/apic/apic.c:1097 asm_sysvec_apic_timer_interrupt+0x12/0x20 kcsan_setup_watchpoint+0x94/0x420 kernel/kcsan/core.c:443 folio_test_anon include/linux/page-flags.h:581 [inline] PageAnon include/linux/page-flags.h:586 [inline] zap_pte_range+0x5ac/0x10e0 mm/memory.c:1347 zap_pmd_range mm/memory.c:1467 [inline] zap_pud_range mm/memory.c:1496 [inline] zap_p4d_range mm/memory.c:1517 [inline] unmap_page_range+0x2dc/0x3d0 mm/memory.c:1538 unmap_single_vma+0x157/0x210 mm/memory.c:1583 unmap_vmas+0xd0/0x180 mm/memory.c:1615 exit_mmap+0x23d/0x470 mm/mmap.c:3170 __mmput+0x27/0x1b0 kernel/fork.c:1113 mmput+0x3d/0x50 kernel/fork.c:1134 exit_mm+0xdb/0x170 kernel/exit.c:507 do_exit+0x608/0x17a0 kernel/exit.c:819 do_group_exit+0xce/0x180 kernel/exit.c:929 get_signal+0xfc3/0x1550 kernel/signal.c:2852 arch_do_signal_or_restart+0x8c/0x2e0 arch/x86/kernel/signal.c:868 handle_signal_work kernel/entry/common.c:148 [inline] exit_to_user_mode_loop kernel/entry/common.c:172 [inline] exit_to_user_mode_prepare+0x113/0x190 kernel/entry/common.c:207 __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:300 do_syscall_64+0x50/0xd0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0x00000000 -> 0xffffffff Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 28712 Comm: syz-executor.0 Tainted: G W 5.16.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet Reported-by: syzbot Link: https://lore.kernel.org/r/20211130170155.2331929-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 19 +++++++++++++------ net/core/dev.c | 5 ++++- 2 files changed, 17 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3ec42495a43a..be5cb3360b94 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4404,7 +4404,8 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - txq->xmit_lock_owner = cpu; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) @@ -4421,26 +4422,32 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - txq->xmit_lock_owner = smp_processor_id(); + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); - if (likely(ok)) - txq->xmit_lock_owner = smp_processor_id(); + + if (likely(ok)) { + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); + } return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - txq->xmit_lock_owner = -1; + /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } diff --git a/net/core/dev.c b/net/core/dev.c index 15ac064b5562..2a352e668d10 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4210,7 +4210,10 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - if (txq->xmit_lock_owner != cpu) { + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; -- cgit v1.2.3 From 57b2b72ac1fc5d55cf3b13207942c109f1a65cb5 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Mon, 29 Nov 2021 09:57:59 -0700 Subject: mm, slab: Remove compiler check in __kmalloc_index The minimum supported version of LLVM has been raised to 11.0.0, meaning this check is always true, so it can be dropped. Signed-off-by: Nathan Chancellor Reviewed-by: Miguel Ojeda Reviewed-by: Mark Brown Reviewed-by: Nick Desaulniers Reviewed-by: Kees Cook Signed-off-by: Masahiro Yamada --- include/linux/slab.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 181045148b06..d3fb5ac71c24 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -411,8 +411,7 @@ static __always_inline unsigned int __kmalloc_index(size_t size, if (size <= 16 * 1024 * 1024) return 24; if (size <= 32 * 1024 * 1024) return 25; - if ((IS_ENABLED(CONFIG_CC_IS_GCC) || CONFIG_CLANG_VERSION >= 110000) - && !IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) + if (!IS_ENABLED(CONFIG_PROFILE_ALL_BRANCHES) && size_is_constant) BUILD_BUG_ON_MSG(1, "unexpected size in kmalloc_index()"); else BUG(); -- cgit v1.2.3 From e7f2be115f0746b969c0df14c0d182f65f005ca5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 26 Oct 2021 16:10:55 +0200 Subject: sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full getrusage(RUSAGE_THREAD) with nohz_full may return shorter utime/stime than the actual time. task_cputime_adjusted() snapshots utime and stime and then adjust their sum to match the scheduler maintained cputime.sum_exec_runtime. Unfortunately in nohz_full, sum_exec_runtime is only updated once per second in the worst case, causing a discrepancy against utime and stime that can be updated anytime by the reader using vtime. To fix this situation, perform an update of cputime.sum_exec_runtime when the cputime snapshot reports the task as actually running while the tick is disabled. The related overhead is then contained within the relevant situations. Reported-by: Hasegawa Hitomi Signed-off-by: Frederic Weisbecker Signed-off-by: Hasegawa Hitomi Signed-off-by: Thomas Gleixner Tested-by: Masayoshi Mizuma Acked-by: Phil Auld Link: https://lore.kernel.org/r/20211026141055.57358-3-frederic@kernel.org --- include/linux/sched/cputime.h | 5 +++-- kernel/sched/cputime.c | 12 +++++++++--- 2 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 6c9f19a33865..ce3c58286062 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -18,15 +18,16 @@ #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -extern void task_cputime(struct task_struct *t, +extern bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime); extern u64 task_gtime(struct task_struct *t); #else -static inline void task_cputime(struct task_struct *t, +static inline bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { *utime = t->utime; *stime = t->stime; + return false; } static inline u64 task_gtime(struct task_struct *t) diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 872e481d5098..9392aea1804e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; - task_cputime(p, &cputime.utime, &cputime.stime); + if (task_cputime(p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime = task_sched_runtime(p); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } EXPORT_SYMBOL_GPL(task_cputime_adjusted); @@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) +bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { struct vtime *vtime = &t->vtime; unsigned int seq; u64 delta; + int ret; if (!vtime_accounting_enabled()) { *utime = t->utime; *stime = t->stime; - return; + return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; @@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) if (vtime->state < VTIME_SYS) continue; + ret = true; delta = vtime_delta(vtime); /* @@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return ret; } static int vtime_state_fetch(struct vtime *vtime, int cpu) -- cgit v1.2.3 From f83baa0cb6cfc92ebaf7f9d3a99d7e34f2e77a8a Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Dec 2021 19:35:01 +0100 Subject: HID: add hid_is_usb() function to make it simpler for USB detection A number of HID drivers already call hid_is_using_ll_driver() but only for the detection of if this is a USB device or not. Make this more obvious by creating hid_is_usb() and calling the function that way. Also converts the existing hid_is_using_ll_driver() functions to use the new call. Cc: Jiri Kosina Cc: Benjamin Tissoires Cc: linux-input@vger.kernel.org Cc: stable@vger.kernel.org Tested-by: Benjamin Tissoires Signed-off-by: Greg Kroah-Hartman Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211201183503.2373082-1-gregkh@linuxfoundation.org --- drivers/hid/hid-asus.c | 6 ++---- drivers/hid/hid-logitech-dj.c | 2 +- drivers/hid/hid-u2fzero.c | 2 +- drivers/hid/hid-uclogic-params.c | 3 +-- drivers/hid/wacom_sys.c | 2 +- include/linux/hid.h | 5 +++++ 6 files changed, 11 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index f3ecddc519ee..08c9a9a60ae4 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1028,8 +1028,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) if (drvdata->quirks & QUIRK_IS_MULTITOUCH) drvdata->tp = &asus_i2c_tp; - if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && - hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && hid_is_usb(hdev)) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); if (intf->altsetting->desc.bInterfaceNumber == T100_TPAD_INTF) { @@ -1057,8 +1056,7 @@ static int asus_probe(struct hid_device *hdev, const struct hid_device_id *id) drvdata->tp = &asus_t100chi_tp; } - if ((drvdata->quirks & QUIRK_MEDION_E1239T) && - hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if ((drvdata->quirks & QUIRK_MEDION_E1239T) && hid_is_usb(hdev)) { struct usb_host_interface *alt = to_usb_interface(hdev->dev.parent)->altsetting; diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index a0017b010c34..7106b921b53c 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1777,7 +1777,7 @@ static int logi_dj_probe(struct hid_device *hdev, case recvr_type_bluetooth: no_dj_interfaces = 2; break; case recvr_type_dinovo: no_dj_interfaces = 2; break; } - if (hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if (hid_is_usb(hdev)) { intf = to_usb_interface(hdev->dev.parent); if (intf && intf->altsetting->desc.bInterfaceNumber >= no_dj_interfaces) { diff --git a/drivers/hid/hid-u2fzero.c b/drivers/hid/hid-u2fzero.c index 31ea7fc69916..ad489caf53ad 100644 --- a/drivers/hid/hid-u2fzero.c +++ b/drivers/hid/hid-u2fzero.c @@ -311,7 +311,7 @@ static int u2fzero_probe(struct hid_device *hdev, unsigned int minor; int ret; - if (!hid_is_using_ll_driver(hdev, &usb_hid_driver)) + if (!hid_is_usb(hdev)) return -EINVAL; dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL); diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 3d67b748a3b9..adff1bd68d9f 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -843,8 +843,7 @@ int uclogic_params_init(struct uclogic_params *params, struct uclogic_params p = {0, }; /* Check arguments */ - if (params == NULL || hdev == NULL || - !hid_is_using_ll_driver(hdev, &usb_hid_driver)) { + if (params == NULL || hdev == NULL || !hid_is_usb(hdev)) { rc = -EINVAL; goto cleanup; } diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 2717d39600b4..22d73772fbc5 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -2214,7 +2214,7 @@ static void wacom_update_name(struct wacom *wacom, const char *suffix) if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) { char *product_name = wacom->hdev->name; - if (hid_is_using_ll_driver(wacom->hdev, &usb_hid_driver)) { + if (hid_is_usb(wacom->hdev)) { struct usb_interface *intf = to_usb_interface(wacom->hdev->dev.parent); struct usb_device *dev = interface_to_usbdev(intf); product_name = dev->product; diff --git a/include/linux/hid.h b/include/linux/hid.h index 9e067f937dbc..f453be385bd4 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -840,6 +840,11 @@ static inline bool hid_is_using_ll_driver(struct hid_device *hdev, return hdev->ll_driver == driver; } +static inline bool hid_is_usb(struct hid_device *hdev) +{ + return hid_is_using_ll_driver(hdev, &usb_hid_driver); +} + #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 -- cgit v1.2.3 From 9e3562080950b6e3fe38a5e34ddd5b1c618f2019 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 2 Dec 2021 10:53:33 +0100 Subject: HID: add suspend/resume helpers There is a lot of duplication of code in the HID low level drivers. Better have everything in one place so we can eventually extend it in a generic way. Signed-off-by: Benjamin Tissoires Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211202095334.14399-4-benjamin.tissoires@redhat.com --- drivers/hid/hid-core.c | 29 +++++++++++++++++++++++++++++ drivers/hid/i2c-hid/i2c-hid-core.c | 15 ++++----------- drivers/hid/surface-hid/surface_hid_core.c | 25 +++++-------------------- drivers/hid/usbhid/hid-core.c | 19 ++++++++----------- include/linux/hid.h | 10 ++++++++++ 5 files changed, 56 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index dbed2524fd47..5402329d6eca 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2126,6 +2126,35 @@ void hid_hw_close(struct hid_device *hdev) } EXPORT_SYMBOL_GPL(hid_hw_close); +#ifdef CONFIG_PM +int hid_driver_suspend(struct hid_device *hdev, pm_message_t state) +{ + if (hdev->driver && hdev->driver->suspend) + return hdev->driver->suspend(hdev, state); + + return 0; +} +EXPORT_SYMBOL_GPL(hid_driver_suspend); + +int hid_driver_reset_resume(struct hid_device *hdev) +{ + if (hdev->driver && hdev->driver->reset_resume) + return hdev->driver->reset_resume(hdev); + + return 0; +} +EXPORT_SYMBOL_GPL(hid_driver_reset_resume); + +int hid_driver_resume(struct hid_device *hdev) +{ + if (hdev->driver && hdev->driver->resume) + return hdev->driver->resume(hdev); + + return 0; +} +EXPORT_SYMBOL_GPL(hid_driver_resume); +#endif /* CONFIG_PM */ + struct hid_dynid { struct list_head list; struct hid_device_id id; diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 517141138b00..4cdd862ca1cb 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -1063,11 +1063,9 @@ static int i2c_hid_core_suspend(struct device *dev) int ret; int wake_status; - if (hid->driver && hid->driver->suspend) { - ret = hid->driver->suspend(hid, PMSG_SUSPEND); - if (ret < 0) - return ret; - } + ret = hid_driver_suspend(hid, PMSG_SUSPEND); + if (ret < 0) + return ret; /* Save some power */ i2c_hid_set_power(client, I2C_HID_PWR_SLEEP); @@ -1125,12 +1123,7 @@ static int i2c_hid_core_resume(struct device *dev) if (ret) return ret; - if (hid->driver && hid->driver->reset_resume) { - ret = hid->driver->reset_resume(hid); - return ret; - } - - return 0; + return hid_driver_reset_resume(hid); } #endif diff --git a/drivers/hid/surface-hid/surface_hid_core.c b/drivers/hid/surface-hid/surface_hid_core.c index 5571e74abe91..e46330b2e561 100644 --- a/drivers/hid/surface-hid/surface_hid_core.c +++ b/drivers/hid/surface-hid/surface_hid_core.c @@ -204,50 +204,35 @@ static int surface_hid_suspend(struct device *dev) { struct surface_hid_device *d = dev_get_drvdata(dev); - if (d->hid->driver && d->hid->driver->suspend) - return d->hid->driver->suspend(d->hid, PMSG_SUSPEND); - - return 0; + return hid_driver_suspend(d->hid, PMSG_SUSPEND); } static int surface_hid_resume(struct device *dev) { struct surface_hid_device *d = dev_get_drvdata(dev); - if (d->hid->driver && d->hid->driver->resume) - return d->hid->driver->resume(d->hid); - - return 0; + return hid_driver_resume(d->hid); } static int surface_hid_freeze(struct device *dev) { struct surface_hid_device *d = dev_get_drvdata(dev); - if (d->hid->driver && d->hid->driver->suspend) - return d->hid->driver->suspend(d->hid, PMSG_FREEZE); - - return 0; + return hid_driver_suspend(d->hid, PMSG_FREEZE); } static int surface_hid_poweroff(struct device *dev) { struct surface_hid_device *d = dev_get_drvdata(dev); - if (d->hid->driver && d->hid->driver->suspend) - return d->hid->driver->suspend(d->hid, PMSG_HIBERNATE); - - return 0; + return hid_driver_suspend(d->hid, PMSG_HIBERNATE); } static int surface_hid_restore(struct device *dev) { struct surface_hid_device *d = dev_get_drvdata(dev); - if (d->hid->driver && d->hid->driver->reset_resume) - return d->hid->driver->reset_resume(d->hid); - - return 0; + return hid_driver_reset_resume(d->hid); } const struct dev_pm_ops surface_hid_pm_ops = { diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index 2dcaf31eb9cd..54752c85604b 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -1563,8 +1563,8 @@ static int hid_resume_common(struct hid_device *hid, bool driver_suspended) int status = 0; hid_restart_io(hid); - if (driver_suspended && hid->driver && hid->driver->resume) - status = hid->driver->resume(hid); + if (driver_suspended) + status = hid_driver_resume(hid); return status; } @@ -1588,11 +1588,9 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message) { set_bit(HID_SUSPENDED, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); - if (hid->driver && hid->driver->suspend) { - status = hid->driver->suspend(hid, message); - if (status < 0) - goto failed; - } + status = hid_driver_suspend(hid, message); + if (status < 0) + goto failed; driver_suspended = true; } else { usbhid_mark_busy(usbhid); @@ -1602,8 +1600,7 @@ static int hid_suspend(struct usb_interface *intf, pm_message_t message) } else { /* TODO: resume() might need to handle suspend failure */ - if (hid->driver && hid->driver->suspend) - status = hid->driver->suspend(hid, message); + status = hid_driver_suspend(hid, message); driver_suspended = true; spin_lock_irq(&usbhid->lock); set_bit(HID_SUSPENDED, &usbhid->iofl); @@ -1644,8 +1641,8 @@ static int hid_reset_resume(struct usb_interface *intf) int status; status = hid_post_reset(intf); - if (status >= 0 && hid->driver && hid->driver->reset_resume) { - int ret = hid->driver->reset_resume(hid); + if (status >= 0) { + int ret = hid_driver_reset_resume(hid); if (ret < 0) status = ret; } diff --git a/include/linux/hid.h b/include/linux/hid.h index 9e067f937dbc..ebe3ec98db6b 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -923,6 +923,16 @@ s32 hid_snto32(__u32 value, unsigned n); __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, unsigned offset, unsigned n); +#ifdef CONFIG_PM +int hid_driver_suspend(struct hid_device *hdev, pm_message_t state); +int hid_driver_reset_resume(struct hid_device *hdev); +int hid_driver_resume(struct hid_device *hdev); +#else +static inline int hid_driver_suspend(struct hid_device *hdev, pm_message_t state) { return 0; } +static inline int hid_driver_reset_resume(struct hid_device *hdev) { return 0; } +static inline int hid_driver_resume(struct hid_device *hdev) { return 0; } +#endif + /** * hid_device_io_start - enable HID input during probe, remove * -- cgit v1.2.3 From f65a0b1f3e79444bba9ac56435eeb32db85ab2c9 Mon Sep 17 00:00:00 2001 From: Benjamin Tissoires Date: Thu, 2 Dec 2021 10:53:34 +0100 Subject: HID: do not inline some hid_hw_ functions We don't gain much by having them as inline, and it actually prevents us to attach a probe to those helpers. Signed-off-by: Benjamin Tissoires Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211202095334.14399-5-benjamin.tissoires@redhat.com --- drivers/hid/hid-core.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/hid.h | 68 +++++--------------------------------------------- 2 files changed, 70 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 5402329d6eca..f1aed5bbd000 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2126,6 +2126,70 @@ void hid_hw_close(struct hid_device *hdev) } EXPORT_SYMBOL_GPL(hid_hw_close); +/** + * hid_hw_request - send report request to device + * + * @hdev: hid device + * @report: report to send + * @reqtype: hid request type + */ +void hid_hw_request(struct hid_device *hdev, + struct hid_report *report, int reqtype) +{ + if (hdev->ll_driver->request) + return hdev->ll_driver->request(hdev, report, reqtype); + + __hid_request(hdev, report, reqtype); +} +EXPORT_SYMBOL_GPL(hid_hw_request); + +/** + * hid_hw_raw_request - send report request to device + * + * @hdev: hid device + * @reportnum: report ID + * @buf: in/out data to transfer + * @len: length of buf + * @rtype: HID report type + * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT + * + * Return: count of data transferred, negative if error + * + * Same behavior as hid_hw_request, but with raw buffers instead. + */ +int hid_hw_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + size_t len, unsigned char rtype, int reqtype) +{ + if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) + return -EINVAL; + + return hdev->ll_driver->raw_request(hdev, reportnum, buf, len, + rtype, reqtype); +} +EXPORT_SYMBOL_GPL(hid_hw_raw_request); + +/** + * hid_hw_output_report - send output report to device + * + * @hdev: hid device + * @buf: raw data to transfer + * @len: length of buf + * + * Return: count of data transferred, negative if error + */ +int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len) +{ + if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) + return -EINVAL; + + if (hdev->ll_driver->output_report) + return hdev->ll_driver->output_report(hdev, buf, len); + + return -ENOSYS; +} +EXPORT_SYMBOL_GPL(hid_hw_output_report); + #ifdef CONFIG_PM int hid_driver_suspend(struct hid_device *hdev, pm_message_t state) { diff --git a/include/linux/hid.h b/include/linux/hid.h index ebe3ec98db6b..b2fea7fc54a1 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1066,6 +1066,12 @@ int __must_check hid_hw_start(struct hid_device *hdev, void hid_hw_stop(struct hid_device *hdev); int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); +void hid_hw_request(struct hid_device *hdev, + struct hid_report *report, int reqtype); +int hid_hw_raw_request(struct hid_device *hdev, + unsigned char reportnum, __u8 *buf, + size_t len, unsigned char rtype, int reqtype); +int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len); /** * hid_hw_power - requests underlying HW to go into given power mode @@ -1083,68 +1089,6 @@ static inline int hid_hw_power(struct hid_device *hdev, int level) } -/** - * hid_hw_request - send report request to device - * - * @hdev: hid device - * @report: report to send - * @reqtype: hid request type - */ -static inline void hid_hw_request(struct hid_device *hdev, - struct hid_report *report, int reqtype) -{ - if (hdev->ll_driver->request) - return hdev->ll_driver->request(hdev, report, reqtype); - - __hid_request(hdev, report, reqtype); -} - -/** - * hid_hw_raw_request - send report request to device - * - * @hdev: hid device - * @reportnum: report ID - * @buf: in/out data to transfer - * @len: length of buf - * @rtype: HID report type - * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT - * - * Return: count of data transferred, negative if error - * - * Same behavior as hid_hw_request, but with raw buffers instead. - */ -static inline int hid_hw_raw_request(struct hid_device *hdev, - unsigned char reportnum, __u8 *buf, - size_t len, unsigned char rtype, int reqtype) -{ - if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) - return -EINVAL; - - return hdev->ll_driver->raw_request(hdev, reportnum, buf, len, - rtype, reqtype); -} - -/** - * hid_hw_output_report - send output report to device - * - * @hdev: hid device - * @buf: raw data to transfer - * @len: length of buf - * - * Return: count of data transferred, negative if error - */ -static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, - size_t len) -{ - if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) - return -EINVAL; - - if (hdev->ll_driver->output_report) - return hdev->ll_driver->output_report(hdev, buf, len); - - return -ENOSYS; -} - /** * hid_hw_idle - send idle request to device * -- cgit v1.2.3 From 8293eb995f349aed28006792cad4cb48091919dd Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Dec 2021 10:10:25 -0800 Subject: bpf: Rename btf_member accessors. Rename btf_member_bit_offset() and btf_member_bitfield_size() to avoid conflicts with similarly named helpers in libbpf's btf.h. Rename the kernel helpers, since libbpf helpers are part of uapi. Suggested-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211201181040.23337-3-alexei.starovoitov@gmail.com --- include/linux/btf.h | 8 ++++---- kernel/bpf/bpf_struct_ops.c | 6 +++--- kernel/bpf/btf.c | 18 +++++++++--------- net/ipv4/bpf_tcp_ca.c | 6 +++--- 4 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 203eef993d76..956f70388f69 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -194,15 +194,15 @@ static inline bool btf_type_kflag(const struct btf_type *t) return BTF_INFO_KFLAG(t->info); } -static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) : member->offset; } -static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) : 0; diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 8ecfe4752769..21069dbe9138 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -165,7 +165,7 @@ void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) break; } - if (btf_member_bitfield_size(t, member)) { + if (__btf_member_bitfield_size(t, member)) { pr_warn("bit field member %s in struct %s is not supported\n", mname, st_ops->name); break; @@ -296,7 +296,7 @@ static int check_zero_holes(const struct btf_type *t, void *data) const struct btf_type *mtype; for_each_member(i, t, member) { - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (moff > prev_mend && memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; @@ -387,7 +387,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, struct bpf_prog *prog; u32 moff; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b9d23be1e99..f4119a99da7b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -2969,7 +2969,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env, return -EINVAL; } - offset = btf_member_bit_offset(t, member); + offset = __btf_member_bit_offset(t, member); if (is_union && offset) { btf_verifier_log_member(env, t, member, "Invalid member bits_offset"); @@ -3094,7 +3094,7 @@ static int btf_find_struct_field(const struct btf *btf, const struct btf_type *t if (off != -ENOENT) /* only one such field is allowed */ return -E2BIG; - off = btf_member_bit_offset(t, member); + off = __btf_member_bit_offset(t, member); if (off % 8) /* valid C code cannot generate such BTF */ return -EINVAL; @@ -3184,8 +3184,8 @@ static void __btf_struct_show(const struct btf *btf, const struct btf_type *t, btf_show_start_member(show, member); - member_offset = btf_member_bit_offset(t, member); - bitfield_size = btf_member_bitfield_size(t, member); + member_offset = __btf_member_bit_offset(t, member); + bitfield_size = __btf_member_bitfield_size(t, member); bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); bits8_offset = BITS_PER_BYTE_MASKED(member_offset); if (bitfield_size) { @@ -5060,7 +5060,7 @@ again: if (array_elem->nelems != 0) goto error; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off < moff) goto error; @@ -5083,14 +5083,14 @@ error: for_each_member(i, t, member) { /* offset of the field in bytes */ - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; if (off + size <= moff) /* won't find anything, field is already too far */ break; - if (btf_member_bitfield_size(t, member)) { - u32 end_bit = btf_member_bit_offset(t, member) + - btf_member_bitfield_size(t, member); + if (__btf_member_bitfield_size(t, member)) { + u32 end_bit = __btf_member_bit_offset(t, member) + + __btf_member_bitfield_size(t, member); /* off <= moff instead of off == moff because clang * does not generate a BTF member for anonymous diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 2cf02b4d77fb..67466dbff152 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -169,7 +169,7 @@ static u32 prog_ops_moff(const struct bpf_prog *prog) t = bpf_tcp_congestion_ops.type; m = &btf_type_member(t)[midx]; - return btf_member_bit_offset(t, m) / 8; + return __btf_member_bit_offset(t, m) / 8; } static const struct bpf_func_proto * @@ -244,7 +244,7 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, utcp_ca = (const struct tcp_congestion_ops *)udata; tcp_ca = (struct tcp_congestion_ops *)kdata; - moff = btf_member_bit_offset(t, member) / 8; + moff = __btf_member_bit_offset(t, member) / 8; switch (moff) { case offsetof(struct tcp_congestion_ops, flags): if (utcp_ca->flags & ~TCP_CONG_MASK) @@ -274,7 +274,7 @@ static int bpf_tcp_ca_init_member(const struct btf_type *t, static int bpf_tcp_ca_check_member(const struct btf_type *t, const struct btf_member *member) { - if (is_unsupported(btf_member_bit_offset(t, member) / 8)) + if (is_unsupported(__btf_member_bit_offset(t, member) / 8)) return -ENOTSUPP; return 0; } -- cgit v1.2.3 From 29db4bea1d10b73749d7992c1fc9ac13499e8871 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Dec 2021 10:10:26 -0800 Subject: bpf: Prepare relo_core.c for kernel duty. Make relo_core.c to be compiled for the kernel and for user space libbpf. Note the patch is reducing BPF_CORE_SPEC_MAX_LEN from 64 to 32. This is the maximum number of nested structs and arrays. For example: struct sample { int a; struct { int b[10]; }; }; struct sample *s = ...; int *y = &s->b[5]; This field access is encoded as "0:1:0:5" and spec len is 4. The follow up patch might bump it back to 64. Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211201181040.23337-4-alexei.starovoitov@gmail.com --- include/linux/btf.h | 81 +++++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/Makefile | 4 +++ kernel/bpf/btf.c | 26 +++++++++++++++ tools/lib/bpf/relo_core.c | 76 +++++++++++++++++++++++++++++++++++++------- 4 files changed, 176 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 956f70388f69..acef6ef28768 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -144,6 +144,53 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +static inline u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(u32 *)(t + 1)); +} + +static inline u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(u32 *)(t + 1)); +} + static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); @@ -184,6 +231,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t) return BTF_INFO_VLEN(t->info); } +static inline u16 btf_vlen(const struct btf_type *t) +{ + return btf_type_vlen(t); +} + static inline u16 btf_func_linkage(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -208,11 +260,40 @@ static inline u32 __btf_member_bitfield_size(const struct btf_type *struct_type, : 0; } +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bit_offset(t, m); +} + +static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bitfield_size(t, m); +} + static inline const struct btf_member *btf_type_member(const struct btf_type *t) { return (const struct btf_member *)(t + 1); } +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index cf6ca339f3cd..c1a9be6a4b9f 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -36,3 +36,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_struct_ops.o obj-${CONFIG_BPF_LSM} += bpf_lsm.o endif obj-$(CONFIG_BPF_PRELOAD) += preload/ + +obj-$(CONFIG_BPF_SYSCALL) += relo_core.o +$(obj)/relo_core.o: $(srctree)/tools/lib/bpf/relo_core.c FORCE + $(call if_changed_rule,cc_o_c) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f4119a99da7b..c79595aad55b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6413,3 +6413,29 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + +int bpf_core_types_are_compat(const struct btf *local_btf, __u32 local_id, + const struct btf *targ_btf, __u32 targ_id) +{ + return -EOPNOTSUPP; +} + +static bool bpf_core_is_flavor_sep(const char *s) +{ + /* check X___Y name pattern, where X and Y are not underscores */ + return s[0] != '_' && /* X */ + s[1] == '_' && s[2] == '_' && s[3] == '_' && /* ___ */ + s[4] != '_'; /* Y */ +} + +size_t bpf_core_essential_name_len(const char *name) +{ + size_t n = strlen(name); + int i; + + for (i = n - 5; i >= 0; i--) { + if (bpf_core_is_flavor_sep(name + i)) + return i + 1; + } + return n; +} diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c index c0904f4cb514..56dbe6d16664 100644 --- a/tools/lib/bpf/relo_core.c +++ b/tools/lib/bpf/relo_core.c @@ -1,6 +1,60 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2019 Facebook */ +#ifdef __KERNEL__ +#include +#include +#include +#include +#include "relo_core.h" + +static const char *btf_kind_str(const struct btf_type *t) +{ + return btf_type_str(t); +} + +static bool is_ldimm64_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_LD | BPF_IMM | BPF_DW); +} + +static const struct btf_type * +skip_mods_and_typedefs(const struct btf *btf, u32 id, u32 *res_id) +{ + return btf_type_skip_modifiers(btf, id, res_id); +} + +static const char *btf__name_by_offset(const struct btf *btf, u32 offset) +{ + return btf_name_by_offset(btf, offset); +} + +static s64 btf__resolve_size(const struct btf *btf, u32 type_id) +{ + const struct btf_type *t; + int size; + + t = btf_type_by_id(btf, type_id); + t = btf_resolve_size(btf, t, &size); + if (IS_ERR(t)) + return PTR_ERR(t); + return size; +} + +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +#undef pr_warn +#undef pr_info +#undef pr_debug +#define pr_warn(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_info(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define pr_debug(fmt, log, ...) bpf_log((void *)log, fmt, "", ##__VA_ARGS__) +#define libbpf_print(level, fmt, ...) bpf_log((void *)prog_name, fmt, ##__VA_ARGS__) +#else #include #include #include @@ -12,8 +66,9 @@ #include "btf.h" #include "str_error.h" #include "libbpf_internal.h" +#endif -#define BPF_CORE_SPEC_MAX_LEN 64 +#define BPF_CORE_SPEC_MAX_LEN 32 /* represents BPF CO-RE field or array element accessor */ struct bpf_core_accessor { @@ -150,7 +205,7 @@ static bool core_relo_is_enumval_based(enum bpf_core_relo_kind kind) * Enum value-based relocations (ENUMVAL_EXISTS/ENUMVAL_VALUE) use access * string to specify enumerator's value index that need to be relocated. */ -static int bpf_core_parse_spec(const struct btf *btf, +static int bpf_core_parse_spec(const char *prog_name, const struct btf *btf, __u32 type_id, const char *spec_str, enum bpf_core_relo_kind relo_kind, @@ -272,8 +327,8 @@ static int bpf_core_parse_spec(const struct btf *btf, return sz; spec->bit_offset += access_idx * sz * 8; } else { - pr_warn("relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", - type_id, spec_str, i, id, btf_kind_str(t)); + pr_warn("prog '%s': relo for [%u] %s (at idx %d) captures type [%d] of unexpected kind %s\n", + prog_name, type_id, spec_str, i, id, btf_kind_str(t)); return -EINVAL; } } @@ -346,8 +401,6 @@ recur: targ_id = btf_array(targ_type)->type; goto recur; default: - pr_warn("unexpected kind %d relocated, local [%d], target [%d]\n", - btf_kind(local_type), local_id, targ_id); return 0; } } @@ -1045,7 +1098,7 @@ poison: * [] () + => @, * where is a C-syntax view of recorded field access, e.g.: x.a[3].b */ -static void bpf_core_dump_spec(int level, const struct bpf_core_spec *spec) +static void bpf_core_dump_spec(const char *prog_name, int level, const struct bpf_core_spec *spec) { const struct btf_type *t; const struct btf_enum *e; @@ -1167,7 +1220,8 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, if (str_is_empty(spec_str)) return -EINVAL; - err = bpf_core_parse_spec(local_btf, local_id, spec_str, relo->kind, &local_spec); + err = bpf_core_parse_spec(prog_name, local_btf, local_id, spec_str, + relo->kind, &local_spec); if (err) { pr_warn("prog '%s': relo #%d: parsing [%d] %s %s + %s failed: %d\n", prog_name, relo_idx, local_id, btf_kind_str(local_type), @@ -1178,7 +1232,7 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, pr_debug("prog '%s': relo #%d: kind <%s> (%d), spec is ", prog_name, relo_idx, core_relo_kind_str(relo->kind), relo->kind); - bpf_core_dump_spec(LIBBPF_DEBUG, &local_spec); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, &local_spec); libbpf_print(LIBBPF_DEBUG, "\n"); /* TYPE_ID_LOCAL relo is special and doesn't need candidate search */ @@ -1204,14 +1258,14 @@ int bpf_core_apply_relo_insn(const char *prog_name, struct bpf_insn *insn, if (err < 0) { pr_warn("prog '%s': relo #%d: error matching candidate #%d ", prog_name, relo_idx, i); - bpf_core_dump_spec(LIBBPF_WARN, &cand_spec); + bpf_core_dump_spec(prog_name, LIBBPF_WARN, &cand_spec); libbpf_print(LIBBPF_WARN, ": %d\n", err); return err; } pr_debug("prog '%s': relo #%d: %s candidate #%d ", prog_name, relo_idx, err == 0 ? "non-matching" : "matching", i); - bpf_core_dump_spec(LIBBPF_DEBUG, &cand_spec); + bpf_core_dump_spec(prog_name, LIBBPF_DEBUG, &cand_spec); libbpf_print(LIBBPF_DEBUG, "\n"); if (err == 0) -- cgit v1.2.3 From fbd94c7afcf99c9f3b1ba1168657ecc428eb2c8d Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Wed, 1 Dec 2021 10:10:28 -0800 Subject: bpf: Pass a set of bpf_core_relo-s to prog_load command. struct bpf_core_relo is generated by llvm and processed by libbpf. It's a de-facto uapi. With CO-RE in the kernel the struct bpf_core_relo becomes uapi de-jure. Add an ability to pass a set of 'struct bpf_core_relo' to prog_load command and let the kernel perform CO-RE relocations. Note the struct bpf_line_info and struct bpf_func_info have the same layout when passed from LLVM to libbpf and from libbpf to the kernel except "insn_off" fields means "byte offset" when LLVM generates it. Then libbpf converts it to "insn index" to pass to the kernel. The struct bpf_core_relo's "insn_off" field is always "byte offset". Signed-off-by: Alexei Starovoitov Signed-off-by: Andrii Nakryiko Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211201181040.23337-6-alexei.starovoitov@gmail.com --- include/linux/bpf.h | 8 +++++ include/uapi/linux/bpf.h | 59 +++++++++++++++++++++++++++++++- kernel/bpf/btf.c | 6 ++++ kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 76 ++++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 59 +++++++++++++++++++++++++++++++- tools/lib/bpf/relo_core.h | 53 ----------------------------- 7 files changed, 207 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cad0829710be..8bbf08fbab66 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1732,6 +1732,14 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +struct bpf_core_ctx { + struct bpf_verifier_log *log; + const struct btf *btf; +}; + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9e66b1880020..c26871263f1f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -6393,4 +6395,59 @@ enum bpf_core_relo_kind { BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ }; +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index c79595aad55b..0d070461e2b8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6439,3 +6439,9 @@ size_t bpf_core_essential_name_len(const char *name) } return n; } + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn) +{ + return -EOPNOTSUPP; +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 47089d1d67a4..b3ada4085f85 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2184,7 +2184,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD fd_array +#define BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6c9c0d9a04a0..6522ffdea487 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10273,6 +10273,78 @@ err_free: return err; } +#define MIN_CORE_RELO_SIZE sizeof(struct bpf_core_relo) +#define MAX_CORE_RELO_SIZE MAX_FUNCINFO_REC_SIZE + +static int check_core_relo(struct bpf_verifier_env *env, + const union bpf_attr *attr, + bpfptr_t uattr) +{ + u32 i, nr_core_relo, ncopy, expected_size, rec_size; + struct bpf_core_relo core_relo = {}; + struct bpf_prog *prog = env->prog; + const struct btf *btf = prog->aux->btf; + struct bpf_core_ctx ctx = { + .log = &env->log, + .btf = btf, + }; + bpfptr_t u_core_relo; + int err; + + nr_core_relo = attr->core_relo_cnt; + if (!nr_core_relo) + return 0; + if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo)) + return -EINVAL; + + rec_size = attr->core_relo_rec_size; + if (rec_size < MIN_CORE_RELO_SIZE || + rec_size > MAX_CORE_RELO_SIZE || + rec_size % sizeof(u32)) + return -EINVAL; + + u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel); + expected_size = sizeof(struct bpf_core_relo); + ncopy = min_t(u32, expected_size, rec_size); + + /* Unlike func_info and line_info, copy and apply each CO-RE + * relocation record one at a time. + */ + for (i = 0; i < nr_core_relo; i++) { + /* future proofing when sizeof(bpf_core_relo) changes */ + err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size); + if (err) { + if (err == -E2BIG) { + verbose(env, "nonzero tailing record in core_relo"); + if (copy_to_bpfptr_offset(uattr, + offsetof(union bpf_attr, core_relo_rec_size), + &expected_size, sizeof(expected_size))) + err = -EFAULT; + } + break; + } + + if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) { + err = -EFAULT; + break; + } + + if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) { + verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n", + i, core_relo.insn_off, prog->len); + err = -EINVAL; + break; + } + + err = bpf_core_apply(&ctx, &core_relo, i, + &prog->insnsi[core_relo.insn_off / 8]); + if (err) + break; + bpfptr_add(&u_core_relo, rec_size); + } + return err; +} + static int check_btf_info(struct bpf_verifier_env *env, const union bpf_attr *attr, bpfptr_t uattr) @@ -10303,6 +10375,10 @@ static int check_btf_info(struct bpf_verifier_env *env, if (err) return err; + err = check_core_relo(env, attr, uattr); + if (err) + return err; + return 0; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9e66b1880020..c26871263f1f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -6393,4 +6395,59 @@ enum bpf_core_relo_kind { BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ }; +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h index 3d0b86e7f439..f410691cc4e5 100644 --- a/tools/lib/bpf/relo_core.h +++ b/tools/lib/bpf/relo_core.h @@ -6,59 +6,6 @@ #include -/* The minimum bpf_core_relo checked by the loader - * - * CO-RE relocation captures the following data: - * - insn_off - instruction offset (in bytes) within a BPF program that needs - * its insn->imm field to be relocated with actual field info; - * - type_id - BTF type ID of the "root" (containing) entity of a relocatable - * type or field; - * - access_str_off - offset into corresponding .BTF string section. String - * interpretation depends on specific relocation kind: - * - for field-based relocations, string encodes an accessed field using - * a sequence of field and array indices, separated by colon (:). It's - * conceptually very close to LLVM's getelementptr ([0]) instruction's - * arguments for identifying offset to a field. - * - for type-based relocations, strings is expected to be just "0"; - * - for enum value-based relocations, string contains an index of enum - * value within its enum type; - * - * Example to provide a better feel. - * - * struct sample { - * int a; - * struct { - * int b[10]; - * }; - * }; - * - * struct sample *s = ...; - * int x = &s->a; // encoded as "0:0" (a is field #0) - * int y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, - * // b is field #0 inside anon struct, accessing elem #5) - * int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) - * - * type_id for all relocs in this example will capture BTF type id of - * `struct sample`. - * - * Such relocation is emitted when using __builtin_preserve_access_index() - * Clang built-in, passing expression that captures field address, e.g.: - * - * bpf_probe_read(&dst, sizeof(dst), - * __builtin_preserve_access_index(&src->a.b.c)); - * - * In this case Clang will emit field relocation recording necessary data to - * be able to find offset of embedded `a.b.c` field within `src` struct. - * - * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction - */ -struct bpf_core_relo { - __u32 insn_off; - __u32 type_id; - __u32 access_str_off; - enum bpf_core_relo_kind kind; -}; - struct bpf_core_cand { const struct btf *btf; const struct btf_type *t; -- cgit v1.2.3 From d9847eb8be3d895b2b5f514fdf3885d47a0b92a2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 22 Nov 2021 20:17:40 +0530 Subject: bpf: Make CONFIG_DEBUG_INFO_BTF depend upon CONFIG_BPF_SYSCALL Vinicius Costa Gomes reported [0] that build fails when CONFIG_DEBUG_INFO_BTF is enabled and CONFIG_BPF_SYSCALL is disabled. This leads to btf.c not being compiled, and then no symbol being present in vmlinux for the declarations in btf.h. Since BTF is not useful without enabling BPF subsystem, disallow this combination. However, theoretically disabling both now could still fail, as the symbol for kfunc_btf_id_list variables is not available. This isn't a problem as the compiler usually optimizes the whole register/unregister call, but at lower optimization levels it can fail the build in linking stage. Fix that by adding dummy variables so that modules taking address of them still work, but the whole thing is a noop. [0]: https://lore.kernel.org/bpf/20211110205418.332403-1-vinicius.gomes@intel.com Fixes: 14f267d95fe4 ("bpf: btf: Introduce helpers for dynamic BTF set registration") Reported-by: Vinicius Costa Gomes Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211122144742.477787-2-memxor@gmail.com --- include/linux/btf.h | 14 ++++++++++---- kernel/bpf/btf.c | 9 ++------- lib/Kconfig.debug | 1 + 3 files changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/btf.h b/include/linux/btf.h index 203eef993d76..0e1b6281fd8f 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -245,7 +245,10 @@ struct kfunc_btf_id_set { struct module *owner; }; -struct kfunc_btf_id_list; +struct kfunc_btf_id_list { + struct list_head list; + struct mutex mutex; +}; #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -254,6 +257,9 @@ void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l, struct kfunc_btf_id_set *s); bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, struct module *owner); + +extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; +extern struct kfunc_btf_id_list prog_test_kfunc_list; #else static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, struct kfunc_btf_id_set *s) @@ -268,13 +274,13 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, { return false; } + +static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused; +static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused; #endif #define DEFINE_KFUNC_BTF_ID_SET(set, name) \ struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \ THIS_MODULE } -extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list; -extern struct kfunc_btf_id_list prog_test_kfunc_list; - #endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dbc3ad07e21b..ea3df9867cec 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6346,11 +6346,6 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) /* BTF ID set registration API for modules */ -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -6389,8 +6384,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, return false; } -#endif - #define DEFINE_KFUNC_BTF_ID_LIST(name) \ struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ @@ -6398,3 +6391,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + +#endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 9ef7ce18b4f5..596bb5e4790c 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -316,6 +316,7 @@ config DEBUG_INFO_BTF bool "Generate BTF typeinfo" depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST + depends on BPF_SYSCALL help Generate deduplicated BTF type information from DWARF debug info. Turning this on expects presence of pahole tool, which will convert -- cgit v1.2.3 From b247f32aecad09e6cf7edff7739e6f2c9dc5fca9 Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Thu, 28 Oct 2021 16:03:06 +0300 Subject: net/mlx5: Dynamically resize flow counters query buffer The flow counters bulk query buffer is allocated once during mlx5_fc_init_stats(). For PFs and VFs this buffer usually takes a little more than 512KB of memory, which is aligned to the next power of 2, to 1MB. For SFs, this buffer is reduced and takes around 128 Bytes. The buffer size determines the maximum number of flow counters that can be queried at a time. Thus, having a bigger buffer can improve performance for users that need to query many flow counters. There are cases that don't use many flow counters and don't need a big buffer (e.g. SFs, VFs). Since this size is critical with large scale, in these cases the buffer size should be reduced. In order to reduce memory consumption while maintaining query performance, change the query buffer's allocation scheme to the following: - First allocate the buffer with small initial size. - If the number of counters surpasses the initial size, resize the buffer to the maximum size. The buffer only grows and isn't shrank, because users with many flow counters don't care about the buffer size and we don't want to add resize overhead if the current number of counters drops. This solution is preferable to the current one, which is less accurate and only addresses SFs. Signed-off-by: Avihai Horon Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed --- .../net/ethernet/mellanox/mlx5/core/fs_counters.c | 74 ++++++++++++++++++---- include/linux/mlx5/driver.h | 4 ++ 2 files changed, 64 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 7e0e04cf26f8..b406e0367af6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -38,9 +38,10 @@ #include "fs_cmd.h" #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) +#define MLX5_FC_BULK_QUERY_ALLOC_PERIOD msecs_to_jiffies(180 * 1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) -#define MLX5_SF_NUM_COUNTERS_BULK 8 +#define MLX5_INIT_COUNTERS_BULK 8 #define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) #define MLX5_FC_POOL_USED_BUFF_RATIO 10 @@ -145,13 +146,15 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, spin_unlock(&fc_stats->counters_idr_lock); } -static int get_max_bulk_query_len(struct mlx5_core_dev *dev) +static int get_init_bulk_query_len(struct mlx5_core_dev *dev) { - int num_counters_bulk = mlx5_core_is_sf(dev) ? - MLX5_SF_NUM_COUNTERS_BULK : - MLX5_SW_MAX_COUNTERS_BULK; + return min_t(int, MLX5_INIT_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +} - return min_t(int, num_counters_bulk, +static int get_max_bulk_query_len(struct mlx5_core_dev *dev) +{ + return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); } @@ -177,7 +180,7 @@ static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; bool query_more_counters = (first->id <= last_id); - int max_bulk_len = get_max_bulk_query_len(dev); + int cur_bulk_len = fc_stats->bulk_query_len; u32 *data = fc_stats->bulk_query_out; struct mlx5_fc *counter = first; u32 bulk_base_id; @@ -189,7 +192,7 @@ static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, bulk_base_id = counter->id & ~0x3; /* number of counters to query inc. the last counter */ - bulk_len = min_t(int, max_bulk_len, + bulk_len = min_t(int, cur_bulk_len, ALIGN(last_id - bulk_base_id + 1, 4)); err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len, @@ -230,6 +233,41 @@ static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) mlx5_fc_free(dev, counter); } +static void mlx5_fc_stats_bulk_query_size_increase(struct mlx5_core_dev *dev) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int max_bulk_len = get_max_bulk_query_len(dev); + unsigned long now = jiffies; + u32 *bulk_query_out_tmp; + int max_out_len; + + if (fc_stats->bulk_query_alloc_failed && + time_before(now, fc_stats->next_bulk_query_alloc)) + return; + + max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); + bulk_query_out_tmp = kzalloc(max_out_len, GFP_KERNEL); + if (!bulk_query_out_tmp) { + mlx5_core_warn_once(dev, + "Can't increase flow counters bulk query buffer size, insufficient memory, bulk_size(%d)\n", + max_bulk_len); + fc_stats->bulk_query_alloc_failed = true; + fc_stats->next_bulk_query_alloc = + now + MLX5_FC_BULK_QUERY_ALLOC_PERIOD; + return; + } + + kfree(fc_stats->bulk_query_out); + fc_stats->bulk_query_out = bulk_query_out_tmp; + fc_stats->bulk_query_len = max_bulk_len; + if (fc_stats->bulk_query_alloc_failed) { + mlx5_core_info(dev, + "Flow counters bulk query buffer size increased, bulk_size(%d)\n", + max_bulk_len); + fc_stats->bulk_query_alloc_failed = false; + } +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, @@ -247,15 +285,22 @@ static void mlx5_fc_stats_work(struct work_struct *work) queue_delayed_work(fc_stats->wq, &fc_stats->work, fc_stats->sampling_interval); - llist_for_each_entry(counter, addlist, addlist) + llist_for_each_entry(counter, addlist, addlist) { mlx5_fc_stats_insert(dev, counter); + fc_stats->num_counters++; + } llist_for_each_entry_safe(counter, tmp, dellist, dellist) { mlx5_fc_stats_remove(dev, counter); mlx5_fc_release(dev, counter); + fc_stats->num_counters--; } + if (fc_stats->bulk_query_len < get_max_bulk_query_len(dev) && + fc_stats->num_counters > get_init_bulk_query_len(dev)) + mlx5_fc_stats_bulk_query_size_increase(dev); + if (time_before(now, fc_stats->next_query) || list_empty(&fc_stats->counters)) return; @@ -378,8 +423,8 @@ EXPORT_SYMBOL(mlx5_fc_destroy); int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - int max_bulk_len; - int max_out_len; + int init_bulk_len; + int init_out_len; spin_lock_init(&fc_stats->counters_idr_lock); idr_init(&fc_stats->counters_idr); @@ -387,11 +432,12 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); - max_bulk_len = get_max_bulk_query_len(dev); - max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); - fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL); + init_bulk_len = get_init_bulk_query_len(dev); + init_out_len = mlx5_cmd_fc_get_bulk_query_out_len(init_bulk_len); + fc_stats->bulk_query_out = kzalloc(init_out_len, GFP_KERNEL); if (!fc_stats->bulk_query_out) return -ENOMEM; + fc_stats->bulk_query_len = init_bulk_len; fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a623ec635947..78655d8d13a7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -478,6 +478,10 @@ struct mlx5_fc_stats { unsigned long next_query; unsigned long sampling_interval; /* jiffies */ u32 *bulk_query_out; + int bulk_query_len; + size_t num_counters; + bool bulk_query_alloc_failed; + unsigned long next_bulk_query_alloc; struct mlx5_fc_pool fc_pool; }; -- cgit v1.2.3 From e2748ad5257754a47376e28c0f9dda4f5c1e5ca3 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:02:00 -0600 Subject: mtd: remove unused header file Commit d24dbd7541ff ("mtd: maps: Get rid of the latch-addr-flash driver") removed the last user of but left the header file behind. Nothing uses this file, delete it now. Cc: Boris Brezillon Cc: Miquel Raynal Cc: Richard Weinberger Cc: Vignesh Raghavendra Cc: linux-mtd@lists.infradead.org Signed-off-by: Jonathan Corbet Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211102220203.940290-7-corbet@lwn.net --- include/linux/mtd/latch-addr-flash.h | 29 ----------------------------- 1 file changed, 29 deletions(-) delete mode 100644 include/linux/mtd/latch-addr-flash.h (limited to 'include/linux') diff --git a/include/linux/mtd/latch-addr-flash.h b/include/linux/mtd/latch-addr-flash.h deleted file mode 100644 index e94b8e128074..000000000000 --- a/include/linux/mtd/latch-addr-flash.h +++ /dev/null @@ -1,29 +0,0 @@ -/* - * Interface for NOR flash driver whose high address lines are latched - * - * Copyright © 2008 MontaVista Software, Inc. - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ -#ifndef __LATCH_ADDR_FLASH__ -#define __LATCH_ADDR_FLASH__ - -struct map_info; -struct mtd_partition; - -struct latch_addr_flash_data { - unsigned int width; - unsigned int size; - - int (*init)(void *data, int cs); - void (*done)(void *data); - void (*set_window)(unsigned long offset, void *data); - void *data; - - unsigned int nr_parts; - struct mtd_partition *parts; -}; - -#endif -- cgit v1.2.3 From 2c4dcd7fd57b20a21b65da04d89c38a7217d79cf Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 29 Nov 2021 14:03:07 +0100 Subject: topology/sysfs: export die attributes only if an architectures has support The die_id and die_cpus topology sysfs attributes have been added with commit 0e344d8c709f ("cpu/topology: Export die_id") and commit 2e4c54dac7b3 ("topology: Create core_cpus and die_cpus sysfs attributes"). While they are currently only used and useful for x86 they are still present with bogus default values for all architectures. Instead of enforcing such new sysfs attributes to all architectures, make them only optional visible if an architecture opts in by defining both the topology_die_id and topology_die_cpumask attributes. This is similar to what was done when the book and drawer topology levels were introduced: avoid useless and therefore confusing sysfs attributes for architectures which cannot make use of them. This should not break any existing applications, since this is a rather new interface and applications should be able to handle also older kernel versions without such attributes - besides that they contain only useful information for x86. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Heiko Carstens Link: https://lore.kernel.org/r/20211129130309.3256168-2-hca@linux.ibm.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cputopology.rst | 3 +++ drivers/base/topology.c | 8 ++++++++ include/linux/topology.h | 4 ++++ 3 files changed, 15 insertions(+) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cputopology.rst b/Documentation/admin-guide/cputopology.rst index 6b62e182baf4..c68d07533c45 100644 --- a/Documentation/admin-guide/cputopology.rst +++ b/Documentation/admin-guide/cputopology.rst @@ -11,6 +11,9 @@ Architecture-neutral, drivers/base/topology.c, exports these attributes. However, the book and drawer related sysfs files will only be created if CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively. +The die hierarchy related sysfs files will only be created if an architecture +provides the related macros as described below. + CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390, where they reflect the cpu and cache hierarchy. diff --git a/drivers/base/topology.c b/drivers/base/topology.c index 8f2b641d0b8c..f079a55793ec 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -45,8 +45,10 @@ static ssize_t name##_list_read(struct file *file, struct kobject *kobj, \ define_id_show_func(physical_package_id); static DEVICE_ATTR_RO(physical_package_id); +#ifdef TOPOLOGY_DIE_SYSFS define_id_show_func(die_id); static DEVICE_ATTR_RO(die_id); +#endif define_id_show_func(cluster_id); static DEVICE_ATTR_RO(cluster_id); @@ -70,9 +72,11 @@ define_siblings_read_func(cluster_cpus, cluster_cpumask); static BIN_ATTR_RO(cluster_cpus, 0); static BIN_ATTR_RO(cluster_cpus_list, 0); +#ifdef TOPOLOGY_DIE_SYSFS define_siblings_read_func(die_cpus, die_cpumask); static BIN_ATTR_RO(die_cpus, 0); static BIN_ATTR_RO(die_cpus_list, 0); +#endif define_siblings_read_func(package_cpus, core_cpumask); static BIN_ATTR_RO(package_cpus, 0); @@ -103,8 +107,10 @@ static struct bin_attribute *bin_attrs[] = { &bin_attr_core_siblings_list, &bin_attr_cluster_cpus, &bin_attr_cluster_cpus_list, +#ifdef TOPOLOGY_DIE_SYSFS &bin_attr_die_cpus, &bin_attr_die_cpus_list, +#endif &bin_attr_package_cpus, &bin_attr_package_cpus_list, #ifdef CONFIG_SCHED_BOOK @@ -120,7 +126,9 @@ static struct bin_attribute *bin_attrs[] = { static struct attribute *default_attrs[] = { &dev_attr_physical_package_id.attr, +#ifdef TOPOLOGY_DIE_SYSFS &dev_attr_die_id.attr, +#endif &dev_attr_cluster_id.attr, &dev_attr_core_id.attr, #ifdef CONFIG_SCHED_BOOK diff --git a/include/linux/topology.h b/include/linux/topology.h index 0b3704ad13c8..8d1bdae76230 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -180,6 +180,10 @@ static inline int cpu_to_mem(int cpu) #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ +#if defined(topology_die_id) && defined(topology_die_cpumask) +#define TOPOLOGY_DIE_SYSFS +#endif + #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif -- cgit v1.2.3 From e795707703b32fecdd7467afcc33ff1e92416c05 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 29 Nov 2021 14:03:08 +0100 Subject: topology/sysfs: export cluster attributes only if an architectures has support The cluster_id and cluster_cpus topology sysfs attributes have been added with commit c5e22feffdd7 ("topology: Represent clusters of CPUs within a die"). They are currently only used for x86, arm64, and riscv (via generic arch topology), however they are still present with bogus default values for all other architectures. Instead of enforcing such new sysfs attributes to all architectures, make them only optional visible if an architecture opts in by defining both the topology_cluster_id and topology_cluster_cpumask attributes. This is similar to what was done when the book and drawer topology levels were introduced: avoid useless and therefore confusing sysfs attributes for architectures which cannot make use of them. This should not break any existing applications, since this is a new interface introduced with the v5.16 merge window. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Heiko Carstens Link: https://lore.kernel.org/r/20211129130309.3256168-3-hca@linux.ibm.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cputopology.rst | 4 ++-- drivers/base/topology.c | 8 ++++++++ include/linux/topology.h | 3 +++ 3 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cputopology.rst b/Documentation/admin-guide/cputopology.rst index c68d07533c45..ad2238b41439 100644 --- a/Documentation/admin-guide/cputopology.rst +++ b/Documentation/admin-guide/cputopology.rst @@ -11,8 +11,8 @@ Architecture-neutral, drivers/base/topology.c, exports these attributes. However, the book and drawer related sysfs files will only be created if CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively. -The die hierarchy related sysfs files will only be created if an architecture -provides the related macros as described below. +The die and cluster hierarchy related sysfs files will only be created if an +architecture provides the related macros as described below. CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390, where they reflect the cpu and cache hierarchy. diff --git a/drivers/base/topology.c b/drivers/base/topology.c index f079a55793ec..9d049724e4b4 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -50,8 +50,10 @@ define_id_show_func(die_id); static DEVICE_ATTR_RO(die_id); #endif +#ifdef TOPOLOGY_CLUSTER_SYSFS define_id_show_func(cluster_id); static DEVICE_ATTR_RO(cluster_id); +#endif define_id_show_func(core_id); static DEVICE_ATTR_RO(core_id); @@ -68,9 +70,11 @@ define_siblings_read_func(core_siblings, core_cpumask); static BIN_ATTR_RO(core_siblings, 0); static BIN_ATTR_RO(core_siblings_list, 0); +#ifdef TOPOLOGY_CLUSTER_SYSFS define_siblings_read_func(cluster_cpus, cluster_cpumask); static BIN_ATTR_RO(cluster_cpus, 0); static BIN_ATTR_RO(cluster_cpus_list, 0); +#endif #ifdef TOPOLOGY_DIE_SYSFS define_siblings_read_func(die_cpus, die_cpumask); @@ -105,8 +109,10 @@ static struct bin_attribute *bin_attrs[] = { &bin_attr_thread_siblings_list, &bin_attr_core_siblings, &bin_attr_core_siblings_list, +#ifdef TOPOLOGY_CLUSTER_SYSFS &bin_attr_cluster_cpus, &bin_attr_cluster_cpus_list, +#endif #ifdef TOPOLOGY_DIE_SYSFS &bin_attr_die_cpus, &bin_attr_die_cpus_list, @@ -129,7 +135,9 @@ static struct attribute *default_attrs[] = { #ifdef TOPOLOGY_DIE_SYSFS &dev_attr_die_id.attr, #endif +#ifdef TOPOLOGY_CLUSTER_SYSFS &dev_attr_cluster_id.attr, +#endif &dev_attr_core_id.attr, #ifdef CONFIG_SCHED_BOOK &dev_attr_book_id.attr, diff --git a/include/linux/topology.h b/include/linux/topology.h index 8d1bdae76230..d52be69037db 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -183,6 +183,9 @@ static inline int cpu_to_mem(int cpu) #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif +#if defined(topology_cluster_id) && defined(topology_cluster_cpumask) +#define TOPOLOGY_CLUSTER_SYSFS +#endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) -- cgit v1.2.3 From f1045056c726440469d89d23c13734bcd6c0d15b Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 29 Nov 2021 14:03:09 +0100 Subject: topology/sysfs: rework book and drawer topology ifdefery Provide default defines for the topology_book_[id|cpumask] and topology_drawer_[id|cpumask] macros just like for each other topology level. This way all topology levels are handled in a similar way. Still the the book and drawer levels are only used on s390, and also the sysfs attributes are only created on s390. However other architectures may opt in if wanted. Acked-by: Peter Zijlstra (Intel) Signed-off-by: Heiko Carstens Link: https://lore.kernel.org/r/20211129130309.3256168-4-hca@linux.ibm.com Signed-off-by: Greg Kroah-Hartman --- Documentation/admin-guide/cputopology.rst | 36 +++++++++++++------------------ drivers/base/topology.c | 12 +++++------ include/linux/topology.h | 18 ++++++++++++++++ 3 files changed, 39 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cputopology.rst b/Documentation/admin-guide/cputopology.rst index ad2238b41439..677ba1c2c820 100644 --- a/Documentation/admin-guide/cputopology.rst +++ b/Documentation/admin-guide/cputopology.rst @@ -8,14 +8,9 @@ to /proc/cpuinfo output of some architectures. They reside in Documentation/ABI/stable/sysfs-devices-system-cpu. Architecture-neutral, drivers/base/topology.c, exports these attributes. -However, the book and drawer related sysfs files will only be created if -CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively. - -The die and cluster hierarchy related sysfs files will only be created if an -architecture provides the related macros as described below. - -CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390, -where they reflect the cpu and cache hierarchy. +However the die, cluster, book, and drawer hierarchy related sysfs files will +only be created if an architecture provides the related macros as described +below. For an architecture to support this feature, it must define some of these macros in include/asm-XXX/topology.h:: @@ -42,19 +37,18 @@ To be consistent on all architectures, include/linux/topology.h provides default definitions for any of the above macros that are not defined by include/asm-XXX/topology.h: -1) topology_physical_package_id: -1 -2) topology_die_id: -1 -3) topology_cluster_id: -1 -4) topology_core_id: 0 -5) topology_sibling_cpumask: just the given CPU -6) topology_core_cpumask: just the given CPU -7) topology_cluster_cpumask: just the given CPU -8) topology_die_cpumask: just the given CPU - -For architectures that don't support books (CONFIG_SCHED_BOOK) there are no -default definitions for topology_book_id() and topology_book_cpumask(). -For architectures that don't support drawers (CONFIG_SCHED_DRAWER) there are -no default definitions for topology_drawer_id() and topology_drawer_cpumask(). + 1) topology_physical_package_id: -1 + 2) topology_die_id: -1 + 3) topology_cluster_id: -1 + 4) topology_core_id: 0 + 5) topology_book_id: -1 + 6) topology_drawer_id: -1 + 7) topology_sibling_cpumask: just the given CPU + 8) topology_core_cpumask: just the given CPU + 9) topology_cluster_cpumask: just the given CPU +10) topology_die_cpumask: just the given CPU +11) topology_book_cpumask: just the given CPU +12) topology_drawer_cpumask: just the given CPU Additionally, CPU topology information is provided under /sys/devices/system/cpu and includes these files. The internal diff --git a/drivers/base/topology.c b/drivers/base/topology.c index 9d049724e4b4..fc24e89f9592 100644 --- a/drivers/base/topology.c +++ b/drivers/base/topology.c @@ -86,7 +86,7 @@ define_siblings_read_func(package_cpus, core_cpumask); static BIN_ATTR_RO(package_cpus, 0); static BIN_ATTR_RO(package_cpus_list, 0); -#ifdef CONFIG_SCHED_BOOK +#ifdef TOPOLOGY_BOOK_SYSFS define_id_show_func(book_id); static DEVICE_ATTR_RO(book_id); define_siblings_read_func(book_siblings, book_cpumask); @@ -94,7 +94,7 @@ static BIN_ATTR_RO(book_siblings, 0); static BIN_ATTR_RO(book_siblings_list, 0); #endif -#ifdef CONFIG_SCHED_DRAWER +#ifdef TOPOLOGY_DRAWER_SYSFS define_id_show_func(drawer_id); static DEVICE_ATTR_RO(drawer_id); define_siblings_read_func(drawer_siblings, drawer_cpumask); @@ -119,11 +119,11 @@ static struct bin_attribute *bin_attrs[] = { #endif &bin_attr_package_cpus, &bin_attr_package_cpus_list, -#ifdef CONFIG_SCHED_BOOK +#ifdef TOPOLOGY_BOOK_SYSFS &bin_attr_book_siblings, &bin_attr_book_siblings_list, #endif -#ifdef CONFIG_SCHED_DRAWER +#ifdef TOPOLOGY_DRAWER_SYSFS &bin_attr_drawer_siblings, &bin_attr_drawer_siblings_list, #endif @@ -139,10 +139,10 @@ static struct attribute *default_attrs[] = { &dev_attr_cluster_id.attr, #endif &dev_attr_core_id.attr, -#ifdef CONFIG_SCHED_BOOK +#ifdef TOPOLOGY_BOOK_SYSFS &dev_attr_book_id.attr, #endif -#ifdef CONFIG_SCHED_DRAWER +#ifdef TOPOLOGY_DRAWER_SYSFS &dev_attr_drawer_id.attr, #endif NULL diff --git a/include/linux/topology.h b/include/linux/topology.h index d52be69037db..a6e201758ae9 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -186,6 +186,12 @@ static inline int cpu_to_mem(int cpu) #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif +#if defined(topology_book_id) && defined(topology_book_cpumask) +#define TOPOLOGY_BOOK_SYSFS +#endif +#if defined(topology_drawer_id) && defined(topology_drawer_cpumask) +#define TOPOLOGY_DRAWER_SYSFS +#endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) @@ -199,6 +205,12 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif +#ifndef topology_book_id +#define topology_book_id(cpu) ((void)(cpu), -1) +#endif +#ifndef topology_drawer_id +#define topology_drawer_id(cpu) ((void)(cpu), -1) +#endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif @@ -211,6 +223,12 @@ static inline int cpu_to_mem(int cpu) #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif +#ifndef topology_book_cpumask +#define topology_book_cpumask(cpu) cpumask_of(cpu) +#endif +#ifndef topology_drawer_cpumask +#define topology_drawer_cpumask(cpu) cpumask_of(cpu) +#endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) -- cgit v1.2.3 From c7fdb2404f66131bc9c22e06f712717288826487 Mon Sep 17 00:00:00 2001 From: Abhyuday Godhasara Date: Sun, 28 Nov 2021 23:02:14 -0800 Subject: drivers: soc: xilinx: add xilinx event management driver Xilinx event management driver provides an interface to subscribe or unsubscribe for the event/callback supported by firmware. An agent can use this driver to register for Error Event, Device Event and Suspend callback. This driver only allows one agent per event to do registration. Driver will return an error in case of multiple registration for the same event. This driver gets notification from firmware through TF-A as SGI. During initialization, event manager driver register handler for SGI used for notification. It also provides SGI number info to TF-A by using IOCTL_REGISTER_SGI call to TF-A. After receiving notification from firmware, the driver makes an SMC call to TF-A to get IPI data. From the IPI data provided by TF-A, event manager identified the cause of event and forward that event/callback notification to the respective subscribed driver. After this, in case of Error Event, driver performs unregistration as firmware expecting from agent to do re-registration if the agent wants to get notified on the second occurrence of an error event. Add new IOCTL id IOCTL_REGISTER_SGI = 25 which is used to register SGI on TF-A. Older firmware doesn't have all required support for event handling which is required by the event manager driver. So add check for the register notifier version in the event manager driver. Xilinx event management driver provides support to subscribe for multiple error events with the use of Event Mask in a single call of xlnx_register_event(). Agent driver can provide 'Event' parameter value as ORed of multiple event masks to register single callback for multiple events. For example, to register callback for event=0x1 and event=0x2 for the given node, agent can provide event=0x3 (0x1 | 0x2). It is not possible to register multiple events for different nodes in a single registration call. Also provide support to receive multiple error events as in single notification from firmware and then forward it to subscribed drivers via registered callback one by one. Acked-by: Michal Simek Signed-off-by: Tejas Patel Signed-off-by: Rajan Vaja Signed-off-by: Abhyuday Godhasara Link: https://lore.kernel.org/r/20211129070216.30253-2-abhyuday.godhasara@xilinx.com Signed-off-by: Greg Kroah-Hartman --- MAINTAINERS | 6 + drivers/soc/xilinx/Kconfig | 10 + drivers/soc/xilinx/Makefile | 1 + drivers/soc/xilinx/xlnx_event_manager.c | 600 ++++++++++++++++++++++++++++ include/linux/firmware/xlnx-event-manager.h | 36 ++ include/linux/firmware/xlnx-zynqmp.h | 2 + 6 files changed, 655 insertions(+) create mode 100644 drivers/soc/xilinx/xlnx_event_manager.c create mode 100644 include/linux/firmware/xlnx-event-manager.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 0533c00325d6..3ef68211cc6f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -20946,6 +20946,12 @@ T: git https://github.com/Xilinx/linux-xlnx.git F: Documentation/devicetree/bindings/phy/xlnx,zynqmp-psgtr.yaml F: drivers/phy/xilinx/phy-zynqmp.c +XILINX EVENT MANAGEMENT DRIVER +M: Abhyuday Godhasara +S: Maintained +F: drivers/soc/xilinx/xlnx_event_manager.c +F: include/linux/firmware/xlnx-event-manager.h + XILLYBUS DRIVER M: Eli Billauer L: linux-kernel@vger.kernel.org diff --git a/drivers/soc/xilinx/Kconfig b/drivers/soc/xilinx/Kconfig index 53af9115dc31..8a755a5c8836 100644 --- a/drivers/soc/xilinx/Kconfig +++ b/drivers/soc/xilinx/Kconfig @@ -25,4 +25,14 @@ config ZYNQMP_PM_DOMAINS Say yes to enable device power management through PM domains If in doubt, say N. +config XLNX_EVENT_MANAGER + bool "Enable Xilinx Event Management Driver" + depends on ZYNQMP_FIRMWARE + default ZYNQMP_FIRMWARE + help + Say yes to enable event management support for Xilinx. + This driver uses firmware driver as an interface for event/power + management request to firmware. + + If in doubt, say N. endmenu diff --git a/drivers/soc/xilinx/Makefile b/drivers/soc/xilinx/Makefile index 9854e6f6086b..41e585bc9c67 100644 --- a/drivers/soc/xilinx/Makefile +++ b/drivers/soc/xilinx/Makefile @@ -1,3 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ZYNQMP_POWER) += zynqmp_power.o obj-$(CONFIG_ZYNQMP_PM_DOMAINS) += zynqmp_pm_domains.o +obj-$(CONFIG_XLNX_EVENT_MANAGER) += xlnx_event_manager.o diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c new file mode 100644 index 000000000000..b27f8853508e --- /dev/null +++ b/drivers/soc/xilinx/xlnx_event_manager.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Xilinx Event Management Driver + * + * Copyright (C) 2021 Xilinx, Inc. + * + * Abhyuday Godhasara + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number1); + +static int virq_sgi; +static int event_manager_availability = -EACCES; + +/* SGI number used for Event management driver */ +#define XLNX_EVENT_SGI_NUM (15) + +/* Max number of driver can register for same event */ +#define MAX_DRIVER_PER_EVENT (10U) + +/* Max HashMap Order for PM API feature check (1<<7 = 128) */ +#define REGISTERED_DRIVER_MAX_ORDER (7) + +#define MAX_BITS (32U) /* Number of bits available for error mask */ + +#define FIRMWARE_VERSION_MASK (0xFFFFU) +#define REGISTER_NOTIFIER_FIRMWARE_VERSION (2U) + +static DEFINE_HASHTABLE(reg_driver_map, REGISTERED_DRIVER_MAX_ORDER); +static int sgi_num = XLNX_EVENT_SGI_NUM; + +/** + * struct registered_event_data - Registered Event Data. + * @key: key is the combine id(Node-Id | Event-Id) of type u64 + * where upper u32 for Node-Id and lower u32 for Event-Id, + * And this used as key to index into hashmap. + * @agent_data: Data passed back to handler function. + * @cb_type: Type of Api callback, like PM_NOTIFY_CB, etc. + * @eve_cb: Function pointer to store the callback function. + * @wake: If this flag set, firmware will wakeup processor if is + * in sleep or power down state. + * @hentry: hlist_node that hooks this entry into hashtable. + */ +struct registered_event_data { + u64 key; + enum pm_api_cb_id cb_type; + void *agent_data; + + event_cb_func_t eve_cb; + bool wake; + struct hlist_node hentry; +}; + +static bool xlnx_is_error_event(const u32 node_id) +{ + if (node_id == EVENT_ERROR_PMC_ERR1 || + node_id == EVENT_ERROR_PMC_ERR2 || + node_id == EVENT_ERROR_PSM_ERR1 || + node_id == EVENT_ERROR_PSM_ERR2) + return true; + + return false; +} + +static int xlnx_add_cb_for_notify_event(const u32 node_id, const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data) +{ + u64 key = 0; + struct registered_event_data *eve_data; + + key = ((u64)node_id << 32U) | (u64)event; + /* Check for existing entry in hash table for given key id */ + hash_for_each_possible(reg_driver_map, eve_data, hentry, key) { + if (eve_data->key == key) { + pr_err("Found as already registered\n"); + return -EINVAL; + } + } + + /* Add new entry if not present */ + eve_data = kmalloc(sizeof(*eve_data), GFP_KERNEL); + if (!eve_data) + return -ENOMEM; + + eve_data->key = key; + eve_data->cb_type = PM_NOTIFY_CB; + eve_data->eve_cb = cb_fun; + eve_data->wake = wake; + eve_data->agent_data = data; + + hash_add(reg_driver_map, &eve_data->hentry, key); + + return 0; +} + +static int xlnx_add_cb_for_suspend(event_cb_func_t cb_fun, void *data) +{ + struct registered_event_data *eve_data; + + /* Check for existing entry in hash table for given cb_type */ + hash_for_each_possible(reg_driver_map, eve_data, hentry, PM_INIT_SUSPEND_CB) { + if (eve_data->cb_type == PM_INIT_SUSPEND_CB) { + pr_err("Found as already registered\n"); + return -EINVAL; + } + } + + /* Add new entry if not present */ + eve_data = kmalloc(sizeof(*eve_data), GFP_KERNEL); + if (!eve_data) + return -ENOMEM; + + eve_data->key = 0; + eve_data->cb_type = PM_INIT_SUSPEND_CB; + eve_data->eve_cb = cb_fun; + eve_data->agent_data = data; + + hash_add(reg_driver_map, &eve_data->hentry, PM_INIT_SUSPEND_CB); + + return 0; +} + +static int xlnx_remove_cb_for_suspend(event_cb_func_t cb_fun) +{ + bool is_callback_found = false; + struct registered_event_data *eve_data; + + /* Check for existing entry in hash table for given cb_type */ + hash_for_each_possible(reg_driver_map, eve_data, hentry, PM_INIT_SUSPEND_CB) { + if (eve_data->cb_type == PM_INIT_SUSPEND_CB && + eve_data->eve_cb == cb_fun) { + is_callback_found = true; + /* remove an object from a hashtable */ + hash_del(&eve_data->hentry); + kfree(eve_data); + } + } + if (!is_callback_found) { + pr_warn("Didn't find any registered callback for suspend event\n"); + return -EINVAL; + } + + return 0; +} + +static int xlnx_remove_cb_for_notify_event(const u32 node_id, const u32 event, + event_cb_func_t cb_fun) +{ + bool is_callback_found = false; + struct registered_event_data *eve_data; + u64 key = ((u64)node_id << 32U) | (u64)event; + + /* Check for existing entry in hash table for given key id */ + hash_for_each_possible(reg_driver_map, eve_data, hentry, key) { + if (eve_data->key == key && + eve_data->eve_cb == cb_fun) { + is_callback_found = true; + /* remove an object from a hashtable */ + hash_del(&eve_data->hentry); + kfree(eve_data); + } + } + if (!is_callback_found) { + pr_warn("Didn't find any registered callback for 0x%x 0x%x\n", + node_id, event); + return -EINVAL; + } + + return 0; +} + +/** + * xlnx_register_event() - Register for the event. + * @cb_type: Type of callback from pm_api_cb_id, + * PM_NOTIFY_CB - for Error Events, + * PM_INIT_SUSPEND_CB - for suspend callback. + * @node_id: Node-Id related to event. + * @event: Event Mask for the Error Event. + * @wake: Flag specifying whether the subsystem should be woken upon + * event notification. + * @cb_fun: Function pointer to store the callback function. + * @data: Pointer for the driver instance. + * + * Return: Returns 0 on successful registration else error code. + */ +int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, const u32 event, + const bool wake, event_cb_func_t cb_fun, void *data) +{ + int ret = 0; + u32 eve; + int pos; + + if (event_manager_availability) + return event_manager_availability; + + if (cb_type != PM_NOTIFY_CB && cb_type != PM_INIT_SUSPEND_CB) { + pr_err("%s() Unsupported Callback 0x%x\n", __func__, cb_type); + return -EINVAL; + } + + if (!cb_fun) + return -EFAULT; + + if (cb_type == PM_INIT_SUSPEND_CB) { + ret = xlnx_add_cb_for_suspend(cb_fun, data); + } else { + if (!xlnx_is_error_event(node_id)) { + /* Add entry for Node-Id/Event in hash table */ + ret = xlnx_add_cb_for_notify_event(node_id, event, wake, cb_fun, data); + } else { + /* Add into Hash table */ + for (pos = 0; pos < MAX_BITS; pos++) { + eve = event & (1 << pos); + if (!eve) + continue; + + /* Add entry for Node-Id/Eve in hash table */ + ret = xlnx_add_cb_for_notify_event(node_id, eve, wake, cb_fun, + data); + /* Break the loop if got error */ + if (ret) + break; + } + if (ret) { + /* Skip the Event for which got the error */ + pos--; + /* Remove registered(during this call) event from hash table */ + for ( ; pos >= 0; pos--) { + eve = event & (1 << pos); + if (!eve) + continue; + xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun); + } + } + } + + if (ret) { + pr_err("%s() failed for 0x%x and 0x%x: %d\r\n", __func__, node_id, + event, ret); + return ret; + } + + /* Register for Node-Id/Event combination in firmware */ + ret = zynqmp_pm_register_notifier(node_id, event, wake, true); + if (ret) { + pr_err("%s() failed for 0x%x and 0x%x: %d\r\n", __func__, node_id, + event, ret); + /* Remove already registered event from hash table */ + if (xlnx_is_error_event(node_id)) { + for (pos = 0; pos < MAX_BITS; pos++) { + eve = event & (1 << pos); + if (!eve) + continue; + xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun); + } + } else { + xlnx_remove_cb_for_notify_event(node_id, event, cb_fun); + } + return ret; + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(xlnx_register_event); + +/** + * xlnx_unregister_event() - Unregister for the event. + * @cb_type: Type of callback from pm_api_cb_id, + * PM_NOTIFY_CB - for Error Events, + * PM_INIT_SUSPEND_CB - for suspend callback. + * @node_id: Node-Id related to event. + * @event: Event Mask for the Error Event. + * @cb_fun: Function pointer of callback function. + * + * Return: Returns 0 on successful unregistration else error code. + */ +int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, const u32 event, + event_cb_func_t cb_fun) +{ + int ret; + u32 eve, pos; + + if (event_manager_availability) + return event_manager_availability; + + if (cb_type != PM_NOTIFY_CB && cb_type != PM_INIT_SUSPEND_CB) { + pr_err("%s() Unsupported Callback 0x%x\n", __func__, cb_type); + return -EINVAL; + } + + if (!cb_fun) + return -EFAULT; + + if (cb_type == PM_INIT_SUSPEND_CB) { + ret = xlnx_remove_cb_for_suspend(cb_fun); + } else { + /* Remove Node-Id/Event from hash table */ + if (!xlnx_is_error_event(node_id)) { + xlnx_remove_cb_for_notify_event(node_id, event, cb_fun); + } else { + for (pos = 0; pos < MAX_BITS; pos++) { + eve = event & (1 << pos); + if (!eve) + continue; + + xlnx_remove_cb_for_notify_event(node_id, eve, cb_fun); + } + } + + /* Un-register for Node-Id/Event combination */ + ret = zynqmp_pm_register_notifier(node_id, event, false, false); + if (ret) { + pr_err("%s() failed for 0x%x and 0x%x: %d\n", + __func__, node_id, event, ret); + return ret; + } + } + + return ret; +} +EXPORT_SYMBOL_GPL(xlnx_unregister_event); + +static void xlnx_call_suspend_cb_handler(const u32 *payload) +{ + bool is_callback_found = false; + struct registered_event_data *eve_data; + u32 cb_type = payload[0]; + + /* Check for existing entry in hash table for given cb_type */ + hash_for_each_possible(reg_driver_map, eve_data, hentry, cb_type) { + if (eve_data->cb_type == cb_type) { + eve_data->eve_cb(&payload[0], eve_data->agent_data); + is_callback_found = true; + } + } + if (!is_callback_found) + pr_warn("Didn't find any registered callback for suspend event\n"); +} + +static void xlnx_call_notify_cb_handler(const u32 *payload) +{ + bool is_callback_found = false; + struct registered_event_data *eve_data; + u64 key = ((u64)payload[1] << 32U) | (u64)payload[2]; + int ret; + + /* Check for existing entry in hash table for given key id */ + hash_for_each_possible(reg_driver_map, eve_data, hentry, key) { + if (eve_data->key == key) { + eve_data->eve_cb(&payload[0], eve_data->agent_data); + is_callback_found = true; + + /* re register with firmware to get future events */ + ret = zynqmp_pm_register_notifier(payload[1], payload[2], + eve_data->wake, true); + if (ret) { + pr_err("%s() failed for 0x%x and 0x%x: %d\r\n", __func__, + payload[1], payload[2], ret); + /* Remove already registered event from hash table */ + xlnx_remove_cb_for_notify_event(payload[1], payload[2], + eve_data->eve_cb); + } + } + } + if (!is_callback_found) + pr_warn("Didn't find any registered callback for 0x%x 0x%x\n", + payload[1], payload[2]); +} + +static void xlnx_get_event_callback_data(u32 *buf) +{ + zynqmp_pm_invoke_fn(GET_CALLBACK_DATA, 0, 0, 0, 0, buf); +} + +static irqreturn_t xlnx_event_handler(int irq, void *dev_id) +{ + u32 cb_type, node_id, event, pos; + u32 payload[CB_MAX_PAYLOAD_SIZE] = {0}; + u32 event_data[CB_MAX_PAYLOAD_SIZE] = {0}; + + /* Get event data */ + xlnx_get_event_callback_data(payload); + + /* First element is callback type, others are callback arguments */ + cb_type = payload[0]; + + if (cb_type == PM_NOTIFY_CB) { + node_id = payload[1]; + event = payload[2]; + if (!xlnx_is_error_event(node_id)) { + xlnx_call_notify_cb_handler(payload); + } else { + /* + * Each call back function expecting payload as an input arguments. + * We can get multiple error events as in one call back through error + * mask. So payload[2] may can contain multiple error events. + * In reg_driver_map database we store data in the combination of single + * node_id-error combination. + * So coping the payload message into event_data and update the + * event_data[2] with Error Mask for single error event and use + * event_data as input argument for registered call back function. + * + */ + memcpy(event_data, payload, (4 * CB_MAX_PAYLOAD_SIZE)); + /* Support Multiple Error Event */ + for (pos = 0; pos < MAX_BITS; pos++) { + if ((0 == (event & (1 << pos)))) + continue; + event_data[2] = (event & (1 << pos)); + xlnx_call_notify_cb_handler(event_data); + } + } + } else if (cb_type == PM_INIT_SUSPEND_CB) { + xlnx_call_suspend_cb_handler(payload); + } else { + pr_err("%s() Unsupported Callback %d\n", __func__, cb_type); + } + + return IRQ_HANDLED; +} + +static int xlnx_event_cpuhp_start(unsigned int cpu) +{ + enable_percpu_irq(virq_sgi, IRQ_TYPE_NONE); + + return 0; +} + +static int xlnx_event_cpuhp_down(unsigned int cpu) +{ + disable_percpu_irq(virq_sgi); + + return 0; +} + +static void xlnx_disable_percpu_irq(void *data) +{ + disable_percpu_irq(virq_sgi); +} + +static int xlnx_event_init_sgi(struct platform_device *pdev) +{ + int ret = 0; + int cpu = smp_processor_id(); + /* + * IRQ related structures are used for the following: + * for each SGI interrupt ensure its mapped by GIC IRQ domain + * and that each corresponding linux IRQ for the HW IRQ has + * a handler for when receiving an interrupt from the remote + * processor. + */ + struct irq_domain *domain; + struct irq_fwspec sgi_fwspec; + struct device_node *interrupt_parent = NULL; + struct device *parent = pdev->dev.parent; + + /* Find GIC controller to map SGIs. */ + interrupt_parent = of_irq_find_parent(parent->of_node); + if (!interrupt_parent) { + dev_err(&pdev->dev, "Failed to find property for Interrupt parent\n"); + return -EINVAL; + } + + /* Each SGI needs to be associated with GIC's IRQ domain. */ + domain = irq_find_host(interrupt_parent); + of_node_put(interrupt_parent); + + /* Each mapping needs GIC domain when finding IRQ mapping. */ + sgi_fwspec.fwnode = domain->fwnode; + + /* + * When irq domain looks at mapping each arg is as follows: + * 3 args for: interrupt type (SGI), interrupt # (set later), type + */ + sgi_fwspec.param_count = 1; + + /* Set SGI's hwirq */ + sgi_fwspec.param[0] = sgi_num; + virq_sgi = irq_create_fwspec_mapping(&sgi_fwspec); + + per_cpu(cpu_number1, cpu) = cpu; + ret = request_percpu_irq(virq_sgi, xlnx_event_handler, "xlnx_event_mgmt", + &cpu_number1); + WARN_ON(ret); + if (ret) { + irq_dispose_mapping(virq_sgi); + return ret; + } + + irq_to_desc(virq_sgi); + irq_set_status_flags(virq_sgi, IRQ_PER_CPU); + + return ret; +} + +static void xlnx_event_cleanup_sgi(struct platform_device *pdev) +{ + int cpu = smp_processor_id(); + + per_cpu(cpu_number1, cpu) = cpu; + + cpuhp_remove_state(CPUHP_AP_ONLINE_DYN); + + on_each_cpu(xlnx_disable_percpu_irq, NULL, 1); + + irq_clear_status_flags(virq_sgi, IRQ_PER_CPU); + free_percpu_irq(virq_sgi, &cpu_number1); + irq_dispose_mapping(virq_sgi); +} + +static int xlnx_event_manager_probe(struct platform_device *pdev) +{ + int ret; + + ret = zynqmp_pm_feature(PM_REGISTER_NOTIFIER); + if (ret < 0) { + dev_err(&pdev->dev, "Feature check failed with %d\n", ret); + return ret; + } + + if ((ret & FIRMWARE_VERSION_MASK) < + REGISTER_NOTIFIER_FIRMWARE_VERSION) { + dev_err(&pdev->dev, "Register notifier version error. Expected Firmware: v%d - Found: v%d\n", + REGISTER_NOTIFIER_FIRMWARE_VERSION, + ret & FIRMWARE_VERSION_MASK); + return -EOPNOTSUPP; + } + + /* Initialize the SGI */ + ret = xlnx_event_init_sgi(pdev); + if (ret) { + dev_err(&pdev->dev, "SGI Init has been failed with %d\n", ret); + return ret; + } + + /* Setup function for the CPU hot-plug cases */ + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "soc/event:starting", + xlnx_event_cpuhp_start, xlnx_event_cpuhp_down); + + ret = zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_REGISTER_SGI, sgi_num, + 0, NULL); + if (ret) { + dev_err(&pdev->dev, "SGI %d Registration over TF-A failed with %d\n", sgi_num, ret); + xlnx_event_cleanup_sgi(pdev); + return ret; + } + + event_manager_availability = 0; + + dev_info(&pdev->dev, "SGI %d Registered over TF-A\n", sgi_num); + dev_info(&pdev->dev, "Xilinx Event Management driver probed\n"); + + return ret; +} + +static int xlnx_event_manager_remove(struct platform_device *pdev) +{ + int i; + struct registered_event_data *eve_data; + struct hlist_node *tmp; + int ret; + + hash_for_each_safe(reg_driver_map, i, tmp, eve_data, hentry) { + hash_del(&eve_data->hentry); + kfree(eve_data); + } + + ret = zynqmp_pm_invoke_fn(PM_IOCTL, 0, IOCTL_REGISTER_SGI, 0, 1, NULL); + if (ret) + dev_err(&pdev->dev, "SGI unregistration over TF-A failed with %d\n", ret); + + xlnx_event_cleanup_sgi(pdev); + + event_manager_availability = -EACCES; + + return ret; +} + +static struct platform_driver xlnx_event_manager_driver = { + .probe = xlnx_event_manager_probe, + .remove = xlnx_event_manager_remove, + .driver = { + .name = "xlnx_event_manager", + }, +}; +module_param(sgi_num, uint, 0); +module_platform_driver(xlnx_event_manager_driver); diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h new file mode 100644 index 000000000000..3f87c4929d21 --- /dev/null +++ b/include/linux/firmware/xlnx-event-manager.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _FIRMWARE_XLNX_EVENT_MANAGER_H_ +#define _FIRMWARE_XLNX_EVENT_MANAGER_H_ + +#include + +#define CB_MAX_PAYLOAD_SIZE (4U) /*In payload maximum 32bytes */ + +/************************** Exported Function *****************************/ + +typedef void (*event_cb_func_t)(const u32 *payload, void *data); + +#if IS_REACHABLE(CONFIG_XLNX_EVENT_MANAGER) +int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data); + +int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, event_cb_func_t cb_fun); +#else +static inline int xlnx_register_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, const bool wake, + event_cb_func_t cb_fun, void *data) +{ + return -ENODEV; +} + +static inline int xlnx_unregister_event(const enum pm_api_cb_id cb_type, const u32 node_id, + const u32 event, event_cb_func_t cb_fun) +{ + return -ENODEV; +} +#endif + +#endif /* _FIRMWARE_XLNX_EVENT_MANAGER_H_ */ diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index 077e894bb340..907cb01890cf 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -141,6 +141,8 @@ enum pm_ioctl_id { /* Set healthy bit value */ IOCTL_SET_BOOT_HEALTH_STATUS = 17, IOCTL_OSPI_MUX_SELECT = 21, + /* Register SGI to ATF */ + IOCTL_REGISTER_SGI = 25, }; enum pm_query_id { -- cgit v1.2.3 From 14866a7db8da1f61fb6135c461b733694eea9580 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 1 Dec 2021 20:43:03 -0800 Subject: Documentation/auxiliary_bus: Add example code for module_auxiliary_driver() Add an example code snipit to the module_auxiliary_driver() documentation which is consistent with the other example code in the elsewhere in the documentation. Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20211202044305.4006853-6-ira.weiny@intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/auxiliary_bus.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index fc51d45f106b..605b27aab693 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -66,6 +66,10 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv); * Helper macro for auxiliary drivers which do not do anything special in * module init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() + * + * .. code-block:: c + * + * module_auxiliary_driver(my_drv); */ #define module_auxiliary_driver(__auxiliary_driver) \ module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister) -- cgit v1.2.3 From e1b5186810cc7d4ec60447032636b8e6772dbbc6 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Wed, 1 Dec 2021 20:43:05 -0800 Subject: Documentation/auxiliary_bus: Move the text into the code The code and documentation are more difficult to maintain when kept separately. This is further compounded when the standard structure documentation infrastructure is not used. Move the documentation into the code, use the standard documentation infrastructure, add current documented functions, and reference the text in the rst file. Suggested-by: Greg Kroah-Hartman Signed-off-by: Ira Weiny Link: https://lore.kernel.org/r/20211202044305.4006853-8-ira.weiny@intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/auxiliary_bus.rst | 298 ++--------------------------- drivers/base/auxiliary.c | 141 ++++++++++++++ include/linux/auxiliary_bus.h | 160 ++++++++++++++++ 3 files changed, 318 insertions(+), 281 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/auxiliary_bus.rst b/Documentation/driver-api/auxiliary_bus.rst index 3786e4664a1e..cec84908fbc0 100644 --- a/Documentation/driver-api/auxiliary_bus.rst +++ b/Documentation/driver-api/auxiliary_bus.rst @@ -6,309 +6,45 @@ Auxiliary Bus ============= -In some subsystems, the functionality of the core device (PCI/ACPI/other) is -too complex for a single device to be managed by a monolithic driver -(e.g. Sound Open Firmware), multiple devices might implement a common -intersection of functionality (e.g. NICs + RDMA), or a driver may want to -export an interface for another subsystem to drive (e.g. SIOV Physical Function -export Virtual Function management). A split of the functionality into child- -devices representing sub-domains of functionality makes it possible to -compartmentalize, layer, and distribute domain-specific concerns via a Linux -device-driver model. - -An example for this kind of requirement is the audio subsystem where a single -IP is handling multiple entities such as HDMI, Soundwire, local devices such as -mics/speakers etc. The split for the core's functionality can be arbitrary or -be defined by the DSP firmware topology and include hooks for test/debug. This -allows for the audio core device to be minimal and focused on hardware-specific -control and communication. - -Each auxiliary_device represents a part of its parent functionality. The -generic behavior can be extended and specialized as needed by encapsulating an -auxiliary_device within other domain-specific structures and the use of .ops -callbacks. Devices on the auxiliary bus do not share any structures and the use -of a communication channel with the parent is domain-specific. - -Note that ops are intended as a way to augment instance behavior within a class -of auxiliary devices, it is not the mechanism for exporting common -infrastructure from the parent. Consider EXPORT_SYMBOL_NS() to convey -infrastructure from the parent module to the auxiliary module(s). - +.. kernel-doc:: drivers/base/auxiliary.c + :doc: PURPOSE When Should the Auxiliary Bus Be Used ===================================== -The auxiliary bus is to be used when a driver and one or more kernel modules, -who share a common header file with the driver, need a mechanism to connect and -provide access to a shared object allocated by the auxiliary_device's -registering driver. The registering driver for the auxiliary_device(s) and the -kernel module(s) registering auxiliary_drivers can be from the same subsystem, -or from multiple subsystems. - -The emphasis here is on a common generic interface that keeps subsystem -customization out of the bus infrastructure. - -One example is a PCI network device that is RDMA-capable and exports a child -device to be driven by an auxiliary_driver in the RDMA subsystem. The PCI -driver allocates and registers an auxiliary_device for each physical -function on the NIC. The RDMA driver registers an auxiliary_driver that claims -each of these auxiliary_devices. This conveys data/ops published by the parent -PCI device/driver to the RDMA auxiliary_driver. - -Another use case is for the PCI device to be split out into multiple sub -functions. For each sub function an auxiliary_device is created. A PCI sub -function driver binds to such devices that creates its own one or more class -devices. A PCI sub function auxiliary device is likely to be contained in a -struct with additional attributes such as user defined sub function number and -optional attributes such as resources and a link to the parent device. These -attributes could be used by systemd/udev; and hence should be initialized -before a driver binds to an auxiliary_device. +.. kernel-doc:: drivers/base/auxiliary.c + :doc: USAGE -A key requirement for utilizing the auxiliary bus is that there is no -dependency on a physical bus, device, register accesses or regmap support. -These individual devices split from the core cannot live on the platform bus as -they are not physical devices that are controlled by DT/ACPI. The same -argument applies for not using MFD in this scenario as MFD relies on individual -function devices being physical devices. Auxiliary Device Creation ========================= -An auxiliary_device represents a part of its parent device's functionality. It -is given a name that, combined with the registering drivers KBUILD_MODNAME, -creates a match_name that is used for driver binding, and an id that combined -with the match_name provide a unique name to register with the bus subsystem. -For example, a driver registering an auxiliary device is named 'foo_mod.ko' and -the subdevice is named 'foo_dev'. The match name is therefore -'foo_mod.foo_dev'. - -.. code-block:: c - - struct auxiliary_device { - struct device dev; - const char *name; - u32 id; - }; - -Registering an auxiliary_device is a three-step process. - -First, a 'struct auxiliary_device' needs to be defined or allocated for each -sub-device desired. The name, id, dev.release, and dev.parent fields of this -structure must be filled in as follows. - -The 'name' field is to be given a name that is recognized by the auxiliary -driver. If two auxiliary_devices with the same match_name, eg -"foo_mod.foo_dev", are registered onto the bus, they must have unique id -values (e.g. "x" and "y") so that the registered devices names are "foo_mod.foo_dev.x" -and "foo_mod.foo_dev.y". If match_name + id are not unique, then the device_add fails -and generates an error message. - -The auxiliary_device.dev.type.release or auxiliary_device.dev.release must be -populated with a non-NULL pointer to successfully register the -auxiliary_device. This release call is where resources associated with the -auxiliary device must be free'ed. Because once the device is placed on the bus -the parent driver can not tell what other code may have a reference to this -data. - -The auxiliary_device.dev.parent should be set. Typically to the registering -drivers device. - -Second, call auxiliary_device_init(), which checks several aspects of the -auxiliary_device struct and performs a device_initialize(). After this step -completes, any error state must have a call to auxiliary_device_uninit() in its -resolution path. - -The third and final step in registering an auxiliary_device is to perform a -call to auxiliary_device_add(), which sets the name of the device and adds the -device to the bus. - -.. code-block:: c - - #define MY_DEVICE_NAME "foo_dev" - - ... - - struct auxiliary_device *my_aux_dev = my_aux_dev_alloc(xxx); - - /* Step 1: */ - my_aux_dev->name = MY_DEVICE_NAME; - my_aux_dev->id = my_unique_id_alloc(xxx); - my_aux_dev->dev.release = my_aux_dev_release; - my_aux_dev->dev.parent = my_dev; - - /* Step 2: */ - if (auxiliary_device_init(my_aux_dev)) - goto fail; - - /* Step 3: */ - if (auxiliary_device_add(my_aux_dev)) { - auxiliary_device_uninit(my_aux_dev); - goto fail; - } - - ... - - -Unregistering an auxiliary_device is a two-step process to mirror the register -process. First call auxiliary_device_delete(), then call -auxiliary_device_uninit(). - - -.. code-block:: c - - auxiliary_device_delete(my_dev->my_aux_dev); - auxiliary_device_uninit(my_dev->my_aux_dev); +.. kernel-doc:: include/linux/auxiliary_bus.h + :identifiers: auxiliary_device +.. kernel-doc:: drivers/base/auxiliary.c + :identifiers: auxiliary_device_init __auxiliary_device_add + auxiliary_find_device Auxiliary Device Memory Model and Lifespan ------------------------------------------ -The registering driver is the entity that allocates memory for the -auxiliary_device and registers it on the auxiliary bus. It is important to note -that, as opposed to the platform bus, the registering driver is wholly -responsible for the management of the memory used for the device object. - -To be clear the memory for the auxiliary_device is freed in the release() -callback defined by the registering driver. The registering driver should only -call auxiliary_device_delete() and then auxiliary_device_uninit() when it is -done with the device. The release() function is then automatically called if -and when other code releases their reference to the devices. - -A parent object, defined in the shared header file, contains the -auxiliary_device. It also contains a pointer to the shared object(s), which -also is defined in the shared header. Both the parent object and the shared -object(s) are allocated by the registering driver. This layout allows the -auxiliary_driver's registering module to perform a container_of() call to go -from the pointer to the auxiliary_device, that is passed during the call to the -auxiliary_driver's probe function, up to the parent object, and then have -access to the shared object(s). - -The memory for the shared object(s) must have a lifespan equal to, or greater -than, the lifespan of the memory for the auxiliary_device. The -auxiliary_driver should only consider that the shared object is valid as long -as the auxiliary_device is still registered on the auxiliary bus. It is up to -the registering driver to manage (e.g. free or keep available) the memory for -the shared object beyond the life of the auxiliary_device. - -The registering driver must unregister all auxiliary devices before its own -driver.remove() is completed. An easy way to ensure this is to use the -devm_add_action_or_reset() call to register a function against the parent device -which unregisters the auxiliary device object(s). - -Finally, any operations which operate on the auxiliary devices must continue to -function (if only to return an error) after the registering driver unregisters -the auxiliary device. +.. kernel-doc:: include/linux/auxiliary_bus.h + :doc: DEVICE_LIFESPAN Auxiliary Drivers ================= -Auxiliary drivers follow the standard driver model convention, where -discovery/enumeration is handled by the core, and drivers -provide probe() and remove() methods. They support power management -and shutdown notifications using the standard conventions. - -.. code-block:: c - - struct auxiliary_driver { - int (*probe)(struct auxiliary_device *, - const struct auxiliary_device_id *id); - void (*remove)(struct auxiliary_device *); - void (*shutdown)(struct auxiliary_device *); - int (*suspend)(struct auxiliary_device *, pm_message_t); - int (*resume)(struct auxiliary_device *); - struct device_driver driver; - const struct auxiliary_device_id *id_table; - }; - -Auxiliary drivers register themselves with the bus by calling -auxiliary_driver_register(). The id_table contains the match_names of auxiliary -devices that a driver can bind with. - -.. code-block:: c - - static const struct auxiliary_device_id my_auxiliary_id_table[] = { - { .name = "foo_mod.foo_dev" }, - {}, - }; - - MODULE_DEVICE_TABLE(auxiliary, my_auxiliary_id_table); - - struct auxiliary_driver my_drv = { - .name = "myauxiliarydrv", - .id_table = my_auxiliary_id_table, - .probe = my_drv_probe, - .remove = my_drv_remove - }; +.. kernel-doc:: include/linux/auxiliary_bus.h + :identifiers: auxiliary_driver module_auxiliary_driver +.. kernel-doc:: drivers/base/auxiliary.c + :identifiers: __auxiliary_driver_register auxiliary_driver_unregister Example Usage ============= -Auxiliary devices are created and registered by a subsystem-level core device -that needs to break up its functionality into smaller fragments. One way to -extend the scope of an auxiliary_device is to encapsulate it within a domain- -pecific structure defined by the parent device. This structure contains the -auxiliary_device and any associated shared data/callbacks needed to establish -the connection with the parent. - -An example is: - -.. code-block:: c - - struct foo { - struct auxiliary_device auxdev; - void (*connect)(struct auxiliary_device *auxdev); - void (*disconnect)(struct auxiliary_device *auxdev); - void *data; - }; - -The parent device then registers the auxiliary_device by calling -auxiliary_device_init(), and then auxiliary_device_add(), with the pointer to -the auxdev member of the above structure. The parent provides a name for the -auxiliary_device that, combined with the parent's KBUILD_MODNAME, creates a -match_name that is be used for matching and binding with a driver. - -Whenever an auxiliary_driver is registered, based on the match_name, the -auxiliary_driver's probe() is invoked for the matching devices. The -auxiliary_driver can also be encapsulated inside custom drivers that make the -core device's functionality extensible by adding additional domain-specific ops -as follows: - -.. code-block:: c - - struct my_ops { - void (*send)(struct auxiliary_device *auxdev); - void (*receive)(struct auxiliary_device *auxdev); - }; - - - struct my_driver { - struct auxiliary_driver auxiliary_drv; - const struct my_ops ops; - }; - -An example of this type of usage is: - -.. code-block:: c - - const struct auxiliary_device_id my_auxiliary_id_table[] = { - { .name = "foo_mod.foo_dev" }, - { }, - }; - - const struct my_ops my_custom_ops = { - .send = my_tx, - .receive = my_rx, - }; +.. kernel-doc:: drivers/base/auxiliary.c + :doc: EXAMPLE - const struct my_driver my_drv = { - .auxiliary_drv = { - .name = "myauxiliarydrv", - .id_table = my_auxiliary_id_table, - .probe = my_probe, - .remove = my_remove, - .shutdown = my_shutdown, - }, - .ops = my_custom_ops, - }; diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c index ab5315681a42..8c5e65930617 100644 --- a/drivers/base/auxiliary.c +++ b/drivers/base/auxiliary.c @@ -17,6 +17,147 @@ #include #include "base.h" +/** + * DOC: PURPOSE + * + * In some subsystems, the functionality of the core device (PCI/ACPI/other) is + * too complex for a single device to be managed by a monolithic driver (e.g. + * Sound Open Firmware), multiple devices might implement a common intersection + * of functionality (e.g. NICs + RDMA), or a driver may want to export an + * interface for another subsystem to drive (e.g. SIOV Physical Function export + * Virtual Function management). A split of the functionality into child- + * devices representing sub-domains of functionality makes it possible to + * compartmentalize, layer, and distribute domain-specific concerns via a Linux + * device-driver model. + * + * An example for this kind of requirement is the audio subsystem where a + * single IP is handling multiple entities such as HDMI, Soundwire, local + * devices such as mics/speakers etc. The split for the core's functionality + * can be arbitrary or be defined by the DSP firmware topology and include + * hooks for test/debug. This allows for the audio core device to be minimal + * and focused on hardware-specific control and communication. + * + * Each auxiliary_device represents a part of its parent functionality. The + * generic behavior can be extended and specialized as needed by encapsulating + * an auxiliary_device within other domain-specific structures and the use of + * .ops callbacks. Devices on the auxiliary bus do not share any structures and + * the use of a communication channel with the parent is domain-specific. + * + * Note that ops are intended as a way to augment instance behavior within a + * class of auxiliary devices, it is not the mechanism for exporting common + * infrastructure from the parent. Consider EXPORT_SYMBOL_NS() to convey + * infrastructure from the parent module to the auxiliary module(s). + */ + +/** + * DOC: USAGE + * + * The auxiliary bus is to be used when a driver and one or more kernel + * modules, who share a common header file with the driver, need a mechanism to + * connect and provide access to a shared object allocated by the + * auxiliary_device's registering driver. The registering driver for the + * auxiliary_device(s) and the kernel module(s) registering auxiliary_drivers + * can be from the same subsystem, or from multiple subsystems. + * + * The emphasis here is on a common generic interface that keeps subsystem + * customization out of the bus infrastructure. + * + * One example is a PCI network device that is RDMA-capable and exports a child + * device to be driven by an auxiliary_driver in the RDMA subsystem. The PCI + * driver allocates and registers an auxiliary_device for each physical + * function on the NIC. The RDMA driver registers an auxiliary_driver that + * claims each of these auxiliary_devices. This conveys data/ops published by + * the parent PCI device/driver to the RDMA auxiliary_driver. + * + * Another use case is for the PCI device to be split out into multiple sub + * functions. For each sub function an auxiliary_device is created. A PCI sub + * function driver binds to such devices that creates its own one or more class + * devices. A PCI sub function auxiliary device is likely to be contained in a + * struct with additional attributes such as user defined sub function number + * and optional attributes such as resources and a link to the parent device. + * These attributes could be used by systemd/udev; and hence should be + * initialized before a driver binds to an auxiliary_device. + * + * A key requirement for utilizing the auxiliary bus is that there is no + * dependency on a physical bus, device, register accesses or regmap support. + * These individual devices split from the core cannot live on the platform bus + * as they are not physical devices that are controlled by DT/ACPI. The same + * argument applies for not using MFD in this scenario as MFD relies on + * individual function devices being physical devices. + */ + +/** + * DOC: EXAMPLE + * + * Auxiliary devices are created and registered by a subsystem-level core + * device that needs to break up its functionality into smaller fragments. One + * way to extend the scope of an auxiliary_device is to encapsulate it within a + * domain- pecific structure defined by the parent device. This structure + * contains the auxiliary_device and any associated shared data/callbacks + * needed to establish the connection with the parent. + * + * An example is: + * + * .. code-block:: c + * + * struct foo { + * struct auxiliary_device auxdev; + * void (*connect)(struct auxiliary_device *auxdev); + * void (*disconnect)(struct auxiliary_device *auxdev); + * void *data; + * }; + * + * The parent device then registers the auxiliary_device by calling + * auxiliary_device_init(), and then auxiliary_device_add(), with the pointer + * to the auxdev member of the above structure. The parent provides a name for + * the auxiliary_device that, combined with the parent's KBUILD_MODNAME, + * creates a match_name that is be used for matching and binding with a driver. + * + * Whenever an auxiliary_driver is registered, based on the match_name, the + * auxiliary_driver's probe() is invoked for the matching devices. The + * auxiliary_driver can also be encapsulated inside custom drivers that make + * the core device's functionality extensible by adding additional + * domain-specific ops as follows: + * + * .. code-block:: c + * + * struct my_ops { + * void (*send)(struct auxiliary_device *auxdev); + * void (*receive)(struct auxiliary_device *auxdev); + * }; + * + * + * struct my_driver { + * struct auxiliary_driver auxiliary_drv; + * const struct my_ops ops; + * }; + * + * An example of this type of usage is: + * + * .. code-block:: c + * + * const struct auxiliary_device_id my_auxiliary_id_table[] = { + * { .name = "foo_mod.foo_dev" }, + * { }, + * }; + * + * const struct my_ops my_custom_ops = { + * .send = my_tx, + * .receive = my_rx, + * }; + * + * const struct my_driver my_drv = { + * .auxiliary_drv = { + * .name = "myauxiliarydrv", + * .id_table = my_auxiliary_id_table, + * .probe = my_probe, + * .remove = my_remove, + * .shutdown = my_shutdown, + * }, + * .ops = my_custom_ops, + * }; + */ + static const struct auxiliary_device_id *auxiliary_match_id(const struct auxiliary_device_id *id, const struct auxiliary_device *auxdev) { diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index 605b27aab693..e6d8b5c16226 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -11,12 +11,172 @@ #include #include +/** + * DOC: DEVICE_LIFESPAN + * + * The registering driver is the entity that allocates memory for the + * auxiliary_device and registers it on the auxiliary bus. It is important to + * note that, as opposed to the platform bus, the registering driver is wholly + * responsible for the management of the memory used for the device object. + * + * To be clear the memory for the auxiliary_device is freed in the release() + * callback defined by the registering driver. The registering driver should + * only call auxiliary_device_delete() and then auxiliary_device_uninit() when + * it is done with the device. The release() function is then automatically + * called if and when other code releases their reference to the devices. + * + * A parent object, defined in the shared header file, contains the + * auxiliary_device. It also contains a pointer to the shared object(s), which + * also is defined in the shared header. Both the parent object and the shared + * object(s) are allocated by the registering driver. This layout allows the + * auxiliary_driver's registering module to perform a container_of() call to go + * from the pointer to the auxiliary_device, that is passed during the call to + * the auxiliary_driver's probe function, up to the parent object, and then + * have access to the shared object(s). + * + * The memory for the shared object(s) must have a lifespan equal to, or + * greater than, the lifespan of the memory for the auxiliary_device. The + * auxiliary_driver should only consider that the shared object is valid as + * long as the auxiliary_device is still registered on the auxiliary bus. It + * is up to the registering driver to manage (e.g. free or keep available) the + * memory for the shared object beyond the life of the auxiliary_device. + * + * The registering driver must unregister all auxiliary devices before its own + * driver.remove() is completed. An easy way to ensure this is to use the + * devm_add_action_or_reset() call to register a function against the parent + * device which unregisters the auxiliary device object(s). + * + * Finally, any operations which operate on the auxiliary devices must continue + * to function (if only to return an error) after the registering driver + * unregisters the auxiliary device. + */ + +/** + * struct auxiliary_device - auxiliary device object. + * @dev: Device, + * The release and parent fields of the device structure must be filled + * in + * @name: Match name found by the auxiliary device driver, + * @id: unique identitier if multiple devices of the same name are exported, + * + * An auxiliary_device represents a part of its parent device's functionality. + * It is given a name that, combined with the registering drivers + * KBUILD_MODNAME, creates a match_name that is used for driver binding, and an + * id that combined with the match_name provide a unique name to register with + * the bus subsystem. For example, a driver registering an auxiliary device is + * named 'foo_mod.ko' and the subdevice is named 'foo_dev'. The match name is + * therefore 'foo_mod.foo_dev'. + * + * Registering an auxiliary_device is a three-step process. + * + * First, a 'struct auxiliary_device' needs to be defined or allocated for each + * sub-device desired. The name, id, dev.release, and dev.parent fields of + * this structure must be filled in as follows. + * + * The 'name' field is to be given a name that is recognized by the auxiliary + * driver. If two auxiliary_devices with the same match_name, eg + * "foo_mod.foo_dev", are registered onto the bus, they must have unique id + * values (e.g. "x" and "y") so that the registered devices names are + * "foo_mod.foo_dev.x" and "foo_mod.foo_dev.y". If match_name + id are not + * unique, then the device_add fails and generates an error message. + * + * The auxiliary_device.dev.type.release or auxiliary_device.dev.release must + * be populated with a non-NULL pointer to successfully register the + * auxiliary_device. This release call is where resources associated with the + * auxiliary device must be free'ed. Because once the device is placed on the + * bus the parent driver can not tell what other code may have a reference to + * this data. + * + * The auxiliary_device.dev.parent should be set. Typically to the registering + * drivers device. + * + * Second, call auxiliary_device_init(), which checks several aspects of the + * auxiliary_device struct and performs a device_initialize(). After this step + * completes, any error state must have a call to auxiliary_device_uninit() in + * its resolution path. + * + * The third and final step in registering an auxiliary_device is to perform a + * call to auxiliary_device_add(), which sets the name of the device and adds + * the device to the bus. + * + * .. code-block:: c + * + * #define MY_DEVICE_NAME "foo_dev" + * + * ... + * + * struct auxiliary_device *my_aux_dev = my_aux_dev_alloc(xxx); + * + * // Step 1: + * my_aux_dev->name = MY_DEVICE_NAME; + * my_aux_dev->id = my_unique_id_alloc(xxx); + * my_aux_dev->dev.release = my_aux_dev_release; + * my_aux_dev->dev.parent = my_dev; + * + * // Step 2: + * if (auxiliary_device_init(my_aux_dev)) + * goto fail; + * + * // Step 3: + * if (auxiliary_device_add(my_aux_dev)) { + * auxiliary_device_uninit(my_aux_dev); + * goto fail; + * } + * + * ... + * + * + * Unregistering an auxiliary_device is a two-step process to mirror the + * register process. First call auxiliary_device_delete(), then call + * auxiliary_device_uninit(). + * + * .. code-block:: c + * + * auxiliary_device_delete(my_dev->my_aux_dev); + * auxiliary_device_uninit(my_dev->my_aux_dev); + */ struct auxiliary_device { struct device dev; const char *name; u32 id; }; +/** + * struct auxiliary_driver - Definition of an auxiliary bus driver + * @probe: Called when a matching device is added to the bus. + * @remove: Called when device is removed from the bus. + * @shutdown: Called at shut-down time to quiesce the device. + * @suspend: Called to put the device to sleep mode. Usually to a power state. + * @resume: Called to bring a device from sleep mode. + * @name: Driver name. + * @driver: Core driver structure. + * @id_table: Table of devices this driver should match on the bus. + * + * Auxiliary drivers follow the standard driver model convention, where + * discovery/enumeration is handled by the core, and drivers provide probe() + * and remove() methods. They support power management and shutdown + * notifications using the standard conventions. + * + * Auxiliary drivers register themselves with the bus by calling + * auxiliary_driver_register(). The id_table contains the match_names of + * auxiliary devices that a driver can bind with. + * + * .. code-block:: c + * + * static const struct auxiliary_device_id my_auxiliary_id_table[] = { + * { .name = "foo_mod.foo_dev" }, + * {}, + * }; + * + * MODULE_DEVICE_TABLE(auxiliary, my_auxiliary_id_table); + * + * struct auxiliary_driver my_drv = { + * .name = "myauxiliarydrv", + * .id_table = my_auxiliary_id_table, + * .probe = my_drv_probe, + * .remove = my_drv_remove + * }; + */ struct auxiliary_driver { int (*probe)(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id); void (*remove)(struct auxiliary_device *auxdev); -- cgit v1.2.3 From bb49e9e730c2906a958eee273a7819f401543d6c Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:16:58 +0100 Subject: fs: add is_idmapped_mnt() helper Multiple places open-code the same check to determine whether a given mount is idmapped. Introduce a simple helper function that can be used instead. This allows us to get rid of the fragile open-coding. We will later change the check that is used to determine whether a given mount is idmapped. Introducing a helper allows us to do this in a single place instead of doing it for multiple places. Link: https://lore.kernel.org/r/20211123114227.3124056-2-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-2-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-2-brauner@kernel.org Cc: Seth Forshee Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- fs/cachefiles/bind.c | 2 +- fs/ecryptfs/main.c | 2 +- fs/namespace.c | 2 +- fs/nfsd/export.c | 2 +- fs/overlayfs/super.c | 2 +- fs/proc_namespace.c | 2 +- include/linux/fs.h | 14 ++++++++++++++ 7 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index d463d89f5db8..146291be6263 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -117,7 +117,7 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) root = path.dentry; ret = -EINVAL; - if (mnt_user_ns(path.mnt) != &init_user_ns) { + if (is_idmapped_mnt(path.mnt)) { pr_warn("File cache on idmapped mounts not supported"); goto error_unsupported; } diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index d66bbd2df191..2dd23a82e0de 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -537,7 +537,7 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags goto out_free; } - if (mnt_user_ns(path.mnt) != &init_user_ns) { + if (is_idmapped_mnt(path.mnt)) { rc = -EINVAL; printk(KERN_ERR "Mounting on idmapped mounts currently disallowed\n"); goto out_free; diff --git a/fs/namespace.c b/fs/namespace.c index 659a8f39c61a..4994b816a74c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -3936,7 +3936,7 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) * mapping. It makes things simpler and callers can just create * another bind-mount they can idmap if they want to. */ - if (mnt_user_ns(m) != &init_user_ns) + if (is_idmapped_mnt(m)) return -EPERM; /* The underlying filesystem doesn't support idmapped mounts yet. */ diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 9421dae22737..668c7527b17e 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -427,7 +427,7 @@ static int check_export(struct path *path, int *flags, unsigned char *uuid) return -EINVAL; } - if (mnt_user_ns(path->mnt) != &init_user_ns) { + if (is_idmapped_mnt(path->mnt)) { dprintk("exp_export: export of idmapped mounts not yet supported.\n"); return -EINVAL; } diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 265181c110ae..7bb0a47cb615 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -873,7 +873,7 @@ static int ovl_mount_dir_noesc(const char *name, struct path *path) pr_err("filesystem on '%s' not supported\n", name); goto out_put; } - if (mnt_user_ns(path->mnt) != &init_user_ns) { + if (is_idmapped_mnt(path->mnt)) { pr_err("idmapped layers are currently not supported\n"); goto out_put; } diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c index 392ef5162655..49650e54d2f8 100644 --- a/fs/proc_namespace.c +++ b/fs/proc_namespace.c @@ -80,7 +80,7 @@ static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt) seq_puts(m, fs_infop->str); } - if (mnt_user_ns(mnt) != &init_user_ns) + if (is_idmapped_mnt(mnt)) seq_puts(m, ",idmapped"); } diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..06cbefd76de7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2724,6 +2724,20 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) { return mnt_user_ns(file->f_path.mnt); } + +/** + * is_idmapped_mnt - check whether a mount is mapped + * @mnt: the mount to check + * + * If @mnt has an idmapping attached to it @mnt is mapped. + * + * Return: true if mount is mapped, false if not. + */ +static inline bool is_idmapped_mnt(const struct vfsmount *mnt) +{ + return mnt_user_ns(mnt) != &init_user_ns; +} + extern long vfs_truncate(const struct path *, loff_t); int do_truncate(struct user_namespace *, struct dentry *, loff_t start, unsigned int time_attrs, struct file *filp); -- cgit v1.2.3 From a793d79ea3e041081cd7cbd8ee43d0b5e4914a2b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:16:59 +0100 Subject: fs: move mapping helpers The low-level mapping helpers were so far crammed into fs.h. They are out of place there. The fs.h header should just contain the higher-level mapping helpers that interact directly with vfs objects such as struct super_block or struct inode and not the bare mapping helpers. Similarly, only vfs and specific fs code shall interact with low-level mapping helpers. And so they won't be made accessible automatically through regular {g,u}id helpers. Link: https://lore.kernel.org/r/20211123114227.3124056-3-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-3-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-3-brauner@kernel.org Cc: Seth Forshee Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- fs/ksmbd/smbacl.c | 1 + fs/ksmbd/smbacl.h | 1 + fs/open.c | 1 + fs/posix_acl.c | 1 + fs/xfs/xfs_linux.h | 1 + include/linux/fs.h | 91 +------------------------------------ include/linux/mnt_idmapping.h | 101 ++++++++++++++++++++++++++++++++++++++++++ security/commoncap.c | 1 + 8 files changed, 108 insertions(+), 90 deletions(-) create mode 100644 include/linux/mnt_idmapping.h (limited to 'include/linux') diff --git a/fs/ksmbd/smbacl.c b/fs/ksmbd/smbacl.c index bd792db32623..ab8099e0fd7f 100644 --- a/fs/ksmbd/smbacl.c +++ b/fs/ksmbd/smbacl.c @@ -9,6 +9,7 @@ #include #include #include +#include #include "smbacl.h" #include "smb_common.h" diff --git a/fs/ksmbd/smbacl.h b/fs/ksmbd/smbacl.h index 73e08cad412b..eba1ebb9e92e 100644 --- a/fs/ksmbd/smbacl.h +++ b/fs/ksmbd/smbacl.h @@ -11,6 +11,7 @@ #include #include #include +#include #include "mgmt/tree_connect.h" diff --git a/fs/open.c b/fs/open.c index f732fb94600c..2450cc1a2f64 100644 --- a/fs/open.c +++ b/fs/open.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "internal.h" diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 9323a854a60a..632bfdcf7cc0 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -23,6 +23,7 @@ #include #include #include +#include static struct posix_acl **acl_by_type(struct inode *inode, int type) { diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h index c174262a074e..09a8fba84ff9 100644 --- a/fs/xfs/xfs_linux.h +++ b/fs/xfs/xfs_linux.h @@ -61,6 +61,7 @@ typedef __u32 xfs_nlink_t; #include #include #include +#include #include #include diff --git a/include/linux/fs.h b/include/linux/fs.h index 06cbefd76de7..b3bcb2129699 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -1624,34 +1625,6 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } -/** - * kuid_into_mnt - map a kuid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return make_kuid(mnt_userns, __kuid_val(kuid)); -} - -/** - * kgid_into_mnt - map a kgid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return make_kgid(mnt_userns, __kgid_val(kgid)); -} - /** * i_uid_into_mnt - map an inode's i_uid down into a mnt_userns * @mnt_userns: user namespace of the mount the inode was found from @@ -1680,68 +1653,6 @@ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, return kgid_into_mnt(mnt_userns, inode->i_gid); } -/** - * kuid_from_mnt - map a kuid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped up according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return KUIDT_INIT(from_kuid(mnt_userns, kuid)); -} - -/** - * kgid_from_mnt - map a kgid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped up according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return KGIDT_INIT(from_kgid(mnt_userns, kgid)); -} - -/** - * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsuid. A common example is initializing the i_uid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsuid mapped up according to @mnt_userns. - */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) -{ - return kuid_from_mnt(mnt_userns, current_fsuid()); -} - -/** - * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * - * Use this helper to initialize a new vfs or filesystem object based on - * the caller's fsgid. A common example is initializing the i_gid field of - * a newly allocated inode triggered by a creation event such as mkdir or - * O_CREAT. Other examples include the allocation of quotas for a specific - * user. - * - * Return: the caller's current fsgid mapped up according to @mnt_userns. - */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) -{ - return kgid_from_mnt(mnt_userns, current_fsgid()); -} - /** * inode_fsuid_set - initialize inode's i_uid field with callers fsuid * @inode: inode to initialize diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h new file mode 100644 index 000000000000..47c7811fadfe --- /dev/null +++ b/include/linux/mnt_idmapping.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_MNT_IDMAPPING_H +#define _LINUX_MNT_IDMAPPING_H + +#include +#include + +struct user_namespace; +extern struct user_namespace init_user_ns; + +/** + * kuid_into_mnt - map a kuid down into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kuid: kuid to be mapped + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping INVALID_UID is returned. + */ +static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return make_kuid(mnt_userns, __kuid_val(kuid)); +} + +/** + * kgid_into_mnt - map a kgid down into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kgid: kgid to be mapped + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping INVALID_GID is returned. + */ +static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return make_kgid(mnt_userns, __kgid_val(kgid)); +} + +/** + * kuid_from_mnt - map a kuid up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kuid: kuid to be mapped + * + * Return: @kuid mapped up according to @mnt_userns. + * If @kuid has no mapping INVALID_UID is returned. + */ +static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, + kuid_t kuid) +{ + return KUIDT_INIT(from_kuid(mnt_userns, kuid)); +} + +/** + * kgid_from_mnt - map a kgid up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * @kgid: kgid to be mapped + * + * Return: @kgid mapped up according to @mnt_userns. + * If @kgid has no mapping INVALID_GID is returned. + */ +static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, + kgid_t kgid) +{ + return KGIDT_INIT(from_kgid(mnt_userns, kgid)); +} + +/** + * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsuid. A common example is initializing the i_uid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsuid mapped up according to @mnt_userns. + */ +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) +{ + return kuid_from_mnt(mnt_userns, current_fsuid()); +} + +/** + * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns + * @mnt_userns: user namespace of the relevant mount + * + * Use this helper to initialize a new vfs or filesystem object based on + * the caller's fsgid. A common example is initializing the i_gid field of + * a newly allocated inode triggered by a creation event such as mkdir or + * O_CREAT. Other examples include the allocation of quotas for a specific + * user. + * + * Return: the caller's current fsgid mapped up according to @mnt_userns. + */ +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) +{ + return kgid_from_mnt(mnt_userns, current_fsgid()); +} + +#endif /* _LINUX_MNT_IDMAPPING_H */ diff --git a/security/commoncap.c b/security/commoncap.c index 3f810d37b71b..09479f71ee2e 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -24,6 +24,7 @@ #include #include #include +#include /* * If a non-root user executes a setuid-root binary in -- cgit v1.2.3 From 476860b3eb4a50958243158861d5340066df5af2 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:17:00 +0100 Subject: fs: tweak fsuidgid_has_mapping() If the caller's fs{g,u}id aren't mapped in the mount's idmapping we can return early and skip the check whether the mapped fs{g,u}id also have a mapping in the filesystem's idmapping. If the fs{g,u}id aren't mapped in the mount's idmapping they consequently can't be mapped in the filesystem's idmapping. So there's no point in checking that. Link: https://lore.kernel.org/r/20211123114227.3124056-4-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-4-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-4-brauner@kernel.org Cc: Seth Forshee Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- include/linux/fs.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b3bcb2129699..db5ee15e36b1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1695,10 +1695,18 @@ static inline void inode_fsgid_set(struct inode *inode, static inline bool fsuidgid_has_mapping(struct super_block *sb, struct user_namespace *mnt_userns) { - struct user_namespace *s_user_ns = sb->s_user_ns; + struct user_namespace *fs_userns = sb->s_user_ns; + kuid_t kuid; + kgid_t kgid; - return kuid_has_mapping(s_user_ns, mapped_fsuid(mnt_userns)) && - kgid_has_mapping(s_user_ns, mapped_fsgid(mnt_userns)); + kuid = mapped_fsuid(mnt_userns); + if (!uid_valid(kuid)) + return false; + kgid = mapped_fsgid(mnt_userns); + if (!gid_valid(kgid)) + return false; + return kuid_has_mapping(fs_userns, kuid) && + kgid_has_mapping(fs_userns, kgid); } extern struct timespec64 current_time(struct inode *inode); -- cgit v1.2.3 From 1ac2a4104968e0a60b4b3572216a92aab5c1b025 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:17:01 +0100 Subject: fs: account for filesystem mappings Currently we only support idmapped mounts for filesystems mounted without an idmapping. This was a conscious decision mentioned in multiple places (cf. e.g. [1]). As explained at length in [3] it is perfectly fine to extend support for idmapped mounts to filesystem's mounted with an idmapping should the need arise. The need has been there for some time now. Various container projects in userspace need this to run unprivileged and nested unprivileged containers (cf. [2]). Before we can port any filesystem that is mountable with an idmapping to support idmapped mounts we need to first extend the mapping helpers to account for the filesystem's idmapping. This again, is explained at length in our documentation at [3] but I'll give an overview here again. Currently, the low-level mapping helpers implement the remapping algorithms described in [3] in a simplified manner. Because we could rely on the fact that all filesystems supporting idmapped mounts are mounted without an idmapping the translation step from or into the filesystem idmapping could be skipped. In order to support idmapped mounts of filesystem's mountable with an idmapping the translation step we were able to skip before cannot be skipped anymore. A filesystem mounted with an idmapping is very likely to not use an identity mapping and will instead use a non-identity mapping. So the translation step from or into the filesystem's idmapping in the remapping algorithm cannot be skipped for such filesystems. More details with examples can be found in [3]. This patch adds a few new and prepares some already existing low-level mapping helpers to perform the full translation algorithm explained in [3]. The low-level helpers can be written in a way that they only perform the additional translation step when the filesystem is indeed mounted with an idmapping. If the low-level helpers detect that they are not dealing with an idmapped mount they can simply return the relevant k{g,u}id unchanged; no remapping needs to be performed at all. The no_idmapping() helper detects whether the shortcut can be used. If the low-level helpers detected that they are dealing with an idmapped mount but the underlying filesystem is mounted without an idmapping we can rely on the previous shorcut and can continue to skip the translation step from or into the filesystem's idmapping. These checks guarantee that only the minimal amount of work is performed. As before, if idmapped mounts aren't used the low-level helpers are idempotent and no work is performed at all. This patch adds the helpers mapped_k{g,u}id_fs() and mapped_k{g,u}id_user(). Following patches will port all places to replace the old k{g,u}id_into_mnt() and k{g,u}id_from_mnt() with these two new helpers. After the conversion is done k{g,u}id_into_mnt() and k{g,u}id_from_mnt() will be removed. This also concludes the renaming of the mapping helpers we started in [4]. Now, all mapping helpers will started with the "mapped_" prefix making everything nice and consistent. The mapped_k{g,u}id_fs() helpers replace the k{g,u}id_into_mnt() helpers. They are to be used when k{g,u}ids are to be mapped from the vfs, e.g. from from struct inode's i_{g,u}id. Conversely, the mapped_k{g,u}id_user() helpers replace the k{g,u}id_from_mnt() helpers. They are to be used when k{g,u}ids are to be written to disk, e.g. when entering from a system call to change ownership of a file. This patch only introduces the helpers. It doesn't yet convert the relevant places to account for filesystem mounted with an idmapping. [1]: commit 2ca4dcc4909d ("fs/mount_setattr: tighten permission checks") [2]: https://github.com/containers/podman/issues/10374 [3]: Documentations/filesystems/idmappings.rst [4]: commit a65e58e791a1 ("fs: document and rename fsid helpers") Link: https://lore.kernel.org/r/20211123114227.3124056-5-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-5-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-5-brauner@kernel.org Cc: Seth Forshee Cc: Amir Goldstein Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- include/linux/fs.h | 4 +- include/linux/mnt_idmapping.h | 193 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 191 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index db5ee15e36b1..57aee6ebba72 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1636,7 +1636,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kuid_into_mnt(mnt_userns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, &init_user_ns, inode->i_uid); } /** @@ -1650,7 +1650,7 @@ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return kgid_into_mnt(mnt_userns, inode->i_gid); + return mapped_kgid_fs(mnt_userns, &init_user_ns, inode->i_gid); } /** diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 47c7811fadfe..60341cd33ccc 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -6,6 +6,11 @@ #include struct user_namespace; +/* + * Carries the initial idmapping of 0:0:4294967295 which is an identity + * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is + * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. + */ extern struct user_namespace init_user_ns; /** @@ -64,9 +69,189 @@ static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, return KGIDT_INIT(from_kgid(mnt_userns, kgid)); } +/** + * initial_idmapping - check whether this is the initial mapping + * @ns: idmapping to check + * + * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, + * [...], 1000 to 1000 [...]. + * + * Return: true if this is the initial mapping, false if not. + */ +static inline bool initial_idmapping(const struct user_namespace *ns) +{ + return ns == &init_user_ns; +} + +/** + * no_idmapping - check whether we can skip remapping a kuid/gid + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * + * This function can be used to check whether a remapping between two + * idmappings is required. + * An idmapped mount is a mount that has an idmapping attached to it that + * is different from the filsystem's idmapping and the initial idmapping. + * If the initial mapping is used or the idmapping of the mount and the + * filesystem are identical no remapping is required. + * + * Return: true if remapping can be skipped, false if not. + */ +static inline bool no_idmapping(const struct user_namespace *mnt_userns, + const struct user_namespace *fs_userns) +{ + return initial_idmapping(mnt_userns) || mnt_userns == fs_userns; +} + +/** + * mapped_kuid_fs - map a filesystem kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Take a @kuid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kuid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * from_kuid() so we can simply retrieve the value via __kuid_val() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + if (initial_idmapping(fs_userns)) + uid = __kuid_val(kuid); + else + uid = from_kuid(fs_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + return make_kuid(mnt_userns, uid); +} + +/** + * mapped_kgid_fs - map a filesystem kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Take a @kgid and remap it from @fs_userns into @mnt_userns. Use this + * function when preparing a @kgid to be reported to userspace. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * from_kgid() so we can simply retrieve the value via __kgid_val() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_fs(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + if (initial_idmapping(fs_userns)) + gid = __kgid_val(kgid); + else + gid = from_kgid(fs_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + return make_kgid(mnt_userns, gid); +} + +/** + * mapped_kuid_user - map a user kuid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kuid : kuid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kuid into @fs_userns. Use this + * function when preparing a @kuid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kuid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kuid won't change when calling + * make_kuid() so we can simply retrieve the value via KUIDT_INIT() + * directly. + * + * Return: @kuid mapped according to @mnt_userns. + * If @kuid has no mapping in either @mnt_userns or @fs_userns INVALID_UID is + * returned. + */ +static inline kuid_t mapped_kuid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kuid_t kuid) +{ + uid_t uid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kuid; + uid = from_kuid(mnt_userns, kuid); + if (uid == (uid_t)-1) + return INVALID_UID; + if (initial_idmapping(fs_userns)) + return KUIDT_INIT(uid); + return make_kuid(fs_userns, uid); +} + +/** + * mapped_kgid_user - map a user kgid into a mnt_userns + * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping + * @kgid : kgid to be mapped + * + * Use the idmapping of @mnt_userns to remap a @kgid into @fs_userns. Use this + * function when preparing a @kgid to be written to disk or inode. + * + * If no_idmapping() determines that this is not an idmapped mount we can + * simply return @kgid unchanged. + * If initial_idmapping() tells us that the filesystem is not mounted with an + * idmapping we know the value of @kgid won't change when calling + * make_kgid() so we can simply retrieve the value via KGIDT_INIT() + * directly. + * + * Return: @kgid mapped according to @mnt_userns. + * If @kgid has no mapping in either @mnt_userns or @fs_userns INVALID_GID is + * returned. + */ +static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns, + kgid_t kgid) +{ + gid_t gid; + + if (no_idmapping(mnt_userns, fs_userns)) + return kgid; + gid = from_kgid(mnt_userns, kgid); + if (gid == (gid_t)-1) + return INVALID_GID; + if (initial_idmapping(fs_userns)) + return KGIDT_INIT(gid); + return make_kgid(fs_userns, gid); +} + /** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount + * @mnt_userns: the mount's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of @@ -78,12 +263,12 @@ static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, */ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) { - return kuid_from_mnt(mnt_userns, current_fsuid()); + return mapped_kuid_user(mnt_userns, &init_user_ns, current_fsuid()); } /** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount + * @mnt_userns: the mount's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of @@ -95,7 +280,7 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) */ static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) { - return kgid_from_mnt(mnt_userns, current_fsgid()); + return mapped_kgid_user(mnt_userns, &init_user_ns, current_fsgid()); } #endif /* _LINUX_MNT_IDMAPPING_H */ -- cgit v1.2.3 From 8581fd402a0cf80b5298e3b225e7a7bd8f110e69 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 2 Dec 2021 12:34:00 -0800 Subject: treewide: Add missing includes masked by cgroup -> bpf dependency MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit cgroup.h (therefore swap.h, therefore half of the universe) includes bpf.h which in turn includes module.h and slab.h. Since we're about to get rid of that dependency we need to clean things up. v2: drop the cpu.h include from cacheinfo.h, it's not necessary and it makes riscv sensitive to ordering of include files. Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Reviewed-by: Christoph Hellwig Acked-by: Krzysztof Wilczyński Acked-by: Peter Chen Acked-by: SeongJae Park Acked-by: Jani Nikula Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/all/20211120035253.72074-1-kuba@kernel.org/ # v1 Link: https://lore.kernel.org/all/20211120165528.197359-1-kuba@kernel.org/ # cacheinfo discussion Link: https://lore.kernel.org/bpf/20211202203400.1208663-1-kuba@kernel.org --- block/fops.c | 1 + drivers/gpu/drm/drm_gem_shmem_helper.c | 1 + drivers/gpu/drm/i915/gt/intel_gtt.c | 1 + drivers/gpu/drm/i915/i915_request.c | 1 + drivers/gpu/drm/lima/lima_device.c | 1 + drivers/gpu/drm/msm/msm_gem_shrinker.c | 1 + drivers/gpu/drm/ttm/ttm_tt.c | 1 + drivers/net/ethernet/huawei/hinic/hinic_sriov.c | 1 + drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c | 2 ++ drivers/pci/controller/dwc/pci-exynos.c | 1 + drivers/pci/controller/dwc/pcie-qcom-ep.c | 1 + drivers/usb/cdns3/host.c | 1 + include/linux/cacheinfo.h | 1 - include/linux/device/driver.h | 1 + include/linux/filter.h | 2 +- mm/damon/vaddr.c | 1 + mm/memory_hotplug.c | 1 + mm/swap_slots.c | 1 + 18 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/fops.c b/block/fops.c index ad732a36f9b3..3cb1e81929bc 100644 --- a/block/fops.c +++ b/block/fops.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "blk.h" static inline struct inode *bdev_file_inode(struct file *file) diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index 7b9f69f21f1e..bca0de92802e 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -9,6 +9,7 @@ #include #include #include +#include #ifdef CONFIG_X86 #include diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 67d14afa6623..b67f620c3d93 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -6,6 +6,7 @@ #include /* fault-inject.h is not standalone! */ #include +#include #include "gem/i915_gem_lmem.h" #include "i915_trace.h" diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 820a1f38b271..89cccefeea63 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -29,6 +29,7 @@ #include #include #include +#include #include "gem/i915_gem_context.h" #include "gt/intel_breadcrumbs.h" diff --git a/drivers/gpu/drm/lima/lima_device.c b/drivers/gpu/drm/lima/lima_device.c index 65fdca366e41..f74f8048af8f 100644 --- a/drivers/gpu/drm/lima/lima_device.c +++ b/drivers/gpu/drm/lima/lima_device.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 4a1420b05e97..086dacf2f26a 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -5,6 +5,7 @@ */ #include +#include #include "msm_drv.h" #include "msm_gem.h" diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c index 7e83c00a3f48..79c870a3bef8 100644 --- a/drivers/gpu/drm/ttm/ttm_tt.c +++ b/drivers/gpu/drm/ttm/ttm_tt.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index a78c398bf5b2..01e7d3c0b68e 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "hinic_hw_dev.h" #include "hinic_dev.h" diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c index 0ef68fdd1f26..61c20907315f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c @@ -5,6 +5,8 @@ * */ +#include + #include "otx2_common.h" #include "otx2_ptp.h" diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index c24dab383654..722dacdd5a17 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -19,6 +19,7 @@ #include #include #include +#include #include "pcie-designware.h" diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c index 7b17da2f9b3f..cfe66bf04c1d 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-ep.c +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -18,6 +18,7 @@ #include #include #include +#include #include "pcie-designware.h" diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c index 84dadfa726aa..9643b905e2d8 100644 --- a/drivers/usb/cdns3/host.c +++ b/drivers/usb/cdns3/host.c @@ -10,6 +10,7 @@ */ #include +#include #include "core.h" #include "drd.h" #include "host-export.h" diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h index 2f909ed084c6..4ff37cb763ae 100644 --- a/include/linux/cacheinfo.h +++ b/include/linux/cacheinfo.h @@ -3,7 +3,6 @@ #define _LINUX_CACHEINFO_H #include -#include #include #include diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h index a498ebcf4993..15e7c5e15d62 100644 --- a/include/linux/device/driver.h +++ b/include/linux/device/driver.h @@ -18,6 +18,7 @@ #include #include #include +#include /** * enum probe_type - device driver probe type to try diff --git a/include/linux/filter.h b/include/linux/filter.h index 534f678ca50f..7f1e88e3e2b5 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -6,6 +6,7 @@ #define __LINUX_FILTER_H__ #include +#include #include #include #include @@ -26,7 +27,6 @@ #include #include -#include struct sk_buff; struct sock; diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 35fe49080ee9..47f47f60440e 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "prmtv-common.h" diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 852041f6be41..2a9627dc784c 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -35,6 +35,7 @@ #include #include #include +#include #include diff --git a/mm/swap_slots.c b/mm/swap_slots.c index 16f706c55d92..2b5531840583 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 4bdcd1dd4d2f973b1a89fb20ba720d879e9e506b Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 28 Oct 2021 08:47:05 -0600 Subject: mm: move filemap_range_needs_writeback() into header No functional changes in this patch, just in preparation for efficiently calling this light function from the block O_DIRECT handling. Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Jens Axboe --- fs/iomap/direct-io.c | 1 + include/linux/fs.h | 2 -- include/linux/pagemap.h | 29 +++++++++++++++++++++++++++++ mm/filemap.c | 32 +++----------------------------- 4 files changed, 33 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index b4dc51063d36..03ea367df19a 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..6b8dc1a78df6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2847,8 +2847,6 @@ static inline int filemap_fdatawait(struct address_space *mapping) extern bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); -extern bool filemap_range_needs_writeback(struct address_space *, - loff_t lstart, loff_t lend); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); extern int __filemap_fdatawrite_range(struct address_space *mapping, diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 605246452305..274a0710f2c5 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -963,6 +963,35 @@ static inline int add_to_page_cache(struct page *page, int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); +bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte); + +/** + * filemap_range_needs_writeback - check if range potentially needs writeback + * @mapping: address space within which to check + * @start_byte: offset in bytes where the range starts + * @end_byte: offset in bytes where the range ends (inclusive) + * + * Find at least one page in the range supplied, usually used to check if + * direct writing in this range will trigger a writeback. Used by O_DIRECT + * read/write with IOCB_NOWAIT, to see if the caller needs to do + * filemap_write_and_wait_range() before proceeding. + * + * Return: %true if the caller should do filemap_write_and_wait_range() before + * doing O_DIRECT to a page in this range, %false otherwise. + */ +static inline bool filemap_range_needs_writeback(struct address_space *mapping, + loff_t start_byte, + loff_t end_byte) +{ + if (!mapping->nrpages) + return false; + if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && + !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + return false; + return filemap_range_has_writeback(mapping, start_byte, end_byte); +} + /** * struct readahead_control - Describes a readahead request. * diff --git a/mm/filemap.c b/mm/filemap.c index daa0e23a6ee6..655c9eec06b3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -646,8 +646,8 @@ static bool mapping_needs_writeback(struct address_space *mapping) return mapping->nrpages; } -static bool filemap_range_has_writeback(struct address_space *mapping, - loff_t start_byte, loff_t end_byte) +bool filemap_range_has_writeback(struct address_space *mapping, + loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; @@ -667,34 +667,8 @@ static bool filemap_range_has_writeback(struct address_space *mapping, } rcu_read_unlock(); return page != NULL; - -} - -/** - * filemap_range_needs_writeback - check if range potentially needs writeback - * @mapping: address space within which to check - * @start_byte: offset in bytes where the range starts - * @end_byte: offset in bytes where the range ends (inclusive) - * - * Find at least one page in the range supplied, usually used to check if - * direct writing in this range will trigger a writeback. Used by O_DIRECT - * read/write with IOCB_NOWAIT, to see if the caller needs to do - * filemap_write_and_wait_range() before proceeding. - * - * Return: %true if the caller should do filemap_write_and_wait_range() before - * doing O_DIRECT to a page in this range, %false otherwise. - */ -bool filemap_range_needs_writeback(struct address_space *mapping, - loff_t start_byte, loff_t end_byte) -{ - if (!mapping_needs_writeback(mapping)) - return false; - if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && - !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) - return false; - return filemap_range_has_writeback(mapping, start_byte, end_byte); } -EXPORT_SYMBOL_GPL(filemap_range_needs_writeback); +EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range -- cgit v1.2.3 From 0a467d0fdd9594fbb449ebc93852533332c528fd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 14 Oct 2021 14:39:59 -0600 Subject: block: switch to atomic_t for request references refcount_t is not as expensive as it used to be, but it's still more expensive than the io_uring method of using atomic_t and just checking for potential over/underflow. This borrows that same implementation, which in turn is based on the mm implementation from Linus. Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-flush.c | 4 ++-- block/blk-mq-tag.c | 2 +- block/blk-mq.c | 12 ++++++------ block/blk.h | 31 +++++++++++++++++++++++++++++++ include/linux/blk-mq.h | 2 +- 5 files changed, 41 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/block/blk-flush.c b/block/blk-flush.c index f78bb39e589e..e4df894189ce 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -229,7 +229,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); - if (!refcount_dec_and_test(&flush_rq->ref)) { + if (!req_ref_put_and_test(flush_rq)) { fq->rq_status = error; spin_unlock_irqrestore(&fq->mq_flush_lock, flags); return; @@ -349,7 +349,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, * and READ flush_rq->end_io */ smp_wmb(); - refcount_set(&flush_rq->ref, 1); + req_ref_set(flush_rq, 1); blk_flush_queue_rq(flush_rq, false); } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 995336abee33..380e2dd31bfc 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -228,7 +228,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, spin_lock_irqsave(&tags->lock, flags); rq = tags->rqs[bitnr]; - if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref)) + if (!rq || rq->tag != bitnr || !req_ref_inc_not_zero(rq)) rq = NULL; spin_unlock_irqrestore(&tags->lock, flags); return rq; diff --git a/block/blk-mq.c b/block/blk-mq.c index fc4520e992b1..8c7cab75229e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -394,7 +394,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, INIT_LIST_HEAD(&rq->queuelist); /* tag was already set */ WRITE_ONCE(rq->deadline, 0); - refcount_set(&rq->ref, 1); + req_ref_set(rq, 1); if (rq->rq_flags & RQF_ELV) { struct elevator_queue *e = data->q->elevator; @@ -642,7 +642,7 @@ void blk_mq_free_request(struct request *rq) rq_qos_done(q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); - if (refcount_dec_and_test(&rq->ref)) + if (req_ref_put_and_test(rq)) __blk_mq_free_request(rq); } EXPORT_SYMBOL_GPL(blk_mq_free_request); @@ -938,7 +938,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob) rq_qos_done(rq->q, rq); WRITE_ONCE(rq->state, MQ_RQ_IDLE); - if (!refcount_dec_and_test(&rq->ref)) + if (!req_ref_put_and_test(rq)) continue; blk_crypto_free_request(rq); @@ -1401,7 +1401,7 @@ void blk_mq_put_rq_ref(struct request *rq) { if (is_flush_rq(rq)) rq->end_io(rq, 0); - else if (refcount_dec_and_test(&rq->ref)) + else if (req_ref_put_and_test(rq)) __blk_mq_free_request(rq); } @@ -3049,7 +3049,7 @@ static void blk_mq_clear_rq_mapping(struct blk_mq_tags *drv_tags, unsigned long rq_addr = (unsigned long)rq; if (rq_addr >= start && rq_addr < end) { - WARN_ON_ONCE(refcount_read(&rq->ref) != 0); + WARN_ON_ONCE(req_ref_read(rq) != 0); cmpxchg(&drv_tags->rqs[i], rq, NULL); } } @@ -3383,7 +3383,7 @@ static void blk_mq_clear_flush_rq_mapping(struct blk_mq_tags *tags, if (!tags) return; - WARN_ON_ONCE(refcount_read(&flush_rq->ref) != 0); + WARN_ON_ONCE(req_ref_read(flush_rq) != 0); for (i = 0; i < queue_depth; i++) cmpxchg(&tags->rqs[i], flush_rq, NULL); diff --git a/block/blk.h b/block/blk.h index a55d82c3d1c2..24d8b333bb03 100644 --- a/block/blk.h +++ b/block/blk.h @@ -461,4 +461,35 @@ static inline bool should_fail_request(struct block_device *part, } #endif /* CONFIG_FAIL_MAKE_REQUEST */ +/* + * Optimized request reference counting. Ideally we'd make timeouts be more + * clever, as that's the only reason we need references at all... But until + * this happens, this is faster than using refcount_t. Also see: + * + * abc54d634334 ("io_uring: switch to atomic_t for io_kiocb reference count") + */ +#define req_ref_zero_or_close_to_overflow(req) \ + ((unsigned int) atomic_read(&(req->ref)) + 127u <= 127u) + +static inline bool req_ref_inc_not_zero(struct request *req) +{ + return atomic_inc_not_zero(&req->ref); +} + +static inline bool req_ref_put_and_test(struct request *req) +{ + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + return atomic_dec_and_test(&req->ref); +} + +static inline void req_ref_set(struct request *req, int value) +{ + atomic_set(&req->ref, value); +} + +static inline int req_ref_read(struct request *req) +{ + return atomic_read(&req->ref); +} + #endif /* BLK_INTERNAL_H */ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1b87b7c8bbff..561beb5be7ec 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -139,7 +139,7 @@ struct request { unsigned short ioprio; enum mq_rq_state state; - refcount_t ref; + atomic_t ref; unsigned long deadline; -- cgit v1.2.3 From 704b914f15fb7daaf517e3acc4bed472b50ca19e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 3 Dec 2021 21:15:32 +0800 Subject: blk-mq: move srcu from blk_mq_hw_ctx to request_queue In case of BLK_MQ_F_BLOCKING, per-hctx srcu is used to protect dispatch critical area. However, this srcu instance stays at the end of hctx, and it often takes standalone cacheline, often cold. Inside srcu_read_lock() and srcu_read_unlock(), WRITE is always done on the indirect percpu variable which is allocated from heap instead of being embedded, srcu->srcu_idx is read only in srcu_read_lock(). It doesn't matter if srcu structure stays in hctx or request queue. So switch to per-request-queue srcu for protecting dispatch, and this way simplifies quiesce a lot, not mention quiesce is always done on the request queue wide. Signed-off-by: Ming Lei Link: https://lore.kernel.org/r/20211203131534.3668411-3-ming.lei@redhat.com Signed-off-by: Jens Axboe --- block/blk-core.c | 27 ++++++++++++++++++++++----- block/blk-mq-sysfs.c | 2 -- block/blk-mq.c | 37 ++++++++----------------------------- block/blk-mq.h | 4 ++-- block/blk-sysfs.c | 3 ++- block/blk.h | 10 +++++++++- block/genhd.c | 2 +- include/linux/blk-mq.h | 8 -------- include/linux/blkdev.h | 9 +++++++++ 9 files changed, 53 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index b0660c9df852..10619fd83c1b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -66,6 +66,7 @@ DEFINE_IDA(blk_queue_ida); * For queue allocation */ struct kmem_cache *blk_requestq_cachep; +struct kmem_cache *blk_requestq_srcu_cachep; /* * Controlling structure to kblockd @@ -437,21 +438,27 @@ static void blk_timeout_work(struct work_struct *work) { } -struct request_queue *blk_alloc_queue(int node_id) +struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) { struct request_queue *q; int ret; - q = kmem_cache_alloc_node(blk_requestq_cachep, - GFP_KERNEL | __GFP_ZERO, node_id); + q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu), + GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return NULL; + if (alloc_srcu) { + blk_queue_flag_set(QUEUE_FLAG_HAS_SRCU, q); + if (init_srcu_struct(q->srcu) != 0) + goto fail_q; + } + q->last_merge = NULL; q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL); if (q->id < 0) - goto fail_q; + goto fail_srcu; ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0); if (ret) @@ -508,8 +515,11 @@ fail_split: bioset_exit(&q->bio_split); fail_id: ida_simple_remove(&blk_queue_ida, q->id); +fail_srcu: + if (alloc_srcu) + cleanup_srcu_struct(q->srcu); fail_q: - kmem_cache_free(blk_requestq_cachep, q); + kmem_cache_free(blk_get_queue_kmem_cache(alloc_srcu), q); return NULL; } @@ -1301,6 +1311,9 @@ int __init blk_dev_init(void) sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); + BUILD_BUG_ON(ALIGN(offsetof(struct request_queue, srcu), + __alignof__(struct request_queue)) != + sizeof(struct request_queue)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", @@ -1311,6 +1324,10 @@ int __init blk_dev_init(void) blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); + blk_requestq_srcu_cachep = kmem_cache_create("request_queue_srcu", + sizeof(struct request_queue) + + sizeof(struct srcu_struct), 0, SLAB_PANIC, NULL); + blk_debugfs_root = debugfs_create_dir("block", NULL); return 0; diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 253c857cba47..674786574075 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -36,8 +36,6 @@ static void blk_mq_hw_sysfs_release(struct kobject *kobj) struct blk_mq_hw_ctx *hctx = container_of(kobj, struct blk_mq_hw_ctx, kobj); - if (hctx->flags & BLK_MQ_F_BLOCKING) - cleanup_srcu_struct(hctx->srcu); blk_free_flush_queue(hctx->fq); sbitmap_free(&hctx->ctx_map); free_cpumask_var(hctx->cpumask); diff --git a/block/blk-mq.c b/block/blk-mq.c index 494da31dc1a5..6a2c2704454e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -260,17 +260,9 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait); */ void blk_mq_wait_quiesce_done(struct request_queue *q) { - struct blk_mq_hw_ctx *hctx; - unsigned int i; - bool rcu = false; - - queue_for_each_hw_ctx(q, hctx, i) { - if (hctx->flags & BLK_MQ_F_BLOCKING) - synchronize_srcu(hctx->srcu); - else - rcu = true; - } - if (rcu) + if (blk_queue_has_srcu(q)) + synchronize_srcu(q->srcu); + else synchronize_rcu(); } EXPORT_SYMBOL_GPL(blk_mq_wait_quiesce_done); @@ -3400,20 +3392,6 @@ static void blk_mq_exit_hw_queues(struct request_queue *q, } } -static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set) -{ - int hw_ctx_size = sizeof(struct blk_mq_hw_ctx); - - BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, srcu), - __alignof__(struct blk_mq_hw_ctx)) != - sizeof(struct blk_mq_hw_ctx)); - - if (tag_set->flags & BLK_MQ_F_BLOCKING) - hw_ctx_size += sizeof(struct srcu_struct); - - return hw_ctx_size; -} - static int blk_mq_init_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned hctx_idx) @@ -3451,7 +3429,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx; gfp_t gfp = GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY; - hctx = kzalloc_node(blk_mq_hw_ctx_size(set), gfp, node); + hctx = kzalloc_node(sizeof(struct blk_mq_hw_ctx), gfp, node); if (!hctx) goto fail_alloc_hctx; @@ -3493,8 +3471,6 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, if (!hctx->fq) goto free_bitmap; - if (hctx->flags & BLK_MQ_F_BLOCKING) - init_srcu_struct(hctx->srcu); blk_mq_hctx_kobj_init(hctx); return hctx; @@ -3830,7 +3806,7 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, struct request_queue *q; int ret; - q = blk_alloc_queue(set->numa_node); + q = blk_alloc_queue(set->numa_node, set->flags & BLK_MQ_F_BLOCKING); if (!q) return ERR_PTR(-ENOMEM); q->queuedata = queuedata; @@ -3979,6 +3955,9 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, struct request_queue *q) { + WARN_ON_ONCE(blk_queue_has_srcu(q) != + !!(set->flags & BLK_MQ_F_BLOCKING)); + /* mark the queue as mq asap */ q->mq_ops = set->ops; diff --git a/block/blk-mq.h b/block/blk-mq.h index e4c396204928..792f0b29c6eb 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -385,9 +385,9 @@ do { \ int srcu_idx; \ \ might_sleep(); \ - srcu_idx = srcu_read_lock((hctx)->srcu); \ + srcu_idx = srcu_read_lock((hctx)->queue->srcu); \ (dispatch_ops); \ - srcu_read_unlock((hctx)->srcu, srcu_idx); \ + srcu_read_unlock((hctx)->queue->srcu, srcu_idx); \ } \ } while (0) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 4622da4bb992..3e6357321225 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -735,7 +735,8 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head) { struct request_queue *q = container_of(rcu_head, struct request_queue, rcu_head); - kmem_cache_free(blk_requestq_cachep, q); + + kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q); } /* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */ diff --git a/block/blk.h b/block/blk.h index 24d8b333bb03..7ccb7c7d86b3 100644 --- a/block/blk.h +++ b/block/blk.h @@ -27,6 +27,7 @@ struct blk_flush_queue { }; extern struct kmem_cache *blk_requestq_cachep; +extern struct kmem_cache *blk_requestq_srcu_cachep; extern struct kobj_type blk_queue_ktype; extern struct ida blk_queue_ida; @@ -424,7 +425,14 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); -struct request_queue *blk_alloc_queue(int node_id); +static inline struct kmem_cache *blk_get_queue_kmem_cache(bool srcu) +{ + if (srcu) + return blk_requestq_srcu_cachep; + return blk_requestq_cachep; +} +struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu); + int disk_scan_partitions(struct gendisk *disk, fmode_t mode); int disk_alloc_events(struct gendisk *disk); diff --git a/block/genhd.c b/block/genhd.c index 5179a4f00fba..3c139a1b6f04 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1338,7 +1338,7 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) struct request_queue *q; struct gendisk *disk; - q = blk_alloc_queue(node); + q = blk_alloc_queue(node, false); if (!q) return NULL; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 561beb5be7ec..ecdc049b52fa 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -4,7 +4,6 @@ #include #include -#include #include #include #include @@ -375,13 +374,6 @@ struct blk_mq_hw_ctx { * q->unused_hctx_list. */ struct list_head hctx_list; - - /** - * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is - * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also - * blk_mq_hw_ctx_size(). - */ - struct srcu_struct srcu[]; }; /** diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0a4416ef4fbf..c80cfaefc0a8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -16,6 +16,7 @@ #include #include #include +#include struct module; struct request_queue; @@ -373,11 +374,18 @@ struct request_queue { * devices that do not have multiple independent access ranges. */ struct blk_independent_access_ranges *ia_ranges; + + /** + * @srcu: Sleepable RCU. Use as lock when type of the request queue + * is blocking (BLK_MQ_F_BLOCKING). Must be the last member + */ + struct srcu_struct srcu[]; }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ +#define QUEUE_FLAG_HAS_SRCU 2 /* SRCU is allocated */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ @@ -415,6 +423,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) +#define blk_queue_has_srcu(q) test_bit(QUEUE_FLAG_HAS_SRCU, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) -- cgit v1.2.3 From 0cc3a8017900f856f9bf4fdc41c2b5cb1670aabe Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 2 Dec 2021 13:01:56 -0800 Subject: qed*: enhance tx timeout debug info This patch add some new qed APIs to query status block info and report various data to MFW on tx timeout event Along with that it enhances qede to dump more debug logs (not just specific to the queue which was reported by stack) on tx timeout which includes various other basic metadata about all tx queues and other info (like status block etc.) Signed-off-by: Manish Chopra Signed-off-by: Prabhakar Kushwaha Signed-off-by: Alok Prasad Signed-off-by: Ariel Elior Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qed/qed_int.c | 22 +++++++ drivers/net/ethernet/qlogic/qed/qed_int.h | 13 ++++ drivers/net/ethernet/qlogic/qed/qed_main.c | 47 +++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 2 + drivers/net/ethernet/qlogic/qed/qed_reg_addr.h | 2 + drivers/net/ethernet/qlogic/qede/qede_main.c | 91 +++++++++++++++++++++----- include/linux/qed/qed_if.h | 11 ++++ 7 files changed, 173 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index 6958adeca86d..82e74f62b677 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -2399,3 +2399,25 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, return rc; } + +int qed_int_get_sb_dbg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_sb_info *p_sb, struct qed_sb_info_dbg *p_info) +{ + u16 sbid = p_sb->igu_sb_id; + u32 i; + + if (IS_VF(p_hwfn->cdev)) + return -EINVAL; + + if (sbid >= NUM_OF_SBS(p_hwfn->cdev)) + return -EINVAL; + + p_info->igu_prod = qed_rd(p_hwfn, p_ptt, IGU_REG_PRODUCER_MEMORY + sbid * 4); + p_info->igu_cons = qed_rd(p_hwfn, p_ptt, IGU_REG_CONSUMER_MEM + sbid * 4); + + for (i = 0; i < PIS_PER_SB; i++) + p_info->pi[i] = (u16)qed_rd(p_hwfn, p_ptt, + CAU_REG_PI_MEMORY + sbid * 4 * PIS_PER_SB + i * 4); + + return 0; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h index 84c17e97f569..7e5127f61744 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.h +++ b/drivers/net/ethernet/qlogic/qed/qed_int.h @@ -185,6 +185,19 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev); */ void qed_int_attn_clr_enable(struct qed_dev *cdev, bool clr_enable); +/** + * qed_int_get_sb_dbg: Read debug information regarding a given SB + * + * @p_hwfn: hw function pointer + * @p_ptt: ptt resource + * @p_sb: pointer to status block for which we want to get info + * @p_info: pointer to struct to fill with information regarding SB + * + * Return: 0 with status block info filled on success, otherwise return error + */ +int qed_int_get_sb_dbg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_sb_info *p_sb, struct qed_sb_info_dbg *p_info); + /** * qed_db_rec_handler(): Doorbell Recovery handler. * Run doorbell recovery in case of PF overflow (and flush DORQ if diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 7673b3e07736..a18d2ea96b26 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -2936,6 +2936,30 @@ out: return status; } +static int +qed_get_sb_info(struct qed_dev *cdev, struct qed_sb_info *sb, + u16 qid, struct qed_sb_info_dbg *sb_dbg) +{ + struct qed_hwfn *hwfn = &cdev->hwfns[qid % cdev->num_hwfns]; + struct qed_ptt *ptt; + int rc; + + if (IS_VF(cdev)) + return -EINVAL; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) { + DP_NOTICE(hwfn, "Can't acquire PTT\n"); + return -EAGAIN; + } + + memset(sb_dbg, 0, sizeof(*sb_dbg)); + rc = qed_int_get_sb_dbg(hwfn, ptt, sb, sb_dbg); + + qed_ptt_release(hwfn, ptt); + return rc; +} + static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf, u8 dev_addr, u32 offset, u32 len) { @@ -2978,6 +3002,27 @@ static int qed_set_grc_config(struct qed_dev *cdev, u32 cfg_id, u32 val) return rc; } +static __printf(2, 3) void qed_mfw_report(struct qed_dev *cdev, char *fmt, ...) +{ + char buf[QED_MFW_REPORT_STR_SIZE]; + struct qed_hwfn *p_hwfn; + struct qed_ptt *p_ptt; + va_list vl; + + va_start(vl, fmt); + vsnprintf(buf, QED_MFW_REPORT_STR_SIZE, fmt, vl); + va_end(vl); + + if (IS_PF(cdev)) { + p_hwfn = QED_LEADING_HWFN(cdev); + p_ptt = qed_ptt_acquire(p_hwfn); + if (p_ptt) { + qed_mcp_send_raw_debug_data(p_hwfn, p_ptt, buf, strlen(buf)); + qed_ptt_release(p_hwfn, p_ptt); + } + } +} + static u8 qed_get_affin_hwfn_idx(struct qed_dev *cdev) { return QED_AFFIN_HWFN_IDX(cdev); @@ -3038,6 +3083,8 @@ const struct qed_common_ops qed_common_ops_pass = { .read_nvm_cfg = &qed_nvm_flash_cfg_read, .read_nvm_cfg_len = &qed_nvm_flash_cfg_len, .set_grc_config = &qed_set_grc_config, + .mfw_report = &qed_mfw_report, + .get_sb_info = &qed_get_sb_info, }; void qed_get_protocol_stats(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 564723800d15..2c28d5f86497 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -15,6 +15,8 @@ #include "qed_hsi.h" #include "qed_dev_api.h" +#define QED_MFW_REPORT_STR_SIZE 256 + struct qed_mcp_link_speed_params { bool autoneg; diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index 6f1a52e6beb2..b5e35f433a20 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -550,6 +550,8 @@ 0x1 << 1) #define IGU_REG_BLOCK_CONFIGURATION_PXP_TPH_INTERFACE_EN ( \ 0x1 << 0) +#define IGU_REG_PRODUCER_MEMORY 0x182000UL +#define IGU_REG_CONSUMER_MEM 0x183000UL #define IGU_REG_MAPPING_MEMORY \ 0x184000UL #define IGU_REG_STATISTIC_NUM_VF_MSG_SENT \ diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 06c6a5813606..b4e5a15e308b 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -509,34 +509,95 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; } -static void qede_tx_log_print(struct qede_dev *edev, struct qede_tx_queue *txq) +static void qede_fp_sb_dump(struct qede_dev *edev, struct qede_fastpath *fp) { + char *p_sb = (char *)fp->sb_info->sb_virt; + u32 sb_size, i; + + sb_size = sizeof(struct status_block); + + for (i = 0; i < sb_size; i += 8) + DP_NOTICE(edev, + "%02hhX %02hhX %02hhX %02hhX %02hhX %02hhX %02hhX %02hhX\n", + p_sb[i], p_sb[i + 1], p_sb[i + 2], p_sb[i + 3], + p_sb[i + 4], p_sb[i + 5], p_sb[i + 6], p_sb[i + 7]); +} + +static void +qede_txq_fp_log_metadata(struct qede_dev *edev, + struct qede_fastpath *fp, struct qede_tx_queue *txq) +{ + struct qed_chain *p_chain = &txq->tx_pbl; + + /* Dump txq/fp/sb ids etc. other metadata */ DP_NOTICE(edev, - "Txq[%d]: FW cons [host] %04x, SW cons %04x, SW prod %04x [Jiffies %lu]\n", - txq->index, le16_to_cpu(*txq->hw_cons_ptr), - qed_chain_get_cons_idx(&txq->tx_pbl), - qed_chain_get_prod_idx(&txq->tx_pbl), - jiffies); + "fpid 0x%x sbid 0x%x txqid [0x%x] ndev_qid [0x%x] cos [0x%x] p_chain %p cap %d size %d jiffies %lu HZ 0x%x\n", + fp->id, fp->sb_info->igu_sb_id, txq->index, txq->ndev_txq_id, txq->cos, + p_chain, p_chain->capacity, p_chain->size, jiffies, HZ); + + /* Dump all the relevant prod/cons indexes */ + DP_NOTICE(edev, + "hw cons %04x sw_tx_prod=0x%x, sw_tx_cons=0x%x, bd_prod 0x%x bd_cons 0x%x\n", + le16_to_cpu(*txq->hw_cons_ptr), txq->sw_tx_prod, txq->sw_tx_cons, + qed_chain_get_prod_idx(p_chain), qed_chain_get_cons_idx(p_chain)); +} + +static void +qede_tx_log_print(struct qede_dev *edev, struct qede_fastpath *fp, struct qede_tx_queue *txq) +{ + struct qed_sb_info_dbg sb_dbg; + int rc; + + /* sb info */ + qede_fp_sb_dump(edev, fp); + + memset(&sb_dbg, 0, sizeof(sb_dbg)); + rc = edev->ops->common->get_sb_info(edev->cdev, fp->sb_info, (u16)fp->id, &sb_dbg); + + DP_NOTICE(edev, "IGU: prod %08x cons %08x CAU Tx %04x\n", + sb_dbg.igu_prod, sb_dbg.igu_cons, sb_dbg.pi[TX_PI(txq->cos)]); + + /* report to mfw */ + edev->ops->common->mfw_report(edev->cdev, + "Txq[%d]: FW cons [host] %04x, SW cons %04x, SW prod %04x [Jiffies %lu]\n", + txq->index, le16_to_cpu(*txq->hw_cons_ptr), + qed_chain_get_cons_idx(&txq->tx_pbl), + qed_chain_get_prod_idx(&txq->tx_pbl), jiffies); + if (!rc) + edev->ops->common->mfw_report(edev->cdev, + "Txq[%d]: SB[0x%04x] - IGU: prod %08x cons %08x CAU Tx %04x\n", + txq->index, fp->sb_info->igu_sb_id, + sb_dbg.igu_prod, sb_dbg.igu_cons, + sb_dbg.pi[TX_PI(txq->cos)]); } static void qede_tx_timeout(struct net_device *dev, unsigned int txqueue) { struct qede_dev *edev = netdev_priv(dev); - struct qede_tx_queue *txq; - int cos; + int i; netif_carrier_off(dev); DP_NOTICE(edev, "TX timeout on queue %u!\n", txqueue); - if (!(edev->fp_array[txqueue].type & QEDE_FASTPATH_TX)) - return; + for_each_queue(i) { + struct qede_tx_queue *txq; + struct qede_fastpath *fp; + int cos; - for_each_cos_in_txq(edev, cos) { - txq = &edev->fp_array[txqueue].txq[cos]; + fp = &edev->fp_array[i]; + if (!(fp->type & QEDE_FASTPATH_TX)) + continue; - if (qed_chain_get_cons_idx(&txq->tx_pbl) != - qed_chain_get_prod_idx(&txq->tx_pbl)) - qede_tx_log_print(edev, txq); + for_each_cos_in_txq(edev, cos) { + txq = &fp->txq[cos]; + + /* Dump basic metadata for all queues */ + qede_txq_fp_log_metadata(edev, fp, txq); + + if (qed_chain_get_cons_idx(&txq->tx_pbl) != + qed_chain_get_prod_idx(&txq->tx_pbl)) + qede_tx_log_print(edev, fp, txq); + } } if (IS_VF(edev)) diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 0dae7fcc5ef2..9f4bfa2a4829 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -807,6 +807,12 @@ struct qed_devlink { struct devlink_health_reporter *fw_reporter; }; +struct qed_sb_info_dbg { + u32 igu_prod; + u32 igu_cons; + u16 pi[PIS_PER_SB]; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -1194,6 +1200,11 @@ struct qed_common_ops { struct devlink* (*devlink_register)(struct qed_dev *cdev); void (*devlink_unregister)(struct devlink *devlink); + + __printf(2, 3) void (*mfw_report)(struct qed_dev *cdev, char *fmt, ...); + + int (*get_sb_info)(struct qed_dev *cdev, struct qed_sb_info *sb, + u16 qid, struct qed_sb_info_dbg *sb_dbg); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From 823163ba6e52e644be5df4539a19e3df8d0988dd Mon Sep 17 00:00:00 2001 From: Manish Chopra Date: Thu, 2 Dec 2021 13:01:57 -0800 Subject: qed*: esl priv flag support through ethtool ESL(Enhanced System Lockdown) was designed to lock PCI adapter firmware images and prevent changes to critical non-volatile configuration data so that uncontrolled, malicious or unintentional modification to the adapters are avoided, ensuring it's operational state. Once this feature is enabled, the device is locked, rejecting any modification to non-volatile images. Once unlocked, the protection is off such that firmware and non-volatile configurations may be altered. Driver just reflects the capability and status of this through the ethtool private flag. Signed-off-by: Manish Chopra Signed-off-by: Prabhakar Kushwaha Signed-off-by: Alok Prasad Signed-off-by: Ariel Elior Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/qlogic/qed/qed_main.c | 25 ++++++++++++++++++++++++- drivers/net/ethernet/qlogic/qed/qed_mcp.c | 22 ++++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mcp.h | 20 ++++++++++++++++++++ drivers/net/ethernet/qlogic/qed/qed_mfw_hsi.h | 1 + drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 13 +++++++++++++ include/linux/qed/qed_if.h | 3 +++ 6 files changed, 83 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index a18d2ea96b26..46d4207f22a3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -447,7 +447,7 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->wol_support = true; dev_info->smart_an = qed_mcp_is_smart_an_supported(p_hwfn); - + dev_info->esl = qed_mcp_is_esl_supported(p_hwfn); dev_info->abs_pf_id = QED_LEADING_HWFN(cdev)->abs_pf_id; } else { qed_vf_get_fw_version(&cdev->hwfns[0], &dev_info->fw_major, @@ -3028,6 +3028,28 @@ static u8 qed_get_affin_hwfn_idx(struct qed_dev *cdev) return QED_AFFIN_HWFN_IDX(cdev); } +static int qed_get_esl_status(struct qed_dev *cdev, bool *esl_active) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *ptt; + int rc = 0; + + *esl_active = false; + + if (IS_VF(cdev)) + return 0; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + rc = qed_mcp_get_esl_status(hwfn, ptt, esl_active); + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static struct qed_selftest_ops qed_selftest_ops_pass = { .selftest_memory = &qed_selftest_memory, .selftest_interrupt = &qed_selftest_interrupt, @@ -3085,6 +3107,7 @@ const struct qed_common_ops qed_common_ops_pass = { .set_grc_config = &qed_set_grc_config, .mfw_report = &qed_mfw_report, .get_sb_info = &qed_get_sb_info, + .get_esl_status = &qed_get_esl_status, }; void qed_get_protocol_stats(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 64678a256f3b..da1eadabcb41 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -4158,3 +4158,25 @@ qed_mcp_send_raw_debug_data(struct qed_hwfn *p_hwfn, return qed_mcp_send_debug_data(p_hwfn, p_ptt, QED_MCP_DBG_DATA_TYPE_RAW, p_buf, size); } + +bool qed_mcp_is_esl_supported(struct qed_hwfn *p_hwfn) +{ + return !!(p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_ENHANCED_SYS_LCK); +} + +int qed_mcp_get_esl_status(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool *active) +{ + u32 resp = 0, param = 0; + int rc; + + rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_GET_MANAGEMENT_STATUS, 0, &resp, ¶m); + if (rc) { + DP_NOTICE(p_hwfn, "Failed to send ESL command, rc = %d\n", rc); + return rc; + } + + *active = !!(param & FW_MB_PARAM_MANAGEMENT_STATUS_LOCKDOWN_ENABLED); + + return 0; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 2c28d5f86497..369e1892450a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -1339,4 +1339,24 @@ int qed_mcp_nvm_get_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, u32 len); + +/** + * qed_mcp_is_esl_supported(): Return whether management firmware support ESL or not. + * + * @p_hwfn: hw function pointer + * + * Return: true if esl is supported, otherwise return false + */ +bool qed_mcp_is_esl_supported(struct qed_hwfn *p_hwfn); + +/** + * qed_mcp_get_esl_status(): Get enhanced system lockdown status + * + * @p_hwfn: hw function pointer + * @p_ptt: ptt resource pointer + * @active: ESL active status data pointer + * + * Return: 0 with esl status info on success, otherwise return error + */ +int qed_mcp_get_esl_status(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool *active); #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_mfw_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_mfw_hsi.h index 8a0e3c5d4bda..b70ee8200e15 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mfw_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mfw_hsi.h @@ -1191,6 +1191,7 @@ enum drv_msg_code_enum { DRV_MSG_CODE_CFG_VF_MSIX = DRV_MSG_CODE(0xc001), DRV_MSG_CODE_CFG_PF_VFS_MSIX = DRV_MSG_CODE(0xc002), DRV_MSG_CODE_DEBUG_DATA_SEND = DRV_MSG_CODE(0xc004), + DRV_MSG_CODE_GET_MANAGEMENT_STATUS = DRV_MSG_CODE(0xc007), }; #define DRV_MSG_CODE_VMAC_TYPE_SHIFT 4 diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 100c9c52c20b..97a7ab0826ed 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -168,6 +168,8 @@ enum { QEDE_PRI_FLAG_CMT, QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */ QEDE_PRI_FLAG_RECOVER_ON_ERROR, + QEDE_PRI_FLAG_ESL_SUPPORT, /* MFW supports Enhanced System Lockdown */ + QEDE_PRI_FLAG_ESL_ACTIVE, /* Enhanced System Lockdown Active status */ QEDE_PRI_FLAG_LEN, }; @@ -175,6 +177,8 @@ static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = { "Coupled-Function", "SmartAN capable", "Recover on error", + "ESL capable", + "ESL active", }; enum qede_ethtool_tests { @@ -478,6 +482,7 @@ static int qede_get_sset_count(struct net_device *dev, int stringset) static u32 qede_get_priv_flags(struct net_device *dev) { struct qede_dev *edev = netdev_priv(dev); + bool esl_active; u32 flags = 0; if (edev->dev_info.common.num_hwfns > 1) @@ -489,6 +494,14 @@ static u32 qede_get_priv_flags(struct net_device *dev) if (edev->err_flags & BIT(QEDE_ERR_IS_RECOVERABLE)) flags |= BIT(QEDE_PRI_FLAG_RECOVER_ON_ERROR); + if (edev->dev_info.common.esl) + flags |= BIT(QEDE_PRI_FLAG_ESL_SUPPORT); + + edev->ops->common->get_esl_status(edev->cdev, &esl_active); + + if (esl_active) + flags |= BIT(QEDE_PRI_FLAG_ESL_ACTIVE); + return flags; } diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 9f4bfa2a4829..6dc4943d8aec 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -652,6 +652,7 @@ struct qed_dev_info { bool wol_support; bool smart_an; + bool esl; /* MBI version */ u32 mbi_version; @@ -1205,6 +1206,8 @@ struct qed_common_ops { int (*get_sb_info)(struct qed_dev *cdev, struct qed_sb_info *sb, u16 qid, struct qed_sb_info_dbg *sb_dbg); + + int (*get_esl_status)(struct qed_dev *cdev, bool *esl_active); }; #define MASK_FIELD(_name, _value) \ -- cgit v1.2.3 From a3642021923b26d86bb27d88c826494827612c06 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 29 Nov 2021 18:46:47 +0100 Subject: locking/rtmutex: Add rt_mutex_lock_nest_lock() and rt_mutex_lock_killable(). The locking selftest for ww-mutex expects to operate directly on the base-mutex which becomes a rtmutex on PREEMPT_RT. Add a rtmutex based implementation of mutex_lock_nest_lock() and mutex_lock_killable() named rt_mutex_lock_nest_lock() abd rt_mutex_lock_killable(). Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211129174654.668506-5-bigeasy@linutronix.de --- include/linux/rtmutex.h | 9 +++++++++ kernel/locking/rtmutex_api.c | 30 ++++++++++++++++++++++++++---- 2 files changed, 35 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 9deedfeec2b1..7d049883a08a 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -99,13 +99,22 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock #ifdef CONFIG_DEBUG_LOCK_ALLOC extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +extern void _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock); #define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#define rt_mutex_lock_nest_lock(lock, nest_lock) \ + do { \ + typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ + _rt_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ + } while (0) + #else extern void rt_mutex_lock(struct rt_mutex *lock); #define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#define rt_mutex_lock_nest_lock(lock, nest_lock) rt_mutex_lock(lock) #endif extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); +extern int rt_mutex_lock_killable(struct rt_mutex *lock); extern int rt_mutex_trylock(struct rt_mutex *lock); extern void rt_mutex_unlock(struct rt_mutex *lock); diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c index 5c9299aaabae..900220941caa 100644 --- a/kernel/locking/rtmutex_api.c +++ b/kernel/locking/rtmutex_api.c @@ -21,12 +21,13 @@ int max_lock_depth = 1024; */ static __always_inline int __rt_mutex_lock_common(struct rt_mutex *lock, unsigned int state, + struct lockdep_map *nest_lock, unsigned int subclass) { int ret; might_sleep(); - mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, _RET_IP_); ret = __rt_mutex_lock(&lock->rtmutex, state); if (ret) mutex_release(&lock->dep_map, _RET_IP_); @@ -48,10 +49,16 @@ EXPORT_SYMBOL(rt_mutex_base_init); */ void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) { - __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, subclass); + __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, subclass); } EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); +void __sched _rt_mutex_lock_nest_lock(struct rt_mutex *lock, struct lockdep_map *nest_lock) +{ + __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, nest_lock, 0); +} +EXPORT_SYMBOL_GPL(_rt_mutex_lock_nest_lock); + #else /* !CONFIG_DEBUG_LOCK_ALLOC */ /** @@ -61,7 +68,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0); + __rt_mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, NULL, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock); #endif @@ -77,10 +84,25 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); */ int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) { - return __rt_mutex_lock_common(lock, TASK_INTERRUPTIBLE, 0); + return __rt_mutex_lock_common(lock, TASK_INTERRUPTIBLE, NULL, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); +/** + * rt_mutex_lock_killable - lock a rt_mutex killable + * + * @lock: the rt_mutex to be locked + * + * Returns: + * 0 on success + * -EINTR when interrupted by a signal + */ +int __sched rt_mutex_lock_killable(struct rt_mutex *lock) +{ + return __rt_mutex_lock_common(lock, TASK_KILLABLE, NULL, 0); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + /** * rt_mutex_trylock - try to lock a rt_mutex * -- cgit v1.2.3 From 0c1d7a2c2d32fac7ff4a644724b2d52a64184645 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 29 Nov 2021 18:46:48 +0100 Subject: lockdep: Remove softirq accounting on PREEMPT_RT. There is not really a softirq context on PREEMPT_RT. Softirqs on PREEMPT_RT are always invoked within the context of a threaded interrupt handler or within ksoftirqd. The "in-softirq" context is preemptible and is protected by a per-CPU lock to ensure mutual exclusion. There is no difference on PREEMPT_RT between spin_lock_irq() and spin_lock() because the former does not disable interrupts. Therefore if a lock is used in_softirq() and locked once with spin_lock_irq() then lockdep will report this with "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage". Teach lockdep that we don't really do softirqs on -RT. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211129174654.668506-6-bigeasy@linutronix.de --- include/linux/irqflags.h | 23 +++++++++++++++-------- kernel/locking/lockdep.c | 2 ++ 2 files changed, 17 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 600c10da321a..4b140938b03e 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -71,14 +71,6 @@ do { \ do { \ __this_cpu_dec(hardirq_context); \ } while (0) -# define lockdep_softirq_enter() \ -do { \ - current->softirq_context++; \ -} while (0) -# define lockdep_softirq_exit() \ -do { \ - current->softirq_context--; \ -} while (0) # define lockdep_hrtimer_enter(__hrtimer) \ ({ \ @@ -140,6 +132,21 @@ do { \ # define lockdep_irq_work_exit(__work) do { } while (0) #endif +#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT) +# define lockdep_softirq_enter() \ +do { \ + current->softirq_context++; \ +} while (0) +# define lockdep_softirq_exit() \ +do { \ + current->softirq_context--; \ +} while (0) + +#else +# define lockdep_softirq_enter() do { } while (0) +# define lockdep_softirq_exit() do { } while (0) +#endif + #if defined(CONFIG_IRQSOFF_TRACER) || \ defined(CONFIG_PREEMPT_TRACER) extern void stop_critical_timings(void); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 2270ec68f10a..4a882f83aeb9 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -5485,6 +5485,7 @@ static noinstr void check_flags(unsigned long flags) } } +#ifndef CONFIG_PREEMPT_RT /* * We dont accurately track softirq state in e.g. * hardirq contexts (such as on 4KSTACKS), so only @@ -5499,6 +5500,7 @@ static noinstr void check_flags(unsigned long flags) DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); } } +#endif if (!debug_locks) print_irqtrace_events(current); -- cgit v1.2.3 From c0bed69daf4b67809b58cc7cd81a8fa4f45bc161 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 3 Dec 2021 15:59:34 +0800 Subject: locking: Make owner_on_cpu() into Move the owner_on_cpu() from kernel/locking/rwsem.c into include/linux/sched.h with under CONFIG_SMP, then use it in the mutex/rwsem/rtmutex to simplify the code. Signed-off-by: Kefeng Wang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211203075935.136808-2-wangkefeng.wang@huawei.com --- include/linux/sched.h | 9 +++++++++ kernel/locking/mutex.c | 11 ++--------- kernel/locking/rtmutex.c | 5 ++--- kernel/locking/rwsem.c | 9 --------- 4 files changed, 13 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..ff609d9c2f21 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2171,6 +2171,15 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask); #endif #ifdef CONFIG_SMP +static inline bool owner_on_cpu(struct task_struct *owner) +{ + /* + * As lock holder preemption issue, we both skip spinning if + * task is not on cpu or its cpu is preempted + */ + return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); +} + /* Returns effective CPU energy utilization, as seen by the scheduler */ unsigned long sched_cpu_util(int cpu, unsigned long max); #endif /* CONFIG_SMP */ diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index db1913611192..5e3585950ec8 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -367,8 +367,7 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner, /* * Use vcpu_is_preempted to detect lock holder preemption issue. */ - if (!owner->on_cpu || need_resched() || - vcpu_is_preempted(task_cpu(owner))) { + if (!owner_on_cpu(owner) || need_resched()) { ret = false; break; } @@ -403,14 +402,8 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) * structure won't go away during the spinning period. */ owner = __mutex_owner(lock); - - /* - * As lock holder preemption issue, we both skip spinning if task is not - * on cpu or its cpu is preempted - */ - if (owner) - retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); + retval = owner_on_cpu(owner); /* * If lock->owner is not set, the mutex has been released. Return true diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index f89620852774..0c1f2e3f019a 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1382,9 +1382,8 @@ static bool rtmutex_spin_on_owner(struct rt_mutex_base *lock, * for CONFIG_PREEMPT_RCU=y) * - the VCPU on which owner runs is preempted */ - if (!owner->on_cpu || need_resched() || - rt_mutex_waiter_is_top_waiter(lock, waiter) || - vcpu_is_preempted(task_cpu(owner))) { + if (!owner_on_cpu(owner) || need_resched() || + rt_mutex_waiter_is_top_waiter(lock, waiter)) { res = false; break; } diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index c51387a43265..b92d0a830568 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -613,15 +613,6 @@ static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem) return false; } -static inline bool owner_on_cpu(struct task_struct *owner) -{ - /* - * As lock holder preemption issue, we both skip spinning if - * task is not on cpu or its cpu is preempted - */ - return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); -} - static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) { struct task_struct *owner; -- cgit v1.2.3 From 4cf75fd4a2545ca4deea992f929602c9fdbe8058 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Fri, 3 Dec 2021 15:59:35 +0800 Subject: locking: Mark racy reads of owner->on_cpu One of the more frequent data races reported by KCSAN is the racy read in mutex_spin_on_owner(), which is usually reported as "race of unknown origin" without showing the writer. This is due to the racing write occurring in kernel/sched. Locally enabling KCSAN in kernel/sched shows: | write (marked) to 0xffff97f205079934 of 4 bytes by task 316 on cpu 6: | finish_task kernel/sched/core.c:4632 [inline] | finish_task_switch kernel/sched/core.c:4848 | context_switch kernel/sched/core.c:4975 [inline] | __schedule kernel/sched/core.c:6253 | schedule kernel/sched/core.c:6326 | schedule_preempt_disabled kernel/sched/core.c:6385 | __mutex_lock_common kernel/locking/mutex.c:680 | __mutex_lock kernel/locking/mutex.c:740 [inline] | __mutex_lock_slowpath kernel/locking/mutex.c:1028 | mutex_lock kernel/locking/mutex.c:283 | tty_open_by_driver drivers/tty/tty_io.c:2062 [inline] | ... | | read to 0xffff97f205079934 of 4 bytes by task 322 on cpu 3: | mutex_spin_on_owner kernel/locking/mutex.c:370 | mutex_optimistic_spin kernel/locking/mutex.c:480 | __mutex_lock_common kernel/locking/mutex.c:610 | __mutex_lock kernel/locking/mutex.c:740 [inline] | __mutex_lock_slowpath kernel/locking/mutex.c:1028 | mutex_lock kernel/locking/mutex.c:283 | tty_open_by_driver drivers/tty/tty_io.c:2062 [inline] | ... | | value changed: 0x00000001 -> 0x00000000 This race is clearly intentional, and the potential for miscompilation is slim due to surrounding barrier() and cpu_relax(), and the value being used as a boolean. Nevertheless, marking this reader would more clearly denote intent and make it obvious that concurrency is expected. Use READ_ONCE() to avoid having to reason about compiler optimizations now and in future. With previous refactor, mark the read to owner->on_cpu in owner_on_cpu(), which immediately precedes the loop executing mutex_spin_on_owner(). Signed-off-by: Marco Elver Signed-off-by: Kefeng Wang Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211203075935.136808-3-wangkefeng.wang@huawei.com --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index ff609d9c2f21..0b9b0e3f4791 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2177,7 +2177,7 @@ static inline bool owner_on_cpu(struct task_struct *owner) * As lock holder preemption issue, we both skip spinning if * task is not on cpu or its cpu is preempted */ - return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); + return READ_ONCE(owner->on_cpu) && !vcpu_is_preempted(task_cpu(owner)); } /* Returns effective CPU energy utilization, as seen by the scheduler */ -- cgit v1.2.3 From fb08a1908cb119a4585611d91461ab6d27756b14 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:38 +0100 Subject: dax: simplify the dax_device <-> gendisk association Replace the dax_host_hash with an xarray indexed by the pointer value of the gendisk, and require explicitly calls from the block drivers that want to associate their gendisk with a dax_device. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/bus.c | 6 +-- drivers/dax/super.c | 109 +++++++++++-------------------------------- drivers/md/dm.c | 6 ++- drivers/nvdimm/pmem.c | 10 +++- drivers/s390/block/dcssblk.c | 11 +++-- fs/fuse/virtio_fs.c | 2 +- include/linux/dax.h | 19 ++++++-- 7 files changed, 66 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 452cf7860926..6683d42c32c5 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1321,10 +1321,10 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) } /* - * No 'host' or dax_operations since there is no access to this - * device outside of mmap of the resulting character device. + * No dax_operations since there is no access to this device outside of + * mmap of the resulting character device. */ - dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC); + dax_dev = alloc_dax(dev_dax, NULL, DAXDEV_F_SYNC); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto err_alloc_dax; diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e20d0cef10a1..bf77c3da5d56 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -7,10 +7,8 @@ #include #include #include -#include #include #include -#include #include #include #include @@ -21,15 +19,12 @@ * struct dax_device - anchor object for dax services * @inode: core vfs * @cdev: optional character interface for "device dax" - * @host: optional name for lookups where the device path is not available * @private: dax driver private data * @flags: state and boolean properties */ struct dax_device { - struct hlist_node list; struct inode inode; struct cdev cdev; - const char *host; void *private; unsigned long flags; const struct dax_operations *ops; @@ -42,10 +37,6 @@ static DEFINE_IDA(dax_minor_ida); static struct kmem_cache *dax_cache __read_mostly; static struct super_block *dax_superblock __read_mostly; -#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head)) -static struct hlist_head dax_host_list[DAX_HASH_SIZE]; -static DEFINE_SPINLOCK(dax_host_lock); - int dax_read_lock(void) { return srcu_read_lock(&dax_srcu); @@ -58,13 +49,22 @@ void dax_read_unlock(int id) } EXPORT_SYMBOL_GPL(dax_read_unlock); -static int dax_host_hash(const char *host) +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) +#include + +static DEFINE_XARRAY(dax_hosts); + +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { - return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE; + return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL); } +EXPORT_SYMBOL_GPL(dax_add_host); -#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) -#include +void dax_remove_host(struct gendisk *disk) +{ + xa_erase(&dax_hosts, (unsigned long)disk); +} +EXPORT_SYMBOL_GPL(dax_remove_host); int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, pgoff_t *pgoff) @@ -81,41 +81,24 @@ int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, EXPORT_SYMBOL(bdev_dax_pgoff); /** - * dax_get_by_host() - temporary lookup mechanism for filesystem-dax - * @host: alternate name for the device registered by a dax driver + * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax + * @bdev: block device to find a dax_device for */ -static struct dax_device *dax_get_by_host(const char *host) +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { - struct dax_device *dax_dev, *found = NULL; - int hash, id; + struct dax_device *dax_dev; + int id; - if (!host) + if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; - hash = dax_host_hash(host); - id = dax_read_lock(); - spin_lock(&dax_host_lock); - hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) { - if (!dax_alive(dax_dev) - || strcmp(host, dax_dev->host) != 0) - continue; - - if (igrab(&dax_dev->inode)) - found = dax_dev; - break; - } - spin_unlock(&dax_host_lock); + dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk); + if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode)) + dax_dev = NULL; dax_read_unlock(id); - return found; -} - -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) -{ - if (!blk_queue_dax(bdev->bd_disk->queue)) - return NULL; - return dax_get_by_host(bdev->bd_disk->disk_name); + return dax_dev; } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); @@ -361,12 +344,7 @@ void kill_dax(struct dax_device *dax_dev) return; clear_bit(DAXDEV_ALIVE, &dax_dev->flags); - synchronize_srcu(&dax_srcu); - - spin_lock(&dax_host_lock); - hlist_del_init(&dax_dev->list); - spin_unlock(&dax_host_lock); } EXPORT_SYMBOL_GPL(kill_dax); @@ -398,8 +376,6 @@ static struct dax_device *to_dax_dev(struct inode *inode) static void dax_free_inode(struct inode *inode) { struct dax_device *dax_dev = to_dax_dev(inode); - kfree(dax_dev->host); - dax_dev->host = NULL; if (inode->i_rdev) ida_simple_remove(&dax_minor_ida, iminor(inode)); kmem_cache_free(dax_cache, dax_dev); @@ -474,54 +450,25 @@ static struct dax_device *dax_dev_get(dev_t devt) return dax_dev; } -static void dax_add_host(struct dax_device *dax_dev, const char *host) -{ - int hash; - - /* - * Unconditionally init dax_dev since it's coming from a - * non-zeroed slab cache - */ - INIT_HLIST_NODE(&dax_dev->list); - dax_dev->host = host; - if (!host) - return; - - hash = dax_host_hash(host); - spin_lock(&dax_host_lock); - hlist_add_head(&dax_dev->list, &dax_host_list[hash]); - spin_unlock(&dax_host_lock); -} - -struct dax_device *alloc_dax(void *private, const char *__host, - const struct dax_operations *ops, unsigned long flags) +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, + unsigned long flags) { struct dax_device *dax_dev; - const char *host; dev_t devt; int minor; - if (ops && !ops->zero_page_range) { - pr_debug("%s: error: device does not provide dax" - " operation zero_page_range()\n", - __host ? __host : "Unknown"); + if (WARN_ON_ONCE(ops && !ops->zero_page_range)) return ERR_PTR(-EINVAL); - } - - host = kstrdup(__host, GFP_KERNEL); - if (__host && !host) - return ERR_PTR(-ENOMEM); minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL); if (minor < 0) - goto err_minor; + return ERR_PTR(-ENOMEM); devt = MKDEV(MAJOR(dax_devt), minor); dax_dev = dax_dev_get(devt); if (!dax_dev) goto err_dev; - dax_add_host(dax_dev, host); dax_dev->ops = ops; dax_dev->private = private; if (flags & DAXDEV_F_SYNC) @@ -531,8 +478,6 @@ struct dax_device *alloc_dax(void *private, const char *__host, err_dev: ida_simple_remove(&dax_minor_ida, minor); - err_minor: - kfree(host); return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(alloc_dax); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index b93fcc91176e..a8c650276b32 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1683,6 +1683,7 @@ static void cleanup_mapped_device(struct mapped_device *md) bioset_exit(&md->io_bs); if (md->dax_dev) { + dax_remove_host(md->disk); kill_dax(md->dax_dev); put_dax(md->dax_dev); md->dax_dev = NULL; @@ -1784,12 +1785,13 @@ static struct mapped_device *alloc_dev(int minor) sprintf(md->disk->disk_name, "dm-%d", minor); if (IS_ENABLED(CONFIG_FS_DAX)) { - md->dax_dev = alloc_dax(md, md->disk->disk_name, - &dm_dax_ops, 0); + md->dax_dev = alloc_dax(md, &dm_dax_ops, 0); if (IS_ERR(md->dax_dev)) { md->dax_dev = NULL; goto bad; } + if (dax_add_host(md->dax_dev, md->disk)) + goto bad; } format_dev_t(md->name, MKDEV(_major, minor)); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index fe7ece1534e1..1018f0d44acb 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -379,6 +379,7 @@ static void pmem_release_disk(void *__pmem) { struct pmem_device *pmem = __pmem; + dax_remove_host(pmem->disk); kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); del_gendisk(pmem->disk); @@ -497,17 +498,20 @@ static int pmem_attach_disk(struct device *dev, if (is_nvdimm_sync(nd_region)) flags = DAXDEV_F_SYNC; - dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags); + dax_dev = alloc_dax(pmem, &pmem_dax_ops, flags); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto out; } + rc = dax_add_host(dax_dev, disk); + if (rc) + goto out_cleanup_dax; dax_write_cache(dax_dev, nvdimm_has_cache(nd_region)); pmem->dax_dev = dax_dev; rc = device_add_disk(dev, disk, pmem_attribute_groups); if (rc) - goto out_cleanup_dax; + goto out_remove_host; if (devm_add_action_or_reset(dev, pmem_release_disk, pmem)) return -ENOMEM; @@ -519,6 +523,8 @@ static int pmem_attach_disk(struct device *dev, dev_warn(dev, "'badblocks' notification disabled\n"); return 0; +out_remove_host: + dax_remove_host(pmem->disk); out_cleanup_dax: kill_dax(pmem->dax_dev); put_dax(pmem->dax_dev); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 27ab888b44d0..657e492f2bc2 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -687,18 +687,21 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char if (rc) goto put_dev; - dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name, - &dcssblk_dax_ops, DAXDEV_F_SYNC); + dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops, + DAXDEV_F_SYNC); if (IS_ERR(dev_info->dax_dev)) { rc = PTR_ERR(dev_info->dax_dev); dev_info->dax_dev = NULL; goto put_dev; } + rc = dax_add_host(dev_info->dax_dev, dev_info->gd); + if (rc) + goto out_dax; get_device(&dev_info->dev); rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL); if (rc) - goto out_dax; + goto out_dax_host; switch (dev_info->segment_type) { case SEG_TYPE_SR: @@ -714,6 +717,8 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char rc = count; goto out; +out_dax_host: + dax_remove_host(dev_info->gd); out_dax: put_device(&dev_info->dev); kill_dax(dev_info->dax_dev); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 4cfa4bc1f579..242cc1c0d7ed 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -850,7 +850,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); - fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0); + fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops, 0); if (IS_ERR(fs->dax_dev)) return PTR_ERR(fs->dax_dev); diff --git a/include/linux/dax.h b/include/linux/dax.h index 8623caa67388..e2e9a67004cb 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -11,9 +11,11 @@ typedef unsigned long dax_entry_t; +struct dax_device; +struct gendisk; struct iomap_ops; struct iomap; -struct dax_device; + struct dax_operations { /* * direct_access: translate a device-relative @@ -39,8 +41,8 @@ struct dax_operations { }; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *alloc_dax(void *private, const char *host, - const struct dax_operations *ops, unsigned long flags); +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, + unsigned long flags); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); @@ -68,7 +70,7 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, return dax_synchronous(dax_dev); } #else -static inline struct dax_device *alloc_dax(void *private, const char *host, +static inline struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, unsigned long flags) { /* @@ -107,6 +109,8 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, struct writeback_control; int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) +int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); +void dax_remove_host(struct gendisk *disk); bool generic_fsdax_supported(struct dax_device *dax_dev, struct block_device *bdev, int blocksize, sector_t start, sector_t sectors); @@ -128,6 +132,13 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st dax_entry_t dax_lock_page(struct page *page); void dax_unlock_page(struct page *page, dax_entry_t cookie); #else +static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) +{ + return 0; +} +static inline void dax_remove_host(struct gendisk *disk) +{ +} #define generic_fsdax_supported NULL static inline bool dax_supported(struct dax_device *dax_dev, -- cgit v1.2.3 From 7b0800d00dae8c897398abaf61e82db0d67d7afc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:42 +0100 Subject: dax: remove dax_capable Just open code the block size and dax_dev == NULL checks in the callers. Signed-off-by: Christoph Hellwig Acked-by: Mike Snitzer Reviewed-by: Gao Xiang [erofs] Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-9-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 36 ------------------------------------ drivers/md/dm-table.c | 22 +++++++++++----------- drivers/md/dm.c | 21 --------------------- drivers/md/dm.h | 4 ---- drivers/nvdimm/pmem.c | 1 - drivers/s390/block/dcssblk.c | 1 - fs/erofs/super.c | 11 +++++++---- fs/ext2/super.c | 6 ++++-- fs/ext4/super.c | 9 ++++++--- fs/xfs/xfs_super.c | 21 ++++++++------------- include/linux/dax.h | 14 -------------- 11 files changed, 36 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index f2cef47bdeaf..90b5733f5a70 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -107,42 +107,6 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) return dax_dev; } EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev); - -bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors) -{ - if (blocksize != PAGE_SIZE) { - pr_info("%pg: error: unsupported blocksize for dax\n", bdev); - return false; - } - - if (!dax_dev) { - pr_debug("%pg: error: dax unsupported by block device\n", bdev); - return false; - } - - return true; -} -EXPORT_SYMBOL_GPL(generic_fsdax_supported); - -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) -{ - bool ret = false; - int id; - - if (!dax_dev) - return false; - - id = dax_read_lock(); - if (dax_alive(dax_dev) && dax_dev->ops->dax_supported) - ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize, - start, len); - dax_read_unlock(id); - return ret; -} -EXPORT_SYMBOL_GPL(dax_supported); #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ enum dax_device_flags { diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index aa173f5bdc3d..e43096cfe9e2 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -806,12 +806,14 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) EXPORT_SYMBOL_GPL(dm_table_set_type); /* validate the dax capability of the target device span */ -int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, +static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - int blocksize = *(int *) data; + if (dev->dax_dev) + return false; - return !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len); + DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev); + return true; } /* Check devices support synchronous DAX */ @@ -821,8 +823,8 @@ static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_de return !dev->dax_dev || !dax_synchronous(dev->dax_dev); } -bool dm_table_supports_dax(struct dm_table *t, - iterate_devices_callout_fn iterate_fn, int *blocksize) +static bool dm_table_supports_dax(struct dm_table *t, + iterate_devices_callout_fn iterate_fn) { struct dm_target *ti; unsigned i; @@ -835,7 +837,7 @@ bool dm_table_supports_dax(struct dm_table *t, return false; if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, iterate_fn, blocksize)) + ti->type->iterate_devices(ti, iterate_fn, NULL)) return false; } @@ -862,7 +864,6 @@ static int dm_table_determine_type(struct dm_table *t) struct dm_target *tgt; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); - int page_size = PAGE_SIZE; if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ @@ -906,7 +907,7 @@ static int dm_table_determine_type(struct dm_table *t) verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; - if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) || + if (dm_table_supports_dax(t, device_not_dax_capable) || (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) { t->type = DM_TYPE_DAX_BIO_BASED; } @@ -1976,7 +1977,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, struct queue_limits *limits) { bool wc = false, fua = false; - int page_size = PAGE_SIZE; int r; /* @@ -2010,9 +2010,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } blk_queue_write_cache(q, wc, fua); - if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) { + if (dm_table_supports_dax(t, device_not_dax_capable)) { blk_queue_flag_set(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL)) + if (dm_table_supports_dax(t, device_not_dax_synchronous_capable)) set_dax_synchronous(t->md->dax_dev); } else diff --git a/drivers/md/dm.c b/drivers/md/dm.c index a8c650276b32..4eba27e75c23 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1027,26 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len) -{ - struct mapped_device *md = dax_get_private(dax_dev); - struct dm_table *map; - bool ret = false; - int srcu_idx; - - map = dm_get_live_table(md, &srcu_idx); - if (!map) - goto out; - - ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize); - -out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) { @@ -3044,7 +3024,6 @@ static const struct block_device_operations dm_rq_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, - .dax_supported = dm_dax_supported, .copy_from_iter = dm_dax_copy_from_iter, .copy_to_iter = dm_dax_copy_to_iter, .zero_page_range = dm_dax_zero_page_range, diff --git a/drivers/md/dm.h b/drivers/md/dm.h index 742d9c80efe1..9013dc1a7b00 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -73,10 +73,6 @@ bool dm_table_bio_based(struct dm_table *t); bool dm_table_request_based(struct dm_table *t); void dm_table_free_md_mempools(struct dm_table *t); struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t); -bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn, - int *blocksize); -int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data); void dm_lock_md_type(struct mapped_device *md); void dm_unlock_md_type(struct mapped_device *md); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 1018f0d44acb..4190c8c46ca8 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -321,7 +321,6 @@ static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, - .dax_supported = generic_fsdax_supported, .copy_from_iter = pmem_copy_from_iter, .copy_to_iter = pmem_copy_to_iter, .zero_page_range = pmem_dax_zero_page_range, diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 657e492f2bc2..e65e83764d1c 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -72,7 +72,6 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, static const struct dax_operations dcssblk_dax_ops = { .direct_access = dcssblk_dax_direct_access, - .dax_supported = generic_fsdax_supported, .copy_from_iter = dcssblk_dax_copy_from_iter, .copy_to_iter = dcssblk_dax_copy_to_iter, .zero_page_range = dcssblk_dax_zero_page_range, diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 6a969b1e0ee6..0aed886473c8 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -652,10 +652,13 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - if (test_opt(&sbi->opt, DAX_ALWAYS) && - !dax_supported(sbi->dax_dev, sb->s_bdev, EROFS_BLKSIZ, 0, bdev_nr_sectors(sb->s_bdev))) { - errorfc(fc, "DAX unsupported by block device. Turning off DAX."); - clear_opt(&sbi->opt, DAX_ALWAYS); + if (test_opt(&sbi->opt, DAX_ALWAYS)) { + BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE); + + if (!sbi->dax_dev) { + errorfc(fc, "DAX unsupported by block device. Turning off DAX."); + clear_opt(&sbi->opt, DAX_ALWAYS); + } } sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_maxbytes = MAX_LFS_FILESIZE; diff --git a/fs/ext2/super.c b/fs/ext2/super.c index d8d580b609ba..a964066a80aa 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -946,11 +946,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size); if (test_opt(sb, DAX)) { - if (!dax_supported(dax_dev, sb->s_bdev, blocksize, 0, - bdev_nr_sectors(sb->s_bdev))) { + if (!dax_dev) { ext2_msg(sb, KERN_ERR, "DAX unsupported by block device. Turning off DAX."); clear_opt(sbi->s_mount_opt, DAX); + } else if (blocksize != PAGE_SIZE) { + ext2_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); + clear_opt(sbi->s_mount_opt, DAX); } } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4e33b5eca694..fd3d68f10ee5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4299,9 +4299,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto failed_mount; } - if (dax_supported(dax_dev, sb->s_bdev, blocksize, 0, - bdev_nr_sectors(sb->s_bdev))) - set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + if (dax_dev) { + if (blocksize == PAGE_SIZE) + set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags); + else + ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n"); + } if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) { if (ext4_has_feature_inline_data(sb)) { diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 875fd3151d6c..c4297206f483 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -331,28 +331,23 @@ xfs_set_inode_alloc( return xfs_is_inode32(mp) ? maxagi : agcount; } -static bool -xfs_buftarg_is_dax( - struct super_block *sb, - struct xfs_buftarg *bt) -{ - return dax_supported(bt->bt_daxdev, bt->bt_bdev, sb->s_blocksize, 0, - bdev_nr_sectors(bt->bt_bdev)); -} - static int xfs_setup_dax_always( struct xfs_mount *mp) { - struct super_block *sb = mp->m_super; - - if (!xfs_buftarg_is_dax(sb, mp->m_ddev_targp) && - (!mp->m_rtdev_targp || !xfs_buftarg_is_dax(sb, mp->m_rtdev_targp))) { + if (!mp->m_ddev_targp->bt_daxdev && + (!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) { xfs_alert(mp, "DAX unsupported by block device. Turning off DAX."); goto disable_dax; } + if (mp->m_super->s_blocksize != PAGE_SIZE) { + xfs_alert(mp, + "DAX not supported for blocksize. Turning off DAX."); + goto disable_dax; + } + if (xfs_has_reflink(mp)) { xfs_alert(mp, "DAX and reflink cannot be used together!"); return -EINVAL; diff --git a/include/linux/dax.h b/include/linux/dax.h index e2e9a67004cb..439c3c70e347 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -111,12 +111,6 @@ int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); -bool generic_fsdax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t sectors); - -bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev, - int blocksize, sector_t start, sector_t len); static inline void fs_put_dax(struct dax_device *dax_dev) { @@ -139,14 +133,6 @@ static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) static inline void dax_remove_host(struct gendisk *disk) { } -#define generic_fsdax_supported NULL - -static inline bool dax_supported(struct dax_device *dax_dev, - struct block_device *bdev, int blocksize, sector_t start, - sector_t len) -{ - return false; -} static inline void fs_put_dax(struct dax_device *dax_dev) { -- cgit v1.2.3 From 60696eb26a37ab0199f7833ddbc1b75138c36d16 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:48 +0100 Subject: fsdax: simplify the pgoff calculation Replace the two steps of dax_iomap_sector and bdev_dax_pgoff with a single dax_iomap_pgoff helper that avoids lots of cumbersome sector conversions. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-15-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 14 -------------- fs/dax.c | 35 ++++++++++------------------------- include/linux/dax.h | 1 - 3 files changed, 10 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 90b5733f5a70..45d931aefd06 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -66,20 +66,6 @@ void dax_remove_host(struct gendisk *disk) } EXPORT_SYMBOL_GPL(dax_remove_host); -int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size, - pgoff_t *pgoff) -{ - sector_t start_sect = bdev ? get_start_sect(bdev) : 0; - phys_addr_t phys_off = (start_sect + sector) * 512; - - if (pgoff) - *pgoff = PHYS_PFN(phys_off); - if (phys_off % PAGE_SIZE || size % PAGE_SIZE) - return -EINVAL; - return 0; -} -EXPORT_SYMBOL(bdev_dax_pgoff); - /** * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax * @bdev: block device to find a dax_device for diff --git a/fs/dax.c b/fs/dax.c index e51b4129d1b6..5364549d67a4 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -709,23 +709,22 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, return __dax_invalidate_entry(mapping, index, false); } -static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos) +static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos) { - return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9; + phys_addr_t paddr = iomap->addr + (pos & PAGE_MASK) - iomap->offset; + + if (iomap->bdev) + paddr += (get_start_sect(iomap->bdev) << SECTOR_SHIFT); + return PHYS_PFN(paddr); } static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter) { - sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos); + pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos); void *vto, *kaddr; - pgoff_t pgoff; long rc; int id; - rc = bdev_dax_pgoff(iter->iomap.bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; - id = dax_read_lock(); rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL); if (rc < 0) { @@ -1013,14 +1012,10 @@ EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size, pfn_t *pfnp) { - const sector_t sector = dax_iomap_sector(iomap, pos); - pgoff_t pgoff; + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); int id, rc; long length; - rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff); - if (rc) - return rc; id = dax_read_lock(); length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size), NULL, pfnp); @@ -1129,7 +1124,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf, s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) { sector_t sector = iomap_sector(iomap, pos & PAGE_MASK); - pgoff_t pgoff; + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); long rc, id; void *kaddr; bool page_aligned = false; @@ -1140,10 +1135,6 @@ s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) (size == PAGE_SIZE)) page_aligned = true; - rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff); - if (rc) - return rc; - id = dax_read_lock(); if (page_aligned) @@ -1169,7 +1160,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, const struct iomap *iomap = &iomi->iomap; loff_t length = iomap_length(iomi); loff_t pos = iomi->pos; - struct block_device *bdev = iomap->bdev; struct dax_device *dax_dev = iomap->dax_dev; loff_t end = pos + length, done = 0; ssize_t ret = 0; @@ -1203,9 +1193,8 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, while (pos < end) { unsigned offset = pos & (PAGE_SIZE - 1); const size_t size = ALIGN(length + offset, PAGE_SIZE); - const sector_t sector = dax_iomap_sector(iomap, pos); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); ssize_t map_len; - pgoff_t pgoff; void *kaddr; if (fatal_signal_pending(current)) { @@ -1213,10 +1202,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, break; } - ret = bdev_dax_pgoff(bdev, sector, size, &pgoff); - if (ret) - break; - map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, NULL); if (map_len < 0) { diff --git a/include/linux/dax.h b/include/linux/dax.h index 439c3c70e347..324363b798ec 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -107,7 +107,6 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, #endif struct writeback_control; -int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff); #if IS_ENABLED(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); -- cgit v1.2.3 From c6f40468657d16e4010ef84bf32a761feb3469ea Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:52 +0100 Subject: fsdax: decouple zeroing from the iomap buffered I/O code Unshare the DAX and iomap buffered I/O page zeroing code. This code previously did a IS_DAX check deep inside the iomap code, which in fact was the only DAX check in the code. Instead move these checks into the callers. Most callers already have DAX special casing anyway and XFS will need it for reflink support as well. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-19-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 77 +++++++++++++++++++++++++++++++++++++++++--------- fs/ext2/inode.c | 7 +++-- fs/ext4/inode.c | 5 ++-- fs/iomap/buffered-io.c | 35 ++++++++--------------- fs/xfs/xfs_iomap.c | 7 ++++- include/linux/dax.h | 7 ++++- 6 files changed, 94 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/dax.c b/fs/dax.c index d5db1297a0bb..43d58b4219fd 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1135,24 +1135,73 @@ static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap) +static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero) { - pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); - long rc, id; - unsigned offset = offset_in_page(pos); - unsigned size = min_t(u64, PAGE_SIZE - offset, length); + const struct iomap *iomap = &iter->iomap; + const struct iomap *srcmap = iomap_iter_srcmap(iter); + loff_t pos = iter->pos; + u64 length = iomap_length(iter); + s64 written = 0; + + /* already zeroed? we're done. */ + if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) + return length; + + do { + unsigned offset = offset_in_page(pos); + unsigned size = min_t(u64, PAGE_SIZE - offset, length); + pgoff_t pgoff = dax_iomap_pgoff(iomap, pos); + long rc; + int id; - id = dax_read_lock(); - if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) - rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); - else - rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); - dax_read_unlock(id); + id = dax_read_lock(); + if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE) + rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1); + else + rc = dax_memzero(iomap->dax_dev, pgoff, offset, size); + dax_read_unlock(id); - if (rc < 0) - return rc; - return size; + if (rc < 0) + return rc; + pos += size; + length -= size; + written += size; + if (did_zero) + *did_zero = true; + } while (length > 0); + + return written; +} + +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops) +{ + struct iomap_iter iter = { + .inode = inode, + .pos = pos, + .len = len, + .flags = IOMAP_ZERO, + }; + int ret; + + while ((ret = iomap_iter(&iter, ops)) > 0) + iter.processed = dax_zero_iter(&iter, did_zero); + return ret; +} +EXPORT_SYMBOL_GPL(dax_zero_range); + +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops) +{ + unsigned int blocksize = i_blocksize(inode); + unsigned int off = pos & (blocksize - 1); + + /* Block boundary? Nothing to do */ + if (!off) + return 0; + return dax_zero_range(inode, pos, blocksize - off, did_zero, ops); } +EXPORT_SYMBOL_GPL(dax_truncate_page); static loff_t dax_iomap_iter(const struct iomap_iter *iomi, struct iov_iter *iter) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 333fa62661d5..01d69618277d 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "ext2.h" #include "acl.h" #include "xattr.h" @@ -1297,9 +1298,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize) inode_dio_wait(inode); if (IS_DAX(inode)) { - error = iomap_zero_range(inode, newsize, - PAGE_ALIGN(newsize) - newsize, NULL, - &ext2_iomap_ops); + error = dax_zero_range(inode, newsize, + PAGE_ALIGN(newsize) - newsize, NULL, + &ext2_iomap_ops); } else if (test_opt(inode->i_sb, NOBH)) error = nobh_truncate_page(inode->i_mapping, newsize, ext2_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index bfd3545f1e5d..d316a2009489 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -41,6 +41,7 @@ #include #include #include +#include #include "ext4_jbd2.h" #include "xattr.h" @@ -3780,8 +3781,8 @@ static int ext4_block_zero_page_range(handle_t *handle, length = max; if (IS_DAX(inode)) { - return iomap_zero_range(inode, from, length, NULL, - &ext4_iomap_ops); + return dax_zero_range(inode, from, length, NULL, + &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 1753c26c8e76..b1511255b4df 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -870,26 +870,8 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, } EXPORT_SYMBOL_GPL(iomap_file_unshare); -static s64 __iomap_zero_iter(struct iomap_iter *iter, loff_t pos, u64 length) -{ - struct page *page; - int status; - unsigned offset = offset_in_page(pos); - unsigned bytes = min_t(u64, PAGE_SIZE - offset, length); - - status = iomap_write_begin(iter, pos, bytes, &page); - if (status) - return status; - - zero_user(page, offset, bytes); - mark_page_accessed(page); - - return iomap_write_end(iter, pos, bytes, bytes, page); -} - static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) { - struct iomap *iomap = &iter->iomap; const struct iomap *srcmap = iomap_iter_srcmap(iter); loff_t pos = iter->pos; loff_t length = iomap_length(iter); @@ -900,12 +882,19 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero) return length; do { - s64 bytes; + unsigned offset = offset_in_page(pos); + size_t bytes = min_t(u64, PAGE_SIZE - offset, length); + struct page *page; + int status; - if (IS_DAX(iter->inode)) - bytes = dax_iomap_zero(pos, length, iomap); - else - bytes = __iomap_zero_iter(iter, pos, length); + status = iomap_write_begin(iter, pos, bytes, &page); + if (status) + return status; + + zero_user(page, offset, bytes); + mark_page_accessed(page); + + bytes = iomap_write_end(iter, pos, bytes, bytes, page); if (bytes < 0) return bytes; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6d71ae9f2ae..6a0c3b307bd7 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -28,7 +28,6 @@ #include "xfs_dquot.h" #include "xfs_reflink.h" - #define XFS_ALLOC_ALIGN(mp, off) \ (((off) >> mp->m_allocsize_log) << mp->m_allocsize_log) @@ -1321,6 +1320,9 @@ xfs_zero_range( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_zero_range(inode, pos, len, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_zero_range(inode, pos, len, did_zero, &xfs_buffered_write_iomap_ops); } @@ -1333,6 +1335,9 @@ xfs_truncate_page( { struct inode *inode = VFS_I(ip); + if (IS_DAX(inode)) + return dax_truncate_page(inode, pos, did_zero, + &xfs_buffered_write_iomap_ops); return iomap_truncate_page(inode, pos, did_zero, &xfs_buffered_write_iomap_ops); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 324363b798ec..b79036743e7f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -14,6 +14,7 @@ typedef unsigned long dax_entry_t; struct dax_device; struct gendisk; struct iomap_ops; +struct iomap_iter; struct iomap; struct dax_operations { @@ -170,6 +171,11 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie) } #endif +int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, + const struct iomap_ops *ops); +int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero, + const struct iomap_ops *ops); + #if IS_ENABLED(CONFIG_DAX) int dax_read_lock(void); void dax_read_unlock(int id); @@ -204,7 +210,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index); int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index); -s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap); static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); -- cgit v1.2.3 From 952da06375c8f3aa58474fff718d9ae8442531b9 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:58 +0100 Subject: iomap: add a IOMAP_DAX flag Add a flag so that the file system can easily detect DAX operations based just on the iomap operation requested instead of looking at inode state using IS_DAX. This will be needed to apply the to be added partition offset only for operations that actually use DAX, but not things like fiemap that are based on the block device. In the long run it should also allow turning the bdev, dax_dev and inline_data into a union. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-25-hch@lst.de Signed-off-by: Dan Williams --- fs/dax.c | 7 ++++--- fs/ext4/inode.c | 4 ++-- fs/xfs/xfs_iomap.c | 7 ++++--- fs/xfs/xfs_iomap.h | 3 ++- fs/xfs/xfs_pnfs.c | 2 +- include/linux/iomap.h | 5 +++++ 6 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/dax.c b/fs/dax.c index 43d58b4219fd..148e8b0967f3 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1180,7 +1180,7 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, .inode = inode, .pos = pos, .len = len, - .flags = IOMAP_ZERO, + .flags = IOMAP_DAX | IOMAP_ZERO, }; int ret; @@ -1308,6 +1308,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter, .inode = iocb->ki_filp->f_mapping->host, .pos = iocb->ki_pos, .len = iov_iter_count(iter), + .flags = IOMAP_DAX, }; loff_t done = 0; int ret; @@ -1461,7 +1462,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp, .inode = mapping->host, .pos = (loff_t)vmf->pgoff << PAGE_SHIFT, .len = PAGE_SIZE, - .flags = IOMAP_FAULT, + .flags = IOMAP_DAX | IOMAP_FAULT, }; vm_fault_t ret = 0; void *entry; @@ -1570,7 +1571,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, struct iomap_iter iter = { .inode = mapping->host, .len = PMD_SIZE, - .flags = IOMAP_FAULT, + .flags = IOMAP_DAX | IOMAP_FAULT, }; vm_fault_t ret = VM_FAULT_FALLBACK; pgoff_t max_pgoff; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d316a2009489..89c4a174bd39 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3349,8 +3349,8 @@ retry: * DAX and direct I/O are the only two operations that are currently * supported with IOMAP_WRITE. */ - WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT)); - if (IS_DAX(inode)) + WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT))); + if (flags & IOMAP_DAX) m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; /* * We use i_size instead of i_disksize here because delalloc writeback diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index d6beb1502f8b..0ed3e7674353 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -188,6 +188,7 @@ xfs_iomap_write_direct( struct xfs_inode *ip, xfs_fileoff_t offset_fsb, xfs_fileoff_t count_fsb, + unsigned int flags, struct xfs_bmbt_irec *imap) { struct xfs_mount *mp = ip->i_mount; @@ -229,7 +230,7 @@ xfs_iomap_write_direct( * the reserve block pool for bmbt block allocation if there is no space * left but we need to do unwritten extent conversion. */ - if (IS_DAX(VFS_I(ip))) { + if (flags & IOMAP_DAX) { bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO; if (imap->br_state == XFS_EXT_UNWRITTEN) { force = true; @@ -620,7 +621,7 @@ imap_needs_alloc( imap->br_startblock == DELAYSTARTBLOCK) return true; /* we convert unwritten extents before copying the data for DAX */ - if (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN) + if ((flags & IOMAP_DAX) && imap->br_state == XFS_EXT_UNWRITTEN) return true; return false; } @@ -826,7 +827,7 @@ allocate_blocks: xfs_iunlock(ip, lockmode); error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb, - &imap); + flags, &imap); if (error) return error; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index 657cc02290f2..e88dc162c785 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -12,7 +12,8 @@ struct xfs_inode; struct xfs_bmbt_irec; int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb, - xfs_fileoff_t count_fsb, struct xfs_bmbt_irec *imap); + xfs_fileoff_t count_fsb, unsigned int flags, + struct xfs_bmbt_irec *imap); int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool); xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip, xfs_fileoff_t end_fsb); diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c index 7ce1ea11fc3f..d6334abbc0b3 100644 --- a/fs/xfs/xfs_pnfs.c +++ b/fs/xfs/xfs_pnfs.c @@ -155,7 +155,7 @@ xfs_fs_map_blocks( xfs_iunlock(ip, lock_flags); error = xfs_iomap_write_direct(ip, offset_fsb, - end_fsb - offset_fsb, &imap); + end_fsb - offset_fsb, 0, &imap); if (error) goto out_unlock; diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6d1b08d0ae93..5b9432f9f79e 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -141,6 +141,11 @@ struct iomap_page_ops { #define IOMAP_NOWAIT (1 << 5) /* do not block */ #define IOMAP_OVERWRITE_ONLY (1 << 6) /* only pure overwrites allowed */ #define IOMAP_UNSHARE (1 << 7) /* unshare_file_range */ +#ifdef CONFIG_FS_DAX +#define IOMAP_DAX (1 << 8) /* DAX mapping */ +#else +#define IOMAP_DAX 0 +#endif /* CONFIG_FS_DAX */ struct iomap_ops { /* -- cgit v1.2.3 From cd913c76f489def1a388e3a5b10df94948ede3f5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:21:59 +0100 Subject: dax: return the partition offset from fs_dax_get_by_bdev Prepare for the removal of the block_device from the DAX I/O path by returning the partition offset from fs_dax_get_by_bdev so that the file systems have it at hand for use during I/O. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-26-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 9 ++++++--- drivers/md/dm.c | 4 ++-- fs/erofs/internal.h | 2 ++ fs/erofs/super.c | 4 ++-- fs/ext2/ext2.h | 1 + fs/ext2/super.c | 2 +- fs/ext4/ext4.h | 1 + fs/ext4/super.c | 2 +- fs/xfs/xfs_buf.c | 2 +- fs/xfs/xfs_buf.h | 1 + include/linux/dax.h | 6 ++++-- 11 files changed, 22 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 45d931aefd06..e7152a6c4cc4 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -69,17 +69,20 @@ EXPORT_SYMBOL_GPL(dax_remove_host); /** * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax * @bdev: block device to find a dax_device for + * @start_off: returns the byte offset into the dax_device that @bdev starts */ -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off) { struct dax_device *dax_dev; + u64 part_size; int id; if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; - if ((get_start_sect(bdev) * SECTOR_SIZE) % PAGE_SIZE || - (bdev_nr_sectors(bdev) * SECTOR_SIZE) % PAGE_SIZE) { + *start_off = get_start_sect(bdev) * SECTOR_SIZE; + part_size = bdev_nr_sectors(bdev) * SECTOR_SIZE; + if (*start_off % PAGE_SIZE || part_size % PAGE_SIZE) { pr_info("%pg: error: unaligned partition for dax\n", bdev); return NULL; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4eba27e75c23..4e997c02bb0a 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -637,7 +637,7 @@ static int open_table_device(struct table_device *td, dev_t dev, struct mapped_device *md) { struct block_device *bdev; - + u64 part_off; int r; BUG_ON(td->dm_dev.bdev); @@ -653,7 +653,7 @@ static int open_table_device(struct table_device *td, dev_t dev, } td->dm_dev.bdev = bdev; - td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev); + td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off); return 0; } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 3265688af7f9..c1e65346e9f1 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -51,6 +51,7 @@ struct erofs_device_info { char *path; struct block_device *bdev; struct dax_device *dax_dev; + u64 dax_part_off; u32 blocks; u32 mapped_blkaddr; @@ -109,6 +110,7 @@ struct erofs_sb_info { #endif /* CONFIG_EROFS_FS_ZIP */ struct erofs_dev_context *devs; struct dax_device *dax_dev; + u64 dax_part_off; u64 total_blocks; u32 primarydevice_blocks; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 0aed886473c8..71efce16024d 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -312,7 +312,7 @@ static int erofs_init_devices(struct super_block *sb, goto err_out; } dif->bdev = bdev; - dif->dax_dev = fs_dax_get_by_bdev(bdev); + dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off); dif->blocks = le32_to_cpu(dis->blocks); dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr); sbi->total_blocks += dif->blocks; @@ -644,7 +644,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sb->s_fs_info = sbi; sbi->opt = ctx->opt; - sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev); + sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off); sbi->devs = ctx->devs; ctx->devs = NULL; diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 3be9dd6412b7..d4f306aa5ace 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -118,6 +118,7 @@ struct ext2_sb_info { spinlock_t s_lock; struct mb_cache *s_ea_block_cache; struct dax_device *s_daxdev; + u64 s_dax_part_off; }; static inline spinlock_t * diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 7e23482862e6..94f1fbd7d3ac 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -831,7 +831,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent) } sb->s_fs_info = sbi; sbi->s_sb_block = sb_block; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); spin_lock_init(&sbi->s_lock); ret = -EINVAL; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 404dd50856e5..9cc55bcda6ba 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1697,6 +1697,7 @@ struct ext4_sb_info { */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; + u64 s_dax_part_off; #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8d7e3449c647..56228e33e52a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3913,7 +3913,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) if (!sbi->s_blockgroup_lock) goto out_free_base; - sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev); + sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off); sb->s_fs_info = sbi; sbi->s_sb = sb; sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 4d4553ffa705..bbb0fbd34e64 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1945,7 +1945,7 @@ xfs_alloc_buftarg( btp->bt_mount = mp; btp->bt_dev = bdev->bd_dev; btp->bt_bdev = bdev; - btp->bt_daxdev = fs_dax_get_by_bdev(bdev); + btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off); /* * Buffer IO error rate limiting. Limit it to no more than 10 messages diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index bd7f709f0d23..edcb6254fa6a 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -89,6 +89,7 @@ typedef struct xfs_buftarg { dev_t bt_dev; struct block_device *bt_bdev; struct dax_device *bt_daxdev; + u64 bt_dax_part_off; struct xfs_mount *bt_mount; unsigned int bt_meta_sectorsize; size_t bt_meta_sectormask; diff --git a/include/linux/dax.h b/include/linux/dax.h index b79036743e7f..f6f353382cc9 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -117,7 +117,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) put_dax(dax_dev); } -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev); +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off); int dax_writeback_mapping_range(struct address_space *mapping, struct dax_device *dax_dev, struct writeback_control *wbc); @@ -138,7 +139,8 @@ static inline void fs_put_dax(struct dax_device *dax_dev) { } -static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) +static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off) { return NULL; } -- cgit v1.2.3 From 2ede892342b3c628991ff1b9060108a7edd92d94 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Nov 2021 11:22:01 +0100 Subject: dax: fix up some of the block device related ifdefs The DAX device <-> block device association is only enabled if CONFIG_BLOCK is enabled. Update dax.h to account for that and use the right conditions for the fs_put_dax stub as well. Signed-off-by: Christoph Hellwig Reviewed-by: Dan Williams Reviewed-by: Darrick J. Wong Link: https://lore.kernel.org/r/20211129102203.2243509-28-hch@lst.de Signed-off-by: Dan Williams --- include/linux/dax.h | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dax.h b/include/linux/dax.h index f6f353382cc9..87ae4c9b1d65 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -108,24 +108,15 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, #endif struct writeback_control; -#if IS_ENABLED(CONFIG_FS_DAX) +#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); void dax_remove_host(struct gendisk *disk); - +struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, + u64 *start_off); static inline void fs_put_dax(struct dax_device *dax_dev) { put_dax(dax_dev); } - -struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, - u64 *start_off); -int dax_writeback_mapping_range(struct address_space *mapping, - struct dax_device *dax_dev, struct writeback_control *wbc); - -struct page *dax_layout_busy_page(struct address_space *mapping); -struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); -dax_entry_t dax_lock_page(struct page *page); -void dax_unlock_page(struct page *page, dax_entry_t cookie); #else static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) { @@ -134,17 +125,25 @@ static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk) static inline void dax_remove_host(struct gendisk *disk) { } - -static inline void fs_put_dax(struct dax_device *dax_dev) -{ -} - static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off) { return NULL; } +static inline void fs_put_dax(struct dax_device *dax_dev) +{ +} +#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */ +#if IS_ENABLED(CONFIG_FS_DAX) +int dax_writeback_mapping_range(struct address_space *mapping, + struct dax_device *dax_dev, struct writeback_control *wbc); + +struct page *dax_layout_busy_page(struct address_space *mapping); +struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end); +dax_entry_t dax_lock_page(struct page *page); +void dax_unlock_page(struct page *page, dax_entry_t cookie); +#else static inline struct page *dax_layout_busy_page(struct address_space *mapping) { return NULL; -- cgit v1.2.3 From 866de407444398bc8140ea70de1dba5f91cc34ac Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 3 Dec 2021 13:30:01 +0800 Subject: bpf: Disallow BPF_LOG_KERNEL log level for bpf(BPF_BTF_LOAD) BPF_LOG_KERNEL is only used internally, so disallow bpf_btf_load() to set log level as BPF_LOG_KERNEL. The same checking has already been done in bpf_check(), so factor out a helper to check the validity of log attributes and use it in both places. Fixes: 8580ac9404f6 ("bpf: Process in-kernel BTF") Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211203053001.740945-1-houtao1@huawei.com --- include/linux/bpf_verifier.h | 7 +++++++ kernel/bpf/btf.c | 3 +-- kernel/bpf/verifier.c | 6 +++--- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c8a78e830fca..182b16a91084 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -396,6 +396,13 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) log->level == BPF_LOG_KERNEL); } +static inline bool +bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) +{ + return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && + log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); +} + #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2a902a946f70..36a5cc0f53c6 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4473,8 +4473,7 @@ static struct btf *btf_parse(bpfptr_t btf_data, u32 btf_data_size, log->len_total = log_size; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || - !log->level || !log->ubuf) { + if (!bpf_verifier_log_attr_valid(log)) { err = -EINVAL; goto errout; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6522ffdea487..1126b75fe650 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14050,11 +14050,11 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) log->ubuf = (char __user *) (unsigned long) attr->log_buf; log->len_total = attr->log_size; - ret = -EINVAL; /* log attributes have to be sane */ - if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 || - !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK) + if (!bpf_verifier_log_attr_valid(log)) { + ret = -EINVAL; goto err_unlock; + } } if (IS_ERR(btf_vmlinux)) { -- cgit v1.2.3 From b80892ca022e9eb484771a66eb68e12364695a2a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 28 Oct 2021 17:10:17 +0200 Subject: memremap: remove support for external pgmap refcounts No driver is left using the external pgmap refcount, so remove the code to support it. Signed-off-by: Christoph Hellwig Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211028151017.50234-1-hch@lst.de Signed-off-by: Dan Williams --- drivers/pci/p2pdma.c | 2 +- include/linux/memremap.h | 18 ++---------- mm/memremap.c | 59 ++++++++------------------------------- tools/testing/nvdimm/test/iomap.c | 43 ++++++++-------------------- 4 files changed, 28 insertions(+), 94 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 8d47cb7218d1..454d5f6f16ff 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -219,7 +219,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr, pci_bus_address(pdev, bar) + offset, range_len(&pgmap->range), dev_to_node(&pdev->dev), - pgmap->ref); + &pgmap->ref); if (error) goto pages_free; diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..a8bc588fe7aa 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -72,16 +72,6 @@ struct dev_pagemap_ops { */ void (*page_free)(struct page *page); - /* - * Transition the refcount in struct dev_pagemap to the dead state. - */ - void (*kill)(struct dev_pagemap *pgmap); - - /* - * Wait for refcount in struct dev_pagemap to be idle and reap it. - */ - void (*cleanup)(struct dev_pagemap *pgmap); - /* * Used for private (un-addressable) device memory only. Must migrate * the page back to a CPU accessible page. @@ -95,8 +85,7 @@ struct dev_pagemap_ops { * struct dev_pagemap - metadata for ZONE_DEVICE mappings * @altmap: pre-allocated/reserved memory for vmemmap allocations * @ref: reference count that pins the devm_memremap_pages() mapping - * @internal_ref: internal reference if @ref is not provided by the caller - * @done: completion for @internal_ref + * @done: completion for @ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior * @ops: method table @@ -109,8 +98,7 @@ struct dev_pagemap_ops { */ struct dev_pagemap { struct vmem_altmap altmap; - struct percpu_ref *ref; - struct percpu_ref internal_ref; + struct percpu_ref ref; struct completion done; enum memory_type type; unsigned int flags; @@ -191,7 +179,7 @@ static inline unsigned long memremap_compat_align(void) static inline void put_dev_pagemap(struct dev_pagemap *pgmap) { if (pgmap) - percpu_ref_put(pgmap->ref); + percpu_ref_put(&pgmap->ref); } #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/mm/memremap.c b/mm/memremap.c index 5a66a71ab591..643965da13a6 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -112,30 +112,6 @@ static unsigned long pfn_next(unsigned long pfn) #define for_each_device_pfn(pfn, map, i) \ for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) -static void dev_pagemap_kill(struct dev_pagemap *pgmap) -{ - if (pgmap->ops && pgmap->ops->kill) - pgmap->ops->kill(pgmap); - else - percpu_ref_kill(pgmap->ref); -} - -static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) -{ - if (pgmap->ops && pgmap->ops->cleanup) { - pgmap->ops->cleanup(pgmap); - } else { - wait_for_completion(&pgmap->done); - percpu_ref_exit(pgmap->ref); - } - /* - * Undo the pgmap ref assignment for the internal case as the - * caller may re-enable the same pgmap. - */ - if (pgmap->ref == &pgmap->internal_ref) - pgmap->ref = NULL; -} - static void pageunmap_range(struct dev_pagemap *pgmap, int range_id) { struct range *range = &pgmap->ranges[range_id]; @@ -167,11 +143,12 @@ void memunmap_pages(struct dev_pagemap *pgmap) unsigned long pfn; int i; - dev_pagemap_kill(pgmap); + percpu_ref_kill(&pgmap->ref); for (i = 0; i < pgmap->nr_range; i++) for_each_device_pfn(pfn, pgmap, i) put_page(pfn_to_page(pfn)); - dev_pagemap_cleanup(pgmap); + wait_for_completion(&pgmap->done); + percpu_ref_exit(&pgmap->ref); for (i = 0; i < pgmap->nr_range; i++) pageunmap_range(pgmap, i); @@ -188,8 +165,7 @@ static void devm_memremap_pages_release(void *data) static void dev_pagemap_percpu_release(struct percpu_ref *ref) { - struct dev_pagemap *pgmap = - container_of(ref, struct dev_pagemap, internal_ref); + struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref); complete(&pgmap->done); } @@ -295,8 +271,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id) - - pfn_first(pgmap, range_id)); + percpu_ref_get_many(&pgmap->ref, + pfn_end(pgmap, range_id) - pfn_first(pgmap, range_id)); return 0; err_add_memory: @@ -362,22 +338,11 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid) break; } - if (!pgmap->ref) { - if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) - return ERR_PTR(-EINVAL); - - init_completion(&pgmap->done); - error = percpu_ref_init(&pgmap->internal_ref, - dev_pagemap_percpu_release, 0, GFP_KERNEL); - if (error) - return ERR_PTR(error); - pgmap->ref = &pgmap->internal_ref; - } else { - if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); - } - } + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0, + GFP_KERNEL); + if (error) + return ERR_PTR(error); devmap_managed_enable_get(pgmap); @@ -486,7 +451,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, /* fall back to slow path lookup */ rcu_read_lock(); pgmap = xa_load(&pgmap_array, PHYS_PFN(phys)); - if (pgmap && !percpu_ref_tryget_live(pgmap->ref)) + if (pgmap && !percpu_ref_tryget_live(&pgmap->ref)) pgmap = NULL; rcu_read_unlock(); diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c index ed563bdd88f3..b752ce47ead3 100644 --- a/tools/testing/nvdimm/test/iomap.c +++ b/tools/testing/nvdimm/test/iomap.c @@ -100,25 +100,17 @@ static void nfit_test_kill(void *_pgmap) { struct dev_pagemap *pgmap = _pgmap; - WARN_ON(!pgmap || !pgmap->ref); - - if (pgmap->ops && pgmap->ops->kill) - pgmap->ops->kill(pgmap); - else - percpu_ref_kill(pgmap->ref); - - if (pgmap->ops && pgmap->ops->cleanup) { - pgmap->ops->cleanup(pgmap); - } else { - wait_for_completion(&pgmap->done); - percpu_ref_exit(pgmap->ref); - } + WARN_ON(!pgmap); + + percpu_ref_kill(&pgmap->ref); + + wait_for_completion(&pgmap->done); + percpu_ref_exit(&pgmap->ref); } static void dev_pagemap_percpu_release(struct percpu_ref *ref) { - struct dev_pagemap *pgmap = - container_of(ref, struct dev_pagemap, internal_ref); + struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref); complete(&pgmap->done); } @@ -132,22 +124,11 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (!nfit_res) return devm_memremap_pages(dev, pgmap); - if (!pgmap->ref) { - if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup)) - return ERR_PTR(-EINVAL); - - init_completion(&pgmap->done); - error = percpu_ref_init(&pgmap->internal_ref, - dev_pagemap_percpu_release, 0, GFP_KERNEL); - if (error) - return ERR_PTR(error); - pgmap->ref = &pgmap->internal_ref; - } else { - if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) { - WARN(1, "Missing reference count teardown definition\n"); - return ERR_PTR(-EINVAL); - } - } + init_completion(&pgmap->done); + error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0, + GFP_KERNEL); + if (error) + return ERR_PTR(error); error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap); if (error) -- cgit v1.2.3 From 02e4079913500f24ceb082d8d87d8665f044b298 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:17:04 +0100 Subject: fs: remove unused low-level mapping helpers Now that we ported all places to use the new low-level mapping helpers that are able to support filesystems mounted with an idmapping we can remove the old low-level mapping helpers. With the removal of these old helpers we also conclude the renaming of the mapping helpers we started in commit a65e58e791a1 ("fs: document and rename fsid helpers"). Link: https://lore.kernel.org/r/20211123114227.3124056-8-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-8-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-8-brauner@kernel.org Cc: Seth Forshee Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- include/linux/mnt_idmapping.h | 56 ------------------------------------------- 1 file changed, 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 60341cd33ccc..0c6ab3f4c952 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -13,62 +13,6 @@ struct user_namespace; */ extern struct user_namespace init_user_ns; -/** - * kuid_into_mnt - map a kuid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_into_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return make_kuid(mnt_userns, __kuid_val(kuid)); -} - -/** - * kgid_into_mnt - map a kgid down into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_into_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return make_kgid(mnt_userns, __kgid_val(kgid)); -} - -/** - * kuid_from_mnt - map a kuid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kuid: kuid to be mapped - * - * Return: @kuid mapped up according to @mnt_userns. - * If @kuid has no mapping INVALID_UID is returned. - */ -static inline kuid_t kuid_from_mnt(struct user_namespace *mnt_userns, - kuid_t kuid) -{ - return KUIDT_INIT(from_kuid(mnt_userns, kuid)); -} - -/** - * kgid_from_mnt - map a kgid up into a mnt_userns - * @mnt_userns: user namespace of the relevant mount - * @kgid: kgid to be mapped - * - * Return: @kgid mapped up according to @mnt_userns. - * If @kgid has no mapping INVALID_GID is returned. - */ -static inline kgid_t kgid_from_mnt(struct user_namespace *mnt_userns, - kgid_t kgid) -{ - return KGIDT_INIT(from_kgid(mnt_userns, kgid)); -} - /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check -- cgit v1.2.3 From 209188ce75d0d357c292f6bb81d712acdd4e7db7 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:17:05 +0100 Subject: fs: port higher-level mapping helpers Enable the mapped_fs{g,u}id() helpers to support filesystems mounted with an idmapping. Apart from core mapping helpers that use mapped_fs{g,u}id() to initialize struct inode's i_{g,u}id fields xfs is the only place that uses these low-level helpers directly. The patch only extends the helpers to be able to take the filesystem idmapping into account. Since we don't actually yet pass the filesystem's idmapping in no functional changes happen. This will happen in a final patch. Link: https://lore.kernel.org/r/20211123114227.3124056-9-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-9-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-9-brauner@kernel.org Cc: Seth Forshee Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- fs/xfs/xfs_inode.c | 8 ++++---- fs/xfs/xfs_symlink.c | 4 ++-- include/linux/fs.h | 8 ++++---- include/linux/mnt_idmapping.h | 12 ++++++++---- 4 files changed, 18 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 64b9bf334806..5ca689459bed 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -988,8 +988,8 @@ xfs_create( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) @@ -1142,8 +1142,8 @@ xfs_create_tmpfile( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c index fc2c6a404647..a31d2e5d0321 100644 --- a/fs/xfs/xfs_symlink.c +++ b/fs/xfs/xfs_symlink.c @@ -184,8 +184,8 @@ xfs_symlink( /* * Make sure that we have allocated dquot(s) on disk. */ - error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns), - mapped_fsgid(mnt_userns), prid, + error = xfs_qm_vop_dqalloc(dp, mapped_fsuid(mnt_userns, &init_user_ns), + mapped_fsgid(mnt_userns, &init_user_ns), prid, XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp, &pdqp); if (error) diff --git a/include/linux/fs.h b/include/linux/fs.h index 57aee6ebba72..e1f28f757f1b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1664,7 +1664,7 @@ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns); + inode->i_uid = mapped_fsuid(mnt_userns, &init_user_ns); } /** @@ -1678,7 +1678,7 @@ static inline void inode_fsuid_set(struct inode *inode, static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns); + inode->i_gid = mapped_fsgid(mnt_userns, &init_user_ns); } /** @@ -1699,10 +1699,10 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, kuid_t kuid; kgid_t kgid; - kuid = mapped_fsuid(mnt_userns); + kuid = mapped_fsuid(mnt_userns, &init_user_ns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns); + kgid = mapped_fsgid(mnt_userns, &init_user_ns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h index 0c6ab3f4c952..ee5a217de2a8 100644 --- a/include/linux/mnt_idmapping.h +++ b/include/linux/mnt_idmapping.h @@ -196,6 +196,7 @@ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, /** * mapped_fsuid - return caller's fsuid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsuid. A common example is initializing the i_uid field of @@ -205,14 +206,16 @@ static inline kgid_t mapped_kgid_user(struct user_namespace *mnt_userns, * * Return: the caller's current fsuid mapped up according to @mnt_userns. */ -static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) +static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { - return mapped_kuid_user(mnt_userns, &init_user_ns, current_fsuid()); + return mapped_kuid_user(mnt_userns, fs_userns, current_fsuid()); } /** * mapped_fsgid - return caller's fsgid mapped up into a mnt_userns * @mnt_userns: the mount's idmapping + * @fs_userns: the filesystem's idmapping * * Use this helper to initialize a new vfs or filesystem object based on * the caller's fsgid. A common example is initializing the i_gid field of @@ -222,9 +225,10 @@ static inline kuid_t mapped_fsuid(struct user_namespace *mnt_userns) * * Return: the caller's current fsgid mapped up according to @mnt_userns. */ -static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns) +static inline kgid_t mapped_fsgid(struct user_namespace *mnt_userns, + struct user_namespace *fs_userns) { - return mapped_kgid_user(mnt_userns, &init_user_ns, current_fsgid()); + return mapped_kgid_user(mnt_userns, fs_userns, current_fsgid()); } #endif /* _LINUX_MNT_IDMAPPING_H */ -- cgit v1.2.3 From a1ec9040a2a9122605ac26e5725c6de019184419 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:17:06 +0100 Subject: fs: add i_user_ns() helper Since we'll be passing the filesystem's idmapping in even more places in the following patches and we do already dereference struct inode to get to the filesystem's idmapping multiple times add a tiny helper. Link: https://lore.kernel.org/r/20211123114227.3124056-10-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-10-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-10-brauner@kernel.org Cc: Seth Forshee Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Amir Goldstein Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- include/linux/fs.h | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index e1f28f757f1b..3d6d514943ab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1600,6 +1600,11 @@ struct super_block { struct list_head s_inodes_wb; /* writeback inodes */ } __randomize_layout; +static inline struct user_namespace *i_user_ns(const struct inode *inode) +{ + return inode->i_sb->s_user_ns; +} + /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can * instead deal with the raw numeric values that are stored @@ -1607,22 +1612,22 @@ struct super_block { */ static inline uid_t i_uid_read(const struct inode *inode) { - return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); + return from_kuid(i_user_ns(inode), inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { - return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); + return from_kgid(i_user_ns(inode), inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { - inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); + inode->i_uid = make_kuid(i_user_ns(inode), uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { - inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); + inode->i_gid = make_kgid(i_user_ns(inode), gid); } /** -- cgit v1.2.3 From bd303368b776eead1c29e6cdda82bde7128b82a7 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 3 Dec 2021 12:17:07 +0100 Subject: fs: support mapped mounts of mapped filesystems In previous patches we added new and modified existing helpers to handle idmapped mounts of filesystems mounted with an idmapping. In this final patch we convert all relevant places in the vfs to actually pass the filesystem's idmapping into these helpers. With this the vfs is in shape to handle idmapped mounts of filesystems mounted with an idmapping. Note that this is just the generic infrastructure. Actually adding support for idmapped mounts to a filesystem mountable with an idmapping is follow-up work. In this patch we extend the definition of an idmapped mount from a mount that that has the initial idmapping attached to it to a mount that has an idmapping attached to it which is not the same as the idmapping the filesystem was mounted with. As before we do not allow the initial idmapping to be attached to a mount. In addition this patch prevents that the idmapping the filesystem was mounted with can be attached to a mount created based on this filesystem. This has multiple reasons and advantages. First, attaching the initial idmapping or the filesystem's idmapping doesn't make much sense as in both cases the values of the i_{g,u}id and other places where k{g,u}ids are used do not change. Second, a user that really wants to do this for whatever reason can just create a separate dedicated identical idmapping to attach to the mount. Third, we can continue to use the initial idmapping as an indicator that a mount is not idmapped allowing us to continue to keep passing the initial idmapping into the mapping helpers to tell them that something isn't an idmapped mount even if the filesystem is mounted with an idmapping. Link: https://lore.kernel.org/r/20211123114227.3124056-11-brauner@kernel.org (v1) Link: https://lore.kernel.org/r/20211130121032.3753852-11-brauner@kernel.org (v2) Link: https://lore.kernel.org/r/20211203111707.3901969-11-brauner@kernel.org Cc: Seth Forshee Cc: Amir Goldstein Cc: Christoph Hellwig Cc: Al Viro CC: linux-fsdevel@vger.kernel.org Reviewed-by: Seth Forshee Signed-off-by: Christian Brauner --- fs/namespace.c | 51 ++++++++++++++++++++++++++++++++++++++------------- fs/open.c | 7 ++++--- fs/posix_acl.c | 8 ++++---- include/linux/fs.h | 17 +++++++++-------- security/commoncap.c | 9 ++++----- 5 files changed, 59 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/namespace.c b/fs/namespace.c index 4994b816a74c..08266a35c0c1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -31,6 +31,7 @@ #include #include #include +#include #include "pnode.h" #include "internal.h" @@ -561,7 +562,7 @@ static void free_vfsmnt(struct mount *mnt) struct user_namespace *mnt_userns; mnt_userns = mnt_user_ns(&mnt->mnt); - if (mnt_userns != &init_user_ns) + if (!initial_idmapping(mnt_userns)) put_user_ns(mnt_userns); kfree_const(mnt->mnt_devname); #ifdef CONFIG_SMP @@ -965,6 +966,7 @@ static struct mount *skip_mnt_tree(struct mount *p) struct vfsmount *vfs_create_mount(struct fs_context *fc) { struct mount *mnt; + struct user_namespace *fs_userns; if (!fc->root) return ERR_PTR(-EINVAL); @@ -982,6 +984,10 @@ struct vfsmount *vfs_create_mount(struct fs_context *fc) mnt->mnt_mountpoint = mnt->mnt.mnt_root; mnt->mnt_parent = mnt; + fs_userns = mnt->mnt.mnt_sb->s_user_ns; + if (!initial_idmapping(fs_userns)) + mnt->mnt.mnt_userns = get_user_ns(fs_userns); + lock_mount_hash(); list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts); unlock_mount_hash(); @@ -1072,7 +1078,7 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, atomic_inc(&sb->s_active); mnt->mnt.mnt_userns = mnt_user_ns(&old->mnt); - if (mnt->mnt.mnt_userns != &init_user_ns) + if (!initial_idmapping(mnt->mnt.mnt_userns)) mnt->mnt.mnt_userns = get_user_ns(mnt->mnt.mnt_userns); mnt->mnt.mnt_sb = sb; mnt->mnt.mnt_root = dget(root); @@ -3927,10 +3933,18 @@ static unsigned int recalc_flags(struct mount_kattr *kattr, struct mount *mnt) static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { struct vfsmount *m = &mnt->mnt; + struct user_namespace *fs_userns = m->mnt_sb->s_user_ns; if (!kattr->mnt_userns) return 0; + /* + * Creating an idmapped mount with the filesystem wide idmapping + * doesn't make sense so block that. We don't allow mushy semantics. + */ + if (kattr->mnt_userns == fs_userns) + return -EINVAL; + /* * Once a mount has been idmapped we don't allow it to change its * mapping. It makes things simpler and callers can just create @@ -3943,12 +3957,8 @@ static int can_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) if (!(m->mnt_sb->s_type->fs_flags & FS_ALLOW_IDMAP)) return -EINVAL; - /* Don't yet support filesystem mountable in user namespaces. */ - if (m->mnt_sb->s_user_ns != &init_user_ns) - return -EINVAL; - /* We're not controlling the superblock. */ - if (!capable(CAP_SYS_ADMIN)) + if (!ns_capable(fs_userns, CAP_SYS_ADMIN)) return -EPERM; /* Mount has already been visible in the filesystem hierarchy. */ @@ -4002,14 +4012,27 @@ out: static void do_idmap_mount(const struct mount_kattr *kattr, struct mount *mnt) { - struct user_namespace *mnt_userns; + struct user_namespace *mnt_userns, *old_mnt_userns; if (!kattr->mnt_userns) return; + /* + * We're the only ones able to change the mount's idmapping. So + * mnt->mnt.mnt_userns is stable and we can retrieve it directly. + */ + old_mnt_userns = mnt->mnt.mnt_userns; + mnt_userns = get_user_ns(kattr->mnt_userns); /* Pairs with smp_load_acquire() in mnt_user_ns(). */ smp_store_release(&mnt->mnt.mnt_userns, mnt_userns); + + /* + * If this is an idmapped filesystem drop the reference we've taken + * in vfs_create_mount() before. + */ + if (!initial_idmapping(old_mnt_userns)) + put_user_ns(old_mnt_userns); } static void mount_setattr_commit(struct mount_kattr *kattr, @@ -4133,13 +4156,15 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, } /* - * The init_user_ns is used to indicate that a vfsmount is not idmapped. - * This is simpler than just having to treat NULL as unmapped. Users - * wanting to idmap a mount to init_user_ns can just use a namespace - * with an identity mapping. + * The initial idmapping cannot be used to create an idmapped + * mount. We use the initial idmapping as an indicator of a mount + * that is not idmapped. It can simply be passed into helpers that + * are aware of idmapped mounts as a convenient shortcut. A user + * can just create a dedicated identity mapping to achieve the same + * result. */ mnt_userns = container_of(ns, struct user_namespace, ns); - if (mnt_userns == &init_user_ns) { + if (initial_idmapping(mnt_userns)) { err = -EPERM; goto out_fput; } diff --git a/fs/open.c b/fs/open.c index 40a00e71865b..9ff2f621b760 100644 --- a/fs/open.c +++ b/fs/open.c @@ -641,7 +641,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode) int chown_common(const struct path *path, uid_t user, gid_t group) { - struct user_namespace *mnt_userns; + struct user_namespace *mnt_userns, *fs_userns; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; int error; @@ -653,8 +653,9 @@ int chown_common(const struct path *path, uid_t user, gid_t group) gid = make_kgid(current_user_ns(), group); mnt_userns = mnt_user_ns(path->mnt); - uid = mapped_kuid_user(mnt_userns, &init_user_ns, uid); - gid = mapped_kgid_user(mnt_userns, &init_user_ns, gid); + fs_userns = i_user_ns(inode); + uid = mapped_kuid_user(mnt_userns, fs_userns, uid); + gid = mapped_kgid_user(mnt_userns, fs_userns, gid); retry_deleg: newattrs.ia_valid = ATTR_CTIME; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 4b5fb9a9b90f..80acb6885cf9 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -376,8 +376,8 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, break; case ACL_USER: uid = mapped_kuid_fs(mnt_userns, - &init_user_ns, - pa->e_uid); + i_user_ns(inode), + pa->e_uid); if (uid_eq(uid, current_fsuid())) goto mask; break; @@ -391,8 +391,8 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode, break; case ACL_GROUP: gid = mapped_kgid_fs(mnt_userns, - &init_user_ns, - pa->e_gid); + i_user_ns(inode), + pa->e_gid); if (in_group_p(gid)) { found = 1; if ((pa->e_perm & want) == want) diff --git a/include/linux/fs.h b/include/linux/fs.h index 3d6d514943ab..493b87e3616b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1641,7 +1641,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kuid_fs(mnt_userns, &init_user_ns, inode->i_uid); + return mapped_kuid_fs(mnt_userns, i_user_ns(inode), inode->i_uid); } /** @@ -1655,7 +1655,7 @@ static inline kuid_t i_uid_into_mnt(struct user_namespace *mnt_userns, static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, const struct inode *inode) { - return mapped_kgid_fs(mnt_userns, &init_user_ns, inode->i_gid); + return mapped_kgid_fs(mnt_userns, i_user_ns(inode), inode->i_gid); } /** @@ -1669,7 +1669,7 @@ static inline kgid_t i_gid_into_mnt(struct user_namespace *mnt_userns, static inline void inode_fsuid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_uid = mapped_fsuid(mnt_userns, &init_user_ns); + inode->i_uid = mapped_fsuid(mnt_userns, i_user_ns(inode)); } /** @@ -1683,7 +1683,7 @@ static inline void inode_fsuid_set(struct inode *inode, static inline void inode_fsgid_set(struct inode *inode, struct user_namespace *mnt_userns) { - inode->i_gid = mapped_fsgid(mnt_userns, &init_user_ns); + inode->i_gid = mapped_fsgid(mnt_userns, i_user_ns(inode)); } /** @@ -1704,10 +1704,10 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb, kuid_t kuid; kgid_t kgid; - kuid = mapped_fsuid(mnt_userns, &init_user_ns); + kuid = mapped_fsuid(mnt_userns, fs_userns); if (!uid_valid(kuid)) return false; - kgid = mapped_fsgid(mnt_userns, &init_user_ns); + kgid = mapped_fsgid(mnt_userns, fs_userns); if (!gid_valid(kgid)) return false; return kuid_has_mapping(fs_userns, kuid) && @@ -2653,13 +2653,14 @@ static inline struct user_namespace *file_mnt_user_ns(struct file *file) * is_idmapped_mnt - check whether a mount is mapped * @mnt: the mount to check * - * If @mnt has an idmapping attached to it @mnt is mapped. + * If @mnt has an idmapping attached different from the + * filesystem's idmapping then @mnt is mapped. * * Return: true if mount is mapped, false if not. */ static inline bool is_idmapped_mnt(const struct vfsmount *mnt) { - return mnt_user_ns(mnt) != &init_user_ns; + return mnt_user_ns(mnt) != mnt->mnt_sb->s_user_ns; } extern long vfs_truncate(const struct path *, loff_t); diff --git a/security/commoncap.c b/security/commoncap.c index d288a62e2999..5fc8986c3c77 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -419,7 +419,7 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, kroot = make_kuid(fs_ns, root); /* If this is an idmapped mount shift the kuid. */ - kroot = mapped_kuid_fs(mnt_userns, &init_user_ns, kroot); + kroot = mapped_kuid_fs(mnt_userns, fs_ns, kroot); /* If the root kuid maps to a valid uid in current ns, then return * this as a nscap. */ @@ -556,13 +556,12 @@ int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry, return -EINVAL; if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP)) return -EPERM; - if (size == XATTR_CAPS_SZ_2 && (mnt_userns == &init_user_ns)) + if (size == XATTR_CAPS_SZ_2 && (mnt_userns == fs_ns)) if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) /* user is privileged, just write the v2 */ return size; - rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, - &init_user_ns); + rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns, fs_ns); if (!uid_valid(rootid)) return -EINVAL; @@ -703,7 +702,7 @@ int get_vfs_caps_from_disk(struct user_namespace *mnt_userns, /* Limit the caps to the mounter of the filesystem * or the more limited uid specified in the xattr. */ - rootkuid = mapped_kuid_fs(mnt_userns, &init_user_ns, rootkuid); + rootkuid = mapped_kuid_fs(mnt_userns, fs_ns, rootkuid); if (!rootid_owns_currentns(rootkuid)) return -ENODATA; -- cgit v1.2.3 From 019cd8a9e3bcbbf6bac8036a9ae545f7858e0c08 Mon Sep 17 00:00:00 2001 From: Jonathan Corbet Date: Tue, 2 Nov 2021 16:02:01 -0600 Subject: ARM: ixp4xx: remove unused header file pata_ixp4xx_cf.h Commit b00ced38e317 ("ARM: ixp4xx: Delete Avila boardfiles") removed the last use of but left the header file in place. Nothing uses this file, delete it now. Cc: Linus Walleij Cc: Arnd Bergmann Signed-off-by: Jonathan Corbet Acked-by: Arnd Bergmann Signed-off-by: Linus Walleij --- include/linux/platform_data/pata_ixp4xx_cf.h | 21 --------------------- 1 file changed, 21 deletions(-) delete mode 100644 include/linux/platform_data/pata_ixp4xx_cf.h (limited to 'include/linux') diff --git a/include/linux/platform_data/pata_ixp4xx_cf.h b/include/linux/platform_data/pata_ixp4xx_cf.h deleted file mode 100644 index e60fa41da4a5..000000000000 --- a/include/linux/platform_data/pata_ixp4xx_cf.h +++ /dev/null @@ -1,21 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __PLATFORM_DATA_PATA_IXP4XX_H -#define __PLATFORM_DATA_PATA_IXP4XX_H - -#include - -/* - * This structure provide a means for the board setup code - * to give information to th pata_ixp4xx driver. It is - * passed as platform_data. - */ -struct ixp4xx_pata_data { - volatile u32 *cs0_cfg; - volatile u32 *cs1_cfg; - unsigned long cs0_bits; - unsigned long cs1_bits; - void __iomem *cmd; - void __iomem *ctl; -}; - -#endif -- cgit v1.2.3 From 52f982f00b220d097a71a23c149a1d18efc08e63 Mon Sep 17 00:00:00 2001 From: Ondrej Mosnacek Date: Mon, 6 Dec 2021 14:24:06 +0100 Subject: security,selinux: remove security_add_mnt_opt() Its last user has been removed in commit f2aedb713c28 ("NFS: Add fs_context support."). Signed-off-by: Ondrej Mosnacek Reviewed-by: Casey Schaufler Signed-off-by: Paul Moore --- include/linux/lsm_hook_defs.h | 2 -- include/linux/lsm_hooks.h | 2 -- include/linux/security.h | 8 -------- security/security.c | 8 -------- security/selinux/hooks.c | 39 --------------------------------------- 5 files changed, 59 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ae2228f0711d..a5a724c308d8 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -78,8 +78,6 @@ LSM_HOOK(int, 0, sb_set_mnt_opts, struct super_block *sb, void *mnt_opts, LSM_HOOK(int, 0, sb_clone_mnt_opts, const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags) -LSM_HOOK(int, 0, sb_add_mnt_opt, const char *option, const char *val, - int len, void **mnt_opts) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 52c1990644b9..3bf5c658bc44 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -180,8 +180,6 @@ * Copy all security options from a given superblock to another * @oldsb old superblock which contain information to clone * @newsb new superblock which needs filled in - * @sb_add_mnt_opt: - * Add one mount @option to @mnt_opts. * @sb_parse_opts_str: * Parse a string of security data filling in the opts structure * @options string containing all mount options known by the LSM diff --git a/include/linux/security.h b/include/linux/security.h index bb301963e333..6d72772182c8 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -313,8 +313,6 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, struct super_block *newsb, unsigned long kern_flags, unsigned long *set_kern_flags); -int security_add_mnt_opt(const char *option, const char *val, - int len, void **mnt_opts); int security_move_mount(const struct path *from_path, const struct path *to_path); int security_dentry_init_security(struct dentry *dentry, int mode, const struct qstr *name, @@ -711,12 +709,6 @@ static inline int security_sb_clone_mnt_opts(const struct super_block *oldsb, return 0; } -static inline int security_add_mnt_opt(const char *option, const char *val, - int len, void **mnt_opts) -{ - return 0; -} - static inline int security_move_mount(const struct path *from_path, const struct path *to_path) { diff --git a/security/security.c b/security/security.c index edb922b8bf4a..3d4eb474f35b 100644 --- a/security/security.c +++ b/security/security.c @@ -994,14 +994,6 @@ int security_sb_clone_mnt_opts(const struct super_block *oldsb, } EXPORT_SYMBOL(security_sb_clone_mnt_opts); -int security_add_mnt_opt(const char *option, const char *val, int len, - void **mnt_opts) -{ - return call_int_hook(sb_add_mnt_opt, -EINVAL, - option, val, len, mnt_opts); -} -EXPORT_SYMBOL(security_add_mnt_opt); - int security_move_mount(const struct path *from_path, const struct path *to_path) { return call_int_hook(move_mount, 0, from_path, to_path); diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 726175254f60..818ce976ff6c 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1010,44 +1010,6 @@ Einval: return -EINVAL; } -static int selinux_add_mnt_opt(const char *option, const char *val, int len, - void **mnt_opts) -{ - int token = Opt_error; - int rc, i; - - for (i = 0; i < ARRAY_SIZE(tokens); i++) { - if (strcmp(option, tokens[i].name) == 0) { - token = tokens[i].opt; - break; - } - } - - if (token == Opt_error) - return -EINVAL; - - if (token != Opt_seclabel) { - val = kmemdup_nul(val, len, GFP_KERNEL); - if (!val) { - rc = -ENOMEM; - goto free_opt; - } - } - rc = selinux_add_opt(token, val, mnt_opts); - if (unlikely(rc)) { - kfree(val); - goto free_opt; - } - return rc; - -free_opt: - if (*mnt_opts) { - selinux_free_mnt_opts(*mnt_opts); - *mnt_opts = NULL; - } - return rc; -} - static int show_sid(struct seq_file *m, u32 sid) { char *context = NULL; @@ -7285,7 +7247,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(fs_context_dup, selinux_fs_context_dup), LSM_HOOK_INIT(fs_context_parse_param, selinux_fs_context_parse_param), LSM_HOOK_INIT(sb_eat_lsm_opts, selinux_sb_eat_lsm_opts), - LSM_HOOK_INIT(sb_add_mnt_opt, selinux_add_mnt_opt), #ifdef CONFIG_SECURITY_NETWORK_XFRM LSM_HOOK_INIT(xfrm_policy_clone_security, selinux_xfrm_policy_clone), #endif -- cgit v1.2.3 From 8ab30a331946c34e4ba022c44df8624acea1c74e Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 6 Dec 2021 20:49:48 +0800 Subject: blk-mq: Drop busy_iter_fn blk_mq_hw_ctx argument The only user of blk_mq_hw_ctx blk_mq_hw_ctx argument is blk_mq_rq_inflight(). Function blk_mq_rq_inflight() uses the hctx to find the associated request queue to match against the request. However this same check is already done in caller bt_iter(), so drop this check. With that change there are no more users of busy_iter_fn blk_mq_hw_ctx argument, so drop the argument. Reviewed-by Hannes Reinecke Signed-off-by: John Garry Reviewed-by: Ming Lei Tested-by: Kashyap Desai Link: https://lore.kernel.org/r/1638794990-137490-2-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 2 +- block/blk-mq.c | 17 ++++++++--------- include/linux/blk-mq.h | 3 +-- 3 files changed, 10 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 380e2dd31bfc..d3cf91d764d5 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -254,7 +254,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) return true; if (rq->q == hctx->queue && rq->mq_hctx == hctx) - ret = iter_data->fn(hctx, rq, iter_data->data, reserved); + ret = iter_data->fn(rq, iter_data->data, reserved); blk_mq_put_rq_ref(rq); return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 0bf3523dd1f5..103c0f58853c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -127,8 +127,7 @@ struct mq_inflight { unsigned int inflight[2]; }; -static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, - struct request *rq, void *priv, +static bool blk_mq_check_inflight(struct request *rq, void *priv, bool reserved) { struct mq_inflight *mi = priv; @@ -1308,14 +1307,15 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); -static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq, - void *priv, bool reserved) +static bool blk_mq_rq_inflight(struct request *rq, void *priv, + bool reserved) { /* - * If we find a request that isn't idle and the queue matches, - * we know the queue is busy. Return false to stop the iteration. + * If we find a request that isn't idle we know the queue is busy + * as it's checked in the iter. + * Return false to stop the iteration. */ - if (blk_mq_request_started(rq) && rq->q == hctx->queue) { + if (blk_mq_request_started(rq)) { bool *busy = priv; *busy = true; @@ -1377,8 +1377,7 @@ void blk_mq_put_rq_ref(struct request *rq) __blk_mq_free_request(rq); } -static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, - struct request *rq, void *priv, bool reserved) +static bool blk_mq_check_expired(struct request *rq, void *priv, bool reserved) { unsigned long *next = priv; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index ecdc049b52fa..17ebf29e42d8 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -470,8 +470,7 @@ struct blk_mq_queue_data { bool last; }; -typedef bool (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *, - bool); +typedef bool (busy_iter_fn)(struct request *, void *, bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); /** -- cgit v1.2.3 From fc39f8d2d1c10ac04976b0a247865bb0cec4dd88 Mon Sep 17 00:00:00 2001 From: John Garry Date: Mon, 6 Dec 2021 20:49:49 +0800 Subject: blk-mq: Delete busy_iter_fn Typedefs busy_iter_fn and busy_tag_iter_fn are now identical, so delete busy_iter_fn to reduce duplication. It would be nicer to delete busy_tag_iter_fn, as the name busy_iter_fn is less specific. However busy_tag_iter_fn is used in many different parts of the tree, unlike busy_iter_fn which is just use in block/, so just take the straightforward path now, so that we could rename later treewide. Signed-off-by: John Garry Reviewed-by: Ming Lei Reviewed-by: Hannes Reinecke Tested-by: Kashyap Desai Link: https://lore.kernel.org/r/1638794990-137490-3-git-send-email-john.garry@huawei.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 6 +++--- block/blk-mq-tag.h | 2 +- include/linux/blk-mq.h | 1 - 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index d3cf91d764d5..58b80d4b7a07 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -215,7 +215,7 @@ void blk_mq_put_tags(struct blk_mq_tags *tags, int *tag_array, int nr_tags) struct bt_iter_data { struct blk_mq_hw_ctx *hctx; - busy_iter_fn *fn; + busy_tag_iter_fn *fn; void *data; bool reserved; }; @@ -274,7 +274,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * bitmap_tags member of struct blk_mq_tags. */ static void bt_for_each(struct blk_mq_hw_ctx *hctx, struct sbitmap_queue *bt, - busy_iter_fn *fn, void *data, bool reserved) + busy_tag_iter_fn *fn, void *data, bool reserved) { struct bt_iter_data iter_data = { .hctx = hctx, @@ -457,7 +457,7 @@ EXPORT_SYMBOL(blk_mq_tagset_wait_completed_request); * called for all requests on all queues that share that tag set and not only * for requests associated with @q. */ -void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, +void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, void *priv) { struct blk_mq_hw_ctx *hctx; diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index df787b5a23bd..5668e28be0b7 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -28,7 +28,7 @@ extern void blk_mq_tag_resize_shared_tags(struct blk_mq_tag_set *set, extern void blk_mq_tag_update_sched_shared_tags(struct request_queue *q); extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); -void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, +void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_tag_iter_fn *fn, void *priv); void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, void *priv); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 17ebf29e42d8..772f8f921526 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -470,7 +470,6 @@ struct blk_mq_queue_data { bool last; }; -typedef bool (busy_iter_fn)(struct request *, void *, bool); typedef bool (busy_tag_iter_fn)(struct request *, void *, bool); /** -- cgit v1.2.3 From 05770dd0ad110854c7157d95700d7c89979cdb3e Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Mon, 22 Nov 2021 18:30:12 +0900 Subject: tracing: Support __rel_loc relative dynamic data location attribute Add '__rel_loc' new dynamic data location attribute which encodes the data location from the next to the field itself. The '__data_loc' is used for encoding the dynamic data location on the trace event record. But '__data_loc' is not useful if the writer doesn't know the event header (e.g. user event), because it records the dynamic data offset from the entry of the record, not the field itself. This new '__rel_loc' attribute encodes the data location relatively from the next of the field. For example, when there is a record like below (the number in the parentheses is the size of fields) |header(N)|common(M)|fields(K)|__data_loc(4)|fields(L)|data(G)| In this case, '__data_loc' field will be __data_loc = (G << 16) | (N+M+K+4+L) If '__rel_loc' is used, this will be |header(N)|common(M)|fields(K)|__rel_loc(4)|fields(L)|data(G)| where __rel_loc = (G << 16) | (L) This case shows L bytes after the '__rel_loc' attribute field, if there is no fields after the __rel_loc field, L must be 0. This is relatively easy (and no need to consider the kernel header change) when the event data fields are composed by user who doesn't know header and common fields. Link: https://lkml.kernel.org/r/163757341258.510314.4214431827833229956.stgit@devnote2 Cc: Beau Belgrave Cc: Namhyung Kim Cc: Tom Zanussi Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- include/linux/trace_events.h | 1 + kernel/trace/trace.h | 1 + kernel/trace/trace_events_filter.c | 32 ++++++++++++++++++++++++++++++-- kernel/trace/trace_events_hist.c | 21 +++++++++++++++++++-- kernel/trace/trace_events_inject.c | 11 +++++++++-- 5 files changed, 60 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 2d167ac3452c..3900404aa063 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -782,6 +782,7 @@ enum { FILTER_OTHER = 0, FILTER_STATIC_STRING, FILTER_DYN_STRING, + FILTER_RDYN_STRING, FILTER_PTR_STRING, FILTER_TRACE_FN, FILTER_COMM, diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 38715aa6cfdf..5db2bec8ca7e 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1465,6 +1465,7 @@ struct filter_pred { static inline bool is_string_field(struct ftrace_event_field *field) { return field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING || field->filter_type == FILTER_STATIC_STRING || field->filter_type == FILTER_PTR_STRING || field->filter_type == FILTER_COMM; diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index c9124038b140..996920ed1812 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -706,6 +706,29 @@ static int filter_pred_strloc(struct filter_pred *pred, void *event) return match; } +/* + * Filter predicate for relative dynamic sized arrays of characters. + * These are implemented through a list of strings at the end + * of the entry as same as dynamic string. + * The difference is that the relative one records the location offset + * from the field itself, not the event entry. + */ +static int filter_pred_strrelloc(struct filter_pred *pred, void *event) +{ + u32 *item = (u32 *)(event + pred->offset); + u32 str_item = *item; + int str_loc = str_item & 0xffff; + int str_len = str_item >> 16; + char *addr = (char *)(&item[1]) + str_loc; + int cmp, match; + + cmp = pred->regex.match(addr, &pred->regex, str_len); + + match = cmp ^ pred->not; + + return match; +} + /* Filter predicate for CPUs. */ static int filter_pred_cpu(struct filter_pred *pred, void *event) { @@ -756,7 +779,7 @@ static int filter_pred_none(struct filter_pred *pred, void *event) * * Note: * - @str might not be NULL-terminated if it's of type DYN_STRING - * or STATIC_STRING, unless @len is zero. + * RDYN_STRING, or STATIC_STRING, unless @len is zero. */ static int regex_match_full(char *str, struct regex *r, int len) @@ -1083,6 +1106,9 @@ int filter_assign_type(const char *type) if (strstr(type, "__data_loc") && strstr(type, "char")) return FILTER_DYN_STRING; + if (strstr(type, "__rel_loc") && strstr(type, "char")) + return FILTER_RDYN_STRING; + if (strchr(type, '[') && strstr(type, "char")) return FILTER_STATIC_STRING; @@ -1318,8 +1344,10 @@ static int parse_pred(const char *str, void *data, pred->fn = filter_pred_string; pred->regex.field_len = field->size; - } else if (field->filter_type == FILTER_DYN_STRING) + } else if (field->filter_type == FILTER_DYN_STRING) { pred->fn = filter_pred_strloc; + } else if (field->filter_type == FILTER_RDYN_STRING) + pred->fn = filter_pred_strrelloc; else pred->fn = filter_pred_pchar; /* go past the last quote */ diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 319f9c8ca7e7..9b8da439149c 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -217,6 +217,20 @@ static u64 hist_field_dynstring(struct hist_field *hist_field, return (u64)(unsigned long)addr; } +static u64 hist_field_reldynstring(struct hist_field *hist_field, + struct tracing_map_elt *elt, + struct trace_buffer *buffer, + struct ring_buffer_event *rbe, + void *event) +{ + u32 *item = event + hist_field->field->offset; + u32 str_item = *item; + int str_loc = str_item & 0xffff; + char *addr = (char *)&item[1] + str_loc; + + return (u64)(unsigned long)addr; +} + static u64 hist_field_pstring(struct hist_field *hist_field, struct tracing_map_elt *elt, struct trace_buffer *buffer, @@ -1956,8 +1970,10 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (field->filter_type == FILTER_STATIC_STRING) { hist_field->fn = hist_field_string; hist_field->size = field->size; - } else if (field->filter_type == FILTER_DYN_STRING) + } else if (field->filter_type == FILTER_DYN_STRING) { hist_field->fn = hist_field_dynstring; + } else if (field->filter_type == FILTER_RDYN_STRING) + hist_field->fn = hist_field_reldynstring; else hist_field->fn = hist_field_pstring; } else { @@ -4961,7 +4977,8 @@ static inline void add_to_key(char *compound_key, void *key, struct ftrace_event_field *field; field = key_field->field; - if (field->filter_type == FILTER_DYN_STRING) + if (field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING) size = *(u32 *)(rec + field->offset) >> 16; else if (field->filter_type == FILTER_STATIC_STRING) size = field->size; diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c index c188045c5f97..d6b4935a78c0 100644 --- a/kernel/trace/trace_events_inject.c +++ b/kernel/trace/trace_events_inject.c @@ -168,10 +168,14 @@ static void *trace_alloc_entry(struct trace_event_call *call, int *size) continue; if (field->filter_type == FILTER_STATIC_STRING) continue; - if (field->filter_type == FILTER_DYN_STRING) { + if (field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING) { u32 *str_item; int str_loc = entry_size & 0xffff; + if (field->filter_type == FILTER_RDYN_STRING) + str_loc -= field->offset + field->size; + str_item = (u32 *)(entry + field->offset); *str_item = str_loc; /* string length is 0. */ } else { @@ -214,7 +218,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) if (field->filter_type == FILTER_STATIC_STRING) { strlcpy(entry + field->offset, addr, field->size); - } else if (field->filter_type == FILTER_DYN_STRING) { + } else if (field->filter_type == FILTER_DYN_STRING || + field->filter_type == FILTER_RDYN_STRING) { int str_len = strlen(addr) + 1; int str_loc = entry_size & 0xffff; u32 *str_item; @@ -229,6 +234,8 @@ static int parse_entry(char *str, struct trace_event_call *call, void **pentry) strlcpy(entry + (entry_size - str_len), addr, str_len); str_item = (u32 *)(entry + field->offset); + if (field->filter_type == FILTER_RDYN_STRING) + str_loc -= field->offset + field->size; *str_item = (str_len << 16) | str_loc; } else { char **paddr; -- cgit v1.2.3 From 8c33915d77a565b8b5d44e6368e22b6ea300b7a8 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Sun, 28 Nov 2021 20:00:29 +0100 Subject: platform/x86: wmi: Add no_notify_data flag to struct wmi_driver Some WMI implementations do notifies on WMI objects without a _WED method allow WMI drivers to indicate that _WED should not be called for notifies on the WMI objects the driver is bound to. Instead the driver's notify callback will simply be called with a NULL data argument. Reported-by: Yauhen Kharuzhy Reviewed-by: Andy Shevchenko Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20211128190031.405620-3-hdegoede@redhat.com --- drivers/platform/x86/wmi.c | 10 ++++++---- include/linux/wmi.h | 1 + 2 files changed, 7 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c index 02aba274c4bc..58a23a9adbef 100644 --- a/drivers/platform/x86/wmi.c +++ b/drivers/platform/x86/wmi.c @@ -1331,10 +1331,12 @@ static void acpi_wmi_notify_handler(acpi_handle handle, u32 event, struct acpi_buffer evdata = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_status status; - status = get_event_data(wblock, &evdata); - if (ACPI_FAILURE(status)) { - dev_warn(&wblock->dev.dev, "failed to get event data\n"); - return; + if (!driver->no_notify_data) { + status = get_event_data(wblock, &evdata); + if (ACPI_FAILURE(status)) { + dev_warn(&wblock->dev.dev, "failed to get event data\n"); + return; + } } if (driver->notify) diff --git a/include/linux/wmi.h b/include/linux/wmi.h index 2cb3913c1f50..b88d7b58e61e 100644 --- a/include/linux/wmi.h +++ b/include/linux/wmi.h @@ -35,6 +35,7 @@ extern int set_required_buffer_size(struct wmi_device *wdev, u64 length); struct wmi_driver { struct device_driver driver; const struct wmi_device_id *id_table; + bool no_notify_data; int (*probe)(struct wmi_device *wdev, const void *context); void (*remove)(struct wmi_device *wdev); -- cgit v1.2.3 From 4e66934eaadc83b27ada8d42b60894018f3bfabf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:21:55 -0800 Subject: lib: add reference counting tracking infrastructure It can be hard to track where references are taken and released. In networking, we have annoying issues at device or netns dismantles, and we had various proposals to ease root causing them. This patch adds new infrastructure pairing refcount increases and decreases. This will self document code, because programmers will have to associate increments/decrements. This is controled by CONFIG_REF_TRACKER which can be selected by users of this feature. This adds both cpu and memory costs, and thus should probably be used with care. Signed-off-by: Eric Dumazet Reviewed-by: Dmitry Vyukov Signed-off-by: Jakub Kicinski --- include/linux/ref_tracker.h | 73 +++++++++++++++++++++++ lib/Kconfig | 5 ++ lib/Makefile | 2 + lib/ref_tracker.c | 140 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 220 insertions(+) create mode 100644 include/linux/ref_tracker.h create mode 100644 lib/ref_tracker.c (limited to 'include/linux') diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h new file mode 100644 index 000000000000..c11c9db5825c --- /dev/null +++ b/include/linux/ref_tracker.h @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#ifndef _LINUX_REF_TRACKER_H +#define _LINUX_REF_TRACKER_H +#include +#include +#include + +struct ref_tracker; + +struct ref_tracker_dir { +#ifdef CONFIG_REF_TRACKER + spinlock_t lock; + unsigned int quarantine_avail; + refcount_t untracked; + struct list_head list; /* List of active trackers */ + struct list_head quarantine; /* List of dead trackers */ +#endif +}; + +#ifdef CONFIG_REF_TRACKER +static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, + unsigned int quarantine_count) +{ + INIT_LIST_HEAD(&dir->list); + INIT_LIST_HEAD(&dir->quarantine); + spin_lock_init(&dir->lock); + dir->quarantine_avail = quarantine_count; + refcount_set(&dir->untracked, 1); +} + +void ref_tracker_dir_exit(struct ref_tracker_dir *dir); + +void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit); + +int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, gfp_t gfp); + +int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp); + +#else /* CONFIG_REF_TRACKER */ + +static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, + unsigned int quarantine_count) +{ +} + +static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir) +{ +} + +static inline void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ +} + +static inline int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, + gfp_t gfp) +{ + return 0; +} + +static inline int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp) +{ + return 0; +} + +#endif + +#endif /* _LINUX_REF_TRACKER_H */ diff --git a/lib/Kconfig b/lib/Kconfig index 5e7165e6a346..655b0e43f260 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -680,6 +680,11 @@ config STACK_HASH_ORDER Select the hash size as a power of 2 for the stackdepot hash table. Choose a lower value to reduce the memory impact. +config REF_TRACKER + bool + depends on STACKTRACE_SUPPORT + select STACKDEPOT + config SBITMAP bool diff --git a/lib/Makefile b/lib/Makefile index 364c23f15578..c1fd9243ddb9 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -270,6 +270,8 @@ obj-$(CONFIG_STACKDEPOT) += stackdepot.o KASAN_SANITIZE_stackdepot.o := n KCOV_INSTRUMENT_stackdepot.o := n +obj-$(CONFIG_REF_TRACKER) += ref_tracker.o + libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o \ fdt_empty_tree.o fdt_addresses.o $(foreach file, $(libfdt_files), \ diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c new file mode 100644 index 000000000000..0ae2e66dcf0f --- /dev/null +++ b/lib/ref_tracker.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include +#include +#include +#include +#include + +#define REF_TRACKER_STACK_ENTRIES 16 + +struct ref_tracker { + struct list_head head; /* anchor into dir->list or dir->quarantine */ + bool dead; + depot_stack_handle_t alloc_stack_handle; + depot_stack_handle_t free_stack_handle; +}; + +void ref_tracker_dir_exit(struct ref_tracker_dir *dir) +{ + struct ref_tracker *tracker, *n; + unsigned long flags; + bool leak = false; + + spin_lock_irqsave(&dir->lock, flags); + list_for_each_entry_safe(tracker, n, &dir->quarantine, head) { + list_del(&tracker->head); + kfree(tracker); + dir->quarantine_avail++; + } + list_for_each_entry_safe(tracker, n, &dir->list, head) { + pr_err("leaked reference.\n"); + if (tracker->alloc_stack_handle) + stack_depot_print(tracker->alloc_stack_handle); + leak = true; + list_del(&tracker->head); + kfree(tracker); + } + spin_unlock_irqrestore(&dir->lock, flags); + WARN_ON_ONCE(leak); + WARN_ON_ONCE(refcount_read(&dir->untracked) != 1); +} +EXPORT_SYMBOL(ref_tracker_dir_exit); + +void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ + struct ref_tracker *tracker; + unsigned long flags; + unsigned int i = 0; + + spin_lock_irqsave(&dir->lock, flags); + list_for_each_entry(tracker, &dir->list, head) { + if (i < display_limit) { + pr_err("leaked reference.\n"); + if (tracker->alloc_stack_handle) + stack_depot_print(tracker->alloc_stack_handle); + i++; + } else { + break; + } + } + spin_unlock_irqrestore(&dir->lock, flags); +} +EXPORT_SYMBOL(ref_tracker_dir_print); + +int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, + gfp_t gfp) +{ + unsigned long entries[REF_TRACKER_STACK_ENTRIES]; + struct ref_tracker *tracker; + unsigned int nr_entries; + unsigned long flags; + + *trackerp = tracker = kzalloc(sizeof(*tracker), gfp | __GFP_NOFAIL); + if (unlikely(!tracker)) { + pr_err_once("memory allocation failure, unreliable refcount tracker.\n"); + refcount_inc(&dir->untracked); + return -ENOMEM; + } + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); + nr_entries = filter_irq_stacks(entries, nr_entries); + tracker->alloc_stack_handle = stack_depot_save(entries, nr_entries, gfp); + + spin_lock_irqsave(&dir->lock, flags); + list_add(&tracker->head, &dir->list); + spin_unlock_irqrestore(&dir->lock, flags); + return 0; +} +EXPORT_SYMBOL_GPL(ref_tracker_alloc); + +int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp) +{ + unsigned long entries[REF_TRACKER_STACK_ENTRIES]; + struct ref_tracker *tracker = *trackerp; + depot_stack_handle_t stack_handle; + unsigned int nr_entries; + unsigned long flags; + + if (!tracker) { + refcount_dec(&dir->untracked); + return -EEXIST; + } + nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1); + nr_entries = filter_irq_stacks(entries, nr_entries); + stack_handle = stack_depot_save(entries, nr_entries, GFP_ATOMIC); + + spin_lock_irqsave(&dir->lock, flags); + if (tracker->dead) { + pr_err("reference already released.\n"); + if (tracker->alloc_stack_handle) { + pr_err("allocated in:\n"); + stack_depot_print(tracker->alloc_stack_handle); + } + if (tracker->free_stack_handle) { + pr_err("freed in:\n"); + stack_depot_print(tracker->free_stack_handle); + } + spin_unlock_irqrestore(&dir->lock, flags); + WARN_ON_ONCE(1); + return -EINVAL; + } + tracker->dead = true; + + tracker->free_stack_handle = stack_handle; + + list_move_tail(&tracker->head, &dir->quarantine); + if (!dir->quarantine_avail) { + tracker = list_first_entry(&dir->quarantine, struct ref_tracker, head); + list_del(&tracker->head); + } else { + dir->quarantine_avail--; + tracker = NULL; + } + spin_unlock_irqrestore(&dir->lock, flags); + + kfree(tracker); + return 0; +} +EXPORT_SYMBOL_GPL(ref_tracker_free); -- cgit v1.2.3 From 4d92b95ff2f95f13df9bad0b5a25a9f60e72758d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:21:57 -0800 Subject: net: add net device refcount tracker infrastructure net device are refcounted. Over the years we had numerous bugs caused by imbalanced dev_hold() and dev_put() calls. The general idea is to be able to precisely pair each decrement with a corresponding prior increment. Both share a cookie, basically a pointer to private data storing stack traces. This patch adds dev_hold_track() and dev_put_track(). To use these helpers, each data structure owning a refcount should also use a "netdevice_tracker" to pair the hold and put. netdevice_tracker dev_tracker; ... dev_hold_track(dev, &dev_tracker, GFP_ATOMIC); ... dev_put_track(dev, &dev_tracker); Whenever a leak happens, we will get precise stack traces of the point dev_hold_track() happened, at device dismantle phase. We will also get a stack trace if too many dev_put_track() for the same netdevice_tracker are attempted. This is guarded by CONFIG_NET_DEV_REFCNT_TRACKER option. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 45 +++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 5 +++++ net/Kconfig.debug | 10 ++++++++++ net/core/dev.c | 3 +++ 4 files changed, 63 insertions(+) create mode 100644 net/Kconfig.debug (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 65117f01d5f2..143d60ed0047 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -48,6 +48,7 @@ #include #include #include +#include struct netpoll_info; struct device; @@ -300,6 +301,12 @@ enum netdev_state_t { }; +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER +typedef struct ref_tracker *netdevice_tracker; +#else +typedef struct {} netdevice_tracker; +#endif + struct gro_list { struct list_head list; int count; @@ -1865,6 +1872,7 @@ enum netdev_ml_priv_type { * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @dev_refcnt: Number of references to this device + * @refcnt_tracker: Tracker directory for tracked references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * @@ -2178,6 +2186,7 @@ struct net_device { #else refcount_t dev_refcnt; #endif + struct ref_tracker_dir refcnt_tracker; struct list_head link_watch_list; @@ -3805,6 +3814,7 @@ void netdev_run_todo(void); * @dev: network device * * Release reference to device to allow it to be freed. + * Try using dev_put_track() instead. */ static inline void dev_put(struct net_device *dev) { @@ -3822,6 +3832,7 @@ static inline void dev_put(struct net_device *dev) * @dev: network device * * Hold reference to device to keep it from being freed. + * Try using dev_hold_track() instead. */ static inline void dev_hold(struct net_device *dev) { @@ -3834,6 +3845,40 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +static inline void netdev_tracker_free(struct net_device *dev, + netdevice_tracker *tracker) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_free(&dev->refcnt_tracker, tracker); +#endif +} + +static inline void dev_hold_track(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ + if (dev) { + dev_hold(dev); + netdev_tracker_alloc(dev, tracker, gfp); + } +} + +static inline void dev_put_track(struct net_device *dev, + netdevice_tracker *tracker) +{ + if (dev) { + netdev_tracker_free(dev, tracker); + dev_put(dev); + } +} + /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 633c2c5cb45b..6504b97f8dfd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -598,6 +598,11 @@ config DEBUG_MISC Say Y here if you need to enable miscellaneous debug code that should be under a more specific debug option but isn't. +menu "Networking Debugging" + +source "net/Kconfig.debug" + +endmenu # "Networking Debugging" menu "Memory Debugging" diff --git a/net/Kconfig.debug b/net/Kconfig.debug new file mode 100644 index 000000000000..fb5c70e01cb3 --- /dev/null +++ b/net/Kconfig.debug @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0-only + +config NET_DEV_REFCNT_TRACKER + bool "Enable net device refcount tracking" + depends on DEBUG_KERNEL && STACKTRACE_SUPPORT + select REF_TRACKER + default n + help + Enable debugging feature to track device references. + This adds memory and cpu costs. diff --git a/net/core/dev.c b/net/core/dev.c index aba8acc1238c..1740d6cfe86b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9864,6 +9864,7 @@ static void netdev_wait_allrefs(struct net_device *dev) netdev_unregister_timeout_secs * HZ)) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, refcnt); + ref_tracker_dir_print(&dev->refcnt_tracker, 10); warning_time = jiffies; } } @@ -10154,6 +10155,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + ref_tracker_dir_init(&dev->refcnt_tracker, 128); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) @@ -10270,6 +10272,7 @@ void free_netdev(struct net_device *dev) list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); + ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; -- cgit v1.2.3 From 80e8921b2b72c300ca56a01729004d30bedb82cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:21:58 -0800 Subject: net: add net device refcount tracker to struct netdev_rx_queue This helps debugging net device refcount leaks. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ net/core/net-sysfs.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 143d60ed0047..3d691fadd569 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -741,6 +741,8 @@ struct netdev_rx_queue { #endif struct kobject kobj; struct net_device *dev; + netdevice_tracker dev_tracker; + #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index affe34d71d31..27a7ac2e516f 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1004,7 +1004,7 @@ static void rx_queue_release(struct kobject *kobj) #endif memset(kobj, 0, sizeof(*kobj)); - dev_put(queue->dev); + dev_put_track(queue->dev, &queue->dev_tracker); } static const void *rx_queue_namespace(struct kobject *kobj) @@ -1044,7 +1044,7 @@ static int rx_queue_add_kobject(struct net_device *dev, int index) /* Kobject_put later will trigger rx_queue_release call which * decreases dev refcount: Take that reference here */ - dev_hold(queue->dev); + dev_hold_track(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &rx_queue_ktype, NULL, -- cgit v1.2.3 From 0b688f24b7d611db3a02f3d4ab562d049c78a17d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:21:59 -0800 Subject: net: add net device refcount tracker to struct netdev_queue This will help debugging pesky netdev reference leaks. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ net/core/net-sysfs.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3d691fadd569..b4f704337f65 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -586,6 +586,8 @@ struct netdev_queue { * read-mostly part */ struct net_device *dev; + netdevice_tracker dev_tracker; + struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 27a7ac2e516f..3b2cdbbdc858 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1607,7 +1607,7 @@ static void netdev_queue_release(struct kobject *kobj) struct netdev_queue *queue = to_netdev_queue(kobj); memset(kobj, 0, sizeof(*kobj)); - dev_put(queue->dev); + dev_put_track(queue->dev, &queue->dev_tracker); } static const void *netdev_queue_namespace(struct kobject *kobj) @@ -1647,7 +1647,7 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index) /* Kobject_put later will trigger netdev_queue_release call * which decreases dev refcount: Take that reference here */ - dev_hold(queue->dev); + dev_hold_track(queue->dev, &queue->dev_tracker, GFP_KERNEL); kobj->kset = dev->queues_kset; error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, -- cgit v1.2.3 From 9038c320001dd07f60736018edf608ac5baca0ab Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:22:03 -0800 Subject: net: dst: add net device refcount tracking to dst_entry We want to track all dev_hold()/dev_put() to ease leak hunting. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 17 +++++++++++++++++ include/net/dst.h | 1 + net/core/dst.c | 8 ++++---- net/ipv4/route.c | 7 ++++--- net/ipv6/route.c | 5 +++-- 5 files changed, 29 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b4f704337f65..afed3b10491b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3883,6 +3883,23 @@ static inline void dev_put_track(struct net_device *dev, } } +static inline void dev_replace_track(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + if (odev) + ref_tracker_free(&odev->refcnt_tracker, tracker); +#endif + dev_hold(ndev); + dev_put(odev); +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + if (ndev) + ref_tracker_alloc(&ndev->refcnt_tracker, tracker, gfp); +#endif +} + /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. diff --git a/include/net/dst.h b/include/net/dst.h index a057319aabef..6aa252c3fc55 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -77,6 +77,7 @@ struct dst_entry { #ifndef CONFIG_64BIT atomic_t __refcnt; /* 32-bit offset 64 */ #endif + netdevice_tracker dev_tracker; }; struct dst_metrics { diff --git a/net/core/dst.c b/net/core/dst.c index 497ef9b3fc6a..d16c2c9bfebd 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -49,7 +49,7 @@ void dst_init(struct dst_entry *dst, struct dst_ops *ops, unsigned short flags) { dst->dev = dev; - dev_hold(dev); + dev_hold_track(dev, &dst->dev_tracker, GFP_ATOMIC); dst->ops = ops; dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; @@ -117,7 +117,7 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) if (dst->ops->destroy) dst->ops->destroy(dst); - dev_put(dst->dev); + dev_put_track(dst->dev, &dst->dev_tracker); lwtstate_put(dst->lwtstate); @@ -159,8 +159,8 @@ void dst_dev_put(struct dst_entry *dst) dst->input = dst_discard; dst->output = dst_discard_out; dst->dev = blackhole_netdev; - dev_hold(dst->dev); - dev_put(dev); + dev_replace_track(dev, blackhole_netdev, &dst->dev_tracker, + GFP_ATOMIC); } EXPORT_SYMBOL(dst_dev_put); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 243a0c52be42..843a7a3699fe 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1531,8 +1531,9 @@ void rt_flush_dev(struct net_device *dev) if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; - dev_hold(rt->dst.dev); - dev_put(dev); + dev_replace_track(dev, blackhole_netdev, + &rt->dst.dev_tracker, + GFP_ATOMIC); } spin_unlock_bh(&ul->lock); } @@ -2819,7 +2820,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or new->output = dst_discard_out; new->dev = net->loopback_dev; - dev_hold(new->dev); + dev_hold_track(new->dev, &new->dev_tracker, GFP_ATOMIC); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f0d29fcb2094..ba4dc94d76d6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -182,8 +182,9 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; - dev_hold(rt->dst.dev); - dev_put(rt_dev); + dev_replace_track(rt_dev, blackhole_netdev, + &rt->dst.dev_tracker, + GFP_ATOMIC); } } spin_unlock_bh(&ul->lock); -- cgit v1.2.3 From c04438f58d140723e58050fcb9d33d84cb39e9e9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:22:12 -0800 Subject: ipv4: add net device refcount tracker to struct in_device Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/inetdevice.h | 2 ++ net/ipv4/devinet.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 518b484a7f07..674aeead6260 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -24,6 +24,8 @@ struct ipv4_devconf { struct in_device { struct net_device *dev; + netdevice_tracker dev_tracker; + refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 323e622ff9b7..fba2bffd65f7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -243,7 +243,7 @@ void in_dev_finish_destroy(struct in_device *idev) #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif - dev_put(dev); + dev_put_track(dev, &idev->dev_tracker); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else @@ -271,7 +271,7 @@ static struct in_device *inetdev_init(struct net_device *dev) if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ - dev_hold(dev); + dev_hold_track(dev, &in_dev->dev_tracker, GFP_KERNEL); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); -- cgit v1.2.3 From 63f13937cbe9b00982dfc8e578b1aec8e5037333 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:22:14 -0800 Subject: net: linkwatch: add net device refcount tracker Add a netdevice_tracker inside struct net_device, to track the self reference when a device is in lweventlist. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ net/core/link_watch.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index afed3b10491b..69dca1edd5a6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1950,6 +1950,7 @@ enum netdev_ml_priv_type { * keep a list of interfaces to be deleted. * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. + * @linkwatch_dev_tracker: refcount tracker used by linkwatch. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2280,6 +2281,7 @@ struct net_device { struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; u8 dev_addr_shadow[MAX_ADDR_LEN]; + netdevice_tracker linkwatch_dev_tracker; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 9599afd0862d..d7d089963b1d 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -109,7 +109,7 @@ static void linkwatch_add_event(struct net_device *dev) spin_lock_irqsave(&lweventlist_lock, flags); if (list_empty(&dev->link_watch_list)) { list_add_tail(&dev->link_watch_list, &lweventlist); - dev_hold(dev); + dev_hold_track(dev, &dev->linkwatch_dev_tracker, GFP_ATOMIC); } spin_unlock_irqrestore(&lweventlist_lock, flags); } @@ -166,7 +166,7 @@ static void linkwatch_do_dev(struct net_device *dev) netdev_state_change(dev); } - dev_put(dev); + dev_put_track(dev, &dev->linkwatch_dev_tracker); } static void __linkwatch_run_queue(int urgent_only) -- cgit v1.2.3 From 42120a86438379eb77424831ae3d696c2d5cb622 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:22:16 -0800 Subject: ipmr, ip6mr: add net device refcount tracker to struct vif_device Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/mroute_base.h | 2 ++ net/ipv4/ipmr.c | 3 ++- net/ipv6/ip6mr.c | 3 ++- 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 8071148f29a6..e05ee9f001ff 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -12,6 +12,7 @@ /** * struct vif_device - interface representor for multicast routing * @dev: network device being used + * @dev_tracker: refcount tracker for @dev reference * @bytes_in: statistic; bytes ingressing * @bytes_out: statistic; bytes egresing * @pkt_in: statistic; packets ingressing @@ -26,6 +27,7 @@ */ struct vif_device { struct net_device *dev; + netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; unsigned long rate_limit; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2dda856ca260..4c7aca884fa9 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -696,7 +696,7 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); - dev_put(dev); + dev_put_track(dev, &v->dev_tracker); return 0; } @@ -896,6 +896,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, /* And finish update writing critical data */ write_lock_bh(&mrt_lock); v->dev = dev; + netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); if (v->flags & VIFF_REGISTER) mrt->mroute_reg_vif_num = vifi; if (vifi+1 > mrt->maxvif) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 36ed9efb8825..a77a15a7f3dc 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -746,7 +746,7 @@ static int mif6_delete(struct mr_table *mrt, int vifi, int notify, if ((v->flags & MIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); - dev_put(dev); + dev_put_track(dev, &v->dev_tracker); return 0; } @@ -919,6 +919,7 @@ static int mif6_add(struct net *net, struct mr_table *mrt, /* And finish update writing critical data */ write_lock_bh(&mrt_lock); v->dev = dev; + netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC); #ifdef CONFIG_IPV6_PIMSM_V2 if (v->flags & MIFF_REGISTER) mrt->mroute_reg_vif_num = vifi; -- cgit v1.2.3 From 5fa5ae605821e0e10ee489d9a6e331fd287ccc57 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 4 Dec 2021 20:22:17 -0800 Subject: netpoll: add net device refcount tracker to struct netpoll Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- drivers/net/netconsole.c | 2 +- include/linux/netpoll.h | 1 + net/core/netpoll.c | 4 ++-- 3 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index ccecba908ded..ab8cd5551020 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -721,7 +721,7 @@ restart: __netpoll_cleanup(&nt->np); spin_lock_irqsave(&target_list_lock, flags); - dev_put(nt->np.dev); + dev_put_track(nt->np.dev, &nt->np.dev_tracker); nt->np.dev = NULL; nt->enabled = false; stopped = true; diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e6a2d72e0dc7..bd19c4b91e31 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -24,6 +24,7 @@ union inet_addr { struct netpoll { struct net_device *dev; + netdevice_tracker dev_tracker; char dev_name[IFNAMSIZ]; const char *name; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index edfc0f8011f8..db724463e7cd 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -776,7 +776,7 @@ put_noaddr: err = __netpoll_setup(np, ndev); if (err) goto put; - + netdev_tracker_alloc(ndev, &np->dev_tracker, GFP_KERNEL); rtnl_unlock(); return 0; @@ -853,7 +853,7 @@ void netpoll_cleanup(struct netpoll *np) if (!np->dev) goto out; __netpoll_cleanup(np); - dev_put(np->dev); + dev_put_track(np->dev, &np->dev_tracker); np->dev = NULL; out: rtnl_unlock(); -- cgit v1.2.3 From 45cac6754529ae17345d8f5b632d9e602a091a20 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Dec 2021 20:53:56 -0800 Subject: net: fix recent csum changes Vladimir reported csum issues after my recent change in skb_postpull_rcsum() Issue here is the following: initial skb->csum is the csum of [part to be pulled][rest of packet] Old code: skb->csum = csum_sub(skb->csum, csum_partial(pull, pull_length, 0)); New code: skb->csum = ~csum_partial(pull, pull_length, ~skb->csum); This is broken if the csum of [pulled part] happens to be equal to skb->csum, because end result of skb->csum is 0 in new code, instead of being 0xffffffff David Laight suggested to use skb->csum = -csum_partial(pull, pull_length, -skb->csum); I based my patches on existing code present in include/net/seg6.h, update_csum_diff4() and update_csum_diff16() which might need a similar fix. I guess that my tests, mostly pulling 40 bytes of IPv6 header were not providing enough entropy to hit this bug. v2: added wsum_negate() to make sparse happy. Fixes: 29c3002644bd ("net: optimize skb_postpull_rcsum()") Fixes: 0bd28476f636 ("gro: optimize skb_gro_postpull_rcsum()") Signed-off-by: Eric Dumazet Reported-by: Vladimir Oltean Suggested-by: David Laight Cc: David Lebrun Tested-by: Vladimir Oltean Link: https://lore.kernel.org/r/20211204045356.3659278-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 3 ++- include/net/checksum.h | 4 ++++ include/net/gro.h | 4 ++-- 3 files changed, 8 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eae4bd3237a4..dd262bd8ddbe 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3486,7 +3486,8 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = ~csum_partial(start, len, ~skb->csum); + skb->csum = wsum_negate(csum_partial(start, len, + wsum_negate(skb->csum))); else if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; diff --git a/include/net/checksum.h b/include/net/checksum.h index 5b96d5bd6e54..5218041e5c8f 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -180,4 +180,8 @@ static inline void remcsum_unadjust(__sum16 *psum, __wsum delta) *psum = csum_fold(csum_sub(delta, (__force __wsum)*psum)); } +static inline __wsum wsum_negate(__wsum val) +{ + return (__force __wsum)-((__force u32)val); +} #endif diff --git a/include/net/gro.h b/include/net/gro.h index b1139fca7c43..8f75802d50fd 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -173,8 +173,8 @@ static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { if (NAPI_GRO_CB(skb)->csum_valid) - NAPI_GRO_CB(skb)->csum = ~csum_partial(start, len, - ~NAPI_GRO_CB(skb)->csum); + NAPI_GRO_CB(skb)->csum = wsum_negate(csum_partial(start, len, + wsum_negate(NAPI_GRO_CB(skb)->csum))); } /* GRO checksum functions. These are logical equivalents of the normal -- cgit v1.2.3 From f0e6e6fa41b3d2aa1dcb61dd4ed6d7be004bb5a8 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 18 Oct 2021 17:14:07 +0200 Subject: KVM: Drop stale kvm_is_transparent_hugepage() declaration kvm_is_transparent_hugepage() was removed in commit 205d76ff0684 ("KVM: Remove kvm_is_transparent_hugepage() and PageTransCompoundMap()") but its declaration in include/linux/kvm_host.h persisted. Drop it. Fixes: 205d76ff0684 (""KVM: Remove kvm_is_transparent_hugepage() and PageTransCompoundMap()") Signed-off-by: Vitaly Kuznetsov Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211018151407.2107363-1-vkuznets@redhat.com --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..6d138adc78af 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1174,7 +1174,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu); bool kvm_is_reserved_pfn(kvm_pfn_t pfn); bool kvm_is_zone_device_pfn(kvm_pfn_t pfn); -bool kvm_is_transparent_hugepage(kvm_pfn_t pfn); struct kvm_irq_ack_notifier { struct hlist_node link; -- cgit v1.2.3 From 77993b595ada5731e513eb06a0f4bf4b9f1e9532 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 29 Nov 2021 18:46:54 +0100 Subject: locking: Allow to include asm/spinlock_types.h from linux/spinlock_types_raw.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The printk header file includes ratelimit_types.h for its __ratelimit() based usage. It is required for the static initializer used in printk_ratelimited(). It uses a raw_spinlock_t and includes the spinlock_types.h. PREEMPT_RT substitutes spinlock_t with a rtmutex based implementation and so its spinlock_t implmentation (provided by spinlock_rt.h) includes rtmutex.h and atomic.h which leads to recursive includes where defines are missing. By including only the raw_spinlock_t defines it avoids the atomic.h related includes at this stage. An example on powerpc: | CALL scripts/atomic/check-atomics.sh |In file included from include/linux/bug.h:5, | from include/linux/page-flags.h:10, | from kernel/bounds.c:10: |arch/powerpc/include/asm/page_32.h: In function ‘clear_page’: |arch/powerpc/include/asm/bug.h:87:4: error: implicit declaration of function â=80=98__WARNâ=80=99 [-Werror=3Dimplicit-function-declaration] | 87 | __WARN(); \ | | ^~~~~~ |arch/powerpc/include/asm/page_32.h:48:2: note: in expansion of macro ‘WARN_ONâ€=99 | 48 | WARN_ON((unsigned long)addr & (L1_CACHE_BYTES - 1)); | | ^~~~~~~ |arch/powerpc/include/asm/bug.h:58:17: error: invalid application of ‘sizeofâ€=99 to incomplete type ‘struct bug_entryâ€=99 | 58 | "i" (sizeof(struct bug_entry)), \ | | ^~~~~~ |arch/powerpc/include/asm/bug.h:89:3: note: in expansion of macro ‘BUG_ENTRYâ€=99 | 89 | BUG_ENTRY(PPC_TLNEI " %4, 0", \ | | ^~~~~~~~~ |arch/powerpc/include/asm/page_32.h:48:2: note: in expansion of macro ‘WARN_ONâ€=99 | 48 | WARN_ON((unsigned long)addr & (L1_CACHE_BYTES - 1)); | | ^~~~~~~ |In file included from arch/powerpc/include/asm/ptrace.h:298, | from arch/powerpc/include/asm/hw_irq.h:12, | from arch/powerpc/include/asm/irqflags.h:12, | from include/linux/irqflags.h:16, | from include/asm-generic/cmpxchg-local.h:6, | from arch/powerpc/include/asm/cmpxchg.h:526, | from arch/powerpc/include/asm/atomic.h:11, | from include/linux/atomic.h:7, | from include/linux/rwbase_rt.h:6, | from include/linux/rwlock_types.h:55, | from include/linux/spinlock_types.h:74, | from include/linux/ratelimit_types.h:7, | from include/linux/printk.h:10, | from include/asm-generic/bug.h:22, | from arch/powerpc/include/asm/bug.h:109, | from include/linux/bug.h:5, | from include/linux/page-flags.h:10, | from kernel/bounds.c:10: |include/linux/thread_info.h: In function â=80=98copy_overflowâ=80=99: |include/linux/thread_info.h:210:2: error: implicit declaration of function â=80=98WARNâ=80=99 [-Werror=3Dimplicit-function-declaration] | 210 | WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); | | ^~~~ The WARN / BUG include pulls in printk.h and then ptrace.h expects WARN (from bug.h) which is not yet complete. Even hw_irq.h has WARN_ON() statements. On POWERPC64 there are missing atomic64 defines while building 32bit VDSO: | VDSO32C arch/powerpc/kernel/vdso32/vgettimeofday.o |In file included from include/linux/atomic.h:80, | from include/linux/rwbase_rt.h:6, | from include/linux/rwlock_types.h:55, | from include/linux/spinlock_types.h:74, | from include/linux/ratelimit_types.h:7, | from include/linux/printk.h:10, | from include/linux/kernel.h:19, | from arch/powerpc/include/asm/page.h:11, | from arch/powerpc/include/asm/vdso/gettimeofday.h:5, | from include/vdso/datapage.h:137, | from lib/vdso/gettimeofday.c:5, | from : |include/linux/atomic-arch-fallback.h: In function ‘arch_atomic64_incâ€=99: |include/linux/atomic-arch-fallback.h:1447:2: error: implicit declaration of function ‘arch_atomic64_add’; did you mean ‘arch_atomic_add’? [-Werror=3Dimpl |icit-function-declaration] | 1447 | arch_atomic64_add(1, v); | | ^~~~~~~~~~~~~~~~~ | | arch_atomic_add The generic fallback is not included, atomics itself are not used. If kernel.h does not include printk.h then it comes later from the bug.h include. Allow asm/spinlock_types.h to be included from linux/spinlock_types_raw.h. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211129174654.668506-12-bigeasy@linutronix.de --- arch/alpha/include/asm/spinlock_types.h | 2 +- arch/arm/include/asm/spinlock_types.h | 2 +- arch/arm64/include/asm/spinlock_types.h | 2 +- arch/csky/include/asm/spinlock_types.h | 2 +- arch/hexagon/include/asm/spinlock_types.h | 2 +- arch/ia64/include/asm/spinlock_types.h | 2 +- arch/powerpc/include/asm/simple_spinlock_types.h | 2 +- arch/powerpc/include/asm/spinlock_types.h | 2 +- arch/riscv/include/asm/spinlock_types.h | 2 +- arch/s390/include/asm/spinlock_types.h | 2 +- arch/sh/include/asm/spinlock_types.h | 2 +- arch/xtensa/include/asm/spinlock_types.h | 2 +- include/linux/ratelimit_types.h | 2 +- include/linux/spinlock_types_up.h | 2 +- 14 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h index 1d5716bc060b..2526fd3be5fd 100644 --- a/arch/alpha/include/asm/spinlock_types.h +++ b/arch/alpha/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef _ALPHA_SPINLOCK_TYPES_H #define _ALPHA_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h index 5976958647fe..0c14b36ef101 100644 --- a/arch/arm/include/asm/spinlock_types.h +++ b/arch/arm/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h index 18782f0c4721..11ab1c077697 100644 --- a/arch/arm64/include/asm/spinlock_types.h +++ b/arch/arm64/include/asm/spinlock_types.h @@ -5,7 +5,7 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) +#if !defined(__LINUX_SPINLOCK_TYPES_RAW_H) && !defined(__ASM_SPINLOCK_H) # error "please don't include this file directly" #endif diff --git a/arch/csky/include/asm/spinlock_types.h b/arch/csky/include/asm/spinlock_types.h index 8ff0f6ff3a00..db87a12c3827 100644 --- a/arch/csky/include/asm/spinlock_types.h +++ b/arch/csky/include/asm/spinlock_types.h @@ -3,7 +3,7 @@ #ifndef __ASM_CSKY_SPINLOCK_TYPES_H #define __ASM_CSKY_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h index 19d233497ba5..d5f66495b670 100644 --- a/arch/hexagon/include/asm/spinlock_types.h +++ b/arch/hexagon/include/asm/spinlock_types.h @@ -8,7 +8,7 @@ #ifndef _ASM_SPINLOCK_TYPES_H #define _ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h index 6e345fefcdca..14b8a161c165 100644 --- a/arch/ia64/include/asm/spinlock_types.h +++ b/arch/ia64/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef _ASM_IA64_SPINLOCK_TYPES_H #define _ASM_IA64_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h index 0f3cdd8faa95..08243338069d 100644 --- a/arch/powerpc/include/asm/simple_spinlock_types.h +++ b/arch/powerpc/include/asm/simple_spinlock_types.h @@ -2,7 +2,7 @@ #ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H #define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h index c5d742f18021..d5f8a74ed2e8 100644 --- a/arch/powerpc/include/asm/spinlock_types.h +++ b/arch/powerpc/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H #define _ASM_POWERPC_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/riscv/include/asm/spinlock_types.h b/arch/riscv/include/asm/spinlock_types.h index f398e7638dd6..5a35a49505da 100644 --- a/arch/riscv/include/asm/spinlock_types.h +++ b/arch/riscv/include/asm/spinlock_types.h @@ -6,7 +6,7 @@ #ifndef _ASM_RISCV_SPINLOCK_TYPES_H #define _ASM_RISCV_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h index a2bbfd7df85f..b69695e39957 100644 --- a/arch/s390/include/asm/spinlock_types.h +++ b/arch/s390/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h index e82369f286a2..907bda4b1619 100644 --- a/arch/sh/include/asm/spinlock_types.h +++ b/arch/sh/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef __ASM_SH_SPINLOCK_TYPES_H #define __ASM_SH_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h index 64c9389254f1..797aed7df3dd 100644 --- a/arch/xtensa/include/asm/spinlock_types.h +++ b/arch/xtensa/include/asm/spinlock_types.h @@ -2,7 +2,7 @@ #ifndef __ASM_SPINLOCK_TYPES_H #define __ASM_SPINLOCK_TYPES_H -#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) +#if !defined(__LINUX_SPINLOCK_TYPES_RAW_H) && !defined(__ASM_SPINLOCK_H) # error "please don't include this file directly" #endif diff --git a/include/linux/ratelimit_types.h b/include/linux/ratelimit_types.h index b676aa419eef..c21c7f8103e2 100644 --- a/include/linux/ratelimit_types.h +++ b/include/linux/ratelimit_types.h @@ -4,7 +4,7 @@ #include #include -#include +#include #define DEFAULT_RATELIMIT_INTERVAL (5 * HZ) #define DEFAULT_RATELIMIT_BURST 10 diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h index c09b6407ae1b..7f86a2016ac5 100644 --- a/include/linux/spinlock_types_up.h +++ b/include/linux/spinlock_types_up.h @@ -1,7 +1,7 @@ #ifndef __LINUX_SPINLOCK_TYPES_UP_H #define __LINUX_SPINLOCK_TYPES_UP_H -#ifndef __LINUX_SPINLOCK_TYPES_H +#ifndef __LINUX_SPINLOCK_TYPES_RAW_H # error "please don't include this file directly" #endif -- cgit v1.2.3 From 8d9f738f16a3ee9f2341578873c542ddd9802fe4 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Tue, 7 Dec 2021 20:32:30 +0800 Subject: regulator: fix bullet lists of regulator_ops comment Since 89a6a5e56c82("regulator: add property parsing and callbacks to set protection limits") which introduced a warning: Documentation/driver-api/regulator:166: ./include/linux/regulator/driver.h:96: WARNING: Unexpected indentation. Documentation/driver-api/regulator:166: ./include/linux/regulator/driver.h:98: WARNING: Block quote ends without a blank line; unexpected unindent. Let's fix them. Signed-off-by: Yanteng Si Link: https://lore.kernel.org/r/20211207123230.2262047-1-siyanteng@loongson.cn Signed-off-by: Mark Brown --- include/linux/regulator/driver.h | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h index 4078c7776453..720684995a77 100644 --- a/include/linux/regulator/driver.h +++ b/include/linux/regulator/driver.h @@ -90,15 +90,19 @@ enum regulator_detection_severity { * @set_over_current_protection: Support enabling of and setting limits for over * current situation detection. Detection can be configured for three * levels of severity. - * REGULATOR_SEVERITY_PROT should automatically shut down the regulator(s). - * REGULATOR_SEVERITY_ERR should indicate that over-current situation is - * caused by an unrecoverable error but HW does not perform - * automatic shut down. - * REGULATOR_SEVERITY_WARN should indicate situation where hardware is - * still believed to not be damaged but that a board sepcific - * recovery action is needed. If lim_uA is 0 the limit should not - * be changed but the detection should just be enabled/disabled as - * is requested. + * + * - REGULATOR_SEVERITY_PROT should automatically shut down the regulator(s). + * + * - REGULATOR_SEVERITY_ERR should indicate that over-current situation is + * caused by an unrecoverable error but HW does not perform + * automatic shut down. + * + * - REGULATOR_SEVERITY_WARN should indicate situation where hardware is + * still believed to not be damaged but that a board sepcific + * recovery action is needed. If lim_uA is 0 the limit should not + * be changed but the detection should just be enabled/disabled as + * is requested. + * * @set_over_voltage_protection: Support enabling of and setting limits for over * voltage situation detection. Detection can be configured for same * severities as over current protection. Units of uV. -- cgit v1.2.3 From 13244cccc2b61ec715f0ac583d3037497004d4a5 Mon Sep 17 00:00:00 2001 From: Luiz Augusto von Dentz Date: Wed, 1 Dec 2021 10:54:52 -0800 Subject: skbuff: introduce skb_pull_data Like skb_pull but returns the original data pointer before pulling the data after performing a check against sbk->len. This allows to change code that does "struct foo *p = (void *)skb->data;" which is hard to audit and error prone, to: p = skb_pull_data(skb, sizeof(*p)); if (!p) return; Which is both safer and cleaner. Acked-by: Jakub Kicinski Signed-off-by: Luiz Augusto von Dentz Signed-off-by: Dan Carpenter Signed-off-by: Marcel Holtmann --- include/linux/skbuff.h | 2 ++ net/core/skbuff.c | 24 ++++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index eba256af64a5..877dda38684a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2373,6 +2373,8 @@ static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } +void *skb_pull_data(struct sk_buff *skb, size_t len); + void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a33247fdb8f5..dd3ef966efdb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2023,6 +2023,30 @@ void *skb_pull(struct sk_buff *skb, unsigned int len) } EXPORT_SYMBOL(skb_pull); +/** + * skb_pull_data - remove data from the start of a buffer returning its + * original position. + * @skb: buffer to use + * @len: amount of data to remove + * + * This function removes data from the start of a buffer, returning + * the memory to the headroom. A pointer to the original data in the buffer + * is returned after checking if there is enough data to pull. Once the + * data has been pulled future pushes will overwrite the old data. + */ +void *skb_pull_data(struct sk_buff *skb, size_t len) +{ + void *data = skb->data; + + if (skb->len < len) + return NULL; + + skb_pull(skb, len); + + return data; +} +EXPORT_SYMBOL(skb_pull_data); + /** * skb_trim - remove end from a buffer * @skb: buffer to alter -- cgit v1.2.3 From 6fadaa565882cd7afc501de5921db6f5e45c784b Mon Sep 17 00:00:00 2001 From: Maxim Galaganov Date: Fri, 3 Dec 2021 14:35:39 -0800 Subject: tcp: expose __tcp_sock_set_cork and __tcp_sock_set_nodelay Expose __tcp_sock_set_cork() and __tcp_sock_set_nodelay() for use in MPTCP setsockopt code -- namely for syncing MPTCP socket options with subflows inside sync_socket_options() while already holding the subflow socket lock. Acked-by: Paolo Abeni Acked-by: Matthieu Baerts Signed-off-by: Maxim Galaganov Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- include/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 4 ++-- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 48d8a363319e..78b91bb92f0d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -512,11 +512,13 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); +void __tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepcnt(struct sock *sk, int val); int tcp_sock_set_keepidle_locked(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); +void __tcp_sock_set_nodelay(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6ab82e1a1d41..20054618c87e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3207,7 +3207,7 @@ static void tcp_enable_tx_delay(void) * TCP_CORK can be set together with TCP_NODELAY and it is stronger than * TCP_NODELAY. */ -static void __tcp_sock_set_cork(struct sock *sk, bool on) +void __tcp_sock_set_cork(struct sock *sk, bool on) { struct tcp_sock *tp = tcp_sk(sk); @@ -3235,7 +3235,7 @@ EXPORT_SYMBOL(tcp_sock_set_cork); * However, when TCP_NODELAY is set we make an explicit push, which overrides * even TCP_CORK for currently queued segments. */ -static void __tcp_sock_set_nodelay(struct sock *sk, bool on) +void __tcp_sock_set_nodelay(struct sock *sk, bool on) { if (on) { tcp_sk(sk)->nonagle |= TCP_NAGLE_OFF|TCP_NAGLE_PUSH; -- cgit v1.2.3 From 213d56bf33bdda835bac04046f09256a75c5ca8e Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 19 Oct 2021 02:08:07 +0200 Subject: rcu/nocb: Prepare state machine for a new step Currently SEGCBLIST_SOFTIRQ_ONLY is a bit of an exception among the segcblist flags because it is an exclusive state that doesn't mix up with the other flags. Remove it in favour of: _ A flag specifying that rcu_core() needs to perform callbacks execution and acceleration and _ A flag specifying we want the nocb lock to be held in any needed circumstances This clarifies the code and is more flexible: It allows to have a state where rcu_core() runs with locking while offloading hasn't started yet. This is a necessary step to prepare for triggering rcu_core() at the very beginning of the de-offloading process so that rcu_core() won't dismiss work while being preempted by the de-offloading process, at least not without a pending subsequent rcu_core() that will quickly catch up. Reviewed-by: Valentin Schneider Tested-by: Valentin Schneider Tested-by: Sebastian Andrzej Siewior Signed-off-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Josh Triplett Cc: Joel Fernandes Cc: Boqun Feng Cc: Neeraj Upadhyay Cc: Uladzislau Rezki Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney --- include/linux/rcu_segcblist.h | 37 +++++++++++++++++++++++-------------- kernel/rcu/rcu_segcblist.c | 6 +++--- kernel/rcu/rcu_segcblist.h | 12 +++++++----- kernel/rcu/tree.c | 2 +- kernel/rcu/tree_nocb.h | 24 ++++++++++++++++-------- 5 files changed, 50 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 3db96c4f45fd..812961b1d064 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -69,7 +69,7 @@ struct rcu_cblist { * * * ---------------------------------------------------------------------------- - * | SEGCBLIST_SOFTIRQ_ONLY | + * | SEGCBLIST_RCU_CORE | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, without holding nocb_lock. | @@ -77,7 +77,7 @@ struct rcu_cblist { * | * v * ---------------------------------------------------------------------------- - * | SEGCBLIST_OFFLOADED | + * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads, | @@ -89,7 +89,9 @@ struct rcu_cblist { * | | * v v * --------------------------------------- ----------------------------------| - * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_RCU_CORE | | | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | * | SEGCBLIST_KTHREAD_CB | | SEGCBLIST_KTHREAD_GP | * | | | | * | | | | @@ -104,9 +106,10 @@ struct rcu_cblist { * | * v * |--------------------------------------------------------------------------| - * | SEGCBLIST_OFFLOADED | | - * | SEGCBLIST_KTHREAD_CB | | - * | SEGCBLIST_KTHREAD_GP | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_GP | | + * | SEGCBLIST_KTHREAD_CB | * | | * | Kthreads handle callbacks holding nocb_lock, local rcu_core() stops | * | handling callbacks. Enable bypass queueing. | @@ -120,7 +123,8 @@ struct rcu_cblist { * * * |--------------------------------------------------------------------------| - * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | * | | @@ -130,6 +134,8 @@ struct rcu_cblist { * | * v * |--------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | * | | @@ -143,7 +149,9 @@ struct rcu_cblist { * | | * v v * ---------------------------------------------------------------------------| - * | | + * | | | + * | SEGCBLIST_RCU_CORE | | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | SEGCBLIST_LOCKING | | * | SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | * | | | * | GP kthread woke up and | CB kthread woke up and | @@ -159,7 +167,7 @@ struct rcu_cblist { * | * v * ---------------------------------------------------------------------------- - * | 0 | + * | SEGCBLIST_RCU_CORE | SEGCBLIST_LOCKING | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed. | @@ -168,17 +176,18 @@ struct rcu_cblist { * | * v * ---------------------------------------------------------------------------- - * | SEGCBLIST_SOFTIRQ_ONLY | + * | SEGCBLIST_RCU_CORE | * | | * | Callbacks processed by rcu_core() from softirqs or local | * | rcuc kthread, without holding nocb_lock. | * ---------------------------------------------------------------------------- */ #define SEGCBLIST_ENABLED BIT(0) -#define SEGCBLIST_SOFTIRQ_ONLY BIT(1) -#define SEGCBLIST_KTHREAD_CB BIT(2) -#define SEGCBLIST_KTHREAD_GP BIT(3) -#define SEGCBLIST_OFFLOADED BIT(4) +#define SEGCBLIST_RCU_CORE BIT(1) +#define SEGCBLIST_LOCKING BIT(2) +#define SEGCBLIST_KTHREAD_CB BIT(3) +#define SEGCBLIST_KTHREAD_GP BIT(4) +#define SEGCBLIST_OFFLOADED BIT(5) struct rcu_segcblist { struct rcu_head *head; diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index aaa111237b60..c07aab6e39ef 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -261,14 +261,14 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) } /* - * Mark the specified rcu_segcblist structure as offloaded. + * Mark the specified rcu_segcblist structure as offloaded (or not) */ void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload) { if (offload) { - rcu_segcblist_clear_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY); - rcu_segcblist_set_flags(rsclp, SEGCBLIST_OFFLOADED); + rcu_segcblist_set_flags(rsclp, SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED); } else { + rcu_segcblist_set_flags(rsclp, SEGCBLIST_RCU_CORE); rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED); } } diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 9a19328ff251..e373fbe44da5 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -80,11 +80,14 @@ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp) return rcu_segcblist_test_flags(rsclp, SEGCBLIST_ENABLED); } -/* Is the specified rcu_segcblist offloaded, or is SEGCBLIST_SOFTIRQ_ONLY set? */ +/* + * Is the specified rcu_segcblist NOCB offloaded (or in the middle of the + * [de]offloading process)? + */ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp) { if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - !rcu_segcblist_test_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY)) + rcu_segcblist_test_flags(rsclp, SEGCBLIST_LOCKING)) return true; return false; @@ -92,9 +95,8 @@ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp) static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp) { - int flags = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | SEGCBLIST_OFFLOADED; - - if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && (rsclp->flags & flags) == flags) + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + !rcu_segcblist_test_flags(rsclp, SEGCBLIST_RCU_CORE)) return true; return false; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8706b30c2ac8..e905d7e4ddb9 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -79,7 +79,7 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, .dynticks = ATOMIC_INIT(1), #ifdef CONFIG_RCU_NOCB_CPU - .cblist.flags = SEGCBLIST_SOFTIRQ_ONLY, + .cblist.flags = SEGCBLIST_RCU_CORE, #endif }; static struct rcu_state rcu_state = { diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 368ef7b9af4f..b3e07d0bfbbf 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -1000,12 +1000,12 @@ static long rcu_nocb_rdp_deoffload(void *arg) */ rcu_nocb_lock_irqsave(rdp, flags); /* - * Theoretically we could set SEGCBLIST_SOFTIRQ_ONLY after the nocb + * Theoretically we could clear SEGCBLIST_LOCKING after the nocb * lock is released but how about being paranoid for once? */ - rcu_segcblist_set_flags(cblist, SEGCBLIST_SOFTIRQ_ONLY); + rcu_segcblist_clear_flags(cblist, SEGCBLIST_LOCKING); /* - * With SEGCBLIST_SOFTIRQ_ONLY, we can't use + * Without SEGCBLIST_LOCKING, we can't use * rcu_nocb_unlock_irqrestore() anymore. */ raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); @@ -1058,14 +1058,14 @@ static long rcu_nocb_rdp_offload(void *arg) pr_info("Offloading %d\n", rdp->cpu); /* - * Can't use rcu_nocb_lock_irqsave() while we are in - * SEGCBLIST_SOFTIRQ_ONLY mode. + * Can't use rcu_nocb_lock_irqsave() before SEGCBLIST_LOCKING + * is set. */ raw_spin_lock_irqsave(&rdp->nocb_lock, flags); /* * We didn't take the nocb lock while working on the - * rdp->cblist in SEGCBLIST_SOFTIRQ_ONLY mode. + * rdp->cblist with SEGCBLIST_LOCKING cleared (pure softirq/rcuc mode). * Every modifications that have been done previously on * rdp->cblist must be visible remotely by the nocb kthreads * upon wake up after reading the cblist flags. @@ -1084,6 +1084,14 @@ static long rcu_nocb_rdp_offload(void *arg) rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB) && rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)); + /* + * All kthreads are ready to work, we can finally relieve rcu_core() and + * enable nocb bypass. + */ + rcu_nocb_lock_irqsave(rdp, flags); + rcu_segcblist_clear_flags(cblist, SEGCBLIST_RCU_CORE); + rcu_nocb_unlock_irqrestore(rdp, flags); + return ret; } @@ -1154,8 +1162,8 @@ void __init rcu_init_nohz(void) if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); rcu_segcblist_offload(&rdp->cblist, true); - rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB); - rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP); + rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP); + rcu_segcblist_clear_flags(&rdp->cblist, SEGCBLIST_RCU_CORE); } rcu_organize_nocb_kthreads(); } -- cgit v1.2.3 From fbb94cbd70d41c7511460896dfc7f9ea5da704b3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 19 Oct 2021 02:08:08 +0200 Subject: rcu/nocb: Invoke rcu_core() at the start of deoffloading On PREEMPT_RT, if rcu_core() is preempted by the de-offloading process, some work, such as callbacks acceleration and invocation, may be left unattended due to the volatile checks on the offloaded state. In the worst case this work is postponed until the next rcu_pending() check that can take a jiffy to reach, which can be a problem in case of callbacks flooding. Solve that with invoking rcu_core() early in the de-offloading process. This way any work dismissed by an ongoing rcu_core() call fooled by a preempting deoffloading process will be caught up by a nearby future recall to rcu_core(), this time fully aware of the de-offloading state. Tested-by: Valentin Schneider Tested-by: Sebastian Andrzej Siewior Signed-off-by: Frederic Weisbecker Cc: Valentin Schneider Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Josh Triplett Cc: Joel Fernandes Cc: Boqun Feng Cc: Neeraj Upadhyay Cc: Uladzislau Rezki Cc: Thomas Gleixner Signed-off-by: Paul E. McKenney --- include/linux/rcu_segcblist.h | 14 ++++++++++++++ kernel/rcu/rcu_segcblist.c | 6 ++---- kernel/rcu/tree.c | 17 +++++++++++++++++ kernel/rcu/tree_nocb.h | 9 +++++++++ 4 files changed, 42 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 812961b1d064..659d13a7ddaa 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -136,6 +136,20 @@ struct rcu_cblist { * |--------------------------------------------------------------------------| * | SEGCBLIST_RCU_CORE | | * | SEGCBLIST_LOCKING | | + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | + * | handles callbacks concurrently. Bypass enqueue is enabled. | + * | Invoke RCU core so we make sure not to preempt it in the middle with | + * | leaving some urgent work unattended within a jiffy. | + * ---------------------------------------------------------------------------- + * | + * v + * |--------------------------------------------------------------------------| + * | SEGCBLIST_RCU_CORE | | + * | SEGCBLIST_LOCKING | | * | SEGCBLIST_KTHREAD_CB | | * | SEGCBLIST_KTHREAD_GP | * | | diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index c07aab6e39ef..81145c3ece25 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -265,12 +265,10 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) */ void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload) { - if (offload) { + if (offload) rcu_segcblist_set_flags(rsclp, SEGCBLIST_LOCKING | SEGCBLIST_OFFLOADED); - } else { - rcu_segcblist_set_flags(rsclp, SEGCBLIST_RCU_CORE); + else rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED); - } } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e905d7e4ddb9..a329adfece86 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -2707,6 +2707,23 @@ static __latent_entropy void rcu_core(void) unsigned long flags; struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; + /* + * On RT rcu_core() can be preempted when IRQs aren't disabled. + * Therefore this function can race with concurrent NOCB (de-)offloading + * on this CPU and the below condition must be considered volatile. + * However if we race with: + * + * _ Offloading: In the worst case we accelerate or process callbacks + * concurrently with NOCB kthreads. We are guaranteed to + * call rcu_nocb_lock() if that happens. + * + * _ Deoffloading: In the worst case we miss callbacks acceleration or + * processing. This is fine because the early stage + * of deoffloading invokes rcu_core() after setting + * SEGCBLIST_RCU_CORE. So we guarantee that we'll process + * what could have been dismissed without the need to wait + * for the next rcu_pending() check in the next jiffy. + */ const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist); if (cpu_is_offline(smp_processor_id())) diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index b3e07d0bfbbf..2461fe8d0c23 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -990,6 +990,15 @@ static long rcu_nocb_rdp_deoffload(void *arg) * will refuse to put anything into the bypass. */ WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies)); + /* + * Start with invoking rcu_core() early. This way if the current thread + * happens to preempt an ongoing call to rcu_core() in the middle, + * leaving some work dismissed because rcu_core() still thinks the rdp is + * completely offloaded, we are guaranteed a nearby future instance of + * rcu_core() to catch up. + */ + rcu_segcblist_set_flags(cblist, SEGCBLIST_RCU_CORE); + invoke_rcu_core(); ret = rdp_offload_toggle(rdp, false, flags); swait_event_exclusive(rdp->nocb_state_wq, !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB | -- cgit v1.2.3 From 81faa4f6fba429334ff72bb5ba7696818509b5b5 Mon Sep 17 00:00:00 2001 From: Li Zhijian Date: Wed, 3 Nov 2021 16:30:28 +0800 Subject: locktorture,rcutorture,torture: Always log error message Unconditionally log messages corresponding to errors. Acked-by: Davidlohr Bueso Signed-off-by: Li Zhijian Signed-off-by: Paul E. McKenney --- include/linux/torture.h | 9 ++------- kernel/locking/locktorture.c | 4 ++-- kernel/rcu/rcutorture.c | 8 ++++---- kernel/torture.c | 4 ++-- 4 files changed, 10 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/torture.h b/include/linux/torture.h index 24f58e50a94b..63fa4196e51c 100644 --- a/include/linux/torture.h +++ b/include/linux/torture.h @@ -38,13 +38,8 @@ do { \ pr_alert("%s" TORTURE_FLAG " %s\n", torture_type, s); \ } \ } while (0) -#define VERBOSE_TOROUT_ERRSTRING(s) \ -do { \ - if (verbose) { \ - verbose_torout_sleep(); \ - pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s); \ - } \ -} while (0) +#define TOROUT_ERRSTRING(s) \ + pr_alert("%s" TORTURE_FLAG "!!! %s\n", torture_type, s) void verbose_torout_sleep(void); #define torture_init_error(firsterr) \ diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 397ac13d2ef7..9c2fb613a55d 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -1047,7 +1047,7 @@ static int __init lock_torture_init(void) sizeof(writer_tasks[0]), GFP_KERNEL); if (writer_tasks == NULL) { - VERBOSE_TOROUT_ERRSTRING("writer_tasks: Out of memory"); + TOROUT_ERRSTRING("writer_tasks: Out of memory"); firsterr = -ENOMEM; goto unwind; } @@ -1058,7 +1058,7 @@ static int __init lock_torture_init(void) sizeof(reader_tasks[0]), GFP_KERNEL); if (reader_tasks == NULL) { - VERBOSE_TOROUT_ERRSTRING("reader_tasks: Out of memory"); + TOROUT_ERRSTRING("reader_tasks: Out of memory"); kfree(writer_tasks); writer_tasks = NULL; firsterr = -ENOMEM; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 503e14e62e8f..36a273589a35 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -2774,7 +2774,7 @@ static int rcu_torture_read_exit(void *unused) &trs, "%s", "rcu_torture_read_exit_child"); if (IS_ERR(tsp)) { - VERBOSE_TOROUT_ERRSTRING("out of memory"); + TOROUT_ERRSTRING("out of memory"); errexit = true; tsp = NULL; break; @@ -3101,7 +3101,7 @@ rcu_torture_init(void) sizeof(fakewriter_tasks[0]), GFP_KERNEL); if (fakewriter_tasks == NULL) { - VERBOSE_TOROUT_ERRSTRING("out of memory"); + TOROUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } @@ -3117,7 +3117,7 @@ rcu_torture_init(void) rcu_torture_reader_mbchk = kcalloc(nrealreaders, sizeof(*rcu_torture_reader_mbchk), GFP_KERNEL); if (!reader_tasks || !rcu_torture_reader_mbchk) { - VERBOSE_TOROUT_ERRSTRING("out of memory"); + TOROUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } @@ -3136,7 +3136,7 @@ rcu_torture_init(void) if (nrealnocbers > 0) { nocb_tasks = kcalloc(nrealnocbers, sizeof(nocb_tasks[0]), GFP_KERNEL); if (nocb_tasks == NULL) { - VERBOSE_TOROUT_ERRSTRING("out of memory"); + TOROUT_ERRSTRING("out of memory"); firsterr = -ENOMEM; goto unwind; } diff --git a/kernel/torture.c b/kernel/torture.c index bb8f411c974b..ef27a6c82451 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -570,7 +570,7 @@ int torture_shuffle_init(long shuffint) shuffle_idle_cpu = -1; if (!alloc_cpumask_var(&shuffle_tmp_mask, GFP_KERNEL)) { - VERBOSE_TOROUT_ERRSTRING("Failed to alloc mask"); + TOROUT_ERRSTRING("Failed to alloc mask"); return -ENOMEM; } @@ -934,7 +934,7 @@ int _torture_create_kthread(int (*fn)(void *arg), void *arg, char *s, char *m, *tp = kthread_run(fn, arg, "%s", s); if (IS_ERR(*tp)) { ret = PTR_ERR(*tp); - VERBOSE_TOROUT_ERRSTRING(f); + TOROUT_ERRSTRING(f); *tp = NULL; } torture_shuffle_task_register(*tp); -- cgit v1.2.3 From 08f0b22d731fa86957749c649d6ef6ebc07e8ad2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Dec 2021 17:30:27 -0800 Subject: net: eql: add net device refcount tracker Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- drivers/net/eql.c | 4 ++-- include/linux/if_eql.h | 1 + 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/eql.c b/drivers/net/eql.c index 8ef34901c2d8..1111d1f33865 100644 --- a/drivers/net/eql.c +++ b/drivers/net/eql.c @@ -225,7 +225,7 @@ static void eql_kill_one_slave(slave_queue_t *queue, slave_t *slave) list_del(&slave->list); queue->num_slaves--; slave->dev->flags &= ~IFF_SLAVE; - dev_put(slave->dev); + dev_put_track(slave->dev, &slave->dev_tracker); kfree(slave); } @@ -399,7 +399,7 @@ static int __eql_insert_slave(slave_queue_t *queue, slave_t *slave) if (duplicate_slave) eql_kill_one_slave(queue, duplicate_slave); - dev_hold(slave->dev); + dev_hold_track(slave->dev, &slave->dev_tracker, GFP_ATOMIC); list_add(&slave->list, &queue->all_slaves); queue->num_slaves++; slave->dev->flags |= IFF_SLAVE; diff --git a/include/linux/if_eql.h b/include/linux/if_eql.h index d984694c384d..d75601d613cc 100644 --- a/include/linux/if_eql.h +++ b/include/linux/if_eql.h @@ -26,6 +26,7 @@ typedef struct slave { struct list_head list; struct net_device *dev; + netdevice_tracker dev_tracker; long priority; long priority_bps; long priority_Bps; -- cgit v1.2.3 From 19c9ebf6ed70856385296a65e78c1699081b152f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Dec 2021 17:30:28 -0800 Subject: vlan: add net device refcount tracker Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/if_vlan.h | 3 +++ net/8021q/vlan_dev.c | 4 ++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 41a518336673..8420fe504927 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -162,6 +162,7 @@ struct netpoll; * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice + * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats @@ -177,6 +178,8 @@ struct vlan_dev_priv { u16 flags; struct net_device *real_dev; + netdevice_tracker dev_tracker; + unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 866556e041b7..26d031a43cc1 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -616,7 +616,7 @@ static int vlan_dev_init(struct net_device *dev) return -ENOMEM; /* Get vlan's reference to real_dev */ - dev_hold(real_dev); + dev_hold_track(real_dev, &vlan->dev_tracker, GFP_KERNEL); return 0; } @@ -848,7 +848,7 @@ static void vlan_dev_free(struct net_device *dev) vlan->vlan_pcpu_stats = NULL; /* Get rid of the vlan's reference to real_dev */ - dev_put(vlan->real_dev); + dev_put_track(vlan->real_dev, &vlan->dev_tracker); } void vlan_setup(struct net_device *dev) -- cgit v1.2.3 From f12bf6f3f942b37de65eeea8be25903587fec930 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Dec 2021 17:30:30 -0800 Subject: net: watchdog: add net device refcount tracker Add a netdevice_tracker inside struct net_device, to track the self reference when a device has an active watchdog timer. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 2 ++ net/sched/sch_generic.c | 10 ++++++---- 2 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69dca1edd5a6..1a748ee9a421 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1951,6 +1951,7 @@ enum netdev_ml_priv_type { * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. + * @watchdog_dev_tracker: refcount tracker used by watchdog. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -2282,6 +2283,7 @@ struct net_device { u8 dev_addr_shadow[MAX_ADDR_LEN]; netdevice_tracker linkwatch_dev_tracker; + netdevice_tracker watchdog_dev_tracker; }; #define to_net_dev(d) container_of(d, struct net_device, dev) diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 8c8fbf2e3856..b07bd1c7330f 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -499,6 +499,7 @@ EXPORT_SYMBOL(netif_tx_unlock); static void dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); + bool release = true; spin_lock(&dev->tx_global_lock); if (!qdisc_tx_is_noop(dev)) { @@ -534,12 +535,13 @@ static void dev_watchdog(struct timer_list *t) if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) - dev_hold(dev); + release = false; } } spin_unlock(&dev->tx_global_lock); - dev_put(dev); + if (release) + dev_put_track(dev, &dev->watchdog_dev_tracker); } void __netdev_watchdog_up(struct net_device *dev) @@ -549,7 +551,7 @@ void __netdev_watchdog_up(struct net_device *dev) dev->watchdog_timeo = 5*HZ; if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) - dev_hold(dev); + dev_hold_track(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC); } } EXPORT_SYMBOL_GPL(__netdev_watchdog_up); @@ -563,7 +565,7 @@ static void dev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) - dev_put(dev); + dev_put_track(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } -- cgit v1.2.3 From a97770cc4016c2733bcef9dbe3d5b1ad02d13356 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Mon, 6 Dec 2021 16:12:27 +0800 Subject: net: phy: Remove unnecessary indentation in the comments of phy_device Fix warning as: linux-next/Documentation/networking/kapi:122: ./include/linux/phy.h:543: WARNING: Unexpected indentation. linux-next/Documentation/networking/kapi:122: ./include/linux/phy.h:544: WARNING: Block quote ends without a blank line; unexpected unindent. linux-next/Documentation/networking/kapi:122: ./include/linux/phy.h:546: WARNING: Unexpected indentation. Suggested-by: Akira Yokosawa Signed-off-by: Yanteng Si Signed-off-by: Jakub Kicinski --- include/linux/phy.h | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 96e43fbb2dd8..cbf03a5f9cf5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -538,11 +538,12 @@ struct macsec_ops; * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY * @state: State of the PHY for management purposes * @dev_flags: Device-specific flags used by the PHY driver. - * Bits [15:0] are free to use by the PHY driver to communicate - * driver specific behavior. - * Bits [23:16] are currently reserved for future use. - * Bits [31:24] are reserved for defining generic - * PHY driver behavior. + * + * - Bits [15:0] are free to use by the PHY driver to communicate + * driver specific behavior. + * - Bits [23:16] are currently reserved for future use. + * - Bits [31:24] are reserved for defining generic + * PHY driver behavior. * @irq: IRQ number of the PHY's interrupt (-1 if none) * @phy_timer: The timer for handling the state machine * @phylink: Pointer to phylink instance for this PHY -- cgit v1.2.3 From 330c6d3bfa268794bf692165d0f781f1c2d4d83e Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Wed, 24 Nov 2021 10:45:36 +0900 Subject: can: bittiming: replace CAN units with the generic ones from linux/units.h In [1], we introduced a set of units in linux/can/bittiming.h. Since then, generic SI prefixes were added to linux/units.h in [2]. Those new prefixes can perfectly replace CAN specific ones. This patch replaces all occurrences of the CAN units with their corresponding prefix (from linux/units) and the unit (as a comment) according to below table. CAN units SI metric prefix (from linux/units) + unit (as a comment) ------------------------------------------------------------------------ CAN_KBPS KILO /* BPS */ CAN_MBPS MEGA /* BPS */ CAM_MHZ MEGA /* Hz */ The definition are then removed from linux/can/bittiming.h [1] commit 1d7750760b70 ("can: bittiming: add CAN_KBPS, CAN_MBPS and CAN_MHZ macros") [2] commit 26471d4a6cf8 ("units: Add SI metric prefix definitions") Link: https://lore.kernel.org/all/20211124014536.782550-1-mailhol.vincent@wanadoo.fr Suggested-by: Jimmy Assarsson Suggested-by: Oliver Hartkopp Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/bittiming.c | 5 +++-- drivers/net/can/usb/etas_es58x/es581_4.c | 5 +++-- drivers/net/can/usb/etas_es58x/es58x_fd.c | 5 +++-- include/linux/can/bittiming.h | 7 ------- 4 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index 0509625c3082..d5fca3bfaf9a 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -4,6 +4,7 @@ * Copyright (C) 2008-2009 Wolfgang Grandegger */ +#include #include #ifdef CONFIG_CAN_CALC_BITTIMING @@ -81,9 +82,9 @@ int can_calc_bittiming(struct net_device *dev, struct can_bittiming *bt, if (bt->sample_point) { sample_point_nominal = bt->sample_point; } else { - if (bt->bitrate > 800 * CAN_KBPS) + if (bt->bitrate > 800 * KILO /* BPS */) sample_point_nominal = 750; - else if (bt->bitrate > 500 * CAN_KBPS) + else if (bt->bitrate > 500 * KILO /* BPS */) sample_point_nominal = 800; else sample_point_nominal = 875; diff --git a/drivers/net/can/usb/etas_es58x/es581_4.c b/drivers/net/can/usb/etas_es58x/es581_4.c index 14e360c9f2c9..1bcdcece5ec7 100644 --- a/drivers/net/can/usb/etas_es58x/es581_4.c +++ b/drivers/net/can/usb/etas_es58x/es581_4.c @@ -10,6 +10,7 @@ */ #include +#include #include #include "es58x_core.h" @@ -469,8 +470,8 @@ const struct es58x_parameters es581_4_param = { .bittiming_const = &es581_4_bittiming_const, .data_bittiming_const = NULL, .tdc_const = NULL, - .bitrate_max = 1 * CAN_MBPS, - .clock = {.freq = 50 * CAN_MHZ}, + .bitrate_max = 1 * MEGA /* BPS */, + .clock = {.freq = 50 * MEGA /* Hz */}, .ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC, .tx_start_of_frame = 0xAFAF, .rx_start_of_frame = 0xFAFA, diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index 4f0cae29f4d8..ec87126e1a7d 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -12,6 +12,7 @@ */ #include +#include #include #include "es58x_core.h" @@ -522,8 +523,8 @@ const struct es58x_parameters es58x_fd_param = { * Mbps work in an optimal environment but are not recommended * for production environment. */ - .bitrate_max = 8 * CAN_MBPS, - .clock = {.freq = 80 * CAN_MHZ}, + .bitrate_max = 8 * MEGA /* BPS */, + .clock = {.freq = 80 * MEGA /* Hz */}, .ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO, diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 20b50baf3a02..a81652d1c6f3 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -12,13 +12,6 @@ #define CAN_SYNC_SEG 1 -/* Kilobits and Megabits per second */ -#define CAN_KBPS 1000UL -#define CAN_MBPS 1000000UL - -/* Megahertz */ -#define CAN_MHZ 1000000UL - #define CAN_CTRLMODE_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) -- cgit v1.2.3 From 27592ae8dbe41033261b6fdf27d78998aabd2665 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Nov 2021 16:03:57 +0000 Subject: KVM: Move wiping of the kvm->vcpus array to common code All architectures have similar loops iterating over the vcpus, freeing one vcpu at a time, and eventually wiping the reference off the vcpus array. They are also inconsistently taking the kvm->lock mutex when wiping the references from the array. Make this code common, which will simplify further changes. The locking is dropped altogether, as this should only be called when there is no further references on the kvm structure. Reviewed-by: Claudio Imbrenda Signed-off-by: Marc Zyngier Message-Id: <20211116160403.4074052-2-maz@kernel.org> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arm.c | 10 +--------- arch/mips/kvm/mips.c | 21 +-------------------- arch/powerpc/kvm/powerpc.c | 10 +--------- arch/riscv/kvm/vm.c | 10 +--------- arch/s390/kvm/kvm-s390.c | 18 +----------------- arch/x86/kvm/x86.c | 9 +-------- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 17 +++++++++++++++-- 8 files changed, 22 insertions(+), 75 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e4727dc771bf..362b10cb992c 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -175,19 +175,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) */ void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - bitmap_free(kvm->arch.pmu_filter); kvm_vgic_destroy(kvm); - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index aa20d074d388..6aa5e3771d05 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -171,25 +171,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) return 0; } -void kvm_mips_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) { - kvm_vcpu_destroy(vcpu); - } - - mutex_lock(&kvm->lock); - - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - - mutex_unlock(&kvm->lock); -} - static void kvm_mips_free_gpa_pt(struct kvm *kvm) { /* It should always be safe to remove after flushing the whole range */ @@ -199,7 +180,7 @@ static void kvm_mips_free_gpa_pt(struct kvm *kvm) void kvm_arch_destroy_vm(struct kvm *kvm) { - kvm_mips_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); kvm_mips_free_gpa_pt(kvm); } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index a72920f4f221..98f5d90ebf5a 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -463,9 +463,6 @@ err_out: void kvm_arch_destroy_vm(struct kvm *kvm) { - unsigned int i; - struct kvm_vcpu *vcpu; - #ifdef CONFIG_KVM_XICS /* * We call kick_all_cpus_sync() to ensure that all @@ -476,14 +473,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kick_all_cpus_sync(); #endif - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); + kvm_destroy_vcpus(kvm); mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); kvmppc_core_destroy_vm(kvm); diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index fb18af34a4b5..7619691d8953 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -46,15 +46,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) void kvm_arch_destroy_vm(struct kvm *kvm) { - int i; - - for (i = 0; i < KVM_MAX_VCPUS; ++i) { - if (kvm->vcpus[i]) { - kvm_vcpu_destroy(kvm->vcpus[i]); - kvm->vcpus[i] = NULL; - } - } - atomic_set(&kvm->online_vcpus, 0); + kvm_destroy_vcpus(kvm); } int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 14a18ba5ff2c..6eeb59af5d74 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2821,27 +2821,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)(vcpu->arch.sie_block)); } -static void kvm_free_vcpus(struct kvm *kvm) -{ - unsigned int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); -} - void kvm_arch_destroy_vm(struct kvm *kvm) { u16 rc, rrc; - kvm_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); sca_dispose(kvm); kvm_s390_gisa_destroy(kvm); /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index e0aa4dd53c7f..0e6d11a726cd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11423,15 +11423,8 @@ static void kvm_free_vcpus(struct kvm *kvm) kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } - kvm_for_each_vcpu(i, vcpu, kvm) - kvm_vcpu_destroy(vcpu); - - mutex_lock(&kvm->lock); - for (i = 0; i < atomic_read(&kvm->online_vcpus); i++) - kvm->vcpus[i] = NULL; - atomic_set(&kvm->online_vcpus, 0); - mutex_unlock(&kvm->lock); + kvm_destroy_vcpus(kvm); } void kvm_arch_sync_events(struct kvm *kvm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c310648cc8f1..e2f9f8f67c58 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -733,7 +733,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) if (WARN_ON_ONCE(!memslot->npages)) { \ } else -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu); +void kvm_destroy_vcpus(struct kvm *kvm); void vcpu_load(struct kvm_vcpu *vcpu); void vcpu_put(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 72c4e6b39389..0a504c7988dc 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -435,7 +435,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->last_used_slot = 0; } -void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) +static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_dirty_ring_free(&vcpu->dirty_ring); kvm_arch_vcpu_destroy(vcpu); @@ -450,7 +450,20 @@ void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } -EXPORT_SYMBOL_GPL(kvm_vcpu_destroy); + +void kvm_destroy_vcpus(struct kvm *kvm) +{ + unsigned int i; + struct kvm_vcpu *vcpu; + + kvm_for_each_vcpu(i, vcpu, kvm) { + kvm_vcpu_destroy(vcpu); + kvm->vcpus[i] = NULL; + } + + atomic_set(&kvm->online_vcpus, 0); +} +EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) -- cgit v1.2.3 From c5b077549136584618a66258f09d8d4b41e7409c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Nov 2021 16:04:01 +0000 Subject: KVM: Convert the kvm->vcpus array to a xarray At least on arm64 and x86, the vcpus array is pretty huge (up to 1024 entries on x86) and is mostly empty in the majority of the cases (running 1k vcpu VMs is not that common). This mean that we end-up with a 4kB block of unused memory in the middle of the kvm structure. Instead of wasting away this memory, let's use an xarray instead, which gives us almost the same flexibility as a normal array, but with a reduced memory usage with smaller VMs. Signed-off-by: Marc Zyngier Message-Id: <20211116160403.4074052-6-maz@kernel.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 5 +++-- virt/kvm/kvm_main.c | 15 +++++++++------ 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e2f9f8f67c58..2201dc07126a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -552,7 +553,7 @@ struct kvm { struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; - struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; + struct xarray vcpu_array; /* Used to wait for completion of MMU notifiers. */ spinlock_t mn_invalidate_lock; @@ -701,7 +702,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); - return kvm->vcpus[i]; + return xa_load(&kvm->vcpu_array, i); } #define kvm_for_each_vcpu(idx, vcpup, kvm) \ diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0a504c7988dc..594f90307b20 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -458,7 +458,7 @@ void kvm_destroy_vcpus(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { kvm_vcpu_destroy(vcpu); - kvm->vcpus[i] = NULL; + xa_erase(&kvm->vcpu_array, i); } atomic_set(&kvm->online_vcpus, 0); @@ -1063,6 +1063,7 @@ static struct kvm *kvm_create_vm(unsigned long type) mutex_init(&kvm->slots_arch_lock); spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); + xa_init(&kvm->vcpu_array); INIT_LIST_HEAD(&kvm->devices); @@ -3598,7 +3599,10 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); - BUG_ON(kvm->vcpus[vcpu->vcpu_idx]); + r = xa_insert(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, GFP_KERNEL_ACCOUNT); + BUG_ON(r == -EBUSY); + if (r) + goto unlock_vcpu_destroy; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", @@ -3608,15 +3612,14 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { + xa_erase(&kvm->vcpu_array, vcpu->vcpu_idx); kvm_put_kvm_no_destroy(kvm); goto unlock_vcpu_destroy; } - kvm->vcpus[vcpu->vcpu_idx] = vcpu; - /* - * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus - * before kvm->online_vcpu's incremented value. + * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu + * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); -- cgit v1.2.3 From 46808a4cb89708c2e5b264eb9d1035762581921b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Nov 2021 16:04:02 +0000 Subject: KVM: Use 'unsigned long' as kvm_for_each_vcpu()'s index Everywhere we use kvm_for_each_vpcu(), we use an int as the vcpu index. Unfortunately, we're about to move rework the iterator, which requires this to be upgrade to an unsigned long. Let's bite the bullet and repaint all of it in one go. Signed-off-by: Marc Zyngier Message-Id: <20211116160403.4074052-7-maz@kernel.org> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arch_timer.c | 8 ++++---- arch/arm64/kvm/arm.c | 6 +++--- arch/arm64/kvm/pmu-emul.c | 2 +- arch/arm64/kvm/psci.c | 6 +++--- arch/arm64/kvm/reset.c | 2 +- arch/arm64/kvm/vgic/vgic-init.c | 10 ++++++---- arch/arm64/kvm/vgic/vgic-kvm-device.c | 2 +- arch/arm64/kvm/vgic/vgic-mmio-v2.c | 3 +-- arch/arm64/kvm/vgic/vgic-mmio-v3.c | 7 ++++--- arch/arm64/kvm/vgic/vgic-v3.c | 4 ++-- arch/arm64/kvm/vgic/vgic-v4.c | 5 +++-- arch/arm64/kvm/vgic/vgic.c | 2 +- arch/powerpc/kvm/book3s_32_mmu.c | 2 +- arch/powerpc/kvm/book3s_64_mmu.c | 2 +- arch/powerpc/kvm/book3s_hv.c | 8 ++++---- arch/powerpc/kvm/book3s_pr.c | 2 +- arch/powerpc/kvm/book3s_xics.c | 6 +++--- arch/powerpc/kvm/book3s_xics.h | 2 +- arch/powerpc/kvm/book3s_xive.c | 15 +++++++++------ arch/powerpc/kvm/book3s_xive.h | 4 ++-- arch/powerpc/kvm/book3s_xive_native.c | 8 ++++---- arch/powerpc/kvm/e500_emulate.c | 2 +- arch/riscv/kvm/vcpu_sbi.c | 2 +- arch/riscv/kvm/vmid.c | 2 +- arch/s390/kvm/interrupt.c | 2 +- arch/s390/kvm/kvm-s390.c | 21 +++++++++++---------- arch/s390/kvm/kvm-s390.h | 4 ++-- arch/x86/kvm/hyperv.c | 7 ++++--- arch/x86/kvm/i8254.c | 2 +- arch/x86/kvm/i8259.c | 5 +++-- arch/x86/kvm/ioapic.c | 4 ++-- arch/x86/kvm/irq_comm.c | 7 ++++--- arch/x86/kvm/kvm_onhyperv.c | 3 ++- arch/x86/kvm/lapic.c | 6 +++--- arch/x86/kvm/svm/avic.c | 2 +- arch/x86/kvm/svm/sev.c | 9 +++++---- arch/x86/kvm/x86.c | 23 ++++++++++++----------- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 13 +++++++------ 39 files changed, 118 insertions(+), 104 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 3df67c127489..d6f4114f1d11 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -750,7 +750,7 @@ int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu) /* Make the updates of cntvoff for all vtimer contexts atomic */ static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff) { - int i; + unsigned long i; struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tmp; @@ -1189,8 +1189,8 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu) static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu) { - int vtimer_irq, ptimer_irq; - int i, ret; + int vtimer_irq, ptimer_irq, ret; + unsigned long i; vtimer_irq = vcpu_vtimer(vcpu)->irq.irq; ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu)); @@ -1297,7 +1297,7 @@ void kvm_timer_init_vhe(void) static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { vcpu_vtimer(vcpu)->irq.irq = vtimer_irq; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 362b10cb992c..b6e65c6eb1d3 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -631,7 +631,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm) void kvm_arm_halt_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) @@ -641,7 +641,7 @@ void kvm_arm_halt_guest(struct kvm *kvm) void kvm_arm_resume_guest(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -2027,7 +2027,7 @@ static int finalize_hyp_mode(void) struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; mpidr &= MPIDR_HWID_BITMASK; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index a5e4bbf5e68f..0404357705a8 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -900,7 +900,7 @@ static int kvm_arm_pmu_v3_init(struct kvm_vcpu *vcpu) */ static bool pmu_irq_is_valid(struct kvm *kvm, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 74c47d420253..ed675fce8fb7 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -121,8 +121,8 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) { - int i, matching_cpus = 0; - unsigned long mpidr; + int matching_cpus = 0; + unsigned long i, mpidr; unsigned long target_affinity; unsigned long target_affinity_mask; unsigned long lowest_affinity_level; @@ -164,7 +164,7 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu) static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; /* diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 426bd7fbc3fd..97de30a79770 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -170,7 +170,7 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu) { struct kvm_vcpu *tmp; bool is32bit; - int i; + unsigned long i; is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); if (!cpus_have_const_cap(ARM64_HAS_32BIT_EL1) && is32bit) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 0a06d0648970..a7382bda9676 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -70,8 +70,9 @@ void kvm_vgic_early_init(struct kvm *kvm) */ int kvm_vgic_create(struct kvm *kvm, u32 type) { - int i, ret; struct kvm_vcpu *vcpu; + unsigned long i; + int ret; if (irqchip_in_kernel(kvm)) return -EEXIST; @@ -255,7 +256,8 @@ int vgic_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int ret = 0, i, idx; + int ret = 0, i; + unsigned long idx; if (vgic_initialized(kvm)) return 0; @@ -308,7 +310,7 @@ int vgic_init(struct kvm *kvm) goto out; } - kvm_for_each_vcpu(i, vcpu, kvm) + kvm_for_each_vcpu(idx, vcpu, kvm) kvm_vgic_vcpu_enable(vcpu); ret = kvm_vgic_setup_default_irq_routing(kvm); @@ -370,7 +372,7 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static void __kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; vgic_debug_destroy(kvm); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index 0d000d2fe8d2..c6d52a1fd9c8 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -325,7 +325,7 @@ void unlock_all_vcpus(struct kvm *kvm) bool lock_all_vcpus(struct kvm *kvm) { struct kvm_vcpu *tmp_vcpu; - int c; + unsigned long c; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c index 5f9014ae595b..12e4c223e6b8 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c @@ -113,9 +113,8 @@ static void vgic_mmio_write_sgir(struct kvm_vcpu *source_vcpu, int intid = val & 0xf; int targets = (val >> 16) & 0xff; int mode = (val >> 24) & 0x03; - int c; struct kvm_vcpu *vcpu; - unsigned long flags; + unsigned long flags, c; switch (mode) { case 0x0: /* as specified by targets */ diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index bf7ec4a78497..82906cb3f713 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -754,7 +754,8 @@ static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu) static int vgic_register_all_redist_iodevs(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c, ret = 0; + unsigned long c; + int ret = 0; kvm_for_each_vcpu(c, vcpu, kvm) { ret = vgic_register_redist_iodev(vcpu); @@ -995,10 +996,10 @@ void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1) struct kvm_vcpu *c_vcpu; u16 target_cpus; u64 mpidr; - int sgi, c; + int sgi; int vcpu_id = vcpu->vcpu_id; bool broadcast; - unsigned long flags; + unsigned long c, flags; sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT; broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 04f62c4b07fb..5fedaee15e72 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -542,13 +542,13 @@ int vgic_v3_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; int ret = 0; - int c; + unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { - kvm_debug("vcpu %d redistributor base not set\n", c); + kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index 772dd15a22c7..ad06ba6c9b00 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -189,7 +189,7 @@ void vgic_v4_configure_vsgis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_arm_halt_guest(kvm); @@ -235,7 +235,8 @@ int vgic_v4_init(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; - int i, nr_vcpus, ret; + int nr_vcpus, ret; + unsigned long i; if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index 5dad4996cfb2..9b98876a8a93 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -990,7 +990,7 @@ int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu) void vgic_kick_vcpus(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int c; + unsigned long c; /* * We've injected an interrupt, time to find out who deserves diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c index 3fbd570f9c1e..0215f32932a9 100644 --- a/arch/powerpc/kvm/book3s_32_mmu.c +++ b/arch/powerpc/kvm/book3s_32_mmu.c @@ -337,7 +337,7 @@ static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum, static void kvmppc_mmu_book3s_32_tlbie(struct kvm_vcpu *vcpu, ulong ea, bool large) { - int i; + unsigned long i; struct kvm_vcpu *v; /* flush this VA on all cpus */ diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index feee40cb2ba1..61290282fd9e 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -530,7 +530,7 @@ static void kvmppc_mmu_book3s_64_tlbie(struct kvm_vcpu *vcpu, ulong va, bool large) { u64 mask = 0xFFFFFFFFFULL; - long i; + unsigned long i; struct kvm_vcpu *v; dprintk("KVM MMU: tlbie(0x%lx)\n", va); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 7b74fc0a986b..32873c6985f9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -1993,7 +1993,7 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, */ if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.vcore != vc) @@ -4786,8 +4786,8 @@ static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm, { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int i, r; - unsigned long n; + int r; + unsigned long n, i; unsigned long *buf, *p; struct kvm_vcpu *vcpu; @@ -5861,7 +5861,7 @@ static int kvmhv_svm_off(struct kvm *kvm) int mmu_was_ready; int srcu_idx; int ret = 0; - int i; + unsigned long i; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) return ret; diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 6bc9425acb32..bb0612c49b92 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -428,7 +428,7 @@ static int kvmppc_core_check_requests_pr(struct kvm_vcpu *vcpu) /************* MMU Notifiers *************/ static bool do_kvm_unmap_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { - long i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index ebd5d920de8c..9cc466006e8b 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -942,8 +942,8 @@ static int xics_debug_show(struct seq_file *m, void *private) struct kvmppc_xics *xics = m->private; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; - int icsid, i; - unsigned long flags; + int icsid; + unsigned long flags, i; unsigned long t_rm_kick_vcpu, t_rm_check_resend; unsigned long t_rm_notify_eoi; unsigned long t_reject, t_check_resend; @@ -1340,7 +1340,7 @@ static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) static void kvmppc_xics_release(struct kvm_device *dev) { struct kvmppc_xics *xics = dev->private; - int i; + unsigned long i; struct kvm *kvm = xics->kvm; struct kvm_vcpu *vcpu; diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h index 6231f76bdd66..8e4c79e2fcd8 100644 --- a/arch/powerpc/kvm/book3s_xics.h +++ b/arch/powerpc/kvm/book3s_xics.h @@ -116,7 +116,7 @@ static inline struct kvmppc_icp *kvmppc_xics_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.icp && nr == vcpu->arch.icp->server_num) diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c index 225008882958..e216c068075d 100644 --- a/arch/powerpc/kvm/book3s_xive.c +++ b/arch/powerpc/kvm/book3s_xive.c @@ -368,7 +368,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio) { struct kvmppc_xive *xive = kvm->arch.xive; struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; lockdep_assert_held(&xive->lock); @@ -439,7 +440,8 @@ static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio) int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio) { struct kvm_vcpu *vcpu; - int i, rc; + unsigned long i; + int rc; /* Locate target server */ vcpu = kvmppc_xive_find_server(kvm, *server); @@ -1519,7 +1521,8 @@ static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q) static void xive_pre_save_scan(struct kvmppc_xive *xive) { struct kvm_vcpu *vcpu = NULL; - int i, j; + unsigned long i; + int j; /* * See comment in xive_get_source() about how this @@ -1700,7 +1703,7 @@ static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu; @@ -2037,7 +2040,7 @@ static void kvmppc_xive_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive device\n"); @@ -2291,7 +2294,7 @@ static int xive_debug_show(struct seq_file *m, void *private) u64 t_vm_h_cppr = 0; u64 t_vm_h_eoi = 0; u64 t_vm_h_ipi = 0; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h index e6a9651c6f1e..09d0657596c3 100644 --- a/arch/powerpc/kvm/book3s_xive.h +++ b/arch/powerpc/kvm/book3s_xive.h @@ -199,7 +199,7 @@ struct kvmppc_xive_vcpu { static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num) @@ -240,7 +240,7 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server) static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id) diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c index 99db9ac49901..561a5bfe0468 100644 --- a/arch/powerpc/kvm/book3s_xive_native.c +++ b/arch/powerpc/kvm/book3s_xive_native.c @@ -807,7 +807,7 @@ static int kvmppc_xive_reset(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -916,7 +916,7 @@ static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive) { struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; pr_devel("%s\n", __func__); @@ -1017,7 +1017,7 @@ static void kvmppc_xive_native_release(struct kvm_device *dev) struct kvmppc_xive *xive = dev->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; pr_devel("Releasing xive native device\n"); @@ -1214,7 +1214,7 @@ static int xive_native_debug_show(struct seq_file *m, void *private) struct kvmppc_xive *xive = m->private; struct kvm *kvm = xive->kvm; struct kvm_vcpu *vcpu; - unsigned int i; + unsigned long i; if (!kvm) return 0; diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c index 64eb833e9f02..051102d50c31 100644 --- a/arch/powerpc/kvm/e500_emulate.c +++ b/arch/powerpc/kvm/e500_emulate.c @@ -65,7 +65,7 @@ static int kvmppc_e500_emul_msgsnd(struct kvm_vcpu *vcpu, int rb) ulong param = vcpu->arch.regs.gpr[rb]; int prio = dbell2prio(rb); int pir = param & PPC_DBELL_PIR_MASK; - int i; + unsigned long i; struct kvm_vcpu *cvcpu; if (prio < 0) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index 3b0e703d22cf..d0d2bcab2f7b 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -60,7 +60,7 @@ int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, struct kvm_run *run, u32 type) { - int i; + unsigned long i; struct kvm_vcpu *tmp; kvm_for_each_vcpu(i, tmp, vcpu->kvm) diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 2c6253b293bc..807228f8f409 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -65,7 +65,7 @@ bool kvm_riscv_stage2_vmid_ver_changed(struct kvm_vmid *vmid) void kvm_riscv_stage2_vmid_update(struct kvm_vcpu *vcpu) { - int i; + unsigned long i; struct kvm_vcpu *v; struct cpumask hmask; struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid; diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c3bd993fdd0c..1aa094810f6d 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2659,7 +2659,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr) static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = 0; - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; switch (attr->group) { diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7a0f5abaa484..fd5f4ec1b4b9 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -295,7 +295,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val, { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; unsigned long long *delta = v; list_for_each_entry(kvm, &vm_list, vm_list) { @@ -682,7 +682,7 @@ out: static void icpt_operexc_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -936,7 +936,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu); void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_s390_vcpu_block_all(kvm); @@ -1021,7 +1021,7 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr) static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req) { - int cx; + unsigned long cx; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(cx, vcpu, kvm) @@ -2206,7 +2206,7 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) struct kvm_vcpu *vcpu; u16 rc, rrc; int ret = 0; - int i; + unsigned long i; /* * We ignore failures and try to destroy as many CPUs as possible. @@ -2230,7 +2230,8 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp) static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc) { - int i, r = 0; + unsigned long i; + int r = 0; u16 dummy; struct kvm_vcpu *vcpu; @@ -2929,7 +2930,7 @@ static int sca_switch_to_extended(struct kvm *kvm) struct bsca_block *old_sca = kvm->arch.sca; struct esca_block *new_sca; struct kvm_vcpu *vcpu; - unsigned int vcpu_idx; + unsigned long vcpu_idx; u32 scaol, scaoh; if (kvm->arch.use_esca) @@ -3411,7 +3412,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, struct kvm *kvm = gmap->private; struct kvm_vcpu *vcpu; unsigned long prefix; - int i; + unsigned long i; if (gmap_is_shadow(gmap)) return; @@ -3904,7 +3905,7 @@ void kvm_s390_set_tod_clock(struct kvm *kvm, { struct kvm_vcpu *vcpu; union tod_clock clk; - int i; + unsigned long i; mutex_lock(&kvm->lock); preempt_disable(); @@ -4536,7 +4537,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu) static void __disable_ibs_on_all_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index c07a050d757d..b887fe7a7064 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -357,7 +357,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu); static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; WARN_ON(!mutex_is_locked(&kvm->lock)); @@ -367,7 +367,7 @@ static inline void kvm_s390_vcpu_block_all(struct kvm *kvm) static inline void kvm_s390_vcpu_unblock_all(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 5e19e6e4c2ce..7179fa645eda 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -164,7 +164,7 @@ static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, static struct kvm_vcpu *get_vcpu_by_vpidx(struct kvm *kvm, u32 vpidx) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (vpidx >= KVM_MAX_VCPUS) return NULL; @@ -1716,7 +1716,8 @@ static __always_inline unsigned long *sparse_set_to_vcpu_mask( { struct kvm_hv *hv = to_kvm_hv(kvm); struct kvm_vcpu *vcpu; - int i, bank, sbank = 0; + int bank, sbank = 0; + unsigned long i; memset(vp_bitmap, 0, KVM_HV_MAX_SPARSE_VCPU_SET_BITS * sizeof(*vp_bitmap)); @@ -1863,7 +1864,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, .vector = vector }; struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 5a69cce4d72d..0b65a764ed3a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -242,7 +242,7 @@ static void pit_do_work(struct kthread_work *work) struct kvm_pit *pit = container_of(work, struct kvm_pit, expired); struct kvm *kvm = pit->kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; struct kvm_kpit_state *ps = &pit->pit_state; if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0)) diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index 0b80263d46d8..814064d06016 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -50,7 +50,7 @@ static void pic_unlock(struct kvm_pic *s) { bool wakeup = s->wakeup_needed; struct kvm_vcpu *vcpu; - int i; + unsigned long i; s->wakeup_needed = false; @@ -270,7 +270,8 @@ int kvm_pic_read_irq(struct kvm *kvm) static void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq, i; + int irq; + unsigned long i; struct kvm_vcpu *vcpu; u8 edge_irr = s->irr & ~s->elcr; bool found = false; diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 816a82515dcd..decfa36b7891 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -149,7 +149,7 @@ void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu) static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; if (RTC_GSI >= IOAPIC_NUM_PINS) return; @@ -184,7 +184,7 @@ static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic) static void ioapic_lazy_update_eoi(struct kvm_ioapic *ioapic, int irq) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; union kvm_ioapic_redirect_entry *entry = &ioapic->redirtbl[irq]; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index d5b72a08e566..39ad02d6dc63 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -45,9 +45,9 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, struct dest_map *dest_map) { - int i, r = -1; + int r = -1; struct kvm_vcpu *vcpu, *lowest = NULL; - unsigned long dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)]; unsigned int dest_vcpus = 0; if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map)) @@ -320,7 +320,8 @@ int kvm_set_routing_entry(struct kvm *kvm, bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_vcpu **dest_vcpu) { - int i, r = 0; + int r = 0; + unsigned long i; struct kvm_vcpu *vcpu; if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu)) diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index c7db2df50a7a..b469f45e3fe4 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -33,7 +33,8 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; - int ret = 0, i, nr_unique_valid_roots; + int ret = 0, nr_unique_valid_roots; + unsigned long i; hpa_t root; spin_lock(&kvm_arch->hv_root_tdp_lock); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index f206fc35deff..451e80306b51 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -185,7 +185,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) { struct kvm_apic_map *new, *old = NULL; struct kvm_vcpu *vcpu; - int i; + unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ @@ -1172,8 +1172,8 @@ void kvm_bitmap_or_dest_vcpus(struct kvm *kvm, struct kvm_lapic_irq *irq, struct kvm_lapic *src = NULL; struct kvm_apic_map *map; struct kvm_vcpu *vcpu; - unsigned long bitmap; - int i, vcpu_idx; + unsigned long bitmap, i; + int vcpu_idx; bool ret; rcu_read_lock(); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 8f9af7b7dbbe..b7200595cbd4 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -293,7 +293,7 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { bool m = kvm_apic_match_dest(vcpu, source, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 7656a2c5662a..322553322202 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -636,7 +636,8 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_vcpu *vcpu; - int i, ret; + unsigned long i; + int ret; if (!sev_es_guest(kvm)) return -ENOTTY; @@ -1593,7 +1594,7 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm) static int sev_lock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, j; + unsigned long i, j; kvm_for_each_vcpu(i, vcpu, kvm) { if (mutex_lock_killable(&vcpu->mutex)) @@ -1615,7 +1616,7 @@ out_unlock: static void sev_unlock_vcpus_for_migration(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { mutex_unlock(&vcpu->mutex); @@ -1642,7 +1643,7 @@ static void sev_migrate_from(struct kvm_sev_info *dst, static int sev_es_migrate_from(struct kvm *dst, struct kvm *src) { - int i; + unsigned long i; struct kvm_vcpu *dst_vcpu, *src_vcpu; struct vcpu_svm *dst_svm, *src_svm; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0e6d11a726cd..96bcf2035bdc 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2816,7 +2816,7 @@ static void kvm_end_pvclock_update(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct kvm_vcpu *vcpu; - int i; + unsigned long i; write_seqcount_end(&ka->pvclock_sc); raw_spin_unlock_irq(&ka->tsc_write_lock); @@ -3065,7 +3065,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) static void kvmclock_update_fn(struct work_struct *work) { - int i; + unsigned long i; struct delayed_work *dwork = to_delayed_work(work); struct kvm_arch *ka = container_of(dwork, struct kvm_arch, kvmclock_update_work); @@ -5692,7 +5692,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) * VM-Exit. */ struct kvm_vcpu *vcpu; - int i; + unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); @@ -5961,7 +5961,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) static int kvm_arch_suspend_notifier(struct kvm *kvm) { struct kvm_vcpu *vcpu; - int i, ret = 0; + unsigned long i; + int ret = 0; mutex_lock(&kvm->lock); kvm_for_each_vcpu(i, vcpu, kvm) { @@ -8388,7 +8389,8 @@ static void __kvmclock_cpufreq_notifier(struct cpufreq_freqs *freq, int cpu) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i, send_ipi = 0; + int send_ipi = 0; + unsigned long i; /* * We allow guests to temporarily run on slowing clocks, @@ -8561,9 +8563,8 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { static void pvclock_gtod_update_fn(struct work_struct *work) { struct kvm *kvm; - struct kvm_vcpu *vcpu; - int i; + unsigned long i; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -10672,7 +10673,7 @@ static void kvm_arch_vcpu_guestdbg_update_apicv_inhibit(struct kvm *kvm) { bool inhibit = false; struct kvm_vcpu *vcpu; - int i; + unsigned long i; down_write(&kvm->arch.apicv_update_lock); @@ -11160,7 +11161,7 @@ int kvm_arch_hardware_enable(void) { struct kvm *kvm; struct kvm_vcpu *vcpu; - int i; + unsigned long i; int ret; u64 local_tsc; u64 max_tsc = 0; @@ -11413,7 +11414,7 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) static void kvm_free_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; /* @@ -11659,7 +11660,7 @@ out_free: void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) { struct kvm_vcpu *vcpu; - int i; + unsigned long i; /* * memslots->generation has been incremented. diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2201dc07126a..7da6086262c6 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -714,7 +714,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { struct kvm_vcpu *vcpu = NULL; - int i; + unsigned long i; if (id < 0) return NULL; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 594f90307b20..1c68384a7c4b 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -305,8 +305,9 @@ bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, { struct kvm_vcpu *vcpu; struct cpumask *cpus; + unsigned long i; bool called; - int i, me; + int me; me = get_cpu(); @@ -453,7 +454,7 @@ static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) void kvm_destroy_vcpus(struct kvm *kvm) { - unsigned int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { @@ -3389,10 +3390,10 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + unsigned long i; int yielded = 0; int try = 3; int pass; - int i; kvm_vcpu_set_in_spin_loop(me, true); /* @@ -4201,7 +4202,7 @@ static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; int cleared = 0; @@ -5120,7 +5121,7 @@ static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; *val = 0; @@ -5133,7 +5134,7 @@ static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { - int i; + unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) -- cgit v1.2.3 From 214bd3a6f46981b7867946e1b4f628a06bcf2091 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 16 Nov 2021 16:04:03 +0000 Subject: KVM: Convert kvm_for_each_vcpu() to using xa_for_each_range() Now that the vcpu array is backed by an xarray, use the optimised iterator that matches the underlying data structure. Suggested-by: Sean Christopherson Signed-off-by: Marc Zyngier Message-Id: <20211116160403.4074052-8-maz@kernel.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7da6086262c6..66548287ed42 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -705,11 +705,9 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) return xa_load(&kvm->vcpu_array, i); } -#define kvm_for_each_vcpu(idx, vcpup, kvm) \ - for (idx = 0; \ - idx < atomic_read(&kvm->online_vcpus) && \ - (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \ - idx++) +#define kvm_for_each_vcpu(idx, vcpup, kvm) \ + xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \ + (atomic_read(&kvm->online_vcpus) - 1)) static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) { -- cgit v1.2.3 From afa319a54a8c760ba59683cd3c4318635049a664 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 6 Dec 2021 20:54:07 +0100 Subject: KVM: Require total number of memslot pages to fit in an unsigned long Explicitly disallow creating more memslot pages than can fit in an unsigned long, KVM doesn't correctly handle a total number of memslot pages that doesn't fit in an unsigned long and remedying that would be a waste of time. For a 64-bit kernel, this is a nop as memslots are not allowed to overlap in the gfn address space. With a 32-bit kernel, userspace can at most address 3gb of virtual memory, whereas wrapping the total number of pages would require 4tb+ of guest physical memory. Even with x86's second address space for SMM, userspace would need to alias all of guest memory more than one _thousand_ times. And on older x86 hardware with MAXPHYADDR < 43, the guest couldn't actually access any of those aliases even if userspace lied about guest.MAXPHYADDR. On 390 and arm64, this is a nop as they don't support 32-bit hosts. On x86, practically speaking this is simply acknowledging reality as the existing kvm_mmu_calculate_default_mmu_pages() assumes the total number of pages fits in an "unsigned long". On PPC, this is likely a nop as every flavor of PPC KVM assumes gfns (and gpas!) fit in unsigned long. arch/powerpc/kvm/book3s_32_mmu_host.c goes a step further and fails the build if CONFIG_PTE_64BIT=y, which presumably means that it does't support 64-bit physical addresses. On MIPS, this is also likely a nop as the core MMU helpers assume gpas fit in unsigned long, e.g. see kvm_mips_##name##_pte. And finally, RISC-V is a "don't care" as it doesn't exist in any release, i.e. there is no established ABI to break. Signed-off-by: Sean Christopherson Reviewed-by: Maciej S. Szmigiero Signed-off-by: Maciej S. Szmigiero Message-Id: <1c2c91baf8e78acccd4dad38da591002e61c013c.1638817638.git.maciej.szmigiero@oracle.com> --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 66548287ed42..e38705359af5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -552,6 +552,7 @@ struct kvm { */ struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ + unsigned long nr_memslot_pages; struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct xarray vcpu_array; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1c68384a7c4b..538fd57ea339 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1638,6 +1638,15 @@ static int kvm_set_memslot(struct kvm *kvm, update_memslots(slots, new, change); slots = install_new_memslots(kvm, as_id, slots); + /* + * Update the total number of memslot pages before calling the arch + * hook so that architectures can consume the result directly. + */ + if (change == KVM_MR_DELETE) + kvm->nr_memslot_pages -= old.npages; + else if (change == KVM_MR_CREATE) + kvm->nr_memslot_pages += new->npages; + kvm_arch_commit_memory_region(kvm, mem, &old, new, change); /* Free the old memslot's metadata. Note, this is the full copy!!! */ @@ -1668,6 +1677,9 @@ static int kvm_delete_memslot(struct kvm *kvm, if (!old->npages) return -EINVAL; + if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) + return -EIO; + memset(&new, 0, sizeof(new)); new.id = old->id; /* @@ -1751,6 +1763,13 @@ int __kvm_set_memory_region(struct kvm *kvm, if (!old.npages) { change = KVM_MR_CREATE; new.dirty_bitmap = NULL; + + /* + * To simplify KVM internals, the total number of pages across + * all memslots must fit in an unsigned long. + */ + if ((kvm->nr_memslot_pages + new.npages) < kvm->nr_memslot_pages) + return -EINVAL; } else { /* Modify an existing slot. */ if ((new.userspace_addr != old.userspace_addr) || (new.npages != old.npages) || -- cgit v1.2.3 From 537a17b3149300987456e8949ccb991e604047d6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 6 Dec 2021 20:54:11 +0100 Subject: KVM: Let/force architectures to deal with arch specific memslot data Pass the "old" slot to kvm_arch_prepare_memory_region() and force arch code to handle propagating arch specific data from "new" to "old" when necessary. This is a baby step towards dynamically allocating "new" from the get go, and is a (very) minor performance boost on x86 due to not unnecessarily copying arch data. For PPC HV, copy the rmap in the !CREATE and !DELETE paths, i.e. for MOVE and FLAGS_ONLY. This is functionally a nop as the previous behavior would overwrite the pointer for CREATE, and eventually discard/ignore it for DELETE. For x86, copy the arch data only for FLAGS_ONLY changes. Unlike PPC HV, x86 needs to reallocate arch data in the MOVE case as the size of x86's allocations depend on the alignment of the memslot's gfn. Opportunistically tweak kvm_arch_prepare_memory_region()'s param order to match the "commit" prototype. Signed-off-by: Sean Christopherson Reviewed-by: Maciej S. Szmigiero [mss: add missing RISCV kvm_arch_prepare_memory_region() change] Signed-off-by: Maciej S. Szmigiero Message-Id: <67dea5f11bbcfd71e3da5986f11e87f5dd4013f9.1638817639.git.maciej.szmigiero@oracle.com> --- arch/arm64/kvm/mmu.c | 7 ++++--- arch/mips/kvm/mips.c | 3 ++- arch/powerpc/include/asm/kvm_ppc.h | 10 ++++++---- arch/powerpc/kvm/book3s.c | 12 ++++++------ arch/powerpc/kvm/book3s_hv.c | 17 ++++++++++------- arch/powerpc/kvm/book3s_pr.c | 9 +++++---- arch/powerpc/kvm/booke.c | 5 +++-- arch/powerpc/kvm/powerpc.c | 5 +++-- arch/riscv/kvm/mmu.c | 7 ++++--- arch/s390/kvm/kvm-s390.c | 3 ++- arch/x86/kvm/x86.c | 15 +++++++++++---- include/linux/kvm_host.h | 3 ++- virt/kvm/kvm_main.c | 5 +---- 13 files changed, 59 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 326cdfec74a1..5d474360bf6c 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1486,8 +1486,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { hva_t hva = mem->userspace_addr; @@ -1502,7 +1503,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the IPA * space addressable by the KVM guest IPA space. */ - if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) + if ((new->base_gfn + new->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT)) return -EFAULT; mmap_read_lock(current->mm); @@ -1536,7 +1537,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (vma->vm_flags & VM_PFNMAP) { /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; break; } diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 043204cd585f..b2ce10784eb0 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -214,8 +214,9 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index 671fbd1a765e..b01760dd1374 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -200,12 +200,13 @@ extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); extern int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); extern void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm, @@ -274,12 +275,13 @@ struct kvmppc_ops { int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log); void (*flush_memslot)(struct kvm *kvm, struct kvm_memory_slot *memslot); int (*prepare_memory_region)(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void (*commit_memory_region)(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); bool (*unmap_gfn_range)(struct kvm *kvm, struct kvm_gfn_range *range); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index b785f6772391..8250e8308674 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -847,17 +847,17 @@ void kvmppc_core_flush_memslot(struct kvm *kvm, struct kvm_memory_slot *memslot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { - return kvm->arch.kvm_ops->prepare_memory_region(kvm, memslot, mem, - change); + return kvm->arch.kvm_ops->prepare_memory_region(kvm, mem, old, new, change); } void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 32873c6985f9..d7594d49d288 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -4854,17 +4854,20 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *slot) } static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, - struct kvm_memory_slot *slot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { unsigned long npages = mem->memory_size >> PAGE_SHIFT; if (change == KVM_MR_CREATE) { - slot->arch.rmap = vzalloc(array_size(npages, - sizeof(*slot->arch.rmap))); - if (!slot->arch.rmap) + new->arch.rmap = vzalloc(array_size(npages, + sizeof(*new->arch.rmap))); + if (!new->arch.rmap) return -ENOMEM; + } else if (change != KVM_MR_DELETE) { + new->arch.rmap = old->arch.rmap; } return 0; @@ -4872,7 +4875,7 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm, static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index bb0612c49b92..ffb559cf25f4 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -1899,16 +1899,17 @@ static void kvmppc_core_flush_memslot_pr(struct kvm *kvm, } static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { return 0; } static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 8c15c90dd3a9..93c2ac2bee09 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -1821,8 +1821,9 @@ void kvmppc_core_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvmppc_core_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { return 0; @@ -1830,7 +1831,7 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm, void kvmppc_core_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - const struct kvm_memory_slot *old, + struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 98f5d90ebf5a..e875874cf836 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -698,11 +698,12 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { - return kvmppc_core_prepare_memory_region(kvm, memslot, mem, change); + return kvmppc_core_prepare_memory_region(kvm, mem, old, new, change); } void kvm_arch_commit_memory_region(struct kvm *kvm, diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index fc058ff5f4b6..50380f525345 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -477,8 +477,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { hva_t hva = mem->userspace_addr; @@ -494,7 +495,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, * Prevent userspace from creating a memory region outside of the GPA * space addressable by the KVM guest GPA space. */ - if ((memslot->base_gfn + memslot->npages) >= + if ((new->base_gfn + new->npages) >= (stage2_gpa_size >> PAGE_SHIFT)) return -EFAULT; @@ -541,7 +542,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, pa += vm_start - vma->vm_start; /* IO region dirty page logging not allowed */ - if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { ret = -EINVAL; goto out; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index fd5f4ec1b4b9..3beefadda0db 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5007,8 +5007,9 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change) { /* A few sanity checks. We can have memory slots which have to be diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 96bcf2035bdc..287ff4e43a13 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11674,13 +11674,20 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, - const struct kvm_userspace_memory_region *mem, - enum kvm_mr_change change) + const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) { if (change == KVM_MR_CREATE || change == KVM_MR_MOVE) - return kvm_alloc_memslot_metadata(kvm, memslot, + return kvm_alloc_memslot_metadata(kvm, new, mem->memory_size >> PAGE_SHIFT); + + if (change == KVM_MR_FLAGS_ONLY) + memcpy(&new->arch, &old->arch, sizeof(old->arch)); + else if (WARN_ON_ONCE(change != KVM_MR_DELETE)) + return -EIO; + return 0; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index e38705359af5..cb7311dc6f32 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -833,8 +833,9 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - struct kvm_memory_slot *memslot, const struct kvm_userspace_memory_region *mem, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a7a1c872fe6d..46060cc542ef 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1636,10 +1636,7 @@ static int kvm_set_memslot(struct kvm *kvm, old.as_id = new->as_id; } - /* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */ - memcpy(&new->arch, &old.arch, sizeof(old.arch)); - - r = kvm_arch_prepare_memory_region(kvm, new, mem, change); + r = kvm_arch_prepare_memory_region(kvm, mem, &old, new, change); if (r) goto out_slots; -- cgit v1.2.3 From 6a99c6e3f52a6f0d4c6ebcfa7359c718a19ffbe6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 6 Dec 2021 20:54:18 +0100 Subject: KVM: Stop passing kvm_userspace_memory_region to arch memslot hooks Drop the @mem param from kvm_arch_{prepare,commit}_memory_region() now that its use has been removed in all architectures. No functional change intended. Signed-off-by: Sean Christopherson Reviewed-by: Maciej S. Szmigiero Signed-off-by: Maciej S. Szmigiero Message-Id: --- arch/arm64/kvm/mmu.c | 2 -- arch/mips/kvm/mips.c | 2 -- arch/powerpc/kvm/powerpc.c | 2 -- arch/riscv/kvm/mmu.c | 2 -- arch/s390/kvm/kvm-s390.c | 2 -- arch/x86/kvm/x86.c | 2 -- include/linux/kvm_host.h | 2 -- virt/kvm/kvm_main.c | 9 ++++----- 8 files changed, 4 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index dd95350ea15d..9b2d881ccf49 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1463,7 +1463,6 @@ out: } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -1486,7 +1485,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index bda717301db8..e59cb6246f76 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -214,7 +214,6 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -223,7 +222,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 575140ecb23c..f1233500f4dc 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -698,7 +698,6 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -707,7 +706,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 573ade138204..7d884b15cf5e 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -462,7 +462,6 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -477,7 +476,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, } int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 959a568a97be..5dddd7817905 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -5007,7 +5007,6 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -5035,7 +5034,6 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2a7567adb799..f862c514c2c0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11674,7 +11674,6 @@ void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) } int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) @@ -11778,7 +11777,6 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, } void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index cb7311dc6f32..da0d4f21a150 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -833,12 +833,10 @@ int __kvm_set_memory_region(struct kvm *kvm, void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot); void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen); int kvm_arch_prepare_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change); void kvm_arch_commit_memory_region(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 46060cc542ef..373079a03710 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1550,7 +1550,6 @@ static void kvm_copy_memslots_arch(struct kvm_memslots *to, } static int kvm_set_memslot(struct kvm *kvm, - const struct kvm_userspace_memory_region *mem, struct kvm_memory_slot *new, enum kvm_mr_change change) { @@ -1636,7 +1635,7 @@ static int kvm_set_memslot(struct kvm *kvm, old.as_id = new->as_id; } - r = kvm_arch_prepare_memory_region(kvm, mem, &old, new, change); + r = kvm_arch_prepare_memory_region(kvm, &old, new, change); if (r) goto out_slots; @@ -1652,7 +1651,7 @@ static int kvm_set_memslot(struct kvm *kvm, else if (change == KVM_MR_CREATE) kvm->nr_memslot_pages += new->npages; - kvm_arch_commit_memory_region(kvm, mem, &old, new, change); + kvm_arch_commit_memory_region(kvm, &old, new, change); /* Free the old memslot's metadata. Note, this is the full copy!!! */ if (change == KVM_MR_DELETE) @@ -1737,7 +1736,7 @@ int __kvm_set_memory_region(struct kvm *kvm, new.id = id; new.as_id = as_id; - return kvm_set_memslot(kvm, mem, &new, KVM_MR_DELETE); + return kvm_set_memslot(kvm, &new, KVM_MR_DELETE); } new.as_id = as_id; @@ -1800,7 +1799,7 @@ int __kvm_set_memory_region(struct kvm *kvm, bitmap_set(new.dirty_bitmap, 0, new.npages); } - r = kvm_set_memslot(kvm, mem, &new, change); + r = kvm_set_memslot(kvm, &new, change); if (r) goto out_bitmap; -- cgit v1.2.3 From c928bfc2632fa3dd6a3bd4504ac6d8e42302287a Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 6 Dec 2021 20:54:25 +0100 Subject: KVM: Integrate gfn_to_memslot_approx() into search_memslots() s390 arch has gfn_to_memslot_approx() which is almost identical to search_memslots(), differing only in that in case the gfn falls in a hole one of the memslots bordering the hole is returned. Add this lookup mode as an option to search_memslots() so we don't have two almost identical functions for looking up a memslot by its gfn. Signed-off-by: Maciej S. Szmigiero [sean: tweaked helper names to keep gfn_to_memslot_approx() in s390] Reviewed-by: Sean Christopherson Message-Id: <171cd89b52c718dbe180ecd909b4437a64a7e2ec.1638817640.git.maciej.szmigiero@oracle.com> --- arch/s390/kvm/kvm-s390.c | 45 ++++++++------------------------------------- include/linux/kvm_host.h | 35 +++++++++++++++++++++++++++-------- virt/kvm/kvm_main.c | 2 +- 3 files changed, 36 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 251059ff81fc..631be750af08 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1943,41 +1943,6 @@ out: /* for consistency */ #define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX) -/* - * Similar to gfn_to_memslot, but returns the index of a memslot also when the - * address falls in a hole. In that case the index of one of the memslots - * bordering the hole is returned. - */ -static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn) -{ - int start = 0, end = slots->used_slots; - int slot = atomic_read(&slots->last_used_slot); - struct kvm_memory_slot *memslots = slots->memslots; - - if (gfn >= memslots[slot].base_gfn && - gfn < memslots[slot].base_gfn + memslots[slot].npages) - return slot; - - while (start < end) { - slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - if (start >= slots->used_slots) - return slots->used_slots - 1; - - if (gfn >= memslots[start].base_gfn && - gfn < memslots[start].base_gfn + memslots[start].npages) { - atomic_set(&slots->last_used_slot, start); - } - - return start; -} - static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, u8 *res, unsigned long bufsize) { @@ -2001,11 +1966,17 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, return 0; } +static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots, + gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, true); +} + static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, unsigned long cur_gfn) { - int slotidx = gfn_to_memslot_approx(slots, cur_gfn); - struct kvm_memory_slot *ms = slots->memslots + slotidx; + struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn); + int slotidx = ms - slots->memslots; unsigned long ofs = cur_gfn - ms->base_gfn; if (ms->base_gfn + ms->npages <= cur_gfn) { diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index da0d4f21a150..2f80ce84fbcf 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1233,10 +1233,14 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) * Returns a pointer to the memslot that contains gfn and records the index of * the slot in index. Otherwise returns NULL. * + * With "approx" set returns the memslot also when the address falls + * in a hole. In that case one of the memslots bordering the hole is + * returned. + * * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index, bool approx) { int start = 0, end = slots->used_slots; struct kvm_memory_slot *memslots = slots->memslots; @@ -1254,22 +1258,26 @@ search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index) start = slot + 1; } + if (approx && start >= slots->used_slots) { + *index = slots->used_slots - 1; + return &memslots[slots->used_slots - 1]; + } + slot = try_get_memslot(slots, start, gfn); if (slot) { *index = start; return slot; } + if (approx) { + *index = start; + return &memslots[start]; + } return NULL; } -/* - * __gfn_to_memslot() and its descendants are here because it is called from - * non-modular code in arch/powerpc/kvm/book3s_64_vio{,_hv}.c. gfn_to_memslot() - * itself isn't here as an inline because that would bloat other code too much. - */ static inline struct kvm_memory_slot * -__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; int slot_index = atomic_read(&slots->last_used_slot); @@ -1278,7 +1286,7 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) if (slot) return slot; - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, &slot_index, approx); if (slot) { atomic_set(&slots->last_used_slot, slot_index); return slot; @@ -1287,6 +1295,17 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) return NULL; } +/* + * __gfn_to_memslot() and its descendants are here to allow arch code to inline + * the lookups in hot paths. gfn_to_memslot() itself isn't here as an inline + * because that would bloat other code too much. + */ +static inline struct kvm_memory_slot * +__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn) +{ + return ____gfn_to_memslot(slots, gfn, false); +} + static inline unsigned long __gfn_to_hva_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 8ccb1ac82d38..6ca076ae64a2 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2141,7 +2141,7 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn * search_memslots() instead of __gfn_to_memslot() to avoid * thrashing the VM-wide last_used_index in kvm_memslots. */ - slot = search_memslots(slots, gfn, &slot_index); + slot = search_memslots(slots, gfn, &slot_index, false); if (slot) { vcpu->last_used_slot = slot_index; return slot; -- cgit v1.2.3 From 26b8345abc75a7404716864710930407b7d873f9 Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 6 Dec 2021 20:54:27 +0100 Subject: KVM: Resolve memslot ID via a hash table instead of via a static array Memslot ID to the corresponding memslot mappings are currently kept as indices in static id_to_index array. The size of this array depends on the maximum allowed memslot count (regardless of the number of memslots actually in use). This has become especially problematic recently, when memslot count cap was removed, so the maximum count is now full 32k memslots - the maximum allowed by the current KVM API. Keeping these IDs in a hash table (instead of an array) avoids this problem. Resolving a memslot ID to the actual memslot (instead of its index) will also enable transitioning away from an array-based implementation of the whole memslots structure in a later commit. Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: <117fb2c04320e6cd6cf34f205a72eadb0aa8d5f9.1638817640.git.maciej.szmigiero@oracle.com> --- include/linux/kvm_host.h | 25 ++++++++----- virt/kvm/kvm_main.c | 95 ++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 91 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 2f80ce84fbcf..79db70a8323e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -426,6 +427,7 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) struct kvm_memory_slot { + struct hlist_node id_node; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -527,8 +529,15 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) */ struct kvm_memslots { u64 generation; - /* The mapping table from slot id to the index in memslots[]. */ - short id_to_index[KVM_MEM_SLOTS_NUM]; + /* + * The mapping table from slot id to the index in memslots[]. + * + * 7-bit bucket count matches the size of the old id to index array for + * 512 slots, while giving good performance with this slot count. + * Higher bucket counts bring only small performance improvements but + * always result in higher memory usage (even for lower memslot counts). + */ + DECLARE_HASHTABLE(id_hash, 7); atomic_t last_used_slot; int used_slots; struct kvm_memory_slot memslots[]; @@ -796,16 +805,14 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { - int index = slots->id_to_index[id]; struct kvm_memory_slot *slot; - if (index < 0) - return NULL; - - slot = &slots->memslots[index]; + hash_for_each_possible(slots->id_hash, slot, id_node, id) { + if (slot->id == id) + return slot; + } - WARN_ON(slot->id != id); - return slot; + return NULL; } /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a60d09beef61..dbff2ac9a8e3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -867,15 +867,13 @@ static void kvm_destroy_pm_notifier(struct kvm *kvm) static struct kvm_memslots *kvm_alloc_memslots(void) { - int i; struct kvm_memslots *slots; slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); if (!slots) return NULL; - for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) - slots->id_to_index[i] = -1; + hash_init(slots->id_hash); return slots; } @@ -1274,17 +1272,48 @@ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) return 0; } +static void kvm_replace_memslot(struct kvm_memslots *slots, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + /* + * Remove the old memslot from the hash list, copying the node data + * would corrupt the list. + */ + if (old) { + hash_del(&old->id_node); + + if (!new) + return; + + /* Copy the source *data*, not the pointer, to the destination. */ + *new = *old; + } + + /* (Re)Add the new memslot. */ + hash_add(slots->id_hash, &new->id_node, new->id); +} + +static void kvm_shift_memslot(struct kvm_memslots *slots, int dst, int src) +{ + struct kvm_memory_slot *mslots = slots->memslots; + + kvm_replace_memslot(slots, &mslots[src], &mslots[dst]); +} + /* * Delete a memslot by decrementing the number of used slots and shifting all * other entries in the array forward one spot. + * @memslot is a detached dummy struct with just .id and .as_id filled. */ static inline void kvm_memslot_delete(struct kvm_memslots *slots, struct kvm_memory_slot *memslot) { struct kvm_memory_slot *mslots = slots->memslots; + struct kvm_memory_slot *oldslot = id_to_memslot(slots, memslot->id); int i; - if (WARN_ON(slots->id_to_index[memslot->id] == -1)) + if (WARN_ON(!oldslot)) return; slots->used_slots--; @@ -1292,12 +1321,17 @@ static inline void kvm_memslot_delete(struct kvm_memslots *slots, if (atomic_read(&slots->last_used_slot) >= slots->used_slots) atomic_set(&slots->last_used_slot, 0); - for (i = slots->id_to_index[memslot->id]; i < slots->used_slots; i++) { - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; - } + /* + * Remove the to-be-deleted memslot from the list _before_ shifting + * the trailing memslots forward, its data will be overwritten. + * Defer the (somewhat pointless) copying of the memslot until after + * the last slot has been shifted to avoid overwriting said last slot. + */ + kvm_replace_memslot(slots, oldslot, NULL); + + for (i = oldslot - mslots; i < slots->used_slots; i++) + kvm_shift_memslot(slots, i, i + 1); mslots[i] = *memslot; - slots->id_to_index[memslot->id] = -1; } /* @@ -1315,30 +1349,39 @@ static inline int kvm_memslot_insert_back(struct kvm_memslots *slots) * itself is not preserved in the array, i.e. not swapped at this time, only * its new index into the array is tracked. Returns the changed memslot's * current index into the memslots array. + * The memslot at the returned index will not be in @slots->id_hash by then. + * @memslot is a detached struct with desired final data of the changed slot. */ static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, struct kvm_memory_slot *memslot) { struct kvm_memory_slot *mslots = slots->memslots; + struct kvm_memory_slot *oldslot = id_to_memslot(slots, memslot->id); int i; - if (slots->id_to_index[memslot->id] == -1 || !slots->used_slots) + if (!oldslot || !slots->used_slots) return -1; + /* + * Delete the slot from the hash table before sorting the remaining + * slots, the slot's data may be overwritten when copying slots as part + * of the sorting proccess. update_memslots() will unconditionally + * rewrite the entire slot and re-add it to the hash table. + */ + kvm_replace_memslot(slots, oldslot, NULL); + /* * Move the target memslot backward in the array by shifting existing * memslots with a higher GFN (than the target memslot) towards the * front of the array. */ - for (i = slots->id_to_index[memslot->id]; i < slots->used_slots - 1; i++) { + for (i = oldslot - mslots; i < slots->used_slots - 1; i++) { if (memslot->base_gfn > mslots[i + 1].base_gfn) break; WARN_ON_ONCE(memslot->base_gfn == mslots[i + 1].base_gfn); - /* Shift the next memslot forward one and update its index. */ - mslots[i] = mslots[i + 1]; - slots->id_to_index[mslots[i].id] = i; + kvm_shift_memslot(slots, i, i + 1); } return i; } @@ -1349,6 +1392,10 @@ static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, * is not preserved in the array, i.e. not swapped at this time, only its new * index into the array is tracked. Returns the changed memslot's final index * into the memslots array. + * The memslot at the returned index will not be in @slots->id_hash by then. + * @memslot is a detached struct with desired final data of the new or + * changed slot. + * Assumes that the memslot at @start index is not in @slots->id_hash. */ static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, struct kvm_memory_slot *memslot, @@ -1363,9 +1410,7 @@ static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, WARN_ON_ONCE(memslot->base_gfn == mslots[i - 1].base_gfn); - /* Shift the next memslot back one and update its index. */ - mslots[i] = mslots[i - 1]; - slots->id_to_index[mslots[i].id] = i; + kvm_shift_memslot(slots, i, i - 1); } return i; } @@ -1410,6 +1455,9 @@ static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, * most likely to be referenced, sorting it to the front of the array was * advantageous. The current binary search starts from the middle of the array * and uses an LRU pointer to improve performance for all memslots and GFNs. + * + * @memslot is a detached struct, not a part of the current or new memslot + * array. */ static void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *memslot, @@ -1434,7 +1482,7 @@ static void update_memslots(struct kvm_memslots *slots, * its index accordingly. */ slots->memslots[i] = *memslot; - slots->id_to_index[memslot->id] = i; + kvm_replace_memslot(slots, NULL, &slots->memslots[i]); } } @@ -1527,6 +1575,7 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, { struct kvm_memslots *slots; size_t new_size; + struct kvm_memory_slot *memslot; if (change == KVM_MR_CREATE) new_size = kvm_memslots_size(old->used_slots + 1); @@ -1534,8 +1583,14 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, new_size = kvm_memslots_size(old->used_slots); slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); - if (likely(slots)) - memcpy(slots, old, kvm_memslots_size(old->used_slots)); + if (unlikely(!slots)) + return NULL; + + memcpy(slots, old, kvm_memslots_size(old->used_slots)); + + hash_init(slots->id_hash); + kvm_for_each_memslot(memslot, slots) + hash_add(slots->id_hash, &memslot->id_node, memslot->id); return slots; } -- cgit v1.2.3 From ed922739c9199bf515a3e7fec3e319ce1edeef2a Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 6 Dec 2021 20:54:28 +0100 Subject: KVM: Use interval tree to do fast hva lookup in memslots The current memslots implementation only allows quick binary search by gfn, quick lookup by hva is not possible - the implementation has to do a linear scan of the whole memslots array, even though the operation being performed might apply just to a single memslot. This significantly hurts performance of per-hva operations with higher memslot counts. Since hva ranges can overlap between memslots an interval tree is needed for tracking them. [sean: handle interval tree updates in kvm_replace_memslot()] Signed-off-by: Maciej S. Szmigiero Message-Id: --- arch/arm64/kvm/Kconfig | 1 + arch/mips/kvm/Kconfig | 1 + arch/powerpc/kvm/Kconfig | 1 + arch/s390/kvm/Kconfig | 1 + arch/x86/kvm/Kconfig | 1 + include/linux/kvm_host.h | 3 +++ virt/kvm/kvm_main.c | 53 +++++++++++++++++++++++++++++++++++------------- 7 files changed, 47 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 8ffcbe29395e..f1f8fc069a97 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -39,6 +39,7 @@ menuconfig KVM select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_VCPU_RUN_PID_CHANGE select SCHED_INFO + select INTERVAL_TREE help Support hosting virtualized guest machines. diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index a77297480f56..91d197bee9c0 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select KVM_MMIO select MMU_NOTIFIER select SRCU + select INTERVAL_TREE help Support for hosting Guest kernels. diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index ff581d70f20c..e4c24f524ba8 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select KVM_VFIO select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS + select INTERVAL_TREE config KVM_BOOK3S_HANDLER bool diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 67a8e770e369..2e84d3922f7c 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -33,6 +33,7 @@ config KVM select HAVE_KVM_NO_POLL select SRCU select KVM_VFIO + select INTERVAL_TREE help Support hosting paravirtualized guest machines using the SIE virtualization capability on the mainframe. This should work diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 619186138176..7618bef0a4a9 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -43,6 +43,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO select SRCU + select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM help Support hosting fully virtualized guest machines using hardware diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 79db70a8323e..9552ad6d6652 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -30,6 +30,7 @@ #include #include #include +#include #include #include @@ -428,6 +429,7 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) struct kvm_memory_slot { struct hlist_node id_node; + struct interval_tree_node hva_node; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -529,6 +531,7 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) */ struct kvm_memslots { u64 generation; + struct rb_root_cached hva_tree; /* * The mapping table from slot id to the index in memslots[]. * diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dbff2ac9a8e3..6ba7468bdbe3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -512,6 +512,12 @@ static void kvm_null_fn(void) } #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) +/* Iterate over each memslot intersecting [start, last] (inclusive) range */ +#define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ + for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ + node; \ + node = interval_tree_iter_next(node, start, last)) \ + static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, const struct kvm_hva_range *range) { @@ -521,6 +527,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, struct kvm_memslots *slots; int i, idx; + if (WARN_ON_ONCE(range->end <= range->start)) + return 0; + /* A null handler is allowed if and only if on_lock() is provided. */ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && IS_KVM_NULL_FN(range->handler))) @@ -529,15 +538,17 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + struct interval_tree_node *node; + slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot_in_hva_range(node, slots, + range->start, range->end - 1) { unsigned long hva_start, hva_end; + slot = container_of(node, struct kvm_memory_slot, hva_node); hva_start = max(range->start, slot->userspace_addr); hva_end = min(range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); - if (hva_start >= hva_end) - continue; /* * To optimize for the likely case where the address @@ -873,6 +884,7 @@ static struct kvm_memslots *kvm_alloc_memslots(void) if (!slots) return NULL; + slots->hva_tree = RB_ROOT_CACHED; hash_init(slots->id_hash); return slots; @@ -1277,21 +1289,28 @@ static void kvm_replace_memslot(struct kvm_memslots *slots, struct kvm_memory_slot *new) { /* - * Remove the old memslot from the hash list, copying the node data - * would corrupt the list. + * Remove the old memslot from the hash list and interval tree, copying + * the node data would corrupt the structures. */ if (old) { hash_del(&old->id_node); + interval_tree_remove(&old->hva_node, &slots->hva_tree); if (!new) return; /* Copy the source *data*, not the pointer, to the destination. */ *new = *old; + } else { + /* If @old is NULL, initialize @new's hva range. */ + new->hva_node.start = new->userspace_addr; + new->hva_node.last = new->userspace_addr + + (new->npages << PAGE_SHIFT) - 1; } /* (Re)Add the new memslot. */ hash_add(slots->id_hash, &new->id_node, new->id); + interval_tree_insert(&new->hva_node, &slots->hva_tree); } static void kvm_shift_memslot(struct kvm_memslots *slots, int dst, int src) @@ -1322,7 +1341,7 @@ static inline void kvm_memslot_delete(struct kvm_memslots *slots, atomic_set(&slots->last_used_slot, 0); /* - * Remove the to-be-deleted memslot from the list _before_ shifting + * Remove the to-be-deleted memslot from the list/tree _before_ shifting * the trailing memslots forward, its data will be overwritten. * Defer the (somewhat pointless) copying of the memslot until after * the last slot has been shifted to avoid overwriting said last slot. @@ -1349,7 +1368,8 @@ static inline int kvm_memslot_insert_back(struct kvm_memslots *slots) * itself is not preserved in the array, i.e. not swapped at this time, only * its new index into the array is tracked. Returns the changed memslot's * current index into the memslots array. - * The memslot at the returned index will not be in @slots->id_hash by then. + * The memslot at the returned index will not be in @slots->hva_tree or + * @slots->id_hash by then. * @memslot is a detached struct with desired final data of the changed slot. */ static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, @@ -1363,10 +1383,10 @@ static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, return -1; /* - * Delete the slot from the hash table before sorting the remaining - * slots, the slot's data may be overwritten when copying slots as part - * of the sorting proccess. update_memslots() will unconditionally - * rewrite the entire slot and re-add it to the hash table. + * Delete the slot from the hash table and interval tree before sorting + * the remaining slots, the slot's data may be overwritten when copying + * slots as part of the sorting proccess. update_memslots() will + * unconditionally rewrite and re-add the entire slot. */ kvm_replace_memslot(slots, oldslot, NULL); @@ -1392,10 +1412,12 @@ static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, * is not preserved in the array, i.e. not swapped at this time, only its new * index into the array is tracked. Returns the changed memslot's final index * into the memslots array. - * The memslot at the returned index will not be in @slots->id_hash by then. + * The memslot at the returned index will not be in @slots->hva_tree or + * @slots->id_hash by then. * @memslot is a detached struct with desired final data of the new or * changed slot. - * Assumes that the memslot at @start index is not in @slots->id_hash. + * Assumes that the memslot at @start index is not in @slots->hva_tree or + * @slots->id_hash. */ static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, struct kvm_memory_slot *memslot, @@ -1588,9 +1610,12 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, memcpy(slots, old, kvm_memslots_size(old->used_slots)); + slots->hva_tree = RB_ROOT_CACHED; hash_init(slots->id_hash); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, slots) { + interval_tree_insert(&memslot->hva_node, &slots->hva_tree); hash_add(slots->id_hash, &memslot->id_node, memslot->id); + } return slots; } -- cgit v1.2.3 From a54d806688fe1e482350ce759a8a0fc9ebf814b0 Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 6 Dec 2021 20:54:30 +0100 Subject: KVM: Keep memslots in tree-based structures instead of array-based ones The current memslot code uses a (reverse gfn-ordered) memslot array for keeping track of them. Because the memslot array that is currently in use cannot be modified every memslot management operation (create, delete, move, change flags) has to make a copy of the whole array so it has a scratch copy to work on. Strictly speaking, however, it is only necessary to make copy of the memslot that is being modified, copying all the memslots currently present is just a limitation of the array-based memslot implementation. Two memslot sets, however, are still needed so the VM continues to run on the currently active set while the requested operation is being performed on the second, currently inactive one. In order to have two memslot sets, but only one copy of actual memslots it is necessary to split out the memslot data from the memslot sets. The memslots themselves should be also kept independent of each other so they can be individually added or deleted. These two memslot sets should normally point to the same set of memslots. They can, however, be desynchronized when performing a memslot management operation by replacing the memslot to be modified by its copy. After the operation is complete, both memslot sets once again point to the same, common set of memslot data. This commit implements the aforementioned idea. For tracking of gfns an ordinary rbtree is used since memslots cannot overlap in the guest address space and so this data structure is sufficient for ensuring that lookups are done quickly. The "last used slot" mini-caches (both per-slot set one and per-vCPU one), that keep track of the last found-by-gfn memslot, are still present in the new code. Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: <17c0cf3663b760a0d3753d4ac08c0753e941b811.1638817641.git.maciej.szmigiero@oracle.com> --- arch/arm64/kvm/mmu.c | 8 +- arch/powerpc/kvm/book3s_64_mmu_hv.c | 4 +- arch/powerpc/kvm/book3s_hv.c | 3 +- arch/powerpc/kvm/book3s_hv_nested.c | 4 +- arch/powerpc/kvm/book3s_hv_uvmem.c | 14 +- arch/s390/kvm/kvm-s390.c | 24 +- arch/s390/kvm/kvm-s390.h | 6 +- arch/x86/kvm/debugfs.c | 6 +- arch/x86/kvm/mmu/mmu.c | 8 +- include/linux/kvm_host.h | 143 ++++--- virt/kvm/kvm_main.c | 761 +++++++++++++++++++----------------- 11 files changed, 503 insertions(+), 478 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 9b2d881ccf49..e65acf35cee3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -210,13 +210,13 @@ static void stage2_flush_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_flush_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); @@ -595,14 +595,14 @@ void stage2_unmap_vm(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int idx; + int idx, bkt; idx = srcu_read_lock(&kvm->srcu); mmap_read_lock(current->mm); spin_lock(&kvm->mmu_lock); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) + kvm_for_each_memslot(memslot, bkt, slots) stage2_unmap_memslot(kvm, memslot); spin_unlock(&kvm->mmu_lock); diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index c63e263312a4..213232914367 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -734,11 +734,11 @@ void kvmppc_rmap_reset(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { /* Mutual exclusion with kvm_unmap_hva_range etc. */ spin_lock(&kvm->mmu_lock); /* diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 2b59ecc5f8c6..51e1c29a6fa0 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -5880,11 +5880,12 @@ static int kvmhv_svm_off(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { struct kvm_memory_slot *memslot; struct kvm_memslots *slots = __kvm_memslots(kvm, i); + int bkt; if (!slots) continue; - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { kvmppc_uvmem_drop_pages(memslot, kvm, true); uv_unregister_mem_slot(kvm->arch.lpid, memslot->id); } diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c index ed8a2c9f5629..9435e482d514 100644 --- a/arch/powerpc/kvm/book3s_hv_nested.c +++ b/arch/powerpc/kvm/book3s_hv_nested.c @@ -749,7 +749,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) struct kvm_nested_guest *gp; struct kvm_nested_guest *freelist = NULL; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; spin_lock(&kvm->mmu_lock); for (i = 0; i <= kvm->arch.max_nested_lpid; i++) { @@ -770,7 +770,7 @@ void kvmhv_release_all_nested(struct kvm *kvm) } srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmhv_free_memslot_nest_rmap(memslot); srcu_read_unlock(&kvm->srcu, srcu_idx); } diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 28c436df9935..e414ca44839f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -459,7 +459,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) struct kvm_memslots *slots; struct kvm_memory_slot *memslot, *m; int ret = H_SUCCESS; - int srcu_idx; + int srcu_idx, bkt; kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START; @@ -478,7 +478,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) /* register the memslot */ slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = __kvmppc_uvmem_memslot_create(kvm, memslot); if (ret) break; @@ -486,7 +486,7 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm) if (ret) { slots = kvm_memslots(kvm); - kvm_for_each_memslot(m, slots) { + kvm_for_each_memslot(m, bkt, slots) { if (m == memslot) break; __kvmppc_uvmem_memslot_delete(kvm, memslot); @@ -647,7 +647,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot, unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) { - int srcu_idx; + int srcu_idx, bkt; struct kvm_memory_slot *memslot; /* @@ -662,7 +662,7 @@ unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm) srcu_idx = srcu_read_lock(&kvm->srcu); - kvm_for_each_memslot(memslot, kvm_memslots(kvm)) + kvm_for_each_memslot(memslot, bkt, kvm_memslots(kvm)) kvmppc_uvmem_drop_pages(memslot, kvm, false); srcu_read_unlock(&kvm->srcu, srcu_idx); @@ -821,7 +821,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int srcu_idx; + int srcu_idx, bkt; long ret = H_SUCCESS; if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)) @@ -830,7 +830,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm) /* migrate any unmoved normal pfn to device pfns*/ srcu_idx = srcu_read_lock(&kvm->srcu); slots = kvm_memslots(kvm); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { ret = kvmppc_uv_migrate_mem_slot(kvm, memslot); if (ret) { /* diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5044b2a2c0cc..b943a589ee41 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1037,13 +1037,13 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) struct kvm_memory_slot *ms; struct kvm_memslots *slots; unsigned long ram_pages = 0; - int slotnr; + int bkt; /* migration mode already enabled */ if (kvm->arch.migration_mode) return 0; slots = kvm_memslots(kvm); - if (!slots || !slots->used_slots) + if (!slots || kvm_memslots_empty(slots)) return -EINVAL; if (!kvm->arch.use_cmma) { @@ -1051,8 +1051,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm) return 0; } /* mark all the pages in active slots as dirty */ - for (slotnr = 0; slotnr < slots->used_slots; slotnr++) { - ms = slots->memslots + slotnr; + kvm_for_each_memslot(ms, bkt, slots) { if (!ms->dirty_bitmap) return -EINVAL; /* @@ -1976,22 +1975,21 @@ static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots, unsigned long cur_gfn) { struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn); - int slotidx = ms - slots->memslots; unsigned long ofs = cur_gfn - ms->base_gfn; + struct rb_node *mnode = &ms->gfn_node[slots->node_idx]; if (ms->base_gfn + ms->npages <= cur_gfn) { - slotidx--; + mnode = rb_next(mnode); /* If we are above the highest slot, wrap around */ - if (slotidx < 0) - slotidx = slots->used_slots - 1; + if (!mnode) + mnode = rb_first(&slots->gfn_tree); - ms = slots->memslots + slotidx; + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = 0; } ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs); - while ((slotidx > 0) && (ofs >= ms->npages)) { - slotidx--; - ms = slots->memslots + slotidx; + while (ofs >= ms->npages && (mnode = rb_next(mnode))) { + ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]); ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0); } return ms->base_gfn + ofs; @@ -2004,7 +2002,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *ms; - if (unlikely(!slots->used_slots)) + if (unlikely(kvm_memslots_empty(slots))) return 0; cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index cc309cc37e96..60f0effcce99 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -220,12 +220,14 @@ static inline void kvm_s390_set_user_cpu_state_ctrl(struct kvm *kvm) /* get the end gfn of the last (highest gfn) memslot */ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots) { + struct rb_node *node; struct kvm_memory_slot *ms; - if (WARN_ON(!slots->used_slots)) + if (WARN_ON(kvm_memslots_empty(slots))) return 0; - ms = slots->memslots; + node = rb_last(&slots->gfn_tree); + ms = container_of(node, struct kvm_memory_slot, gfn_node[slots->node_idx]); return ms->base_gfn + ms->npages; } diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 54a83a744538..543a8c04025c 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -107,9 +107,10 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + int bkt; + slots = __kvm_memslots(kvm, i); - for (j = 0; j < slots->used_slots; j++) { - slot = &slots->memslots[j]; + kvm_for_each_memslot(slot, bkt, slots) for (k = 0; k < KVM_NR_PAGE_SIZES; k++) { rmap = slot->arch.rmap[k]; lpage_size = kvm_mmu_slot_lpages(slot, k + 1); @@ -121,7 +122,6 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) cur[index]++; } } - } } write_unlock(&kvm->mmu_lock); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index e41cf095f2d1..c61430994d19 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3409,7 +3409,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; - int r = 0, i; + int r = 0, i, bkt; /* * Check if this is the first shadow root being allocated before @@ -3434,7 +3434,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(slot, slots) { + kvm_for_each_memslot(slot, bkt, slots) { /* * Both of these functions are no-ops if the target is * already allocated, so unconditionally calling both @@ -5730,14 +5730,14 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) struct kvm_memslots *slots; bool flush = false; gfn_t start, end; - int i; + int i, bkt; if (!kvm_memslots_have_rmaps(kvm)) return flush; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, slots) { + kvm_for_each_memslot(memslot, bkt, slots) { start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); if (start >= end) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9552ad6d6652..9eda8a63feae 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -358,11 +359,13 @@ struct kvm_vcpu { struct kvm_dirty_ring dirty_ring; /* - * The index of the most recently used memslot by this vCPU. It's ok - * if this becomes stale due to memslot changes since we always check - * it is a valid slot. + * The most recently used memslot by this vCPU and the slots generation + * for which it is valid. + * No wraparound protection is needed since generations won't overflow in + * thousands of years, even assuming 1M memslot operations per second. */ - int last_used_slot; + struct kvm_memory_slot *last_used_slot; + u64 last_used_slot_gen; }; /* must be called with irqs disabled */ @@ -427,9 +430,26 @@ static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) */ #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1) +/* + * Since at idle each memslot belongs to two memslot sets it has to contain + * two embedded nodes for each data structure that it forms a part of. + * + * Two memslot sets (one active and one inactive) are necessary so the VM + * continues to run on one memslot set while the other is being modified. + * + * These two memslot sets normally point to the same set of memslots. + * They can, however, be desynchronized when performing a memslot management + * operation by replacing the memslot to be modified by its copy. + * After the operation is complete, both memslot sets once again point to + * the same, common set of memslot data. + * + * The memslots themselves are independent of each other so they can be + * individually added or deleted. + */ struct kvm_memory_slot { - struct hlist_node id_node; - struct interval_tree_node hva_node; + struct hlist_node id_node[2]; + struct interval_tree_node hva_node[2]; + struct rb_node gfn_node[2]; gfn_t base_gfn; unsigned long npages; unsigned long *dirty_bitmap; @@ -524,16 +544,13 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -/* - * Note: - * memslots are not sorted by id anymore, please use id_to_memslot() - * to get the memslot by its id. - */ struct kvm_memslots { u64 generation; + atomic_long_t last_used_slot; struct rb_root_cached hva_tree; + struct rb_root gfn_tree; /* - * The mapping table from slot id to the index in memslots[]. + * The mapping table from slot id to memslot. * * 7-bit bucket count matches the size of the old id to index array for * 512 slots, while giving good performance with this slot count. @@ -541,9 +558,7 @@ struct kvm_memslots { * always result in higher memory usage (even for lower memslot counts). */ DECLARE_HASHTABLE(id_hash, 7); - atomic_t last_used_slot; - int used_slots; - struct kvm_memory_slot memslots[]; + int node_idx; }; struct kvm { @@ -565,6 +580,9 @@ struct kvm { struct mutex slots_arch_lock; struct mm_struct *mm; /* userspace tied to this vm */ unsigned long nr_memslot_pages; + /* The two memslot sets - active and inactive (per address space) */ + struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2]; + /* The current active memslot set for each address space */ struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM]; struct xarray vcpu_array; @@ -739,11 +757,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -#define kvm_for_each_memslot(memslot, slots) \ - for (memslot = &slots->memslots[0]; \ - memslot < slots->memslots + slots->used_slots; memslot++) \ - if (WARN_ON_ONCE(!memslot->npages)) { \ - } else +static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} void kvm_destroy_vcpus(struct kvm *kvm); @@ -805,12 +822,23 @@ static inline struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu) return __kvm_memslots(vcpu->kvm, as_id); } +static inline bool kvm_memslots_empty(struct kvm_memslots *slots) +{ + return RB_EMPTY_ROOT(&slots->gfn_tree); +} + +#define kvm_for_each_memslot(memslot, bkt, slots) \ + hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \ + if (WARN_ON_ONCE(!memslot->npages)) { \ + } else + static inline struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) { struct kvm_memory_slot *slot; + int idx = slots->node_idx; - hash_for_each_possible(slots->id_hash, slot, id_node, id) { + hash_for_each_possible(slots->id_hash, slot, id_node[idx], id) { if (slot->id == id) return slot; } @@ -1214,25 +1242,15 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id); bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args); /* - * Returns a pointer to the memslot at slot_index if it contains gfn. + * Returns a pointer to the memslot if it contains gfn. * Otherwise returns NULL. */ static inline struct kvm_memory_slot * -try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) +try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - struct kvm_memory_slot *slot; - - if (slot_index < 0 || slot_index >= slots->used_slots) + if (!slot) return NULL; - /* - * slot_index can come from vcpu->last_used_slot which is not kept - * in sync with userspace-controllable memslot deletion. So use nospec - * to prevent the CPU from speculating past the end of memslots[]. - */ - slot_index = array_index_nospec(slot_index, slots->used_slots); - slot = &slots->memslots[slot_index]; - if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages) return slot; else @@ -1240,65 +1258,46 @@ try_get_memslot(struct kvm_memslots *slots, int slot_index, gfn_t gfn) } /* - * Returns a pointer to the memslot that contains gfn and records the index of - * the slot in index. Otherwise returns NULL. + * Returns a pointer to the memslot that contains gfn. Otherwise returns NULL. * * With "approx" set returns the memslot also when the address falls * in a hole. In that case one of the memslots bordering the hole is * returned. - * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! */ static inline struct kvm_memory_slot * -search_memslots(struct kvm_memslots *slots, gfn_t gfn, int *index, bool approx) +search_memslots(struct kvm_memslots *slots, gfn_t gfn, bool approx) { - int start = 0, end = slots->used_slots; - struct kvm_memory_slot *memslots = slots->memslots; struct kvm_memory_slot *slot; - - if (unlikely(!slots->used_slots)) - return NULL; - - while (start < end) { - int slot = start + (end - start) / 2; - - if (gfn >= memslots[slot].base_gfn) - end = slot; - else - start = slot + 1; - } - - if (approx && start >= slots->used_slots) { - *index = slots->used_slots - 1; - return &memslots[slots->used_slots - 1]; - } - - slot = try_get_memslot(slots, start, gfn); - if (slot) { - *index = start; - return slot; - } - if (approx) { - *index = start; - return &memslots[start]; + struct rb_node *node; + int idx = slots->node_idx; + + slot = NULL; + for (node = slots->gfn_tree.rb_node; node; ) { + slot = container_of(node, struct kvm_memory_slot, gfn_node[idx]); + if (gfn >= slot->base_gfn) { + if (gfn < slot->base_gfn + slot->npages) + return slot; + node = node->rb_right; + } else + node = node->rb_left; } - return NULL; + return approx ? slot : NULL; } static inline struct kvm_memory_slot * ____gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn, bool approx) { struct kvm_memory_slot *slot; - int slot_index = atomic_read(&slots->last_used_slot); - slot = try_get_memslot(slots, slot_index, gfn); + slot = (struct kvm_memory_slot *)atomic_long_read(&slots->last_used_slot); + slot = try_get_memslot(slot, gfn); if (slot) return slot; - slot = search_memslots(slots, gfn, &slot_index, approx); + slot = search_memslots(slots, gfn, approx); if (slot) { - atomic_set(&slots->last_used_slot, slot_index); + atomic_long_set(&slots->last_used_slot, (unsigned long)slot); return slot; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 6ba7468bdbe3..a87df97e0b14 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -433,7 +433,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); - vcpu->last_used_slot = 0; + vcpu->last_used_slot = NULL; } static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) @@ -545,7 +545,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, range->start, range->end - 1) { unsigned long hva_start, hva_end; - slot = container_of(node, struct kvm_memory_slot, hva_node); + slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); hva_start = max(range->start, slot->userspace_addr); hva_end = min(range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); @@ -876,20 +876,6 @@ static void kvm_destroy_pm_notifier(struct kvm *kvm) } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ -static struct kvm_memslots *kvm_alloc_memslots(void) -{ - struct kvm_memslots *slots; - - slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT); - if (!slots) - return NULL; - - slots->hva_tree = RB_ROOT_CACHED; - hash_init(slots->id_hash); - - return slots; -} - static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) @@ -899,27 +885,33 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) memslot->dirty_bitmap = NULL; } +/* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); - slot->flags = 0; - slot->npages = 0; + kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { + struct hlist_node *idnode; struct kvm_memory_slot *memslot; + int bkt; - if (!slots) + /* + * The same memslot objects live in both active and inactive sets, + * arbitrarily free using index '1' so the second invocation of this + * function isn't operating over a structure with dangling pointers + * (even though this function isn't actually touching them). + */ + if (!slots->node_idx) return; - kvm_for_each_memslot(memslot, slots) + hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot); - - kvfree(slots); } static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) @@ -1058,8 +1050,9 @@ int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) static struct kvm *kvm_create_vm(unsigned long type) { struct kvm *kvm = kvm_arch_alloc_vm(); + struct kvm_memslots *slots; int r = -ENOMEM; - int i; + int i, j; if (!kvm) return ERR_PTR(-ENOMEM); @@ -1087,13 +1080,20 @@ static struct kvm *kvm_create_vm(unsigned long type) refcount_set(&kvm->users_count, 1); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_memslots *slots = kvm_alloc_memslots(); + for (j = 0; j < 2; j++) { + slots = &kvm->__memslots[i][j]; - if (!slots) - goto out_err_no_arch_destroy_vm; - /* Generations must be different for each address space. */ - slots->generation = i; - rcu_assign_pointer(kvm->memslots[i], slots); + atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); + slots->hva_tree = RB_ROOT_CACHED; + slots->gfn_tree = RB_ROOT; + hash_init(slots->id_hash); + slots->node_idx = j; + + /* Generations must be different for each address space. */ + slots->generation = i; + } + + rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); } for (i = 0; i < KVM_NR_BUSES; i++) { @@ -1147,8 +1147,6 @@ out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); @@ -1213,8 +1211,10 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) - kvm_free_memslots(kvm, __kvm_memslots(kvm, i)); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + kvm_free_memslots(kvm, &kvm->__memslots[i][0]); + kvm_free_memslots(kvm, &kvm->__memslots[i][1]); + } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); @@ -1284,227 +1284,136 @@ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) return 0; } -static void kvm_replace_memslot(struct kvm_memslots *slots, - struct kvm_memory_slot *old, - struct kvm_memory_slot *new) -{ - /* - * Remove the old memslot from the hash list and interval tree, copying - * the node data would corrupt the structures. - */ - if (old) { - hash_del(&old->id_node); - interval_tree_remove(&old->hva_node, &slots->hva_tree); - - if (!new) - return; - - /* Copy the source *data*, not the pointer, to the destination. */ - *new = *old; - } else { - /* If @old is NULL, initialize @new's hva range. */ - new->hva_node.start = new->userspace_addr; - new->hva_node.last = new->userspace_addr + - (new->npages << PAGE_SHIFT) - 1; - } - - /* (Re)Add the new memslot. */ - hash_add(slots->id_hash, &new->id_node, new->id); - interval_tree_insert(&new->hva_node, &slots->hva_tree); -} - -static void kvm_shift_memslot(struct kvm_memslots *slots, int dst, int src) +static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { - struct kvm_memory_slot *mslots = slots->memslots; + struct kvm_memslots *active = __kvm_memslots(kvm, as_id); + int node_idx_inactive = active->node_idx ^ 1; - kvm_replace_memslot(slots, &mslots[src], &mslots[dst]); + return &kvm->__memslots[as_id][node_idx_inactive]; } /* - * Delete a memslot by decrementing the number of used slots and shifting all - * other entries in the array forward one spot. - * @memslot is a detached dummy struct with just .id and .as_id filled. + * Helper to get the address space ID when one of memslot pointers may be NULL. + * This also serves as a sanity that at least one of the pointers is non-NULL, + * and that their address space IDs don't diverge. */ -static inline void kvm_memslot_delete(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot) +static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, + struct kvm_memory_slot *b) { - struct kvm_memory_slot *mslots = slots->memslots; - struct kvm_memory_slot *oldslot = id_to_memslot(slots, memslot->id); - int i; - - if (WARN_ON(!oldslot)) - return; - - slots->used_slots--; + if (WARN_ON_ONCE(!a && !b)) + return 0; - if (atomic_read(&slots->last_used_slot) >= slots->used_slots) - atomic_set(&slots->last_used_slot, 0); + if (!a) + return b->as_id; + if (!b) + return a->as_id; - /* - * Remove the to-be-deleted memslot from the list/tree _before_ shifting - * the trailing memslots forward, its data will be overwritten. - * Defer the (somewhat pointless) copying of the memslot until after - * the last slot has been shifted to avoid overwriting said last slot. - */ - kvm_replace_memslot(slots, oldslot, NULL); - - for (i = oldslot - mslots; i < slots->used_slots; i++) - kvm_shift_memslot(slots, i, i + 1); - mslots[i] = *memslot; + WARN_ON_ONCE(a->as_id != b->as_id); + return a->as_id; } -/* - * "Insert" a new memslot by incrementing the number of used slots. Returns - * the new slot's initial index into the memslots array. - */ -static inline int kvm_memslot_insert_back(struct kvm_memslots *slots) +static void kvm_insert_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) { - return slots->used_slots++; -} - -/* - * Move a changed memslot backwards in the array by shifting existing slots - * with a higher GFN toward the front of the array. Note, the changed memslot - * itself is not preserved in the array, i.e. not swapped at this time, only - * its new index into the array is tracked. Returns the changed memslot's - * current index into the memslots array. - * The memslot at the returned index will not be in @slots->hva_tree or - * @slots->id_hash by then. - * @memslot is a detached struct with desired final data of the changed slot. - */ -static inline int kvm_memslot_move_backward(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot) -{ - struct kvm_memory_slot *mslots = slots->memslots; - struct kvm_memory_slot *oldslot = id_to_memslot(slots, memslot->id); - int i; - - if (!oldslot || !slots->used_slots) - return -1; - - /* - * Delete the slot from the hash table and interval tree before sorting - * the remaining slots, the slot's data may be overwritten when copying - * slots as part of the sorting proccess. update_memslots() will - * unconditionally rewrite and re-add the entire slot. - */ - kvm_replace_memslot(slots, oldslot, NULL); - - /* - * Move the target memslot backward in the array by shifting existing - * memslots with a higher GFN (than the target memslot) towards the - * front of the array. - */ - for (i = oldslot - mslots; i < slots->used_slots - 1; i++) { - if (memslot->base_gfn > mslots[i + 1].base_gfn) - break; + struct rb_root *gfn_tree = &slots->gfn_tree; + struct rb_node **node, *parent; + int idx = slots->node_idx; - WARN_ON_ONCE(memslot->base_gfn == mslots[i + 1].base_gfn); + parent = NULL; + for (node = &gfn_tree->rb_node; *node; ) { + struct kvm_memory_slot *tmp; - kvm_shift_memslot(slots, i, i + 1); + tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); + parent = *node; + if (slot->base_gfn < tmp->base_gfn) + node = &(*node)->rb_left; + else if (slot->base_gfn > tmp->base_gfn) + node = &(*node)->rb_right; + else + BUG(); } - return i; + + rb_link_node(&slot->gfn_node[idx], parent, node); + rb_insert_color(&slot->gfn_node[idx], gfn_tree); } -/* - * Move a changed memslot forwards in the array by shifting existing slots with - * a lower GFN toward the back of the array. Note, the changed memslot itself - * is not preserved in the array, i.e. not swapped at this time, only its new - * index into the array is tracked. Returns the changed memslot's final index - * into the memslots array. - * The memslot at the returned index will not be in @slots->hva_tree or - * @slots->id_hash by then. - * @memslot is a detached struct with desired final data of the new or - * changed slot. - * Assumes that the memslot at @start index is not in @slots->hva_tree or - * @slots->id_hash. - */ -static inline int kvm_memslot_move_forward(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot, - int start) +static void kvm_erase_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *slot) { - struct kvm_memory_slot *mslots = slots->memslots; - int i; + rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); +} - for (i = start; i > 0; i--) { - if (memslot->base_gfn < mslots[i - 1].base_gfn) - break; +static void kvm_replace_gfn_node(struct kvm_memslots *slots, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int idx = slots->node_idx; - WARN_ON_ONCE(memslot->base_gfn == mslots[i - 1].base_gfn); + WARN_ON_ONCE(old->base_gfn != new->base_gfn); - kvm_shift_memslot(slots, i, i - 1); - } - return i; + rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], + &slots->gfn_tree); } /* - * Re-sort memslots based on their GFN to account for an added, deleted, or - * moved memslot. Sorting memslots by GFN allows using a binary search during - * memslot lookup. - * - * IMPORTANT: Slots are sorted from highest GFN to lowest GFN! I.e. the entry - * at memslots[0] has the highest GFN. - * - * The sorting algorithm takes advantage of having initially sorted memslots - * and knowing the position of the changed memslot. Sorting is also optimized - * by not swapping the updated memslot and instead only shifting other memslots - * and tracking the new index for the update memslot. Only once its final - * index is known is the updated memslot copied into its position in the array. - * - * - When deleting a memslot, the deleted memslot simply needs to be moved to - * the end of the array. - * - * - When creating a memslot, the algorithm "inserts" the new memslot at the - * end of the array and then it forward to its correct location. - * - * - When moving a memslot, the algorithm first moves the updated memslot - * backward to handle the scenario where the memslot's GFN was changed to a - * lower value. update_memslots() then falls through and runs the same flow - * as creating a memslot to move the memslot forward to handle the scenario - * where its GFN was changed to a higher value. + * Replace @old with @new in the inactive memslots. * - * Note, slots are sorted from highest->lowest instead of lowest->highest for - * historical reasons. Originally, invalid memslots where denoted by having - * GFN=0, thus sorting from highest->lowest naturally sorted invalid memslots - * to the end of the array. The current algorithm uses dedicated logic to - * delete a memslot and thus does not rely on invalid memslots having GFN=0. + * With NULL @old this simply adds @new. + * With NULL @new this simply removes @old. * - * The other historical motiviation for highest->lowest was to improve the - * performance of memslot lookup. KVM originally used a linear search starting - * at memslots[0]. On x86, the largest memslot usually has one of the highest, - * if not *the* highest, GFN, as the bulk of the guest's RAM is located in a - * single memslot above the 4gb boundary. As the largest memslot is also the - * most likely to be referenced, sorting it to the front of the array was - * advantageous. The current binary search starts from the middle of the array - * and uses an LRU pointer to improve performance for all memslots and GFNs. - * - * @memslot is a detached struct, not a part of the current or new memslot - * array. + * If @new is non-NULL its hva_node[slots_idx] range has to be set + * appropriately. */ -static void update_memslots(struct kvm_memslots *slots, - struct kvm_memory_slot *memslot, - enum kvm_mr_change change) +static void kvm_replace_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) { - int i; + int as_id = kvm_memslots_get_as_id(old, new); + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + int idx = slots->node_idx; - if (change == KVM_MR_DELETE) { - kvm_memslot_delete(slots, memslot); - } else { - if (change == KVM_MR_CREATE) - i = kvm_memslot_insert_back(slots); - else - i = kvm_memslot_move_backward(slots, memslot); - i = kvm_memslot_move_forward(slots, memslot, i); + if (old) { + hash_del(&old->id_node[idx]); + interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); - if (WARN_ON_ONCE(i < 0)) + if ((long)old == atomic_long_read(&slots->last_used_slot)) + atomic_long_set(&slots->last_used_slot, (long)new); + + if (!new) { + kvm_erase_gfn_node(slots, old); return; + } + } - /* - * Copy the memslot to its new position in memslots and update - * its index accordingly. - */ - slots->memslots[i] = *memslot; - kvm_replace_memslot(slots, NULL, &slots->memslots[i]); + /* + * Initialize @new's hva range. Do this even when replacing an @old + * slot, kvm_copy_memslot() deliberately does not touch node data. + */ + new->hva_node[idx].start = new->userspace_addr; + new->hva_node[idx].last = new->userspace_addr + + (new->npages << PAGE_SHIFT) - 1; + + /* + * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), + * hva_node needs to be swapped with remove+insert even though hva can't + * change when replacing an existing slot. + */ + hash_add(slots->id_hash, &new->id_node[idx], new->id); + interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); + + /* + * If the memslot gfn is unchanged, rb_replace_node() can be used to + * switch the node in the gfn tree instead of removing the old and + * inserting the new as two separate operations. Replacement is a + * single O(1) operation versus two O(log(n)) operations for + * remove+insert. + */ + if (old && old->base_gfn == new->base_gfn) { + kvm_replace_gfn_node(slots, old, new); + } else { + if (old) + kvm_erase_gfn_node(slots, old); + kvm_insert_gfn_node(slots, new); } } @@ -1522,11 +1431,12 @@ static int check_memory_region_flags(const struct kvm_userspace_memory_region *m return 0; } -static struct kvm_memslots *install_new_memslots(struct kvm *kvm, - int as_id, struct kvm_memslots *slots) +static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { - struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); - u64 gen = old_memslots->generation; + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); + + /* Grab the generation from the activate memslots. */ + u64 gen = __kvm_memslots(kvm, as_id)->generation; WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; @@ -1577,58 +1487,6 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; - - return old_memslots; -} - -static size_t kvm_memslots_size(int slots) -{ - return sizeof(struct kvm_memslots) + - (sizeof(struct kvm_memory_slot) * slots); -} - -/* - * Note, at a minimum, the current number of used slots must be allocated, even - * when deleting a memslot, as we need a complete duplicate of the memslots for - * use when invalidating a memslot prior to deleting/moving the memslot. - */ -static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, - enum kvm_mr_change change) -{ - struct kvm_memslots *slots; - size_t new_size; - struct kvm_memory_slot *memslot; - - if (change == KVM_MR_CREATE) - new_size = kvm_memslots_size(old->used_slots + 1); - else - new_size = kvm_memslots_size(old->used_slots); - - slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT); - if (unlikely(!slots)) - return NULL; - - memcpy(slots, old, kvm_memslots_size(old->used_slots)); - - slots->hva_tree = RB_ROOT_CACHED; - hash_init(slots->id_hash); - kvm_for_each_memslot(memslot, slots) { - interval_tree_insert(&memslot->hva_node, &slots->hva_tree); - hash_add(slots->id_hash, &memslot->id_node, memslot->id); - } - - return slots; -} - -static void kvm_copy_memslots_arch(struct kvm_memslots *to, - struct kvm_memslots *from) -{ - int i; - - WARN_ON_ONCE(to->used_slots != from->used_slots); - - for (i = 0; i < from->used_slots; i++) - to->memslots[i].arch = from->memslots[i].arch; } static int kvm_prepare_memory_region(struct kvm *kvm, @@ -1683,31 +1541,214 @@ static void kvm_commit_memory_region(struct kvm *kvm, kvm_arch_commit_memory_region(kvm, old, new, change); + switch (change) { + case KVM_MR_CREATE: + /* Nothing more to do. */ + break; + case KVM_MR_DELETE: + /* Free the old memslot and all its metadata. */ + kvm_free_memslot(kvm, old); + break; + case KVM_MR_MOVE: + case KVM_MR_FLAGS_ONLY: + /* + * Free the dirty bitmap as needed; the below check encompasses + * both the flags and whether a ring buffer is being used) + */ + if (old->dirty_bitmap && !new->dirty_bitmap) + kvm_destroy_dirty_bitmap(old); + + /* + * The final quirk. Free the detached, old slot, but only its + * memory, not any metadata. Metadata, including arch specific + * data, may be reused by @new. + */ + kfree(old); + break; + default: + BUG(); + } +} + +/* + * Activate @new, which must be installed in the inactive slots by the caller, + * by swapping the active slots and then propagating @new to @old once @old is + * unreachable and can be safely modified. + * + * With NULL @old this simply adds @new to @active (while swapping the sets). + * With NULL @new this simply removes @old from @active and frees it + * (while also swapping the sets). + */ +static void kvm_activate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *new) +{ + int as_id = kvm_memslots_get_as_id(old, new); + + kvm_swap_active_memslots(kvm, as_id); + + /* Propagate the new memslot to the now inactive memslots. */ + kvm_replace_memslot(kvm, old, new); +} + +static void kvm_copy_memslot(struct kvm_memory_slot *dest, + const struct kvm_memory_slot *src) +{ + dest->base_gfn = src->base_gfn; + dest->npages = src->npages; + dest->dirty_bitmap = src->dirty_bitmap; + dest->arch = src->arch; + dest->userspace_addr = src->userspace_addr; + dest->flags = src->flags; + dest->id = src->id; + dest->as_id = src->as_id; +} + +static void kvm_invalidate_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *working_slot) +{ /* - * Free the old memslot's metadata. On DELETE, free the whole thing, - * otherwise free the dirty bitmap as needed (the below effectively - * checks both the flags and whether a ring buffer is being used). + * Mark the current slot INVALID. As with all memslot modifications, + * this must be done on an unreachable slot to avoid modifying the + * current slot in the active tree. */ - if (change == KVM_MR_DELETE) - kvm_free_memslot(kvm, old); - else if (old->dirty_bitmap && !new->dirty_bitmap) - kvm_destroy_dirty_bitmap(old); + kvm_copy_memslot(working_slot, old); + working_slot->flags |= KVM_MEMSLOT_INVALID; + kvm_replace_memslot(kvm, old, working_slot); + + /* + * Activate the slot that is now marked INVALID, but don't propagate + * the slot to the now inactive slots. The slot is either going to be + * deleted or recreated as a new slot. + */ + kvm_swap_active_memslots(kvm, old->as_id); + + /* + * From this point no new shadow pages pointing to a deleted, or moved, + * memslot will be created. Validation of sp->gfn happens in: + * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) + * - kvm_is_visible_gfn (mmu_check_root) + */ + kvm_arch_flush_shadow_memslot(kvm, working_slot); + + /* Was released by kvm_swap_active_memslots, reacquire. */ + mutex_lock(&kvm->slots_arch_lock); + + /* + * Copy the arch-specific field of the newly-installed slot back to the + * old slot as the arch data could have changed between releasing + * slots_arch_lock in install_new_memslots() and re-acquiring the lock + * above. Writers are required to retrieve memslots *after* acquiring + * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. + */ + old->arch = working_slot->arch; +} + +static void kvm_create_memslot(struct kvm *kvm, + const struct kvm_memory_slot *new, + struct kvm_memory_slot *working) +{ + /* + * Add the new memslot to the inactive set as a copy of the + * new memslot data provided by userspace. + */ + kvm_copy_memslot(working, new); + kvm_replace_memslot(kvm, NULL, working); + kvm_activate_memslot(kvm, NULL, working); +} + +static void kvm_delete_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + struct kvm_memory_slot *invalid_slot) +{ + /* + * Remove the old memslot (in the inactive memslots) by passing NULL as + * the "new" slot. + */ + kvm_replace_memslot(kvm, old, NULL); + + /* And do the same for the invalid version in the active slot. */ + kvm_activate_memslot(kvm, invalid_slot, NULL); + + /* Free the invalid slot, the caller will clean up the old slot. */ + kfree(invalid_slot); +} + +static struct kvm_memory_slot *kvm_move_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + struct kvm_memory_slot *invalid_slot) +{ + struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, old->as_id); + + /* + * The memslot's gfn is changing, remove it from the inactive tree, it + * will be re-added with its updated gfn. Because its range is + * changing, an in-place replace is not possible. + */ + kvm_erase_gfn_node(slots, old); + + /* + * The old slot is now fully disconnected, reuse its memory for the + * persistent copy of "new". + */ + kvm_copy_memslot(old, new); + + /* Re-add to the gfn tree with the updated gfn */ + kvm_insert_gfn_node(slots, old); + + /* Replace the current INVALID slot with the updated memslot. */ + kvm_activate_memslot(kvm, invalid_slot, old); + + /* + * Clear the INVALID flag so that the invalid_slot is now a perfect + * copy of the old slot. Return it for cleanup in the caller. + */ + WARN_ON_ONCE(!(invalid_slot->flags & KVM_MEMSLOT_INVALID)); + invalid_slot->flags &= ~KVM_MEMSLOT_INVALID; + return invalid_slot; +} + +static void kvm_update_flags_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + struct kvm_memory_slot *working_slot) +{ + /* + * Similar to the MOVE case, but the slot doesn't need to be zapped as + * an intermediate step. Instead, the old memslot is simply replaced + * with a new, updated copy in both memslot sets. + */ + kvm_copy_memslot(working_slot, new); + kvm_replace_memslot(kvm, old, working_slot); + kvm_activate_memslot(kvm, old, working_slot); } static int kvm_set_memslot(struct kvm *kvm, + struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { - struct kvm_memory_slot *slot, old; - struct kvm_memslots *slots; + struct kvm_memory_slot *working; int r; /* - * Released in install_new_memslots. + * Modifications are done on an unreachable slot. Any changes are then + * (eventually) propagated to both the active and inactive slots. This + * allocation would ideally be on-demand (in helpers), but is done here + * to avoid having to handle failure after kvm_prepare_memory_region(). + */ + working = kzalloc(sizeof(*working), GFP_KERNEL_ACCOUNT); + if (!working) + return -ENOMEM; + + /* + * Released in kvm_swap_active_memslots. * * Must be held from before the current memslots are copied until * after the new memslots are installed with rcu_assign_pointer, - * then released before the synchronize srcu in install_new_memslots. + * then released before the synchronize srcu in kvm_swap_active_memslots. * * When modifying memslots outside of the slots_lock, must be held * before reading the pointer to the current memslots until after all @@ -1718,87 +1759,60 @@ static int kvm_set_memslot(struct kvm *kvm, */ mutex_lock(&kvm->slots_arch_lock); - slots = kvm_dup_memslots(__kvm_memslots(kvm, new->as_id), change); - if (!slots) { - mutex_unlock(&kvm->slots_arch_lock); - return -ENOMEM; - } - - if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { - /* - * Note, the INVALID flag needs to be in the appropriate entry - * in the freshly allocated memslots, not in @old or @new. - */ - slot = id_to_memslot(slots, new->id); - slot->flags |= KVM_MEMSLOT_INVALID; - - /* - * We can re-use the old memslots, the only difference from the - * newly installed memslots is the invalid flag, which will get - * dropped by update_memslots anyway. We'll also revert to the - * old memslots if preparing the new memory region fails. - */ - slots = install_new_memslots(kvm, new->as_id, slots); - - /* From this point no new shadow pages pointing to a deleted, - * or moved, memslot will be created. - * - * validation of sp->gfn happens in: - * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) - * - kvm_is_visible_gfn (mmu_check_root) - */ - kvm_arch_flush_shadow_memslot(kvm, slot); - - /* Released in install_new_memslots. */ - mutex_lock(&kvm->slots_arch_lock); + /* + * Invalidate the old slot if it's being deleted or moved. This is + * done prior to actually deleting/moving the memslot to allow vCPUs to + * continue running by ensuring there are no mappings or shadow pages + * for the memslot when it is deleted/moved. Without pre-invalidation + * (and without a lock), a window would exist between effecting the + * delete/move and committing the changes in arch code where KVM or a + * guest could access a non-existent memslot. + */ + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + kvm_invalidate_memslot(kvm, old, working); + r = kvm_prepare_memory_region(kvm, old, new, change); + if (r) { /* - * The arch-specific fields of the now-active memslots could - * have been modified between releasing slots_arch_lock in - * install_new_memslots and re-acquiring slots_arch_lock above. - * Copy them to the inactive memslots. Arch code is required - * to retrieve memslots *after* acquiring slots_arch_lock, thus - * the active memslots are guaranteed to be fresh. + * For DELETE/MOVE, revert the above INVALID change. No + * modifications required since the original slot was preserved + * in the inactive slots. Changing the active memslots also + * release slots_arch_lock. */ - kvm_copy_memslots_arch(slots, __kvm_memslots(kvm, new->as_id)); + if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) + kvm_activate_memslot(kvm, working, old); + else + mutex_unlock(&kvm->slots_arch_lock); + kfree(working); + return r; } /* - * Make a full copy of the old memslot, the pointer will become stale - * when the memslots are re-sorted by update_memslots(), and the old - * memslot needs to be referenced after calling update_memslots(), e.g. - * to free its resources and for arch specific behavior. This needs to - * happen *after* (re)acquiring slots_arch_lock. + * For DELETE and MOVE, the working slot is now active as the INVALID + * version of the old slot. MOVE is particularly special as it reuses + * the old slot and returns a copy of the old slot (in working_slot). + * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the + * old slot is detached but otherwise preserved. */ - slot = id_to_memslot(slots, new->id); - if (slot) { - old = *slot; - } else { - WARN_ON_ONCE(change != KVM_MR_CREATE); - memset(&old, 0, sizeof(old)); - old.id = new->id; - old.as_id = new->as_id; - } - - r = kvm_prepare_memory_region(kvm, &old, new, change); - if (r) - goto out_slots; - - update_memslots(slots, new, change); - slots = install_new_memslots(kvm, new->as_id, slots); + if (change == KVM_MR_CREATE) + kvm_create_memslot(kvm, new, working); + else if (change == KVM_MR_DELETE) + kvm_delete_memslot(kvm, old, working); + else if (change == KVM_MR_MOVE) + old = kvm_move_memslot(kvm, old, new, working); + else if (change == KVM_MR_FLAGS_ONLY) + kvm_update_flags_memslot(kvm, old, new, working); + else + BUG(); - kvm_commit_memory_region(kvm, &old, new, change); + /* + * No need to refresh new->arch, changes after dropping slots_arch_lock + * will directly hit the final, active memsot. Architectures are + * responsible for knowing that new->arch may be stale. + */ + kvm_commit_memory_region(kvm, old, new, change); - kvfree(slots); return 0; - -out_slots: - if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) - slots = install_new_memslots(kvm, new->as_id, slots); - else - mutex_unlock(&kvm->slots_arch_lock); - kvfree(slots); - return r; } /* @@ -1859,7 +1873,7 @@ int __kvm_set_memory_region(struct kvm *kvm, new.id = id; new.as_id = as_id; - return kvm_set_memslot(kvm, &new, KVM_MR_DELETE); + return kvm_set_memslot(kvm, old, &new, KVM_MR_DELETE); } new.as_id = as_id; @@ -1896,8 +1910,10 @@ int __kvm_set_memory_region(struct kvm *kvm, } if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { + int bkt; + /* Check for overlaps */ - kvm_for_each_memslot(tmp, __kvm_memslots(kvm, as_id)) { + kvm_for_each_memslot(tmp, bkt, __kvm_memslots(kvm, as_id)) { if (tmp->id == id) continue; if (!((new.base_gfn + new.npages <= tmp->base_gfn) || @@ -1906,7 +1922,7 @@ int __kvm_set_memory_region(struct kvm *kvm, } } - return kvm_set_memslot(kvm, &new, change); + return kvm_set_memslot(kvm, old, &new, change); } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); @@ -2211,21 +2227,30 @@ EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); + u64 gen = slots->generation; struct kvm_memory_slot *slot; - int slot_index; - slot = try_get_memslot(slots, vcpu->last_used_slot, gfn); + /* + * This also protects against using a memslot from a different address space, + * since different address spaces have different generation numbers. + */ + if (unlikely(gen != vcpu->last_used_slot_gen)) { + vcpu->last_used_slot = NULL; + vcpu->last_used_slot_gen = gen; + } + + slot = try_get_memslot(vcpu->last_used_slot, gfn); if (slot) return slot; /* * Fall back to searching all memslots. We purposely use * search_memslots() instead of __gfn_to_memslot() to avoid - * thrashing the VM-wide last_used_index in kvm_memslots. + * thrashing the VM-wide last_used_slot in kvm_memslots. */ - slot = search_memslots(slots, gfn, &slot_index, false); + slot = search_memslots(slots, gfn, false); if (slot) { - vcpu->last_used_slot = slot_index; + vcpu->last_used_slot = slot; return slot; } -- cgit v1.2.3 From f4209439b522432d140d33393d4a3f12e695527b Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 6 Dec 2021 20:54:32 +0100 Subject: KVM: Optimize gfn lookup in kvm_zap_gfn_range() Introduce a memslots gfn upper bound operation and use it to optimize kvm_zap_gfn_range(). This way this handler can do a quick lookup for intersecting gfns and won't have to do a linear scan of the whole memslot set. Signed-off-by: Maciej S. Szmigiero Message-Id: --- arch/x86/kvm/mmu/mmu.c | 12 +++++-- include/linux/kvm_host.h | 94 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 103 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c61430994d19..b83ae4804176 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5728,19 +5728,22 @@ static bool __kvm_zap_rmaps(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) { const struct kvm_memory_slot *memslot; struct kvm_memslots *slots; + struct kvm_memslot_iter iter; bool flush = false; gfn_t start, end; - int i, bkt; + int i; if (!kvm_memslots_have_rmaps(kvm)) return flush; for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); - kvm_for_each_memslot(memslot, bkt, slots) { + + kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { + memslot = iter.slot; start = max(gfn_start, memslot->base_gfn); end = min(gfn_end, memslot->base_gfn + memslot->npages); - if (start >= end) + if (WARN_ON_ONCE(start >= end)) continue; flush = slot_handle_level_range(kvm, memslot, kvm_zap_rmapp, @@ -5761,6 +5764,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) bool flush; int i; + if (WARN_ON_ONCE(gfn_end <= gfn_start)) + return; + write_lock(&kvm->mmu_lock); kvm_inc_notifier_count(kvm, gfn_start, gfn_end); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9eda8a63feae..3bc98497e796 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -846,6 +846,100 @@ struct kvm_memory_slot *id_to_memslot(struct kvm_memslots *slots, int id) return NULL; } +/* Iterator used for walking memslots that overlap a gfn range. */ +struct kvm_memslot_iter { + struct kvm_memslots *slots; + struct rb_node *node; + struct kvm_memory_slot *slot; +}; + +static inline void kvm_memslot_iter_next(struct kvm_memslot_iter *iter) +{ + iter->node = rb_next(iter->node); + if (!iter->node) + return; + + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[iter->slots->node_idx]); +} + +static inline void kvm_memslot_iter_start(struct kvm_memslot_iter *iter, + struct kvm_memslots *slots, + gfn_t start) +{ + int idx = slots->node_idx; + struct rb_node *tmp; + struct kvm_memory_slot *slot; + + iter->slots = slots; + + /* + * Find the so called "upper bound" of a key - the first node that has + * its key strictly greater than the searched one (the start gfn in our case). + */ + iter->node = NULL; + for (tmp = slots->gfn_tree.rb_node; tmp; ) { + slot = container_of(tmp, struct kvm_memory_slot, gfn_node[idx]); + if (start < slot->base_gfn) { + iter->node = tmp; + tmp = tmp->rb_left; + } else { + tmp = tmp->rb_right; + } + } + + /* + * Find the slot with the lowest gfn that can possibly intersect with + * the range, so we'll ideally have slot start <= range start + */ + if (iter->node) { + /* + * A NULL previous node means that the very first slot + * already has a higher start gfn. + * In this case slot start > range start. + */ + tmp = rb_prev(iter->node); + if (tmp) + iter->node = tmp; + } else { + /* a NULL node below means no slots */ + iter->node = rb_last(&slots->gfn_tree); + } + + if (iter->node) { + iter->slot = container_of(iter->node, struct kvm_memory_slot, gfn_node[idx]); + + /* + * It is possible in the slot start < range start case that the + * found slot ends before or at range start (slot end <= range start) + * and so it does not overlap the requested range. + * + * In such non-overlapping case the next slot (if it exists) will + * already have slot start > range start, otherwise the logic above + * would have found it instead of the current slot. + */ + if (iter->slot->base_gfn + iter->slot->npages <= start) + kvm_memslot_iter_next(iter); + } +} + +static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_t end) +{ + if (!iter->node) + return false; + + /* + * If this slot starts beyond or at the end of the range so does + * every next one + */ + return iter->slot->base_gfn < end; +} + +/* Iterate over each memslot at least partially intersecting [start, end) range */ +#define kvm_for_each_memslot_in_gfn_range(iter, slots, start, end) \ + for (kvm_memslot_iter_start(iter, slots, start); \ + kvm_memslot_iter_is_valid(iter, end); \ + kvm_memslot_iter_next(iter)) + /* * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations: * - create a new memory slot -- cgit v1.2.3 From 8283e36abfff507c64fe8289ac30ea7ab59648aa Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Mon, 15 Nov 2021 15:45:58 -0800 Subject: KVM: x86/mmu: Propagate memslot const qualifier In preparation for implementing in-place hugepage promotion, various functions will need to be called from zap_collapsible_spte_range, which has the const qualifier on its memslot argument. Propagate the const qualifier to the various functions which will be needed. This just serves to simplify the following patch. No functional change intended. Signed-off-by: Ben Gardon Message-Id: <20211115234603.2908381-11-bgardon@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_page_track.h | 4 ++-- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/mmu/mmu_internal.h | 2 +- arch/x86/kvm/mmu/page_track.c | 4 ++-- arch/x86/kvm/mmu/spte.c | 2 +- arch/x86/kvm/mmu/spte.h | 2 +- include/linux/kvm_host.h | 10 +++++----- virt/kvm/kvm_main.c | 12 ++++++------ 8 files changed, 19 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index e99a30a4d38b..eb186bc57f6a 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -64,8 +64,8 @@ void kvm_slot_page_track_remove_page(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, enum kvm_page_track_mode mode); bool kvm_slot_page_track_is_active(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode); + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode); void kvm_page_track_register_notifier(struct kvm *kvm, diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 29bcf26b0cb3..c28cf7eeb79d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2580,7 +2580,7 @@ static void kvm_unsync_page(struct kvm *kvm, struct kvm_mmu_page *sp) * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must * be write-protected. */ -int mmu_try_to_unsync_pages(struct kvm *kvm, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch) { struct kvm_mmu_page *sp; diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 787b8c553b9e..da6166b5c377 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -117,7 +117,7 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } -int mmu_try_to_unsync_pages(struct kvm *kvm, struct kvm_memory_slot *slot, +int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 35c221d5f6ce..68eb1fb548b6 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -174,8 +174,8 @@ EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page); * check if the corresponding access on the specified guest page is tracked. */ bool kvm_slot_page_track_is_active(struct kvm *kvm, - struct kvm_memory_slot *slot, gfn_t gfn, - enum kvm_page_track_mode mode) + const struct kvm_memory_slot *slot, + gfn_t gfn, enum kvm_page_track_mode mode) { int index; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 8d3fe4311bc1..8a7b03207762 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -90,7 +90,7 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte) diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index cc432f9a966b..a4af2a42695c 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -330,7 +330,7 @@ static inline u64 get_mmio_spte_generation(u64 spte) } bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - struct kvm_memory_slot *slot, + const struct kvm_memory_slot *slot, unsigned int pte_access, gfn_t gfn, kvm_pfn_t pfn, u64 old_spte, bool prefetch, bool can_unsync, bool host_writable, u64 *new_spte); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3bc98497e796..3eb7695aaa73 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -460,7 +460,7 @@ struct kvm_memory_slot { u16 as_id; }; -static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot) +static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_LOG_DIRTY_PAGES; } @@ -994,9 +994,9 @@ void kvm_set_page_accessed(struct page *page); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn); -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn); +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva); @@ -1073,7 +1073,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); -void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e588dc4f9b7d..f93b60165fd7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2285,12 +2285,12 @@ out: return size; } -static bool memslot_is_readonly(struct kvm_memory_slot *slot) +static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } -static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, +static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -2585,7 +2585,7 @@ exit: return pfn; } -kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, +kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool *async, bool write_fault, bool *writable, hva_t *hva) { @@ -2625,13 +2625,13 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL); } @@ -3150,7 +3150,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty_in_slot(struct kvm *kvm, - struct kvm_memory_slot *memslot, + const struct kvm_memory_slot *memslot, gfn_t gfn) { if (memslot && kvm_slot_dirty_track_enabled(memslot)) { -- cgit v1.2.3 From 510958e997217e39a16b47afb5a44dfa39013964 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 8 Oct 2021 19:11:57 -0700 Subject: KVM: Force PPC to define its own rcuwait object Do not define/reference kvm_vcpu.wait if __KVM_HAVE_ARCH_WQP is true, and instead force the architecture (PPC) to define its own rcuwait object. Allowing common KVM to directly access vcpu->wait without a guard makes it all too easy to introduce potential bugs, e.g. kvm_vcpu_block(), kvm_vcpu_on_spin(), and async_pf_execute() all operate on vcpu->wait, not the result of kvm_arch_vcpu_get_wait(), and so may do the wrong thing for PPC. Due to PPC's shenanigans with respect to callbacks and waits (it switches to the virtual core's wait object at KVM_RUN!?!?), it's not clear whether or not this fixes any bugs. Signed-off-by: Sean Christopherson Message-Id: <20211009021236.4122790-5-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kvm/powerpc.c | 3 ++- include/linux/kvm_host.h | 2 ++ virt/kvm/async_pf.c | 2 +- virt/kvm/kvm_main.c | 9 ++++++--- 5 files changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e4d23193eba7..6ec97eff9563 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -749,6 +749,7 @@ struct kvm_vcpu_arch { u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; + struct rcuwait wait; struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index f1233500f4dc..7de9ddbc6af1 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -753,7 +753,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) goto out_vcpu_uninit; - vcpu->arch.waitp = &vcpu->wait; + rcuwait_init(&vcpu->arch.wait); + vcpu->arch.waitp = &vcpu->arch.wait; kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3eb7695aaa73..afacbfb2e482 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -314,7 +314,9 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; +#ifndef __KVM_HAVE_ARCH_WQP struct rcuwait wait; +#endif struct pid __rcu *pid; int sigset_active; sigset_t sigset; diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index dd777688d14a..ccb35c22785e 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -85,7 +85,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, cr2_or_gpa); - rcuwait_wake_up(&vcpu->wait); + rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a26b069a6929..11db44f4110e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -422,7 +422,9 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; +#ifndef __KVM_HAVE_ARCH_WQP rcuwait_init(&vcpu->wait); +#endif kvm_async_pf_vcpu_init(vcpu); vcpu->pre_pcpu = -1; @@ -3284,6 +3286,7 @@ update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited) */ void kvm_vcpu_block(struct kvm_vcpu *vcpu) { + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); ktime_t start, cur, poll_end; bool waited = false; @@ -3322,7 +3325,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) } - prepare_to_rcuwait(&vcpu->wait); + prepare_to_rcuwait(wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); @@ -3332,7 +3335,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) waited = true; schedule(); } - finish_rcuwait(&vcpu->wait); + finish_rcuwait(wait); cur = ktime_get(); if (waited) { vcpu->stat.generic.halt_wait_ns += @@ -3544,7 +3547,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (rcuwait_active(&vcpu->wait) && + if (rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)) && !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && -- cgit v1.2.3 From 91b99ea7065786d0bff1c9281b002455dbaeb08b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 8 Oct 2021 19:12:06 -0700 Subject: KVM: Rename kvm_vcpu_block() => kvm_vcpu_halt() Rename kvm_vcpu_block() to kvm_vcpu_halt() in preparation for splitting the actual "block" sequences into a separate helper (to be named kvm_vcpu_block()). x86 will use the standalone block-only path to handle non-halt cases where the vCPU is not runnable. Rename block_ns to halt_ns to match the new function name. No functional change intended. Reviewed-by: David Matlack Reviewed-by: Christian Borntraeger Signed-off-by: Sean Christopherson Message-Id: <20211009021236.4122790-14-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arch_timer.c | 2 +- arch/arm64/kvm/arm.c | 2 +- arch/arm64/kvm/handle_exit.c | 2 +- arch/arm64/kvm/psci.c | 2 +- arch/mips/kvm/emulate.c | 2 +- arch/powerpc/kvm/book3s_pr.c | 2 +- arch/powerpc/kvm/book3s_pr_papr.c | 2 +- arch/powerpc/kvm/booke.c | 2 +- arch/powerpc/kvm/powerpc.c | 2 +- arch/riscv/kvm/vcpu_exit.c | 2 +- arch/s390/kvm/interrupt.c | 2 +- arch/x86/kvm/x86.c | 11 +++++++++-- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 20 +++++++++----------- 14 files changed, 30 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index d6f4114f1d11..3aeaa79ad4a2 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -467,7 +467,7 @@ out: } /* - * Schedule the background timer before calling kvm_vcpu_block, so that this + * Schedule the background timer before calling kvm_vcpu_halt, so that this * thread is removed from its waitqueue and made runnable when there's a timer * interrupt to handle. */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ced54a3a3db0..77ecc11d67ae 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -681,7 +681,7 @@ void kvm_vcpu_wfi(struct kvm_vcpu *vcpu) vgic_v4_put(vcpu, true); preempt_enable(); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); preempt_disable(); diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 4794563a506b..6d0baf71aa67 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -82,7 +82,7 @@ static int handle_no_fpsimd(struct kvm_vcpu *vcpu) * * WFE: Yield the CPU and come back to this vcpu when the scheduler * decides to. - * WFI: Simply call kvm_vcpu_block(), which will halt execution of + * WFI: Simply call kvm_vcpu_halt(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. */ diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index ed675fce8fb7..ad6c9ef32928 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -46,7 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); return PSCI_RET_SUCCESS; diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 22e745e49b0a..b494d8d39290 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -952,7 +952,7 @@ enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu) if (!vcpu->arch.pending_exceptions) { kvm_vz_lose_htimer(vcpu); vcpu->arch.wait = 1; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); /* * We we are runnable, then definitely go off to user space to diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 30426e8c8cf6..34a801c3604a 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -492,7 +492,7 @@ static void kvmppc_set_msr_pr(struct kvm_vcpu *vcpu, u64 msr) if (msr & MSR_POW) { if (!vcpu->arch.pending_exceptions) { - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c index ac14239f3424..1f10e7dfcdd0 100644 --- a/arch/powerpc/kvm/book3s_pr_papr.c +++ b/arch/powerpc/kvm/book3s_pr_papr.c @@ -376,7 +376,7 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd) return kvmppc_h_pr_stuff_tce(vcpu); case H_CEDE: kvmppc_set_msr_fast(vcpu, kvmppc_get_msr(vcpu) | MSR_EE); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); vcpu->stat.generic.halt_wakeup++; return EMULATE_DONE; diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 53b4c9597c30..06c5830a93f9 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -718,7 +718,7 @@ int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu) if (vcpu->arch.shared->msr & MSR_WE) { local_irq_enable(); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); hard_irq_disable(); diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 7de9ddbc6af1..2ad0ccd202d5 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -236,7 +236,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu) break; case EV_HCALL_TOKEN(EV_IDLE): r = EV_SUCCESS; - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); break; default: diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index 7f2d742ae4c6..571f319e995a 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -146,7 +146,7 @@ static int system_opcode_insn(struct kvm_vcpu *vcpu, vcpu->stat.wfi_exit_stat++; if (!kvm_arch_vcpu_runnable(vcpu)) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); vcpu->arch.srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_clear_request(KVM_REQ_UNHALT, vcpu); } diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 3c8246fa208b..dbabd6f2404e 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -1335,7 +1335,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 4, "enabled wait: %llu ns", sltime); no_timer: srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); vcpu->valid_wakeup = false; __unset_cpu_idle(vcpu); vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 43cabc747318..e3dd76f251e9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8727,6 +8727,13 @@ void kvm_arch_exit(void) static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { + /* + * The vCPU has halted, e.g. executed HLT. Update the run state if the + * local APIC is in-kernel, the run loop will detect the non-runnable + * state and halt the vCPU. Exit to userspace if the local APIC is + * managed by userspace, in which case userspace is responsible for + * handling wake events. + */ ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { vcpu->arch.mp_state = state; @@ -9999,7 +10006,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) if (!kvm_arch_vcpu_runnable(vcpu) && (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) @@ -10196,7 +10203,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) r = -EINTR; goto out; } - kvm_vcpu_block(vcpu); + kvm_vcpu_halt(vcpu); if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index afacbfb2e482..ea3c22d55d56 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1102,7 +1102,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); -void kvm_vcpu_block(struct kvm_vcpu *vcpu); +void kvm_vcpu_halt(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 53c58606e1e2..0d301c95fa1a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3294,17 +3294,14 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, } } -/* - * The vCPU has executed a HLT instruction with in-kernel mode enabled. - */ -void kvm_vcpu_block(struct kvm_vcpu *vcpu) +void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; ktime_t start, cur, poll_end; bool waited = false; - u64 block_ns; + u64 halt_ns; start = cur = poll_end = ktime_get(); if (do_halt_poll) { @@ -3346,7 +3343,8 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: - block_ns = ktime_to_ns(cur) - ktime_to_ns(start); + /* The total time the vCPU was "halted", including polling time. */ + halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); /* * Note, halt-polling is considered successful so long as the vCPU was @@ -3360,24 +3358,24 @@ out: if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); } else if (vcpu->kvm->max_halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) + if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && - block_ns > vcpu->kvm->max_halt_poll_ns) + halt_ns > vcpu->kvm->max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns && - block_ns < vcpu->kvm->max_halt_poll_ns) + halt_ns < vcpu->kvm->max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } - trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); + trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_vcpu_block); +EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { -- cgit v1.2.3 From fac4268894394213127e43856f41d10f29131e69 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 8 Oct 2021 19:12:07 -0700 Subject: KVM: Split out a kvm_vcpu_block() helper from kvm_vcpu_halt() Factor out the "block" part of kvm_vcpu_halt() so that x86 can emulate non-halt wait/sleep/block conditions that should not be subjected to halt-polling. No functional change intended. Reviewed-by: Christian Borntraeger Reviewed-by: David Matlack Signed-off-by: Sean Christopherson Message-Id: <20211009021236.4122790-15-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 52 +++++++++++++++++++++++++++++++++--------------- 2 files changed, 37 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ea3c22d55d56..bd13c5b5bd1d 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1103,6 +1103,7 @@ void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); void kvm_vcpu_halt(struct kvm_vcpu *vcpu); +bool kvm_vcpu_block(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0d301c95fa1a..370b95ad5f03 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3272,6 +3272,35 @@ out: return ret; } +/* + * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is + * pending. This is mostly used when halting a vCPU, but may also be used + * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. + */ +bool kvm_vcpu_block(struct kvm_vcpu *vcpu) +{ + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + bool waited = false; + + kvm_arch_vcpu_blocking(vcpu); + + prepare_to_rcuwait(wait); + for (;;) { + set_current_state(TASK_INTERRUPTIBLE); + + if (kvm_vcpu_check_block(vcpu) < 0) + break; + + waited = true; + schedule(); + } + finish_rcuwait(wait); + + kvm_arch_vcpu_unblocking(vcpu); + + return waited; +} + static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, ktime_t end, bool success) { @@ -3294,9 +3323,14 @@ static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, } } +/* + * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt + * polling is enabled, busy wait for a short time before blocking to avoid the + * expensive block+unblock sequence if a wake event arrives soon after the vCPU + * is halted. + */ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { - struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); bool do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; ktime_t start, cur, poll_end; @@ -3319,21 +3353,7 @@ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) } while (kvm_vcpu_can_poll(cur, stop)); } - kvm_arch_vcpu_blocking(vcpu); - - prepare_to_rcuwait(wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - - if (kvm_vcpu_check_block(vcpu) < 0) - break; - - waited = true; - schedule(); - } - finish_rcuwait(wait); - - kvm_arch_vcpu_unblocking(vcpu); + waited = kvm_vcpu_block(vcpu); cur = ktime_get(); if (waited) { -- cgit v1.2.3 From c3858335c711569b82a234a560dc19247e8f3fcc Mon Sep 17 00:00:00 2001 From: Jing Zhang Date: Fri, 8 Oct 2021 19:12:08 -0700 Subject: KVM: stats: Add stat to detect if vcpu is currently blocking Add a "blocking" stat that userspace can use to detect the case where a vCPU is not being run because of an vCPU/guest action, e.g. HLT or WFS on x86, WFI on arm64, etc... Current guest/host/halt stats don't show this well, e.g. if a guest halts for a long period of time then the vCPU could could appear pathologically blocked due to a host condition, when in reality the vCPU has been put into a not-runnable state by the guest. Originally-by: Cannon Matthews Suggested-by: Sean Christopherson Reviewed-by: David Matlack Signed-off-by: Jing Zhang [sean: renamed stat to "blocking", massaged changelog] Signed-off-by: Sean Christopherson Message-Id: <20211009021236.4122790-16-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 3 ++- include/linux/kvm_types.h | 1 + virt/kvm/kvm_main.c | 4 ++++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index bd13c5b5bd1d..dc7740cafea7 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1587,7 +1587,8 @@ struct _kvm_stats_desc { STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_poll_fail_hist, \ HALT_POLL_HIST_COUNT), \ STATS_DESC_LOGHIST_TIME_NSEC(VCPU_GENERIC, halt_wait_hist, \ - HALT_POLL_HIST_COUNT) + HALT_POLL_HIST_COUNT), \ + STATS_DESC_ICOUNTER(VCPU_GENERIC, blocking) extern struct dentry *kvm_debugfs_dir; diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 234eab059839..888ef12862c9 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -87,6 +87,7 @@ struct kvm_vcpu_stat_generic { u64 halt_poll_success_hist[HALT_POLL_HIST_COUNT]; u64 halt_poll_fail_hist[HALT_POLL_HIST_COUNT]; u64 halt_wait_hist[HALT_POLL_HIST_COUNT]; + u64 blocking; }; #define KVM_STATS_NAME_SIZE 48 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 370b95ad5f03..2630db6e8cb5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3282,6 +3282,8 @@ bool kvm_vcpu_block(struct kvm_vcpu *vcpu) struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool waited = false; + vcpu->stat.generic.blocking = 1; + kvm_arch_vcpu_blocking(vcpu); prepare_to_rcuwait(wait); @@ -3298,6 +3300,8 @@ bool kvm_vcpu_block(struct kvm_vcpu *vcpu) kvm_arch_vcpu_unblocking(vcpu); + vcpu->stat.generic.blocking = 0; + return waited; } -- cgit v1.2.3 From d92a5d1c6c757f659ffb9c2c2e65fcf3d571c14e Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 8 Oct 2021 19:12:12 -0700 Subject: KVM: Add helpers to wake/query blocking vCPU Add helpers to wake and query a blocking vCPU. In addition to providing nice names, the helpers reduce the probability of KVM neglecting to use kvm_arch_vcpu_get_wait(). No functional change intended. Signed-off-by: Sean Christopherson Message-Id: <20211009021236.4122790-20-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/arm64/kvm/arch_timer.c | 3 +-- arch/arm64/kvm/arm.c | 2 +- arch/x86/kvm/lapic.c | 2 +- include/linux/kvm_host.h | 14 ++++++++++++++ virt/kvm/async_pf.c | 2 +- virt/kvm/kvm_main.c | 8 ++------ 6 files changed, 20 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 3aeaa79ad4a2..6e542e2eae32 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -649,7 +649,6 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; - struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); if (unlikely(!timer->enabled)) return; @@ -672,7 +671,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); - if (rcuwait_active(wait)) + if (kvm_vcpu_is_blocking(vcpu)) kvm_timer_blocking(vcpu); /* diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 77ecc11d67ae..14106a7c75b5 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -631,7 +631,7 @@ void kvm_arm_resume_guest(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); + __kvm_vcpu_wake_up(vcpu); } } diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 451e80306b51..bbac8477b3ec 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1931,7 +1931,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(rcuwait_active(&vcpu->wait)); + WARN_ON(kvm_vcpu_is_blocking(vcpu)); apic_timer_expired(apic, false); cancel_hv_timer(apic); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dc7740cafea7..f8ed799e8674 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1286,6 +1286,20 @@ static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) #endif } +/* + * Wake a vCPU if necessary, but don't do any stats/metadata updates. Returns + * true if the vCPU was blocking and was awakened, false otherwise. + */ +static inline bool __kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) +{ + return !!rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); +} + +static inline bool kvm_vcpu_is_blocking(struct kvm_vcpu *vcpu) +{ + return rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)); +} + #ifdef __KVM_HAVE_ARCH_INTC_INITIALIZED /* * returns true if the virtual interrupt controller is initialized and diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index ccb35c22785e..9bfe1d6f6529 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -85,7 +85,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, cr2_or_gpa); - rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); + __kvm_vcpu_wake_up(vcpu); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 97bde32082d0..f3acff708bf5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3403,10 +3403,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { - struct rcuwait *waitp; - - waitp = kvm_arch_vcpu_get_wait(vcpu); - if (rcuwait_wake_up(waitp)) { + if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.generic.halt_wakeup; return true; @@ -3574,8 +3571,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (rcuwait_active(kvm_arch_vcpu_get_wait(vcpu)) && - !vcpu_dy_runnable(vcpu)) + if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && -- cgit v1.2.3 From 815f0e738a8d5663a02350e2580706829144a722 Mon Sep 17 00:00:00 2001 From: Horatiu Vultur Date: Wed, 3 Nov 2021 09:50:59 +0100 Subject: clk: gate: Add devm_clk_hw_register_gate() Add devm_clk_hw_register_gate() - devres-managed version of clk_hw_register_gate() Suggested-by: Stephen Boyd Signed-off-by: Horatiu Vultur Acked-by: Nicolas Ferre Signed-off-by: Nicolas Ferre Link: https://lore.kernel.org/r/20211103085102.1656081-2-horatiu.vultur@microchip.com --- drivers/clk/clk-gate.c | 35 +++++++++++++++++++++++++++++++++++ include/linux/clk-provider.h | 23 +++++++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/linux') diff --git a/drivers/clk/clk-gate.c b/drivers/clk/clk-gate.c index 070dc47e95a1..64283807600b 100644 --- a/drivers/clk/clk-gate.c +++ b/drivers/clk/clk-gate.c @@ -7,6 +7,7 @@ */ #include +#include #include #include #include @@ -222,3 +223,37 @@ void clk_hw_unregister_gate(struct clk_hw *hw) kfree(gate); } EXPORT_SYMBOL_GPL(clk_hw_unregister_gate); + +static void devm_clk_hw_release_gate(struct device *dev, void *res) +{ + clk_hw_unregister_gate(*(struct clk_hw **)res); +} + +struct clk_hw *__devm_clk_hw_register_gate(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, + unsigned long flags, + void __iomem *reg, u8 bit_idx, + u8 clk_gate_flags, spinlock_t *lock) +{ + struct clk_hw **ptr, *hw; + + ptr = devres_alloc(devm_clk_hw_release_gate, sizeof(*ptr), GFP_KERNEL); + if (!ptr) + return ERR_PTR(-ENOMEM); + + hw = __clk_hw_register_gate(dev, np, name, parent_name, parent_hw, + parent_data, flags, reg, bit_idx, + clk_gate_flags, lock); + + if (!IS_ERR(hw)) { + *ptr = hw; + devres_add(dev, ptr); + } else { + devres_free(ptr); + } + + return hw; +} +EXPORT_SYMBOL_GPL(__devm_clk_hw_register_gate); diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index f59c875271a0..2faa6f7aa8a8 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -490,6 +490,13 @@ struct clk_hw *__clk_hw_register_gate(struct device *dev, unsigned long flags, void __iomem *reg, u8 bit_idx, u8 clk_gate_flags, spinlock_t *lock); +struct clk_hw *__devm_clk_hw_register_gate(struct device *dev, + struct device_node *np, const char *name, + const char *parent_name, const struct clk_hw *parent_hw, + const struct clk_parent_data *parent_data, + unsigned long flags, + void __iomem *reg, u8 bit_idx, + u8 clk_gate_flags, spinlock_t *lock); struct clk *clk_register_gate(struct device *dev, const char *name, const char *parent_name, unsigned long flags, void __iomem *reg, u8 bit_idx, @@ -544,6 +551,22 @@ struct clk *clk_register_gate(struct device *dev, const char *name, __clk_hw_register_gate((dev), NULL, (name), NULL, NULL, (parent_data), \ (flags), (reg), (bit_idx), \ (clk_gate_flags), (lock)) +/** + * devm_clk_hw_register_gate - register a gate clock with the clock framework + * @dev: device that is registering this clock + * @name: name of this clock + * @parent_name: name of this clock's parent + * @flags: framework-specific flags for this clock + * @reg: register address to control gating of this clock + * @bit_idx: which bit in the register controls gating of this clock + * @clk_gate_flags: gate-specific flags for this clock + * @lock: shared register lock for this clock + */ +#define devm_clk_hw_register_gate(dev, name, parent_name, flags, reg, bit_idx,\ + clk_gate_flags, lock) \ + __devm_clk_hw_register_gate((dev), NULL, (name), (parent_name), NULL, \ + NULL, (flags), (reg), (bit_idx), \ + (clk_gate_flags), (lock)) void clk_unregister_gate(struct clk *clk); void clk_hw_unregister_gate(struct clk_hw *hw); int clk_gate_is_enabled(struct clk_hw *hw); -- cgit v1.2.3 From 444dd878e85fb33fcfb2682cfdab4c236f33ea3e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 3 Dec 2021 17:19:47 +0100 Subject: PM: runtime: Fix pm_runtime_active() kerneldoc comment The kerneldoc comment of pm_runtime_active() does not reflect the behavior of the function, so update it accordingly. Fixes: 403d2d116ec0 ("PM: runtime: Add kerneldoc comments to multiple helpers") Signed-off-by: Rafael J. Wysocki Reviewed-by: Ulf Hansson --- include/linux/pm_runtime.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 222da43b7096..eddd66d426ca 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -129,7 +129,7 @@ static inline bool pm_runtime_suspended(struct device *dev) * pm_runtime_active - Check whether or not a device is runtime-active. * @dev: Target device. * - * Return %true if runtime PM is enabled for @dev and its runtime PM status is + * Return %true if runtime PM is disabled for @dev or its runtime PM status is * %RPM_ACTIVE, or %false otherwise. * * Note that the return value of this function can only be trusted if it is -- cgit v1.2.3 From 74d9555580c48a04b2c3b742dfb0c80777aa0b26 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Mon, 8 Nov 2021 16:09:41 +0000 Subject: PM: hibernate: Allow ACPI hardware signature to be honoured Theoretically, when the hardware signature in FACS changes, the OS is supposed to gracefully decline to attempt to resume from S4: "If the signature has changed, OSPM will not restore the system context and can boot from scratch" In practice, Windows doesn't do this and many laptop vendors do allow the signature to change especially when docking/undocking, so it would be a bad idea to simply comply with the specification by default in the general case. However, there are use cases where we do want the compliant behaviour and we know it's safe. Specifically, when resuming virtual machines where we know the hypervisor has changed sufficiently that resume will fail. We really want to be able to *tell* the guest kernel not to try, so it boots cleanly and doesn't just crash. This patch provides a way to opt in to the spec-compliant behaviour on the command line. A follow-up patch may do this automatically for certain "known good" machines based on a DMI match, or perhaps just for all hypervisor guests since there's no good reason a hypervisor would change the hardware_signature that it exposes to guests *unless* it wants them to obey the ACPI specification. Signed-off-by: David Woodhouse Signed-off-by: Rafael J. Wysocki --- Documentation/admin-guide/kernel-parameters.txt | 15 +++++++++++--- arch/x86/kernel/acpi/sleep.c | 4 +++- drivers/acpi/sleep.c | 26 ++++++++++++++++++++----- include/linux/acpi.h | 2 +- include/linux/suspend.h | 1 + kernel/power/power.h | 1 + kernel/power/swap.c | 16 +++++++++++++-- 7 files changed, 53 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9725c546a0d4..10e0a3a27516 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -225,14 +225,23 @@ For broken nForce2 BIOS resulting in XT-PIC timer. acpi_sleep= [HW,ACPI] Sleep options - Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, - old_ordering, nonvs, sci_force_enable, nobl } + Format: { s3_bios, s3_mode, s3_beep, s4_hwsig, + s4_nohwsig, old_ordering, nonvs, + sci_force_enable, nobl } See Documentation/power/video.rst for information on s3_bios and s3_mode. s3_beep is for debugging; it makes the PC's speaker beep as soon as the kernel's real-mode entry point is called. + s4_hwsig causes the kernel to check the ACPI hardware + signature during resume from hibernation, and gracefully + refuse to resume if it has changed. This complies with + the ACPI specification but not with reality, since + Windows does not do this and many laptops do change it + on docking. So the default behaviour is to allow resume + and simply warn when the signature changes, unless the + s4_hwsig option is enabled. s4_nohwsig prevents ACPI hardware signature from being - used during resume from hibernation. + used (or even warned about) during resume. old_ordering causes the ACPI 1.0 ordering of the _PTS control method, with respect to putting devices into low power states, to be enforced (the ACPI 2.0 ordering diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 3f85fcae450c..1e97f944b47d 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -139,8 +139,10 @@ static int __init acpi_sleep_setup(char *str) if (strncmp(str, "s3_beep", 7) == 0) acpi_realmode_flags |= 4; #ifdef CONFIG_HIBERNATION + if (strncmp(str, "s4_hwsig", 8) == 0) + acpi_check_s4_hw_signature(1); if (strncmp(str, "s4_nohwsig", 10) == 0) - acpi_no_s4_hw_signature(); + acpi_check_s4_hw_signature(0); #endif if (strncmp(str, "nonvs", 5) == 0) acpi_nvs_nosave(); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index eaa47753b758..4dfbfc69db34 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -877,11 +877,11 @@ static inline void acpi_sleep_syscore_init(void) {} #ifdef CONFIG_HIBERNATION static unsigned long s4_hardware_signature; static struct acpi_table_facs *facs; -static bool nosigcheck; +static int sigcheck = -1; /* Default behaviour is just to warn */ -void __init acpi_no_s4_hw_signature(void) +void __init acpi_check_s4_hw_signature(int check) { - nosigcheck = true; + sigcheck = check; } static int acpi_hibernation_begin(pm_message_t stage) @@ -1009,12 +1009,28 @@ static void acpi_sleep_hibernate_setup(void) hibernation_set_ops(old_suspend_ordering ? &acpi_hibernation_ops_old : &acpi_hibernation_ops); sleep_states[ACPI_STATE_S4] = 1; - if (nosigcheck) + if (!sigcheck) return; acpi_get_table(ACPI_SIG_FACS, 1, (struct acpi_table_header **)&facs); - if (facs) + if (facs) { + /* + * s4_hardware_signature is the local variable which is just + * used to warn about mismatch after we're attempting to + * resume (in violation of the ACPI specification.) + */ s4_hardware_signature = facs->hardware_signature; + + if (sigcheck > 0) { + /* + * If we're actually obeying the ACPI specification + * then the signature is written out as part of the + * swsusp header, in order to allow the boot kernel + * to gracefully decline to resume. + */ + swsusp_hardware_signature = facs->hardware_signature; + } + } } #else /* !CONFIG_HIBERNATION */ static inline void acpi_sleep_hibernate_setup(void) {} diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b28f8790192a..6c0798db6bde 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -506,7 +506,7 @@ acpi_status acpi_release_memory(acpi_handle handle, struct resource *res, int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION -void __init acpi_no_s4_hw_signature(void); +void __init acpi_check_s4_hw_signature(int check); #endif #ifdef CONFIG_PM_SLEEP diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8af13ba60c7e..5785d909c321 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -446,6 +446,7 @@ extern unsigned long get_safe_page(gfp_t gfp_mask); extern asmlinkage int swsusp_arch_suspend(void); extern asmlinkage int swsusp_arch_resume(void); +extern u32 swsusp_hardware_signature; extern void hibernation_set_ops(const struct platform_hibernation_ops *ops); extern int hibernate(void); extern bool system_entering_hibernation(void); diff --git a/kernel/power/power.h b/kernel/power/power.h index 326f8d032eb5..b4f433943209 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -170,6 +170,7 @@ extern int swsusp_swap_in_use(void); #define SF_PLATFORM_MODE 1 #define SF_NOCOMPRESS_MODE 2 #define SF_CRC32_MODE 4 +#define SF_HW_SIG 8 /* kernel/power/hibernate.c */ extern int swsusp_check(void); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index ff326c2cb77b..ad10359030a4 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -36,6 +36,8 @@ #define HIBERNATE_SIG "S1SUSPEND" +u32 swsusp_hardware_signature; + /* * When reading an {un,}compressed image, we may restore pages in place, * in which case some architectures need these pages cleaning before they @@ -104,7 +106,8 @@ struct swap_map_handle { struct swsusp_header { char reserved[PAGE_SIZE - 20 - sizeof(sector_t) - sizeof(int) - - sizeof(u32)]; + sizeof(u32) - sizeof(u32)]; + u32 hw_sig; u32 crc32; sector_t image; unsigned int flags; /* Flags to pass to the "boot" kernel */ @@ -312,7 +315,6 @@ static int hib_wait_io(struct hib_bio_batch *hb) /* * Saving part */ - static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) { int error; @@ -324,6 +326,10 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) memcpy(swsusp_header->orig_sig,swsusp_header->sig, 10); memcpy(swsusp_header->sig, HIBERNATE_SIG, 10); swsusp_header->image = handle->first_sector; + if (swsusp_hardware_signature) { + swsusp_header->hw_sig = swsusp_hardware_signature; + flags |= SF_HW_SIG; + } swsusp_header->flags = flags; if (flags & SF_CRC32_MODE) swsusp_header->crc32 = handle->crc32; @@ -1537,6 +1543,12 @@ int swsusp_check(void) } else { error = -EINVAL; } + if (!error && swsusp_header->flags & SF_HW_SIG && + swsusp_header->hw_sig != swsusp_hardware_signature) { + pr_info("Suspend image hardware signature mismatch (%08x now %08x); aborting resume.\n", + swsusp_header->hw_sig, swsusp_hardware_signature); + error = -EINVAL; + } put: if (error) -- cgit v1.2.3 From 8260b9820f7050461b8969305bbd8cb5654f0c74 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Mon, 6 Dec 2021 16:55:03 +0300 Subject: x86/sev: Use CC_ATTR attribute to generalize string I/O unroll INS/OUTS are not supported in TDX guests and cause #UD. Kernel has to avoid them when running in TDX guest. To support existing usage, string I/O operations are unrolled using IN/OUT instructions. AMD SEV platform implements this support by adding unroll logic in ins#bwl()/outs#bwl() macros with SEV-specific checks. Since TDX VM guests will also need similar support, use CC_ATTR_GUEST_UNROLL_STRING_IO and generic cc_platform_has() API to implement it. String I/O helpers were the last users of sev_key_active() interface and sev_enable_key static key. Remove them. [ bp: Move comment too and do not delete it. ] Suggested-by: Tom Lendacky Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Kirill A. Shutemov Signed-off-by: Borislav Petkov Reviewed-by: Tony Luck Reviewed-by: Tom Lendacky Tested-by: Tom Lendacky Link: https://lkml.kernel.org/r/20211206135505.75045-2-kirill.shutemov@linux.intel.com --- arch/x86/include/asm/io.h | 20 +++----------------- arch/x86/kernel/cc_platform.c | 8 ++++++++ arch/x86/mm/mem_encrypt.c | 10 ---------- include/linux/cc_platform.h | 11 +++++++++++ 4 files changed, 22 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 5c6a4af0b911..f6d91ecb8026 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -40,6 +40,7 @@ #include #include +#include #include #include #include @@ -256,21 +257,6 @@ static inline void slow_down_io(void) #endif -#ifdef CONFIG_AMD_MEM_ENCRYPT -#include - -extern struct static_key_false sev_enable_key; -static inline bool sev_key_active(void) -{ - return static_branch_unlikely(&sev_enable_key); -} - -#else /* !CONFIG_AMD_MEM_ENCRYPT */ - -static inline bool sev_key_active(void) { return false; } - -#endif /* CONFIG_AMD_MEM_ENCRYPT */ - #define BUILDIO(bwl, bw, type) \ static inline void out##bwl(unsigned type value, int port) \ { \ @@ -301,7 +287,7 @@ static inline unsigned type in##bwl##_p(int port) \ \ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ { \ - if (sev_key_active()) { \ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ unsigned type *value = (unsigned type *)addr; \ while (count) { \ out##bwl(*value, port); \ @@ -317,7 +303,7 @@ static inline void outs##bwl(int port, const void *addr, unsigned long count) \ \ static inline void ins##bwl(int port, void *addr, unsigned long count) \ { \ - if (sev_key_active()) { \ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ unsigned type *value = (unsigned type *)addr; \ while (count) { \ *value = in##bwl(port); \ diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c index 03bb2f343ddb..8a25b1c0d480 100644 --- a/arch/x86/kernel/cc_platform.c +++ b/arch/x86/kernel/cc_platform.c @@ -50,6 +50,14 @@ static bool amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_STATE_ENCRYPT: return sev_status & MSR_AMD64_SEV_ES_ENABLED; + /* + * With SEV, the rep string I/O instructions need to be unrolled + * but SEV-ES supports them through the #VC handler. + */ + case CC_ATTR_GUEST_UNROLL_STRING_IO: + return (sev_status & MSR_AMD64_SEV_ENABLED) && + !(sev_status & MSR_AMD64_SEV_ES_ENABLED); + default: return false; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 35487305d8af..b520021a7e7b 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -43,8 +43,6 @@ u64 sme_me_mask __section(".data") = 0; u64 sev_status __section(".data") = 0; u64 sev_check_data __section(".data") = 0; EXPORT_SYMBOL(sme_me_mask); -DEFINE_STATIC_KEY_FALSE(sev_enable_key); -EXPORT_SYMBOL_GPL(sev_enable_key); /* Buffer used for early in-place encryption by BSP, no locking needed */ static char sme_early_buffer[PAGE_SIZE] __initdata __aligned(PAGE_SIZE); @@ -499,14 +497,6 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); - /* - * With SEV, we need to unroll the rep string I/O instructions, - * but SEV-ES supports them through the #VC handler. - */ - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT) && - !cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) - static_branch_enable(&sev_enable_key); - print_mem_encrypt_feature_info(); } diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index a075b70b9a70..efd8205282da 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -61,6 +61,17 @@ enum cc_attr { * Examples include SEV-ES. */ CC_ATTR_GUEST_STATE_ENCRYPT, + + /** + * @CC_ATTR_GUEST_UNROLL_STRING_IO: String I/O is implemented with + * IN/OUT instructions + * + * The platform/OS is running as a guest/virtual machine and uses + * IN/OUT instructions in place of string I/O. + * + * Examples include TDX guest & SEV. + */ + CC_ATTR_GUEST_UNROLL_STRING_IO, }; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -- cgit v1.2.3 From 3f9bb0301d50ce27421eff4b710c2bbe58111a83 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 6 Dec 2021 18:57:47 +0200 Subject: net: dsa: make dp->bridge_num one-based MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I have seen too many bugs already due to the fact that we must encode an invalid dp->bridge_num as a negative value, because the natural tendency is to check that invalid value using (!dp->bridge_num). Latest example can be seen in commit 1bec0f05062c ("net: dsa: fix bridge_num not getting cleared after ports leaving the bridge"). Convert the existing users to assume that dp->bridge_num == 0 is the encoding for invalid, and valid bridge numbers start from 1. Signed-off-by: Vladimir Oltean Reviewed-by: Alvin Šipraga Signed-off-by: Jakub Kicinski --- drivers/net/dsa/mv88e6xxx/chip.c | 12 ++++++------ include/linux/dsa/8021q.h | 6 +++--- include/net/dsa.h | 6 +++--- net/dsa/dsa2.c | 24 ++++++++++++------------ net/dsa/dsa_priv.h | 5 +++-- net/dsa/port.c | 11 ++++++----- net/dsa/tag_8021q.c | 12 +++++++----- net/dsa/tag_dsa.c | 2 +- 8 files changed, 41 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index f00cbf5753b9..de3401b2c86c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1250,10 +1250,10 @@ static u16 mv88e6xxx_port_vlan(struct mv88e6xxx_chip *chip, int dev, int port) /* dev is a virtual bridge */ } else { list_for_each_entry(dp, &dst->ports, list) { - if (dp->bridge_num < 0) + if (!dp->bridge_num) continue; - if (dp->bridge_num + 1 + dst->last_switch != dev) + if (dp->bridge_num + dst->last_switch != dev) continue; br = dp->bridge_dev; @@ -2527,9 +2527,9 @@ static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, * physical switches, so start from beyond that range. */ static int mv88e6xxx_map_virtual_bridge_to_pvt(struct dsa_switch *ds, - int bridge_num) + unsigned int bridge_num) { - u8 dev = bridge_num + ds->dst->last_switch + 1; + u8 dev = bridge_num + ds->dst->last_switch; struct mv88e6xxx_chip *chip = ds->priv; int err; @@ -2542,14 +2542,14 @@ static int mv88e6xxx_map_virtual_bridge_to_pvt(struct dsa_switch *ds, static int mv88e6xxx_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, struct net_device *br, - int bridge_num) + unsigned int bridge_num) { return mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num); } static void mv88e6xxx_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, struct net_device *br, - int bridge_num) + unsigned int bridge_num) { int err; diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 254b165f2b44..0af4371fbebb 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -38,13 +38,13 @@ void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, struct net_device *br, - int bridge_num); + unsigned int bridge_num); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, struct net_device *br, - int bridge_num); + unsigned int bridge_num); -u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); +u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); diff --git a/include/net/dsa.h b/include/net/dsa.h index 8ca9d50cbbc2..a23cfbaa09d6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -257,7 +257,7 @@ struct dsa_port { bool learning; u8 stp_state; struct net_device *bridge_dev; - int bridge_num; + unsigned int bridge_num; struct devlink_port devlink_port; bool devlink_port_setup; struct phylink *pl; @@ -754,11 +754,11 @@ struct dsa_switch_ops { /* Called right after .port_bridge_join() */ int (*port_bridge_tx_fwd_offload)(struct dsa_switch *ds, int port, struct net_device *bridge, - int bridge_num); + unsigned int bridge_num); /* Called right before .port_bridge_leave() */ void (*port_bridge_tx_fwd_unoffload)(struct dsa_switch *ds, int port, struct net_device *bridge, - int bridge_num); + unsigned int bridge_num); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 826957b6442b..9606e56710a5 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -141,23 +141,23 @@ static int dsa_bridge_num_find(const struct net_device *bridge_dev) */ list_for_each_entry(dst, &dsa_tree_list, list) list_for_each_entry(dp, &dst->ports, list) - if (dp->bridge_dev == bridge_dev && - dp->bridge_num != -1) + if (dp->bridge_dev == bridge_dev && dp->bridge_num) return dp->bridge_num; - return -1; + return 0; } -int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) { - int bridge_num = dsa_bridge_num_find(bridge_dev); + unsigned int bridge_num = dsa_bridge_num_find(bridge_dev); - if (bridge_num < 0) { + if (!bridge_num) { /* First port that offloads TX forwarding for this bridge */ - bridge_num = find_first_zero_bit(&dsa_fwd_offloading_bridges, - DSA_MAX_NUM_OFFLOADING_BRIDGES); + bridge_num = find_next_zero_bit(&dsa_fwd_offloading_bridges, + DSA_MAX_NUM_OFFLOADING_BRIDGES, + 1); if (bridge_num >= max) - return -1; + return 0; set_bit(bridge_num, &dsa_fwd_offloading_bridges); } @@ -165,12 +165,13 @@ int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) return bridge_num; } -void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num) +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num) { /* Check if the bridge is still in use, otherwise it is time * to clean it up so we can reuse this bridge_num later. */ - if (dsa_bridge_num_find(bridge_dev) < 0) + if (!dsa_bridge_num_find(bridge_dev)) clear_bit(bridge_num, &dsa_fwd_offloading_bridges); } @@ -1184,7 +1185,6 @@ static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) dp->ds = ds; dp->index = index; - dp->bridge_num = -1; INIT_LIST_HEAD(&dp->list); list_add_tail(&dp->list, &dst->ports); diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3fb2c37c9b88..70c4a5b36a8b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -546,8 +546,9 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, struct net_device *master, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); -int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); -void dsa_bridge_num_put(const struct net_device *bridge_dev, int bridge_num); +unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); +void dsa_bridge_num_put(const struct net_device *bridge_dev, + unsigned int bridge_num); /* tag_8021q.c */ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, diff --git a/net/dsa/port.c b/net/dsa/port.c index 6d5ebe61280b..9a77bd1373e2 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -273,14 +273,14 @@ static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) static void dsa_port_bridge_tx_fwd_unoffload(struct dsa_port *dp, struct net_device *bridge_dev) { - int bridge_num = dp->bridge_num; + unsigned int bridge_num = dp->bridge_num; struct dsa_switch *ds = dp->ds; /* No bridge TX forwarding offload => do nothing */ - if (!ds->ops->port_bridge_tx_fwd_unoffload || dp->bridge_num == -1) + if (!ds->ops->port_bridge_tx_fwd_unoffload || !dp->bridge_num) return; - dp->bridge_num = -1; + dp->bridge_num = 0; dsa_bridge_num_put(bridge_dev, bridge_num); @@ -295,14 +295,15 @@ static bool dsa_port_bridge_tx_fwd_offload(struct dsa_port *dp, struct net_device *bridge_dev) { struct dsa_switch *ds = dp->ds; - int bridge_num, err; + unsigned int bridge_num; + int err; if (!ds->ops->port_bridge_tx_fwd_offload) return false; bridge_num = dsa_bridge_num_get(bridge_dev, ds->num_fwd_offloading_bridges); - if (bridge_num < 0) + if (!bridge_num) return false; dp->bridge_num = bridge_num; diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 72cac2c0af7b..df59f16436a5 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -67,10 +67,12 @@ #define DSA_8021Q_PORT(x) (((x) << DSA_8021Q_PORT_SHIFT) & \ DSA_8021Q_PORT_MASK) -u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num) +u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num) { - /* The VBID value of 0 is reserved for precise TX */ - return DSA_8021Q_DIR_TX | DSA_8021Q_VBID(bridge_num + 1); + /* The VBID value of 0 is reserved for precise TX, but it is also + * reserved/invalid for the bridge_num, so all is well. + */ + return DSA_8021Q_DIR_TX | DSA_8021Q_VBID(bridge_num); } EXPORT_SYMBOL_GPL(dsa_8021q_bridge_tx_fwd_offload_vid); @@ -409,7 +411,7 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, struct net_device *br, - int bridge_num) + unsigned int bridge_num) { u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); @@ -420,7 +422,7 @@ EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_offload); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, struct net_device *br, - int bridge_num) + unsigned int bridge_num) { u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index b3da4b2ea11c..a7d70ae7cc97 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -140,7 +140,7 @@ static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, * packets on behalf of a virtual switch device with an index * past the physical switches. */ - tag_dev = dst->last_switch + 1 + dp->bridge_num; + tag_dev = dst->last_switch + dp->bridge_num; tag_port = 0; } else { cmd = DSA_CMD_FROM_CPU; -- cgit v1.2.3 From d3eed0e57d5d1bcbf1bd60f83a4adfe7d7b8dd9c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Mon, 6 Dec 2021 18:57:56 +0200 Subject: net: dsa: keep the bridge_dev and bridge_num as part of the same structure MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The main desire behind this is to provide coherent bridge information to the fast path without locking. For example, right now we set dp->bridge_dev and dp->bridge_num from separate code paths, it is theoretically possible for a packet transmission to read these two port properties consecutively and find a bridge number which does not correspond with the bridge device. Another desire is to start passing more complex bridge information to dsa_switch_ops functions. For example, with FDB isolation, it is expected that drivers will need to be passed the bridge which requested an FDB/MDB entry to be offloaded, and along with that bridge_dev, the associated bridge_num should be passed too, in case the driver might want to implement an isolation scheme based on that number. We already pass the {bridge_dev, bridge_num} pair to the TX forwarding offload switch API, however we'd like to remove that and squash it into the basic bridge join/leave API. So that means we need to pass this pair to the bridge join/leave API. During dsa_port_bridge_leave, first we unset dp->bridge_dev, then we call the driver's .port_bridge_leave with what used to be our dp->bridge_dev, but provided as an argument. When bridge_dev and bridge_num get folded into a single structure, we need to preserve this behavior in dsa_port_bridge_leave: we need a copy of what used to be in dp->bridge. Switch drivers check bridge membership by comparing dp->bridge_dev with the provided bridge_dev, but now, if we provide the struct dsa_bridge as a pointer, they cannot keep comparing dp->bridge to the provided pointer, since this only points to an on-stack copy. To make this obvious and prevent driver writers from forgetting and doing stupid things, in this new API, the struct dsa_bridge is provided as a full structure (not very large, contains an int and a pointer) instead of a pointer. An explicit comparison function needs to be used to determine bridge membership: dsa_port_offloads_bridge(). Signed-off-by: Vladimir Oltean Reviewed-by: Alvin Šipraga Signed-off-by: Jakub Kicinski --- drivers/net/dsa/b53/b53_common.c | 8 ++-- drivers/net/dsa/b53/b53_priv.h | 4 +- drivers/net/dsa/dsa_loop.c | 8 ++-- drivers/net/dsa/hirschmann/hellcreek.c | 4 +- drivers/net/dsa/lan9303-core.c | 4 +- drivers/net/dsa/lantiq_gswip.c | 14 ++++--- drivers/net/dsa/microchip/ksz_common.c | 4 +- drivers/net/dsa/microchip/ksz_common.h | 4 +- drivers/net/dsa/mt7530.c | 8 ++-- drivers/net/dsa/mv88e6xxx/chip.c | 26 ++++++------- drivers/net/dsa/ocelot/felix.c | 8 ++-- drivers/net/dsa/qca8k.c | 12 +++--- drivers/net/dsa/rtl8366rb.c | 8 ++-- drivers/net/dsa/sja1105/sja1105_main.c | 12 +++--- drivers/net/dsa/xrs700x/xrs700x.c | 10 ++--- include/linux/dsa/8021q.h | 7 ++-- include/net/dsa.h | 34 ++++++++++------- net/dsa/dsa2.c | 43 ++++++++++++++------- net/dsa/dsa_priv.h | 10 +++-- net/dsa/port.c | 70 ++++++++++++++++++---------------- net/dsa/slave.c | 2 +- net/dsa/switch.c | 13 ++++--- net/dsa/tag_8021q.c | 12 +++--- 23 files changed, 177 insertions(+), 148 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d5e78f51f42d..4e41b1a63108 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1860,7 +1860,7 @@ int b53_mdb_del(struct dsa_switch *ds, int port, } EXPORT_SYMBOL(b53_mdb_del); -int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) +int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct b53_device *dev = ds->priv; s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index; @@ -1887,7 +1887,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), &pvlan); b53_for_each_port(dev, i) { - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Add this local port to the remote port VLAN control @@ -1911,7 +1911,7 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *br) } EXPORT_SYMBOL(b53_br_join); -void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) +void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge) { struct b53_device *dev = ds->priv; struct b53_vlan *vl = &dev->vlans[0]; @@ -1923,7 +1923,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_for_each_port(dev, i) { /* Don't touch the remaining ports */ - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; b53_read16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(i), ®); diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 579da74ada64..ee17f8b516ca 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -324,8 +324,8 @@ void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset, void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); int b53_get_sset_count(struct dsa_switch *ds, int port, int sset); void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data); -int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); -void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); +int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge); +void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); int b53_br_flags_pre(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index e638e3eea911..70db3a9aa355 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -167,19 +167,19 @@ static int dsa_loop_phy_write(struct dsa_switch *ds, int port, } static int dsa_loop_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { dev_dbg(ds->dev, "%s: port: %d, bridge: %s\n", - __func__, port, bridge->name); + __func__, port, bridge.dev->name); return 0; } static void dsa_loop_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { dev_dbg(ds->dev, "%s: port: %d, bridge: %s\n", - __func__, port, bridge->name); + __func__, port, bridge.dev->name); } static void dsa_loop_port_stp_state_set(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c index 86839b43011b..c8dc83c69147 100644 --- a/drivers/net/dsa/hirschmann/hellcreek.c +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -674,7 +674,7 @@ static int hellcreek_bridge_flags(struct dsa_switch *ds, int port, } static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct hellcreek *hellcreek = ds->priv; @@ -691,7 +691,7 @@ static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port, } static void hellcreek_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct hellcreek *hellcreek = ds->priv; diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index 1c2bdcde6979..29d909484275 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1103,7 +1103,7 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port) } static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct lan9303 *chip = ds->priv; @@ -1117,7 +1117,7 @@ static int lan9303_port_bridge_join(struct dsa_switch *ds, int port, } static void lan9303_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct lan9303 *chip = ds->priv; diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 6317d0ae42d0..1f59fefc29c1 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1146,16 +1146,17 @@ static int gswip_vlan_remove(struct gswip_priv *priv, } static int gswip_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { + struct net_device *br = bridge.dev; struct gswip_priv *priv = ds->priv; int err; /* When the bridge uses VLAN filtering we have to configure VLAN * specific bridges. No bridge is configured here. */ - if (!br_vlan_enabled(bridge)) { - err = gswip_vlan_add_unaware(priv, bridge, port); + if (!br_vlan_enabled(br)) { + err = gswip_vlan_add_unaware(priv, br, port); if (err) return err; priv->port_vlan_filter &= ~BIT(port); @@ -1166,8 +1167,9 @@ static int gswip_port_bridge_join(struct dsa_switch *ds, int port, } static void gswip_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { + struct net_device *br = bridge.dev; struct gswip_priv *priv = ds->priv; gswip_add_single_port_br(priv, port, true); @@ -1175,8 +1177,8 @@ static void gswip_port_bridge_leave(struct dsa_switch *ds, int port, /* When the bridge uses VLAN filtering we have to configure VLAN * specific bridges. No bridge is configured here. */ - if (!br_vlan_enabled(bridge)) - gswip_vlan_remove(priv, bridge, port, 0, true, false); + if (!br_vlan_enabled(br)) + gswip_vlan_remove(priv, br, port, 0, true, false); } static int gswip_port_vlan_prepare(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index cebcb73cda76..40d6e3f4deb5 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -192,7 +192,7 @@ void ksz_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *buf) EXPORT_SYMBOL_GPL(ksz_get_ethtool_stats); int ksz_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { /* port_stp_state_set() will be called after to put the port in * appropriate state so there is no need to do anything. @@ -203,7 +203,7 @@ int ksz_port_bridge_join(struct dsa_switch *ds, int port, EXPORT_SYMBOL_GPL(ksz_port_bridge_join); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { /* port_stp_state_set() will be called after to put the port in * forwarding state so there is no need to do anything. diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 54b456bc8972..88e5a5d56219 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -155,9 +155,9 @@ void ksz_mac_link_down(struct dsa_switch *ds, int port, unsigned int mode, int ksz_sset_count(struct dsa_switch *ds, int port, int sset); void ksz_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *buf); int ksz_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br); + struct dsa_bridge bridge); void ksz_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br); + struct dsa_bridge bridge); void ksz_port_fast_age(struct dsa_switch *ds, int port); int ksz_port_fdb_dump(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 73c9f79f9e9f..5b74c542b1e6 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1186,7 +1186,7 @@ mt7530_port_bridge_flags(struct dsa_switch *ds, int port, static int mt7530_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; u32 port_bitmap = BIT(MT7530_CPU_PORT); @@ -1204,7 +1204,7 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port, * same bridge. If the port is disabled, port matrix is kept * and not being setup until the port becomes enabled. */ - if (dsa_port_bridge_dev_get(other_dp) != bridge) + if (!dsa_port_offloads_bridge(other_dp, &bridge)) continue; if (priv->ports[other_port].enable) @@ -1303,7 +1303,7 @@ mt7530_port_set_vlan_aware(struct dsa_switch *ds, int port) static void mt7530_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; struct mt7530_priv *priv = ds->priv; @@ -1320,7 +1320,7 @@ mt7530_port_bridge_leave(struct dsa_switch *ds, int port, * in the same bridge. If the port is disabled, port matrix * is kept and not being setup until the port becomes enabled. */ - if (dsa_port_bridge_dev_get(other_dp) != bridge) + if (!dsa_port_offloads_bridge(other_dp, &bridge)) continue; if (priv->ports[other_port].enable) diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 5afc7a1c0dbb..aa5c5d4950d8 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2410,7 +2410,7 @@ static int mv88e6xxx_port_fdb_dump(struct dsa_switch *ds, int port, } static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, - struct net_device *br) + struct dsa_bridge bridge) { struct dsa_switch *ds = chip->ds; struct dsa_switch_tree *dst = ds->dst; @@ -2418,7 +2418,7 @@ static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, int err; list_for_each_entry(dp, &dst->ports, list) { - if (dsa_port_bridge_dev_get(dp) == br) { + if (dsa_port_offloads_bridge(dp, &bridge)) { if (dp->ds == ds) { /* This is a local bridge group member, * remap its Port VLAN Map. @@ -2442,14 +2442,14 @@ static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, } static int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; int err; mv88e6xxx_reg_lock(chip); - err = mv88e6xxx_bridge_map(chip, br); + err = mv88e6xxx_bridge_map(chip, bridge); if (err) goto unlock; @@ -2464,14 +2464,14 @@ unlock: } static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; int err; mv88e6xxx_reg_lock(chip); - if (mv88e6xxx_bridge_map(chip, br) || + if (mv88e6xxx_bridge_map(chip, bridge) || mv88e6xxx_port_vlan_map(chip, port)) dev_err(ds->dev, "failed to remap in-chip Port VLAN\n"); @@ -2486,7 +2486,7 @@ static void mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, int tree_index, int sw_index, - int port, struct net_device *br) + int port, struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; int err; @@ -2503,7 +2503,7 @@ static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, static void mv88e6xxx_crosschip_bridge_leave(struct dsa_switch *ds, int tree_index, int sw_index, - int port, struct net_device *br) + int port, struct dsa_bridge bridge) { struct mv88e6xxx_chip *chip = ds->priv; @@ -2535,19 +2535,17 @@ static int mv88e6xxx_map_virtual_bridge_to_pvt(struct dsa_switch *ds, } static int mv88e6xxx_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - unsigned int bridge_num) + struct dsa_bridge bridge) { - return mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num); + return mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge.num); } static void mv88e6xxx_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - unsigned int bridge_num) + struct dsa_bridge bridge) { int err; - err = mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge_num); + err = mv88e6xxx_map_virtual_bridge_to_pvt(ds, bridge.num); if (err) { dev_err(ds->dev, "failed to remap cross-chip Port VLAN: %pe\n", ERR_PTR(err)); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 57beab3d3ff3..b7e5a5c611dd 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -706,21 +706,21 @@ static int felix_bridge_flags(struct dsa_switch *ds, int port, } static int felix_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct ocelot *ocelot = ds->priv; - ocelot_port_bridge_join(ocelot, port, br); + ocelot_port_bridge_join(ocelot, port, bridge.dev); return 0; } static void felix_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { struct ocelot *ocelot = ds->priv; - ocelot_port_bridge_leave(ocelot, port, br); + ocelot_port_bridge_leave(ocelot, port, bridge.dev); } static int felix_lag_join(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 7053a3510d71..dc983f79f0d6 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1810,8 +1810,8 @@ qca8k_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) QCA8K_PORT_LOOKUP_STATE_MASK, stp_state); } -static int -qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) +static int qca8k_port_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; int port_mask, cpu_port; @@ -1823,7 +1823,7 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) for (i = 0; i < QCA8K_NUM_PORTS; i++) { if (dsa_is_cpu_port(ds, i)) continue; - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Add this port to the portvlan mask of the other ports * in the bridge @@ -1844,8 +1844,8 @@ qca8k_port_bridge_join(struct dsa_switch *ds, int port, struct net_device *br) return ret; } -static void -qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) +static void qca8k_port_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge) { struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv; int cpu_port, i; @@ -1855,7 +1855,7 @@ qca8k_port_bridge_leave(struct dsa_switch *ds, int port, struct net_device *br) for (i = 0; i < QCA8K_NUM_PORTS; i++) { if (dsa_is_cpu_port(ds, i)) continue; - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Remove this port to the portvlan mask of the other ports * in the bridge diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c index b6f277a04989..fac2333a3f5e 100644 --- a/drivers/net/dsa/rtl8366rb.c +++ b/drivers/net/dsa/rtl8366rb.c @@ -1186,7 +1186,7 @@ rtl8366rb_port_disable(struct dsa_switch *ds, int port) static int rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { struct realtek_smi *smi = ds->priv; unsigned int port_bitmap = 0; @@ -1198,7 +1198,7 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, if (i == port) continue; /* Not on this bridge */ - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != bridge) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Join this port to each other port on the bridge */ ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), @@ -1218,7 +1218,7 @@ rtl8366rb_port_bridge_join(struct dsa_switch *ds, int port, static void rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { struct realtek_smi *smi = ds->priv; unsigned int port_bitmap = 0; @@ -1230,7 +1230,7 @@ rtl8366rb_port_bridge_leave(struct dsa_switch *ds, int port, if (i == port) continue; /* Not on this bridge */ - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != bridge) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* Remove this port from any other port on the bridge */ ret = regmap_update_bits(smi->map, RTL8366RB_PORT_ISO(i), diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 5e03eda4c16f..24584fe2e760 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -1980,7 +1980,7 @@ static int sja1105_manage_flood_domains(struct sja1105_private *priv) } static int sja1105_bridge_member(struct dsa_switch *ds, int port, - struct net_device *br, bool member) + struct dsa_bridge bridge, bool member) { struct sja1105_l2_forwarding_entry *l2_fwd; struct sja1105_private *priv = ds->priv; @@ -2005,7 +2005,7 @@ static int sja1105_bridge_member(struct dsa_switch *ds, int port, */ if (i == port) continue; - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != br) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; sja1105_port_allow_traffic(l2_fwd, i, port, member); sja1105_port_allow_traffic(l2_fwd, port, i, member); @@ -2074,15 +2074,15 @@ static void sja1105_bridge_stp_state_set(struct dsa_switch *ds, int port, } static int sja1105_bridge_join(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { - return sja1105_bridge_member(ds, port, br, true); + return sja1105_bridge_member(ds, port, bridge, true); } static void sja1105_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *br) + struct dsa_bridge bridge) { - sja1105_bridge_member(ds, port, br, false); + sja1105_bridge_member(ds, port, bridge, false); } #define BYTES_PER_KBIT (1000LL / 8) diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 7c2b6c32242d..ebb55dfd9c4e 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -501,7 +501,7 @@ static void xrs700x_mac_link_up(struct dsa_switch *ds, int port, } static int xrs700x_bridge_common(struct dsa_switch *ds, int port, - struct net_device *bridge, bool join) + struct dsa_bridge bridge, bool join) { unsigned int i, cpu_mask = 0, mask = 0; struct xrs700x *priv = ds->priv; @@ -513,14 +513,14 @@ static int xrs700x_bridge_common(struct dsa_switch *ds, int port, cpu_mask |= BIT(i); - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) == bridge) + if (dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; mask |= BIT(i); } for (i = 0; i < ds->num_ports; i++) { - if (dsa_port_bridge_dev_get(dsa_to_port(ds, i)) != bridge) + if (!dsa_port_offloads_bridge(dsa_to_port(ds, i), &bridge)) continue; /* 1 = Disable forwarding to the port */ @@ -540,13 +540,13 @@ static int xrs700x_bridge_common(struct dsa_switch *ds, int port, } static int xrs700x_bridge_join(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { return xrs700x_bridge_common(ds, port, bridge, true); } static void xrs700x_bridge_leave(struct dsa_switch *ds, int port, - struct net_device *bridge) + struct dsa_bridge bridge) { xrs700x_bridge_common(ds, port, bridge, false); } diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 0af4371fbebb..939a1beaddf7 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -7,6 +7,7 @@ #include #include +#include struct dsa_switch; struct dsa_port; @@ -37,12 +38,10 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - unsigned int bridge_num); + struct dsa_bridge bridge); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - unsigned int bridge_num); + struct dsa_bridge bridge); u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); diff --git a/include/net/dsa.h b/include/net/dsa.h index 899e13d56fc2..b9789c0cd5e3 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -219,6 +219,11 @@ struct dsa_mall_tc_entry { }; }; +struct dsa_bridge { + struct net_device *dev; + unsigned int num; + refcount_t refcount; +}; struct dsa_port { /* A CPU port is physically connected to a master device. @@ -256,8 +261,7 @@ struct dsa_port { /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ bool learning; u8 stp_state; - struct net_device *bridge_dev; - unsigned int bridge_num; + struct dsa_bridge *bridge; struct devlink_port devlink_port; bool devlink_port_setup; struct phylink *pl; @@ -588,7 +592,7 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { - if (!dp->bridge_dev) + if (!dp->bridge) return NULL; if (dp->lag_dev) @@ -602,12 +606,12 @@ struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) static inline struct net_device * dsa_port_bridge_dev_get(const struct dsa_port *dp) { - return dp->bridge_dev; + return dp->bridge ? dp->bridge->dev : NULL; } static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) { - return dp->bridge_num; + return dp->bridge ? dp->bridge->num : 0; } static inline bool dsa_port_bridge_same(const struct dsa_port *a, @@ -636,6 +640,12 @@ dsa_port_offloads_bridge_dev(struct dsa_port *dp, return dsa_port_bridge_dev_get(dp) == bridge_dev; } +static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, + const struct dsa_bridge *bridge) +{ + return dsa_port_bridge_dev_get(dp) == bridge->dev; +} + /* Returns true if any port of this tree offloads the given net_device */ static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, const struct net_device *dev) @@ -812,17 +822,15 @@ struct dsa_switch_ops { */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, - struct net_device *bridge); + struct dsa_bridge bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port, - struct net_device *bridge); + struct dsa_bridge bridge); /* Called right after .port_bridge_join() */ int (*port_bridge_tx_fwd_offload)(struct dsa_switch *ds, int port, - struct net_device *bridge, - unsigned int bridge_num); + struct dsa_bridge bridge); /* Called right before .port_bridge_leave() */ void (*port_bridge_tx_fwd_unoffload)(struct dsa_switch *ds, int port, - struct net_device *bridge, - unsigned int bridge_num); + struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); @@ -894,10 +902,10 @@ struct dsa_switch_ops { */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct net_device *br); + struct dsa_bridge bridge); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct net_device *br); + struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 4901cdc264ee..8814fa0e44c8 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -129,20 +129,29 @@ void dsa_lag_unmap(struct dsa_switch_tree *dst, struct net_device *lag) } } +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_bridge_dev_get(dp) == br) + return dp->bridge; + + return NULL; +} + static int dsa_bridge_num_find(const struct net_device *bridge_dev) { struct dsa_switch_tree *dst; - struct dsa_port *dp; - /* When preparing the offload for a port, it will have a valid - * dp->bridge_dev pointer but a not yet valid dp->bridge_num. - * However there might be other ports having the same dp->bridge_dev - * and a valid dp->bridge_num, so just ignore this port. - */ - list_for_each_entry(dst, &dsa_tree_list, list) - list_for_each_entry(dp, &dst->ports, list) - if (dp->bridge_dev == bridge_dev && dp->bridge_num) - return dp->bridge_num; + list_for_each_entry(dst, &dsa_tree_list, list) { + struct dsa_bridge *bridge; + + bridge = dsa_tree_bridge_find(dst, bridge_dev); + if (bridge) + return bridge->num; + } return 0; } @@ -151,6 +160,12 @@ unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) { unsigned int bridge_num = dsa_bridge_num_find(bridge_dev); + /* Switches without FDB isolation support don't get unique + * bridge numbering + */ + if (!max) + return 0; + if (!bridge_num) { /* First port that requests FDB isolation or TX forwarding * offload for this bridge @@ -170,11 +185,11 @@ unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max) void dsa_bridge_num_put(const struct net_device *bridge_dev, unsigned int bridge_num) { - /* Check if the bridge is still in use, otherwise it is time - * to clean it up so we can reuse this bridge_num later. + /* Since we refcount bridges, we know that when we call this function + * it is no longer in use, so we can just go ahead and remove it from + * the bit mask. */ - if (!dsa_bridge_num_find(bridge_dev)) - clear_bit(bridge_num, &dsa_fwd_offloading_bridges); + clear_bit(bridge_num, &dsa_fwd_offloading_bridges); } struct dsa_switch *dsa_switch_find(int tree_index, int sw_index) diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index b4f9df4e38b2..da6ff99ba5ed 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -52,7 +52,7 @@ struct dsa_notifier_ageing_time_info { /* DSA_NOTIFIER_BRIDGE_* */ struct dsa_notifier_bridge_info { - struct net_device *br; + struct dsa_bridge bridge; int tree_index; int sw_index; int port; @@ -374,7 +374,7 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) if (dp->type != DSA_PORT_TYPE_USER) continue; - if (!dp->bridge_dev) + if (!dp->bridge) continue; if (dp->stp_state != BR_STATE_LEARNING && @@ -403,7 +403,7 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) /* If the ingress port offloads the bridge, we mark the frame as autonomously * forwarded by hardware, so the software bridge doesn't forward in twice, back * to us, because we already did. However, if we're in fallback mode and we do - * software bridging, we are not offloading it, therefore the dp->bridge_dev + * software bridging, we are not offloading it, therefore the dp->bridge * pointer is not populated, and flooding needs to be done by software (we are * effectively operating in standalone ports mode). */ @@ -411,7 +411,7 @@ static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - skb->offload_fwd_mark = !!(dp->bridge_dev); + skb->offload_fwd_mark = !!(dp->bridge); } /* Helper for removing DSA header tags from packets in the RX path. @@ -508,6 +508,8 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); void dsa_bridge_num_put(const struct net_device *bridge_dev, unsigned int bridge_num); +struct dsa_bridge *dsa_tree_bridge_find(struct dsa_switch_tree *dst, + const struct net_device *br); /* tag_8021q.c */ int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, diff --git a/net/dsa/port.c b/net/dsa/port.c index f6ea41cbcdd5..fbf2d7fc5c91 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -130,7 +130,7 @@ int dsa_port_enable_rt(struct dsa_port *dp, struct phy_device *phy) return err; } - if (!dp->bridge_dev) + if (!dp->bridge) dsa_port_set_state_now(dp, BR_STATE_FORWARDING, false); if (dp->pl) @@ -158,7 +158,7 @@ void dsa_port_disable_rt(struct dsa_port *dp) if (dp->pl) phylink_stop(dp->pl); - if (!dp->bridge_dev) + if (!dp->bridge) dsa_port_set_state_now(dp, BR_STATE_DISABLED, false); if (ds->ops->port_disable) @@ -271,36 +271,32 @@ static void dsa_port_switchdev_unsync_attrs(struct dsa_port *dp) } static void dsa_port_bridge_tx_fwd_unoffload(struct dsa_port *dp, - struct net_device *bridge_dev, - unsigned int bridge_num) + struct dsa_bridge bridge) { struct dsa_switch *ds = dp->ds; /* No bridge TX forwarding offload => do nothing */ - if (!ds->ops->port_bridge_tx_fwd_unoffload || !bridge_num) + if (!ds->ops->port_bridge_tx_fwd_unoffload || !bridge.num) return; /* Notify the chips only once the offload has been deactivated, so * that they can update their configuration accordingly. */ - ds->ops->port_bridge_tx_fwd_unoffload(ds, dp->index, bridge_dev, - bridge_num); + ds->ops->port_bridge_tx_fwd_unoffload(ds, dp->index, bridge); } static bool dsa_port_bridge_tx_fwd_offload(struct dsa_port *dp, - struct net_device *bridge_dev, - unsigned int bridge_num) + struct dsa_bridge bridge) { struct dsa_switch *ds = dp->ds; int err; /* FDB isolation is required for TX forwarding offload */ - if (!ds->ops->port_bridge_tx_fwd_offload || !bridge_num) + if (!ds->ops->port_bridge_tx_fwd_offload || !bridge.num) return false; /* Notify the driver */ - err = ds->ops->port_bridge_tx_fwd_offload(ds, dp->index, bridge_dev, - bridge_num); + err = ds->ops->port_bridge_tx_fwd_offload(ds, dp->index, bridge); return err ? false : true; } @@ -310,21 +306,32 @@ static int dsa_port_bridge_create(struct dsa_port *dp, struct netlink_ext_ack *extack) { struct dsa_switch *ds = dp->ds; - unsigned int bridge_num; + struct dsa_bridge *bridge; - dp->bridge_dev = br; - - if (!ds->max_num_bridges) + bridge = dsa_tree_bridge_find(ds->dst, br); + if (bridge) { + refcount_inc(&bridge->refcount); + dp->bridge = bridge; return 0; + } + + bridge = kzalloc(sizeof(*bridge), GFP_KERNEL); + if (!bridge) + return -ENOMEM; + + refcount_set(&bridge->refcount, 1); + + bridge->dev = br; - bridge_num = dsa_bridge_num_get(br, ds->max_num_bridges); - if (!bridge_num) { + bridge->num = dsa_bridge_num_get(br, ds->max_num_bridges); + if (ds->max_num_bridges && !bridge->num) { NL_SET_ERR_MSG_MOD(extack, "Range of offloadable bridges exceeded"); + kfree(bridge); return -EOPNOTSUPP; } - dp->bridge_num = bridge_num; + dp->bridge = bridge; return 0; } @@ -332,16 +339,17 @@ static int dsa_port_bridge_create(struct dsa_port *dp, static void dsa_port_bridge_destroy(struct dsa_port *dp, const struct net_device *br) { - struct dsa_switch *ds = dp->ds; + struct dsa_bridge *bridge = dp->bridge; + + dp->bridge = NULL; - dp->bridge_dev = NULL; + if (!refcount_dec_and_test(&bridge->refcount)) + return; - if (ds->max_num_bridges) { - int bridge_num = dp->bridge_num; + if (bridge->num) + dsa_bridge_num_put(br, bridge->num); - dp->bridge_num = 0; - dsa_bridge_num_put(br, bridge_num); - } + kfree(bridge); } int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, @@ -351,7 +359,6 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, .tree_index = dp->ds->dst->index, .sw_index = dp->ds->index, .port = dp->index, - .br = br, }; struct net_device *dev = dp->slave; struct net_device *brport_dev; @@ -367,12 +374,12 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, brport_dev = dsa_port_to_bridge_port(dp); + info.bridge = *dp->bridge; err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_JOIN, &info); if (err) goto out_rollback; - tx_fwd_offload = dsa_port_bridge_tx_fwd_offload(dp, br, - dsa_port_bridge_num_get(dp)); + tx_fwd_offload = dsa_port_bridge_tx_fwd_offload(dp, info.bridge); err = switchdev_bridge_port_offload(brport_dev, dev, dp, &dsa_slave_switchdev_notifier, @@ -415,12 +422,11 @@ void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br) void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) { - unsigned int bridge_num = dsa_port_bridge_num_get(dp); struct dsa_notifier_bridge_info info = { .tree_index = dp->ds->dst->index, .sw_index = dp->ds->index, .port = dp->index, - .br = br, + .bridge = *dp->bridge, }; int err; @@ -429,7 +435,7 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) */ dsa_port_bridge_destroy(dp, br); - dsa_port_bridge_tx_fwd_unoffload(dp, br, bridge_num); + dsa_port_bridge_tx_fwd_unoffload(dp, info.bridge); err = dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); if (err) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 4a4c31cce80d..88f7b8686dac 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1564,7 +1564,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) if (!dp->ds->mtu_enforcement_ingress) return; - if (!dp->bridge_dev) + if (!dp->bridge) return; INIT_LIST_HEAD(&hw_port_list); diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 7993192fe769..cd0630dd5417 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -95,7 +95,7 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, if (!ds->ops->port_bridge_join) return -EOPNOTSUPP; - err = ds->ops->port_bridge_join(ds, info->port, info->br); + err = ds->ops->port_bridge_join(ds, info->port, info->bridge); if (err) return err; } @@ -104,7 +104,7 @@ static int dsa_switch_bridge_join(struct dsa_switch *ds, ds->ops->crosschip_bridge_join) { err = ds->ops->crosschip_bridge_join(ds, info->tree_index, info->sw_index, - info->port, info->br); + info->port, info->bridge); if (err) return err; } @@ -124,19 +124,20 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, if (dst->index == info->tree_index && ds->index == info->sw_index && ds->ops->port_bridge_leave) - ds->ops->port_bridge_leave(ds, info->port, info->br); + ds->ops->port_bridge_leave(ds, info->port, info->bridge); if ((dst->index != info->tree_index || ds->index != info->sw_index) && ds->ops->crosschip_bridge_leave) ds->ops->crosschip_bridge_leave(ds, info->tree_index, info->sw_index, info->port, - info->br); + info->bridge); - if (ds->needs_standalone_vlan_filtering && !br_vlan_enabled(info->br)) { + if (ds->needs_standalone_vlan_filtering && + !br_vlan_enabled(info->bridge.dev)) { change_vlan_filtering = true; vlan_filtering = true; } else if (!ds->needs_standalone_vlan_filtering && - br_vlan_enabled(info->br)) { + br_vlan_enabled(info->bridge.dev)) { change_vlan_filtering = true; vlan_filtering = false; } diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index e9d5e566973c..27712a81c967 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -337,7 +337,7 @@ dsa_port_tag_8021q_bridge_match(struct dsa_port *dp, return false; if (dsa_port_is_user(dp)) - return dsa_port_bridge_dev_get(dp) == info->br; + return dsa_port_offloads_bridge(dp, &info->bridge); return false; } @@ -410,10 +410,9 @@ int dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, } int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - unsigned int bridge_num) + struct dsa_bridge bridge) { - u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge.num); return dsa_port_tag_8021q_vlan_add(dsa_to_port(ds, port), tx_vid, true); @@ -421,10 +420,9 @@ int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, EXPORT_SYMBOL_GPL(dsa_tag_8021q_bridge_tx_fwd_offload); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - unsigned int bridge_num) + struct dsa_bridge bridge) { - u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge_num); + u16 tx_vid = dsa_8021q_bridge_tx_fwd_offload_vid(bridge.num); dsa_port_tag_8021q_vlan_del(dsa_to_port(ds, port), tx_vid, true); } -- cgit v1.2.3 From 283e6f5a8166f075eba78da6b867d76cc5d47e77 Mon Sep 17 00:00:00 2001 From: Sergey Ryazanov Date: Tue, 7 Dec 2021 12:21:40 +0300 Subject: net: wwan: make debugfs optional Debugfs interface is optional for the regular modem use. Some distros and users will want to disable this feature for security or kernel size reasons. So add a configuration option that allows to completely disable the debugfs interface of the WWAN devices. A primary considered use case for this option was embedded firmwares. For example, in OpenWrt, you can not completely disable debugfs, as a lot of wireless stuff can only be configured and monitored with the debugfs knobs. At the same time, reducing the size of a kernel and modules is an essential task in the world of embedded software. Disabling the WWAN and IOSM debugfs interfaces allows us to save 50K (x86-64 build) of space for module storage. Not much, but already considerable when you only have 16MB of storage. So it is hard to just disable whole debugfs. Users need some fine grained set of options to control which debugfs interface is important and should be available and which is not. The new configuration symbol is enabled by default and is hidden under the EXPERT option. So a regular user would not be bothered by another one configuration question. While an embedded distro maintainer will be able to a little more reduce the final image size. Signed-off-by: Sergey Ryazanov Reviewed-by: Leon Romanovsky Reviewed-by: Loic Poulain Acked-by: M Chetan Kumar Signed-off-by: Jakub Kicinski --- drivers/net/wwan/Kconfig | 13 ++++++++++++- drivers/net/wwan/iosm/Makefile | 4 +++- drivers/net/wwan/iosm/iosm_ipc_debugfs.h | 5 +++++ drivers/net/wwan/iosm/iosm_ipc_imem.c | 2 +- drivers/net/wwan/iosm/iosm_ipc_imem.h | 4 ++++ drivers/net/wwan/iosm/iosm_ipc_trace.c | 6 ++++-- drivers/net/wwan/iosm/iosm_ipc_trace.h | 20 +++++++++++++++++++- drivers/net/wwan/wwan_core.c | 17 +++++++++++++---- include/linux/wwan.h | 7 +++++++ 9 files changed, 68 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wwan/Kconfig b/drivers/net/wwan/Kconfig index 9f5111a77da9..609fd4a2c865 100644 --- a/drivers/net/wwan/Kconfig +++ b/drivers/net/wwan/Kconfig @@ -16,6 +16,17 @@ config WWAN if WWAN +config WWAN_DEBUGFS + bool "WWAN devices debugfs interface" if EXPERT + depends on DEBUG_FS + default y + help + Enables debugfs infrastructure for the WWAN core and device drivers. + + If this option is selected, then you can find the debug interface + elements for each WWAN device in a directory that is corresponding to + the device name: debugfs/wwan/wwanX. + config WWAN_HWSIM tristate "Simulated WWAN device" help @@ -85,7 +96,7 @@ config IOSM tristate "IOSM Driver for Intel M.2 WWAN Device" depends on INTEL_IOMMU select NET_DEVLINK - select RELAY + select RELAY if WWAN_DEBUGFS help This driver enables Intel M.2 WWAN Device communication. diff --git a/drivers/net/wwan/iosm/Makefile b/drivers/net/wwan/iosm/Makefile index 5091f664af0d..fa8d6afd18e1 100644 --- a/drivers/net/wwan/iosm/Makefile +++ b/drivers/net/wwan/iosm/Makefile @@ -21,7 +21,9 @@ iosm-y = \ iosm_ipc_mux_codec.o \ iosm_ipc_devlink.o \ iosm_ipc_flash.o \ - iosm_ipc_coredump.o \ + iosm_ipc_coredump.o + +iosm-$(CONFIG_WWAN_DEBUGFS) += \ iosm_ipc_debugfs.o \ iosm_ipc_trace.o diff --git a/drivers/net/wwan/iosm/iosm_ipc_debugfs.h b/drivers/net/wwan/iosm/iosm_ipc_debugfs.h index 35788039f13f..8a84bfa2c14a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_debugfs.h +++ b/drivers/net/wwan/iosm/iosm_ipc_debugfs.h @@ -6,7 +6,12 @@ #ifndef IOSM_IPC_DEBUGFS_H #define IOSM_IPC_DEBUGFS_H +#ifdef CONFIG_WWAN_DEBUGFS void ipc_debugfs_init(struct iosm_imem *ipc_imem); void ipc_debugfs_deinit(struct iosm_imem *ipc_imem); +#else +static inline void ipc_debugfs_init(struct iosm_imem *ipc_imem) {} +static inline void ipc_debugfs_deinit(struct iosm_imem *ipc_imem) {} +#endif #endif diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index 25b889922912..2a6ddd7c6c88 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -274,7 +274,7 @@ static void ipc_imem_dl_skb_process(struct iosm_imem *ipc_imem, ipc_imem_sys_devlink_notify_rx(ipc_imem->ipc_devlink, skb); else if (ipc_is_trace_channel(ipc_imem, port_id)) - ipc_trace_port_rx(ipc_imem->trace, skb); + ipc_trace_port_rx(ipc_imem, skb); else wwan_port_rx(ipc_imem->ipc_port[port_id]->iosm_port, skb); diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h index 1b8c7b8959c6..86a1ffe61729 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -351,7 +351,9 @@ struct iosm_imem { struct iosm_mux *mux; struct iosm_cdev *ipc_port[IPC_MEM_MAX_CHANNELS]; struct iosm_pcie *pcie; +#ifdef CONFIG_WWAN_DEBUGFS struct iosm_trace *trace; +#endif struct device *dev; enum ipc_mem_device_ipc_state ipc_requested_state; struct ipc_mem_channel channels[IPC_MEM_MAX_CHANNELS]; @@ -381,7 +383,9 @@ struct iosm_imem { ev_mux_net_transmit_pending:1, reset_det_n:1, pcie_wake_n:1; +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *debugfs_dir; +#endif }; /** diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.c b/drivers/net/wwan/iosm/iosm_ipc_trace.c index 5243ead90b5f..eeecfa3d10c5 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.c +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.c @@ -17,11 +17,13 @@ /** * ipc_trace_port_rx - Receive trace packet from cp and write to relay buffer - * @ipc_trace: Pointer to the ipc trace data-struct + * @ipc_imem: Pointer to iosm_imem structure * @skb: Pointer to struct sk_buff */ -void ipc_trace_port_rx(struct iosm_trace *ipc_trace, struct sk_buff *skb) +void ipc_trace_port_rx(struct iosm_imem *ipc_imem, struct sk_buff *skb) { + struct iosm_trace *ipc_trace = ipc_imem->trace; + if (ipc_trace->ipc_rchan) relay_write(ipc_trace->ipc_rchan, skb->data, skb->len); diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.h b/drivers/net/wwan/iosm/iosm_ipc_trace.h index 419540c91219..5ebe7790585c 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.h +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.h @@ -45,6 +45,8 @@ struct iosm_trace { enum trace_ctrl_mode mode; }; +#ifdef CONFIG_WWAN_DEBUGFS + static inline bool ipc_is_trace_channel(struct iosm_imem *ipc_mem, u16 chl_id) { return ipc_mem->trace && ipc_mem->trace->chl_id == chl_id; @@ -52,5 +54,21 @@ static inline bool ipc_is_trace_channel(struct iosm_imem *ipc_mem, u16 chl_id) struct iosm_trace *ipc_trace_init(struct iosm_imem *ipc_imem); void ipc_trace_deinit(struct iosm_trace *ipc_trace); -void ipc_trace_port_rx(struct iosm_trace *ipc_trace, struct sk_buff *skb); +void ipc_trace_port_rx(struct iosm_imem *ipc_imem, struct sk_buff *skb); + +#else + +static inline bool ipc_is_trace_channel(struct iosm_imem *ipc_mem, u16 chl_id) +{ + return false; +} + +static inline void ipc_trace_port_rx(struct iosm_imem *ipc_imem, + struct sk_buff *skb) +{ + dev_kfree_skb(skb); +} + +#endif + #endif diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c index 5bf62dc35ac7..1508dc2a497b 100644 --- a/drivers/net/wwan/wwan_core.c +++ b/drivers/net/wwan/wwan_core.c @@ -50,7 +50,9 @@ struct wwan_device { atomic_t port_id; const struct wwan_ops *ops; void *ops_ctxt; +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *debugfs_dir; +#endif }; /** @@ -146,6 +148,7 @@ static struct wwan_device *wwan_dev_get_by_name(const char *name) return to_wwan_dev(dev); } +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent) { struct wwan_device *wwandev; @@ -157,6 +160,7 @@ struct dentry *wwan_get_debugfs_dir(struct device *parent) return wwandev->debugfs_dir; } EXPORT_SYMBOL_GPL(wwan_get_debugfs_dir); +#endif /* This function allocates and registers a new WWAN device OR if a WWAN device * already exist for the given parent, it gets a reference and return it. @@ -166,7 +170,6 @@ EXPORT_SYMBOL_GPL(wwan_get_debugfs_dir); static struct wwan_device *wwan_create_dev(struct device *parent) { struct wwan_device *wwandev; - const char *wwandev_name; int err, id; /* The 'find-alloc-register' operation must be protected against @@ -206,9 +209,11 @@ static struct wwan_device *wwan_create_dev(struct device *parent) goto done_unlock; } - wwandev_name = kobject_name(&wwandev->dev.kobj); - wwandev->debugfs_dir = debugfs_create_dir(wwandev_name, - wwan_debugfs_dir); +#ifdef CONFIG_WWAN_DEBUGFS + wwandev->debugfs_dir = + debugfs_create_dir(kobject_name(&wwandev->dev.kobj), + wwan_debugfs_dir); +#endif done_unlock: mutex_unlock(&wwan_register_lock); @@ -240,7 +245,9 @@ static void wwan_remove_dev(struct wwan_device *wwandev) ret = device_for_each_child(&wwandev->dev, NULL, is_wwan_child); if (!ret) { +#ifdef CONFIG_WWAN_DEBUGFS debugfs_remove_recursive(wwandev->debugfs_dir); +#endif device_unregister(&wwandev->dev); } else { put_device(&wwandev->dev); @@ -1140,7 +1147,9 @@ static int __init wwan_init(void) goto destroy; } +#ifdef CONFIG_WWAN_DEBUGFS wwan_debugfs_dir = debugfs_create_dir("wwan", NULL); +#endif return 0; diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 1646aa3e6779..e143c88bf4b0 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -171,6 +171,13 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, void wwan_unregister_ops(struct device *parent); +#ifdef CONFIG_WWAN_DEBUGFS struct dentry *wwan_get_debugfs_dir(struct device *parent); +#else +static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) +{ + return ERR_PTR(-ENODEV); +} +#endif #endif /* __WWAN_H */ -- cgit v1.2.3 From 1197528aaea79ed4909aba695d18fdecc5387a36 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:28 +0100 Subject: genirq/msi: Guard sysfs code No point in building unused code when CONFIG_SYSFS=n. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211206210223.985907940@linutronix.de --- include/linux/msi.h | 10 ++++++++++ kernel/irq/msi.c | 2 ++ 2 files changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index e616f94c7c58..d43b9469c88b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -239,9 +239,19 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); +#ifdef CONFIG_SYSFS const struct attribute_group **msi_populate_sysfs(struct device *dev); void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups); +#else +static inline const struct attribute_group **msi_populate_sysfs(struct device *dev) +{ + return NULL; +} +static inline void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups) +{ +} +#endif /* * The arch hooks to setup up msi irqs. Default functions are implemented diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7f350ae59c5f..a8a0daeb22f5 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -72,6 +72,7 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(get_cached_msi_msg); +#ifdef CONFIG_SYSFS static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -204,6 +205,7 @@ void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_ir kfree(msi_irq_groups); } } +#endif #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN static inline void irq_chip_write_msi_msg(struct irq_data *data, -- cgit v1.2.3 From 1dd2c6a0817fd08f80dee75d7d3bd99a0c4b828d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:29 +0100 Subject: genirq/msi: Remove unused domain callbacks No users and there is no need to grow them. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211126223824.322987915@linutronix.de Link: https://lore.kernel.org/r/20211206210224.041777889@linutronix.de --- include/linux/msi.h | 11 ++++------- kernel/irq/msi.c | 5 ----- 2 files changed, 4 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index d43b9469c88b..4b962f73f84a 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -304,7 +304,6 @@ struct msi_domain_info; * @msi_free: Domain specific function to free a MSI interrupts * @msi_check: Callback for verification of the domain/info/dev data * @msi_prepare: Prepare the allocation of the interrupts in the domain - * @msi_finish: Optional callback to finalize the allocation * @set_desc: Set the msi descriptor for an interrupt * @handle_error: Optional error handler if the allocation fails * @domain_alloc_irqs: Optional function to override the default allocation @@ -312,12 +311,11 @@ struct msi_domain_info; * @domain_free_irqs: Optional function to override the default free * function. * - * @get_hwirq, @msi_init and @msi_free are callbacks used by - * msi_create_irq_domain() and related interfaces + * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying + * irqdomain. * - * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error - * are callbacks used by msi_domain_alloc_irqs() and related - * interfaces which are based on msi_desc. + * @msi_check, @msi_prepare, @handle_error and @set_desc are callbacks used by + * msi_domain_alloc/free_irqs(). * * @domain_alloc_irqs, @domain_free_irqs can be used to override the * default allocation/free functions (__msi_domain_alloc/free_irqs). This @@ -351,7 +349,6 @@ struct msi_domain_ops { int (*msi_prepare)(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg); - void (*msi_finish)(msi_alloc_info_t *arg, int retval); void (*set_desc)(msi_alloc_info_t *arg, struct msi_desc *desc); int (*handle_error)(struct irq_domain *domain, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index a8a0daeb22f5..cd4fa264c7c6 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -562,8 +562,6 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, ret = -ENOSPC; if (ops->handle_error) ret = ops->handle_error(domain, desc, ret); - if (ops->msi_finish) - ops->msi_finish(&arg, ret); return ret; } @@ -573,9 +571,6 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, } } - if (ops->msi_finish) - ops->msi_finish(&arg, 0); - can_reserve = msi_check_reservation_mode(domain, info, dev); /* -- cgit v1.2.3 From 3ba1f050c91d5ce3672dbf3a55dc2451c0b342e2 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:31 +0100 Subject: genirq/msi: Fixup includes Remove the kobject.h include from msi.h as it's not required and add a sysfs.h include to the core code instead. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20211206210224.103502021@linutronix.de --- include/linux/msi.h | 2 +- kernel/irq/msi.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 4b962f73f84a..5c627750f269 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -2,7 +2,7 @@ #ifndef LINUX_MSI_H #define LINUX_MSI_H -#include +#include #include #include diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index cd4fa264c7c6..6718bab1bde3 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include "internals.h" -- cgit v1.2.3 From 9e8688c5f2990dadcf83728cd00a7e8497fc6aa9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:33 +0100 Subject: PCI/MSI: Make pci_msi_domain_write_msg() static There is no point to have this function public as it is set by the PCI core anyway when a PCI/MSI irqdomain is created. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas # PCI Link: https://lore.kernel.org/r/20211206210224.157070464@linutronix.de --- drivers/irqchip/irq-gic-v2m.c | 1 - drivers/irqchip/irq-gic-v3-its-pci-msi.c | 1 - drivers/irqchip/irq-gic-v3-mbi.c | 1 - drivers/pci/msi.c | 2 +- include/linux/msi.h | 1 - 5 files changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c index 9349fc68b81a..62cc78e0da78 100644 --- a/drivers/irqchip/irq-gic-v2m.c +++ b/drivers/irqchip/irq-gic-v2m.c @@ -88,7 +88,6 @@ static struct irq_chip gicv2m_msi_irq_chip = { .irq_mask = gicv2m_mask_msi_irq, .irq_unmask = gicv2m_unmask_msi_irq, .irq_eoi = irq_chip_eoi_parent, - .irq_write_msi_msg = pci_msi_domain_write_msg, }; static struct msi_domain_info gicv2m_msi_domain_info = { diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c index ad2810c017ed..93f77a8196da 100644 --- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c @@ -28,7 +28,6 @@ static struct irq_chip its_msi_irq_chip = { .irq_unmask = its_unmask_msi_irq, .irq_mask = its_mask_msi_irq, .irq_eoi = irq_chip_eoi_parent, - .irq_write_msi_msg = pci_msi_domain_write_msg, }; static int its_pci_msi_vec_count(struct pci_dev *pdev, void *data) diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c index b84c9c2eccdc..a2163d32f17d 100644 --- a/drivers/irqchip/irq-gic-v3-mbi.c +++ b/drivers/irqchip/irq-gic-v3-mbi.c @@ -171,7 +171,6 @@ static struct irq_chip mbi_msi_irq_chip = { .irq_unmask = mbi_unmask_msi_irq, .irq_eoi = irq_chip_eoi_parent, .irq_compose_msi_msg = mbi_compose_msi_msg, - .irq_write_msi_msg = pci_msi_domain_write_msg, }; static struct msi_domain_info mbi_msi_domain_info = { diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 00ed45fea482..afa8ba28904b 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1281,7 +1281,7 @@ EXPORT_SYMBOL_GPL(msi_desc_to_pci_sysdata); * @irq_data: Pointer to interrupt data of the MSI interrupt * @msg: Pointer to the message */ -void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg) +static void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg) { struct msi_desc *desc = irq_data_get_msi_desc(irq_data); diff --git a/include/linux/msi.h b/include/linux/msi.h index 5c627750f269..d7b143a79cb4 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -455,7 +455,6 @@ void *platform_msi_get_host_data(struct irq_domain *domain); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -- cgit v1.2.3 From ade044a3d0f0389e4f916337c505550acc3fd011 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:34 +0100 Subject: PCI/MSI: Remove msi_desc_to_pci_sysdata() Last user is gone long ago. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211206210224.210768199@linutronix.de --- drivers/pci/msi.c | 8 -------- include/linux/msi.h | 5 ----- 2 files changed, 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index afa8ba28904b..e1aecd9b82d9 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1267,14 +1267,6 @@ struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) } EXPORT_SYMBOL(msi_desc_to_pci_dev); -void *msi_desc_to_pci_sysdata(struct msi_desc *desc) -{ - struct pci_dev *dev = msi_desc_to_pci_dev(desc); - - return dev->bus->sysdata; -} -EXPORT_SYMBOL_GPL(msi_desc_to_pci_sysdata); - #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN /** * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space diff --git a/include/linux/msi.h b/include/linux/msi.h index d7b143a79cb4..ac6fec105edc 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -218,13 +218,8 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, for_each_msi_entry((desc), &(pdev)->dev) struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); -void *msi_desc_to_pci_sysdata(struct msi_desc *desc); void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); #else /* CONFIG_PCI_MSI */ -static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc) -{ - return NULL; -} static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) { } -- cgit v1.2.3 From e58f2259b91c02974c20db7b28d39d810a21249b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:39 +0100 Subject: genirq/msi, treewide: Use a named struct for PCI/MSI attributes The unnamed struct sucks and is in the way of further cleanups. Stick the PCI related MSI data into a real data structure and cleanup all users. No functional change. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Reviewed-by: Greg Kroah-Hartman Acked-by: Kalle Valo Link: https://lore.kernel.org/r/20211206210224.374863119@linutronix.de --- arch/powerpc/platforms/cell/axon_msi.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 4 +- arch/powerpc/platforms/pseries/msi.c | 6 +- arch/sparc/kernel/pci_msi.c | 4 +- arch/x86/kernel/apic/msi.c | 2 +- arch/x86/pci/xen.c | 6 +- drivers/net/wireless/ath/ath11k/pci.c | 2 +- drivers/pci/msi.c | 116 +++++++++++++++--------------- drivers/pci/xen-pcifront.c | 2 +- include/linux/msi.h | 84 +++++++++++----------- kernel/irq/msi.c | 4 +- 11 files changed, 115 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c index 82335e364c44..79e21128518c 100644 --- a/arch/powerpc/platforms/cell/axon_msi.c +++ b/arch/powerpc/platforms/cell/axon_msi.c @@ -212,7 +212,7 @@ static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg) entry = first_pci_msi_entry(dev); for (; dn; dn = of_get_next_parent(dn)) { - if (entry->msi_attrib.is_64) { + if (entry->pci.msi_attrib.is_64) { prop = of_get_property(dn, "msi-address-64", &len); if (prop) break; diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 004cd6a96c8a..8913c86009d9 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2154,10 +2154,10 @@ static void pnv_msi_compose_msg(struct irq_data *d, struct msi_msg *msg) int rc; rc = __pnv_pci_ioda_msi_setup(phb, pdev, d->hwirq, - entry->msi_attrib.is_64, msg); + entry->pci.msi_attrib.is_64, msg); if (rc) dev_err(&pdev->dev, "Failed to setup %s-bit MSI #%ld : %d\n", - entry->msi_attrib.is_64 ? "64" : "32", d->hwirq, rc); + entry->pci.msi_attrib.is_64 ? "64" : "32", d->hwirq, rc); } /* diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index 8627362f613e..8e287204eeae 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -332,7 +332,7 @@ static int check_msix_entries(struct pci_dev *pdev) expected = 0; for_each_pci_msi_entry(entry, pdev) { - if (entry->msi_attrib.entry_nr != expected) { + if (entry->pci.msi_attrib.entry_nr != expected) { pr_debug("rtas_msi: bad MSI-X entries.\n"); return -EINVAL; } @@ -449,7 +449,7 @@ static int pseries_msi_ops_prepare(struct irq_domain *domain, struct device *dev { struct pci_dev *pdev = to_pci_dev(dev); struct msi_desc *desc = first_pci_msi_entry(pdev); - int type = desc->msi_attrib.is_msix ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI; + int type = desc->pci.msi_attrib.is_msix ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI; return rtas_prepare_msi_irqs(pdev, nvec, type, arg); } @@ -580,7 +580,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq int hwirq; int i, ret; - hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_attrib.entry_nr); + hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->pci.msi_attrib.entry_nr); if (hwirq < 0) { dev_err(&pdev->dev, "Failed to query HW IRQ: %d\n", hwirq); return hwirq; diff --git a/arch/sparc/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c index fb5899cbfa51..9ed11985768e 100644 --- a/arch/sparc/kernel/pci_msi.c +++ b/arch/sparc/kernel/pci_msi.c @@ -146,13 +146,13 @@ static int sparc64_setup_msi_irq(unsigned int *irq_p, msiqid = pick_msiq(pbm); err = ops->msi_setup(pbm, msiqid, msi, - (entry->msi_attrib.is_64 ? 1 : 0)); + (entry->pci.msi_attrib.is_64 ? 1 : 0)); if (err) goto out_msi_free; pbm->msi_irq_table[msi - pbm->msi_first] = *irq_p; - if (entry->msi_attrib.is_64) { + if (entry->pci.msi_attrib.is_64) { msg.address_hi = pbm->msi64_start >> 32; msg.address_lo = pbm->msi64_start & 0xffffffff; } else { diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index dbacb9ec8843..1656477e4169 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -163,7 +163,7 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, struct msi_desc *desc = first_pci_msi_entry(pdev); init_irq_alloc_info(arg, NULL); - if (desc->msi_attrib.is_msix) { + if (desc->pci.msi_attrib.is_msix) { arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; } else { arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 12da00558631..2dace884d6f7 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -306,7 +306,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return -EINVAL; map_irq.table_base = pci_resource_start(dev, bir); - map_irq.entry_nr = msidesc->msi_attrib.entry_nr; + map_irq.entry_nr = msidesc->pci.msi_attrib.entry_nr; } ret = -EINVAL; @@ -398,7 +398,7 @@ static void xen_pv_teardown_msi_irqs(struct pci_dev *dev) { struct msi_desc *msidesc = first_pci_msi_entry(dev); - if (msidesc->msi_attrib.is_msix) + if (msidesc->pci.msi_attrib.is_msix) xen_pci_frontend_disable_msix(dev); else xen_pci_frontend_disable_msi(dev); @@ -414,7 +414,7 @@ static int xen_msi_domain_alloc_irqs(struct irq_domain *domain, if (WARN_ON_ONCE(!dev_is_pci(dev))) return -EINVAL; - if (first_msi_entry(dev)->msi_attrib.is_msix) + if (first_msi_entry(dev)->pci.msi_attrib.is_msix) type = PCI_CAP_ID_MSIX; else type = PCI_CAP_ID_MSI; diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index 3d353e7c9d5c..d9d00e499174 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -911,7 +911,7 @@ static int ath11k_pci_alloc_msi(struct ath11k_pci *ab_pci) } ab_pci->msi_ep_base_data = msi_desc->msg.data; - if (msi_desc->msi_attrib.is_64) + if (msi_desc->pci.msi_attrib.is_64) set_bit(ATH11K_PCI_FLAG_IS_MSI_64, &ab_pci->flags); ath11k_dbg(ab, ATH11K_DBG_PCI, "msi base data is %d\n", ab_pci->msi_ep_base_data); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index e1aecd9b82d9..b6cd8b337210 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -138,9 +138,9 @@ void __weak arch_restore_msi_irqs(struct pci_dev *dev) static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) { /* Don't shift by >= width of type */ - if (desc->msi_attrib.multi_cap >= 5) + if (desc->pci.msi_attrib.multi_cap >= 5) return 0xffffffff; - return (1 << (1 << desc->msi_attrib.multi_cap)) - 1; + return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; } static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) @@ -148,14 +148,14 @@ static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 s raw_spinlock_t *lock = &desc->dev->msi_lock; unsigned long flags; - if (!desc->msi_attrib.can_mask) + if (!desc->pci.msi_attrib.can_mask) return; raw_spin_lock_irqsave(lock, flags); - desc->msi_mask &= ~clear; - desc->msi_mask |= set; - pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos, - desc->msi_mask); + desc->pci.msi_mask &= ~clear; + desc->pci.msi_mask |= set; + pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->pci.mask_pos, + desc->pci.msi_mask); raw_spin_unlock_irqrestore(lock, flags); } @@ -171,7 +171,7 @@ static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask) static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc) { - return desc->mask_base + desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; + return desc->pci.mask_base + desc->pci.msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; } /* @@ -184,27 +184,27 @@ static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl) { void __iomem *desc_addr = pci_msix_desc_addr(desc); - if (desc->msi_attrib.can_mask) + if (desc->pci.msi_attrib.can_mask) writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } static inline void pci_msix_mask(struct msi_desc *desc) { - desc->msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; - pci_msix_write_vector_ctrl(desc, desc->msix_ctrl); + desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT; + pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); /* Flush write to device */ - readl(desc->mask_base); + readl(desc->pci.mask_base); } static inline void pci_msix_unmask(struct msi_desc *desc) { - desc->msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; - pci_msix_write_vector_ctrl(desc, desc->msix_ctrl); + desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; + pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl); } static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) { - if (desc->msi_attrib.is_msix) + if (desc->pci.msi_attrib.is_msix) pci_msix_mask(desc); else pci_msi_mask(desc, mask); @@ -212,7 +212,7 @@ static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask) static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask) { - if (desc->msi_attrib.is_msix) + if (desc->pci.msi_attrib.is_msix) pci_msix_unmask(desc); else pci_msi_unmask(desc, mask); @@ -256,10 +256,10 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) BUG_ON(dev->current_state != PCI_D0); - if (entry->msi_attrib.is_msix) { + if (entry->pci.msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); - if (WARN_ON_ONCE(entry->msi_attrib.is_virtual)) + if (WARN_ON_ONCE(entry->pci.msi_attrib.is_virtual)) return; msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR); @@ -271,7 +271,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, &msg->address_lo); - if (entry->msi_attrib.is_64) { + if (entry->pci.msi_attrib.is_64) { pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, &msg->address_hi); pci_read_config_word(dev, pos + PCI_MSI_DATA_64, &data); @@ -289,12 +289,12 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) { /* Don't touch the hardware now */ - } else if (entry->msi_attrib.is_msix) { + } else if (entry->pci.msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); - u32 ctrl = entry->msix_ctrl; + u32 ctrl = entry->pci.msix_ctrl; bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT); - if (entry->msi_attrib.is_virtual) + if (entry->pci.msi_attrib.is_virtual) goto skip; /* @@ -323,12 +323,12 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl); msgctl &= ~PCI_MSI_FLAGS_QSIZE; - msgctl |= entry->msi_attrib.multiple << 4; + msgctl |= entry->pci.msi_attrib.multiple << 4; pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl); pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, msg->address_lo); - if (entry->msi_attrib.is_64) { + if (entry->pci.msi_attrib.is_64) { pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, msg->address_hi); pci_write_config_word(dev, pos + PCI_MSI_DATA_64, @@ -376,9 +376,9 @@ static void free_msi_irqs(struct pci_dev *dev) pci_msi_teardown_msi_irqs(dev); list_for_each_entry_safe(entry, tmp, msi_list, list) { - if (entry->msi_attrib.is_msix) { + if (entry->pci.msi_attrib.is_msix) { if (list_is_last(&entry->list, msi_list)) - iounmap(entry->mask_base); + iounmap(entry->pci.mask_base); } list_del(&entry->list); @@ -420,7 +420,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev) pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); pci_msi_update_mask(entry, 0, 0); control &= ~PCI_MSI_FLAGS_QSIZE; - control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; + control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE; pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); } @@ -449,7 +449,7 @@ static void __pci_restore_msix_state(struct pci_dev *dev) arch_restore_msi_irqs(dev); for_each_pci_msi_entry(entry, dev) - pci_msix_write_vector_ctrl(entry, entry->msix_ctrl); + pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } @@ -481,24 +481,24 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING) control |= PCI_MSI_FLAGS_MASKBIT; - entry->msi_attrib.is_msix = 0; - entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); - entry->msi_attrib.is_virtual = 0; - entry->msi_attrib.entry_nr = 0; - entry->msi_attrib.can_mask = !pci_msi_ignore_mask && + entry->pci.msi_attrib.is_msix = 0; + entry->pci.msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); + entry->pci.msi_attrib.is_virtual = 0; + entry->pci.msi_attrib.entry_nr = 0; + entry->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && !!(control & PCI_MSI_FLAGS_MASKBIT); - entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ - entry->msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1; - entry->msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec)); + entry->pci.msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ + entry->pci.msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1; + entry->pci.msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec)); if (control & PCI_MSI_FLAGS_64BIT) - entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64; + entry->pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_64; else - entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32; + entry->pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_32; /* Save the initial mask status */ - if (entry->msi_attrib.can_mask) - pci_read_config_dword(dev, entry->mask_pos, &entry->msi_mask); + if (entry->pci.msi_attrib.can_mask) + pci_read_config_dword(dev, entry->pci.mask_pos, &entry->pci.msi_mask); out: kfree(masks); @@ -630,26 +630,26 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, goto out; } - entry->msi_attrib.is_msix = 1; - entry->msi_attrib.is_64 = 1; + entry->pci.msi_attrib.is_msix = 1; + entry->pci.msi_attrib.is_64 = 1; if (entries) - entry->msi_attrib.entry_nr = entries[i].entry; + entry->pci.msi_attrib.entry_nr = entries[i].entry; else - entry->msi_attrib.entry_nr = i; + entry->pci.msi_attrib.entry_nr = i; - entry->msi_attrib.is_virtual = - entry->msi_attrib.entry_nr >= vec_count; + entry->pci.msi_attrib.is_virtual = + entry->pci.msi_attrib.entry_nr >= vec_count; - entry->msi_attrib.can_mask = !pci_msi_ignore_mask && - !entry->msi_attrib.is_virtual; + entry->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && + !entry->pci.msi_attrib.is_virtual; - entry->msi_attrib.default_irq = dev->irq; - entry->mask_base = base; + entry->pci.msi_attrib.default_irq = dev->irq; + entry->pci.mask_base = base; - if (entry->msi_attrib.can_mask) { + if (entry->pci.msi_attrib.can_mask) { addr = pci_msix_desc_addr(entry); - entry->msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); + entry->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } list_add_tail(&entry->list, dev_to_msi_list(&dev->dev)); @@ -874,7 +874,7 @@ static void pci_msi_shutdown(struct pci_dev *dev) pci_msi_unmask(desc, msi_multi_mask(desc)); /* Restore dev->irq to its default pin-assertion IRQ */ - dev->irq = desc->msi_attrib.default_irq; + dev->irq = desc->pci.msi_attrib.default_irq; pcibios_alloc_irq(dev); } @@ -1203,7 +1203,7 @@ int pci_irq_vector(struct pci_dev *dev, unsigned int nr) struct msi_desc *entry; for_each_pci_msi_entry(entry, dev) { - if (entry->msi_attrib.entry_nr == nr) + if (entry->pci.msi_attrib.entry_nr == nr) return entry->irq; } WARN_ON_ONCE(1); @@ -1242,7 +1242,7 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) struct msi_desc *entry; for_each_pci_msi_entry(entry, dev) { - if (entry->msi_attrib.entry_nr == nr) + if (entry->pci.msi_attrib.entry_nr == nr) return &entry->affinity->mask; } WARN_ON_ONCE(1); @@ -1295,14 +1295,14 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) { struct pci_dev *dev = msi_desc_to_pci_dev(desc); - return (irq_hw_number_t)desc->msi_attrib.entry_nr | + return (irq_hw_number_t)desc->pci.msi_attrib.entry_nr | pci_dev_id(dev) << 11 | (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; } static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) { - return !desc->msi_attrib.is_msix && desc->nvec_used > 1; + return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1; } /** @@ -1326,7 +1326,7 @@ int pci_msi_domain_check_cap(struct irq_domain *domain, if (pci_msi_desc_is_multi_msi(desc) && !(info->flags & MSI_FLAG_MULTI_PCI_MSI)) return 1; - else if (desc->msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX)) + else if (desc->pci.msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX)) return -ENOTSUPP; return 0; diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index d858d25b6cab..699cc9544424 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -263,7 +263,7 @@ static int pci_frontend_enable_msix(struct pci_dev *dev, i = 0; for_each_pci_msi_entry(entry, dev) { - op.msix_entries[i].entry = entry->msi_attrib.entry_nr; + op.msix_entries[i].entry = entry->pci.msi_attrib.entry_nr; /* Vector is useless at this point. */ op.msix_entries[i].vector = -1; i++; diff --git a/include/linux/msi.h b/include/linux/msi.h index ac6fec105edc..7e5c13f4e41b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -68,6 +68,42 @@ static inline void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, struct msi_msg *msg); +/** + * pci_msi_desc - PCI/MSI specific MSI descriptor data + * + * @msi_mask: [PCI MSI] MSI cached mask bits + * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits + * @is_msix: [PCI MSI/X] True if MSI-X + * @multiple: [PCI MSI/X] log2 num of messages allocated + * @multi_cap: [PCI MSI/X] log2 num of messages supported + * @can_mask: [PCI MSI/X] Masking supported? + * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit + * @entry_nr: [PCI MSI/X] Entry which is described by this descriptor + * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq + * @mask_pos: [PCI MSI] Mask register position + * @mask_base: [PCI MSI-X] Mask register base address + */ +struct pci_msi_desc { + union { + u32 msi_mask; + u32 msix_ctrl; + }; + struct { + u8 is_msix : 1; + u8 multiple : 3; + u8 multi_cap : 3; + u8 can_mask : 1; + u8 is_64 : 1; + u8 is_virtual : 1; + u16 entry_nr; + unsigned default_irq; + } msi_attrib; + union { + u8 mask_pos; + void __iomem *mask_base; + }; +}; + /** * platform_msi_desc - Platform device specific msi descriptor data * @msi_priv_data: Pointer to platform private data @@ -107,17 +143,7 @@ struct ti_sci_inta_msi_desc { * address or data changes * @write_msi_msg_data: Data parameter for the callback. * - * @msi_mask: [PCI MSI] MSI cached mask bits - * @msix_ctrl: [PCI MSI-X] MSI-X cached per vector control bits - * @is_msix: [PCI MSI/X] True if MSI-X - * @multiple: [PCI MSI/X] log2 num of messages allocated - * @multi_cap: [PCI MSI/X] log2 num of messages supported - * @maskbit: [PCI MSI/X] Mask-Pending bit supported? - * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit - * @entry_nr: [PCI MSI/X] Entry which is described by this descriptor - * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq - * @mask_pos: [PCI MSI] Mask register position - * @mask_base: [PCI MSI-X] Mask register base address + * @pci: [PCI] PCI speficic msi descriptor data * @platform: [platform] Platform device specific msi descriptor data * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data * @inta: [INTA] TISCI based INTA specific msi descriptor data @@ -138,38 +164,10 @@ struct msi_desc { void *write_msi_msg_data; union { - /* PCI MSI/X specific data */ - struct { - union { - u32 msi_mask; - u32 msix_ctrl; - }; - struct { - u8 is_msix : 1; - u8 multiple : 3; - u8 multi_cap : 3; - u8 can_mask : 1; - u8 is_64 : 1; - u8 is_virtual : 1; - u16 entry_nr; - unsigned default_irq; - } msi_attrib; - union { - u8 mask_pos; - void __iomem *mask_base; - }; - }; - - /* - * Non PCI variants add their data structure here. New - * entries need to use a named structure. We want - * proper name spaces for this. The PCI part is - * anonymous for now as it would require an immediate - * tree wide cleanup. - */ - struct platform_msi_desc platform; - struct fsl_mc_msi_desc fsl_mc; - struct ti_sci_inta_msi_desc inta; + struct pci_msi_desc pci; + struct platform_msi_desc platform; + struct fsl_mc_msi_desc fsl_mc; + struct ti_sci_inta_msi_desc inta; }; }; diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 6718bab1bde3..7d78d8aff076 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -91,7 +91,7 @@ static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, return -ENODEV; if (dev_is_pci(dev)) - is_msix = entry->msi_attrib.is_msix; + is_msix = entry->pci.msi_attrib.is_msix; return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi"); } @@ -535,7 +535,7 @@ static bool msi_check_reservation_mode(struct irq_domain *domain, * masking and MSI does so when the can_mask attribute is set. */ desc = first_msi_entry(dev); - return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask; + return desc->pci.msi_attrib.is_msix || desc->pci.msi_attrib.can_mask; } int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, -- cgit v1.2.3 From ae72f3156729541581f526b85883ca53a20df2fa Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:42 +0100 Subject: PCI/MSI: Make arch_restore_msi_irqs() less horrible. Make arch_restore_msi_irqs() return a boolean which indicates whether the core code should restore the MSI message or not. Get rid of the indirection in x86. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas # PCI Link: https://lore.kernel.org/r/20211206210224.485668098@linutronix.de --- arch/s390/pci/pci_irq.c | 4 +-- arch/x86/include/asm/x86_init.h | 6 ---- arch/x86/include/asm/xen/hypervisor.h | 8 ++++++ arch/x86/kernel/apic/msi.c | 6 ++++ arch/x86/kernel/x86_init.c | 12 -------- arch/x86/pci/xen.c | 13 +++++---- drivers/pci/msi.c | 54 ++++++++++++----------------------- include/linux/msi.h | 7 ++--- 8 files changed, 45 insertions(+), 65 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 954bb7a83124..2beb8a082e6f 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -387,13 +387,13 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs); } -void arch_restore_msi_irqs(struct pci_dev *pdev) +bool arch_restore_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); if (!zdev->irqs_registered) zpci_set_irq(zdev); - default_restore_msi_irqs(pdev); + return true; } static struct airq_struct zpci_airq = { diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 5c69f7eb5d47..22b7412c08f6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -289,12 +289,6 @@ struct x86_platform_ops { struct x86_hyper_runtime hyper; }; -struct pci_dev; - -struct x86_msi_ops { - void (*restore_msi_irqs)(struct pci_dev *dev); -}; - struct x86_apic_ops { unsigned int (*io_apic_read) (unsigned int apic, unsigned int reg); void (*restore)(void); diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 5adab895127e..677f84d0039f 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -57,6 +57,14 @@ static inline bool __init xen_x2apic_para_available(void) } #endif +struct pci_dev; + +#ifdef CONFIG_XEN_DOM0 +bool xen_initdom_restore_msi(struct pci_dev *dev); +#else +static inline bool xen_initdom_restore_msi(struct pci_dev *dev) { return true; } +#endif + #ifdef CONFIG_HOTPLUG_CPU void xen_arch_register_cpu(int num); void xen_arch_unregister_cpu(int num); diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 1656477e4169..b270b70f41c6 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -19,6 +19,7 @@ #include #include #include +#include struct irq_domain *x86_pci_msi_default_domain __ro_after_init; @@ -345,3 +346,8 @@ void dmar_free_hwirq(int irq) irq_domain_free_irqs(irq, 1); } #endif + +bool arch_restore_msi_irqs(struct pci_dev *dev) +{ + return xen_initdom_restore_msi(dev); +} diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 8b395821cb8d..7d20c1d34a3c 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -145,18 +145,6 @@ struct x86_platform_ops x86_platform __ro_after_init = { EXPORT_SYMBOL_GPL(x86_platform); -#if defined(CONFIG_PCI_MSI) -struct x86_msi_ops x86_msi __ro_after_init = { - .restore_msi_irqs = default_restore_msi_irqs, -}; - -/* MSI arch specific hooks */ -void arch_restore_msi_irqs(struct pci_dev *dev) -{ - x86_msi.restore_msi_irqs(dev); -} -#endif - struct x86_apic_ops x86_apic_ops __ro_after_init = { .io_apic_read = native_io_apic_read, .restore = native_restore_boot_irq_mode, diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 2dace884d6f7..a63d30a52879 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -351,10 +351,13 @@ out: return ret; } -static void xen_initdom_restore_msi_irqs(struct pci_dev *dev) +bool xen_initdom_restore_msi(struct pci_dev *dev) { int ret = 0; + if (!xen_initial_domain()) + return true; + if (pci_seg_supported) { struct physdev_pci_device restore_ext; @@ -375,10 +378,10 @@ static void xen_initdom_restore_msi_irqs(struct pci_dev *dev) ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore); WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret); } + return false; } #else /* CONFIG_XEN_PV_DOM0 */ #define xen_initdom_setup_msi_irqs NULL -#define xen_initdom_restore_msi_irqs NULL #endif /* !CONFIG_XEN_PV_DOM0 */ static void xen_teardown_msi_irqs(struct pci_dev *dev) @@ -466,12 +469,10 @@ static __init struct irq_domain *xen_create_pci_msi_domain(void) static __init void xen_setup_pci_msi(void) { if (xen_pv_domain()) { - if (xen_initial_domain()) { + if (xen_initial_domain()) xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs; - x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs; - } else { + else xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs; - } xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs; pci_msi_ignore_mask = 1; } else if (xen_hvm_domain()) { diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index b6cd8b337210..8260b06ab583 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -106,29 +106,6 @@ void __weak arch_teardown_msi_irqs(struct pci_dev *dev) } #endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ -static void default_restore_msi_irq(struct pci_dev *dev, int irq) -{ - struct msi_desc *entry; - - entry = NULL; - if (dev->msix_enabled) { - for_each_pci_msi_entry(entry, dev) { - if (irq == entry->irq) - break; - } - } else if (dev->msi_enabled) { - entry = irq_get_msi_desc(irq); - } - - if (entry) - __pci_write_msi_msg(entry, &entry->msg); -} - -void __weak arch_restore_msi_irqs(struct pci_dev *dev) -{ - return default_restore_msi_irqs(dev); -} - /* * PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to * mask all MSI interrupts by clearing the MSI enable bit does not work @@ -242,14 +219,6 @@ void pci_msi_unmask_irq(struct irq_data *data) } EXPORT_SYMBOL_GPL(pci_msi_unmask_irq); -void default_restore_msi_irqs(struct pci_dev *dev) -{ - struct msi_desc *entry; - - for_each_pci_msi_entry(entry, dev) - default_restore_msi_irq(dev, entry->irq); -} - void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { struct pci_dev *dev = msi_desc_to_pci_dev(entry); @@ -403,10 +372,19 @@ static void pci_msi_set_enable(struct pci_dev *dev, int enable) pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control); } +/* + * Architecture override returns true when the PCI MSI message should be + * written by the generic restore function. + */ +bool __weak arch_restore_msi_irqs(struct pci_dev *dev) +{ + return true; +} + static void __pci_restore_msi_state(struct pci_dev *dev) { - u16 control; struct msi_desc *entry; + u16 control; if (!dev->msi_enabled) return; @@ -415,7 +393,8 @@ static void __pci_restore_msi_state(struct pci_dev *dev) pci_intx_for_msi(dev, 0); pci_msi_set_enable(dev, 0); - arch_restore_msi_irqs(dev); + if (arch_restore_msi_irqs(dev)) + __pci_write_msi_msg(entry, &entry->msg); pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); pci_msi_update_mask(entry, 0, 0); @@ -437,6 +416,7 @@ static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) static void __pci_restore_msix_state(struct pci_dev *dev) { struct msi_desc *entry; + bool write_msg; if (!dev->msix_enabled) return; @@ -447,9 +427,13 @@ static void __pci_restore_msix_state(struct pci_dev *dev) pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL); - arch_restore_msi_irqs(dev); - for_each_pci_msi_entry(entry, dev) + write_msg = arch_restore_msi_irqs(dev); + + for_each_pci_msi_entry(entry, dev) { + if (write_msg) + __pci_write_msi_msg(entry, &entry->msg); pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); + } pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } diff --git a/include/linux/msi.h b/include/linux/msi.h index 7e5c13f4e41b..673899fc24f6 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -273,11 +273,10 @@ static inline void arch_teardown_msi_irqs(struct pci_dev *dev) #endif /* - * The restore hooks are still available as they are useful even - * for fully irq domain based setups. Courtesy to XEN/X86. + * The restore hook is still available even for fully irq domain based + * setups. Courtesy to XEN/X86. */ -void arch_restore_msi_irqs(struct pci_dev *dev); -void default_restore_msi_irqs(struct pci_dev *dev); +bool arch_restore_msi_irqs(struct pci_dev *dev); #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN -- cgit v1.2.3 From aa423ac4221abdfb8588751e7838ca5f42f56db3 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:52 +0100 Subject: PCI/MSI: Split out irqdomain code Move the irqdomain specific code into its own file. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Reviewed-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211206210224.817754783@linutronix.de --- drivers/pci/msi/Makefile | 1 + drivers/pci/msi/irqdomain.c | 279 ++++++++++++++++++++++++++++++++++++++ drivers/pci/msi/legacy.c | 13 +- drivers/pci/msi/msi.c | 319 ++------------------------------------------ drivers/pci/msi/msi.h | 39 ++++++ include/linux/msi.h | 11 -- 6 files changed, 340 insertions(+), 322 deletions(-) create mode 100644 drivers/pci/msi/irqdomain.c create mode 100644 drivers/pci/msi/msi.h (limited to 'include/linux') diff --git a/drivers/pci/msi/Makefile b/drivers/pci/msi/Makefile index 64bf14737bde..93ef7b9e404d 100644 --- a/drivers/pci/msi/Makefile +++ b/drivers/pci/msi/Makefile @@ -3,4 +3,5 @@ # Makefile for the PCI/MSI obj-$(CONFIG_PCI) += pcidev_msi.o obj-$(CONFIG_PCI_MSI) += msi.o +obj-$(CONFIG_PCI_MSI_IRQ_DOMAIN) += irqdomain.o obj-$(CONFIG_PCI_MSI_ARCH_FALLBACKS) += legacy.o diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c new file mode 100644 index 000000000000..123450e715cb --- /dev/null +++ b/drivers/pci/msi/irqdomain.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI Message Signaled Interrupt (MSI) - irqdomain support + */ +#include +#include +#include + +#include "msi.h" + +int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + struct irq_domain *domain; + + domain = dev_get_msi_domain(&dev->dev); + if (domain && irq_domain_is_hierarchy(domain)) + return msi_domain_alloc_irqs(domain, &dev->dev, nvec); + + return pci_msi_legacy_setup_msi_irqs(dev, nvec, type); +} + +void pci_msi_teardown_msi_irqs(struct pci_dev *dev) +{ + struct irq_domain *domain; + + domain = dev_get_msi_domain(&dev->dev); + if (domain && irq_domain_is_hierarchy(domain)) + msi_domain_free_irqs(domain, &dev->dev); + else + pci_msi_legacy_teardown_msi_irqs(dev); +} + +/** + * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space + * @irq_data: Pointer to interrupt data of the MSI interrupt + * @msg: Pointer to the message + */ +static void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg) +{ + struct msi_desc *desc = irq_data_get_msi_desc(irq_data); + + /* + * For MSI-X desc->irq is always equal to irq_data->irq. For + * MSI only the first interrupt of MULTI MSI passes the test. + */ + if (desc->irq == irq_data->irq) + __pci_write_msi_msg(desc, msg); +} + +/** + * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source + * @desc: Pointer to the MSI descriptor + * + * The ID number is only used within the irqdomain. + */ +static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) +{ + struct pci_dev *dev = msi_desc_to_pci_dev(desc); + + return (irq_hw_number_t)desc->pci.msi_attrib.entry_nr | + pci_dev_id(dev) << 11 | + (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; +} + +static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) +{ + return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1; +} + +/** + * pci_msi_domain_check_cap - Verify that @domain supports the capabilities + * for @dev + * @domain: The interrupt domain to check + * @info: The domain info for verification + * @dev: The device to check + * + * Returns: + * 0 if the functionality is supported + * 1 if Multi MSI is requested, but the domain does not support it + * -ENOTSUPP otherwise + */ +int pci_msi_domain_check_cap(struct irq_domain *domain, + struct msi_domain_info *info, struct device *dev) +{ + struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev)); + + /* Special handling to support __pci_enable_msi_range() */ + if (pci_msi_desc_is_multi_msi(desc) && + !(info->flags & MSI_FLAG_MULTI_PCI_MSI)) + return 1; + else if (desc->pci.msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX)) + return -ENOTSUPP; + + return 0; +} + +static int pci_msi_domain_handle_error(struct irq_domain *domain, + struct msi_desc *desc, int error) +{ + /* Special handling to support __pci_enable_msi_range() */ + if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC) + return 1; + + return error; +} + +static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, + struct msi_desc *desc) +{ + arg->desc = desc; + arg->hwirq = pci_msi_domain_calc_hwirq(desc); +} + +static struct msi_domain_ops pci_msi_domain_ops_default = { + .set_desc = pci_msi_domain_set_desc, + .msi_check = pci_msi_domain_check_cap, + .handle_error = pci_msi_domain_handle_error, +}; + +static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) +{ + struct msi_domain_ops *ops = info->ops; + + if (ops == NULL) { + info->ops = &pci_msi_domain_ops_default; + } else { + if (ops->set_desc == NULL) + ops->set_desc = pci_msi_domain_set_desc; + if (ops->msi_check == NULL) + ops->msi_check = pci_msi_domain_check_cap; + if (ops->handle_error == NULL) + ops->handle_error = pci_msi_domain_handle_error; + } +} + +static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + BUG_ON(!chip); + if (!chip->irq_write_msi_msg) + chip->irq_write_msi_msg = pci_msi_domain_write_msg; + if (!chip->irq_mask) + chip->irq_mask = pci_msi_mask_irq; + if (!chip->irq_unmask) + chip->irq_unmask = pci_msi_unmask_irq; +} + +/** + * pci_msi_create_irq_domain - Create a MSI interrupt domain + * @fwnode: Optional fwnode of the interrupt controller + * @info: MSI domain info + * @parent: Parent irq domain + * + * Updates the domain and chip ops and creates a MSI interrupt domain. + * + * Returns: + * A domain pointer or NULL in case of failure. + */ +struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, + struct msi_domain_info *info, + struct irq_domain *parent) +{ + struct irq_domain *domain; + + if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE)) + info->flags &= ~MSI_FLAG_LEVEL_CAPABLE; + + if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) + pci_msi_domain_update_dom_ops(info); + if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) + pci_msi_domain_update_chip_ops(info); + + info->flags |= MSI_FLAG_ACTIVATE_EARLY; + if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) + info->flags |= MSI_FLAG_MUST_REACTIVATE; + + /* PCI-MSI is oneshot-safe */ + info->chip->flags |= IRQCHIP_ONESHOT_SAFE; + + domain = msi_create_irq_domain(fwnode, info, parent); + if (!domain) + return NULL; + + irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI); + return domain; +} +EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); + +/* + * Users of the generic MSI infrastructure expect a device to have a single ID, + * so with DMA aliases we have to pick the least-worst compromise. Devices with + * DMA phantom functions tend to still emit MSIs from the real function number, + * so we ignore those and only consider topological aliases where either the + * alias device or RID appears on a different bus number. We also make the + * reasonable assumption that bridges are walked in an upstream direction (so + * the last one seen wins), and the much braver assumption that the most likely + * case is that of PCI->PCIe so we should always use the alias RID. This echoes + * the logic from intel_irq_remapping's set_msi_sid(), which presumably works + * well enough in practice; in the face of the horrible PCIe<->PCI-X conditions + * for taking ownership all we can really do is close our eyes and hope... + */ +static int get_msi_id_cb(struct pci_dev *pdev, u16 alias, void *data) +{ + u32 *pa = data; + u8 bus = PCI_BUS_NUM(*pa); + + if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus) + *pa = alias; + + return 0; +} + +/** + * pci_msi_domain_get_msi_rid - Get the MSI requester id (RID) + * @domain: The interrupt domain + * @pdev: The PCI device. + * + * The RID for a device is formed from the alias, with a firmware + * supplied mapping applied + * + * Returns: The RID. + */ +u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev) +{ + struct device_node *of_node; + u32 rid = pci_dev_id(pdev); + + pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); + + of_node = irq_domain_get_of_node(domain); + rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) : + iort_msi_map_id(&pdev->dev, rid); + + return rid; +} + +/** + * pci_msi_get_device_domain - Get the MSI domain for a given PCI device + * @pdev: The PCI device + * + * Use the firmware data to find a device-specific MSI domain + * (i.e. not one that is set as a default). + * + * Returns: The corresponding MSI domain or NULL if none has been found. + */ +struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) +{ + struct irq_domain *dom; + u32 rid = pci_dev_id(pdev); + + pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); + dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI); + if (!dom) + dom = iort_get_device_domain(&pdev->dev, rid, + DOMAIN_BUS_PCI_MSI); + return dom; +} + +/** + * pci_dev_has_special_msi_domain - Check whether the device is handled by + * a non-standard PCI-MSI domain + * @pdev: The PCI device to check. + * + * Returns: True if the device irqdomain or the bus irqdomain is + * non-standard PCI/MSI. + */ +bool pci_dev_has_special_msi_domain(struct pci_dev *pdev) +{ + struct irq_domain *dom = dev_get_msi_domain(&pdev->dev); + + if (!dom) + dom = dev_get_msi_domain(&pdev->bus->dev); + + if (!dom) + return true; + + return dom->bus_token != DOMAIN_BUS_PCI_MSI; +} diff --git a/drivers/pci/msi/legacy.c b/drivers/pci/msi/legacy.c index 4c76c59f563e..023de20ee3a7 100644 --- a/drivers/pci/msi/legacy.c +++ b/drivers/pci/msi/legacy.c @@ -4,8 +4,7 @@ * * Legacy architecture specific setup and teardown mechanism. */ -#include -#include +#include "msi.h" /* Arch hooks */ int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc) @@ -50,3 +49,13 @@ void __weak arch_teardown_msi_irqs(struct pci_dev *dev) } } } + +int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + return arch_setup_msi_irqs(dev, nvec, type); +} + +void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) +{ + arch_teardown_msi_irqs(dev); +} diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 78f10ce6e0cb..8926a6c8b345 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -6,64 +6,16 @@ * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com) * Copyright (C) 2016 Christoph Hellwig. */ - -#include #include #include #include -#include -#include -#include -#include #include "../pci.h" +#include "msi.h" static int pci_msi_enable = 1; int pci_msi_ignore_mask; -#define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) - -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - struct irq_domain *domain; - - domain = dev_get_msi_domain(&dev->dev); - if (domain && irq_domain_is_hierarchy(domain)) - return msi_domain_alloc_irqs(domain, &dev->dev, nvec); - - return arch_setup_msi_irqs(dev, nvec, type); -} - -static void pci_msi_teardown_msi_irqs(struct pci_dev *dev) -{ - struct irq_domain *domain; - - domain = dev_get_msi_domain(&dev->dev); - if (domain && irq_domain_is_hierarchy(domain)) - msi_domain_free_irqs(domain, &dev->dev); - else - arch_teardown_msi_irqs(dev); -} -#else -#define pci_msi_setup_msi_irqs arch_setup_msi_irqs -#define pci_msi_teardown_msi_irqs arch_teardown_msi_irqs -#endif - -/* - * PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to - * mask all MSI interrupts by clearing the MSI enable bit does not work - * reliably as devices without an INTx disable bit will then generate a - * level IRQ which will never be cleared. - */ -static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) -{ - /* Don't shift by >= width of type */ - if (desc->pci.msi_attrib.multi_cap >= 5) - return 0xffffffff; - return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; -} - static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) { raw_spinlock_t *lock = &desc->dev->msi_lock; @@ -903,23 +855,6 @@ void pci_disable_msix(struct pci_dev *dev) } EXPORT_SYMBOL(pci_disable_msix); -void pci_no_msi(void) -{ - pci_msi_enable = 0; -} - -/** - * pci_msi_enabled - is MSI enabled? - * - * Returns true if MSI has not been disabled by the command-line option - * pci=nomsi. - **/ -int pci_msi_enabled(void) -{ - return pci_msi_enable; -} -EXPORT_SYMBOL(pci_msi_enabled); - static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd) { @@ -1195,253 +1130,19 @@ struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) } EXPORT_SYMBOL(msi_desc_to_pci_dev); -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN -/** - * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space - * @irq_data: Pointer to interrupt data of the MSI interrupt - * @msg: Pointer to the message - */ -static void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg) -{ - struct msi_desc *desc = irq_data_get_msi_desc(irq_data); - - /* - * For MSI-X desc->irq is always equal to irq_data->irq. For - * MSI only the first interrupt of MULTI MSI passes the test. - */ - if (desc->irq == irq_data->irq) - __pci_write_msi_msg(desc, msg); -} - -/** - * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source - * @desc: Pointer to the MSI descriptor - * - * The ID number is only used within the irqdomain. - */ -static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) -{ - struct pci_dev *dev = msi_desc_to_pci_dev(desc); - - return (irq_hw_number_t)desc->pci.msi_attrib.entry_nr | - pci_dev_id(dev) << 11 | - (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; -} - -static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) -{ - return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1; -} - -/** - * pci_msi_domain_check_cap - Verify that @domain supports the capabilities - * for @dev - * @domain: The interrupt domain to check - * @info: The domain info for verification - * @dev: The device to check - * - * Returns: - * 0 if the functionality is supported - * 1 if Multi MSI is requested, but the domain does not support it - * -ENOTSUPP otherwise - */ -int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, struct device *dev) -{ - struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev)); - - /* Special handling to support __pci_enable_msi_range() */ - if (pci_msi_desc_is_multi_msi(desc) && - !(info->flags & MSI_FLAG_MULTI_PCI_MSI)) - return 1; - else if (desc->pci.msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX)) - return -ENOTSUPP; - - return 0; -} - -static int pci_msi_domain_handle_error(struct irq_domain *domain, - struct msi_desc *desc, int error) -{ - /* Special handling to support __pci_enable_msi_range() */ - if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC) - return 1; - - return error; -} - -static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, - struct msi_desc *desc) -{ - arg->desc = desc; - arg->hwirq = pci_msi_domain_calc_hwirq(desc); -} - -static struct msi_domain_ops pci_msi_domain_ops_default = { - .set_desc = pci_msi_domain_set_desc, - .msi_check = pci_msi_domain_check_cap, - .handle_error = pci_msi_domain_handle_error, -}; - -static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) -{ - struct msi_domain_ops *ops = info->ops; - - if (ops == NULL) { - info->ops = &pci_msi_domain_ops_default; - } else { - if (ops->set_desc == NULL) - ops->set_desc = pci_msi_domain_set_desc; - if (ops->msi_check == NULL) - ops->msi_check = pci_msi_domain_check_cap; - if (ops->handle_error == NULL) - ops->handle_error = pci_msi_domain_handle_error; - } -} - -static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info) -{ - struct irq_chip *chip = info->chip; - - BUG_ON(!chip); - if (!chip->irq_write_msi_msg) - chip->irq_write_msi_msg = pci_msi_domain_write_msg; - if (!chip->irq_mask) - chip->irq_mask = pci_msi_mask_irq; - if (!chip->irq_unmask) - chip->irq_unmask = pci_msi_unmask_irq; -} - -/** - * pci_msi_create_irq_domain - Create a MSI interrupt domain - * @fwnode: Optional fwnode of the interrupt controller - * @info: MSI domain info - * @parent: Parent irq domain - * - * Updates the domain and chip ops and creates a MSI interrupt domain. - * - * Returns: - * A domain pointer or NULL in case of failure. - */ -struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, - struct irq_domain *parent) -{ - struct irq_domain *domain; - - if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE)) - info->flags &= ~MSI_FLAG_LEVEL_CAPABLE; - - if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) - pci_msi_domain_update_dom_ops(info); - if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) - pci_msi_domain_update_chip_ops(info); - - info->flags |= MSI_FLAG_ACTIVATE_EARLY; - if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) - info->flags |= MSI_FLAG_MUST_REACTIVATE; - - /* PCI-MSI is oneshot-safe */ - info->chip->flags |= IRQCHIP_ONESHOT_SAFE; - - domain = msi_create_irq_domain(fwnode, info, parent); - if (!domain) - return NULL; - - irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI); - return domain; -} -EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); - -/* - * Users of the generic MSI infrastructure expect a device to have a single ID, - * so with DMA aliases we have to pick the least-worst compromise. Devices with - * DMA phantom functions tend to still emit MSIs from the real function number, - * so we ignore those and only consider topological aliases where either the - * alias device or RID appears on a different bus number. We also make the - * reasonable assumption that bridges are walked in an upstream direction (so - * the last one seen wins), and the much braver assumption that the most likely - * case is that of PCI->PCIe so we should always use the alias RID. This echoes - * the logic from intel_irq_remapping's set_msi_sid(), which presumably works - * well enough in practice; in the face of the horrible PCIe<->PCI-X conditions - * for taking ownership all we can really do is close our eyes and hope... - */ -static int get_msi_id_cb(struct pci_dev *pdev, u16 alias, void *data) -{ - u32 *pa = data; - u8 bus = PCI_BUS_NUM(*pa); - - if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus) - *pa = alias; - - return 0; -} - -/** - * pci_msi_domain_get_msi_rid - Get the MSI requester id (RID) - * @domain: The interrupt domain - * @pdev: The PCI device. - * - * The RID for a device is formed from the alias, with a firmware - * supplied mapping applied - * - * Returns: The RID. - */ -u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev) -{ - struct device_node *of_node; - u32 rid = pci_dev_id(pdev); - - pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); - - of_node = irq_domain_get_of_node(domain); - rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) : - iort_msi_map_id(&pdev->dev, rid); - - return rid; -} - -/** - * pci_msi_get_device_domain - Get the MSI domain for a given PCI device - * @pdev: The PCI device - * - * Use the firmware data to find a device-specific MSI domain - * (i.e. not one that is set as a default). - * - * Returns: The corresponding MSI domain or NULL if none has been found. - */ -struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev) +void pci_no_msi(void) { - struct irq_domain *dom; - u32 rid = pci_dev_id(pdev); - - pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); - dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI); - if (!dom) - dom = iort_get_device_domain(&pdev->dev, rid, - DOMAIN_BUS_PCI_MSI); - return dom; + pci_msi_enable = 0; } /** - * pci_dev_has_special_msi_domain - Check whether the device is handled by - * a non-standard PCI-MSI domain - * @pdev: The PCI device to check. + * pci_msi_enabled - is MSI enabled? * - * Returns: True if the device irqdomain or the bus irqdomain is - * non-standard PCI/MSI. - */ -bool pci_dev_has_special_msi_domain(struct pci_dev *pdev) + * Returns true if MSI has not been disabled by the command-line option + * pci=nomsi. + **/ +int pci_msi_enabled(void) { - struct irq_domain *dom = dev_get_msi_domain(&pdev->dev); - - if (!dom) - dom = dev_get_msi_domain(&pdev->bus->dev); - - if (!dom) - return true; - - return dom->bus_token != DOMAIN_BUS_PCI_MSI; + return pci_msi_enable; } - -#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */ +EXPORT_SYMBOL(pci_msi_enabled); diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h new file mode 100644 index 000000000000..dbeff066bedd --- /dev/null +++ b/drivers/pci/msi/msi.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include + +#define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) + +extern int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +extern void pci_msi_teardown_msi_irqs(struct pci_dev *dev); + +#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS +extern int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); +extern void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev); +#else +static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) +{ + WARN_ON_ONCE(1); + return -ENODEV; +} + +static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) +{ + WARN_ON_ONCE(1); +} +#endif + +/* + * PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to + * mask all MSI interrupts by clearing the MSI enable bit does not work + * reliably as devices without an INTx disable bit will then generate a + * level IRQ which will never be cleared. + */ +static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) +{ + /* Don't shift by >= width of type */ + if (desc->pci.msi_attrib.multi_cap >= 5) + return 0xffffffff; + return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1; +} diff --git a/include/linux/msi.h b/include/linux/msi.h index 673899fc24f6..7ff7cf23b78d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -259,17 +259,6 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -#else -static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) -{ - WARN_ON_ONCE(1); - return -ENODEV; -} - -static inline void arch_teardown_msi_irqs(struct pci_dev *dev) -{ - WARN_ON_ONCE(1); -} #endif /* -- cgit v1.2.3 From 85aa607e79f8343f1ea028b29bdf8b6bc99c729a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:54 +0100 Subject: PCI/MSI: Sanitize MSI-X table map handling Unmapping the MSI-X base mapping in the loops which allocate/free MSI descriptors is daft and in the way of allowing runtime expansion of MSI-X descriptors. Store the mapping in struct pci_dev and free it after freeing the MSI-X descriptors. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211206210224.871651518@linutronix.de --- drivers/pci/msi/msi.c | 18 ++++++++---------- include/linux/pci.h | 1 + 2 files changed, 9 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 8926a6c8b345..465fe9e00294 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -241,14 +241,14 @@ static void free_msi_irqs(struct pci_dev *dev) pci_msi_teardown_msi_irqs(dev); list_for_each_entry_safe(entry, tmp, msi_list, list) { - if (entry->pci.msi_attrib.is_msix) { - if (list_is_last(&entry->list, msi_list)) - iounmap(entry->pci.mask_base); - } - list_del(&entry->list); free_msi_entry(entry); } + + if (dev->msix_base) { + iounmap(dev->msix_base); + dev->msix_base = NULL; + } } static void pci_intx_for_msi(struct pci_dev *dev, int enable) @@ -501,10 +501,6 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, for (i = 0, curmsk = masks; i < nvec; i++) { entry = alloc_msi_entry(&dev->dev, 1, curmsk); if (!entry) { - if (!i) - iounmap(base); - else - free_msi_irqs(dev); /* No enough memory. Don't try again */ ret = -ENOMEM; goto out; @@ -602,12 +598,14 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, goto out_disable; } + dev->msix_base = base; + /* Ensure that all table entries are masked. */ msix_mask_all(base, tsize); ret = msix_setup_entries(dev, base, entries, nvec, affd); if (ret) - goto out_disable; + goto out_free; ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); if (ret) diff --git a/include/linux/pci.h b/include/linux/pci.h index 18a75c8e615c..8cb103677f5a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -473,6 +473,7 @@ struct pci_dev { u8 ptm_granularity; #endif #ifdef CONFIG_PCI_MSI + void __iomem *msix_base; const struct attribute_group **msi_irq_groups; #endif struct pci_vpd vpd; -- cgit v1.2.3 From cd119b09a87d8beb50356d8c5c6aa42d89c44eb7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:56 +0100 Subject: PCI/MSI: Move msi_lock to struct pci_dev It's only required for PCI/MSI. So no point in having it in every struct device. Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211206210224.925241961@linutronix.de --- drivers/base/core.c | 1 - drivers/pci/msi/msi.c | 2 +- drivers/pci/probe.c | 4 +++- include/linux/device.h | 2 -- include/linux/pci.h | 1 + 5 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index fd034d742447..f26c668092d6 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2875,7 +2875,6 @@ void device_initialize(struct device *dev) device_pm_init(dev); set_dev_node(dev, NUMA_NO_NODE); #ifdef CONFIG_GENERIC_MSI_IRQ - raw_spin_lock_init(&dev->msi_lock); INIT_LIST_HEAD(&dev->msi_list); #endif INIT_LIST_HEAD(&dev->links.consumers); diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 465fe9e00294..443a16c67e1a 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -18,7 +18,7 @@ int pci_msi_ignore_mask; static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) { - raw_spinlock_t *lock = &desc->dev->msi_lock; + raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock; unsigned long flags; if (!desc->pci.msi_attrib.can_mask) diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 087d3658f75c..443efb00e219 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2311,7 +2311,9 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) INIT_LIST_HEAD(&dev->bus_list); dev->dev.type = &pci_dev_type; dev->bus = pci_bus_get(bus); - +#ifdef CONFIG_PCI_MSI + raw_spin_lock_init(&dev->msi_lock); +#endif return dev; } EXPORT_SYMBOL(pci_alloc_dev); diff --git a/include/linux/device.h b/include/linux/device.h index e270cb740b9e..2a22875238a6 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -407,7 +407,6 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. - * @msi_lock: Lock to protect MSI mask cache and mask register * @msi_list: Hosts MSI descriptors * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. @@ -508,7 +507,6 @@ struct device { struct dev_pin_info *pins; #endif #ifdef CONFIG_GENERIC_MSI_IRQ - raw_spinlock_t msi_lock; struct list_head msi_list; #endif #ifdef CONFIG_DMA_OPS diff --git a/include/linux/pci.h b/include/linux/pci.h index 8cb103677f5a..5cc46baef519 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -474,6 +474,7 @@ struct pci_dev { #endif #ifdef CONFIG_PCI_MSI void __iomem *msix_base; + raw_spinlock_t msi_lock; const struct attribute_group **msi_irq_groups; #endif struct pci_vpd vpd; -- cgit v1.2.3 From 57ce3a3c99b21e9c4f951ef01e0a3603c987c259 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:57 +0100 Subject: PCI/MSI: Make pci_msi_domain_check_cap() static No users outside of that file. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Reviewed-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211206210224.980989243@linutronix.de --- drivers/pci/msi/irqdomain.c | 5 +++-- include/linux/msi.h | 2 -- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 123450e715cb..6abd8aff2cea 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -79,8 +79,9 @@ static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc) * 1 if Multi MSI is requested, but the domain does not support it * -ENOTSUPP otherwise */ -int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, struct device *dev) +static int pci_msi_domain_check_cap(struct irq_domain *domain, + struct msi_domain_info *info, + struct device *dev) { struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev)); diff --git a/include/linux/msi.h b/include/linux/msi.h index 7ff7cf23b78d..5248678e05d1 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -439,8 +439,6 @@ void *platform_msi_get_host_data(struct irq_domain *domain); struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, struct msi_domain_info *info, struct irq_domain *parent); -int pci_msi_domain_check_cap(struct irq_domain *domain, - struct msi_domain_info *info, struct device *dev); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); bool pci_dev_has_special_msi_domain(struct pci_dev *pdev); -- cgit v1.2.3 From 890337624e1fa2da079fc1c036a62d178c985280 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:27:59 +0100 Subject: genirq/msi: Handle PCI/MSI allocation fail in core code Get rid of yet another irqdomain callback and let the core code return the already available information of how many descriptors could be allocated. Signed-off-by: Thomas Gleixner Tested-by: Juergen Gross Reviewed-by: Jason Gunthorpe Reviewed-by: Greg Kroah-Hartman Acked-by: Bjorn Helgaas # PCI Link: https://lore.kernel.org/r/20211206210225.046615302@linutronix.de --- drivers/pci/msi/irqdomain.c | 13 ------------- include/linux/msi.h | 5 +---- kernel/irq/msi.c | 29 +++++++++++++++++++++++++---- 3 files changed, 26 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 6abd8aff2cea..a5546900244d 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -95,16 +95,6 @@ static int pci_msi_domain_check_cap(struct irq_domain *domain, return 0; } -static int pci_msi_domain_handle_error(struct irq_domain *domain, - struct msi_desc *desc, int error) -{ - /* Special handling to support __pci_enable_msi_range() */ - if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC) - return 1; - - return error; -} - static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { @@ -115,7 +105,6 @@ static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, static struct msi_domain_ops pci_msi_domain_ops_default = { .set_desc = pci_msi_domain_set_desc, .msi_check = pci_msi_domain_check_cap, - .handle_error = pci_msi_domain_handle_error, }; static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) @@ -129,8 +118,6 @@ static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) ops->set_desc = pci_msi_domain_set_desc; if (ops->msi_check == NULL) ops->msi_check = pci_msi_domain_check_cap; - if (ops->handle_error == NULL) - ops->handle_error = pci_msi_domain_handle_error; } } diff --git a/include/linux/msi.h b/include/linux/msi.h index 5248678e05d1..ba4a39c430b5 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -286,7 +286,6 @@ struct msi_domain_info; * @msi_check: Callback for verification of the domain/info/dev data * @msi_prepare: Prepare the allocation of the interrupts in the domain * @set_desc: Set the msi descriptor for an interrupt - * @handle_error: Optional error handler if the allocation fails * @domain_alloc_irqs: Optional function to override the default allocation * function. * @domain_free_irqs: Optional function to override the default free @@ -295,7 +294,7 @@ struct msi_domain_info; * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying * irqdomain. * - * @msi_check, @msi_prepare, @handle_error and @set_desc are callbacks used by + * @msi_check, @msi_prepare and @set_desc are callbacks used by * msi_domain_alloc/free_irqs(). * * @domain_alloc_irqs, @domain_free_irqs can be used to override the @@ -332,8 +331,6 @@ struct msi_domain_ops { msi_alloc_info_t *arg); void (*set_desc)(msi_alloc_info_t *arg, struct msi_desc *desc); - int (*handle_error)(struct irq_domain *domain, - struct msi_desc *desc, int error); int (*domain_alloc_irqs)(struct irq_domain *domain, struct device *dev, int nvec); void (*domain_free_irqs)(struct irq_domain *domain, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 7d78d8aff076..4a7a7f0f5102 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -538,6 +538,27 @@ static bool msi_check_reservation_mode(struct irq_domain *domain, return desc->pci.msi_attrib.is_msix || desc->pci.msi_attrib.can_mask; } +static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc, + int allocated) +{ + switch(domain->bus_token) { + case DOMAIN_BUS_PCI_MSI: + case DOMAIN_BUS_VMD_MSI: + if (IS_ENABLED(CONFIG_PCI_MSI)) + break; + fallthrough; + default: + return -ENOSPC; + } + + /* Let a failed PCI multi MSI allocation retry */ + if (desc->nvec_used > 1) + return 1; + + /* If there was a successful allocation let the caller know */ + return allocated ? allocated : -ENOSPC; +} + int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec) { @@ -546,6 +567,7 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, struct irq_data *irq_data; struct msi_desc *desc; msi_alloc_info_t arg = { }; + int allocated = 0; int i, ret, virq; bool can_reserve; @@ -560,16 +582,15 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, dev_to_node(dev), &arg, false, desc->affinity); if (virq < 0) { - ret = -ENOSPC; - if (ops->handle_error) - ret = ops->handle_error(domain, desc, ret); - return ret; + ret = msi_handle_pci_fail(domain, desc, allocated); + goto cleanup; } for (i = 0; i < desc->nvec_used; i++) { irq_set_msi_desc_off(virq, i, desc); irq_debugfs_copy_devname(virq + i, dev); } + allocated++; } can_reserve = msi_check_reservation_mode(domain, info, dev); -- cgit v1.2.3 From 50468e4313355b161cac8a5155a45832995b7f25 Mon Sep 17 00:00:00 2001 From: Jarkko Sakkinen Date: Tue, 16 Nov 2021 18:21:16 +0200 Subject: x86/sgx: Add an attribute for the amount of SGX memory in a NUMA node == Problem == The amount of SGX memory on a system is determined by the BIOS and it varies wildly between systems. It can be as small as dozens of MB's and as large as many GB's on servers. Just like how applications need to know how much regular RAM is available, enclave builders need to know how much SGX memory an enclave can consume. == Solution == Introduce a new sysfs file: /sys/devices/system/node/nodeX/x86/sgx_total_bytes to enumerate the amount of SGX memory available in each NUMA node. This serves the same function for SGX as /proc/meminfo or /sys/devices/system/node/nodeX/meminfo does for normal RAM. 'sgx_total_bytes' is needed today to help drive the SGX selftests. SGX-specific swap code is exercised by creating overcommitted enclaves which are larger than the physical SGX memory on the system. They currently use a CPUID-based approach which can diverge from the actual amount of SGX memory available. 'sgx_total_bytes' ensures that the selftests can work efficiently and do not attempt stupid things like creating a 100,000 MB enclave on a system with 128 MB of SGX memory. == Implementation Details == Introduce CONFIG_HAVE_ARCH_NODE_DEV_GROUP opt-in flag to expose an arch specific attribute group, and add an attribute for the amount of SGX memory in bytes to each NUMA node: == ABI Design Discussion == As opposed to the per-node ABI, a single, global ABI was considered. However, this would prevent enclaves from being able to size themselves so that they fit on a single NUMA node. Essentially, a single value would rule out NUMA optimizations for enclaves. Create a new "x86/" directory inside each "nodeX/" sysfs directory. 'sgx_total_bytes' is expected to be the first of at least a few sgx-specific files to be placed in the new directory. Just scanning /proc/meminfo, these are the no-brainers that we have for RAM, but we need for SGX: MemTotal: xxxx kB // sgx_total_bytes (implemented here) MemFree: yyyy kB // sgx_free_bytes SwapTotal: zzzz kB // sgx_swapped_bytes So, at *least* three. I think we will eventually end up needing something more along the lines of a dozen. A new directory (as opposed to being in the nodeX/ "root") directory avoids cluttering the root with several "sgx_*" files. Place the new file in a new "nodeX/x86/" directory because SGX is highly x86-specific. It is very unlikely that any other architecture (or even non-Intel x86 vendor) will ever implement SGX. Using "sgx/" as opposed to "x86/" was also considered. But, there is a real chance this can get used for other arch-specific purposes. [ dhansen: rewrite changelog ] Signed-off-by: Jarkko Sakkinen Signed-off-by: Dave Hansen Acked-by: Greg Kroah-Hartman Acked-by: Borislav Petkov Link: https://lkml.kernel.org/r/20211116162116.93081-2-jarkko@kernel.org --- Documentation/ABI/stable/sysfs-devices-node | 6 ++++++ arch/Kconfig | 4 ++++ arch/x86/Kconfig | 1 + arch/x86/kernel/cpu/sgx/main.c | 20 ++++++++++++++++++++ arch/x86/kernel/cpu/sgx/sgx.h | 1 + drivers/base/node.c | 3 +++ include/linux/numa.h | 4 ++++ 7 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node index 484fc04bcc25..8db67aa472f1 100644 --- a/Documentation/ABI/stable/sysfs-devices-node +++ b/Documentation/ABI/stable/sysfs-devices-node @@ -176,3 +176,9 @@ Contact: Keith Busch Description: The cache write policy: 0 for write-back, 1 for write-through, other or unknown. + +What: /sys/devices/system/node/nodeX/x86/sgx_total_bytes +Date: November 2021 +Contact: Jarkko Sakkinen +Description: + The total amount of SGX physical memory in bytes. diff --git a/arch/Kconfig b/arch/Kconfig index 26b8ed11639d..0a9dadb00b61 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1302,6 +1302,10 @@ config ARCH_HAS_PARANOID_L1D_FLUSH config DYNAMIC_SIGFRAME bool +# Select, if arch has a named attribute group bound to NUMA device nodes. +config HAVE_ARCH_NODE_DEV_GROUP + bool + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b9281fab4e3e..f2b699d12eb8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -269,6 +269,7 @@ config X86 select HAVE_ARCH_KCSAN if X86_64 select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS + select HAVE_ARCH_NODE_DEV_GROUP if X86_SGX imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI config INSTRUCTION_DECODER diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 6036328de255..2857a49f2335 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -825,9 +825,11 @@ static bool __init sgx_page_cache_init(void) INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list); INIT_LIST_HEAD(&sgx_numa_nodes[nid].sgx_poison_page_list); node_set(nid, sgx_numa_mask); + sgx_numa_nodes[nid].size = 0; } sgx_epc_sections[i].node = &sgx_numa_nodes[nid]; + sgx_numa_nodes[nid].size += size; sgx_nr_epc_sections++; } @@ -901,6 +903,24 @@ int sgx_set_attribute(unsigned long *allowed_attributes, } EXPORT_SYMBOL_GPL(sgx_set_attribute); +#ifdef CONFIG_NUMA +static ssize_t sgx_total_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + return sysfs_emit(buf, "%lu\n", sgx_numa_nodes[dev->id].size); +} +static DEVICE_ATTR_RO(sgx_total_bytes); + +static struct attribute *arch_node_dev_attrs[] = { + &dev_attr_sgx_total_bytes.attr, + NULL, +}; + +const struct attribute_group arch_node_dev_group = { + .name = "x86", + .attrs = arch_node_dev_attrs, +}; +#endif /* CONFIG_NUMA */ + static int __init sgx_init(void) { int ret; diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index 9ec3136c7800..0f17def9fe6f 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -44,6 +44,7 @@ struct sgx_epc_page { struct sgx_numa_node { struct list_head free_page_list; struct list_head sgx_poison_page_list; + unsigned long size; spinlock_t lock; }; diff --git a/drivers/base/node.c b/drivers/base/node.c index b5a4ba18f9f9..87acc47e8951 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -581,6 +581,9 @@ static const struct attribute_group node_dev_group = { static const struct attribute_group *node_dev_groups[] = { &node_dev_group, +#ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP + &arch_node_dev_group, +#endif NULL }; diff --git a/include/linux/numa.h b/include/linux/numa.h index cb44cfe2b725..59df211d051f 100644 --- a/include/linux/numa.h +++ b/include/linux/numa.h @@ -58,4 +58,8 @@ static inline int phys_to_target_node(u64 start) } #endif +#ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP +extern const struct attribute_group arch_node_dev_group; +#endif + #endif /* _LINUX_NUMA_H */ -- cgit v1.2.3 From 67b967ddd93d0ed57d392a00f6f90060f0910c0e Mon Sep 17 00:00:00 2001 From: Miquel Raynal Date: Thu, 18 Nov 2021 12:46:59 +0100 Subject: mtd: Introduce an expert mode for forensics and debugging purposes When developping NAND controller drivers or when debugging filesystem corruptions, it is quite common to need hacking locally into the MTD/NAND core in order to get access to the content of the bad blocks. Instead of having multiple implementations out there let's provide a simple yet effective specific MTD-wide debugfs entry to fully disable these checks on purpose. A warning is added to inform the user when this mode gets enabled. Signed-off-by: Miquel Raynal Link: https://lore.kernel.org/linux-mtd/20211118114659.1282855-1-miquel.raynal@bootlin.com --- drivers/mtd/mtdcore.c | 10 ++++++++++ drivers/mtd/nand/core.c | 3 +++ drivers/mtd/nand/raw/nand_base.c | 3 +++ drivers/mtd/nand/raw/nand_bbt.c | 3 +++ include/linux/mtd/mtd.h | 3 +++ 5 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index a7723a708ea7..70f492dce158 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -2370,6 +2370,14 @@ static struct backing_dev_info * __init mtd_bdi_init(const char *name) return ret ? ERR_PTR(ret) : bdi; } +char *mtd_expert_analysis_warning = + "Bad block checks have been entirely disabled.\n" + "This is only reserved for post-mortem forensics and debug purposes.\n" + "Never enable this mode if you do not know what you are doing!\n"; +EXPORT_SYMBOL_GPL(mtd_expert_analysis_warning); +bool mtd_expert_analysis_mode; +EXPORT_SYMBOL_GPL(mtd_expert_analysis_mode); + static struct proc_dir_entry *proc_mtd; static int __init init_mtd(void) @@ -2393,6 +2401,8 @@ static int __init init_mtd(void) goto out_procfs; dfs_dir_mtd = debugfs_create_dir("mtd", NULL); + debugfs_create_bool("expert_analysis_mode", 0600, dfs_dir_mtd, + &mtd_expert_analysis_mode); return 0; diff --git a/drivers/mtd/nand/core.c b/drivers/mtd/nand/core.c index 5e13a03d2b32..416947f28b67 100644 --- a/drivers/mtd/nand/core.c +++ b/drivers/mtd/nand/core.c @@ -21,6 +21,9 @@ */ bool nanddev_isbad(struct nand_device *nand, const struct nand_pos *pos) { + if (WARN_ONCE(mtd_expert_analysis_mode, mtd_expert_analysis_warning)) + return false; + if (nanddev_bbt_is_initialized(nand)) { unsigned int entry; int status; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 3d6c6e880520..b3a9bc08b4bb 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -321,6 +321,9 @@ static int nand_isbad_bbm(struct nand_chip *chip, loff_t ofs) if (nand_region_is_secured(chip, ofs, mtd->erasesize)) return -EIO; + if (WARN_ONCE(mtd_expert_analysis_mode, mtd_expert_analysis_warning)) + return 0; + if (chip->legacy.block_bad) return chip->legacy.block_bad(chip, ofs); diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index b7ad030225f8..ab630af3a309 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -1455,6 +1455,9 @@ int nand_isbad_bbt(struct nand_chip *this, loff_t offs, int allowbbt) pr_debug("nand_isbad_bbt(): bbt info for offs 0x%08x: (block %d) 0x%02x\n", (unsigned int)offs, block, res); + if (WARN_ONCE(mtd_expert_analysis_mode, mtd_expert_analysis_warning)) + return 0; + switch (res) { case BBT_BLOCK_GOOD: return 0; diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index f5e7dfc2e4e9..1ffa933121f6 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -711,4 +711,7 @@ static inline int mtd_is_bitflip_or_eccerr(int err) { unsigned mtd_mmap_capabilities(struct mtd_info *mtd); +extern char *mtd_expert_analysis_warning; +extern bool mtd_expert_analysis_mode; + #endif /* __MTD_MTD_H__ */ -- cgit v1.2.3 From cab2d3fd6866e089b5c50db09dece131f85bfebd Mon Sep 17 00:00:00 2001 From: Loic Poulain Date: Thu, 9 Dec 2021 18:46:33 +0530 Subject: bus: mhi: core: Add support for forced PM resume For whatever reason, some devices like QCA6390, WCN6855 using ath11k are not in M3 state during PM resume, but still functional. The mhi_pm_resume should then not fail in those cases, and let the higher level device specific stack continue resuming process. Add an API mhi_pm_resume_force(), to force resuming irrespective of the current MHI state. This fixes a regression with non functional ath11k WiFi after suspend/resume cycle on some machines. Bug report: https://bugzilla.kernel.org/show_bug.cgi?id=214179 Link: https://lore.kernel.org/regressions/871r5p0x2u.fsf@codeaurora.org/ Fixes: 020d3b26c07a ("bus: mhi: Early MHI resume failure in non M3 state") Cc: stable@vger.kernel.org #5.13 Reported-by: Kalle Valo Reported-by: Pengyu Ma Tested-by: Kalle Valo Acked-by: Kalle Valo Signed-off-by: Loic Poulain [mani: Switched to API, added bug report, reported-by tags and CCed stable] Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20211209131633.4168-1-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/core/pm.c | 21 ++++++++++++++++++--- drivers/net/wireless/ath/ath11k/mhi.c | 6 +++++- include/linux/mhi.h | 13 +++++++++++++ 3 files changed, 36 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index fb99e3727155..547e6e769546 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -881,7 +881,7 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl) } EXPORT_SYMBOL_GPL(mhi_pm_suspend); -int mhi_pm_resume(struct mhi_controller *mhi_cntrl) +static int __mhi_pm_resume(struct mhi_controller *mhi_cntrl, bool force) { struct mhi_chan *itr, *tmp; struct device *dev = &mhi_cntrl->mhi_dev->dev; @@ -898,8 +898,12 @@ int mhi_pm_resume(struct mhi_controller *mhi_cntrl) if (MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state)) return -EIO; - if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3) - return -EINVAL; + if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3) { + dev_warn(dev, "Resuming from non M3 state (%s)\n", + TO_MHI_STATE_STR(mhi_get_mhi_state(mhi_cntrl))); + if (!force) + return -EINVAL; + } /* Notify clients about exiting LPM */ list_for_each_entry_safe(itr, tmp, &mhi_cntrl->lpm_chans, node) { @@ -940,8 +944,19 @@ int mhi_pm_resume(struct mhi_controller *mhi_cntrl) return 0; } + +int mhi_pm_resume(struct mhi_controller *mhi_cntrl) +{ + return __mhi_pm_resume(mhi_cntrl, false); +} EXPORT_SYMBOL_GPL(mhi_pm_resume); +int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl) +{ + return __mhi_pm_resume(mhi_cntrl, true); +} +EXPORT_SYMBOL_GPL(mhi_pm_resume_force); + int __mhi_device_get_sync(struct mhi_controller *mhi_cntrl) { int ret; diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c index 26c7ae242db6..49c0b1ad40a0 100644 --- a/drivers/net/wireless/ath/ath11k/mhi.c +++ b/drivers/net/wireless/ath/ath11k/mhi.c @@ -533,7 +533,11 @@ static int ath11k_mhi_set_state(struct ath11k_pci *ab_pci, ret = mhi_pm_suspend(ab_pci->mhi_ctrl); break; case ATH11K_MHI_RESUME: - ret = mhi_pm_resume(ab_pci->mhi_ctrl); + /* Do force MHI resume as some devices like QCA6390, WCN6855 + * are not in M3 state but they are functional. So just ignore + * the MHI state while resuming. + */ + ret = mhi_pm_resume_force(ab_pci->mhi_ctrl); break; case ATH11K_MHI_TRIGGER_RDDM: ret = mhi_force_rddm_mode(ab_pci->mhi_ctrl); diff --git a/include/linux/mhi.h b/include/linux/mhi.h index 723985879035..a5cc4cdf9cc8 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -663,6 +663,19 @@ int mhi_pm_suspend(struct mhi_controller *mhi_cntrl); */ int mhi_pm_resume(struct mhi_controller *mhi_cntrl); +/** + * mhi_pm_resume_force - Force resume MHI from suspended state + * @mhi_cntrl: MHI controller + * + * Resume the device irrespective of its MHI state. As per the MHI spec, devices + * has to be in M3 state during resume. But some devices seem to be in a + * different MHI state other than M3 but they continue working fine if allowed. + * This API is intented to be used for such devices. + * + * Return: 0 if the resume succeeds, a negative error code otherwise + */ +int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl); + /** * mhi_download_rddm_image - Download ramdump image from device for * debugging purpose. -- cgit v1.2.3 From dc70ec217cec504e6f8fee8fd91bf5c118af05f2 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 21 Nov 2021 12:54:40 +0000 Subject: KVM: Introduce CONFIG_HAVE_KVM_DIRTY_RING I'd like to make the build include dirty_ring.c based on whether the arch wants it or not. That's a whole lot simpler if there's a config symbol instead of doing it implicitly on KVM_DIRTY_LOG_PAGE_OFFSET being set to something non-zero. Signed-off-by: David Woodhouse Message-Id: <20211121125451.9489-2-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/Kconfig | 1 + include/linux/kvm_dirty_ring.h | 8 ++++---- virt/kvm/Kconfig | 3 +++ virt/kvm/kvm_main.c | 4 ++-- 4 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 7618bef0a4a9..03b2ce34e7f4 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -27,6 +27,7 @@ config KVM select MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_IRQFD + select HAVE_KVM_DIRTY_RING select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 120e5e90fa1d..4da8d4a4140b 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -27,9 +27,9 @@ struct kvm_dirty_ring { int index; }; -#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0) +#ifndef CONFIG_HAVE_KVM_DIRTY_RING /* - * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should + * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should * not be included as well, so define these nop functions for the arch. */ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) @@ -74,7 +74,7 @@ static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) return true; } -#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#else /* CONFIG_HAVE_KVM_DIRTY_RING */ u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); @@ -98,6 +98,6 @@ struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset); void kvm_dirty_ring_free(struct kvm_dirty_ring *ring); bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring); -#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */ +#endif /* CONFIG_HAVE_KVM_DIRTY_RING */ #endif /* KVM_DIRTY_RING_H */ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 62b39149b8c8..97cf5413ac25 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -13,6 +13,9 @@ config HAVE_KVM_IRQFD config HAVE_KVM_IRQ_ROUTING bool +config HAVE_KVM_DIRTY_RING + bool + config HAVE_KVM_EVENTFD bool select EVENTFD diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index f3acff708bf5..b0f7e6eb00ff 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3600,7 +3600,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { -#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 +#ifdef CONFIG_HAVE_KVM_DIRTY_RING return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + kvm->dirty_ring_size / PAGE_SIZE); @@ -4305,7 +4305,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; case KVM_CAP_DIRTY_LOG_RING: -#if KVM_DIRTY_LOG_PAGE_OFFSET > 0 +#ifdef CONFIG_HAVE_KVM_DIRTY_RING return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; -- cgit v1.2.3 From 42288cb44c4b5fff7653bc392b583a2b8bd6a8c0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:51 -0800 Subject: wait: add wake_up_pollfree() Several ->poll() implementations are special in that they use a waitqueue whose lifetime is the current task, rather than the struct file as is normally the case. This is okay for blocking polls, since a blocking poll occurs within one task; however, non-blocking polls require another solution. This solution is for the queue to be cleared before it is freed, using 'wake_up_poll(wq, EPOLLHUP | POLLFREE);'. However, that has a bug: wake_up_poll() calls __wake_up() with nr_exclusive=1. Therefore, if there are multiple "exclusive" waiters, and the wakeup function for the first one returns a positive value, only that one will be called. That's *not* what's needed for POLLFREE; POLLFREE is special in that it really needs to wake up everyone. Considering the three non-blocking poll systems: - io_uring poll doesn't handle POLLFREE at all, so it is broken anyway. - aio poll is unaffected, since it doesn't support exclusive waits. However, that's fragile, as someone could add this feature later. - epoll doesn't appear to be broken by this, since its wakeup function returns 0 when it sees POLLFREE. But this is fragile. Although there is a workaround (see epoll), it's better to define a function which always sends POLLFREE to all waiters. Add such a function. Also make it verify that the queue really becomes empty after all waiters have been woken up. Reported-by: Linus Torvalds Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211209010455.42744-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- include/linux/wait.h | 26 ++++++++++++++++++++++++++ kernel/sched/wait.c | 7 +++++++ 2 files changed, 33 insertions(+) (limited to 'include/linux') diff --git a/include/linux/wait.h b/include/linux/wait.h index 2d0df57c9902..851e07da2583 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -217,6 +217,7 @@ void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key); void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr); void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); +void __wake_up_pollfree(struct wait_queue_head *wq_head); #define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL) #define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL) @@ -245,6 +246,31 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode); #define wake_up_interruptible_sync_poll_locked(x, m) \ __wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m)) +/** + * wake_up_pollfree - signal that a polled waitqueue is going away + * @wq_head: the wait queue head + * + * In the very rare cases where a ->poll() implementation uses a waitqueue whose + * lifetime is tied to a task rather than to the 'struct file' being polled, + * this function must be called before the waitqueue is freed so that + * non-blocking polls (e.g. epoll) are notified that the queue is going away. + * + * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via + * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU. + */ +static inline void wake_up_pollfree(struct wait_queue_head *wq_head) +{ + /* + * For performance reasons, we don't always take the queue lock here. + * Therefore, we might race with someone removing the last entry from + * the queue, and proceed while they still hold the queue lock. + * However, rcu_read_lock() is required to be held in such cases, so we + * can safely proceed with an RCU-delayed free. + */ + if (waitqueue_active(wq_head)) + __wake_up_pollfree(wq_head); +} + #define ___wait_cond_timeout(condition) \ ({ \ bool __cond = (condition); \ diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 76577d1642a5..eca38107b32f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any -- cgit v1.2.3 From 6abfaaf124a81b7d2ab132cc2c9885baa14171e5 Mon Sep 17 00:00:00 2001 From: Lukas Czerner Date: Wed, 27 Oct 2021 16:18:45 +0200 Subject: fs_parse: allow parameter value to be empty Allow parameter value to be empty by specifying fs_param_can_be_empty flag. Signed-off-by: Lukas Czerner Cc: Al Viro Reviewed-by: Carlos Maiolino Link: https://lore.kernel.org/r/20211027141857.33657-2-lczerner@redhat.com Signed-off-by: Theodore Ts'o --- fs/fs_parser.c | 31 +++++++++++++++++++++++-------- include/linux/fs_parser.h | 2 +- 2 files changed, 24 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/fs_parser.c b/fs/fs_parser.c index 3df07c0e32b3..ed40ce5742fd 100644 --- a/fs/fs_parser.c +++ b/fs/fs_parser.c @@ -199,6 +199,8 @@ int fs_param_is_bool(struct p_log *log, const struct fs_parameter_spec *p, int b; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); + if (!*param->string && (p->flags & fs_param_can_be_empty)) + return 0; b = lookup_constant(bool_names, param->string, -1); if (b == -1) return fs_param_bad_value(log, param); @@ -211,8 +213,11 @@ int fs_param_is_u32(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { int base = (unsigned long)p->data; - if (param->type != fs_value_is_string || - kstrtouint(param->string, base, &result->uint_32) < 0) + if (param->type != fs_value_is_string) + return fs_param_bad_value(log, param); + if (!*param->string && (p->flags & fs_param_can_be_empty)) + return 0; + if (kstrtouint(param->string, base, &result->uint_32) < 0) return fs_param_bad_value(log, param); return 0; } @@ -221,8 +226,11 @@ EXPORT_SYMBOL(fs_param_is_u32); int fs_param_is_s32(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { - if (param->type != fs_value_is_string || - kstrtoint(param->string, 0, &result->int_32) < 0) + if (param->type != fs_value_is_string) + return fs_param_bad_value(log, param); + if (!*param->string && (p->flags & fs_param_can_be_empty)) + return 0; + if (kstrtoint(param->string, 0, &result->int_32) < 0) return fs_param_bad_value(log, param); return 0; } @@ -231,8 +239,11 @@ EXPORT_SYMBOL(fs_param_is_s32); int fs_param_is_u64(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { - if (param->type != fs_value_is_string || - kstrtoull(param->string, 0, &result->uint_64) < 0) + if (param->type != fs_value_is_string) + return fs_param_bad_value(log, param); + if (!*param->string && (p->flags & fs_param_can_be_empty)) + return 0; + if (kstrtoull(param->string, 0, &result->uint_64) < 0) return fs_param_bad_value(log, param); return 0; } @@ -244,6 +255,8 @@ int fs_param_is_enum(struct p_log *log, const struct fs_parameter_spec *p, const struct constant_table *c; if (param->type != fs_value_is_string) return fs_param_bad_value(log, param); + if (!*param->string && (p->flags & fs_param_can_be_empty)) + return 0; c = __lookup_constant(p->data, param->string); if (!c) return fs_param_bad_value(log, param); @@ -255,7 +268,8 @@ EXPORT_SYMBOL(fs_param_is_enum); int fs_param_is_string(struct p_log *log, const struct fs_parameter_spec *p, struct fs_parameter *param, struct fs_parse_result *result) { - if (param->type != fs_value_is_string || !*param->string) + if (param->type != fs_value_is_string || + (!*param->string && !(p->flags & fs_param_can_be_empty))) return fs_param_bad_value(log, param); return 0; } @@ -275,7 +289,8 @@ int fs_param_is_fd(struct p_log *log, const struct fs_parameter_spec *p, { switch (param->type) { case fs_value_is_string: - if (kstrtouint(param->string, 0, &result->uint_32) < 0) + if ((!*param->string && !(p->flags & fs_param_can_be_empty)) || + kstrtouint(param->string, 0, &result->uint_32) < 0) break; if (result->uint_32 <= INT_MAX) return 0; diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index aab0ffc6bac6..f103c91139d4 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -42,7 +42,7 @@ struct fs_parameter_spec { u8 opt; /* Option number (returned by fs_parse()) */ unsigned short flags; #define fs_param_neg_with_no 0x0002 /* "noxxx" is negative param */ -#define fs_param_neg_with_empty 0x0004 /* "xxx=" is negative param */ +#define fs_param_can_be_empty 0x0004 /* "xxx=" is allowed */ #define fs_param_deprecated 0x0008 /* The param is deprecated */ const void *data; }; -- cgit v1.2.3 From 3e5b1feccea7db576353ffc302f78d522e4116e6 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 9 Dec 2021 13:11:32 +0000 Subject: net: phylink: add legacy_pre_march2020 indicator Add a boolean to phylink_config to indicate whether a driver has not been updated for the changes in commit 7cceb599d15d ("net: phylink: avoid mac_config calls"), and thus are reliant on the old behaviour. We were currently keying the phylink behaviour on the presence of a PCS, but this is sub-optimal for modern drivers that may not have a PCS. This commit merely introduces the new flag, but does not add any use, since we need all legacy drivers to set this flag before it can be used. Once these legacy drivers have been updated, we can remove this flag. Signed-off-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- include/linux/phylink.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 01224235df0f..d005b8e36048 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -84,6 +84,8 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance + * @legacy_pre_march2020: driver has not been updated for March 2020 updates + * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @pcs_poll: MAC PCS cannot provide link change interrupt * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. @@ -97,6 +99,7 @@ enum phylink_op_type { struct phylink_config { struct device *dev; enum phylink_op_type type; + bool legacy_pre_march2020; bool pcs_poll; bool poll_fixed_state; bool ovr_an_inband; -- cgit v1.2.3 From 001f4261fe4d5ae710cf1f445b6cae6d9d3ae26e Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Thu, 9 Dec 2021 13:11:48 +0000 Subject: net: phylink: use legacy_pre_march2020 Use the legacy flag to indicate whether we should operate in legacy mode. This allows us to stop using the presence of a PCS as an indicator to the age of the phylink user, and make PCS presence optional. Legacy mode involves: 1) calling mac_config() whenever the link comes up 2) calling mac_config() whenever the inband advertisement changes, possibly followed by a call to mac_an_restart() 3) making use of mac_an_restart() 4) making use of mac_pcs_get_state() All the above functionality was moved to a seperate "PCS" block of operations in March 2020. Update the documents to indicate that the differences that this flag makes. Signed-off-by: Russell King (Oracle) Signed-off-by: Jakub Kicinski --- drivers/net/phy/phylink.c | 12 ++++++------ include/linux/phylink.h | 17 +++++++++++++++++ 2 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 8e3861f09b4f..e47f2baf4b07 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -742,7 +742,7 @@ static void phylink_mac_pcs_an_restart(struct phylink *pl) phylink_autoneg_inband(pl->cur_link_an_mode)) { if (pl->pcs_ops) pl->pcs_ops->pcs_an_restart(pl->pcs); - else + else if (pl->config->legacy_pre_march2020) pl->mac_ops->mac_an_restart(pl->config); } } @@ -803,7 +803,7 @@ static int phylink_change_inband_advert(struct phylink *pl) if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state)) return 0; - if (!pl->pcs_ops) { + if (!pl->pcs_ops && pl->config->legacy_pre_march2020) { /* Legacy method */ phylink_mac_config(pl, &pl->link_config); phylink_mac_pcs_an_restart(pl); @@ -854,7 +854,8 @@ static void phylink_mac_pcs_get_state(struct phylink *pl, if (pl->pcs_ops) pl->pcs_ops->pcs_get_state(pl->pcs, state); - else if (pl->mac_ops->mac_pcs_get_state) + else if (pl->mac_ops->mac_pcs_get_state && + pl->config->legacy_pre_march2020) pl->mac_ops->mac_pcs_get_state(pl->config, state); else state->link = 0; @@ -1048,12 +1049,11 @@ static void phylink_resolve(struct work_struct *w) } phylink_major_config(pl, false, &link_state); pl->link_config.interface = link_state.interface; - } else if (!pl->pcs_ops) { + } else if (!pl->pcs_ops && pl->config->legacy_pre_march2020) { /* The interface remains unchanged, only the speed, * duplex or pause settings have changed. Call the * old mac_config() method to configure the MAC/PCS - * only if we do not have a PCS installed (an - * unconverted user.) + * only if we do not have a legacy MAC driver. */ phylink_mac_config(pl, &link_state); } diff --git a/include/linux/phylink.h b/include/linux/phylink.h index d005b8e36048..a2f266cc3442 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -190,6 +190,10 @@ void validate(struct phylink_config *config, unsigned long *supported, * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_pcs_get_state(struct phylink_config *config, struct phylink_link_state *state); @@ -230,6 +234,15 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set + * in their &phylnk_config and which don't have a PCS), this function will be + * called on each link up event, and to also change the in-band advert. For + * non-legacy drivers, it will only be called to reconfigure the MAC for a + * "major" change in e.g. interface mode. It will not be called for changes + * in speed, duplex or pause modes or to change the in-band advertisement. + * In any case, it is strongly preferred that speed, duplex and pause settings + * are handled in the mac_link_up() method and not in this method. + * * (this requires a rewrite - please refer to mac_link_up() for situations * where the PCS and MAC are not tightly integrated.) * @@ -314,6 +327,10 @@ int mac_finish(struct phylink_config *config, unsigned int mode, /** * mac_an_restart() - restart 802.3z BaseX autonegotiation * @config: a pointer to a &struct phylink_config. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_an_restart(struct phylink_config *config); -- cgit v1.2.3 From 1a2fb220edca98d18f90e3ef5bd6853a6b22b1b8 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 6 Dec 2021 22:27:58 -0800 Subject: skbuff: Extract list pointers to silence compiler warnings Under both -Warray-bounds and the object_size sanitizer, the compiler is upset about accessing prev/next of sk_buff when the object it thinks it is coming from is sk_buff_head. The warning is a false positive due to the compiler taking a conservative approach, opting to warn at casting time rather than access time. However, in support of enabling -Warray-bounds globally (which has found many real bugs), arrange things for sk_buff so that the compiler can unambiguously see that there is no intention to access anything except prev/next. Introduce and cast to a separate struct sk_buff_list, which contains _only_ the first two fields, silencing the warnings: In file included from ./include/net/net_namespace.h:39, from ./include/linux/netdevice.h:37, from net/core/netpoll.c:17: net/core/netpoll.c: In function 'refill_skbs': ./include/linux/skbuff.h:2086:9: warning: array subscript 'struct sk_buff[0]' is partly outside array bounds of 'struct sk_buff_head[1]' [-Warray-bounds] 2086 | __skb_insert(newsk, next->prev, next, list); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ net/core/netpoll.c:49:28: note: while referencing 'skb_pool' 49 | static struct sk_buff_head skb_pool; | ^~~~~~~~ This change results in no executable instruction differences. Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/20211207062758.2324338-1-keescook@chromium.org Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dd262bd8ddbe..6535294f6a48 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -292,9 +292,11 @@ struct tc_skb_ext { #endif struct sk_buff_head { - /* These two members must be first. */ - struct sk_buff *next; - struct sk_buff *prev; + /* These two members must be first to match sk_buff. */ + struct_group_tagged(sk_buff_list, list, + struct sk_buff *next; + struct sk_buff *prev; + ); __u32 qlen; spinlock_t lock; @@ -730,7 +732,7 @@ typedef unsigned char *sk_buff_data_t; struct sk_buff { union { struct { - /* These two members must be first. */ + /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; @@ -1976,8 +1978,8 @@ static inline void __skb_insert(struct sk_buff *newsk, */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); - WRITE_ONCE(next->prev, newsk); - WRITE_ONCE(prev->next, newsk); + WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); + WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } @@ -2073,7 +2075,7 @@ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { - __skb_insert(newsk, prev, prev->next, list); + __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, @@ -2083,7 +2085,7 @@ static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { - __skb_insert(newsk, next->prev, next, list); + __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** -- cgit v1.2.3 From a4f1192cb53758a7210ed5a9ee695aeba22f75fb Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 9 Dec 2021 14:30:33 +0200 Subject: percpu_ref: Replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Signed-off-by: Andy Shevchenko Signed-off-by: Dennis Zhou --- include/linux/percpu-refcount.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h index b31d3f3312ce..d73a1c08c3e3 100644 --- a/include/linux/percpu-refcount.h +++ b/include/linux/percpu-refcount.h @@ -51,9 +51,9 @@ #define _LINUX_PERCPU_REFCOUNT_H #include -#include #include #include +#include #include struct percpu_ref; -- cgit v1.2.3 From 9756f64c8f2d19c0029a5827bda8ac275302ec22 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 30 Nov 2021 12:44:11 +0100 Subject: kcsan: Avoid checking scoped accesses from nested contexts Avoid checking scoped accesses from nested contexts (such as nested interrupts or in scheduler code) which share the same kcsan_ctx. This is to avoid detecting false positive races of accesses in the same thread with currently scoped accesses: consider setting up a watchpoint for a non-scoped (normal) access that also "conflicts" with a current scoped access. In a nested interrupt (or in the scheduler), which shares the same kcsan_ctx, we cannot check scoped accesses set up in the parent context -- simply ignore them in this case. With the introduction of kcsan_ctx::disable_scoped, we can also clean up kcsan_check_scoped_accesses()'s recursion guard, and do not need to modify the list's prev pointer. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan.h | 1 + kernel/kcsan/core.c | 18 +++++++++++++++--- 2 files changed, 16 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index fc266ecb2a4d..13cef3458fed 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -21,6 +21,7 @@ */ struct kcsan_ctx { int disable_count; /* disable counter */ + int disable_scoped; /* disable scoped access counter */ int atomic_next; /* number of following atomic ops */ /* diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index e34a1710b7bc..bd359f8ee63a 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -204,15 +204,17 @@ check_access(const volatile void *ptr, size_t size, int type, unsigned long ip); static noinline void kcsan_check_scoped_accesses(void) { struct kcsan_ctx *ctx = get_ctx(); - struct list_head *prev_save = ctx->scoped_accesses.prev; struct kcsan_scoped_access *scoped_access; - ctx->scoped_accesses.prev = NULL; /* Avoid recursion. */ + if (ctx->disable_scoped) + return; + + ctx->disable_scoped++; list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) { check_access(scoped_access->ptr, scoped_access->size, scoped_access->type, scoped_access->ip); } - ctx->scoped_accesses.prev = prev_save; + ctx->disable_scoped--; } /* Rules for generic atomic accesses. Called from fast-path. */ @@ -465,6 +467,15 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned goto out; } + /* + * Avoid races of scoped accesses from nested interrupts (or scheduler). + * Assume setting up a watchpoint for a non-scoped (normal) access that + * also conflicts with a current scoped access. In a nested interrupt, + * which shares the context, it would check a conflicting scoped access. + * To avoid, disable scoped access checking. + */ + ctx->disable_scoped++; + /* * Save and restore the IRQ state trace touched by KCSAN, since KCSAN's * runtime is entered for every memory access, and potentially useful @@ -578,6 +589,7 @@ out_unlock: if (!kcsan_interrupt_watcher) local_irq_restore(irq_flags); kcsan_restore_irqtrace(current); + ctx->disable_scoped--; out: user_access_restore(ua_flags); } -- cgit v1.2.3 From 69562e4983d93e2791c0bf128b07462afbd7f4dc Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Thu, 5 Aug 2021 14:57:45 +0200 Subject: kcsan: Add core support for a subset of weak memory modeling Add support for modeling a subset of weak memory, which will enable detection of a subset of data races due to missing memory barriers. KCSAN's approach to detecting missing memory barriers is based on modeling access reordering, and enabled if `CONFIG_KCSAN_WEAK_MEMORY=y`, which depends on `CONFIG_KCSAN_STRICT=y`. The feature can be enabled or disabled at boot and runtime via the `kcsan.weak_memory` boot parameter. Each memory access for which a watchpoint is set up, is also selected for simulated reordering within the scope of its function (at most 1 in-flight access). We are limited to modeling the effects of "buffering" (delaying the access), since the runtime cannot "prefetch" accesses (therefore no acquire modeling). Once an access has been selected for reordering, it is checked along every other access until the end of the function scope. If an appropriate memory barrier is encountered, the access will no longer be considered for reordering. When the result of a memory operation should be ordered by a barrier, KCSAN can then detect data races where the conflict only occurs as a result of a missing barrier due to reordering accesses. Suggested-by: Dmitry Vyukov Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 10 ++- include/linux/kcsan.h | 10 ++- include/linux/sched.h | 3 + kernel/kcsan/core.c | 202 +++++++++++++++++++++++++++++++++++++++---- lib/Kconfig.kcsan | 20 +++++ scripts/Makefile.kcsan | 9 +- 6 files changed, 235 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 5f5965246877..a1c6a89fde71 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -99,7 +99,15 @@ void kcsan_set_access_mask(unsigned long mask); /* Scoped access information. */ struct kcsan_scoped_access { - struct list_head list; + union { + struct list_head list; /* scoped_accesses list */ + /* + * Not an entry in scoped_accesses list; stack depth from where + * the access was initialized. + */ + int stack_depth; + }; + /* Access information. */ const volatile void *ptr; size_t size; diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h index 13cef3458fed..c07c71f5ba4f 100644 --- a/include/linux/kcsan.h +++ b/include/linux/kcsan.h @@ -49,8 +49,16 @@ struct kcsan_ctx { */ unsigned long access_mask; - /* List of scoped accesses. */ + /* List of scoped accesses; likely to be empty. */ struct list_head scoped_accesses; + +#ifdef CONFIG_KCSAN_WEAK_MEMORY + /* + * Scoped access for modeling access reordering to detect missing memory + * barriers; only keep 1 to keep fast-path complexity manageable. + */ + struct kcsan_scoped_access reorder_access; +#endif }; /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..0cd40b010487 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1339,6 +1339,9 @@ struct task_struct { #ifdef CONFIG_TRACE_IRQFLAGS struct irqtrace_events kcsan_save_irqtrace; #endif +#ifdef CONFIG_KCSAN_WEAK_MEMORY + int kcsan_stack_depth; +#endif #endif #if IS_ENABLED(CONFIG_KUNIT) diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index bd359f8ee63a..481f8a524089 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -40,6 +40,13 @@ module_param_named(udelay_interrupt, kcsan_udelay_interrupt, uint, 0644); module_param_named(skip_watch, kcsan_skip_watch, long, 0644); module_param_named(interrupt_watcher, kcsan_interrupt_watcher, bool, 0444); +#ifdef CONFIG_KCSAN_WEAK_MEMORY +static bool kcsan_weak_memory = true; +module_param_named(weak_memory, kcsan_weak_memory, bool, 0644); +#else +#define kcsan_weak_memory false +#endif + bool kcsan_enabled; /* Per-CPU kcsan_ctx for interrupts */ @@ -351,6 +358,67 @@ void kcsan_restore_irqtrace(struct task_struct *task) #endif } +static __always_inline int get_kcsan_stack_depth(void) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + return current->kcsan_stack_depth; +#else + BUILD_BUG(); + return 0; +#endif +} + +static __always_inline void add_kcsan_stack_depth(int val) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + current->kcsan_stack_depth += val; +#else + BUILD_BUG(); +#endif +} + +static __always_inline struct kcsan_scoped_access *get_reorder_access(struct kcsan_ctx *ctx) +{ +#ifdef CONFIG_KCSAN_WEAK_MEMORY + return ctx->disable_scoped ? NULL : &ctx->reorder_access; +#else + return NULL; +#endif +} + +static __always_inline bool +find_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, + int type, unsigned long ip) +{ + struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); + + if (!reorder_access) + return false; + + /* + * Note: If accesses are repeated while reorder_access is identical, + * never matches the new access, because !(type & KCSAN_ACCESS_SCOPED). + */ + return reorder_access->ptr == ptr && reorder_access->size == size && + reorder_access->type == type && reorder_access->ip == ip; +} + +static inline void +set_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size, + int type, unsigned long ip) +{ + struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); + + if (!reorder_access || !kcsan_weak_memory) + return; + + reorder_access->ptr = ptr; + reorder_access->size = size; + reorder_access->type = type | KCSAN_ACCESS_SCOPED; + reorder_access->ip = ip; + reorder_access->stack_depth = get_kcsan_stack_depth(); +} + /* * Pull everything together: check_access() below contains the performance * critical operations; the fast-path (including check_access) functions should @@ -389,8 +457,10 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr, * The access_mask check relies on value-change comparison. To avoid * reporting a race where e.g. the writer set up the watchpoint, but the * reader has access_mask!=0, we have to ignore the found watchpoint. + * + * reorder_access is never created from an access with access_mask set. */ - if (ctx->access_mask) + if (ctx->access_mask && !find_reorder_access(ctx, ptr, size, type, ip)) return; /* @@ -440,11 +510,13 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0; atomic_long_t *watchpoint; u64 old, new, diff; - unsigned long access_mask; enum kcsan_value_change value_change = KCSAN_VALUE_CHANGE_MAYBE; + bool interrupt_watcher = kcsan_interrupt_watcher; unsigned long ua_flags = user_access_save(); struct kcsan_ctx *ctx = get_ctx(); + unsigned long access_mask = ctx->access_mask; unsigned long irq_flags = 0; + bool is_reorder_access; /* * Always reset kcsan_skip counter in slow-path to avoid underflow; see @@ -467,6 +539,17 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned goto out; } + /* + * The local CPU cannot observe reordering of its own accesses, and + * therefore we need to take care of 2 cases to avoid false positives: + * + * 1. Races of the reordered access with interrupts. To avoid, if + * the current access is reorder_access, disable interrupts. + * 2. Avoid races of scoped accesses from nested interrupts (below). + */ + is_reorder_access = find_reorder_access(ctx, ptr, size, type, ip); + if (is_reorder_access) + interrupt_watcher = false; /* * Avoid races of scoped accesses from nested interrupts (or scheduler). * Assume setting up a watchpoint for a non-scoped (normal) access that @@ -482,7 +565,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned * information is lost if dirtied by KCSAN. */ kcsan_save_irqtrace(current); - if (!kcsan_interrupt_watcher) + if (!interrupt_watcher) local_irq_save(irq_flags); watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write); @@ -503,7 +586,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned * Read the current value, to later check and infer a race if the data * was modified via a non-instrumented access, e.g. from a device. */ - old = read_instrumented_memory(ptr, size); + old = is_reorder_access ? 0 : read_instrumented_memory(ptr, size); /* * Delay this thread, to increase probability of observing a racy @@ -515,8 +598,17 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned * Re-read value, and check if it is as expected; if not, we infer a * racy access. */ - access_mask = ctx->access_mask; - new = read_instrumented_memory(ptr, size); + if (!is_reorder_access) { + new = read_instrumented_memory(ptr, size); + } else { + /* + * Reordered accesses cannot be used for value change detection, + * because the memory location may no longer be accessible and + * could result in a fault. + */ + new = 0; + access_mask = 0; + } diff = old ^ new; if (access_mask) @@ -585,11 +677,20 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned */ remove_watchpoint(watchpoint); atomic_long_dec(&kcsan_counters[KCSAN_COUNTER_USED_WATCHPOINTS]); + out_unlock: - if (!kcsan_interrupt_watcher) + if (!interrupt_watcher) local_irq_restore(irq_flags); kcsan_restore_irqtrace(current); ctx->disable_scoped--; + + /* + * Reordered accesses cannot be used for value change detection, + * therefore never consider for reordering if access_mask is set. + * ASSERT_EXCLUSIVE are not real accesses, ignore them as well. + */ + if (!access_mask && !is_assert) + set_reorder_access(ctx, ptr, size, type, ip); out: user_access_restore(ua_flags); } @@ -597,7 +698,6 @@ out: static __always_inline void check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) { - const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0; atomic_long_t *watchpoint; long encoded_watchpoint; @@ -608,12 +708,14 @@ check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) if (unlikely(size == 0)) return; +again: /* * Avoid user_access_save in fast-path: find_watchpoint is safe without * user_access_save, as the address that ptr points to is only used to * check if a watchpoint exists; ptr is never dereferenced. */ - watchpoint = find_watchpoint((unsigned long)ptr, size, !is_write, + watchpoint = find_watchpoint((unsigned long)ptr, size, + !(type & KCSAN_ACCESS_WRITE), &encoded_watchpoint); /* * It is safe to check kcsan_is_enabled() after find_watchpoint in the @@ -627,9 +729,42 @@ check_access(const volatile void *ptr, size_t size, int type, unsigned long ip) else { struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */ - if (unlikely(should_watch(ctx, ptr, size, type))) + if (unlikely(should_watch(ctx, ptr, size, type))) { kcsan_setup_watchpoint(ptr, size, type, ip); - else if (unlikely(ctx->scoped_accesses.prev)) + return; + } + + if (!(type & KCSAN_ACCESS_SCOPED)) { + struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx); + + if (reorder_access) { + /* + * reorder_access check: simulates reordering of + * the access after subsequent operations. + */ + ptr = reorder_access->ptr; + type = reorder_access->type; + ip = reorder_access->ip; + /* + * Upon a nested interrupt, this context's + * reorder_access can be modified (shared ctx). + * We know that upon return, reorder_access is + * always invalidated by setting size to 0 via + * __tsan_func_exit(). Therefore we must read + * and check size after the other fields. + */ + barrier(); + size = READ_ONCE(reorder_access->size); + if (size) + goto again; + } + } + + /* + * Always checked last, right before returning from runtime; + * if reorder_access is valid, checked after it was checked. + */ + if (unlikely(ctx->scoped_accesses.prev)) kcsan_check_scoped_accesses(); } } @@ -916,19 +1051,56 @@ DEFINE_TSAN_VOLATILE_READ_WRITE(8); DEFINE_TSAN_VOLATILE_READ_WRITE(16); /* - * The below are not required by KCSAN, but can still be emitted by the - * compiler. + * Function entry and exit are used to determine the validty of reorder_access. + * Reordering of the access ends at the end of the function scope where the + * access happened. This is done for two reasons: + * + * 1. Artificially limits the scope where missing barriers are detected. + * This minimizes false positives due to uninstrumented functions that + * contain the required barriers but were missed. + * + * 2. Simplifies generating the stack trace of the access. */ void __tsan_func_entry(void *call_pc); -void __tsan_func_entry(void *call_pc) +noinline void __tsan_func_entry(void *call_pc) { + if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) + return; + + add_kcsan_stack_depth(1); } EXPORT_SYMBOL(__tsan_func_entry); + void __tsan_func_exit(void); -void __tsan_func_exit(void) +noinline void __tsan_func_exit(void) { + struct kcsan_scoped_access *reorder_access; + + if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY)) + return; + + reorder_access = get_reorder_access(get_ctx()); + if (!reorder_access) + goto out; + + if (get_kcsan_stack_depth() <= reorder_access->stack_depth) { + /* + * Access check to catch cases where write without a barrier + * (supposed release) was last access in function: because + * instrumentation is inserted before the real access, a data + * race due to the write giving up a c-s would only be caught if + * we do the conflicting access after. + */ + check_access(reorder_access->ptr, reorder_access->size, + reorder_access->type, reorder_access->ip); + reorder_access->size = 0; + reorder_access->stack_depth = INT_MIN; + } +out: + add_kcsan_stack_depth(-1); } EXPORT_SYMBOL(__tsan_func_exit); + void __tsan_init(void); void __tsan_init(void) { diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index e0a93ffdef30..e4394ea8068b 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -191,6 +191,26 @@ config KCSAN_STRICT closely aligns with the rules defined by the Linux-kernel memory consistency model (LKMM). +config KCSAN_WEAK_MEMORY + bool "Enable weak memory modeling to detect missing memory barriers" + default y + depends on KCSAN_STRICT + # We can either let objtool nop __tsan_func_{entry,exit}() and builtin + # atomics instrumentation in .noinstr.text, or use a compiler that can + # implement __no_kcsan to really remove all instrumentation. + depends on STACK_VALIDATION || CC_IS_GCC + help + Enable support for modeling a subset of weak memory, which allows + detecting a subset of data races due to missing memory barriers. + + Depends on KCSAN_STRICT, because the options strenghtening certain + plain accesses by default (depending on !KCSAN_STRICT) reduce the + ability to detect any data races invoving reordered accesses, in + particular reordered writes. + + Weak memory modeling relies on additional instrumentation and may + affect performance. + config KCSAN_REPORT_VALUE_CHANGE_ONLY bool "Only report races where watcher observed a data value change" default y diff --git a/scripts/Makefile.kcsan b/scripts/Makefile.kcsan index 37cb504c77e1..4c7f0d282e42 100644 --- a/scripts/Makefile.kcsan +++ b/scripts/Makefile.kcsan @@ -9,7 +9,12 @@ endif # Keep most options here optional, to allow enabling more compilers if absence # of some options does not break KCSAN nor causes false positive reports. -export CFLAGS_KCSAN := -fsanitize=thread \ - $(call cc-option,$(call cc-param,tsan-instrument-func-entry-exit=0) -fno-optimize-sibling-calls) \ +kcsan-cflags := -fsanitize=thread -fno-optimize-sibling-calls \ $(call cc-option,$(call cc-param,tsan-compound-read-before-write=1),$(call cc-option,$(call cc-param,tsan-instrument-read-before-write=1))) \ $(call cc-param,tsan-distinguish-volatile=1) + +ifndef CONFIG_KCSAN_WEAK_MEMORY +kcsan-cflags += $(call cc-option,$(call cc-param,tsan-instrument-func-entry-exit=0)) +endif + +export CFLAGS_KCSAN := $(kcsan-cflags) -- cgit v1.2.3 From 0b8b0830ac1419d7250fde31ea78793a03f3db44 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 30 Nov 2021 12:44:13 +0100 Subject: kcsan: Add core memory barrier instrumentation functions Add the core memory barrier instrumentation functions. These invalidate the current in-flight reordered access based on the rules for the respective barrier types and in-flight access type. To obtain barrier instrumentation that can be disabled via __no_kcsan with appropriate compiler-support (and not just with objtool help), barrier instrumentation repurposes __atomic_signal_fence(), instead of inserting explicit calls. Crucially, __atomic_signal_fence() normally does not map to any real instructions, but is still intercepted by fsanitize=thread. As a result, like any other instrumentation done by the compiler, barrier instrumentation can be disabled with __no_kcsan. Unfortunately Clang and GCC currently differ in their __no_kcsan aka __no_sanitize_thread behaviour with respect to builtin atomics (and __tsan_func_{entry,exit}) instrumentation. This is already reflected in Kconfig.kcsan's dependencies for KCSAN_WEAK_MEMORY. A later change will introduce support for newer versions of Clang that can implement __no_kcsan to also remove the additional instrumentation introduced by KCSAN_WEAK_MEMORY. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 71 ++++++++++++++++++++++++++++++++++++++++++-- kernel/kcsan/core.c | 68 +++++++++++++++++++++++++++++++++++++++++- 2 files changed, 136 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index a1c6a89fde71..9d2c869167f2 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -36,6 +36,36 @@ */ void __kcsan_check_access(const volatile void *ptr, size_t size, int type); +/* + * See definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c. + * Note: The mappings are arbitrary, and do not reflect any real mappings of C11 + * memory orders to the LKMM memory orders and vice-versa! + */ +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb __ATOMIC_SEQ_CST +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb __ATOMIC_ACQ_REL +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb __ATOMIC_ACQUIRE +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_release __ATOMIC_RELEASE + +/** + * __kcsan_mb - full memory barrier instrumentation + */ +void __kcsan_mb(void); + +/** + * __kcsan_wmb - write memory barrier instrumentation + */ +void __kcsan_wmb(void); + +/** + * __kcsan_rmb - read memory barrier instrumentation + */ +void __kcsan_rmb(void); + +/** + * __kcsan_release - release barrier instrumentation + */ +void __kcsan_release(void); + /** * kcsan_disable_current - disable KCSAN for the current context * @@ -159,6 +189,10 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa); static inline void __kcsan_check_access(const volatile void *ptr, size_t size, int type) { } +static inline void __kcsan_mb(void) { } +static inline void __kcsan_wmb(void) { } +static inline void __kcsan_rmb(void) { } +static inline void __kcsan_release(void) { } static inline void kcsan_disable_current(void) { } static inline void kcsan_enable_current(void) { } static inline void kcsan_enable_current_nowarn(void) { } @@ -191,12 +225,45 @@ static inline void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) { } */ #define __kcsan_disable_current kcsan_disable_current #define __kcsan_enable_current kcsan_enable_current_nowarn -#else +#else /* __SANITIZE_THREAD__ */ static inline void kcsan_check_access(const volatile void *ptr, size_t size, int type) { } static inline void __kcsan_enable_current(void) { } static inline void __kcsan_disable_current(void) { } -#endif +#endif /* __SANITIZE_THREAD__ */ + +#if defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__SANITIZE_THREAD__) +/* + * Normal barrier instrumentation is not done via explicit calls, but by mapping + * to a repurposed __atomic_signal_fence(), which normally does not generate any + * real instructions, but is still intercepted by fsanitize=thread. This means, + * like any other compile-time instrumentation, barrier instrumentation can be + * disabled with the __no_kcsan function attribute. + * + * Also see definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c. + */ +#define __KCSAN_BARRIER_TO_SIGNAL_FENCE(name) \ + static __always_inline void kcsan_##name(void) \ + { \ + barrier(); \ + __atomic_signal_fence(__KCSAN_BARRIER_TO_SIGNAL_FENCE_##name); \ + barrier(); \ + } +__KCSAN_BARRIER_TO_SIGNAL_FENCE(mb) +__KCSAN_BARRIER_TO_SIGNAL_FENCE(wmb) +__KCSAN_BARRIER_TO_SIGNAL_FENCE(rmb) +__KCSAN_BARRIER_TO_SIGNAL_FENCE(release) +#elif defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__KCSAN_INSTRUMENT_BARRIERS__) +#define kcsan_mb __kcsan_mb +#define kcsan_wmb __kcsan_wmb +#define kcsan_rmb __kcsan_rmb +#define kcsan_release __kcsan_release +#else /* CONFIG_KCSAN_WEAK_MEMORY && ... */ +static inline void kcsan_mb(void) { } +static inline void kcsan_wmb(void) { } +static inline void kcsan_rmb(void) { } +static inline void kcsan_release(void) { } +#endif /* CONFIG_KCSAN_WEAK_MEMORY && ... */ /** * __kcsan_check_read - check regular read access for races diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 481f8a524089..916060913966 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -939,6 +939,22 @@ void __kcsan_check_access(const volatile void *ptr, size_t size, int type) } EXPORT_SYMBOL(__kcsan_check_access); +#define DEFINE_MEMORY_BARRIER(name, order_before_cond) \ + void __kcsan_##name(void) \ + { \ + struct kcsan_scoped_access *sa = get_reorder_access(get_ctx()); \ + if (!sa) \ + return; \ + if (order_before_cond) \ + sa->size = 0; \ + } \ + EXPORT_SYMBOL(__kcsan_##name) + +DEFINE_MEMORY_BARRIER(mb, true); +DEFINE_MEMORY_BARRIER(wmb, sa->type & (KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND)); +DEFINE_MEMORY_BARRIER(rmb, !(sa->type & KCSAN_ACCESS_WRITE) || (sa->type & KCSAN_ACCESS_COMPOUND)); +DEFINE_MEMORY_BARRIER(release, true); + /* * KCSAN uses the same instrumentation that is emitted by supported compilers * for ThreadSanitizer (TSAN). @@ -1123,10 +1139,19 @@ EXPORT_SYMBOL(__tsan_init); * functions, whose job is to also execute the operation itself. */ +static __always_inline void kcsan_atomic_builtin_memorder(int memorder) +{ + if (memorder == __ATOMIC_RELEASE || + memorder == __ATOMIC_SEQ_CST || + memorder == __ATOMIC_ACQ_REL) + __kcsan_release(); +} + #define DEFINE_TSAN_ATOMIC_LOAD_STORE(bits) \ u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder); \ u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder) \ { \ + kcsan_atomic_builtin_memorder(memorder); \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_); \ } \ @@ -1136,6 +1161,7 @@ EXPORT_SYMBOL(__tsan_init); void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder); \ void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder) \ { \ + kcsan_atomic_builtin_memorder(memorder); \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_); \ @@ -1148,6 +1174,7 @@ EXPORT_SYMBOL(__tsan_init); u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder); \ u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder) \ { \ + kcsan_atomic_builtin_memorder(memorder); \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ @@ -1180,6 +1207,7 @@ EXPORT_SYMBOL(__tsan_init); int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp, \ u##bits val, int mo, int fail_mo) \ { \ + kcsan_atomic_builtin_memorder(mo); \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ @@ -1195,6 +1223,7 @@ EXPORT_SYMBOL(__tsan_init); u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \ int mo, int fail_mo) \ { \ + kcsan_atomic_builtin_memorder(mo); \ if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \ check_access(ptr, bits / BITS_PER_BYTE, \ KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \ @@ -1226,10 +1255,47 @@ DEFINE_TSAN_ATOMIC_OPS(64); void __tsan_atomic_thread_fence(int memorder); void __tsan_atomic_thread_fence(int memorder) { + kcsan_atomic_builtin_memorder(memorder); __atomic_thread_fence(memorder); } EXPORT_SYMBOL(__tsan_atomic_thread_fence); +/* + * In instrumented files, we emit instrumentation for barriers by mapping the + * kernel barriers to an __atomic_signal_fence(), which is interpreted specially + * and otherwise has no relation to a real __atomic_signal_fence(). No known + * kernel code uses __atomic_signal_fence(). + * + * Since fsanitize=thread instrumentation handles __atomic_signal_fence(), which + * are turned into calls to __tsan_atomic_signal_fence(), such instrumentation + * can be disabled via the __no_kcsan function attribute (vs. an explicit call + * which could not). When __no_kcsan is requested, __atomic_signal_fence() + * generates no code. + * + * Note: The result of using __atomic_signal_fence() with KCSAN enabled is + * potentially limiting the compiler's ability to reorder operations; however, + * if barriers were instrumented with explicit calls (without LTO), the compiler + * couldn't optimize much anyway. The result of a hypothetical architecture + * using __atomic_signal_fence() in normal code would be KCSAN false negatives. + */ void __tsan_atomic_signal_fence(int memorder); -void __tsan_atomic_signal_fence(int memorder) { } +noinline void __tsan_atomic_signal_fence(int memorder) +{ + switch (memorder) { + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb: + __kcsan_mb(); + break; + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb: + __kcsan_wmb(); + break; + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb: + __kcsan_rmb(); + break; + case __KCSAN_BARRIER_TO_SIGNAL_FENCE_release: + __kcsan_release(); + break; + default: + break; + } +} EXPORT_SYMBOL(__tsan_atomic_signal_fence); -- cgit v1.2.3 From f948666de517cf8ebef7cb2c9b2d669dec4bfe2e Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 30 Nov 2021 12:44:22 +0100 Subject: locking/barriers, kcsan: Add instrumentation for barriers Adds the required KCSAN instrumentation for barriers if CONFIG_SMP. KCSAN supports modeling the effects of: smp_mb() smp_rmb() smp_wmb() smp_store_release() Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/asm-generic/barrier.h | 29 +++++++++++++++-------------- include/linux/spinlock.h | 2 +- 2 files changed, 16 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 640f09479bdf..27a9c9edfef6 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -14,6 +14,7 @@ #ifndef __ASSEMBLY__ #include +#include #include #ifndef nop @@ -62,15 +63,15 @@ #ifdef CONFIG_SMP #ifndef smp_mb -#define smp_mb() __smp_mb() +#define smp_mb() do { kcsan_mb(); __smp_mb(); } while (0) #endif #ifndef smp_rmb -#define smp_rmb() __smp_rmb() +#define smp_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0) #endif #ifndef smp_wmb -#define smp_wmb() __smp_wmb() +#define smp_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0) #endif #else /* !CONFIG_SMP */ @@ -123,19 +124,19 @@ do { \ #ifdef CONFIG_SMP #ifndef smp_store_mb -#define smp_store_mb(var, value) __smp_store_mb(var, value) +#define smp_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0) #endif #ifndef smp_mb__before_atomic -#define smp_mb__before_atomic() __smp_mb__before_atomic() +#define smp_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0) #endif #ifndef smp_mb__after_atomic -#define smp_mb__after_atomic() __smp_mb__after_atomic() +#define smp_mb__after_atomic() do { kcsan_mb(); __smp_mb__after_atomic(); } while (0) #endif #ifndef smp_store_release -#define smp_store_release(p, v) __smp_store_release(p, v) +#define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0) #endif #ifndef smp_load_acquire @@ -178,13 +179,13 @@ do { \ #endif /* CONFIG_SMP */ /* Barriers for virtual machine guests when talking to an SMP host */ -#define virt_mb() __smp_mb() -#define virt_rmb() __smp_rmb() -#define virt_wmb() __smp_wmb() -#define virt_store_mb(var, value) __smp_store_mb(var, value) -#define virt_mb__before_atomic() __smp_mb__before_atomic() -#define virt_mb__after_atomic() __smp_mb__after_atomic() -#define virt_store_release(p, v) __smp_store_release(p, v) +#define virt_mb() do { kcsan_mb(); __smp_mb(); } while (0) +#define virt_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0) +#define virt_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0) +#define virt_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0) +#define virt_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0) +#define virt_mb__after_atomic() do { kcsan_mb(); __smp_mb__after_atomic(); } while (0) +#define virt_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0) #define virt_load_acquire(p) __smp_load_acquire(p) /** diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index b4e5ca23f840..5c0c5174155d 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -171,7 +171,7 @@ do { \ * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock -#define smp_mb__after_spinlock() do { } while (0) +#define smp_mb__after_spinlock() kcsan_mb() #endif #ifdef CONFIG_DEBUG_SPINLOCK -- cgit v1.2.3 From e87c4f6642f49627c3430cb3ee78c73fb51b48e4 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 30 Nov 2021 12:44:24 +0100 Subject: locking/atomics, kcsan: Add instrumentation for barriers Adds the required KCSAN instrumentation for barriers of atomics. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/atomic/atomic-instrumented.h | 135 ++++++++++++++++++++++++++++- scripts/atomic/gen-atomic-instrumented.sh | 41 +++++++-- 2 files changed, 166 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index a0f654370da3..5d69b143c28e 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -45,6 +45,7 @@ atomic_set(atomic_t *v, int i) static __always_inline void atomic_set_release(atomic_t *v, int i) { + kcsan_release(); instrument_atomic_write(v, sizeof(*v)); arch_atomic_set_release(v, i); } @@ -59,6 +60,7 @@ atomic_add(int i, atomic_t *v) static __always_inline int atomic_add_return(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return(i, v); } @@ -73,6 +75,7 @@ atomic_add_return_acquire(int i, atomic_t *v) static __always_inline int atomic_add_return_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_return_release(i, v); } @@ -87,6 +90,7 @@ atomic_add_return_relaxed(int i, atomic_t *v) static __always_inline int atomic_fetch_add(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add(i, v); } @@ -101,6 +105,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_add_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_release(i, v); } @@ -122,6 +127,7 @@ atomic_sub(int i, atomic_t *v) static __always_inline int atomic_sub_return(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return(i, v); } @@ -136,6 +142,7 @@ atomic_sub_return_acquire(int i, atomic_t *v) static __always_inline int atomic_sub_return_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_return_release(i, v); } @@ -150,6 +157,7 @@ atomic_sub_return_relaxed(int i, atomic_t *v) static __always_inline int atomic_fetch_sub(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub(i, v); } @@ -164,6 +172,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_sub_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_sub_release(i, v); } @@ -185,6 +194,7 @@ atomic_inc(atomic_t *v) static __always_inline int atomic_inc_return(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return(v); } @@ -199,6 +209,7 @@ atomic_inc_return_acquire(atomic_t *v) static __always_inline int atomic_inc_return_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_return_release(v); } @@ -213,6 +224,7 @@ atomic_inc_return_relaxed(atomic_t *v) static __always_inline int atomic_fetch_inc(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc(v); } @@ -227,6 +239,7 @@ atomic_fetch_inc_acquire(atomic_t *v) static __always_inline int atomic_fetch_inc_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_inc_release(v); } @@ -248,6 +261,7 @@ atomic_dec(atomic_t *v) static __always_inline int atomic_dec_return(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return(v); } @@ -262,6 +276,7 @@ atomic_dec_return_acquire(atomic_t *v) static __always_inline int atomic_dec_return_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_return_release(v); } @@ -276,6 +291,7 @@ atomic_dec_return_relaxed(atomic_t *v) static __always_inline int atomic_fetch_dec(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec(v); } @@ -290,6 +306,7 @@ atomic_fetch_dec_acquire(atomic_t *v) static __always_inline int atomic_fetch_dec_release(atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_dec_release(v); } @@ -311,6 +328,7 @@ atomic_and(int i, atomic_t *v) static __always_inline int atomic_fetch_and(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and(i, v); } @@ -325,6 +343,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_and_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_and_release(i, v); } @@ -346,6 +365,7 @@ atomic_andnot(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot(i, v); } @@ -360,6 +380,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_andnot_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_andnot_release(i, v); } @@ -381,6 +402,7 @@ atomic_or(int i, atomic_t *v) static __always_inline int atomic_fetch_or(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or(i, v); } @@ -395,6 +417,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_or_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_or_release(i, v); } @@ -416,6 +439,7 @@ atomic_xor(int i, atomic_t *v) static __always_inline int atomic_fetch_xor(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor(i, v); } @@ -430,6 +454,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v) static __always_inline int atomic_fetch_xor_release(int i, atomic_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_xor_release(i, v); } @@ -444,6 +469,7 @@ atomic_fetch_xor_relaxed(int i, atomic_t *v) static __always_inline int atomic_xchg(atomic_t *v, int i) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg(v, i); } @@ -458,6 +484,7 @@ atomic_xchg_acquire(atomic_t *v, int i) static __always_inline int atomic_xchg_release(atomic_t *v, int i) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_xchg_release(v, i); } @@ -472,6 +499,7 @@ atomic_xchg_relaxed(atomic_t *v, int i) static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg(v, old, new); } @@ -486,6 +514,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new) static __always_inline int atomic_cmpxchg_release(atomic_t *v, int old, int new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_cmpxchg_release(v, old, new); } @@ -500,6 +529,7 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new) static __always_inline bool atomic_try_cmpxchg(atomic_t *v, int *old, int new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg(v, old, new); @@ -516,6 +546,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) static __always_inline bool atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_try_cmpxchg_release(v, old, new); @@ -532,6 +563,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) static __always_inline bool atomic_sub_and_test(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_sub_and_test(i, v); } @@ -539,6 +571,7 @@ atomic_sub_and_test(int i, atomic_t *v) static __always_inline bool atomic_dec_and_test(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_and_test(v); } @@ -546,6 +579,7 @@ atomic_dec_and_test(atomic_t *v) static __always_inline bool atomic_inc_and_test(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_and_test(v); } @@ -553,6 +587,7 @@ atomic_inc_and_test(atomic_t *v) static __always_inline bool atomic_add_negative(int i, atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_negative(i, v); } @@ -560,6 +595,7 @@ atomic_add_negative(int i, atomic_t *v) static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_fetch_add_unless(v, a, u); } @@ -567,6 +603,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u) static __always_inline bool atomic_add_unless(atomic_t *v, int a, int u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_add_unless(v, a, u); } @@ -574,6 +611,7 @@ atomic_add_unless(atomic_t *v, int a, int u) static __always_inline bool atomic_inc_not_zero(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_not_zero(v); } @@ -581,6 +619,7 @@ atomic_inc_not_zero(atomic_t *v) static __always_inline bool atomic_inc_unless_negative(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_inc_unless_negative(v); } @@ -588,6 +627,7 @@ atomic_inc_unless_negative(atomic_t *v) static __always_inline bool atomic_dec_unless_positive(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_unless_positive(v); } @@ -595,6 +635,7 @@ atomic_dec_unless_positive(atomic_t *v) static __always_inline int atomic_dec_if_positive(atomic_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_dec_if_positive(v); } @@ -623,6 +664,7 @@ atomic64_set(atomic64_t *v, s64 i) static __always_inline void atomic64_set_release(atomic64_t *v, s64 i) { + kcsan_release(); instrument_atomic_write(v, sizeof(*v)); arch_atomic64_set_release(v, i); } @@ -637,6 +679,7 @@ atomic64_add(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return(i, v); } @@ -651,6 +694,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_add_return_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_return_release(i, v); } @@ -665,6 +709,7 @@ atomic64_add_return_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add(i, v); } @@ -679,6 +724,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_release(i, v); } @@ -700,6 +746,7 @@ atomic64_sub(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return(i, v); } @@ -714,6 +761,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_sub_return_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_return_release(i, v); } @@ -728,6 +776,7 @@ atomic64_sub_return_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub(i, v); } @@ -742,6 +791,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_sub_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_sub_release(i, v); } @@ -763,6 +813,7 @@ atomic64_inc(atomic64_t *v) static __always_inline s64 atomic64_inc_return(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return(v); } @@ -777,6 +828,7 @@ atomic64_inc_return_acquire(atomic64_t *v) static __always_inline s64 atomic64_inc_return_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_return_release(v); } @@ -791,6 +843,7 @@ atomic64_inc_return_relaxed(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc(v); } @@ -805,6 +858,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v) static __always_inline s64 atomic64_fetch_inc_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_inc_release(v); } @@ -826,6 +880,7 @@ atomic64_dec(atomic64_t *v) static __always_inline s64 atomic64_dec_return(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return(v); } @@ -840,6 +895,7 @@ atomic64_dec_return_acquire(atomic64_t *v) static __always_inline s64 atomic64_dec_return_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_return_release(v); } @@ -854,6 +910,7 @@ atomic64_dec_return_relaxed(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec(v); } @@ -868,6 +925,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v) static __always_inline s64 atomic64_fetch_dec_release(atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_dec_release(v); } @@ -889,6 +947,7 @@ atomic64_and(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and(i, v); } @@ -903,6 +962,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_and_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_and_release(i, v); } @@ -924,6 +984,7 @@ atomic64_andnot(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot(i, v); } @@ -938,6 +999,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_andnot_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_andnot_release(i, v); } @@ -959,6 +1021,7 @@ atomic64_or(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or(i, v); } @@ -973,6 +1036,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_or_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_or_release(i, v); } @@ -994,6 +1058,7 @@ atomic64_xor(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor(i, v); } @@ -1008,6 +1073,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_xor_release(s64 i, atomic64_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_xor_release(i, v); } @@ -1022,6 +1088,7 @@ atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v) static __always_inline s64 atomic64_xchg(atomic64_t *v, s64 i) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg(v, i); } @@ -1036,6 +1103,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i) static __always_inline s64 atomic64_xchg_release(atomic64_t *v, s64 i) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_xchg_release(v, i); } @@ -1050,6 +1118,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 i) static __always_inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg(v, old, new); } @@ -1064,6 +1133,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new) static __always_inline s64 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_cmpxchg_release(v, old, new); } @@ -1078,6 +1148,7 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new) static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg(v, old, new); @@ -1094,6 +1165,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic64_try_cmpxchg_release(v, old, new); @@ -1110,6 +1182,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_sub_and_test(i, v); } @@ -1117,6 +1190,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v) static __always_inline bool atomic64_dec_and_test(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_and_test(v); } @@ -1124,6 +1198,7 @@ atomic64_dec_and_test(atomic64_t *v) static __always_inline bool atomic64_inc_and_test(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_and_test(v); } @@ -1131,6 +1206,7 @@ atomic64_inc_and_test(atomic64_t *v) static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_negative(i, v); } @@ -1138,6 +1214,7 @@ atomic64_add_negative(s64 i, atomic64_t *v) static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_fetch_add_unless(v, a, u); } @@ -1145,6 +1222,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_add_unless(v, a, u); } @@ -1152,6 +1230,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u) static __always_inline bool atomic64_inc_not_zero(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_not_zero(v); } @@ -1159,6 +1238,7 @@ atomic64_inc_not_zero(atomic64_t *v) static __always_inline bool atomic64_inc_unless_negative(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_inc_unless_negative(v); } @@ -1166,6 +1246,7 @@ atomic64_inc_unless_negative(atomic64_t *v) static __always_inline bool atomic64_dec_unless_positive(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_unless_positive(v); } @@ -1173,6 +1254,7 @@ atomic64_dec_unless_positive(atomic64_t *v) static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic64_dec_if_positive(v); } @@ -1201,6 +1283,7 @@ atomic_long_set(atomic_long_t *v, long i) static __always_inline void atomic_long_set_release(atomic_long_t *v, long i) { + kcsan_release(); instrument_atomic_write(v, sizeof(*v)); arch_atomic_long_set_release(v, i); } @@ -1215,6 +1298,7 @@ atomic_long_add(long i, atomic_long_t *v) static __always_inline long atomic_long_add_return(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_return(i, v); } @@ -1229,6 +1313,7 @@ atomic_long_add_return_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_add_return_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_return_release(i, v); } @@ -1243,6 +1328,7 @@ atomic_long_add_return_relaxed(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_add(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_add(i, v); } @@ -1257,6 +1343,7 @@ atomic_long_fetch_add_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_add_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_add_release(i, v); } @@ -1278,6 +1365,7 @@ atomic_long_sub(long i, atomic_long_t *v) static __always_inline long atomic_long_sub_return(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_sub_return(i, v); } @@ -1292,6 +1380,7 @@ atomic_long_sub_return_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_sub_return_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_sub_return_release(i, v); } @@ -1306,6 +1395,7 @@ atomic_long_sub_return_relaxed(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_sub(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_sub(i, v); } @@ -1320,6 +1410,7 @@ atomic_long_fetch_sub_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_sub_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_sub_release(i, v); } @@ -1341,6 +1432,7 @@ atomic_long_inc(atomic_long_t *v) static __always_inline long atomic_long_inc_return(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_return(v); } @@ -1355,6 +1447,7 @@ atomic_long_inc_return_acquire(atomic_long_t *v) static __always_inline long atomic_long_inc_return_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_return_release(v); } @@ -1369,6 +1462,7 @@ atomic_long_inc_return_relaxed(atomic_long_t *v) static __always_inline long atomic_long_fetch_inc(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_inc(v); } @@ -1383,6 +1477,7 @@ atomic_long_fetch_inc_acquire(atomic_long_t *v) static __always_inline long atomic_long_fetch_inc_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_inc_release(v); } @@ -1404,6 +1499,7 @@ atomic_long_dec(atomic_long_t *v) static __always_inline long atomic_long_dec_return(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_return(v); } @@ -1418,6 +1514,7 @@ atomic_long_dec_return_acquire(atomic_long_t *v) static __always_inline long atomic_long_dec_return_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_return_release(v); } @@ -1432,6 +1529,7 @@ atomic_long_dec_return_relaxed(atomic_long_t *v) static __always_inline long atomic_long_fetch_dec(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_dec(v); } @@ -1446,6 +1544,7 @@ atomic_long_fetch_dec_acquire(atomic_long_t *v) static __always_inline long atomic_long_fetch_dec_release(atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_dec_release(v); } @@ -1467,6 +1566,7 @@ atomic_long_and(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_and(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_and(i, v); } @@ -1481,6 +1581,7 @@ atomic_long_fetch_and_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_and_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_and_release(i, v); } @@ -1502,6 +1603,7 @@ atomic_long_andnot(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_andnot(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_andnot(i, v); } @@ -1516,6 +1618,7 @@ atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_andnot_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_andnot_release(i, v); } @@ -1537,6 +1640,7 @@ atomic_long_or(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_or(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_or(i, v); } @@ -1551,6 +1655,7 @@ atomic_long_fetch_or_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_or_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_or_release(i, v); } @@ -1572,6 +1677,7 @@ atomic_long_xor(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_xor(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_xor(i, v); } @@ -1586,6 +1692,7 @@ atomic_long_fetch_xor_acquire(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_xor_release(long i, atomic_long_t *v) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_xor_release(i, v); } @@ -1600,6 +1707,7 @@ atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v) static __always_inline long atomic_long_xchg(atomic_long_t *v, long i) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_xchg(v, i); } @@ -1614,6 +1722,7 @@ atomic_long_xchg_acquire(atomic_long_t *v, long i) static __always_inline long atomic_long_xchg_release(atomic_long_t *v, long i) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_xchg_release(v, i); } @@ -1628,6 +1737,7 @@ atomic_long_xchg_relaxed(atomic_long_t *v, long i) static __always_inline long atomic_long_cmpxchg(atomic_long_t *v, long old, long new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_cmpxchg(v, old, new); } @@ -1642,6 +1752,7 @@ atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new) static __always_inline long atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_cmpxchg_release(v, old, new); } @@ -1656,6 +1767,7 @@ atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new) static __always_inline bool atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_long_try_cmpxchg(v, old, new); @@ -1672,6 +1784,7 @@ atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) static __always_inline bool atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { + kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); instrument_atomic_read_write(old, sizeof(*old)); return arch_atomic_long_try_cmpxchg_release(v, old, new); @@ -1688,6 +1801,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) static __always_inline bool atomic_long_sub_and_test(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_sub_and_test(i, v); } @@ -1695,6 +1809,7 @@ atomic_long_sub_and_test(long i, atomic_long_t *v) static __always_inline bool atomic_long_dec_and_test(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_and_test(v); } @@ -1702,6 +1817,7 @@ atomic_long_dec_and_test(atomic_long_t *v) static __always_inline bool atomic_long_inc_and_test(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_and_test(v); } @@ -1709,6 +1825,7 @@ atomic_long_inc_and_test(atomic_long_t *v) static __always_inline bool atomic_long_add_negative(long i, atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_negative(i, v); } @@ -1716,6 +1833,7 @@ atomic_long_add_negative(long i, atomic_long_t *v) static __always_inline long atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_fetch_add_unless(v, a, u); } @@ -1723,6 +1841,7 @@ atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u) static __always_inline bool atomic_long_add_unless(atomic_long_t *v, long a, long u) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_add_unless(v, a, u); } @@ -1730,6 +1849,7 @@ atomic_long_add_unless(atomic_long_t *v, long a, long u) static __always_inline bool atomic_long_inc_not_zero(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_not_zero(v); } @@ -1737,6 +1857,7 @@ atomic_long_inc_not_zero(atomic_long_t *v) static __always_inline bool atomic_long_inc_unless_negative(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_inc_unless_negative(v); } @@ -1744,6 +1865,7 @@ atomic_long_inc_unless_negative(atomic_long_t *v) static __always_inline bool atomic_long_dec_unless_positive(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_unless_positive(v); } @@ -1751,6 +1873,7 @@ atomic_long_dec_unless_positive(atomic_long_t *v) static __always_inline long atomic_long_dec_if_positive(atomic_long_t *v) { + kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); return arch_atomic_long_dec_if_positive(v); } @@ -1758,6 +1881,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define xchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg(__ai_ptr, __VA_ARGS__); \ }) @@ -1772,6 +1896,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define xchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_xchg_release(__ai_ptr, __VA_ARGS__); \ }) @@ -1786,6 +1911,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) @@ -1800,6 +1926,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \ }) @@ -1814,6 +1941,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg64(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \ }) @@ -1828,6 +1956,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg64_release(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \ }) @@ -1843,6 +1972,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \ @@ -1861,6 +1991,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) ({ \ typeof(ptr) __ai_ptr = (ptr); \ typeof(oldp) __ai_oldp = (oldp); \ + kcsan_release(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \ arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \ @@ -1892,6 +2023,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define sync_cmpxchg(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \ arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \ }) @@ -1899,6 +2031,7 @@ atomic_long_dec_if_positive(atomic_long_t *v) #define cmpxchg_double(ptr, ...) \ ({ \ typeof(ptr) __ai_ptr = (ptr); \ + kcsan_mb(); \ instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \ arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \ }) @@ -1912,4 +2045,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) }) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 2a9553f0a9d5619f19151092df5cabbbf16ce835 +// 87c974b93032afd42143613434d1a7788fa598f9 diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh index 035ceb4ee85c..68f902731d01 100755 --- a/scripts/atomic/gen-atomic-instrumented.sh +++ b/scripts/atomic/gen-atomic-instrumented.sh @@ -34,6 +34,14 @@ gen_param_check() gen_params_checks() { local meta="$1"; shift + local order="$1"; shift + + if [ "${order}" = "_release" ]; then + printf "\tkcsan_release();\n" + elif [ -z "${order}" ] && ! meta_in "$meta" "slv"; then + # RMW with return value is fully ordered + printf "\tkcsan_mb();\n" + fi while [ "$#" -gt 0 ]; do gen_param_check "$meta" "$1" @@ -56,7 +64,7 @@ gen_proto_order_variant() local ret="$(gen_ret_type "${meta}" "${int}")" local params="$(gen_params "${int}" "${atomic}" "$@")" - local checks="$(gen_params_checks "${meta}" "$@")" + local checks="$(gen_params_checks "${meta}" "${order}" "$@")" local args="$(gen_args "$@")" local retstmt="$(gen_ret_stmt "${meta}")" @@ -75,29 +83,44 @@ EOF gen_xchg() { local xchg="$1"; shift + local order="$1"; shift local mult="$1"; shift + kcsan_barrier="" + if [ "${xchg%_local}" = "${xchg}" ]; then + case "$order" in + _release) kcsan_barrier="kcsan_release()" ;; + "") kcsan_barrier="kcsan_mb()" ;; + esac + fi + if [ "${xchg%${xchg#try_cmpxchg}}" = "try_cmpxchg" ] ; then cat < Date: Tue, 30 Nov 2021 12:44:32 +0100 Subject: compiler_attributes.h: Add __disable_sanitizer_instrumentation The new attribute maps to __attribute__((disable_sanitizer_instrumentation)), which will be supported by Clang >= 14.0. Future support in GCC is also possible. This attribute disables compiler instrumentation for kernel sanitizer tools, making it easier to implement noinstr. It is different from the existing __no_sanitize* attributes, which may still allow certain types of instrumentation to prevent false positives. Signed-off-by: Alexander Potapenko Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/compiler_attributes.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index b9121afd8733..37e260020221 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -308,6 +308,24 @@ # define __compiletime_warning(msg) #endif +/* + * Optional: only supported since clang >= 14.0 + * + * clang: https://clang.llvm.org/docs/AttributeReference.html#disable-sanitizer-instrumentation + * + * disable_sanitizer_instrumentation is not always similar to + * no_sanitize(()): the latter may still let specific sanitizers + * insert code into functions to prevent false positives. Unlike that, + * disable_sanitizer_instrumentation prevents all kinds of instrumentation to + * functions with the attribute. + */ +#if __has_attribute(disable_sanitizer_instrumentation) +# define __disable_sanitizer_instrumentation \ + __attribute__((disable_sanitizer_instrumentation)) +#else +# define __disable_sanitizer_instrumentation +#endif + /* * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute -- cgit v1.2.3 From bd3d5bd1a0ad386475ea7a3de8a91e7d8a600536 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Tue, 30 Nov 2021 12:44:33 +0100 Subject: kcsan: Support WEAK_MEMORY with Clang where no objtool support exists Clang and GCC behave a little differently when it comes to the __no_sanitize_thread attribute, which has valid reasons, and depending on context either one could be right. Traditionally, user space ThreadSanitizer [1] still expects instrumented builtin atomics (to avoid false positives) and __tsan_func_{entry,exit} (to generate meaningful stack traces), even if the function has the attribute no_sanitize("thread"). [1] https://clang.llvm.org/docs/ThreadSanitizer.html#attribute-no-sanitize-thread GCC doesn't follow the same policy (for better or worse), and removes all kinds of instrumentation if no_sanitize is added. Arguably, since this may be a problem for user space ThreadSanitizer, we expect this may change in future. Since KCSAN != ThreadSanitizer, the likelihood of false positives even without barrier instrumentation everywhere, is much lower by design. At least for Clang, however, to fully remove all sanitizer instrumentation, we must add the disable_sanitizer_instrumentation attribute, which is available since Clang 14.0. Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/compiler_types.h | 13 ++++++++++++- lib/Kconfig.kcsan | 2 +- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 1d32f4c03c9e..3c1795fdb568 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -198,9 +198,20 @@ struct ftrace_likely_data { # define __no_kasan_or_inline __always_inline #endif -#define __no_kcsan __no_sanitize_thread #ifdef __SANITIZE_THREAD__ +/* + * Clang still emits instrumentation for __tsan_func_{entry,exit}() and builtin + * atomics even with __no_sanitize_thread (to avoid false positives in userspace + * ThreadSanitizer). The kernel's requirements are stricter and we really do not + * want any instrumentation with __no_kcsan. + * + * Therefore we add __disable_sanitizer_instrumentation where available to + * disable all instrumentation. See Kconfig.kcsan where this is mandatory. + */ +# define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused +#else +# define __no_kcsan #endif #ifndef __no_sanitize_or_inline diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index e4394ea8068b..63b70b8c5551 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -198,7 +198,7 @@ config KCSAN_WEAK_MEMORY # We can either let objtool nop __tsan_func_{entry,exit}() and builtin # atomics instrumentation in .noinstr.text, or use a compiler that can # implement __no_kcsan to really remove all instrumentation. - depends on STACK_VALIDATION || CC_IS_GCC + depends on STACK_VALIDATION || CC_IS_GCC || CLANG_VERSION >= 140000 help Enable support for modeling a subset of weak memory, which allows detecting a subset of data races due to missing memory barriers. -- cgit v1.2.3 From 80d7476fa20a3cc83f76b3b02a7575891d1e7511 Mon Sep 17 00:00:00 2001 From: Marco Elver Date: Sat, 4 Dec 2021 13:57:03 +0100 Subject: kcsan: Turn barrier instrumentation into macros Some architectures use barriers in 'extern inline' functions, from which we should not refer to static inline functions. For example, building Alpha with gcc and W=1 shows: ./include/asm-generic/barrier.h:70:30: warning: 'kcsan_rmb' is static but used in inline function 'pmd_offset' which is not static 70 | #define smp_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0) | ^~~~~~~~~ ./arch/alpha/include/asm/pgtable.h:293:9: note: in expansion of macro 'smp_rmb' 293 | smp_rmb(); /* see above */ | ^~~~~~~ Which seems to warn about 6.7.4#3 of the C standard: "An inline definition of a function with external linkage shall not contain a definition of a modifiable object with static or thread storage duration, and shall not contain a reference to an identifier with internal linkage." Fix it by turning barrier instrumentation into macros, which matches definitions in . Perhaps we can revert this change in future, when there are no more 'extern inline' users left. Link: https://lkml.kernel.org/r/202112041334.X44uWZXf-lkp@intel.com Reported-by: kernel test robot Signed-off-by: Marco Elver Signed-off-by: Paul E. McKenney --- include/linux/kcsan-checks.h | 24 +++++++++++++----------- 1 file changed, 13 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h index 9d2c869167f2..92f3843d9ebb 100644 --- a/include/linux/kcsan-checks.h +++ b/include/linux/kcsan-checks.h @@ -241,28 +241,30 @@ static inline void __kcsan_disable_current(void) { } * disabled with the __no_kcsan function attribute. * * Also see definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c. + * + * These are all macros, like , since some architectures use them + * in non-static inline functions. */ #define __KCSAN_BARRIER_TO_SIGNAL_FENCE(name) \ - static __always_inline void kcsan_##name(void) \ - { \ + do { \ barrier(); \ __atomic_signal_fence(__KCSAN_BARRIER_TO_SIGNAL_FENCE_##name); \ barrier(); \ - } -__KCSAN_BARRIER_TO_SIGNAL_FENCE(mb) -__KCSAN_BARRIER_TO_SIGNAL_FENCE(wmb) -__KCSAN_BARRIER_TO_SIGNAL_FENCE(rmb) -__KCSAN_BARRIER_TO_SIGNAL_FENCE(release) + } while (0) +#define kcsan_mb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(mb) +#define kcsan_wmb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(wmb) +#define kcsan_rmb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(rmb) +#define kcsan_release() __KCSAN_BARRIER_TO_SIGNAL_FENCE(release) #elif defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__KCSAN_INSTRUMENT_BARRIERS__) #define kcsan_mb __kcsan_mb #define kcsan_wmb __kcsan_wmb #define kcsan_rmb __kcsan_rmb #define kcsan_release __kcsan_release #else /* CONFIG_KCSAN_WEAK_MEMORY && ... */ -static inline void kcsan_mb(void) { } -static inline void kcsan_wmb(void) { } -static inline void kcsan_rmb(void) { } -static inline void kcsan_release(void) { } +#define kcsan_mb() do { } while (0) +#define kcsan_wmb() do { } while (0) +#define kcsan_rmb() do { } while (0) +#define kcsan_release() do { } while (0) #endif /* CONFIG_KCSAN_WEAK_MEMORY && ... */ /** -- cgit v1.2.3 From db67097aa6f2587b44055f2e16db72a11e17faef Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 9 Dec 2021 21:31:56 -0700 Subject: pktdvd: stop using bdi congestion framework. The bdi congestion framework isn't widely used and should be deprecated. pktdvd makes use of it to track congestion, but this can be done entirely internally to pktdvd, so it doesn't need to use the framework. So introduce a "congested" flag. When waiting for bio_queue_size to drop, set this flag and a var_waitqueue() to wait for it. When bio_queue_size does drop and this flag is set, clear the flag and call wake_up_var(). We don't use a wait_var_event macro for the waiting as we need to set the flag and drop the spinlock before calling schedule() and while that is possible with __wait_var_event(), result is not easy to read. Reviewed-by: Christoph Hellwig Signed-off-by: NeilBrown Link: https://lore.kernel.org/r/163910843527.9928.857338663717630212@noble.neil.brown.name Signed-off-by: Jens Axboe --- drivers/block/pktcdvd.c | 31 ++++++++++++++++++++----------- include/linux/pktcdvd.h | 2 ++ 2 files changed, 22 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 887c98d61684..713b7dcf39f9 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -1107,7 +1107,6 @@ static int pkt_handle_queue(struct pktcdvd_device *pd) sector_t zone = 0; /* Suppress gcc warning */ struct pkt_rb_node *node, *first_node; struct rb_node *n; - int wakeup; atomic_set(&pd->scan_queue, 0); @@ -1179,12 +1178,14 @@ try_next_bio: spin_unlock(&pkt->lock); } /* check write congestion marks, and if bio_queue_size is - below, wake up any waiters */ - wakeup = (pd->write_congestion_on > 0 - && pd->bio_queue_size <= pd->write_congestion_off); + * below, wake up any waiters + */ + if (pd->congested && + pd->bio_queue_size <= pd->write_congestion_off) { + pd->congested = false; + wake_up_var(&pd->congested); + } spin_unlock(&pd->lock); - if (wakeup) - clear_bdi_congested(pd->disk->bdi, BLK_RW_ASYNC); pkt->sleep_time = max(PACKET_WAIT_TIME, 1); pkt_set_state(pkt, PACKET_WAITING_STATE); @@ -2356,7 +2357,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) } spin_unlock(&pd->cdrw.active_list_lock); - /* + /* * Test if there is enough room left in the bio work queue * (queue size >= congestion on mark). * If not, wait till the work queue size is below the congestion off mark. @@ -2364,12 +2365,20 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) spin_lock(&pd->lock); if (pd->write_congestion_on > 0 && pd->bio_queue_size >= pd->write_congestion_on) { - set_bdi_congested(bio->bi_bdev->bd_disk->bdi, BLK_RW_ASYNC); - do { + struct wait_bit_queue_entry wqe; + + init_wait_var_entry(&wqe, &pd->congested, 0); + for (;;) { + prepare_to_wait_event(__var_waitqueue(&pd->congested), + &wqe.wq_entry, + TASK_UNINTERRUPTIBLE); + if (pd->bio_queue_size <= pd->write_congestion_off) + break; + pd->congested = true; spin_unlock(&pd->lock); - congestion_wait(BLK_RW_ASYNC, HZ); + schedule(); spin_lock(&pd->lock); - } while(pd->bio_queue_size > pd->write_congestion_off); + } } spin_unlock(&pd->lock); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index 174601554b06..c391e694aa26 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -183,6 +183,8 @@ struct pktcdvd_device spinlock_t lock; /* Serialize access to bio_queue */ struct rb_root bio_queue; /* Work queue of bios we need to handle */ int bio_queue_size; /* Number of nodes in bio_queue */ + bool congested; /* Someone is waiting for bio_queue_size + * to drop. */ sector_t current_sector; /* Keep track of where the elevator is */ atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ /* needs to be run. */ -- cgit v1.2.3 From f95711242390d759f69fd67ad46b31491fe904d6 Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Wed, 8 Dec 2021 17:43:53 +0000 Subject: EDAC: Add RDDR5 and LRDDR5 memory types Include Registered-DDR5 and Load-Reduced DDR5 in the list of memory types. Signed-off-by: Yazen Ghannam Signed-off-by: Borislav Petkov Link: https://lore.kernel.org/r/20211208174356.1997855-2-yazen.ghannam@amd.com --- drivers/edac/edac_mc.c | 2 ++ include/linux/edac.h | 6 ++++++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/edac/edac_mc.c b/drivers/edac/edac_mc.c index 9f82ca295353..9d9aabdec96b 100644 --- a/drivers/edac/edac_mc.c +++ b/drivers/edac/edac_mc.c @@ -162,6 +162,8 @@ const char * const edac_mem_types[] = { [MEM_LPDDR4] = "Low-Power-DDR4-RAM", [MEM_LRDDR4] = "Load-Reduced-DDR4-RAM", [MEM_DDR5] = "Unbuffered-DDR5", + [MEM_RDDR5] = "Registered-DDR5", + [MEM_LRDDR5] = "Load-Reduced-DDR5-RAM", [MEM_NVDIMM] = "Non-volatile-RAM", [MEM_WIO2] = "Wide-IO-2", [MEM_HBM2] = "High-bandwidth-memory-Gen2", diff --git a/include/linux/edac.h b/include/linux/edac.h index 4207d06996a4..e730b3468719 100644 --- a/include/linux/edac.h +++ b/include/linux/edac.h @@ -182,6 +182,8 @@ static inline char *mc_event_error_type(const unsigned int err_type) * @MEM_LRDDR4: Load-Reduced DDR4 memory. * @MEM_LPDDR4: Low-Power DDR4 memory. * @MEM_DDR5: Unbuffered DDR5 RAM + * @MEM_RDDR5: Registered DDR5 RAM + * @MEM_LRDDR5: Load-Reduced DDR5 memory. * @MEM_NVDIMM: Non-volatile RAM * @MEM_WIO2: Wide I/O 2. * @MEM_HBM2: High bandwidth Memory Gen 2. @@ -211,6 +213,8 @@ enum mem_type { MEM_LRDDR4, MEM_LPDDR4, MEM_DDR5, + MEM_RDDR5, + MEM_LRDDR5, MEM_NVDIMM, MEM_WIO2, MEM_HBM2, @@ -239,6 +243,8 @@ enum mem_type { #define MEM_FLAG_LRDDR4 BIT(MEM_LRDDR4) #define MEM_FLAG_LPDDR4 BIT(MEM_LPDDR4) #define MEM_FLAG_DDR5 BIT(MEM_DDR5) +#define MEM_FLAG_RDDR5 BIT(MEM_RDDR5) +#define MEM_FLAG_LRDDR5 BIT(MEM_LRDDR5) #define MEM_FLAG_NVDIMM BIT(MEM_NVDIMM) #define MEM_FLAG_WIO2 BIT(MEM_WIO2) #define MEM_FLAG_HBM2 BIT(MEM_HBM2) -- cgit v1.2.3 From 1614b2b11fab29dd4ff31ebba9d266961f5af69e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 29 Nov 2021 14:28:41 +0000 Subject: arch: Make ARCH_STACKWALK independent of STACKTRACE Make arch_stack_walk() available for ARCH_STACKWALK architectures without it being entangled in STACKTRACE. Link: https://lore.kernel.org/lkml/20211022152104.356586621@infradead.org/ Signed-off-by: Peter Zijlstra (Intel) [Mark: rebase, drop unnecessary arm change] Signed-off-by: Mark Rutland Cc: Albert Ou Cc: Borislav Petkov Cc: Christian Borntraeger Cc: Dave Hansen Cc: Heiko Carstens Cc: Ingo Molnar Cc: Michael Ellerman Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Thomas Gleixner Cc: Vasily Gorbik Link: https://lore.kernel.org/r/20211129142849.3056714-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/stacktrace.c | 4 ---- arch/powerpc/kernel/Makefile | 3 +-- arch/riscv/kernel/stacktrace.c | 4 ---- arch/s390/kernel/Makefile | 3 +-- arch/x86/kernel/Makefile | 2 +- include/linux/stacktrace.h | 35 ++++++++++++++++++----------------- 6 files changed, 21 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 94f83cd44e50..e6ba6b000564 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -221,8 +221,6 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) barrier(); } -#ifdef CONFIG_STACKTRACE - noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) @@ -241,5 +239,3 @@ noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry, walk_stackframe(task, &frame, consume_entry, cookie); } - -#endif diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 5fa68c2ef1f8..b039877c743d 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -47,7 +47,7 @@ obj-y := cputable.o syscalls.o \ udbg.o misc.o io.o misc_$(BITS).o \ of_platform.o prom_parse.o firmware.o \ hw_breakpoint_constraints.o interrupt.o \ - kdebugfs.o + kdebugfs.o stacktrace.o obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o \ paca.o nvram_64.o note.o @@ -116,7 +116,6 @@ obj-$(CONFIG_OPTPROBES) += optprobes.o optprobes_head.o obj-$(CONFIG_KPROBES_ON_FTRACE) += kprobes-ftrace.o obj-$(CONFIG_UPROBES) += uprobes.o obj-$(CONFIG_PPC_UDBG_16550) += legacy_serial.o udbg_16550.o -obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o obj-$(CONFIG_ARCH_HAS_DMA_SET_MASK) += dma-mask.o diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 0fcdc0233fac..201ee206fb57 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -139,12 +139,8 @@ unsigned long __get_wchan(struct task_struct *task) return pc; } -#ifdef CONFIG_STACKTRACE - noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { walk_stackframe(task, regs, consume_entry, cookie); } - -#endif /* CONFIG_STACKTRACE */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 80f500ffb55c..be8007f367aa 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -40,7 +40,7 @@ obj-y += sysinfo.o lgr.o os_info.o machine_kexec.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o -obj-y += smp.o text_amode31.o +obj-y += smp.o text_amode31.o stacktrace.o extra-y += head64.o vmlinux.lds @@ -55,7 +55,6 @@ compat-obj-$(CONFIG_AUDIT) += compat_audit.o obj-$(CONFIG_COMPAT) += compat_linux.o compat_signal.o obj-$(CONFIG_COMPAT) += $(compat-obj-y) obj-$(CONFIG_EARLY_PRINTK) += early_printk.o -obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KPROBES) += kprobes_insn_page.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 2ff3e600f426..6aef9ee28a39 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -84,7 +84,7 @@ obj-$(CONFIG_IA32_EMULATION) += tls.o obj-y += step.o obj-$(CONFIG_INTEL_TXT) += tboot.o obj-$(CONFIG_ISA_DMA_API) += i8237.o -obj-$(CONFIG_STACKTRACE) += stacktrace.o +obj-y += stacktrace.o obj-y += cpu/ obj-y += acpi/ obj-y += reboot.o diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index bef158815e83..97455880ac41 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -8,22 +8,6 @@ struct task_struct; struct pt_regs; -#ifdef CONFIG_STACKTRACE -void stack_trace_print(const unsigned long *trace, unsigned int nr_entries, - int spaces); -int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, - unsigned int nr_entries, int spaces); -unsigned int stack_trace_save(unsigned long *store, unsigned int size, - unsigned int skipnr); -unsigned int stack_trace_save_tsk(struct task_struct *task, - unsigned long *store, unsigned int size, - unsigned int skipnr); -unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, - unsigned int size, unsigned int skipnr); -unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); -unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); - -/* Internal interfaces. Do not use in generic code */ #ifdef CONFIG_ARCH_STACKWALK /** @@ -76,8 +60,25 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, const struct pt_regs *regs); +#endif /* CONFIG_ARCH_STACKWALK */ -#else /* CONFIG_ARCH_STACKWALK */ +#ifdef CONFIG_STACKTRACE +void stack_trace_print(const unsigned long *trace, unsigned int nr_entries, + int spaces); +int stack_trace_snprint(char *buf, size_t size, const unsigned long *entries, + unsigned int nr_entries, int spaces); +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr); +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); +unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries); + +#ifndef CONFIG_ARCH_STACKWALK +/* Internal interfaces. Do not use in generic code */ struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; -- cgit v1.2.3 From 9ba74e6c9e9d0c5c1e5792a7111fc7d1a0589cb8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Dec 2021 23:44:21 -0800 Subject: net: add networking namespace refcount tracker We have 100+ syzbot reports about netns being dismantled too soon, still unresolved as of today. We think a missing get_net() or an extra put_net() is the root cause. In order to find the bug(s), and be able to spot future ones, this patch adds CONFIG_NET_NS_REFCNT_TRACKER and new helpers to precisely pair all put_net() with corresponding get_net(). To use these helpers, each data structure owning a refcount should also use a "netns_tracker" to pair the get and put. Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 9 +-------- include/net/net_namespace.h | 34 ++++++++++++++++++++++++++++++++++ include/net/net_trackers.h | 18 ++++++++++++++++++ net/Kconfig.debug | 9 +++++++++ net/core/net_namespace.c | 3 +++ 5 files changed, 65 insertions(+), 8 deletions(-) create mode 100644 include/net/net_trackers.h (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1a748ee9a421..235d5d082f1a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -48,7 +48,7 @@ #include #include #include -#include +#include struct netpoll_info; struct device; @@ -300,13 +300,6 @@ enum netdev_state_t { __LINK_STATE_TESTING, }; - -#ifdef CONFIG_NET_DEV_REFCNT_TRACKER -typedef struct ref_tracker *netdevice_tracker; -#else -typedef struct {} netdevice_tracker; -#endif - struct gro_list { struct list_head list; int count; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index bb5fa5914032..5b61c462e534 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -34,6 +34,7 @@ #include #include #include +#include #include #include #include @@ -87,6 +88,7 @@ struct net { struct idr netns_ids; struct ns_common ns; + struct ref_tracker_dir refcnt_tracker; struct list_head dev_base_head; struct proc_dir_entry *proc_net; @@ -240,6 +242,7 @@ void ipx_unregister_sysctl(void); #ifdef CONFIG_NET_NS void __put_net(struct net *net); +/* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { refcount_inc(&net->ns.count); @@ -258,6 +261,7 @@ static inline struct net *maybe_get_net(struct net *net) return net; } +/* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->ns.count)) @@ -308,6 +312,36 @@ static inline int check_net(const struct net *net) #endif +static inline void netns_tracker_alloc(struct net *net, + netns_tracker *tracker, gfp_t gfp) +{ +#ifdef CONFIG_NET_NS_REFCNT_TRACKER + ref_tracker_alloc(&net->refcnt_tracker, tracker, gfp); +#endif +} + +static inline void netns_tracker_free(struct net *net, + netns_tracker *tracker) +{ +#ifdef CONFIG_NET_NS_REFCNT_TRACKER + ref_tracker_free(&net->refcnt_tracker, tracker); +#endif +} + +static inline struct net *get_net_track(struct net *net, + netns_tracker *tracker, gfp_t gfp) +{ + get_net(net); + netns_tracker_alloc(net, tracker, gfp); + return net; +} + +static inline void put_net_track(struct net *net, netns_tracker *tracker) +{ + netns_tracker_free(net, tracker); + put_net(net); +} + typedef struct { #ifdef CONFIG_NET_NS struct net *net; diff --git a/include/net/net_trackers.h b/include/net/net_trackers.h new file mode 100644 index 000000000000..d94c76cf15a9 --- /dev/null +++ b/include/net/net_trackers.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NET_TRACKERS_H +#define __NET_NET_TRACKERS_H +#include + +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER +typedef struct ref_tracker *netdevice_tracker; +#else +typedef struct {} netdevice_tracker; +#endif + +#ifdef CONFIG_NET_NS_REFCNT_TRACKER +typedef struct ref_tracker *netns_tracker; +#else +typedef struct {} netns_tracker; +#endif + +#endif /* __NET_NET_TRACKERS_H */ diff --git a/net/Kconfig.debug b/net/Kconfig.debug index fb5c70e01cb3..2f50611df858 100644 --- a/net/Kconfig.debug +++ b/net/Kconfig.debug @@ -8,3 +8,12 @@ config NET_DEV_REFCNT_TRACKER help Enable debugging feature to track device references. This adds memory and cpu costs. + +config NET_NS_REFCNT_TRACKER + bool "Enable networking namespace refcount tracking" + depends on DEBUG_KERNEL && STACKTRACE_SUPPORT + select REF_TRACKER + default n + help + Enable debugging feature to track netns references. + This adds memory and cpu costs. diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 202fa5eacd0f..9b7171c40434 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -311,6 +311,8 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) LIST_HEAD(net_exit_list); refcount_set(&net->ns.count, 1); + ref_tracker_dir_init(&net->refcnt_tracker, 128); + refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); @@ -635,6 +637,7 @@ static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { + ref_tracker_dir_exit(&net->refcnt_tracker); /* Cleanup the network namespace in process context */ if (llist_add(&net->cleanup_list, &cleanup_list)) queue_work(netns_wq, &net_cleanup_work); -- cgit v1.2.3 From 04a931e58d1944ab3d1e11fdfde1947fbe5b6a37 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 9 Dec 2021 23:44:23 -0800 Subject: net: add netns refcount tracker to struct seq_net_private Signed-off-by: Eric Dumazet Signed-off-by: Jakub Kicinski --- fs/proc/proc_net.c | 19 ++++++++++++++++--- include/linux/seq_file_net.h | 3 ++- 2 files changed, 18 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 15c2e55d2ed2..39b823ab2564 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -61,15 +61,27 @@ static int seq_open_net(struct inode *inode, struct file *file) } #ifdef CONFIG_NET_NS p->net = net; + netns_tracker_alloc(net, &p->ns_tracker, GFP_KERNEL); #endif return 0; } +static void seq_file_net_put_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + struct seq_net_private *priv = seq->private; + + put_net_track(priv->net, &priv->ns_tracker); +#else + put_net(&init_net); +#endif +} + static int seq_release_net(struct inode *ino, struct file *f) { struct seq_file *seq = f->private_data; - put_net(seq_file_net(seq)); + seq_file_net_put_net(seq); seq_release_private(ino, f); return 0; } @@ -87,7 +99,8 @@ int bpf_iter_init_seq_net(void *priv_data, struct bpf_iter_aux_info *aux) #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; - p->net = get_net(current->nsproxy->net_ns); + p->net = get_net_track(current->nsproxy->net_ns, &p->ns_tracker, + GFP_KERNEL); #endif return 0; } @@ -97,7 +110,7 @@ void bpf_iter_fini_seq_net(void *priv_data) #ifdef CONFIG_NET_NS struct seq_net_private *p = priv_data; - put_net(p->net); + put_net_track(p->net, &p->ns_tracker); #endif } diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index 0fdbe1ddd8d1..b97912fdbae7 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -9,7 +9,8 @@ extern struct net init_net; struct seq_net_private { #ifdef CONFIG_NET_NS - struct net *net; + struct net *net; + netns_tracker ns_tracker; #endif }; -- cgit v1.2.3 From 65c7cdedeb3026fabcc967a7aae2f755ad4d0783 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 3 Sep 2021 11:24:17 -0400 Subject: genirq: Provide new interfaces for affinity hints The discussion about removing the side effect of irq_set_affinity_hint() of actually applying the cpumask (if not NULL) as affinity to the interrupt, unearthed a few unpleasantries: 1) The modular perf drivers rely on the current behaviour for the very wrong reasons. 2) While none of the other drivers prevents user space from changing the affinity, a cursorily inspection shows that there are at least expectations in some drivers. #1 needs to be cleaned up anyway, so that's not a problem #2 might result in subtle regressions especially when irqbalanced (which nowadays ignores the affinity hint) is disabled. Provide new interfaces: irq_update_affinity_hint() - Only sets the affinity hint pointer irq_set_affinity_and_hint() - Set the pointer and apply the affinity to the interrupt Make irq_set_affinity_hint() a wrapper around irq_apply_affinity_hint() and document it to be phased out. Signed-off-by: Thomas Gleixner Signed-off-by: Nitesh Narayan Lal Signed-off-by: Thomas Gleixner Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20210501021832.743094-1-jesse.brandeburg@intel.com Link: https://lore.kernel.org/r/20210903152430.244937-2-nitesh@redhat.com --- include/linux/interrupt.h | 53 ++++++++++++++++++++++++++++++++++++++++++++++- kernel/irq/manage.c | 8 +++---- 2 files changed, 56 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 1f22a30c0963..9367f1cb2e3c 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -329,7 +329,46 @@ extern int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask); extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); -extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); +extern int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, + bool setaffinity); + +/** + * irq_update_affinity_hint - Update the affinity hint + * @irq: Interrupt to update + * @m: cpumask pointer (NULL to clear the hint) + * + * Updates the affinity hint, but does not change the affinity of the interrupt. + */ +static inline int +irq_update_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + return __irq_apply_affinity_hint(irq, m, false); +} + +/** + * irq_set_affinity_and_hint - Update the affinity hint and apply the provided + * cpumask to the interrupt + * @irq: Interrupt to update + * @m: cpumask pointer (NULL to clear the hint) + * + * Updates the affinity hint and if @m is not NULL it applies it as the + * affinity of that interrupt. + */ +static inline int +irq_set_affinity_and_hint(unsigned int irq, const struct cpumask *m) +{ + return __irq_apply_affinity_hint(irq, m, true); +} + +/* + * Deprecated. Use irq_update_affinity_hint() or irq_set_affinity_and_hint() + * instead. + */ +static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +{ + return irq_set_affinity_and_hint(irq, m); +} + extern int irq_update_affinity_desc(unsigned int irq, struct irq_affinity_desc *affinity); @@ -361,6 +400,18 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } +static inline int irq_update_affinity_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} + +static inline int irq_set_affinity_and_hint(unsigned int irq, + const struct cpumask *m) +{ + return -EINVAL; +} + static inline int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) { diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 7405e384e5ed..f23ffd30385b 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -486,7 +486,8 @@ int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask) } EXPORT_SYMBOL_GPL(irq_force_affinity); -int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) +int __irq_apply_affinity_hint(unsigned int irq, const struct cpumask *m, + bool setaffinity) { unsigned long flags; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL); @@ -495,12 +496,11 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) return -EINVAL; desc->affinity_hint = m; irq_put_desc_unlock(desc, flags); - /* set the initial affinity to prevent every interrupt being on CPU0 */ - if (m) + if (m && setaffinity) __irq_set_affinity(irq, m, false); return 0; } -EXPORT_SYMBOL_GPL(irq_set_affinity_hint); +EXPORT_SYMBOL_GPL(__irq_apply_affinity_hint); static void irq_affinity_notify(struct work_struct *work) { -- cgit v1.2.3 From e4779015fd5d2fb8390c258268addff24d6077c7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 10 Dec 2021 14:46:22 -0800 Subject: timers: implement usleep_idle_range() Patch series "mm/damon: Fix fake /proc/loadavg reports", v3. This patchset fixes DAMON's fake load report issue. The first patch makes yet another variant of usleep_range() for this fix, and the second patch fixes the issue of DAMON by making it using the newly introduced function. This patch (of 2): Some kernel threads such as DAMON could need to repeatedly sleep in micro seconds level. Because usleep_range() sleeps in uninterruptible state, however, such threads would make /proc/loadavg reports fake load. To help such cases, this commit implements a variant of usleep_range() called usleep_idle_range(). It is same to usleep_range() but sets the state of the current task as TASK_IDLE while sleeping. Link: https://lkml.kernel.org/r/20211126145015.15862-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211126145015.15862-2-sj@kernel.org Signed-off-by: SeongJae Park Suggested-by: Andrew Morton Reviewed-by: Thomas Gleixner Tested-by: Oleksandr Natalenko Cc: John Stultz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delay.h | 14 +++++++++++++- kernel/time/timer.c | 16 +++++++++------- 2 files changed, 22 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delay.h b/include/linux/delay.h index 8eacf67eb212..039e7e0c7378 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -20,6 +20,7 @@ */ #include +#include extern unsigned long loops_per_jiffy; @@ -58,7 +59,18 @@ void calibrate_delay(void); void __attribute__((weak)) calibration_delay_done(void); void msleep(unsigned int msecs); unsigned long msleep_interruptible(unsigned int msecs); -void usleep_range(unsigned long min, unsigned long max); +void usleep_range_state(unsigned long min, unsigned long max, + unsigned int state); + +static inline void usleep_range(unsigned long min, unsigned long max) +{ + usleep_range_state(min, max, TASK_UNINTERRUPTIBLE); +} + +static inline void usleep_idle_range(unsigned long min, unsigned long max) +{ + usleep_range_state(min, max, TASK_IDLE); +} static inline void ssleep(unsigned int seconds) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e3d2c23c413d..85f1021ad459 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs) EXPORT_SYMBOL(msleep_interruptible); /** - * usleep_range - Sleep for an approximate time - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep + * usleep_range_state - Sleep for an approximate time in a given state + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range() instead of udelay(). The sleep improves responsiveness + * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ -void __sched usleep_range(unsigned long min, unsigned long max) +void __sched usleep_range_state(unsigned long min, unsigned long max, + unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } -EXPORT_SYMBOL(usleep_range); +EXPORT_SYMBOL(usleep_range_state); -- cgit v1.2.3 From bff8c3848e071d387d8b0784dc91fa49cd563774 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 10 Nov 2021 11:01:03 +0100 Subject: bitfield.h: Fix "type of reg too small for mask" test The test: 'mask > (typeof(_reg))~0ull' only works correctly when both sides are unsigned, consider: - 0xff000000 vs (int)~0ull - 0x000000ff vs (int)~0ull Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20211110101324.950210584@infradead.org --- include/linux/bitfield.h | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h index 4e035aca6f7e..6093fa6db260 100644 --- a/include/linux/bitfield.h +++ b/include/linux/bitfield.h @@ -41,6 +41,22 @@ #define __bf_shf(x) (__builtin_ffsll(x) - 1) +#define __scalar_type_to_unsigned_cases(type) \ + unsigned type: (unsigned type)0, \ + signed type: (unsigned type)0 + +#define __unsigned_scalar_typeof(x) typeof( \ + _Generic((x), \ + char: (unsigned char)0, \ + __scalar_type_to_unsigned_cases(char), \ + __scalar_type_to_unsigned_cases(short), \ + __scalar_type_to_unsigned_cases(int), \ + __scalar_type_to_unsigned_cases(long), \ + __scalar_type_to_unsigned_cases(long long), \ + default: (x))) + +#define __bf_cast_unsigned(type, x) ((__unsigned_scalar_typeof(type))(x)) + #define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx) \ ({ \ BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask), \ @@ -49,7 +65,8 @@ BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ? \ ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \ _pfx "value too large for the field"); \ - BUILD_BUG_ON_MSG((_mask) > (typeof(_reg))~0ull, \ + BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) > \ + __bf_cast_unsigned(_reg, ~0ull), \ _pfx "type of reg too small for mask"); \ __BUILD_BUG_ON_NOT_POWER_OF_2((_mask) + \ (1ULL << __bf_shf(_mask))); \ -- cgit v1.2.3 From 4121485d271bd730537f613ce041e7ea659606a7 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 9 Dec 2021 21:52:31 +0200 Subject: PCI: Sort Intel Device IDs by value MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sort Intel Device IDs by value. [bhelgaas: lower-case Intel section since we're touching it anyway] Link: https://lore.kernel.org/r/20211209195231.2785-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Bjorn Helgaas Reviewed-by: Krzysztof Wilczyński --- include/linux/pci_ids.h | 50 ++++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 011f2f1ea5bb..0d26ab7eb7dc 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -2635,8 +2635,8 @@ #define PCI_DEVICE_ID_INTEL_PXHD_0 0x0320 #define PCI_DEVICE_ID_INTEL_PXHD_1 0x0321 #define PCI_DEVICE_ID_INTEL_PXH_0 0x0329 -#define PCI_DEVICE_ID_INTEL_PXH_1 0x032A -#define PCI_DEVICE_ID_INTEL_PXHV 0x032C +#define PCI_DEVICE_ID_INTEL_PXH_1 0x032a +#define PCI_DEVICE_ID_INTEL_PXHV 0x032c #define PCI_DEVICE_ID_INTEL_80332_0 0x0330 #define PCI_DEVICE_ID_INTEL_80332_1 0x0332 #define PCI_DEVICE_ID_INTEL_80333_0 0x0370 @@ -2654,14 +2654,14 @@ #define PCI_DEVICE_ID_INTEL_MFD_SDIO2 0x0822 #define PCI_DEVICE_ID_INTEL_MFD_EMMC0 0x0823 #define PCI_DEVICE_ID_INTEL_MFD_EMMC1 0x0824 -#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084F -#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095E +#define PCI_DEVICE_ID_INTEL_MRST_SD2 0x084f +#define PCI_DEVICE_ID_INTEL_QUARK_X1000_ILB 0x095e #define PCI_DEVICE_ID_INTEL_I960 0x0960 #define PCI_DEVICE_ID_INTEL_I960RM 0x0962 #define PCI_DEVICE_ID_INTEL_CENTERTON_ILB 0x0c60 #define PCI_DEVICE_ID_INTEL_8257X_SOL 0x1062 #define PCI_DEVICE_ID_INTEL_82573E_SOL 0x1085 -#define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108F +#define PCI_DEVICE_ID_INTEL_82573L_SOL 0x108f #define PCI_DEVICE_ID_INTEL_82815_MC 0x1130 #define PCI_DEVICE_ID_INTEL_82815_CGC 0x1132 #define PCI_DEVICE_ID_INTEL_82092AA_0 0x1221 @@ -2755,12 +2755,6 @@ #define PCI_DEVICE_ID_INTEL_82801EB_11 0x24db #define PCI_DEVICE_ID_INTEL_82801EB_12 0x24dc #define PCI_DEVICE_ID_INTEL_82801EB_13 0x24dd -#define PCI_DEVICE_ID_INTEL_ESB_1 0x25a1 -#define PCI_DEVICE_ID_INTEL_ESB_2 0x25a2 -#define PCI_DEVICE_ID_INTEL_ESB_4 0x25a4 -#define PCI_DEVICE_ID_INTEL_ESB_5 0x25a6 -#define PCI_DEVICE_ID_INTEL_ESB_9 0x25ab -#define PCI_DEVICE_ID_INTEL_ESB_10 0x25ac #define PCI_DEVICE_ID_INTEL_82820_HB 0x2500 #define PCI_DEVICE_ID_INTEL_82820_UP_HB 0x2501 #define PCI_DEVICE_ID_INTEL_82850_HB 0x2530 @@ -2775,14 +2769,15 @@ #define PCI_DEVICE_ID_INTEL_82915G_IG 0x2582 #define PCI_DEVICE_ID_INTEL_82915GM_HB 0x2590 #define PCI_DEVICE_ID_INTEL_82915GM_IG 0x2592 -#define PCI_DEVICE_ID_INTEL_5000_ERR 0x25F0 -#define PCI_DEVICE_ID_INTEL_5000_FBD0 0x25F5 -#define PCI_DEVICE_ID_INTEL_5000_FBD1 0x25F6 -#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 -#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 -#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 -#define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27A0 -#define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27A2 +#define PCI_DEVICE_ID_INTEL_ESB_1 0x25a1 +#define PCI_DEVICE_ID_INTEL_ESB_2 0x25a2 +#define PCI_DEVICE_ID_INTEL_ESB_4 0x25a4 +#define PCI_DEVICE_ID_INTEL_ESB_5 0x25a6 +#define PCI_DEVICE_ID_INTEL_ESB_9 0x25ab +#define PCI_DEVICE_ID_INTEL_ESB_10 0x25ac +#define PCI_DEVICE_ID_INTEL_5000_ERR 0x25f0 +#define PCI_DEVICE_ID_INTEL_5000_FBD0 0x25f5 +#define PCI_DEVICE_ID_INTEL_5000_FBD1 0x25f6 #define PCI_DEVICE_ID_INTEL_ICH6_0 0x2640 #define PCI_DEVICE_ID_INTEL_ICH6_1 0x2641 #define PCI_DEVICE_ID_INTEL_ICH6_2 0x2642 @@ -2794,6 +2789,11 @@ #define PCI_DEVICE_ID_INTEL_ESB2_14 0x2698 #define PCI_DEVICE_ID_INTEL_ESB2_17 0x269b #define PCI_DEVICE_ID_INTEL_ESB2_18 0x269e +#define PCI_DEVICE_ID_INTEL_82945G_HB 0x2770 +#define PCI_DEVICE_ID_INTEL_82945G_IG 0x2772 +#define PCI_DEVICE_ID_INTEL_3000_HB 0x2778 +#define PCI_DEVICE_ID_INTEL_82945GM_HB 0x27a0 +#define PCI_DEVICE_ID_INTEL_82945GM_IG 0x27a2 #define PCI_DEVICE_ID_INTEL_ICH7_0 0x27b8 #define PCI_DEVICE_ID_INTEL_ICH7_1 0x27b9 #define PCI_DEVICE_ID_INTEL_ICH7_30 0x27b0 @@ -2846,7 +2846,7 @@ #define PCI_DEVICE_ID_INTEL_LYNNFIELD_QPI_PHY0 0x2c91 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MCR 0x2c98 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TAD 0x2c99 -#define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST 0x2c9C +#define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_TEST 0x2c9c #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_CTRL 0x2ca0 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_ADDR 0x2ca1 #define PCI_DEVICE_ID_INTEL_LYNNFIELD_MC_CH0_RANK 0x2ca2 @@ -2958,16 +2958,16 @@ #define PCI_DEVICE_ID_INTEL_SBRIDGE_BR 0x3cf5 /* 13.6 */ #define PCI_DEVICE_ID_INTEL_SBRIDGE_SAD1 0x3cf6 /* 12.7 */ #define PCI_DEVICE_ID_INTEL_IOAT_SNB 0x402f -#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 -#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 -#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 -#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 #define PCI_DEVICE_ID_INTEL_5400_ERR 0x4030 #define PCI_DEVICE_ID_INTEL_5400_FBD0 0x4035 #define PCI_DEVICE_ID_INTEL_5400_FBD1 0x4036 -#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_EP80579_0 0x5031 #define PCI_DEVICE_ID_INTEL_EP80579_1 0x5032 +#define PCI_DEVICE_ID_INTEL_5100_16 0x65f0 +#define PCI_DEVICE_ID_INTEL_5100_19 0x65f3 +#define PCI_DEVICE_ID_INTEL_5100_21 0x65f5 +#define PCI_DEVICE_ID_INTEL_5100_22 0x65f6 +#define PCI_DEVICE_ID_INTEL_IOAT_SCNB 0x65ff #define PCI_DEVICE_ID_INTEL_82371SB_0 0x7000 #define PCI_DEVICE_ID_INTEL_82371SB_1 0x7010 #define PCI_DEVICE_ID_INTEL_82371SB_2 0x7020 -- cgit v1.2.3 From c5fb19937455095573a19ddcbff32e993ed10e35 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 10 Dec 2021 22:16:49 +0800 Subject: bpf: Add bpf_strncmp helper The helper compares two strings: one string is a null-terminated read-only string, and another string has const max storage size but doesn't need to be null-terminated. It can be used to compare file name in tracing or LSM program. Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211210141652.877186-2-houtao1@huawei.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++++ kernel/bpf/helpers.c | 16 ++++++++++++++++ tools/include/uapi/linux/bpf.h | 11 +++++++++++ 4 files changed, 39 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0ceb54c6342f..7a40022e3d00 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2163,6 +2163,7 @@ extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; +extern const struct bpf_func_proto bpf_strncmp_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c26871263f1f..2820c77e4846 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4983,6 +4983,16 @@ union bpf_attr { * Return * The number of loops performed, **-EINVAL** for invalid **flags**, * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5167,6 +5177,7 @@ union bpf_attr { FN(kallsyms_lookup_name), \ FN(find_vma), \ FN(loop), \ + FN(strncmp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 19fecfeaa9c2..8babae03d30a 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -565,6 +565,20 @@ const struct bpf_func_proto bpf_strtoul_proto = { }; #endif +BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2) +{ + return strncmp(s1, s2, s1_sz); +} + +const struct bpf_func_proto bpf_strncmp_proto = { + .func = bpf_strncmp, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_CONST_STR, +}; + BPF_CALL_4(bpf_get_ns_current_pid_tgid, u64, dev, u64, ino, struct bpf_pidns_info *, nsdata, u32, size) { @@ -1378,6 +1392,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_for_each_map_elem_proto; case BPF_FUNC_loop: return &bpf_loop_proto; + case BPF_FUNC_strncmp: + return &bpf_strncmp_proto; default: break; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c26871263f1f..2820c77e4846 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4983,6 +4983,16 @@ union bpf_attr { * Return * The number of loops performed, **-EINVAL** for invalid **flags**, * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5167,6 +5177,7 @@ union bpf_attr { FN(kallsyms_lookup_name), \ FN(find_vma), \ FN(loop), \ + FN(strncmp), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 35d976802124303a5b3eb7ec3ed188d568204373 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:38 +0200 Subject: net: dsa: tag_ocelot: convert to tagger-owned data The felix driver makes very light use of dp->priv, and the tagger is effectively stateless. dp->priv is practically only needed to set up a callback to perform deferred xmit of PTP and STP packets using the ocelot-8021q tagging protocol (the main ocelot tagging protocol makes no use of dp->priv, although this driver sets up dp->priv irrespective of actual tagging protocol in use). struct felix_port (what used to be pointed to by dp->priv) is removed and replaced with a two-sided structure. The public side of this structure, visible to the switch driver, is ocelot_8021q_tagger_data. The private side is ocelot_8021q_tagger_private, and the latter structure physically encapsulates the former. The public half of the tagger data structure can be accessed through a helper of the same name (ocelot_8021q_tagger_data) which also sanity-checks the protocol currently in use by the switch. The public/private split was requested by Andrew Lunn. Suggested-by: Andrew Lunn Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 64 ++++++++---------------------------- include/linux/dsa/ocelot.h | 12 +++++-- net/dsa/tag_ocelot_8021q.c | 73 ++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 94 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index a02fec33552d..f4fc403fbc1e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1155,38 +1155,22 @@ static void felix_port_deferred_xmit(struct kthread_work *work) kfree(xmit_work); } -static int felix_port_setup_tagger_data(struct dsa_switch *ds, int port) +static int felix_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) { - struct dsa_port *dp = dsa_to_port(ds, port); - struct ocelot *ocelot = ds->priv; - struct felix *felix = ocelot_to_felix(ocelot); - struct felix_port *felix_port; + struct ocelot_8021q_tagger_data *tagger_data; - if (!dsa_port_is_user(dp)) + switch (proto) { + case DSA_TAG_PROTO_OCELOT_8021Q: + tagger_data = ocelot_8021q_tagger_data(ds); + tagger_data->xmit_work_fn = felix_port_deferred_xmit; return 0; - - felix_port = kzalloc(sizeof(*felix_port), GFP_KERNEL); - if (!felix_port) - return -ENOMEM; - - felix_port->xmit_worker = felix->xmit_worker; - felix_port->xmit_work_fn = felix_port_deferred_xmit; - - dp->priv = felix_port; - - return 0; -} - -static void felix_port_teardown_tagger_data(struct dsa_switch *ds, int port) -{ - struct dsa_port *dp = dsa_to_port(ds, port); - struct felix_port *felix_port = dp->priv; - - if (!felix_port) - return; - - dp->priv = NULL; - kfree(felix_port); + case DSA_TAG_PROTO_OCELOT: + case DSA_TAG_PROTO_SEVILLE: + return 0; + default: + return -EPROTONOSUPPORT; + } } /* Hardware initialization done here so that we can allocate structures with @@ -1217,12 +1201,6 @@ static int felix_setup(struct dsa_switch *ds) } } - felix->xmit_worker = kthread_create_worker(0, "felix_xmit"); - if (IS_ERR(felix->xmit_worker)) { - err = PTR_ERR(felix->xmit_worker); - goto out_deinit_timestamp; - } - for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) continue; @@ -1233,14 +1211,6 @@ static int felix_setup(struct dsa_switch *ds) * bits of vlan tag. */ felix_port_qos_map_init(ocelot, port); - - err = felix_port_setup_tagger_data(ds, port); - if (err) { - dev_err(ds->dev, - "port %d failed to set up tagger data: %pe\n", - port, ERR_PTR(err)); - goto out_deinit_ports; - } } err = ocelot_devlink_sb_register(ocelot); @@ -1268,13 +1238,9 @@ out_deinit_ports: if (dsa_is_unused_port(ds, port)) continue; - felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } - kthread_destroy_worker(felix->xmit_worker); - -out_deinit_timestamp: ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1303,12 +1269,9 @@ static void felix_teardown(struct dsa_switch *ds) if (dsa_is_unused_port(ds, port)) continue; - felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } - kthread_destroy_worker(felix->xmit_worker); - ocelot_devlink_sb_unregister(ocelot); ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1648,6 +1611,7 @@ felix_mrp_del_ring_role(struct dsa_switch *ds, int port, const struct dsa_switch_ops felix_switch_ops = { .get_tag_protocol = felix_get_tag_protocol, .change_tag_protocol = felix_change_tag_protocol, + .connect_tag_protocol = felix_connect_tag_protocol, .setup = felix_setup, .teardown = felix_teardown, .set_ageing_time = felix_set_ageing_time, diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 7ee708ad7df2..dca2969015d8 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -8,6 +8,7 @@ #include #include #include +#include struct ocelot_skb_cb { struct sk_buff *clone; @@ -168,11 +169,18 @@ struct felix_deferred_xmit_work { struct kthread_work work; }; -struct felix_port { +struct ocelot_8021q_tagger_data { void (*xmit_work_fn)(struct kthread_work *work); - struct kthread_worker *xmit_worker; }; +static inline struct ocelot_8021q_tagger_data * +ocelot_8021q_tagger_data(struct dsa_switch *ds) +{ + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_OCELOT_8021Q); + + return ds->tagger_data; +} + static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) { packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index a1919ea5e828..fe451f4de7ba 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -12,25 +12,39 @@ #include #include "dsa_priv.h" +struct ocelot_8021q_tagger_private { + struct ocelot_8021q_tagger_data data; /* Must be first */ + struct kthread_worker *xmit_worker; +}; + static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { + struct ocelot_8021q_tagger_private *priv = dp->ds->tagger_data; + struct ocelot_8021q_tagger_data *data = &priv->data; + void (*xmit_work_fn)(struct kthread_work *work); struct felix_deferred_xmit_work *xmit_work; - struct felix_port *felix_port = dp->priv; + struct kthread_worker *xmit_worker; + + xmit_work_fn = data->xmit_work_fn; + xmit_worker = priv->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); if (!xmit_work) return NULL; /* Calls felix_port_deferred_xmit in felix.c */ - kthread_init_work(&xmit_work->work, felix_port->xmit_work_fn); + kthread_init_work(&xmit_work->work, xmit_work_fn); /* Increase refcount so the kfree_skb in dsa_slave_xmit * won't really free the packet. */ xmit_work->dp = dp; xmit_work->skb = skb_get(skb); - kthread_queue_work(felix_port->xmit_worker, &xmit_work->work); + kthread_queue_work(xmit_worker, &xmit_work->work); return NULL; } @@ -67,11 +81,64 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, return skb; } +static void ocelot_disconnect(struct dsa_switch_tree *dst) +{ + struct ocelot_8021q_tagger_private *priv; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + priv = dp->ds->tagger_data; + + if (!priv) + continue; + + if (priv->xmit_worker) + kthread_destroy_worker(priv->xmit_worker); + + kfree(priv); + dp->ds->tagger_data = NULL; + } +} + +static int ocelot_connect(struct dsa_switch_tree *dst) +{ + struct ocelot_8021q_tagger_private *priv; + struct dsa_port *dp; + int err; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->tagger_data) + continue; + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto out; + } + + priv->xmit_worker = kthread_create_worker(0, "felix_xmit"); + if (IS_ERR(priv->xmit_worker)) { + err = PTR_ERR(priv->xmit_worker); + goto out; + } + + dp->ds->tagger_data = priv; + } + + return 0; + +out: + ocelot_disconnect(dst); + return err; +} + static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .name = "ocelot-8021q", .proto = DSA_TAG_PROTO_OCELOT_8021Q, .xmit = ocelot_xmit, .rcv = ocelot_rcv, + .connect = ocelot_connect, + .disconnect = ocelot_disconnect, .needed_headroom = VLAN_HLEN, .promisc_on_master = true, }; -- cgit v1.2.3 From d38049bbe7601f38d598f5da5ff09980483b290a Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:40 +0200 Subject: net: dsa: sja1105: bring deferred xmit implementation in line with ocelot-8021q When the ocelot-8021q driver was converted to deferred xmit as part of commit 8d5f7954b7c8 ("net: dsa: felix: break at first CPU port during init and teardown"), the deferred implementation was deliberately made subtly different from what sja1105 has. The implementation differences lied on the following observations: - There might be a race between these two lines in tag_sja1105.c: skb_queue_tail(&sp->xmit_queue, skb_get(skb)); kthread_queue_work(sp->xmit_worker, &sp->xmit_work); and the skb dequeue logic in sja1105_port_deferred_xmit(). For example, the xmit_work might be already queued, however the work item has just finished walking through the skb queue. Because we don't check the return code from kthread_queue_work, we don't do anything if the work item is already queued. However, nobody will take that skb and send it, at least until the next timestampable skb is sent. This creates additional (and avoidable) TX timestamping latency. To close that race, what the ocelot-8021q driver does is it doesn't keep a single work item per port, and a skb timestamping queue, but rather dynamically allocates a work item per packet. - It is also unnecessary to have more than one kthread that does the work. So delete the per-port kthread allocations and replace them with a single kthread which is global to the switch. This change brings the two implementations in line by applying those observations to the sja1105 driver as well. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 77 ++++++++++++++-------------------- include/linux/dsa/sja1105.h | 11 +++-- net/dsa/tag_sja1105.c | 21 ++++++++-- 3 files changed, 57 insertions(+), 52 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index f7c88da377e4..c21822bb6834 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2675,10 +2675,8 @@ static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, return NETDEV_TX_OK; } -#define work_to_port(work) \ - container_of((work), struct sja1105_port, xmit_work) -#define tagger_to_sja1105(t) \ - container_of((t), struct sja1105_private, tagger_data) +#define work_to_xmit_work(w) \ + container_of((w), struct sja1105_deferred_xmit_work, work) /* Deferred work is unfortunately necessary because setting up the management * route cannot be done from atomit context (SPI transfer takes a sleepable @@ -2686,25 +2684,25 @@ static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, */ static void sja1105_port_deferred_xmit(struct kthread_work *work) { - struct sja1105_port *sp = work_to_port(work); - struct sja1105_tagger_data *tagger_data = sp->data; - struct sja1105_private *priv = tagger_to_sja1105(tagger_data); - int port = sp - priv->ports; - struct sk_buff *skb; + struct sja1105_deferred_xmit_work *xmit_work = work_to_xmit_work(work); + struct sk_buff *clone, *skb = xmit_work->skb; + struct dsa_switch *ds = xmit_work->dp->ds; + struct sja1105_private *priv = ds->priv; + int port = xmit_work->dp->index; - while ((skb = skb_dequeue(&sp->xmit_queue)) != NULL) { - struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + clone = SJA1105_SKB_CB(skb)->clone; - mutex_lock(&priv->mgmt_lock); + mutex_lock(&priv->mgmt_lock); - sja1105_mgmt_xmit(priv->ds, port, 0, skb, !!clone); + sja1105_mgmt_xmit(ds, port, 0, skb, !!clone); - /* The clone, if there, was made by dsa_skb_tx_timestamp */ - if (clone) - sja1105_ptp_txtstamp_skb(priv->ds, port, clone); + /* The clone, if there, was made by dsa_skb_tx_timestamp */ + if (clone) + sja1105_ptp_txtstamp_skb(ds, port, clone); - mutex_unlock(&priv->mgmt_lock); - } + mutex_unlock(&priv->mgmt_lock); + + kfree(xmit_work); } /* The MAXAGE setting belongs to the L2 Forwarding Parameters table, @@ -3009,54 +3007,43 @@ static int sja1105_port_bridge_flags(struct dsa_switch *ds, int port, static void sja1105_teardown_ports(struct sja1105_private *priv) { - struct dsa_switch *ds = priv->ds; - int port; - - for (port = 0; port < ds->num_ports; port++) { - struct sja1105_port *sp = &priv->ports[port]; + struct sja1105_tagger_data *tagger_data = &priv->tagger_data; - if (sp->xmit_worker) - kthread_destroy_worker(sp->xmit_worker); - } + kthread_destroy_worker(tagger_data->xmit_worker); } static int sja1105_setup_ports(struct sja1105_private *priv) { struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct dsa_switch *ds = priv->ds; - int port, rc; + struct kthread_worker *worker; + int port; + + worker = kthread_create_worker(0, "dsa%d:%d_xmit", ds->dst->index, + ds->index); + if (IS_ERR(worker)) { + dev_err(ds->dev, + "failed to create deferred xmit thread: %pe\n", + worker); + return PTR_ERR(worker); + } + + tagger_data->xmit_worker = worker; + tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; /* Connections between dsa_port and sja1105_port */ for (port = 0; port < ds->num_ports; port++) { struct sja1105_port *sp = &priv->ports[port]; struct dsa_port *dp = dsa_to_port(ds, port); - struct kthread_worker *worker; - struct net_device *slave; if (!dsa_port_is_user(dp)) continue; dp->priv = sp; sp->data = tagger_data; - slave = dp->slave; - kthread_init_work(&sp->xmit_work, sja1105_port_deferred_xmit); - worker = kthread_create_worker(0, "%s_xmit", slave->name); - if (IS_ERR(worker)) { - rc = PTR_ERR(worker); - dev_err(ds->dev, - "failed to create deferred xmit thread: %d\n", - rc); - goto out_destroy_workers; - } - sp->xmit_worker = worker; - skb_queue_head_init(&sp->xmit_queue); } return 0; - -out_destroy_workers: - sja1105_teardown_ports(priv); - return rc; } /* The programming model for the SJA1105 switch is "all-at-once" via static diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e6c78be40bde..acd9d2afccab 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -37,6 +37,12 @@ #define SJA1105_HWTS_RX_EN 0 +struct sja1105_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + /* Global tagger data: each struct sja1105_port has a reference to * the structure defined in struct sja1105_private. */ @@ -52,6 +58,8 @@ struct sja1105_tagger_data { * 2-step TX timestamps */ struct sk_buff_head skb_txtstamp_queue; + struct kthread_worker *xmit_worker; + void (*xmit_work_fn)(struct kthread_work *work); }; struct sja1105_skb_cb { @@ -65,9 +73,6 @@ struct sja1105_skb_cb { ((struct sja1105_skb_cb *)((skb)->cb)) struct sja1105_port { - struct kthread_worker *xmit_worker; - struct kthread_work xmit_work; - struct sk_buff_head xmit_queue; struct sja1105_tagger_data *data; bool hwts_tx_en; }; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 6c293c2a3008..7008952b6c1d 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -125,16 +125,29 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { + void (*xmit_work_fn)(struct kthread_work *work); + struct sja1105_deferred_xmit_work *xmit_work; struct sja1105_port *sp = dp->priv; + struct kthread_worker *xmit_worker; - if (!dsa_port_is_sja1105(dp)) - return skb; + xmit_work_fn = sp->data->xmit_work_fn; + xmit_worker = sp->data->xmit_worker; + + if (!xmit_work_fn || !xmit_worker) + return NULL; + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + kthread_init_work(&xmit_work->work, xmit_work_fn); /* Increase refcount so the kfree_skb in dsa_slave_xmit * won't really free the packet. */ - skb_queue_tail(&sp->xmit_queue, skb_get(skb)); - kthread_queue_work(sp->xmit_worker, &sp->xmit_work); + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(xmit_worker, &xmit_work->work); return NULL; } -- cgit v1.2.3 From 6f6770ab1ce2b56619264ec6be0b62f05564dcf6 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:41 +0200 Subject: net: dsa: sja1105: remove hwts_tx_en from tagger data This tagger property is in fact not used at all by the tagger, only by the switch driver. Therefore it makes sense to be moved to sja1105_private. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 1 + drivers/net/dsa/sja1105/sja1105_ptp.c | 9 ++++----- include/linux/dsa/sja1105.h | 1 - 3 files changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 21dba16af097..b0612c763ec0 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -249,6 +249,7 @@ struct sja1105_private { bool fixed_link[SJA1105_MAX_NUM_PORTS]; unsigned long ucast_egress_floods; unsigned long bcast_egress_floods; + unsigned long hwts_tx_en; const struct sja1105_info *info; size_t max_xfer_len; struct spi_device *spidev; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 54396992a919..b97bd4d948f5 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -98,10 +98,10 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) switch (config.tx_type) { case HWTSTAMP_TX_OFF: - priv->ports[port].hwts_tx_en = false; + priv->hwts_tx_en &= ~BIT(port); break; case HWTSTAMP_TX_ON: - priv->ports[port].hwts_tx_en = true; + priv->hwts_tx_en |= BIT(port); break; default: return -ERANGE; @@ -140,7 +140,7 @@ int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr) struct hwtstamp_config config; config.flags = 0; - if (priv->ports[port].hwts_tx_en) + if (priv->hwts_tx_en & BIT(port)) config.tx_type = HWTSTAMP_TX_ON; else config.tx_type = HWTSTAMP_TX_OFF; @@ -486,10 +486,9 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) void sja1105_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sja1105_private *priv = ds->priv; - struct sja1105_port *sp = &priv->ports[port]; struct sk_buff *clone; - if (!sp->hwts_tx_en) + if (!(priv->hwts_tx_en & BIT(port))) return; clone = skb_clone_sk(skb); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index acd9d2afccab..32a8a1344cf6 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -74,7 +74,6 @@ struct sja1105_skb_cb { struct sja1105_port { struct sja1105_tagger_data *data; - bool hwts_tx_en; }; /* Timestamps are in units of 8 ns clock ticks (equivalent to -- cgit v1.2.3 From bfcf1425222008e7390c0784b0f3bb7b497fccaa Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:42 +0200 Subject: net: dsa: sja1105: make dp->priv point directly to sja1105_tagger_data The design of the sja1105 tagger dp->priv is that each port has a separate struct sja1105_port, and the sp->data pointer points to a common struct sja1105_tagger_data. We have removed all per-port members accessible by the tagger, and now only struct sja1105_tagger_data remains. Make dp->priv point directly to this. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 1 - drivers/net/dsa/sja1105/sja1105_main.c | 15 +++-------- drivers/net/dsa/sja1105/sja1105_ptp.c | 14 +++++----- include/linux/dsa/sja1105.h | 8 +----- net/dsa/tag_sja1105.c | 48 ++++++++++++++++++---------------- 5 files changed, 37 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index b0612c763ec0..6ef6fb4f30e6 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -257,7 +257,6 @@ struct sja1105_private { u16 bridge_pvid[SJA1105_MAX_NUM_PORTS]; u16 tag_8021q_pvid[SJA1105_MAX_NUM_PORTS]; struct sja1105_flow_block flow_block; - struct sja1105_port ports[SJA1105_MAX_NUM_PORTS]; /* Serializes transmission of management frames so that * the switch doesn't confuse them with one another. */ diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index c21822bb6834..e7a6cc7f681c 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3017,7 +3017,7 @@ static int sja1105_setup_ports(struct sja1105_private *priv) struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct dsa_switch *ds = priv->ds; struct kthread_worker *worker; - int port; + struct dsa_port *dp; worker = kthread_create_worker(0, "dsa%d:%d_xmit", ds->dst->index, ds->index); @@ -3031,17 +3031,8 @@ static int sja1105_setup_ports(struct sja1105_private *priv) tagger_data->xmit_worker = worker; tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; - /* Connections between dsa_port and sja1105_port */ - for (port = 0; port < ds->num_ports; port++) { - struct sja1105_port *sp = &priv->ports[port]; - struct dsa_port *dp = dsa_to_port(ds, port); - - if (!dsa_port_is_user(dp)) - continue; - - dp->priv = sp; - sp->data = tagger_data; - } + dsa_switch_for_each_user_port(dp, ds) + dp->priv = tagger_data; return 0; } diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index b97bd4d948f5..9077067328c2 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -461,22 +461,24 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct sja1105_private *priv = ds->priv; - struct sja1105_port *sp = &priv->ports[port]; + struct sja1105_tagger_data *tagger_data; u8 ts_id; + tagger_data = &priv->tagger_data; + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - spin_lock(&sp->data->meta_lock); + spin_lock(&tagger_data->meta_lock); - ts_id = sp->data->ts_id; + ts_id = tagger_data->ts_id; /* Deal automatically with 8-bit wraparound */ - sp->data->ts_id++; + tagger_data->ts_id++; SJA1105_SKB_CB(clone)->ts_id = ts_id; - spin_unlock(&sp->data->meta_lock); + spin_unlock(&tagger_data->meta_lock); - skb_queue_tail(&sp->data->skb_txtstamp_queue, clone); + skb_queue_tail(&tagger_data->skb_txtstamp_queue, clone); } /* Called from dsa_skb_tx_timestamp. This callback is just to clone diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 32a8a1344cf6..1dda9cce85d9 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -43,9 +43,7 @@ struct sja1105_deferred_xmit_work { struct kthread_work work; }; -/* Global tagger data: each struct sja1105_port has a reference to - * the structure defined in struct sja1105_private. - */ +/* Global tagger data */ struct sja1105_tagger_data { struct sk_buff *stampable_skb; /* Protects concurrent access to the meta state machine @@ -72,10 +70,6 @@ struct sja1105_skb_cb { #define SJA1105_SKB_CB(skb) \ ((struct sja1105_skb_cb *)((skb)->cb)) -struct sja1105_port { - struct sja1105_tagger_data *data; -}; - /* Timestamps are in units of 8 ns clock ticks (equivalent to * a fixed 125 MHz clock). */ diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 7008952b6c1d..fc2af71b965c 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -125,13 +125,13 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { + struct sja1105_tagger_data *tagger_data = dp->priv; void (*xmit_work_fn)(struct kthread_work *work); struct sja1105_deferred_xmit_work *xmit_work; - struct sja1105_port *sp = dp->priv; struct kthread_worker *xmit_worker; - xmit_work_fn = sp->data->xmit_work_fn; - xmit_worker = sp->data->xmit_worker; + xmit_work_fn = tagger_data->xmit_work_fn; + xmit_worker = tagger_data->xmit_worker; if (!xmit_work_fn || !xmit_worker) return NULL; @@ -368,32 +368,32 @@ static struct sk_buff */ if (is_link_local) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; + struct sja1105_tagger_data *tagger_data = dp->priv; if (unlikely(!dsa_port_is_sja1105(dp))) return skb; - if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) /* Do normal processing. */ return skb; - spin_lock(&sp->data->meta_lock); + spin_lock(&tagger_data->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? */ - if (sp->data->stampable_skb) { + if (tagger_data->stampable_skb) { dev_err_ratelimited(dp->ds->dev, "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); - kfree_skb(sp->data->stampable_skb); + kfree_skb(tagger_data->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv * from freeing the skb. */ - sp->data->stampable_skb = skb_get(skb); - spin_unlock(&sp->data->meta_lock); + tagger_data->stampable_skb = skb_get(skb); + spin_unlock(&tagger_data->meta_lock); /* Tell DSA we got nothing */ return NULL; @@ -406,7 +406,7 @@ static struct sk_buff */ } else if (is_meta) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_port *sp = dp->priv; + struct sja1105_tagger_data *tagger_data = dp->priv; struct sk_buff *stampable_skb; if (unlikely(!dsa_port_is_sja1105(dp))) @@ -415,13 +415,13 @@ static struct sk_buff /* Drop the meta frame if we're not in the right state * to process it. */ - if (!test_bit(SJA1105_HWTS_RX_EN, &sp->data->state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) return NULL; - spin_lock(&sp->data->meta_lock); + spin_lock(&tagger_data->meta_lock); - stampable_skb = sp->data->stampable_skb; - sp->data->stampable_skb = NULL; + stampable_skb = tagger_data->stampable_skb; + tagger_data->stampable_skb = NULL; /* Was this a meta frame instead of the link-local * that we were expecting? @@ -429,14 +429,14 @@ static struct sk_buff if (!stampable_skb) { dev_err_ratelimited(dp->ds->dev, "Unexpected meta frame\n"); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&tagger_data->meta_lock); return NULL; } if (stampable_skb->dev != skb->dev) { dev_err_ratelimited(dp->ds->dev, "Meta frame on wrong port\n"); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&tagger_data->meta_lock); return NULL; } @@ -447,7 +447,7 @@ static struct sk_buff skb = stampable_skb; sja1105_transfer_meta(skb, meta); - spin_unlock(&sp->data->meta_lock); + spin_unlock(&tagger_data->meta_lock); } return skb; @@ -545,8 +545,8 @@ static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, { struct sk_buff *skb, *skb_tmp, *skb_match = NULL; struct dsa_port *dp = dsa_to_port(ds, port); + struct sja1105_tagger_data *tagger_data; struct skb_shared_hwtstamps shwt = {0}; - struct sja1105_port *sp = dp->priv; if (!dsa_port_is_sja1105(dp)) return; @@ -555,19 +555,21 @@ static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, if (dir == SJA1110_META_TSTAMP_RX) return; - spin_lock(&sp->data->skb_txtstamp_queue.lock); + tagger_data = dp->priv; - skb_queue_walk_safe(&sp->data->skb_txtstamp_queue, skb, skb_tmp) { + spin_lock(&tagger_data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&tagger_data->skb_txtstamp_queue, skb, skb_tmp) { if (SJA1105_SKB_CB(skb)->ts_id != ts_id) continue; - __skb_unlink(skb, &sp->data->skb_txtstamp_queue); + __skb_unlink(skb, &tagger_data->skb_txtstamp_queue); skb_match = skb; break; } - spin_unlock(&sp->data->skb_txtstamp_queue.lock); + spin_unlock(&tagger_data->skb_txtstamp_queue.lock); if (WARN_ON(!skb_match)) return; -- cgit v1.2.3 From 22ee9f8e4011fb8a6d75dc2f9a43360d4f400235 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:43 +0200 Subject: net: dsa: sja1105: move ts_id from sja1105_tagger_data The TX timestamp ID is incremented by the SJA1110 PTP timestamping callback (->port_tx_timestamp) for every packet, when cloning it. It isn't used by the tagger at all, even though it sits inside the struct sja1105_tagger_data. Also, serialization to this structure is currently done through tagger_data->meta_lock, which is a cheap hack because the meta_lock isn't used for anything else on SJA1110 (sja1105_rcv_meta_state_machine isn't called). This change moves ts_id from sja1105_tagger_data to sja1105_private and introduces a dedicated spinlock for it, also in sja1105_private. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 3 +++ drivers/net/dsa/sja1105/sja1105_main.c | 1 + drivers/net/dsa/sja1105/sja1105_ptp.c | 8 ++++---- include/linux/dsa/sja1105.h | 1 - 4 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 6ef6fb4f30e6..850a7d3e69bb 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -261,6 +261,9 @@ struct sja1105_private { * the switch doesn't confuse them with one another. */ struct mutex mgmt_lock; + /* PTP two-step TX timestamp ID, and its serialization lock */ + spinlock_t ts_id_lock; + u8 ts_id; /* Serializes access to the dynamic config interface */ struct mutex dynamic_config_lock; struct devlink_region **regions; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index e7a6cc7f681c..880f28ea184f 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3348,6 +3348,7 @@ static int sja1105_probe(struct spi_device *spi) mutex_init(&priv->ptp_data.lock); mutex_init(&priv->dynamic_config_lock); mutex_init(&priv->mgmt_lock); + spin_lock_init(&priv->ts_id_lock); rc = sja1105_parse_dt(priv); if (rc < 0) { diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 9077067328c2..0904ab10bd2f 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -468,15 +468,15 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - spin_lock(&tagger_data->meta_lock); + spin_lock(&priv->ts_id_lock); - ts_id = tagger_data->ts_id; + ts_id = priv->ts_id; /* Deal automatically with 8-bit wraparound */ - tagger_data->ts_id++; + priv->ts_id++; SJA1105_SKB_CB(clone)->ts_id = ts_id; - spin_unlock(&tagger_data->meta_lock); + spin_unlock(&priv->ts_id_lock); skb_queue_tail(&tagger_data->skb_txtstamp_queue, clone); } diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 1dda9cce85d9..d8ee53085c09 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -51,7 +51,6 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; - u8 ts_id; /* Used on SJA1110 where meta frames are generated only for * 2-step TX timestamps */ -- cgit v1.2.3 From c79e84866d2ac637fce921a28288f214e91d662b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:44 +0200 Subject: net: dsa: tag_sja1105: convert to tagger-owned data Currently, struct sja1105_tagger_data is a part of struct sja1105_private, and is used by the sja1105 driver to populate dp->priv. With the movement towards tagger-owned storage, the sja1105 driver should not be the owner of this memory. This change implements the connection between the sja1105 switch driver and its tagging protocol, which means that sja1105_tagger_data no longer stays in dp->priv but in ds->tagger_data, and that the sja1105 driver now only populates the sja1105_port_deferred_xmit callback pointer. The kthread worker is now the responsibility of the tagger. The sja1105 driver also alters the tagger's state some more, especially with regard to the PTP RX timestamping state. This will be fixed up a bit in further changes. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105.h | 1 - drivers/net/dsa/sja1105/sja1105_main.c | 54 ++++++-------------- drivers/net/dsa/sja1105/sja1105_ptp.c | 35 ++++++------- include/linux/dsa/sja1105.h | 7 ++- net/dsa/tag_sja1105.c | 90 +++++++++++++++++++++++++++------- 5 files changed, 110 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index 850a7d3e69bb..9ba2ec2b966d 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -272,7 +272,6 @@ struct sja1105_private { struct mii_bus *mdio_base_tx; struct mii_bus *mdio_pcs; struct dw_xpcs *xpcs[SJA1105_MAX_NUM_PORTS]; - struct sja1105_tagger_data tagger_data; struct sja1105_ptp_data ptp_data; struct sja1105_tas_data tas_data; }; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 880f28ea184f..4f5ea5d6a623 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2705,6 +2705,21 @@ static void sja1105_port_deferred_xmit(struct kthread_work *work) kfree(xmit_work); } +static int sja1105_connect_tag_protocol(struct dsa_switch *ds, + enum dsa_tag_protocol proto) +{ + struct sja1105_tagger_data *tagger_data; + + switch (proto) { + case DSA_TAG_PROTO_SJA1105: + tagger_data = sja1105_tagger_data(ds); + tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; + return 0; + default: + return -EPROTONOSUPPORT; + } +} + /* The MAXAGE setting belongs to the L2 Forwarding Parameters table, * which cannot be reconfigured at runtime. So a switch reset is required. */ @@ -3005,38 +3020,6 @@ static int sja1105_port_bridge_flags(struct dsa_switch *ds, int port, return 0; } -static void sja1105_teardown_ports(struct sja1105_private *priv) -{ - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; - - kthread_destroy_worker(tagger_data->xmit_worker); -} - -static int sja1105_setup_ports(struct sja1105_private *priv) -{ - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; - struct dsa_switch *ds = priv->ds; - struct kthread_worker *worker; - struct dsa_port *dp; - - worker = kthread_create_worker(0, "dsa%d:%d_xmit", ds->dst->index, - ds->index); - if (IS_ERR(worker)) { - dev_err(ds->dev, - "failed to create deferred xmit thread: %pe\n", - worker); - return PTR_ERR(worker); - } - - tagger_data->xmit_worker = worker; - tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; - - dsa_switch_for_each_user_port(dp, ds) - dp->priv = tagger_data; - - return 0; -} - /* The programming model for the SJA1105 switch is "all-at-once" via static * configuration tables. Some of these can be dynamically modified at runtime, * but not the xMII mode parameters table. @@ -3082,10 +3065,6 @@ static int sja1105_setup(struct dsa_switch *ds) } } - rc = sja1105_setup_ports(priv); - if (rc) - goto out_static_config_free; - sja1105_tas_setup(ds); sja1105_flower_setup(ds); @@ -3142,7 +3121,6 @@ out_ptp_clock_unregister: out_flower_teardown: sja1105_flower_teardown(ds); sja1105_tas_teardown(ds); - sja1105_teardown_ports(priv); out_static_config_free: sja1105_static_config_free(&priv->static_config); @@ -3162,12 +3140,12 @@ static void sja1105_teardown(struct dsa_switch *ds) sja1105_ptp_clock_unregister(ds); sja1105_flower_teardown(ds); sja1105_tas_teardown(ds); - sja1105_teardown_ports(priv); sja1105_static_config_free(&priv->static_config); } static const struct dsa_switch_ops sja1105_switch_ops = { .get_tag_protocol = sja1105_get_tag_protocol, + .connect_tag_protocol = sja1105_connect_tag_protocol, .setup = sja1105_setup, .teardown = sja1105_teardown, .set_ageing_time = sja1105_set_ageing_time, diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 0904ab10bd2f..b34e4674e217 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -58,13 +58,13 @@ enum sja1105_ptp_clk_mode { #define ptp_data_to_sja1105(d) \ container_of((d), struct sja1105_private, ptp_data) -/* Must be called only with priv->tagger_data.state bit +/* Must be called only with the tagger_data->state bit * SJA1105_HWTS_RX_EN cleared */ static int sja1105_change_rxtstamping(struct sja1105_private *priv, + struct sja1105_tagger_data *tagger_data, bool on) { - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; struct sja1105_general_params_entry *general_params; struct sja1105_table *table; @@ -75,9 +75,9 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, general_params->send_meta0 = on; /* Initialize the meta state machine to a known state */ - if (priv->tagger_data.stampable_skb) { - kfree_skb(priv->tagger_data.stampable_skb); - priv->tagger_data.stampable_skb = NULL; + if (tagger_data->stampable_skb) { + kfree_skb(tagger_data->stampable_skb); + tagger_data->stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); skb_queue_purge(&tagger_data->skb_txtstamp_queue); @@ -88,6 +88,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct hwtstamp_config config; bool rx_on; @@ -116,17 +117,17 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) break; } - if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) { - clear_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); + if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) { + clear_bit(SJA1105_HWTS_RX_EN, &tagger_data->state); - rc = sja1105_change_rxtstamping(priv, rx_on); + rc = sja1105_change_rxtstamping(priv, tagger_data, rx_on); if (rc < 0) { dev_err(ds->dev, "Failed to change RX timestamping: %d\n", rc); return rc; } if (rx_on) - set_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state); + set_bit(SJA1105_HWTS_RX_EN, &tagger_data->state); } if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) @@ -136,6 +137,7 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct hwtstamp_config config; @@ -144,7 +146,7 @@ int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr) config.tx_type = HWTSTAMP_TX_ON; else config.tx_type = HWTSTAMP_TX_OFF; - if (test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) + if (test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; else config.rx_filter = HWTSTAMP_FILTER_NONE; @@ -417,10 +419,11 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; - if (!test_bit(SJA1105_HWTS_RX_EN, &priv->tagger_data.state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) return false; /* We need to read the full PTP clock to reconstruct the Rx @@ -459,13 +462,11 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, */ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct sja1105_private *priv = ds->priv; - struct sja1105_tagger_data *tagger_data; u8 ts_id; - tagger_data = &priv->tagger_data; - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; spin_lock(&priv->ts_id_lock); @@ -897,7 +898,6 @@ static struct ptp_pin_desc sja1105_ptp_pin = { int sja1105_ptp_clock_register(struct dsa_switch *ds) { struct sja1105_private *priv = ds->priv; - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; ptp_data->caps = (struct ptp_clock_info) { @@ -919,9 +919,6 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); - /* Only used on SJA1110 */ - skb_queue_head_init(&tagger_data->skb_txtstamp_queue); - spin_lock_init(&tagger_data->meta_lock); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); if (IS_ERR_OR_NULL(ptp_data->clock)) @@ -937,8 +934,8 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) void sja1105_ptp_clock_unregister(struct dsa_switch *ds) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; - struct sja1105_tagger_data *tagger_data = &priv->tagger_data; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; if (IS_ERR_OR_NULL(ptp_data->clock)) diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index d8ee53085c09..9f7d42cbbc08 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -84,9 +84,12 @@ static inline s64 sja1105_ticks_to_ns(s64 ticks) return ticks * SJA1105_TICK_NS; } -static inline bool dsa_port_is_sja1105(struct dsa_port *dp) +static inline struct sja1105_tagger_data * +sja1105_tagger_data(struct dsa_switch *ds) { - return true; + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1105); + + return ds->tagger_data; } #endif /* _NET_DSA_SJA1105_H */ diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index fc2af71b965c..f3c1b31645f5 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -125,7 +125,7 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb) static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { - struct sja1105_tagger_data *tagger_data = dp->priv; + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(dp->ds); void (*xmit_work_fn)(struct kthread_work *work); struct sja1105_deferred_xmit_work *xmit_work; struct kthread_worker *xmit_worker; @@ -368,10 +368,10 @@ static struct sk_buff */ if (is_link_local) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_tagger_data *tagger_data = dp->priv; + struct sja1105_tagger_data *tagger_data; + struct dsa_switch *ds = dp->ds; - if (unlikely(!dsa_port_is_sja1105(dp))) - return skb; + tagger_data = sja1105_tagger_data(ds); if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) /* Do normal processing. */ @@ -382,7 +382,7 @@ static struct sk_buff * that we were expecting? */ if (tagger_data->stampable_skb) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); @@ -406,11 +406,11 @@ static struct sk_buff */ } else if (is_meta) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_tagger_data *tagger_data = dp->priv; + struct sja1105_tagger_data *tagger_data; + struct dsa_switch *ds = dp->ds; struct sk_buff *stampable_skb; - if (unlikely(!dsa_port_is_sja1105(dp))) - return skb; + tagger_data = sja1105_tagger_data(ds); /* Drop the meta frame if we're not in the right state * to process it. @@ -427,14 +427,14 @@ static struct sk_buff * that we were expecting? */ if (!stampable_skb) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Unexpected meta frame\n"); spin_unlock(&tagger_data->meta_lock); return NULL; } if (stampable_skb->dev != skb->dev) { - dev_err_ratelimited(dp->ds->dev, + dev_err_ratelimited(ds->dev, "Meta frame on wrong port\n"); spin_unlock(&tagger_data->meta_lock); return NULL; @@ -543,20 +543,14 @@ static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, enum sja1110_meta_tstamp dir, u64 tstamp) { + struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sk_buff *skb, *skb_tmp, *skb_match = NULL; - struct dsa_port *dp = dsa_to_port(ds, port); - struct sja1105_tagger_data *tagger_data; struct skb_shared_hwtstamps shwt = {0}; - if (!dsa_port_is_sja1105(dp)) - return; - /* We don't care about RX timestamps on the CPU port */ if (dir == SJA1110_META_TSTAMP_RX) return; - tagger_data = dp->priv; - spin_lock(&tagger_data->skb_txtstamp_queue.lock); skb_queue_walk_safe(&tagger_data->skb_txtstamp_queue, skb, skb_tmp) { @@ -737,11 +731,71 @@ static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; } +static void sja1105_disconnect(struct dsa_switch_tree *dst) +{ + struct sja1105_tagger_data *tagger_data; + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) { + tagger_data = dp->ds->tagger_data; + + if (!tagger_data) + continue; + + if (tagger_data->xmit_worker) + kthread_destroy_worker(tagger_data->xmit_worker); + + kfree(tagger_data); + dp->ds->tagger_data = NULL; + } +} + +static int sja1105_connect(struct dsa_switch_tree *dst) +{ + struct sja1105_tagger_data *tagger_data; + struct kthread_worker *xmit_worker; + struct dsa_port *dp; + int err; + + list_for_each_entry(dp, &dst->ports, list) { + if (dp->ds->tagger_data) + continue; + + tagger_data = kzalloc(sizeof(*tagger_data), GFP_KERNEL); + if (!tagger_data) { + err = -ENOMEM; + goto out; + } + + /* Only used on SJA1110 */ + skb_queue_head_init(&tagger_data->skb_txtstamp_queue); + spin_lock_init(&tagger_data->meta_lock); + + xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", + dst->index, dp->ds->index); + if (IS_ERR(xmit_worker)) { + err = PTR_ERR(xmit_worker); + goto out; + } + + tagger_data->xmit_worker = xmit_worker; + dp->ds->tagger_data = tagger_data; + } + + return 0; + +out: + sja1105_disconnect(dst); + return err; +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, + .connect = sja1105_connect, + .disconnect = sja1105_disconnect, .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, .promisc_on_master = true, @@ -755,6 +809,8 @@ static const struct dsa_device_ops sja1110_netdev_ops = { .proto = DSA_TAG_PROTO_SJA1110, .xmit = sja1110_xmit, .rcv = sja1110_rcv, + .connect = sja1105_connect, + .disconnect = sja1105_disconnect, .flow_dissect = sja1110_flow_dissect, .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, -- cgit v1.2.3 From fcbf979a5b4b5784bfb5647ae6190cd5c2ae595d Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:45 +0200 Subject: Revert "net: dsa: move sja1110_process_meta_tstamp inside the tagging protocol driver" This reverts commit 6d709cadfde68dbd12bef12fcced6222226dcb06. The above change was done to avoid calling symbols exported by the switch driver from the tagging protocol driver. With the tagger-owned storage model, we have a new option on our hands, and that is for the switch driver to provide a data consumer handler in the form of a function pointer inside the ->connect_tag_protocol() method. Having a function pointer avoids the problems of the exported symbols approach. By creating a handler for metadata frames holding TX timestamps on SJA1110, we are able to eliminate an skb queue from the tagger data, and replace it with a simple, and stateless, function pointer. This skb queue is now handled exclusively by sja1105_ptp.c, which makes the code easier to follow, as it used to be before the reverted patch. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 1 + drivers/net/dsa/sja1105/sja1105_ptp.c | 44 ++++++++++++++++++++++++++---- drivers/net/dsa/sja1105/sja1105_ptp.h | 24 ++++++++++++++++ include/linux/dsa/sja1105.h | 26 +++++------------- net/dsa/tag_sja1105.c | 50 +++++----------------------------- 5 files changed, 78 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 4f5ea5d6a623..9171fbea588c 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2714,6 +2714,7 @@ static int sja1105_connect_tag_protocol(struct dsa_switch *ds, case DSA_TAG_PROTO_SJA1105: tagger_data = sja1105_tagger_data(ds); tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; + tagger_data->meta_tstamp_handler = sja1110_process_meta_tstamp; return 0; default: return -EPROTONOSUPPORT; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index b34e4674e217..a9f7e4ae0bb2 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -80,7 +80,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, tagger_data->stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&tagger_data->skb_txtstamp_queue); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -456,15 +456,48 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return priv->info->rxtstamp(ds, port, skb); } +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shwt = {0}; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&ptp_data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&ptp_data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} + /* In addition to cloning the skb which is done by the common * sja1105_port_txtstamp, we need to generate a timestamp ID and save the * packet to the TX timestamping queue. */ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { - struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; u8 ts_id; skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; @@ -479,7 +512,7 @@ void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) spin_unlock(&priv->ts_id_lock); - skb_queue_tail(&tagger_data->skb_txtstamp_queue, clone); + skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); } /* Called from dsa_skb_tx_timestamp. This callback is just to clone @@ -919,6 +952,8 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); + /* Only used on SJA1110 */ + skb_queue_head_init(&ptp_data->skb_txtstamp_queue); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); if (IS_ERR_OR_NULL(ptp_data->clock)) @@ -934,7 +969,6 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) void sja1105_ptp_clock_unregister(struct dsa_switch *ds) { - struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); struct sja1105_private *priv = ds->priv; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; @@ -943,7 +977,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); - skb_queue_purge(&tagger_data->skb_txtstamp_queue); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 3ae6b9fdd492..416461ee95d2 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -8,6 +8,21 @@ #if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) +/* Timestamps are in units of 8 ns clock ticks (equivalent to + * a fixed 125 MHz clock). + */ +#define SJA1105_TICK_NS 8 + +static inline s64 ns_to_sja1105_ticks(s64 ns) +{ + return ns / SJA1105_TICK_NS; +} + +static inline s64 sja1105_ticks_to_ns(s64 ticks) +{ + return ticks * SJA1105_TICK_NS; +} + /* Calculate the first base_time in the future that satisfies this * relationship: * @@ -62,6 +77,10 @@ struct sja1105_ptp_data { struct timer_list extts_timer; /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; @@ -112,6 +131,9 @@ bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + #else struct sja1105_ptp_cmd; @@ -178,6 +200,8 @@ static inline int sja1105_ptp_commit(struct dsa_switch *ds, #define sja1110_rxtstamp NULL #define sja1110_txtstamp NULL +#define sja1110_process_meta_tstamp NULL + #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ #endif /* _SJA1105_PTP_H */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 9f7d42cbbc08..d216211b64f8 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -37,6 +37,11 @@ #define SJA1105_HWTS_RX_EN 0 +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + struct sja1105_deferred_xmit_work { struct dsa_port *dp; struct sk_buff *skb; @@ -51,12 +56,10 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; - /* Used on SJA1110 where meta frames are generated only for - * 2-step TX timestamps - */ - struct sk_buff_head skb_txtstamp_queue; struct kthread_worker *xmit_worker; void (*xmit_work_fn)(struct kthread_work *work); + void (*meta_tstamp_handler)(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); }; struct sja1105_skb_cb { @@ -69,21 +72,6 @@ struct sja1105_skb_cb { #define SJA1105_SKB_CB(skb) \ ((struct sja1105_skb_cb *)((skb)->cb)) -/* Timestamps are in units of 8 ns clock ticks (equivalent to - * a fixed 125 MHz clock). - */ -#define SJA1105_TICK_NS 8 - -static inline s64 ns_to_sja1105_ticks(s64 ns) -{ - return ns / SJA1105_TICK_NS; -} - -static inline s64 sja1105_ticks_to_ns(s64 ticks) -{ - return ticks * SJA1105_TICK_NS; -} - static inline struct sja1105_tagger_data * sja1105_tagger_data(struct dsa_switch *ds) { diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index f3c1b31645f5..fe6a6d95bb26 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include "dsa_priv.h" @@ -54,11 +53,6 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 -enum sja1110_meta_tstamp { - SJA1110_META_TSTAMP_TX = 0, - SJA1110_META_TSTAMP_RX = 1, -}; - /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -539,44 +533,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } -static void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, - u8 ts_id, enum sja1110_meta_tstamp dir, - u64 tstamp) -{ - struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(ds); - struct sk_buff *skb, *skb_tmp, *skb_match = NULL; - struct skb_shared_hwtstamps shwt = {0}; - - /* We don't care about RX timestamps on the CPU port */ - if (dir == SJA1110_META_TSTAMP_RX) - return; - - spin_lock(&tagger_data->skb_txtstamp_queue.lock); - - skb_queue_walk_safe(&tagger_data->skb_txtstamp_queue, skb, skb_tmp) { - if (SJA1105_SKB_CB(skb)->ts_id != ts_id) - continue; - - __skb_unlink(skb, &tagger_data->skb_txtstamp_queue); - skb_match = skb; - - break; - } - - spin_unlock(&tagger_data->skb_txtstamp_queue.lock); - - if (WARN_ON(!skb_match)) - return; - - shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); - skb_complete_tx_timestamp(skb_match, &shwt); -} - static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) { u8 *buf = dsa_etype_header_pos_rx(skb) + SJA1110_HEADER_LEN; int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct sja1105_tagger_data *tagger_data; struct net_device *master = skb->dev; struct dsa_port *cpu_dp; struct dsa_switch *ds; @@ -590,6 +552,10 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) return NULL; } + tagger_data = sja1105_tagger_data(ds); + if (!tagger_data->meta_tstamp_handler) + return NULL; + for (i = 0; i <= n_ts; i++) { u8 ts_id, source_port, dir; u64 tstamp; @@ -599,8 +565,8 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) dir = (buf[1] & BIT(3)) >> 3; tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); - sja1110_process_meta_tstamp(ds, source_port, ts_id, dir, - tstamp); + tagger_data->meta_tstamp_handler(ds, source_port, ts_id, dir, + tstamp); buf += SJA1110_META_TSTAMP_SIZE; } @@ -767,8 +733,6 @@ static int sja1105_connect(struct dsa_switch_tree *dst) goto out; } - /* Only used on SJA1110 */ - skb_queue_head_init(&tagger_data->skb_txtstamp_queue); spin_lock_init(&tagger_data->meta_lock); xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", -- cgit v1.2.3 From 950a419d9de13668f86828394cb242a1f9dece74 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 10 Dec 2021 01:34:46 +0200 Subject: net: dsa: tag_sja1105: split sja1105_tagger_data into private and public sections The sja1105 driver messes with the tagging protocol's state when PTP RX timestamping is enabled/disabled. This is fundamentally necessary because the tagger needs to know what to do when it receives a PTP packet. If RX timestamping is enabled, then a metadata follow-up frame is expected, and this holds the (partial) timestamp. So the tagger plays hide-and-seek with the network stack until it also gets the metadata frame, and then presents a single packet, the timestamped PTP packet. But when RX timestamping isn't enabled, there is no metadata frame expected, so the hide-and-seek game must be turned off and the packet must be delivered right away to the network stack. Considering this, we create a pseudo isolation by devising two tagger methods callable by the switch: one to get the RX timestamping state, and one to set it. Since we can't export symbols between the tagger and the switch driver, these methods are exposed through function pointers. After this change, the public portion of the sja1105_tagger_data contains only function pointers. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_ptp.c | 22 +++---- include/linux/dsa/sja1105.h | 13 ++-- net/dsa/tag_sja1105.c | 109 ++++++++++++++++++++++++---------- 3 files changed, 91 insertions(+), 53 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index a9f7e4ae0bb2..be3068a935af 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -58,11 +58,10 @@ enum sja1105_ptp_clk_mode { #define ptp_data_to_sja1105(d) \ container_of((d), struct sja1105_private, ptp_data) -/* Must be called only with the tagger_data->state bit - * SJA1105_HWTS_RX_EN cleared +/* Must be called only while the RX timestamping state of the tagger + * is turned off */ static int sja1105_change_rxtstamping(struct sja1105_private *priv, - struct sja1105_tagger_data *tagger_data, bool on) { struct sja1105_ptp_data *ptp_data = &priv->ptp_data; @@ -74,11 +73,6 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, general_params->send_meta1 = on; general_params->send_meta0 = on; - /* Initialize the meta state machine to a known state */ - if (tagger_data->stampable_skb) { - kfree_skb(tagger_data->stampable_skb); - tagger_data->stampable_skb = NULL; - } ptp_cancel_worker_sync(ptp_data->clock); skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); @@ -117,17 +111,17 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr) break; } - if (rx_on != test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) { - clear_bit(SJA1105_HWTS_RX_EN, &tagger_data->state); + if (rx_on != tagger_data->rxtstamp_get_state(ds)) { + tagger_data->rxtstamp_set_state(ds, false); - rc = sja1105_change_rxtstamping(priv, tagger_data, rx_on); + rc = sja1105_change_rxtstamping(priv, rx_on); if (rc < 0) { dev_err(ds->dev, "Failed to change RX timestamping: %d\n", rc); return rc; } if (rx_on) - set_bit(SJA1105_HWTS_RX_EN, &tagger_data->state); + tagger_data->rxtstamp_set_state(ds, true); } if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) @@ -146,7 +140,7 @@ int sja1105_hwtstamp_get(struct dsa_switch *ds, int port, struct ifreq *ifr) config.tx_type = HWTSTAMP_TX_ON; else config.tx_type = HWTSTAMP_TX_OFF; - if (test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) + if (tagger_data->rxtstamp_get_state(ds)) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; else config.rx_filter = HWTSTAMP_FILTER_NONE; @@ -423,7 +417,7 @@ bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) struct sja1105_private *priv = ds->priv; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; - if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) + if (!tagger_data->rxtstamp_get_state(ds)) return false; /* We need to read the full PTP clock to reconstruct the Rx diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index d216211b64f8..e9cb1ae6d742 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -35,8 +35,6 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull -#define SJA1105_HWTS_RX_EN 0 - enum sja1110_meta_tstamp { SJA1110_META_TSTAMP_TX = 0, SJA1110_META_TSTAMP_RX = 1, @@ -50,16 +48,13 @@ struct sja1105_deferred_xmit_work { /* Global tagger data */ struct sja1105_tagger_data { - struct sk_buff *stampable_skb; - /* Protects concurrent access to the meta state machine - * from taggers running on multiple ports on SMP systems - */ - spinlock_t meta_lock; - unsigned long state; - struct kthread_worker *xmit_worker; + /* Tagger to switch */ void (*xmit_work_fn)(struct kthread_work *work); void (*meta_tstamp_handler)(struct dsa_switch *ds, int port, u8 ts_id, enum sja1110_meta_tstamp dir, u64 tstamp); + /* Switch to tagger */ + bool (*rxtstamp_get_state)(struct dsa_switch *ds); + void (*rxtstamp_set_state)(struct dsa_switch *ds, bool on); }; struct sja1105_skb_cb { diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index fe6a6d95bb26..93d2484b2480 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -53,6 +53,25 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 +#define SJA1105_HWTS_RX_EN 0 + +struct sja1105_tagger_private { + struct sja1105_tagger_data data; /* Must be first */ + unsigned long state; + /* Protects concurrent access to the meta state machine + * from taggers running on multiple ports on SMP systems + */ + spinlock_t meta_lock; + struct sk_buff *stampable_skb; + struct kthread_worker *xmit_worker; +}; + +static struct sja1105_tagger_private * +sja1105_tagger_private(struct dsa_switch *ds) +{ + return ds->tagger_data; +} + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -120,12 +139,13 @@ static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) { struct sja1105_tagger_data *tagger_data = sja1105_tagger_data(dp->ds); + struct sja1105_tagger_private *priv = sja1105_tagger_private(dp->ds); void (*xmit_work_fn)(struct kthread_work *work); struct sja1105_deferred_xmit_work *xmit_work; struct kthread_worker *xmit_worker; xmit_work_fn = tagger_data->xmit_work_fn; - xmit_worker = tagger_data->xmit_worker; + xmit_worker = priv->xmit_worker; if (!xmit_work_fn || !xmit_worker) return NULL; @@ -362,32 +382,32 @@ static struct sk_buff */ if (is_link_local) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_tagger_data *tagger_data; + struct sja1105_tagger_private *priv; struct dsa_switch *ds = dp->ds; - tagger_data = sja1105_tagger_data(ds); + priv = sja1105_tagger_private(ds); - if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) /* Do normal processing. */ return skb; - spin_lock(&tagger_data->meta_lock); + spin_lock(&priv->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? */ - if (tagger_data->stampable_skb) { + if (priv->stampable_skb) { dev_err_ratelimited(ds->dev, "Expected meta frame, is %12llx " "in the DSA master multicast filter?\n", SJA1105_META_DMAC); - kfree_skb(tagger_data->stampable_skb); + kfree_skb(priv->stampable_skb); } /* Hold a reference to avoid dsa_switch_rcv * from freeing the skb. */ - tagger_data->stampable_skb = skb_get(skb); - spin_unlock(&tagger_data->meta_lock); + priv->stampable_skb = skb_get(skb); + spin_unlock(&priv->meta_lock); /* Tell DSA we got nothing */ return NULL; @@ -400,22 +420,22 @@ static struct sk_buff */ } else if (is_meta) { struct dsa_port *dp = dsa_slave_to_port(skb->dev); - struct sja1105_tagger_data *tagger_data; + struct sja1105_tagger_private *priv; struct dsa_switch *ds = dp->ds; struct sk_buff *stampable_skb; - tagger_data = sja1105_tagger_data(ds); + priv = sja1105_tagger_private(ds); /* Drop the meta frame if we're not in the right state * to process it. */ - if (!test_bit(SJA1105_HWTS_RX_EN, &tagger_data->state)) + if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) return NULL; - spin_lock(&tagger_data->meta_lock); + spin_lock(&priv->meta_lock); - stampable_skb = tagger_data->stampable_skb; - tagger_data->stampable_skb = NULL; + stampable_skb = priv->stampable_skb; + priv->stampable_skb = NULL; /* Was this a meta frame instead of the link-local * that we were expecting? @@ -423,14 +443,14 @@ static struct sk_buff if (!stampable_skb) { dev_err_ratelimited(ds->dev, "Unexpected meta frame\n"); - spin_unlock(&tagger_data->meta_lock); + spin_unlock(&priv->meta_lock); return NULL; } if (stampable_skb->dev != skb->dev) { dev_err_ratelimited(ds->dev, "Meta frame on wrong port\n"); - spin_unlock(&tagger_data->meta_lock); + spin_unlock(&priv->meta_lock); return NULL; } @@ -441,12 +461,36 @@ static struct sk_buff skb = stampable_skb; sja1105_transfer_meta(skb, meta); - spin_unlock(&tagger_data->meta_lock); + spin_unlock(&priv->meta_lock); } return skb; } +static bool sja1105_rxtstamp_get_state(struct dsa_switch *ds) +{ + struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); + + return test_bit(SJA1105_HWTS_RX_EN, &priv->state); +} + +static void sja1105_rxtstamp_set_state(struct dsa_switch *ds, bool on) +{ + struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); + + if (on) + set_bit(SJA1105_HWTS_RX_EN, &priv->state); + else + clear_bit(SJA1105_HWTS_RX_EN, &priv->state); + + /* Initialize the meta state machine to a known state */ + if (!priv->stampable_skb) + return; + + kfree_skb(priv->stampable_skb); + priv->stampable_skb = NULL; +} + static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { u16 tpid = ntohs(eth_hdr(skb)->h_proto); @@ -699,26 +743,27 @@ static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, static void sja1105_disconnect(struct dsa_switch_tree *dst) { - struct sja1105_tagger_data *tagger_data; + struct sja1105_tagger_private *priv; struct dsa_port *dp; list_for_each_entry(dp, &dst->ports, list) { - tagger_data = dp->ds->tagger_data; + priv = dp->ds->tagger_data; - if (!tagger_data) + if (!priv) continue; - if (tagger_data->xmit_worker) - kthread_destroy_worker(tagger_data->xmit_worker); + if (priv->xmit_worker) + kthread_destroy_worker(priv->xmit_worker); - kfree(tagger_data); - dp->ds->tagger_data = NULL; + kfree(priv); + dp->ds->priv = NULL; } } static int sja1105_connect(struct dsa_switch_tree *dst) { struct sja1105_tagger_data *tagger_data; + struct sja1105_tagger_private *priv; struct kthread_worker *xmit_worker; struct dsa_port *dp; int err; @@ -727,13 +772,13 @@ static int sja1105_connect(struct dsa_switch_tree *dst) if (dp->ds->tagger_data) continue; - tagger_data = kzalloc(sizeof(*tagger_data), GFP_KERNEL); - if (!tagger_data) { + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { err = -ENOMEM; goto out; } - spin_lock_init(&tagger_data->meta_lock); + spin_lock_init(&priv->meta_lock); xmit_worker = kthread_create_worker(0, "dsa%d:%d_xmit", dst->index, dp->ds->index); @@ -742,8 +787,12 @@ static int sja1105_connect(struct dsa_switch_tree *dst) goto out; } - tagger_data->xmit_worker = xmit_worker; - dp->ds->tagger_data = tagger_data; + priv->xmit_worker = xmit_worker; + /* Export functions for switch driver use */ + tagger_data = &priv->data; + tagger_data->rxtstamp_get_state = sja1105_rxtstamp_get_state; + tagger_data->rxtstamp_set_state = sja1105_rxtstamp_set_state; + dp->ds->tagger_data = priv; } return 0; -- cgit v1.2.3 From 9020ef659885f2622cfb386cc229b6d618362895 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 17 Oct 2021 18:22:09 +0100 Subject: iio: trigger: Fix a scheduling whilst atomic issue seen on tsc2046 IIO triggers are software IRQ chips that split an incoming IRQ into separate IRQs routed to all devices using the trigger. When all consumers are done then a trigger callback reenable() is called. There are a few circumstances under which this can happen in atomic context. 1) A single user of the trigger that calls the iio_trigger_done() function from interrupt context. 2) A race between disconnecting the last device from a trigger and the trigger itself sucessfully being disabled. To avoid a resulting scheduling whilst atomic, close this second corner by using schedule_work() to ensure the reenable is not done in atomic context. Note that drivers must be careful to manage the interaction of set_state() and reenable() callbacks to ensure appropriate reference counting if they are relying on the same hardware controls. Deliberately taking this the slow path rather than via a fixes tree because the error has hard to hit and I would like it to soak for a while before hitting a release kernel. Signed-off-by: Jonathan Cameron Cc: Pengutronix Kernel Team Cc: Dmitry Torokhov Tested-by: Oleksij Rempel Cc: Link: https://lore.kernel.org/r/20211017172209.112387-1-jic23@kernel.org --- drivers/iio/industrialio-trigger.c | 36 +++++++++++++++++++++++++++++++++++- include/linux/iio/trigger.h | 2 ++ 2 files changed, 37 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c index b23caa2f2aa1..d3bdc9800b4a 100644 --- a/drivers/iio/industrialio-trigger.c +++ b/drivers/iio/industrialio-trigger.c @@ -162,6 +162,39 @@ static struct iio_trigger *iio_trigger_acquire_by_name(const char *name) return trig; } +static void iio_reenable_work_fn(struct work_struct *work) +{ + struct iio_trigger *trig = container_of(work, struct iio_trigger, + reenable_work); + + /* + * This 'might' occur after the trigger state is set to disabled - + * in that case the driver should skip reenabling. + */ + trig->ops->reenable(trig); +} + +/* + * In general, reenable callbacks may need to sleep and this path is + * not performance sensitive, so just queue up a work item + * to reneable the trigger for us. + * + * Races that can cause this. + * 1) A handler occurs entirely in interrupt context so the counter + * the final decrement is still in this interrupt. + * 2) The trigger has been removed, but one last interrupt gets through. + * + * For (1) we must call reenable, but not in atomic context. + * For (2) it should be safe to call reenanble, if drivers never blindly + * reenable after state is off. + */ +static void iio_trigger_notify_done_atomic(struct iio_trigger *trig) +{ + if (atomic_dec_and_test(&trig->use_count) && trig->ops && + trig->ops->reenable) + schedule_work(&trig->reenable_work); +} + void iio_trigger_poll(struct iio_trigger *trig) { int i; @@ -173,7 +206,7 @@ void iio_trigger_poll(struct iio_trigger *trig) if (trig->subirqs[i].enabled) generic_handle_irq(trig->subirq_base + i); else - iio_trigger_notify_done(trig); + iio_trigger_notify_done_atomic(trig); } } } @@ -535,6 +568,7 @@ struct iio_trigger *viio_trigger_alloc(struct device *parent, trig->dev.type = &iio_trig_type; trig->dev.bus = &iio_bus_type; device_initialize(&trig->dev); + INIT_WORK(&trig->reenable_work, iio_reenable_work_fn); mutex_init(&trig->pool_lock); trig->subirq_base = irq_alloc_descs(-1, 0, diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index 096f68dd2e0c..4c69b144677b 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -55,6 +55,7 @@ struct iio_trigger_ops { * @attached_own_device:[INTERN] if we are using our own device as trigger, * i.e. if we registered a poll function to the same * device as the one providing the trigger. + * @reenable_work: [INTERN] work item used to ensure reenable can sleep. **/ struct iio_trigger { const struct iio_trigger_ops *ops; @@ -74,6 +75,7 @@ struct iio_trigger { unsigned long pool[BITS_TO_LONGS(CONFIG_IIO_CONSUMERS_PER_TRIGGER)]; struct mutex pool_lock; bool attached_own_device; + struct work_struct reenable_work; }; -- cgit v1.2.3 From 3ac27afefd5dd6a53e830542b899f092a58b6b51 Mon Sep 17 00:00:00 2001 From: Jonathan Cameron Date: Sun, 5 Dec 2021 17:01:29 +0000 Subject: iio:dac:ad5755: Switch to generic firmware properties and drop pdata Lars pointed out that platform data can also be supported via the generic properties interface, so there is no point in continuing to support it separately. Hence squish the linux/platform_data/ad5755.h header into the c file and drop accessing the platform data directly. Done by inspection only. Mostly completely mechanical with the exception of a few places where default value handling is cleaner done by first setting the value, then calling the firmware reading function but and not checking the return value, as opposed to reading firmware then setting the default if an error occurs. Part of general attempt to move all of IIO over to generic device properties, both to enable other firmware types and to remove drivers that can be the source of of_ specific behaviour in new drivers. Suggested-by: Lars-Peter Clausen Signed-off-by: Jonathan Cameron Reviewed-by: Andy Shevchenko --- drivers/iio/dac/ad5755.c | 152 ++++++++++++++++++++++++++--------- include/linux/platform_data/ad5755.h | 102 ----------------------- 2 files changed, 116 insertions(+), 138 deletions(-) delete mode 100644 include/linux/platform_data/ad5755.h (limited to 'include/linux') diff --git a/drivers/iio/dac/ad5755.c b/drivers/iio/dac/ad5755.c index cabc38d54085..7a62e6e1d5f1 100644 --- a/drivers/iio/dac/ad5755.c +++ b/drivers/iio/dac/ad5755.c @@ -13,10 +13,10 @@ #include #include #include -#include +#include + #include #include -#include #define AD5755_NUM_CHANNELS 4 @@ -63,6 +63,101 @@ #define AD5755_SLEW_RATE_SHIFT 3 #define AD5755_SLEW_ENABLE BIT(12) +enum ad5755_mode { + AD5755_MODE_VOLTAGE_0V_5V = 0, + AD5755_MODE_VOLTAGE_0V_10V = 1, + AD5755_MODE_VOLTAGE_PLUSMINUS_5V = 2, + AD5755_MODE_VOLTAGE_PLUSMINUS_10V = 3, + AD5755_MODE_CURRENT_4mA_20mA = 4, + AD5755_MODE_CURRENT_0mA_20mA = 5, + AD5755_MODE_CURRENT_0mA_24mA = 6, +}; + +enum ad5755_dc_dc_phase { + AD5755_DC_DC_PHASE_ALL_SAME_EDGE = 0, + AD5755_DC_DC_PHASE_A_B_SAME_EDGE_C_D_OPP_EDGE = 1, + AD5755_DC_DC_PHASE_A_C_SAME_EDGE_B_D_OPP_EDGE = 2, + AD5755_DC_DC_PHASE_90_DEGREE = 3, +}; + +enum ad5755_dc_dc_freq { + AD5755_DC_DC_FREQ_250kHZ = 0, + AD5755_DC_DC_FREQ_410kHZ = 1, + AD5755_DC_DC_FREQ_650kHZ = 2, +}; + +enum ad5755_dc_dc_maxv { + AD5755_DC_DC_MAXV_23V = 0, + AD5755_DC_DC_MAXV_24V5 = 1, + AD5755_DC_DC_MAXV_27V = 2, + AD5755_DC_DC_MAXV_29V5 = 3, +}; + +enum ad5755_slew_rate { + AD5755_SLEW_RATE_64k = 0, + AD5755_SLEW_RATE_32k = 1, + AD5755_SLEW_RATE_16k = 2, + AD5755_SLEW_RATE_8k = 3, + AD5755_SLEW_RATE_4k = 4, + AD5755_SLEW_RATE_2k = 5, + AD5755_SLEW_RATE_1k = 6, + AD5755_SLEW_RATE_500 = 7, + AD5755_SLEW_RATE_250 = 8, + AD5755_SLEW_RATE_125 = 9, + AD5755_SLEW_RATE_64 = 10, + AD5755_SLEW_RATE_32 = 11, + AD5755_SLEW_RATE_16 = 12, + AD5755_SLEW_RATE_8 = 13, + AD5755_SLEW_RATE_4 = 14, + AD5755_SLEW_RATE_0_5 = 15, +}; + +enum ad5755_slew_step_size { + AD5755_SLEW_STEP_SIZE_1 = 0, + AD5755_SLEW_STEP_SIZE_2 = 1, + AD5755_SLEW_STEP_SIZE_4 = 2, + AD5755_SLEW_STEP_SIZE_8 = 3, + AD5755_SLEW_STEP_SIZE_16 = 4, + AD5755_SLEW_STEP_SIZE_32 = 5, + AD5755_SLEW_STEP_SIZE_64 = 6, + AD5755_SLEW_STEP_SIZE_128 = 7, + AD5755_SLEW_STEP_SIZE_256 = 8, +}; + +/** + * struct ad5755_platform_data - AD5755 DAC driver platform data + * @ext_dc_dc_compenstation_resistor: Whether an external DC-DC converter + * compensation register is used. + * @dc_dc_phase: DC-DC converter phase. + * @dc_dc_freq: DC-DC converter frequency. + * @dc_dc_maxv: DC-DC maximum allowed boost voltage. + * @dac: Per DAC instance parameters. + * @dac.mode: The mode to be used for the DAC output. + * @dac.ext_current_sense_resistor: Whether an external current sense resistor + * is used. + * @dac.enable_voltage_overrange: Whether to enable 20% voltage output overrange. + * @dac.slew.enable: Whether to enable digital slew. + * @dac.slew.rate: Slew rate of the digital slew. + * @dac.slew.step_size: Slew step size of the digital slew. + **/ +struct ad5755_platform_data { + bool ext_dc_dc_compenstation_resistor; + enum ad5755_dc_dc_phase dc_dc_phase; + enum ad5755_dc_dc_freq dc_dc_freq; + enum ad5755_dc_dc_maxv dc_dc_maxv; + + struct { + enum ad5755_mode mode; + bool ext_current_sense_resistor; + bool enable_voltage_overrange; + struct { + bool enable; + enum ad5755_slew_rate rate; + enum ad5755_slew_step_size step_size; + } slew; + } dac[4]; +}; + /** * struct ad5755_chip_info - chip specific information * @channel_template: channel specification @@ -111,7 +206,6 @@ enum ad5755_type { ID_AD5737, }; -#ifdef CONFIG_OF static const int ad5755_dcdc_freq_table[][2] = { { 250000, AD5755_DC_DC_FREQ_250kHZ }, { 410000, AD5755_DC_DC_FREQ_410kHZ }, @@ -154,7 +248,6 @@ static const int ad5755_slew_step_table[][2] = { { 2, AD5755_SLEW_STEP_SIZE_2 }, { 1, AD5755_SLEW_STEP_SIZE_1 }, }; -#endif static int ad5755_write_unlocked(struct iio_dev *indio_dev, unsigned int reg, unsigned int val) @@ -604,30 +697,29 @@ static const struct ad5755_platform_data ad5755_default_pdata = { }, }; -#ifdef CONFIG_OF -static struct ad5755_platform_data *ad5755_parse_dt(struct device *dev) +static struct ad5755_platform_data *ad5755_parse_fw(struct device *dev) { - struct device_node *np = dev->of_node; - struct device_node *pp; + struct fwnode_handle *pp; struct ad5755_platform_data *pdata; unsigned int tmp; unsigned int tmparray[3]; int devnr, i; + if (!dev_fwnode(dev)) + return NULL; + pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL); if (!pdata) return NULL; pdata->ext_dc_dc_compenstation_resistor = - of_property_read_bool(np, "adi,ext-dc-dc-compenstation-resistor"); + device_property_read_bool(dev, "adi,ext-dc-dc-compenstation-resistor"); - if (!of_property_read_u32(np, "adi,dc-dc-phase", &tmp)) - pdata->dc_dc_phase = tmp; - else - pdata->dc_dc_phase = AD5755_DC_DC_PHASE_ALL_SAME_EDGE; + pdata->dc_dc_phase = AD5755_DC_DC_PHASE_ALL_SAME_EDGE; + device_property_read_u32(dev, "adi,dc-dc-phase", &pdata->dc_dc_phase); pdata->dc_dc_freq = AD5755_DC_DC_FREQ_410kHZ; - if (!of_property_read_u32(np, "adi,dc-dc-freq-hz", &tmp)) { + if (!device_property_read_u32(dev, "adi,dc-dc-freq-hz", &tmp)) { for (i = 0; i < ARRAY_SIZE(ad5755_dcdc_freq_table); i++) { if (tmp == ad5755_dcdc_freq_table[i][0]) { pdata->dc_dc_freq = ad5755_dcdc_freq_table[i][1]; @@ -641,7 +733,7 @@ static struct ad5755_platform_data *ad5755_parse_dt(struct device *dev) } pdata->dc_dc_maxv = AD5755_DC_DC_MAXV_23V; - if (!of_property_read_u32(np, "adi,dc-dc-max-microvolt", &tmp)) { + if (!device_property_read_u32(dev, "adi,dc-dc-max-microvolt", &tmp)) { for (i = 0; i < ARRAY_SIZE(ad5755_dcdc_maxv_table); i++) { if (tmp == ad5755_dcdc_maxv_table[i][0]) { pdata->dc_dc_maxv = ad5755_dcdc_maxv_table[i][1]; @@ -654,25 +746,23 @@ static struct ad5755_platform_data *ad5755_parse_dt(struct device *dev) } devnr = 0; - for_each_child_of_node(np, pp) { + device_for_each_child_node(dev, pp) { if (devnr >= AD5755_NUM_CHANNELS) { dev_err(dev, "There are too many channels defined in DT\n"); goto error_out; } - if (!of_property_read_u32(pp, "adi,mode", &tmp)) - pdata->dac[devnr].mode = tmp; - else - pdata->dac[devnr].mode = AD5755_MODE_CURRENT_4mA_20mA; + pdata->dac[devnr].mode = AD5755_MODE_CURRENT_4mA_20mA; + fwnode_property_read_u32(pp, "adi,mode", &pdata->dac[devnr].mode); pdata->dac[devnr].ext_current_sense_resistor = - of_property_read_bool(pp, "adi,ext-current-sense-resistor"); + fwnode_property_read_bool(pp, "adi,ext-current-sense-resistor"); pdata->dac[devnr].enable_voltage_overrange = - of_property_read_bool(pp, "adi,enable-voltage-overrange"); + fwnode_property_read_bool(pp, "adi,enable-voltage-overrange"); - if (!of_property_read_u32_array(pp, "adi,slew", tmparray, 3)) { + if (!fwnode_property_read_u32_array(pp, "adi,slew", tmparray, 3)) { pdata->dac[devnr].slew.enable = tmparray[0]; pdata->dac[devnr].slew.rate = AD5755_SLEW_RATE_64k; @@ -715,18 +805,11 @@ static struct ad5755_platform_data *ad5755_parse_dt(struct device *dev) devm_kfree(dev, pdata); return NULL; } -#else -static -struct ad5755_platform_data *ad5755_parse_dt(struct device *dev) -{ - return NULL; -} -#endif static int ad5755_probe(struct spi_device *spi) { enum ad5755_type type = spi_get_device_id(spi)->driver_data; - const struct ad5755_platform_data *pdata = dev_get_platdata(&spi->dev); + const struct ad5755_platform_data *pdata; struct iio_dev *indio_dev; struct ad5755_state *st; int ret; @@ -751,13 +834,10 @@ static int ad5755_probe(struct spi_device *spi) mutex_init(&st->lock); - if (spi->dev.of_node) - pdata = ad5755_parse_dt(&spi->dev); - else - pdata = spi->dev.platform_data; + pdata = ad5755_parse_fw(&spi->dev); if (!pdata) { - dev_warn(&spi->dev, "no platform data? using default\n"); + dev_warn(&spi->dev, "no firmware provided parameters? using default\n"); pdata = &ad5755_default_pdata; } diff --git a/include/linux/platform_data/ad5755.h b/include/linux/platform_data/ad5755.h deleted file mode 100644 index e371e08f04bc..000000000000 --- a/include/linux/platform_data/ad5755.h +++ /dev/null @@ -1,102 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright 2012 Analog Devices Inc. - */ -#ifndef __LINUX_PLATFORM_DATA_AD5755_H__ -#define __LINUX_PLATFORM_DATA_AD5755_H__ - -enum ad5755_mode { - AD5755_MODE_VOLTAGE_0V_5V = 0, - AD5755_MODE_VOLTAGE_0V_10V = 1, - AD5755_MODE_VOLTAGE_PLUSMINUS_5V = 2, - AD5755_MODE_VOLTAGE_PLUSMINUS_10V = 3, - AD5755_MODE_CURRENT_4mA_20mA = 4, - AD5755_MODE_CURRENT_0mA_20mA = 5, - AD5755_MODE_CURRENT_0mA_24mA = 6, -}; - -enum ad5755_dc_dc_phase { - AD5755_DC_DC_PHASE_ALL_SAME_EDGE = 0, - AD5755_DC_DC_PHASE_A_B_SAME_EDGE_C_D_OPP_EDGE = 1, - AD5755_DC_DC_PHASE_A_C_SAME_EDGE_B_D_OPP_EDGE = 2, - AD5755_DC_DC_PHASE_90_DEGREE = 3, -}; - -enum ad5755_dc_dc_freq { - AD5755_DC_DC_FREQ_250kHZ = 0, - AD5755_DC_DC_FREQ_410kHZ = 1, - AD5755_DC_DC_FREQ_650kHZ = 2, -}; - -enum ad5755_dc_dc_maxv { - AD5755_DC_DC_MAXV_23V = 0, - AD5755_DC_DC_MAXV_24V5 = 1, - AD5755_DC_DC_MAXV_27V = 2, - AD5755_DC_DC_MAXV_29V5 = 3, -}; - -enum ad5755_slew_rate { - AD5755_SLEW_RATE_64k = 0, - AD5755_SLEW_RATE_32k = 1, - AD5755_SLEW_RATE_16k = 2, - AD5755_SLEW_RATE_8k = 3, - AD5755_SLEW_RATE_4k = 4, - AD5755_SLEW_RATE_2k = 5, - AD5755_SLEW_RATE_1k = 6, - AD5755_SLEW_RATE_500 = 7, - AD5755_SLEW_RATE_250 = 8, - AD5755_SLEW_RATE_125 = 9, - AD5755_SLEW_RATE_64 = 10, - AD5755_SLEW_RATE_32 = 11, - AD5755_SLEW_RATE_16 = 12, - AD5755_SLEW_RATE_8 = 13, - AD5755_SLEW_RATE_4 = 14, - AD5755_SLEW_RATE_0_5 = 15, -}; - -enum ad5755_slew_step_size { - AD5755_SLEW_STEP_SIZE_1 = 0, - AD5755_SLEW_STEP_SIZE_2 = 1, - AD5755_SLEW_STEP_SIZE_4 = 2, - AD5755_SLEW_STEP_SIZE_8 = 3, - AD5755_SLEW_STEP_SIZE_16 = 4, - AD5755_SLEW_STEP_SIZE_32 = 5, - AD5755_SLEW_STEP_SIZE_64 = 6, - AD5755_SLEW_STEP_SIZE_128 = 7, - AD5755_SLEW_STEP_SIZE_256 = 8, -}; - -/** - * struct ad5755_platform_data - AD5755 DAC driver platform data - * @ext_dc_dc_compenstation_resistor: Whether an external DC-DC converter - * compensation register is used. - * @dc_dc_phase: DC-DC converter phase. - * @dc_dc_freq: DC-DC converter frequency. - * @dc_dc_maxv: DC-DC maximum allowed boost voltage. - * @dac.mode: The mode to be used for the DAC output. - * @dac.ext_current_sense_resistor: Whether an external current sense resistor - * is used. - * @dac.enable_voltage_overrange: Whether to enable 20% voltage output overrange. - * @dac.slew.enable: Whether to enable digital slew. - * @dac.slew.rate: Slew rate of the digital slew. - * @dac.slew.step_size: Slew step size of the digital slew. - **/ -struct ad5755_platform_data { - bool ext_dc_dc_compenstation_resistor; - enum ad5755_dc_dc_phase dc_dc_phase; - enum ad5755_dc_dc_freq dc_dc_freq; - enum ad5755_dc_dc_maxv dc_dc_maxv; - - struct { - enum ad5755_mode mode; - bool ext_current_sense_resistor; - bool enable_voltage_overrange; - struct { - bool enable; - enum ad5755_slew_rate rate; - enum ad5755_slew_step_size step_size; - } slew; - } dac[4]; -}; - -#endif -- cgit v1.2.3 From c537be0bfad6337f2afd618fe252c03217191405 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 3 Dec 2021 11:28:46 +0100 Subject: i2c: acpi: Add i2c_acpi_new_device_by_fwnode() function Change i2c_acpi_new_device() into i2c_acpi_new_device_by_fwnode() and add a static inline wrapper providing the old i2c_acpi_new_device() behavior. This is necessary because in some cases we may only have access to the fwnode / acpi_device and not to the matching physical-node struct device *. Suggested-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Acked-by: Mika Westerberg Acked-by: Wolfram Sang Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20211203102857.44539-4-hdegoede@redhat.com --- drivers/i2c/i2c-core-acpi.c | 17 +++++++++++------ include/linux/i2c.h | 17 +++++++++++++---- 2 files changed, 24 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-acpi.c b/drivers/i2c/i2c-core-acpi.c index 04338cbd08a9..c87ce2276007 100644 --- a/drivers/i2c/i2c-core-acpi.c +++ b/drivers/i2c/i2c-core-acpi.c @@ -476,8 +476,8 @@ struct notifier_block i2c_acpi_notifier = { }; /** - * i2c_acpi_new_device - Create i2c-client for the Nth I2cSerialBus resource - * @dev: Device owning the ACPI resources to get the client from + * i2c_acpi_new_device_by_fwnode - Create i2c-client for the Nth I2cSerialBus resource + * @fwnode: fwnode with the ACPI resources to get the client from * @index: Index of ACPI resource to get * @info: describes the I2C device; note this is modified (addr gets set) * Context: can sleep @@ -493,15 +493,20 @@ struct notifier_block i2c_acpi_notifier = { * Returns a pointer to the new i2c-client, or error pointer in case of failure. * Specifically, -EPROBE_DEFER is returned if the adapter is not found. */ -struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, - struct i2c_board_info *info) +struct i2c_client *i2c_acpi_new_device_by_fwnode(struct fwnode_handle *fwnode, + int index, + struct i2c_board_info *info) { - struct acpi_device *adev = ACPI_COMPANION(dev); struct i2c_acpi_lookup lookup; struct i2c_adapter *adapter; + struct acpi_device *adev; LIST_HEAD(resource_list); int ret; + adev = to_acpi_device_node(fwnode); + if (!adev) + return ERR_PTR(-ENODEV); + memset(&lookup, 0, sizeof(lookup)); lookup.info = info; lookup.device_handle = acpi_device_handle(adev); @@ -523,7 +528,7 @@ struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, return i2c_new_client_device(adapter, info); } -EXPORT_SYMBOL_GPL(i2c_acpi_new_device); +EXPORT_SYMBOL_GPL(i2c_acpi_new_device_by_fwnode); bool i2c_acpi_waive_d0_probe(struct device *dev) { diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 16119ac1aa97..7d4f52ceb7b5 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -1025,8 +1025,9 @@ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); u32 i2c_acpi_find_bus_speed(struct device *dev); -struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, - struct i2c_board_info *info); +struct i2c_client *i2c_acpi_new_device_by_fwnode(struct fwnode_handle *fwnode, + int index, + struct i2c_board_info *info); struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); bool i2c_acpi_waive_d0_probe(struct device *dev); #else @@ -1043,8 +1044,9 @@ static inline u32 i2c_acpi_find_bus_speed(struct device *dev) { return 0; } -static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, - int index, struct i2c_board_info *info) +static inline struct i2c_client *i2c_acpi_new_device_by_fwnode( + struct fwnode_handle *fwnode, int index, + struct i2c_board_info *info) { return ERR_PTR(-ENODEV); } @@ -1058,4 +1060,11 @@ static inline bool i2c_acpi_waive_d0_probe(struct device *dev) } #endif /* CONFIG_ACPI */ +static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, + int index, + struct i2c_board_info *info) +{ + return i2c_acpi_new_device_by_fwnode(dev_fwnode(dev), index, info); +} + #endif /* _LINUX_I2C_H */ -- cgit v1.2.3 From 9dfa374cc6d04d2515adc21c39e356b64ee45a29 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 3 Dec 2021 11:28:47 +0100 Subject: platform_data: Add linux/platform_data/tps68470.h file The clk and regulator frameworks expect clk/regulator consumer-devices to have info about the consumed clks/regulators described in the device's fw_node. To work around cases where this info is not present in the firmware tables, which is often the case on x86/ACPI devices, both frameworks allow the provider-driver to attach info about consumers to the provider-device during probe/registration of the provider device. The TI TPS68470 PMIC is used x86/ACPI devices with the consumer-info missing from the ACPI tables. Thus the tps68470-clk and tps68470-regulator drivers must provide the consumer-info at probe time. Define tps68470_clk_platform_data and tps68470_regulator_platform_data structs to allow the x86 platform code to pass the necessary consumer info to these drivers. Reviewed-by: Andy Shevchenko Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20211203102857.44539-5-hdegoede@redhat.com --- include/linux/platform_data/tps68470.h | 35 ++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 include/linux/platform_data/tps68470.h (limited to 'include/linux') diff --git a/include/linux/platform_data/tps68470.h b/include/linux/platform_data/tps68470.h new file mode 100644 index 000000000000..126d082c3f2e --- /dev/null +++ b/include/linux/platform_data/tps68470.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * TI TPS68470 PMIC platform data definition. + * + * Copyright (c) 2021 Red Hat Inc. + * + * Red Hat authors: + * Hans de Goede + */ +#ifndef __PDATA_TPS68470_H +#define __PDATA_TPS68470_H + +enum tps68470_regulators { + TPS68470_CORE, + TPS68470_ANA, + TPS68470_VCM, + TPS68470_VIO, + TPS68470_VSIO, + TPS68470_AUX1, + TPS68470_AUX2, + TPS68470_NUM_REGULATORS +}; + +struct regulator_init_data; + +struct tps68470_regulator_platform_data { + const struct regulator_init_data *reg_init_data[TPS68470_NUM_REGULATORS]; +}; + +struct tps68470_clk_platform_data { + const char *consumer_dev_name; + const char *consumer_con_id; +}; + +#endif -- cgit v1.2.3 From 3c118547f87e930d45a5787e386734015dd93b32 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 10 Dec 2021 21:29:59 +0100 Subject: u64_stats: Disable preemption on 32bit UP+SMP PREEMPT_RT during updates. On PREEMPT_RT the seqcount_t for synchronisation is required on 32bit architectures even on UP because the softirq (and the threaded IRQ handler) can be preempted. With the seqcount_t for synchronisation, a reader with higher priority can preempt the writer and then spin endlessly in read_seqcount_begin() while the writer can't make progress. To avoid such a lock up on PREEMPT_RT the writer must disable preemption during the update. There is no need to disable interrupts because no writer is using this API in hard-IRQ context on PREEMPT_RT. Disable preemption on 32bit-RT within the u64_stats write section. Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/u64_stats_sync.h | 42 ++++++++++++++++++++++++++++-------------- 1 file changed, 28 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e8ec116c916b..6ad4e9032d53 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -66,7 +66,7 @@ #include struct u64_stats_sync { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) seqcount_t seq; #endif }; @@ -125,7 +125,7 @@ static inline void u64_stats_inc(u64_stats_t *p) } #endif -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) #define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) #else static inline void u64_stats_init(struct u64_stats_sync *syncp) @@ -135,15 +135,19 @@ static inline void u64_stats_init(struct u64_stats_sync *syncp) static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); write_seqcount_begin(&syncp->seq); #endif } static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); #endif } @@ -152,8 +156,11 @@ u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) { unsigned long flags = 0; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - local_irq_save(flags); +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_irq_save(flags); write_seqcount_begin(&syncp->seq); #endif return flags; @@ -163,15 +170,18 @@ static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, unsigned long flags) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - local_irq_restore(flags); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_irq_restore(flags); #endif } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); #else return 0; @@ -180,7 +190,7 @@ static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync * static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -189,7 +199,7 @@ static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *sy static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_retry(&syncp->seq, start); #else return false; @@ -199,7 +209,7 @@ static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_enable(); #endif return __u64_stats_fetch_retry(syncp, start); @@ -213,7 +223,9 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_disable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -222,7 +234,9 @@ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_enable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_enable(); #endif return __u64_stats_fetch_retry(syncp, start); -- cgit v1.2.3 From 4bc5e64e6cf37007e436970024e5998ee0935651 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Fri, 26 Nov 2021 01:13:32 +0100 Subject: efi: Move efifb_setup_from_dmi() prototype from arch headers Commit 8633ef82f101 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") made the Generic System Framebuffers (sysfb) driver able to be built on non-x86 architectures. But it left the efifb_setup_from_dmi() function prototype declaration in the architecture specific headers. This could lead to the following compiler warning as reported by the kernel test robot: drivers/firmware/efi/sysfb_efi.c:70:6: warning: no previous prototype for function 'efifb_setup_from_dmi' [-Wmissing-prototypes] void efifb_setup_from_dmi(struct screen_info *si, const char *opt) ^ drivers/firmware/efi/sysfb_efi.c:70:1: note: declare 'static' if the function is not intended to be used outside of this translation unit void efifb_setup_from_dmi(struct screen_info *si, const char *opt) Fixes: 8633ef82f101 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") Reported-by: kernel test robot Cc: # 5.15.x Signed-off-by: Javier Martinez Canillas Acked-by: Thomas Zimmermann Link: https://lore.kernel.org/r/20211126001333.555514-1-javierm@redhat.com Signed-off-by: Ard Biesheuvel --- arch/arm/include/asm/efi.h | 1 - arch/arm64/include/asm/efi.h | 1 - arch/riscv/include/asm/efi.h | 1 - arch/x86/include/asm/efi.h | 2 -- include/linux/efi.h | 6 ++++++ 5 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index a6f3b179e8a9..27218eabbf9a 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -17,7 +17,6 @@ #ifdef CONFIG_EFI void efi_init(void); -extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index d3e1825337be..ad55079abe47 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,7 +14,6 @@ #ifdef CONFIG_EFI extern void efi_init(void); -extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); #else #define efi_init() #endif diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 49b398fe99f1..cc4f6787f937 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -13,7 +13,6 @@ #ifdef CONFIG_EFI extern void efi_init(void); -extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); #else #define efi_init() #endif diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 4d0b126835b8..63158fd55856 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -197,8 +197,6 @@ static inline bool efi_runtime_supported(void) extern void parse_efi_setup(u64 phys_addr, u32 data_len); -extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); - extern void efi_thunk_runtime_setup(void); efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, unsigned long descriptor_size, diff --git a/include/linux/efi.h b/include/linux/efi.h index dbd39b20e034..ef8dbc0a1522 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1283,4 +1283,10 @@ static inline struct efi_mokvar_table_entry *efi_mokvar_entry_find( } #endif +#ifdef CONFIG_SYSFB +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); +#else +static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) { } +#endif + #endif /* _LINUX_EFI_H */ -- cgit v1.2.3 From f92c1e183604c20ce00eb889315fdaa8f2d9e509 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 8 Dec 2021 20:32:44 +0100 Subject: bpf: Add get_func_[arg|ret|arg_cnt] helpers Adding following helpers for tracing programs: Get n-th argument of the traced function: long bpf_get_func_arg(void *ctx, u32 n, u64 *value) Get return value of the traced function: long bpf_get_func_ret(void *ctx, u64 *value) Get arguments count of the traced function: long bpf_get_func_arg_cnt(void *ctx) The trampoline now stores number of arguments on ctx-8 address, so it's easy to verify argument index and find return value argument's position. Moving function ip address on the trampoline stack behind the number of functions arguments, so it's now stored on ctx-16 address if it's needed. All helpers above are inlined by verifier. Also bit unrelated small change - using newly added function bpf_prog_has_trampoline in check_get_func_ip. Signed-off-by: Jiri Olsa Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211208193245.172141-5-jolsa@kernel.org --- arch/x86/net/bpf_jit_comp.c | 15 +++++++- include/linux/bpf.h | 5 +++ include/uapi/linux/bpf.h | 28 +++++++++++++++ kernel/bpf/trampoline.c | 8 +++++ kernel/bpf/verifier.c | 77 +++++++++++++++++++++++++++++++++++++++--- kernel/trace/bpf_trace.c | 55 +++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 28 +++++++++++++++ 7 files changed, 209 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 10fab8cb3fb5..4bbcded07415 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1941,7 +1941,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i void *orig_call) { int ret, i, nr_args = m->nr_args; - int regs_off, ip_off, stack_size = nr_args * 8; + int regs_off, ip_off, args_off, stack_size = nr_args * 8; struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY]; struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT]; struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; @@ -1968,6 +1968,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * RBP - regs_off [ reg_arg1 ] program's ctx pointer * + * RBP - args_off [ args count ] always + * * RBP - ip_off [ traced function ] BPF_TRAMP_F_IP_ARG flag */ @@ -1978,6 +1980,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i regs_off = stack_size; + /* args count */ + stack_size += 8; + args_off = stack_size; + if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -1996,6 +2002,13 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ EMIT1(0x53); /* push rbx */ + /* Store number of arguments of the traced function: + * mov rax, nr_args + * mov QWORD PTR [rbp - args_off], rax + */ + emit_mov_imm64(&prog, BPF_REG_0, 0, (u32) nr_args); + emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -args_off); + if (flags & BPF_TRAMP_F_IP_ARG) { /* Store IP address of the traced function: * mov rax, QWORD PTR [rbp + 8] diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 7a40022e3d00..965fffaf0308 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -777,6 +777,7 @@ void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 pages); void bpf_jit_uncharge_modmem(u32 pages); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -805,6 +806,10 @@ static inline bool is_bpf_image_address(unsigned long address) { return false; } +static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + return false; +} #endif struct bpf_func_info_aux { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2820c77e4846..b0383d371b9a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4993,6 +4993,31 @@ union bpf_attr { * An integer less than, equal to, or greater than zero * if the first **s1_sz** bytes of **s1** is found to be * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= arguments count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of arguments of the traced function (for tracing programs). + * + * Return + * The number of arguments of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5178,6 +5203,9 @@ union bpf_attr { FN(find_vma), \ FN(loop), \ FN(strncmp), \ + FN(get_func_arg), \ + FN(get_func_ret), \ + FN(get_func_arg_cnt), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index e98de5e73ba5..4b6974a195c1 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -27,6 +27,14 @@ static struct hlist_head trampoline_table[TRAMPOLINE_TABLE_SIZE]; /* serializes access to trampoline_table */ static DEFINE_MUTEX(trampoline_mutex); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + enum bpf_attach_type eatype = prog->expected_attach_type; + + return eatype == BPF_TRACE_FENTRY || eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN; +} + void *bpf_jit_alloc_exec_page(void) { void *image; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b39de3ae50f5..d74e8a99412e 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6395,13 +6395,11 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env, static int check_get_func_ip(struct bpf_verifier_env *env) { - enum bpf_attach_type eatype = env->prog->expected_attach_type; enum bpf_prog_type type = resolve_prog_type(env->prog); int func_id = BPF_FUNC_get_func_ip; if (type == BPF_PROG_TYPE_TRACING) { - if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT && - eatype != BPF_MODIFY_RETURN) { + if (!bpf_prog_has_trampoline(env->prog)) { verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n", func_id_name(func_id), func_id); return -ENOTSUPP; @@ -12997,6 +12995,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, static int do_misc_fixups(struct bpf_verifier_env *env) { struct bpf_prog *prog = env->prog; + enum bpf_attach_type eatype = prog->expected_attach_type; bool expect_blinding = bpf_jit_blinding_enabled(prog); enum bpf_prog_type prog_type = resolve_prog_type(prog); struct bpf_insn *insn = prog->insnsi; @@ -13367,11 +13366,79 @@ patch_map_ops_generic: continue; } + /* Implement bpf_get_func_arg inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_JMP32_REG(BPF_JGE, BPF_REG_2, BPF_REG_0, 6); + insn_buf[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 3); + insn_buf[3] = BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_1); + insn_buf[4] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0); + insn_buf[5] = BPF_STX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[6] = BPF_MOV64_IMM(BPF_REG_0, 0); + insn_buf[7] = BPF_JMP_A(1); + insn_buf[8] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL); + cnt = 9; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + /* Implement bpf_get_func_ret inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_ret) { + if (eatype == BPF_TRACE_FEXIT || + eatype == BPF_MODIFY_RETURN) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + insn_buf[1] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3); + insn_buf[2] = BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_1); + insn_buf[3] = BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0); + insn_buf[4] = BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_3, 0); + insn_buf[5] = BPF_MOV64_IMM(BPF_REG_0, 0); + cnt = 6; + } else { + insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, -EOPNOTSUPP); + cnt = 1; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + + /* Implement get_func_arg_cnt inline. */ + if (prog_type == BPF_PROG_TYPE_TRACING && + insn->imm == BPF_FUNC_get_func_arg_cnt) { + /* Load nr_args from ctx - 8 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); + if (!new_prog) + return -ENOMEM; + + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + /* Implement bpf_get_func_ip inline. */ if (prog_type == BPF_PROG_TYPE_TRACING && insn->imm == BPF_FUNC_get_func_ip) { - /* Load IP address from ctx - 8 */ - insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8); + /* Load IP address from ctx - 16 */ + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -16); new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1); if (!new_prog) diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 623dd0684429..cea2ca6df949 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1012,7 +1012,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx) { /* This helper call is inlined by verifier. */ - return ((u64 *)ctx)[-1]; + return ((u64 *)ctx)[-2]; } static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = { @@ -1091,6 +1091,53 @@ static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { .arg2_type = ARG_CONST_SIZE_OR_ZERO, }; +BPF_CALL_3(get_func_arg, void *, ctx, u32, n, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + if ((u64) n >= nr_args) + return -EINVAL; + *value = ((u64 *)ctx)[n]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_arg_proto = { + .func = get_func_arg, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value) +{ + /* This helper call is inlined by verifier. */ + u64 nr_args = ((u64 *)ctx)[-1]; + + *value = ((u64 *)ctx)[nr_args]; + return 0; +} + +static const struct bpf_func_proto bpf_get_func_ret_proto = { + .func = get_func_ret, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_LONG, +}; + +BPF_CALL_1(get_func_arg_cnt, void *, ctx) +{ + /* This helper call is inlined by verifier. */ + return ((u64 *)ctx)[-1]; +} + +static const struct bpf_func_proto bpf_get_func_arg_cnt_proto = { + .func = get_func_arg_cnt, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1629,6 +1676,12 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) NULL; case BPF_FUNC_d_path: return &bpf_d_path_proto; + case BPF_FUNC_get_func_arg: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_proto : NULL; + case BPF_FUNC_get_func_ret: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_ret_proto : NULL; + case BPF_FUNC_get_func_arg_cnt: + return bpf_prog_has_trampoline(prog) ? &bpf_get_func_arg_cnt_proto : NULL; default: fn = raw_tp_prog_func_proto(func_id, prog); if (!fn && prog->expected_attach_type == BPF_TRACE_ITER) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 2820c77e4846..b0383d371b9a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4993,6 +4993,31 @@ union bpf_attr { * An integer less than, equal to, or greater than zero * if the first **s1_sz** bytes of **s1** is found to be * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= arguments count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of arguments of the traced function (for tracing programs). + * + * Return + * The number of arguments of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5178,6 +5203,9 @@ union bpf_attr { FN(find_vma), \ FN(loop), \ FN(strncmp), \ + FN(get_func_arg), \ + FN(get_func_ret), \ + FN(get_func_arg_cnt), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 0e25498f8cd43c1b5aa327f373dd094e9a006da7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 28 Jun 2021 14:52:01 -0500 Subject: exit: Add and use make_task_dead. There are two big uses of do_exit. The first is it's design use to be the guts of the exit(2) system call. The second use is to terminate a task after something catastrophic has happened like a NULL pointer in kernel code. Add a function make_task_dead that is initialy exactly the same as do_exit to cover the cases where do_exit is called to handle catastrophic failure. In time this can probably be reduced to just a light wrapper around do_task_dead. For now keep it exactly the same so that there will be no behavioral differences introducing this new concept. Replace all of the uses of do_exit that use it for catastraphic task cleanup with make_task_dead to make it clear what the code is doing. As part of this rename rewind_stack_do_exit rewind_stack_and_make_dead. Signed-off-by: "Eric W. Biederman" --- arch/alpha/kernel/traps.c | 6 +++--- arch/alpha/mm/fault.c | 2 +- arch/arm/kernel/traps.c | 2 +- arch/arm/mm/fault.c | 2 +- arch/arm64/kernel/traps.c | 2 +- arch/arm64/mm/fault.c | 2 +- arch/csky/abiv1/alignment.c | 2 +- arch/csky/kernel/traps.c | 2 +- arch/csky/mm/fault.c | 2 +- arch/h8300/kernel/traps.c | 2 +- arch/h8300/mm/fault.c | 2 +- arch/hexagon/kernel/traps.c | 2 +- arch/ia64/kernel/mca_drv.c | 2 +- arch/ia64/kernel/traps.c | 2 +- arch/ia64/mm/fault.c | 2 +- arch/m68k/kernel/traps.c | 2 +- arch/m68k/mm/fault.c | 2 +- arch/microblaze/kernel/exceptions.c | 4 ++-- arch/mips/kernel/traps.c | 2 +- arch/nds32/kernel/fpu.c | 2 +- arch/nds32/kernel/traps.c | 8 ++++---- arch/nios2/kernel/traps.c | 4 ++-- arch/openrisc/kernel/traps.c | 2 +- arch/parisc/kernel/traps.c | 2 +- arch/powerpc/kernel/traps.c | 8 ++++---- arch/riscv/kernel/traps.c | 2 +- arch/riscv/mm/fault.c | 2 +- arch/s390/kernel/dumpstack.c | 2 +- arch/s390/kernel/nmi.c | 2 +- arch/sh/kernel/traps.c | 2 +- arch/sparc/kernel/traps_32.c | 4 +--- arch/sparc/kernel/traps_64.c | 4 +--- arch/x86/entry/entry_32.S | 6 +++--- arch/x86/entry/entry_64.S | 6 +++--- arch/x86/kernel/dumpstack.c | 4 ++-- arch/xtensa/kernel/traps.c | 2 +- include/linux/sched/task.h | 1 + kernel/exit.c | 9 +++++++++ tools/objtool/check.c | 3 ++- 39 files changed, 63 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c index 2ae34702456c..8a66fe544c69 100644 --- a/arch/alpha/kernel/traps.c +++ b/arch/alpha/kernel/traps.c @@ -190,7 +190,7 @@ die_if_kernel(char * str, struct pt_regs *regs, long err, unsigned long *r9_15) local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } #ifndef CONFIG_MATHEMU @@ -575,7 +575,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg, printk("Bad unaligned kernel access at %016lx: %p %lx %lu\n", pc, va, opcode, reg); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); got_exception: /* Ok, we caught the exception, but we don't want it. Is there @@ -630,7 +630,7 @@ got_exception: local_irq_enable(); while (1); } - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index eee5102c3d88..e9193d52222e 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -204,7 +204,7 @@ retry: printk(KERN_ALERT "Unable to handle kernel paging request at " "virtual address %016lx\n", address); die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16); - do_exit(SIGKILL); + make_task_dead(SIGKILL); /* We ran out of memory, or some other thing happened to us that made us unable to handle the page fault gracefully. */ diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 195dff58bafc..b4bd2e5f17c1 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -333,7 +333,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) if (panic_on_oops) panic("Fatal exception"); if (signr) - do_exit(signr); + make_task_dead(signr); } /* diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index bc8779d54a64..bf1a0c618c49 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -111,7 +111,7 @@ static void die_kernel_fault(const char *msg, struct mm_struct *mm, show_pte(KERN_ALERT, mm, addr); die("Oops", regs, fsr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } /* diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 7b21213a570f..bdd456e4e7f4 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -235,7 +235,7 @@ void die(const char *str, struct pt_regs *regs, int err) raw_spin_unlock_irqrestore(&die_lock, flags); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } static void arm64_show_signal(int signo, const char *str) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9ae24e3b72be..11a28cace2d2 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -302,7 +302,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c index cb2a0d94a144..5e2fb45d605c 100644 --- a/arch/csky/abiv1/alignment.c +++ b/arch/csky/abiv1/alignment.c @@ -294,7 +294,7 @@ bad_area: __func__, opcode, rz, rx, imm, addr); show_regs(regs); bust_spinlocks(0); - do_exit(SIGKILL); + make_dead_task(SIGKILL); } force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr); diff --git a/arch/csky/kernel/traps.c b/arch/csky/kernel/traps.c index e5fbf8653a21..88a47035b925 100644 --- a/arch/csky/kernel/traps.c +++ b/arch/csky/kernel/traps.c @@ -109,7 +109,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_dead_task(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) diff --git a/arch/csky/mm/fault.c b/arch/csky/mm/fault.c index 466ad949818a..7215a46b6b8e 100644 --- a/arch/csky/mm/fault.c +++ b/arch/csky/mm/fault.c @@ -67,7 +67,7 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) pr_alert("Unable to handle kernel paging request at virtual " "addr 0x%08lx, pc: 0x%08lx\n", addr, regs->pc); die(regs, "Oops"); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) diff --git a/arch/h8300/kernel/traps.c b/arch/h8300/kernel/traps.c index bdbe988d8dbc..3d4e0bde37ae 100644 --- a/arch/h8300/kernel/traps.c +++ b/arch/h8300/kernel/traps.c @@ -106,7 +106,7 @@ void die(const char *str, struct pt_regs *fp, unsigned long err) dump(fp); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_dead_task(SIGSEGV); } static int kstack_depth_to_print = 24; diff --git a/arch/h8300/mm/fault.c b/arch/h8300/mm/fault.c index d4bc9c16f2df..0223528565dd 100644 --- a/arch/h8300/mm/fault.c +++ b/arch/h8300/mm/fault.c @@ -51,7 +51,7 @@ asmlinkage int do_page_fault(struct pt_regs *regs, unsigned long address, printk(" at virtual address %08lx\n", address); if (!user_mode(regs)) die("Oops", regs, error_code); - do_exit(SIGKILL); + make_dead_task(SIGKILL); return 1; } diff --git a/arch/hexagon/kernel/traps.c b/arch/hexagon/kernel/traps.c index edfc35dafeb1..6dd6cf0ab711 100644 --- a/arch/hexagon/kernel/traps.c +++ b/arch/hexagon/kernel/traps.c @@ -214,7 +214,7 @@ int die(const char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - do_exit(err); + make_dead_task(err); return 0; } diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index 5bfc79be4cef..23c203639a96 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -176,7 +176,7 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr) spin_unlock(&mca_bh_lock); /* This process is about to be killed itself */ - do_exit(SIGKILL); + make_task_dead(SIGKILL); } /** diff --git a/arch/ia64/kernel/traps.c b/arch/ia64/kernel/traps.c index e13cb905930f..753642366e12 100644 --- a/arch/ia64/kernel/traps.c +++ b/arch/ia64/kernel/traps.c @@ -85,7 +85,7 @@ die (const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); return 0; } diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 02de2e70c587..4796cccbf74f 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -259,7 +259,7 @@ retry: regs = NULL; bust_spinlocks(0); if (regs) - do_exit(SIGKILL); + make_task_dead(SIGKILL); return; out_of_memory: diff --git a/arch/m68k/kernel/traps.c b/arch/m68k/kernel/traps.c index 34d6458340b0..59fc63feb0dc 100644 --- a/arch/m68k/kernel/traps.c +++ b/arch/m68k/kernel/traps.c @@ -1131,7 +1131,7 @@ void die_if_kernel (char *str, struct pt_regs *fp, int nr) pr_crit("%s: %08x\n", str, nr); show_registers(fp); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } asmlinkage void set_esp0(unsigned long ssp) diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index ef46e77e97a5..fcb3a0d8421c 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -48,7 +48,7 @@ int send_fault_sig(struct pt_regs *regs) pr_alert("Unable to handle kernel access"); pr_cont(" at virtual address %p\n", addr); die_if_kernel("Oops", regs, 0 /*error_code*/); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } return 1; diff --git a/arch/microblaze/kernel/exceptions.c b/arch/microblaze/kernel/exceptions.c index 908788497b28..fd153d5fab98 100644 --- a/arch/microblaze/kernel/exceptions.c +++ b/arch/microblaze/kernel/exceptions.c @@ -44,10 +44,10 @@ void die(const char *str, struct pt_regs *fp, long err) pr_warn("Oops: %s, sig: %ld\n", str, err); show_regs(fp); spin_unlock_irq(&die_lock); - /* do_exit() should take care of panic'ing from an interrupt + /* make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); } /* for user application debugging */ diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index d26b0fb8ea06..a486486b2355 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -422,7 +422,7 @@ void __noreturn die(const char *str, struct pt_regs *regs) if (regs && kexec_should_crash(current)) crash_kexec(regs); - do_exit(sig); + make_task_dead(sig); } extern struct exception_table_entry __start___dbe_table[]; diff --git a/arch/nds32/kernel/fpu.c b/arch/nds32/kernel/fpu.c index 9edd7ed7d7bf..701c09a668de 100644 --- a/arch/nds32/kernel/fpu.c +++ b/arch/nds32/kernel/fpu.c @@ -223,7 +223,7 @@ inline void handle_fpu_exception(struct pt_regs *regs) } } else if (fpcsr & FPCSR_mskRIT) { if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); si_signo = SIGILL; } diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index ca75d475eda4..c0a8f3344fb9 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -141,7 +141,7 @@ void __noreturn die(const char *str, struct pt_regs *regs, int err) bust_spinlocks(0); spin_unlock_irq(&die_lock); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } EXPORT_SYMBOL(die); @@ -240,7 +240,7 @@ void unhandled_interruption(struct pt_regs *regs) pr_emerg("unhandled_interruption\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL); } @@ -251,7 +251,7 @@ void unhandled_exceptions(unsigned long entry, unsigned long addr, addr, type); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGKILL); + make_task_dead(SIGKILL); force_sig(SIGKILL); } @@ -278,7 +278,7 @@ void do_revinsn(struct pt_regs *regs) pr_emerg("Reserved Instruction\n"); show_regs(regs); if (!user_mode(regs)) - do_exit(SIGILL); + make_task_dead(SIGILL); force_sig(SIGILL); } diff --git a/arch/nios2/kernel/traps.c b/arch/nios2/kernel/traps.c index 596986a74a26..85ac49d64cf7 100644 --- a/arch/nios2/kernel/traps.c +++ b/arch/nios2/kernel/traps.c @@ -37,10 +37,10 @@ void die(const char *str, struct pt_regs *regs, long err) show_regs(regs); spin_unlock_irq(&die_lock); /* - * do_exit() should take care of panic'ing from an interrupt + * make_task_dead() should take care of panic'ing from an interrupt * context so we don't handle it here */ - do_exit(err); + make_task_dead(err); } void _exception(int signo, struct pt_regs *regs, int code, unsigned long addr) diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c index 0898cb159fac..0446a3c34372 100644 --- a/arch/openrisc/kernel/traps.c +++ b/arch/openrisc/kernel/traps.c @@ -212,7 +212,7 @@ void __noreturn die(const char *str, struct pt_regs *regs, long err) __asm__ __volatile__("l.nop 1"); do {} while (1); #endif - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* This is normally the 'Oops' routine */ diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c index b11fb26ce299..df2122c50d78 100644 --- a/arch/parisc/kernel/traps.c +++ b/arch/parisc/kernel/traps.c @@ -269,7 +269,7 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err) panic("Fatal exception"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } /* gdb uses break 4,8 */ diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c index 11741703d26e..a08bb7cefdc5 100644 --- a/arch/powerpc/kernel/traps.c +++ b/arch/powerpc/kernel/traps.c @@ -245,7 +245,7 @@ static void oops_end(unsigned long flags, struct pt_regs *regs, if (panic_on_oops) panic("Fatal exception"); - do_exit(signr); + make_task_dead(signr); } NOKPROBE_SYMBOL(oops_end); @@ -792,9 +792,9 @@ int machine_check_generic(struct pt_regs *regs) void die_mce(const char *str, struct pt_regs *regs, long err) { /* - * The machine check wants to kill the interrupted context, but - * do_exit() checks for in_interrupt() and panics in that case, so - * exit the irq/nmi before calling die. + * The machine check wants to kill the interrupted context, + * but make_task_dead() checks for in_interrupt() and panics + * in that case, so exit the irq/nmi before calling die. */ if (in_nmi()) nmi_exit(); diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 0daaa3e4630d..fe92e119e6a3 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -54,7 +54,7 @@ void die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception"); if (ret != NOTIFY_STOP) - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index aa08dd2f8fae..42118bc728f9 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -31,7 +31,7 @@ static void die_kernel_fault(const char *msg, unsigned long addr, bust_spinlocks(0); die(regs, "Oops"); - do_exit(SIGKILL); + make_task_dead(SIGKILL); } static inline void no_context(struct pt_regs *regs, unsigned long addr) diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 0681c55e831d..1e3233eb510a 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -224,5 +224,5 @@ void __noreturn die(struct pt_regs *regs, const char *str) if (panic_on_oops) panic("Fatal exception: panic_on_oops"); oops_exit(); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 20f8e1868853..a4d8c058dd27 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -175,7 +175,7 @@ void __s390_handle_mcck(void) "malfunction (code 0x%016lx).\n", mcck.mcck_code); printk(KERN_EMERG "mcck: task: %s, pid: %d.\n", current->comm, current->pid); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } } diff --git a/arch/sh/kernel/traps.c b/arch/sh/kernel/traps.c index cbe3201d4f21..01884054aeb2 100644 --- a/arch/sh/kernel/traps.c +++ b/arch/sh/kernel/traps.c @@ -57,7 +57,7 @@ void __noreturn die(const char *str, struct pt_regs *regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(SIGSEGV); + make_task_dead(SIGSEGV); } void die_if_kernel(const char *str, struct pt_regs *regs, long err) diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c index 5630e5a395e0..179aabfa712e 100644 --- a/arch/sparc/kernel/traps_32.c +++ b/arch/sparc/kernel/traps_32.c @@ -86,9 +86,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } printk("Instruction DUMP:"); instruction_dump ((unsigned long *) regs->pc); - if(regs->psr & PSR_PS) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->psr & PSR_PS) ? SIGKILL : SIGSEGV); } void do_hw_interrupt(struct pt_regs *regs, unsigned long type) diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c index 6863025ed56d..21077821f427 100644 --- a/arch/sparc/kernel/traps_64.c +++ b/arch/sparc/kernel/traps_64.c @@ -2559,9 +2559,7 @@ void __noreturn die_if_kernel(char *str, struct pt_regs *regs) } if (panic_on_oops) panic("Fatal exception"); - if (regs->tstate & TSTATE_PRIV) - do_exit(SIGKILL); - do_exit(SIGSEGV); + make_task_dead((regs->tstate & TSTATE_PRIV)? SIGKILL : SIGSEGV); } EXPORT_SYMBOL(die_if_kernel); diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ccb9d32768f3..7738fad6a85e 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1248,14 +1248,14 @@ SYM_CODE_START(asm_exc_nmi) SYM_CODE_END(asm_exc_nmi) .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp movl PER_CPU_VAR(cpu_current_top_of_stack), %esi leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp - call do_exit + call make_task_dead 1: jmp 1b -SYM_CODE_END(rewind_stack_do_exit) +SYM_CODE_END(rewind_stack_and_make_dead) .popsection diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e38a4cf795d9..f09276457942 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1429,7 +1429,7 @@ SYM_CODE_END(ignore_sysret) #endif .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_do_exit) +SYM_CODE_START(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp @@ -1438,6 +1438,6 @@ SYM_CODE_START(rewind_stack_do_exit) leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS - call do_exit -SYM_CODE_END(rewind_stack_do_exit) + call make_task_dead +SYM_CODE_END(rewind_stack_and_make_dead) .popsection diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index ea4fe192189d..53de044e5654 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -351,7 +351,7 @@ unsigned long oops_begin(void) } NOKPROBE_SYMBOL(oops_begin); -void __noreturn rewind_stack_do_exit(int signr); +void __noreturn rewind_stack_and_make_dead(int signr); void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { @@ -386,7 +386,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * reuse the task stack and that existing poisons are invalid. */ kasan_unpoison_task_stack(current); - rewind_stack_do_exit(signr); + rewind_stack_and_make_dead(signr); } NOKPROBE_SYMBOL(oops_end); diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 4b4dbeb2d612..9345007d474d 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -552,5 +552,5 @@ void __noreturn die(const char * str, struct pt_regs * regs, long err) if (panic_on_oops) panic("Fatal exception"); - do_exit(err); + make_task_dead(err); } diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index ba88a6987400..2d4bbd9c3278 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -59,6 +59,7 @@ extern void sched_post_fork(struct task_struct *p, extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); +void __noreturn make_task_dead(int signr); extern void proc_caches_init(void); diff --git a/kernel/exit.c b/kernel/exit.c index f702a6a63686..bfa513c5b227 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -884,6 +884,15 @@ void __noreturn do_exit(long code) } EXPORT_SYMBOL_GPL(do_exit); +void __noreturn make_task_dead(int signr) +{ + /* + * Take the task off the cpu after something catastrophic has + * happened. + */ + do_exit(signr); +} + void complete_and_exit(struct completion *comp, long code) { if (comp) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 21735829b860..e6ab5687770b 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -168,6 +168,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", + "make_task_dead", "__module_put_and_exit", "complete_and_exit", "__reiserfs_panic", @@ -175,7 +176,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "fortify_panic", "usercopy_abort", "machine_real_restart", - "rewind_stack_do_exit", + "rewind_stack_and_make_dead" "kunit_try_catch_throw", "xen_start_kernel", "cpu_bringup_and_idle", -- cgit v1.2.3 From bbda86e988d4c124e4cfa816291cbd583ae8bfb1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 22 Nov 2021 10:27:36 -0600 Subject: exit: Implement kthread_exit The way the per task_struct exit_code is used by kernel threads is not quite compatible how it is used by userspace applications. The low byte of the userspace exit_code value encodes the exit signal. While kthreads just use the value as an int holding ordinary kernel function exit status like -EPERM. Add kthread_exit to clearly separate the two kinds of uses. Signed-off-by: "Eric W. Biederman" --- include/linux/kthread.h | 1 + kernel/kthread.c | 23 +++++++++++++++++++---- tools/objtool/check.c | 1 + 3 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 346b0f269161..22c43d419687 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -70,6 +70,7 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); +void kthread_exit(long result) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/kernel/kthread.c b/kernel/kthread.c index 7113003fab63..77b7c3f23f18 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -268,6 +268,21 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); +/** + * kthread_exit - Cause the current kthread return @result to kthread_stop(). + * @result: The integer value to return to kthread_stop(). + * + * While kthread_exit can be called directly, it exists so that + * functions which do some additional work in non-modular code such as + * module_put_and_kthread_exit can be implemented. + * + * Does not return. + */ +void __noreturn kthread_exit(long result) +{ + do_exit(result); +} + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; @@ -286,13 +301,13 @@ static int kthread(void *_create) done = xchg(&create->done, NULL); if (!done) { kfree(create); - do_exit(-EINTR); + kthread_exit(-EINTR); } if (!self) { create->result = ERR_PTR(-ENOMEM); complete(done); - do_exit(-ENOMEM); + kthread_exit(-ENOMEM); } self->threadfn = threadfn; @@ -326,7 +341,7 @@ static int kthread(void *_create) __kthread_parkme(self); ret = threadfn(data); } - do_exit(ret); + kthread_exit(ret); } /* called from kernel_clone() to get node information for about to be created task */ @@ -627,7 +642,7 @@ EXPORT_SYMBOL_GPL(kthread_park); * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * - * If threadfn() may call do_exit() itself, the caller must ensure + * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() diff --git a/tools/objtool/check.c b/tools/objtool/check.c index e6ab5687770b..90108fe5610d 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -168,6 +168,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "panic", "do_exit", "do_task_dead", + "kthread_exit", "make_task_dead", "__module_put_and_exit", "complete_and_exit", -- cgit v1.2.3 From ca3574bd653aba234a4b31955f2778947403be16 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 3 Dec 2021 11:00:19 -0600 Subject: exit: Rename module_put_and_exit to module_put_and_kthread_exit Update module_put_and_exit to call kthread_exit instead of do_exit. Change the name to reflect this change in functionality. All of the users of module_put_and_exit are causing the current kthread to exit so this change makes it clear what is happening. There is no functional change. Signed-off-by: "Eric W. Biederman" --- crypto/algboss.c | 4 ++-- fs/cifs/connect.c | 2 +- fs/nfs/callback.c | 4 ++-- fs/nfs/nfs4state.c | 2 +- fs/nfsd/nfssvc.c | 2 +- include/linux/module.h | 6 +++--- kernel/module.c | 6 +++--- net/bluetooth/bnep/core.c | 2 +- net/bluetooth/cmtp/core.c | 2 +- net/bluetooth/hidp/core.c | 2 +- tools/objtool/check.c | 2 +- 11 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/crypto/algboss.c b/crypto/algboss.c index 1814d2c5188a..eb5fe84efb83 100644 --- a/crypto/algboss.c +++ b/crypto/algboss.c @@ -67,7 +67,7 @@ out: complete_all(¶m->larval->completion); crypto_alg_put(¶m->larval->alg); kfree(param); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int cryptomgr_schedule_probe(struct crypto_larval *larval) @@ -190,7 +190,7 @@ skiptest: crypto_alg_tested(param->driver, err); kfree(param); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } static int cryptomgr_schedule_test(struct crypto_alg *alg) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 82577a7a5bb1..39fbe9acbf51 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1139,7 +1139,7 @@ next_pdu: } memalloc_noreclaim_restore(noreclaim_flag); - module_put_and_exit(0); + module_put_and_kthread_exit(0); } /* diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 86d856de1389..3c86a559a321 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -93,7 +93,7 @@ nfs4_callback_svc(void *vrqstp) svc_process(rqstp); } svc_exit_thread(rqstp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } @@ -137,7 +137,7 @@ nfs41_callback_svc(void *vrqstp) } } svc_exit_thread(rqstp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ecc4594299d6..ea41af731978 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2689,6 +2689,6 @@ static int nfs4_run_state_manager(void *ptr) allow_signal(SIGKILL); nfs4_state_manager(clp); nfs_put_client(clp); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 80431921e5d7..5ce9f14318c4 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -986,7 +986,7 @@ out: /* Release module */ mutex_unlock(&nfsd_mutex); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/include/linux/module.h b/include/linux/module.h index c9f1200b2312..f03be97e9ec1 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -595,9 +595,9 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); -extern void __noreturn __module_put_and_exit(struct module *mod, +extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); -#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code) +#define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); @@ -790,7 +790,7 @@ static inline int unregister_module_notifier(struct notifier_block *nb) return 0; } -#define module_put_and_exit(code) do_exit(code) +#define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { diff --git a/kernel/module.c b/kernel/module.c index 84a9141a5e15..a3aa00bf270d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -337,12 +337,12 @@ static inline void add_taint_module(struct module *mod, unsigned flag, * A thread that wants to hold a reference to a module only while it * is running can call this to safely exit. nfsd and lockd use this. */ -void __noreturn __module_put_and_exit(struct module *mod, long code) +void __noreturn __module_put_and_kthread_exit(struct module *mod, long code) { module_put(mod); - do_exit(code); + kthread_exit(code); } -EXPORT_SYMBOL(__module_put_and_exit); +EXPORT_SYMBOL(__module_put_and_kthread_exit); /* Find a module section: 0 means not found. */ static unsigned int find_sec(const struct load_info *info, const char *name) diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index c9add7753b9f..40baa6b7321a 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -535,7 +535,7 @@ static int bnep_session(void *arg) up_write(&bnep_session_sem); free_netdev(dev); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bluetooth/cmtp/core.c b/net/bluetooth/cmtp/core.c index 0a2d78e811cf..9bfded6b74b3 100644 --- a/net/bluetooth/cmtp/core.c +++ b/net/bluetooth/cmtp/core.c @@ -323,7 +323,7 @@ static int cmtp_session(void *arg) up_write(&cmtp_session_sem); kfree(session); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index 80848dfc01db..5940744a8cd8 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -1305,7 +1305,7 @@ static int hidp_session_thread(void *arg) l2cap_unregister_user(session->conn, &session->user); hidp_session_put(session); - module_put_and_exit(0); + module_put_and_kthread_exit(0); return 0; } diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 90108fe5610d..120e9598c11a 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -170,7 +170,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "do_task_dead", "kthread_exit", "make_task_dead", - "__module_put_and_exit", + "__module_put_and_kthread_exit", "complete_and_exit", "__reiserfs_panic", "lbug_with_loc", -- cgit v1.2.3 From cead18552660702a4a46f58e65188fe5f36e9dfe Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 22 Nov 2021 11:15:19 -0600 Subject: exit: Rename complete_and_exit to kthread_complete_and_exit Update complete_and_exit to call kthread_exit instead of do_exit. Change the name to reflect this change in functionality. All of the users of complete_and_exit are causing the current kthread to exit so this change makes it clear what is happening. Move the implementation of kthread_complete_and_exit from kernel/exit.c to to kernel/kthread.c. As this function is kthread specific it makes most sense to live with the kthread functions. There are no functional change. Signed-off-by: "Eric W. Biederman" --- drivers/net/wireless/rsi/rsi_91x_coex.c | 2 +- drivers/net/wireless/rsi/rsi_91x_main.c | 2 +- drivers/net/wireless/rsi/rsi_91x_sdio_ops.c | 2 +- drivers/net/wireless/rsi/rsi_91x_usb_ops.c | 2 +- drivers/pnp/pnpbios/core.c | 6 +++--- drivers/staging/rts5208/rtsx.c | 16 ++++++++-------- drivers/usb/atm/usbatm.c | 2 +- drivers/usb/gadget/function/f_mass_storage.c | 2 +- fs/jffs2/background.c | 2 +- include/linux/kernel.h | 1 - include/linux/kthread.h | 1 + kernel/exit.c | 9 --------- kernel/kthread.c | 21 +++++++++++++++++++++ lib/kunit/try-catch.c | 4 ++-- tools/objtool/check.c | 2 +- 15 files changed, 43 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/rsi/rsi_91x_coex.c b/drivers/net/wireless/rsi/rsi_91x_coex.c index a0c5d02ae88c..8a3d86897ea8 100644 --- a/drivers/net/wireless/rsi/rsi_91x_coex.c +++ b/drivers/net/wireless/rsi/rsi_91x_coex.c @@ -63,7 +63,7 @@ static void rsi_coex_scheduler_thread(struct rsi_common *common) rsi_coex_sched_tx_pkts(coex_cb); } while (atomic_read(&coex_cb->coex_tx_thread.thread_done) == 0); - complete_and_exit(&coex_cb->coex_tx_thread.completion, 0); + kthread_complete_and_exit(&coex_cb->coex_tx_thread.completion, 0); } int rsi_coex_recv_pkt(struct rsi_common *common, u8 *msg) diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c index f1bf71e6c608..c7f5cec5e446 100644 --- a/drivers/net/wireless/rsi/rsi_91x_main.c +++ b/drivers/net/wireless/rsi/rsi_91x_main.c @@ -260,7 +260,7 @@ static void rsi_tx_scheduler_thread(struct rsi_common *common) if (common->init_done) rsi_core_qos_processor(common); } while (atomic_read(&common->tx_thread.thread_done) == 0); - complete_and_exit(&common->tx_thread.completion, 0); + kthread_complete_and_exit(&common->tx_thread.completion, 0); } #ifdef CONFIG_RSI_COEX diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c index 8ace1874e5cb..b2b47a0abcbf 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c @@ -75,7 +75,7 @@ void rsi_sdio_rx_thread(struct rsi_common *common) rsi_dbg(INFO_ZONE, "%s: Terminated SDIO RX thread\n", __func__); atomic_inc(&sdev->rx_thread.thread_done); - complete_and_exit(&sdev->rx_thread.completion, 0); + kthread_complete_and_exit(&sdev->rx_thread.completion, 0); } /** diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c index 4ffcdde1acb1..5130b0e72adc 100644 --- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c +++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c @@ -56,6 +56,6 @@ void rsi_usb_rx_thread(struct rsi_common *common) out: rsi_dbg(INFO_ZONE, "%s: Terminated thread\n", __func__); skb_queue_purge(&dev->rx_q); - complete_and_exit(&dev->rx_thread.completion, 0); + kthread_complete_and_exit(&dev->rx_thread.completion, 0); } diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c index 669ef4700c1a..f7e86ae9f72f 100644 --- a/drivers/pnp/pnpbios/core.c +++ b/drivers/pnp/pnpbios/core.c @@ -160,7 +160,7 @@ static int pnp_dock_thread(void *unused) * No dock to manage */ case PNP_FUNCTION_NOT_SUPPORTED: - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); case PNP_SYSTEM_NOT_DOCKED: d = 0; break; @@ -170,7 +170,7 @@ static int pnp_dock_thread(void *unused) default: pnpbios_print_status("pnp_dock_thread", status); printk(KERN_WARNING "PnPBIOS: disabling dock monitoring.\n"); - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); } if (d != docked) { if (pnp_dock_event(d, &now) == 0) { @@ -183,7 +183,7 @@ static int pnp_dock_thread(void *unused) } } } - complete_and_exit(&unload_sem, 0); + kthread_complete_and_exit(&unload_sem, 0); } static int pnpbios_get_resources(struct pnp_dev *dev) diff --git a/drivers/staging/rts5208/rtsx.c b/drivers/staging/rts5208/rtsx.c index 91fcf85e150a..5a58dac76c88 100644 --- a/drivers/staging/rts5208/rtsx.c +++ b/drivers/staging/rts5208/rtsx.c @@ -450,13 +450,13 @@ skip_for_abort: * after the down() -- that's necessary for the thread-shutdown * case. * - * complete_and_exit() goes even further than this -- it is safe in - * the case that the thread of the caller is going away (not just - * the structure) -- this is necessary for the module-remove case. - * This is important in preemption kernels, which transfer the flow - * of execution immediately upon a complete(). + * kthread_complete_and_exit() goes even further than this -- + * it is safe in the case that the thread of the caller is going away + * (not just the structure) -- this is necessary for the module-remove + * case. This is important in preemption kernels, which transfer the + * flow of execution immediately upon a complete(). */ - complete_and_exit(&dev->control_exit, 0); + kthread_complete_and_exit(&dev->control_exit, 0); } static int rtsx_polling_thread(void *__dev) @@ -501,7 +501,7 @@ static int rtsx_polling_thread(void *__dev) mutex_unlock(&dev->dev_mutex); } - complete_and_exit(&dev->polling_exit, 0); + kthread_complete_and_exit(&dev->polling_exit, 0); } /* @@ -682,7 +682,7 @@ static int rtsx_scan_thread(void *__dev) /* Should we unbind if no devices were detected? */ } - complete_and_exit(&dev->scanning_done, 0); + kthread_complete_and_exit(&dev->scanning_done, 0); } static void rtsx_init_options(struct rtsx_chip *chip) diff --git a/drivers/usb/atm/usbatm.c b/drivers/usb/atm/usbatm.c index da17be1ef64e..e3a49d837609 100644 --- a/drivers/usb/atm/usbatm.c +++ b/drivers/usb/atm/usbatm.c @@ -969,7 +969,7 @@ static int usbatm_do_heavy_init(void *arg) instance->thread = NULL; mutex_unlock(&instance->serialize); - complete_and_exit(&instance->thread_exited, ret); + kthread_complete_and_exit(&instance->thread_exited, ret); } static int usbatm_heavy_init(struct usbatm_data *instance) diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c index 752439690fda..46dd11dcb3a8 100644 --- a/drivers/usb/gadget/function/f_mass_storage.c +++ b/drivers/usb/gadget/function/f_mass_storage.c @@ -2547,7 +2547,7 @@ static int fsg_main_thread(void *common_) up_write(&common->filesem); /* Let fsg_unbind() know the thread has exited */ - complete_and_exit(&common->thread_notifier, 0); + kthread_complete_and_exit(&common->thread_notifier, 0); } diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c index 2b4d5013dc5d..6da92ecaf66d 100644 --- a/fs/jffs2/background.c +++ b/fs/jffs2/background.c @@ -161,5 +161,5 @@ static int jffs2_garbage_collect_thread(void *_c) spin_lock(&c->erase_completion_lock); c->gc_task = NULL; spin_unlock(&c->erase_completion_lock); - complete_and_exit(&c->gc_thread_exit, 0); + kthread_complete_and_exit(&c->gc_thread_exit, 0); } diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..055eb203c00e 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -187,7 +187,6 @@ static inline void might_fault(void) { } #endif void do_exit(long error_code) __noreturn; -void complete_and_exit(struct completion *, long) __noreturn; extern int num_to_str(char *buf, int size, unsigned long long num, unsigned int width); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 22c43d419687..d86a7e3b9a52 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -71,6 +71,7 @@ int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); void kthread_exit(long result) __noreturn; +void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/kernel/exit.c b/kernel/exit.c index 57afac845a0a..6c4b04531f17 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -891,15 +891,6 @@ void __noreturn make_task_dead(int signr) do_exit(signr); } -void complete_and_exit(struct completion *comp, long code) -{ - if (comp) - complete(comp); - - do_exit(code); -} -EXPORT_SYMBOL(complete_and_exit); - SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); diff --git a/kernel/kthread.c b/kernel/kthread.c index 77b7c3f23f18..4388d6694a7f 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -283,6 +283,27 @@ void __noreturn kthread_exit(long result) do_exit(result); } +/** + * kthread_complete_and exit - Exit the current kthread. + * @comp: Completion to complete + * @code: The integer value to return to kthread_stop(). + * + * If present complete @comp and the reuturn code to kthread_stop(). + * + * A kernel thread whose module may be removed after the completion of + * @comp can use this function exit safely. + * + * Does not return. + */ +void __noreturn kthread_complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + kthread_exit(code); +} +EXPORT_SYMBOL(kthread_complete_and_exit); + static int kthread(void *_create) { static const struct sched_param param = { .sched_priority = 0 }; diff --git a/lib/kunit/try-catch.c b/lib/kunit/try-catch.c index 0dd434e40487..be38a2c5ecc2 100644 --- a/lib/kunit/try-catch.c +++ b/lib/kunit/try-catch.c @@ -17,7 +17,7 @@ void __noreturn kunit_try_catch_throw(struct kunit_try_catch *try_catch) { try_catch->try_result = -EFAULT; - complete_and_exit(try_catch->try_completion, -EFAULT); + kthread_complete_and_exit(try_catch->try_completion, -EFAULT); } EXPORT_SYMBOL_GPL(kunit_try_catch_throw); @@ -27,7 +27,7 @@ static int kunit_generic_run_threadfn_adapter(void *data) try_catch->try(try_catch->context); - complete_and_exit(try_catch->try_completion, 0); + kthread_complete_and_exit(try_catch->try_completion, 0); } static unsigned long kunit_test_timeout(void) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 120e9598c11a..282273a1ffa5 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -171,7 +171,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func, "kthread_exit", "make_task_dead", "__module_put_and_kthread_exit", - "complete_and_exit", + "kthread_complete_and_exit", "__reiserfs_panic", "lbug_with_loc", "fortify_panic", -- cgit v1.2.3 From 40966e316f86b8cfd83abd31ccb4df729309d3e7 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Dec 2021 09:56:14 -0600 Subject: kthread: Ensure struct kthread is present for all kthreads Today the rules are a bit iffy and arbitrary about which kernel threads have struct kthread present. Both idle threads and thread started with create_kthread want struct kthread present so that is effectively all kernel threads. Make the rule that if PF_KTHREAD and the task is running then struct kthread is present. This will allow the kernel thread code to using tsk->exit_code with different semantics from ordinary processes. To make ensure that struct kthread is present for all kernel threads move it's allocation into copy_process. Add a deallocation of struct kthread in exec for processes that were kernel threads. Move the allocation of struct kthread for the initial thread earlier so that it is not repeated for each additional idle thread. Move the initialization of struct kthread into set_kthread_struct so that the structure is always and reliably initailized. Clear set_child_tid in free_kthread_struct to ensure the kthread struct is reliably freed during exec. The function free_kthread_struct does not need to clear vfork_done during exec as exec_mm_release called from exec_mmap has already cleared vfork_done. Signed-off-by: "Eric W. Biederman" --- fs/exec.c | 2 ++ include/linux/kthread.h | 2 +- kernel/fork.c | 4 ++++ kernel/kthread.c | 31 ++++++++++++++----------------- kernel/sched/core.c | 16 ++++++++-------- 5 files changed, 29 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 537d92c41105..59cac7c18178 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1307,6 +1307,8 @@ int begin_new_exec(struct linux_binprm * bprm) */ force_uaccess_begin(); + if (me->flags & PF_KTHREAD) + free_kthread_struct(me); me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_KTHREAD | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index d86a7e3b9a52..4f3433afb54b 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,7 +33,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); -void set_kthread_struct(struct task_struct *p); +bool set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); bool kthread_is_per_cpu(struct task_struct *k); diff --git a/kernel/fork.c b/kernel/fork.c index 3244cc56b697..04fa3e5d97af 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2118,6 +2118,10 @@ static __latent_entropy struct task_struct *copy_process( p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); + if (p->flags & PF_KTHREAD) { + if (!set_kthread_struct(p)) + goto bad_fork_cleanup_threadgroup_lock; + } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { diff --git a/kernel/kthread.c b/kernel/kthread.c index 4388d6694a7f..8e5f44bed027 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -93,20 +93,27 @@ static inline struct kthread *__to_kthread(struct task_struct *p) return kthread; } -void set_kthread_struct(struct task_struct *p) +bool set_kthread_struct(struct task_struct *p) { struct kthread *kthread; - if (__to_kthread(p)) - return; + if (WARN_ON_ONCE(to_kthread(p))) + return false; kthread = kzalloc(sizeof(*kthread), GFP_KERNEL); + if (!kthread) + return false; + + init_completion(&kthread->exited); + init_completion(&kthread->parked); + p->vfork_done = &kthread->exited; + /* * We abuse ->set_child_tid to avoid the new member and because it - * can't be wrongly copied by copy_process(). We also rely on fact - * that the caller can't exec, so PF_KTHREAD can't be cleared. + * can't be wrongly copied by copy_process(). */ p->set_child_tid = (__force void __user *)kthread; + return true; } void free_kthread_struct(struct task_struct *k) @@ -114,13 +121,13 @@ void free_kthread_struct(struct task_struct *k) struct kthread *kthread; /* - * Can be NULL if this kthread was created by kernel_thread() - * or if kmalloc() in kthread() failed. + * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread && kthread->blkcg_css); #endif + k->set_child_tid = (__force void __user *)NULL; kfree(kthread); } @@ -315,7 +322,6 @@ static int kthread(void *_create) struct kthread *self; int ret; - set_kthread_struct(current); self = to_kthread(current); /* If user was SIGKILLed, I release the structure. */ @@ -325,17 +331,8 @@ static int kthread(void *_create) kthread_exit(-EINTR); } - if (!self) { - create->result = ERR_PTR(-ENOMEM); - complete(done); - kthread_exit(-ENOMEM); - } - self->threadfn = threadfn; self->data = data; - init_completion(&self->exited); - init_completion(&self->parked); - current->vfork_done = &self->exited; /* * The new thread inherited kthreadd's priority and CPU mask. Reset diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3c9b0fda64ac..0404a8c572a1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8599,14 +8599,6 @@ void __init init_idle(struct task_struct *idle, int cpu) __sched_fork(0, idle); - /* - * The idle task doesn't need the kthread struct to function, but it - * is dressed up as a per-CPU kthread and thus needs to play the part - * if we want to avoid special-casing it in code that deals with per-CPU - * kthreads. - */ - set_kthread_struct(idle); - raw_spin_lock_irqsave(&idle->pi_lock, flags); raw_spin_rq_lock(rq); @@ -9427,6 +9419,14 @@ void __init sched_init(void) mmgrab(&init_mm); enter_lazy_tlb(&init_mm, current); + /* + * The idle task doesn't need the kthread struct to function, but it + * is dressed up as a per-CPU kthread and thus needs to play the part + * if we want to avoid special-casing it in code that deals with per-CPU + * kthreads. + */ + WARN_ON(set_kthread_struct(current)); + /* * Make us the idle thread. Technically, schedule() should not be * called from this thread, however somewhere below it might be, -- cgit v1.2.3 From df5e49c880ea0776806b8a9f8ab95e035272cf6f Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: SUNRPC: change svc_get() to return the svc. It is common for 'get' functions to return the object that was 'got', and there are a couple of places where users of svc_get() would be a little simpler if svc_get() did that. Make it so. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 6 ++---- fs/nfs/callback.c | 6 ++---- include/linux/sunrpc/svc.h | 3 ++- 3 files changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index b220e1b91726..2f50d5b2a8a4 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -430,14 +430,12 @@ static struct svc_serv *lockd_create_svc(void) /* * Check whether we're already up and running. */ - if (nlmsvc_rqst) { + if (nlmsvc_rqst) /* * Note: increase service usage, because later in case of error * svc_destroy() will be called. */ - svc_get(nlmsvc_rqst->rq_server); - return nlmsvc_rqst->rq_server; - } + return svc_get(nlmsvc_rqst->rq_server); /* * Sanity check: if there's no pid, diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 86d856de1389..6e5e742a42b8 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -266,14 +266,12 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) /* * Check whether we're already up and running. */ - if (cb_info->serv) { + if (cb_info->serv) /* * Note: increase service usage, because later in case of error * svc_destroy() will be called. */ - svc_get(cb_info->serv); - return cb_info->serv; - } + return svc_get(cb_info->serv); switch (minorversion) { case 0: diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 0ae28ae6caf2..5d9568953fcd 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -120,9 +120,10 @@ struct svc_serv { * change the number of threads. Horrible, but there it is. * Should be called with the "service mutex" held. */ -static inline void svc_get(struct svc_serv *serv) +static inline struct svc_serv *svc_get(struct svc_serv *serv) { serv->sv_nrthreads++; + return serv; } /* -- cgit v1.2.3 From 8c62d12740a1450d2e8456d5747f440e10db281a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: SUNRPC/NFSD: clean up get/put functions. svc_destroy() is poorly named - it doesn't necessarily destroy the svc, it might just reduce the ref count. nfsd_destroy() is poorly named for the same reason. This patch: - removes the refcount functionality from svc_destroy(), moving it to a new svc_put(). Almost all previous callers of svc_destroy() now call svc_put(). - renames nfsd_destroy() to nfsd_put() and improves the code, using the new svc_destroy() rather than svc_put() - removes a few comments that explain the important for balanced get/put calls. This should be obvious. The only non-trivial part of this is that svc_destroy() would call svc_sock_update() on a non-final decrement. It can no longer do that, and svc_put() isn't really a good place of it. This call is now made from svc_exit_thread() which seems like a good place. This makes the call *before* sv_nrthreads is decremented rather than after. This is not particularly important as the call just sets a flag which causes sv_nrthreads set be checked later. A subsequent patch will improve the ordering. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 6 +----- fs/nfs/callback.c | 14 ++------------ fs/nfsd/nfsctl.c | 4 ++-- fs/nfsd/nfsd.h | 2 +- fs/nfsd/nfssvc.c | 30 ++++++++++++++++-------------- include/linux/sunrpc/svc.h | 26 +++++++++++++++++++++++--- net/sunrpc/svc.c | 19 +++++-------------- 7 files changed, 50 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 2f50d5b2a8a4..135bd86ed3ad 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -431,10 +431,6 @@ static struct svc_serv *lockd_create_svc(void) * Check whether we're already up and running. */ if (nlmsvc_rqst) - /* - * Note: increase service usage, because later in case of error - * svc_destroy() will be called. - */ return svc_get(nlmsvc_rqst->rq_server); /* @@ -495,7 +491,7 @@ int lockd_up(struct net *net, const struct cred *cred) * so we exit through here on both success and failure. */ err_put: - svc_destroy(serv); + svc_put(serv); err_create: mutex_unlock(&nlmsvc_mutex); return error; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 6e5e742a42b8..edbc7579b4aa 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -267,10 +267,6 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion) * Check whether we're already up and running. */ if (cb_info->serv) - /* - * Note: increase service usage, because later in case of error - * svc_destroy() will be called. - */ return svc_get(cb_info->serv); switch (minorversion) { @@ -333,16 +329,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) goto err_start; cb_info->users++; - /* - * svc_create creates the svc_serv with sv_nrthreads == 1, and then - * svc_prepare_thread increments that. So we need to call svc_destroy - * on both success and failure so that the refcount is 1 when the - * thread exits. - */ err_net: if (!cb_info->users) cb_info->serv = NULL; - svc_destroy(serv); + svc_put(serv); err_create: mutex_unlock(&nfs_callback_mutex); return ret; @@ -368,7 +358,7 @@ void nfs_callback_down(int minorversion, struct net *net) if (cb_info->users == 0) { svc_get(serv); serv->sv_ops->svo_setup(serv, NULL, 0); - svc_destroy(serv); + svc_put(serv); dprintk("nfs_callback_down: service destroyed\n"); cb_info->serv = NULL; } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index bf4c9996ad92..17521fada83f 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -743,7 +743,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); if (err < 0 && list_empty(&nn->nfsd_serv->sv_permsocks)) { - nfsd_destroy(net); + nfsd_put(net); return err; } @@ -796,7 +796,7 @@ out_err: if (!list_empty(&nn->nfsd_serv->sv_permsocks)) nn->nfsd_serv->sv_nrthreads--; else - nfsd_destroy(net); + nfsd_put(net); return err; } diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 498e5a489826..3e5008b475ff 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -97,7 +97,7 @@ int nfsd_pool_stats_open(struct inode *, struct file *); int nfsd_pool_stats_release(struct inode *, struct file *); void nfsd_shutdown_threads(struct net *net); -void nfsd_destroy(struct net *net); +void nfsd_put(struct net *net); bool i_am_nfsd(void); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 80431921e5d7..a0a7564e6c73 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -623,7 +623,7 @@ void nfsd_shutdown_threads(struct net *net) svc_get(serv); /* Kill outstanding nfsd threads */ serv->sv_ops->svo_setup(serv, NULL, 0); - nfsd_destroy(net); + nfsd_put(net); mutex_unlock(&nfsd_mutex); /* Wait for shutdown of nfsd_serv to complete */ wait_for_completion(&nn->nfsd_shutdown_complete); @@ -656,7 +656,10 @@ int nfsd_create_serv(struct net *net) nn->nfsd_serv->sv_maxconn = nn->max_connections; error = svc_bind(nn->nfsd_serv, net); if (error < 0) { - svc_destroy(nn->nfsd_serv); + /* NOT nfsd_put() as notifiers (see below) haven't + * been set up yet. + */ + svc_put(nn->nfsd_serv); nfsd_complete_shutdown(net); return error; } @@ -697,16 +700,16 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) return 0; } -void nfsd_destroy(struct net *net) +void nfsd_put(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - int destroy = (nn->nfsd_serv->sv_nrthreads == 1); - if (destroy) + nn->nfsd_serv->sv_nrthreads -= 1; + if (nn->nfsd_serv->sv_nrthreads == 0) { svc_shutdown_net(nn->nfsd_serv, net); - svc_destroy(nn->nfsd_serv); - if (destroy) + svc_destroy(nn->nfsd_serv); nfsd_complete_shutdown(net); + } } int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) @@ -758,7 +761,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) if (err) break; } - nfsd_destroy(net); + nfsd_put(net); return err; } @@ -795,7 +798,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) error = nfsd_startup_net(net, cred); if (error) - goto out_destroy; + goto out_put; error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, NULL, nrservs); if (error) @@ -808,8 +811,8 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) out_shutdown: if (error < 0 && !nfsd_up_before) nfsd_shutdown_net(net); -out_destroy: - nfsd_destroy(net); /* Release server */ +out_put: + nfsd_put(net); out: mutex_unlock(&nfsd_mutex); return error; @@ -982,7 +985,7 @@ out: /* Release the thread */ svc_exit_thread(rqstp); - nfsd_destroy(net); + nfsd_put(net); /* Release module */ mutex_unlock(&nfsd_mutex); @@ -1109,8 +1112,7 @@ int nfsd_pool_stats_release(struct inode *inode, struct file *file) struct net *net = inode->i_sb->s_fs_info; mutex_lock(&nfsd_mutex); - /* this function really, really should have been called svc_put() */ - nfsd_destroy(net); + nfsd_put(net); mutex_unlock(&nfsd_mutex); return ret; } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 5d9568953fcd..73d56d33a36d 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -114,8 +114,13 @@ struct svc_serv { #endif /* CONFIG_SUNRPC_BACKCHANNEL */ }; -/* - * We use sv_nrthreads as a reference count. svc_destroy() drops +/** + * svc_get() - increment reference count on a SUNRPC serv + * @serv: the svc_serv to have count incremented + * + * Returns: the svc_serv that was passed in. + * + * We use sv_nrthreads as a reference count. svc_put() drops * this refcount, so we need to bump it up around operations that * change the number of threads. Horrible, but there it is. * Should be called with the "service mutex" held. @@ -126,6 +131,22 @@ static inline struct svc_serv *svc_get(struct svc_serv *serv) return serv; } +void svc_destroy(struct svc_serv *serv); + +/** + * svc_put - decrement reference count on a SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * When the reference count reaches zero, svc_destroy() + * is called to clean up and free the serv. + */ +static inline void svc_put(struct svc_serv *serv) +{ + serv->sv_nrthreads -= 1; + if (serv->sv_nrthreads == 0) + svc_destroy(serv); +} + /* * Maximum payload size supported by a kernel RPC server. * This is use to determine the max number of pages nfsd is @@ -515,7 +536,6 @@ struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); -void svc_destroy(struct svc_serv *); void svc_shutdown_net(struct svc_serv *, struct net *); int svc_process(struct svc_rqst *); int bc_svc_process(struct svc_serv *, struct rpc_rqst *, diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 4292278a9552..55a1bf0d129f 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -528,17 +528,7 @@ EXPORT_SYMBOL_GPL(svc_shutdown_net); void svc_destroy(struct svc_serv *serv) { - dprintk("svc: svc_destroy(%s, %d)\n", - serv->sv_program->pg_name, - serv->sv_nrthreads); - - if (serv->sv_nrthreads) { - if (--(serv->sv_nrthreads) != 0) { - svc_sock_update_bufs(serv); - return; - } - } else - printk("svc_destroy: no threads for serv=%p!\n", serv); + dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); del_timer_sync(&serv->sv_temptimer); @@ -892,9 +882,10 @@ svc_exit_thread(struct svc_rqst *rqstp) svc_rqst_free(rqstp); - /* Release the server */ - if (serv) - svc_destroy(serv); + if (!serv) + return; + svc_sock_update_bufs(serv); + svc_destroy(serv); } EXPORT_SYMBOL_GPL(svc_exit_thread); -- cgit v1.2.3 From ec52361df99b490f6af412b046df9799b92c1050 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: SUNRPC: stop using ->sv_nrthreads as a refcount The use of sv_nrthreads as a general refcount results in clumsy code, as is seen by various comments needed to explain the situation. This patch introduces a 'struct kref' and uses that for reference counting, leaving sv_nrthreads to be a pure count of threads. The kref is managed particularly in svc_get() and svc_put(), and also nfsd_put(); svc_destroy() now takes a pointer to the embedded kref, rather than to the serv. nfsd allows the svc_serv to exist with ->sv_nrhtreads being zero. This happens when a transport is created before the first thread is started. To support this, a 'keep_active' flag is introduced which holds a ref on the svc_serv. This is set when any listening socket is successfully added (unless there are running threads), and cleared when the number of threads is set. So when the last thread exits, the nfs_serv will be destroyed. The use of 'keep_active' replaces previous code which checked if there were any permanent sockets. We no longer clear ->rq_server when nfsd() exits. This was done to prevent svc_exit_thread() from calling svc_destroy(). Instead we take an extra reference to the svc_serv to prevent svc_destroy() from being called. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 4 ---- fs/nfs/callback.c | 2 +- fs/nfsd/netns.h | 7 +++++++ fs/nfsd/nfsctl.c | 22 ++++++++++------------ fs/nfsd/nfssvc.c | 42 ++++++++++++++++++++++++++---------------- include/linux/sunrpc/svc.h | 14 ++++---------- net/sunrpc/svc.c | 22 +++++++++++----------- 7 files changed, 59 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 135bd86ed3ad..a9669b106dbd 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -486,10 +486,6 @@ int lockd_up(struct net *net, const struct cred *cred) goto err_put; } nlmsvc_users++; - /* - * Note: svc_serv structures have an initial use count of 1, - * so we exit through here on both success and failure. - */ err_put: svc_put(serv); err_create: diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index edbc7579b4aa..d9d78ffd1d65 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -169,7 +169,7 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, if (nrservs < NFS4_MIN_NR_CALLBACK_THREADS) nrservs = NFS4_MIN_NR_CALLBACK_THREADS; - if (serv->sv_nrthreads-1 == nrservs) + if (serv->sv_nrthreads == nrservs) return 0; ret = serv->sv_ops->svo_setup(serv, NULL, nrservs); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 935c1028c217..08bcd8f23b01 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -123,6 +123,13 @@ struct nfsd_net { u32 clverifier_counter; struct svc_serv *nfsd_serv; + /* When a listening socket is added to nfsd, keep_active is set + * and this justifies a reference on nfsd_serv. This stops + * nfsd_serv from being freed. When the number of threads is + * set, keep_active is cleared and the reference is dropped. So + * when the last thread exits, the service will be destroyed. + */ + int keep_active; wait_queue_head_t ntf_wq; atomic_t ntf_refcnt; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 17521fada83f..7b557eb8211a 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -742,13 +742,12 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred return err; err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred); - if (err < 0 && list_empty(&nn->nfsd_serv->sv_permsocks)) { - nfsd_put(net); - return err; - } - /* Decrease the count, but don't shut down the service */ - nn->nfsd_serv->sv_nrthreads--; + if (err >= 0 && + !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(nn->nfsd_serv); + + nfsd_put(net); return err; } @@ -783,8 +782,10 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr if (err < 0 && err != -EAFNOSUPPORT) goto out_close; - /* Decrease the count, but don't shut down the service */ - nn->nfsd_serv->sv_nrthreads--; + if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1)) + svc_get(nn->nfsd_serv); + + nfsd_put(net); return 0; out_close: xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port); @@ -793,10 +794,7 @@ out_close: svc_xprt_put(xprt); } out_err: - if (!list_empty(&nn->nfsd_serv->sv_permsocks)) - nn->nfsd_serv->sv_nrthreads--; - else - nfsd_put(net); + nfsd_put(net); return err; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index a0a7564e6c73..5f605e7e8091 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -60,13 +60,13 @@ static __be32 nfsd_init_request(struct svc_rqst *, * extent ->sv_temp_socks and ->sv_permsocks. It also protects nfsdstats.th_cnt * * If (out side the lock) nn->nfsd_serv is non-NULL, then it must point to a - * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0. That number - * of nfsd threads must exist and each must listed in ->sp_all_threads in each - * entry of ->sv_pools[]. + * properly initialised 'struct svc_serv' with ->sv_nrthreads > 0 (unless + * nn->keep_active is set). That number of nfsd threads must + * exist and each must be listed in ->sp_all_threads in some entry of + * ->sv_pools[]. * - * Transitions of the thread count between zero and non-zero are of particular - * interest since the svc_serv needs to be created and initialized at that - * point, or freed. + * Each active thread holds a counted reference on nn->nfsd_serv, as does + * the nn->keep_active flag and various transient calls to svc_get(). * * Finally, the nfsd_mutex also protects some of the global variables that are * accessed when nfsd starts and that are settable via the write_* routines in @@ -700,14 +700,22 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) return 0; } +/* This is the callback for kref_put() below. + * There is no code here as the first thing to be done is + * call svc_shutdown_net(), but we cannot get the 'net' from + * the kref. So do all the work when kref_put returns true. + */ +static void nfsd_noop(struct kref *ref) +{ +} + void nfsd_put(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nn->nfsd_serv->sv_nrthreads -= 1; - if (nn->nfsd_serv->sv_nrthreads == 0) { + if (kref_put(&nn->nfsd_serv->sv_refcnt, nfsd_noop)) { svc_shutdown_net(nn->nfsd_serv, net); - svc_destroy(nn->nfsd_serv); + svc_destroy(&nn->nfsd_serv->sv_refcnt); nfsd_complete_shutdown(net); } } @@ -803,15 +811,14 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) NULL, nrservs); if (error) goto out_shutdown; - /* We are holding a reference to nn->nfsd_serv which - * we don't want to count in the return value, - * so subtract 1 - */ - error = nn->nfsd_serv->sv_nrthreads - 1; + error = nn->nfsd_serv->sv_nrthreads; out_shutdown: if (error < 0 && !nfsd_up_before) nfsd_shutdown_net(net); out_put: + /* Threads now hold service active */ + if (xchg(&nn->keep_active, 0)) + nfsd_put(net); nfsd_put(net); out: mutex_unlock(&nfsd_mutex); @@ -980,11 +987,15 @@ nfsd(void *vrqstp) nfsdstats.th_cnt --; out: - rqstp->rq_server = NULL; + /* Take an extra ref so that the svc_put in svc_exit_thread() + * doesn't call svc_destroy() + */ + svc_get(nn->nfsd_serv); /* Release the thread */ svc_exit_thread(rqstp); + /* Now if needed we call svc_destroy in appropriate context */ nfsd_put(net); /* Release module */ @@ -1099,7 +1110,6 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file) mutex_unlock(&nfsd_mutex); return -ENODEV; } - /* bump up the psudo refcount while traversing */ svc_get(nn->nfsd_serv); ret = svc_pool_stats_open(nn->nfsd_serv, file); mutex_unlock(&nfsd_mutex); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 73d56d33a36d..3903b4ae8ac5 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -85,6 +85,7 @@ struct svc_serv { struct svc_program * sv_program; /* RPC program */ struct svc_stat * sv_stats; /* RPC statistics */ spinlock_t sv_lock; + struct kref sv_refcnt; unsigned int sv_nrthreads; /* # of server threads */ unsigned int sv_maxconn; /* max connections allowed or * '0' causing max to be based @@ -119,19 +120,14 @@ struct svc_serv { * @serv: the svc_serv to have count incremented * * Returns: the svc_serv that was passed in. - * - * We use sv_nrthreads as a reference count. svc_put() drops - * this refcount, so we need to bump it up around operations that - * change the number of threads. Horrible, but there it is. - * Should be called with the "service mutex" held. */ static inline struct svc_serv *svc_get(struct svc_serv *serv) { - serv->sv_nrthreads++; + kref_get(&serv->sv_refcnt); return serv; } -void svc_destroy(struct svc_serv *serv); +void svc_destroy(struct kref *); /** * svc_put - decrement reference count on a SUNRPC serv @@ -142,9 +138,7 @@ void svc_destroy(struct svc_serv *serv); */ static inline void svc_put(struct svc_serv *serv) { - serv->sv_nrthreads -= 1; - if (serv->sv_nrthreads == 0) - svc_destroy(serv); + kref_put(&serv->sv_refcnt, svc_destroy); } /* diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 55a1bf0d129f..acddc6e12e9e 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -435,7 +435,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools, return NULL; serv->sv_name = prog->pg_name; serv->sv_program = prog; - serv->sv_nrthreads = 1; + kref_init(&serv->sv_refcnt); serv->sv_stats = prog->pg_stats; if (bufsize > RPCSVC_MAXPAYLOAD) bufsize = RPCSVC_MAXPAYLOAD; @@ -526,10 +526,11 @@ EXPORT_SYMBOL_GPL(svc_shutdown_net); * protect the sv_nrthreads, sv_permsocks and sv_tempsocks. */ void -svc_destroy(struct svc_serv *serv) +svc_destroy(struct kref *ref) { - dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); + struct svc_serv *serv = container_of(ref, struct svc_serv, sv_refcnt); + dprintk("svc: svc_destroy(%s)\n", serv->sv_program->pg_name); del_timer_sync(&serv->sv_temptimer); /* @@ -637,6 +638,7 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) if (!rqstp) return ERR_PTR(-ENOMEM); + svc_get(serv); serv->sv_nrthreads++; spin_lock_bh(&pool->sp_lock); pool->sp_nrthreads++; @@ -776,8 +778,7 @@ int svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { if (pool == NULL) { - /* The -1 assumes caller has done a svc_get() */ - nrservs -= (serv->sv_nrthreads-1); + nrservs -= serv->sv_nrthreads; } else { spin_lock_bh(&pool->sp_lock); nrservs -= pool->sp_nrthreads; @@ -814,8 +815,7 @@ int svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { if (pool == NULL) { - /* The -1 assumes caller has done a svc_get() */ - nrservs -= (serv->sv_nrthreads-1); + nrservs -= serv->sv_nrthreads; } else { spin_lock_bh(&pool->sp_lock); nrservs -= pool->sp_nrthreads; @@ -880,12 +880,12 @@ svc_exit_thread(struct svc_rqst *rqstp) list_del_rcu(&rqstp->rq_all); spin_unlock_bh(&pool->sp_lock); + serv->sv_nrthreads -= 1; + svc_sock_update_bufs(serv); + svc_rqst_free(rqstp); - if (!serv) - return; - svc_sock_update_bufs(serv); - svc_destroy(serv); + svc_put(serv); } EXPORT_SYMBOL_GPL(svc_exit_thread); -- cgit v1.2.3 From 3409e4f1e8f239f0ed81be0b068ecf4e73e2e826 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: NFSD: Make it possible to use svc_set_num_threads_sync nfsd cannot currently use svc_set_num_threads_sync. It instead uses svc_set_num_threads which does *not* wait for threads to all exit, and has a separate mechanism (nfsd_shutdown_complete) to wait for completion. The reason that nfsd is unlike other services is that nfsd threads can exit separately from svc_set_num_threads being called - they die on receipt of SIGKILL. Also, when the last thread exits, the service must be shut down (sockets closed). For this, the nfsd_mutex needs to be taken, and as that mutex needs to be held while svc_set_num_threads is called, the one cannot wait for the other. This patch changes the nfsd thread so that it can drop the ref on the service without blocking on nfsd_mutex, so that svc_set_num_threads_sync can be used: - if it can drop a non-last reference, it does that. This does not trigger shutdown and does not require a mutex. This will likely happen for all but the last thread signalled, and for all threads being shut down by nfsd_shutdown_threads() - if it can get the mutex without blocking (trylock), it does that and then drops the reference. This will likely happen for the last thread killed by SIGKILL - Otherwise there might be an unrelated task holding the mutex, possibly in another network namespace, or nfsd_shutdown_threads() might be just about to get a reference on the service, after which we can drop ours safely. We cannot conveniently get wakeup notifications on these events, and we are unlikely to need to, so we sleep briefly and check again. With this we can discard nfsd_shutdown_complete and nfsd_complete_shutdown(), and switch to svc_set_num_threads_sync. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/nfsd/netns.h | 3 --- fs/nfsd/nfssvc.c | 41 ++++++++++++++++++++--------------------- include/linux/sunrpc/svc.h | 13 +++++++++++++ 3 files changed, 33 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 08bcd8f23b01..1fd59eb0730b 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -134,9 +134,6 @@ struct nfsd_net { wait_queue_head_t ntf_wq; atomic_t ntf_refcnt; - /* Allow umount to wait for nfsd state cleanup */ - struct completion nfsd_shutdown_complete; - /* * clientid and stateid data for construction of net unique COPY * stateids. diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 097abd8b059c..d0d9107a1b93 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -593,20 +593,10 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = { .svo_shutdown = nfsd_last_thread, .svo_function = nfsd, .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads, + .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; -static void nfsd_complete_shutdown(struct net *net) -{ - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - WARN_ON(!mutex_is_locked(&nfsd_mutex)); - - nn->nfsd_serv = NULL; - complete(&nn->nfsd_shutdown_complete); -} - void nfsd_shutdown_threads(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -624,8 +614,6 @@ void nfsd_shutdown_threads(struct net *net) serv->sv_ops->svo_setup(serv, NULL, 0); nfsd_put(net); mutex_unlock(&nfsd_mutex); - /* Wait for shutdown of nfsd_serv to complete */ - wait_for_completion(&nn->nfsd_shutdown_complete); } bool i_am_nfsd(void) @@ -650,7 +638,6 @@ int nfsd_create_serv(struct net *net) &nfsd_thread_sv_ops); if (nn->nfsd_serv == NULL) return -ENOMEM; - init_completion(&nn->nfsd_shutdown_complete); nn->nfsd_serv->sv_maxconn = nn->max_connections; error = svc_bind(nn->nfsd_serv, net); @@ -659,7 +646,7 @@ int nfsd_create_serv(struct net *net) * been set up yet. */ svc_put(nn->nfsd_serv); - nfsd_complete_shutdown(net); + nn->nfsd_serv = NULL; return error; } @@ -715,7 +702,7 @@ void nfsd_put(struct net *net) if (kref_put(&nn->nfsd_serv->sv_refcnt, nfsd_noop)) { svc_shutdown_net(nn->nfsd_serv, net); svc_destroy(&nn->nfsd_serv->sv_refcnt); - nfsd_complete_shutdown(net); + nn->nfsd_serv = NULL; } } @@ -743,7 +730,7 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) if (tot > NFSD_MAXSERVS) { /* total too large: scale down requested numbers */ for (i = 0; i < n && tot > 0; i++) { - int new = nthreads[i] * NFSD_MAXSERVS / tot; + int new = nthreads[i] * NFSD_MAXSERVS / tot; tot -= (nthreads[i] - new); nthreads[i] = new; } @@ -989,10 +976,22 @@ out: /* Release the thread */ svc_exit_thread(rqstp); - /* Now if needed we call svc_destroy in appropriate context */ - mutex_lock(&nfsd_mutex); - nfsd_put(net); - mutex_unlock(&nfsd_mutex); + /* We need to drop a ref, but may not drop the last reference + * without holding nfsd_mutex, and we cannot wait for nfsd_mutex as that + * could deadlock with nfsd_shutdown_threads() waiting for us. + * So three options are: + * - drop a non-final reference, + * - get the mutex without waiting + * - sleep briefly andd try the above again + */ + while (!svc_put_not_last(nn->nfsd_serv)) { + if (mutex_trylock(&nfsd_mutex)) { + nfsd_put(net); + mutex_unlock(&nfsd_mutex); + break; + } + msleep(20); + } /* Release module */ module_put_and_exit(0); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 3903b4ae8ac5..36bfc0281988 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -141,6 +141,19 @@ static inline void svc_put(struct svc_serv *serv) kref_put(&serv->sv_refcnt, svc_destroy); } +/** + * svc_put_not_last - decrement non-final reference count on SUNRPC serv + * @serv: the svc_serv to have count decremented + * + * Returns: %true is refcount was decremented. + * + * If the refcount is 1, it is not decremented and instead failure is reported. + */ +static inline bool svc_put_not_last(struct svc_serv *serv) +{ + return refcount_dec_not_one(&serv->sv_refcnt.refcount); +} + /* * Maximum payload size supported by a kernel RPC server. * This is use to determine the max number of pages nfsd is -- cgit v1.2.3 From 3ebdbe5203a874614819700d3f470724cb803709 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: SUNRPC: discard svo_setup and rename svc_set_num_threads_sync() The ->svo_setup callback serves no purpose. It is always called from within the same module that chooses which callback is needed. So discard it and call the relevant function directly. Now that svc_set_num_threads() is no longer used remove it and rename svc_set_num_threads_sync() to remove the "_sync" suffix. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/nfs/callback.c | 8 +++----- fs/nfsd/nfssvc.c | 11 +++++------ include/linux/sunrpc/svc.h | 4 ---- net/sunrpc/svc.c | 49 ++-------------------------------------------- 4 files changed, 10 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index d9d78ffd1d65..6cdc9d18a7dd 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -172,9 +172,9 @@ static int nfs_callback_start_svc(int minorversion, struct rpc_xprt *xprt, if (serv->sv_nrthreads == nrservs) return 0; - ret = serv->sv_ops->svo_setup(serv, NULL, nrservs); + ret = svc_set_num_threads(serv, NULL, nrservs); if (ret) { - serv->sv_ops->svo_setup(serv, NULL, 0); + svc_set_num_threads(serv, NULL, 0); return ret; } dprintk("nfs_callback_up: service started\n"); @@ -235,14 +235,12 @@ err_bind: static const struct svc_serv_ops nfs40_cb_sv_ops = { .svo_function = nfs4_callback_svc, .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; #if defined(CONFIG_NFS_V4_1) static const struct svc_serv_ops nfs41_cb_sv_ops = { .svo_function = nfs41_callback_svc, .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; @@ -357,7 +355,7 @@ void nfs_callback_down(int minorversion, struct net *net) cb_info->users--; if (cb_info->users == 0) { svc_get(serv); - serv->sv_ops->svo_setup(serv, NULL, 0); + svc_set_num_threads(serv, NULL, 0); svc_put(serv); dprintk("nfs_callback_down: service destroyed\n"); cb_info->serv = NULL; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index d0d9107a1b93..020156e96bdb 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -593,7 +593,6 @@ static const struct svc_serv_ops nfsd_thread_sv_ops = { .svo_shutdown = nfsd_last_thread, .svo_function = nfsd, .svo_enqueue_xprt = svc_xprt_do_enqueue, - .svo_setup = svc_set_num_threads_sync, .svo_module = THIS_MODULE, }; @@ -611,7 +610,7 @@ void nfsd_shutdown_threads(struct net *net) svc_get(serv); /* Kill outstanding nfsd threads */ - serv->sv_ops->svo_setup(serv, NULL, 0); + svc_set_num_threads(serv, NULL, 0); nfsd_put(net); mutex_unlock(&nfsd_mutex); } @@ -750,8 +749,9 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net) /* apply the new numbers */ svc_get(nn->nfsd_serv); for (i = 0; i < n; i++) { - err = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, - &nn->nfsd_serv->sv_pools[i], nthreads[i]); + err = svc_set_num_threads(nn->nfsd_serv, + &nn->nfsd_serv->sv_pools[i], + nthreads[i]); if (err) break; } @@ -793,8 +793,7 @@ nfsd_svc(int nrservs, struct net *net, const struct cred *cred) error = nfsd_startup_net(net, cred); if (error) goto out_put; - error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv, - NULL, nrservs); + error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs); if (error) goto out_shutdown; error = nn->nfsd_serv->sv_nrthreads; diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 36bfc0281988..0b38c6eaf985 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -64,9 +64,6 @@ struct svc_serv_ops { /* queue up a transport for servicing */ void (*svo_enqueue_xprt)(struct svc_xprt *); - /* set up thread (or whatever) execution context */ - int (*svo_setup)(struct svc_serv *, struct svc_pool *, int); - /* optional module to count when adding threads (pooled svcs only) */ struct module *svo_module; }; @@ -541,7 +538,6 @@ void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, const struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); -int svc_set_num_threads_sync(struct svc_serv *, struct svc_pool *, int); int svc_pool_stats_open(struct svc_serv *serv, struct file *file); void svc_shutdown_net(struct svc_serv *, struct net *); int svc_process(struct svc_rqst *); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 2b2042234e4b..5513f8c9a8d6 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -743,58 +743,13 @@ svc_start_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) return 0; } - -/* destroy old threads */ -static int -svc_signal_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) -{ - struct task_struct *task; - unsigned int state = serv->sv_nrthreads-1; - - /* destroy old threads */ - do { - task = choose_victim(serv, pool, &state); - if (task == NULL) - break; - send_sig(SIGINT, task, 1); - nrservs++; - } while (nrservs < 0); - - return 0; -} - /* * Create or destroy enough new threads to make the number * of threads the given number. If `pool' is non-NULL, applies * only to threads in that pool, otherwise round-robins between * all pools. Caller must ensure that mutual exclusion between this and * server startup or shutdown. - * - * Destroying threads relies on the service threads filling in - * rqstp->rq_task, which only the nfs ones do. Assumes the serv - * has been created using svc_create_pooled(). - * - * Based on code that used to be in nfsd_svc() but tweaked - * to be pool-aware. */ -int -svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) -{ - if (pool == NULL) { - nrservs -= serv->sv_nrthreads; - } else { - spin_lock_bh(&pool->sp_lock); - nrservs -= pool->sp_nrthreads; - spin_unlock_bh(&pool->sp_lock); - } - - if (nrservs > 0) - return svc_start_kthreads(serv, pool, nrservs); - if (nrservs < 0) - return svc_signal_kthreads(serv, pool, nrservs); - return 0; -} -EXPORT_SYMBOL_GPL(svc_set_num_threads); /* destroy old threads */ static int @@ -815,7 +770,7 @@ svc_stop_kthreads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) } int -svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrservs) +svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs) { if (pool == NULL) { nrservs -= serv->sv_nrthreads; @@ -831,7 +786,7 @@ svc_set_num_threads_sync(struct svc_serv *serv, struct svc_pool *pool, int nrser return svc_stop_kthreads(serv, pool, nrservs); return 0; } -EXPORT_SYMBOL_GPL(svc_set_num_threads_sync); +EXPORT_SYMBOL_GPL(svc_set_num_threads); /** * svc_rqst_replace_page - Replace one page in rq_pages[] -- cgit v1.2.3 From cf0e124e0a489944d08fcc3c694d2b234d2cc658 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: SUNRPC: move the pool_map definitions (back) into svc.c These definitions are not used outside of svc.c, and there is no evidence that they ever have been. So move them into svc.c and make the declarations 'static'. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- include/linux/sunrpc/svc.h | 25 ------------------------- net/sunrpc/svc.c | 31 +++++++++++++++++++++++++------ 2 files changed, 25 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 0b38c6eaf985..d69e6108cb83 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -494,29 +494,6 @@ struct svc_procedure { const char * pc_name; /* for display */ }; -/* - * Mode for mapping cpus to pools. - */ -enum { - SVC_POOL_AUTO = -1, /* choose one of the others */ - SVC_POOL_GLOBAL, /* no mapping, just a single global pool - * (legacy & UP mode) */ - SVC_POOL_PERCPU, /* one pool per cpu */ - SVC_POOL_PERNODE /* one pool per numa node */ -}; - -struct svc_pool_map { - int count; /* How many svc_servs use us */ - int mode; /* Note: int not enum to avoid - * warnings about "enumeration value - * not handled in switch" */ - unsigned int npools; - unsigned int *pool_to; /* maps pool id to cpu or node */ - unsigned int *to_pool; /* maps cpu or node to pool id */ -}; - -extern struct svc_pool_map svc_pool_map; - /* * Function prototypes. */ @@ -533,8 +510,6 @@ void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); void svc_exit_thread(struct svc_rqst *); -unsigned int svc_pool_map_get(void); -void svc_pool_map_put(void); struct svc_serv * svc_create_pooled(struct svc_program *, unsigned int, const struct svc_serv_ops *); int svc_set_num_threads(struct svc_serv *, struct svc_pool *, int); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 5513f8c9a8d6..f0dd9ef7e0cd 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -41,14 +41,35 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net); #define SVC_POOL_DEFAULT SVC_POOL_GLOBAL +/* + * Mode for mapping cpus to pools. + */ +enum { + SVC_POOL_AUTO = -1, /* choose one of the others */ + SVC_POOL_GLOBAL, /* no mapping, just a single global pool + * (legacy & UP mode) */ + SVC_POOL_PERCPU, /* one pool per cpu */ + SVC_POOL_PERNODE /* one pool per numa node */ +}; + /* * Structure for mapping cpus to pools and vice versa. * Setup once during sunrpc initialisation. */ -struct svc_pool_map svc_pool_map = { + +struct svc_pool_map { + int count; /* How many svc_servs use us */ + int mode; /* Note: int not enum to avoid + * warnings about "enumeration value + * not handled in switch" */ + unsigned int npools; + unsigned int *pool_to; /* maps pool id to cpu or node */ + unsigned int *to_pool; /* maps cpu or node to pool id */ +}; + +static struct svc_pool_map svc_pool_map = { .mode = SVC_POOL_DEFAULT }; -EXPORT_SYMBOL_GPL(svc_pool_map); static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */ @@ -222,7 +243,7 @@ svc_pool_map_init_pernode(struct svc_pool_map *m) * vice versa). Initialise the map if we're the first user. * Returns the number of pools. */ -unsigned int +static unsigned int svc_pool_map_get(void) { struct svc_pool_map *m = &svc_pool_map; @@ -257,7 +278,6 @@ svc_pool_map_get(void) mutex_unlock(&svc_pool_map_mutex); return m->npools; } -EXPORT_SYMBOL_GPL(svc_pool_map_get); /* * Drop a reference to the global map of cpus to pools. @@ -266,7 +286,7 @@ EXPORT_SYMBOL_GPL(svc_pool_map_get); * mode using the pool_mode module option without * rebooting or re-loading sunrpc.ko. */ -void +static void svc_pool_map_put(void) { struct svc_pool_map *m = &svc_pool_map; @@ -283,7 +303,6 @@ svc_pool_map_put(void) mutex_unlock(&svc_pool_map_mutex); } -EXPORT_SYMBOL_GPL(svc_pool_map_put); static int svc_pool_map_get_node(unsigned int pidx) { -- cgit v1.2.3 From 6b044fbaab02292fedb17565dbb3f2528083b169 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 29 Nov 2021 15:51:25 +1100 Subject: lockd: use svc_set_num_threads() for thread start and stop svc_set_num_threads() does everything that lockd_start_svc() does, except set sv_maxconn. It also (when passed 0) finds the threads and stops them with kthread_stop(). So move the setting for sv_maxconn, and use svc_set_num_thread() We now don't need nlmsvc_task. Now that we use svc_set_num_threads() it makes sense to set svo_module. This request that the thread exists with module_put_and_exit(). Also fix the documentation for svo_module to make this explicit. svc_prepare_thread is now only used where it is defined, so it can be made static. Signed-off-by: NeilBrown Signed-off-by: Chuck Lever --- fs/lockd/svc.c | 58 +++++++--------------------------------------- include/linux/sunrpc/svc.h | 6 ++--- net/sunrpc/svc.c | 3 +-- 3 files changed, 12 insertions(+), 55 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 1a7c11118b32..4defefd89cbf 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -55,7 +55,6 @@ EXPORT_SYMBOL_GPL(nlmsvc_ops); static DEFINE_MUTEX(nlmsvc_mutex); static unsigned int nlmsvc_users; static struct svc_serv *nlmsvc_serv; -static struct task_struct *nlmsvc_task; unsigned long nlmsvc_timeout; unsigned int lockd_net_id; @@ -186,7 +185,7 @@ lockd(void *vrqstp) svc_exit_thread(rqstp); - return 0; + module_put_and_exit(0); } static int create_lockd_listener(struct svc_serv *serv, const char *name, @@ -292,8 +291,8 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net) __func__, net->ns.inum); } } else { - pr_err("%s: no users! task=%p, net=%x\n", - __func__, nlmsvc_task, net->ns.inum); + pr_err("%s: no users! net=%x\n", + __func__, net->ns.inum); BUG(); } } @@ -351,49 +350,11 @@ static struct notifier_block lockd_inet6addr_notifier = { }; #endif -static int lockd_start_svc(struct svc_serv *serv) -{ - int error; - struct svc_rqst *rqst; - - /* - * Create the kernel thread and wait for it to start. - */ - rqst = svc_prepare_thread(serv, &serv->sv_pools[0], NUMA_NO_NODE); - if (IS_ERR(rqst)) { - error = PTR_ERR(rqst); - printk(KERN_WARNING - "lockd_up: svc_rqst allocation failed, error=%d\n", - error); - goto out_rqst; - } - - svc_sock_update_bufs(serv); - serv->sv_maxconn = nlm_max_connections; - - nlmsvc_task = kthread_create(lockd, rqst, "%s", serv->sv_name); - if (IS_ERR(nlmsvc_task)) { - error = PTR_ERR(nlmsvc_task); - printk(KERN_WARNING - "lockd_up: kthread_run failed, error=%d\n", error); - goto out_task; - } - rqst->rq_task = nlmsvc_task; - wake_up_process(nlmsvc_task); - - dprintk("lockd_up: service started\n"); - return 0; - -out_task: - svc_exit_thread(rqst); - nlmsvc_task = NULL; -out_rqst: - return error; -} - static const struct svc_serv_ops lockd_sv_ops = { .svo_shutdown = svc_rpcb_cleanup, + .svo_function = lockd, .svo_enqueue_xprt = svc_xprt_do_enqueue, + .svo_module = THIS_MODULE, }; static int lockd_get(void) @@ -425,7 +386,8 @@ static int lockd_get(void) return -ENOMEM; } - error = lockd_start_svc(serv); + serv->sv_maxconn = nlm_max_connections; + error = svc_set_num_threads(serv, NULL, 1); /* The thread now holds the only reference */ svc_put(serv); if (error < 0) @@ -453,11 +415,7 @@ static void lockd_put(void) unregister_inet6addr_notifier(&lockd_inet6addr_notifier); #endif - if (nlmsvc_task) { - kthread_stop(nlmsvc_task); - dprintk("lockd_down: service stopped\n"); - nlmsvc_task = NULL; - } + svc_set_num_threads(nlmsvc_serv, NULL, 0); nlmsvc_serv = NULL; dprintk("lockd_down: service destroyed\n"); } diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index d69e6108cb83..cf175d47c6b7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -64,7 +64,9 @@ struct svc_serv_ops { /* queue up a transport for servicing */ void (*svo_enqueue_xprt)(struct svc_xprt *); - /* optional module to count when adding threads (pooled svcs only) */ + /* optional module to count when adding threads. + * Thread function must call module_put_and_exit() to exit. + */ struct module *svo_module; }; @@ -504,8 +506,6 @@ struct svc_serv *svc_create(struct svc_program *, unsigned int, const struct svc_serv_ops *); struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node); -struct svc_rqst *svc_prepare_thread(struct svc_serv *serv, - struct svc_pool *pool, int node); void svc_rqst_replace_page(struct svc_rqst *rqstp, struct page *page); void svc_rqst_free(struct svc_rqst *); diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 5fbe7f55289e..2aabec2b4bec 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -652,7 +652,7 @@ out_enomem: } EXPORT_SYMBOL_GPL(svc_rqst_alloc); -struct svc_rqst * +static struct svc_rqst * svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) { struct svc_rqst *rqstp; @@ -672,7 +672,6 @@ svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node) spin_unlock_bh(&pool->sp_lock); return rqstp; } -EXPORT_SYMBOL_GPL(svc_prepare_thread); /* * Choose a pool in which to create a new thread, for svc_set_num_threads -- cgit v1.2.3 From c8064e5b4adac5e1255cf4f3b374e75b5376e7ca Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 30 Nov 2021 11:08:07 +0100 Subject: bpf: Let bpf_warn_invalid_xdp_action() report more info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In non trivial scenarios, the action id alone is not sufficient to identify the program causing the warning. Before the previous patch, the generated stack-trace pointed out at least the involved device driver. Let's additionally include the program name and id, and the relevant device name. If the user needs additional infos, he can fetch them via a kernel probe, leveraging the arguments added here. Signed-off-by: Paolo Abeni Signed-off-by: Daniel Borkmann Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/bpf/ddb96bb975cbfddb1546cf5da60e77d5100b533c.1638189075.git.pabeni@redhat.com --- drivers/net/ethernet/amazon/ena/ena_netdev.c | 2 +- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 +- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 2 +- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 2 +- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 2 +- drivers/net/ethernet/freescale/enetc/enetc.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 2 +- drivers/net/ethernet/intel/i40e/i40e_xsk.c | 2 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +- drivers/net/ethernet/intel/ice/ice_xsk.c | 2 +- drivers/net/ethernet/intel/igb/igb_main.c | 2 +- drivers/net/ethernet/intel/igc/igc_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c | 2 +- drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 2 +- drivers/net/ethernet/marvell/mvneta.c | 2 +- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 2 +- drivers/net/ethernet/microsoft/mana/mana_bpf.c | 2 +- drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 2 +- drivers/net/ethernet/qlogic/qede/qede_fp.c | 2 +- drivers/net/ethernet/sfc/rx.c | 2 +- drivers/net/ethernet/socionext/netsec.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 +- drivers/net/ethernet/ti/cpsw_priv.c | 2 +- drivers/net/hyperv/netvsc_bpf.c | 2 +- drivers/net/tun.c | 2 +- drivers/net/veth.c | 4 ++-- drivers/net/virtio_net.c | 4 ++-- drivers/net/xen-netfront.c | 2 +- include/linux/filter.h | 2 +- kernel/bpf/cpumap.c | 4 ++-- kernel/bpf/devmap.c | 4 ++-- net/core/dev.c | 2 +- net/core/filter.c | 6 +++--- 37 files changed, 43 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 7d5d885d85d5..3b46f1df5609 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -434,7 +434,7 @@ static int ena_xdp_execute(struct ena_ring *rx_ring, struct xdp_buff *xdp) xdp_stat = &rx_ring->rx_stats.xdp_pass; break; default: - bpf_warn_invalid_xdp_action(verdict); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, verdict); xdp_stat = &rx_ring->rx_stats.xdp_invalid; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index c8083df5e0ab..52fad0fdeacf 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -195,7 +195,7 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, *event |= BNXT_REDIRECT_EVENT; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(bp->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(bp->dev, xdp_prog, act); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index bb45d5df2856..30450efccad7 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -590,7 +590,7 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, nicvf_xdp_sq_append_pkt(nic, sq, (u64)xdp.data, dma_addr, len); return true; default: - bpf_warn_invalid_xdp_action(action); + bpf_warn_invalid_xdp_action(nic->netdev, prog, action); fallthrough; case XDP_ABORTED: trace_xdp_exception(nic->netdev, prog, action); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index d6871437d951..c78883c3a2c8 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2623,7 +2623,7 @@ static u32 dpaa_run_xdp(struct dpaa_priv *priv, struct qm_fd *fd, void *vaddr, } break; default: - bpf_warn_invalid_xdp_action(xdp_act); + bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act); fallthrough; case XDP_ABORTED: trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 8e643567abce..d21ba70ef4a3 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -374,7 +374,7 @@ static u32 dpaa2_eth_run_xdp(struct dpaa2_eth_priv *priv, dpaa2_eth_xdp_enqueue(priv, ch, fd, vaddr, rx_fq->flowid); break; default: - bpf_warn_invalid_xdp_action(xdp_act); + bpf_warn_invalid_xdp_action(priv->net_dev, xdp_prog, xdp_act); fallthrough; case XDP_ABORTED: trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act); diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 504e12554079..eacb41f86bdb 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1547,7 +1547,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, switch (xdp_act) { default: - bpf_warn_invalid_xdp_action(xdp_act); + bpf_warn_invalid_xdp_action(rx_ring->ndev, prog, xdp_act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rx_ring->ndev, prog, xdp_act); diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 10a83e5385c7..b399ca649f09 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2322,7 +2322,7 @@ static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) result = I40E_XDP_REDIR; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index ea06e957393e..945b1bb9c6f4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -176,7 +176,7 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) goto out_failure; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index bc3ba19dc88f..56940bb908bc 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -561,7 +561,7 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, goto out_failure; return ICE_XDP_REDIR; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index bb9a80847298..ef4b213881f3 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -483,7 +483,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, goto out_failure; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index dd208930fbe4..337a7197e96f 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8422,7 +8422,7 @@ static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, result = IGB_XDP_REDIR; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 142c57b7a451..7f2ce4b256d9 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2241,7 +2241,7 @@ static int __igc_xdp_run_prog(struct igc_adapter *adapter, return IGC_XDP_REDIRECT; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(adapter->netdev, prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 0f9f022260d7..265bc52aacf8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2235,7 +2235,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, result = IXGBE_XDP_REDIR; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index db2bc58dfcfd..b3fd8e5cd85b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -131,7 +131,7 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, goto out_failure; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index b1dfbaff8b31..2459ecf65125 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1070,7 +1070,7 @@ static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, goto out_failure; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: out_failure: diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index ce810fc3c1a2..23cc4b874285 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2239,7 +2239,7 @@ mvneta_run_xdp(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, mvneta_xdp_put_buff(pp, rxq, xdp, sinfo, sync); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(pp->dev, prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(pp->dev, prog, act); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 8e5820d12362..7273a4c9dbb1 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3823,7 +3823,7 @@ mvpp2_run_xdp(struct mvpp2_port *port, struct bpf_prog *prog, } break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(port->dev, prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(port->dev, prog, act); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 0cc6353254bf..7c4068c5d1ac 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -1198,7 +1198,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf, put_page(page); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act); break; case XDP_ABORTED: trace_xdp_exception(pfvf->netdev, prog, act); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 650e6a1844ae..8cfc649f226b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -812,7 +812,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud trace_xdp_exception(dev, xdp_prog, act); goto xdp_drop_no_cnt; /* Drop on xmit failure */ default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 2f0df5cc1a2d..338d65e2c9ce 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -151,7 +151,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, rq->stats->xdp_redirect++; return true; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rq->netdev, prog, act); fallthrough; case XDP_ABORTED: xdp_abort: diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c index 1bc8ff388341..1d2f948b5c00 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c +++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c @@ -60,7 +60,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(ndev, prog, act); } out: diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 6e38da4ad554..79257ec41987 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1944,7 +1944,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) xdp_prog, act); continue; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(dp->netdev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dp->netdev, xdp_prog, act); diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 5ea9cb4311a1..b242000a77fd 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1153,7 +1153,7 @@ static bool qede_rx_xdp(struct qede_dev *edev, qede_rx_bd_ring_consume(rxq); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(edev->ndev, prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(edev->ndev, prog, act); diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 606750938b89..2375cef577e4 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -338,7 +338,7 @@ static bool efx_do_xdp(struct efx_nic *efx, struct efx_channel *channel, break; default: - bpf_warn_invalid_xdp_action(xdp_act); + bpf_warn_invalid_xdp_action(efx->net_dev, xdp_prog, xdp_act); efx_free_rx_buffers(rx_queue, rx_buf, 1); channel->n_rx_xdp_bad_drops++; trace_xdp_exception(efx->net_dev, xdp_prog, xdp_act); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index de7d8bf2c226..25dcd8eda5fc 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -933,7 +933,7 @@ static u32 netsec_run_xdp(struct netsec_priv *priv, struct bpf_prog *prog, } break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(priv->ndev, prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(priv->ndev, prog, act); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 4e05c1d92935..7f62ddc90088 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4714,7 +4714,7 @@ static int __stmmac_xdp_run_prog(struct stmmac_priv *priv, res = STMMAC_XDP_REDIRECT; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(priv->dev, prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(priv->dev, prog, act); diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index c99dd9735087..67c4009fd16c 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1366,7 +1366,7 @@ int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp, xdp_do_flush_map(); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(ndev, prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(ndev, prog, act); diff --git a/drivers/net/hyperv/netvsc_bpf.c b/drivers/net/hyperv/netvsc_bpf.c index aa877da113f8..7856905414eb 100644 --- a/drivers/net/hyperv/netvsc_bpf.c +++ b/drivers/net/hyperv/netvsc_bpf.c @@ -68,7 +68,7 @@ u32 netvsc_run_xdp(struct net_device *ndev, struct netvsc_channel *nvchan, break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(ndev, prog, act); } out: diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 1572878c3403..0e5d2272f63a 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1551,7 +1551,7 @@ static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, case XDP_PASS: break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(tun->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(tun->dev, xdp_prog, act); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 38f6da24f460..700cc9374f9c 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -644,7 +644,7 @@ static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, rcu_read_unlock(); goto xdp_xmit; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); @@ -794,7 +794,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, rcu_read_unlock(); goto xdp_xmit; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 088d9404c93d..d3e0b3a533cd 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -812,7 +812,7 @@ static struct sk_buff *receive_small(struct net_device *dev, rcu_read_unlock(); goto xdp_xmit; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); @@ -1025,7 +1025,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, rcu_read_unlock(); goto xdp_xmit; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(vi->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(vi->dev, xdp_prog, act); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 911f43986a8c..7b7eb617051a 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -930,7 +930,7 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata, break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(queue->info->netdev, prog, act); } return act; diff --git a/include/linux/filter.h b/include/linux/filter.h index 68c6b5c208e7..60eec80fa1d4 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1027,7 +1027,7 @@ void xdp_do_flush(void); */ #define xdp_do_flush_map xdp_do_flush -void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 585b2b77ccc4..0421061d95f1 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -195,7 +195,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu, } return; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, rcpu->prog, act); @@ -254,7 +254,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, } break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act); fallthrough; case XDP_DROP: xdp_return_frame(xdpf); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index f02d04540c0c..6feea293ff10 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -348,7 +348,7 @@ static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, frames[nframes++] = xdpf; break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dev, xdp_prog, act); @@ -507,7 +507,7 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev __skb_push(skb, skb->mac_len); break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(dst->dev, dst->xdp_prog, act); diff --git a/net/core/dev.c b/net/core/dev.c index 4420086f3aeb..c431c8925eed 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4708,7 +4708,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, case XDP_PASS: break; default: - bpf_warn_invalid_xdp_action(act); + bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(skb->dev, xdp_prog, act); diff --git a/net/core/filter.c b/net/core/filter.c index ad8619aa77b7..3f656391af7e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8180,13 +8180,13 @@ static bool xdp_is_valid_access(int off, int size, return __is_valid_xdp_access(off, size); } -void bpf_warn_invalid_xdp_action(u32 act) +void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act) { const u32 act_max = XDP_REDIRECT; - pr_warn_once("%s XDP return value %u, expect packet loss!\n", + pr_warn_once("%s XDP return value %u on prog %s (id %d) dev %s, expect packet loss!\n", act > act_max ? "Illegal" : "Driver unsupported", - act); + act, prog->aux->name, prog->aux->id, dev ? dev->name : "N/A"); } EXPORT_SYMBOL_GPL(bpf_warn_invalid_xdp_action); -- cgit v1.2.3 From 22c3f2f56bd9c901e1da69040680c311f310635d Mon Sep 17 00:00:00 2001 From: Maor Gottlieb Date: Wed, 1 Dec 2021 11:36:18 -0800 Subject: net/mlx5: Separate FDB namespace This patch doesn't add an additional namespaces, but just separates the naming to be used by each FDB user, bypass and kernel. Downstream patches will actually split this up and allow to have more than single priority for the bypass users. Signed-off-by: Maor Gottlieb Reviewed-by: Mark Bloch Signed-off-by: Saeed Mahameed Acked-by: Leon Romanovsky Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/fs.c | 14 +++++++------- drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c | 4 +++- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 1 + include/linux/mlx5/fs.h | 1 + 4 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/fs.c b/drivers/infiniband/hw/mlx5/fs.c index b780185d9dc6..510ef85ef6e4 100644 --- a/drivers/infiniband/hw/mlx5/fs.c +++ b/drivers/infiniband/hw/mlx5/fs.c @@ -1508,7 +1508,7 @@ _get_flow_table(struct mlx5_ib_dev *dev, !esw_encap) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; break; - case MLX5_FLOW_NAMESPACE_FDB: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: max_table_size = BIT( MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, log_max_ft_size)); if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, decap) && esw_encap) @@ -1546,7 +1546,7 @@ _get_flow_table(struct mlx5_ib_dev *dev, case MLX5_FLOW_NAMESPACE_EGRESS: prio = &dev->flow_db->egress_prios[priority]; break; - case MLX5_FLOW_NAMESPACE_FDB: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: prio = &dev->flow_db->fdb; break; case MLX5_FLOW_NAMESPACE_RDMA_RX: @@ -1937,7 +1937,7 @@ mlx5_ib_ft_type_to_namespace(enum mlx5_ib_uapi_flow_table_type table_type, *namespace = MLX5_FLOW_NAMESPACE_EGRESS; break; case MLX5_IB_UAPI_FLOW_TABLE_TYPE_FDB: - *namespace = MLX5_FLOW_NAMESPACE_FDB; + *namespace = MLX5_FLOW_NAMESPACE_FDB_BYPASS; break; case MLX5_IB_UAPI_FLOW_TABLE_TYPE_RDMA_RX: *namespace = MLX5_FLOW_NAMESPACE_RDMA_RX; @@ -2029,8 +2029,8 @@ static int get_dests(struct uverbs_attr_bundle *attrs, } /* Allow only DEVX object, drop as dest for FDB */ - if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB && !(dest_devx || - (*flags & MLX5_IB_ATTR_CREATE_FLOW_FLAGS_DROP))) + if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS && + !(dest_devx || (*flags & MLX5_IB_ATTR_CREATE_FLOW_FLAGS_DROP))) return -EINVAL; /* Allow only DEVX object or QP as dest when inserting to RDMA_RX */ @@ -2050,7 +2050,7 @@ static int get_dests(struct uverbs_attr_bundle *attrs, if (!is_flow_dest(devx_obj, dest_id, dest_type)) return -EINVAL; /* Allow only flow table as dest when inserting to FDB or RDMA_RX */ - if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB || + if ((fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS || fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_RDMA_RX) && *dest_type != MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE) return -EINVAL; @@ -2320,7 +2320,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_FLOW_MATCHER_CREATE)( if (err) goto end; - if (obj->ns_type == MLX5_FLOW_NAMESPACE_FDB && + if (obj->ns_type == MLX5_FLOW_NAMESPACE_FDB_BYPASS && mlx5_eswitch_mode(dev->mdev) != MLX5_ESWITCH_OFFLOADS) { err = -EINVAL; goto end; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 750b21124a1a..762b9730a897 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -788,7 +788,8 @@ static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, int err; u32 *in; - if (namespace == MLX5_FLOW_NAMESPACE_FDB) + if (namespace == MLX5_FLOW_NAMESPACE_FDB || + namespace == MLX5_FLOW_NAMESPACE_FDB_BYPASS) max_encap_size = MLX5_CAP_ESW(dev, max_encap_header_size); else max_encap_size = MLX5_CAP_FLOWTABLE(dev, max_encap_header_size); @@ -860,6 +861,7 @@ static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, switch (namespace) { case MLX5_FLOW_NAMESPACE_FDB: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: max_actions = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, max_modify_header_actions); table_type = FS_FT_FDB; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 386ab9a2d490..2d26e16a67cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2220,6 +2220,7 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, switch (type) { case MLX5_FLOW_NAMESPACE_FDB: + case MLX5_FLOW_NAMESPACE_FDB_BYPASS: if (steering->fdb_root_ns) return &steering->fdb_root_ns->ns; return NULL; diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index cd2d4c572367..b1aad14689e3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_ANCHOR, + MLX5_FLOW_NAMESPACE_FDB_BYPASS, MLX5_FLOW_NAMESPACE_FDB, MLX5_FLOW_NAMESPACE_ESW_EGRESS, MLX5_FLOW_NAMESPACE_ESW_INGRESS, -- cgit v1.2.3 From 8aa45b544db9788b0fcc7a300eba8a3ade5d3d50 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 10 Dec 2021 13:11:34 +0200 Subject: HID: Add map_msc() to avoid boilerplate code Since we are going to have more MSC events too, add map_msc() that can be used to fill in necessary fields and avoid boilerplate code. Signed-off-by: Mika Westerberg Reviewed-by: Benjamin Tissoires Signed-off-by: Tero Kristo Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211210111138.1248187-2-tero.kristo@linux.intel.com --- drivers/hid/hid-input.c | 6 ++---- include/linux/hid.h | 4 ++++ 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 217f2d1b91c5..fbbb82f65842 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -52,6 +52,7 @@ static const struct { #define map_rel(c) hid_map_usage(hidinput, usage, &bit, &max, EV_REL, (c)) #define map_key(c) hid_map_usage(hidinput, usage, &bit, &max, EV_KEY, (c)) #define map_led(c) hid_map_usage(hidinput, usage, &bit, &max, EV_LED, (c)) +#define map_msc(c) hid_map_usage(hidinput, usage, &bit, &max, EV_MSC, (c)) #define map_abs_clear(c) hid_map_usage_clear(hidinput, usage, &bit, \ &max, EV_ABS, (c)) @@ -874,10 +875,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x5b: /* TransducerSerialNumber */ case 0x6e: /* TransducerSerialNumber2 */ - usage->type = EV_MSC; - usage->code = MSC_SERIAL; - bit = input->mscbit; - max = MSC_MAX; + map_msc(MSC_SERIAL); break; default: goto unknown; diff --git a/include/linux/hid.h b/include/linux/hid.h index b2fea7fc54a1..f18e2cf5d74d 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1010,6 +1010,10 @@ static inline void hid_map_usage(struct hid_input *hidinput, bmap = input->ledbit; limit = LED_MAX; break; + case EV_MSC: + bmap = input->mscbit; + limit = MSC_MAX; + break; } if (unlikely(c > limit || !bmap)) { -- cgit v1.2.3 From ae7fafa6896ae762ff489a5e71c8e5fabfeb61ee Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Fri, 10 Dec 2021 13:11:36 +0200 Subject: HID: Add hid usages for USI style pens Add usage codes for USI style pens, based on the USB-HID usage table: https://usb.org/document-library/hid-usage-tables-122 See chapter 16, Digitizers Page (0x0D) Signed-off-by: Tero Kristo Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211210111138.1248187-4-tero.kristo@linux.intel.com --- include/linux/hid.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index f18e2cf5d74d..fa2ddda84a53 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -241,6 +241,7 @@ struct hid_item { #define HID_DG_TOUCH 0x000d0033 #define HID_DG_UNTOUCH 0x000d0034 #define HID_DG_TAP 0x000d0035 +#define HID_DG_TRANSDUCER_INDEX 0x000d0038 #define HID_DG_TABLETFUNCTIONKEY 0x000d0039 #define HID_DG_PROGRAMCHANGEKEY 0x000d003a #define HID_DG_BATTERYSTRENGTH 0x000d003b @@ -253,6 +254,15 @@ struct hid_item { #define HID_DG_BARRELSWITCH 0x000d0044 #define HID_DG_ERASER 0x000d0045 #define HID_DG_TABLETPICK 0x000d0046 +#define HID_DG_PEN_COLOR 0x000d005c +#define HID_DG_PEN_LINE_WIDTH 0x000d005e +#define HID_DG_PEN_LINE_STYLE 0x000d0070 +#define HID_DG_PEN_LINE_STYLE_INK 0x000d0072 +#define HID_DG_PEN_LINE_STYLE_PENCIL 0x000d0073 +#define HID_DG_PEN_LINE_STYLE_HIGHLIGHTER 0x000d0074 +#define HID_DG_PEN_LINE_STYLE_CHISEL_MARKER 0x000d0075 +#define HID_DG_PEN_LINE_STYLE_BRUSH 0x000d0076 +#define HID_DG_PEN_LINE_STYLE_NO_PREFERENCE 0x000d0077 #define HID_CP_CONSUMERCONTROL 0x000c0001 #define HID_CP_NUMERICKEYPAD 0x000c0002 -- cgit v1.2.3 From 5904a3f9d756f108279f8c5b8f17ca6ddfb28d24 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 10 Dec 2021 13:11:37 +0200 Subject: HID: input: Make hidinput_find_field() static This function is not called outside of hid-input.c so we can make it static. Signed-off-by: Mika Westerberg Reviewed-by: Benjamin Tissoires Signed-off-by: Tero Kristo Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211210111138.1248187-5-tero.kristo@linux.intel.com --- drivers/hid/hid-input.c | 4 ++-- include/linux/hid.h | 1 - 2 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 93bbc33da3c3..4186143da7c6 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1461,7 +1461,8 @@ void hidinput_report_event(struct hid_device *hid, struct hid_report *report) } EXPORT_SYMBOL_GPL(hidinput_report_event); -int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field) +static int hidinput_find_field(struct hid_device *hid, unsigned int type, + unsigned int code, struct hid_field **field) { struct hid_report *report; int i, j; @@ -1476,7 +1477,6 @@ int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int } return -1; } -EXPORT_SYMBOL_GPL(hidinput_find_field); struct hid_field *hidinput_get_led_field(struct hid_device *hid) { diff --git a/include/linux/hid.h b/include/linux/hid.h index fa2ddda84a53..ff8b6973022a 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -899,7 +899,6 @@ extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, u32, int); -int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); -- cgit v1.2.3 From fd8d135b2c5e88662f2729e034913f183455a667 Mon Sep 17 00:00:00 2001 From: Alistair Francis Date: Wed, 8 Dec 2021 22:40:43 +1000 Subject: HID: quirks: Allow inverting the absolute X/Y values Add a HID_QUIRK_X_INVERT/HID_QUIRK_Y_INVERT quirk that can be used to invert the X/Y values. Signed-off-by: Alistair Francis [bentiss: silence checkpatch warning] Signed-off-by: Benjamin Tissoires Link: https://lore.kernel.org/r/20211208124045.61815-2-alistair@alistair23.me --- drivers/hid/hid-input.c | 6 ++++++ include/linux/hid.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 4186143da7c6..5f357dddcc01 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1329,6 +1329,12 @@ void hidinput_hid_event(struct hid_device *hid, struct hid_field *field, struct input = field->hidinput->input; + if (usage->type == EV_ABS && + (((*quirks & HID_QUIRK_X_INVERT) && usage->code == ABS_X) || + ((*quirks & HID_QUIRK_Y_INVERT) && usage->code == ABS_Y))) { + value = field->logical_maximum - value; + } + if (usage->hat_min < usage->hat_max || usage->hat_dir) { int hat_dir = usage->hat_dir; if (!hat_dir) diff --git a/include/linux/hid.h b/include/linux/hid.h index ff8b6973022a..a14c089eb0c1 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -359,6 +359,8 @@ struct hid_item { /* BIT(9) reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */ #define HID_QUIRK_ALWAYS_POLL BIT(10) #define HID_QUIRK_INPUT_PER_APP BIT(11) +#define HID_QUIRK_X_INVERT BIT(12) +#define HID_QUIRK_Y_INVERT BIT(13) #define HID_QUIRK_SKIP_OUTPUT_REPORTS BIT(16) #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID BIT(17) #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP BIT(18) -- cgit v1.2.3 From 369461ce8fb6c8156206c7110d7da48e9fbc41bb Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 8 Dec 2021 14:11:20 -0600 Subject: x86: perf: Move RDPMC event flag to a common definition In preparation to enable user counter access on arm64 and to move some of the user access handling to perf core, create a common event flag for user counter access and convert x86 to use it. Since the architecture specific flags start at the LSB, starting at the MSB for common flags. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Kan Liang Cc: Thomas Gleixner Cc: Borislav Petkov Cc: x86@kernel.org Cc: "H. Peter Anvin" Cc: linux-perf-users@vger.kernel.org Reviewed-by: Mark Rutland Reviewed-by: Thomas Gleixner Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20211208201124.310740-2-robh@kernel.org Signed-off-by: Will Deacon --- arch/x86/events/core.c | 10 +++++----- arch/x86/events/perf_event.h | 2 +- include/linux/perf_event.h | 9 +++++++++ 3 files changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 38b2c779146f..68dea7ce6a22 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2476,7 +2476,7 @@ static int x86_pmu_event_init(struct perf_event *event) if (READ_ONCE(x86_pmu.attr_rdpmc) && !(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS)) - event->hw.flags |= PERF_X86_EVENT_RDPMC_ALLOWED; + event->hw.flags |= PERF_EVENT_FLAG_USER_READ_CNT; return err; } @@ -2510,7 +2510,7 @@ void perf_clear_dirty_counters(void) static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { - if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; /* @@ -2531,7 +2531,7 @@ static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { - if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT)) return; if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) @@ -2542,7 +2542,7 @@ static int x86_pmu_event_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; - if (!(hwc->flags & PERF_X86_EVENT_RDPMC_ALLOWED)) + if (!(hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) return 0; if (is_metric_idx(hwc->idx)) @@ -2725,7 +2725,7 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time = 0; userpg->cap_user_time_zero = 0; userpg->cap_user_rdpmc = - !!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED); + !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT); userpg->pmc_width = x86_pmu.cntval_bits; if (!using_native_sched_clock() || !sched_clock_stable()) diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 5480db242083..9d376e528dfc 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -74,7 +74,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode) #define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ #define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ #define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ + #define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ #define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ #define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0dcfd265beed..ba9467972c09 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -129,6 +129,15 @@ struct hw_perf_event_extra { int idx; /* index in shared_regs->regs[] */ }; +/** + * hw_perf_event::flag values + * + * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific + * usage. + */ +#define PERF_EVENT_FLAG_ARCH 0x0000ffff +#define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 + /** * struct hw_perf_event - performance event hardware details: */ -- cgit v1.2.3 From 82ff0c022d19c2ad69a472692bb7ee01ac07a40b Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 8 Dec 2021 14:11:21 -0600 Subject: perf: Add a counter for number of user access events in context On arm64, user space counter access will be controlled differently compared to x86. On x86, access in the strictest mode is enabled for all tasks in an MM when any event is mmap'ed. For arm64, access is explicitly requested for an event and only enabled when the event's context is active. This avoids hooks into the arch context switch code and gives better control of when access is enabled. In order to configure user space access when the PMU is enabled, it is necessary to know if any event (currently active or not) in the current context has user space accessed enabled. Add a counter similar to other counters in the context to avoid walking the event list every time. Reviewed-by: Mark Rutland Reviewed-by: Thomas Gleixner Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20211208201124.310740-3-robh@kernel.org Signed-off-by: Will Deacon --- include/linux/perf_event.h | 1 + kernel/events/core.c | 4 ++++ 2 files changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index ba9467972c09..411e34210fbf 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -831,6 +831,7 @@ struct perf_event_context { int nr_events; int nr_active; + int nr_user; int is_active; int nr_stat; int nr_freq; diff --git a/kernel/events/core.c b/kernel/events/core.c index 30d94f68c5bd..1362b9b770d8 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1808,6 +1808,8 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; + if (event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) + ctx->nr_user++; if (event->attr.inherit_stat) ctx->nr_stat++; @@ -1999,6 +2001,8 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; ctx->nr_events--; + if (event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) + ctx->nr_user--; if (event->attr.inherit_stat) ctx->nr_stat--; -- cgit v1.2.3 From 8404b0fbc7fbd42e5c5d28cdedd450e70829c77a Mon Sep 17 00:00:00 2001 From: Qi Liu Date: Thu, 2 Dec 2021 16:06:33 +0800 Subject: drivers/perf: hisi: Add driver for HiSilicon PCIe PMU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit PCIe PMU Root Complex Integrated End Point(RCiEP) device is supported to sample bandwidth, latency, buffer occupation etc. Each PMU RCiEP device monitors multiple Root Ports, and each RCiEP is registered as a PMU in /sys/bus/event_source/devices, so users can select target PMU, and use filter to do further sets. Filtering options contains: event - select the event. port - select target Root Ports. Information of Root Ports are shown under sysfs. bdf - select requester_id of target EP device. trig_len - set trigger condition for starting event statistics. trig_mode - set trigger mode. 0 means starting to statistic when bigger than trigger condition, and 1 means smaller. thr_len - set threshold for statistics. thr_mode - set threshold mode. 0 means count when bigger than threshold, and 1 means smaller. Acked-by: Krzysztof Wilczyński Reviewed-by: John Garry Signed-off-by: Qi Liu Reviewed-by: Shaokun Zhang Link: https://lore.kernel.org/r/20211202080633.2919-3-liuqi115@huawei.com Signed-off-by: Will Deacon --- MAINTAINERS | 2 + drivers/perf/hisilicon/Kconfig | 9 + drivers/perf/hisilicon/Makefile | 2 + drivers/perf/hisilicon/hisi_pcie_pmu.c | 948 +++++++++++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 5 files changed, 962 insertions(+) create mode 100644 drivers/perf/hisilicon/hisi_pcie_pmu.c (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 360e9aa0205d..90a7d7b21982 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8607,8 +8607,10 @@ F: drivers/misc/hisi_hikey_usb.c HISILICON PMU DRIVER M: Shaokun Zhang +M: Qi Liu S: Supported W: http://www.hisilicon.com +F: Documentation/admin-guide/perf/hisi-pcie-pmu.rst F: Documentation/admin-guide/perf/hisi-pmu.rst F: drivers/perf/hisilicon diff --git a/drivers/perf/hisilicon/Kconfig b/drivers/perf/hisilicon/Kconfig index c5d1b7019fff..5546218b5598 100644 --- a/drivers/perf/hisilicon/Kconfig +++ b/drivers/perf/hisilicon/Kconfig @@ -5,3 +5,12 @@ config HISI_PMU help Support for HiSilicon SoC L3 Cache performance monitor, Hydra Home Agent performance monitor and DDR Controller performance monitor. + +config HISI_PCIE_PMU + tristate "HiSilicon PCIE PERF PMU" + depends on PCI && ARM64 + help + Provide support for HiSilicon PCIe performance monitoring unit (PMU) + RCiEP devices. + Adds the PCIe PMU into perf events system for monitoring latency, + bandwidth etc. diff --git a/drivers/perf/hisilicon/Makefile b/drivers/perf/hisilicon/Makefile index 7643c9f93e36..506ed39e3266 100644 --- a/drivers/perf/hisilicon/Makefile +++ b/drivers/perf/hisilicon/Makefile @@ -2,3 +2,5 @@ obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \ hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \ hisi_uncore_pa_pmu.o + +obj-$(CONFIG_HISI_PCIE_PMU) += hisi_pcie_pmu.o diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c new file mode 100644 index 000000000000..21771708597d --- /dev/null +++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c @@ -0,0 +1,948 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This driver adds support for PCIe PMU RCiEP device. Related + * perf events are bandwidth, latency etc. + * + * Copyright (C) 2021 HiSilicon Limited + * Author: Qi Liu + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DRV_NAME "hisi_pcie_pmu" +/* Define registers */ +#define HISI_PCIE_GLOBAL_CTRL 0x00 +#define HISI_PCIE_EVENT_CTRL 0x010 +#define HISI_PCIE_CNT 0x090 +#define HISI_PCIE_EXT_CNT 0x110 +#define HISI_PCIE_INT_STAT 0x150 +#define HISI_PCIE_INT_MASK 0x154 +#define HISI_PCIE_REG_BDF 0xfe0 +#define HISI_PCIE_REG_VERSION 0xfe4 +#define HISI_PCIE_REG_INFO 0xfe8 + +/* Define command in HISI_PCIE_GLOBAL_CTRL */ +#define HISI_PCIE_GLOBAL_EN 0x01 +#define HISI_PCIE_GLOBAL_NONE 0 + +/* Define command in HISI_PCIE_EVENT_CTRL */ +#define HISI_PCIE_EVENT_EN BIT_ULL(20) +#define HISI_PCIE_RESET_CNT BIT_ULL(22) +#define HISI_PCIE_INIT_SET BIT_ULL(34) +#define HISI_PCIE_THR_EN BIT_ULL(26) +#define HISI_PCIE_TARGET_EN BIT_ULL(32) +#define HISI_PCIE_TRIG_EN BIT_ULL(52) + +/* Define offsets in HISI_PCIE_EVENT_CTRL */ +#define HISI_PCIE_EVENT_M GENMASK_ULL(15, 0) +#define HISI_PCIE_THR_MODE_M GENMASK_ULL(27, 27) +#define HISI_PCIE_THR_M GENMASK_ULL(31, 28) +#define HISI_PCIE_TARGET_M GENMASK_ULL(52, 36) +#define HISI_PCIE_TRIG_MODE_M GENMASK_ULL(53, 53) +#define HISI_PCIE_TRIG_M GENMASK_ULL(59, 56) + +#define HISI_PCIE_MAX_COUNTERS 8 +#define HISI_PCIE_REG_STEP 8 +#define HISI_PCIE_THR_MAX_VAL 10 +#define HISI_PCIE_TRIG_MAX_VAL 10 +#define HISI_PCIE_MAX_PERIOD (GENMASK_ULL(63, 0)) +#define HISI_PCIE_INIT_VAL BIT_ULL(63) + +struct hisi_pcie_pmu { + struct perf_event *hw_events[HISI_PCIE_MAX_COUNTERS]; + struct hlist_node node; + struct pci_dev *pdev; + struct pmu pmu; + void __iomem *base; + int irq; + u32 identifier; + /* Minimum and maximum BDF of root ports monitored by PMU */ + u16 bdf_min; + u16 bdf_max; + int on_cpu; +}; + +struct hisi_pcie_reg_pair { + u16 lo; + u16 hi; +}; + +#define to_pcie_pmu(p) (container_of((p), struct hisi_pcie_pmu, pmu)) +#define GET_PCI_DEVFN(bdf) ((bdf) & 0xff) + +#define HISI_PCIE_PMU_FILTER_ATTR(_name, _config, _hi, _lo) \ + static u64 hisi_pcie_get_##_name(struct perf_event *event) \ + { \ + return FIELD_GET(GENMASK(_hi, _lo), event->attr._config); \ + } \ + +HISI_PCIE_PMU_FILTER_ATTR(event, config, 16, 0); +HISI_PCIE_PMU_FILTER_ATTR(thr_len, config1, 3, 0); +HISI_PCIE_PMU_FILTER_ATTR(thr_mode, config1, 4, 4); +HISI_PCIE_PMU_FILTER_ATTR(trig_len, config1, 8, 5); +HISI_PCIE_PMU_FILTER_ATTR(trig_mode, config1, 9, 9); +HISI_PCIE_PMU_FILTER_ATTR(port, config2, 15, 0); +HISI_PCIE_PMU_FILTER_ATTR(bdf, config2, 31, 16); + +static ssize_t hisi_pcie_format_sysfs_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct dev_ext_attribute *eattr; + + eattr = container_of(attr, struct dev_ext_attribute, attr); + + return sysfs_emit(buf, "%s\n", (char *)eattr->var); +} + +static ssize_t hisi_pcie_event_sysfs_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct perf_pmu_events_attr *pmu_attr = + container_of(attr, struct perf_pmu_events_attr, attr); + + return sysfs_emit(buf, "config=0x%llx\n", pmu_attr->id); +} + +#define HISI_PCIE_PMU_FORMAT_ATTR(_name, _format) \ + (&((struct dev_ext_attribute[]){ \ + { .attr = __ATTR(_name, 0444, hisi_pcie_format_sysfs_show, \ + NULL), \ + .var = (void *)_format } \ + })[0].attr.attr) + +#define HISI_PCIE_PMU_EVENT_ATTR(_name, _id) \ + PMU_EVENT_ATTR_ID(_name, hisi_pcie_event_sysfs_show, _id) + +static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return cpumap_print_to_pagebuf(true, buf, cpumask_of(pcie_pmu->on_cpu)); +} +static DEVICE_ATTR_RO(cpumask); + +static ssize_t identifier_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(buf, "%#x\n", pcie_pmu->identifier); +} +static DEVICE_ATTR_RO(identifier); + +static ssize_t bus_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(dev_get_drvdata(dev)); + + return sysfs_emit(buf, "%#04x\n", PCI_BUS_NUM(pcie_pmu->bdf_min)); +} +static DEVICE_ATTR_RO(bus); + +static struct hisi_pcie_reg_pair +hisi_pcie_parse_reg_value(struct hisi_pcie_pmu *pcie_pmu, u32 reg_off) +{ + u32 val = readl_relaxed(pcie_pmu->base + reg_off); + struct hisi_pcie_reg_pair regs = { + .lo = val, + .hi = val >> 16, + }; + + return regs; +} + +/* + * Hardware counter and ext_counter work together for bandwidth, latency, bus + * utilization and buffer occupancy events. For example, RX memory write latency + * events(index = 0x0010), counter counts total delay cycles and ext_counter + * counts RX memory write PCIe packets number. + * + * As we don't want PMU driver to process these two data, "delay cycles" can + * be treated as an independent event(index = 0x0010), "RX memory write packets + * number" as another(index = 0x10010). BIT 16 is used to distinguish and 0-15 + * bits are "real" event index, which can be used to set HISI_PCIE_EVENT_CTRL. + */ +#define EXT_COUNTER_IS_USED(idx) ((idx) & BIT(16)) + +static u32 hisi_pcie_get_real_event(struct perf_event *event) +{ + return hisi_pcie_get_event(event) & GENMASK(15, 0); +} + +static u32 hisi_pcie_pmu_get_offset(u32 offset, u32 idx) +{ + return offset + HISI_PCIE_REG_STEP * idx; +} + +static u32 hisi_pcie_pmu_readl(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, + u32 idx) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + return readl_relaxed(pcie_pmu->base + offset); +} + +static void hisi_pcie_pmu_writel(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, u32 idx, u32 val) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + writel_relaxed(val, pcie_pmu->base + offset); +} + +static u64 hisi_pcie_pmu_readq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, u32 idx) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + return readq_relaxed(pcie_pmu->base + offset); +} + +static void hisi_pcie_pmu_writeq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset, u32 idx, u64 val) +{ + u32 offset = hisi_pcie_pmu_get_offset(reg_offset, idx); + + writeq_relaxed(val, pcie_pmu->base + offset); +} + +static void hisi_pcie_pmu_config_filter(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + u64 reg = HISI_PCIE_INIT_SET; + u64 port, trig_len, thr_len; + + /* Config HISI_PCIE_EVENT_CTRL according to event. */ + reg |= FIELD_PREP(HISI_PCIE_EVENT_M, hisi_pcie_get_real_event(event)); + + /* Config HISI_PCIE_EVENT_CTRL according to root port or EP device. */ + port = hisi_pcie_get_port(event); + if (port) + reg |= FIELD_PREP(HISI_PCIE_TARGET_M, port); + else + reg |= HISI_PCIE_TARGET_EN | + FIELD_PREP(HISI_PCIE_TARGET_M, hisi_pcie_get_bdf(event)); + + /* Config HISI_PCIE_EVENT_CTRL according to trigger condition. */ + trig_len = hisi_pcie_get_trig_len(event); + if (trig_len) { + reg |= FIELD_PREP(HISI_PCIE_TRIG_M, trig_len); + reg |= FIELD_PREP(HISI_PCIE_TRIG_MODE_M, hisi_pcie_get_trig_mode(event)); + reg |= HISI_PCIE_TRIG_EN; + } + + /* Config HISI_PCIE_EVENT_CTRL according to threshold condition. */ + thr_len = hisi_pcie_get_thr_len(event); + if (thr_len) { + reg |= FIELD_PREP(HISI_PCIE_THR_M, thr_len); + reg |= FIELD_PREP(HISI_PCIE_THR_MODE_M, hisi_pcie_get_thr_mode(event)); + reg |= HISI_PCIE_THR_EN; + } + + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, reg); +} + +static void hisi_pcie_pmu_clear_filter(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, hwc->idx, HISI_PCIE_INIT_SET); +} + +static bool hisi_pcie_pmu_valid_requester_id(struct hisi_pcie_pmu *pcie_pmu, u32 bdf) +{ + struct pci_dev *root_port, *pdev; + u16 rp_bdf; + + pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pcie_pmu->pdev->bus), PCI_BUS_NUM(bdf), + GET_PCI_DEVFN(bdf)); + if (!pdev) + return false; + + root_port = pcie_find_root_port(pdev); + if (!root_port) { + pci_dev_put(pdev); + return false; + } + + pci_dev_put(pdev); + rp_bdf = pci_dev_id(root_port); + return rp_bdf >= pcie_pmu->bdf_min && rp_bdf <= pcie_pmu->bdf_max; +} + +static bool hisi_pcie_pmu_valid_filter(struct perf_event *event, + struct hisi_pcie_pmu *pcie_pmu) +{ + u32 requester_id = hisi_pcie_get_bdf(event); + + if (hisi_pcie_get_thr_len(event) > HISI_PCIE_THR_MAX_VAL) + return false; + + if (hisi_pcie_get_trig_len(event) > HISI_PCIE_TRIG_MAX_VAL) + return false; + + if (requester_id) { + if (!hisi_pcie_pmu_valid_requester_id(pcie_pmu, requester_id)) + return false; + } + + return true; +} + +static bool hisi_pcie_pmu_cmp_event(struct perf_event *target, + struct perf_event *event) +{ + return hisi_pcie_get_real_event(target) == hisi_pcie_get_real_event(event); +} + +static bool hisi_pcie_pmu_validate_event_group(struct perf_event *event) +{ + struct perf_event *sibling, *leader = event->group_leader; + struct perf_event *event_group[HISI_PCIE_MAX_COUNTERS]; + int counters = 1; + int num; + + event_group[0] = leader; + if (!is_software_event(leader)) { + if (leader->pmu != event->pmu) + return false; + + if (leader != event && !hisi_pcie_pmu_cmp_event(leader, event)) + event_group[counters++] = event; + } + + for_each_sibling_event(sibling, event->group_leader) { + if (is_software_event(sibling)) + continue; + + if (sibling->pmu != event->pmu) + return false; + + for (num = 0; num < counters; num++) { + if (hisi_pcie_pmu_cmp_event(event_group[num], sibling)) + break; + } + + if (num == counters) + event_group[counters++] = sibling; + } + + return counters <= HISI_PCIE_MAX_COUNTERS; +} + +static int hisi_pcie_pmu_event_init(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + event->cpu = pcie_pmu->on_cpu; + + if (EXT_COUNTER_IS_USED(hisi_pcie_get_event(event))) + hwc->event_base = HISI_PCIE_EXT_CNT; + else + hwc->event_base = HISI_PCIE_CNT; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* Sampling is not supported. */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EOPNOTSUPP; + + if (!hisi_pcie_pmu_valid_filter(event, pcie_pmu)) + return -EINVAL; + + if (!hisi_pcie_pmu_validate_event_group(event)) + return -EINVAL; + + return 0; +} + +static u64 hisi_pcie_pmu_read_counter(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + u32 idx = event->hw.idx; + + return hisi_pcie_pmu_readq(pcie_pmu, event->hw.event_base, idx); +} + +static int hisi_pcie_pmu_find_related_event(struct hisi_pcie_pmu *pcie_pmu, + struct perf_event *event) +{ + struct perf_event *sibling; + int idx; + + for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { + sibling = pcie_pmu->hw_events[idx]; + if (!sibling) + continue; + + if (!hisi_pcie_pmu_cmp_event(sibling, event)) + continue; + + /* Related events must be used in group */ + if (sibling->group_leader == event->group_leader) + return idx; + else + return -EINVAL; + } + + return idx; +} + +static int hisi_pcie_pmu_get_event_idx(struct hisi_pcie_pmu *pcie_pmu) +{ + int idx; + + for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { + if (!pcie_pmu->hw_events[idx]) + return idx; + } + + return -EINVAL; +} + +static void hisi_pcie_pmu_event_update(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 new_cnt, prev_cnt, delta; + + do { + prev_cnt = local64_read(&hwc->prev_count); + new_cnt = hisi_pcie_pmu_read_counter(event); + } while (local64_cmpxchg(&hwc->prev_count, prev_cnt, + new_cnt) != prev_cnt); + + delta = (new_cnt - prev_cnt) & HISI_PCIE_MAX_PERIOD; + local64_add(delta, &event->count); +} + +static void hisi_pcie_pmu_read(struct perf_event *event) +{ + hisi_pcie_pmu_event_update(event); +} + +static void hisi_pcie_pmu_set_period(struct perf_event *event) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + local64_set(&hwc->prev_count, HISI_PCIE_INIT_VAL); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_CNT, idx, HISI_PCIE_INIT_VAL); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EXT_CNT, idx, HISI_PCIE_INIT_VAL); +} + +static void hisi_pcie_pmu_enable_counter(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + u64 val; + + val = hisi_pcie_pmu_readq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx); + val |= HISI_PCIE_EVENT_EN; + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, val); +} + +static void hisi_pcie_pmu_disable_counter(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + u64 val; + + val = hisi_pcie_pmu_readq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx); + val &= ~HISI_PCIE_EVENT_EN; + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, val); +} + +static void hisi_pcie_pmu_enable_int(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + + hisi_pcie_pmu_writel(pcie_pmu, HISI_PCIE_INT_MASK, idx, 0); +} + +static void hisi_pcie_pmu_disable_int(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc) +{ + u32 idx = hwc->idx; + + hisi_pcie_pmu_writel(pcie_pmu, HISI_PCIE_INT_MASK, idx, 1); +} + +static void hisi_pcie_pmu_reset_counter(struct hisi_pcie_pmu *pcie_pmu, int idx) +{ + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, HISI_PCIE_RESET_CNT); + hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EVENT_CTRL, idx, HISI_PCIE_INIT_SET); +} + +static void hisi_pcie_pmu_start(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + u64 prev_cnt; + + if (WARN_ON_ONCE(!(hwc->state & PERF_HES_STOPPED))) + return; + + WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE)); + hwc->state = 0; + + hisi_pcie_pmu_config_filter(event); + hisi_pcie_pmu_enable_counter(pcie_pmu, hwc); + hisi_pcie_pmu_enable_int(pcie_pmu, hwc); + hisi_pcie_pmu_set_period(event); + + if (flags & PERF_EF_RELOAD) { + prev_cnt = local64_read(&hwc->prev_count); + hisi_pcie_pmu_writeq(pcie_pmu, hwc->event_base, idx, prev_cnt); + } + + perf_event_update_userpage(event); +} + +static void hisi_pcie_pmu_stop(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + hisi_pcie_pmu_event_update(event); + hisi_pcie_pmu_disable_int(pcie_pmu, hwc); + hisi_pcie_pmu_disable_counter(pcie_pmu, hwc); + hisi_pcie_pmu_clear_filter(event); + WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED); + hwc->state |= PERF_HES_STOPPED; + + if (hwc->state & PERF_HES_UPTODATE) + return; + + hwc->state |= PERF_HES_UPTODATE; +} + +static int hisi_pcie_pmu_add(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx; + + hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + + /* Check all working events to find a related event. */ + idx = hisi_pcie_pmu_find_related_event(pcie_pmu, event); + if (idx < 0) + return idx; + + /* Current event shares an enabled counter with the related event */ + if (idx < HISI_PCIE_MAX_COUNTERS) { + hwc->idx = idx; + goto start_count; + } + + idx = hisi_pcie_pmu_get_event_idx(pcie_pmu); + if (idx < 0) + return idx; + + hwc->idx = idx; + pcie_pmu->hw_events[idx] = event; + /* Reset Counter to avoid previous statistic interference. */ + hisi_pcie_pmu_reset_counter(pcie_pmu, idx); + +start_count: + if (flags & PERF_EF_START) + hisi_pcie_pmu_start(event, PERF_EF_RELOAD); + + return 0; +} + +static void hisi_pcie_pmu_del(struct perf_event *event, int flags) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + + hisi_pcie_pmu_stop(event, PERF_EF_UPDATE); + pcie_pmu->hw_events[hwc->idx] = NULL; + perf_event_update_userpage(event); +} + +static void hisi_pcie_pmu_enable(struct pmu *pmu) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(pmu); + int num; + + for (num = 0; num < HISI_PCIE_MAX_COUNTERS; num++) { + if (pcie_pmu->hw_events[num]) + break; + } + + if (num == HISI_PCIE_MAX_COUNTERS) + return; + + writel(HISI_PCIE_GLOBAL_EN, pcie_pmu->base + HISI_PCIE_GLOBAL_CTRL); +} + +static void hisi_pcie_pmu_disable(struct pmu *pmu) +{ + struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(pmu); + + writel(HISI_PCIE_GLOBAL_NONE, pcie_pmu->base + HISI_PCIE_GLOBAL_CTRL); +} + +static irqreturn_t hisi_pcie_pmu_irq(int irq, void *data) +{ + struct hisi_pcie_pmu *pcie_pmu = data; + irqreturn_t ret = IRQ_NONE; + struct perf_event *event; + u32 overflown; + int idx; + + for (idx = 0; idx < HISI_PCIE_MAX_COUNTERS; idx++) { + overflown = hisi_pcie_pmu_readl(pcie_pmu, HISI_PCIE_INT_STAT, idx); + if (!overflown) + continue; + + /* Clear status of interrupt. */ + hisi_pcie_pmu_writel(pcie_pmu, HISI_PCIE_INT_STAT, idx, 1); + event = pcie_pmu->hw_events[idx]; + if (!event) + continue; + + hisi_pcie_pmu_event_update(event); + hisi_pcie_pmu_set_period(event); + ret = IRQ_HANDLED; + } + + return ret; +} + +static int hisi_pcie_pmu_irq_register(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + int irq, ret; + + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + pci_err(pdev, "Failed to enable MSI vectors: %d\n", ret); + return ret; + } + + irq = pci_irq_vector(pdev, 0); + ret = request_irq(irq, hisi_pcie_pmu_irq, IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME, + pcie_pmu); + if (ret) { + pci_err(pdev, "Failed to register IRQ: %d\n", ret); + pci_free_irq_vectors(pdev); + return ret; + } + + pcie_pmu->irq = irq; + + return 0; +} + +static void hisi_pcie_pmu_irq_unregister(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + free_irq(pcie_pmu->irq, pcie_pmu); + pci_free_irq_vectors(pdev); +} + +static int hisi_pcie_pmu_online_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node); + + if (pcie_pmu->on_cpu == -1) { + pcie_pmu->on_cpu = cpu; + WARN_ON(irq_set_affinity(pcie_pmu->irq, cpumask_of(cpu))); + } + + return 0; +} + +static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) +{ + struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node); + unsigned int target; + + /* Nothing to do if this CPU doesn't own the PMU */ + if (pcie_pmu->on_cpu != cpu) + return 0; + + pcie_pmu->on_cpu = -1; + /* Choose a new CPU from all online cpus. */ + target = cpumask_first(cpu_online_mask); + if (target >= nr_cpu_ids) { + pci_err(pcie_pmu->pdev, "There is no CPU to set\n"); + return 0; + } + + perf_pmu_migrate_context(&pcie_pmu->pmu, cpu, target); + /* Use this CPU for event counting */ + pcie_pmu->on_cpu = target; + WARN_ON(irq_set_affinity(pcie_pmu->irq, cpumask_of(target))); + + return 0; +} + +static struct attribute *hisi_pcie_pmu_events_attr[] = { + HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_latency, 0x0010), + HISI_PCIE_PMU_EVENT_ATTR(rx_mwr_cnt, 0x10010), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_latency, 0x0210), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_cnt, 0x10210), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_latency, 0x0011), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_cnt, 0x10011), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_flux, 0x1005), + HISI_PCIE_PMU_EVENT_ATTR(rx_mrd_time, 0x11005), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_flux, 0x2004), + HISI_PCIE_PMU_EVENT_ATTR(tx_mrd_time, 0x12004), + NULL +}; + +static struct attribute_group hisi_pcie_pmu_events_group = { + .name = "events", + .attrs = hisi_pcie_pmu_events_attr, +}; + +static struct attribute *hisi_pcie_pmu_format_attr[] = { + HISI_PCIE_PMU_FORMAT_ATTR(event, "config:0-16"), + HISI_PCIE_PMU_FORMAT_ATTR(thr_len, "config1:0-3"), + HISI_PCIE_PMU_FORMAT_ATTR(thr_mode, "config1:4"), + HISI_PCIE_PMU_FORMAT_ATTR(trig_len, "config1:5-8"), + HISI_PCIE_PMU_FORMAT_ATTR(trig_mode, "config1:9"), + HISI_PCIE_PMU_FORMAT_ATTR(port, "config2:0-15"), + HISI_PCIE_PMU_FORMAT_ATTR(bdf, "config2:16-31"), + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_format_group = { + .name = "format", + .attrs = hisi_pcie_pmu_format_attr, +}; + +static struct attribute *hisi_pcie_pmu_bus_attrs[] = { + &dev_attr_bus.attr, + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_bus_attr_group = { + .attrs = hisi_pcie_pmu_bus_attrs, +}; + +static struct attribute *hisi_pcie_pmu_cpumask_attrs[] = { + &dev_attr_cpumask.attr, + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_cpumask_attr_group = { + .attrs = hisi_pcie_pmu_cpumask_attrs, +}; + +static struct attribute *hisi_pcie_pmu_identifier_attrs[] = { + &dev_attr_identifier.attr, + NULL +}; + +static const struct attribute_group hisi_pcie_pmu_identifier_attr_group = { + .attrs = hisi_pcie_pmu_identifier_attrs, +}; + +static const struct attribute_group *hisi_pcie_pmu_attr_groups[] = { + &hisi_pcie_pmu_events_group, + &hisi_pcie_pmu_format_group, + &hisi_pcie_pmu_bus_attr_group, + &hisi_pcie_pmu_cpumask_attr_group, + &hisi_pcie_pmu_identifier_attr_group, + NULL +}; + +static int hisi_pcie_alloc_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + struct hisi_pcie_reg_pair regs; + u16 sicl_id, core_id; + char *name; + + regs = hisi_pcie_parse_reg_value(pcie_pmu, HISI_PCIE_REG_BDF); + pcie_pmu->bdf_min = regs.lo; + pcie_pmu->bdf_max = regs.hi; + + regs = hisi_pcie_parse_reg_value(pcie_pmu, HISI_PCIE_REG_INFO); + sicl_id = regs.hi; + core_id = regs.lo; + + name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_pcie%u_core%u", sicl_id, core_id); + if (!name) + return -ENOMEM; + + pcie_pmu->pdev = pdev; + pcie_pmu->on_cpu = -1; + pcie_pmu->identifier = readl(pcie_pmu->base + HISI_PCIE_REG_VERSION); + pcie_pmu->pmu = (struct pmu) { + .name = name, + .module = THIS_MODULE, + .event_init = hisi_pcie_pmu_event_init, + .pmu_enable = hisi_pcie_pmu_enable, + .pmu_disable = hisi_pcie_pmu_disable, + .add = hisi_pcie_pmu_add, + .del = hisi_pcie_pmu_del, + .start = hisi_pcie_pmu_start, + .stop = hisi_pcie_pmu_stop, + .read = hisi_pcie_pmu_read, + .task_ctx_nr = perf_invalid_context, + .attr_groups = hisi_pcie_pmu_attr_groups, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE, + }; + + return 0; +} + +static int hisi_pcie_init_pmu(struct pci_dev *pdev, struct hisi_pcie_pmu *pcie_pmu) +{ + int ret; + + pcie_pmu->base = pci_ioremap_bar(pdev, 2); + if (!pcie_pmu->base) { + pci_err(pdev, "Ioremap failed for pcie_pmu resource\n"); + return -ENOMEM; + } + + ret = hisi_pcie_alloc_pmu(pdev, pcie_pmu); + if (ret) + goto err_iounmap; + + ret = hisi_pcie_pmu_irq_register(pdev, pcie_pmu); + if (ret) + goto err_iounmap; + + ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, &pcie_pmu->node); + if (ret) { + pci_err(pdev, "Failed to register hotplug: %d\n", ret); + goto err_irq_unregister; + } + + ret = perf_pmu_register(&pcie_pmu->pmu, pcie_pmu->pmu.name, -1); + if (ret) { + pci_err(pdev, "Failed to register PCIe PMU: %d\n", ret); + goto err_hotplug_unregister; + } + + return ret; + +err_hotplug_unregister: + cpuhp_state_remove_instance_nocalls( + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, &pcie_pmu->node); + +err_irq_unregister: + hisi_pcie_pmu_irq_unregister(pdev, pcie_pmu); + +err_iounmap: + iounmap(pcie_pmu->base); + + return ret; +} + +static void hisi_pcie_uninit_pmu(struct pci_dev *pdev) +{ + struct hisi_pcie_pmu *pcie_pmu = pci_get_drvdata(pdev); + + perf_pmu_unregister(&pcie_pmu->pmu); + cpuhp_state_remove_instance_nocalls( + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, &pcie_pmu->node); + hisi_pcie_pmu_irq_unregister(pdev, pcie_pmu); + iounmap(pcie_pmu->base); +} + +static int hisi_pcie_init_dev(struct pci_dev *pdev) +{ + int ret; + + ret = pcim_enable_device(pdev); + if (ret) { + pci_err(pdev, "Failed to enable PCI device: %d\n", ret); + return ret; + } + + ret = pcim_iomap_regions(pdev, BIT(2), DRV_NAME); + if (ret < 0) { + pci_err(pdev, "Failed to request PCI mem regions: %d\n", ret); + return ret; + } + + pci_set_master(pdev); + + return 0; +} + +static int hisi_pcie_pmu_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct hisi_pcie_pmu *pcie_pmu; + int ret; + + pcie_pmu = devm_kzalloc(&pdev->dev, sizeof(*pcie_pmu), GFP_KERNEL); + if (!pcie_pmu) + return -ENOMEM; + + ret = hisi_pcie_init_dev(pdev); + if (ret) + return ret; + + ret = hisi_pcie_init_pmu(pdev, pcie_pmu); + if (ret) + return ret; + + pci_set_drvdata(pdev, pcie_pmu); + + return ret; +} + +static void hisi_pcie_pmu_remove(struct pci_dev *pdev) +{ + hisi_pcie_uninit_pmu(pdev); + pci_set_drvdata(pdev, NULL); +} + +static const struct pci_device_id hisi_pcie_pmu_ids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa12d) }, + { 0, } +}; +MODULE_DEVICE_TABLE(pci, hisi_pcie_pmu_ids); + +static struct pci_driver hisi_pcie_pmu_driver = { + .name = DRV_NAME, + .id_table = hisi_pcie_pmu_ids, + .probe = hisi_pcie_pmu_probe, + .remove = hisi_pcie_pmu_remove, +}; + +static int __init hisi_pcie_module_init(void) +{ + int ret; + + ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, + "AP_PERF_ARM_HISI_PCIE_PMU_ONLINE", + hisi_pcie_pmu_online_cpu, + hisi_pcie_pmu_offline_cpu); + if (ret) { + pr_err("Failed to setup PCIe PMU hotplug: %d\n", ret); + return ret; + } + + ret = pci_register_driver(&hisi_pcie_pmu_driver); + if (ret) + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE); + + return ret; +} +module_init(hisi_pcie_module_init); + +static void __exit hisi_pcie_module_exit(void) +{ + pci_unregister_driver(&hisi_pcie_pmu_driver); + cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE); +} +module_exit(hisi_pcie_module_exit); + +MODULE_DESCRIPTION("HiSilicon PCIe PMU driver"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Qi Liu "); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 773c83730906..411a428ace4d 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -225,6 +225,7 @@ enum cpuhp_state { CPUHP_AP_PERF_ARM_HISI_L3_ONLINE, CPUHP_AP_PERF_ARM_HISI_PA_ONLINE, CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE, + CPUHP_AP_PERF_ARM_HISI_PCIE_PMU_ONLINE, CPUHP_AP_PERF_ARM_L2X0_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE, CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE, -- cgit v1.2.3 From c8a2a011cd04054a6577d8cf774adf9e09302876 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 14 Dec 2021 03:45:35 +0200 Subject: net: dsa: sja1105: fix broken connection with the sja1110 tagger The driver was incorrectly converted assuming that "sja1105" is the only tagger supported by this driver. This results in SJA1110 switches failing to probe: sja1105 spi1.0: Unable to connect to tag protocol "sja1110": -EPROTONOSUPPORT sja1105: probe of spi1.2 failed with error -93 Add DSA_TAG_PROTO_SJA1110 to the list of supported taggers by the sja1105 driver. The sja1105_tagger_data structure format is common for the two tagging protocols. Fixes: c79e84866d2a ("net: dsa: tag_sja1105: convert to tagger-owned data") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/dsa/sja1105/sja1105_main.c | 16 ++++++++-------- include/linux/dsa/sja1105.h | 3 ++- 2 files changed, 10 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 9171fbea588c..b513713be610 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2708,17 +2708,17 @@ static void sja1105_port_deferred_xmit(struct kthread_work *work) static int sja1105_connect_tag_protocol(struct dsa_switch *ds, enum dsa_tag_protocol proto) { + struct sja1105_private *priv = ds->priv; struct sja1105_tagger_data *tagger_data; - switch (proto) { - case DSA_TAG_PROTO_SJA1105: - tagger_data = sja1105_tagger_data(ds); - tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; - tagger_data->meta_tstamp_handler = sja1110_process_meta_tstamp; - return 0; - default: + if (proto != priv->info->tag_proto) return -EPROTONOSUPPORT; - } + + tagger_data = sja1105_tagger_data(ds); + tagger_data->xmit_work_fn = sja1105_port_deferred_xmit; + tagger_data->meta_tstamp_handler = sja1110_process_meta_tstamp; + + return 0; } /* The MAXAGE setting belongs to the L2 Forwarding Parameters table, diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e9cb1ae6d742..159e43171ccc 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -70,7 +70,8 @@ struct sja1105_skb_cb { static inline struct sja1105_tagger_data * sja1105_tagger_data(struct dsa_switch *ds) { - BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1105); + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1105 && + ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1110); return ds->tagger_data; } -- cgit v1.2.3 From 9280ac2e6f199cddcd746a9ba459136b8666287b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 14 Dec 2021 07:15:15 -0800 Subject: net: dev_replace_track() cleanup Use existing helpers (netdev_tracker_free() and netdev_tracker_alloc()) to remove ifdefery. Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20211214151515.312535-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 235d5d082f1a..c06e9dc1a317 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3885,16 +3885,14 @@ static inline void dev_replace_track(struct net_device *odev, netdevice_tracker *tracker, gfp_t gfp) { -#ifdef CONFIG_NET_DEV_REFCNT_TRACKER if (odev) - ref_tracker_free(&odev->refcnt_tracker, tracker); -#endif + netdev_tracker_free(odev, tracker); + dev_hold(ndev); dev_put(odev); -#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + if (ndev) - ref_tracker_alloc(&ndev->refcnt_tracker, tracker, gfp); -#endif + netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on -- cgit v1.2.3 From ad69cd9972e79aba103ba5365de0acd35770c265 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:27 +0200 Subject: fsnotify: clarify object type argument In preparation for separating object type from iterator type, rename some 'type' arguments in functions to 'obj_type' and remove the unused interface to clear marks by object type mask. Link: https://lore.kernel.org/r/20211129201537.1932819-2-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify_user.c | 8 ++++---- fs/notify/group.c | 2 +- fs/notify/mark.c | 27 +++++++++++++++------------ include/linux/fsnotify_backend.h | 28 ++++++++++++---------------- 4 files changed, 32 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 559bc1e9926d..ab24c37f1fdf 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1057,7 +1057,7 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark, static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, fsnotify_connp_t *connp, - unsigned int type, + unsigned int obj_type, __kernel_fsid_t *fsid) { struct ucounts *ucounts = group->fanotify_data.ucounts; @@ -1080,7 +1080,7 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group, } fsnotify_init_mark(mark, group); - ret = fsnotify_add_mark_locked(mark, connp, type, 0, fsid); + ret = fsnotify_add_mark_locked(mark, connp, obj_type, 0, fsid); if (ret) { fsnotify_put_mark(mark); goto out_dec_ucounts; @@ -1105,7 +1105,7 @@ static int fanotify_group_init_error_pool(struct fsnotify_group *group) } static int fanotify_add_mark(struct fsnotify_group *group, - fsnotify_connp_t *connp, unsigned int type, + fsnotify_connp_t *connp, unsigned int obj_type, __u32 mask, unsigned int flags, __kernel_fsid_t *fsid) { @@ -1116,7 +1116,7 @@ static int fanotify_add_mark(struct fsnotify_group *group, mutex_lock(&group->mark_mutex); fsn_mark = fsnotify_find_mark(connp, group); if (!fsn_mark) { - fsn_mark = fanotify_add_new_mark(group, connp, type, fsid); + fsn_mark = fanotify_add_new_mark(group, connp, obj_type, fsid); if (IS_ERR(fsn_mark)) { mutex_unlock(&group->mark_mutex); return PTR_ERR(fsn_mark); diff --git a/fs/notify/group.c b/fs/notify/group.c index 6a297efc4788..b7d4d64f87c2 100644 --- a/fs/notify/group.c +++ b/fs/notify/group.c @@ -58,7 +58,7 @@ void fsnotify_destroy_group(struct fsnotify_group *group) fsnotify_group_stop_queueing(group); /* Clear all marks for this group and queue them for destruction */ - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES_MASK); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_ANY); /* * Some marks can still be pinned when waiting for response from diff --git a/fs/notify/mark.c b/fs/notify/mark.c index fa1d99101f89..52af2e9dadc0 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -496,7 +496,7 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, - unsigned int type, + unsigned int obj_type, __kernel_fsid_t *fsid) { struct inode *inode = NULL; @@ -507,7 +507,7 @@ static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); - conn->type = type; + conn->type = obj_type; conn->obj = connp; /* Cache fsid of filesystem containing the object */ if (fsid) { @@ -572,7 +572,8 @@ out: * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, + fsnotify_connp_t *connp, + unsigned int obj_type, int allow_dups, __kernel_fsid_t *fsid) { struct fsnotify_mark *lmark, *last = NULL; @@ -580,7 +581,7 @@ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, int cmp; int err = 0; - if (WARN_ON(!fsnotify_valid_obj_type(type))) + if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* Backend is expected to check for zero fsid (e.g. tmpfs) */ @@ -592,7 +593,8 @@ restart: conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); - err = fsnotify_attach_connector_to_object(connp, type, fsid); + err = fsnotify_attach_connector_to_object(connp, obj_type, + fsid); if (err) return err; goto restart; @@ -665,7 +667,7 @@ out_err: * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, + fsnotify_connp_t *connp, unsigned int obj_type, int allow_dups, __kernel_fsid_t *fsid) { struct fsnotify_group *group = mark->group; @@ -686,7 +688,7 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); - ret = fsnotify_add_mark_list(mark, connp, type, allow_dups, fsid); + ret = fsnotify_add_mark_list(mark, connp, obj_type, allow_dups, fsid); if (ret) goto err; @@ -706,13 +708,14 @@ err: } int fsnotify_add_mark(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups, __kernel_fsid_t *fsid) + unsigned int obj_type, int allow_dups, + __kernel_fsid_t *fsid) { int ret; struct fsnotify_group *group = mark->group; mutex_lock(&group->mark_mutex); - ret = fsnotify_add_mark_locked(mark, connp, type, allow_dups, fsid); + ret = fsnotify_add_mark_locked(mark, connp, obj_type, allow_dups, fsid); mutex_unlock(&group->mark_mutex); return ret; } @@ -747,14 +750,14 @@ EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, - unsigned int type_mask) + unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ - if (type_mask == FSNOTIFY_OBJ_ALL_TYPES_MASK) { + if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } @@ -769,7 +772,7 @@ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, */ mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { - if ((1U << mark->connector->type) & type_mask) + if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } mutex_unlock(&group->mark_mutex); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 51ef2b079bfa..b9c84b1dbcc8 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -338,6 +338,7 @@ static inline struct fs_error_report *fsnotify_data_error_report( } enum fsnotify_obj_type { + FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, @@ -346,15 +347,9 @@ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; -#define FSNOTIFY_OBJ_TYPE_INODE_FL (1U << FSNOTIFY_OBJ_TYPE_INODE) -#define FSNOTIFY_OBJ_TYPE_PARENT_FL (1U << FSNOTIFY_OBJ_TYPE_PARENT) -#define FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL (1U << FSNOTIFY_OBJ_TYPE_VFSMOUNT) -#define FSNOTIFY_OBJ_TYPE_SB_FL (1U << FSNOTIFY_OBJ_TYPE_SB) -#define FSNOTIFY_OBJ_ALL_TYPES_MASK ((1U << FSNOTIFY_OBJ_TYPE_COUNT) - 1) - -static inline bool fsnotify_valid_obj_type(unsigned int type) +static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { - return (type < FSNOTIFY_OBJ_TYPE_COUNT); + return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { @@ -387,7 +382,7 @@ static inline void fsnotify_iter_set_report_type_mark( static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & FSNOTIFY_OBJ_TYPE_##NAME##_FL) ? \ + return (iter_info->report_mask & (1U << FSNOTIFY_OBJ_TYPE_##NAME)) ? \ iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ } @@ -604,11 +599,11 @@ extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn, __kernel_fsid_t *fsid); /* attach the mark to the object */ extern int fsnotify_add_mark(struct fsnotify_mark *mark, - fsnotify_connp_t *connp, unsigned int type, + fsnotify_connp_t *connp, unsigned int obj_type, int allow_dups, __kernel_fsid_t *fsid); extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark, fsnotify_connp_t *connp, - unsigned int type, int allow_dups, + unsigned int obj_type, int allow_dups, __kernel_fsid_t *fsid); /* attach the mark to the inode */ @@ -637,22 +632,23 @@ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); -/* run all the marks in a group, and clear all of the marks attached to given object type */ -extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int type); +/* Clear all of the marks of a group attached to a given object type */ +extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, + unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { - fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB_FL); + fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); -- cgit v1.2.3 From 1c9007d62bea6fd164285314f7553f73e5308863 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:28 +0200 Subject: fsnotify: separate mark iterator type from object type enum They are two different types that use the same enum, so this confusing. Use the object type to indicate the type of object mark is attached to and the iter type to indicate the type of watch. A group can have two different watches of the same object type (parent and child watches) that match the same event. Link: https://lore.kernel.org/r/20211129201537.1932819-3-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 6 +++--- fs/notify/fsnotify.c | 18 +++++++++--------- fs/notify/mark.c | 4 ++-- include/linux/fsnotify_backend.h | 41 +++++++++++++++++++++++++++------------- 4 files changed, 42 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index b6091775aa6e..652fe84cb8ac 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -299,7 +299,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, return 0; } - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { if (!fsnotify_iter_should_report_type(iter_info, type)) continue; mark = iter_info->marks[type]; @@ -318,7 +318,7 @@ static u32 fanotify_group_event_mask(struct fsnotify_group *group, * If the event is on a child and this mark is on a parent not * watching children, don't send it! */ - if (type == FSNOTIFY_OBJ_TYPE_PARENT && + if (type == FSNOTIFY_ITER_TYPE_PARENT && !(mark->mask & FS_EVENT_ON_CHILD)) continue; @@ -746,7 +746,7 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info) int type; __kernel_fsid_t fsid = {}; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { struct fsnotify_mark_connector *conn; if (!fsnotify_iter_should_report_type(iter_info, type)) diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 4034ca566f95..0c94457c625e 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -330,7 +330,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type, /* clear ignored on inode modification */ if (mask & FS_MODIFY) { - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { if (!fsnotify_iter_should_report_type(iter_info, type)) continue; mark = iter_info->marks[type]; @@ -340,7 +340,7 @@ static int send_to_group(__u32 mask, const void *data, int data_type, } } - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { if (!fsnotify_iter_should_report_type(iter_info, type)) continue; mark = iter_info->marks[type]; @@ -405,7 +405,7 @@ static unsigned int fsnotify_iter_select_report_types( int type; /* Choose max prio group among groups of all queue heads */ - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) > 0) @@ -417,7 +417,7 @@ static unsigned int fsnotify_iter_select_report_types( /* Set the report mask for marks from same group as max prio group */ iter_info->report_mask = 0; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { mark = iter_info->marks[type]; if (mark && fsnotify_compare_groups(max_prio_group, mark->group) == 0) @@ -435,7 +435,7 @@ static void fsnotify_iter_next(struct fsnotify_iter_info *iter_info) { int type; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { if (fsnotify_iter_should_report_type(iter_info, type)) iter_info->marks[type] = fsnotify_next_mark(iter_info->marks[type]); @@ -519,18 +519,18 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - iter_info.marks[FSNOTIFY_OBJ_TYPE_SB] = + iter_info.marks[FSNOTIFY_ITER_TYPE_SB] = fsnotify_first_mark(&sb->s_fsnotify_marks); if (mnt) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] = + iter_info.marks[FSNOTIFY_ITER_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } if (inode) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = + iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } if (parent) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_PARENT] = + iter_info.marks[FSNOTIFY_ITER_TYPE_PARENT] = fsnotify_first_mark(&parent->i_fsnotify_marks); } diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 52af2e9dadc0..9007d6affff3 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -353,7 +353,7 @@ bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) { int type; - fsnotify_foreach_obj_type(type) { + fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); @@ -382,7 +382,7 @@ void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - fsnotify_foreach_obj_type(type) + fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index b9c84b1dbcc8..73739fee1710 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -337,10 +337,25 @@ static inline struct fs_error_report *fsnotify_data_error_report( } } +/* + * Index to merged marks iterator array that correlates to a type of watch. + * The type of watched object can be deduced from the iterator type, but not + * the other way around, because an event can match different watched objects + * of the same object type. + * For example, both parent and child are watching an object of type inode. + */ +enum fsnotify_iter_type { + FSNOTIFY_ITER_TYPE_INODE, + FSNOTIFY_ITER_TYPE_VFSMOUNT, + FSNOTIFY_ITER_TYPE_SB, + FSNOTIFY_ITER_TYPE_PARENT, + FSNOTIFY_ITER_TYPE_COUNT +}; + +/* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, - FSNOTIFY_OBJ_TYPE_PARENT, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, @@ -353,37 +368,37 @@ static inline bool fsnotify_valid_obj_type(unsigned int obj_type) } struct fsnotify_iter_info { - struct fsnotify_mark *marks[FSNOTIFY_OBJ_TYPE_COUNT]; + struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) { - return (iter_info->report_mask & (1U << type)); + return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( - struct fsnotify_iter_info *iter_info, int type) + struct fsnotify_iter_info *iter_info, int iter_type) { - iter_info->report_mask |= (1U << type); + iter_info->report_mask |= (1U << iter_type); } static inline void fsnotify_iter_set_report_type_mark( - struct fsnotify_iter_info *iter_info, int type, + struct fsnotify_iter_info *iter_info, int iter_type, struct fsnotify_mark *mark) { - iter_info->marks[type] = mark; - iter_info->report_mask |= (1U << type); + iter_info->marks[iter_type] = mark; + iter_info->report_mask |= (1U << iter_type); } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ - return (iter_info->report_mask & (1U << FSNOTIFY_OBJ_TYPE_##NAME)) ? \ - iter_info->marks[FSNOTIFY_OBJ_TYPE_##NAME] : NULL; \ + return (iter_info->report_mask & (1U << FSNOTIFY_ITER_TYPE_##NAME)) ? \ + iter_info->marks[FSNOTIFY_ITER_TYPE_##NAME] : NULL; \ } FSNOTIFY_ITER_FUNCS(inode, INODE) @@ -391,8 +406,8 @@ FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) -#define fsnotify_foreach_obj_type(type) \ - for (type = 0; type < FSNOTIFY_OBJ_TYPE_COUNT; type++) +#define fsnotify_foreach_iter_type(type) \ + for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) /* * fsnotify_connp_t is what we embed in objects which connector can be attached -- cgit v1.2.3 From d61fd650e9d206a71fda789f02a1ced4b19944c4 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:29 +0200 Subject: fanotify: introduce group flag FAN_REPORT_TARGET_FID FAN_REPORT_FID is ambiguous in that it reports the fid of the child for some events and the fid of the parent for create/delete/move events. The new FAN_REPORT_TARGET_FID flag is an implicit request to report the fid of the target object of the operation (a.k.a the child inode) also in create/delete/move events in addition to the fid of the parent and the name of the child. To reduce the test matrix for uninteresting use cases, the new FAN_REPORT_TARGET_FID flag requires both FAN_REPORT_NAME and FAN_REPORT_FID. The convenience macro FAN_REPORT_DFID_NAME_TARGET combines FAN_REPORT_TARGET_FID with all the required flags. Link: https://lore.kernel.org/r/20211129201537.1932819-4-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 48 ++++++++++++++++++++++++++++---------- fs/notify/fanotify/fanotify_user.c | 11 ++++++++- include/linux/fanotify.h | 2 +- include/uapi/linux/fanotify.h | 4 ++++ 4 files changed, 51 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 652fe84cb8ac..85e542b164c8 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -458,17 +458,41 @@ out_err: } /* - * The inode to use as identifier when reporting fid depends on the event. - * Report the modified directory inode on dirent modification events. - * Report the "victim" inode otherwise. + * FAN_REPORT_FID is ambiguous in that it reports the fid of the child for + * some events and the fid of the parent for create/delete/move events. + * + * With the FAN_REPORT_TARGET_FID flag, the fid of the child is reported + * also in create/delete/move events in addition to the fid of the parent + * and the name of the child. + */ +static inline bool fanotify_report_child_fid(unsigned int fid_mode, u32 mask) +{ + if (mask & ALL_FSNOTIFY_DIRENT_EVENTS) + return (fid_mode & FAN_REPORT_TARGET_FID); + + return (fid_mode & FAN_REPORT_FID) && !(mask & FAN_ONDIR); +} + +/* + * The inode to use as identifier when reporting fid depends on the event + * and the group flags. + * + * With the group flag FAN_REPORT_TARGET_FID, always report the child fid. + * + * Without the group flag FAN_REPORT_TARGET_FID, report the modified directory + * fid on dirent events and the child fid otherwise. + * * For example: - * FS_ATTRIB reports the child inode even if reported on a watched parent. - * FS_CREATE reports the modified dir inode and not the created inode. + * FS_ATTRIB reports the child fid even if reported on a watched parent. + * FS_CREATE reports the modified dir fid without FAN_REPORT_TARGET_FID. + * and reports the created child fid with FAN_REPORT_TARGET_FID. */ static struct inode *fanotify_fid_inode(u32 event_mask, const void *data, - int data_type, struct inode *dir) + int data_type, struct inode *dir, + unsigned int fid_mode) { - if (event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) + if ((event_mask & ALL_FSNOTIFY_DIRENT_EVENTS) && + !(fid_mode & FAN_REPORT_TARGET_FID)) return dir; return fsnotify_data_inode(data, data_type); @@ -647,10 +671,11 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, { struct fanotify_event *event = NULL; gfp_t gfp = GFP_KERNEL_ACCOUNT; - struct inode *id = fanotify_fid_inode(mask, data, data_type, dir); + unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); + struct inode *id = fanotify_fid_inode(mask, data, data_type, dir, + fid_mode); struct inode *dirid = fanotify_dfid_inode(mask, data, data_type, dir); const struct path *path = fsnotify_data_path(data, data_type); - unsigned int fid_mode = FAN_GROUP_FLAG(group, FANOTIFY_FID_BITS); struct mem_cgroup *old_memcg; struct inode *child = NULL; bool name_event = false; @@ -660,11 +685,10 @@ static struct fanotify_event *fanotify_alloc_event(struct fsnotify_group *group, if ((fid_mode & FAN_REPORT_DIR_FID) && dirid) { /* - * With both flags FAN_REPORT_DIR_FID and FAN_REPORT_FID, we - * report the child fid for events reported on a non-dir child + * For certain events and group flags, report the child fid * in addition to reporting the parent fid and maybe child name. */ - if ((fid_mode & FAN_REPORT_FID) && id != dirid && !ondir) + if (fanotify_report_child_fid(fid_mode, mask) && id != dirid) child = id; id = dirid; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ab24c37f1fdf..00bbc29712bb 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1275,6 +1275,15 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags) if ((fid_mode & FAN_REPORT_NAME) && !(fid_mode & FAN_REPORT_DIR_FID)) return -EINVAL; + /* + * FAN_REPORT_TARGET_FID requires FAN_REPORT_NAME and FAN_REPORT_FID + * and is used as an indication to report both dir and child fid on all + * dirent events. + */ + if ((fid_mode & FAN_REPORT_TARGET_FID) && + (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID))) + return -EINVAL; + f_flags = O_RDWR | FMODE_NONOTIFY; if (flags & FAN_CLOEXEC) f_flags |= O_CLOEXEC; @@ -1667,7 +1676,7 @@ static int __init fanotify_user_setup(void) FANOTIFY_DEFAULT_MAX_USER_MARKS); BUILD_BUG_ON(FANOTIFY_INIT_FLAGS & FANOTIFY_INTERNAL_GROUP_FLAGS); - BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 11); + BUILD_BUG_ON(HWEIGHT32(FANOTIFY_INIT_FLAGS) != 12); BUILD_BUG_ON(HWEIGHT32(FANOTIFY_MARK_FLAGS) != 9); fanotify_mark_cache = KMEM_CACHE(fsnotify_mark, diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 616af2ea20f3..376e050e6f38 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -25,7 +25,7 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ #define FANOTIFY_CLASS_BITS (FAN_CLASS_NOTIF | FANOTIFY_PERM_CLASSES) -#define FANOTIFY_FID_BITS (FAN_REPORT_FID | FAN_REPORT_DFID_NAME) +#define FANOTIFY_FID_BITS (FAN_REPORT_DFID_NAME_TARGET) #define FANOTIFY_INFO_MODES (FANOTIFY_FID_BITS | FAN_REPORT_PIDFD) diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index bd1932c2074d..60f73639a896 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -57,9 +57,13 @@ #define FAN_REPORT_FID 0x00000200 /* Report unique file id */ #define FAN_REPORT_DIR_FID 0x00000400 /* Report unique directory id */ #define FAN_REPORT_NAME 0x00000800 /* Report events with name */ +#define FAN_REPORT_TARGET_FID 0x00001000 /* Report dirent target id */ /* Convenience macro - FAN_REPORT_NAME requires FAN_REPORT_DIR_FID */ #define FAN_REPORT_DFID_NAME (FAN_REPORT_DIR_FID | FAN_REPORT_NAME) +/* Convenience macro - FAN_REPORT_TARGET_FID requires all other FID flags */ +#define FAN_REPORT_DFID_NAME_TARGET (FAN_REPORT_DFID_NAME | \ + FAN_REPORT_FID | FAN_REPORT_TARGET_FID) /* Deprecated - do not use this in programs and do not add new flags here! */ #define FAN_ALL_INIT_FLAGS (FAN_CLOEXEC | FAN_NONBLOCK | \ -- cgit v1.2.3 From e54183fa7047c15819bc155f4c58501d9a9a3489 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:30 +0200 Subject: fsnotify: generate FS_RENAME event with rich information The dnotify FS_DN_RENAME event is used to request notification about a move within the same parent directory and was always coupled with the FS_MOVED_FROM event. Rename the FS_DN_RENAME event flag to FS_RENAME, decouple it from FS_MOVED_FROM and report it with the moved dentry instead of the moved inode, so it has the information about both old and new parent and name. Generate the FS_RENAME event regardless of same parent dir and apply the "same parent" rule in the generic fsnotify_handle_event() helper that is used to call backends with ->handle_inode_event() method (i.e. dnotify). The ->handle_inode_event() method is not rich enough to report both old and new parent and name anyway. The enriched event is reported to fanotify over the ->handle_event() method with the old and new dir inode marks in marks array slots for ITER_TYPE_INODE and a new iter type slot ITER_TYPE_INODE2. The enriched event will be used for reporting old and new parent+name to fanotify groups with FAN_RENAME events. Link: https://lore.kernel.org/r/20211129201537.1932819-5-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/dnotify/dnotify.c | 2 +- fs/notify/fsnotify.c | 37 +++++++++++++++++++++++++++++-------- include/linux/dnotify.h | 2 +- include/linux/fsnotify.h | 9 ++++++--- include/linux/fsnotify_backend.h | 7 ++++--- 5 files changed, 41 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index e85e13c50d6d..d5ebebb034ff 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -196,7 +196,7 @@ static __u32 convert_arg(unsigned long arg) if (arg & DN_ATTRIB) new_mask |= FS_ATTRIB; if (arg & DN_RENAME) - new_mask |= FS_DN_RENAME; + new_mask |= FS_RENAME; if (arg & DN_CREATE) new_mask |= (FS_CREATE | FS_MOVED_TO); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 0c94457c625e..ab81a0776ece 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -279,6 +279,18 @@ static int fsnotify_handle_event(struct fsnotify_group *group, __u32 mask, WARN_ON_ONCE(fsnotify_iter_vfsmount_mark(iter_info))) return 0; + /* + * For FS_RENAME, 'dir' is old dir and 'data' is new dentry. + * The only ->handle_inode_event() backend that supports FS_RENAME is + * dnotify, where it means file was renamed within same parent. + */ + if (mask & FS_RENAME) { + struct dentry *moved = fsnotify_data_dentry(data, data_type); + + if (dir != moved->d_parent->d_inode) + return 0; + } + if (parent_mark) { /* * parent_mark indicates that the parent inode is watching @@ -469,7 +481,9 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, struct super_block *sb = fsnotify_data_sb(data, data_type); struct fsnotify_iter_info iter_info = {}; struct mount *mnt = NULL; - struct inode *parent = NULL; + struct inode *inode2 = NULL; + struct dentry *moved; + int inode2_type; int ret = 0; __u32 test_mask, marks_mask; @@ -479,12 +493,19 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, if (!inode) { /* Dirent event - report on TYPE_INODE to dir */ inode = dir; + /* For FS_RENAME, inode is old_dir and inode2 is new_dir */ + if (mask & FS_RENAME) { + moved = fsnotify_data_dentry(data, data_type); + inode2 = moved->d_parent->d_inode; + inode2_type = FSNOTIFY_ITER_TYPE_INODE2; + } } else if (mask & FS_EVENT_ON_CHILD) { /* * Event on child - report on TYPE_PARENT to dir if it is * watching children and on TYPE_INODE to child. */ - parent = dir; + inode2 = dir; + inode2_type = FSNOTIFY_ITER_TYPE_PARENT; } /* @@ -497,7 +518,7 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, if (!sb->s_fsnotify_marks && (!mnt || !mnt->mnt_fsnotify_marks) && (!inode || !inode->i_fsnotify_marks) && - (!parent || !parent->i_fsnotify_marks)) + (!inode2 || !inode2->i_fsnotify_marks)) return 0; marks_mask = sb->s_fsnotify_mask; @@ -505,8 +526,8 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, marks_mask |= mnt->mnt_fsnotify_mask; if (inode) marks_mask |= inode->i_fsnotify_mask; - if (parent) - marks_mask |= parent->i_fsnotify_mask; + if (inode2) + marks_mask |= inode2->i_fsnotify_mask; /* @@ -529,9 +550,9 @@ int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, iter_info.marks[FSNOTIFY_ITER_TYPE_INODE] = fsnotify_first_mark(&inode->i_fsnotify_marks); } - if (parent) { - iter_info.marks[FSNOTIFY_ITER_TYPE_PARENT] = - fsnotify_first_mark(&parent->i_fsnotify_marks); + if (inode2) { + iter_info.marks[inode2_type] = + fsnotify_first_mark(&inode2->i_fsnotify_marks); } /* diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index 0aad774beaec..b87c3b85a166 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -26,7 +26,7 @@ struct dnotify_struct { FS_MODIFY | FS_MODIFY_CHILD |\ FS_ACCESS | FS_ACCESS_CHILD |\ FS_ATTRIB | FS_ATTRIB_CHILD |\ - FS_CREATE | FS_DN_RENAME |\ + FS_CREATE | FS_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) extern int dir_notify_enable; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 787545e87eeb..3a2d7dc3c607 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -144,16 +144,19 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir, u32 fs_cookie = fsnotify_get_cookie(); __u32 old_dir_mask = FS_MOVED_FROM; __u32 new_dir_mask = FS_MOVED_TO; + __u32 rename_mask = FS_RENAME; const struct qstr *new_name = &moved->d_name; - if (old_dir == new_dir) - old_dir_mask |= FS_DN_RENAME; - if (isdir) { old_dir_mask |= FS_ISDIR; new_dir_mask |= FS_ISDIR; + rename_mask |= FS_ISDIR; } + /* Event with information about both old and new parent+name */ + fsnotify_name(rename_mask, moved, FSNOTIFY_EVENT_DENTRY, + old_dir, old_name, 0); + fsnotify_name(old_dir_mask, source, FSNOTIFY_EVENT_INODE, old_dir, old_name, fs_cookie); fsnotify_name(new_dir_mask, source, FSNOTIFY_EVENT_INODE, diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 73739fee1710..790c31844db5 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -63,7 +63,7 @@ */ #define FS_EVENT_ON_CHILD 0x08000000 -#define FS_DN_RENAME 0x10000000 /* file renamed */ +#define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_IN_ONESHOT 0x80000000 /* only send event once */ @@ -76,7 +76,7 @@ * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ -#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE) +#define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) @@ -101,7 +101,7 @@ /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ - FS_DELETE_SELF | FS_MOVE_SELF | FS_DN_RENAME | \ + FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) @@ -349,6 +349,7 @@ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, + FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_COUNT }; -- cgit v1.2.3 From 8cc3b1ccd930fe6971e1527f0c4f1bdc8cb56026 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 29 Nov 2021 22:15:37 +0200 Subject: fanotify: wire up FAN_RENAME event FAN_RENAME is the successor of FAN_MOVED_FROM and FAN_MOVED_TO and can be used to get the old and new parent+name information in a single event. FAN_MOVED_FROM and FAN_MOVED_TO are still supported for backward compatibility, but it makes little sense to use them together with FAN_RENAME in the same group. FAN_RENAME uses special info type records to report the old and new parent+name, so reporting only old and new parent id is less useful and was not implemented. Therefore, FAN_REANAME requires a group with flag FAN_REPORT_NAME. Link: https://lore.kernel.org/r/20211129201537.1932819-12-amir73il@gmail.com Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 2 +- fs/notify/fanotify/fanotify_user.c | 8 ++++++++ include/linux/fanotify.h | 3 ++- 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 0da305b6f3e2..985e995d2a39 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -930,7 +930,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(FAN_RENAME != FS_RENAME); - BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 20); + BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 21); mask = fanotify_group_event_mask(group, iter_info, &match_mask, mask, data, data_type, dir); diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index eb2a0251b318..73a3e939c921 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1586,6 +1586,14 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, (!fid_mode || mark_type == FAN_MARK_MOUNT)) goto fput_and_out; + /* + * FAN_RENAME uses special info type records to report the old and + * new parent+name. Reporting only old and new parent id is less + * useful and was not implemented. + */ + if (mask & FAN_RENAME && !(fid_mode & FAN_REPORT_NAME)) + goto fput_and_out; + if (flags & FAN_MARK_FLUSH) { ret = 0; if (mark_type == FAN_MARK_MOUNT) diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 376e050e6f38..3afdf339d53c 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -82,7 +82,8 @@ extern struct ctl_table fanotify_table[]; /* for sysctl */ * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. */ -#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE) +#define FANOTIFY_DIRENT_EVENTS (FAN_MOVE | FAN_CREATE | FAN_DELETE | \ + FAN_RENAME) /* Events that can be reported with event->fd */ #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS) -- cgit v1.2.3 From f1d9268e061863ead77b07f5a6807d063e28a1c2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 14 Dec 2021 07:09:33 -0800 Subject: net: add net device refcount tracker to struct packet_type Most notable changes are in af_packet, tipc ones are trivial. Signed-off-by: Eric Dumazet Cc: Jon Maloy Cc: Ying Xue Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/packet/af_packet.c | 14 +++++++++++--- net/tipc/bearer.c | 4 ++-- 3 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c06e9dc1a317..a419718612c6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2533,6 +2533,7 @@ struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ + netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a1ffdb48cc47..71854a16afbb 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3109,7 +3109,7 @@ static int packet_release(struct socket *sock) packet_cached_dev_reset(po); if (po->prot_hook.dev) { - dev_put(po->prot_hook.dev); + dev_put_track(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -3217,18 +3217,25 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; + dev_put_track(dev_curr, &po->prot_hook.dev_tracker); + dev_curr = NULL; + if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { + if (dev) + netdev_tracker_alloc(dev, + &po->prot_hook.dev_tracker, + GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } - dev_put(dev_curr); + dev_put_track(dev_curr, &po->prot_hook.dev_tracker); if (proto == 0 || !need_rehook) goto out_unlock; @@ -4138,7 +4145,8 @@ static int packet_notifier(struct notifier_block *this, if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); - dev_put(po->prot_hook.dev); + dev_put_track(po->prot_hook.dev, + &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 60bc74b76adc..473a790f5894 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -787,7 +787,7 @@ int tipc_attach_loopback(struct net *net) if (!dev) return -ENODEV; - dev_hold(dev); + dev_hold_track(dev, &tn->loopback_pt.dev_tracker, GFP_KERNEL); tn->loopback_pt.dev = dev; tn->loopback_pt.type = htons(ETH_P_TIPC); tn->loopback_pt.func = tipc_loopback_rcv_pkt; @@ -800,7 +800,7 @@ void tipc_detach_loopback(struct net *net) struct tipc_net *tn = tipc_net(net); dev_remove_pack(&tn->loopback_pt); - dev_put(net->loopback_dev); + dev_put_track(net->loopback_dev, &tn->loopback_pt.dev_tracker); } /* Caller should hold rtnl_lock to protect the bearer */ -- cgit v1.2.3 From 685b1afd7911676691c4167f420e16a957f5a38e Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 9 Dec 2021 12:09:23 +0200 Subject: net/mlx5: Introduce log_max_current_uc_list_wr_supported bit Downstream patch will use this bit in order to know whether the device supports changing of max_uc_list. Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3636df90899a..d3899fc33fd7 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1621,7 +1621,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ext_stride_num_range[0x1]; u8 roce_rw_supported[0x1]; - u8 reserved_at_3a2[0x1]; + u8 log_max_current_uc_list_wr_supported[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; -- cgit v1.2.3 From ff5f87cb6a75dbf6d30668d2464e46249dd5c47f Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 3 Dec 2021 11:28:49 +0100 Subject: clk: Introduce clk-tps68470 driver The TPS68470 PMIC provides Clocks, GPIOs and Regulators. At present in the kernel the Regulators and Clocks are controlled by an OpRegion driver designed to work with power control methods defined in ACPI, but some platforms lack those methods, meaning drivers need to be able to consume the resources of these chips through the usual frameworks. This commit adds a driver for the clocks provided by the tps68470, and is designed to bind to the platform_device registered by the intel_skl_int3472 module. This is based on this out of tree driver written by Intel: https://github.com/intel/linux-intel-lts/blob/4.14/base/drivers/clk/clk-tps68470.c with various cleanups added. Reviewed-by: Andy Shevchenko Signed-off-by: Hans de Goede Link: https://lore.kernel.org/r/20211203102857.44539-7-hdegoede@redhat.com Signed-off-by: Stephen Boyd --- drivers/clk/Kconfig | 8 ++ drivers/clk/Makefile | 1 + drivers/clk/clk-tps68470.c | 261 +++++++++++++++++++++++++++++++++++++++++++ include/linux/mfd/tps68470.h | 11 ++ 4 files changed, 281 insertions(+) create mode 100644 drivers/clk/clk-tps68470.c (limited to 'include/linux') diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index c5b3dc97396a..4e9098d79249 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -169,6 +169,14 @@ config COMMON_CLK_CDCE706 help This driver supports TI CDCE706 programmable 3-PLL clock synthesizer. +config COMMON_CLK_TPS68470 + tristate "Clock Driver for TI TPS68470 PMIC" + depends on I2C + depends on INTEL_SKL_INT3472 || COMPILE_TEST + select REGMAP_I2C + help + This driver supports the clocks provided by the TPS68470 PMIC. + config COMMON_CLK_CDCE925 tristate "Clock driver for TI CDCE913/925/937/949 devices" depends on I2C diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index e42312121e51..6b6a88ae1425 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -63,6 +63,7 @@ obj-$(CONFIG_COMMON_CLK_SI570) += clk-si570.o obj-$(CONFIG_COMMON_CLK_STM32F) += clk-stm32f4.o obj-$(CONFIG_COMMON_CLK_STM32H7) += clk-stm32h7.o obj-$(CONFIG_COMMON_CLK_STM32MP157) += clk-stm32mp1.o +obj-$(CONFIG_COMMON_CLK_TPS68470) += clk-tps68470.o obj-$(CONFIG_CLK_TWL6040) += clk-twl6040.o obj-$(CONFIG_ARCH_VT8500) += clk-vt8500.o obj-$(CONFIG_COMMON_CLK_VC5) += clk-versaclock5.o diff --git a/drivers/clk/clk-tps68470.c b/drivers/clk/clk-tps68470.c new file mode 100644 index 000000000000..e5fbefd6ac2d --- /dev/null +++ b/drivers/clk/clk-tps68470.c @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clock driver for TPS68470 PMIC + * + * Copyright (c) 2021 Red Hat Inc. + * Copyright (C) 2018 Intel Corporation + * + * Authors: + * Hans de Goede + * Zaikuo Wang + * Tianshu Qiu + * Jian Xu Zheng + * Yuning Pu + * Antti Laakso + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define TPS68470_CLK_NAME "tps68470-clk" + +#define to_tps68470_clkdata(clkd) \ + container_of(clkd, struct tps68470_clkdata, clkout_hw) + +static struct tps68470_clkout_freqs { + unsigned long freq; + unsigned int xtaldiv; + unsigned int plldiv; + unsigned int postdiv; + unsigned int buckdiv; + unsigned int boostdiv; +} clk_freqs[] = { +/* + * The PLL is used to multiply the crystal oscillator + * frequency range of 3 MHz to 27 MHz by a programmable + * factor of F = (M/N)*(1/P) such that the output + * available at the HCLK_A or HCLK_B pins are in the range + * of 4 MHz to 64 MHz in increments of 0.1 MHz. + * + * hclk_# = osc_in * (((plldiv*2)+320) / (xtaldiv+30)) * (1 / 2^postdiv) + * + * PLL_REF_CLK should be as close as possible to 100kHz + * PLL_REF_CLK = input clk / XTALDIV[7:0] + 30) + * + * PLL_VCO_CLK = (PLL_REF_CLK * (plldiv*2 + 320)) + * + * BOOST should be as close as possible to 2Mhz + * BOOST = PLL_VCO_CLK / (BOOSTDIV[4:0] + 16) * + * + * BUCK should be as close as possible to 5.2Mhz + * BUCK = PLL_VCO_CLK / (BUCKDIV[3:0] + 5) + * + * osc_in xtaldiv plldiv postdiv hclk_# + * 20Mhz 170 32 1 19.2Mhz + * 20Mhz 170 40 1 20Mhz + * 20Mhz 170 80 1 24Mhz + */ + { 19200000, 170, 32, 1, 2, 3 }, + { 20000000, 170, 40, 1, 3, 4 }, + { 24000000, 170, 80, 1, 4, 8 }, +}; + +struct tps68470_clkdata { + struct clk_hw clkout_hw; + struct regmap *regmap; + unsigned long rate; +}; + +static int tps68470_clk_is_prepared(struct clk_hw *hw) +{ + struct tps68470_clkdata *clkdata = to_tps68470_clkdata(hw); + int val; + + if (regmap_read(clkdata->regmap, TPS68470_REG_PLLCTL, &val)) + return 0; + + return val & TPS68470_PLL_EN_MASK; +} + +static int tps68470_clk_prepare(struct clk_hw *hw) +{ + struct tps68470_clkdata *clkdata = to_tps68470_clkdata(hw); + + regmap_write(clkdata->regmap, TPS68470_REG_CLKCFG1, + (TPS68470_PLL_OUTPUT_ENABLE << TPS68470_OUTPUT_A_SHIFT) | + (TPS68470_PLL_OUTPUT_ENABLE << TPS68470_OUTPUT_B_SHIFT)); + + regmap_update_bits(clkdata->regmap, TPS68470_REG_PLLCTL, + TPS68470_PLL_EN_MASK, TPS68470_PLL_EN_MASK); + + /* + * The PLLCTL reg lock bit is set by the PMIC after approx. 4ms and + * does not indicate a true lock, so just wait 4 ms. + */ + usleep_range(4000, 5000); + + return 0; +} + +static void tps68470_clk_unprepare(struct clk_hw *hw) +{ + struct tps68470_clkdata *clkdata = to_tps68470_clkdata(hw); + + /* Disable clock first ... */ + regmap_update_bits(clkdata->regmap, TPS68470_REG_PLLCTL, TPS68470_PLL_EN_MASK, 0); + + /* ... and then tri-state the clock outputs. */ + regmap_write(clkdata->regmap, TPS68470_REG_CLKCFG1, 0); +} + +static unsigned long tps68470_clk_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) +{ + struct tps68470_clkdata *clkdata = to_tps68470_clkdata(hw); + + return clkdata->rate; +} + +/* + * This returns the index of the clk_freqs[] cfg with the closest rate for + * use in tps68470_clk_round_rate(). tps68470_clk_set_rate() checks that + * the rate of the returned cfg is an exact match. + */ +static unsigned int tps68470_clk_cfg_lookup(unsigned long rate) +{ + long diff, best_diff = LONG_MAX; + unsigned int i, best_idx = 0; + + for (i = 0; i < ARRAY_SIZE(clk_freqs); i++) { + diff = clk_freqs[i].freq - rate; + if (diff == 0) + return i; + + diff = abs(diff); + if (diff < best_diff) { + best_diff = diff; + best_idx = i; + } + } + + return best_idx; +} + +static long tps68470_clk_round_rate(struct clk_hw *hw, unsigned long rate, + unsigned long *parent_rate) +{ + unsigned int idx = tps68470_clk_cfg_lookup(rate); + + return clk_freqs[idx].freq; +} + +static int tps68470_clk_set_rate(struct clk_hw *hw, unsigned long rate, + unsigned long parent_rate) +{ + struct tps68470_clkdata *clkdata = to_tps68470_clkdata(hw); + unsigned int idx = tps68470_clk_cfg_lookup(rate); + + if (rate != clk_freqs[idx].freq) + return -EINVAL; + + regmap_write(clkdata->regmap, TPS68470_REG_BOOSTDIV, clk_freqs[idx].boostdiv); + regmap_write(clkdata->regmap, TPS68470_REG_BUCKDIV, clk_freqs[idx].buckdiv); + regmap_write(clkdata->regmap, TPS68470_REG_PLLSWR, TPS68470_PLLSWR_DEFAULT); + regmap_write(clkdata->regmap, TPS68470_REG_XTALDIV, clk_freqs[idx].xtaldiv); + regmap_write(clkdata->regmap, TPS68470_REG_PLLDIV, clk_freqs[idx].plldiv); + regmap_write(clkdata->regmap, TPS68470_REG_POSTDIV, clk_freqs[idx].postdiv); + regmap_write(clkdata->regmap, TPS68470_REG_POSTDIV2, clk_freqs[idx].postdiv); + regmap_write(clkdata->regmap, TPS68470_REG_CLKCFG2, TPS68470_CLKCFG2_DRV_STR_2MA); + + regmap_write(clkdata->regmap, TPS68470_REG_PLLCTL, + TPS68470_OSC_EXT_CAP_DEFAULT << TPS68470_OSC_EXT_CAP_SHIFT | + TPS68470_CLK_SRC_XTAL << TPS68470_CLK_SRC_SHIFT); + + clkdata->rate = rate; + + return 0; +} + +static const struct clk_ops tps68470_clk_ops = { + .is_prepared = tps68470_clk_is_prepared, + .prepare = tps68470_clk_prepare, + .unprepare = tps68470_clk_unprepare, + .recalc_rate = tps68470_clk_recalc_rate, + .round_rate = tps68470_clk_round_rate, + .set_rate = tps68470_clk_set_rate, +}; + +static int tps68470_clk_probe(struct platform_device *pdev) +{ + struct tps68470_clk_platform_data *pdata = pdev->dev.platform_data; + struct clk_init_data tps68470_clk_initdata = { + .name = TPS68470_CLK_NAME, + .ops = &tps68470_clk_ops, + /* Changing the dividers when the PLL is on is not allowed */ + .flags = CLK_SET_RATE_GATE, + }; + struct tps68470_clkdata *tps68470_clkdata; + int ret; + + tps68470_clkdata = devm_kzalloc(&pdev->dev, sizeof(*tps68470_clkdata), + GFP_KERNEL); + if (!tps68470_clkdata) + return -ENOMEM; + + tps68470_clkdata->regmap = dev_get_drvdata(pdev->dev.parent); + tps68470_clkdata->clkout_hw.init = &tps68470_clk_initdata; + + /* Set initial rate */ + tps68470_clk_set_rate(&tps68470_clkdata->clkout_hw, clk_freqs[0].freq, 0); + + ret = devm_clk_hw_register(&pdev->dev, &tps68470_clkdata->clkout_hw); + if (ret) + return ret; + + ret = devm_clk_hw_register_clkdev(&pdev->dev, &tps68470_clkdata->clkout_hw, + TPS68470_CLK_NAME, NULL); + if (ret) + return ret; + + if (pdata) { + ret = devm_clk_hw_register_clkdev(&pdev->dev, + &tps68470_clkdata->clkout_hw, + pdata->consumer_con_id, + pdata->consumer_dev_name); + } + + return ret; +} + +static struct platform_driver tps68470_clk_driver = { + .driver = { + .name = TPS68470_CLK_NAME, + }, + .probe = tps68470_clk_probe, +}; + +/* + * The ACPI tps68470 probe-ordering depends on the clk/gpio/regulator drivers + * registering before the drivers for the camera-sensors which use them bind. + * subsys_initcall() ensures this when the drivers are builtin. + */ +static int __init tps68470_clk_init(void) +{ + return platform_driver_register(&tps68470_clk_driver); +} +subsys_initcall(tps68470_clk_init); + +static void __exit tps68470_clk_exit(void) +{ + platform_driver_unregister(&tps68470_clk_driver); +} +module_exit(tps68470_clk_exit); + +MODULE_ALIAS("platform:tps68470-clk"); +MODULE_DESCRIPTION("clock driver for TPS68470 pmic"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/mfd/tps68470.h b/include/linux/mfd/tps68470.h index ffe81127d91c..7807fa329db0 100644 --- a/include/linux/mfd/tps68470.h +++ b/include/linux/mfd/tps68470.h @@ -75,6 +75,17 @@ #define TPS68470_CLKCFG1_MODE_A_MASK GENMASK(1, 0) #define TPS68470_CLKCFG1_MODE_B_MASK GENMASK(3, 2) +#define TPS68470_CLKCFG2_DRV_STR_2MA 0x05 +#define TPS68470_PLL_OUTPUT_ENABLE 0x02 +#define TPS68470_CLK_SRC_XTAL BIT(0) +#define TPS68470_PLLSWR_DEFAULT GENMASK(1, 0) +#define TPS68470_OSC_EXT_CAP_DEFAULT 0x05 + +#define TPS68470_OUTPUT_A_SHIFT 0x00 +#define TPS68470_OUTPUT_B_SHIFT 0x02 +#define TPS68470_CLK_SRC_SHIFT GENMASK(2, 0) +#define TPS68470_OSC_EXT_CAP_SHIFT BIT(2) + #define TPS68470_GPIO_CTL_REG_A(x) (TPS68470_REG_GPCTL0A + (x) * 2) #define TPS68470_GPIO_CTL_REG_B(x) (TPS68470_REG_GPCTL0B + (x) * 2) #define TPS68470_GPIO_MODE_MASK GENMASK(1, 0) -- cgit v1.2.3 From dfd0743f1d9ea76931510ed150334d571fbab49d Mon Sep 17 00:00:00 2001 From: Jens Wiklander Date: Thu, 9 Dec 2021 15:59:37 +0100 Subject: tee: handle lookup of shm with reference count 0 Since the tee subsystem does not keep a strong reference to its idle shared memory buffers, it races with other threads that try to destroy a shared memory through a close of its dma-buf fd or by unmapping the memory. In tee_shm_get_from_id() when a lookup in teedev->idr has been successful, it is possible that the tee_shm is in the dma-buf teardown path, but that path is blocked by the teedev mutex. Since we don't have an API to tell if the tee_shm is in the dma-buf teardown path or not we must find another way of detecting this condition. Fix this by doing the reference counting directly on the tee_shm using a new refcount_t refcount field. dma-buf is replaced by using anon_inode_getfd() instead, this separates the life-cycle of the underlying file from the tee_shm. tee_shm_put() is updated to hold the mutex when decreasing the refcount to 0 and then remove the tee_shm from teedev->idr before releasing the mutex. This means that the tee_shm can never be found unless it has a refcount larger than 0. Fixes: 967c9cca2cc5 ("tee: generic TEE subsystem") Cc: stable@vger.kernel.org Reviewed-by: Greg Kroah-Hartman Reviewed-by: Lars Persson Reviewed-by: Sumit Garg Reported-by: Patrik Lantz Signed-off-by: Jens Wiklander --- drivers/tee/tee_shm.c | 174 ++++++++++++++++++------------------------------ include/linux/tee_drv.h | 4 +- 2 files changed, 68 insertions(+), 110 deletions(-) (limited to 'include/linux') diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index 8a8deb95e918..499fccba3d74 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -1,20 +1,17 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2015-2016, Linaro Limited + * Copyright (c) 2015-2017, 2019-2021 Linaro Limited */ +#include #include -#include -#include #include +#include #include #include #include #include -#include #include "tee_private.h" -MODULE_IMPORT_NS(DMA_BUF); - static void release_registered_pages(struct tee_shm *shm) { if (shm->pages) { @@ -31,16 +28,8 @@ static void release_registered_pages(struct tee_shm *shm) } } -static void tee_shm_release(struct tee_shm *shm) +static void tee_shm_release(struct tee_device *teedev, struct tee_shm *shm) { - struct tee_device *teedev = shm->ctx->teedev; - - if (shm->flags & TEE_SHM_DMA_BUF) { - mutex_lock(&teedev->mutex); - idr_remove(&teedev->idr, shm->id); - mutex_unlock(&teedev->mutex); - } - if (shm->flags & TEE_SHM_POOL) { struct tee_shm_pool_mgr *poolm; @@ -67,45 +56,6 @@ static void tee_shm_release(struct tee_shm *shm) tee_device_put(teedev); } -static struct sg_table *tee_shm_op_map_dma_buf(struct dma_buf_attachment - *attach, enum dma_data_direction dir) -{ - return NULL; -} - -static void tee_shm_op_unmap_dma_buf(struct dma_buf_attachment *attach, - struct sg_table *table, - enum dma_data_direction dir) -{ -} - -static void tee_shm_op_release(struct dma_buf *dmabuf) -{ - struct tee_shm *shm = dmabuf->priv; - - tee_shm_release(shm); -} - -static int tee_shm_op_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma) -{ - struct tee_shm *shm = dmabuf->priv; - size_t size = vma->vm_end - vma->vm_start; - - /* Refuse sharing shared memory provided by application */ - if (shm->flags & TEE_SHM_USER_MAPPED) - return -EINVAL; - - return remap_pfn_range(vma, vma->vm_start, shm->paddr >> PAGE_SHIFT, - size, vma->vm_page_prot); -} - -static const struct dma_buf_ops tee_shm_dma_buf_ops = { - .map_dma_buf = tee_shm_op_map_dma_buf, - .unmap_dma_buf = tee_shm_op_unmap_dma_buf, - .release = tee_shm_op_release, - .mmap = tee_shm_op_mmap, -}; - struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags) { struct tee_device *teedev = ctx->teedev; @@ -140,6 +90,7 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags) goto err_dev_put; } + refcount_set(&shm->refcount, 1); shm->flags = flags | TEE_SHM_POOL; shm->ctx = ctx; if (flags & TEE_SHM_DMA_BUF) @@ -153,10 +104,7 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags) goto err_kfree; } - if (flags & TEE_SHM_DMA_BUF) { - DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - mutex_lock(&teedev->mutex); shm->id = idr_alloc(&teedev->idr, shm, 1, 0, GFP_KERNEL); mutex_unlock(&teedev->mutex); @@ -164,28 +112,11 @@ struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags) ret = ERR_PTR(shm->id); goto err_pool_free; } - - exp_info.ops = &tee_shm_dma_buf_ops; - exp_info.size = shm->size; - exp_info.flags = O_RDWR; - exp_info.priv = shm; - - shm->dmabuf = dma_buf_export(&exp_info); - if (IS_ERR(shm->dmabuf)) { - ret = ERR_CAST(shm->dmabuf); - goto err_rem; - } } teedev_ctx_get(ctx); return shm; -err_rem: - if (flags & TEE_SHM_DMA_BUF) { - mutex_lock(&teedev->mutex); - idr_remove(&teedev->idr, shm->id); - mutex_unlock(&teedev->mutex); - } err_pool_free: poolm->ops->free(poolm, shm); err_kfree: @@ -246,6 +177,7 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, goto err; } + refcount_set(&shm->refcount, 1); shm->flags = flags | TEE_SHM_REGISTER; shm->ctx = ctx; shm->id = -1; @@ -306,22 +238,6 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr, goto err; } - if (flags & TEE_SHM_DMA_BUF) { - DEFINE_DMA_BUF_EXPORT_INFO(exp_info); - - exp_info.ops = &tee_shm_dma_buf_ops; - exp_info.size = shm->size; - exp_info.flags = O_RDWR; - exp_info.priv = shm; - - shm->dmabuf = dma_buf_export(&exp_info); - if (IS_ERR(shm->dmabuf)) { - ret = ERR_CAST(shm->dmabuf); - teedev->desc->ops->shm_unregister(ctx, shm); - goto err; - } - } - return shm; err: if (shm) { @@ -339,6 +255,35 @@ err: } EXPORT_SYMBOL_GPL(tee_shm_register); +static int tee_shm_fop_release(struct inode *inode, struct file *filp) +{ + tee_shm_put(filp->private_data); + return 0; +} + +static int tee_shm_fop_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct tee_shm *shm = filp->private_data; + size_t size = vma->vm_end - vma->vm_start; + + /* Refuse sharing shared memory provided by application */ + if (shm->flags & TEE_SHM_USER_MAPPED) + return -EINVAL; + + /* check for overflowing the buffer's size */ + if (vma->vm_pgoff + vma_pages(vma) > shm->size >> PAGE_SHIFT) + return -EINVAL; + + return remap_pfn_range(vma, vma->vm_start, shm->paddr >> PAGE_SHIFT, + size, vma->vm_page_prot); +} + +static const struct file_operations tee_shm_fops = { + .owner = THIS_MODULE, + .release = tee_shm_fop_release, + .mmap = tee_shm_fop_mmap, +}; + /** * tee_shm_get_fd() - Increase reference count and return file descriptor * @shm: Shared memory handle @@ -351,10 +296,11 @@ int tee_shm_get_fd(struct tee_shm *shm) if (!(shm->flags & TEE_SHM_DMA_BUF)) return -EINVAL; - get_dma_buf(shm->dmabuf); - fd = dma_buf_fd(shm->dmabuf, O_CLOEXEC); + /* matched by tee_shm_put() in tee_shm_op_release() */ + refcount_inc(&shm->refcount); + fd = anon_inode_getfd("tee_shm", &tee_shm_fops, shm, O_RDWR); if (fd < 0) - dma_buf_put(shm->dmabuf); + tee_shm_put(shm); return fd; } @@ -364,17 +310,7 @@ int tee_shm_get_fd(struct tee_shm *shm) */ void tee_shm_free(struct tee_shm *shm) { - /* - * dma_buf_put() decreases the dmabuf reference counter and will - * call tee_shm_release() when the last reference is gone. - * - * In the case of driver private memory we call tee_shm_release - * directly instead as it doesn't have a reference counter. - */ - if (shm->flags & TEE_SHM_DMA_BUF) - dma_buf_put(shm->dmabuf); - else - tee_shm_release(shm); + tee_shm_put(shm); } EXPORT_SYMBOL_GPL(tee_shm_free); @@ -481,10 +417,15 @@ struct tee_shm *tee_shm_get_from_id(struct tee_context *ctx, int id) teedev = ctx->teedev; mutex_lock(&teedev->mutex); shm = idr_find(&teedev->idr, id); + /* + * If the tee_shm was found in the IDR it must have a refcount + * larger than 0 due to the guarantee in tee_shm_put() below. So + * it's safe to use refcount_inc(). + */ if (!shm || shm->ctx != ctx) shm = ERR_PTR(-EINVAL); - else if (shm->flags & TEE_SHM_DMA_BUF) - get_dma_buf(shm->dmabuf); + else + refcount_inc(&shm->refcount); mutex_unlock(&teedev->mutex); return shm; } @@ -496,7 +437,24 @@ EXPORT_SYMBOL_GPL(tee_shm_get_from_id); */ void tee_shm_put(struct tee_shm *shm) { - if (shm->flags & TEE_SHM_DMA_BUF) - dma_buf_put(shm->dmabuf); + struct tee_device *teedev = shm->ctx->teedev; + bool do_release = false; + + mutex_lock(&teedev->mutex); + if (refcount_dec_and_test(&shm->refcount)) { + /* + * refcount has reached 0, we must now remove it from the + * IDR before releasing the mutex. This will guarantee that + * the refcount_inc() in tee_shm_get_from_id() never starts + * from 0. + */ + if (shm->flags & TEE_SHM_DMA_BUF) + idr_remove(&teedev->idr, shm->id); + do_release = true; + } + mutex_unlock(&teedev->mutex); + + if (do_release) + tee_shm_release(teedev, shm); } EXPORT_SYMBOL_GPL(tee_shm_put); diff --git a/include/linux/tee_drv.h b/include/linux/tee_drv.h index a1f03461369b..cf5999626e28 100644 --- a/include/linux/tee_drv.h +++ b/include/linux/tee_drv.h @@ -195,7 +195,7 @@ int tee_session_calc_client_uuid(uuid_t *uuid, u32 connection_method, * @offset: offset of buffer in user space * @pages: locked pages from userspace * @num_pages: number of locked pages - * @dmabuf: dmabuf used to for exporting to user space + * @refcount: reference counter * @flags: defined by TEE_SHM_* in tee_drv.h * @id: unique id of a shared memory object on this device, shared * with user space @@ -214,7 +214,7 @@ struct tee_shm { unsigned int offset; struct page **pages; size_t num_pages; - struct dma_buf *dmabuf; + refcount_t refcount; u32 flags; int id; u64 sec_world_id; -- cgit v1.2.3 From d1e86325af377129adb7fc6f34eb044ca6068b47 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 15 Dec 2021 15:34:15 +0000 Subject: net: phylink: add mac_select_pcs() method to phylink_mac_ops mac_select_pcs() allows us to have an explicit point to query which PCS the MAC wishes to use for a particular PHY interface mode, thereby allowing us to add support to validate the link settings with the PCS. Phylink will also use this to select the PCS to be used during a major configuration event without the MAC driver needing to call phylink_set_pcs(). Note that if mac_select_pcs() is present, the supported_interfaces bitmap must be filled in; this avoids mac_select_pcs() being called with PHY_INTERFACE_MODE_NA when we want to get support for all interface types. Phylink will return an error in phylink_create() unless this condition is satisfied. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 68 ++++++++++++++++++++++++++++++++++++++++------- include/linux/phylink.h | 18 +++++++++++++ 2 files changed, 77 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 20df8af3e201..c7035d65e159 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -419,6 +419,23 @@ void phylink_generic_validate(struct phylink_config *config, } EXPORT_SYMBOL_GPL(phylink_generic_validate); +static int phylink_validate_mac_and_pcs(struct phylink *pl, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct phylink_pcs *pcs; + + if (pl->mac_ops->mac_select_pcs) { + pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); + if (IS_ERR(pcs)) + return PTR_ERR(pcs); + } + + pl->mac_ops->validate(pl->config, supported, state); + + return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; +} + static int phylink_validate_any(struct phylink *pl, unsigned long *supported, struct phylink_link_state *state) { @@ -434,9 +451,10 @@ static int phylink_validate_any(struct phylink *pl, unsigned long *supported, t = *state; t.interface = intf; - pl->mac_ops->validate(pl->config, s, &t); - linkmode_or(all_s, all_s, s); - linkmode_or(all_adv, all_adv, t.advertising); + if (!phylink_validate_mac_and_pcs(pl, s, &t)) { + linkmode_or(all_s, all_s, s); + linkmode_or(all_adv, all_adv, t.advertising); + } } } @@ -458,9 +476,7 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported, return -EINVAL; } - pl->mac_ops->validate(pl->config, supported, state); - - return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; + return phylink_validate_mac_and_pcs(pl, supported, state); } static int phylink_parse_fixedlink(struct phylink *pl, @@ -750,10 +766,21 @@ static void phylink_mac_pcs_an_restart(struct phylink *pl) static void phylink_major_config(struct phylink *pl, bool restart, const struct phylink_link_state *state) { + struct phylink_pcs *pcs = NULL; int err; phylink_dbg(pl, "major config %s\n", phy_modes(state->interface)); + if (pl->mac_ops->mac_select_pcs) { + pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); + if (IS_ERR(pcs)) { + phylink_err(pl, + "mac_select_pcs unexpectedly failed: %pe\n", + pcs); + return; + } + } + if (pl->mac_ops->mac_prepare) { err = pl->mac_ops->mac_prepare(pl->config, pl->cur_link_an_mode, state->interface); @@ -764,6 +791,12 @@ static void phylink_major_config(struct phylink *pl, bool restart, } } + /* If we have a new PCS, switch to the new PCS after preparing the MAC + * for the change. + */ + if (pcs) + phylink_set_pcs(pl, pcs); + phylink_mac_config(pl, state); if (pl->pcs_ops) { @@ -1155,6 +1188,14 @@ struct phylink *phylink_create(struct phylink_config *config, struct phylink *pl; int ret; + /* Validate the supplied configuration */ + if (mac_ops->mac_select_pcs && + phy_interface_empty(config->supported_interfaces)) { + dev_err(config->dev, + "phylink: error: empty supported_interfaces but mac_select_pcs() method present\n"); + return ERR_PTR(-EINVAL); + } + pl = kzalloc(sizeof(*pl), GFP_KERNEL); if (!pl) return ERR_PTR(-ENOMEM); @@ -1222,9 +1263,10 @@ EXPORT_SYMBOL_GPL(phylink_create); * @pl: a pointer to a &struct phylink returned from phylink_create() * @pcs: a pointer to the &struct phylink_pcs * - * Bind the MAC PCS to phylink. This may be called after phylink_create(), - * in mac_prepare() or mac_config() methods if it is desired to dynamically - * change the PCS. + * Bind the MAC PCS to phylink. This may be called after phylink_create(). + * If it is desired to dynamically change the PCS, then the preferred method + * is to use mac_select_pcs(), but it may also be called in mac_prepare() + * or mac_config(). * * Please note that there are behavioural changes with the mac_config() * callback if a PCS is present (denoting a newer setup) so removing a PCS @@ -1235,6 +1277,14 @@ void phylink_set_pcs(struct phylink *pl, struct phylink_pcs *pcs) { pl->pcs = pcs; pl->pcs_ops = pcs->ops; + + if (!pl->phylink_disable_state && + pl->cfg_link_an_mode == MLO_AN_INBAND) { + if (pl->config->pcs_poll || pcs->poll) + mod_timer(&pl->link_poll, jiffies + HZ); + else + del_timer(&pl->link_poll); + } } EXPORT_SYMBOL_GPL(phylink_set_pcs); diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a2f266cc3442..b3086dcafeaf 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -112,6 +112,7 @@ struct phylink_config { /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. + * @mac_select_pcs: Select a PCS for the interface mode. * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. @@ -126,6 +127,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); + struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, + phy_interface_t interface); void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, @@ -178,6 +181,21 @@ struct phylink_mac_ops { */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); +/** + * mac_select_pcs: Select a PCS for the interface mode. + * @config: a pointer to a &struct phylink_config. + * @interface: PHY interface mode for PCS + * + * Return the &struct phylink_pcs for the specified interface mode, or + * NULL if none is required, or an error pointer on error. + * + * This must not modify any state. It is used to query which PCS should + * be used. Phylink will use this during validation to ensure that the + * configuration is valid, and when setting a configuration to internally + * set the PCS that will be used. + */ +struct phylink_pcs *mac_select_pcs(struct phylink_config *config, + phy_interface_t interface); /** * mac_pcs_get_state() - Read the current inband link state from the hardware -- cgit v1.2.3 From 0d22d4b626a4eaa3196019092eb6c1919e9f8caa Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Wed, 15 Dec 2021 15:34:20 +0000 Subject: net: phylink: add pcs_validate() method Add a hook for PCS to validate the link parameters. This avoids MAC drivers having to have knowledge of their PCS in their validate() method, thereby allowing several MAC drivers to be simplfied. Signed-off-by: Russell King (Oracle) Signed-off-by: David S. Miller --- drivers/net/phy/phylink.c | 31 +++++++++++++++++++++++++++++++ include/linux/phylink.h | 20 ++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index c7035d65e159..420201858564 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -424,13 +424,44 @@ static int phylink_validate_mac_and_pcs(struct phylink *pl, struct phylink_link_state *state) { struct phylink_pcs *pcs; + int ret; + /* Get the PCS for this interface mode */ if (pl->mac_ops->mac_select_pcs) { pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); if (IS_ERR(pcs)) return PTR_ERR(pcs); + } else { + pcs = pl->pcs; + } + + if (pcs) { + /* The PCS, if present, must be setup before phylink_create() + * has been called. If the ops is not initialised, print an + * error and backtrace rather than oopsing the kernel. + */ + if (!pcs->ops) { + phylink_err(pl, "interface %s: uninitialised PCS\n", + phy_modes(state->interface)); + dump_stack(); + return -EINVAL; + } + + /* Validate the link parameters with the PCS */ + if (pcs->ops->pcs_validate) { + ret = pcs->ops->pcs_validate(pcs, supported, state); + if (ret < 0 || phylink_is_empty_linkmode(supported)) + return -EINVAL; + + /* Ensure the advertising mask is a subset of the + * supported mask. + */ + linkmode_and(state->advertising, state->advertising, + supported); + } } + /* Then validate the link parameters with the MAC */ pl->mac_ops->validate(pl->config, supported, state); return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; diff --git a/include/linux/phylink.h b/include/linux/phylink.h index b3086dcafeaf..713a0c928b7c 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -416,6 +416,7 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. + * @pcs_validate: validate the link configuration. * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -423,6 +424,8 @@ struct phylink_pcs { * (where necessary). */ struct phylink_pcs_ops { + int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode, @@ -435,6 +438,23 @@ struct phylink_pcs_ops { }; #if 0 /* For kernel-doc purposes only. */ +/** + * pcs_validate() - validate the link configuration. + * @pcs: a pointer to a &struct phylink_pcs. + * @supported: ethtool bitmask for supported link modes. + * @state: a const pointer to a &struct phylink_link_state. + * + * Validate the interface mode, and advertising's autoneg bit, removing any + * media ethtool link modes that would not be supportable from the supported + * mask. Phylink will propagate the changes to the advertising mask. See the + * &struct phylink_mac_ops validate() method. + * + * Returns -EINVAL if the interface mode/autoneg mode is not supported. + * Returns non-zero positive if the link state can be supported. + */ +int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); + /** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. -- cgit v1.2.3 From c6aeaf56f468a565f6d2f27325fc07d35cdcd3cb Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 9 Sep 2021 15:51:24 +0200 Subject: drm/tegra: Implement correct DMA-BUF semantics DMA-BUF requires that each device that accesses a DMA-BUF attaches to it separately. To do so the host1x_bo_pin() and host1x_bo_unpin() functions need to be reimplemented so that they can return a mapping, which either represents an attachment or a map of the driver's own GEM object. Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/gem.c | 163 ++++++++++++++++++++++++++--------------- drivers/gpu/drm/tegra/plane.c | 60 ++++----------- drivers/gpu/drm/tegra/plane.h | 2 +- drivers/gpu/drm/tegra/submit.c | 62 +++++++++++----- drivers/gpu/drm/tegra/uapi.c | 68 +++++++---------- drivers/gpu/drm/tegra/uapi.h | 5 +- drivers/gpu/host1x/job.c | 160 ++++++++++++++-------------------------- drivers/gpu/host1x/job.h | 6 +- include/linux/host1x.h | 30 +++++--- 9 files changed, 268 insertions(+), 288 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index d38fd7e12b57..f00938d8bc88 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -23,86 +23,96 @@ MODULE_IMPORT_NS(DMA_BUF); -static void tegra_bo_put(struct host1x_bo *bo) +static unsigned int sg_dma_count_chunks(struct scatterlist *sgl, unsigned int nents) { - struct tegra_bo *obj = host1x_to_tegra_bo(bo); + dma_addr_t next = ~(dma_addr_t)0; + unsigned int count = 0, i; + struct scatterlist *s; - drm_gem_object_put(&obj->gem); -} + for_each_sg(sgl, s, nents, i) { + /* sg_dma_address(s) is only valid for entries that have sg_dma_len(s) != 0. */ + if (!sg_dma_len(s)) + continue; -/* XXX move this into lib/scatterlist.c? */ -static int sg_alloc_table_from_sg(struct sg_table *sgt, struct scatterlist *sg, - unsigned int nents, gfp_t gfp_mask) -{ - struct scatterlist *dst; - unsigned int i; - int err; + if (sg_dma_address(s) != next) { + next = sg_dma_address(s) + sg_dma_len(s); + count++; + } + } - err = sg_alloc_table(sgt, nents, gfp_mask); - if (err < 0) - return err; + return count; +} - dst = sgt->sgl; +static inline unsigned int sgt_dma_count_chunks(struct sg_table *sgt) +{ + return sg_dma_count_chunks(sgt->sgl, sgt->nents); +} - for (i = 0; i < nents; i++) { - sg_set_page(dst, sg_page(sg), sg->length, 0); - dst = sg_next(dst); - sg = sg_next(sg); - } +static void tegra_bo_put(struct host1x_bo *bo) +{ + struct tegra_bo *obj = host1x_to_tegra_bo(bo); - return 0; + drm_gem_object_put(&obj->gem); } -static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, - dma_addr_t *phys) +static struct host1x_bo_mapping *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction direction) { struct tegra_bo *obj = host1x_to_tegra_bo(bo); - struct sg_table *sgt; + struct drm_gem_object *gem = &obj->gem; + struct host1x_bo_mapping *map; int err; + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) + return ERR_PTR(-ENOMEM); + + map->bo = host1x_bo_get(bo); + map->direction = direction; + map->dev = dev; + /* - * If we've manually mapped the buffer object through the IOMMU, make - * sure to return the IOVA address of our mapping. - * - * Similarly, for buffers that have been allocated by the DMA API the - * physical address can be used for devices that are not attached to - * an IOMMU. For these devices, callers must pass a valid pointer via - * the @phys argument. - * - * Imported buffers were also already mapped at import time, so the - * existing mapping can be reused. + * Imported buffers need special treatment to satisfy the semantics of DMA-BUF. */ - if (phys) { - *phys = obj->iova; - return NULL; + if (gem->import_attach) { + struct dma_buf *buf = gem->import_attach->dmabuf; + + map->attach = dma_buf_attach(buf, dev); + if (IS_ERR(map->attach)) { + err = PTR_ERR(map->attach); + goto free; + } + + map->sgt = dma_buf_map_attachment(map->attach, direction); + if (IS_ERR(map->sgt)) { + dma_buf_detach(buf, map->attach); + err = PTR_ERR(map->sgt); + goto free; + } + + err = sgt_dma_count_chunks(map->sgt); + map->size = gem->size; + + goto out; } /* * If we don't have a mapping for this buffer yet, return an SG table * so that host1x can do the mapping for us via the DMA API. */ - sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); - if (!sgt) - return ERR_PTR(-ENOMEM); + map->sgt = kzalloc(sizeof(*map->sgt), GFP_KERNEL); + if (!map->sgt) { + err = -ENOMEM; + goto free; + } if (obj->pages) { /* * If the buffer object was allocated from the explicit IOMMU * API code paths, construct an SG table from the pages. */ - err = sg_alloc_table_from_pages(sgt, obj->pages, obj->num_pages, - 0, obj->gem.size, GFP_KERNEL); - if (err < 0) - goto free; - } else if (obj->sgt) { - /* - * If the buffer object already has an SG table but no pages - * were allocated for it, it means the buffer was imported and - * the SG table needs to be copied to avoid overwriting any - * other potential users of the original SG table. - */ - err = sg_alloc_table_from_sg(sgt, obj->sgt->sgl, - obj->sgt->orig_nents, GFP_KERNEL); + err = sg_alloc_table_from_pages(map->sgt, obj->pages, obj->num_pages, 0, gem->size, + GFP_KERNEL); if (err < 0) goto free; } else { @@ -111,25 +121,56 @@ static struct sg_table *tegra_bo_pin(struct device *dev, struct host1x_bo *bo, * not imported, it had to be allocated with the DMA API, so * the DMA API helper can be used. */ - err = dma_get_sgtable(dev, sgt, obj->vaddr, obj->iova, - obj->gem.size); + err = dma_get_sgtable(dev, map->sgt, obj->vaddr, obj->iova, gem->size); if (err < 0) goto free; } - return sgt; + err = dma_map_sgtable(dev, map->sgt, direction, 0); + if (err) + goto free_sgt; + +out: + /* + * If we've manually mapped the buffer object through the IOMMU, make sure to return the + * existing IOVA address of our mapping. + */ + if (!obj->mm) { + map->phys = sg_dma_address(map->sgt->sgl); + map->chunks = err; + } else { + map->phys = obj->iova; + map->chunks = 1; + } + + map->size = gem->size; + return map; + +free_sgt: + sg_free_table(map->sgt); free: - kfree(sgt); + kfree(map->sgt); + kfree(map); return ERR_PTR(err); } -static void tegra_bo_unpin(struct device *dev, struct sg_table *sgt) +static void tegra_bo_unpin(struct host1x_bo_mapping *map) { - if (sgt) { - sg_free_table(sgt); - kfree(sgt); + if (!map) + return; + + if (map->attach) { + dma_buf_unmap_attachment(map->attach, map->sgt, map->direction); + dma_buf_detach(map->attach->dmabuf, map->attach); + } else { + dma_unmap_sgtable(map->dev, map->sgt, map->direction, 0); + sg_free_table(map->sgt); + kfree(map->sgt); } + + host1x_bo_put(map->bo); + kfree(map); } static void *tegra_bo_mmap(struct host1x_bo *bo) diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index 16a1cdc28657..e579d966e8dc 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -74,7 +74,7 @@ tegra_plane_atomic_duplicate_state(struct drm_plane *plane) for (i = 0; i < 3; i++) { copy->iova[i] = DMA_MAPPING_ERROR; - copy->sgt[i] = NULL; + copy->map[i] = NULL; } return ©->base; @@ -138,55 +138,37 @@ const struct drm_plane_funcs tegra_plane_funcs = { static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) { - struct iommu_domain *domain = iommu_get_domain_for_dev(dc->dev); unsigned int i; int err; for (i = 0; i < state->base.fb->format->num_planes; i++) { struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); - dma_addr_t phys_addr, *phys; - struct sg_table *sgt; + struct host1x_bo_mapping *map; - /* - * If we're not attached to a domain, we already stored the - * physical address when the buffer was allocated. If we're - * part of a group that's shared between all display - * controllers, we've also already mapped the framebuffer - * through the SMMU. In both cases we can short-circuit the - * code below and retrieve the stored IOV address. - */ - if (!domain || dc->client.group) - phys = &phys_addr; - else - phys = NULL; - - sgt = host1x_bo_pin(dc->dev, &bo->base, phys); - if (IS_ERR(sgt)) { - err = PTR_ERR(sgt); + map = host1x_bo_pin(dc->dev, &bo->base, DMA_TO_DEVICE); + if (IS_ERR(map)) { + err = PTR_ERR(map); goto unpin; } - if (sgt) { - err = dma_map_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); - if (err) - goto unpin; - + if (!dc->client.group) { /* * The display controller needs contiguous memory, so * fail if the buffer is discontiguous and we fail to * map its SG table to a single contiguous chunk of * I/O virtual memory. */ - if (sgt->nents > 1) { + if (map->chunks > 1) { err = -EINVAL; goto unpin; } - state->iova[i] = sg_dma_address(sgt->sgl); - state->sgt[i] = sgt; + state->iova[i] = map->phys; } else { - state->iova[i] = phys_addr; + state->iova[i] = bo->iova; } + + state->map[i] = map; } return 0; @@ -195,15 +177,9 @@ unpin: dev_err(dc->dev, "failed to map plane %u: %d\n", i, err); while (i--) { - struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); - struct sg_table *sgt = state->sgt[i]; - - if (sgt) - dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); - - host1x_bo_unpin(dc->dev, &bo->base, sgt); + host1x_bo_unpin(state->map[i]); state->iova[i] = DMA_MAPPING_ERROR; - state->sgt[i] = NULL; + state->map[i] = NULL; } return err; @@ -214,15 +190,9 @@ static void tegra_dc_unpin(struct tegra_dc *dc, struct tegra_plane_state *state) unsigned int i; for (i = 0; i < state->base.fb->format->num_planes; i++) { - struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); - struct sg_table *sgt = state->sgt[i]; - - if (sgt) - dma_unmap_sgtable(dc->dev, sgt, DMA_TO_DEVICE, 0); - - host1x_bo_unpin(dc->dev, &bo->base, sgt); + host1x_bo_unpin(state->map[i]); state->iova[i] = DMA_MAPPING_ERROR; - state->sgt[i] = NULL; + state->map[i] = NULL; } } diff --git a/drivers/gpu/drm/tegra/plane.h b/drivers/gpu/drm/tegra/plane.h index d9470780c803..dfb20712fbd7 100644 --- a/drivers/gpu/drm/tegra/plane.h +++ b/drivers/gpu/drm/tegra/plane.h @@ -43,7 +43,7 @@ struct tegra_plane_legacy_blending_state { struct tegra_plane_state { struct drm_plane_state base; - struct sg_table *sgt[3]; + struct host1x_bo_mapping *map[3]; dma_addr_t iova[3]; struct tegra_bo_tiling tiling; diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c index 776f825df52f..6b950388527b 100644 --- a/drivers/gpu/drm/tegra/submit.c +++ b/drivers/gpu/drm/tegra/submit.c @@ -64,33 +64,61 @@ static void gather_bo_put(struct host1x_bo *host_bo) kref_put(&bo->ref, gather_bo_release); } -static struct sg_table * -gather_bo_pin(struct device *dev, struct host1x_bo *host_bo, dma_addr_t *phys) +static struct host1x_bo_mapping * +gather_bo_pin(struct device *dev, struct host1x_bo *bo, enum dma_data_direction direction) { - struct gather_bo *bo = container_of(host_bo, struct gather_bo, base); - struct sg_table *sgt; + struct gather_bo *gather = container_of(bo, struct gather_bo, base); + struct host1x_bo_mapping *map; int err; - sgt = kzalloc(sizeof(*sgt), GFP_KERNEL); - if (!sgt) + map = kzalloc(sizeof(*map), GFP_KERNEL); + if (!map) return ERR_PTR(-ENOMEM); - err = dma_get_sgtable(bo->dev, sgt, bo->gather_data, bo->gather_data_dma, - bo->gather_data_words * 4); - if (err) { - kfree(sgt); - return ERR_PTR(err); + map->bo = host1x_bo_get(bo); + map->direction = direction; + map->dev = dev; + + map->sgt = kzalloc(sizeof(*map->sgt), GFP_KERNEL); + if (!map->sgt) { + err = -ENOMEM; + goto free; } - return sgt; + err = dma_get_sgtable(gather->dev, map->sgt, gather->gather_data, gather->gather_data_dma, + gather->gather_data_words * 4); + if (err) + goto free_sgt; + + err = dma_map_sgtable(dev, map->sgt, direction, 0); + if (err) + goto free_sgt; + + map->phys = sg_dma_address(map->sgt->sgl); + map->size = gather->gather_data_words * 4; + map->chunks = err; + + return map; + +free_sgt: + sg_free_table(map->sgt); + kfree(map->sgt); +free: + kfree(map); + return ERR_PTR(err); } -static void gather_bo_unpin(struct device *dev, struct sg_table *sgt) +static void gather_bo_unpin(struct host1x_bo_mapping *map) { - if (sgt) { - sg_free_table(sgt); - kfree(sgt); - } + if (!map) + return; + + dma_unmap_sgtable(map->dev, map->sgt, map->direction, 0); + sg_free_table(map->sgt); + kfree(map->sgt); + host1x_bo_put(map->bo); + + kfree(map); } static void *gather_bo_mmap(struct host1x_bo *host_bo) diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index 690a339c52ec..d31df8e129c5 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -17,11 +17,7 @@ static void tegra_drm_mapping_release(struct kref *ref) struct tegra_drm_mapping *mapping = container_of(ref, struct tegra_drm_mapping, ref); - if (mapping->sgt) - dma_unmap_sgtable(mapping->dev, mapping->sgt, mapping->direction, - DMA_ATTR_SKIP_CPU_SYNC); - - host1x_bo_unpin(mapping->dev, mapping->bo, mapping->sgt); + host1x_bo_unpin(mapping->map); host1x_bo_put(mapping->bo); kfree(mapping); @@ -159,6 +155,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f struct drm_tegra_channel_map *args = data; struct tegra_drm_mapping *mapping; struct tegra_drm_context *context; + enum dma_data_direction direction; int err = 0; if (args->flags & ~DRM_TEGRA_CHANNEL_MAP_READ_WRITE) @@ -180,68 +177,53 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f kref_init(&mapping->ref); - mapping->dev = context->client->base.dev; mapping->bo = tegra_gem_lookup(file, args->handle); if (!mapping->bo) { err = -EINVAL; - goto unlock; + goto free; } - if (context->client->base.group) { - /* IOMMU domain managed directly using IOMMU API */ - host1x_bo_pin(mapping->dev, mapping->bo, &mapping->iova); - } else { - switch (args->flags & DRM_TEGRA_CHANNEL_MAP_READ_WRITE) { - case DRM_TEGRA_CHANNEL_MAP_READ_WRITE: - mapping->direction = DMA_BIDIRECTIONAL; - break; - - case DRM_TEGRA_CHANNEL_MAP_WRITE: - mapping->direction = DMA_FROM_DEVICE; - break; - - case DRM_TEGRA_CHANNEL_MAP_READ: - mapping->direction = DMA_TO_DEVICE; - break; + switch (args->flags & DRM_TEGRA_CHANNEL_MAP_READ_WRITE) { + case DRM_TEGRA_CHANNEL_MAP_READ_WRITE: + direction = DMA_BIDIRECTIONAL; + break; - default: - return -EINVAL; - } + case DRM_TEGRA_CHANNEL_MAP_WRITE: + direction = DMA_FROM_DEVICE; + break; - mapping->sgt = host1x_bo_pin(mapping->dev, mapping->bo, NULL); - if (IS_ERR(mapping->sgt)) { - err = PTR_ERR(mapping->sgt); - goto put_gem; - } + case DRM_TEGRA_CHANNEL_MAP_READ: + direction = DMA_TO_DEVICE; + break; - err = dma_map_sgtable(mapping->dev, mapping->sgt, mapping->direction, - DMA_ATTR_SKIP_CPU_SYNC); - if (err) - goto unpin; + default: + err = -EINVAL; + goto put_gem; + } - mapping->iova = sg_dma_address(mapping->sgt->sgl); + mapping->map = host1x_bo_pin(context->client->base.dev, mapping->bo, direction); + if (IS_ERR(mapping->map)) { + err = PTR_ERR(mapping->map); + goto put_gem; } + mapping->iova = mapping->map->phys; mapping->iova_end = mapping->iova + host1x_to_tegra_bo(mapping->bo)->gem.size; err = xa_alloc(&context->mappings, &args->mapping, mapping, XA_LIMIT(1, U32_MAX), GFP_KERNEL); if (err < 0) - goto unmap; + goto unpin; mutex_unlock(&fpriv->lock); return 0; -unmap: - if (mapping->sgt) { - dma_unmap_sgtable(mapping->dev, mapping->sgt, mapping->direction, - DMA_ATTR_SKIP_CPU_SYNC); - } unpin: - host1x_bo_unpin(mapping->dev, mapping->bo, mapping->sgt); + host1x_bo_unpin(mapping->map); put_gem: host1x_bo_put(mapping->bo); +free: kfree(mapping); unlock: mutex_unlock(&fpriv->lock); diff --git a/drivers/gpu/drm/tegra/uapi.h b/drivers/gpu/drm/tegra/uapi.h index 12adad770ad3..92ff1e44ff15 100644 --- a/drivers/gpu/drm/tegra/uapi.h +++ b/drivers/gpu/drm/tegra/uapi.h @@ -27,10 +27,9 @@ struct tegra_drm_file { struct tegra_drm_mapping { struct kref ref; - struct device *dev; + struct host1x_bo_mapping *map; struct host1x_bo *bo; - struct sg_table *sgt; - enum dma_data_direction direction; + dma_addr_t iova; dma_addr_t iova_end; }; diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 0eef6df7c89e..64bcc3d83efc 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -134,20 +134,20 @@ EXPORT_SYMBOL(host1x_job_add_wait); static unsigned int pin_job(struct host1x *host, struct host1x_job *job) { + unsigned long mask = HOST1X_RELOC_READ | HOST1X_RELOC_WRITE; struct host1x_client *client = job->client; struct device *dev = client->dev; struct host1x_job_gather *g; - struct iommu_domain *domain; - struct sg_table *sgt; unsigned int i; int err; - domain = iommu_get_domain_for_dev(dev); job->num_unpins = 0; for (i = 0; i < job->num_relocs; i++) { struct host1x_reloc *reloc = &job->relocs[i]; - dma_addr_t phys_addr, *phys; + enum dma_data_direction direction; + struct host1x_bo_mapping *map; + struct host1x_bo *bo; reloc->target.bo = host1x_bo_get(reloc->target.bo); if (!reloc->target.bo) { @@ -155,64 +155,44 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - /* - * If the client device is not attached to an IOMMU, the - * physical address of the buffer object can be used. - * - * Similarly, when an IOMMU domain is shared between all - * host1x clients, the IOVA is already available, so no - * need to map the buffer object again. - * - * XXX Note that this isn't always safe to do because it - * relies on an assumption that no cache maintenance is - * needed on the buffer objects. - */ - if (!domain || client->group) - phys = &phys_addr; - else - phys = NULL; - - sgt = host1x_bo_pin(dev, reloc->target.bo, phys); - if (IS_ERR(sgt)) { - err = PTR_ERR(sgt); - goto unpin; - } + bo = reloc->target.bo; - if (sgt) { - unsigned long mask = HOST1X_RELOC_READ | - HOST1X_RELOC_WRITE; - enum dma_data_direction dir; - - switch (reloc->flags & mask) { - case HOST1X_RELOC_READ: - dir = DMA_TO_DEVICE; - break; + switch (reloc->flags & mask) { + case HOST1X_RELOC_READ: + direction = DMA_TO_DEVICE; + break; - case HOST1X_RELOC_WRITE: - dir = DMA_FROM_DEVICE; - break; + case HOST1X_RELOC_WRITE: + direction = DMA_FROM_DEVICE; + break; - case HOST1X_RELOC_READ | HOST1X_RELOC_WRITE: - dir = DMA_BIDIRECTIONAL; - break; + case HOST1X_RELOC_READ | HOST1X_RELOC_WRITE: + direction = DMA_BIDIRECTIONAL; + break; - default: - err = -EINVAL; - goto unpin; - } + default: + err = -EINVAL; + goto unpin; + } - err = dma_map_sgtable(dev, sgt, dir, 0); - if (err) - goto unpin; + map = host1x_bo_pin(dev, bo, direction); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto unpin; + } - job->unpins[job->num_unpins].dev = dev; - job->unpins[job->num_unpins].dir = dir; - phys_addr = sg_dma_address(sgt->sgl); + /* + * host1x clients are generally not able to do scatter-gather themselves, so fail + * if the buffer is discontiguous and we fail to map its SG table to a single + * contiguous chunk of I/O virtual memory. + */ + if (map->chunks > 1) { + err = -EINVAL; + goto unpin; } - job->addr_phys[job->num_unpins] = phys_addr; - job->unpins[job->num_unpins].bo = reloc->target.bo; - job->unpins[job->num_unpins].sgt = sgt; + job->addr_phys[job->num_unpins] = map->phys; + job->unpins[job->num_unpins].map = map; job->num_unpins++; } @@ -224,12 +204,11 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) return 0; for (i = 0; i < job->num_cmds; i++) { + struct host1x_bo_mapping *map; size_t gather_size = 0; struct scatterlist *sg; - dma_addr_t phys_addr; unsigned long shift; struct iova *alloc; - dma_addr_t *phys; unsigned int j; if (job->cmds[i].is_wait) @@ -243,25 +222,16 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - /** - * If the host1x is not attached to an IOMMU, there is no need - * to map the buffer object for the host1x, since the physical - * address can simply be used. - */ - if (!iommu_get_domain_for_dev(host->dev)) - phys = &phys_addr; - else - phys = NULL; - - sgt = host1x_bo_pin(host->dev, g->bo, phys); - if (IS_ERR(sgt)) { - err = PTR_ERR(sgt); - goto put; + map = host1x_bo_pin(host->dev, g->bo, DMA_TO_DEVICE); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto unpin; } if (host->domain) { - for_each_sgtable_sg(sgt, sg, j) + for_each_sgtable_sg(map->sgt, sg, j) gather_size += sg->length; + gather_size = iova_align(&host->iova, gather_size); shift = iova_shift(&host->iova); @@ -272,33 +242,23 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto put; } - err = iommu_map_sgtable(host->domain, - iova_dma_addr(&host->iova, alloc), - sgt, IOMMU_READ); + err = iommu_map_sgtable(host->domain, iova_dma_addr(&host->iova, alloc), + map->sgt, IOMMU_READ); if (err == 0) { __free_iova(&host->iova, alloc); err = -EINVAL; goto put; } - job->unpins[job->num_unpins].size = gather_size; - phys_addr = iova_dma_addr(&host->iova, alloc); - } else if (sgt) { - err = dma_map_sgtable(host->dev, sgt, DMA_TO_DEVICE, 0); - if (err) - goto put; - - job->unpins[job->num_unpins].dir = DMA_TO_DEVICE; - job->unpins[job->num_unpins].dev = host->dev; - phys_addr = sg_dma_address(sgt->sgl); + map->phys = iova_dma_addr(&host->iova, alloc); + map->size = gather_size; } - job->addr_phys[job->num_unpins] = phys_addr; - job->gather_addr_phys[i] = phys_addr; - - job->unpins[job->num_unpins].bo = g->bo; - job->unpins[job->num_unpins].sgt = sgt; + job->addr_phys[job->num_unpins] = map->phys; + job->unpins[job->num_unpins].map = map; job->num_unpins++; + + job->gather_addr_phys[i] = map->phys; } return 0; @@ -690,22 +650,16 @@ void host1x_job_unpin(struct host1x_job *job) unsigned int i; for (i = 0; i < job->num_unpins; i++) { - struct host1x_job_unpin_data *unpin = &job->unpins[i]; - struct device *dev = unpin->dev ?: host->dev; - struct sg_table *sgt = unpin->sgt; - - if (!job->enable_firewall && unpin->size && host->domain) { - iommu_unmap(host->domain, job->addr_phys[i], - unpin->size); - free_iova(&host->iova, - iova_pfn(&host->iova, job->addr_phys[i])); - } + struct host1x_bo_mapping *map = job->unpins[i].map; + struct host1x_bo *bo = map->bo; - if (unpin->dev && sgt) - dma_unmap_sgtable(unpin->dev, sgt, unpin->dir, 0); + if (!job->enable_firewall && map->size && host->domain) { + iommu_unmap(host->domain, job->addr_phys[i], map->size); + free_iova(&host->iova, iova_pfn(&host->iova, job->addr_phys[i])); + } - host1x_bo_unpin(dev, unpin->bo, sgt); - host1x_bo_put(unpin->bo); + host1x_bo_unpin(map); + host1x_bo_put(bo); } job->num_unpins = 0; diff --git a/drivers/gpu/host1x/job.h b/drivers/gpu/host1x/job.h index b4428c5495c9..dad5a1946693 100644 --- a/drivers/gpu/host1x/job.h +++ b/drivers/gpu/host1x/job.h @@ -35,11 +35,7 @@ struct host1x_job_cmd { }; struct host1x_job_unpin_data { - struct host1x_bo *bo; - struct sg_table *sgt; - struct device *dev; - size_t size; - enum dma_data_direction dir; + struct host1x_bo_mapping *map; }; /* diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 7bccf589aba7..157326074df8 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -7,6 +7,7 @@ #define __LINUX_HOST1X_H #include +#include #include enum host1x_class { @@ -82,12 +83,23 @@ struct host1x_client { struct host1x_bo; struct sg_table; +struct host1x_bo_mapping { + struct dma_buf_attachment *attach; + enum dma_data_direction direction; + struct host1x_bo *bo; + struct sg_table *sgt; + unsigned int chunks; + struct device *dev; + dma_addr_t phys; + size_t size; +}; + struct host1x_bo_ops { struct host1x_bo *(*get)(struct host1x_bo *bo); void (*put)(struct host1x_bo *bo); - struct sg_table *(*pin)(struct device *dev, struct host1x_bo *bo, - dma_addr_t *phys); - void (*unpin)(struct device *dev, struct sg_table *sgt); + struct host1x_bo_mapping *(*pin)(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction dir); + void (*unpin)(struct host1x_bo_mapping *map); void *(*mmap)(struct host1x_bo *bo); void (*munmap)(struct host1x_bo *bo, void *addr); }; @@ -112,17 +124,15 @@ static inline void host1x_bo_put(struct host1x_bo *bo) bo->ops->put(bo); } -static inline struct sg_table *host1x_bo_pin(struct device *dev, - struct host1x_bo *bo, - dma_addr_t *phys) +static inline struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction dir) { - return bo->ops->pin(dev, bo, phys); + return bo->ops->pin(dev, bo, dir); } -static inline void host1x_bo_unpin(struct device *dev, struct host1x_bo *bo, - struct sg_table *sgt) +static inline void host1x_bo_unpin(struct host1x_bo_mapping *map) { - bo->ops->unpin(dev, sgt); + map->bo->ops->unpin(map); } static inline void *host1x_bo_mmap(struct host1x_bo *bo) -- cgit v1.2.3 From 1f39b1dfa53c84b56d7ad37fed44afda7004959d Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 7 Feb 2020 16:50:52 +0100 Subject: drm/tegra: Implement buffer object cache This cache is used to avoid mapping and unmapping buffer objects unnecessarily. Mappings are cached per client and stay hot until the buffer object is destroyed. Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/gem.c | 14 ++++++-- drivers/gpu/drm/tegra/plane.c | 2 +- drivers/gpu/drm/tegra/submit.c | 1 + drivers/gpu/drm/tegra/uapi.c | 2 +- drivers/gpu/host1x/bus.c | 78 ++++++++++++++++++++++++++++++++++++++++++ drivers/gpu/host1x/dev.c | 2 ++ drivers/gpu/host1x/dev.h | 2 ++ drivers/gpu/host1x/job.c | 4 +-- include/linux/host1x.h | 53 ++++++++++++++++++++++------ 9 files changed, 141 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c index f00938d8bc88..fce0e52973c2 100644 --- a/drivers/gpu/drm/tegra/gem.c +++ b/drivers/gpu/drm/tegra/gem.c @@ -67,6 +67,7 @@ static struct host1x_bo_mapping *tegra_bo_pin(struct device *dev, struct host1x_ if (!map) return ERR_PTR(-ENOMEM); + kref_init(&map->ref); map->bo = host1x_bo_get(bo); map->direction = direction; map->dev = dev; @@ -157,9 +158,6 @@ free: static void tegra_bo_unpin(struct host1x_bo_mapping *map) { - if (!map) - return; - if (map->attach) { dma_buf_unmap_attachment(map->attach, map->sgt, map->direction); dma_buf_detach(map->attach->dmabuf, map->attach); @@ -493,8 +491,18 @@ free: void tegra_bo_free_object(struct drm_gem_object *gem) { struct tegra_drm *tegra = gem->dev->dev_private; + struct host1x_bo_mapping *mapping, *tmp; struct tegra_bo *bo = to_tegra_bo(gem); + /* remove all mappings of this buffer object from any caches */ + list_for_each_entry_safe(mapping, tmp, &bo->base.mappings, list) { + if (mapping->cache) + host1x_bo_unpin(mapping); + else + dev_err(gem->dev->dev, "mapping %p stale for device %s\n", mapping, + dev_name(mapping->dev)); + } + if (tegra->domain) tegra_bo_iommu_unmap(tegra, bo); diff --git a/drivers/gpu/drm/tegra/plane.c b/drivers/gpu/drm/tegra/plane.c index e579d966e8dc..f8e8afcbcbf2 100644 --- a/drivers/gpu/drm/tegra/plane.c +++ b/drivers/gpu/drm/tegra/plane.c @@ -145,7 +145,7 @@ static int tegra_dc_pin(struct tegra_dc *dc, struct tegra_plane_state *state) struct tegra_bo *bo = tegra_fb_get_plane(state->base.fb, i); struct host1x_bo_mapping *map; - map = host1x_bo_pin(dc->dev, &bo->base, DMA_TO_DEVICE); + map = host1x_bo_pin(dc->dev, &bo->base, DMA_TO_DEVICE, &dc->client.cache); if (IS_ERR(map)) { err = PTR_ERR(map); goto unpin; diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c index 6b950388527b..c32698404e36 100644 --- a/drivers/gpu/drm/tegra/submit.c +++ b/drivers/gpu/drm/tegra/submit.c @@ -75,6 +75,7 @@ gather_bo_pin(struct device *dev, struct host1x_bo *bo, enum dma_data_direction if (!map) return ERR_PTR(-ENOMEM); + kref_init(&map->ref); map->bo = host1x_bo_get(bo); map->direction = direction; map->dev = dev; diff --git a/drivers/gpu/drm/tegra/uapi.c b/drivers/gpu/drm/tegra/uapi.c index d31df8e129c5..9ab9179d2026 100644 --- a/drivers/gpu/drm/tegra/uapi.c +++ b/drivers/gpu/drm/tegra/uapi.c @@ -201,7 +201,7 @@ int tegra_drm_ioctl_channel_map(struct drm_device *drm, void *data, struct drm_f goto put_gem; } - mapping->map = host1x_bo_pin(context->client->base.dev, mapping->bo, direction); + mapping->map = host1x_bo_pin(context->client->base.dev, mapping->bo, direction, NULL); if (IS_ERR(mapping->map)) { err = PTR_ERR(mapping->map); goto put_gem; diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 218e3718fd68..0b67d894470d 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -742,6 +742,7 @@ EXPORT_SYMBOL(host1x_driver_unregister); */ void __host1x_client_init(struct host1x_client *client, struct lock_class_key *key) { + host1x_bo_cache_init(&client->cache); INIT_LIST_HEAD(&client->list); __mutex_init(&client->lock, "host1x client lock", key); client->usecount = 0; @@ -830,6 +831,8 @@ int host1x_client_unregister(struct host1x_client *client) mutex_unlock(&clients_lock); + host1x_bo_cache_destroy(&client->cache); + return 0; } EXPORT_SYMBOL(host1x_client_unregister); @@ -904,3 +907,78 @@ unlock: return err; } EXPORT_SYMBOL(host1x_client_resume); + +struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction dir, + struct host1x_bo_cache *cache) +{ + struct host1x_bo_mapping *mapping; + + if (cache) { + mutex_lock(&cache->lock); + + list_for_each_entry(mapping, &cache->mappings, entry) { + if (mapping->bo == bo && mapping->direction == dir) { + kref_get(&mapping->ref); + goto unlock; + } + } + } + + mapping = bo->ops->pin(dev, bo, dir); + if (IS_ERR(mapping)) + goto unlock; + + spin_lock(&mapping->bo->lock); + list_add_tail(&mapping->list, &bo->mappings); + spin_unlock(&mapping->bo->lock); + + if (cache) { + INIT_LIST_HEAD(&mapping->entry); + mapping->cache = cache; + + list_add_tail(&mapping->entry, &cache->mappings); + + /* bump reference count to track the copy in the cache */ + kref_get(&mapping->ref); + } + +unlock: + if (cache) + mutex_unlock(&cache->lock); + + return mapping; +} +EXPORT_SYMBOL(host1x_bo_pin); + +static void __host1x_bo_unpin(struct kref *ref) +{ + struct host1x_bo_mapping *mapping = to_host1x_bo_mapping(ref); + + /* + * When the last reference of the mapping goes away, make sure to remove the mapping from + * the cache. + */ + if (mapping->cache) + list_del(&mapping->entry); + + spin_lock(&mapping->bo->lock); + list_del(&mapping->list); + spin_unlock(&mapping->bo->lock); + + mapping->bo->ops->unpin(mapping); +} + +void host1x_bo_unpin(struct host1x_bo_mapping *mapping) +{ + struct host1x_bo_cache *cache = mapping->cache; + + if (cache) + mutex_lock(&cache->lock); + + kref_put(&mapping->ref, __host1x_bo_unpin); + + if (cache) + mutex_unlock(&cache->lock); +} +EXPORT_SYMBOL(host1x_bo_unpin); diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index fbb6447b8659..85eb3d19bbdb 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -386,6 +386,7 @@ static int host1x_probe(struct platform_device *pdev) if (syncpt_irq < 0) return syncpt_irq; + host1x_bo_cache_init(&host->cache); mutex_init(&host->devices_lock); INIT_LIST_HEAD(&host->devices); INIT_LIST_HEAD(&host->list); @@ -512,6 +513,7 @@ static int host1x_remove(struct platform_device *pdev) reset_control_assert(host->rst); clk_disable_unprepare(host->clk); host1x_iommu_exit(host); + host1x_bo_cache_destroy(&host->cache); return 0; } diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h index fa6d4bc46e98..5b7fdea5d169 100644 --- a/drivers/gpu/host1x/dev.h +++ b/drivers/gpu/host1x/dev.h @@ -149,6 +149,8 @@ struct host1x { struct list_head list; struct device_dma_parameters dma_parms; + + struct host1x_bo_cache cache; }; void host1x_hypervisor_writel(struct host1x *host1x, u32 r, u32 v); diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c index 64bcc3d83efc..5e8c183167b7 100644 --- a/drivers/gpu/host1x/job.c +++ b/drivers/gpu/host1x/job.c @@ -175,7 +175,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - map = host1x_bo_pin(dev, bo, direction); + map = host1x_bo_pin(dev, bo, direction, &client->cache); if (IS_ERR(map)) { err = PTR_ERR(map); goto unpin; @@ -222,7 +222,7 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job) goto unpin; } - map = host1x_bo_pin(host->dev, g->bo, DMA_TO_DEVICE); + map = host1x_bo_pin(host->dev, g->bo, DMA_TO_DEVICE, &host->cache); if (IS_ERR(map)) { err = PTR_ERR(map); goto unpin; diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 157326074df8..d0bb16cdd005 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -8,6 +8,7 @@ #include #include +#include #include enum host1x_class { @@ -24,6 +25,28 @@ struct iommu_group; u64 host1x_get_dma_mask(struct host1x *host1x); +/** + * struct host1x_bo_cache - host1x buffer object cache + * @mappings: list of mappings + * @lock: synchronizes accesses to the list of mappings + */ +struct host1x_bo_cache { + struct list_head mappings; + struct mutex lock; +}; + +static inline void host1x_bo_cache_init(struct host1x_bo_cache *cache) +{ + INIT_LIST_HEAD(&cache->mappings); + mutex_init(&cache->lock); +} + +static inline void host1x_bo_cache_destroy(struct host1x_bo_cache *cache) +{ + /* XXX warn if not empty? */ + mutex_destroy(&cache->lock); +} + /** * struct host1x_client_ops - host1x client operations * @early_init: host1x client early initialization code @@ -74,6 +97,8 @@ struct host1x_client { struct host1x_client *parent; unsigned int usecount; struct mutex lock; + + struct host1x_bo_cache cache; }; /* @@ -84,16 +109,26 @@ struct host1x_bo; struct sg_table; struct host1x_bo_mapping { + struct kref ref; struct dma_buf_attachment *attach; enum dma_data_direction direction; + struct list_head list; struct host1x_bo *bo; struct sg_table *sgt; unsigned int chunks; struct device *dev; dma_addr_t phys; size_t size; + + struct host1x_bo_cache *cache; + struct list_head entry; }; +static inline struct host1x_bo_mapping *to_host1x_bo_mapping(struct kref *ref) +{ + return container_of(ref, struct host1x_bo_mapping, ref); +} + struct host1x_bo_ops { struct host1x_bo *(*get)(struct host1x_bo *bo); void (*put)(struct host1x_bo *bo); @@ -106,11 +141,15 @@ struct host1x_bo_ops { struct host1x_bo { const struct host1x_bo_ops *ops; + struct list_head mappings; + spinlock_t lock; }; static inline void host1x_bo_init(struct host1x_bo *bo, const struct host1x_bo_ops *ops) { + INIT_LIST_HEAD(&bo->mappings); + spin_lock_init(&bo->lock); bo->ops = ops; } @@ -124,16 +163,10 @@ static inline void host1x_bo_put(struct host1x_bo *bo) bo->ops->put(bo); } -static inline struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo, - enum dma_data_direction dir) -{ - return bo->ops->pin(dev, bo, dir); -} - -static inline void host1x_bo_unpin(struct host1x_bo_mapping *map) -{ - map->bo->ops->unpin(map); -} +struct host1x_bo_mapping *host1x_bo_pin(struct device *dev, struct host1x_bo *bo, + enum dma_data_direction dir, + struct host1x_bo_cache *cache); +void host1x_bo_unpin(struct host1x_bo_mapping *map); static inline void *host1x_bo_mmap(struct host1x_bo *bo) { -- cgit v1.2.3 From 46f226c93d35b936aeec6eb31da932dc2e86f413 Mon Sep 17 00:00:00 2001 From: Mikko Perttunen Date: Thu, 16 Sep 2021 17:55:17 +0300 Subject: drm/tegra: Add NVDEC driver Add support for booting and using NVDEC on Tegra210, Tegra186 and Tegra194 to the Host1x and TegraDRM drivers. Booting in secure mode is not currently supported. Signed-off-by: Mikko Perttunen Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/Makefile | 3 +- drivers/gpu/drm/tegra/drm.c | 4 + drivers/gpu/drm/tegra/drm.h | 1 + drivers/gpu/drm/tegra/nvdec.c | 464 +++++++++++++++++++++++++++++++++++++++++ drivers/gpu/host1x/dev.c | 18 ++ include/linux/host1x.h | 2 + 6 files changed, 491 insertions(+), 1 deletion(-) create mode 100644 drivers/gpu/drm/tegra/nvdec.c (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/Makefile b/drivers/gpu/drm/tegra/Makefile index d801909182cf..df6cc986aeba 100644 --- a/drivers/gpu/drm/tegra/Makefile +++ b/drivers/gpu/drm/tegra/Makefile @@ -23,7 +23,8 @@ tegra-drm-y := \ gr2d.o \ gr3d.o \ falcon.o \ - vic.o + vic.o \ + nvdec.o tegra-drm-y += trace.o diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index 8d37d6b00562..2e7da2a7505d 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1344,15 +1344,18 @@ static const struct of_device_id host1x_drm_subdevs[] = { { .compatible = "nvidia,tegra210-sor", }, { .compatible = "nvidia,tegra210-sor1", }, { .compatible = "nvidia,tegra210-vic", }, + { .compatible = "nvidia,tegra210-nvdec", }, { .compatible = "nvidia,tegra186-display", }, { .compatible = "nvidia,tegra186-dc", }, { .compatible = "nvidia,tegra186-sor", }, { .compatible = "nvidia,tegra186-sor1", }, { .compatible = "nvidia,tegra186-vic", }, + { .compatible = "nvidia,tegra186-nvdec", }, { .compatible = "nvidia,tegra194-display", }, { .compatible = "nvidia,tegra194-dc", }, { .compatible = "nvidia,tegra194-sor", }, { .compatible = "nvidia,tegra194-vic", }, + { .compatible = "nvidia,tegra194-nvdec", }, { /* sentinel */ } }; @@ -1376,6 +1379,7 @@ static struct platform_driver * const drivers[] = { &tegra_gr2d_driver, &tegra_gr3d_driver, &tegra_vic_driver, + &tegra_nvdec_driver, }; static int __init host1x_drm_init(void) diff --git a/drivers/gpu/drm/tegra/drm.h b/drivers/gpu/drm/tegra/drm.h index 8b28327c931c..fc0a19554eac 100644 --- a/drivers/gpu/drm/tegra/drm.h +++ b/drivers/gpu/drm/tegra/drm.h @@ -202,5 +202,6 @@ extern struct platform_driver tegra_sor_driver; extern struct platform_driver tegra_gr2d_driver; extern struct platform_driver tegra_gr3d_driver; extern struct platform_driver tegra_vic_driver; +extern struct platform_driver tegra_nvdec_driver; #endif /* HOST1X_DRM_H */ diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c new file mode 100644 index 000000000000..c3b6fe7fb454 --- /dev/null +++ b/drivers/gpu/drm/tegra/nvdec.c @@ -0,0 +1,464 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2015-2021, NVIDIA Corporation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "drm.h" +#include "falcon.h" +#include "vic.h" + +struct nvdec_config { + const char *firmware; + unsigned int version; + bool supports_sid; +}; + +struct nvdec { + struct falcon falcon; + + void __iomem *regs; + struct tegra_drm_client client; + struct host1x_channel *channel; + struct device *dev; + struct clk *clk; + + /* Platform configuration */ + const struct nvdec_config *config; +}; + +static inline struct nvdec *to_nvdec(struct tegra_drm_client *client) +{ + return container_of(client, struct nvdec, client); +} + +static void nvdec_writel(struct nvdec *nvdec, u32 value, unsigned int offset) +{ + writel(value, nvdec->regs + offset); +} + +static int nvdec_boot(struct nvdec *nvdec) +{ +#ifdef CONFIG_IOMMU_API + struct iommu_fwspec *spec = dev_iommu_fwspec_get(nvdec->dev); +#endif + int err; + +#ifdef CONFIG_IOMMU_API + if (nvdec->config->supports_sid && spec) { + u32 value; + + value = TRANSCFG_ATT(1, TRANSCFG_SID_FALCON) | TRANSCFG_ATT(0, TRANSCFG_SID_HW); + nvdec_writel(nvdec, value, VIC_TFBIF_TRANSCFG); + + if (spec->num_ids > 0) { + value = spec->ids[0] & 0xffff; + + nvdec_writel(nvdec, value, VIC_THI_STREAMID0); + nvdec_writel(nvdec, value, VIC_THI_STREAMID1); + } + } +#endif + + err = falcon_boot(&nvdec->falcon); + if (err < 0) + return err; + + err = falcon_wait_idle(&nvdec->falcon); + if (err < 0) { + dev_err(nvdec->dev, "falcon boot timed out\n"); + return err; + } + + return 0; +} + +static int nvdec_init(struct host1x_client *client) +{ + struct tegra_drm_client *drm = host1x_to_drm_client(client); + struct drm_device *dev = dev_get_drvdata(client->host); + struct tegra_drm *tegra = dev->dev_private; + struct nvdec *nvdec = to_nvdec(drm); + int err; + + err = host1x_client_iommu_attach(client); + if (err < 0 && err != -ENODEV) { + dev_err(nvdec->dev, "failed to attach to domain: %d\n", err); + return err; + } + + nvdec->channel = host1x_channel_request(client); + if (!nvdec->channel) { + err = -ENOMEM; + goto detach; + } + + client->syncpts[0] = host1x_syncpt_request(client, 0); + if (!client->syncpts[0]) { + err = -ENOMEM; + goto free_channel; + } + + err = tegra_drm_register_client(tegra, drm); + if (err < 0) + goto free_syncpt; + + /* + * Inherit the DMA parameters (such as maximum segment size) from the + * parent host1x device. + */ + client->dev->dma_parms = client->host->dma_parms; + + return 0; + +free_syncpt: + host1x_syncpt_put(client->syncpts[0]); +free_channel: + host1x_channel_put(nvdec->channel); +detach: + host1x_client_iommu_detach(client); + + return err; +} + +static int nvdec_exit(struct host1x_client *client) +{ + struct tegra_drm_client *drm = host1x_to_drm_client(client); + struct drm_device *dev = dev_get_drvdata(client->host); + struct tegra_drm *tegra = dev->dev_private; + struct nvdec *nvdec = to_nvdec(drm); + int err; + + /* avoid a dangling pointer just in case this disappears */ + client->dev->dma_parms = NULL; + + err = tegra_drm_unregister_client(tegra, drm); + if (err < 0) + return err; + + host1x_syncpt_put(client->syncpts[0]); + host1x_channel_put(nvdec->channel); + host1x_client_iommu_detach(client); + + if (client->group) { + dma_unmap_single(nvdec->dev, nvdec->falcon.firmware.phys, + nvdec->falcon.firmware.size, DMA_TO_DEVICE); + tegra_drm_free(tegra, nvdec->falcon.firmware.size, + nvdec->falcon.firmware.virt, + nvdec->falcon.firmware.iova); + } else { + dma_free_coherent(nvdec->dev, nvdec->falcon.firmware.size, + nvdec->falcon.firmware.virt, + nvdec->falcon.firmware.iova); + } + + return 0; +} + +static const struct host1x_client_ops nvdec_client_ops = { + .init = nvdec_init, + .exit = nvdec_exit, +}; + +static int nvdec_load_firmware(struct nvdec *nvdec) +{ + struct host1x_client *client = &nvdec->client.base; + struct tegra_drm *tegra = nvdec->client.drm; + dma_addr_t iova; + size_t size; + void *virt; + int err; + + if (nvdec->falcon.firmware.virt) + return 0; + + err = falcon_read_firmware(&nvdec->falcon, nvdec->config->firmware); + if (err < 0) + return err; + + size = nvdec->falcon.firmware.size; + + if (!client->group) { + virt = dma_alloc_coherent(nvdec->dev, size, &iova, GFP_KERNEL); + + err = dma_mapping_error(nvdec->dev, iova); + if (err < 0) + return err; + } else { + virt = tegra_drm_alloc(tegra, size, &iova); + } + + nvdec->falcon.firmware.virt = virt; + nvdec->falcon.firmware.iova = iova; + + err = falcon_load_firmware(&nvdec->falcon); + if (err < 0) + goto cleanup; + + /* + * In this case we have received an IOVA from the shared domain, so we + * need to make sure to get the physical address so that the DMA API + * knows what memory pages to flush the cache for. + */ + if (client->group) { + dma_addr_t phys; + + phys = dma_map_single(nvdec->dev, virt, size, DMA_TO_DEVICE); + + err = dma_mapping_error(nvdec->dev, phys); + if (err < 0) + goto cleanup; + + nvdec->falcon.firmware.phys = phys; + } + + return 0; + +cleanup: + if (!client->group) + dma_free_coherent(nvdec->dev, size, virt, iova); + else + tegra_drm_free(tegra, size, virt, iova); + + return err; +} + + +static int nvdec_runtime_resume(struct device *dev) +{ + struct nvdec *nvdec = dev_get_drvdata(dev); + int err; + + err = clk_prepare_enable(nvdec->clk); + if (err < 0) + return err; + + usleep_range(10, 20); + + err = nvdec_load_firmware(nvdec); + if (err < 0) + goto disable; + + err = nvdec_boot(nvdec); + if (err < 0) + goto disable; + + return 0; + +disable: + clk_disable_unprepare(nvdec->clk); + return err; +} + +static int nvdec_runtime_suspend(struct device *dev) +{ + struct nvdec *nvdec = dev_get_drvdata(dev); + + clk_disable_unprepare(nvdec->clk); + + return 0; +} + +static int nvdec_open_channel(struct tegra_drm_client *client, + struct tegra_drm_context *context) +{ + struct nvdec *nvdec = to_nvdec(client); + int err; + + err = pm_runtime_get_sync(nvdec->dev); + if (err < 0) { + pm_runtime_put(nvdec->dev); + return err; + } + + context->channel = host1x_channel_get(nvdec->channel); + if (!context->channel) { + pm_runtime_put(nvdec->dev); + return -ENOMEM; + } + + return 0; +} + +static void nvdec_close_channel(struct tegra_drm_context *context) +{ + struct nvdec *nvdec = to_nvdec(context->client); + + host1x_channel_put(context->channel); + pm_runtime_put(nvdec->dev); +} + +static const struct tegra_drm_client_ops nvdec_ops = { + .open_channel = nvdec_open_channel, + .close_channel = nvdec_close_channel, + .submit = tegra_drm_submit, +}; + +#define NVIDIA_TEGRA_210_NVDEC_FIRMWARE "nvidia/tegra210/nvdec.bin" + +static const struct nvdec_config nvdec_t210_config = { + .firmware = NVIDIA_TEGRA_210_NVDEC_FIRMWARE, + .version = 0x21, + .supports_sid = false, +}; + +#define NVIDIA_TEGRA_186_NVDEC_FIRMWARE "nvidia/tegra186/nvdec.bin" + +static const struct nvdec_config nvdec_t186_config = { + .firmware = NVIDIA_TEGRA_186_NVDEC_FIRMWARE, + .version = 0x18, + .supports_sid = true, +}; + +#define NVIDIA_TEGRA_194_NVDEC_FIRMWARE "nvidia/tegra194/nvdec.bin" + +static const struct nvdec_config nvdec_t194_config = { + .firmware = NVIDIA_TEGRA_194_NVDEC_FIRMWARE, + .version = 0x19, + .supports_sid = true, +}; + +static const struct of_device_id tegra_nvdec_of_match[] = { + { .compatible = "nvidia,tegra210-nvdec", .data = &nvdec_t210_config }, + { .compatible = "nvidia,tegra186-nvdec", .data = &nvdec_t186_config }, + { .compatible = "nvidia,tegra194-nvdec", .data = &nvdec_t194_config }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra_nvdec_of_match); + +static int nvdec_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct host1x_syncpt **syncpts; + struct nvdec *nvdec; + u32 host_class; + int err; + + /* inherit DMA mask from host1x parent */ + err = dma_coerce_mask_and_coherent(dev, *dev->parent->dma_mask); + if (err < 0) { + dev_err(&pdev->dev, "failed to set DMA mask: %d\n", err); + return err; + } + + nvdec = devm_kzalloc(dev, sizeof(*nvdec), GFP_KERNEL); + if (!nvdec) + return -ENOMEM; + + nvdec->config = of_device_get_match_data(dev); + + syncpts = devm_kzalloc(dev, sizeof(*syncpts), GFP_KERNEL); + if (!syncpts) + return -ENOMEM; + + nvdec->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); + if (IS_ERR(nvdec->regs)) + return PTR_ERR(nvdec->regs); + + nvdec->clk = devm_clk_get(dev, NULL); + if (IS_ERR(nvdec->clk)) { + dev_err(&pdev->dev, "failed to get clock\n"); + return PTR_ERR(nvdec->clk); + } + + err = of_property_read_u32(dev->of_node, "nvidia,host1x-class", &host_class); + if (err < 0) + host_class = HOST1X_CLASS_NVDEC; + + nvdec->falcon.dev = dev; + nvdec->falcon.regs = nvdec->regs; + + err = falcon_init(&nvdec->falcon); + if (err < 0) + return err; + + platform_set_drvdata(pdev, nvdec); + + INIT_LIST_HEAD(&nvdec->client.base.list); + nvdec->client.base.ops = &nvdec_client_ops; + nvdec->client.base.dev = dev; + nvdec->client.base.class = host_class; + nvdec->client.base.syncpts = syncpts; + nvdec->client.base.num_syncpts = 1; + nvdec->dev = dev; + + INIT_LIST_HEAD(&nvdec->client.list); + nvdec->client.version = nvdec->config->version; + nvdec->client.ops = &nvdec_ops; + + err = host1x_client_register(&nvdec->client.base); + if (err < 0) { + dev_err(dev, "failed to register host1x client: %d\n", err); + goto exit_falcon; + } + + pm_runtime_enable(&pdev->dev); + pm_runtime_set_autosuspend_delay(&pdev->dev, 500); + pm_runtime_use_autosuspend(&pdev->dev); + + return 0; + +exit_falcon: + falcon_exit(&nvdec->falcon); + + return err; +} + +static int nvdec_remove(struct platform_device *pdev) +{ + struct nvdec *nvdec = platform_get_drvdata(pdev); + int err; + + err = host1x_client_unregister(&nvdec->client.base); + if (err < 0) { + dev_err(&pdev->dev, "failed to unregister host1x client: %d\n", + err); + return err; + } + + if (pm_runtime_enabled(&pdev->dev)) + pm_runtime_disable(&pdev->dev); + else + nvdec_runtime_suspend(&pdev->dev); + + falcon_exit(&nvdec->falcon); + + return 0; +} + +static const struct dev_pm_ops nvdec_pm_ops = { + SET_RUNTIME_PM_OPS(nvdec_runtime_suspend, nvdec_runtime_resume, NULL) +}; + +struct platform_driver tegra_nvdec_driver = { + .driver = { + .name = "tegra-nvdec", + .of_match_table = tegra_nvdec_of_match, + .pm = &nvdec_pm_ops + }, + .probe = nvdec_probe, + .remove = nvdec_remove, +}; + +#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_210_NVDEC_FIRMWARE); +#endif +#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_186_NVDEC_FIRMWARE); +#endif +#if IS_ENABLED(CONFIG_ARCH_TEGRA_194_SOC) +MODULE_FIRMWARE(NVIDIA_TEGRA_194_NVDEC_FIRMWARE); +#endif diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 85eb3d19bbdb..3d4cabdbc78d 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -132,6 +132,12 @@ static const struct host1x_sid_entry tegra186_sid_table[] = { .offset = 0x30, .limit = 0x34 }, + { + /* NVDEC */ + .base = 0x1b00, + .offset = 0x30, + .limit = 0x34 + }, }; static const struct host1x_info host1x06_info = { @@ -156,6 +162,18 @@ static const struct host1x_sid_entry tegra194_sid_table[] = { .offset = 0x30, .limit = 0x34 }, + { + /* NVDEC */ + .base = 0x1b00, + .offset = 0x30, + .limit = 0x34 + }, + { + /* NVDEC1 */ + .base = 0x1bc0, + .offset = 0x30, + .limit = 0x34 + }, }; static const struct host1x_info host1x07_info = { diff --git a/include/linux/host1x.h b/include/linux/host1x.h index d0bb16cdd005..2ca53d7ed7ca 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -17,6 +17,8 @@ enum host1x_class { HOST1X_CLASS_GR2D_SB = 0x52, HOST1X_CLASS_VIC = 0x5D, HOST1X_CLASS_GR3D = 0x60, + HOST1X_CLASS_NVDEC = 0xF0, + HOST1X_CLASS_NVDEC1 = 0xF5, }; struct host1x; -- cgit v1.2.3 From 9ca790f44606109071ab1a3a37ed99e91794c37c Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Wed, 1 Dec 2021 02:23:16 +0300 Subject: gpu: host1x: Add host1x_channel_stop() Add host1x_channel_stop() which waits till channel becomes idle and then stops the channel hardware. This is needed for supporting suspend/resume by host1x drivers since the hardware state is lost after power-gating, thus the channel needs to be stopped before client enters into suspend. Tested-by: Peter Geis # Ouya T30 Tested-by: Paul Fertser # PAZ00 T20 Tested-by: Nicolas Chauvet # PAZ00 T20 and TK1 T124 Tested-by: Matt Merhar # Ouya T30 Signed-off-by: Dmitry Osipenko Signed-off-by: Thierry Reding --- drivers/gpu/host1x/channel.c | 8 ++++++++ include/linux/host1x.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/gpu/host1x/channel.c b/drivers/gpu/host1x/channel.c index 4cd212bb570d..2a9a3a8d5931 100644 --- a/drivers/gpu/host1x/channel.c +++ b/drivers/gpu/host1x/channel.c @@ -75,6 +75,14 @@ struct host1x_channel *host1x_channel_get_index(struct host1x *host, return ch; } +void host1x_channel_stop(struct host1x_channel *channel) +{ + struct host1x *host = dev_get_drvdata(channel->dev->parent); + + host1x_hw_cdma_stop(host, &channel->cdma); +} +EXPORT_SYMBOL(host1x_channel_stop); + static void release_channel(struct kref *kref) { struct host1x_channel *channel = diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 2ca53d7ed7ca..e8dc5bc41f79 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -226,6 +226,7 @@ struct host1x_job; struct host1x_channel *host1x_channel_request(struct host1x_client *client); struct host1x_channel *host1x_channel_get(struct host1x_channel *channel); +void host1x_channel_stop(struct host1x_channel *channel); void host1x_channel_put(struct host1x_channel *channel); int host1x_job_submit(struct host1x_job *job); -- cgit v1.2.3 From c0cdc89072a3e1ae3981437f385de14b7bba8fd8 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 27 Oct 2021 16:15:04 +0100 Subject: irqchip/gic-v3-its: Give the percpu rdist struct its own flags field Later patches will require tracking some per-rdist status. Reuse the bytes "lost" to padding within the __percpu rdist struct as a flags field, and re-encode ->lpi_enabled within said flags. No change in functionality intended. Signed-off-by: Valentin Schneider Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211027151506.2085066-2-valentin.schneider@arm.com --- drivers/irqchip/irq-gic-v3-its.c | 8 +++++--- include/linux/irqchip/arm-gic-v3.h | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index eb0882d15366..74c22741f3ce 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -46,6 +46,8 @@ #define RDIST_FLAGS_PROPBASE_NEEDS_FLUSHING (1 << 0) #define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1) +#define RD_LOCAL_LPI_ENABLED BIT(0) + static u32 lpi_id_bits; /* @@ -3044,7 +3046,7 @@ static void its_cpu_init_lpis(void) phys_addr_t paddr; u64 val, tmp; - if (gic_data_rdist()->lpi_enabled) + if (gic_data_rdist()->flags & RD_LOCAL_LPI_ENABLED) return; val = readl_relaxed(rbase + GICR_CTLR); @@ -3158,7 +3160,7 @@ static void its_cpu_init_lpis(void) /* Make sure the GIC has seen the above */ dsb(sy); out: - gic_data_rdist()->lpi_enabled = true; + gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(), gic_data_rdist()->pend_page ? "allocated" : "reserved", @@ -5138,7 +5140,7 @@ static int redist_disable_lpis(void) * * If running with preallocated tables, there is nothing to do. */ - if (gic_data_rdist()->lpi_enabled || + if ((gic_data_rdist()->flags & RD_LOCAL_LPI_ENABLED) || (gic_rdists->flags & RDIST_FLAGS_RD_TABLES_PREALLOCATED)) return 0; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 81cbf85f73de..0dc34d7d735a 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -615,7 +615,7 @@ struct rdists { void __iomem *rd_base; struct page *pend_page; phys_addr_t phys_base; - bool lpi_enabled; + u64 flags; cpumask_t *vpe_table_mask; void *vpe_l1_base; } __percpu *rdist; -- cgit v1.2.3 From d23bc2bc1d634658d7fa96395419c1c553a784f0 Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 27 Oct 2021 16:15:05 +0100 Subject: irqchip/gic-v3-its: Postpone LPI pending table freeing and memreserve Memory used by the LPI tables have to be made persistent for kexec to have a chance to work, as explained in [1]. If they have been made persistent and we are booting into a kexec'd kernel, we also need to free the pages that were preemptively allocated by the new kernel for those tables. Both of those operations currently happen during its_cpu_init(), which happens in a _STARTING (IOW atomic) cpuhp callback for secondary CPUs. efi_mem_reserve_iomem() issues a GFP_ATOMIC allocation, which unfortunately doesn't work under PREEMPT_RT (this ends up grabbing a non-raw spinlock, which can sleep under PREEMPT_RT). Similarly, freeing the pages ends up grabbing a sleepable spinlock. Since the memreserve is only required by kexec, it doesn't have to be done so early in the secondary boot process. Issue the reservation in a new CPUHP_AP_ONLINE_DYN cpuhp callback, and piggy-back the page freeing on top of it. A CPU gets to run the body of this new callback exactly once. As kexec issues a machine_shutdown() prior to machine_kexec(), it will be serialized vs a CPU being plugged to life by the hotplug machinery - either the CPU will have been brought up and have had its redistributor's pending table memreserved, or it never went online and will have its table allocated by the new kernel. [1]: https://lore.kernel.org/lkml/20180921195954.21574-1-marc.zyngier@arm.com/ Signed-off-by: Valentin Schneider Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211027151506.2085066-3-valentin.schneider@arm.com --- drivers/irqchip/irq-gic-v3-its.c | 58 +++++++++++++++++++++++++++++++++++--- drivers/irqchip/irq-gic-v3.c | 1 + include/linux/irqchip/arm-gic-v3.h | 1 + 3 files changed, 56 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 74c22741f3ce..f860733d3e4e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -47,6 +47,8 @@ #define RDIST_FLAGS_RD_TABLES_PREALLOCATED (1 << 1) #define RD_LOCAL_LPI_ENABLED BIT(0) +#define RD_LOCAL_PENDTABLE_PREALLOCATED BIT(1) +#define RD_LOCAL_MEMRESERVE_DONE BIT(2) static u32 lpi_id_bits; @@ -3065,15 +3067,13 @@ static void its_cpu_init_lpis(void) paddr &= GENMASK_ULL(51, 16); WARN_ON(!gic_check_reserved_range(paddr, LPI_PENDBASE_SZ)); - its_free_pending_table(gic_data_rdist()->pend_page); - gic_data_rdist()->pend_page = NULL; + gic_data_rdist()->flags |= RD_LOCAL_PENDTABLE_PREALLOCATED; goto out; } pend_page = gic_data_rdist()->pend_page; paddr = page_to_phys(pend_page); - WARN_ON(gic_reserve_range(paddr, LPI_PENDBASE_SZ)); /* set PROPBASE */ val = (gic_rdists->prop_table_pa | @@ -3163,7 +3163,8 @@ out: gic_data_rdist()->flags |= RD_LOCAL_LPI_ENABLED; pr_info("GICv3: CPU%d: using %s LPI pending table @%pa\n", smp_processor_id(), - gic_data_rdist()->pend_page ? "allocated" : "reserved", + gic_data_rdist()->flags & RD_LOCAL_PENDTABLE_PREALLOCATED ? + "reserved" : "allocated", &paddr); } @@ -5202,6 +5203,38 @@ int its_cpu_init(void) return 0; } +static int its_cpu_memreserve_lpi(unsigned int cpu) +{ + struct page *pend_page; + int ret = 0; + + /* This gets to run exactly once per CPU */ + if (gic_data_rdist()->flags & RD_LOCAL_MEMRESERVE_DONE) + return 0; + + pend_page = gic_data_rdist()->pend_page; + if (WARN_ON(!pend_page)) { + ret = -ENOMEM; + goto out; + } + /* + * If the pending table was pre-programmed, free the memory we + * preemptively allocated. Otherwise, reserve that memory for + * later kexecs. + */ + if (gic_data_rdist()->flags & RD_LOCAL_PENDTABLE_PREALLOCATED) { + its_free_pending_table(pend_page); + gic_data_rdist()->pend_page = NULL; + } else { + phys_addr_t paddr = page_to_phys(pend_page); + WARN_ON(gic_reserve_range(paddr, LPI_PENDBASE_SZ)); + } + +out: + gic_data_rdist()->flags |= RD_LOCAL_MEMRESERVE_DONE; + return ret; +} + static const struct of_device_id its_device_id[] = { { .compatible = "arm,gic-v3-its", }, {}, @@ -5385,6 +5418,23 @@ static void __init its_acpi_probe(void) static void __init its_acpi_probe(void) { } #endif +int __init its_lpi_memreserve_init(void) +{ + int state; + + if (!efi_enabled(EFI_CONFIG_TABLES)) + return 0; + + state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "irqchip/arm/gicv3/memreserve:online", + its_cpu_memreserve_lpi, + NULL); + if (state < 0) + return state; + + return 0; +} + int __init its_init(struct fwnode_handle *handle, struct rdists *rdists, struct irq_domain *parent_domain) { diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index daec3309b014..9fa3e1d16721 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1802,6 +1802,7 @@ static int __init gic_init_bases(void __iomem *dist_base, if (gic_dist_supports_lpis()) { its_init(handle, &gic_data.rdists, gic_data.domain); its_cpu_init(); + its_lpi_memreserve_init(); } else { if (IS_ENABLED(CONFIG_ARM_GIC_V2M)) gicv2m_init(handle, gic_data.domain); diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 0dc34d7d735a..51b85506ae90 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -632,6 +632,7 @@ struct rdists { struct irq_domain; struct fwnode_handle; +int __init its_lpi_memreserve_init(void); int its_cpu_init(void); int its_init(struct fwnode_handle *handle, struct rdists *rdists, struct irq_domain *domain); -- cgit v1.2.3 From 835f442fdbce33a47a6bde356643fd7e3ef7ec1b Mon Sep 17 00:00:00 2001 From: Valentin Schneider Date: Wed, 27 Oct 2021 16:15:06 +0100 Subject: irqchip/gic-v3-its: Limit memreserve cpuhp state lifetime The new memreserve cpuhp callback only needs to survive up until a point where every CPU in the system has booted once. Beyond that, it becomes a no-op and can be put in the bin. Signed-off-by: Valentin Schneider Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211027151506.2085066-4-valentin.schneider@arm.com --- drivers/irqchip/irq-gic-v3-its.c | 16 ++++++++++++++++ include/linux/irqchip/arm-gic-v3.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index f860733d3e4e..ee83eb377d7e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -5203,6 +5203,15 @@ int its_cpu_init(void) return 0; } +static void rdist_memreserve_cpuhp_cleanup_workfn(struct work_struct *work) +{ + cpuhp_remove_state_nocalls(gic_rdists->cpuhp_memreserve_state); + gic_rdists->cpuhp_memreserve_state = CPUHP_INVALID; +} + +static DECLARE_WORK(rdist_memreserve_cpuhp_cleanup_work, + rdist_memreserve_cpuhp_cleanup_workfn); + static int its_cpu_memreserve_lpi(unsigned int cpu) { struct page *pend_page; @@ -5231,6 +5240,10 @@ static int its_cpu_memreserve_lpi(unsigned int cpu) } out: + /* Last CPU being brought up gets to issue the cleanup */ + if (cpumask_equal(&cpus_booted_once_mask, cpu_possible_mask)) + schedule_work(&rdist_memreserve_cpuhp_cleanup_work); + gic_data_rdist()->flags |= RD_LOCAL_MEMRESERVE_DONE; return ret; } @@ -5425,6 +5438,7 @@ int __init its_lpi_memreserve_init(void) if (!efi_enabled(EFI_CONFIG_TABLES)) return 0; + gic_rdists->cpuhp_memreserve_state = CPUHP_INVALID; state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "irqchip/arm/gicv3/memreserve:online", its_cpu_memreserve_lpi, @@ -5432,6 +5446,8 @@ int __init its_lpi_memreserve_init(void) if (state < 0) return state; + gic_rdists->cpuhp_memreserve_state = state; + return 0; } diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 51b85506ae90..12d91f0dedf9 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -624,6 +624,7 @@ struct rdists { u64 flags; u32 gicd_typer; u32 gicd_typer2; + int cpuhp_memreserve_state; bool has_vlpis; bool has_rvpeid; bool has_direct_lpi; -- cgit v1.2.3 From 3c67d44de787dff288d7f2a51c372b22f7356db6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Dec 2021 06:48:53 -0700 Subject: block: add mq_ops->queue_rqs hook If we have a list of requests in our plug list, send it to the driver in one go, if possible. The driver must set mq_ops->queue_rqs() to support this, if not the usual one-by-one path is used. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 26 +++++++++++++++++++++++--- include/linux/blk-mq.h | 8 ++++++++ 2 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 75154cc788db..51991232824a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2553,6 +2553,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) { struct blk_mq_hw_ctx *this_hctx; struct blk_mq_ctx *this_ctx; + struct request *rq; unsigned int depth; LIST_HEAD(list); @@ -2561,7 +2562,28 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) plug->rq_count = 0; if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) { - struct request_queue *q = rq_list_peek(&plug->mq_list)->q; + struct request_queue *q; + + rq = rq_list_peek(&plug->mq_list); + q = rq->q; + + /* + * Peek first request and see if we have a ->queue_rqs() hook. + * If we do, we can dispatch the whole plug list in one go. We + * already know at this point that all requests belong to the + * same queue, caller must ensure that's the case. + * + * Since we pass off the full list to the driver at this point, + * we do not increment the active request count for the queue. + * Bypass shared tags for now because of that. + */ + if (q->mq_ops->queue_rqs && + !(rq->mq_hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { + blk_mq_run_dispatch_ops(q, + q->mq_ops->queue_rqs(&plug->mq_list)); + if (rq_list_empty(plug->mq_list)) + return; + } blk_mq_run_dispatch_ops(q, blk_mq_plug_issue_direct(plug, false)); @@ -2573,8 +2595,6 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) this_ctx = NULL; depth = 0; do { - struct request *rq; - rq = rq_list_pop(&plug->mq_list); if (!this_hctx) { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 772f8f921526..550996cf419c 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -492,6 +492,14 @@ struct blk_mq_ops { */ void (*commit_rqs)(struct blk_mq_hw_ctx *); + /** + * @queue_rqs: Queue a list of new requests. Driver is guaranteed + * that each request belongs to the same queue. If the driver doesn't + * empty the @rqlist completely, then the rest will be queued + * individually by the block layer upon return. + */ + void (*queue_rqs)(struct request **rqlist); + /** * @get_budget: Reserve budget before queue request, once .queue_rq is * run, it is driver's responsibility to release the -- cgit v1.2.3 From 8a2ba1785c5803d59a63b6320ff54fd4a37a41ce Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 9 Dec 2021 07:31:21 +0100 Subject: block: remove the nr_task field from struct io_context Nothing ever looks at ->nr_tasks, so remove it. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20211209063131.18537-2-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-ioc.c | 3 --- include/linux/iocontext.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 536fb496ad76..96336c2134ef 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -207,7 +207,6 @@ void exit_io_context(struct task_struct *task) task->io_context = NULL; task_unlock(task); - atomic_dec(&ioc->nr_tasks); put_io_context_active(ioc); } @@ -259,7 +258,6 @@ static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) return NULL; atomic_long_set(&ioc->refcount, 1); - atomic_set(&ioc->nr_tasks, 1); atomic_set(&ioc->active_ref, 1); spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); @@ -339,7 +337,6 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk) if (clone_flags & CLONE_IO) { atomic_long_inc(&ioc->refcount); atomic_inc(&ioc->active_ref); - atomic_inc(&ioc->nr_tasks); tsk->io_context = ioc; } else if (ioprio_valid(ioc->ioprio)) { tsk->io_context = alloc_io_context(GFP_KERNEL, NUMA_NO_NODE); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index c1229fbd6691..82c7f4f5f4f5 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -99,7 +99,6 @@ struct io_cq { struct io_context { atomic_long_t refcount; atomic_t active_ref; - atomic_t nr_tasks; /* all the fields below are protected by this lock */ spinlock_t lock; -- cgit v1.2.3 From a411cd3cfdc5bbd1329d5b33dbf39e2b5213969d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 9 Dec 2021 07:31:27 +0100 Subject: block: move set_task_ioprio to blk-ioc.c Keep set_task_ioprio with the other low-level code that accesses the io_context structure. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20211209063131.18537-8-hch@lst.de Signed-off-by: Jens Axboe --- block/blk-ioc.c | 34 ++++++++++++++++++++++++++++++++-- block/ioprio.c | 32 -------------------------------- include/linux/iocontext.h | 2 -- 3 files changed, 32 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/block/blk-ioc.c b/block/blk-ioc.c index f98a29ee8f36..c25ce2f3eb19 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include "blk.h" @@ -280,8 +281,8 @@ static struct io_context *create_task_io_context(struct task_struct *task, * This function always goes through task_lock() and it's better to use * %current->io_context + get_io_context() for %current. */ -struct io_context *get_task_io_context(struct task_struct *task, - gfp_t gfp_flags, int node) +static struct io_context *get_task_io_context(struct task_struct *task, + gfp_t gfp_flags, int node) { struct io_context *ioc; @@ -298,6 +299,35 @@ struct io_context *get_task_io_context(struct task_struct *task, return ioc; } +int set_task_ioprio(struct task_struct *task, int ioprio) +{ + int err; + struct io_context *ioc; + const struct cred *cred = current_cred(), *tcred; + + rcu_read_lock(); + tcred = __task_cred(task); + if (!uid_eq(tcred->uid, cred->euid) && + !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); + return -EPERM; + } + rcu_read_unlock(); + + err = security_task_setioprio(task, ioprio); + if (err) + return err; + + ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE); + if (ioc) { + ioc->ioprio = ioprio; + put_io_context(ioc); + } + + return err; +} +EXPORT_SYMBOL_GPL(set_task_ioprio); + int __copy_io(unsigned long clone_flags, struct task_struct *tsk) { struct io_context *ioc = current->io_context; diff --git a/block/ioprio.c b/block/ioprio.c index 313c14a70bbd..e118f4bf2dc6 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -22,46 +22,14 @@ */ #include #include -#include #include #include #include #include -#include -#include #include #include #include -int set_task_ioprio(struct task_struct *task, int ioprio) -{ - int err; - struct io_context *ioc; - const struct cred *cred = current_cred(), *tcred; - - rcu_read_lock(); - tcred = __task_cred(task); - if (!uid_eq(tcred->uid, cred->euid) && - !uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) { - rcu_read_unlock(); - return -EPERM; - } - rcu_read_unlock(); - - err = security_task_setioprio(task, ioprio); - if (err) - return err; - - ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE); - if (ioc) { - ioc->ioprio = ioprio; - put_io_context(ioc); - } - - return err; -} -EXPORT_SYMBOL_GPL(set_task_ioprio); - int ioprio_check_cap(int ioprio) { int class = IOPRIO_PRIO_CLASS(ioprio); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 82c7f4f5f4f5..648331f35fc6 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -116,8 +116,6 @@ struct task_struct; #ifdef CONFIG_BLOCK void put_io_context(struct io_context *ioc); void exit_io_context(struct task_struct *task); -struct io_context *get_task_io_context(struct task_struct *task, - gfp_t gfp_flags, int node); int __copy_io(unsigned long clone_flags, struct task_struct *tsk); static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk) { -- cgit v1.2.3 From 5ef1630586317e92c9ebd7b4ce48f393b7ff790f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 9 Dec 2021 07:31:31 +0100 Subject: block: only build the icq tracking code when needed Only bfq needs to code to track icq, so make it conditional. Signed-off-by: Christoph Hellwig Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/20211209063131.18537-12-hch@lst.de Signed-off-by: Jens Axboe --- block/Kconfig | 3 +++ block/Kconfig.iosched | 1 + block/blk-ioc.c | 68 ++++++++++++++++++++++++++++------------------- block/blk.h | 6 +++++ include/linux/iocontext.h | 6 +++-- 5 files changed, 55 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/block/Kconfig b/block/Kconfig index c6ce41a5e5b2..d5d4197b7ed2 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -35,6 +35,9 @@ config BLK_CGROUP_RWSTAT config BLK_DEV_BSG_COMMON tristate +config BLK_ICQ + bool + config BLK_DEV_BSGLIB bool "Block layer SG support v4 helper lib" select BLK_DEV_BSG_COMMON diff --git a/block/Kconfig.iosched b/block/Kconfig.iosched index 885fee86dfca..615516146086 100644 --- a/block/Kconfig.iosched +++ b/block/Kconfig.iosched @@ -18,6 +18,7 @@ config MQ_IOSCHED_KYBER config IOSCHED_BFQ tristate "BFQ I/O scheduler" + select BLK_ICQ help BFQ I/O scheduler for BLK-MQ. BFQ distributes the bandwidth of of the device among all processes according to their weights, diff --git a/block/blk-ioc.c b/block/blk-ioc.c index dc7fb064fd5f..87bdc9ca8295 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -19,6 +19,7 @@ */ static struct kmem_cache *iocontext_cachep; +#ifdef CONFIG_BLK_ICQ /** * get_io_context - increment reference count to io_context * @ioc: io_context to get @@ -162,6 +163,42 @@ static bool ioc_delay_free(struct io_context *ioc) return false; } +/** + * ioc_clear_queue - break any ioc association with the specified queue + * @q: request_queue being cleared + * + * Walk @q->icq_list and exit all io_cq's. + */ +void ioc_clear_queue(struct request_queue *q) +{ + LIST_HEAD(icq_list); + + spin_lock_irq(&q->queue_lock); + list_splice_init(&q->icq_list, &icq_list); + spin_unlock_irq(&q->queue_lock); + + rcu_read_lock(); + while (!list_empty(&icq_list)) { + struct io_cq *icq = + list_entry(icq_list.next, struct io_cq, q_node); + + spin_lock_irq(&icq->ioc->lock); + if (!(icq->flags & ICQ_DESTROYED)) + ioc_destroy_icq(icq); + spin_unlock_irq(&icq->ioc->lock); + } + rcu_read_unlock(); +} +#else /* CONFIG_BLK_ICQ */ +static inline void ioc_exit_icqs(struct io_context *ioc) +{ +} +static inline bool ioc_delay_free(struct io_context *ioc) +{ + return false; +} +#endif /* CONFIG_BLK_ICQ */ + /** * put_io_context - put a reference of io_context * @ioc: io_context to put @@ -193,33 +230,6 @@ void exit_io_context(struct task_struct *task) } } -/** - * ioc_clear_queue - break any ioc association with the specified queue - * @q: request_queue being cleared - * - * Walk @q->icq_list and exit all io_cq's. - */ -void ioc_clear_queue(struct request_queue *q) -{ - LIST_HEAD(icq_list); - - spin_lock_irq(&q->queue_lock); - list_splice_init(&q->icq_list, &icq_list); - spin_unlock_irq(&q->queue_lock); - - rcu_read_lock(); - while (!list_empty(&icq_list)) { - struct io_cq *icq = - list_entry(icq_list.next, struct io_cq, q_node); - - spin_lock_irq(&icq->ioc->lock); - if (!(icq->flags & ICQ_DESTROYED)) - ioc_destroy_icq(icq); - spin_unlock_irq(&icq->ioc->lock); - } - rcu_read_unlock(); -} - static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) { struct io_context *ioc; @@ -231,10 +241,12 @@ static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) atomic_long_set(&ioc->refcount, 1); atomic_set(&ioc->active_ref, 1); +#ifdef CONFIG_BLK_ICQ spin_lock_init(&ioc->lock); INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC); INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); +#endif return ioc; } @@ -300,6 +312,7 @@ int __copy_io(unsigned long clone_flags, struct task_struct *tsk) return 0; } +#ifdef CONFIG_BLK_ICQ /** * ioc_lookup_icq - lookup io_cq from ioc * @q: the associated request_queue @@ -428,6 +441,7 @@ struct io_cq *ioc_find_get_icq(struct request_queue *q) return icq; } EXPORT_SYMBOL_GPL(ioc_find_get_icq); +#endif /* CONFIG_BLK_ICQ */ static int __init blk_ioc_init(void) { diff --git a/block/blk.h b/block/blk.h index 7ccb7c7d86b3..8bd43b3ad33d 100644 --- a/block/blk.h +++ b/block/blk.h @@ -366,7 +366,13 @@ static inline unsigned int bio_aligned_discard_max_sectors( */ struct io_cq *ioc_find_get_icq(struct request_queue *q); struct io_cq *ioc_lookup_icq(struct request_queue *q); +#ifdef CONFIG_BLK_ICQ void ioc_clear_queue(struct request_queue *q); +#else +static inline void ioc_clear_queue(struct request_queue *q) +{ +} +#endif /* CONFIG_BLK_ICQ */ #ifdef CONFIG_BLK_DEV_THROTTLING_LOW extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page); diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h index 648331f35fc6..14f7eaf1b443 100644 --- a/include/linux/iocontext.h +++ b/include/linux/iocontext.h @@ -100,16 +100,18 @@ struct io_context { atomic_long_t refcount; atomic_t active_ref; + unsigned short ioprio; + +#ifdef CONFIG_BLK_ICQ /* all the fields below are protected by this lock */ spinlock_t lock; - unsigned short ioprio; - struct radix_tree_root icq_tree; struct io_cq __rcu *icq_hint; struct hlist_head icq_list; struct work_struct release_work; +#endif /* CONFIG_BLK_ICQ */ }; struct task_struct; -- cgit v1.2.3 From 85f5a74c2b9ba213d4102dc12ccbfdbe26472abb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 8 Apr 2021 01:33:45 -0400 Subject: block: Add bio_add_folio() This is a thin wrapper around bio_add_page(). The main advantage here is the documentation that folios larger than 2GiB are not supported. It's not currently possible to allocate folios that large, but if it ever becomes possible, this function will fail gracefully instead of doing I/O to the wrong bytes. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jens Axboe Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- block/bio.c | 22 ++++++++++++++++++++++ include/linux/bio.h | 3 ++- 2 files changed, 24 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index 15ab0d6d1c06..4b3087e20d51 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1033,6 +1033,28 @@ int bio_add_page(struct bio *bio, struct page *page, } EXPORT_SYMBOL(bio_add_page); +/** + * bio_add_folio - Attempt to add part of a folio to a bio. + * @bio: BIO to add to. + * @folio: Folio to add. + * @len: How many bytes from the folio to add. + * @off: First byte in this folio to add. + * + * Filesystems that use folios can call this function instead of calling + * bio_add_page() for each page in the folio. If @off is bigger than + * PAGE_SIZE, this function can create a bio_vec that starts in a page + * after the bv_page. BIOs do not support folios that are 4GiB or larger. + * + * Return: Whether the addition was successful. + */ +bool bio_add_folio(struct bio *bio, struct folio *folio, size_t len, + size_t off) +{ + if (len > UINT_MAX || off > UINT_MAX) + return 0; + return bio_add_page(bio, &folio->page, len, off) > 0; +} + void __bio_release_pages(struct bio *bio, bool mark_dirty) { struct bvec_iter_all iter_all; diff --git a/include/linux/bio.h b/include/linux/bio.h index fe6bdfbbef66..a783cac49978 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -409,7 +409,8 @@ extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); -extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); +int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off); +bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); int bio_add_zone_append_page(struct bio *bio, struct page *page, -- cgit v1.2.3 From 640d1930bef4f87ec8d8d2b05f0f6edc1dfcf662 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Jan 2021 10:58:17 -0500 Subject: block: Add bio_for_each_folio_all() Allow callers to iterate over each folio instead of each page. The bio need not have been constructed using folios originally. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jens Axboe Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- Documentation/core-api/kernel-api.rst | 1 + include/linux/bio.h | 53 ++++++++++++++++++++++++++++++++++- 2 files changed, 53 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst index 2e7186805148..7f0cb604b6ab 100644 --- a/Documentation/core-api/kernel-api.rst +++ b/Documentation/core-api/kernel-api.rst @@ -279,6 +279,7 @@ Accounting Framework Block Devices ============= +.. kernel-doc:: include/linux/bio.h .. kernel-doc:: block/blk-core.c :export: diff --git a/include/linux/bio.h b/include/linux/bio.h index a783cac49978..e3c9e8207f12 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -166,7 +166,7 @@ static inline void bio_advance(struct bio *bio, unsigned int nbytes) */ #define bio_for_each_bvec_all(bvl, bio, i) \ for (i = 0, bvl = bio_first_bvec_all(bio); \ - i < (bio)->bi_vcnt; i++, bvl++) \ + i < (bio)->bi_vcnt; i++, bvl++) #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) @@ -260,6 +260,57 @@ static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) return &bio->bi_io_vec[bio->bi_vcnt - 1]; } +/** + * struct folio_iter - State for iterating all folios in a bio. + * @folio: The current folio we're iterating. NULL after the last folio. + * @offset: The byte offset within the current folio. + * @length: The number of bytes in this iteration (will not cross folio + * boundary). + */ +struct folio_iter { + struct folio *folio; + size_t offset; + size_t length; + /* private: for use by the iterator */ + size_t _seg_count; + int _i; +}; + +static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio, + int i) +{ + struct bio_vec *bvec = bio_first_bvec_all(bio) + i; + + fi->folio = page_folio(bvec->bv_page); + fi->offset = bvec->bv_offset + + PAGE_SIZE * (bvec->bv_page - &fi->folio->page); + fi->_seg_count = bvec->bv_len; + fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count); + fi->_i = i; +} + +static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio) +{ + fi->_seg_count -= fi->length; + if (fi->_seg_count) { + fi->folio = folio_next(fi->folio); + fi->offset = 0; + fi->length = min(folio_size(fi->folio), fi->_seg_count); + } else if (fi->_i + 1 < bio->bi_vcnt) { + bio_first_folio(fi, bio, fi->_i + 1); + } else { + fi->folio = NULL; + } +} + +/** + * bio_for_each_folio_all - Iterate over each folio in a bio. + * @fi: struct folio_iter which is updated for each folio. + * @bio: struct bio to iterate over. + */ +#define bio_for_each_folio_all(fi, bio) \ + for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio)) + enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ -- cgit v1.2.3 From 8306a5f56305521d8b307b4ee1f69949fbb49279 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 28 Apr 2021 07:51:36 -0400 Subject: iomap: Add iomap_invalidate_folio Keep iomap_invalidatepage around as a wrapper for use in address_space operations. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 20 ++++++++++++-------- include/linux/iomap.h | 1 + 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index b0192b148c9f..de7ce1909527 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -479,23 +479,27 @@ iomap_releasepage(struct page *page, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(iomap_releasepage); -void -iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len) +void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len) { - struct folio *folio = page_folio(page); - - trace_iomap_invalidatepage(page->mapping->host, offset, len); + trace_iomap_invalidatepage(folio->mapping->host, offset, len); /* * If we're invalidating the entire page, clear the dirty state from it * and release it to avoid unnecessary buildup of the LRU. */ - if (offset == 0 && len == PAGE_SIZE) { - WARN_ON_ONCE(PageWriteback(page)); - cancel_dirty_page(page); + if (offset == 0 && len == folio_size(folio)) { + WARN_ON_ONCE(folio_test_writeback(folio)); + folio_cancel_dirty(folio); iomap_page_release(folio); } } +EXPORT_SYMBOL_GPL(iomap_invalidate_folio); + +void iomap_invalidatepage(struct page *page, unsigned int offset, + unsigned int len) +{ + iomap_invalidate_folio(page_folio(page), offset, len); +} EXPORT_SYMBOL_GPL(iomap_invalidatepage); #ifdef CONFIG_MIGRATION diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 6d1b08d0ae93..29491fb9c5ba 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -225,6 +225,7 @@ void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); int iomap_is_partially_uptodate(struct page *page, unsigned long from, unsigned long count); int iomap_releasepage(struct page *page, gfp_t gfp_mask); +void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len); void iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len); #ifdef CONFIG_MIGRATION -- cgit v1.2.3 From ea6fa4961aab8f90a8aa03575a98b4bda368d4b6 Mon Sep 17 00:00:00 2001 From: Mateusz Jończyk Date: Fri, 10 Dec 2021 21:01:26 +0100 Subject: rtc: mc146818-lib: fix RTC presence check MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To prevent an infinite loop in mc146818_get_time(), commit 211e5db19d15 ("rtc: mc146818: Detect and handle broken RTCs") added a check for RTC availability. Together with a later fix, it checked if bit 6 in register 0x0d is cleared. This, however, caused a false negative on a motherboard with an AMD SB710 southbridge; according to the specification [1], bit 6 of register 0x0d of this chipset is a scratchbit. This caused a regression in Linux 5.11 - the RTC was determined broken by the kernel and not used by rtc-cmos.c [3]. This problem was also reported in Fedora [4]. As a better alternative, check whether the UIP ("Update-in-progress") bit is set for longer then 10ms. If that is the case, then apparently the RTC is either absent (and all register reads return 0xff) or broken. Also limit the number of loop iterations in mc146818_get_time() to 10 to prevent an infinite loop there. The functions mc146818_get_time() and mc146818_does_rtc_work() will be refactored later in this patch series, in order to fix a separate problem with reading / setting the RTC alarm time. This is done so to avoid a confusion about what is being fixed when. In a previous approach to this problem, I implemented a check whether the RTC_HOURS register contains a value <= 24. This, however, sometimes did not work correctly on my Intel Kaby Lake laptop. According to Intel's documentation [2], "the time and date RAM locations (0-9) are disconnected from the external bus" during the update cycle so reading this register without checking the UIP bit is incorrect. [1] AMD SB700/710/750 Register Reference Guide, page 308, https://developer.amd.com/wordpress/media/2012/10/43009_sb7xx_rrg_pub_1.00.pdf [2] 7th Generation Intel ® Processor Family I/O for U/Y Platforms [...] Datasheet Volume 1 of 2, page 209 Intel's Document Number: 334658-006, https://www.intel.com/content/dam/www/public/us/en/documents/datasheets/7th-and-8th-gen-core-family-mobile-u-y-processor-lines-i-o-datasheet-vol-1.pdf [3] Functions in arch/x86/kernel/rtc.c apparently were using it. [4] https://bugzilla.redhat.com/show_bug.cgi?id=1936688 Fixes: 211e5db19d15 ("rtc: mc146818: Detect and handle broken RTCs") Fixes: ebb22a059436 ("rtc: mc146818: Dont test for bit 0-5 in Register D") Signed-off-by: Mateusz Jończyk Cc: Thomas Gleixner Cc: Alessandro Zummo Cc: Alexandre Belloni Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211210200131.153887-5-mat.jonczyk@o2.pl --- drivers/rtc/rtc-cmos.c | 10 ++++------ drivers/rtc/rtc-mc146818-lib.c | 34 ++++++++++++++++++++++++++++++---- include/linux/mc146818rtc.h | 1 + 3 files changed, 35 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c index d0f58cca5c20..b90a603d6b12 100644 --- a/drivers/rtc/rtc-cmos.c +++ b/drivers/rtc/rtc-cmos.c @@ -800,16 +800,14 @@ cmos_do_probe(struct device *dev, struct resource *ports, int rtc_irq) rename_region(ports, dev_name(&cmos_rtc.rtc->dev)); - spin_lock_irq(&rtc_lock); - - /* Ensure that the RTC is accessible. Bit 6 must be 0! */ - if ((CMOS_READ(RTC_VALID) & 0x40) != 0) { - spin_unlock_irq(&rtc_lock); - dev_warn(dev, "not accessible\n"); + if (!mc146818_does_rtc_work()) { + dev_warn(dev, "broken or not accessible\n"); retval = -ENXIO; goto cleanup1; } + spin_lock_irq(&rtc_lock); + if (!(flags & CMOS_RTC_FLAGS_NOFREQ)) { /* force periodic irq to CMOS reset default of 1024Hz; * diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index ccd974b8a75a..d8e67a01220e 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -8,10 +8,36 @@ #include #endif +/* + * If the UIP (Update-in-progress) bit of the RTC is set for more then + * 10ms, the RTC is apparently broken or not present. + */ +bool mc146818_does_rtc_work(void) +{ + int i; + unsigned char val; + unsigned long flags; + + for (i = 0; i < 10; i++) { + spin_lock_irqsave(&rtc_lock, flags); + val = CMOS_READ(RTC_FREQ_SELECT); + spin_unlock_irqrestore(&rtc_lock, flags); + + if ((val & RTC_UIP) == 0) + return true; + + mdelay(1); + } + + return false; +} +EXPORT_SYMBOL_GPL(mc146818_does_rtc_work); + unsigned int mc146818_get_time(struct rtc_time *time) { unsigned char ctrl; unsigned long flags; + unsigned int iter_count = 0; unsigned char century = 0; bool retry; @@ -20,13 +46,13 @@ unsigned int mc146818_get_time(struct rtc_time *time) #endif again: - spin_lock_irqsave(&rtc_lock, flags); - /* Ensure that the RTC is accessible. Bit 6 must be 0! */ - if (WARN_ON_ONCE((CMOS_READ(RTC_VALID) & 0x40) != 0)) { - spin_unlock_irqrestore(&rtc_lock, flags); + if (iter_count > 10) { memset(time, 0, sizeof(*time)); return -EIO; } + iter_count++; + + spin_lock_irqsave(&rtc_lock, flags); /* * Check whether there is an update in progress during which the diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 0661af17a758..69c80c4325bf 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -123,6 +123,7 @@ struct cmos_rtc_board_info { #define RTC_IO_EXTENT_USED RTC_IO_EXTENT #endif /* ARCH_RTC_LOCATION */ +bool mc146818_does_rtc_work(void); unsigned int mc146818_get_time(struct rtc_time *time); int mc146818_set_time(struct rtc_time *time); -- cgit v1.2.3 From ec5895c0f2d87b9bf4185db1915e40fa6fcfc0ac Mon Sep 17 00:00:00 2001 From: Mateusz Jończyk Date: Fri, 10 Dec 2021 21:01:27 +0100 Subject: rtc: mc146818-lib: extract mc146818_avoid_UIP MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Function mc146818_get_time() contains an elaborate mechanism of reading the RTC time while no RTC update is in progress. It turns out that reading the RTC alarm clock also requires avoiding the RTC update. Therefore, the mechanism in mc146818_get_time() should be reused - so extract it into a separate function. The logic in mc146818_avoid_UIP() is same as in mc146818_get_time() except that after every if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { there is now "mdelay(1)". To avoid producing a very unreadable patch, mc146818_get_time() will be refactored to use mc146818_avoid_UIP() in the next patch. Signed-off-by: Mateusz Jończyk Cc: Alessandro Zummo Cc: Alexandre Belloni Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211210200131.153887-6-mat.jonczyk@o2.pl --- drivers/rtc/rtc-mc146818-lib.c | 70 ++++++++++++++++++++++++++++++++++++++++++ include/linux/mc146818rtc.h | 3 ++ 2 files changed, 73 insertions(+) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index d8e67a01220e..b20f4ebb2f3a 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -8,6 +8,76 @@ #include #endif +/* + * Execute a function while the UIP (Update-in-progress) bit of the RTC is + * unset. + * + * Warning: callback may be executed more then once. + */ +bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + void *param) +{ + int i; + unsigned long flags; + unsigned char seconds; + + for (i = 0; i < 10; i++) { + spin_lock_irqsave(&rtc_lock, flags); + + /* + * Check whether there is an update in progress during which the + * readout is unspecified. The maximum update time is ~2ms. Poll + * every msec for completion. + * + * Store the second value before checking UIP so a long lasting + * NMI which happens to hit after the UIP check cannot make + * an update cycle invisible. + */ + seconds = CMOS_READ(RTC_SECONDS); + + if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { + spin_unlock_irqrestore(&rtc_lock, flags); + mdelay(1); + continue; + } + + /* Revalidate the above readout */ + if (seconds != CMOS_READ(RTC_SECONDS)) { + spin_unlock_irqrestore(&rtc_lock, flags); + continue; + } + + if (callback) + callback(seconds, param); + + /* + * Check for the UIP bit again. If it is set now then + * the above values may contain garbage. + */ + if (CMOS_READ(RTC_FREQ_SELECT) & RTC_UIP) { + spin_unlock_irqrestore(&rtc_lock, flags); + mdelay(1); + continue; + } + + /* + * A NMI might have interrupted the above sequence so check + * whether the seconds value has changed which indicates that + * the NMI took longer than the UIP bit was set. Unlikely, but + * possible and there is also virt... + */ + if (seconds != CMOS_READ(RTC_SECONDS)) { + spin_unlock_irqrestore(&rtc_lock, flags); + continue; + } + spin_unlock_irqrestore(&rtc_lock, flags); + + return true; + } + return false; +} +EXPORT_SYMBOL_GPL(mc146818_avoid_UIP); + /* * If the UIP (Update-in-progress) bit of the RTC is set for more then * 10ms, the RTC is apparently broken or not present. diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 69c80c4325bf..67fb0a12becc 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -127,4 +127,7 @@ bool mc146818_does_rtc_work(void); unsigned int mc146818_get_time(struct rtc_time *time); int mc146818_set_time(struct rtc_time *time); +bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), + void *param); + #endif /* _MC146818RTC_H */ -- cgit v1.2.3 From 34fff62827b254f8a43633cc878deb04bf11297c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:18:54 +0100 Subject: device: Move MSI related data into a struct The only unconditional part of MSI data in struct device is the irqdomain pointer. Everything else can be allocated on demand. Create a data structure and move the irqdomain pointer into it. The other MSI specific parts are going to be removed from struct device in later steps. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Arnd Bergmann Link: https://lore.kernel.org/r/20211210221813.617178827@linutronix.de --- drivers/base/platform-msi.c | 12 ++++++------ drivers/dma/ti/k3-udma.c | 4 ++-- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 2 +- drivers/irqchip/irq-mvebu-icu.c | 6 +++--- drivers/soc/ti/k3-ringacc.c | 4 ++-- drivers/soc/ti/ti_sci_inta_msi.c | 2 +- include/linux/device.h | 20 ++++++++++++++------ 7 files changed, 29 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 3d6c8f9caf43..f1f0876510a4 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -210,10 +210,10 @@ platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec, * accordingly (which would impact the max number of MSI * capable devices). */ - if (!dev->msi_domain || !write_msi_msg || !nvec || nvec > MAX_DEV_MSIS) + if (!dev->msi.domain || !write_msi_msg || !nvec || nvec > MAX_DEV_MSIS) return ERR_PTR(-EINVAL); - if (dev->msi_domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) { + if (dev->msi.domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) { dev_err(dev, "Incompatible msi_domain, giving up\n"); return ERR_PTR(-EINVAL); } @@ -269,7 +269,7 @@ int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, if (err) goto out_free_priv_data; - err = msi_domain_alloc_irqs(dev->msi_domain, dev, nvec); + err = msi_domain_alloc_irqs(dev->msi.domain, dev, nvec); if (err) goto out_free_desc; @@ -282,7 +282,7 @@ int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, return 0; out_free_irqs: - msi_domain_free_irqs(dev->msi_domain, dev); + msi_domain_free_irqs(dev->msi.domain, dev); out_free_desc: platform_msi_free_descs(dev, 0, nvec); out_free_priv_data: @@ -306,7 +306,7 @@ void platform_msi_domain_free_irqs(struct device *dev) platform_msi_free_priv_data(desc->platform.msi_priv_data); } - msi_domain_free_irqs(dev->msi_domain, dev); + msi_domain_free_irqs(dev->msi.domain, dev); platform_msi_free_descs(dev, 0, MAX_DEV_MSIS); } EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); @@ -354,7 +354,7 @@ __platform_msi_create_device_domain(struct device *dev, return NULL; data->host_data = host_data; - domain = irq_domain_create_hierarchy(dev->msi_domain, 0, + domain = irq_domain_create_hierarchy(dev->msi.domain, 0, is_tree ? 0 : nvec, dev->fwnode, ops, data); if (!domain) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 041d8e32d630..20edd0bf3e8b 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -5279,9 +5279,9 @@ static int udma_probe(struct platform_device *pdev) if (IS_ERR(ud->ringacc)) return PTR_ERR(ud->ringacc); - dev->msi_domain = of_msi_get_domain(dev, dev->of_node, + dev->msi.domain = of_msi_get_domain(dev, dev->of_node, DOMAIN_BUS_TI_SCI_INTA_MSI); - if (!dev->msi_domain) { + if (!dev->msi.domain) { dev_err(dev, "Failed to get MSI domain\n"); return -EPROBE_DEFER; } diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index f5848b351b19..5ba9006ec550 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3170,7 +3170,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) if (!(smmu->features & ARM_SMMU_FEAT_MSI)) return; - if (!dev->msi_domain) { + if (!dev->msi.domain) { dev_info(smmu->dev, "msi_domain absent - falling back to wired irqs\n"); return; } diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c index 3e7297fc5948..4a4a65a6f632 100644 --- a/drivers/irqchip/irq-mvebu-icu.c +++ b/drivers/irqchip/irq-mvebu-icu.c @@ -314,12 +314,12 @@ static int mvebu_icu_subset_probe(struct platform_device *pdev) msi_data->subset_data = of_device_get_match_data(dev); } - dev->msi_domain = of_msi_get_domain(dev, dev->of_node, + dev->msi.domain = of_msi_get_domain(dev, dev->of_node, DOMAIN_BUS_PLATFORM_MSI); - if (!dev->msi_domain) + if (!dev->msi.domain) return -EPROBE_DEFER; - msi_parent_dn = irq_domain_get_of_node(dev->msi_domain); + msi_parent_dn = irq_domain_get_of_node(dev->msi.domain); if (!msi_parent_dn) return -ENODEV; diff --git a/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c index 312ba0f98ad7..26159a5eef88 100644 --- a/drivers/soc/ti/k3-ringacc.c +++ b/drivers/soc/ti/k3-ringacc.c @@ -1356,9 +1356,9 @@ static int k3_ringacc_init(struct platform_device *pdev, struct resource *res; int ret, i; - dev->msi_domain = of_msi_get_domain(dev, dev->of_node, + dev->msi.domain = of_msi_get_domain(dev, dev->of_node, DOMAIN_BUS_TI_SCI_INTA_MSI); - if (!dev->msi_domain) { + if (!dev->msi.domain) { dev_err(dev, "Failed to get MSI domain\n"); return -EPROBE_DEFER; } diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c index a1d9c027022a..428a482df0f2 100644 --- a/drivers/soc/ti/ti_sci_inta_msi.c +++ b/drivers/soc/ti/ti_sci_inta_msi.c @@ -140,7 +140,7 @@ EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_alloc_irqs); void ti_sci_inta_msi_domain_free_irqs(struct device *dev) { - msi_domain_free_irqs(dev->msi_domain, dev); + msi_domain_free_irqs(dev->msi.domain, dev); ti_sci_inta_msi_free_descs(dev); } EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_free_irqs); diff --git a/include/linux/device.h b/include/linux/device.h index 2a22875238a6..f212b7a7b156 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -371,6 +371,16 @@ struct dev_links_info { enum dl_dev_state status; }; +/** + * struct dev_msi_info - Device data related to MSI + * @domain: The MSI interrupt domain associated to the device + */ +struct dev_msi_info { +#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN + struct irq_domain *domain; +#endif +}; + /** * struct device - The basic device structure * @parent: The device's "parent" device, the device to which it is attached. @@ -407,8 +417,8 @@ struct dev_links_info { * @em_pd: device's energy model performance domain * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. + * @msi: MSI related data * @msi_list: Hosts MSI descriptors - * @msi_domain: The generic MSI domain this device is using. * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). @@ -500,12 +510,10 @@ struct device { struct em_perf_domain *em_pd; #endif -#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - struct irq_domain *msi_domain; -#endif #ifdef CONFIG_PINCTRL struct dev_pin_info *pins; #endif + struct dev_msi_info msi; #ifdef CONFIG_GENERIC_MSI_IRQ struct list_head msi_list; #endif @@ -666,7 +674,7 @@ static inline void set_dev_node(struct device *dev, int node) static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - return dev->msi_domain; + return dev->msi.domain; #else return NULL; #endif @@ -675,7 +683,7 @@ static inline struct irq_domain *dev_get_msi_domain(const struct device *dev) static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d) { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN - dev->msi_domain = d; + dev->msi.domain = d; #endif } -- cgit v1.2.3 From 013bd8e543c2c777b586cf033c588ea82bd502db Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:18:55 +0100 Subject: device: Add device:: Msi_data pointer and struct msi_device_data Create struct msi_device_data and add a pointer of that type to struct dev_msi_info, which is part of struct device. Provide an allocator function which can be invoked from the MSI interrupt allocation code pathes. Add a properties field to the data structure as a first member so the allocation size is not zero bytes. The field will be uses later on. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221813.676660809@linutronix.de --- include/linux/device.h | 5 +++++ include/linux/msi.h | 18 ++++++++++++++++++ kernel/irq/msi.c | 32 ++++++++++++++++++++++++++++++++ 3 files changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/device.h b/include/linux/device.h index f212b7a7b156..f0033cd93631 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -45,6 +45,7 @@ struct iommu_ops; struct iommu_group; struct dev_pin_info; struct dev_iommu; +struct msi_device_data; /** * struct subsys_interface - interfaces to device functions @@ -374,11 +375,15 @@ struct dev_links_info { /** * struct dev_msi_info - Device data related to MSI * @domain: The MSI interrupt domain associated to the device + * @data: Pointer to MSI device data */ struct dev_msi_info { #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN struct irq_domain *domain; #endif +#ifdef CONFIG_GENERIC_MSI_IRQ + struct msi_device_data *data; +#endif }; /** diff --git a/include/linux/msi.h b/include/linux/msi.h index ba4a39c430b5..7e4c8fd7c65d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -171,6 +171,16 @@ struct msi_desc { }; }; +/** + * msi_device_data - MSI per device data + * @properties: MSI properties which are interesting to drivers + */ +struct msi_device_data { + unsigned long properties; +}; + +int msi_setup_device_data(struct device *dev); + /* Helpers to hide struct msi_desc implementation details */ #define msi_desc_to_dev(desc) ((desc)->dev) #define dev_to_msi_list(dev) (&(dev)->msi_list) @@ -233,10 +243,16 @@ void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); #ifdef CONFIG_SYSFS +int msi_device_populate_sysfs(struct device *dev); +void msi_device_destroy_sysfs(struct device *dev); + const struct attribute_group **msi_populate_sysfs(struct device *dev); void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups); #else +static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } +static inline void msi_device_destroy_sysfs(struct device *dev) { } + static inline const struct attribute_group **msi_populate_sysfs(struct device *dev) { return NULL; @@ -384,6 +400,8 @@ enum { MSI_FLAG_MUST_REACTIVATE = (1 << 5), /* Is level-triggered capable, using two messages */ MSI_FLAG_LEVEL_CAPABLE = (1 << 6), + /* Populate sysfs on alloc() and destroy it on free() */ + MSI_FLAG_DEV_SYSFS = (1 << 7), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index b3f73ef0376c..6bca6ad9bf69 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -73,6 +73,38 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) } EXPORT_SYMBOL_GPL(get_cached_msi_msg); +static void msi_device_data_release(struct device *dev, void *res) +{ + WARN_ON_ONCE(!list_empty(&dev->msi_list)); + dev->msi.data = NULL; +} + +/** + * msi_setup_device_data - Setup MSI device data + * @dev: Device for which MSI device data should be set up + * + * Return: 0 on success, appropriate error code otherwise + * + * This can be called more than once for @dev. If the MSI device data is + * already allocated the call succeeds. The allocated memory is + * automatically released when the device is destroyed. + */ +int msi_setup_device_data(struct device *dev) +{ + struct msi_device_data *md; + + if (dev->msi.data) + return 0; + + md = devres_alloc(msi_device_data_release, sizeof(*md), GFP_KERNEL); + if (!md) + return -ENOMEM; + + dev->msi.data = md; + devres_add(dev, md); + return 0; +} + #ifdef CONFIG_SYSFS static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, char *buf) -- cgit v1.2.3 From 3f35d2cf9fbc656db82579d849cc69c373b1ad0d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Wed, 15 Dec 2021 18:16:44 +0100 Subject: PCI/MSI: Decouple MSI[-X] disable from pcim_release() The MSI core will introduce runtime allocation of MSI related data. This data will be devres managed and has to be set up before enabling PCI/MSI[-X]. This would introduce an ordering issue vs. pcim_release(). The setup order is: pcim_enable_device() devres_alloc(pcim_release...); ... pci_irq_alloc() msi_setup_device_data() devres_alloc(msi_device_data_release, ...) and once the device is released these release functions are invoked in the opposite order: msi_device_data_release() ... pcim_release() pci_disable_msi[x]() which is obviously wrong, because pci_disable_msi[x]() requires the MSI data to be available to tear down the MSI[-X] interrupts. Remove the MSI[-X] teardown from pcim_release() and add an explicit action to be installed on the attempt of enabling PCI/MSI[-X]. This allows the MSI core data allocation to be ordered correctly in a subsequent step. Reported-by: Nishanth Menon Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/87tuf9rdoj.ffs@tglx --- drivers/pci/msi/msi.c | 33 +++++++++++++++++++++++++++++++++ drivers/pci/pci.c | 5 ----- include/linux/pci.h | 3 ++- 3 files changed, 35 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 5af8d9b6d424..358b63e507e9 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -341,6 +341,31 @@ void pci_restore_msi_state(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_restore_msi_state); +static void pcim_msi_release(void *pcidev) +{ + struct pci_dev *dev = pcidev; + + dev->is_msi_managed = false; + pci_free_irq_vectors(dev); +} + +/* + * Needs to be separate from pcim_release to prevent an ordering problem + * vs. msi_device_data_release() in the MSI core code. + */ +static int pcim_setup_msi_release(struct pci_dev *dev) +{ + int ret; + + if (!pci_is_managed(dev) || dev->is_msi_managed) + return 0; + + ret = devm_add_action(&dev->dev, pcim_msi_release, dev); + if (!ret) + dev->is_msi_managed = true; + return ret; +} + static struct msi_desc * msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) { @@ -884,6 +909,10 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, if (nvec > maxvec) nvec = maxvec; + rc = pcim_setup_msi_release(dev); + if (rc) + return rc; + for (;;) { if (affd) { nvec = irq_calc_affinity_vectors(minvec, nvec, affd); @@ -927,6 +956,10 @@ static int __pci_enable_msix_range(struct pci_dev *dev, if (WARN_ON_ONCE(dev->msix_enabled)) return -EINVAL; + rc = pcim_setup_msi_release(dev); + if (rc) + return rc; + for (;;) { if (affd) { nvec = irq_calc_affinity_vectors(minvec, nvec, affd); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 3d2fb394986a..f3f606c232a8 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2024,11 +2024,6 @@ static void pcim_release(struct device *gendev, void *res) struct pci_devres *this = res; int i; - if (dev->msi_enabled) - pci_disable_msi(dev); - if (dev->msix_enabled) - pci_disable_msix(dev); - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) if (this->region_mask & (1 << i)) pci_release_region(dev, i); diff --git a/include/linux/pci.h b/include/linux/pci.h index 5cc46baef519..a09736d3e05e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -425,7 +425,8 @@ struct pci_dev { unsigned int ats_enabled:1; /* Address Translation Svc */ unsigned int pasid_enabled:1; /* Process Address Space ID */ unsigned int pri_enabled:1; /* Page Request Interface */ - unsigned int is_managed:1; + unsigned int is_managed:1; /* Managed via devres */ + unsigned int is_msi_managed:1; /* MSI release via devres installed */ unsigned int needs_freset:1; /* Requires fundamental reset */ unsigned int state_saved:1; unsigned int is_physfn:1; -- cgit v1.2.3 From bf6e054e0e3fbc9614355b760e18c8a14f952a4e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:03 +0100 Subject: genirq/msi: Provide msi_device_populate/destroy_sysfs() Add new allocation functions which can be activated by domain info flags. They store the groups pointer in struct msi_device_data. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221813.988659194@linutronix.de --- include/linux/msi.h | 4 ++++ kernel/irq/msi.c | 42 ++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 44 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 7e4c8fd7c65d..1b96dc483b88 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -56,6 +56,8 @@ struct irq_data; struct msi_desc; struct pci_dev; struct platform_msi_priv_data; +struct attribute_group; + void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); @@ -174,9 +176,11 @@ struct msi_desc { /** * msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers + * @attrs: Pointer to the sysfs attribute group */ struct msi_device_data { unsigned long properties; + const struct attribute_group **attrs; }; int msi_setup_device_data(struct device *dev); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 6bca6ad9bf69..dd65e678a46c 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -199,6 +199,20 @@ error_attrs: return ERR_PTR(ret); } +/** + * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device + * @dev: The device (PCI, platform etc) which will get sysfs entries + */ +int msi_device_populate_sysfs(struct device *dev) +{ + const struct attribute_group **group = msi_populate_sysfs(dev); + + if (IS_ERR(group)) + return PTR_ERR(group); + dev->msi.data->attrs = group; + return 0; +} + /** * msi_destroy_sysfs - Destroy msi_irqs sysfs entries for devices * @dev: The device(PCI, platform etc) who will remove sysfs entries @@ -225,6 +239,17 @@ void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_ir kfree(msi_irq_groups); } } + +/** + * msi_device_destroy_sysfs - Destroy msi_irqs sysfs entries for a device + * @dev: The device (PCI, platform etc) for which to remove + * sysfs entries + */ +void msi_device_destroy_sysfs(struct device *dev) +{ + msi_destroy_sysfs(dev, dev->msi.data->attrs); + dev->msi.data->attrs = NULL; +} #endif #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN @@ -672,8 +697,19 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; + int ret; + + ret = ops->domain_alloc_irqs(domain, dev, nvec); + if (ret) + return ret; + + if (!(info->flags & MSI_FLAG_DEV_SYSFS)) + return 0; - return ops->domain_alloc_irqs(domain, dev, nvec); + ret = msi_device_populate_sysfs(dev); + if (ret) + msi_domain_free_irqs(domain, dev); + return ret; } void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) @@ -712,7 +748,9 @@ void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; - return ops->domain_free_irqs(domain, dev); + if (info->flags & MSI_FLAG_DEV_SYSFS) + msi_device_destroy_sysfs(dev); + ops->domain_free_irqs(domain, dev); } /** -- cgit v1.2.3 From ffd84485e6beb9cad3e5a133d88201b995298c33 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:05 +0100 Subject: PCI/MSI: Let the irq code handle sysfs groups Set the domain info flag which makes the core code handle sysfs groups and put an explicit invocation into the legacy code. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211210221814.048612053@linutronix.de --- drivers/pci/msi/irqdomain.c | 2 +- drivers/pci/msi/legacy.c | 6 +++++- drivers/pci/msi/msi.c | 23 ----------------------- include/linux/pci.h | 1 - 4 files changed, 6 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index a5546900244d..26b23a1c4f60 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -159,7 +159,7 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); - info->flags |= MSI_FLAG_ACTIVATE_EARLY; + info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS; if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) info->flags |= MSI_FLAG_MUST_REACTIVATE; diff --git a/drivers/pci/msi/legacy.c b/drivers/pci/msi/legacy.c index d52cff17b694..773f35122bbb 100644 --- a/drivers/pci/msi/legacy.c +++ b/drivers/pci/msi/legacy.c @@ -70,10 +70,14 @@ int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { int ret = arch_setup_msi_irqs(dev, nvec, type); - return pci_msi_setup_check_result(dev, type, ret); + ret = pci_msi_setup_check_result(dev, type, ret); + if (!ret) + ret = msi_device_populate_sysfs(&dev->dev); + return ret; } void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev) { + msi_device_destroy_sysfs(&dev->dev); arch_teardown_msi_irqs(dev); } diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 369e3c5827b2..76c15be8e1cc 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -233,11 +233,6 @@ static void free_msi_irqs(struct pci_dev *dev) for (i = 0; i < entry->nvec_used; i++) BUG_ON(irq_has_action(entry->irq + i)); - if (dev->msi_irq_groups) { - msi_destroy_sysfs(&dev->dev, dev->msi_irq_groups); - dev->msi_irq_groups = NULL; - } - pci_msi_teardown_msi_irqs(dev); list_for_each_entry_safe(entry, tmp, msi_list, list) { @@ -455,7 +450,6 @@ static int msi_verify_entries(struct pci_dev *dev) static int msi_capability_init(struct pci_dev *dev, int nvec, struct irq_affinity *affd) { - const struct attribute_group **groups; struct msi_desc *entry; int ret; @@ -486,14 +480,6 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, if (ret) goto err; - groups = msi_populate_sysfs(&dev->dev); - if (IS_ERR(groups)) { - ret = PTR_ERR(groups); - goto err; - } - - dev->msi_irq_groups = groups; - /* Set MSI enabled bits */ pci_intx_for_msi(dev, 0); pci_msi_set_enable(dev, 1); @@ -622,7 +608,6 @@ static void msix_mask_all(void __iomem *base, int tsize) static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, int nvec, struct irq_affinity *affd) { - const struct attribute_group **groups; void __iomem *base; int ret, tsize; u16 control; @@ -664,14 +649,6 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, msix_update_entries(dev, entries); - groups = msi_populate_sysfs(&dev->dev); - if (IS_ERR(groups)) { - ret = PTR_ERR(groups); - goto out_free; - } - - dev->msi_irq_groups = groups; - /* Disable INTX */ pci_intx_for_msi(dev, 0); diff --git a/include/linux/pci.h b/include/linux/pci.h index a09736d3e05e..0a7b6b2f163b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -476,7 +476,6 @@ struct pci_dev { #ifdef CONFIG_PCI_MSI void __iomem *msix_base; raw_spinlock_t msi_lock; - const struct attribute_group **msi_irq_groups; #endif struct pci_vpd vpd; #ifdef CONFIG_PCIE_DPC -- cgit v1.2.3 From 24cff375fdb663c2238f06693a067b9219596fdc Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:08 +0100 Subject: genirq/msi: Remove the original sysfs interfaces No more users. Refactor the core code accordingly and move the global interface under CONFIG_PCI_MSI_ARCH_FALLBACKS. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.168362229@linutronix.de --- include/linux/msi.h | 18 +++--------------- kernel/irq/msi.c | 53 ++++++++++++++++++++--------------------------------- 2 files changed, 23 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 1b96dc483b88..634a12962e72 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -249,22 +249,10 @@ void pci_msi_unmask_irq(struct irq_data *data); #ifdef CONFIG_SYSFS int msi_device_populate_sysfs(struct device *dev); void msi_device_destroy_sysfs(struct device *dev); - -const struct attribute_group **msi_populate_sysfs(struct device *dev); -void msi_destroy_sysfs(struct device *dev, - const struct attribute_group **msi_irq_groups); -#else +#else /* CONFIG_SYSFS */ static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } static inline void msi_device_destroy_sysfs(struct device *dev) { } - -static inline const struct attribute_group **msi_populate_sysfs(struct device *dev) -{ - return NULL; -} -static inline void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups) -{ -} -#endif +#endif /* !CONFIG_SYSFS */ /* * The arch hooks to setup up msi irqs. Default functions are implemented @@ -279,7 +267,7 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); -#endif +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* * The restore hook is still available even for fully irq domain based diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index dd65e678a46c..8e433f1a24fb 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -118,12 +118,8 @@ static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, /** * msi_populate_sysfs - Populate msi_irqs sysfs entries for devices * @dev: The device(PCI, platform etc) who will get sysfs entries - * - * Return attribute_group ** so that specific bus MSI can save it to - * somewhere during initilizing msi irqs. If devices has no MSI irq, - * return NULL; if it fails to populate sysfs, return ERR_PTR */ -const struct attribute_group **msi_populate_sysfs(struct device *dev) +static const struct attribute_group **msi_populate_sysfs(struct device *dev) { const struct attribute_group **msi_irq_groups; struct attribute **msi_attrs, *msi_attr; @@ -213,33 +209,6 @@ int msi_device_populate_sysfs(struct device *dev) return 0; } -/** - * msi_destroy_sysfs - Destroy msi_irqs sysfs entries for devices - * @dev: The device(PCI, platform etc) who will remove sysfs entries - * @msi_irq_groups: attribute_group for device msi_irqs entries - */ -void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups) -{ - struct device_attribute *dev_attr; - struct attribute **msi_attrs; - int count = 0; - - if (msi_irq_groups) { - sysfs_remove_groups(&dev->kobj, msi_irq_groups); - msi_attrs = msi_irq_groups[0]->attrs; - while (msi_attrs[count]) { - dev_attr = container_of(msi_attrs[count], - struct device_attribute, attr); - kfree(dev_attr->attr.name); - kfree(dev_attr); - ++count; - } - kfree(msi_attrs); - kfree(msi_irq_groups[0]); - kfree(msi_irq_groups); - } -} - /** * msi_device_destroy_sysfs - Destroy msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) for which to remove @@ -247,8 +216,26 @@ void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_ir */ void msi_device_destroy_sysfs(struct device *dev) { - msi_destroy_sysfs(dev, dev->msi.data->attrs); + const struct attribute_group **msi_irq_groups = dev->msi.data->attrs; + struct device_attribute *dev_attr; + struct attribute **msi_attrs; + int count = 0; + dev->msi.data->attrs = NULL; + if (!msi_irq_groups) + return; + + sysfs_remove_groups(&dev->kobj, msi_irq_groups); + msi_attrs = msi_irq_groups[0]->attrs; + while (msi_attrs[count]) { + dev_attr = container_of(msi_attrs[count], struct device_attribute, attr); + kfree(dev_attr->attr.name); + kfree(dev_attr); + ++count; + } + kfree(msi_attrs); + kfree(msi_irq_groups[0]); + kfree(msi_irq_groups); } #endif -- cgit v1.2.3 From 9835cec6d557b0bff3d48bd91cd0484aba59386c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:09 +0100 Subject: platform-msi: Rename functions and clarify comments It's hard to distinguish what platform_msi_domain_alloc() and platform_msi_domain_alloc_irqs() are about. Make the distinction more explicit and add comments which explain the use cases properly. Signed-off-by: Thomas Gleixner Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.228706214@linutronix.de --- drivers/base/platform-msi.c | 36 +++++++++++++++++++++--------------- drivers/irqchip/irq-mbigen.c | 4 ++-- drivers/irqchip/irq-mvebu-icu.c | 6 +++--- include/linux/msi.h | 8 ++++---- 4 files changed, 30 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 5d50793dded6..46ee9554717b 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -313,17 +313,18 @@ EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); * a platform-msi domain * @domain: The platform-msi domain * - * Returns the private data provided when calling - * platform_msi_create_device_domain. + * Return: The private data provided when calling + * platform_msi_create_device_domain(). */ void *platform_msi_get_host_data(struct irq_domain *domain) { struct platform_msi_priv_data *data = domain->host_data; + return data->host_data; } /** - * __platform_msi_create_device_domain - Create a platform-msi domain + * __platform_msi_create_device_domain - Create a platform-msi device domain * * @dev: The device generating the MSIs * @nvec: The number of MSIs that need to be allocated @@ -332,7 +333,11 @@ void *platform_msi_get_host_data(struct irq_domain *domain) * @ops: The hierarchy domain operations to use * @host_data: Private data associated to this domain * - * Returns an irqdomain for @nvec interrupts + * Return: An irqdomain for @nvec interrupts on success, NULL in case of error. + * + * This is for interrupt domains which stack on a platform-msi domain + * created by platform_msi_create_irq_domain(). @dev->msi.domain points to + * that platform-msi domain which is the parent for the new domain. */ struct irq_domain * __platform_msi_create_device_domain(struct device *dev, @@ -372,18 +377,19 @@ free_priv: } /** - * platform_msi_domain_free - Free interrupts associated with a platform-msi - * domain + * platform_msi_device_domain_free - Free interrupts associated with a platform-msi + * device domain * - * @domain: The platform-msi domain + * @domain: The platform-msi device domain * @virq: The base irq from which to perform the free operation * @nvec: How many interrupts to free from @virq */ -void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nvec) +void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nvec) { struct platform_msi_priv_data *data = domain->host_data; struct msi_desc *desc, *tmp; + for_each_msi_entry_safe(desc, tmp, data->dev) { if (WARN_ON(!desc->irq || desc->nvec_used != 1)) return; @@ -397,10 +403,10 @@ void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, } /** - * platform_msi_domain_alloc - Allocate interrupts associated with - * a platform-msi domain + * platform_msi_device_domain_alloc - Allocate interrupts associated with + * a platform-msi device domain * - * @domain: The platform-msi domain + * @domain: The platform-msi device domain * @virq: The base irq from which to perform the allocate operation * @nr_irqs: How many interrupts to free from @virq * @@ -408,8 +414,8 @@ void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, * with irq_domain_mutex held (which can only be done as part of a * top-level interrupt allocation). */ -int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs) +int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { struct platform_msi_priv_data *data = domain->host_data; int err; @@ -421,7 +427,7 @@ int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, err = msi_domain_populate_irqs(domain->parent, data->dev, virq, nr_irqs, &data->arg); if (err) - platform_msi_domain_free(domain, virq, nr_irqs); + platform_msi_device_domain_free(domain, virq, nr_irqs); return err; } diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c index 12df2162108e..f3faf5c99770 100644 --- a/drivers/irqchip/irq-mbigen.c +++ b/drivers/irqchip/irq-mbigen.c @@ -207,7 +207,7 @@ static int mbigen_irq_domain_alloc(struct irq_domain *domain, if (err) return err; - err = platform_msi_domain_alloc(domain, virq, nr_irqs); + err = platform_msi_device_domain_alloc(domain, virq, nr_irqs); if (err) return err; @@ -223,7 +223,7 @@ static int mbigen_irq_domain_alloc(struct irq_domain *domain, static void mbigen_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { - platform_msi_domain_free(domain, virq, nr_irqs); + platform_msi_device_domain_free(domain, virq, nr_irqs); } static const struct irq_domain_ops mbigen_domain_ops = { diff --git a/drivers/irqchip/irq-mvebu-icu.c b/drivers/irqchip/irq-mvebu-icu.c index 4a4a65a6f632..497da344717c 100644 --- a/drivers/irqchip/irq-mvebu-icu.c +++ b/drivers/irqchip/irq-mvebu-icu.c @@ -221,7 +221,7 @@ mvebu_icu_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, icu_irqd->icu_group = msi_data->subset_data->icu_group; icu_irqd->icu = icu; - err = platform_msi_domain_alloc(domain, virq, nr_irqs); + err = platform_msi_device_domain_alloc(domain, virq, nr_irqs); if (err) { dev_err(icu->dev, "failed to allocate ICU interrupt in parent domain\n"); goto free_irqd; @@ -245,7 +245,7 @@ mvebu_icu_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, return 0; free_msi: - platform_msi_domain_free(domain, virq, nr_irqs); + platform_msi_device_domain_free(domain, virq, nr_irqs); free_irqd: kfree(icu_irqd); return err; @@ -260,7 +260,7 @@ mvebu_icu_irq_domain_free(struct irq_domain *domain, unsigned int virq, kfree(icu_irqd); - platform_msi_domain_free(domain, virq, nr_irqs); + platform_msi_device_domain_free(domain, virq, nr_irqs); } static const struct irq_domain_ops mvebu_icu_domain_ops = { diff --git a/include/linux/msi.h b/include/linux/msi.h index 634a12962e72..12dd28629c43 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -435,10 +435,10 @@ __platform_msi_create_device_domain(struct device *dev, #define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \ __platform_msi_create_device_domain(dev, nvec, true, write, ops, data) -int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, - unsigned int nr_irqs); -void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq, - unsigned int nvec); +int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nvec); void *platform_msi_get_host_data(struct irq_domain *domain); #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */ -- cgit v1.2.3 From fc22e7dbcdb3e06a3d3ce05fc91c6a2345411f9b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:11 +0100 Subject: platform-msi: Store platform private data pointer in msi_device_data Storing the platform private data in a MSI descriptor is sloppy at best. The data belongs to the device and not to the descriptor. Add a pointer to struct msi_device_data and store the pointer there. Signed-off-by: Thomas Gleixner Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.287680528@linutronix.de --- drivers/base/platform-msi.c | 79 ++++++++++++++++++--------------------------- include/linux/msi.h | 4 +-- 2 files changed, 34 insertions(+), 49 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 46ee9554717b..1487906ad5e0 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -38,9 +38,7 @@ static DEFINE_IDA(platform_msi_devid_ida); */ static irq_hw_number_t platform_msi_calc_hwirq(struct msi_desc *desc) { - u32 devid; - - devid = desc->platform.msi_priv_data->devid; + u32 devid = desc->dev->msi.data->platform_data->devid; return (devid << (32 - DEV_ID_SHIFT)) | desc->platform.msi_index; } @@ -85,11 +83,8 @@ static void platform_msi_update_dom_ops(struct msi_domain_info *info) static void platform_msi_write_msg(struct irq_data *data, struct msi_msg *msg) { struct msi_desc *desc = irq_data_get_msi_desc(data); - struct platform_msi_priv_data *priv_data; - - priv_data = desc->platform.msi_priv_data; - priv_data->write_msg(desc, msg); + desc->dev->msi.data->platform_data->write_msg(desc, msg); } static void platform_msi_update_chip_ops(struct msi_domain_info *info) @@ -126,9 +121,7 @@ static void platform_msi_free_descs(struct device *dev, int base, int nvec) } static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq, - int nvec, - struct platform_msi_priv_data *data) - + int nvec) { struct msi_desc *desc; int i, base = 0; @@ -144,7 +137,6 @@ static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq, if (!desc) break; - desc->platform.msi_priv_data = data; desc->platform.msi_index = base + i; desc->irq = virq ? virq + i : 0; @@ -161,11 +153,9 @@ static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq, return 0; } -static int platform_msi_alloc_descs(struct device *dev, int nvec, - struct platform_msi_priv_data *data) - +static int platform_msi_alloc_descs(struct device *dev, int nvec) { - return platform_msi_alloc_descs_with_irq(dev, 0, nvec, data); + return platform_msi_alloc_descs_with_irq(dev, 0, nvec); } /** @@ -199,9 +189,8 @@ struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode, return domain; } -static struct platform_msi_priv_data * -platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec, - irq_write_msi_msg_t write_msi_msg) +static int platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec, + irq_write_msi_msg_t write_msi_msg) { struct platform_msi_priv_data *datap; int err; @@ -213,41 +202,44 @@ platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec, * capable devices). */ if (!dev->msi.domain || !write_msi_msg || !nvec || nvec > MAX_DEV_MSIS) - return ERR_PTR(-EINVAL); + return -EINVAL; if (dev->msi.domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) { dev_err(dev, "Incompatible msi_domain, giving up\n"); - return ERR_PTR(-EINVAL); + return -EINVAL; } err = msi_setup_device_data(dev); if (err) - return ERR_PTR(err); + return err; - /* Already had a helping of MSI? Greed... */ - if (!list_empty(dev_to_msi_list(dev))) - return ERR_PTR(-EBUSY); + /* Already initialized? */ + if (dev->msi.data->platform_data) + return -EBUSY; datap = kzalloc(sizeof(*datap), GFP_KERNEL); if (!datap) - return ERR_PTR(-ENOMEM); + return -ENOMEM; datap->devid = ida_simple_get(&platform_msi_devid_ida, 0, 1 << DEV_ID_SHIFT, GFP_KERNEL); if (datap->devid < 0) { err = datap->devid; kfree(datap); - return ERR_PTR(err); + return err; } datap->write_msg = write_msi_msg; datap->dev = dev; - - return datap; + dev->msi.data->platform_data = datap; + return 0; } -static void platform_msi_free_priv_data(struct platform_msi_priv_data *data) +static void platform_msi_free_priv_data(struct device *dev) { + struct platform_msi_priv_data *data = dev->msi.data->platform_data; + + dev->msi.data->platform_data = NULL; ida_simple_remove(&platform_msi_devid_ida, data->devid); kfree(data); } @@ -264,14 +256,13 @@ static void platform_msi_free_priv_data(struct platform_msi_priv_data *data) int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, irq_write_msi_msg_t write_msi_msg) { - struct platform_msi_priv_data *priv_data; int err; - priv_data = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg); - if (IS_ERR(priv_data)) - return PTR_ERR(priv_data); + err = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg); + if (err) + return err; - err = platform_msi_alloc_descs(dev, nvec, priv_data); + err = platform_msi_alloc_descs(dev, nvec); if (err) goto out_free_priv_data; @@ -284,8 +275,7 @@ int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec, out_free_desc: platform_msi_free_descs(dev, 0, nvec); out_free_priv_data: - platform_msi_free_priv_data(priv_data); - + platform_msi_free_priv_data(dev); return err; } EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs); @@ -296,15 +286,9 @@ EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs); */ void platform_msi_domain_free_irqs(struct device *dev) { - if (!list_empty(dev_to_msi_list(dev))) { - struct msi_desc *desc; - - desc = first_msi_entry(dev); - platform_msi_free_priv_data(desc->platform.msi_priv_data); - } - msi_domain_free_irqs(dev->msi.domain, dev); platform_msi_free_descs(dev, 0, MAX_DEV_MSIS); + platform_msi_free_priv_data(dev); } EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs); @@ -351,10 +335,11 @@ __platform_msi_create_device_domain(struct device *dev, struct irq_domain *domain; int err; - data = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg); - if (IS_ERR(data)) + err = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg); + if (err) return NULL; + data = dev->msi.data->platform_data; data->host_data = host_data; domain = irq_domain_create_hierarchy(dev->msi.domain, 0, is_tree ? 0 : nvec, @@ -372,7 +357,7 @@ __platform_msi_create_device_domain(struct device *dev, free_domain: irq_domain_remove(domain); free_priv: - platform_msi_free_priv_data(data); + platform_msi_free_priv_data(dev); return NULL; } @@ -420,7 +405,7 @@ int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int vir struct platform_msi_priv_data *data = domain->host_data; int err; - err = platform_msi_alloc_descs_with_irq(data->dev, virq, nr_irqs, data); + err = platform_msi_alloc_descs_with_irq(data->dev, virq, nr_irqs); if (err) return err; diff --git a/include/linux/msi.h b/include/linux/msi.h index 12dd28629c43..cdf0d09c3ad4 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -108,11 +108,9 @@ struct pci_msi_desc { /** * platform_msi_desc - Platform device specific msi descriptor data - * @msi_priv_data: Pointer to platform private data * @msi_index: The index of the MSI descriptor for multi MSI */ struct platform_msi_desc { - struct platform_msi_priv_data *msi_priv_data; u16 msi_index; }; @@ -177,10 +175,12 @@ struct msi_desc { * msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers * @attrs: Pointer to the sysfs attribute group + * @platform_data: Platform-MSI specific data */ struct msi_device_data { unsigned long properties; const struct attribute_group **attrs; + struct platform_msi_priv_data *platform_data; }; int msi_setup_device_data(struct device *dev); -- cgit v1.2.3 From 20c6d424cfe641659c9a025db8a8608701b27246 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:12 +0100 Subject: genirq/msi: Consolidate MSI descriptor data All non PCI/MSI usage variants have data structures in struct msi_desc with only one member: xxx_index. PCI/MSI has a entry_nr member. Add a common msi_index member to struct msi_desc so all implementations can share it which allows further consolidation. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.350967317@linutronix.de --- include/linux/msi.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index cdf0d09c3ad4..ee8fe49dedd1 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -143,6 +143,7 @@ struct ti_sci_inta_msi_desc { * address or data changes * @write_msi_msg_data: Data parameter for the callback. * + * @msi_index: Index of the msi descriptor * @pci: [PCI] PCI speficic msi descriptor data * @platform: [platform] Platform device specific msi descriptor data * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data @@ -163,6 +164,7 @@ struct msi_desc { void (*write_msi_msg)(struct msi_desc *entry, void *data); void *write_msi_msg_data; + u16 msi_index; union { struct pci_msi_desc pci; struct platform_msi_desc platform; -- cgit v1.2.3 From dba27c7fa36f468e7eb29b216879f8c33bf0955d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:14 +0100 Subject: platform-msi: Use msi_desc::msi_index Use the common msi_index member and get rid of the pointless wrapper struct. Signed-off-by: Thomas Gleixner Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.413638645@linutronix.de --- drivers/base/platform-msi.c | 10 +++++----- drivers/dma/qcom/hidma.c | 4 ++-- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 4 ++-- drivers/mailbox/bcm-flexrm-mailbox.c | 4 ++-- include/linux/msi.h | 10 ---------- 5 files changed, 11 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c index 1487906ad5e0..88bdc4b19916 100644 --- a/drivers/base/platform-msi.c +++ b/drivers/base/platform-msi.c @@ -40,7 +40,7 @@ static irq_hw_number_t platform_msi_calc_hwirq(struct msi_desc *desc) { u32 devid = desc->dev->msi.data->platform_data->devid; - return (devid << (32 - DEV_ID_SHIFT)) | desc->platform.msi_index; + return (devid << (32 - DEV_ID_SHIFT)) | desc->msi_index; } static void platform_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) @@ -112,8 +112,8 @@ static void platform_msi_free_descs(struct device *dev, int base, int nvec) struct msi_desc *desc, *tmp; list_for_each_entry_safe(desc, tmp, dev_to_msi_list(dev), list) { - if (desc->platform.msi_index >= base && - desc->platform.msi_index < (base + nvec)) { + if (desc->msi_index >= base && + desc->msi_index < (base + nvec)) { list_del(&desc->list); free_msi_entry(desc); } @@ -129,7 +129,7 @@ static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq, if (!list_empty(dev_to_msi_list(dev))) { desc = list_last_entry(dev_to_msi_list(dev), struct msi_desc, list); - base = desc->platform.msi_index + 1; + base = desc->msi_index + 1; } for (i = 0; i < nvec; i++) { @@ -137,7 +137,7 @@ static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq, if (!desc) break; - desc->platform.msi_index = base + i; + desc->msi_index = base + i; desc->irq = virq ? virq + i : 0; list_add_tail(&desc->list, dev_to_msi_list(dev)); diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c index 23d64489d25f..db8241bfe199 100644 --- a/drivers/dma/qcom/hidma.c +++ b/drivers/dma/qcom/hidma.c @@ -666,7 +666,7 @@ static void hidma_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) struct device *dev = msi_desc_to_dev(desc); struct hidma_dev *dmadev = dev_get_drvdata(dev); - if (!desc->platform.msi_index) { + if (!desc->msi_index) { writel(msg->address_lo, dmadev->dev_evca + 0x118); writel(msg->address_hi, dmadev->dev_evca + 0x11C); writel(msg->data, dmadev->dev_evca + 0x120); @@ -702,7 +702,7 @@ static int hidma_request_msi(struct hidma_dev *dmadev, return rc; for_each_msi_entry(desc, &pdev->dev) { - if (!desc->platform.msi_index) + if (!desc->msi_index) dmadev->msi_virqbase = desc->irq; rc = devm_request_irq(&pdev->dev, desc->irq, diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 5ba9006ec550..beaf91bca30a 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3142,7 +3142,7 @@ static void arm_smmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) phys_addr_t doorbell; struct device *dev = msi_desc_to_dev(desc); struct arm_smmu_device *smmu = dev_get_drvdata(dev); - phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index]; + phys_addr_t *cfg = arm_smmu_msi_cfg[desc->msi_index]; doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo; doorbell &= MSI_CFG0_ADDR_MASK; @@ -3183,7 +3183,7 @@ static void arm_smmu_setup_msis(struct arm_smmu_device *smmu) } for_each_msi_entry(desc, dev) { - switch (desc->platform.msi_index) { + switch (desc->msi_index) { case EVTQ_MSI_INDEX: smmu->evtq.q.irq = desc->irq; break; diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index 78073ad1f2f1..53a84733d8cc 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -1484,7 +1484,7 @@ static void flexrm_mbox_msi_write(struct msi_desc *desc, struct msi_msg *msg) { struct device *dev = msi_desc_to_dev(desc); struct flexrm_mbox *mbox = dev_get_drvdata(dev); - struct flexrm_ring *ring = &mbox->rings[desc->platform.msi_index]; + struct flexrm_ring *ring = &mbox->rings[desc->msi_index]; /* Configure per-Ring MSI registers */ writel_relaxed(msg->address_lo, ring->regs + RING_MSI_ADDR_LS); @@ -1609,7 +1609,7 @@ static int flexrm_mbox_probe(struct platform_device *pdev) /* Save alloced IRQ numbers for each ring */ for_each_msi_entry(desc, dev) { - ring = &mbox->rings[desc->platform.msi_index]; + ring = &mbox->rings[desc->msi_index]; ring->irq = desc->irq; } diff --git a/include/linux/msi.h b/include/linux/msi.h index ee8fe49dedd1..1d85e954e130 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -106,14 +106,6 @@ struct pci_msi_desc { }; }; -/** - * platform_msi_desc - Platform device specific msi descriptor data - * @msi_index: The index of the MSI descriptor for multi MSI - */ -struct platform_msi_desc { - u16 msi_index; -}; - /** * fsl_mc_msi_desc - FSL-MC device specific msi descriptor data * @msi_index: The index of the MSI descriptor @@ -145,7 +137,6 @@ struct ti_sci_inta_msi_desc { * * @msi_index: Index of the msi descriptor * @pci: [PCI] PCI speficic msi descriptor data - * @platform: [platform] Platform device specific msi descriptor data * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data * @inta: [INTA] TISCI based INTA specific msi descriptor data */ @@ -167,7 +158,6 @@ struct msi_desc { u16 msi_index; union { struct pci_msi_desc pci; - struct platform_msi_desc platform; struct fsl_mc_msi_desc fsl_mc; struct ti_sci_inta_msi_desc inta; }; -- cgit v1.2.3 From 78ee9fb4b8b126ed84a819a6e1732fd3039b525a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:15 +0100 Subject: bus: fsl-mc-msi: Use msi_desc::msi_index Use the common msi_index member and get rid of the pointless wrapper struct. Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.477386185@linutronix.de --- drivers/bus/fsl-mc/fsl-mc-allocator.c | 2 +- drivers/bus/fsl-mc/fsl-mc-msi.c | 6 +++--- include/linux/msi.h | 10 ---------- 3 files changed, 4 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/fsl-mc-allocator.c b/drivers/bus/fsl-mc/fsl-mc-allocator.c index 6c513556911e..3370b63bad5f 100644 --- a/drivers/bus/fsl-mc/fsl-mc-allocator.c +++ b/drivers/bus/fsl-mc/fsl-mc-allocator.c @@ -393,7 +393,7 @@ int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev, } for_each_msi_entry(msi_desc, &mc_bus_dev->dev) { - mc_dev_irq = &irq_resources[msi_desc->fsl_mc.msi_index]; + mc_dev_irq = &irq_resources[msi_desc->msi_index]; mc_dev_irq->msi_desc = msi_desc; mc_dev_irq->resource.id = msi_desc->irq; } diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index c6215b7fe27c..2ffb70550a39 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -29,7 +29,7 @@ static irq_hw_number_t fsl_mc_domain_calc_hwirq(struct fsl_mc_device *dev, * Make the base hwirq value for ICID*10000 so it is readable * as a decimal value in /proc/interrupts. */ - return (irq_hw_number_t)(desc->fsl_mc.msi_index + (dev->icid * 10000)); + return (irq_hw_number_t)(desc->msi_index + (dev->icid * 10000)); } static void fsl_mc_msi_set_desc(msi_alloc_info_t *arg, @@ -122,7 +122,7 @@ static void fsl_mc_msi_write_msg(struct irq_data *irq_data, struct fsl_mc_device *mc_bus_dev = to_fsl_mc_device(msi_desc->dev); struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev); struct fsl_mc_device_irq *mc_dev_irq = - &mc_bus->irq_resources[msi_desc->fsl_mc.msi_index]; + &mc_bus->irq_resources[msi_desc->msi_index]; msi_desc->msg = *msg; @@ -235,7 +235,7 @@ static int fsl_mc_msi_alloc_descs(struct device *dev, unsigned int irq_count) goto cleanup_msi_descs; } - msi_desc->fsl_mc.msi_index = i; + msi_desc->msi_index = i; INIT_LIST_HEAD(&msi_desc->list); list_add_tail(&msi_desc->list, dev_to_msi_list(dev)); } diff --git a/include/linux/msi.h b/include/linux/msi.h index 1d85e954e130..25edf83ede41 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -106,14 +106,6 @@ struct pci_msi_desc { }; }; -/** - * fsl_mc_msi_desc - FSL-MC device specific msi descriptor data - * @msi_index: The index of the MSI descriptor - */ -struct fsl_mc_msi_desc { - u16 msi_index; -}; - /** * ti_sci_inta_msi_desc - TISCI based INTA specific msi descriptor data * @dev_index: TISCI device index @@ -137,7 +129,6 @@ struct ti_sci_inta_msi_desc { * * @msi_index: Index of the msi descriptor * @pci: [PCI] PCI speficic msi descriptor data - * @fsl_mc: [fsl-mc] FSL MC device specific msi descriptor data * @inta: [INTA] TISCI based INTA specific msi descriptor data */ struct msi_desc { @@ -158,7 +149,6 @@ struct msi_desc { u16 msi_index; union { struct pci_msi_desc pci; - struct fsl_mc_msi_desc fsl_mc; struct ti_sci_inta_msi_desc inta; }; }; -- cgit v1.2.3 From 0f18095871fc59c89a281caf6f18538cf9e50fbf Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:17 +0100 Subject: soc: ti: ti_sci_inta_msi: Use msi_desc::msi_index Use the common msi_index member and get rid of the pointless wrapper struct. Signed-off-by: Thomas Gleixner Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Nishanth Menon Link: https://lore.kernel.org/r/20211210221814.540704224@linutronix.de --- drivers/irqchip/irq-ti-sci-inta.c | 2 +- drivers/soc/ti/ti_sci_inta_msi.c | 6 +++--- include/linux/msi.h | 16 ++-------------- 3 files changed, 6 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index 8eba08db33b2..5fdbb4358dd0 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -595,7 +595,7 @@ static void ti_sci_inta_msi_set_desc(msi_alloc_info_t *arg, struct platform_device *pdev = to_platform_device(desc->dev); arg->desc = desc; - arg->hwirq = TO_HWIRQ(pdev->id, desc->inta.dev_index); + arg->hwirq = TO_HWIRQ(pdev->id, desc->msi_index); } static struct msi_domain_ops ti_sci_inta_msi_ops = { diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c index a89bcbcd4694..9d23daac74c3 100644 --- a/drivers/soc/ti/ti_sci_inta_msi.c +++ b/drivers/soc/ti/ti_sci_inta_msi.c @@ -84,7 +84,7 @@ static int ti_sci_inta_msi_alloc_descs(struct device *dev, return -ENOMEM; } - msi_desc->inta.dev_index = res->desc[set].start + i; + msi_desc->msi_index = res->desc[set].start + i; INIT_LIST_HEAD(&msi_desc->list); list_add_tail(&msi_desc->list, dev_to_msi_list(dev)); count++; @@ -96,7 +96,7 @@ static int ti_sci_inta_msi_alloc_descs(struct device *dev, return -ENOMEM; } - msi_desc->inta.dev_index = res->desc[set].start_sec + i; + msi_desc->msi_index = res->desc[set].start_sec + i; INIT_LIST_HEAD(&msi_desc->list); list_add_tail(&msi_desc->list, dev_to_msi_list(dev)); count++; @@ -154,7 +154,7 @@ unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 dev_index) struct msi_desc *desc; for_each_msi_entry(desc, dev) - if (desc->inta.dev_index == dev_index) + if (desc->msi_index == dev_index) return desc->irq; return -ENODEV; diff --git a/include/linux/msi.h b/include/linux/msi.h index 25edf83ede41..45ec5d07a5f3 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -106,14 +106,6 @@ struct pci_msi_desc { }; }; -/** - * ti_sci_inta_msi_desc - TISCI based INTA specific msi descriptor data - * @dev_index: TISCI device index - */ -struct ti_sci_inta_msi_desc { - u16 dev_index; -}; - /** * struct msi_desc - Descriptor structure for MSI based interrupts * @list: List head for management @@ -128,8 +120,7 @@ struct ti_sci_inta_msi_desc { * @write_msi_msg_data: Data parameter for the callback. * * @msi_index: Index of the msi descriptor - * @pci: [PCI] PCI speficic msi descriptor data - * @inta: [INTA] TISCI based INTA specific msi descriptor data + * @pci: PCI specific msi descriptor data */ struct msi_desc { /* Shared device/bus type independent data */ @@ -147,10 +138,7 @@ struct msi_desc { void *write_msi_msg_data; u16 msi_index; - union { - struct pci_msi_desc pci; - struct ti_sci_inta_msi_desc inta; - }; + struct pci_msi_desc pci; }; /** -- cgit v1.2.3 From 173ffad79d177d9a91fbf3be6bf67ca81e0f765a Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:18 +0100 Subject: PCI/MSI: Use msi_desc::msi_index The usage of msi_desc::pci::entry_nr is confusing at best. It's the index into the MSI[X] descriptor table. Use msi_desc::msi_index which is shared between all MSI incarnations instead of having a PCI specific storage for no value. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211210221814.602911509@linutronix.de --- arch/powerpc/platforms/pseries/msi.c | 4 ++-- arch/x86/pci/xen.c | 2 +- drivers/pci/msi/irqdomain.c | 2 +- drivers/pci/msi/msi.c | 20 ++++++++------------ drivers/pci/xen-pcifront.c | 2 +- include/linux/msi.h | 2 -- 6 files changed, 13 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/pseries/msi.c b/arch/powerpc/platforms/pseries/msi.c index dc8cf3603f9a..27cd1fb7e02b 100644 --- a/arch/powerpc/platforms/pseries/msi.c +++ b/arch/powerpc/platforms/pseries/msi.c @@ -332,7 +332,7 @@ static int check_msix_entries(struct pci_dev *pdev) expected = 0; for_each_pci_msi_entry(entry, pdev) { - if (entry->pci.msi_attrib.entry_nr != expected) { + if (entry->msi_index != expected) { pr_debug("rtas_msi: bad MSI-X entries.\n"); return -EINVAL; } @@ -579,7 +579,7 @@ static int pseries_irq_domain_alloc(struct irq_domain *domain, unsigned int virq int hwirq; int i, ret; - hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->pci.msi_attrib.entry_nr); + hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_index); if (hwirq < 0) { dev_err(&pdev->dev, "Failed to query HW IRQ: %d\n", hwirq); return hwirq; diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index bfd87b46bc51..ded032053479 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -306,7 +306,7 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return -EINVAL; map_irq.table_base = pci_resource_start(dev, bir); - map_irq.entry_nr = msidesc->pci.msi_attrib.entry_nr; + map_irq.entry_nr = msidesc->msi_index; } ret = -EINVAL; diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 26b23a1c4f60..422420276d6f 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -57,7 +57,7 @@ static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) { struct pci_dev *dev = msi_desc_to_pci_dev(desc); - return (irq_hw_number_t)desc->pci.msi_attrib.entry_nr | + return (irq_hw_number_t)desc->msi_index | pci_dev_id(dev) << 11 | (pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27; } diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 76c15be8e1cc..8fb4dd2a18b9 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -44,7 +44,7 @@ static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask) static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc) { - return desc->pci.mask_base + desc->pci.msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; + return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE; } /* @@ -394,13 +394,10 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING) control |= PCI_MSI_FLAGS_MASKBIT; - entry->pci.msi_attrib.is_msix = 0; - entry->pci.msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); - entry->pci.msi_attrib.is_virtual = 0; - entry->pci.msi_attrib.entry_nr = 0; + entry->pci.msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); entry->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && !!(control & PCI_MSI_FLAGS_MASKBIT); - entry->pci.msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ + entry->pci.msi_attrib.default_irq = dev->irq; entry->pci.msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1; entry->pci.msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec)); @@ -542,12 +539,11 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->pci.msi_attrib.is_64 = 1; if (entries) - entry->pci.msi_attrib.entry_nr = entries[i].entry; + entry->msi_index = entries[i].entry; else - entry->pci.msi_attrib.entry_nr = i; + entry->msi_index = i; - entry->pci.msi_attrib.is_virtual = - entry->pci.msi_attrib.entry_nr >= vec_count; + entry->pci.msi_attrib.is_virtual = entry->msi_index >= vec_count; entry->pci.msi_attrib.can_mask = !pci_msi_ignore_mask && !entry->pci.msi_attrib.is_virtual; @@ -1088,7 +1084,7 @@ int pci_irq_vector(struct pci_dev *dev, unsigned int nr) struct msi_desc *entry; for_each_pci_msi_entry(entry, dev) { - if (entry->pci.msi_attrib.entry_nr == nr) + if (entry->msi_index == nr) return entry->irq; } WARN_ON_ONCE(1); @@ -1127,7 +1123,7 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr) struct msi_desc *entry; for_each_pci_msi_entry(entry, dev) { - if (entry->pci.msi_attrib.entry_nr == nr) + if (entry->msi_index == nr) return &entry->affinity->mask; } WARN_ON_ONCE(1); diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 699cc9544424..bacf51152168 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -263,7 +263,7 @@ static int pci_frontend_enable_msix(struct pci_dev *dev, i = 0; for_each_pci_msi_entry(entry, dev) { - op.msix_entries[i].entry = entry->pci.msi_attrib.entry_nr; + op.msix_entries[i].entry = entry->msi_index; /* Vector is useless at this point. */ op.msix_entries[i].vector = -1; i++; diff --git a/include/linux/msi.h b/include/linux/msi.h index 45ec5d07a5f3..b3d3b0bf59fe 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -80,7 +80,6 @@ typedef void (*irq_write_msi_msg_t)(struct msi_desc *desc, * @multi_cap: [PCI MSI/X] log2 num of messages supported * @can_mask: [PCI MSI/X] Masking supported? * @is_64: [PCI MSI/X] Address size: 0=32bit 1=64bit - * @entry_nr: [PCI MSI/X] Entry which is described by this descriptor * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq * @mask_pos: [PCI MSI] Mask register position * @mask_base: [PCI MSI-X] Mask register base address @@ -97,7 +96,6 @@ struct pci_msi_desc { u8 can_mask : 1; u8 is_64 : 1; u8 is_virtual : 1; - u16 entry_nr; unsigned default_irq; } msi_attrib; union { -- cgit v1.2.3 From 7a823443e9b4ed1ff4a3026d184f09d23fd6d9c9 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:20 +0100 Subject: PCI/MSI: Provide MSI_FLAG_MSIX_CONTIGUOUS Provide a domain info flag which makes the core code check for a contiguous MSI-X index on allocation. That's simpler than checking it at some other domain callback in architecture code. Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20211210221814.662401116@linutronix.de --- drivers/pci/msi/irqdomain.c | 16 ++++++++++++++-- include/linux/msi.h | 2 ++ 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index 422420276d6f..180b2a18dc19 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -89,9 +89,21 @@ static int pci_msi_domain_check_cap(struct irq_domain *domain, if (pci_msi_desc_is_multi_msi(desc) && !(info->flags & MSI_FLAG_MULTI_PCI_MSI)) return 1; - else if (desc->pci.msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX)) - return -ENOTSUPP; + if (desc->pci.msi_attrib.is_msix) { + if (!(info->flags & MSI_FLAG_PCI_MSIX)) + return -ENOTSUPP; + + if (info->flags & MSI_FLAG_MSIX_CONTIGUOUS) { + unsigned int idx = 0; + + /* Check for gaps in the entry indices */ + for_each_msi_entry(desc, dev) { + if (desc->msi_index != idx++) + return -ENOTSUPP; + } + } + } return 0; } diff --git a/include/linux/msi.h b/include/linux/msi.h index b3d3b0bf59fe..d206239e6fa8 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -362,6 +362,8 @@ enum { MSI_FLAG_LEVEL_CAPABLE = (1 << 6), /* Populate sysfs on alloc() and destroy it on free() */ MSI_FLAG_DEV_SYSFS = (1 << 7), + /* MSI-X entries must be contiguous */ + MSI_FLAG_MSIX_CONTIGUOUS = (1 << 8), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, -- cgit v1.2.3 From cf15f43acaad31dabb2646cef170a506a1d663eb Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:23 +0100 Subject: genirq/msi: Provide interface to retrieve Linux interrupt number This allows drivers to retrieve the Linux interrupt number instead of fiddling with MSI descriptors. msi_get_virq() returns the Linux interrupt number or 0 in case that there is no entry for the given MSI index. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221814.780824745@linutronix.de --- include/linux/msi.h | 2 ++ kernel/irq/msi.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index d206239e6fa8..7593fc383dba 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -153,6 +153,8 @@ struct msi_device_data { int msi_setup_device_data(struct device *dev); +unsigned int msi_get_virq(struct device *dev, unsigned int index); + /* Helpers to hide struct msi_desc implementation details */ #define msi_desc_to_dev(desc) ((desc)->dev) #define dev_to_msi_list(dev) (&(dev)->msi_list) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 8e433f1a24fb..ab5e83f41188 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -105,6 +105,42 @@ int msi_setup_device_data(struct device *dev) return 0; } +/** + * msi_get_virq - Return Linux interrupt number of a MSI interrupt + * @dev: Device to operate on + * @index: MSI interrupt index to look for (0-based) + * + * Return: The Linux interrupt number on success (> 0), 0 if not found + */ +unsigned int msi_get_virq(struct device *dev, unsigned int index) +{ + struct msi_desc *desc; + bool pcimsi; + + if (!dev->msi.data) + return 0; + + pcimsi = dev_is_pci(dev) ? to_pci_dev(dev)->msi_enabled : false; + + for_each_msi_entry(desc, dev) { + /* PCI-MSI has only one descriptor for multiple interrupts. */ + if (pcimsi) { + if (desc->irq && index < desc->nvec_used) + return desc->irq + index; + break; + } + + /* + * PCI-MSIX and platform MSI use a descriptor per + * interrupt. + */ + if (desc->msi_index == index) + return desc->irq; + } + return 0; +} +EXPORT_SYMBOL_GPL(msi_get_virq); + #ifdef CONFIG_SYSFS static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, char *buf) -- cgit v1.2.3 From d86a6d47bcc6b41fe2a4e13313d66a772d00382f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:34 +0100 Subject: bus: fsl-mc: fsl-mc-allocator: Rework MSI handling Storing a pointer to the MSI descriptor just to track the Linux interrupt number is daft. Just store the interrupt number and be done with it. Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211210221815.207838579@linutronix.de --- drivers/bus/fsl-mc/dprc-driver.c | 8 ++++---- drivers/bus/fsl-mc/fsl-mc-allocator.c | 9 ++------- drivers/bus/fsl-mc/fsl-mc-msi.c | 6 +++--- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 ++-- drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c | 4 +--- drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 5 ++--- drivers/soc/fsl/dpio/dpio-driver.c | 8 ++++---- drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c | 4 ++-- include/linux/fsl/mc.h | 4 ++-- 9 files changed, 22 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/fsl-mc/dprc-driver.c b/drivers/bus/fsl-mc/dprc-driver.c index 315e830b6ecd..5e70f9775a0e 100644 --- a/drivers/bus/fsl-mc/dprc-driver.c +++ b/drivers/bus/fsl-mc/dprc-driver.c @@ -400,7 +400,7 @@ static irqreturn_t dprc_irq0_handler_thread(int irq_num, void *arg) struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev); struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev); struct fsl_mc_io *mc_io = mc_dev->mc_io; - struct msi_desc *msi_desc = mc_dev->irqs[0]->msi_desc; + int irq = mc_dev->irqs[0]->virq; dev_dbg(dev, "DPRC IRQ %d triggered on CPU %u\n", irq_num, smp_processor_id()); @@ -409,7 +409,7 @@ static irqreturn_t dprc_irq0_handler_thread(int irq_num, void *arg) return IRQ_HANDLED; mutex_lock(&mc_bus->scan_mutex); - if (!msi_desc || msi_desc->irq != (u32)irq_num) + if (irq != (u32)irq_num) goto out; status = 0; @@ -521,7 +521,7 @@ static int register_dprc_irq_handler(struct fsl_mc_device *mc_dev) * function that programs the MSI physically in the device */ error = devm_request_threaded_irq(&mc_dev->dev, - irq->msi_desc->irq, + irq->virq, dprc_irq0_handler, dprc_irq0_handler_thread, IRQF_NO_SUSPEND | IRQF_ONESHOT, @@ -771,7 +771,7 @@ static void dprc_teardown_irq(struct fsl_mc_device *mc_dev) (void)disable_dprc_irq(mc_dev); - devm_free_irq(&mc_dev->dev, irq->msi_desc->irq, &mc_dev->dev); + devm_free_irq(&mc_dev->dev, irq->virq, &mc_dev->dev); fsl_mc_free_irqs(mc_dev); } diff --git a/drivers/bus/fsl-mc/fsl-mc-allocator.c b/drivers/bus/fsl-mc/fsl-mc-allocator.c index 3370b63bad5f..dced427ca8ba 100644 --- a/drivers/bus/fsl-mc/fsl-mc-allocator.c +++ b/drivers/bus/fsl-mc/fsl-mc-allocator.c @@ -350,7 +350,6 @@ int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev, unsigned int irq_count) { unsigned int i; - struct msi_desc *msi_desc; struct fsl_mc_device_irq *irq_resources; struct fsl_mc_device_irq *mc_dev_irq; int error; @@ -388,16 +387,12 @@ int fsl_mc_populate_irq_pool(struct fsl_mc_device *mc_bus_dev, mc_dev_irq->resource.type = res_pool->type; mc_dev_irq->resource.data = mc_dev_irq; mc_dev_irq->resource.parent_pool = res_pool; + mc_dev_irq->virq = msi_get_virq(&mc_bus_dev->dev, i); + mc_dev_irq->resource.id = mc_dev_irq->virq; INIT_LIST_HEAD(&mc_dev_irq->resource.node); list_add_tail(&mc_dev_irq->resource.node, &res_pool->free_list); } - for_each_msi_entry(msi_desc, &mc_bus_dev->dev) { - mc_dev_irq = &irq_resources[msi_desc->msi_index]; - mc_dev_irq->msi_desc = msi_desc; - mc_dev_irq->resource.id = msi_desc->irq; - } - res_pool->max_count = irq_count; res_pool->free_count = irq_count; mc_bus->irq_resources = irq_resources; diff --git a/drivers/bus/fsl-mc/fsl-mc-msi.c b/drivers/bus/fsl-mc/fsl-mc-msi.c index 2ffb70550a39..4823947d7d6f 100644 --- a/drivers/bus/fsl-mc/fsl-mc-msi.c +++ b/drivers/bus/fsl-mc/fsl-mc-msi.c @@ -58,11 +58,11 @@ static void fsl_mc_msi_update_dom_ops(struct msi_domain_info *info) } static void __fsl_mc_msi_write_msg(struct fsl_mc_device *mc_bus_dev, - struct fsl_mc_device_irq *mc_dev_irq) + struct fsl_mc_device_irq *mc_dev_irq, + struct msi_desc *msi_desc) { int error; struct fsl_mc_device *owner_mc_dev = mc_dev_irq->mc_dev; - struct msi_desc *msi_desc = mc_dev_irq->msi_desc; struct dprc_irq_cfg irq_cfg; /* @@ -129,7 +129,7 @@ static void fsl_mc_msi_write_msg(struct irq_data *irq_data, /* * Program the MSI (paddr, value) pair in the device: */ - __fsl_mc_msi_write_msg(mc_bus_dev, mc_dev_irq); + __fsl_mc_msi_write_msg(mc_bus_dev, mc_dev_irq, msi_desc); } static void fsl_mc_msi_update_chip_ops(struct msi_domain_info *info) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 8e643567abce..2c53f957e373 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -4246,7 +4246,7 @@ static int dpaa2_eth_setup_irqs(struct fsl_mc_device *ls_dev) } irq = ls_dev->irqs[0]; - err = devm_request_threaded_irq(&ls_dev->dev, irq->msi_desc->irq, + err = devm_request_threaded_irq(&ls_dev->dev, irq->virq, NULL, dpni_irq0_handler_thread, IRQF_NO_SUSPEND | IRQF_ONESHOT, dev_name(&ls_dev->dev), &ls_dev->dev); @@ -4273,7 +4273,7 @@ static int dpaa2_eth_setup_irqs(struct fsl_mc_device *ls_dev) return 0; free_irq: - devm_free_irq(&ls_dev->dev, irq->msi_desc->irq, &ls_dev->dev); + devm_free_irq(&ls_dev->dev, irq->virq, &ls_dev->dev); free_mc_irq: fsl_mc_free_irqs(ls_dev); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c index 32b5faa87bb8..5f5f8c53c4a0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c @@ -129,7 +129,6 @@ static irqreturn_t dpaa2_ptp_irq_handler_thread(int irq, void *priv) static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) { struct device *dev = &mc_dev->dev; - struct fsl_mc_device_irq *irq; struct ptp_qoriq *ptp_qoriq; struct device_node *node; void __iomem *base; @@ -177,8 +176,7 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev) goto err_unmap; } - irq = mc_dev->irqs[0]; - ptp_qoriq->irq = irq->msi_desc->irq; + ptp_qoriq->irq = mc_dev->irqs[0]->virq; err = request_threaded_irq(ptp_qoriq->irq, NULL, dpaa2_ptp_irq_handler_thread, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index d039457928b0..084cc4d2d876 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1553,8 +1553,7 @@ static int dpaa2_switch_setup_irqs(struct fsl_mc_device *sw_dev) irq = sw_dev->irqs[DPSW_IRQ_INDEX_IF]; - err = devm_request_threaded_irq(dev, irq->msi_desc->irq, - NULL, + err = devm_request_threaded_irq(dev, irq->virq, NULL, dpaa2_switch_irq0_handler_thread, IRQF_NO_SUSPEND | IRQF_ONESHOT, dev_name(dev), dev); @@ -1580,7 +1579,7 @@ static int dpaa2_switch_setup_irqs(struct fsl_mc_device *sw_dev) return 0; free_devm_irq: - devm_free_irq(dev, irq->msi_desc->irq, dev); + devm_free_irq(dev, irq->virq, dev); free_irq: fsl_mc_free_irqs(sw_dev); return err; diff --git a/drivers/soc/fsl/dpio/dpio-driver.c b/drivers/soc/fsl/dpio/dpio-driver.c index dd948889eeab..5a2edc48dd79 100644 --- a/drivers/soc/fsl/dpio/dpio-driver.c +++ b/drivers/soc/fsl/dpio/dpio-driver.c @@ -88,7 +88,7 @@ static void unregister_dpio_irq_handlers(struct fsl_mc_device *dpio_dev) irq = dpio_dev->irqs[0]; /* clear the affinity hint */ - irq_set_affinity_hint(irq->msi_desc->irq, NULL); + irq_set_affinity_hint(irq->virq, NULL); } static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) @@ -98,7 +98,7 @@ static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) irq = dpio_dev->irqs[0]; error = devm_request_irq(&dpio_dev->dev, - irq->msi_desc->irq, + irq->virq, dpio_irq_handler, 0, dev_name(&dpio_dev->dev), @@ -111,10 +111,10 @@ static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu) } /* set the affinity hint */ - if (irq_set_affinity_hint(irq->msi_desc->irq, cpumask_of(cpu))) + if (irq_set_affinity_hint(irq->virq, cpumask_of(cpu))) dev_err(&dpio_dev->dev, "irq_set_affinity failed irq %d cpu %d\n", - irq->msi_desc->irq, cpu); + irq->virq, cpu); return 0; } diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c index 77e584093a23..7b428eac3d3e 100644 --- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c @@ -67,7 +67,7 @@ static int vfio_set_trigger(struct vfio_fsl_mc_device *vdev, int hwirq; int ret; - hwirq = vdev->mc_dev->irqs[index]->msi_desc->irq; + hwirq = vdev->mc_dev->irqs[index]->virq; if (irq->trigger) { free_irq(hwirq, irq); kfree(irq->name); @@ -137,7 +137,7 @@ static int vfio_fsl_mc_set_irq_trigger(struct vfio_fsl_mc_device *vdev, return vfio_set_trigger(vdev, index, fd); } - hwirq = vdev->mc_dev->irqs[index]->msi_desc->irq; + hwirq = vdev->mc_dev->irqs[index]->virq; irq = &vdev->mc_irqs[index]; diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h index e026f6c48b49..7b6c42bfb660 100644 --- a/include/linux/fsl/mc.h +++ b/include/linux/fsl/mc.h @@ -91,13 +91,13 @@ struct fsl_mc_resource { /** * struct fsl_mc_device_irq - MC object device message-based interrupt - * @msi_desc: pointer to MSI descriptor allocated by fsl_mc_msi_alloc_descs() + * @virq: Linux virtual interrupt number * @mc_dev: MC object device that owns this interrupt * @dev_irq_index: device-relative IRQ index * @resource: MC generic resource associated with the interrupt */ struct fsl_mc_device_irq { - struct msi_desc *msi_desc; + unsigned int virq; struct fsl_mc_device *mc_dev; u8 dev_irq_index; struct fsl_mc_resource resource; -- cgit v1.2.3 From 89e0032ec201f76c86d6e3e6f94574dfb8e39b71 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Dec 2021 23:19:35 +0100 Subject: soc: ti: ti_sci_inta_msi: Get rid of ti_sci_inta_msi_get_virq() Just use the core function msi_get_virq(). Signed-off-by: Thomas Gleixner Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Acked-by: Arnd Bergmann Acked-by: Vinod Koul Acked-by: Nishanth Menon Link: https://lore.kernel.org/r/20211210221815.269468319@linutronix.de --- drivers/dma/ti/k3-udma-private.c | 6 ++---- drivers/dma/ti/k3-udma.c | 10 ++++------ drivers/soc/ti/k3-ringacc.c | 2 +- drivers/soc/ti/ti_sci_inta_msi.c | 12 ------------ include/linux/soc/ti/ti_sci_inta_msi.h | 1 - 5 files changed, 7 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma/ti/k3-udma-private.c b/drivers/dma/ti/k3-udma-private.c index aada84f40723..d4f1e4e9603a 100644 --- a/drivers/dma/ti/k3-udma-private.c +++ b/drivers/dma/ti/k3-udma-private.c @@ -168,8 +168,7 @@ int xudma_pktdma_tflow_get_irq(struct udma_dev *ud, int udma_tflow_id) { const struct udma_oes_offsets *oes = &ud->soc_data->oes; - return ti_sci_inta_msi_get_virq(ud->dev, udma_tflow_id + - oes->pktdma_tchan_flow); + return msi_get_virq(ud->dev, udma_tflow_id + oes->pktdma_tchan_flow); } EXPORT_SYMBOL(xudma_pktdma_tflow_get_irq); @@ -177,7 +176,6 @@ int xudma_pktdma_rflow_get_irq(struct udma_dev *ud, int udma_rflow_id) { const struct udma_oes_offsets *oes = &ud->soc_data->oes; - return ti_sci_inta_msi_get_virq(ud->dev, udma_rflow_id + - oes->pktdma_rchan_flow); + return msi_get_virq(ud->dev, udma_rflow_id + oes->pktdma_rchan_flow); } EXPORT_SYMBOL(xudma_pktdma_rflow_get_irq); diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 20edd0bf3e8b..86f7a0ae2648 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -2313,8 +2313,7 @@ static int udma_alloc_chan_resources(struct dma_chan *chan) /* Event from UDMA (TR events) only needed for slave TR mode channels */ if (is_slave_direction(uc->config.dir) && !uc->config.pkt_mode) { - uc->irq_num_udma = ti_sci_inta_msi_get_virq(ud->dev, - irq_udma_idx); + uc->irq_num_udma = msi_get_virq(ud->dev, irq_udma_idx); if (uc->irq_num_udma <= 0) { dev_err(ud->dev, "Failed to get udma irq (index: %u)\n", irq_udma_idx); @@ -2486,7 +2485,7 @@ static int bcdma_alloc_chan_resources(struct dma_chan *chan) uc->psil_paired = true; } - uc->irq_num_ring = ti_sci_inta_msi_get_virq(ud->dev, irq_ring_idx); + uc->irq_num_ring = msi_get_virq(ud->dev, irq_ring_idx); if (uc->irq_num_ring <= 0) { dev_err(ud->dev, "Failed to get ring irq (index: %u)\n", irq_ring_idx); @@ -2503,8 +2502,7 @@ static int bcdma_alloc_chan_resources(struct dma_chan *chan) /* Event from BCDMA (TR events) only needed for slave channels */ if (is_slave_direction(uc->config.dir)) { - uc->irq_num_udma = ti_sci_inta_msi_get_virq(ud->dev, - irq_udma_idx); + uc->irq_num_udma = msi_get_virq(ud->dev, irq_udma_idx); if (uc->irq_num_udma <= 0) { dev_err(ud->dev, "Failed to get bcdma irq (index: %u)\n", irq_udma_idx); @@ -2672,7 +2670,7 @@ static int pktdma_alloc_chan_resources(struct dma_chan *chan) uc->psil_paired = true; - uc->irq_num_ring = ti_sci_inta_msi_get_virq(ud->dev, irq_ring_idx); + uc->irq_num_ring = msi_get_virq(ud->dev, irq_ring_idx); if (uc->irq_num_ring <= 0) { dev_err(ud->dev, "Failed to get ring irq (index: %u)\n", irq_ring_idx); diff --git a/drivers/soc/ti/k3-ringacc.c b/drivers/soc/ti/k3-ringacc.c index 26159a5eef88..56be39161489 100644 --- a/drivers/soc/ti/k3-ringacc.c +++ b/drivers/soc/ti/k3-ringacc.c @@ -647,7 +647,7 @@ int k3_ringacc_get_ring_irq_num(struct k3_ring *ring) if (!ring) return -EINVAL; - irq_num = ti_sci_inta_msi_get_virq(ring->parent->dev, ring->ring_id); + irq_num = msi_get_virq(ring->parent->dev, ring->ring_id); if (irq_num <= 0) irq_num = -EINVAL; return irq_num; diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c index 9d23daac74c3..b68cc6d042b2 100644 --- a/drivers/soc/ti/ti_sci_inta_msi.c +++ b/drivers/soc/ti/ti_sci_inta_msi.c @@ -148,15 +148,3 @@ void ti_sci_inta_msi_domain_free_irqs(struct device *dev) ti_sci_inta_msi_free_descs(dev); } EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_free_irqs); - -unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 dev_index) -{ - struct msi_desc *desc; - - for_each_msi_entry(desc, dev) - if (desc->msi_index == dev_index) - return desc->irq; - - return -ENODEV; -} -EXPORT_SYMBOL_GPL(ti_sci_inta_msi_get_virq); diff --git a/include/linux/soc/ti/ti_sci_inta_msi.h b/include/linux/soc/ti/ti_sci_inta_msi.h index e3aa8b14612e..25ea78a8ea5c 100644 --- a/include/linux/soc/ti/ti_sci_inta_msi.h +++ b/include/linux/soc/ti/ti_sci_inta_msi.h @@ -18,6 +18,5 @@ struct irq_domain struct irq_domain *parent); int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev, struct ti_sci_resource *res); -unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 index); void ti_sci_inta_msi_domain_free_irqs(struct device *dev); #endif /* __INCLUDE_LINUX_IRQCHIP_TI_SCI_INTA_H */ -- cgit v1.2.3 From 125282cd4f33ecd53a24ae4807409da0e5e90fd4 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:04 +0100 Subject: genirq/msi: Move descriptor list to struct msi_device_data It's only required when MSI is in use. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210747.650487479@linutronix.de --- drivers/base/core.c | 3 --- include/linux/device.h | 4 ---- include/linux/msi.h | 4 +++- kernel/irq/msi.c | 5 ++++- 4 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index f26c668092d6..f8987867789f 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2874,9 +2874,6 @@ void device_initialize(struct device *dev) INIT_LIST_HEAD(&dev->devres_head); device_pm_init(dev); set_dev_node(dev, NUMA_NO_NODE); -#ifdef CONFIG_GENERIC_MSI_IRQ - INIT_LIST_HEAD(&dev->msi_list); -#endif INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); INIT_LIST_HEAD(&dev->links.defer_sync); diff --git a/include/linux/device.h b/include/linux/device.h index f0033cd93631..93459724dcde 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -423,7 +423,6 @@ struct dev_msi_info { * @pins: For device pin management. * See Documentation/driver-api/pin-control.rst for details. * @msi: MSI related data - * @msi_list: Hosts MSI descriptors * @numa_node: NUMA node this device is close to. * @dma_ops: DMA mapping operations for this device. * @dma_mask: Dma mask (if dma'ble device). @@ -519,9 +518,6 @@ struct device { struct dev_pin_info *pins; #endif struct dev_msi_info msi; -#ifdef CONFIG_GENERIC_MSI_IRQ - struct list_head msi_list; -#endif #ifdef CONFIG_DMA_OPS const struct dma_map_ops *dma_ops; #endif diff --git a/include/linux/msi.h b/include/linux/msi.h index 7593fc383dba..4223e47103ed 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -144,11 +144,13 @@ struct msi_desc { * @properties: MSI properties which are interesting to drivers * @attrs: Pointer to the sysfs attribute group * @platform_data: Platform-MSI specific data + * @list: List of MSI descriptors associated to the device */ struct msi_device_data { unsigned long properties; const struct attribute_group **attrs; struct platform_msi_priv_data *platform_data; + struct list_head list; }; int msi_setup_device_data(struct device *dev); @@ -157,7 +159,7 @@ unsigned int msi_get_virq(struct device *dev, unsigned int index); /* Helpers to hide struct msi_desc implementation details */ #define msi_desc_to_dev(desc) ((desc)->dev) -#define dev_to_msi_list(dev) (&(dev)->msi_list) +#define dev_to_msi_list(dev) (&(dev)->msi.data->list) #define first_msi_entry(dev) \ list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list) #define for_each_msi_entry(desc, dev) \ diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index ab5e83f41188..c66787daee57 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -75,7 +75,9 @@ EXPORT_SYMBOL_GPL(get_cached_msi_msg); static void msi_device_data_release(struct device *dev, void *res) { - WARN_ON_ONCE(!list_empty(&dev->msi_list)); + struct msi_device_data *md = res; + + WARN_ON_ONCE(!list_empty(&md->list)); dev->msi.data = NULL; } @@ -100,6 +102,7 @@ int msi_setup_device_data(struct device *dev) if (!md) return -ENOMEM; + INIT_LIST_HEAD(&md->list); dev->msi.data = md; devres_add(dev, md); return 0; -- cgit v1.2.3 From b5f687f97d1e112493fe0447a1fb09fbd93c334b Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:05 +0100 Subject: genirq/msi: Add mutex for MSI list protection For upcoming runtime extensions of MSI-X interrupts it's required to protect the MSI descriptor list. Add a mutex to struct msi_device_data and provide lock/unlock functions. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210747.708877269@linutronix.de --- include/linux/msi.h | 5 +++++ kernel/irq/msi.c | 21 +++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 4223e47103ed..2cf6c530588d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -3,6 +3,7 @@ #define LINUX_MSI_H #include +#include #include #include @@ -145,17 +146,21 @@ struct msi_desc { * @attrs: Pointer to the sysfs attribute group * @platform_data: Platform-MSI specific data * @list: List of MSI descriptors associated to the device + * @mutex: Mutex protecting the MSI list */ struct msi_device_data { unsigned long properties; const struct attribute_group **attrs; struct platform_msi_priv_data *platform_data; struct list_head list; + struct mutex mutex; }; int msi_setup_device_data(struct device *dev); unsigned int msi_get_virq(struct device *dev, unsigned int index); +void msi_lock_descs(struct device *dev); +void msi_unlock_descs(struct device *dev); /* Helpers to hide struct msi_desc implementation details */ #define msi_desc_to_dev(desc) ((desc)->dev) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index c66787daee57..97ec245803f0 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -103,11 +103,32 @@ int msi_setup_device_data(struct device *dev) return -ENOMEM; INIT_LIST_HEAD(&md->list); + mutex_init(&md->mutex); dev->msi.data = md; devres_add(dev, md); return 0; } +/** + * msi_lock_descs - Lock the MSI descriptor storage of a device + * @dev: Device to operate on + */ +void msi_lock_descs(struct device *dev) +{ + mutex_lock(&dev->msi.data->mutex); +} +EXPORT_SYMBOL_GPL(msi_lock_descs); + +/** + * msi_unlock_descs - Unlock the MSI descriptor storage of a device + * @dev: Device to operate on + */ +void msi_unlock_descs(struct device *dev) +{ + mutex_unlock(&dev->msi.data->mutex); +} +EXPORT_SYMBOL_GPL(msi_unlock_descs); + /** * msi_get_virq - Return Linux interrupt number of a MSI interrupt * @dev: Device to operate on -- cgit v1.2.3 From 0f62d941acf9ac3b6025692ce649b1f282b89e7f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:07 +0100 Subject: genirq/msi: Provide msi_domain_alloc/free_irqs_descs_locked() Usage sites which do allocations of the MSI descriptors before invoking msi_domain_alloc_irqs() require to lock the MSI decriptors accross the operation. Provide entry points which can be called with the MSI mutex held and lock the mutex in the existing entry points. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210747.765371053@linutronix.de --- include/linux/msi.h | 3 +++ kernel/irq/msi.c | 74 +++++++++++++++++++++++++++++++++++++++++------------ 2 files changed, 61 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 2cf6c530588d..69c588efe85b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -383,9 +383,12 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode, struct irq_domain *parent); int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); +int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, + int nvec); int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec); void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); +void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev); void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev); struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 97ec245803f0..3b21e99bb793 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -672,10 +672,8 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, dev_to_node(dev), &arg, false, desc->affinity); - if (virq < 0) { - ret = msi_handle_pci_fail(domain, desc, allocated); - goto cleanup; - } + if (virq < 0) + return msi_handle_pci_fail(domain, desc, allocated); for (i = 0; i < desc->nvec_used; i++) { irq_set_msi_desc_off(virq, i, desc); @@ -709,7 +707,7 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, } ret = irq_domain_activate_irq(irq_data, can_reserve); if (ret) - goto cleanup; + return ret; } skip_activate: @@ -724,38 +722,63 @@ skip_activate: } } return 0; - -cleanup: - msi_domain_free_irqs(domain, dev); - return ret; } /** - * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain + * msi_domain_alloc_irqs_descs_locked - Allocate interrupts from a MSI interrupt domain * @domain: The domain to allocate from * @dev: Pointer to device struct of the device for which the interrupts * are allocated * @nvec: The number of interrupts to allocate * + * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() + * pair. Use this for MSI irqdomains which implement their own vector + * allocation/free. + * * Return: %0 on success or an error code. */ -int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, - int nvec) +int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev, + int nvec) { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; int ret; + lockdep_assert_held(&dev->msi.data->mutex); + ret = ops->domain_alloc_irqs(domain, dev, nvec); if (ret) - return ret; + goto cleanup; if (!(info->flags & MSI_FLAG_DEV_SYSFS)) return 0; ret = msi_device_populate_sysfs(dev); if (ret) - msi_domain_free_irqs(domain, dev); + goto cleanup; + return 0; + +cleanup: + msi_domain_free_irqs_descs_locked(domain, dev); + return ret; +} + +/** + * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain + * @domain: The domain to allocate from + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @nvec: The number of interrupts to allocate + * + * Return: %0 on success or an error code. + */ +int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec) +{ + int ret; + + msi_lock_descs(dev); + ret = msi_domain_alloc_irqs_descs_locked(domain, dev, nvec); + msi_unlock_descs(dev); return ret; } @@ -785,21 +808,40 @@ void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) } /** - * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated to @dev + * msi_domain_free_irqs_descs_locked - Free interrupts from a MSI interrupt @domain associated to @dev * @domain: The domain to managing the interrupts * @dev: Pointer to device struct of the device for which the interrupts * are free + * + * Must be invoked from within a msi_lock_descs() / msi_unlock_descs() + * pair. Use this for MSI irqdomains which implement their own vector + * allocation. */ -void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev) { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; + lockdep_assert_held(&dev->msi.data->mutex); + if (info->flags & MSI_FLAG_DEV_SYSFS) msi_device_destroy_sysfs(dev); ops->domain_free_irqs(domain, dev); } +/** + * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated to @dev + * @domain: The domain to managing the interrupts + * @dev: Pointer to device struct of the device for which the interrupts + * are free + */ +void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) +{ + msi_lock_descs(dev); + msi_domain_free_irqs_descs_locked(domain, dev); + msi_unlock_descs(dev); +} + /** * msi_get_domain_info - Get the MSI interrupt domain info for @domain * @domain: The interrupt domain to retrieve data from -- cgit v1.2.3 From 1046f71d7268b1680d7b044dea83c664403f6302 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:08 +0100 Subject: genirq/msi: Provide a set of advanced MSI accessors and iterators In preparation for dynamic handling of MSI-X interrupts provide a new set of MSI descriptor accessor functions and iterators. They are benefitial per se as they allow to cleanup quite some code in various MSI domain implementations. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210747.818635078@linutronix.de --- include/linux/msi.h | 33 ++++++++++++++++++ kernel/irq/msi.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 129 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 69c588efe85b..703221f7e9ea 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -140,6 +140,18 @@ struct msi_desc { struct pci_msi_desc pci; }; +/* + * Filter values for the MSI descriptor iterators and accessor functions. + */ +enum msi_desc_filter { + /* All descriptors */ + MSI_DESC_ALL, + /* Descriptors which have no interrupt associated */ + MSI_DESC_NOTASSOCIATED, + /* Descriptors which have an interrupt associated */ + MSI_DESC_ASSOCIATED, +}; + /** * msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers @@ -147,6 +159,7 @@ struct msi_desc { * @platform_data: Platform-MSI specific data * @list: List of MSI descriptors associated to the device * @mutex: Mutex protecting the MSI list + * @__next: Cached pointer to the next entry for iterators */ struct msi_device_data { unsigned long properties; @@ -154,6 +167,7 @@ struct msi_device_data { struct platform_msi_priv_data *platform_data; struct list_head list; struct mutex mutex; + struct msi_desc *__next; }; int msi_setup_device_data(struct device *dev); @@ -162,6 +176,25 @@ unsigned int msi_get_virq(struct device *dev, unsigned int index); void msi_lock_descs(struct device *dev); void msi_unlock_descs(struct device *dev); +struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter); +struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); + +/** + * msi_for_each_desc - Iterate the MSI descriptors + * + * @desc: struct msi_desc pointer used as iterator + * @dev: struct device pointer - device to iterate + * @filter: Filter for descriptor selection + * + * Notes: + * - The loop must be protected with a msi_lock_descs()/msi_unlock_descs() + * pair. + * - It is safe to remove a retrieved MSI descriptor in the loop. + */ +#define msi_for_each_desc(desc, dev, filter) \ + for ((desc) = msi_first_desc((dev), (filter)); (desc); \ + (desc) = msi_next_desc((dev), (filter))) + /* Helpers to hide struct msi_desc implementation details */ #define msi_desc_to_dev(desc) ((desc)->dev) #define dev_to_msi_list(dev) (&(dev)->msi.data->list) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 3b21e99bb793..bc67b2cafc9d 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -125,10 +125,106 @@ EXPORT_SYMBOL_GPL(msi_lock_descs); */ void msi_unlock_descs(struct device *dev) { + /* Clear the next pointer which was cached by the iterator */ + dev->msi.data->__next = NULL; mutex_unlock(&dev->msi.data->mutex); } EXPORT_SYMBOL_GPL(msi_unlock_descs); +static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) +{ + switch (filter) { + case MSI_DESC_ALL: + return true; + case MSI_DESC_NOTASSOCIATED: + return !desc->irq; + case MSI_DESC_ASSOCIATED: + return !!desc->irq; + } + WARN_ON_ONCE(1); + return false; +} + +static struct msi_desc *msi_find_first_desc(struct device *dev, enum msi_desc_filter filter) +{ + struct msi_desc *desc; + + list_for_each_entry(desc, dev_to_msi_list(dev), list) { + if (msi_desc_match(desc, filter)) + return desc; + } + return NULL; +} + +/** + * msi_first_desc - Get the first MSI descriptor of a device + * @dev: Device to operate on + * @filter: Descriptor state filter + * + * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs() + * must be invoked before the call. + * + * Return: Pointer to the first MSI descriptor matching the search + * criteria, NULL if none found. + */ +struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter) +{ + struct msi_desc *desc; + + if (WARN_ON_ONCE(!dev->msi.data)) + return NULL; + + lockdep_assert_held(&dev->msi.data->mutex); + + desc = msi_find_first_desc(dev, filter); + dev->msi.data->__next = desc ? list_next_entry(desc, list) : NULL; + return desc; +} +EXPORT_SYMBOL_GPL(msi_first_desc); + +static struct msi_desc *__msi_next_desc(struct device *dev, enum msi_desc_filter filter, + struct msi_desc *from) +{ + struct msi_desc *desc = from; + + list_for_each_entry_from(desc, dev_to_msi_list(dev), list) { + if (msi_desc_match(desc, filter)) + return desc; + } + return NULL; +} + +/** + * msi_next_desc - Get the next MSI descriptor of a device + * @dev: Device to operate on + * + * The first invocation of msi_next_desc() has to be preceeded by a + * successful incovation of __msi_first_desc(). Consecutive invocations are + * only valid if the previous one was successful. All these operations have + * to be done within the same MSI mutex held region. + * + * Return: Pointer to the next MSI descriptor matching the search + * criteria, NULL if none found. + */ +struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter) +{ + struct msi_device_data *data = dev->msi.data; + struct msi_desc *desc; + + if (WARN_ON_ONCE(!data)) + return NULL; + + lockdep_assert_held(&data->mutex); + + if (!data->__next) + return NULL; + + desc = __msi_next_desc(dev, filter, data->__next); + dev->msi.data->__next = desc ? list_next_entry(desc, list) : NULL; + return desc; +} +EXPORT_SYMBOL_GPL(msi_next_desc); + /** * msi_get_virq - Return Linux interrupt number of a MSI interrupt * @dev: Device to operate on -- cgit v1.2.3 From 602905253607ba892336f7bba8bb45b5be819d87 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:10 +0100 Subject: genirq/msi: Provide msi_alloc_msi_desc() and a simple allocator Provide msi_alloc_msi_desc() which takes a template MSI descriptor for initializing a newly allocated descriptor. This allows to simplify various usage sites of alloc_msi_entry() and moves the storage handling into the core code. For simple cases where only a linear vector space is required provide msi_add_simple_msi_descs() which just allocates a linear range of MSI descriptors and fills msi_desc::msi_index accordingly. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210747.873833567@linutronix.de --- include/linux/msi.h | 2 ++ kernel/irq/msi.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 703221f7e9ea..bbb8c1e2c18b 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -247,6 +247,8 @@ static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) } #endif /* CONFIG_PCI_MSI */ +int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); + struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, const struct irq_affinity_desc *affinity); void free_msi_entry(struct msi_desc *entry); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index bc67b2cafc9d..6ffe75eeba59 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -60,6 +60,65 @@ void free_msi_entry(struct msi_desc *entry) kfree(entry); } +/** + * msi_add_msi_desc - Allocate and initialize a MSI descriptor + * @dev: Pointer to the device for which the descriptor is allocated + * @init_desc: Pointer to an MSI descriptor to initialize the new descriptor + * + * Return: 0 on success or an appropriate failure code. + */ +int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) +{ + struct msi_desc *desc; + + lockdep_assert_held(&dev->msi.data->mutex); + + desc = alloc_msi_entry(dev, init_desc->nvec_used, init_desc->affinity); + if (!desc) + return -ENOMEM; + + /* Copy the MSI index and type specific data to the new descriptor. */ + desc->msi_index = init_desc->msi_index; + desc->pci = init_desc->pci; + + list_add_tail(&desc->list, &dev->msi.data->list); + return 0; +} + +/** + * msi_add_simple_msi_descs - Allocate and initialize MSI descriptors + * @dev: Pointer to the device for which the descriptors are allocated + * @index: Index for the first MSI descriptor + * @ndesc: Number of descriptors to allocate + * + * Return: 0 on success or an appropriate failure code. + */ +static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsigned int ndesc) +{ + struct msi_desc *desc, *tmp; + LIST_HEAD(list); + unsigned int i; + + lockdep_assert_held(&dev->msi.data->mutex); + + for (i = 0; i < ndesc; i++) { + desc = alloc_msi_entry(dev, 1, NULL); + if (!desc) + goto fail; + desc->msi_index = index + i; + list_add_tail(&desc->list, &list); + } + list_splice_tail(&list, &dev->msi.data->list); + return 0; + +fail: + list_for_each_entry_safe(desc, tmp, &list, list) { + list_del(&desc->list); + free_msi_entry(desc); + } + return -ENOMEM; +} + void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { *msg = entry->msg; -- cgit v1.2.3 From 645474e2cee450131e8b8d8a69a5d9bbabd43f3f Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:12 +0100 Subject: genirq/msi: Provide domain flags to allocate/free MSI descriptors automatically Provide domain info flags which tell the core to allocate simple descriptors or to free descriptors when the interrupts are freed and implement the required functionality. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210747.928198636@linutronix.de --- include/linux/msi.h | 17 +++++++++++++++++ kernel/irq/msi.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 65 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index bbb8c1e2c18b..17e47ab8d57a 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -105,6 +105,8 @@ struct pci_msi_desc { }; }; +#define MSI_MAX_INDEX ((unsigned int)USHRT_MAX) + /** * struct msi_desc - Descriptor structure for MSI based interrupts * @list: List head for management @@ -248,6 +250,17 @@ static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) #endif /* CONFIG_PCI_MSI */ int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc); +void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, + unsigned int first_index, unsigned int last_index); + +/** + * msi_free_msi_descs - Free MSI descriptors of a device + * @dev: Device to free the descriptors + */ +static inline void msi_free_msi_descs(struct device *dev) +{ + msi_free_msi_descs_range(dev, MSI_DESC_ALL, 0, MSI_MAX_INDEX); +} struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, const struct irq_affinity_desc *affinity); @@ -408,6 +421,10 @@ enum { MSI_FLAG_DEV_SYSFS = (1 << 7), /* MSI-X entries must be contiguous */ MSI_FLAG_MSIX_CONTIGUOUS = (1 << 8), + /* Allocate simple MSI descriptors */ + MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS = (1 << 9), + /* Free MSI descriptors */ + MSI_FLAG_FREE_MSI_DESCS = (1 << 10), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 6ffe75eeba59..b511dc1a0219 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -119,6 +119,32 @@ fail: return -ENOMEM; } +/** + * msi_free_msi_descs_range - Free MSI descriptors of a device + * @dev: Device to free the descriptors + * @filter: Descriptor state filter + * @first_index: Index to start freeing from + * @last_index: Last index to be freed + */ +void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, + unsigned int first_index, unsigned int last_index) +{ + struct msi_desc *desc; + + lockdep_assert_held(&dev->msi.data->mutex); + + msi_for_each_desc(desc, dev, filter) { + /* + * Stupid for now to handle MSI device domain until the + * storage is switched over to an xarray. + */ + if (desc->msi_index < first_index || desc->msi_index > last_index) + continue; + list_del(&desc->list); + free_msi_entry(desc); + } +} + void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) { *msg = entry->msg; @@ -879,6 +905,16 @@ skip_activate: return 0; } +static int msi_domain_add_simple_msi_descs(struct msi_domain_info *info, + struct device *dev, + unsigned int num_descs) +{ + if (!(info->flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS)) + return 0; + + return msi_add_simple_msi_descs(dev, 0, num_descs); +} + /** * msi_domain_alloc_irqs_descs_locked - Allocate interrupts from a MSI interrupt domain * @domain: The domain to allocate from @@ -901,6 +937,10 @@ int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device lockdep_assert_held(&dev->msi.data->mutex); + ret = msi_domain_add_simple_msi_descs(info, dev, nvec); + if (ret) + return ret; + ret = ops->domain_alloc_irqs(domain, dev, nvec); if (ret) goto cleanup; @@ -962,6 +1002,13 @@ void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) } } +static void msi_domain_free_msi_descs(struct msi_domain_info *info, + struct device *dev) +{ + if (info->flags & MSI_FLAG_FREE_MSI_DESCS) + msi_free_msi_descs(dev); +} + /** * msi_domain_free_irqs_descs_locked - Free interrupts from a MSI interrupt @domain associated to @dev * @domain: The domain to managing the interrupts @@ -982,6 +1029,7 @@ void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device if (info->flags & MSI_FLAG_DEV_SYSFS) msi_device_destroy_sysfs(dev); ops->domain_free_irqs(domain, dev); + msi_domain_free_msi_descs(info, dev); } /** -- cgit v1.2.3 From 7ad321a5eadb52b4af1c577dda51783e08235ea7 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:37 +0100 Subject: soc: ti: ti_sci_inta_msi: Remove ti_sci_inta_msi_domain_free_irqs() The function has no users and is pointless now that the core frees the MSI descriptors, which means potential users can just use msi_domain_free_irqs(). Signed-off-by: Thomas Gleixner Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210748.793119155@linutronix.de --- drivers/soc/ti/ti_sci_inta_msi.c | 6 ------ include/linux/soc/ti/ti_sci_inta_msi.h | 1 - 2 files changed, 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/soc/ti/ti_sci_inta_msi.c b/drivers/soc/ti/ti_sci_inta_msi.c index 31399118fcc6..991c78b34745 100644 --- a/drivers/soc/ti/ti_sci_inta_msi.c +++ b/drivers/soc/ti/ti_sci_inta_msi.c @@ -122,9 +122,3 @@ unlock: return ret; } EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_alloc_irqs); - -void ti_sci_inta_msi_domain_free_irqs(struct device *dev) -{ - msi_domain_free_irqs(dev->msi.domain, dev); -} -EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_free_irqs); diff --git a/include/linux/soc/ti/ti_sci_inta_msi.h b/include/linux/soc/ti/ti_sci_inta_msi.h index 25ea78a8ea5c..4dba2f2aff6f 100644 --- a/include/linux/soc/ti/ti_sci_inta_msi.h +++ b/include/linux/soc/ti/ti_sci_inta_msi.h @@ -18,5 +18,4 @@ struct irq_domain struct irq_domain *parent); int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev, struct ti_sci_resource *res); -void ti_sci_inta_msi_domain_free_irqs(struct device *dev); #endif /* __INCLUDE_LINUX_IRQCHIP_TI_SCI_INTA_H */ -- cgit v1.2.3 From ef8dd01538ea2553ab101ddce6a85a321406d9c0 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:44 +0100 Subject: genirq/msi: Make interrupt allocation less convoluted There is no real reason to do several loops over the MSI descriptors instead of just doing one loop. In case of an error everything is undone anyway so it does not matter whether it's a partial or a full rollback. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210749.010234767@linutronix.de --- .clang-format | 1 - include/linux/msi.h | 6 --- kernel/irq/msi.c | 129 ++++++++++++++++++++++++++++------------------------ 3 files changed, 69 insertions(+), 67 deletions(-) (limited to 'include/linux') diff --git a/.clang-format b/.clang-format index 15d4eaabc6b5..fa959436bcfd 100644 --- a/.clang-format +++ b/.clang-format @@ -216,7 +216,6 @@ ForEachMacros: - 'for_each_migratetype_order' - 'for_each_msi_entry' - 'for_each_msi_entry_safe' - - 'for_each_msi_vector' - 'for_each_net' - 'for_each_net_continue_reverse' - 'for_each_netdev' diff --git a/include/linux/msi.h b/include/linux/msi.h index 17e47ab8d57a..e8dd0be17e89 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -206,12 +206,6 @@ struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); list_for_each_entry((desc), dev_to_msi_list((dev)), list) #define for_each_msi_entry_safe(desc, tmp, dev) \ list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list) -#define for_each_msi_vector(desc, __irq, dev) \ - for_each_msi_entry((desc), (dev)) \ - if ((desc)->irq) \ - for (__irq = (desc)->irq; \ - __irq < ((desc)->irq + (desc)->nvec_used); \ - __irq++) #ifdef CONFIG_IRQ_MSI_IOMMU static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 09f34e17e891..bbe36e20a986 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -828,23 +828,74 @@ static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc, return allocated ? allocated : -ENOSPC; } +#define VIRQ_CAN_RESERVE 0x01 +#define VIRQ_ACTIVATE 0x02 +#define VIRQ_NOMASK_QUIRK 0x04 + +static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags) +{ + struct irq_data *irqd = irq_domain_get_irq_data(domain, virq); + int ret; + + if (!(vflags & VIRQ_CAN_RESERVE)) { + irqd_clr_can_reserve(irqd); + if (vflags & VIRQ_NOMASK_QUIRK) + irqd_set_msi_nomask_quirk(irqd); + } + + if (!(vflags & VIRQ_ACTIVATE)) + return 0; + + ret = irq_domain_activate_irq(irqd, vflags & VIRQ_CAN_RESERVE); + if (ret) + return ret; + /* + * If the interrupt uses reservation mode, clear the activated bit + * so request_irq() will assign the final vector. + */ + if (vflags & VIRQ_CAN_RESERVE) + irqd_clr_activated(irqd); + return 0; +} + int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec) { struct msi_domain_info *info = domain->host_data; struct msi_domain_ops *ops = info->ops; - struct irq_data *irq_data; - struct msi_desc *desc; msi_alloc_info_t arg = { }; + unsigned int vflags = 0; + struct msi_desc *desc; int allocated = 0; int i, ret, virq; - bool can_reserve; ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg); if (ret) return ret; - for_each_msi_entry(desc, dev) { + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (info->flags & MSI_FLAG_ACTIVATE_EARLY) + vflags |= VIRQ_ACTIVATE; + + /* + * Interrupt can use a reserved vector and will not occupy + * a real device vector until the interrupt is requested. + */ + if (msi_check_reservation_mode(domain, info, dev)) { + vflags |= VIRQ_CAN_RESERVE; + /* + * MSI affinity setting requires a special quirk (X86) when + * reservation mode is active. + */ + if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) + vflags |= VIRQ_NOMASK_QUIRK; + } + + msi_for_each_desc(desc, dev, MSI_DESC_NOTASSOCIATED) { ops->set_desc(&arg, desc); virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used, @@ -856,49 +907,12 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, for (i = 0; i < desc->nvec_used; i++) { irq_set_msi_desc_off(virq, i, desc); irq_debugfs_copy_devname(virq + i, dev); + ret = msi_init_virq(domain, virq + i, vflags); + if (ret) + return ret; } allocated++; } - - can_reserve = msi_check_reservation_mode(domain, info, dev); - - /* - * This flag is set by the PCI layer as we need to activate - * the MSI entries before the PCI layer enables MSI in the - * card. Otherwise the card latches a random msi message. - */ - if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY)) - goto skip_activate; - - for_each_msi_vector(desc, i, dev) { - if (desc->irq == i) { - virq = desc->irq; - dev_dbg(dev, "irq [%d-%d] for MSI\n", - virq, virq + desc->nvec_used - 1); - } - - irq_data = irq_domain_get_irq_data(domain, i); - if (!can_reserve) { - irqd_clr_can_reserve(irq_data); - if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK) - irqd_set_msi_nomask_quirk(irq_data); - } - ret = irq_domain_activate_irq(irq_data, can_reserve); - if (ret) - return ret; - } - -skip_activate: - /* - * If these interrupts use reservation mode, clear the activated bit - * so request_irq() will assign the final vector. - */ - if (can_reserve) { - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - irqd_clr_activated(irq_data); - } - } return 0; } @@ -976,26 +990,21 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nve void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { - struct irq_data *irq_data; + struct irq_data *irqd; struct msi_desc *desc; int i; - for_each_msi_vector(desc, i, dev) { - irq_data = irq_domain_get_irq_data(domain, i); - if (irqd_is_activated(irq_data)) - irq_domain_deactivate_irq(irq_data); - } - - for_each_msi_entry(desc, dev) { - /* - * We might have failed to allocate an MSI early - * enough that there is no IRQ associated to this - * entry. If that's the case, don't do anything. - */ - if (desc->irq) { - irq_domain_free_irqs(desc->irq, desc->nvec_used); - desc->irq = 0; + /* Only handle MSI entries which have an interrupt associated */ + msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) { + /* Make sure all interrupts are deactivated */ + for (i = 0; i < desc->nvec_used; i++) { + irqd = irq_domain_get_irq_data(domain, desc->irq + i); + if (irqd && irqd_is_activated(irqd)) + irq_domain_deactivate_irq(irqd); } + + irq_domain_free_irqs(desc->irq, desc->nvec_used); + desc->irq = 0; } } -- cgit v1.2.3 From cc9a246dbf6bdef56d9eee296a1db52dd0607976 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:47 +0100 Subject: genirq/msi: Mop up old interfaces Get rid of the old iterators, alloc/free functions and adjust the core code accordingly. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210749.117395027@linutronix.de --- include/linux/msi.h | 15 --------------- kernel/irq/msi.c | 31 +++++++++++++++---------------- 2 files changed, 15 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index e8dd0be17e89..b54010ba7b0d 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -197,15 +197,7 @@ struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter); for ((desc) = msi_first_desc((dev), (filter)); (desc); \ (desc) = msi_next_desc((dev), (filter))) -/* Helpers to hide struct msi_desc implementation details */ #define msi_desc_to_dev(desc) ((desc)->dev) -#define dev_to_msi_list(dev) (&(dev)->msi.data->list) -#define first_msi_entry(dev) \ - list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list) -#define for_each_msi_entry(desc, dev) \ - list_for_each_entry((desc), dev_to_msi_list((dev)), list) -#define for_each_msi_entry_safe(desc, tmp, dev) \ - list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list) #ifdef CONFIG_IRQ_MSI_IOMMU static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc) @@ -231,10 +223,6 @@ static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc, #endif #ifdef CONFIG_PCI_MSI -#define first_pci_msi_entry(pdev) first_msi_entry(&(pdev)->dev) -#define for_each_pci_msi_entry(desc, pdev) \ - for_each_msi_entry((desc), &(pdev)->dev) - struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc); void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg); #else /* CONFIG_PCI_MSI */ @@ -256,9 +244,6 @@ static inline void msi_free_msi_descs(struct device *dev) msi_free_msi_descs_range(dev, MSI_DESC_ALL, 0, MSI_MAX_INDEX); } -struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, - const struct irq_affinity_desc *affinity); -void free_msi_entry(struct msi_desc *entry); void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 745434efb557..e8c19740ca0c 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -19,8 +19,10 @@ #include "internals.h" +#define dev_to_msi_list(dev) (&(dev)->msi.data->list) + /** - * alloc_msi_entry - Allocate an initialized msi_desc + * msi_alloc_desc - Allocate an initialized msi_desc * @dev: Pointer to the device for which this is allocated * @nvec: The number of vectors used in this entry * @affinity: Optional pointer to an affinity mask array size of @nvec @@ -30,12 +32,11 @@ * * Return: pointer to allocated &msi_desc on success or %NULL on failure */ -struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, - const struct irq_affinity_desc *affinity) +static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec, + const struct irq_affinity_desc *affinity) { - struct msi_desc *desc; + struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL); - desc = kzalloc(sizeof(*desc), GFP_KERNEL); if (!desc) return NULL; @@ -43,21 +44,19 @@ struct msi_desc *alloc_msi_entry(struct device *dev, int nvec, desc->dev = dev; desc->nvec_used = nvec; if (affinity) { - desc->affinity = kmemdup(affinity, - nvec * sizeof(*desc->affinity), GFP_KERNEL); + desc->affinity = kmemdup(affinity, nvec * sizeof(*desc->affinity), GFP_KERNEL); if (!desc->affinity) { kfree(desc); return NULL; } } - return desc; } -void free_msi_entry(struct msi_desc *entry) +static void msi_free_desc(struct msi_desc *desc) { - kfree(entry->affinity); - kfree(entry); + kfree(desc->affinity); + kfree(desc); } /** @@ -73,7 +72,7 @@ int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) lockdep_assert_held(&dev->msi.data->mutex); - desc = alloc_msi_entry(dev, init_desc->nvec_used, init_desc->affinity); + desc = msi_alloc_desc(dev, init_desc->nvec_used, init_desc->affinity); if (!desc) return -ENOMEM; @@ -102,7 +101,7 @@ static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsi lockdep_assert_held(&dev->msi.data->mutex); for (i = 0; i < ndesc; i++) { - desc = alloc_msi_entry(dev, 1, NULL); + desc = msi_alloc_desc(dev, 1, NULL); if (!desc) goto fail; desc->msi_index = index + i; @@ -114,7 +113,7 @@ static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsi fail: list_for_each_entry_safe(desc, tmp, &list, list) { list_del(&desc->list); - free_msi_entry(desc); + msi_free_desc(desc); } return -ENOMEM; } @@ -141,7 +140,7 @@ void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, if (desc->msi_index < first_index || desc->msi_index > last_index) continue; list_del(&desc->list); - free_msi_entry(desc); + msi_free_desc(desc); } } @@ -745,7 +744,7 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, msi_lock_descs(dev); for (virq = virq_base; virq < virq_base + nvec; virq++) { - desc = alloc_msi_entry(dev, 1, NULL); + desc = msi_alloc_desc(dev, 1, NULL); if (!desc) { ret = -ENOMEM; goto fail; -- cgit v1.2.3 From ef3350c53d2aac65cf1c4ecc968bbb1de5f421ea Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:49 +0100 Subject: genirq/msi: Add abuse prevention comment to msi header Hope dies last. Signed-off-by: Thomas Gleixner Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210749.170847844@linutronix.de --- include/linux/msi.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index b54010ba7b0d..70cc6a555a8e 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -2,6 +2,20 @@ #ifndef LINUX_MSI_H #define LINUX_MSI_H +/* + * This header file contains MSI data structures and functions which are + * only relevant for: + * - Interrupt core code + * - PCI/MSI core code + * - MSI interrupt domain implementations + * - IOMMU, low level VFIO, NTB and other justified exceptions + * dealing with low level MSI details. + * + * Regular device drivers have no business with any of these functions and + * especially storing MSI descriptor pointers in random code is considered + * abuse. The only function which is relevant for drivers is msi_get_virq(). + */ + #include #include #include -- cgit v1.2.3 From bf5e758f02fc739589dcc6a3395c3a3eb77b5c90 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:50 +0100 Subject: genirq/msi: Simplify sysfs handling The sysfs handling for MSI is a convoluted maze and it is in the way of supporting dynamic expansion of the MSI-X vectors because it only supports a one off bulk population/free of the sysfs entries. Change it to do: 1) Creating an empty sysfs attribute group when msi_device_data is allocated 2) Populate the entries when the MSI descriptor is initialized 3) Free the entries when a MSI descriptor is detached from a Linux interrupt. 4) Provide functions for the legacy non-irqdomain fallback code to do a bulk population/free. This code won't support dynamic expansion. This makes the code simpler and reduces the number of allocations as the empty attribute group can be shared. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210749.224917330@linutronix.de --- include/linux/msi.h | 23 +++--- kernel/irq/msi.c | 198 ++++++++++++++++++++++++---------------------------- 2 files changed, 103 insertions(+), 118 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 70cc6a555a8e..1a00367d2cfa 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -71,7 +71,7 @@ struct irq_data; struct msi_desc; struct pci_dev; struct platform_msi_priv_data; -struct attribute_group; +struct device_attribute; void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg); #ifdef CONFIG_GENERIC_MSI_IRQ @@ -129,6 +129,7 @@ struct pci_msi_desc { * @dev: Pointer to the device which uses this descriptor * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor + * @sysfs_attr: Pointer to sysfs device attribute * * @write_msi_msg: Callback that may be called when the MSI message * address or data changes @@ -148,6 +149,9 @@ struct msi_desc { #ifdef CONFIG_IRQ_MSI_IOMMU const void *iommu_cookie; #endif +#ifdef CONFIG_SYSFS + struct device_attribute *sysfs_attrs; +#endif void (*write_msi_msg)(struct msi_desc *entry, void *data); void *write_msi_msg_data; @@ -171,7 +175,6 @@ enum msi_desc_filter { /** * msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers - * @attrs: Pointer to the sysfs attribute group * @platform_data: Platform-MSI specific data * @list: List of MSI descriptors associated to the device * @mutex: Mutex protecting the MSI list @@ -179,7 +182,6 @@ enum msi_desc_filter { */ struct msi_device_data { unsigned long properties; - const struct attribute_group **attrs; struct platform_msi_priv_data *platform_data; struct list_head list; struct mutex mutex; @@ -264,14 +266,6 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -#ifdef CONFIG_SYSFS -int msi_device_populate_sysfs(struct device *dev); -void msi_device_destroy_sysfs(struct device *dev); -#else /* CONFIG_SYSFS */ -static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } -static inline void msi_device_destroy_sysfs(struct device *dev) { } -#endif /* !CONFIG_SYSFS */ - /* * The arch hooks to setup up msi irqs. Default functions are implemented * as weak symbols so that they /can/ be overriden by architecture specific @@ -285,6 +279,13 @@ int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc); void arch_teardown_msi_irq(unsigned int irq); int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type); void arch_teardown_msi_irqs(struct pci_dev *dev); +#ifdef CONFIG_SYSFS +int msi_device_populate_sysfs(struct device *dev); +void msi_device_destroy_sysfs(struct device *dev); +#else /* CONFIG_SYSFS */ +static inline int msi_device_populate_sysfs(struct device *dev) { return 0; } +static inline void msi_device_destroy_sysfs(struct device *dev) { } +#endif /* !CONFIG_SYSFS */ #endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */ /* diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index e8c19740ca0c..d290e09258bc 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -19,6 +19,7 @@ #include "internals.h" +static inline int msi_sysfs_create_group(struct device *dev); #define dev_to_msi_list(dev) (&(dev)->msi.data->list) /** @@ -178,6 +179,7 @@ static void msi_device_data_release(struct device *dev, void *res) int msi_setup_device_data(struct device *dev) { struct msi_device_data *md; + int ret; if (dev->msi.data) return 0; @@ -186,6 +188,12 @@ int msi_setup_device_data(struct device *dev) if (!md) return -ENOMEM; + ret = msi_sysfs_create_group(dev); + if (ret) { + devres_free(md); + return ret; + } + INIT_LIST_HEAD(&md->list); mutex_init(&md->mutex); dev->msi.data = md; @@ -351,6 +359,20 @@ unsigned int msi_get_virq(struct device *dev, unsigned int index) EXPORT_SYMBOL_GPL(msi_get_virq); #ifdef CONFIG_SYSFS +static struct attribute *msi_dev_attrs[] = { + NULL +}; + +static const struct attribute_group msi_irqs_group = { + .name = "msi_irqs", + .attrs = msi_dev_attrs, +}; + +static inline int msi_sysfs_create_group(struct device *dev) +{ + return devm_device_add_group(dev, &msi_irqs_group); +} + static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -360,97 +382,74 @@ static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr, return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi"); } -/** - * msi_populate_sysfs - Populate msi_irqs sysfs entries for devices - * @dev: The device(PCI, platform etc) who will get sysfs entries - */ -static const struct attribute_group **msi_populate_sysfs(struct device *dev) +static void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { - const struct attribute_group **msi_irq_groups; - struct attribute **msi_attrs, *msi_attr; - struct device_attribute *msi_dev_attr; - struct attribute_group *msi_irq_group; - struct msi_desc *entry; - int ret = -ENOMEM; - int num_msi = 0; - int count = 0; + struct device_attribute *attrs = desc->sysfs_attrs; int i; - /* Determine how many msi entries we have */ - msi_for_each_desc(entry, dev, MSI_DESC_ALL) - num_msi += entry->nvec_used; - if (!num_msi) - return NULL; + if (!attrs) + return; - /* Dynamically create the MSI attributes for the device */ - msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL); - if (!msi_attrs) - return ERR_PTR(-ENOMEM); - - msi_for_each_desc(entry, dev, MSI_DESC_ALL) { - for (i = 0; i < entry->nvec_used; i++) { - msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL); - if (!msi_dev_attr) - goto error_attrs; - msi_attrs[count] = &msi_dev_attr->attr; - - sysfs_attr_init(&msi_dev_attr->attr); - msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d", - entry->irq + i); - if (!msi_dev_attr->attr.name) - goto error_attrs; - msi_dev_attr->attr.mode = 0444; - msi_dev_attr->show = msi_mode_show; - ++count; - } + desc->sysfs_attrs = NULL; + for (i = 0; i < desc->nvec_used; i++) { + if (attrs[i].show) + sysfs_remove_file_from_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name); + kfree(attrs[i].attr.name); } + kfree(attrs); +} - msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL); - if (!msi_irq_group) - goto error_attrs; - msi_irq_group->name = "msi_irqs"; - msi_irq_group->attrs = msi_attrs; +static int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) +{ + struct device_attribute *attrs; + int ret, i; - msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL); - if (!msi_irq_groups) - goto error_irq_group; - msi_irq_groups[0] = msi_irq_group; + attrs = kcalloc(desc->nvec_used, sizeof(*attrs), GFP_KERNEL); + if (!attrs) + return -ENOMEM; - ret = sysfs_create_groups(&dev->kobj, msi_irq_groups); - if (ret) - goto error_irq_groups; - - return msi_irq_groups; - -error_irq_groups: - kfree(msi_irq_groups); -error_irq_group: - kfree(msi_irq_group); -error_attrs: - count = 0; - msi_attr = msi_attrs[count]; - while (msi_attr) { - msi_dev_attr = container_of(msi_attr, struct device_attribute, attr); - kfree(msi_attr->name); - kfree(msi_dev_attr); - ++count; - msi_attr = msi_attrs[count]; + desc->sysfs_attrs = attrs; + for (i = 0; i < desc->nvec_used; i++) { + sysfs_attr_init(&attrs[i].attr); + attrs[i].attr.name = kasprintf(GFP_KERNEL, "%d", desc->irq + i); + if (!attrs[i].attr.name) { + ret = -ENOMEM; + goto fail; + } + + attrs[i].attr.mode = 0444; + attrs[i].show = msi_mode_show; + + ret = sysfs_add_file_to_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name); + if (ret) { + attrs[i].show = NULL; + goto fail; + } } - kfree(msi_attrs); - return ERR_PTR(ret); + return 0; + +fail: + msi_sysfs_remove_desc(dev, desc); + return ret; } +#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS /** * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device * @dev: The device (PCI, platform etc) which will get sysfs entries */ int msi_device_populate_sysfs(struct device *dev) { - const struct attribute_group **group = msi_populate_sysfs(dev); + struct msi_desc *desc; + int ret; - if (IS_ERR(group)) - return PTR_ERR(group); - dev->msi.data->attrs = group; + msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) { + if (desc->sysfs_attrs) + continue; + ret = msi_sysfs_populate_desc(dev, desc); + if (ret) + return ret; + } return 0; } @@ -461,28 +460,17 @@ int msi_device_populate_sysfs(struct device *dev) */ void msi_device_destroy_sysfs(struct device *dev) { - const struct attribute_group **msi_irq_groups = dev->msi.data->attrs; - struct device_attribute *dev_attr; - struct attribute **msi_attrs; - int count = 0; - - dev->msi.data->attrs = NULL; - if (!msi_irq_groups) - return; + struct msi_desc *desc; - sysfs_remove_groups(&dev->kobj, msi_irq_groups); - msi_attrs = msi_irq_groups[0]->attrs; - while (msi_attrs[count]) { - dev_attr = container_of(msi_attrs[count], struct device_attribute, attr); - kfree(dev_attr->attr.name); - kfree(dev_attr); - ++count; - } - kfree(msi_attrs); - kfree(msi_irq_groups[0]); - kfree(msi_irq_groups); + msi_for_each_desc(desc, dev, MSI_DESC_ALL) + msi_sysfs_remove_desc(dev, desc); } -#endif +#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */ +#else /* CONFIG_SYSFS */ +static inline int msi_sysfs_create_group(struct device *dev) { return 0; } +static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; } +static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { } +#endif /* !CONFIG_SYSFS */ #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN static inline void irq_chip_write_msi_msg(struct irq_data *data, @@ -914,6 +902,12 @@ int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, ret = msi_init_virq(domain, virq + i, vflags); if (ret) return ret; + + if (info->flags & MSI_FLAG_DEV_SYSFS) { + ret = msi_sysfs_populate_desc(dev, desc); + if (ret) + return ret; + } } allocated++; } @@ -958,18 +952,7 @@ int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device ret = ops->domain_alloc_irqs(domain, dev, nvec); if (ret) - goto cleanup; - - if (!(info->flags & MSI_FLAG_DEV_SYSFS)) - return 0; - - ret = msi_device_populate_sysfs(dev); - if (ret) - goto cleanup; - return 0; - -cleanup: - msi_domain_free_irqs_descs_locked(domain, dev); + msi_domain_free_irqs_descs_locked(domain, dev); return ret; } @@ -994,6 +977,7 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nve void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) { + struct msi_domain_info *info = domain->host_data; struct irq_data *irqd; struct msi_desc *desc; int i; @@ -1008,6 +992,8 @@ void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev) } irq_domain_free_irqs(desc->irq, desc->nvec_used); + if (info->flags & MSI_FLAG_DEV_SYSFS) + msi_sysfs_remove_desc(dev, desc); desc->irq = 0; } } @@ -1036,8 +1022,6 @@ void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device lockdep_assert_held(&dev->msi.data->mutex); - if (info->flags & MSI_FLAG_DEV_SYSFS) - msi_device_destroy_sysfs(dev); ops->domain_free_irqs(domain, dev); msi_domain_free_msi_descs(info, dev); } -- cgit v1.2.3 From cd6cf06590b9792340dceaa285138777f3cc4d90 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 6 Dec 2021 23:51:52 +0100 Subject: genirq/msi: Convert storage to xarray The current linked list storage for MSI descriptors is suboptimal in several ways: 1) Looking up a MSI desciptor requires a O(n) list walk in the worst case 2) The upcoming support of runtime expansion of MSI-X vectors would need to do a full list walk to figure out whether a particular index is already associated. 3) Runtime expansion of sparse allocations is even more complex as the current implementation assumes an ordered list (increasing MSI index). Use an xarray which solves all of the above problems nicely. Signed-off-by: Thomas Gleixner Tested-by: Michael Kelley Tested-by: Nishanth Menon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Jason Gunthorpe Link: https://lore.kernel.org/r/20211206210749.280627070@linutronix.de --- include/linux/msi.h | 13 ++-- kernel/irq/msi.c | 169 ++++++++++++++++++++++++---------------------------- 2 files changed, 83 insertions(+), 99 deletions(-) (limited to 'include/linux') diff --git a/include/linux/msi.h b/include/linux/msi.h index 1a00367d2cfa..fc918a658d48 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -17,6 +17,7 @@ */ #include +#include #include #include #include @@ -123,7 +124,6 @@ struct pci_msi_desc { /** * struct msi_desc - Descriptor structure for MSI based interrupts - * @list: List head for management * @irq: The base interrupt number * @nvec_used: The number of vectors used * @dev: Pointer to the device which uses this descriptor @@ -140,7 +140,6 @@ struct pci_msi_desc { */ struct msi_desc { /* Shared device/bus type independent data */ - struct list_head list; unsigned int irq; unsigned int nvec_used; struct device *dev; @@ -176,16 +175,16 @@ enum msi_desc_filter { * msi_device_data - MSI per device data * @properties: MSI properties which are interesting to drivers * @platform_data: Platform-MSI specific data - * @list: List of MSI descriptors associated to the device - * @mutex: Mutex protecting the MSI list - * @__next: Cached pointer to the next entry for iterators + * @mutex: Mutex protecting the MSI descriptor store + * @__store: Xarray for storing MSI descriptor pointers + * @__iter_idx: Index to search the next entry for iterators */ struct msi_device_data { unsigned long properties; struct platform_msi_priv_data *platform_data; - struct list_head list; struct mutex mutex; - struct msi_desc *__next; + struct xarray __store; + unsigned long __iter_idx; }; int msi_setup_device_data(struct device *dev); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index d290e09258bc..173bc04f9fe5 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -20,7 +20,6 @@ #include "internals.h" static inline int msi_sysfs_create_group(struct device *dev); -#define dev_to_msi_list(dev) (&(dev)->msi.data->list) /** * msi_alloc_desc - Allocate an initialized msi_desc @@ -41,7 +40,6 @@ static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec, if (!desc) return NULL; - INIT_LIST_HEAD(&desc->list); desc->dev = dev; desc->nvec_used = nvec; if (affinity) { @@ -60,6 +58,17 @@ static void msi_free_desc(struct msi_desc *desc) kfree(desc); } +static int msi_insert_desc(struct msi_device_data *md, struct msi_desc *desc, unsigned int index) +{ + int ret; + + desc->msi_index = index; + ret = xa_insert(&md->__store, index, desc, GFP_KERNEL); + if (ret) + msi_free_desc(desc); + return ret; +} + /** * msi_add_msi_desc - Allocate and initialize a MSI descriptor * @dev: Pointer to the device for which the descriptor is allocated @@ -77,12 +86,9 @@ int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) if (!desc) return -ENOMEM; - /* Copy the MSI index and type specific data to the new descriptor. */ - desc->msi_index = init_desc->msi_index; + /* Copy type specific data to the new descriptor. */ desc->pci = init_desc->pci; - - list_add_tail(&desc->list, &dev->msi.data->list); - return 0; + return msi_insert_desc(dev->msi.data, desc, init_desc->msi_index); } /** @@ -95,28 +101,41 @@ int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc) */ static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsigned int ndesc) { - struct msi_desc *desc, *tmp; - LIST_HEAD(list); - unsigned int i; + unsigned int idx, last = index + ndesc - 1; + struct msi_desc *desc; + int ret; lockdep_assert_held(&dev->msi.data->mutex); - for (i = 0; i < ndesc; i++) { + for (idx = index; idx <= last; idx++) { desc = msi_alloc_desc(dev, 1, NULL); if (!desc) + goto fail_mem; + ret = msi_insert_desc(dev->msi.data, desc, idx); + if (ret) goto fail; - desc->msi_index = index + i; - list_add_tail(&desc->list, &list); } - list_splice_tail(&list, &dev->msi.data->list); return 0; +fail_mem: + ret = -ENOMEM; fail: - list_for_each_entry_safe(desc, tmp, &list, list) { - list_del(&desc->list); - msi_free_desc(desc); + msi_free_msi_descs_range(dev, MSI_DESC_NOTASSOCIATED, index, last); + return ret; +} + +static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) +{ + switch (filter) { + case MSI_DESC_ALL: + return true; + case MSI_DESC_NOTASSOCIATED: + return !desc->irq; + case MSI_DESC_ASSOCIATED: + return !!desc->irq; } - return -ENOMEM; + WARN_ON_ONCE(1); + return false; } /** @@ -129,19 +148,17 @@ fail: void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter, unsigned int first_index, unsigned int last_index) { + struct xarray *xa = &dev->msi.data->__store; struct msi_desc *desc; + unsigned long idx; lockdep_assert_held(&dev->msi.data->mutex); - msi_for_each_desc(desc, dev, filter) { - /* - * Stupid for now to handle MSI device domain until the - * storage is switched over to an xarray. - */ - if (desc->msi_index < first_index || desc->msi_index > last_index) - continue; - list_del(&desc->list); - msi_free_desc(desc); + xa_for_each_range(xa, idx, desc, first_index, last_index) { + if (msi_desc_match(desc, filter)) { + xa_erase(xa, idx); + msi_free_desc(desc); + } } } @@ -162,7 +179,8 @@ static void msi_device_data_release(struct device *dev, void *res) { struct msi_device_data *md = res; - WARN_ON_ONCE(!list_empty(&md->list)); + WARN_ON_ONCE(!xa_empty(&md->__store)); + xa_destroy(&md->__store); dev->msi.data = NULL; } @@ -194,7 +212,7 @@ int msi_setup_device_data(struct device *dev) return ret; } - INIT_LIST_HEAD(&md->list); + xa_init(&md->__store); mutex_init(&md->mutex); dev->msi.data = md; devres_add(dev, md); @@ -217,34 +235,21 @@ EXPORT_SYMBOL_GPL(msi_lock_descs); */ void msi_unlock_descs(struct device *dev) { - /* Clear the next pointer which was cached by the iterator */ - dev->msi.data->__next = NULL; + /* Invalidate the index wich was cached by the iterator */ + dev->msi.data->__iter_idx = MSI_MAX_INDEX; mutex_unlock(&dev->msi.data->mutex); } EXPORT_SYMBOL_GPL(msi_unlock_descs); -static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter) -{ - switch (filter) { - case MSI_DESC_ALL: - return true; - case MSI_DESC_NOTASSOCIATED: - return !desc->irq; - case MSI_DESC_ASSOCIATED: - return !!desc->irq; - } - WARN_ON_ONCE(1); - return false; -} - -static struct msi_desc *msi_find_first_desc(struct device *dev, enum msi_desc_filter filter) +static struct msi_desc *msi_find_desc(struct msi_device_data *md, enum msi_desc_filter filter) { struct msi_desc *desc; - list_for_each_entry(desc, dev_to_msi_list(dev), list) { + xa_for_each_start(&md->__store, md->__iter_idx, desc, md->__iter_idx) { if (msi_desc_match(desc, filter)) return desc; } + md->__iter_idx = MSI_MAX_INDEX; return NULL; } @@ -261,37 +266,24 @@ static struct msi_desc *msi_find_first_desc(struct device *dev, enum msi_desc_fi */ struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter) { - struct msi_desc *desc; + struct msi_device_data *md = dev->msi.data; - if (WARN_ON_ONCE(!dev->msi.data)) + if (WARN_ON_ONCE(!md)) return NULL; - lockdep_assert_held(&dev->msi.data->mutex); + lockdep_assert_held(&md->mutex); - desc = msi_find_first_desc(dev, filter); - dev->msi.data->__next = desc ? list_next_entry(desc, list) : NULL; - return desc; + md->__iter_idx = 0; + return msi_find_desc(md, filter); } EXPORT_SYMBOL_GPL(msi_first_desc); -static struct msi_desc *__msi_next_desc(struct device *dev, enum msi_desc_filter filter, - struct msi_desc *from) -{ - struct msi_desc *desc = from; - - list_for_each_entry_from(desc, dev_to_msi_list(dev), list) { - if (msi_desc_match(desc, filter)) - return desc; - } - return NULL; -} - /** * msi_next_desc - Get the next MSI descriptor of a device * @dev: Device to operate on * * The first invocation of msi_next_desc() has to be preceeded by a - * successful incovation of __msi_first_desc(). Consecutive invocations are + * successful invocation of __msi_first_desc(). Consecutive invocations are * only valid if the previous one was successful. All these operations have * to be done within the same MSI mutex held region. * @@ -300,20 +292,18 @@ static struct msi_desc *__msi_next_desc(struct device *dev, enum msi_desc_filter */ struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter) { - struct msi_device_data *data = dev->msi.data; - struct msi_desc *desc; + struct msi_device_data *md = dev->msi.data; - if (WARN_ON_ONCE(!data)) + if (WARN_ON_ONCE(!md)) return NULL; - lockdep_assert_held(&data->mutex); + lockdep_assert_held(&md->mutex); - if (!data->__next) + if (md->__iter_idx >= (unsigned long)MSI_MAX_INDEX) return NULL; - desc = __msi_next_desc(dev, filter, data->__next); - dev->msi.data->__next = desc ? list_next_entry(desc, list) : NULL; - return desc; + md->__iter_idx++; + return msi_find_desc(md, filter); } EXPORT_SYMBOL_GPL(msi_next_desc); @@ -336,21 +326,18 @@ unsigned int msi_get_virq(struct device *dev, unsigned int index) pcimsi = dev_is_pci(dev) ? to_pci_dev(dev)->msi_enabled : false; msi_lock_descs(dev); - msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) { - /* PCI-MSI has only one descriptor for multiple interrupts. */ - if (pcimsi) { - if (index < desc->nvec_used) - ret = desc->irq + index; - break; - } - + desc = xa_load(&dev->msi.data->__store, pcimsi ? 0 : index); + if (desc && desc->irq) { /* + * PCI-MSI has only one descriptor for multiple interrupts. * PCI-MSIX and platform MSI use a descriptor per * interrupt. */ - if (desc->msi_index == index) { + if (pcimsi) { + if (index < desc->nvec_used) + ret = desc->irq + index; + } else { ret = desc->irq; - break; } } msi_unlock_descs(dev); @@ -731,16 +718,13 @@ int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev, int ret, virq; msi_lock_descs(dev); - for (virq = virq_base; virq < virq_base + nvec; virq++) { - desc = msi_alloc_desc(dev, 1, NULL); - if (!desc) { - ret = -ENOMEM; - goto fail; - } + ret = msi_add_simple_msi_descs(dev, virq_base, nvec); + if (ret) + goto unlock; - desc->msi_index = virq; + for (virq = virq_base; virq < virq_base + nvec; virq++) { + desc = xa_load(&dev->msi.data->__store, virq); desc->irq = virq; - list_add_tail(&desc->list, &dev->msi.data->list); ops->set_desc(arg, desc); ret = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg); @@ -756,6 +740,7 @@ fail: for (--virq; virq >= virq_base; virq--) irq_domain_free_irqs_common(domain, virq, 1); msi_free_msi_descs_range(dev, MSI_DESC_ALL, virq_base, virq_base + nvec - 1); +unlock: msi_unlock_descs(dev); return ret; } -- cgit v1.2.3 From 60f20d84dc813f1342771a3e4f06d89da26dc412 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 18 Nov 2021 12:12:10 -0600 Subject: of/fdt: Rework early_init_dt_scan_chosen() to call directly Use of the of_scan_flat_dt() function predates libfdt and is discouraged as libfdt provides a nicer set of APIs. Rework early_init_dt_scan_chosen() to be called directly and use libfdt. Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Frank Rowand Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Rob Herring Reviewed-by: Frank Rowand Link: https://lore.kernel.org/r/20211118181213.1433346-2-robh@kernel.org --- arch/powerpc/kernel/prom.c | 2 +- arch/powerpc/mm/nohash/kaslr_booke.c | 4 +--- drivers/of/fdt.c | 39 ++++++++++++++++++------------------ include/linux/of_fdt.h | 3 +-- 4 files changed, 22 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 2e67588f6f6e..c6c398ccd98a 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -402,7 +402,7 @@ static int __init early_init_dt_scan_chosen_ppc(unsigned long node, const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */ /* Use common scan routine to determine if this is the chosen node */ - if (early_init_dt_scan_chosen(node, uname, depth, data) == 0) + if (early_init_dt_scan_chosen(data) < 0) return 0; #ifdef CONFIG_PPC64 diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c index 8fc49b1b4a91..90debe19ab4c 100644 --- a/arch/powerpc/mm/nohash/kaslr_booke.c +++ b/arch/powerpc/mm/nohash/kaslr_booke.c @@ -44,9 +44,7 @@ struct regions __initdata regions; static __init void kaslr_get_cmdline(void *fdt) { - int node = fdt_path_offset(fdt, "/chosen"); - - early_init_dt_scan_chosen(node, "chosen", 1, boot_command_line); + early_init_dt_scan_chosen(boot_command_line); } static unsigned long __init rotate_xor(unsigned long hash, const void *area, diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index bdca35284ceb..1f1705f76263 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1124,18 +1124,18 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname, return 0; } -int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, - int depth, void *data) +int __init early_init_dt_scan_chosen(char *cmdline) { - int l; + int l, node; const char *p; const void *rng_seed; + const void *fdt = initial_boot_params; - pr_debug("search \"chosen\", depth: %d, uname: %s\n", depth, uname); - - if (depth != 1 || !data || - (strcmp(uname, "chosen") != 0 && strcmp(uname, "chosen@0") != 0)) - return 0; + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + node = fdt_path_offset(fdt, "/chosen@0"); + if (node < 0) + return -ENOENT; early_init_dt_check_for_initrd(node); early_init_dt_check_for_elfcorehdr(node); @@ -1144,7 +1144,7 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, /* Retrieve command line */ p = of_get_flat_dt_prop(node, "bootargs", &l); if (p != NULL && l > 0) - strlcpy(data, p, min(l, COMMAND_LINE_SIZE)); + strlcpy(cmdline, p, min(l, COMMAND_LINE_SIZE)); /* * CONFIG_CMDLINE is meant to be a default in case nothing else @@ -1153,18 +1153,18 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, */ #ifdef CONFIG_CMDLINE #if defined(CONFIG_CMDLINE_EXTEND) - strlcat(data, " ", COMMAND_LINE_SIZE); - strlcat(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + strlcat(cmdline, " ", COMMAND_LINE_SIZE); + strlcat(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); #elif defined(CONFIG_CMDLINE_FORCE) - strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + strlcpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); #else /* No arguments from boot loader, use kernel's cmdl*/ - if (!((char *)data)[0]) - strlcpy(data, CONFIG_CMDLINE, COMMAND_LINE_SIZE); + if (!((char *)cmdline)[0]) + strlcpy(cmdline, CONFIG_CMDLINE, COMMAND_LINE_SIZE); #endif #endif /* CONFIG_CMDLINE */ - pr_debug("Command line is: %s\n", (char *)data); + pr_debug("Command line is: %s\n", (char *)cmdline); rng_seed = of_get_flat_dt_prop(node, "rng-seed", &l); if (rng_seed && l > 0) { @@ -1178,8 +1178,7 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, fdt_totalsize(initial_boot_params)); } - /* break now */ - return 1; + return 0; } #ifndef MIN_MEMBLOCK_ADDR @@ -1261,14 +1260,14 @@ bool __init early_init_dt_verify(void *params) void __init early_init_dt_scan_nodes(void) { - int rc = 0; + int rc; /* Initialize {size,address}-cells info */ of_scan_flat_dt(early_init_dt_scan_root, NULL); /* Retrieve various information from the /chosen node */ - rc = of_scan_flat_dt(early_init_dt_scan_chosen, boot_command_line); - if (!rc) + rc = early_init_dt_scan_chosen(boot_command_line); + if (rc) pr_warn("No chosen node found, continuing without\n"); /* Setup memory, calling early_init_dt_add_memory_arch */ diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index cf48983d3c86..654722235df6 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -58,8 +58,7 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern unsigned long of_get_flat_dt_root(void); extern uint32_t of_get_flat_dt_phandle(unsigned long node); -extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_chosen(char *cmdline); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); extern int early_init_dt_scan_chosen_stdout(void); -- cgit v1.2.3 From d665881d2171b62ca1ea23be89be6f2a8a330bb2 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Thu, 18 Nov 2021 12:12:11 -0600 Subject: of/fdt: Rework early_init_dt_scan_root() to call directly Use of the of_scan_flat_dt() function predates libfdt and is discouraged as libfdt provides a nicer set of APIs. Rework early_init_dt_scan_root() to be called directly and use libfdt. Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Frank Rowand Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Rob Herring Reviewed-by: Frank Rowand Link: https://lore.kernel.org/r/20211118181213.1433346-3-robh@kernel.org --- arch/powerpc/kernel/prom.c | 4 ++-- drivers/of/fdt.c | 14 +++++++------- include/linux/of_fdt.h | 3 +-- 3 files changed, 10 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index c6c398ccd98a..6e1a106f02eb 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -748,7 +748,7 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line); /* Scan memory nodes and rebuild MEMBLOCKs */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); + early_init_dt_scan_root(); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); parse_early_param(); @@ -857,7 +857,7 @@ void __init early_get_first_memblock_info(void *params, phys_addr_t *size) * mess the memblock. */ add_mem_to_memblock = 0; - of_scan_flat_dt(early_init_dt_scan_root, NULL); + early_init_dt_scan_root(); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); add_mem_to_memblock = 1; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 1f1705f76263..5e216555fe4f 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1042,13 +1042,14 @@ int __init early_init_dt_scan_chosen_stdout(void) /* * early_init_dt_scan_root - fetch the top level address and size cells */ -int __init early_init_dt_scan_root(unsigned long node, const char *uname, - int depth, void *data) +int __init early_init_dt_scan_root(void) { const __be32 *prop; + const void *fdt = initial_boot_params; + int node = fdt_path_offset(fdt, "/"); - if (depth != 0) - return 0; + if (node < 0) + return -ENODEV; dt_root_size_cells = OF_ROOT_NODE_SIZE_CELLS_DEFAULT; dt_root_addr_cells = OF_ROOT_NODE_ADDR_CELLS_DEFAULT; @@ -1063,8 +1064,7 @@ int __init early_init_dt_scan_root(unsigned long node, const char *uname, dt_root_addr_cells = be32_to_cpup(prop); pr_debug("dt_root_addr_cells = %x\n", dt_root_addr_cells); - /* break now */ - return 1; + return 0; } u64 __init dt_mem_next_cell(int s, const __be32 **cellp) @@ -1263,7 +1263,7 @@ void __init early_init_dt_scan_nodes(void) int rc; /* Initialize {size,address}-cells info */ - of_scan_flat_dt(early_init_dt_scan_root, NULL); + early_init_dt_scan_root(); /* Retrieve various information from the /chosen node */ rc = early_init_dt_scan_chosen(boot_command_line); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 654722235df6..df3d31926c3c 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -68,8 +68,7 @@ extern void early_init_dt_add_memory_arch(u64 base, u64 size); extern u64 dt_mem_next_cell(int s, const __be32 **cellp); /* Early flat tree scan hooks */ -extern int early_init_dt_scan_root(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_root(void); extern bool early_init_dt_scan(void *params); extern bool early_init_dt_verify(void *params); -- cgit v1.2.3 From 1f012283e9360fb4007308f04cfaeb205e34b684 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 15 Dec 2021 09:01:02 -0600 Subject: of/fdt: Rework early_init_dt_scan_memory() to call directly Use of the of_scan_flat_dt() function predates libfdt and is discouraged as libfdt provides a nicer set of APIs. Rework early_init_dt_scan_memory() to be called directly and use libfdt. Cc: John Crispin Cc: Thomas Bogendoerfer Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Frank Rowand Cc: linux-mips@vger.kernel.org Cc: linuxppc-dev@lists.ozlabs.org Reviewed-by: Frank Rowand Signed-off-by: Rob Herring Tested-by: Michael Ellerman Link: https://lore.kernel.org/r/20211215150102.1303588-1-robh@kernel.org --- arch/mips/ralink/of.c | 19 +++---------- arch/powerpc/kernel/prom.c | 21 +++++++------- drivers/of/fdt.c | 68 ++++++++++++++++++++++++---------------------- include/linux/of_fdt.h | 3 +- 4 files changed, 51 insertions(+), 60 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 0135376c5de5..35a87a2da10b 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -53,17 +53,6 @@ void __init device_tree_init(void) unflatten_and_copy_device_tree(); } -static int memory_dtb; - -static int __init early_init_dt_find_memory(unsigned long node, - const char *uname, int depth, void *data) -{ - if (depth == 1 && !strcmp(uname, "memory@0")) - memory_dtb = 1; - - return 0; -} - void __init plat_mem_setup(void) { void *dtb; @@ -77,10 +66,10 @@ void __init plat_mem_setup(void) dtb = get_fdt(); __dt_setup_arch(dtb); - of_scan_flat_dt(early_init_dt_find_memory, NULL); - if (memory_dtb) - of_scan_flat_dt(early_init_dt_scan_memory, NULL); - else if (soc_info.mem_detect) + if (!early_init_dt_scan_memory()) + return; + + if (soc_info.mem_detect) soc_info.mem_detect(); else if (soc_info.mem_size) memblock_add(soc_info.mem_base, soc_info.mem_size * SZ_1M); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 6e1a106f02eb..ad1230c4f3fe 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -532,19 +532,18 @@ static int __init early_init_drmem_lmb(struct drmem_lmb *lmb, } #endif /* CONFIG_PPC_PSERIES */ -static int __init early_init_dt_scan_memory_ppc(unsigned long node, - const char *uname, - int depth, void *data) +static int __init early_init_dt_scan_memory_ppc(void) { #ifdef CONFIG_PPC_PSERIES - if (depth == 1 && - strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) { + const void *fdt = initial_boot_params; + int node = fdt_path_offset(fdt, "/ibm,dynamic-reconfiguration-memory"); + + if (node > 0) walk_drmem_lmbs_early(node, NULL, early_init_drmem_lmb); - return 0; - } + #endif - - return early_init_dt_scan_memory(node, uname, depth, data); + + return early_init_dt_scan_memory(); } /* @@ -749,7 +748,7 @@ void __init early_init_devtree(void *params) /* Scan memory nodes and rebuild MEMBLOCKs */ early_init_dt_scan_root(); - of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + early_init_dt_scan_memory_ppc(); parse_early_param(); @@ -858,7 +857,7 @@ void __init early_get_first_memblock_info(void *params, phys_addr_t *size) */ add_mem_to_memblock = 0; early_init_dt_scan_root(); - of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); + early_init_dt_scan_memory_ppc(); add_mem_to_memblock = 1; if (size) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 5e216555fe4f..a835c458f50a 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1078,49 +1078,53 @@ u64 __init dt_mem_next_cell(int s, const __be32 **cellp) /* * early_init_dt_scan_memory - Look for and parse memory nodes */ -int __init early_init_dt_scan_memory(unsigned long node, const char *uname, - int depth, void *data) +int __init early_init_dt_scan_memory(void) { - const char *type = of_get_flat_dt_prop(node, "device_type", NULL); - const __be32 *reg, *endp; - int l; - bool hotpluggable; + int node; + const void *fdt = initial_boot_params; - /* We are scanning "memory" nodes only */ - if (type == NULL || strcmp(type, "memory") != 0) - return 0; + fdt_for_each_subnode(node, fdt, 0) { + const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *reg, *endp; + int l; + bool hotpluggable; - reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l); - if (reg == NULL) - reg = of_get_flat_dt_prop(node, "reg", &l); - if (reg == NULL) - return 0; + /* We are scanning "memory" nodes only */ + if (type == NULL || strcmp(type, "memory") != 0) + continue; - endp = reg + (l / sizeof(__be32)); - hotpluggable = of_get_flat_dt_prop(node, "hotpluggable", NULL); + reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l); + if (reg == NULL) + reg = of_get_flat_dt_prop(node, "reg", &l); + if (reg == NULL) + continue; - pr_debug("memory scan node %s, reg size %d,\n", uname, l); + endp = reg + (l / sizeof(__be32)); + hotpluggable = of_get_flat_dt_prop(node, "hotpluggable", NULL); - while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { - u64 base, size; + pr_debug("memory scan node %s, reg size %d,\n", + fdt_get_name(fdt, node, NULL), l); - base = dt_mem_next_cell(dt_root_addr_cells, ®); - size = dt_mem_next_cell(dt_root_size_cells, ®); + while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) { + u64 base, size; - if (size == 0) - continue; - pr_debug(" - %llx, %llx\n", base, size); + base = dt_mem_next_cell(dt_root_addr_cells, ®); + size = dt_mem_next_cell(dt_root_size_cells, ®); - early_init_dt_add_memory_arch(base, size); + if (size == 0) + continue; + pr_debug(" - %llx, %llx\n", base, size); - if (!hotpluggable) - continue; + early_init_dt_add_memory_arch(base, size); - if (memblock_mark_hotplug(base, size)) - pr_warn("failed to mark hotplug range 0x%llx - 0x%llx\n", - base, base + size); - } + if (!hotpluggable) + continue; + if (memblock_mark_hotplug(base, size)) + pr_warn("failed to mark hotplug range 0x%llx - 0x%llx\n", + base, base + size); + } + } return 0; } @@ -1271,7 +1275,7 @@ void __init early_init_dt_scan_nodes(void) pr_warn("No chosen node found, continuing without\n"); /* Setup memory, calling early_init_dt_add_memory_arch */ - of_scan_flat_dt(early_init_dt_scan_memory, NULL); + early_init_dt_scan_memory(); /* Handle linux,usable-memory-range property */ memblock_cap_memory_range(cap_mem_addr, cap_mem_size); diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index df3d31926c3c..914739f3c192 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -59,8 +59,7 @@ extern unsigned long of_get_flat_dt_root(void); extern uint32_t of_get_flat_dt_phandle(unsigned long node); extern int early_init_dt_scan_chosen(char *cmdline); -extern int early_init_dt_scan_memory(unsigned long node, const char *uname, - int depth, void *data); +extern int early_init_dt_scan_memory(void); extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); -- cgit v1.2.3 From f7ea534a0920dbaf71a8003936e178e14ec9271d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 15 Dec 2021 18:55:36 -0800 Subject: add includes masked by cgroup -> bpf dependency cgroup pulls in BPF which pulls in a lot of includes. We're about to break that chain so fix those who were depending on it. Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211216025538.1649516-2-kuba@kernel.org --- arch/s390/mm/hugetlbpage.c | 1 + include/linux/perf_event.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/linux') diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index da36d13ffc16..082793d497ec 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -9,6 +9,7 @@ #define KMSG_COMPONENT "hugetlb" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#include #include #include #include diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0dcfd265beed..4a021149eaf0 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -611,6 +611,7 @@ struct swevent_hlist { #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 +struct bpf_prog; struct perf_cgroup; struct perf_buffer; -- cgit v1.2.3 From fd1740b6abac39f68ce12e201697f106e0f1d519 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 15 Dec 2021 18:55:38 -0800 Subject: bpf: Remove the cgroup -> bpf header dependecy Remove the dependency from cgroup-defs.h to bpf-cgroup.h and bpf.h. This reduces the incremental build size of x86 allmodconfig after bpf.h was touched from ~17k objects rebuilt to ~5k objects. bpf.h is 2.2kLoC and is modified relatively often. We need a new header with just the definition of struct cgroup_bpf and enum cgroup_bpf_attach_type, this is akin to cgroup-defs.h. Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Acked-by: Tejun Heo Link: https://lore.kernel.org/bpf/20211216025538.1649516-4-kuba@kernel.org --- include/linux/bpf-cgroup-defs.h | 70 +++++++++++++++++++++++++++++++++++++++++ include/linux/bpf-cgroup.h | 57 +-------------------------------- include/linux/cgroup-defs.h | 2 +- 3 files changed, 72 insertions(+), 57 deletions(-) create mode 100644 include/linux/bpf-cgroup-defs.h (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h new file mode 100644 index 000000000000..695d1224a71b --- /dev/null +++ b/include/linux/bpf-cgroup-defs.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_CGROUP_DEFS_H +#define _BPF_CGROUP_DEFS_H + +#ifdef CONFIG_CGROUP_BPF + +#include +#include +#include + +struct bpf_prog_array; + +enum cgroup_bpf_attach_type { + CGROUP_BPF_ATTACH_TYPE_INVALID = -1, + CGROUP_INET_INGRESS = 0, + CGROUP_INET_EGRESS, + CGROUP_INET_SOCK_CREATE, + CGROUP_SOCK_OPS, + CGROUP_DEVICE, + CGROUP_INET4_BIND, + CGROUP_INET6_BIND, + CGROUP_INET4_CONNECT, + CGROUP_INET6_CONNECT, + CGROUP_INET4_POST_BIND, + CGROUP_INET6_POST_BIND, + CGROUP_UDP4_SENDMSG, + CGROUP_UDP6_SENDMSG, + CGROUP_SYSCTL, + CGROUP_UDP4_RECVMSG, + CGROUP_UDP6_RECVMSG, + CGROUP_GETSOCKOPT, + CGROUP_SETSOCKOPT, + CGROUP_INET4_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, + CGROUP_INET4_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, + CGROUP_INET_SOCK_RELEASE, + MAX_CGROUP_BPF_ATTACH_TYPE +}; + +struct cgroup_bpf { + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS + */ + struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; + + /* list of cgroup shared storages */ + struct list_head storages; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array *inactive; + + /* reference counter used to detach bpf programs after cgroup removal */ + struct percpu_ref refcnt; + + /* cgroup_bpf is released using a work queue */ + struct work_struct release_work; +}; + +#else /* CONFIG_CGROUP_BPF */ +struct cgroup_bpf {}; +#endif /* CONFIG_CGROUP_BPF */ + +#endif diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 11820a430d6c..b525d8cdc25b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -3,10 +3,10 @@ #define _BPF_CGROUP_H #include +#include #include #include #include -#include #include #include @@ -23,33 +23,6 @@ struct ctl_table_header; struct task_struct; #ifdef CONFIG_CGROUP_BPF -enum cgroup_bpf_attach_type { - CGROUP_BPF_ATTACH_TYPE_INVALID = -1, - CGROUP_INET_INGRESS = 0, - CGROUP_INET_EGRESS, - CGROUP_INET_SOCK_CREATE, - CGROUP_SOCK_OPS, - CGROUP_DEVICE, - CGROUP_INET4_BIND, - CGROUP_INET6_BIND, - CGROUP_INET4_CONNECT, - CGROUP_INET6_CONNECT, - CGROUP_INET4_POST_BIND, - CGROUP_INET6_POST_BIND, - CGROUP_UDP4_SENDMSG, - CGROUP_UDP6_SENDMSG, - CGROUP_SYSCTL, - CGROUP_UDP4_RECVMSG, - CGROUP_UDP6_RECVMSG, - CGROUP_GETSOCKOPT, - CGROUP_SETSOCKOPT, - CGROUP_INET4_GETPEERNAME, - CGROUP_INET6_GETPEERNAME, - CGROUP_INET4_GETSOCKNAME, - CGROUP_INET6_GETSOCKNAME, - CGROUP_INET_SOCK_RELEASE, - MAX_CGROUP_BPF_ATTACH_TYPE -}; #define CGROUP_ATYPE(type) \ case BPF_##type: return type @@ -127,33 +100,6 @@ struct bpf_prog_list { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; -struct bpf_prog_array; - -struct cgroup_bpf { - /* array of effective progs in this cgroup */ - struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; - - /* attached progs to this cgroup and attach flags - * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will - * have either zero or one element - * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS - */ - struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; - u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; - - /* list of cgroup shared storages */ - struct list_head storages; - - /* temp storage for effective prog array used by prog_attach/detach */ - struct bpf_prog_array *inactive; - - /* reference counter used to detach bpf programs after cgroup removal */ - struct percpu_ref refcnt; - - /* cgroup_bpf is released using a work queue */ - struct work_struct release_work; -}; - int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); @@ -451,7 +397,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else -struct cgroup_bpf {}; static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index db2e147e069f..411684c80cf3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #ifdef CONFIG_CGROUPS -- cgit v1.2.3 From 0f55f9ed21f96630c6ec96805d42f92c0b458b37 Mon Sep 17 00:00:00 2001 From: Christy Lee Date: Thu, 16 Dec 2021 13:33:56 -0800 Subject: bpf: Only print scratched registers and stack slots to verifier logs. When printing verifier state for any log level, print full verifier state only on function calls or on errors. Otherwise, only print the registers and stack slots that were accessed. Log size differences: verif_scale_loop6 before: 234566564 verif_scale_loop6 after: 72143943 69% size reduction kfree_skb before: 166406 kfree_skb after: 55386 69% size reduction Before: 156: (61) r0 = *(u32 *)(r1 +0) 157: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=ctx(id=0,off=0,imm=0) R2_w=invP0 R10=fp0 fp-8_w=00000000 fp-16_w=00\ 000000 fp-24_w=00000000 fp-32_w=00000000 fp-40_w=00000000 fp-48_w=00000000 fp-56_w=00000000 fp-64_w=00000000 fp-72_w=00000000 fp-80_w=00000\ 000 fp-88_w=00000000 fp-96_w=00000000 fp-104_w=00000000 fp-112_w=00000000 fp-120_w=00000000 fp-128_w=00000000 fp-136_w=00000000 fp-144_w=00\ 000000 fp-152_w=00000000 fp-160_w=00000000 fp-168_w=00000000 fp-176_w=00000000 fp-184_w=00000000 fp-192_w=00000000 fp-200_w=00000000 fp-208\ _w=00000000 fp-216_w=00000000 fp-224_w=00000000 fp-232_w=00000000 fp-240_w=00000000 fp-248_w=00000000 fp-256_w=00000000 fp-264_w=00000000 f\ p-272_w=00000000 fp-280_w=00000000 fp-288_w=00000000 fp-296_w=00000000 fp-304_w=00000000 fp-312_w=00000000 fp-320_w=00000000 fp-328_w=00000\ 000 fp-336_w=00000000 fp-344_w=00000000 fp-352_w=00000000 fp-360_w=00000000 fp-368_w=00000000 fp-376_w=00000000 fp-384_w=00000000 fp-392_w=\ 00000000 fp-400_w=00000000 fp-408_w=00000000 fp-416_w=00000000 fp-424_w=00000000 fp-432_w=00000000 fp-440_w=00000000 fp-448_w=00000000 ; return skb->len; 157: (95) exit Func#4 is safe for any args that match its prototype Validating get_constant() func#5... 158: R1=invP(id=0) R10=fp0 ; int get_constant(long val) 158: (bf) r0 = r1 159: R0_w=invP(id=1) R1=invP(id=1) R10=fp0 ; return val - 122; 159: (04) w0 += -122 160: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=invP(id=1) R10=fp0 ; return val - 122; 160: (95) exit Func#5 is safe for any args that match its prototype Validating get_skb_ifindex() func#6... 161: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R3=invP(id=0) R10=fp0 ; int get_skb_ifindex(int val, struct __sk_buff *skb, int var) 161: (bc) w0 = w3 162: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R3=invP(id=0) R10=fp0 After: 156: (61) r0 = *(u32 *)(r1 +0) 157: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R1=ctx(id=0,off=0,imm=0) ; return skb->len; 157: (95) exit Func#4 is safe for any args that match its prototype Validating get_constant() func#5... 158: R1=invP(id=0) R10=fp0 ; int get_constant(long val) 158: (bf) r0 = r1 159: R0_w=invP(id=1) R1=invP(id=1) ; return val - 122; 159: (04) w0 += -122 160: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return val - 122; 160: (95) exit Func#5 is safe for any args that match its prototype Validating get_skb_ifindex() func#6... 161: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R3=invP(id=0) R10=fp0 ; int get_skb_ifindex(int val, struct __sk_buff *skb, int var) 161: (bc) w0 = w3 162: R0_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R3=invP(id=0) Signed-off-by: Christy Lee Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211216213358.3374427-2-christylee@fb.com --- include/linux/bpf_verifier.h | 7 +++ kernel/bpf/verifier.c | 83 +++++++++++++++++++++----- tools/testing/selftests/bpf/prog_tests/align.c | 30 +++++----- 3 files changed, 91 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 182b16a91084..c66f238c538d 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -474,6 +474,13 @@ struct bpf_verifier_env { /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; bpfptr_t fd_array; + + /* bit mask to keep track of whether a register has been accessed + * since the last time the function state was printed + */ + u32 scratched_regs; + /* Same as scratched_regs but for stack slots */ + u64 scratched_stack_slots; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f0604796132f..ded6e816dcd9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -609,6 +609,44 @@ static const char *kernel_type_name(const struct btf* btf, u32 id) return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } +static void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno) +{ + env->scratched_regs |= 1U << regno; +} + +static void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi) +{ + env->scratched_stack_slots |= 1UL << spi; +} + +static bool reg_scratched(const struct bpf_verifier_env *env, u32 regno) +{ + return (env->scratched_regs >> regno) & 1; +} + +static bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno) +{ + return (env->scratched_stack_slots >> regno) & 1; +} + +static bool verifier_state_scratched(const struct bpf_verifier_env *env) +{ + return env->scratched_regs || env->scratched_stack_slots; +} + +static void mark_verifier_state_clean(struct bpf_verifier_env *env) +{ + env->scratched_regs = 0U; + env->scratched_stack_slots = 0UL; +} + +/* Used for printing the entire verifier state. */ +static void mark_verifier_state_scratched(struct bpf_verifier_env *env) +{ + env->scratched_regs = ~0U; + env->scratched_stack_slots = ~0UL; +} + /* The reg state of a pointer or a bounded scalar was saved when * it was spilled to the stack. */ @@ -624,7 +662,8 @@ static void scrub_spilled_slot(u8 *stype) } static void print_verifier_state(struct bpf_verifier_env *env, - const struct bpf_func_state *state) + const struct bpf_func_state *state, + bool print_all) { const struct bpf_reg_state *reg; enum bpf_reg_type t; @@ -637,6 +676,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, t = reg->type; if (t == NOT_INIT) continue; + if (!print_all && !reg_scratched(env, i)) + continue; verbose(env, " R%d", i); print_liveness(env, reg->live); verbose(env, "=%s", reg_type_str[t]); @@ -726,6 +767,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, types_buf[BPF_REG_SIZE] = 0; if (!valid) continue; + if (!print_all && !stack_slot_scratched(env, i)) + continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); if (is_spilled_reg(&state->stack[i])) { @@ -751,6 +794,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (state->in_async_callback_fn) verbose(env, " async_cb"); verbose(env, "\n"); + mark_verifier_state_clean(env); } /* copy array src of length n * size bytes to dst. dst is reallocated if it's too @@ -1541,6 +1585,7 @@ static void init_func_state(struct bpf_verifier_env *env, state->frameno = frameno; state->subprogno = subprogno; init_reg_state(env, state); + mark_verifier_state_scratched(env); } /* Similar to push_stack(), but for async callbacks */ @@ -2228,6 +2273,8 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return -EINVAL; } + mark_reg_scratched(env, regno); + reg = ®s[regno]; rw64 = is_reg64(env, insn, regno, reg, t); if (t == SRC_OP) { @@ -2678,7 +2725,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, reg->precise = true; } if (env->log.level & BPF_LOG_LEVEL) { - print_verifier_state(env, func); + print_verifier_state(env, func, false); verbose(env, "parent %s regs=%x stack=%llx marks\n", new_marks ? "didn't have" : "already had", reg_mask, stack_mask); @@ -2837,6 +2884,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, env->insn_aux_data[insn_idx].sanitize_stack_spill = true; } + mark_stack_slot_scratched(env, spi); if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && !register_is_null(reg) && env->bpf_capable) { if (dst_reg != BPF_REG_FP) { @@ -2958,6 +3006,7 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, slot = -i - 1; spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; + mark_stack_slot_scratched(env, spi); if (!env->allow_ptr_leaks && *stype != NOT_INIT @@ -3376,7 +3425,7 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, * to make sure our theoretical access will be safe. */ if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, state); + print_verifier_state(env, state, false); /* The minimum value is only important with signed * comparisons where we can't assume the floor of a @@ -6011,9 +6060,9 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "caller:\n"); - print_verifier_state(env, caller); + print_verifier_state(env, caller, true); verbose(env, "callee:\n"); - print_verifier_state(env, callee); + print_verifier_state(env, callee, true); } return 0; } @@ -6228,9 +6277,9 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) *insn_idx = callee->callsite + 1; if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); - print_verifier_state(env, callee); + print_verifier_state(env, callee, true); verbose(env, "to caller at %d:\n", *insn_idx); - print_verifier_state(env, caller); + print_verifier_state(env, caller, true); } /* clear everything in the callee */ free_func_state(callee); @@ -8249,12 +8298,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, /* Got here implies adding two SCALAR_VALUEs */ if (WARN_ON_ONCE(ptr_reg)) { - print_verifier_state(env, state); + print_verifier_state(env, state, true); verbose(env, "verifier internal error: unexpected ptr_reg\n"); return -EINVAL; } if (WARN_ON(!src_reg)) { - print_verifier_state(env, state); + print_verifier_state(env, state, true); verbose(env, "verifier internal error: no src_reg\n"); return -EINVAL; } @@ -9389,7 +9438,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, this_branch->frame[this_branch->curframe]); + print_verifier_state(env, this_branch->frame[this_branch->curframe], false); return 0; } @@ -11259,14 +11308,17 @@ static int do_check(struct bpf_verifier_env *env) if (env->log.level & BPF_LOG_LEVEL2 || (env->log.level & BPF_LOG_LEVEL && do_print_state)) { - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "%d:", env->insn_idx); - else + if (env->log.level & BPF_LOG_LEVEL2) { + if (verifier_state_scratched(env)) + verbose(env, "%d:", env->insn_idx); + } else { verbose(env, "\nfrom %d to %d%s:", env->prev_insn_idx, env->insn_idx, env->cur_state->speculative ? " (speculative execution)" : ""); - print_verifier_state(env, state->frame[state->curframe]); + } + print_verifier_state(env, state->frame[state->curframe], + false); do_print_state = false; } @@ -11488,6 +11540,7 @@ static int do_check(struct bpf_verifier_env *env) if (err) return err; process_bpf_exit: + mark_verifier_state_scratched(env); update_branch_counts(env, env->cur_state); err = pop_stack(env, &prev_insn_idx, &env->insn_idx, pop_log); @@ -14148,6 +14201,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr) } } + mark_verifier_state_clean(env); + if (IS_ERR(btf_vmlinux)) { /* Either gcc or pahole or kernel are broken. */ verbose(env, "in-kernel BTF is malformed\n"); diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index 837f67c6bfda..aeb2080a67f7 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -39,8 +39,8 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, {1, "R3_w=inv2"}, {2, "R3_w=inv4"}, {3, "R3_w=inv8"}, @@ -67,8 +67,8 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, {1, "R3_w=inv1"}, {2, "R3_w=inv2"}, {3, "R3_w=inv4"}, @@ -96,8 +96,8 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, {1, "R3_w=inv4"}, {2, "R3_w=inv8"}, {3, "R3_w=inv10"}, @@ -118,8 +118,8 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {1, "R1=ctx(id=0,off=0,imm=0)"}, - {1, "R10=fp0"}, + {0, "R1=ctx(id=0,off=0,imm=0)"}, + {0, "R10=fp0"}, {1, "R3_w=inv7"}, {2, "R3_w=inv7"}, {3, "R3_w=inv14"}, @@ -161,13 +161,13 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {7, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, + {6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, {8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, {9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, {10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, {11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {18, "R3=pkt_end(id=0,off=0,imm=0)"}, + {13, "R3_w=pkt_end(id=0,off=0,imm=0)"}, {18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, {19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, {20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, @@ -234,10 +234,10 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, + {3, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, {5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, {6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, - {10, "R2=pkt(id=0,off=0,r=18,imm=0)"}, + {9, "R2=pkt(id=0,off=0,r=18,imm=0)"}, {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, {14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, @@ -296,7 +296,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. @@ -386,7 +386,7 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {8, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, @@ -458,7 +458,7 @@ static struct bpf_align_test tests[] = { /* Checked s>=0 */ {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {12, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able -- cgit v1.2.3 From 2e5766483c8c5cf886b4dc647a1741738dde7d79 Mon Sep 17 00:00:00 2001 From: Christy Lee Date: Thu, 16 Dec 2021 19:42:45 -0800 Subject: bpf: Right align verifier states in verifier logs. Make the verifier logs more readable, print the verifier states on the corresponding instruction line. If the previous line was not a bpf instruction, then print the verifier states on its own line. Before: Validating test_pkt_access_subprog3() func#3... 86: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R10=fp0 ; int test_pkt_access_subprog3(int val, struct __sk_buff *skb) 86: (bf) r6 = r2 87: R2=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 87: (bc) w7 = w1 88: R1=invP(id=0) R7_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 88: (bf) r1 = r6 89: R1_w=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 89: (85) call pc+9 Func#4 is global and valid. Skipping. 90: R0_w=invP(id=0) 90: (bc) w8 = w0 91: R0_w=invP(id=0) R8_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 91: (b7) r1 = 123 92: R1_w=invP123 92: (85) call pc+65 Func#5 is global and valid. Skipping. 93: R0=invP(id=0) After: 86: R1=invP(id=0) R2=ctx(id=0,off=0,imm=0) R10=fp0 ; int test_pkt_access_subprog3(int val, struct __sk_buff *skb) 86: (bf) r6 = r2 ; R2=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 87: (bc) w7 = w1 ; R1=invP(id=0) R7_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 88: (bf) r1 = r6 ; R1_w=ctx(id=0,off=0,imm=0) R6_w=ctx(id=0,off=0,imm=0) 89: (85) call pc+9 Func#4 is global and valid. Skipping. 90: R0_w=invP(id=0) 90: (bc) w8 = w0 ; R0_w=invP(id=0) R8_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) ; return get_skb_len(skb) * get_skb_ifindex(val, skb, get_constant(123)); 91: (b7) r1 = 123 ; R1_w=invP123 92: (85) call pc+65 Func#5 is global and valid. Skipping. 93: R0=invP(id=0) Signed-off-by: Christy Lee Acked-by: Andrii Nakryiko Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 3 + kernel/bpf/verifier.c | 57 ++++++--- tools/testing/selftests/bpf/prog_tests/align.c | 169 ++++++++++++++----------- 3 files changed, 131 insertions(+), 98 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c66f238c538d..ee931398f311 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -388,6 +388,8 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ +#define BPF_LOG_MIN_ALIGNMENT 8U +#define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { @@ -481,6 +483,7 @@ struct bpf_verifier_env { u32 scratched_regs; /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; + u32 prev_log_len, prev_insn_print_len; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ded6e816dcd9..72c4a6bbb5bc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -797,6 +797,25 @@ static void print_verifier_state(struct bpf_verifier_env *env, mark_verifier_state_clean(env); } +static inline u32 vlog_alignment(u32 pos) +{ + return round_up(max(pos + BPF_LOG_MIN_ALIGNMENT / 2, BPF_LOG_ALIGNMENT), + BPF_LOG_MIN_ALIGNMENT) - pos - 1; +} + +static void print_insn_state(struct bpf_verifier_env *env, + const struct bpf_func_state *state) +{ + if (env->prev_log_len && env->prev_log_len == env->log.len_used) { + /* remove new line character */ + bpf_vlog_reset(&env->log, env->prev_log_len - 1); + verbose(env, "%*c;", vlog_alignment(env->prev_insn_print_len), ' '); + } else { + verbose(env, "%d:", env->insn_idx); + } + print_verifier_state(env, state, false); +} + /* copy array src of length n * size bytes to dst. dst is reallocated if it's too * small to hold src. This is different from krealloc since we don't want to preserve * the contents of dst. @@ -2725,10 +2744,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, reg->precise = true; } if (env->log.level & BPF_LOG_LEVEL) { - print_verifier_state(env, func, false); - verbose(env, "parent %s regs=%x stack=%llx marks\n", + verbose(env, "parent %s regs=%x stack=%llx marks:", new_marks ? "didn't have" : "already had", reg_mask, stack_mask); + print_verifier_state(env, func, true); } if (!reg_mask && !stack_mask) @@ -3423,11 +3442,8 @@ static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno, /* We may have adjusted the register pointing to memory region, so we * need to try adding each of min_value and max_value to off * to make sure our theoretical access will be safe. - */ - if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, state, false); - - /* The minimum value is only important with signed + * + * The minimum value is only important with signed * comparisons where we can't assume the floor of a * value is 0. If we are using signed variables for our * index'es we need to make sure that whatever we use @@ -9438,7 +9454,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, return -EACCES; } if (env->log.level & BPF_LOG_LEVEL) - print_verifier_state(env, this_branch->frame[this_branch->curframe], false); + print_insn_state(env, this_branch->frame[this_branch->curframe]); return 0; } @@ -11306,19 +11322,12 @@ static int do_check(struct bpf_verifier_env *env) if (need_resched()) cond_resched(); - if (env->log.level & BPF_LOG_LEVEL2 || - (env->log.level & BPF_LOG_LEVEL && do_print_state)) { - if (env->log.level & BPF_LOG_LEVEL2) { - if (verifier_state_scratched(env)) - verbose(env, "%d:", env->insn_idx); - } else { - verbose(env, "\nfrom %d to %d%s:", - env->prev_insn_idx, env->insn_idx, - env->cur_state->speculative ? - " (speculative execution)" : ""); - } - print_verifier_state(env, state->frame[state->curframe], - false); + if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) { + verbose(env, "\nfrom %d to %d%s:", + env->prev_insn_idx, env->insn_idx, + env->cur_state->speculative ? + " (speculative execution)" : ""); + print_verifier_state(env, state->frame[state->curframe], true); do_print_state = false; } @@ -11329,9 +11338,15 @@ static int do_check(struct bpf_verifier_env *env) .private_data = env, }; + if (verifier_state_scratched(env)) + print_insn_state(env, state->frame[state->curframe]); + verbose_linfo(env, env->insn_idx, "; "); + env->prev_log_len = env->log.len_used; verbose(env, "%d: ", env->insn_idx); print_bpf_insn(&cbs, insn, env->allow_ptr_leaks); + env->prev_insn_print_len = env->log.len_used - env->prev_log_len; + env->prev_log_len = env->log.len_used; } if (bpf_prog_is_dev_bound(env->prog->aux)) { diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c index aeb2080a67f7..0ee29e11eaee 100644 --- a/tools/testing/selftests/bpf/prog_tests/align.c +++ b/tools/testing/selftests/bpf/prog_tests/align.c @@ -41,11 +41,11 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1=ctx(id=0,off=0,imm=0)"}, {0, "R10=fp0"}, - {1, "R3_w=inv2"}, - {2, "R3_w=inv4"}, - {3, "R3_w=inv8"}, - {4, "R3_w=inv16"}, - {5, "R3_w=inv32"}, + {0, "R3_w=inv2"}, + {1, "R3_w=inv4"}, + {2, "R3_w=inv8"}, + {3, "R3_w=inv16"}, + {4, "R3_w=inv32"}, }, }, { @@ -69,17 +69,17 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1=ctx(id=0,off=0,imm=0)"}, {0, "R10=fp0"}, - {1, "R3_w=inv1"}, - {2, "R3_w=inv2"}, - {3, "R3_w=inv4"}, - {4, "R3_w=inv8"}, - {5, "R3_w=inv16"}, - {6, "R3_w=inv1"}, - {7, "R4_w=inv32"}, - {8, "R4_w=inv16"}, - {9, "R4_w=inv8"}, - {10, "R4_w=inv4"}, - {11, "R4_w=inv2"}, + {0, "R3_w=inv1"}, + {1, "R3_w=inv2"}, + {2, "R3_w=inv4"}, + {3, "R3_w=inv8"}, + {4, "R3_w=inv16"}, + {5, "R3_w=inv1"}, + {6, "R4_w=inv32"}, + {7, "R4_w=inv16"}, + {8, "R4_w=inv8"}, + {9, "R4_w=inv4"}, + {10, "R4_w=inv2"}, }, }, { @@ -98,12 +98,12 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1=ctx(id=0,off=0,imm=0)"}, {0, "R10=fp0"}, - {1, "R3_w=inv4"}, - {2, "R3_w=inv8"}, - {3, "R3_w=inv10"}, - {4, "R4_w=inv8"}, - {5, "R4_w=inv12"}, - {6, "R4_w=inv14"}, + {0, "R3_w=inv4"}, + {1, "R3_w=inv8"}, + {2, "R3_w=inv10"}, + {3, "R4_w=inv8"}, + {4, "R4_w=inv12"}, + {5, "R4_w=inv14"}, }, }, { @@ -120,10 +120,10 @@ static struct bpf_align_test tests[] = { .matches = { {0, "R1=ctx(id=0,off=0,imm=0)"}, {0, "R10=fp0"}, + {0, "R3_w=inv7"}, {1, "R3_w=inv7"}, - {2, "R3_w=inv7"}, - {3, "R3_w=inv14"}, - {4, "R3_w=inv56"}, + {2, "R3_w=inv14"}, + {3, "R3_w=inv56"}, }, }, @@ -162,18 +162,18 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { {6, "R0_w=pkt(id=0,off=8,r=8,imm=0)"}, - {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {13, "R3_w=pkt_end(id=0,off=0,imm=0)"}, - {18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, - {20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {7, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {8, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {9, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {10, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {12, "R3_w=pkt_end(id=0,off=0,imm=0)"}, + {17, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {18, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, + {19, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {20, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {21, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {22, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, }, }, { @@ -194,16 +194,16 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {10, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {12, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {14, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, - {15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {6, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {7, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {9, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {10, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {11, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {12, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {13, "R4_w=inv(id=1,umax_value=255,var_off=(0x0; 0xff))"}, + {14, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {15, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, }, }, { @@ -234,14 +234,14 @@ static struct bpf_align_test tests[] = { }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {3, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, - {5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, - {6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, + {2, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, + {4, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, + {5, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, {9, "R2=pkt(id=0,off=0,r=18,imm=0)"}, {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {13, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, {14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, - {15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, }, }, { @@ -297,7 +297,7 @@ static struct bpf_align_test tests[] = { * alignment of 4. */ {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. */ @@ -313,11 +313,11 @@ static struct bpf_align_test tests[] = { /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - {18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - {19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {18, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off * (14) which is 16. Then the variable offset is 4-byte @@ -329,18 +329,18 @@ static struct bpf_align_test tests[] = { /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {26, "R5_w=pkt(id=0,off=14,r=8"}, + {25, "R5_w=pkt(id=0,off=14,r=8"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). */ - {27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {26, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant is added to R5 again, setting reg->off to 18. */ - {28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {27, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* And once more we add a variable; resulting var_off * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, + {28, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so @@ -387,12 +387,12 @@ static struct bpf_align_test tests[] = { * alignment of 4. */ {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {7, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {8, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, - {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, + {12, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so @@ -403,12 +403,12 @@ static struct bpf_align_test tests[] = { /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ - {18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {17, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, - {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, + {20, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc)"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so @@ -448,18 +448,18 @@ static struct bpf_align_test tests[] = { .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {4, "R5_w=pkt_end(id=0,off=0,imm=0)"}, + {3, "R5_w=pkt_end(id=0,off=0,imm=0)"}, /* (ptr - ptr) << 2 == unknown, (4n) */ - {6, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, + {5, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc)"}, /* (4n) + 14 == (4n+2). We blow our bounds, because * the add could overflow. */ - {7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {6, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>=0 */ {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* packet pointer + nonnegative (4n+2) */ - {12, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, - {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, + {12, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"}, /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. * We checked the bounds, but it might have been able * to overflow if the packet pointer started in the @@ -502,14 +502,14 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* New unknown value in R7 is (4n) */ - {11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ - {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, + {11, "R6=inv(id=0,smin_value=-1006,smax_value=1034,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"}, /* Checked s>= 0 */ {14, "R6=inv(id=0,umin_value=2,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, @@ -556,14 +556,14 @@ static struct bpf_align_test tests[] = { /* Calculated offset in R6 has unknown value, but known * alignment of 4. */ - {7, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, - {10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + {6, "R2_w=pkt(id=0,off=0,r=8,imm=0)"}, + {9, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, /* Adding 14 makes R6 be (4n+2) */ - {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + {10, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ {13, "R5_w=pkt(id=2,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c)"}, /* New unknown value in R7 is (4n), >= 76 */ - {15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + {14, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ {16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"}, /* At the time the word size load is performed from R5, @@ -625,12 +625,15 @@ static int do_test_single(struct bpf_align_test *test) line_ptr = strtok(bpf_vlog_copy, "\n"); for (i = 0; i < MAX_MATCHES; i++) { struct bpf_reg_match m = test->matches[i]; + int tmp; if (!m.match) break; while (line_ptr) { cur_line = -1; sscanf(line_ptr, "%u: ", &cur_line); + if (cur_line == -1) + sscanf(line_ptr, "from %u to %u: ", &tmp, &cur_line); if (cur_line == m.line) break; line_ptr = strtok(NULL, "\n"); @@ -642,7 +645,19 @@ static int do_test_single(struct bpf_align_test *test) printf("%s", bpf_vlog); break; } + /* Check the next line as well in case the previous line + * did not have a corresponding bpf insn. Example: + * func#0 @0 + * 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 + * 0: (b7) r3 = 2 ; R3_w=inv2 + */ if (!strstr(line_ptr, m.match)) { + cur_line = -1; + line_ptr = strtok(NULL, "\n"); + sscanf(line_ptr, "%u: ", &cur_line); + } + if (cur_line != m.line || !line_ptr || + !strstr(line_ptr, m.match)) { printf("Failed to find match %u: %s\n", m.line, m.match); ret = 1; -- cgit v1.2.3 From 03de6b273805b3c552ff158f8688555937375926 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Nov 2021 23:22:00 +0100 Subject: dmaengine: qcom-adm: stop abusing slave_id config The slave_id was previously used to pick one DMA slave instead of another, but this is now done through the DMA descriptors in device tree. For the qcom_adm driver, the configuration is documented in the DT binding to contain a tuple of device identifier and a "crci" field, but the implementation ends up using only a single cell for identifying the slave, with the crci getting passed in nonstandard properties of the device, and passed through the dma driver using the old slave_id field. Part of the problem apparently is that the nand driver ends up using only a single DMA request ID, but requires distinct values for "crci" depending on the type of transfer. Change both the dmaengine driver and the two slave drivers to allow the documented binding to work in addition to the ad-hoc passing of crci values. In order to no longer abuse the slave_id field, pass the data using the "peripheral_config" mechanism instead. Signed-off-by: Arnd Bergmann Acked-by: Mark Brown Link: https://lore.kernel.org/r/20211122222203.4103644-9-arnd@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/qcom/qcom_adm.c | 56 ++++++++++++++++++++++++++++++++++----- drivers/mtd/nand/raw/qcom_nandc.c | 14 ++++++++-- drivers/tty/serial/msm_serial.c | 15 +++++++++-- include/linux/dma/qcom_adm.h | 12 +++++++++ 4 files changed, 86 insertions(+), 11 deletions(-) create mode 100644 include/linux/dma/qcom_adm.h (limited to 'include/linux') diff --git a/drivers/dma/qcom/qcom_adm.c b/drivers/dma/qcom/qcom_adm.c index ee78bed8d60d..facdacf8aede 100644 --- a/drivers/dma/qcom/qcom_adm.c +++ b/drivers/dma/qcom/qcom_adm.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -140,6 +141,8 @@ struct adm_chan { struct adm_async_desc *curr_txd; struct dma_slave_config slave; + u32 crci; + u32 mux; struct list_head node; int error; @@ -379,8 +382,8 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan, return ERR_PTR(-EINVAL); } - crci = achan->slave.slave_id & 0xf; - if (!crci || achan->slave.slave_id > 0x1f) { + crci = achan->crci & 0xf; + if (!crci || achan->crci > 0x1f) { dev_err(adev->dev, "invalid crci value\n"); return ERR_PTR(-EINVAL); } @@ -403,9 +406,7 @@ static struct dma_async_tx_descriptor *adm_prep_slave_sg(struct dma_chan *chan, if (!async_desc) return ERR_PTR(-ENOMEM); - if (crci) - async_desc->mux = achan->slave.slave_id & ADM_CRCI_MUX_SEL ? - ADM_CRCI_CTL_MUX_SEL : 0; + async_desc->mux = achan->mux ? ADM_CRCI_CTL_MUX_SEL : 0; async_desc->crci = crci; async_desc->blk_size = blk_size; async_desc->dma_len = single_count * sizeof(struct adm_desc_hw_single) + @@ -488,10 +489,13 @@ static int adm_terminate_all(struct dma_chan *chan) static int adm_slave_config(struct dma_chan *chan, struct dma_slave_config *cfg) { struct adm_chan *achan = to_adm_chan(chan); + struct qcom_adm_peripheral_config *config = cfg->peripheral_config; unsigned long flag; spin_lock_irqsave(&achan->vc.lock, flag); memcpy(&achan->slave, cfg, sizeof(struct dma_slave_config)); + if (cfg->peripheral_size == sizeof(config)) + achan->crci = config->crci; spin_unlock_irqrestore(&achan->vc.lock, flag); return 0; @@ -694,6 +698,45 @@ static void adm_channel_init(struct adm_device *adev, struct adm_chan *achan, achan->vc.desc_free = adm_dma_free_desc; } +/** + * adm_dma_xlate + * @dma_spec: pointer to DMA specifier as found in the device tree + * @ofdma: pointer to DMA controller data + * + * This can use either 1-cell or 2-cell formats, the first cell + * identifies the slave device, while the optional second cell + * contains the crci value. + * + * Returns pointer to appropriate dma channel on success or NULL on error. + */ +static struct dma_chan *adm_dma_xlate(struct of_phandle_args *dma_spec, + struct of_dma *ofdma) +{ + struct dma_device *dev = ofdma->of_dma_data; + struct dma_chan *chan, *candidate = NULL; + struct adm_chan *achan; + + if (!dev || dma_spec->args_count > 2) + return NULL; + + list_for_each_entry(chan, &dev->channels, device_node) + if (chan->chan_id == dma_spec->args[0]) { + candidate = chan; + break; + } + + if (!candidate) + return NULL; + + achan = to_adm_chan(candidate); + if (dma_spec->args_count == 2) + achan->crci = dma_spec->args[1]; + else + achan->crci = 0; + + return dma_get_slave_channel(candidate); +} + static int adm_dma_probe(struct platform_device *pdev) { struct adm_device *adev; @@ -838,8 +881,7 @@ static int adm_dma_probe(struct platform_device *pdev) goto err_disable_clks; } - ret = of_dma_controller_register(pdev->dev.of_node, - of_dma_xlate_by_chan_id, + ret = of_dma_controller_register(pdev->dev.of_node, adm_dma_xlate, &adev->common); if (ret) goto err_unregister_dma; diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 04e6f7b26706..7c6efa3b6255 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -952,6 +953,7 @@ static int prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, struct dma_async_tx_descriptor *dma_desc; struct scatterlist *sgl; struct dma_slave_config slave_conf; + struct qcom_adm_peripheral_config periph_conf = {}; enum dma_transfer_direction dir_eng; int ret; @@ -983,11 +985,19 @@ static int prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, if (read) { slave_conf.src_maxburst = 16; slave_conf.src_addr = nandc->base_dma + reg_off; - slave_conf.slave_id = nandc->data_crci; + if (nandc->data_crci) { + periph_conf.crci = nandc->data_crci; + slave_conf.peripheral_config = &periph_conf; + slave_conf.peripheral_size = sizeof(periph_conf); + } } else { slave_conf.dst_maxburst = 16; slave_conf.dst_addr = nandc->base_dma + reg_off; - slave_conf.slave_id = nandc->cmd_crci; + if (nandc->cmd_crci) { + periph_conf.crci = nandc->cmd_crci; + slave_conf.peripheral_config = &periph_conf; + slave_conf.peripheral_size = sizeof(periph_conf); + } } ret = dmaengine_slave_config(nandc->chan, &slave_conf); diff --git a/drivers/tty/serial/msm_serial.c b/drivers/tty/serial/msm_serial.c index fcef7a961430..c6be09f44dc1 100644 --- a/drivers/tty/serial/msm_serial.c +++ b/drivers/tty/serial/msm_serial.c @@ -9,6 +9,7 @@ #include #include +#include #include #include #include @@ -290,6 +291,7 @@ static void msm_request_tx_dma(struct msm_port *msm_port, resource_size_t base) { struct device *dev = msm_port->uart.dev; struct dma_slave_config conf; + struct qcom_adm_peripheral_config periph_conf = {}; struct msm_dma *dma; u32 crci = 0; int ret; @@ -308,7 +310,11 @@ static void msm_request_tx_dma(struct msm_port *msm_port, resource_size_t base) conf.device_fc = true; conf.dst_addr = base + UARTDM_TF; conf.dst_maxburst = UARTDM_BURST_SIZE; - conf.slave_id = crci; + if (crci) { + conf.peripheral_config = &periph_conf; + conf.peripheral_size = sizeof(periph_conf); + periph_conf.crci = crci; + } ret = dmaengine_slave_config(dma->chan, &conf); if (ret) @@ -333,6 +339,7 @@ static void msm_request_rx_dma(struct msm_port *msm_port, resource_size_t base) { struct device *dev = msm_port->uart.dev; struct dma_slave_config conf; + struct qcom_adm_peripheral_config periph_conf = {}; struct msm_dma *dma; u32 crci = 0; int ret; @@ -355,7 +362,11 @@ static void msm_request_rx_dma(struct msm_port *msm_port, resource_size_t base) conf.device_fc = true; conf.src_addr = base + UARTDM_RF; conf.src_maxburst = UARTDM_BURST_SIZE; - conf.slave_id = crci; + if (crci) { + conf.peripheral_config = &periph_conf; + conf.peripheral_size = sizeof(periph_conf); + periph_conf.crci = crci; + } ret = dmaengine_slave_config(dma->chan, &conf); if (ret) diff --git a/include/linux/dma/qcom_adm.h b/include/linux/dma/qcom_adm.h new file mode 100644 index 000000000000..af20df674f0c --- /dev/null +++ b/include/linux/dma/qcom_adm.h @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only +#ifndef __LINUX_DMA_QCOM_ADM_H +#define __LINUX_DMA_QCOM_ADM_H + +#include + +struct qcom_adm_peripheral_config { + u32 crci; + u32 mux; +}; + +#endif /* __LINUX_DMA_QCOM_ADM_H */ -- cgit v1.2.3 From 93cdb5b0dc56cc7a8b87a61146495f3bdc93d7ba Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Nov 2021 23:22:01 +0100 Subject: dmaengine: xilinx_dpdma: stop using slave_id field The display driver wants to pass a custom flag to the DMA engine driver, which it started doing by using the slave_id field that was traditionally used for a different purpose. As there is no longer a correct use for the slave_id field, it should really be removed, and the remaining users changed over to something different. The new mechanism for passing nonstandard settings is using the .peripheral_config field, so use that to pass a newly defined structure here, making it clear that this will not work in portable drivers. Reviewed-by: Laurent Pinchart Signed-off-by: Arnd Bergmann Acked-by: Mark Brown Link: https://lore.kernel.org/r/20211122222203.4103644-10-arnd@kernel.org Signed-off-by: Vinod Koul --- drivers/dma/xilinx/xilinx_dpdma.c | 17 +++++++++++------ drivers/gpu/drm/xlnx/zynqmp_disp.c | 9 +++++++-- include/linux/dma/xilinx_dpdma.h | 11 +++++++++++ 3 files changed, 29 insertions(+), 8 deletions(-) create mode 100644 include/linux/dma/xilinx_dpdma.h (limited to 'include/linux') diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index ce5c66e6897d..b0f4948b00a5 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -1273,6 +1274,7 @@ static int xilinx_dpdma_config(struct dma_chan *dchan, struct dma_slave_config *config) { struct xilinx_dpdma_chan *chan = to_xilinx_chan(dchan); + struct xilinx_dpdma_peripheral_config *pconfig; unsigned long flags; /* @@ -1282,15 +1284,18 @@ static int xilinx_dpdma_config(struct dma_chan *dchan, * fixed both on the DPDMA side and on the DP controller side. */ - spin_lock_irqsave(&chan->lock, flags); - /* - * Abuse the slave_id to indicate that the channel is part of a video - * group. + * Use the peripheral_config to indicate that the channel is part + * of a video group. This requires matching use of the custom + * structure in each driver. */ - if (chan->id <= ZYNQMP_DPDMA_VIDEO2) - chan->video_group = config->slave_id != 0; + pconfig = config->peripheral_config; + if (WARN_ON(pconfig && config->peripheral_size != sizeof(*pconfig))) + return -EINVAL; + spin_lock_irqsave(&chan->lock, flags); + if (chan->id <= ZYNQMP_DPDMA_VIDEO2 && pconfig) + chan->video_group = pconfig->video_group; spin_unlock_irqrestore(&chan->lock, flags); return 0; diff --git a/drivers/gpu/drm/xlnx/zynqmp_disp.c b/drivers/gpu/drm/xlnx/zynqmp_disp.c index ff2b308d8651..11c409cbc88e 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_disp.c +++ b/drivers/gpu/drm/xlnx/zynqmp_disp.c @@ -24,6 +24,7 @@ #include #include +#include #include #include #include @@ -1058,14 +1059,18 @@ static void zynqmp_disp_layer_set_format(struct zynqmp_disp_layer *layer, zynqmp_disp_avbuf_set_format(layer->disp, layer, layer->disp_fmt); /* - * Set slave_id for each DMA channel to indicate they're part of a + * Set pconfig for each DMA channel to indicate they're part of a * video group. */ for (i = 0; i < info->num_planes; i++) { struct zynqmp_disp_layer_dma *dma = &layer->dmas[i]; + struct xilinx_dpdma_peripheral_config pconfig = { + .video_group = true, + }; struct dma_slave_config config = { .direction = DMA_MEM_TO_DEV, - .slave_id = 1, + .peripheral_config = &pconfig, + .peripheral_size = sizeof(pconfig), }; dmaengine_slave_config(dma->chan, &config); diff --git a/include/linux/dma/xilinx_dpdma.h b/include/linux/dma/xilinx_dpdma.h new file mode 100644 index 000000000000..83a1377f03f8 --- /dev/null +++ b/include/linux/dma/xilinx_dpdma.h @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#ifndef __LINUX_DMA_XILINX_DPDMA_H +#define __LINUX_DMA_XILINX_DPDMA_H + +#include + +struct xilinx_dpdma_peripheral_config { + bool video_group; +}; + +#endif /* __LINUX_DMA_XILINX_DPDMA_H */ -- cgit v1.2.3 From 3c219644075795a99271d345efdfa8b256e55161 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Nov 2021 23:22:03 +0100 Subject: dmaengine: remove slave_id config field All references to the slave_id field have been removed, so remove the field as well to prevent new references from creeping in again. Originally this allowed slave DMA drivers to configure which device is accessed with the dmaengine_slave_config() call, but this was inconsistent, as the same information is also passed while requesting a channel, and never changes in practice. In modern kernels, the device is always selected when requesting the channel, so the .slave_id field is no longer useful. Reviewed-by: Laurent Pinchart Signed-off-by: Arnd Bergmann Acked-by: Mark Brown Link: https://lore.kernel.org/r/20211122222203.4103644-12-arnd@kernel.org Signed-off-by: Vinod Koul --- include/linux/dmaengine.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h index 9000f3ffce8b..0349b35235e6 100644 --- a/include/linux/dmaengine.h +++ b/include/linux/dmaengine.h @@ -418,9 +418,6 @@ enum dma_slave_buswidth { * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill * with 'true' if peripheral should be flow controller. Direction will be * selected at Runtime. - * @slave_id: Slave requester id. Only valid for slave channels. The dma - * slave peripheral will have unique id as dma requester which need to be - * pass as slave config. * @peripheral_config: peripheral configuration for programming peripheral * for dmaengine transfer * @peripheral_size: peripheral configuration buffer size @@ -448,7 +445,6 @@ struct dma_slave_config { u32 src_port_window_size; u32 dst_port_window_size; bool device_fc; - unsigned int slave_id; void *peripheral_config; size_t peripheral_size; }; -- cgit v1.2.3 From 3d725965f836a7acbd1674e33644bec18373de53 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Tue, 7 Dec 2021 15:33:06 -0800 Subject: crypto: ccp - Add SEV_INIT_EX support Add new module parameter to allow users to use SEV_INIT_EX instead of SEV_INIT. This helps users who lock their SPI bus to use the PSP for SEV functionality. The 'init_ex_path' parameter defaults to NULL which means the kernel will use SEV_INIT, if a path is specified SEV_INIT_EX will be used with the data found at the path. On certain PSP commands this file is written to as the PSP updates the NV memory region. Depending on file system initialization this file open may fail during module init but the CCP driver for SEV already has sufficient retries for platform initialization. During normal operation of PSP system and SEV commands if the PSP has not been initialized it is at run time. If the file at 'init_ex_path' does not exist the PSP will not be initialized. The user must create the file prior to use with 32Kb of 0xFFs per spec. Signed-off-by: David Rientjes Co-developed-by: Peter Gonda Signed-off-by: Peter Gonda Reviewed-by: Marc Orr Reported-by: kernel test robot Acked-by: Brijesh Singh Cc: Tom Lendacky Cc: Brijesh Singh Cc: Marc Orr Cc: Joerg Roedel Cc: Herbert Xu Cc: David Rientjes Cc: John Allen Cc: "David S. Miller" Cc: Paolo Bonzini Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu --- Documentation/virt/kvm/amd-memory-encryption.rst | 6 + drivers/crypto/ccp/sev-dev.c | 193 +++++++++++++++++++++-- include/linux/psp-sev.h | 21 +++ 3 files changed, 205 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/amd-memory-encryption.rst b/Documentation/virt/kvm/amd-memory-encryption.rst index 5c081c8c7164..1c6847fff304 100644 --- a/Documentation/virt/kvm/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/amd-memory-encryption.rst @@ -85,6 +85,12 @@ guests, such as launching, running, snapshotting, migrating and decommissioning. The KVM_SEV_INIT command is used by the hypervisor to initialize the SEV platform context. In a typical workflow, this command should be the first command issued. +The firmware can be initialized either by using its own non-volatile storage or +the OS can manage the NV storage for the firmware using the module parameter +``init_ex_path``. The file specified by ``init_ex_path`` must exist. To create +a new NV storage file allocate the file with 32KB bytes of 0xFF as required by +the SEV spec. + Returns: 0 on success, -negative on error 2. KVM_SEV_LAUNCH_START diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index 686b16e69de7..991cc5aaaa0f 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -22,6 +22,7 @@ #include #include #include +#include #include @@ -43,6 +44,10 @@ static int psp_probe_timeout = 5; module_param(psp_probe_timeout, int, 0644); MODULE_PARM_DESC(psp_probe_timeout, " default timeout value, in seconds, during PSP device probe"); +static char *init_ex_path; +module_param(init_ex_path, charp, 0444); +MODULE_PARM_DESC(init_ex_path, " Path for INIT_EX data; if set try INIT_EX"); + static bool psp_init_on_probe = true; module_param(psp_init_on_probe, bool, 0444); MODULE_PARM_DESC(psp_init_on_probe, " if true, the PSP will be initialized on module init. Else the PSP will be initialized on the first command requiring it"); @@ -62,6 +67,14 @@ static int psp_timeout; #define SEV_ES_TMR_SIZE (1024 * 1024) static void *sev_es_tmr; +/* INIT_EX NV Storage: + * The NV Storage is a 32Kb area and must be 4Kb page aligned. Use the page + * allocator to allocate the memory, which will return aligned memory for the + * specified allocation order. + */ +#define NV_LENGTH (32 * 1024) +static void *sev_init_ex_buffer; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -111,6 +124,7 @@ static int sev_cmd_buffer_len(int cmd) { switch (cmd) { case SEV_CMD_INIT: return sizeof(struct sev_data_init); + case SEV_CMD_INIT_EX: return sizeof(struct sev_data_init_ex); case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); @@ -156,6 +170,101 @@ static void *sev_fw_alloc(unsigned long len) return page_address(page); } +static int sev_read_init_ex_file(void) +{ + struct sev_device *sev = psp_master->sev_data; + struct file *fp; + ssize_t nread; + + lockdep_assert_held(&sev_cmd_mutex); + + if (!sev_init_ex_buffer) + return -EOPNOTSUPP; + + fp = filp_open(init_ex_path, O_RDONLY, 0); + if (IS_ERR(fp)) { + int ret = PTR_ERR(fp); + + dev_err(sev->dev, + "SEV: could not open %s for read, error %d\n", + init_ex_path, ret); + return ret; + } + + nread = kernel_read(fp, sev_init_ex_buffer, NV_LENGTH, NULL); + if (nread != NV_LENGTH) { + dev_err(sev->dev, + "SEV: failed to read %u bytes to non volatile memory area, ret %ld\n", + NV_LENGTH, nread); + return -EIO; + } + + dev_dbg(sev->dev, "SEV: read %ld bytes from NV file\n", nread); + filp_close(fp, NULL); + + return 0; +} + +static void sev_write_init_ex_file(void) +{ + struct sev_device *sev = psp_master->sev_data; + struct file *fp; + loff_t offset = 0; + ssize_t nwrite; + + lockdep_assert_held(&sev_cmd_mutex); + + if (!sev_init_ex_buffer) + return; + + fp = filp_open(init_ex_path, O_CREAT | O_WRONLY, 0600); + if (IS_ERR(fp)) { + dev_err(sev->dev, + "SEV: could not open file for write, error %ld\n", + PTR_ERR(fp)); + return; + } + + nwrite = kernel_write(fp, sev_init_ex_buffer, NV_LENGTH, &offset); + vfs_fsync(fp, 0); + filp_close(fp, NULL); + + if (nwrite != NV_LENGTH) { + dev_err(sev->dev, + "SEV: failed to write %u bytes to non volatile memory area, ret %ld\n", + NV_LENGTH, nwrite); + return; + } + + dev_dbg(sev->dev, "SEV: write successful to NV file\n"); +} + +static void sev_write_init_ex_file_if_required(int cmd_id) +{ + lockdep_assert_held(&sev_cmd_mutex); + + if (!sev_init_ex_buffer) + return; + + /* + * Only a few platform commands modify the SPI/NV area, but none of the + * non-platform commands do. Only INIT(_EX), PLATFORM_RESET, PEK_GEN, + * PEK_CERT_IMPORT, and PDH_GEN do. + */ + switch (cmd_id) { + case SEV_CMD_FACTORY_RESET: + case SEV_CMD_INIT_EX: + case SEV_CMD_PDH_GEN: + case SEV_CMD_PEK_CERT_IMPORT: + case SEV_CMD_PEK_GEN: + break; + default: + return; + }; + + sev_write_init_ex_file(); +} + static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) { struct psp_device *psp = psp_master; @@ -225,6 +334,8 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) dev_dbg(sev->dev, "sev command %#x failed (%#010x)\n", cmd, reg & PSP_CMDRESP_ERR_MASK); ret = -EIO; + } else { + sev_write_init_ex_file_if_required(cmd); } print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, @@ -251,37 +362,71 @@ static int sev_do_cmd(int cmd, void *data, int *psp_ret) return rc; } -static int __sev_platform_init_locked(int *error) +static int __sev_init_locked(int *error) { - struct psp_device *psp = psp_master; struct sev_data_init data; - struct sev_device *sev; - int psp_ret, rc = 0; - if (!psp || !psp->sev_data) - return -ENODEV; + memset(&data, 0, sizeof(data)); + if (sev_es_tmr) { + /* + * Do not include the encryption mask on the physical + * address of the TMR (firmware should clear it anyway). + */ + data.tmr_address = __pa(sev_es_tmr); - sev = psp->sev_data; + data.flags |= SEV_INIT_FLAGS_SEV_ES; + data.tmr_len = SEV_ES_TMR_SIZE; + } - if (sev->state == SEV_STATE_INIT) - return 0; + return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error); +} + +static int __sev_init_ex_locked(int *error) +{ + struct sev_data_init_ex data; + int ret; memset(&data, 0, sizeof(data)); - if (sev_es_tmr) { - u64 tmr_pa; + data.length = sizeof(data); + data.nv_address = __psp_pa(sev_init_ex_buffer); + data.nv_len = NV_LENGTH; + + ret = sev_read_init_ex_file(); + if (ret) + return ret; + if (sev_es_tmr) { /* * Do not include the encryption mask on the physical * address of the TMR (firmware should clear it anyway). */ - tmr_pa = __pa(sev_es_tmr); + data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_address = tmr_pa; data.tmr_len = SEV_ES_TMR_SIZE; } - rc = __sev_do_cmd_locked(SEV_CMD_INIT, &data, &psp_ret); + return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error); +} + +static int __sev_platform_init_locked(int *error) +{ + struct psp_device *psp = psp_master; + struct sev_device *sev; + int rc, psp_ret; + int (*init_function)(int *error); + + if (!psp || !psp->sev_data) + return -ENODEV; + + sev = psp->sev_data; + + if (sev->state == SEV_STATE_INIT) + return 0; + + init_function = sev_init_ex_buffer ? __sev_init_ex_locked : + __sev_init_locked; + rc = init_function(&psp_ret); if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) { /* * Initialization command returned an integrity check failure @@ -291,7 +436,7 @@ static int __sev_platform_init_locked(int *error) * with a reset state. */ dev_dbg(sev->dev, "SEV: retrying INIT command"); - rc = __sev_do_cmd_locked(SEV_CMD_INIT, &data, &psp_ret); + rc = init_function(&psp_ret); } if (error) *error = psp_ret; @@ -1066,6 +1211,12 @@ static void sev_firmware_shutdown(struct sev_device *sev) get_order(SEV_ES_TMR_SIZE)); sev_es_tmr = NULL; } + + if (sev_init_ex_buffer) { + free_pages((unsigned long)sev_init_ex_buffer, + get_order(NV_LENGTH)); + sev_init_ex_buffer = NULL; + } } void sev_dev_destroy(struct psp_device *psp) @@ -1110,6 +1261,18 @@ void sev_pci_init(void) sev_update_firmware(sev->dev) == 0) sev_get_api_version(); + /* If an init_ex_path is provided rely on INIT_EX for PSP initialization + * instead of INIT. + */ + if (init_ex_path) { + sev_init_ex_buffer = sev_fw_alloc(NV_LENGTH); + if (!sev_init_ex_buffer) { + dev_err(sev->dev, + "SEV: INIT_EX NV memory allocation failed\n"); + goto err; + } + } + /* Obtain the TMR memory area for SEV-ES use */ sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); if (!sev_es_tmr) diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h index d48a7192e881..1595088c428b 100644 --- a/include/linux/psp-sev.h +++ b/include/linux/psp-sev.h @@ -52,6 +52,7 @@ enum sev_cmd { SEV_CMD_DF_FLUSH = 0x00A, SEV_CMD_DOWNLOAD_FIRMWARE = 0x00B, SEV_CMD_GET_ID = 0x00C, + SEV_CMD_INIT_EX = 0x00D, /* Guest commands */ SEV_CMD_DECOMMISSION = 0x020, @@ -102,6 +103,26 @@ struct sev_data_init { u32 tmr_len; /* In */ } __packed; +/** + * struct sev_data_init_ex - INIT_EX command parameters + * + * @length: len of the command buffer read by the PSP + * @flags: processing flags + * @tmr_address: system physical address used for SEV-ES + * @tmr_len: len of tmr_address + * @nv_address: system physical address used for PSP NV storage + * @nv_len: len of nv_address + */ +struct sev_data_init_ex { + u32 length; /* In */ + u32 flags; /* In */ + u64 tmr_address; /* In */ + u32 tmr_len; /* In */ + u32 reserved; /* In */ + u64 nv_address; /* In/Out */ + u32 nv_len; /* In */ +} __packed; + #define SEV_INIT_FLAGS_SEV_ES 0x01 /** -- cgit v1.2.3 From 9dfa5b6f5efb85efe69fd3b7b0b912004d9547f1 Mon Sep 17 00:00:00 2001 From: Lu Baolu Date: Thu, 16 Dec 2021 09:17:03 +0800 Subject: iommu/vt-d: Remove unused macros These macros has no reference in the tree anymore. Cleanup them. Signed-off-by: Lu Baolu Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211216011703.763331-1-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- include/linux/intel-svm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/intel-svm.h b/include/linux/intel-svm.h index 57cceecbe37f..1b73bab7eeff 100644 --- a/include/linux/intel-svm.h +++ b/include/linux/intel-svm.h @@ -8,12 +8,6 @@ #ifndef __INTEL_SVM_H__ #define __INTEL_SVM_H__ -/* Values for rxwp in fault_cb callback */ -#define SVM_REQ_READ (1<<3) -#define SVM_REQ_WRITE (1<<2) -#define SVM_REQ_EXEC (1<<1) -#define SVM_REQ_PRIV (1<<0) - /* Page Request Queue depth */ #define PRQ_ORDER 2 #define PRQ_RING_MASK ((0x1000 << PRQ_ORDER) - 0x20) -- cgit v1.2.3 From b62e3317b68d9c84301940ca8ca9c35a584111b2 Mon Sep 17 00:00:00 2001 From: Xiang wangx Date: Thu, 16 Dec 2021 23:19:16 +0800 Subject: net: fix typo in a comment The double 'as' in a comment is repeated, thus it should be removed. Signed-off-by: Xiang wangx Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index be5cb3360b94..6aadcc0ecb5b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1937,7 +1937,7 @@ enum netdev_ml_priv_type { * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * - * @nested_level: Used as as a parameter of spin_lock_nested() of + * @nested_level: Used as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. -- cgit v1.2.3 From dd61b29207ca4f346fbd9c06bc49f093e3369185 Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Tue, 7 Dec 2021 10:34:06 +0100 Subject: gpiolib: provide gpiod_remove_hogs() Currently all users of gpiod_add_hogs() call it only once at system init so there never was any need for a mechanism allowing to remove them. Now the upcoming gpio-sim will need to tear down chips with hogged lines so provide a function that allows to remove hogs. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij --- drivers/gpio/gpiolib.c | 11 +++++++++++ include/linux/gpio/machine.h | 2 ++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 535eb1b509c1..467f4a8586a0 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -3557,6 +3557,17 @@ void gpiod_add_hogs(struct gpiod_hog *hogs) } EXPORT_SYMBOL_GPL(gpiod_add_hogs); +void gpiod_remove_hogs(struct gpiod_hog *hogs) +{ + struct gpiod_hog *hog; + + mutex_lock(&gpio_machine_hogs_mutex); + for (hog = &hogs[0]; hog->chip_label; hog++) + list_del(&hog->list); + mutex_unlock(&gpio_machine_hogs_mutex); +} +EXPORT_SYMBOL_GPL(gpiod_remove_hogs); + static struct gpiod_lookup_table *gpiod_find_lookup_table(struct device *dev) { const char *dev_id = dev ? dev_name(dev) : NULL; diff --git a/include/linux/gpio/machine.h b/include/linux/gpio/machine.h index d755e529c1e3..2647dd10b541 100644 --- a/include/linux/gpio/machine.h +++ b/include/linux/gpio/machine.h @@ -100,6 +100,7 @@ void gpiod_add_lookup_table(struct gpiod_lookup_table *table); void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n); void gpiod_remove_lookup_table(struct gpiod_lookup_table *table); void gpiod_add_hogs(struct gpiod_hog *hogs); +void gpiod_remove_hogs(struct gpiod_hog *hogs); #else /* ! CONFIG_GPIOLIB */ static inline void gpiod_add_lookup_table(struct gpiod_lookup_table *table) {} @@ -108,6 +109,7 @@ void gpiod_add_lookup_tables(struct gpiod_lookup_table **tables, size_t n) {} static inline void gpiod_remove_lookup_table(struct gpiod_lookup_table *table) {} static inline void gpiod_add_hogs(struct gpiod_hog *hogs) {} +static inline void gpiod_remove_hogs(struct gpiod_hog *hogs) {} #endif /* CONFIG_GPIOLIB */ #endif /* __LINUX_GPIO_MACHINE_H */ -- cgit v1.2.3 From 990f6756bb64756d2d1033118cded6333b43397d Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Mon, 13 Dec 2021 11:16:41 +0100 Subject: gpiolib: allow to specify the firmware node in struct gpio_chip Software nodes allow us to represent hierarchies for device components that don't have their struct device representation yet - for instance: banks of GPIOs under a common GPIO expander. The core gpiolib core however doesn't offer any way of passing this information from the drivers. This extends struct gpio_chip with a pointer to fwnode that can be set by the driver and used to pass device properties for child nodes. This is similar to how we handle device-tree sub-nodes with CONFIG_OF_GPIO enabled. Signed-off-by: Bartosz Golaszewski Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij --- drivers/gpio/gpiolib.c | 7 ++++++- include/linux/gpio/driver.h | 2 ++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 467f4a8586a0..4d666767c9ab 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -593,7 +593,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct lock_class_key *lock_key, struct lock_class_key *request_key) { - struct fwnode_handle *fwnode = gc->parent ? dev_fwnode(gc->parent) : NULL; + struct fwnode_handle *fwnode = NULL; struct gpio_device *gdev; unsigned long flags; int base = gc->base; @@ -601,6 +601,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, int ret = 0; u32 ngpios; + if (gc->fwnode) + fwnode = gc->fwnode; + else if (gc->parent) + fwnode = dev_fwnode(gc->parent); + /* * First: allocate and populate the internal stat container, and * set up the struct device. diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index a673a359e20b..b0728c8ad90c 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -289,6 +289,7 @@ struct gpio_irq_chip { * number or the name of the SoC IP-block implementing it. * @gpiodev: the internal state holder, opaque struct * @parent: optional parent device providing the GPIOs + * @fwnode: optional fwnode providing this controller's properties * @owner: helps prevent removal of modules exporting active GPIOs * @request: optional hook for chip-specific activation, such as * enabling module power and clock; may sleep @@ -377,6 +378,7 @@ struct gpio_chip { const char *label; struct gpio_device *gpiodev; struct device *parent; + struct fwnode_handle *fwnode; struct module *owner; int (*request)(struct gpio_chip *gc, -- cgit v1.2.3 From c06ef740d401d0f4ab188882bf6f8d9cf0f75eaf Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 7 Dec 2021 00:20:59 +0000 Subject: PM: core: Redefine pm_ptr() macro The pm_ptr() macro was previously conditionally defined, according to the value of the CONFIG_PM option. This meant that the pointed structure was either referenced (if CONFIG_PM was set), or never referenced (if CONFIG_PM was not set), causing it to be detected as unused by the compiler. This worked fine, but required the __maybe_unused compiler attribute to be used to every symbol pointed to by a pointer wrapped with pm_ptr(). We can do better. With this change, the pm_ptr() is now defined the same, independently of the value of CONFIG_PM. It now uses the (?:) ternary operator to conditionally resolve to its argument. Since the condition is known at compile time, the compiler will then choose to discard the unused symbols, which won't need to be tagged with __maybe_unused anymore. This pm_ptr() macro is usually used with pointers to dev_pm_ops structures created with SIMPLE_DEV_PM_OPS() or similar macros. These do use a __maybe_unused flag, which is now useless with this change, so it later can be removed. However in the meantime it causes no harm, and all the drivers still compile fine with the new pm_ptr() macro. Signed-off-by: Paul Cercueil Reviewed-by: Jonathan Cameron Reviewed-by: Arnd Bergmann Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 1d8209c09686..b88ac7dcf2a2 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -373,11 +373,7 @@ const struct dev_pm_ops __maybe_unused name = { \ SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ } -#ifdef CONFIG_PM -#define pm_ptr(_ptr) (_ptr) -#else -#define pm_ptr(_ptr) NULL -#endif +#define pm_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM), (_ptr)) /* * PM_EVENT_ messages -- cgit v1.2.3 From 1a3c7bb088266fa2db017be299f91f1c1894c857 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 7 Dec 2021 00:21:00 +0000 Subject: PM: core: Add new *_PM_OPS macros, deprecate old ones This commit introduces the following macros: SYSTEM_SLEEP_PM_OPS() LATE_SYSTEM_SLEEP_PM_OPS() NOIRQ_SYSTEM_SLEEP_PM_OPS() RUNTIME_PM_OPS() These new macros are very similar to their SET_*_PM_OPS() equivalent. They however differ in the fact that the callbacks they set will always be seen as referenced by the compiler. This means that the callback functions don't need to be wrapped with a #ifdef CONFIG_PM guard, or tagged with __maybe_unused, to prevent the compiler from complaining about unused static symbols. The compiler will then simply evaluate at compile time whether or not these symbols are dead code. The callbacks that are only useful with CONFIG_PM_SLEEP is enabled, are now also wrapped with a new pm_sleep_ptr() macro, which is inspired from pm_ptr(). This is needed for drivers that use different callbacks for sleep and runtime PM, to handle the case where CONFIG_PM is set and CONFIG_PM_SLEEP is not. This commit also deprecates the following macros: SIMPLE_DEV_PM_OPS() UNIVERSAL_DEV_PM_OPS() And introduces the following macros: DEFINE_SIMPLE_DEV_PM_OPS() DEFINE_UNIVERSAL_DEV_PM_OPS() These macros are similar to the functions they were created to replace, with the following differences: - They use the new macros introduced above, and as such always reference the provided callback functions. - They are not tagged with __maybe_unused. They are meant to be used with pm_ptr() or pm_sleep_ptr() for DEFINE_UNIVERSAL_DEV_PM_OPS() and DEFINE_SIMPLE_DEV_PM_OPS() respectively. - They declare the symbol static, since every driver seems to do that anyway; and if a non-static use-case is needed an indirection pointer could be used. The point of this change, is to progressively switch from a code model where PM callbacks are all protected behind CONFIG_PM guards, to a code model where the PM callbacks are always seen by the compiler, but discarded if not used. Signed-off-by: Paul Cercueil Reviewed-by: Jonathan Cameron Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 74 ++++++++++++++++++++++++++++++++++++------------------ 1 file changed, 50 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index b88ac7dcf2a2..fc9691cb01b4 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -300,47 +300,59 @@ struct dev_pm_ops { int (*runtime_idle)(struct device *dev); }; +#define SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend = pm_sleep_ptr(suspend_fn), \ + .resume = pm_sleep_ptr(resume_fn), \ + .freeze = pm_sleep_ptr(suspend_fn), \ + .thaw = pm_sleep_ptr(resume_fn), \ + .poweroff = pm_sleep_ptr(suspend_fn), \ + .restore = pm_sleep_ptr(resume_fn), + +#define LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_late = pm_sleep_ptr(suspend_fn), \ + .resume_early = pm_sleep_ptr(resume_fn), \ + .freeze_late = pm_sleep_ptr(suspend_fn), \ + .thaw_early = pm_sleep_ptr(resume_fn), \ + .poweroff_late = pm_sleep_ptr(suspend_fn), \ + .restore_early = pm_sleep_ptr(resume_fn), + +#define NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + .suspend_noirq = pm_sleep_ptr(suspend_fn), \ + .resume_noirq = pm_sleep_ptr(resume_fn), \ + .freeze_noirq = pm_sleep_ptr(suspend_fn), \ + .thaw_noirq = pm_sleep_ptr(resume_fn), \ + .poweroff_noirq = pm_sleep_ptr(suspend_fn), \ + .restore_noirq = pm_sleep_ptr(resume_fn), + +#define RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ + .runtime_suspend = suspend_fn, \ + .runtime_resume = resume_fn, \ + .runtime_idle = idle_fn, + #ifdef CONFIG_PM_SLEEP #define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend = suspend_fn, \ - .resume = resume_fn, \ - .freeze = suspend_fn, \ - .thaw = resume_fn, \ - .poweroff = suspend_fn, \ - .restore = resume_fn, + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM_SLEEP #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend_late = suspend_fn, \ - .resume_early = resume_fn, \ - .freeze_late = suspend_fn, \ - .thaw_early = resume_fn, \ - .poweroff_late = suspend_fn, \ - .restore_early = resume_fn, + LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_LATE_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM_SLEEP #define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - .suspend_noirq = suspend_fn, \ - .resume_noirq = resume_fn, \ - .freeze_noirq = suspend_fn, \ - .thaw_noirq = resume_fn, \ - .poweroff_noirq = suspend_fn, \ - .restore_noirq = resume_fn, + NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #else #define SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) #endif #ifdef CONFIG_PM #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ - .runtime_suspend = suspend_fn, \ - .runtime_resume = resume_fn, \ - .runtime_idle = idle_fn, + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #else #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #endif @@ -349,9 +361,9 @@ struct dev_pm_ops { * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. */ -#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops __maybe_unused name = { \ - SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ +#define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +static const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } /* @@ -367,6 +379,19 @@ const struct dev_pm_ops __maybe_unused name = { \ * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). */ +#define DEFINE_UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ +static const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ +} + +/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ +#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +const struct dev_pm_ops __maybe_unused name = { \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ +} + +/* Deprecated. Use DEFINE_UNIVERSAL_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ @@ -374,6 +399,7 @@ const struct dev_pm_ops __maybe_unused name = { \ } #define pm_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM), (_ptr)) +#define pm_sleep_ptr(_ptr) PTR_IF(IS_ENABLED(CONFIG_PM_SLEEP), (_ptr)) /* * PM_EVENT_ messages -- cgit v1.2.3 From 931da6a0de5d620425af4425344259e6ff46b654 Mon Sep 17 00:00:00 2001 From: Zhang Rui Date: Tue, 7 Dec 2021 21:17:34 +0800 Subject: powercap: intel_rapl: support new layout of Psys PowerLimit Register on SPR On Sapphire Rapids, the layout of the Psys domain Power Limit Register is different from from what it was before. Enhance the code to support the new Psys PL register layout. Signed-off-by: Zhang Rui Reported-and-tested-by: Alkattan Dana [ rjw: Subject and changelog edits ] Signed-off-by: Rafael J. Wysocki --- drivers/powercap/intel_rapl_common.c | 61 ++++++++++++++++++++++++++++++++++-- include/linux/intel_rapl.h | 6 ++++ 2 files changed, 65 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c index 7c0099e7a6d7..07611a00b78f 100644 --- a/drivers/powercap/intel_rapl_common.c +++ b/drivers/powercap/intel_rapl_common.c @@ -61,6 +61,20 @@ #define PERF_STATUS_THROTTLE_TIME_MASK 0xffffffff #define PP_POLICY_MASK 0x1F +/* + * SPR has different layout for Psys Domain PowerLimit registers. + * There are 17 bits of PL1 and PL2 instead of 15 bits. + * The Enable bits and TimeWindow bits are also shifted as a result. + */ +#define PSYS_POWER_LIMIT1_MASK 0x1FFFF +#define PSYS_POWER_LIMIT1_ENABLE BIT(17) + +#define PSYS_POWER_LIMIT2_MASK (0x1FFFFULL<<32) +#define PSYS_POWER_LIMIT2_ENABLE BIT_ULL(49) + +#define PSYS_TIME_WINDOW1_MASK (0x7FULL<<19) +#define PSYS_TIME_WINDOW2_MASK (0x7FULL<<51) + /* Non HW constants */ #define RAPL_PRIMITIVE_DERIVED BIT(1) /* not from raw data */ #define RAPL_PRIMITIVE_DUMMY BIT(2) @@ -97,6 +111,7 @@ struct rapl_defaults { bool to_raw); unsigned int dram_domain_energy_unit; unsigned int psys_domain_energy_unit; + bool spr_psys_bits; }; static struct rapl_defaults *rapl_defaults; @@ -669,12 +684,51 @@ static struct rapl_primitive_info rpi[] = { RAPL_DOMAIN_REG_PERF, TIME_UNIT, 0), PRIMITIVE_INFO_INIT(PRIORITY_LEVEL, PP_POLICY_MASK, 0, RAPL_DOMAIN_REG_POLICY, ARBITRARY_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_POWER_LIMIT1, PSYS_POWER_LIMIT1_MASK, 0, + RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_POWER_LIMIT2, PSYS_POWER_LIMIT2_MASK, 32, + RAPL_DOMAIN_REG_LIMIT, POWER_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_PL1_ENABLE, PSYS_POWER_LIMIT1_ENABLE, 17, + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_PL2_ENABLE, PSYS_POWER_LIMIT2_ENABLE, 49, + RAPL_DOMAIN_REG_LIMIT, ARBITRARY_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_TIME_WINDOW1, PSYS_TIME_WINDOW1_MASK, 19, + RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0), + PRIMITIVE_INFO_INIT(PSYS_TIME_WINDOW2, PSYS_TIME_WINDOW2_MASK, 51, + RAPL_DOMAIN_REG_LIMIT, TIME_UNIT, 0), /* non-hardware */ PRIMITIVE_INFO_INIT(AVERAGE_POWER, 0, 0, 0, POWER_UNIT, RAPL_PRIMITIVE_DERIVED), {NULL, 0, 0, 0}, }; +static enum rapl_primitives +prim_fixups(struct rapl_domain *rd, enum rapl_primitives prim) +{ + if (!rapl_defaults->spr_psys_bits) + return prim; + + if (rd->id != RAPL_DOMAIN_PLATFORM) + return prim; + + switch (prim) { + case POWER_LIMIT1: + return PSYS_POWER_LIMIT1; + case POWER_LIMIT2: + return PSYS_POWER_LIMIT2; + case PL1_ENABLE: + return PSYS_PL1_ENABLE; + case PL2_ENABLE: + return PSYS_PL2_ENABLE; + case TIME_WINDOW1: + return PSYS_TIME_WINDOW1; + case TIME_WINDOW2: + return PSYS_TIME_WINDOW2; + default: + return prim; + } +} + /* Read primitive data based on its related struct rapl_primitive_info. * if xlate flag is set, return translated data based on data units, i.e. * time, energy, and power. @@ -692,7 +746,8 @@ static int rapl_read_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, bool xlate, u64 *data) { u64 value; - struct rapl_primitive_info *rp = &rpi[prim]; + enum rapl_primitives prim_fixed = prim_fixups(rd, prim); + struct rapl_primitive_info *rp = &rpi[prim_fixed]; struct reg_action ra; int cpu; @@ -738,7 +793,8 @@ static int rapl_write_data_raw(struct rapl_domain *rd, enum rapl_primitives prim, unsigned long long value) { - struct rapl_primitive_info *rp = &rpi[prim]; + enum rapl_primitives prim_fixed = prim_fixups(rd, prim); + struct rapl_primitive_info *rp = &rpi[prim_fixed]; int cpu; u64 bits; struct reg_action ra; @@ -981,6 +1037,7 @@ static const struct rapl_defaults rapl_defaults_spr_server = { .compute_time_window = rapl_compute_time_window_core, .dram_domain_energy_unit = 15300, .psys_domain_energy_unit = 1000000000, + .spr_psys_bits = true, }; static const struct rapl_defaults rapl_defaults_byt = { diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h index 93780834fc8f..9f4b6f5b822f 100644 --- a/include/linux/intel_rapl.h +++ b/include/linux/intel_rapl.h @@ -58,6 +58,12 @@ enum rapl_primitives { THROTTLED_TIME, PRIORITY_LEVEL, + PSYS_POWER_LIMIT1, + PSYS_POWER_LIMIT2, + PSYS_PL1_ENABLE, + PSYS_PL2_ENABLE, + PSYS_TIME_WINDOW1, + PSYS_TIME_WINDOW2, /* below are not raw primitive data */ AVERAGE_POWER, NR_RAPL_PRIMITIVES, -- cgit v1.2.3 From c24efa6732788f0be22cdf5d2aedd5e3117e983f Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 7 Dec 2021 19:54:32 +0100 Subject: PM: runtime: Capture device status before disabling runtime PM In some cases (for example, during system-wide suspend and resume of devices) it is useful to know whether or not runtime PM has ever been enabled for a given device and, if so, what the runtime PM status of it had been right before runtime PM was disabled for it last time. For this reason, introduce a new struct dev_pm_info field called last_status that will be used for capturing the runtime PM status of the device when its power.disable_depth counter changes from 0 to 1. The new field will be set to RPM_INVALID to start with and whenever power.disable_depth changes from 1 to 0, so it will be valid only when runtime PM of the device is currently disabled, but it has been enabled at least once. Immediately use power.last_status in rpm_resume() to make it handle the case when PM runtime is disabled for the device, but its runtime PM status is RPM_ACTIVE more consistently. Namely, make it return 1 if power.last_status is also equal to RPM_ACTIVE in that case (the idea being that if the status was RPM_ACTIVE last time when power.disable_depth was changing from 0 to 1 and it is still RPM_ACTIVE, it can be assumed to reflect what happened to the device last time when it was using runtime PM) and -EACCES otherwise. Update the documentation to provide a description of last_status and change the description of pm_runtime_resume() in it to reflect the new behavior of rpm_active(). While at it, rearrange the code in pm_runtime_enable() to be more straightforward and replace the WARN() macro in it with a pr_warn() invocation which is less disruptive. Link: https://lore.kernel.org/linux-pm/20211026222626.39222-1-ulf.hansson@linaro.org/t/#u Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- Documentation/power/runtime_pm.rst | 14 ++++++++---- drivers/base/power/runtime.c | 45 +++++++++++++++++++++----------------- include/linux/pm.h | 2 ++ 3 files changed, 37 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst index d6bf84f061f4..65b86e487afe 100644 --- a/Documentation/power/runtime_pm.rst +++ b/Documentation/power/runtime_pm.rst @@ -265,6 +265,10 @@ defined in include/linux/pm.h: RPM_SUSPENDED, which means that each device is initially regarded by the PM core as 'suspended', regardless of its real hardware status + `enum rpm_status last_status;` + - the last runtime PM status of the device captured before disabling runtime + PM for it (invalid initially and when disable_depth is 0) + `unsigned int runtime_auto;` - if set, indicates that the user space has allowed the device driver to power manage the device at run time via the /sys/devices/.../power/control @@ -333,10 +337,12 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h: `int pm_runtime_resume(struct device *dev);` - execute the subsystem-level resume callback for the device; returns 0 on - success, 1 if the device's runtime PM status was already 'active' or - error code on failure, where -EAGAIN means it may be safe to attempt to - resume the device again in future, but 'power.runtime_error' should be - checked additionally, and -EACCES means that 'power.disable_depth' is + success, 1 if the device's runtime PM status is already 'active' (also if + 'power.disable_depth' is nonzero, but the status was 'active' when it was + changing from 0 to 1) or error code on failure, where -EAGAIN means it may + be safe to attempt to resume the device again in future, but + 'power.runtime_error' should be checked additionally, and -EACCES means + that the callback could not be run, because 'power.disable_depth' was different from 0 `int pm_runtime_resume_and_get(struct device *dev);` diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index d504cd4ab3cb..844b6b811610 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -742,13 +742,15 @@ static int rpm_resume(struct device *dev, int rpmflags) trace_rpm_resume_rcuidle(dev, rpmflags); repeat: - if (dev->power.runtime_error) + if (dev->power.runtime_error) { retval = -EINVAL; - else if (dev->power.disable_depth == 1 && dev->power.is_suspended - && dev->power.runtime_status == RPM_ACTIVE) - retval = 1; - else if (dev->power.disable_depth > 0) - retval = -EACCES; + } else if (dev->power.disable_depth > 0) { + if (dev->power.runtime_status == RPM_ACTIVE && + dev->power.last_status == RPM_ACTIVE) + retval = 1; + else + retval = -EACCES; + } if (retval) goto out; @@ -1410,8 +1412,10 @@ void __pm_runtime_disable(struct device *dev, bool check_resume) /* Update time accounting before disabling PM-runtime. */ update_pm_runtime_accounting(dev); - if (!dev->power.disable_depth++) + if (!dev->power.disable_depth++) { __pm_runtime_barrier(dev); + dev->power.last_status = dev->power.runtime_status; + } out: spin_unlock_irq(&dev->power.lock); @@ -1428,23 +1432,23 @@ void pm_runtime_enable(struct device *dev) spin_lock_irqsave(&dev->power.lock, flags); - if (dev->power.disable_depth > 0) { - dev->power.disable_depth--; - - /* About to enable runtime pm, set accounting_timestamp to now */ - if (!dev->power.disable_depth) - dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); - } else { + if (!dev->power.disable_depth) { dev_warn(dev, "Unbalanced %s!\n", __func__); + goto out; } - WARN(!dev->power.disable_depth && - dev->power.runtime_status == RPM_SUSPENDED && - !dev->power.ignore_children && - atomic_read(&dev->power.child_count) > 0, - "Enabling runtime PM for inactive device (%s) with active children\n", - dev_name(dev)); + if (--dev->power.disable_depth > 0) + goto out; + dev->power.last_status = RPM_INVALID; + dev->power.accounting_timestamp = ktime_get_mono_fast_ns(); + + if (dev->power.runtime_status == RPM_SUSPENDED && + !dev->power.ignore_children && + atomic_read(&dev->power.child_count) > 0) + dev_warn(dev, "Enabling runtime PM for inactive device with active children\n"); + +out: spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_runtime_enable); @@ -1640,6 +1644,7 @@ EXPORT_SYMBOL_GPL(__pm_runtime_use_autosuspend); void pm_runtime_init(struct device *dev) { dev->power.runtime_status = RPM_SUSPENDED; + dev->power.last_status = RPM_INVALID; dev->power.idle_notification = false; dev->power.disable_depth = 1; diff --git a/include/linux/pm.h b/include/linux/pm.h index fc9691cb01b4..e1e9402180b9 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -521,6 +521,7 @@ const struct dev_pm_ops __maybe_unused name = { \ */ enum rpm_status { + RPM_INVALID = -1, RPM_ACTIVE = 0, RPM_RESUMING, RPM_SUSPENDED, @@ -634,6 +635,7 @@ struct dev_pm_info { unsigned int links_count; enum rpm_request request; enum rpm_status runtime_status; + enum rpm_status last_status; int runtime_error; int autosuspend_delay; u64 last_busy; -- cgit v1.2.3 From d1579e61192e0e686faa4208500ef4c3b529b16c Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 10 Dec 2021 17:10:13 +0100 Subject: PM: runtime: Add safety net to supplier device release Because refcount_dec_not_one() returns true if the target refcount becomes saturated, it is generally unsafe to use its return value as a loop termination condition, but that is what happens when a device link's supplier device is released during runtime PM suspend operations and on device link removal. To address this, introduce pm_runtime_release_supplier() to be used in the above cases which will check the supplier device's runtime PM usage counter in addition to the refcount_dec_not_one() return value, so the loop can be terminated in case the rpm_active refcount value becomes invalid, and update the code in question to use it as appropriate. This change is not expected to have any visible functional impact. Reported-by: Peter Zijlstra Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Acked-by: Peter Zijlstra (Intel) --- drivers/base/core.c | 3 +-- drivers/base/power/runtime.c | 41 ++++++++++++++++++++++++++++++----------- include/linux/pm_runtime.h | 3 +++ 3 files changed, 34 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index fd034d742447..b191bd17de89 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -485,8 +485,7 @@ static void device_link_release_fn(struct work_struct *work) /* Ensure that all references to the link object have been dropped. */ device_link_synchronize_removal(); - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); + pm_runtime_release_supplier(link, true); put_device(link->consumer); put_device(link->supplier); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 844b6b811610..f1b856ea8e10 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -305,19 +305,40 @@ static int rpm_get_suppliers(struct device *dev) return 0; } +/** + * pm_runtime_release_supplier - Drop references to device link's supplier. + * @link: Target device link. + * @check_idle: Whether or not to check if the supplier device is idle. + * + * Drop all runtime PM references associated with @link to its supplier device + * and if @check_idle is set, check if that device is idle (and so it can be + * suspended). + */ +void pm_runtime_release_supplier(struct device_link *link, bool check_idle) +{ + struct device *supplier = link->supplier; + + /* + * The additional power.usage_count check is a safety net in case + * the rpm_active refcount becomes saturated, in which case + * refcount_dec_not_one() would return true forever, but it is not + * strictly necessary. + */ + while (refcount_dec_not_one(&link->rpm_active) && + atomic_read(&supplier->power.usage_count) > 0) + pm_runtime_put_noidle(supplier); + + if (check_idle) + pm_request_idle(supplier); +} + static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, - device_links_read_lock_held()) { - - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put_noidle(link->supplier); - - if (try_to_suspend) - pm_request_idle(link->supplier); - } + device_links_read_lock_held()) + pm_runtime_release_supplier(link, try_to_suspend); } static void rpm_put_suppliers(struct device *dev) @@ -1777,9 +1798,7 @@ void pm_runtime_drop_link(struct device_link *link) return; pm_runtime_drop_link_count(link->consumer); - - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); + pm_runtime_release_supplier(link, true); } static bool pm_runtime_need_not_resume(struct device *dev) diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index eddd66d426ca..016de5776b6d 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -58,6 +58,7 @@ extern void pm_runtime_get_suppliers(struct device *dev); extern void pm_runtime_put_suppliers(struct device *dev); extern void pm_runtime_new_link(struct device *dev); extern void pm_runtime_drop_link(struct device_link *link); +extern void pm_runtime_release_supplier(struct device_link *link, bool check_idle); extern int devm_pm_runtime_enable(struct device *dev); @@ -283,6 +284,8 @@ static inline void pm_runtime_get_suppliers(struct device *dev) {} static inline void pm_runtime_put_suppliers(struct device *dev) {} static inline void pm_runtime_new_link(struct device *dev) {} static inline void pm_runtime_drop_link(struct device_link *link) {} +static inline void pm_runtime_release_supplier(struct device_link *link, + bool check_idle) {} #endif /* !CONFIG_PM */ -- cgit v1.2.3 From 227fee5fc99eeb74d43bf68832f6d59d30ac07d8 Mon Sep 17 00:00:00 2001 From: Manivannan Sadhasivam Date: Thu, 16 Dec 2021 13:42:25 +0530 Subject: bus: mhi: core: Add an API for auto queueing buffers for DL channel Add a new API "mhi_prepare_for_transfer_autoqueue" for using with client drivers like QRTR to request MHI core to autoqueue buffers for the DL channel along with starting both UL and DL channels. So far, the "auto_queue" flag specified by the controller drivers in channel definition served this purpose but this will be removed at some point in future. Cc: netdev@vger.kernel.org Cc: Jakub Kicinski Cc: David S. Miller Cc: Greg Kroah-Hartman Co-developed-by: Loic Poulain Acked-by: Jakub Kicinski Signed-off-by: Loic Poulain Signed-off-by: Manivannan Sadhasivam Link: https://lore.kernel.org/r/20211216081227.237749-9-manivannan.sadhasivam@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/bus/mhi/core/internal.h | 6 +++++- drivers/bus/mhi/core/main.c | 21 +++++++++++++++++---- include/linux/mhi.h | 21 ++++++++++++++++----- net/qrtr/mhi.c | 2 +- 4 files changed, 39 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 9d72b1d1e986..e2e10474a9d9 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -682,8 +682,12 @@ void mhi_deinit_free_irq(struct mhi_controller *mhi_cntrl); void mhi_rddm_prepare(struct mhi_controller *mhi_cntrl, struct image_info *img_info); void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl); + +/* Automatically allocate and queue inbound buffers */ +#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0) int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan); + struct mhi_chan *mhi_chan, unsigned int flags); + int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan); void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl, diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index 930aba666b67..ffde617f93a3 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1430,7 +1430,7 @@ exit_unprepare_channel: } int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, - struct mhi_chan *mhi_chan) + struct mhi_chan *mhi_chan, unsigned int flags) { int ret = 0; struct device *dev = &mhi_chan->mhi_dev->dev; @@ -1455,6 +1455,9 @@ int mhi_prepare_channel(struct mhi_controller *mhi_cntrl, if (ret) goto error_pm_state; + if (mhi_chan->dir == DMA_FROM_DEVICE) + mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS); + /* Pre-allocate buffer for xfer ring */ if (mhi_chan->pre_alloc) { int nr_el = get_nr_avail_ring_elements(mhi_cntrl, @@ -1610,8 +1613,7 @@ void mhi_reset_chan(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan) read_unlock_bh(&mhi_cntrl->pm_lock); } -/* Move channel to start state */ -int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) +static int __mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags) { int ret, dir; struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; @@ -1622,7 +1624,7 @@ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) if (!mhi_chan) continue; - ret = mhi_prepare_channel(mhi_cntrl, mhi_chan); + ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags); if (ret) goto error_open_chan; } @@ -1640,8 +1642,19 @@ error_open_chan: return ret; } + +int mhi_prepare_for_transfer(struct mhi_device *mhi_dev) +{ + return __mhi_prepare_for_transfer(mhi_dev, 0); +} EXPORT_SYMBOL_GPL(mhi_prepare_for_transfer); +int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev) +{ + return __mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS); +} +EXPORT_SYMBOL_GPL(mhi_prepare_for_transfer_autoqueue); + void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev) { struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; diff --git a/include/linux/mhi.h b/include/linux/mhi.h index a5cc4cdf9cc8..a5441ad33c74 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -730,15 +730,26 @@ void mhi_device_put(struct mhi_device *mhi_dev); /** * mhi_prepare_for_transfer - Setup UL and DL channels for data transfer. - * Allocate and initialize the channel context and - * also issue the START channel command to both - * channels. Channels can be started only if both - * host and device execution environments match and - * channels are in a DISABLED state. * @mhi_dev: Device associated with the channels + * + * Allocate and initialize the channel context and also issue the START channel + * command to both channels. Channels can be started only if both host and + * device execution environments match and channels are in a DISABLED state. */ int mhi_prepare_for_transfer(struct mhi_device *mhi_dev); +/** + * mhi_prepare_for_transfer_autoqueue - Setup UL and DL channels with auto queue + * buffers for DL traffic + * @mhi_dev: Device associated with the channels + * + * Allocate and initialize the channel context and also issue the START channel + * command to both channels. Channels can be started only if both host and + * device execution environments match and channels are in a DISABLED state. + * The MHI core will automatically allocate and queue buffers for the DL traffic. + */ +int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev); + /** * mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer. * Issue the RESET channel command and let the diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c index fa611678af05..18196e1c8c2f 100644 --- a/net/qrtr/mhi.c +++ b/net/qrtr/mhi.c @@ -79,7 +79,7 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev, int rc; /* start channels */ - rc = mhi_prepare_for_transfer(mhi_dev); + rc = mhi_prepare_for_transfer_autoqueue(mhi_dev); if (rc) return rc; -- cgit v1.2.3 From 49f39cb0ef198ae3c73765c9b9ee3034e4c9f076 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 1 Dec 2021 14:59:30 +0200 Subject: device property: Fix documentation for FWNODE_GRAPH_DEVICE_DISABLED FWNODE_GRAPH_DEVICE_DISABLED flag was meant for also returning endpoints connected to disabled devices, but it also may return endpoints that are not connected. Fix this in documentation. Also fwnode_graph_get_endpoint_by_id() was affeced by this. Also improve the language a little bit. Fixes: 0fcc2bdc8aff ("device property: Add fwnode_graph_get_endpoint_by_id()") Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 4 ++-- include/linux/property.h | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index b7b3a7b86006..e2860abf9889 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -1063,8 +1063,8 @@ EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_node); * has not been found, look for the closest endpoint ID greater than the * specified one and return the endpoint that corresponds to it, if present. * - * Do not return endpoints that belong to disabled devices, unless - * FWNODE_GRAPH_DEVICE_DISABLED is passed in @flags. + * Does not return endpoints that belong to disabled devices or endpoints that + * are unconnected, unless FWNODE_GRAPH_DEVICE_DISABLED is passed in @flags. * * The returned endpoint needs to be released by calling fwnode_handle_put() on * it when it is not needed any more. diff --git a/include/linux/property.h b/include/linux/property.h index 16f736c698a2..7a2df45ec3ae 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -414,7 +414,8 @@ static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) * one. * @FWNODE_GRAPH_DEVICE_DISABLED: That the device to which the remote * endpoint of the given endpoint belongs to, - * may be disabled. + * may be disabled, or that the endpoint is not + * connected. */ #define FWNODE_GRAPH_ENDPOINT_NEXT BIT(0) #define FWNODE_GRAPH_DEVICE_DISABLED BIT(1) -- cgit v1.2.3 From c87b8fc569667610b4891cad1e4a663e5a94d8f8 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 1 Dec 2021 14:59:33 +0200 Subject: device property: Implement fwnode_graph_get_endpoint_count() Add fwnode_graph_get_endpoint_count() function to provide generic implementation of of_graph_get_endpoint_count(). The former by default only counts endpoints to available devices which is consistent with the rest of the fwnode graph API. By providing FWNODE_GRAPH_DEVICE_DISABLED flag, also unconnected endpoints and endpoints to disabled devices are counted. Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 49 ++++++++++++++++++++++++++++++++++++++---------- include/linux/property.h | 2 ++ 2 files changed, 41 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index e2860abf9889..39435ba64dac 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -1049,6 +1049,18 @@ fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port_id, } EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_node); +static bool fwnode_graph_remote_available(struct fwnode_handle *ep) +{ + struct fwnode_handle *dev_node; + bool available; + + dev_node = fwnode_graph_get_remote_port_parent(ep); + available = fwnode_device_is_available(dev_node); + fwnode_handle_put(dev_node); + + return available; +} + /** * fwnode_graph_get_endpoint_by_id - get endpoint by port and endpoint numbers * @fwnode: parent fwnode_handle containing the graph @@ -1082,16 +1094,8 @@ fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, struct fwnode_endpoint fwnode_ep = { 0 }; int ret; - if (enabled_only) { - struct fwnode_handle *dev_node; - bool available; - - dev_node = fwnode_graph_get_remote_port_parent(ep); - available = fwnode_device_is_available(dev_node); - fwnode_handle_put(dev_node); - if (!available) - continue; - } + if (enabled_only && !fwnode_graph_remote_available(ep)) + continue; ret = fwnode_graph_parse_endpoint(ep, &fwnode_ep); if (ret < 0) @@ -1124,6 +1128,31 @@ fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, } EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_by_id); +/** + * fwnode_graph_get_endpoint_count - Count endpoints on a device node + * @fwnode: The node related to a device + * @flags: fwnode lookup flags + * Count endpoints in a device node. + * + * If FWNODE_GRAPH_DEVICE_DISABLED flag is specified, also unconnected endpoints + * and endpoints connected to disabled devices are counted. + */ +unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, + unsigned long flags) +{ + struct fwnode_handle *ep; + unsigned int count = 0; + + fwnode_graph_for_each_endpoint(fwnode, ep) { + if (flags & FWNODE_GRAPH_DEVICE_DISABLED || + fwnode_graph_remote_available(ep)) + count++; + } + + return count; +} +EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_count); + /** * fwnode_graph_parse_endpoint - parse common endpoint node properties * @fwnode: pointer to endpoint fwnode_handle diff --git a/include/linux/property.h b/include/linux/property.h index 7a2df45ec3ae..8c0104871252 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -423,6 +423,8 @@ static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) struct fwnode_handle * fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, u32 port, u32 endpoint, unsigned long flags); +unsigned int fwnode_graph_get_endpoint_count(struct fwnode_handle *fwnode, + unsigned long flags); #define fwnode_graph_for_each_endpoint(fwnode, child) \ for (child = NULL; \ -- cgit v1.2.3 From c49eea6ffec626c059ace085fce1bf501b05dbc7 Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Wed, 1 Dec 2021 15:01:15 +0200 Subject: device property: Drop fwnode_graph_get_remote_node() fwnode_graph_get_remote_node() is only used by the tegra-video driver. Convert it to use newer fwnode_graph_get_endpoint_by_id() and drop now-unused fwnode_graph_get_remote_node(). Signed-off-by: Sakari Ailus Reviewed-by: Andy Shevchenko Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 38 ---------------------------------- drivers/staging/media/tegra-video/vi.c | 12 +++++++---- include/linux/property.h | 3 --- 3 files changed, 8 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index 3ff44dd92e52..5379eae478b1 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -1011,44 +1011,6 @@ fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) } EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_endpoint); -/** - * fwnode_graph_get_remote_node - get remote parent node for given port/endpoint - * @fwnode: pointer to parent fwnode_handle containing graph port/endpoint - * @port_id: identifier of the parent port node - * @endpoint_id: identifier of the endpoint node - * - * Return: Remote fwnode handle associated with remote endpoint node linked - * to @node. Use fwnode_node_put() on it when done. - */ -struct fwnode_handle * -fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port_id, - u32 endpoint_id) -{ - struct fwnode_handle *endpoint; - - fwnode_graph_for_each_endpoint(fwnode, endpoint) { - struct fwnode_endpoint fwnode_ep; - struct fwnode_handle *remote; - int ret; - - ret = fwnode_graph_parse_endpoint(endpoint, &fwnode_ep); - if (ret < 0) - continue; - - if (fwnode_ep.port != port_id || fwnode_ep.id != endpoint_id) - continue; - - remote = fwnode_graph_get_remote_port_parent(endpoint); - if (!remote) - return NULL; - - return fwnode_device_is_available(remote) ? remote : NULL; - } - - return NULL; -} -EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_node); - static bool fwnode_graph_remote_available(struct fwnode_handle *ep) { struct fwnode_handle *dev_node; diff --git a/drivers/staging/media/tegra-video/vi.c b/drivers/staging/media/tegra-video/vi.c index 69d9787d5338..d1f43f465c22 100644 --- a/drivers/staging/media/tegra-video/vi.c +++ b/drivers/staging/media/tegra-video/vi.c @@ -1845,7 +1845,6 @@ static int tegra_vi_graph_init(struct tegra_vi *vi) struct tegra_vi_channel *chan; struct fwnode_handle *fwnode = dev_fwnode(vi->dev); int ret; - struct fwnode_handle *remote = NULL; /* * Walk the links to parse the full graph. Each channel will have @@ -1857,11 +1856,16 @@ static int tegra_vi_graph_init(struct tegra_vi *vi) * next channels. */ list_for_each_entry(chan, &vi->vi_chans, list) { - remote = fwnode_graph_get_remote_node(fwnode, chan->portnos[0], - 0); - if (!remote) + struct fwnode_handle *ep, *remote; + + ep = fwnode_graph_get_endpoint_by_id(fwnode, + chan->portnos[0], 0, 0); + if (!ep) continue; + remote = fwnode_graph_get_remote_port_parent(ep); + fwnode_handle_put(ep); + ret = tegra_vi_graph_parse_one(chan, remote); fwnode_handle_put(remote); if (ret < 0 || list_empty(&chan->notifier.asd_list)) diff --git a/include/linux/property.h b/include/linux/property.h index 8c0104871252..8355f99ebd47 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -397,9 +397,6 @@ struct fwnode_handle *fwnode_graph_get_remote_port( const struct fwnode_handle *fwnode); struct fwnode_handle *fwnode_graph_get_remote_endpoint( const struct fwnode_handle *fwnode); -struct fwnode_handle * -fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, - u32 endpoint); static inline bool fwnode_graph_is_endpoint(struct fwnode_handle *fwnode) { -- cgit v1.2.3 From bd0b536dc2e1e9828a85b1e3470ee7bafc3b36f6 Mon Sep 17 00:00:00 2001 From: Brett Creeley Date: Mon, 29 Nov 2021 16:15:59 -0800 Subject: virtchnl: Add support for new VLAN capabilities Currently VIRTCHNL only allows for VLAN filtering and offloads to happen on a single 802.1Q VLAN. Add support to filter and offload on inner, outer, and/or inner + outer VLANs. This is done by introducing the new capability VIRTCHNL_VF_OFFLOAD_VLAN_V2. The flow to negotiate this new capability is shown below. 1. VF - sets the VIRTCHNL_VF_OFFLOAD_VLAN_V2 bit in the virtchnl_vf_resource.vf_caps_flags during the VIRTCHNL_OP_GET_VF_RESOURCES request message. The VF should also set the VIRTCHNL_VF_OFFLOAD_VLAN bit in case the PF driver doesn't support the new capability. 2. PF - sets the VLAN capability bit it supports in the VIRTCHNL_OP_GET_VF_RESOURCES response message. This will either be VIRTCHNL_VF_OFFLOAD_VLAN_V2, VIRTCHNL_VF_OFFLOAD_VLAN, or none. 3. VF - If the VIRTCHNL_VF_OFFLOAD_VLAN_V2 capability was ACK'd by the PF, then the VF needs to request the VLAN capabilities of the PF/Device by issuing a VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS request. If the VIRTCHNL_VF_OFFLOAD_VLAN capability was ACK'd then the VF knows only single 802.1Q VLAN filtering/offloads are supported. If no VLAN capability is ACK'd then the PF/Device doesn't support hardware VLAN filtering/offloads for this VF. 4. PF - Populates the virtchnl_vlan_caps structure based on what it allows/supports for that VF and sends that response via VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS. After VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS is successfully negotiated the VF driver needs to interpret the capabilities supported by the underlying PF/Device. The VF will be allowed to filter/offload the inner 802.1Q, outer (various ethertype), inner 802.1Q + outer (various ethertypes), or none based on which fields are set. The VF will also need to interpret where the VLAN tag should be inserted and/or stripped based on the negotiated capabilities. Signed-off-by: Brett Creeley Tested-by: Konrad Jankowski Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 377 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 377 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b30a1bc74fc7..2ce27e8e4f19 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -141,6 +141,13 @@ enum virtchnl_ops { VIRTCHNL_OP_DEL_RSS_CFG = 46, VIRTCHNL_OP_ADD_FDIR_FILTER = 47, VIRTCHNL_OP_DEL_FDIR_FILTER = 48, + VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS = 51, + VIRTCHNL_OP_ADD_VLAN_V2 = 52, + VIRTCHNL_OP_DEL_VLAN_V2 = 53, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 = 54, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55, + VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56, + VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57, VIRTCHNL_OP_MAX, }; @@ -246,6 +253,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 BIT(18) @@ -475,6 +483,351 @@ struct virtchnl_vlan_filter_list { VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); +/* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related + * structures and opcodes. + * + * VIRTCHNL_VLAN_UNSUPPORTED - This field is not supported and if a VF driver + * populates it the PF should return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED. + * + * VIRTCHNL_VLAN_ETHERTYPE_8100 - This field supports 0x8100 ethertype. + * VIRTCHNL_VLAN_ETHERTYPE_88A8 - This field supports 0x88A8 ethertype. + * VIRTCHNL_VLAN_ETHERTYPE_9100 - This field supports 0x9100 ethertype. + * + * VIRTCHNL_VLAN_ETHERTYPE_AND - Used when multiple ethertypes can be supported + * by the PF concurrently. For example, if the PF can support + * VIRTCHNL_VLAN_ETHERTYPE_8100 AND VIRTCHNL_VLAN_ETHERTYPE_88A8 filters it + * would OR the following bits: + * + * VIRTHCNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * The VF would interpret this as VLAN filtering can be supported on both 0x8100 + * and 0x88A8 VLAN ethertypes. + * + * VIRTCHNL_ETHERTYPE_XOR - Used when only a single ethertype can be supported + * by the PF concurrently. For example if the PF can support + * VIRTCHNL_VLAN_ETHERTYPE_8100 XOR VIRTCHNL_VLAN_ETHERTYPE_88A8 stripping + * offload it would OR the following bits: + * + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * The VF would interpret this as VLAN stripping can be supported on either + * 0x8100 or 0x88a8 VLAN ethertypes. So when requesting VLAN stripping via + * VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 the specified ethertype will override + * the previously set value. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1 - Used to tell the VF to insert and/or + * strip the VLAN tag using the L2TAG1 field of the Tx/Rx descriptors. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 - Used to tell the VF to insert hardware + * offloaded VLAN tags using the L2TAG2 field of the Tx descriptor. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 - Used to tell the VF to strip hardware + * offloaded VLAN tags using the L2TAG2_2 field of the Rx descriptor. + * + * VIRTCHNL_VLAN_PRIO - This field supports VLAN priority bits. This is used for + * VLAN filtering if the underlying PF supports it. + * + * VIRTCHNL_VLAN_TOGGLE_ALLOWED - This field is used to say whether a + * certain VLAN capability can be toggled. For example if the underlying PF/CP + * allows the VF to toggle VLAN filtering, stripping, and/or insertion it should + * set this bit along with the supported ethertypes. + */ +enum virtchnl_vlan_support { + VIRTCHNL_VLAN_UNSUPPORTED = 0, + VIRTCHNL_VLAN_ETHERTYPE_8100 = BIT(0), + VIRTCHNL_VLAN_ETHERTYPE_88A8 = BIT(1), + VIRTCHNL_VLAN_ETHERTYPE_9100 = BIT(2), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1 = BIT(8), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 = BIT(9), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 = BIT(10), + VIRTCHNL_VLAN_PRIO = BIT(24), + VIRTCHNL_VLAN_FILTER_MASK = BIT(28), + VIRTCHNL_VLAN_ETHERTYPE_AND = BIT(29), + VIRTCHNL_VLAN_ETHERTYPE_XOR = BIT(30), + VIRTCHNL_VLAN_TOGGLE = BIT(31), +}; + +/* This structure is used as part of the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS + * for filtering, insertion, and stripping capabilities. + * + * If only outer capabilities are supported (for filtering, insertion, and/or + * stripping) then this refers to the outer most or single VLAN from the VF's + * perspective. + * + * If only inner capabilities are supported (for filtering, insertion, and/or + * stripping) then this refers to the outer most or single VLAN from the VF's + * perspective. Functionally this is the same as if only outer capabilities are + * supported. The VF driver is just forced to use the inner fields when + * adding/deleting filters and enabling/disabling offloads (if supported). + * + * If both outer and inner capabilities are supported (for filtering, insertion, + * and/or stripping) then outer refers to the outer most or single VLAN and + * inner refers to the second VLAN, if it exists, in the packet. + * + * There is no support for tunneled VLAN offloads, so outer or inner are never + * referring to a tunneled packet from the VF's perspective. + */ +struct virtchnl_vlan_supported_caps { + u32 outer; + u32 inner; +}; + +/* The PF populates these fields based on the supported VLAN filtering. If a + * field is VIRTCHNL_VLAN_UNSUPPORTED then it's not supported and the PF will + * reject any VIRTCHNL_OP_ADD_VLAN_V2 or VIRTCHNL_OP_DEL_VLAN_V2 messages using + * the unsupported fields. + * + * Also, a VF is only allowed to toggle its VLAN filtering setting if the + * VIRTCHNL_VLAN_TOGGLE bit is set. + * + * The ethertype(s) specified in the ethertype_init field are the ethertypes + * enabled for VLAN filtering. VLAN filtering in this case refers to the outer + * most VLAN from the VF's perspective. If both inner and outer filtering are + * allowed then ethertype_init only refers to the outer most VLAN as only + * VLAN ethertype supported for inner VLAN filtering is + * VIRTCHNL_VLAN_ETHERTYPE_8100. By default, inner VLAN filtering is disabled + * when both inner and outer filtering are allowed. + * + * The max_filters field tells the VF how many VLAN filters it's allowed to have + * at any one time. If it exceeds this amount and tries to add another filter, + * then the request will be rejected by the PF. To prevent failures, the VF + * should keep track of how many VLAN filters it has added and not attempt to + * add more than max_filters. + */ +struct virtchnl_vlan_filtering_caps { + struct virtchnl_vlan_supported_caps filtering_support; + u32 ethertype_init; + u16 max_filters; + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vlan_filtering_caps); + +/* This enum is used for the virtchnl_vlan_offload_caps structure to specify + * if the PF supports a different ethertype for stripping and insertion. + * + * VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION - The ethertype(s) specified + * for stripping affect the ethertype(s) specified for insertion and visa versa + * as well. If the VF tries to configure VLAN stripping via + * VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 with VIRTCHNL_VLAN_ETHERTYPE_8100 then + * that will be the ethertype for both stripping and insertion. + * + * VIRTCHNL_ETHERTYPE_MATCH_NOT_REQUIRED - The ethertype(s) specified for + * stripping do not affect the ethertype(s) specified for insertion and visa + * versa. + */ +enum virtchnl_vlan_ethertype_match { + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION = 0, + VIRTCHNL_ETHERTYPE_MATCH_NOT_REQUIRED = 1, +}; + +/* The PF populates these fields based on the supported VLAN offloads. If a + * field is VIRTCHNL_VLAN_UNSUPPORTED then it's not supported and the PF will + * reject any VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 or + * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 messages using the unsupported fields. + * + * Also, a VF is only allowed to toggle its VLAN offload setting if the + * VIRTCHNL_VLAN_TOGGLE_ALLOWED bit is set. + * + * The VF driver needs to be aware of how the tags are stripped by hardware and + * inserted by the VF driver based on the level of offload support. The PF will + * populate these fields based on where the VLAN tags are expected to be + * offloaded via the VIRTHCNL_VLAN_TAG_LOCATION_* bits. The VF will need to + * interpret these fields. See the definition of the + * VIRTCHNL_VLAN_TAG_LOCATION_* bits above the virtchnl_vlan_support + * enumeration. + */ +struct virtchnl_vlan_offload_caps { + struct virtchnl_vlan_supported_caps stripping_support; + struct virtchnl_vlan_supported_caps insertion_support; + u32 ethertype_init; + u8 ethertype_match; + u8 pad[3]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_vlan_offload_caps); + +/* VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS + * VF sends this message to determine its VLAN capabilities. + * + * PF will mark which capabilities it supports based on hardware support and + * current configuration. For example, if a port VLAN is configured the PF will + * not allow outer VLAN filtering, stripping, or insertion to be configured so + * it will block these features from the VF. + * + * The VF will need to cross reference its capabilities with the PFs + * capabilities in the response message from the PF to determine the VLAN + * support. + */ +struct virtchnl_vlan_caps { + struct virtchnl_vlan_filtering_caps filtering; + struct virtchnl_vlan_offload_caps offloads; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_caps); + +struct virtchnl_vlan { + u16 tci; /* tci[15:13] = PCP and tci[11:0] = VID */ + u16 tci_mask; /* only valid if VIRTCHNL_VLAN_FILTER_MASK set in + * filtering caps + */ + u16 tpid; /* 0x8100, 0x88a8, etc. and only type(s) set in + * filtering caps. Note that tpid here does not refer to + * VIRTCHNL_VLAN_ETHERTYPE_*, but it refers to the + * actual 2-byte VLAN TPID + */ + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan); + +struct virtchnl_vlan_filter { + struct virtchnl_vlan inner; + struct virtchnl_vlan outer; + u8 pad[16]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(32, virtchnl_vlan_filter); + +/* VIRTCHNL_OP_ADD_VLAN_V2 + * VIRTCHNL_OP_DEL_VLAN_V2 + * + * VF sends these messages to add/del one or more VLAN tag filters for Rx + * traffic. + * + * The PF attempts to add the filters and returns status. + * + * The VF should only ever attempt to add/del virtchnl_vlan_filter(s) using the + * supported fields negotiated via VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS. + */ +struct virtchnl_vlan_filter_list_v2 { + u16 vport_id; + u16 num_elements; + u8 pad[4]; + struct virtchnl_vlan_filter filters[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2); + +/* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 + * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 + * VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 + * VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 + * + * VF sends this message to enable or disable VLAN stripping or insertion. It + * also needs to specify an ethertype. The VF knows which VLAN ethertypes are + * allowed and whether or not it's allowed to enable/disable the specific + * offload via the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS message. The VF needs to + * parse the virtchnl_vlan_caps.offloads fields to determine which offload + * messages are allowed. + * + * For example, if the PF populates the virtchnl_vlan_caps.offloads in the + * following manner the VF will be allowed to enable and/or disable 0x8100 inner + * VLAN insertion and/or stripping via the opcodes listed above. Inner in this + * case means the outer most or single VLAN from the VF's perspective. This is + * because no outer offloads are supported. See the comments above the + * virtchnl_vlan_supported_caps structure for more details. + * + * virtchnl_vlan_caps.offloads.stripping_support.inner = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * virtchnl_vlan_caps.offloads.insertion_support.inner = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * In order to enable inner (again note that in this case inner is the outer + * most or single VLAN from the VF's perspective) VLAN stripping for 0x8100 + * VLANs, the VF would populate the virtchnl_vlan_setting structure in the + * following manner and send the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 message. + * + * virtchnl_vlan_setting.inner_ethertype_setting = + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + * + * The reason that VLAN TPID(s) are not being used for the + * outer_ethertype_setting and inner_ethertype_setting fields is because it's + * possible a device could support VLAN insertion and/or stripping offload on + * multiple ethertypes concurrently, so this method allows a VF to request + * multiple ethertypes in one message using the virtchnl_vlan_support + * enumeration. + * + * For example, if the PF populates the virtchnl_vlan_caps.offloads in the + * following manner the VF will be allowed to enable 0x8100 and 0x88a8 outer + * VLAN insertion and stripping simultaneously. The + * virtchnl_vlan_caps.offloads.ethertype_match field will also have to be + * populated based on what the PF can support. + * + * virtchnl_vlan_caps.offloads.stripping_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * virtchnl_vlan_caps.offloads.insertion_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * In order to enable outer VLAN stripping for 0x8100 and 0x88a8 VLANs, the VF + * would populate the virthcnl_vlan_offload_structure in the following manner + * and send the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 message. + * + * virtchnl_vlan_setting.outer_ethertype_setting = + * VIRTHCNL_VLAN_ETHERTYPE_8100 | + * VIRTHCNL_VLAN_ETHERTYPE_88A8; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + * + * There is also the case where a PF and the underlying hardware can support + * VLAN offloads on multiple ethertypes, but not concurrently. For example, if + * the PF populates the virtchnl_vlan_caps.offloads in the following manner the + * VF will be allowed to enable and/or disable 0x8100 XOR 0x88a8 outer VLAN + * offloads. The ethertypes must match for stripping and insertion. + * + * virtchnl_vlan_caps.offloads.stripping_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * virtchnl_vlan_caps.offloads.insertion_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * virtchnl_vlan_caps.offloads.ethertype_match = + * VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + * + * In order to enable outer VLAN stripping for 0x88a8 VLANs, the VF would + * populate the virtchnl_vlan_setting structure in the following manner and send + * the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2. Also, this will change the + * ethertype for VLAN insertion if it's enabled. So, for completeness, a + * VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 with the same ethertype should be sent. + * + * virtchnl_vlan_setting.outer_ethertype_setting = VIRTHCNL_VLAN_ETHERTYPE_88A8; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + */ +struct virtchnl_vlan_setting { + u32 outer_ethertype_setting; + u32 inner_ethertype_setting; + u16 vport_id; + u8 pad[6]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vlan_setting); + /* VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE * VF sends VSI id and flags. * PF returns status code in retval. @@ -1156,6 +1509,30 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_DEL_FDIR_FILTER: valid_len = sizeof(struct virtchnl_fdir_del); break; + case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: + break; + case VIRTCHNL_OP_ADD_VLAN_V2: + case VIRTCHNL_OP_DEL_VLAN_V2: + valid_len = sizeof(struct virtchnl_vlan_filter_list_v2); + if (msglen >= valid_len) { + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + + valid_len += (vfl->num_elements - 1) * + sizeof(struct virtchnl_vlan_filter); + + if (vfl->num_elements == 0) { + err_msg_format = true; + break; + } + } + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2: + case VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2: + case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: + valid_len = sizeof(struct virtchnl_vlan_setting); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: -- cgit v1.2.3 From 877fee2a0c65a3b0b6ac0e90d7d7718b5a0341d3 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Fri, 17 Dec 2021 15:15:15 +0100 Subject: PCI: Convert pci_dev_present() stub to static inline Change the pci_dev_present() stub which is used when CONFIG_PCI is not set from a #define to a static inline stub. Thix should fix clang -Werror builds failing due to errors like this: drivers/platform/x86/thinkpad_acpi.c:4475:35: error: unused variable 'fwbug_cards_ids' [-Werror,-Wunused-const-variable] Where fwbug_cards_ids is an array of pci_device_id passed to pci_dev_present() during a quirk check. Link: https://lore.kernel.org/r/20211217141515.379586-1-hdegoede@redhat.com Reported-by: kernel test robot Signed-off-by: Hans de Goede Signed-off-by: Bjorn Helgaas Reviewed-by: Andy Shevchenko Cc: platform-driver-x86@vger.kernel.org --- include/linux/pci.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 18a75c8e615c..7d825637d7ca 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1775,7 +1775,10 @@ static inline struct pci_dev *pci_get_class(unsigned int class, struct pci_dev *from) { return NULL; } -#define pci_dev_present(ids) (0) + +static inline int pci_dev_present(const struct pci_device_id *ids) +{ return 0; } + #define no_pci_devices() (1) #define pci_dev_put(dev) do { } while (0) -- cgit v1.2.3 From 3849595866166b23bf6a0cb9ff87e06423167f67 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 14 Dec 2021 19:24:34 +0200 Subject: net/sched: flow_dissector: Fix matching on zone id for invalid conns If ct rejects a flow, it removes the conntrack info from the skb. act_ct sets the post_ct variable so the dissector will see this case as an +tracked +invalid state, but the zone id is lost with the conntrack info. To restore the zone id on such cases, set the last executed zone, via the tc control block, when passing ct, and read it back in the dissector if there is no ct info on the skb (invalid connection). Fixes: 7baf2429a1a9 ("net/sched: cls_flower add CT_FLAGS_INVALID flag support") Signed-off-by: Paul Blakey Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- include/net/pkt_sched.h | 1 + net/core/flow_dissector.c | 3 ++- net/sched/act_ct.c | 1 + net/sched/cls_flower.c | 3 ++- 5 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c8cb7e697d47..2ecf8cfd2223 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1380,7 +1380,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, size_t mapsize, - bool post_ct); + bool post_ct, u16 zone); void skb_flow_dissect_tunnel_info(const struct sk_buff *skb, struct flow_dissector *flow_dissector, diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 05f18e81f3e8..9e71691c491b 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -198,6 +198,7 @@ struct tc_skb_cb { u16 mru; bool post_ct; + u16 zone; /* Only valid if post_ct = true */ }; static inline struct tc_skb_cb *tc_skb_cb(const struct sk_buff *skb) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3255f57f5131..1b094c481f1d 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -238,7 +238,7 @@ void skb_flow_dissect_ct(const struct sk_buff *skb, struct flow_dissector *flow_dissector, void *target_container, u16 *ctinfo_map, - size_t mapsize, bool post_ct) + size_t mapsize, bool post_ct, u16 zone) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) struct flow_dissector_key_ct *key; @@ -260,6 +260,7 @@ skb_flow_dissect_ct(const struct sk_buff *skb, if (!ct) { key->ct_state = TCA_FLOWER_KEY_CT_FLAGS_TRACKED | TCA_FLOWER_KEY_CT_FLAGS_INVALID; + key->ct_zone = zone; return; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 98e248b9c0b1..ab3591408419 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1049,6 +1049,7 @@ out_push: skb_push_rcsum(skb, nh_ofs); tc_skb_cb(skb)->post_ct = true; + tc_skb_cb(skb)->zone = p->zone; out_clear: if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9782b93db1b3..ef54ed395874 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -311,6 +311,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, { struct cls_fl_head *head = rcu_dereference_bh(tp->root); bool post_ct = tc_skb_cb(skb)->post_ct; + u16 zone = tc_skb_cb(skb)->zone; struct fl_flow_key skb_key; struct fl_flow_mask *mask; struct cls_fl_filter *f; @@ -328,7 +329,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, skb_flow_dissect_ct(skb, &mask->dissector, &skb_key, fl_ct_info_to_flower_map, ARRAY_SIZE(fl_ct_info_to_flower_map), - post_ct); + post_ct, zone); skb_flow_dissect_hash(skb, &mask->dissector, &skb_key); skb_flow_dissect(skb, &mask->dissector, &skb_key, FLOW_DISSECTOR_F_STOP_BEFORE_ENCAP); -- cgit v1.2.3 From 635d448a1cce4b4ebee52b351052c70434fa90ea Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Tue, 14 Dec 2021 19:24:35 +0200 Subject: net: openvswitch: Fix matching zone id for invalid conns arriving from tc Zone id is not restored if we passed ct and ct rejected the connection, as there is no ct info on the skb. Save the zone from tc skb cb to tc skb extension and pass it on to ovs, use that info to restore the zone id for invalid connections. Fixes: d29334c15d33 ("net/sched: act_api: fix miss set post_ct for ovs after do conntrack in act_ct") Signed-off-by: Paul Blakey Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 + net/openvswitch/flow.c | 8 +++++++- net/sched/cls_api.c | 1 + 3 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2ecf8cfd2223..4507d77d6941 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -286,6 +286,7 @@ struct nf_bridge_info { struct tc_skb_ext { __u32 chain; __u16 mru; + __u16 zone; bool post_ct; }; #endif diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 9713035b89e3..6d262d9aa10e 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -34,6 +34,7 @@ #include #include #include +#include #include "conntrack.h" #include "datapath.h" @@ -860,6 +861,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, #endif bool post_ct = false; int res, err; + u16 zone = 0; /* Extract metadata from packet. */ if (tun_info) { @@ -898,6 +900,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->recirc_id = tc_ext ? tc_ext->chain : 0; OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; post_ct = tc_ext ? tc_ext->post_ct : false; + zone = post_ct ? tc_ext->zone : 0; } else { key->recirc_id = 0; } @@ -906,8 +909,11 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, #endif err = key_extract(skb, key); - if (!err) + if (!err) { ovs_ct_fill_key(skb, key, post_ct); /* Must be after key_extract(). */ + if (post_ct && !skb_get_nfct(skb)) + key->ct_zone = zone; + } return err; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ff8a9383bf1c..35c74bdde848 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1625,6 +1625,7 @@ int tcf_classify(struct sk_buff *skb, ext->chain = last_executed_chain; ext->mru = cb->mru; ext->post_ct = cb->post_ct; + ext->zone = cb->zone; } return ret; -- cgit v1.2.3 From 6e478521df535b9d5ef5eb84d4352f235bbbef99 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 30 Jul 2021 09:56:05 -0400 Subject: iomap,xfs: Convert ->discard_page to ->discard_folio XFS has the only implementation of ->discard_page today, so convert it to use folios in the same patch as converting the API. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 4 ++-- fs/xfs/xfs_aops.c | 24 ++++++++++++------------ include/linux/iomap.h | 2 +- 3 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index b78a456e696f..b403b83eedaf 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1360,8 +1360,8 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, * won't be affected by I/O completion and we must unlock it * now. */ - if (wpc->ops->discard_page) - wpc->ops->discard_page(page, file_offset); + if (wpc->ops->discard_folio) + wpc->ops->discard_folio(folio, file_offset); if (!count) { ClearPageUptodate(page); unlock_page(page); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index c8c15c3c3147..4098a9875c5b 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -437,37 +437,37 @@ xfs_prepare_ioend( * see a ENOSPC in writeback). */ static void -xfs_discard_page( - struct page *page, - loff_t fileoff) +xfs_discard_folio( + struct folio *folio, + loff_t pos) { - struct inode *inode = page->mapping->host; + struct inode *inode = folio->mapping->host; struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; - unsigned int pageoff = offset_in_page(fileoff); - xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, fileoff); - xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff); + size_t offset = offset_in_folio(folio, pos); + xfs_fileoff_t start_fsb = XFS_B_TO_FSBT(mp, pos); + xfs_fileoff_t pageoff_fsb = XFS_B_TO_FSBT(mp, offset); int error; if (xfs_is_shutdown(mp)) goto out_invalidate; xfs_alert_ratelimited(mp, - "page discard on page "PTR_FMT", inode 0x%llx, offset %llu.", - page, ip->i_ino, fileoff); + "page discard on page "PTR_FMT", inode 0x%llx, pos %llu.", + folio, ip->i_ino, pos); error = xfs_bmap_punch_delalloc_range(ip, start_fsb, - i_blocks_per_page(inode, page) - pageoff_fsb); + i_blocks_per_folio(inode, folio) - pageoff_fsb); if (error && !xfs_is_shutdown(mp)) xfs_alert(mp, "page discard unable to remove delalloc mapping."); out_invalidate: - iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff); + iomap_invalidate_folio(folio, offset, folio_size(folio) - offset); } static const struct iomap_writeback_ops xfs_writeback_ops = { .map_blocks = xfs_map_blocks, .prepare_ioend = xfs_prepare_ioend, - .discard_page = xfs_discard_page, + .discard_folio = xfs_discard_folio, }; STATIC int diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 29491fb9c5ba..5ef5088dbbd8 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -285,7 +285,7 @@ struct iomap_writeback_ops { * Optional, allows the file system to discard state on a page where * we failed to submit any I/O. */ - void (*discard_page)(struct page *page, loff_t fileoff); + void (*discard_folio)(struct folio *folio, loff_t pos); }; struct iomap_writepage_ctx { -- cgit v1.2.3 From e17f7a0bc4daa44a4809f5f2f947aa2aa74d1369 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:05 +0100 Subject: uio: remove copy_from_iter_flushcache() and copy_mc_to_iter() These two wrappers are never used. Signed-off-by: Christoph Hellwig Link: https://lore.kernel.org/r/20211215084508.435401-2-hch@lst.de Signed-off-by: Dan Williams --- drivers/nvdimm/pmem.c | 4 +--- include/linux/uio.h | 20 +------------------- 2 files changed, 2 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 4190c8c46ca8..d225bcfa67cf 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -302,9 +302,7 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev, } /* - * Use the 'no check' versions of copy_from_iter_flushcache() and - * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds - * checking, both file offset and device offset, is handled by + * Bounds checking, both file offset and device offset, is handled by * dax_iomap_actor() */ static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, diff --git a/include/linux/uio.h b/include/linux/uio.h index 6350354f97e9..494d552c1d66 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -196,7 +196,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE /* * Note, users like pmem that depend on the stricter semantics of - * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for + * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the * destination is flushed from the cache on return. */ @@ -211,24 +211,6 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i); #define _copy_mc_to_iter _copy_to_iter #endif -static __always_inline __must_check -size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, false))) - return 0; - else - return _copy_from_iter_flushcache(addr, bytes, i); -} - -static __always_inline __must_check -size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (unlikely(!check_copy_size(addr, bytes, true))) - return 0; - else - return _copy_mc_to_iter(addr, bytes, i); -} - size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -- cgit v1.2.3 From fd1d00ec92002d8fe28ca981a72395eaa7ae3d11 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:06 +0100 Subject: dax: simplify dax_synchronous and set_dax_synchronous Remove the pointless wrappers. Signed-off-by: Christoph Hellwig Reviewed-by: Pankaj Gupta Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211215084508.435401-3-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/super.c | 8 ++++---- include/linux/dax.h | 12 ++---------- 2 files changed, 6 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e7152a6c4cc4..e18155f43a63 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -208,17 +208,17 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(dax_write_cache_enabled); -bool __dax_synchronous(struct dax_device *dax_dev) +bool dax_synchronous(struct dax_device *dax_dev) { return test_bit(DAXDEV_SYNC, &dax_dev->flags); } -EXPORT_SYMBOL_GPL(__dax_synchronous); +EXPORT_SYMBOL_GPL(dax_synchronous); -void __set_dax_synchronous(struct dax_device *dax_dev) +void set_dax_synchronous(struct dax_device *dax_dev) { set_bit(DAXDEV_SYNC, &dax_dev->flags); } -EXPORT_SYMBOL_GPL(__set_dax_synchronous); +EXPORT_SYMBOL_GPL(set_dax_synchronous); bool dax_alive(struct dax_device *dax_dev) { diff --git a/include/linux/dax.h b/include/linux/dax.h index 87ae4c9b1d65..3bd1fdb5d5f4 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -48,16 +48,8 @@ void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); bool dax_write_cache_enabled(struct dax_device *dax_dev); -bool __dax_synchronous(struct dax_device *dax_dev); -static inline bool dax_synchronous(struct dax_device *dax_dev) -{ - return __dax_synchronous(dax_dev); -} -void __set_dax_synchronous(struct dax_device *dax_dev); -static inline void set_dax_synchronous(struct dax_device *dax_dev) -{ - __set_dax_synchronous(dax_dev); -} +bool dax_synchronous(struct dax_device *dax_dev); +void set_dax_synchronous(struct dax_device *dax_dev); /* * Check if given mapping is supported by the file / underlying device. */ -- cgit v1.2.3 From 30c6828a17a572aeb9e3a3bacce05fdcf1106541 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:07 +0100 Subject: dax: remove the DAXDEV_F_SYNC flag Remove the DAXDEV_F_SYNC flag and thus the flags argument to alloc_dax and just let the drivers call set_dax_synchronous directly. Signed-off-by: Christoph Hellwig Reviewed-by: Pankaj Gupta Reviewed-by: Dan Williams Link: https://lore.kernel.org/r/20211215084508.435401-4-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/bus.c | 3 ++- drivers/dax/super.c | 6 +----- drivers/md/dm.c | 2 +- drivers/nvdimm/pmem.c | 7 +++---- drivers/s390/block/dcssblk.c | 4 ++-- fs/fuse/virtio_fs.c | 2 +- include/linux/dax.h | 8 ++------ 7 files changed, 12 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 6683d42c32c5..da2a14d096d2 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1324,11 +1324,12 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) * No dax_operations since there is no access to this device outside of * mmap of the resulting character device. */ - dax_dev = alloc_dax(dev_dax, NULL, DAXDEV_F_SYNC); + dax_dev = alloc_dax(dev_dax, NULL); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto err_alloc_dax; } + set_dax_synchronous(dax_dev); /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e18155f43a63..e81d5ee57390 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -345,8 +345,7 @@ static struct dax_device *dax_dev_get(dev_t devt) return dax_dev; } -struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, - unsigned long flags) +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops) { struct dax_device *dax_dev; dev_t devt; @@ -366,9 +365,6 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, dax_dev->ops = ops; dax_dev->private = private; - if (flags & DAXDEV_F_SYNC) - set_dax_synchronous(dax_dev); - return dax_dev; err_dev: diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4e997c02bb0a..f4b972af1092 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1765,7 +1765,7 @@ static struct mapped_device *alloc_dev(int minor) sprintf(md->disk->disk_name, "dm-%d", minor); if (IS_ENABLED(CONFIG_FS_DAX)) { - md->dax_dev = alloc_dax(md, &dm_dax_ops, 0); + md->dax_dev = alloc_dax(md, &dm_dax_ops); if (IS_ERR(md->dax_dev)) { md->dax_dev = NULL; goto bad; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index d225bcfa67cf..18b1d9c55831 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -400,7 +400,6 @@ static int pmem_attach_disk(struct device *dev, struct gendisk *disk; void *addr; int rc; - unsigned long flags = 0UL; pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL); if (!pmem) @@ -493,13 +492,13 @@ static int pmem_attach_disk(struct device *dev, nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range); disk->bb = &pmem->bb; - if (is_nvdimm_sync(nd_region)) - flags = DAXDEV_F_SYNC; - dax_dev = alloc_dax(pmem, &pmem_dax_ops, flags); + dax_dev = alloc_dax(pmem, &pmem_dax_ops); if (IS_ERR(dax_dev)) { rc = PTR_ERR(dax_dev); goto out; } + if (is_nvdimm_sync(nd_region)) + set_dax_synchronous(dax_dev); rc = dax_add_host(dax_dev, disk); if (rc) goto out_cleanup_dax; diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index e65e83764d1c..10823debc09b 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -686,13 +686,13 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char if (rc) goto put_dev; - dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops, - DAXDEV_F_SYNC); + dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops); if (IS_ERR(dev_info->dax_dev)) { rc = PTR_ERR(dev_info->dax_dev); dev_info->dax_dev = NULL; goto put_dev; } + set_dax_synchronous(dev_info->dax_dev); rc = dax_add_host(dev_info->dax_dev, dev_info->gd); if (rc) goto out_dax; diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 242cc1c0d7ed..5c03a0364a9b 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -850,7 +850,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); - fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops, 0); + fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops); if (IS_ERR(fs->dax_dev)) return PTR_ERR(fs->dax_dev); diff --git a/include/linux/dax.h b/include/linux/dax.h index 3bd1fdb5d5f4..c04f46478e3b 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -6,9 +6,6 @@ #include #include -/* Flag for synchronous flush */ -#define DAXDEV_F_SYNC (1UL << 0) - typedef unsigned long dax_entry_t; struct dax_device; @@ -42,8 +39,7 @@ struct dax_operations { }; #if IS_ENABLED(CONFIG_DAX) -struct dax_device *alloc_dax(void *private, const struct dax_operations *ops, - unsigned long flags); +struct dax_device *alloc_dax(void *private, const struct dax_operations *ops); void put_dax(struct dax_device *dax_dev); void kill_dax(struct dax_device *dax_dev); void dax_write_cache(struct dax_device *dax_dev, bool wc); @@ -64,7 +60,7 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, } #else static inline struct dax_device *alloc_dax(void *private, - const struct dax_operations *ops, unsigned long flags) + const struct dax_operations *ops) { /* * Callers should check IS_ENABLED(CONFIG_DAX) to know if this -- cgit v1.2.3 From 7ac5360cd4d02cc7e0eaf10867f599e041822f12 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 15 Dec 2021 09:45:08 +0100 Subject: dax: remove the copy_from_iter and copy_to_iter methods These methods indirect the actual DAX read/write path. In the end pmem uses magic flush and mc safe variants and fuse and dcssblk use plain ones while device mapper picks redirects to the underlying device. Add set_dax_nocache() and set_dax_nomc() APIs to control which copy routines are used to remove indirect call from the read/write fast path as well as a lot of boilerplate code. Signed-off-by: Christoph Hellwig Reviewed-by: Vivek Goyal [virtiofs] Link: https://lore.kernel.org/r/20211215084508.435401-5-hch@lst.de Signed-off-by: Dan Williams --- drivers/dax/bus.c | 2 ++ drivers/dax/super.c | 36 ++++++++++++++++--- drivers/md/dm-linear.c | 20 ----------- drivers/md/dm-log-writes.c | 80 ------------------------------------------- drivers/md/dm-stripe.c | 20 ----------- drivers/md/dm.c | 52 ++-------------------------- drivers/nvdimm/pmem.c | 20 ++--------- drivers/s390/block/dcssblk.c | 14 -------- fs/dax.c | 5 --- fs/fuse/virtio_fs.c | 16 --------- include/linux/dax.h | 9 ++--- include/linux/device-mapper.h | 4 --- 12 files changed, 41 insertions(+), 237 deletions(-) (limited to 'include/linux') diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index da2a14d096d2..ee4568ef757c 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -1330,6 +1330,8 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data) goto err_alloc_dax; } set_dax_synchronous(dax_dev); + set_dax_nocache(dax_dev); + set_dax_nomc(dax_dev); /* a device_dax instance is dead while the driver is not attached */ kill_dax(dax_dev); diff --git a/drivers/dax/super.c b/drivers/dax/super.c index e81d5ee57390..e3029389d809 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -105,6 +105,10 @@ enum dax_device_flags { DAXDEV_WRITE_CACHE, /* flag to check if device supports synchronous flush */ DAXDEV_SYNC, + /* do not leave the caches dirty after writes */ + DAXDEV_NOCACHE, + /* handle CPU fetch exceptions during reads */ + DAXDEV_NOMC, }; /** @@ -146,9 +150,15 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, if (!dax_alive(dax_dev)) return 0; - return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i); + /* + * The userspace address for the memory copy has already been validated + * via access_ok() in vfs_write, so use the 'no check' version to bypass + * the HARDENED_USERCOPY overhead. + */ + if (test_bit(DAXDEV_NOCACHE, &dax_dev->flags)) + return _copy_from_iter_flushcache(addr, bytes, i); + return _copy_from_iter(addr, bytes, i); } -EXPORT_SYMBOL_GPL(dax_copy_from_iter); size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) @@ -156,9 +166,15 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr, if (!dax_alive(dax_dev)) return 0; - return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i); + /* + * The userspace address for the memory copy has already been validated + * via access_ok() in vfs_red, so use the 'no check' version to bypass + * the HARDENED_USERCOPY overhead. + */ + if (test_bit(DAXDEV_NOMC, &dax_dev->flags)) + return _copy_mc_to_iter(addr, bytes, i); + return _copy_to_iter(addr, bytes, i); } -EXPORT_SYMBOL_GPL(dax_copy_to_iter); int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) @@ -220,6 +236,18 @@ void set_dax_synchronous(struct dax_device *dax_dev) } EXPORT_SYMBOL_GPL(set_dax_synchronous); +void set_dax_nocache(struct dax_device *dax_dev) +{ + set_bit(DAXDEV_NOCACHE, &dax_dev->flags); +} +EXPORT_SYMBOL_GPL(set_dax_nocache); + +void set_dax_nomc(struct dax_device *dax_dev) +{ + set_bit(DAXDEV_NOMC, &dax_dev->flags); +} +EXPORT_SYMBOL_GPL(set_dax_nomc); + bool dax_alive(struct dax_device *dax_dev) { lockdep_assert_held(&dax_srcu); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 90de42f6743a..1b97a11d7151 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -180,22 +180,6 @@ static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - - return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); -} - -static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -206,8 +190,6 @@ static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define linear_dax_direct_access NULL -#define linear_dax_copy_from_iter NULL -#define linear_dax_copy_to_iter NULL #define linear_dax_zero_page_range NULL #endif @@ -225,8 +207,6 @@ static struct target_type linear_target = { .prepare_ioctl = linear_prepare_ioctl, .iterate_devices = linear_iterate_devices, .direct_access = linear_dax_direct_access, - .dax_copy_from_iter = linear_dax_copy_from_iter, - .dax_copy_to_iter = linear_dax_copy_to_iter, .dax_zero_page_range = linear_dax_zero_page_range, }; diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index cdb22e7a1d0d..139b09b06eda 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -902,51 +902,6 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit } #if IS_ENABLED(CONFIG_FS_DAX) -static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes, - struct iov_iter *i) -{ - struct pending_block *block; - - if (!bytes) - return 0; - - block = kzalloc(sizeof(struct pending_block), GFP_KERNEL); - if (!block) { - DMERR("Error allocating dax pending block"); - return -ENOMEM; - } - - block->data = kzalloc(bytes, GFP_KERNEL); - if (!block->data) { - DMERR("Error allocating dax data space"); - kfree(block); - return -ENOMEM; - } - - /* write data provided via the iterator */ - if (!copy_from_iter(block->data, bytes, i)) { - DMERR("Error copying dax data"); - kfree(block->data); - kfree(block); - return -EIO; - } - - /* rewind the iterator so that the block driver can use it */ - iov_iter_revert(i, bytes); - - block->datalen = bytes; - block->sector = bio_to_dev_sectors(lc, sector); - block->nr_sectors = ALIGN(bytes, lc->sectorsize) >> lc->sectorshift; - - atomic_inc(&lc->pending_blocks); - spin_lock_irq(&lc->blocks_lock); - list_add_tail(&block->list, &lc->unflushed_blocks); - spin_unlock_irq(&lc->blocks_lock); - wake_up_process(lc->log_kthread); - - return 0; -} - static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff) { @@ -964,37 +919,6 @@ static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t log_writes_dax_copy_from_iter(struct dm_target *ti, - pgoff_t pgoff, void *addr, size_t bytes, - struct iov_iter *i) -{ - struct log_writes_c *lc = ti->private; - sector_t sector = pgoff * PAGE_SECTORS; - struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - int err; - - /* Don't bother doing anything if logging has been disabled */ - if (!lc->logging_enabled) - goto dax_copy; - - err = log_dax(lc, sector, bytes, i); - if (err) { - DMWARN("Error %d logging DAX write", err); - return 0; - } -dax_copy: - return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); -} - -static size_t log_writes_dax_copy_to_iter(struct dm_target *ti, - pgoff_t pgoff, void *addr, size_t bytes, - struct iov_iter *i) -{ - struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -1005,8 +929,6 @@ static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define log_writes_dax_direct_access NULL -#define log_writes_dax_copy_from_iter NULL -#define log_writes_dax_copy_to_iter NULL #define log_writes_dax_zero_page_range NULL #endif @@ -1024,8 +946,6 @@ static struct target_type log_writes_target = { .iterate_devices = log_writes_iterate_devices, .io_hints = log_writes_io_hints, .direct_access = log_writes_dax_direct_access, - .dax_copy_from_iter = log_writes_dax_copy_from_iter, - .dax_copy_to_iter = log_writes_dax_copy_to_iter, .dax_zero_page_range = log_writes_dax_zero_page_range, }; diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 50dba3f39274..e566115ec0bb 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -324,22 +324,6 @@ static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff, return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn); } -static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - - return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i); -} - -static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff); - - return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i); -} - static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages) { @@ -350,8 +334,6 @@ static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff, #else #define stripe_dax_direct_access NULL -#define stripe_dax_copy_from_iter NULL -#define stripe_dax_copy_to_iter NULL #define stripe_dax_zero_page_range NULL #endif @@ -488,8 +470,6 @@ static struct target_type stripe_target = { .iterate_devices = stripe_iterate_devices, .io_hints = stripe_io_hints, .direct_access = stripe_dax_direct_access, - .dax_copy_from_iter = stripe_dax_copy_from_iter, - .dax_copy_to_iter = stripe_dax_copy_to_iter, .dax_zero_page_range = stripe_dax_zero_page_range, }; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index f4b972af1092..ce250bd274f3 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1027,54 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return ret; } -static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct mapped_device *md = dax_get_private(dax_dev); - sector_t sector = pgoff * PAGE_SECTORS; - struct dm_target *ti; - long ret = 0; - int srcu_idx; - - ti = dm_dax_get_live_target(md, sector, &srcu_idx); - - if (!ti) - goto out; - if (!ti->type->dax_copy_from_iter) { - ret = copy_from_iter(addr, bytes, i); - goto out; - } - ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i); - out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - -static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - struct mapped_device *md = dax_get_private(dax_dev); - sector_t sector = pgoff * PAGE_SECTORS; - struct dm_target *ti; - long ret = 0; - int srcu_idx; - - ti = dm_dax_get_live_target(md, sector, &srcu_idx); - - if (!ti) - goto out; - if (!ti->type->dax_copy_to_iter) { - ret = copy_to_iter(addr, bytes, i); - goto out; - } - ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i); - out: - dm_put_live_table(md, srcu_idx); - - return ret; -} - static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -1770,6 +1722,8 @@ static struct mapped_device *alloc_dev(int minor) md->dax_dev = NULL; goto bad; } + set_dax_nocache(md->dax_dev); + set_dax_nomc(md->dax_dev); if (dax_add_host(md->dax_dev, md->disk)) goto bad; } @@ -3024,8 +2978,6 @@ static const struct block_device_operations dm_rq_blk_dops = { static const struct dax_operations dm_dax_ops = { .direct_access = dm_dax_direct_access, - .copy_from_iter = dm_dax_copy_from_iter, - .copy_to_iter = dm_dax_copy_to_iter, .zero_page_range = dm_dax_zero_page_range, }; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 18b1d9c55831..58d95242a836 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -301,26 +301,8 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev, return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn); } -/* - * Bounds checking, both file offset and device offset, is handled by - * dax_iomap_actor() - */ -static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - return _copy_from_iter_flushcache(addr, bytes, i); -} - -static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i) -{ - return _copy_mc_to_iter(addr, bytes, i); -} - static const struct dax_operations pmem_dax_ops = { .direct_access = pmem_dax_direct_access, - .copy_from_iter = pmem_copy_from_iter, - .copy_to_iter = pmem_copy_to_iter, .zero_page_range = pmem_dax_zero_page_range, }; @@ -497,6 +479,8 @@ static int pmem_attach_disk(struct device *dev, rc = PTR_ERR(dax_dev); goto out; } + set_dax_nocache(dax_dev); + set_dax_nomc(dax_dev); if (is_nvdimm_sync(nd_region)) set_dax_synchronous(dax_dev); rc = dax_add_host(dax_dev, disk); diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 10823debc09b..d614843caf6c 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -44,18 +44,6 @@ static const struct block_device_operations dcssblk_devops = { .release = dcssblk_release, }; -static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) -{ - return copy_from_iter(addr, bytes, i); -} - -static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i) -{ - return copy_to_iter(addr, bytes, i); -} - static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -72,8 +60,6 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev, static const struct dax_operations dcssblk_dax_ops = { .direct_access = dcssblk_dax_direct_access, - .copy_from_iter = dcssblk_dax_copy_from_iter, - .copy_to_iter = dcssblk_dax_copy_to_iter, .zero_page_range = dcssblk_dax_zero_page_range, }; diff --git a/fs/dax.c b/fs/dax.c index e0eecd8e3a8f..cd03485867a7 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -1260,11 +1260,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, if (map_len > end - pos) map_len = end - pos; - /* - * The userspace address for the memory copy has already been - * validated via access_ok() in either vfs_read() or - * vfs_write(), depending on which operation we are doing. - */ if (iov_iter_rw(iter) == WRITE) xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr, map_len, iter); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 5c03a0364a9b..3928cd8ceba6 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -753,20 +753,6 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } -static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, - size_t bytes, struct iov_iter *i) -{ - return copy_from_iter(addr, bytes, i); -} - -static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev, - pgoff_t pgoff, void *addr, - size_t bytes, struct iov_iter *i) -{ - return copy_to_iter(addr, bytes, i); -} - static int virtio_fs_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { @@ -783,8 +769,6 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev, static const struct dax_operations virtio_fs_dax_ops = { .direct_access = virtio_fs_direct_access, - .copy_from_iter = virtio_fs_copy_from_iter, - .copy_to_iter = virtio_fs_copy_to_iter, .zero_page_range = virtio_fs_zero_page_range, }; diff --git a/include/linux/dax.h b/include/linux/dax.h index c04f46478e3b..9fc5f99a0ae2 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -28,12 +28,6 @@ struct dax_operations { */ bool (*dax_supported)(struct dax_device *, struct block_device *, int, sector_t, sector_t); - /* copy_from_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); - /* copy_to_iter: required operation for fs-dax direct-i/o */ - size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t, - struct iov_iter *); /* zero_page_range: required operation. Zero page range */ int (*zero_page_range)(struct dax_device *, pgoff_t, size_t); }; @@ -95,6 +89,9 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma, } #endif +void set_dax_nocache(struct dax_device *dax_dev); +void set_dax_nomc(struct dax_device *dax_dev); + struct writeback_control; #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX) int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index a7df155ea49b..b26fecf6c8e8 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -147,8 +147,6 @@ typedef int (*dm_busy_fn) (struct dm_target *ti); */ typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff, long nr_pages, void **kaddr, pfn_t *pfn); -typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff, - void *addr, size_t bytes, struct iov_iter *i); typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff, size_t nr_pages); @@ -200,8 +198,6 @@ struct target_type { dm_iterate_devices_fn iterate_devices; dm_io_hints_fn io_hints; dm_dax_direct_access_fn direct_access; - dm_dax_copy_iter_fn dax_copy_from_iter; - dm_dax_copy_iter_fn dax_copy_to_iter; dm_dax_zero_page_range_fn dax_zero_page_range; /* For internal device-mapper use. */ -- cgit v1.2.3 From d639b9d13a39cf15639cbe6e8b2c43eb60148a73 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:44 -0800 Subject: bpf: Introduce composable reg, ret and arg types. There are some common properties shared between bpf reg, ret and arg values. For instance, a value may be a NULL pointer, or a pointer to a read-only memory. Previously, to express these properties, enumeration was used. For example, in order to test whether a reg value can be NULL, reg_type_may_be_null() simply enumerates all types that are possibly NULL. The problem of this approach is that it's not scalable and causes a lot of duplication. These properties can be combined, for example, a type could be either MAYBE_NULL or RDONLY, or both. This patch series rewrites the layout of reg_type, arg_type and ret_type, so that common properties can be extracted and represented as composable flag. For example, one can write ARG_PTR_TO_MEM | PTR_MAYBE_NULL which is equivalent to the previous ARG_PTR_TO_MEM_OR_NULL The type ARG_PTR_TO_MEM are called "base type" in this patch. Base types can be extended with flags. A flag occupies the higher bits while base types sits in the lower bits. This patch in particular sets up a set of macro for this purpose. The following patches will rewrite arg_types, ret_types and reg_types respectively. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-2-haoluo@google.com --- include/linux/bpf.h | 42 ++++++++++++++++++++++++++++++++++++++++++ include/linux/bpf_verifier.h | 13 +++++++++++++ 2 files changed, 55 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 965fffaf0308..41bb3687cc85 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -297,6 +297,29 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, extern const struct bpf_map_ops bpf_map_offload_ops; +/* bpf_type_flag contains a set of flags that are applicable to the values of + * arg_type, ret_type and reg_type. For example, a pointer value may be null, + * or a memory is read-only. We classify types into two categories: base types + * and extended types. Extended types are base types combined with a type flag. + * + * Currently there are no more than 32 base types in arg_type, ret_type and + * reg_types. + */ +#define BPF_BASE_TYPE_BITS 8 + +enum bpf_type_flag { + /* PTR may be NULL. */ + PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = PTR_MAYBE_NULL, +}; + +/* Max number of base types. */ +#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) + +/* Max number of all types. */ +#define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) + /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ @@ -343,7 +366,13 @@ enum bpf_arg_type { ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { @@ -359,7 +388,14 @@ enum bpf_return_type { RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ + __BPF_RET_TYPE_MAX, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL @@ -461,7 +497,13 @@ enum bpf_reg_type { PTR_TO_FUNC, /* reg points to a bpf program function */ PTR_TO_MAP_KEY, /* reg points to a map element key */ __BPF_REG_TYPE_MAX, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index ee931398f311..34e4ceaca3c7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -546,5 +546,18 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); +#define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) + +/* extract base type from bpf_{arg, return, reg}_type. */ +static inline u32 base_type(u32 type) +{ + return type & BPF_BASE_TYPE_MASK; +} + +/* extract flags from an extended type. See bpf_type_flag in bpf.h. */ +static inline u32 type_flag(u32 type) +{ + return type & ~BPF_BASE_TYPE_MASK; +} #endif /* _LINUX_BPF_VERIFIER_H */ -- cgit v1.2.3 From 48946bd6a5d695c50b34546864b79c1f910a33c1 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:45 -0800 Subject: bpf: Replace ARG_XXX_OR_NULL with ARG_XXX | PTR_MAYBE_NULL We have introduced a new type to make bpf_arg composable, by reserving high bits of bpf_arg to represent flags of a type. One of the flags is PTR_MAYBE_NULL which indicates a pointer may be NULL. When applying this flag to an arg_type, it means the arg can take NULL pointer. This patch switches the qualified arg_types to use this flag. The arg_types changed in this patch include: 1. ARG_PTR_TO_MAP_VALUE_OR_NULL 2. ARG_PTR_TO_MEM_OR_NULL 3. ARG_PTR_TO_CTX_OR_NULL 4. ARG_PTR_TO_SOCKET_OR_NULL 5. ARG_PTR_TO_ALLOC_MEM_OR_NULL 6. ARG_PTR_TO_STACK_OR_NULL This patch does not eliminate the use of these arg_types, instead it makes them an alias to the 'ARG_XXX | PTR_MAYBE_NULL'. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-3-haoluo@google.com --- include/linux/bpf.h | 15 +++++++++------ kernel/bpf/verifier.c | 39 ++++++++++++++------------------------- 2 files changed, 23 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 41bb3687cc85..765bd7cc4272 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -331,13 +331,11 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */ ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, * helper function must fill all bytes or clear * them in error case. @@ -347,26 +345,31 @@ enum bpf_arg_type { ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ - ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ - ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ - ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ - ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ + ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, + /* Extended arg_types. */ + ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, + ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, + ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, + ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, + ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, + ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 07d7d6124a18..6095a75c1118 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -475,14 +475,9 @@ static bool arg_type_may_be_refcounted(enum bpf_arg_type type) return type == ARG_PTR_TO_SOCK_COMMON; } -static bool arg_type_may_be_null(enum bpf_arg_type type) +static bool type_may_be_null(u32 type) { - return type == ARG_PTR_TO_MAP_VALUE_OR_NULL || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_CTX_OR_NULL || - type == ARG_PTR_TO_SOCKET_OR_NULL || - type == ARG_PTR_TO_ALLOC_MEM_OR_NULL || - type == ARG_PTR_TO_STACK_OR_NULL; + return type & PTR_MAYBE_NULL; } /* Determine whether the function releases some resources allocated by another @@ -5016,9 +5011,8 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { - return type == ARG_PTR_TO_MEM || - type == ARG_PTR_TO_MEM_OR_NULL || - type == ARG_PTR_TO_UNINIT_MEM; + return base_type(type) == ARG_PTR_TO_MEM || + base_type(type) == ARG_PTR_TO_UNINIT_MEM; } static bool arg_type_is_mem_size(enum bpf_arg_type type) @@ -5155,31 +5149,26 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = { [ARG_PTR_TO_MAP_KEY] = &map_key_value_types, [ARG_PTR_TO_MAP_VALUE] = &map_key_value_types, [ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types, - [ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types, [ARG_CONST_SIZE] = &scalar_types, [ARG_CONST_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types, [ARG_CONST_MAP_PTR] = &const_map_ptr_types, [ARG_PTR_TO_CTX] = &context_types, - [ARG_PTR_TO_CTX_OR_NULL] = &context_types, [ARG_PTR_TO_SOCK_COMMON] = &sock_types, #ifdef CONFIG_NET [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types, #endif [ARG_PTR_TO_SOCKET] = &fullsock_types, - [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types, [ARG_PTR_TO_BTF_ID] = &btf_ptr_types, [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types, [ARG_PTR_TO_MEM] = &mem_types, - [ARG_PTR_TO_MEM_OR_NULL] = &mem_types, [ARG_PTR_TO_UNINIT_MEM] = &mem_types, [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types, - [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types, [ARG_PTR_TO_INT] = &int_ptr_types, [ARG_PTR_TO_LONG] = &int_ptr_types, [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types, [ARG_PTR_TO_FUNC] = &func_ptr_types, - [ARG_PTR_TO_STACK_OR_NULL] = &stack_ptr_types, + [ARG_PTR_TO_STACK] = &stack_ptr_types, [ARG_PTR_TO_CONST_STR] = &const_str_ptr_types, [ARG_PTR_TO_TIMER] = &timer_types, }; @@ -5193,7 +5182,7 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, const struct bpf_reg_types *compatible; int i, j; - compatible = compatible_reg_types[arg_type]; + compatible = compatible_reg_types[base_type(arg_type)]; if (!compatible) { verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type); return -EFAULT; @@ -5274,15 +5263,14 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return -EACCES; } - if (arg_type == ARG_PTR_TO_MAP_VALUE || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE || - arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) { + if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || + base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { err = resolve_map_arg_type(env, meta, &arg_type); if (err) return err; } - if (register_is_null(reg) && arg_type_may_be_null(arg_type)) + if (register_is_null(reg) && type_may_be_null(arg_type)) /* A NULL register has a SCALAR_VALUE type, so skip * type checking. */ @@ -5351,10 +5339,11 @@ skip_type_check: err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE || - (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL && - !register_is_null(reg)) || - arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { + } else if (base_type(arg_type) == ARG_PTR_TO_MAP_VALUE || + base_type(arg_type) == ARG_PTR_TO_UNINIT_MAP_VALUE) { + if (type_may_be_null(arg_type) && register_is_null(reg)) + return 0; + /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ -- cgit v1.2.3 From 3c4807322660d4290ac9062c034aed6b87243861 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:46 -0800 Subject: bpf: Replace RET_XXX_OR_NULL with RET_XXX | PTR_MAYBE_NULL We have introduced a new type to make bpf_ret composable, by reserving high bits to represent flags. One of the flag is PTR_MAYBE_NULL, which indicates a pointer may be NULL. When applying this flag to ret_types, it means the returned value could be a NULL pointer. This patch switches the qualified arg_types to use this flag. The ret_types changed in this patch include: 1. RET_PTR_TO_MAP_VALUE_OR_NULL 2. RET_PTR_TO_SOCKET_OR_NULL 3. RET_PTR_TO_TCP_SOCK_OR_NULL 4. RET_PTR_TO_SOCK_COMMON_OR_NULL 5. RET_PTR_TO_ALLOC_MEM_OR_NULL 6. RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL 7. RET_PTR_TO_BTF_ID_OR_NULL This patch doesn't eliminate the use of these names, instead it makes them aliases to 'RET_PTR_TO_XXX | PTR_MAYBE_NULL'. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-4-haoluo@google.com --- include/linux/bpf.h | 19 ++++++++++++------- kernel/bpf/helpers.c | 2 +- kernel/bpf/verifier.c | 52 +++++++++++++++++++++++++-------------------------- 3 files changed, 39 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 765bd7cc4272..975a1d5951bd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -382,17 +382,22 @@ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ - RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ - RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ - RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ - RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ - RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ - RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ - RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ + RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ + RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ + RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ + RET_PTR_TO_ALLOC_MEM, /* returns a pointer to dynamically allocated memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, + /* Extended ret_types. */ + RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, + RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, + RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, + RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, + RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, + /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 34d6f91dec1c..c49dc5cbe0a7 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -682,7 +682,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu) const struct bpf_func_proto bpf_per_cpu_ptr_proto = { .func = bpf_per_cpu_ptr, .gpl_only = false, - .ret_type = RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, + .ret_type = RET_PTR_TO_MEM_OR_BTF_ID | PTR_MAYBE_NULL, .arg1_type = ARG_PTR_TO_PERCPU_BTF_ID, .arg2_type = ARG_ANYTHING, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 6095a75c1118..ccc068c5c5f2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6473,6 +6473,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn int *insn_idx_p) { const struct bpf_func_proto *fn = NULL; + enum bpf_return_type ret_type; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; @@ -6612,13 +6613,13 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; /* update return register (already marked as written above) */ - if (fn->ret_type == RET_INTEGER) { + ret_type = fn->ret_type; + if (ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); - } else if (fn->ret_type == RET_VOID) { + } else if (ret_type == RET_VOID) { regs[BPF_REG_0].type = NOT_INIT; - } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL || - fn->ret_type == RET_PTR_TO_MAP_VALUE) { + } else if (base_type(ret_type) == RET_PTR_TO_MAP_VALUE) { /* There is no offset yet applied, variable or fixed */ mark_reg_known_zero(env, regs, BPF_REG_0); /* remember map_ptr, so that check_map_access() @@ -6632,28 +6633,27 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; - if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { + if (type_may_be_null(ret_type)) { + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; + } else { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; if (map_value_has_spin_lock(meta.map_ptr)) regs[BPF_REG_0].id = ++env->id_gen; - } else { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; } - } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { + } else if (base_type(ret_type) == RET_PTR_TO_SOCKET) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) { + } else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; - } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { + } else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; - } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) { + } else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) { mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; regs[BPF_REG_0].mem_size = meta.mem_size; - } else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL || - fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) { + } else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) { const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); @@ -6672,28 +6672,28 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } regs[BPF_REG_0].type = - fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? - PTR_TO_MEM : PTR_TO_MEM_OR_NULL; + (ret_type & PTR_MAYBE_NULL) ? + PTR_TO_MEM_OR_NULL : PTR_TO_MEM; regs[BPF_REG_0].mem_size = tsize; } else { regs[BPF_REG_0].type = - fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? - PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL; + (ret_type & PTR_MAYBE_NULL) ? + PTR_TO_BTF_ID_OR_NULL : PTR_TO_BTF_ID; regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } - } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL || - fn->ret_type == RET_PTR_TO_BTF_ID) { + } else if (base_type(ret_type) == RET_PTR_TO_BTF_ID) { int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_BTF_ID ? - PTR_TO_BTF_ID : - PTR_TO_BTF_ID_OR_NULL; + regs[BPF_REG_0].type = (ret_type & PTR_MAYBE_NULL) ? + PTR_TO_BTF_ID_OR_NULL : + PTR_TO_BTF_ID; ret_btf_id = *fn->ret_btf_id; if (ret_btf_id == 0) { - verbose(env, "invalid return type %d of func %s#%d\n", - fn->ret_type, func_id_name(func_id), func_id); + verbose(env, "invalid return type %u of func %s#%d\n", + base_type(ret_type), func_id_name(func_id), + func_id); return -EINVAL; } /* current BPF helper definitions are only coming from @@ -6702,8 +6702,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs[BPF_REG_0].btf = btf_vmlinux; regs[BPF_REG_0].btf_id = ret_btf_id; } else { - verbose(env, "unknown return type %d of func %s#%d\n", - fn->ret_type, func_id_name(func_id), func_id); + verbose(env, "unknown return type %u of func %s#%d\n", + base_type(ret_type), func_id_name(func_id), func_id); return -EINVAL; } -- cgit v1.2.3 From c25b2ae136039ffa820c26138ed4a5e5f3ab3841 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:47 -0800 Subject: bpf: Replace PTR_TO_XXX_OR_NULL with PTR_TO_XXX | PTR_MAYBE_NULL We have introduced a new type to make bpf_reg composable, by allocating bits in the type to represent flags. One of the flags is PTR_MAYBE_NULL which indicates a pointer may be NULL. This patch switches the qualified reg_types to use this flag. The reg_types changed in this patch include: 1. PTR_TO_MAP_VALUE_OR_NULL 2. PTR_TO_SOCKET_OR_NULL 3. PTR_TO_SOCK_COMMON_OR_NULL 4. PTR_TO_TCP_SOCK_OR_NULL 5. PTR_TO_BTF_ID_OR_NULL 6. PTR_TO_MEM_OR_NULL 7. PTR_TO_RDONLY_BUF_OR_NULL 8. PTR_TO_RDWR_BUF_OR_NULL Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/r/20211217003152.48334-5-haoluo@google.com --- include/linux/bpf.h | 18 +-- include/linux/bpf_verifier.h | 4 + kernel/bpf/btf.c | 7 +- kernel/bpf/map_iter.c | 4 +- kernel/bpf/verifier.c | 298 ++++++++++++++++++------------------------- net/core/bpf_sk_storage.c | 2 +- net/core/sock_map.c | 2 +- 7 files changed, 147 insertions(+), 188 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 975a1d5951bd..c3de62267b84 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -465,18 +465,15 @@ enum bpf_reg_type { PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ - PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ - PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ - PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need @@ -494,18 +491,21 @@ enum bpf_reg_type { * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ - PTR_TO_BTF_ID_OR_NULL, PTR_TO_MEM, /* reg points to valid memory region */ - PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ - PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ - PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ - PTR_TO_MAP_KEY, /* reg points to a map element key */ __BPF_REG_TYPE_MAX, + /* Extended reg_types. */ + PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, + PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, + PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, + PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, + PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, + PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MEM, + /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 34e4ceaca3c7..143401d4c9d9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,6 +18,8 @@ * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) +/* size of type_str_buf in bpf_verifier. */ +#define TYPE_STR_BUF_LEN 64 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -484,6 +486,8 @@ struct bpf_verifier_env { /* Same as scratched_regs but for stack slots */ u64 scratched_stack_slots; u32 prev_log_len, prev_insn_print_len; + /* buffer used in reg_type_str() to generate reg_type string */ + char type_str_buf[TYPE_STR_BUF_LEN]; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index a17de71abd2e..4e2ca7bea6c4 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4940,10 +4940,13 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, /* check for PTR_TO_RDONLY_BUF_OR_NULL or PTR_TO_RDWR_BUF_OR_NULL */ for (i = 0; i < prog->aux->ctx_arg_info_size; i++) { const struct bpf_ctx_arg_aux *ctx_arg_info = &prog->aux->ctx_arg_info[i]; + u32 type, flag; + type = base_type(ctx_arg_info->reg_type); + flag = type_flag(ctx_arg_info->reg_type); if (ctx_arg_info->offset == off && - (ctx_arg_info->reg_type == PTR_TO_RDONLY_BUF_OR_NULL || - ctx_arg_info->reg_type == PTR_TO_RDWR_BUF_OR_NULL)) { + (type == PTR_TO_RDWR_BUF || type == PTR_TO_RDONLY_BUF) && + (flag & PTR_MAYBE_NULL)) { info->reg_type = ctx_arg_info->reg_type; return true; } diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 6a9542af4212..631f0e44b7a9 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = { .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map_elem, key), - PTR_TO_RDONLY_BUF_OR_NULL }, + PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL }, { offsetof(struct bpf_iter__bpf_map_elem, value), - PTR_TO_RDWR_BUF_OR_NULL }, + PTR_TO_RDWR_BUF | PTR_MAYBE_NULL }, }, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ccc068c5c5f2..97e9d3f31443 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -442,18 +442,6 @@ static bool reg_type_not_null(enum bpf_reg_type type) type == PTR_TO_SOCK_COMMON; } -static bool reg_type_may_be_null(enum bpf_reg_type type) -{ - return type == PTR_TO_MAP_VALUE_OR_NULL || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_SOCK_COMMON_OR_NULL || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_BTF_ID_OR_NULL || - type == PTR_TO_MEM_OR_NULL || - type == PTR_TO_RDONLY_BUF_OR_NULL || - type == PTR_TO_RDWR_BUF_OR_NULL; -} - static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) { return reg->type == PTR_TO_MAP_VALUE && @@ -462,12 +450,9 @@ static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) { - return type == PTR_TO_SOCKET || - type == PTR_TO_SOCKET_OR_NULL || - type == PTR_TO_TCP_SOCK || - type == PTR_TO_TCP_SOCK_OR_NULL || - type == PTR_TO_MEM || - type == PTR_TO_MEM_OR_NULL; + return base_type(type) == PTR_TO_SOCKET || + base_type(type) == PTR_TO_TCP_SOCK || + base_type(type) == PTR_TO_MEM; } static bool arg_type_may_be_refcounted(enum bpf_arg_type type) @@ -537,39 +522,52 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) insn->imm == BPF_CMPXCHG; } -/* string representation of 'enum bpf_reg_type' */ -static const char * const reg_type_str[] = { - [NOT_INIT] = "?", - [SCALAR_VALUE] = "inv", - [PTR_TO_CTX] = "ctx", - [CONST_PTR_TO_MAP] = "map_ptr", - [PTR_TO_MAP_VALUE] = "map_value", - [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null", - [PTR_TO_STACK] = "fp", - [PTR_TO_PACKET] = "pkt", - [PTR_TO_PACKET_META] = "pkt_meta", - [PTR_TO_PACKET_END] = "pkt_end", - [PTR_TO_FLOW_KEYS] = "flow_keys", - [PTR_TO_SOCKET] = "sock", - [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", - [PTR_TO_SOCK_COMMON] = "sock_common", - [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", - [PTR_TO_TCP_SOCK] = "tcp_sock", - [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", - [PTR_TO_TP_BUFFER] = "tp_buffer", - [PTR_TO_XDP_SOCK] = "xdp_sock", - [PTR_TO_BTF_ID] = "ptr_", - [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_", - [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", - [PTR_TO_MEM] = "mem", - [PTR_TO_MEM_OR_NULL] = "mem_or_null", - [PTR_TO_RDONLY_BUF] = "rdonly_buf", - [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null", - [PTR_TO_RDWR_BUF] = "rdwr_buf", - [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null", - [PTR_TO_FUNC] = "func", - [PTR_TO_MAP_KEY] = "map_key", -}; +/* string representation of 'enum bpf_reg_type' + * + * Note that reg_type_str() can not appear more than once in a single verbose() + * statement. + */ +static const char *reg_type_str(struct bpf_verifier_env *env, + enum bpf_reg_type type) +{ + char postfix[16] = {0}; + static const char * const str[] = { + [NOT_INIT] = "?", + [SCALAR_VALUE] = "inv", + [PTR_TO_CTX] = "ctx", + [CONST_PTR_TO_MAP] = "map_ptr", + [PTR_TO_MAP_VALUE] = "map_value", + [PTR_TO_STACK] = "fp", + [PTR_TO_PACKET] = "pkt", + [PTR_TO_PACKET_META] = "pkt_meta", + [PTR_TO_PACKET_END] = "pkt_end", + [PTR_TO_FLOW_KEYS] = "flow_keys", + [PTR_TO_SOCKET] = "sock", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TP_BUFFER] = "tp_buffer", + [PTR_TO_XDP_SOCK] = "xdp_sock", + [PTR_TO_BTF_ID] = "ptr_", + [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", + [PTR_TO_MEM] = "mem", + [PTR_TO_RDONLY_BUF] = "rdonly_buf", + [PTR_TO_RDWR_BUF] = "rdwr_buf", + [PTR_TO_FUNC] = "func", + [PTR_TO_MAP_KEY] = "map_key", + }; + + if (type & PTR_MAYBE_NULL) { + if (base_type(type) == PTR_TO_BTF_ID || + base_type(type) == PTR_TO_PERCPU_BTF_ID) + strncpy(postfix, "or_null_", 16); + else + strncpy(postfix, "_or_null", 16); + } + + snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s", + str[base_type(type)], postfix); + return env->type_str_buf; +} static char slot_type_char[] = { [STACK_INVALID] = '?', @@ -675,7 +673,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, continue; verbose(env, " R%d", i); print_liveness(env, reg->live); - verbose(env, "=%s", reg_type_str[t]); + verbose(env, "=%s", reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if ((t == SCALAR_VALUE || t == PTR_TO_STACK) && @@ -683,9 +681,8 @@ static void print_verifier_state(struct bpf_verifier_env *env, /* reg->off should be 0 for SCALAR_VALUE */ verbose(env, "%lld", reg->var_off.value + reg->off); } else { - if (t == PTR_TO_BTF_ID || - t == PTR_TO_BTF_ID_OR_NULL || - t == PTR_TO_PERCPU_BTF_ID) + if (base_type(t) == PTR_TO_BTF_ID || + base_type(t) == PTR_TO_PERCPU_BTF_ID) verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) @@ -694,10 +691,9 @@ static void print_verifier_state(struct bpf_verifier_env *env, verbose(env, ",off=%d", reg->off); if (type_is_pkt_pointer(t)) verbose(env, ",r=%d", reg->range); - else if (t == CONST_PTR_TO_MAP || - t == PTR_TO_MAP_KEY || - t == PTR_TO_MAP_VALUE || - t == PTR_TO_MAP_VALUE_OR_NULL) + else if (base_type(t) == CONST_PTR_TO_MAP || + base_type(t) == PTR_TO_MAP_KEY || + base_type(t) == PTR_TO_MAP_VALUE) verbose(env, ",ks=%d,vs=%d", reg->map_ptr->key_size, reg->map_ptr->value_size); @@ -769,7 +765,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; - verbose(env, "=%s", reg_type_str[t]); + verbose(env, "=%s", reg_type_str(env, t)); if (t == SCALAR_VALUE && reg->precise) verbose(env, "P"); if (t == SCALAR_VALUE && tnum_is_const(reg->var_off)) @@ -1202,8 +1198,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { - switch (reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: { + if (base_type(reg->type) == PTR_TO_MAP_VALUE) { const struct bpf_map *map = reg->map_ptr; if (map->inner_map_meta) { @@ -1222,32 +1217,10 @@ static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) } else { reg->type = PTR_TO_MAP_VALUE; } - break; - } - case PTR_TO_SOCKET_OR_NULL: - reg->type = PTR_TO_SOCKET; - break; - case PTR_TO_SOCK_COMMON_OR_NULL: - reg->type = PTR_TO_SOCK_COMMON; - break; - case PTR_TO_TCP_SOCK_OR_NULL: - reg->type = PTR_TO_TCP_SOCK; - break; - case PTR_TO_BTF_ID_OR_NULL: - reg->type = PTR_TO_BTF_ID; - break; - case PTR_TO_MEM_OR_NULL: - reg->type = PTR_TO_MEM; - break; - case PTR_TO_RDONLY_BUF_OR_NULL: - reg->type = PTR_TO_RDONLY_BUF; - break; - case PTR_TO_RDWR_BUF_OR_NULL: - reg->type = PTR_TO_RDWR_BUF; - break; - default: - WARN_ONCE(1, "unknown nullable register type"); + return; } + + reg->type &= ~PTR_MAYBE_NULL; } static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg) @@ -2103,7 +2076,7 @@ static int mark_reg_read(struct bpf_verifier_env *env, break; if (parent->live & REG_LIVE_DONE) { verbose(env, "verifier BUG type %s var_off %lld off %d\n", - reg_type_str[parent->type], + reg_type_str(env, parent->type), parent->var_off.value, parent->off); return -EFAULT; } @@ -2768,9 +2741,8 @@ static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi) static bool is_spillable_regtype(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_MAP_VALUE: - case PTR_TO_MAP_VALUE_OR_NULL: case PTR_TO_STACK: case PTR_TO_CTX: case PTR_TO_PACKET: @@ -2779,21 +2751,14 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_FLOW_KEYS: case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: case PTR_TO_RDONLY_BUF: - case PTR_TO_RDONLY_BUF_OR_NULL: case PTR_TO_RDWR_BUF: - case PTR_TO_RDWR_BUF_OR_NULL: case PTR_TO_PERCPU_BTF_ID: case PTR_TO_MEM: - case PTR_TO_MEM_OR_NULL: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: return true; @@ -3633,7 +3598,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, */ *reg_type = info.reg_type; - if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) { + if (base_type(*reg_type) == PTR_TO_BTF_ID) { *btf = info.btf; *btf_id = info.btf_id; } else { @@ -3701,7 +3666,7 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, } verbose(env, "R%d invalid %s access off=%d size=%d\n", - regno, reg_type_str[reg->type], off, size); + regno, reg_type_str(env, reg->type), off, size); return -EACCES; } @@ -4466,7 +4431,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else { mark_reg_known_zero(env, regs, value_regno); - if (reg_type_may_be_null(reg_type)) + if (type_may_be_null(reg_type)) regs[value_regno].id = ++env->id_gen; /* A load of ctx field could have different * actual load size with the one encoded in the @@ -4474,8 +4439,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * a sub-register. */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; - if (reg_type == PTR_TO_BTF_ID || - reg_type == PTR_TO_BTF_ID_OR_NULL) { + if (base_type(reg_type) == PTR_TO_BTF_ID) { regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; } @@ -4528,7 +4492,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); + regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_sock_access(env, insn_idx, regno, off, size, t); @@ -4547,7 +4511,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (reg->type == PTR_TO_RDONLY_BUF) { if (t == BPF_WRITE) { verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str[reg->type]); + regno, reg_type_str(env, reg->type)); return -EACCES; } err = check_buffer_access(env, reg, regno, off, size, false, @@ -4563,7 +4527,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EACCES; } @@ -4630,7 +4594,7 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n", insn->dst_reg, - reg_type_str[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } @@ -4850,9 +4814,9 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, register_is_null(reg)) return 0; - verbose(env, "R%d type=%s expected=%s\n", regno, - reg_type_str[reg->type], - reg_type_str[PTR_TO_STACK]); + verbose(env, "R%d type=%s ", regno, + reg_type_str(env, reg->type)); + verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK)); return -EACCES; } } @@ -4863,7 +4827,7 @@ int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, if (register_is_null(reg)) return 0; - if (reg_type_may_be_null(reg->type)) { + if (type_may_be_null(reg->type)) { /* Assuming that the register contains a value check if the memory * access is safe. Temporarily save and restore the register's state as * the conversion shouldn't be visible to a caller. @@ -5197,10 +5161,10 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, goto found; } - verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]); + verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, type)); for (j = 0; j + 1 < i; j++) - verbose(env, "%s, ", reg_type_str[compatible->types[j]]); - verbose(env, "%s\n", reg_type_str[compatible->types[j]]); + verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); + verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES; found: @@ -6474,6 +6438,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn { const struct bpf_func_proto *fn = NULL; enum bpf_return_type ret_type; + enum bpf_type_flag ret_flag; struct bpf_reg_state *regs; struct bpf_call_arg_meta meta; int insn_idx = *insn_idx_p; @@ -6614,6 +6579,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn /* update return register (already marked as written above) */ ret_type = fn->ret_type; + ret_flag = type_flag(fn->ret_type); if (ret_type == RET_INTEGER) { /* sets type to SCALAR_VALUE */ mark_reg_unknown(env, regs, BPF_REG_0); @@ -6633,25 +6599,23 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } regs[BPF_REG_0].map_ptr = meta.map_ptr; regs[BPF_REG_0].map_uid = meta.map_uid; - if (type_may_be_null(ret_type)) { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; - } else { - regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; - if (map_value_has_spin_lock(meta.map_ptr)) - regs[BPF_REG_0].id = ++env->id_gen; + regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag; + if (!type_may_be_null(ret_type) && + map_value_has_spin_lock(meta.map_ptr)) { + regs[BPF_REG_0].id = ++env->id_gen; } } else if (base_type(ret_type) == RET_PTR_TO_SOCKET) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag; } else if (base_type(ret_type) == RET_PTR_TO_SOCK_COMMON) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag; } else if (base_type(ret_type) == RET_PTR_TO_TCP_SOCK) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag; } else if (base_type(ret_type) == RET_PTR_TO_ALLOC_MEM) { mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = meta.mem_size; } else if (base_type(ret_type) == RET_PTR_TO_MEM_OR_BTF_ID) { const struct btf_type *t; @@ -6671,14 +6635,10 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn tname, PTR_ERR(ret)); return -EINVAL; } - regs[BPF_REG_0].type = - (ret_type & PTR_MAYBE_NULL) ? - PTR_TO_MEM_OR_NULL : PTR_TO_MEM; + regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag; regs[BPF_REG_0].mem_size = tsize; } else { - regs[BPF_REG_0].type = - (ret_type & PTR_MAYBE_NULL) ? - PTR_TO_BTF_ID_OR_NULL : PTR_TO_BTF_ID; + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } @@ -6686,9 +6646,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn int ret_btf_id; mark_reg_known_zero(env, regs, BPF_REG_0); - regs[BPF_REG_0].type = (ret_type & PTR_MAYBE_NULL) ? - PTR_TO_BTF_ID_OR_NULL : - PTR_TO_BTF_ID; + regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag; ret_btf_id = *fn->ret_btf_id; if (ret_btf_id == 0) { verbose(env, "invalid return type %u of func %s#%d\n", @@ -6707,7 +6665,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (reg_type_may_be_null(regs[BPF_REG_0].type)) + if (type_may_be_null(regs[BPF_REG_0].type)) regs[BPF_REG_0].id = ++env->id_gen; if (is_ptr_cast_function(func_id)) { @@ -6916,25 +6874,25 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env, if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) { verbose(env, "math between %s pointer and %lld is not allowed\n", - reg_type_str[type], val); + reg_type_str(env, type), val); return false; } if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) { verbose(env, "%s pointer offset %d is not allowed\n", - reg_type_str[type], reg->off); + reg_type_str(env, type), reg->off); return false; } if (smin == S64_MIN) { verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n", - reg_type_str[type]); + reg_type_str(env, type)); return false; } if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) { verbose(env, "value %lld makes %s pointer be out of bounds\n", - smin, reg_type_str[type]); + smin, reg_type_str(env, type)); return false; } @@ -7311,11 +7269,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, return -EACCES; } - switch (ptr_reg->type) { - case PTR_TO_MAP_VALUE_OR_NULL: + if (ptr_reg->type & PTR_MAYBE_NULL) { verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; + } + + switch (base_type(ptr_reg->type)) { case CONST_PTR_TO_MAP: /* smin_val represents the known value */ if (known && smin_val == 0 && opcode == BPF_ADD) @@ -7323,14 +7283,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, fallthrough; case PTR_TO_PACKET_END: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: verbose(env, "R%d pointer arithmetic on %s prohibited\n", - dst, reg_type_str[ptr_reg->type]); + dst, reg_type_str(env, ptr_reg->type)); return -EACCES; default: break; @@ -9049,7 +9006,7 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, struct bpf_reg_state *reg, u32 id, bool is_null) { - if (reg_type_may_be_null(reg->type) && reg->id == id && + if (type_may_be_null(reg->type) && reg->id == id && !WARN_ON_ONCE(!reg->id)) { /* Old offset (both fixed and variable parts) should * have been known-zero, because we don't allow pointer @@ -9427,7 +9384,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, */ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K && insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) && - reg_type_may_be_null(dst_reg->type)) { + type_may_be_null(dst_reg->type)) { /* Mark all identical registers in each branch as either * safe or unknown depending R == 0 or R != 0 conditional. */ @@ -9681,7 +9638,7 @@ static int check_return_code(struct bpf_verifier_env *env) /* enforce return zero from async callbacks like timer */ if (reg->type != SCALAR_VALUE) { verbose(env, "In async callback the register R0 is not a known value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } @@ -9695,7 +9652,7 @@ static int check_return_code(struct bpf_verifier_env *env) if (is_subprog) { if (reg->type != SCALAR_VALUE) { verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } return 0; @@ -9759,7 +9716,7 @@ static int check_return_code(struct bpf_verifier_env *env) if (reg->type != SCALAR_VALUE) { verbose(env, "At program exit the register R0 is not a known value (%s)\n", - reg_type_str[reg->type]); + reg_type_str(env, reg->type)); return -EINVAL; } @@ -10616,7 +10573,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, return true; if (rcur->type == NOT_INIT) return false; - switch (rold->type) { + switch (base_type(rold->type)) { case SCALAR_VALUE: if (env->explore_alu_limits) return false; @@ -10638,6 +10595,22 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, } case PTR_TO_MAP_KEY: case PTR_TO_MAP_VALUE: + /* a PTR_TO_MAP_VALUE could be safe to use as a + * PTR_TO_MAP_VALUE_OR_NULL into the same map. + * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- + * checked, doing so could have affected others with the same + * id, and we can't check for that because we lost the id when + * we converted to a PTR_TO_MAP_VALUE. + */ + if (type_may_be_null(rold->type)) { + if (!type_may_be_null(rcur->type)) + return false; + if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) + return false; + /* Check our ids match any regs they're supposed to */ + return check_ids(rold->id, rcur->id, idmap); + } + /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. * 'id' is not compared, since it's only used for maps with @@ -10649,20 +10622,6 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && tnum_in(rold->var_off, rcur->var_off); - case PTR_TO_MAP_VALUE_OR_NULL: - /* a PTR_TO_MAP_VALUE could be safe to use as a - * PTR_TO_MAP_VALUE_OR_NULL into the same map. - * However, if the old PTR_TO_MAP_VALUE_OR_NULL then got NULL- - * checked, doing so could have affected others with the same - * id, and we can't check for that because we lost the id when - * we converted to a PTR_TO_MAP_VALUE. - */ - if (rcur->type != PTR_TO_MAP_VALUE_OR_NULL) - return false; - if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, id))) - return false; - /* Check our ids match any regs they're supposed to */ - return check_ids(rold->id, rcur->id, idmap); case PTR_TO_PACKET_META: case PTR_TO_PACKET: if (rcur->type != rold->type) @@ -10691,11 +10650,8 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, case PTR_TO_PACKET_END: case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: /* Only valid matches are exact, which memcmp() above * would have accepted @@ -11221,17 +11177,13 @@ next: /* Return true if it's OK to have the same insn return a different type. */ static bool reg_type_mismatch_ok(enum bpf_reg_type type) { - switch (type) { + switch (base_type(type)) { case PTR_TO_CTX: case PTR_TO_SOCKET: - case PTR_TO_SOCKET_OR_NULL: case PTR_TO_SOCK_COMMON: - case PTR_TO_SOCK_COMMON_OR_NULL: case PTR_TO_TCP_SOCK: - case PTR_TO_TCP_SOCK_OR_NULL: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_BTF_ID_OR_NULL: return false; default: return true; @@ -11457,7 +11409,7 @@ static int do_check(struct bpf_verifier_env *env) if (is_ctx_reg(env, insn->dst_reg)) { verbose(env, "BPF_ST stores into R%d %s is not allowed\n", insn->dst_reg, - reg_type_str[reg_state(env, insn->dst_reg)->type]); + reg_type_str(env, reg_state(env, insn->dst_reg)->type)); return -EACCES; } diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 68d2cbf8331a..4cb5ef8eddbc 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -929,7 +929,7 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), - PTR_TO_RDWR_BUF_OR_NULL }, + PTR_TO_RDWR_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 4ca4b11f4e5f..96d4ea7e6918 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1564,7 +1564,7 @@ static struct bpf_iter_reg sock_map_iter_reg = { .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__sockmap, key), - PTR_TO_RDONLY_BUF_OR_NULL }, + PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL }, { offsetof(struct bpf_iter__sockmap, sk), PTR_TO_BTF_ID_OR_NULL }, }, -- cgit v1.2.3 From 20b2aff4bc15bda809f994761d5719827d66c0b4 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:48 -0800 Subject: bpf: Introduce MEM_RDONLY flag This patch introduce a flag MEM_RDONLY to tag a reg value pointing to read-only memory. It makes the following changes: 1. PTR_TO_RDWR_BUF -> PTR_TO_BUF 2. PTR_TO_RDONLY_BUF -> PTR_TO_BUF | MEM_RDONLY Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-6-haoluo@google.com --- include/linux/bpf.h | 8 +++-- kernel/bpf/btf.c | 3 +- kernel/bpf/map_iter.c | 4 +-- kernel/bpf/verifier.c | 84 ++++++++++++++++++++++++++++------------------- net/core/bpf_sk_storage.c | 2 +- net/core/sock_map.c | 2 +- 6 files changed, 60 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c3de62267b84..126048110bdb 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -311,7 +311,10 @@ enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = PTR_MAYBE_NULL, + /* MEM is read-only. */ + MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_RDONLY, }; /* Max number of base types. */ @@ -492,8 +495,7 @@ enum bpf_reg_type { * an explicit null check is required for this struct. */ PTR_TO_MEM, /* reg points to valid memory region */ - PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ - PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ + PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ __BPF_REG_TYPE_MAX, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 4e2ca7bea6c4..d1447b075c73 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4944,8 +4944,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, type = base_type(ctx_arg_info->reg_type); flag = type_flag(ctx_arg_info->reg_type); - if (ctx_arg_info->offset == off && - (type == PTR_TO_RDWR_BUF || type == PTR_TO_RDONLY_BUF) && + if (ctx_arg_info->offset == off && type == PTR_TO_BUF && (flag & PTR_MAYBE_NULL)) { info->reg_type = ctx_arg_info->reg_type; return true; diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 631f0e44b7a9..b0fa190b0979 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -174,9 +174,9 @@ static const struct bpf_iter_reg bpf_map_elem_reg_info = { .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_map_elem, key), - PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL }, + PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, { offsetof(struct bpf_iter__bpf_map_elem, value), - PTR_TO_RDWR_BUF | PTR_MAYBE_NULL }, + PTR_TO_BUF | PTR_MAYBE_NULL }, }, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 97e9d3f31443..e0a8a55ea3df 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -455,6 +455,11 @@ static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type) base_type(type) == PTR_TO_MEM; } +static bool type_is_rdonly_mem(u32 type) +{ + return type & MEM_RDONLY; +} + static bool arg_type_may_be_refcounted(enum bpf_arg_type type) { return type == ARG_PTR_TO_SOCK_COMMON; @@ -530,7 +535,7 @@ static bool is_cmpxchg_insn(const struct bpf_insn *insn) static const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) { - char postfix[16] = {0}; + char postfix[16] = {0}, prefix[16] = {0}; static const char * const str[] = { [NOT_INIT] = "?", [SCALAR_VALUE] = "inv", @@ -550,8 +555,7 @@ static const char *reg_type_str(struct bpf_verifier_env *env, [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_", [PTR_TO_MEM] = "mem", - [PTR_TO_RDONLY_BUF] = "rdonly_buf", - [PTR_TO_RDWR_BUF] = "rdwr_buf", + [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", }; @@ -564,8 +568,11 @@ static const char *reg_type_str(struct bpf_verifier_env *env, strncpy(postfix, "_or_null", 16); } - snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s", - str[base_type(type)], postfix); + if (type & MEM_RDONLY) + strncpy(prefix, "rdonly_", 16); + + snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", + prefix, str[base_type(type)], postfix); return env->type_str_buf; } @@ -2755,8 +2762,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: - case PTR_TO_RDONLY_BUF: - case PTR_TO_RDWR_BUF: + case PTR_TO_BUF: case PTR_TO_PERCPU_BTF_ID: case PTR_TO_MEM: case PTR_TO_FUNC: @@ -4508,22 +4514,28 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn } else if (reg->type == CONST_PTR_TO_MAP) { err = check_ptr_to_map_access(env, regs, regno, off, size, t, value_regno); - } else if (reg->type == PTR_TO_RDONLY_BUF) { - if (t == BPF_WRITE) { - verbose(env, "R%d cannot write into %s\n", - regno, reg_type_str(env, reg->type)); - return -EACCES; + } else if (base_type(reg->type) == PTR_TO_BUF) { + bool rdonly_mem = type_is_rdonly_mem(reg->type); + const char *buf_info; + u32 *max_access; + + if (rdonly_mem) { + if (t == BPF_WRITE) { + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str(env, reg->type)); + return -EACCES; + } + buf_info = "rdonly"; + max_access = &env->prog->aux->max_rdonly_access; + } else { + buf_info = "rdwr"; + max_access = &env->prog->aux->max_rdwr_access; } + err = check_buffer_access(env, reg, regno, off, size, false, - "rdonly", - &env->prog->aux->max_rdonly_access); - if (!err && value_regno >= 0) - mark_reg_unknown(env, regs, value_regno); - } else if (reg->type == PTR_TO_RDWR_BUF) { - err = check_buffer_access(env, reg, regno, off, size, false, - "rdwr", - &env->prog->aux->max_rdwr_access); - if (!err && t == BPF_READ && value_regno >= 0) + buf_info, max_access); + + if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, @@ -4771,8 +4783,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + const char *buf_info; + u32 *max_access; - switch (reg->type) { + switch (base_type(reg->type)) { case PTR_TO_PACKET: case PTR_TO_PACKET_META: return check_packet_access(env, regno, reg->off, access_size, @@ -4791,18 +4805,20 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); - case PTR_TO_RDONLY_BUF: - if (meta && meta->raw_mode) - return -EACCES; - return check_buffer_access(env, reg, regno, reg->off, - access_size, zero_size_allowed, - "rdonly", - &env->prog->aux->max_rdonly_access); - case PTR_TO_RDWR_BUF: + case PTR_TO_BUF: + if (type_is_rdonly_mem(reg->type)) { + if (meta && meta->raw_mode) + return -EACCES; + + buf_info = "rdonly"; + max_access = &env->prog->aux->max_rdonly_access; + } else { + buf_info = "rdwr"; + max_access = &env->prog->aux->max_rdwr_access; + } return check_buffer_access(env, reg, regno, reg->off, access_size, zero_size_allowed, - "rdwr", - &env->prog->aux->max_rdwr_access); + buf_info, max_access); case PTR_TO_STACK: return check_stack_range_initialized( env, @@ -5081,8 +5097,8 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, - PTR_TO_RDONLY_BUF, - PTR_TO_RDWR_BUF, + PTR_TO_BUF, + PTR_TO_BUF | MEM_RDONLY, }, }; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 4cb5ef8eddbc..ea61dfe19c86 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -929,7 +929,7 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), - PTR_TO_RDWR_BUF | PTR_MAYBE_NULL }, + PTR_TO_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 96d4ea7e6918..9618ab6d7cc9 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1564,7 +1564,7 @@ static struct bpf_iter_reg sock_map_iter_reg = { .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__sockmap, key), - PTR_TO_RDONLY_BUF | PTR_MAYBE_NULL }, + PTR_TO_BUF | PTR_MAYBE_NULL | MEM_RDONLY }, { offsetof(struct bpf_iter__sockmap, sk), PTR_TO_BTF_ID_OR_NULL }, }, -- cgit v1.2.3 From cf9f2f8d62eca810afbd1ee6cc0800202b000e57 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:49 -0800 Subject: bpf: Convert PTR_TO_MEM_OR_NULL to composable types. Remove PTR_TO_MEM_OR_NULL and replace it with PTR_TO_MEM combined with flag PTR_MAYBE_NULL. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-7-haoluo@google.com --- include/linux/bpf.h | 1 - kernel/bpf/btf.c | 2 +- kernel/bpf/verifier.c | 2 +- 3 files changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 126048110bdb..567d83bf28f9 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -506,7 +506,6 @@ enum bpf_reg_type { PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, - PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index d1447b075c73..d948b5be3bb8 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5859,7 +5859,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, return -EINVAL; } - reg->type = PTR_TO_MEM_OR_NULL; + reg->type = PTR_TO_MEM | PTR_MAYBE_NULL; reg->id = ++env->id_gen; continue; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e0a8a55ea3df..9073337ac66f 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -13578,7 +13578,7 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) mark_reg_known_zero(env, regs, i); else if (regs[i].type == SCALAR_VALUE) mark_reg_unknown(env, regs, i); - else if (regs[i].type == PTR_TO_MEM_OR_NULL) { + else if (base_type(regs[i].type) == PTR_TO_MEM) { const u32 mem_size = regs[i].mem_size; mark_reg_known_zero(env, regs, i); -- cgit v1.2.3 From 216e3cd2f28dbbf1fe86848e0e29e6693b9f0a20 Mon Sep 17 00:00:00 2001 From: Hao Luo Date: Thu, 16 Dec 2021 16:31:51 -0800 Subject: bpf: Add MEM_RDONLY for helper args that are pointers to rdonly mem. Some helper functions may modify its arguments, for example, bpf_d_path, bpf_get_stack etc. Previously, their argument types were marked as ARG_PTR_TO_MEM, which is compatible with read-only mem types, such as PTR_TO_RDONLY_BUF. Therefore it's legitimate, but technically incorrect, to modify a read-only memory by passing it into one of such helper functions. This patch tags the bpf_args compatible with immutable memory with MEM_RDONLY flag. The arguments that don't have this flag will be only compatible with mutable memory types, preventing the helper from modifying a read-only memory. The bpf_args that have MEM_RDONLY are compatible with both mutable memory and immutable memory. Signed-off-by: Hao Luo Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211217003152.48334-9-haoluo@google.com --- include/linux/bpf.h | 4 ++- kernel/bpf/btf.c | 2 +- kernel/bpf/cgroup.c | 2 +- kernel/bpf/helpers.c | 8 +++--- kernel/bpf/ringbuf.c | 2 +- kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 20 ++++++++++++--- kernel/trace/bpf_trace.c | 26 ++++++++++---------- net/core/filter.c | 64 ++++++++++++++++++++++++------------------------ 9 files changed, 73 insertions(+), 57 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 567d83bf28f9..26753139d5b4 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -311,7 +311,9 @@ enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), - /* MEM is read-only. */ + /* MEM is read-only. When applied on bpf_arg, it indicates the arg is + * compatible with both mutable and immutable memory. + */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), __BPF_TYPE_LAST_FLAG = MEM_RDONLY, diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index d948b5be3bb8..b3fddfb5bc84 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6353,7 +6353,7 @@ const struct bpf_func_proto bpf_btf_find_by_name_kind_proto = { .func = bpf_btf_find_by_name_kind, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 43eb3501721b..514b4681a90a 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1789,7 +1789,7 @@ static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6a65e2a62b01..01cfdf40c838 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -531,7 +531,7 @@ const struct bpf_func_proto bpf_strtol_proto = { .func = bpf_strtol, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, @@ -559,7 +559,7 @@ const struct bpf_func_proto bpf_strtoul_proto = { .func = bpf_strtoul, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_LONG, @@ -645,7 +645,7 @@ const struct bpf_func_proto bpf_event_output_data_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1026,7 +1026,7 @@ const struct bpf_func_proto bpf_snprintf_proto = { .arg1_type = ARG_PTR_TO_MEM_OR_NULL, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_PTR_TO_CONST_STR, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 9e0c10c6892a..638d7fd7b375 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -444,7 +444,7 @@ const struct bpf_func_proto bpf_ringbuf_output_proto = { .func = bpf_ringbuf_output, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index da07bdf71697..fa4505f9b611 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4773,7 +4773,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f49b3d334f4e..ca5cd0de804c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5113,7 +5113,6 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_VALUE, PTR_TO_MEM, PTR_TO_BUF, - PTR_TO_BUF | MEM_RDONLY, }, }; @@ -5183,6 +5182,21 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, return -EFAULT; } + /* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY + * + * Same for MAYBE_NULL: + * + * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL, + * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL + * + * Therefore we fold these flags depending on the arg_type before comparison. + */ + if (arg_type & MEM_RDONLY) + type &= ~MEM_RDONLY; + if (arg_type & PTR_MAYBE_NULL) + type &= ~PTR_MAYBE_NULL; + for (i = 0; i < ARRAY_SIZE(compatible->types); i++) { expected = compatible->types[i]; if (expected == NOT_INIT) @@ -5192,14 +5206,14 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno, goto found; } - verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, type)); + verbose(env, "R%d type=%s expected=", regno, reg_type_str(env, reg->type)); for (j = 0; j + 1 < i; j++) verbose(env, "%s, ", reg_type_str(env, compatible->types[j])); verbose(env, "%s\n", reg_type_str(env, compatible->types[j])); return -EACCES; found: - if (type == PTR_TO_BTF_ID) { + if (reg->type == PTR_TO_BTF_ID) { if (!arg_btf_id) { if (!compatible->btf_id) { verbose(env, "verifier internal error: missing arg compatible BTF ID\n"); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index cea2ca6df949..21aa30644219 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -345,7 +345,7 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -394,7 +394,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, }; @@ -450,9 +450,9 @@ static const struct bpf_func_proto bpf_trace_vprintk_proto = { .func = bpf_trace_vprintk, .gpl_only = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM, + .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -492,9 +492,9 @@ static const struct bpf_func_proto bpf_seq_printf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -509,7 +509,7 @@ static const struct bpf_func_proto bpf_seq_write_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -533,7 +533,7 @@ static const struct bpf_func_proto bpf_seq_printf_btf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, .arg1_btf_id = &btf_seq_file_ids[0], - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -694,7 +694,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1004,7 +1004,7 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -1334,7 +1334,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1556,7 +1556,7 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -1610,7 +1610,7 @@ static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; diff --git a/net/core/filter.c b/net/core/filter.c index 3f656391af7e..606ab5a98a1a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1712,7 +1712,7 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE, .arg5_type = ARG_ANYTHING, }; @@ -2017,9 +2017,9 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { .gpl_only = false, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_MEM_OR_NULL, + .arg1_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg2_type = ARG_CONST_SIZE_OR_ZERO, - .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg3_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; @@ -2540,7 +2540,7 @@ static const struct bpf_func_proto bpf_redirect_neigh_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, - .arg2_type = ARG_PTR_TO_MEM_OR_NULL, + .arg2_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE_OR_ZERO, .arg4_type = ARG_ANYTHING, }; @@ -4173,7 +4173,7 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -4187,7 +4187,7 @@ const struct bpf_func_proto bpf_skb_output_proto = { .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -4370,7 +4370,7 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_key_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; @@ -4396,7 +4396,7 @@ static const struct bpf_func_proto bpf_skb_set_tunnel_opt_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -4566,7 +4566,7 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -4580,7 +4580,7 @@ const struct bpf_func_proto bpf_xdp_output_proto = { .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; @@ -5066,7 +5066,7 @@ const struct bpf_func_proto bpf_sk_setsockopt_proto = { .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; @@ -5100,7 +5100,7 @@ static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; @@ -5134,7 +5134,7 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; @@ -5309,7 +5309,7 @@ static const struct bpf_func_proto bpf_bind_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; @@ -5897,7 +5897,7 @@ static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; @@ -5907,7 +5907,7 @@ static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; @@ -5950,7 +5950,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; @@ -6038,7 +6038,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, - .arg3_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE }; @@ -6263,7 +6263,7 @@ static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = { .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6282,7 +6282,7 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = { .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6301,7 +6301,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6338,7 +6338,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = { .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6361,7 +6361,7 @@ static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = { .pkt_access = true, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6384,7 +6384,7 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { .pkt_access = true, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6403,7 +6403,7 @@ static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_SOCK_COMMON_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6422,7 +6422,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6441,7 +6441,7 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_SOCKET_OR_NULL, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, @@ -6754,9 +6754,9 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; @@ -6823,9 +6823,9 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .pkt_access = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, - .arg4_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg5_type = ARG_CONST_SIZE, }; @@ -7054,7 +7054,7 @@ static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; -- cgit v1.2.3 From 8cbfe939abe905280279e84a297b1cb34e0d0ec9 Mon Sep 17 00:00:00 2001 From: Baowen Zheng Date: Fri, 17 Dec 2021 19:16:22 +0100 Subject: flow_offload: allow user to offload tc action to net device Use flow_indr_dev_register/flow_indr_dev_setup_offload to offload tc action. We need to call tc_cleanup_flow_action to clean up tc action entry since in tc_setup_action, some actions may hold dev refcnt, especially the mirror action. Signed-off-by: Baowen Zheng Signed-off-by: Louis Peens Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + include/net/flow_offload.h | 17 +++++++++ include/net/pkt_cls.h | 5 +++ net/core/flow_offload.c | 42 +++++++++++++++++---- net/sched/act_api.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++ net/sched/act_csum.c | 4 +- net/sched/act_ct.c | 4 +- net/sched/act_gact.c | 13 ++++++- net/sched/act_gate.c | 4 +- net/sched/act_mirred.c | 13 ++++++- net/sched/act_mpls.c | 16 +++++++- net/sched/act_police.c | 4 +- net/sched/act_sample.c | 4 +- net/sched/act_skbedit.c | 11 +++++- net/sched/act_tunnel_key.c | 9 ++++- net/sched/act_vlan.c | 16 +++++++- net/sched/cls_api.c | 21 +++++++++-- 17 files changed, 254 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index a419718612c6..8b0bdeb4734e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -920,6 +920,7 @@ enum tc_setup_type { TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, TC_SETUP_QDISC_HTB, + TC_SETUP_ACT, }; /* These structures hold the attributes of bpf state that are being passed diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 2271da5aa8ee..5b8c54eb7a6b 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -551,6 +551,23 @@ struct flow_cls_offload { u32 classid; }; +enum offload_act_command { + FLOW_ACT_REPLACE, + FLOW_ACT_DESTROY, + FLOW_ACT_STATS, +}; + +struct flow_offload_action { + struct netlink_ext_ack *extack; /* NULL in FLOW_ACT_STATS process*/ + enum offload_act_command command; + enum flow_action_id id; + u32 index; + struct flow_stats stats; + struct flow_action action; +}; + +struct flow_offload_action *offload_action_alloc(unsigned int num_actions); + static inline struct flow_rule * flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) { diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 5d4ff76d37e2..1bfb616ea759 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -262,6 +262,9 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts) for (; 0; (void)(i), (void)(a), (void)(exts)) #endif +#define tcf_act_for_each_action(i, a, actions) \ + for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++) + static inline void tcf_exts_stats_update(const struct tcf_exts *exts, u64 bytes, u64 packets, u64 drops, u64 lastuse, @@ -539,6 +542,8 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) int tc_setup_offload_action(struct flow_action *flow_action, const struct tcf_exts *exts); void tc_cleanup_offload_action(struct flow_action *flow_action); +int tc_setup_action(struct flow_action *flow_action, + struct tc_action *actions[]); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 6beaea13564a..022c945817fa 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -27,6 +27,26 @@ struct flow_rule *flow_rule_alloc(unsigned int num_actions) } EXPORT_SYMBOL(flow_rule_alloc); +struct flow_offload_action *offload_action_alloc(unsigned int num_actions) +{ + struct flow_offload_action *fl_action; + int i; + + fl_action = kzalloc(struct_size(fl_action, action.entries, num_actions), + GFP_KERNEL); + if (!fl_action) + return NULL; + + fl_action->action.num_entries = num_actions; + /* Pre-fill each action hw_stats with DONT_CARE. + * Caller can override this if it wants stats for a given action. + */ + for (i = 0; i < num_actions; i++) + fl_action->action.entries[i].hw_stats = FLOW_ACTION_HW_STATS_DONT_CARE; + + return fl_action; +} + #define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \ const struct flow_match *__m = &(__rule)->match; \ struct flow_dissector *__d = (__m)->dissector; \ @@ -549,19 +569,25 @@ int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch, void (*cleanup)(struct flow_block_cb *block_cb)) { struct flow_indr_dev *this; + u32 count = 0; + int err; mutex_lock(&flow_indr_block_lock); + if (bo) { + if (bo->command == FLOW_BLOCK_BIND) + indir_dev_add(data, dev, sch, type, cleanup, bo); + else if (bo->command == FLOW_BLOCK_UNBIND) + indir_dev_remove(data); + } - if (bo->command == FLOW_BLOCK_BIND) - indir_dev_add(data, dev, sch, type, cleanup, bo); - else if (bo->command == FLOW_BLOCK_UNBIND) - indir_dev_remove(data); - - list_for_each_entry(this, &flow_block_indr_dev_list, list) - this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup); + list_for_each_entry(this, &flow_block_indr_dev_list, list) { + err = this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup); + if (!err) + count++; + } mutex_unlock(&flow_indr_block_lock); - return list_empty(&bo->cb_list) ? -EOPNOTSUPP : 0; + return (bo && list_empty(&bo->cb_list)) ? -EOPNOTSUPP : count; } EXPORT_SYMBOL(flow_indr_dev_setup_offload); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 3258da3d5bed..5c21401b0555 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -19,8 +19,10 @@ #include #include #include +#include #include #include +#include #ifdef CONFIG_INET DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count); @@ -129,8 +131,92 @@ static void free_tcf(struct tc_action *p) kfree(p); } +static unsigned int tcf_offload_act_num_actions_single(struct tc_action *act) +{ + if (is_tcf_pedit(act)) + return tcf_pedit_nkeys(act); + else + return 1; +} + +static int offload_action_init(struct flow_offload_action *fl_action, + struct tc_action *act, + enum offload_act_command cmd, + struct netlink_ext_ack *extack) +{ + fl_action->extack = extack; + fl_action->command = cmd; + fl_action->index = act->tcfa_index; + + if (act->ops->offload_act_setup) + return act->ops->offload_act_setup(act, fl_action, NULL, false); + + return -EOPNOTSUPP; +} + +static int tcf_action_offload_cmd(struct flow_offload_action *fl_act, + struct netlink_ext_ack *extack) +{ + int err; + + err = flow_indr_dev_setup_offload(NULL, NULL, TC_SETUP_ACT, + fl_act, NULL, NULL); + if (err < 0) + return err; + + return 0; +} + +/* offload the tc action after it is inserted */ +static int tcf_action_offload_add(struct tc_action *action, + struct netlink_ext_ack *extack) +{ + struct tc_action *actions[TCA_ACT_MAX_PRIO] = { + [0] = action, + }; + struct flow_offload_action *fl_action; + int num, err = 0; + + num = tcf_offload_act_num_actions_single(action); + fl_action = offload_action_alloc(num); + if (!fl_action) + return -ENOMEM; + + err = offload_action_init(fl_action, action, FLOW_ACT_REPLACE, extack); + if (err) + goto fl_err; + + err = tc_setup_action(&fl_action->action, actions); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Failed to setup tc actions for offload\n"); + goto fl_err; + } + + err = tcf_action_offload_cmd(fl_action, extack); + tc_cleanup_offload_action(&fl_action->action); + +fl_err: + kfree(fl_action); + + return err; +} + +static int tcf_action_offload_del(struct tc_action *action) +{ + struct flow_offload_action fl_act = {}; + int err = 0; + + err = offload_action_init(&fl_act, action, FLOW_ACT_DESTROY, NULL); + if (err) + return err; + + return tcf_action_offload_cmd(&fl_act, NULL); +} + static void tcf_action_cleanup(struct tc_action *p) { + tcf_action_offload_del(p); if (p->ops->cleanup) p->ops->cleanup(p); @@ -1061,6 +1147,11 @@ err_out: return ERR_PTR(err); } +static bool tc_act_bind(u32 flags) +{ + return !!(flags & TCA_ACT_FLAGS_BIND); +} + /* Returns numbers of initialized actions or negative error. */ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, @@ -1103,6 +1194,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, sz += tcf_action_fill_size(act); /* Start from index 0 */ actions[i - 1] = act; + if (!tc_act_bind(flags)) + tcf_action_offload_add(act, extack); } /* We have to commit them all together, because if any error happened in diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 4428852a03d7..e0f515b774ca 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -705,7 +705,9 @@ static int tcf_csum_offload_act_setup(struct tc_action *act, void *entry_data, entry->csum_flags = tcf_csum_update_flags(act); *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_CSUM; } return 0; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index dc64f31e5191..1c537913a189 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1505,7 +1505,9 @@ static int tcf_ct_offload_act_setup(struct tc_action *act, void *entry_data, entry->ct.flow_table = tcf_ct_ft(act); *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_CT; } return 0; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index f77be22069f4..bde6a6c01e64 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -272,7 +272,18 @@ static int tcf_gact_offload_act_setup(struct tc_action *act, void *entry_data, } *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_gact_ok(act)) + fl_action->id = FLOW_ACTION_ACCEPT; + else if (is_tcf_gact_shot(act)) + fl_action->id = FLOW_ACTION_DROP; + else if (is_tcf_gact_trap(act)) + fl_action->id = FLOW_ACTION_TRAP; + else if (is_tcf_gact_goto_chain(act)) + fl_action->id = FLOW_ACTION_GOTO; + else + return -EOPNOTSUPP; } return 0; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 1d8297497692..d56e73843a4b 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -637,7 +637,9 @@ static int tcf_gate_offload_act_setup(struct tc_action *act, void *entry_data, return err; *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_GATE; } return 0; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 8eecf55be0a2..39acd1d18609 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -482,7 +482,18 @@ static int tcf_mirred_offload_act_setup(struct tc_action *act, void *entry_data, } *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_mirred_egress_redirect(act)) + fl_action->id = FLOW_ACTION_REDIRECT; + else if (is_tcf_mirred_egress_mirror(act)) + fl_action->id = FLOW_ACTION_MIRRED; + else if (is_tcf_mirred_ingress_redirect(act)) + fl_action->id = FLOW_ACTION_REDIRECT_INGRESS; + else if (is_tcf_mirred_ingress_mirror(act)) + fl_action->id = FLOW_ACTION_MIRRED_INGRESS; + else + return -EOPNOTSUPP; } return 0; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index a4615e1331e0..b9ff3459fdab 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -415,7 +415,21 @@ static int tcf_mpls_offload_act_setup(struct tc_action *act, void *entry_data, } *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + switch (tcf_mpls_action(act)) { + case TCA_MPLS_ACT_PUSH: + fl_action->id = FLOW_ACTION_MPLS_PUSH; + break; + case TCA_MPLS_ACT_POP: + fl_action->id = FLOW_ACTION_MPLS_POP; + break; + case TCA_MPLS_ACT_MODIFY: + fl_action->id = FLOW_ACTION_MPLS_MANGLE; + break; + default: + return -EOPNOTSUPP; + } } return 0; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index abb6d16a20b2..0923aa2b8f8a 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -421,7 +421,9 @@ static int tcf_police_offload_act_setup(struct tc_action *act, void *entry_data, entry->police.mtu = tcf_police_tcfp_mtu(act); *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_POLICE; } return 0; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 07e56903211e..9a22cdda6bbd 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -303,7 +303,9 @@ static int tcf_sample_offload_act_setup(struct tc_action *act, void *entry_data, tcf_offload_sample_get_group(entry, act); *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + fl_action->id = FLOW_ACTION_SAMPLE; } return 0; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index c380f9e6cc95..ceba11b198bb 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -347,7 +347,16 @@ static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data } *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_skbedit_mark(act)) + fl_action->id = FLOW_ACTION_MARK; + else if (is_tcf_skbedit_ptype(act)) + fl_action->id = FLOW_ACTION_PTYPE; + else if (is_tcf_skbedit_priority(act)) + fl_action->id = FLOW_ACTION_PRIORITY; + else + return -EOPNOTSUPP; } return 0; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index e96a65a5323e..23aba03d26a8 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -827,7 +827,14 @@ static int tcf_tunnel_key_offload_act_setup(struct tc_action *act, } *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + if (is_tcf_tunnel_set(act)) + fl_action->id = FLOW_ACTION_TUNNEL_ENCAP; + else if (is_tcf_tunnel_release(act)) + fl_action->id = FLOW_ACTION_TUNNEL_DECAP; + else + return -EOPNOTSUPP; } return 0; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 0300792084f0..756e2dcde1cd 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -395,7 +395,21 @@ static int tcf_vlan_offload_act_setup(struct tc_action *act, void *entry_data, } *index_inc = 1; } else { - return -EOPNOTSUPP; + struct flow_offload_action *fl_action = entry_data; + + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + fl_action->id = FLOW_ACTION_VLAN_PUSH; + break; + case TCA_VLAN_ACT_POP: + fl_action->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + fl_action->id = FLOW_ACTION_VLAN_MANGLE; + break; + default: + return -EOPNOTSUPP; + } } return 0; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 53f263c9a725..353e1eed48be 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3488,8 +3488,8 @@ static int tc_setup_offload_act(struct tc_action *act, #endif } -int tc_setup_offload_action(struct flow_action *flow_action, - const struct tcf_exts *exts) +int tc_setup_action(struct flow_action *flow_action, + struct tc_action *actions[]) { int i, j, index, err = 0; struct tc_action *act; @@ -3498,11 +3498,11 @@ int tc_setup_offload_action(struct flow_action *flow_action, BUILD_BUG_ON(TCA_ACT_HW_STATS_IMMEDIATE != FLOW_ACTION_HW_STATS_IMMEDIATE); BUILD_BUG_ON(TCA_ACT_HW_STATS_DELAYED != FLOW_ACTION_HW_STATS_DELAYED); - if (!exts) + if (!actions) return 0; j = 0; - tcf_exts_for_each_action(i, act, exts) { + tcf_act_for_each_action(i, act, actions) { struct flow_action_entry *entry; entry = &flow_action->entries[j]; @@ -3531,6 +3531,19 @@ err_out_locked: spin_unlock_bh(&act->tcfa_lock); goto err_out; } + +int tc_setup_offload_action(struct flow_action *flow_action, + const struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + if (!exts) + return 0; + + return tc_setup_action(flow_action, exts->actions); +#else + return 0; +#endif +} EXPORT_SYMBOL(tc_setup_offload_action); unsigned int tcf_exts_num_actions(struct tcf_exts *exts) -- cgit v1.2.3 From 7d4203c13435c0bdae61bf16bbd0408d5b958ade Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Thu, 25 Nov 2021 18:15:37 +0100 Subject: mm: add virt_to_folio() and folio_address() These two wrappers around their respective struct page variants will be useful in the following patches. Signed-off-by: Vlastimil Babka Acked-by: Johannes Weiner Reviewed-by: Roman Gushchin --- include/linux/mm.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..4a6cf22483da 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -863,6 +863,13 @@ static inline struct page *virt_to_head_page(const void *x) return compound_head(page); } +static inline struct folio *virt_to_folio(const void *x) +{ + struct page *page = virt_to_page(x); + + return page_folio(page); +} + void __put_page(struct page *page); void put_pages_list(struct list_head *pages); @@ -1753,6 +1760,11 @@ void page_address_init(void); #define page_address_init() do { } while(0) #endif +static inline void *folio_address(const struct folio *folio) +{ + return page_address(&folio->page); +} + extern void *page_rmapping(struct page *page); extern struct anon_vma *page_anon_vma(struct page *page); extern pgoff_t __page_file_index(struct page *page); -- cgit v1.2.3 From d5c383f2c98ac58c210b266cdaf7b86bc32d1ad1 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 17 Dec 2021 15:30:56 +0000 Subject: iommu/iova: Squash entry_dtor abstraction All flush queues are driven by iommu-dma now, so there is no need to abstract entry_dtor or its data any more. Squash the now-canonical implementation directly into the IOVA code to get it out of the way. Reviewed-by: John Garry Reviewed-by: Christoph Hellwig Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/2260f8de00ab5e0f9d2a1cf8978e6ae7cd4f182c.1639753638.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 17 ++--------------- drivers/iommu/iova.c | 28 +++++++++++++++------------- include/linux/iova.h | 26 +++----------------------- 3 files changed, 20 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 84dee53fe892..6691f3cd768f 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -64,18 +64,6 @@ static int __init iommu_dma_forcedac_setup(char *str) } early_param("iommu.forcedac", iommu_dma_forcedac_setup); -static void iommu_dma_entry_dtor(unsigned long data) -{ - struct page *freelist = (struct page *)data; - - while (freelist) { - unsigned long p = (unsigned long)page_address(freelist); - - freelist = freelist->freelist; - free_page(p); - } -} - static inline size_t cookie_msi_granule(struct iommu_dma_cookie *cookie) { if (cookie->type == IOMMU_DMA_IOVA_COOKIE) @@ -324,8 +312,7 @@ int iommu_dma_init_fq(struct iommu_domain *domain) if (cookie->fq_domain) return 0; - ret = init_iova_flush_queue(&cookie->iovad, iommu_dma_flush_iotlb_all, - iommu_dma_entry_dtor); + ret = init_iova_flush_queue(&cookie->iovad, iommu_dma_flush_iotlb_all); if (ret) { pr_warn("iova flush queue initialization failed\n"); return ret; @@ -471,7 +458,7 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, else if (gather && gather->queued) queue_iova(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad), - (unsigned long)gather->freelist); + gather->freelist); else free_iova_fast(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad)); diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 670211e41771..541857ca4fd5 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -91,11 +91,9 @@ static void free_iova_flush_queue(struct iova_domain *iovad) iovad->fq = NULL; iovad->flush_cb = NULL; - iovad->entry_dtor = NULL; } -int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, iova_entry_dtor entry_dtor) +int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb) { struct iova_fq __percpu *queue; int cpu; @@ -108,7 +106,6 @@ int init_iova_flush_queue(struct iova_domain *iovad, return -ENOMEM; iovad->flush_cb = flush_cb; - iovad->entry_dtor = entry_dtor; for_each_possible_cpu(cpu) { struct iova_fq *fq; @@ -547,6 +544,16 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size) } EXPORT_SYMBOL_GPL(free_iova_fast); +static void fq_entry_dtor(struct page *freelist) +{ + while (freelist) { + unsigned long p = (unsigned long)page_address(freelist); + + freelist = freelist->freelist; + free_page(p); + } +} + #define fq_ring_for_each(i, fq) \ for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE) @@ -579,9 +586,7 @@ static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq) if (fq->entries[idx].counter >= counter) break; - if (iovad->entry_dtor) - iovad->entry_dtor(fq->entries[idx].data); - + fq_entry_dtor(fq->entries[idx].freelist); free_iova_fast(iovad, fq->entries[idx].iova_pfn, fq->entries[idx].pages); @@ -606,15 +611,12 @@ static void fq_destroy_all_entries(struct iova_domain *iovad) * bother to free iovas, just call the entry_dtor on all remaining * entries. */ - if (!iovad->entry_dtor) - return; - for_each_possible_cpu(cpu) { struct iova_fq *fq = per_cpu_ptr(iovad->fq, cpu); int idx; fq_ring_for_each(idx, fq) - iovad->entry_dtor(fq->entries[idx].data); + fq_entry_dtor(fq->entries[idx].freelist); } } @@ -639,7 +641,7 @@ static void fq_flush_timeout(struct timer_list *t) void queue_iova(struct iova_domain *iovad, unsigned long pfn, unsigned long pages, - unsigned long data) + struct page *freelist) { struct iova_fq *fq; unsigned long flags; @@ -673,7 +675,7 @@ void queue_iova(struct iova_domain *iovad, fq->entries[idx].iova_pfn = pfn; fq->entries[idx].pages = pages; - fq->entries[idx].data = data; + fq->entries[idx].freelist = freelist; fq->entries[idx].counter = atomic64_read(&iovad->fq_flush_start_cnt); spin_unlock_irqrestore(&fq->lock, flags); diff --git a/include/linux/iova.h b/include/linux/iova.h index 71d8a2de6635..e746d8e41449 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -40,9 +40,6 @@ struct iova_domain; /* Call-Back from IOVA code into IOMMU drivers */ typedef void (* iova_flush_cb)(struct iova_domain *domain); -/* Destructor for per-entry data */ -typedef void (* iova_entry_dtor)(unsigned long data); - /* Number of entries per Flush Queue */ #define IOVA_FQ_SIZE 256 @@ -53,7 +50,7 @@ typedef void (* iova_entry_dtor)(unsigned long data); struct iova_fq_entry { unsigned long iova_pfn; unsigned long pages; - unsigned long data; + struct page *freelist; u64 counter; /* Flush counter when this entrie was added */ }; @@ -88,9 +85,6 @@ struct iova_domain { iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU TLBs */ - iova_entry_dtor entry_dtor; /* IOMMU driver specific destructor for - iova entry */ - struct timer_list fq_timer; /* Timer to regularily empty the flush-queues */ atomic_t fq_timer_on; /* 1 when timer is active, 0 @@ -146,15 +140,14 @@ void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); void queue_iova(struct iova_domain *iovad, unsigned long pfn, unsigned long pages, - unsigned long data); + struct page *freelist); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, iova_entry_dtor entry_dtor); +int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else @@ -189,12 +182,6 @@ static inline void free_iova_fast(struct iova_domain *iovad, { } -static inline void queue_iova(struct iova_domain *iovad, - unsigned long pfn, unsigned long pages, - unsigned long data) -{ -} - static inline unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, @@ -216,13 +203,6 @@ static inline void init_iova_domain(struct iova_domain *iovad, { } -static inline int init_iova_flush_queue(struct iova_domain *iovad, - iova_flush_cb flush_cb, - iova_entry_dtor entry_dtor) -{ - return -ENODEV; -} - static inline struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn) { -- cgit v1.2.3 From 649ad9835a3783bcb6c69368fa939e0010abb2c6 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 17 Dec 2021 15:30:57 +0000 Subject: iommu/iova: Squash flush_cb abstraction Once again, with iommu-dma now being the only flush queue user, we no longer need the extra level of indirection through flush_cb. Squash that and let the flush queue code call the domain method directly. This does mean temporarily having to carry an additional copy of the IOMMU domain pointer around instead, but only until a later patch untangles it again. Reviewed-by: John Garry Reviewed-by: Christoph Hellwig Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/e3f9b4acdd6640012ef4fbc819ac868d727b64a9.1639753638.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 13 +------------ drivers/iommu/iova.c | 11 +++++------ include/linux/iova.h | 11 +++-------- 3 files changed, 9 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 6691f3cd768f..c63d93581a4e 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -282,17 +282,6 @@ static int iova_reserve_iommu_regions(struct device *dev, return ret; } -static void iommu_dma_flush_iotlb_all(struct iova_domain *iovad) -{ - struct iommu_dma_cookie *cookie; - struct iommu_domain *domain; - - cookie = container_of(iovad, struct iommu_dma_cookie, iovad); - domain = cookie->fq_domain; - - domain->ops->flush_iotlb_all(domain); -} - static bool dev_is_untrusted(struct device *dev) { return dev_is_pci(dev) && to_pci_dev(dev)->untrusted; @@ -312,7 +301,7 @@ int iommu_dma_init_fq(struct iommu_domain *domain) if (cookie->fq_domain) return 0; - ret = init_iova_flush_queue(&cookie->iovad, iommu_dma_flush_iotlb_all); + ret = init_iova_flush_queue(&cookie->iovad, domain); if (ret) { pr_warn("iova flush queue initialization failed\n"); return ret; diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 541857ca4fd5..bbf642940988 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -63,7 +63,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, iovad->start_pfn = start_pfn; iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad)); iovad->max32_alloc_size = iovad->dma_32bit_pfn; - iovad->flush_cb = NULL; + iovad->fq_domain = NULL; iovad->fq = NULL; iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR; rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node); @@ -90,10 +90,10 @@ static void free_iova_flush_queue(struct iova_domain *iovad) free_percpu(iovad->fq); iovad->fq = NULL; - iovad->flush_cb = NULL; + iovad->fq_domain = NULL; } -int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb) +int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_domain) { struct iova_fq __percpu *queue; int cpu; @@ -105,8 +105,6 @@ int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb) if (!queue) return -ENOMEM; - iovad->flush_cb = flush_cb; - for_each_possible_cpu(cpu) { struct iova_fq *fq; @@ -117,6 +115,7 @@ int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb) spin_lock_init(&fq->lock); } + iovad->fq_domain = fq_domain; iovad->fq = queue; timer_setup(&iovad->fq_timer, fq_flush_timeout, 0); @@ -598,7 +597,7 @@ static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq) static void iova_domain_flush(struct iova_domain *iovad) { atomic64_inc(&iovad->fq_flush_start_cnt); - iovad->flush_cb(iovad); + iovad->fq_domain->ops->flush_iotlb_all(iovad->fq_domain); atomic64_inc(&iovad->fq_flush_finish_cnt); } diff --git a/include/linux/iova.h b/include/linux/iova.h index e746d8e41449..99be4fcea4f3 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -14,6 +14,7 @@ #include #include #include +#include /* iova structure */ struct iova { @@ -35,11 +36,6 @@ struct iova_rcache { struct iova_cpu_rcache __percpu *cpu_rcaches; }; -struct iova_domain; - -/* Call-Back from IOVA code into IOMMU drivers */ -typedef void (* iova_flush_cb)(struct iova_domain *domain); - /* Number of entries per Flush Queue */ #define IOVA_FQ_SIZE 256 @@ -82,8 +78,7 @@ struct iova_domain { struct iova anchor; /* rbtree lookup anchor */ struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ - iova_flush_cb flush_cb; /* Call-Back function to flush IOMMU - TLBs */ + struct iommu_domain *fq_domain; struct timer_list fq_timer; /* Timer to regularily empty the flush-queues */ @@ -147,7 +142,7 @@ struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -int init_iova_flush_queue(struct iova_domain *iovad, iova_flush_cb flush_cb); +int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_domain); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else -- cgit v1.2.3 From 87f60cc65d24939353b40aa1d9297fea080cdf8d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 17 Dec 2021 15:31:00 +0000 Subject: iommu/vt-d: Use put_pages_list page->freelist is for the use of slab. We already have the ability to free a list of pages in the core mm, but it requires the use of a list_head and for the pages to be chained together through page->lru. Switch the Intel IOMMU and IOVA code over to using free_pages_list(). Signed-off-by: Matthew Wilcox (Oracle) [rm: split from original patch, cosmetic tweaks, fix fq entries] Signed-off-by: Robin Murphy Reviewed-by: Lu Baolu Link: https://lore.kernel.org/r/2115b560d9a0ce7cd4b948bd51a2b7bde8fdfd59.1639753638.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 2 +- drivers/iommu/intel/iommu.c | 89 ++++++++++++++++----------------------------- drivers/iommu/iova.c | 26 +++++-------- include/linux/iommu.h | 3 +- include/linux/iova.h | 4 +- 5 files changed, 45 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index c63d93581a4e..ccacd0f71443 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -447,7 +447,7 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, else if (gather && gather->queued) queue_iova(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad), - gather->freelist); + &gather->freelist); else free_iova_fast(iovad, iova_pfn(iovad, iova), size >> iova_shift(iovad)); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index b6a8f3282411..17b3d97111f3 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -1303,35 +1303,30 @@ static void dma_pte_free_pagetable(struct dmar_domain *domain, know the hardware page-walk will no longer touch them. The 'pte' argument is the *parent* PTE, pointing to the page that is to be freed. */ -static struct page *dma_pte_list_pagetables(struct dmar_domain *domain, - int level, struct dma_pte *pte, - struct page *freelist) +static void dma_pte_list_pagetables(struct dmar_domain *domain, + int level, struct dma_pte *pte, + struct list_head *freelist) { struct page *pg; pg = pfn_to_page(dma_pte_addr(pte) >> PAGE_SHIFT); - pg->freelist = freelist; - freelist = pg; + list_add_tail(&pg->lru, freelist); if (level == 1) - return freelist; + return; pte = page_address(pg); do { if (dma_pte_present(pte) && !dma_pte_superpage(pte)) - freelist = dma_pte_list_pagetables(domain, level - 1, - pte, freelist); + dma_pte_list_pagetables(domain, level - 1, pte, freelist); pte++; } while (!first_pte_in_page(pte)); - - return freelist; } -static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level, - struct dma_pte *pte, unsigned long pfn, - unsigned long start_pfn, - unsigned long last_pfn, - struct page *freelist) +static void dma_pte_clear_level(struct dmar_domain *domain, int level, + struct dma_pte *pte, unsigned long pfn, + unsigned long start_pfn, unsigned long last_pfn, + struct list_head *freelist) { struct dma_pte *first_pte = NULL, *last_pte = NULL; @@ -1350,7 +1345,7 @@ static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level, /* These suborbinate page tables are going away entirely. Don't bother to clear them; we're just going to *free* them. */ if (level > 1 && !dma_pte_superpage(pte)) - freelist = dma_pte_list_pagetables(domain, level - 1, pte, freelist); + dma_pte_list_pagetables(domain, level - 1, pte, freelist); dma_clear_pte(pte); if (!first_pte) @@ -1358,10 +1353,10 @@ static struct page *dma_pte_clear_level(struct dmar_domain *domain, int level, last_pte = pte; } else if (level > 1) { /* Recurse down into a level that isn't *entirely* obsolete */ - freelist = dma_pte_clear_level(domain, level - 1, - phys_to_virt(dma_pte_addr(pte)), - level_pfn, start_pfn, last_pfn, - freelist); + dma_pte_clear_level(domain, level - 1, + phys_to_virt(dma_pte_addr(pte)), + level_pfn, start_pfn, last_pfn, + freelist); } next: pfn = level_pfn + level_size(level); @@ -1370,47 +1365,28 @@ next: if (first_pte) domain_flush_cache(domain, first_pte, (void *)++last_pte - (void *)first_pte); - - return freelist; } /* We can't just free the pages because the IOMMU may still be walking the page tables, and may have cached the intermediate levels. The pages can only be freed after the IOTLB flush has been done. */ -static struct page *domain_unmap(struct dmar_domain *domain, - unsigned long start_pfn, - unsigned long last_pfn, - struct page *freelist) +static void domain_unmap(struct dmar_domain *domain, unsigned long start_pfn, + unsigned long last_pfn, struct list_head *freelist) { BUG_ON(!domain_pfn_supported(domain, start_pfn)); BUG_ON(!domain_pfn_supported(domain, last_pfn)); BUG_ON(start_pfn > last_pfn); /* we don't need lock here; nobody else touches the iova range */ - freelist = dma_pte_clear_level(domain, agaw_to_level(domain->agaw), - domain->pgd, 0, start_pfn, last_pfn, - freelist); + dma_pte_clear_level(domain, agaw_to_level(domain->agaw), + domain->pgd, 0, start_pfn, last_pfn, freelist); /* free pgd */ if (start_pfn == 0 && last_pfn == DOMAIN_MAX_PFN(domain->gaw)) { struct page *pgd_page = virt_to_page(domain->pgd); - pgd_page->freelist = freelist; - freelist = pgd_page; - + list_add_tail(&pgd_page->lru, freelist); domain->pgd = NULL; } - - return freelist; -} - -static void dma_free_pagelist(struct page *freelist) -{ - struct page *pg; - - while ((pg = freelist)) { - freelist = pg->freelist; - free_pgtable_page(page_address(pg)); - } } /* iommu handling */ @@ -2095,11 +2071,10 @@ static void domain_exit(struct dmar_domain *domain) domain_remove_dev_info(domain); if (domain->pgd) { - struct page *freelist; + LIST_HEAD(freelist); - freelist = domain_unmap(domain, 0, - DOMAIN_MAX_PFN(domain->gaw), NULL); - dma_free_pagelist(freelist); + domain_unmap(domain, 0, DOMAIN_MAX_PFN(domain->gaw), &freelist); + put_pages_list(&freelist); } free_domain_mem(domain); @@ -4192,19 +4167,17 @@ static int intel_iommu_memory_notifier(struct notifier_block *nb, { struct dmar_drhd_unit *drhd; struct intel_iommu *iommu; - struct page *freelist; + LIST_HEAD(freelist); - freelist = domain_unmap(si_domain, - start_vpfn, last_vpfn, - NULL); + domain_unmap(si_domain, start_vpfn, last_vpfn, &freelist); rcu_read_lock(); for_each_active_iommu(iommu, drhd) iommu_flush_iotlb_psi(iommu, si_domain, start_vpfn, mhp->nr_pages, - !freelist, 0); + list_empty(&freelist), 0); rcu_read_unlock(); - dma_free_pagelist(freelist); + put_pages_list(&freelist); } break; } @@ -5211,8 +5184,7 @@ static size_t intel_iommu_unmap(struct iommu_domain *domain, start_pfn = iova >> VTD_PAGE_SHIFT; last_pfn = (iova + size - 1) >> VTD_PAGE_SHIFT; - gather->freelist = domain_unmap(dmar_domain, start_pfn, - last_pfn, gather->freelist); + domain_unmap(dmar_domain, start_pfn, last_pfn, &gather->freelist); if (dmar_domain->max_addr == iova + size) dmar_domain->max_addr = iova; @@ -5248,9 +5220,10 @@ static void intel_iommu_tlb_sync(struct iommu_domain *domain, for_each_domain_iommu(iommu_id, dmar_domain) iommu_flush_iotlb_psi(g_iommus[iommu_id], dmar_domain, - start_pfn, nrpages, !gather->freelist, 0); + start_pfn, nrpages, + list_empty(&gather->freelist), 0); - dma_free_pagelist(gather->freelist); + put_pages_list(&gather->freelist); } static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain, diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index bbf642940988..962614c7afbb 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -96,7 +96,7 @@ static void free_iova_flush_queue(struct iova_domain *iovad) int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_domain) { struct iova_fq __percpu *queue; - int cpu; + int i, cpu; atomic64_set(&iovad->fq_flush_start_cnt, 0); atomic64_set(&iovad->fq_flush_finish_cnt, 0); @@ -113,6 +113,9 @@ int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_dom fq->tail = 0; spin_lock_init(&fq->lock); + + for (i = 0; i < IOVA_FQ_SIZE; i++) + INIT_LIST_HEAD(&fq->entries[i].freelist); } iovad->fq_domain = fq_domain; @@ -543,16 +546,6 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size) } EXPORT_SYMBOL_GPL(free_iova_fast); -static void fq_entry_dtor(struct page *freelist) -{ - while (freelist) { - unsigned long p = (unsigned long)page_address(freelist); - - freelist = freelist->freelist; - free_page(p); - } -} - #define fq_ring_for_each(i, fq) \ for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE) @@ -585,7 +578,7 @@ static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq) if (fq->entries[idx].counter >= counter) break; - fq_entry_dtor(fq->entries[idx].freelist); + put_pages_list(&fq->entries[idx].freelist); free_iova_fast(iovad, fq->entries[idx].iova_pfn, fq->entries[idx].pages); @@ -607,15 +600,14 @@ static void fq_destroy_all_entries(struct iova_domain *iovad) /* * This code runs when the iova_domain is being detroyed, so don't - * bother to free iovas, just call the entry_dtor on all remaining - * entries. + * bother to free iovas, just free any remaining pagetable pages. */ for_each_possible_cpu(cpu) { struct iova_fq *fq = per_cpu_ptr(iovad->fq, cpu); int idx; fq_ring_for_each(idx, fq) - fq_entry_dtor(fq->entries[idx].freelist); + put_pages_list(&fq->entries[idx].freelist); } } @@ -640,7 +632,7 @@ static void fq_flush_timeout(struct timer_list *t) void queue_iova(struct iova_domain *iovad, unsigned long pfn, unsigned long pages, - struct page *freelist) + struct list_head *freelist) { struct iova_fq *fq; unsigned long flags; @@ -674,8 +666,8 @@ void queue_iova(struct iova_domain *iovad, fq->entries[idx].iova_pfn = pfn; fq->entries[idx].pages = pages; - fq->entries[idx].freelist = freelist; fq->entries[idx].counter = atomic64_read(&iovad->fq_flush_start_cnt); + list_splice(freelist, &fq->entries[idx].freelist); spin_unlock_irqrestore(&fq->lock, flags); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index d2f3435e7d17..de0c57a567c8 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -186,7 +186,7 @@ struct iommu_iotlb_gather { unsigned long start; unsigned long end; size_t pgsize; - struct page *freelist; + struct list_head freelist; bool queued; }; @@ -399,6 +399,7 @@ static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather) { *gather = (struct iommu_iotlb_gather) { .start = ULONG_MAX, + .freelist = LIST_HEAD_INIT(gather->freelist), }; } diff --git a/include/linux/iova.h b/include/linux/iova.h index 99be4fcea4f3..072a09c06e8a 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -46,7 +46,7 @@ struct iova_rcache { struct iova_fq_entry { unsigned long iova_pfn; unsigned long pages; - struct page *freelist; + struct list_head freelist; u64 counter; /* Flush counter when this entrie was added */ }; @@ -135,7 +135,7 @@ void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); void queue_iova(struct iova_domain *iovad, unsigned long pfn, unsigned long pages, - struct page *freelist); + struct list_head *freelist); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, -- cgit v1.2.3 From a17e3026bc4da9135ca9a42ec0b1fa67f95172e3 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Fri, 17 Dec 2021 15:31:03 +0000 Subject: iommu: Move flush queue data into iommu_dma_cookie Complete the move into iommu-dma by refactoring the flush queues themselves to belong to the DMA cookie rather than the IOVA domain. The refactoring may as well extend to some minor cosmetic aspects too, to help us stay one step ahead of the style police. Signed-off-by: Robin Murphy Link: https://lore.kernel.org/r/24304722005bc6f144e2a1fdd865d1465722fc2e.1639753638.git.robin.murphy@arm.com Signed-off-by: Joerg Roedel --- drivers/iommu/dma-iommu.c | 171 +++++++++++++++++++++++++--------------------- drivers/iommu/iova.c | 2 - include/linux/iova.h | 44 +----------- 3 files changed, 95 insertions(+), 122 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 96057bec4164..d85d54f2b549 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -9,9 +9,12 @@ */ #include +#include +#include #include -#include +#include #include +#include #include #include #include @@ -20,11 +23,10 @@ #include #include #include -#include #include +#include +#include #include -#include -#include struct iommu_dma_msi_page { struct list_head list; @@ -41,7 +43,19 @@ struct iommu_dma_cookie { enum iommu_dma_cookie_type type; union { /* Full allocator for IOMMU_DMA_IOVA_COOKIE */ - struct iova_domain iovad; + struct { + struct iova_domain iovad; + + struct iova_fq __percpu *fq; /* Flush queue */ + /* Number of TLB flushes that have been started */ + atomic64_t fq_flush_start_cnt; + /* Number of TLB flushes that have been finished */ + atomic64_t fq_flush_finish_cnt; + /* Timer to regularily empty the flush queues */ + struct timer_list fq_timer; + /* 1 when timer is active, 0 when not */ + atomic_t fq_timer_on; + }; /* Trivial linear page allocator for IOMMU_DMA_MSI_COOKIE */ dma_addr_t msi_iova; }; @@ -64,6 +78,27 @@ static int __init iommu_dma_forcedac_setup(char *str) } early_param("iommu.forcedac", iommu_dma_forcedac_setup); +/* Number of entries per flush queue */ +#define IOVA_FQ_SIZE 256 + +/* Timeout (in ms) after which entries are flushed from the queue */ +#define IOVA_FQ_TIMEOUT 10 + +/* Flush queue entry for deferred flushing */ +struct iova_fq_entry { + unsigned long iova_pfn; + unsigned long pages; + struct list_head freelist; + u64 counter; /* Flush counter when this entry was added */ +}; + +/* Per-CPU flush queue structure */ +struct iova_fq { + struct iova_fq_entry entries[IOVA_FQ_SIZE]; + unsigned int head, tail; + spinlock_t lock; +}; + #define fq_ring_for_each(i, fq) \ for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE) @@ -73,9 +108,9 @@ static inline bool fq_full(struct iova_fq *fq) return (((fq->tail + 1) % IOVA_FQ_SIZE) == fq->head); } -static inline unsigned fq_ring_add(struct iova_fq *fq) +static inline unsigned int fq_ring_add(struct iova_fq *fq) { - unsigned idx = fq->tail; + unsigned int idx = fq->tail; assert_spin_locked(&fq->lock); @@ -84,10 +119,10 @@ static inline unsigned fq_ring_add(struct iova_fq *fq) return idx; } -static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq) +static void fq_ring_free(struct iommu_dma_cookie *cookie, struct iova_fq *fq) { - u64 counter = atomic64_read(&iovad->fq_flush_finish_cnt); - unsigned idx; + u64 counter = atomic64_read(&cookie->fq_flush_finish_cnt); + unsigned int idx; assert_spin_locked(&fq->lock); @@ -97,7 +132,7 @@ static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq) break; put_pages_list(&fq->entries[idx].freelist); - free_iova_fast(iovad, + free_iova_fast(&cookie->iovad, fq->entries[idx].iova_pfn, fq->entries[idx].pages); @@ -105,50 +140,50 @@ static void fq_ring_free(struct iova_domain *iovad, struct iova_fq *fq) } } -static void iova_domain_flush(struct iova_domain *iovad) +static void fq_flush_iotlb(struct iommu_dma_cookie *cookie) { - atomic64_inc(&iovad->fq_flush_start_cnt); - iovad->fq_domain->ops->flush_iotlb_all(iovad->fq_domain); - atomic64_inc(&iovad->fq_flush_finish_cnt); + atomic64_inc(&cookie->fq_flush_start_cnt); + cookie->fq_domain->ops->flush_iotlb_all(cookie->fq_domain); + atomic64_inc(&cookie->fq_flush_finish_cnt); } static void fq_flush_timeout(struct timer_list *t) { - struct iova_domain *iovad = from_timer(iovad, t, fq_timer); + struct iommu_dma_cookie *cookie = from_timer(cookie, t, fq_timer); int cpu; - atomic_set(&iovad->fq_timer_on, 0); - iova_domain_flush(iovad); + atomic_set(&cookie->fq_timer_on, 0); + fq_flush_iotlb(cookie); for_each_possible_cpu(cpu) { unsigned long flags; struct iova_fq *fq; - fq = per_cpu_ptr(iovad->fq, cpu); + fq = per_cpu_ptr(cookie->fq, cpu); spin_lock_irqsave(&fq->lock, flags); - fq_ring_free(iovad, fq); + fq_ring_free(cookie, fq); spin_unlock_irqrestore(&fq->lock, flags); } } -void queue_iova(struct iova_domain *iovad, +static void queue_iova(struct iommu_dma_cookie *cookie, unsigned long pfn, unsigned long pages, struct list_head *freelist) { struct iova_fq *fq; unsigned long flags; - unsigned idx; + unsigned int idx; /* * Order against the IOMMU driver's pagetable update from unmapping - * @pte, to guarantee that iova_domain_flush() observes that if called + * @pte, to guarantee that fq_flush_iotlb() observes that if called * from a different CPU before we release the lock below. Full barrier * so it also pairs with iommu_dma_init_fq() to avoid seeing partially * written fq state here. */ smp_mb(); - fq = raw_cpu_ptr(iovad->fq); + fq = raw_cpu_ptr(cookie->fq); spin_lock_irqsave(&fq->lock, flags); /* @@ -156,65 +191,66 @@ void queue_iova(struct iova_domain *iovad, * flushed out on another CPU. This makes the fq_full() check below less * likely to be true. */ - fq_ring_free(iovad, fq); + fq_ring_free(cookie, fq); if (fq_full(fq)) { - iova_domain_flush(iovad); - fq_ring_free(iovad, fq); + fq_flush_iotlb(cookie); + fq_ring_free(cookie, fq); } idx = fq_ring_add(fq); fq->entries[idx].iova_pfn = pfn; fq->entries[idx].pages = pages; - fq->entries[idx].counter = atomic64_read(&iovad->fq_flush_start_cnt); + fq->entries[idx].counter = atomic64_read(&cookie->fq_flush_start_cnt); list_splice(freelist, &fq->entries[idx].freelist); spin_unlock_irqrestore(&fq->lock, flags); /* Avoid false sharing as much as possible. */ - if (!atomic_read(&iovad->fq_timer_on) && - !atomic_xchg(&iovad->fq_timer_on, 1)) - mod_timer(&iovad->fq_timer, + if (!atomic_read(&cookie->fq_timer_on) && + !atomic_xchg(&cookie->fq_timer_on, 1)) + mod_timer(&cookie->fq_timer, jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT)); } -static void free_iova_flush_queue(struct iova_domain *iovad) +static void iommu_dma_free_fq(struct iommu_dma_cookie *cookie) { int cpu, idx; - if (!iovad->fq) + if (!cookie->fq) return; - del_timer_sync(&iovad->fq_timer); - /* - * This code runs when the iova_domain is being detroyed, so don't - * bother to free iovas, just free any remaining pagetable pages. - */ + del_timer_sync(&cookie->fq_timer); + /* The IOVAs will be torn down separately, so just free our queued pages */ for_each_possible_cpu(cpu) { - struct iova_fq *fq = per_cpu_ptr(iovad->fq, cpu); + struct iova_fq *fq = per_cpu_ptr(cookie->fq, cpu); fq_ring_for_each(idx, fq) put_pages_list(&fq->entries[idx].freelist); } - free_percpu(iovad->fq); - - iovad->fq = NULL; - iovad->fq_domain = NULL; + free_percpu(cookie->fq); } -int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_domain) +/* sysfs updates are serialised by the mutex of the group owning @domain */ +int iommu_dma_init_fq(struct iommu_domain *domain) { + struct iommu_dma_cookie *cookie = domain->iova_cookie; struct iova_fq __percpu *queue; int i, cpu; - atomic64_set(&iovad->fq_flush_start_cnt, 0); - atomic64_set(&iovad->fq_flush_finish_cnt, 0); + if (cookie->fq_domain) + return 0; + + atomic64_set(&cookie->fq_flush_start_cnt, 0); + atomic64_set(&cookie->fq_flush_finish_cnt, 0); queue = alloc_percpu(struct iova_fq); - if (!queue) + if (!queue) { + pr_warn("iova flush queue initialization failed\n"); return -ENOMEM; + } for_each_possible_cpu(cpu) { struct iova_fq *fq = per_cpu_ptr(queue, cpu); @@ -228,12 +264,16 @@ int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_dom INIT_LIST_HEAD(&fq->entries[i].freelist); } - iovad->fq_domain = fq_domain; - iovad->fq = queue; - - timer_setup(&iovad->fq_timer, fq_flush_timeout, 0); - atomic_set(&iovad->fq_timer_on, 0); + cookie->fq = queue; + timer_setup(&cookie->fq_timer, fq_flush_timeout, 0); + atomic_set(&cookie->fq_timer_on, 0); + /* + * Prevent incomplete fq state being observable. Pairs with path from + * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova() + */ + smp_wmb(); + WRITE_ONCE(cookie->fq_domain, domain); return 0; } @@ -318,7 +358,7 @@ void iommu_put_dma_cookie(struct iommu_domain *domain) return; if (cookie->type == IOMMU_DMA_IOVA_COOKIE && cookie->iovad.granule) { - free_iova_flush_queue(&cookie->iovad); + iommu_dma_free_fq(cookie); put_iova_domain(&cookie->iovad); } @@ -467,29 +507,6 @@ static bool dev_use_swiotlb(struct device *dev) return IS_ENABLED(CONFIG_SWIOTLB) && dev_is_untrusted(dev); } -/* sysfs updates are serialised by the mutex of the group owning @domain */ -int iommu_dma_init_fq(struct iommu_domain *domain) -{ - struct iommu_dma_cookie *cookie = domain->iova_cookie; - int ret; - - if (cookie->fq_domain) - return 0; - - ret = init_iova_flush_queue(&cookie->iovad, domain); - if (ret) { - pr_warn("iova flush queue initialization failed\n"); - return ret; - } - /* - * Prevent incomplete iovad->fq being observable. Pairs with path from - * __iommu_dma_unmap() through iommu_dma_free_iova() to queue_iova() - */ - smp_wmb(); - WRITE_ONCE(cookie->fq_domain, domain); - return 0; -} - /** * iommu_dma_init_domain - Initialise a DMA mapping domain * @domain: IOMMU domain previously prepared by iommu_get_dma_cookie() @@ -620,7 +637,7 @@ static void iommu_dma_free_iova(struct iommu_dma_cookie *cookie, if (cookie->type == IOMMU_DMA_MSI_COOKIE) cookie->msi_iova -= size; else if (gather && gather->queued) - queue_iova(iovad, iova_pfn(iovad, iova), + queue_iova(cookie, iova_pfn(iovad, iova), size >> iova_shift(iovad), &gather->freelist); else diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index 081e5c0cf940..b28c9435b898 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -61,8 +61,6 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule, iovad->start_pfn = start_pfn; iovad->dma_32bit_pfn = 1UL << (32 - iova_shift(iovad)); iovad->max32_alloc_size = iovad->dma_32bit_pfn; - iovad->fq_domain = NULL; - iovad->fq = NULL; iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR; rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node); rb_insert_color(&iovad->anchor.node, &iovad->rbroot); diff --git a/include/linux/iova.h b/include/linux/iova.h index 072a09c06e8a..0abd48c5e622 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -12,9 +12,6 @@ #include #include #include -#include -#include -#include /* iova structure */ struct iova { @@ -36,27 +33,6 @@ struct iova_rcache { struct iova_cpu_rcache __percpu *cpu_rcaches; }; -/* Number of entries per Flush Queue */ -#define IOVA_FQ_SIZE 256 - -/* Timeout (in ms) after which entries are flushed from the Flush-Queue */ -#define IOVA_FQ_TIMEOUT 10 - -/* Flush Queue entry for defered flushing */ -struct iova_fq_entry { - unsigned long iova_pfn; - unsigned long pages; - struct list_head freelist; - u64 counter; /* Flush counter when this entrie was added */ -}; - -/* Per-CPU Flush Queue structure */ -struct iova_fq { - struct iova_fq_entry entries[IOVA_FQ_SIZE]; - unsigned head, tail; - spinlock_t lock; -}; - /* holds all the iova translations for a domain */ struct iova_domain { spinlock_t iova_rbtree_lock; /* Lock to protect update of rbtree */ @@ -67,23 +43,9 @@ struct iova_domain { unsigned long start_pfn; /* Lower limit for this domain */ unsigned long dma_32bit_pfn; unsigned long max32_alloc_size; /* Size of last failed allocation */ - struct iova_fq __percpu *fq; /* Flush Queue */ - - atomic64_t fq_flush_start_cnt; /* Number of TLB flushes that - have been started */ - - atomic64_t fq_flush_finish_cnt; /* Number of TLB flushes that - have been finished */ - struct iova anchor; /* rbtree lookup anchor */ - struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ - - struct iommu_domain *fq_domain; - struct timer_list fq_timer; /* Timer to regularily empty the - flush-queues */ - atomic_t fq_timer_on; /* 1 when timer is active, 0 - when not */ + struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE]; /* IOVA range caches */ struct hlist_node cpuhp_dead; }; @@ -133,16 +95,12 @@ struct iova *alloc_iova(struct iova_domain *iovad, unsigned long size, bool size_aligned); void free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size); -void queue_iova(struct iova_domain *iovad, - unsigned long pfn, unsigned long pages, - struct list_head *freelist); unsigned long alloc_iova_fast(struct iova_domain *iovad, unsigned long size, unsigned long limit_pfn, bool flush_rcache); struct iova *reserve_iova(struct iova_domain *iovad, unsigned long pfn_lo, unsigned long pfn_hi); void init_iova_domain(struct iova_domain *iovad, unsigned long granule, unsigned long start_pfn); -int init_iova_flush_queue(struct iova_domain *iovad, struct iommu_domain *fq_domain); struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn); void put_iova_domain(struct iova_domain *iovad); #else -- cgit v1.2.3 From 5bc9a9dd75351023793d8aa4116ead005d659729 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 19 Dec 2021 21:51:24 +0200 Subject: rfkill: allow to get the software rfkill state iwlwifi needs to be able to differentiate between the software rfkill state and the hardware rfkill state. The reason for this is that iwlwifi needs to notify any change in the software rfkill state even when it doesn't own the device (which means even when the hardware rfkill is asserted). In order to be able to know the software rfkill when the host does not own the device, iwlwifi needs to be able to ask the state of the software rfkill ignoring the state of the hardware rfkill. Signed-off-by: Emmanuel Grumbach Link: https://lore.kernel.org/r/20211219195124.125689-1-emmanuel.grumbach@intel.com Signed-off-by: Johannes Berg --- include/linux/rfkill.h | 7 +++++++ net/rfkill/core.c | 12 ++++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 231e06b74b50..c35f3962dc4f 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -229,6 +229,13 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); */ bool rfkill_blocked(struct rfkill *rfkill); +/** + * rfkill_soft_blocked - Query soft rfkill block state + * + * @rfkill: rfkill struct to query + */ +bool rfkill_soft_blocked(struct rfkill *rfkill); + /** * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type diff --git a/net/rfkill/core.c b/net/rfkill/core.c index ac15a944573f..5b1927d66f0d 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -946,6 +946,18 @@ bool rfkill_blocked(struct rfkill *rfkill) } EXPORT_SYMBOL(rfkill_blocked); +bool rfkill_soft_blocked(struct rfkill *rfkill) +{ + unsigned long flags; + u32 state; + + spin_lock_irqsave(&rfkill->lock, flags); + state = rfkill->state; + spin_unlock_irqrestore(&rfkill->lock, flags); + + return !!(state & RFKILL_BLOCK_SW); +} +EXPORT_SYMBOL(rfkill_soft_blocked); struct rfkill * __must_check rfkill_alloc(const char *name, struct device *parent, -- cgit v1.2.3 From aade40b62745cf0b4e8a17d43652c5faff354e6b Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Mon, 20 Dec 2021 13:34:48 +0100 Subject: iommu/iova: Temporarily include dma-mapping.h from iova.h Some users of iova.h still expect that dma-mapping.h is also included. Re-add the include until these users are updated to fix compile failures in the iommu tree. Acked-by: Robin Murphy Link: https://lore.kernel.org/r/20211220123448.19996-1-joro@8bytes.org Signed-off-by: Joerg Roedel --- include/linux/iova.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/iova.h b/include/linux/iova.h index 0abd48c5e622..cea79cb9f26c 100644 --- a/include/linux/iova.h +++ b/include/linux/iova.h @@ -12,6 +12,7 @@ #include #include #include +#include /* iova structure */ struct iova { -- cgit v1.2.3 From 59f37b7370ef56e6faf25d0e18bc597a0af40bb8 Mon Sep 17 00:00:00 2001 From: Sam Protsenko Date: Sat, 4 Dec 2021 21:57:55 +0200 Subject: tty: serial: samsung: Remove USI initialization USI control is now extracted to the dedicated USI driver. Remove USI related code from serial driver to avoid conflicts and code duplication. Signed-off-by: Sam Protsenko Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20211204195757.8600-4-semen.protsenko@linaro.org Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/samsung_tty.c | 36 ++++-------------------------------- include/linux/serial_s3c.h | 9 --------- 2 files changed, 4 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serial/samsung_tty.c b/drivers/tty/serial/samsung_tty.c index ca084c10d0bb..f986a9253dc8 100644 --- a/drivers/tty/serial/samsung_tty.c +++ b/drivers/tty/serial/samsung_tty.c @@ -65,7 +65,6 @@ enum s3c24xx_port_type { struct s3c24xx_uart_info { char *name; enum s3c24xx_port_type type; - bool has_usi; unsigned int port_type; unsigned int fifosize; unsigned long rx_fifomask; @@ -1357,28 +1356,6 @@ static int apple_s5l_serial_startup(struct uart_port *port) return ret; } -static void exynos_usi_init(struct uart_port *port) -{ - struct s3c24xx_uart_port *ourport = to_ourport(port); - struct s3c24xx_uart_info *info = ourport->info; - unsigned int val; - - if (!info->has_usi) - return; - - /* Clear the software reset of USI block (it's set at startup) */ - val = rd_regl(port, USI_CON); - val &= ~USI_CON_RESET_MASK; - wr_regl(port, USI_CON, val); - udelay(1); - - /* Continuously provide the clock to USI IP w/o gating (for Rx mode) */ - val = rd_regl(port, USI_OPTION); - val &= ~USI_OPTION_HWACG_MASK; - val |= USI_OPTION_HWACG_CLKREQ_ON; - wr_regl(port, USI_OPTION, val); -} - /* power power management control */ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, @@ -1405,8 +1382,6 @@ static void s3c24xx_serial_pm(struct uart_port *port, unsigned int level, if (!IS_ERR(ourport->baudclk)) clk_prepare_enable(ourport->baudclk); - - exynos_usi_init(port); break; default: dev_err(port->dev, "s3c24xx_serial: unknown pm %d\n", level); @@ -2130,8 +2105,6 @@ static int s3c24xx_serial_init_port(struct s3c24xx_uart_port *ourport, if (ret) pr_warn("uart: failed to enable baudclk\n"); - exynos_usi_init(port); - /* Keep all interrupts masked and cleared */ switch (ourport->info->type) { case TYPE_S3C6400: @@ -2780,11 +2753,10 @@ static struct s3c24xx_serial_drv_data s5pv210_serial_drv_data = { #endif #if defined(CONFIG_ARCH_EXYNOS) -#define EXYNOS_COMMON_SERIAL_DRV_DATA(_has_usi) \ +#define EXYNOS_COMMON_SERIAL_DRV_DATA() \ .info = &(struct s3c24xx_uart_info) { \ .name = "Samsung Exynos UART", \ .type = TYPE_S3C6400, \ - .has_usi = _has_usi, \ .port_type = PORT_S3C6400, \ .has_divslot = 1, \ .rx_fifomask = S5PV210_UFSTAT_RXMASK, \ @@ -2805,17 +2777,17 @@ static struct s3c24xx_serial_drv_data s5pv210_serial_drv_data = { } \ static struct s3c24xx_serial_drv_data exynos4210_serial_drv_data = { - EXYNOS_COMMON_SERIAL_DRV_DATA(false), + EXYNOS_COMMON_SERIAL_DRV_DATA(), .fifosize = { 256, 64, 16, 16 }, }; static struct s3c24xx_serial_drv_data exynos5433_serial_drv_data = { - EXYNOS_COMMON_SERIAL_DRV_DATA(false), + EXYNOS_COMMON_SERIAL_DRV_DATA(), .fifosize = { 64, 256, 16, 256 }, }; static struct s3c24xx_serial_drv_data exynos850_serial_drv_data = { - EXYNOS_COMMON_SERIAL_DRV_DATA(true), + EXYNOS_COMMON_SERIAL_DRV_DATA(), .fifosize = { 256, 64, 64, 64 }, }; diff --git a/include/linux/serial_s3c.h b/include/linux/serial_s3c.h index cf0de4a86640..f6c3323fc4c5 100644 --- a/include/linux/serial_s3c.h +++ b/include/linux/serial_s3c.h @@ -27,15 +27,6 @@ #define S3C2410_UERSTAT (0x14) #define S3C2410_UFSTAT (0x18) #define S3C2410_UMSTAT (0x1C) -#define USI_CON (0xC4) -#define USI_OPTION (0xC8) - -#define USI_CON_RESET (1<<0) -#define USI_CON_RESET_MASK (1<<0) - -#define USI_OPTION_HWACG_CLKREQ_ON (1<<1) -#define USI_OPTION_HWACG_CLKSTOP_ON (1<<2) -#define USI_OPTION_HWACG_MASK (3<<1) #define S3C2410_LCON_CFGMASK ((0xF<<3)|(0x3)) -- cgit v1.2.3 From 1a5e91d8375fc8369207cc0b9894a324f2bbf1d9 Mon Sep 17 00:00:00 2001 From: Tianyu Lan Date: Mon, 13 Dec 2021 02:14:02 -0500 Subject: swiotlb: Add swiotlb bounce buffer remap function for HV IVM In Isolation VM with AMD SEV, bounce buffer needs to be accessed via extra address space which is above shared_gpa_boundary (E.G 39 bit address line) reported by Hyper-V CPUID ISOLATION_CONFIG. The access physical address will be original physical address + shared_gpa_boundary. The shared_gpa_boundary in the AMD SEV SNP spec is called virtual top of memory(vTOM). Memory addresses below vTOM are automatically treated as private while memory above vTOM is treated as shared. Expose swiotlb_unencrypted_base for platforms to set unencrypted memory base offset and platform calls swiotlb_update_mem_attributes() to remap swiotlb mem to unencrypted address space. memremap() can not be called in the early stage and so put remapping code into swiotlb_update_mem_attributes(). Store remap address and use it to copy data from/to swiotlb bounce buffer. Signed-off-by: Tianyu Lan Acked-by: Christoph Hellwig Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20211213071407.314309-2-ltykernel@gmail.com Signed-off-by: Wei Liu --- include/linux/swiotlb.h | 6 ++++++ kernel/dma/swiotlb.c | 43 +++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 47 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h index 569272871375..f6c3638255d5 100644 --- a/include/linux/swiotlb.h +++ b/include/linux/swiotlb.h @@ -73,6 +73,9 @@ extern enum swiotlb_force swiotlb_force; * @end: The end address of the swiotlb memory pool. Used to do a quick * range check to see if the memory was in fact allocated by this * API. + * @vaddr: The vaddr of the swiotlb memory pool. The swiotlb memory pool + * may be remapped in the memory encrypted case and store virtual + * address for bounce buffer operation. * @nslabs: The number of IO TLB blocks (in groups of 64) between @start and * @end. For default swiotlb, this is command line adjustable via * setup_io_tlb_npages. @@ -92,6 +95,7 @@ extern enum swiotlb_force swiotlb_force; struct io_tlb_mem { phys_addr_t start; phys_addr_t end; + void *vaddr; unsigned long nslabs; unsigned long used; unsigned int index; @@ -186,4 +190,6 @@ static inline bool is_swiotlb_for_alloc(struct device *dev) } #endif /* CONFIG_DMA_RESTRICTED_POOL */ +extern phys_addr_t swiotlb_unencrypted_base; + #endif /* __LINUX_SWIOTLB_H */ diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 8e840fbbed7c..b36c1cdd0c4f 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -50,6 +50,7 @@ #include #include +#include #include #include #include @@ -72,6 +73,8 @@ enum swiotlb_force swiotlb_force; struct io_tlb_mem io_tlb_default_mem; +phys_addr_t swiotlb_unencrypted_base; + /* * Max segment that we can provide which (if pages are contingous) will * not be bounced (unless SWIOTLB_FORCE is set). @@ -155,6 +158,27 @@ static inline unsigned long nr_slots(u64 val) return DIV_ROUND_UP(val, IO_TLB_SIZE); } +/* + * Remap swioltb memory in the unencrypted physical address space + * when swiotlb_unencrypted_base is set. (e.g. for Hyper-V AMD SEV-SNP + * Isolation VMs). + */ +static void *swiotlb_mem_remap(struct io_tlb_mem *mem, unsigned long bytes) +{ + void *vaddr = NULL; + + if (swiotlb_unencrypted_base) { + phys_addr_t paddr = mem->start + swiotlb_unencrypted_base; + + vaddr = memremap(paddr, bytes, MEMREMAP_WB); + if (!vaddr) + pr_err("Failed to map the unencrypted memory %pa size %lx.\n", + &paddr, bytes); + } + + return vaddr; +} + /* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to @@ -172,7 +196,12 @@ void __init swiotlb_update_mem_attributes(void) vaddr = phys_to_virt(mem->start); bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT); - memset(vaddr, 0, bytes); + + mem->vaddr = swiotlb_mem_remap(mem, bytes); + if (!mem->vaddr) + mem->vaddr = vaddr; + + memset(mem->vaddr, 0, bytes); } static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, @@ -196,7 +225,17 @@ static void swiotlb_init_io_tlb_mem(struct io_tlb_mem *mem, phys_addr_t start, mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; } + + /* + * If swiotlb_unencrypted_base is set, the bounce buffer memory will + * be remapped and cleared in swiotlb_update_mem_attributes. + */ + if (swiotlb_unencrypted_base) + return; + memset(vaddr, 0, bytes); + mem->vaddr = vaddr; + return; } int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) @@ -371,7 +410,7 @@ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size phys_addr_t orig_addr = mem->slots[index].orig_addr; size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); - unsigned char *vaddr = phys_to_virt(tlb_addr); + unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; unsigned int tlb_offset, orig_addr_offset; if (orig_addr == INVALID_PHYS_ADDR) -- cgit v1.2.3 From 743b237c3a7b0f5b44aa704aae8a1058877b6322 Mon Sep 17 00:00:00 2001 From: Tianyu Lan Date: Mon, 13 Dec 2021 02:14:05 -0500 Subject: scsi: storvsc: Add Isolation VM support for storvsc driver In Isolation VM, all shared memory with host needs to mark visible to host via hvcall. vmbus_establish_gpadl() has already done it for storvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_ mpb_desc() still needs to be handled. Use DMA API(scsi_dma_map/unmap) to map these memory during sending/receiving packet and return swiotlb bounce buffer dma address. In Isolation VM, swiotlb bounce buffer is marked to be visible to host and the swiotlb force mode is enabled. Set device's dma min align mask to HV_HYP_PAGE_SIZE - 1 in order to keep the original data offset in the bounce buffer. Signed-off-by: Tianyu Lan Reviewed-by: Long Li Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20211213071407.314309-5-ltykernel@gmail.com Signed-off-by: Wei Liu --- drivers/hv/vmbus_drv.c | 4 ++++ drivers/scsi/storvsc_drv.c | 37 +++++++++++++++++++++---------------- include/linux/hyperv.h | 1 + 3 files changed, 26 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 392c1ac4f819..ae6ec503399a 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include "hyperv_vmbus.h" @@ -2078,6 +2079,7 @@ struct hv_device *vmbus_device_create(const guid_t *type, return child_device_obj; } +static u64 vmbus_dma_mask = DMA_BIT_MASK(64); /* * vmbus_device_register - Register the child device */ @@ -2118,6 +2120,8 @@ int vmbus_device_register(struct hv_device *child_device_obj) } hv_debug_add_dev_dir(child_device_obj); + child_device_obj->device.dma_mask = &vmbus_dma_mask; + child_device_obj->device.dma_parms = &child_device_obj->dma_parms; return 0; err_kset_unregister: diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 20595c0ba0ae..ae293600d799 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -21,6 +21,8 @@ #include #include #include +#include + #include #include #include @@ -1336,6 +1338,7 @@ static void storvsc_on_channel_callback(void *context) continue; } request = (struct storvsc_cmd_request *)scsi_cmd_priv(scmnd); + scsi_dma_unmap(scmnd); } storvsc_on_receive(stor_device, packet, request); @@ -1749,7 +1752,6 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) struct hv_host_device *host_dev = shost_priv(host); struct hv_device *dev = host_dev->dev; struct storvsc_cmd_request *cmd_request = scsi_cmd_priv(scmnd); - int i; struct scatterlist *sgl; unsigned int sg_count; struct vmscsi_request *vm_srb; @@ -1831,10 +1833,11 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) payload_sz = sizeof(cmd_request->mpb); if (sg_count) { - unsigned int hvpgoff, hvpfns_to_add; unsigned long offset_in_hvpg = offset_in_hvpage(sgl->offset); unsigned int hvpg_count = HVPFN_UP(offset_in_hvpg + length); - u64 hvpfn; + struct scatterlist *sg; + unsigned long hvpfn, hvpfns_to_add; + int j, i = 0; if (hvpg_count > MAX_PAGE_BUFFER_COUNT) { @@ -1848,21 +1851,22 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) payload->range.len = length; payload->range.offset = offset_in_hvpg; + sg_count = scsi_dma_map(scmnd); + if (sg_count < 0) + return SCSI_MLQUEUE_DEVICE_BUSY; - for (i = 0; sgl != NULL; sgl = sg_next(sgl)) { + for_each_sg(sgl, sg, sg_count, j) { /* - * Init values for the current sgl entry. hvpgoff - * and hvpfns_to_add are in units of Hyper-V size - * pages. Handling the PAGE_SIZE != HV_HYP_PAGE_SIZE - * case also handles values of sgl->offset that are - * larger than PAGE_SIZE. Such offsets are handled - * even on other than the first sgl entry, provided - * they are a multiple of PAGE_SIZE. + * Init values for the current sgl entry. hvpfns_to_add + * is in units of Hyper-V size pages. Handling the + * PAGE_SIZE != HV_HYP_PAGE_SIZE case also handles + * values of sgl->offset that are larger than PAGE_SIZE. + * Such offsets are handled even on other than the first + * sgl entry, provided they are a multiple of PAGE_SIZE. */ - hvpgoff = HVPFN_DOWN(sgl->offset); - hvpfn = page_to_hvpfn(sg_page(sgl)) + hvpgoff; - hvpfns_to_add = HVPFN_UP(sgl->offset + sgl->length) - - hvpgoff; + hvpfn = HVPFN_DOWN(sg_dma_address(sg)); + hvpfns_to_add = HVPFN_UP(sg_dma_address(sg) + + sg_dma_len(sg)) - hvpfn; /* * Fill the next portion of the PFN array with @@ -1872,7 +1876,7 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) * the PFN array is filled. */ while (hvpfns_to_add--) - payload->range.pfn_array[i++] = hvpfn++; + payload->range.pfn_array[i++] = hvpfn++; } } @@ -2016,6 +2020,7 @@ static int storvsc_probe(struct hv_device *device, stor_device->vmscsi_size_delta = sizeof(struct vmscsi_win8_extension); spin_lock_init(&stor_device->lock); hv_set_drvdata(device, stor_device); + dma_set_min_align_mask(&device->device, HV_HYP_PAGE_SIZE - 1); stor_device->port_number = host->host_no; ret = storvsc_connect_to_vsp(device, storvsc_ringbuffer_size, is_fc); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b823311eac79..650a0574b746 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1261,6 +1261,7 @@ struct hv_device { struct vmbus_channel *channel; struct kset *channels_kset; + struct device_dma_parameters dma_parms; /* place holder to keep track of the dir for hv device in debugfs */ struct dentry *debug_dir; -- cgit v1.2.3 From 846da38de0e8224f2f94b885125cf1fd2d7b0d39 Mon Sep 17 00:00:00 2001 From: Tianyu Lan Date: Mon, 13 Dec 2021 02:14:06 -0500 Subject: net: netvsc: Add Isolation VM support for netvsc driver In Isolation VM, all shared memory with host needs to mark visible to host via hvcall. vmbus_establish_gpadl() has already done it for netvsc rx/tx ring buffer. The page buffer used by vmbus_sendpacket_ pagebuffer() stills need to be handled. Use DMA API to map/umap these memory during sending/receiving packet and Hyper-V swiotlb bounce buffer dma address will be returned. The swiotlb bounce buffer has been masked to be visible to host during boot up. rx/tx ring buffer is allocated via vzalloc() and they need to be mapped into unencrypted address space(above vTOM) before sharing with host and accessing. Add hv_map/unmap_memory() to map/umap rx /tx ring buffer. Signed-off-by: Tianyu Lan Reviewed-by: Haiyang Zhang Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20211213071407.314309-6-ltykernel@gmail.com Signed-off-by: Wei Liu --- arch/x86/hyperv/ivm.c | 28 ++++++++ drivers/hv/hv_common.c | 11 +++ drivers/net/hyperv/hyperv_net.h | 5 ++ drivers/net/hyperv/netvsc.c | 136 +++++++++++++++++++++++++++++++++++++- drivers/net/hyperv/netvsc_drv.c | 1 + drivers/net/hyperv/rndis_filter.c | 2 + include/asm-generic/mshyperv.h | 2 + include/linux/hyperv.h | 5 ++ 8 files changed, 187 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 69c7a57f3307..2b994117581e 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -287,3 +287,31 @@ int hv_set_mem_host_visibility(unsigned long kbuffer, int pagecount, bool visibl kfree(pfn_array); return ret; } + +/* + * hv_map_memory - map memory to extra space in the AMD SEV-SNP Isolation VM. + */ +void *hv_map_memory(void *addr, unsigned long size) +{ + unsigned long *pfns = kcalloc(size / PAGE_SIZE, + sizeof(unsigned long), GFP_KERNEL); + void *vaddr; + int i; + + if (!pfns) + return NULL; + + for (i = 0; i < size / PAGE_SIZE; i++) + pfns[i] = vmalloc_to_pfn(addr + i * PAGE_SIZE) + + (ms_hyperv.shared_gpa_boundary >> PAGE_SHIFT); + + vaddr = vmap_pfn(pfns, size / PAGE_SIZE, PAGE_KERNEL_IO); + kfree(pfns); + + return vaddr; +} + +void hv_unmap_memory(void *addr) +{ + vunmap(addr); +} diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 7be173a99f27..3c5cb1f70319 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -295,3 +295,14 @@ u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_s return HV_STATUS_INVALID_PARAMETER; } EXPORT_SYMBOL_GPL(hv_ghcb_hypercall); + +void __weak *hv_map_memory(void *addr, unsigned long size) +{ + return NULL; +} +EXPORT_SYMBOL_GPL(hv_map_memory); + +void __weak hv_unmap_memory(void *addr) +{ +} +EXPORT_SYMBOL_GPL(hv_unmap_memory); diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 315278a7cf88..cf69da0e296c 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -164,6 +164,7 @@ struct hv_netvsc_packet { u32 total_bytes; u32 send_buf_index; u32 total_data_buflen; + struct hv_dma_range *dma_range; }; #define NETVSC_HASH_KEYLEN 40 @@ -1074,6 +1075,7 @@ struct netvsc_device { /* Receive buffer allocated by us but manages by NetVSP */ void *recv_buf; + void *recv_original_buf; u32 recv_buf_size; /* allocated bytes */ struct vmbus_gpadl recv_buf_gpadl_handle; u32 recv_section_cnt; @@ -1082,6 +1084,7 @@ struct netvsc_device { /* Send buffer allocated by us */ void *send_buf; + void *send_original_buf; u32 send_buf_size; struct vmbus_gpadl send_buf_gpadl_handle; u32 send_section_cnt; @@ -1731,4 +1734,6 @@ struct rndis_message { #define RETRY_US_HI 10000 #define RETRY_MAX 2000 /* >10 sec */ +void netvsc_dma_unmap(struct hv_device *hv_dev, + struct hv_netvsc_packet *packet); #endif /* _HYPERV_NET_H */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 396bc1c204e6..ea2d867121d5 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -153,8 +153,21 @@ static void free_netvsc_device(struct rcu_head *head) int i; kfree(nvdev->extension); - vfree(nvdev->recv_buf); - vfree(nvdev->send_buf); + + if (nvdev->recv_original_buf) { + hv_unmap_memory(nvdev->recv_buf); + vfree(nvdev->recv_original_buf); + } else { + vfree(nvdev->recv_buf); + } + + if (nvdev->send_original_buf) { + hv_unmap_memory(nvdev->send_buf); + vfree(nvdev->send_original_buf); + } else { + vfree(nvdev->send_buf); + } + kfree(nvdev->send_section_map); for (i = 0; i < VRSS_CHANNEL_MAX; i++) { @@ -338,6 +351,7 @@ static int netvsc_init_buf(struct hv_device *device, unsigned int buf_size; size_t map_words; int i, ret = 0; + void *vaddr; /* Get receive buffer area. */ buf_size = device_info->recv_sections * device_info->recv_section_size; @@ -373,6 +387,17 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; } + if (hv_isolation_type_snp()) { + vaddr = hv_map_memory(net_device->recv_buf, buf_size); + if (!vaddr) { + ret = -ENOMEM; + goto cleanup; + } + + net_device->recv_original_buf = net_device->recv_buf; + net_device->recv_buf = vaddr; + } + /* Notify the NetVsp of the gpadl handle */ init_packet = &net_device->channel_init_pkt; memset(init_packet, 0, sizeof(struct nvsp_message)); @@ -476,6 +501,17 @@ static int netvsc_init_buf(struct hv_device *device, goto cleanup; } + if (hv_isolation_type_snp()) { + vaddr = hv_map_memory(net_device->send_buf, buf_size); + if (!vaddr) { + ret = -ENOMEM; + goto cleanup; + } + + net_device->send_original_buf = net_device->send_buf; + net_device->send_buf = vaddr; + } + /* Notify the NetVsp of the gpadl handle */ init_packet = &net_device->channel_init_pkt; memset(init_packet, 0, sizeof(struct nvsp_message)); @@ -766,7 +802,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev, /* Notify the layer above us */ if (likely(skb)) { - const struct hv_netvsc_packet *packet + struct hv_netvsc_packet *packet = (struct hv_netvsc_packet *)skb->cb; u32 send_index = packet->send_buf_index; struct netvsc_stats *tx_stats; @@ -782,6 +818,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev, tx_stats->bytes += packet->total_bytes; u64_stats_update_end(&tx_stats->syncp); + netvsc_dma_unmap(ndev_ctx->device_ctx, packet); napi_consume_skb(skb, budget); } @@ -946,6 +983,88 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, memset(dest, 0, padding); } +void netvsc_dma_unmap(struct hv_device *hv_dev, + struct hv_netvsc_packet *packet) +{ + u32 page_count = packet->cp_partial ? + packet->page_buf_cnt - packet->rmsg_pgcnt : + packet->page_buf_cnt; + int i; + + if (!hv_is_isolation_supported()) + return; + + if (!packet->dma_range) + return; + + for (i = 0; i < page_count; i++) + dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma, + packet->dma_range[i].mapping_size, + DMA_TO_DEVICE); + + kfree(packet->dma_range); +} + +/* netvsc_dma_map - Map swiotlb bounce buffer with data page of + * packet sent by vmbus_sendpacket_pagebuffer() in the Isolation + * VM. + * + * In isolation VM, netvsc send buffer has been marked visible to + * host and so the data copied to send buffer doesn't need to use + * bounce buffer. The data pages handled by vmbus_sendpacket_pagebuffer() + * may not be copied to send buffer and so these pages need to be + * mapped with swiotlb bounce buffer. netvsc_dma_map() is to do + * that. The pfns in the struct hv_page_buffer need to be converted + * to bounce buffer's pfn. The loop here is necessary because the + * entries in the page buffer array are not necessarily full + * pages of data. Each entry in the array has a separate offset and + * len that may be non-zero, even for entries in the middle of the + * array. And the entries are not physically contiguous. So each + * entry must be individually mapped rather than as a contiguous unit. + * So not use dma_map_sg() here. + */ +static int netvsc_dma_map(struct hv_device *hv_dev, + struct hv_netvsc_packet *packet, + struct hv_page_buffer *pb) +{ + u32 page_count = packet->cp_partial ? + packet->page_buf_cnt - packet->rmsg_pgcnt : + packet->page_buf_cnt; + dma_addr_t dma; + int i; + + if (!hv_is_isolation_supported()) + return 0; + + packet->dma_range = kcalloc(page_count, + sizeof(*packet->dma_range), + GFP_KERNEL); + if (!packet->dma_range) + return -ENOMEM; + + for (i = 0; i < page_count; i++) { + char *src = phys_to_virt((pb[i].pfn << HV_HYP_PAGE_SHIFT) + + pb[i].offset); + u32 len = pb[i].len; + + dma = dma_map_single(&hv_dev->device, src, len, + DMA_TO_DEVICE); + if (dma_mapping_error(&hv_dev->device, dma)) { + kfree(packet->dma_range); + return -ENOMEM; + } + + /* pb[].offset and pb[].len are not changed during dma mapping + * and so not reassign. + */ + packet->dma_range[i].dma = dma; + packet->dma_range[i].mapping_size = len; + pb[i].pfn = dma >> HV_HYP_PAGE_SHIFT; + } + + return 0; +} + static inline int netvsc_send_pkt( struct hv_device *device, struct hv_netvsc_packet *packet, @@ -986,14 +1105,24 @@ static inline int netvsc_send_pkt( trace_nvsp_send_pkt(ndev, out_channel, rpkt); + packet->dma_range = NULL; if (packet->page_buf_cnt) { if (packet->cp_partial) pb += packet->rmsg_pgcnt; + ret = netvsc_dma_map(ndev_ctx->device_ctx, packet, pb); + if (ret) { + ret = -EAGAIN; + goto exit; + } + ret = vmbus_sendpacket_pagebuffer(out_channel, pb, packet->page_buf_cnt, &nvmsg, sizeof(nvmsg), req_id); + + if (ret) + netvsc_dma_unmap(ndev_ctx->device_ctx, packet); } else { ret = vmbus_sendpacket(out_channel, &nvmsg, sizeof(nvmsg), @@ -1001,6 +1130,7 @@ static inline int netvsc_send_pkt( VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); } +exit: if (ret == 0) { atomic_inc_return(&nvchan->queue_sends); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 7e66ae1d2a59..17958533bf30 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2512,6 +2512,7 @@ static int netvsc_probe(struct hv_device *dev, net->netdev_ops = &device_ops; net->ethtool_ops = ðtool_ops; SET_NETDEV_DEV(net, &dev->device); + dma_set_min_align_mask(&dev->device, HV_HYP_PAGE_SIZE - 1); /* We always need headroom for rndis header */ net->needed_headroom = RNDIS_AND_PPI_SIZE; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index f6c9c2a670f9..448fcc325ed7 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -361,6 +361,8 @@ static void rndis_filter_receive_response(struct net_device *ndev, } } + netvsc_dma_unmap(((struct net_device_context *) + netdev_priv(ndev))->device_ctx, &request->pkt); complete(&request->wait_event); } else { netdev_err(ndev, diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 3e2248ac328e..94e73ba129c5 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -269,6 +269,8 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void *hv_map_memory(void *addr, unsigned long size); +void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ static inline bool hv_is_hyperv_initialized(void) { return false; } static inline bool hv_is_hibernation_supported(void) { return false; } diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 650a0574b746..f565a8938836 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1584,6 +1584,11 @@ struct hyperv_service_callback { void (*callback)(void *context); }; +struct hv_dma_range { + dma_addr_t dma; + u32 mapping_size; +}; + #define MAX_SRV_VER 0x7ffffff extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen, const int *fw_version, int fw_vercnt, -- cgit v1.2.3 From 6fc61c39ee1adb5f4115d288c876772fcd8b6979 Mon Sep 17 00:00:00 2001 From: Konrad Dybcio Date: Sun, 21 Nov 2021 01:20:46 +0100 Subject: soc: qcom: llcc: Add configuration data for SM8350 Add LLCC configuration data for SM8350 SoC. Signed-off-by: Konrad Dybcio Signed-off-by: Bjorn Andersson Link: https://lore.kernel.org/r/20211121002050.36977-2-konrad.dybcio@somainline.org --- drivers/soc/qcom/llcc-qcom.c | 28 ++++++++++++++++++++++++++++ include/linux/soc/qcom/llcc-qcom.h | 3 +++ 2 files changed, 31 insertions(+) (limited to 'include/linux') diff --git a/drivers/soc/qcom/llcc-qcom.c b/drivers/soc/qcom/llcc-qcom.c index 6bf2f1d1f2c5..ec52f29c8867 100644 --- a/drivers/soc/qcom/llcc-qcom.c +++ b/drivers/soc/qcom/llcc-qcom.c @@ -195,6 +195,28 @@ static const struct llcc_slice_config sm8250_data[] = { { LLCC_WRCACHE, 31, 256, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, }; +static const struct llcc_slice_config sm8350_data[] = { + { LLCC_CPUSS, 1, 3072, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 1 }, + { LLCC_VIDSC0, 2, 512, 3, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_AUDIO, 6, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 0, 0 }, + { LLCC_MDMHPGRW, 7, 1024, 3, 0, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_MODHW, 9, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_CMPT, 10, 3072, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_GPUHTW, 11, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_GPU, 12, 1024, 1, 0, 0xfff, 0x0, 0, 0, 0, 1, 1, 0 }, + { LLCC_MMUHWT, 13, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 0, 1 }, + { LLCC_DISP, 16, 3072, 2, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_MDMPNG, 21, 1024, 0, 1, 0xf, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_AUDHW, 22, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_CVP, 28, 512, 3, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_MODPE, 29, 256, 1, 1, 0xf, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_APTCM, 30, 1024, 3, 1, 0x0, 0x1, 1, 0, 0, 0, 1, 0 }, + { LLCC_WRCACHE, 31, 512, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 0, 1 }, + { LLCC_CVPFW, 17, 512, 1, 0, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_CPUSS1, 3, 1024, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 1, 0 }, + { LLCC_CPUHWT, 5, 512, 1, 1, 0xfff, 0x0, 0, 0, 0, 0, 0, 1 }, +}; + static const struct qcom_llcc_config sc7180_cfg = { .sct_data = sc7180_data, .size = ARRAY_SIZE(sc7180_data), @@ -228,6 +250,11 @@ static const struct qcom_llcc_config sm8250_cfg = { .size = ARRAY_SIZE(sm8250_data), }; +static const struct qcom_llcc_config sm8350_cfg = { + .sct_data = sm8350_data, + .size = ARRAY_SIZE(sm8350_data), +}; + static struct llcc_drv_data *drv_data = (void *) -EPROBE_DEFER; /** @@ -644,6 +671,7 @@ static const struct of_device_id qcom_llcc_of_match[] = { { .compatible = "qcom,sm6350-llcc", .data = &sm6350_cfg }, { .compatible = "qcom,sm8150-llcc", .data = &sm8150_cfg }, { .compatible = "qcom,sm8250-llcc", .data = &sm8250_cfg }, + { .compatible = "qcom,sm8350-llcc", .data = &sm8350_cfg }, { } }; diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h index 437c9df13229..9e8fd92c96b7 100644 --- a/include/linux/soc/qcom/llcc-qcom.h +++ b/include/linux/soc/qcom/llcc-qcom.h @@ -33,6 +33,9 @@ #define LLCC_MODPE 29 #define LLCC_APTCM 30 #define LLCC_WRCACHE 31 +#define LLCC_CVPFW 32 +#define LLCC_CPUSS1 33 +#define LLCC_CPUHWT 36 /** * struct llcc_slice_desc - Cache slice descriptor -- cgit v1.2.3 From 7e5cced9ca84df52d874aca6b632f930b3dc5bc6 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 20 Dec 2021 09:49:01 -0500 Subject: net: accept UFOv6 packages in virtio_net_hdr_to_skb Skb with skb->protocol 0 at the time of virtio_net_hdr_to_skb may have a protocol inferred from virtio_net_hdr with virtio_net_hdr_set_proto. Unlike TCP, UDP does not have separate types for IPv4 and IPv6. Type VIRTIO_NET_HDR_GSO_UDP is guessed to be IPv4/UDP. As of the below commit, UFOv6 packets are dropped due to not matching the protocol as obtained from dev_parse_header_protocol. Invert the test to take that L2 protocol field as starting point and pass both UFOv4 and UFOv6 for VIRTIO_NET_HDR_GSO_UDP. Fixes: 924a9bc362a5 ("net: check if protocol extracted by virtio_net_hdr_set_proto is correct") Link: https://lore.kernel.org/netdev/CABcq3pG9GRCYqFDBAJ48H1vpnnX=41u+MhQnayF1ztLH4WX0Fw@mail.gmail.com/ Reported-by: Andrew Melnichenko Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20211220144901.2784030-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 04e87f4b9417..22dd48c82560 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -7,6 +7,21 @@ #include #include +static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) +{ + switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + return protocol == cpu_to_be16(ETH_P_IP); + case VIRTIO_NET_HDR_GSO_TCPV6: + return protocol == cpu_to_be16(ETH_P_IPV6); + case VIRTIO_NET_HDR_GSO_UDP: + return protocol == cpu_to_be16(ETH_P_IP) || + protocol == cpu_to_be16(ETH_P_IPV6); + default: + return false; + } +} + static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { @@ -88,9 +103,12 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb->protocol) { __be16 protocol = dev_parse_header_protocol(skb); - virtio_net_hdr_set_proto(skb, hdr); - if (protocol && protocol != skb->protocol) + if (!protocol) + virtio_net_hdr_set_proto(skb, hdr); + else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type)) return -EINVAL; + else + skb->protocol = protocol; } retry: if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, -- cgit v1.2.3 From 1ed1d592113959f00cc552c3b9f47ca2d157768f Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Mon, 20 Dec 2021 09:50:27 -0500 Subject: net: skip virtio_net_hdr_set_proto if protocol already set virtio_net_hdr_set_proto infers skb->protocol from the virtio_net_hdr gso_type, to avoid packets getting dropped for lack of a proto type. Its protocol choice is a guess, especially in the case of UFO, where the single VIRTIO_NET_HDR_GSO_UDP label covers both UFOv4 and UFOv6. Skip this best effort if the field is already initialized. Whether explicitly from userspace, or implicitly based on an earlier call to dev_parse_header_protocol (which is more robust, but was introduced after this patch). Fixes: 9d2f67e43b73 ("net/packet: fix packet drop as of virtio gso") Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20211220145027.2784293-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/virtio_net.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 22dd48c82560..a960de68ac69 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -25,6 +25,9 @@ static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, const struct virtio_net_hdr *hdr) { + if (skb->protocol) + return 0; + switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: case VIRTIO_NET_HDR_GSO_UDP: -- cgit v1.2.3 From 80a5ca99c5c04be6777df225ab932142a9d60c3f Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 16 Dec 2021 11:33:00 +0800 Subject: rapidio: remove not used macro definition in rio_ids.h The definition of RIO_VID_FREESCALE, RIO_DID_MPC8560, RIO_DID_TSI500, RIO_DID_TSI576 and RIO_DID_TSI721 are not used for many years in the current code, so just remove them. Signed-off-by: Tiezhu Yang Link: https://lore.kernel.org/r/1639625581-22867-2-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Greg Kroah-Hartman --- include/linux/rio_ids.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index 4846f72759b2..e74d8840708a 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -9,15 +9,10 @@ #ifndef LINUX_RIO_IDS_H #define LINUX_RIO_IDS_H -#define RIO_VID_FREESCALE 0x0002 -#define RIO_DID_MPC8560 0x0003 - #define RIO_VID_TUNDRA 0x000d -#define RIO_DID_TSI500 0x0500 #define RIO_DID_TSI568 0x0568 #define RIO_DID_TSI572 0x0572 #define RIO_DID_TSI574 0x0574 -#define RIO_DID_TSI576 0x0578 /* Same ID as Tsi578 */ #define RIO_DID_TSI577 0x0577 #define RIO_DID_TSI578 0x0578 @@ -33,7 +28,6 @@ #define RIO_DID_IDTCPS1616 0x0379 #define RIO_DID_IDTVPS1616 0x0377 #define RIO_DID_IDTSPS1616 0x0378 -#define RIO_DID_TSI721 0x80ab #define RIO_DID_IDTRXS1632 0x80e5 #define RIO_DID_IDTRXS2448 0x80e6 -- cgit v1.2.3 From 612d4904191ff9aca01b1e087d8687b3a223cb33 Mon Sep 17 00:00:00 2001 From: Tiezhu Yang Date: Thu, 16 Dec 2021 11:33:01 +0800 Subject: rapidio: remove not used code about RIO_VID_TUNDRA According to https://rapidio.org/vendor-id/, there is no 0x000d vendor id in the complete and current list of VendorIDs, it means that the related code is dead code now, so just remove them. Signed-off-by: Tiezhu Yang Link: https://lore.kernel.org/r/1639625581-22867-3-git-send-email-yangtiezhu@loongson.cn Signed-off-by: Greg Kroah-Hartman --- drivers/rapidio/switches/Kconfig | 11 -- drivers/rapidio/switches/Makefile | 2 - drivers/rapidio/switches/tsi568.c | 195 -------------------- drivers/rapidio/switches/tsi57x.c | 365 -------------------------------------- include/linux/rio_ids.h | 7 - 5 files changed, 580 deletions(-) delete mode 100644 drivers/rapidio/switches/tsi568.c delete mode 100644 drivers/rapidio/switches/tsi57x.c (limited to 'include/linux') diff --git a/drivers/rapidio/switches/Kconfig b/drivers/rapidio/switches/Kconfig index 3e18f9c51e29..02771ba3e54f 100644 --- a/drivers/rapidio/switches/Kconfig +++ b/drivers/rapidio/switches/Kconfig @@ -2,22 +2,11 @@ # # RapidIO switches configuration # -config RAPIDIO_TSI57X - tristate "IDT Tsi57x SRIO switches support" - help - Includes support for IDT Tsi57x family of serial RapidIO switches. - config RAPIDIO_CPS_XX tristate "IDT CPS-xx SRIO switches support" help Includes support for IDT CPS-16/12/10/8 serial RapidIO switches. -config RAPIDIO_TSI568 - tristate "Tsi568 SRIO switch support" - default n - help - Includes support for IDT Tsi568 serial RapidIO switch. - config RAPIDIO_CPS_GEN2 tristate "IDT CPS Gen.2 SRIO switch support" default n diff --git a/drivers/rapidio/switches/Makefile b/drivers/rapidio/switches/Makefile index 69e7de31e41c..ef1749a79c2b 100644 --- a/drivers/rapidio/switches/Makefile +++ b/drivers/rapidio/switches/Makefile @@ -3,8 +3,6 @@ # Makefile for RIO switches # -obj-$(CONFIG_RAPIDIO_TSI57X) += tsi57x.o obj-$(CONFIG_RAPIDIO_CPS_XX) += idtcps.o -obj-$(CONFIG_RAPIDIO_TSI568) += tsi568.o obj-$(CONFIG_RAPIDIO_CPS_GEN2) += idt_gen2.o obj-$(CONFIG_RAPIDIO_RXS_GEN3) += idt_gen3.o diff --git a/drivers/rapidio/switches/tsi568.c b/drivers/rapidio/switches/tsi568.c deleted file mode 100644 index 103b48a24980..000000000000 --- a/drivers/rapidio/switches/tsi568.c +++ /dev/null @@ -1,195 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RapidIO Tsi568 switch support - * - * Copyright 2009-2010 Integrated Device Technology, Inc. - * Alexandre Bounine - * - Added EM support - * - Modified switch operations initialization. - * - * Copyright 2005 MontaVista Software, Inc. - * Matt Porter - */ - -#include -#include -#include -#include -#include -#include "../rio.h" - -/* Global (broadcast) route registers */ -#define SPBC_ROUTE_CFG_DESTID 0x10070 -#define SPBC_ROUTE_CFG_PORT 0x10074 - -/* Per port route registers */ -#define SPP_ROUTE_CFG_DESTID(n) (0x11070 + 0x100*n) -#define SPP_ROUTE_CFG_PORT(n) (0x11074 + 0x100*n) - -#define TSI568_SP_MODE(n) (0x11004 + 0x100*n) -#define TSI568_SP_MODE_PW_DIS 0x08000000 - -static int -tsi568_route_add_entry(struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 route_port) -{ - if (table == RIO_GLOBAL_TABLE) { - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_DESTID, route_destid); - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_PORT, route_port); - } else { - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_DESTID(table), - route_destid); - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_PORT(table), route_port); - } - - udelay(10); - - return 0; -} - -static int -tsi568_route_get_entry(struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 *route_port) -{ - int ret = 0; - u32 result; - - if (table == RIO_GLOBAL_TABLE) { - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_DESTID, route_destid); - rio_mport_read_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_PORT, &result); - } else { - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_DESTID(table), - route_destid); - rio_mport_read_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_PORT(table), &result); - } - - *route_port = result; - if (*route_port > 15) - ret = -1; - - return ret; -} - -static int -tsi568_route_clr_table(struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table) -{ - u32 route_idx; - u32 lut_size; - - lut_size = (mport->sys_size) ? 0x1ff : 0xff; - - if (table == RIO_GLOBAL_TABLE) { - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_DESTID, 0x80000000); - for (route_idx = 0; route_idx <= lut_size; route_idx++) - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_PORT, - RIO_INVALID_ROUTE); - } else { - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_DESTID(table), - 0x80000000); - for (route_idx = 0; route_idx <= lut_size; route_idx++) - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_PORT(table), - RIO_INVALID_ROUTE); - } - - return 0; -} - -static int -tsi568_em_init(struct rio_dev *rdev) -{ - u32 regval; - int portnum; - - pr_debug("TSI568 %s [%d:%d]\n", __func__, rdev->destid, rdev->hopcount); - - /* Make sure that Port-Writes are disabled (for all ports) */ - for (portnum = 0; - portnum < RIO_GET_TOTAL_PORTS(rdev->swpinfo); portnum++) { - rio_read_config_32(rdev, TSI568_SP_MODE(portnum), ®val); - rio_write_config_32(rdev, TSI568_SP_MODE(portnum), - regval | TSI568_SP_MODE_PW_DIS); - } - - return 0; -} - -static struct rio_switch_ops tsi568_switch_ops = { - .owner = THIS_MODULE, - .add_entry = tsi568_route_add_entry, - .get_entry = tsi568_route_get_entry, - .clr_table = tsi568_route_clr_table, - .set_domain = NULL, - .get_domain = NULL, - .em_init = tsi568_em_init, - .em_handle = NULL, -}; - -static int tsi568_probe(struct rio_dev *rdev, const struct rio_device_id *id) -{ - pr_debug("RIO: %s for %s\n", __func__, rio_name(rdev)); - - spin_lock(&rdev->rswitch->lock); - - if (rdev->rswitch->ops) { - spin_unlock(&rdev->rswitch->lock); - return -EINVAL; - } - - rdev->rswitch->ops = &tsi568_switch_ops; - spin_unlock(&rdev->rswitch->lock); - return 0; -} - -static void tsi568_remove(struct rio_dev *rdev) -{ - pr_debug("RIO: %s for %s\n", __func__, rio_name(rdev)); - spin_lock(&rdev->rswitch->lock); - if (rdev->rswitch->ops != &tsi568_switch_ops) { - spin_unlock(&rdev->rswitch->lock); - return; - } - rdev->rswitch->ops = NULL; - spin_unlock(&rdev->rswitch->lock); -} - -static const struct rio_device_id tsi568_id_table[] = { - {RIO_DEVICE(RIO_DID_TSI568, RIO_VID_TUNDRA)}, - { 0, } /* terminate list */ -}; - -static struct rio_driver tsi568_driver = { - .name = "tsi568", - .id_table = tsi568_id_table, - .probe = tsi568_probe, - .remove = tsi568_remove, -}; - -static int __init tsi568_init(void) -{ - return rio_register_driver(&tsi568_driver); -} - -static void __exit tsi568_exit(void) -{ - rio_unregister_driver(&tsi568_driver); -} - -device_initcall(tsi568_init); -module_exit(tsi568_exit); - -MODULE_DESCRIPTION("IDT Tsi568 Serial RapidIO switch driver"); -MODULE_AUTHOR("Integrated Device Technology, Inc."); -MODULE_LICENSE("GPL"); diff --git a/drivers/rapidio/switches/tsi57x.c b/drivers/rapidio/switches/tsi57x.c deleted file mode 100644 index 271762046f8c..000000000000 --- a/drivers/rapidio/switches/tsi57x.c +++ /dev/null @@ -1,365 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * RapidIO Tsi57x switch family support - * - * Copyright 2009-2010 Integrated Device Technology, Inc. - * Alexandre Bounine - * - Added EM support - * - Modified switch operations initialization. - * - * Copyright 2005 MontaVista Software, Inc. - * Matt Porter - */ - -#include -#include -#include -#include -#include -#include "../rio.h" - -/* Global (broadcast) route registers */ -#define SPBC_ROUTE_CFG_DESTID 0x10070 -#define SPBC_ROUTE_CFG_PORT 0x10074 - -/* Per port route registers */ -#define SPP_ROUTE_CFG_DESTID(n) (0x11070 + 0x100*n) -#define SPP_ROUTE_CFG_PORT(n) (0x11074 + 0x100*n) - -#define TSI578_SP_MODE(n) (0x11004 + n*0x100) -#define TSI578_SP_MODE_GLBL 0x10004 -#define TSI578_SP_MODE_PW_DIS 0x08000000 -#define TSI578_SP_MODE_LUT_512 0x01000000 - -#define TSI578_SP_CTL_INDEP(n) (0x13004 + n*0x100) -#define TSI578_SP_LUT_PEINF(n) (0x13010 + n*0x100) -#define TSI578_SP_CS_TX(n) (0x13014 + n*0x100) -#define TSI578_SP_INT_STATUS(n) (0x13018 + n*0x100) - -#define TSI578_GLBL_ROUTE_BASE 0x10078 - -static int -tsi57x_route_add_entry(struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 route_port) -{ - if (table == RIO_GLOBAL_TABLE) { - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_DESTID, route_destid); - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_PORT, route_port); - } else { - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_DESTID(table), route_destid); - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_PORT(table), route_port); - } - - udelay(10); - - return 0; -} - -static int -tsi57x_route_get_entry(struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table, u16 route_destid, u8 *route_port) -{ - int ret = 0; - u32 result; - - if (table == RIO_GLOBAL_TABLE) { - /* Use local RT of the ingress port to avoid possible - race condition */ - rio_mport_read_config_32(mport, destid, hopcount, - RIO_SWP_INFO_CAR, &result); - table = (result & RIO_SWP_INFO_PORT_NUM_MASK); - } - - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_DESTID(table), route_destid); - rio_mport_read_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_PORT(table), &result); - - *route_port = (u8)result; - if (*route_port > 15) - ret = -1; - - return ret; -} - -static int -tsi57x_route_clr_table(struct rio_mport *mport, u16 destid, u8 hopcount, - u16 table) -{ - u32 route_idx; - u32 lut_size; - - lut_size = (mport->sys_size) ? 0x1ff : 0xff; - - if (table == RIO_GLOBAL_TABLE) { - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_DESTID, 0x80000000); - for (route_idx = 0; route_idx <= lut_size; route_idx++) - rio_mport_write_config_32(mport, destid, hopcount, - SPBC_ROUTE_CFG_PORT, - RIO_INVALID_ROUTE); - } else { - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_DESTID(table), 0x80000000); - for (route_idx = 0; route_idx <= lut_size; route_idx++) - rio_mport_write_config_32(mport, destid, hopcount, - SPP_ROUTE_CFG_PORT(table) , RIO_INVALID_ROUTE); - } - - return 0; -} - -static int -tsi57x_set_domain(struct rio_mport *mport, u16 destid, u8 hopcount, - u8 sw_domain) -{ - u32 regval; - - /* - * Switch domain configuration operates only at global level - */ - - /* Turn off flat (LUT_512) mode */ - rio_mport_read_config_32(mport, destid, hopcount, - TSI578_SP_MODE_GLBL, ®val); - rio_mport_write_config_32(mport, destid, hopcount, TSI578_SP_MODE_GLBL, - regval & ~TSI578_SP_MODE_LUT_512); - /* Set switch domain base */ - rio_mport_write_config_32(mport, destid, hopcount, - TSI578_GLBL_ROUTE_BASE, - (u32)(sw_domain << 24)); - return 0; -} - -static int -tsi57x_get_domain(struct rio_mport *mport, u16 destid, u8 hopcount, - u8 *sw_domain) -{ - u32 regval; - - /* - * Switch domain configuration operates only at global level - */ - rio_mport_read_config_32(mport, destid, hopcount, - TSI578_GLBL_ROUTE_BASE, ®val); - - *sw_domain = (u8)(regval >> 24); - - return 0; -} - -static int -tsi57x_em_init(struct rio_dev *rdev) -{ - u32 regval; - int portnum; - - pr_debug("TSI578 %s [%d:%d]\n", __func__, rdev->destid, rdev->hopcount); - - for (portnum = 0; - portnum < RIO_GET_TOTAL_PORTS(rdev->swpinfo); portnum++) { - /* Make sure that Port-Writes are enabled (for all ports) */ - rio_read_config_32(rdev, - TSI578_SP_MODE(portnum), ®val); - rio_write_config_32(rdev, - TSI578_SP_MODE(portnum), - regval & ~TSI578_SP_MODE_PW_DIS); - - /* Clear all pending interrupts */ - rio_read_config_32(rdev, - RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum), - ®val); - rio_write_config_32(rdev, - RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum), - regval & 0x07120214); - - rio_read_config_32(rdev, - TSI578_SP_INT_STATUS(portnum), ®val); - rio_write_config_32(rdev, - TSI578_SP_INT_STATUS(portnum), - regval & 0x000700bd); - - /* Enable all interrupts to allow ports to send a port-write */ - rio_read_config_32(rdev, - TSI578_SP_CTL_INDEP(portnum), ®val); - rio_write_config_32(rdev, - TSI578_SP_CTL_INDEP(portnum), - regval | 0x000b0000); - - /* Skip next (odd) port if the current port is in x4 mode */ - rio_read_config_32(rdev, - RIO_DEV_PORT_N_CTL_CSR(rdev, portnum), - ®val); - if ((regval & RIO_PORT_N_CTL_PWIDTH) == RIO_PORT_N_CTL_PWIDTH_4) - portnum++; - } - - /* set TVAL = ~50us */ - rio_write_config_32(rdev, - rdev->phys_efptr + RIO_PORT_LINKTO_CTL_CSR, 0x9a << 8); - - return 0; -} - -static int -tsi57x_em_handler(struct rio_dev *rdev, u8 portnum) -{ - struct rio_mport *mport = rdev->net->hport; - u32 intstat, err_status; - int sendcount, checkcount; - u8 route_port; - u32 regval; - - rio_read_config_32(rdev, - RIO_DEV_PORT_N_ERR_STS_CSR(rdev, portnum), - &err_status); - - if ((err_status & RIO_PORT_N_ERR_STS_PORT_OK) && - (err_status & (RIO_PORT_N_ERR_STS_OUT_ES | - RIO_PORT_N_ERR_STS_INP_ES))) { - /* Remove any queued packets by locking/unlocking port */ - rio_read_config_32(rdev, - RIO_DEV_PORT_N_CTL_CSR(rdev, portnum), - ®val); - if (!(regval & RIO_PORT_N_CTL_LOCKOUT)) { - rio_write_config_32(rdev, - RIO_DEV_PORT_N_CTL_CSR(rdev, portnum), - regval | RIO_PORT_N_CTL_LOCKOUT); - udelay(50); - rio_write_config_32(rdev, - RIO_DEV_PORT_N_CTL_CSR(rdev, portnum), - regval); - } - - /* Read from link maintenance response register to clear - * valid bit - */ - rio_read_config_32(rdev, - RIO_DEV_PORT_N_MNT_RSP_CSR(rdev, portnum), - ®val); - - /* Send a Packet-Not-Accepted/Link-Request-Input-Status control - * symbol to recover from IES/OES - */ - sendcount = 3; - while (sendcount) { - rio_write_config_32(rdev, - TSI578_SP_CS_TX(portnum), 0x40fc8000); - checkcount = 3; - while (checkcount--) { - udelay(50); - rio_read_config_32(rdev, - RIO_DEV_PORT_N_MNT_RSP_CSR(rdev, - portnum), - ®val); - if (regval & RIO_PORT_N_MNT_RSP_RVAL) - goto exit_es; - } - - sendcount--; - } - } - -exit_es: - /* Clear implementation specific error status bits */ - rio_read_config_32(rdev, TSI578_SP_INT_STATUS(portnum), &intstat); - pr_debug("TSI578[%x:%x] SP%d_INT_STATUS=0x%08x\n", - rdev->destid, rdev->hopcount, portnum, intstat); - - if (intstat & 0x10000) { - rio_read_config_32(rdev, - TSI578_SP_LUT_PEINF(portnum), ®val); - regval = (mport->sys_size) ? (regval >> 16) : (regval >> 24); - route_port = rdev->rswitch->route_table[regval]; - pr_debug("RIO: TSI578[%s] P%d LUT Parity Error (destID=%d)\n", - rio_name(rdev), portnum, regval); - tsi57x_route_add_entry(mport, rdev->destid, rdev->hopcount, - RIO_GLOBAL_TABLE, regval, route_port); - } - - rio_write_config_32(rdev, TSI578_SP_INT_STATUS(portnum), - intstat & 0x000700bd); - - return 0; -} - -static struct rio_switch_ops tsi57x_switch_ops = { - .owner = THIS_MODULE, - .add_entry = tsi57x_route_add_entry, - .get_entry = tsi57x_route_get_entry, - .clr_table = tsi57x_route_clr_table, - .set_domain = tsi57x_set_domain, - .get_domain = tsi57x_get_domain, - .em_init = tsi57x_em_init, - .em_handle = tsi57x_em_handler, -}; - -static int tsi57x_probe(struct rio_dev *rdev, const struct rio_device_id *id) -{ - pr_debug("RIO: %s for %s\n", __func__, rio_name(rdev)); - - spin_lock(&rdev->rswitch->lock); - - if (rdev->rswitch->ops) { - spin_unlock(&rdev->rswitch->lock); - return -EINVAL; - } - rdev->rswitch->ops = &tsi57x_switch_ops; - - if (rdev->do_enum) { - /* Ensure that default routing is disabled on startup */ - rio_write_config_32(rdev, RIO_STD_RTE_DEFAULT_PORT, - RIO_INVALID_ROUTE); - } - - spin_unlock(&rdev->rswitch->lock); - return 0; -} - -static void tsi57x_remove(struct rio_dev *rdev) -{ - pr_debug("RIO: %s for %s\n", __func__, rio_name(rdev)); - spin_lock(&rdev->rswitch->lock); - if (rdev->rswitch->ops != &tsi57x_switch_ops) { - spin_unlock(&rdev->rswitch->lock); - return; - } - rdev->rswitch->ops = NULL; - spin_unlock(&rdev->rswitch->lock); -} - -static const struct rio_device_id tsi57x_id_table[] = { - {RIO_DEVICE(RIO_DID_TSI572, RIO_VID_TUNDRA)}, - {RIO_DEVICE(RIO_DID_TSI574, RIO_VID_TUNDRA)}, - {RIO_DEVICE(RIO_DID_TSI577, RIO_VID_TUNDRA)}, - {RIO_DEVICE(RIO_DID_TSI578, RIO_VID_TUNDRA)}, - { 0, } /* terminate list */ -}; - -static struct rio_driver tsi57x_driver = { - .name = "tsi57x", - .id_table = tsi57x_id_table, - .probe = tsi57x_probe, - .remove = tsi57x_remove, -}; - -static int __init tsi57x_init(void) -{ - return rio_register_driver(&tsi57x_driver); -} - -static void __exit tsi57x_exit(void) -{ - rio_unregister_driver(&tsi57x_driver); -} - -device_initcall(tsi57x_init); -module_exit(tsi57x_exit); - -MODULE_DESCRIPTION("IDT Tsi57x Serial RapidIO switch family driver"); -MODULE_AUTHOR("Integrated Device Technology, Inc."); -MODULE_LICENSE("GPL"); diff --git a/include/linux/rio_ids.h b/include/linux/rio_ids.h index e74d8840708a..c7e2f21dd5c1 100644 --- a/include/linux/rio_ids.h +++ b/include/linux/rio_ids.h @@ -9,13 +9,6 @@ #ifndef LINUX_RIO_IDS_H #define LINUX_RIO_IDS_H -#define RIO_VID_TUNDRA 0x000d -#define RIO_DID_TSI568 0x0568 -#define RIO_DID_TSI572 0x0572 -#define RIO_DID_TSI574 0x0574 -#define RIO_DID_TSI577 0x0577 -#define RIO_DID_TSI578 0x0578 - #define RIO_VID_IDT 0x0038 #define RIO_DID_IDT70K200 0x0310 #define RIO_DID_IDTCPS8 0x035c -- cgit v1.2.3 From 0032ca576a79946492194ae4860b462d32815c66 Mon Sep 17 00:00:00 2001 From: Yanteng Si Date: Tue, 21 Dec 2021 17:16:46 +0900 Subject: counter: Add the necessary colons and indents to the comments of counter_compi Since commit aaec1a0f76ec ("counter: Internalize sysfs interface code") introduce a warning as: linux-next/Documentation/driver-api/generic-counter:234: ./include/linux/counter.h:43: WARNING: Unexpected indentation. linux-next/Documentation/driver-api/generic-counter:234: ./include/linux/counter.h:45: WARNING: Block quote ends without a blank line; unexpected unindent. Add the necessary colons and indents. Fixes: aaec1a0f76ec ("counter: Internalize sysfs interface code") Signed-off-by: Yanteng Si Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/26011e814d6eca02c7ebdbb92f171a49928a7e89.1640072891.git.vilhelm.gray@gmail.com Signed-off-by: Greg Kroah-Hartman --- include/linux/counter.h | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/counter.h b/include/linux/counter.h index b7d0a00a61cf..dfbde2808998 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -38,64 +38,64 @@ enum counter_comp_type { * @type: Counter component data type * @name: device-specific component name * @priv: component-relevant data - * @action_read Synapse action mode read callback. The read value of the + * @action_read: Synapse action mode read callback. The read value of the * respective Synapse action mode should be passed back via * the action parameter. - * @device_u8_read Device u8 component read callback. The read value of the + * @device_u8_read: Device u8 component read callback. The read value of the * respective Device u8 component should be passed back via * the val parameter. - * @count_u8_read Count u8 component read callback. The read value of the + * @count_u8_read: Count u8 component read callback. The read value of the * respective Count u8 component should be passed back via * the val parameter. - * @signal_u8_read Signal u8 component read callback. The read value of the + * @signal_u8_read: Signal u8 component read callback. The read value of the * respective Signal u8 component should be passed back via * the val parameter. - * @device_u32_read Device u32 component read callback. The read value of + * @device_u32_read: Device u32 component read callback. The read value of * the respective Device u32 component should be passed * back via the val parameter. - * @count_u32_read Count u32 component read callback. The read value of the + * @count_u32_read: Count u32 component read callback. The read value of the * respective Count u32 component should be passed back via * the val parameter. - * @signal_u32_read Signal u32 component read callback. The read value of + * @signal_u32_read: Signal u32 component read callback. The read value of * the respective Signal u32 component should be passed * back via the val parameter. - * @device_u64_read Device u64 component read callback. The read value of + * @device_u64_read: Device u64 component read callback. The read value of * the respective Device u64 component should be passed * back via the val parameter. - * @count_u64_read Count u64 component read callback. The read value of the + * @count_u64_read: Count u64 component read callback. The read value of the * respective Count u64 component should be passed back via * the val parameter. - * @signal_u64_read Signal u64 component read callback. The read value of + * @signal_u64_read: Signal u64 component read callback. The read value of * the respective Signal u64 component should be passed * back via the val parameter. - * @action_write Synapse action mode write callback. The write value of + * @action_write: Synapse action mode write callback. The write value of * the respective Synapse action mode is passed via the * action parameter. - * @device_u8_write Device u8 component write callback. The write value of + * @device_u8_write: Device u8 component write callback. The write value of * the respective Device u8 component is passed via the val * parameter. - * @count_u8_write Count u8 component write callback. The write value of + * @count_u8_write: Count u8 component write callback. The write value of * the respective Count u8 component is passed via the val * parameter. - * @signal_u8_write Signal u8 component write callback. The write value of + * @signal_u8_write: Signal u8 component write callback. The write value of * the respective Signal u8 component is passed via the val * parameter. - * @device_u32_write Device u32 component write callback. The write value of + * @device_u32_write: Device u32 component write callback. The write value of * the respective Device u32 component is passed via the * val parameter. - * @count_u32_write Count u32 component write callback. The write value of + * @count_u32_write: Count u32 component write callback. The write value of * the respective Count u32 component is passed via the val * parameter. - * @signal_u32_write Signal u32 component write callback. The write value of + * @signal_u32_write: Signal u32 component write callback. The write value of * the respective Signal u32 component is passed via the * val parameter. - * @device_u64_write Device u64 component write callback. The write value of + * @device_u64_write: Device u64 component write callback. The write value of * the respective Device u64 component is passed via the * val parameter. - * @count_u64_write Count u64 component write callback. The write value of + * @count_u64_write: Count u64 component write callback. The write value of * the respective Count u64 component is passed via the val * parameter. - * @signal_u64_write Signal u64 component write callback. The write value of + * @signal_u64_write: Signal u64 component write callback. The write value of * the respective Signal u64 component is passed via the * val parameter. */ -- cgit v1.2.3 From 79f1c7304295bbbc611bc53cfd5425b777b3e840 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 9 Dec 2021 14:30:08 +0200 Subject: kernfs: Replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Acked-by: Tejun Heo Signed-off-by: Andy Shevchenko Link: https://lore.kernel.org/r/20211209123008.3391-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/kernfs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 9f650986a81b..861c4f0f8a29 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -6,7 +6,6 @@ #ifndef __LINUX_KERNFS_H #define __LINUX_KERNFS_H -#include #include #include #include @@ -14,6 +13,8 @@ #include #include #include +#include +#include #include #include #include @@ -23,6 +24,7 @@ struct dentry; struct iattr; struct seq_file; struct vm_area_struct; +struct vm_operations_struct; struct super_block; struct file_system_type; struct poll_table_struct; -- cgit v1.2.3 From eca6e2d4a4a4b824f055eeaaa24f1c2327fb91a2 Mon Sep 17 00:00:00 2001 From: Anand Ashok Dumbre Date: Fri, 3 Dec 2021 21:23:54 +0000 Subject: device property: Add fwnode_iomap() This patch introduces a new helper routine - fwnode_iomap(), which allows to map the memory mapped IO for a given device node. This implementation does not cover the ACPI case and may be expanded in the future. The main purpose here is to be able to develop resource provider agnostic drivers. Suggested-by: Andy Shevchenko Signed-off-by: Anand Ashok Dumbre Reviewed-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20211203212358.31444-2-anand.ashok.dumbre@xilinx.com Signed-off-by: Jonathan Cameron --- drivers/base/property.c | 16 ++++++++++++++++ include/linux/property.h | 2 ++ 2 files changed, 18 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index f1f35b48ab8b..ed4470410030 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -958,6 +958,22 @@ int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index) } EXPORT_SYMBOL(fwnode_irq_get); +/** + * fwnode_iomap - Maps the memory mapped IO for a given fwnode + * @fwnode: Pointer to the firmware node + * @index: Index of the IO range + * + * Returns a pointer to the mapped memory. + */ +void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index) +{ + if (IS_ENABLED(CONFIG_OF_ADDRESS) && is_of_node(fwnode)) + return of_iomap(to_of_node(fwnode), index); + + return NULL; +} +EXPORT_SYMBOL(fwnode_iomap); + /** * fwnode_graph_get_next_endpoint - Get next endpoint firmware node * @fwnode: Pointer to the parent firmware node diff --git a/include/linux/property.h b/include/linux/property.h index 88fa726a76df..6670d5a1ec2a 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -122,6 +122,8 @@ void fwnode_handle_put(struct fwnode_handle *fwnode); int fwnode_irq_get(const struct fwnode_handle *fwnode, unsigned int index); +void __iomem *fwnode_iomap(struct fwnode_handle *fwnode, int index); + unsigned int device_get_child_node_count(struct device *dev); static inline bool device_property_read_bool(struct device *dev, -- cgit v1.2.3 From 1b0b6cc8030d08d2a24e9e5f85dc36c5a58200ba Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Wed, 24 Nov 2021 00:27:01 +0100 Subject: power: supply: add charge_behaviour attributes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This a revised version of "[RFC] add standardized attributes for force_discharge and inhibit_charge" [0], incorporating discussion results. The biggest change is the switch from two boolean attributes to a single enum attribute. [0] https://lore.kernel.org/platform-driver-x86/21569a89-8303-8573-05fb-c2fec29983d1@gmail.com/ Signed-off-by: Thomas Weißschuh Acked-by: Sebastian Reichel Link: https://lore.kernel.org/r/20211123232704.25394-2-linux@weissschuh.net Signed-off-by: Hans de Goede --- Documentation/ABI/testing/sysfs-class-power | 14 ++++++++++++++ include/linux/power_supply.h | 7 +++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power index f7904efc4cfa..cece094764f8 100644 --- a/Documentation/ABI/testing/sysfs-class-power +++ b/Documentation/ABI/testing/sysfs-class-power @@ -455,6 +455,20 @@ Description: "Unknown", "Charging", "Discharging", "Not charging", "Full" +What: /sys/class/power_supply//charge_behaviour +Date: November 2021 +Contact: linux-pm@vger.kernel.org +Description: + Represents the charging behaviour. + + Access: Read, Write + + Valid values: + ================ ==================================== + auto: Charge normally, respect thresholds + inhibit-charge: Do not charge while AC is attached + force-discharge: Force discharge while AC is attached + What: /sys/class/power_supply//technology Date: May 2007 Contact: linux-pm@vger.kernel.org diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 9ca1f120a211..70c333e86293 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -132,6 +132,7 @@ enum power_supply_property { POWER_SUPPLY_PROP_CHARGE_CONTROL_LIMIT_MAX, POWER_SUPPLY_PROP_CHARGE_CONTROL_START_THRESHOLD, /* in percents! */ POWER_SUPPLY_PROP_CHARGE_CONTROL_END_THRESHOLD, /* in percents! */ + POWER_SUPPLY_PROP_CHARGE_BEHAVIOUR, POWER_SUPPLY_PROP_INPUT_CURRENT_LIMIT, POWER_SUPPLY_PROP_INPUT_VOLTAGE_LIMIT, POWER_SUPPLY_PROP_INPUT_POWER_LIMIT, @@ -202,6 +203,12 @@ enum power_supply_usb_type { POWER_SUPPLY_USB_TYPE_APPLE_BRICK_ID, /* Apple Charging Method */ }; +enum power_supply_charge_behaviour { + POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO = 0, + POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE, + POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE, +}; + enum power_supply_notifier_events { PSY_EVENT_PROP_CHANGED, }; -- cgit v1.2.3 From 539b9c94ac83563842a27e8cc3de5164b15c4de0 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Wed, 24 Nov 2021 00:27:02 +0100 Subject: power: supply: add helpers for charge_behaviour sysfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit These helper functions can be used by drivers to implement their own sysfs-attributes. This is useful for ACPI-drivers extending the default ACPI-battery with their own charge_behaviour attributes. Signed-off-by: Thomas Weißschuh Acked-by: Sebastian Reichel Link: https://lore.kernel.org/r/20211123232704.25394-3-linux@weissschuh.net Signed-off-by: Hans de Goede --- drivers/power/supply/power_supply_sysfs.c | 55 +++++++++++++++++++++++++++++++ include/linux/power_supply.h | 9 +++++ 2 files changed, 64 insertions(+) (limited to 'include/linux') diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c index c3d7cbcd4fad..5e3b8c15ddbe 100644 --- a/drivers/power/supply/power_supply_sysfs.c +++ b/drivers/power/supply/power_supply_sysfs.c @@ -133,6 +133,12 @@ static const char * const POWER_SUPPLY_SCOPE_TEXT[] = { [POWER_SUPPLY_SCOPE_DEVICE] = "Device", }; +static const char * const POWER_SUPPLY_CHARGE_BEHAVIOUR_TEXT[] = { + [POWER_SUPPLY_CHARGE_BEHAVIOUR_AUTO] = "auto", + [POWER_SUPPLY_CHARGE_BEHAVIOUR_INHIBIT_CHARGE] = "inhibit-charge", + [POWER_SUPPLY_CHARGE_BEHAVIOUR_FORCE_DISCHARGE] = "force-discharge", +}; + static struct power_supply_attr power_supply_attrs[] = { /* Properties of type `int' */ POWER_SUPPLY_ENUM_ATTR(STATUS), @@ -484,3 +490,52 @@ out: return ret; } + +ssize_t power_supply_charge_behaviour_show(struct device *dev, + unsigned int available_behaviours, + enum power_supply_charge_behaviour current_behaviour, + char *buf) +{ + bool match = false, available, active; + ssize_t count = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(POWER_SUPPLY_CHARGE_BEHAVIOUR_TEXT); i++) { + available = available_behaviours & BIT(i); + active = i == current_behaviour; + + if (available && active) { + count += sysfs_emit_at(buf, count, "[%s] ", + POWER_SUPPLY_CHARGE_BEHAVIOUR_TEXT[i]); + match = true; + } else if (available) { + count += sysfs_emit_at(buf, count, "%s ", + POWER_SUPPLY_CHARGE_BEHAVIOUR_TEXT[i]); + } + } + + if (!match) { + dev_warn(dev, "driver reporting unsupported charge behaviour\n"); + return -EINVAL; + } + + if (count) + buf[count - 1] = '\n'; + + return count; +} +EXPORT_SYMBOL_GPL(power_supply_charge_behaviour_show); + +int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf) +{ + int i = sysfs_match_string(POWER_SUPPLY_CHARGE_BEHAVIOUR_TEXT, buf); + + if (i < 0) + return i; + + if (available_behaviours & BIT(i)) + return i; + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(power_supply_charge_behaviour_parse); diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 70c333e86293..71f0379c2af8 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -546,4 +546,13 @@ static inline void power_supply_remove_hwmon_sysfs(struct power_supply *psy) {} #endif +#ifdef CONFIG_SYSFS +ssize_t power_supply_charge_behaviour_show(struct device *dev, + unsigned int available_behaviours, + enum power_supply_charge_behaviour behaviour, + char *buf); + +int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf); +#endif + #endif /* __LINUX_POWER_SUPPLY_H__ */ -- cgit v1.2.3 From 37ae5a0f5287a52cf51242e76ccf198d02ffe495 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Sat, 18 Dec 2021 18:41:56 +0900 Subject: block: use "unsigned long" for blk_validate_block_size(). Since lo_simple_ioctl(LOOP_SET_BLOCK_SIZE) and ioctl(NBD_SET_BLKSIZE) pass user-controlled "unsigned long arg" to blk_validate_block_size(), "unsigned long" should be used for validation. Signed-off-by: Tetsuo Handa Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/9ecbf057-4375-c2db-ab53-e4cc0dff953d@i-love.sakura.ne.jp Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c80cfaefc0a8..bb5fb7282e6e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -45,7 +45,7 @@ struct blk_crypto_profile; */ #define BLKCG_MAX_POLS 6 -static inline int blk_validate_block_size(unsigned int bsize) +static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; -- cgit v1.2.3 From dcce50e6cc4d86a63dc0a9a6ee7d4f948ccd53a1 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Mon, 8 Nov 2021 14:35:59 -0800 Subject: compiler.h: Fix annotation macro misplacement with Clang When building with Clang and CONFIG_TRACE_BRANCH_PROFILING, there are a lot of unreachable warnings, like: arch/x86/kernel/traps.o: warning: objtool: handle_xfd_event()+0x134: unreachable instruction Without an input to the inline asm, 'volatile' is ignored for some reason and Clang feels free to move the reachable() annotation away from its intended location. Fix that by re-adding the counter value to the inputs. Fixes: f1069a8756b9 ("compiler.h: Avoid using inline asm operand modifiers") Fixes: c199f64ff93c ("instrumentation.h: Avoid using inline asm operand modifiers") Reported-by: kernel test robot Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/0417e96909b97a406323409210de7bf13df0b170.1636410380.git.jpoimboe@redhat.com Cc: Peter Zijlstra Cc: x86@kernel.org Cc: Vasily Gorbik Cc: Miroslav Benes --- include/linux/compiler.h | 4 ++-- include/linux/instrumentation.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 3d5af56337bd..429dcebe2b99 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -121,7 +121,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.reachable\n\t" \ ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define annotate_reachable() __annotate_reachable(__COUNTER__) @@ -129,7 +129,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define annotate_unreachable() __annotate_unreachable(__COUNTER__) diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h index fa2cd8c63dcc..24359b4a9605 100644 --- a/include/linux/instrumentation.h +++ b/include/linux/instrumentation.h @@ -11,7 +11,7 @@ asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_begin\n\t" \ ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_begin() __instrumentation_begin(__COUNTER__) @@ -50,7 +50,7 @@ asm volatile(__stringify(c) ": nop\n\t" \ ".pushsection .discard.instr_end\n\t" \ ".long " __stringify(c) "b - .\n\t" \ - ".popsection\n\t"); \ + ".popsection\n\t" : : "i" (c)); \ }) #define instrumentation_end() __instrumentation_end(__COUNTER__) #else -- cgit v1.2.3 From f857acfc457ea63fa5b862d77f055665d863acfe Mon Sep 17 00:00:00 2001 From: Logan Gunthorpe Date: Wed, 17 Nov 2021 14:53:48 -0700 Subject: lib/scatterlist: cleanup macros into static inline functions Convert the sg_is_chain(), sg_is_last() and sg_chain_ptr() macros into static inline functions. There's no reason for these to be macros and static inline are generally preferred these days. Also introduce the SG_PAGE_LINK_MASK define so the P2PDMA work, which is adding another bit to this mask, can do so more easily. Suggested-by: Jason Gunthorpe Signed-off-by: Logan Gunthorpe Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/scatterlist.h | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h index 266754a55327..7ff9d6386c12 100644 --- a/include/linux/scatterlist.h +++ b/include/linux/scatterlist.h @@ -69,10 +69,27 @@ struct sg_append_table { * a valid sg entry, or whether it points to the start of a new scatterlist. * Those low bits are there for everyone! (thanks mason :-) */ -#define sg_is_chain(sg) ((sg)->page_link & SG_CHAIN) -#define sg_is_last(sg) ((sg)->page_link & SG_END) -#define sg_chain_ptr(sg) \ - ((struct scatterlist *) ((sg)->page_link & ~(SG_CHAIN | SG_END))) +#define SG_PAGE_LINK_MASK (SG_CHAIN | SG_END) + +static inline unsigned int __sg_flags(struct scatterlist *sg) +{ + return sg->page_link & SG_PAGE_LINK_MASK; +} + +static inline struct scatterlist *sg_chain_ptr(struct scatterlist *sg) +{ + return (struct scatterlist *)(sg->page_link & ~SG_PAGE_LINK_MASK); +} + +static inline bool sg_is_chain(struct scatterlist *sg) +{ + return __sg_flags(sg) & SG_CHAIN; +} + +static inline bool sg_is_last(struct scatterlist *sg) +{ + return __sg_flags(sg) & SG_END; +} /** * sg_assign_page - Assign a given page to an SG entry @@ -92,7 +109,7 @@ static inline void sg_assign_page(struct scatterlist *sg, struct page *page) * In order for the low bit stealing approach to work, pages * must be aligned at a 32-bit boundary as a minimum. */ - BUG_ON((unsigned long) page & (SG_CHAIN | SG_END)); + BUG_ON((unsigned long)page & SG_PAGE_LINK_MASK); #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif @@ -126,7 +143,7 @@ static inline struct page *sg_page(struct scatterlist *sg) #ifdef CONFIG_DEBUG_SG BUG_ON(sg_is_chain(sg)); #endif - return (struct page *)((sg)->page_link & ~(SG_CHAIN | SG_END)); + return (struct page *)((sg)->page_link & ~SG_PAGE_LINK_MASK); } /** -- cgit v1.2.3 From 365481e42a8a95c55e43e8cc236138718e762e7b Mon Sep 17 00:00:00 2001 From: "David E. Box" Date: Tue, 7 Dec 2021 17:50:11 -0800 Subject: driver core: auxiliary bus: Add driver data helpers Adds get/set driver data helpers for auxiliary devices. Reviewed-by: Mark Gross Reviewed-by: Andy Shevchenko Signed-off-by: David E. Box Link: https://lore.kernel.org/r/20211208015015.891275-3-david.e.box@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/linux/auxiliary_bus.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h index e6d8b5c16226..de21d9d24a95 100644 --- a/include/linux/auxiliary_bus.h +++ b/include/linux/auxiliary_bus.h @@ -188,6 +188,16 @@ struct auxiliary_driver { const struct auxiliary_device_id *id_table; }; +static inline void *auxiliary_get_drvdata(struct auxiliary_device *auxdev) +{ + return dev_get_drvdata(&auxdev->dev); +} + +static inline void auxiliary_set_drvdata(struct auxiliary_device *auxdev, void *data) +{ + dev_set_drvdata(&auxdev->dev, data); +} + static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev) { return container_of(dev, struct auxiliary_device, dev); -- cgit v1.2.3 From b398123bff3bcbc1facb0f29bf6e7b9f1bc55931 Mon Sep 17 00:00:00 2001 From: Pingfan Liu Date: Wed, 15 Dec 2021 10:13:48 +0800 Subject: efi: apply memblock cap after memblock_add() On arm64, during kdump kernel saves vmcore, it runs into the following bug: ... [ 15.148919] usercopy: Kernel memory exposure attempt detected from SLUB object 'kmem_cache_node' (offset 0, size 4096)! [ 15.159707] ------------[ cut here ]------------ [ 15.164311] kernel BUG at mm/usercopy.c:99! [ 15.168482] Internal error: Oops - BUG: 0 [#1] SMP [ 15.173261] Modules linked in: xfs libcrc32c crct10dif_ce ghash_ce sha2_ce sha256_arm64 sha1_ce sbsa_gwdt ast i2c_algo_bit drm_vram_helper drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops cec drm_ttm_helper ttm drm nvme nvme_core xgene_hwmon i2c_designware_platform i2c_designware_core dm_mirror dm_region_hash dm_log dm_mod overlay squashfs zstd_decompress loop [ 15.206186] CPU: 0 PID: 542 Comm: cp Not tainted 5.16.0-rc4 #1 [ 15.212006] Hardware name: GIGABYTE R272-P30-JG/MP32-AR0-JG, BIOS F12 (SCP: 1.5.20210426) 05/13/2021 [ 15.221125] pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 15.228073] pc : usercopy_abort+0x9c/0xa0 [ 15.232074] lr : usercopy_abort+0x9c/0xa0 [ 15.236070] sp : ffff8000121abba0 [ 15.239371] x29: ffff8000121abbb0 x28: 0000000000003000 x27: 0000000000000000 [ 15.246494] x26: 0000000080000400 x25: 0000ffff885c7000 x24: 0000000000000000 [ 15.253617] x23: 000007ff80400000 x22: ffff07ff80401000 x21: 0000000000000001 [ 15.260739] x20: 0000000000001000 x19: ffff07ff80400000 x18: ffffffffffffffff [ 15.267861] x17: 656a626f2042554c x16: 53206d6f72662064 x15: 6574636574656420 [ 15.274983] x14: 74706d6574746120 x13: 2129363930342065 x12: 7a6973202c302074 [ 15.282105] x11: ffffc8b041d1b148 x10: 00000000ffff8000 x9 : ffffc8b04012812c [ 15.289228] x8 : 00000000ffff7fff x7 : ffffc8b041d1b148 x6 : 0000000000000000 [ 15.296349] x5 : 0000000000000000 x4 : 0000000000007fff x3 : 0000000000000000 [ 15.303471] x2 : 0000000000000000 x1 : ffff07ff8c064800 x0 : 000000000000006b [ 15.310593] Call trace: [ 15.313027] usercopy_abort+0x9c/0xa0 [ 15.316677] __check_heap_object+0xd4/0xf0 [ 15.320762] __check_object_size.part.0+0x160/0x1e0 [ 15.325628] __check_object_size+0x2c/0x40 [ 15.329711] copy_oldmem_page+0x7c/0x140 [ 15.333623] read_from_oldmem.part.0+0xfc/0x1c0 [ 15.338142] __read_vmcore.constprop.0+0x23c/0x350 [ 15.342920] read_vmcore+0x28/0x34 [ 15.346309] proc_reg_read+0xb4/0xf0 [ 15.349871] vfs_read+0xb8/0x1f0 [ 15.353088] ksys_read+0x74/0x100 [ 15.356390] __arm64_sys_read+0x28/0x34 ... This bug introduced by commit b261dba2fdb2 ("arm64: kdump: Remove custom linux,usable-memory-range handling"), which moves memblock_cap_memory_range() to fdt, but it breaches the rules that memblock_cap_memory_range() should come after memblock_add() etc as said in commit e888fa7bb882 ("memblock: Check memory add/cap ordering"). As a consequence, the virtual address set up by copy_oldmem_page() does not bail out from the test of virt_addr_valid() in check_heap_object(), and finally hits the BUG_ON(). Since memblock allocator has no idea about when the memblock is fully populated, while efi_init() is aware, so tackling this issue by calling the interface early_init_dt_check_for_usable_mem_range() exposed by of/fdt. Fixes: b261dba2fdb2 ("arm64: kdump: Remove custom linux,usable-memory-range handling") Signed-off-by: Pingfan Liu Cc: Rob Herring Cc: Zhen Lei Cc: Catalin Marinas Cc: Will Deacon Cc: Andrew Morton Cc: Mike Rapoport Cc: Geert Uytterhoeven Cc: Frank Rowand Cc: Ard Biesheuvel Cc: Nick Terrell Cc: linux-arm-kernel@lists.infradead.org To: devicetree@vger.kernel.org To: linux-efi@vger.kernel.org Acked-by: Ard Biesheuvel Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20211215021348.8766-1-kernelfans@gmail.com --- drivers/firmware/efi/efi-init.c | 5 +++++ drivers/of/fdt.c | 2 +- include/linux/of_fdt.h | 2 ++ 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index b19ce1a83f91..b2c829e95bd1 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -235,6 +235,11 @@ void __init efi_init(void) } reserve_regions(); + /* + * For memblock manipulation, the cap should come after the memblock_add(). + * And now, memblock is fully populated, it is time to do capping. + */ + early_init_dt_check_for_usable_mem_range(); efi_esrt_init(); efi_mokvar_table_init(); diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 5a238a933eb2..65af475dfa95 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -971,7 +971,7 @@ static unsigned long chosen_node_offset = -FDT_ERR_NOTFOUND; * early_init_dt_check_for_usable_mem_range - Decode usable memory range * location from flat tree */ -static void __init early_init_dt_check_for_usable_mem_range(void) +void __init early_init_dt_check_for_usable_mem_range(void) { const __be32 *prop; int len; diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index cf48983d3c86..ad09beb6d13c 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -62,6 +62,7 @@ extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data); extern int early_init_dt_scan_memory(unsigned long node, const char *uname, int depth, void *data); +extern void early_init_dt_check_for_usable_mem_range(void); extern int early_init_dt_scan_chosen_stdout(void); extern void early_init_fdt_scan_reserved_mem(void); extern void early_init_fdt_reserve_self(void); @@ -86,6 +87,7 @@ extern void unflatten_and_copy_device_tree(void); extern void early_init_devtree(void *); extern void early_get_first_memblock_info(void *, phys_addr_t *); #else /* CONFIG_OF_EARLY_FLATTREE */ +static inline void early_init_dt_check_for_usable_mem_range(void) {} static inline int early_init_dt_scan_chosen_stdout(void) { return -ENODEV; } static inline void early_init_fdt_scan_reserved_mem(void) {} static inline void early_init_fdt_reserve_self(void) {} -- cgit v1.2.3 From f2f8115fe8b390af27d013411045bd712a812103 Mon Sep 17 00:00:00 2001 From: Roger Quadros Date: Tue, 21 Dec 2021 15:17:56 +0200 Subject: memory: omap-gpmc: Use a compatible match table when checking for NAND controller As more compatibles can be added to the GPMC NAND controller driver use a compatible match table. Signed-off-by: Roger Quadros Acked-by: Miquel Raynal Link: https://lore.kernel.org/r/20211221131757.2030-4-rogerq@kernel.org [krzysztof: remove "is_nand" variable] Signed-off-by: Krzysztof Kozlowski --- drivers/memory/omap-gpmc.c | 2 +- drivers/mtd/nand/raw/omap2.c | 5 +---- include/linux/platform_data/mtd-nand-omap2.h | 9 ++++++++- 3 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 5e2ba39b6450..ed11887c1b7c 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -2183,7 +2183,7 @@ static int gpmc_probe_generic_child(struct platform_device *pdev, } } - if (of_device_is_compatible(child, "ti,omap2-nand")) { + if (of_match_node(omap_nand_ids, child)) { /* NAND specific setup */ val = 8; of_property_read_u32(child, "nand-bus-width", &val); diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c index b26d4947af02..e6dd8b4cf0d2 100644 --- a/drivers/mtd/nand/raw/omap2.c +++ b/drivers/mtd/nand/raw/omap2.c @@ -2352,10 +2352,7 @@ static int omap_nand_remove(struct platform_device *pdev) return ret; } -static const struct of_device_id omap_nand_ids[] = { - { .compatible = "ti,omap2-nand", }, - {}, -}; +/* omap_nand_ids defined in linux/platform_data/mtd-nand-omap2.h */ MODULE_DEVICE_TABLE(of, omap_nand_ids); static struct platform_driver omap_nand_driver = { diff --git a/include/linux/platform_data/mtd-nand-omap2.h b/include/linux/platform_data/mtd-nand-omap2.h index de6ada739121..92f011805ad4 100644 --- a/include/linux/platform_data/mtd-nand-omap2.h +++ b/include/linux/platform_data/mtd-nand-omap2.h @@ -7,6 +7,7 @@ #define _MTD_NAND_OMAP2_H #include +#include #define GPMC_BCH_NUM_REMAINDER 8 @@ -61,4 +62,10 @@ struct gpmc_nand_regs { void __iomem *gpmc_bch_result5[GPMC_BCH_NUM_REMAINDER]; void __iomem *gpmc_bch_result6[GPMC_BCH_NUM_REMAINDER]; }; -#endif + +static const struct of_device_id omap_nand_ids[] = { + { .compatible = "ti,omap2-nand", }, + {}, +}; + +#endif /* _MTD_NAND_OMAP2_H */ -- cgit v1.2.3 From d7f55471db2719629f773c2d6b5742a69595bfd3 Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Fri, 17 Dec 2021 10:07:54 +0800 Subject: memblock: fix memblock_phys_alloc() section mismatch error Fix modpost Section mismatch error in memblock_phys_alloc() [...] WARNING: modpost: vmlinux.o(.text.unlikely+0x1dcc): Section mismatch in reference from the function memblock_phys_alloc() to the function .init.text:memblock_phys_alloc_range() The function memblock_phys_alloc() references the function __init memblock_phys_alloc_range(). This is often because memblock_phys_alloc lacks a __init annotation or the annotation of memblock_phys_alloc_range is wrong. ERROR: modpost: Section mismatches detected. Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them. [...] memblock_phys_alloc() is a one-line wrapper, make it __always_inline to avoid these section mismatches. Reported-by: k2ci Suggested-by: Mike Rapoport Signed-off-by: Jackie Liu [rppt: slightly massaged changelog ] Signed-off-by: Mike Rapoport Link: https://lore.kernel.org/r/20211217020754.2874872-1-liu.yun@linux.dev --- include/linux/memblock.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 8adcf1fa8096..9dc7cb239d21 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -405,8 +405,8 @@ phys_addr_t memblock_alloc_range_nid(phys_addr_t size, phys_addr_t end, int nid, bool exact_nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -static inline phys_addr_t memblock_phys_alloc(phys_addr_t size, - phys_addr_t align) +static __always_inline phys_addr_t memblock_phys_alloc(phys_addr_t size, + phys_addr_t align) { return memblock_phys_alloc_range(size, align, 0, MEMBLOCK_ALLOC_ACCESSIBLE); -- cgit v1.2.3 From 6fd3c510ee4b37f2f9fe3d3cafbfa459e15c5e11 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 22 Dec 2021 13:15:32 -0800 Subject: bio.h: fix kernel-doc warnings Fix all kernel-doc warnings in : include/linux/bio.h:136: warning: Function parameter or member 'nbytes' not described in 'bio_advance' include/linux/bio.h:136: warning: Excess function parameter 'bytes' description in 'bio_advance' include/linux/bio.h:391: warning: No description found for return value of 'bio_next_split' Signed-off-by: Randy Dunlap Cc: Kent Overstreet Cc: Jens Axboe Cc: linux-block@vger.kernel.org Link: https://lore.kernel.org/r/20211222211532.24060-1-rdunlap@infradead.org Signed-off-by: Jens Axboe --- include/linux/bio.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index fe6bdfbbef66..0a41efe02208 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -124,7 +124,7 @@ void __bio_advance(struct bio *, unsigned bytes); /** * bio_advance - increment/complete a bio by some number of bytes * @bio: bio to advance - * @bytes: number of bytes to complete + * @nbytes: number of bytes to complete * * This updates bi_sector, bi_size and bi_idx; if the number of bytes to * complete doesn't align with a bvec boundary, then bv_len and bv_offset will @@ -332,7 +332,7 @@ extern struct bio *bio_split(struct bio *bio, int sectors, * @gfp: gfp mask * @bs: bio set to allocate from * - * Returns a bio representing the next @sectors of @bio - if the bio is smaller + * Return: a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, -- cgit v1.2.3 From a16c7246368db8935652c805bc446928d0e1c0aa Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 22 Dec 2021 13:52:39 -0800 Subject: block: remove unnecessary trailing '\' While harmless, the blank line is certainly not intended to be part of the rq_list_for_each() macro. Remove it. Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20211222215239.1768164-1-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5fb7282e6e..22746b2d6825 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1363,7 +1363,7 @@ struct io_comp_batch { }) #define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) #define rq_list_next(rq) (rq)->rq_next #define rq_list_empty(list) ((list) == (struct request *) NULL) -- cgit v1.2.3 From 6e1fcab00a23f7fe9f4fe9704905a790efa1eeab Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 20 Dec 2021 19:21:26 +0800 Subject: scsi: block: pm: Always set request queue runtime active in blk_post_runtime_resume() John Garry reported a deadlock that occurs when trying to access a runtime-suspended SATA device. For obscure reasons, the rescan procedure causes the link to be hard-reset, which disconnects the device. The rescan tries to carry out a runtime resume when accessing the device. scsi_rescan_device() holds the SCSI device lock and won't release it until it can put commands onto the device's block queue. This can't happen until the queue is successfully runtime-resumed or the device is unregistered. But the runtime resume fails because the device is disconnected, and __scsi_remove_device() can't do the unregistration because it can't get the device lock. The best way to resolve this deadlock appears to be to allow the block queue to start running again even after an unsuccessful runtime resume. The idea is that the driver or the SCSI error handler will need to be able to use the queue to resolve the runtime resume failure. This patch removes the err argument to blk_post_runtime_resume() and makes the routine act as though the resume was successful always. This fixes the deadlock. Link: https://lore.kernel.org/r/1639999298-244569-4-git-send-email-chenxiang66@hisilicon.com Fixes: e27829dc92e5 ("scsi: serialize ->rescan against ->remove") Reported-and-tested-by: John Garry Reviewed-by: Bart Van Assche Signed-off-by: Alan Stern Signed-off-by: Xiang Chen Signed-off-by: Martin K. Petersen --- block/blk-pm.c | 22 +++++++--------------- drivers/scsi/scsi_pm.c | 2 +- include/linux/blk-pm.h | 2 +- 3 files changed, 9 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/block/blk-pm.c b/block/blk-pm.c index 17bd020268d4..2dad62cc1572 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -163,27 +163,19 @@ EXPORT_SYMBOL(blk_pre_runtime_resume); /** * blk_post_runtime_resume - Post runtime resume processing * @q: the queue of the device - * @err: return value of the device's runtime_resume function * * Description: - * Update the queue's runtime status according to the return value of the - * device's runtime_resume function. If the resume was successful, call - * blk_set_runtime_active() to do the real work of restarting the queue. + * For historical reasons, this routine merely calls blk_set_runtime_active() + * to do the real work of restarting the queue. It does this regardless of + * whether the device's runtime-resume succeeded; even if it failed the + * driver or error handler will need to communicate with the device. * * This function should be called near the end of the device's * runtime_resume callback. */ -void blk_post_runtime_resume(struct request_queue *q, int err) +void blk_post_runtime_resume(struct request_queue *q) { - if (!q->dev) - return; - if (!err) { - blk_set_runtime_active(q); - } else { - spin_lock_irq(&q->queue_lock); - q->rpm_status = RPM_SUSPENDED; - spin_unlock_irq(&q->queue_lock); - } + blk_set_runtime_active(q); } EXPORT_SYMBOL(blk_post_runtime_resume); @@ -201,7 +193,7 @@ EXPORT_SYMBOL(blk_post_runtime_resume); * runtime PM status and re-enable peeking requests from the queue. It * should be called before first request is added to the queue. * - * This function is also called by blk_post_runtime_resume() for successful + * This function is also called by blk_post_runtime_resume() for * runtime resumes. It does everything necessary to restart the queue. */ void blk_set_runtime_active(struct request_queue *q) diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c index 0e841e8761c5..d581613d87c7 100644 --- a/drivers/scsi/scsi_pm.c +++ b/drivers/scsi/scsi_pm.c @@ -180,7 +180,7 @@ static int sdev_runtime_resume(struct device *dev) blk_pre_runtime_resume(sdev->request_queue); if (pm && pm->runtime_resume) err = pm->runtime_resume(dev); - blk_post_runtime_resume(sdev->request_queue, err); + blk_post_runtime_resume(sdev->request_queue); return err; } diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h index b80c65aba249..2580e05a8ab6 100644 --- a/include/linux/blk-pm.h +++ b/include/linux/blk-pm.h @@ -14,7 +14,7 @@ extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); extern int blk_pre_runtime_suspend(struct request_queue *q); extern void blk_post_runtime_suspend(struct request_queue *q, int err); extern void blk_pre_runtime_resume(struct request_queue *q); -extern void blk_post_runtime_resume(struct request_queue *q, int err); +extern void blk_post_runtime_resume(struct request_queue *q); extern void blk_set_runtime_active(struct request_queue *q); #else static inline void blk_pm_runtime_init(struct request_queue *q, -- cgit v1.2.3 From 30be4551f9e26292599e666985119a5b559a2e4a Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 22 Dec 2021 18:32:56 +0200 Subject: wwan: Replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. Signed-off-by: Andy Shevchenko Reviewed-by: Sergey Ryazanov Signed-off-by: David S. Miller --- include/linux/wwan.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/wwan.h b/include/linux/wwan.h index e143c88bf4b0..afb3334ec8c5 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -4,12 +4,9 @@ #ifndef __WWAN_H #define __WWAN_H -#include -#include #include -#include -#include #include +#include /** * enum wwan_port_type - WWAN port types @@ -37,6 +34,10 @@ enum wwan_port_type { WWAN_PORT_UNKNOWN, }; +struct device; +struct file; +struct netlink_ext_ack; +struct sk_buff; struct wwan_port; /** struct wwan_port_ops - The WWAN port operations -- cgit v1.2.3 From 7da1d1ddd1f02e5de7497a0c849256912652fb6c Mon Sep 17 00:00:00 2001 From: Nick Child Date: Thu, 16 Dec 2021 17:00:35 -0500 Subject: cuda/pmu: Make find_via_cuda/pmu init functions Make `find_via_cuda` and `find_via_pmu` initialization functions. Previously, their definitions in `drivers/macintosh/via-cuda.h` include the `__init` attribute but their alternative definitions in `arch/powerpc/powermac/sectup./c` and prototypes in `include/linux/ cuda.h` and `include/linux/pmu.h` do not use the `__init` macro. Since, only initialization functions call `find_via_cuda` and `find_via_pmu` it is safe to label these functions with `__init`. Signed-off-by: Nick Child Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20211216220035.605465-21-nick.child@ibm.com --- arch/powerpc/platforms/powermac/setup.c | 4 ++-- include/linux/cuda.h | 2 +- include/linux/pmu.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c index f7661b81db18..974d4b49867b 100644 --- a/arch/powerpc/platforms/powermac/setup.c +++ b/arch/powerpc/platforms/powermac/setup.c @@ -166,7 +166,7 @@ static void pmac_show_cpuinfo(struct seq_file *m) } #ifndef CONFIG_ADB_CUDA -int find_via_cuda(void) +int __init find_via_cuda(void) { struct device_node *dn = of_find_node_by_name(NULL, "via-cuda"); @@ -180,7 +180,7 @@ int find_via_cuda(void) #endif #ifndef CONFIG_ADB_PMU -int find_via_pmu(void) +int __init find_via_pmu(void) { struct device_node *dn = of_find_node_by_name(NULL, "via-pmu"); diff --git a/include/linux/cuda.h b/include/linux/cuda.h index 45bfe9d61271..daf3e6f98444 100644 --- a/include/linux/cuda.h +++ b/include/linux/cuda.h @@ -12,7 +12,7 @@ #include -extern int find_via_cuda(void); +extern int __init find_via_cuda(void); extern int cuda_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); extern void cuda_poll(void); diff --git a/include/linux/pmu.h b/include/linux/pmu.h index 52453a24a24f..c677442d007c 100644 --- a/include/linux/pmu.h +++ b/include/linux/pmu.h @@ -13,7 +13,7 @@ #include -extern int find_via_pmu(void); +extern int __init find_via_pmu(void); extern int pmu_request(struct adb_request *req, void (*done)(struct adb_request *), int nbytes, ...); -- cgit v1.2.3 From 66b354064a35b6379963cba27b5d37a278fc9bd9 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Tue, 23 Nov 2021 11:16:00 +0100 Subject: powercap/drivers/dtpm: Remove unused function definition The dtpm.h header file is exporting a function which is not implemented neither needed. Remove it. Signed-off-by: Daniel Lezcano Link: https://lore.kernel.org/r/20211123101601.2433340-1-daniel.lezcano@linaro.org --- include/linux/dtpm.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h index 2890f6370eb9..d37e5d06a357 100644 --- a/include/linux/dtpm.h +++ b/include/linux/dtpm.h @@ -70,6 +70,4 @@ void dtpm_unregister(struct dtpm *dtpm); int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent); -int dtpm_register_cpu(struct dtpm *parent); - #endif -- cgit v1.2.3 From dd123e62bdedcd3a486e48e883ec63138ec2c14c Mon Sep 17 00:00:00 2001 From: Henning Schild Date: Mon, 13 Dec 2021 13:04:59 +0100 Subject: platform/x86: simatic-ipc: add main driver for Siemens devices This mainly implements detection of these devices and will allow secondary drivers to work on such machines. The identification is DMI-based with a vendor specific way to tell them apart in a reliable way. Drivers for LEDs and Watchdogs will follow to make use of that platform detection. There is also some code to allow secondary drivers to find GPIO memory, that needs to be in place because the pinctrl drivers do not come up. Signed-off-by: Henning Schild Link: https://lore.kernel.org/r/20211213120502.20661-2-henning.schild@siemens.com Reviewed-by: Hans de Goede Signed-off-by: Hans de Goede --- drivers/platform/x86/Kconfig | 12 ++ drivers/platform/x86/Makefile | 3 + drivers/platform/x86/simatic-ipc.c | 176 +++++++++++++++++++++ include/linux/platform_data/x86/simatic-ipc-base.h | 29 ++++ include/linux/platform_data/x86/simatic-ipc.h | 72 +++++++++ 5 files changed, 292 insertions(+) create mode 100644 drivers/platform/x86/simatic-ipc.c create mode 100644 include/linux/platform_data/x86/simatic-ipc-base.h create mode 100644 include/linux/platform_data/x86/simatic-ipc.h (limited to 'include/linux') diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 961f33bea1f1..afa0f9b0141d 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -1088,6 +1088,18 @@ config INTEL_SCU_IPC_UTIL low level access for debug work and updating the firmware. Say N unless you will be doing this on an Intel MID platform. +config SIEMENS_SIMATIC_IPC + tristate "Siemens Simatic IPC Class driver" + depends on PCI + help + This Simatic IPC class driver is the central of several drivers. It + is mainly used for system identification, after which drivers in other + classes will take care of driving specifics of those machines. + i.e. LEDs and watchdog. + + To compile this driver as a module, choose M here: the module + will be called simatic-ipc. + endif # X86_PLATFORM_DEVICES config PMC_ATOM diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile index 18b11769073b..d477aad34fab 100644 --- a/drivers/platform/x86/Makefile +++ b/drivers/platform/x86/Makefile @@ -124,3 +124,6 @@ obj-$(CONFIG_INTEL_SCU_PLATFORM) += intel_scu_pltdrv.o obj-$(CONFIG_INTEL_SCU_WDT) += intel_scu_wdt.o obj-$(CONFIG_INTEL_SCU_IPC_UTIL) += intel_scu_ipcutil.o obj-$(CONFIG_PMC_ATOM) += pmc_atom.o + +# Siemens Simatic Industrial PCs +obj-$(CONFIG_SIEMENS_SIMATIC_IPC) += simatic-ipc.o diff --git a/drivers/platform/x86/simatic-ipc.c b/drivers/platform/x86/simatic-ipc.c new file mode 100644 index 000000000000..b599cda5ba3c --- /dev/null +++ b/drivers/platform/x86/simatic-ipc.c @@ -0,0 +1,176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Siemens SIMATIC IPC platform driver + * + * Copyright (c) Siemens AG, 2018-2021 + * + * Authors: + * Henning Schild + * Jan Kiszka + * Gerd Haeussler + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include + +static struct platform_device *ipc_led_platform_device; +static struct platform_device *ipc_wdt_platform_device; + +static const struct dmi_system_id simatic_ipc_whitelist[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SIEMENS AG"), + }, + }, + {} +}; + +static struct simatic_ipc_platform platform_data; + +static struct { + u32 station_id; + u8 led_mode; + u8 wdt_mode; +} device_modes[] = { + {SIMATIC_IPC_IPC127E, SIMATIC_IPC_DEVICE_127E, SIMATIC_IPC_DEVICE_NONE}, + {SIMATIC_IPC_IPC227D, SIMATIC_IPC_DEVICE_227D, SIMATIC_IPC_DEVICE_NONE}, + {SIMATIC_IPC_IPC227E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_227E}, + {SIMATIC_IPC_IPC277E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_227E}, + {SIMATIC_IPC_IPC427D, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_NONE}, + {SIMATIC_IPC_IPC427E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_427E}, + {SIMATIC_IPC_IPC477E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_427E}, +}; + +static int register_platform_devices(u32 station_id) +{ + u8 ledmode = SIMATIC_IPC_DEVICE_NONE; + u8 wdtmode = SIMATIC_IPC_DEVICE_NONE; + int i; + + platform_data.devmode = SIMATIC_IPC_DEVICE_NONE; + + for (i = 0; i < ARRAY_SIZE(device_modes); i++) { + if (device_modes[i].station_id == station_id) { + ledmode = device_modes[i].led_mode; + wdtmode = device_modes[i].wdt_mode; + break; + } + } + + if (ledmode != SIMATIC_IPC_DEVICE_NONE) { + platform_data.devmode = ledmode; + ipc_led_platform_device = + platform_device_register_data(NULL, + KBUILD_MODNAME "_leds", PLATFORM_DEVID_NONE, + &platform_data, + sizeof(struct simatic_ipc_platform)); + if (IS_ERR(ipc_led_platform_device)) + return PTR_ERR(ipc_led_platform_device); + + pr_debug("device=%s created\n", + ipc_led_platform_device->name); + } + + if (wdtmode != SIMATIC_IPC_DEVICE_NONE) { + platform_data.devmode = wdtmode; + ipc_wdt_platform_device = + platform_device_register_data(NULL, + KBUILD_MODNAME "_wdt", PLATFORM_DEVID_NONE, + &platform_data, + sizeof(struct simatic_ipc_platform)); + if (IS_ERR(ipc_wdt_platform_device)) + return PTR_ERR(ipc_wdt_platform_device); + + pr_debug("device=%s created\n", + ipc_wdt_platform_device->name); + } + + if (ledmode == SIMATIC_IPC_DEVICE_NONE && + wdtmode == SIMATIC_IPC_DEVICE_NONE) { + pr_warn("unsupported IPC detected, station id=%08x\n", + station_id); + return -EINVAL; + } + + return 0; +} + +/* FIXME: this should eventually be done with generic P2SB discovery code + * the individual drivers for watchdogs and LEDs access memory that implements + * GPIO, but pinctrl will not come up because of missing ACPI entries + * + * While there is no conflict a cleaner solution would be to somehow bring up + * pinctrl even with these ACPI entries missing, and base the drivers on pinctrl. + * After which the following function could be dropped, together with the code + * poking the memory. + */ +/* + * Get membase address from PCI, used in leds and wdt module. Here we read + * the bar0. The final address calculation is done in the appropriate modules + */ +u32 simatic_ipc_get_membase0(unsigned int p2sb) +{ + struct pci_bus *bus; + u32 bar0 = 0; + /* + * The GPIO memory is in bar0 of the hidden P2SB device. + * Unhide the device to have a quick look at it, before we hide it + * again. + * Also grab the pci rescan lock so that device does not get discovered + * and remapped while it is visible. + * This code is inspired by drivers/mfd/lpc_ich.c + */ + bus = pci_find_bus(0, 0); + pci_lock_rescan_remove(); + pci_bus_write_config_byte(bus, p2sb, 0xE1, 0x0); + pci_bus_read_config_dword(bus, p2sb, PCI_BASE_ADDRESS_0, &bar0); + + bar0 &= ~0xf; + pci_bus_write_config_byte(bus, p2sb, 0xE1, 0x1); + pci_unlock_rescan_remove(); + + return bar0; +} +EXPORT_SYMBOL(simatic_ipc_get_membase0); + +static int __init simatic_ipc_init_module(void) +{ + const struct dmi_system_id *match; + u32 station_id; + int err; + + match = dmi_first_match(simatic_ipc_whitelist); + if (!match) + return 0; + + err = dmi_walk(simatic_ipc_find_dmi_entry_helper, &station_id); + + if (err || station_id == SIMATIC_IPC_INVALID_STATION_ID) { + pr_warn("DMI entry %d not found\n", SIMATIC_IPC_DMI_ENTRY_OEM); + return 0; + } + + return register_platform_devices(station_id); +} + +static void __exit simatic_ipc_exit_module(void) +{ + platform_device_unregister(ipc_led_platform_device); + ipc_led_platform_device = NULL; + + platform_device_unregister(ipc_wdt_platform_device); + ipc_wdt_platform_device = NULL; +} + +module_init(simatic_ipc_init_module); +module_exit(simatic_ipc_exit_module); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Gerd Haeussler "); +MODULE_ALIAS("dmi:*:svnSIEMENSAG:*"); diff --git a/include/linux/platform_data/x86/simatic-ipc-base.h b/include/linux/platform_data/x86/simatic-ipc-base.h new file mode 100644 index 000000000000..62d2bc774067 --- /dev/null +++ b/include/linux/platform_data/x86/simatic-ipc-base.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Siemens SIMATIC IPC drivers + * + * Copyright (c) Siemens AG, 2018-2021 + * + * Authors: + * Henning Schild + * Gerd Haeussler + */ + +#ifndef __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H +#define __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H + +#include + +#define SIMATIC_IPC_DEVICE_NONE 0 +#define SIMATIC_IPC_DEVICE_227D 1 +#define SIMATIC_IPC_DEVICE_427E 2 +#define SIMATIC_IPC_DEVICE_127E 3 +#define SIMATIC_IPC_DEVICE_227E 4 + +struct simatic_ipc_platform { + u8 devmode; +}; + +u32 simatic_ipc_get_membase0(unsigned int p2sb); + +#endif /* __PLATFORM_DATA_X86_SIMATIC_IPC_BASE_H */ diff --git a/include/linux/platform_data/x86/simatic-ipc.h b/include/linux/platform_data/x86/simatic-ipc.h new file mode 100644 index 000000000000..f3b76b39776b --- /dev/null +++ b/include/linux/platform_data/x86/simatic-ipc.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Siemens SIMATIC IPC drivers + * + * Copyright (c) Siemens AG, 2018-2021 + * + * Authors: + * Henning Schild + * Gerd Haeussler + */ + +#ifndef __PLATFORM_DATA_X86_SIMATIC_IPC_H +#define __PLATFORM_DATA_X86_SIMATIC_IPC_H + +#include +#include + +#define SIMATIC_IPC_DMI_ENTRY_OEM 129 +/* binary type */ +#define SIMATIC_IPC_DMI_TYPE 0xff +#define SIMATIC_IPC_DMI_GROUP 0x05 +#define SIMATIC_IPC_DMI_ENTRY 0x02 +#define SIMATIC_IPC_DMI_TID 0x02 + +enum simatic_ipc_station_ids { + SIMATIC_IPC_INVALID_STATION_ID = 0, + SIMATIC_IPC_IPC227D = 0x00000501, + SIMATIC_IPC_IPC427D = 0x00000701, + SIMATIC_IPC_IPC227E = 0x00000901, + SIMATIC_IPC_IPC277E = 0x00000902, + SIMATIC_IPC_IPC427E = 0x00000A01, + SIMATIC_IPC_IPC477E = 0x00000A02, + SIMATIC_IPC_IPC127E = 0x00000D01, +}; + +static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len) +{ + struct { + u8 type; /* type (0xff = binary) */ + u8 len; /* len of data entry */ + u8 group; + u8 entry; + u8 tid; + __le32 station_id; /* station id (LE) */ + } __packed * data_entry = (void *)data + sizeof(struct dmi_header); + + while ((u8 *)data_entry < data + max_len) { + if (data_entry->type == SIMATIC_IPC_DMI_TYPE && + data_entry->len == sizeof(*data_entry) && + data_entry->group == SIMATIC_IPC_DMI_GROUP && + data_entry->entry == SIMATIC_IPC_DMI_ENTRY && + data_entry->tid == SIMATIC_IPC_DMI_TID) { + return le32_to_cpu(data_entry->station_id); + } + data_entry = (void *)((u8 *)(data_entry) + data_entry->len); + } + + return SIMATIC_IPC_INVALID_STATION_ID; +} + +static inline void +simatic_ipc_find_dmi_entry_helper(const struct dmi_header *dh, void *_data) +{ + u32 *id = _data; + + if (dh->type != SIMATIC_IPC_DMI_ENTRY_OEM) + return; + + *id = simatic_ipc_get_station_id((u8 *)dh, dh->length); +} + +#endif /* __PLATFORM_DATA_X86_SIMATIC_IPC_H */ -- cgit v1.2.3 From b86947b52f0d0e5b6e6f0510933ca13aad266e47 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Fri, 24 Dec 2021 10:10:29 +0800 Subject: ASoC/soundwire: intel: simplify callbacks for params/hw_free We don't really need to pass a substream to the callback, we only need the direction. No functionality change, only simplification to enable improve suspend with paused streams. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Ranjani Sridharan Signed-off-by: Bard Liao Acked-By: Vinod Koul Link: https://lore.kernel.org/r/20211224021034.26635-3-yung-chuan.liao@linux.intel.com Signed-off-by: Mark Brown --- drivers/soundwire/intel.c | 14 +++++++------- include/linux/soundwire/sdw_intel.h | 4 ++-- sound/soc/sof/intel/hda.c | 6 ++---- 3 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 78037ffdb09b..25c5f5b9f058 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -711,7 +711,7 @@ intel_pdi_alh_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi) } static int intel_params_stream(struct sdw_intel *sdw, - struct snd_pcm_substream *substream, + int stream, struct snd_soc_dai *dai, struct snd_pcm_hw_params *hw_params, int link_id, int alh_stream_id) @@ -719,7 +719,7 @@ static int intel_params_stream(struct sdw_intel *sdw, struct sdw_intel_link_res *res = sdw->link_res; struct sdw_intel_stream_params_data params_data; - params_data.substream = substream; + params_data.stream = stream; /* direction */ params_data.dai = dai; params_data.hw_params = hw_params; params_data.link_id = link_id; @@ -732,14 +732,14 @@ static int intel_params_stream(struct sdw_intel *sdw, } static int intel_free_stream(struct sdw_intel *sdw, - struct snd_pcm_substream *substream, + int stream, struct snd_soc_dai *dai, int link_id) { struct sdw_intel_link_res *res = sdw->link_res; struct sdw_intel_stream_free_data free_data; - free_data.substream = substream; + free_data.stream = stream; /* direction */ free_data.dai = dai; free_data.link_id = link_id; @@ -876,7 +876,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream, dma->hw_params = params; /* Inform DSP about PDI stream number */ - ret = intel_params_stream(sdw, substream, dai, params, + ret = intel_params_stream(sdw, substream->stream, dai, params, sdw->instance, pdi->intel_alh_id); if (ret) @@ -953,7 +953,7 @@ static int intel_prepare(struct snd_pcm_substream *substream, sdw_cdns_config_stream(cdns, ch, dir, dma->pdi); /* Inform DSP about PDI stream number */ - ret = intel_params_stream(sdw, substream, dai, + ret = intel_params_stream(sdw, substream->stream, dai, dma->hw_params, sdw->instance, dma->pdi->intel_alh_id); @@ -987,7 +987,7 @@ intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) return ret; } - ret = intel_free_stream(sdw, substream, dai, sdw->instance); + ret = intel_free_stream(sdw, substream->stream, dai, sdw->instance); if (ret < 0) { dev_err(dai->dev, "intel_free_stream: failed %d\n", ret); return ret; diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 8a463b8fc12a..67e0d3e750b5 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -92,7 +92,7 @@ * firmware. */ struct sdw_intel_stream_params_data { - struct snd_pcm_substream *substream; + int stream; struct snd_soc_dai *dai; struct snd_pcm_hw_params *hw_params; int link_id; @@ -105,7 +105,7 @@ struct sdw_intel_stream_params_data { * firmware. */ struct sdw_intel_stream_free_data { - struct snd_pcm_substream *substream; + int stream; struct snd_soc_dai *dai; int link_id; }; diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c index 99255028d3fe..c8fb082209ce 100644 --- a/sound/soc/sof/intel/hda.c +++ b/sound/soc/sof/intel/hda.c @@ -184,12 +184,11 @@ static int sdw_dai_config_ipc(struct snd_sof_dev *sdev, static int sdw_params_stream(struct device *dev, struct sdw_intel_stream_params_data *params_data) { - struct snd_pcm_substream *substream = params_data->substream; struct snd_sof_dev *sdev = dev_get_drvdata(dev); struct snd_soc_dai *d = params_data->dai; struct snd_soc_dapm_widget *w; - w = snd_soc_dai_get_widget(d, substream->stream); + w = snd_soc_dai_get_widget(d, params_data->stream); return sdw_dai_config_ipc(sdev, w, params_data->link_id, params_data->alh_stream_id, d->id, true); @@ -198,12 +197,11 @@ static int sdw_params_stream(struct device *dev, static int sdw_free_stream(struct device *dev, struct sdw_intel_stream_free_data *free_data) { - struct snd_pcm_substream *substream = free_data->substream; struct snd_sof_dev *sdev = dev_get_drvdata(dev); struct snd_soc_dai *d = free_data->dai; struct snd_soc_dapm_widget *w; - w = snd_soc_dai_get_widget(d, substream->stream); + w = snd_soc_dai_get_widget(d, free_data->stream); /* send invalid stream_id */ return sdw_dai_config_ipc(sdev, w, free_data->link_id, 0xFFFF, d->id, false); -- cgit v1.2.3 From 54bf7fa3efd08eea03e4bac04e188ee3db6173a7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 13 Dec 2021 17:11:45 +0100 Subject: ima: Fix undefined arch_ima_get_secureboot() and co Currently arch_ima_get_secureboot() and arch_get_ima_policy() are defined only when CONFIG_IMA is set, and this makes any code calling those functions without CONFIG_IMA fail. Move the declaration and the dummy definition of those functions outside ifdef-CONFIG_IMA block for fixing the undefined symbols. Signed-off-by: Takashi Iwai [zohar@linux.ibm.com: removed in-tree/out-of-tree comment in patch description] Reviewed-by: Petr Vorel Signed-off-by: Mimi Zohar --- include/linux/ima.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ima.h b/include/linux/ima.h index b6ab66a546ae..426b1744215e 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -50,21 +50,6 @@ static inline void ima_appraise_parse_cmdline(void) {} extern void ima_add_kexec_buffer(struct kimage *image); #endif -#ifdef CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT -extern bool arch_ima_get_secureboot(void); -extern const char * const *arch_get_ima_policy(void); -#else -static inline bool arch_ima_get_secureboot(void) -{ - return false; -} - -static inline const char * const *arch_get_ima_policy(void) -{ - return NULL; -} -#endif - #else static inline enum hash_algo ima_get_current_hash_algo(void) { @@ -155,6 +140,21 @@ static inline int ima_measure_critical_data(const char *event_label, #endif /* CONFIG_IMA */ +#ifdef CONFIG_IMA_SECURE_AND_OR_TRUSTED_BOOT +extern bool arch_ima_get_secureboot(void); +extern const char * const *arch_get_ima_policy(void); +#else +static inline bool arch_ima_get_secureboot(void) +{ + return false; +} + +static inline const char * const *arch_get_ima_policy(void) +{ + return NULL; +} +#endif + #ifndef CONFIG_IMA_KEXEC struct kimage; -- cgit v1.2.3 From 94ab10dd42a70acc5208a41325617e3d9cf81a70 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Fri, 24 Dec 2021 21:12:48 -0800 Subject: mm: delete unsafe BUG from page_cache_add_speculative() It is not easily reproducible, but on 5.16-rc I have several times hit the VM_BUG_ON_PAGE(PageTail(page), page) in page_cache_add_speculative(): usually from filemap_get_read_batch() for an ext4 read, yesterday from next_uptodate_page() from filemap_map_pages() for a shmem fault. That BUG used to be placed where page_ref_add_unless() had succeeded, but now it is placed before folio_ref_add_unless() is attempted: that is not safe, since it is only the acquired reference which makes the page safe from racing THP collapse or split. We could keep the BUG, checking PageTail only when folio_ref_try_add_rcu() has succeeded; but I don't think it adds much value - just delete it. Link: https://lkml.kernel.org/r/8b98fc6f-3439-8614-c3f3-945c659a1aba@google.com Fixes: 020853b6f5ea ("mm: Add folio_try_get_rcu()") Signed-off-by: Hugh Dickins Acked-by: Kirill A. Shutemov Reviewed-by: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Cc: William Kucharski Cc: Christoph Hellwig Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pagemap.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 605246452305..d150a9082b31 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -285,7 +285,6 @@ static inline struct inode *folio_inode(struct folio *folio) static inline bool page_cache_add_speculative(struct page *page, int count) { - VM_BUG_ON_PAGE(PageTail(page), page); return folio_ref_try_add_rcu((struct folio *)page, count); } -- cgit v1.2.3 From 595ec1973c276f6c0c1de8aca5eef8dfd81f9b49 Mon Sep 17 00:00:00 2001 From: Thibaut Sautereau Date: Fri, 24 Dec 2021 21:12:51 -0800 Subject: mm/page_alloc: fix __alloc_size attribute for alloc_pages_exact_nid The second parameter of alloc_pages_exact_nid is the one indicating the size of memory pointed by the returned pointer. Link: https://lkml.kernel.org/r/YbjEgwhn4bGblp//@coeus Fixes: abd58f38dfb4 ("mm/page_alloc: add __alloc_size attributes for better bounds checking") Signed-off-by: Thibaut Sautereau Acked-by: Kees Cook Cc: Daniel Micay Cc: Levente Polyak Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index b976c4177299..8fcc38467af6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -624,7 +624,7 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1); void free_pages_exact(void *virt, size_t size); -__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(1); +__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) -- cgit v1.2.3 From 4fb0abfee424b05f0ec6d2d09e38f04ee2b82a8a Mon Sep 17 00:00:00 2001 From: Yazen Ghannam Date: Mon, 8 Nov 2021 15:51:21 -0600 Subject: x86/amd_nb: Add AMD Family 19h Models (10h-1Fh) and (A0h-AFh) PCI IDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the new PCI Device IDs to support new generation of AMD 19h family of processors. Signed-off-by: Yazen Ghannam Signed-off-by: Babu Moger Acked-by: Krzysztof Wilczyński Acked-by: Borislav Petkov Acked-by: Bjorn Helgaas # pci_ids.h Link: https://lore.kernel.org/r/163640828133.955062.18349019796157170473.stgit@bmoger-ubuntu Signed-off-by: Guenter Roeck --- arch/x86/kernel/amd_nb.c | 5 +++++ include/linux/pci_ids.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index c92c9c774c0e..f3e885f3dd0f 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -19,12 +19,14 @@ #define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 #define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 #define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 +#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT 0x14a4 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec #define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 #define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1 #define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 #define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e @@ -39,6 +41,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, {} }; @@ -61,6 +64,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, {} @@ -78,6 +82,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 011f2f1ea5bb..b5248f27910e 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -555,6 +555,7 @@ #define PCI_DEVICE_ID_AMD_17H_M60H_DF_F3 0x144b #define PCI_DEVICE_ID_AMD_17H_M70H_DF_F3 0x1443 #define PCI_DEVICE_ID_AMD_19H_DF_F3 0x1653 +#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F3 0x14b0 #define PCI_DEVICE_ID_AMD_19H_M40H_DF_F3 0x167c #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F3 0x166d #define PCI_DEVICE_ID_AMD_CNB17H_F3 0x1703 -- cgit v1.2.3 From 11a24ca7e34d968991a7d437b950d1924396bd81 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Thu, 25 Nov 2021 03:08:38 +0100 Subject: hwmon: (ntc_thermistor) Merge platform data into driver Platform data is supposed to be used with "board files", device descriptions in C. Since the introduction of the NTC driver in 2011, no such platforms have been submitted to the Linux kernel, and their use is strongly discouraged in favor of Device Tree, ACPI or as last resort software firmware nodes. Drop the external header and copy the platform data into the driver file. Cc: Peter Rosin Cc: Chris Lesiak Signed-off-by: Linus Walleij Link: https://lore.kernel.org/r/20211125020841.3616359-2-linus.walleij@linaro.org Signed-off-by: Guenter Roeck --- drivers/hwmon/ntc_thermistor.c | 41 ++++++++++++++++++++--- include/linux/platform_data/ntc_thermistor.h | 50 ---------------------------- 2 files changed, 36 insertions(+), 55 deletions(-) delete mode 100644 include/linux/platform_data/ntc_thermistor.h (limited to 'include/linux') diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index cf26c44f2b88..034ef55d0706 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -14,12 +14,45 @@ #include #include #include +#include +#include -#include +enum ntc_thermistor_type { + TYPE_B57330V2103, + TYPE_B57891S0103, + TYPE_NCPXXWB473, + TYPE_NCPXXWF104, + TYPE_NCPXXWL333, + TYPE_NCPXXXH103, +}; -#include +struct ntc_thermistor_platform_data { + /* + * One (not both) of read_uV and read_ohm should be provided and only + * one of the two should be provided. + * Both functions should return negative value for an error case. + * + * pullup_uV, pullup_ohm, pulldown_ohm, and connect are required to use + * read_uV() + * + * How to setup pullup_ohm, pulldown_ohm, and connect is + * described at Documentation/hwmon/ntc_thermistor.rst + * + * pullup/down_ohm: 0 for infinite / not-connected + * + * chan: iio_channel pointer to communicate with the ADC which the + * thermistor is using for conversion of the analog values. + */ + int (*read_uv)(struct ntc_thermistor_platform_data *); + unsigned int pullup_uv; -#include + unsigned int pullup_ohm; + unsigned int pulldown_ohm; + enum { NTC_CONNECTED_POSITIVE, NTC_CONNECTED_GROUND } connect; + struct iio_channel *chan; + + int (*read_ohm)(void); +}; struct ntc_compensation { int temp_c; @@ -651,8 +684,6 @@ static int ntc_thermistor_probe(struct platform_device *pdev) pdata = ntc_thermistor_parse_dt(dev); if (IS_ERR(pdata)) return PTR_ERR(pdata); - else if (pdata == NULL) - pdata = dev_get_platdata(dev); if (!pdata) { dev_err(dev, "No platform init data supplied.\n"); diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h deleted file mode 100644 index b324d03e580c..000000000000 --- a/include/linux/platform_data/ntc_thermistor.h +++ /dev/null @@ -1,50 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * ntc_thermistor.h - NTC Thermistors - * - * Copyright (C) 2010 Samsung Electronics - * MyungJoo Ham - */ -#ifndef _LINUX_NTC_H -#define _LINUX_NTC_H - -struct iio_channel; - -enum ntc_thermistor_type { - TYPE_B57330V2103, - TYPE_B57891S0103, - TYPE_NCPXXWB473, - TYPE_NCPXXWF104, - TYPE_NCPXXWL333, - TYPE_NCPXXXH103, -}; - -struct ntc_thermistor_platform_data { - /* - * One (not both) of read_uV and read_ohm should be provided and only - * one of the two should be provided. - * Both functions should return negative value for an error case. - * - * pullup_uV, pullup_ohm, pulldown_ohm, and connect are required to use - * read_uV() - * - * How to setup pullup_ohm, pulldown_ohm, and connect is - * described at Documentation/hwmon/ntc_thermistor.rst - * - * pullup/down_ohm: 0 for infinite / not-connected - * - * chan: iio_channel pointer to communicate with the ADC which the - * thermistor is using for conversion of the analog values. - */ - int (*read_uv)(struct ntc_thermistor_platform_data *); - unsigned int pullup_uv; - - unsigned int pullup_ohm; - unsigned int pulldown_ohm; - enum { NTC_CONNECTED_POSITIVE, NTC_CONNECTED_GROUND } connect; - struct iio_channel *chan; - - int (*read_ohm)(void); -}; - -#endif /* _LINUX_NTC_H */ -- cgit v1.2.3 From 130d168866a11829b844ffdb19b9aefe384f754c Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 16 Dec 2021 16:42:57 +0100 Subject: hwmon: prefix kernel-doc comments for structs with struct The command ./scripts/kernel-doc -none include/linux/hwmon.h warns: include/linux/hwmon.h:406: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Channel information include/linux/hwmon.h:425: warning: This comment starts with '/**', but isn't a kernel-doc comment. Refer Documentation/doc-guide/kernel-doc.rst * Chip configuration Address those kernel-doc warnings by prefixing kernel-doc descriptions for structs with the keyword 'struct'. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20211216154257.26758-1-lukas.bulwahn@gmail.com Signed-off-by: Guenter Roeck --- include/linux/hwmon.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h index 1e8d6ea8992e..fad1f1df26df 100644 --- a/include/linux/hwmon.h +++ b/include/linux/hwmon.h @@ -403,7 +403,7 @@ struct hwmon_ops { }; /** - * Channel information + * struct hwmon_channel_info - Channel information * @type: Channel type. * @config: Pointer to NULL-terminated list of channel parameters. * Use for per-channel attributes. @@ -422,7 +422,7 @@ struct hwmon_channel_info { }) /** - * Chip configuration + * struct hwmon_chip_info - Chip configuration * @ops: Pointer to hwmon operations. * @info: Null-terminated list of channel information. */ -- cgit v1.2.3 From ee6d3dd4ed48ab24b74bab3c3977b8218518247d Mon Sep 17 00:00:00 2001 From: Wedson Almeida Filho Date: Fri, 24 Dec 2021 23:13:45 +0000 Subject: driver core: make kobj_type constant. This way instances of kobj_type (which contain function pointers) can be stored in .rodata, which means that they cannot be [easily/accidentally] modified at runtime. Signed-off-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20211224231345.777370-1-wedsonaf@google.com Signed-off-by: Greg Kroah-Hartman --- Documentation/core-api/kobject.rst | 4 ++-- drivers/base/bus.c | 2 +- drivers/base/core.c | 2 +- include/linux/kobject.h | 8 ++++---- kernel/params.c | 2 +- lib/kobject.c | 8 ++++---- 6 files changed, 13 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/kobject.rst b/Documentation/core-api/kobject.rst index 2739f8b72575..d3b5bf9f643a 100644 --- a/Documentation/core-api/kobject.rst +++ b/Documentation/core-api/kobject.rst @@ -118,7 +118,7 @@ Initialization of kobjects Code which creates a kobject must, of course, initialize that object. Some of the internal fields are setup with a (mandatory) call to kobject_init():: - void kobject_init(struct kobject *kobj, struct kobj_type *ktype); + void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); The ktype is required for a kobject to be created properly, as every kobject must have an associated kobj_type. After calling kobject_init(), to @@ -156,7 +156,7 @@ kobject_name():: There is a helper function to both initialize and add the kobject to the kernel at the same time, called surprisingly enough kobject_init_and_add():: - int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, + int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); The arguments are the same as the individual kobject_init() and diff --git a/drivers/base/bus.c b/drivers/base/bus.c index bdc98c5713d5..a64454f5f8c0 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -165,7 +165,7 @@ static struct kobj_type bus_ktype = { static int bus_uevent_filter(struct kset *kset, struct kobject *kobj) { - struct kobj_type *ktype = get_ktype(kobj); + const struct kobj_type *ktype = get_ktype(kobj); if (ktype == &bus_ktype) return 1; diff --git a/drivers/base/core.c b/drivers/base/core.c index fd034d742447..d712ea11066b 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2263,7 +2263,7 @@ static struct kobj_type device_ktype = { static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) { - struct kobj_type *ktype = get_ktype(kobj); + const struct kobj_type *ktype = get_ktype(kobj); if (ktype == &device_ktype) { struct device *dev = kobj_to_dev(kobj); diff --git a/include/linux/kobject.h b/include/linux/kobject.h index c740062b4b1a..683172b2e094 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -66,7 +66,7 @@ struct kobject { struct list_head entry; struct kobject *parent; struct kset *kset; - struct kobj_type *ktype; + const struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE @@ -90,13 +90,13 @@ static inline const char *kobject_name(const struct kobject *kobj) return kobj->name; } -extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); +extern void kobject_init(struct kobject *kobj, const struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, - struct kobj_type *ktype, struct kobject *parent, + const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); @@ -217,7 +217,7 @@ static inline void kset_put(struct kset *k) kobject_put(&k->kobj); } -static inline struct kobj_type *get_ktype(struct kobject *kobj) +static inline const struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } diff --git a/kernel/params.c b/kernel/params.c index 8299bd764e42..9b90e3c4d3c0 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -928,7 +928,7 @@ static const struct sysfs_ops module_sysfs_ops = { static int uevent_filter(struct kset *kset, struct kobject *kobj) { - struct kobj_type *ktype = get_ktype(kobj); + const struct kobj_type *ktype = get_ktype(kobj); if (ktype == &module_ktype) return 1; diff --git a/lib/kobject.c b/lib/kobject.c index 4a56f519139d..56fa037501b5 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -65,7 +65,7 @@ void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid) */ static int populate_dir(struct kobject *kobj) { - struct kobj_type *t = get_ktype(kobj); + const struct kobj_type *t = get_ktype(kobj); struct attribute *attr; int error = 0; int i; @@ -346,7 +346,7 @@ EXPORT_SYMBOL(kobject_set_name); * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ -void kobject_init(struct kobject *kobj, struct kobj_type *ktype) +void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; @@ -461,7 +461,7 @@ EXPORT_SYMBOL(kobject_add); * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ -int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, +int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; @@ -679,7 +679,7 @@ EXPORT_SYMBOL(kobject_get_unless_zero); static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; - struct kobj_type *t = get_ktype(kobj); + const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("kobject: '%s' (%p): %s, parent %p\n", -- cgit v1.2.3 From 1882de7fc56c2b0ea91dd9fd9922d434fc3feb15 Mon Sep 17 00:00:00 2001 From: Chen Yu Date: Wed, 22 Dec 2021 12:31:03 +0800 Subject: efi: Introduce EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER and corresponding structures Platform Firmware Runtime Update image starts with UEFI headers, and the headers are defined in UEFI specification, but some of them have not been defined in the kernel yet. For example, the header layout of a capsule file looks like this: EFI_CAPSULE_HEADER EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER EFI_FIRMWARE_IMAGE_AUTHENTICATION These structures would be used by the Platform Firmware Runtime Update driver to parse the format of capsule file to verify if the corresponding version number is valid. In this way, if the user provides an invalid capsule image, the kernel could be used as a guard to reject it, without switching to the Management Mode (which might be costly). EFI_CAPSULE_HEADER has been defined in the kernel, but the other structures have not been defined yet, so do that. Besides, EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER and EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER are required to be packed in the uefi specification. For this reason, use the __packed attribute to indicate to the compiler that the entire structure can appear misaligned in memory (as suggested by Ard) in case one of them follows the other directly in a capsule header. Acked-by: Ard Biesheuvel Signed-off-by: Chen Yu Signed-off-by: Rafael J. Wysocki --- include/linux/efi.h | 46 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 46 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index dbd39b20e034..80e970f7e6f8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -148,6 +148,52 @@ typedef struct { u32 imagesize; } efi_capsule_header_t; +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_HEADER */ +struct efi_manage_capsule_header { + u32 ver; + u16 emb_drv_cnt; + u16 payload_cnt; + /* + * Variable-size array of the size given by the sum of + * emb_drv_cnt and payload_cnt. + */ + u64 offset_list[]; +} __packed; + +/* EFI_FIRMWARE_MANAGEMENT_CAPSULE_IMAGE_HEADER */ +struct efi_manage_capsule_image_header { + u32 ver; + efi_guid_t image_type_id; + u8 image_index; + u8 reserved_bytes[3]; + u32 image_size; + u32 vendor_code_size; + /* hw_ins was introduced in version 2 */ + u64 hw_ins; + /* capsule_support was introduced in version 3 */ + u64 capsule_support; +} __packed; + +/* WIN_CERTIFICATE */ +struct win_cert { + u32 len; + u16 rev; + u16 cert_type; +}; + +/* WIN_CERTIFICATE_UEFI_GUID */ +struct win_cert_uefi_guid { + struct win_cert hdr; + efi_guid_t cert_type; + u8 cert_data[]; +}; + +/* EFI_FIRMWARE_IMAGE_AUTHENTICATION */ +struct efi_image_auth { + u64 mon_count; + struct win_cert_uefi_guid auth_info; +}; + /* * EFI capsule flags */ -- cgit v1.2.3 From cf6299b6101903c31bddb0065804b2121ed510c7 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 27 Dec 2021 17:39:24 +0100 Subject: kobject: remove kset from struct kset_uevent_ops callbacks There is no need to pass the pointer to the kset in the struct kset_uevent_ops callbacks as no one uses it, so just remove that pointer entirely. Reviewed-by: Rafael J. Wysocki Reviewed-by: Wedson Almeida Filho Link: https://lore.kernel.org/r/20211227163924.3970661-1-gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman --- Documentation/core-api/kobject.rst | 7 +++---- Documentation/translations/zh_CN/core-api/kobject.rst | 7 +++---- drivers/base/bus.c | 2 +- drivers/base/core.c | 11 +++++------ drivers/dma-buf/dma-buf-sysfs-stats.c | 2 +- fs/dlm/lockspace.c | 3 +-- fs/gfs2/sys.c | 3 +-- include/linux/kobject.h | 7 +++---- kernel/params.c | 2 +- lib/kobject_uevent.c | 6 +++--- 10 files changed, 22 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/Documentation/core-api/kobject.rst b/Documentation/core-api/kobject.rst index d3b5bf9f643a..3d6e3107315d 100644 --- a/Documentation/core-api/kobject.rst +++ b/Documentation/core-api/kobject.rst @@ -373,10 +373,9 @@ If a kset wishes to control the uevent operations of the kobjects associated with it, it can use the struct kset_uevent_ops to handle it:: struct kset_uevent_ops { - int (* const filter)(struct kset *kset, struct kobject *kobj); - const char *(* const name)(struct kset *kset, struct kobject *kobj); - int (* const uevent)(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env); + int (* const filter)(struct kobject *kobj); + const char *(* const name)(struct kobject *kobj); + int (* const uevent)(struct kobject *kobj, struct kobj_uevent_env *env); }; diff --git a/Documentation/translations/zh_CN/core-api/kobject.rst b/Documentation/translations/zh_CN/core-api/kobject.rst index b7c37794cc7f..95634083dca0 100644 --- a/Documentation/translations/zh_CN/core-api/kobject.rst +++ b/Documentation/translations/zh_CN/core-api/kobject.rst @@ -325,10 +325,9 @@ ksets 结构体kset_uevent_ops来处理它:: struct kset_uevent_ops { - int (* const filter)(struct kset *kset, struct kobject *kobj); - const char *(* const name)(struct kset *kset, struct kobject *kobj); - int (* const uevent)(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env); + int (* const filter)(struct kobject *kobj); + const char *(* const name)(struct kobject *kobj); + int (* const uevent)(struct kobject *kobj, struct kobj_uevent_env *env); }; diff --git a/drivers/base/bus.c b/drivers/base/bus.c index a64454f5f8c0..97936ec49bde 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -163,7 +163,7 @@ static struct kobj_type bus_ktype = { .release = bus_release, }; -static int bus_uevent_filter(struct kset *kset, struct kobject *kobj) +static int bus_uevent_filter(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); diff --git a/drivers/base/core.c b/drivers/base/core.c index d712ea11066b..60d703ebd123 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2261,7 +2261,7 @@ static struct kobj_type device_ktype = { }; -static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) +static int dev_uevent_filter(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); @@ -2275,7 +2275,7 @@ static int dev_uevent_filter(struct kset *kset, struct kobject *kobj) return 0; } -static const char *dev_uevent_name(struct kset *kset, struct kobject *kobj) +static const char *dev_uevent_name(struct kobject *kobj) { struct device *dev = kobj_to_dev(kobj); @@ -2286,8 +2286,7 @@ static const char *dev_uevent_name(struct kset *kset, struct kobject *kobj) return NULL; } -static int dev_uevent(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env) +static int dev_uevent(struct kobject *kobj, struct kobj_uevent_env *env) { struct device *dev = kobj_to_dev(kobj); int retval = 0; @@ -2382,7 +2381,7 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, /* respect filter */ if (kset->uevent_ops && kset->uevent_ops->filter) - if (!kset->uevent_ops->filter(kset, &dev->kobj)) + if (!kset->uevent_ops->filter(&dev->kobj)) goto out; env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); @@ -2390,7 +2389,7 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, return -ENOMEM; /* let the kset specific function add its keys */ - retval = kset->uevent_ops->uevent(kset, &dev->kobj, env); + retval = kset->uevent_ops->uevent(&dev->kobj, env); if (retval) goto out; diff --git a/drivers/dma-buf/dma-buf-sysfs-stats.c b/drivers/dma-buf/dma-buf-sysfs-stats.c index 053baadcada9..2bba0babcb62 100644 --- a/drivers/dma-buf/dma-buf-sysfs-stats.c +++ b/drivers/dma-buf/dma-buf-sysfs-stats.c @@ -132,7 +132,7 @@ void dma_buf_stats_teardown(struct dma_buf *dmabuf) /* Statistics files do not need to send uevents. */ -static int dmabuf_sysfs_uevent_filter(struct kset *kset, struct kobject *kobj) +static int dmabuf_sysfs_uevent_filter(struct kobject *kobj) { return 0; } diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c index 10eddfa6c3d7..0bbb346cb892 100644 --- a/fs/dlm/lockspace.c +++ b/fs/dlm/lockspace.c @@ -216,8 +216,7 @@ static int do_uevent(struct dlm_ls *ls, int in) return ls->ls_uevent_result; } -static int dlm_uevent(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env) +static int dlm_uevent(struct kobject *kobj, struct kobj_uevent_env *env) { struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj); diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c index c0a34d9ddee4..a6002b2d146d 100644 --- a/fs/gfs2/sys.c +++ b/fs/gfs2/sys.c @@ -767,8 +767,7 @@ void gfs2_sys_fs_del(struct gfs2_sbd *sdp) wait_for_completion(&sdp->sd_kobj_unregister); } -static int gfs2_uevent(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env) +static int gfs2_uevent(struct kobject *kobj, struct kobj_uevent_env *env) { struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj); struct super_block *s = sdp->sd_vfs; diff --git a/include/linux/kobject.h b/include/linux/kobject.h index 683172b2e094..ad90b49824dc 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -153,10 +153,9 @@ struct kobj_uevent_env { }; struct kset_uevent_ops { - int (* const filter)(struct kset *kset, struct kobject *kobj); - const char *(* const name)(struct kset *kset, struct kobject *kobj); - int (* const uevent)(struct kset *kset, struct kobject *kobj, - struct kobj_uevent_env *env); + int (* const filter)(struct kobject *kobj); + const char *(* const name)(struct kobject *kobj); + int (* const uevent)(struct kobject *kobj, struct kobj_uevent_env *env); }; struct kobj_attribute { diff --git a/kernel/params.c b/kernel/params.c index 9b90e3c4d3c0..5b92310425c5 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -926,7 +926,7 @@ static const struct sysfs_ops module_sysfs_ops = { .store = module_attr_store, }; -static int uevent_filter(struct kset *kset, struct kobject *kobj) +static int uevent_filter(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index c87d5b6a8a55..7c44b7ae4c5c 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -501,7 +501,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) - if (!uevent_ops->filter(kset, kobj)) { + if (!uevent_ops->filter(kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); @@ -510,7 +510,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, /* originating subsystem */ if (uevent_ops && uevent_ops->name) - subsystem = uevent_ops->name(kset, kobj); + subsystem = uevent_ops->name(kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { @@ -554,7 +554,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { - retval = uevent_ops->uevent(kset, kobj, env); + retval = uevent_ops->uevent(kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, -- cgit v1.2.3 From d6b9c679bbac1d1d2fcac64391b4cadb91763a6f Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Fri, 12 Nov 2021 14:46:32 -0800 Subject: watchdog: bcm7038_wdt: Support platform data configuration The BCM7038 watchdog driver needs to be able to obtain a specific clock name on BCM63xx platforms which is the "periph" clock ticking at 50MHz. make it possible to specify the clock name to obtain via platform data. Signed-off-by: Florian Fainelli Reviewed-by: Guenter Roeck Link: https://lore.kernel.org/r/20211112224636.395101-4-f.fainelli@gmail.com Signed-off-by: Guenter Roeck Signed-off-by: Wim Van Sebroeck --- drivers/watchdog/bcm7038_wdt.c | 8 +++++++- include/linux/platform_data/bcm7038_wdt.h | 8 ++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) create mode 100644 include/linux/platform_data/bcm7038_wdt.h (limited to 'include/linux') diff --git a/drivers/watchdog/bcm7038_wdt.c b/drivers/watchdog/bcm7038_wdt.c index acaaa0005d5b..506cd7ef9c77 100644 --- a/drivers/watchdog/bcm7038_wdt.c +++ b/drivers/watchdog/bcm7038_wdt.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -133,8 +134,10 @@ static void bcm7038_clk_disable_unprepare(void *data) static int bcm7038_wdt_probe(struct platform_device *pdev) { + struct bcm7038_wdt_platform_data *pdata = pdev->dev.platform_data; struct device *dev = &pdev->dev; struct bcm7038_watchdog *wdt; + const char *clk_name = NULL; int err; wdt = devm_kzalloc(dev, sizeof(*wdt), GFP_KERNEL); @@ -147,7 +150,10 @@ static int bcm7038_wdt_probe(struct platform_device *pdev) if (IS_ERR(wdt->base)) return PTR_ERR(wdt->base); - wdt->clk = devm_clk_get(dev, NULL); + if (pdata && pdata->clk_name) + clk_name = pdata->clk_name; + + wdt->clk = devm_clk_get(dev, clk_name); /* If unable to get clock, use default frequency */ if (!IS_ERR(wdt->clk)) { err = clk_prepare_enable(wdt->clk); diff --git a/include/linux/platform_data/bcm7038_wdt.h b/include/linux/platform_data/bcm7038_wdt.h new file mode 100644 index 000000000000..e18cfd9ec8f9 --- /dev/null +++ b/include/linux/platform_data/bcm7038_wdt.h @@ -0,0 +1,8 @@ +#ifndef __BCM7038_WDT_PDATA_H +#define __BCM7038_WDT_PDATA_H + +struct bcm7038_wdt_platform_data { + const char *clk_name; +}; + +#endif /* __BCM7038_WDT_PDATA_H */ -- cgit v1.2.3 From b92e301633f0f454aa1cfedac2e096bb9649b367 Mon Sep 17 00:00:00 2001 From: Jonathan Neuschäfer Date: Sat, 18 Dec 2021 16:25:53 +0100 Subject: mfd: ntxec: Change return type of ntxec_reg8 from __be16 to u16 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Register values in NTXEC are big-endian on the I2C bus, but the regmap subsystem handles the conversion between CPU-endian and big-endian data internally. ntxec_reg8 should thus return u16, not __be16. Reported-by: kernel test robot Signed-off-by: Jonathan Neuschäfer Signed-off-by: Lee Jones Link: https://lore.kernel.org/r/20211218152553.744615-1-j.neuschaefer@gmx.net --- include/linux/mfd/ntxec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/ntxec.h b/include/linux/mfd/ntxec.h index 26ab3b8eb612..cc6f07bfa2b3 100644 --- a/include/linux/mfd/ntxec.h +++ b/include/linux/mfd/ntxec.h @@ -26,7 +26,7 @@ struct ntxec { * This convenience function converts an 8-bit value to 16-bit for use in the * second kind of register. */ -static inline __be16 ntxec_reg8(u8 value) +static inline u16 ntxec_reg8(u8 value) { return value << 8; } -- cgit v1.2.3 From b6459415b384cb829f0b2a4268f211c789f6cf0b Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 28 Dec 2021 16:49:13 -0800 Subject: net: Don't include filter.h from net/sock.h sock.h is pretty heavily used (5k objects rebuilt on x86 after it's touched). We can drop the include of filter.h from it and add a forward declaration of struct sk_filter instead. This decreases the number of rebuilt objects when bpf.h is touched from ~5k to ~1k. There's a lot of missing includes this was masking. Primarily in networking tho, this time. Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Acked-by: Marc Kleine-Budde Acked-by: Florian Fainelli Acked-by: Nikolay Aleksandrov Acked-by: Stefano Garzarella Link: https://lore.kernel.org/bpf/20211229004913.513372-1-kuba@kernel.org --- drivers/bluetooth/btqca.c | 1 + drivers/infiniband/core/cache.c | 1 + drivers/infiniband/hw/irdma/ctrl.c | 2 ++ drivers/infiniband/hw/irdma/uda.c | 2 ++ drivers/infiniband/hw/mlx5/doorbell.c | 1 + drivers/infiniband/hw/mlx5/qp.c | 1 + drivers/net/amt.c | 1 + drivers/net/appletalk/ipddp.c | 1 + drivers/net/bonding/bond_main.c | 1 + drivers/net/can/usb/peak_usb/pcan_usb.c | 1 + drivers/net/dsa/microchip/ksz8795.c | 1 + drivers/net/dsa/xrs700x/xrs700x.c | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 1 + drivers/net/ethernet/huawei/hinic/hinic_tx.c | 1 + drivers/net/ethernet/intel/ice/ice_devlink.c | 2 ++ drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 2 ++ drivers/net/ethernet/intel/igc/igc_xdp.c | 1 + drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 1 + drivers/net/ethernet/mellanox/mlx5/core/en/qos.c | 1 + drivers/net/ethernet/sfc/efx.c | 1 + drivers/net/ethernet/sfc/efx_channels.c | 1 + drivers/net/ethernet/sfc/efx_common.c | 1 + drivers/net/hamradio/hdlcdrv.c | 1 + drivers/net/hamradio/scc.c | 1 + drivers/net/loopback.c | 1 + drivers/net/vrf.c | 1 + drivers/net/wireless/ath/ath11k/debugfs.c | 2 ++ drivers/net/wireless/realtek/rtw89/debug.c | 2 ++ fs/nfs/dir.c | 1 + fs/nfs/fs_context.c | 1 + fs/select.c | 1 + include/linux/bpf_local_storage.h | 1 + include/linux/dsa/loop.h | 1 + include/net/ipv6.h | 2 ++ include/net/route.h | 1 + include/net/sock.h | 2 +- include/net/xdp_sock.h | 1 + kernel/sysctl.c | 1 + net/bluetooth/bnep/sock.c | 1 + net/bluetooth/eir.h | 2 ++ net/bluetooth/hidp/sock.c | 1 + net/bluetooth/l2cap_sock.c | 1 + net/bridge/br_ioctl.c | 1 + net/caif/caif_socket.c | 1 + net/core/devlink.c | 1 + net/core/flow_dissector.c | 1 + net/core/lwt_bpf.c | 1 + net/core/sock_diag.c | 1 + net/core/sysctl_net_core.c | 1 + net/decnet/dn_nsp_in.c | 1 + net/dsa/dsa_priv.h | 1 + net/ethtool/ioctl.c | 1 + net/ipv4/nexthop.c | 1 + net/ipv6/ip6_fib.c | 1 + net/ipv6/seg6_local.c | 1 + net/iucv/af_iucv.c | 1 + net/kcm/kcmsock.c | 1 + net/netfilter/nfnetlink_hook.c | 1 + net/netfilter/nft_reject_netdev.c | 1 + net/netlink/af_netlink.c | 2 ++ net/packet/af_packet.c | 1 + net/rose/rose_in.c | 1 + net/sched/sch_frag.c | 1 + net/smc/smc_ib.c | 2 ++ net/smc/smc_ism.c | 1 + net/unix/af_unix.c | 1 + net/vmw_vsock/af_vsock.c | 1 + net/xdp/xskmap.c | 1 + net/xfrm/xfrm_state.c | 1 + net/xfrm/xfrm_user.c | 1 + 70 files changed, 80 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index be04d74037d2..f7bf311d7910 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -6,6 +6,7 @@ */ #include #include +#include #include #include diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 0c98dd3dee67..b79f816a7203 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -33,6 +33,7 @@ * SOFTWARE. */ +#include #include #include #include diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c index 7264f8c2f7d5..3141a9c85de5 100644 --- a/drivers/infiniband/hw/irdma/ctrl.c +++ b/drivers/infiniband/hw/irdma/ctrl.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 or Linux-OpenIB /* Copyright (c) 2015 - 2021 Intel Corporation */ +#include + #include "osdep.h" #include "status.h" #include "hmc.h" diff --git a/drivers/infiniband/hw/irdma/uda.c b/drivers/infiniband/hw/irdma/uda.c index f5b1b6150cdc..7a9988ddbd01 100644 --- a/drivers/infiniband/hw/irdma/uda.c +++ b/drivers/infiniband/hw/irdma/uda.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 or Linux-OpenIB /* Copyright (c) 2016 - 2021 Intel Corporation */ +#include + #include "osdep.h" #include "status.h" #include "hmc.h" diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 6398e2f48579..e32111117a5e 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -32,6 +32,7 @@ #include #include +#include #include #include "mlx5_ib.h" diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index e5abbcfc1d57..29475cf8c7c3 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -30,6 +30,7 @@ * SOFTWARE. */ +#include #include #include #include diff --git a/drivers/net/amt.c b/drivers/net/amt.c index b732ee9a50ef..a1c7a8acd9c8 100644 --- a/drivers/net/amt.c +++ b/drivers/net/amt.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index 5566daefbff4..d558535390f9 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -23,6 +23,7 @@ * of the GNU General Public License, incorporated herein by reference. */ +#include #include #include #include diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 0f39ad2af81c..d483f1102a9e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -35,6 +35,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c index 876218752766..ac6772fe9746 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb.c @@ -8,6 +8,7 @@ * * Many thanks to Klaus Hitschler */ +#include #include #include #include diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 013e9c02be71..991b9c6b6ce7 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 35fa19ddaf19..0730352cdd57 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 951c4c569a9b..4da31b1b84f9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -9,6 +9,7 @@ #include #include +#include #include #include "bnxt_hsi.h" #include "bnxt.h" diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index a984a7a6dd2e..8d59babbf476 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -4,6 +4,7 @@ * Copyright(c) 2017 Huawei Technologies Co., Ltd */ +#include #include #include #include diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 1cfe918db8b9..716ec8616ff0 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020, Intel Corporation. */ +#include + #include "ice.h" #include "ice_lib.h" #include "ice_devlink.h" diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 1dd7e84f41f8..9520b140bdbf 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019, Intel Corporation. */ +#include + #include "ice_txrx_lib.h" #include "ice_eswitch.h" #include "ice_lib.h" diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index a8cf5374be47..aeeb34e64610 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2020, Intel Corporation. */ +#include #include #include "igc.h" diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index f1c10f2bda78..40acfe12adc9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -33,6 +33,7 @@ #include #include +#include #include #include #include diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c index 50977f01a050..00449df98a5e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* Copyright (c) 2020, Mellanox Technologies inc. All rights reserved. */ +#include #include "en.h" #include "params.h" diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index a8c252e2b252..302dc835ac3d 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -5,6 +5,7 @@ * Copyright 2005-2013 Solarflare Communications Inc. */ +#include #include #include #include diff --git a/drivers/net/ethernet/sfc/efx_channels.c b/drivers/net/ethernet/sfc/efx_channels.c index 3dbea028b325..b015d1f2e204 100644 --- a/drivers/net/ethernet/sfc/efx_channels.c +++ b/drivers/net/ethernet/sfc/efx_channels.c @@ -10,6 +10,7 @@ #include "net_driver.h" #include +#include #include "efx_channels.h" #include "efx.h" #include "efx_common.h" diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c index f187631b2c5c..af37c990217e 100644 --- a/drivers/net/ethernet/sfc/efx_common.c +++ b/drivers/net/ethernet/sfc/efx_common.c @@ -9,6 +9,7 @@ */ #include "net_driver.h" +#include #include #include #include diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index b0edb91bb10a..8297411e87ea 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -30,6 +30,7 @@ /*****************************************************************************/ #include +#include #include #include #include diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c index 3d59dac063ac..f90830d3dfa6 100644 --- a/drivers/net/hamradio/scc.c +++ b/drivers/net/hamradio/scc.c @@ -148,6 +148,7 @@ /* ----------------------------------------------------------------------- */ +#include #include #include #include diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index a1c77cc00416..ed0edf5884ef 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -44,6 +44,7 @@ #include #include #include +#include #include #include #include /* For the statistics structure. */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index b4c64226b7ca..e0b1ab99a359 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c index dba055d085be..eb8b4f20c95e 100644 --- a/drivers/net/wireless/ath/ath11k/debugfs.c +++ b/drivers/net/wireless/ath/ath11k/debugfs.c @@ -3,6 +3,8 @@ * Copyright (c) 2018-2020 The Linux Foundation. All rights reserved. */ +#include + #include "debugfs.h" #include "core.h" diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c index 1e85808aaf4b..be761157ea22 100644 --- a/drivers/net/wireless/realtek/rtw89/debug.c +++ b/drivers/net/wireless/realtek/rtw89/debug.c @@ -2,6 +2,8 @@ /* Copyright(c) 2019-2020 Realtek Corporation */ +#include + #include "coex.h" #include "debug.h" #include "fw.h" diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 731d31015b6a..347793626f19 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -18,6 +18,7 @@ * 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM */ +#include #include #include #include diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 0d444a90f513..ea17fa1f31ec 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -10,6 +10,7 @@ * Split from fs/nfs/super.c by David Howells */ +#include #include #include #include diff --git a/fs/select.c b/fs/select.c index 945896d0ac9e..02cd8cb5e69f 100644 --- a/fs/select.c +++ b/fs/select.c @@ -15,6 +15,7 @@ * of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian). */ +#include #include #include #include diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 24496bc28e7b..a2b625960ffe 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -8,6 +8,7 @@ #define _BPF_LOCAL_STORAGE_H #include +#include #include #include #include diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h index 5a3470bcc8a7..b8fef35591aa 100644 --- a/include/linux/dsa/loop.h +++ b/include/linux/dsa/loop.h @@ -2,6 +2,7 @@ #ifndef DSA_LOOP_H #define DSA_LOOP_H +#include #include #include #include diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 53ac7707ca70..3afcb128e064 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -21,6 +21,8 @@ #include #include +struct ip_tunnel_info; + #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 diff --git a/include/net/route.h b/include/net/route.h index 2e6c0e153e3a..4c858dcf1aa8 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -43,6 +43,7 @@ #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) +struct ip_tunnel_info; struct fib_nh; struct fib_info; struct uncached_list; diff --git a/include/net/sock.h b/include/net/sock.h index 37f878564d25..40f6406b9ca5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -56,7 +56,6 @@ #include #include #include -#include #include #include #include @@ -249,6 +248,7 @@ struct sock_common { }; struct bpf_local_storage; +struct sk_filter; /** * struct sock - network layer representation of sockets diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index fff069d2ed1b..3057e1a4a11c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -6,6 +6,7 @@ #ifndef _LINUX_XDP_SOCK_H #define _LINUX_XDP_SOCK_H +#include #include #include #include diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 083be6af29d7..d7ed1dffa426 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include diff --git a/net/bluetooth/bnep/sock.c b/net/bluetooth/bnep/sock.c index d515571b2afb..57d509d77cb4 100644 --- a/net/bluetooth/bnep/sock.c +++ b/net/bluetooth/bnep/sock.c @@ -24,6 +24,7 @@ SOFTWARE IS DISCLAIMED. */ +#include #include #include diff --git a/net/bluetooth/eir.h b/net/bluetooth/eir.h index 724662f8f8b1..05e2e917fc25 100644 --- a/net/bluetooth/eir.h +++ b/net/bluetooth/eir.h @@ -5,6 +5,8 @@ * Copyright (C) 2021 Intel Corporation */ +#include + void eir_create(struct hci_dev *hdev, u8 *data); u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr); diff --git a/net/bluetooth/hidp/sock.c b/net/bluetooth/hidp/sock.c index 595fb3c9d6c3..369ed92dac99 100644 --- a/net/bluetooth/hidp/sock.c +++ b/net/bluetooth/hidp/sock.c @@ -20,6 +20,7 @@ SOFTWARE IS DISCLAIMED. */ +#include #include #include diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 4574c5cb1b59..dc50737b785b 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -29,6 +29,7 @@ #include #include +#include #include #include diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c index db4ab2c2ce18..9b54d7d0bfc4 100644 --- a/net/bridge/br_ioctl.c +++ b/net/bridge/br_ioctl.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index e12fd3cad619..2b8892d502f7 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ +#include #include #include #include diff --git a/net/core/devlink.c b/net/core/devlink.c index 0a9349a02cad..492a26d3c3f1 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -7,6 +7,7 @@ * Copyright (c) 2016 Jiri Pirko */ +#include #include #include #include diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 257976cb55ce..de1109f2cfcf 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 2f7940bcf715..349480ef68a5 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -2,6 +2,7 @@ /* Copyright (c) 2016 Thomas Graf */ +#include #include #include #include diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index c9c45b935f99..f7cf74cdd3db 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -1,5 +1,6 @@ /* License: GPL */ +#include #include #include #include diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 5f88526ad61c..7b4d485aac7a 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -6,6 +6,7 @@ * Added /proc/sys/net/core directory entry (empty =) ). [MS] */ +#include #include #include #include diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index 7ab788f41a3f..c59be5b04479 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -38,6 +38,7 @@ *******************************************************************************/ #include +#include #include #include #include diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 38ce5129a33d..0194a969c9b5 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -8,6 +8,7 @@ #define __DSA_PRIV_H #include +#include #include #include #include diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 9a113d893521..b2cdba1b4aae 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 1319d093cdda..eeafeccebb8d 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0371d2c14145..463c37dea449 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -15,6 +15,7 @@ #define pr_fmt(fmt) "IPv6: " fmt +#include #include #include #include diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 2dc40b3f373e..a5eea182149d 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -7,6 +7,7 @@ * eBPF support: Mathieu Xhonneux */ +#include #include #include #include diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 49ecbe8d176a..a1760add5bf1 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -13,6 +13,7 @@ #define KMSG_COMPONENT "af_iucv" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#include #include #include #include diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 11a715d76a4f..71899e5a5a11 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index d5c719c9e36c..71e29adac48b 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c index d89f68754f42..61cd8c4ac385 100644 --- a/net/netfilter/nft_reject_netdev.c +++ b/net/netfilter/nft_reject_netdev.c @@ -4,6 +4,7 @@ * Copyright (c) 2020 Jose M. Guisado */ +#include #include #include #include diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4be2d97ff93e..7b344035bfe3 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -20,8 +20,10 @@ #include +#include #include #include +#include #include #include #include diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a1ffdb48cc47..3ca4f890371a 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -49,6 +49,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include +#include #include #include #include diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c index 6af786d66b03..4d67f36dce1b 100644 --- a/net/rose/rose_in.c +++ b/net/rose/rose_in.c @@ -9,6 +9,7 @@ * diagrams as the code is not obvious and probably very easy to break. */ #include +#include #include #include #include diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c index 8c06381391d6..cd85a69820b1 100644 --- a/net/sched/sch_frag.c +++ b/net/sched/sch_frag.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +#include #include #include #include diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index d93055ec17ae..905604c378ad 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -12,6 +12,8 @@ * Author(s): Ursula Braun */ +#include +#include #include #include #include diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index fd28cc498b98..a2084ecdb97e 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -6,6 +6,7 @@ * Copyright IBM Corp. 2018 */ +#include #include #include #include diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4d6e33bbd446..c19569819866 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -89,6 +89,7 @@ #include #include #include +#include #include #include #include diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ed0df839c38c..3235261f138d 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -85,6 +85,7 @@ * TCP_LISTEN - listening */ +#include #include #include #include diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 2e48d0e094d9..65b53fb3de13 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -4,6 +4,7 @@ */ #include +#include #include #include #include diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a2f4001221d1..0407272a990c 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -14,6 +14,7 @@ * */ +#include #include #include #include diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 7c36cc1f3d79..e3e26f4da6c2 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -11,6 +11,7 @@ * */ +#include #include #include #include -- cgit v1.2.3 From 0fe4b381a59ebc53522fce579b281a67a9e1bee6 Mon Sep 17 00:00:00 2001 From: KP Singh Date: Fri, 24 Dec 2021 15:29:15 +0000 Subject: bpf: Allow bpf_local_storage to be used by sleepable programs Other maps like hashmaps are already available to sleepable programs. Sleepable BPF programs run under trace RCU. Allow task, sk and inode storage to be used from sleepable programs. This allows sleepable and non-sleepable programs to provide shareable annotations on kernel objects. Sleepable programs run in trace RCU where as non-sleepable programs run in a normal RCU critical section i.e. __bpf_prog_enter{_sleepable} and __bpf_prog_exit{_sleepable}) (rcu_read_lock or rcu_read_lock_trace). In order to make the local storage maps accessible to both sleepable and non-sleepable programs, one needs to call both call_rcu_tasks_trace and call_rcu to wait for both trace and classical RCU grace periods to expire before freeing memory. Paul's work on call_rcu_tasks_trace allows us to have per CPU queueing for call_rcu_tasks_trace. This behaviour can be achieved by setting rcupdate.rcu_task_enqueue_lim= boot parameter. In light of these new performance changes and to keep the local storage code simple, avoid adding a new flag for sleepable maps / local storage to select the RCU synchronization (trace / classical). Also, update the dereferencing of the pointers to use rcu_derference_check (with either the trace or normal RCU locks held) with a common bpf_rcu_lock_held helper method. Signed-off-by: KP Singh Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20211224152916.1550677-2-kpsingh@kernel.org --- include/linux/bpf_local_storage.h | 5 ++++ kernel/bpf/bpf_inode_storage.c | 6 ++++- kernel/bpf/bpf_local_storage.c | 50 +++++++++++++++++++++++++++++---------- kernel/bpf/bpf_task_storage.c | 6 ++++- kernel/bpf/verifier.c | 3 +++ net/core/bpf_sk_storage.c | 8 ++++++- 6 files changed, 62 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index a2b625960ffe..37b3906af8b1 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -17,6 +17,9 @@ #define BPF_LOCAL_STORAGE_CACHE_SIZE 16 +#define bpf_rcu_lock_held() \ + (rcu_read_lock_held() || rcu_read_lock_trace_held() || \ + rcu_read_lock_bh_held()) struct bpf_local_storage_map_bucket { struct hlist_head list; raw_spinlock_t lock; @@ -162,4 +165,6 @@ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags); +void bpf_local_storage_free_rcu(struct rcu_head *rcu); + #endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 96ceed0e0fb5..e29d9e3d853e 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -17,6 +17,7 @@ #include #include #include +#include DEFINE_BPF_STORAGE_CACHE(inode_cache); @@ -44,7 +45,8 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, if (!bsb) return NULL; - inode_storage = rcu_dereference(bsb->storage); + inode_storage = + rcu_dereference_check(bsb->storage, bpf_rcu_lock_held()); if (!inode_storage) return NULL; @@ -172,6 +174,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, { struct bpf_local_storage_data *sdata; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; @@ -204,6 +207,7 @@ BPF_CALL_4(bpf_inode_storage_get, struct bpf_map *, map, struct inode *, inode, BPF_CALL_2(bpf_inode_storage_delete, struct bpf_map *, map, struct inode *, inode) { + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!inode) return -EINVAL; diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index b305270b7a4b..71de2a89869c 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -11,6 +11,9 @@ #include #include #include +#include +#include +#include #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) @@ -81,6 +84,22 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, return NULL; } +void bpf_local_storage_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage *local_storage; + + local_storage = container_of(rcu, struct bpf_local_storage, rcu); + kfree_rcu(local_storage, rcu); +} + +static void bpf_selem_free_rcu(struct rcu_head *rcu) +{ + struct bpf_local_storage_elem *selem; + + selem = container_of(rcu, struct bpf_local_storage_elem, rcu); + kfree_rcu(selem, rcu); +} + /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. @@ -93,7 +112,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, bool free_local_storage; void *owner; - smap = rcu_dereference(SDATA(selem)->smap); + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); owner = local_storage->owner; /* All uncharging on the owner must be done first. @@ -118,12 +137,12 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, * * Although the unlock will be done under * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(local_storage, rcu) is done + * read if the freeing of the storage is done * after the raw_spin_unlock_bh(&local_storage->lock). * * Hence, a "bool free_local_storage" is returned - * to the caller which then calls the kfree_rcu() - * after unlock. + * to the caller which then calls then frees the storage after + * all the RCU grace periods have expired. */ } hlist_del_init_rcu(&selem->snode); @@ -131,8 +150,7 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - kfree_rcu(selem, rcu); - + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); return free_local_storage; } @@ -146,7 +164,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) /* selem has already been unlinked from sk */ return; - local_storage = rcu_dereference(selem->local_storage); + local_storage = rcu_dereference_check(selem->local_storage, + bpf_rcu_lock_held()); raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( @@ -154,7 +173,8 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) raw_spin_unlock_irqrestore(&local_storage->lock, flags); if (free_local_storage) - kfree_rcu(local_storage, rcu); + call_rcu_tasks_trace(&local_storage->rcu, + bpf_local_storage_free_rcu); } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, @@ -174,7 +194,7 @@ void bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) /* selem has already be unlinked from smap */ return; - smap = rcu_dereference(SDATA(selem)->smap); + smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, selem); raw_spin_lock_irqsave(&b->lock, flags); if (likely(selem_linked_to_map(selem))) @@ -213,12 +233,14 @@ bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem; /* Fast path (cache hit) */ - sdata = rcu_dereference(local_storage->cache[smap->cache_idx]); + sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], + bpf_rcu_lock_held()); if (sdata && rcu_access_pointer(sdata->smap) == smap) return sdata; /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode) + hlist_for_each_entry_rcu(selem, &local_storage->list, snode, + rcu_read_lock_trace_held()) if (rcu_access_pointer(SDATA(selem)->smap) == smap) break; @@ -306,7 +328,8 @@ int bpf_local_storage_alloc(void *owner, * bucket->list, first_selem can be freed immediately * (instead of kfree_rcu) because * bpf_local_storage_map_free() does a - * synchronize_rcu() before walking the bucket->list. + * synchronize_rcu_mult (waiting for both sleepable and + * normal programs) before walking the bucket->list. * Hence, no one is accessing selem from the * bucket->list under rcu_read_lock(). */ @@ -342,7 +365,8 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, !map_value_has_spin_lock(&smap->map))) return ERR_PTR(-EINVAL); - local_storage = rcu_dereference(*owner_storage(smap, owner)); + local_storage = rcu_dereference_check(*owner_storage(smap, owner), + bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index bb69aea1a777..5da7bed0f5f6 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -17,6 +17,7 @@ #include #include #include +#include DEFINE_BPF_STORAGE_CACHE(task_cache); @@ -59,7 +60,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map, struct bpf_local_storage *task_storage; struct bpf_local_storage_map *smap; - task_storage = rcu_dereference(task->bpf_storage); + task_storage = + rcu_dereference_check(task->bpf_storage, bpf_rcu_lock_held()); if (!task_storage) return NULL; @@ -229,6 +231,7 @@ BPF_CALL_4(bpf_task_storage_get, struct bpf_map *, map, struct task_struct *, { struct bpf_local_storage_data *sdata; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) return (unsigned long)NULL; @@ -260,6 +263,7 @@ BPF_CALL_2(bpf_task_storage_delete, struct bpf_map *, map, struct task_struct *, { int ret; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!task) return -EINVAL; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ca5cd0de804c..133599dfe2a2 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -11874,6 +11874,9 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } break; case BPF_MAP_TYPE_RINGBUF: + case BPF_MAP_TYPE_INODE_STORAGE: + case BPF_MAP_TYPE_SK_STORAGE: + case BPF_MAP_TYPE_TASK_STORAGE: break; default: verbose(env, diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index ea61dfe19c86..d9c37fd10809 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -13,6 +13,7 @@ #include #include #include +#include DEFINE_BPF_STORAGE_CACHE(sk_cache); @@ -22,7 +23,8 @@ bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) struct bpf_local_storage *sk_storage; struct bpf_local_storage_map *smap; - sk_storage = rcu_dereference(sk->sk_bpf_storage); + sk_storage = + rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held()); if (!sk_storage) return NULL; @@ -258,6 +260,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, { struct bpf_local_storage_data *sdata; + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; @@ -288,6 +291,7 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk)) return -EINVAL; @@ -416,6 +420,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return (unsigned long)NULL; @@ -425,6 +430,7 @@ BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { + WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return -EPERM; -- cgit v1.2.3 From aebb51ec3db2a871d74b4afad3f9914812acf120 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 29 Dec 2021 17:27:42 -0800 Subject: bpf: Invert the dependency between bpf-netns.h and netns/bpf.h netns/bpf.h gets included by netdevice.h (thru net_namespace.h) which in turn gets included in a lot of places. We should keep netns/bpf.h as light-weight as possible. bpf-netns.h seems to contain more implementation details than deserves to be included in a netns header. It needs to pull in uapi/bpf.h to get various enum types. Move enum netns_bpf_attach_type to netns/bpf.h and invert the dependency. This makes netns/bpf.h fit the mold of a struct definition header more clearly, and drops the number of objects rebuilt when uapi/bpf.h is touched from 7.7k to 1.1k. Signed-off-by: Jakub Kicinski Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211230012742.770642-3-kuba@kernel.org --- include/linux/bpf-netns.h | 8 +------- include/net/netns/bpf.h | 9 ++++++++- 2 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 722f799c1a2e..413cfa5e4b07 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -3,15 +3,9 @@ #define _BPF_NETNS_H #include +#include #include -enum netns_bpf_attach_type { - NETNS_BPF_INVALID = -1, - NETNS_BPF_FLOW_DISSECTOR = 0, - NETNS_BPF_SK_LOOKUP, - MAX_NETNS_BPF_ATTACH_TYPE -}; - static inline enum netns_bpf_attach_type to_netns_bpf_attach_type(enum bpf_attach_type attach_type) { diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h index 0ca6a1b87185..2c01a278d1eb 100644 --- a/include/net/netns/bpf.h +++ b/include/net/netns/bpf.h @@ -6,11 +6,18 @@ #ifndef __NETNS_BPF_H__ #define __NETNS_BPF_H__ -#include +#include struct bpf_prog; struct bpf_prog_array; +enum netns_bpf_attach_type { + NETNS_BPF_INVALID = -1, + NETNS_BPF_FLOW_DISSECTOR = 0, + NETNS_BPF_SK_LOOKUP, + MAX_NETNS_BPF_ATTACH_TYPE +}; + struct netns_bpf { /* Array of programs to run compiled from progs or links */ struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE]; -- cgit v1.2.3 From 730b49aac426e1e8016d3c2dd6b407e500423821 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 23 Dec 2021 11:24:22 +0300 Subject: usb: typec: port-mapper: Convert to the component framework Instead of trying to keep track of the connections to the USB Type-C connectors separately, letting the component framework take care of that. From now on every USB Type-C connector will register itself as "aggregate" - component master - and anything that can be connected to it inside the system can then simply register itself as a generic component. The matching of the components and the connector shall rely on ACPI _PLD initially. Before registering itself as the aggregate, the connector will find all other ACPI devices that have matching _PLD crc hash with it (matching value in the pld_crc member of struct acpi_device), and add a component match entry for each one of them. Because only ACPI is supported for now, the driver shall only be build when ACPI is supported. This removes the need for the custom API that the driver exposed. The components and the connector can therefore exist completely independently of each other. The order in which they are registered, as well as are they modules or not, is now irrelevant. Acked-by: Rafael J. Wysocki Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20211223082422.45637-1-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/typec/Makefile | 3 +- drivers/usb/typec/class.c | 2 - drivers/usb/typec/class.h | 10 +- drivers/usb/typec/port-mapper.c | 279 ++++++---------------------------------- include/linux/usb/typec.h | 12 -- 5 files changed, 46 insertions(+), 260 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/typec/Makefile b/drivers/usb/typec/Makefile index a0adb8947a30..57870a2bd787 100644 --- a/drivers/usb/typec/Makefile +++ b/drivers/usb/typec/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_TYPEC) += typec.o -typec-y := class.o mux.o bus.o port-mapper.o +typec-y := class.o mux.o bus.o +typec-$(CONFIG_ACPI) += port-mapper.o obj-$(CONFIG_TYPEC) += altmodes/ obj-$(CONFIG_TYPEC_TCPM) += tcpm/ obj-$(CONFIG_TYPEC_UCSI) += ucsi/ diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index aeef453aa658..45a6f0c807cb 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -2039,8 +2039,6 @@ struct typec_port *typec_register_port(struct device *parent, ida_init(&port->mode_ids); mutex_init(&port->port_type_lock); - mutex_init(&port->port_list_lock); - INIT_LIST_HEAD(&port->port_list); port->id = id; port->ops = cap->ops; diff --git a/drivers/usb/typec/class.h b/drivers/usb/typec/class.h index aef03eb7e152..0f1bd6d19d67 100644 --- a/drivers/usb/typec/class.h +++ b/drivers/usb/typec/class.h @@ -54,11 +54,6 @@ struct typec_port { const struct typec_capability *cap; const struct typec_operations *ops; - - struct list_head port_list; - struct mutex port_list_lock; /* Port list lock */ - - void *pld; }; #define to_typec_port(_dev_) container_of(_dev_, struct typec_port, dev) @@ -79,7 +74,12 @@ extern const struct device_type typec_port_dev_type; extern struct class typec_mux_class; extern struct class typec_class; +#if defined(CONFIG_ACPI) int typec_link_ports(struct typec_port *connector); void typec_unlink_ports(struct typec_port *connector); +#else +static inline int typec_link_ports(struct typec_port *connector) { return 0; } +static inline void typec_unlink_ports(struct typec_port *connector) { } +#endif #endif /* __USB_TYPEC_CLASS__ */ diff --git a/drivers/usb/typec/port-mapper.c b/drivers/usb/typec/port-mapper.c index 9b0991bdf391..07d307418b47 100644 --- a/drivers/usb/typec/port-mapper.c +++ b/drivers/usb/typec/port-mapper.c @@ -7,273 +7,72 @@ */ #include -#include -#include +#include #include "class.h" -struct port_node { - struct list_head list; - struct device *dev; - void *pld; -}; - -static int acpi_pld_match(const struct acpi_pld_info *pld1, - const struct acpi_pld_info *pld2) -{ - if (!pld1 || !pld2) - return 0; - - /* - * To speed things up, first checking only the group_position. It seems - * to often have the first unique value in the _PLD. - */ - if (pld1->group_position == pld2->group_position) - return !memcmp(pld1, pld2, sizeof(struct acpi_pld_info)); - - return 0; -} - -static void *get_pld(struct device *dev) +static int typec_aggregate_bind(struct device *dev) { -#ifdef CONFIG_ACPI - struct acpi_pld_info *pld; - acpi_status status; - - if (!has_acpi_companion(dev)) - return NULL; - - status = acpi_get_physical_device_location(ACPI_HANDLE(dev), &pld); - if (ACPI_FAILURE(status)) - return NULL; - - return pld; -#else - return NULL; -#endif -} - -static void free_pld(void *pld) -{ -#ifdef CONFIG_ACPI - ACPI_FREE(pld); -#endif + return component_bind_all(dev, NULL); } -static int __link_port(struct typec_port *con, struct port_node *node) +static void typec_aggregate_unbind(struct device *dev) { - int ret; - - ret = sysfs_create_link(&node->dev->kobj, &con->dev.kobj, "connector"); - if (ret) - return ret; - - ret = sysfs_create_link(&con->dev.kobj, &node->dev->kobj, - dev_name(node->dev)); - if (ret) { - sysfs_remove_link(&node->dev->kobj, "connector"); - return ret; - } - - list_add_tail(&node->list, &con->port_list); - - return 0; + component_unbind_all(dev, NULL); } -static int link_port(struct typec_port *con, struct port_node *node) -{ - int ret; - - mutex_lock(&con->port_list_lock); - ret = __link_port(con, node); - mutex_unlock(&con->port_list_lock); - - return ret; -} - -static void __unlink_port(struct typec_port *con, struct port_node *node) -{ - sysfs_remove_link(&con->dev.kobj, dev_name(node->dev)); - sysfs_remove_link(&node->dev->kobj, "connector"); - list_del(&node->list); -} - -static void unlink_port(struct typec_port *con, struct port_node *node) -{ - mutex_lock(&con->port_list_lock); - __unlink_port(con, node); - mutex_unlock(&con->port_list_lock); -} - -static struct port_node *create_port_node(struct device *port) -{ - struct port_node *node; - - node = kzalloc(sizeof(*node), GFP_KERNEL); - if (!node) - return ERR_PTR(-ENOMEM); - - node->dev = get_device(port); - node->pld = get_pld(port); - - return node; -} - -static void remove_port_node(struct port_node *node) -{ - put_device(node->dev); - free_pld(node->pld); - kfree(node); -} - -static int connector_match(struct device *dev, const void *data) -{ - const struct port_node *node = data; - - if (!is_typec_port(dev)) - return 0; - - return acpi_pld_match(to_typec_port(dev)->pld, node->pld); -} - -static struct device *find_connector(struct port_node *node) -{ - if (!node->pld) - return NULL; - - return class_find_device(&typec_class, NULL, node, connector_match); -} - -/** - * typec_link_port - Link a port to its connector - * @port: The port device - * - * Find the connector of @port and create symlink named "connector" for it. - * Returns 0 on success, or errno in case of a failure. - * - * NOTE. The function increments the reference count of @port on success. - */ -int typec_link_port(struct device *port) -{ - struct device *connector; - struct port_node *node; - int ret; - - node = create_port_node(port); - if (IS_ERR(node)) - return PTR_ERR(node); - - connector = find_connector(node); - if (!connector) { - ret = 0; - goto remove_node; - } - - ret = link_port(to_typec_port(connector), node); - if (ret) - goto put_connector; - - return 0; - -put_connector: - put_device(connector); -remove_node: - remove_port_node(node); - - return ret; -} -EXPORT_SYMBOL_GPL(typec_link_port); - -static int port_match_and_unlink(struct device *connector, void *port) -{ - struct port_node *node; - struct port_node *tmp; - int ret = 0; - - if (!is_typec_port(connector)) - return 0; - - mutex_lock(&to_typec_port(connector)->port_list_lock); - list_for_each_entry_safe(node, tmp, &to_typec_port(connector)->port_list, list) { - ret = node->dev == port; - if (ret) { - unlink_port(to_typec_port(connector), node); - remove_port_node(node); - put_device(connector); - break; - } - } - mutex_unlock(&to_typec_port(connector)->port_list_lock); +static const struct component_master_ops typec_aggregate_ops = { + .bind = typec_aggregate_bind, + .unbind = typec_aggregate_unbind, +}; - return ret; -} +struct each_port_arg { + struct typec_port *port; + struct component_match *match; +}; -/** - * typec_unlink_port - Unlink port from its connector - * @port: The port device - * - * Removes the symlink "connector" and decrements the reference count of @port. - */ -void typec_unlink_port(struct device *port) +static int typec_port_compare(struct device *dev, void *fwnode) { - class_for_each_device(&typec_class, NULL, port, port_match_and_unlink); + return device_match_fwnode(dev, fwnode); } -EXPORT_SYMBOL_GPL(typec_unlink_port); -static int each_port(struct device *port, void *connector) +static int typec_port_match(struct device *dev, void *data) { - struct port_node *node; - int ret; - - node = create_port_node(port); - if (IS_ERR(node)) - return PTR_ERR(node); + struct acpi_device *adev = to_acpi_device(dev); + struct each_port_arg *arg = data; + struct acpi_device *con_adev; - if (!connector_match(connector, node)) { - remove_port_node(node); + con_adev = ACPI_COMPANION(&arg->port->dev); + if (con_adev == adev) return 0; - } - - ret = link_port(to_typec_port(connector), node); - if (ret) { - remove_port_node(node->pld); - return ret; - } - - get_device(connector); + if (con_adev->pld_crc == adev->pld_crc) + component_match_add(&arg->port->dev, &arg->match, typec_port_compare, + acpi_fwnode_handle(adev)); return 0; } int typec_link_ports(struct typec_port *con) { - int ret = 0; + struct each_port_arg arg = { .port = con, .match = NULL }; - con->pld = get_pld(&con->dev); - if (!con->pld) - return 0; + bus_for_each_dev(&acpi_bus_type, NULL, &arg, typec_port_match); - ret = usb_for_each_port(&con->dev, each_port); - if (ret) - typec_unlink_ports(con); - - return ret; + /* + * REVISIT: Now each connector can have only a single component master. + * So far only the USB ports connected to the USB Type-C connector share + * the _PLD with it, but if there one day is something else (like maybe + * the DisplayPort ACPI device object) that also shares the _PLD with + * the connector, every one of those needs to have its own component + * master, because each different type of component needs to be bind to + * the connector independently of the other components. That requires + * improvements to the component framework. Right now you can only have + * one master per device. + */ + return component_master_add_with_match(&con->dev, &typec_aggregate_ops, arg.match); } void typec_unlink_ports(struct typec_port *con) { - struct port_node *node; - struct port_node *tmp; - - mutex_lock(&con->port_list_lock); - - list_for_each_entry_safe(node, tmp, &con->port_list, list) { - __unlink_port(con, node); - remove_port_node(node); - put_device(&con->dev); - } - - mutex_unlock(&con->port_list_lock); - - free_pld(con->pld); + component_master_del(&con->dev, &typec_aggregate_ops); } diff --git a/include/linux/usb/typec.h b/include/linux/usb/typec.h index e2e44bb1dad8..7ba45a97eeae 100644 --- a/include/linux/usb/typec.h +++ b/include/linux/usb/typec.h @@ -305,16 +305,4 @@ void typec_partner_set_svdm_version(struct typec_partner *partner, enum usb_pd_svdm_ver svdm_version); int typec_get_negotiated_svdm_version(struct typec_port *port); -#if IS_REACHABLE(CONFIG_TYPEC) -int typec_link_port(struct device *port); -void typec_unlink_port(struct device *port); -#else -static inline int typec_link_port(struct device *port) -{ - return 0; -} - -static inline void typec_unlink_port(struct device *port) { } -#endif - #endif /* __LINUX_USB_TYPEC_H */ -- cgit v1.2.3 From 510a0bdb2bfcff8d7be822c72adc3add7a97d559 Mon Sep 17 00:00:00 2001 From: Heikki Krogerus Date: Thu, 23 Dec 2021 11:24:32 +0300 Subject: usb: Remove usb_for_each_port() There are no more users for the function. Reviewed-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Signed-off-by: Heikki Krogerus Link: https://lore.kernel.org/r/20211223082432.45653-1-heikki.krogerus@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/usb.c | 46 ---------------------------------------------- include/linux/usb.h | 9 --------- 2 files changed, 55 deletions(-) (limited to 'include/linux') diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c index 62368c4ed37a..2ce3667ec6fa 100644 --- a/drivers/usb/core/usb.c +++ b/drivers/usb/core/usb.c @@ -398,52 +398,6 @@ int usb_for_each_dev(void *data, int (*fn)(struct usb_device *, void *)) } EXPORT_SYMBOL_GPL(usb_for_each_dev); -struct each_hub_arg { - void *data; - int (*fn)(struct device *, void *); -}; - -static int __each_hub(struct usb_device *hdev, void *data) -{ - struct each_hub_arg *arg = (struct each_hub_arg *)data; - struct usb_hub *hub; - int ret = 0; - int i; - - hub = usb_hub_to_struct_hub(hdev); - if (!hub) - return 0; - - mutex_lock(&usb_port_peer_mutex); - - for (i = 0; i < hdev->maxchild; i++) { - ret = arg->fn(&hub->ports[i]->dev, arg->data); - if (ret) - break; - } - - mutex_unlock(&usb_port_peer_mutex); - - return ret; -} - -/** - * usb_for_each_port - interate over all USB ports in the system - * @data: data pointer that will be handed to the callback function - * @fn: callback function to be called for each USB port - * - * Iterate over all USB ports and call @fn for each, passing it @data. If it - * returns anything other than 0, we break the iteration prematurely and return - * that value. - */ -int usb_for_each_port(void *data, int (*fn)(struct device *, void *)) -{ - struct each_hub_arg arg = {data, fn}; - - return usb_for_each_dev(&arg, __each_hub); -} -EXPORT_SYMBOL_GPL(usb_for_each_port); - /** * usb_release_dev - free a usb device structure when all users of it are finished. * @dev: device that's been disconnected diff --git a/include/linux/usb.h b/include/linux/usb.h index 7ccaa76a9a96..200b7b79acb5 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -875,15 +875,6 @@ extern struct usb_host_interface *usb_find_alt_setting( unsigned int iface_num, unsigned int alt_num); -#if IS_REACHABLE(CONFIG_USB) -int usb_for_each_port(void *data, int (*fn)(struct device *, void *)); -#else -static inline int usb_for_each_port(void *data, int (*fn)(struct device *, void *)) -{ - return 0; -} -#endif - /* port claiming functions */ int usb_hub_claim_port(struct usb_device *hdev, unsigned port1, struct usb_dev_state *owner); -- cgit v1.2.3 From b4a29b94804c4774f22555651296b838df6ec0e4 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Tue, 28 Dec 2021 18:22:00 +0100 Subject: serial: 8250: Move Alpha-specific quirk out of the core struct uart_8250_port contains mcr_mask and mcr_force members whose sole purpose is to work around an Alpha-specific quirk. This code doesn't belong in the core where it is executed by everyone else, so move it to a proper ->set_mctrl callback which is used on the affected Alpha machine only. The quirk was introduced in January 1995: https://git.kernel.org/pub/scm/linux/kernel/git/history/history.git/diff/drivers/char/serial.c?h=1.1.83 The members in struct uart_8250_port were added in 2002: https://git.kernel.org/history/history/c/4524aad27854 The quirk applies to non-PCI Alphas and arch/alpha/Kconfig specifies "select FORCE_PCI if !ALPHA_JENSEN". So apparently the only affected machine is the EISA-based Jensen that Linus was working on back then: https://lore.kernel.org/all/CAHk-=wj1JWZ3sCrGz16nxEj7=0O+srMg6Ah3iPTDXSPKEws_SA@mail.gmail.com/ Up until now the quirk is not applied unless CONFIG_PCI is disabled. If users forget to do that or run a generic Alpha kernel, the serial ports aren't usable on Jensen. Avoid by confining the quirk to CONFIG_ALPHA_JENSEN instead of !CONFIG_PCI. On generic Alpha kernels, auto-detect at runtime whether the quirk needs to be applied. Cc: Russell King Cc: Ulrich Teichert Cc: Linus Torvalds Signed-off-by: Lukas Wunner Link: https://lore.kernel.org/r/b83d069cb516549b8a5420e097bb6bdd806f36fc.1640695609.git.lukas@wunner.de Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serial/8250/8250.h | 12 ++---------- drivers/tty/serial/8250/8250_alpha.c | 21 +++++++++++++++++++++ drivers/tty/serial/8250/8250_core.c | 9 ++++----- drivers/tty/serial/8250/8250_port.c | 2 +- drivers/tty/serial/8250/Makefile | 2 ++ drivers/tty/serial/sunsu.c | 3 ++- include/linux/serial_8250.h | 2 -- 7 files changed, 32 insertions(+), 19 deletions(-) create mode 100644 drivers/tty/serial/8250/8250_alpha.c (limited to 'include/linux') diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 6473361525d1..db784ace25d8 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -241,16 +241,8 @@ static inline int serial8250_in_MCR(struct uart_8250_port *up) return mctrl; } -#if defined(__alpha__) && !defined(CONFIG_PCI) -/* - * Digital did something really horribly wrong with the OUT1 and OUT2 - * lines on at least some ALPHA's. The failure mode is that if either - * is cleared, the machine locks up with endless interrupts. - */ -#define ALPHA_KLUDGE_MCR (UART_MCR_OUT2 | UART_MCR_OUT1) -#else -#define ALPHA_KLUDGE_MCR 0 -#endif +bool alpha_jensen(void); +void alpha_jensen_set_mctrl(struct uart_port *port, unsigned int mctrl); #ifdef CONFIG_SERIAL_8250_PNP int serial8250_pnp_init(void); diff --git a/drivers/tty/serial/8250/8250_alpha.c b/drivers/tty/serial/8250/8250_alpha.c new file mode 100644 index 000000000000..58e70328aa4d --- /dev/null +++ b/drivers/tty/serial/8250/8250_alpha.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include "8250.h" + +bool alpha_jensen(void) +{ + return !strcmp(alpha_mv.vector_name, "Jensen"); +} + +void alpha_jensen_set_mctrl(struct uart_port *port, unsigned int mctrl) +{ + /* + * Digital did something really horribly wrong with the OUT1 and OUT2 + * lines on Alpha Jensen. The failure mode is that if either is + * cleared, the machine locks up with endless interrupts. + */ + mctrl |= TIOCM_OUT1 | TIOCM_OUT2; + + serial8250_do_set_mctrl(port, mctrl); +} diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 1ce193daea7f..01d30f6ed8fb 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -509,11 +509,10 @@ static void __init serial8250_isa_init_ports(void) up->ops = &univ8250_driver_ops; - /* - * ALPHA_KLUDGE_MCR needs to be killed. - */ - up->mcr_mask = ~ALPHA_KLUDGE_MCR; - up->mcr_force = ALPHA_KLUDGE_MCR; + if (IS_ENABLED(CONFIG_ALPHA_JENSEN) || + (IS_ENABLED(CONFIG_ALPHA_GENERIC) && alpha_jensen())) + port->set_mctrl = alpha_jensen_set_mctrl; + serial8250_set_defaults(up); } diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 7e7e67dea0ad..2abb3de11a48 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -2026,7 +2026,7 @@ void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl) mcr = serial8250_TIOCM_to_MCR(mctrl); - mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr; + mcr |= up->mcr; serial8250_out_MCR(up, mcr); } diff --git a/drivers/tty/serial/8250/Makefile b/drivers/tty/serial/8250/Makefile index 4e4913e0e4d2..bee908f99ea0 100644 --- a/drivers/tty/serial/8250/Makefile +++ b/drivers/tty/serial/8250/Makefile @@ -5,6 +5,8 @@ obj-$(CONFIG_SERIAL_8250) += 8250.o 8250_base.o 8250-y := 8250_core.o +8250-$(CONFIG_ALPHA_GENERIC) += 8250_alpha.o +8250-$(CONFIG_ALPHA_JENSEN) += 8250_alpha.o 8250-$(CONFIG_SERIAL_8250_PNP) += 8250_pnp.o 8250_base-y := 8250_port.o 8250_base-$(CONFIG_SERIAL_8250_DMA) += 8250_dma.o diff --git a/drivers/tty/serial/sunsu.c b/drivers/tty/serial/sunsu.c index 425a016f9db7..98b2f4fb9a99 100644 --- a/drivers/tty/serial/sunsu.c +++ b/drivers/tty/serial/sunsu.c @@ -127,7 +127,8 @@ static void serial_out(struct uart_sunsu_port *up, int offset, int value) * gate outputs a logical one. Since we use level triggered interrupts * we have lockup and watchdog reset. We cannot mask IRQ because * keyboard shares IRQ with us (Word has it as Bob Smelik's design). - * This problem is similar to what Alpha people suffer, see serial.c. + * This problem is similar to what Alpha people suffer, see + * 8250_alpha.c. */ if (offset == UART_MCR) value |= UART_MCR_OUT2; diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 5db211f43b29..ff84a3ed10ea 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -104,8 +104,6 @@ struct uart_8250_port { unsigned char ier; unsigned char lcr; unsigned char mcr; - unsigned char mcr_mask; /* mask of user bits */ - unsigned char mcr_force; /* mask of forced bits */ unsigned char cur_iotype; /* Running I/O type */ unsigned int rpm_tx_active; unsigned char canary; /* non-zero during system sleep -- cgit v1.2.3 From d8e9a406a931f687945703a4bac45042eb81ce92 Mon Sep 17 00:00:00 2001 From: Magnus Damm Date: Sun, 12 Dec 2021 22:21:28 +0900 Subject: serdev: BREAK/FRAME/PARITY/OVERRUN notification prototype V2 Allow serdev device drivers get notified by hardware errors such as BREAK, FRAME, PARITY and OVERRUN. With this patch, in the event of an error detected in the UART device driver the serdev_device_driver will get the newly introduced ->error() callback invoked if serdev_device_set_error_mask() has previously been used to enable the type of error. The errors are taken straight from the TTY layer and fed into the serdev_device_driver after filtering out only enabled errors. Without this patch the hardware errors never reach the serdev_device_driver. Signed-off-by: Magnus Damm Link: https://lore.kernel.org/r/163931528842.27756.3665040315954968747.sendpatchset@octo Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serdev/core.c | 11 +++++++++ drivers/tty/serdev/serdev-ttyport.c | 49 +++++++++++++++++++++++++++++++++++++ include/linux/serdev.h | 22 +++++++++++++++++ 3 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index f1324fe99378..5c25ae20e508 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -349,6 +349,17 @@ unsigned int serdev_device_set_baudrate(struct serdev_device *serdev, unsigned i } EXPORT_SYMBOL_GPL(serdev_device_set_baudrate); +void serdev_device_set_error_mask(struct serdev_device *serdev, unsigned long mask) +{ + struct serdev_controller *ctrl = serdev->ctrl; + + if (!ctrl || !ctrl->ops->set_error_mask) + return; + + ctrl->ops->set_error_mask(ctrl, mask); +} +EXPORT_SYMBOL_GPL(serdev_device_set_error_mask); + void serdev_device_set_flow_control(struct serdev_device *serdev, bool enable) { struct serdev_controller *ctrl = serdev->ctrl; diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c index d367803e2044..239a1d5c66df 100644 --- a/drivers/tty/serdev/serdev-ttyport.c +++ b/drivers/tty/serdev/serdev-ttyport.c @@ -2,6 +2,7 @@ /* * Copyright (C) 2016-2017 Linaro Ltd., Rob Herring */ +#include #include #include #include @@ -9,6 +10,10 @@ #include #define SERPORT_ACTIVE 1 +#define SERPORT_NOTIFY_BREAK 2 +#define SERPORT_NOTIFY_FRAME 3 +#define SERPORT_NOTIFY_PARITY 4 +#define SERPORT_NOTIFY_OVERRUN 5 struct serport { struct tty_port *port; @@ -27,11 +32,39 @@ static int ttyport_receive_buf(struct tty_port *port, const unsigned char *cp, { struct serdev_controller *ctrl = port->client_data; struct serport *serport = serdev_controller_get_drvdata(ctrl); + unsigned long errors = 0; + unsigned int i; int ret; if (!test_bit(SERPORT_ACTIVE, &serport->flags)) return 0; + for (i = 0; fp && i < count; i++) { + switch (fp[i]) { + case TTY_BREAK: + if (test_bit(SERPORT_NOTIFY_BREAK, &serport->flags)) + __set_bit(SERDEV_ERROR_BREAK, &errors); + break; + + case TTY_FRAME: + if (test_bit(SERPORT_NOTIFY_FRAME, &serport->flags)) + __set_bit(SERDEV_ERROR_FRAME, &errors); + break; + + case TTY_PARITY: + if (test_bit(SERPORT_NOTIFY_PARITY, &serport->flags)) + __set_bit(SERDEV_ERROR_PARITY, &errors); + break; + + case TTY_OVERRUN: + if (test_bit(SERPORT_NOTIFY_OVERRUN, &serport->flags)) + __set_bit(SERDEV_ERROR_OVERRUN, &errors); + break; + } + } + if (errors) + serdev_controller_error(ctrl, errors); + ret = serdev_controller_receive_buf(ctrl, cp, count); dev_WARN_ONCE(&ctrl->dev, ret < 0 || ret > count, @@ -180,6 +213,21 @@ static unsigned int ttyport_set_baudrate(struct serdev_controller *ctrl, unsigne return ktermios.c_ospeed; } +static void ttyport_set_error_mask(struct serdev_controller *ctrl, + unsigned long m) +{ + struct serport *sp = serdev_controller_get_drvdata(ctrl); + + assign_bit(SERPORT_NOTIFY_BREAK, &sp->flags, + m & BIT(SERDEV_ERROR_BREAK)); + assign_bit(SERPORT_NOTIFY_FRAME, &sp->flags, + m & BIT(SERDEV_ERROR_FRAME)); + assign_bit(SERPORT_NOTIFY_PARITY, &sp->flags, + m & BIT(SERDEV_ERROR_PARITY)); + assign_bit(SERPORT_NOTIFY_OVERRUN, &sp->flags, + m & BIT(SERDEV_ERROR_OVERRUN)); +} + static void ttyport_set_flow_control(struct serdev_controller *ctrl, bool enable) { struct serport *serport = serdev_controller_get_drvdata(ctrl); @@ -253,6 +301,7 @@ static const struct serdev_controller_ops ctrl_ops = { .write_room = ttyport_write_room, .open = ttyport_open, .close = ttyport_close, + .set_error_mask = ttyport_set_error_mask, .set_flow_control = ttyport_set_flow_control, .set_parity = ttyport_set_parity, .set_baudrate = ttyport_set_baudrate, diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 3368c261ab62..0d0b22fc7e37 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -19,12 +19,15 @@ struct serdev_device; /** * struct serdev_device_ops - Callback operations for a serdev device + * @error: Function called with errors received from device; + * may sleep. * @receive_buf: Function called with data received from device; * returns number of bytes accepted; may sleep. * @write_wakeup: Function called when ready to transmit more data; must * not sleep. */ struct serdev_device_ops { + void (*error)(struct serdev_device *, unsigned long); int (*receive_buf)(struct serdev_device *, const unsigned char *, size_t); void (*write_wakeup)(struct serdev_device *); }; @@ -76,6 +79,11 @@ enum serdev_parity { SERDEV_PARITY_ODD, }; +#define SERDEV_ERROR_BREAK 0 +#define SERDEV_ERROR_FRAME 1 +#define SERDEV_ERROR_PARITY 2 +#define SERDEV_ERROR_OVERRUN 3 + /* * serdev controller structures */ @@ -85,6 +93,7 @@ struct serdev_controller_ops { int (*write_room)(struct serdev_controller *); int (*open)(struct serdev_controller *); void (*close)(struct serdev_controller *); + void (*set_error_mask)(struct serdev_controller *, unsigned long); void (*set_flow_control)(struct serdev_controller *, bool); int (*set_parity)(struct serdev_controller *, enum serdev_parity); unsigned int (*set_baudrate)(struct serdev_controller *, unsigned int); @@ -190,12 +199,24 @@ static inline int serdev_controller_receive_buf(struct serdev_controller *ctrl, return serdev->ops->receive_buf(serdev, data, count); } +static inline void serdev_controller_error(struct serdev_controller *ctrl, + unsigned long errors) +{ + struct serdev_device *serdev = ctrl->serdev; + + if (!serdev || !serdev->ops->error) + return; + + serdev->ops->error(serdev, errors); +} + #if IS_ENABLED(CONFIG_SERIAL_DEV_BUS) int serdev_device_open(struct serdev_device *); void serdev_device_close(struct serdev_device *); int devm_serdev_device_open(struct device *, struct serdev_device *); unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int); +void serdev_device_set_error_mask(struct serdev_device *, unsigned long); void serdev_device_set_flow_control(struct serdev_device *, bool); int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t); void serdev_device_wait_until_sent(struct serdev_device *, long); @@ -238,6 +259,7 @@ static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev { return 0; } +static inline void serdev_device_set_error_mask(struct serdev_device *sdev, unsigned long mask) {} static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {} static inline int serdev_device_write_buf(struct serdev_device *serdev, const unsigned char *buf, -- cgit v1.2.3 From 5207fb2f311b0c45a9abfa1c84b7a7b657ffa550 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 30 Dec 2021 16:02:41 +0100 Subject: counter: Provide a wrapper to access device private data MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For now this just wraps accessing struct counter_device::priv. However this is about to change and converting drivers to this helper individually makes fixing device lifetime issues result in easier to review patches. Reviewed-by: Jonathan Cameron Acked-by: William Breathitt Gray Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20211230150300.72196-5-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/counter/counter-core.c | 12 ++++++++++++ include/linux/counter.h | 2 ++ 2 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index f053a43c6c04..00c41f28c101 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -45,6 +45,18 @@ static struct bus_type counter_bus_type = { static dev_t counter_devt; +/** + * counter_priv - access counter device private data + * @counter: counter device + * + * Get the counter device private data + */ +void *counter_priv(const struct counter_device *const counter) +{ + return counter->priv; +} +EXPORT_SYMBOL_GPL(counter_priv); + /** * counter_register - register Counter to the system * @counter: pointer to Counter to register diff --git a/include/linux/counter.h b/include/linux/counter.h index dfbde2808998..627f1757f6bb 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -329,6 +329,8 @@ struct counter_device { struct mutex ops_exist_lock; }; +void *counter_priv(const struct counter_device *const counter); + int counter_register(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, -- cgit v1.2.3 From c18e2760308e30f007fa24b558b87c39d7e86ff1 Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 30 Dec 2021 16:02:50 +0100 Subject: counter: Provide alternative counter registration functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current implementation gets device lifetime tracking wrong. The problem is that allocation of struct counter_device is controlled by the individual drivers but this structure contains a struct device that might have to live longer than a driver is bound. As a result a command sequence like: { sleep 5; echo bang; } > /dev/counter0 & sleep 1; echo 40000000.timer:counter > /sys/bus/platform/drivers/stm32-timer-counter/unbind can keep a reference to the struct device and unbinding results in freeing the memory occupied by this device resulting in an oops. This commit provides two new functions (plus some helpers): - counter_alloc() to allocate a struct counter_device that is automatically freed once the embedded struct device is released - counter_add() to register such a device. Note that this commit doesn't fix any issues, all drivers have to be converted to these new functions to correct the lifetime problems. Reviewed-by: Jonathan Cameron Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20211230150300.72196-14-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/counter/counter-core.c | 168 ++++++++++++++++++++++++++++++++++++++++- include/linux/counter.h | 15 ++++ 2 files changed, 181 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index 00c41f28c101..b3fa15bbcbdb 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -24,6 +25,16 @@ /* Provides a unique ID for each counter device */ static DEFINE_IDA(counter_ida); +struct counter_device_allochelper { + struct counter_device counter; + + /* + * This is cache line aligned to ensure private data behaves like if it + * were kmalloced separately. + */ + unsigned long privdata[] ____cacheline_aligned; +}; + static void counter_device_release(struct device *dev) { struct counter_device *const counter = @@ -31,6 +42,9 @@ static void counter_device_release(struct device *dev) counter_chrdev_remove(counter); ida_free(&counter_ida, dev->id); + + if (!counter->legacy_device) + kfree(container_of(counter, struct counter_device_allochelper, counter)); } static struct device_type counter_device_type = { @@ -53,7 +67,14 @@ static dev_t counter_devt; */ void *counter_priv(const struct counter_device *const counter) { - return counter->priv; + if (counter->legacy_device) { + return counter->priv; + } else { + struct counter_device_allochelper *ch = + container_of(counter, struct counter_device_allochelper, counter); + + return &ch->privdata; + } } EXPORT_SYMBOL_GPL(counter_priv); @@ -74,6 +95,8 @@ int counter_register(struct counter_device *const counter) int id; int err; + counter->legacy_device = true; + /* Acquire unique ID */ id = ida_alloc(&counter_ida, GFP_KERNEL); if (id < 0) @@ -114,6 +137,95 @@ err_free_id: } EXPORT_SYMBOL_GPL(counter_register); +/** + * counter_alloc - allocate a counter_device + * @sizeof_priv: size of the driver private data + * + * This is part one of counter registration. The structure is allocated + * dynamically to ensure the right lifetime for the embedded struct device. + * + * If this succeeds, call counter_put() to get rid of the counter_device again. + */ +struct counter_device *counter_alloc(size_t sizeof_priv) +{ + struct counter_device_allochelper *ch; + struct counter_device *counter; + struct device *dev; + int err; + + ch = kzalloc(sizeof(*ch) + sizeof_priv, GFP_KERNEL); + if (!ch) { + err = -ENOMEM; + goto err_alloc_ch; + } + + counter = &ch->counter; + dev = &counter->dev; + + /* Acquire unique ID */ + err = ida_alloc(&counter_ida, GFP_KERNEL); + if (err < 0) + goto err_ida_alloc; + dev->id = err; + + mutex_init(&counter->ops_exist_lock); + dev->type = &counter_device_type; + dev->bus = &counter_bus_type; + dev->devt = MKDEV(MAJOR(counter_devt), dev->id); + + err = counter_chrdev_add(counter); + if (err < 0) + goto err_chrdev_add; + + device_initialize(dev); + + return counter; + +err_chrdev_add: + + ida_free(&counter_ida, dev->id); +err_ida_alloc: + + kfree(ch); +err_alloc_ch: + + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(counter_alloc); + +void counter_put(struct counter_device *counter) +{ + put_device(&counter->dev); +} +EXPORT_SYMBOL_GPL(counter_put); + +/** + * counter_add - complete registration of a counter + * @counter: the counter to add + * + * This is part two of counter registration. + * + * If this succeeds, call counter_unregister() to get rid of the counter_device again. + */ +int counter_add(struct counter_device *counter) +{ + int err; + struct device *dev = &counter->dev; + + if (counter->parent) { + dev->parent = counter->parent; + dev->of_node = counter->parent->of_node; + } + + err = counter_sysfs_add(counter); + if (err < 0) + return err; + + /* implies device_add(dev) */ + return cdev_device_add(&counter->chrdev, dev); +} +EXPORT_SYMBOL_GPL(counter_add); + /** * counter_unregister - unregister Counter from the system * @counter: pointer to Counter to unregister @@ -134,7 +246,8 @@ void counter_unregister(struct counter_device *const counter) mutex_unlock(&counter->ops_exist_lock); - put_device(&counter->dev); + if (counter->legacy_device) + put_device(&counter->dev); } EXPORT_SYMBOL_GPL(counter_unregister); @@ -168,6 +281,57 @@ int devm_counter_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_counter_register); +static void devm_counter_put(void *counter) +{ + counter_put(counter); +} + +/** + * devm_counter_alloc - allocate a counter_device + * @dev: the device to register the release callback for + * @sizeof_priv: size of the driver private data + * + * This is the device managed version of counter_add(). It registers a cleanup + * callback to care for calling counter_put(). + */ +struct counter_device *devm_counter_alloc(struct device *dev, size_t sizeof_priv) +{ + struct counter_device *counter; + int err; + + counter = counter_alloc(sizeof_priv); + if (IS_ERR(counter)) + return counter; + + err = devm_add_action_or_reset(dev, devm_counter_put, counter); + if (err < 0) + return ERR_PTR(err); + + return counter; +} +EXPORT_SYMBOL_GPL(devm_counter_alloc); + +/** + * devm_counter_add - complete registration of a counter + * @dev: the device to register the release callback for + * @counter: the counter to add + * + * This is the device managed version of counter_add(). It registers a cleanup + * callback to care for calling counter_unregister(). + */ +int devm_counter_add(struct device *dev, + struct counter_device *const counter) +{ + int err; + + err = counter_add(counter); + if (err < 0) + return err; + + return devm_add_action_or_reset(dev, devm_counter_release, counter); +} +EXPORT_SYMBOL_GPL(devm_counter_add); + #define COUNTER_DEV_MAX 256 static int __init counter_init(void) diff --git a/include/linux/counter.h b/include/linux/counter.h index 627f1757f6bb..ed8d5820f0d1 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -327,14 +327,29 @@ struct counter_device { spinlock_t events_in_lock; struct mutex events_out_lock; struct mutex ops_exist_lock; + + /* + * This can go away once all drivers are converted to + * counter_alloc()/counter_add(). + */ + bool legacy_device; }; void *counter_priv(const struct counter_device *const counter); int counter_register(struct counter_device *const counter); + +struct counter_device *counter_alloc(size_t sizeof_priv); +void counter_put(struct counter_device *const counter); +int counter_add(struct counter_device *const counter); + void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, struct counter_device *const counter); +struct counter_device *devm_counter_alloc(struct device *dev, + size_t sizeof_priv); +int devm_counter_add(struct device *dev, + struct counter_device *const counter); void counter_push_event(struct counter_device *const counter, const u8 event, const u8 channel); -- cgit v1.2.3 From f2ee4759fb700b32a1bd830960fe86bf6bdfd0ab Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Thu, 30 Dec 2021 16:03:00 +0100 Subject: counter: remove old and now unused registration API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Usage of counter_register() yields issues in device lifetime tracking. All drivers were converted to the new API, so the old one can go away. Reviewed-by: Jonathan Cameron Acked-by: William Breathitt Gray Signed-off-by: Uwe Kleine-König Link: https://lore.kernel.org/r/20211230150300.72196-24-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/counter/counter-core.c | 100 ++--------------------------------------- include/linux/counter.h | 12 ----- 2 files changed, 4 insertions(+), 108 deletions(-) (limited to 'include/linux') diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index b3fa15bbcbdb..7e0957eea094 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -43,8 +43,7 @@ static void counter_device_release(struct device *dev) counter_chrdev_remove(counter); ida_free(&counter_ida, dev->id); - if (!counter->legacy_device) - kfree(container_of(counter, struct counter_device_allochelper, counter)); + kfree(container_of(counter, struct counter_device_allochelper, counter)); } static struct device_type counter_device_type = { @@ -67,76 +66,13 @@ static dev_t counter_devt; */ void *counter_priv(const struct counter_device *const counter) { - if (counter->legacy_device) { - return counter->priv; - } else { - struct counter_device_allochelper *ch = - container_of(counter, struct counter_device_allochelper, counter); + struct counter_device_allochelper *ch = + container_of(counter, struct counter_device_allochelper, counter); - return &ch->privdata; - } + return &ch->privdata; } EXPORT_SYMBOL_GPL(counter_priv); -/** - * counter_register - register Counter to the system - * @counter: pointer to Counter to register - * - * This function registers a Counter to the system. A sysfs "counter" directory - * will be created and populated with sysfs attributes correlating with the - * Counter Signals, Synapses, and Counts respectively. - * - * RETURNS: - * 0 on success, negative error number on failure. - */ -int counter_register(struct counter_device *const counter) -{ - struct device *const dev = &counter->dev; - int id; - int err; - - counter->legacy_device = true; - - /* Acquire unique ID */ - id = ida_alloc(&counter_ida, GFP_KERNEL); - if (id < 0) - return id; - - mutex_init(&counter->ops_exist_lock); - - /* Configure device structure for Counter */ - dev->id = id; - dev->type = &counter_device_type; - dev->bus = &counter_bus_type; - dev->devt = MKDEV(MAJOR(counter_devt), id); - if (counter->parent) { - dev->parent = counter->parent; - dev->of_node = counter->parent->of_node; - } - device_initialize(dev); - - err = counter_sysfs_add(counter); - if (err < 0) - goto err_free_id; - - err = counter_chrdev_add(counter); - if (err < 0) - goto err_free_id; - - err = cdev_device_add(&counter->chrdev, dev); - if (err < 0) - goto err_remove_chrdev; - - return 0; - -err_remove_chrdev: - counter_chrdev_remove(counter); -err_free_id: - put_device(dev); - return err; -} -EXPORT_SYMBOL_GPL(counter_register); - /** * counter_alloc - allocate a counter_device * @sizeof_priv: size of the driver private data @@ -245,9 +181,6 @@ void counter_unregister(struct counter_device *const counter) wake_up(&counter->events_wait); mutex_unlock(&counter->ops_exist_lock); - - if (counter->legacy_device) - put_device(&counter->dev); } EXPORT_SYMBOL_GPL(counter_unregister); @@ -256,31 +189,6 @@ static void devm_counter_release(void *counter) counter_unregister(counter); } -/** - * devm_counter_register - Resource-managed counter_register - * @dev: device to allocate counter_device for - * @counter: pointer to Counter to register - * - * Managed counter_register. The Counter registered with this function is - * automatically unregistered on driver detach. This function calls - * counter_register internally. Refer to that function for more information. - * - * RETURNS: - * 0 on success, negative error number on failure. - */ -int devm_counter_register(struct device *dev, - struct counter_device *const counter) -{ - int err; - - err = counter_register(counter); - if (err < 0) - return err; - - return devm_add_action_or_reset(dev, devm_counter_release, counter); -} -EXPORT_SYMBOL_GPL(devm_counter_register); - static void devm_counter_put(void *counter) { counter_put(counter); diff --git a/include/linux/counter.h b/include/linux/counter.h index ed8d5820f0d1..1fe17f5adb09 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -314,8 +314,6 @@ struct counter_device { struct counter_comp *ext; size_t num_ext; - void *priv; - struct device dev; struct cdev chrdev; struct list_head events_list; @@ -327,25 +325,15 @@ struct counter_device { spinlock_t events_in_lock; struct mutex events_out_lock; struct mutex ops_exist_lock; - - /* - * This can go away once all drivers are converted to - * counter_alloc()/counter_add(). - */ - bool legacy_device; }; void *counter_priv(const struct counter_device *const counter); -int counter_register(struct counter_device *const counter); - struct counter_device *counter_alloc(size_t sizeof_priv); void counter_put(struct counter_device *const counter); int counter_add(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); -int devm_counter_register(struct device *dev, - struct counter_device *const counter); struct counter_device *devm_counter_alloc(struct device *dev, size_t sizeof_priv); int devm_counter_add(struct device *dev, -- cgit v1.2.3 From d6c6d0bb2cb3af91c9c1546af7cdf4770d0df443 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 29 Dec 2021 12:36:20 +0100 Subject: net: remove references to CONFIG_IRDA in network header files Commit d64c2a76123f ("staging: irda: remove the irda network stack and drivers") removes the config IRDA. Remove the remaining references to this non-existing config in the network header files. Signed-off-by: Lukas Bulwahn Link: https://lore.kernel.org/r/20211229113620.19368-1-lukas.bulwahn@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/atalk.h | 2 +- include/linux/netdevice.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/atalk.h b/include/linux/atalk.h index f6034ba774be..a55bfc6567d0 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -113,7 +113,7 @@ extern int aarp_proto_init(void); /* Inter module exports */ /* Give a device find its atif control structure */ -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) static inline struct atalk_iface *atalk_find_dev(struct net_device *dev) { return dev->atalk_ptr; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2684bdb6defa..6f99c8f51b60 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2098,7 +2098,7 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif struct in_device __rcu *ip_ptr; -- cgit v1.2.3 From c3fb0e280b4cdbf382f59eb6b276e4c6047bc219 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Thu, 18 Nov 2021 02:32:37 +0200 Subject: net/mlx5: DR, Fix lower case macro prefix "mlx5_" to "MLX5_" Macros prefix should be capital letters - fix the prefix in mlx5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED. Signed-off-by: Yevgeny Kliteynik --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c | 2 +- include/linux/mlx5/mlx5_ifc.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 1d8febed0d76..0d7575b64ca4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -152,7 +152,7 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->flex_parser_id_mpls_over_gre = MLX5_CAP_GEN(mdev, flex_parser_id_outer_first_mpls_over_gre); - if (caps->flex_protocols & mlx5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED) + if (caps->flex_protocols & MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED) caps->flex_parser_id_mpls_over_udp = MLX5_CAP_GEN(mdev, flex_parser_id_outer_first_mpls_over_udp_label); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 3d0cdc36a91a..613074d50212 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -359,7 +359,7 @@ static bool dr_mask_is_tnl_mpls_over_gre(struct mlx5dr_match_param *mask, static int dr_matcher_supp_tnl_mpls_over_udp(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & mlx5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED; + return caps->flex_protocols & MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED; } static bool dr_mask_is_tnl_mpls_over_udp(struct mlx5dr_match_param *mask, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index e9db12aae8f9..18b816b41545 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1291,7 +1291,7 @@ enum { enum { MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED = 1 << 4, - mlx5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, + MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, -- cgit v1.2.3 From 0f2a6c3b9219bdf497750258cd2ad513f0056b42 Mon Sep 17 00:00:00 2001 From: Muhammad Sammar Date: Sun, 5 Sep 2021 15:16:21 +0300 Subject: net/mlx5: Add misc5 flow table match parameters Add support for misc5 match parameter as per HW spec, this will allow matching on tunnel_header fields. Signed-off-by: Muhammad Sammar Signed-off-by: Yevgeny Kliteynik --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +- include/linux/mlx5/device.h | 1 + include/linux/mlx5/mlx5_ifc.h | 25 ++++++++++++++++++++++- include/uapi/rdma/mlx5_user_ioctl_cmds.h | 2 +- 4 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 7711db245c63..5469b08d635f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -203,7 +203,7 @@ struct mlx5_ft_underlay_qp { u32 qpn; }; -#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_c00 +#define MLX5_FTE_MATCH_PARAM_RESERVED reserved_at_e00 /* Calculate the fte_match_param length and without the reserved length. * Make sure the reserved field is the last. */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 9c25edfd59a6..604b85dd770a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1117,6 +1117,7 @@ enum { MLX5_MATCH_MISC_PARAMETERS_2 = 1 << 3, MLX5_MATCH_MISC_PARAMETERS_3 = 1 << 4, MLX5_MATCH_MISC_PARAMETERS_4 = 1 << 5, + MLX5_MATCH_MISC_PARAMETERS_5 = 1 << 6, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 18b816b41545..c74c5e147cb9 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -670,6 +670,26 @@ struct mlx5_ifc_fte_match_set_misc4_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_fte_match_set_misc5_bits { + u8 macsec_tag_0[0x20]; + + u8 macsec_tag_1[0x20]; + + u8 macsec_tag_2[0x20]; + + u8 macsec_tag_3[0x20]; + + u8 tunnel_header_0[0x20]; + + u8 tunnel_header_1[0x20]; + + u8 tunnel_header_2[0x20]; + + u8 tunnel_header_3[0x20]; + + u8 reserved_at_100[0x100]; +}; + struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; @@ -1839,7 +1859,9 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_misc4_bits misc_parameters_4; - u8 reserved_at_c00[0x400]; + struct mlx5_ifc_fte_match_set_misc5_bits misc_parameters_5; + + u8 reserved_at_e00[0x200]; }; enum { @@ -5977,6 +5999,7 @@ enum { MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_4 = 0x5, + MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_5 = 0x6, }; struct mlx5_ifc_query_flow_group_out_bits { diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index ca2372864b70..e539c84d63f1 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -252,7 +252,7 @@ enum mlx5_ib_device_query_context_attrs { MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT), }; -#define MLX5_IB_DW_MATCH_PARAM 0x90 +#define MLX5_IB_DW_MATCH_PARAM 0xA0 struct mlx5_ib_match_params { __u32 match_params[MLX5_IB_DW_MATCH_PARAM]; -- cgit v1.2.3 From f59464e257bdbd4df6df9a4505d7858a0baf6cf7 Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Mon, 8 Nov 2021 02:42:50 +0200 Subject: net/mlx5: DR, Add support for matching on geneve_tlv_option_0_exist field Match on geneve_tlv_option_0_exist field on devices that support STEv1. Signed-off-by: Muhammad Sammar Signed-off-by: Yevgeny Kliteynik --- .../ethernet/mellanox/mlx5/core/steering/dr_cmd.c | 7 ++++++ .../mellanox/mlx5/core/steering/dr_matcher.c | 17 +++++++++++++ .../ethernet/mellanox/mlx5/core/steering/dr_ste.c | 17 +++++++++++++ .../ethernet/mellanox/mlx5/core/steering/dr_ste.h | 1 + .../mellanox/mlx5/core/steering/dr_ste_v1.c | 28 ++++++++++++++++++++++ .../mellanox/mlx5/core/steering/dr_types.h | 9 ++++++- .../mellanox/mlx5/core/steering/mlx5_ifc_dr.h | 8 +++++++ include/linux/mlx5/mlx5_ifc.h | 6 +++-- 8 files changed, 90 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index e1a79eb66f3c..4dd619d238cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -132,6 +132,13 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->isolate_vl_tc = MLX5_CAP_GEN(mdev, isolate_vl_tc_new); + /* geneve_tlv_option_0_exist is the indication of + * STE support for lookup type flex_parser_ok + */ + caps->flex_parser_ok_bits_supp = + MLX5_CAP_FLOWTABLE(mdev, + flow_table_properties_nic_receive.ft_field_support.geneve_tlv_option_0_exist); + if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED) { caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index b3e7a611f99e..d9f66faa619e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -140,6 +140,19 @@ static bool dr_mask_is_tnl_geneve_tlv_opt(struct mlx5dr_match_misc3 *misc3) return misc3->geneve_tlv_option_0_data; } +static bool +dr_matcher_supp_flex_parser_ok(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_parser_ok_bits_supp; +} + +static bool dr_mask_is_tnl_geneve_tlv_opt_exist_set(struct mlx5dr_match_misc *misc, + struct mlx5dr_domain *dmn) +{ + return dr_matcher_supp_flex_parser_ok(&dmn->info.caps) && + misc->geneve_tlv_option_0_exist; +} + static bool dr_matcher_supp_tnl_geneve(struct mlx5dr_cmd_caps *caps) { @@ -521,6 +534,10 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, mlx5dr_ste_build_tnl_geneve_tlv_opt(ste_ctx, &sb[idx++], &mask, &dmn->info.caps, inner, rx); + if (dr_mask_is_tnl_geneve_tlv_opt_exist_set(&mask.misc, dmn)) + mlx5dr_ste_build_tnl_geneve_tlv_opt_exist(ste_ctx, &sb[idx++], + &mask, &dmn->info.caps, + inner, rx); } else if (dr_mask_is_tnl_gtpu_any(&mask, dmn)) { if (dr_mask_is_tnl_gtpu_flex_parser_0(&mask, dmn)) mlx5dr_ste_build_tnl_gtpu_flex_parser_0(ste_ctx, &sb[idx++], diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 67094dba233c..7e61742e58a0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -719,6 +719,8 @@ static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec, bo spec->vxlan_vni = IFC_GET_CLR(fte_match_set_misc, mask, vxlan_vni, clr); spec->geneve_vni = IFC_GET_CLR(fte_match_set_misc, mask, geneve_vni, clr); + spec->geneve_tlv_option_0_exist = + IFC_GET_CLR(fte_match_set_misc, mask, geneve_tlv_option_0_exist, clr); spec->geneve_oam = IFC_GET_CLR(fte_match_set_misc, mask, geneve_oam, clr); spec->outer_ipv6_flow_label = @@ -1214,6 +1216,21 @@ void mlx5dr_ste_build_tnl_geneve_tlv_opt(struct mlx5dr_ste_ctx *ste_ctx, ste_ctx->build_tnl_geneve_tlv_opt_init(sb, mask); } +void mlx5dr_ste_build_tnl_geneve_tlv_opt_exist(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) +{ + if (!ste_ctx->build_tnl_geneve_tlv_opt_exist_init) + return; + + sb->rx = rx; + sb->caps = caps; + sb->inner = inner; + ste_ctx->build_tnl_geneve_tlv_opt_exist_init(sb, mask); +} + void mlx5dr_ste_build_tnl_gtpu(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h index e6c25bdf0da0..ca8fa32b8680 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h @@ -135,6 +135,7 @@ struct mlx5dr_ste_ctx { void DR_STE_CTX_BUILDER(tnl_vxlan_gpe); void DR_STE_CTX_BUILDER(tnl_geneve); void DR_STE_CTX_BUILDER(tnl_geneve_tlv_opt); + void DR_STE_CTX_BUILDER(tnl_geneve_tlv_opt_exist); void DR_STE_CTX_BUILDER(register_0); void DR_STE_CTX_BUILDER(register_1); void DR_STE_CTX_BUILDER(src_gvmi_qpn); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 9c72be2c2b6b..6ca06800f1d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -47,6 +47,7 @@ enum { DR_STE_V1_LU_TYPE_ETHL3_IPV4_MISC_I = 0x000f, DR_STE_V1_LU_TYPE_STEERING_REGISTERS_0 = 0x010f, DR_STE_V1_LU_TYPE_STEERING_REGISTERS_1 = 0x0110, + DR_STE_V1_LU_TYPE_FLEX_PARSER_OK = 0x0011, DR_STE_V1_LU_TYPE_FLEX_PARSER_0 = 0x0111, DR_STE_V1_LU_TYPE_FLEX_PARSER_1 = 0x0112, DR_STE_V1_LU_TYPE_ETHL4_MISC_O = 0x0113, @@ -1942,6 +1943,32 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb, sb->ste_build_tag_func = &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_tag; } +static int +dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + uint8_t *tag) +{ + u8 parser_id = sb->caps->flex_parser_id_geneve_tlv_option_0; + struct mlx5dr_match_misc *misc = &value->misc; + + if (misc->geneve_tlv_option_0_exist) { + MLX5_SET(ste_flex_parser_ok, tag, flex_parsers_ok, 1 << parser_id); + misc->geneve_tlv_option_0_exist = 0; + } + + return 0; +} + +static void +dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) +{ + sb->lu_type = DR_STE_V1_LU_TYPE_FLEX_PARSER_OK; + dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_tag(mask, sb, sb->bit_mask); + sb->byte_mask = mlx5dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_tag; +} + static int dr_ste_v1_build_flex_parser_tnl_gtpu_tag(struct mlx5dr_match_param *value, struct mlx5dr_ste_build *sb, u8 *tag) @@ -2041,6 +2068,7 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = { .build_tnl_vxlan_gpe_init = &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init, .build_tnl_geneve_init = &dr_ste_v1_build_flex_parser_tnl_geneve_init, .build_tnl_geneve_tlv_opt_init = &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init, + .build_tnl_geneve_tlv_opt_exist_init = &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init, .build_register_0_init = &dr_ste_v1_build_register_0_init, .build_register_1_init = &dr_ste_v1_build_register_1_init, .build_src_gvmi_qpn_init = &dr_ste_v1_build_src_gvmi_qpn_init, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 5805e2554a59..21a9b07ba327 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -442,6 +442,11 @@ void mlx5dr_ste_build_tnl_geneve_tlv_opt(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_match_param *mask, struct mlx5dr_cmd_caps *caps, bool inner, bool rx); +void mlx5dr_ste_build_tnl_geneve_tlv_opt_exist(struct mlx5dr_ste_ctx *ste_ctx, + struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); void mlx5dr_ste_build_tnl_gtpu(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, @@ -666,7 +671,8 @@ struct mlx5dr_match_misc { u32 reserved_auto3:8; u32 geneve_vni:24; /* GENEVE VNI field (outer) */ - u32 reserved_auto4:7; + u32 reserved_auto4:6; + u32 geneve_tlv_option_0_exist:1; u32 geneve_oam:1; /* GENEVE OAM field (outer) */ u32 reserved_auto5:12; @@ -842,6 +848,7 @@ struct mlx5dr_cmd_caps { u8 flex_parser_id_gtpu_teid; u8 flex_parser_id_gtpu_dw_2; u8 flex_parser_id_gtpu_first_ext_dw_0; + u8 flex_parser_ok_bits_supp; u8 max_ft_level; u16 roce_min_src_udp; u8 sw_format_ver; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h index d0e20bda2622..9604b2091358 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -447,6 +447,14 @@ struct mlx5_ifc_ste_flex_parser_1_bits { u8 flex_parser_4[0x20]; }; +struct mlx5_ifc_ste_flex_parser_ok_bits { + u8 flex_parser_3[0x20]; + u8 flex_parser_2[0x20]; + u8 flex_parsers_ok[0x8]; + u8 reserved_at_48[0x18]; + u8 flex_parser_0[0x20]; +}; + struct mlx5_ifc_ste_flex_parser_tnl_bits { u8 flex_parser_tunneling_header_63_32[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c74c5e147cb9..deaa0f71213f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -372,7 +372,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 reserved_at_37[0x9]; u8 geneve_tlv_option_0_data[0x1]; - u8 reserved_at_41[0x4]; + u8 geneve_tlv_option_0_exist[0x1]; + u8 reserved_at_42[0x3]; u8 outer_first_mpls_over_udp[0x4]; u8 outer_first_mpls_over_gre[0x4]; u8 inner_first_mpls[0x4]; @@ -551,7 +552,8 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 bth_opcode[0x8]; u8 geneve_vni[0x18]; - u8 reserved_at_d8[0x7]; + u8 reserved_at_d8[0x6]; + u8 geneve_tlv_option_0_exist[0x1]; u8 geneve_oam[0x1]; u8 reserved_at_e0[0xc]; -- cgit v1.2.3 From 4ff725e1d4adfd313bc9767523fc8d6e90d50f9c Mon Sep 17 00:00:00 2001 From: Yevgeny Kliteynik Date: Tue, 23 Nov 2021 02:11:12 +0200 Subject: net/mlx5: DR, Ignore modify TTL if device doesn't support it When modifying TTL, packet's csum has to be recalculated. Due to HW issue in ConnectX-5, csum recalculation for modify TTL is supported through a work-around that is specifically enabled by configuration. If the work-around isn't enabled, ignore the modify TTL action rather than adding an unsupported action. Signed-off-by: Yevgeny Kliteynik --- .../mellanox/mlx5/core/steering/dr_action.c | 21 ++++++++++++++++++--- include/linux/mlx5/mlx5_ifc.h | 2 +- 2 files changed, 19 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index f0faf04536d3..c61a5e83c78c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -1560,6 +1560,12 @@ dr_action_modify_check_is_ttl_modify(const void *sw_action) return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL; } +static bool dr_action_modify_ttl_ignore(struct mlx5dr_domain *dmn) +{ + return !mlx5dr_ste_supp_ttl_cs_recalc(&dmn->info.caps) && + !MLX5_CAP_ESW_FLOWTABLE(dmn->mdev, fdb_ipv4_ttl_modify); +} + static int dr_actions_convert_modify_header(struct mlx5dr_action *action, u32 max_hw_actions, u32 num_sw_actions, @@ -1591,8 +1597,13 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, if (ret) return ret; - if (!(*modify_ttl)) - *modify_ttl = dr_action_modify_check_is_ttl_modify(sw_action); + if (!(*modify_ttl) && + dr_action_modify_check_is_ttl_modify(sw_action)) { + if (dr_action_modify_ttl_ignore(dmn)) + continue; + + *modify_ttl = true; + } /* Convert SW action to HW action */ ret = dr_action_modify_sw_to_hw(dmn, @@ -1631,7 +1642,7 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, * modify actions doesn't exceeds the limit */ hw_idx++; - if ((num_sw_actions + hw_idx - i) >= max_hw_actions) { + if (hw_idx >= max_hw_actions) { mlx5dr_dbg(dmn, "Modify header action number exceeds HW limit\n"); return -EINVAL; } @@ -1642,6 +1653,10 @@ static int dr_actions_convert_modify_header(struct mlx5dr_action *action, hw_idx++; } + /* if the resulting HW actions list is empty, add NOP action */ + if (!hw_idx) + hw_idx++; + *num_hw_actions = hw_idx; return 0; diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index deaa0f71213f..598ac3bcc901 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -833,7 +833,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_to_vport_reg_c_id[0x8]; u8 reserved_at_8[0xd]; u8 fdb_modify_header_fwd_to_table[0x1]; - u8 reserved_at_16[0x1]; + u8 fdb_ipv4_ttl_modify[0x1]; u8 flow_source[0x1]; u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; -- cgit v1.2.3 From 99a507a8ea28542ec196e2dd80096708e2482735 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Dec 2021 13:42:30 +0100 Subject: Revert "serdev: BREAK/FRAME/PARITY/OVERRUN notification prototype V2" This reverts commit d8e9a406a931f687945703a4bac45042eb81ce92. It needs some future changes as pointed out by Johan and is not ready to be merged just yet. Reported-by: Johan Hovold Cc: Magnus Damm Link: https://lore.kernel.org/r/Yc7oZ/1tu95Z4wPS@hovoldconsulting.com Signed-off-by: Greg Kroah-Hartman --- drivers/tty/serdev/core.c | 11 --------- drivers/tty/serdev/serdev-ttyport.c | 49 ------------------------------------- include/linux/serdev.h | 22 ----------------- 3 files changed, 82 deletions(-) (limited to 'include/linux') diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c index 5c25ae20e508..f1324fe99378 100644 --- a/drivers/tty/serdev/core.c +++ b/drivers/tty/serdev/core.c @@ -349,17 +349,6 @@ unsigned int serdev_device_set_baudrate(struct serdev_device *serdev, unsigned i } EXPORT_SYMBOL_GPL(serdev_device_set_baudrate); -void serdev_device_set_error_mask(struct serdev_device *serdev, unsigned long mask) -{ - struct serdev_controller *ctrl = serdev->ctrl; - - if (!ctrl || !ctrl->ops->set_error_mask) - return; - - ctrl->ops->set_error_mask(ctrl, mask); -} -EXPORT_SYMBOL_GPL(serdev_device_set_error_mask); - void serdev_device_set_flow_control(struct serdev_device *serdev, bool enable) { struct serdev_controller *ctrl = serdev->ctrl; diff --git a/drivers/tty/serdev/serdev-ttyport.c b/drivers/tty/serdev/serdev-ttyport.c index 239a1d5c66df..d367803e2044 100644 --- a/drivers/tty/serdev/serdev-ttyport.c +++ b/drivers/tty/serdev/serdev-ttyport.c @@ -2,7 +2,6 @@ /* * Copyright (C) 2016-2017 Linaro Ltd., Rob Herring */ -#include #include #include #include @@ -10,10 +9,6 @@ #include #define SERPORT_ACTIVE 1 -#define SERPORT_NOTIFY_BREAK 2 -#define SERPORT_NOTIFY_FRAME 3 -#define SERPORT_NOTIFY_PARITY 4 -#define SERPORT_NOTIFY_OVERRUN 5 struct serport { struct tty_port *port; @@ -32,39 +27,11 @@ static int ttyport_receive_buf(struct tty_port *port, const unsigned char *cp, { struct serdev_controller *ctrl = port->client_data; struct serport *serport = serdev_controller_get_drvdata(ctrl); - unsigned long errors = 0; - unsigned int i; int ret; if (!test_bit(SERPORT_ACTIVE, &serport->flags)) return 0; - for (i = 0; fp && i < count; i++) { - switch (fp[i]) { - case TTY_BREAK: - if (test_bit(SERPORT_NOTIFY_BREAK, &serport->flags)) - __set_bit(SERDEV_ERROR_BREAK, &errors); - break; - - case TTY_FRAME: - if (test_bit(SERPORT_NOTIFY_FRAME, &serport->flags)) - __set_bit(SERDEV_ERROR_FRAME, &errors); - break; - - case TTY_PARITY: - if (test_bit(SERPORT_NOTIFY_PARITY, &serport->flags)) - __set_bit(SERDEV_ERROR_PARITY, &errors); - break; - - case TTY_OVERRUN: - if (test_bit(SERPORT_NOTIFY_OVERRUN, &serport->flags)) - __set_bit(SERDEV_ERROR_OVERRUN, &errors); - break; - } - } - if (errors) - serdev_controller_error(ctrl, errors); - ret = serdev_controller_receive_buf(ctrl, cp, count); dev_WARN_ONCE(&ctrl->dev, ret < 0 || ret > count, @@ -213,21 +180,6 @@ static unsigned int ttyport_set_baudrate(struct serdev_controller *ctrl, unsigne return ktermios.c_ospeed; } -static void ttyport_set_error_mask(struct serdev_controller *ctrl, - unsigned long m) -{ - struct serport *sp = serdev_controller_get_drvdata(ctrl); - - assign_bit(SERPORT_NOTIFY_BREAK, &sp->flags, - m & BIT(SERDEV_ERROR_BREAK)); - assign_bit(SERPORT_NOTIFY_FRAME, &sp->flags, - m & BIT(SERDEV_ERROR_FRAME)); - assign_bit(SERPORT_NOTIFY_PARITY, &sp->flags, - m & BIT(SERDEV_ERROR_PARITY)); - assign_bit(SERPORT_NOTIFY_OVERRUN, &sp->flags, - m & BIT(SERDEV_ERROR_OVERRUN)); -} - static void ttyport_set_flow_control(struct serdev_controller *ctrl, bool enable) { struct serport *serport = serdev_controller_get_drvdata(ctrl); @@ -301,7 +253,6 @@ static const struct serdev_controller_ops ctrl_ops = { .write_room = ttyport_write_room, .open = ttyport_open, .close = ttyport_close, - .set_error_mask = ttyport_set_error_mask, .set_flow_control = ttyport_set_flow_control, .set_parity = ttyport_set_parity, .set_baudrate = ttyport_set_baudrate, diff --git a/include/linux/serdev.h b/include/linux/serdev.h index 0d0b22fc7e37..3368c261ab62 100644 --- a/include/linux/serdev.h +++ b/include/linux/serdev.h @@ -19,15 +19,12 @@ struct serdev_device; /** * struct serdev_device_ops - Callback operations for a serdev device - * @error: Function called with errors received from device; - * may sleep. * @receive_buf: Function called with data received from device; * returns number of bytes accepted; may sleep. * @write_wakeup: Function called when ready to transmit more data; must * not sleep. */ struct serdev_device_ops { - void (*error)(struct serdev_device *, unsigned long); int (*receive_buf)(struct serdev_device *, const unsigned char *, size_t); void (*write_wakeup)(struct serdev_device *); }; @@ -79,11 +76,6 @@ enum serdev_parity { SERDEV_PARITY_ODD, }; -#define SERDEV_ERROR_BREAK 0 -#define SERDEV_ERROR_FRAME 1 -#define SERDEV_ERROR_PARITY 2 -#define SERDEV_ERROR_OVERRUN 3 - /* * serdev controller structures */ @@ -93,7 +85,6 @@ struct serdev_controller_ops { int (*write_room)(struct serdev_controller *); int (*open)(struct serdev_controller *); void (*close)(struct serdev_controller *); - void (*set_error_mask)(struct serdev_controller *, unsigned long); void (*set_flow_control)(struct serdev_controller *, bool); int (*set_parity)(struct serdev_controller *, enum serdev_parity); unsigned int (*set_baudrate)(struct serdev_controller *, unsigned int); @@ -199,24 +190,12 @@ static inline int serdev_controller_receive_buf(struct serdev_controller *ctrl, return serdev->ops->receive_buf(serdev, data, count); } -static inline void serdev_controller_error(struct serdev_controller *ctrl, - unsigned long errors) -{ - struct serdev_device *serdev = ctrl->serdev; - - if (!serdev || !serdev->ops->error) - return; - - serdev->ops->error(serdev, errors); -} - #if IS_ENABLED(CONFIG_SERIAL_DEV_BUS) int serdev_device_open(struct serdev_device *); void serdev_device_close(struct serdev_device *); int devm_serdev_device_open(struct device *, struct serdev_device *); unsigned int serdev_device_set_baudrate(struct serdev_device *, unsigned int); -void serdev_device_set_error_mask(struct serdev_device *, unsigned long); void serdev_device_set_flow_control(struct serdev_device *, bool); int serdev_device_write_buf(struct serdev_device *, const unsigned char *, size_t); void serdev_device_wait_until_sent(struct serdev_device *, long); @@ -259,7 +238,6 @@ static inline unsigned int serdev_device_set_baudrate(struct serdev_device *sdev { return 0; } -static inline void serdev_device_set_error_mask(struct serdev_device *sdev, unsigned long mask) {} static inline void serdev_device_set_flow_control(struct serdev_device *sdev, bool enable) {} static inline int serdev_device_write_buf(struct serdev_device *serdev, const unsigned char *buf, -- cgit v1.2.3 From 9a45ac2320d0a6ae01880a30d4b86025fce4061b Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 22 Dec 2021 22:41:18 -0500 Subject: fbdev: fbmem: add a helper to determine if an aperture is used by a fw fb Add a function for drivers to check if the a firmware initialized fb is corresponds to their aperture. This allows drivers to check if the device corresponds to what the firmware set up as the display device. Bug: https://bugzilla.kernel.org/show_bug.cgi?id=215203 Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1840 Signed-off-by: Alex Deucher --- drivers/video/fbdev/core/fbmem.c | 47 ++++++++++++++++++++++++++++++++++++++++ include/linux/fb.h | 1 + 2 files changed, 48 insertions(+) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c index 826175ad88a2..0fa7ede94fa6 100644 --- a/drivers/video/fbdev/core/fbmem.c +++ b/drivers/video/fbdev/core/fbmem.c @@ -1762,6 +1762,53 @@ int remove_conflicting_framebuffers(struct apertures_struct *a, } EXPORT_SYMBOL(remove_conflicting_framebuffers); +/** + * is_firmware_framebuffer - detect if firmware-configured framebuffer matches + * @a: memory range, users of which are to be checked + * + * This function checks framebuffer devices (initialized by firmware/bootloader) + * which use memory range described by @a. If @a matchesm the function returns + * true, otherwise false. + */ +bool is_firmware_framebuffer(struct apertures_struct *a) +{ + bool do_free = false; + bool found = false; + int i; + + if (!a) { + a = alloc_apertures(1); + if (!a) + return false; + + a->ranges[0].base = 0; + a->ranges[0].size = ~0; + do_free = true; + } + + mutex_lock(®istration_lock); + /* check all firmware fbs and kick off if the base addr overlaps */ + for_each_registered_fb(i) { + struct apertures_struct *gen_aper; + + if (!(registered_fb[i]->flags & FBINFO_MISC_FIRMWARE)) + continue; + + gen_aper = registered_fb[i]->apertures; + if (fb_do_apertures_overlap(gen_aper, a)) { + found = true; + break; + } + } + mutex_unlock(®istration_lock); + + if (do_free) + kfree(a); + + return found; +} +EXPORT_SYMBOL(is_firmware_framebuffer); + /** * remove_conflicting_pci_framebuffers - remove firmware-configured framebuffers for PCI devices * @pdev: PCI device diff --git a/include/linux/fb.h b/include/linux/fb.h index 6f3db99ab990..3da95842b207 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -610,6 +610,7 @@ extern int remove_conflicting_pci_framebuffers(struct pci_dev *pdev, const char *name); extern int remove_conflicting_framebuffers(struct apertures_struct *a, const char *name, bool primary); +extern bool is_firmware_framebuffer(struct apertures_struct *a); extern int fb_prepare_logo(struct fb_info *fb_info, int rotate); extern int fb_show_logo(struct fb_info *fb_info, int rotate); extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size); -- cgit v1.2.3 From 1b4e3f26f9f7553b260b8aed43967500961448a6 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 2 Dec 2021 15:06:14 +0000 Subject: mm: vmscan: Reduce throttling due to a failure to make progress Mike Galbraith, Alexey Avramov and Darrick Wong all reported similar problems due to reclaim throttling for excessive lengths of time. In Alexey's case, a memory hog that should go OOM quickly stalls for several minutes before stalling. In Mike and Darrick's cases, a small memcg environment stalled excessively even though the system had enough memory overall. Commit 69392a403f49 ("mm/vmscan: throttle reclaim when no progress is being made") introduced the problem although commit a19594ca4a8b ("mm/vmscan: increase the timeout if page reclaim is not making progress") made it worse. Systems at or near an OOM state that cannot be recovered must reach OOM quickly and memcg should kill tasks if a memcg is near OOM. To address this, only stall for the first zone in the zonelist, reduce the timeout to 1 tick for VMSCAN_THROTTLE_NOPROGRESS and only stall if the scan control nr_reclaimed is 0, kswapd is still active and there were excessive pages pending for writeback. If kswapd has stopped reclaiming due to excessive failures, do not stall at all so that OOM triggers relatively quickly. Similarly, if an LRU is simply congested, only lightly throttle similar to NOPROGRESS. Alexey's original case was the most straight forward for i in {1..3}; do tail /dev/zero; done On vanilla 5.16-rc1, this test stalled heavily, after the patch the test completes in a few seconds similar to 5.15. Alexey's second test case added watching a youtube video while tail runs 10 times. On 5.15, playback only jitters slightly, 5.16-rc1 stalls a lot with lots of frames missing and numerous audio glitches. With this patch applies, the video plays similarly to 5.15. [lkp@intel.com: Fix W=1 build warning] Link: https://lore.kernel.org/r/99e779783d6c7fce96448a3402061b9dc1b3b602.camel@gmx.de Link: https://lore.kernel.org/r/20211124011954.7cab9bb4@mail.inbox.lv Link: https://lore.kernel.org/r/20211022144651.19914-1-mgorman@techsingularity.net Link: https://lore.kernel.org/r/20211202150614.22440-1-mgorman@techsingularity.net Link: https://linux-regtracking.leemhuis.info/regzbot/regression/20211124011954.7cab9bb4@mail.inbox.lv/ Reported-and-tested-by: Alexey Avramov Reported-and-tested-by: Mike Galbraith Reported-and-tested-by: Darrick J. Wong Reported-by: kernel test robot Acked-by: Hugh Dickins Tracked-by: Thorsten Leemhuis Fixes: 69392a403f49 ("mm/vmscan: throttle reclaim when no progress is being made") Signed-off-by: Mel Gorman Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/trace/events/vmscan.h | 4 ++- mm/vmscan.c | 64 +++++++++++++++++++++++++++++++++++++------ 3 files changed, 59 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 58e744b78c2c..936dc0b6c226 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -277,6 +277,7 @@ enum vmscan_throttle_state { VMSCAN_THROTTLE_WRITEBACK, VMSCAN_THROTTLE_ISOLATED, VMSCAN_THROTTLE_NOPROGRESS, + VMSCAN_THROTTLE_CONGESTED, NR_VMSCAN_THROTTLE, }; diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h index f25a6149d3ba..ca2e9009a651 100644 --- a/include/trace/events/vmscan.h +++ b/include/trace/events/vmscan.h @@ -30,12 +30,14 @@ #define _VMSCAN_THROTTLE_WRITEBACK (1 << VMSCAN_THROTTLE_WRITEBACK) #define _VMSCAN_THROTTLE_ISOLATED (1 << VMSCAN_THROTTLE_ISOLATED) #define _VMSCAN_THROTTLE_NOPROGRESS (1 << VMSCAN_THROTTLE_NOPROGRESS) +#define _VMSCAN_THROTTLE_CONGESTED (1 << VMSCAN_THROTTLE_CONGESTED) #define show_throttle_flags(flags) \ (flags) ? __print_flags(flags, "|", \ {_VMSCAN_THROTTLE_WRITEBACK, "VMSCAN_THROTTLE_WRITEBACK"}, \ {_VMSCAN_THROTTLE_ISOLATED, "VMSCAN_THROTTLE_ISOLATED"}, \ - {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"} \ + {_VMSCAN_THROTTLE_NOPROGRESS, "VMSCAN_THROTTLE_NOPROGRESS"}, \ + {_VMSCAN_THROTTLE_CONGESTED, "VMSCAN_THROTTLE_CONGESTED"} \ ) : "VMSCAN_THROTTLE_NONE" diff --git a/mm/vmscan.c b/mm/vmscan.c index fb9584641ac7..4c4d5f6cd8a3 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1021,6 +1021,39 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +static bool skip_throttle_noprogress(pg_data_t *pgdat) +{ + int reclaimable = 0, write_pending = 0; + int i; + + /* + * If kswapd is disabled, reschedule if necessary but do not + * throttle as the system is likely near OOM. + */ + if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES) + return true; + + /* + * If there are a lot of dirty/writeback pages then do not + * throttle as throttling will occur when the pages cycle + * towards the end of the LRU if still under writeback. + */ + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zone *zone = pgdat->node_zones + i; + + if (!populated_zone(zone)) + continue; + + reclaimable += zone_reclaimable_pages(zone); + write_pending += zone_page_state_snapshot(zone, + NR_ZONE_WRITE_PENDING); + } + if (2 * write_pending <= reclaimable) + return true; + + return false; +} + void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) { wait_queue_head_t *wqh = &pgdat->reclaim_wait[reason]; @@ -1056,8 +1089,16 @@ void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason) } break; + case VMSCAN_THROTTLE_CONGESTED: + fallthrough; case VMSCAN_THROTTLE_NOPROGRESS: - timeout = HZ/2; + if (skip_throttle_noprogress(pgdat)) { + cond_resched(); + return; + } + + timeout = 1; + break; case VMSCAN_THROTTLE_ISOLATED: timeout = HZ/50; @@ -3321,7 +3362,7 @@ again: if (!current_is_kswapd() && current_may_throttle() && !sc->hibernation_mode && test_bit(LRUVEC_CONGESTED, &target_lruvec->flags)) - reclaim_throttle(pgdat, VMSCAN_THROTTLE_WRITEBACK); + reclaim_throttle(pgdat, VMSCAN_THROTTLE_CONGESTED); if (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed, sc)) @@ -3386,16 +3427,16 @@ static void consider_reclaim_throttle(pg_data_t *pgdat, struct scan_control *sc) } /* - * Do not throttle kswapd on NOPROGRESS as it will throttle on - * VMSCAN_THROTTLE_WRITEBACK if there are too many pages under - * writeback and marked for immediate reclaim at the tail of - * the LRU. + * Do not throttle kswapd or cgroup reclaim on NOPROGRESS as it will + * throttle on VMSCAN_THROTTLE_WRITEBACK if there are too many pages + * under writeback and marked for immediate reclaim at the tail of the + * LRU. */ - if (current_is_kswapd()) + if (current_is_kswapd() || cgroup_reclaim(sc)) return; /* Throttle if making no progress at high prioities. */ - if (sc->priority < DEF_PRIORITY - 2) + if (sc->priority == 1 && !sc->nr_reclaimed) reclaim_throttle(pgdat, VMSCAN_THROTTLE_NOPROGRESS); } @@ -3415,6 +3456,7 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) unsigned long nr_soft_scanned; gfp_t orig_mask; pg_data_t *last_pgdat = NULL; + pg_data_t *first_pgdat = NULL; /* * If the number of buffer_heads in the machine exceeds the maximum @@ -3478,14 +3520,18 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) /* need some check for avoid more shrink_zone() */ } + if (!first_pgdat) + first_pgdat = zone->zone_pgdat; + /* See comment about same check for global reclaim above */ if (zone->zone_pgdat == last_pgdat) continue; last_pgdat = zone->zone_pgdat; shrink_node(zone->zone_pgdat, sc); - consider_reclaim_throttle(zone->zone_pgdat, sc); } + consider_reclaim_throttle(first_pgdat, sc); + /* * Restore to original mask to avoid the impact on the caller if we * promoted it to __GFP_HIGHMEM. -- cgit v1.2.3 From e7026f15564fbe0c8b091f218203111f77b84eda Mon Sep 17 00:00:00 2001 From: Colin Foster Date: Tue, 28 Dec 2021 21:03:06 -0800 Subject: net: phy: lynx: refactor Lynx PCS module to use generic phylink_pcs Remove references to lynx_pcs structures so drivers like the Felix DSA can reference alternate PCS drivers. Signed-off-by: Colin Foster Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 3 +-- drivers/net/dsa/ocelot/felix.h | 2 +- drivers/net/dsa/ocelot/felix_vsc9959.c | 20 +++++++++++--------- drivers/net/dsa/ocelot/seville_vsc9953.c | 22 ++++++++++++---------- drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c | 13 ++++++++----- drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h | 3 +-- drivers/net/ethernet/freescale/enetc/enetc_pf.c | 16 ++++++++++------ drivers/net/ethernet/freescale/enetc/enetc_pf.h | 4 ++-- drivers/net/pcs/pcs-lynx.c | 24 ++++++++++++++++++++---- include/linux/pcs-lynx.h | 9 +++------ 10 files changed, 69 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index f4fc403fbc1e..bb2a43070ea8 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include "felix.h" @@ -832,7 +831,7 @@ static void felix_phylink_mac_config(struct dsa_switch *ds, int port, struct dsa_port *dp = dsa_to_port(ds, port); if (felix->pcs && felix->pcs[port]) - phylink_set_pcs(dp->pl, &felix->pcs[port]->pcs); + phylink_set_pcs(dp->pl, felix->pcs[port]); } static void felix_phylink_mac_link_down(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 515bddc012c0..9395ac119d33 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -62,7 +62,7 @@ struct felix { const struct felix_info *info; struct ocelot ocelot; struct mii_bus *imdio; - struct lynx_pcs **pcs; + struct phylink_pcs **pcs; resource_size_t switch_base; resource_size_t imdio_base; enum dsa_tag_protocol tag_proto; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 4ffd303c64ea..93ad1d65e212 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1039,7 +1039,7 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) int rc; felix->pcs = devm_kcalloc(dev, felix->info->num_ports, - sizeof(struct lynx_pcs *), + sizeof(struct phylink_pcs *), GFP_KERNEL); if (!felix->pcs) { dev_err(dev, "failed to allocate array for PCS PHYs\n"); @@ -1088,8 +1088,8 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct phylink_pcs *phylink_pcs; struct mdio_device *pcs; - struct lynx_pcs *lynx; if (dsa_is_unused_port(felix->ds, port)) continue; @@ -1101,13 +1101,13 @@ static int vsc9959_mdio_bus_alloc(struct ocelot *ocelot) if (IS_ERR(pcs)) continue; - lynx = lynx_pcs_create(pcs); - if (!lynx) { + phylink_pcs = lynx_pcs_create(pcs); + if (!phylink_pcs) { mdio_device_free(pcs); continue; } - felix->pcs[port] = lynx; + felix->pcs[port] = phylink_pcs; dev_info(dev, "Found PCS at internal MDIO address %d\n", port); } @@ -1121,13 +1121,15 @@ static void vsc9959_mdio_bus_free(struct ocelot *ocelot) int port; for (port = 0; port < ocelot->num_phys_ports; port++) { - struct lynx_pcs *pcs = felix->pcs[port]; + struct phylink_pcs *phylink_pcs = felix->pcs[port]; + struct mdio_device *mdio_device; - if (!pcs) + if (!phylink_pcs) continue; - mdio_device_free(pcs->mdio); - lynx_pcs_destroy(pcs); + mdio_device = lynx_get_mdio_device(phylink_pcs); + mdio_device_free(mdio_device); + lynx_pcs_destroy(phylink_pcs); } mdiobus_unregister(felix->imdio); } diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index e110550e3507..d34d0f737c16 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1012,7 +1012,7 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) int rc; felix->pcs = devm_kcalloc(dev, felix->info->num_ports, - sizeof(struct phy_device *), + sizeof(struct phylink_pcs *), GFP_KERNEL); if (!felix->pcs) { dev_err(dev, "failed to allocate array for PCS PHYs\n"); @@ -1039,9 +1039,9 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) for (port = 0; port < felix->info->num_ports; port++) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - int addr = port + 4; + struct phylink_pcs *phylink_pcs; struct mdio_device *pcs; - struct lynx_pcs *lynx; + int addr = port + 4; if (dsa_is_unused_port(felix->ds, port)) continue; @@ -1053,13 +1053,13 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) if (IS_ERR(pcs)) continue; - lynx = lynx_pcs_create(pcs); - if (!lynx) { + phylink_pcs = lynx_pcs_create(pcs); + if (!phylink_pcs) { mdio_device_free(pcs); continue; } - felix->pcs[port] = lynx; + felix->pcs[port] = phylink_pcs; dev_info(dev, "Found PCS at internal MDIO address %d\n", addr); } @@ -1073,13 +1073,15 @@ static void vsc9953_mdio_bus_free(struct ocelot *ocelot) int port; for (port = 0; port < ocelot->num_phys_ports; port++) { - struct lynx_pcs *pcs = felix->pcs[port]; + struct phylink_pcs *phylink_pcs = felix->pcs[port]; + struct mdio_device *mdio_device; - if (!pcs) + if (!phylink_pcs) continue; - mdio_device_free(pcs->mdio); - lynx_pcs_destroy(pcs); + mdio_device = lynx_get_mdio_device(phylink_pcs); + mdio_device_free(mdio_device); + lynx_pcs_destroy(phylink_pcs); } mdiobus_unregister(felix->imdio); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 34b2a73c347f..7f509f427e3d 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -2,6 +2,7 @@ /* Copyright 2019 NXP */ #include +#include #include #include "dpaa2-eth.h" @@ -204,11 +205,13 @@ static int dpaa2_pcs_create(struct dpaa2_mac *mac, static void dpaa2_pcs_destroy(struct dpaa2_mac *mac) { - struct lynx_pcs *pcs = mac->pcs; + struct phylink_pcs *phylink_pcs = mac->pcs; - if (pcs) { - struct device *dev = &pcs->mdio->dev; - lynx_pcs_destroy(pcs); + if (phylink_pcs) { + struct mdio_device *mdio = lynx_get_mdio_device(phylink_pcs); + struct device *dev = &mdio->dev; + + lynx_pcs_destroy(phylink_pcs); put_device(dev); mac->pcs = NULL; } @@ -292,7 +295,7 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) mac->phylink = phylink; if (mac->pcs) - phylink_set_pcs(mac->phylink, &mac->pcs->pcs); + phylink_set_pcs(mac->phylink, mac->pcs); err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0); if (err) { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index 7842cbb2207a..1331a8477fe4 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -7,7 +7,6 @@ #include #include #include -#include #include "dpmac.h" #include "dpmac-cmd.h" @@ -23,7 +22,7 @@ struct dpaa2_mac { struct phylink *phylink; phy_interface_t if_mode; enum dpmac_link_type if_link_type; - struct lynx_pcs *pcs; + struct phylink_pcs *pcs; struct fwnode_handle *fw_node; }; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index fe6a544f37f0..e36d2d2ba03d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "enetc_ierb.h" #include "enetc_pf.h" @@ -828,7 +829,7 @@ static int enetc_imdio_create(struct enetc_pf *pf) { struct device *dev = &pf->si->pdev->dev; struct enetc_mdio_priv *mdio_priv; - struct lynx_pcs *pcs_lynx; + struct phylink_pcs *phylink_pcs; struct mdio_device *pcs; struct mii_bus *bus; int err; @@ -860,8 +861,8 @@ static int enetc_imdio_create(struct enetc_pf *pf) goto unregister_mdiobus; } - pcs_lynx = lynx_pcs_create(pcs); - if (!pcs_lynx) { + phylink_pcs = lynx_pcs_create(pcs); + if (!phylink_pcs) { mdio_device_free(pcs); err = -ENOMEM; dev_err(dev, "cannot create lynx pcs (%d)\n", err); @@ -869,7 +870,7 @@ static int enetc_imdio_create(struct enetc_pf *pf) } pf->imdio = bus; - pf->pcs = pcs_lynx; + pf->pcs = phylink_pcs; return 0; @@ -882,8 +883,11 @@ free_mdio_bus: static void enetc_imdio_remove(struct enetc_pf *pf) { + struct mdio_device *mdio_device; + if (pf->pcs) { - mdio_device_free(pf->pcs->mdio); + mdio_device = lynx_get_mdio_device(pf->pcs); + mdio_device_free(mdio_device); lynx_pcs_destroy(pf->pcs); } if (pf->imdio) { @@ -941,7 +945,7 @@ static void enetc_pl_mac_config(struct phylink_config *config, priv = netdev_priv(pf->si->ndev); if (pf->pcs) - phylink_set_pcs(priv->phylink, &pf->pcs->pcs); + phylink_set_pcs(priv->phylink, pf->pcs); } static void enetc_force_rgmii_mac(struct enetc_hw *hw, int speed, int duplex) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h index 263946c51e37..c26bd66e4597 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h @@ -2,7 +2,7 @@ /* Copyright 2017-2019 NXP */ #include "enetc.h" -#include +#include #define ENETC_PF_NUM_RINGS 8 @@ -46,7 +46,7 @@ struct enetc_pf { struct mii_bus *mdio; /* saved for cleanup */ struct mii_bus *imdio; - struct lynx_pcs *pcs; + struct phylink_pcs *pcs; phy_interface_t if_mode; struct phylink_config phylink_config; diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c index af36cd647bf5..7ff7f86ad430 100644 --- a/drivers/net/pcs/pcs-lynx.c +++ b/drivers/net/pcs/pcs-lynx.c @@ -22,6 +22,11 @@ #define IF_MODE_SPEED_MSK GENMASK(3, 2) #define IF_MODE_HALF_DUPLEX BIT(4) +struct lynx_pcs { + struct phylink_pcs pcs; + struct mdio_device *mdio; +}; + enum sgmii_speed { SGMII_SPEED_10 = 0, SGMII_SPEED_100 = 1, @@ -30,6 +35,15 @@ enum sgmii_speed { }; #define phylink_pcs_to_lynx(pl_pcs) container_of((pl_pcs), struct lynx_pcs, pcs) +#define lynx_to_phylink_pcs(lynx) (&(lynx)->pcs) + +struct mdio_device *lynx_get_mdio_device(struct phylink_pcs *pcs) +{ + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + return lynx->mdio; +} +EXPORT_SYMBOL(lynx_get_mdio_device); static void lynx_pcs_get_state_usxgmii(struct mdio_device *pcs, struct phylink_link_state *state) @@ -329,7 +343,7 @@ static const struct phylink_pcs_ops lynx_pcs_phylink_ops = { .pcs_link_up = lynx_pcs_link_up, }; -struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio) +struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio) { struct lynx_pcs *lynx_pcs; @@ -341,13 +355,15 @@ struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio) lynx_pcs->pcs.ops = &lynx_pcs_phylink_ops; lynx_pcs->pcs.poll = true; - return lynx_pcs; + return lynx_to_phylink_pcs(lynx_pcs); } EXPORT_SYMBOL(lynx_pcs_create); -void lynx_pcs_destroy(struct lynx_pcs *pcs) +void lynx_pcs_destroy(struct phylink_pcs *pcs) { - kfree(pcs); + struct lynx_pcs *lynx = phylink_pcs_to_lynx(pcs); + + kfree(lynx); } EXPORT_SYMBOL(lynx_pcs_destroy); diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h index a6440d6ebe95..5712cc2ce775 100644 --- a/include/linux/pcs-lynx.h +++ b/include/linux/pcs-lynx.h @@ -9,13 +9,10 @@ #include #include -struct lynx_pcs { - struct phylink_pcs pcs; - struct mdio_device *mdio; -}; +struct mdio_device *lynx_get_mdio_device(struct phylink_pcs *pcs); -struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); +struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio); -void lynx_pcs_destroy(struct lynx_pcs *pcs); +void lynx_pcs_destroy(struct phylink_pcs *pcs); #endif /* __LINUX_PCS_LYNX_H */ -- cgit v1.2.3 From ece014141cd4b49f2d763f28b19e417b84460560 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 3 May 2021 07:29:47 -0400 Subject: mm/doc: Add documentation for folio_test_uptodate Move the PG_uptodate documentation to be documentation for folio_test_uptodate() and expand on it a little. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/page-flags.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..b3d353d537e2 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -68,9 +68,6 @@ * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as * a result of MADV_FREE). * - * PG_uptodate tells whether the page's contents is valid. When a read - * completes, the page becomes uptodate, unless a disk I/O error happened. - * * PG_referenced, PG_reclaim are used for page reclaim for anonymous and * file-backed pagecache (see mm/vmscan.c). * @@ -615,6 +612,16 @@ TESTPAGEFLAG_FALSE(Ksm, ksm) u64 stable_page_flags(struct page *page); +/** + * folio_test_uptodate - Is this folio up to date? + * @folio: The folio. + * + * The uptodate flag is set on a folio when every byte in the folio is + * at least as new as the corresponding bytes on storage. Anonymous + * and CoW folios are always uptodate. If the folio is not uptodate, + * some of the bytes in it may be; see the is_partially_uptodate() + * address_space operation. + */ static inline bool folio_test_uptodate(struct folio *folio) { bool ret = test_bit(PG_uptodate, folio_flags(folio, 0)); -- cgit v1.2.3 From 10331795fb7991a39ebd0330fdb074cbd81fef48 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 6 Dec 2021 15:24:51 -0500 Subject: pagevec: Add folio_batch The folio_batch is the same as the pagevec, except that it is typed to contain folios and not pages. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski --- include/linux/pagevec.h | 69 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 7f3f19065a9f..c3fa616d7ae7 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -15,8 +15,10 @@ #define PAGEVEC_SIZE 15 struct page; +struct folio; struct address_space; +/* Layout must match folio_batch */ struct pagevec { unsigned char nr; bool percpu_pvec_drained; @@ -81,4 +83,71 @@ static inline void pagevec_release(struct pagevec *pvec) __pagevec_release(pvec); } +/** + * struct folio_batch - A collection of folios. + * + * The folio_batch is used to amortise the cost of retrieving and + * operating on a set of folios. The order of folios in the batch may be + * significant (eg delete_from_page_cache_batch()). Some users of the + * folio_batch store "exceptional" entries in it which can be removed + * by calling folio_batch_remove_exceptionals(). + */ +struct folio_batch { + unsigned char nr; + bool percpu_pvec_drained; + struct folio *folios[PAGEVEC_SIZE]; +}; + +/* Layout must match pagevec */ +static_assert(sizeof(struct pagevec) == sizeof(struct folio_batch)); +static_assert(offsetof(struct pagevec, pages) == + offsetof(struct folio_batch, folios)); + +/** + * folio_batch_init() - Initialise a batch of folios + * @fbatch: The folio batch. + * + * A freshly initialised folio_batch contains zero folios. + */ +static inline void folio_batch_init(struct folio_batch *fbatch) +{ + fbatch->nr = 0; +} + +static inline unsigned int folio_batch_count(struct folio_batch *fbatch) +{ + return fbatch->nr; +} + +static inline unsigned int fbatch_space(struct folio_batch *fbatch) +{ + return PAGEVEC_SIZE - fbatch->nr; +} + +/** + * folio_batch_add() - Add a folio to a batch. + * @fbatch: The folio batch. + * @folio: The folio to add. + * + * The folio is added to the end of the batch. + * The batch must have previously been initialised using folio_batch_init(). + * + * Return: The number of slots still available. + */ +static inline unsigned folio_batch_add(struct folio_batch *fbatch, + struct folio *folio) +{ + fbatch->folios[fbatch->nr++] = folio; + return fbatch_space(fbatch); +} + +static inline void folio_batch_release(struct folio_batch *fbatch) +{ + pagevec_release((struct pagevec *)fbatch); +} + +static inline void folio_batch_remove_exceptionals(struct folio_batch *fbatch) +{ + pagevec_remove_exceptionals((struct pagevec *)fbatch); +} #endif /* _LINUX_PAGEVEC_H */ -- cgit v1.2.3 From e66d70c034dbdfe1a48863f0865ac86aaf2fef1a Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Mon, 13 Dec 2021 10:51:41 +0530 Subject: dmaengine: xilinx_dpdma: use correct SDPX tag for header file Commit 188c310bdd5d ("dmaengine: xilinx_dpdma: stop using slave_id field") add the header file with incorrect format for SPDX tag, fix that WARNING: Improper SPDX comment style for 'include/linux/dma/xilinx_dpdma.h', please use '/*' instead #1: FILE: include/linux/dma/xilinx_dpdma.h:1: +// SPDX-License-Identifier: GPL-2.0 WARNING: Missing or malformed SPDX-License-Identifier tag in line 1 #1: FILE: include/linux/dma/xilinx_dpdma.h:1: +// SPDX-License-Identifier: GPL-2.0 Fixes: 188c310bdd5d ("dmaengine: xilinx_dpdma: stop using slave_id field") Signed-off-by: Vinod Koul Link: https://lore.kernel.org/r/20211213052141.850807-1-vkoul@kernel.org Signed-off-by: Vinod Koul --- include/linux/dma/xilinx_dpdma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dma/xilinx_dpdma.h b/include/linux/dma/xilinx_dpdma.h index 83a1377f03f8..02a4adf8921b 100644 --- a/include/linux/dma/xilinx_dpdma.h +++ b/include/linux/dma/xilinx_dpdma.h @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DMA_XILINX_DPDMA_H #define __LINUX_DMA_XILINX_DPDMA_H -- cgit v1.2.3 From 25fd330370ac40653671f323acc7fb6db27ef6fe Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 15 Dec 2021 02:01:18 +0100 Subject: power: supply_core: Pass pointer to battery info The function to retrieve battery info (from the device tree) assumes we have a static info struct that gets populated by calling into power_supply_get_battery_info(). This is awkward since I want to support tables of static battery info by just assigning a pointer to all info based on e.g. a compatible value in the device tree. We also have a mixture of static and dynamically allocated variables here. Bite the bullet and let power_supply_get_battery_info() allocate also the memory used for the very top level struct power_supply_battery_info container. Pass pointers around and lifecycle this with the psy device just like the stuff we allocate inside it. Change all current users over. As part of the change, initializers need to be added to some previously uninitialized fields in struct power_supply_battery_info. Reviewed-By: Matti Vaittinen Signed-off-by: Linus Walleij Signed-off-by: Sebastian Reichel --- drivers/power/supply/ab8500-bm.h | 2 +- drivers/power/supply/ab8500_bmdata.c | 7 +++--- drivers/power/supply/ab8500_btemp.c | 10 ++++++--- drivers/power/supply/ab8500_chargalg.c | 16 +++++++------- drivers/power/supply/ab8500_fg.c | 18 ++++++++------- drivers/power/supply/axp20x_battery.c | 6 ++--- drivers/power/supply/bd99954-charger.c | 24 +++++++++++--------- drivers/power/supply/bq24190_charger.c | 6 ++--- drivers/power/supply/bq2515x_charger.c | 8 +++---- drivers/power/supply/bq256xx_charger.c | 24 ++++++++++---------- drivers/power/supply/bq25980_charger.c | 6 ++--- drivers/power/supply/bq27xxx_battery.c | 38 ++++++++++++++++---------------- drivers/power/supply/cw2015_battery.c | 20 +++++++++++------ drivers/power/supply/ingenic-battery.c | 14 ++++++------ drivers/power/supply/power_supply_core.c | 19 ++++++++++++++-- drivers/power/supply/sc2731_charger.c | 8 +++---- drivers/power/supply/sc27xx_fuel_gauge.c | 22 +++++++++--------- drivers/power/supply/smb347-charger.c | 34 ++++++++++++++-------------- include/linux/power_supply.h | 2 +- 19 files changed, 157 insertions(+), 127 deletions(-) (limited to 'include/linux') diff --git a/drivers/power/supply/ab8500-bm.h b/drivers/power/supply/ab8500-bm.h index 57e1a8e27e51..56a5aaf9a27a 100644 --- a/drivers/power/supply/ab8500-bm.h +++ b/drivers/power/supply/ab8500-bm.h @@ -439,7 +439,7 @@ struct ab8500_bm_charger_parameters { * @fg_params fuel gauge parameters */ struct ab8500_bm_data { - struct power_supply_battery_info bi; + struct power_supply_battery_info *bi; int temp_now; int temp_interval_chg; int temp_interval_nochg; diff --git a/drivers/power/supply/ab8500_bmdata.c b/drivers/power/supply/ab8500_bmdata.c index 62953f9cb85a..7ae95f537580 100644 --- a/drivers/power/supply/ab8500_bmdata.c +++ b/drivers/power/supply/ab8500_bmdata.c @@ -167,15 +167,16 @@ struct ab8500_bm_data ab8500_bm_data = { int ab8500_bm_of_probe(struct power_supply *psy, struct ab8500_bm_data *bm) { - struct power_supply_battery_info *bi = &bm->bi; + struct power_supply_battery_info *bi; struct device *dev = &psy->dev; int ret; - ret = power_supply_get_battery_info(psy, bi); + ret = power_supply_get_battery_info(psy, &bm->bi); if (ret) { dev_err(dev, "cannot retrieve battery info\n"); return ret; } + bi = bm->bi; /* Fill in defaults for any data missing from the device tree */ if (bi->charge_full_design_uah < 0) @@ -240,5 +241,5 @@ int ab8500_bm_of_probe(struct power_supply *psy, void ab8500_bm_of_remove(struct power_supply *psy, struct ab8500_bm_data *bm) { - power_supply_put_battery_info(psy, &bm->bi); + power_supply_put_battery_info(psy, bm->bi); } diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c index 20253b8a7fe9..cc33c5187fbb 100644 --- a/drivers/power/supply/ab8500_btemp.c +++ b/drivers/power/supply/ab8500_btemp.c @@ -451,12 +451,13 @@ static int ab8500_btemp_res_to_temp(struct ab8500_btemp *di, */ static int ab8500_btemp_measure_temp(struct ab8500_btemp *di) { + struct power_supply_battery_info *bi = di->bm->bi; int temp, ret; static int prev; int rbat, rntc, vntc; if ((di->bm->adc_therm == AB8500_ADC_THERM_BATCTRL) && - (di->bm->bi.technology == POWER_SUPPLY_TECHNOLOGY_UNKNOWN)) { + (bi && (bi->technology == POWER_SUPPLY_TECHNOLOGY_UNKNOWN))) { rbat = ab8500_btemp_get_batctrl_res(di); if (rbat < 0) { @@ -540,7 +541,7 @@ static int ab8500_btemp_id(struct ab8500_btemp *di) * that need it. */ if ((di->bm->adc_therm == AB8500_ADC_THERM_BATCTRL) && - (di->bm->bi.technology == POWER_SUPPLY_TECHNOLOGY_LIPO) && + (di->bm->bi && (di->bm->bi->technology == POWER_SUPPLY_TECHNOLOGY_LIPO)) && (res <= 53407) && (res >= 12500)) { dev_dbg(di->dev, "Set BATCTRL current source to 20uA\n"); di->curr_source = BTEMP_BATCTRL_CURR_SRC_20UA; @@ -807,7 +808,10 @@ static int ab8500_btemp_get_property(struct power_supply *psy, val->intval = 1; break; case POWER_SUPPLY_PROP_TECHNOLOGY: - val->intval = di->bm->bi.technology; + if (di->bm->bi) + val->intval = di->bm->bi->technology; + else + val->intval = POWER_SUPPLY_TECHNOLOGY_UNKNOWN; break; case POWER_SUPPLY_PROP_TEMP: val->intval = ab8500_btemp_get_temp(di); diff --git a/drivers/power/supply/ab8500_chargalg.c b/drivers/power/supply/ab8500_chargalg.c index 86d740ce3a63..c4a2fe07126c 100644 --- a/drivers/power/supply/ab8500_chargalg.c +++ b/drivers/power/supply/ab8500_chargalg.c @@ -352,7 +352,7 @@ static void ab8500_chargalg_state_to(struct ab8500_chargalg *di, static int ab8500_chargalg_check_charger_enable(struct ab8500_chargalg *di) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; switch (di->charge_state) { case STATE_NORMAL: @@ -731,7 +731,7 @@ static void ab8500_chargalg_start_charging(struct ab8500_chargalg *di, */ static void ab8500_chargalg_check_temp(struct ab8500_chargalg *di) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; if (di->batt_data.temp > (bi->temp_alert_min + di->t_hyst_norm) && di->batt_data.temp < (bi->temp_alert_max - di->t_hyst_norm)) { @@ -802,10 +802,10 @@ static void ab8500_chargalg_end_of_charge(struct ab8500_chargalg *di) if (di->charge_status == POWER_SUPPLY_STATUS_CHARGING && di->charge_state == STATE_NORMAL && !di->maintenance_chg && (di->batt_data.volt_uv >= - di->bm->bi.overvoltage_limit_uv || + di->bm->bi->overvoltage_limit_uv || di->events.usb_cv_active || di->events.ac_cv_active) && di->batt_data.avg_curr_ua < - di->bm->bi.charge_term_current_ua && + di->bm->bi->charge_term_current_ua && di->batt_data.avg_curr_ua > 0) { if (++di->eoc_cnt >= EOC_COND_CNT) { di->eoc_cnt = 0; @@ -827,7 +827,7 @@ static void ab8500_chargalg_end_of_charge(struct ab8500_chargalg *di) static void init_maxim_chg_curr(struct ab8500_chargalg *di) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; di->ccm.original_iset_ua = bi->constant_charge_current_max_ua; di->ccm.current_iset_ua = bi->constant_charge_current_max_ua; @@ -920,7 +920,7 @@ static enum maxim_ret ab8500_chargalg_chg_curr_maxim(struct ab8500_chargalg *di) static void handle_maxim_chg_curr(struct ab8500_chargalg *di) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; enum maxim_ret ret; int result; @@ -1299,7 +1299,7 @@ static void ab8500_chargalg_external_power_changed(struct power_supply *psy) */ static void ab8500_chargalg_algorithm(struct ab8500_chargalg *di) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; int charger_status; int ret; int curr_step_lvl_ua; @@ -1723,7 +1723,7 @@ static int ab8500_chargalg_get_property(struct power_supply *psy, if (di->events.batt_ovv) { val->intval = POWER_SUPPLY_HEALTH_OVERVOLTAGE; } else if (di->events.btemp_underover) { - if (di->batt_data.temp <= di->bm->bi.temp_min) + if (di->batt_data.temp <= di->bm->bi->temp_min) val->intval = POWER_SUPPLY_HEALTH_COLD; else val->intval = POWER_SUPPLY_HEALTH_OVERHEAT; diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c index eb3e5c4ca44f..b0919a6a6587 100644 --- a/drivers/power/supply/ab8500_fg.c +++ b/drivers/power/supply/ab8500_fg.c @@ -852,7 +852,7 @@ static int ab8500_fg_bat_voltage(struct ab8500_fg *di) */ static int ab8500_fg_volt_to_capacity(struct ab8500_fg *di, int voltage_uv) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; /* Multiply by 10 because the capacity is tracked in per mille */ return power_supply_batinfo_ocv2cap(bi, voltage_uv, di->bat_temp) * 10; @@ -881,7 +881,7 @@ static int ab8500_fg_uncomp_volt_to_capacity(struct ab8500_fg *di) */ static int ab8500_fg_battery_resistance(struct ab8500_fg *di) { - struct power_supply_battery_info *bi = &di->bm->bi; + struct power_supply_battery_info *bi = di->bm->bi; int resistance_percent = 0; int resistance; @@ -2140,11 +2140,13 @@ static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data) struct power_supply *ext = dev_get_drvdata(dev); const char **supplicants = (const char **)ext->supplied_to; struct ab8500_fg *di; + struct power_supply_battery_info *bi; union power_supply_propval ret; int j; psy = (struct power_supply *)data; di = power_supply_get_drvdata(psy); + bi = di->bm->bi; /* * For all psy where the name of your driver @@ -2207,8 +2209,8 @@ static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data) switch (ext->desc->type) { case POWER_SUPPLY_TYPE_BATTERY: if (!di->flags.batt_id_received && - (di->bm->bi.technology != - POWER_SUPPLY_TECHNOLOGY_UNKNOWN)) { + (bi && (bi->technology != + POWER_SUPPLY_TECHNOLOGY_UNKNOWN))) { const struct ab8500_battery_type *b; b = di->bm->bat_type; @@ -2216,13 +2218,13 @@ static int ab8500_fg_get_ext_psy_data(struct device *dev, void *data) di->flags.batt_id_received = true; di->bat_cap.max_mah_design = - di->bm->bi.charge_full_design_uah; + di->bm->bi->charge_full_design_uah; di->bat_cap.max_mah = di->bat_cap.max_mah_design; di->vbat_nom_uv = - di->bm->bi.voltage_max_design_uv; + di->bm->bi->voltage_max_design_uv; } if (ret.intval) @@ -2992,9 +2994,9 @@ static int ab8500_fg_bind(struct device *dev, struct device *master, return -ENOMEM; } - di->bat_cap.max_mah_design = di->bm->bi.charge_full_design_uah; + di->bat_cap.max_mah_design = di->bm->bi->charge_full_design_uah; di->bat_cap.max_mah = di->bat_cap.max_mah_design; - di->vbat_nom_uv = di->bm->bi.voltage_max_design_uv; + di->vbat_nom_uv = di->bm->bi->voltage_max_design_uv; /* Start the coulomb counter */ ab8500_fg_coulomb_counter(di, true); diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c index 18a9db0df4b1..5d197141f476 100644 --- a/drivers/power/supply/axp20x_battery.c +++ b/drivers/power/supply/axp20x_battery.c @@ -561,7 +561,7 @@ static int axp20x_power_probe(struct platform_device *pdev) { struct axp20x_batt_ps *axp20x_batt; struct power_supply_config psy_cfg = {}; - struct power_supply_battery_info info; + struct power_supply_battery_info *info; struct device *dev = &pdev->dev; if (!of_device_is_available(pdev->dev.of_node)) @@ -615,8 +615,8 @@ static int axp20x_power_probe(struct platform_device *pdev) } if (!power_supply_get_battery_info(axp20x_batt->batt, &info)) { - int vmin = info.voltage_min_design_uv; - int ccc = info.constant_charge_current_max_ua; + int vmin = info->voltage_min_design_uv; + int ccc = info->constant_charge_current_max_ua; if (vmin > 0 && axp20x_set_voltage_min_design(axp20x_batt, vmin)) diff --git a/drivers/power/supply/bd99954-charger.c b/drivers/power/supply/bd99954-charger.c index ffd8bfa08179..96e93e1b8094 100644 --- a/drivers/power/supply/bd99954-charger.c +++ b/drivers/power/supply/bd99954-charger.c @@ -882,7 +882,7 @@ struct dt_init { static int bd9995x_fw_probe(struct bd9995x_device *bd) { int ret; - struct power_supply_battery_info info; + struct power_supply_battery_info *info; u32 property; int i; int regval; @@ -891,49 +891,41 @@ static int bd9995x_fw_probe(struct bd9995x_device *bd) struct battery_init battery_inits[] = { { .name = "trickle-charging current", - .info_data = &info.tricklecharge_current_ua, .range = &charging_current_ranges[0], .ranges = 2, .data = &init->itrich_set, }, { .name = "pre-charging current", - .info_data = &info.precharge_current_ua, .range = &charging_current_ranges[0], .ranges = 2, .data = &init->iprech_set, }, { .name = "pre-to-trickle charge voltage threshold", - .info_data = &info.precharge_voltage_max_uv, .range = &trickle_to_pre_threshold_ranges[0], .ranges = 2, .data = &init->vprechg_th_set, }, { .name = "charging termination current", - .info_data = &info.charge_term_current_ua, .range = &charging_current_ranges[0], .ranges = 2, .data = &init->iterm_set, }, { .name = "charging re-start voltage", - .info_data = &info.charge_restart_voltage_uv, .range = &charge_voltage_regulation_ranges[0], .ranges = 2, .data = &init->vrechg_set, }, { .name = "battery overvoltage limit", - .info_data = &info.overvoltage_limit_uv, .range = &charge_voltage_regulation_ranges[0], .ranges = 2, .data = &init->vbatovp_set, }, { .name = "fast-charging max current", - .info_data = &info.constant_charge_current_max_ua, .range = &fast_charge_current_ranges[0], .ranges = 1, .data = &init->ichg_set, }, { .name = "fast-charging voltage", - .info_data = &info.constant_charge_voltage_max_uv, .range = &charge_voltage_regulation_ranges[0], .ranges = 2, .data = &init->vfastchg_reg_set1, @@ -966,6 +958,16 @@ static int bd9995x_fw_probe(struct bd9995x_device *bd) if (ret < 0) return ret; + /* Put pointers to the generic battery info */ + battery_inits[0].info_data = &info->tricklecharge_current_ua; + battery_inits[1].info_data = &info->precharge_current_ua; + battery_inits[2].info_data = &info->precharge_voltage_max_uv; + battery_inits[3].info_data = &info->charge_term_current_ua; + battery_inits[4].info_data = &info->charge_restart_voltage_uv; + battery_inits[5].info_data = &info->overvoltage_limit_uv; + battery_inits[6].info_data = &info->constant_charge_current_max_ua; + battery_inits[7].info_data = &info->constant_charge_voltage_max_uv; + for (i = 0; i < ARRAY_SIZE(battery_inits); i++) { int val = *battery_inits[i].info_data; const struct linear_range *range = battery_inits[i].range; @@ -980,7 +982,7 @@ static int bd9995x_fw_probe(struct bd9995x_device *bd) dev_err(bd->dev, "Unsupported value for %s\n", battery_inits[i].name); - power_supply_put_battery_info(bd->charger, &info); + power_supply_put_battery_info(bd->charger, info); return -EINVAL; } if (!found) { @@ -991,7 +993,7 @@ static int bd9995x_fw_probe(struct bd9995x_device *bd) *(battery_inits[i].data) = regval; } - power_supply_put_battery_info(bd->charger, &info); + power_supply_put_battery_info(bd->charger, info); for (i = 0; i < ARRAY_SIZE(props); i++) { ret = device_property_read_u32(bd->dev, props[i].prop, diff --git a/drivers/power/supply/bq24190_charger.c b/drivers/power/supply/bq24190_charger.c index 35ff0c8fe96f..06c34b09349c 100644 --- a/drivers/power/supply/bq24190_charger.c +++ b/drivers/power/supply/bq24190_charger.c @@ -1670,7 +1670,7 @@ static int bq24190_hw_init(struct bq24190_dev_info *bdi) static int bq24190_get_config(struct bq24190_dev_info *bdi) { const char * const s = "ti,system-minimum-microvolt"; - struct power_supply_battery_info info = {}; + struct power_supply_battery_info *info; int v; if (device_property_read_u32(bdi->dev, s, &v) == 0) { @@ -1684,7 +1684,7 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi) if (bdi->dev->of_node && !power_supply_get_battery_info(bdi->charger, &info)) { - v = info.precharge_current_ua / 1000; + v = info->precharge_current_ua / 1000; if (v >= BQ24190_REG_PCTCC_IPRECHG_MIN && v <= BQ24190_REG_PCTCC_IPRECHG_MAX) bdi->iprechg = v; @@ -1692,7 +1692,7 @@ static int bq24190_get_config(struct bq24190_dev_info *bdi) dev_warn(bdi->dev, "invalid value for battery:precharge-current-microamp: %d\n", v); - v = info.charge_term_current_ua / 1000; + v = info->charge_term_current_ua / 1000; if (v >= BQ24190_REG_PCTCC_ITERM_MIN && v <= BQ24190_REG_PCTCC_ITERM_MAX) bdi->iterm = v; diff --git a/drivers/power/supply/bq2515x_charger.c b/drivers/power/supply/bq2515x_charger.c index 374b112f712a..4f76ad9c2f18 100644 --- a/drivers/power/supply/bq2515x_charger.c +++ b/drivers/power/supply/bq2515x_charger.c @@ -945,7 +945,7 @@ static int bq2515x_power_supply_register(struct bq2515x_device *bq2515x, static int bq2515x_hw_init(struct bq2515x_device *bq2515x) { int ret; - struct power_supply_battery_info bat_info = { }; + struct power_supply_battery_info *bat_info; ret = bq2515x_disable_watchdog_timers(bq2515x); if (ret) @@ -969,13 +969,13 @@ static int bq2515x_hw_init(struct bq2515x_device *bq2515x) } else { bq2515x->init_data.ichg = - bat_info.constant_charge_current_max_ua; + bat_info->constant_charge_current_max_ua; bq2515x->init_data.vbatreg = - bat_info.constant_charge_voltage_max_uv; + bat_info->constant_charge_voltage_max_uv; bq2515x->init_data.iprechg = - bat_info.precharge_current_ua; + bat_info->precharge_current_ua; } ret = bq2515x_set_const_charge_current(bq2515x, diff --git a/drivers/power/supply/bq256xx_charger.c b/drivers/power/supply/bq256xx_charger.c index f501ecd49202..b274942dc46a 100644 --- a/drivers/power/supply/bq256xx_charger.c +++ b/drivers/power/supply/bq256xx_charger.c @@ -1504,7 +1504,7 @@ static int bq256xx_power_supply_init(struct bq256xx_device *bq, static int bq256xx_hw_init(struct bq256xx_device *bq) { - struct power_supply_battery_info bat_info = { }; + struct power_supply_battery_info *bat_info; int wd_reg_val = BQ256XX_WATCHDOG_DIS; int ret = 0; int i; @@ -1526,16 +1526,16 @@ static int bq256xx_hw_init(struct bq256xx_device *bq) if (ret) { dev_warn(bq->dev, "battery info missing, default values will be applied\n"); - bat_info.constant_charge_current_max_ua = + bat_info->constant_charge_current_max_ua = bq->chip_info->bq256xx_def_ichg; - bat_info.constant_charge_voltage_max_uv = + bat_info->constant_charge_voltage_max_uv = bq->chip_info->bq256xx_def_vbatreg; - bat_info.precharge_current_ua = + bat_info->precharge_current_ua = bq->chip_info->bq256xx_def_iprechg; - bat_info.charge_term_current_ua = + bat_info->charge_term_current_ua = bq->chip_info->bq256xx_def_iterm; bq->init_data.ichg_max = @@ -1545,10 +1545,10 @@ static int bq256xx_hw_init(struct bq256xx_device *bq) bq->chip_info->bq256xx_max_vbatreg; } else { bq->init_data.ichg_max = - bat_info.constant_charge_current_max_ua; + bat_info->constant_charge_current_max_ua; bq->init_data.vbatreg_max = - bat_info.constant_charge_voltage_max_uv; + bat_info->constant_charge_voltage_max_uv; } ret = bq->chip_info->bq256xx_set_vindpm(bq, bq->init_data.vindpm); @@ -1560,26 +1560,26 @@ static int bq256xx_hw_init(struct bq256xx_device *bq) return ret; ret = bq->chip_info->bq256xx_set_ichg(bq, - bat_info.constant_charge_current_max_ua); + bat_info->constant_charge_current_max_ua); if (ret) return ret; ret = bq->chip_info->bq256xx_set_iprechg(bq, - bat_info.precharge_current_ua); + bat_info->precharge_current_ua); if (ret) return ret; ret = bq->chip_info->bq256xx_set_vbatreg(bq, - bat_info.constant_charge_voltage_max_uv); + bat_info->constant_charge_voltage_max_uv); if (ret) return ret; ret = bq->chip_info->bq256xx_set_iterm(bq, - bat_info.charge_term_current_ua); + bat_info->charge_term_current_ua); if (ret) return ret; - power_supply_put_battery_info(bq->charger, &bat_info); + power_supply_put_battery_info(bq->charger, bat_info); return 0; } diff --git a/drivers/power/supply/bq25980_charger.c b/drivers/power/supply/bq25980_charger.c index 0008c229fd9c..9daa6d14db4d 100644 --- a/drivers/power/supply/bq25980_charger.c +++ b/drivers/power/supply/bq25980_charger.c @@ -1079,7 +1079,7 @@ static int bq25980_power_supply_init(struct bq25980_device *bq, static int bq25980_hw_init(struct bq25980_device *bq) { - struct power_supply_battery_info bat_info = { }; + struct power_supply_battery_info *bat_info; int wd_reg_val = BQ25980_WATCHDOG_DIS; int wd_max_val = BQ25980_NUM_WD_VAL - 1; int ret = 0; @@ -1112,8 +1112,8 @@ static int bq25980_hw_init(struct bq25980_device *bq) return -EINVAL; } - bq->init_data.ichg_max = bat_info.constant_charge_current_max_ua; - bq->init_data.vreg_max = bat_info.constant_charge_voltage_max_uv; + bq->init_data.ichg_max = bat_info->constant_charge_current_max_ua; + bq->init_data.vreg_max = bat_info->constant_charge_voltage_max_uv; if (bq->state.bypass) { ret = regmap_update_bits(bq->regmap, BQ25980_CHRGR_CTRL_2, diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 7e5e24b585d8..72e727cd31e8 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1474,7 +1474,7 @@ static void bq27xxx_battery_set_config(struct bq27xxx_device_info *di, static void bq27xxx_battery_settings(struct bq27xxx_device_info *di) { - struct power_supply_battery_info info = {}; + struct power_supply_battery_info *info; unsigned int min, max; if (power_supply_get_battery_info(di->bat, &info) < 0) @@ -1485,43 +1485,43 @@ static void bq27xxx_battery_settings(struct bq27xxx_device_info *di) return; } - if (info.energy_full_design_uwh != info.charge_full_design_uah) { - if (info.energy_full_design_uwh == -EINVAL) + if (info->energy_full_design_uwh != info->charge_full_design_uah) { + if (info->energy_full_design_uwh == -EINVAL) dev_warn(di->dev, "missing battery:energy-full-design-microwatt-hours\n"); - else if (info.charge_full_design_uah == -EINVAL) + else if (info->charge_full_design_uah == -EINVAL) dev_warn(di->dev, "missing battery:charge-full-design-microamp-hours\n"); } /* assume min == 0 */ max = di->dm_regs[BQ27XXX_DM_DESIGN_ENERGY].max; - if (info.energy_full_design_uwh > max * 1000) { + if (info->energy_full_design_uwh > max * 1000) { dev_err(di->dev, "invalid battery:energy-full-design-microwatt-hours %d\n", - info.energy_full_design_uwh); - info.energy_full_design_uwh = -EINVAL; + info->energy_full_design_uwh); + info->energy_full_design_uwh = -EINVAL; } /* assume min == 0 */ max = di->dm_regs[BQ27XXX_DM_DESIGN_CAPACITY].max; - if (info.charge_full_design_uah > max * 1000) { + if (info->charge_full_design_uah > max * 1000) { dev_err(di->dev, "invalid battery:charge-full-design-microamp-hours %d\n", - info.charge_full_design_uah); - info.charge_full_design_uah = -EINVAL; + info->charge_full_design_uah); + info->charge_full_design_uah = -EINVAL; } min = di->dm_regs[BQ27XXX_DM_TERMINATE_VOLTAGE].min; max = di->dm_regs[BQ27XXX_DM_TERMINATE_VOLTAGE].max; - if ((info.voltage_min_design_uv < min * 1000 || - info.voltage_min_design_uv > max * 1000) && - info.voltage_min_design_uv != -EINVAL) { + if ((info->voltage_min_design_uv < min * 1000 || + info->voltage_min_design_uv > max * 1000) && + info->voltage_min_design_uv != -EINVAL) { dev_err(di->dev, "invalid battery:voltage-min-design-microvolt %d\n", - info.voltage_min_design_uv); - info.voltage_min_design_uv = -EINVAL; + info->voltage_min_design_uv); + info->voltage_min_design_uv = -EINVAL; } - if ((info.energy_full_design_uwh != -EINVAL && - info.charge_full_design_uah != -EINVAL) || - info.voltage_min_design_uv != -EINVAL) - bq27xxx_battery_set_config(di, &info); + if ((info->energy_full_design_uwh != -EINVAL && + info->charge_full_design_uah != -EINVAL) || + info->voltage_min_design_uv != -EINVAL) + bq27xxx_battery_set_config(di, info); } /* diff --git a/drivers/power/supply/cw2015_battery.c b/drivers/power/supply/cw2015_battery.c index 091868e9e9e8..0c87ad0dbf71 100644 --- a/drivers/power/supply/cw2015_battery.c +++ b/drivers/power/supply/cw2015_battery.c @@ -61,7 +61,7 @@ struct cw_battery { struct delayed_work battery_delay_work; struct regmap *regmap; struct power_supply *rk_bat; - struct power_supply_battery_info battery; + struct power_supply_battery_info *battery; u8 *bat_profile; bool charger_attached; @@ -505,22 +505,22 @@ static int cw_battery_get_property(struct power_supply *psy, case POWER_SUPPLY_PROP_CHARGE_FULL: case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN: - if (cw_bat->battery.charge_full_design_uah > 0) - val->intval = cw_bat->battery.charge_full_design_uah; + if (cw_bat->battery->charge_full_design_uah > 0) + val->intval = cw_bat->battery->charge_full_design_uah; else val->intval = 0; break; case POWER_SUPPLY_PROP_CHARGE_NOW: - val->intval = cw_bat->battery.charge_full_design_uah; + val->intval = cw_bat->battery->charge_full_design_uah; val->intval = val->intval * cw_bat->soc / 100; break; case POWER_SUPPLY_PROP_CURRENT_NOW: if (cw_battery_valid_time_to_empty(cw_bat) && - cw_bat->battery.charge_full_design_uah > 0) { + cw_bat->battery->charge_full_design_uah > 0) { /* calculate remaining capacity */ - val->intval = cw_bat->battery.charge_full_design_uah; + val->intval = cw_bat->battery->charge_full_design_uah; val->intval = val->intval * cw_bat->soc / 100; /* estimate current based on time to empty */ @@ -687,6 +687,12 @@ static int cw_bat_probe(struct i2c_client *client) ret = power_supply_get_battery_info(cw_bat->rk_bat, &cw_bat->battery); if (ret) { + /* Allocate an empty battery */ + cw_bat->battery = devm_kzalloc(&client->dev, + sizeof(cw_bat->battery), + GFP_KERNEL); + if (!cw_bat->battery) + return -ENOMEM; dev_warn(cw_bat->dev, "No monitored battery, some properties will be missing\n"); } @@ -724,7 +730,7 @@ static int cw_bat_remove(struct i2c_client *client) struct cw_battery *cw_bat = i2c_get_clientdata(client); cancel_delayed_work_sync(&cw_bat->battery_delay_work); - power_supply_put_battery_info(cw_bat->rk_bat, &cw_bat->battery); + power_supply_put_battery_info(cw_bat->rk_bat, cw_bat->battery); return 0; } diff --git a/drivers/power/supply/ingenic-battery.c b/drivers/power/supply/ingenic-battery.c index 8b18219ebe90..2e7fdfde47ec 100644 --- a/drivers/power/supply/ingenic-battery.c +++ b/drivers/power/supply/ingenic-battery.c @@ -18,7 +18,7 @@ struct ingenic_battery { struct iio_channel *channel; struct power_supply_desc desc; struct power_supply *battery; - struct power_supply_battery_info info; + struct power_supply_battery_info *info; }; static int ingenic_battery_get_property(struct power_supply *psy, @@ -26,7 +26,7 @@ static int ingenic_battery_get_property(struct power_supply *psy, union power_supply_propval *val) { struct ingenic_battery *bat = power_supply_get_drvdata(psy); - struct power_supply_battery_info *info = &bat->info; + struct power_supply_battery_info *info = bat->info; int ret; switch (psp) { @@ -80,7 +80,7 @@ static int ingenic_battery_set_scale(struct ingenic_battery *bat) if (ret != IIO_AVAIL_LIST || scale_type != IIO_VAL_FRACTIONAL_LOG2) return -EINVAL; - max_mV = bat->info.voltage_max_design_uv / 1000; + max_mV = bat->info->voltage_max_design_uv / 1000; for (i = 0; i < scale_len; i += 2) { u64 scale_mV = (max_raw * scale_raw[i]) >> scale_raw[i + 1]; @@ -156,13 +156,13 @@ static int ingenic_battery_probe(struct platform_device *pdev) dev_err(dev, "Unable to get battery info: %d\n", ret); return ret; } - if (bat->info.voltage_min_design_uv < 0) { + if (bat->info->voltage_min_design_uv < 0) { dev_err(dev, "Unable to get voltage min design\n"); - return bat->info.voltage_min_design_uv; + return bat->info->voltage_min_design_uv; } - if (bat->info.voltage_max_design_uv < 0) { + if (bat->info->voltage_max_design_uv < 0) { dev_err(dev, "Unable to get voltage max design\n"); - return bat->info.voltage_max_design_uv; + return bat->info->voltage_max_design_uv; } return ingenic_battery_set_scale(bat); diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index 2907b84ceea9..fffb87dca5a0 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -564,14 +564,19 @@ EXPORT_SYMBOL_GPL(devm_power_supply_get_by_phandle); #endif /* CONFIG_OF */ int power_supply_get_battery_info(struct power_supply *psy, - struct power_supply_battery_info *info) + struct power_supply_battery_info **info_out) { struct power_supply_resistance_temp_table *resist_table; + struct power_supply_battery_info *info; struct device_node *battery_np; const char *value; int err, len, index; const __be32 *list; + info = devm_kmalloc(&psy->dev, sizeof(*info), GFP_KERNEL); + if (!info) + return -ENOMEM; + info->technology = POWER_SUPPLY_TECHNOLOGY_UNKNOWN; info->energy_full_design_uwh = -EINVAL; info->charge_full_design_uah = -EINVAL; @@ -581,6 +586,10 @@ int power_supply_get_battery_info(struct power_supply *psy, info->charge_term_current_ua = -EINVAL; info->constant_charge_current_max_ua = -EINVAL; info->constant_charge_voltage_max_uv = -EINVAL; + info->tricklecharge_current_ua = -EINVAL; + info->precharge_voltage_max_uv = -EINVAL; + info->charge_restart_voltage_uv = -EINVAL; + info->overvoltage_limit_uv = -EINVAL; info->temp_ambient_alert_min = INT_MIN; info->temp_ambient_alert_max = INT_MAX; info->temp_alert_min = INT_MIN; @@ -728,7 +737,7 @@ int power_supply_get_battery_info(struct power_supply *psy, list = of_get_property(battery_np, "resistance-temp-table", &len); if (!list || !len) - goto out_put_node; + goto out_ret_pointer; info->resist_table_size = len / (2 * sizeof(__be32)); resist_table = info->resist_table = devm_kcalloc(&psy->dev, @@ -746,6 +755,10 @@ int power_supply_get_battery_info(struct power_supply *psy, resist_table[index].resistance = be32_to_cpu(*list++); } +out_ret_pointer: + /* Finally return the whole thing */ + *info_out = info; + out_put_node: of_node_put(battery_np); return err; @@ -764,6 +777,8 @@ void power_supply_put_battery_info(struct power_supply *psy, if (info->resist_table) devm_kfree(&psy->dev, info->resist_table); + + devm_kfree(&psy->dev, info); } EXPORT_SYMBOL_GPL(power_supply_put_battery_info); diff --git a/drivers/power/supply/sc2731_charger.c b/drivers/power/supply/sc2731_charger.c index 288b79836c13..9ac17cf7a126 100644 --- a/drivers/power/supply/sc2731_charger.c +++ b/drivers/power/supply/sc2731_charger.c @@ -368,7 +368,7 @@ static int sc2731_charger_usb_change(struct notifier_block *nb, static int sc2731_charger_hw_init(struct sc2731_charger_info *info) { - struct power_supply_battery_info bat_info = { }; + struct power_supply_battery_info *bat_info; u32 term_currrent, term_voltage, cur_val, vol_val; int ret; @@ -390,7 +390,7 @@ static int sc2731_charger_hw_init(struct sc2731_charger_info *info) cur_val = 0x2; vol_val = 0x1; } else { - term_currrent = bat_info.charge_term_current_ua / 1000; + term_currrent = bat_info->charge_term_current_ua / 1000; if (term_currrent <= 90) cur_val = 0; @@ -399,7 +399,7 @@ static int sc2731_charger_hw_init(struct sc2731_charger_info *info) else cur_val = ((term_currrent - 90) / 25) + 1; - term_voltage = bat_info.constant_charge_voltage_max_uv / 1000; + term_voltage = bat_info->constant_charge_voltage_max_uv / 1000; if (term_voltage > 4500) term_voltage = 4500; @@ -409,7 +409,7 @@ static int sc2731_charger_hw_init(struct sc2731_charger_info *info) else vol_val = 0; - power_supply_put_battery_info(info->psy_usb, &bat_info); + power_supply_put_battery_info(info->psy_usb, bat_info); } /* Set charge termination current */ diff --git a/drivers/power/supply/sc27xx_fuel_gauge.c b/drivers/power/supply/sc27xx_fuel_gauge.c index ae45069bd5e1..632977f84b95 100644 --- a/drivers/power/supply/sc27xx_fuel_gauge.c +++ b/drivers/power/supply/sc27xx_fuel_gauge.c @@ -998,7 +998,7 @@ static int sc27xx_fgu_calibration(struct sc27xx_fgu_data *data) static int sc27xx_fgu_hw_init(struct sc27xx_fgu_data *data) { - struct power_supply_battery_info info = { }; + struct power_supply_battery_info *info; struct power_supply_battery_ocv_table *table; int ret, delta_clbcnt, alarm_adc; @@ -1008,16 +1008,16 @@ static int sc27xx_fgu_hw_init(struct sc27xx_fgu_data *data) return ret; } - data->total_cap = info.charge_full_design_uah / 1000; - data->max_volt = info.constant_charge_voltage_max_uv / 1000; - data->internal_resist = info.factory_internal_resistance_uohm / 1000; - data->min_volt = info.voltage_min_design_uv; + data->total_cap = info->charge_full_design_uah / 1000; + data->max_volt = info->constant_charge_voltage_max_uv / 1000; + data->internal_resist = info->factory_internal_resistance_uohm / 1000; + data->min_volt = info->voltage_min_design_uv; /* * For SC27XX fuel gauge device, we only use one ocv-capacity * table in normal temperature 20 Celsius. */ - table = power_supply_find_ocv2cap_table(&info, 20, &data->table_len); + table = power_supply_find_ocv2cap_table(info, 20, &data->table_len); if (!table) return -EINVAL; @@ -1025,7 +1025,7 @@ static int sc27xx_fgu_hw_init(struct sc27xx_fgu_data *data) data->table_len * sizeof(*table), GFP_KERNEL); if (!data->cap_table) { - power_supply_put_battery_info(data->battery, &info); + power_supply_put_battery_info(data->battery, info); return -ENOMEM; } @@ -1035,19 +1035,19 @@ static int sc27xx_fgu_hw_init(struct sc27xx_fgu_data *data) if (!data->alarm_cap) data->alarm_cap += 1; - data->resist_table_len = info.resist_table_size; + data->resist_table_len = info->resist_table_size; if (data->resist_table_len > 0) { - data->resist_table = devm_kmemdup(data->dev, info.resist_table, + data->resist_table = devm_kmemdup(data->dev, info->resist_table, data->resist_table_len * sizeof(struct power_supply_resistance_temp_table), GFP_KERNEL); if (!data->resist_table) { - power_supply_put_battery_info(data->battery, &info); + power_supply_put_battery_info(data->battery, info); return -ENOMEM; } } - power_supply_put_battery_info(data->battery, &info); + power_supply_put_battery_info(data->battery, info); ret = sc27xx_fgu_calibration(data); if (ret) diff --git a/drivers/power/supply/smb347-charger.c b/drivers/power/supply/smb347-charger.c index 753944e774c4..d56e469043bb 100644 --- a/drivers/power/supply/smb347-charger.c +++ b/drivers/power/supply/smb347-charger.c @@ -1281,7 +1281,7 @@ static void smb347_dt_parse_dev_info(struct smb347_charger *smb) static int smb347_get_battery_info(struct smb347_charger *smb) { - struct power_supply_battery_info info = {}; + struct power_supply_battery_info *info; struct power_supply *supply; int err; @@ -1296,29 +1296,29 @@ static int smb347_get_battery_info(struct smb347_charger *smb) if (err) return err; - if (info.constant_charge_current_max_ua != -EINVAL) - smb->max_charge_current = info.constant_charge_current_max_ua; + if (info->constant_charge_current_max_ua != -EINVAL) + smb->max_charge_current = info->constant_charge_current_max_ua; - if (info.constant_charge_voltage_max_uv != -EINVAL) - smb->max_charge_voltage = info.constant_charge_voltage_max_uv; + if (info->constant_charge_voltage_max_uv != -EINVAL) + smb->max_charge_voltage = info->constant_charge_voltage_max_uv; - if (info.precharge_current_ua != -EINVAL) - smb->pre_charge_current = info.precharge_current_ua; + if (info->precharge_current_ua != -EINVAL) + smb->pre_charge_current = info->precharge_current_ua; - if (info.charge_term_current_ua != -EINVAL) - smb->termination_current = info.charge_term_current_ua; + if (info->charge_term_current_ua != -EINVAL) + smb->termination_current = info->charge_term_current_ua; - if (info.temp_alert_min != INT_MIN) - smb->soft_cold_temp_limit = info.temp_alert_min; + if (info->temp_alert_min != INT_MIN) + smb->soft_cold_temp_limit = info->temp_alert_min; - if (info.temp_alert_max != INT_MAX) - smb->soft_hot_temp_limit = info.temp_alert_max; + if (info->temp_alert_max != INT_MAX) + smb->soft_hot_temp_limit = info->temp_alert_max; - if (info.temp_min != INT_MIN) - smb->hard_cold_temp_limit = info.temp_min; + if (info->temp_min != INT_MIN) + smb->hard_cold_temp_limit = info->temp_min; - if (info.temp_max != INT_MAX) - smb->hard_hot_temp_limit = info.temp_max; + if (info->temp_max != INT_MAX) + smb->hard_hot_temp_limit = info->temp_max; /* Suspend when battery temperature is outside hard limits */ if (smb->hard_cold_temp_limit != SMB3XX_TEMP_USE_DEFAULT || diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index f6e94eae4f28..86b4d5c4dab9 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -575,7 +575,7 @@ devm_power_supply_get_by_phandle(struct device *dev, const char *property) #endif /* CONFIG_OF */ extern int power_supply_get_battery_info(struct power_supply *psy, - struct power_supply_battery_info *info); + struct power_supply_battery_info **info_out); extern void power_supply_put_battery_info(struct power_supply *psy, struct power_supply_battery_info *info); extern int power_supply_ocv2cap_simple(struct power_supply_battery_ocv_table *table, -- cgit v1.2.3 From d5dbcca70182501bed99de85c224cef04c38ed92 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Mon, 3 Jan 2022 17:24:08 +0100 Subject: pktcdvd: convert to use attribute groups There is no need to create kobject children of the pktcdvd device just to display a subdirectory name. Instead, use a named attribute group which removes the extra kobjects and also fixes the userspace race where the device is created yet tools like libudev can not see the attributes as they think the subdirectories are some other sort of device. Cc: linux-block@vger.kernel.org Cc: Jens Axboe Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20220103162408.742003-1-gregkh@linuxfoundation.org Signed-off-by: Jens Axboe --- drivers/block/pktcdvd.c | 275 +++++++++++++++++++++++------------------------- include/linux/pktcdvd.h | 10 -- 2 files changed, 134 insertions(+), 151 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 713b7dcf39f9..2b6b70a39e76 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -113,57 +113,10 @@ static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd) return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1); } -/* - * create and register a pktcdvd kernel object. - */ -static struct pktcdvd_kobj* pkt_kobj_create(struct pktcdvd_device *pd, - const char* name, - struct kobject* parent, - struct kobj_type* ktype) -{ - struct pktcdvd_kobj *p; - int error; - - p = kzalloc(sizeof(*p), GFP_KERNEL); - if (!p) - return NULL; - p->pd = pd; - error = kobject_init_and_add(&p->kobj, ktype, parent, "%s", name); - if (error) { - kobject_put(&p->kobj); - return NULL; - } - kobject_uevent(&p->kobj, KOBJ_ADD); - return p; -} -/* - * remove a pktcdvd kernel object. - */ -static void pkt_kobj_remove(struct pktcdvd_kobj *p) -{ - if (p) - kobject_put(&p->kobj); -} -/* - * default release function for pktcdvd kernel objects. - */ -static void pkt_kobj_release(struct kobject *kobj) -{ - kfree(to_pktcdvdkobj(kobj)); -} - - /********************************************************** - * * sysfs interface for pktcdvd * by (C) 2006 Thomas Maier - * - **********************************************************/ - -#define DEF_ATTR(_obj,_name,_mode) \ - static struct attribute _obj = { .name = _name, .mode = _mode } - -/********************************************************** + /sys/class/pktcdvd/pktcdvd[0-7]/ stat/reset stat/packets_started @@ -176,75 +129,94 @@ static void pkt_kobj_release(struct kobject *kobj) write_queue/congestion_on **********************************************************/ -DEF_ATTR(kobj_pkt_attr_st1, "reset", 0200); -DEF_ATTR(kobj_pkt_attr_st2, "packets_started", 0444); -DEF_ATTR(kobj_pkt_attr_st3, "packets_finished", 0444); -DEF_ATTR(kobj_pkt_attr_st4, "kb_written", 0444); -DEF_ATTR(kobj_pkt_attr_st5, "kb_read", 0444); -DEF_ATTR(kobj_pkt_attr_st6, "kb_read_gather", 0444); - -static struct attribute *kobj_pkt_attrs_stat[] = { - &kobj_pkt_attr_st1, - &kobj_pkt_attr_st2, - &kobj_pkt_attr_st3, - &kobj_pkt_attr_st4, - &kobj_pkt_attr_st5, - &kobj_pkt_attr_st6, - NULL -}; +static ssize_t packets_started_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); -DEF_ATTR(kobj_pkt_attr_wq1, "size", 0444); -DEF_ATTR(kobj_pkt_attr_wq2, "congestion_off", 0644); -DEF_ATTR(kobj_pkt_attr_wq3, "congestion_on", 0644); + return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started); +} +static DEVICE_ATTR_RO(packets_started); -static struct attribute *kobj_pkt_attrs_wqueue[] = { - &kobj_pkt_attr_wq1, - &kobj_pkt_attr_wq2, - &kobj_pkt_attr_wq3, - NULL -}; +static ssize_t packets_finished_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); -static ssize_t kobj_pkt_show(struct kobject *kobj, - struct attribute *attr, char *data) + return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended); +} +static DEVICE_ATTR_RO(packets_finished); + +static ssize_t kb_written_show(struct device *dev, + struct device_attribute *attr, char *buf) { - struct pktcdvd_device *pd = to_pktcdvdkobj(kobj)->pd; - int n = 0; - int v; - if (strcmp(attr->name, "packets_started") == 0) { - n = sprintf(data, "%lu\n", pd->stats.pkt_started); + struct pktcdvd_device *pd = dev_get_drvdata(dev); - } else if (strcmp(attr->name, "packets_finished") == 0) { - n = sprintf(data, "%lu\n", pd->stats.pkt_ended); + return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1); +} +static DEVICE_ATTR_RO(kb_written); - } else if (strcmp(attr->name, "kb_written") == 0) { - n = sprintf(data, "%lu\n", pd->stats.secs_w >> 1); +static ssize_t kb_read_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); - } else if (strcmp(attr->name, "kb_read") == 0) { - n = sprintf(data, "%lu\n", pd->stats.secs_r >> 1); + return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1); +} +static DEVICE_ATTR_RO(kb_read); - } else if (strcmp(attr->name, "kb_read_gather") == 0) { - n = sprintf(data, "%lu\n", pd->stats.secs_rg >> 1); +static ssize_t kb_read_gather_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); - } else if (strcmp(attr->name, "size") == 0) { - spin_lock(&pd->lock); - v = pd->bio_queue_size; - spin_unlock(&pd->lock); - n = sprintf(data, "%d\n", v); + return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1); +} +static DEVICE_ATTR_RO(kb_read_gather); - } else if (strcmp(attr->name, "congestion_off") == 0) { - spin_lock(&pd->lock); - v = pd->write_congestion_off; - spin_unlock(&pd->lock); - n = sprintf(data, "%d\n", v); +static ssize_t reset_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); - } else if (strcmp(attr->name, "congestion_on") == 0) { - spin_lock(&pd->lock); - v = pd->write_congestion_on; - spin_unlock(&pd->lock); - n = sprintf(data, "%d\n", v); + if (len > 0) { + pd->stats.pkt_started = 0; + pd->stats.pkt_ended = 0; + pd->stats.secs_w = 0; + pd->stats.secs_rg = 0; + pd->stats.secs_r = 0; } + return len; +} +static DEVICE_ATTR_WO(reset); + +static struct attribute *pkt_stat_attrs[] = { + &dev_attr_packets_finished.attr, + &dev_attr_packets_started.attr, + &dev_attr_kb_read.attr, + &dev_attr_kb_written.attr, + &dev_attr_kb_read_gather.attr, + &dev_attr_reset.attr, + NULL, +}; + +static const struct attribute_group pkt_stat_group = { + .name = "stat", + .attrs = pkt_stat_attrs, +}; + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int n; + + spin_lock(&pd->lock); + n = sysfs_emit(buf, "%d\n", pd->bio_queue_size); + spin_unlock(&pd->lock); return n; } +static DEVICE_ATTR_RO(size); static void init_write_congestion_marks(int* lo, int* hi) { @@ -263,30 +235,56 @@ static void init_write_congestion_marks(int* lo, int* hi) } } -static ssize_t kobj_pkt_store(struct kobject *kobj, - struct attribute *attr, - const char *data, size_t len) +static ssize_t congestion_off_show(struct device *dev, + struct device_attribute *attr, char *buf) { - struct pktcdvd_device *pd = to_pktcdvdkobj(kobj)->pd; - int val; + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int n; - if (strcmp(attr->name, "reset") == 0 && len > 0) { - pd->stats.pkt_started = 0; - pd->stats.pkt_ended = 0; - pd->stats.secs_w = 0; - pd->stats.secs_rg = 0; - pd->stats.secs_r = 0; + spin_lock(&pd->lock); + n = sysfs_emit(buf, "%d\n", pd->write_congestion_off); + spin_unlock(&pd->lock); + return n; +} + +static ssize_t congestion_off_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int val; - } else if (strcmp(attr->name, "congestion_off") == 0 - && sscanf(data, "%d", &val) == 1) { + if (sscanf(buf, "%d", &val) == 1) { spin_lock(&pd->lock); pd->write_congestion_off = val; init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on); spin_unlock(&pd->lock); + } + return len; +} +static DEVICE_ATTR_RW(congestion_off); + +static ssize_t congestion_on_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int n; - } else if (strcmp(attr->name, "congestion_on") == 0 - && sscanf(data, "%d", &val) == 1) { + spin_lock(&pd->lock); + n = sysfs_emit(buf, "%d\n", pd->write_congestion_on); + spin_unlock(&pd->lock); + return n; +} + +static ssize_t congestion_on_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pktcdvd_device *pd = dev_get_drvdata(dev); + int val; + + if (sscanf(buf, "%d", &val) == 1) { spin_lock(&pd->lock); pd->write_congestion_on = val; init_write_congestion_marks(&pd->write_congestion_off, @@ -295,44 +293,39 @@ static ssize_t kobj_pkt_store(struct kobject *kobj, } return len; } +static DEVICE_ATTR_RW(congestion_on); -static const struct sysfs_ops kobj_pkt_ops = { - .show = kobj_pkt_show, - .store = kobj_pkt_store +static struct attribute *pkt_wq_attrs[] = { + &dev_attr_congestion_on.attr, + &dev_attr_congestion_off.attr, + &dev_attr_size.attr, + NULL, }; -static struct kobj_type kobj_pkt_type_stat = { - .release = pkt_kobj_release, - .sysfs_ops = &kobj_pkt_ops, - .default_attrs = kobj_pkt_attrs_stat + +static const struct attribute_group pkt_wq_group = { + .name = "write_queue", + .attrs = pkt_wq_attrs, }; -static struct kobj_type kobj_pkt_type_wqueue = { - .release = pkt_kobj_release, - .sysfs_ops = &kobj_pkt_ops, - .default_attrs = kobj_pkt_attrs_wqueue + +static const struct attribute_group *pkt_groups[] = { + &pkt_stat_group, + &pkt_wq_group, + NULL, }; static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) { if (class_pktcdvd) { - pd->dev = device_create(class_pktcdvd, NULL, MKDEV(0, 0), NULL, - "%s", pd->name); + pd->dev = device_create_with_groups(class_pktcdvd, NULL, + MKDEV(0, 0), pd, pkt_groups, + "%s", pd->name); if (IS_ERR(pd->dev)) pd->dev = NULL; } - if (pd->dev) { - pd->kobj_stat = pkt_kobj_create(pd, "stat", - &pd->dev->kobj, - &kobj_pkt_type_stat); - pd->kobj_wqueue = pkt_kobj_create(pd, "write_queue", - &pd->dev->kobj, - &kobj_pkt_type_wqueue); - } } static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd) { - pkt_kobj_remove(pd->kobj_stat); - pkt_kobj_remove(pd->kobj_wqueue); if (class_pktcdvd) device_unregister(pd->dev); } diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h index c391e694aa26..f9c5ac80d59b 100644 --- a/include/linux/pktcdvd.h +++ b/include/linux/pktcdvd.h @@ -152,14 +152,6 @@ struct packet_stacked_data }; #define PSD_POOL_SIZE 64 -struct pktcdvd_kobj -{ - struct kobject kobj; - struct pktcdvd_device *pd; -}; -#define to_pktcdvdkobj(_k) \ - ((struct pktcdvd_kobj*)container_of(_k,struct pktcdvd_kobj,kobj)) - struct pktcdvd_device { struct block_device *bdev; /* dev attached */ @@ -197,8 +189,6 @@ struct pktcdvd_device int write_congestion_on; struct device *dev; /* sysfs pktcdvd[0-7] dev */ - struct pktcdvd_kobj *kobj_stat; /* sysfs pktcdvd[0-7]/stat/ */ - struct pktcdvd_kobj *kobj_wqueue; /* sysfs pktcdvd[0-7]/write_queue/ */ struct dentry *dfs_d_root; /* debugfs: devname directory */ struct dentry *dfs_f_info; /* debugfs: info file */ -- cgit v1.2.3 From 6c952a0dc9c3ced98c4c8aa7cd11c25c59157f1f Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:20:26 +0100 Subject: ata: libata: Add ata_port_classify() helper Add an ata_port_classify() helper to print out the results from the device classification and remove the debugging statements from ata_dev_classify(). Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libahci.c | 2 +- drivers/ata/libata-core.c | 21 +++++---------------- drivers/ata/libata-sff.c | 2 +- drivers/ata/libata-transport.c | 30 ++++++++++++++++++++++++++++++ drivers/ata/sata_fsl.c | 2 +- drivers/ata/sata_inic162x.c | 2 +- drivers/ata/sata_sil24.c | 2 +- include/linux/libata.h | 2 ++ 8 files changed, 42 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c index 94edbc89a48c..b7b460560a92 100644 --- a/drivers/ata/libahci.c +++ b/drivers/ata/libahci.c @@ -1300,7 +1300,7 @@ unsigned int ahci_dev_classify(struct ata_port *ap) tf.lbal = (tmp >> 8) & 0xff; tf.nsect = (tmp) & 0xff; - return ata_dev_classify(&tf); + return ata_port_classify(ap, &tf); } EXPORT_SYMBOL_GPL(ahci_dev_classify); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 72f56c32fe83..28645ac04d9f 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1007,32 +1007,21 @@ unsigned int ata_dev_classify(const struct ata_taskfile *tf) * SEMB signature. This is worked around in * ata_dev_read_id(). */ - if ((tf->lbam == 0) && (tf->lbah == 0)) { - DPRINTK("found ATA device by sig\n"); + if (tf->lbam == 0 && tf->lbah == 0) return ATA_DEV_ATA; - } - if ((tf->lbam == 0x14) && (tf->lbah == 0xeb)) { - DPRINTK("found ATAPI device by sig\n"); + if (tf->lbam == 0x14 && tf->lbah == 0xeb) return ATA_DEV_ATAPI; - } - if ((tf->lbam == 0x69) && (tf->lbah == 0x96)) { - DPRINTK("found PMP device by sig\n"); + if (tf->lbam == 0x69 && tf->lbah == 0x96) return ATA_DEV_PMP; - } - if ((tf->lbam == 0x3c) && (tf->lbah == 0xc3)) { - DPRINTK("found SEMB device by sig (could be ATA device)\n"); + if (tf->lbam == 0x3c && tf->lbah == 0xc3) return ATA_DEV_SEMB; - } - if ((tf->lbam == 0xcd) && (tf->lbah == 0xab)) { - DPRINTK("found ZAC device by sig\n"); + if (tf->lbam == 0xcd && tf->lbah == 0xab) return ATA_DEV_ZAC; - } - DPRINTK("unknown device\n"); return ATA_DEV_UNKNOWN; } EXPORT_SYMBOL_GPL(ata_dev_classify); diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 39c026f3948c..a119fabe0919 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -1853,7 +1853,7 @@ unsigned int ata_sff_dev_classify(struct ata_device *dev, int present, return ATA_DEV_NONE; /* determine if device is ATA or ATAPI */ - class = ata_dev_classify(&tf); + class = ata_port_classify(ap, &tf); if (class == ATA_DEV_UNKNOWN) { /* If the device failed diagnostic, it's likely to diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c index 4162d625fc92..ca129854a88c 100644 --- a/drivers/ata/libata-transport.c +++ b/drivers/ata/libata-transport.c @@ -321,6 +321,36 @@ int ata_tport_add(struct device *parent, return error; } +/** + * ata_port_classify - determine device type based on ATA-spec signature + * @ap: ATA port device on which the classification should be run + * @tf: ATA taskfile register set for device to be identified + * + * A wrapper around ata_dev_classify() to provide additional logging + * + * RETURNS: + * Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP, + * %ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure. + */ +unsigned int ata_port_classify(struct ata_port *ap, + const struct ata_taskfile *tf) +{ + int i; + unsigned int class = ata_dev_classify(tf); + + /* Start with index '1' to skip the 'unknown' entry */ + for (i = 1; i < ARRAY_SIZE(ata_class_names); i++) { + if (ata_class_names[i].value == class) { + ata_port_dbg(ap, "found %s device by sig\n", + ata_class_names[i].name); + return class; + } + } + + ata_port_info(ap, "found unknown device (class %u)\n", class); + return class; +} +EXPORT_SYMBOL_GPL(ata_port_classify); /* * ATA link attributes diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index ec52511ae60f..7504d9fbff2a 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -814,7 +814,7 @@ static unsigned int sata_fsl_dev_classify(struct ata_port *ap) tf.lbal = (temp >> 8) & 0xff; tf.nsect = temp & 0xff; - return ata_dev_classify(&tf); + return ata_port_classify(ap, &tf); } static int sata_fsl_hardreset(struct ata_link *link, unsigned int *class, diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c index e517bd8822a5..b6239dae524a 100644 --- a/drivers/ata/sata_inic162x.c +++ b/drivers/ata/sata_inic162x.c @@ -657,7 +657,7 @@ static int inic_hardreset(struct ata_link *link, unsigned int *class, } inic_tf_read(ap, &tf); - *class = ata_dev_classify(&tf); + *class = ata_port_classify(ap, &tf); } return 0; diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index f99ec6f7d7c0..7e9c1945dc81 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -680,7 +680,7 @@ static int sil24_softreset(struct ata_link *link, unsigned int *class, } sil24_read_tf(ap, 0, &tf); - *class = ata_dev_classify(&tf); + *class = ata_port_classify(ap, &tf); DPRINTK("EXIT, class=%u\n", *class); return 0; diff --git a/include/linux/libata.h b/include/linux/libata.h index 2a8404b26083..235fdbeb19ea 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1160,6 +1160,8 @@ extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc); extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem); extern unsigned int ata_dev_classify(const struct ata_taskfile *tf); +extern unsigned int ata_port_classify(struct ata_port *ap, + const struct ata_taskfile *tf); extern void ata_dev_disable(struct ata_device *adev); extern void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); -- cgit v1.2.3 From e41294408c56c68ea0f269d757527bf33b39118a Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Mon, 3 Jan 2022 18:11:31 +0100 Subject: icmp: ICMPV6: Examine invoking packet for Segment Route Headers. RFC8754 says: ICMP error packets generated within the SR domain are sent to source nodes within the SR domain. The invoking packet in the ICMP error message may contain an SRH. Since the destination address of a packet with an SRH changes as each segment is processed, it may not be the destination used by the socket or application that generated the invoking packet. For the source of an invoking packet to process the ICMP error message, the ultimate destination address of the IPv6 header may be required. The following logic is used to determine the destination address for use by protocol-error handlers. * Walk all extension headers of the invoking IPv6 packet to the routing extension header preceding the upper-layer header. - If routing header is type 4 Segment Routing Header (SRH) o The SID at Segment List[0] may be used as the destination address of the invoking packet. Mangle the skb so the network header points to the invoking packet inside the ICMP packet. The seg6 helpers can then be used on the skb to find any segment routing headers. If found, mark this fact in the IPv6 control block of the skb, and store the offset into the packet of the SRH. Then restore the skb back to its old state. Signed-off-by: Andrew Lunn Reviewed-by: David Ahern Reviewed-by: Willem de Bruijn Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 ++ include/net/seg6.h | 1 + net/ipv6/icmp.c | 6 +++++- net/ipv6/seg6.c | 30 ++++++++++++++++++++++++++++++ 4 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 20c1f968da7c..a59d25f19385 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -133,6 +133,7 @@ struct inet6_skb_parm { __u16 dsthao; #endif __u16 frag_max_size; + __u16 srhoff; #define IP6SKB_XFRM_TRANSFORMED 1 #define IP6SKB_FORWARDED 2 @@ -142,6 +143,7 @@ struct inet6_skb_parm { #define IP6SKB_HOPBYHOP 32 #define IP6SKB_L3SLAVE 64 #define IP6SKB_JUMBOGRAM 128 +#define IP6SKB_SEG6 256 }; #if defined(CONFIG_NET_L3_MASTER_DEV) diff --git a/include/net/seg6.h b/include/net/seg6.h index a6f25983670a..02b0cd305787 100644 --- a/include/net/seg6.h +++ b/include/net/seg6.h @@ -59,6 +59,7 @@ extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags); +extern void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index a7c31ab67c5d..96c5cc0f30ce 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include #include @@ -820,6 +821,7 @@ out_bh_enable: void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) { + struct inet6_skb_parm *opt = IP6CB(skb); const struct inet6_protocol *ipprot; int inner_offset; __be16 frag_off; @@ -829,6 +831,8 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; + seg6_icmp_srh(skb, opt); + nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr; if (ipv6_ext_hdr(nexthdr)) { /* now skip over extension headers */ @@ -853,7 +857,7 @@ void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info) ipprot = rcu_dereference(inet6_protos[nexthdr]); if (ipprot && ipprot->err_handler) - ipprot->err_handler(skb, NULL, type, code, inner_offset, info); + ipprot->err_handler(skb, opt, type, code, inner_offset, info); raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info); return; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 5bc9bf892199..73aaabf0e966 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -104,6 +104,36 @@ struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) return srh; } +/* Determine if an ICMP invoking packet contains a segment routing + * header. If it does, extract the offset to the true destination + * address, which is in the first segment address. + */ +void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt) +{ + __u16 network_header = skb->network_header; + struct ipv6_sr_hdr *srh; + + /* Update network header to point to the invoking packet + * inside the ICMP packet, so we can use the seg6_get_srh() + * helper. + */ + skb_reset_network_header(skb); + + srh = seg6_get_srh(skb, 0); + if (!srh) + goto out; + + if (srh->type != IPV6_SRCRT_TYPE_4) + goto out; + + opt->flags |= IP6SKB_SEG6; + opt->srhoff = (unsigned char *)srh - skb->data; + +out: + /* Restore the network header back to the ICMP packet */ + skb->network_header = network_header; +} + static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { -- cgit v1.2.3 From f083266487690124481eac0869da850406fb3ed3 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sun, 29 Aug 2021 09:18:53 +0200 Subject: headers/uninline: Uninline single-use function: kobject_has_children() This was the only usage of in , so we'll able to decouple the two after this change. Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 17 +++++++++++++++++ include/linux/kobject.h | 17 ----------------- 2 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/core.c b/drivers/base/core.c index 60d703ebd123..603941b00988 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -3028,6 +3028,23 @@ static inline struct kobject *get_glue_dir(struct device *dev) return dev->kobj.parent; } +/** + * kobject_has_children - Returns whether a kobject has children. + * @kobj: the object to test + * + * This will return whether a kobject has other kobjects as children. + * + * It does NOT account for the presence of attribute files, only sub + * directories. It also assumes there is no concurrent addition or + * removal of such children, and thus relies on external locking. + */ +static inline bool kobject_has_children(struct kobject *kobj) +{ + WARN_ON_ONCE(kref_read(&kobj->kref) == 0); + + return kobj->sd && kobj->sd->dir.subdirs; +} + /* * make sure cleaning up dir as the last step, we need to make * sure .release handler of kobject is run with holding the diff --git a/include/linux/kobject.h b/include/linux/kobject.h index ad90b49824dc..c7b47399b36a 100644 --- a/include/linux/kobject.h +++ b/include/linux/kobject.h @@ -117,23 +117,6 @@ extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); -/** - * kobject_has_children - Returns whether a kobject has children. - * @kobj: the object to test - * - * This will return whether a kobject has other kobjects as children. - * - * It does NOT account for the presence of attribute files, only sub - * directories. It also assumes there is no concurrent addition or - * removal of such children, and thus relies on external locking. - */ -static inline bool kobject_has_children(struct kobject *kobj) -{ - WARN_ON_ONCE(kref_read(&kobj->kref) == 0); - - return kobj->sd && kobj->sd->dir.subdirs; -} - struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; -- cgit v1.2.3 From d9c19d32d86fa54934b632c4314beb067bf98378 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 18 Oct 2021 10:39:06 -0400 Subject: iov_iter: Add copy_folio_to_iter() This wrapper around copy_page_to_iter() works because copy_page_to_iter() handles compound pages correctly. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski --- include/linux/uio.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index 6350354f97e9..43321dbebba8 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -7,6 +7,7 @@ #include #include +#include #include struct page; @@ -146,6 +147,12 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); +static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset, + size_t bytes, struct iov_iter *i) +{ + return copy_page_to_iter(&folio->page, offset, bytes, i); +} + static __always_inline __must_check size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { -- cgit v1.2.3 From 5bf34d7c7ffe773c3b3c1b6ebf39e0f34a2436ec Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 28 Nov 2021 14:24:43 -0500 Subject: mm: Add folio_test_pmd_mappable() Add a predicate to determine if the folio might be mapped by a PMD entry. If CONFIG_TRANSPARENT_HUGEPAGE is disabled, we know it can't be, even if it's large enough. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/huge_mm.h | 14 ++++++++++++++ include/linux/mm.h | 42 +++++++++++++++++++++--------------------- 2 files changed, 35 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f280f33ff223..e4c18ba8d3bf 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -274,6 +274,15 @@ static inline int thp_nr_pages(struct page *page) return 1; } +/** + * folio_test_pmd_mappable - Can we map this folio with a PMD? + * @folio: The folio to test + */ +static inline bool folio_test_pmd_mappable(struct folio *folio) +{ + return folio_order(folio) >= HPAGE_PMD_ORDER; +} + struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, @@ -339,6 +348,11 @@ static inline int thp_nr_pages(struct page *page) return 1; } +static inline bool folio_test_pmd_mappable(struct folio *folio) +{ + return false; +} + static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..72ca04f16711 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -714,6 +714,27 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +static inline unsigned int compound_order(struct page *page) +{ + if (!PageHead(page)) + return 0; + return page[1].compound_order; +} + +/** + * folio_order - The allocation order of a folio. + * @folio: The folio. + * + * A folio is composed of 2^order pages. See get_order() for the definition + * of order. + * + * Return: The order of the folio. + */ +static inline unsigned int folio_order(struct folio *folio) +{ + return compound_order(&folio->page); +} + #include /* @@ -906,27 +927,6 @@ static inline void destroy_compound_page(struct page *page) compound_page_dtors[page[1].compound_dtor](page); } -static inline unsigned int compound_order(struct page *page) -{ - if (!PageHead(page)) - return 0; - return page[1].compound_order; -} - -/** - * folio_order - The allocation order of a folio. - * @folio: The folio. - * - * A folio is composed of 2^order pages. See get_order() for the definition - * of order. - * - * Return: The order of the folio. - */ -static inline unsigned int folio_order(struct folio *folio) -{ - return compound_order(&folio->page); -} - static inline bool hpage_pincount_available(struct page *page) { /* -- cgit v1.2.3 From 9f2b04a25a41b1f41b3cead4f56854a4192ec5b0 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 16 Aug 2021 23:36:31 -0400 Subject: filemap: Add folio_put_wait_locked() Convert all three callers of put_and_wait_on_page_locked() to folio_put_wait_locked(). This shrinks the kernel overall by 19 bytes. filemap_update_page() shrinks by 19 bytes while __migration_entry_wait() is unchanged. folio_put_wait_locked() is 14 bytes smaller than put_and_wait_on_page_locked(), but pmd_migration_entry_wait() grows by 14 bytes. It removes the assumption from pmd_migration_entry_wait() that pages cannot be larger than a PMD (which is true today, but may be interesting to explore in the future). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/pagemap.h | 2 +- mm/filemap.c | 27 +++++++++++++++------------ mm/migrate.c | 21 ++++++++++----------- 3 files changed, 26 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 605246452305..841f7ba62d7d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -868,7 +868,7 @@ static inline int wait_on_page_locked_killable(struct page *page) return folio_wait_locked_killable(page_folio(page)); } -int put_and_wait_on_page_locked(struct page *page, int state); +int folio_put_wait_locked(struct folio *folio, int state); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); diff --git a/mm/filemap.c b/mm/filemap.c index 39c4c46c6133..5dd3c6e39c9f 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1259,10 +1259,10 @@ enum behavior { * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like - * wait_on_page_writeback() waiting on PG_writeback. + * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, - * like put_and_wait_on_page_locked() on PG_locked. + * like folio_put_wait_locked() on PG_locked. */ }; @@ -1439,22 +1439,21 @@ int folio_wait_bit_killable(struct folio *folio, int bit_nr) EXPORT_SYMBOL(folio_wait_bit_killable); /** - * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked - * @page: The page to wait for. + * folio_put_wait_locked - Drop a reference and wait for it to be unlocked + * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * - * The caller should hold a reference on @page. They expect the page to + * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration - * (for example) by holding the reference while waiting for the page to + * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not - * dereference @page. + * dereference @folio. * - * Return: 0 if the page was unlocked or -EINTR if interrupted by a signal. + * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ -int put_and_wait_on_page_locked(struct page *page, int state) +int folio_put_wait_locked(struct folio *folio, int state) { - return folio_wait_bit_common(page_folio(page), PG_locked, state, - DROP); + return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** @@ -2447,7 +2446,11 @@ static int filemap_update_page(struct kiocb *iocb, goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); - put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE); + /* + * This is where we usually end up waiting for a + * previously submitted readahead to finish. + */ + folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); diff --git a/mm/migrate.c b/mm/migrate.c index cf25b00f03c8..311638177536 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -291,7 +291,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, { pte_t pte; swp_entry_t entry; - struct page *page; + struct folio *folio; spin_lock(ptl); pte = *ptep; @@ -302,18 +302,17 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!is_migration_entry(entry)) goto out; - page = pfn_swap_entry_to_page(entry); - page = compound_head(page); + folio = page_folio(pfn_swap_entry_to_page(entry)); /* * Once page cache replacement of page migration started, page_count - * is zero; but we must not call put_and_wait_on_page_locked() without - * a ref. Use get_page_unless_zero(), and just fault again if it fails. + * is zero; but we must not call folio_put_wait_locked() without + * a ref. Use folio_try_get(), and just fault again if it fails. */ - if (!get_page_unless_zero(page)) + if (!folio_try_get(folio)) goto out; pte_unmap_unlock(ptep, ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); + folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); return; out: pte_unmap_unlock(ptep, ptl); @@ -338,16 +337,16 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; - struct page *page; + struct folio *folio; ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; - page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd)); - if (!get_page_unless_zero(page)) + folio = page_folio(pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd))); + if (!folio_try_get(folio)) goto unlock; spin_unlock(ptl); - put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE); + folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); return; unlock: spin_unlock(ptl); -- cgit v1.2.3 From 621db4880d305bc37b343b1671e03b7eb5d61389 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 8 May 2021 20:04:05 -0400 Subject: filemap: Add filemap_unaccount_folio() Replace unaccount_page_cache_page() with filemap_unaccount_folio(). The bug handling path could be a bit more robust (eg taking into account the mapcounts of tail pages), but it's really never supposed to happen. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/pagemap.h | 5 ---- mm/filemap.c | 70 ++++++++++++++++++++++++------------------------- 2 files changed, 35 insertions(+), 40 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 841f7ba62d7d..077b6f378666 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -884,11 +884,6 @@ static inline void __set_page_dirty(struct page *page, } void folio_account_cleaned(struct folio *folio, struct address_space *mapping, struct bdi_writeback *wb); -static inline void account_page_cleaned(struct page *page, - struct address_space *mapping, struct bdi_writeback *wb) -{ - return folio_account_cleaned(page_folio(page), mapping, wb); -} void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { diff --git a/mm/filemap.c b/mm/filemap.c index 38fb26e16b85..600b8c921a67 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -145,74 +145,74 @@ static void page_cache_delete(struct address_space *mapping, mapping->nrpages -= nr; } -static void unaccount_page_cache_page(struct address_space *mapping, - struct page *page) +static void filemap_unaccount_folio(struct address_space *mapping, + struct folio *folio) { - int nr; + long nr; /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave * stale data around in the cleancache once our page is gone */ - if (PageUptodate(page) && PageMappedToDisk(page)) - cleancache_put_page(page); + if (folio_test_uptodate(folio) && folio_test_mappedtodisk(folio)) + cleancache_put_page(&folio->page); else - cleancache_invalidate_page(mapping, page); + cleancache_invalidate_page(mapping, &folio->page); - VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(page_mapped(page), page); - if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(page_mapped(page))) { + VM_BUG_ON_FOLIO(folio_mapped(folio), folio); + if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { int mapcount; pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", - current->comm, page_to_pfn(page)); - dump_page(page, "still mapped when deleted"); + current->comm, folio_pfn(folio)); + dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); - mapcount = page_mapcount(page); + mapcount = page_mapcount(&folio->page); if (mapping_exiting(mapping) && - page_count(page) >= mapcount + 2) { + folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's - * a good bet that actually the page is unmapped, + * a good bet that actually the folio is unmapped, * and we'd prefer not to leak it: if we're wrong, * some other bad page check should catch it later. */ - page_mapcount_reset(page); - page_ref_sub(page, mapcount); + page_mapcount_reset(&folio->page); + folio_ref_sub(folio, mapcount); } } - /* hugetlb pages do not participate in page cache accounting. */ - if (PageHuge(page)) + /* hugetlb folios do not participate in page cache accounting. */ + if (folio_test_hugetlb(folio)) return; - nr = thp_nr_pages(page); + nr = folio_nr_pages(folio); - __mod_lruvec_page_state(page, NR_FILE_PAGES, -nr); - if (PageSwapBacked(page)) { - __mod_lruvec_page_state(page, NR_SHMEM, -nr); - if (PageTransHuge(page)) - __mod_lruvec_page_state(page, NR_SHMEM_THPS, -nr); - } else if (PageTransHuge(page)) { - __mod_lruvec_page_state(page, NR_FILE_THPS, -nr); + __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); + if (folio_test_swapbacked(folio)) { + __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); + if (folio_test_pmd_mappable(folio)) + __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); + } else if (folio_test_pmd_mappable(folio)) { + __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* - * At this point page must be either written or cleaned by - * truncate. Dirty page here signals a bug and loss of + * At this point folio must be either written or cleaned by + * truncate. Dirty folio here signals a bug and loss of * unwritten data. * - * This fixes dirty accounting after removing the page entirely - * but leaves PageDirty set: it has no effect for truncated - * page and anyway will be cleared before returning page into + * This fixes dirty accounting after removing the folio entirely + * but leaves the dirty flag set: it has no effect for truncated + * folio and anyway will be cleared before returning folio to * buddy allocator. */ - if (WARN_ON_ONCE(PageDirty(page))) - account_page_cleaned(page, mapping, inode_to_wb(mapping->host)); + if (WARN_ON_ONCE(folio_test_dirty(folio))) + folio_account_cleaned(folio, mapping, + inode_to_wb(mapping->host)); } /* @@ -227,7 +227,7 @@ void __delete_from_page_cache(struct page *page, void *shadow) trace_mm_filemap_delete_from_page_cache(page); - unaccount_page_cache_page(mapping, page); + filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } @@ -348,7 +348,7 @@ void delete_from_page_cache_batch(struct address_space *mapping, for (i = 0; i < pagevec_count(pvec); i++) { trace_mm_filemap_delete_from_page_cache(pvec->pages[i]); - unaccount_page_cache_page(mapping, pvec->pages[i]); + filemap_unaccount_folio(mapping, page_folio(pvec->pages[i])); } page_cache_delete_batch(mapping, pvec); xa_unlock_irq(&mapping->i_pages); -- cgit v1.2.3 From 452e9e6992fe058a650c81d01a9982e3faf10278 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 9 May 2021 09:33:42 -0400 Subject: filemap: Add filemap_remove_folio and __filemap_remove_folio Reimplement __delete_from_page_cache() as a wrapper around __filemap_remove_folio() and delete_from_page_cache() as a wrapper around filemap_remove_folio(). Remove the EXPORT_SYMBOL as delete_from_page_cache() was not used by any in-tree modules. Convert page_cache_free_page() into filemap_free_folio(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/pagemap.h | 9 +++++++-- mm/filemap.c | 43 ++++++++++++++++++++----------------------- mm/folio-compat.c | 5 +++++ 3 files changed, 32 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 077b6f378666..3f26b191ede3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -930,8 +930,13 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); -extern void delete_from_page_cache(struct page *page); -extern void __delete_from_page_cache(struct page *page, void *shadow); +void filemap_remove_folio(struct folio *folio); +void delete_from_page_cache(struct page *page); +void __filemap_remove_folio(struct folio *folio, void *shadow); +static inline void __delete_from_page_cache(struct page *page, void *shadow) +{ + __filemap_remove_folio(page_folio(page), shadow); +} void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); diff --git a/mm/filemap.c b/mm/filemap.c index bcdc8bb4d2c8..4fe845b30f33 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -220,58 +220,55 @@ static void filemap_unaccount_folio(struct address_space *mapping, * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ -void __delete_from_page_cache(struct page *page, void *shadow) +void __filemap_remove_folio(struct folio *folio, void *shadow) { - struct folio *folio = page_folio(page); - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); - filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } -static void page_cache_free_page(struct address_space *mapping, - struct page *page) +static void filemap_free_folio(struct address_space *mapping, + struct folio *folio) { void (*freepage)(struct page *); freepage = mapping->a_ops->freepage; if (freepage) - freepage(page); + freepage(&folio->page); - if (PageTransHuge(page) && !PageHuge(page)) { - page_ref_sub(page, thp_nr_pages(page)); - VM_BUG_ON_PAGE(page_count(page) <= 0, page); + if (folio_test_large(folio) && !folio_test_hugetlb(folio)) { + folio_ref_sub(folio, folio_nr_pages(folio)); + VM_BUG_ON_FOLIO(folio_ref_count(folio) <= 0, folio); } else { - put_page(page); + folio_put(folio); } } /** - * delete_from_page_cache - delete page from page cache - * @page: the page which the kernel is trying to remove from page cache + * filemap_remove_folio - Remove folio from page cache. + * @folio: The folio. * - * This must be called only on pages that have been verified to be in the page - * cache and locked. It will never put the page into the free list, the caller - * has a reference on the page. + * This must be called only on folios that are locked and have been + * verified to be in the page cache. It will never put the folio into + * the free list because the caller has a reference on the page. */ -void delete_from_page_cache(struct page *page) +void filemap_remove_folio(struct folio *folio) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping = folio->mapping; - BUG_ON(!PageLocked(page)); + BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); - __delete_from_page_cache(page, NULL); + __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); - page_cache_free_page(mapping, page); + filemap_free_folio(mapping, folio); } -EXPORT_SYMBOL(delete_from_page_cache); /* * page_cache_delete_batch - delete several pages from page cache @@ -358,7 +355,7 @@ void delete_from_page_cache_batch(struct address_space *mapping, spin_unlock(&mapping->host->i_lock); for (i = 0; i < pagevec_count(pvec); i++) - page_cache_free_page(mapping, pvec->pages[i]); + filemap_free_folio(mapping, page_folio(pvec->pages[i])); } int filemap_check_errors(struct address_space *mapping) diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 5b6ae1da314e..749a695b4217 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -140,3 +140,8 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(grab_cache_page_write_begin); + +void delete_from_page_cache(struct page *page) +{ + return filemap_remove_folio(page_folio(page)); +} -- cgit v1.2.3 From bb2e98b613a3c76c904dfa82eb4b86773817598b Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 28 Nov 2021 16:14:50 -0500 Subject: filemap: Remove thp_contains() This function is now unused, so delete it. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/pagemap.h | 9 --------- 1 file changed, 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 3f26b191ede3..8c2cad7f0c36 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -512,15 +512,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, mapping_gfp_mask(mapping)); } -/* Does this page contain this index? */ -static inline bool thp_contains(struct page *head, pgoff_t index) -{ - /* HugeTLBfs indexes the page cache in units of hpage_size */ - if (PageHuge(head)) - return head->index == index; - return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL)); -} - #define swapcache_index(folio) __page_file_index(&(folio)->page) /** -- cgit v1.2.3 From 7836d9990079ed611199819ccf487061b748193a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 27 May 2021 12:30:54 -0400 Subject: readahead: Convert page_cache_async_ra() to take a folio Using the folio here avoids checking whether it's a tail page. This patch mostly just enables some of the following patches. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/pagemap.h | 4 ++-- mm/readahead.c | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 8c2cad7f0c36..30302be6977f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -993,7 +993,7 @@ struct readahead_control { void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); -void page_cache_async_ra(struct readahead_control *, struct page *, +void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); @@ -1040,7 +1040,7 @@ void page_cache_async_readahead(struct address_space *mapping, struct page *page, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); - page_cache_async_ra(&ractl, page, req_count); + page_cache_async_ra(&ractl, page_folio(page), req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) diff --git a/mm/readahead.c b/mm/readahead.c index 6ae5693de28c..e48e78641772 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -581,7 +581,7 @@ void page_cache_sync_ra(struct readahead_control *ractl, EXPORT_SYMBOL_GPL(page_cache_sync_ra); void page_cache_async_ra(struct readahead_control *ractl, - struct page *page, unsigned long req_count) + struct folio *folio, unsigned long req_count) { /* no read-ahead */ if (!ractl->ra->ra_pages) @@ -590,10 +590,10 @@ void page_cache_async_ra(struct readahead_control *ractl, /* * Same bit is used for PG_readahead and PG_reclaim. */ - if (PageWriteback(page)) + if (folio_test_writeback(folio)) return; - ClearPageReadahead(page); + folio_clear_readahead(folio); /* * Defer asynchronous read-ahead on IO congestion. -- cgit v1.2.3 From 539a3322f208db478db88c4a76239476defce6b1 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 16 Dec 2020 11:45:30 -0500 Subject: filemap: Add read_cache_folio and read_mapping_folio Reimplement read_cache_page() as a wrapper around read_cache_folio(). Saves over 400 bytes of text from do_read_cache_folio() which more than makes up for the extra 100 bytes of text added to the various wrapper functions. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski --- include/linux/pagemap.h | 12 +++++- mm/filemap.c | 97 ++++++++++++++++++++++++++----------------------- 2 files changed, 61 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 30302be6977f..7bef50ea5435 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -629,8 +629,10 @@ static inline struct page *grab_cache_page(struct address_space *mapping, return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } -extern struct page * read_cache_page(struct address_space *mapping, - pgoff_t index, filler_t *filler, void *data); +struct folio *read_cache_folio(struct address_space *, pgoff_t index, + filler_t *filler, void *data); +struct page *read_cache_page(struct address_space *, pgoff_t index, + filler_t *filler, void *data); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, @@ -642,6 +644,12 @@ static inline struct page *read_mapping_page(struct address_space *mapping, return read_cache_page(mapping, index, NULL, data); } +static inline struct folio *read_mapping_folio(struct address_space *mapping, + pgoff_t index, void *data) +{ + return read_cache_folio(mapping, index, NULL, data); +} + /* * Get index of the page within radix-tree (but not for hugetlb pages). * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE) diff --git a/mm/filemap.c b/mm/filemap.c index fc0f1d9904d2..f98e084ffb31 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3418,35 +3418,20 @@ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); -static struct page *wait_on_page_read(struct page *page) +static struct folio *do_read_cache_folio(struct address_space *mapping, + pgoff_t index, filler_t filler, void *data, gfp_t gfp) { - if (!IS_ERR(page)) { - wait_on_page_locked(page); - if (!PageUptodate(page)) { - put_page(page); - page = ERR_PTR(-EIO); - } - } - return page; -} - -static struct page *do_read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data, - gfp_t gfp) -{ - struct page *page; + struct folio *folio; int err; repeat: - page = find_get_page(mapping, index); - if (!page) { - page = __page_cache_alloc(gfp); - if (!page) + folio = filemap_get_folio(mapping, index); + if (!folio) { + folio = filemap_alloc_folio(gfp, 0); + if (!folio) return ERR_PTR(-ENOMEM); - err = add_to_page_cache_lru(page, mapping, index, gfp); + err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { - put_page(page); + folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ @@ -3455,21 +3440,24 @@ repeat: filler: if (filler) - err = filler(data, page); + err = filler(data, &folio->page); else - err = mapping->a_ops->readpage(data, page); + err = mapping->a_ops->readpage(data, &folio->page); if (err < 0) { - put_page(page); + folio_put(folio); return ERR_PTR(err); } - page = wait_on_page_read(page); - if (IS_ERR(page)) - return page; + folio_wait_locked(folio); + if (!folio_test_uptodate(folio)) { + folio_put(folio); + return ERR_PTR(-EIO); + } + goto out; } - if (PageUptodate(page)) + if (folio_test_uptodate(folio)) goto out; /* @@ -3503,23 +3491,23 @@ filler: * avoid spurious serialisations and wakeups when multiple processes * wait on the same page for IO to complete. */ - wait_on_page_locked(page); - if (PageUptodate(page)) + folio_wait_locked(folio); + if (folio_test_uptodate(folio)) goto out; /* Distinguish between all the cases under the safety of the lock */ - lock_page(page); + folio_lock(folio); /* Case c or d, restart the operation */ - if (!page->mapping) { - unlock_page(page); - put_page(page); + if (!folio->mapping) { + folio_unlock(folio); + folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ - if (PageUptodate(page)) { - unlock_page(page); + if (folio_test_uptodate(folio)) { + folio_unlock(folio); goto out; } @@ -3529,16 +3517,16 @@ filler: * Clear page error before actual read, PG_error will be * set again if read page fails. */ - ClearPageError(page); + folio_clear_error(folio); goto filler; out: - mark_page_accessed(page); - return page; + folio_mark_accessed(folio); + return folio; } /** - * read_cache_page - read into page cache, fill it if needed + * read_cache_folio - read into page cache, fill it if needed * @mapping: the page's address_space * @index: the page index * @filler: function to perform the read @@ -3553,10 +3541,27 @@ out: * * Return: up to date page on success, ERR_PTR() on failure. */ +struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, + filler_t filler, void *data) +{ + return do_read_cache_folio(mapping, index, filler, data, + mapping_gfp_mask(mapping)); +} +EXPORT_SYMBOL(read_cache_folio); + +static struct page *do_read_cache_page(struct address_space *mapping, + pgoff_t index, filler_t *filler, void *data, gfp_t gfp) +{ + struct folio *folio; + + folio = do_read_cache_folio(mapping, index, filler, data, gfp); + if (IS_ERR(folio)) + return &folio->page; + return folio_file_page(folio, index); +} + struct page *read_cache_page(struct address_space *mapping, - pgoff_t index, - int (*filler)(void *, struct page *), - void *data) + pgoff_t index, filler_t *filler, void *data) { return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping)); -- cgit v1.2.3 From 82c50f8b443359ec99348cd9b1289f55cd47779d Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 28 Jul 2021 15:14:48 -0400 Subject: filemap: Add filemap_release_folio() Reimplement try_to_release_page() as a wrapper around filemap_release_folio(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/mm.h | 1 - include/linux/pagemap.h | 2 ++ mm/filemap.c | 39 +++++++++++++++++++-------------------- mm/folio-compat.c | 6 ++++++ 4 files changed, 27 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 72ca04f16711..145f045b0ddc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1970,7 +1970,6 @@ int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, struct page **pages); struct page *get_dump_page(unsigned long addr); -extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 7bef50ea5435..eb6e58e106c8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -939,6 +939,8 @@ static inline void __delete_from_page_cache(struct page *page, void *shadow) void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, struct pagevec *pvec); +int try_to_release_page(struct page *page, gfp_t gfp); +bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); diff --git a/mm/filemap.c b/mm/filemap.c index bbe982e64e62..4c39e09a2f51 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3889,33 +3889,32 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) EXPORT_SYMBOL(generic_file_write_iter); /** - * try_to_release_page() - release old fs-specific metadata on a page + * filemap_release_folio() - Release fs-specific metadata on a folio. + * @folio: The folio which the kernel is trying to free. + * @gfp: Memory allocation flags (and I/O mode). * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) + * The address_space is trying to release any data attached to a folio + * (presumably at folio->private). * - * The address_space is to try to release any data against the page - * (presumably at page->private). + * This will also be called if the private_2 flag is set on a page, + * indicating that the folio has other metadata associated with it. * - * This may also be called if PG_fscache is set on a page, indicating that the - * page is known to the local caching routines. + * The @gfp argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block + * (__GFP_RECLAIM & __GFP_FS). * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_RECLAIM & __GFP_FS). - * - * Return: %1 if the release was successful, otherwise return zero. + * Return: %true if the release was successful, otherwise %false. */ -int try_to_release_page(struct page *page, gfp_t gfp_mask) +bool filemap_release_folio(struct folio *folio, gfp_t gfp) { - struct address_space * const mapping = page->mapping; + struct address_space * const mapping = folio->mapping; - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; + BUG_ON(!folio_test_locked(folio)); + if (folio_test_writeback(folio)) + return false; if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); + return mapping->a_ops->releasepage(&folio->page, gfp); + return try_to_free_buffers(&folio->page); } - -EXPORT_SYMBOL(try_to_release_page); +EXPORT_SYMBOL(filemap_release_folio); diff --git a/mm/folio-compat.c b/mm/folio-compat.c index 749a695b4217..749555a232a8 100644 --- a/mm/folio-compat.c +++ b/mm/folio-compat.c @@ -145,3 +145,9 @@ void delete_from_page_cache(struct page *page) { return filemap_remove_folio(page_folio(page)); } + +int try_to_release_page(struct page *page, gfp_t gfp) +{ + return filemap_release_folio(page_folio(page), gfp); +} +EXPORT_SYMBOL(try_to_release_page); -- cgit v1.2.3 From 77e2a04745ff8e391ad402e2d2d1157a5d3a7ebc Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Tue, 4 Jan 2022 19:51:08 +0000 Subject: ACPI: PCC: Implement OperationRegion handler for the PCC Type 3 subtype PCC OpRegion provides a mechanism to communicate with the platform directly from the AML. PCCT provides the list of PCC channel available in the platform, a subset or all of them can be used in PCC Opregion. This patch registers the PCC OpRegion handler before ACPI tables are loaded. This relies on the special context data passed to identify and set up the PCC channel before the OpRegion handler is executed for the first time. Typical PCC Opregion declaration looks like this: OperationRegion (PFRM, PCC, 2, 0x74) Field (PFRM, ByteAcc, NoLock, Preserve) { SIGN, 32, FLGS, 32, LEN, 32, CMD, 32, DATA, 800 } It contains four named double words followed by 100 bytes of buffer names DATA. ASL can fill out the buffer something like: /* Create global or local buffer */ Name (BUFF, Buffer (0x0C){}) /* Create double word fields over the buffer */ CreateDWordField (BUFF, 0x0, WD0) CreateDWordField (BUFF, 0x04, WD1) CreateDWordField (BUFF, 0x08, WD2) /* Fill the named fields */ WD0 = 0x50434300 SIGN = BUFF WD0 = 1 FLGS = BUFF WD0 = 0x10 LEN = BUFF /* Fill the payload in the DATA buffer */ WD0 = 0 WD1 = 0x08 WD2 = 0 DATA = BUFF /* Write to CMD field to trigger handler */ WD0 = 0x4404 CMD = BUFF This buffer is received by acpi_pcc_opregion_space_handler. This handler will fetch the complete buffer via internal_pcc_buffer. The setup handler will receive the special PCC context data which will contain the PCC channel index which used to set up the channel. The buffer pointer and length is saved in region context which is then used in the handler. (kernel test robot: Build failure with CONFIG_ACPI_DEBUGGER) Link: https://lore.kernel.org/r/202201041539.feAV0l27-lkp@intel.com Reported-by: kernel test robot Signed-off-by: Sudeep Holla Signed-off-by: Rafael J. Wysocki --- drivers/acpi/Kconfig | 17 +++++++ drivers/acpi/Makefile | 1 + drivers/acpi/acpi_pcc.c | 120 ++++++++++++++++++++++++++++++++++++++++++++++++ drivers/acpi/bus.c | 1 + include/linux/acpi.h | 6 +++ 5 files changed, 145 insertions(+) create mode 100644 drivers/acpi/acpi_pcc.c (limited to 'include/linux') diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index cdbdf68bd98f..60b5424bd318 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -524,6 +524,23 @@ config ACPI_PPTT bool endif +config ACPI_PCC + bool "ACPI PCC Address Space" + depends on PCC + default y + help + The PCC Address Space also referred as PCC Operation Region pertains + to the region of PCC subspace that succeeds the PCC signature. + + The PCC Operation Region works in conjunction with the PCC Table + (Platform Communications Channel Table). PCC subspaces that are + marked for use as PCC Operation Regions must not be used as PCC + subspaces for the standard ACPI features such as CPPC, RASF, PDTT and + MPST. These standard features must always use the PCC Table instead. + + Enable this feature if you want to set up and install the PCC Address + Space handler to handle PCC OpRegion in the firmware. + source "drivers/acpi/pmic/Kconfig" config ACPI_VIOT diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile index 3018714e87d9..08c2d985c57c 100644 --- a/drivers/acpi/Makefile +++ b/drivers/acpi/Makefile @@ -67,6 +67,7 @@ acpi-$(CONFIG_ACPI_LPIT) += acpi_lpit.o acpi-$(CONFIG_ACPI_GENERIC_GSI) += irq.o acpi-$(CONFIG_ACPI_WATCHDOG) += acpi_watchdog.o acpi-$(CONFIG_ACPI_PRMT) += prmt.o +acpi-$(CONFIG_ACPI_PCC) += acpi_pcc.o # Address translation acpi-$(CONFIG_ACPI_ADXL) += acpi_adxl.o diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c new file mode 100644 index 000000000000..41e3ebd204ff --- /dev/null +++ b/drivers/acpi/acpi_pcc.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Author: Sudeep Holla + * Copyright 2021 Arm Limited + * + * The PCC Address Space also referred as PCC Operation Region pertains to the + * region of PCC subspace that succeeds the PCC signature. The PCC Operation + * Region works in conjunction with the PCC Table(Platform Communications + * Channel Table). PCC subspaces that are marked for use as PCC Operation + * Regions must not be used as PCC subspaces for the standard ACPI features + * such as CPPC, RASF, PDTT and MPST. These standard features must always use + * the PCC Table instead. + * + * This driver sets up the PCC Address Space and installs an handler to enable + * handling of PCC OpRegion in the firmware. + * + */ +#include +#include +#include +#include +#include + +#include + +struct pcc_data { + struct pcc_mbox_chan *pcc_chan; + void __iomem *pcc_comm_addr; + struct completion done; + struct mbox_client cl; + struct acpi_pcc_info ctx; +}; + +struct acpi_pcc_info pcc_ctx; + +static void pcc_rx_callback(struct mbox_client *cl, void *m) +{ + struct pcc_data *data = container_of(cl, struct pcc_data, cl); + + complete(&data->done); +} + +static acpi_status +acpi_pcc_address_space_setup(acpi_handle region_handle, u32 function, + void *handler_context, void **region_context) +{ + struct pcc_data *data; + struct acpi_pcc_info *ctx = handler_context; + struct pcc_mbox_chan *pcc_chan; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return AE_NO_MEMORY; + + data->cl.rx_callback = pcc_rx_callback; + data->cl.knows_txdone = true; + data->ctx.length = ctx->length; + data->ctx.subspace_id = ctx->subspace_id; + data->ctx.internal_buffer = ctx->internal_buffer; + + init_completion(&data->done); + data->pcc_chan = pcc_mbox_request_channel(&data->cl, ctx->subspace_id); + if (IS_ERR(data->pcc_chan)) { + pr_err("Failed to find PCC channel for subspace %d\n", + ctx->subspace_id); + return AE_NOT_FOUND; + } + + pcc_chan = data->pcc_chan; + data->pcc_comm_addr = acpi_os_ioremap(pcc_chan->shmem_base_addr, + pcc_chan->shmem_size); + if (!data->pcc_comm_addr) { + pr_err("Failed to ioremap PCC comm region mem for %d\n", + ctx->subspace_id); + return AE_NO_MEMORY; + } + + *region_context = data; + return AE_OK; +} + +static acpi_status +acpi_pcc_address_space_handler(u32 function, acpi_physical_address addr, + u32 bits, acpi_integer *value, + void *handler_context, void *region_context) +{ + int ret; + struct pcc_data *data = region_context; + + reinit_completion(&data->done); + + /* Write to Shared Memory */ + memcpy_toio(data->pcc_comm_addr, (void *)value, data->ctx.length); + + ret = mbox_send_message(data->pcc_chan->mchan, NULL); + if (ret < 0) + return AE_ERROR; + + if (data->pcc_chan->mchan->mbox->txdone_irq) + wait_for_completion(&data->done); + + mbox_client_txdone(data->pcc_chan->mchan, ret); + + memcpy_fromio(value, data->pcc_comm_addr, data->ctx.length); + + return AE_OK; +} + +void __init acpi_init_pcc(void) +{ + acpi_status status; + + status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT, + ACPI_ADR_SPACE_PLATFORM_COMM, + &acpi_pcc_address_space_handler, + &acpi_pcc_address_space_setup, + &pcc_ctx); + if (ACPI_FAILURE(status)) + pr_alert("OperationRegion handler could not be installed\n"); +} diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index fa923a929224..b64014b4203e 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1320,6 +1320,7 @@ static int __init acpi_init(void) pr_debug("%s: kset create error\n", __func__); init_prmt(); + acpi_init_pcc(); result = acpi_bus_init(); if (result) { kobject_put(acpi_kobj); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index b28f8790192a..93eaba2485e3 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1389,6 +1389,12 @@ static inline int find_acpi_cpu_cache_topology(unsigned int cpu, int level) } #endif +#ifdef CONFIG_ACPI_PCC +void acpi_init_pcc(void); +#else +static inline void acpi_init_pcc(void) { } +#endif + #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); -- cgit v1.2.3 From 742bef476ca5352b16063161fb73a56629a6d995 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:20:35 +0100 Subject: ata: libata: move ata_{port,link,dev}_dbg to standard pr_XXX() macros Use standard pr_{debug,info,notice,warn,err} macros instead of the hand-crafted printk helpers. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-acpi.c | 48 ++++++++++++++++-------------- drivers/ata/libata-core.c | 61 --------------------------------------- drivers/ata/pata_ixp4xx_cf.c | 6 ++-- include/linux/libata.h | 69 ++++++++++++++++++++++++-------------------- 4 files changed, 67 insertions(+), 117 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 7a7d6642edcc..7007377880ce 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -650,9 +650,7 @@ static int ata_acpi_run_tf(struct ata_device *dev, struct ata_taskfile *pptf = NULL; struct ata_taskfile tf, ptf, rtf; unsigned int err_mask; - const char *level; const char *descr; - char msg[60]; int rc; if ((gtf->tf[0] == 0) && (gtf->tf[1] == 0) && (gtf->tf[2] == 0) @@ -666,6 +664,10 @@ static int ata_acpi_run_tf(struct ata_device *dev, pptf = &ptf; } + descr = ata_get_cmd_descript(tf.command); + if (!descr) + descr = "unknown"; + if (!ata_acpi_filter_tf(dev, &tf, pptf)) { rtf = tf; err_mask = ata_exec_internal(dev, &rtf, NULL, @@ -673,40 +675,42 @@ static int ata_acpi_run_tf(struct ata_device *dev, switch (err_mask) { case 0: - level = KERN_DEBUG; - snprintf(msg, sizeof(msg), "succeeded"); + ata_dev_dbg(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) succeeded\n", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr); rc = 1; break; case AC_ERR_DEV: - level = KERN_INFO; - snprintf(msg, sizeof(msg), - "rejected by device (Stat=0x%02x Err=0x%02x)", - rtf.command, rtf.feature); + ata_dev_info(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) rejected by device (Stat=0x%02x Err=0x%02x)", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr, + rtf.command, rtf.feature); rc = 0; break; default: - level = KERN_ERR; - snprintf(msg, sizeof(msg), - "failed (Emask=0x%x Stat=0x%02x Err=0x%02x)", - err_mask, rtf.command, rtf.feature); + ata_dev_err(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) failed (Emask=0x%x Stat=0x%02x Err=0x%02x)", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr, + err_mask, rtf.command, rtf.feature); rc = -EIO; break; } } else { - level = KERN_INFO; - snprintf(msg, sizeof(msg), "filtered out"); + ata_dev_info(dev, + "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x" + "(%s) filtered out\n", + tf.command, tf.feature, tf.nsect, tf.lbal, + tf.lbam, tf.lbah, tf.device, descr); rc = 0; } - descr = ata_get_cmd_descript(tf.command); - - ata_dev_printk(dev, level, - "ACPI cmd %02x/%02x:%02x:%02x:%02x:%02x:%02x (%s) %s\n", - tf.command, tf.feature, tf.nsect, tf.lbal, - tf.lbam, tf.lbah, tf.device, - (descr ? descr : "unknown"), msg); - return rc; } diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 3db4fd2029ce..d19984e5dfbc 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -6510,67 +6510,6 @@ const struct ata_port_info ata_dummy_port_info = { }; EXPORT_SYMBOL_GPL(ata_dummy_port_info); -/* - * Utility print functions - */ -void ata_port_printk(const struct ata_port *ap, const char *level, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - printk("%sata%u: %pV", level, ap->print_id, &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ata_port_printk); - -void ata_link_printk(const struct ata_link *link, const char *level, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - if (sata_pmp_attached(link->ap) || link->ap->slave_link) - printk("%sata%u.%02u: %pV", - level, link->ap->print_id, link->pmp, &vaf); - else - printk("%sata%u: %pV", - level, link->ap->print_id, &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ata_link_printk); - -void ata_dev_printk(const struct ata_device *dev, const char *level, - const char *fmt, ...) -{ - struct va_format vaf; - va_list args; - - va_start(args, fmt); - - vaf.fmt = fmt; - vaf.va = &args; - - printk("%sata%u.%02u: %pV", - level, dev->link->ap->print_id, dev->link->pmp + dev->devno, - &vaf); - - va_end(args); -} -EXPORT_SYMBOL(ata_dev_printk); - void ata_print_version(const struct device *dev, const char *version) { dev_printk(KERN_DEBUG, dev, "version %s\n", version); diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c index 99c63087c8ae..17b557c91e1c 100644 --- a/drivers/ata/pata_ixp4xx_cf.c +++ b/drivers/ata/pata_ixp4xx_cf.c @@ -114,7 +114,7 @@ static void ixp4xx_set_piomode(struct ata_port *ap, struct ata_device *adev) { struct ixp4xx_pata *ixpp = ap->host->private_data; - ata_dev_printk(adev, KERN_INFO, "configured for PIO%d 8bit\n", + ata_dev_info(adev, "configured for PIO%d 8bit\n", adev->pio_mode - XFER_PIO_0); ixp4xx_set_8bit_timing(ixpp, adev->pio_mode); } @@ -132,8 +132,8 @@ static unsigned int ixp4xx_mmio_data_xfer(struct ata_queued_cmd *qc, struct ixp4xx_pata *ixpp = ap->host->private_data; unsigned long flags; - ata_dev_printk(adev, KERN_DEBUG, "%s %d bytes\n", (rw == READ) ? "READ" : "WRITE", - buflen); + ata_dev_dbg(adev, "%s %d bytes\n", (rw == READ) ? "READ" : "WRITE", + buflen); spin_lock_irqsave(ap->lock, flags); /* set the expansion bus in 16bit mode and restore diff --git a/include/linux/libata.h b/include/linux/libata.h index 235fdbeb19ea..39cdde0b9491 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1489,51 +1489,61 @@ static inline int sata_srst_pmp(struct ata_link *link) return link->pmp; } -/* - * printk helpers - */ -__printf(3, 4) -void ata_port_printk(const struct ata_port *ap, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_link_printk(const struct ata_link *link, const char *level, - const char *fmt, ...); -__printf(3, 4) -void ata_dev_printk(const struct ata_device *dev, const char *level, - const char *fmt, ...); +#define ata_port_printk(level, ap, fmt, ...) \ + pr_ ## level ("ata%u: " fmt, (ap)->print_id, ##__VA_ARGS__) #define ata_port_err(ap, fmt, ...) \ - ata_port_printk(ap, KERN_ERR, fmt, ##__VA_ARGS__) + ata_port_printk(err, ap, fmt, ##__VA_ARGS__) #define ata_port_warn(ap, fmt, ...) \ - ata_port_printk(ap, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_port_printk(warn, ap, fmt, ##__VA_ARGS__) #define ata_port_notice(ap, fmt, ...) \ - ata_port_printk(ap, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_port_printk(notice, ap, fmt, ##__VA_ARGS__) #define ata_port_info(ap, fmt, ...) \ - ata_port_printk(ap, KERN_INFO, fmt, ##__VA_ARGS__) + ata_port_printk(info, ap, fmt, ##__VA_ARGS__) #define ata_port_dbg(ap, fmt, ...) \ - ata_port_printk(ap, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_port_printk(debug, ap, fmt, ##__VA_ARGS__) + +#define ata_link_printk(level, link, fmt, ...) \ +do { \ + if (sata_pmp_attached((link)->ap) || \ + (link)->ap->slave_link) \ + pr_ ## level ("ata%u.%02u: " fmt, \ + (link)->ap->print_id, \ + (link)->pmp, \ + ##__VA_ARGS__); \ + else \ + pr_ ## level ("ata%u: " fmt, \ + (link)->ap->print_id, \ + ##__VA_ARGS__); \ +} while (0) #define ata_link_err(link, fmt, ...) \ - ata_link_printk(link, KERN_ERR, fmt, ##__VA_ARGS__) + ata_link_printk(err, link, fmt, ##__VA_ARGS__) #define ata_link_warn(link, fmt, ...) \ - ata_link_printk(link, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_link_printk(warn, link, fmt, ##__VA_ARGS__) #define ata_link_notice(link, fmt, ...) \ - ata_link_printk(link, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_link_printk(notice, link, fmt, ##__VA_ARGS__) #define ata_link_info(link, fmt, ...) \ - ata_link_printk(link, KERN_INFO, fmt, ##__VA_ARGS__) + ata_link_printk(info, link, fmt, ##__VA_ARGS__) #define ata_link_dbg(link, fmt, ...) \ - ata_link_printk(link, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_link_printk(debug, link, fmt, ##__VA_ARGS__) + +#define ata_dev_printk(level, dev, fmt, ...) \ + pr_ ## level("ata%u.%02u: " fmt, \ + (dev)->link->ap->print_id, \ + (dev)->link->pmp + (dev)->devno, \ + ##__VA_ARGS__) #define ata_dev_err(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_ERR, fmt, ##__VA_ARGS__) + ata_dev_printk(err, dev, fmt, ##__VA_ARGS__) #define ata_dev_warn(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_WARNING, fmt, ##__VA_ARGS__) + ata_dev_printk(warn, dev, fmt, ##__VA_ARGS__) #define ata_dev_notice(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_NOTICE, fmt, ##__VA_ARGS__) + ata_dev_printk(notice, dev, fmt, ##__VA_ARGS__) #define ata_dev_info(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_INFO, fmt, ##__VA_ARGS__) + ata_dev_printk(info, dev, fmt, ##__VA_ARGS__) #define ata_dev_dbg(dev, fmt, ...) \ - ata_dev_printk(dev, KERN_DEBUG, fmt, ##__VA_ARGS__) + ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__) void ata_print_version(const struct device *dev, const char *version); @@ -2067,11 +2077,8 @@ static inline u8 ata_wait_idle(struct ata_port *ap) { u8 status = ata_sff_busy_wait(ap, ATA_BUSY | ATA_DRQ, 1000); -#ifdef ATA_DEBUG if (status != 0xff && (status & (ATA_BUSY | ATA_DRQ))) - ata_port_printk(ap, KERN_DEBUG, "abnormal Status 0x%X\n", - status); -#endif + ata_port_dbg(ap, "abnormal Status 0x%X\n", status); return status; } -- cgit v1.2.3 From d97c75edd806669c9f4b56c0ddae37725c0b708c Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:01 +0100 Subject: ata: libata: drop ata_msg_error() and ata_msg_intr() Unused. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 6 +++--- include/linux/libata.h | 4 ---- 2 files changed, 3 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 447a46bdc820..165210576288 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5345,11 +5345,11 @@ struct ata_port *ata_port_alloc(struct ata_host *host) #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ - ap->msg_enable = 0x00FF; + ap->msg_enable = 0x003F; #elif defined(ATA_DEBUG) - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN | ATA_MSG_ERR; + ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN; #else - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_ERR | ATA_MSG_WARN; + ap->msg_enable = ATA_MSG_DRV | ATA_MSG_WARN; #endif mutex_init(&ap->scsi_scan_mutex); diff --git a/include/linux/libata.h b/include/linux/libata.h index 39cdde0b9491..4f0a85f4e69a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -78,8 +78,6 @@ enum { ATA_MSG_WARN = 0x0008, ATA_MSG_MALLOC = 0x0010, ATA_MSG_CTL = 0x0020, - ATA_MSG_INTR = 0x0040, - ATA_MSG_ERR = 0x0080, }; #define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) @@ -88,8 +86,6 @@ enum { #define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) #define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) #define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL) -#define ata_msg_intr(p) ((p)->msg_enable & ATA_MSG_INTR) -#define ata_msg_err(p) ((p)->msg_enable & ATA_MSG_ERR) static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { -- cgit v1.2.3 From 5cef96b4207e01c9cdb7752acaa178056fe94632 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:02 +0100 Subject: ata: libata: drop ata_msg_ctl() The one caller have been converted to dynamic debugging. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 7 ++----- include/linux/libata.h | 2 -- 2 files changed, 2 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 165210576288..5b50a6d0d6eb 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1763,9 +1763,6 @@ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class, int may_fallback = 1, tried_spinup = 0; int rc; - if (ata_msg_ctl(ap)) - ata_dev_dbg(dev, "%s: ENTER\n", __func__); - retry: ata_tf_init(dev, &tf); @@ -5345,9 +5342,9 @@ struct ata_port *ata_port_alloc(struct ata_host *host) #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ - ap->msg_enable = 0x003F; + ap->msg_enable = 0x001F; #elif defined(ATA_DEBUG) - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN; + ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_WARN; #else ap->msg_enable = ATA_MSG_DRV | ATA_MSG_WARN; #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 4f0a85f4e69a..e384cce62963 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -77,7 +77,6 @@ enum { ATA_MSG_PROBE = 0x0004, ATA_MSG_WARN = 0x0008, ATA_MSG_MALLOC = 0x0010, - ATA_MSG_CTL = 0x0020, }; #define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) @@ -85,7 +84,6 @@ enum { #define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) #define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) #define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) -#define ata_msg_ctl(p) ((p)->msg_enable & ATA_MSG_CTL) static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { -- cgit v1.2.3 From 2f784b923d50cdef1f6bd24d7c18614321b0833a Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:03 +0100 Subject: ata: libata: drop ata_msg_malloc() Unused. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 2 +- include/linux/libata.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 5b50a6d0d6eb..3accab132492 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5342,7 +5342,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host) #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ - ap->msg_enable = 0x001F; + ap->msg_enable = 0x000F; #elif defined(ATA_DEBUG) ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_WARN; #else diff --git a/include/linux/libata.h b/include/linux/libata.h index e384cce62963..5651bbf4902b 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -76,14 +76,12 @@ enum { ATA_MSG_INFO = 0x0002, ATA_MSG_PROBE = 0x0004, ATA_MSG_WARN = 0x0008, - ATA_MSG_MALLOC = 0x0010, }; #define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) #define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) #define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) #define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) -#define ata_msg_malloc(p) ((p)->msg_enable & ATA_MSG_MALLOC) static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { -- cgit v1.2.3 From 16d424672716dc886fb58ec4a47a408db4781cc0 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:04 +0100 Subject: ata: libata: drop ata_msg_warn() The WARN level was always enabled, so drop ata_msg_warn(). Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 19 ++++++++----------- include/linux/libata.h | 2 -- 2 files changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 3accab132492..b5334e0a8603 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1571,9 +1571,8 @@ unsigned ata_exec_internal_sg(struct ata_device *dev, else ata_qc_complete(qc); - if (ata_msg_warn(ap)) - ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n", - command); + ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n", + command); } spin_unlock_irqrestore(ap->lock, flags); @@ -1932,9 +1931,8 @@ retry: return 0; err_out: - if (ata_msg_warn(ap)) - ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n", - reason, err_mask); + ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n", + reason, err_mask); return rc; } @@ -2683,8 +2681,7 @@ int ata_dev_configure(struct ata_device *dev) rc = atapi_cdb_len(id); if ((rc < 12) || (rc > ATAPI_CDB_LEN)) { - if (ata_msg_warn(ap)) - ata_dev_warn(dev, "unsupported CDB len\n"); + ata_dev_warn(dev, "unsupported CDB len %d\n", rc); rc = -EINVAL; goto err_out_nosup; } @@ -5342,11 +5339,11 @@ struct ata_port *ata_port_alloc(struct ata_host *host) #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ - ap->msg_enable = 0x000F; + ap->msg_enable = 0x0007; #elif defined(ATA_DEBUG) - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_WARN; + ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO; #else - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_WARN; + ap->msg_enable = ATA_MSG_DRV; #endif mutex_init(&ap->scsi_scan_mutex); diff --git a/include/linux/libata.h b/include/linux/libata.h index 5651bbf4902b..0e5ed2ff94be 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -75,13 +75,11 @@ enum { ATA_MSG_DRV = 0x0001, ATA_MSG_INFO = 0x0002, ATA_MSG_PROBE = 0x0004, - ATA_MSG_WARN = 0x0008, }; #define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) #define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) #define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) -#define ata_msg_warn(p) ((p)->msg_enable & ATA_MSG_WARN) static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { -- cgit v1.2.3 From 17a1e1be2fc7dc99945b41df0485037dcb6044d0 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:05 +0100 Subject: ata: libata: drop ata_msg_probe() All callsites have been converted to dynamic debugging. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-acpi.c | 23 +++++++---------------- drivers/ata/libata-core.c | 20 +++++++------------- drivers/ata/libata-sff.c | 4 ---- include/linux/libata.h | 2 -- 4 files changed, 14 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c index 9e1e62b9cf63..8cfa8c96bb13 100644 --- a/drivers/ata/libata-acpi.c +++ b/drivers/ata/libata-acpi.c @@ -402,7 +402,6 @@ EXPORT_SYMBOL_GPL(ata_acpi_stm); */ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) { - struct ata_port *ap = dev->link->ap; acpi_status status; struct acpi_buffer output; union acpi_object *out_obj; @@ -418,10 +417,6 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) output.length = ACPI_ALLOCATE_BUFFER; output.pointer = NULL; /* ACPI-CA sets this; save/free it later */ - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: ENTER: port#: %d\n", - __func__, ap->port_no); - /* _GTF has no input parameters */ status = acpi_evaluate_object(ata_dev_acpi_handle(dev), "_GTF", NULL, &output); @@ -437,11 +432,9 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) } if (!output.length || !output.pointer) { - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: Run _GTF: length or ptr is NULL (0x%llx, 0x%p)\n", - __func__, - (unsigned long long)output.length, - output.pointer); + ata_dev_dbg(dev, "Run _GTF: length or ptr is NULL (0x%llx, 0x%p)\n", + (unsigned long long)output.length, + output.pointer); rc = -EINVAL; goto out_free; } @@ -464,9 +457,8 @@ static int ata_dev_get_GTF(struct ata_device *dev, struct ata_acpi_gtf **gtf) rc = out_obj->buffer.length / REGS_PER_GTF; if (gtf) { *gtf = (void *)out_obj->buffer.pointer; - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: returning gtf=%p, gtf_count=%d\n", - __func__, *gtf, rc); + ata_dev_dbg(dev, "returning gtf=%p, gtf_count=%d\n", + *gtf, rc); } return rc; @@ -778,9 +770,8 @@ static int ata_acpi_push_id(struct ata_device *dev) struct acpi_object_list input; union acpi_object in_params[1]; - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: ix = %d, port#: %d\n", - __func__, dev->devno, ap->port_no); + ata_dev_dbg(dev, "%s: ix = %d, port#: %d\n", + __func__, dev->devno, ap->port_no); /* Give the drive Identify data to the drive via the _SDD method */ /* _SDD: set up input parameters */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b5334e0a8603..623a6f272c7e 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2535,9 +2535,6 @@ int ata_dev_configure(struct ata_device *dev) return 0; } - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: ENTER\n", __func__); - /* set horkage */ dev->horkage |= ata_dev_blacklisted(dev); ata_force_horkage(dev); @@ -2585,13 +2582,12 @@ int ata_dev_configure(struct ata_device *dev) return rc; /* print device capabilities */ - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, - "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x " - "85:%04x 86:%04x 87:%04x 88:%04x\n", - __func__, - id[49], id[82], id[83], id[84], - id[85], id[86], id[87], id[88]); + ata_dev_dbg(dev, + "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x " + "85:%04x 86:%04x 87:%04x 88:%04x\n", + __func__, + id[49], id[82], id[83], id[84], + id[85], id[86], id[87], id[88]); /* initialize to-be-configured parameters */ dev->flags &= ~ATA_DFLAG_CFG_MASK; @@ -2791,8 +2787,6 @@ int ata_dev_configure(struct ata_device *dev) return 0; err_out_nosup: - if (ata_msg_probe(ap)) - ata_dev_dbg(dev, "%s: EXIT, err\n", __func__); return rc; } @@ -5339,7 +5333,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host) #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ - ap->msg_enable = 0x0007; + ap->msg_enable = 0x0003; #elif defined(ATA_DEBUG) ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO; #else diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index d5dbeb68b2bf..01f1673f3297 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -330,10 +330,6 @@ EXPORT_SYMBOL_GPL(ata_sff_dev_select); static void ata_dev_select(struct ata_port *ap, unsigned int device, unsigned int wait, unsigned int can_sleep) { - if (ata_msg_probe(ap)) - ata_port_info(ap, "ata_dev_select: ENTER, device %u, wait %u\n", - device, wait); - if (wait) ata_wait_idle(ap); diff --git a/include/linux/libata.h b/include/linux/libata.h index 0e5ed2ff94be..455d7e77e562 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -74,12 +74,10 @@ enum { ATA_MSG_DRV = 0x0001, ATA_MSG_INFO = 0x0002, - ATA_MSG_PROBE = 0x0004, }; #define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) #define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) -#define ata_msg_probe(p) ((p)->msg_enable & ATA_MSG_PROBE) static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { -- cgit v1.2.3 From 96c810f216cb6da15bfa8fe8ef3bf73ca91c5dd8 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:06 +0100 Subject: ata: libata: drop ata_msg_info() Convert the sole caller to ata_dev_dbg() and remove the definition. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 10 +++------- include/linux/libata.h | 2 -- 2 files changed, 3 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 623a6f272c7e..80ca94eb3ce0 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2530,8 +2530,8 @@ int ata_dev_configure(struct ata_device *dev) char modelbuf[ATA_ID_PROD_LEN+1]; int rc; - if (!ata_dev_enabled(dev) && ata_msg_info(ap)) { - ata_dev_info(dev, "%s: ENTER/EXIT -- nodev\n", __func__); + if (!ata_dev_enabled(dev)) { + ata_dev_dbg(dev, "no device\n"); return 0; } @@ -5333,11 +5333,7 @@ struct ata_port *ata_port_alloc(struct ata_host *host) #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ - ap->msg_enable = 0x0003; -#elif defined(ATA_DEBUG) - ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO; -#else - ap->msg_enable = ATA_MSG_DRV; + ap->msg_enable = 0x0001; #endif mutex_init(&ap->scsi_scan_mutex); diff --git a/include/linux/libata.h b/include/linux/libata.h index 455d7e77e562..524d09b1dc82 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -73,11 +73,9 @@ enum { ATA_MSG_DRV = 0x0001, - ATA_MSG_INFO = 0x0002, }; #define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) -#define ata_msg_info(p) ((p)->msg_enable & ATA_MSG_INFO) static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { -- cgit v1.2.3 From 1c95a27c1e544f723f6e0e5a4384098f92996ec0 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:07 +0100 Subject: ata: libata: drop ata_msg_drv() Callers are already protected by ata_dev_print_info(), so no need to have an additional configuration parameter here. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 19 ++++++------------- drivers/ata/libata-eh.c | 3 +-- include/linux/libata.h | 6 ------ 3 files changed, 7 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 80ca94eb3ce0..9c2947905d1e 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2354,7 +2354,6 @@ static void ata_dev_config_trusted(struct ata_device *dev) static int ata_dev_config_lba(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; const u16 *id = dev->id; const char *lba_desc; char ncq_desc[24]; @@ -2376,7 +2375,7 @@ static int ata_dev_config_lba(struct ata_device *dev) ret = ata_dev_config_ncq(dev, ncq_desc, sizeof(ncq_desc)); /* print device info to dmesg */ - if (ata_msg_drv(ap) && ata_dev_print_info(dev)) + if (ata_dev_print_info(dev)) ata_dev_info(dev, "%llu sectors, multi %u: %s %s\n", (unsigned long long)dev->n_sectors, @@ -2387,7 +2386,6 @@ static int ata_dev_config_lba(struct ata_device *dev) static void ata_dev_config_chs(struct ata_device *dev) { - struct ata_port *ap = dev->link->ap; const u16 *id = dev->id; if (ata_id_current_chs_valid(id)) { @@ -2403,7 +2401,7 @@ static void ata_dev_config_chs(struct ata_device *dev) } /* print device info to dmesg */ - if (ata_msg_drv(ap) && ata_dev_print_info(dev)) + if (ata_dev_print_info(dev)) ata_dev_info(dev, "%llu sectors, multi %u, CHS %u/%u/%u\n", (unsigned long long)dev->n_sectors, @@ -2644,7 +2642,7 @@ int ata_dev_configure(struct ata_device *dev) } /* print device info to dmesg */ - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_info(dev, "%s: %s, %s, max %s\n", revbuf, modelbuf, fwrevbuf, ata_mode_string(xfer_mask)); @@ -2664,7 +2662,7 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_cpr(dev); dev->cdb_len = 32; - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_print_features(dev); } @@ -2721,7 +2719,7 @@ int ata_dev_configure(struct ata_device *dev) } /* print device info to dmesg */ - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_info(dev, "ATAPI: %s, %s, max %s%s%s%s\n", modelbuf, fwrevbuf, @@ -2738,7 +2736,7 @@ int ata_dev_configure(struct ata_device *dev) /* Limit PATA drive on SATA cable bridge transfers to udma5, 200 sectors */ if (ata_dev_knobble(dev)) { - if (ata_msg_drv(ap) && print_info) + if (print_info) ata_dev_info(dev, "applying bridge limits\n"); dev->udma_mask &= ATA_UDMA5; dev->max_sectors = ATA_MAX_SECTORS; @@ -5331,11 +5329,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host) ap->host = host; ap->dev = host->dev; -#if defined(ATA_VERBOSE_DEBUG) - /* turn on all debugging levels */ - ap->msg_enable = 0x0001; -#endif - mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 8bf52a6239aa..7951fd946bf9 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1214,8 +1214,7 @@ void ata_dev_disable(struct ata_device *dev) if (!ata_dev_enabled(dev)) return; - if (ata_msg_drv(dev->link->ap)) - ata_dev_warn(dev, "disabled\n"); + ata_dev_warn(dev, "disable device\n"); ata_acpi_on_disable(dev); ata_down_xfermask_limit(dev, ATA_DNXFER_FORCE_PIO0 | ATA_DNXFER_QUIET); dev->class++; diff --git a/include/linux/libata.h b/include/linux/libata.h index 524d09b1dc82..65172609a005 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -71,12 +71,6 @@ /* NEW: debug levels */ #define HAVE_LIBATA_MSG 1 -enum { - ATA_MSG_DRV = 0x0001, -}; - -#define ata_msg_drv(p) ((p)->msg_enable & ATA_MSG_DRV) - static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) { if (dval < 0 || dval >= (sizeof(u32) * 8)) -- cgit v1.2.3 From db45905e74e6ae035305719bc683eca40f526669 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:08 +0100 Subject: ata: libata: remove 'new' ata message handling Remove the remaining bits for the 'new' ata message handling. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- include/linux/libata.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 65172609a005..145c0132b75e 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -68,18 +68,6 @@ } \ }) -/* NEW: debug levels */ -#define HAVE_LIBATA_MSG 1 - -static inline u32 ata_msg_init(int dval, int default_msg_enable_bits) -{ - if (dval < 0 || dval >= (sizeof(u32) * 8)) - return default_msg_enable_bits; /* should be 0x1 - only driver info msgs */ - if (!dval) - return 0; - return (1 << dval) - 1; -} - /* defines only for the constants which don't work well as enums */ #define ATA_TAG_POISON 0xfafbfcfdU @@ -864,7 +852,6 @@ struct ata_port { unsigned int hsm_task_state; - u32 msg_enable; struct list_head eh_done_q; wait_queue_head_t eh_wait_q; int eh_tries; -- cgit v1.2.3 From 870bb833c0acb29d8471eac5c2d2e6274826dbb6 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Tue, 21 Dec 2021 08:21:09 +0100 Subject: ata: libata: remove debug compilation switches Unused now, so remove and drop any references to them. Signed-off-by: Hannes Reinecke Signed-off-by: Damien Le Moal --- drivers/ata/libata-sff.c | 1 - drivers/ata/pata_ep93xx.c | 1 - drivers/ata/sata_rcar.c | 1 - include/linux/libata.h | 16 ---------------- 4 files changed, 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c index 01f1673f3297..75217828dfe3 100644 --- a/drivers/ata/libata-sff.c +++ b/drivers/ata/libata-sff.c @@ -2091,7 +2091,6 @@ void ata_sff_drain_fifo(struct ata_queued_cmd *qc) && count < 65536; count += 2) ioread16(ap->ioaddr.data_addr); - /* Can become DEBUG later */ if (count) ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count); diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c index 46208ececbb6..b78f71c70f27 100644 --- a/drivers/ata/pata_ep93xx.c +++ b/drivers/ata/pata_ep93xx.c @@ -855,7 +855,6 @@ static void ep93xx_pata_drain_fifo(struct ata_queued_cmd *qc) && count < 65536; count += 2) ep93xx_pata_read_reg(drv_data, IDECTRL_ADDR_DATA); - /* Can become DEBUG later */ if (count) ata_port_dbg(ap, "drained %d bytes to clear DRQ.\n", count); diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 91b39a6aa9f7..3d96b6faa3f0 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -479,7 +479,6 @@ static void sata_rcar_drain_fifo(struct ata_queued_cmd *qc) count < 65536; count += 2) ioread32(ap->ioaddr.data_addr); - /* Can become DEBUG later */ if (count) ata_port_dbg(ap, "drained %d bytes to clear DRQ\n", count); } diff --git a/include/linux/libata.h b/include/linux/libata.h index 145c0132b75e..c258f69106f4 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -39,25 +39,9 @@ * compile-time options: to be removed as soon as all the drivers are * converted to the new debugging mechanism */ -#undef ATA_DEBUG /* debugging output */ -#undef ATA_VERBOSE_DEBUG /* yet more debugging output */ #undef ATA_IRQ_TRAP /* define to ack screaming irqs */ -#undef ATA_NDEBUG /* define to disable quick runtime checks */ -/* note: prints function name for you */ -#ifdef ATA_DEBUG -#define DPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#ifdef ATA_VERBOSE_DEBUG -#define VPRINTK(fmt, args...) printk(KERN_ERR "%s: " fmt, __func__, ## args) -#else -#define VPRINTK(fmt, args...) -#endif /* ATA_VERBOSE_DEBUG */ -#else -#define DPRINTK(fmt, args...) -#define VPRINTK(fmt, args...) -#endif /* ATA_DEBUG */ - #define ata_print_version_once(dev, version) \ ({ \ static bool __print_once; \ -- cgit v1.2.3 From cc4b08c31b5c51352f258032cc65e884b3e61e6a Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 7 Dec 2021 21:15:31 +0900 Subject: can: do not increase tx_bytes statistics for RTR frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The actual payload length of the CAN Remote Transmission Request (RTR) frames is always 0, i.e. no payload is transmitted on the wire. However, those RTR frames still use the DLC to indicate the length of the requested frame. As such, net_device_stats::tx_bytes should not be increased when sending RTR frames. The function can_get_echo_skb() already returns the correct length, even for RTR frames (c.f. [1]). However, for historical reasons, the drivers do not use can_get_echo_skb()'s return value and instead, most of them store a temporary length (or dlc) in some local structure or array. Using the return value of can_get_echo_skb() solves the issue. After doing this, such length/dlc fields become unused and so this patch does the adequate cleaning when needed. This patch fixes all the CAN drivers. Finally, can_get_echo_skb() is decorated with the __must_check attribute in order to force future drivers to correctly use its return value (else the compiler would emit a warning). [1] commit ed3320cec279 ("can: dev: __can_get_echo_skb(): fix real payload length return value for RTR frames") Link: https://lore.kernel.org/all/20211207121531.42941-6-mailhol.vincent@wanadoo.fr Cc: Nicolas Ferre Cc: Alexandre Belloni Cc: Ludovic Desroches Cc: Maxime Ripard Cc: Chen-Yu Tsai Cc: Jernej Skrabec Cc: Yasushi SHOJI Cc: Oliver Hartkopp Cc: Stephane Grosjean Cc: Andreas Larsson Tested-by: Jimmy Assarsson # kvaser Signed-off-by: Vincent Mailhol Acked-by: Stefan Mätje # esd_usb2 Tested-by: Stefan Mätje # esd_usb2 [mkl: add conversion for grcan] Signed-off-by: Marc Kleine-Budde --- drivers/net/can/at91_can.c | 8 ++--- drivers/net/can/c_can/c_can.h | 1 - drivers/net/can/c_can/c_can_main.c | 7 ++-- drivers/net/can/cc770/cc770.c | 8 ++--- drivers/net/can/grcan.c | 17 ++------- drivers/net/can/janz-ican3.c | 3 +- drivers/net/can/mscan/mscan.c | 4 +-- drivers/net/can/pch_can.c | 9 ++--- drivers/net/can/peak_canfd/peak_canfd.c | 3 +- drivers/net/can/rcar/rcar_can.c | 11 +++--- drivers/net/can/rcar/rcar_canfd.c | 6 +--- drivers/net/can/sja1000/sja1000.c | 4 +-- drivers/net/can/slcan.c | 3 +- drivers/net/can/softing/softing_main.c | 8 ++--- drivers/net/can/spi/hi311x.c | 24 ++++++------- drivers/net/can/spi/mcp251x.c | 25 +++++++------- drivers/net/can/sun4i_can.c | 5 +-- drivers/net/can/usb/ems_usb.c | 7 ++-- drivers/net/can/usb/esd_usb2.c | 6 ++-- drivers/net/can/usb/gs_usb.c | 7 ++-- drivers/net/can/usb/kvaser_usb/kvaser_usb.h | 5 ++- drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 2 +- drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 42 +++++++++++------------ drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 13 +++---- drivers/net/can/usb/mcba_usb.c | 12 +++---- drivers/net/can/usb/peak_usb/pcan_usb_core.c | 20 +++++------ drivers/net/can/usb/peak_usb/pcan_usb_core.h | 1 - drivers/net/can/usb/ucan.c | 10 ++---- drivers/net/can/usb/usb_8dev.c | 6 +--- drivers/net/can/vcan.c | 7 ++-- drivers/net/can/vxcan.c | 2 +- include/linux/can/skb.h | 5 +-- 32 files changed, 116 insertions(+), 175 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 97f1d08b4133..a00655ccda02 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -448,7 +448,6 @@ static void at91_chip_stop(struct net_device *dev, enum can_state state) static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct at91_priv *priv = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; struct can_frame *cf = (struct can_frame *)skb->data; unsigned int mb, prio; u32 reg_mid, reg_mcr; @@ -480,8 +479,6 @@ static netdev_tx_t at91_start_xmit(struct sk_buff *skb, struct net_device *dev) /* This triggers transmission */ at91_write(priv, AT91_MCR(mb), reg_mcr); - stats->tx_bytes += cf->len; - /* _NOTE_: subtract AT91_MB_TX_FIRST offset from mb! */ can_put_echo_skb(skb, dev, mb - get_mb_tx_first(priv), 0); @@ -852,7 +849,10 @@ static void at91_irq_tx(struct net_device *dev, u32 reg_sr) if (likely(reg_msr & AT91_MSR_MRDY && ~reg_msr & AT91_MSR_MABT)) { /* _NOTE_: subtract AT91_MB_TX_FIRST offset from mb! */ - can_get_echo_skb(dev, mb - get_mb_tx_first(priv), NULL); + dev->stats.tx_bytes += + can_get_echo_skb(dev, + mb - get_mb_tx_first(priv), + NULL); dev->stats.tx_packets++; can_led_event(dev, CAN_LED_EVENT_TX); } diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index 08b6efa7a1a7..bd2f6dc01194 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -211,7 +211,6 @@ struct c_can_priv { struct c_can_raminit raminit_sys; /* RAMINIT via syscon regmap */ void (*raminit)(const struct c_can_priv *priv, bool enable); u32 comm_rcv_high; - u32 dlc[]; }; struct net_device *alloc_c_can_dev(int msg_obj_num); diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index 29e91804d81c..faa217f26771 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -477,7 +477,6 @@ static netdev_tx_t c_can_start_xmit(struct sk_buff *skb, * transmit as we might race against do_tx(). */ c_can_setup_tx_object(dev, IF_TX, frame, idx); - priv->dlc[idx] = frame->len; can_put_echo_skb(skb, dev, idx, 0); obj = idx + priv->msg_obj_tx_first; c_can_object_put(dev, IF_TX, obj, cmd); @@ -742,8 +741,7 @@ static void c_can_do_tx(struct net_device *dev) * NAPI. We are not transmitting. */ c_can_inval_tx_object(dev, IF_NAPI, obj); - can_get_echo_skb(dev, idx, NULL); - bytes += priv->dlc[idx]; + bytes += can_get_echo_skb(dev, idx, NULL); pkts++; } @@ -1227,8 +1225,7 @@ struct net_device *alloc_c_can_dev(int msg_obj_num) struct c_can_priv *priv; int msg_obj_tx_num = msg_obj_num / 2; - dev = alloc_candev(struct_size(priv, dlc, msg_obj_tx_num), - msg_obj_tx_num); + dev = alloc_candev(sizeof(*priv), msg_obj_tx_num); if (!dev) return NULL; diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index 994073c0a2f6..bb7224cfc6ab 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -664,7 +664,6 @@ static void cc770_tx_interrupt(struct net_device *dev, unsigned int o) struct cc770_priv *priv = netdev_priv(dev); struct net_device_stats *stats = &dev->stats; unsigned int mo = obj2msgobj(o); - struct can_frame *cf; u8 ctrl1; ctrl1 = cc770_read_reg(priv, msgobj[mo].ctrl1); @@ -696,12 +695,9 @@ static void cc770_tx_interrupt(struct net_device *dev, unsigned int o) return; } - cf = (struct can_frame *)priv->tx_skb->data; - stats->tx_bytes += cf->len; - stats->tx_packets++; - can_put_echo_skb(priv->tx_skb, dev, 0, 0); - can_get_echo_skb(dev, 0, NULL); + stats->tx_bytes += can_get_echo_skb(dev, 0, NULL); + stats->tx_packets++; priv->tx_skb = NULL; netif_wake_queue(dev); diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index 1b8ef97e4139..d0c5a7a60daf 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -255,7 +255,6 @@ struct grcan_priv { struct grcan_dma dma; struct sk_buff **echo_skb; /* We allocate this on our own */ - u8 *txdlc; /* Length of queued frames */ /* The echo skb pointer, pointing into echo_skb and indicating which * frames can be echoed back. See the "Notes on the tx cyclic buffer @@ -515,9 +514,7 @@ static int catch_up_echo_skb(struct net_device *dev, int budget, bool echo) if (echo) { /* Normal echo of messages */ stats->tx_packets++; - stats->tx_bytes += priv->txdlc[i]; - priv->txdlc[i] = 0; - can_get_echo_skb(dev, i, NULL); + stats->tx_bytes += can_get_echo_skb(dev, i, NULL); } else { /* For cleanup of untransmitted messages */ can_free_echo_skb(dev, i, NULL); @@ -1062,16 +1059,10 @@ static int grcan_open(struct net_device *dev) priv->can.echo_skb_max = dma->tx.size; priv->can.echo_skb = priv->echo_skb; - priv->txdlc = kcalloc(dma->tx.size, sizeof(*priv->txdlc), GFP_KERNEL); - if (!priv->txdlc) { - err = -ENOMEM; - goto exit_free_echo_skb; - } - /* Get can device up */ err = open_candev(dev); if (err) - goto exit_free_txdlc; + goto exit_free_echo_skb; err = request_irq(dev->irq, grcan_interrupt, IRQF_SHARED, dev->name, dev); @@ -1093,8 +1084,6 @@ static int grcan_open(struct net_device *dev) exit_close_candev: close_candev(dev); -exit_free_txdlc: - kfree(priv->txdlc); exit_free_echo_skb: kfree(priv->echo_skb); exit_free_dma_buffers: @@ -1129,7 +1118,6 @@ static int grcan_close(struct net_device *dev) priv->can.echo_skb_max = 0; priv->can.echo_skb = NULL; kfree(priv->echo_skb); - kfree(priv->txdlc); return 0; } @@ -1447,7 +1435,6 @@ static netdev_tx_t grcan_start_xmit(struct sk_buff *skb, * can_put_echo_skb would be an error unless other measures are * taken. */ - priv->txdlc[slotindex] = cf->len; /* Store dlc for statistics */ can_put_echo_skb(skb, dev, slotindex, 0); /* Make sure everything is written before allowing hardware to diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index 5c589aa9dff8..5b677af5f2a4 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1294,7 +1294,8 @@ static unsigned int ican3_get_echo_skb(struct ican3_dev *mod) } cf = (struct can_frame *)skb->data; - dlc = cf->len; + if (!(cf->can_id & CAN_RTR_FLAG)) + dlc = cf->len; /* check flag whether this packet has to be looped back */ if (skb->pkt_type != PACKET_LOOPBACK) { diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 59b8284d00e5..5b5802fac772 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -448,9 +448,9 @@ static irqreturn_t mscan_isr(int irq, void *dev_id) continue; out_8(®s->cantbsel, mask); - stats->tx_bytes += in_8(®s->tx.dlr); + stats->tx_bytes += can_get_echo_skb(dev, entry->id, + NULL); stats->tx_packets++; - can_get_echo_skb(dev, entry->id, NULL); priv->tx_active &= ~mask; list_del(pos); } diff --git a/drivers/net/can/pch_can.c b/drivers/net/can/pch_can.c index b46f9cfb9e0a..888bef03de09 100644 --- a/drivers/net/can/pch_can.c +++ b/drivers/net/can/pch_can.c @@ -707,16 +707,13 @@ static void pch_can_tx_complete(struct net_device *ndev, u32 int_stat) { struct pch_can_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &(priv->ndev->stats); - u32 dlc; - can_get_echo_skb(ndev, int_stat - PCH_RX_OBJ_END - 1, NULL); + stats->tx_bytes += can_get_echo_skb(ndev, int_stat - PCH_RX_OBJ_END - 1, + NULL); + stats->tx_packets++; iowrite32(PCH_CMASK_RX_TX_GET | PCH_CMASK_CLRINTPND, &priv->regs->ifregs[1].cmask); pch_can_rw_msg_obj(&priv->regs->ifregs[1].creq, int_stat); - dlc = can_cc_dlc2len(ioread32(&priv->regs->ifregs[1].mcont) & - PCH_IF_MCONT_DLC); - stats->tx_bytes += dlc; - stats->tx_packets++; if (int_stat == PCH_TX_OBJ_END) netif_wake_queue(ndev); } diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index 216609198eac..b2dea360813d 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -266,10 +266,9 @@ static int pucan_handle_can_rx(struct peak_canfd_priv *priv, unsigned long flags; spin_lock_irqsave(&priv->echo_lock, flags); - can_get_echo_skb(priv->ndev, msg->client, NULL); /* count bytes of the echo instead of skb */ - stats->tx_bytes += cf_len; + stats->tx_bytes += can_get_echo_skb(priv->ndev, msg->client, NULL); stats->tx_packets++; /* restart tx queue (a slot is free) */ diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 62bbd58bfef8..33e37395379d 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -94,7 +94,6 @@ struct rcar_can_priv { struct rcar_can_regs __iomem *regs; struct clk *clk; struct clk *can_clk; - u8 tx_dlc[RCAR_CAN_FIFO_DEPTH]; u32 tx_head; u32 tx_tail; u8 clock_select; @@ -379,10 +378,11 @@ static void rcar_can_tx_done(struct net_device *ndev) if (priv->tx_head - priv->tx_tail <= unsent) break; stats->tx_packets++; - stats->tx_bytes += priv->tx_dlc[priv->tx_tail % - RCAR_CAN_FIFO_DEPTH]; - priv->tx_dlc[priv->tx_tail % RCAR_CAN_FIFO_DEPTH] = 0; - can_get_echo_skb(ndev, priv->tx_tail % RCAR_CAN_FIFO_DEPTH, NULL); + stats->tx_bytes += + can_get_echo_skb(ndev, + priv->tx_tail % RCAR_CAN_FIFO_DEPTH, + NULL); + priv->tx_tail++; netif_wake_queue(ndev); } @@ -612,7 +612,6 @@ static netdev_tx_t rcar_can_start_xmit(struct sk_buff *skb, writeb(cf->len, &priv->regs->mb[RCAR_CAN_TX_FIFO_MBX].dlc); - priv->tx_dlc[priv->tx_head % RCAR_CAN_FIFO_DEPTH] = cf->len; can_put_echo_skb(skb, ndev, priv->tx_head % RCAR_CAN_FIFO_DEPTH, 0); priv->tx_head++; /* Start Tx: write 0xff to the TFPCR register to increment diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index b1eded2f2c5d..d0e795f60338 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -502,7 +502,6 @@ struct rcar_canfd_channel { struct rcar_canfd_global *gpriv; /* Controller reference */ void __iomem *base; /* Register base address */ struct napi_struct napi; - u8 tx_len[RCANFD_FIFO_DEPTH]; /* For net stats */ u32 tx_head; /* Incremented on xmit */ u32 tx_tail; /* Incremented on xmit done */ u32 channel; /* Channel number */ @@ -1049,9 +1048,7 @@ static void rcar_canfd_tx_done(struct net_device *ndev) sent = priv->tx_tail % RCANFD_FIFO_DEPTH; stats->tx_packets++; - stats->tx_bytes += priv->tx_len[sent]; - priv->tx_len[sent] = 0; - can_get_echo_skb(ndev, sent, NULL); + stats->tx_bytes += can_get_echo_skb(ndev, sent, NULL); spin_lock_irqsave(&priv->tx_lock, flags); priv->tx_tail++; @@ -1461,7 +1458,6 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, RCANFD_C_CFDF(ch, RCANFD_CFFIFO_IDX, 0)); } - priv->tx_len[priv->tx_head % RCANFD_FIFO_DEPTH] = cf->len; can_put_echo_skb(skb, ndev, priv->tx_head % RCANFD_FIFO_DEPTH, 0); spin_lock_irqsave(&priv->tx_lock, flags); diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 4bf44d449987..966316479485 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -527,10 +527,8 @@ irqreturn_t sja1000_interrupt(int irq, void *dev_id) can_free_echo_skb(dev, 0, NULL); } else { /* transmission complete */ - stats->tx_bytes += - priv->read_reg(priv, SJA1000_FI) & 0xf; + stats->tx_bytes += can_get_echo_skb(dev, 0, NULL); stats->tx_packets++; - can_get_echo_skb(dev, 0, NULL); } netif_wake_queue(dev); can_led_event(dev, CAN_LED_EVENT_TX); diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index 5cf03458e948..d4c7ce998a34 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -290,6 +290,8 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf) if (!(cf->can_id & CAN_RTR_FLAG)) { for (i = 0; i < cf->len; i++) pos = hex_byte_pack_upper(pos, cf->data[i]); + + sl->dev->stats.tx_bytes += cf->len; } *pos++ = '\r'; @@ -306,7 +308,6 @@ static void slc_encaps(struct slcan *sl, struct can_frame *cf) actual = sl->tty->ops->write(sl->tty, sl->xbuff, pos - sl->xbuff); sl->xleft = (pos - sl->xbuff) - actual; sl->xhead = sl->xbuff + actual; - sl->dev->stats.tx_bytes += cf->len; } /* Write out any remaining transmit buffer. Scheduled when tty is writable */ diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index cfc1325aad10..d74e895bddf7 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -282,7 +282,10 @@ static int softing_handle_1(struct softing *card) skb = priv->can.echo_skb[priv->tx.echo_get]; if (skb) skb->tstamp = ktime; - can_get_echo_skb(netdev, priv->tx.echo_get, NULL); + ++netdev->stats.tx_packets; + netdev->stats.tx_bytes += + can_get_echo_skb(netdev, priv->tx.echo_get, + NULL); ++priv->tx.echo_get; if (priv->tx.echo_get >= TX_ECHO_SKB_MAX) priv->tx.echo_get = 0; @@ -290,9 +293,6 @@ static int softing_handle_1(struct softing *card) --priv->tx.pending; if (card->tx.pending) --card->tx.pending; - ++netdev->stats.tx_packets; - if (!(msg.can_id & CAN_RTR_FLAG)) - netdev->stats.tx_bytes += msg.len; } else { int ret; diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index 506625082b84..cfcc14fe3e42 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -153,7 +153,6 @@ struct hi3110_priv { u8 *spi_rx_buf; struct sk_buff *tx_skb; - int tx_len; struct workqueue_struct *wq; struct work_struct tx_work; @@ -166,6 +165,8 @@ struct hi3110_priv { #define HI3110_AFTER_SUSPEND_POWER 4 #define HI3110_AFTER_SUSPEND_RESTART 8 int restart_tx; + bool tx_busy; + struct regulator *power; struct regulator *transceiver; struct clk *clk; @@ -175,13 +176,13 @@ static void hi3110_clean(struct net_device *net) { struct hi3110_priv *priv = netdev_priv(net); - if (priv->tx_skb || priv->tx_len) + if (priv->tx_skb || priv->tx_busy) net->stats.tx_errors++; dev_kfree_skb(priv->tx_skb); - if (priv->tx_len) + if (priv->tx_busy) can_free_echo_skb(priv->net, 0, NULL); priv->tx_skb = NULL; - priv->tx_len = 0; + priv->tx_busy = false; } /* Note about handling of error return of hi3110_spi_trans: accessing @@ -369,7 +370,7 @@ static netdev_tx_t hi3110_hard_start_xmit(struct sk_buff *skb, struct hi3110_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; - if (priv->tx_skb || priv->tx_len) { + if (priv->tx_skb || priv->tx_busy) { dev_err(&spi->dev, "hard_xmit called while tx busy\n"); return NETDEV_TX_BUSY; } @@ -586,7 +587,7 @@ static void hi3110_tx_work_handler(struct work_struct *ws) } else { frame = (struct can_frame *)priv->tx_skb->data; hi3110_hw_tx(spi, frame); - priv->tx_len = 1 + frame->len; + priv->tx_busy = true; can_put_echo_skb(priv->tx_skb, net, 0, 0); priv->tx_skb = NULL; } @@ -721,14 +722,11 @@ static irqreturn_t hi3110_can_ist(int irq, void *dev_id) } } - if (priv->tx_len && statf & HI3110_STAT_TXMTY) { + if (priv->tx_busy && statf & HI3110_STAT_TXMTY) { net->stats.tx_packets++; - net->stats.tx_bytes += priv->tx_len - 1; + net->stats.tx_bytes += can_get_echo_skb(net, 0, NULL); can_led_event(net, CAN_LED_EVENT_TX); - if (priv->tx_len) { - can_get_echo_skb(net, 0, NULL); - priv->tx_len = 0; - } + priv->tx_busy = false; netif_wake_queue(net); } @@ -755,7 +753,7 @@ static int hi3110_open(struct net_device *net) priv->force_quit = 0; priv->tx_skb = NULL; - priv->tx_len = 0; + priv->tx_busy = false; ret = request_threaded_irq(spi->irq, NULL, hi3110_can_ist, flags, DEVICE_NAME, priv); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index 0da965da32cb..025e07cb7439 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -237,7 +237,6 @@ struct mcp251x_priv { u8 *spi_rx_buf; struct sk_buff *tx_skb; - int tx_len; struct workqueue_struct *wq; struct work_struct tx_work; @@ -250,6 +249,8 @@ struct mcp251x_priv { #define AFTER_SUSPEND_POWER 4 #define AFTER_SUSPEND_RESTART 8 int restart_tx; + bool tx_busy; + struct regulator *power; struct regulator *transceiver; struct clk *clk; @@ -272,13 +273,13 @@ static void mcp251x_clean(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); - if (priv->tx_skb || priv->tx_len) + if (priv->tx_skb || priv->tx_busy) net->stats.tx_errors++; dev_kfree_skb(priv->tx_skb); - if (priv->tx_len) + if (priv->tx_busy) can_free_echo_skb(priv->net, 0, NULL); priv->tx_skb = NULL; - priv->tx_len = 0; + priv->tx_busy = false; } /* Note about handling of error return of mcp251x_spi_trans: accessing @@ -785,7 +786,7 @@ static netdev_tx_t mcp251x_hard_start_xmit(struct sk_buff *skb, struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; - if (priv->tx_skb || priv->tx_len) { + if (priv->tx_skb || priv->tx_busy) { dev_warn(&spi->dev, "hard_xmit called while tx busy\n"); return NETDEV_TX_BUSY; } @@ -1010,7 +1011,7 @@ static void mcp251x_tx_work_handler(struct work_struct *ws) if (frame->len > CAN_FRAME_MAX_DATA_LEN) frame->len = CAN_FRAME_MAX_DATA_LEN; mcp251x_hw_tx(spi, frame, 0); - priv->tx_len = 1 + frame->len; + priv->tx_busy = true; can_put_echo_skb(priv->tx_skb, net, 0, 0); priv->tx_skb = NULL; } @@ -1176,12 +1177,12 @@ static irqreturn_t mcp251x_can_ist(int irq, void *dev_id) break; if (intf & CANINTF_TX) { - net->stats.tx_packets++; - net->stats.tx_bytes += priv->tx_len - 1; can_led_event(net, CAN_LED_EVENT_TX); - if (priv->tx_len) { - can_get_echo_skb(net, 0, NULL); - priv->tx_len = 0; + if (priv->tx_busy) { + net->stats.tx_packets++; + net->stats.tx_bytes += can_get_echo_skb(net, 0, + NULL); + priv->tx_busy = false; } netif_wake_queue(net); } @@ -1208,7 +1209,7 @@ static int mcp251x_open(struct net_device *net) priv->force_quit = 0; priv->tx_skb = NULL; - priv->tx_len = 0; + priv->tx_busy = false; if (!dev_fwnode(&spi->dev)) flags = IRQF_TRIGGER_FALLING; diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index e18868a43ce8..25d6d81ab4f4 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -661,11 +661,8 @@ static irqreturn_t sun4i_can_interrupt(int irq, void *dev_id) if (isrc & SUN4I_INT_TBUF_VLD) { /* transmission complete interrupt */ - stats->tx_bytes += - readl(priv->base + - SUN4I_REG_RBUF_RBACK_START_ADDR) & 0xf; + stats->tx_bytes += can_get_echo_skb(dev, 0, NULL); stats->tx_packets++; - can_get_echo_skb(dev, 0, NULL); netif_wake_queue(dev); can_led_event(dev, CAN_LED_EVENT_TX); } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index c9b6adf5c1ec..7bedceffdfa3 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -230,7 +230,6 @@ struct ems_tx_urb_context { struct ems_usb *dev; u32 echo_index; - u8 dlc; }; struct ems_usb { @@ -517,9 +516,8 @@ static void ems_usb_write_bulk_callback(struct urb *urb) /* transmission complete interrupt */ netdev->stats.tx_packets++; - netdev->stats.tx_bytes += context->dlc; - - can_get_echo_skb(netdev, context->echo_index, NULL); + netdev->stats.tx_bytes += can_get_echo_skb(netdev, context->echo_index, + NULL); /* Release context */ context->echo_index = MAX_TX_URBS; @@ -805,7 +803,6 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne context->dev = dev; context->echo_index = i; - context->dlc = cf->len; usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf, size, ems_usb_write_bulk_callback, context); diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 9ac7ee44b6e3..286daaaea0b8 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -183,7 +183,6 @@ struct esd_usb2_net_priv; struct esd_tx_urb_context { struct esd_usb2_net_priv *priv; u32 echo_index; - int len; /* CAN payload length */ }; struct esd_usb2 { @@ -357,8 +356,8 @@ static void esd_usb2_tx_done_msg(struct esd_usb2_net_priv *priv, if (!msg->msg.txdone.status) { stats->tx_packets++; - stats->tx_bytes += context->len; - can_get_echo_skb(netdev, context->echo_index, NULL); + stats->tx_bytes += can_get_echo_skb(netdev, context->echo_index, + NULL); } else { stats->tx_errors++; can_free_echo_skb(netdev, context->echo_index, NULL); @@ -783,7 +782,6 @@ static netdev_tx_t esd_usb2_start_xmit(struct sk_buff *skb, context->priv = priv; context->echo_index = i; - context->len = cf->len; /* hnd must not be 0 - MSB is stripped in txdone handling */ msg->msg.tx.hnd = 0x80000000 | i; /* returned in TX done message */ diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 1b400de00f51..03b012963c20 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -357,9 +357,6 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) goto resubmit_urb; } - netdev->stats.tx_packets++; - netdev->stats.tx_bytes += hf->can_dlc; - txc = gs_get_tx_context(dev, hf->echo_id); /* bad devices send bad echo_ids. */ @@ -370,7 +367,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) goto resubmit_urb; } - can_get_echo_skb(netdev, hf->echo_id, NULL); + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += can_get_echo_skb(netdev, hf->echo_id, + NULL); gs_free_tx_context(txc); diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h index 390b6bde883c..3a49257f9fa6 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -77,7 +77,6 @@ struct kvaser_usb_dev_card_data { struct kvaser_usb_tx_urb_context { struct kvaser_usb_net_priv *priv; u32 echo_index; - int dlc; }; struct kvaser_usb { @@ -162,8 +161,8 @@ struct kvaser_usb_dev_ops { void (*dev_read_bulk_callback)(struct kvaser_usb *dev, void *buf, int len); void *(*dev_frame_to_cmd)(const struct kvaser_usb_net_priv *priv, - const struct sk_buff *skb, int *frame_len, - int *cmd_len, u16 transid); + const struct sk_buff *skb, int *cmd_len, + u16 transid); }; struct kvaser_usb_dev_cfg { diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 3e682ef43f8e..c4b4d3d0a387 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -565,7 +565,7 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb, goto freeurb; } - buf = dev->ops->dev_frame_to_cmd(priv, skb, &context->dlc, &cmd_len, + buf = dev->ops->dev_frame_to_cmd(priv, skb, &cmd_len, context->echo_index); if (!buf) { stats->tx_dropped++; diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c index bc902da9c6eb..a26823c5b62a 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -1114,6 +1114,7 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, struct kvaser_usb_tx_urb_context *context; struct kvaser_usb_net_priv *priv; unsigned long irq_flags; + unsigned int len; bool one_shot_fail = false; bool is_err_frame = false; u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd); @@ -1140,21 +1141,22 @@ static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev, } context = &priv->tx_contexts[transid % dev->max_tx_urbs]; - if (!one_shot_fail && !is_err_frame) { - struct net_device_stats *stats = &priv->netdev->stats; - - stats->tx_packets++; - stats->tx_bytes += can_fd_dlc2len(context->dlc); - } spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags); - can_get_echo_skb(priv->netdev, context->echo_index, NULL); + len = can_get_echo_skb(priv->netdev, context->echo_index, NULL); context->echo_index = dev->max_tx_urbs; --priv->active_tx_contexts; netif_wake_queue(priv->netdev); spin_unlock_irqrestore(&priv->tx_contexts_lock, irq_flags); + + if (!one_shot_fail && !is_err_frame) { + struct net_device_stats *stats = &priv->netdev->stats; + + stats->tx_packets++; + stats->tx_bytes += len; + } } static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev, @@ -1373,8 +1375,8 @@ static void kvaser_usb_hydra_handle_cmd(const struct kvaser_usb *dev, static void * kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv, - const struct sk_buff *skb, int *frame_len, - int *cmd_len, u16 transid) + const struct sk_buff *skb, int *cmd_len, + u16 transid) { struct kvaser_usb *dev = priv->dev; struct kvaser_cmd_ext *cmd; @@ -1386,8 +1388,6 @@ kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv, u32 kcan_id; u32 kcan_header; - *frame_len = nbr_of_bytes; - cmd = kcalloc(1, sizeof(struct kvaser_cmd_ext), GFP_ATOMIC); if (!cmd) return NULL; @@ -1453,8 +1453,8 @@ kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv, static void * kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv, - const struct sk_buff *skb, int *frame_len, - int *cmd_len, u16 transid) + const struct sk_buff *skb, int *cmd_len, + u16 transid) { struct kvaser_usb *dev = priv->dev; struct kvaser_cmd *cmd; @@ -1462,8 +1462,6 @@ kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv, u32 flags; u32 id; - *frame_len = cf->len; - cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC); if (!cmd) return NULL; @@ -1497,7 +1495,7 @@ kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv, cmd->tx_can.id = cpu_to_le32(id); cmd->tx_can.flags = flags; - memcpy(cmd->tx_can.data, cf->data, *frame_len); + memcpy(cmd->tx_can.data, cf->data, cf->len); return cmd; } @@ -2005,17 +2003,17 @@ static void kvaser_usb_hydra_read_bulk_callback(struct kvaser_usb *dev, static void * kvaser_usb_hydra_frame_to_cmd(const struct kvaser_usb_net_priv *priv, - const struct sk_buff *skb, int *frame_len, - int *cmd_len, u16 transid) + const struct sk_buff *skb, int *cmd_len, + u16 transid) { void *buf; if (priv->dev->card_data.capabilities & KVASER_USB_HYDRA_CAP_EXT_CMD) - buf = kvaser_usb_hydra_frame_to_cmd_ext(priv, skb, frame_len, - cmd_len, transid); + buf = kvaser_usb_hydra_frame_to_cmd_ext(priv, skb, cmd_len, + transid); else - buf = kvaser_usb_hydra_frame_to_cmd_std(priv, skb, frame_len, - cmd_len, transid); + buf = kvaser_usb_hydra_frame_to_cmd_std(priv, skb, cmd_len, + transid); return buf; } diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c index 891271af7616..c805b999c543 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -389,16 +389,14 @@ static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_32mhz = { static void * kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv, - const struct sk_buff *skb, int *frame_len, - int *cmd_len, u16 transid) + const struct sk_buff *skb, int *cmd_len, + u16 transid) { struct kvaser_usb *dev = priv->dev; struct kvaser_cmd *cmd; u8 *cmd_tx_can_flags = NULL; /* GCC */ struct can_frame *cf = (struct can_frame *)skb->data; - *frame_len = cf->len; - cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC); if (cmd) { cmd->u.tx_can.tid = transid & 0xff; @@ -654,12 +652,11 @@ static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev, priv->can.state = CAN_STATE_ERROR_ACTIVE; } - stats->tx_packets++; - stats->tx_bytes += context->dlc; - spin_lock_irqsave(&priv->tx_contexts_lock, flags); - can_get_echo_skb(priv->netdev, context->echo_index, NULL); + stats->tx_packets++; + stats->tx_bytes += can_get_echo_skb(priv->netdev, + context->echo_index, NULL); context->echo_index = dev->max_tx_urbs; --priv->active_tx_contexts; netif_wake_queue(priv->netdev); diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 4d20ea860ea8..77bddff86252 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -64,7 +64,6 @@ struct mcba_usb_ctx { struct mcba_priv *priv; u32 ndx; - u8 dlc; bool can; }; @@ -184,13 +183,10 @@ static inline struct mcba_usb_ctx *mcba_usb_get_free_ctx(struct mcba_priv *priv, ctx = &priv->tx_context[i]; ctx->ndx = i; - if (cf) { + if (cf) ctx->can = true; - ctx->dlc = cf->len; - } else { + else ctx->can = false; - ctx->dlc = 0; - } atomic_dec(&priv->free_ctx_cnt); break; @@ -236,10 +232,10 @@ static void mcba_usb_write_bulk_callback(struct urb *urb) return; netdev->stats.tx_packets++; - netdev->stats.tx_bytes += ctx->dlc; + netdev->stats.tx_bytes += can_get_echo_skb(netdev, ctx->ndx, + NULL); can_led_event(netdev, CAN_LED_EVENT_TX); - can_get_echo_skb(netdev, ctx->ndx, NULL); } if (urb->status) diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 6107fef9f4a0..b850ff8fe4bd 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -291,6 +291,7 @@ static void peak_usb_write_bulk_callback(struct urb *urb) struct peak_tx_urb_context *context = urb->context; struct peak_usb_device *dev; struct net_device *netdev; + int tx_bytes; BUG_ON(!context); @@ -305,10 +306,6 @@ static void peak_usb_write_bulk_callback(struct urb *urb) /* check tx status */ switch (urb->status) { case 0: - /* transmission complete */ - netdev->stats.tx_packets++; - netdev->stats.tx_bytes += context->data_len; - /* prevent tx timeout */ netif_trans_update(netdev); break; @@ -327,12 +324,17 @@ static void peak_usb_write_bulk_callback(struct urb *urb) } /* should always release echo skb and corresponding context */ - can_get_echo_skb(netdev, context->echo_index, NULL); + tx_bytes = can_get_echo_skb(netdev, context->echo_index, NULL); context->echo_index = PCAN_USB_MAX_TX_URBS; - /* do wakeup tx queue in case of success only */ - if (!urb->status) + if (!urb->status) { + /* transmission complete */ + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += tx_bytes; + + /* do wakeup tx queue in case of success only */ netif_wake_queue(netdev); + } } /* @@ -344,7 +346,6 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, struct peak_usb_device *dev = netdev_priv(netdev); struct peak_tx_urb_context *context = NULL; struct net_device_stats *stats = &netdev->stats; - struct canfd_frame *cfd = (struct canfd_frame *)skb->data; struct urb *urb; u8 *obuf; int i, err; @@ -378,9 +379,6 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb, context->echo_index = i; - /* Note: this works with CANFD frames too */ - context->data_len = cfd->len; - usb_anchor_urb(urb, &dev->tx_submitted); can_put_echo_skb(skb, netdev, context->echo_index, 0); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.h b/drivers/net/can/usb/peak_usb/pcan_usb_core.h index daa19f57e742..f60af573a2e0 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.h +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.h @@ -99,7 +99,6 @@ struct peak_time_ref { struct peak_tx_urb_context { struct peak_usb_device *dev; u32 echo_index; - u8 data_len; struct urb *urb; }; diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index 388899019955..c7c41d1fd038 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -259,7 +259,6 @@ struct ucan_priv; /* Context Information for transmission URBs */ struct ucan_urb_context { struct ucan_priv *up; - u8 dlc; bool allocated; }; @@ -637,7 +636,7 @@ static void ucan_tx_complete_msg(struct ucan_priv *up, { unsigned long flags; u16 count, i; - u8 echo_index, dlc; + u8 echo_index; u16 len = le16_to_cpu(m->len); struct ucan_urb_context *context; @@ -661,7 +660,6 @@ static void ucan_tx_complete_msg(struct ucan_priv *up, /* gather information from the context */ context = &up->context_array[echo_index]; - dlc = READ_ONCE(context->dlc); /* Release context and restart queue if necessary. * Also check if the context was allocated @@ -674,8 +672,8 @@ static void ucan_tx_complete_msg(struct ucan_priv *up, UCAN_TX_COMPLETE_SUCCESS) { /* update statistics */ up->netdev->stats.tx_packets++; - up->netdev->stats.tx_bytes += dlc; - can_get_echo_skb(up->netdev, echo_index, NULL); + up->netdev->stats.tx_bytes += + can_get_echo_skb(up->netdev, echo_index, NULL); } else { up->netdev->stats.tx_dropped++; can_free_echo_skb(up->netdev, echo_index, NULL); @@ -1089,8 +1087,6 @@ static struct urb *ucan_prepare_tx_urb(struct ucan_priv *up, } m->len = cpu_to_le16(mlen); - context->dlc = cf->len; - m->subtype = echo_index; /* build the urb */ diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index d0ef1478cf0a..431af1ec1e3c 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -114,7 +114,6 @@ struct usb_8dev_tx_urb_context { struct usb_8dev_priv *priv; u32 echo_index; - u8 dlc; }; /* Structure to hold all of our device specific stuff */ @@ -581,9 +580,7 @@ static void usb_8dev_write_bulk_callback(struct urb *urb) urb->status); netdev->stats.tx_packets++; - netdev->stats.tx_bytes += context->dlc; - - can_get_echo_skb(netdev, context->echo_index, NULL); + netdev->stats.tx_bytes += can_get_echo_skb(netdev, context->echo_index, NULL); can_led_event(netdev, CAN_LED_EVENT_TX); @@ -654,7 +651,6 @@ static netdev_tx_t usb_8dev_start_xmit(struct sk_buff *skb, context->priv = priv; context->echo_index = i; - context->dlc = cf->len; usb_fill_bulk_urb(urb, priv->udev, usb_sndbulkpipe(priv->udev, USB_8DEV_ENDP_DATA_TX), diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c index 067705e2850b..c42f18845b02 100644 --- a/drivers/net/can/vcan.c +++ b/drivers/net/can/vcan.c @@ -87,13 +87,14 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) { struct canfd_frame *cfd = (struct canfd_frame *)skb->data; struct net_device_stats *stats = &dev->stats; - int loop; + int loop, len; if (can_dropped_invalid_skb(dev, skb)) return NETDEV_TX_OK; + len = cfd->can_id & CAN_RTR_FLAG ? 0 : cfd->len; stats->tx_packets++; - stats->tx_bytes += cfd->len; + stats->tx_bytes += len; /* set flag whether this packet has to be looped back */ loop = skb->pkt_type == PACKET_LOOPBACK; @@ -105,7 +106,7 @@ static netdev_tx_t vcan_tx(struct sk_buff *skb, struct net_device *dev) * CAN core already did the echo for us */ stats->rx_packets++; - stats->rx_bytes += cfd->len; + stats->rx_bytes += len; } consume_skb(skb); return NETDEV_TX_OK; diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 8861a7d875e7..47ccc15a3486 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -62,7 +62,7 @@ static netdev_tx_t vxcan_xmit(struct sk_buff *skb, struct net_device *dev) skb->dev = peer; skb->ip_summed = CHECKSUM_UNNECESSARY; - len = cfd->len; + len = cfd->can_id & CAN_RTR_FLAG ? 0 : cfd->len; if (netif_rx_ni(skb) == NET_RX_SUCCESS) { srcstats->tx_packets++; srcstats->tx_bytes += len; diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index d311bc369a39..fdb22b00674a 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -21,8 +21,9 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx, - unsigned int *frame_len_ptr); +unsigned int __must_check can_get_echo_skb(struct net_device *dev, + unsigned int idx, + unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); -- cgit v1.2.3 From c9e1d8ed304cc6106c3241add170193995953325 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 14 Dec 2021 01:02:23 +0900 Subject: can: dev: replace can_priv::ctrlmode_static by can_get_static_ctrlmode() The statically enabled features of a CAN controller can be retrieved using below formula: | u32 ctrlmode_static = priv->ctrlmode & ~priv->ctrlmode_supported; As such, there is no need to store this information. This patch remove the field ctrlmode_static of struct can_priv and provides, in replacement, the inline function can_get_static_ctrlmode() which returns the same value. Link: https://lore.kernel.org/all/20211213160226.56219-2-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/dev.c | 5 +++-- drivers/net/can/dev/netlink.c | 2 +- include/linux/can/dev.h | 7 +++++-- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 4845ae6456e1..c192f25f9695 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -296,6 +296,7 @@ EXPORT_SYMBOL_GPL(free_candev); int can_change_mtu(struct net_device *dev, int new_mtu) { struct can_priv *priv = netdev_priv(dev); + u32 ctrlmode_static = can_get_static_ctrlmode(priv); /* Do not allow changing the MTU while running */ if (dev->flags & IFF_UP) @@ -305,7 +306,7 @@ int can_change_mtu(struct net_device *dev, int new_mtu) switch (new_mtu) { case CAN_MTU: /* 'CANFD-only' controllers can not switch to CAN_MTU */ - if (priv->ctrlmode_static & CAN_CTRLMODE_FD) + if (ctrlmode_static & CAN_CTRLMODE_FD) return -EINVAL; priv->ctrlmode &= ~CAN_CTRLMODE_FD; @@ -314,7 +315,7 @@ int can_change_mtu(struct net_device *dev, int new_mtu) case CANFD_MTU: /* check for potential CANFD ability */ if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD) && - !(priv->ctrlmode_static & CAN_CTRLMODE_FD)) + !(ctrlmode_static & CAN_CTRLMODE_FD)) return -EINVAL; priv->ctrlmode |= CAN_CTRLMODE_FD; diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 95cca4e5251f..26c336808be5 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -211,7 +211,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], if (dev->flags & IFF_UP) return -EBUSY; cm = nla_data(data[IFLA_CAN_CTRLMODE]); - ctrlstatic = priv->ctrlmode_static; + ctrlstatic = can_get_static_ctrlmode(priv); maskedflags = cm->flags & cm->mask; /* check whether provided bits are allowed to be passed */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 45f19d9db5ca..92e2d69462f0 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -69,7 +69,6 @@ struct can_priv { /* CAN controller features - see include/uapi/linux/can/netlink.h */ u32 ctrlmode; /* current options setting */ u32 ctrlmode_supported; /* options that can be modified by netlink */ - u32 ctrlmode_static; /* static enabled options for driver/hardware */ int restart_ms; struct delayed_work restart_work; @@ -139,13 +138,17 @@ static inline void can_set_static_ctrlmode(struct net_device *dev, /* alloc_candev() succeeded => netdev_priv() is valid at this point */ priv->ctrlmode = static_mode; - priv->ctrlmode_static = static_mode; /* override MTU which was set by default in can_setup()? */ if (static_mode & CAN_CTRLMODE_FD) dev->mtu = CANFD_MTU; } +static inline u32 can_get_static_ctrlmode(struct can_priv *priv) +{ + return priv->ctrlmode & ~priv->ctrlmode_supported; +} + void can_setup(struct net_device *dev); struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max, -- cgit v1.2.3 From 7d4a101c0bd3c6e5c6e45c705a54f7bc8f6c128d Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 14 Dec 2021 01:02:24 +0900 Subject: can: dev: add sanity check in can_set_static_ctrlmode() Previous patch removed can_priv::ctrlmode_static to replace it with can_get_static_ctrlmode(). A condition sine qua non for this to work is that the controller static modes should never be set in can_priv::ctrlmode_supported (c.f. the comment on can_priv::ctrlmode_supported which states that it is for "options that can be *modified* by netlink"). Also, this condition is already correctly fulfilled by all existing drivers which rely on the ctrlmode_static feature. Nonetheless, we added an extra safeguard in can_set_static_ctrlmode() to return an error value and to warn the developer who would be adventurous enough to set to static a given feature that is already set to supported. The drivers which rely on the static controller mode are then updated to check the return value of can_set_static_ctrlmode(). Link: https://lore.kernel.org/all/20211213160226.56219-3-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/m_can/m_can.c | 10 +++++++--- drivers/net/can/rcar/rcar_canfd.c | 4 +++- include/linux/can/dev.h | 11 +++++++++-- 3 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index ae2349420983..5b47cd867783 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -1456,7 +1456,7 @@ static bool m_can_niso_supported(struct m_can_classdev *cdev) static int m_can_dev_setup(struct m_can_classdev *cdev) { struct net_device *dev = cdev->net; - int m_can_version; + int m_can_version, err; m_can_version = m_can_check_core_release(cdev); /* return if unsupported version */ @@ -1486,7 +1486,9 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) switch (cdev->version) { case 30: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */ - can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); + err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); + if (err) + return err; cdev->can.bittiming_const = cdev->bit_timing ? cdev->bit_timing : &m_can_bittiming_const_30X; @@ -1496,7 +1498,9 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) break; case 31: /* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */ - can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); + err = can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO); + if (err) + return err; cdev->can.bittiming_const = cdev->bit_timing ? cdev->bit_timing : &m_can_bittiming_const_31X; diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index d0e795f60338..82cc71d5ee10 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1699,7 +1699,9 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, &rcar_canfd_data_bittiming_const; /* Controller starts in CAN FD only mode */ - can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD); + err = can_set_static_ctrlmode(ndev, CAN_CTRLMODE_FD); + if (err) + goto fail; priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING; } else { /* Controller starts in Classical CAN only mode */ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 92e2d69462f0..fff3f70df697 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -131,17 +131,24 @@ static inline s32 can_get_relative_tdco(const struct can_priv *priv) } /* helper to define static CAN controller features at device creation time */ -static inline void can_set_static_ctrlmode(struct net_device *dev, - u32 static_mode) +static inline int __must_check can_set_static_ctrlmode(struct net_device *dev, + u32 static_mode) { struct can_priv *priv = netdev_priv(dev); /* alloc_candev() succeeded => netdev_priv() is valid at this point */ + if (priv->ctrlmode_supported & static_mode) { + netdev_warn(dev, + "Controller features can not be supported and static at the same time\n"); + return -EINVAL; + } priv->ctrlmode = static_mode; /* override MTU which was set by default in can_setup()? */ if (static_mode & CAN_CTRLMODE_FD) dev->mtu = CANFD_MTU; + + return 0; } static inline u32 can_get_static_ctrlmode(struct can_priv *priv) -- cgit v1.2.3 From 5fe1be81efd28bf2afcac218f23118dca6b1b648 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Tue, 14 Dec 2021 01:02:25 +0900 Subject: can: dev: reorder struct can_priv members for better packing Save eight bytes of holes on x86-64 architectures by reordering the members of struct can_priv. Before: | $ pahole -C can_priv drivers/net/can/dev/dev.o | struct can_priv { | struct net_device * dev; /* 0 8 */ | struct can_device_stats can_stats; /* 8 24 */ | const struct can_bittiming_const * bittiming_const; /* 32 8 */ | const struct can_bittiming_const * data_bittiming_const; /* 40 8 */ | struct can_bittiming bittiming; /* 48 32 */ | /* --- cacheline 1 boundary (64 bytes) was 16 bytes ago --- */ | struct can_bittiming data_bittiming; /* 80 32 */ | const struct can_tdc_const * tdc_const; /* 112 8 */ | struct can_tdc tdc; /* 120 12 */ | /* --- cacheline 2 boundary (128 bytes) was 4 bytes ago --- */ | unsigned int bitrate_const_cnt; /* 132 4 */ | const u32 * bitrate_const; /* 136 8 */ | const u32 * data_bitrate_const; /* 144 8 */ | unsigned int data_bitrate_const_cnt; /* 152 4 */ | u32 bitrate_max; /* 156 4 */ | struct can_clock clock; /* 160 4 */ | unsigned int termination_const_cnt; /* 164 4 */ | const u16 * termination_const; /* 168 8 */ | u16 termination; /* 176 2 */ | | /* XXX 6 bytes hole, try to pack */ | | struct gpio_desc * termination_gpio; /* 184 8 */ | /* --- cacheline 3 boundary (192 bytes) --- */ | u16 termination_gpio_ohms[2]; /* 192 4 */ | enum can_state state; /* 196 4 */ | u32 ctrlmode; /* 200 4 */ | u32 ctrlmode_supported; /* 204 4 */ | int restart_ms; /* 208 4 */ | | /* XXX 4 bytes hole, try to pack */ | | struct delayed_work restart_work; /* 216 88 */ | | /* XXX last struct has 4 bytes of padding */ | | /* --- cacheline 4 boundary (256 bytes) was 48 bytes ago --- */ | int (*do_set_bittiming)(struct net_device *); /* 304 8 */ | int (*do_set_data_bittiming)(struct net_device *); /* 312 8 */ | /* --- cacheline 5 boundary (320 bytes) --- */ | int (*do_set_mode)(struct net_device *, enum can_mode); /* 320 8 */ | int (*do_set_termination)(struct net_device *, u16); /* 328 8 */ | int (*do_get_state)(const struct net_device *, enum can_state *); /* 336 8 */ | int (*do_get_berr_counter)(const struct net_device *, struct can_berr_counter *); /* 344 8 */ | unsigned int echo_skb_max; /* 352 4 */ | | /* XXX 4 bytes hole, try to pack */ | | struct sk_buff * * echo_skb; /* 360 8 */ | | /* size: 368, cachelines: 6, members: 32 */ | /* sum members: 354, holes: 3, sum holes: 14 */ | /* paddings: 1, sum paddings: 4 */ | /* last cacheline: 48 bytes */ | }; After: | $ pahole -C can_priv drivers/net/can/dev/dev.o | struct can_priv { | struct net_device * dev; /* 0 8 */ | struct can_device_stats can_stats; /* 8 24 */ | const struct can_bittiming_const * bittiming_const; /* 32 8 */ | const struct can_bittiming_const * data_bittiming_const; /* 40 8 */ | struct can_bittiming bittiming; /* 48 32 */ | /* --- cacheline 1 boundary (64 bytes) was 16 bytes ago --- */ | struct can_bittiming data_bittiming; /* 80 32 */ | const struct can_tdc_const * tdc_const; /* 112 8 */ | struct can_tdc tdc; /* 120 12 */ | /* --- cacheline 2 boundary (128 bytes) was 4 bytes ago --- */ | unsigned int bitrate_const_cnt; /* 132 4 */ | const u32 * bitrate_const; /* 136 8 */ | const u32 * data_bitrate_const; /* 144 8 */ | unsigned int data_bitrate_const_cnt; /* 152 4 */ | u32 bitrate_max; /* 156 4 */ | struct can_clock clock; /* 160 4 */ | unsigned int termination_const_cnt; /* 164 4 */ | const u16 * termination_const; /* 168 8 */ | u16 termination; /* 176 2 */ | | /* XXX 6 bytes hole, try to pack */ | | struct gpio_desc * termination_gpio; /* 184 8 */ | /* --- cacheline 3 boundary (192 bytes) --- */ | u16 termination_gpio_ohms[2]; /* 192 4 */ | unsigned int echo_skb_max; /* 196 4 */ | struct sk_buff * * echo_skb; /* 200 8 */ | enum can_state state; /* 208 4 */ | u32 ctrlmode; /* 212 4 */ | u32 ctrlmode_supported; /* 216 4 */ | int restart_ms; /* 220 4 */ | struct delayed_work restart_work; /* 224 88 */ | | /* XXX last struct has 4 bytes of padding */ | | /* --- cacheline 4 boundary (256 bytes) was 56 bytes ago --- */ | int (*do_set_bittiming)(struct net_device *); /* 312 8 */ | /* --- cacheline 5 boundary (320 bytes) --- */ | int (*do_set_data_bittiming)(struct net_device *); /* 320 8 */ | int (*do_set_mode)(struct net_device *, enum can_mode); /* 328 8 */ | int (*do_set_termination)(struct net_device *, u16); /* 336 8 */ | int (*do_get_state)(const struct net_device *, enum can_state *); /* 344 8 */ | int (*do_get_berr_counter)(const struct net_device *, struct can_berr_counter *); /* 352 8 */ | | /* size: 360, cachelines: 6, members: 32 */ | /* sum members: 354, holes: 1, sum holes: 6 */ | /* paddings: 1, sum paddings: 4 */ | /* last cacheline: 40 bytes */ | }; Link: https://lore.kernel.org/all/20211213160226.56219-4-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index fff3f70df697..c2ea47f30046 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -64,6 +64,9 @@ struct can_priv { struct gpio_desc *termination_gpio; u16 termination_gpio_ohms[CAN_TERMINATION_GPIO_MAX]; + unsigned int echo_skb_max; + struct sk_buff **echo_skb; + enum can_state state; /* CAN controller features - see include/uapi/linux/can/netlink.h */ @@ -83,9 +86,6 @@ struct can_priv { struct can_berr_counter *bec); int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); - unsigned int echo_skb_max; - struct sk_buff **echo_skb; - #ifdef CONFIG_CAN_LEDS struct led_trigger *tx_led_trig; char tx_led_trig_name[CAN_LED_NAME_SZ]; -- cgit v1.2.3 From c6af53f038aa32cec12e8a305ba07c7ef168f1b0 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Tue, 4 Jan 2022 12:07:00 +0000 Subject: net: mdio: add helpers to extract clause 45 regad and devad fields Add a couple of helpers and definitions to extract the clause 45 regad and devad fields from the regnum passed into MDIO drivers. Tested-by: Daniel Golle Reviewed-by: Andrew Lunn Signed-off-by: Russell King (Oracle) Signed-off-by: Daniel Golle Signed-off-by: David S. Miller --- include/linux/mdio.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 9f3587a61e14..ecac96d52e01 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -7,6 +7,7 @@ #define __LINUX_MDIO_H__ #include +#include #include /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit @@ -14,6 +15,7 @@ */ #define MII_ADDR_C45 (1<<30) #define MII_DEVADDR_C45_SHIFT 16 +#define MII_DEVADDR_C45_MASK GENMASK(20, 16) #define MII_REGADDR_C45_MASK GENMASK(15, 0) struct gpio_desc; @@ -381,6 +383,16 @@ static inline u32 mdiobus_c45_addr(int devad, u16 regnum) return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; } +static inline u16 mdiobus_c45_regad(u32 regnum) +{ + return FIELD_GET(MII_REGADDR_C45_MASK, regnum); +} + +static inline u16 mdiobus_c45_devad(u32 regnum) +{ + return FIELD_GET(MII_DEVADDR_C45_MASK, regnum); +} + static inline int __mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, u16 regnum) { -- cgit v1.2.3 From 01ec4a2e8f01f027a0f06cad237c935da8d643bf Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Sat, 3 Jul 2021 00:23:39 +0200 Subject: headers/deps: USB: Optimize dependencies, remove The header is used over 1,400 times in a typical distro build, but few of its users actually need the full header. -------------------------------------------------------------------- | Combined, preprocessed C code size of header, without line markers, | with comments stripped: ------------------------- before: | #include | LOC: 7,078 | headers: 172 after: | #include | LOC: 812 | headers: 38 Remove it and add it to the places that need it. Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/ch9.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/usb/ch9.h b/include/linux/usb/ch9.h index 1cffa34740b0..969e7dba6358 100644 --- a/include/linux/usb/ch9.h +++ b/include/linux/usb/ch9.h @@ -33,7 +33,6 @@ #ifndef __LINUX_USB_CH9_H #define __LINUX_USB_CH9_H -#include #include /* USB 3.2 SuperSpeed Plus phy signaling rate generation and lane count */ @@ -45,6 +44,8 @@ enum usb_ssp_rate { USB_SSP_GEN_2x2, }; +struct device; + extern const char *usb_ep_type_string(int ep_type); extern const char *usb_speed_string(enum usb_device_speed speed); extern enum usb_device_speed usb_get_maximum_speed(struct device *dev); -- cgit v1.2.3 From edce22e19bfa86efa2522d041d6367f2f099e8ed Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 5 Jan 2022 09:05:15 -0800 Subject: block: move rq_list macros to blk-mq.h Move the request list macros to the header file that defines that struct they operate on. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220105170518.3181469-2-kbusch@kernel.org Signed-off-by: Jens Axboe --- fs/io_uring.c | 2 +- include/linux/blk-mq.h | 29 +++++++++++++++++++++++++++++ include/linux/blkdev.h | 29 ----------------------------- 3 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index c4f217613f56..42bbbd34f45e 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -57,7 +57,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 550996cf419c..bf64b94cd64e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -216,6 +216,35 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_dma_dir(rq) \ (op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE) +#define rq_list_add(listptr, rq) do { \ + (rq)->rq_next = *(listptr); \ + *(listptr) = rq; \ +} while (0) + +#define rq_list_pop(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) { \ + __req = *(listptr); \ + *(listptr) = __req->rq_next; \ + } \ + __req; \ +}) + +#define rq_list_peek(listptr) \ +({ \ + struct request *__req = NULL; \ + if ((listptr) && *(listptr)) \ + __req = *(listptr); \ + __req; \ +}) + +#define rq_list_for_each(listptr, pos) \ + for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) + +#define rq_list_next(rq) (rq)->rq_next +#define rq_list_empty(list) ((list) == (struct request *) NULL) + enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 22746b2d6825..9c95df26fc26 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1339,33 +1339,4 @@ struct io_comp_batch { #define DEFINE_IO_COMP_BATCH(name) struct io_comp_batch name = { } -#define rq_list_add(listptr, rq) do { \ - (rq)->rq_next = *(listptr); \ - *(listptr) = rq; \ -} while (0) - -#define rq_list_pop(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) { \ - __req = *(listptr); \ - *(listptr) = __req->rq_next; \ - } \ - __req; \ -}) - -#define rq_list_peek(listptr) \ -({ \ - struct request *__req = NULL; \ - if ((listptr) && *(listptr)) \ - __req = *(listptr); \ - __req; \ -}) - -#define rq_list_for_each(listptr, pos) \ - for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) - -#define rq_list_next(rq) (rq)->rq_next -#define rq_list_empty(list) ((list) == (struct request *) NULL) - #endif /* _LINUX_BLKDEV_H */ -- cgit v1.2.3 From 3764fd05e1f89530e2ee5cbff0b638f2b1141b90 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 5 Jan 2022 09:05:16 -0800 Subject: block: introduce rq_list_for_each_safe macro While iterating a list, a particular request may need to be removed for special handling. Provide an iterator that can safely handle that. Reviewed-by: Christoph Hellwig Signed-off-by: Keith Busch Link: https://lore.kernel.org/r/20220105170518.3181469-3-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index bf64b94cd64e..1467f0fa2142 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -242,6 +242,10 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_list_for_each(listptr, pos) \ for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos)) +#define rq_list_for_each_safe(listptr, pos, nxt) \ + for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos); \ + pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL) + #define rq_list_next(rq) (rq)->rq_next #define rq_list_empty(list) ((list) == (struct request *) NULL) -- cgit v1.2.3 From d2528be7a8b09af9796a270debd14101a72bb552 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 5 Jan 2022 09:05:17 -0800 Subject: block: introduce rq_list_move When iterating a list, a particular request may need to be moved for special handling. Provide a helper function to achieve that so drivers don't need to reimplement rqlist manipulation. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20220105170518.3181469-4-kbusch@kernel.org Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1467f0fa2142..f40a05ecca4a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -249,6 +249,23 @@ static inline unsigned short req_get_ioprio(struct request *req) #define rq_list_next(rq) (rq)->rq_next #define rq_list_empty(list) ((list) == (struct request *) NULL) +/** + * rq_list_move() - move a struct request from one list to another + * @src: The source list @rq is currently in + * @dst: The destination list that @rq will be appended to + * @rq: The request to move + * @prev: The request preceding @rq in @src (NULL if @rq is the head) + */ +static void inline rq_list_move(struct request **src, struct request **dst, + struct request *rq, struct request *prev) +{ + if (prev) + prev->rq_next = rq->rq_next; + else + *src = rq->rq_next; + rq_list_add(dst, rq); +} + enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ -- cgit v1.2.3 From d53ad5d8b218a885e95080d4d3d556b16b91b1b9 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Mon, 3 Jan 2022 16:08:09 +0100 Subject: xdp: Move conversion to xdp_frame out of map functions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit All map redirect functions except XSK maps convert xdp_buff to xdp_frame before enqueueing it. So move this conversion of out the map functions and into xdp_do_redirect(). This removes a bit of duplicated code, but more importantly it makes it possible to support caller-allocated xdp_frame structures, which will be added in a subsequent commit. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220103150812.87914-5-toke@redhat.com --- include/linux/bpf.h | 20 ++++++++++---------- kernel/bpf/cpumap.c | 8 +------- kernel/bpf/devmap.c | 32 +++++++++++--------------------- net/core/filter.c | 24 +++++++++++++++++------- 4 files changed, 39 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 26753139d5b4..6e947cd91152 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1669,17 +1669,17 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ -struct xdp_buff; +struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(void); -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); @@ -1688,7 +1688,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, bool exclude_ingress); void __cpu_map_flush(void); -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); @@ -1866,26 +1866,26 @@ static inline void __dev_flush(void) { } -struct xdp_buff; +struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; @@ -1913,7 +1913,7 @@ static inline void __cpu_map_flush(void) } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, - struct xdp_buff *xdp, + struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 0421061d95f1..b3e6b9422238 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -746,15 +746,9 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) list_add(&bq->flush_node, flush_list); } -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { - struct xdp_frame *xdpf; - - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - /* Info needed when constructing SKB on remote CPU */ xdpf->dev_rx = dev_rx; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 6feea293ff10..fe019dbdb3f0 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -467,24 +467,19 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, bq->q[bq->count++] = xdpf; } -static inline int __xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct xdp_frame *xdpf; int err; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; - err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + err = xdp_ok_fwd_dev(dev, xdpf->len); if (unlikely(err)) return err; - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - bq_enqueue(dev, xdpf, dev_rx, xdp_prog); return 0; } @@ -520,27 +515,27 @@ static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev return act; } -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { - return __xdp_enqueue(dev, xdp, dev_rx, NULL); + return __xdp_enqueue(dev, xdpf, dev_rx, NULL); } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { struct net_device *dev = dst->dev; - return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog); + return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); } -static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp) +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) { if (!obj || !obj->dev->netdev_ops->ndo_xdp_xmit) return false; - if (xdp_ok_fwd_dev(obj->dev, xdp->data_end - xdp->data)) + if (xdp_ok_fwd_dev(obj->dev, xdpf->len)) return false; return true; @@ -586,14 +581,13 @@ static int get_upper_ifindexes(struct net_device *dev, int *indexes) return n; } -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *dst, *last_dst = NULL; int excluded_devices[1+MAX_NEST_DEV]; struct hlist_head *head; - struct xdp_frame *xdpf; int num_excluded = 0; unsigned int i; int err; @@ -603,15 +597,11 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, excluded_devices[num_excluded++] = dev_rx->ifindex; } - xdpf = xdp_convert_buff_to_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { for (i = 0; i < map->max_entries; i++) { dst = rcu_dereference_check(dtab->netdev_map[i], rcu_read_lock_bh_held()); - if (!is_valid_dst(dst, xdp)) + if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) @@ -634,7 +624,7 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, head = dev_map_index_hash(dtab, i); hlist_for_each_entry_rcu(dst, head, index_hlist, lockdep_is_held(&dtab->index_lock)) { - if (!is_valid_dst(dst, xdp)) + if (!is_valid_dst(dst, xdpf)) continue; if (is_ifindex_excluded(excluded_devices, num_excluded, diff --git a/net/core/filter.c b/net/core/filter.c index cac2be559ab0..e2b83056246c 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3964,12 +3964,24 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; + struct xdp_frame *xdpf; struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; + if (map_type == BPF_MAP_TYPE_XSKMAP) { + err = __xsk_map_redirect(fwd, xdp); + goto out; + } + + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) { + err = -EOVERFLOW; + goto err; + } + switch (map_type) { case BPF_MAP_TYPE_DEVMAP: fallthrough; @@ -3977,17 +3989,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, map = READ_ONCE(ri->map); if (unlikely(map)) { WRITE_ONCE(ri->map, NULL); - err = dev_map_enqueue_multi(xdp, dev, map, + err = dev_map_enqueue_multi(xdpf, dev, map, ri->flags & BPF_F_EXCLUDE_INGRESS); } else { - err = dev_map_enqueue(fwd, xdp, dev); + err = dev_map_enqueue(fwd, xdpf, dev); } break; case BPF_MAP_TYPE_CPUMAP: - err = cpu_map_enqueue(fwd, xdp, dev); - break; - case BPF_MAP_TYPE_XSKMAP: - err = __xsk_map_redirect(fwd, xdp); + err = cpu_map_enqueue(fwd, xdpf, dev); break; case BPF_MAP_TYPE_UNSPEC: if (map_id == INT_MAX) { @@ -3996,7 +4005,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, err = -EINVAL; break; } - err = dev_xdp_enqueue(fwd, xdp, dev); + err = dev_xdp_enqueue(fwd, xdpf, dev); break; } fallthrough; @@ -4004,6 +4013,7 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, err = -EBADRQC; } +out: if (unlikely(err)) goto err; -- cgit v1.2.3 From 1372d34ccf6dd480332b2bcb2fd59a2b9a0df415 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Mon, 3 Jan 2022 16:08:10 +0100 Subject: xdp: Add xdp_do_redirect_frame() for pre-computed xdp_frames MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add an xdp_do_redirect_frame() variant which supports pre-computed xdp_frame structures. This will be used in bpf_prog_run() to avoid having to write to the xdp_frame structure when the XDP program doesn't modify the frame boundaries. Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20220103150812.87914-6-toke@redhat.com --- include/linux/filter.h | 4 ++++ net/core/filter.c | 65 +++++++++++++++++++++++++++++++++++++++++--------- 2 files changed, 58 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 60eec80fa1d4..71fa57b88bfc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1019,6 +1019,10 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); +int xdp_do_redirect_frame(struct net_device *dev, + struct xdp_buff *xdp, + struct xdp_frame *xdpf, + struct bpf_prog *prog); void xdp_do_flush(void); /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as diff --git a/net/core/filter.c b/net/core/filter.c index e2b83056246c..4603b7cd3cd1 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3957,26 +3957,44 @@ u32 xdp_master_redirect(struct xdp_buff *xdp) } EXPORT_SYMBOL_GPL(xdp_master_redirect); -int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, - struct bpf_prog *xdp_prog) +static inline int __xdp_do_redirect_xsk(struct bpf_redirect_info *ri, + struct net_device *dev, + struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) { - struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); enum bpf_map_type map_type = ri->map_type; void *fwd = ri->tgt_value; u32 map_id = ri->map_id; - struct xdp_frame *xdpf; - struct bpf_map *map; int err; ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; - if (map_type == BPF_MAP_TYPE_XSKMAP) { - err = __xsk_map_redirect(fwd, xdp); - goto out; - } + err = __xsk_map_redirect(fwd, xdp); + if (unlikely(err)) + goto err; + + _trace_xdp_redirect_map(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index); + return 0; +err: + _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); + return err; +} + +static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri, + struct net_device *dev, + struct xdp_frame *xdpf, + struct bpf_prog *xdp_prog) +{ + enum bpf_map_type map_type = ri->map_type; + void *fwd = ri->tgt_value; + u32 map_id = ri->map_id; + struct bpf_map *map; + int err; + + ri->map_id = 0; /* Valid map id idr range: [1,INT_MAX[ */ + ri->map_type = BPF_MAP_TYPE_UNSPEC; - xdpf = xdp_convert_buff_to_frame(xdp); if (unlikely(!xdpf)) { err = -EOVERFLOW; goto err; @@ -4013,7 +4031,6 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, err = -EBADRQC; } -out: if (unlikely(err)) goto err; @@ -4023,8 +4040,34 @@ err: _trace_xdp_redirect_map_err(dev, xdp_prog, fwd, map_type, map_id, ri->tgt_index, err); return err; } + +int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, + struct bpf_prog *xdp_prog) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + enum bpf_map_type map_type = ri->map_type; + + if (map_type == BPF_MAP_TYPE_XSKMAP) + return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); + + return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp), + xdp_prog); +} EXPORT_SYMBOL_GPL(xdp_do_redirect); +int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, + struct xdp_frame *xdpf, struct bpf_prog *xdp_prog) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + enum bpf_map_type map_type = ri->map_type; + + if (map_type == BPF_MAP_TYPE_XSKMAP) + return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog); + + return __xdp_do_redirect_frame(ri, dev, xdpf, xdp_prog); +} +EXPORT_SYMBOL_GPL(xdp_do_redirect_frame); + static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, -- cgit v1.2.3 From ae16d059f8c9409eba0c412639def0494765b761 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 26 Oct 2021 18:22:44 +0200 Subject: mm/slub: Make object_err() static There are no callers outside of mm/slub.c anymore. Move freelist_corrupted() that calls object_err() to avoid a need for forward declaration. Signed-off-by: Vlastimil Babka Reviewed-by: Roman Gushchin --- include/linux/slub_def.h | 3 --- mm/slub.c | 30 +++++++++++++++--------------- 2 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 0fa751b946fa..1ef68d4de9c0 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -156,9 +156,6 @@ static inline void sysfs_slab_release(struct kmem_cache *s) } #endif -void object_err(struct kmem_cache *s, struct page *page, - u8 *object, char *reason); - void *fixup_red_left(struct kmem_cache *s, void *p); static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, diff --git a/mm/slub.c b/mm/slub.c index abe7db581d68..2ccb1c71fc36 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -822,20 +822,6 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...) va_end(args); } -static bool freelist_corrupted(struct kmem_cache *s, struct page *page, - void **freelist, void *nextfree) -{ - if ((s->flags & SLAB_CONSISTENCY_CHECKS) && - !check_valid_pointer(s, page, nextfree) && freelist) { - object_err(s, page, *freelist, "Freechain corrupt"); - *freelist = NULL; - slab_fix(s, "Isolate corrupted freechain"); - return true; - } - - return false; -} - static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) { unsigned int off; /* Offset of last byte */ @@ -875,7 +861,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) dump_stack(); } -void object_err(struct kmem_cache *s, struct page *page, +static void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason) { if (slab_add_kunit_errors()) @@ -886,6 +872,20 @@ void object_err(struct kmem_cache *s, struct page *page, add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } +static bool freelist_corrupted(struct kmem_cache *s, struct page *page, + void **freelist, void *nextfree) +{ + if ((s->flags & SLAB_CONSISTENCY_CHECKS) && + !check_valid_pointer(s, page, nextfree) && freelist) { + object_err(s, page, *freelist, "Freechain corrupt"); + *freelist = NULL; + slab_fix(s, "Isolate corrupted freechain"); + return true; + } + + return false; +} + static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, const char *fmt, ...) { -- cgit v1.2.3 From d122019bf061cccc4583eb9ad40bf58c2fe517be Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Oct 2021 14:45:51 +0100 Subject: mm: Split slab into its own type Make struct slab independent of struct page. It still uses the underlying memory in struct page for storing slab-specific data, but slab and slub can now be weaned off using struct page directly. Some of the wrapper functions (slab_address() and slab_order()) still need to cast to struct folio, but this is a significant disentanglement. [ vbabka@suse.cz: Rebase on folios, use folio instead of page where possible. Do not duplicate flags field in struct slab, instead make the related accessors go through slab_folio(). For testing pfmemalloc use the folio_*_active flag accessors directly so the PageSlabPfmemalloc wrappers can be removed later. Make folio_slab() expect only folio_test_slab() == true folios and virt_to_slab() return NULL when folio_test_slab() == false. Move struct slab to mm/slab.h. Don't represent with struct slab pages that are not true slab pages, but just a compound page obtained directly rom page allocator (with large kmalloc() for SLUB and SLOB). ] Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Vlastimil Babka Acked-by: Johannes Weiner Reviewed-by: Roman Gushchin --- include/linux/mm_types.h | 10 +-- mm/slab.h | 167 +++++++++++++++++++++++++++++++++++++++++++++++ mm/slub.c | 8 +-- 3 files changed, 176 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c3a6e6209600..1ae3537c7920 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -56,11 +56,11 @@ struct mem_cgroup; * in each subpage, but you may need to restore some of their values * afterwards. * - * SLUB uses cmpxchg_double() to atomically update its freelist and - * counters. That requires that freelist & counters be adjacent and - * double-word aligned. We align all struct pages to double-word - * boundaries, and ensure that 'freelist' is aligned within the - * struct. + * SLUB uses cmpxchg_double() to atomically update its freelist and counters. + * That requires that freelist & counters in struct slab be adjacent and + * double-word aligned. Because struct slab currently just reinterprets the + * bits of struct page, we align all struct pages to double-word boundaries, + * and ensure that 'freelist' is aligned within struct slab. */ #ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE #define _struct_page_alignment __aligned(2 * sizeof(unsigned long)) diff --git a/mm/slab.h b/mm/slab.h index 56ad7eea3ddf..0e67a8cb7f80 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -5,6 +5,173 @@ * Internal slab definitions */ +/* Reuses the bits in struct page */ +struct slab { + unsigned long __page_flags; + union { + struct list_head slab_list; + struct { /* Partial pages */ + struct slab *next; +#ifdef CONFIG_64BIT + int slabs; /* Nr of slabs left */ +#else + short int slabs; +#endif + }; + struct rcu_head rcu_head; + }; + struct kmem_cache *slab_cache; /* not slob */ + /* Double-word boundary */ + void *freelist; /* first free object */ + union { + void *s_mem; /* slab: first object */ + unsigned long counters; /* SLUB */ + struct { /* SLUB */ + unsigned inuse:16; + unsigned objects:15; + unsigned frozen:1; + }; + }; + + union { + unsigned int active; /* SLAB */ + int units; /* SLOB */ + }; + atomic_t __page_refcount; +#ifdef CONFIG_MEMCG + unsigned long memcg_data; +#endif +}; + +#define SLAB_MATCH(pg, sl) \ + static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl)) +SLAB_MATCH(flags, __page_flags); +SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */ +SLAB_MATCH(slab_list, slab_list); +SLAB_MATCH(rcu_head, rcu_head); +SLAB_MATCH(slab_cache, slab_cache); +SLAB_MATCH(s_mem, s_mem); +SLAB_MATCH(active, active); +SLAB_MATCH(_refcount, __page_refcount); +#ifdef CONFIG_MEMCG +SLAB_MATCH(memcg_data, memcg_data); +#endif +#undef SLAB_MATCH +static_assert(sizeof(struct slab) <= sizeof(struct page)); + +/** + * folio_slab - Converts from folio to slab. + * @folio: The folio. + * + * Currently struct slab is a different representation of a folio where + * folio_test_slab() is true. + * + * Return: The slab which contains this folio. + */ +#define folio_slab(folio) (_Generic((folio), \ + const struct folio *: (const struct slab *)(folio), \ + struct folio *: (struct slab *)(folio))) + +/** + * slab_folio - The folio allocated for a slab + * @slab: The slab. + * + * Slabs are allocated as folios that contain the individual objects and are + * using some fields in the first struct page of the folio - those fields are + * now accessed by struct slab. It is occasionally necessary to convert back to + * a folio in order to communicate with the rest of the mm. Please use this + * helper function instead of casting yourself, as the implementation may change + * in the future. + */ +#define slab_folio(s) (_Generic((s), \ + const struct slab *: (const struct folio *)s, \ + struct slab *: (struct folio *)s)) + +/** + * page_slab - Converts from first struct page to slab. + * @p: The first (either head of compound or single) page of slab. + * + * A temporary wrapper to convert struct page to struct slab in situations where + * we know the page is the compound head, or single order-0 page. + * + * Long-term ideally everything would work with struct slab directly or go + * through folio to struct slab. + * + * Return: The slab which contains this page + */ +#define page_slab(p) (_Generic((p), \ + const struct page *: (const struct slab *)(p), \ + struct page *: (struct slab *)(p))) + +/** + * slab_page - The first struct page allocated for a slab + * @slab: The slab. + * + * A convenience wrapper for converting slab to the first struct page of the + * underlying folio, to communicate with code not yet converted to folio or + * struct slab. + */ +#define slab_page(s) folio_page(slab_folio(s), 0) + +/* + * If network-based swap is enabled, sl*b must keep track of whether pages + * were allocated from pfmemalloc reserves. + */ +static inline bool slab_test_pfmemalloc(const struct slab *slab) +{ + return folio_test_active((struct folio *)slab_folio(slab)); +} + +static inline void slab_set_pfmemalloc(struct slab *slab) +{ + folio_set_active(slab_folio(slab)); +} + +static inline void slab_clear_pfmemalloc(struct slab *slab) +{ + folio_clear_active(slab_folio(slab)); +} + +static inline void __slab_clear_pfmemalloc(struct slab *slab) +{ + __folio_clear_active(slab_folio(slab)); +} + +static inline void *slab_address(const struct slab *slab) +{ + return folio_address(slab_folio(slab)); +} + +static inline int slab_nid(const struct slab *slab) +{ + return folio_nid(slab_folio(slab)); +} + +static inline pg_data_t *slab_pgdat(const struct slab *slab) +{ + return folio_pgdat(slab_folio(slab)); +} + +static inline struct slab *virt_to_slab(const void *addr) +{ + struct folio *folio = virt_to_folio(addr); + + if (!folio_test_slab(folio)) + return NULL; + + return folio_slab(folio); +} + +static inline int slab_order(const struct slab *slab) +{ + return folio_order((struct folio *)slab_folio(slab)); +} + +static inline size_t slab_size(const struct slab *slab) +{ + return PAGE_SIZE << slab_order(slab); +} + #ifdef CONFIG_SLOB /* * Common fields provided in kmem_cache by all slab allocators diff --git a/mm/slub.c b/mm/slub.c index 2ccb1c71fc36..a211d96011ba 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3787,7 +3787,7 @@ static unsigned int slub_min_objects; * requested a higher minimum order then we start with that one instead of * the smallest order which will fit the object. */ -static inline unsigned int slab_order(unsigned int size, +static inline unsigned int calc_slab_order(unsigned int size, unsigned int min_objects, unsigned int max_order, unsigned int fract_leftover) { @@ -3851,7 +3851,7 @@ static inline int calculate_order(unsigned int size) fraction = 16; while (fraction >= 4) { - order = slab_order(size, min_objects, + order = calc_slab_order(size, min_objects, slub_max_order, fraction); if (order <= slub_max_order) return order; @@ -3864,14 +3864,14 @@ static inline int calculate_order(unsigned int size) * We were unable to place multiple objects in a slab. Now * lets see if we can place a single object there. */ - order = slab_order(size, 1, slub_max_order, 1); + order = calc_slab_order(size, 1, slub_max_order, 1); if (order <= slub_max_order) return order; /* * Doh this slab cannot be placed using slub_max_order. */ - order = slab_order(size, 1, MAX_ORDER, 1); + order = calc_slab_order(size, 1, MAX_ORDER, 1); if (order < MAX_ORDER) return order; return -ENOSYS; -- cgit v1.2.3 From 0b3eb091d5759479d44cb793fad2c51ea06bdcec Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Oct 2021 14:45:56 +0100 Subject: mm: Convert check_heap_object() to use struct slab Ensure that we're not seeing a tail page inside __check_heap_object() by converting to a slab instead of a page. Take the opportunity to mark the slab as const since we're not modifying it. Also move the declaration of __check_heap_object() to mm/slab.h so it's not available to the wider kernel. [ vbabka@suse.cz: in check_heap_object() only convert to struct slab for actual PageSlab pages; use folio as intermediate step instead of page ] Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Vlastimil Babka Reviewed-by: Roman Gushchin --- include/linux/slab.h | 8 -------- mm/slab.c | 14 +++++++------- mm/slab.h | 11 +++++++++++ mm/slub.c | 10 +++++----- mm/usercopy.c | 13 +++++++------ 5 files changed, 30 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab.h b/include/linux/slab.h index 181045148b06..367366f1d1ff 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -189,14 +189,6 @@ bool kmem_valid_obj(void *object); void kmem_dump_obj(void *object); #endif -#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR -void __check_heap_object(const void *ptr, unsigned long n, struct page *page, - bool to_user); -#else -static inline void __check_heap_object(const void *ptr, unsigned long n, - struct page *page, bool to_user) { } -#endif - /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. diff --git a/mm/slab.c b/mm/slab.c index 44bc1fcd1393..38fcd3f496df 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -372,8 +372,8 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp) static int slab_max_order = SLAB_MAX_ORDER_LO; static bool slab_max_order_set __initdata; -static inline void *index_to_obj(struct kmem_cache *cache, struct page *page, - unsigned int idx) +static inline void *index_to_obj(struct kmem_cache *cache, + const struct page *page, unsigned int idx) { return page->s_mem + cache->size * idx; } @@ -4166,8 +4166,8 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer, * Returns NULL if check passes, otherwise const char * to name of cache * to indicate an error. */ -void __check_heap_object(const void *ptr, unsigned long n, struct page *page, - bool to_user) +void __check_heap_object(const void *ptr, unsigned long n, + const struct slab *slab, bool to_user) { struct kmem_cache *cachep; unsigned int objnr; @@ -4176,15 +4176,15 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, ptr = kasan_reset_tag(ptr); /* Find and validate object. */ - cachep = page->slab_cache; - objnr = obj_to_index(cachep, page, (void *)ptr); + cachep = slab->slab_cache; + objnr = obj_to_index(cachep, slab_page(slab), (void *)ptr); BUG_ON(objnr >= cachep->num); /* Find offset within object. */ if (is_kfence_address(ptr)) offset = ptr - kfence_object_start(ptr); else - offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); + offset = ptr - index_to_obj(cachep, slab_page(slab), objnr) - obj_offset(cachep); /* Allow address range falling entirely within usercopy region. */ if (offset >= cachep->useroffset && diff --git a/mm/slab.h b/mm/slab.h index 9ae9f6c3d1cb..039babfde2fe 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -812,4 +812,15 @@ struct kmem_obj_info { void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab); #endif +#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR +void __check_heap_object(const void *ptr, unsigned long n, + const struct slab *slab, bool to_user); +#else +static inline +void __check_heap_object(const void *ptr, unsigned long n, + const struct slab *slab, bool to_user) +{ +} +#endif + #endif /* MM_SLAB_H */ diff --git a/mm/slub.c b/mm/slub.c index 8e9667815f81..8b82188849ae 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4485,8 +4485,8 @@ EXPORT_SYMBOL(__kmalloc_node); * Returns NULL if check passes, otherwise const char * to name of cache * to indicate an error. */ -void __check_heap_object(const void *ptr, unsigned long n, struct page *page, - bool to_user) +void __check_heap_object(const void *ptr, unsigned long n, + const struct slab *slab, bool to_user) { struct kmem_cache *s; unsigned int offset; @@ -4495,10 +4495,10 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, ptr = kasan_reset_tag(ptr); /* Find object and usable object size. */ - s = page->slab_cache; + s = slab->slab_cache; /* Reject impossible pointers. */ - if (ptr < page_address(page)) + if (ptr < slab_address(slab)) usercopy_abort("SLUB object not in SLUB page?!", NULL, to_user, 0, n); @@ -4506,7 +4506,7 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, if (is_kfence) offset = ptr - kfence_object_start(ptr); else - offset = (ptr - page_address(page)) % s->size; + offset = (ptr - slab_address(slab)) % s->size; /* Adjust for redzone and reject if within the redzone. */ if (!is_kfence && kmem_cache_debug_flags(s, SLAB_RED_ZONE)) { diff --git a/mm/usercopy.c b/mm/usercopy.c index b3de3c4eefba..d0d268135d96 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -20,6 +20,7 @@ #include #include #include +#include "slab.h" /* * Checks if a given pointer and length is contained by the current @@ -223,7 +224,7 @@ static inline void check_page_span(const void *ptr, unsigned long n, static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { - struct page *page; + struct folio *folio; if (!virt_addr_valid(ptr)) return; @@ -231,16 +232,16 @@ static inline void check_heap_object(const void *ptr, unsigned long n, /* * When CONFIG_HIGHMEM=y, kmap_to_page() will give either the * highmem page or fallback to virt_to_page(). The following - * is effectively a highmem-aware virt_to_head_page(). + * is effectively a highmem-aware virt_to_slab(). */ - page = compound_head(kmap_to_page((void *)ptr)); + folio = page_folio(kmap_to_page((void *)ptr)); - if (PageSlab(page)) { + if (folio_test_slab(folio)) { /* Check slab allocator for flags and size. */ - __check_heap_object(ptr, n, page, to_user); + __check_heap_object(ptr, n, folio_slab(folio), to_user); } else { /* Verify object does not incorrectly span multiple pages. */ - check_page_span(ptr, n, page, to_user); + check_page_span(ptr, n, folio_page(folio, 0), to_user); } } -- cgit v1.2.3 From bb192ed9aa7191a5d65548f82c42b6750d65f569 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Wed, 3 Nov 2021 15:39:59 +0100 Subject: mm/slub: Convert most struct page to struct slab by spatch The majority of conversion from struct page to struct slab in SLUB internals can be delegated to a coccinelle semantic patch. This includes renaming of variables with 'page' in name to 'slab', and similar. Big thanks to Julia Lawall and Luis Chamberlain for help with coccinelle. // Options: --include-headers --no-includes --smpl-spacing include/linux/slub_def.h mm/slub.c // Note: needs coccinelle 1.1.1 to avoid breaking whitespace, and ocaml for the // embedded script // build list of functions to exclude from applying the next rule @initialize:ocaml@ @@ let ok_function p = not (List.mem (List.hd p).current_element ["nearest_obj";"obj_to_index";"objs_per_slab_page";"__slab_lock";"__slab_unlock";"free_nonslab_page";"kmalloc_large_node"]) // convert the type from struct page to struct page in all functions except the // list from previous rule // this also affects struct kmem_cache_cpu, but that's ok @@ position p : script:ocaml() { ok_function p }; @@ - struct page@p + struct slab // in struct kmem_cache_cpu, change the name from page to slab // the type was already converted by the previous rule @@ @@ struct kmem_cache_cpu { ... -struct slab *page; +struct slab *slab; ... } // there are many places that use c->page which is now c->slab after the // previous rule @@ struct kmem_cache_cpu *c; @@ -c->page +c->slab @@ @@ struct kmem_cache { ... - unsigned int cpu_partial_pages; + unsigned int cpu_partial_slabs; ... } @@ struct kmem_cache *s; @@ - s->cpu_partial_pages + s->cpu_partial_slabs @@ @@ static void - setup_page_debug( + setup_slab_debug( ...) {...} @@ @@ - setup_page_debug( + setup_slab_debug( ...); // for all functions (with exceptions), change any "struct slab *page" // parameter to "struct slab *slab" in the signature, and generally all // occurences of "page" to "slab" in the body - with some special cases. @@ identifier fn !~ "free_nonslab_page|obj_to_index|objs_per_slab_page|nearest_obj"; @@ fn(..., - struct slab *page + struct slab *slab ,...) { <... - page + slab ...> } // similar to previous but the param is called partial_page @@ identifier fn; @@ fn(..., - struct slab *partial_page + struct slab *partial_slab ,...) { <... - partial_page + partial_slab ...> } // similar to previous but for functions that take pointer to struct page ptr @@ identifier fn; @@ fn(..., - struct slab **ret_page + struct slab **ret_slab ,...) { <... - ret_page + ret_slab ...> } // functions converted by previous rules that were temporarily called using // slab_page(E) so we want to remove the wrapper now that they accept struct // slab ptr directly @@ identifier fn =~ "slab_free|do_slab_free"; expression E; @@ fn(..., - slab_page(E) + E ,...) // similar to previous but for another pattern @@ identifier fn =~ "slab_pad_check|check_object"; @@ fn(..., - folio_page(folio, 0) + slab ,...) // functions that were returning struct page ptr and now will return struct // slab ptr, including slab_page() wrapper removal @@ identifier fn =~ "allocate_slab|new_slab"; expression E; @@ static -struct slab * +struct slab * fn(...) { <... - slab_page(E) + E ...> } // rename any former struct page * declarations @@ @@ struct slab * ( - page + slab | - partial_page + partial_slab | - oldpage + oldslab ) ; // this has to be separate from previous rule as page and page2 appear at the // same line @@ @@ struct slab * -page2 +slab2 ; // similar but with initial assignment @@ expression E; @@ struct slab * ( - page + slab | - flush_page + flush_slab | - discard_page + slab_to_discard | - page_to_unfreeze + slab_to_unfreeze ) = E; // convert most of struct page to struct slab usage inside functions (with // exceptions), including specific variable renames @@ identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node"; expression E; @@ fn(...) { <... ( - int pages; + int slabs; | - int pages = E; + int slabs = E; | - page + slab | - flush_page + flush_slab | - partial_page + partial_slab | - oldpage->pages + oldslab->slabs | - oldpage + oldslab | - unsigned int nr_pages; + unsigned int nr_slabs; | - nr_pages + nr_slabs | - unsigned int partial_pages = E; + unsigned int partial_slabs = E; | - partial_pages + partial_slabs ) ...> } // this has to be split out from the previous rule so that lines containing // multiple matching changes will be fully converted @@ identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node"; @@ fn(...) { <... ( - slab->pages + slab->slabs | - pages + slabs | - page2 + slab2 | - discard_page + slab_to_discard | - page_to_unfreeze + slab_to_unfreeze ) ...> } // after we simply changed all occurences of page to slab, some usages need // adjustment for slab-specific functions, or use slab_page() wrapper @@ identifier fn !~ "nearest_obj|obj_to_index|objs_per_slab_page|__slab_(un)*lock|__free_slab|free_nonslab_page|kmalloc_large_node"; @@ fn(...) { <... ( - page_slab(slab) + slab | - kasan_poison_slab(slab) + kasan_poison_slab(slab_page(slab)) | - page_address(slab) + slab_address(slab) | - page_size(slab) + slab_size(slab) | - PageSlab(slab) + folio_test_slab(slab_folio(slab)) | - page_to_nid(slab) + slab_nid(slab) | - compound_order(slab) + slab_order(slab) ) ...> } Signed-off-by: Vlastimil Babka Reviewed-by: Roman Gushchin Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Julia Lawall Cc: Luis Chamberlain --- include/linux/slub_def.h | 6 +- mm/slub.c | 872 +++++++++++++++++++++++------------------------ 2 files changed, 439 insertions(+), 439 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 1ef68d4de9c0..00d99afe1c0e 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -48,9 +48,9 @@ enum stat_item { struct kmem_cache_cpu { void **freelist; /* Pointer to next available object */ unsigned long tid; /* Globally unique transaction id */ - struct page *page; /* The slab from which we are allocating */ + struct slab *slab; /* The slab from which we are allocating */ #ifdef CONFIG_SLUB_CPU_PARTIAL - struct page *partial; /* Partially allocated frozen slabs */ + struct slab *partial; /* Partially allocated frozen slabs */ #endif local_lock_t lock; /* Protects the fields above */ #ifdef CONFIG_SLUB_STATS @@ -100,7 +100,7 @@ struct kmem_cache { /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; /* Number of per cpu partial pages to keep around */ - unsigned int cpu_partial_pages; + unsigned int cpu_partial_slabs; #endif struct kmem_cache_order_objects oo; diff --git a/mm/slub.c b/mm/slub.c index c369806084e1..e89208f3197a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -417,7 +417,7 @@ static inline unsigned int oo_objects(struct kmem_cache_order_objects x) #ifdef CONFIG_SLUB_CPU_PARTIAL static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) { - unsigned int nr_pages; + unsigned int nr_slabs; s->cpu_partial = nr_objects; @@ -427,8 +427,8 @@ static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) * growth of the list. For simplicity we assume that the pages will * be half-full. */ - nr_pages = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo)); - s->cpu_partial_pages = nr_pages; + nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo)); + s->cpu_partial_slabs = nr_slabs; } #else static inline void @@ -456,16 +456,16 @@ static __always_inline void __slab_unlock(struct slab *slab) __bit_spin_unlock(PG_locked, &page->flags); } -static __always_inline void slab_lock(struct page *page, unsigned long *flags) +static __always_inline void slab_lock(struct slab *slab, unsigned long *flags) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_save(*flags); - __slab_lock(page_slab(page)); + __slab_lock(slab); } -static __always_inline void slab_unlock(struct page *page, unsigned long *flags) +static __always_inline void slab_unlock(struct slab *slab, unsigned long *flags) { - __slab_unlock(page_slab(page)); + __slab_unlock(slab); if (IS_ENABLED(CONFIG_PREEMPT_RT)) local_irq_restore(*flags); } @@ -475,7 +475,7 @@ static __always_inline void slab_unlock(struct page *page, unsigned long *flags) * by an _irqsave() lock variant. Except on PREEMPT_RT where locks are different * so we disable interrupts as part of slab_[un]lock(). */ -static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page, +static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab, void *freelist_old, unsigned long counters_old, void *freelist_new, unsigned long counters_new, const char *n) @@ -485,7 +485,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page #if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) if (s->flags & __CMPXCHG_DOUBLE) { - if (cmpxchg_double(&page->freelist, &page->counters, + if (cmpxchg_double(&slab->freelist, &slab->counters, freelist_old, counters_old, freelist_new, counters_new)) return true; @@ -495,15 +495,15 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page /* init to 0 to prevent spurious warnings */ unsigned long flags = 0; - slab_lock(page, &flags); - if (page->freelist == freelist_old && - page->counters == counters_old) { - page->freelist = freelist_new; - page->counters = counters_new; - slab_unlock(page, &flags); + slab_lock(slab, &flags); + if (slab->freelist == freelist_old && + slab->counters == counters_old) { + slab->freelist = freelist_new; + slab->counters = counters_new; + slab_unlock(slab, &flags); return true; } - slab_unlock(page, &flags); + slab_unlock(slab, &flags); } cpu_relax(); @@ -516,7 +516,7 @@ static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page return false; } -static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, +static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab, void *freelist_old, unsigned long counters_old, void *freelist_new, unsigned long counters_new, const char *n) @@ -524,7 +524,7 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, #if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \ defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE) if (s->flags & __CMPXCHG_DOUBLE) { - if (cmpxchg_double(&page->freelist, &page->counters, + if (cmpxchg_double(&slab->freelist, &slab->counters, freelist_old, counters_old, freelist_new, counters_new)) return true; @@ -534,16 +534,16 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, unsigned long flags; local_irq_save(flags); - __slab_lock(page_slab(page)); - if (page->freelist == freelist_old && - page->counters == counters_old) { - page->freelist = freelist_new; - page->counters = counters_new; - __slab_unlock(page_slab(page)); + __slab_lock(slab); + if (slab->freelist == freelist_old && + slab->counters == counters_old) { + slab->freelist = freelist_new; + slab->counters = counters_new; + __slab_unlock(slab); local_irq_restore(flags); return true; } - __slab_unlock(page_slab(page)); + __slab_unlock(slab); local_irq_restore(flags); } @@ -562,14 +562,14 @@ static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; static DEFINE_RAW_SPINLOCK(object_map_lock); static void __fill_map(unsigned long *obj_map, struct kmem_cache *s, - struct page *page) + struct slab *slab) { - void *addr = page_address(page); + void *addr = slab_address(slab); void *p; - bitmap_zero(obj_map, page->objects); + bitmap_zero(obj_map, slab->objects); - for (p = page->freelist; p; p = get_freepointer(s, p)) + for (p = slab->freelist; p; p = get_freepointer(s, p)) set_bit(__obj_to_index(s, addr, p), obj_map); } @@ -599,14 +599,14 @@ static inline bool slab_add_kunit_errors(void) { return false; } * Node listlock must be held to guarantee that the page does * not vanish from under us. */ -static unsigned long *get_map(struct kmem_cache *s, struct page *page) +static unsigned long *get_map(struct kmem_cache *s, struct slab *slab) __acquires(&object_map_lock) { VM_BUG_ON(!irqs_disabled()); raw_spin_lock(&object_map_lock); - __fill_map(object_map, s, page); + __fill_map(object_map, s, slab); return object_map; } @@ -667,17 +667,17 @@ static inline void metadata_access_disable(void) /* Verify that a pointer has an address that is valid within a slab page */ static inline int check_valid_pointer(struct kmem_cache *s, - struct page *page, void *object) + struct slab *slab, void *object) { void *base; if (!object) return 1; - base = page_address(page); + base = slab_address(slab); object = kasan_reset_tag(object); object = restore_red_left(s, object); - if (object < base || object >= base + page->objects * s->size || + if (object < base || object >= base + slab->objects * s->size || (object - base) % s->size) { return 0; } @@ -827,14 +827,14 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...) va_end(args); } -static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) +static void print_trailer(struct kmem_cache *s, struct slab *slab, u8 *p) { unsigned int off; /* Offset of last byte */ - u8 *addr = page_address(page); + u8 *addr = slab_address(slab); print_tracking(s, p); - print_slab_info(page_slab(page)); + print_slab_info(slab); pr_err("Object 0x%p @offset=%tu fp=0x%p\n\n", p, p - addr, get_freepointer(s, p)); @@ -866,23 +866,23 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) dump_stack(); } -static void object_err(struct kmem_cache *s, struct page *page, +static void object_err(struct kmem_cache *s, struct slab *slab, u8 *object, char *reason) { if (slab_add_kunit_errors()) return; slab_bug(s, "%s", reason); - print_trailer(s, page, object); + print_trailer(s, slab, object); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } -static bool freelist_corrupted(struct kmem_cache *s, struct page *page, +static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab, void **freelist, void *nextfree) { if ((s->flags & SLAB_CONSISTENCY_CHECKS) && - !check_valid_pointer(s, page, nextfree) && freelist) { - object_err(s, page, *freelist, "Freechain corrupt"); + !check_valid_pointer(s, slab, nextfree) && freelist) { + object_err(s, slab, *freelist, "Freechain corrupt"); *freelist = NULL; slab_fix(s, "Isolate corrupted freechain"); return true; @@ -891,7 +891,7 @@ static bool freelist_corrupted(struct kmem_cache *s, struct page *page, return false; } -static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, +static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab, const char *fmt, ...) { va_list args; @@ -904,7 +904,7 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page, vsnprintf(buf, sizeof(buf), fmt, args); va_end(args); slab_bug(s, "%s", buf); - print_slab_info(page_slab(page)); + print_slab_info(slab); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } @@ -932,13 +932,13 @@ static void restore_bytes(struct kmem_cache *s, char *message, u8 data, memset(from, data, to - from); } -static int check_bytes_and_report(struct kmem_cache *s, struct page *page, +static int check_bytes_and_report(struct kmem_cache *s, struct slab *slab, u8 *object, char *what, u8 *start, unsigned int value, unsigned int bytes) { u8 *fault; u8 *end; - u8 *addr = page_address(page); + u8 *addr = slab_address(slab); metadata_access_enable(); fault = memchr_inv(kasan_reset_tag(start), value, bytes); @@ -957,7 +957,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n", fault, end - 1, fault - addr, fault[0], value); - print_trailer(s, page, object); + print_trailer(s, slab, object); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); skip_bug_print: @@ -1003,7 +1003,7 @@ skip_bug_print: * may be used with merged slabcaches. */ -static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) +static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p) { unsigned long off = get_info_end(s); /* The end of info */ @@ -1016,12 +1016,12 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) if (size_from_object(s) == off) return 1; - return check_bytes_and_report(s, page, p, "Object padding", + return check_bytes_and_report(s, slab, p, "Object padding", p + off, POISON_INUSE, size_from_object(s) - off); } /* Check the pad bytes at the end of a slab page */ -static int slab_pad_check(struct kmem_cache *s, struct page *page) +static int slab_pad_check(struct kmem_cache *s, struct slab *slab) { u8 *start; u8 *fault; @@ -1033,8 +1033,8 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) if (!(s->flags & SLAB_POISON)) return 1; - start = page_address(page); - length = page_size(page); + start = slab_address(slab); + length = slab_size(slab); end = start + length; remainder = length % s->size; if (!remainder) @@ -1049,7 +1049,7 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) while (end > fault && end[-1] == POISON_INUSE) end--; - slab_err(s, page, "Padding overwritten. 0x%p-0x%p @offset=%tu", + slab_err(s, slab, "Padding overwritten. 0x%p-0x%p @offset=%tu", fault, end - 1, fault - start); print_section(KERN_ERR, "Padding ", pad, remainder); @@ -1057,23 +1057,23 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) return 0; } -static int check_object(struct kmem_cache *s, struct page *page, +static int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { u8 *p = object; u8 *endobject = object + s->object_size; if (s->flags & SLAB_RED_ZONE) { - if (!check_bytes_and_report(s, page, object, "Left Redzone", + if (!check_bytes_and_report(s, slab, object, "Left Redzone", object - s->red_left_pad, val, s->red_left_pad)) return 0; - if (!check_bytes_and_report(s, page, object, "Right Redzone", + if (!check_bytes_and_report(s, slab, object, "Right Redzone", endobject, val, s->inuse - s->object_size)) return 0; } else { if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) { - check_bytes_and_report(s, page, p, "Alignment padding", + check_bytes_and_report(s, slab, p, "Alignment padding", endobject, POISON_INUSE, s->inuse - s->object_size); } @@ -1081,15 +1081,15 @@ static int check_object(struct kmem_cache *s, struct page *page, if (s->flags & SLAB_POISON) { if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) && - (!check_bytes_and_report(s, page, p, "Poison", p, + (!check_bytes_and_report(s, slab, p, "Poison", p, POISON_FREE, s->object_size - 1) || - !check_bytes_and_report(s, page, p, "End Poison", + !check_bytes_and_report(s, slab, p, "End Poison", p + s->object_size - 1, POISON_END, 1))) return 0; /* * check_pad_bytes cleans up on its own. */ - check_pad_bytes(s, page, p); + check_pad_bytes(s, slab, p); } if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) @@ -1100,8 +1100,8 @@ static int check_object(struct kmem_cache *s, struct page *page, return 1; /* Check free pointer validity */ - if (!check_valid_pointer(s, page, get_freepointer(s, p))) { - object_err(s, page, p, "Freepointer corrupt"); + if (!check_valid_pointer(s, slab, get_freepointer(s, p))) { + object_err(s, slab, p, "Freepointer corrupt"); /* * No choice but to zap it and thus lose the remainder * of the free objects in this slab. May cause @@ -1113,28 +1113,28 @@ static int check_object(struct kmem_cache *s, struct page *page, return 1; } -static int check_slab(struct kmem_cache *s, struct page *page) +static int check_slab(struct kmem_cache *s, struct slab *slab) { int maxobj; - if (!PageSlab(page)) { - slab_err(s, page, "Not a valid slab page"); + if (!folio_test_slab(slab_folio(slab))) { + slab_err(s, slab, "Not a valid slab page"); return 0; } - maxobj = order_objects(compound_order(page), s->size); - if (page->objects > maxobj) { - slab_err(s, page, "objects %u > max %u", - page->objects, maxobj); + maxobj = order_objects(slab_order(slab), s->size); + if (slab->objects > maxobj) { + slab_err(s, slab, "objects %u > max %u", + slab->objects, maxobj); return 0; } - if (page->inuse > page->objects) { - slab_err(s, page, "inuse %u > max %u", - page->inuse, page->objects); + if (slab->inuse > slab->objects) { + slab_err(s, slab, "inuse %u > max %u", + slab->inuse, slab->objects); return 0; } /* Slab_pad_check fixes things up after itself */ - slab_pad_check(s, page); + slab_pad_check(s, slab); return 1; } @@ -1142,26 +1142,26 @@ static int check_slab(struct kmem_cache *s, struct page *page) * Determine if a certain object on a page is on the freelist. Must hold the * slab lock to guarantee that the chains are in a consistent state. */ -static int on_freelist(struct kmem_cache *s, struct page *page, void *search) +static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search) { int nr = 0; void *fp; void *object = NULL; int max_objects; - fp = page->freelist; - while (fp && nr <= page->objects) { + fp = slab->freelist; + while (fp && nr <= slab->objects) { if (fp == search) return 1; - if (!check_valid_pointer(s, page, fp)) { + if (!check_valid_pointer(s, slab, fp)) { if (object) { - object_err(s, page, object, + object_err(s, slab, object, "Freechain corrupt"); set_freepointer(s, object, NULL); } else { - slab_err(s, page, "Freepointer corrupt"); - page->freelist = NULL; - page->inuse = page->objects; + slab_err(s, slab, "Freepointer corrupt"); + slab->freelist = NULL; + slab->inuse = slab->objects; slab_fix(s, "Freelist cleared"); return 0; } @@ -1172,34 +1172,34 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search) nr++; } - max_objects = order_objects(compound_order(page), s->size); + max_objects = order_objects(slab_order(slab), s->size); if (max_objects > MAX_OBJS_PER_PAGE) max_objects = MAX_OBJS_PER_PAGE; - if (page->objects != max_objects) { - slab_err(s, page, "Wrong number of objects. Found %d but should be %d", - page->objects, max_objects); - page->objects = max_objects; + if (slab->objects != max_objects) { + slab_err(s, slab, "Wrong number of objects. Found %d but should be %d", + slab->objects, max_objects); + slab->objects = max_objects; slab_fix(s, "Number of objects adjusted"); } - if (page->inuse != page->objects - nr) { - slab_err(s, page, "Wrong object count. Counter is %d but counted were %d", - page->inuse, page->objects - nr); - page->inuse = page->objects - nr; + if (slab->inuse != slab->objects - nr) { + slab_err(s, slab, "Wrong object count. Counter is %d but counted were %d", + slab->inuse, slab->objects - nr); + slab->inuse = slab->objects - nr; slab_fix(s, "Object count adjusted"); } return search == NULL; } -static void trace(struct kmem_cache *s, struct page *page, void *object, +static void trace(struct kmem_cache *s, struct slab *slab, void *object, int alloc) { if (s->flags & SLAB_TRACE) { pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n", s->name, alloc ? "alloc" : "free", - object, page->inuse, - page->freelist); + object, slab->inuse, + slab->freelist); if (!alloc) print_section(KERN_INFO, "Object ", (void *)object, @@ -1213,22 +1213,22 @@ static void trace(struct kmem_cache *s, struct page *page, void *object, * Tracking of fully allocated slabs for debugging purposes. */ static void add_full(struct kmem_cache *s, - struct kmem_cache_node *n, struct page *page) + struct kmem_cache_node *n, struct slab *slab) { if (!(s->flags & SLAB_STORE_USER)) return; lockdep_assert_held(&n->list_lock); - list_add(&page->slab_list, &n->full); + list_add(&slab->slab_list, &n->full); } -static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page) +static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) { if (!(s->flags & SLAB_STORE_USER)) return; lockdep_assert_held(&n->list_lock); - list_del(&page->slab_list); + list_del(&slab->slab_list); } /* Tracking of the number of slabs for debugging purposes */ @@ -1268,7 +1268,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) } /* Object debug checks for alloc/free paths */ -static void setup_object_debug(struct kmem_cache *s, struct page *page, +static void setup_object_debug(struct kmem_cache *s, struct slab *slab, void *object) { if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)) @@ -1279,89 +1279,89 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page, } static -void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) +void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) { if (!kmem_cache_debug_flags(s, SLAB_POISON)) return; metadata_access_enable(); - memset(kasan_reset_tag(addr), POISON_INUSE, page_size(page)); + memset(kasan_reset_tag(addr), POISON_INUSE, slab_size(slab)); metadata_access_disable(); } static inline int alloc_consistency_checks(struct kmem_cache *s, - struct page *page, void *object) + struct slab *slab, void *object) { - if (!check_slab(s, page)) + if (!check_slab(s, slab)) return 0; - if (!check_valid_pointer(s, page, object)) { - object_err(s, page, object, "Freelist Pointer check fails"); + if (!check_valid_pointer(s, slab, object)) { + object_err(s, slab, object, "Freelist Pointer check fails"); return 0; } - if (!check_object(s, page, object, SLUB_RED_INACTIVE)) + if (!check_object(s, slab, object, SLUB_RED_INACTIVE)) return 0; return 1; } static noinline int alloc_debug_processing(struct kmem_cache *s, - struct page *page, + struct slab *slab, void *object, unsigned long addr) { if (s->flags & SLAB_CONSISTENCY_CHECKS) { - if (!alloc_consistency_checks(s, page, object)) + if (!alloc_consistency_checks(s, slab, object)) goto bad; } /* Success perform special debug activities for allocs */ if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_ALLOC, addr); - trace(s, page, object, 1); + trace(s, slab, object, 1); init_object(s, object, SLUB_RED_ACTIVE); return 1; bad: - if (PageSlab(page)) { + if (folio_test_slab(slab_folio(slab))) { /* * If this is a slab page then lets do the best we can * to avoid issues in the future. Marking all objects * as used avoids touching the remaining objects. */ slab_fix(s, "Marking all objects used"); - page->inuse = page->objects; - page->freelist = NULL; + slab->inuse = slab->objects; + slab->freelist = NULL; } return 0; } static inline int free_consistency_checks(struct kmem_cache *s, - struct page *page, void *object, unsigned long addr) + struct slab *slab, void *object, unsigned long addr) { - if (!check_valid_pointer(s, page, object)) { - slab_err(s, page, "Invalid object pointer 0x%p", object); + if (!check_valid_pointer(s, slab, object)) { + slab_err(s, slab, "Invalid object pointer 0x%p", object); return 0; } - if (on_freelist(s, page, object)) { - object_err(s, page, object, "Object already free"); + if (on_freelist(s, slab, object)) { + object_err(s, slab, object, "Object already free"); return 0; } - if (!check_object(s, page, object, SLUB_RED_ACTIVE)) + if (!check_object(s, slab, object, SLUB_RED_ACTIVE)) return 0; - if (unlikely(s != page->slab_cache)) { - if (!PageSlab(page)) { - slab_err(s, page, "Attempt to free object(0x%p) outside of slab", + if (unlikely(s != slab->slab_cache)) { + if (!folio_test_slab(slab_folio(slab))) { + slab_err(s, slab, "Attempt to free object(0x%p) outside of slab", object); - } else if (!page->slab_cache) { + } else if (!slab->slab_cache) { pr_err("SLUB : no slab for object 0x%p.\n", object); dump_stack(); } else - object_err(s, page, object, + object_err(s, slab, object, "page slab pointer corrupt."); return 0; } @@ -1370,21 +1370,21 @@ static inline int free_consistency_checks(struct kmem_cache *s, /* Supports checking bulk free of a constructed freelist */ static noinline int free_debug_processing( - struct kmem_cache *s, struct page *page, + struct kmem_cache *s, struct slab *slab, void *head, void *tail, int bulk_cnt, unsigned long addr) { - struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + struct kmem_cache_node *n = get_node(s, slab_nid(slab)); void *object = head; int cnt = 0; unsigned long flags, flags2; int ret = 0; spin_lock_irqsave(&n->list_lock, flags); - slab_lock(page, &flags2); + slab_lock(slab, &flags2); if (s->flags & SLAB_CONSISTENCY_CHECKS) { - if (!check_slab(s, page)) + if (!check_slab(s, slab)) goto out; } @@ -1392,13 +1392,13 @@ next_object: cnt++; if (s->flags & SLAB_CONSISTENCY_CHECKS) { - if (!free_consistency_checks(s, page, object, addr)) + if (!free_consistency_checks(s, slab, object, addr)) goto out; } if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_FREE, addr); - trace(s, page, object, 0); + trace(s, slab, object, 0); /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ init_object(s, object, SLUB_RED_INACTIVE); @@ -1411,10 +1411,10 @@ next_object: out: if (cnt != bulk_cnt) - slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n", + slab_err(s, slab, "Bulk freelist count(%d) invalid(%d)\n", bulk_cnt, cnt); - slab_unlock(page, &flags2); + slab_unlock(slab, &flags2); spin_unlock_irqrestore(&n->list_lock, flags); if (!ret) slab_fix(s, "Object at 0x%p not freed", object); @@ -1629,26 +1629,26 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, } #else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, - struct page *page, void *object) {} + struct slab *slab, void *object) {} static inline -void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) {} +void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {} static inline int alloc_debug_processing(struct kmem_cache *s, - struct page *page, void *object, unsigned long addr) { return 0; } + struct slab *slab, void *object, unsigned long addr) { return 0; } static inline int free_debug_processing( - struct kmem_cache *s, struct page *page, + struct kmem_cache *s, struct slab *slab, void *head, void *tail, int bulk_cnt, unsigned long addr) { return 0; } -static inline int slab_pad_check(struct kmem_cache *s, struct page *page) +static inline int slab_pad_check(struct kmem_cache *s, struct slab *slab) { return 1; } -static inline int check_object(struct kmem_cache *s, struct page *page, +static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, - struct page *page) {} + struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, - struct page *page) {} + struct slab *slab) {} slab_flags_t kmem_cache_flags(unsigned int object_size, slab_flags_t flags, const char *name) { @@ -1667,7 +1667,7 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) {} -static bool freelist_corrupted(struct kmem_cache *s, struct page *page, +static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab, void **freelist, void *nextfree) { return false; @@ -1772,10 +1772,10 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, return *head != NULL; } -static void *setup_object(struct kmem_cache *s, struct page *page, +static void *setup_object(struct kmem_cache *s, struct slab *slab, void *object) { - setup_object_debug(s, page, object); + setup_object_debug(s, slab, object); object = kasan_init_slab_obj(s, object); if (unlikely(s->ctor)) { kasan_unpoison_object_data(s, object); @@ -1853,7 +1853,7 @@ static void __init init_freelist_randomization(void) } /* Get the next entry on the pre-computed freelist randomized */ -static void *next_freelist_entry(struct kmem_cache *s, struct page *page, +static void *next_freelist_entry(struct kmem_cache *s, struct slab *slab, unsigned long *pos, void *start, unsigned long page_limit, unsigned long freelist_count) @@ -1875,32 +1875,32 @@ static void *next_freelist_entry(struct kmem_cache *s, struct page *page, } /* Shuffle the single linked freelist based on a random pre-computed sequence */ -static bool shuffle_freelist(struct kmem_cache *s, struct page *page) +static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab) { void *start; void *cur; void *next; unsigned long idx, pos, page_limit, freelist_count; - if (page->objects < 2 || !s->random_seq) + if (slab->objects < 2 || !s->random_seq) return false; freelist_count = oo_objects(s->oo); pos = get_random_int() % freelist_count; - page_limit = page->objects * s->size; - start = fixup_red_left(s, page_address(page)); + page_limit = slab->objects * s->size; + start = fixup_red_left(s, slab_address(slab)); /* First entry is used as the base of the freelist */ - cur = next_freelist_entry(s, page, &pos, start, page_limit, + cur = next_freelist_entry(s, slab, &pos, start, page_limit, freelist_count); - cur = setup_object(s, page, cur); - page->freelist = cur; + cur = setup_object(s, slab, cur); + slab->freelist = cur; - for (idx = 1; idx < page->objects; idx++) { - next = next_freelist_entry(s, page, &pos, start, page_limit, + for (idx = 1; idx < slab->objects; idx++) { + next = next_freelist_entry(s, slab, &pos, start, page_limit, freelist_count); - next = setup_object(s, page, next); + next = setup_object(s, slab, next); set_freepointer(s, cur, next); cur = next; } @@ -1914,15 +1914,15 @@ static inline int init_cache_random_seq(struct kmem_cache *s) return 0; } static inline void init_freelist_randomization(void) { } -static inline bool shuffle_freelist(struct kmem_cache *s, struct page *page) +static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab) { return false; } #endif /* CONFIG_SLAB_FREELIST_RANDOM */ -static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) +static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) { - struct page *page; + struct slab *slab; struct kmem_cache_order_objects oo = s->oo; gfp_t alloc_gfp; void *start, *p, *next; @@ -1941,60 +1941,60 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min)) alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL); - page = slab_page(alloc_slab_page(s, alloc_gfp, node, oo)); - if (unlikely(!page)) { + slab = alloc_slab_page(s, alloc_gfp, node, oo); + if (unlikely(!slab)) { oo = s->min; alloc_gfp = flags; /* * Allocation may have failed due to fragmentation. * Try a lower order alloc if possible */ - page = slab_page(alloc_slab_page(s, alloc_gfp, node, oo)); - if (unlikely(!page)) + slab = alloc_slab_page(s, alloc_gfp, node, oo); + if (unlikely(!slab)) goto out; stat(s, ORDER_FALLBACK); } - page->objects = oo_objects(oo); + slab->objects = oo_objects(oo); - account_slab(page_slab(page), oo_order(oo), s, flags); + account_slab(slab, oo_order(oo), s, flags); - page->slab_cache = s; + slab->slab_cache = s; - kasan_poison_slab(page); + kasan_poison_slab(slab_page(slab)); - start = page_address(page); + start = slab_address(slab); - setup_page_debug(s, page, start); + setup_slab_debug(s, slab, start); - shuffle = shuffle_freelist(s, page); + shuffle = shuffle_freelist(s, slab); if (!shuffle) { start = fixup_red_left(s, start); - start = setup_object(s, page, start); - page->freelist = start; - for (idx = 0, p = start; idx < page->objects - 1; idx++) { + start = setup_object(s, slab, start); + slab->freelist = start; + for (idx = 0, p = start; idx < slab->objects - 1; idx++) { next = p + s->size; - next = setup_object(s, page, next); + next = setup_object(s, slab, next); set_freepointer(s, p, next); p = next; } set_freepointer(s, p, NULL); } - page->inuse = page->objects; - page->frozen = 1; + slab->inuse = slab->objects; + slab->frozen = 1; out: - if (!page) + if (!slab) return NULL; - inc_slabs_node(s, page_to_nid(page), page->objects); + inc_slabs_node(s, slab_nid(slab), slab->objects); - return page; + return slab; } -static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) +static struct slab *new_slab(struct kmem_cache *s, gfp_t flags, int node) { if (unlikely(flags & GFP_SLAB_BUG_MASK)) flags = kmalloc_fix_flags(flags); @@ -2014,9 +2014,9 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab) if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) { void *p; - slab_pad_check(s, folio_page(folio, 0)); + slab_pad_check(s, slab); for_each_object(p, s, slab_address(slab), slab->objects) - check_object(s, folio_page(folio, 0), p, SLUB_RED_INACTIVE); + check_object(s, slab, p, SLUB_RED_INACTIVE); } __slab_clear_pfmemalloc(slab); @@ -2030,50 +2030,50 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab) static void rcu_free_slab(struct rcu_head *h) { - struct page *page = container_of(h, struct page, rcu_head); + struct slab *slab = container_of(h, struct slab, rcu_head); - __free_slab(page->slab_cache, page_slab(page)); + __free_slab(slab->slab_cache, slab); } -static void free_slab(struct kmem_cache *s, struct page *page) +static void free_slab(struct kmem_cache *s, struct slab *slab) { if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) { - call_rcu(&page->rcu_head, rcu_free_slab); + call_rcu(&slab->rcu_head, rcu_free_slab); } else - __free_slab(s, page_slab(page)); + __free_slab(s, slab); } -static void discard_slab(struct kmem_cache *s, struct page *page) +static void discard_slab(struct kmem_cache *s, struct slab *slab) { - dec_slabs_node(s, page_to_nid(page), page->objects); - free_slab(s, page); + dec_slabs_node(s, slab_nid(slab), slab->objects); + free_slab(s, slab); } /* * Management of partially allocated slabs. */ static inline void -__add_partial(struct kmem_cache_node *n, struct page *page, int tail) +__add_partial(struct kmem_cache_node *n, struct slab *slab, int tail) { n->nr_partial++; if (tail == DEACTIVATE_TO_TAIL) - list_add_tail(&page->slab_list, &n->partial); + list_add_tail(&slab->slab_list, &n->partial); else - list_add(&page->slab_list, &n->partial); + list_add(&slab->slab_list, &n->partial); } static inline void add_partial(struct kmem_cache_node *n, - struct page *page, int tail) + struct slab *slab, int tail) { lockdep_assert_held(&n->list_lock); - __add_partial(n, page, tail); + __add_partial(n, slab, tail); } static inline void remove_partial(struct kmem_cache_node *n, - struct page *page) + struct slab *slab) { lockdep_assert_held(&n->list_lock); - list_del(&page->slab_list); + list_del(&slab->slab_list); n->nr_partial--; } @@ -2084,12 +2084,12 @@ static inline void remove_partial(struct kmem_cache_node *n, * Returns a list of objects or NULL if it fails. */ static inline void *acquire_slab(struct kmem_cache *s, - struct kmem_cache_node *n, struct page *page, + struct kmem_cache_node *n, struct slab *slab, int mode) { void *freelist; unsigned long counters; - struct page new; + struct slab new; lockdep_assert_held(&n->list_lock); @@ -2098,11 +2098,11 @@ static inline void *acquire_slab(struct kmem_cache *s, * The old freelist is the list of objects for the * per cpu allocation list. */ - freelist = page->freelist; - counters = page->counters; + freelist = slab->freelist; + counters = slab->counters; new.counters = counters; if (mode) { - new.inuse = page->objects; + new.inuse = slab->objects; new.freelist = NULL; } else { new.freelist = freelist; @@ -2111,21 +2111,21 @@ static inline void *acquire_slab(struct kmem_cache *s, VM_BUG_ON(new.frozen); new.frozen = 1; - if (!__cmpxchg_double_slab(s, page, + if (!__cmpxchg_double_slab(s, slab, freelist, counters, new.freelist, new.counters, "acquire_slab")) return NULL; - remove_partial(n, page); + remove_partial(n, slab); WARN_ON(!freelist); return freelist; } #ifdef CONFIG_SLUB_CPU_PARTIAL -static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain); +static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain); #else -static inline void put_cpu_partial(struct kmem_cache *s, struct page *page, +static inline void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain) { } #endif static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags); @@ -2134,12 +2134,12 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags); * Try to allocate a partial slab from a specific node. */ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, - struct page **ret_page, gfp_t gfpflags) + struct slab **ret_slab, gfp_t gfpflags) { - struct page *page, *page2; + struct slab *slab, *slab2; void *object = NULL; unsigned long flags; - unsigned int partial_pages = 0; + unsigned int partial_slabs = 0; /* * Racy check. If we mistakenly see no partial slabs then we @@ -2151,28 +2151,28 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, return NULL; spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry_safe(page, page2, &n->partial, slab_list) { + list_for_each_entry_safe(slab, slab2, &n->partial, slab_list) { void *t; - if (!pfmemalloc_match(page_slab(page), gfpflags)) + if (!pfmemalloc_match(slab, gfpflags)) continue; - t = acquire_slab(s, n, page, object == NULL); + t = acquire_slab(s, n, slab, object == NULL); if (!t) break; if (!object) { - *ret_page = page; + *ret_slab = slab; stat(s, ALLOC_FROM_PARTIAL); object = t; } else { - put_cpu_partial(s, page, 0); + put_cpu_partial(s, slab, 0); stat(s, CPU_PARTIAL_NODE); - partial_pages++; + partial_slabs++; } #ifdef CONFIG_SLUB_CPU_PARTIAL if (!kmem_cache_has_cpu_partial(s) - || partial_pages > s->cpu_partial_pages / 2) + || partial_slabs > s->cpu_partial_slabs / 2) break; #else break; @@ -2187,7 +2187,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, * Get a page from somewhere. Search in increasing NUMA distances. */ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, - struct page **ret_page) + struct slab **ret_slab) { #ifdef CONFIG_NUMA struct zonelist *zonelist; @@ -2229,7 +2229,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, if (n && cpuset_zone_allowed(zone, flags) && n->nr_partial > s->min_partial) { - object = get_partial_node(s, n, ret_page, flags); + object = get_partial_node(s, n, ret_slab, flags); if (object) { /* * Don't check read_mems_allowed_retry() @@ -2251,7 +2251,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, * Get a partial page, lock it and return it. */ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, - struct page **ret_page) + struct slab **ret_slab) { void *object; int searchnode = node; @@ -2259,11 +2259,11 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, if (node == NUMA_NO_NODE) searchnode = numa_mem_id(); - object = get_partial_node(s, get_node(s, searchnode), ret_page, flags); + object = get_partial_node(s, get_node(s, searchnode), ret_slab, flags); if (object || node != NUMA_NO_NODE) return object; - return get_any_partial(s, flags, ret_page); + return get_any_partial(s, flags, ret_slab); } #ifdef CONFIG_PREEMPTION @@ -2345,20 +2345,20 @@ static void init_kmem_cache_cpus(struct kmem_cache *s) * Assumes the slab has been already safely taken away from kmem_cache_cpu * by the caller. */ -static void deactivate_slab(struct kmem_cache *s, struct page *page, +static void deactivate_slab(struct kmem_cache *s, struct slab *slab, void *freelist) { enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE }; - struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + struct kmem_cache_node *n = get_node(s, slab_nid(slab)); int lock = 0, free_delta = 0; enum slab_modes l = M_NONE, m = M_NONE; void *nextfree, *freelist_iter, *freelist_tail; int tail = DEACTIVATE_TO_HEAD; unsigned long flags = 0; - struct page new; - struct page old; + struct slab new; + struct slab old; - if (page->freelist) { + if (slab->freelist) { stat(s, DEACTIVATE_REMOTE_FREES); tail = DEACTIVATE_TO_TAIL; } @@ -2377,7 +2377,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, * 'freelist_iter' is already corrupted. So isolate all objects * starting at 'freelist_iter' by skipping them. */ - if (freelist_corrupted(s, page, &freelist_iter, nextfree)) + if (freelist_corrupted(s, slab, &freelist_iter, nextfree)) break; freelist_tail = freelist_iter; @@ -2404,8 +2404,8 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, */ redo: - old.freelist = READ_ONCE(page->freelist); - old.counters = READ_ONCE(page->counters); + old.freelist = READ_ONCE(slab->freelist); + old.counters = READ_ONCE(slab->counters); VM_BUG_ON(!old.frozen); /* Determine target state of the slab */ @@ -2447,18 +2447,18 @@ redo: if (l != m) { if (l == M_PARTIAL) - remove_partial(n, page); + remove_partial(n, slab); else if (l == M_FULL) - remove_full(s, n, page); + remove_full(s, n, slab); if (m == M_PARTIAL) - add_partial(n, page, tail); + add_partial(n, slab, tail); else if (m == M_FULL) - add_full(s, n, page); + add_full(s, n, slab); } l = m; - if (!cmpxchg_double_slab(s, page, + if (!cmpxchg_double_slab(s, slab, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")) @@ -2473,26 +2473,26 @@ redo: stat(s, DEACTIVATE_FULL); else if (m == M_FREE) { stat(s, DEACTIVATE_EMPTY); - discard_slab(s, page); + discard_slab(s, slab); stat(s, FREE_SLAB); } } #ifdef CONFIG_SLUB_CPU_PARTIAL -static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page) +static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab) { struct kmem_cache_node *n = NULL, *n2 = NULL; - struct page *page, *discard_page = NULL; + struct slab *slab, *slab_to_discard = NULL; unsigned long flags = 0; - while (partial_page) { - struct page new; - struct page old; + while (partial_slab) { + struct slab new; + struct slab old; - page = partial_page; - partial_page = page->next; + slab = partial_slab; + partial_slab = slab->next; - n2 = get_node(s, page_to_nid(page)); + n2 = get_node(s, slab_nid(slab)); if (n != n2) { if (n) spin_unlock_irqrestore(&n->list_lock, flags); @@ -2503,8 +2503,8 @@ static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page) do { - old.freelist = page->freelist; - old.counters = page->counters; + old.freelist = slab->freelist; + old.counters = slab->counters; VM_BUG_ON(!old.frozen); new.counters = old.counters; @@ -2512,16 +2512,16 @@ static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page) new.frozen = 0; - } while (!__cmpxchg_double_slab(s, page, + } while (!__cmpxchg_double_slab(s, slab, old.freelist, old.counters, new.freelist, new.counters, "unfreezing slab")); if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) { - page->next = discard_page; - discard_page = page; + slab->next = slab_to_discard; + slab_to_discard = slab; } else { - add_partial(n, page, DEACTIVATE_TO_TAIL); + add_partial(n, slab, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } } @@ -2529,12 +2529,12 @@ static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page) if (n) spin_unlock_irqrestore(&n->list_lock, flags); - while (discard_page) { - page = discard_page; - discard_page = discard_page->next; + while (slab_to_discard) { + slab = slab_to_discard; + slab_to_discard = slab_to_discard->next; stat(s, DEACTIVATE_EMPTY); - discard_slab(s, page); + discard_slab(s, slab); stat(s, FREE_SLAB); } } @@ -2544,28 +2544,28 @@ static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page) */ static void unfreeze_partials(struct kmem_cache *s) { - struct page *partial_page; + struct slab *partial_slab; unsigned long flags; local_lock_irqsave(&s->cpu_slab->lock, flags); - partial_page = this_cpu_read(s->cpu_slab->partial); + partial_slab = this_cpu_read(s->cpu_slab->partial); this_cpu_write(s->cpu_slab->partial, NULL); local_unlock_irqrestore(&s->cpu_slab->lock, flags); - if (partial_page) - __unfreeze_partials(s, partial_page); + if (partial_slab) + __unfreeze_partials(s, partial_slab); } static void unfreeze_partials_cpu(struct kmem_cache *s, struct kmem_cache_cpu *c) { - struct page *partial_page; + struct slab *partial_slab; - partial_page = slub_percpu_partial(c); + partial_slab = slub_percpu_partial(c); c->partial = NULL; - if (partial_page) - __unfreeze_partials(s, partial_page); + if (partial_slab) + __unfreeze_partials(s, partial_slab); } /* @@ -2575,42 +2575,42 @@ static void unfreeze_partials_cpu(struct kmem_cache *s, * If we did not find a slot then simply move all the partials to the * per node partial list. */ -static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) +static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain) { - struct page *oldpage; - struct page *page_to_unfreeze = NULL; + struct slab *oldslab; + struct slab *slab_to_unfreeze = NULL; unsigned long flags; - int pages = 0; + int slabs = 0; local_lock_irqsave(&s->cpu_slab->lock, flags); - oldpage = this_cpu_read(s->cpu_slab->partial); + oldslab = this_cpu_read(s->cpu_slab->partial); - if (oldpage) { - if (drain && oldpage->pages >= s->cpu_partial_pages) { + if (oldslab) { + if (drain && oldslab->slabs >= s->cpu_partial_slabs) { /* * Partial array is full. Move the existing set to the * per node partial list. Postpone the actual unfreezing * outside of the critical section. */ - page_to_unfreeze = oldpage; - oldpage = NULL; + slab_to_unfreeze = oldslab; + oldslab = NULL; } else { - pages = oldpage->pages; + slabs = oldslab->slabs; } } - pages++; + slabs++; - page->pages = pages; - page->next = oldpage; + slab->slabs = slabs; + slab->next = oldslab; - this_cpu_write(s->cpu_slab->partial, page); + this_cpu_write(s->cpu_slab->partial, slab); local_unlock_irqrestore(&s->cpu_slab->lock, flags); - if (page_to_unfreeze) { - __unfreeze_partials(s, page_to_unfreeze); + if (slab_to_unfreeze) { + __unfreeze_partials(s, slab_to_unfreeze); stat(s, CPU_PARTIAL_DRAIN); } } @@ -2626,22 +2626,22 @@ static inline void unfreeze_partials_cpu(struct kmem_cache *s, static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { unsigned long flags; - struct page *page; + struct slab *slab; void *freelist; local_lock_irqsave(&s->cpu_slab->lock, flags); - page = c->page; + slab = c->slab; freelist = c->freelist; - c->page = NULL; + c->slab = NULL; c->freelist = NULL; c->tid = next_tid(c->tid); local_unlock_irqrestore(&s->cpu_slab->lock, flags); - if (page) { - deactivate_slab(s, page, freelist); + if (slab) { + deactivate_slab(s, slab, freelist); stat(s, CPUSLAB_FLUSH); } } @@ -2650,14 +2650,14 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); void *freelist = c->freelist; - struct page *page = c->page; + struct slab *slab = c->slab; - c->page = NULL; + c->slab = NULL; c->freelist = NULL; c->tid = next_tid(c->tid); - if (page) { - deactivate_slab(s, page, freelist); + if (slab) { + deactivate_slab(s, slab, freelist); stat(s, CPUSLAB_FLUSH); } @@ -2686,7 +2686,7 @@ static void flush_cpu_slab(struct work_struct *w) s = sfw->s; c = this_cpu_ptr(s->cpu_slab); - if (c->page) + if (c->slab) flush_slab(s, c); unfreeze_partials(s); @@ -2696,7 +2696,7 @@ static bool has_cpu_slab(int cpu, struct kmem_cache *s) { struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); - return c->page || slub_percpu_partial(c); + return c->slab || slub_percpu_partial(c); } static DEFINE_MUTEX(flush_lock); @@ -2758,19 +2758,19 @@ static int slub_cpu_dead(unsigned int cpu) * Check if the objects in a per cpu structure fit numa * locality expectations. */ -static inline int node_match(struct page *page, int node) +static inline int node_match(struct slab *slab, int node) { #ifdef CONFIG_NUMA - if (node != NUMA_NO_NODE && page_to_nid(page) != node) + if (node != NUMA_NO_NODE && slab_nid(slab) != node) return 0; #endif return 1; } #ifdef CONFIG_SLUB_DEBUG -static int count_free(struct page *page) +static int count_free(struct slab *slab) { - return page->objects - page->inuse; + return slab->objects - slab->inuse; } static inline unsigned long node_nr_objs(struct kmem_cache_node *n) @@ -2781,15 +2781,15 @@ static inline unsigned long node_nr_objs(struct kmem_cache_node *n) #if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS) static unsigned long count_partial(struct kmem_cache_node *n, - int (*get_count)(struct page *)) + int (*get_count)(struct slab *)) { unsigned long flags; unsigned long x = 0; - struct page *page; + struct slab *slab; spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, slab_list) - x += get_count(page); + list_for_each_entry(slab, &n->partial, slab_list) + x += get_count(slab); spin_unlock_irqrestore(&n->list_lock, flags); return x; } @@ -2848,25 +2848,25 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags) * * If this function returns NULL then the page has been unfrozen. */ -static inline void *get_freelist(struct kmem_cache *s, struct page *page) +static inline void *get_freelist(struct kmem_cache *s, struct slab *slab) { - struct page new; + struct slab new; unsigned long counters; void *freelist; lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock)); do { - freelist = page->freelist; - counters = page->counters; + freelist = slab->freelist; + counters = slab->counters; new.counters = counters; VM_BUG_ON(!new.frozen); - new.inuse = page->objects; + new.inuse = slab->objects; new.frozen = freelist != NULL; - } while (!__cmpxchg_double_slab(s, page, + } while (!__cmpxchg_double_slab(s, slab, freelist, counters, NULL, new.counters, "get_freelist")); @@ -2897,15 +2897,15 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void *freelist; - struct page *page; + struct slab *slab; unsigned long flags; stat(s, ALLOC_SLOWPATH); reread_page: - page = READ_ONCE(c->page); - if (!page) { + slab = READ_ONCE(c->slab); + if (!slab) { /* * if the node is not online or has no normal memory, just * ignore the node constraint @@ -2917,7 +2917,7 @@ reread_page: } redo: - if (unlikely(!node_match(page, node))) { + if (unlikely(!node_match(slab, node))) { /* * same as above but node_match() being false already * implies node != NUMA_NO_NODE @@ -2936,12 +2936,12 @@ redo: * PFMEMALLOC but right now, we are losing the pfmemalloc * information when the page leaves the per-cpu allocator */ - if (unlikely(!pfmemalloc_match(page_slab(page), gfpflags))) + if (unlikely(!pfmemalloc_match(slab, gfpflags))) goto deactivate_slab; /* must check again c->page in case we got preempted and it changed */ local_lock_irqsave(&s->cpu_slab->lock, flags); - if (unlikely(page != c->page)) { + if (unlikely(slab != c->slab)) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); goto reread_page; } @@ -2949,10 +2949,10 @@ redo: if (freelist) goto load_freelist; - freelist = get_freelist(s, page); + freelist = get_freelist(s, slab); if (!freelist) { - c->page = NULL; + c->slab = NULL; local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, DEACTIVATE_BYPASS); goto new_slab; @@ -2969,7 +2969,7 @@ load_freelist: * page is pointing to the page from which the objects are obtained. * That page must be frozen for per cpu allocations to work. */ - VM_BUG_ON(!c->page->frozen); + VM_BUG_ON(!c->slab->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); local_unlock_irqrestore(&s->cpu_slab->lock, flags); @@ -2978,21 +2978,21 @@ load_freelist: deactivate_slab: local_lock_irqsave(&s->cpu_slab->lock, flags); - if (page != c->page) { + if (slab != c->slab) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); goto reread_page; } freelist = c->freelist; - c->page = NULL; + c->slab = NULL; c->freelist = NULL; local_unlock_irqrestore(&s->cpu_slab->lock, flags); - deactivate_slab(s, page, freelist); + deactivate_slab(s, slab, freelist); new_slab: if (slub_percpu_partial(c)) { local_lock_irqsave(&s->cpu_slab->lock, flags); - if (unlikely(c->page)) { + if (unlikely(c->slab)) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); goto reread_page; } @@ -3002,8 +3002,8 @@ new_slab: goto new_objects; } - page = c->page = slub_percpu_partial(c); - slub_set_percpu_partial(c, page); + slab = c->slab = slub_percpu_partial(c); + slub_set_percpu_partial(c, slab); local_unlock_irqrestore(&s->cpu_slab->lock, flags); stat(s, CPU_PARTIAL_ALLOC); goto redo; @@ -3011,15 +3011,15 @@ new_slab: new_objects: - freelist = get_partial(s, gfpflags, node, &page); + freelist = get_partial(s, gfpflags, node, &slab); if (freelist) goto check_new_page; slub_put_cpu_ptr(s->cpu_slab); - page = new_slab(s, gfpflags, node); + slab = new_slab(s, gfpflags, node); c = slub_get_cpu_ptr(s->cpu_slab); - if (unlikely(!page)) { + if (unlikely(!slab)) { slab_out_of_memory(s, gfpflags, node); return NULL; } @@ -3028,15 +3028,15 @@ new_objects: * No other reference to the page yet so we can * muck around with it freely without cmpxchg */ - freelist = page->freelist; - page->freelist = NULL; + freelist = slab->freelist; + slab->freelist = NULL; stat(s, ALLOC_SLAB); check_new_page: if (kmem_cache_debug(s)) { - if (!alloc_debug_processing(s, page, freelist, addr)) { + if (!alloc_debug_processing(s, slab, freelist, addr)) { /* Slab failed checks. Next slab needed */ goto new_slab; } else { @@ -3048,7 +3048,7 @@ check_new_page: } } - if (unlikely(!pfmemalloc_match(page_slab(page), gfpflags))) + if (unlikely(!pfmemalloc_match(slab, gfpflags))) /* * For !pfmemalloc_match() case we don't load freelist so that * we don't make further mismatched allocations easier. @@ -3058,29 +3058,29 @@ check_new_page: retry_load_page: local_lock_irqsave(&s->cpu_slab->lock, flags); - if (unlikely(c->page)) { + if (unlikely(c->slab)) { void *flush_freelist = c->freelist; - struct page *flush_page = c->page; + struct slab *flush_slab = c->slab; - c->page = NULL; + c->slab = NULL; c->freelist = NULL; c->tid = next_tid(c->tid); local_unlock_irqrestore(&s->cpu_slab->lock, flags); - deactivate_slab(s, flush_page, flush_freelist); + deactivate_slab(s, flush_slab, flush_freelist); stat(s, CPUSLAB_FLUSH); goto retry_load_page; } - c->page = page; + c->slab = slab; goto load_freelist; return_single: - deactivate_slab(s, page, get_freepointer(s, freelist)); + deactivate_slab(s, slab, get_freepointer(s, freelist)); return freelist; } @@ -3137,7 +3137,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, { void *object; struct kmem_cache_cpu *c; - struct page *page; + struct slab *slab; unsigned long tid; struct obj_cgroup *objcg = NULL; bool init = false; @@ -3184,7 +3184,7 @@ redo: */ object = c->freelist; - page = c->page; + slab = c->slab; /* * We cannot use the lockless fastpath on PREEMPT_RT because if a * slowpath has taken the local_lock_irqsave(), it is not protected @@ -3193,7 +3193,7 @@ redo: * there is a suitable cpu freelist. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) || - unlikely(!object || !page || !node_match(page, node))) { + unlikely(!object || !slab || !node_match(slab, node))) { object = __slab_alloc(s, gfpflags, node, addr, c); } else { void *next_object = get_freepointer_safe(s, object); @@ -3298,14 +3298,14 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); * lock and free the item. If there is no additional partial page * handling required then we can return immediately. */ -static void __slab_free(struct kmem_cache *s, struct page *page, +static void __slab_free(struct kmem_cache *s, struct slab *slab, void *head, void *tail, int cnt, unsigned long addr) { void *prior; int was_frozen; - struct page new; + struct slab new; unsigned long counters; struct kmem_cache_node *n = NULL; unsigned long flags; @@ -3316,7 +3316,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, return; if (kmem_cache_debug(s) && - !free_debug_processing(s, page, head, tail, cnt, addr)) + !free_debug_processing(s, slab, head, tail, cnt, addr)) return; do { @@ -3324,8 +3324,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page, spin_unlock_irqrestore(&n->list_lock, flags); n = NULL; } - prior = page->freelist; - counters = page->counters; + prior = slab->freelist; + counters = slab->counters; set_freepointer(s, tail, prior); new.counters = counters; was_frozen = new.frozen; @@ -3344,7 +3344,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, } else { /* Needs to be taken off a list */ - n = get_node(s, page_to_nid(page)); + n = get_node(s, slab_nid(slab)); /* * Speculatively acquire the list_lock. * If the cmpxchg does not succeed then we may @@ -3358,7 +3358,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, } } - } while (!cmpxchg_double_slab(s, page, + } while (!cmpxchg_double_slab(s, slab, prior, counters, head, new.counters, "__slab_free")); @@ -3376,7 +3376,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * If we just froze the page then put it onto the * per cpu partial list. */ - put_cpu_partial(s, page, 1); + put_cpu_partial(s, slab, 1); stat(s, CPU_PARTIAL_FREE); } @@ -3391,8 +3391,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * then add it. */ if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) { - remove_full(s, n, page); - add_partial(n, page, DEACTIVATE_TO_TAIL); + remove_full(s, n, slab); + add_partial(n, slab, DEACTIVATE_TO_TAIL); stat(s, FREE_ADD_PARTIAL); } spin_unlock_irqrestore(&n->list_lock, flags); @@ -3403,16 +3403,16 @@ slab_empty: /* * Slab on the partial list. */ - remove_partial(n, page); + remove_partial(n, slab); stat(s, FREE_REMOVE_PARTIAL); } else { /* Slab must be on the full list */ - remove_full(s, n, page); + remove_full(s, n, slab); } spin_unlock_irqrestore(&n->list_lock, flags); stat(s, FREE_SLAB); - discard_slab(s, page); + discard_slab(s, slab); } /* @@ -3431,7 +3431,7 @@ slab_empty: * count (cnt). Bulk free indicated by tail pointer being set. */ static __always_inline void do_slab_free(struct kmem_cache *s, - struct page *page, void *head, void *tail, + struct slab *slab, void *head, void *tail, int cnt, unsigned long addr) { void *tail_obj = tail ? : head; @@ -3454,7 +3454,7 @@ redo: /* Same with comment on barrier() in slab_alloc_node() */ barrier(); - if (likely(page == c->page)) { + if (likely(slab == c->slab)) { #ifndef CONFIG_PREEMPT_RT void **freelist = READ_ONCE(c->freelist); @@ -3480,7 +3480,7 @@ redo: local_lock(&s->cpu_slab->lock); c = this_cpu_ptr(s->cpu_slab); - if (unlikely(page != c->page)) { + if (unlikely(slab != c->slab)) { local_unlock(&s->cpu_slab->lock); goto redo; } @@ -3495,11 +3495,11 @@ redo: #endif stat(s, FREE_FASTPATH); } else - __slab_free(s, page, head, tail_obj, cnt, addr); + __slab_free(s, slab, head, tail_obj, cnt, addr); } -static __always_inline void slab_free(struct kmem_cache *s, struct page *page, +static __always_inline void slab_free(struct kmem_cache *s, struct slab *slab, void *head, void *tail, int cnt, unsigned long addr) { @@ -3508,13 +3508,13 @@ static __always_inline void slab_free(struct kmem_cache *s, struct page *page, * to remove objects, whose reuse must be delayed. */ if (slab_free_freelist_hook(s, &head, &tail, &cnt)) - do_slab_free(s, page, head, tail, cnt, addr); + do_slab_free(s, slab, head, tail, cnt, addr); } #ifdef CONFIG_KASAN_GENERIC void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr) { - do_slab_free(cache, slab_page(virt_to_slab(x)), x, NULL, 1, addr); + do_slab_free(cache, virt_to_slab(x), x, NULL, 1, addr); } #endif @@ -3524,7 +3524,7 @@ void kmem_cache_free(struct kmem_cache *s, void *x) if (!s) return; trace_kmem_cache_free(_RET_IP_, x, s->name); - slab_free(s, slab_page(virt_to_slab(x)), x, NULL, 1, _RET_IP_); + slab_free(s, virt_to_slab(x), x, NULL, 1, _RET_IP_); } EXPORT_SYMBOL(kmem_cache_free); @@ -3654,7 +3654,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) if (!df.slab) continue; - slab_free(df.s, slab_page(df.slab), df.freelist, df.tail, df.cnt, _RET_IP_); + slab_free(df.s, df.slab, df.freelist, df.tail, df.cnt, _RET_IP_); } while (likely(size)); } EXPORT_SYMBOL(kmem_cache_free_bulk); @@ -3924,38 +3924,38 @@ static struct kmem_cache *kmem_cache_node; */ static void early_kmem_cache_node_alloc(int node) { - struct page *page; + struct slab *slab; struct kmem_cache_node *n; BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node)); - page = new_slab(kmem_cache_node, GFP_NOWAIT, node); + slab = new_slab(kmem_cache_node, GFP_NOWAIT, node); - BUG_ON(!page); - if (page_to_nid(page) != node) { + BUG_ON(!slab); + if (slab_nid(slab) != node) { pr_err("SLUB: Unable to allocate memory from node %d\n", node); pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n"); } - n = page->freelist; + n = slab->freelist; BUG_ON(!n); #ifdef CONFIG_SLUB_DEBUG init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); init_tracking(kmem_cache_node, n); #endif n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL, false); - page->freelist = get_freepointer(kmem_cache_node, n); - page->inuse = 1; - page->frozen = 0; + slab->freelist = get_freepointer(kmem_cache_node, n); + slab->inuse = 1; + slab->frozen = 0; kmem_cache_node->node[node] = n; init_kmem_cache_node(n); - inc_slabs_node(kmem_cache_node, node, page->objects); + inc_slabs_node(kmem_cache_node, node, slab->objects); /* * No locks need to be taken here as it has just been * initialized and there is no concurrent access. */ - __add_partial(n, page, DEACTIVATE_TO_HEAD); + __add_partial(n, slab, DEACTIVATE_TO_HEAD); } static void free_kmem_cache_nodes(struct kmem_cache *s) @@ -4241,20 +4241,20 @@ error: return -EINVAL; } -static void list_slab_objects(struct kmem_cache *s, struct page *page, +static void list_slab_objects(struct kmem_cache *s, struct slab *slab, const char *text) { #ifdef CONFIG_SLUB_DEBUG - void *addr = page_address(page); + void *addr = slab_address(slab); unsigned long flags; unsigned long *map; void *p; - slab_err(s, page, text, s->name); - slab_lock(page, &flags); + slab_err(s, slab, text, s->name); + slab_lock(slab, &flags); - map = get_map(s, page); - for_each_object(p, s, addr, page->objects) { + map = get_map(s, slab); + for_each_object(p, s, addr, slab->objects) { if (!test_bit(__obj_to_index(s, addr, p), map)) { pr_err("Object 0x%p @offset=%tu\n", p, p - addr); @@ -4262,7 +4262,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, } } put_map(map); - slab_unlock(page, &flags); + slab_unlock(slab, &flags); #endif } @@ -4274,23 +4274,23 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { LIST_HEAD(discard); - struct page *page, *h; + struct slab *slab, *h; BUG_ON(irqs_disabled()); spin_lock_irq(&n->list_lock); - list_for_each_entry_safe(page, h, &n->partial, slab_list) { - if (!page->inuse) { - remove_partial(n, page); - list_add(&page->slab_list, &discard); + list_for_each_entry_safe(slab, h, &n->partial, slab_list) { + if (!slab->inuse) { + remove_partial(n, slab); + list_add(&slab->slab_list, &discard); } else { - list_slab_objects(s, page, + list_slab_objects(s, slab, "Objects remaining in %s on __kmem_cache_shutdown()"); } } spin_unlock_irq(&n->list_lock); - list_for_each_entry_safe(page, h, &discard, slab_list) - discard_slab(s, page); + list_for_each_entry_safe(slab, h, &discard, slab_list) + discard_slab(s, slab); } bool __kmem_cache_empty(struct kmem_cache *s) @@ -4560,7 +4560,7 @@ void kfree(const void *x) return; } slab = folio_slab(folio); - slab_free(slab->slab_cache, slab_page(slab), object, NULL, 1, _RET_IP_); + slab_free(slab->slab_cache, slab, object, NULL, 1, _RET_IP_); } EXPORT_SYMBOL(kfree); @@ -4580,8 +4580,8 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s) int node; int i; struct kmem_cache_node *n; - struct page *page; - struct page *t; + struct slab *slab; + struct slab *t; struct list_head discard; struct list_head promote[SHRINK_PROMOTE_MAX]; unsigned long flags; @@ -4600,8 +4600,8 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s) * Note that concurrent frees may occur while we hold the * list_lock. page->inuse here is the upper limit. */ - list_for_each_entry_safe(page, t, &n->partial, slab_list) { - int free = page->objects - page->inuse; + list_for_each_entry_safe(slab, t, &n->partial, slab_list) { + int free = slab->objects - slab->inuse; /* Do not reread page->inuse */ barrier(); @@ -4609,11 +4609,11 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s) /* We do not keep full slabs on the list */ BUG_ON(free <= 0); - if (free == page->objects) { - list_move(&page->slab_list, &discard); + if (free == slab->objects) { + list_move(&slab->slab_list, &discard); n->nr_partial--; } else if (free <= SHRINK_PROMOTE_MAX) - list_move(&page->slab_list, promote + free - 1); + list_move(&slab->slab_list, promote + free - 1); } /* @@ -4626,8 +4626,8 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s) spin_unlock_irqrestore(&n->list_lock, flags); /* Release empty slabs */ - list_for_each_entry_safe(page, t, &discard, slab_list) - discard_slab(s, page); + list_for_each_entry_safe(slab, t, &discard, slab_list) + discard_slab(s, slab); if (slabs_node(s, node)) ret = 1; @@ -4788,7 +4788,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) */ __flush_cpu_slab(s, smp_processor_id()); for_each_kmem_cache_node(s, node, n) { - struct page *p; + struct slab *p; list_for_each_entry(p, &n->partial, slab_list) p->slab_cache = s; @@ -4966,54 +4966,54 @@ EXPORT_SYMBOL(__kmalloc_node_track_caller); #endif #ifdef CONFIG_SYSFS -static int count_inuse(struct page *page) +static int count_inuse(struct slab *slab) { - return page->inuse; + return slab->inuse; } -static int count_total(struct page *page) +static int count_total(struct slab *slab) { - return page->objects; + return slab->objects; } #endif #ifdef CONFIG_SLUB_DEBUG -static void validate_slab(struct kmem_cache *s, struct page *page, +static void validate_slab(struct kmem_cache *s, struct slab *slab, unsigned long *obj_map) { void *p; - void *addr = page_address(page); + void *addr = slab_address(slab); unsigned long flags; - slab_lock(page, &flags); + slab_lock(slab, &flags); - if (!check_slab(s, page) || !on_freelist(s, page, NULL)) + if (!check_slab(s, slab) || !on_freelist(s, slab, NULL)) goto unlock; /* Now we know that a valid freelist exists */ - __fill_map(obj_map, s, page); - for_each_object(p, s, addr, page->objects) { + __fill_map(obj_map, s, slab); + for_each_object(p, s, addr, slab->objects) { u8 val = test_bit(__obj_to_index(s, addr, p), obj_map) ? SLUB_RED_INACTIVE : SLUB_RED_ACTIVE; - if (!check_object(s, page, p, val)) + if (!check_object(s, slab, p, val)) break; } unlock: - slab_unlock(page, &flags); + slab_unlock(slab, &flags); } static int validate_slab_node(struct kmem_cache *s, struct kmem_cache_node *n, unsigned long *obj_map) { unsigned long count = 0; - struct page *page; + struct slab *slab; unsigned long flags; spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, slab_list) { - validate_slab(s, page, obj_map); + list_for_each_entry(slab, &n->partial, slab_list) { + validate_slab(s, slab, obj_map); count++; } if (count != n->nr_partial) { @@ -5025,8 +5025,8 @@ static int validate_slab_node(struct kmem_cache *s, if (!(s->flags & SLAB_STORE_USER)) goto out; - list_for_each_entry(page, &n->full, slab_list) { - validate_slab(s, page, obj_map); + list_for_each_entry(slab, &n->full, slab_list) { + validate_slab(s, slab, obj_map); count++; } if (count != atomic_long_read(&n->nr_slabs)) { @@ -5192,15 +5192,15 @@ static int add_location(struct loc_track *t, struct kmem_cache *s, } static void process_slab(struct loc_track *t, struct kmem_cache *s, - struct page *page, enum track_item alloc, + struct slab *slab, enum track_item alloc, unsigned long *obj_map) { - void *addr = page_address(page); + void *addr = slab_address(slab); void *p; - __fill_map(obj_map, s, page); + __fill_map(obj_map, s, slab); - for_each_object(p, s, addr, page->objects) + for_each_object(p, s, addr, slab->objects) if (!test_bit(__obj_to_index(s, addr, p), obj_map)) add_location(t, s, get_track(s, p, alloc)); } @@ -5242,32 +5242,32 @@ static ssize_t show_slab_objects(struct kmem_cache *s, struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); int node; - struct page *page; + struct slab *slab; - page = READ_ONCE(c->page); - if (!page) + slab = READ_ONCE(c->slab); + if (!slab) continue; - node = page_to_nid(page); + node = slab_nid(slab); if (flags & SO_TOTAL) - x = page->objects; + x = slab->objects; else if (flags & SO_OBJECTS) - x = page->inuse; + x = slab->inuse; else x = 1; total += x; nodes[node] += x; - page = slub_percpu_partial_read_once(c); - if (page) { - node = page_to_nid(page); + slab = slub_percpu_partial_read_once(c); + if (slab) { + node = slab_nid(slab); if (flags & SO_TOTAL) WARN_ON_ONCE(1); else if (flags & SO_OBJECTS) WARN_ON_ONCE(1); else - x = page->pages; + x = slab->slabs; total += x; nodes[node] += x; } @@ -5469,33 +5469,33 @@ SLAB_ATTR_RO(objects_partial); static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) { int objects = 0; - int pages = 0; + int slabs = 0; int cpu; int len = 0; for_each_online_cpu(cpu) { - struct page *page; + struct slab *slab; - page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); + slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); - if (page) - pages += page->pages; + if (slab) + slabs += slab->slabs; } /* Approximate half-full pages , see slub_set_cpu_partial() */ - objects = (pages * oo_objects(s->oo)) / 2; - len += sysfs_emit_at(buf, len, "%d(%d)", objects, pages); + objects = (slabs * oo_objects(s->oo)) / 2; + len += sysfs_emit_at(buf, len, "%d(%d)", objects, slabs); #ifdef CONFIG_SMP for_each_online_cpu(cpu) { - struct page *page; + struct slab *slab; - page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); - if (page) { - pages = READ_ONCE(page->pages); - objects = (pages * oo_objects(s->oo)) / 2; + slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu)); + if (slab) { + slabs = READ_ONCE(slab->slabs); + objects = (slabs * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, " C%d=%d(%d)", - cpu, objects, pages); + cpu, objects, slabs); } } #endif @@ -6163,16 +6163,16 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep) for_each_kmem_cache_node(s, node, n) { unsigned long flags; - struct page *page; + struct slab *slab; if (!atomic_long_read(&n->nr_slabs)) continue; spin_lock_irqsave(&n->list_lock, flags); - list_for_each_entry(page, &n->partial, slab_list) - process_slab(t, s, page, alloc, obj_map); - list_for_each_entry(page, &n->full, slab_list) - process_slab(t, s, page, alloc, obj_map); + list_for_each_entry(slab, &n->partial, slab_list) + process_slab(t, s, slab, alloc, obj_map); + list_for_each_entry(slab, &n->full, slab_list) + process_slab(t, s, slab, alloc, obj_map); spin_unlock_irqrestore(&n->list_lock, flags); } -- cgit v1.2.3 From c2092c12064a9728b2928979f88575cc1c2247fa Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 15 Nov 2021 16:55:15 +0100 Subject: mm/slub: Finish struct page to struct slab conversion Update comments mentioning pages to mention slabs where appropriate. Also some goto labels. Signed-off-by: Vlastimil Babka Reviewed-by: Roman Gushchin --- include/linux/slub_def.h | 2 +- mm/slub.c | 105 +++++++++++++++++++++++------------------------ 2 files changed, 53 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 00d99afe1c0e..8a9c2876ca89 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -99,7 +99,7 @@ struct kmem_cache { #ifdef CONFIG_SLUB_CPU_PARTIAL /* Number of per cpu partial objects to keep around */ unsigned int cpu_partial; - /* Number of per cpu partial pages to keep around */ + /* Number of per cpu partial slabs to keep around */ unsigned int cpu_partial_slabs; #endif struct kmem_cache_order_objects oo; diff --git a/mm/slub.c b/mm/slub.c index e89208f3197a..cc64ba9d9963 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -48,7 +48,7 @@ * 1. slab_mutex (Global Mutex) * 2. node->list_lock (Spinlock) * 3. kmem_cache->cpu_slab->lock (Local lock) - * 4. slab_lock(page) (Only on some arches or for debugging) + * 4. slab_lock(slab) (Only on some arches or for debugging) * 5. object_map_lock (Only for debugging) * * slab_mutex @@ -64,19 +64,19 @@ * * The slab_lock is only used for debugging and on arches that do not * have the ability to do a cmpxchg_double. It only protects: - * A. page->freelist -> List of object free in a page - * B. page->inuse -> Number of objects in use - * C. page->objects -> Number of objects in page - * D. page->frozen -> frozen state + * A. slab->freelist -> List of free objects in a slab + * B. slab->inuse -> Number of objects in use + * C. slab->objects -> Number of objects in slab + * D. slab->frozen -> frozen state * * Frozen slabs * * If a slab is frozen then it is exempt from list management. It is not * on any list except per cpu partial list. The processor that froze the - * slab is the one who can perform list operations on the page. Other + * slab is the one who can perform list operations on the slab. Other * processors may put objects onto the freelist but the processor that * froze the slab is the only one that can retrieve the objects from the - * page's freelist. + * slab's freelist. * * list_lock * @@ -135,7 +135,7 @@ * minimal so we rely on the page allocators per cpu caches for * fast frees and allocs. * - * page->frozen The slab is frozen and exempt from list processing. + * slab->frozen The slab is frozen and exempt from list processing. * This means that the slab is dedicated to a purpose * such as satisfying allocations for a specific * processor. Objects may be freed in the slab while @@ -250,7 +250,7 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s) #define OO_SHIFT 16 #define OO_MASK ((1 << OO_SHIFT) - 1) -#define MAX_OBJS_PER_PAGE 32767 /* since page.objects is u15 */ +#define MAX_OBJS_PER_PAGE 32767 /* since slab.objects is u15 */ /* Internal SLUB flags */ /* Poison object */ @@ -423,8 +423,8 @@ static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects) /* * We take the number of objects but actually limit the number of - * pages on the per cpu partial list, in order to limit excessive - * growth of the list. For simplicity we assume that the pages will + * slabs on the per cpu partial list, in order to limit excessive + * growth of the list. For simplicity we assume that the slabs will * be half-full. */ nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo)); @@ -594,9 +594,9 @@ static inline bool slab_add_kunit_errors(void) { return false; } #endif /* - * Determine a map of object in use on a page. + * Determine a map of objects in use in a slab. * - * Node listlock must be held to guarantee that the page does + * Node listlock must be held to guarantee that the slab does * not vanish from under us. */ static unsigned long *get_map(struct kmem_cache *s, struct slab *slab) @@ -1139,7 +1139,7 @@ static int check_slab(struct kmem_cache *s, struct slab *slab) } /* - * Determine if a certain object on a page is on the freelist. Must hold the + * Determine if a certain object in a slab is on the freelist. Must hold the * slab lock to guarantee that the chains are in a consistent state. */ static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search) @@ -2184,7 +2184,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n, } /* - * Get a page from somewhere. Search in increasing NUMA distances. + * Get a slab from somewhere. Search in increasing NUMA distances. */ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, struct slab **ret_slab) @@ -2248,7 +2248,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags, } /* - * Get a partial page, lock it and return it. + * Get a partial slab, lock it and return it. */ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node, struct slab **ret_slab) @@ -2340,7 +2340,7 @@ static void init_kmem_cache_cpus(struct kmem_cache *s) } /* - * Finishes removing the cpu slab. Merges cpu's freelist with page's freelist, + * Finishes removing the cpu slab. Merges cpu's freelist with slab's freelist, * unfreezes the slabs and puts it on the proper list. * Assumes the slab has been already safely taken away from kmem_cache_cpu * by the caller. @@ -2387,18 +2387,18 @@ static void deactivate_slab(struct kmem_cache *s, struct slab *slab, } /* - * Stage two: Unfreeze the page while splicing the per-cpu - * freelist to the head of page's freelist. + * Stage two: Unfreeze the slab while splicing the per-cpu + * freelist to the head of slab's freelist. * - * Ensure that the page is unfrozen while the list presence + * Ensure that the slab is unfrozen while the list presence * reflects the actual number of objects during unfreeze. * * We setup the list membership and then perform a cmpxchg - * with the count. If there is a mismatch then the page - * is not unfrozen but the page is on the wrong list. + * with the count. If there is a mismatch then the slab + * is not unfrozen but the slab is on the wrong list. * * Then we restart the process which may have to remove - * the page from the list that we just put it on again + * the slab from the list that we just put it on again * because the number of objects in the slab may have * changed. */ @@ -2426,9 +2426,8 @@ redo: if (!lock) { lock = 1; /* - * Taking the spinlock removes the possibility - * that acquire_slab() will see a slab page that - * is frozen + * Taking the spinlock removes the possibility that + * acquire_slab() will see a slab that is frozen */ spin_lock_irqsave(&n->list_lock, flags); } @@ -2569,8 +2568,8 @@ static void unfreeze_partials_cpu(struct kmem_cache *s, } /* - * Put a page that was just frozen (in __slab_free|get_partial_node) into a - * partial page slot if available. + * Put a slab that was just frozen (in __slab_free|get_partial_node) into a + * partial slab slot if available. * * If we did not find a slot then simply move all the partials to the * per node partial list. @@ -2841,12 +2840,12 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags) } /* - * Check the page->freelist of a page and either transfer the freelist to the - * per cpu freelist or deactivate the page. + * Check the slab->freelist and either transfer the freelist to the + * per cpu freelist or deactivate the slab. * - * The page is still frozen if the return value is not NULL. + * The slab is still frozen if the return value is not NULL. * - * If this function returns NULL then the page has been unfrozen. + * If this function returns NULL then the slab has been unfrozen. */ static inline void *get_freelist(struct kmem_cache *s, struct slab *slab) { @@ -2902,7 +2901,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, stat(s, ALLOC_SLOWPATH); -reread_page: +reread_slab: slab = READ_ONCE(c->slab); if (!slab) { @@ -2939,11 +2938,11 @@ redo: if (unlikely(!pfmemalloc_match(slab, gfpflags))) goto deactivate_slab; - /* must check again c->page in case we got preempted and it changed */ + /* must check again c->slab in case we got preempted and it changed */ local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(slab != c->slab)) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); - goto reread_page; + goto reread_slab; } freelist = c->freelist; if (freelist) @@ -2966,8 +2965,8 @@ load_freelist: /* * freelist is pointing to the list of objects to be used. - * page is pointing to the page from which the objects are obtained. - * That page must be frozen for per cpu allocations to work. + * slab is pointing to the slab from which the objects are obtained. + * That slab must be frozen for per cpu allocations to work. */ VM_BUG_ON(!c->slab->frozen); c->freelist = get_freepointer(s, freelist); @@ -2980,7 +2979,7 @@ deactivate_slab: local_lock_irqsave(&s->cpu_slab->lock, flags); if (slab != c->slab) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); - goto reread_page; + goto reread_slab; } freelist = c->freelist; c->slab = NULL; @@ -2994,7 +2993,7 @@ new_slab: local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(c->slab)) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); - goto reread_page; + goto reread_slab; } if (unlikely(!slub_percpu_partial(c))) { local_unlock_irqrestore(&s->cpu_slab->lock, flags); @@ -3013,7 +3012,7 @@ new_objects: freelist = get_partial(s, gfpflags, node, &slab); if (freelist) - goto check_new_page; + goto check_new_slab; slub_put_cpu_ptr(s->cpu_slab); slab = new_slab(s, gfpflags, node); @@ -3025,7 +3024,7 @@ new_objects: } /* - * No other reference to the page yet so we can + * No other reference to the slab yet so we can * muck around with it freely without cmpxchg */ freelist = slab->freelist; @@ -3033,7 +3032,7 @@ new_objects: stat(s, ALLOC_SLAB); -check_new_page: +check_new_slab: if (kmem_cache_debug(s)) { if (!alloc_debug_processing(s, slab, freelist, addr)) { @@ -3055,7 +3054,7 @@ check_new_page: */ goto return_single; -retry_load_page: +retry_load_slab: local_lock_irqsave(&s->cpu_slab->lock, flags); if (unlikely(c->slab)) { @@ -3072,7 +3071,7 @@ retry_load_page: stat(s, CPUSLAB_FLUSH); - goto retry_load_page; + goto retry_load_slab; } c->slab = slab; @@ -3169,9 +3168,9 @@ redo: /* * Irqless object alloc/free algorithm used here depends on sequence * of fetching cpu_slab's data. tid should be fetched before anything - * on c to guarantee that object and page associated with previous tid + * on c to guarantee that object and slab associated with previous tid * won't be used with current tid. If we fetch tid first, object and - * page could be one associated with next tid and our alloc/free + * slab could be one associated with next tid and our alloc/free * request will be failed. In this case, we will retry. So, no problem. */ barrier(); @@ -3295,7 +3294,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); * have a longer lifetime than the cpu slabs in most processing loads. * * So we still attempt to reduce cache line usage. Just take the slab - * lock and free the item. If there is no additional partial page + * lock and free the item. If there is no additional partial slab * handling required then we can return immediately. */ static void __slab_free(struct kmem_cache *s, struct slab *slab, @@ -3373,7 +3372,7 @@ static void __slab_free(struct kmem_cache *s, struct slab *slab, stat(s, FREE_FROZEN); } else if (new.frozen) { /* - * If we just froze the page then put it onto the + * If we just froze the slab then put it onto the * per cpu partial list. */ put_cpu_partial(s, slab, 1); @@ -3427,7 +3426,7 @@ slab_empty: * with all sorts of special processing. * * Bulk free of a freelist with several objects (all pointing to the - * same page) possible by specifying head and tail ptr, plus objects + * same slab) possible by specifying head and tail ptr, plus objects * count (cnt). Bulk free indicated by tail pointer being set. */ static __always_inline void do_slab_free(struct kmem_cache *s, @@ -4213,7 +4212,7 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) #endif /* - * The larger the object size is, the more pages we want on the partial + * The larger the object size is, the more slabs we want on the partial * list to avoid pounding the page allocator excessively. */ set_min_partial(s, ilog2(s->size) / 2); @@ -4598,12 +4597,12 @@ static int __kmem_cache_do_shrink(struct kmem_cache *s) * Build lists of slabs to discard or promote. * * Note that concurrent frees may occur while we hold the - * list_lock. page->inuse here is the upper limit. + * list_lock. slab->inuse here is the upper limit. */ list_for_each_entry_safe(slab, t, &n->partial, slab_list) { int free = slab->objects - slab->inuse; - /* Do not reread page->inuse */ + /* Do not reread slab->inuse */ barrier(); /* We do not keep full slabs on the list */ @@ -5482,7 +5481,7 @@ static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf) slabs += slab->slabs; } - /* Approximate half-full pages , see slub_set_cpu_partial() */ + /* Approximate half-full slabs, see slub_set_cpu_partial() */ objects = (slabs * oo_objects(s->oo)) / 2; len += sysfs_emit_at(buf, len, "%d(%d)", objects, slabs); -- cgit v1.2.3 From 40f3bf0cb04c91d33531b1b95788ad2f0e4062cf Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 2 Nov 2021 15:42:04 +0100 Subject: mm: Convert struct page to struct slab in functions used by other subsystems KASAN, KFENCE and memcg interact with SLAB or SLUB internals through functions nearest_obj(), obj_to_index() and objs_per_slab() that use struct page as parameter. This patch converts it to struct slab including all callers, through a coccinelle semantic patch. // Options: --include-headers --no-includes --smpl-spacing include/linux/slab_def.h include/linux/slub_def.h mm/slab.h mm/kasan/*.c mm/kfence/kfence_test.c mm/memcontrol.c mm/slab.c mm/slub.c // Note: needs coccinelle 1.1.1 to avoid breaking whitespace @@ @@ -objs_per_slab_page( +objs_per_slab( ... ) { ... } @@ @@ -objs_per_slab_page( +objs_per_slab( ... ) @@ identifier fn =~ "obj_to_index|objs_per_slab"; @@ fn(..., - const struct page *page + const struct slab *slab ,...) { <... ( - page_address(page) + slab_address(slab) | - page + slab ) ...> } @@ identifier fn =~ "nearest_obj"; @@ fn(..., - struct page *page + const struct slab *slab ,...) { <... ( - page_address(page) + slab_address(slab) | - page + slab ) ...> } @@ identifier fn =~ "nearest_obj|obj_to_index|objs_per_slab"; expression E; @@ fn(..., ( - slab_page(E) + E | - virt_to_page(E) + virt_to_slab(E) | - virt_to_head_page(E) + virt_to_slab(E) | - page + page_slab(page) ) ,...) Signed-off-by: Vlastimil Babka Reviewed-by: Andrey Konovalov Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Julia Lawall Cc: Luis Chamberlain Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Marco Elver Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Cc: --- include/linux/slab_def.h | 16 ++++++++-------- include/linux/slub_def.h | 18 +++++++++--------- mm/kasan/common.c | 4 ++-- mm/kasan/generic.c | 2 +- mm/kasan/report.c | 2 +- mm/kasan/report_tags.c | 2 +- mm/kfence/kfence_test.c | 4 ++-- mm/memcontrol.c | 4 ++-- mm/slab.c | 10 +++++----- mm/slab.h | 4 ++-- mm/slub.c | 2 +- 11 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h index 3aa5e1e73ab6..e24c9aff6fed 100644 --- a/include/linux/slab_def.h +++ b/include/linux/slab_def.h @@ -87,11 +87,11 @@ struct kmem_cache { struct kmem_cache_node *node[MAX_NUMNODES]; }; -static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, +static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab, void *x) { - void *object = x - (x - page->s_mem) % cache->size; - void *last_object = page->s_mem + (cache->num - 1) * cache->size; + void *object = x - (x - slab->s_mem) % cache->size; + void *last_object = slab->s_mem + (cache->num - 1) * cache->size; if (unlikely(object > last_object)) return last_object; @@ -106,16 +106,16 @@ static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, * reciprocal_divide(offset, cache->reciprocal_buffer_size) */ static inline unsigned int obj_to_index(const struct kmem_cache *cache, - const struct page *page, void *obj) + const struct slab *slab, void *obj) { - u32 offset = (obj - page->s_mem); + u32 offset = (obj - slab->s_mem); return reciprocal_divide(offset, cache->reciprocal_buffer_size); } -static inline int objs_per_slab_page(const struct kmem_cache *cache, - const struct page *page) +static inline int objs_per_slab(const struct kmem_cache *cache, + const struct slab *slab) { - if (is_kfence_address(page_address(page))) + if (is_kfence_address(slab_address(slab))) return 1; return cache->num; } diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index 8a9c2876ca89..33c5c0e3bd8d 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -158,11 +158,11 @@ static inline void sysfs_slab_release(struct kmem_cache *s) void *fixup_red_left(struct kmem_cache *s, void *p); -static inline void *nearest_obj(struct kmem_cache *cache, struct page *page, +static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab, void *x) { - void *object = x - (x - page_address(page)) % cache->size; - void *last_object = page_address(page) + - (page->objects - 1) * cache->size; + void *object = x - (x - slab_address(slab)) % cache->size; + void *last_object = slab_address(slab) + + (slab->objects - 1) * cache->size; void *result = (unlikely(object > last_object)) ? last_object : object; result = fixup_red_left(cache, result); @@ -178,16 +178,16 @@ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, } static inline unsigned int obj_to_index(const struct kmem_cache *cache, - const struct page *page, void *obj) + const struct slab *slab, void *obj) { if (is_kfence_address(obj)) return 0; - return __obj_to_index(cache, page_address(page), obj); + return __obj_to_index(cache, slab_address(slab), obj); } -static inline int objs_per_slab_page(const struct kmem_cache *cache, - const struct page *page) +static inline int objs_per_slab(const struct kmem_cache *cache, + const struct slab *slab) { - return page->objects; + return slab->objects; } #endif /* _LINUX_SLUB_DEF_H */ diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 8428da2aaf17..6a1cd2d38bff 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -298,7 +298,7 @@ static inline u8 assign_tag(struct kmem_cache *cache, /* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */ #ifdef CONFIG_SLAB /* For SLAB assign tags based on the object index in the freelist. */ - return (u8)obj_to_index(cache, virt_to_head_page(object), (void *)object); + return (u8)obj_to_index(cache, virt_to_slab(object), (void *)object); #else /* * For SLUB assign a random tag during slab creation, otherwise reuse @@ -341,7 +341,7 @@ static inline bool ____kasan_slab_free(struct kmem_cache *cache, void *object, if (is_kfence_address(object)) return false; - if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) != + if (unlikely(nearest_obj(cache, virt_to_slab(object), object) != object)) { kasan_report_invalid_free(tagged_object, ip); return true; diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 84a038b07c6f..5d0b79416c4e 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -339,7 +339,7 @@ static void __kasan_record_aux_stack(void *addr, bool can_alloc) return; cache = page->slab_cache; - object = nearest_obj(cache, page, addr); + object = nearest_obj(cache, page_slab(page), addr); alloc_meta = kasan_get_alloc_meta(cache, object); if (!alloc_meta) return; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 0bc10f452f7e..e00999dc6499 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -249,7 +249,7 @@ static void print_address_description(void *addr, u8 tag) if (page && PageSlab(page)) { struct kmem_cache *cache = page->slab_cache; - void *object = nearest_obj(cache, page, addr); + void *object = nearest_obj(cache, page_slab(page), addr); describe_object(cache, object, addr, tag); } diff --git a/mm/kasan/report_tags.c b/mm/kasan/report_tags.c index 8a319fc16dab..06c21dd77493 100644 --- a/mm/kasan/report_tags.c +++ b/mm/kasan/report_tags.c @@ -23,7 +23,7 @@ const char *kasan_get_bug_type(struct kasan_access_info *info) page = kasan_addr_to_page(addr); if (page && PageSlab(page)) { cache = page->slab_cache; - object = nearest_obj(cache, page, (void *)addr); + object = nearest_obj(cache, page_slab(page), (void *)addr); alloc_meta = kasan_get_alloc_meta(cache, object); if (alloc_meta) { diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index 695030c1fff8..f7276711d7b9 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -291,8 +291,8 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat * even for KFENCE objects; these are required so that * memcg accounting works correctly. */ - KUNIT_EXPECT_EQ(test, obj_to_index(s, page, alloc), 0U); - KUNIT_EXPECT_EQ(test, objs_per_slab_page(s, page), 1); + KUNIT_EXPECT_EQ(test, obj_to_index(s, page_slab(page), alloc), 0U); + KUNIT_EXPECT_EQ(test, objs_per_slab(s, page_slab(page)), 1); if (policy == ALLOCATE_ANY) return alloc; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2ed5f2a0879d..f7b789e692a0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2819,7 +2819,7 @@ static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp, bool new_page) { - unsigned int objects = objs_per_slab_page(s, page); + unsigned int objects = objs_per_slab(s, page_slab(page)); unsigned long memcg_data; void *vec; @@ -2881,7 +2881,7 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p) struct obj_cgroup *objcg; unsigned int off; - off = obj_to_index(page->slab_cache, page, p); + off = obj_to_index(page->slab_cache, page_slab(page), p); objcg = page_objcgs(page)[off]; if (objcg) return obj_cgroup_memcg(objcg); diff --git a/mm/slab.c b/mm/slab.c index 547ed068a569..c13258116791 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1559,7 +1559,7 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp) struct slab *slab = virt_to_slab(objp); unsigned int objnr; - objnr = obj_to_index(cachep, slab_page(slab), objp); + objnr = obj_to_index(cachep, slab, objp); if (objnr) { objp = index_to_obj(cachep, slab, objnr - 1); realobj = (char *)objp + obj_offset(cachep); @@ -2529,7 +2529,7 @@ static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slab) static void slab_put_obj(struct kmem_cache *cachep, struct slab *slab, void *objp) { - unsigned int objnr = obj_to_index(cachep, slab_page(slab), objp); + unsigned int objnr = obj_to_index(cachep, slab, objp); #if DEBUG unsigned int i; @@ -2716,7 +2716,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, if (cachep->flags & SLAB_STORE_USER) *dbg_userword(cachep, objp) = (void *)caller; - objnr = obj_to_index(cachep, slab_page(slab), objp); + objnr = obj_to_index(cachep, slab, objp); BUG_ON(objnr >= cachep->num); BUG_ON(objp != index_to_obj(cachep, slab, objnr)); @@ -3662,7 +3662,7 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) objp = object - obj_offset(cachep); kpp->kp_data_offset = obj_offset(cachep); slab = virt_to_slab(objp); - objnr = obj_to_index(cachep, slab_page(slab), objp); + objnr = obj_to_index(cachep, slab, objp); objp = index_to_obj(cachep, slab, objnr); kpp->kp_objp = objp; if (DEBUG && cachep->flags & SLAB_STORE_USER) @@ -4180,7 +4180,7 @@ void __check_heap_object(const void *ptr, unsigned long n, /* Find and validate object. */ cachep = slab->slab_cache; - objnr = obj_to_index(cachep, slab_page(slab), (void *)ptr); + objnr = obj_to_index(cachep, slab, (void *)ptr); BUG_ON(objnr >= cachep->num); /* Find offset within object. */ diff --git a/mm/slab.h b/mm/slab.h index 039babfde2fe..bca9181e96d7 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -483,7 +483,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, continue; } - off = obj_to_index(s, page, p[i]); + off = obj_to_index(s, page_slab(page), p[i]); obj_cgroup_get(objcg); page_objcgs(page)[off] = objcg; mod_objcg_state(objcg, page_pgdat(page), @@ -522,7 +522,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, else s = s_orig; - off = obj_to_index(s, page, p[i]); + off = obj_to_index(s, page_slab(page), p[i]); objcg = objcgs[off]; if (!objcg) continue; diff --git a/mm/slub.c b/mm/slub.c index cc64ba9d9963..ddf21c7a381a 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4342,7 +4342,7 @@ void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab) #else objp = objp0; #endif - objnr = obj_to_index(s, slab_page(slab), objp); + objnr = obj_to_index(s, slab, objp); kpp->kp_data_offset = (unsigned long)((char *)objp0 - (char *)objp); objp = base + s->size * objnr; kpp->kp_objp = objp; -- cgit v1.2.3 From 4b5f8d9a895ada8e0abb58ccd35d9fe229e3a595 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Tue, 2 Nov 2021 22:42:04 +0100 Subject: mm/memcg: Convert slab objcgs from struct page to struct slab page->memcg_data is used with MEMCG_DATA_OBJCGS flag only for slab pages so convert all the related infrastructure to struct slab. Also use struct folio instead of struct page when resolving object pointers. This is not just mechanistic changing of types and names. Now in mem_cgroup_from_obj() we use folio_test_slab() to decide if we interpret the folio as a real slab instead of a large kmalloc, instead of relying on MEMCG_DATA_OBJCGS bit that used to be checked in page_objcgs_check(). Similarly in memcg_slab_free_hook() where we can encounter kmalloc_large() pages (here the folio slab flag check is implied by virt_to_slab()). As a result, page_objcgs_check() can be dropped instead of converted. To avoid include cycles, move the inline definition of slab_objcgs() from memcontrol.h to mm/slab.h. Signed-off-by: Vlastimil Babka Reviewed-by: Roman Gushchin Cc: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: --- include/linux/memcontrol.h | 48 ------------------------------ mm/memcontrol.c | 55 ++++++++++++++++++---------------- mm/slab.h | 73 +++++++++++++++++++++++++++++++--------------- 3 files changed, 80 insertions(+), 96 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c5c403f4be6..e34112f6a369 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -536,45 +536,6 @@ static inline bool folio_memcg_kmem(struct folio *folio) return folio->memcg_data & MEMCG_DATA_KMEM; } -/* - * page_objcgs - get the object cgroups vector associated with a page - * @page: a pointer to the page struct - * - * Returns a pointer to the object cgroups vector associated with the page, - * or NULL. This function assumes that the page is known to have an - * associated object cgroups vector. It's not safe to call this function - * against pages, which might have an associated memory cgroup: e.g. - * kernel stack pages. - */ -static inline struct obj_cgroup **page_objcgs(struct page *page) -{ - unsigned long memcg_data = READ_ONCE(page->memcg_data); - - VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page); - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); - - return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); -} - -/* - * page_objcgs_check - get the object cgroups vector associated with a page - * @page: a pointer to the page struct - * - * Returns a pointer to the object cgroups vector associated with the page, - * or NULL. This function is safe to use if the page can be directly associated - * with a memory cgroup. - */ -static inline struct obj_cgroup **page_objcgs_check(struct page *page) -{ - unsigned long memcg_data = READ_ONCE(page->memcg_data); - - if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS)) - return NULL; - - VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); - - return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); -} #else static inline bool folio_memcg_kmem(struct folio *folio) @@ -582,15 +543,6 @@ static inline bool folio_memcg_kmem(struct folio *folio) return false; } -static inline struct obj_cgroup **page_objcgs(struct page *page) -{ - return NULL; -} - -static inline struct obj_cgroup **page_objcgs_check(struct page *page) -{ - return NULL; -} #endif static inline bool PageMemcgKmem(struct page *page) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index f7b789e692a0..4a7b3ebf8e48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2816,31 +2816,31 @@ static inline void mod_objcg_mlstate(struct obj_cgroup *objcg, rcu_read_unlock(); } -int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, - gfp_t gfp, bool new_page) +int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s, + gfp_t gfp, bool new_slab) { - unsigned int objects = objs_per_slab(s, page_slab(page)); + unsigned int objects = objs_per_slab(s, slab); unsigned long memcg_data; void *vec; gfp &= ~OBJCGS_CLEAR_MASK; vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp, - page_to_nid(page)); + slab_nid(slab)); if (!vec) return -ENOMEM; memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS; - if (new_page) { + if (new_slab) { /* - * If the slab page is brand new and nobody can yet access - * it's memcg_data, no synchronization is required and - * memcg_data can be simply assigned. + * If the slab is brand new and nobody can yet access its + * memcg_data, no synchronization is required and memcg_data can + * be simply assigned. */ - page->memcg_data = memcg_data; - } else if (cmpxchg(&page->memcg_data, 0, memcg_data)) { + slab->memcg_data = memcg_data; + } else if (cmpxchg(&slab->memcg_data, 0, memcg_data)) { /* - * If the slab page is already in use, somebody can allocate - * and assign obj_cgroups in parallel. In this case the existing + * If the slab is already in use, somebody can allocate and + * assign obj_cgroups in parallel. In this case the existing * objcg vector should be reused. */ kfree(vec); @@ -2865,38 +2865,43 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, */ struct mem_cgroup *mem_cgroup_from_obj(void *p) { - struct page *page; + struct folio *folio; if (mem_cgroup_disabled()) return NULL; - page = virt_to_head_page(p); + folio = virt_to_folio(p); /* * Slab objects are accounted individually, not per-page. * Memcg membership data for each individual object is saved in - * the page->obj_cgroups. + * slab->memcg_data. */ - if (page_objcgs_check(page)) { - struct obj_cgroup *objcg; + if (folio_test_slab(folio)) { + struct obj_cgroup **objcgs; + struct slab *slab; unsigned int off; - off = obj_to_index(page->slab_cache, page_slab(page), p); - objcg = page_objcgs(page)[off]; - if (objcg) - return obj_cgroup_memcg(objcg); + slab = folio_slab(folio); + objcgs = slab_objcgs(slab); + if (!objcgs) + return NULL; + + off = obj_to_index(slab->slab_cache, slab, p); + if (objcgs[off]) + return obj_cgroup_memcg(objcgs[off]); return NULL; } /* - * page_memcg_check() is used here, because page_has_obj_cgroups() - * check above could fail because the object cgroups vector wasn't set - * at that moment, but it can be set concurrently. + * page_memcg_check() is used here, because in theory we can encounter + * a folio where the slab flag has been cleared already, but + * slab->memcg_data has not been freed yet * page_memcg_check(page) will guarantee that a proper memory * cgroup pointer or NULL will be returned. */ - return page_memcg_check(page); + return page_memcg_check(folio_page(folio, 0)); } __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) diff --git a/mm/slab.h b/mm/slab.h index bca9181e96d7..b8d7ed42cca8 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -412,15 +412,33 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla } #ifdef CONFIG_MEMCG_KMEM -int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, - gfp_t gfp, bool new_page); +/* + * slab_objcgs - get the object cgroups vector associated with a slab + * @slab: a pointer to the slab struct + * + * Returns a pointer to the object cgroups vector associated with the slab, + * or NULL if no such vector has been associated yet. + */ +static inline struct obj_cgroup **slab_objcgs(struct slab *slab) +{ + unsigned long memcg_data = READ_ONCE(slab->memcg_data); + + VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), + slab_page(slab)); + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab)); + + return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s, + gfp_t gfp, bool new_slab); void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat, enum node_stat_item idx, int nr); -static inline void memcg_free_page_obj_cgroups(struct page *page) +static inline void memcg_free_slab_cgroups(struct slab *slab) { - kfree(page_objcgs(page)); - page->memcg_data = 0; + kfree(slab_objcgs(slab)); + slab->memcg_data = 0; } static inline size_t obj_full_size(struct kmem_cache *s) @@ -465,7 +483,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, size_t size, void **p) { - struct page *page; + struct slab *slab; unsigned long off; size_t i; @@ -474,19 +492,19 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, for (i = 0; i < size; i++) { if (likely(p[i])) { - page = virt_to_head_page(p[i]); + slab = virt_to_slab(p[i]); - if (!page_objcgs(page) && - memcg_alloc_page_obj_cgroups(page, s, flags, + if (!slab_objcgs(slab) && + memcg_alloc_slab_cgroups(slab, s, flags, false)) { obj_cgroup_uncharge(objcg, obj_full_size(s)); continue; } - off = obj_to_index(s, page_slab(page), p[i]); + off = obj_to_index(s, slab, p[i]); obj_cgroup_get(objcg); - page_objcgs(page)[off] = objcg; - mod_objcg_state(objcg, page_pgdat(page), + slab_objcgs(slab)[off] = objcg; + mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s), obj_full_size(s)); } else { obj_cgroup_uncharge(objcg, obj_full_size(s)); @@ -501,7 +519,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, struct kmem_cache *s; struct obj_cgroup **objcgs; struct obj_cgroup *objcg; - struct page *page; + struct slab *slab; unsigned int off; int i; @@ -512,43 +530,52 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, if (unlikely(!p[i])) continue; - page = virt_to_head_page(p[i]); - objcgs = page_objcgs_check(page); + slab = virt_to_slab(p[i]); + /* we could be given a kmalloc_large() object, skip those */ + if (!slab) + continue; + + objcgs = slab_objcgs(slab); if (!objcgs) continue; if (!s_orig) - s = page->slab_cache; + s = slab->slab_cache; else s = s_orig; - off = obj_to_index(s, page_slab(page), p[i]); + off = obj_to_index(s, slab, p[i]); objcg = objcgs[off]; if (!objcg) continue; objcgs[off] = NULL; obj_cgroup_uncharge(objcg, obj_full_size(s)); - mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s), + mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s), -obj_full_size(s)); obj_cgroup_put(objcg); } } #else /* CONFIG_MEMCG_KMEM */ +static inline struct obj_cgroup **slab_objcgs(struct slab *slab) +{ + return NULL; +} + static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr) { return NULL; } -static inline int memcg_alloc_page_obj_cgroups(struct page *page, +static inline int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s, gfp_t gfp, - bool new_page) + bool new_slab) { return 0; } -static inline void memcg_free_page_obj_cgroups(struct page *page) +static inline void memcg_free_slab_cgroups(struct slab *slab) { } @@ -587,7 +614,7 @@ static __always_inline void account_slab(struct slab *slab, int order, struct kmem_cache *s, gfp_t gfp) { if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT)) - memcg_alloc_page_obj_cgroups(slab_page(slab), s, gfp, true); + memcg_alloc_slab_cgroups(slab, s, gfp, true); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), PAGE_SIZE << order); @@ -597,7 +624,7 @@ static __always_inline void unaccount_slab(struct slab *slab, int order, struct kmem_cache *s) { if (memcg_kmem_enabled()) - memcg_free_page_obj_cgroups(slab_page(slab)); + memcg_free_slab_cgroups(slab); mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s), -(PAGE_SIZE << order)); -- cgit v1.2.3 From 6e48a966dfd18987fec9385566a67d36e2b5fc11 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Oct 2021 14:46:46 +0100 Subject: mm/kasan: Convert to struct folio and struct slab KASAN accesses some slab related struct page fields so we need to convert it to struct slab. Some places are a bit simplified thanks to kasan_addr_to_slab() encapsulating the PageSlab flag check through virt_to_slab(). When resolving object address to either a real slab or a large kmalloc, use struct folio as the intermediate type for testing the slab flag to avoid unnecessary implicit compound_head(). [ vbabka@suse.cz: use struct folio, adjust to differences in previous patches ] Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Vlastimil Babka Reviewed-by: Andrey Konovalov Reviewed-by: Roman Gushchin Tested-by: Hyeongogn Yoo <42.hyeyoo@gmail.com> Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: --- include/linux/kasan.h | 9 +++++---- mm/kasan/common.c | 23 +++++++++++++---------- mm/kasan/generic.c | 8 ++++---- mm/kasan/kasan.h | 1 + mm/kasan/quarantine.c | 2 +- mm/kasan/report.c | 13 +++++++++++-- mm/kasan/report_tags.c | 10 +++++----- mm/slab.c | 2 +- mm/slub.c | 2 +- 9 files changed, 42 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d8783b682669..fb78108d694e 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -9,6 +9,7 @@ struct kmem_cache; struct page; +struct slab; struct vm_struct; struct task_struct; @@ -193,11 +194,11 @@ static __always_inline size_t kasan_metadata_size(struct kmem_cache *cache) return 0; } -void __kasan_poison_slab(struct page *page); -static __always_inline void kasan_poison_slab(struct page *page) +void __kasan_poison_slab(struct slab *slab); +static __always_inline void kasan_poison_slab(struct slab *slab) { if (kasan_enabled()) - __kasan_poison_slab(page); + __kasan_poison_slab(slab); } void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object); @@ -322,7 +323,7 @@ static inline void kasan_cache_create(struct kmem_cache *cache, slab_flags_t *flags) {} static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {} static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; } -static inline void kasan_poison_slab(struct page *page) {} +static inline void kasan_poison_slab(struct slab *slab) {} static inline void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) {} static inline void kasan_poison_object_data(struct kmem_cache *cache, diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 6a1cd2d38bff..7c06db78a76c 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -247,8 +247,9 @@ struct kasan_free_meta *kasan_get_free_meta(struct kmem_cache *cache, } #endif -void __kasan_poison_slab(struct page *page) +void __kasan_poison_slab(struct slab *slab) { + struct page *page = slab_page(slab); unsigned long i; for (i = 0; i < compound_nr(page); i++) @@ -401,9 +402,9 @@ void __kasan_kfree_large(void *ptr, unsigned long ip) void __kasan_slab_free_mempool(void *ptr, unsigned long ip) { - struct page *page; + struct folio *folio; - page = virt_to_head_page(ptr); + folio = virt_to_folio(ptr); /* * Even though this function is only called for kmem_cache_alloc and @@ -411,12 +412,14 @@ void __kasan_slab_free_mempool(void *ptr, unsigned long ip) * !PageSlab() when the size provided to kmalloc is larger than * KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc. */ - if (unlikely(!PageSlab(page))) { + if (unlikely(!folio_test_slab(folio))) { if (____kasan_kfree_large(ptr, ip)) return; - kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE, false); + kasan_poison(ptr, folio_size(folio), KASAN_FREE_PAGE, false); } else { - ____kasan_slab_free(page->slab_cache, ptr, ip, false, false); + struct slab *slab = folio_slab(folio); + + ____kasan_slab_free(slab->slab_cache, ptr, ip, false, false); } } @@ -560,7 +563,7 @@ void * __must_check __kasan_kmalloc_large(const void *ptr, size_t size, void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flags) { - struct page *page; + struct slab *slab; if (unlikely(object == ZERO_SIZE_PTR)) return (void *)object; @@ -572,13 +575,13 @@ void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flag */ kasan_unpoison(object, size, false); - page = virt_to_head_page(object); + slab = virt_to_slab(object); /* Piggy-back on kmalloc() instrumentation to poison the redzone. */ - if (unlikely(!PageSlab(page))) + if (unlikely(!slab)) return __kasan_kmalloc_large(object, size, flags); else - return ____kasan_kmalloc(page->slab_cache, object, size, flags); + return ____kasan_kmalloc(slab->slab_cache, object, size, flags); } bool __kasan_check_byte(const void *address, unsigned long ip) diff --git a/mm/kasan/generic.c b/mm/kasan/generic.c index 5d0b79416c4e..a25ad4090615 100644 --- a/mm/kasan/generic.c +++ b/mm/kasan/generic.c @@ -330,16 +330,16 @@ DEFINE_ASAN_SET_SHADOW(f8); static void __kasan_record_aux_stack(void *addr, bool can_alloc) { - struct page *page = kasan_addr_to_page(addr); + struct slab *slab = kasan_addr_to_slab(addr); struct kmem_cache *cache; struct kasan_alloc_meta *alloc_meta; void *object; - if (is_kfence_address(addr) || !(page && PageSlab(page))) + if (is_kfence_address(addr) || !slab) return; - cache = page->slab_cache; - object = nearest_obj(cache, page_slab(page), addr); + cache = slab->slab_cache; + object = nearest_obj(cache, slab, addr); alloc_meta = kasan_get_alloc_meta(cache, object); if (!alloc_meta) return; diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index aebd8df86a1f..c17fa8d26ffe 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -265,6 +265,7 @@ bool kasan_report(unsigned long addr, size_t size, void kasan_report_invalid_free(void *object, unsigned long ip); struct page *kasan_addr_to_page(const void *addr); +struct slab *kasan_addr_to_slab(const void *addr); depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc); void kasan_set_track(struct kasan_track *track, gfp_t flags); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index d8ccff4c1275..587da8995f2d 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -117,7 +117,7 @@ static unsigned long quarantine_batch_size; static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink) { - return virt_to_head_page(qlink)->slab_cache; + return virt_to_slab(qlink)->slab_cache; } static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index e00999dc6499..3ad9624dcc56 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -150,6 +150,14 @@ struct page *kasan_addr_to_page(const void *addr) return NULL; } +struct slab *kasan_addr_to_slab(const void *addr) +{ + if ((addr >= (void *)PAGE_OFFSET) && + (addr < high_memory)) + return virt_to_slab(addr); + return NULL; +} + static void describe_object_addr(struct kmem_cache *cache, void *object, const void *addr) { @@ -248,8 +256,9 @@ static void print_address_description(void *addr, u8 tag) pr_err("\n"); if (page && PageSlab(page)) { - struct kmem_cache *cache = page->slab_cache; - void *object = nearest_obj(cache, page_slab(page), addr); + struct slab *slab = page_slab(page); + struct kmem_cache *cache = slab->slab_cache; + void *object = nearest_obj(cache, slab, addr); describe_object(cache, object, addr, tag); } diff --git a/mm/kasan/report_tags.c b/mm/kasan/report_tags.c index 06c21dd77493..1b41de88c53e 100644 --- a/mm/kasan/report_tags.c +++ b/mm/kasan/report_tags.c @@ -12,7 +12,7 @@ const char *kasan_get_bug_type(struct kasan_access_info *info) #ifdef CONFIG_KASAN_TAGS_IDENTIFY struct kasan_alloc_meta *alloc_meta; struct kmem_cache *cache; - struct page *page; + struct slab *slab; const void *addr; void *object; u8 tag; @@ -20,10 +20,10 @@ const char *kasan_get_bug_type(struct kasan_access_info *info) tag = get_tag(info->access_addr); addr = kasan_reset_tag(info->access_addr); - page = kasan_addr_to_page(addr); - if (page && PageSlab(page)) { - cache = page->slab_cache; - object = nearest_obj(cache, page_slab(page), (void *)addr); + slab = kasan_addr_to_slab(addr); + if (slab) { + cache = slab->slab_cache; + object = nearest_obj(cache, slab, (void *)addr); alloc_meta = kasan_get_alloc_meta(cache, object); if (alloc_meta) { diff --git a/mm/slab.c b/mm/slab.c index c13258116791..ddf5737c63d9 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2604,7 +2604,7 @@ static struct slab *cache_grow_begin(struct kmem_cache *cachep, * page_address() in the latter returns a non-tagged pointer, * as it should be for slab pages. */ - kasan_poison_slab(slab_page(slab)); + kasan_poison_slab(slab); /* Get slab management. */ freelist = alloc_slabmgmt(cachep, slab, offset, diff --git a/mm/slub.c b/mm/slub.c index ddf21c7a381a..d08ba1025aae 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1961,7 +1961,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) slab->slab_cache = s; - kasan_poison_slab(slab_page(slab)); + kasan_poison_slab(slab); start = slab_address(slab); -- cgit v1.2.3 From c5e97ed154589524a1df4ae2be55c4cfdb0d0573 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Oct 2021 14:46:48 +0100 Subject: bootmem: Use page->index instead of page->freelist page->freelist is for the use of slab. Using page->index is the same set of bits as page->freelist, and by using an integer instead of a pointer, we can avoid casts. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Vlastimil Babka Acked-by: Johannes Weiner Cc: Dave Hansen Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Cc: "H. Peter Anvin" --- arch/x86/mm/init_64.c | 2 +- include/linux/bootmem_info.h | 2 +- mm/bootmem_info.c | 7 +++---- mm/sparse.c | 2 +- 4 files changed, 6 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 36098226a957..96d34ebb20a9 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -981,7 +981,7 @@ static void __meminit free_pagetable(struct page *page, int order) if (PageReserved(page)) { __ClearPageReserved(page); - magic = (unsigned long)page->freelist; + magic = page->index; if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) { while (nr_pages--) put_page_bootmem(page++); diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h index 2bc8b1f69c93..cc35d010fa94 100644 --- a/include/linux/bootmem_info.h +++ b/include/linux/bootmem_info.h @@ -30,7 +30,7 @@ void put_page_bootmem(struct page *page); */ static inline void free_bootmem_page(struct page *page) { - unsigned long magic = (unsigned long)page->freelist; + unsigned long magic = page->index; /* * The reserve_bootmem_region sets the reserved flag on bootmem diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c index f03f42f426f6..f18a631e7479 100644 --- a/mm/bootmem_info.c +++ b/mm/bootmem_info.c @@ -15,7 +15,7 @@ void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) { - page->freelist = (void *)type; + page->index = type; SetPagePrivate(page); set_page_private(page, info); page_ref_inc(page); @@ -23,14 +23,13 @@ void get_page_bootmem(unsigned long info, struct page *page, unsigned long type) void put_page_bootmem(struct page *page) { - unsigned long type; + unsigned long type = page->index; - type = (unsigned long) page->freelist; BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE || type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE); if (page_ref_dec_return(page) == 1) { - page->freelist = NULL; + page->index = 0; ClearPagePrivate(page); set_page_private(page, 0); INIT_LIST_HEAD(&page->lru); diff --git a/mm/sparse.c b/mm/sparse.c index e5c84b0cf0c9..d21c6e5910d0 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -722,7 +722,7 @@ static void free_map_bootmem(struct page *memmap) >> PAGE_SHIFT; for (i = 0; i < nr_pages; i++, page++) { - magic = (unsigned long) page->freelist; + magic = page->index; BUG_ON(magic == NODE_INFO); -- cgit v1.2.3 From 007747a984ea5e895b7d8b056b24ebf431e1e71d Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Wed, 5 Jan 2022 11:33:26 +0100 Subject: net: fix SOF_TIMESTAMPING_BIND_PHC to work with multiple sockets When multiple sockets using the SOF_TIMESTAMPING_BIND_PHC flag received a packet with a hardware timestamp (e.g. multiple PTP instances in different PTP domains using the UDPv4/v6 multicast or L2 transport), the timestamps received on some sockets were corrupted due to repeated conversion of the same timestamp (by the same or different vclocks). Fix ptp_convert_timestamp() to not modify the shared skb timestamp and return the converted timestamp as a ktime_t instead. If the conversion fails, return 0 to not confuse the application with timestamps corresponding to an unexpected PHC. Fixes: d7c088265588 ("net: socket: support hardware timestamp conversion to PHC bound") Signed-off-by: Miroslav Lichvar Cc: Yangbo Lu Cc: Richard Cochran Acked-by: Richard Cochran Signed-off-by: David S. Miller --- drivers/ptp/ptp_vclock.c | 10 +++++----- include/linux/ptp_clock_kernel.h | 12 +++++++----- net/socket.c | 9 ++++++--- 3 files changed, 18 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index baee0379482b..ab1d233173e1 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -185,8 +185,8 @@ out: } EXPORT_SYMBOL(ptp_get_vclocks_index); -void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index) +ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) { char name[PTP_CLOCK_NAME_LEN] = ""; struct ptp_vclock *vclock; @@ -198,12 +198,12 @@ void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", vclock_index); dev = class_find_device_by_name(ptp_class, name); if (!dev) - return; + return 0; ptp = dev_get_drvdata(dev); if (!ptp->is_virtual_clock) { put_device(dev); - return; + return 0; } vclock = info_to_vclock(ptp->info); @@ -215,7 +215,7 @@ void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, spin_unlock_irqrestore(&vclock->lock, flags); put_device(dev); - hwtstamps->hwtstamp = ns_to_ktime(ns); + return ns_to_ktime(ns); } EXPORT_SYMBOL(ptp_convert_timestamp); #endif diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 2e5565067355..554454cb8693 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -351,15 +351,17 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); * * @hwtstamps: skb_shared_hwtstamps structure pointer * @vclock_index: phc index of ptp vclock. + * + * Returns converted timestamp, or 0 on error. */ -void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index); +ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index); #else static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } -static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index) -{ } +static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ return 0; } #endif diff --git a/net/socket.c b/net/socket.c index 5e644c858428..50cf75730fd7 100644 --- a/net/socket.c +++ b/net/socket.c @@ -830,6 +830,7 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + ktime_t hwtstamp; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ @@ -878,10 +879,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC) - ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc); + hwtstamp = ptp_convert_timestamp(shhwtstamps, + sk->sk_bind_phc); + else + hwtstamp = shhwtstamps->hwtstamp; - if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp, - tss.ts + 2)) { + if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { empty = 0; if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && -- cgit v1.2.3 From eac1b93c14d645ef147b049ace0d5230df755548 Mon Sep 17 00:00:00 2001 From: Coco Li Date: Wed, 5 Jan 2022 02:48:38 -0800 Subject: gro: add ability to control gro max packet size Eric Dumazet suggested to allow users to modify max GRO packet size. We have seen GRO being disabled by users of appliances (such as wifi access points) because of claimed bufferbloat issues, or some work arounds in sch_cake, to split GRO/GSO packets. Instead of disabling GRO completely, one can chose to limit the maximum packet size of GRO packets, depending on their latency constraints. This patch adds a per device gro_max_size attribute that can be changed with ip link command. ip link set dev eth0 gro_max_size 16000 Suggested-by: Eric Dumazet Signed-off-by: Coco Li Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 11 +++++++++++ include/uapi/linux/if_link.h | 1 + net/core/dev.c | 1 + net/core/gro.c | 6 +++++- net/core/rtnetlink.c | 22 ++++++++++++++++++++++ tools/include/uapi/linux/if_link.h | 1 + 6 files changed, 41 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6f99c8f51b60..3213c7227b59 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1942,6 +1942,8 @@ enum netdev_ml_priv_type { * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. + * @gro_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO) * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. @@ -2131,6 +2133,8 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; +#define GRO_MAX_SIZE 65536 + unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -4806,6 +4810,13 @@ static inline void netif_set_gso_max_segs(struct net_device *dev, WRITE_ONCE(dev->gso_max_segs, segs); } +static inline void netif_set_gro_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_max_size, size); +} + static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, int pulled_hlen, u16 mac_offset, int mac_len) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 4ac53b30b6dc..6218f93f5c1a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -347,6 +347,7 @@ enum { */ IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, __IFLA_MAX }; diff --git a/net/core/dev.c b/net/core/dev.c index 6c8b226b5f2f..83a4089990a0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10180,6 +10180,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->gro_max_size = GRO_MAX_SIZE; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP diff --git a/net/core/gro.c b/net/core/gro.c index 8ec8b44596da..a11b286d1495 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -132,10 +132,14 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) unsigned int headlen = skb_headlen(skb); unsigned int len = skb_gro_len(skb); unsigned int delta_truesize; + unsigned int gro_max_size; unsigned int new_truesize; struct sk_buff *lp; - if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush)) + /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ + gro_max_size = READ_ONCE(p->dev->gro_max_size); + + if (unlikely(p->len + len >= gro_max_size || NAPI_GRO_CB(skb)->flush)) return -E2BIG; lp = NAPI_GRO_CB(p)->last; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d6eba554b137..e476403231f0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1026,6 +1026,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_NUM_RX_QUEUES */ + nla_total_size(4) /* IFLA_GSO_MAX_SEGS */ + nla_total_size(4) /* IFLA_GSO_MAX_SIZE */ + + nla_total_size(4) /* IFLA_GRO_MAX_SIZE */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + nla_total_size(4) /* IFLA_CARRIER_CHANGES */ @@ -1728,6 +1729,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) || nla_put_u32(skb, IFLA_GSO_MAX_SEGS, dev->gso_max_segs) || nla_put_u32(skb, IFLA_GSO_MAX_SIZE, dev->gso_max_size) || + nla_put_u32(skb, IFLA_GRO_MAX_SIZE, dev->gro_max_size) || #ifdef CONFIG_RPS nla_put_u32(skb, IFLA_NUM_RX_QUEUES, dev->num_rx_queues) || #endif @@ -1880,6 +1882,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED }, [IFLA_NEW_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), [IFLA_PARENT_DEV_NAME] = { .type = NLA_NUL_STRING }, + [IFLA_GRO_MAX_SIZE] = { .type = NLA_U32 }, }; static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { @@ -2299,6 +2302,14 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[], } } + if (tb[IFLA_GRO_MAX_SIZE]) { + u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]); + + if (gro_max_size > GRO_MAX_SIZE) { + NL_SET_ERR_MSG(extack, "too big gro_max_size"); + return -EINVAL; + } + } return 0; } @@ -2772,6 +2783,15 @@ static int do_setlink(const struct sk_buff *skb, } } + if (tb[IFLA_GRO_MAX_SIZE]) { + u32 gro_max_size = nla_get_u32(tb[IFLA_GRO_MAX_SIZE]); + + if (dev->gro_max_size ^ gro_max_size) { + netif_set_gro_max_size(dev, gro_max_size); + status |= DO_SETLINK_MODIFIED; + } + } + if (tb[IFLA_OPERSTATE]) set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); @@ -3222,6 +3242,8 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE])); if (tb[IFLA_GSO_MAX_SEGS]) netif_set_gso_max_segs(dev, nla_get_u32(tb[IFLA_GSO_MAX_SEGS])); + if (tb[IFLA_GRO_MAX_SIZE]) + netif_set_gro_max_size(dev, nla_get_u32(tb[IFLA_GRO_MAX_SIZE])); return dev; } diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 4ac53b30b6dc..6218f93f5c1a 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -347,6 +347,7 @@ enum { */ IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, __IFLA_MAX }; -- cgit v1.2.3 From 3809fe479861194e310c23ed48b010c7c0f72d22 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Thu, 16 Dec 2021 10:21:57 +0100 Subject: HID: address kernel-doc warnings The command ./scripts/kernel-doc -none include/linux/hid.h reports: include/linux/hid.h:818: warning: cannot understand function prototype: 'struct hid_ll_driver ' include/linux/hid.h:1135: warning: expecting prototype for hid_may_wakeup(). Prototype was for hid_hw_may_wakeup() instead Address those kernel-doc warnings. Signed-off-by: Lukas Bulwahn Signed-off-by: Jiri Kosina --- include/linux/hid.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index f453be385bd4..aaf89a8a836c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -788,7 +788,7 @@ struct hid_driver { container_of(pdrv, struct hid_driver, driver) /** - * hid_ll_driver - low level driver callbacks + * struct hid_ll_driver - low level driver callbacks * @start: called on probe to start the device * @stop: called on remove * @open: called by input layer on open @@ -1158,7 +1158,7 @@ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, } /** - * hid_may_wakeup - return if the hid device may act as a wakeup source during system-suspend + * hid_hw_may_wakeup - return if the hid device may act as a wakeup source during system-suspend * * @hdev: hid device */ -- cgit v1.2.3 From 36dacddbf0bdba86cd00f066b4d724157eeb63f1 Mon Sep 17 00:00:00 2001 From: Dirk Müller Date: Wed, 5 Jan 2022 17:38:47 +0100 Subject: lib/raid6: Use strict priority ranking for pq gen() benchmarking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit On x86_64, currently 3 variants of AVX512, 3 variants of AVX2 and 3 variants of SSE2 are benchmarked on initialization, taking between 144-153 jiffies. Testing across a hardware pool of various generations of intel cpus I could not find a single case where SSE2 won over AVX2 or AVX512. There are cases where AVX2 wins over AVX512 however. Change "prefer" into an integer priority field (similar to how recov selection works) to have more than one ranking level available, which is backwards compatible with existing behavior. Give AVX2/512 variants higher priority over SSE2 in order to skip SSE testing when AVX is available. in a AVX2/x86_64/HZ=250 case this saves in the order of 200ms of initialization time. Signed-off-by: Dirk Müller Acked-by: Paul Menzel Signed-off-by: Song Liu --- include/linux/raid/pq.h | 2 +- lib/raid6/algos.c | 2 +- lib/raid6/avx2.c | 8 ++++---- lib/raid6/avx512.c | 6 +++--- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h index 154e954b711d..d6e5a1feb947 100644 --- a/include/linux/raid/pq.h +++ b/include/linux/raid/pq.h @@ -81,7 +81,7 @@ struct raid6_calls { void (*xor_syndrome)(int, int, int, size_t, void **); int (*valid)(void); /* Returns 1 if this routine set is usable */ const char *name; /* Name of this routine set */ - int prefer; /* Has special performance attribute */ + int priority; /* Relative priority ranking if non-zero */ }; /* Selected algorithm */ diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 9b7e8a837b27..39b74221f4a7 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -151,7 +151,7 @@ static inline const struct raid6_calls *raid6_choose_gen( const struct raid6_calls *best; for (bestgenperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) { - if (!best || (*algo)->prefer >= best->prefer) { + if (!best || (*algo)->priority >= best->priority) { if ((*algo)->valid && !(*algo)->valid()) continue; diff --git a/lib/raid6/avx2.c b/lib/raid6/avx2.c index f299476e1d76..059024234dce 100644 --- a/lib/raid6/avx2.c +++ b/lib/raid6/avx2.c @@ -132,7 +132,7 @@ const struct raid6_calls raid6_avx2x1 = { raid6_avx21_xor_syndrome, raid6_have_avx2, "avx2x1", - 1 /* Has cache hints */ + .priority = 2 /* Prefer AVX2 over priority 1 (SSE2 and others) */ }; /* @@ -262,7 +262,7 @@ const struct raid6_calls raid6_avx2x2 = { raid6_avx22_xor_syndrome, raid6_have_avx2, "avx2x2", - 1 /* Has cache hints */ + .priority = 2 /* Prefer AVX2 over priority 1 (SSE2 and others) */ }; #ifdef CONFIG_X86_64 @@ -465,6 +465,6 @@ const struct raid6_calls raid6_avx2x4 = { raid6_avx24_xor_syndrome, raid6_have_avx2, "avx2x4", - 1 /* Has cache hints */ + .priority = 2 /* Prefer AVX2 over priority 1 (SSE2 and others) */ }; -#endif +#endif /* CONFIG_X86_64 */ diff --git a/lib/raid6/avx512.c b/lib/raid6/avx512.c index bb684d144ee2..9c3e822e1adf 100644 --- a/lib/raid6/avx512.c +++ b/lib/raid6/avx512.c @@ -162,7 +162,7 @@ const struct raid6_calls raid6_avx512x1 = { raid6_avx5121_xor_syndrome, raid6_have_avx512, "avx512x1", - 1 /* Has cache hints */ + .priority = 2 /* Prefer AVX512 over priority 1 (SSE2 and others) */ }; /* @@ -319,7 +319,7 @@ const struct raid6_calls raid6_avx512x2 = { raid6_avx5122_xor_syndrome, raid6_have_avx512, "avx512x2", - 1 /* Has cache hints */ + .priority = 2 /* Prefer AVX512 over priority 1 (SSE2 and others) */ }; #ifdef CONFIG_X86_64 @@ -557,7 +557,7 @@ const struct raid6_calls raid6_avx512x4 = { raid6_avx5124_xor_syndrome, raid6_have_avx512, "avx512x4", - 1 /* Has cache hints */ + .priority = 2 /* Prefer AVX512 over priority 1 (SSE2 and others) */ }; #endif -- cgit v1.2.3 From 07f910f9b7295b6a28b337fedb56e612684c5659 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Mon, 4 Oct 2021 14:46:50 +0100 Subject: mm: Remove slab from struct page All members of struct slab can now be removed from struct page. This shrinks the definition of struct page by 30 LOC, making it easier to understand. Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Vlastimil Babka --- include/linux/mm_types.h | 28 ---------------------------- include/linux/page-flags.h | 37 ------------------------------------- mm/slab.h | 6 ------ 3 files changed, 71 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 1ae3537c7920..646f3ed4f6df 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -118,31 +118,6 @@ struct page { atomic_long_t pp_frag_count; }; }; - struct { /* slab, slob and slub */ - union { - struct list_head slab_list; - struct { /* Partial pages */ - struct page *next; -#ifdef CONFIG_64BIT - int pages; /* Nr of pages left */ -#else - short int pages; -#endif - }; - }; - struct kmem_cache *slab_cache; /* not slob */ - /* Double-word boundary */ - void *freelist; /* first free object */ - union { - void *s_mem; /* slab: first object */ - unsigned long counters; /* SLUB */ - struct { /* SLUB */ - unsigned inuse:16; - unsigned objects:15; - unsigned frozen:1; - }; - }; - }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ @@ -206,9 +181,6 @@ struct page { * which are currently stored here. */ unsigned int page_type; - - unsigned int active; /* SLAB */ - int units; /* SLOB */ }; /* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..1b08e33265fa 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -909,43 +909,6 @@ extern bool is_free_buddy_page(struct page *page); __PAGEFLAG(Isolated, isolated, PF_ANY); -/* - * If network-based swap is enabled, sl*b must keep track of whether pages - * were allocated from pfmemalloc reserves. - */ -static inline int PageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - return PageActive(page); -} - -/* - * A version of PageSlabPfmemalloc() for opportunistic checks where the page - * might have been freed under us and not be a PageSlab anymore. - */ -static inline int __PageSlabPfmemalloc(struct page *page) -{ - return PageActive(page); -} - -static inline void SetPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - SetPageActive(page); -} - -static inline void __ClearPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - __ClearPageActive(page); -} - -static inline void ClearPageSlabPfmemalloc(struct page *page) -{ - VM_BUG_ON_PAGE(!PageSlab(page), page); - ClearPageActive(page); -} - #ifdef CONFIG_MMU #define __PG_MLOCKED (1UL << PG_mlocked) #else diff --git a/mm/slab.h b/mm/slab.h index 95b9a74a2d51..207658b200ef 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -67,14 +67,8 @@ struct slab { static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl)) SLAB_MATCH(flags, __page_flags); SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */ -SLAB_MATCH(slab_list, slab_list); #ifndef CONFIG_SLOB SLAB_MATCH(rcu_head, rcu_head); -SLAB_MATCH(slab_cache, slab_cache); -#endif -#ifdef CONFIG_SLAB -SLAB_MATCH(s_mem, s_mem); -SLAB_MATCH(active, active); #endif SLAB_MATCH(_refcount, __page_refcount); #ifdef CONFIG_MEMCG -- cgit v1.2.3 From b5e7b59c3480f355910f9d2c6ece5857922a5e54 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 28 Sep 2021 09:47:57 +1000 Subject: NFS: change nfs_access_get_cached to only report the mask Currently the nfs_access_get_cached family of functions report a 'struct nfs_access_entry' as the result, with both .mask and .cred set. However the .cred is never used. This is probably good and there is no guarantee that it won't be freed before use. Change to only report the 'mask' - as this is all that is used or needed. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 20 +++++++++----------- fs/nfs/nfs4proc.c | 18 +++++++++--------- include/linux/nfs_fs.h | 4 ++-- 3 files changed, 20 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 731d31015b6a..8487a6d69116 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2673,7 +2673,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co return NULL; } -static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, bool may_block) +static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_access_entry *cache; @@ -2703,8 +2703,7 @@ static int nfs_access_get_cached_locked(struct inode *inode, const struct cred * spin_lock(&inode->i_lock); retry = false; } - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); err = 0; out: @@ -2716,7 +2715,7 @@ out_zap: return -ENOENT; } -static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res) +static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask) { /* Only check the most recently returned cache entry, * but do it without locking. @@ -2738,22 +2737,21 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre goto out; if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS)) goto out; - res->cred = cache->cred; - res->mask = cache->mask; + *mask = cache->mask; err = 0; out: rcu_read_unlock(); return err; } -int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct -nfs_access_entry *res, bool may_block) +int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block) { int status; - status = nfs_access_get_cached_rcu(inode, cred, res); + status = nfs_access_get_cached_rcu(inode, cred, mask); if (status != 0) - status = nfs_access_get_cached_locked(inode, cred, res, + status = nfs_access_get_cached_locked(inode, cred, mask, may_block); return status; @@ -2874,7 +2872,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) trace_nfs_access_enter(inode); - status = nfs_access_get_cached(inode, cred, &cache, may_block); + status = nfs_access_get_cached(inode, cred, &cache.mask, may_block); if (status == 0) goto out_cached; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ee3bc79f6ca3..322ff45ad15c 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -7611,7 +7611,7 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, const char *key, const void *buf, size_t buflen, int flags) { - struct nfs_access_entry cache; + u32 mask; int ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) @@ -7626,8 +7626,8 @@ static int nfs4_xattr_set_nfs4_user(const struct xattr_handler *handler, * do a cached access check for the XA* flags to possibly avoid * doing an RPC and getting EACCES back. */ - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAWRITE)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAWRITE)) return -EACCES; } @@ -7648,14 +7648,14 @@ static int nfs4_xattr_get_nfs4_user(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *key, void *buf, size_t buflen) { - struct nfs_access_entry cache; + u32 mask; ssize_t ret; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return -EOPNOTSUPP; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XAREAD)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XAREAD)) return -EACCES; } @@ -7680,13 +7680,13 @@ nfs4_listxattr_nfs4_user(struct inode *inode, char *list, size_t list_len) ssize_t ret, size; char *buf; size_t buflen; - struct nfs_access_entry cache; + u32 mask; if (!nfs_server_capable(inode, NFS_CAP_XATTR)) return 0; - if (!nfs_access_get_cached(inode, current_cred(), &cache, true)) { - if (!(cache.mask & NFS_ACCESS_XALIST)) + if (!nfs_access_get_cached(inode, current_cred(), &mask, true)) { + if (!(mask & NFS_ACCESS_XALIST)) return 0; } diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 05f249f20f55..f33559acbcc2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -533,8 +533,8 @@ extern int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr); extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags); extern void nfs_access_zap_cache(struct inode *inode); -extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, struct nfs_access_entry *res, - bool may_block); +extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred, + u32 *mask, bool may_block); /* * linux/fs/nfs/symlink.c -- cgit v1.2.3 From 73fbb3fa647bdb5b60469af8101c741ece03a825 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 28 Sep 2021 09:47:57 +1000 Subject: NFS: pass cred explicitly for access tests Storing the 'struct cred *' in nfs_access_entry is problematic. An active 'cred' can keep a 'struct key *' active, and a quota is imposed on the number of such keys that a user can maintain. Cached 'nfs_access_entry' structs have indefinite lifetime, and having these keep 'struct key's alive imposes on that quota. So a future patch will remove the ->cred ref from nfs_access_entry. To prepare, change various functions to not assume there is a 'cred' in the nfs_access_entry, but to pass the cred around explicitly. Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 17 ++++++++++------- fs/nfs/nfs3proc.c | 5 +++-- fs/nfs/nfs4proc.c | 12 +++++++----- include/linux/nfs_fs.h | 2 +- include/linux/nfs_xdr.h | 2 +- 5 files changed, 22 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 8487a6d69116..a34351ce79a2 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2758,7 +2758,9 @@ int nfs_access_get_cached(struct inode *inode, const struct cred *cred, } EXPORT_SYMBOL_GPL(nfs_access_get_cached); -static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) +static void nfs_access_add_rbtree(struct inode *inode, + struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_inode *nfsi = NFS_I(inode); struct rb_root *root_node = &nfsi->access_cache; @@ -2771,7 +2773,7 @@ static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry * while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); - cmp = cred_fscmp(set->cred, entry->cred); + cmp = cred_fscmp(cred, entry->cred); if (cmp < 0) p = &parent->rb_left; @@ -2793,13 +2795,14 @@ found: nfs_access_free_entry(entry); } -void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) +void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, + const struct cred *cred) { struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->cred = get_cred(set->cred); + cache->cred = get_cred(cred); cache->mask = set->mask; /* The above field assignments must be visible @@ -2807,7 +2810,7 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) * use rcu_assign_pointer, so just force the memory barrier. */ smp_wmb(); - nfs_access_add_rbtree(inode, cache); + nfs_access_add_rbtree(inode, cache, cred); /* Update accounting */ smp_mb__before_atomic(); @@ -2893,7 +2896,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) else cache.mask |= NFS_ACCESS_EXECUTE; cache.cred = cred; - status = NFS_PROTO(inode)->access(inode, &cache); + status = NFS_PROTO(inode)->access(inode, &cache, cred); if (status != 0) { if (status == -ESTALE) { if (!S_ISDIR(inode->i_mode)) @@ -2903,7 +2906,7 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) } goto out; } - nfs_access_add_cache(inode, &cache); + nfs_access_add_cache(inode, &cache, cred); out_cached: cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode); if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 7100514d306b..1597eef40d54 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -220,7 +220,8 @@ static int nfs3_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, task_flags); } -static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs3_accessargs arg = { .fh = NFS_FH(inode), @@ -231,7 +232,7 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry) .rpc_proc = &nfs3_procedures[NFS3PROC_ACCESS], .rpc_argp = &arg, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = -ENOMEM; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 322ff45ad15c..f02aa9877e6f 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2655,7 +2655,7 @@ static int nfs4_opendata_access(const struct cred *cred, cache.cred = cred; nfs_access_set_mask(&cache, opendata->o_res.access_result); - nfs_access_add_cache(state->inode, &cache); + nfs_access_add_cache(state->inode, &cache, cred); flags = NFS4_ACCESS_READ | NFS4_ACCESS_EXECUTE | NFS4_ACCESS_LOOKUP; if ((mask & ~cache.mask & flags) == 0) @@ -4441,7 +4441,8 @@ static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle, return err; } -static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs_server *server = NFS_SERVER(inode); struct nfs4_accessargs args = { @@ -4455,7 +4456,7 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ACCESS], .rpc_argp = &args, .rpc_resp = &res, - .rpc_cred = entry->cred, + .rpc_cred = cred, }; int status = 0; @@ -4475,14 +4476,15 @@ static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry return status; } -static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) +static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry, + const struct cred *cred) { struct nfs4_exception exception = { .interruptible = true, }; int err; do { - err = _nfs4_proc_access(inode, entry); + err = _nfs4_proc_access(inode, entry, cred); trace_nfs4_access(inode, err); err = nfs4_handle_exception(NFS_SERVER(inode), err, &exception); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index f33559acbcc2..c33b1b792bc9 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -396,7 +396,7 @@ extern int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fa extern int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fattr *fattr); extern int nfs_getattr(struct user_namespace *, const struct path *, struct kstat *, u32, unsigned int); -extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *); +extern void nfs_access_add_cache(struct inode *, struct nfs_access_entry *, const struct cred *); extern void nfs_access_set_mask(struct nfs_access_entry *, u32); extern int nfs_permission(struct user_namespace *, struct inode *, int); extern int nfs_open(struct inode *, struct file *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 967a0098f0a9..9102bdaa3faa 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1737,7 +1737,7 @@ struct nfs_rpc_ops { struct nfs_fh *, struct nfs_fattr *); int (*lookupp) (struct inode *, struct nfs_fh *, struct nfs_fattr *); - int (*access) (struct inode *, struct nfs_access_entry *); + int (*access) (struct inode *, struct nfs_access_entry *, const struct cred *); int (*readlink)(struct inode *, struct page *, unsigned int, unsigned int); int (*create) (struct inode *, struct dentry *, -- cgit v1.2.3 From 6238aec83f3fb12132f964937e5bbcf248fea8f9 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 28 Sep 2021 09:47:57 +1000 Subject: NFS: don't store 'struct cred *' in struct nfs_access_entry Storing the 'struct cred *' in nfs_access_entry is problematic. An active 'cred' can keep a 'struct key *' active, and a quota is imposed on the number of such keys that a user can maintain. Cached 'nfs_access_entry' structs have indefinite lifetime, and having these keep 'struct key's alive imposes on that quota. So remove the 'struct cred *' and replace it with the fields we need: kuid_t, kgid_t, and struct group_info * This makes the 'struct nfs_access_entry' 64 bits larger. New function "access_cmp" is introduced which is identical to cred_fscmp() except that the second arg is an 'nfs_access_entry', rather than a 'cred' Fixes: b68572e07c58 ("NFS: change access cache to use 'struct cred'.") Signed-off-by: NeilBrown Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 50 ++++++++++++++++++++++++++++++++++++++++++++------ fs/nfs/nfs4proc.c | 1 - include/linux/nfs_fs.h | 4 +++- 3 files changed, 47 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a34351ce79a2..7dee3fd10382 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2528,7 +2528,7 @@ MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache lengt static void nfs_access_free_entry(struct nfs_access_entry *entry) { - put_cred(entry->cred); + put_group_info(entry->group_info); kfree_rcu(entry, rcu_head); smp_mb__before_atomic(); atomic_long_dec(&nfs_access_nr_entries); @@ -2654,6 +2654,43 @@ void nfs_access_zap_cache(struct inode *inode) } EXPORT_SYMBOL_GPL(nfs_access_zap_cache); +static int access_cmp(const struct cred *a, const struct nfs_access_entry *b) +{ + struct group_info *ga, *gb; + int g; + + if (uid_lt(a->fsuid, b->fsuid)) + return -1; + if (uid_gt(a->fsuid, b->fsuid)) + return 1; + + if (gid_lt(a->fsgid, b->fsgid)) + return -1; + if (gid_gt(a->fsgid, b->fsgid)) + return 1; + + ga = a->group_info; + gb = b->group_info; + if (ga == gb) + return 0; + if (ga == NULL) + return -1; + if (gb == NULL) + return 1; + if (ga->ngroups < gb->ngroups) + return -1; + if (ga->ngroups > gb->ngroups) + return 1; + + for (g = 0; g < ga->ngroups; g++) { + if (gid_lt(ga->gid[g], gb->gid[g])) + return -1; + if (gid_gt(ga->gid[g], gb->gid[g])) + return 1; + } + return 0; +} + static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred) { struct rb_node *n = NFS_I(inode)->access_cache.rb_node; @@ -2661,7 +2698,7 @@ static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, co while (n != NULL) { struct nfs_access_entry *entry = rb_entry(n, struct nfs_access_entry, rb_node); - int cmp = cred_fscmp(cred, entry->cred); + int cmp = access_cmp(cred, entry); if (cmp < 0) n = n->rb_left; @@ -2731,7 +2768,7 @@ static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cre lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru)); cache = list_entry(lh, struct nfs_access_entry, lru); if (lh == &nfsi->access_cache_entry_lru || - cred_fscmp(cred, cache->cred) != 0) + access_cmp(cred, cache) != 0) cache = NULL; if (cache == NULL) goto out; @@ -2773,7 +2810,7 @@ static void nfs_access_add_rbtree(struct inode *inode, while (*p != NULL) { parent = *p; entry = rb_entry(parent, struct nfs_access_entry, rb_node); - cmp = cred_fscmp(cred, entry->cred); + cmp = access_cmp(cred, entry); if (cmp < 0) p = &parent->rb_left; @@ -2802,7 +2839,9 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set, if (cache == NULL) return; RB_CLEAR_NODE(&cache->rb_node); - cache->cred = get_cred(cred); + cache->fsuid = cred->fsuid; + cache->fsgid = cred->fsgid; + cache->group_info = get_group_info(cred->group_info); cache->mask = set->mask; /* The above field assignments must be visible @@ -2895,7 +2934,6 @@ static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask) cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP; else cache.mask |= NFS_ACCESS_EXECUTE; - cache.cred = cred; status = NFS_PROTO(inode)->access(inode, &cache, cred); if (status != 0) { if (status == -ESTALE) { diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index f02aa9877e6f..5d9ff01ddf46 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2653,7 +2653,6 @@ static int nfs4_opendata_access(const struct cred *cred, } else if ((fmode & FMODE_READ) && !opendata->file_created) mask = NFS4_ACCESS_READ; - cache.cred = cred; nfs_access_set_mask(&cache, opendata->o_res.access_result); nfs_access_add_cache(state->inode, &cache, cred); diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index c33b1b792bc9..450e393d4bf2 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -61,7 +61,9 @@ struct nfs_access_entry { struct rb_node rb_node; struct list_head lru; - const struct cred * cred; + kuid_t fsuid; + kgid_t fsgid; + struct group_info *group_info; __u32 mask; struct rcu_head rcu_head; }; -- cgit v1.2.3 From 1ab5be4ac5b1c9ce39ce1037c45b68d2ce6eede0 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Fri, 17 Dec 2021 15:36:54 -0500 Subject: NFSv4: Add some support for case insensitive filesystems Add capabilities to allow the NFS client to recognise when it is dealing with case insensitive and case preserving filesystems. Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 8 +++++++- fs/nfs/nfs4xdr.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/linux/nfs_fs_sb.h | 2 ++ include/linux/nfs_xdr.h | 2 ++ 4 files changed, 51 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 5d9ff01ddf46..a6d7472058ad 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3840,7 +3840,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f FATTR4_WORD0_FH_EXPIRE_TYPE | FATTR4_WORD0_LINK_SUPPORT | FATTR4_WORD0_SYMLINK_SUPPORT | - FATTR4_WORD0_ACLSUPPORT; + FATTR4_WORD0_ACLSUPPORT | + FATTR4_WORD0_CASE_INSENSITIVE | + FATTR4_WORD0_CASE_PRESERVING; if (minorversion) bitmask[2] = FATTR4_WORD2_SUPPATTR_EXCLCREAT; @@ -3869,6 +3871,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f server->caps |= NFS_CAP_HARDLINKS; if (res.has_symlinks != 0) server->caps |= NFS_CAP_SYMLINKS; + if (res.case_insensitive) + server->caps |= NFS_CAP_CASE_INSENSITIVE; + if (res.case_preserving) + server->caps |= NFS_CAP_CASE_PRESERVING; #ifdef CONFIG_NFS_V4_SECURITY_LABEL if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) server->caps |= NFS_CAP_SECURITY_LABEL; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 801119b7a596..a9487c840052 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -3533,6 +3533,42 @@ static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint return 0; } +static int decode_attr_case_insensitive(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_INSENSITIVE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_INSENSITIVE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_INSENSITIVE; + } + dprintk("%s: case_insensitive=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + +static int decode_attr_case_preserving(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) +{ + __be32 *p; + + *res = 0; + if (unlikely(bitmap[0] & (FATTR4_WORD0_CASE_PRESERVING - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_CASE_PRESERVING)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + return -EIO; + *res = be32_to_cpup(p); + bitmap[0] &= ~FATTR4_WORD0_CASE_PRESERVING; + } + dprintk("%s: case_preserving=%s\n", __func__, *res == 0 ? "false" : "true"); + return 0; +} + static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) { __be32 *p; @@ -4413,6 +4449,10 @@ static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_re goto xdr_error; if ((status = decode_attr_aclsupport(xdr, bitmap, &res->acl_bitmask)) != 0) goto xdr_error; + if ((status = decode_attr_case_insensitive(xdr, bitmap, &res->case_insensitive)) != 0) + goto xdr_error; + if ((status = decode_attr_case_preserving(xdr, bitmap, &res->case_preserving)) != 0) + goto xdr_error; if ((status = decode_attr_exclcreat_supported(xdr, bitmap, res->exclcreat_bitmask)) != 0) goto xdr_error; diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2a9acbfe00f0..f24fc67af42d 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -271,6 +271,8 @@ struct nfs_server { #define NFS_CAP_ACLS (1U << 3) #define NFS_CAP_ATOMIC_OPEN (1U << 4) #define NFS_CAP_LGOPEN (1U << 5) +#define NFS_CAP_CASE_INSENSITIVE (1U << 6) +#define NFS_CAP_CASE_PRESERVING (1U << 7) #define NFS_CAP_POSIX_LOCK (1U << 14) #define NFS_CAP_UIDGID_NOMAP (1U << 15) #define NFS_CAP_STATEID_NFSV41 (1U << 16) diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9102bdaa3faa..ddff92396a3f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1194,6 +1194,8 @@ struct nfs4_server_caps_res { u32 has_links; u32 has_symlinks; u32 fh_expire_type; + u32 case_insensitive; + u32 case_preserving; }; #define NFS4_PATHNAME_MAXCOMPONENTS 512 -- cgit v1.2.3 From 703f7066f40599c290babdb79dd61319264987e9 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 7 Dec 2021 13:17:33 +0100 Subject: random: remove unused irq_flags argument from add_interrupt_randomness() Since commit ee3e00e9e7101 ("random: use registers from interrupted code for CPU's w/o a cycle counter") the irq_flags argument is no longer used. Remove unused irq_flags. Cc: Borislav Petkov Cc: Dave Hansen Cc: Dexuan Cui Cc: H. Peter Anvin Cc: Haiyang Zhang Cc: Ingo Molnar Cc: K. Y. Srinivasan Cc: Stephen Hemminger Cc: Thomas Gleixner Cc: Wei Liu Cc: linux-hyperv@vger.kernel.org Cc: x86@kernel.org Signed-off-by: Sebastian Andrzej Siewior Acked-by: Wei Liu Signed-off-by: Jason A. Donenfeld --- arch/x86/kernel/cpu/mshyperv.c | 2 +- drivers/char/random.c | 4 ++-- drivers/hv/vmbus_drv.c | 2 +- include/linux/random.h | 2 +- kernel/irq/handle.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index ff55df60228f..2a0f83678911 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -79,7 +79,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_stimer0) inc_irq_stat(hyperv_stimer0_count); if (hv_stimer0_handler) hv_stimer0_handler(); - add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0); + add_interrupt_randomness(HYPERV_STIMER0_VECTOR); ack_APIC_irq(); set_irq_regs(old_regs); diff --git a/drivers/char/random.c b/drivers/char/random.c index c81485e2f126..4b0753eb8bfb 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -200,7 +200,7 @@ * void add_device_randomness(const void *buf, unsigned int size); * void add_input_randomness(unsigned int type, unsigned int code, * unsigned int value); - * void add_interrupt_randomness(int irq, int irq_flags); + * void add_interrupt_randomness(int irq); * void add_disk_randomness(struct gendisk *disk); * void add_hwgenerator_randomness(const char *buffer, size_t count, * size_t entropy); @@ -1253,7 +1253,7 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs) return *ptr; } -void add_interrupt_randomness(int irq, int irq_flags) +void add_interrupt_randomness(int irq) { struct entropy_store *r; struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 392c1ac4f819..7ae04ccb1043 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1381,7 +1381,7 @@ static void vmbus_isr(void) tasklet_schedule(&hv_cpu->msg_dpc); } - add_interrupt_randomness(vmbus_interrupt, 0); + add_interrupt_randomness(vmbus_interrupt); } static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id) diff --git a/include/linux/random.h b/include/linux/random.h index f45b8be3e3c4..c45b2693e51f 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -35,7 +35,7 @@ static inline void add_latent_entropy(void) {} extern void add_input_randomness(unsigned int type, unsigned int code, unsigned int value) __latent_entropy; -extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; +extern void add_interrupt_randomness(int irq) __latent_entropy; extern void get_random_bytes(void *buf, int nbytes); extern int wait_for_random_bytes(void); diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 27182003b879..68c76c3caaf5 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -197,7 +197,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval = __handle_irq_event_percpu(desc, &flags); - add_interrupt_randomness(desc->irq_data.irq, flags); + add_interrupt_randomness(desc->irq_data.irq); if (!irq_settings_no_debug(desc)) note_interrupt(desc, retval); -- cgit v1.2.3 From 79b60ca83b6fa63ef307d2edcc77ee6581da8971 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Sun, 12 Dec 2021 14:51:27 +0200 Subject: net/mlx5: Introduce API for bulk request and release of IRQs Currently IRQs are requested one by one. To balance spreading IRQs among cpus using such scheme requires remembering cpu mask for the cpus used for a given device. This complicates the IRQ allocation scheme in subsequent patch. Hence, prepare the code for bulk IRQs allocation. This enables spreading IRQs among cpus in subsequent patch. Signed-off-by: Shay Drory Reviewed-by: Parav Pandit Signed-off-by: Saeed Mahameed --- drivers/infiniband/hw/mlx5/odp.c | 6 -- drivers/net/ethernet/mellanox/mlx5/core/eq.c | 98 ++++++++++++++-------- drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h | 5 +- drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 69 +++++++++++++-- include/linux/mlx5/eq.h | 4 +- 5 files changed, 135 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 91eb615b89ee..86842cd580ba 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1541,16 +1541,10 @@ int mlx5r_odp_create_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq) eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int; param = (struct mlx5_eq_param) { - .irq_index = MLX5_IRQ_EQ_CTRL, .nent = MLX5_IB_NUM_PF_EQE, }; param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT; - if (!zalloc_cpumask_var(¶m.affinity, GFP_KERNEL)) { - err = -ENOMEM; - goto err_wq; - } eq->core = mlx5_eq_create_generic(dev->mdev, ¶m); - free_cpumask_var(param.affinity); if (IS_ERR(eq->core)) { err = PTR_ERR(eq->core); goto err_wq; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 1eb0326a489b..14547b6f2894 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -59,6 +59,8 @@ struct mlx5_eq_table { struct mutex lock; /* sync async eqs creations */ int num_comp_eqs; struct mlx5_irq_table *irq_table; + struct mlx5_irq **comp_irqs; + struct mlx5_irq *ctrl_irq; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap; #endif @@ -266,8 +268,8 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0}; u8 log_eq_stride = ilog2(MLX5_EQE_SIZE); struct mlx5_priv *priv = &dev->priv; - u16 vecidx = param->irq_index; __be64 *pas; + u16 vecidx; void *eqc; int inlen; u32 *in; @@ -289,23 +291,16 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, mlx5_init_fbc(eq->frag_buf.frags, log_eq_stride, log_eq_size, &eq->fbc); init_eq_buf(eq); - if (vecidx == MLX5_IRQ_EQ_CTRL) - eq->irq = mlx5_ctrl_irq_request(dev); - else - eq->irq = mlx5_irq_request(dev, vecidx, param->affinity); - if (IS_ERR(eq->irq)) { - err = PTR_ERR(eq->irq); - goto err_buf; - } - + eq->irq = param->irq; vecidx = mlx5_irq_get_index(eq->irq); + inlen = MLX5_ST_SZ_BYTES(create_eq_in) + MLX5_FLD_SZ_BYTES(create_eq_in, pas[0]) * eq->frag_buf.npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) { err = -ENOMEM; - goto err_irq; + goto err_buf; } pas = (__be64 *)MLX5_ADDR_OF(create_eq_in, in, pas); @@ -349,8 +344,6 @@ err_eq: err_in: kvfree(in); -err_irq: - mlx5_irq_release(eq->irq); err_buf: mlx5_frag_buf_free(dev, &eq->frag_buf); return err; @@ -404,7 +397,6 @@ static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) if (err) mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n", eq->eqn); - mlx5_irq_release(eq->irq); mlx5_frag_buf_free(dev, &eq->frag_buf); return err; @@ -597,11 +589,8 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq, eq->irq_nb.notifier_call = mlx5_eq_async_int; spin_lock_init(&eq->lock); - if (!zalloc_cpumask_var(¶m->affinity, GFP_KERNEL)) - return -ENOMEM; err = create_async_eq(dev, &eq->core, param); - free_cpumask_var(param->affinity); if (err) { mlx5_core_warn(dev, "failed to create %s EQ %d\n", name, err); return err; @@ -646,11 +635,18 @@ static int create_async_eqs(struct mlx5_core_dev *dev) struct mlx5_eq_param param = {}; int err; + /* All the async_eqs are using single IRQ, request one IRQ and share its + * index among all the async_eqs of this device. + */ + table->ctrl_irq = mlx5_ctrl_irq_request(dev); + if (IS_ERR(table->ctrl_irq)) + return PTR_ERR(table->ctrl_irq); + MLX5_NB_INIT(&table->cq_err_nb, cq_err_event_notifier, CQ_ERROR); mlx5_eq_notifier_register(dev, &table->cq_err_nb); param = (struct mlx5_eq_param) { - .irq_index = MLX5_IRQ_EQ_CTRL, + .irq = table->ctrl_irq, .nent = MLX5_NUM_CMD_EQE, .mask[0] = 1ull << MLX5_EVENT_TYPE_CMD, }; @@ -663,7 +659,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); param = (struct mlx5_eq_param) { - .irq_index = MLX5_IRQ_EQ_CTRL, + .irq = table->ctrl_irq, .nent = async_eq_depth_devlink_param_get(dev), }; @@ -673,7 +669,7 @@ static int create_async_eqs(struct mlx5_core_dev *dev) goto err2; param = (struct mlx5_eq_param) { - .irq_index = MLX5_IRQ_EQ_CTRL, + .irq = table->ctrl_irq, .nent = /* TODO: sriov max_vf + */ 1, .mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST, }; @@ -692,6 +688,7 @@ err2: err1: mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); mlx5_eq_notifier_unregister(dev, &table->cq_err_nb); + mlx5_ctrl_irq_release(table->ctrl_irq); return err; } @@ -706,6 +703,7 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev) cleanup_async_eq(dev, &table->cmd_eq, "cmd"); mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); mlx5_eq_notifier_unregister(dev, &table->cq_err_nb); + mlx5_ctrl_irq_release(table->ctrl_irq); } struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev) @@ -733,12 +731,10 @@ mlx5_eq_create_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL); int err; - if (!cpumask_available(param->affinity)) - return ERR_PTR(-EINVAL); - if (!eq) return ERR_PTR(-ENOMEM); + param->irq = dev->priv.eq_table->ctrl_irq; err = create_async_eq(dev, eq, param); if (err) { kvfree(eq); @@ -798,6 +794,45 @@ void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm) } EXPORT_SYMBOL(mlx5_eq_update_ci); +static void comp_irqs_release(struct mlx5_core_dev *dev) +{ + struct mlx5_eq_table *table = dev->priv.eq_table; + + mlx5_irqs_release_vectors(table->comp_irqs, table->num_comp_eqs); + kfree(table->comp_irqs); +} + +static int comp_irqs_request(struct mlx5_core_dev *dev) +{ + struct mlx5_eq_table *table = dev->priv.eq_table; + int ncomp_eqs = table->num_comp_eqs; + u16 *cpus; + int ret; + int i; + + ncomp_eqs = table->num_comp_eqs; + table->comp_irqs = kcalloc(ncomp_eqs, sizeof(*table->comp_irqs), GFP_KERNEL); + if (!table->comp_irqs) + return -ENOMEM; + + cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL); + if (!cpus) { + ret = -ENOMEM; + goto free_irqs; + } + for (i = 0; i < ncomp_eqs; i++) + cpus[i] = cpumask_local_spread(i, dev->priv.numa_node); + ret = mlx5_irqs_request_vectors(dev, cpus, ncomp_eqs, table->comp_irqs); + kfree(cpus); + if (ret < 0) + goto free_irqs; + return ret; + +free_irqs: + kfree(table->comp_irqs); + return ret; +} + static void destroy_comp_eqs(struct mlx5_core_dev *dev) { struct mlx5_eq_table *table = dev->priv.eq_table; @@ -812,6 +847,7 @@ static void destroy_comp_eqs(struct mlx5_core_dev *dev) tasklet_disable(&eq->tasklet_ctx.task); kfree(eq); } + comp_irqs_release(dev); } static u16 comp_eq_depth_devlink_param_get(struct mlx5_core_dev *dev) @@ -838,12 +874,13 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) int err; int i; + ncomp_eqs = comp_irqs_request(dev); + if (ncomp_eqs < 0) + return ncomp_eqs; INIT_LIST_HEAD(&table->comp_eqs_list); - ncomp_eqs = table->num_comp_eqs; nent = comp_eq_depth_devlink_param_get(dev); for (i = 0; i < ncomp_eqs; i++) { struct mlx5_eq_param param = {}; - int vecidx = i; eq = kzalloc(sizeof(*eq), GFP_KERNEL); if (!eq) { @@ -858,18 +895,11 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) eq->irq_nb.notifier_call = mlx5_eq_comp_int; param = (struct mlx5_eq_param) { - .irq_index = vecidx, + .irq = table->comp_irqs[i], .nent = nent, }; - if (!zalloc_cpumask_var(¶m.affinity, GFP_KERNEL)) { - err = -ENOMEM; - goto clean_eq; - } - cpumask_set_cpu(cpumask_local_spread(i, dev->priv.numa_node), - param.affinity); err = create_map_eq(dev, &eq->core, ¶m); - free_cpumask_var(param.affinity); if (err) goto clean_eq; err = mlx5_eq_enable(dev, &eq->core, &eq->irq_nb); @@ -883,7 +913,9 @@ static int create_comp_eqs(struct mlx5_core_dev *dev) list_add_tail(&eq->list, &table->comp_eqs_list); } + table->num_comp_eqs = ncomp_eqs; return 0; + clean_eq: kfree(eq); clean: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h index db58f5e3f457..f2ad3c21802f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h @@ -23,9 +23,12 @@ int mlx5_set_msix_vec_count(struct mlx5_core_dev *dev, int devfn, int mlx5_get_default_msix_vec_count(struct mlx5_core_dev *dev, int num_vfs); struct mlx5_irq *mlx5_ctrl_irq_request(struct mlx5_core_dev *dev); +void mlx5_ctrl_irq_release(struct mlx5_irq *ctrl_irq); struct mlx5_irq *mlx5_irq_request(struct mlx5_core_dev *dev, u16 vecidx, struct cpumask *affinity); -void mlx5_irq_release(struct mlx5_irq *irq); +int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs, + struct mlx5_irq **irqs); +void mlx5_irqs_release_vectors(struct mlx5_irq **irqs, int nirqs); int mlx5_irq_attach_nb(struct mlx5_irq *irq, struct notifier_block *nb); int mlx5_irq_detach_nb(struct mlx5_irq *irq, struct notifier_block *nb); struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 496826a7a88b..2e19c3c222fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -342,13 +342,27 @@ static struct mlx5_irq_pool *ctrl_irq_pool_get(struct mlx5_core_dev *dev) } /** - * mlx5_irq_release - release an IRQ back to the system. - * @irq: irq to be released. + * mlx5_irqs_release - release one or more IRQs back to the system. + * @irqs: IRQs to be released. + * @nirqs: number of IRQs to be released. */ -void mlx5_irq_release(struct mlx5_irq *irq) +static void mlx5_irqs_release(struct mlx5_irq **irqs, int nirqs) { - synchronize_irq(irq->irqn); - irq_put(irq); + int i; + + for (i = 0; i < nirqs; i++) { + synchronize_irq(irqs[i]->irqn); + irq_put(irqs[i]); + } +} + +/** + * mlx5_ctrl_irq_release - release a ctrl IRQ back to the system. + * @ctrl_irq: ctrl IRQ to be released. + */ +void mlx5_ctrl_irq_release(struct mlx5_irq *ctrl_irq) +{ + mlx5_irqs_release(&ctrl_irq, 1); } /** @@ -423,6 +437,51 @@ out: return irq; } +/** + * mlx5_irqs_release_vectors - release one or more IRQs back to the system. + * @irqs: IRQs to be released. + * @nirqs: number of IRQs to be released. + */ +void mlx5_irqs_release_vectors(struct mlx5_irq **irqs, int nirqs) +{ + mlx5_irqs_release(irqs, nirqs); +} + +/** + * mlx5_irqs_request_vectors - request one or more IRQs for mlx5 device. + * @dev: mlx5 device that is requesting the IRQs. + * @cpus: CPUs array for binding the IRQs + * @nirqs: number of IRQs to request. + * @irqs: an output array of IRQs pointers. + * + * Each IRQ is bound to at most 1 CPU. + * This function is requests nirqs IRQs, starting from @vecidx. + * + * This function returns the number of IRQs requested, (which might be smaller than + * @nirqs), if successful, or a negative error code in case of an error. + */ +int mlx5_irqs_request_vectors(struct mlx5_core_dev *dev, u16 *cpus, int nirqs, + struct mlx5_irq **irqs) +{ + cpumask_var_t req_mask; + struct mlx5_irq *irq; + int i; + + if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) + return -ENOMEM; + for (i = 0; i < nirqs; i++) { + cpumask_set_cpu(cpus[i], req_mask); + irq = mlx5_irq_request(dev, i, req_mask); + if (IS_ERR(irq)) + break; + cpumask_clear(req_mask); + irqs[i] = irq; + } + + free_cpumask_var(req_mask); + return i ? i : PTR_ERR(irq); +} + static struct mlx5_irq_pool * irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name, u32 min_threshold, u32 max_threshold) diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index ea3ff5a8ced3..3705a382276b 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -9,13 +9,13 @@ #define MLX5_NUM_SPARE_EQE (0x80) struct mlx5_eq; +struct mlx5_irq; struct mlx5_core_dev; struct mlx5_eq_param { - u8 irq_index; int nent; u64 mask[4]; - cpumask_var_t affinity; + struct mlx5_irq *irq; }; struct mlx5_eq * -- cgit v1.2.3 From 3663f26b389b3951426971b44bb9312fdff0efec Mon Sep 17 00:00:00 2001 From: Ajit Kumar Pandey Date: Sun, 12 Dec 2021 23:35:24 +0530 Subject: drivers: acpi: acpi_apd: Remove unused device property "is-rv" Initially "is-rv" device property is added for 48MHz fixed clock support on Raven or RV architecture. It's unused now as we moved to pci device_id based selection to extend such support on other architectures. This change removed unused code from acpi driver. Signed-off-by: Ajit Kumar Pandey Reviewed-by: Mario Limonciello Link: https://lore.kernel.org/r/20211212180527.1641362-3-AjitKumar.Pandey@amd.com Signed-off-by: Stephen Boyd --- drivers/acpi/acpi_apd.c | 3 --- include/linux/platform_data/clk-fch.h | 1 - 2 files changed, 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 6e02448d15d9..6913e9712852 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -87,9 +87,6 @@ static int fch_misc_setup(struct apd_private_data *pdata) if (ret < 0) return -ENOENT; - if (!acpi_dev_get_property(adev, "is-rv", ACPI_TYPE_INTEGER, &obj)) - clk_data->is_rv = obj->integer.value; - list_for_each_entry(rentry, &resource_list, node) { clk_data->base = devm_ioremap(&adev->dev, rentry->res->start, resource_size(rentry->res)); diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h index b9f682459f08..850ca776156d 100644 --- a/include/linux/platform_data/clk-fch.h +++ b/include/linux/platform_data/clk-fch.h @@ -12,7 +12,6 @@ struct fch_clk_data { void __iomem *base; - u32 is_rv; }; #endif /* __CLK_FCH_H */ -- cgit v1.2.3 From 7fdb98e8a768b3ccc05494d3ea4436047f512b9d Mon Sep 17 00:00:00 2001 From: Ajit Kumar Pandey Date: Sun, 12 Dec 2021 23:35:25 +0530 Subject: ACPI: APD: Add a fmw property clk-name Add a new device property to fetch clk-name from firmware. Signed-off-by: Ajit Kumar Pandey Reviewed-by: Mario Limonciello Link: https://lore.kernel.org/r/20211212180527.1641362-4-AjitKumar.Pandey@amd.com Signed-off-by: Stephen Boyd --- drivers/acpi/acpi_apd.c | 10 ++++++++++ include/linux/platform_data/clk-fch.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/acpi/acpi_apd.c b/drivers/acpi/acpi_apd.c index 6913e9712852..2b958b426b03 100644 --- a/drivers/acpi/acpi_apd.c +++ b/drivers/acpi/acpi_apd.c @@ -87,6 +87,16 @@ static int fch_misc_setup(struct apd_private_data *pdata) if (ret < 0) return -ENOENT; + if (!acpi_dev_get_property(adev, "clk-name", ACPI_TYPE_STRING, &obj)) { + clk_data->name = devm_kzalloc(&adev->dev, obj->string.length, + GFP_KERNEL); + + strcpy(clk_data->name, obj->string.pointer); + } else { + /* Set default name to mclk if entry missing in firmware */ + clk_data->name = "mclk"; + } + list_for_each_entry(rentry, &resource_list, node) { clk_data->base = devm_ioremap(&adev->dev, rentry->res->start, resource_size(rentry->res)); diff --git a/include/linux/platform_data/clk-fch.h b/include/linux/platform_data/clk-fch.h index 850ca776156d..11a2a23fd9b2 100644 --- a/include/linux/platform_data/clk-fch.h +++ b/include/linux/platform_data/clk-fch.h @@ -12,6 +12,7 @@ struct fch_clk_data { void __iomem *base; + char *name; }; #endif /* __CLK_FCH_H */ -- cgit v1.2.3 From 2cee6fbb7f01bcb25f11ef1439e89a29de4c0c1d Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 25 Oct 2021 21:53:44 +0100 Subject: fscache: Remove the contents of the fscache driver, pending rewrite Remove the code that comprises the fscache driver as it's going to be substantially rewritten, with the majority of the code being erased in the rewrite. A small piece of linux/fscache.h is left as that is #included by a bunch of network filesystems. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819578724.215744.18210619052245724238.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906884814.143852.6727245089843862889.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967077097.1823006.1377665951499979089.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021485548.640689.13876080567388696162.stgit@warthog.procyon.org.uk/ # v4 --- fs/9p/vfs_addr.c | 8 +- fs/Makefile | 1 - fs/afs/file.c | 8 +- fs/fscache/Kconfig | 39 -- fs/fscache/Makefile | 20 - fs/fscache/cache.c | 416 -------------- fs/fscache/cookie.c | 1071 ---------------------------------- fs/fscache/fsdef.c | 98 ---- fs/fscache/internal.h | 461 --------------- fs/fscache/io.c | 116 ---- fs/fscache/main.c | 230 -------- fs/fscache/netfs.c | 74 --- fs/fscache/object.c | 1125 ------------------------------------ fs/fscache/operation.c | 633 -------------------- fs/fscache/page.c | 1242 ---------------------------------------- fs/fscache/proc.c | 71 --- fs/fscache/stats.c | 283 --------- include/linux/fscache-cache.h | 548 +----------------- include/linux/fscache.h | 851 +-------------------------- include/trace/events/fscache.h | 523 ----------------- 20 files changed, 13 insertions(+), 7805 deletions(-) delete mode 100644 fs/fscache/Makefile delete mode 100644 fs/fscache/cache.c delete mode 100644 fs/fscache/cookie.c delete mode 100644 fs/fscache/fsdef.c delete mode 100644 fs/fscache/internal.h delete mode 100644 fs/fscache/io.c delete mode 100644 fs/fscache/main.c delete mode 100644 fs/fscache/netfs.c delete mode 100644 fs/fscache/object.c delete mode 100644 fs/fscache/operation.c delete mode 100644 fs/fscache/page.c delete mode 100644 fs/fscache/proc.c delete mode 100644 fs/fscache/stats.c delete mode 100644 include/trace/events/fscache.h (limited to 'include/linux') diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index fac918ccb305..4ea8f862b9e4 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -76,9 +76,7 @@ static void v9fs_req_cleanup(struct address_space *mapping, void *priv) */ static bool v9fs_is_cache_enabled(struct inode *inode) { - struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(inode)); - - return fscache_cookie_enabled(cookie) && !hlist_empty(&cookie->backing_objects); + return fscache_cookie_enabled(v9fs_inode_cookie(V9FS_I(inode))); } /** @@ -87,9 +85,13 @@ static bool v9fs_is_cache_enabled(struct inode *inode) */ static int v9fs_begin_cache_operation(struct netfs_read_request *rreq) { +#ifdef CONFIG_9P_FSCACHE struct fscache_cookie *cookie = v9fs_inode_cookie(V9FS_I(rreq->inode)); return fscache_begin_read_operation(rreq, cookie); +#else + return -ENOBUFS; +#endif } static const struct netfs_read_request_ops v9fs_req_ops = { diff --git a/fs/Makefile b/fs/Makefile index 290815f3fd31..23ddd0803d14 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -67,7 +67,6 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_NETFS_SUPPORT) += netfs/ -obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT4_FS) += ext4/ # We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the diff --git a/fs/afs/file.c b/fs/afs/file.c index cb6ad61eec3b..97a51e1de55c 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -352,16 +352,18 @@ static void afs_init_rreq(struct netfs_read_request *rreq, struct file *file) static bool afs_is_cache_enabled(struct inode *inode) { - struct fscache_cookie *cookie = afs_vnode_cache(AFS_FS_I(inode)); - - return fscache_cookie_enabled(cookie) && !hlist_empty(&cookie->backing_objects); + return fscache_cookie_enabled(afs_vnode_cache(AFS_FS_I(inode))); } static int afs_begin_cache_operation(struct netfs_read_request *rreq) { +#ifdef CONFIG_AFS_FSCACHE struct afs_vnode *vnode = AFS_FS_I(rreq->inode); return fscache_begin_read_operation(rreq, afs_vnode_cache(vnode)); +#else + return -ENOBUFS; +#endif } static int afs_check_write_begin(struct file *file, loff_t pos, unsigned len, diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 76316c4a3fb7..6440484d9461 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -1,43 +1,4 @@ # SPDX-License-Identifier: GPL-2.0-only -config FSCACHE - tristate "General filesystem local caching manager" - select NETFS_SUPPORT - help - This option enables a generic filesystem caching manager that can be - used by various network and other filesystems to cache data locally. - Different sorts of caches can be plugged in, depending on the - resources available. - - See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_STATS - bool "Gather statistical information on local caching" - depends on FSCACHE && PROC_FS - select NETFS_STATS - help - This option causes statistical information to be gathered on local - caching and exported through file: - - /proc/fs/fscache/stats - - The gathering of statistics adds a certain amount of overhead to - execution as there are a quite a few stats gathered, and on a - multi-CPU system these may be on cachelines that keep bouncing - between CPUs. On the other hand, the stats are very useful for - debugging purposes. Saying 'Y' here is recommended. - - See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_DEBUG - bool "Debug FS-Cache" - depends on FSCACHE - help - This permits debugging to be dynamically enabled in the local caching - management module. If this is set, the debugging output may be - enabled by setting bits in /sys/modules/fscache/parameter/debug. - - See Documentation/filesystems/caching/fscache.rst for more information. - config FSCACHE_OLD_API bool diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile deleted file mode 100644 index 03a871d689bb..000000000000 --- a/fs/fscache/Makefile +++ /dev/null @@ -1,20 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# -# Makefile for general filesystem caching code -# - -fscache-y := \ - cache.o \ - cookie.o \ - fsdef.o \ - io.o \ - main.o \ - netfs.o \ - object.o \ - operation.o \ - page.o - -fscache-$(CONFIG_PROC_FS) += proc.o -fscache-$(CONFIG_FSCACHE_STATS) += stats.o - -obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c deleted file mode 100644 index bd4f44c1cce0..000000000000 --- a/fs/fscache/cache.c +++ /dev/null @@ -1,416 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache cache handling - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL CACHE -#include -#include -#include "internal.h" - -LIST_HEAD(fscache_cache_list); -DECLARE_RWSEM(fscache_addremove_sem); -DECLARE_WAIT_QUEUE_HEAD(fscache_cache_cleared_wq); -EXPORT_SYMBOL(fscache_cache_cleared_wq); - -static LIST_HEAD(fscache_cache_tag_list); - -/* - * look up a cache tag - */ -struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *name) -{ - struct fscache_cache_tag *tag, *xtag; - - /* firstly check for the existence of the tag under read lock */ - down_read(&fscache_addremove_sem); - - list_for_each_entry(tag, &fscache_cache_tag_list, link) { - if (strcmp(tag->name, name) == 0) { - atomic_inc(&tag->usage); - up_read(&fscache_addremove_sem); - return tag; - } - } - - up_read(&fscache_addremove_sem); - - /* the tag does not exist - create a candidate */ - xtag = kzalloc(sizeof(*xtag) + strlen(name) + 1, GFP_KERNEL); - if (!xtag) - /* return a dummy tag if out of memory */ - return ERR_PTR(-ENOMEM); - - atomic_set(&xtag->usage, 1); - strcpy(xtag->name, name); - - /* write lock, search again and add if still not present */ - down_write(&fscache_addremove_sem); - - list_for_each_entry(tag, &fscache_cache_tag_list, link) { - if (strcmp(tag->name, name) == 0) { - atomic_inc(&tag->usage); - up_write(&fscache_addremove_sem); - kfree(xtag); - return tag; - } - } - - list_add_tail(&xtag->link, &fscache_cache_tag_list); - up_write(&fscache_addremove_sem); - return xtag; -} - -/* - * release a reference to a cache tag - */ -void __fscache_release_cache_tag(struct fscache_cache_tag *tag) -{ - if (tag != ERR_PTR(-ENOMEM)) { - down_write(&fscache_addremove_sem); - - if (atomic_dec_and_test(&tag->usage)) - list_del_init(&tag->link); - else - tag = NULL; - - up_write(&fscache_addremove_sem); - - kfree(tag); - } -} - -/* - * select a cache in which to store an object - * - the cache addremove semaphore must be at least read-locked by the caller - * - the object will never be an index - */ -struct fscache_cache *fscache_select_cache_for_object( - struct fscache_cookie *cookie) -{ - struct fscache_cache_tag *tag; - struct fscache_object *object; - struct fscache_cache *cache; - - _enter(""); - - if (list_empty(&fscache_cache_list)) { - _leave(" = NULL [no cache]"); - return NULL; - } - - /* we check the parent to determine the cache to use */ - spin_lock(&cookie->lock); - - /* the first in the parent's backing list should be the preferred - * cache */ - if (!hlist_empty(&cookie->backing_objects)) { - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - cache = object->cache; - if (fscache_object_is_dying(object) || - test_bit(FSCACHE_IOERROR, &cache->flags)) - cache = NULL; - - spin_unlock(&cookie->lock); - _leave(" = %s [parent]", cache ? cache->tag->name : "NULL"); - return cache; - } - - /* the parent is unbacked */ - if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) { - /* cookie not an index and is unbacked */ - spin_unlock(&cookie->lock); - _leave(" = NULL [cookie ub,ni]"); - return NULL; - } - - spin_unlock(&cookie->lock); - - if (!cookie->def->select_cache) - goto no_preference; - - /* ask the netfs for its preference */ - tag = cookie->def->select_cache(cookie->parent->netfs_data, - cookie->netfs_data); - if (!tag) - goto no_preference; - - if (tag == ERR_PTR(-ENOMEM)) { - _leave(" = NULL [nomem tag]"); - return NULL; - } - - if (!tag->cache) { - _leave(" = NULL [unbacked tag]"); - return NULL; - } - - if (test_bit(FSCACHE_IOERROR, &tag->cache->flags)) - return NULL; - - _leave(" = %s [specific]", tag->name); - return tag->cache; - -no_preference: - /* netfs has no preference - just select first cache */ - cache = list_entry(fscache_cache_list.next, - struct fscache_cache, link); - _leave(" = %s [first]", cache->tag->name); - return cache; -} - -/** - * fscache_init_cache - Initialise a cache record - * @cache: The cache record to be initialised - * @ops: The cache operations to be installed in that record - * @idfmt: Format string to define identifier - * @...: sprintf-style arguments - * - * Initialise a record of a cache and fill in the name. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, - ...) -{ - va_list va; - - memset(cache, 0, sizeof(*cache)); - - cache->ops = ops; - - va_start(va, idfmt); - vsnprintf(cache->identifier, sizeof(cache->identifier), idfmt, va); - va_end(va); - - INIT_WORK(&cache->op_gc, fscache_operation_gc); - INIT_LIST_HEAD(&cache->link); - INIT_LIST_HEAD(&cache->object_list); - INIT_LIST_HEAD(&cache->op_gc_list); - spin_lock_init(&cache->object_list_lock); - spin_lock_init(&cache->op_gc_list_lock); -} -EXPORT_SYMBOL(fscache_init_cache); - -/** - * fscache_add_cache - Declare a cache as being open for business - * @cache: The record describing the cache - * @ifsdef: The record of the cache object describing the top-level index - * @tagname: The tag describing this cache - * - * Add a cache to the system, making it available for netfs's to use. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -int fscache_add_cache(struct fscache_cache *cache, - struct fscache_object *ifsdef, - const char *tagname) -{ - struct fscache_cache_tag *tag; - - ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index); - BUG_ON(!cache->ops); - BUG_ON(!ifsdef); - - cache->flags = 0; - ifsdef->event_mask = - ((1 << NR_FSCACHE_OBJECT_EVENTS) - 1) & - ~(1 << FSCACHE_OBJECT_EV_CLEARED); - __set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &ifsdef->flags); - - if (!tagname) - tagname = cache->identifier; - - BUG_ON(!tagname[0]); - - _enter("{%s.%s},,%s", cache->ops->name, cache->identifier, tagname); - - /* we use the cache tag to uniquely identify caches */ - tag = __fscache_lookup_cache_tag(tagname); - if (IS_ERR(tag)) - goto nomem; - - if (test_and_set_bit(FSCACHE_TAG_RESERVED, &tag->flags)) - goto tag_in_use; - - cache->kobj = kobject_create_and_add(tagname, fscache_root); - if (!cache->kobj) - goto error; - - ifsdef->cache = cache; - cache->fsdef = ifsdef; - - down_write(&fscache_addremove_sem); - - tag->cache = cache; - cache->tag = tag; - - /* add the cache to the list */ - list_add(&cache->link, &fscache_cache_list); - - /* add the cache's netfs definition index object to the cache's - * list */ - spin_lock(&cache->object_list_lock); - list_add_tail(&ifsdef->cache_link, &cache->object_list); - spin_unlock(&cache->object_list_lock); - - /* add the cache's netfs definition index object to the top level index - * cookie as a known backing object */ - spin_lock(&fscache_fsdef_index.lock); - - hlist_add_head(&ifsdef->cookie_link, - &fscache_fsdef_index.backing_objects); - - refcount_inc(&fscache_fsdef_index.ref); - - /* done */ - spin_unlock(&fscache_fsdef_index.lock); - up_write(&fscache_addremove_sem); - - pr_notice("Cache \"%s\" added (type %s)\n", - cache->tag->name, cache->ops->name); - kobject_uevent(cache->kobj, KOBJ_ADD); - - _leave(" = 0 [%s]", cache->identifier); - return 0; - -tag_in_use: - pr_err("Cache tag '%s' already in use\n", tagname); - __fscache_release_cache_tag(tag); - _leave(" = -EXIST"); - return -EEXIST; - -error: - __fscache_release_cache_tag(tag); - _leave(" = -EINVAL"); - return -EINVAL; - -nomem: - _leave(" = -ENOMEM"); - return -ENOMEM; -} -EXPORT_SYMBOL(fscache_add_cache); - -/** - * fscache_io_error - Note a cache I/O error - * @cache: The record describing the cache - * - * Note that an I/O error occurred in a cache and that it should no longer be - * used for anything. This also reports the error into the kernel log. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -void fscache_io_error(struct fscache_cache *cache) -{ - if (!test_and_set_bit(FSCACHE_IOERROR, &cache->flags)) - pr_err("Cache '%s' stopped due to I/O error\n", - cache->ops->name); -} -EXPORT_SYMBOL(fscache_io_error); - -/* - * request withdrawal of all the objects in a cache - * - all the objects being withdrawn are moved onto the supplied list - */ -static void fscache_withdraw_all_objects(struct fscache_cache *cache, - struct list_head *dying_objects) -{ - struct fscache_object *object; - - while (!list_empty(&cache->object_list)) { - spin_lock(&cache->object_list_lock); - - if (!list_empty(&cache->object_list)) { - object = list_entry(cache->object_list.next, - struct fscache_object, cache_link); - list_move_tail(&object->cache_link, dying_objects); - - _debug("withdraw %x", object->cookie->debug_id); - - /* This must be done under object_list_lock to prevent - * a race with fscache_drop_object(). - */ - fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL); - } - - spin_unlock(&cache->object_list_lock); - cond_resched(); - } -} - -/** - * fscache_withdraw_cache - Withdraw a cache from the active service - * @cache: The record describing the cache - * - * Withdraw a cache from service, unbinding all its cache objects from the - * netfs cookies they're currently representing. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -void fscache_withdraw_cache(struct fscache_cache *cache) -{ - LIST_HEAD(dying_objects); - - _enter(""); - - pr_notice("Withdrawing cache \"%s\"\n", - cache->tag->name); - - /* make the cache unavailable for cookie acquisition */ - if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags)) - BUG(); - - down_write(&fscache_addremove_sem); - list_del_init(&cache->link); - cache->tag->cache = NULL; - up_write(&fscache_addremove_sem); - - /* make sure all pages pinned by operations on behalf of the netfs are - * written to disk */ - fscache_stat(&fscache_n_cop_sync_cache); - cache->ops->sync_cache(cache); - fscache_stat_d(&fscache_n_cop_sync_cache); - - /* dissociate all the netfs pages backed by this cache from the block - * mappings in the cache */ - fscache_stat(&fscache_n_cop_dissociate_pages); - cache->ops->dissociate_pages(cache); - fscache_stat_d(&fscache_n_cop_dissociate_pages); - - /* we now have to destroy all the active objects pertaining to this - * cache - which we do by passing them off to thread pool to be - * disposed of */ - _debug("destroy"); - - fscache_withdraw_all_objects(cache, &dying_objects); - - /* wait for all extant objects to finish their outstanding operations - * and go away */ - _debug("wait for finish"); - wait_event(fscache_cache_cleared_wq, - atomic_read(&cache->object_count) == 0); - _debug("wait for clearance"); - wait_event(fscache_cache_cleared_wq, - list_empty(&cache->object_list)); - _debug("cleared"); - ASSERT(list_empty(&dying_objects)); - - kobject_put(cache->kobj); - - clear_bit(FSCACHE_TAG_RESERVED, &cache->tag->flags); - fscache_release_cache_tag(cache->tag); - cache->tag = NULL; - - _leave(""); -} -EXPORT_SYMBOL(fscache_withdraw_cache); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c deleted file mode 100644 index cd42be646ed3..000000000000 --- a/fs/fscache/cookie.c +++ /dev/null @@ -1,1071 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* netfs cookie management - * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * See Documentation/filesystems/caching/netfs-api.rst for more information on - * the netfs API. - */ - -#define FSCACHE_DEBUG_LEVEL COOKIE -#include -#include -#include "internal.h" - -struct kmem_cache *fscache_cookie_jar; - -static atomic_t fscache_object_debug_id = ATOMIC_INIT(0); - -#define fscache_cookie_hash_shift 15 -static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; -static LIST_HEAD(fscache_cookies); -static DEFINE_RWLOCK(fscache_cookies_lock); - -static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie, - loff_t object_size); -static int fscache_alloc_object(struct fscache_cache *cache, - struct fscache_cookie *cookie); -static int fscache_attach_object(struct fscache_cookie *cookie, - struct fscache_object *object); - -static void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) -{ - struct fscache_object *object; - struct hlist_node *o; - const u8 *k; - unsigned loop; - - pr_err("%c-cookie c=%08x [p=%08x fl=%lx nc=%u na=%u]\n", - prefix, - cookie->debug_id, - cookie->parent ? cookie->parent->debug_id : 0, - cookie->flags, - atomic_read(&cookie->n_children), - atomic_read(&cookie->n_active)); - pr_err("%c-cookie d=%p{%s} n=%p\n", - prefix, - cookie->def, - cookie->def ? cookie->def->name : "?", - cookie->netfs_data); - - o = READ_ONCE(cookie->backing_objects.first); - if (o) { - object = hlist_entry(o, struct fscache_object, cookie_link); - pr_err("%c-cookie o=%u\n", prefix, object->debug_id); - } - - pr_err("%c-key=[%u] '", prefix, cookie->key_len); - k = (cookie->key_len <= sizeof(cookie->inline_key)) ? - cookie->inline_key : cookie->key; - for (loop = 0; loop < cookie->key_len; loop++) - pr_cont("%02x", k[loop]); - pr_cont("'\n"); -} - -void fscache_free_cookie(struct fscache_cookie *cookie) -{ - if (cookie) { - BUG_ON(!hlist_empty(&cookie->backing_objects)); - write_lock(&fscache_cookies_lock); - list_del(&cookie->proc_link); - write_unlock(&fscache_cookies_lock); - if (cookie->aux_len > sizeof(cookie->inline_aux)) - kfree(cookie->aux); - if (cookie->key_len > sizeof(cookie->inline_key)) - kfree(cookie->key); - kmem_cache_free(fscache_cookie_jar, cookie); - } -} - -/* - * Set the index key in a cookie. The cookie struct has space for a 16-byte - * key plus length and hash, but if that's not big enough, it's instead a - * pointer to a buffer containing 3 bytes of hash, 1 byte of length and then - * the key data. - */ -static int fscache_set_key(struct fscache_cookie *cookie, - const void *index_key, size_t index_key_len) -{ - u32 *buf; - int bufs; - - bufs = DIV_ROUND_UP(index_key_len, sizeof(*buf)); - - if (index_key_len > sizeof(cookie->inline_key)) { - buf = kcalloc(bufs, sizeof(*buf), GFP_KERNEL); - if (!buf) - return -ENOMEM; - cookie->key = buf; - } else { - buf = (u32 *)cookie->inline_key; - } - - memcpy(buf, index_key, index_key_len); - cookie->key_hash = fscache_hash(0, buf, bufs); - return 0; -} - -static long fscache_compare_cookie(const struct fscache_cookie *a, - const struct fscache_cookie *b) -{ - const void *ka, *kb; - - if (a->key_hash != b->key_hash) - return (long)a->key_hash - (long)b->key_hash; - if (a->parent != b->parent) - return (long)a->parent - (long)b->parent; - if (a->key_len != b->key_len) - return (long)a->key_len - (long)b->key_len; - if (a->type != b->type) - return (long)a->type - (long)b->type; - - if (a->key_len <= sizeof(a->inline_key)) { - ka = &a->inline_key; - kb = &b->inline_key; - } else { - ka = a->key; - kb = b->key; - } - return memcmp(ka, kb, a->key_len); -} - -static atomic_t fscache_cookie_debug_id = ATOMIC_INIT(1); - -/* - * Allocate a cookie. - */ -struct fscache_cookie *fscache_alloc_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, - const void *index_key, size_t index_key_len, - const void *aux_data, size_t aux_data_len, - void *netfs_data, - loff_t object_size) -{ - struct fscache_cookie *cookie; - - /* allocate and initialise a cookie */ - cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); - if (!cookie) - return NULL; - - cookie->key_len = index_key_len; - cookie->aux_len = aux_data_len; - - if (fscache_set_key(cookie, index_key, index_key_len) < 0) - goto nomem; - - if (cookie->aux_len <= sizeof(cookie->inline_aux)) { - memcpy(cookie->inline_aux, aux_data, cookie->aux_len); - } else { - cookie->aux = kmemdup(aux_data, cookie->aux_len, GFP_KERNEL); - if (!cookie->aux) - goto nomem; - } - - refcount_set(&cookie->ref, 1); - atomic_set(&cookie->n_children, 0); - cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); - - /* We keep the active count elevated until relinquishment to prevent an - * attempt to wake up every time the object operations queue quiesces. - */ - atomic_set(&cookie->n_active, 1); - - cookie->def = def; - cookie->parent = parent; - cookie->netfs_data = netfs_data; - cookie->flags = (1 << FSCACHE_COOKIE_NO_DATA_YET); - cookie->type = def->type; - spin_lock_init(&cookie->lock); - spin_lock_init(&cookie->stores_lock); - INIT_HLIST_HEAD(&cookie->backing_objects); - - /* radix tree insertion won't use the preallocation pool unless it's - * told it may not wait */ - INIT_RADIX_TREE(&cookie->stores, GFP_NOFS & ~__GFP_DIRECT_RECLAIM); - - write_lock(&fscache_cookies_lock); - list_add_tail(&cookie->proc_link, &fscache_cookies); - write_unlock(&fscache_cookies_lock); - return cookie; - -nomem: - fscache_free_cookie(cookie); - return NULL; -} - -/* - * Attempt to insert the new cookie into the hash. If there's a collision, we - * return the old cookie if it's not in use and an error otherwise. - */ -struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *candidate) -{ - struct fscache_cookie *cursor; - struct hlist_bl_head *h; - struct hlist_bl_node *p; - unsigned int bucket; - - bucket = candidate->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1); - h = &fscache_cookie_hash[bucket]; - - hlist_bl_lock(h); - hlist_bl_for_each_entry(cursor, p, h, hash_link) { - if (fscache_compare_cookie(candidate, cursor) == 0) - goto collision; - } - - __set_bit(FSCACHE_COOKIE_ACQUIRED, &candidate->flags); - fscache_cookie_get(candidate->parent, fscache_cookie_get_acquire_parent); - atomic_inc(&candidate->parent->n_children); - hlist_bl_add_head(&candidate->hash_link, h); - hlist_bl_unlock(h); - return candidate; - -collision: - if (test_and_set_bit(FSCACHE_COOKIE_ACQUIRED, &cursor->flags)) { - trace_fscache_cookie(cursor->debug_id, refcount_read(&cursor->ref), - fscache_cookie_collision); - pr_err("Duplicate cookie detected\n"); - fscache_print_cookie(cursor, 'O'); - fscache_print_cookie(candidate, 'N'); - hlist_bl_unlock(h); - return NULL; - } - - fscache_cookie_get(cursor, fscache_cookie_get_reacquire); - hlist_bl_unlock(h); - return cursor; -} - -/* - * request a cookie to represent an object (index, datafile, xattr, etc) - * - parent specifies the parent object - * - the top level index cookie for each netfs is stored in the fscache_netfs - * struct upon registration - * - def points to the definition - * - the netfs_data will be passed to the functions pointed to in *def - * - all attached caches will be searched to see if they contain this object - * - index objects aren't stored on disk until there's a dependent file that - * needs storing - * - other objects are stored in a selected cache immediately, and all the - * indices forming the path to it are instantiated if necessary - * - we never let on to the netfs about errors - * - we may set a negative cookie pointer, but that's okay - */ -struct fscache_cookie *__fscache_acquire_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, - const void *index_key, size_t index_key_len, - const void *aux_data, size_t aux_data_len, - void *netfs_data, - loff_t object_size, - bool enable) -{ - struct fscache_cookie *candidate, *cookie; - - BUG_ON(!def); - - _enter("{%s},{%s},%p,%u", - parent ? (char *) parent->def->name : "", - def->name, netfs_data, enable); - - if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255) - return NULL; - if (!aux_data || !aux_data_len) { - aux_data = NULL; - aux_data_len = 0; - } - - fscache_stat(&fscache_n_acquires); - - /* if there's no parent cookie, then we don't create one here either */ - if (!parent) { - fscache_stat(&fscache_n_acquires_null); - _leave(" [no parent]"); - return NULL; - } - - /* validate the definition */ - BUG_ON(!def->name[0]); - - BUG_ON(def->type == FSCACHE_COOKIE_TYPE_INDEX && - parent->type != FSCACHE_COOKIE_TYPE_INDEX); - - candidate = fscache_alloc_cookie(parent, def, - index_key, index_key_len, - aux_data, aux_data_len, - netfs_data, object_size); - if (!candidate) { - fscache_stat(&fscache_n_acquires_oom); - _leave(" [ENOMEM]"); - return NULL; - } - - cookie = fscache_hash_cookie(candidate); - if (!cookie) { - trace_fscache_cookie(candidate->debug_id, 1, - fscache_cookie_discard); - goto out; - } - - if (cookie == candidate) - candidate = NULL; - - switch (cookie->type) { - case FSCACHE_COOKIE_TYPE_INDEX: - fscache_stat(&fscache_n_cookie_index); - break; - case FSCACHE_COOKIE_TYPE_DATAFILE: - fscache_stat(&fscache_n_cookie_data); - break; - default: - fscache_stat(&fscache_n_cookie_special); - break; - } - - trace_fscache_acquire(cookie); - - if (enable) { - /* if the object is an index then we need do nothing more here - * - we create indices on disk when we need them as an index - * may exist in multiple caches */ - if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) { - if (fscache_acquire_non_index_cookie(cookie, object_size) == 0) { - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } else { - atomic_dec(&parent->n_children); - fscache_cookie_put(cookie, - fscache_cookie_put_acquire_nobufs); - fscache_stat(&fscache_n_acquires_nobufs); - _leave(" = NULL"); - return NULL; - } - } else { - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } - } - - fscache_stat(&fscache_n_acquires_ok); - -out: - fscache_free_cookie(candidate); - return cookie; -} -EXPORT_SYMBOL(__fscache_acquire_cookie); - -/* - * Enable a cookie to permit it to accept new operations. - */ -void __fscache_enable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - loff_t object_size, - bool (*can_enable)(void *data), - void *data) -{ - _enter("%x", cookie->debug_id); - - trace_fscache_enable(cookie); - - wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - TASK_UNINTERRUPTIBLE); - - fscache_update_aux(cookie, aux_data); - - if (test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) - goto out_unlock; - - if (can_enable && !can_enable(data)) { - /* The netfs decided it didn't want to enable after all */ - } else if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) { - /* Wait for outstanding disablement to complete */ - __fscache_wait_on_invalidate(cookie); - - if (fscache_acquire_non_index_cookie(cookie, object_size) == 0) - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } else { - set_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); - } - -out_unlock: - clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK); -} -EXPORT_SYMBOL(__fscache_enable_cookie); - -/* - * acquire a non-index cookie - * - this must make sure the index chain is instantiated and instantiate the - * object representation too - */ -static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie, - loff_t object_size) -{ - struct fscache_object *object; - struct fscache_cache *cache; - int ret; - - _enter(""); - - set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - - /* now we need to see whether the backing objects for this cookie yet - * exist, if not there'll be nothing to search */ - down_read(&fscache_addremove_sem); - - if (list_empty(&fscache_cache_list)) { - up_read(&fscache_addremove_sem); - _leave(" = 0 [no caches]"); - return 0; - } - - /* select a cache in which to store the object */ - cache = fscache_select_cache_for_object(cookie->parent); - if (!cache) { - up_read(&fscache_addremove_sem); - fscache_stat(&fscache_n_acquires_no_cache); - _leave(" = -ENOMEDIUM [no cache]"); - return -ENOMEDIUM; - } - - _debug("cache %s", cache->tag->name); - - set_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags); - - /* ask the cache to allocate objects for this cookie and its parent - * chain */ - ret = fscache_alloc_object(cache, cookie); - if (ret < 0) { - up_read(&fscache_addremove_sem); - _leave(" = %d", ret); - return ret; - } - - spin_lock(&cookie->lock); - if (hlist_empty(&cookie->backing_objects)) { - spin_unlock(&cookie->lock); - goto unavailable; - } - - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - fscache_set_store_limit(object, object_size); - - /* initiate the process of looking up all the objects in the chain - * (done by fscache_initialise_object()) */ - fscache_raise_event(object, FSCACHE_OBJECT_EV_NEW_CHILD); - - spin_unlock(&cookie->lock); - - /* we may be required to wait for lookup to complete at this point */ - if (!fscache_defer_lookup) { - wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - TASK_UNINTERRUPTIBLE); - if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags)) - goto unavailable; - } - - up_read(&fscache_addremove_sem); - _leave(" = 0 [deferred]"); - return 0; - -unavailable: - up_read(&fscache_addremove_sem); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} - -/* - * recursively allocate cache object records for a cookie/cache combination - * - caller must be holding the addremove sem - */ -static int fscache_alloc_object(struct fscache_cache *cache, - struct fscache_cookie *cookie) -{ - struct fscache_object *object; - int ret; - - _enter("%s,%x{%s}", cache->tag->name, cookie->debug_id, cookie->def->name); - - spin_lock(&cookie->lock); - hlist_for_each_entry(object, &cookie->backing_objects, - cookie_link) { - if (object->cache == cache) - goto object_already_extant; - } - spin_unlock(&cookie->lock); - - /* ask the cache to allocate an object (we may end up with duplicate - * objects at this stage, but we sort that out later) */ - fscache_stat(&fscache_n_cop_alloc_object); - object = cache->ops->alloc_object(cache, cookie); - fscache_stat_d(&fscache_n_cop_alloc_object); - if (IS_ERR(object)) { - fscache_stat(&fscache_n_object_no_alloc); - ret = PTR_ERR(object); - goto error; - } - - ASSERTCMP(object->cookie, ==, cookie); - fscache_stat(&fscache_n_object_alloc); - - object->debug_id = atomic_inc_return(&fscache_object_debug_id); - - _debug("ALLOC OBJ%x: %s {%lx}", - object->debug_id, cookie->def->name, object->events); - - ret = fscache_alloc_object(cache, cookie->parent); - if (ret < 0) - goto error_put; - - /* only attach if we managed to allocate all we needed, otherwise - * discard the object we just allocated and instead use the one - * attached to the cookie */ - if (fscache_attach_object(cookie, object) < 0) { - fscache_stat(&fscache_n_cop_put_object); - cache->ops->put_object(object, fscache_obj_put_attach_fail); - fscache_stat_d(&fscache_n_cop_put_object); - } - - _leave(" = 0"); - return 0; - -object_already_extant: - ret = -ENOBUFS; - if (fscache_object_is_dying(object) || - fscache_cache_is_broken(object)) { - spin_unlock(&cookie->lock); - goto error; - } - spin_unlock(&cookie->lock); - _leave(" = 0 [found]"); - return 0; - -error_put: - fscache_stat(&fscache_n_cop_put_object); - cache->ops->put_object(object, fscache_obj_put_alloc_fail); - fscache_stat_d(&fscache_n_cop_put_object); -error: - _leave(" = %d", ret); - return ret; -} - -/* - * attach a cache object to a cookie - */ -static int fscache_attach_object(struct fscache_cookie *cookie, - struct fscache_object *object) -{ - struct fscache_object *p; - struct fscache_cache *cache = object->cache; - int ret; - - _enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id); - - ASSERTCMP(object->cookie, ==, cookie); - - spin_lock(&cookie->lock); - - /* there may be multiple initial creations of this object, but we only - * want one */ - ret = -EEXIST; - hlist_for_each_entry(p, &cookie->backing_objects, cookie_link) { - if (p->cache == object->cache) { - if (fscache_object_is_dying(p)) - ret = -ENOBUFS; - goto cant_attach_object; - } - } - - /* pin the parent object */ - spin_lock_nested(&cookie->parent->lock, 1); - hlist_for_each_entry(p, &cookie->parent->backing_objects, - cookie_link) { - if (p->cache == object->cache) { - if (fscache_object_is_dying(p)) { - ret = -ENOBUFS; - spin_unlock(&cookie->parent->lock); - goto cant_attach_object; - } - object->parent = p; - spin_lock(&p->lock); - p->n_children++; - spin_unlock(&p->lock); - break; - } - } - spin_unlock(&cookie->parent->lock); - - /* attach to the cache's object list */ - if (list_empty(&object->cache_link)) { - spin_lock(&cache->object_list_lock); - list_add(&object->cache_link, &cache->object_list); - spin_unlock(&cache->object_list_lock); - } - - /* Attach to the cookie. The object already has a ref on it. */ - hlist_add_head(&object->cookie_link, &cookie->backing_objects); - ret = 0; - -cant_attach_object: - spin_unlock(&cookie->lock); - _leave(" = %d", ret); - return ret; -} - -/* - * Invalidate an object. Callable with spinlocks held. - */ -void __fscache_invalidate(struct fscache_cookie *cookie) -{ - struct fscache_object *object; - - _enter("{%s}", cookie->def->name); - - fscache_stat(&fscache_n_invalidates); - - /* Only permit invalidation of data files. Invalidating an index will - * require the caller to release all its attachments to the tree rooted - * there, and if it's doing that, it may as well just retire the - * cookie. - */ - ASSERTCMP(cookie->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE); - - /* If there's an object, we tell the object state machine to handle the - * invalidation on our behalf, otherwise there's nothing to do. - */ - if (!hlist_empty(&cookie->backing_objects)) { - spin_lock(&cookie->lock); - - if (fscache_cookie_enabled(cookie) && - !hlist_empty(&cookie->backing_objects) && - !test_and_set_bit(FSCACHE_COOKIE_INVALIDATING, - &cookie->flags)) { - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, - cookie_link); - if (fscache_object_is_live(object)) - fscache_raise_event( - object, FSCACHE_OBJECT_EV_INVALIDATE); - } - - spin_unlock(&cookie->lock); - } - - _leave(""); -} -EXPORT_SYMBOL(__fscache_invalidate); - -/* - * Wait for object invalidation to complete. - */ -void __fscache_wait_on_invalidate(struct fscache_cookie *cookie) -{ - _enter("%x", cookie->debug_id); - - wait_on_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING, - TASK_UNINTERRUPTIBLE); - - _leave(""); -} -EXPORT_SYMBOL(__fscache_wait_on_invalidate); - -/* - * update the index entries backing a cookie - */ -void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) -{ - struct fscache_object *object; - - fscache_stat(&fscache_n_updates); - - if (!cookie) { - fscache_stat(&fscache_n_updates_null); - _leave(" [no cookie]"); - return; - } - - _enter("{%s}", cookie->def->name); - - spin_lock(&cookie->lock); - - fscache_update_aux(cookie, aux_data); - - if (fscache_cookie_enabled(cookie)) { - /* update the index entry on disk in each cache backing this - * cookie. - */ - hlist_for_each_entry(object, - &cookie->backing_objects, cookie_link) { - fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE); - } - } - - spin_unlock(&cookie->lock); - _leave(""); -} -EXPORT_SYMBOL(__fscache_update_cookie); - -/* - * Disable a cookie to stop it from accepting new requests from the netfs. - */ -void __fscache_disable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool invalidate) -{ - struct fscache_object *object; - bool awaken = false; - - _enter("%x,%u", cookie->debug_id, invalidate); - - trace_fscache_disable(cookie); - - ASSERTCMP(atomic_read(&cookie->n_active), >, 0); - - if (atomic_read(&cookie->n_children) != 0) { - pr_err("Cookie '%s' still has children\n", - cookie->def->name); - BUG(); - } - - wait_on_bit_lock(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK, - TASK_UNINTERRUPTIBLE); - - fscache_update_aux(cookie, aux_data); - - if (!test_and_clear_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags)) - goto out_unlock_enable; - - /* If the cookie is being invalidated, wait for that to complete first - * so that we can reuse the flag. - */ - __fscache_wait_on_invalidate(cookie); - - /* Dispose of the backing objects */ - set_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags); - - spin_lock(&cookie->lock); - if (!hlist_empty(&cookie->backing_objects)) { - hlist_for_each_entry(object, &cookie->backing_objects, cookie_link) { - if (invalidate) - set_bit(FSCACHE_OBJECT_RETIRED, &object->flags); - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - fscache_raise_event(object, FSCACHE_OBJECT_EV_KILL); - } - } else { - if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) - awaken = true; - } - spin_unlock(&cookie->lock); - if (awaken) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); - - /* Wait for cessation of activity requiring access to the netfs (when - * n_active reaches 0). This makes sure outstanding reads and writes - * have completed. - */ - if (!atomic_dec_and_test(&cookie->n_active)) { - wait_var_event(&cookie->n_active, - !atomic_read(&cookie->n_active)); - } - - /* Make sure any pending writes are cancelled. */ - if (cookie->type != FSCACHE_COOKIE_TYPE_INDEX) - fscache_invalidate_writes(cookie); - - /* Reset the cookie state if it wasn't relinquished */ - if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) { - atomic_inc(&cookie->n_active); - set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - } - -out_unlock_enable: - clear_bit_unlock(FSCACHE_COOKIE_ENABLEMENT_LOCK, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_ENABLEMENT_LOCK); - _leave(""); -} -EXPORT_SYMBOL(__fscache_disable_cookie); - -/* - * release a cookie back to the cache - * - the object will be marked as recyclable on disk if retire is true - * - all dependents of this cookie must have already been unregistered - * (indices/files/pages) - */ -void __fscache_relinquish_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool retire) -{ - fscache_stat(&fscache_n_relinquishes); - if (retire) - fscache_stat(&fscache_n_relinquishes_retire); - - if (!cookie) { - fscache_stat(&fscache_n_relinquishes_null); - _leave(" [no cookie]"); - return; - } - - _enter("%x{%s,%d},%d", - cookie->debug_id, cookie->def->name, - atomic_read(&cookie->n_active), retire); - - trace_fscache_relinquish(cookie, retire); - - /* No further netfs-accessing operations on this cookie permitted */ - if (test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags)) - BUG(); - - __fscache_disable_cookie(cookie, aux_data, retire); - - /* Clear pointers back to the netfs */ - cookie->netfs_data = NULL; - cookie->def = NULL; - BUG_ON(!radix_tree_empty(&cookie->stores)); - - if (cookie->parent) { - ASSERTCMP(refcount_read(&cookie->parent->ref), >, 0); - ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0); - atomic_dec(&cookie->parent->n_children); - } - - /* Dispose of the netfs's link to the cookie */ - fscache_cookie_put(cookie, fscache_cookie_put_relinquish); - - _leave(""); -} -EXPORT_SYMBOL(__fscache_relinquish_cookie); - -/* - * Remove a cookie from the hash table. - */ -static void fscache_unhash_cookie(struct fscache_cookie *cookie) -{ - struct hlist_bl_head *h; - unsigned int bucket; - - bucket = cookie->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1); - h = &fscache_cookie_hash[bucket]; - - hlist_bl_lock(h); - hlist_bl_del(&cookie->hash_link); - hlist_bl_unlock(h); -} - -/* - * Drop a reference to a cookie. - */ -void fscache_cookie_put(struct fscache_cookie *cookie, - enum fscache_cookie_trace where) -{ - struct fscache_cookie *parent; - int ref; - - _enter("%x", cookie->debug_id); - - do { - unsigned int cookie_debug_id = cookie->debug_id; - bool zero = __refcount_dec_and_test(&cookie->ref, &ref); - - trace_fscache_cookie(cookie_debug_id, ref - 1, where); - if (!zero) - return; - - parent = cookie->parent; - fscache_unhash_cookie(cookie); - fscache_free_cookie(cookie); - - cookie = parent; - where = fscache_cookie_put_parent; - } while (cookie); - - _leave(""); -} - -/* - * Get a reference to a cookie. - */ -struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *cookie, - enum fscache_cookie_trace where) -{ - int ref; - - __refcount_inc(&cookie->ref, &ref); - trace_fscache_cookie(cookie->debug_id, ref + 1, where); - return cookie; -} - -/* - * check the consistency between the netfs inode and the backing cache - * - * NOTE: it only serves no-index type - */ -int __fscache_check_consistency(struct fscache_cookie *cookie, - const void *aux_data) -{ - struct fscache_operation *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,", cookie); - - ASSERTCMP(cookie->type, ==, FSCACHE_COOKIE_TYPE_DATAFILE); - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - if (hlist_empty(&cookie->backing_objects)) - return 0; - - op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!op) - return -ENOMEM; - - fscache_operation_init(cookie, op, NULL, NULL, NULL); - op->flags = FSCACHE_OP_MYTHREAD | - (1 << FSCACHE_OP_WAITING) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - trace_fscache_page_op(cookie, NULL, op, fscache_page_op_check_consistency); - - spin_lock(&cookie->lock); - - fscache_update_aux(cookie, aux_data); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto inconsistent; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - if (test_bit(FSCACHE_IOERROR, &object->cache->flags)) - goto inconsistent; - - op->debug_id = atomic_inc_return(&fscache_op_debug_id); - - __fscache_use_cookie(cookie); - if (fscache_submit_op(object, op) < 0) - goto submit_failed; - - /* the work queue now carries its own ref on the object */ - spin_unlock(&cookie->lock); - - ret = fscache_wait_for_operation_activation(object, op, NULL, NULL); - if (ret == 0) { - /* ask the cache to honour the operation */ - ret = object->cache->ops->check_consistency(op); - fscache_op_complete(op, false); - } else if (ret == -ENOBUFS) { - ret = 0; - } - - fscache_put_operation(op); - _leave(" = %d", ret); - return ret; - -submit_failed: - wake_cookie = __fscache_unuse_cookie(cookie); -inconsistent: - spin_unlock(&cookie->lock); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - kfree(op); - _leave(" = -ESTALE"); - return -ESTALE; -} -EXPORT_SYMBOL(__fscache_check_consistency); - -/* - * Generate a list of extant cookies in /proc/fs/fscache/cookies - */ -static int fscache_cookies_seq_show(struct seq_file *m, void *v) -{ - struct fscache_cookie *cookie; - unsigned int keylen = 0, auxlen = 0; - char _type[3], *type; - u8 *p; - - if (v == &fscache_cookies) { - seq_puts(m, - "COOKIE PARENT USAGE CHILD ACT TY FL DEF NETFS_DATA\n" - "======== ======== ===== ===== === == === ================ ==========\n" - ); - return 0; - } - - cookie = list_entry(v, struct fscache_cookie, proc_link); - - switch (cookie->type) { - case 0: - type = "IX"; - break; - case 1: - type = "DT"; - break; - default: - snprintf(_type, sizeof(_type), "%02u", - cookie->type); - type = _type; - break; - } - - seq_printf(m, - "%08x %08x %5u %5u %3u %s %03lx %-16s %px", - cookie->debug_id, - cookie->parent ? cookie->parent->debug_id : 0, - refcount_read(&cookie->ref), - atomic_read(&cookie->n_children), - atomic_read(&cookie->n_active), - type, - cookie->flags, - cookie->def->name, - cookie->netfs_data); - - keylen = cookie->key_len; - auxlen = cookie->aux_len; - - if (keylen > 0 || auxlen > 0) { - seq_puts(m, " "); - p = keylen <= sizeof(cookie->inline_key) ? - cookie->inline_key : cookie->key; - for (; keylen > 0; keylen--) - seq_printf(m, "%02x", *p++); - if (auxlen > 0) { - seq_puts(m, ", "); - p = auxlen <= sizeof(cookie->inline_aux) ? - cookie->inline_aux : cookie->aux; - for (; auxlen > 0; auxlen--) - seq_printf(m, "%02x", *p++); - } - } - - seq_puts(m, "\n"); - return 0; -} - -static void *fscache_cookies_seq_start(struct seq_file *m, loff_t *_pos) - __acquires(fscache_cookies_lock) -{ - read_lock(&fscache_cookies_lock); - return seq_list_start_head(&fscache_cookies, *_pos); -} - -static void *fscache_cookies_seq_next(struct seq_file *m, void *v, loff_t *_pos) -{ - return seq_list_next(v, &fscache_cookies, _pos); -} - -static void fscache_cookies_seq_stop(struct seq_file *m, void *v) - __releases(rcu) -{ - read_unlock(&fscache_cookies_lock); -} - - -const struct seq_operations fscache_cookies_seq_ops = { - .start = fscache_cookies_seq_start, - .next = fscache_cookies_seq_next, - .stop = fscache_cookies_seq_stop, - .show = fscache_cookies_seq_show, -}; diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c deleted file mode 100644 index 0402673c680e..000000000000 --- a/fs/fscache/fsdef.c +++ /dev/null @@ -1,98 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Filesystem index definition - * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL CACHE -#include -#include "internal.h" - -static -enum fscache_checkaux fscache_fsdef_netfs_check_aux(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size); - -/* - * The root index is owned by FS-Cache itself. - * - * When a netfs requests caching facilities, FS-Cache will, if one doesn't - * already exist, create an entry in the root index with the key being the name - * of the netfs ("AFS" for example), and the auxiliary data holding the index - * structure version supplied by the netfs: - * - * FSDEF - * | - * +-----------+ - * | | - * NFS AFS - * [v=1] [v=1] - * - * If an entry with the appropriate name does already exist, the version is - * compared. If the version is different, the entire subtree from that entry - * will be discarded and a new entry created. - * - * The new entry will be an index, and a cookie referring to it will be passed - * to the netfs. This is then the root handle by which the netfs accesses the - * cache. It can create whatever objects it likes in that index, including - * further indices. - */ -static struct fscache_cookie_def fscache_fsdef_index_def = { - .name = ".FS-Cache", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -struct fscache_cookie fscache_fsdef_index = { - .debug_id = 1, - .ref = REFCOUNT_INIT(1), - .n_active = ATOMIC_INIT(1), - .lock = __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock), - .backing_objects = HLIST_HEAD_INIT, - .def = &fscache_fsdef_index_def, - .flags = 1 << FSCACHE_COOKIE_ENABLED, - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; -EXPORT_SYMBOL(fscache_fsdef_index); - -/* - * Definition of an entry in the root index. Each entry is an index, keyed to - * a specific netfs and only applicable to a particular version of the index - * structure used by that netfs. - */ -struct fscache_cookie_def fscache_fsdef_netfs_def = { - .name = "FSDEF.netfs", - .type = FSCACHE_COOKIE_TYPE_INDEX, - .check_aux = fscache_fsdef_netfs_check_aux, -}; - -/* - * check that the index structure version number stored in the auxiliary data - * matches the one the netfs gave us - */ -static enum fscache_checkaux fscache_fsdef_netfs_check_aux( - void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size) -{ - struct fscache_netfs *netfs = cookie_netfs_data; - uint32_t version; - - _enter("{%s},,%hu", netfs->name, datalen); - - if (datalen != sizeof(version)) { - _leave(" = OBSOLETE [dl=%d v=%zu]", datalen, sizeof(version)); - return FSCACHE_CHECKAUX_OBSOLETE; - } - - memcpy(&version, data, sizeof(version)); - if (version != netfs->version) { - _leave(" = OBSOLETE [ver=%x net=%x]", version, netfs->version); - return FSCACHE_CHECKAUX_OBSOLETE; - } - - _leave(" = OKAY"); - return FSCACHE_CHECKAUX_OKAY; -} diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h deleted file mode 100644 index c3e4804b8fcb..000000000000 --- a/fs/fscache/internal.h +++ /dev/null @@ -1,461 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* Internal definitions for FS-Cache - * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -/* - * Lock order, in the order in which multiple locks should be obtained: - * - fscache_addremove_sem - * - cookie->lock - * - cookie->parent->lock - * - cache->object_list_lock - * - object->lock - * - object->parent->lock - * - cookie->stores_lock - * - fscache_thread_lock - * - */ - -#ifdef pr_fmt -#undef pr_fmt -#endif - -#define pr_fmt(fmt) "FS-Cache: " fmt - -#include -#include -#include -#include - -#define FSCACHE_MIN_THREADS 4 -#define FSCACHE_MAX_THREADS 32 - -/* - * cache.c - */ -extern struct list_head fscache_cache_list; -extern struct rw_semaphore fscache_addremove_sem; - -extern struct fscache_cache *fscache_select_cache_for_object( - struct fscache_cookie *); - -/* - * cookie.c - */ -extern struct kmem_cache *fscache_cookie_jar; -extern const struct seq_operations fscache_cookies_seq_ops; - -extern void fscache_free_cookie(struct fscache_cookie *); -extern struct fscache_cookie *fscache_alloc_cookie(struct fscache_cookie *, - const struct fscache_cookie_def *, - const void *, size_t, - const void *, size_t, - void *, loff_t); -extern struct fscache_cookie *fscache_hash_cookie(struct fscache_cookie *); -extern struct fscache_cookie *fscache_cookie_get(struct fscache_cookie *, - enum fscache_cookie_trace); -extern void fscache_cookie_put(struct fscache_cookie *, - enum fscache_cookie_trace); - -static inline void fscache_cookie_see(struct fscache_cookie *cookie, - enum fscache_cookie_trace where) -{ - trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), - where); -} - -/* - * fsdef.c - */ -extern struct fscache_cookie fscache_fsdef_index; -extern struct fscache_cookie_def fscache_fsdef_netfs_def; - -/* - * main.c - */ -extern unsigned fscache_defer_lookup; -extern unsigned fscache_defer_create; -extern unsigned fscache_debug; -extern struct kobject *fscache_root; -extern struct workqueue_struct *fscache_object_wq; -extern struct workqueue_struct *fscache_op_wq; -DECLARE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); - -extern unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n); - -static inline bool fscache_object_congested(void) -{ - return workqueue_congested(WORK_CPU_UNBOUND, fscache_object_wq); -} - -/* - * object.c - */ -extern void fscache_enqueue_object(struct fscache_object *); - -/* - * operation.c - */ -extern int fscache_submit_exclusive_op(struct fscache_object *, - struct fscache_operation *); -extern int fscache_submit_op(struct fscache_object *, - struct fscache_operation *); -extern int fscache_cancel_op(struct fscache_operation *, bool); -extern void fscache_cancel_all_ops(struct fscache_object *); -extern void fscache_abort_object(struct fscache_object *); -extern void fscache_start_operations(struct fscache_object *); -extern void fscache_operation_gc(struct work_struct *); - -/* - * page.c - */ -extern int fscache_wait_for_deferred_lookup(struct fscache_cookie *); -extern int fscache_wait_for_operation_activation(struct fscache_object *, - struct fscache_operation *, - atomic_t *, - atomic_t *); -extern void fscache_invalidate_writes(struct fscache_cookie *); -struct fscache_retrieval *fscache_alloc_retrieval(struct fscache_cookie *cookie, - struct address_space *mapping, - fscache_rw_complete_t end_io_func, - void *context); - -/* - * proc.c - */ -#ifdef CONFIG_PROC_FS -extern int __init fscache_proc_init(void); -extern void fscache_proc_cleanup(void); -#else -#define fscache_proc_init() (0) -#define fscache_proc_cleanup() do {} while (0) -#endif - -/* - * stats.c - */ -#ifdef CONFIG_FSCACHE_STATS -extern atomic_t fscache_n_ops_processed[FSCACHE_MAX_THREADS]; -extern atomic_t fscache_n_objs_processed[FSCACHE_MAX_THREADS]; - -extern atomic_t fscache_n_op_pend; -extern atomic_t fscache_n_op_run; -extern atomic_t fscache_n_op_enqueue; -extern atomic_t fscache_n_op_deferred_release; -extern atomic_t fscache_n_op_initialised; -extern atomic_t fscache_n_op_release; -extern atomic_t fscache_n_op_gc; -extern atomic_t fscache_n_op_cancelled; -extern atomic_t fscache_n_op_rejected; - -extern atomic_t fscache_n_attr_changed; -extern atomic_t fscache_n_attr_changed_ok; -extern atomic_t fscache_n_attr_changed_nobufs; -extern atomic_t fscache_n_attr_changed_nomem; -extern atomic_t fscache_n_attr_changed_calls; - -extern atomic_t fscache_n_allocs; -extern atomic_t fscache_n_allocs_ok; -extern atomic_t fscache_n_allocs_wait; -extern atomic_t fscache_n_allocs_nobufs; -extern atomic_t fscache_n_allocs_intr; -extern atomic_t fscache_n_allocs_object_dead; -extern atomic_t fscache_n_alloc_ops; -extern atomic_t fscache_n_alloc_op_waits; - -extern atomic_t fscache_n_retrievals; -extern atomic_t fscache_n_retrievals_ok; -extern atomic_t fscache_n_retrievals_wait; -extern atomic_t fscache_n_retrievals_nodata; -extern atomic_t fscache_n_retrievals_nobufs; -extern atomic_t fscache_n_retrievals_intr; -extern atomic_t fscache_n_retrievals_nomem; -extern atomic_t fscache_n_retrievals_object_dead; -extern atomic_t fscache_n_retrieval_ops; -extern atomic_t fscache_n_retrieval_op_waits; - -extern atomic_t fscache_n_stores; -extern atomic_t fscache_n_stores_ok; -extern atomic_t fscache_n_stores_again; -extern atomic_t fscache_n_stores_nobufs; -extern atomic_t fscache_n_stores_oom; -extern atomic_t fscache_n_store_ops; -extern atomic_t fscache_n_store_calls; -extern atomic_t fscache_n_store_pages; -extern atomic_t fscache_n_store_radix_deletes; -extern atomic_t fscache_n_store_pages_over_limit; - -extern atomic_t fscache_n_store_vmscan_not_storing; -extern atomic_t fscache_n_store_vmscan_gone; -extern atomic_t fscache_n_store_vmscan_busy; -extern atomic_t fscache_n_store_vmscan_cancelled; -extern atomic_t fscache_n_store_vmscan_wait; - -extern atomic_t fscache_n_marks; -extern atomic_t fscache_n_uncaches; - -extern atomic_t fscache_n_acquires; -extern atomic_t fscache_n_acquires_null; -extern atomic_t fscache_n_acquires_no_cache; -extern atomic_t fscache_n_acquires_ok; -extern atomic_t fscache_n_acquires_nobufs; -extern atomic_t fscache_n_acquires_oom; - -extern atomic_t fscache_n_invalidates; -extern atomic_t fscache_n_invalidates_run; - -extern atomic_t fscache_n_updates; -extern atomic_t fscache_n_updates_null; -extern atomic_t fscache_n_updates_run; - -extern atomic_t fscache_n_relinquishes; -extern atomic_t fscache_n_relinquishes_null; -extern atomic_t fscache_n_relinquishes_waitcrt; -extern atomic_t fscache_n_relinquishes_retire; - -extern atomic_t fscache_n_cookie_index; -extern atomic_t fscache_n_cookie_data; -extern atomic_t fscache_n_cookie_special; - -extern atomic_t fscache_n_object_alloc; -extern atomic_t fscache_n_object_no_alloc; -extern atomic_t fscache_n_object_lookups; -extern atomic_t fscache_n_object_lookups_negative; -extern atomic_t fscache_n_object_lookups_positive; -extern atomic_t fscache_n_object_lookups_timed_out; -extern atomic_t fscache_n_object_created; -extern atomic_t fscache_n_object_avail; -extern atomic_t fscache_n_object_dead; - -extern atomic_t fscache_n_checkaux_none; -extern atomic_t fscache_n_checkaux_okay; -extern atomic_t fscache_n_checkaux_update; -extern atomic_t fscache_n_checkaux_obsolete; - -extern atomic_t fscache_n_cop_alloc_object; -extern atomic_t fscache_n_cop_lookup_object; -extern atomic_t fscache_n_cop_lookup_complete; -extern atomic_t fscache_n_cop_grab_object; -extern atomic_t fscache_n_cop_invalidate_object; -extern atomic_t fscache_n_cop_update_object; -extern atomic_t fscache_n_cop_drop_object; -extern atomic_t fscache_n_cop_put_object; -extern atomic_t fscache_n_cop_sync_cache; -extern atomic_t fscache_n_cop_attr_changed; -extern atomic_t fscache_n_cop_read_or_alloc_page; -extern atomic_t fscache_n_cop_read_or_alloc_pages; -extern atomic_t fscache_n_cop_allocate_page; -extern atomic_t fscache_n_cop_allocate_pages; -extern atomic_t fscache_n_cop_write_page; -extern atomic_t fscache_n_cop_uncache_page; -extern atomic_t fscache_n_cop_dissociate_pages; - -extern atomic_t fscache_n_cache_no_space_reject; -extern atomic_t fscache_n_cache_stale_objects; -extern atomic_t fscache_n_cache_retired_objects; -extern atomic_t fscache_n_cache_culled_objects; - -static inline void fscache_stat(atomic_t *stat) -{ - atomic_inc(stat); -} - -static inline void fscache_stat_d(atomic_t *stat) -{ - atomic_dec(stat); -} - -#define __fscache_stat(stat) (stat) - -int fscache_stats_show(struct seq_file *m, void *v); -#else - -#define __fscache_stat(stat) (NULL) -#define fscache_stat(stat) do {} while (0) -#define fscache_stat_d(stat) do {} while (0) -#endif - -/* - * raise an event on an object - * - if the event is not masked for that object, then the object is - * queued for attention by the thread pool. - */ -static inline void fscache_raise_event(struct fscache_object *object, - unsigned event) -{ - BUG_ON(event >= NR_FSCACHE_OBJECT_EVENTS); -#if 0 - printk("*** fscache_raise_event(OBJ%d{%lx},%x)\n", - object->debug_id, object->event_mask, (1 << event)); -#endif - if (!test_and_set_bit(event, &object->events) && - test_bit(event, &object->event_mask)) - fscache_enqueue_object(object); -} - -/* - * get an extra reference to a netfs retrieval context - */ -static inline -void *fscache_get_context(struct fscache_cookie *cookie, void *context) -{ - if (cookie->def->get_context) - cookie->def->get_context(cookie->netfs_data, context); - return context; -} - -/* - * release a reference to a netfs retrieval context - */ -static inline -void fscache_put_context(struct fscache_cookie *cookie, void *context) -{ - if (cookie->def->put_context) - cookie->def->put_context(cookie->netfs_data, context); -} - -/* - * Update the auxiliary data on a cookie. - */ -static inline -void fscache_update_aux(struct fscache_cookie *cookie, const void *aux_data) -{ - void *p; - - if (!aux_data) - return; - if (cookie->aux_len <= sizeof(cookie->inline_aux)) - p = cookie->inline_aux; - else - p = cookie->aux; - - if (memcmp(p, aux_data, cookie->aux_len) != 0) { - memcpy(p, aux_data, cookie->aux_len); - set_bit(FSCACHE_COOKIE_AUX_UPDATED, &cookie->flags); - } -} - -/*****************************************************************************/ -/* - * debug tracing - */ -#define dbgprintk(FMT, ...) \ - printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) - -#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__) -#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__) -#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__) - -#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__) - -#ifdef __KDEBUG -#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__) -#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__) -#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__) - -#elif defined(CONFIG_FSCACHE_DEBUG) -#define _enter(FMT, ...) \ -do { \ - if (__do_kdebug(ENTER)) \ - kenter(FMT, ##__VA_ARGS__); \ -} while (0) - -#define _leave(FMT, ...) \ -do { \ - if (__do_kdebug(LEAVE)) \ - kleave(FMT, ##__VA_ARGS__); \ -} while (0) - -#define _debug(FMT, ...) \ -do { \ - if (__do_kdebug(DEBUG)) \ - kdebug(FMT, ##__VA_ARGS__); \ -} while (0) - -#else -#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__) -#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__) -#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__) -#endif - -/* - * determine whether a particular optional debugging point should be logged - * - we need to go through three steps to persuade cpp to correctly join the - * shorthand in FSCACHE_DEBUG_LEVEL with its prefix - */ -#define ____do_kdebug(LEVEL, POINT) \ - unlikely((fscache_debug & \ - (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3)))) -#define ___do_kdebug(LEVEL, POINT) \ - ____do_kdebug(LEVEL, POINT) -#define __do_kdebug(POINT) \ - ___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT) - -#define FSCACHE_DEBUG_CACHE 0 -#define FSCACHE_DEBUG_COOKIE 1 -#define FSCACHE_DEBUG_PAGE 2 -#define FSCACHE_DEBUG_OPERATION 3 - -#define FSCACHE_POINT_ENTER 1 -#define FSCACHE_POINT_LEAVE 2 -#define FSCACHE_POINT_DEBUG 4 - -#ifndef FSCACHE_DEBUG_LEVEL -#define FSCACHE_DEBUG_LEVEL CACHE -#endif - -/* - * assertions - */ -#if 1 /* defined(__KDEBUGALL) */ - -#define ASSERT(X) \ -do { \ - if (unlikely(!(X))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - BUG(); \ - } \ -} while (0) - -#define ASSERTCMP(X, OP, Y) \ -do { \ - if (unlikely(!((X) OP (Y)))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - pr_err("%lx " #OP " %lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - BUG(); \ - } \ -} while (0) - -#define ASSERTIF(C, X) \ -do { \ - if (unlikely((C) && !(X))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - BUG(); \ - } \ -} while (0) - -#define ASSERTIFCMP(C, X, OP, Y) \ -do { \ - if (unlikely((C) && !((X) OP (Y)))) { \ - pr_err("\n"); \ - pr_err("Assertion failed\n"); \ - pr_err("%lx " #OP " %lx is false\n", \ - (unsigned long)(X), (unsigned long)(Y)); \ - BUG(); \ - } \ -} while (0) - -#else - -#define ASSERT(X) do {} while (0) -#define ASSERTCMP(X, OP, Y) do {} while (0) -#define ASSERTIF(C, X) do {} while (0) -#define ASSERTIFCMP(C, X, OP, Y) do {} while (0) - -#endif /* assert or not */ diff --git a/fs/fscache/io.c b/fs/fscache/io.c deleted file mode 100644 index 8ecc1141802f..000000000000 --- a/fs/fscache/io.c +++ /dev/null @@ -1,116 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Cache data I/O routines - * - * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL PAGE -#include -#define FSCACHE_USE_NEW_IO_API -#include -#include -#include -#include "internal.h" - -/* - * Start a cache read operation. - * - we return: - * -ENOMEM - out of memory, some pages may be being read - * -ERESTARTSYS - interrupted, some pages may be being read - * -ENOBUFS - no backing object or space available in which to cache any - * pages not being read - * -ENODATA - no data available in the backing object for some or all of - * the pages - * 0 - dispatched a read on all pages - */ -int __fscache_begin_read_operation(struct netfs_read_request *rreq, - struct fscache_cookie *cookie) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("rr=%08x", rreq->debug_id); - - fscache_stat(&fscache_n_retrievals); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, NULL, NULL, NULL); - if (!op) - return -ENOMEM; - trace_fscache_page_op(cookie, NULL, &op->op, fscache_page_op_retr_multi); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - atomic_inc(&object->n_reads); - __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); - - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_retrieval_ops); - - /* we wait for the operation to become active, and then process it - * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - ret = object->cache->ops->begin_read_operation(rreq, op); - -error: - if (ret == -ENOMEM) - fscache_stat(&fscache_n_retrievals_nomem); - else if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_retrievals_intr); - else if (ret == -ENODATA) - fscache_stat(&fscache_n_retrievals_nodata); - else if (ret < 0) - fscache_stat(&fscache_n_retrievals_nobufs); - else - fscache_stat(&fscache_n_retrievals_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - atomic_dec(&object->n_reads); - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - fscache_put_retrieval(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); -nobufs: - fscache_stat(&fscache_n_retrievals_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_begin_read_operation); diff --git a/fs/fscache/main.c b/fs/fscache/main.c deleted file mode 100644 index 4207f98e405f..000000000000 --- a/fs/fscache/main.c +++ /dev/null @@ -1,230 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* General filesystem local caching manager - * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL CACHE -#include -#include -#include -#include -#include -#include -#define CREATE_TRACE_POINTS -#include "internal.h" - -MODULE_DESCRIPTION("FS Cache Manager"); -MODULE_AUTHOR("Red Hat, Inc."); -MODULE_LICENSE("GPL"); - -unsigned fscache_defer_lookup = 1; -module_param_named(defer_lookup, fscache_defer_lookup, uint, - S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(fscache_defer_lookup, - "Defer cookie lookup to background thread"); - -unsigned fscache_defer_create = 1; -module_param_named(defer_create, fscache_defer_create, uint, - S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(fscache_defer_create, - "Defer cookie creation to background thread"); - -unsigned fscache_debug; -module_param_named(debug, fscache_debug, uint, - S_IWUSR | S_IRUGO); -MODULE_PARM_DESC(fscache_debug, - "FS-Cache debugging mask"); - -struct kobject *fscache_root; -struct workqueue_struct *fscache_object_wq; -struct workqueue_struct *fscache_op_wq; - -DEFINE_PER_CPU(wait_queue_head_t, fscache_object_cong_wait); - -/* these values serve as lower bounds, will be adjusted in fscache_init() */ -static unsigned fscache_object_max_active = 4; -static unsigned fscache_op_max_active = 2; - -#ifdef CONFIG_SYSCTL -static struct ctl_table_header *fscache_sysctl_header; - -static int fscache_max_active_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - struct workqueue_struct **wqp = table->extra1; - unsigned int *datap = table->data; - int ret; - - ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret == 0) - workqueue_set_max_active(*wqp, *datap); - return ret; -} - -static struct ctl_table fscache_sysctls[] = { - { - .procname = "object_max_active", - .data = &fscache_object_max_active, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = fscache_max_active_sysctl, - .extra1 = &fscache_object_wq, - }, - { - .procname = "operation_max_active", - .data = &fscache_op_max_active, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = fscache_max_active_sysctl, - .extra1 = &fscache_op_wq, - }, - {} -}; - -static struct ctl_table fscache_sysctls_root[] = { - { - .procname = "fscache", - .mode = 0555, - .child = fscache_sysctls, - }, - {} -}; -#endif - -/* - * Mixing scores (in bits) for (7,20): - * Input delta: 1-bit 2-bit - * 1 round: 330.3 9201.6 - * 2 rounds: 1246.4 25475.4 - * 3 rounds: 1907.1 31295.1 - * 4 rounds: 2042.3 31718.6 - * Perfect: 2048 31744 - * (32*64) (32*31/2 * 64) - */ -#define HASH_MIX(x, y, a) \ - ( x ^= (a), \ - y ^= x, x = rol32(x, 7),\ - x += y, y = rol32(y,20),\ - y *= 9 ) - -static inline unsigned int fold_hash(unsigned long x, unsigned long y) -{ - /* Use arch-optimized multiply if one exists */ - return __hash_32(y ^ __hash_32(x)); -} - -/* - * Generate a hash. This is derived from full_name_hash(), but we want to be - * sure it is arch independent and that it doesn't change as bits of the - * computed hash value might appear on disk. The caller also guarantees that - * the hashed data will be a series of aligned 32-bit words. - */ -unsigned int fscache_hash(unsigned int salt, unsigned int *data, unsigned int n) -{ - unsigned int a, x = 0, y = salt; - - for (; n; n--) { - a = *data++; - HASH_MIX(x, y, a); - } - return fold_hash(x, y); -} - -/* - * initialise the fs caching module - */ -static int __init fscache_init(void) -{ - unsigned int nr_cpus = num_possible_cpus(); - unsigned int cpu; - int ret; - - fscache_object_max_active = - clamp_val(nr_cpus, - fscache_object_max_active, WQ_UNBOUND_MAX_ACTIVE); - - ret = -ENOMEM; - fscache_object_wq = alloc_workqueue("fscache_object", WQ_UNBOUND, - fscache_object_max_active); - if (!fscache_object_wq) - goto error_object_wq; - - fscache_op_max_active = - clamp_val(fscache_object_max_active / 2, - fscache_op_max_active, WQ_UNBOUND_MAX_ACTIVE); - - ret = -ENOMEM; - fscache_op_wq = alloc_workqueue("fscache_operation", WQ_UNBOUND, - fscache_op_max_active); - if (!fscache_op_wq) - goto error_op_wq; - - for_each_possible_cpu(cpu) - init_waitqueue_head(&per_cpu(fscache_object_cong_wait, cpu)); - - ret = fscache_proc_init(); - if (ret < 0) - goto error_proc; - -#ifdef CONFIG_SYSCTL - ret = -ENOMEM; - fscache_sysctl_header = register_sysctl_table(fscache_sysctls_root); - if (!fscache_sysctl_header) - goto error_sysctl; -#endif - - fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar", - sizeof(struct fscache_cookie), - 0, 0, NULL); - if (!fscache_cookie_jar) { - pr_notice("Failed to allocate a cookie jar\n"); - ret = -ENOMEM; - goto error_cookie_jar; - } - - fscache_root = kobject_create_and_add("fscache", kernel_kobj); - if (!fscache_root) - goto error_kobj; - - pr_notice("Loaded\n"); - return 0; - -error_kobj: - kmem_cache_destroy(fscache_cookie_jar); -error_cookie_jar: -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(fscache_sysctl_header); -error_sysctl: -#endif - fscache_proc_cleanup(); -error_proc: - destroy_workqueue(fscache_op_wq); -error_op_wq: - destroy_workqueue(fscache_object_wq); -error_object_wq: - return ret; -} - -fs_initcall(fscache_init); - -/* - * clean up on module removal - */ -static void __exit fscache_exit(void) -{ - _enter(""); - - kobject_put(fscache_root); - kmem_cache_destroy(fscache_cookie_jar); -#ifdef CONFIG_SYSCTL - unregister_sysctl_table(fscache_sysctl_header); -#endif - fscache_proc_cleanup(); - destroy_workqueue(fscache_op_wq); - destroy_workqueue(fscache_object_wq); - pr_notice("Unloaded\n"); -} - -module_exit(fscache_exit); diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c deleted file mode 100644 index d6bdb7b5e723..000000000000 --- a/fs/fscache/netfs.c +++ /dev/null @@ -1,74 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache netfs (client) registration - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL COOKIE -#include -#include -#include "internal.h" - -/* - * register a network filesystem for caching - */ -int __fscache_register_netfs(struct fscache_netfs *netfs) -{ - struct fscache_cookie *candidate, *cookie; - - _enter("{%s}", netfs->name); - - /* allocate a cookie for the primary index */ - candidate = fscache_alloc_cookie(&fscache_fsdef_index, - &fscache_fsdef_netfs_def, - netfs->name, strlen(netfs->name), - &netfs->version, sizeof(netfs->version), - netfs, 0); - if (!candidate) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - candidate->flags = 1 << FSCACHE_COOKIE_ENABLED; - - /* check the netfs type is not already present */ - cookie = fscache_hash_cookie(candidate); - if (!cookie) - goto already_registered; - if (cookie != candidate) { - trace_fscache_cookie(candidate->debug_id, 1, fscache_cookie_discard); - fscache_free_cookie(candidate); - } - - fscache_cookie_get(cookie->parent, fscache_cookie_get_register_netfs); - atomic_inc(&cookie->parent->n_children); - - netfs->primary_index = cookie; - - pr_notice("Netfs '%s' registered for caching\n", netfs->name); - trace_fscache_netfs(netfs); - _leave(" = 0"); - return 0; - -already_registered: - fscache_cookie_put(candidate, fscache_cookie_put_dup_netfs); - _leave(" = -EEXIST"); - return -EEXIST; -} -EXPORT_SYMBOL(__fscache_register_netfs); - -/* - * unregister a network filesystem from the cache - * - all cookies must have been released first - */ -void __fscache_unregister_netfs(struct fscache_netfs *netfs) -{ - _enter("{%s.%u}", netfs->name, netfs->version); - - fscache_relinquish_cookie(netfs->primary_index, NULL, false); - pr_notice("Netfs '%s' unregistered from caching\n", netfs->name); - - _leave(""); -} -EXPORT_SYMBOL(__fscache_unregister_netfs); diff --git a/fs/fscache/object.c b/fs/fscache/object.c deleted file mode 100644 index 6a675652129b..000000000000 --- a/fs/fscache/object.c +++ /dev/null @@ -1,1125 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache object state machine handler - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * See Documentation/filesystems/caching/object.rst for a description of the - * object state machine and the in-kernel representations. - */ - -#define FSCACHE_DEBUG_LEVEL COOKIE -#include -#include -#include -#include "internal.h" - -static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *, int); -static const struct fscache_state *fscache_kill_dependents(struct fscache_object *, int); -static const struct fscache_state *fscache_drop_object(struct fscache_object *, int); -static const struct fscache_state *fscache_initialise_object(struct fscache_object *, int); -static const struct fscache_state *fscache_invalidate_object(struct fscache_object *, int); -static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *, int); -static const struct fscache_state *fscache_kill_object(struct fscache_object *, int); -static const struct fscache_state *fscache_lookup_failure(struct fscache_object *, int); -static const struct fscache_state *fscache_look_up_object(struct fscache_object *, int); -static const struct fscache_state *fscache_object_available(struct fscache_object *, int); -static const struct fscache_state *fscache_parent_ready(struct fscache_object *, int); -static const struct fscache_state *fscache_update_object(struct fscache_object *, int); -static const struct fscache_state *fscache_object_dead(struct fscache_object *, int); - -#define __STATE_NAME(n) fscache_osm_##n -#define STATE(n) (&__STATE_NAME(n)) - -/* - * Define a work state. Work states are execution states. No event processing - * is performed by them. The function attached to a work state returns a - * pointer indicating the next state to which the state machine should - * transition. Returning NO_TRANSIT repeats the current state, but goes back - * to the scheduler first. - */ -#define WORK_STATE(n, sn, f) \ - const struct fscache_state __STATE_NAME(n) = { \ - .name = #n, \ - .short_name = sn, \ - .work = f \ - } - -/* - * Returns from work states. - */ -#define transit_to(state) ({ prefetch(&STATE(state)->work); STATE(state); }) - -#define NO_TRANSIT ((struct fscache_state *)NULL) - -/* - * Define a wait state. Wait states are event processing states. No execution - * is performed by them. Wait states are just tables of "if event X occurs, - * clear it and transition to state Y". The dispatcher returns to the - * scheduler if none of the events in which the wait state has an interest are - * currently pending. - */ -#define WAIT_STATE(n, sn, ...) \ - const struct fscache_state __STATE_NAME(n) = { \ - .name = #n, \ - .short_name = sn, \ - .work = NULL, \ - .transitions = { __VA_ARGS__, { 0, NULL } } \ - } - -#define TRANSIT_TO(state, emask) \ - { .events = (emask), .transit_to = STATE(state) } - -/* - * The object state machine. - */ -static WORK_STATE(INIT_OBJECT, "INIT", fscache_initialise_object); -static WORK_STATE(PARENT_READY, "PRDY", fscache_parent_ready); -static WORK_STATE(ABORT_INIT, "ABRT", fscache_abort_initialisation); -static WORK_STATE(LOOK_UP_OBJECT, "LOOK", fscache_look_up_object); -static WORK_STATE(OBJECT_AVAILABLE, "AVBL", fscache_object_available); -static WORK_STATE(JUMPSTART_DEPS, "JUMP", fscache_jumpstart_dependents); - -static WORK_STATE(INVALIDATE_OBJECT, "INVL", fscache_invalidate_object); -static WORK_STATE(UPDATE_OBJECT, "UPDT", fscache_update_object); - -static WORK_STATE(LOOKUP_FAILURE, "LCFL", fscache_lookup_failure); -static WORK_STATE(KILL_OBJECT, "KILL", fscache_kill_object); -static WORK_STATE(KILL_DEPENDENTS, "KDEP", fscache_kill_dependents); -static WORK_STATE(DROP_OBJECT, "DROP", fscache_drop_object); -static WORK_STATE(OBJECT_DEAD, "DEAD", fscache_object_dead); - -static WAIT_STATE(WAIT_FOR_INIT, "?INI", - TRANSIT_TO(INIT_OBJECT, 1 << FSCACHE_OBJECT_EV_NEW_CHILD)); - -static WAIT_STATE(WAIT_FOR_PARENT, "?PRN", - TRANSIT_TO(PARENT_READY, 1 << FSCACHE_OBJECT_EV_PARENT_READY)); - -static WAIT_STATE(WAIT_FOR_CMD, "?CMD", - TRANSIT_TO(INVALIDATE_OBJECT, 1 << FSCACHE_OBJECT_EV_INVALIDATE), - TRANSIT_TO(UPDATE_OBJECT, 1 << FSCACHE_OBJECT_EV_UPDATE), - TRANSIT_TO(JUMPSTART_DEPS, 1 << FSCACHE_OBJECT_EV_NEW_CHILD)); - -static WAIT_STATE(WAIT_FOR_CLEARANCE, "?CLR", - TRANSIT_TO(KILL_OBJECT, 1 << FSCACHE_OBJECT_EV_CLEARED)); - -/* - * Out-of-band event transition tables. These are for handling unexpected - * events, such as an I/O error. If an OOB event occurs, the state machine - * clears and disables the event and forces a transition to the nominated work - * state (acurrently executing work states will complete first). - * - * In such a situation, object->state remembers the state the machine should - * have been in/gone to and returning NO_TRANSIT returns to that. - */ -static const struct fscache_transition fscache_osm_init_oob[] = { - TRANSIT_TO(ABORT_INIT, - (1 << FSCACHE_OBJECT_EV_ERROR) | - (1 << FSCACHE_OBJECT_EV_KILL)), - { 0, NULL } -}; - -static const struct fscache_transition fscache_osm_lookup_oob[] = { - TRANSIT_TO(LOOKUP_FAILURE, - (1 << FSCACHE_OBJECT_EV_ERROR) | - (1 << FSCACHE_OBJECT_EV_KILL)), - { 0, NULL } -}; - -static const struct fscache_transition fscache_osm_run_oob[] = { - TRANSIT_TO(KILL_OBJECT, - (1 << FSCACHE_OBJECT_EV_ERROR) | - (1 << FSCACHE_OBJECT_EV_KILL)), - { 0, NULL } -}; - -static int fscache_get_object(struct fscache_object *, - enum fscache_obj_ref_trace); -static void fscache_put_object(struct fscache_object *, - enum fscache_obj_ref_trace); -static bool fscache_enqueue_dependents(struct fscache_object *, int); -static void fscache_dequeue_object(struct fscache_object *); -static void fscache_update_aux_data(struct fscache_object *); - -/* - * we need to notify the parent when an op completes that we had outstanding - * upon it - */ -static inline void fscache_done_parent_op(struct fscache_object *object) -{ - struct fscache_object *parent = object->parent; - - _enter("OBJ%x {OBJ%x,%x}", - object->debug_id, parent->debug_id, parent->n_ops); - - spin_lock_nested(&parent->lock, 1); - parent->n_obj_ops--; - parent->n_ops--; - if (parent->n_ops == 0) - fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED); - spin_unlock(&parent->lock); -} - -/* - * Object state machine dispatcher. - */ -static void fscache_object_sm_dispatcher(struct fscache_object *object) -{ - const struct fscache_transition *t; - const struct fscache_state *state, *new_state; - unsigned long events, event_mask; - bool oob; - int event = -1; - - ASSERT(object != NULL); - - _enter("{OBJ%x,%s,%lx}", - object->debug_id, object->state->name, object->events); - - event_mask = object->event_mask; -restart: - object->event_mask = 0; /* Mask normal event handling */ - state = object->state; -restart_masked: - events = object->events; - - /* Handle any out-of-band events (typically an error) */ - if (events & object->oob_event_mask) { - _debug("{OBJ%x} oob %lx", - object->debug_id, events & object->oob_event_mask); - oob = true; - for (t = object->oob_table; t->events; t++) { - if (events & t->events) { - state = t->transit_to; - ASSERT(state->work != NULL); - event = fls(events & t->events) - 1; - __clear_bit(event, &object->oob_event_mask); - clear_bit(event, &object->events); - goto execute_work_state; - } - } - } - oob = false; - - /* Wait states are just transition tables */ - if (!state->work) { - if (events & event_mask) { - for (t = state->transitions; t->events; t++) { - if (events & t->events) { - new_state = t->transit_to; - event = fls(events & t->events) - 1; - trace_fscache_osm(object, state, - true, false, event); - clear_bit(event, &object->events); - _debug("{OBJ%x} ev %d: %s -> %s", - object->debug_id, event, - state->name, new_state->name); - object->state = state = new_state; - goto execute_work_state; - } - } - - /* The event mask didn't include all the tabled bits */ - BUG(); - } - /* Randomly woke up */ - goto unmask_events; - } - -execute_work_state: - _debug("{OBJ%x} exec %s", object->debug_id, state->name); - - trace_fscache_osm(object, state, false, oob, event); - new_state = state->work(object, event); - event = -1; - if (new_state == NO_TRANSIT) { - _debug("{OBJ%x} %s notrans", object->debug_id, state->name); - if (unlikely(state == STATE(OBJECT_DEAD))) { - _leave(" [dead]"); - return; - } - fscache_enqueue_object(object); - event_mask = object->oob_event_mask; - goto unmask_events; - } - - _debug("{OBJ%x} %s -> %s", - object->debug_id, state->name, new_state->name); - object->state = state = new_state; - - if (state->work) { - if (unlikely(state == STATE(OBJECT_DEAD))) { - _leave(" [dead]"); - return; - } - goto restart_masked; - } - - /* Transited to wait state */ - event_mask = object->oob_event_mask; - for (t = state->transitions; t->events; t++) - event_mask |= t->events; - -unmask_events: - object->event_mask = event_mask; - smp_mb(); - events = object->events; - if (events & event_mask) - goto restart; - _leave(" [msk %lx]", event_mask); -} - -/* - * execute an object - */ -static void fscache_object_work_func(struct work_struct *work) -{ - struct fscache_object *object = - container_of(work, struct fscache_object, work); - - _enter("{OBJ%x}", object->debug_id); - - fscache_object_sm_dispatcher(object); - fscache_put_object(object, fscache_obj_put_work); -} - -/** - * fscache_object_init - Initialise a cache object description - * @object: Object description - * @cookie: Cookie object will be attached to - * @cache: Cache in which backing object will be found - * - * Initialise a cache object description to its basic values. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -void fscache_object_init(struct fscache_object *object, - struct fscache_cookie *cookie, - struct fscache_cache *cache) -{ - const struct fscache_transition *t; - - atomic_inc(&cache->object_count); - - object->state = STATE(WAIT_FOR_INIT); - object->oob_table = fscache_osm_init_oob; - object->flags = 1 << FSCACHE_OBJECT_IS_LIVE; - spin_lock_init(&object->lock); - INIT_LIST_HEAD(&object->cache_link); - INIT_HLIST_NODE(&object->cookie_link); - INIT_WORK(&object->work, fscache_object_work_func); - INIT_LIST_HEAD(&object->dependents); - INIT_LIST_HEAD(&object->dep_link); - INIT_LIST_HEAD(&object->pending_ops); - object->n_children = 0; - object->n_ops = object->n_in_progress = object->n_exclusive = 0; - object->events = 0; - object->store_limit = 0; - object->store_limit_l = 0; - object->cache = cache; - object->cookie = cookie; - fscache_cookie_get(cookie, fscache_cookie_get_attach_object); - object->parent = NULL; -#ifdef CONFIG_FSCACHE_OBJECT_LIST - RB_CLEAR_NODE(&object->objlist_link); -#endif - - object->oob_event_mask = 0; - for (t = object->oob_table; t->events; t++) - object->oob_event_mask |= t->events; - object->event_mask = object->oob_event_mask; - for (t = object->state->transitions; t->events; t++) - object->event_mask |= t->events; -} -EXPORT_SYMBOL(fscache_object_init); - -/* - * Mark the object as no longer being live, making sure that we synchronise - * against op submission. - */ -static inline void fscache_mark_object_dead(struct fscache_object *object) -{ - spin_lock(&object->lock); - clear_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); - spin_unlock(&object->lock); -} - -/* - * Abort object initialisation before we start it. - */ -static const struct fscache_state *fscache_abort_initialisation(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_event_mask = 0; - fscache_dequeue_object(object); - return transit_to(KILL_OBJECT); -} - -/* - * initialise an object - * - check the specified object's parent to see if we can make use of it - * immediately to do a creation - * - we may need to start the process of creating a parent and we need to wait - * for the parent's lookup and creation to complete if it's not there yet - */ -static const struct fscache_state *fscache_initialise_object(struct fscache_object *object, - int event) -{ - struct fscache_object *parent; - bool success; - - _enter("{OBJ%x},%d", object->debug_id, event); - - ASSERT(list_empty(&object->dep_link)); - - parent = object->parent; - if (!parent) { - _leave(" [no parent]"); - return transit_to(DROP_OBJECT); - } - - _debug("parent: %s of:%lx", parent->state->name, parent->flags); - - if (fscache_object_is_dying(parent)) { - _leave(" [bad parent]"); - return transit_to(DROP_OBJECT); - } - - if (fscache_object_is_available(parent)) { - _leave(" [ready]"); - return transit_to(PARENT_READY); - } - - _debug("wait"); - - spin_lock(&parent->lock); - fscache_stat(&fscache_n_cop_grab_object); - success = false; - if (fscache_object_is_live(parent) && - object->cache->ops->grab_object(object, fscache_obj_get_add_to_deps)) { - list_add(&object->dep_link, &parent->dependents); - success = true; - } - fscache_stat_d(&fscache_n_cop_grab_object); - spin_unlock(&parent->lock); - if (!success) { - _leave(" [grab failed]"); - return transit_to(DROP_OBJECT); - } - - /* fscache_acquire_non_index_cookie() uses this - * to wake the chain up */ - fscache_raise_event(parent, FSCACHE_OBJECT_EV_NEW_CHILD); - _leave(" [wait]"); - return transit_to(WAIT_FOR_PARENT); -} - -/* - * Once the parent object is ready, we should kick off our lookup op. - */ -static const struct fscache_state *fscache_parent_ready(struct fscache_object *object, - int event) -{ - struct fscache_object *parent = object->parent; - - _enter("{OBJ%x},%d", object->debug_id, event); - - ASSERT(parent != NULL); - - spin_lock(&parent->lock); - parent->n_ops++; - parent->n_obj_ops++; - spin_unlock(&parent->lock); - - _leave(""); - return transit_to(LOOK_UP_OBJECT); -} - -/* - * look an object up in the cache from which it was allocated - * - we hold an "access lock" on the parent object, so the parent object cannot - * be withdrawn by either party till we've finished - */ -static const struct fscache_state *fscache_look_up_object(struct fscache_object *object, - int event) -{ - struct fscache_cookie *cookie = object->cookie; - struct fscache_object *parent = object->parent; - int ret; - - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_table = fscache_osm_lookup_oob; - - ASSERT(parent != NULL); - ASSERTCMP(parent->n_ops, >, 0); - ASSERTCMP(parent->n_obj_ops, >, 0); - - /* make sure the parent is still available */ - ASSERT(fscache_object_is_available(parent)); - - if (fscache_object_is_dying(parent) || - test_bit(FSCACHE_IOERROR, &object->cache->flags) || - !fscache_use_cookie(object)) { - _leave(" [unavailable]"); - return transit_to(LOOKUP_FAILURE); - } - - _debug("LOOKUP \"%s\" in \"%s\"", - cookie->def->name, object->cache->tag->name); - - fscache_stat(&fscache_n_object_lookups); - fscache_stat(&fscache_n_cop_lookup_object); - ret = object->cache->ops->lookup_object(object); - fscache_stat_d(&fscache_n_cop_lookup_object); - - fscache_unuse_cookie(object); - - if (ret == -ETIMEDOUT) { - /* probably stuck behind another object, so move this one to - * the back of the queue */ - fscache_stat(&fscache_n_object_lookups_timed_out); - _leave(" [timeout]"); - return NO_TRANSIT; - } - - if (ret < 0) { - _leave(" [error]"); - return transit_to(LOOKUP_FAILURE); - } - - _leave(" [ok]"); - return transit_to(OBJECT_AVAILABLE); -} - -/** - * fscache_object_lookup_negative - Note negative cookie lookup - * @object: Object pointing to cookie to mark - * - * Note negative lookup, permitting those waiting to read data from an already - * existing backing object to continue as there's no data for them to read. - */ -void fscache_object_lookup_negative(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - - _enter("{OBJ%x,%s}", object->debug_id, object->state->name); - - if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) { - fscache_stat(&fscache_n_object_lookups_negative); - - /* Allow write requests to begin stacking up and read requests to begin - * returning ENODATA. - */ - set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - - clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - } - _leave(""); -} -EXPORT_SYMBOL(fscache_object_lookup_negative); - -/** - * fscache_obtained_object - Note successful object lookup or creation - * @object: Object pointing to cookie to mark - * - * Note successful lookup and/or creation, permitting those waiting to write - * data to a backing object to continue. - * - * Note that after calling this, an object's cookie may be relinquished by the - * netfs, and so must be accessed with object lock held. - */ -void fscache_obtained_object(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - - _enter("{OBJ%x,%s}", object->debug_id, object->state->name); - - /* if we were still looking up, then we must have a positive lookup - * result, in which case there may be data available */ - if (!test_and_set_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)) { - fscache_stat(&fscache_n_object_lookups_positive); - - /* We do (presumably) have data */ - clear_bit_unlock(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - clear_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - - /* Allow write requests to begin stacking up and read requests - * to begin shovelling data. - */ - clear_bit_unlock(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags); - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - } else { - fscache_stat(&fscache_n_object_created); - } - - set_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); - _leave(""); -} -EXPORT_SYMBOL(fscache_obtained_object); - -/* - * handle an object that has just become available - */ -static const struct fscache_state *fscache_object_available(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_table = fscache_osm_run_oob; - - spin_lock(&object->lock); - - fscache_done_parent_op(object); - if (object->n_in_progress == 0) { - if (object->n_ops > 0) { - ASSERTCMP(object->n_ops, >=, object->n_obj_ops); - fscache_start_operations(object); - } else { - ASSERT(list_empty(&object->pending_ops)); - } - } - spin_unlock(&object->lock); - - fscache_stat(&fscache_n_cop_lookup_complete); - object->cache->ops->lookup_complete(object); - fscache_stat_d(&fscache_n_cop_lookup_complete); - - fscache_stat(&fscache_n_object_avail); - - _leave(""); - return transit_to(JUMPSTART_DEPS); -} - -/* - * Wake up this object's dependent objects now that we've become available. - */ -static const struct fscache_state *fscache_jumpstart_dependents(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_PARENT_READY)) - return NO_TRANSIT; /* Not finished; requeue */ - return transit_to(WAIT_FOR_CMD); -} - -/* - * Handle lookup or creation failute. - */ -static const struct fscache_state *fscache_lookup_failure(struct fscache_object *object, - int event) -{ - struct fscache_cookie *cookie; - - _enter("{OBJ%x},%d", object->debug_id, event); - - object->oob_event_mask = 0; - - fscache_stat(&fscache_n_cop_lookup_complete); - object->cache->ops->lookup_complete(object); - fscache_stat_d(&fscache_n_cop_lookup_complete); - - set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags); - - cookie = object->cookie; - set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags); - if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - - fscache_done_parent_op(object); - return transit_to(KILL_OBJECT); -} - -/* - * Wait for completion of all active operations on this object and the death of - * all child objects of this object. - */ -static const struct fscache_state *fscache_kill_object(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x,%d,%d},%d", - object->debug_id, object->n_ops, object->n_children, event); - - fscache_mark_object_dead(object); - object->oob_event_mask = 0; - - if (test_bit(FSCACHE_OBJECT_RETIRED, &object->flags)) { - /* Reject any new read/write ops and abort any that are pending. */ - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - fscache_cancel_all_ops(object); - } - - if (list_empty(&object->dependents) && - object->n_ops == 0 && - object->n_children == 0) - return transit_to(DROP_OBJECT); - - if (object->n_in_progress == 0) { - spin_lock(&object->lock); - if (object->n_ops > 0 && object->n_in_progress == 0) - fscache_start_operations(object); - spin_unlock(&object->lock); - } - - if (!list_empty(&object->dependents)) - return transit_to(KILL_DEPENDENTS); - - return transit_to(WAIT_FOR_CLEARANCE); -} - -/* - * Kill dependent objects. - */ -static const struct fscache_state *fscache_kill_dependents(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - if (!fscache_enqueue_dependents(object, FSCACHE_OBJECT_EV_KILL)) - return NO_TRANSIT; /* Not finished */ - return transit_to(WAIT_FOR_CLEARANCE); -} - -/* - * Drop an object's attachments - */ -static const struct fscache_state *fscache_drop_object(struct fscache_object *object, - int event) -{ - struct fscache_object *parent = object->parent; - struct fscache_cookie *cookie = object->cookie; - struct fscache_cache *cache = object->cache; - bool awaken = false; - - _enter("{OBJ%x,%d},%d", object->debug_id, object->n_children, event); - - ASSERT(cookie != NULL); - ASSERT(!hlist_unhashed(&object->cookie_link)); - - if (test_bit(FSCACHE_COOKIE_AUX_UPDATED, &cookie->flags)) { - _debug("final update"); - fscache_update_aux_data(object); - } - - /* Make sure the cookie no longer points here and that the netfs isn't - * waiting for us. - */ - spin_lock(&cookie->lock); - hlist_del_init(&object->cookie_link); - if (hlist_empty(&cookie->backing_objects) && - test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) - awaken = true; - spin_unlock(&cookie->lock); - - if (awaken) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); - if (test_and_clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP); - - - /* Prevent a race with our last child, which has to signal EV_CLEARED - * before dropping our spinlock. - */ - spin_lock(&object->lock); - spin_unlock(&object->lock); - - /* Discard from the cache's collection of objects */ - spin_lock(&cache->object_list_lock); - list_del_init(&object->cache_link); - spin_unlock(&cache->object_list_lock); - - fscache_stat(&fscache_n_cop_drop_object); - cache->ops->drop_object(object); - fscache_stat_d(&fscache_n_cop_drop_object); - - /* The parent object wants to know when all it dependents have gone */ - if (parent) { - _debug("release parent OBJ%x {%d}", - parent->debug_id, parent->n_children); - - spin_lock(&parent->lock); - parent->n_children--; - if (parent->n_children == 0) - fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED); - spin_unlock(&parent->lock); - object->parent = NULL; - } - - /* this just shifts the object release to the work processor */ - fscache_put_object(object, fscache_obj_put_drop_obj); - fscache_stat(&fscache_n_object_dead); - - _leave(""); - return transit_to(OBJECT_DEAD); -} - -/* - * get a ref on an object - */ -static int fscache_get_object(struct fscache_object *object, - enum fscache_obj_ref_trace why) -{ - int ret; - - fscache_stat(&fscache_n_cop_grab_object); - ret = object->cache->ops->grab_object(object, why) ? 0 : -EAGAIN; - fscache_stat_d(&fscache_n_cop_grab_object); - return ret; -} - -/* - * Discard a ref on an object - */ -static void fscache_put_object(struct fscache_object *object, - enum fscache_obj_ref_trace why) -{ - fscache_stat(&fscache_n_cop_put_object); - object->cache->ops->put_object(object, why); - fscache_stat_d(&fscache_n_cop_put_object); -} - -/** - * fscache_object_destroy - Note that a cache object is about to be destroyed - * @object: The object to be destroyed - * - * Note the imminent destruction and deallocation of a cache object record. - */ -void fscache_object_destroy(struct fscache_object *object) -{ - /* We can get rid of the cookie now */ - fscache_cookie_put(object->cookie, fscache_cookie_put_object); - object->cookie = NULL; -} -EXPORT_SYMBOL(fscache_object_destroy); - -/* - * enqueue an object for metadata-type processing - */ -void fscache_enqueue_object(struct fscache_object *object) -{ - _enter("{OBJ%x}", object->debug_id); - - if (fscache_get_object(object, fscache_obj_get_queue) >= 0) { - wait_queue_head_t *cong_wq = - &get_cpu_var(fscache_object_cong_wait); - - if (queue_work(fscache_object_wq, &object->work)) { - if (fscache_object_congested()) - wake_up(cong_wq); - } else - fscache_put_object(object, fscache_obj_put_queue); - - put_cpu_var(fscache_object_cong_wait); - } -} - -/** - * fscache_object_sleep_till_congested - Sleep until object wq is congested - * @timeoutp: Scheduler sleep timeout - * - * Allow an object handler to sleep until the object workqueue is congested. - * - * The caller must set up a wake up event before calling this and must have set - * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own - * condition before calling this function as no test is made here. - * - * %true is returned if the object wq is congested, %false otherwise. - */ -bool fscache_object_sleep_till_congested(signed long *timeoutp) -{ - wait_queue_head_t *cong_wq = this_cpu_ptr(&fscache_object_cong_wait); - DEFINE_WAIT(wait); - - if (fscache_object_congested()) - return true; - - add_wait_queue_exclusive(cong_wq, &wait); - if (!fscache_object_congested()) - *timeoutp = schedule_timeout(*timeoutp); - finish_wait(cong_wq, &wait); - - return fscache_object_congested(); -} -EXPORT_SYMBOL_GPL(fscache_object_sleep_till_congested); - -/* - * Enqueue the dependents of an object for metadata-type processing. - * - * If we don't manage to finish the list before the scheduler wants to run - * again then return false immediately. We return true if the list was - * cleared. - */ -static bool fscache_enqueue_dependents(struct fscache_object *object, int event) -{ - struct fscache_object *dep; - bool ret = true; - - _enter("{OBJ%x}", object->debug_id); - - if (list_empty(&object->dependents)) - return true; - - spin_lock(&object->lock); - - while (!list_empty(&object->dependents)) { - dep = list_entry(object->dependents.next, - struct fscache_object, dep_link); - list_del_init(&dep->dep_link); - - fscache_raise_event(dep, event); - fscache_put_object(dep, fscache_obj_put_enq_dep); - - if (!list_empty(&object->dependents) && need_resched()) { - ret = false; - break; - } - } - - spin_unlock(&object->lock); - return ret; -} - -/* - * remove an object from whatever queue it's waiting on - */ -static void fscache_dequeue_object(struct fscache_object *object) -{ - _enter("{OBJ%x}", object->debug_id); - - if (!list_empty(&object->dep_link)) { - spin_lock(&object->parent->lock); - list_del_init(&object->dep_link); - spin_unlock(&object->parent->lock); - } - - _leave(""); -} - -/** - * fscache_check_aux - Ask the netfs whether an object on disk is still valid - * @object: The object to ask about - * @data: The auxiliary data for the object - * @datalen: The size of the auxiliary data - * @object_size: The size of the object according to the server. - * - * This function consults the netfs about the coherency state of an object. - * The caller must be holding a ref on cookie->n_active (held by - * fscache_look_up_object() on behalf of the cache backend during object lookup - * and creation). - */ -enum fscache_checkaux fscache_check_aux(struct fscache_object *object, - const void *data, uint16_t datalen, - loff_t object_size) -{ - enum fscache_checkaux result; - - if (!object->cookie->def->check_aux) { - fscache_stat(&fscache_n_checkaux_none); - return FSCACHE_CHECKAUX_OKAY; - } - - result = object->cookie->def->check_aux(object->cookie->netfs_data, - data, datalen, object_size); - switch (result) { - /* entry okay as is */ - case FSCACHE_CHECKAUX_OKAY: - fscache_stat(&fscache_n_checkaux_okay); - break; - - /* entry requires update */ - case FSCACHE_CHECKAUX_NEEDS_UPDATE: - fscache_stat(&fscache_n_checkaux_update); - break; - - /* entry requires deletion */ - case FSCACHE_CHECKAUX_OBSOLETE: - fscache_stat(&fscache_n_checkaux_obsolete); - break; - - default: - BUG(); - } - - return result; -} -EXPORT_SYMBOL(fscache_check_aux); - -/* - * Asynchronously invalidate an object. - */ -static const struct fscache_state *_fscache_invalidate_object(struct fscache_object *object, - int event) -{ - struct fscache_operation *op; - struct fscache_cookie *cookie = object->cookie; - - _enter("{OBJ%x},%d", object->debug_id, event); - - /* We're going to need the cookie. If the cookie is not available then - * retire the object instead. - */ - if (!fscache_use_cookie(object)) { - ASSERT(radix_tree_empty(&object->cookie->stores)); - set_bit(FSCACHE_OBJECT_RETIRED, &object->flags); - _leave(" [no cookie]"); - return transit_to(KILL_OBJECT); - } - - /* Reject any new read/write ops and abort any that are pending. */ - fscache_invalidate_writes(cookie); - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - fscache_cancel_all_ops(object); - - /* Now we have to wait for in-progress reads and writes */ - op = kzalloc(sizeof(*op), GFP_KERNEL); - if (!op) - goto nomem; - - fscache_operation_init(cookie, op, object->cache->ops->invalidate_object, - NULL, NULL); - op->flags = FSCACHE_OP_ASYNC | - (1 << FSCACHE_OP_EXCLUSIVE) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - trace_fscache_page_op(cookie, NULL, op, fscache_page_op_invalidate); - - spin_lock(&cookie->lock); - if (fscache_submit_exclusive_op(object, op) < 0) - goto submit_op_failed; - spin_unlock(&cookie->lock); - fscache_put_operation(op); - - /* Once we've completed the invalidation, we know there will be no data - * stored in the cache and thus we can reinstate the data-check-skip - * optimisation. - */ - set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - - /* We can allow read and write requests to come in once again. They'll - * queue up behind our exclusive invalidation operation. - */ - if (test_and_clear_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) - wake_up_bit(&cookie->flags, FSCACHE_COOKIE_INVALIDATING); - _leave(" [ok]"); - return transit_to(UPDATE_OBJECT); - -nomem: - fscache_mark_object_dead(object); - fscache_unuse_cookie(object); - _leave(" [ENOMEM]"); - return transit_to(KILL_OBJECT); - -submit_op_failed: - fscache_mark_object_dead(object); - spin_unlock(&cookie->lock); - fscache_unuse_cookie(object); - kfree(op); - _leave(" [EIO]"); - return transit_to(KILL_OBJECT); -} - -static const struct fscache_state *fscache_invalidate_object(struct fscache_object *object, - int event) -{ - const struct fscache_state *s; - - fscache_stat(&fscache_n_invalidates_run); - fscache_stat(&fscache_n_cop_invalidate_object); - s = _fscache_invalidate_object(object, event); - fscache_stat_d(&fscache_n_cop_invalidate_object); - return s; -} - -/* - * Update auxiliary data. - */ -static void fscache_update_aux_data(struct fscache_object *object) -{ - fscache_stat(&fscache_n_updates_run); - fscache_stat(&fscache_n_cop_update_object); - object->cache->ops->update_object(object); - fscache_stat_d(&fscache_n_cop_update_object); -} - -/* - * Asynchronously update an object. - */ -static const struct fscache_state *fscache_update_object(struct fscache_object *object, - int event) -{ - _enter("{OBJ%x},%d", object->debug_id, event); - - fscache_update_aux_data(object); - - _leave(""); - return transit_to(WAIT_FOR_CMD); -} - -/** - * fscache_object_retrying_stale - Note retrying stale object - * @object: The object that will be retried - * - * Note that an object lookup found an on-disk object that was adjudged to be - * stale and has been deleted. The lookup will be retried. - */ -void fscache_object_retrying_stale(struct fscache_object *object) -{ - fscache_stat(&fscache_n_cache_no_space_reject); -} -EXPORT_SYMBOL(fscache_object_retrying_stale); - -/** - * fscache_object_mark_killed - Note that an object was killed - * @object: The object that was culled - * @why: The reason the object was killed. - * - * Note that an object was killed. Returns true if the object was - * already marked killed, false if it wasn't. - */ -void fscache_object_mark_killed(struct fscache_object *object, - enum fscache_why_object_killed why) -{ - if (test_and_set_bit(FSCACHE_OBJECT_KILLED_BY_CACHE, &object->flags)) { - pr_err("Error: Object already killed by cache [%s]\n", - object->cache->identifier); - return; - } - - switch (why) { - case FSCACHE_OBJECT_NO_SPACE: - fscache_stat(&fscache_n_cache_no_space_reject); - break; - case FSCACHE_OBJECT_IS_STALE: - fscache_stat(&fscache_n_cache_stale_objects); - break; - case FSCACHE_OBJECT_WAS_RETIRED: - fscache_stat(&fscache_n_cache_retired_objects); - break; - case FSCACHE_OBJECT_WAS_CULLED: - fscache_stat(&fscache_n_cache_culled_objects); - break; - } -} -EXPORT_SYMBOL(fscache_object_mark_killed); - -/* - * The object is dead. We can get here if an object gets queued by an event - * that would lead to its death (such as EV_KILL) when the dispatcher is - * already running (and so can be requeued) but hasn't yet cleared the event - * mask. - */ -static const struct fscache_state *fscache_object_dead(struct fscache_object *object, - int event) -{ - if (!test_and_set_bit(FSCACHE_OBJECT_RUN_AFTER_DEAD, - &object->flags)) - return NO_TRANSIT; - - WARN(true, "FS-Cache object redispatched after death"); - return NO_TRANSIT; -} diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c deleted file mode 100644 index e002cdfaf3cc..000000000000 --- a/fs/fscache/operation.c +++ /dev/null @@ -1,633 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache worker operation management routines - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * See Documentation/filesystems/caching/operations.rst - */ - -#define FSCACHE_DEBUG_LEVEL OPERATION -#include -#include -#include -#include "internal.h" - -atomic_t fscache_op_debug_id; -EXPORT_SYMBOL(fscache_op_debug_id); - -static void fscache_operation_dummy_cancel(struct fscache_operation *op) -{ -} - -/** - * fscache_operation_init - Do basic initialisation of an operation - * @cookie: The cookie to operate on - * @op: The operation to initialise - * @processor: The function to perform the operation - * @cancel: A function to handle operation cancellation - * @release: The release function to assign - * - * Do basic initialisation of an operation. The caller must still set flags, - * object and processor if needed. - */ -void fscache_operation_init(struct fscache_cookie *cookie, - struct fscache_operation *op, - fscache_operation_processor_t processor, - fscache_operation_cancel_t cancel, - fscache_operation_release_t release) -{ - INIT_WORK(&op->work, fscache_op_work_func); - atomic_set(&op->usage, 1); - op->state = FSCACHE_OP_ST_INITIALISED; - op->debug_id = atomic_inc_return(&fscache_op_debug_id); - op->processor = processor; - op->cancel = cancel ?: fscache_operation_dummy_cancel; - op->release = release; - INIT_LIST_HEAD(&op->pend_link); - fscache_stat(&fscache_n_op_initialised); - trace_fscache_op(cookie, op, fscache_op_init); -} -EXPORT_SYMBOL(fscache_operation_init); - -/** - * fscache_enqueue_operation - Enqueue an operation for processing - * @op: The operation to enqueue - * - * Enqueue an operation for processing by the FS-Cache thread pool. - * - * This will get its own ref on the object. - */ -void fscache_enqueue_operation(struct fscache_operation *op) -{ - struct fscache_cookie *cookie = op->object->cookie; - - _enter("{OBJ%x OP%x,%u}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); - - ASSERT(list_empty(&op->pend_link)); - ASSERT(op->processor != NULL); - ASSERT(fscache_object_is_available(op->object)); - ASSERTCMP(atomic_read(&op->usage), >, 0); - ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS, - op->state, ==, FSCACHE_OP_ST_CANCELLED); - - fscache_stat(&fscache_n_op_enqueue); - switch (op->flags & FSCACHE_OP_TYPE) { - case FSCACHE_OP_ASYNC: - trace_fscache_op(cookie, op, fscache_op_enqueue_async); - _debug("queue async"); - atomic_inc(&op->usage); - if (!queue_work(fscache_op_wq, &op->work)) - fscache_put_operation(op); - break; - case FSCACHE_OP_MYTHREAD: - trace_fscache_op(cookie, op, fscache_op_enqueue_mythread); - _debug("queue for caller's attention"); - break; - default: - pr_err("Unexpected op type %lx", op->flags); - BUG(); - break; - } -} -EXPORT_SYMBOL(fscache_enqueue_operation); - -/* - * start an op running - */ -static void fscache_run_op(struct fscache_object *object, - struct fscache_operation *op) -{ - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING); - - op->state = FSCACHE_OP_ST_IN_PROGRESS; - object->n_in_progress++; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - if (op->processor) - fscache_enqueue_operation(op); - else - trace_fscache_op(object->cookie, op, fscache_op_run); - fscache_stat(&fscache_n_op_run); -} - -/* - * report an unexpected submission - */ -static void fscache_report_unexpected_submission(struct fscache_object *object, - struct fscache_operation *op, - const struct fscache_state *ostate) -{ - static bool once_only; - struct fscache_operation *p; - unsigned n; - - if (once_only) - return; - once_only = true; - - kdebug("unexpected submission OP%x [OBJ%x %s]", - op->debug_id, object->debug_id, object->state->name); - kdebug("objstate=%s [%s]", object->state->name, ostate->name); - kdebug("objflags=%lx", object->flags); - kdebug("objevent=%lx [%lx]", object->events, object->event_mask); - kdebug("ops=%u inp=%u exc=%u", - object->n_ops, object->n_in_progress, object->n_exclusive); - - if (!list_empty(&object->pending_ops)) { - n = 0; - list_for_each_entry(p, &object->pending_ops, pend_link) { - ASSERTCMP(p->object, ==, object); - kdebug("%p %p", op->processor, op->release); - n++; - } - - kdebug("n=%u", n); - } - - dump_stack(); -} - -/* - * submit an exclusive operation for an object - * - other ops are excluded from running simultaneously with this one - * - this gets any extra refs it needs on an op - */ -int fscache_submit_exclusive_op(struct fscache_object *object, - struct fscache_operation *op) -{ - const struct fscache_state *ostate; - unsigned long flags; - int ret; - - _enter("{OBJ%x OP%x},", object->debug_id, op->debug_id); - - trace_fscache_op(object->cookie, op, fscache_op_submit_ex); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED); - ASSERTCMP(atomic_read(&op->usage), >, 0); - - spin_lock(&object->lock); - ASSERTCMP(object->n_ops, >=, object->n_in_progress); - ASSERTCMP(object->n_ops, >=, object->n_exclusive); - ASSERT(list_empty(&op->pend_link)); - - ostate = object->state; - smp_rmb(); - - op->state = FSCACHE_OP_ST_PENDING; - flags = READ_ONCE(object->flags); - if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) { - fscache_stat(&fscache_n_op_rejected); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else if (unlikely(fscache_cache_is_broken(object))) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -EIO; - } else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) { - op->object = object; - object->n_ops++; - object->n_exclusive++; /* reads and writes must wait */ - - if (object->n_in_progress > 0) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - } else if (!list_empty(&object->pending_ops)) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - fscache_start_operations(object); - } else { - ASSERTCMP(object->n_in_progress, ==, 0); - fscache_run_op(object, op); - } - - /* need to issue a new write op after this */ - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) { - op->object = object; - object->n_ops++; - object->n_exclusive++; /* reads and writes must wait */ - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else { - fscache_report_unexpected_submission(object, op, ostate); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } - - spin_unlock(&object->lock); - return ret; -} - -/* - * submit an operation for an object - * - objects may be submitted only in the following states: - * - during object creation (write ops may be submitted) - * - whilst the object is active - * - after an I/O error incurred in one of the two above states (op rejected) - * - this gets any extra refs it needs on an op - */ -int fscache_submit_op(struct fscache_object *object, - struct fscache_operation *op) -{ - const struct fscache_state *ostate; - unsigned long flags; - int ret; - - _enter("{OBJ%x OP%x},{%u}", - object->debug_id, op->debug_id, atomic_read(&op->usage)); - - trace_fscache_op(object->cookie, op, fscache_op_submit); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_INITIALISED); - ASSERTCMP(atomic_read(&op->usage), >, 0); - - spin_lock(&object->lock); - ASSERTCMP(object->n_ops, >=, object->n_in_progress); - ASSERTCMP(object->n_ops, >=, object->n_exclusive); - ASSERT(list_empty(&op->pend_link)); - - ostate = object->state; - smp_rmb(); - - op->state = FSCACHE_OP_ST_PENDING; - flags = READ_ONCE(object->flags); - if (unlikely(!(flags & BIT(FSCACHE_OBJECT_IS_LIVE)))) { - fscache_stat(&fscache_n_op_rejected); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else if (unlikely(fscache_cache_is_broken(object))) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -EIO; - } else if (flags & BIT(FSCACHE_OBJECT_IS_AVAILABLE)) { - op->object = object; - object->n_ops++; - - if (object->n_exclusive > 0) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - } else if (!list_empty(&object->pending_ops)) { - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - fscache_start_operations(object); - } else { - ASSERTCMP(object->n_exclusive, ==, 0); - fscache_run_op(object, op); - } - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_IS_LOOKED_UP)) { - op->object = object; - object->n_ops++; - atomic_inc(&op->usage); - list_add_tail(&op->pend_link, &object->pending_ops); - fscache_stat(&fscache_n_op_pend); - ret = 0; - } else if (flags & BIT(FSCACHE_OBJECT_KILLED_BY_CACHE)) { - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } else { - fscache_report_unexpected_submission(object, op, ostate); - ASSERT(!fscache_object_is_active(object)); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - ret = -ENOBUFS; - } - - spin_unlock(&object->lock); - return ret; -} - -/* - * queue an object for withdrawal on error, aborting all following asynchronous - * operations - */ -void fscache_abort_object(struct fscache_object *object) -{ - _enter("{OBJ%x}", object->debug_id); - - fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR); -} - -/* - * Jump start the operation processing on an object. The caller must hold - * object->lock. - */ -void fscache_start_operations(struct fscache_object *object) -{ - struct fscache_operation *op; - bool stop = false; - - while (!list_empty(&object->pending_ops) && !stop) { - op = list_entry(object->pending_ops.next, - struct fscache_operation, pend_link); - - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) { - if (object->n_in_progress > 0) - break; - stop = true; - } - list_del_init(&op->pend_link); - fscache_run_op(object, op); - - /* the pending queue was holding a ref on the object */ - fscache_put_operation(op); - } - - ASSERTCMP(object->n_in_progress, <=, object->n_ops); - - _debug("woke %d ops on OBJ%x", - object->n_in_progress, object->debug_id); -} - -/* - * cancel an operation that's pending on an object - */ -int fscache_cancel_op(struct fscache_operation *op, - bool cancel_in_progress_op) -{ - struct fscache_object *object = op->object; - bool put = false; - int ret; - - _enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id); - - trace_fscache_op(object->cookie, op, fscache_op_cancel); - - ASSERTCMP(op->state, >=, FSCACHE_OP_ST_PENDING); - ASSERTCMP(op->state, !=, FSCACHE_OP_ST_CANCELLED); - ASSERTCMP(atomic_read(&op->usage), >, 0); - - spin_lock(&object->lock); - - ret = -EBUSY; - if (op->state == FSCACHE_OP_ST_PENDING) { - ASSERT(!list_empty(&op->pend_link)); - list_del_init(&op->pend_link); - put = true; - - fscache_stat(&fscache_n_op_cancelled); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - ret = 0; - } else if (op->state == FSCACHE_OP_ST_IN_PROGRESS && cancel_in_progress_op) { - ASSERTCMP(object->n_in_progress, >, 0); - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - object->n_in_progress--; - if (object->n_in_progress == 0) - fscache_start_operations(object); - - fscache_stat(&fscache_n_op_cancelled); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - ret = 0; - } - - if (put) - fscache_put_operation(op); - spin_unlock(&object->lock); - _leave(" = %d", ret); - return ret; -} - -/* - * Cancel all pending operations on an object - */ -void fscache_cancel_all_ops(struct fscache_object *object) -{ - struct fscache_operation *op; - - _enter("OBJ%x", object->debug_id); - - spin_lock(&object->lock); - - while (!list_empty(&object->pending_ops)) { - op = list_entry(object->pending_ops.next, - struct fscache_operation, pend_link); - fscache_stat(&fscache_n_op_cancelled); - list_del_init(&op->pend_link); - - trace_fscache_op(object->cookie, op, fscache_op_cancel_all); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_PENDING); - op->cancel(op); - op->state = FSCACHE_OP_ST_CANCELLED; - - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags)) - wake_up_bit(&op->flags, FSCACHE_OP_WAITING); - fscache_put_operation(op); - cond_resched_lock(&object->lock); - } - - spin_unlock(&object->lock); - _leave(""); -} - -/* - * Record the completion or cancellation of an in-progress operation. - */ -void fscache_op_complete(struct fscache_operation *op, bool cancelled) -{ - struct fscache_object *object = op->object; - - _enter("OBJ%x", object->debug_id); - - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS); - ASSERTCMP(object->n_in_progress, >, 0); - ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags), - object->n_exclusive, >, 0); - ASSERTIFCMP(test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags), - object->n_in_progress, ==, 1); - - spin_lock(&object->lock); - - if (!cancelled) { - trace_fscache_op(object->cookie, op, fscache_op_completed); - op->state = FSCACHE_OP_ST_COMPLETE; - } else { - op->cancel(op); - trace_fscache_op(object->cookie, op, fscache_op_cancelled); - op->state = FSCACHE_OP_ST_CANCELLED; - } - - if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) - object->n_exclusive--; - object->n_in_progress--; - if (object->n_in_progress == 0) - fscache_start_operations(object); - - spin_unlock(&object->lock); - _leave(""); -} -EXPORT_SYMBOL(fscache_op_complete); - -/* - * release an operation - * - queues pending ops if this is the last in-progress op - */ -void fscache_put_operation(struct fscache_operation *op) -{ - struct fscache_object *object; - struct fscache_cache *cache; - - _enter("{OBJ%x OP%x,%d}", - op->object ? op->object->debug_id : 0, - op->debug_id, atomic_read(&op->usage)); - - ASSERTCMP(atomic_read(&op->usage), >, 0); - - if (!atomic_dec_and_test(&op->usage)) - return; - - trace_fscache_op(op->object ? op->object->cookie : NULL, op, fscache_op_put); - - _debug("PUT OP"); - ASSERTIFCMP(op->state != FSCACHE_OP_ST_INITIALISED && - op->state != FSCACHE_OP_ST_COMPLETE, - op->state, ==, FSCACHE_OP_ST_CANCELLED); - - fscache_stat(&fscache_n_op_release); - - if (op->release) { - op->release(op); - op->release = NULL; - } - op->state = FSCACHE_OP_ST_DEAD; - - object = op->object; - if (likely(object)) { - if (test_bit(FSCACHE_OP_DEC_READ_CNT, &op->flags)) - atomic_dec(&object->n_reads); - if (test_bit(FSCACHE_OP_UNUSE_COOKIE, &op->flags)) - fscache_unuse_cookie(object); - - /* now... we may get called with the object spinlock held, so we - * complete the cleanup here only if we can immediately acquire the - * lock, and defer it otherwise */ - if (!spin_trylock(&object->lock)) { - _debug("defer put"); - fscache_stat(&fscache_n_op_deferred_release); - - cache = object->cache; - spin_lock(&cache->op_gc_list_lock); - list_add_tail(&op->pend_link, &cache->op_gc_list); - spin_unlock(&cache->op_gc_list_lock); - schedule_work(&cache->op_gc); - _leave(" [defer]"); - return; - } - - ASSERTCMP(object->n_ops, >, 0); - object->n_ops--; - if (object->n_ops == 0) - fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED); - - spin_unlock(&object->lock); - } - - kfree(op); - _leave(" [done]"); -} -EXPORT_SYMBOL(fscache_put_operation); - -/* - * garbage collect operations that have had their release deferred - */ -void fscache_operation_gc(struct work_struct *work) -{ - struct fscache_operation *op; - struct fscache_object *object; - struct fscache_cache *cache = - container_of(work, struct fscache_cache, op_gc); - int count = 0; - - _enter(""); - - do { - spin_lock(&cache->op_gc_list_lock); - if (list_empty(&cache->op_gc_list)) { - spin_unlock(&cache->op_gc_list_lock); - break; - } - - op = list_entry(cache->op_gc_list.next, - struct fscache_operation, pend_link); - list_del(&op->pend_link); - spin_unlock(&cache->op_gc_list_lock); - - object = op->object; - trace_fscache_op(object->cookie, op, fscache_op_gc); - - spin_lock(&object->lock); - - _debug("GC DEFERRED REL OBJ%x OP%x", - object->debug_id, op->debug_id); - fscache_stat(&fscache_n_op_gc); - - ASSERTCMP(atomic_read(&op->usage), ==, 0); - ASSERTCMP(op->state, ==, FSCACHE_OP_ST_DEAD); - - ASSERTCMP(object->n_ops, >, 0); - object->n_ops--; - if (object->n_ops == 0) - fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED); - - spin_unlock(&object->lock); - kfree(op); - - } while (count++ < 20); - - if (!list_empty(&cache->op_gc_list)) - schedule_work(&cache->op_gc); - - _leave(""); -} - -/* - * execute an operation using fs_op_wq to provide processing context - - * the caller holds a ref to this object, so we don't need to hold one - */ -void fscache_op_work_func(struct work_struct *work) -{ - struct fscache_operation *op = - container_of(work, struct fscache_operation, work); - - _enter("{OBJ%x OP%x,%d}", - op->object->debug_id, op->debug_id, atomic_read(&op->usage)); - - trace_fscache_op(op->object->cookie, op, fscache_op_work); - - ASSERT(op->processor != NULL); - op->processor(op); - fscache_put_operation(op); - - _leave(""); -} diff --git a/fs/fscache/page.c b/fs/fscache/page.c deleted file mode 100644 index 27df94ef0e0b..000000000000 --- a/fs/fscache/page.c +++ /dev/null @@ -1,1242 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* Cache page management and data I/O routines - * - * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL PAGE -#include -#include -#include -#include -#include -#include "internal.h" - -/* - * check to see if a page is being written to the cache - */ -bool __fscache_check_page_write(struct fscache_cookie *cookie, struct page *page) -{ - void *val; - - rcu_read_lock(); - val = radix_tree_lookup(&cookie->stores, page->index); - rcu_read_unlock(); - trace_fscache_check_page(cookie, page, val, 0); - - return val != NULL; -} -EXPORT_SYMBOL(__fscache_check_page_write); - -/* - * wait for a page to finish being written to the cache - */ -void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page) -{ - wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0); - - trace_fscache_page(cookie, page, fscache_page_write_wait); - - wait_event(*wq, !__fscache_check_page_write(cookie, page)); -} -EXPORT_SYMBOL(__fscache_wait_on_page_write); - -/* - * wait for a page to finish being written to the cache. Put a timeout here - * since we might be called recursively via parent fs. - */ -static -bool release_page_wait_timeout(struct fscache_cookie *cookie, struct page *page) -{ - wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0); - - return wait_event_timeout(*wq, !__fscache_check_page_write(cookie, page), - HZ); -} - -/* - * decide whether a page can be released, possibly by cancelling a store to it - * - we're allowed to sleep if __GFP_DIRECT_RECLAIM is flagged - */ -bool __fscache_maybe_release_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - struct page *xpage; - void *val; - - _enter("%p,%p,%x", cookie, page, gfp); - - trace_fscache_page(cookie, page, fscache_page_maybe_release); - -try_again: - rcu_read_lock(); - val = radix_tree_lookup(&cookie->stores, page->index); - if (!val) { - rcu_read_unlock(); - fscache_stat(&fscache_n_store_vmscan_not_storing); - __fscache_uncache_page(cookie, page); - return true; - } - - /* see if the page is actually undergoing storage - if so we can't get - * rid of it till the cache has finished with it */ - if (radix_tree_tag_get(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG)) { - rcu_read_unlock(); - goto page_busy; - } - - /* the page is pending storage, so we attempt to cancel the store and - * discard the store request so that the page can be reclaimed */ - spin_lock(&cookie->stores_lock); - rcu_read_unlock(); - - if (radix_tree_tag_get(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG)) { - /* the page started to undergo storage whilst we were looking, - * so now we can only wait or return */ - spin_unlock(&cookie->stores_lock); - goto page_busy; - } - - xpage = radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - spin_unlock(&cookie->stores_lock); - - if (xpage) { - fscache_stat(&fscache_n_store_vmscan_cancelled); - fscache_stat(&fscache_n_store_radix_deletes); - ASSERTCMP(xpage, ==, page); - } else { - fscache_stat(&fscache_n_store_vmscan_gone); - } - - wake_up_bit(&cookie->flags, 0); - trace_fscache_wake_cookie(cookie); - if (xpage) - put_page(xpage); - __fscache_uncache_page(cookie, page); - return true; - -page_busy: - /* We will wait here if we're allowed to, but that could deadlock the - * allocator as the work threads writing to the cache may all end up - * sleeping on memory allocation, so we may need to impose a timeout - * too. */ - if (!(gfp & __GFP_DIRECT_RECLAIM) || !(gfp & __GFP_FS)) { - fscache_stat(&fscache_n_store_vmscan_busy); - return false; - } - - fscache_stat(&fscache_n_store_vmscan_wait); - if (!release_page_wait_timeout(cookie, page)) - _debug("fscache writeout timeout page: %p{%lx}", - page, page->index); - - gfp &= ~__GFP_DIRECT_RECLAIM; - goto try_again; -} -EXPORT_SYMBOL(__fscache_maybe_release_page); - -/* - * note that a page has finished being written to the cache - */ -static void fscache_end_page_write(struct fscache_object *object, - struct page *page) -{ - struct fscache_cookie *cookie; - struct page *xpage = NULL, *val; - - spin_lock(&object->lock); - cookie = object->cookie; - if (cookie) { - /* delete the page from the tree if it is now no longer - * pending */ - spin_lock(&cookie->stores_lock); - radix_tree_tag_clear(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG); - trace_fscache_page(cookie, page, fscache_page_radix_clear_store); - if (!radix_tree_tag_get(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG)) { - fscache_stat(&fscache_n_store_radix_deletes); - xpage = radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - trace_fscache_page(cookie, page, fscache_page_write_end); - - val = radix_tree_lookup(&cookie->stores, page->index); - trace_fscache_check_page(cookie, page, val, 1); - } else { - trace_fscache_page(cookie, page, fscache_page_write_end_pend); - } - spin_unlock(&cookie->stores_lock); - wake_up_bit(&cookie->flags, 0); - trace_fscache_wake_cookie(cookie); - } else { - trace_fscache_page(cookie, page, fscache_page_write_end_noc); - } - spin_unlock(&object->lock); - if (xpage) - put_page(xpage); -} - -/* - * actually apply the changed attributes to a cache object - */ -static void fscache_attr_changed_op(struct fscache_operation *op) -{ - struct fscache_object *object = op->object; - int ret; - - _enter("{OBJ%x OP%x}", object->debug_id, op->debug_id); - - fscache_stat(&fscache_n_attr_changed_calls); - - if (fscache_object_is_active(object)) { - fscache_stat(&fscache_n_cop_attr_changed); - ret = object->cache->ops->attr_changed(object); - fscache_stat_d(&fscache_n_cop_attr_changed); - if (ret < 0) - fscache_abort_object(object); - fscache_op_complete(op, ret < 0); - } else { - fscache_op_complete(op, true); - } - - _leave(""); -} - -/* - * notification that the attributes on an object have changed - */ -int __fscache_attr_changed(struct fscache_cookie *cookie) -{ - struct fscache_operation *op; - struct fscache_object *object; - bool wake_cookie = false; - - _enter("%p", cookie); - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - - fscache_stat(&fscache_n_attr_changed); - - op = kzalloc(sizeof(*op), GFP_KERNEL); - if (!op) { - fscache_stat(&fscache_n_attr_changed_nomem); - _leave(" = -ENOMEM"); - return -ENOMEM; - } - - fscache_operation_init(cookie, op, fscache_attr_changed_op, NULL, NULL); - trace_fscache_page_op(cookie, NULL, op, fscache_page_op_attr_changed); - op->flags = FSCACHE_OP_ASYNC | - (1 << FSCACHE_OP_EXCLUSIVE) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - if (fscache_submit_exclusive_op(object, op) < 0) - goto nobufs_dec; - spin_unlock(&cookie->lock); - fscache_stat(&fscache_n_attr_changed_ok); - fscache_put_operation(op); - _leave(" = 0"); - return 0; - -nobufs_dec: - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs: - spin_unlock(&cookie->lock); - fscache_put_operation(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - fscache_stat(&fscache_n_attr_changed_nobufs); - _leave(" = %d", -ENOBUFS); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_attr_changed); - -/* - * Handle cancellation of a pending retrieval op - */ -static void fscache_do_cancel_retrieval(struct fscache_operation *_op) -{ - struct fscache_retrieval *op = - container_of(_op, struct fscache_retrieval, op); - - atomic_set(&op->n_pages, 0); -} - -/* - * release a retrieval op reference - */ -static void fscache_release_retrieval_op(struct fscache_operation *_op) -{ - struct fscache_retrieval *op = - container_of(_op, struct fscache_retrieval, op); - - _enter("{OP%x}", op->op.debug_id); - - ASSERTIFCMP(op->op.state != FSCACHE_OP_ST_INITIALISED, - atomic_read(&op->n_pages), ==, 0); - - if (op->context) - fscache_put_context(op->cookie, op->context); - - _leave(""); -} - -/* - * allocate a retrieval op - */ -struct fscache_retrieval *fscache_alloc_retrieval( - struct fscache_cookie *cookie, - struct address_space *mapping, - fscache_rw_complete_t end_io_func, - void *context) -{ - struct fscache_retrieval *op; - - /* allocate a retrieval operation and attempt to submit it */ - op = kzalloc(sizeof(*op), GFP_NOIO); - if (!op) { - fscache_stat(&fscache_n_retrievals_nomem); - return NULL; - } - - fscache_operation_init(cookie, &op->op, NULL, - fscache_do_cancel_retrieval, - fscache_release_retrieval_op); - op->op.flags = FSCACHE_OP_MYTHREAD | - (1UL << FSCACHE_OP_WAITING) | - (1UL << FSCACHE_OP_UNUSE_COOKIE); - op->cookie = cookie; - op->mapping = mapping; - op->end_io_func = end_io_func; - op->context = context; - INIT_LIST_HEAD(&op->to_do); - - /* Pin the netfs read context in case we need to do the actual netfs - * read because we've encountered a cache read failure. - */ - if (context) - fscache_get_context(op->cookie, context); - return op; -} - -/* - * wait for a deferred lookup to complete - */ -int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie) -{ - _enter(""); - - if (!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) { - _leave(" = 0 [imm]"); - return 0; - } - - fscache_stat(&fscache_n_retrievals_wait); - - if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP, - TASK_INTERRUPTIBLE) != 0) { - fscache_stat(&fscache_n_retrievals_intr); - _leave(" = -ERESTARTSYS"); - return -ERESTARTSYS; - } - - ASSERT(!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)); - - smp_rmb(); - _leave(" = 0 [dly]"); - return 0; -} - -/* - * wait for an object to become active (or dead) - */ -int fscache_wait_for_operation_activation(struct fscache_object *object, - struct fscache_operation *op, - atomic_t *stat_op_waits, - atomic_t *stat_object_dead) -{ - int ret; - - if (!test_bit(FSCACHE_OP_WAITING, &op->flags)) - goto check_if_dead; - - _debug(">>> WT"); - if (stat_op_waits) - fscache_stat(stat_op_waits); - if (wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - TASK_INTERRUPTIBLE) != 0) { - trace_fscache_op(object->cookie, op, fscache_op_signal); - ret = fscache_cancel_op(op, false); - if (ret == 0) - return -ERESTARTSYS; - - /* it's been removed from the pending queue by another party, - * so we should get to run shortly */ - wait_on_bit(&op->flags, FSCACHE_OP_WAITING, - TASK_UNINTERRUPTIBLE); - } - _debug("<<< GO"); - -check_if_dead: - if (op->state == FSCACHE_OP_ST_CANCELLED) { - if (stat_object_dead) - fscache_stat(stat_object_dead); - _leave(" = -ENOBUFS [cancelled]"); - return -ENOBUFS; - } - if (unlikely(fscache_object_is_dying(object) || - fscache_cache_is_broken(object))) { - enum fscache_operation_state state = op->state; - trace_fscache_op(object->cookie, op, fscache_op_signal); - fscache_cancel_op(op, true); - if (stat_object_dead) - fscache_stat(stat_object_dead); - _leave(" = -ENOBUFS [obj dead %d]", state); - return -ENOBUFS; - } - return 0; -} - -/* - * read a page from the cache or allocate a block in which to store it - * - we return: - * -ENOMEM - out of memory, nothing done - * -ERESTARTSYS - interrupted - * -ENOBUFS - no backing object available in which to cache the block - * -ENODATA - no data available in the backing object for this block - * 0 - dispatched a read - it'll call end_io_func() when finished - */ -int __fscache_read_or_alloc_page(struct fscache_cookie *cookie, - struct page *page, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,%p,,,", cookie, page); - - fscache_stat(&fscache_n_retrievals); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(page, !=, NULL); - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, page->mapping, - end_io_func, context); - if (!op) { - _leave(" = -ENOMEM"); - return -ENOMEM; - } - atomic_set(&op->n_pages, 1); - trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_retr_one); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - ASSERT(test_bit(FSCACHE_OBJECT_IS_LOOKED_UP, &object->flags)); - - __fscache_use_cookie(cookie); - atomic_inc(&object->n_reads); - __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); - - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_retrieval_ops); - - /* we wait for the operation to become active, and then process it - * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { - fscache_stat(&fscache_n_cop_allocate_page); - ret = object->cache->ops->allocate_page(op, page, gfp); - fscache_stat_d(&fscache_n_cop_allocate_page); - if (ret == 0) - ret = -ENODATA; - } else { - fscache_stat(&fscache_n_cop_read_or_alloc_page); - ret = object->cache->ops->read_or_alloc_page(op, page, gfp); - fscache_stat_d(&fscache_n_cop_read_or_alloc_page); - } - -error: - if (ret == -ENOMEM) - fscache_stat(&fscache_n_retrievals_nomem); - else if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_retrievals_intr); - else if (ret == -ENODATA) - fscache_stat(&fscache_n_retrievals_nodata); - else if (ret < 0) - fscache_stat(&fscache_n_retrievals_nobufs); - else - fscache_stat(&fscache_n_retrievals_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - atomic_dec(&object->n_reads); - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - fscache_put_retrieval(op); -nobufs: - fscache_stat(&fscache_n_retrievals_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_read_or_alloc_page); - -/* - * read a list of page from the cache or allocate a block in which to store - * them - * - we return: - * -ENOMEM - out of memory, some pages may be being read - * -ERESTARTSYS - interrupted, some pages may be being read - * -ENOBUFS - no backing object or space available in which to cache any - * pages not being read - * -ENODATA - no data available in the backing object for some or all of - * the pages - * 0 - dispatched a read on all pages - * - * end_io_func() will be called for each page read from the cache as it is - * finishes being read - * - * any pages for which a read is dispatched will be removed from pages and - * nr_pages - */ -int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,,%d,,,", cookie, *nr_pages); - - fscache_stat(&fscache_n_retrievals); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(*nr_pages, >, 0); - ASSERT(!list_empty(pages)); - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, mapping, end_io_func, context); - if (!op) - return -ENOMEM; - atomic_set(&op->n_pages, *nr_pages); - trace_fscache_page_op(cookie, NULL, &op->op, fscache_page_op_retr_multi); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - atomic_inc(&object->n_reads); - __set_bit(FSCACHE_OP_DEC_READ_CNT, &op->op.flags); - - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_retrieval_ops); - - /* we wait for the operation to become active, and then process it - * *here*, in this thread, and not in the thread pool */ - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_retrieval_op_waits), - __fscache_stat(&fscache_n_retrievals_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) { - fscache_stat(&fscache_n_cop_allocate_pages); - ret = object->cache->ops->allocate_pages( - op, pages, nr_pages, gfp); - fscache_stat_d(&fscache_n_cop_allocate_pages); - } else { - fscache_stat(&fscache_n_cop_read_or_alloc_pages); - ret = object->cache->ops->read_or_alloc_pages( - op, pages, nr_pages, gfp); - fscache_stat_d(&fscache_n_cop_read_or_alloc_pages); - } - -error: - if (ret == -ENOMEM) - fscache_stat(&fscache_n_retrievals_nomem); - else if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_retrievals_intr); - else if (ret == -ENODATA) - fscache_stat(&fscache_n_retrievals_nodata); - else if (ret < 0) - fscache_stat(&fscache_n_retrievals_nobufs); - else - fscache_stat(&fscache_n_retrievals_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - atomic_dec(&object->n_reads); - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - fscache_put_retrieval(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); -nobufs: - fscache_stat(&fscache_n_retrievals_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_read_or_alloc_pages); - -/* - * allocate a block in the cache on which to store a page - * - we return: - * -ENOMEM - out of memory, nothing done - * -ERESTARTSYS - interrupted - * -ENOBUFS - no backing object available in which to cache the block - * 0 - block allocated - */ -int __fscache_alloc_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - struct fscache_retrieval *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,%p,,,", cookie, page); - - fscache_stat(&fscache_n_allocs); - - if (hlist_empty(&cookie->backing_objects)) - goto nobufs; - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(page, !=, NULL); - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - if (fscache_wait_for_deferred_lookup(cookie) < 0) - return -ERESTARTSYS; - - op = fscache_alloc_retrieval(cookie, page->mapping, NULL, NULL); - if (!op) - return -ENOMEM; - atomic_set(&op->n_pages, 1); - trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_alloc_one); - - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs_unlock; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - __fscache_use_cookie(cookie); - if (fscache_submit_op(object, &op->op) < 0) - goto nobufs_unlock_dec; - spin_unlock(&cookie->lock); - - fscache_stat(&fscache_n_alloc_ops); - - ret = fscache_wait_for_operation_activation( - object, &op->op, - __fscache_stat(&fscache_n_alloc_op_waits), - __fscache_stat(&fscache_n_allocs_object_dead)); - if (ret < 0) - goto error; - - /* ask the cache to honour the operation */ - fscache_stat(&fscache_n_cop_allocate_page); - ret = object->cache->ops->allocate_page(op, page, gfp); - fscache_stat_d(&fscache_n_cop_allocate_page); - -error: - if (ret == -ERESTARTSYS) - fscache_stat(&fscache_n_allocs_intr); - else if (ret < 0) - fscache_stat(&fscache_n_allocs_nobufs); - else - fscache_stat(&fscache_n_allocs_ok); - - fscache_put_retrieval(op); - _leave(" = %d", ret); - return ret; - -nobufs_unlock_dec: - wake_cookie = __fscache_unuse_cookie(cookie); -nobufs_unlock: - spin_unlock(&cookie->lock); - fscache_put_retrieval(op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); -nobufs: - fscache_stat(&fscache_n_allocs_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; -} -EXPORT_SYMBOL(__fscache_alloc_page); - -/* - * Unmark pages allocate in the readahead code path (via: - * fscache_readpages_or_alloc) after delegating to the base filesystem - */ -void __fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages) -{ - struct page *page; - - list_for_each_entry(page, pages, lru) { - if (PageFsCache(page)) - __fscache_uncache_page(cookie, page); - } -} -EXPORT_SYMBOL(__fscache_readpages_cancel); - -/* - * release a write op reference - */ -static void fscache_release_write_op(struct fscache_operation *_op) -{ - _enter("{OP%x}", _op->debug_id); -} - -/* - * perform the background storage of a page into the cache - */ -static void fscache_write_op(struct fscache_operation *_op) -{ - struct fscache_storage *op = - container_of(_op, struct fscache_storage, op); - struct fscache_object *object = op->op.object; - struct fscache_cookie *cookie; - struct page *page; - unsigned n; - void *results[1]; - int ret; - - _enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage)); - -again: - spin_lock(&object->lock); - cookie = object->cookie; - - if (!fscache_object_is_active(object)) { - /* If we get here, then the on-disk cache object likely no - * longer exists, so we should just cancel this write - * operation. - */ - spin_unlock(&object->lock); - fscache_op_complete(&op->op, true); - _leave(" [inactive]"); - return; - } - - if (!cookie) { - /* If we get here, then the cookie belonging to the object was - * detached, probably by the cookie being withdrawn due to - * memory pressure, which means that the pages we might write - * to the cache from no longer exist - therefore, we can just - * cancel this write operation. - */ - spin_unlock(&object->lock); - fscache_op_complete(&op->op, true); - _leave(" [cancel] op{f=%lx s=%u} obj{s=%s f=%lx}", - _op->flags, _op->state, object->state->short_name, - object->flags); - return; - } - - spin_lock(&cookie->stores_lock); - - fscache_stat(&fscache_n_store_calls); - - /* find a page to store */ - results[0] = NULL; - page = NULL; - n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, 1, - FSCACHE_COOKIE_PENDING_TAG); - trace_fscache_gang_lookup(cookie, &op->op, results, n, op->store_limit); - if (n != 1) - goto superseded; - page = results[0]; - _debug("gang %d [%lx]", n, page->index); - - radix_tree_tag_set(&cookie->stores, page->index, - FSCACHE_COOKIE_STORING_TAG); - radix_tree_tag_clear(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG); - trace_fscache_page(cookie, page, fscache_page_radix_pend2store); - - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); - - if (page->index >= op->store_limit) - goto discard_page; - - fscache_stat(&fscache_n_store_pages); - fscache_stat(&fscache_n_cop_write_page); - ret = object->cache->ops->write_page(op, page); - fscache_stat_d(&fscache_n_cop_write_page); - trace_fscache_wrote_page(cookie, page, &op->op, ret); - fscache_end_page_write(object, page); - if (ret < 0) { - fscache_abort_object(object); - fscache_op_complete(&op->op, true); - } else { - fscache_enqueue_operation(&op->op); - } - - _leave(""); - return; - -discard_page: - fscache_stat(&fscache_n_store_pages_over_limit); - trace_fscache_wrote_page(cookie, page, &op->op, -ENOBUFS); - fscache_end_page_write(object, page); - goto again; - -superseded: - /* this writer is going away and there aren't any more things to - * write */ - _debug("cease"); - spin_unlock(&cookie->stores_lock); - clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags); - spin_unlock(&object->lock); - fscache_op_complete(&op->op, false); - _leave(""); -} - -/* - * Clear the pages pending writing for invalidation - */ -void fscache_invalidate_writes(struct fscache_cookie *cookie) -{ - struct page *page; - void *results[16]; - int n, i; - - _enter(""); - - for (;;) { - spin_lock(&cookie->stores_lock); - n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, - ARRAY_SIZE(results), - FSCACHE_COOKIE_PENDING_TAG); - if (n == 0) { - spin_unlock(&cookie->stores_lock); - break; - } - - for (i = n - 1; i >= 0; i--) { - page = results[i]; - radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - trace_fscache_page(cookie, page, fscache_page_inval); - } - - spin_unlock(&cookie->stores_lock); - - for (i = n - 1; i >= 0; i--) - put_page(results[i]); - } - - wake_up_bit(&cookie->flags, 0); - trace_fscache_wake_cookie(cookie); - - _leave(""); -} - -/* - * request a page be stored in the cache - * - returns: - * -ENOMEM - out of memory, nothing done - * -ENOBUFS - no backing object available in which to cache the page - * 0 - dispatched a write - it'll call end_io_func() when finished - * - * if the cookie still has a backing object at this point, that object can be - * in one of a few states with respect to storage processing: - * - * (1) negative lookup, object not yet created (FSCACHE_COOKIE_CREATING is - * set) - * - * (a) no writes yet - * - * (b) writes deferred till post-creation (mark page for writing and - * return immediately) - * - * (2) negative lookup, object created, initial fill being made from netfs - * - * (a) fill point not yet reached this page (mark page for writing and - * return) - * - * (b) fill point passed this page (queue op to store this page) - * - * (3) object extant (queue op to store this page) - * - * any other state is invalid - */ -int __fscache_write_page(struct fscache_cookie *cookie, - struct page *page, - loff_t object_size, - gfp_t gfp) -{ - struct fscache_storage *op; - struct fscache_object *object; - bool wake_cookie = false; - int ret; - - _enter("%p,%x,", cookie, (u32) page->flags); - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERT(PageFsCache(page)); - - fscache_stat(&fscache_n_stores); - - if (test_bit(FSCACHE_COOKIE_INVALIDATING, &cookie->flags)) { - _leave(" = -ENOBUFS [invalidating]"); - return -ENOBUFS; - } - - op = kzalloc(sizeof(*op), GFP_NOIO | __GFP_NOMEMALLOC | __GFP_NORETRY); - if (!op) - goto nomem; - - fscache_operation_init(cookie, &op->op, fscache_write_op, NULL, - fscache_release_write_op); - op->op.flags = FSCACHE_OP_ASYNC | - (1 << FSCACHE_OP_WAITING) | - (1 << FSCACHE_OP_UNUSE_COOKIE); - - ret = radix_tree_maybe_preload(gfp & ~__GFP_HIGHMEM); - if (ret < 0) - goto nomem_free; - - trace_fscache_page_op(cookie, page, &op->op, fscache_page_op_write_one); - - ret = -ENOBUFS; - spin_lock(&cookie->lock); - - if (!fscache_cookie_enabled(cookie) || - hlist_empty(&cookie->backing_objects)) - goto nobufs; - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - if (test_bit(FSCACHE_IOERROR, &object->cache->flags)) - goto nobufs; - - trace_fscache_page(cookie, page, fscache_page_write); - - /* add the page to the pending-storage radix tree on the backing - * object */ - spin_lock(&object->lock); - - if (object->store_limit_l != object_size) - fscache_set_store_limit(object, object_size); - - spin_lock(&cookie->stores_lock); - - _debug("store limit %llx", (unsigned long long) object->store_limit); - - ret = radix_tree_insert(&cookie->stores, page->index, page); - if (ret < 0) { - if (ret == -EEXIST) - goto already_queued; - _debug("insert failed %d", ret); - goto nobufs_unlock_obj; - } - - trace_fscache_page(cookie, page, fscache_page_radix_insert); - radix_tree_tag_set(&cookie->stores, page->index, - FSCACHE_COOKIE_PENDING_TAG); - trace_fscache_page(cookie, page, fscache_page_radix_set_pend); - get_page(page); - - /* we only want one writer at a time, but we do need to queue new - * writers after exclusive ops */ - if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags)) - goto already_pending; - - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); - - op->op.debug_id = atomic_inc_return(&fscache_op_debug_id); - op->store_limit = object->store_limit; - - __fscache_use_cookie(cookie); - if (fscache_submit_op(object, &op->op) < 0) - goto submit_failed; - - spin_unlock(&cookie->lock); - radix_tree_preload_end(); - fscache_stat(&fscache_n_store_ops); - fscache_stat(&fscache_n_stores_ok); - - /* the work queue now carries its own ref on the object */ - fscache_put_operation(&op->op); - _leave(" = 0"); - return 0; - -already_queued: - fscache_stat(&fscache_n_stores_again); -already_pending: - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); - spin_unlock(&cookie->lock); - radix_tree_preload_end(); - fscache_put_operation(&op->op); - fscache_stat(&fscache_n_stores_ok); - _leave(" = 0"); - return 0; - -submit_failed: - spin_lock(&cookie->stores_lock); - radix_tree_delete(&cookie->stores, page->index); - trace_fscache_page(cookie, page, fscache_page_radix_delete); - spin_unlock(&cookie->stores_lock); - wake_cookie = __fscache_unuse_cookie(cookie); - put_page(page); - ret = -ENOBUFS; - goto nobufs; - -nobufs_unlock_obj: - spin_unlock(&cookie->stores_lock); - spin_unlock(&object->lock); -nobufs: - spin_unlock(&cookie->lock); - radix_tree_preload_end(); - fscache_put_operation(&op->op); - if (wake_cookie) - __fscache_wake_unused_cookie(cookie); - fscache_stat(&fscache_n_stores_nobufs); - _leave(" = -ENOBUFS"); - return -ENOBUFS; - -nomem_free: - fscache_put_operation(&op->op); -nomem: - fscache_stat(&fscache_n_stores_oom); - _leave(" = -ENOMEM"); - return -ENOMEM; -} -EXPORT_SYMBOL(__fscache_write_page); - -/* - * remove a page from the cache - */ -void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page) -{ - struct fscache_object *object; - - _enter(",%p", page); - - ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX); - ASSERTCMP(page, !=, NULL); - - fscache_stat(&fscache_n_uncaches); - - /* cache withdrawal may beat us to it */ - if (!PageFsCache(page)) - goto done; - - trace_fscache_page(cookie, page, fscache_page_uncache); - - /* get the object */ - spin_lock(&cookie->lock); - - if (hlist_empty(&cookie->backing_objects)) { - ClearPageFsCache(page); - goto done_unlock; - } - - object = hlist_entry(cookie->backing_objects.first, - struct fscache_object, cookie_link); - - /* there might now be stuff on disk we could read */ - clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags); - - /* only invoke the cache backend if we managed to mark the page - * uncached here; this deals with synchronisation vs withdrawal */ - if (TestClearPageFsCache(page) && - object->cache->ops->uncache_page) { - /* the cache backend releases the cookie lock */ - fscache_stat(&fscache_n_cop_uncache_page); - object->cache->ops->uncache_page(object, page); - fscache_stat_d(&fscache_n_cop_uncache_page); - goto done; - } - -done_unlock: - spin_unlock(&cookie->lock); -done: - _leave(""); -} -EXPORT_SYMBOL(__fscache_uncache_page); - -/** - * fscache_mark_page_cached - Mark a page as being cached - * @op: The retrieval op pages are being marked for - * @page: The page to be marked - * - * Mark a netfs page as being cached. After this is called, the netfs - * must call fscache_uncache_page() to remove the mark. - */ -void fscache_mark_page_cached(struct fscache_retrieval *op, struct page *page) -{ - struct fscache_cookie *cookie = op->op.object->cookie; - -#ifdef CONFIG_FSCACHE_STATS - atomic_inc(&fscache_n_marks); -#endif - - trace_fscache_page(cookie, page, fscache_page_cached); - - _debug("- mark %p{%lx}", page, page->index); - if (TestSetPageFsCache(page)) { - static bool once_only; - if (!once_only) { - once_only = true; - pr_warn("Cookie type %s marked page %lx multiple times\n", - cookie->def->name, page->index); - } - } - - if (cookie->def->mark_page_cached) - cookie->def->mark_page_cached(cookie->netfs_data, - op->mapping, page); -} -EXPORT_SYMBOL(fscache_mark_page_cached); - -/** - * fscache_mark_pages_cached - Mark pages as being cached - * @op: The retrieval op pages are being marked for - * @pagevec: The pages to be marked - * - * Mark a bunch of netfs pages as being cached. After this is called, - * the netfs must call fscache_uncache_page() to remove the mark. - */ -void fscache_mark_pages_cached(struct fscache_retrieval *op, - struct pagevec *pagevec) -{ - unsigned long loop; - - for (loop = 0; loop < pagevec->nr; loop++) - fscache_mark_page_cached(op, pagevec->pages[loop]); - - pagevec_reinit(pagevec); -} -EXPORT_SYMBOL(fscache_mark_pages_cached); - -/* - * Uncache all the pages in an inode that are marked PG_fscache, assuming them - * to be associated with the given cookie. - */ -void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, - struct inode *inode) -{ - struct address_space *mapping = inode->i_mapping; - struct pagevec pvec; - pgoff_t next; - int i; - - _enter("%p,%p", cookie, inode); - - if (!mapping || mapping->nrpages == 0) { - _leave(" [no pages]"); - return; - } - - pagevec_init(&pvec); - next = 0; - do { - if (!pagevec_lookup(&pvec, mapping, &next)) - break; - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - if (PageFsCache(page)) { - __fscache_wait_on_page_write(cookie, page); - __fscache_uncache_page(cookie, page); - } - } - pagevec_release(&pvec); - cond_resched(); - } while (next); - - _leave(""); -} -EXPORT_SYMBOL(__fscache_uncache_all_inode_pages); diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c deleted file mode 100644 index 061df8f61ffc..000000000000 --- a/fs/fscache/proc.c +++ /dev/null @@ -1,71 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache statistics viewing interface - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL OPERATION -#include -#include -#include -#include "internal.h" - -/* - * initialise the /proc/fs/fscache/ directory - */ -int __init fscache_proc_init(void) -{ - _enter(""); - - if (!proc_mkdir("fs/fscache", NULL)) - goto error_dir; - - if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL, - &fscache_cookies_seq_ops)) - goto error_cookies; - -#ifdef CONFIG_FSCACHE_STATS - if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, - fscache_stats_show)) - goto error_stats; -#endif - -#ifdef CONFIG_FSCACHE_OBJECT_LIST - if (!proc_create("fs/fscache/objects", S_IFREG | 0444, NULL, - &fscache_objlist_proc_ops)) - goto error_objects; -#endif - - _leave(" = 0"); - return 0; - -#ifdef CONFIG_FSCACHE_OBJECT_LIST -error_objects: -#endif -#ifdef CONFIG_FSCACHE_STATS - remove_proc_entry("fs/fscache/stats", NULL); -error_stats: -#endif - remove_proc_entry("fs/fscache/cookies", NULL); -error_cookies: - remove_proc_entry("fs/fscache", NULL); -error_dir: - _leave(" = -ENOMEM"); - return -ENOMEM; -} - -/* - * clean up the /proc/fs/fscache/ directory - */ -void fscache_proc_cleanup(void) -{ -#ifdef CONFIG_FSCACHE_OBJECT_LIST - remove_proc_entry("fs/fscache/objects", NULL); -#endif -#ifdef CONFIG_FSCACHE_STATS - remove_proc_entry("fs/fscache/stats", NULL); -#endif - remove_proc_entry("fs/fscache/cookies", NULL); - remove_proc_entry("fs/fscache", NULL); -} diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c deleted file mode 100644 index a7c3ed89a3e0..000000000000 --- a/fs/fscache/stats.c +++ /dev/null @@ -1,283 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* FS-Cache statistics - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#define FSCACHE_DEBUG_LEVEL THREAD -#include -#include -#include -#include "internal.h" - -/* - * operation counters - */ -atomic_t fscache_n_op_pend; -atomic_t fscache_n_op_run; -atomic_t fscache_n_op_enqueue; -atomic_t fscache_n_op_deferred_release; -atomic_t fscache_n_op_initialised; -atomic_t fscache_n_op_release; -atomic_t fscache_n_op_gc; -atomic_t fscache_n_op_cancelled; -atomic_t fscache_n_op_rejected; - -atomic_t fscache_n_attr_changed; -atomic_t fscache_n_attr_changed_ok; -atomic_t fscache_n_attr_changed_nobufs; -atomic_t fscache_n_attr_changed_nomem; -atomic_t fscache_n_attr_changed_calls; - -atomic_t fscache_n_allocs; -atomic_t fscache_n_allocs_ok; -atomic_t fscache_n_allocs_wait; -atomic_t fscache_n_allocs_nobufs; -atomic_t fscache_n_allocs_intr; -atomic_t fscache_n_allocs_object_dead; -atomic_t fscache_n_alloc_ops; -atomic_t fscache_n_alloc_op_waits; - -atomic_t fscache_n_retrievals; -atomic_t fscache_n_retrievals_ok; -atomic_t fscache_n_retrievals_wait; -atomic_t fscache_n_retrievals_nodata; -atomic_t fscache_n_retrievals_nobufs; -atomic_t fscache_n_retrievals_intr; -atomic_t fscache_n_retrievals_nomem; -atomic_t fscache_n_retrievals_object_dead; -atomic_t fscache_n_retrieval_ops; -atomic_t fscache_n_retrieval_op_waits; - -atomic_t fscache_n_stores; -atomic_t fscache_n_stores_ok; -atomic_t fscache_n_stores_again; -atomic_t fscache_n_stores_nobufs; -atomic_t fscache_n_stores_oom; -atomic_t fscache_n_store_ops; -atomic_t fscache_n_store_calls; -atomic_t fscache_n_store_pages; -atomic_t fscache_n_store_radix_deletes; -atomic_t fscache_n_store_pages_over_limit; - -atomic_t fscache_n_store_vmscan_not_storing; -atomic_t fscache_n_store_vmscan_gone; -atomic_t fscache_n_store_vmscan_busy; -atomic_t fscache_n_store_vmscan_cancelled; -atomic_t fscache_n_store_vmscan_wait; - -atomic_t fscache_n_marks; -atomic_t fscache_n_uncaches; - -atomic_t fscache_n_acquires; -atomic_t fscache_n_acquires_null; -atomic_t fscache_n_acquires_no_cache; -atomic_t fscache_n_acquires_ok; -atomic_t fscache_n_acquires_nobufs; -atomic_t fscache_n_acquires_oom; - -atomic_t fscache_n_invalidates; -atomic_t fscache_n_invalidates_run; - -atomic_t fscache_n_updates; -atomic_t fscache_n_updates_null; -atomic_t fscache_n_updates_run; - -atomic_t fscache_n_relinquishes; -atomic_t fscache_n_relinquishes_null; -atomic_t fscache_n_relinquishes_waitcrt; -atomic_t fscache_n_relinquishes_retire; - -atomic_t fscache_n_cookie_index; -atomic_t fscache_n_cookie_data; -atomic_t fscache_n_cookie_special; - -atomic_t fscache_n_object_alloc; -atomic_t fscache_n_object_no_alloc; -atomic_t fscache_n_object_lookups; -atomic_t fscache_n_object_lookups_negative; -atomic_t fscache_n_object_lookups_positive; -atomic_t fscache_n_object_lookups_timed_out; -atomic_t fscache_n_object_created; -atomic_t fscache_n_object_avail; -atomic_t fscache_n_object_dead; - -atomic_t fscache_n_checkaux_none; -atomic_t fscache_n_checkaux_okay; -atomic_t fscache_n_checkaux_update; -atomic_t fscache_n_checkaux_obsolete; - -atomic_t fscache_n_cop_alloc_object; -atomic_t fscache_n_cop_lookup_object; -atomic_t fscache_n_cop_lookup_complete; -atomic_t fscache_n_cop_grab_object; -atomic_t fscache_n_cop_invalidate_object; -atomic_t fscache_n_cop_update_object; -atomic_t fscache_n_cop_drop_object; -atomic_t fscache_n_cop_put_object; -atomic_t fscache_n_cop_sync_cache; -atomic_t fscache_n_cop_attr_changed; -atomic_t fscache_n_cop_read_or_alloc_page; -atomic_t fscache_n_cop_read_or_alloc_pages; -atomic_t fscache_n_cop_allocate_page; -atomic_t fscache_n_cop_allocate_pages; -atomic_t fscache_n_cop_write_page; -atomic_t fscache_n_cop_uncache_page; -atomic_t fscache_n_cop_dissociate_pages; - -atomic_t fscache_n_cache_no_space_reject; -atomic_t fscache_n_cache_stale_objects; -atomic_t fscache_n_cache_retired_objects; -atomic_t fscache_n_cache_culled_objects; - -/* - * display the general statistics - */ -int fscache_stats_show(struct seq_file *m, void *v) -{ - seq_puts(m, "FS-Cache statistics\n"); - - seq_printf(m, "Cookies: idx=%u dat=%u spc=%u\n", - atomic_read(&fscache_n_cookie_index), - atomic_read(&fscache_n_cookie_data), - atomic_read(&fscache_n_cookie_special)); - - seq_printf(m, "Objects: alc=%u nal=%u avl=%u ded=%u\n", - atomic_read(&fscache_n_object_alloc), - atomic_read(&fscache_n_object_no_alloc), - atomic_read(&fscache_n_object_avail), - atomic_read(&fscache_n_object_dead)); - seq_printf(m, "ChkAux : non=%u ok=%u upd=%u obs=%u\n", - atomic_read(&fscache_n_checkaux_none), - atomic_read(&fscache_n_checkaux_okay), - atomic_read(&fscache_n_checkaux_update), - atomic_read(&fscache_n_checkaux_obsolete)); - - seq_printf(m, "Pages : mrk=%u unc=%u\n", - atomic_read(&fscache_n_marks), - atomic_read(&fscache_n_uncaches)); - - seq_printf(m, "Acquire: n=%u nul=%u noc=%u ok=%u nbf=%u" - " oom=%u\n", - atomic_read(&fscache_n_acquires), - atomic_read(&fscache_n_acquires_null), - atomic_read(&fscache_n_acquires_no_cache), - atomic_read(&fscache_n_acquires_ok), - atomic_read(&fscache_n_acquires_nobufs), - atomic_read(&fscache_n_acquires_oom)); - - seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u tmo=%u\n", - atomic_read(&fscache_n_object_lookups), - atomic_read(&fscache_n_object_lookups_negative), - atomic_read(&fscache_n_object_lookups_positive), - atomic_read(&fscache_n_object_created), - atomic_read(&fscache_n_object_lookups_timed_out)); - - seq_printf(m, "Invals : n=%u run=%u\n", - atomic_read(&fscache_n_invalidates), - atomic_read(&fscache_n_invalidates_run)); - - seq_printf(m, "Updates: n=%u nul=%u run=%u\n", - atomic_read(&fscache_n_updates), - atomic_read(&fscache_n_updates_null), - atomic_read(&fscache_n_updates_run)); - - seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u rtr=%u\n", - atomic_read(&fscache_n_relinquishes), - atomic_read(&fscache_n_relinquishes_null), - atomic_read(&fscache_n_relinquishes_waitcrt), - atomic_read(&fscache_n_relinquishes_retire)); - - seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n", - atomic_read(&fscache_n_attr_changed), - atomic_read(&fscache_n_attr_changed_ok), - atomic_read(&fscache_n_attr_changed_nobufs), - atomic_read(&fscache_n_attr_changed_nomem), - atomic_read(&fscache_n_attr_changed_calls)); - - seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n", - atomic_read(&fscache_n_allocs), - atomic_read(&fscache_n_allocs_ok), - atomic_read(&fscache_n_allocs_wait), - atomic_read(&fscache_n_allocs_nobufs), - atomic_read(&fscache_n_allocs_intr)); - seq_printf(m, "Allocs : ops=%u owt=%u abt=%u\n", - atomic_read(&fscache_n_alloc_ops), - atomic_read(&fscache_n_alloc_op_waits), - atomic_read(&fscache_n_allocs_object_dead)); - - seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u" - " int=%u oom=%u\n", - atomic_read(&fscache_n_retrievals), - atomic_read(&fscache_n_retrievals_ok), - atomic_read(&fscache_n_retrievals_wait), - atomic_read(&fscache_n_retrievals_nodata), - atomic_read(&fscache_n_retrievals_nobufs), - atomic_read(&fscache_n_retrievals_intr), - atomic_read(&fscache_n_retrievals_nomem)); - seq_printf(m, "Retrvls: ops=%u owt=%u abt=%u\n", - atomic_read(&fscache_n_retrieval_ops), - atomic_read(&fscache_n_retrieval_op_waits), - atomic_read(&fscache_n_retrievals_object_dead)); - - seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n", - atomic_read(&fscache_n_stores), - atomic_read(&fscache_n_stores_ok), - atomic_read(&fscache_n_stores_again), - atomic_read(&fscache_n_stores_nobufs), - atomic_read(&fscache_n_stores_oom)); - seq_printf(m, "Stores : ops=%u run=%u pgs=%u rxd=%u olm=%u\n", - atomic_read(&fscache_n_store_ops), - atomic_read(&fscache_n_store_calls), - atomic_read(&fscache_n_store_pages), - atomic_read(&fscache_n_store_radix_deletes), - atomic_read(&fscache_n_store_pages_over_limit)); - - seq_printf(m, "VmScan : nos=%u gon=%u bsy=%u can=%u wt=%u\n", - atomic_read(&fscache_n_store_vmscan_not_storing), - atomic_read(&fscache_n_store_vmscan_gone), - atomic_read(&fscache_n_store_vmscan_busy), - atomic_read(&fscache_n_store_vmscan_cancelled), - atomic_read(&fscache_n_store_vmscan_wait)); - - seq_printf(m, "Ops : pend=%u run=%u enq=%u can=%u rej=%u\n", - atomic_read(&fscache_n_op_pend), - atomic_read(&fscache_n_op_run), - atomic_read(&fscache_n_op_enqueue), - atomic_read(&fscache_n_op_cancelled), - atomic_read(&fscache_n_op_rejected)); - seq_printf(m, "Ops : ini=%u dfr=%u rel=%u gc=%u\n", - atomic_read(&fscache_n_op_initialised), - atomic_read(&fscache_n_op_deferred_release), - atomic_read(&fscache_n_op_release), - atomic_read(&fscache_n_op_gc)); - - seq_printf(m, "CacheOp: alo=%d luo=%d luc=%d gro=%d\n", - atomic_read(&fscache_n_cop_alloc_object), - atomic_read(&fscache_n_cop_lookup_object), - atomic_read(&fscache_n_cop_lookup_complete), - atomic_read(&fscache_n_cop_grab_object)); - seq_printf(m, "CacheOp: inv=%d upo=%d dro=%d pto=%d atc=%d syn=%d\n", - atomic_read(&fscache_n_cop_invalidate_object), - atomic_read(&fscache_n_cop_update_object), - atomic_read(&fscache_n_cop_drop_object), - atomic_read(&fscache_n_cop_put_object), - atomic_read(&fscache_n_cop_attr_changed), - atomic_read(&fscache_n_cop_sync_cache)); - seq_printf(m, "CacheOp: rap=%d ras=%d alp=%d als=%d wrp=%d ucp=%d dsp=%d\n", - atomic_read(&fscache_n_cop_read_or_alloc_page), - atomic_read(&fscache_n_cop_read_or_alloc_pages), - atomic_read(&fscache_n_cop_allocate_page), - atomic_read(&fscache_n_cop_allocate_pages), - atomic_read(&fscache_n_cop_write_page), - atomic_read(&fscache_n_cop_uncache_page), - atomic_read(&fscache_n_cop_dissociate_pages)); - seq_printf(m, "CacheEv: nsp=%d stl=%d rtr=%d cul=%d\n", - atomic_read(&fscache_n_cache_no_space_reject), - atomic_read(&fscache_n_cache_stale_objects), - atomic_read(&fscache_n_cache_retired_objects), - atomic_read(&fscache_n_cache_culled_objects)); - netfs_stats_show(m); - return 0; -} diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 8d39491c5f9f..47f21a53ac4b 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching backing cache interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -15,551 +15,5 @@ #define _LINUX_FSCACHE_CACHE_H #include -#include -#include - -#define NR_MAXCACHES BITS_PER_LONG - -struct fscache_cache; -struct fscache_cache_ops; -struct fscache_object; -struct fscache_operation; - -enum fscache_obj_ref_trace { - fscache_obj_get_add_to_deps, - fscache_obj_get_queue, - fscache_obj_put_alloc_fail, - fscache_obj_put_attach_fail, - fscache_obj_put_drop_obj, - fscache_obj_put_enq_dep, - fscache_obj_put_queue, - fscache_obj_put_work, - fscache_obj_ref__nr_traces -}; - -/* - * cache tag definition - */ -struct fscache_cache_tag { - struct list_head link; - struct fscache_cache *cache; /* cache referred to by this tag */ - unsigned long flags; -#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */ - atomic_t usage; - char name[]; /* tag name */ -}; - -/* - * cache definition - */ -struct fscache_cache { - const struct fscache_cache_ops *ops; - struct fscache_cache_tag *tag; /* tag representing this cache */ - struct kobject *kobj; /* system representation of this cache */ - struct list_head link; /* link in list of caches */ - size_t max_index_size; /* maximum size of index data */ - char identifier[36]; /* cache label */ - - /* node management */ - struct work_struct op_gc; /* operation garbage collector */ - struct list_head object_list; /* list of data/index objects */ - struct list_head op_gc_list; /* list of ops to be deleted */ - spinlock_t object_list_lock; - spinlock_t op_gc_list_lock; - atomic_t object_count; /* no. of live objects in this cache */ - struct fscache_object *fsdef; /* object for the fsdef index */ - unsigned long flags; -#define FSCACHE_IOERROR 0 /* cache stopped on I/O error */ -#define FSCACHE_CACHE_WITHDRAWN 1 /* cache has been withdrawn */ -}; - -extern wait_queue_head_t fscache_cache_cleared_wq; - -/* - * operation to be applied to a cache object - * - retrieval initiation operations are done in the context of the process - * that issued them, and not in an async thread pool - */ -typedef void (*fscache_operation_release_t)(struct fscache_operation *op); -typedef void (*fscache_operation_processor_t)(struct fscache_operation *op); -typedef void (*fscache_operation_cancel_t)(struct fscache_operation *op); - -enum fscache_operation_state { - FSCACHE_OP_ST_BLANK, /* Op is not yet submitted */ - FSCACHE_OP_ST_INITIALISED, /* Op is initialised */ - FSCACHE_OP_ST_PENDING, /* Op is blocked from running */ - FSCACHE_OP_ST_IN_PROGRESS, /* Op is in progress */ - FSCACHE_OP_ST_COMPLETE, /* Op is complete */ - FSCACHE_OP_ST_CANCELLED, /* Op has been cancelled */ - FSCACHE_OP_ST_DEAD /* Op is now dead */ -}; - -struct fscache_operation { - struct work_struct work; /* record for async ops */ - struct list_head pend_link; /* link in object->pending_ops */ - struct fscache_object *object; /* object to be operated upon */ - - unsigned long flags; -#define FSCACHE_OP_TYPE 0x000f /* operation type */ -#define FSCACHE_OP_ASYNC 0x0001 /* - async op, processor may sleep for disk */ -#define FSCACHE_OP_MYTHREAD 0x0002 /* - processing is done be issuing thread, not pool */ -#define FSCACHE_OP_WAITING 4 /* cleared when op is woken */ -#define FSCACHE_OP_EXCLUSIVE 5 /* exclusive op, other ops must wait */ -#define FSCACHE_OP_DEC_READ_CNT 6 /* decrement object->n_reads on destruction */ -#define FSCACHE_OP_UNUSE_COOKIE 7 /* call fscache_unuse_cookie() on completion */ -#define FSCACHE_OP_KEEP_FLAGS 0x00f0 /* flags to keep when repurposing an op */ - - enum fscache_operation_state state; - atomic_t usage; - unsigned debug_id; /* debugging ID */ - - /* operation processor callback - * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform - * the op in a non-pool thread */ - fscache_operation_processor_t processor; - - /* Operation cancellation cleanup (optional) */ - fscache_operation_cancel_t cancel; - - /* operation releaser */ - fscache_operation_release_t release; -}; - -extern atomic_t fscache_op_debug_id; -extern void fscache_op_work_func(struct work_struct *work); - -extern void fscache_enqueue_operation(struct fscache_operation *); -extern void fscache_op_complete(struct fscache_operation *, bool); -extern void fscache_put_operation(struct fscache_operation *); -extern void fscache_operation_init(struct fscache_cookie *, - struct fscache_operation *, - fscache_operation_processor_t, - fscache_operation_cancel_t, - fscache_operation_release_t); - -/* - * data read operation - */ -struct fscache_retrieval { - struct fscache_operation op; - struct fscache_cookie *cookie; /* The netfs cookie */ - struct address_space *mapping; /* netfs pages */ - fscache_rw_complete_t end_io_func; /* function to call on I/O completion */ - void *context; /* netfs read context (pinned) */ - struct list_head to_do; /* list of things to be done by the backend */ - atomic_t n_pages; /* number of pages to be retrieved */ -}; - -typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op, - struct page *page, - gfp_t gfp); - -typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op, - struct list_head *pages, - unsigned *nr_pages, - gfp_t gfp); - -/** - * fscache_get_retrieval - Get an extra reference on a retrieval operation - * @op: The retrieval operation to get a reference on - * - * Get an extra reference on a retrieval operation. - */ -static inline -struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op) -{ - atomic_inc(&op->op.usage); - return op; -} - -/** - * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing - * @op: The retrieval operation affected - * - * Enqueue a retrieval operation for processing by the FS-Cache thread pool. - */ -static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op) -{ - fscache_enqueue_operation(&op->op); -} - -/** - * fscache_retrieval_complete - Record (partial) completion of a retrieval - * @op: The retrieval operation affected - * @n_pages: The number of pages to account for - */ -static inline void fscache_retrieval_complete(struct fscache_retrieval *op, - int n_pages) -{ - if (atomic_sub_return_relaxed(n_pages, &op->n_pages) <= 0) - fscache_op_complete(&op->op, false); -} - -/** - * fscache_put_retrieval - Drop a reference to a retrieval operation - * @op: The retrieval operation affected - * - * Drop a reference to a retrieval operation. - */ -static inline void fscache_put_retrieval(struct fscache_retrieval *op) -{ - fscache_put_operation(&op->op); -} - -/* - * cached page storage work item - * - used to do three things: - * - batch writes to the cache - * - do cache writes asynchronously - * - defer writes until cache object lookup completion - */ -struct fscache_storage { - struct fscache_operation op; - pgoff_t store_limit; /* don't write more than this */ -}; - -/* - * cache operations - */ -struct fscache_cache_ops { - /* name of cache provider */ - const char *name; - - /* allocate an object record for a cookie */ - struct fscache_object *(*alloc_object)(struct fscache_cache *cache, - struct fscache_cookie *cookie); - - /* look up the object for a cookie - * - return -ETIMEDOUT to be requeued - */ - int (*lookup_object)(struct fscache_object *object); - - /* finished looking up */ - void (*lookup_complete)(struct fscache_object *object); - - /* increment the usage count on this object (may fail if unmounting) */ - struct fscache_object *(*grab_object)(struct fscache_object *object, - enum fscache_obj_ref_trace why); - - /* pin an object in the cache */ - int (*pin_object)(struct fscache_object *object); - - /* unpin an object in the cache */ - void (*unpin_object)(struct fscache_object *object); - - /* check the consistency between the backing cache and the FS-Cache - * cookie */ - int (*check_consistency)(struct fscache_operation *op); - - /* store the updated auxiliary data on an object */ - void (*update_object)(struct fscache_object *object); - - /* Invalidate an object */ - void (*invalidate_object)(struct fscache_operation *op); - - /* discard the resources pinned by an object and effect retirement if - * necessary */ - void (*drop_object)(struct fscache_object *object); - - /* dispose of a reference to an object */ - void (*put_object)(struct fscache_object *object, - enum fscache_obj_ref_trace why); - - /* sync a cache */ - void (*sync_cache)(struct fscache_cache *cache); - - /* notification that the attributes of a non-index object (such as - * i_size) have changed */ - int (*attr_changed)(struct fscache_object *object); - - /* reserve space for an object's data and associated metadata */ - int (*reserve_space)(struct fscache_object *object, loff_t i_size); - - /* request a backing block for a page be read or allocated in the - * cache */ - fscache_page_retrieval_func_t read_or_alloc_page; - - /* request backing blocks for a list of pages be read or allocated in - * the cache */ - fscache_pages_retrieval_func_t read_or_alloc_pages; - - /* request a backing block for a page be allocated in the cache so that - * it can be written directly */ - fscache_page_retrieval_func_t allocate_page; - - /* request backing blocks for pages be allocated in the cache so that - * they can be written directly */ - fscache_pages_retrieval_func_t allocate_pages; - - /* write a page to its backing block in the cache */ - int (*write_page)(struct fscache_storage *op, struct page *page); - - /* detach backing block from a page (optional) - * - must release the cookie lock before returning - * - may sleep - */ - void (*uncache_page)(struct fscache_object *object, - struct page *page); - - /* dissociate a cache from all the pages it was backing */ - void (*dissociate_pages)(struct fscache_cache *cache); - - /* Begin a read operation for the netfs lib */ - int (*begin_read_operation)(struct netfs_read_request *rreq, - struct fscache_retrieval *op); -}; - -extern struct fscache_cookie fscache_fsdef_index; - -/* - * Event list for fscache_object::{event_mask,events} - */ -enum { - FSCACHE_OBJECT_EV_NEW_CHILD, /* T if object has a new child */ - FSCACHE_OBJECT_EV_PARENT_READY, /* T if object's parent is ready */ - FSCACHE_OBJECT_EV_UPDATE, /* T if object should be updated */ - FSCACHE_OBJECT_EV_INVALIDATE, /* T if cache requested object invalidation */ - FSCACHE_OBJECT_EV_CLEARED, /* T if accessors all gone */ - FSCACHE_OBJECT_EV_ERROR, /* T if fatal error occurred during processing */ - FSCACHE_OBJECT_EV_KILL, /* T if netfs relinquished or cache withdrew object */ - NR_FSCACHE_OBJECT_EVENTS -}; - -#define FSCACHE_OBJECT_EVENTS_MASK ((1UL << NR_FSCACHE_OBJECT_EVENTS) - 1) - -/* - * States for object state machine. - */ -struct fscache_transition { - unsigned long events; - const struct fscache_state *transit_to; -}; - -struct fscache_state { - char name[24]; - char short_name[8]; - const struct fscache_state *(*work)(struct fscache_object *object, - int event); - const struct fscache_transition transitions[]; -}; - -/* - * on-disk cache file or index handle - */ -struct fscache_object { - const struct fscache_state *state; /* Object state machine state */ - const struct fscache_transition *oob_table; /* OOB state transition table */ - int debug_id; /* debugging ID */ - int n_children; /* number of child objects */ - int n_ops; /* number of extant ops on object */ - int n_obj_ops; /* number of object ops outstanding on object */ - int n_in_progress; /* number of ops in progress */ - int n_exclusive; /* number of exclusive ops queued or in progress */ - atomic_t n_reads; /* number of read ops in progress */ - spinlock_t lock; /* state and operations lock */ - - unsigned long lookup_jif; /* time at which lookup started */ - unsigned long oob_event_mask; /* OOB events this object is interested in */ - unsigned long event_mask; /* events this object is interested in */ - unsigned long events; /* events to be processed by this object - * (order is important - using fls) */ - - unsigned long flags; -#define FSCACHE_OBJECT_LOCK 0 /* T if object is busy being processed */ -#define FSCACHE_OBJECT_PENDING_WRITE 1 /* T if object has pending write */ -#define FSCACHE_OBJECT_WAITING 2 /* T if object is waiting on its parent */ -#define FSCACHE_OBJECT_IS_LIVE 3 /* T if object is not withdrawn or relinquished */ -#define FSCACHE_OBJECT_IS_LOOKED_UP 4 /* T if object has been looked up */ -#define FSCACHE_OBJECT_IS_AVAILABLE 5 /* T if object has become active */ -#define FSCACHE_OBJECT_RETIRED 6 /* T if object was retired on relinquishment */ -#define FSCACHE_OBJECT_KILLED_BY_CACHE 7 /* T if object was killed by the cache */ -#define FSCACHE_OBJECT_RUN_AFTER_DEAD 8 /* T if object has been dispatched after death */ - - struct list_head cache_link; /* link in cache->object_list */ - struct hlist_node cookie_link; /* link in cookie->backing_objects */ - struct fscache_cache *cache; /* cache that supplied this object */ - struct fscache_cookie *cookie; /* netfs's file/index object */ - struct fscache_object *parent; /* parent object */ - struct work_struct work; /* attention scheduling record */ - struct list_head dependents; /* FIFO of dependent objects */ - struct list_head dep_link; /* link in parent's dependents list */ - struct list_head pending_ops; /* unstarted operations on this object */ - pgoff_t store_limit; /* current storage limit */ - loff_t store_limit_l; /* current storage limit */ -}; - -extern void fscache_object_init(struct fscache_object *, struct fscache_cookie *, - struct fscache_cache *); -extern void fscache_object_destroy(struct fscache_object *); - -extern void fscache_object_lookup_negative(struct fscache_object *object); -extern void fscache_obtained_object(struct fscache_object *object); - -static inline bool fscache_object_is_live(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_LIVE, &object->flags); -} - -static inline bool fscache_object_is_dying(struct fscache_object *object) -{ - return !fscache_object_is_live(object); -} - -static inline bool fscache_object_is_available(struct fscache_object *object) -{ - return test_bit(FSCACHE_OBJECT_IS_AVAILABLE, &object->flags); -} - -static inline bool fscache_cache_is_broken(struct fscache_object *object) -{ - return test_bit(FSCACHE_IOERROR, &object->cache->flags); -} - -static inline bool fscache_object_is_active(struct fscache_object *object) -{ - return fscache_object_is_available(object) && - fscache_object_is_live(object) && - !fscache_cache_is_broken(object); -} - -/** - * fscache_object_destroyed - Note destruction of an object in a cache - * @cache: The cache from which the object came - * - * Note the destruction and deallocation of an object record in a cache. - */ -static inline void fscache_object_destroyed(struct fscache_cache *cache) -{ - if (atomic_dec_and_test(&cache->object_count)) - wake_up_all(&fscache_cache_cleared_wq); -} - -/** - * fscache_object_lookup_error - Note an object encountered an error - * @object: The object on which the error was encountered - * - * Note that an object encountered a fatal error (usually an I/O error) and - * that it should be withdrawn as soon as possible. - */ -static inline void fscache_object_lookup_error(struct fscache_object *object) -{ - set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events); -} - -/** - * fscache_set_store_limit - Set the maximum size to be stored in an object - * @object: The object to set the maximum on - * @i_size: The limit to set in bytes - * - * Set the maximum size an object is permitted to reach, implying the highest - * byte that may be written. Intended to be called by the attr_changed() op. - * - * See Documentation/filesystems/caching/backend-api.rst for a complete - * description. - */ -static inline -void fscache_set_store_limit(struct fscache_object *object, loff_t i_size) -{ - object->store_limit_l = i_size; - object->store_limit = i_size >> PAGE_SHIFT; - if (i_size & ~PAGE_MASK) - object->store_limit++; -} - -/** - * fscache_end_io - End a retrieval operation on a page - * @op: The FS-Cache operation covering the retrieval - * @page: The page that was to be fetched - * @error: The error code (0 if successful) - * - * Note the end of an operation to retrieve a page, as covered by a particular - * operation record. - */ -static inline void fscache_end_io(struct fscache_retrieval *op, - struct page *page, int error) -{ - op->end_io_func(page, op->context, error); -} - -static inline void __fscache_use_cookie(struct fscache_cookie *cookie) -{ - atomic_inc(&cookie->n_active); -} - -/** - * fscache_use_cookie - Request usage of cookie attached to an object - * @object: Object description - * - * Request usage of the cookie attached to an object. NULL is returned if the - * relinquishment had reduced the cookie usage count to 0. - */ -static inline bool fscache_use_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - return atomic_inc_not_zero(&cookie->n_active) != 0; -} - -static inline bool __fscache_unuse_cookie(struct fscache_cookie *cookie) -{ - return atomic_dec_and_test(&cookie->n_active); -} - -static inline void __fscache_wake_unused_cookie(struct fscache_cookie *cookie) -{ - wake_up_var(&cookie->n_active); -} - -/** - * fscache_unuse_cookie - Cease usage of cookie attached to an object - * @object: Object description - * - * Cease usage of the cookie attached to an object. When the users count - * reaches zero then the cookie relinquishment will be permitted to proceed. - */ -static inline void fscache_unuse_cookie(struct fscache_object *object) -{ - struct fscache_cookie *cookie = object->cookie; - if (__fscache_unuse_cookie(cookie)) - __fscache_wake_unused_cookie(cookie); -} - -/* - * out-of-line cache backend functions - */ -extern __printf(3, 4) -void fscache_init_cache(struct fscache_cache *cache, - const struct fscache_cache_ops *ops, - const char *idfmt, ...); - -extern int fscache_add_cache(struct fscache_cache *cache, - struct fscache_object *fsdef, - const char *tagname); -extern void fscache_withdraw_cache(struct fscache_cache *cache); - -extern void fscache_io_error(struct fscache_cache *cache); - -extern void fscache_mark_page_cached(struct fscache_retrieval *op, - struct page *page); - -extern void fscache_mark_pages_cached(struct fscache_retrieval *op, - struct pagevec *pagevec); - -extern bool fscache_object_sleep_till_congested(signed long *timeoutp); - -extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object, - const void *data, - uint16_t datalen, - loff_t object_size); - -extern void fscache_object_retrying_stale(struct fscache_object *object); - -enum fscache_why_object_killed { - FSCACHE_OBJECT_IS_STALE, - FSCACHE_OBJECT_NO_SPACE, - FSCACHE_OBJECT_WAS_RETIRED, - FSCACHE_OBJECT_WAS_CULLED, -}; -extern void fscache_object_mark_killed(struct fscache_object *object, - enum fscache_why_object_killed why); #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 3b2282c157f7..0364a4ca16f6 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -15,861 +15,14 @@ #define _LINUX_FSCACHE_H #include -#include -#include -#include -#include #include #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) -#define fscache_available() (1) #define fscache_cookie_valid(cookie) (cookie) +#define fscache_cookie_enabled(cookie) (cookie) #else -#define fscache_available() (0) #define fscache_cookie_valid(cookie) (0) +#define fscache_cookie_enabled(cookie) (0) #endif - -/* pattern used to fill dead space in an index entry */ -#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79 - -struct pagevec; -struct fscache_cache_tag; -struct fscache_cookie; -struct fscache_netfs; -struct netfs_read_request; - -typedef void (*fscache_rw_complete_t)(struct page *page, - void *context, - int error); - -/* result of index entry consultation */ -enum fscache_checkaux { - FSCACHE_CHECKAUX_OKAY, /* entry okay as is */ - FSCACHE_CHECKAUX_NEEDS_UPDATE, /* entry requires update */ - FSCACHE_CHECKAUX_OBSOLETE, /* entry requires deletion */ -}; - -/* - * fscache cookie definition - */ -struct fscache_cookie_def { - /* name of cookie type */ - char name[16]; - - /* cookie type */ - uint8_t type; -#define FSCACHE_COOKIE_TYPE_INDEX 0 -#define FSCACHE_COOKIE_TYPE_DATAFILE 1 - - /* select the cache into which to insert an entry in this index - * - optional - * - should return a cache identifier or NULL to cause the cache to be - * inherited from the parent if possible or the first cache picked - * for a non-index file if not - */ - struct fscache_cache_tag *(*select_cache)( - const void *parent_netfs_data, - const void *cookie_netfs_data); - - /* consult the netfs about the state of an object - * - this function can be absent if the index carries no state data - * - the netfs data from the cookie being used as the target is - * presented, as is the auxiliary data and the object size - */ - enum fscache_checkaux (*check_aux)(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size); - - /* get an extra reference on a read context - * - this function can be absent if the completion function doesn't - * require a context - */ - void (*get_context)(void *cookie_netfs_data, void *context); - - /* release an extra reference on a read context - * - this function can be absent if the completion function doesn't - * require a context - */ - void (*put_context)(void *cookie_netfs_data, void *context); - - /* indicate page that now have cache metadata retained - * - this function should mark the specified page as now being cached - * - the page will have been marked with PG_fscache before this is - * called, so this is optional - */ - void (*mark_page_cached)(void *cookie_netfs_data, - struct address_space *mapping, - struct page *page); -}; - -/* - * fscache cached network filesystem type - * - name, version and ops must be filled in before registration - * - all other fields will be set during registration - */ -struct fscache_netfs { - uint32_t version; /* indexing version */ - const char *name; /* filesystem name */ - struct fscache_cookie *primary_index; -}; - -/* - * data file or index object cookie - * - a file will only appear in one cache - * - a request to cache a file may or may not be honoured, subject to - * constraints such as disk space - * - indices are created on disk just-in-time - */ -struct fscache_cookie { - refcount_t ref; /* number of users of this cookie */ - atomic_t n_children; /* number of children of this cookie */ - atomic_t n_active; /* number of active users of netfs ptrs */ - unsigned int debug_id; - spinlock_t lock; - spinlock_t stores_lock; /* lock on page store tree */ - struct hlist_head backing_objects; /* object(s) backing this file/index */ - const struct fscache_cookie_def *def; /* definition */ - struct fscache_cookie *parent; /* parent of this entry */ - struct hlist_bl_node hash_link; /* Link in hash table */ - struct list_head proc_link; /* Link in proc list */ - void *netfs_data; /* back pointer to netfs */ - struct radix_tree_root stores; /* pages to be stored on this cookie */ -#define FSCACHE_COOKIE_PENDING_TAG 0 /* pages tag: pending write to cache */ -#define FSCACHE_COOKIE_STORING_TAG 1 /* pages tag: writing to cache */ - - unsigned long flags; -#define FSCACHE_COOKIE_LOOKING_UP 0 /* T if non-index cookie being looked up still */ -#define FSCACHE_COOKIE_NO_DATA_YET 1 /* T if new object with no cached data yet */ -#define FSCACHE_COOKIE_UNAVAILABLE 2 /* T if cookie is unavailable (error, etc) */ -#define FSCACHE_COOKIE_INVALIDATING 3 /* T if cookie is being invalidated */ -#define FSCACHE_COOKIE_RELINQUISHED 4 /* T if cookie has been relinquished */ -#define FSCACHE_COOKIE_ENABLED 5 /* T if cookie is enabled */ -#define FSCACHE_COOKIE_ENABLEMENT_LOCK 6 /* T if cookie is being en/disabled */ -#define FSCACHE_COOKIE_AUX_UPDATED 8 /* T if the auxiliary data was updated */ -#define FSCACHE_COOKIE_ACQUIRED 9 /* T if cookie is in use */ -#define FSCACHE_COOKIE_RELINQUISHING 10 /* T if cookie is being relinquished */ - - u8 type; /* Type of object */ - u8 key_len; /* Length of index key */ - u8 aux_len; /* Length of auxiliary data */ - u32 key_hash; /* Hash of parent, type, key, len */ - union { - void *key; /* Index key */ - u8 inline_key[16]; /* - If the key is short enough */ - }; - union { - void *aux; /* Auxiliary data */ - u8 inline_aux[8]; /* - If the aux data is short enough */ - }; -}; - -static inline bool fscache_cookie_enabled(struct fscache_cookie *cookie) -{ - return fscache_cookie_valid(cookie) && test_bit(FSCACHE_COOKIE_ENABLED, &cookie->flags); -} - -/* - * slow-path functions for when there is actually caching available, and the - * netfs does actually have a valid token - * - these are not to be called directly - * - these are undefined symbols when FS-Cache is not configured and the - * optimiser takes care of not using them - */ -extern int __fscache_register_netfs(struct fscache_netfs *); -extern void __fscache_unregister_netfs(struct fscache_netfs *); -extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *); -extern void __fscache_release_cache_tag(struct fscache_cache_tag *); - -extern struct fscache_cookie *__fscache_acquire_cookie( - struct fscache_cookie *, - const struct fscache_cookie_def *, - const void *, size_t, - const void *, size_t, - void *, loff_t, bool); -extern void __fscache_relinquish_cookie(struct fscache_cookie *, const void *, bool); -extern int __fscache_check_consistency(struct fscache_cookie *, const void *); -extern void __fscache_update_cookie(struct fscache_cookie *, const void *); -extern int __fscache_attr_changed(struct fscache_cookie *); -extern void __fscache_invalidate(struct fscache_cookie *); -extern void __fscache_wait_on_invalidate(struct fscache_cookie *); - -#ifdef FSCACHE_USE_NEW_IO_API -extern int __fscache_begin_read_operation(struct netfs_read_request *, struct fscache_cookie *); -#else -extern int __fscache_read_or_alloc_page(struct fscache_cookie *, - struct page *, - fscache_rw_complete_t, - void *, - gfp_t); -extern int __fscache_read_or_alloc_pages(struct fscache_cookie *, - struct address_space *, - struct list_head *, - unsigned *, - fscache_rw_complete_t, - void *, - gfp_t); -extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t); -extern int __fscache_write_page(struct fscache_cookie *, struct page *, loff_t, gfp_t); -extern void __fscache_uncache_page(struct fscache_cookie *, struct page *); -extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *); -extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *); -extern bool __fscache_maybe_release_page(struct fscache_cookie *, struct page *, - gfp_t); -extern void __fscache_uncache_all_inode_pages(struct fscache_cookie *, - struct inode *); -extern void __fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages); -#endif /* FSCACHE_USE_NEW_IO_API */ - -extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); -extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, - bool (*)(void *), void *); - -/** - * fscache_register_netfs - Register a filesystem as desiring caching services - * @netfs: The description of the filesystem - * - * Register a filesystem as desiring caching services if they're available. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_register_netfs(struct fscache_netfs *netfs) -{ - if (fscache_available()) - return __fscache_register_netfs(netfs); - else - return 0; -} - -/** - * fscache_unregister_netfs - Indicate that a filesystem no longer desires - * caching services - * @netfs: The description of the filesystem - * - * Indicate that a filesystem no longer desires caching services for the - * moment. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_unregister_netfs(struct fscache_netfs *netfs) -{ - if (fscache_available()) - __fscache_unregister_netfs(netfs); -} - -/** - * fscache_lookup_cache_tag - Look up a cache tag - * @name: The name of the tag to search for - * - * Acquire a specific cache referral tag that can be used to select a specific - * cache in which to cache an index. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name) -{ - if (fscache_available()) - return __fscache_lookup_cache_tag(name); - else - return NULL; -} - -/** - * fscache_release_cache_tag - Release a cache tag - * @tag: The tag to release - * - * Release a reference to a cache referral tag previously looked up. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_release_cache_tag(struct fscache_cache_tag *tag) -{ - if (fscache_available()) - __fscache_release_cache_tag(tag); -} - -/** - * fscache_acquire_cookie - Acquire a cookie to represent a cache object - * @parent: The cookie that's to be the parent of this one - * @def: A description of the cache object, including callback operations - * @index_key: The index key for this cookie - * @index_key_len: Size of the index key - * @aux_data: The auxiliary data for the cookie (may be NULL) - * @aux_data_len: Size of the auxiliary data buffer - * @netfs_data: An arbitrary piece of data to be kept in the cookie to - * represent the cache object to the netfs - * @object_size: The initial size of object - * @enable: Whether or not to enable a data cookie immediately - * - * This function is used to inform FS-Cache about part of an index hierarchy - * that can be used to locate files. This is done by requesting a cookie for - * each index in the path to the file. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -struct fscache_cookie *fscache_acquire_cookie( - struct fscache_cookie *parent, - const struct fscache_cookie_def *def, - const void *index_key, - size_t index_key_len, - const void *aux_data, - size_t aux_data_len, - void *netfs_data, - loff_t object_size, - bool enable) -{ - if (fscache_cookie_valid(parent) && fscache_cookie_enabled(parent)) - return __fscache_acquire_cookie(parent, def, - index_key, index_key_len, - aux_data, aux_data_len, - netfs_data, object_size, enable); - else - return NULL; -} - -/** - * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding - * it - * @cookie: The cookie being returned - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @retire: True if the cache object the cookie represents is to be discarded - * - * This function returns a cookie to the cache, forcibly discarding the - * associated cache object if retire is set to true. The opportunity is - * provided to update the auxiliary data in the cache before the object is - * disconnected. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_relinquish_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool retire) -{ - if (fscache_cookie_valid(cookie)) - __fscache_relinquish_cookie(cookie, aux_data, retire); -} - -/** - * fscache_check_consistency - Request validation of a cache's auxiliary data - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an consistency check from fscache, which passes the request to the - * backing cache. The auxiliary data on the cookie will be updated first if - * @aux_data is set. - * - * Returns 0 if consistent and -ESTALE if inconsistent. May also - * return -ENOMEM and -ERESTARTSYS. - */ -static inline -int fscache_check_consistency(struct fscache_cookie *cookie, - const void *aux_data) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_check_consistency(cookie, aux_data); - else - return 0; -} - -/** - * fscache_update_cookie - Request that a cache object be updated - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * - * Request an update of the index data for the cache object associated with the - * cookie. The auxiliary data on the cookie will be updated first if @aux_data - * is set. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_update_cookie(cookie, aux_data); -} - -/** - * fscache_pin_cookie - Pin a data-storage cache object in its cache - * @cookie: The cookie representing the cache object - * - * Permit data-storage cache objects to be pinned in the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_pin_cookie(struct fscache_cookie *cookie) -{ - return -ENOBUFS; -} - -/** - * fscache_pin_cookie - Unpin a data-storage cache object in its cache - * @cookie: The cookie representing the cache object - * - * Permit data-storage cache objects to be unpinned from the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_unpin_cookie(struct fscache_cookie *cookie) -{ -} - -/** - * fscache_attr_changed - Notify cache that an object's attributes changed - * @cookie: The cookie representing the cache object - * - * Send a notification to the cache indicating that an object's attributes have - * changed. This includes the data size. These attributes will be obtained - * through the get_attr() cookie definition op. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_attr_changed(struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_attr_changed(cookie); - else - return -ENOBUFS; -} - -/** - * fscache_invalidate - Notify cache that an object needs invalidation - * @cookie: The cookie representing the cache object - * - * Notify the cache that an object is needs to be invalidated and that it - * should abort any retrievals or stores it is doing on the cache. The object - * is then marked non-caching until such time as the invalidation is complete. - * - * This can be called with spinlocks held. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_invalidate(struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_invalidate(cookie); -} - -/** - * fscache_wait_on_invalidate - Wait for invalidation to complete - * @cookie: The cookie representing the cache object - * - * Wait for the invalidation of an object to complete. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_wait_on_invalidate(struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_invalidate(cookie); -} - -/** - * fscache_reserve_space - Reserve data space for a cached object - * @cookie: The cookie representing the cache object - * @i_size: The amount of space to be reserved - * - * Reserve an amount of space in the cache for the cache object attached to a - * cookie so that a write to that object within the space can always be - * honoured. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size) -{ - return -ENOBUFS; -} - -#ifdef FSCACHE_USE_NEW_IO_API - -/** - * fscache_begin_read_operation - Begin a read operation for the netfs lib - * @rreq: The read request being undertaken - * @cookie: The cookie representing the cache object - * - * Begin a read operation on behalf of the netfs helper library. @rreq - * indicates the read request to which the operation state should be attached; - * @cookie indicates the cache object that will be accessed. - * - * This is intended to be called from the ->begin_cache_operation() netfs lib - * operation as implemented by the network filesystem. - * - * Returns: - * * 0 - Success - * * -ENOBUFS - No caching available - * * Other error code from the cache, such as -ENOMEM. - */ -static inline -int fscache_begin_read_operation(struct netfs_read_request *rreq, - struct fscache_cookie *cookie) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_begin_read_operation(rreq, cookie); - return -ENOBUFS; -} - -#else /* FSCACHE_USE_NEW_IO_API */ - -/** - * fscache_read_or_alloc_page - Read a page from the cache or allocate a block - * in which to store it - * @cookie: The cookie representing the cache object - * @page: The netfs page to fill if possible - * @end_io_func: The callback to invoke when and if the page is filled - * @context: An arbitrary piece of data to pass on to end_io_func() - * @gfp: The conditions under which memory allocation should be made - * - * Read a page from the cache, or if that's not possible make a potential - * one-block reservation in the cache into which the page may be stored once - * fetched from the server. - * - * If the page is not backed by the cache object, or if it there's some reason - * it can't be, -ENOBUFS will be returned and nothing more will be done for - * that page. - * - * Else, if that page is backed by the cache, a read will be initiated directly - * to the netfs's page and 0 will be returned by this function. The - * end_io_func() callback will be invoked when the operation terminates on a - * completion or failure. Note that the callback may be invoked before the - * return. - * - * Else, if the page is unbacked, -ENODATA is returned and a block may have - * been allocated in the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_read_or_alloc_page(struct fscache_cookie *cookie, - struct page *page, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_page(cookie, page, end_io_func, - context, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate - * blocks in which to store them - * @cookie: The cookie representing the cache object - * @mapping: The netfs inode mapping to which the pages will be attached - * @pages: A list of potential netfs pages to be filled - * @nr_pages: Number of pages to be read and/or allocated - * @end_io_func: The callback to invoke when and if each page is filled - * @context: An arbitrary piece of data to pass on to end_io_func() - * @gfp: The conditions under which memory allocation should be made - * - * Read a set of pages from the cache, or if that's not possible, attempt to - * make a potential one-block reservation for each page in the cache into which - * that page may be stored once fetched from the server. - * - * If some pages are not backed by the cache object, or if it there's some - * reason they can't be, -ENOBUFS will be returned and nothing more will be - * done for that pages. - * - * Else, if some of the pages are backed by the cache, a read will be initiated - * directly to the netfs's page and 0 will be returned by this function. The - * end_io_func() callback will be invoked when the operation terminates on a - * completion or failure. Note that the callback may be invoked before the - * return. - * - * Else, if a page is unbacked, -ENODATA is returned and a block may have - * been allocated in the cache. - * - * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in - * regard to different pages, the return values are prioritised in that order. - * Any pages submitted for reading are removed from the pages list. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_read_or_alloc_pages(struct fscache_cookie *cookie, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages, - fscache_rw_complete_t end_io_func, - void *context, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_read_or_alloc_pages(cookie, mapping, pages, - nr_pages, end_io_func, - context, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_alloc_page - Allocate a block in which to store a page - * @cookie: The cookie representing the cache object - * @page: The netfs page to allocate a page for - * @gfp: The conditions under which memory allocation should be made - * - * Request Allocation a block in the cache in which to store a netfs page - * without retrieving any contents from the cache. - * - * If the page is not backed by a file then -ENOBUFS will be returned and - * nothing more will be done, and no reservation will be made. - * - * Else, a block will be allocated if one wasn't already, and 0 will be - * returned - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_alloc_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_alloc_page(cookie, page, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_readpages_cancel - Cancel read/alloc on pages - * @cookie: The cookie representing the inode's cache object. - * @pages: The netfs pages that we canceled write on in readpages() - * - * Uncache/unreserve the pages reserved earlier in readpages() via - * fscache_readpages_or_alloc() and similar. In most successful caches in - * readpages() this doesn't do anything. In cases when the underlying netfs's - * readahead failed we need to clean up the pagelist (unmark and uncache). - * - * This function may sleep as it may have to clean up disk state. - */ -static inline -void fscache_readpages_cancel(struct fscache_cookie *cookie, - struct list_head *pages) -{ - if (fscache_cookie_valid(cookie)) - __fscache_readpages_cancel(cookie, pages); -} - -/** - * fscache_write_page - Request storage of a page in the cache - * @cookie: The cookie representing the cache object - * @page: The netfs page to store - * @object_size: Updated size of object - * @gfp: The conditions under which memory allocation should be made - * - * Request the contents of the netfs page be written into the cache. This - * request may be ignored if no cache block is currently allocated, in which - * case it will return -ENOBUFS. - * - * If a cache block was already allocated, a write will be initiated and 0 will - * be returned. The PG_fscache_write page bit is set immediately and will then - * be cleared at the completion of the write to indicate the success or failure - * of the operation. Note that the completion may happen before the return. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -int fscache_write_page(struct fscache_cookie *cookie, - struct page *page, - loff_t object_size, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - return __fscache_write_page(cookie, page, object_size, gfp); - else - return -ENOBUFS; -} - -/** - * fscache_uncache_page - Indicate that caching is no longer required on a page - * @cookie: The cookie representing the cache object - * @page: The netfs page that was being cached. - * - * Tell the cache that we no longer want a page to be cached and that it should - * remove any knowledge of the netfs page it may have. - * - * Note that this cannot cancel any outstanding I/O operations between this - * page and the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_uncache_page(struct fscache_cookie *cookie, - struct page *page) -{ - if (fscache_cookie_valid(cookie)) - __fscache_uncache_page(cookie, page); -} - -/** - * fscache_check_page_write - Ask if a page is being writing to the cache - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * - * Ask the cache if a page is being written to the cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -bool fscache_check_page_write(struct fscache_cookie *cookie, - struct page *page) -{ - if (fscache_cookie_valid(cookie)) - return __fscache_check_page_write(cookie, page); - return false; -} - -/** - * fscache_wait_on_page_write - Wait for a page to complete writing to the cache - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * - * Ask the cache to wake us up when a page is no longer being written to the - * cache. - * - * See Documentation/filesystems/caching/netfs-api.rst for a complete - * description. - */ -static inline -void fscache_wait_on_page_write(struct fscache_cookie *cookie, - struct page *page) -{ - if (fscache_cookie_valid(cookie)) - __fscache_wait_on_page_write(cookie, page); -} - -/** - * fscache_maybe_release_page - Consider releasing a page, cancelling a store - * @cookie: The cookie representing the cache object - * @page: The netfs page that is being cached. - * @gfp: The gfp flags passed to releasepage() - * - * Consider releasing a page for the vmscan algorithm, on behalf of the netfs's - * releasepage() call. A storage request on the page may cancelled if it is - * not currently being processed. - * - * The function returns true if the page no longer has a storage request on it, - * and false if a storage request is left in place. If true is returned, the - * page will have been passed to fscache_uncache_page(). If false is returned - * the page cannot be freed yet. - */ -static inline -bool fscache_maybe_release_page(struct fscache_cookie *cookie, - struct page *page, - gfp_t gfp) -{ - if (fscache_cookie_valid(cookie) && PageFsCache(page)) - return __fscache_maybe_release_page(cookie, page, gfp); - return true; -} - -/** - * fscache_uncache_all_inode_pages - Uncache all an inode's pages - * @cookie: The cookie representing the inode's cache object. - * @inode: The inode to uncache pages from. - * - * Uncache all the pages in an inode that are marked PG_fscache, assuming them - * to be associated with the given cookie. - * - * This function may sleep. It will wait for pages that are being written out - * and will wait whilst the PG_fscache mark is removed by the cache. - */ -static inline -void fscache_uncache_all_inode_pages(struct fscache_cookie *cookie, - struct inode *inode) -{ - if (fscache_cookie_valid(cookie)) - __fscache_uncache_all_inode_pages(cookie, inode); -} - -#endif /* FSCACHE_USE_NEW_IO_API */ - -/** - * fscache_disable_cookie - Disable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @invalidate: Invalidate the backing object - * - * Disable a cookie from accepting further alloc, read, write, invalidate, - * update or acquire operations. Outstanding operations can still be waited - * upon and pages can still be uncached and the cookie relinquished. - * - * This will not return until all outstanding operations have completed. - * - * If @invalidate is set, then the backing object will be invalidated and - * detached, otherwise it will just be detached. - * - * If @aux_data is set, then auxiliary data will be updated from that. - */ -static inline -void fscache_disable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - bool invalidate) -{ - if (fscache_cookie_valid(cookie) && fscache_cookie_enabled(cookie)) - __fscache_disable_cookie(cookie, aux_data, invalidate); -} - -/** - * fscache_enable_cookie - Reenable a cookie - * @cookie: The cookie representing the cache object - * @aux_data: The updated auxiliary data for the cookie (may be NULL) - * @object_size: Current size of object - * @can_enable: A function to permit enablement once lock is held - * @data: Data for can_enable() - * - * Reenable a previously disabled cookie, allowing it to accept further alloc, - * read, write, invalidate, update or acquire operations. An attempt will be - * made to immediately reattach the cookie to a backing object. If @aux_data - * is set, the auxiliary data attached to the cookie will be updated. - * - * The can_enable() function is called (if not NULL) once the enablement lock - * is held to rule on whether enablement is still permitted to go ahead. - */ -static inline -void fscache_enable_cookie(struct fscache_cookie *cookie, - const void *aux_data, - loff_t object_size, - bool (*can_enable)(void *data), - void *data) -{ - if (fscache_cookie_valid(cookie) && !fscache_cookie_enabled(cookie)) - __fscache_enable_cookie(cookie, aux_data, object_size, - can_enable, data); -} - #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h deleted file mode 100644 index 446392f5ba83..000000000000 --- a/include/trace/events/fscache.h +++ /dev/null @@ -1,523 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* FS-Cache tracepoints - * - * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM fscache - -#if !defined(_TRACE_FSCACHE_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_FSCACHE_H - -#include -#include - -/* - * Define enums for tracing information. - */ -#ifndef __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY -#define __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY - -enum fscache_cookie_trace { - fscache_cookie_collision, - fscache_cookie_discard, - fscache_cookie_get_acquire_parent, - fscache_cookie_get_attach_object, - fscache_cookie_get_reacquire, - fscache_cookie_get_register_netfs, - fscache_cookie_put_acquire_nobufs, - fscache_cookie_put_dup_netfs, - fscache_cookie_put_relinquish, - fscache_cookie_put_object, - fscache_cookie_put_parent, -}; - -enum fscache_page_trace { - fscache_page_cached, - fscache_page_inval, - fscache_page_maybe_release, - fscache_page_radix_clear_store, - fscache_page_radix_delete, - fscache_page_radix_insert, - fscache_page_radix_pend2store, - fscache_page_radix_set_pend, - fscache_page_uncache, - fscache_page_write, - fscache_page_write_end, - fscache_page_write_end_pend, - fscache_page_write_end_noc, - fscache_page_write_wait, - fscache_page_trace__nr -}; - -enum fscache_op_trace { - fscache_op_cancel, - fscache_op_cancel_all, - fscache_op_cancelled, - fscache_op_completed, - fscache_op_enqueue_async, - fscache_op_enqueue_mythread, - fscache_op_gc, - fscache_op_init, - fscache_op_put, - fscache_op_run, - fscache_op_signal, - fscache_op_submit, - fscache_op_submit_ex, - fscache_op_work, - fscache_op_trace__nr -}; - -enum fscache_page_op_trace { - fscache_page_op_alloc_one, - fscache_page_op_attr_changed, - fscache_page_op_check_consistency, - fscache_page_op_invalidate, - fscache_page_op_retr_multi, - fscache_page_op_retr_one, - fscache_page_op_write_one, - fscache_page_op_trace__nr -}; - -#endif - -/* - * Declare tracing information enums and their string mappings for display. - */ -#define fscache_cookie_traces \ - EM(fscache_cookie_collision, "*COLLISION*") \ - EM(fscache_cookie_discard, "DISCARD") \ - EM(fscache_cookie_get_acquire_parent, "GET prn") \ - EM(fscache_cookie_get_attach_object, "GET obj") \ - EM(fscache_cookie_get_reacquire, "GET raq") \ - EM(fscache_cookie_get_register_netfs, "GET net") \ - EM(fscache_cookie_put_acquire_nobufs, "PUT nbf") \ - EM(fscache_cookie_put_dup_netfs, "PUT dnt") \ - EM(fscache_cookie_put_relinquish, "PUT rlq") \ - EM(fscache_cookie_put_object, "PUT obj") \ - E_(fscache_cookie_put_parent, "PUT prn") - -#define fscache_page_traces \ - EM(fscache_page_cached, "Cached ") \ - EM(fscache_page_inval, "InvalPg") \ - EM(fscache_page_maybe_release, "MayRels") \ - EM(fscache_page_uncache, "Uncache") \ - EM(fscache_page_radix_clear_store, "RxCStr ") \ - EM(fscache_page_radix_delete, "RxDel ") \ - EM(fscache_page_radix_insert, "RxIns ") \ - EM(fscache_page_radix_pend2store, "RxP2S ") \ - EM(fscache_page_radix_set_pend, "RxSPend ") \ - EM(fscache_page_write, "WritePg") \ - EM(fscache_page_write_end, "EndPgWr") \ - EM(fscache_page_write_end_pend, "EndPgWP") \ - EM(fscache_page_write_end_noc, "EndPgNC") \ - E_(fscache_page_write_wait, "WtOnWrt") - -#define fscache_op_traces \ - EM(fscache_op_cancel, "Cancel1") \ - EM(fscache_op_cancel_all, "CancelA") \ - EM(fscache_op_cancelled, "Canclld") \ - EM(fscache_op_completed, "Complet") \ - EM(fscache_op_enqueue_async, "EnqAsyn") \ - EM(fscache_op_enqueue_mythread, "EnqMyTh") \ - EM(fscache_op_gc, "GC ") \ - EM(fscache_op_init, "Init ") \ - EM(fscache_op_put, "Put ") \ - EM(fscache_op_run, "Run ") \ - EM(fscache_op_signal, "Signal ") \ - EM(fscache_op_submit, "Submit ") \ - EM(fscache_op_submit_ex, "SubmitX") \ - E_(fscache_op_work, "Work ") - -#define fscache_page_op_traces \ - EM(fscache_page_op_alloc_one, "Alloc1 ") \ - EM(fscache_page_op_attr_changed, "AttrChg") \ - EM(fscache_page_op_check_consistency, "CheckCn") \ - EM(fscache_page_op_invalidate, "Inval ") \ - EM(fscache_page_op_retr_multi, "RetrMul") \ - EM(fscache_page_op_retr_one, "Retr1 ") \ - E_(fscache_page_op_write_one, "Write1 ") - -/* - * Export enum symbols via userspace. - */ -#undef EM -#undef E_ -#define EM(a, b) TRACE_DEFINE_ENUM(a); -#define E_(a, b) TRACE_DEFINE_ENUM(a); - -fscache_cookie_traces; - -/* - * Now redefine the EM() and E_() macros to map the enums to the strings that - * will be printed in the output. - */ -#undef EM -#undef E_ -#define EM(a, b) { a, b }, -#define E_(a, b) { a, b } - - -TRACE_EVENT(fscache_cookie, - TP_PROTO(unsigned int cookie_debug_id, - int ref, - enum fscache_cookie_trace where), - - TP_ARGS(cookie_debug_id, ref, where), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(enum fscache_cookie_trace, where ) - __field(int, ref ) - ), - - TP_fast_assign( - __entry->cookie = cookie_debug_id; - __entry->where = where; - __entry->ref = ref; - ), - - TP_printk("%s c=%08x r=%d", - __print_symbolic(__entry->where, fscache_cookie_traces), - __entry->cookie, __entry->ref) - ); - -TRACE_EVENT(fscache_netfs, - TP_PROTO(struct fscache_netfs *netfs), - - TP_ARGS(netfs), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __array(char, name, 8 ) - ), - - TP_fast_assign( - __entry->cookie = netfs->primary_index->debug_id; - strncpy(__entry->name, netfs->name, 8); - __entry->name[7] = 0; - ), - - TP_printk("c=%08x n=%s", - __entry->cookie, __entry->name) - ); - -TRACE_EVENT(fscache_acquire, - TP_PROTO(struct fscache_cookie *cookie), - - TP_ARGS(cookie), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, parent ) - __array(char, name, 8 ) - __field(int, p_ref ) - __field(int, p_n_children ) - __field(u8, p_flags ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->parent = cookie->parent->debug_id; - __entry->p_ref = refcount_read(&cookie->parent->ref); - __entry->p_n_children = atomic_read(&cookie->parent->n_children); - __entry->p_flags = cookie->parent->flags; - memcpy(__entry->name, cookie->def->name, 8); - __entry->name[7] = 0; - ), - - TP_printk("c=%08x p=%08x pr=%d pc=%d pf=%02x n=%s", - __entry->cookie, __entry->parent, __entry->p_ref, - __entry->p_n_children, __entry->p_flags, __entry->name) - ); - -TRACE_EVENT(fscache_relinquish, - TP_PROTO(struct fscache_cookie *cookie, bool retire), - - TP_ARGS(cookie, retire), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, parent ) - __field(int, ref ) - __field(int, n_children ) - __field(int, n_active ) - __field(u8, flags ) - __field(bool, retire ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->parent = cookie->parent->debug_id; - __entry->ref = refcount_read(&cookie->ref); - __entry->n_children = atomic_read(&cookie->n_children); - __entry->n_active = atomic_read(&cookie->n_active); - __entry->flags = cookie->flags; - __entry->retire = retire; - ), - - TP_printk("c=%08x r=%d p=%08x Nc=%d Na=%d f=%02x r=%u", - __entry->cookie, __entry->ref, - __entry->parent, __entry->n_children, __entry->n_active, - __entry->flags, __entry->retire) - ); - -TRACE_EVENT(fscache_enable, - TP_PROTO(struct fscache_cookie *cookie), - - TP_ARGS(cookie), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(int, ref ) - __field(int, n_children ) - __field(int, n_active ) - __field(u8, flags ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->ref = refcount_read(&cookie->ref); - __entry->n_children = atomic_read(&cookie->n_children); - __entry->n_active = atomic_read(&cookie->n_active); - __entry->flags = cookie->flags; - ), - - TP_printk("c=%08x r=%d Nc=%d Na=%d f=%02x", - __entry->cookie, __entry->ref, - __entry->n_children, __entry->n_active, __entry->flags) - ); - -TRACE_EVENT(fscache_disable, - TP_PROTO(struct fscache_cookie *cookie), - - TP_ARGS(cookie), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(int, ref ) - __field(int, n_children ) - __field(int, n_active ) - __field(u8, flags ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->ref = refcount_read(&cookie->ref); - __entry->n_children = atomic_read(&cookie->n_children); - __entry->n_active = atomic_read(&cookie->n_active); - __entry->flags = cookie->flags; - ), - - TP_printk("c=%08x r=%d Nc=%d Na=%d f=%02x", - __entry->cookie, __entry->ref, - __entry->n_children, __entry->n_active, __entry->flags) - ); - -TRACE_EVENT(fscache_osm, - TP_PROTO(struct fscache_object *object, - const struct fscache_state *state, - bool wait, bool oob, s8 event_num), - - TP_ARGS(object, state, wait, oob, event_num), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, object ) - __array(char, state, 8 ) - __field(bool, wait ) - __field(bool, oob ) - __field(s8, event_num ) - ), - - TP_fast_assign( - __entry->cookie = object->cookie->debug_id; - __entry->object = object->debug_id; - __entry->wait = wait; - __entry->oob = oob; - __entry->event_num = event_num; - memcpy(__entry->state, state->short_name, 8); - ), - - TP_printk("c=%08x o=%08d %s %s%sev=%d", - __entry->cookie, - __entry->object, - __entry->state, - __print_symbolic(__entry->wait, - { true, "WAIT" }, - { false, "WORK" }), - __print_symbolic(__entry->oob, - { true, " OOB " }, - { false, " " }), - __entry->event_num) - ); - -TRACE_EVENT(fscache_page, - TP_PROTO(struct fscache_cookie *cookie, struct page *page, - enum fscache_page_trace why), - - TP_ARGS(cookie, page, why), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(pgoff_t, page ) - __field(enum fscache_page_trace, why ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->page = page->index; - __entry->why = why; - ), - - TP_printk("c=%08x %s pg=%lx", - __entry->cookie, - __print_symbolic(__entry->why, fscache_page_traces), - __entry->page) - ); - -TRACE_EVENT(fscache_check_page, - TP_PROTO(struct fscache_cookie *cookie, struct page *page, - void *val, int n), - - TP_ARGS(cookie, page, val, n), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(void *, page ) - __field(void *, val ) - __field(int, n ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->page = page; - __entry->val = val; - __entry->n = n; - ), - - TP_printk("c=%08x pg=%p val=%p n=%d", - __entry->cookie, __entry->page, __entry->val, __entry->n) - ); - -TRACE_EVENT(fscache_wake_cookie, - TP_PROTO(struct fscache_cookie *cookie), - - TP_ARGS(cookie), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - ), - - TP_printk("c=%08x", __entry->cookie) - ); - -TRACE_EVENT(fscache_op, - TP_PROTO(struct fscache_cookie *cookie, struct fscache_operation *op, - enum fscache_op_trace why), - - TP_ARGS(cookie, op, why), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, op ) - __field(enum fscache_op_trace, why ) - ), - - TP_fast_assign( - __entry->cookie = cookie ? cookie->debug_id : 0; - __entry->op = op->debug_id; - __entry->why = why; - ), - - TP_printk("c=%08x op=%08x %s", - __entry->cookie, __entry->op, - __print_symbolic(__entry->why, fscache_op_traces)) - ); - -TRACE_EVENT(fscache_page_op, - TP_PROTO(struct fscache_cookie *cookie, struct page *page, - struct fscache_operation *op, enum fscache_page_op_trace what), - - TP_ARGS(cookie, page, op, what), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, op ) - __field(pgoff_t, page ) - __field(enum fscache_page_op_trace, what ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->page = page ? page->index : 0; - __entry->op = op->debug_id; - __entry->what = what; - ), - - TP_printk("c=%08x %s pg=%lx op=%08x", - __entry->cookie, - __print_symbolic(__entry->what, fscache_page_op_traces), - __entry->page, __entry->op) - ); - -TRACE_EVENT(fscache_wrote_page, - TP_PROTO(struct fscache_cookie *cookie, struct page *page, - struct fscache_operation *op, int ret), - - TP_ARGS(cookie, page, op, ret), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, op ) - __field(pgoff_t, page ) - __field(int, ret ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->page = page->index; - __entry->op = op->debug_id; - __entry->ret = ret; - ), - - TP_printk("c=%08x pg=%lx op=%08x ret=%d", - __entry->cookie, __entry->page, __entry->op, __entry->ret) - ); - -TRACE_EVENT(fscache_gang_lookup, - TP_PROTO(struct fscache_cookie *cookie, struct fscache_operation *op, - void **results, int n, pgoff_t store_limit), - - TP_ARGS(cookie, op, results, n, store_limit), - - TP_STRUCT__entry( - __field(unsigned int, cookie ) - __field(unsigned int, op ) - __field(pgoff_t, results0 ) - __field(int, n ) - __field(pgoff_t, store_limit ) - ), - - TP_fast_assign( - __entry->cookie = cookie->debug_id; - __entry->op = op->debug_id; - __entry->results0 = results[0] ? ((struct page *)results[0])->index : (pgoff_t)-1; - __entry->n = n; - __entry->store_limit = store_limit; - ), - - TP_printk("c=%08x op=%08x r0=%lx n=%d sl=%lx", - __entry->cookie, __entry->op, __entry->results0, __entry->n, - __entry->store_limit) - ); - -#endif /* _TRACE_FSCACHE_H */ - -/* This part must be outside protection */ -#include -- cgit v1.2.3 From a39c41b853ee51f4dcd19f5556f860ae8e2f23d3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:30:37 +0100 Subject: netfs: Pass a flag to ->prepare_write() to say if there's no alloc'd space Pass a flag to ->prepare_write() to indicate if there's definitely no space allocated in the cache yet (for instance if we've already checked as we were asked to do a read). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819583123.215744.12783808230464471417.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906886835.143852.6689886781122679769.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967079100.1823006.12889542712309574359.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021489334.640689.3131206613015409076.stgit@warthog.procyon.org.uk/ # v4 --- fs/netfs/read_helper.c | 2 +- include/linux/netfs.h | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 75c76cbb27cc..9dd76b8914f2 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -323,7 +323,7 @@ static void netfs_rreq_do_write_to_cache(struct netfs_read_request *rreq) } ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len, - rreq->i_size); + rreq->i_size, true); if (ret < 0) { trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write); trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ca0683b9e3d1..1ea22fc48818 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -232,7 +232,8 @@ struct netfs_cache_ops { * actually do. */ int (*prepare_write)(struct netfs_cache_resources *cres, - loff_t *_start, size_t *_len, loff_t i_size); + loff_t *_start, size_t *_len, loff_t i_size, + bool no_space_allocated_yet); }; struct readahead_control; -- cgit v1.2.3 From 1e1236b841166f1d2daf36fdf6bb3e656bc5f5ca Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:34:41 +0100 Subject: fscache: Introduce new driver Introduce basic skeleton of the new, rewritten fscache driver. Changes ======= ver #3: - Use remove_proc_subtree(), not remove_proc_entry() to remove a populated dir. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819584034.215744.4290533472390439030.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906887770.143852.3577888294989185666.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967080039.1823006.5702921801104057922.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021491014.640689.4292699878317589512.stgit@warthog.procyon.org.uk/ # v4 --- fs/Makefile | 1 + fs/fscache/Kconfig | 39 +++++++++ fs/fscache/Makefile | 12 +++ fs/fscache/internal.h | 183 +++++++++++++++++++++++++++++++++++++++++ fs/fscache/main.c | 65 +++++++++++++++ fs/fscache/proc.c | 42 ++++++++++ fs/fscache/stats.c | 22 +++++ include/linux/fscache-cache.h | 2 + include/linux/fscache.h | 6 +- include/trace/events/fscache.h | 49 +++++++++++ 10 files changed, 420 insertions(+), 1 deletion(-) create mode 100644 fs/fscache/Makefile create mode 100644 fs/fscache/internal.h create mode 100644 fs/fscache/main.c create mode 100644 fs/fscache/proc.c create mode 100644 fs/fscache/stats.c create mode 100644 include/trace/events/fscache.h (limited to 'include/linux') diff --git a/fs/Makefile b/fs/Makefile index 23ddd0803d14..290815f3fd31 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -67,6 +67,7 @@ obj-$(CONFIG_DLM) += dlm/ # Do not add any filesystems before this line obj-$(CONFIG_NETFS_SUPPORT) += netfs/ +obj-$(CONFIG_FSCACHE) += fscache/ obj-$(CONFIG_REISERFS_FS) += reiserfs/ obj-$(CONFIG_EXT4_FS) += ext4/ # We place ext4 before ext2 so that clean ext3 root fs's do NOT mount using the diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 6440484d9461..76316c4a3fb7 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -1,4 +1,43 @@ # SPDX-License-Identifier: GPL-2.0-only +config FSCACHE + tristate "General filesystem local caching manager" + select NETFS_SUPPORT + help + This option enables a generic filesystem caching manager that can be + used by various network and other filesystems to cache data locally. + Different sorts of caches can be plugged in, depending on the + resources available. + + See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_STATS + bool "Gather statistical information on local caching" + depends on FSCACHE && PROC_FS + select NETFS_STATS + help + This option causes statistical information to be gathered on local + caching and exported through file: + + /proc/fs/fscache/stats + + The gathering of statistics adds a certain amount of overhead to + execution as there are a quite a few stats gathered, and on a + multi-CPU system these may be on cachelines that keep bouncing + between CPUs. On the other hand, the stats are very useful for + debugging purposes. Saying 'Y' here is recommended. + + See Documentation/filesystems/caching/fscache.rst for more information. + +config FSCACHE_DEBUG + bool "Debug FS-Cache" + depends on FSCACHE + help + This permits debugging to be dynamically enabled in the local caching + management module. If this is set, the debugging output may be + enabled by setting bits in /sys/modules/fscache/parameter/debug. + + See Documentation/filesystems/caching/fscache.rst for more information. + config FSCACHE_OLD_API bool diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile new file mode 100644 index 000000000000..f9722de32247 --- /dev/null +++ b/fs/fscache/Makefile @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for general filesystem caching code +# + +fscache-y := \ + main.o + +fscache-$(CONFIG_PROC_FS) += proc.o +fscache-$(CONFIG_FSCACHE_STATS) += stats.o + +obj-$(CONFIG_FSCACHE) := fscache.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h new file mode 100644 index 000000000000..ea52f8594a77 --- /dev/null +++ b/fs/fscache/internal.h @@ -0,0 +1,183 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Internal definitions for FS-Cache + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "FS-Cache: " fmt + +#include +#include +#include +#include +#include + +/* + * main.c + */ +extern unsigned fscache_debug; + +/* + * proc.c + */ +#ifdef CONFIG_PROC_FS +extern int __init fscache_proc_init(void); +extern void fscache_proc_cleanup(void); +#else +#define fscache_proc_init() (0) +#define fscache_proc_cleanup() do {} while (0) +#endif + +/* + * stats.c + */ +#ifdef CONFIG_FSCACHE_STATS + +static inline void fscache_stat(atomic_t *stat) +{ + atomic_inc(stat); +} + +static inline void fscache_stat_d(atomic_t *stat) +{ + atomic_dec(stat); +} + +#define __fscache_stat(stat) (stat) + +int fscache_stats_show(struct seq_file *m, void *v); +#else + +#define __fscache_stat(stat) (NULL) +#define fscache_stat(stat) do {} while (0) +#define fscache_stat_d(stat) do {} while (0) +#endif + + +/*****************************************************************************/ +/* + * debug tracing + */ +#define dbgprintk(FMT, ...) \ + printk("[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__) + +#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__) +#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__) +#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__) + +#define kjournal(FMT, ...) no_printk(FMT, ##__VA_ARGS__) + +#ifdef __KDEBUG +#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__) +#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__) +#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__) + +#elif defined(CONFIG_FSCACHE_DEBUG) +#define _enter(FMT, ...) \ +do { \ + if (__do_kdebug(ENTER)) \ + kenter(FMT, ##__VA_ARGS__); \ +} while (0) + +#define _leave(FMT, ...) \ +do { \ + if (__do_kdebug(LEAVE)) \ + kleave(FMT, ##__VA_ARGS__); \ +} while (0) + +#define _debug(FMT, ...) \ +do { \ + if (__do_kdebug(DEBUG)) \ + kdebug(FMT, ##__VA_ARGS__); \ +} while (0) + +#else +#define _enter(FMT, ...) no_printk("==> %s("FMT")", __func__, ##__VA_ARGS__) +#define _leave(FMT, ...) no_printk("<== %s()"FMT"", __func__, ##__VA_ARGS__) +#define _debug(FMT, ...) no_printk(FMT, ##__VA_ARGS__) +#endif + +/* + * determine whether a particular optional debugging point should be logged + * - we need to go through three steps to persuade cpp to correctly join the + * shorthand in FSCACHE_DEBUG_LEVEL with its prefix + */ +#define ____do_kdebug(LEVEL, POINT) \ + unlikely((fscache_debug & \ + (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3)))) +#define ___do_kdebug(LEVEL, POINT) \ + ____do_kdebug(LEVEL, POINT) +#define __do_kdebug(POINT) \ + ___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT) + +#define FSCACHE_DEBUG_CACHE 0 +#define FSCACHE_DEBUG_COOKIE 1 +#define FSCACHE_DEBUG_OBJECT 2 +#define FSCACHE_DEBUG_OPERATION 3 + +#define FSCACHE_POINT_ENTER 1 +#define FSCACHE_POINT_LEAVE 2 +#define FSCACHE_POINT_DEBUG 4 + +#ifndef FSCACHE_DEBUG_LEVEL +#define FSCACHE_DEBUG_LEVEL CACHE +#endif + +/* + * assertions + */ +#if 1 /* defined(__KDEBUGALL) */ + +#define ASSERT(X) \ +do { \ + if (unlikely(!(X))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTCMP(X, OP, Y) \ +do { \ + if (unlikely(!((X) OP (Y)))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ + (unsigned long)(X), (unsigned long)(Y)); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTIF(C, X) \ +do { \ + if (unlikely((C) && !(X))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + BUG(); \ + } \ +} while (0) + +#define ASSERTIFCMP(C, X, OP, Y) \ +do { \ + if (unlikely((C) && !((X) OP (Y)))) { \ + pr_err("\n"); \ + pr_err("Assertion failed\n"); \ + pr_err("%lx " #OP " %lx is false\n", \ + (unsigned long)(X), (unsigned long)(Y)); \ + BUG(); \ + } \ +} while (0) + +#else + +#define ASSERT(X) do {} while (0) +#define ASSERTCMP(X, OP, Y) do {} while (0) +#define ASSERTIF(C, X) do {} while (0) +#define ASSERTIFCMP(C, X, OP, Y) do {} while (0) + +#endif /* assert or not */ diff --git a/fs/fscache/main.c b/fs/fscache/main.c new file mode 100644 index 000000000000..819de2ee1276 --- /dev/null +++ b/fs/fscache/main.c @@ -0,0 +1,65 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* General filesystem local caching manager + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#define CREATE_TRACE_POINTS +#include "internal.h" + +MODULE_DESCRIPTION("FS Cache Manager"); +MODULE_AUTHOR("Red Hat, Inc."); +MODULE_LICENSE("GPL"); + +unsigned fscache_debug; +module_param_named(debug, fscache_debug, uint, + S_IWUSR | S_IRUGO); +MODULE_PARM_DESC(fscache_debug, + "FS-Cache debugging mask"); + +struct workqueue_struct *fscache_wq; +EXPORT_SYMBOL(fscache_wq); + +/* + * initialise the fs caching module + */ +static int __init fscache_init(void) +{ + int ret = -ENOMEM; + + fscache_wq = alloc_workqueue("fscache", WQ_UNBOUND | WQ_FREEZABLE, 0); + if (!fscache_wq) + goto error_wq; + + ret = fscache_proc_init(); + if (ret < 0) + goto error_proc; + + pr_notice("Loaded\n"); + return 0; + +error_proc: + destroy_workqueue(fscache_wq); +error_wq: + return ret; +} + +fs_initcall(fscache_init); + +/* + * clean up on module removal + */ +static void __exit fscache_exit(void) +{ + _enter(""); + + fscache_proc_cleanup(); + destroy_workqueue(fscache_wq); + pr_notice("Unloaded\n"); +} + +module_exit(fscache_exit); diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c new file mode 100644 index 000000000000..4d866ac41776 --- /dev/null +++ b/fs/fscache/proc.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* FS-Cache statistics viewing interface + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#include +#include "internal.h" + +/* + * initialise the /proc/fs/fscache/ directory + */ +int __init fscache_proc_init(void) +{ + if (!proc_mkdir("fs/fscache", NULL)) + goto error_dir; + +#ifdef CONFIG_FSCACHE_STATS + if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, + fscache_stats_show)) + goto error; +#endif + + return 0; + +error: + remove_proc_entry("fs/fscache", NULL); +error_dir: + return -ENOMEM; +} + +/* + * clean up the /proc/fs/fscache/ directory + */ +void fscache_proc_cleanup(void) +{ + remove_proc_subtree("fs/fscache", NULL); +} diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c new file mode 100644 index 000000000000..bd92f93e1680 --- /dev/null +++ b/fs/fscache/stats.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* FS-Cache statistics + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#include "internal.h" + +/* + * display the general statistics + */ +int fscache_stats_show(struct seq_file *m, void *v) +{ + seq_puts(m, "FS-Cache statistics\n"); + + netfs_stats_show(m); + return 0; +} diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 47f21a53ac4b..d6910a913918 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -16,4 +16,6 @@ #include +extern struct workqueue_struct *fscache_wq; + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 0364a4ca16f6..1cf90c252aac 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ /* General filesystem caching interface * - * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * NOTE!!! See: @@ -18,9 +18,13 @@ #include #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) +#define __fscache_available (1) +#define fscache_available() (1) #define fscache_cookie_valid(cookie) (cookie) #define fscache_cookie_enabled(cookie) (cookie) #else +#define __fscache_available (0) +#define fscache_available() (0) #define fscache_cookie_valid(cookie) (0) #define fscache_cookie_enabled(cookie) (0) #endif diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h new file mode 100644 index 000000000000..fe214c5cc87f --- /dev/null +++ b/include/trace/events/fscache.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* FS-Cache tracepoints + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM fscache + +#if !defined(_TRACE_FSCACHE_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_FSCACHE_H + +#include +#include + +/* + * Define enums for tracing information. + */ +#ifndef __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY +#define __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY + +#endif + +/* + * Declare tracing information enums and their string mappings for display. + */ + +/* + * Export enum symbols via userspace. + */ +#undef EM +#undef E_ +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define E_(a, b) TRACE_DEFINE_ENUM(a); + +/* + * Now redefine the EM() and E_() macros to map the enums to the strings that + * will be printed in the output. + */ +#undef EM +#undef E_ +#define EM(a, b) { a, b }, +#define E_(a, b) { a, b } + + +#endif /* _TRACE_FSCACHE_H */ + +/* This part must be outside protection */ +#include -- cgit v1.2.3 From 9549332df4ed4e761a1d41c83f2c25d28bb22431 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:00:26 +0100 Subject: fscache: Implement cache registration Implement a register of caches and provide functions to manage it. Two functions are provided for the cache backend to use: (1) Acquire a cache cookie: struct fscache_cache *fscache_acquire_cache(const char *name) This gets the cache cookie for a cache of the specified name and moves it to the preparation state. If a nameless cache cookie exists, that will be given this name and used. (2) Relinquish a cache cookie: void fscache_relinquish_cache(struct fscache_cache *cache); This relinquishes a cache cookie, cleans it and makes it available if it's still referenced by a network filesystem. Note that network filesystems don't deal with cache cookies directly, but rather go straight to the volume registration. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819587157.215744.13523139317322503286.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906889665.143852.10378009165231294456.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967085081.1823006.2218944206363626210.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021494847.640689.10109692261640524343.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 1 + fs/fscache/cache.c | 274 +++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 33 +++++ fs/fscache/proc.c | 4 + include/linux/fscache-cache.h | 34 +++++ include/trace/events/fscache.h | 43 +++++++ 6 files changed, 389 insertions(+) create mode 100644 fs/fscache/cache.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index f9722de32247..d9fc22c18090 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -4,6 +4,7 @@ # fscache-y := \ + cache.o \ main.o fscache-$(CONFIG_PROC_FS) += proc.o diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c new file mode 100644 index 000000000000..8db77bb9f8e2 --- /dev/null +++ b/fs/fscache/cache.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* FS-Cache cache handling + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL CACHE +#include +#include +#include "internal.h" + +static LIST_HEAD(fscache_caches); +DECLARE_RWSEM(fscache_addremove_sem); +EXPORT_SYMBOL(fscache_addremove_sem); + +static atomic_t fscache_cache_debug_id; + +/* + * Allocate a cache cookie. + */ +static struct fscache_cache *fscache_alloc_cache(const char *name) +{ + struct fscache_cache *cache; + + cache = kzalloc(sizeof(*cache), GFP_KERNEL); + if (cache) { + if (name) { + cache->name = kstrdup(name, GFP_KERNEL); + if (!cache->name) { + kfree(cache); + return NULL; + } + } + refcount_set(&cache->ref, 1); + INIT_LIST_HEAD(&cache->cache_link); + cache->debug_id = atomic_inc_return(&fscache_cache_debug_id); + } + return cache; +} + +static bool fscache_get_cache_maybe(struct fscache_cache *cache, + enum fscache_cache_trace where) +{ + bool success; + int ref; + + success = __refcount_inc_not_zero(&cache->ref, &ref); + if (success) + trace_fscache_cache(cache->debug_id, ref + 1, where); + return success; +} + +/* + * Look up a cache cookie. + */ +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache) +{ + struct fscache_cache *candidate, *cache, *unnamed = NULL; + + /* firstly check for the existence of the cache under read lock */ + down_read(&fscache_addremove_sem); + + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && name && strcmp(cache->name, name) == 0 && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + if (!cache->name && !name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + } + + if (!name) { + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_r; + } + } + + up_read(&fscache_addremove_sem); + + /* the cache does not exist - create a candidate */ + candidate = fscache_alloc_cache(name); + if (!candidate) + return ERR_PTR(-ENOMEM); + + /* write lock, search again and add if still not present */ + down_write(&fscache_addremove_sem); + + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && name && strcmp(cache->name, name) == 0 && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + if (!cache->name) { + unnamed = cache; + if (!name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + } + } + + if (unnamed && is_cache && + fscache_get_cache_maybe(unnamed, fscache_cache_get_acquire)) + goto use_unnamed_cache; + + if (!name) { + list_for_each_entry(cache, &fscache_caches, cache_link) { + if (cache->name && + fscache_get_cache_maybe(cache, fscache_cache_get_acquire)) + goto got_cache_w; + } + } + + list_add_tail(&candidate->cache_link, &fscache_caches); + trace_fscache_cache(candidate->debug_id, + refcount_read(&candidate->ref), + fscache_cache_new_acquire); + up_write(&fscache_addremove_sem); + return candidate; + +got_cache_r: + up_read(&fscache_addremove_sem); + return cache; +use_unnamed_cache: + cache = unnamed; + cache->name = candidate->name; + candidate->name = NULL; +got_cache_w: + up_write(&fscache_addremove_sem); + kfree(candidate->name); + kfree(candidate); + return cache; +} + +/** + * fscache_acquire_cache - Acquire a cache-level cookie. + * @name: The name of the cache. + * + * Get a cookie to represent an actual cache. If a name is given and there is + * a nameless cache record available, this will acquire that and set its name, + * directing all the volumes using it to this cache. + * + * The cache will be switched over to the preparing state if not currently in + * use, otherwise -EBUSY will be returned. + */ +struct fscache_cache *fscache_acquire_cache(const char *name) +{ + struct fscache_cache *cache; + + ASSERT(name); + cache = fscache_lookup_cache(name, true); + if (IS_ERR(cache)) + return cache; + + if (!fscache_set_cache_state_maybe(cache, + FSCACHE_CACHE_IS_NOT_PRESENT, + FSCACHE_CACHE_IS_PREPARING)) { + pr_warn("Cache tag %s in use\n", name); + fscache_put_cache(cache, fscache_cache_put_cache); + return ERR_PTR(-EBUSY); + } + + return cache; +} +EXPORT_SYMBOL(fscache_acquire_cache); + +/** + * fscache_put_cache - Release a cache-level cookie. + * @cache: The cache cookie to be released + * @where: An indication of where the release happened + * + * Release the caller's reference on a cache-level cookie. The @where + * indication should give information about the circumstances in which the call + * occurs and will be logged through a tracepoint. + */ +void fscache_put_cache(struct fscache_cache *cache, + enum fscache_cache_trace where) +{ + unsigned int debug_id = cache->debug_id; + bool zero; + int ref; + + if (IS_ERR_OR_NULL(cache)) + return; + + zero = __refcount_dec_and_test(&cache->ref, &ref); + trace_fscache_cache(debug_id, ref - 1, where); + + if (zero) { + down_write(&fscache_addremove_sem); + list_del_init(&cache->cache_link); + up_write(&fscache_addremove_sem); + kfree(cache->name); + kfree(cache); + } +} + +/** + * fscache_relinquish_cache - Reset cache state and release cookie + * @cache: The cache cookie to be released + * + * Reset the state of a cache and release the caller's reference on a cache + * cookie. + */ +void fscache_relinquish_cache(struct fscache_cache *cache) +{ + enum fscache_cache_trace where = + (cache->state == FSCACHE_CACHE_IS_PREPARING) ? + fscache_cache_put_prep_failed : + fscache_cache_put_relinquish; + + cache->cache_priv = NULL; + smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_put_cache(cache, where); +} +EXPORT_SYMBOL(fscache_relinquish_cache); + +#ifdef CONFIG_PROC_FS +static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; + +/* + * Generate a list of caches in /proc/fs/fscache/caches + */ +static int fscache_caches_seq_show(struct seq_file *m, void *v) +{ + struct fscache_cache *cache; + + if (v == &fscache_caches) { + seq_puts(m, + "CACHE REF VOLS OBJS ACCES S NAME\n" + "======== ===== ===== ===== ===== = ===============\n" + ); + return 0; + } + + cache = list_entry(v, struct fscache_cache, cache_link); + seq_printf(m, + "%08x %5d %5d %5d %5d %c %s\n", + cache->debug_id, + refcount_read(&cache->ref), + atomic_read(&cache->n_volumes), + atomic_read(&cache->object_count), + atomic_read(&cache->n_accesses), + fscache_cache_states[cache->state], + cache->name ?: "-"); + return 0; +} + +static void *fscache_caches_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(fscache_addremove_sem) +{ + down_read(&fscache_addremove_sem); + return seq_list_start_head(&fscache_caches, *_pos); +} + +static void *fscache_caches_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_caches, _pos); +} + +static void fscache_caches_seq_stop(struct seq_file *m, void *v) + __releases(fscache_addremove_sem) +{ + up_read(&fscache_addremove_sem); +} + +const struct seq_operations fscache_caches_seq_ops = { + .start = fscache_caches_seq_start, + .next = fscache_caches_seq_next, + .stop = fscache_caches_seq_stop, + .show = fscache_caches_seq_show, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index f345bdb018ba..8fd39e7735fc 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -17,6 +17,39 @@ #include #include +/* + * cache.c + */ +#ifdef CONFIG_PROC_FS +extern const struct seq_operations fscache_caches_seq_ops; +#endif +struct fscache_cache *fscache_lookup_cache(const char *name, bool is_cache); +void fscache_put_cache(struct fscache_cache *cache, enum fscache_cache_trace where); + +static inline enum fscache_cache_state fscache_cache_state(const struct fscache_cache *cache) +{ + return smp_load_acquire(&cache->state); +} + +static inline bool fscache_cache_is_live(const struct fscache_cache *cache) +{ + return fscache_cache_state(cache) == FSCACHE_CACHE_IS_ACTIVE; +} + +static inline void fscache_set_cache_state(struct fscache_cache *cache, + enum fscache_cache_state new_state) +{ + smp_store_release(&cache->state, new_state); + +} + +static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, + enum fscache_cache_state old_state, + enum fscache_cache_state new_state) +{ + return try_cmpxchg_release(&cache->state, &old_state, new_state); +} + /* * main.c */ diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 4d866ac41776..93b925709e09 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -19,6 +19,10 @@ int __init fscache_proc_init(void) if (!proc_mkdir("fs/fscache", NULL)) goto error_dir; + if (!proc_create_seq("fs/fscache/caches", S_IFREG | 0444, NULL, + &fscache_caches_seq_ops)) + goto error; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index d6910a913918..18cd5c9877bb 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -16,6 +16,40 @@ #include +enum fscache_cache_trace; +enum fscache_access_trace; + +enum fscache_cache_state { + FSCACHE_CACHE_IS_NOT_PRESENT, /* No cache is present for this name */ + FSCACHE_CACHE_IS_PREPARING, /* A cache is preparing to come live */ + FSCACHE_CACHE_IS_ACTIVE, /* Attached cache is active and can be used */ + FSCACHE_CACHE_GOT_IOERROR, /* Attached cache stopped on I/O error */ + FSCACHE_CACHE_IS_WITHDRAWN, /* Attached cache is being withdrawn */ +#define NR__FSCACHE_CACHE_STATE (FSCACHE_CACHE_IS_WITHDRAWN + 1) +}; + +/* + * Cache cookie. + */ +struct fscache_cache { + struct list_head cache_link; /* Link in cache list */ + void *cache_priv; /* Private cache data (or NULL) */ + refcount_t ref; + atomic_t n_volumes; /* Number of active volumes; */ + atomic_t n_accesses; /* Number of in-progress accesses on the cache */ + atomic_t object_count; /* no. of live objects in this cache */ + unsigned int debug_id; + enum fscache_cache_state state; + char *name; +}; + extern struct workqueue_struct *fscache_wq; +/* + * out-of-line cache backend functions + */ +extern struct rw_semaphore fscache_addremove_sem; +extern struct fscache_cache *fscache_acquire_cache(const char *name); +extern void fscache_relinquish_cache(struct fscache_cache *cache); + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index fe214c5cc87f..3b8e0597b2c1 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -19,11 +19,27 @@ #ifndef __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY #define __FSCACHE_DECLARE_TRACE_ENUMS_ONCE_ONLY +enum fscache_cache_trace { + fscache_cache_collision, + fscache_cache_get_acquire, + fscache_cache_new_acquire, + fscache_cache_put_cache, + fscache_cache_put_prep_failed, + fscache_cache_put_relinquish, +}; + #endif /* * Declare tracing information enums and their string mappings for display. */ +#define fscache_cache_traces \ + EM(fscache_cache_collision, "*COLLIDE*") \ + EM(fscache_cache_get_acquire, "GET acq ") \ + EM(fscache_cache_new_acquire, "NEW acq ") \ + EM(fscache_cache_put_cache, "PUT cache") \ + EM(fscache_cache_put_prep_failed, "PUT pfail") \ + E_(fscache_cache_put_relinquish, "PUT relnq") /* * Export enum symbols via userspace. @@ -33,6 +49,8 @@ #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); +fscache_cache_traces; + /* * Now redefine the EM() and E_() macros to map the enums to the strings that * will be printed in the output. @@ -43,6 +61,31 @@ #define E_(a, b) { a, b } +TRACE_EVENT(fscache_cache, + TP_PROTO(unsigned int cache_debug_id, + int usage, + enum fscache_cache_trace where), + + TP_ARGS(cache_debug_id, usage, where), + + TP_STRUCT__entry( + __field(unsigned int, cache ) + __field(int, usage ) + __field(enum fscache_cache_trace, where ) + ), + + TP_fast_assign( + __entry->cache = cache_debug_id; + __entry->usage = usage; + __entry->where = where; + ), + + TP_printk("C=%08x %s r=%d", + __entry->cache, + __print_symbolic(__entry->where, fscache_cache_traces), + __entry->usage) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 62ab63352350e881ae693a8236b35d7d0516c78b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:26:17 +0100 Subject: fscache: Implement volume registration Add functions to the fscache API to allow volumes to be acquired and relinquished by the network filesystem. A volume is an index of data storage cache objects. A volume is represented by a volume cookie in the API. A filesystem would typically create a volume for a superblock and then create per-inode cookies within it. To request a volume, the filesystem calls: struct fscache_volume * fscache_acquire_volume(const char *volume_key, const char *cache_name, const void *coherency_data, size_t coherency_len) The volume_key is a printable string used to match the volume in the cache. It should not contain any '/' characters. For AFS, for example, this would be "afs,,", e.g. "afs,example.com,523001". The cache_name can be NULL, but if not it should be a string indicating the name of the cache to use if there's more than one available. The coherency data, if given, is an arbitrarily-sized blob that's attached to the volume and is compared when the volume is looked up. If it doesn't match, the old volume is judged to be out of date and it and everything within it is discarded. Acquiring a volume twice concurrently is disallowed, though the function will wait if an old volume cookie is being relinquishing. When a network filesystem has finished with a volume, it should return the volume cookie by calling: void fscache_relinquish_volume(struct fscache_volume *volume, const void *coherency_data, bool invalidate) If invalidate is true, the entire volume will be discarded; if false, the volume will be synced and the coherency data will be updated. Changes ======= ver #4: - Removed an extraneous param from kdoc on fscache_relinquish_volume()[3]. ver #3: - fscache_hash()'s size parameter is now in bytes. Use __le32 as the unit to round up to. - When comparing cookies, simply see if the attributes are the same rather than subtracting them to produce a strcmp-style return[2]. - Make the coherency data an arbitrary blob rather than a u64, but don't store it for the moment. ver #2: - Fix error check[1]. - Make a fscache_acquire_volume() return errors, including EBUSY if a conflicting volume cookie already exists. No error is printed now - that's left to the netfs. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/20211203095608.GC2480@kili/ [1] Link: https://lore.kernel.org/r/CAHk-=whtkzB446+hX0zdLsdcUJsJ=8_-0S1mE_R+YurThfUbLA@mail.gmail.com/ [2] Link: https://lore.kernel.org/r/20211220224646.30e8205c@canb.auug.org.au/ [3] Link: https://lore.kernel.org/r/163819588944.215744.1629085755564865996.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906890630.143852.13972180614535611154.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967086836.1823006.8191672796841981763.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021495816.640689.4403156093668590217.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 3 +- fs/fscache/internal.h | 14 ++ fs/fscache/proc.c | 4 + fs/fscache/stats.c | 12 ++ fs/fscache/volume.c | 340 +++++++++++++++++++++++++++++++++++++++++ include/linux/fscache.h | 84 ++++++++++ include/trace/events/fscache.h | 61 +++++++- 7 files changed, 516 insertions(+), 2 deletions(-) create mode 100644 fs/fscache/volume.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index d9fc22c18090..bb5282ae682f 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -5,7 +5,8 @@ fscache-y := \ cache.o \ - main.o + main.o \ + volume.o fscache-$(CONFIG_PROC_FS) += proc.o fscache-$(CONFIG_FSCACHE_STATS) += stats.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 8fd39e7735fc..07dc9cbc2280 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -72,6 +72,9 @@ extern void fscache_proc_cleanup(void); * stats.c */ #ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_volumes; +extern atomic_t fscache_n_volumes_collision; +extern atomic_t fscache_n_volumes_nomem; static inline void fscache_stat(atomic_t *stat) { @@ -93,6 +96,17 @@ int fscache_stats_show(struct seq_file *m, void *v); #define fscache_stat_d(stat) do {} while (0) #endif +/* + * volume.c + */ +extern const struct seq_operations fscache_volumes_seq_ops; + +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where); +void fscache_create_volume(struct fscache_volume *volume, bool wait); + /*****************************************************************************/ /* diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index 93b925709e09..bc6ecbdd065d 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -23,6 +23,10 @@ int __init fscache_proc_init(void) &fscache_caches_seq_ops)) goto error; + if (!proc_create_seq("fs/fscache/volumes", S_IFREG | 0444, NULL, + &fscache_volumes_seq_ops)) + goto error; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index bd92f93e1680..b811a4d03585 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -10,12 +10,24 @@ #include #include "internal.h" +/* + * operation counters + */ +atomic_t fscache_n_volumes; +atomic_t fscache_n_volumes_collision; +atomic_t fscache_n_volumes_nomem; + /* * display the general statistics */ int fscache_stats_show(struct seq_file *m, void *v) { seq_puts(m, "FS-Cache statistics\n"); + seq_printf(m, "Cookies: v=%d vcol=%u voom=%u\n", + atomic_read(&fscache_n_volumes), + atomic_read(&fscache_n_volumes_collision), + atomic_read(&fscache_n_volumes_nomem) + ); netfs_stats_show(m); return 0; diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c new file mode 100644 index 000000000000..630894fefd02 --- /dev/null +++ b/fs/fscache/volume.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Volume-level cache cookie handling. + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include +#include +#include "internal.h" + +#define fscache_volume_hash_shift 10 +static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift]; +static atomic_t fscache_volume_debug_id; +static LIST_HEAD(fscache_volumes); + +struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + int ref; + + __refcount_inc(&volume->ref, &ref); + trace_fscache_volume(volume->debug_id, ref + 1, where); + return volume; +} + +static void fscache_see_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + int ref = refcount_read(&volume->ref); + + trace_fscache_volume(volume->debug_id, ref, where); +} + +static bool fscache_volume_same(const struct fscache_volume *a, + const struct fscache_volume *b) +{ + size_t klen; + + if (a->key_hash != b->key_hash || + a->cache != b->cache || + a->key[0] != b->key[0]) + return false; + + klen = round_up(a->key[0] + 1, sizeof(__le32)); + return memcmp(a->key, b->key, klen) == 0; +} + +static bool fscache_is_acquire_pending(struct fscache_volume *volume) +{ + return test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &volume->flags); +} + +static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, + unsigned int collidee_debug_id) +{ + wait_var_event_timeout(&candidate->flags, + fscache_is_acquire_pending(candidate), 20 * HZ); + if (!fscache_is_acquire_pending(candidate)) { + pr_notice("Potential volume collision new=%08x old=%08x", + candidate->debug_id, collidee_debug_id); + fscache_stat(&fscache_n_volumes_collision); + wait_var_event(&candidate->flags, fscache_is_acquire_pending(candidate)); + } +} + +/* + * Attempt to insert the new volume into the hash. If there's a collision, we + * wait for the old volume to complete if it's being relinquished and an error + * otherwise. + */ +static bool fscache_hash_volume(struct fscache_volume *candidate) +{ + struct fscache_volume *cursor; + struct hlist_bl_head *h; + struct hlist_bl_node *p; + unsigned int bucket, collidee_debug_id = 0; + + bucket = candidate->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); + h = &fscache_volume_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_volume_same(candidate, cursor)) { + if (!test_bit(FSCACHE_VOLUME_RELINQUISHED, &cursor->flags)) + goto collision; + fscache_see_volume(cursor, fscache_volume_get_hash_collision); + set_bit(FSCACHE_VOLUME_COLLIDED_WITH, &cursor->flags); + set_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags); + collidee_debug_id = cursor->debug_id; + break; + } + } + + hlist_bl_add_head(&candidate->hash_link, h); + hlist_bl_unlock(h); + + if (test_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &candidate->flags)) + fscache_wait_on_volume_collision(candidate, collidee_debug_id); + return true; + +collision: + fscache_see_volume(cursor, fscache_volume_collision); + hlist_bl_unlock(h); + return false; +} + +/* + * Allocate and initialise a volume representation cookie. + */ +static struct fscache_volume *fscache_alloc_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + struct fscache_volume *volume; + struct fscache_cache *cache; + size_t klen, hlen; + char *key; + + cache = fscache_lookup_cache(cache_name, false); + if (IS_ERR(cache)) + return NULL; + + volume = kzalloc(sizeof(*volume), GFP_KERNEL); + if (!volume) + goto err_cache; + + volume->cache = cache; + INIT_LIST_HEAD(&volume->proc_link); + INIT_WORK(&volume->work, NULL /* PLACEHOLDER */); + refcount_set(&volume->ref, 1); + spin_lock_init(&volume->lock); + + /* Stick the length on the front of the key and pad it out to make + * hashing easier. + */ + klen = strlen(volume_key); + hlen = round_up(1 + klen + 1, sizeof(__le32)); + key = kzalloc(hlen, GFP_KERNEL); + if (!key) + goto err_vol; + key[0] = klen; + memcpy(key + 1, volume_key, klen); + + volume->key = key; + volume->key_hash = fscache_hash(0, key, hlen); + + volume->debug_id = atomic_inc_return(&fscache_volume_debug_id); + down_write(&fscache_addremove_sem); + atomic_inc(&cache->n_volumes); + list_add_tail(&volume->proc_link, &fscache_volumes); + fscache_see_volume(volume, fscache_volume_new_acquire); + fscache_stat(&fscache_n_volumes); + up_write(&fscache_addremove_sem); + _leave(" = v=%x", volume->debug_id); + return volume; + +err_vol: + kfree(volume); +err_cache: + fscache_put_cache(cache, fscache_cache_put_alloc_volume); + fscache_stat(&fscache_n_volumes_nomem); + return NULL; +} + +/* + * Acquire a volume representation cookie and link it to a (proposed) cache. + */ +struct fscache_volume *__fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + struct fscache_volume *volume; + + volume = fscache_alloc_volume(volume_key, cache_name, + coherency_data, coherency_len); + if (!volume) + return ERR_PTR(-ENOMEM); + + if (!fscache_hash_volume(volume)) { + fscache_put_volume(volume, fscache_volume_put_hash_collision); + return ERR_PTR(-EBUSY); + } + + // PLACEHOLDER: Create the volume if we have a cache available + return volume; +} +EXPORT_SYMBOL(__fscache_acquire_volume); + +static void fscache_wake_pending_volume(struct fscache_volume *volume, + struct hlist_bl_head *h) +{ + struct fscache_volume *cursor; + struct hlist_bl_node *p; + + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_volume_same(cursor, volume)) { + fscache_see_volume(cursor, fscache_volume_see_hash_wake); + clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); + wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING); + return; + } + } +} + +/* + * Remove a volume cookie from the hash table. + */ +static void fscache_unhash_volume(struct fscache_volume *volume) +{ + struct hlist_bl_head *h; + unsigned int bucket; + + bucket = volume->key_hash & (ARRAY_SIZE(fscache_volume_hash) - 1); + h = &fscache_volume_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_del(&volume->hash_link); + if (test_bit(FSCACHE_VOLUME_COLLIDED_WITH, &volume->flags)) + fscache_wake_pending_volume(volume, h); + hlist_bl_unlock(h); +} + +/* + * Drop a cache's volume attachments. + */ +static void fscache_free_volume(struct fscache_volume *volume) +{ + struct fscache_cache *cache = volume->cache; + + if (volume->cache_priv) { + // PLACEHOLDER: Detach any attached cache + } + + down_write(&fscache_addremove_sem); + list_del_init(&volume->proc_link); + atomic_dec(&volume->cache->n_volumes); + up_write(&fscache_addremove_sem); + + if (!hlist_bl_unhashed(&volume->hash_link)) + fscache_unhash_volume(volume); + + trace_fscache_volume(volume->debug_id, 0, fscache_volume_free); + kfree(volume->key); + kfree(volume); + fscache_stat_d(&fscache_n_volumes); + fscache_put_cache(cache, fscache_cache_put_volume); +} + +/* + * Drop a reference to a volume cookie. + */ +void fscache_put_volume(struct fscache_volume *volume, + enum fscache_volume_trace where) +{ + if (volume) { + unsigned int debug_id = volume->debug_id; + bool zero; + int ref; + + zero = __refcount_dec_and_test(&volume->ref, &ref); + trace_fscache_volume(debug_id, ref - 1, where); + if (zero) + fscache_free_volume(volume); + } +} + +/* + * Relinquish a volume representation cookie. + */ +void __fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) +{ + if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags))) + return; + + if (invalidate) + set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags); + + fscache_put_volume(volume, fscache_volume_put_relinquish); +} +EXPORT_SYMBOL(__fscache_relinquish_volume); + +#ifdef CONFIG_PROC_FS +/* + * Generate a list of volumes in /proc/fs/fscache/volumes + */ +static int fscache_volumes_seq_show(struct seq_file *m, void *v) +{ + struct fscache_volume *volume; + + if (v == &fscache_volumes) { + seq_puts(m, + "VOLUME REF nCOOK ACC FL CACHE KEY\n" + "======== ===== ===== === == =============== ================\n"); + return 0; + } + + volume = list_entry(v, struct fscache_volume, proc_link); + seq_printf(m, + "%08x %5d %5d %3d %02lx %-15.15s %s\n", + volume->debug_id, + refcount_read(&volume->ref), + atomic_read(&volume->n_cookies), + atomic_read(&volume->n_accesses), + volume->flags, + volume->cache->name ?: "-", + volume->key + 1); + return 0; +} + +static void *fscache_volumes_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(&fscache_addremove_sem) +{ + down_read(&fscache_addremove_sem); + return seq_list_start_head(&fscache_volumes, *_pos); +} + +static void *fscache_volumes_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_volumes, _pos); +} + +static void fscache_volumes_seq_stop(struct seq_file *m, void *v) + __releases(&fscache_addremove_sem) +{ + up_read(&fscache_addremove_sem); +} + +const struct seq_operations fscache_volumes_seq_ops = { + .start = fscache_volumes_seq_start, + .next = fscache_volumes_seq_next, + .stop = fscache_volumes_seq_stop, + .show = fscache_volumes_seq_show, +}; +#endif /* CONFIG_PROC_FS */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 1cf90c252aac..131a741a6652 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -20,13 +20,97 @@ #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) #define __fscache_available (1) #define fscache_available() (1) +#define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) #define fscache_cookie_enabled(cookie) (cookie) #else #define __fscache_available (0) #define fscache_available() (0) +#define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) #define fscache_cookie_enabled(cookie) (0) #endif +/* + * Volume representation cookie. + */ +struct fscache_volume { + refcount_t ref; + atomic_t n_cookies; /* Number of data cookies in volume */ + atomic_t n_accesses; /* Number of cache accesses in progress */ + unsigned int debug_id; + unsigned int key_hash; /* Hash of key string */ + char *key; /* Volume ID, eg. "afs@example.com@1234" */ + struct list_head proc_link; /* Link in /proc/fs/fscache/volumes */ + struct hlist_bl_node hash_link; /* Link in hash table */ + struct work_struct work; + struct fscache_cache *cache; /* The cache in which this resides */ + void *cache_priv; /* Cache private data */ + spinlock_t lock; + unsigned long flags; +#define FSCACHE_VOLUME_RELINQUISHED 0 /* Volume is being cleaned up */ +#define FSCACHE_VOLUME_INVALIDATE 1 /* Volume was invalidated */ +#define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ +#define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ +#define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ +}; + +/* + * slow-path functions for when there is actually caching available, and the + * netfs does actually have a valid token + * - these are not to be called directly + * - these are undefined symbols when FS-Cache is not configured and the + * optimiser takes care of not using them + */ +extern struct fscache_volume *__fscache_acquire_volume(const char *, const char *, + const void *, size_t); +extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); + +/** + * fscache_acquire_volume - Register a volume as desiring caching services + * @volume_key: An identification string for the volume + * @cache_name: The name of the cache to use (or NULL for the default) + * @coherency_data: Piece of arbitrary coherency data to check (or NULL) + * @coherency_len: The size of the coherency data + * + * Register a volume as desiring caching services if they're available. The + * caller must provide an identifier for the volume and may also indicate which + * cache it should be in. If a preexisting volume entry is found in the cache, + * the coherency data must match otherwise the entry will be invalidated. + * + * Returns a cookie pointer on success, -ENOMEM if out of memory or -EBUSY if a + * cache volume of that name is already acquired. Note that "NULL" is a valid + * cookie pointer and can be returned if caching is refused. + */ +static inline +struct fscache_volume *fscache_acquire_volume(const char *volume_key, + const char *cache_name, + const void *coherency_data, + size_t coherency_len) +{ + if (!fscache_available()) + return NULL; + return __fscache_acquire_volume(volume_key, cache_name, + coherency_data, coherency_len); +} + +/** + * fscache_relinquish_volume - Cease caching a volume + * @volume: The volume cookie + * @coherency_data: Piece of arbitrary coherency data to set (or NULL) + * @invalidate: True if the volume should be invalidated + * + * Indicate that a filesystem no longer desires caching services for a volume. + * The caller must have relinquished all file cookies prior to calling this. + * The stored coherency data is updated. + */ +static inline +void fscache_relinquish_volume(struct fscache_volume *volume, + const void *coherency_data, + bool invalidate) +{ + if (fscache_volume_valid(volume)) + __fscache_relinquish_volume(volume, coherency_data, invalidate); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 3b8e0597b2c1..eeb3e7d88e20 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -23,9 +23,26 @@ enum fscache_cache_trace { fscache_cache_collision, fscache_cache_get_acquire, fscache_cache_new_acquire, + fscache_cache_put_alloc_volume, fscache_cache_put_cache, fscache_cache_put_prep_failed, fscache_cache_put_relinquish, + fscache_cache_put_volume, +}; + +enum fscache_volume_trace { + fscache_volume_collision, + fscache_volume_get_cookie, + fscache_volume_get_create_work, + fscache_volume_get_hash_collision, + fscache_volume_free, + fscache_volume_new_acquire, + fscache_volume_put_cookie, + fscache_volume_put_create_work, + fscache_volume_put_hash_collision, + fscache_volume_put_relinquish, + fscache_volume_see_create_work, + fscache_volume_see_hash_wake, }; #endif @@ -37,9 +54,25 @@ enum fscache_cache_trace { EM(fscache_cache_collision, "*COLLIDE*") \ EM(fscache_cache_get_acquire, "GET acq ") \ EM(fscache_cache_new_acquire, "NEW acq ") \ + EM(fscache_cache_put_alloc_volume, "PUT alvol") \ EM(fscache_cache_put_cache, "PUT cache") \ EM(fscache_cache_put_prep_failed, "PUT pfail") \ - E_(fscache_cache_put_relinquish, "PUT relnq") + EM(fscache_cache_put_relinquish, "PUT relnq") \ + E_(fscache_cache_put_volume, "PUT vol ") + +#define fscache_volume_traces \ + EM(fscache_volume_collision, "*COLLIDE*") \ + EM(fscache_volume_get_cookie, "GET cook ") \ + EM(fscache_volume_get_create_work, "GET creat") \ + EM(fscache_volume_get_hash_collision, "GET hcoll") \ + EM(fscache_volume_free, "FREE ") \ + EM(fscache_volume_new_acquire, "NEW acq ") \ + EM(fscache_volume_put_cookie, "PUT cook ") \ + EM(fscache_volume_put_create_work, "PUT creat") \ + EM(fscache_volume_put_hash_collision, "PUT hcoll") \ + EM(fscache_volume_put_relinquish, "PUT relnq") \ + EM(fscache_volume_see_create_work, "SEE creat") \ + E_(fscache_volume_see_hash_wake, "SEE hwake") /* * Export enum symbols via userspace. @@ -50,6 +83,7 @@ enum fscache_cache_trace { #define E_(a, b) TRACE_DEFINE_ENUM(a); fscache_cache_traces; +fscache_volume_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -86,6 +120,31 @@ TRACE_EVENT(fscache_cache, __entry->usage) ); +TRACE_EVENT(fscache_volume, + TP_PROTO(unsigned int volume_debug_id, + int usage, + enum fscache_volume_trace where), + + TP_ARGS(volume_debug_id, usage, where), + + TP_STRUCT__entry( + __field(unsigned int, volume ) + __field(int, usage ) + __field(enum fscache_volume_trace, where ) + ), + + TP_fast_assign( + __entry->volume = volume_debug_id; + __entry->usage = usage; + __entry->where = where; + ), + + TP_printk("V=%08x %s u=%d", + __entry->volume, + __print_symbolic(__entry->where, fscache_volume_traces), + __entry->usage) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 7f3283aba39a0f395700c3b5defa4ec49d9914b3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie registration Add functions to the fscache API to allow data file cookies to be acquired and relinquished by the network filesystem. It is intended that the filesystem will create such cookies per-inode under a volume. To request a cookie, the filesystem should call: struct fscache_cookie * fscache_acquire_cookie(struct fscache_volume *volume, u8 advice, const void *index_key, size_t index_key_len, const void *aux_data, size_t aux_data_len, loff_t object_size) The filesystem must first have created a volume cookie, which is passed in here. If it passes in NULL then the function will just return a NULL cookie. A binary key should be passed in index_key and is of size index_key_len. This is saved in the cookie and is used to locate the associated data in the cache. A coherency data buffer of size aux_data_len will be allocated and initialised from the buffer pointed to by aux_data. This is used to validate cache objects when they're opened and is stored on disk with them when they're committed. The data is stored in the cookie and will be updateable by various functions in later patches. The object_size must also be given. This is also used to perform a coherency check and to size the backing storage appropriately. This function disallows a cookie from being acquired twice in parallel, though it will cause the second user to wait if the first is busy relinquishing its cookie. When a network filesystem has finished with a cookie, it should call: void fscache_relinquish_cookie(struct fscache_volume *volume, bool retire) If retire is true, any backing data will be discarded immediately. Changes ======= ver #3: - fscache_hash()'s size parameter is now in bytes. Use __le32 as the unit to round up to. - When comparing cookies, simply see if the attributes are the same rather than subtracting them to produce a strcmp-style return[1]. - Add a check to see if the cookie is still hashed at the point of freeing. ver #2: - Don't hold n_accesses elevated whilst cache is bound to a cookie, but rather add a flag that prevents the state machine from being queued when n_accesses reaches 0. - Remove the unused cookie pointer field from the fscache_acquire tracepoint. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/CAHk-=whtkzB446+hX0zdLsdcUJsJ=8_-0S1mE_R+YurThfUbLA@mail.gmail.com/ [1] Link: https://lore.kernel.org/r/163819590658.215744.14934902514281054323.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906891983.143852.6219772337558577395.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967088507.1823006.12659006350221417165.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021498432.640689.12743483856927722772.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 1 + fs/fscache/cookie.c | 497 +++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 23 ++ fs/fscache/main.c | 12 + fs/fscache/proc.c | 4 + fs/fscache/stats.c | 28 ++- include/linux/fscache-cache.h | 22 ++ include/linux/fscache.h | 134 +++++++++++ include/trace/events/fscache.h | 111 +++++++++ 9 files changed, 831 insertions(+), 1 deletion(-) create mode 100644 fs/fscache/cookie.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index bb5282ae682f..bcc79615f93a 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -5,6 +5,7 @@ fscache-y := \ cache.o \ + cookie.o \ main.o \ volume.o diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c new file mode 100644 index 000000000000..438b0098aa73 --- /dev/null +++ b/fs/fscache/cookie.c @@ -0,0 +1,497 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* netfs cookie management + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * See Documentation/filesystems/caching/netfs-api.rst for more information on + * the netfs API. + */ + +#define FSCACHE_DEBUG_LEVEL COOKIE +#include +#include +#include "internal.h" + +struct kmem_cache *fscache_cookie_jar; + +static void fscache_drop_cookie(struct fscache_cookie *cookie); + +#define fscache_cookie_hash_shift 15 +static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; +static LIST_HEAD(fscache_cookies); +static DEFINE_RWLOCK(fscache_cookies_lock); +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFWRD"; + +void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) +{ + const u8 *k; + + pr_err("%c-cookie c=%08x [fl=%lx na=%u nA=%u s=%c]\n", + prefix, + cookie->debug_id, + cookie->flags, + atomic_read(&cookie->n_active), + atomic_read(&cookie->n_accesses), + fscache_cookie_states[cookie->state]); + pr_err("%c-cookie V=%08x [%s]\n", + prefix, + cookie->volume->debug_id, + cookie->volume->key); + + k = (cookie->key_len <= sizeof(cookie->inline_key)) ? + cookie->inline_key : cookie->key; + pr_err("%c-key=[%u] '%*phN'\n", prefix, cookie->key_len, cookie->key_len, k); +} + +static void fscache_free_cookie(struct fscache_cookie *cookie) +{ + if (WARN_ON_ONCE(test_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags))) { + fscache_print_cookie(cookie, 'F'); + return; + } + + write_lock(&fscache_cookies_lock); + list_del(&cookie->proc_link); + write_unlock(&fscache_cookies_lock); + if (cookie->aux_len > sizeof(cookie->inline_aux)) + kfree(cookie->aux); + if (cookie->key_len > sizeof(cookie->inline_key)) + kfree(cookie->key); + fscache_stat_d(&fscache_n_cookies); + kmem_cache_free(fscache_cookie_jar, cookie); +} + +static inline void wake_up_cookie_state(struct fscache_cookie *cookie) +{ + /* Use a barrier to ensure that waiters see the state variable + * change, as spin_unlock doesn't guarantee a barrier. + * + * See comments over wake_up_bit() and waitqueue_active(). + */ + smp_mb(); + wake_up_var(&cookie->state); +} + +static void __fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) +{ + cookie->state = state; +} + +/* + * Change the state a cookie is at and wake up anyone waiting for that - but + * only if the cookie isn't already marked as being in a cleanup state. + */ +void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) +{ + bool changed = false; + + spin_lock(&cookie->lock); + switch (cookie->state) { + case FSCACHE_COOKIE_STATE_RELINQUISHING: + break; + default: + __fscache_set_cookie_state(cookie, state); + changed = true; + break; + } + spin_unlock(&cookie->lock); + if (changed) + wake_up_cookie_state(cookie); +} +EXPORT_SYMBOL(fscache_set_cookie_state); + +/* + * Set the index key in a cookie. The cookie struct has space for a 16-byte + * key plus length and hash, but if that's not big enough, it's instead a + * pointer to a buffer containing 3 bytes of hash, 1 byte of length and then + * the key data. + */ +static int fscache_set_key(struct fscache_cookie *cookie, + const void *index_key, size_t index_key_len) +{ + void *buf; + size_t buf_size; + + buf_size = round_up(index_key_len, sizeof(__le32)); + + if (index_key_len > sizeof(cookie->inline_key)) { + buf = kzalloc(buf_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + cookie->key = buf; + } else { + buf = cookie->inline_key; + } + + memcpy(buf, index_key, index_key_len); + cookie->key_hash = fscache_hash(cookie->volume->key_hash, + buf, buf_size); + return 0; +} + +static bool fscache_cookie_same(const struct fscache_cookie *a, + const struct fscache_cookie *b) +{ + const void *ka, *kb; + + if (a->key_hash != b->key_hash || + a->volume != b->volume || + a->key_len != b->key_len) + return false; + + if (a->key_len <= sizeof(a->inline_key)) { + ka = &a->inline_key; + kb = &b->inline_key; + } else { + ka = a->key; + kb = b->key; + } + return memcmp(ka, kb, a->key_len) == 0; +} + +static atomic_t fscache_cookie_debug_id = ATOMIC_INIT(1); + +/* + * Allocate a cookie. + */ +static struct fscache_cookie *fscache_alloc_cookie( + struct fscache_volume *volume, + u8 advice, + const void *index_key, size_t index_key_len, + const void *aux_data, size_t aux_data_len, + loff_t object_size) +{ + struct fscache_cookie *cookie; + + /* allocate and initialise a cookie */ + cookie = kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL); + if (!cookie) + return NULL; + fscache_stat(&fscache_n_cookies); + + cookie->volume = volume; + cookie->advice = advice; + cookie->key_len = index_key_len; + cookie->aux_len = aux_data_len; + cookie->object_size = object_size; + if (object_size == 0) + __set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + + if (fscache_set_key(cookie, index_key, index_key_len) < 0) + goto nomem; + + if (cookie->aux_len <= sizeof(cookie->inline_aux)) { + memcpy(cookie->inline_aux, aux_data, cookie->aux_len); + } else { + cookie->aux = kmemdup(aux_data, cookie->aux_len, GFP_KERNEL); + if (!cookie->aux) + goto nomem; + } + + refcount_set(&cookie->ref, 1); + cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); + cookie->state = FSCACHE_COOKIE_STATE_QUIESCENT; + spin_lock_init(&cookie->lock); + INIT_LIST_HEAD(&cookie->commit_link); + INIT_WORK(&cookie->work, NULL /* PLACEHOLDER */); + + write_lock(&fscache_cookies_lock); + list_add_tail(&cookie->proc_link, &fscache_cookies); + write_unlock(&fscache_cookies_lock); + fscache_see_cookie(cookie, fscache_cookie_new_acquire); + return cookie; + +nomem: + fscache_free_cookie(cookie); + return NULL; +} + +static void fscache_wait_on_collision(struct fscache_cookie *candidate, + struct fscache_cookie *wait_for) +{ + enum fscache_cookie_state *statep = &wait_for->state; + + wait_var_event_timeout(statep, READ_ONCE(*statep) == FSCACHE_COOKIE_STATE_DROPPED, + 20 * HZ); + if (READ_ONCE(*statep) != FSCACHE_COOKIE_STATE_DROPPED) { + pr_notice("Potential collision c=%08x old: c=%08x", + candidate->debug_id, wait_for->debug_id); + wait_var_event(statep, READ_ONCE(*statep) == FSCACHE_COOKIE_STATE_DROPPED); + } +} + +/* + * Attempt to insert the new cookie into the hash. If there's a collision, we + * wait for the old cookie to complete if it's being relinquished and an error + * otherwise. + */ +static bool fscache_hash_cookie(struct fscache_cookie *candidate) +{ + struct fscache_cookie *cursor, *wait_for = NULL; + struct hlist_bl_head *h; + struct hlist_bl_node *p; + unsigned int bucket; + + bucket = candidate->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1); + h = &fscache_cookie_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_for_each_entry(cursor, p, h, hash_link) { + if (fscache_cookie_same(candidate, cursor)) { + if (!test_bit(FSCACHE_COOKIE_RELINQUISHED, &cursor->flags)) + goto collision; + wait_for = fscache_get_cookie(cursor, + fscache_cookie_get_hash_collision); + break; + } + } + + fscache_get_volume(candidate->volume, fscache_volume_get_cookie); + atomic_inc(&candidate->volume->n_cookies); + hlist_bl_add_head(&candidate->hash_link, h); + set_bit(FSCACHE_COOKIE_IS_HASHED, &candidate->flags); + hlist_bl_unlock(h); + + if (wait_for) { + fscache_wait_on_collision(candidate, wait_for); + fscache_put_cookie(wait_for, fscache_cookie_put_hash_collision); + } + return true; + +collision: + trace_fscache_cookie(cursor->debug_id, refcount_read(&cursor->ref), + fscache_cookie_collision); + pr_err("Duplicate cookie detected\n"); + fscache_print_cookie(cursor, 'O'); + fscache_print_cookie(candidate, 'N'); + hlist_bl_unlock(h); + return false; +} + +/* + * Request a cookie to represent a data storage object within a volume. + * + * We never let on to the netfs about errors. We may set a negative cookie + * pointer, but that's okay + */ +struct fscache_cookie *__fscache_acquire_cookie( + struct fscache_volume *volume, + u8 advice, + const void *index_key, size_t index_key_len, + const void *aux_data, size_t aux_data_len, + loff_t object_size) +{ + struct fscache_cookie *cookie; + + _enter("V=%x", volume->debug_id); + + if (!index_key || !index_key_len || index_key_len > 255 || aux_data_len > 255) + return NULL; + if (!aux_data || !aux_data_len) { + aux_data = NULL; + aux_data_len = 0; + } + + fscache_stat(&fscache_n_acquires); + + cookie = fscache_alloc_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); + if (!cookie) { + fscache_stat(&fscache_n_acquires_oom); + return NULL; + } + + if (!fscache_hash_cookie(cookie)) { + fscache_see_cookie(cookie, fscache_cookie_discard); + fscache_free_cookie(cookie); + return NULL; + } + + trace_fscache_acquire(cookie); + fscache_stat(&fscache_n_acquires_ok); + _leave(" = c=%08x", cookie->debug_id); + return cookie; +} +EXPORT_SYMBOL(__fscache_acquire_cookie); + +/* + * Remove a cookie from the hash table. + */ +static void fscache_unhash_cookie(struct fscache_cookie *cookie) +{ + struct hlist_bl_head *h; + unsigned int bucket; + + bucket = cookie->key_hash & (ARRAY_SIZE(fscache_cookie_hash) - 1); + h = &fscache_cookie_hash[bucket]; + + hlist_bl_lock(h); + hlist_bl_del(&cookie->hash_link); + clear_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags); + hlist_bl_unlock(h); +} + +/* + * Finalise a cookie after all its resources have been disposed of. + */ +static void fscache_drop_cookie(struct fscache_cookie *cookie) +{ + spin_lock(&cookie->lock); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); + + fscache_unhash_cookie(cookie); + fscache_stat(&fscache_n_relinquishes_dropped); +} + +/* + * Allow the netfs to release a cookie back to the cache. + * - the object will be marked as recyclable on disk if retire is true + */ +void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) +{ + fscache_stat(&fscache_n_relinquishes); + if (retire) + fscache_stat(&fscache_n_relinquishes_retire); + + _enter("c=%08x{%d},%d", + cookie->debug_id, atomic_read(&cookie->n_active), retire); + + if (WARN(test_and_set_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Cookie c=%x already relinquished\n", cookie->debug_id)) + return; + + if (retire) + set_bit(FSCACHE_COOKIE_RETIRED, &cookie->flags); + trace_fscache_relinquish(cookie, retire); + + ASSERTCMP(atomic_read(&cookie->n_active), ==, 0); + ASSERTCMP(atomic_read(&cookie->volume->n_cookies), >, 0); + atomic_dec(&cookie->volume->n_cookies); + + set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); + + if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) + ; // PLACEHOLDER: Do something here if the cookie was cached + else + fscache_drop_cookie(cookie); + fscache_put_cookie(cookie, fscache_cookie_put_relinquish); +} +EXPORT_SYMBOL(__fscache_relinquish_cookie); + +/* + * Drop a reference to a cookie. + */ +void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + struct fscache_volume *volume = cookie->volume; + unsigned int cookie_debug_id = cookie->debug_id; + bool zero; + int ref; + + zero = __refcount_dec_and_test(&cookie->ref, &ref); + trace_fscache_cookie(cookie_debug_id, ref - 1, where); + if (zero) { + fscache_free_cookie(cookie); + fscache_put_volume(volume, fscache_volume_put_cookie); + } +} +EXPORT_SYMBOL(fscache_put_cookie); + +/* + * Get a reference to a cookie. + */ +struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + int ref; + + __refcount_inc(&cookie->ref, &ref); + trace_fscache_cookie(cookie->debug_id, ref + 1, where); + return cookie; +} +EXPORT_SYMBOL(fscache_get_cookie); + +/* + * Generate a list of extant cookies in /proc/fs/fscache/cookies + */ +static int fscache_cookies_seq_show(struct seq_file *m, void *v) +{ + struct fscache_cookie *cookie; + unsigned int keylen = 0, auxlen = 0; + u8 *p; + + if (v == &fscache_cookies) { + seq_puts(m, + "COOKIE VOLUME REF ACT ACC S FL DEF \n" + "======== ======== === === === = == ================\n" + ); + return 0; + } + + cookie = list_entry(v, struct fscache_cookie, proc_link); + + seq_printf(m, + "%08x %08x %3d %3d %3d %c %02lx", + cookie->debug_id, + cookie->volume->debug_id, + refcount_read(&cookie->ref), + atomic_read(&cookie->n_active), + atomic_read(&cookie->n_accesses), + fscache_cookie_states[cookie->state], + cookie->flags); + + keylen = cookie->key_len; + auxlen = cookie->aux_len; + + if (keylen > 0 || auxlen > 0) { + seq_puts(m, " "); + p = keylen <= sizeof(cookie->inline_key) ? + cookie->inline_key : cookie->key; + for (; keylen > 0; keylen--) + seq_printf(m, "%02x", *p++); + if (auxlen > 0) { + seq_puts(m, ", "); + p = auxlen <= sizeof(cookie->inline_aux) ? + cookie->inline_aux : cookie->aux; + for (; auxlen > 0; auxlen--) + seq_printf(m, "%02x", *p++); + } + } + + seq_puts(m, "\n"); + return 0; +} + +static void *fscache_cookies_seq_start(struct seq_file *m, loff_t *_pos) + __acquires(fscache_cookies_lock) +{ + read_lock(&fscache_cookies_lock); + return seq_list_start_head(&fscache_cookies, *_pos); +} + +static void *fscache_cookies_seq_next(struct seq_file *m, void *v, loff_t *_pos) +{ + return seq_list_next(v, &fscache_cookies, _pos); +} + +static void fscache_cookies_seq_stop(struct seq_file *m, void *v) + __releases(rcu) +{ + read_unlock(&fscache_cookies_lock); +} + + +const struct seq_operations fscache_cookies_seq_ops = { + .start = fscache_cookies_seq_start, + .next = fscache_cookies_seq_next, + .stop = fscache_cookies_seq_stop, + .show = fscache_cookies_seq_show, +}; diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 07dc9cbc2280..71c897757d44 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -50,6 +50,20 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, return try_cmpxchg_release(&cache->state, &old_state, new_state); } +/* + * cookie.c + */ +extern struct kmem_cache *fscache_cookie_jar; +extern const struct seq_operations fscache_cookies_seq_ops; + +extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); +static inline void fscache_see_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + trace_fscache_cookie(cookie->debug_id, refcount_read(&cookie->ref), + where); +} + /* * main.c */ @@ -75,6 +89,15 @@ extern void fscache_proc_cleanup(void); extern atomic_t fscache_n_volumes; extern atomic_t fscache_n_volumes_collision; extern atomic_t fscache_n_volumes_nomem; +extern atomic_t fscache_n_cookies; + +extern atomic_t fscache_n_acquires; +extern atomic_t fscache_n_acquires_ok; +extern atomic_t fscache_n_acquires_oom; + +extern atomic_t fscache_n_relinquishes; +extern atomic_t fscache_n_relinquishes_retire; +extern atomic_t fscache_n_relinquishes_dropped; static inline void fscache_stat(atomic_t *stat) { diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 687b34903d5b..ae493e9ca1c9 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -79,9 +79,20 @@ static int __init fscache_init(void) if (ret < 0) goto error_proc; + fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar", + sizeof(struct fscache_cookie), + 0, 0, NULL); + if (!fscache_cookie_jar) { + pr_notice("Failed to allocate a cookie jar\n"); + ret = -ENOMEM; + goto error_cookie_jar; + } + pr_notice("Loaded\n"); return 0; +error_cookie_jar: + fscache_proc_cleanup(); error_proc: destroy_workqueue(fscache_wq); error_wq: @@ -97,6 +108,7 @@ static void __exit fscache_exit(void) { _enter(""); + kmem_cache_destroy(fscache_cookie_jar); fscache_proc_cleanup(); destroy_workqueue(fscache_wq); pr_notice("Unloaded\n"); diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c index bc6ecbdd065d..dc3b0e9c8cce 100644 --- a/fs/fscache/proc.c +++ b/fs/fscache/proc.c @@ -27,6 +27,10 @@ int __init fscache_proc_init(void) &fscache_volumes_seq_ops)) goto error; + if (!proc_create_seq("fs/fscache/cookies", S_IFREG | 0444, NULL, + &fscache_cookies_seq_ops)) + goto error; + #ifdef CONFIG_FSCACHE_STATS if (!proc_create_single("fs/fscache/stats", S_IFREG | 0444, NULL, fscache_stats_show)) diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index b811a4d03585..252e883ae148 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -16,6 +16,18 @@ atomic_t fscache_n_volumes; atomic_t fscache_n_volumes_collision; atomic_t fscache_n_volumes_nomem; +atomic_t fscache_n_cookies; + +atomic_t fscache_n_acquires; +atomic_t fscache_n_acquires_ok; +atomic_t fscache_n_acquires_oom; + +atomic_t fscache_n_updates; +EXPORT_SYMBOL(fscache_n_updates); + +atomic_t fscache_n_relinquishes; +atomic_t fscache_n_relinquishes_retire; +atomic_t fscache_n_relinquishes_dropped; /* * display the general statistics @@ -23,12 +35,26 @@ atomic_t fscache_n_volumes_nomem; int fscache_stats_show(struct seq_file *m, void *v) { seq_puts(m, "FS-Cache statistics\n"); - seq_printf(m, "Cookies: v=%d vcol=%u voom=%u\n", + seq_printf(m, "Cookies: n=%d v=%d vcol=%u voom=%u\n", + atomic_read(&fscache_n_cookies), atomic_read(&fscache_n_volumes), atomic_read(&fscache_n_volumes_collision), atomic_read(&fscache_n_volumes_nomem) ); + seq_printf(m, "Acquire: n=%u ok=%u oom=%u\n", + atomic_read(&fscache_n_acquires), + atomic_read(&fscache_n_acquires_ok), + atomic_read(&fscache_n_acquires_oom)); + + seq_printf(m, "Updates: n=%u\n", + atomic_read(&fscache_n_updates)); + + seq_printf(m, "Relinqs: n=%u rtr=%u drop=%u\n", + atomic_read(&fscache_n_relinquishes), + atomic_read(&fscache_n_relinquishes_retire), + atomic_read(&fscache_n_relinquishes_dropped)); + netfs_stats_show(m); return 0; } diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 18cd5c9877bb..c4355b888c91 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -17,6 +17,7 @@ #include enum fscache_cache_trace; +enum fscache_cookie_trace; enum fscache_access_trace; enum fscache_cache_state { @@ -52,4 +53,25 @@ extern struct rw_semaphore fscache_addremove_sem; extern struct fscache_cache *fscache_acquire_cache(const char *name); extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_put_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where); +extern void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state); + +/** + * fscache_get_key - Get a pointer to the cookie key + * @cookie: The cookie to query + * + * Return a pointer to the where a cookie's key is stored. + */ +static inline void *fscache_get_key(struct fscache_cookie *cookie) +{ + if (cookie->key_len <= sizeof(cookie->inline_key)) + return cookie->inline_key; + else + return cookie->key; +} + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 131a741a6652..4450d17c11e8 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -31,6 +31,27 @@ #define fscache_cookie_enabled(cookie) (0) #endif +struct fscache_cookie; + +#define FSCACHE_ADV_SINGLE_CHUNK 0x01 /* The object is a single chunk of data */ +#define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ +#define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ + +/* + * Data object state. + */ +enum fscache_cookie_state { + FSCACHE_COOKIE_STATE_QUIESCENT, /* The cookie is uncached */ + FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ + FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ + FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ + FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ + FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ + FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ + FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ +#define FSCACHE_COOKIE_STATE__NR (FSCACHE_COOKIE_STATE_DROPPED + 1) +} __attribute__((mode(byte))); + /* * Volume representation cookie. */ @@ -55,6 +76,60 @@ struct fscache_volume { #define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ }; +/* + * Data file representation cookie. + * - a file will only appear in one cache + * - a request to cache a file may or may not be honoured, subject to + * constraints such as disk space + * - indices are created on disk just-in-time + */ +struct fscache_cookie { + refcount_t ref; + atomic_t n_active; /* number of active users of cookie */ + atomic_t n_accesses; /* Number of cache accesses in progress */ + unsigned int debug_id; + unsigned int inval_counter; /* Number of invalidations made */ + spinlock_t lock; + struct fscache_volume *volume; /* Parent volume of this file. */ + void *cache_priv; /* Cache-side representation */ + struct hlist_bl_node hash_link; /* Link in hash table */ + struct list_head proc_link; /* Link in proc list */ + struct list_head commit_link; /* Link in commit queue */ + struct work_struct work; /* Commit/relinq/withdraw work */ + loff_t object_size; /* Size of the netfs object */ + unsigned long unused_at; /* Time at which unused (jiffies) */ + unsigned long flags; +#define FSCACHE_COOKIE_RELINQUISHED 0 /* T if cookie has been relinquished */ +#define FSCACHE_COOKIE_RETIRED 1 /* T if this cookie has retired on relinq */ +#define FSCACHE_COOKIE_IS_CACHING 2 /* T if this cookie is cached */ +#define FSCACHE_COOKIE_NO_DATA_TO_READ 3 /* T if this cookie has nothing to read */ +#define FSCACHE_COOKIE_NEEDS_UPDATE 4 /* T if attrs have been updated */ +#define FSCACHE_COOKIE_HAS_BEEN_CACHED 5 /* T if cookie needs withdraw-on-relinq */ +#define FSCACHE_COOKIE_DISABLED 6 /* T if cookie has been disabled */ +#define FSCACHE_COOKIE_LOCAL_WRITE 7 /* T if cookie has been modified locally */ +#define FSCACHE_COOKIE_NO_ACCESS_WAKE 8 /* T if no wake when n_accesses goes 0 */ +#define FSCACHE_COOKIE_DO_RELINQUISH 9 /* T if this cookie needs relinquishment */ +#define FSCACHE_COOKIE_DO_WITHDRAW 10 /* T if this cookie needs withdrawing */ +#define FSCACHE_COOKIE_DO_LRU_DISCARD 11 /* T if this cookie needs LRU discard */ +#define FSCACHE_COOKIE_DO_PREP_TO_WRITE 12 /* T if cookie needs write preparation */ +#define FSCACHE_COOKIE_HAVE_DATA 13 /* T if this cookie has data stored */ +#define FSCACHE_COOKIE_IS_HASHED 14 /* T if this cookie is hashed */ + + enum fscache_cookie_state state; + u8 advice; /* FSCACHE_ADV_* */ + u8 key_len; /* Length of index key */ + u8 aux_len; /* Length of auxiliary data */ + u32 key_hash; /* Hash of volume, key, len */ + union { + void *key; /* Index key */ + u8 inline_key[16]; /* - If the key is short enough */ + }; + union { + void *aux; /* Auxiliary data */ + u8 inline_aux[8]; /* - If the aux data is short enough */ + }; +}; + /* * slow-path functions for when there is actually caching available, and the * netfs does actually have a valid token @@ -66,6 +141,14 @@ extern struct fscache_volume *__fscache_acquire_volume(const char *, const char const void *, size_t); extern void __fscache_relinquish_volume(struct fscache_volume *, const void *, bool); +extern struct fscache_cookie *__fscache_acquire_cookie( + struct fscache_volume *, + u8, + const void *, size_t, + const void *, size_t, + loff_t); +extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); + /** * fscache_acquire_volume - Register a volume as desiring caching services * @volume_key: An identification string for the volume @@ -113,4 +196,55 @@ void fscache_relinquish_volume(struct fscache_volume *volume, __fscache_relinquish_volume(volume, coherency_data, invalidate); } +/** + * fscache_acquire_cookie - Acquire a cookie to represent a cache object + * @volume: The volume in which to locate/create this cookie + * @advice: Advice flags (FSCACHE_COOKIE_ADV_*) + * @index_key: The index key for this cookie + * @index_key_len: Size of the index key + * @aux_data: The auxiliary data for the cookie (may be NULL) + * @aux_data_len: Size of the auxiliary data buffer + * @object_size: The initial size of object + * + * Acquire a cookie to represent a data file within the given cache volume. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, + u8 advice, + const void *index_key, + size_t index_key_len, + const void *aux_data, + size_t aux_data_len, + loff_t object_size) +{ + if (!fscache_volume_valid(volume)) + return NULL; + return __fscache_acquire_cookie(volume, advice, + index_key, index_key_len, + aux_data, aux_data_len, + object_size); +} + +/** + * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding + * it + * @cookie: The cookie being returned + * @retire: True if the cache object the cookie represents is to be discarded + * + * This function returns a cookie to the cache, forcibly discarding the + * associated cache object if retire is set to true. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) +{ + if (fscache_cookie_valid(cookie)) + __fscache_relinquish_cookie(cookie, retire); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index eeb3e7d88e20..9286e1c4b2ac 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -45,6 +45,23 @@ enum fscache_volume_trace { fscache_volume_see_hash_wake, }; +enum fscache_cookie_trace { + fscache_cookie_collision, + fscache_cookie_discard, + fscache_cookie_get_end_access, + fscache_cookie_get_hash_collision, + fscache_cookie_new_acquire, + fscache_cookie_put_hash_collision, + fscache_cookie_put_over_queued, + fscache_cookie_put_relinquish, + fscache_cookie_put_withdrawn, + fscache_cookie_put_work, + fscache_cookie_see_active, + fscache_cookie_see_relinquish, + fscache_cookie_see_withdraw, + fscache_cookie_see_work, +}; + #endif /* @@ -74,6 +91,22 @@ enum fscache_volume_trace { EM(fscache_volume_see_create_work, "SEE creat") \ E_(fscache_volume_see_hash_wake, "SEE hwake") +#define fscache_cookie_traces \ + EM(fscache_cookie_collision, "*COLLIDE*") \ + EM(fscache_cookie_discard, "DISCARD ") \ + EM(fscache_cookie_get_hash_collision, "GET hcoll") \ + EM(fscache_cookie_get_end_access, "GQ endac") \ + EM(fscache_cookie_new_acquire, "NEW acq ") \ + EM(fscache_cookie_put_hash_collision, "PUT hcoll") \ + EM(fscache_cookie_put_over_queued, "PQ overq") \ + EM(fscache_cookie_put_relinquish, "PUT relnq") \ + EM(fscache_cookie_put_withdrawn, "PUT wthdn") \ + EM(fscache_cookie_put_work, "PQ work ") \ + EM(fscache_cookie_see_active, "- activ") \ + EM(fscache_cookie_see_relinquish, "- x-rlq") \ + EM(fscache_cookie_see_withdraw, "- x-wth") \ + E_(fscache_cookie_see_work, "- work ") + /* * Export enum symbols via userspace. */ @@ -84,6 +117,7 @@ enum fscache_volume_trace { fscache_cache_traces; fscache_volume_traces; +fscache_cookie_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -145,6 +179,83 @@ TRACE_EVENT(fscache_volume, __entry->usage) ); +TRACE_EVENT(fscache_cookie, + TP_PROTO(unsigned int cookie_debug_id, + int ref, + enum fscache_cookie_trace where), + + TP_ARGS(cookie_debug_id, ref, where), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(int, ref ) + __field(enum fscache_cookie_trace, where ) + ), + + TP_fast_assign( + __entry->cookie = cookie_debug_id; + __entry->ref = ref; + __entry->where = where; + ), + + TP_printk("c=%08x %s r=%d", + __entry->cookie, + __print_symbolic(__entry->where, fscache_cookie_traces), + __entry->ref) + ); + +TRACE_EVENT(fscache_acquire, + TP_PROTO(struct fscache_cookie *cookie), + + TP_ARGS(cookie), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(unsigned int, volume ) + __field(int, v_ref ) + __field(int, v_n_cookies ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->volume = cookie->volume->debug_id; + __entry->v_ref = refcount_read(&cookie->volume->ref); + __entry->v_n_cookies = atomic_read(&cookie->volume->n_cookies); + ), + + TP_printk("c=%08x V=%08x vr=%d vc=%d", + __entry->cookie, + __entry->volume, __entry->v_ref, __entry->v_n_cookies) + ); + +TRACE_EVENT(fscache_relinquish, + TP_PROTO(struct fscache_cookie *cookie, bool retire), + + TP_ARGS(cookie, retire), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(unsigned int, volume ) + __field(int, ref ) + __field(int, n_active ) + __field(u8, flags ) + __field(bool, retire ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->volume = cookie->volume->debug_id; + __entry->ref = refcount_read(&cookie->ref); + __entry->n_active = atomic_read(&cookie->n_active); + __entry->flags = cookie->flags; + __entry->retire = retire; + ), + + TP_printk("c=%08x V=%08x r=%d U=%d f=%02x rt=%u", + __entry->cookie, __entry->volume, __entry->ref, + __entry->n_active, __entry->flags, __entry->retire) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From e6acd3299badbfb5fb0231d42481d4f5dedf5599 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:26:17 +0100 Subject: fscache: Implement volume-level access helpers Add a pair of helper functions to manage access to a volume, pinning the volume in place for the duration to prevent cache withdrawal from removing it: bool fscache_begin_volume_access(struct fscache_volume *volume, enum fscache_access_trace why); void fscache_end_volume_access(struct fscache_volume *volume, enum fscache_access_trace why); The way the access gate on the volume works/will work is: (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), then we return false to indicate access was not permitted. (2) If the cache tests as live, then we increment the volume's n_accesses count and then recheck the cache liveness, ending the access if it ceased to be live. (3) When we end the access, we decrement the volume's n_accesses and wake up the any waiters if it reaches 0. (4) Whilst the cache is caching, the volume's n_accesses is kept artificially incremented to prevent wakeups from happening. (5) When the cache is taken offline, the state is changed to prevent new accesses, the volume's n_accesses is decremented and we wait for it to become 0. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819594158.215744.8285859817391683254.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906894315.143852.5454793807544710479.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967095028.1823006.9173132503876627466.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021501546.640689.9631510472149608443.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/internal.h | 3 ++ fs/fscache/main.c | 1 + fs/fscache/volume.c | 84 ++++++++++++++++++++++++++++++++++++++++++ include/linux/fscache-cache.h | 4 ++ include/trace/events/fscache.h | 34 +++++++++++++++++ 5 files changed, 126 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index be29816b37ef..91a4ea08ec0b 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -130,6 +130,9 @@ struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where); void fscache_put_volume(struct fscache_volume *volume, enum fscache_volume_trace where); +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); void fscache_create_volume(struct fscache_volume *volume, bool wait); diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 876f4bee5840..6cab5d99ba4c 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -22,6 +22,7 @@ MODULE_PARM_DESC(fscache_debug, "FS-Cache debugging mask"); EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache); +EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume); struct workqueue_struct *fscache_wq; EXPORT_SYMBOL(fscache_wq); diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index 630894fefd02..20497f0f10bb 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -33,6 +33,90 @@ static void fscache_see_volume(struct fscache_volume *volume, trace_fscache_volume(volume->debug_id, ref, where); } +/* + * Pin the cache behind a volume so that we can access it. + */ +static void __fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + n_accesses = atomic_inc_return(&volume->n_accesses); + smp_mb__after_atomic(); + trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, + refcount_read(&volume->ref), + n_accesses, why); +} + +/** + * fscache_begin_volume_access - Pin a cache so a volume can be accessed + * @volume: The volume cookie + * @cookie: A datafile cookie for a tracing reference (or NULL) + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing a volume and returns true if successful. This works as follows: + * + * (1) If the cache tests as not live (state is not FSCACHE_CACHE_IS_ACTIVE), + * then we return false to indicate access was not permitted. + * + * (2) If the cache tests as live, then we increment the volume's n_accesses + * count and then recheck the cache liveness, ending the access if it + * ceased to be live. + * + * (3) When we end the access, we decrement the volume's n_accesses and wake + * up the any waiters if it reaches 0. + * + * (4) Whilst the cache is caching, the volume's n_accesses is kept + * artificially incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline, the state is changed to prevent new + * accesses, the volume's n_accesses is decremented and we wait for it to + * become 0. + * + * The datafile @cookie and the @why indicator are merely provided for tracing + * purposes. + */ +bool fscache_begin_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + if (!fscache_cache_is_live(volume->cache)) + return false; + __fscache_begin_volume_access(volume, cookie, why); + if (!fscache_cache_is_live(volume->cache)) { + fscache_end_volume_access(volume, cookie, fscache_access_unlive); + return false; + } + return true; +} + +/** + * fscache_end_volume_access - Unpin a cache at the end of an access. + * @volume: The volume cookie + * @cookie: A datafile cookie for a tracing reference (or NULL) + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache volume after we've accessed it. The datafile @cookie and the + * @why indicator are merely provided for tracing purposes. + */ +void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&volume->n_accesses); + trace_fscache_access_volume(volume->debug_id, cookie ? cookie->debug_id : 0, + refcount_read(&volume->ref), + n_accesses, why); + if (n_accesses == 0) + wake_up_var(&volume->n_accesses); +} +EXPORT_SYMBOL(fscache_end_volume_access); + static bool fscache_volume_same(const struct fscache_volume *a, const struct fscache_volume *b) { diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index c4355b888c91..fbbd8a2afe12 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -53,6 +53,10 @@ extern struct rw_semaphore fscache_addremove_sem; extern struct fscache_cache *fscache_acquire_cache(const char *name); extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern void fscache_end_volume_access(struct fscache_volume *volume, + struct fscache_cookie *cookie, + enum fscache_access_trace why); + extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); extern void fscache_put_cookie(struct fscache_cookie *cookie, diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 734966bc49e1..4f40cfa52469 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -43,6 +43,7 @@ enum fscache_volume_trace { fscache_volume_put_relinquish, fscache_volume_see_create_work, fscache_volume_see_hash_wake, + fscache_volume_wait_create_work, }; enum fscache_cookie_trace { @@ -245,6 +246,39 @@ TRACE_EVENT(fscache_access_cache, __entry->n_accesses) ); +TRACE_EVENT(fscache_access_volume, + TP_PROTO(unsigned int volume_debug_id, + unsigned int cookie_debug_id, + int ref, + int n_accesses, + enum fscache_access_trace why), + + TP_ARGS(volume_debug_id, cookie_debug_id, ref, n_accesses, why), + + TP_STRUCT__entry( + __field(unsigned int, volume ) + __field(unsigned int, cookie ) + __field(int, ref ) + __field(int, n_accesses ) + __field(enum fscache_access_trace, why ) + ), + + TP_fast_assign( + __entry->volume = volume_debug_id; + __entry->cookie = cookie_debug_id; + __entry->ref = ref; + __entry->n_accesses = n_accesses; + __entry->why = why; + ), + + TP_printk("V=%08x c=%08x %s r=%d a=%d", + __entry->volume, + __entry->cookie, + __print_symbolic(__entry->why, fscache_access_traces), + __entry->ref, + __entry->n_accesses) + ); + TRACE_EVENT(fscache_acquire, TP_PROTO(struct fscache_cookie *cookie), -- cgit v1.2.3 From a7733fb632722a2f085f9324f14783effe268ed3 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie-level access helpers Add a number of helper functions to manage access to a cookie, pinning the cache object in place for the duration to prevent cache withdrawal from removing it: (1) void fscache_init_access_gate(struct fscache_cookie *cookie); This function initialises the access count when a cache binds to a cookie. An extra ref is taken on the access count to prevent wakeups while the cache is active. We're only interested in the wakeup when a cookie is being withdrawn and we're waiting for it to quiesce - at which point the counter will be decremented before the wait. The FSCACHE_COOKIE_NACC_ELEVATED flag is set on the cookie to keep track of the extra ref in order to handle a race between relinquishment and withdrawal both trying to drop the extra ref. (2) bool fscache_begin_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); This function attempts to begin access upon a cookie, pinning it in place if it's cached. If successful, it returns true and leaves a the access count incremented. (3) void fscache_end_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); This function drops the access count obtained by (2), permitting object withdrawal to take place when it reaches zero. A tracepoint is provided to track changes to the access counter on a cookie. Changes ======= ver #2: - Don't hold n_accesses elevated whilst cache is bound to a cookie, but rather add a flag that prevents the state machine from being queued when n_accesses reaches 0. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819595085.215744.1706073049250505427.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906895313.143852.10141619544149102193.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967095980.1823006.1133648159424418877.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021503063.640689.8870918985269528670.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 98 ++++++++++++++++++++++++++++++++++++++++++ fs/fscache/internal.h | 3 ++ fs/fscache/main.c | 1 + include/linux/fscache-cache.h | 2 + include/trace/events/fscache.h | 29 +++++++++++++ 5 files changed, 133 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 438b0098aa73..04d2127bd354 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -62,6 +62,104 @@ static void fscache_free_cookie(struct fscache_cookie *cookie) kmem_cache_free(fscache_cookie_jar, cookie); } +/* + * Initialise the access gate on a cookie by setting a flag to prevent the + * state machine from being queued when the access counter transitions to 0. + * We're only interested in this when we withdraw caching services from the + * cookie. + */ +static void fscache_init_access_gate(struct fscache_cookie *cookie) +{ + int n_accesses; + + n_accesses = atomic_read(&cookie->n_accesses); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, fscache_access_cache_pin); + set_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags); +} + +/** + * fscache_end_cookie_access - Unpin a cache at the end of an access. + * @cookie: A data file cookie + * @why: An indication of the circumstances of the access for tracing + * + * Unpin a cache cookie after we've accessed it and bring a deferred + * relinquishment or withdrawal state into effect. + * + * The @why indicator is provided for tracing purposes. + */ +void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + smp_mb__before_atomic(); + n_accesses = atomic_dec_return(&cookie->n_accesses); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, why); + if (n_accesses == 0 && + !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) { + // PLACEHOLDER: Need to poke the state machine + } +} +EXPORT_SYMBOL(fscache_end_cookie_access); + +/* + * Pin the cache behind a cookie so that we can access it. + */ +static void __fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + int n_accesses; + + n_accesses = atomic_inc_return(&cookie->n_accesses); + smp_mb__after_atomic(); /* (Future) read state after is-caching. + * Reread n_accesses after is-caching + */ + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, why); +} + +/** + * fscache_begin_cookie_access - Pin a cache so data can be accessed + * @cookie: A data file cookie + * @why: An indication of the circumstances of the access for tracing + * + * Attempt to pin the cache to prevent it from going away whilst we're + * accessing data and returns true if successful. This works as follows: + * + * (1) If the cookie is not being cached (ie. FSCACHE_COOKIE_IS_CACHING is not + * set), we return false to indicate access was not permitted. + * + * (2) If the cookie is being cached, we increment its n_accesses count and + * then recheck the IS_CACHING flag, ending the access if it got cleared. + * + * (3) When we end the access, we decrement the cookie's n_accesses and wake + * up the any waiters if it reaches 0. + * + * (4) Whilst the cookie is actively being cached, its n_accesses is kept + * artificially incremented to prevent wakeups from happening. + * + * (5) When the cache is taken offline or if the cookie is culled, the flag is + * cleared to prevent new accesses, the cookie's n_accesses is decremented + * and we wait for it to become 0. + * + * The @why indicator are merely provided for tracing purposes. + */ +bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why) +{ + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) + return false; + __fscache_begin_cookie_access(cookie, why); + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags) || + !fscache_cache_is_live(cookie->volume->cache)) { + fscache_end_cookie_access(cookie, fscache_access_unlive); + return false; + } + return true; +} + static inline void wake_up_cookie_state(struct fscache_cookie *cookie) { /* Use a barrier to ensure that waiters see the state variable diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 91a4ea08ec0b..e0d8ef212e82 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -59,6 +59,9 @@ extern struct kmem_cache *fscache_cookie_jar; extern const struct seq_operations fscache_cookies_seq_ops; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); +extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); + static inline void fscache_see_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where) { diff --git a/fs/fscache/main.c b/fs/fscache/main.c index 6cab5d99ba4c..dad85fd84f6f 100644 --- a/fs/fscache/main.c +++ b/fs/fscache/main.c @@ -23,6 +23,7 @@ MODULE_PARM_DESC(fscache_debug, EXPORT_TRACEPOINT_SYMBOL(fscache_access_cache); EXPORT_TRACEPOINT_SYMBOL(fscache_access_volume); +EXPORT_TRACEPOINT_SYMBOL(fscache_access); struct workqueue_struct *fscache_wq; EXPORT_SYMBOL(fscache_wq); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index fbbd8a2afe12..66624407ba84 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -61,6 +61,8 @@ extern struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); extern void fscache_put_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); +extern void fscache_end_cookie_access(struct fscache_cookie *cookie, + enum fscache_access_trace why); extern void fscache_set_cookie_state(struct fscache_cookie *cookie, enum fscache_cookie_state state); diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 4f40cfa52469..b1a962adfd16 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -279,6 +279,35 @@ TRACE_EVENT(fscache_access_volume, __entry->n_accesses) ); +TRACE_EVENT(fscache_access, + TP_PROTO(unsigned int cookie_debug_id, + int ref, + int n_accesses, + enum fscache_access_trace why), + + TP_ARGS(cookie_debug_id, ref, n_accesses, why), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(int, ref ) + __field(int, n_accesses ) + __field(enum fscache_access_trace, why ) + ), + + TP_fast_assign( + __entry->cookie = cookie_debug_id; + __entry->ref = ref; + __entry->n_accesses = n_accesses; + __entry->why = why; + ), + + TP_printk("c=%08x %s r=%d a=%d", + __entry->cookie, + __print_symbolic(__entry->why, fscache_access_traces), + __entry->ref, + __entry->n_accesses) + ); + TRACE_EVENT(fscache_acquire, TP_PROTO(struct fscache_cookie *cookie), -- cgit v1.2.3 From 2e0c76aee25f33c482abda6224bd87732359354d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:00:26 +0100 Subject: fscache: Implement functions add/remove a cache Implement functions to allow the cache backend to add or remove a cache: (1) Declare a cache to be live: int fscache_add_cache(struct fscache_cache *cache, const struct fscache_cache_ops *ops, void *cache_priv); Take a previously acquired cache cookie, set the operations table and private data and mark the cache open for access. (2) Withdraw a cache from service: void fscache_withdraw_cache(struct fscache_cache *cache); This marks the cache as withdrawn and thus prevents further cache-level and volume-level accesses. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819596022.215744.8799712491432238827.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906896599.143852.17049208999019262884.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967097870.1823006.3470041000971522030.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021505541.640689.1819714759326331054.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cache.c | 70 +++++++++++++++++++++++++++++++++++++++++++ include/linux/fscache-cache.h | 13 ++++++++ 2 files changed, 83 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index e867cff53a70..bbd102be91c4 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -210,12 +210,55 @@ void fscache_relinquish_cache(struct fscache_cache *cache) fscache_cache_put_prep_failed : fscache_cache_put_relinquish; + cache->ops = NULL; cache->cache_priv = NULL; smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); +/** + * fscache_add_cache - Declare a cache as being open for business + * @cache: The cache-level cookie representing the cache + * @ops: Table of cache operations to use + * @cache_priv: Private data for the cache record + * + * Add a cache to the system, making it available for netfs's to use. + * + * See Documentation/filesystems/caching/backend-api.rst for a complete + * description. + */ +int fscache_add_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + void *cache_priv) +{ + int n_accesses; + + _enter("{%s,%s}", ops->name, cache->name); + + BUG_ON(fscache_cache_state(cache) != FSCACHE_CACHE_IS_PREPARING); + + /* Get a ref on the cache cookie and keep its n_accesses counter raised + * by 1 to prevent wakeups from transitioning it to 0 until we're + * withdrawing caching services from it. + */ + n_accesses = atomic_inc_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, fscache_access_cache_pin); + + down_write(&fscache_addremove_sem); + + cache->ops = ops; + cache->cache_priv = cache_priv; + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_ACTIVE); + + up_write(&fscache_addremove_sem); + pr_notice("Cache \"%s\" added (type %s)\n", cache->name, ops->name); + _leave(" = 0 [%s]", cache->name); + return 0; +} +EXPORT_SYMBOL(fscache_add_cache); + /** * fscache_begin_cache_access - Pin a cache so it can be accessed * @cache: The cache-level cookie @@ -278,6 +321,33 @@ void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_t wake_up_var(&cache->n_accesses); } +/** + * fscache_withdraw_cache - Withdraw a cache from the active service + * @cache: The cache cookie + * + * Begin the process of withdrawing a cache from service. This stops new + * cache-level and volume-level accesses from taking place and waits for + * currently ongoing cache-level accesses to end. + */ +void fscache_withdraw_cache(struct fscache_cache *cache) +{ + int n_accesses; + + pr_notice("Withdrawing cache \"%s\" (%u objs)\n", + cache->name, atomic_read(&cache->object_count)); + + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_WITHDRAWN); + + /* Allow wakeups on dec-to-0 */ + n_accesses = atomic_dec_return(&cache->n_accesses); + trace_fscache_access_cache(cache->debug_id, refcount_read(&cache->ref), + n_accesses, fscache_access_cache_unpin); + + wait_var_event(&cache->n_accesses, + atomic_read(&cache->n_accesses) == 0); +} +EXPORT_SYMBOL(fscache_withdraw_cache); + #ifdef CONFIG_PROC_FS static const char fscache_cache_states[NR__FSCACHE_CACHE_STATE] = "-PAEW"; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 66624407ba84..f78add6e7823 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -33,6 +33,7 @@ enum fscache_cache_state { * Cache cookie. */ struct fscache_cache { + const struct fscache_cache_ops *ops; struct list_head cache_link; /* Link in cache list */ void *cache_priv; /* Private cache data (or NULL) */ refcount_t ref; @@ -44,6 +45,14 @@ struct fscache_cache { char *name; }; +/* + * cache operations + */ +struct fscache_cache_ops { + /* name of cache provider */ + const char *name; +}; + extern struct workqueue_struct *fscache_wq; /* @@ -52,6 +61,10 @@ extern struct workqueue_struct *fscache_wq; extern struct rw_semaphore fscache_addremove_sem; extern struct fscache_cache *fscache_acquire_cache(const char *name); extern void fscache_relinquish_cache(struct fscache_cache *cache); +extern int fscache_add_cache(struct fscache_cache *cache, + const struct fscache_cache_ops *ops, + void *cache_priv); +extern void fscache_withdraw_cache(struct fscache_cache *cache); extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, -- cgit v1.2.3 From bfa22da3ed652aa15acd4246fa13a0de6dbe4a59 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:26:17 +0100 Subject: fscache: Provide and use cache methods to lookup/create/free a volume Add cache methods to lookup, create and remove a volume. Looking up or creating the volume requires the cache pinning for access; freeing the volume requires the volume pinning for access. The ->acquire_volume() method is used to ask the cache backend to lookup and, if necessary, create a volume; the ->free_volume() method is used to free the resources for a volume. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819597821.215744.5225318658134989949.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906898645.143852.8537799955945956818.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967099771.1823006.1455197910571061835.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021507345.640689.4073511598838843040.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/volume.c | 89 ++++++++++++++++++++++++++++++++++++++++-- include/linux/fscache-cache.h | 7 ++++ include/trace/events/fscache.h | 11 +++++- 3 files changed, 103 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index 20497f0f10bb..e1a8e92a6adb 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -15,6 +15,8 @@ static struct hlist_bl_head fscache_volume_hash[1 << fscache_volume_hash_shift]; static atomic_t fscache_volume_debug_id; static LIST_HEAD(fscache_volumes); +static void fscache_create_volume_work(struct work_struct *work); + struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where) { @@ -213,7 +215,7 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, volume->cache = cache; INIT_LIST_HEAD(&volume->proc_link); - INIT_WORK(&volume->work, NULL /* PLACEHOLDER */); + INIT_WORK(&volume->work, fscache_create_volume_work); refcount_set(&volume->ref, 1); spin_lock_init(&volume->lock); @@ -249,6 +251,58 @@ err_cache: return NULL; } +/* + * Create a volume's representation on disk. Have a volume ref and a cache + * access we have to release. + */ +static void fscache_create_volume_work(struct work_struct *work) +{ + const struct fscache_cache_ops *ops; + struct fscache_volume *volume = + container_of(work, struct fscache_volume, work); + + fscache_see_volume(volume, fscache_volume_see_create_work); + + ops = volume->cache->ops; + if (ops->acquire_volume) + ops->acquire_volume(volume); + fscache_end_cache_access(volume->cache, + fscache_access_acquire_volume_end); + + clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); + wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); + fscache_put_volume(volume, fscache_volume_put_create_work); +} + +/* + * Dispatch a worker thread to create a volume's representation on disk. + */ +void fscache_create_volume(struct fscache_volume *volume, bool wait) +{ + if (test_and_set_bit(FSCACHE_VOLUME_CREATING, &volume->flags)) + goto maybe_wait; + if (volume->cache_priv) + goto no_wait; /* We raced */ + if (!fscache_begin_cache_access(volume->cache, + fscache_access_acquire_volume)) + goto no_wait; + + fscache_get_volume(volume, fscache_volume_get_create_work); + if (!schedule_work(&volume->work)) + fscache_put_volume(volume, fscache_volume_put_create_work); + +maybe_wait: + if (wait) { + fscache_see_volume(volume, fscache_volume_wait_create_work); + wait_on_bit(&volume->flags, FSCACHE_VOLUME_CREATING, + TASK_UNINTERRUPTIBLE); + } + return; +no_wait: + clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); + wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); +} + /* * Acquire a volume representation cookie and link it to a (proposed) cache. */ @@ -269,7 +323,7 @@ struct fscache_volume *__fscache_acquire_volume(const char *volume_key, return ERR_PTR(-EBUSY); } - // PLACEHOLDER: Create the volume if we have a cache available + fscache_create_volume(volume, false); return volume; } EXPORT_SYMBOL(__fscache_acquire_volume); @@ -316,7 +370,12 @@ static void fscache_free_volume(struct fscache_volume *volume) struct fscache_cache *cache = volume->cache; if (volume->cache_priv) { - // PLACEHOLDER: Detach any attached cache + __fscache_begin_volume_access(volume, NULL, + fscache_access_relinquish_volume); + if (volume->cache_priv) + cache->ops->free_volume(volume); + fscache_end_volume_access(volume, NULL, + fscache_access_relinquish_volume_end); } down_write(&fscache_addremove_sem); @@ -369,6 +428,30 @@ void __fscache_relinquish_volume(struct fscache_volume *volume, } EXPORT_SYMBOL(__fscache_relinquish_volume); +/** + * fscache_withdraw_volume - Withdraw a volume from being cached + * @volume: Volume cookie + * + * Withdraw a cache volume from service, waiting for all accesses to complete + * before returning. + */ +void fscache_withdraw_volume(struct fscache_volume *volume) +{ + int n_accesses; + + _debug("withdraw V=%x", volume->debug_id); + + /* Allow wakeups on dec-to-0 */ + n_accesses = atomic_dec_return(&volume->n_accesses); + trace_fscache_access_volume(volume->debug_id, 0, + refcount_read(&volume->ref), + n_accesses, fscache_access_cache_unpin); + + wait_var_event(&volume->n_accesses, + atomic_read(&volume->n_accesses) == 0); +} +EXPORT_SYMBOL(fscache_withdraw_volume); + #ifdef CONFIG_PROC_FS /* * Generate a list of volumes in /proc/fs/fscache/volumes diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index f78add6e7823..a10b66ca3544 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -51,6 +51,12 @@ struct fscache_cache { struct fscache_cache_ops { /* name of cache provider */ const char *name; + + /* Acquire a volume */ + void (*acquire_volume)(struct fscache_volume *volume); + + /* Free the cache's data attached to a volume */ + void (*free_volume)(struct fscache_volume *volume); }; extern struct workqueue_struct *fscache_wq; @@ -65,6 +71,7 @@ extern int fscache_add_cache(struct fscache_cache *cache, const struct fscache_cache_ops *ops, void *cache_priv); extern void fscache_withdraw_cache(struct fscache_cache *cache); +extern void fscache_withdraw_volume(struct fscache_volume *volume); extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index b1a962adfd16..1d576bd8112e 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -64,8 +64,12 @@ enum fscache_cookie_trace { }; enum fscache_access_trace { + fscache_access_acquire_volume, + fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_relinquish_volume, + fscache_access_relinquish_volume_end, fscache_access_unlive, }; @@ -96,7 +100,8 @@ enum fscache_access_trace { EM(fscache_volume_put_hash_collision, "PUT hcoll") \ EM(fscache_volume_put_relinquish, "PUT relnq") \ EM(fscache_volume_see_create_work, "SEE creat") \ - E_(fscache_volume_see_hash_wake, "SEE hwake") + EM(fscache_volume_see_hash_wake, "SEE hwake") \ + E_(fscache_volume_wait_create_work, "WAIT crea") #define fscache_cookie_traces \ EM(fscache_cookie_collision, "*COLLIDE*") \ @@ -115,8 +120,12 @@ enum fscache_access_trace { E_(fscache_cookie_see_work, "- work ") #define fscache_access_traces \ + EM(fscache_access_acquire_volume, "BEGIN acq_vol") \ + EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_relinquish_volume, "BEGIN rlq_vol") \ + EM(fscache_access_relinquish_volume_end,"END rlq_vol") \ E_(fscache_access_unlive, "END unlive ") /* -- cgit v1.2.3 From 29f18e79fe7c5f8011befeda9be6b220a350f947 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:00:26 +0100 Subject: fscache: Add a function for a cache backend to note an I/O error Add a function to the backend API to note an I/O error in a cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819598741.215744.891281275151382095.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906901316.143852.15225412215771586528.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967100721.1823006.16435671567428949398.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021508840.640689.11902836226570620424.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cache.c | 20 ++++++++++++++++++++ include/linux/fscache-cache.h | 2 ++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index bbd102be91c4..25eac61f1c29 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -321,6 +321,26 @@ void fscache_end_cache_access(struct fscache_cache *cache, enum fscache_access_t wake_up_var(&cache->n_accesses); } +/** + * fscache_io_error - Note a cache I/O error + * @cache: The record describing the cache + * + * Note that an I/O error occurred in a cache and that it should no longer be + * used for anything. This also reports the error into the kernel log. + * + * See Documentation/filesystems/caching/backend-api.rst for a complete + * description. + */ +void fscache_io_error(struct fscache_cache *cache) +{ + if (fscache_set_cache_state_maybe(cache, + FSCACHE_CACHE_IS_ACTIVE, + FSCACHE_CACHE_GOT_IOERROR)) + pr_err("Cache '%s' stopped due to I/O error\n", + cache->name); +} +EXPORT_SYMBOL(fscache_io_error); + /** * fscache_withdraw_cache - Withdraw a cache from the active service * @cache: The cache cookie diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index a10b66ca3544..936ef731bbc7 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -73,6 +73,8 @@ extern int fscache_add_cache(struct fscache_cache *cache, extern void fscache_withdraw_cache(struct fscache_cache *cache); extern void fscache_withdraw_volume(struct fscache_volume *volume); +extern void fscache_io_error(struct fscache_cache *cache); + extern void fscache_end_volume_access(struct fscache_volume *volume, struct fscache_cookie *cookie, enum fscache_access_trace why); -- cgit v1.2.3 From 5d00e426f95e7ea036fec2a0aceb3f71d6dbdf92 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement simple cookie state machine Implement a very simple cookie state machine to handle lookup, invalidation, withdrawal, relinquishment and, to be added later, commit on LRU discard. Three cache methods are provided: ->lookup_cookie() to look up and, if necessary, create a data storage object; ->withdraw_cookie() to free the resources associated with that object and potentially delete it; and ->prepare_to_write(), to do prepare for changes to the cached data to be modified locally. Changes ======= ver #3: - Fix a race between LRU discard and relinquishment whereby the former would override the latter and thus the latter would never happen[1]. ver #2: - Don't hold n_accesses elevated whilst cache is bound to a cookie, but rather add a flag that prevents the state machine from being queued when n_accesses reaches 0. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/599331.1639410068@warthog.procyon.org.uk/ [1] Link: https://lore.kernel.org/r/163819599657.215744.15799615296912341745.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906903925.143852.1805855338154353867.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967105456.1823006.14730395299835841776.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021510706.640689.7961423370243272583.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 313 +++++++++++++++++++++++++++++++++++------ include/linux/fscache-cache.h | 27 +++- include/trace/events/fscache.h | 4 + 3 files changed, 300 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 04d2127bd354..336046de08ee 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -15,7 +15,8 @@ struct kmem_cache *fscache_cookie_jar; -static void fscache_drop_cookie(struct fscache_cookie *cookie); +static void fscache_cookie_worker(struct work_struct *work); +static void fscache_unhash_cookie(struct fscache_cookie *cookie); #define fscache_cookie_hash_shift 15 static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; @@ -62,6 +63,19 @@ static void fscache_free_cookie(struct fscache_cookie *cookie) kmem_cache_free(fscache_cookie_jar, cookie); } +static void __fscache_queue_cookie(struct fscache_cookie *cookie) +{ + if (!queue_work(fscache_wq, &cookie->work)) + fscache_put_cookie(cookie, fscache_cookie_put_over_queued); +} + +static void fscache_queue_cookie(struct fscache_cookie *cookie, + enum fscache_cookie_trace where) +{ + fscache_get_cookie(cookie, where); + __fscache_queue_cookie(cookie); +} + /* * Initialise the access gate on a cookie by setting a flag to prevent the * state machine from being queued when the access counter transitions to 0. @@ -98,9 +112,8 @@ void fscache_end_cookie_access(struct fscache_cookie *cookie, trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), n_accesses, why); if (n_accesses == 0 && - !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) { - // PLACEHOLDER: Need to poke the state machine - } + !test_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags)) + fscache_queue_cookie(cookie, fscache_cookie_get_end_access); } EXPORT_SYMBOL(fscache_end_cookie_access); @@ -171,35 +184,58 @@ static inline void wake_up_cookie_state(struct fscache_cookie *cookie) wake_up_var(&cookie->state); } +/* + * Change the state a cookie is at and wake up anyone waiting for that. Impose + * an ordering between the stuff stored in the cookie and the state member. + * Paired with fscache_cookie_state(). + */ static void __fscache_set_cookie_state(struct fscache_cookie *cookie, enum fscache_cookie_state state) { - cookie->state = state; + smp_store_release(&cookie->state, state); } -/* - * Change the state a cookie is at and wake up anyone waiting for that - but - * only if the cookie isn't already marked as being in a cleanup state. - */ -void fscache_set_cookie_state(struct fscache_cookie *cookie, - enum fscache_cookie_state state) +static void fscache_set_cookie_state(struct fscache_cookie *cookie, + enum fscache_cookie_state state) { - bool changed = false; - spin_lock(&cookie->lock); - switch (cookie->state) { - case FSCACHE_COOKIE_STATE_RELINQUISHING: - break; - default: - __fscache_set_cookie_state(cookie, state); - changed = true; - break; - } + __fscache_set_cookie_state(cookie, state); spin_unlock(&cookie->lock); - if (changed) - wake_up_cookie_state(cookie); + wake_up_cookie_state(cookie); +} + +/** + * fscache_cookie_lookup_negative - Note negative lookup + * @cookie: The cookie that was being looked up + * + * Note that some part of the metadata path in the cache doesn't exist and so + * we can release any waiting readers in the certain knowledge that there's + * nothing for them to actually read. + * + * This function uses no locking and must only be called from the state machine. + */ +void fscache_cookie_lookup_negative(struct fscache_cookie *cookie) +{ + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_CREATING); +} +EXPORT_SYMBOL(fscache_cookie_lookup_negative); + +/** + * fscache_caching_failed - Report that a failure stopped caching on a cookie + * @cookie: The cookie that was affected + * + * Tell fscache that caching on a cookie needs to be stopped due to some sort + * of failure. + * + * This function uses no locking and must only be called from the state machine. + */ +void fscache_caching_failed(struct fscache_cookie *cookie) +{ + clear_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_FAILED); } -EXPORT_SYMBOL(fscache_set_cookie_state); +EXPORT_SYMBOL(fscache_caching_failed); /* * Set the index key in a cookie. The cookie struct has space for a 16-byte @@ -291,10 +327,10 @@ static struct fscache_cookie *fscache_alloc_cookie( refcount_set(&cookie->ref, 1); cookie->debug_id = atomic_inc_return(&fscache_cookie_debug_id); - cookie->state = FSCACHE_COOKIE_STATE_QUIESCENT; spin_lock_init(&cookie->lock); INIT_LIST_HEAD(&cookie->commit_link); - INIT_WORK(&cookie->work, NULL /* PLACEHOLDER */); + INIT_WORK(&cookie->work, fscache_cookie_worker); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); write_lock(&fscache_cookies_lock); list_add_tail(&cookie->proc_link, &fscache_cookies); @@ -417,6 +453,192 @@ struct fscache_cookie *__fscache_acquire_cookie( } EXPORT_SYMBOL(__fscache_acquire_cookie); +/* + * Prepare a cache object to be written to. + */ +static void fscache_prepare_to_write(struct fscache_cookie *cookie) +{ + cookie->volume->cache->ops->prepare_to_write(cookie); +} + +/* + * Look up a cookie in the cache. + */ +static void fscache_perform_lookup(struct fscache_cookie *cookie) +{ + enum fscache_access_trace trace = fscache_access_lookup_cookie_end_failed; + bool need_withdraw = false; + + _enter(""); + + if (!cookie->volume->cache_priv) { + fscache_create_volume(cookie->volume, true); + if (!cookie->volume->cache_priv) { + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + goto out; + } + } + + if (!cookie->volume->cache->ops->lookup_cookie(cookie)) { + if (cookie->state != FSCACHE_COOKIE_STATE_FAILED) + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + need_withdraw = true; + _leave(" [fail]"); + goto out; + } + + fscache_see_cookie(cookie, fscache_cookie_see_active); + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); + trace = fscache_access_lookup_cookie_end; + +out: + fscache_end_cookie_access(cookie, trace); + if (need_withdraw) + fscache_withdraw_cookie(cookie); + fscache_end_volume_access(cookie->volume, cookie, trace); +} + +/* + * Perform work upon the cookie, such as committing its cache state, + * relinquishing it or withdrawing the backing cache. We're protected from the + * cache going away under us as object withdrawal must come through this + * non-reentrant work item. + */ +static void fscache_cookie_state_machine(struct fscache_cookie *cookie) +{ + enum fscache_cookie_state state; + bool wake = false; + + _enter("c=%x", cookie->debug_id); + +again: + spin_lock(&cookie->lock); +again_locked: + state = cookie->state; + switch (state) { + case FSCACHE_COOKIE_STATE_QUIESCENT: + /* The QUIESCENT state is jumped to the LOOKING_UP state by + * fscache_use_cookie(). + */ + + if (atomic_read(&cookie->n_accesses) == 0 && + test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_RELINQUISHING); + wake = true; + goto again_locked; + } + break; + + case FSCACHE_COOKIE_STATE_LOOKING_UP: + spin_unlock(&cookie->lock); + fscache_init_access_gate(cookie); + fscache_perform_lookup(cookie); + goto again; + + case FSCACHE_COOKIE_STATE_ACTIVE: + if (test_and_clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags)) { + spin_unlock(&cookie->lock); + fscache_prepare_to_write(cookie); + spin_lock(&cookie->lock); + } + fallthrough; + + case FSCACHE_COOKIE_STATE_FAILED: + if (atomic_read(&cookie->n_accesses) != 0) + break; + if (test_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_RELINQUISHING); + wake = true; + goto again_locked; + } + if (test_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_WITHDRAWING); + wake = true; + goto again_locked; + } + break; + + case FSCACHE_COOKIE_STATE_RELINQUISHING: + case FSCACHE_COOKIE_STATE_WITHDRAWING: + if (cookie->cache_priv) { + spin_unlock(&cookie->lock); + cookie->volume->cache->ops->withdraw_cookie(cookie); + spin_lock(&cookie->lock); + } + + switch (state) { + case FSCACHE_COOKIE_STATE_RELINQUISHING: + fscache_see_cookie(cookie, fscache_cookie_see_relinquish); + fscache_unhash_cookie(cookie); + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_DROPPED); + wake = true; + goto out; + case FSCACHE_COOKIE_STATE_WITHDRAWING: + fscache_see_cookie(cookie, fscache_cookie_see_withdraw); + break; + default: + BUG(); + } + + clear_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags); + clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_QUIESCENT); + wake = true; + goto again_locked; + + case FSCACHE_COOKIE_STATE_DROPPED: + break; + + default: + WARN_ONCE(1, "Cookie %x in unexpected state %u\n", + cookie->debug_id, state); + break; + } + +out: + spin_unlock(&cookie->lock); + if (wake) + wake_up_cookie_state(cookie); + _leave(""); +} + +static void fscache_cookie_worker(struct work_struct *work) +{ + struct fscache_cookie *cookie = container_of(work, struct fscache_cookie, work); + + fscache_see_cookie(cookie, fscache_cookie_see_work); + fscache_cookie_state_machine(cookie); + fscache_put_cookie(cookie, fscache_cookie_put_work); +} + +/* + * Wait for the object to become inactive. The cookie's work item will be + * scheduled when someone transitions n_accesses to 0 - but if someone's + * already done that, schedule it anyway. + */ +static void __fscache_withdraw_cookie(struct fscache_cookie *cookie) +{ + int n_accesses; + bool unpinned; + + unpinned = test_and_clear_bit(FSCACHE_COOKIE_NO_ACCESS_WAKE, &cookie->flags); + + /* Need to read the access count after unpinning */ + n_accesses = atomic_read(&cookie->n_accesses); + if (unpinned) + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + n_accesses, fscache_access_cache_unpin); + if (n_accesses == 0) + fscache_queue_cookie(cookie, fscache_cookie_get_end_access); +} + /* * Remove a cookie from the hash table. */ @@ -432,21 +654,27 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie) hlist_bl_del(&cookie->hash_link); clear_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags); hlist_bl_unlock(h); + fscache_stat(&fscache_n_relinquishes_dropped); } -/* - * Finalise a cookie after all its resources have been disposed of. - */ -static void fscache_drop_cookie(struct fscache_cookie *cookie) +static void fscache_drop_withdraw_cookie(struct fscache_cookie *cookie) { - spin_lock(&cookie->lock); - __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); - spin_unlock(&cookie->lock); - wake_up_cookie_state(cookie); + __fscache_withdraw_cookie(cookie); +} - fscache_unhash_cookie(cookie); - fscache_stat(&fscache_n_relinquishes_dropped); +/** + * fscache_withdraw_cookie - Mark a cookie for withdrawal + * @cookie: The cookie to be withdrawn. + * + * Allow the cache backend to withdraw the backing for a cookie for its own + * reasons, even if that cookie is in active use. + */ +void fscache_withdraw_cookie(struct fscache_cookie *cookie) +{ + set_bit(FSCACHE_COOKIE_DO_WITHDRAW, &cookie->flags); + fscache_drop_withdraw_cookie(cookie); } +EXPORT_SYMBOL(fscache_withdraw_cookie); /* * Allow the netfs to release a cookie back to the cache. @@ -473,12 +701,13 @@ void __fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) ASSERTCMP(atomic_read(&cookie->volume->n_cookies), >, 0); atomic_dec(&cookie->volume->n_cookies); - set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); - - if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) - ; // PLACEHOLDER: Do something here if the cookie was cached - else - fscache_drop_cookie(cookie); + if (test_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags)) { + set_bit(FSCACHE_COOKIE_DO_RELINQUISH, &cookie->flags); + fscache_drop_withdraw_cookie(cookie); + } else { + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_DROPPED); + fscache_unhash_cookie(cookie); + } fscache_put_cookie(cookie, fscache_cookie_put_relinquish); } EXPORT_SYMBOL(__fscache_relinquish_cookie); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 936ef731bbc7..ae6a75976450 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -57,6 +57,15 @@ struct fscache_cache_ops { /* Free the cache's data attached to a volume */ void (*free_volume)(struct fscache_volume *volume); + + /* Look up a cookie in the cache */ + bool (*lookup_cookie)(struct fscache_cookie *cookie); + + /* Withdraw an object without any cookie access counts held */ + void (*withdraw_cookie)(struct fscache_cookie *cookie); + + /* Prepare to write to a live cache object */ + void (*prepare_to_write)(struct fscache_cookie *cookie); }; extern struct workqueue_struct *fscache_wq; @@ -72,6 +81,7 @@ extern int fscache_add_cache(struct fscache_cache *cache, void *cache_priv); extern void fscache_withdraw_cache(struct fscache_cache *cache); extern void fscache_withdraw_volume(struct fscache_volume *volume); +extern void fscache_withdraw_cookie(struct fscache_cookie *cookie); extern void fscache_io_error(struct fscache_cache *cache); @@ -85,8 +95,21 @@ extern void fscache_put_cookie(struct fscache_cookie *cookie, enum fscache_cookie_trace where); extern void fscache_end_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); -extern void fscache_set_cookie_state(struct fscache_cookie *cookie, - enum fscache_cookie_state state); +extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); +extern void fscache_caching_failed(struct fscache_cookie *cookie); + +/** + * fscache_cookie_state - Read the state of a cookie + * @cookie: The cookie to query + * + * Get the state of a cookie, imposing an ordering between the cookie contents + * and the state value. Paired with fscache_set_cookie_state(). + */ +static inline +enum fscache_cookie_state fscache_cookie_state(struct fscache_cookie *cookie) +{ + return smp_load_acquire(&cookie->state); +} /** * fscache_get_key - Get a pointer to the cookie key diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 1d576bd8112e..030c97bb9c8b 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -68,6 +68,8 @@ enum fscache_access_trace { fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_lookup_cookie_end, + fscache_access_lookup_cookie_end_failed, fscache_access_relinquish_volume, fscache_access_relinquish_volume_end, fscache_access_unlive, @@ -124,6 +126,8 @@ enum fscache_access_trace { EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_lookup_cookie_end, "END lookup ") \ + EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ EM(fscache_access_relinquish_volume, "BEGIN rlq_vol") \ EM(fscache_access_relinquish_volume_end,"END rlq_vol") \ E_(fscache_access_unlive, "END unlive ") -- cgit v1.2.3 From 12bb21a29c19aae50cfad4e2bb5c943108f34a7d Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie user counting and resource pinning Provide a pair of functions to count the number of users of a cookie (open files, writeback, invalidation, resizing, reads, writes), to obtain and pin resources for the cookie and to prevent culling for the whilst there are users. The first function marks a cookie as being in use: void fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify); The caller should indicate the cookie to use and whether or not the caller is in a context that may modify the cookie (e.g. a file open O_RDWR). If the cookie is not already resourced, fscache will ask the cache backend in the background to do whatever it needs to look up, create or otherwise obtain the resources necessary to access data. This is pinned to the cookie and may not be culled, though it may be withdrawn if the cache as a whole is withdrawn. The second function removes the in-use mark from a cookie and, optionally, updates the coherency data: void fscache_unuse_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size); If non-NULL, the aux_data buffer and/or the object_size will be saved into the cookie and will be set on the backing store when the object is committed. If this removes the last usage on a cookie, the cookie is placed onto an LRU list from which it will be removed and closed after a couple of seconds if it doesn't get reused. This prevents resource overload in the cache - in particular it prevents it from holding too many files open. Changes ======= ver #2: - Fix fscache_unuse_cookie() to use atomic_dec_and_lock() to avoid a potential race if the cookie gets reused before it completes the unusement. - Added missing transition to LRU_DISCARDING state. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819600612.215744.13678350304176542741.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906907567.143852.16979631199380722019.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967106467.1823006.6790864931048582667.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021511674.640689.10084988363699111860.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 218 ++++++++++++++++++++++++++++++++++++++++- fs/fscache/internal.h | 5 + fs/fscache/stats.c | 12 +++ include/linux/fscache.h | 82 +++++++++++++++- include/trace/events/fscache.h | 12 +++ 5 files changed, 327 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 336046de08ee..2f5ee717f2bb 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -15,6 +15,8 @@ struct kmem_cache *fscache_cookie_jar; +static void fscache_cookie_lru_timed_out(struct timer_list *timer); +static void fscache_cookie_lru_worker(struct work_struct *work); static void fscache_cookie_worker(struct work_struct *work); static void fscache_unhash_cookie(struct fscache_cookie *cookie); @@ -22,7 +24,12 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie); static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; static LIST_HEAD(fscache_cookies); static DEFINE_RWLOCK(fscache_cookies_lock); -static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFWRD"; +static LIST_HEAD(fscache_cookie_lru); +static DEFINE_SPINLOCK(fscache_cookie_lru_lock); +DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); +static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFUWRD"; +unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { @@ -47,6 +54,14 @@ void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) static void fscache_free_cookie(struct fscache_cookie *cookie) { + if (WARN_ON_ONCE(!list_empty(&cookie->commit_link))) { + spin_lock(&fscache_cookie_lru_lock); + list_del_init(&cookie->commit_link); + spin_unlock(&fscache_cookie_lru_lock); + fscache_stat_d(&fscache_n_cookies_lru); + fscache_stat(&fscache_n_cookies_lru_removed); + } + if (WARN_ON_ONCE(test_bit(FSCACHE_COOKIE_IS_HASHED, &cookie->flags))) { fscache_print_cookie(cookie, 'F'); return; @@ -498,6 +513,126 @@ out: fscache_end_volume_access(cookie->volume, cookie, trace); } +/* + * Begin the process of looking up a cookie. We offload the actual process to + * a worker thread. + */ +static bool fscache_begin_lookup(struct fscache_cookie *cookie, bool will_modify) +{ + if (will_modify) { + set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); + set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + } + if (!fscache_begin_volume_access(cookie->volume, cookie, + fscache_access_lookup_cookie)) + return false; + + __fscache_begin_cookie_access(cookie, fscache_access_lookup_cookie); + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_LOOKING_UP); + set_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags); + set_bit(FSCACHE_COOKIE_HAS_BEEN_CACHED, &cookie->flags); + return true; +} + +/* + * Start using the cookie for I/O. This prevents the backing object from being + * reaped by VM pressure. + */ +void __fscache_use_cookie(struct fscache_cookie *cookie, bool will_modify) +{ + enum fscache_cookie_state state; + bool queue = false; + + _enter("c=%08x", cookie->debug_id); + + if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Trying to use relinquished cookie\n")) + return; + + spin_lock(&cookie->lock); + + atomic_inc(&cookie->n_active); + +again: + state = fscache_cookie_state(cookie); + switch (state) { + case FSCACHE_COOKIE_STATE_QUIESCENT: + queue = fscache_begin_lookup(cookie, will_modify); + break; + + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_CREATING: + if (will_modify) + set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); + break; + case FSCACHE_COOKIE_STATE_ACTIVE: + if (will_modify && + !test_and_set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags)) { + set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); + queue = true; + } + break; + + case FSCACHE_COOKIE_STATE_FAILED: + case FSCACHE_COOKIE_STATE_WITHDRAWING: + break; + + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + spin_unlock(&cookie->lock); + wait_var_event(&cookie->state, + fscache_cookie_state(cookie) != + FSCACHE_COOKIE_STATE_LRU_DISCARDING); + spin_lock(&cookie->lock); + goto again; + + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + WARN(1, "Can't use cookie in state %u\n", state); + break; + } + + spin_unlock(&cookie->lock); + if (queue) + fscache_queue_cookie(cookie, fscache_cookie_get_use_work); + _leave(""); +} +EXPORT_SYMBOL(__fscache_use_cookie); + +static void fscache_unuse_cookie_locked(struct fscache_cookie *cookie) +{ + clear_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags); + if (!test_bit(FSCACHE_COOKIE_IS_CACHING, &cookie->flags)) + return; + + cookie->unused_at = jiffies; + spin_lock(&fscache_cookie_lru_lock); + if (list_empty(&cookie->commit_link)) { + fscache_get_cookie(cookie, fscache_cookie_get_lru); + fscache_stat(&fscache_n_cookies_lru); + } + list_move_tail(&cookie->commit_link, &fscache_cookie_lru); + + spin_unlock(&fscache_cookie_lru_lock); + timer_reduce(&fscache_cookie_lru_timer, + jiffies + fscache_lru_cookie_timeout); +} + +/* + * Stop using the cookie for I/O. + */ +void __fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) +{ + if (aux_data || object_size) + __fscache_update_cookie(cookie, aux_data, object_size); + + if (atomic_dec_and_lock(&cookie->n_active, &cookie->lock)) { + fscache_unuse_cookie_locked(cookie); + spin_unlock(&cookie->lock); + } +} +EXPORT_SYMBOL(__fscache_unuse_cookie); + /* * Perform work upon the cookie, such as committing its cache state, * relinquishing it or withdrawing the backing cache. We're protected from the @@ -542,6 +677,12 @@ again_locked: fscache_prepare_to_write(cookie); spin_lock(&cookie->lock); } + if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) { + __fscache_set_cookie_state(cookie, + FSCACHE_COOKIE_STATE_LRU_DISCARDING); + wake = true; + goto again_locked; + } fallthrough; case FSCACHE_COOKIE_STATE_FAILED: @@ -561,6 +702,7 @@ again_locked: } break; + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: case FSCACHE_COOKIE_STATE_RELINQUISHING: case FSCACHE_COOKIE_STATE_WITHDRAWING: if (cookie->cache_priv) { @@ -577,6 +719,9 @@ again_locked: FSCACHE_COOKIE_STATE_DROPPED); wake = true; goto out; + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + fscache_see_cookie(cookie, fscache_cookie_see_lru_discard); + break; case FSCACHE_COOKIE_STATE_WITHDRAWING: fscache_see_cookie(cookie, fscache_cookie_see_withdraw); break; @@ -639,6 +784,76 @@ static void __fscache_withdraw_cookie(struct fscache_cookie *cookie) fscache_queue_cookie(cookie, fscache_cookie_get_end_access); } +static void fscache_cookie_lru_do_one(struct fscache_cookie *cookie) +{ + fscache_see_cookie(cookie, fscache_cookie_see_lru_do_one); + + spin_lock(&cookie->lock); + if (cookie->state != FSCACHE_COOKIE_STATE_ACTIVE || + time_before(jiffies, cookie->unused_at + fscache_lru_cookie_timeout) || + atomic_read(&cookie->n_active) > 0) { + spin_unlock(&cookie->lock); + fscache_stat(&fscache_n_cookies_lru_removed); + } else { + set_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags); + spin_unlock(&cookie->lock); + fscache_stat(&fscache_n_cookies_lru_expired); + _debug("lru c=%x", cookie->debug_id); + __fscache_withdraw_cookie(cookie); + } + + fscache_put_cookie(cookie, fscache_cookie_put_lru); +} + +static void fscache_cookie_lru_worker(struct work_struct *work) +{ + struct fscache_cookie *cookie; + unsigned long unused_at; + + spin_lock(&fscache_cookie_lru_lock); + + while (!list_empty(&fscache_cookie_lru)) { + cookie = list_first_entry(&fscache_cookie_lru, + struct fscache_cookie, commit_link); + unused_at = cookie->unused_at + fscache_lru_cookie_timeout; + if (time_before(jiffies, unused_at)) { + timer_reduce(&fscache_cookie_lru_timer, unused_at); + break; + } + + list_del_init(&cookie->commit_link); + fscache_stat_d(&fscache_n_cookies_lru); + spin_unlock(&fscache_cookie_lru_lock); + fscache_cookie_lru_do_one(cookie); + spin_lock(&fscache_cookie_lru_lock); + } + + spin_unlock(&fscache_cookie_lru_lock); +} + +static void fscache_cookie_lru_timed_out(struct timer_list *timer) +{ + queue_work(fscache_wq, &fscache_cookie_lru_work); +} + +static void fscache_cookie_drop_from_lru(struct fscache_cookie *cookie) +{ + bool need_put = false; + + if (!list_empty(&cookie->commit_link)) { + spin_lock(&fscache_cookie_lru_lock); + if (!list_empty(&cookie->commit_link)) { + list_del_init(&cookie->commit_link); + fscache_stat_d(&fscache_n_cookies_lru); + fscache_stat(&fscache_n_cookies_lru_dropped); + need_put = true; + } + spin_unlock(&fscache_cookie_lru_lock); + if (need_put) + fscache_put_cookie(cookie, fscache_cookie_put_lru); + } +} + /* * Remove a cookie from the hash table. */ @@ -659,6 +874,7 @@ static void fscache_unhash_cookie(struct fscache_cookie *cookie) static void fscache_drop_withdraw_cookie(struct fscache_cookie *cookie) { + fscache_cookie_drop_from_lru(cookie); __fscache_withdraw_cookie(cookie); } diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index e0d8ef212e82..ca938e00eaa0 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -57,6 +57,7 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, */ extern struct kmem_cache *fscache_cookie_jar; extern const struct seq_operations fscache_cookies_seq_ops; +extern struct timer_list fscache_cookie_lru_timer; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); extern bool fscache_begin_cookie_access(struct fscache_cookie *cookie, @@ -95,6 +96,10 @@ extern atomic_t fscache_n_volumes; extern atomic_t fscache_n_volumes_collision; extern atomic_t fscache_n_volumes_nomem; extern atomic_t fscache_n_cookies; +extern atomic_t fscache_n_cookies_lru; +extern atomic_t fscache_n_cookies_lru_expired; +extern atomic_t fscache_n_cookies_lru_removed; +extern atomic_t fscache_n_cookies_lru_dropped; extern atomic_t fscache_n_acquires; extern atomic_t fscache_n_acquires_ok; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 252e883ae148..5aa4bd9fe207 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -17,6 +17,10 @@ atomic_t fscache_n_volumes; atomic_t fscache_n_volumes_collision; atomic_t fscache_n_volumes_nomem; atomic_t fscache_n_cookies; +atomic_t fscache_n_cookies_lru; +atomic_t fscache_n_cookies_lru_expired; +atomic_t fscache_n_cookies_lru_removed; +atomic_t fscache_n_cookies_lru_dropped; atomic_t fscache_n_acquires; atomic_t fscache_n_acquires_ok; @@ -47,6 +51,14 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_acquires_ok), atomic_read(&fscache_n_acquires_oom)); + seq_printf(m, "LRU : n=%u exp=%u rmv=%u drp=%u at=%ld\n", + atomic_read(&fscache_n_cookies_lru), + atomic_read(&fscache_n_cookies_lru_expired), + atomic_read(&fscache_n_cookies_lru_removed), + atomic_read(&fscache_n_cookies_lru_dropped), + timer_pending(&fscache_cookie_lru_timer) ? + fscache_cookie_lru_timer.expires - jiffies : 0); + seq_printf(m, "Updates: n=%u\n", atomic_read(&fscache_n_updates)); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 4450d17c11e8..e6c321e5bf73 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -22,12 +22,14 @@ #define fscache_available() (1) #define fscache_volume_valid(volume) (volume) #define fscache_cookie_valid(cookie) (cookie) -#define fscache_cookie_enabled(cookie) (cookie) +#define fscache_resources_valid(cres) ((cres)->cache_priv) +#define fscache_cookie_enabled(cookie) (cookie && !test_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) #else #define __fscache_available (0) #define fscache_available() (0) #define fscache_volume_valid(volume) (0) #define fscache_cookie_valid(cookie) (0) +#define fscache_resources_valid(cres) (false) #define fscache_cookie_enabled(cookie) (0) #endif @@ -46,6 +48,7 @@ enum fscache_cookie_state { FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ + FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ FSCACHE_COOKIE_STATE_RELINQUISHING, /* The cookie is being relinquished */ FSCACHE_COOKIE_STATE_DROPPED, /* The cookie has been dropped */ @@ -147,6 +150,8 @@ extern struct fscache_cookie *__fscache_acquire_cookie( const void *, size_t, const void *, size_t, loff_t); +extern void __fscache_use_cookie(struct fscache_cookie *, bool); +extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); /** @@ -228,6 +233,39 @@ struct fscache_cookie *fscache_acquire_cookie(struct fscache_volume *volume, object_size); } +/** + * fscache_use_cookie - Request usage of cookie attached to an object + * @object: Object description + * @will_modify: If cache is expected to be modified locally + * + * Request usage of the cookie attached to an object. The caller should tell + * the cache if the object's contents are about to be modified locally and then + * the cache can apply the policy that has been set to handle this case. + */ +static inline void fscache_use_cookie(struct fscache_cookie *cookie, + bool will_modify) +{ + if (fscache_cookie_valid(cookie)) + __fscache_use_cookie(cookie, will_modify); +} + +/** + * fscache_unuse_cookie - Cease usage of cookie attached to an object + * @object: Object description + * @aux_data: Updated auxiliary data (or NULL) + * @object_size: Revised size of the object (or NULL) + * + * Cease usage of the cookie attached to an object. When the users count + * reaches zero then the cookie relinquishment will be permitted to proceed. + */ +static inline void fscache_unuse_cookie(struct fscache_cookie *cookie, + const void *aux_data, + const loff_t *object_size) +{ + if (fscache_cookie_valid(cookie)) + __fscache_unuse_cookie(cookie, aux_data, object_size); +} + /** * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding * it @@ -247,4 +285,46 @@ void fscache_relinquish_cookie(struct fscache_cookie *cookie, bool retire) __fscache_relinquish_cookie(cookie, retire); } +/* + * Find the auxiliary data on a cookie. + */ +static inline void *fscache_get_aux(struct fscache_cookie *cookie) +{ + if (cookie->aux_len <= sizeof(cookie->inline_aux)) + return cookie->inline_aux; + else + return cookie->aux; +} + +/* + * Update the auxiliary data on a cookie. + */ +static inline +void fscache_update_aux(struct fscache_cookie *cookie, + const void *aux_data, const loff_t *object_size) +{ + void *p = fscache_get_aux(cookie); + + if (aux_data && p) + memcpy(p, aux_data, cookie->aux_len); + if (object_size) + cookie->object_size = *object_size; +} + +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_updates; +#endif + +static inline +void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) +{ +#ifdef CONFIG_FSCACHE_STATS + atomic_inc(&fscache_n_updates); +#endif + fscache_update_aux(cookie, aux_data, object_size); + smp_wmb(); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 030c97bb9c8b..b0409b1fad23 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -51,13 +51,18 @@ enum fscache_cookie_trace { fscache_cookie_discard, fscache_cookie_get_end_access, fscache_cookie_get_hash_collision, + fscache_cookie_get_lru, + fscache_cookie_get_use_work, fscache_cookie_new_acquire, fscache_cookie_put_hash_collision, + fscache_cookie_put_lru, fscache_cookie_put_over_queued, fscache_cookie_put_relinquish, fscache_cookie_put_withdrawn, fscache_cookie_put_work, fscache_cookie_see_active, + fscache_cookie_see_lru_discard, + fscache_cookie_see_lru_do_one, fscache_cookie_see_relinquish, fscache_cookie_see_withdraw, fscache_cookie_see_work, @@ -68,6 +73,7 @@ enum fscache_access_trace { fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, fscache_access_relinquish_volume, @@ -110,13 +116,18 @@ enum fscache_access_trace { EM(fscache_cookie_discard, "DISCARD ") \ EM(fscache_cookie_get_hash_collision, "GET hcoll") \ EM(fscache_cookie_get_end_access, "GQ endac") \ + EM(fscache_cookie_get_lru, "GET lru ") \ + EM(fscache_cookie_get_use_work, "GQ use ") \ EM(fscache_cookie_new_acquire, "NEW acq ") \ EM(fscache_cookie_put_hash_collision, "PUT hcoll") \ + EM(fscache_cookie_put_lru, "PUT lru ") \ EM(fscache_cookie_put_over_queued, "PQ overq") \ EM(fscache_cookie_put_relinquish, "PUT relnq") \ EM(fscache_cookie_put_withdrawn, "PUT wthdn") \ EM(fscache_cookie_put_work, "PQ work ") \ EM(fscache_cookie_see_active, "- activ") \ + EM(fscache_cookie_see_lru_discard, "- x-lru") \ + EM(fscache_cookie_see_lru_do_one, "- lrudo") \ EM(fscache_cookie_see_relinquish, "- x-rlq") \ EM(fscache_cookie_see_withdraw, "- x-wth") \ E_(fscache_cookie_see_work, "- work ") @@ -126,6 +137,7 @@ enum fscache_access_trace { EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ EM(fscache_access_relinquish_volume, "BEGIN rlq_vol") \ -- cgit v1.2.3 From d24af13e2e2358a602740c7817ea90da43d3e740 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 15:53:34 +0100 Subject: fscache: Implement cookie invalidation Add a function to invalidate the cache behind a cookie: void fscache_invalidate(struct fscache_cookie *cookie, const void *aux_data, loff_t size, unsigned int flags) This causes any cached data for the specified cookie to be discarded. If the cookie is marked as being in use, a new cache object will be created if possible and future I/O will use that instead. In-flight I/O should be abandoned (writes) or reconsidered (reads). Each time it is called cookie->inval_counter is incremented and this can be used to detect invalidation at the end of an I/O operation. The coherency data attached to the cookie can be updated and the cookie size should be reset. One flag is available, FSCACHE_INVAL_DIO_WRITE, which should be used to indicate invalidation due to a DIO write on a file. This will temporarily disable caching for this cookie. Changes ======= ver #2: - Should only change to inval state if can get access to cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819602231.215744.11206598147269491575.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906909707.143852.18056070560477964891.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967107447.1823006.5945029409592119962.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021512640.640689.11418616313147754172.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cookie.c | 88 +++++++++++++++++++++++++++++++++++++++++- fs/fscache/internal.h | 2 + fs/fscache/stats.c | 5 +++ include/linux/fscache-cache.h | 4 ++ include/linux/fscache.h | 31 +++++++++++++++ include/linux/netfs.h | 1 + include/trace/events/fscache.h | 25 ++++++++++++ 7 files changed, 155 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 2f5ee717f2bb..a7ea7d1db032 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -19,6 +19,7 @@ static void fscache_cookie_lru_timed_out(struct timer_list *timer); static void fscache_cookie_lru_worker(struct work_struct *work); static void fscache_cookie_worker(struct work_struct *work); static void fscache_unhash_cookie(struct fscache_cookie *cookie); +static void fscache_perform_invalidation(struct fscache_cookie *cookie); #define fscache_cookie_hash_shift 15 static struct hlist_bl_head fscache_cookie_hash[1 << fscache_cookie_hash_shift]; @@ -28,7 +29,7 @@ static LIST_HEAD(fscache_cookie_lru); static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); -static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAFUWRD"; +static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) @@ -236,6 +237,19 @@ void fscache_cookie_lookup_negative(struct fscache_cookie *cookie) } EXPORT_SYMBOL(fscache_cookie_lookup_negative); +/** + * fscache_resume_after_invalidation - Allow I/O to resume after invalidation + * @cookie: The cookie that was invalidated + * + * Tell fscache that invalidation is sufficiently complete that I/O can be + * allowed again. + */ +void fscache_resume_after_invalidation(struct fscache_cookie *cookie) +{ + fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_ACTIVE); +} +EXPORT_SYMBOL(fscache_resume_after_invalidation); + /** * fscache_caching_failed - Report that a failure stopped caching on a cookie * @cookie: The cookie that was affected @@ -566,6 +580,7 @@ again: set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags); break; case FSCACHE_COOKIE_STATE_ACTIVE: + case FSCACHE_COOKIE_STATE_INVALIDATING: if (will_modify && !test_and_set_bit(FSCACHE_COOKIE_LOCAL_WRITE, &cookie->flags)) { set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); @@ -671,6 +686,11 @@ again_locked: fscache_perform_lookup(cookie); goto again; + case FSCACHE_COOKIE_STATE_INVALIDATING: + spin_unlock(&cookie->lock); + fscache_perform_invalidation(cookie); + goto again; + case FSCACHE_COOKIE_STATE_ACTIVE: if (test_and_clear_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags)) { spin_unlock(&cookie->lock); @@ -962,6 +982,72 @@ struct fscache_cookie *fscache_get_cookie(struct fscache_cookie *cookie, } EXPORT_SYMBOL(fscache_get_cookie); +/* + * Ask the cache to effect invalidation of a cookie. + */ +static void fscache_perform_invalidation(struct fscache_cookie *cookie) +{ + if (!cookie->volume->cache->ops->invalidate_cookie(cookie)) + fscache_caching_failed(cookie); + fscache_end_cookie_access(cookie, fscache_access_invalidate_cookie_end); +} + +/* + * Invalidate an object. + */ +void __fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t new_size, + unsigned int flags) +{ + bool is_caching; + + _enter("c=%x", cookie->debug_id); + + fscache_stat(&fscache_n_invalidates); + + if (WARN(test_bit(FSCACHE_COOKIE_RELINQUISHED, &cookie->flags), + "Trying to invalidate relinquished cookie\n")) + return; + + if ((flags & FSCACHE_INVAL_DIO_WRITE) && + test_and_set_bit(FSCACHE_COOKIE_DISABLED, &cookie->flags)) + return; + + spin_lock(&cookie->lock); + set_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); + fscache_update_aux(cookie, aux_data, &new_size); + cookie->inval_counter++; + trace_fscache_invalidate(cookie, new_size); + + switch (cookie->state) { + case FSCACHE_COOKIE_STATE_INVALIDATING: /* is_still_valid will catch it */ + default: + spin_unlock(&cookie->lock); + _leave(" [no %u]", cookie->state); + return; + + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_CREATING: + spin_unlock(&cookie->lock); + _leave(" [look %x]", cookie->inval_counter); + return; + + case FSCACHE_COOKIE_STATE_ACTIVE: + is_caching = fscache_begin_cookie_access( + cookie, fscache_access_invalidate_cookie); + if (is_caching) + __fscache_set_cookie_state(cookie, FSCACHE_COOKIE_STATE_INVALIDATING); + spin_unlock(&cookie->lock); + wake_up_cookie_state(cookie); + + if (is_caching) + fscache_queue_cookie(cookie, fscache_cookie_get_inval_work); + _leave(" [inv]"); + return; + } +} +EXPORT_SYMBOL(__fscache_invalidate); + /* * Generate a list of extant cookies in /proc/fs/fscache/cookies */ diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index ca938e00eaa0..7fb83d216360 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -105,6 +105,8 @@ extern atomic_t fscache_n_acquires; extern atomic_t fscache_n_acquires_ok; extern atomic_t fscache_n_acquires_oom; +extern atomic_t fscache_n_invalidates; + extern atomic_t fscache_n_relinquishes; extern atomic_t fscache_n_relinquishes_retire; extern atomic_t fscache_n_relinquishes_dropped; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 5aa4bd9fe207..cdbb672a274f 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -26,6 +26,8 @@ atomic_t fscache_n_acquires; atomic_t fscache_n_acquires_ok; atomic_t fscache_n_acquires_oom; +atomic_t fscache_n_invalidates; + atomic_t fscache_n_updates; EXPORT_SYMBOL(fscache_n_updates); @@ -59,6 +61,9 @@ int fscache_stats_show(struct seq_file *m, void *v) timer_pending(&fscache_cookie_lru_timer) ? fscache_cookie_lru_timer.expires - jiffies : 0); + seq_printf(m, "Invals : n=%u\n", + atomic_read(&fscache_n_invalidates)); + seq_printf(m, "Updates: n=%u\n", atomic_read(&fscache_n_updates)); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index ae6a75976450..1ad56bfd9d72 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -64,6 +64,9 @@ struct fscache_cache_ops { /* Withdraw an object without any cookie access counts held */ void (*withdraw_cookie)(struct fscache_cookie *cookie); + /* Invalidate an object */ + bool (*invalidate_cookie)(struct fscache_cookie *cookie); + /* Prepare to write to a live cache object */ void (*prepare_to_write)(struct fscache_cookie *cookie); }; @@ -96,6 +99,7 @@ extern void fscache_put_cookie(struct fscache_cookie *cookie, extern void fscache_end_cookie_access(struct fscache_cookie *cookie, enum fscache_access_trace why); extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); +extern void fscache_resume_after_invalidation(struct fscache_cookie *cookie); extern void fscache_caching_failed(struct fscache_cookie *cookie); /** diff --git a/include/linux/fscache.h b/include/linux/fscache.h index e6c321e5bf73..0f36d1fac237 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -39,6 +39,8 @@ struct fscache_cookie; #define FSCACHE_ADV_WRITE_CACHE 0x00 /* Do cache if written to locally */ #define FSCACHE_ADV_WRITE_NOCACHE 0x02 /* Don't cache if written to locally */ +#define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ + /* * Data object state. */ @@ -47,6 +49,7 @@ enum fscache_cookie_state { FSCACHE_COOKIE_STATE_LOOKING_UP, /* The cache object is being looked up */ FSCACHE_COOKIE_STATE_CREATING, /* The cache object is being created */ FSCACHE_COOKIE_STATE_ACTIVE, /* The cache is active, readable and writable */ + FSCACHE_COOKIE_STATE_INVALIDATING, /* The cache is being invalidated */ FSCACHE_COOKIE_STATE_FAILED, /* The cache failed, withdraw to clear */ FSCACHE_COOKIE_STATE_LRU_DISCARDING, /* The cookie is being discarded by the LRU */ FSCACHE_COOKIE_STATE_WITHDRAWING, /* The cookie is being withdrawn */ @@ -153,6 +156,7 @@ extern struct fscache_cookie *__fscache_acquire_cookie( extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); +extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); /** * fscache_acquire_volume - Register a volume as desiring caching services @@ -327,4 +331,31 @@ void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } +/** + * fscache_invalidate - Notify cache that an object needs invalidation + * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @size: The revised size of the object. + * @flags: Invalidation flags (FSCACHE_INVAL_*) + * + * Notify the cache that an object is needs to be invalidated and that it + * should abort any retrievals or stores it is doing on the cache. This + * increments inval_counter on the cookie which can be used by the caller to + * reconsider I/O requests as they complete. + * + * If @flags has FSCACHE_INVAL_DIO_WRITE set, this indicates that this is due + * to a direct I/O write and will cause caching to be disabled on this cookie + * until it is completely unused. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +void fscache_invalidate(struct fscache_cookie *cookie, + const void *aux_data, loff_t size, unsigned int flags) +{ + if (fscache_cookie_enabled(cookie)) + __fscache_invalidate(cookie, aux_data, size, flags); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 1ea22fc48818..5a46fde65759 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -124,6 +124,7 @@ struct netfs_cache_resources { void *cache_priv; void *cache_priv2; unsigned int debug_id; /* Cookie debug ID */ + unsigned int inval_counter; /* object->inval_counter at begin_op */ }; /* diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index b0409b1fad23..294792881434 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -51,6 +51,7 @@ enum fscache_cookie_trace { fscache_cookie_discard, fscache_cookie_get_end_access, fscache_cookie_get_hash_collision, + fscache_cookie_get_inval_work, fscache_cookie_get_lru, fscache_cookie_get_use_work, fscache_cookie_new_acquire, @@ -73,6 +74,8 @@ enum fscache_access_trace { fscache_access_acquire_volume_end, fscache_access_cache_pin, fscache_access_cache_unpin, + fscache_access_invalidate_cookie, + fscache_access_invalidate_cookie_end, fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, @@ -116,6 +119,7 @@ enum fscache_access_trace { EM(fscache_cookie_discard, "DISCARD ") \ EM(fscache_cookie_get_hash_collision, "GET hcoll") \ EM(fscache_cookie_get_end_access, "GQ endac") \ + EM(fscache_cookie_get_inval_work, "GQ inval") \ EM(fscache_cookie_get_lru, "GET lru ") \ EM(fscache_cookie_get_use_work, "GQ use ") \ EM(fscache_cookie_new_acquire, "NEW acq ") \ @@ -137,6 +141,8 @@ enum fscache_access_trace { EM(fscache_access_acquire_volume_end, "END acq_vol") \ EM(fscache_access_cache_pin, "PIN cache ") \ EM(fscache_access_cache_unpin, "UNPIN cache ") \ + EM(fscache_access_invalidate_cookie, "BEGIN inval ") \ + EM(fscache_access_invalidate_cookie_end,"END inval ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ @@ -385,6 +391,25 @@ TRACE_EVENT(fscache_relinquish, __entry->n_active, __entry->flags, __entry->retire) ); +TRACE_EVENT(fscache_invalidate, + TP_PROTO(struct fscache_cookie *cookie, loff_t new_size), + + TP_ARGS(cookie, new_size), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(loff_t, new_size ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->new_size = new_size; + ), + + TP_printk("c=%08x sz=%llx", + __entry->cookie, __entry->new_size) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From d64f4554dd177c5891c02424a8d9e80590b55b35 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Provide a means to begin an operation Provide a function to begin a read operation: int fscache_begin_read_operation( struct netfs_cache_resources *cres, struct fscache_cookie *cookie) This is primarily intended to be called by network filesystems on behalf of netfslib, but may also be called to use the I/O access functions directly. It attaches the resources required by the cache to cres struct from the supplied cookie. This holds access to the cache behind the cookie for the duration of the operation and forces cache withdrawal and cookie invalidation to perform synchronisation on the operation. cres->inval_counter is set from the cookie at this point so that it can be compared at the end of the operation. Note that this does not guarantee that the cache state is fully set up and able to perform I/O immediately; looking up and creation may be left in progress in the background. The operations intended to be called by the network filesystem, such as reading and writing, are expected to wait for the cookie to move to the correct state. This will, however, potentially sleep, waiting for a certain minimum state to be set or for operations such as invalidate to advance far enough that I/O can resume. Also provide a function for the cache to call to wait for the cache object to get to a state where it can be used for certain things: bool fscache_wait_for_operation(struct netfs_cache_resources *cres, enum fscache_want_stage stage); This looks at the cache resources provided by the begin function and waits for them to get to an appropriate stage. There's a choice of wanting just some parameters (FSCACHE_WANT_PARAM) or the ability to do I/O (FSCACHE_WANT_READ or FSCACHE_WANT_WRITE). Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819603692.215744.146724961588817028.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906910672.143852.13856103384424986357.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967110245.1823006.2239170567540431836.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021513617.640689.16627329360866150606.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/Makefile | 1 + fs/fscache/internal.h | 11 +++ fs/fscache/io.c | 151 +++++++++++++++++++++++++++++++++++++++++ include/linux/fscache-cache.h | 11 +++ include/linux/fscache.h | 49 +++++++++++++ include/trace/events/fscache.h | 6 ++ 6 files changed, 229 insertions(+) create mode 100644 fs/fscache/io.c (limited to 'include/linux') diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile index bcc79615f93a..afb090ea16c4 100644 --- a/fs/fscache/Makefile +++ b/fs/fscache/Makefile @@ -6,6 +6,7 @@ fscache-y := \ cache.o \ cookie.o \ + io.o \ main.o \ volume.o diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 7fb83d216360..017bf3d346a4 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -70,6 +70,17 @@ static inline void fscache_see_cookie(struct fscache_cookie *cookie, where); } +/* + * io.c + */ +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + /* * main.c */ diff --git a/fs/fscache/io.c b/fs/fscache/io.c new file mode 100644 index 000000000000..460a43473019 --- /dev/null +++ b/fs/fscache/io.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Cache data I/O routines + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#define FSCACHE_DEBUG_LEVEL OPERATION +#include +#include +#include +#include +#include +#include "internal.h" + +/** + * fscache_wait_for_operation - Wait for an object become accessible + * @cres: The cache resources for the operation being performed + * @want_state: The minimum state the object must be at + * + * See if the target cache object is at the specified minimum state of + * accessibility yet, and if not, wait for it. + */ +bool fscache_wait_for_operation(struct netfs_cache_resources *cres, + enum fscache_want_state want_state) +{ + struct fscache_cookie *cookie = fscache_cres_cookie(cres); + enum fscache_cookie_state state; + +again: + if (!fscache_cache_is_live(cookie->volume->cache)) { + _leave(" [broken]"); + return false; + } + + state = fscache_cookie_state(cookie); + _enter("c=%08x{%u},%x", cookie->debug_id, state, want_state); + + switch (state) { + case FSCACHE_COOKIE_STATE_CREATING: + case FSCACHE_COOKIE_STATE_INVALIDATING: + if (want_state == FSCACHE_WANT_PARAMS) + goto ready; /* There can be no content */ + fallthrough; + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + wait_var_event(&cookie->state, + fscache_cookie_state(cookie) != state); + goto again; + + case FSCACHE_COOKIE_STATE_ACTIVE: + goto ready; + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + default: + _leave(" [not live]"); + return false; + } + +ready: + if (!cres->cache_priv2) + return cookie->volume->cache->ops->begin_operation(cres, want_state); + return true; +} +EXPORT_SYMBOL(fscache_wait_for_operation); + +/* + * Begin an I/O operation on the cache, waiting till we reach the right state. + * + * Attaches the resources required to the operation resources record. + */ +static int fscache_begin_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie, + enum fscache_want_state want_state, + enum fscache_access_trace why) +{ + enum fscache_cookie_state state; + long timeo; + bool once_only = false; + + cres->ops = NULL; + cres->cache_priv = cookie; + cres->cache_priv2 = NULL; + cres->debug_id = cookie->debug_id; + cres->inval_counter = cookie->inval_counter; + + if (!fscache_begin_cookie_access(cookie, why)) + return -ENOBUFS; + +again: + spin_lock(&cookie->lock); + + state = fscache_cookie_state(cookie); + _enter("c=%08x{%u},%x", cookie->debug_id, state, want_state); + + switch (state) { + case FSCACHE_COOKIE_STATE_LOOKING_UP: + case FSCACHE_COOKIE_STATE_LRU_DISCARDING: + case FSCACHE_COOKIE_STATE_INVALIDATING: + goto wait_for_file_wrangling; + case FSCACHE_COOKIE_STATE_CREATING: + if (want_state == FSCACHE_WANT_PARAMS) + goto ready; /* There can be no content */ + goto wait_for_file_wrangling; + case FSCACHE_COOKIE_STATE_ACTIVE: + goto ready; + case FSCACHE_COOKIE_STATE_DROPPED: + case FSCACHE_COOKIE_STATE_RELINQUISHING: + WARN(1, "Can't use cookie in state %u\n", cookie->state); + goto not_live; + default: + goto not_live; + } + +ready: + spin_unlock(&cookie->lock); + if (!cookie->volume->cache->ops->begin_operation(cres, want_state)) + goto failed; + return 0; + +wait_for_file_wrangling: + spin_unlock(&cookie->lock); + trace_fscache_access(cookie->debug_id, refcount_read(&cookie->ref), + atomic_read(&cookie->n_accesses), + fscache_access_io_wait); + timeo = wait_var_event_timeout(&cookie->state, + fscache_cookie_state(cookie) != state, 20 * HZ); + if (timeo <= 1 && !once_only) { + pr_warn("%s: cookie state change wait timed out: cookie->state=%u state=%u", + __func__, fscache_cookie_state(cookie), state); + fscache_print_cookie(cookie, 'O'); + once_only = true; + } + goto again; + +not_live: + spin_unlock(&cookie->lock); +failed: + cres->cache_priv = NULL; + cres->ops = NULL; + fscache_end_cookie_access(cookie, fscache_access_io_not_live); + _leave(" = -ENOBUFS"); + return -ENOBUFS; +} + +int __fscache_begin_read_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS, + fscache_access_io_read); +} +EXPORT_SYMBOL(__fscache_begin_read_operation); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 1ad56bfd9d72..566497cf5f13 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -67,6 +67,10 @@ struct fscache_cache_ops { /* Invalidate an object */ bool (*invalidate_cookie)(struct fscache_cookie *cookie); + /* Begin an operation for the netfs lib */ + bool (*begin_operation)(struct netfs_cache_resources *cres, + enum fscache_want_state want_state); + /* Prepare to write to a live cache object */ void (*prepare_to_write)(struct fscache_cookie *cookie); }; @@ -101,6 +105,8 @@ extern void fscache_end_cookie_access(struct fscache_cookie *cookie, extern void fscache_cookie_lookup_negative(struct fscache_cookie *cookie); extern void fscache_resume_after_invalidation(struct fscache_cookie *cookie); extern void fscache_caching_failed(struct fscache_cookie *cookie); +extern bool fscache_wait_for_operation(struct netfs_cache_resources *cred, + enum fscache_want_state state); /** * fscache_cookie_state - Read the state of a cookie @@ -129,4 +135,9 @@ static inline void *fscache_get_key(struct fscache_cookie *cookie) return cookie->key; } +static inline struct fscache_cookie *fscache_cres_cookie(struct netfs_cache_resources *cres) +{ + return cres->cache_priv; +} + #endif /* _LINUX_FSCACHE_CACHE_H */ diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 0f36d1fac237..7cdc63c4fe35 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -41,6 +41,12 @@ struct fscache_cookie; #define FSCACHE_INVAL_DIO_WRITE 0x01 /* Invalidate due to DIO write */ +enum fscache_want_state { + FSCACHE_WANT_PARAMS, + FSCACHE_WANT_WRITE, + FSCACHE_WANT_READ, +}; + /* * Data object state. */ @@ -157,6 +163,7 @@ extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); +extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); /** * fscache_acquire_volume - Register a volume as desiring caching services @@ -358,4 +365,46 @@ void fscache_invalidate(struct fscache_cookie *cookie, __fscache_invalidate(cookie, aux_data, size, flags); } +/** + * fscache_operation_valid - Return true if operations resources are usable + * @cres: The resources to check. + * + * Returns a pointer to the operations table if usable or NULL if not. + */ +static inline +const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_resources *cres) +{ + return fscache_resources_valid(cres) ? cres->ops : NULL; +} + +/** + * fscache_begin_read_operation - Begin a read operation for the netfs lib + * @cres: The cache resources for the read being performed + * @cookie: The cookie representing the cache object + * + * Begin a read operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. + * + * This is intended to be called from the ->begin_cache_operation() netfs lib + * operation as implemented by the network filesystem. + * + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. + * + * Returns: + * * 0 - Success + * * -ENOBUFS - No caching available + * * Other error code from the cache, such as -ENOMEM. + */ +static inline +int fscache_begin_read_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_read_operation(cres, cookie); + return -ENOBUFS; +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 294792881434..9f78c903b00a 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -76,6 +76,9 @@ enum fscache_access_trace { fscache_access_cache_unpin, fscache_access_invalidate_cookie, fscache_access_invalidate_cookie_end, + fscache_access_io_not_live, + fscache_access_io_read, + fscache_access_io_wait, fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, @@ -143,6 +146,9 @@ enum fscache_access_trace { EM(fscache_access_cache_unpin, "UNPIN cache ") \ EM(fscache_access_invalidate_cookie, "BEGIN inval ") \ EM(fscache_access_invalidate_cookie_end,"END inval ") \ + EM(fscache_access_io_not_live, "END io_notl") \ + EM(fscache_access_io_read, "BEGIN io_read") \ + EM(fscache_access_io_wait, "WAIT io ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ -- cgit v1.2.3 From cdf262f29488e6c3432911ec487ea41918fcbcd7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 11 Nov 2021 23:14:29 +0000 Subject: fscache: Count data storage objects in a cache Count the data storage objects that are currently allocated in a cache. This is used to pin certain cache structures until cache withdrawal is complete. Three helpers are provided to manage and make use of the count: (1) void fscache_count_object(struct fscache_cache *cache); This should be called by the cache backend to note that an object has been allocated and attached to the cache. (2) void fscache_uncount_object(struct fscache_cache *cache); This should be called by the backend to note that an object has been destroyed. This sends a wakeup event that allows cache withdrawal to proceed if it was waiting for that object. (3) void fscache_wait_for_objects(struct fscache_cache *cache); This can be used by the backend to wait for all outstanding cache object to be destroyed. Each cache's counter is displayed as part of /proc/fs/fscache/caches. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819608594.215744.1812706538117388252.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906911646.143852.168184059935530127.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967111846.1823006.9868154941573671255.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021516219.640689.4934796654308958158.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/cache.c | 2 ++ include/linux/fscache-cache.h | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 41 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index 25eac61f1c29..2749933852a9 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -13,6 +13,8 @@ static LIST_HEAD(fscache_caches); DECLARE_RWSEM(fscache_addremove_sem); EXPORT_SYMBOL(fscache_addremove_sem); +DECLARE_WAIT_QUEUE_HEAD(fscache_clearance_waiters); +EXPORT_SYMBOL(fscache_clearance_waiters); static atomic_t fscache_cache_debug_id; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 566497cf5f13..337335d7a5e2 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -76,6 +76,7 @@ struct fscache_cache_ops { }; extern struct workqueue_struct *fscache_wq; +extern wait_queue_head_t fscache_clearance_waiters; /* * out-of-line cache backend functions @@ -140,4 +141,42 @@ static inline struct fscache_cookie *fscache_cres_cookie(struct netfs_cache_reso return cres->cache_priv; } +/** + * fscache_count_object - Tell fscache that an object has been added + * @cache: The cache to account to + * + * Tell fscache that an object has been added to the cache. This prevents the + * cache from tearing down the cache structure until the object is uncounted. + */ +static inline void fscache_count_object(struct fscache_cache *cache) +{ + atomic_inc(&cache->object_count); +} + +/** + * fscache_uncount_object - Tell fscache that an object has been removed + * @cache: The cache to account to + * + * Tell fscache that an object has been removed from the cache and will no + * longer be accessed. After this point, the cache cookie may be destroyed. + */ +static inline void fscache_uncount_object(struct fscache_cache *cache) +{ + if (atomic_dec_and_test(&cache->object_count)) + wake_up_all(&fscache_clearance_waiters); +} + +/** + * fscache_wait_for_objects - Wait for all objects to be withdrawn + * @cache: The cache to query + * + * Wait for all extant objects in a cache to finish being withdrawn + * and go away. + */ +static inline void fscache_wait_for_objects(struct fscache_cache *cache) +{ + wait_event(fscache_clearance_waiters, + atomic_read(&cache->object_count) == 0); +} + #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 8e7a867bb7309fbf47e8c2a68798b919fc02523f Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 23:06:16 +0100 Subject: fscache: Provide read/write stat counters for the cache Provide read/write stat counters for the cache backend to use. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819609532.215744.10821082637727410554.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906912598.143852.12960327989649429069.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967113830.1823006.3222957649202368162.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021517502.640689.6077928311710357342.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/stats.c | 9 +++++++++ include/linux/fscache-cache.h | 10 ++++++++++ 2 files changed, 19 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index cdbb672a274f..db42beb1ba3f 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -35,6 +35,11 @@ atomic_t fscache_n_relinquishes; atomic_t fscache_n_relinquishes_retire; atomic_t fscache_n_relinquishes_dropped; +atomic_t fscache_n_read; +EXPORT_SYMBOL(fscache_n_read); +atomic_t fscache_n_write; +EXPORT_SYMBOL(fscache_n_write); + /* * display the general statistics */ @@ -72,6 +77,10 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_relinquishes_retire), atomic_read(&fscache_n_relinquishes_dropped)); + seq_printf(m, "IO : rd=%u wr=%u\n", + atomic_read(&fscache_n_read), + atomic_read(&fscache_n_write)); + netfs_stats_show(m); return 0; } diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 337335d7a5e2..796c8b5c5305 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -179,4 +179,14 @@ static inline void fscache_wait_for_objects(struct fscache_cache *cache) atomic_read(&cache->object_count) == 0); } +#ifdef CONFIG_FSCACHE_STATS +extern atomic_t fscache_n_read; +extern atomic_t fscache_n_write; +#define fscache_count_read() atomic_inc(&fscache_n_read) +#define fscache_count_write() atomic_inc(&fscache_n_write) +#else +#define fscache_count_read() do {} while(0) +#define fscache_count_write() do {} while(0) +#endif + #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From ed1235eb78a7421cd0ac2ad09e931f8f07ccdc7c Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 23:10:46 +0100 Subject: fscache: Provide a function to let the netfs update its coherency data Provide a function to let the netfs update its coherency data: void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, const loff_t *object_size); This will update the auxiliary data and/or the size of the object attached to a cookie if either pointer is not-NULL and flag that the disk needs to be updated. Note that fscache_unuse_cookie() also allows this to be done. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819610438.215744.4223265964131424954.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906913530.143852.18150303220217653820.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967117795.1823006.7493373142653442595.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021518440.640689.6369952464473039268.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache.h | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7cdc63c4fe35..fc77648c8af6 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -338,6 +338,28 @@ void __fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); } +/** + * fscache_update_cookie - Request that a cache object be updated + * @cookie: The cookie representing the cache object + * @aux_data: The updated auxiliary data for the cookie (may be NULL) + * @object_size: The current size of the object (may be NULL) + * + * Request an update of the index data for the cache object associated with the + * cookie. The auxiliary data on the cookie will be updated first if @aux_data + * is set and the object size will be updated and the object possibly trimmed + * if @object_size is set. + * + * See Documentation/filesystems/caching/netfs-api.rst for a complete + * description. + */ +static inline +void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, + const loff_t *object_size) +{ + if (fscache_cookie_enabled(cookie)) + __fscache_update_cookie(cookie, aux_data, object_size); +} + /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object -- cgit v1.2.3 From 3a11b3a86366ccbf0818b088ffecadf8b2d61177 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Sep 2021 09:47:45 +0100 Subject: netfs: Pass more information on how to deal with a hole in the cache Pass more information to the cache on how to deal with a hole if it encounters one when trying to read from the cache. Three options are provided: (1) NETFS_READ_HOLE_IGNORE. Read the hole along with the data, assuming it to be a punched-out extent by the backing filesystem. (2) NETFS_READ_HOLE_CLEAR. If there's a hole, erase the requested region of the cache and clear the read buffer. (3) NETFS_READ_HOLE_FAIL. Fail the read if a hole is detected. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819612321.215744.9738308885948264476.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906914460.143852.6284247083607910189.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967119923.1823006.15637375885194297582.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021519762.640689.16994364383313159319.stgit@warthog.procyon.org.uk/ # v4 --- fs/netfs/read_helper.c | 8 ++++---- include/linux/netfs.h | 11 ++++++++++- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/netfs/read_helper.c b/fs/netfs/read_helper.c index 9dd76b8914f2..6169659857b3 100644 --- a/fs/netfs/read_helper.c +++ b/fs/netfs/read_helper.c @@ -170,7 +170,7 @@ static void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error */ static void netfs_read_from_cache(struct netfs_read_request *rreq, struct netfs_read_subrequest *subreq, - bool seek_data) + enum netfs_read_from_hole read_hole) { struct netfs_cache_resources *cres = &rreq->cache_resources; struct iov_iter iter; @@ -180,7 +180,7 @@ static void netfs_read_from_cache(struct netfs_read_request *rreq, subreq->start + subreq->transferred, subreq->len - subreq->transferred); - cres->ops->read(cres, subreq->start, &iter, seek_data, + cres->ops->read(cres, subreq->start, &iter, read_hole, netfs_cache_read_terminated, subreq); } @@ -461,7 +461,7 @@ static void netfs_rreq_short_read(struct netfs_read_request *rreq, netfs_get_read_subrequest(subreq); atomic_inc(&rreq->nr_rd_ops); if (subreq->source == NETFS_READ_FROM_CACHE) - netfs_read_from_cache(rreq, subreq, true); + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_CLEAR); else netfs_read_from_server(rreq, subreq); } @@ -789,7 +789,7 @@ static bool netfs_rreq_submit_slice(struct netfs_read_request *rreq, netfs_read_from_server(rreq, subreq); break; case NETFS_READ_FROM_CACHE: - netfs_read_from_cache(rreq, subreq, false); + netfs_read_from_cache(rreq, subreq, NETFS_READ_HOLE_IGNORE); break; default: BUG(); diff --git a/include/linux/netfs.h b/include/linux/netfs.h index 5a46fde65759..b46c39d98bbd 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -196,6 +196,15 @@ struct netfs_read_request_ops { void (*cleanup)(struct address_space *mapping, void *netfs_priv); }; +/* + * How to handle reading from a hole. + */ +enum netfs_read_from_hole { + NETFS_READ_HOLE_IGNORE, + NETFS_READ_HOLE_CLEAR, + NETFS_READ_HOLE_FAIL, +}; + /* * Table of operations for access to a cache. This is obtained by * rreq->ops->begin_cache_operation(). @@ -208,7 +217,7 @@ struct netfs_cache_ops { int (*read)(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, - bool seek_data, + enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); -- cgit v1.2.3 From 9af1c6c3089b294ffa240e0fbba356666698b6d0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Implement raw I/O interface Provide a pair of functions to perform raw I/O on the cache. The first function allows an arbitrary asynchronous direct-IO read to be made against a cache object, though the read should be aligned and sized appropriately for the backing device: int fscache_read(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, enum netfs_read_from_hole read_hole, netfs_io_terminated_t term_func, void *term_func_priv); The cache resources must have been previously initialised by fscache_begin_read_operation(). A read operation is sent to the backing filesystem, starting at start_pos within the file. The size of the read is specified by the iterator, as is the location of the output buffer. If there is a hole in the data it can be ignored and left to the backing filesystem to deal with (NETFS_READ_HOLE_IGNORE), a hole at the beginning can be skipped over and the buffer padded with zeros (NETFS_READ_HOLE_CLEAR) or -ENODATA can be given (NETFS_READ_HOLE_FAIL). If term_func is not NULL, the operation may be performed asynchronously. Upon completion, successful or otherwise, (*term_func)() will be called and passed term_func_priv, along with an error or the amount of data transferred. If the op is run asynchronously, fscache_read() will return -EIOCBQUEUED. The second function allows an arbitrary asynchronous direct-IO write to be made against a cache object, though the write should be aligned and sized appropriately for the backing device: int fscache_write(struct netfs_cache_resources *cres, loff_t start_pos, struct iov_iter *iter, netfs_io_terminated_t term_func, void *term_func_priv); This works in very similar way to fscache_read(), except that there's no need to deal with holes (they're just overwritten). The caller is responsible for preventing concurrent overlapping writes. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819613224.215744.7877577215582621254.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906915386.143852.16936177636106480724.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967122632.1823006.7487049517698562172.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021521420.640689.12747258780542678309.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache.h | 74 ++++++++++++++++++++++++++++++++++++++++++ include/trace/events/fscache.h | 2 ++ 2 files changed, 76 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index fc77648c8af6..ae753cae0fdd 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -429,4 +429,78 @@ int fscache_begin_read_operation(struct netfs_cache_resources *cres, return -ENOBUFS; } +/** + * fscache_read - Start a read from the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The buffer to fill - and also the length + * @read_hole: How to handle a hole in the data. + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * + * Start a read from the cache. @cres indicates the cache object to read from + * and must be obtained by a call to fscache_begin_operation() beforehand. + * + * The data is read into the iterator, @iter, and that also indicates the size + * of the operation. @start_pos is the start position in the file, though if + * @seek_data is set appropriately, the cache can use SEEK_DATA to find the + * next piece of data, writing zeros for the hole into the iterator. + * + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. + * + * @read_hole indicates how a partially populated region in the cache should be + * handled. It can be one of a number of settings: + * + * NETFS_READ_HOLE_IGNORE - Just try to read (may return a short read). + * + * NETFS_READ_HOLE_CLEAR - Seek for data, clearing the part of the buffer + * skipped over, then do as for IGNORE. + * + * NETFS_READ_HOLE_FAIL - Give ENODATA if we encounter a hole. + */ +static inline +int fscache_read(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + enum netfs_read_from_hole read_hole, + netfs_io_terminated_t term_func, + void *term_func_priv) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->read(cres, start_pos, iter, read_hole, + term_func, term_func_priv); +} + +/** + * fscache_write - Start a write to the cache. + * @cres: The cache resources to use + * @start_pos: The beginning file offset in the cache file + * @iter: The data to write - and also the length + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * + * Start a write to the cache. @cres indicates the cache object to write to and + * must be obtained by a call to fscache_begin_operation() beforehand. + * + * The data to be written is obtained from the iterator, @iter, and that also + * indicates the size of the operation. @start_pos is the start position in + * the file. + * + * Upon termination of the operation, @term_func will be called and supplied + * with @term_func_priv plus the amount of data written, if successful, or the + * error code otherwise. + */ +static inline +int fscache_write(struct netfs_cache_resources *cres, + loff_t start_pos, + struct iov_iter *iter, + netfs_io_terminated_t term_func, + void *term_func_priv) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + return ops->write(cres, start_pos, iter, term_func, term_func_priv); +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 9f78c903b00a..2459d75659cf 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -79,6 +79,7 @@ enum fscache_access_trace { fscache_access_io_not_live, fscache_access_io_read, fscache_access_io_wait, + fscache_access_io_write, fscache_access_lookup_cookie, fscache_access_lookup_cookie_end, fscache_access_lookup_cookie_end_failed, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_access_io_not_live, "END io_notl") \ EM(fscache_access_io_read, "BEGIN io_read") \ EM(fscache_access_io_wait, "WAIT io ") \ + EM(fscache_access_io_write, "BEGIN io_writ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ EM(fscache_access_lookup_cookie_end, "END lookup ") \ EM(fscache_access_lookup_cookie_end_failed,"END lookupf") \ -- cgit v1.2.3 From b6e16652d6c0e4f9e9b120f66966ec153f0623fc Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Implement higher-level write I/O interface Provide a higher-level function than fscache_write() to perform a write from an inode's pagecache to the cache, whilst fending off concurrent writes by means of the PG_fscache mark on a page: void fscache_write_to_cache(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, loff_t i_size, netfs_io_terminated_t term_func, void *term_func_priv, bool caching); If caching is false, this function does nothing except call (*term_func)() if given. It assumes that, in such a case, PG_fscache will not have been set on the pages. Otherwise, if caching is true, this function requires the source pages to have had PG_fscache set on them before calling. start and len define the region of the file to be modified and i_size indicates the new file size. The source pages are extracted from the mapping. term_func and term_func_priv work as for fscache_write(). The PG_fscache marks will be cleared at the end of the operation, before term_func is called or the function otherwise returns. There is an additonal helper function to clear the PG_fscache bits from a range of pages: void fscache_clear_page_bits(struct fscache_cookie *cookie, struct address_space *mapping, loff_t start, size_t len, bool caching); If caching is true, the pages to be managed are expected to be located on mapping in the range defined by start and len. If caching is false, it does nothing. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819614155.215744.5528123235123721230.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906916346.143852.15632773570362489926.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967123599.1823006.12946816026724657428.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021522672.640689.4381958316198807813.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/io.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fscache.h | 63 +++++++++++++++++++++++++++++ 2 files changed, 167 insertions(+) (limited to 'include/linux') diff --git a/fs/fscache/io.c b/fs/fscache/io.c index 460a43473019..74cde7acf434 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -149,3 +149,107 @@ int __fscache_begin_read_operation(struct netfs_cache_resources *cres, fscache_access_io_read); } EXPORT_SYMBOL(__fscache_begin_read_operation); + +struct fscache_write_request { + struct netfs_cache_resources cache_resources; + struct address_space *mapping; + loff_t start; + size_t len; + bool set_bits; + netfs_io_terminated_t term_func; + void *term_func_priv; +}; + +void __fscache_clear_page_bits(struct address_space *mapping, + loff_t start, size_t len) +{ + pgoff_t first = start / PAGE_SIZE; + pgoff_t last = (start + len - 1) / PAGE_SIZE; + struct page *page; + + if (len) { + XA_STATE(xas, &mapping->i_pages, first); + + rcu_read_lock(); + xas_for_each(&xas, page, last) { + end_page_fscache(page); + } + rcu_read_unlock(); + } +} +EXPORT_SYMBOL(__fscache_clear_page_bits); + +/* + * Deal with the completion of writing the data to the cache. + */ +static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, + bool was_async) +{ + struct fscache_write_request *wreq = priv; + + fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), + wreq->mapping, wreq->start, wreq->len, + wreq->set_bits); + + if (wreq->term_func) + wreq->term_func(wreq->term_func_priv, transferred_or_error, + was_async); + fscache_end_operation(&wreq->cache_resources); + kfree(wreq); +} + +void __fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool cond) +{ + struct fscache_write_request *wreq; + struct netfs_cache_resources *cres; + struct iov_iter iter; + int ret = -ENOBUFS; + + if (len == 0) + goto abandon; + + _enter("%llx,%zx", start, len); + + wreq = kzalloc(sizeof(struct fscache_write_request), GFP_NOFS); + if (!wreq) + goto abandon; + wreq->mapping = mapping; + wreq->start = start; + wreq->len = len; + wreq->set_bits = cond; + wreq->term_func = term_func; + wreq->term_func_priv = term_func_priv; + + cres = &wreq->cache_resources; + if (fscache_begin_operation(cres, cookie, FSCACHE_WANT_WRITE, + fscache_access_io_write) < 0) + goto abandon_free; + + ret = cres->ops->prepare_write(cres, &start, &len, i_size, false); + if (ret < 0) + goto abandon_end; + + /* TODO: Consider clearing page bits now for space the write isn't + * covering. This is more complicated than it appears when THPs are + * taken into account. + */ + + iov_iter_xarray(&iter, WRITE, &mapping->i_pages, start, len); + fscache_write(cres, start, &iter, fscache_wreq_done, wreq); + return; + +abandon_end: + return fscache_wreq_done(wreq, ret, false); +abandon_free: + kfree(wreq); +abandon: + fscache_clear_page_bits(cookie, mapping, start, len, cond); + if (term_func) + term_func(term_func_priv, ret, false); +} +EXPORT_SYMBOL(__fscache_write_to_cache); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ae753cae0fdd..9d469613e16c 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -165,6 +165,11 @@ extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); +extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, + loff_t, size_t, loff_t, netfs_io_terminated_t, void *, + bool); +extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t); + /** * fscache_acquire_volume - Register a volume as desiring caching services * @volume_key: An identification string for the volume @@ -503,4 +508,62 @@ int fscache_write(struct netfs_cache_resources *cres, return ops->write(cres, start_pos, iter, term_func, term_func_priv); } +/** + * fscache_clear_page_bits - Clear the PG_fscache bits from a set of pages + * @cookie: The cookie representing the cache object + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to unlock + * @caching: If PG_fscache has been set + * + * Clear the PG_fscache flag from a sequence of pages and wake up anyone who's + * waiting. + */ +static inline void fscache_clear_page_bits(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, + bool caching) +{ + if (caching) + __fscache_clear_page_bits(mapping, start, len); +} + +/** + * fscache_write_to_cache - Save a write to the cache and clear PG_fscache + * @cookie: The cookie representing the cache object + * @mapping: The netfs inode to use as the source + * @start: The start position in @mapping + * @len: The amount of data to write back + * @i_size: The new size of the inode + * @term_func: The function to call upon completion + * @term_func_priv: The private data for @term_func + * @caching: If PG_fscache has been set + * + * Helper function for a netfs to write dirty data from an inode into the cache + * object that's backing it. + * + * @start and @len describe the range of the data. This does not need to be + * page-aligned, but to satisfy DIO requirements, the cache may expand it up to + * the page boundaries on either end. All the pages covering the range must be + * marked with PG_fscache. + * + * If given, @term_func will be called upon completion and supplied with + * @term_func_priv. Note that the PG_fscache flags will have been cleared by + * this point, so the netfs must retain its own pin on the mapping. + */ +static inline void fscache_write_to_cache(struct fscache_cookie *cookie, + struct address_space *mapping, + loff_t start, size_t len, loff_t i_size, + netfs_io_terminated_t term_func, + void *term_func_priv, + bool caching) +{ + if (caching) + __fscache_write_to_cache(cookie, mapping, start, len, i_size, + term_func, term_func_priv, caching); + else if (term_func) + term_func(term_func_priv, -ENOBUFS, false); + +} + #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 08276bdae68b022a7726edf7416b6748e3df5395 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 23:50:01 +0100 Subject: vfs, fscache: Implement pinning of cache usage for writeback Cachefiles has a problem in that it needs to keep the backing file for a cookie open whilst there are local modifications pending that need to be written to it. However, we don't want to keep the file open indefinitely, as that causes EMFILE/ENFILE/ENOMEM problems. Reopening the cache file, however, is a problem if this is being done due to writeback triggered by exit(). Some filesystems will oops if we try to open a file in that context because they want to access current->fs or other resources that have already been dismantled. To get around this, I added the following: (1) An inode flag, I_PINNING_FSCACHE_WB, to be set on a network filesystem inode to indicate that we have a usage count on the cookie caching that inode. (2) A flag in struct writeback_control, unpinned_fscache_wb, that is set when __writeback_single_inode() clears the last dirty page from i_pages - at which point it clears I_PINNING_FSCACHE_WB and sets this flag. This has to be done here so that clearing I_PINNING_FSCACHE_WB can be done atomically with the check of PAGECACHE_TAG_DIRTY that clears I_DIRTY_PAGES. (3) A function, fscache_set_page_dirty(), which if it is not set, sets I_PINNING_FSCACHE_WB and calls fscache_use_cookie() to pin the cache resources. (4) A function, fscache_unpin_writeback(), to be called by ->write_inode() to unuse the cookie. (5) A function, fscache_clear_inode_writeback(), to be called when the inode is evicted, before clear_inode() is called. This cleans up any lingering I_PINNING_FSCACHE_WB. The network filesystem can then use these tools to make sure that fscache_write_to_cache() can write locally modified data to the cache as well as to the server. For the future, I'm working on write helpers for netfs lib that should allow this facility to be removed by keeping track of the dirty regions separately - but that's incomplete at the moment and is also going to be affected by folios, one way or another, since it deals with pages Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819615157.215744.17623791756928043114.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906917856.143852.8224898306177154573.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967124567.1823006.14188359004568060298.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021524705.640689.17824932021727663017.stgit@warthog.procyon.org.uk/ # v4 --- fs/fs-writeback.c | 8 ++++++++ fs/fscache/io.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 3 +++ include/linux/fscache.h | 41 +++++++++++++++++++++++++++++++++++++++++ include/linux/writeback.h | 1 + 5 files changed, 91 insertions(+) (limited to 'include/linux') diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 67f0e88eed01..8294a60ce323 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1666,6 +1666,13 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; + else if (unlikely(inode->i_state & I_PINNING_FSCACHE_WB)) { + if (!(inode->i_state & I_DIRTY_PAGES)) { + inode->i_state &= ~I_PINNING_FSCACHE_WB; + wbc->unpinned_fscache_wb = true; + dirty |= I_PINNING_FSCACHE_WB; /* Cause write_inode */ + } + } spin_unlock(&inode->i_lock); @@ -1675,6 +1682,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) if (ret == 0) ret = err; } + wbc->unpinned_fscache_wb = false; trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } diff --git a/fs/fscache/io.c b/fs/fscache/io.c index 74cde7acf434..e9e5d6758ea8 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -150,6 +150,44 @@ int __fscache_begin_read_operation(struct netfs_cache_resources *cres, } EXPORT_SYMBOL(__fscache_begin_read_operation); +/** + * fscache_set_page_dirty - Mark page dirty and pin a cache object for writeback + * @page: The page being dirtied + * @cookie: The cookie referring to the cache object + * + * Set the dirty flag on a page and pin an in-use cache object in memory when + * dirtying a page so that writeback can later write to it. This is intended + * to be called from the filesystem's ->set_page_dirty() method. + * + * Returns 1 if PG_dirty was set on the page, 0 otherwise. + */ +int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie) +{ + struct inode *inode = page->mapping->host; + bool need_use = false; + + _enter(""); + + if (!__set_page_dirty_nobuffers(page)) + return 0; + if (!fscache_cookie_valid(cookie)) + return 1; + + if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { + spin_lock(&inode->i_lock); + if (!(inode->i_state & I_PINNING_FSCACHE_WB)) { + inode->i_state |= I_PINNING_FSCACHE_WB; + need_use = true; + } + spin_unlock(&inode->i_lock); + + if (need_use) + fscache_use_cookie(cookie, true); + } + return 1; +} +EXPORT_SYMBOL(fscache_set_page_dirty); + struct fscache_write_request { struct netfs_cache_resources cache_resources; struct address_space *mapping; diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..2c0b8e77d9ab 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2418,6 +2418,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * Used to detect that mark_inode_dirty() should not move * inode between dirty lists. * + * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2440,6 +2442,7 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, #define I_CREATING (1 << 15) #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) +#define I_PINNING_FSCACHE_WB (1 << 18) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 9d469613e16c..18e725671594 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -16,6 +16,7 @@ #include #include +#include #if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE) #define __fscache_available (1) @@ -566,4 +567,44 @@ static inline void fscache_write_to_cache(struct fscache_cookie *cookie, } +#if __fscache_available +extern int fscache_set_page_dirty(struct page *page, struct fscache_cookie *cookie); +#else +#define fscache_set_page_dirty(PAGE, COOKIE) (__set_page_dirty_nobuffers((PAGE))) +#endif + +/** + * fscache_unpin_writeback - Unpin writeback resources + * @wbc: The writeback control + * @cookie: The cookie referring to the cache object + * + * Unpin the writeback resources pinned by fscache_set_page_dirty(). This is + * intended to be called by the netfs's ->write_inode() method. + */ +static inline void fscache_unpin_writeback(struct writeback_control *wbc, + struct fscache_cookie *cookie) +{ + if (wbc->unpinned_fscache_wb) + fscache_unuse_cookie(cookie, NULL, NULL); +} + +/** + * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode + * @cookie: The cookie referring to the cache object + * @inode: The inode to clean up + * @aux: Auxiliary data to apply to the inode + * + * Clear any writeback resources held by an inode when the inode is evicted. + * This must be called before clear_inode() is called. + */ +static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, + struct inode *inode, + const void *aux) +{ + if (inode->i_state & I_PINNING_FSCACHE_WB) { + loff_t i_size = i_size_read(inode); + fscache_unuse_cookie(cookie, aux, &i_size); + } +} + #endif /* _LINUX_FSCACHE_H */ diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 3bfd487d1dd2..fec248ab1fec 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -68,6 +68,7 @@ struct writeback_control { unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ + unsigned unpinned_fscache_wb:1; /* Cleared I_PINNING_FSCACHE_WB */ /* * When writeback IOs are bounced through async layers, only the -- cgit v1.2.3 From 1f67e6d0b18853c641d861a671f46a4964a88510 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Provide a function to note the release of a page Provide a function to be called from a network filesystem's releasepage method to indicate that a page has been released that might have been a reflection of data upon the server - and now that data must be reloaded from the server or the cache. This is used to end an optimisation for empty files, in particular files that have just been created locally, whereby we know there cannot yet be any data that we would need to read from the server or the cache. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819617128.215744.4725572296135656508.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906920354.143852.7511819614661372008.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967128061.1823006.611781655060034988.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021525963.640689.9264556596205140044.stgit@warthog.procyon.org.uk/ # v4 --- include/linux/fscache.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 18e725671594..28ce258c1f87 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -607,4 +607,20 @@ static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, } } +/** + * fscache_note_page_release - Note that a netfs page got released + * @cookie: The cookie corresponding to the file + * + * Note that a page that has been copied to the cache has been released. This + * means that future reads will need to look in the cache to see if it's there. + */ +static inline +void fscache_note_page_release(struct fscache_cookie *cookie) +{ + if (cookie && + test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && + test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) + clear_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags); +} + #endif /* _LINUX_FSCACHE_H */ -- cgit v1.2.3 From 16a96bdf92d5af06f9fa6a01a4b08e2fdfed2e5b Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 20 Oct 2021 14:06:34 +0100 Subject: fscache: Provide a function to resize a cookie Provide a function to change the size of the storage attached to a cookie, to match the size of the file being cached when it's changed by truncate or fallocate: void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size); This acts synchronously and is expected to run under the inode lock of the caller. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819621839.215744.7895597119803515402.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906922387.143852.16394459879816147793.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967128998.1823006.10740669081985775576.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021527861.640689.3466382085497236267.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/internal.h | 3 +++ fs/fscache/io.c | 25 +++++++++++++++++++++++++ fs/fscache/stats.c | 9 +++++++-- include/linux/fscache-cache.h | 4 ++++ include/linux/fscache.h | 18 ++++++++++++++++++ include/trace/events/fscache.h | 25 +++++++++++++++++++++++++ 6 files changed, 82 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index 017bf3d346a4..f121c21590dc 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -122,6 +122,9 @@ extern atomic_t fscache_n_relinquishes; extern atomic_t fscache_n_relinquishes_retire; extern atomic_t fscache_n_relinquishes_dropped; +extern atomic_t fscache_n_resizes; +extern atomic_t fscache_n_resizes_null; + static inline void fscache_stat(atomic_t *stat) { atomic_inc(stat); diff --git a/fs/fscache/io.c b/fs/fscache/io.c index e9e5d6758ea8..bed7628a5a9d 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -291,3 +291,28 @@ abandon: term_func(term_func_priv, ret, false); } EXPORT_SYMBOL(__fscache_write_to_cache); + +/* + * Change the size of a backing object. + */ +void __fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) +{ + struct netfs_cache_resources cres; + + trace_fscache_resize(cookie, new_size); + if (fscache_begin_operation(&cres, cookie, FSCACHE_WANT_WRITE, + fscache_access_io_resize) == 0) { + fscache_stat(&fscache_n_resizes); + set_bit(FSCACHE_COOKIE_NEEDS_UPDATE, &cookie->flags); + + /* We cannot defer a resize as we need to do it inside the + * netfs's inode lock so that we're serialised with respect to + * writes. + */ + cookie->volume->cache->ops->resize_cookie(&cres, new_size); + fscache_end_operation(&cres); + } else { + fscache_stat(&fscache_n_resizes_null); + } +} +EXPORT_SYMBOL(__fscache_resize_cookie); diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index db42beb1ba3f..798ee68b3e9d 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -35,6 +35,9 @@ atomic_t fscache_n_relinquishes; atomic_t fscache_n_relinquishes_retire; atomic_t fscache_n_relinquishes_dropped; +atomic_t fscache_n_resizes; +atomic_t fscache_n_resizes_null; + atomic_t fscache_n_read; EXPORT_SYMBOL(fscache_n_read); atomic_t fscache_n_write; @@ -69,8 +72,10 @@ int fscache_stats_show(struct seq_file *m, void *v) seq_printf(m, "Invals : n=%u\n", atomic_read(&fscache_n_invalidates)); - seq_printf(m, "Updates: n=%u\n", - atomic_read(&fscache_n_updates)); + seq_printf(m, "Updates: n=%u rsz=%u rsn=%u\n", + atomic_read(&fscache_n_updates), + atomic_read(&fscache_n_resizes), + atomic_read(&fscache_n_resizes_null)); seq_printf(m, "Relinqs: n=%u rtr=%u drop=%u\n", atomic_read(&fscache_n_relinquishes), diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 796c8b5c5305..3fa4902dc87c 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -64,6 +64,10 @@ struct fscache_cache_ops { /* Withdraw an object without any cookie access counts held */ void (*withdraw_cookie)(struct fscache_cookie *cookie); + /* Change the size of a data object */ + void (*resize_cookie)(struct netfs_cache_resources *cres, + loff_t new_size); + /* Invalidate an object */ bool (*invalidate_cookie)(struct fscache_cookie *cookie); diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 28ce258c1f87..86b1c0db1de5 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -163,6 +163,7 @@ extern struct fscache_cookie *__fscache_acquire_cookie( extern void __fscache_use_cookie(struct fscache_cookie *, bool); extern void __fscache_unuse_cookie(struct fscache_cookie *, const void *, const loff_t *); extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); +extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); @@ -366,6 +367,23 @@ void fscache_update_cookie(struct fscache_cookie *cookie, const void *aux_data, __fscache_update_cookie(cookie, aux_data, object_size); } +/** + * fscache_resize_cookie - Request that a cache object be resized + * @cookie: The cookie representing the cache object + * @new_size: The new size of the object (may be NULL) + * + * Request that the size of an object be changed. + * + * See Documentation/filesystems/caching/netfs-api.txt for a complete + * description. + */ +static inline +void fscache_resize_cookie(struct fscache_cookie *cookie, loff_t new_size) +{ + if (fscache_cookie_enabled(cookie)) + __fscache_resize_cookie(cookie, new_size); +} + /** * fscache_invalidate - Notify cache that an object needs invalidation * @cookie: The cookie representing the cache object diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index 2459d75659cf..5fa37a8b4ec7 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -78,6 +78,7 @@ enum fscache_access_trace { fscache_access_invalidate_cookie_end, fscache_access_io_not_live, fscache_access_io_read, + fscache_access_io_resize, fscache_access_io_wait, fscache_access_io_write, fscache_access_lookup_cookie, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_access_invalidate_cookie_end,"END inval ") \ EM(fscache_access_io_not_live, "END io_notl") \ EM(fscache_access_io_read, "BEGIN io_read") \ + EM(fscache_access_io_resize, "BEGIN io_resz") \ EM(fscache_access_io_wait, "WAIT io ") \ EM(fscache_access_io_write, "BEGIN io_writ") \ EM(fscache_access_lookup_cookie, "BEGIN lookup ") \ @@ -418,6 +420,29 @@ TRACE_EVENT(fscache_invalidate, __entry->cookie, __entry->new_size) ); +TRACE_EVENT(fscache_resize, + TP_PROTO(struct fscache_cookie *cookie, loff_t new_size), + + TP_ARGS(cookie, new_size), + + TP_STRUCT__entry( + __field(unsigned int, cookie ) + __field(loff_t, old_size ) + __field(loff_t, new_size ) + ), + + TP_fast_assign( + __entry->cookie = cookie->debug_id; + __entry->old_size = cookie->object_size; + __entry->new_size = new_size; + ), + + TP_printk("c=%08x os=%08llx sz=%08llx", + __entry->cookie, + __entry->old_size, + __entry->new_size) + ); + #endif /* _TRACE_FSCACHE_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 1bd9c4e4f0494915b2391f373d25096579f835ff Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 18 Nov 2021 08:58:08 +0000 Subject: vfs, cachefiles: Mark a backing file in use with an inode flag Use an inode flag, S_KERNEL_FILE, to mark that a backing file is in use by the kernel to prevent cachefiles or other kernel services from interfering with that file. Alter rmdir to reject attempts to remove a directory marked with this flag. This is used by cachefiles to prevent cachefilesd from removing them. Using S_SWAPFILE instead isn't really viable as that has other effects in the I/O paths. Changes ======= ver #3: - Check for the object pointer being NULL in the tracepoints rather than the caller. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819630256.215744.4815885535039369574.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906931596.143852.8642051223094013028.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967141000.1823006.12920680657559677789.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021541207.640689.564689725898537127.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/Makefile | 1 + fs/cachefiles/namei.c | 43 +++++++++++++++++++++++++++++++++++++++ fs/namei.c | 3 ++- include/linux/fs.h | 1 + include/trace/events/cachefiles.h | 42 ++++++++++++++++++++++++++++++++++++++ 5 files changed, 89 insertions(+), 1 deletion(-) create mode 100644 fs/cachefiles/namei.c (limited to 'include/linux') diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile index 463e3d608b75..e0b092ca077f 100644 --- a/fs/cachefiles/Makefile +++ b/fs/cachefiles/Makefile @@ -7,6 +7,7 @@ cachefiles-y := \ cache.o \ daemon.o \ main.o \ + namei.o \ security.o cachefiles-$(CONFIG_CACHEFILES_ERROR_INJECTION) += error_inject.o diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c new file mode 100644 index 000000000000..913f83f1c900 --- /dev/null +++ b/fs/cachefiles/namei.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* CacheFiles path walking and related routines + * + * Copyright (C) 2021 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include "internal.h" + +/* + * Mark the backing file as being a cache file if it's not already in use. The + * mark tells the culling request command that it's not allowed to cull the + * file or directory. The caller must hold the inode lock. + */ +static bool __cachefiles_mark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + bool can_use = false; + + if (!(inode->i_flags & S_KERNEL_FILE)) { + inode->i_flags |= S_KERNEL_FILE; + trace_cachefiles_mark_active(object, inode); + can_use = true; + } else { + pr_notice("cachefiles: Inode already in use: %pd\n", dentry); + } + + return can_use; +} + +/* + * Unmark a backing inode. The caller must hold the inode lock. + */ +static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + + inode->i_flags &= ~S_KERNEL_FILE; + trace_cachefiles_mark_inactive(object, inode); +} diff --git a/fs/namei.c b/fs/namei.c index 1f9d2187c765..d81f04f8d818 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3958,7 +3958,8 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, inode_lock(dentry->d_inode); error = -EBUSY; - if (is_local_mountpoint(dentry)) + if (is_local_mountpoint(dentry) || + (dentry->d_inode->i_flags & S_KERNEL_FILE)) goto out; error = security_inode_rmdir(dir, dentry); diff --git a/include/linux/fs.h b/include/linux/fs.h index 2c0b8e77d9ab..bcf1ca430139 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2249,6 +2249,7 @@ struct super_operations { #define S_ENCRYPTED (1 << 14) /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD (1 << 15) /* Casefolded file */ #define S_VERITY (1 << 16) /* Verity file (using fs/verity/) */ +#define S_KERNEL_FILE (1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */ /* * Note that nosuid etc flags are inode-specific: setting some file-system diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9bd5a8a60801..6331cd29880d 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -83,6 +83,48 @@ cachefiles_error_traces; #define E_(a, b) { a, b } +TRACE_EVENT(cachefiles_mark_active, + TP_PROTO(struct cachefiles_object *obj, + struct inode *inode), + + TP_ARGS(obj, inode), + + /* Note that obj may be NULL */ + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(ino_t, inode ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->inode = inode->i_ino; + ), + + TP_printk("o=%08x i=%lx", + __entry->obj, __entry->inode) + ); + +TRACE_EVENT(cachefiles_mark_inactive, + TP_PROTO(struct cachefiles_object *obj, + struct inode *inode), + + TP_ARGS(obj, inode), + + /* Note that obj may be NULL */ + TP_STRUCT__entry( + __field(unsigned int, obj ) + __field(ino_t, inode ) + ), + + TP_fast_assign( + __entry->obj = obj ? obj->debug_id : 0; + __entry->inode = inode->i_ino; + ), + + TP_printk("o=%08x i=%lx", + __entry->obj, __entry->inode) + ); + TRACE_EVENT(cachefiles_vfs_error, TP_PROTO(struct cachefiles_object *obj, struct inode *backer, int error, enum cachefiles_error_trace where), -- cgit v1.2.3 From 32e150037dce368d129996ffe5f98217b1974d9e Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 14 Dec 2021 09:51:43 +0000 Subject: fscache, cachefiles: Store the volume coherency data Store the volume coherency data in an xattr and check it when we rebind the volume. If it doesn't match the cache volume is moved to the graveyard and rebuilt anew. Changes ======= ver #4: - Remove a couple of debugging prints. Signed-off-by: David Howells Reviewed-by: Jeff Layton Link: https://lore.kernel.org/r/163967164397.1823006.2950539849831291830.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021563138.640689.15851092065380543119.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/internal.h | 2 + fs/cachefiles/volume.c | 25 ++++++++++++- fs/cachefiles/xattr.c | 78 +++++++++++++++++++++++++++++++++++++++ fs/fscache/volume.c | 14 ++++++- include/linux/fscache.h | 2 + include/trace/events/cachefiles.h | 42 ++++++++++++++++++++- 6 files changed, 157 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index d5868f5514d3..abdd1b66f6b9 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -270,6 +270,8 @@ extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache, struct cachefiles_object *object, struct dentry *dentry); extern void cachefiles_prepare_to_write(struct fscache_cookie *cookie); +extern bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume); +extern int cachefiles_check_volume_xattr(struct cachefiles_volume *volume); /* * Error handling diff --git a/fs/cachefiles/volume.c b/fs/cachefiles/volume.c index 4a14f5e72764..89df0ba8ba5e 100644 --- a/fs/cachefiles/volume.c +++ b/fs/cachefiles/volume.c @@ -22,7 +22,8 @@ void cachefiles_acquire_volume(struct fscache_volume *vcookie) struct dentry *vdentry, *fan; size_t len; char *name; - int n_accesses, i; + bool is_new = false; + int ret, n_accesses, i; _enter(""); @@ -43,11 +44,29 @@ void cachefiles_acquire_volume(struct fscache_volume *vcookie) memcpy(name + 1, vcookie->key + 1, len); name[len + 1] = 0; - vdentry = cachefiles_get_directory(cache, cache->store, name, NULL); +retry: + vdentry = cachefiles_get_directory(cache, cache->store, name, &is_new); if (IS_ERR(vdentry)) goto error_name; volume->dentry = vdentry; + if (is_new) { + if (!cachefiles_set_volume_xattr(volume)) + goto error_dir; + } else { + ret = cachefiles_check_volume_xattr(volume); + if (ret < 0) { + if (ret != -ESTALE) + goto error_dir; + inode_lock_nested(d_inode(cache->store), I_MUTEX_PARENT); + cachefiles_bury_object(cache, NULL, cache->store, vdentry, + FSCACHE_VOLUME_IS_WEIRD); + cachefiles_put_directory(volume->dentry); + cond_resched(); + goto retry; + } + } + for (i = 0; i < 256; i++) { sprintf(name, "@%02x", i); fan = cachefiles_get_directory(cache, vdentry, name, NULL); @@ -74,6 +93,7 @@ void cachefiles_acquire_volume(struct fscache_volume *vcookie) error_fan: for (i = 0; i < 256; i++) cachefiles_put_directory(volume->fanout[i]); +error_dir: cachefiles_put_directory(volume->dentry); error_name: kfree(name); @@ -114,5 +134,6 @@ void cachefiles_free_volume(struct fscache_volume *vcookie) void cachefiles_withdraw_volume(struct cachefiles_volume *volume) { fscache_withdraw_volume(volume->vcookie); + cachefiles_set_volume_xattr(volume); __cachefiles_free_volume(volume); } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 0601c46a22ef..83f41bd0c3a9 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -179,3 +179,81 @@ void cachefiles_prepare_to_write(struct fscache_cookie *cookie) cachefiles_end_secure(cache, saved_cred); } } + +/* + * Set the state xattr on a volume directory. + */ +bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) +{ + unsigned int len = volume->vcookie->coherency_len; + const void *p = volume->vcookie->coherency; + struct dentry *dentry = volume->dentry; + int ret; + + _enter("%x,#%d", volume->vcookie->debug_id, len); + + ret = cachefiles_inject_write_error(); + if (ret == 0) + ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, + p, len, 0); + if (ret < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, + cachefiles_trace_setxattr_error); + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, + cachefiles_coherency_vol_set_fail); + if (ret != -ENOMEM) + cachefiles_io_error( + volume->cache, "Failed to set xattr with error %d", ret); + } else { + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, + cachefiles_coherency_vol_set_ok); + } + + _leave(" = %d", ret); + return ret == 0; +} + +/* + * Check the consistency between the backing cache and the volume cookie. + */ +int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) +{ + struct cachefiles_xattr *buf; + struct dentry *dentry = volume->dentry; + unsigned int len = volume->vcookie->coherency_len; + const void *p = volume->vcookie->coherency; + enum cachefiles_coherency_trace why; + ssize_t xlen; + int ret = -ESTALE; + + _enter(""); + + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + xlen = cachefiles_inject_read_error(); + if (xlen == 0) + xlen = vfs_getxattr(&init_user_ns, dentry, cachefiles_xattr_cache, buf, len); + if (xlen != len) { + if (xlen < 0) { + trace_cachefiles_vfs_error(NULL, d_inode(dentry), xlen, + cachefiles_trace_getxattr_error); + if (xlen == -EIO) + cachefiles_io_error( + volume->cache, + "Failed to read xattr with error %zd", xlen); + } + why = cachefiles_coherency_vol_check_xattr; + } else if (memcmp(buf->data, p, len) != 0) { + why = cachefiles_coherency_vol_check_cmp; + } else { + why = cachefiles_coherency_vol_check_ok; + ret = 0; + } + + trace_cachefiles_vol_coherency(volume, d_inode(dentry)->i_ino, why); + kfree(buf); + _leave(" = %d", ret); + return ret; +} diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index e1a8e92a6adb..a57c6cbee858 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -205,15 +205,22 @@ static struct fscache_volume *fscache_alloc_volume(const char *volume_key, size_t klen, hlen; char *key; + if (!coherency_data) + coherency_len = 0; + cache = fscache_lookup_cache(cache_name, false); if (IS_ERR(cache)) return NULL; - volume = kzalloc(sizeof(*volume), GFP_KERNEL); + volume = kzalloc(struct_size(volume, coherency, coherency_len), + GFP_KERNEL); if (!volume) goto err_cache; volume->cache = cache; + volume->coherency_len = coherency_len; + if (coherency_data) + memcpy(volume->coherency, coherency_data, coherency_len); INIT_LIST_HEAD(&volume->proc_link); INIT_WORK(&volume->work, fscache_create_volume_work); refcount_set(&volume->ref, 1); @@ -421,8 +428,11 @@ void __fscache_relinquish_volume(struct fscache_volume *volume, if (WARN_ON(test_and_set_bit(FSCACHE_VOLUME_RELINQUISHED, &volume->flags))) return; - if (invalidate) + if (invalidate) { set_bit(FSCACHE_VOLUME_INVALIDATE, &volume->flags); + } else if (coherency_data) { + memcpy(volume->coherency, coherency_data, volume->coherency_len); + } fscache_put_volume(volume, fscache_volume_put_relinquish); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 86b1c0db1de5..7bd35f60d19a 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -87,6 +87,8 @@ struct fscache_volume { #define FSCACHE_VOLUME_COLLIDED_WITH 2 /* Volume was collided with */ #define FSCACHE_VOLUME_ACQUIRE_PENDING 3 /* Volume is waiting to complete acquisition */ #define FSCACHE_VOLUME_CREATING 4 /* Volume is being created on disk */ + u8 coherency_len; /* Length of the coherency data */ + u8 coherency[]; /* Coherency data */ }; /* diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index ab1376ebc3ab..1172529b5b49 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -40,6 +40,7 @@ enum fscache_why_object_killed { FSCACHE_OBJECT_NO_SPACE, FSCACHE_OBJECT_WAS_RETIRED, FSCACHE_OBJECT_WAS_CULLED, + FSCACHE_VOLUME_IS_WEIRD, }; enum cachefiles_coherency_trace { @@ -53,6 +54,11 @@ enum cachefiles_coherency_trace { cachefiles_coherency_check_xattr, cachefiles_coherency_set_fail, cachefiles_coherency_set_ok, + cachefiles_coherency_vol_check_cmp, + cachefiles_coherency_vol_check_ok, + cachefiles_coherency_vol_check_xattr, + cachefiles_coherency_vol_set_fail, + cachefiles_coherency_vol_set_ok, }; enum cachefiles_trunc_trace { @@ -103,7 +109,8 @@ enum cachefiles_error_trace { EM(FSCACHE_OBJECT_INVALIDATED, "inval") \ EM(FSCACHE_OBJECT_NO_SPACE, "no_space") \ EM(FSCACHE_OBJECT_WAS_RETIRED, "was_retired") \ - E_(FSCACHE_OBJECT_WAS_CULLED, "was_culled") + EM(FSCACHE_OBJECT_WAS_CULLED, "was_culled") \ + E_(FSCACHE_VOLUME_IS_WEIRD, "volume_weird") #define cachefiles_obj_ref_traces \ EM(cachefiles_obj_get_ioreq, "GET ioreq") \ @@ -129,7 +136,12 @@ enum cachefiles_error_trace { EM(cachefiles_coherency_check_type, "BAD type") \ EM(cachefiles_coherency_check_xattr, "BAD xatt") \ EM(cachefiles_coherency_set_fail, "SET fail") \ - E_(cachefiles_coherency_set_ok, "SET ok ") + EM(cachefiles_coherency_set_ok, "SET ok ") \ + EM(cachefiles_coherency_vol_check_cmp, "VOL BAD cmp ") \ + EM(cachefiles_coherency_vol_check_ok, "VOL OK ") \ + EM(cachefiles_coherency_vol_check_xattr,"VOL BAD xatt") \ + EM(cachefiles_coherency_vol_set_fail, "VOL SET fail") \ + E_(cachefiles_coherency_vol_set_ok, "VOL SET ok ") #define cachefiles_trunc_traces \ EM(cachefiles_trunc_dio_adjust, "DIOADJ") \ @@ -365,6 +377,32 @@ TRACE_EVENT(cachefiles_coherency, __entry->content) ); +TRACE_EVENT(cachefiles_vol_coherency, + TP_PROTO(struct cachefiles_volume *volume, + ino_t ino, + enum cachefiles_coherency_trace why), + + TP_ARGS(volume, ino, why), + + /* Note that obj may be NULL */ + TP_STRUCT__entry( + __field(unsigned int, vol ) + __field(enum cachefiles_coherency_trace, why ) + __field(u64, ino ) + ), + + TP_fast_assign( + __entry->vol = volume->vcookie->debug_id; + __entry->why = why; + __entry->ino = ino; + ), + + TP_printk("V=%08x %s i=%llx", + __entry->vol, + __print_symbolic(__entry->why, cachefiles_coherency_traces), + __entry->ino) + ); + TRACE_EVENT(cachefiles_prep_read, TP_PROTO(struct netfs_read_subrequest *sreq, enum netfs_read_source source, -- cgit v1.2.3 From 3929eca769b5a231010b4978acc61c0735da198f Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 21 Oct 2021 21:58:29 +0100 Subject: fscache, cachefiles: Display stats of no-space events Add stat counters of no-space events that caused caching not to happen and display in /proc/fs/fscache/stats. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819653216.215744.17210522251617386509.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906958369.143852.7257100711818401748.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967166917.1823006.14842444049198947892.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021566184.640689.4417328329632709265.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/cache.c | 18 +++++++++++++++--- fs/cachefiles/daemon.c | 2 +- fs/cachefiles/internal.h | 11 +++++++++-- fs/cachefiles/io.c | 7 +++++-- fs/cachefiles/namei.c | 6 ++++-- fs/fscache/stats.c | 8 ++++++++ include/linux/fscache-cache.h | 6 ++++++ 7 files changed, 48 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index e2cbbc08bad9..809519286335 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -147,7 +147,7 @@ int cachefiles_add_cache(struct cachefiles_cache *cache) pr_info("File cache on %s registered\n", cache_cookie->name); /* check how much space the cache has */ - cachefiles_has_space(cache, 0, 0); + cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); cachefiles_end_secure(cache, saved_cred); _leave(" = 0 [%px]", cache->cache); return 0; @@ -175,7 +175,8 @@ error_getsec: * cache */ int cachefiles_has_space(struct cachefiles_cache *cache, - unsigned fnr, unsigned bnr) + unsigned fnr, unsigned bnr, + enum cachefiles_has_space_for reason) { struct kstatfs stats; u64 b_avail, b_writing; @@ -233,7 +234,7 @@ int cachefiles_has_space(struct cachefiles_cache *cache, ret = -ENOBUFS; if (stats.f_ffree < cache->fstop || b_avail < cache->bstop) - goto begin_cull; + goto stop_and_begin_cull; ret = 0; if (stats.f_ffree < cache->fcull || @@ -252,6 +253,17 @@ int cachefiles_has_space(struct cachefiles_cache *cache, //_leave(" = 0"); return 0; +stop_and_begin_cull: + switch (reason) { + case cachefiles_has_space_for_write: + fscache_count_no_write_space(); + break; + case cachefiles_has_space_for_create: + fscache_count_no_create_space(); + break; + default: + break; + } begin_cull: if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) { _debug("### CULL CACHE ###"); diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 45af558a696e..40a792421fc1 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -170,7 +170,7 @@ static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer, return 0; /* check how much space the cache has */ - cachefiles_has_space(cache, 0, 0); + cachefiles_has_space(cache, 0, 0, cachefiles_has_space_check); /* summarise */ f_released = atomic_xchg(&cache->f_released, 0); diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h index abdd1b66f6b9..8dd54d9375b6 100644 --- a/fs/cachefiles/internal.h +++ b/fs/cachefiles/internal.h @@ -130,10 +130,17 @@ static inline void cachefiles_state_changed(struct cachefiles_cache *cache) * cache.c */ extern int cachefiles_add_cache(struct cachefiles_cache *cache); -extern int cachefiles_has_space(struct cachefiles_cache *cache, - unsigned fnr, unsigned bnr); extern void cachefiles_withdraw_cache(struct cachefiles_cache *cache); +enum cachefiles_has_space_for { + cachefiles_has_space_check, + cachefiles_has_space_for_write, + cachefiles_has_space_for_create, +}; +extern int cachefiles_has_space(struct cachefiles_cache *cache, + unsigned fnr, unsigned bnr, + enum cachefiles_has_space_for reason); + /* * daemon.c */ diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 6f4dce0cfc36..60b1eac2ce78 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -468,7 +468,8 @@ static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, * space, we need to see if it's fully allocated. If it's not, we may * want to cull it. */ - if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE) == 0) + if (cachefiles_has_space(cache, 0, *_len / PAGE_SIZE, + cachefiles_has_space_check) == 0) return 0; /* Enough space to simply overwrite the whole block */ pos = cachefiles_inject_read_error(); @@ -483,6 +484,7 @@ static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, return 0; /* Fully allocated */ /* Partially allocated, but insufficient space: cull. */ + fscache_count_no_write_space(); ret = cachefiles_inject_remove_error(); if (ret == 0) ret = vfs_fallocate(file, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, @@ -498,7 +500,8 @@ static int __cachefiles_prepare_write(struct netfs_cache_resources *cres, return ret; check_space: - return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE); + return cachefiles_has_space(cache, 0, *_len / PAGE_SIZE, + cachefiles_has_space_for_write); } static int cachefiles_prepare_write(struct netfs_cache_resources *cres, diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index b549e9f79c01..ab3ca598acac 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -115,7 +115,8 @@ retry: /* we need to create the subdir if it doesn't exist yet */ if (d_is_negative(subdir)) { - ret = cachefiles_has_space(cache, 1, 0); + ret = cachefiles_has_space(cache, 1, 0, + cachefiles_has_space_for_create); if (ret < 0) goto mkdir_error; @@ -513,7 +514,8 @@ static bool cachefiles_create_file(struct cachefiles_object *object) struct file *file; int ret; - ret = cachefiles_has_space(object->volume->cache, 1, 0); + ret = cachefiles_has_space(object->volume->cache, 1, 0, + cachefiles_has_space_for_create); if (ret < 0) return false; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index 798ee68b3e9d..db2f4e225dd9 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -42,6 +42,10 @@ atomic_t fscache_n_read; EXPORT_SYMBOL(fscache_n_read); atomic_t fscache_n_write; EXPORT_SYMBOL(fscache_n_write); +atomic_t fscache_n_no_write_space; +EXPORT_SYMBOL(fscache_n_no_write_space); +atomic_t fscache_n_no_create_space; +EXPORT_SYMBOL(fscache_n_no_create_space); /* * display the general statistics @@ -82,6 +86,10 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_relinquishes_retire), atomic_read(&fscache_n_relinquishes_dropped)); + seq_printf(m, "NoSpace: nwr=%u ncr=%u\n", + atomic_read(&fscache_n_no_write_space), + atomic_read(&fscache_n_no_create_space)); + seq_printf(m, "IO : rd=%u wr=%u\n", atomic_read(&fscache_n_read), atomic_read(&fscache_n_write)); diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 3fa4902dc87c..007e47f38610 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -186,11 +186,17 @@ static inline void fscache_wait_for_objects(struct fscache_cache *cache) #ifdef CONFIG_FSCACHE_STATS extern atomic_t fscache_n_read; extern atomic_t fscache_n_write; +extern atomic_t fscache_n_no_write_space; +extern atomic_t fscache_n_no_create_space; #define fscache_count_read() atomic_inc(&fscache_n_read) #define fscache_count_write() atomic_inc(&fscache_n_write) +#define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) +#define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) #else #define fscache_count_read() do {} while(0) #define fscache_count_write() do {} while(0) +#define fscache_count_no_write_space() do {} while(0) +#define fscache_count_no_create_space() do {} while(0) #endif #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 9f08ebc3438baaaefcc79654b330209b83397f17 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 22 Oct 2021 09:17:58 +0100 Subject: fscache, cachefiles: Display stat of culling events Add a stat counter of culling events whereby the cache backend culls a file to make space (when asked by cachefilesd in this case) and display in /proc/fs/fscache/stats. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/163819654165.215744.3797804661644212436.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906961387.143852.9291157239960289090.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967168266.1823006.14436200166581605746.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021567619.640689.4339228906248763197.stgit@warthog.procyon.org.uk/ # v4 --- fs/cachefiles/namei.c | 1 + fs/fscache/stats.c | 7 +++++-- include/linux/fscache-cache.h | 3 +++ 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index ab3ca598acac..9bd692870617 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -805,6 +805,7 @@ int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir, if (ret < 0) goto error; + fscache_count_culled(); dput(victim); _leave(" = 0"); return 0; diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c index db2f4e225dd9..fc94e5e79f1c 100644 --- a/fs/fscache/stats.c +++ b/fs/fscache/stats.c @@ -46,6 +46,8 @@ atomic_t fscache_n_no_write_space; EXPORT_SYMBOL(fscache_n_no_write_space); atomic_t fscache_n_no_create_space; EXPORT_SYMBOL(fscache_n_no_create_space); +atomic_t fscache_n_culled; +EXPORT_SYMBOL(fscache_n_culled); /* * display the general statistics @@ -86,9 +88,10 @@ int fscache_stats_show(struct seq_file *m, void *v) atomic_read(&fscache_n_relinquishes_retire), atomic_read(&fscache_n_relinquishes_dropped)); - seq_printf(m, "NoSpace: nwr=%u ncr=%u\n", + seq_printf(m, "NoSpace: nwr=%u ncr=%u cull=%u\n", atomic_read(&fscache_n_no_write_space), - atomic_read(&fscache_n_no_create_space)); + atomic_read(&fscache_n_no_create_space), + atomic_read(&fscache_n_culled)); seq_printf(m, "IO : rd=%u wr=%u\n", atomic_read(&fscache_n_read), diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 007e47f38610..a174cedf4d90 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -188,15 +188,18 @@ extern atomic_t fscache_n_read; extern atomic_t fscache_n_write; extern atomic_t fscache_n_no_write_space; extern atomic_t fscache_n_no_create_space; +extern atomic_t fscache_n_culled; #define fscache_count_read() atomic_inc(&fscache_n_read) #define fscache_count_write() atomic_inc(&fscache_n_write) #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space) #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space) +#define fscache_count_culled() atomic_inc(&fscache_n_culled) #else #define fscache_count_read() do {} while(0) #define fscache_count_write() do {} while(0) #define fscache_count_no_write_space() do {} while(0) #define fscache_count_no_create_space() do {} while(0) +#define fscache_count_culled() do {} while(0) #endif #endif /* _LINUX_FSCACHE_CACHE_H */ -- cgit v1.2.3 From 2efd61a608b0039911924d2e5d7028eb37496e85 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 10 Dec 2021 16:36:20 +0000 Subject: KVM: Warn if mark_page_dirty() is called without an active vCPU The various kvm_write_guest() and mark_page_dirty() functions must only ever be called in the context of an active vCPU, because if dirty ring tracking is enabled it may simply oops when kvm_get_running_vcpu() returns NULL for the vcpu and then kvm_dirty_ring_get() dereferences it. This oops was reported by "butt3rflyh4ck" in https://lore.kernel.org/kvm/CAFcO6XOmoS7EacN_n6v4Txk7xL7iqRa2gABg3F7E3Naf5uG94g@mail.gmail.com/ That actual bug will be fixed under separate cover but this warning should help to prevent new ones from being added. Signed-off-by: David Woodhouse Message-Id: <20211210163625.2886-2-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- include/linux/kvm_dirty_ring.h | 6 ------ virt/kvm/dirty_ring.c | 9 --------- virt/kvm/kvm_main.c | 7 ++++++- 3 files changed, 6 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 4da8d4a4140b..906f899813dc 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -43,11 +43,6 @@ static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, return 0; } -static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) -{ - return NULL; -} - static inline int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring) { @@ -78,7 +73,6 @@ static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring) u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); -struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm); /* * called with kvm->slots_lock held, returns the number of diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 88f4683198ea..8e9874760fb3 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -36,15 +36,6 @@ static bool kvm_dirty_ring_full(struct kvm_dirty_ring *ring) return kvm_dirty_ring_used(ring) >= ring->size; } -struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm) -{ - struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); - - WARN_ON_ONCE(vcpu->kvm != kvm); - - return &vcpu->dirty_ring; -} - static void kvm_reset_dirty_gfn(struct kvm *kvm, u32 slot, u64 offset, u64 mask) { struct kvm_memory_slot *memslot; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index b0f7e6eb00ff..af5b4427b139 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3155,12 +3155,17 @@ void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn) { + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + + if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm)) + return; + if (memslot && kvm_slot_dirty_track_enabled(memslot)) { unsigned long rel_gfn = gfn - memslot->base_gfn; u32 slot = (memslot->as_id << 16) | memslot->id; if (kvm->dirty_ring_size) - kvm_dirty_ring_push(kvm_dirty_ring_get(kvm), + kvm_dirty_ring_push(&vcpu->dirty_ring, slot, rel_gfn); else set_bit_le(rel_gfn, memslot->dirty_bitmap); -- cgit v1.2.3 From 982ed0de4753ed6e71dbd40f82a5a066baf133ed Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 10 Dec 2021 16:36:21 +0000 Subject: KVM: Reinstate gfn_to_pfn_cache with invalidation support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This can be used in two modes. There is an atomic mode where the cached mapping is accessed while holding the rwlock, and a mode where the physical address is used by a vCPU in guest mode. For the latter case, an invalidation will wake the vCPU with the new KVM_REQ_GPC_INVALIDATE, and the architecture will need to refresh any caches it still needs to access before entering guest mode again. Only one vCPU can be targeted by the wake requests; it's simple enough to make it wake all vCPUs or even a mask but I don't see a use case for that additional complexity right now. Invalidation happens from the invalidate_range_start MMU notifier, which needs to be able to sleep in order to wake the vCPU and wait for it. This means that revalidation potentially needs to "wait" for the MMU operation to complete and the invalidate_range_end notifier to be invoked. Like the vCPU when it takes a page fault in that period, we just spin — fixing that in a future patch by implementing an actual *wait* may be another part of shaving this particularly hirsute yak. As noted in the comments in the function itself, the only case where the invalidate_range_start notifier is expected to be called *without* being able to sleep is when the OOM reaper is killing the process. In that case, we expect the vCPU threads already to have exited, and thus there will be nothing to wake, and no reason to wait. So we clear the KVM_REQUEST_WAIT bit and send the request anyway, then complain loudly if there actually *was* anything to wake up. Signed-off-by: David Woodhouse Message-Id: <20211210163625.2886-3-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/Kconfig | 1 + include/linux/kvm_host.h | 103 ++++++++++++++ include/linux/kvm_types.h | 18 +++ virt/kvm/Kconfig | 3 + virt/kvm/Makefile.kvm | 1 + virt/kvm/dirty_ring.c | 2 +- virt/kvm/kvm_main.c | 12 +- virt/kvm/kvm_mm.h | 44 ++++++ virt/kvm/mmu_lock.h | 23 ---- virt/kvm/pfncache.c | 337 ++++++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 517 insertions(+), 27 deletions(-) create mode 100644 virt/kvm/kvm_mm.h delete mode 100644 virt/kvm/mmu_lock.h create mode 100644 virt/kvm/pfncache.c (limited to 'include/linux') diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 03b2ce34e7f4..ebc8ce9ec917 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -26,6 +26,7 @@ config KVM select PREEMPT_NOTIFIERS select MMU_NOTIFIER select HAVE_KVM_IRQCHIP + select HAVE_KVM_PFNCACHE select HAVE_KVM_IRQFD select HAVE_KVM_DIRTY_RING select IRQ_BYPASS_MANAGER diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f9bbcf519280..9bbb1f1d9e48 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -155,6 +155,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_UNBLOCK 2 #define KVM_REQ_UNHALT 3 #define KVM_REQ_VM_DEAD (4 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_GPC_INVALIDATE (5 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQUEST_ARCH_BASE 8 #define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ @@ -593,6 +594,10 @@ struct kvm { unsigned long mn_active_invalidate_count; struct rcuwait mn_memslots_update_rcuwait; + /* For management / invalidation of gfn_to_pfn_caches */ + spinlock_t gpc_lock; + struct list_head gpc_list; + /* * created_vcpus is protected by kvm->lock, and is incremented * at the beginning of KVM_CREATE_VCPU. online_vcpus is only @@ -1099,6 +1104,104 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); +/** + * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a + * given guest physical address. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @vcpu: vCPU to be used for marking pages dirty and to be woken on + * invalidation. + * @guest_uses_pa: indicates that the resulting host physical PFN is used while + * @vcpu is IN_GUEST_MODE so invalidations should wake it. + * @kernel_map: requests a kernel virtual mapping (kmap / memremap). + * @gpa: guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * @dirty: mark the cache dirty immediately. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This primes a gfn_to_pfn_cache and links it into the @kvm's list for + * invalidations to be processed. Invalidation callbacks to @vcpu using + * %KVM_REQ_GPC_INVALIDATE will occur only for MMU notifiers, not for KVM + * memslot changes. Callers are required to use kvm_gfn_to_pfn_cache_check() + * to ensure that the cache is valid before accessing the target page. + */ +int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, bool guest_uses_pa, + bool kernel_map, gpa_t gpa, unsigned long len, + bool dirty); + +/** + * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: current guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * @dirty: mark the cache dirty immediately. + * + * @return: %true if the cache is still valid and the address matches. + * %false if the cache is not valid. + * + * Callers outside IN_GUEST_MODE context should hold a read lock on @gpc->lock + * while calling this function, and then continue to hold the lock until the + * access is complete. + * + * Callers in IN_GUEST_MODE may do so without locking, although they should + * still hold a read lock on kvm->scru for the memslot checks. + */ +bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len); + +/** + * kvm_gfn_to_pfn_cache_refresh - update a previously initialized cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * @gpa: updated guest physical address to map. + * @len: sanity check; the range being access must fit a single page. + * @dirty: mark the cache dirty immediately. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * This will attempt to refresh a gfn_to_pfn_cache. Note that a successful + * returm from this function does not mean the page can be immediately + * accessed because it may have raced with an invalidation. Callers must + * still lock and check the cache status, as this function does not return + * with the lock still held to permit access. + */ +int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len, bool dirty); + +/** + * kvm_gfn_to_pfn_cache_unmap - temporarily unmap a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This unmaps the referenced page and marks it dirty, if appropriate. The + * cache is left in the invalid state but at least the mapping from GPA to + * userspace HVA will remain cached and can be reused on a subsequent + * refresh. + */ +void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache. + * + * @kvm: pointer to kvm instance. + * @gpc: struct gfn_to_pfn_cache object. + * + * This removes a cache from the @kvm's list to be processed on MMU notifier + * invocation. + */ +void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); + void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 888ef12862c9..dceac12c1ce5 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -19,6 +19,7 @@ struct kvm_memslots; enum kvm_mr_change; #include +#include #include @@ -53,6 +54,23 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; +struct gfn_to_pfn_cache { + u64 generation; + gpa_t gpa; + unsigned long uhva; + struct kvm_memory_slot *memslot; + struct kvm_vcpu *vcpu; + struct list_head list; + rwlock_t lock; + void *khva; + kvm_pfn_t pfn; + bool active; + bool valid; + bool dirty; + bool kernel_map; + bool guest_uses_pa; +}; + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 97cf5413ac25..f4834c20e4a6 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -4,6 +4,9 @@ config HAVE_KVM bool +config HAVE_KVM_PFNCACHE + bool + config HAVE_KVM_IRQCHIP bool diff --git a/virt/kvm/Makefile.kvm b/virt/kvm/Makefile.kvm index ffdcad3cc97a..2c27d5d0c367 100644 --- a/virt/kvm/Makefile.kvm +++ b/virt/kvm/Makefile.kvm @@ -11,3 +11,4 @@ kvm-$(CONFIG_KVM_MMIO) += $(KVM)/coalesced_mmio.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-$(CONFIG_HAVE_KVM_IRQ_ROUTING) += $(KVM)/irqchip.o kvm-$(CONFIG_HAVE_KVM_DIRTY_RING) += $(KVM)/dirty_ring.o +kvm-$(CONFIG_HAVE_KVM_PFNCACHE) += $(KVM)/pfncache.o diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index 8e9874760fb3..222ecc81d7df 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -9,7 +9,7 @@ #include #include #include -#include "mmu_lock.h" +#include "kvm_mm.h" int __weak kvm_cpu_dirty_log_size(void) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index af5b4427b139..6e8e9d36f382 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -59,7 +59,7 @@ #include "coalesced_mmio.h" #include "async_pf.h" -#include "mmu_lock.h" +#include "kvm_mm.h" #include "vfio.h" #define CREATE_TRACE_POINTS @@ -711,6 +711,9 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, kvm->mn_active_invalidate_count++; spin_unlock(&kvm->mn_invalidate_lock); + gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end, + hva_range.may_block); + __kvm_handle_hva_range(kvm, &hva_range); return 0; @@ -1071,6 +1074,9 @@ static struct kvm *kvm_create_vm(unsigned long type) rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); + INIT_LIST_HEAD(&kvm->gpc_list); + spin_lock_init(&kvm->gpc_lock); + INIT_LIST_HEAD(&kvm->devices); BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); @@ -2539,8 +2545,8 @@ out: * 2): @write_fault = false && @writable, @writable will tell the caller * whether the mapping is writable. */ -static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, - bool write_fault, bool *writable) +kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable) { struct vm_area_struct *vma; kvm_pfn_t pfn = 0; diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h new file mode 100644 index 000000000000..34ca40823260 --- /dev/null +++ b/virt/kvm/kvm_mm.h @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#ifndef __KVM_MM_H__ +#define __KVM_MM_H__ 1 + +/* + * Architectures can choose whether to use an rwlock or spinlock + * for the mmu_lock. These macros, for use in common code + * only, avoids using #ifdefs in places that must deal with + * multiple architectures. + */ + +#ifdef KVM_HAVE_MMU_RWLOCK +#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock) +#define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock) +#define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock) +#define KVM_MMU_READ_LOCK(kvm) read_lock(&(kvm)->mmu_lock) +#define KVM_MMU_READ_UNLOCK(kvm) read_unlock(&(kvm)->mmu_lock) +#else +#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock) +#define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) +#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) +#define KVM_MMU_READ_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) +#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) +#endif /* KVM_HAVE_MMU_RWLOCK */ + +kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable); + +#ifdef CONFIG_HAVE_KVM_PFNCACHE +void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, + unsigned long start, + unsigned long end, + bool may_block); +#else +static inline void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, + unsigned long start, + unsigned long end, + bool may_block) +{ +} +#endif /* HAVE_KVM_PFNCACHE */ + +#endif /* __KVM_MM_H__ */ diff --git a/virt/kvm/mmu_lock.h b/virt/kvm/mmu_lock.h deleted file mode 100644 index 9e1308f9734c..000000000000 --- a/virt/kvm/mmu_lock.h +++ /dev/null @@ -1,23 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#ifndef KVM_MMU_LOCK_H -#define KVM_MMU_LOCK_H 1 - -/* - * Architectures can choose whether to use an rwlock or spinlock - * for the mmu_lock. These macros, for use in common code - * only, avoids using #ifdefs in places that must deal with - * multiple architectures. - */ - -#ifdef KVM_HAVE_MMU_RWLOCK -#define KVM_MMU_LOCK_INIT(kvm) rwlock_init(&(kvm)->mmu_lock) -#define KVM_MMU_LOCK(kvm) write_lock(&(kvm)->mmu_lock) -#define KVM_MMU_UNLOCK(kvm) write_unlock(&(kvm)->mmu_lock) -#else -#define KVM_MMU_LOCK_INIT(kvm) spin_lock_init(&(kvm)->mmu_lock) -#define KVM_MMU_LOCK(kvm) spin_lock(&(kvm)->mmu_lock) -#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock) -#endif /* KVM_HAVE_MMU_RWLOCK */ - -#endif diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c new file mode 100644 index 000000000000..ce878f4be4da --- /dev/null +++ b/virt/kvm/pfncache.c @@ -0,0 +1,337 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Kernel-based Virtual Machine driver for Linux + * + * This module enables kernel and guest-mode vCPU access to guest physical + * memory with suitable invalidation mechanisms. + * + * Copyright © 2021 Amazon.com, Inc. or its affiliates. + * + * Authors: + * David Woodhouse + */ + +#include +#include +#include +#include +#include + +#include "kvm_mm.h" + +/* + * MMU notifier 'invalidate_range_start' hook. + */ +void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, + unsigned long end, bool may_block) +{ + DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); + struct gfn_to_pfn_cache *gpc; + bool wake_vcpus = false; + + spin_lock(&kvm->gpc_lock); + list_for_each_entry(gpc, &kvm->gpc_list, list) { + write_lock_irq(&gpc->lock); + + /* Only a single page so no need to care about length */ + if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) && + gpc->uhva >= start && gpc->uhva < end) { + gpc->valid = false; + + /* + * If a guest vCPU could be using the physical address, + * it needs to be woken. + */ + if (gpc->guest_uses_pa) { + if (!wake_vcpus) { + wake_vcpus = true; + bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); + } + __set_bit(gpc->vcpu->vcpu_idx, vcpu_bitmap); + } + + /* + * We cannot call mark_page_dirty() from here because + * this physical CPU might not have an active vCPU + * with which to do the KVM dirty tracking. + * + * Neither is there any point in telling the kernel MM + * that the underlying page is dirty. A vCPU in guest + * mode might still be writing to it up to the point + * where we wake them a few lines further down anyway. + * + * So all the dirty marking happens on the unmap. + */ + } + write_unlock_irq(&gpc->lock); + } + spin_unlock(&kvm->gpc_lock); + + if (wake_vcpus) { + unsigned int req = KVM_REQ_GPC_INVALIDATE; + bool called; + + /* + * If the OOM reaper is active, then all vCPUs should have + * been stopped already, so perform the request without + * KVM_REQUEST_WAIT and be sad if any needed to be woken. + */ + if (!may_block) + req &= ~KVM_REQUEST_WAIT; + + called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap); + + WARN_ON_ONCE(called && !may_block); + } +} + +bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + + if ((gpa & ~PAGE_MASK) + len > PAGE_SIZE) + return false; + + if (gpc->gpa != gpa || gpc->generation != slots->generation || + kvm_is_error_hva(gpc->uhva)) + return false; + + if (!gpc->valid) + return false; + + return true; +} +EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_check); + +static void __release_gpc(struct kvm *kvm, kvm_pfn_t pfn, void *khva, + gpa_t gpa, bool dirty) +{ + /* Unmap the old page if it was mapped before, and release it */ + if (!is_error_noslot_pfn(pfn)) { + if (khva) { + if (pfn_valid(pfn)) + kunmap(pfn_to_page(pfn)); +#ifdef CONFIG_HAS_IOMEM + else + memunmap(khva); +#endif + } + + kvm_release_pfn(pfn, dirty); + if (dirty) + mark_page_dirty(kvm, gpa); + } +} + +static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, unsigned long uhva) +{ + unsigned long mmu_seq; + kvm_pfn_t new_pfn; + int retry; + + do { + mmu_seq = kvm->mmu_notifier_seq; + smp_rmb(); + + /* We always request a writeable mapping */ + new_pfn = hva_to_pfn(uhva, false, NULL, true, NULL); + if (is_error_noslot_pfn(new_pfn)) + break; + + KVM_MMU_READ_LOCK(kvm); + retry = mmu_notifier_retry_hva(kvm, mmu_seq, uhva); + KVM_MMU_READ_UNLOCK(kvm); + if (!retry) + break; + + cond_resched(); + } while (1); + + return new_pfn; +} + +int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + gpa_t gpa, unsigned long len, bool dirty) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + unsigned long page_offset = gpa & ~PAGE_MASK; + kvm_pfn_t old_pfn, new_pfn; + unsigned long old_uhva; + gpa_t old_gpa; + void *old_khva; + bool old_valid, old_dirty; + int ret = 0; + + /* + * If must fit within a single page. The 'len' argument is + * only to enforce that. + */ + if (page_offset + len > PAGE_SIZE) + return -EINVAL; + + write_lock_irq(&gpc->lock); + + old_gpa = gpc->gpa; + old_pfn = gpc->pfn; + old_khva = gpc->khva - offset_in_page(gpc->khva); + old_uhva = gpc->uhva; + old_valid = gpc->valid; + old_dirty = gpc->dirty; + + /* If the userspace HVA is invalid, refresh that first */ + if (gpc->gpa != gpa || gpc->generation != slots->generation || + kvm_is_error_hva(gpc->uhva)) { + gfn_t gfn = gpa_to_gfn(gpa); + + gpc->dirty = false; + gpc->gpa = gpa; + gpc->generation = slots->generation; + gpc->memslot = __gfn_to_memslot(slots, gfn); + gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn); + + if (kvm_is_error_hva(gpc->uhva)) { + ret = -EFAULT; + goto out; + } + + gpc->uhva += page_offset; + } + + /* + * If the userspace HVA changed or the PFN was already invalid, + * drop the lock and do the HVA to PFN lookup again. + */ + if (!old_valid || old_uhva != gpc->uhva) { + unsigned long uhva = gpc->uhva; + void *new_khva = NULL; + + /* Placeholders for "hva is valid but not yet mapped" */ + gpc->pfn = KVM_PFN_ERR_FAULT; + gpc->khva = NULL; + gpc->valid = true; + + write_unlock_irq(&gpc->lock); + + new_pfn = hva_to_pfn_retry(kvm, uhva); + if (is_error_noslot_pfn(new_pfn)) { + ret = -EFAULT; + goto map_done; + } + + if (gpc->kernel_map) { + if (new_pfn == old_pfn) { + new_khva = old_khva; + old_pfn = KVM_PFN_ERR_FAULT; + old_khva = NULL; + } else if (pfn_valid(new_pfn)) { + new_khva = kmap(pfn_to_page(new_pfn)); +#ifdef CONFIG_HAS_IOMEM + } else { + new_khva = memremap(pfn_to_hpa(new_pfn), PAGE_SIZE, MEMREMAP_WB); +#endif + } + if (new_khva) + new_khva += page_offset; + else + ret = -EFAULT; + } + + map_done: + write_lock_irq(&gpc->lock); + if (ret) { + gpc->valid = false; + gpc->pfn = KVM_PFN_ERR_FAULT; + gpc->khva = NULL; + } else { + /* At this point, gpc->valid may already have been cleared */ + gpc->pfn = new_pfn; + gpc->khva = new_khva; + } + } else { + /* If the HVA→PFN mapping was already valid, don't unmap it. */ + old_pfn = KVM_PFN_ERR_FAULT; + old_khva = NULL; + } + + out: + if (ret) + gpc->dirty = false; + else + gpc->dirty = dirty; + + write_unlock_irq(&gpc->lock); + + __release_gpc(kvm, old_pfn, old_khva, old_gpa, old_dirty); + + return ret; +} +EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_refresh); + +void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) +{ + void *old_khva; + kvm_pfn_t old_pfn; + bool old_dirty; + gpa_t old_gpa; + + write_lock_irq(&gpc->lock); + + gpc->valid = false; + + old_khva = gpc->khva - offset_in_page(gpc->khva); + old_dirty = gpc->dirty; + old_gpa = gpc->gpa; + old_pfn = gpc->pfn; + + /* + * We can leave the GPA → uHVA map cache intact but the PFN + * lookup will need to be redone even for the same page. + */ + gpc->khva = NULL; + gpc->pfn = KVM_PFN_ERR_FAULT; + + write_unlock_irq(&gpc->lock); + + __release_gpc(kvm, old_pfn, old_khva, old_gpa, old_dirty); +} +EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap); + + +int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, bool guest_uses_pa, + bool kernel_map, gpa_t gpa, unsigned long len, + bool dirty) +{ + if (!gpc->active) { + rwlock_init(&gpc->lock); + + gpc->khva = NULL; + gpc->pfn = KVM_PFN_ERR_FAULT; + gpc->uhva = KVM_HVA_ERR_BAD; + gpc->vcpu = vcpu; + gpc->kernel_map = kernel_map; + gpc->guest_uses_pa = guest_uses_pa; + gpc->valid = false; + gpc->active = true; + + spin_lock(&kvm->gpc_lock); + list_add(&gpc->list, &kvm->gpc_list); + spin_unlock(&kvm->gpc_lock); + } + return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len, dirty); +} +EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_init); + +void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) +{ + if (gpc->active) { + spin_lock(&kvm->gpc_lock); + list_del(&gpc->list); + spin_unlock(&kvm->gpc_lock); + + kvm_gfn_to_pfn_cache_unmap(kvm, gpc); + gpc->active = false; + } +} +EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_destroy); -- cgit v1.2.3 From 14243b387137a4afbe1df5d9dc15182d6657bb79 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Fri, 10 Dec 2021 16:36:23 +0000 Subject: KVM: x86/xen: Add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery This adds basic support for delivering 2 level event channels to a guest. Initially, it only supports delivery via the IRQ routing table, triggered by an eventfd. In order to do so, it has a kvm_xen_set_evtchn_fast() function which will use the pre-mapped shared_info page if it already exists and is still valid, while the slow path through the irqfd_inject workqueue will remap the shared_info page if necessary. It sets the bits in the shared_info page but not the vcpu_info; that is deferred to __kvm_xen_has_interrupt() which raises the vector to the appropriate vCPU. Add a 'verbose' mode to xen_shinfo_test while adding test cases for this. Signed-off-by: David Woodhouse Message-Id: <20211210163625.2886-5-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 21 ++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/irq_comm.c | 12 + arch/x86/kvm/x86.c | 3 +- arch/x86/kvm/xen.c | 262 ++++++++++++++++++++- arch/x86/kvm/xen.h | 9 + include/linux/kvm_host.h | 7 + include/uapi/linux/kvm.h | 11 + .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 184 ++++++++++++++- 9 files changed, 503 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index c168be764707..6b683dfea8f2 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1799,6 +1799,7 @@ No flags are specified so far, the corresponding field must be set to zero. struct kvm_irq_routing_msi msi; struct kvm_irq_routing_s390_adapter adapter; struct kvm_irq_routing_hv_sint hv_sint; + struct kvm_irq_routing_xen_evtchn xen_evtchn; __u32 pad[8]; } u; }; @@ -1808,6 +1809,7 @@ No flags are specified so far, the corresponding field must be set to zero. #define KVM_IRQ_ROUTING_MSI 2 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 #define KVM_IRQ_ROUTING_HV_SINT 4 + #define KVM_IRQ_ROUTING_XEN_EVTCHN 5 flags: @@ -1859,6 +1861,20 @@ address_hi must be zero. __u32 sint; }; + struct kvm_irq_routing_xen_evtchn { + __u32 port; + __u32 vcpu; + __u32 priority; + }; + + +When KVM_CAP_XEN_HVM includes the KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL bit +in its indication of supported features, routing to Xen event channels +is supported. Although the priority field is present, only the value +KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL is supported, which means delivery by +2 level event channels. FIFO event channel support may be added in +the future. + 4.55 KVM_SET_TSC_KHZ -------------------- @@ -7413,6 +7429,7 @@ PVHVM guests. Valid flags are:: #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 2) + #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 3) The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG ioctl is available, for the guest to set its hypercall page. @@ -7432,6 +7449,10 @@ The KVM_XEN_HVM_CONFIG_RUNSTATE flag indicates that the runstate-related features KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR/_CURRENT/_DATA/_ADJUST are supported by the KVM_XEN_VCPU_SET_ATTR/KVM_XEN_VCPU_GET_ATTR ioctls. +The KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL flag indicates that IRQ routing entries +of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority +field set to indicate 2 level event channel delivery. + 8.31 KVM_CAP_PPC_MULTITCE ------------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6e61e11e750f..623fb7c4992c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -610,6 +610,7 @@ struct kvm_vcpu_xen { u64 last_steal; u64 runstate_entry_time; u64 runstate_times[4]; + unsigned long evtchn_pending_sel; }; struct kvm_vcpu_arch { diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 39ad02d6dc63..6e0dab04320e 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -24,6 +24,7 @@ #include "hyperv.h" #include "x86.h" +#include "xen.h" static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -175,6 +176,13 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, return r; break; +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + if (!level) + return -1; + + return kvm_xen_set_evtchn_fast(e, kvm); +#endif default: break; } @@ -310,6 +318,10 @@ int kvm_set_routing_entry(struct kvm *kvm, e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#ifdef CONFIG_KVM_XEN + case KVM_IRQ_ROUTING_XEN_EVTCHN: + return kvm_xen_setup_evtchn(kvm, e, ue); +#endif default: return -EINVAL; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 42bde45a1bc2..3050601d5d73 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4188,7 +4188,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_XEN_HVM: r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_SHARED_INFO; + KVM_XEN_HVM_CONFIG_SHARED_INFO | + KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE; break; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index da4bf2c6407f..ceddabd1f5c6 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "trace.h" @@ -195,6 +196,8 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) int __kvm_xen_has_interrupt(struct kvm_vcpu *v) { + unsigned long evtchn_pending_sel = READ_ONCE(v->arch.xen.evtchn_pending_sel); + bool atomic = in_atomic() || !task_is_running(current); int err; u8 rc = 0; @@ -204,6 +207,9 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) */ struct gfn_to_hva_cache *ghc = &v->arch.xen.vcpu_info_cache; struct kvm_memslots *slots = kvm_memslots(v->kvm); + bool ghc_valid = slots->generation == ghc->generation && + !kvm_is_error_hva(ghc->hva) && ghc->memslot; + unsigned int offset = offsetof(struct vcpu_info, evtchn_upcall_pending); /* No need for compat handling here */ @@ -219,8 +225,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) * cache in kvm_read_guest_offset_cached(), but just uses * __get_user() instead. And falls back to the slow path. */ - if (likely(slots->generation == ghc->generation && - !kvm_is_error_hva(ghc->hva) && ghc->memslot)) { + if (!evtchn_pending_sel && ghc_valid) { /* Fast path */ pagefault_disable(); err = __get_user(rc, (u8 __user *)ghc->hva + offset); @@ -239,11 +244,82 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) * and we'll end up getting called again from a context where we *can* * fault in the page and wait for it. */ - if (in_atomic() || !task_is_running(current)) + if (atomic) return 1; - kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset, - sizeof(rc)); + if (!ghc_valid) { + err = kvm_gfn_to_hva_cache_init(v->kvm, ghc, ghc->gpa, ghc->len); + if (err || !ghc->memslot) { + /* + * If this failed, userspace has screwed up the + * vcpu_info mapping. No interrupts for you. + */ + return 0; + } + } + + /* + * Now we have a valid (protected by srcu) userspace HVA in + * ghc->hva which points to the struct vcpu_info. If there + * are any bits in the in-kernel evtchn_pending_sel then + * we need to write those to the guest vcpu_info and set + * its evtchn_upcall_pending flag. If there aren't any bits + * to add, we only want to *check* evtchn_upcall_pending. + */ + if (evtchn_pending_sel) { + bool long_mode = v->kvm->arch.xen.long_mode; + + if (!user_access_begin((void __user *)ghc->hva, sizeof(struct vcpu_info))) + return 0; + + if (IS_ENABLED(CONFIG_64BIT) && long_mode) { + struct vcpu_info __user *vi = (void __user *)ghc->hva; + + /* Attempt to set the evtchn_pending_sel bits in the + * guest, and if that succeeds then clear the same + * bits in the in-kernel version. */ + asm volatile("1:\t" LOCK_PREFIX "orq %0, %1\n" + "\tnotq %0\n" + "\t" LOCK_PREFIX "andq %0, %2\n" + "2:\n" + "\t.section .fixup,\"ax\"\n" + "3:\tjmp\t2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (evtchn_pending_sel), + "+m" (vi->evtchn_pending_sel), + "+m" (v->arch.xen.evtchn_pending_sel) + : "0" (evtchn_pending_sel)); + } else { + struct compat_vcpu_info __user *vi = (void __user *)ghc->hva; + u32 evtchn_pending_sel32 = evtchn_pending_sel; + + /* Attempt to set the evtchn_pending_sel bits in the + * guest, and if that succeeds then clear the same + * bits in the in-kernel version. */ + asm volatile("1:\t" LOCK_PREFIX "orl %0, %1\n" + "\tnotl %0\n" + "\t" LOCK_PREFIX "andl %0, %2\n" + "2:\n" + "\t.section .fixup,\"ax\"\n" + "3:\tjmp\t2b\n" + "\t.previous\n" + _ASM_EXTABLE_UA(1b, 3b) + : "=r" (evtchn_pending_sel32), + "+m" (vi->evtchn_pending_sel), + "+m" (v->arch.xen.evtchn_pending_sel) + : "0" (evtchn_pending_sel32)); + } + rc = 1; + unsafe_put_user(rc, (u8 __user *)ghc->hva + offset, err); + + err: + user_access_end(); + + mark_page_dirty_in_slot(v->kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + } else { + __get_user(rc, (u8 __user *)ghc->hva + offset); + } return rc; } @@ -740,3 +816,179 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } + +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + +/* + * This follows the kvm_set_irq() API, so it returns: + * < 0 Interrupt was ignored (masked or not delivered for other reasons) + * = 0 Interrupt was coalesced (previous irq is still pending) + * > 0 Number of CPUs interrupt was delivered to + */ +int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm) +{ + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + struct kvm_vcpu *vcpu; + unsigned long *pending_bits, *mask_bits; + unsigned long flags; + int port_word_bit; + bool kick_vcpu = false; + int idx; + int rc; + + vcpu = kvm_get_vcpu_by_id(kvm, e->xen_evtchn.vcpu); + if (!vcpu) + return -1; + + if (!vcpu->arch.xen.vcpu_info_set) + return -1; + + if (e->xen_evtchn.port >= max_evtchn_port(kvm)) + return -1; + + rc = -EWOULDBLOCK; + read_lock_irqsave(&gpc->lock, flags); + + idx = srcu_read_lock(&kvm->srcu); + if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, PAGE_SIZE)) + goto out_rcu; + + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { + struct shared_info *shinfo = gpc->khva; + pending_bits = (unsigned long *)&shinfo->evtchn_pending; + mask_bits = (unsigned long *)&shinfo->evtchn_mask; + port_word_bit = e->xen_evtchn.port / 64; + } else { + struct compat_shared_info *shinfo = gpc->khva; + pending_bits = (unsigned long *)&shinfo->evtchn_pending; + mask_bits = (unsigned long *)&shinfo->evtchn_mask; + port_word_bit = e->xen_evtchn.port / 32; + } + + /* + * If this port wasn't already set, and if it isn't masked, then + * we try to set the corresponding bit in the in-kernel shadow of + * evtchn_pending_sel for the target vCPU. And if *that* wasn't + * already set, then we kick the vCPU in question to write to the + * *real* evtchn_pending_sel in its own guest vcpu_info struct. + */ + if (test_and_set_bit(e->xen_evtchn.port, pending_bits)) { + rc = 0; /* It was already raised */ + } else if (test_bit(e->xen_evtchn.port, mask_bits)) { + rc = -1; /* Masked */ + } else { + rc = 1; /* Delivered. But was the vCPU waking already? */ + if (!test_and_set_bit(port_word_bit, &vcpu->arch.xen.evtchn_pending_sel)) + kick_vcpu = true; + } + + out_rcu: + srcu_read_unlock(&kvm->srcu, idx); + read_unlock_irqrestore(&gpc->lock, flags); + + if (kick_vcpu) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); + } + + return rc; +} + +/* This is the version called from kvm_set_irq() as the .set function */ +static int evtchn_set_fn(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + bool mm_borrowed = false; + int rc; + + if (!level) + return -1; + + rc = kvm_xen_set_evtchn_fast(e, kvm); + if (rc != -EWOULDBLOCK) + return rc; + + if (current->mm != kvm->mm) { + /* + * If not on a thread which already belongs to this KVM, + * we'd better be in the irqfd workqueue. + */ + if (WARN_ON_ONCE(current->mm)) + return -EINVAL; + + kthread_use_mm(kvm->mm); + mm_borrowed = true; + } + + /* + * For the irqfd workqueue, using the main kvm->lock mutex is + * fine since this function is invoked from kvm_set_irq() with + * no other lock held, no srcu. In future if it will be called + * directly from a vCPU thread (e.g. on hypercall for an IPI) + * then it may need to switch to using a leaf-node mutex for + * serializing the shared_info mapping. + */ + mutex_lock(&kvm->lock); + + /* + * It is theoretically possible for the page to be unmapped + * and the MMU notifier to invalidate the shared_info before + * we even get to use it. In that case, this looks like an + * infinite loop. It was tempting to do it via the userspace + * HVA instead... but that just *hides* the fact that it's + * an infinite loop, because if a fault occurs and it waits + * for the page to come back, it can *still* immediately + * fault and have to wait again, repeatedly. + * + * Conversely, the page could also have been reinstated by + * another thread before we even obtain the mutex above, so + * check again *first* before remapping it. + */ + do { + struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; + int idx; + + rc = kvm_xen_set_evtchn_fast(e, kvm); + if (rc != -EWOULDBLOCK) + break; + + idx = srcu_read_lock(&kvm->srcu); + rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, + PAGE_SIZE, false); + srcu_read_unlock(&kvm->srcu, idx); + } while(!rc); + + mutex_unlock(&kvm->lock); + + if (mm_borrowed) + kthread_unuse_mm(kvm->mm); + + return rc; +} + +int kvm_xen_setup_evtchn(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) + +{ + if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm)) + return -EINVAL; + + /* We only support 2 level event channels for now */ + if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL) + return -EINVAL; + + e->xen_evtchn.port = ue->u.xen_evtchn.port; + e->xen_evtchn.vcpu = ue->u.xen_evtchn.vcpu; + e->xen_evtchn.priority = ue->u.xen_evtchn.priority; + e->set = evtchn_set_fn; + + return 0; +} diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index cc0cf5f37450..adbcc9ed59db 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -24,6 +24,12 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc); void kvm_xen_init_vm(struct kvm *kvm); void kvm_xen_destroy_vm(struct kvm *kvm); +int kvm_xen_set_evtchn_fast(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm); +int kvm_xen_setup_evtchn(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue); + static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { return static_branch_unlikely(&kvm_xen_enabled.key) && @@ -134,6 +140,9 @@ struct compat_shared_info { struct compat_arch_shared_info arch; }; +#define COMPAT_EVTCHN_2L_NR_CHANNELS (8 * \ + sizeof_field(struct compat_shared_info, \ + evtchn_pending)) struct compat_vcpu_runstate_info { int state; uint64_t state_entry_time; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9bbb1f1d9e48..3c47b146851a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -497,6 +497,12 @@ struct kvm_hv_sint { u32 sint; }; +struct kvm_xen_evtchn { + u32 port; + u32 vcpu; + u32 priority; +}; + struct kvm_kernel_irq_routing_entry { u32 gsi; u32 type; @@ -517,6 +523,7 @@ struct kvm_kernel_irq_routing_entry { } msi; struct kvm_s390_adapter_int adapter; struct kvm_hv_sint hv_sint; + struct kvm_xen_evtchn xen_evtchn; }; struct hlist_node link; }; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 469f05d69c8d..fbfd70d965c6 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1163,11 +1163,20 @@ struct kvm_irq_routing_hv_sint { __u32 sint; }; +struct kvm_irq_routing_xen_evtchn { + __u32 port; + __u32 vcpu; + __u32 priority; +}; + +#define KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL ((__u32)(-1)) + /* gsi routing entry types */ #define KVM_IRQ_ROUTING_IRQCHIP 1 #define KVM_IRQ_ROUTING_MSI 2 #define KVM_IRQ_ROUTING_S390_ADAPTER 3 #define KVM_IRQ_ROUTING_HV_SINT 4 +#define KVM_IRQ_ROUTING_XEN_EVTCHN 5 struct kvm_irq_routing_entry { __u32 gsi; @@ -1179,6 +1188,7 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing_msi msi; struct kvm_irq_routing_s390_adapter adapter; struct kvm_irq_routing_hv_sint hv_sint; + struct kvm_irq_routing_xen_evtchn xen_evtchn; __u32 pad[8]; } u; }; @@ -1209,6 +1219,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) struct kvm_xen_hvm_config { __u32 flags; diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index a0699f00b3d6..478e0ae8b93e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -14,6 +14,9 @@ #include #include #include +#include + +#include #define VCPU_ID 5 @@ -22,10 +25,15 @@ #define SHINFO_REGION_SLOT 10 #define PAGE_SIZE 4096 +#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE)) +#define DUMMY_REGION_SLOT 11 + +#define SHINFO_ADDR (SHINFO_REGION_GPA) #define PVTIME_ADDR (SHINFO_REGION_GPA + PAGE_SIZE) #define RUNSTATE_ADDR (SHINFO_REGION_GPA + PAGE_SIZE + 0x20) #define VCPU_INFO_ADDR (SHINFO_REGION_GPA + 0x40) +#define SHINFO_VADDR (SHINFO_REGION_GVA) #define RUNSTATE_VADDR (SHINFO_REGION_GVA + PAGE_SIZE + 0x20) #define VCPU_INFO_VADDR (SHINFO_REGION_GVA + 0x40) @@ -73,15 +81,37 @@ struct vcpu_info { struct pvclock_vcpu_time_info time; }; /* 64 bytes (x86) */ +struct shared_info { + struct vcpu_info vcpu_info[32]; + unsigned long evtchn_pending[64]; + unsigned long evtchn_mask[64]; + struct pvclock_wall_clock wc; + uint32_t wc_sec_hi; + /* arch_shared_info here */ +}; + #define RUNSTATE_running 0 #define RUNSTATE_runnable 1 #define RUNSTATE_blocked 2 #define RUNSTATE_offline 3 +static const char *runstate_names[] = { + "running", + "runnable", + "blocked", + "offline" +}; + +struct { + struct kvm_irq_routing info; + struct kvm_irq_routing_entry entries[2]; +} irq_routes; + static void evtchn_handler(struct ex_regs *regs) { struct vcpu_info *vi = (void *)VCPU_INFO_VADDR; vi->evtchn_upcall_pending = 0; + vi->evtchn_pending_sel = 0; GUEST_SYNC(0x20); } @@ -127,7 +157,25 @@ static void guest_code(void) GUEST_SYNC(6); GUEST_ASSERT(rs->time[RUNSTATE_runnable] >= MIN_STEAL_TIME); - GUEST_DONE(); + /* Attempt to deliver a *masked* interrupt */ + GUEST_SYNC(7); + + /* Wait until we see the bit set */ + struct shared_info *si = (void *)SHINFO_VADDR; + while (!si->evtchn_pending[0]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Now deliver an *unmasked* interrupt */ + GUEST_SYNC(8); + + while (!si->evtchn_pending[1]) + __asm__ __volatile__ ("rep nop" : : : "memory"); + + /* Change memslots and deliver an interrupt */ + GUEST_SYNC(9); + + for (;;) + __asm__ __volatile__ ("rep nop" : : : "memory"); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -144,9 +192,18 @@ static int cmp_timespec(struct timespec *a, struct timespec *b) return 0; } +static void handle_alrm(int sig) +{ + TEST_FAIL("IRQ delivery timed out"); +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + bool verbose; + + verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || + !strncmp(argv[1], "--verbose", 10)); int xen_caps = kvm_check_cap(KVM_CAP_XEN_HVM); if (!(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO) ) { @@ -155,6 +212,7 @@ int main(int argc, char *argv[]) } bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); clock_gettime(CLOCK_REALTIME, &min_ts); @@ -166,6 +224,11 @@ int main(int argc, char *argv[]) SHINFO_REGION_GPA, SHINFO_REGION_SLOT, 2, 0); virt_map(vm, SHINFO_REGION_GVA, SHINFO_REGION_GPA, 2); + struct shared_info *shinfo = addr_gpa2hva(vm, SHINFO_VADDR); + + int zero_fd = open("/dev/zero", O_RDONLY); + TEST_ASSERT(zero_fd != -1, "Failed to open /dev/zero"); + struct kvm_xen_hvm_config hvmc = { .flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL, .msr = XEN_HYPERCALL_MSR, @@ -184,6 +247,16 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ha); + /* + * Test what happens when the HVA of the shinfo page is remapped after + * the kernel has a reference to it. But make sure we copy the clock + * info over since that's only set at setup time, and we test it later. + */ + struct pvclock_wall_clock wc_copy = shinfo->wc; + void *m = mmap(shinfo, PAGE_SIZE, PROT_READ|PROT_WRITE, MAP_FIXED|MAP_PRIVATE, zero_fd, 0); + TEST_ASSERT(m == shinfo, "Failed to map /dev/zero over shared info"); + shinfo->wc = wc_copy; + struct kvm_xen_vcpu_attr vi = { .type = KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO, .u.gpa = VCPU_INFO_ADDR, @@ -214,6 +287,49 @@ int main(int argc, char *argv[]) vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &st); } + int irq_fd[2] = { -1, -1 }; + + if (do_eventfd_tests) { + irq_fd[0] = eventfd(0, 0); + irq_fd[1] = eventfd(0, 0); + + /* Unexpected, but not a KVM failure */ + if (irq_fd[0] == -1 || irq_fd[1] == -1) + do_eventfd_tests = false; + } + + if (do_eventfd_tests) { + irq_routes.info.nr = 2; + + irq_routes.entries[0].gsi = 32; + irq_routes.entries[0].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[0].u.xen_evtchn.port = 15; + irq_routes.entries[0].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[0].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + irq_routes.entries[1].gsi = 33; + irq_routes.entries[1].type = KVM_IRQ_ROUTING_XEN_EVTCHN; + irq_routes.entries[1].u.xen_evtchn.port = 66; + irq_routes.entries[1].u.xen_evtchn.vcpu = VCPU_ID; + irq_routes.entries[1].u.xen_evtchn.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + vm_ioctl(vm, KVM_SET_GSI_ROUTING, &irq_routes); + + struct kvm_irqfd ifd = { }; + + ifd.fd = irq_fd[0]; + ifd.gsi = 32; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + ifd.fd = irq_fd[1]; + ifd.gsi = 33; + vm_ioctl(vm, KVM_IRQFD, &ifd); + + struct sigaction sa = { }; + sa.sa_handler = handle_alrm; + sigaction(SIGALRM, &sa, NULL); + } + struct vcpu_info *vinfo = addr_gpa2hva(vm, VCPU_INFO_VADDR); vinfo->evtchn_upcall_pending = 0; @@ -248,6 +364,8 @@ int main(int argc, char *argv[]) switch (uc.args[1]) { case 0: + if (verbose) + printf("Delivering evtchn upcall\n"); evtchn_irq_expected = true; vinfo->evtchn_upcall_pending = 1; break; @@ -256,11 +374,16 @@ int main(int argc, char *argv[]) TEST_ASSERT(!evtchn_irq_expected, "Event channel IRQ not seen"); if (!do_runstate_tests) goto done; + if (verbose) + printf("Testing runstate %s\n", runstate_names[uc.args[1]]); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT; rst.u.runstate.state = uc.args[1]; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 4: + if (verbose) + printf("Testing RUNSTATE_ADJUST\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = (uint64_t)-1; @@ -274,6 +397,8 @@ int main(int argc, char *argv[]) break; case 5: + if (verbose) + printf("Testing RUNSTATE_DATA\n"); rst.type = KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA; memset(&rst.u, 0, sizeof(rst.u)); rst.u.runstate.state = RUNSTATE_running; @@ -282,16 +407,54 @@ int main(int argc, char *argv[]) rst.u.runstate.time_offline = 0x5a; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_SET_ATTR, &rst); break; + case 6: + if (verbose) + printf("Testing steal time\n"); /* Yield until scheduler delay exceeds target */ rundelay = get_run_delay() + MIN_STEAL_TIME; do { sched_yield(); } while (get_run_delay() < rundelay); break; + + case 7: + if (!do_eventfd_tests) + goto done; + if (verbose) + printf("Testing masked event channel\n"); + shinfo->evtchn_mask[0] = 0x8000; + eventfd_write(irq_fd[0], 1UL); + alarm(1); + break; + + case 8: + if (verbose) + printf("Testing unmasked event channel\n"); + /* Unmask that, but deliver the other one */ + shinfo->evtchn_pending[0] = 0; + shinfo->evtchn_mask[0] = 0; + eventfd_write(irq_fd[1], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + + case 9: + if (verbose) + printf("Testing event channel after memslot change\n"); + vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, + DUMMY_REGION_GPA, DUMMY_REGION_SLOT, 1, 0); + eventfd_write(irq_fd[0], 1UL); + evtchn_irq_expected = true; + alarm(1); + break; + case 0x20: TEST_ASSERT(evtchn_irq_expected, "Unexpected event channel IRQ"); evtchn_irq_expected = false; + if (shinfo->evtchn_pending[1] && + shinfo->evtchn_pending[0]) + goto done; break; } break; @@ -318,6 +481,16 @@ int main(int argc, char *argv[]) ti = addr_gpa2hva(vm, SHINFO_REGION_GPA + 0x40 + 0x20); ti2 = addr_gpa2hva(vm, PVTIME_ADDR); + if (verbose) { + printf("Wall clock (v %d) %d.%09d\n", wc->version, wc->sec, wc->nsec); + printf("Time info 1: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti->version, ti->tsc_timestamp, ti->system_time, ti->tsc_to_system_mul, + ti->tsc_shift, ti->flags); + printf("Time info 2: v %u tsc %" PRIu64 " time %" PRIu64 " mul %u shift %u flags %x\n", + ti2->version, ti2->tsc_timestamp, ti2->system_time, ti2->tsc_to_system_mul, + ti2->tsc_shift, ti2->flags); + } + vm_ts.tv_sec = wc->sec; vm_ts.tv_nsec = wc->nsec; TEST_ASSERT(wc->version && !(wc->version & 1), @@ -341,6 +514,15 @@ int main(int argc, char *argv[]) }; vcpu_ioctl(vm, VCPU_ID, KVM_XEN_VCPU_GET_ATTR, &rst); + if (verbose) { + printf("Runstate: %s(%d), entry %" PRIu64 " ns\n", + rs->state <= RUNSTATE_offline ? runstate_names[rs->state] : "unknown", + rs->state, rs->state_entry_time); + for (int i = RUNSTATE_running; i <= RUNSTATE_offline; i++) { + printf("State %s: %" PRIu64 " ns\n", + runstate_names[i], rs->time[i]); + } + } TEST_ASSERT(rs->state == rst.u.runstate.state, "Runstate mismatch"); TEST_ASSERT(rs->state_entry_time == rst.u.runstate.state_entry_time, "State entry time mismatch"); -- cgit v1.2.3 From 44ea62813f0ab3d718de480504f4dfd0bdd01858 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 3 Sep 2021 18:31:40 -0700 Subject: spi: don't include ptp_clock_kernel.h in spi.h Commit b42faeee718c ("spi: Add a PTP system timestamp to the transfer structure") added an include of ptp_clock_kernel.h to spi.h for struct ptp_system_timestamp but a forward declaration is enough. Let's use that to limit the number of objects we have to rebuild every time we touch networking headers. Signed-off-by: Jakub Kicinski Tested-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210904013140.2377609-1-kuba@kernel.org Signed-off-by: Mark Brown --- drivers/spi/spi.c | 1 + include/linux/spi/spi.h | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 7c790858547c..4599b121d744 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -33,6 +33,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index eb7ac8a1e03c..7ab3fed7b804 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -14,12 +14,12 @@ #include #include #include -#include #include struct dma_chan; struct software_node; +struct ptp_system_timestamp; struct spi_controller; struct spi_transfer; struct spi_controller_mem_ops; -- cgit v1.2.3 From 3506659e18a61ae525f3b9b4f5af23b4b149d4db Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sun, 28 Nov 2021 14:53:35 -0500 Subject: mm: Add unmap_mapping_folio() Convert both callers of unmap_mapping_page() to call unmap_mapping_folio() instead. Also move zap_details from linux/mm.h to mm/memory.c Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski --- include/linux/mm.h | 24 ------------------------ mm/internal.h | 4 +++- mm/memory.c | 49 +++++++++++++++++++++++++++++++++++-------------- mm/truncate.c | 4 ++-- 4 files changed, 40 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 145f045b0ddc..c9cdb26802fb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1825,28 +1825,6 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); -/* - * Parameter block passed down to zap_pte_range in exceptional cases. - */ -struct zap_details { - struct address_space *zap_mapping; /* Check page->mapping if set */ - struct page *single_page; /* Locked page to be unmapped */ -}; - -/* - * We set details->zap_mappings when we want to unmap shared but keep private - * pages. Return true if skip zapping this page, false otherwise. - */ -static inline bool -zap_skip_check_mapping(struct zap_details *details, struct page *page) -{ - if (!details || !page) - return false; - - return details->zap_mapping && - (details->zap_mapping != page_rmapping(page)); -} - struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1892,7 +1870,6 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma, extern int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked); -void unmap_mapping_page(struct page *page); void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows); void unmap_mapping_range(struct address_space *mapping, @@ -1913,7 +1890,6 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address, BUG(); return -EFAULT; } -static inline void unmap_mapping_page(struct page *page) { } static inline void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t nr, bool even_cows) { } static inline void unmap_mapping_range(struct address_space *mapping, diff --git a/mm/internal.h b/mm/internal.h index 3b79a5c9427a..1ca93c6cb18c 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -74,6 +74,7 @@ static inline bool can_madv_lru_vma(struct vm_area_struct *vma) return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)); } +struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, @@ -388,6 +389,7 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma); #ifdef CONFIG_MMU +void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_vma_page_range(struct vm_area_struct *vma, @@ -491,8 +493,8 @@ static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf, } return fpin; } - #else /* !CONFIG_MMU */ +static inline void unmap_mapping_folio(struct folio *folio) { } static inline void clear_page_mlock(struct page *page) { } static inline void mlock_vma_page(struct page *page) { } static inline void vunmap_range_noflush(unsigned long start, unsigned long end) diff --git a/mm/memory.c b/mm/memory.c index 8f1de811a1dc..23f2f1300d42 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1304,6 +1304,28 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) return ret; } +/* + * Parameter block passed down to zap_pte_range in exceptional cases. + */ +struct zap_details { + struct address_space *zap_mapping; /* Check page->mapping if set */ + struct folio *single_folio; /* Locked folio to be unmapped */ +}; + +/* + * We set details->zap_mapping when we want to unmap shared but keep private + * pages. Return true if skip zapping this page, false otherwise. + */ +static inline bool +zap_skip_check_mapping(struct zap_details *details, struct page *page) +{ + if (!details || !page) + return false; + + return details->zap_mapping && + (details->zap_mapping != page_rmapping(page)); +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1443,8 +1465,8 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, else if (zap_huge_pmd(tlb, vma, pmd, addr)) goto next; /* fall through */ - } else if (details && details->single_page && - PageTransCompound(details->single_page) && + } else if (details && details->single_folio && + folio_test_pmd_mappable(details->single_folio) && next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) { spinlock_t *ptl = pmd_lock(tlb->mm, pmd); /* @@ -3332,31 +3354,30 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root, } /** - * unmap_mapping_page() - Unmap single page from processes. - * @page: The locked page to be unmapped. + * unmap_mapping_folio() - Unmap single folio from processes. + * @folio: The locked folio to be unmapped. * - * Unmap this page from any userspace process which still has it mmaped. + * Unmap this folio from any userspace process which still has it mmaped. * Typically, for efficiency, the range of nearby pages has already been * unmapped by unmap_mapping_pages() or unmap_mapping_range(). But once - * truncation or invalidation holds the lock on a page, it may find that - * the page has been remapped again: and then uses unmap_mapping_page() + * truncation or invalidation holds the lock on a folio, it may find that + * the page has been remapped again: and then uses unmap_mapping_folio() * to unmap it finally. */ -void unmap_mapping_page(struct page *page) +void unmap_mapping_folio(struct folio *folio) { - struct address_space *mapping = page->mapping; + struct address_space *mapping = folio->mapping; struct zap_details details = { }; pgoff_t first_index; pgoff_t last_index; - VM_BUG_ON(!PageLocked(page)); - VM_BUG_ON(PageTail(page)); + VM_BUG_ON(!folio_test_locked(folio)); - first_index = page->index; - last_index = page->index + thp_nr_pages(page) - 1; + first_index = folio->index; + last_index = folio->index + folio_nr_pages(folio) - 1; details.zap_mapping = mapping; - details.single_page = page; + details.single_folio = folio; i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))) diff --git a/mm/truncate.c b/mm/truncate.c index ab86b07c1e9c..c98feea75a10 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -180,7 +180,7 @@ void do_invalidatepage(struct page *page, unsigned int offset, static void truncate_cleanup_folio(struct folio *folio) { if (folio_mapped(folio)) - unmap_mapping_page(&folio->page); + unmap_mapping_folio(folio); if (folio_has_private(folio)) do_invalidatepage(&folio->page, 0, folio_size(folio)); @@ -670,7 +670,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, wait_on_page_writeback(page); if (page_mapped(page)) - unmap_mapping_page(page); + unmap_mapping_folio(page_folio(page)); BUG_ON(page_mapped(page)); ret2 = do_launder_page(mapping, page); -- cgit v1.2.3 From 1e84a3d997b74c33491899e31d48774f252213ab Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 2 Dec 2021 16:01:55 -0500 Subject: truncate,shmem: Add truncate_inode_folio() Convert all callers of truncate_inode_page() to call truncate_inode_folio() instead, and move the declaration to mm/internal.h. Move the assertion that the caller is not passing in a tail page to generic_error_remove_page(). We can't entirely remove the struct page from the callers yet because the page pointer in the pvec might be a shadow/dax/swap entry instead of actually a page. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/mm.h | 1 - mm/internal.h | 1 + mm/shmem.c | 5 +++-- mm/truncate.c | 23 ++++++++++++----------- 4 files changed, 16 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c9cdb26802fb..d8b7d7ed14dd 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1859,7 +1859,6 @@ extern void truncate_pagecache(struct inode *inode, loff_t new); extern void truncate_setsize(struct inode *inode, loff_t newsize); void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to); void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end); -int truncate_inode_page(struct address_space *mapping, struct page *page); int generic_error_remove_page(struct address_space *mapping, struct page *page); int invalidate_inode_page(struct page *page); diff --git a/mm/internal.h b/mm/internal.h index 1ca93c6cb18c..f9967b0be8bf 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -92,6 +92,7 @@ static inline void force_page_cache_readahead(struct address_space *mapping, unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, pgoff_t end, struct pagevec *pvec, pgoff_t *indices); +int truncate_inode_folio(struct address_space *mapping, struct folio *folio); /** * folio_evictable - Test whether a folio is evictable. diff --git a/mm/shmem.c b/mm/shmem.c index 40da9075374b..dbef008fb6e5 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -950,7 +950,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index += folio_nr_pages(folio) - 1; if (!unfalloc || !folio_test_uptodate(folio)) - truncate_inode_page(mapping, &folio->page); + truncate_inode_folio(mapping, folio); folio_unlock(folio); } pagevec_remove_exceptionals(&pvec); @@ -1027,7 +1027,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, } VM_BUG_ON_PAGE(PageWriteback(page), page); if (shmem_punch_compound(page, start, end)) - truncate_inode_page(mapping, page); + truncate_inode_folio(mapping, + page_folio(page)); else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Wipe the page and don't get stuck */ clear_highpage(page); diff --git a/mm/truncate.c b/mm/truncate.c index c98feea75a10..0000424fc56b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -218,12 +218,9 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) return ret; } -int truncate_inode_page(struct address_space *mapping, struct page *page) +int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { - struct folio *folio = page_folio(page); - VM_BUG_ON_PAGE(PageTail(page), page); - - if (page->mapping != mapping) + if (folio->mapping != mapping) return -EIO; truncate_cleanup_folio(folio); @@ -236,6 +233,8 @@ int truncate_inode_page(struct address_space *mapping, struct page *page) */ int generic_error_remove_page(struct address_space *mapping, struct page *page) { + VM_BUG_ON_PAGE(PageTail(page), page); + if (!mapping) return -EINVAL; /* @@ -244,7 +243,7 @@ int generic_error_remove_page(struct address_space *mapping, struct page *page) */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; - return truncate_inode_page(mapping, page); + return truncate_inode_folio(mapping, page_folio(page)); } EXPORT_SYMBOL(generic_error_remove_page); @@ -395,18 +394,20 @@ void truncate_inode_pages_range(struct address_space *mapping, for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; + struct folio *folio; /* We rely upon deletion not changing page->index */ index = indices[i]; if (xa_is_value(page)) continue; + folio = page_folio(page); - lock_page(page); - WARN_ON(page_to_index(page) != index); - wait_on_page_writeback(page); - truncate_inode_page(mapping, page); - unlock_page(page); + folio_lock(folio); + VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); + folio_wait_writeback(folio); + truncate_inode_folio(mapping, folio); + folio_unlock(folio); } truncate_exceptional_pvec_entries(mapping, &pvec, indices); pagevec_release(&pvec); -- cgit v1.2.3 From 0e499ed3d7a216706e02eeded562627d3e69dcfd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 1 Sep 2020 23:17:50 -0400 Subject: filemap: Return only folios from find_get_entries() The callers have all been converted to work on folios, so convert find_get_entries() to return a batch of folios instead of pages. We also now return multiple large folios in a single call. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Jan Kara Reviewed-by: William Kucharski Reviewed-by: Christoph Hellwig --- include/linux/pagemap.h | 2 -- mm/filemap.c | 43 +++++++++++-------------------------------- mm/internal.h | 4 ++++ mm/shmem.c | 36 ++++++++++++++++++++---------------- mm/truncate.c | 43 ++++++++++++++++++++++++------------------- 5 files changed, 59 insertions(+), 69 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index eb6e58e106c8..d2259a1da51c 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -592,8 +592,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index) return head + (index & (thp_nr_pages(head) - 1)); } -unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices); unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages); diff --git a/mm/filemap.c b/mm/filemap.c index aefa6082b81b..021214fd5354 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2015,57 +2015,36 @@ reset: * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). - * @pvec: Where the resulting entries are placed. + * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in - * the mapping. The entries are placed in @pvec. find_get_entries() - * takes a reference on any actual pages it returns. + * the mapping. The entries are placed in @fbatch. find_get_entries() + * takes a reference on any actual folios it returns. * - * The search returns a group of mapping-contiguous page cache entries - * with ascending indexes. There may be holes in the indices due to - * not-present pages. + * The entries have ascending indexes. The indices may not be consecutive + * due to not-present entries or large folios. * - * Any shadow entries of evicted pages, or swap entries from + * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * - * If it finds a Transparent Huge Page, head or tail, find_get_entries() - * stops at that page: the caller is likely to have a better way to handle - * the compound page as a whole, and then skip its extent, than repeatedly - * calling find_get_entries() to return all its tails. - * - * Return: the number of pages and shadow entries which were found. + * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices) + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; - unsigned int ret = 0; - unsigned nr_entries = PAGEVEC_SIZE; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { - struct page *page = &folio->page; - /* - * Terminate early on finding a THP, to allow the caller to - * handle it all at once; but continue if this is hugetlbfs. - */ - if (!xa_is_value(folio) && folio_test_large(folio) && - !folio_test_hugetlb(folio)) { - page = folio_file_page(folio, xas.xa_index); - nr_entries = ret + 1; - } - - indices[ret] = xas.xa_index; - pvec->pages[ret] = page; - if (++ret == nr_entries) + indices[fbatch->nr] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) break; } rcu_read_unlock(); - pvec->nr = ret; - return ret; + return folio_batch_count(fbatch); } /** diff --git a/mm/internal.h b/mm/internal.h index e5f3ff3ae24e..07124e95e790 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -12,6 +12,8 @@ #include #include +struct folio_batch; + /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints @@ -92,6 +94,8 @@ static inline void force_page_cache_readahead(struct address_space *mapping, unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, pgoff_t end, struct pagevec *pvec, pgoff_t *indices); +unsigned find_get_entries(struct address_space *mapping, pgoff_t start, + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); diff --git a/mm/shmem.c b/mm/shmem.c index dbef008fb6e5..e909c163fb38 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -920,6 +920,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, unsigned int partial_start = lstart & (PAGE_SIZE - 1); unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); struct pagevec pvec; + struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; pgoff_t index; @@ -987,11 +988,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (start >= end) return; + folio_batch_init(&fbatch); index = start; while (index < end) { cond_resched(); - if (!find_get_entries(mapping, index, end - 1, &pvec, + if (!find_get_entries(mapping, index, end - 1, &fbatch, indices)) { /* If all gone or hole-punch or unfalloc, we're done */ if (index == start || end != -1) @@ -1000,14 +1002,14 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, index = start; continue; } - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; index = indices[i]; - if (xa_is_value(page)) { + if (xa_is_value(folio)) { if (unfalloc) continue; - if (shmem_free_swap(mapping, index, page)) { + if (shmem_free_swap(mapping, index, folio)) { /* Swap was replaced by page: retry */ index--; break; @@ -1016,33 +1018,35 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, continue; } - lock_page(page); + folio_lock(folio); - if (!unfalloc || !PageUptodate(page)) { - if (page_mapping(page) != mapping) { + if (!unfalloc || !folio_test_uptodate(folio)) { + struct page *page = folio_file_page(folio, + index); + if (folio_mapping(folio) != mapping) { /* Page was replaced by swap: retry */ - unlock_page(page); + folio_unlock(folio); index--; break; } - VM_BUG_ON_PAGE(PageWriteback(page), page); + VM_BUG_ON_FOLIO(folio_test_writeback(folio), + folio); if (shmem_punch_compound(page, start, end)) - truncate_inode_folio(mapping, - page_folio(page)); + truncate_inode_folio(mapping, folio); else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { /* Wipe the page and don't get stuck */ clear_highpage(page); flush_dcache_page(page); - set_page_dirty(page); + folio_mark_dirty(folio); if (index < round_up(start, HPAGE_PMD_NR)) start = index + 1; } } - unlock_page(page); + folio_unlock(folio); } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); index++; } diff --git a/mm/truncate.c b/mm/truncate.c index 5370094641d6..357af144df63 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -108,6 +108,13 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, pvec->nr = j; } +static void truncate_folio_batch_exceptionals(struct address_space *mapping, + struct folio_batch *fbatch, pgoff_t *indices) +{ + truncate_exceptional_pvec_entries(mapping, (struct pagevec *)fbatch, + indices); +} + /* * Invalidate exceptional entry if easily possible. This handles exceptional * entries for invalidate_inode_pages(). @@ -297,6 +304,7 @@ void truncate_inode_pages_range(struct address_space *mapping, unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; + struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; @@ -379,10 +387,11 @@ void truncate_inode_pages_range(struct address_space *mapping, if (start >= end) goto out; + folio_batch_init(&fbatch); index = start; for ( ; ; ) { cond_resched(); - if (!find_get_entries(mapping, index, end - 1, &pvec, + if (!find_get_entries(mapping, index, end - 1, &fbatch, indices)) { /* If all gone from start onwards, we're done */ if (index == start) @@ -392,16 +401,14 @@ void truncate_inode_pages_range(struct address_space *mapping, continue; } - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - struct folio *folio; + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; - if (xa_is_value(page)) + if (xa_is_value(folio)) continue; - folio = page_folio(page); folio_lock(folio); VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); @@ -410,8 +417,8 @@ void truncate_inode_pages_range(struct address_space *mapping, folio_unlock(folio); index = folio_index(folio) + folio_nr_pages(folio) - 1; } - truncate_exceptional_pvec_entries(mapping, &pvec, indices); - pagevec_release(&pvec); + truncate_folio_batch_exceptionals(mapping, &fbatch, indices); + folio_batch_release(&fbatch); index++; } @@ -625,7 +632,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t index; int i; int ret = 0; @@ -635,23 +642,21 @@ int invalidate_inode_pages2_range(struct address_space *mapping, if (mapping_empty(mapping)) goto out; - pagevec_init(&pvec); + folio_batch_init(&fbatch); index = start; - while (find_get_entries(mapping, index, end, &pvec, indices)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; - struct folio *folio; + while (find_get_entries(mapping, index, end, &fbatch, indices)) { + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; /* We rely upon deletion not changing folio->index */ index = indices[i]; - if (xa_is_value(page)) { + if (xa_is_value(folio)) { if (!invalidate_exceptional_entry2(mapping, - index, page)) + index, folio)) ret = -EBUSY; continue; } - folio = page_folio(page); if (!did_range_unmap && folio_mapped(folio)) { /* @@ -684,8 +689,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping, ret = ret2; folio_unlock(folio); } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); cond_resched(); index++; } -- cgit v1.2.3 From 51dcbdac28d4dde915f78adf08bb3fac87f516e9 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 7 Dec 2021 14:15:07 -0500 Subject: mm: Convert find_lock_entries() to use a folio_batch find_lock_entries() already only returned the head page of folios, so convert it to return a folio_batch instead of a pagevec. That cascades through converting truncate_inode_pages_range() to delete_from_page_cache_batch() and page_cache_delete_batch(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- fs/f2fs/f2fs.h | 2 ++ include/linux/pagemap.h | 4 +-- mm/filemap.c | 60 +++++++++++++++++++++---------------------- mm/internal.h | 2 +- mm/shmem.c | 14 +++++------ mm/truncate.c | 67 +++++++++++++++++++++---------------------------- 6 files changed, 69 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index ce9fc9f13000..d0d603187171 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -28,6 +28,8 @@ #include #include +struct pagevec; + #ifdef CONFIG_F2FS_CHECK_FS #define f2fs_bug_on(sbi, condition) BUG_ON(condition) #else diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index d2259a1da51c..6e038811f4c8 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -16,7 +16,7 @@ #include /* for in_interrupt() */ #include -struct pagevec; +struct folio_batch; static inline bool mapping_empty(struct address_space *mapping) { @@ -936,7 +936,7 @@ static inline void __delete_from_page_cache(struct page *page, void *shadow) } void replace_page_cache_page(struct page *old, struct page *new); void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec); + struct folio_batch *fbatch); int try_to_release_page(struct page *page, gfp_t gfp); bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, diff --git a/mm/filemap.c b/mm/filemap.c index 021214fd5354..9d3bae3e36c3 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -270,30 +270,29 @@ void filemap_remove_folio(struct folio *folio) } /* - * page_cache_delete_batch - delete several pages from page cache - * @mapping: the mapping to which pages belong - * @pvec: pagevec with pages to delete + * page_cache_delete_batch - delete several folios from page cache + * @mapping: the mapping to which folios belong + * @fbatch: batch of folios to delete * - * The function walks over mapping->i_pages and removes pages passed in @pvec - * from the mapping. The function expects @pvec to be sorted by page index - * and is optimised for it to be dense. - * It tolerates holes in @pvec (mapping entries at those indices are not - * modified). The function expects only THP head pages to be present in the - * @pvec. + * The function walks over mapping->i_pages and removes folios passed in + * @fbatch from the mapping. The function expects @fbatch to be sorted + * by page index and is optimised for it to be dense. + * It tolerates holes in @fbatch (mapping entries at those indices are not + * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, - struct pagevec *pvec) + struct folio_batch *fbatch) { - XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); + XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); int total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { - if (i >= pagevec_count(pvec)) + if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ @@ -306,9 +305,9 @@ static void page_cache_delete_batch(struct address_space *mapping, * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ - if (&folio->page != pvec->pages[i]) { + if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > - pvec->pages[i]->index, folio); + fbatch->folios[i]->index, folio); continue; } @@ -316,12 +315,11 @@ static void page_cache_delete_batch(struct address_space *mapping, if (folio->index == xas.xa_index) folio->mapping = NULL; - /* Leave page->index set: truncation lookup relies on it */ + /* Leave folio->index set: truncation lookup relies on it */ /* - * Move to the next page in the vector if this is a regular - * page or the index is of the last sub-page of this compound - * page. + * Move to the next folio in the batch if this is a regular + * folio or the index is of the last sub-page of this folio. */ if (folio->index + folio_nr_pages(folio) - 1 == xas.xa_index) i++; @@ -332,29 +330,29 @@ static void page_cache_delete_batch(struct address_space *mapping, } void delete_from_page_cache_batch(struct address_space *mapping, - struct pagevec *pvec) + struct folio_batch *fbatch) { int i; - if (!pagevec_count(pvec)) + if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); - for (i = 0; i < pagevec_count(pvec); i++) { - struct folio *folio = page_folio(pvec->pages[i]); + for (i = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } - page_cache_delete_batch(mapping, pvec); + page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); - for (i = 0; i < pagevec_count(pvec); i++) - filemap_free_folio(mapping, page_folio(pvec->pages[i])); + for (i = 0; i < folio_batch_count(fbatch); i++) + filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) @@ -2052,8 +2050,8 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). - * @pvec: Where the resulting entries are placed. - * @indices: The cache indices of the entries in @pvec. + * @fbatch: Where the resulting entries are placed. + * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned @@ -2068,7 +2066,7 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices) + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, start); struct folio *folio; @@ -2088,8 +2086,8 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } - indices[pvec->nr] = xas.xa_index; - if (!pagevec_add(pvec, &folio->page)) + indices[fbatch->nr] = xas.xa_index; + if (!folio_batch_add(fbatch, folio)) break; goto next; unlock: @@ -2106,7 +2104,7 @@ next: } rcu_read_unlock(); - return pagevec_count(pvec); + return folio_batch_count(fbatch); } /** diff --git a/mm/internal.h b/mm/internal.h index 07124e95e790..c52c05dc6b1f 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -93,7 +93,7 @@ static inline void force_page_cache_readahead(struct address_space *mapping, } unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, - pgoff_t end, struct pagevec *pvec, pgoff_t *indices); + pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); diff --git a/mm/shmem.c b/mm/shmem.c index e909c163fb38..bbfa2d05e787 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -919,7 +919,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, pgoff_t end = (lend + 1) >> PAGE_SHIFT; unsigned int partial_start = lstart & (PAGE_SIZE - 1); unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1); - struct pagevec pvec; struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; long nr_swaps_freed = 0; @@ -932,12 +931,12 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (info->fallocend > start && info->fallocend <= end && !unfalloc) info->fallocend = start; - pagevec_init(&pvec); + folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, - &pvec, indices)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct folio *folio = (struct folio *)pvec.pages[i]; + &fbatch, indices)) { + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct folio *folio = fbatch.folios[i]; index = indices[i]; @@ -954,8 +953,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, truncate_inode_folio(mapping, folio); folio_unlock(folio); } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); cond_resched(); index++; } @@ -988,7 +987,6 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (start >= end) return; - folio_batch_init(&fbatch); index = start; while (index < end) { cond_resched(); diff --git a/mm/truncate.c b/mm/truncate.c index 357af144df63..e7f5762c43d3 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -56,11 +56,11 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, /* * Unconditionally remove exceptional entries. Usually called from truncate - * path. Note that the pagevec may be altered by this function by removing + * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what pagevec_remove_exceptionals does. */ -static void truncate_exceptional_pvec_entries(struct address_space *mapping, - struct pagevec *pvec, pgoff_t *indices) +static void truncate_folio_batch_exceptionals(struct address_space *mapping, + struct folio_batch *fbatch, pgoff_t *indices) { int i, j; bool dax; @@ -69,11 +69,11 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, if (shmem_mapping(mapping)) return; - for (j = 0; j < pagevec_count(pvec); j++) - if (xa_is_value(pvec->pages[j])) + for (j = 0; j < folio_batch_count(fbatch); j++) + if (xa_is_value(fbatch->folios[j])) break; - if (j == pagevec_count(pvec)) + if (j == folio_batch_count(fbatch)) return; dax = dax_mapping(mapping); @@ -82,12 +82,12 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, xa_lock_irq(&mapping->i_pages); } - for (i = j; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; + for (i = j; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; pgoff_t index = indices[i]; - if (!xa_is_value(page)) { - pvec->pages[j++] = page; + if (!xa_is_value(folio)) { + fbatch->folios[j++] = folio; continue; } @@ -96,7 +96,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, continue; } - __clear_shadow_entry(mapping, index, page); + __clear_shadow_entry(mapping, index, folio); } if (!dax) { @@ -105,14 +105,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); } - pvec->nr = j; -} - -static void truncate_folio_batch_exceptionals(struct address_space *mapping, - struct folio_batch *fbatch, pgoff_t *indices) -{ - truncate_exceptional_pvec_entries(mapping, (struct pagevec *)fbatch, - indices); + fbatch->nr = j; } /* @@ -303,7 +296,6 @@ void truncate_inode_pages_range(struct address_space *mapping, pgoff_t end; /* exclusive */ unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ - struct pagevec pvec; struct folio_batch fbatch; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; @@ -333,18 +325,18 @@ void truncate_inode_pages_range(struct address_space *mapping, else end = (lend + 1) >> PAGE_SHIFT; - pagevec_init(&pvec); + folio_batch_init(&fbatch); index = start; while (index < end && find_lock_entries(mapping, index, end - 1, - &pvec, indices)) { - index = indices[pagevec_count(&pvec) - 1] + 1; - truncate_exceptional_pvec_entries(mapping, &pvec, indices); - for (i = 0; i < pagevec_count(&pvec); i++) - truncate_cleanup_folio(page_folio(pvec.pages[i])); - delete_from_page_cache_batch(mapping, &pvec); - for (i = 0; i < pagevec_count(&pvec); i++) - unlock_page(pvec.pages[i]); - pagevec_release(&pvec); + &fbatch, indices)) { + index = indices[folio_batch_count(&fbatch) - 1] + 1; + truncate_folio_batch_exceptionals(mapping, &fbatch, indices); + for (i = 0; i < folio_batch_count(&fbatch); i++) + truncate_cleanup_folio(fbatch.folios[i]); + delete_from_page_cache_batch(mapping, &fbatch); + for (i = 0; i < folio_batch_count(&fbatch); i++) + folio_unlock(fbatch.folios[i]); + folio_batch_release(&fbatch); cond_resched(); } @@ -387,7 +379,6 @@ void truncate_inode_pages_range(struct address_space *mapping, if (start >= end) goto out; - folio_batch_init(&fbatch); index = start; for ( ; ; ) { cond_resched(); @@ -489,16 +480,16 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_pagevec) { pgoff_t indices[PAGEVEC_SIZE]; - struct pagevec pvec; + struct folio_batch fbatch; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; - pagevec_init(&pvec); - while (find_lock_entries(mapping, index, end, &pvec, indices)) { - for (i = 0; i < pagevec_count(&pvec); i++) { - struct page *page = pvec.pages[i]; + folio_batch_init(&fbatch); + while (find_lock_entries(mapping, index, end, &fbatch, indices)) { + for (i = 0; i < folio_batch_count(&fbatch); i++) { + struct page *page = &fbatch.folios[i]->page; /* We rely upon deletion not changing page->index */ index = indices[i]; @@ -525,8 +516,8 @@ static unsigned long __invalidate_mapping_pages(struct address_space *mapping, } count += ret; } - pagevec_remove_exceptionals(&pvec); - pagevec_release(&pvec); + folio_batch_remove_exceptionals(&fbatch); + folio_batch_release(&fbatch); cond_resched(); index++; } -- cgit v1.2.3 From 1613fac9aaf840af76faa747ea428a714af98dbd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Tue, 7 Dec 2021 14:28:49 -0500 Subject: mm: Remove pagevec_remove_exceptionals() All of its callers now call folio_batch_remove_exceptionals(). Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/pagevec.h | 6 +----- mm/swap.c | 26 +++++++++++++------------- mm/truncate.c | 2 +- 3 files changed, 15 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index c3fa616d7ae7..dda8d5868c81 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -27,7 +27,6 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_lru_add(struct pagevec *pvec); -void pagevec_remove_exceptionals(struct pagevec *pvec); unsigned pagevec_lookup_range(struct pagevec *pvec, struct address_space *mapping, pgoff_t *start, pgoff_t end); @@ -146,8 +145,5 @@ static inline void folio_batch_release(struct folio_batch *fbatch) pagevec_release((struct pagevec *)fbatch); } -static inline void folio_batch_remove_exceptionals(struct folio_batch *fbatch) -{ - pagevec_remove_exceptionals((struct pagevec *)fbatch); -} +void folio_batch_remove_exceptionals(struct folio_batch *fbatch); #endif /* _LINUX_PAGEVEC_H */ diff --git a/mm/swap.c b/mm/swap.c index e8c9dc6d0377..74f6b311d7ee 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1077,24 +1077,24 @@ void __pagevec_lru_add(struct pagevec *pvec) } /** - * pagevec_remove_exceptionals - pagevec exceptionals pruning - * @pvec: The pagevec to prune + * folio_batch_remove_exceptionals() - Prune non-folios from a batch. + * @fbatch: The batch to prune * - * find_get_entries() fills both pages and XArray value entries (aka - * exceptional entries) into the pagevec. This function prunes all - * exceptionals from @pvec without leaving holes, so that it can be - * passed on to page-only pagevec operations. + * find_get_entries() fills a batch with both folios and shadow/swap/DAX + * entries. This function prunes all the non-folio entries from @fbatch + * without leaving holes, so that it can be passed on to folio-only batch + * operations. */ -void pagevec_remove_exceptionals(struct pagevec *pvec) +void folio_batch_remove_exceptionals(struct folio_batch *fbatch) { - int i, j; + unsigned int i, j; - for (i = 0, j = 0; i < pagevec_count(pvec); i++) { - struct page *page = pvec->pages[i]; - if (!xa_is_value(page)) - pvec->pages[j++] = page; + for (i = 0, j = 0; i < folio_batch_count(fbatch); i++) { + struct folio *folio = fbatch->folios[i]; + if (!xa_is_value(folio)) + fbatch->folios[j++] = folio; } - pvec->nr = j; + fbatch->nr = j; } /** diff --git a/mm/truncate.c b/mm/truncate.c index e7f5762c43d3..a1113b0abb30 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -57,7 +57,7 @@ static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing - * exceptional entries similar to what pagevec_remove_exceptionals does. + * exceptional entries similar to what folio_batch_remove_exceptionals() does. */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) -- cgit v1.2.3 From 25a8de7f8d970ffa7263bd9d32a08138cd949f17 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 27 Aug 2021 07:21:49 -0400 Subject: XArray: Add xas_advance() Add a new helper function to help iterate over multi-index entries. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: William Kucharski --- include/linux/xarray.h | 18 ++++++++++++++++++ lib/xarray.c | 6 +++--- 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index a91e3d90df8a..d6d5da6ed735 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -1580,6 +1580,24 @@ static inline void xas_set(struct xa_state *xas, unsigned long index) xas->xa_node = XAS_RESTART; } +/** + * xas_advance() - Skip over sibling entries. + * @xas: XArray operation state. + * @index: Index of last sibling entry. + * + * Move the operation state to refer to the last sibling entry. + * This is useful for loops that normally want to see sibling + * entries but sometimes want to skip them. Use xas_set() if you + * want to move to an index which is not part of this entry. + */ +static inline void xas_advance(struct xa_state *xas, unsigned long index) +{ + unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0; + + xas->xa_index = index; + xas->xa_offset = (index >> shift) & XA_CHUNK_MASK; +} + /** * xas_set_order() - Set up XArray operation state for a multislot entry. * @xas: XArray operation state. diff --git a/lib/xarray.c b/lib/xarray.c index f5d8f54907b4..6f47f6375808 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -157,7 +157,7 @@ static void xas_move_index(struct xa_state *xas, unsigned long offset) xas->xa_index += offset << shift; } -static void xas_advance(struct xa_state *xas) +static void xas_next_offset(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); @@ -1250,7 +1250,7 @@ void *xas_find(struct xa_state *xas, unsigned long max) xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } - xas_advance(xas); + xas_next_offset(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { @@ -1268,7 +1268,7 @@ void *xas_find(struct xa_state *xas, unsigned long max) if (entry && !xa_is_sibling(entry)) return entry; - xas_advance(xas); + xas_next_offset(xas); } if (!xas->xa_node) -- cgit v1.2.3 From 6b24ca4a1a8d4ee3221d6d44ddbb99f542e4bda3 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Sat, 27 Jun 2020 22:19:08 -0400 Subject: mm: Use multi-index entries in the page cache We currently store large folios as 2^N consecutive entries. While this consumes rather more memory than necessary, it also turns out to be buggy. A writeback operation which starts within a tail page of a dirty folio will not write back the folio as the xarray's dirty bit is only set on the head index. With multi-index entries, the dirty bit will be found no matter where in the folio the operation starts. This does end up simplifying the page cache slightly, although not as much as I had hoped. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski --- include/linux/pagemap.h | 10 -------- mm/filemap.c | 61 +++++++++++++++++++++++++++++++------------------ mm/huge_memory.c | 18 +++++++++++---- mm/khugepaged.c | 12 +++++++++- mm/migrate.c | 8 ------- mm/shmem.c | 19 +++++++-------- 6 files changed, 72 insertions(+), 56 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 6e038811f4c8..704cb1b4b15d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -1125,16 +1125,6 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac, VM_BUG_ON_PAGE(PageTail(page), page); array[i++] = page; rac->_batch_count += thp_nr_pages(page); - - /* - * The page cache isn't using multi-index entries yet, - * so the xas cursor needs to be manually moved to the - * next index. This can be removed once the page cache - * is converted. - */ - if (PageHead(page)) - xas_set(&xas, rac->_index + rac->_batch_count); - if (i == array_sz) break; } diff --git a/mm/filemap.c b/mm/filemap.c index 9d3bae3e36c3..33077c264d79 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -135,7 +135,6 @@ static void page_cache_delete(struct address_space *mapping, } VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); - VM_BUG_ON_FOLIO(nr != 1 && shadow, folio); xas_store(&xas, shadow); xas_init_marks(&xas); @@ -286,7 +285,7 @@ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); - int total_pages = 0; + long total_pages = 0; int i = 0; struct folio *folio; @@ -313,18 +312,12 @@ static void page_cache_delete_batch(struct address_space *mapping, WARN_ON_ONCE(!folio_test_locked(folio)); - if (folio->index == xas.xa_index) - folio->mapping = NULL; + folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ - /* - * Move to the next folio in the batch if this is a regular - * folio or the index is of the last sub-page of this folio. - */ - if (folio->index + folio_nr_pages(folio) - 1 == xas.xa_index) - i++; + i++; xas_store(&xas, NULL); - total_pages++; + total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } @@ -2089,24 +2082,27 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start, indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; - goto next; + continue; unlock: folio_unlock(folio); put: folio_put(folio); -next: - if (!xa_is_value(folio) && folio_test_large(folio)) { - xas_set(&xas, folio->index + folio_nr_pages(folio)); - /* Did we wrap on 32-bit? */ - if (!xas.xa_index) - break; - } } rcu_read_unlock(); return folio_batch_count(fbatch); } +static inline +bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max) +{ + if (!folio_test_large(folio) || folio_test_hugetlb(folio)) + return false; + if (index >= max) + return false; + return index < folio->index + folio_nr_pages(folio) - 1; +} + /** * find_get_pages_range - gang pagecache lookup * @mapping: The address_space to search @@ -2145,11 +2141,17 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, if (xa_is_value(folio)) continue; +again: pages[ret] = folio_file_page(folio, xas.xa_index); if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } + if (folio_more_pages(folio, xas.xa_index, end)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } } /* @@ -2207,9 +2209,15 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, if (unlikely(folio != xas_reload(&xas))) goto put_page; - pages[ret] = &folio->page; +again: + pages[ret] = folio_file_page(folio, xas.xa_index); if (++ret == nr_pages) break; + if (folio_more_pages(folio, xas.xa_index, ULONG_MAX)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } continue; put_page: folio_put(folio); @@ -2334,8 +2342,7 @@ static void filemap_get_read_batch(struct address_space *mapping, break; if (folio_test_readahead(folio)) break; - xas.xa_index = folio->index + folio_nr_pages(folio) - 1; - xas.xa_offset = (xas.xa_index >> xas.xa_shift) & XA_CHUNK_MASK; + xas_advance(&xas, folio->index + folio_nr_pages(folio) - 1); continue; put_folio: folio_put(folio); @@ -3284,6 +3291,7 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); do { +again: page = folio_file_page(folio, xas.xa_index); if (PageHWPoison(page)) goto unlock; @@ -3305,9 +3313,18 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf, do_set_pte(vmf, page, addr); /* no need to invalidate: a not-present page won't be cached */ update_mmu_cache(vma, addr, vmf->pte); + if (folio_more_pages(folio, xas.xa_index, end_pgoff)) { + xas.xa_index++; + folio_ref_inc(folio); + goto again; + } folio_unlock(folio); continue; unlock: + if (folio_more_pages(folio, xas.xa_index, end_pgoff)) { + xas.xa_index++; + goto again; + } folio_unlock(folio); folio_put(folio); } while ((folio = next_map_page(mapping, &xas, end_pgoff)) != NULL); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e5483347291c..f58524394dc1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2614,6 +2614,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); struct deferred_split *ds_queue = get_deferred_split_queue(head); + XA_STATE(xas, &head->mapping->i_pages, head->index); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; int extra_pins, ret; @@ -2652,6 +2653,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) goto out; } + xas_split_alloc(&xas, head, compound_order(head), + mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); + if (xas_error(&xas)) { + ret = xas_error(&xas); + goto out; + } + anon_vma = NULL; i_mmap_lock_read(mapping); @@ -2681,13 +2689,12 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); if (mapping) { - XA_STATE(xas, &mapping->i_pages, page_index(head)); - /* * Check if the head page is present in page cache. * We assume all tail are present too, if head is there. */ - xa_lock(&mapping->i_pages); + xas_lock(&xas); + xas_reset(&xas); if (xas_load(&xas) != head) goto fail; } @@ -2703,6 +2710,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (mapping) { int nr = thp_nr_pages(head); + xas_split(&xas, head, thp_order(head)); if (PageSwapBacked(head)) { __mod_lruvec_page_state(head, NR_SHMEM_THPS, -nr); @@ -2719,7 +2727,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) spin_unlock(&ds_queue->split_queue_lock); fail: if (mapping) - xa_unlock(&mapping->i_pages); + xas_unlock(&xas); local_irq_enable(); remap_page(head, thp_nr_pages(head)); ret = -EBUSY; @@ -2733,6 +2741,8 @@ out_unlock: if (mapping) i_mmap_unlock_read(mapping); out: + /* Free any memory we didn't use */ + xas_nomem(&xas, 0); count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e99101162f1a..2e1911cc3466 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1667,7 +1667,10 @@ static void collapse_file(struct mm_struct *mm, } count_memcg_page_event(new_page, THP_COLLAPSE_ALLOC); - /* This will be less messy when we use multi-index entries */ + /* + * Ensure we have slots for all the pages in the range. This is + * almost certainly a no-op because most of the pages must be present + */ do { xas_lock_irq(&xas); xas_create_range(&xas); @@ -1892,6 +1895,9 @@ out_unlock: __mod_lruvec_page_state(new_page, NR_SHMEM, nr_none); } + /* Join all the small entries into a single multi-index entry */ + xas_set_order(&xas, start, HPAGE_PMD_ORDER); + xas_store(&xas, new_page); xa_locked: xas_unlock_irq(&xas); xa_unlocked: @@ -2013,6 +2019,10 @@ static void khugepaged_scan_file(struct mm_struct *mm, continue; } + /* + * XXX: khugepaged should compact smaller compound pages + * into a PMD sized page + */ if (PageTransCompound(page)) { result = SCAN_PAGE_COMPOUND; break; diff --git a/mm/migrate.c b/mm/migrate.c index 311638177536..7079e6b7dbe7 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -433,14 +433,6 @@ int folio_migrate_mapping(struct address_space *mapping, } xas_store(&xas, newfolio); - if (nr > 1) { - int i; - - for (i = 1; i < nr; i++) { - xas_next(&xas); - xas_store(&xas, newfolio); - } - } /* * Drop cache reference from old page by unfreezing diff --git a/mm/shmem.c b/mm/shmem.c index e4c9e5c7081f..28d627444a24 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -694,7 +694,6 @@ static int shmem_add_to_page_cache(struct page *page, struct mm_struct *charge_mm) { XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); - unsigned long i = 0; unsigned long nr = compound_nr(page); int error; @@ -721,20 +720,18 @@ static int shmem_add_to_page_cache(struct page *page, cgroup_throttle_swaprate(page, gfp); do { - void *entry; xas_lock_irq(&xas); - entry = xas_find_conflict(&xas); - if (entry != expected) + if (expected != xas_find_conflict(&xas)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + if (expected && xas_find_conflict(&xas)) { xas_set_err(&xas, -EEXIST); - xas_create_range(&xas); - if (xas_error(&xas)) goto unlock; -next: - xas_store(&xas, page); - if (++i < nr) { - xas_next(&xas); - goto next; } + xas_store(&xas, page); + if (xas_error(&xas)) + goto unlock; if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); __mod_lruvec_page_state(page, NR_SHMEM_THPS, nr); -- cgit v1.2.3 From e32cf5dfbe227b355776948b2c9b5691b84d1cbd Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 22 Dec 2021 22:10:09 -0600 Subject: kthread: Generalize pf_io_worker so it can point to struct kthread The point of using set_child_tid to hold the kthread pointer was that it already did what is necessary. There are now restrictions on when set_child_tid can be initialized and when set_child_tid can be used in schedule_tail. Which indicates that continuing to use set_child_tid to hold the kthread pointer is a bad idea. Instead of continuing to use the set_child_tid field of task_struct generalize the pf_io_worker field of task_struct and use it to hold the kthread pointer. Rename pf_io_worker (which is a void * pointer) to worker_private so it can be used to store kthreads struct kthread pointer. Update the kthread code to store the kthread pointer in the worker_private field. Remove the places where set_child_tid had to be dealt with carefully because kthreads also used it. Link: https://lkml.kernel.org/r/CAHk-=wgtFAA9SbVYg0gR1tqPMC17-NYcs0GQkaYg1bGhh1uJQQ@mail.gmail.com Link: https://lkml.kernel.org/r/87a6grvqy8.fsf_-_@email.froward.int.ebiederm.org Suggested-by: Linus Torvalds Signed-off-by: "Eric W. Biederman" --- fs/io-wq.c | 6 +++--- fs/io-wq.h | 2 +- include/linux/sched.h | 4 ++-- kernel/fork.c | 8 +------- kernel/kthread.c | 14 +++++--------- kernel/sched/core.c | 2 +- 6 files changed, 13 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/io-wq.c b/fs/io-wq.c index 88202de519f6..e4fc7384b40c 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -657,7 +657,7 @@ loop: */ void io_wq_worker_running(struct task_struct *tsk) { - struct io_worker *worker = tsk->pf_io_worker; + struct io_worker *worker = tsk->worker_private; if (!worker) return; @@ -675,7 +675,7 @@ void io_wq_worker_running(struct task_struct *tsk) */ void io_wq_worker_sleeping(struct task_struct *tsk) { - struct io_worker *worker = tsk->pf_io_worker; + struct io_worker *worker = tsk->worker_private; if (!worker) return; @@ -694,7 +694,7 @@ void io_wq_worker_sleeping(struct task_struct *tsk) static void io_init_new_worker(struct io_wqe *wqe, struct io_worker *worker, struct task_struct *tsk) { - tsk->pf_io_worker = worker; + tsk->worker_private = worker; worker->task = tsk; set_cpus_allowed_ptr(tsk, wqe->cpu_mask); tsk->flags |= PF_NO_SETAFFINITY; diff --git a/fs/io-wq.h b/fs/io-wq.h index 41bf37674a49..c7c23947cbcd 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -200,6 +200,6 @@ static inline void io_wq_worker_running(struct task_struct *tsk) static inline bool io_wq_current_is_worker(void) { return in_task() && (current->flags & PF_IO_WORKER) && - current->pf_io_worker; + current->worker_private; } #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..52f2fdffa3ab 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -987,8 +987,8 @@ struct task_struct { /* CLONE_CHILD_CLEARTID: */ int __user *clear_child_tid; - /* PF_IO_WORKER */ - void *pf_io_worker; + /* PF_KTHREAD | PF_IO_WORKER */ + void *worker_private; u64 utime; u64 stime; diff --git a/kernel/fork.c b/kernel/fork.c index 0816be1bb044..6f0293cb29c9 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -950,7 +950,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; - tsk->pf_io_worker = NULL; + tsk->worker_private = NULL; account_kernel_stack(tsk, 1); @@ -2032,12 +2032,6 @@ static __latent_entropy struct task_struct *copy_process( siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } - /* - * This _must_ happen before we call free_task(), i.e. before we jump - * to any of the bad_fork_* labels. This is to avoid freeing - * p->set_child_tid which is (ab)used as a kthread's data pointer for - * kernel threads (PF_KTHREAD). - */ p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? diff --git a/kernel/kthread.c b/kernel/kthread.c index c14707d15341..261a3c3b9c6c 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -72,7 +72,7 @@ enum KTHREAD_BITS { static inline struct kthread *to_kthread(struct task_struct *k) { WARN_ON(!(k->flags & PF_KTHREAD)); - return (__force void *)k->set_child_tid; + return k->worker_private; } /* @@ -80,7 +80,7 @@ static inline struct kthread *to_kthread(struct task_struct *k) * * Per construction; when: * - * (p->flags & PF_KTHREAD) && p->set_child_tid + * (p->flags & PF_KTHREAD) && p->worker_private * * the task is both a kthread and struct kthread is persistent. However * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and @@ -88,7 +88,7 @@ static inline struct kthread *to_kthread(struct task_struct *k) */ static inline struct kthread *__to_kthread(struct task_struct *p) { - void *kthread = (__force void *)p->set_child_tid; + void *kthread = p->worker_private; if (kthread && !(p->flags & PF_KTHREAD)) kthread = NULL; return kthread; @@ -109,11 +109,7 @@ bool set_kthread_struct(struct task_struct *p) init_completion(&kthread->parked); p->vfork_done = &kthread->exited; - /* - * We abuse ->set_child_tid to avoid the new member and because it - * can't be wrongly copied by copy_process(). - */ - p->set_child_tid = (__force void __user *)kthread; + p->worker_private = kthread; return true; } @@ -128,7 +124,7 @@ void free_kthread_struct(struct task_struct *k) #ifdef CONFIG_BLK_CGROUP WARN_ON_ONCE(kthread && kthread->blkcg_css); #endif - k->set_child_tid = (__force void __user *)NULL; + k->worker_private = NULL; kfree(kthread); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d8adbea77be1..ee222b89c692 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4908,7 +4908,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) finish_task_switch(prev); preempt_enable(); - if (!(current->flags & PF_KTHREAD) && current->set_child_tid) + if (current->set_child_tid) put_user(task_pid_vnr(current), current->set_child_tid); calculate_sigpending(); -- cgit v1.2.3 From 3367d1bd738c01b2737eaab7d922bfe5f1a41f38 Mon Sep 17 00:00:00 2001 From: Thomas Weißschuh Date: Sat, 8 Jan 2022 16:31:58 +0100 Subject: power: supply: Provide stubs for charge_behaviour helpers MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When CONFIG_SYSFS is not enabled provide stubs for the helper functions to not break their callers. Fixes: 539b9c94ac83 ("power: supply: add helpers for charge_behaviour sysfs") Reported-by: kernel test robot Signed-off-by: Thomas Weißschuh Link: https://lore.kernel.org/r/20220108153158.189489-1-linux@weissschuh.net Signed-off-by: Hans de Goede --- include/linux/power_supply.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h index 71f0379c2af8..f6b9ed4630fa 100644 --- a/include/linux/power_supply.h +++ b/include/linux/power_supply.h @@ -553,6 +553,21 @@ ssize_t power_supply_charge_behaviour_show(struct device *dev, char *buf); int power_supply_charge_behaviour_parse(unsigned int available_behaviours, const char *buf); +#else +static inline +ssize_t power_supply_charge_behaviour_show(struct device *dev, + unsigned int available_behaviours, + enum power_supply_charge_behaviour behaviour, + char *buf) +{ + return -EOPNOTSUPP; +} + +static inline int power_supply_charge_behaviour_parse(unsigned int available_behaviours, + const char *buf) +{ + return -EOPNOTSUPP; +} #endif #endif /* __LINUX_POWER_SUPPLY_H__ */ -- cgit v1.2.3 From 2f824d4d197e02275562359a2ae5274177ce500c Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 8 Jan 2022 09:48:31 -0600 Subject: signal: Remove SIGNAL_GROUP_COREDUMP After the previous cleanups "signal->core_state" is set whenever SIGNAL_GROUP_COREDUMP is set and "signal->core_state" is tested whenver the code wants to know if a coredump is in progress. The remaining tests of SIGNAL_GROUP_COREDUMP also test to see if SIGNAL_GROUP_EXIT is set. Similarly the only place that sets SIGNAL_GROUP_COREDUMP also sets SIGNAL_GROUP_EXIT. Which makes SIGNAL_GROUP_COREDUMP unecessary and redundant. So stop setting SIGNAL_GROUP_COREDUMP, stop testing SIGNAL_GROUP_COREDUMP, and remove it's definition. With the setting of SIGNAL_GROUP_COREDUMP gone, coredump_finish no longer needs to clear SIGNAL_GROUP_COREDUMP out of signal->flags by setting SIGNAL_GROUP_EXIT. Link: https://lkml.kernel.org/r/20211213225350.27481-5-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- fs/coredump.c | 3 +-- include/linux/sched/signal.h | 3 +-- kernel/signal.c | 2 +- 3 files changed, 3 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/coredump.c b/fs/coredump.c index 0864941a879b..fee1c57aee89 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -353,7 +353,7 @@ static int zap_process(struct task_struct *start, int exit_code) int nr = 0; /* ignore all signals except SIGKILL, see prepare_signal() */ - start->signal->flags = SIGNAL_GROUP_EXIT | SIGNAL_GROUP_COREDUMP; + start->signal->flags = SIGNAL_GROUP_EXIT; start->signal->group_exit_code = exit_code; start->signal->group_stop_count = 0; @@ -427,7 +427,6 @@ static void coredump_finish(bool core_dumped) if (core_dumped && !__fatal_signal_pending(current)) current->signal->group_exit_code |= 0x80; current->signal->group_exit_task = NULL; - current->signal->flags = SIGNAL_GROUP_EXIT; next = current->signal->core_state->dumper.next; current->signal->core_state = NULL; spin_unlock_irq(¤t->sighand->siglock); diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index fa26d2a58413..ecc10e148799 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -256,7 +256,6 @@ struct signal_struct { #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ -#define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ @@ -272,7 +271,7 @@ struct signal_struct { static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { - WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); + WARN_ON(sig->flags & SIGNAL_GROUP_EXIT); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } diff --git a/kernel/signal.c b/kernel/signal.c index 0706c1345a71..bae231bc2f4a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -906,7 +906,7 @@ static bool prepare_signal(int sig, struct task_struct *p, bool force) struct task_struct *t; sigset_t flush; - if ((signal->flags & SIGNAL_GROUP_EXIT) || signal->core_state) { + if (signal->flags & SIGNAL_GROUP_EXIT) { if (signal->core_state) return sig == SIGKILL; /* -- cgit v1.2.3 From 60700e38fb68e800607ca7a027060d5419fc5798 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 6 Jun 2021 13:47:53 -0500 Subject: signal: Rename group_exit_task group_exec_task The only remaining user of group_exit_task is exec. Rename the field so that it is clear which part of the code uses it. Update the comment above the definition of group_exec_task to document how it is currently used. Link: https://lkml.kernel.org/r/20211213225350.27481-7-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- fs/exec.c | 8 ++++---- include/linux/sched/signal.h | 12 ++++-------- kernel/exit.c | 4 ++-- 3 files changed, 10 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/fs/exec.c b/fs/exec.c index 59cac7c18178..9d2925811011 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1054,7 +1054,7 @@ static int de_thread(struct task_struct *tsk) return -EAGAIN; } - sig->group_exit_task = tsk; + sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; @@ -1082,7 +1082,7 @@ static int de_thread(struct task_struct *tsk) write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that - * exit_notify() can't miss ->group_exit_task + * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) @@ -1149,7 +1149,7 @@ static int de_thread(struct task_struct *tsk) release_task(leader); } - sig->group_exit_task = NULL; + sig->group_exec_task = NULL; sig->notify_count = 0; no_thread_group: @@ -1162,7 +1162,7 @@ no_thread_group: killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); - sig->group_exit_task = NULL; + sig->group_exec_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN; diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index ecc10e148799..d3248aba5183 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -109,13 +109,9 @@ struct signal_struct { /* thread group exit support */ int group_exit_code; - /* overloaded: - * - notify group_exit_task when ->count is equal to notify_count - * - everyone except group_exit_task is stopped during signal delivery - * of fatal signals, group_exit_task processes the signal. - */ + /* notify group_exec_task when notify_count is less or equal to 0 */ int notify_count; - struct task_struct *group_exit_task; + struct task_struct *group_exec_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; @@ -275,11 +271,11 @@ static inline void signal_set_stop_flags(struct signal_struct *sig, sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } -/* If true, all threads except ->group_exit_task have pending SIGKILL */ +/* If true, all threads except ->group_exec_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { return (sig->flags & SIGNAL_GROUP_EXIT) || - (sig->group_exit_task != NULL); + (sig->group_exec_task != NULL); } extern void flush_signals(struct task_struct *); diff --git a/kernel/exit.c b/kernel/exit.c index fc0726cb22db..b05578abbf26 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -116,7 +116,7 @@ static void __exit_signal(struct task_struct *tsk) * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) - wake_up_process(sig->group_exit_task); + wake_up_process(sig->group_exec_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); @@ -697,7 +697,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) - wake_up_process(tsk->signal->group_exit_task); + wake_up_process(tsk->signal->group_exec_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { -- cgit v1.2.3 From 49697335e0b441b0553598c1b48ee9ebb053d2f1 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 24 Jun 2021 02:14:30 -0500 Subject: signal: Remove the helper signal_group_exit This helper is misleading. It tests for an ongoing exec as well as the process having received a fatal signal. Sometimes it is appropriate to treat an on-going exec differently than a process that is shutting down due to a fatal signal. In particular taking the fast path out of exit_signals instead of retargeting signals is not appropriate during exec, and not changing the the exit code in do_group_exit during exec. Removing the helper makes it more obvious what is going on as both cases must be coded for explicitly. While removing the helper fix the two cases where I have observed using signal_group_exit resulted in the wrong result. In exit_signals only test for SIGNAL_GROUP_EXIT so that signals are retargetted during an exec. In do_group_exit use 0 as the exit code during an exec as de_thread does not set group_exit_code. As best as I can determine group_exit_code has been is set to 0 most of the time during de_thread. During a thread group stop group_exit_code is set to the stop signal and when the thread group receives SIGCONT group_exit_code is reset to 0. Link: https://lkml.kernel.org/r/20211213225350.27481-8-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- fs/coredump.c | 5 +++-- fs/exec.c | 2 +- include/linux/sched/signal.h | 7 ------- kernel/exit.c | 8 ++++++-- kernel/signal.c | 8 +++++--- 5 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/coredump.c b/fs/coredump.c index c92ffc0bf2c2..7dece20b162b 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -372,11 +372,12 @@ static int zap_process(struct task_struct *start, int exit_code) static int zap_threads(struct task_struct *tsk, struct core_state *core_state, int exit_code) { + struct signal_struct *signal = tsk->signal; int nr = -EAGAIN; spin_lock_irq(&tsk->sighand->siglock); - if (!signal_group_exit(tsk->signal)) { - tsk->signal->core_state = core_state; + if (!(signal->flags & SIGNAL_GROUP_EXIT) && !signal->group_exec_task) { + signal->core_state = core_state; nr = zap_process(tsk, exit_code); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); tsk->flags |= PF_DUMPCORE; diff --git a/fs/exec.c b/fs/exec.c index 9d2925811011..82db656ca709 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1045,7 +1045,7 @@ static int de_thread(struct task_struct *tsk) * Kill all other threads in the thread group. */ spin_lock_irq(lock); - if (signal_group_exit(sig)) { + if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index d3248aba5183..b6ecb9fc4cd2 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -271,13 +271,6 @@ static inline void signal_set_stop_flags(struct signal_struct *sig, sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } -/* If true, all threads except ->group_exec_task have pending SIGKILL */ -static inline int signal_group_exit(const struct signal_struct *sig) -{ - return (sig->flags & SIGNAL_GROUP_EXIT) || - (sig->group_exec_task != NULL); -} - extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); diff --git a/kernel/exit.c b/kernel/exit.c index b05578abbf26..861cfb1e2f77 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -914,15 +914,19 @@ do_group_exit(int exit_code) BUG_ON(exit_code & 0x80); /* core dumps don't get here */ - if (signal_group_exit(sig)) + if (sig->flags & SIGNAL_GROUP_EXIT) exit_code = sig->group_exit_code; + else if (sig->group_exec_task) + exit_code = 0; else if (!thread_group_empty(current)) { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); - if (signal_group_exit(sig)) + if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; + else if (sig->group_exec_task) + exit_code = 0; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; diff --git a/kernel/signal.c b/kernel/signal.c index bae231bc2f4a..167b8e196a79 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2386,7 +2386,8 @@ static bool do_signal_stop(int signr) WARN_ON_ONCE(signr & ~JOBCTL_STOP_SIGMASK); if (!likely(current->jobctl & JOBCTL_STOP_DEQUEUED) || - unlikely(signal_group_exit(sig))) + unlikely(sig->flags & SIGNAL_GROUP_EXIT) || + unlikely(sig->group_exec_task)) return false; /* * There is no group stop already in progress. We must @@ -2693,7 +2694,8 @@ relock: enum pid_type type; /* Has this task already been marked for death? */ - if (signal_group_exit(signal)) { + if ((signal->flags & SIGNAL_GROUP_EXIT) || + signal->group_exec_task) { ksig->info.si_signo = signr = SIGKILL; sigdelset(¤t->pending.signal, SIGKILL); trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, @@ -2949,7 +2951,7 @@ void exit_signals(struct task_struct *tsk) */ cgroup_threadgroup_change_begin(tsk); - if (thread_group_empty(tsk) || signal_group_exit(tsk->signal)) { + if (thread_group_empty(tsk) || (tsk->signal->flags & SIGNAL_GROUP_EXIT)) { tsk->flags |= PF_EXITING; cgroup_threadgroup_change_end(tsk); return; -- cgit v1.2.3 From 2d4bcf886e42f0f4846a3d9bdc3a90d278903a2e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 8 Jan 2022 11:23:02 -0600 Subject: exit: Remove profile_task_exit & profile_munmap When I say remove I mean remove. All profile_task_exit and profile_munmap do is call a blocking notifier chain. The helpers profile_task_register and profile_task_unregister are not called anywhere in the tree. Which means this is all dead code. So remove the dead code and make it easier to read do_exit. Reviewed-by: Christoph Hellwig Link: https://lkml.kernel.org/r/20220103213312.9144-1-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/profile.h | 26 ------------------------- kernel/exit.c | 1 - kernel/profile.c | 50 ------------------------------------------------- mm/mmap.c | 1 - 4 files changed, 78 deletions(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index fd18ca96f557..f7eb2b57d890 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -31,11 +31,6 @@ static inline int create_proc_profile(void) } #endif -enum profile_type { - PROFILE_TASK_EXIT, - PROFILE_MUNMAP -}; - #ifdef CONFIG_PROFILING extern int prof_on __read_mostly; @@ -66,23 +61,14 @@ static inline void profile_hit(int type, void *ip) struct task_struct; struct mm_struct; -/* task is in do_exit() */ -void profile_task_exit(struct task_struct * task); - /* task is dead, free task struct ? Returns 1 if * the task was taken, 0 if the task should be freed. */ int profile_handoff_task(struct task_struct * task); -/* sys_munmap */ -void profile_munmap(unsigned long addr); - int task_handoff_register(struct notifier_block * n); int task_handoff_unregister(struct notifier_block * n); -int profile_event_register(enum profile_type, struct notifier_block * n); -int profile_event_unregister(enum profile_type, struct notifier_block * n); - #else #define prof_on 0 @@ -117,19 +103,7 @@ static inline int task_handoff_unregister(struct notifier_block * n) return -ENOSYS; } -static inline int profile_event_register(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int profile_event_unregister(enum profile_type t, struct notifier_block * n) -{ - return -ENOSYS; -} - -#define profile_task_exit(a) do { } while (0) #define profile_handoff_task(a) (0) -#define profile_munmap(a) do { } while (0) #endif /* CONFIG_PROFILING */ diff --git a/kernel/exit.c b/kernel/exit.c index 861cfb1e2f77..64e907bc87d5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -751,7 +751,6 @@ void __noreturn do_exit(long code) */ force_uaccess_begin(); - profile_task_exit(tsk); kcov_task_exit(tsk); coredump_task_exit(tsk); diff --git a/kernel/profile.c b/kernel/profile.c index eb9c7f0f5ac5..9355cc934a96 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -135,14 +135,7 @@ int __ref profile_init(void) /* Profile event notifications */ -static BLOCKING_NOTIFIER_HEAD(task_exit_notifier); static ATOMIC_NOTIFIER_HEAD(task_free_notifier); -static BLOCKING_NOTIFIER_HEAD(munmap_notifier); - -void profile_task_exit(struct task_struct *task) -{ - blocking_notifier_call_chain(&task_exit_notifier, 0, task); -} int profile_handoff_task(struct task_struct *task) { @@ -151,11 +144,6 @@ int profile_handoff_task(struct task_struct *task) return (ret == NOTIFY_OK) ? 1 : 0; } -void profile_munmap(unsigned long addr) -{ - blocking_notifier_call_chain(&munmap_notifier, 0, (void *)addr); -} - int task_handoff_register(struct notifier_block *n) { return atomic_notifier_chain_register(&task_free_notifier, n); @@ -168,44 +156,6 @@ int task_handoff_unregister(struct notifier_block *n) } EXPORT_SYMBOL_GPL(task_handoff_unregister); -int profile_event_register(enum profile_type type, struct notifier_block *n) -{ - int err = -EINVAL; - - switch (type) { - case PROFILE_TASK_EXIT: - err = blocking_notifier_chain_register( - &task_exit_notifier, n); - break; - case PROFILE_MUNMAP: - err = blocking_notifier_chain_register( - &munmap_notifier, n); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(profile_event_register); - -int profile_event_unregister(enum profile_type type, struct notifier_block *n) -{ - int err = -EINVAL; - - switch (type) { - case PROFILE_TASK_EXIT: - err = blocking_notifier_chain_unregister( - &task_exit_notifier, n); - break; - case PROFILE_MUNMAP: - err = blocking_notifier_chain_unregister( - &munmap_notifier, n); - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(profile_event_unregister); - #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending diff --git a/mm/mmap.c b/mm/mmap.c index bfb0ea164a90..70318c2a47c3 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2928,7 +2928,6 @@ EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { addr = untagged_addr(addr); - profile_munmap(addr); return __vm_munmap(addr, len, true); } -- cgit v1.2.3 From 2873cd31a20c25b5e763b35e5fb886f0938c6dd5 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sat, 8 Jan 2022 10:03:24 -0600 Subject: exit: Remove profile_handoff_task All profile_handoff_task does is notify the task_free_notifier chain. The helpers task_handoff_register and task_handoff_unregister are used to add and delete entries from that chain and are never called. So remove the dead code and make it much easier to read and reason about __put_task_struct. Suggested-by: Al Viro Link: https://lkml.kernel.org/r/87fspyw6m0.fsf@email.froward.int.ebiederm.org Signed-off-by: "Eric W. Biederman" --- include/linux/profile.h | 19 ------------------- kernel/fork.c | 4 +--- kernel/profile.c | 23 ----------------------- 3 files changed, 1 insertion(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/profile.h b/include/linux/profile.h index f7eb2b57d890..11db1ec516e2 100644 --- a/include/linux/profile.h +++ b/include/linux/profile.h @@ -61,14 +61,6 @@ static inline void profile_hit(int type, void *ip) struct task_struct; struct mm_struct; -/* task is dead, free task struct ? Returns 1 if - * the task was taken, 0 if the task should be freed. - */ -int profile_handoff_task(struct task_struct * task); - -int task_handoff_register(struct notifier_block * n); -int task_handoff_unregister(struct notifier_block * n); - #else #define prof_on 0 @@ -93,17 +85,6 @@ static inline void profile_hit(int type, void *ip) return; } -static inline int task_handoff_register(struct notifier_block * n) -{ - return -ENOSYS; -} - -static inline int task_handoff_unregister(struct notifier_block * n) -{ - return -ENOSYS; -} - -#define profile_handoff_task(a) (0) #endif /* CONFIG_PROFILING */ diff --git a/kernel/fork.c b/kernel/fork.c index 6f0293cb29c9..494539ecb6d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -754,9 +754,7 @@ void __put_task_struct(struct task_struct *tsk) delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); - - if (!profile_handoff_task(tsk)) - free_task(tsk); + free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); diff --git a/kernel/profile.c b/kernel/profile.c index 9355cc934a96..37640a0bd8a3 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -133,29 +133,6 @@ int __ref profile_init(void) return -ENOMEM; } -/* Profile event notifications */ - -static ATOMIC_NOTIFIER_HEAD(task_free_notifier); - -int profile_handoff_task(struct task_struct *task) -{ - int ret; - ret = atomic_notifier_call_chain(&task_free_notifier, 0, task); - return (ret == NOTIFY_OK) ? 1 : 0; -} - -int task_handoff_register(struct notifier_block *n) -{ - return atomic_notifier_chain_register(&task_free_notifier, n); -} -EXPORT_SYMBOL_GPL(task_handoff_register); - -int task_handoff_unregister(struct notifier_block *n) -{ - return atomic_notifier_chain_unregister(&task_free_notifier, n); -} -EXPORT_SYMBOL_GPL(task_handoff_unregister); - #if defined(CONFIG_SMP) && defined(CONFIG_PROC_FS) /* * Each cpu has a pair of open-addressed hashtables for pending -- cgit v1.2.3 From 4264178416cd52a55a3eccbefb3973866e060280 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 20 Dec 2021 16:28:53 -0600 Subject: ptrace: Remove unused regs argument from ptrace_report_syscall Link: https://lkml.kernel.org/r/20220103213312.9144-7-ebiederm@xmission.com Signed-off-by: "Eric W. Biederman" --- include/linux/tracehook.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h index 2564b7434b4d..88c007ab5ebc 100644 --- a/include/linux/tracehook.h +++ b/include/linux/tracehook.h @@ -54,8 +54,7 @@ struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ -static inline int ptrace_report_syscall(struct pt_regs *regs, - unsigned long message) +static inline int ptrace_report_syscall(unsigned long message) { int ptrace = current->ptrace; @@ -102,7 +101,7 @@ static inline int ptrace_report_syscall(struct pt_regs *regs, static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { - return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); + return ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** @@ -127,7 +126,7 @@ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) if (step) user_single_step_report(regs); else - ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); + ptrace_report_syscall(PTRACE_EVENTMSG_SYSCALL_EXIT); } /** -- cgit v1.2.3 From 40595cdc93edf4110c0f0c0b06f8d82008f23929 Mon Sep 17 00:00:00 2001 From: "J. Bruce Fields" Date: Thu, 16 Dec 2021 12:20:13 -0500 Subject: nfs: block notification on fs with its own ->lock NFSv4.1 supports an optional lock notification feature which notifies the client when a lock comes available. (Normally NFSv4 clients just poll for locks if necessary.) To make that work, we need to request a blocking lock from the filesystem. We turned that off for NFS in commit f657f8eef3ff ("nfs: don't atempt blocking locks on nfs reexports") [sic] because it actually blocks the nfsd thread while waiting for the lock. Thanks to Vasily Averin for pointing out that NFS isn't the only filesystem with that problem. Any filesystem that leaves ->lock NULL will use posix_lock_file(), which does the right thing. Simplest is just to assume that any filesystem that defines its own ->lock is not safe to request a blocking lock from. So, this patch mostly reverts commit f657f8eef3ff ("nfs: don't atempt blocking locks on nfs reexports") [sic] and commit b840be2f00c0 ("lockd: don't attempt blocking locks on nfs reexports"), and instead uses a check of ->lock (Vasily's suggestion) to decide whether to support blocking lock notifications on a given filesystem. Also add a little documentation. Perhaps someday we could add back an export flag later to allow filesystems with "good" ->lock methods to support blocking lock notifications. Reported-by: Vasily Averin Signed-off-by: J. Bruce Fields [ cel: Description rewritten to address checkpatch nits ] [ cel: Fixed warning when SUNRPC debugging is disabled ] [ cel: Fixed NULL check ] Signed-off-by: Chuck Lever Reviewed-by: Vasily Averin --- fs/lockd/svclock.c | 6 ++++-- fs/nfs/export.c | 2 +- fs/nfsd/nfs4state.c | 18 ++++++++++++------ include/linux/exportfs.h | 2 -- include/linux/lockd/lockd.h | 9 +++++++-- 5 files changed, 24 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index e9b85d8fd5fe..cb3658ab9b7a 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -470,8 +470,10 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, struct nlm_host *host, struct nlm_lock *lock, int wait, struct nlm_cookie *cookie, int reclaim) { - struct nlm_block *block = NULL; +#if IS_ENABLED(CONFIG_SUNRPC_DEBUG) struct inode *inode = nlmsvc_file_inode(file); +#endif + struct nlm_block *block = NULL; int error; int mode; int async_block = 0; @@ -484,7 +486,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file, (long long)lock->fl.fl_end, wait); - if (inode->i_sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS) { + if (nlmsvc_file_file(file)->f_op->lock) { async_block = wait; wait = 0; } diff --git a/fs/nfs/export.c b/fs/nfs/export.c index 171c424cb6d5..01596f2d0a1e 100644 --- a/fs/nfs/export.c +++ b/fs/nfs/export.c @@ -158,5 +158,5 @@ const struct export_operations nfs_export_ops = { .fetch_iversion = nfs_fetch_iversion, .flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK| EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS| - EXPORT_OP_NOATOMIC_ATTR|EXPORT_OP_SYNC_LOCKS, + EXPORT_OP_NOATOMIC_ATTR, }; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 72e3833c3034..d8faccc55479 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -6842,7 +6842,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; - struct super_block *sb; __be32 status = 0; int lkflg; int err; @@ -6864,7 +6863,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } - sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) @@ -6916,8 +6914,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate) && - !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) + if (nfsd4_has_session(cstate)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_READ_LT: @@ -6929,8 +6926,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, fl_type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate) && - !(sb->s_export_op->flags & EXPORT_OP_SYNC_LOCKS)) + if (nfsd4_has_session(cstate)) fl_flags |= FL_SLEEP; fallthrough; case NFS4_WRITE_LT: @@ -6951,6 +6947,16 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } + /* + * Most filesystems with their own ->lock operations will block + * the nfsd thread waiting to acquire the lock. That leads to + * deadlocks (we don't want every nfsd thread tied up waiting + * for file locks), so don't attempt blocking lock notifications + * on those filesystems: + */ + if (nf->nf_file->f_op->lock) + fl_flags &= ~FL_SLEEP; + nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { dprintk("NFSD: %s: unable to allocate block!\n", __func__); diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index 3260fe714846..fe848901fcc3 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -221,8 +221,6 @@ struct export_operations { #define EXPORT_OP_NOATOMIC_ATTR (0x10) /* Filesystem cannot supply atomic attribute updates */ -#define EXPORT_OP_SYNC_LOCKS (0x20) /* Filesystem can't do - asychronous blocking locks */ unsigned long flags; }; diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index c4ae6506b8b3..fcef192e5e45 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -303,10 +303,15 @@ void nlmsvc_invalidate_all(void); int nlmsvc_unlock_all_by_sb(struct super_block *sb); int nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr); +static inline struct file *nlmsvc_file_file(struct nlm_file *file) +{ + return file->f_file[O_RDONLY] ? + file->f_file[O_RDONLY] : file->f_file[O_WRONLY]; +} + static inline struct inode *nlmsvc_file_inode(struct nlm_file *file) { - return locks_inode(file->f_file[O_RDONLY] ? - file->f_file[O_RDONLY] : file->f_file[O_WRONLY]); + return locks_inode(nlmsvc_file_file(file)); } static inline int __nlm_privileged_request4(const struct sockaddr *sap) -- cgit v1.2.3 From 0aa698787aa2a9e8840987e54ba2982559de6404 Mon Sep 17 00:00:00 2001 From: axelj Date: Mon, 13 Dec 2021 08:09:25 +0100 Subject: tpm: Add Upgrade/Reduced mode support for TPM2 modules If something went wrong during the TPM firmware upgrade, like power failure or the firmware image file get corrupted, the TPM might end up in Upgrade or Failure mode upon the next start. The state is persistent between the TPM power cycle/restart. According to TPM specification: * If the TPM is in Upgrade mode, it will answer with TPM2_RC_UPGRADE to all commands except TPM2_FieldUpgradeData(). It may also accept other commands if it is able to complete them using the previously installed firmware. * If the TPM is in Failure mode, it will allow performing TPM initialization but will not provide any crypto operations. Will happily respond to Field Upgrade calls. Change the behavior of the tpm2_auto_startup(), so it detects the active running mode of the TPM by adding the following checks. If tpm2_do_selftest() call returns TPM2_RC_UPGRADE, the TPM is in Upgrade mode. If the TPM is in Failure mode, it will successfully respond to both tpm2_do_selftest() and tpm2_startup() calls. Although, will fail to answer to tpm2_get_cc_attrs_tbl(). Use this fact to conclude that TPM is in Failure mode. If detected that the TPM is in the Upgrade or Failure mode, the function sets TPM_CHIP_FLAG_FIRMWARE_UPGRADE_MODE flag. The TPM_CHIP_FLAG_FIRMWARE_UPGRADE_MODE flag is used later during driver initialization/deinitialization to disable functionality which makes no sense or will fail in the current TPM state. Following functionality is affected: * Do not register TPM as a hwrng * Do not register sysfs entries which provide information impossible to obtain in limited mode * Do not register resource managed character device Signed-off-by: axelj Reviewed-by: Jarkko Sakkinen Signed-off-by: Jarkko Sakkinen --- drivers/char/tpm/tpm-chip.c | 19 ++++++++++++------- drivers/char/tpm/tpm-sysfs.c | 3 +++ drivers/char/tpm/tpm2-cmd.c | 6 ++++++ include/linux/tpm.h | 10 ++++++++++ 4 files changed, 31 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index ddaeceb7e109..b4ed3ae67a4b 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -444,7 +444,7 @@ static int tpm_add_char_device(struct tpm_chip *chip) return rc; } - if (chip->flags & TPM_CHIP_FLAG_TPM2) { + if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip)) { rc = cdev_device_add(&chip->cdevs, &chip->devs); if (rc) { dev_err(&chip->devs, @@ -488,7 +488,8 @@ static void tpm_del_legacy_sysfs(struct tpm_chip *chip) { struct attribute **i; - if (chip->flags & (TPM_CHIP_FLAG_TPM2 | TPM_CHIP_FLAG_VIRTUAL)) + if (chip->flags & (TPM_CHIP_FLAG_TPM2 | TPM_CHIP_FLAG_VIRTUAL) || + tpm_is_firmware_upgrade(chip)) return; sysfs_remove_link(&chip->dev.parent->kobj, "ppi"); @@ -506,7 +507,8 @@ static int tpm_add_legacy_sysfs(struct tpm_chip *chip) struct attribute **i; int rc; - if (chip->flags & (TPM_CHIP_FLAG_TPM2 | TPM_CHIP_FLAG_VIRTUAL)) + if (chip->flags & (TPM_CHIP_FLAG_TPM2 | TPM_CHIP_FLAG_VIRTUAL) || + tpm_is_firmware_upgrade(chip)) return 0; rc = compat_only_sysfs_link_entry_to_kobj( @@ -536,7 +538,7 @@ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) static int tpm_add_hwrng(struct tpm_chip *chip) { - if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM)) + if (!IS_ENABLED(CONFIG_HW_RANDOM_TPM) || tpm_is_firmware_upgrade(chip)) return 0; snprintf(chip->hwrng_name, sizeof(chip->hwrng_name), @@ -550,6 +552,9 @@ static int tpm_get_pcr_allocation(struct tpm_chip *chip) { int rc; + if (tpm_is_firmware_upgrade(chip)) + return 0; + rc = (chip->flags & TPM_CHIP_FLAG_TPM2) ? tpm2_get_pcr_allocation(chip) : tpm1_get_pcr_allocation(chip); @@ -612,7 +617,7 @@ int tpm_chip_register(struct tpm_chip *chip) return 0; out_hwrng: - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM)) + if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip)) hwrng_unregister(&chip->hwrng); out_ppi: tpm_bios_log_teardown(chip); @@ -637,10 +642,10 @@ EXPORT_SYMBOL_GPL(tpm_chip_register); void tpm_chip_unregister(struct tpm_chip *chip) { tpm_del_legacy_sysfs(chip); - if (IS_ENABLED(CONFIG_HW_RANDOM_TPM)) + if (IS_ENABLED(CONFIG_HW_RANDOM_TPM) && !tpm_is_firmware_upgrade(chip)) hwrng_unregister(&chip->hwrng); tpm_bios_log_teardown(chip); - if (chip->flags & TPM_CHIP_FLAG_TPM2) + if (chip->flags & TPM_CHIP_FLAG_TPM2 && !tpm_is_firmware_upgrade(chip)) cdev_device_del(&chip->cdevs, &chip->devs); tpm_del_char_device(chip); } diff --git a/drivers/char/tpm/tpm-sysfs.c b/drivers/char/tpm/tpm-sysfs.c index 63f03cfb8e6a..54c71473aa29 100644 --- a/drivers/char/tpm/tpm-sysfs.c +++ b/drivers/char/tpm/tpm-sysfs.c @@ -480,6 +480,9 @@ void tpm_sysfs_add_device(struct tpm_chip *chip) WARN_ON(chip->groups_cnt != 0); + if (tpm_is_firmware_upgrade(chip)) + return; + if (chip->flags & TPM_CHIP_FLAG_TPM2) chip->groups[chip->groups_cnt++] = &tpm2_dev_group; else diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index a25815a6f625..4704fa553098 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -745,6 +745,12 @@ int tpm2_auto_startup(struct tpm_chip *chip) rc = tpm2_get_cc_attrs_tbl(chip); out: + if (rc == TPM2_RC_UPGRADE) { + dev_info(&chip->dev, "TPM in field upgrade mode, requires firmware upgrade\n"); + chip->flags |= TPM_CHIP_FLAG_FIRMWARE_UPGRADE; + rc = 0; + } + if (rc > 0) rc = -ENODEV; return rc; diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 12d827734686..dfeb25a0362d 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -207,6 +207,7 @@ enum tpm2_return_codes { TPM2_RC_INITIALIZE = 0x0100, /* RC_VER1 */ TPM2_RC_FAILURE = 0x0101, TPM2_RC_DISABLED = 0x0120, + TPM2_RC_UPGRADE = 0x012D, TPM2_RC_COMMAND_CODE = 0x0143, TPM2_RC_TESTING = 0x090A, /* RC_WARN */ TPM2_RC_REFERENCE_H0 = 0x0910, @@ -278,6 +279,7 @@ enum tpm_chip_flags { TPM_CHIP_FLAG_HAVE_TIMEOUTS = BIT(4), TPM_CHIP_FLAG_ALWAYS_POWERED = BIT(5), TPM_CHIP_FLAG_FIRMWARE_POWER_MANAGED = BIT(6), + TPM_CHIP_FLAG_FIRMWARE_UPGRADE = BIT(7), }; #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev) @@ -399,6 +401,14 @@ static inline void tpm_buf_append_u32(struct tpm_buf *buf, const u32 value) tpm_buf_append(buf, (u8 *) &value2, 4); } +/* + * Check if TPM device is in the firmware upgrade mode. + */ +static inline bool tpm_is_firmware_upgrade(struct tpm_chip *chip) +{ + return chip->flags & TPM_CHIP_FLAG_FIRMWARE_UPGRADE; +} + static inline u32 tpm2_rc_value(u32 rc) { return (rc & BIT(7)) ? rc & 0xff : rc; -- cgit v1.2.3 From 292c33c95defd0b814fec1fc8cd60d16556cf7b8 Mon Sep 17 00:00:00 2001 From: Yang Li Date: Fri, 7 Jan 2022 08:52:28 +0800 Subject: block: fix old-style declaration MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the 'inline' keyword to the front of 'void'. Remove a warning found by clang(make W=1 LLVM=1) ./include/linux/blk-mq.h:259:1: warning: ‘inline’ is not at beginning of declaration Reported-by: Abaci Robot Signed-off-by: Yang Li Link: https://lore.kernel.org/r/20220107005228.103927-1-yang.lee@linux.alibaba.com Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index f40a05ecca4a..d319ffa59354 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -256,7 +256,7 @@ static inline unsigned short req_get_ioprio(struct request *req) * @rq: The request to move * @prev: The request preceding @rq in @src (NULL if @rq is the head) */ -static void inline rq_list_move(struct request **src, struct request **dst, +static inline void rq_list_move(struct request **src, struct request **dst, struct request *rq, struct request *prev) { if (prev) -- cgit v1.2.3 From 0ea9fc15b1d7d6636d429e74ffe3f86bf2f2f7d6 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 23 Nov 2021 17:05:07 +0100 Subject: fs/locks: fix fcntl_getlk64/fcntl_setlk64 stub prototypes My patch to rework oabi fcntl64() introduced a harmless sparse warning when file locking is disabled: arch/arm/kernel/sys_oabi-compat.c:251:51: sparse: sparse: incorrect type in argument 3 (different address spaces) @@ expected struct flock64 [noderef] __user *user @@ got struct flock64 * @@ arch/arm/kernel/sys_oabi-compat.c:251:51: sparse: expected struct flock64 [noderef] __user *user arch/arm/kernel/sys_oabi-compat.c:251:51: sparse: got struct flock64 * arch/arm/kernel/sys_oabi-compat.c:265:55: sparse: sparse: incorrect type in argument 4 (different address spaces) @@ expected struct flock64 [noderef] __user *user @@ got struct flock64 * @@ arch/arm/kernel/sys_oabi-compat.c:265:55: sparse: expected struct flock64 [noderef] __user *user arch/arm/kernel/sys_oabi-compat.c:265:55: sparse: got struct flock64 * When file locking is enabled, everything works correctly and the right data gets passed, but the stub declarations in linux/fs.h did not get modified when the calling conventions changed in an earlier patch. Reported-by: kernel test robot Fixes: 7e2d8c29ecdd ("ARM: 9111/1: oabi-compat: rework fcntl64() emulation") Fixes: a75d30c77207 ("fs/locks: pass kernel struct flock to fcntl_getlk/setlk") Cc: Christoph Hellwig Reviewed-by: Christoph Hellwig Acked-by: Christian Brauner Signed-off-by: Arnd Bergmann Signed-off-by: Jeff Layton Signed-off-by: Chuck Lever --- include/linux/fs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..5122d13775c2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1220,13 +1220,13 @@ static inline int fcntl_setlk(unsigned int fd, struct file *file, #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, - struct flock64 __user *user) + struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, - unsigned int cmd, struct flock64 __user *user) + unsigned int cmd, struct flock64 *user) { return -EACCES; } -- cgit v1.2.3 From 719774377622bc4025d2a74f551b5dc2158c6c30 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 7 Jan 2022 05:03:22 +0100 Subject: netfilter: conntrack: convert to refcount_t api Convert nf_conn reference counting from atomic_t to refcount_t based api. refcount_t api provides more runtime sanity checks and will warn on certain constructs, e.g. refcount_inc() on a zero reference count, which usually indicates use-after-free. For this reason template allocation is changed to init the refcount to 1, the subsequenct add operations are removed. Likewise, init_conntrack() is changed to set the initial refcount to 1 instead refcount_inc(). This is safe because the new entry is not (yet) visible to other cpus. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 8 ++++---- net/netfilter/nf_conntrack_core.c | 26 +++++++++++++------------- net/netfilter/nf_conntrack_expect.c | 4 ++-- net/netfilter/nf_conntrack_netlink.c | 6 +++--- net/netfilter/nf_conntrack_standalone.c | 4 ++-- net/netfilter/nf_flow_table_core.c | 2 +- net/netfilter/nf_synproxy_core.c | 1 - net/netfilter/nft_ct.c | 4 +--- net/netfilter/xt_CT.c | 3 +-- net/openvswitch/conntrack.c | 1 - net/sched/act_ct.c | 1 - 11 files changed, 27 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 700ea077ce2d..a03f7a80b9ab 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -2,7 +2,7 @@ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H -#include +#include #include struct ip_conntrack_stat { @@ -25,19 +25,19 @@ struct ip_conntrack_stat { #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { - atomic_t use; + refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); static inline void nf_conntrack_put(struct nf_conntrack *nfct) { - if (nfct && atomic_dec_and_test(&nfct->use)) + if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) - atomic_inc(&nfct->use); + refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index bed0017cadb0..328d359fcabe 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -585,7 +585,7 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, tmpl->status = IPS_TEMPLATE; write_pnet(&tmpl->ct_net, net); nf_ct_zone_add(tmpl, zone); - atomic_set(&tmpl->ct_general.use, 0); + refcount_set(&tmpl->ct_general.use, 1); return tmpl; } @@ -618,7 +618,7 @@ destroy_conntrack(struct nf_conntrack *nfct) struct nf_conn *ct = (struct nf_conn *)nfct; pr_debug("destroy_conntrack(%p)\n", ct); - WARN_ON(atomic_read(&nfct->use) != 0); + WARN_ON(refcount_read(&nfct->use) != 0); if (unlikely(nf_ct_is_template(ct))) { nf_ct_tmpl_free(ct); @@ -742,7 +742,7 @@ nf_ct_match(const struct nf_conn *ct1, const struct nf_conn *ct2) /* caller must hold rcu readlock and none of the nf_conntrack_locks */ static void nf_ct_gc_expired(struct nf_conn *ct) { - if (!atomic_inc_not_zero(&ct->ct_general.use)) + if (!refcount_inc_not_zero(&ct->ct_general.use)) return; if (nf_ct_should_gc(ct)) @@ -810,7 +810,7 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, * in, try to obtain a reference and re-check tuple */ ct = nf_ct_tuplehash_to_ctrack(h); - if (likely(atomic_inc_not_zero(&ct->ct_general.use))) { + if (likely(refcount_inc_not_zero(&ct->ct_general.use))) { if (likely(nf_ct_key_equal(h, tuple, zone, net))) goto found; @@ -907,7 +907,7 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) smp_wmb(); /* The caller holds a reference to this object */ - atomic_set(&ct->ct_general.use, 2); + refcount_set(&ct->ct_general.use, 2); __nf_conntrack_hash_insert(ct, hash, reply_hash); nf_conntrack_double_unlock(hash, reply_hash); NF_CT_STAT_INC(net, insert); @@ -958,7 +958,7 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct) { struct nf_conn_tstamp *tstamp; - atomic_inc(&ct->ct_general.use); + refcount_inc(&ct->ct_general.use); ct->status |= IPS_CONFIRMED; /* set conntrack timestamp, if enabled. */ @@ -1351,7 +1351,7 @@ static unsigned int early_drop_list(struct net *net, nf_ct_is_dying(tmp)) continue; - if (!atomic_inc_not_zero(&tmp->ct_general.use)) + if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue; /* kill only if still in same netns -- might have moved due to @@ -1469,7 +1469,7 @@ static void gc_worker(struct work_struct *work) continue; /* need to take reference to avoid possible races */ - if (!atomic_inc_not_zero(&tmp->ct_general.use)) + if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue; if (gc_worker_skip_ct(tmp)) { @@ -1569,7 +1569,7 @@ __nf_conntrack_alloc(struct net *net, /* Because we use RCU lookups, we set ct_general.use to zero before * this is inserted in any list. */ - atomic_set(&ct->ct_general.use, 0); + refcount_set(&ct->ct_general.use, 0); return ct; out: atomic_dec(&cnet->count); @@ -1594,7 +1594,7 @@ void nf_conntrack_free(struct nf_conn *ct) /* A freed object has refcnt == 0, that's * the golden rule for SLAB_TYPESAFE_BY_RCU */ - WARN_ON(atomic_read(&ct->ct_general.use) != 0); + WARN_ON(refcount_read(&ct->ct_general.use) != 0); nf_ct_ext_destroy(ct); kmem_cache_free(nf_conntrack_cachep, ct); @@ -1686,8 +1686,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (!exp) __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); - /* Now it is inserted into the unconfirmed list, bump refcount */ - nf_conntrack_get(&ct->ct_general); + /* Now it is inserted into the unconfirmed list, set refcount to 1. */ + refcount_set(&ct->ct_general.use, 1); nf_ct_add_to_unconfirmed_list(ct); local_bh_enable(); @@ -2300,7 +2300,7 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), return NULL; found: - atomic_inc(&ct->ct_general.use); + refcount_inc(&ct->ct_general.use); spin_unlock(lockp); local_bh_enable(); return ct; diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 1e89b595ecd0..96948e98ec53 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -203,12 +203,12 @@ nf_ct_find_expectation(struct net *net, * about to invoke ->destroy(), or nf_ct_delete() via timeout * or early_drop(). * - * The atomic_inc_not_zero() check tells: If that fails, we + * The refcount_inc_not_zero() check tells: If that fails, we * know that the ct is being destroyed. If it succeeds, we * can be sure the ct cannot disappear underneath. */ if (unlikely(nf_ct_is_dying(exp->master) || - !atomic_inc_not_zero(&exp->master->ct_general.use))) + !refcount_inc_not_zero(&exp->master->ct_general.use))) return NULL; if (exp->flags & NF_CT_EXPECT_PERMANENT) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4f53d9480ed5..13e2e0390c77 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -508,7 +508,7 @@ nla_put_failure: static int ctnetlink_dump_use(struct sk_buff *skb, const struct nf_conn *ct) { - if (nla_put_be32(skb, CTA_USE, htonl(atomic_read(&ct->ct_general.use)))) + if (nla_put_be32(skb, CTA_USE, htonl(refcount_read(&ct->ct_general.use)))) goto nla_put_failure; return 0; @@ -1200,7 +1200,7 @@ restart: ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { if (i < ARRAY_SIZE(nf_ct_evict) && - atomic_inc_not_zero(&ct->ct_general.use)) + refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; continue; } @@ -1748,7 +1748,7 @@ restart: NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct, dying, 0); if (res < 0) { - if (!atomic_inc_not_zero(&ct->ct_general.use)) + if (!refcount_inc_not_zero(&ct->ct_general.use)) continue; cb->args[0] = cpu; cb->args[1] = (unsigned long)ct; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 80f675d884b2..3e1afd10a9b6 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -303,7 +303,7 @@ static int ct_seq_show(struct seq_file *s, void *v) int ret = 0; WARN_ON(!ct); - if (unlikely(!atomic_inc_not_zero(&ct->ct_general.use))) + if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use))) return 0; if (nf_ct_should_gc(ct)) { @@ -370,7 +370,7 @@ static int ct_seq_show(struct seq_file *s, void *v) ct_show_zone(s, ct, NF_CT_DEFAULT_ZONE_DIR); ct_show_delta_time(s, ct); - seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use)); + seq_printf(s, "use=%u\n", refcount_read(&ct->ct_general.use)); if (seq_has_overflowed(s)) goto release; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index ed37bb9b4e58..b90eca7a2f22 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -48,7 +48,7 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct) struct flow_offload *flow; if (unlikely(nf_ct_is_dying(ct) || - !atomic_inc_not_zero(&ct->ct_general.use))) + !refcount_inc_not_zero(&ct->ct_general.use))) return NULL; flow = kzalloc(sizeof(*flow), GFP_ATOMIC); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 3d6d49420db8..2dfc5dae0656 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -349,7 +349,6 @@ static int __net_init synproxy_net_init(struct net *net) goto err2; __set_bit(IPS_CONFIRMED_BIT, &ct->status); - nf_conntrack_get(&ct->ct_general); snet->tmpl = ct; snet->stats = alloc_percpu(struct synproxy_stats); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 99b1de14ff7e..518d96c8c247 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -259,7 +259,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, ct = this_cpu_read(nft_ct_pcpu_template); - if (likely(atomic_read(&ct->ct_general.use) == 1)) { + if (likely(refcount_read(&ct->ct_general.use) == 1)) { nf_ct_zone_add(ct, &zone); } else { /* previous skb got queued to userspace */ @@ -270,7 +270,6 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr, } } - atomic_inc(&ct->ct_general.use); nf_ct_set(skb, ct, IP_CT_NEW); } #endif @@ -375,7 +374,6 @@ static bool nft_ct_tmpl_alloc_pcpu(void) return false; } - atomic_set(&tmp->ct_general.use, 1); per_cpu(nft_ct_pcpu_template, cpu) = tmp; } diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 0a913ce07425..267757b0392a 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -24,7 +24,7 @@ static inline int xt_ct_target(struct sk_buff *skb, struct nf_conn *ct) return XT_CONTINUE; if (ct) { - atomic_inc(&ct->ct_general.use); + refcount_inc(&ct->ct_general.use); nf_ct_set(skb, ct, IP_CT_NEW); } else { nf_ct_set(skb, ct, IP_CT_UNTRACKED); @@ -201,7 +201,6 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par, goto err4; } __set_bit(IPS_CONFIRMED_BIT, &ct->status); - nf_conntrack_get(&ct->ct_general); out: info->ct = ct; return 0; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 1b5eae57bc90..121664e52271 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1716,7 +1716,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, goto err_free_ct; __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status); - nf_conntrack_get(&ct_info.ct->ct_general); return 0; err_free_ct: __ovs_ct_free_action(&ct_info); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index ab1810f2e660..3fa904cf8f27 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1228,7 +1228,6 @@ static int tcf_ct_fill_params(struct net *net, return -ENOMEM; } __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); - nf_conntrack_get(&tmpl->ct_general); p->tmpl = tmpl; return 0; -- cgit v1.2.3 From 3fce16493dc1aa2c9af3d7e7bd360dfe203a3e6a Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 7 Jan 2022 05:03:23 +0100 Subject: netfilter: core: move ip_ct_attach indirection to struct nf_ct_hook ip_ct_attach predates struct nf_ct_hook, we can place it there and remove the exported symbol. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 2 +- net/netfilter/core.c | 19 ++++++++----------- net/netfilter/nf_conntrack_core.c | 4 +--- 3 files changed, 10 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 3fda1a508733..e0e3f3355ab1 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -440,7 +440,6 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include -extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, @@ -463,6 +462,7 @@ struct nf_ct_hook { void (*destroy)(struct nf_conntrack *); bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); + void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); }; extern struct nf_ct_hook __rcu *nf_ct_hook; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 6dec9cd395f1..dc806dc9fe28 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -673,25 +673,22 @@ struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) -/* This does not belong here, but locally generated errors need it if connection - tracking in use: without this, connection may not be in hash table, and hence - manufactured ICMP or RST packets will not be associated with it. */ -void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) - __rcu __read_mostly; -EXPORT_SYMBOL(ip_ct_attach); - struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); +/* This does not belong here, but locally generated errors need it if connection + * tracking in use: without this, connection may not be in hash table, and hence + * manufactured ICMP or RST packets will not be associated with it. + */ void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { - void (*attach)(struct sk_buff *, const struct sk_buff *); + const struct nf_ct_hook *ct_hook; if (skb->_nfct) { rcu_read_lock(); - attach = rcu_dereference(ip_ct_attach); - if (attach) - attach(new, skb); + ct_hook = rcu_dereference(nf_ct_hook); + if (ct_hook) + ct_hook->attach(new, skb); rcu_read_unlock(); } } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 328d359fcabe..89f1e5f0090b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2455,7 +2455,6 @@ static int kill_all(struct nf_conn *i, void *data) void nf_conntrack_cleanup_start(void) { conntrack_gc_work.exiting = true; - RCU_INIT_POINTER(ip_ct_attach, NULL); } void nf_conntrack_cleanup_end(void) @@ -2774,12 +2773,11 @@ static struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, .destroy = destroy_conntrack, .get_tuple_skb = nf_conntrack_get_tuple_skb, + .attach = nf_conntrack_attach, }; void nf_conntrack_init_end(void) { - /* For use by REJECT target */ - RCU_INIT_POINTER(ip_ct_attach, nf_conntrack_attach); RCU_INIT_POINTER(nf_ct_hook, &nf_conntrack_hook); } -- cgit v1.2.3 From 285c8a7a58158cb1805c97ff03875df2ba2ea1fe Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 7 Jan 2022 05:03:24 +0100 Subject: netfilter: make function op structures const No functional changes, these structures should be const. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter.h | 8 ++++---- net/netfilter/core.c | 10 +++++----- net/netfilter/nf_conntrack_core.c | 4 ++-- net/netfilter/nf_conntrack_netlink.c | 4 ++-- net/netfilter/nf_nat_core.c | 2 +- net/netfilter/nfnetlink_queue.c | 8 ++++---- 6 files changed, 18 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index e0e3f3355ab1..15e71bfff726 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -381,13 +381,13 @@ struct nf_nat_hook { enum ip_conntrack_dir dir); }; -extern struct nf_nat_hook __rcu *nf_nat_hook; +extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #if IS_ENABLED(CONFIG_NF_NAT) - struct nf_nat_hook *nat_hook; + const struct nf_nat_hook *nat_hook; rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); @@ -464,7 +464,7 @@ struct nf_ct_hook { const struct sk_buff *); void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); }; -extern struct nf_ct_hook __rcu *nf_ct_hook; +extern const struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; @@ -479,7 +479,7 @@ struct nfnl_ct_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfnl_ct_hook __rcu *nfnl_ct_hook; +extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; /** * nf_skb_duplicated - TEE target has sent a packet diff --git a/net/netfilter/core.c b/net/netfilter/core.c index dc806dc9fe28..354cb472f386 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -666,14 +666,14 @@ EXPORT_SYMBOL(nf_hook_slow_list); /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ -struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; +const struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); -struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; +const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) -struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; +const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); /* This does not belong here, but locally generated errors need it if connection @@ -696,7 +696,7 @@ EXPORT_SYMBOL(nf_ct_attach); void nf_conntrack_destroy(struct nf_conntrack *nfct) { - struct nf_ct_hook *ct_hook; + const struct nf_ct_hook *ct_hook; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); @@ -709,7 +709,7 @@ EXPORT_SYMBOL(nf_conntrack_destroy); bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { - struct nf_ct_hook *ct_hook; + const struct nf_ct_hook *ct_hook; bool ret = false; rcu_read_lock(); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 89f1e5f0090b..cd3d07e418b5 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2085,9 +2085,9 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { + const struct nf_nat_hook *nat_hook; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; - struct nf_nat_hook *nat_hook; unsigned int status; int dataoff; u16 l3num; @@ -2769,7 +2769,7 @@ err_cachep: return ret; } -static struct nf_ct_hook nf_conntrack_hook = { +static const struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, .destroy = destroy_conntrack, .get_tuple_skb = nf_conntrack_get_tuple_skb, diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 13e2e0390c77..01cc69ab0b4e 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1819,7 +1819,7 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, const struct nlattr *attr) __must_hold(RCU) { - struct nf_nat_hook *nat_hook; + const struct nf_nat_hook *nat_hook; int err; nat_hook = rcu_dereference(nf_nat_hook); @@ -2921,7 +2921,7 @@ static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, nf_ct_tcp_seqadj_set(skb, ct, ctinfo, diff); } -static struct nfnl_ct_hook ctnetlink_glue_hook = { +static const struct nfnl_ct_hook ctnetlink_glue_hook = { .build_size = ctnetlink_glue_build_size, .build = ctnetlink_glue_build, .parse = ctnetlink_glue_parse, diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 3dd130487b5b..2d06a66899b2 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1167,7 +1167,7 @@ static struct pernet_operations nat_net_ops = { .size = sizeof(struct nat_net), }; -static struct nf_nat_hook nat_hook = { +static const struct nf_nat_hook nat_hook = { .parse_nat_setup = nfnetlink_parse_nat_setup, #ifdef CONFIG_XFRM .decode_session = __nf_nat_decode_session, diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 08771f47d469..862d8a3a0911 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -225,7 +225,7 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { - struct nf_ct_hook *ct_hook; + const struct nf_ct_hook *ct_hook; int err; if (verdict == NF_ACCEPT || @@ -388,7 +388,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue, struct net_device *outdev; struct nf_conn *ct = NULL; enum ip_conntrack_info ctinfo = 0; - struct nfnl_ct_hook *nfnl_ct; + const struct nfnl_ct_hook *nfnl_ct; bool csum_verify; char *secdata = NULL; u32 seclen = 0; @@ -1103,7 +1103,7 @@ static int nfqnl_recv_verdict_batch(struct sk_buff *skb, return 0; } -static struct nf_conn *nfqnl_ct_parse(struct nfnl_ct_hook *nfnl_ct, +static struct nf_conn *nfqnl_ct_parse(const struct nfnl_ct_hook *nfnl_ct, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[], struct nf_queue_entry *entry, @@ -1170,11 +1170,11 @@ static int nfqnl_recv_verdict(struct sk_buff *skb, const struct nfnl_info *info, { struct nfnl_queue_net *q = nfnl_queue_pernet(info->net); u_int16_t queue_num = ntohs(info->nfmsg->res_id); + const struct nfnl_ct_hook *nfnl_ct; struct nfqnl_msg_verdict_hdr *vhdr; enum ip_conntrack_info ctinfo; struct nfqnl_instance *queue; struct nf_queue_entry *entry; - struct nfnl_ct_hook *nfnl_ct; struct nf_conn *ct = NULL; unsigned int verdict; int err; -- cgit v1.2.3 From 6ae7989c9af0d98ab64196f4f4c6f6499454bd23 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 7 Jan 2022 05:03:25 +0100 Subject: netfilter: conntrack: avoid useless indirection during conntrack destruction nf_ct_put() results in a usesless indirection: nf_ct_put -> nf_conntrack_put -> nf_conntrack_destroy -> rcu readlock + indirect call of ct_hooks->destroy(). There are two _put helpers: nf_ct_put and nf_conntrack_put. The latter is what should be used in code that MUST NOT cause a linker dependency on the conntrack module (e.g. calls from core network stack). Everyone else should call nf_ct_put() instead. A followup patch will convert a few nf_conntrack_put() calls to nf_ct_put(), in particular from modules that already have a conntrack dependency such as act_ct or even nf_conntrack itself. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nf_conntrack_common.h | 2 ++ include/net/netfilter/nf_conntrack.h | 8 ++++++-- net/netfilter/nf_conntrack_core.c | 12 ++++++------ 3 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index a03f7a80b9ab..2770db2fa080 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -29,6 +29,8 @@ struct nf_conntrack { }; void nf_conntrack_destroy(struct nf_conntrack *nfct); + +/* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index a4a14f3a5e38..8731d5bcb47d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -76,6 +76,8 @@ struct nf_conn { * Hint, SKB address this struct and refcnt via skb->_nfct and * helpers nf_conntrack_get() and nf_conntrack_put(). * Helper nf_ct_put() equals nf_conntrack_put() by dec refcnt, + * except that the latter uses internal indirection and does not + * result in a conntrack module dependency. * beware nf_ct_get() is different and don't inc refcnt. */ struct nf_conntrack ct_general; @@ -170,11 +172,13 @@ nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) return (struct nf_conn *)(nfct & NFCT_PTRMASK); } +void nf_ct_destroy(struct nf_conntrack *nfct); + /* decrement reference count on a conntrack */ static inline void nf_ct_put(struct nf_conn *ct) { - WARN_ON(!ct); - nf_conntrack_put(&ct->ct_general); + if (ct && refcount_dec_and_test(&ct->ct_general.use)) + nf_ct_destroy(&ct->ct_general); } /* Protocol module loading */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index cd3d07e418b5..7a2063abae04 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -558,7 +558,7 @@ static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct) #define NFCT_ALIGN(len) (((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK) -/* Released via destroy_conntrack() */ +/* Released via nf_ct_destroy() */ struct nf_conn *nf_ct_tmpl_alloc(struct net *net, const struct nf_conntrack_zone *zone, gfp_t flags) @@ -612,12 +612,11 @@ static void destroy_gre_conntrack(struct nf_conn *ct) #endif } -static void -destroy_conntrack(struct nf_conntrack *nfct) +void nf_ct_destroy(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; - pr_debug("destroy_conntrack(%p)\n", ct); + pr_debug("%s(%p)\n", __func__, ct); WARN_ON(refcount_read(&nfct->use) != 0); if (unlikely(nf_ct_is_template(ct))) { @@ -643,9 +642,10 @@ destroy_conntrack(struct nf_conntrack *nfct) if (ct->master) nf_ct_put(ct->master); - pr_debug("destroy_conntrack: returning ct=%p to slab\n", ct); + pr_debug("%s: returning ct=%p to slab\n", __func__, ct); nf_conntrack_free(ct); } +EXPORT_SYMBOL(nf_ct_destroy); static void nf_ct_delete_from_lists(struct nf_conn *ct) { @@ -2771,7 +2771,7 @@ err_cachep: static const struct nf_ct_hook nf_conntrack_hook = { .update = nf_conntrack_update, - .destroy = destroy_conntrack, + .destroy = nf_ct_destroy, .get_tuple_skb = nf_conntrack_get_tuple_skb, .attach = nf_conntrack_attach, }; -- cgit v1.2.3 From 6316136ec6e3dd1c302f7e7289a9ee46ecc610ae Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 7 Jan 2022 15:46:16 +0100 Subject: netfilter: egress: avoid a lockdep splat include/linux/netfilter_netdev.h:97 suspicious rcu_dereference_check() usage! 2 locks held by sd-resolve/1100: 0: ..(rcu_read_lock_bh){1:3}, at: ip_finish_output2 1: ..(rcu_read_lock_bh){1:3}, at: __dev_queue_xmit __dev_queue_xmit+0 .. The helper has two callers, one uses rcu_read_lock, the other rcu_read_lock_bh(). Annotate the dereference to reflect this. Fixes: 42df6e1d221dd ("netfilter: Introduce egress hook") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_netdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index b71b57a83bb4..b4dd96e4dc8d 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -94,7 +94,7 @@ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, return skb; #endif - e = rcu_dereference(dev->nf_hooks_egress); + e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; -- cgit v1.2.3 From 6f022c2ddbcefaee79502ce5386dfe351d457070 Mon Sep 17 00:00:00 2001 From: Paul Blakey Date: Thu, 6 Jan 2022 17:38:04 +0200 Subject: net: openvswitch: Fix ct_state nat flags for conns arriving from tc Netfilter conntrack maintains NAT flags per connection indicating whether NAT was configured for the connection. Openvswitch maintains NAT flags on the per packet flow key ct_state field, indicating whether NAT was actually executed on the packet. When a packet misses from tc to ovs the conntrack NAT flags are set. However, NAT was not necessarily executed on the packet because the connection's state might still be in NEW state. As such, openvswitch wrongly assumes that NAT was executed and sets an incorrect flow key NAT flags. Fix this, by flagging to openvswitch which NAT was actually done in act_ct via tc_skb_ext and tc_skb_cb to the openvswitch module, so the packet flow key NAT flags will be correctly set. Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct") Signed-off-by: Paul Blakey Acked-by: Jamal Hadi Salim Link: https://lore.kernel.org/r/20220106153804.26451-1-paulb@nvidia.com Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 +++- include/net/pkt_sched.h | 4 +++- net/openvswitch/flow.c | 16 +++++++++++++--- net/sched/act_ct.c | 6 ++++++ net/sched/cls_api.c | 2 ++ 5 files changed, 27 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4507d77d6941..60ab0c2fe567 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -287,7 +287,9 @@ struct tc_skb_ext { __u32 chain; __u16 mru; __u16 zone; - bool post_ct; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; }; #endif diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9e71691c491b..9e7b21c0b3a6 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -197,7 +197,9 @@ struct tc_skb_cb { struct qdisc_skb_cb qdisc_cb; u16 mru; - bool post_ct; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; u16 zone; /* Only valid if post_ct = true */ }; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 6d262d9aa10e..02096f2ec678 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -859,7 +859,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) struct tc_skb_ext *tc_ext; #endif - bool post_ct = false; + bool post_ct = false, post_ct_snat = false, post_ct_dnat = false; int res, err; u16 zone = 0; @@ -900,6 +900,8 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, key->recirc_id = tc_ext ? tc_ext->chain : 0; OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; post_ct = tc_ext ? tc_ext->post_ct : false; + post_ct_snat = post_ct ? tc_ext->post_ct_snat : false; + post_ct_dnat = post_ct ? tc_ext->post_ct_dnat : false; zone = post_ct ? tc_ext->zone : 0; } else { key->recirc_id = 0; @@ -911,8 +913,16 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, err = key_extract(skb, key); if (!err) { ovs_ct_fill_key(skb, key, post_ct); /* Must be after key_extract(). */ - if (post_ct && !skb_get_nfct(skb)) - key->ct_zone = zone; + if (post_ct) { + if (!skb_get_nfct(skb)) { + key->ct_zone = zone; + } else { + if (!post_ct_dnat) + key->ct_state &= ~OVS_CS_F_DST_NAT; + if (!post_ct_snat) + key->ct_state &= ~OVS_CS_F_SRC_NAT; + } + } } return err; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index ab3591408419..2a17eb77c904 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -839,6 +839,12 @@ static int ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, } err = nf_nat_packet(ct, ctinfo, hooknum, skb); + if (err == NF_ACCEPT) { + if (maniptype == NF_NAT_MANIP_SRC) + tc_skb_cb(skb)->post_ct_snat = 1; + if (maniptype == NF_NAT_MANIP_DST) + tc_skb_cb(skb)->post_ct_dnat = 1; + } out: return err; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 35c74bdde848..cc9409aa755e 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1625,6 +1625,8 @@ int tcf_classify(struct sk_buff *skb, ext->chain = last_executed_chain; ext->mru = cb->mru; ext->post_ct = cb->post_ct; + ext->post_ct_snat = cb->post_ct_snat; + ext->post_ct_dnat = cb->post_ct_dnat; ext->zone = cb->zone; } -- cgit v1.2.3 From c504e5c2f9648a1e5c2be01e8c3f59d394192bd3 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 9 Jan 2022 14:36:26 +0800 Subject: net: skb: introduce kfree_skb_reason() Introduce the interface kfree_skb_reason(), which is able to pass the reason why the skb is dropped to 'kfree_skb' tracepoint. Add the 'reason' field to 'trace_kfree_skb', therefor user can get more detail information about abnormal skb with 'drop_monitor' or eBPF. All drop reasons are defined in the enum 'skb_drop_reason', and they will be print as string in 'kfree_skb' tracepoint in format of 'reason: XXX'. ( Maybe the reasons should be defined in a uapi header file, so that user space can use them? ) Signed-off-by: Menglong Dong Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 23 ++++++++++++++++++++++- include/trace/events/skb.h | 36 +++++++++++++++++++++++++++++------- net/core/dev.c | 3 ++- net/core/drop_monitor.c | 10 +++++++--- net/core/skbuff.c | 12 +++++++----- 5 files changed, 67 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 642acb0d1646..ef0870abc791 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -305,6 +305,17 @@ struct sk_buff_head { struct sk_buff; +/* The reason of skb drop, which is used in kfree_skb_reason(). + * en...maybe they should be splited by group? + * + * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is + * used to translate the reason to string. + */ +enum skb_drop_reason { + SKB_DROP_REASON_NOT_SPECIFIED, + SKB_DROP_REASON_MAX, +}; + /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. @@ -1085,8 +1096,18 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } +void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); + +/** + * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason + * @skb: buffer to free + */ +static inline void kfree_skb(struct sk_buff *skb) +{ + kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); +} + void skb_release_head_state(struct sk_buff *skb); -void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 9e92f22eb086..294c61bbe44b 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -9,29 +9,51 @@ #include #include +#define TRACE_SKB_DROP_REASON \ + EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED) \ + EMe(SKB_DROP_REASON_MAX, MAX) + +#undef EM +#undef EMe + +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +TRACE_SKB_DROP_REASON + +#undef EM +#undef EMe +#define EM(a, b) { a, #b }, +#define EMe(a, b) { a, #b } + /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, - TP_PROTO(struct sk_buff *skb, void *location), + TP_PROTO(struct sk_buff *skb, void *location, + enum skb_drop_reason reason), - TP_ARGS(skb, location), + TP_ARGS(skb, location, reason), TP_STRUCT__entry( - __field( void *, skbaddr ) - __field( void *, location ) - __field( unsigned short, protocol ) + __field(void *, skbaddr) + __field(void *, location) + __field(unsigned short, protocol) + __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->protocol = ntohs(skb->protocol); + __entry->reason = reason; ), - TP_printk("skbaddr=%p protocol=%u location=%p", - __entry->skbaddr, __entry->protocol, __entry->location) + TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", + __entry->skbaddr, __entry->protocol, __entry->location, + __print_symbolic(__entry->reason, + TRACE_SKB_DROP_REASON)) ); TRACE_EVENT(consume_skb, diff --git a/net/core/dev.c b/net/core/dev.c index 83a4089990a0..84a0d9542fe9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4899,7 +4899,8 @@ static __latent_entropy void net_tx_action(struct softirq_action *h) if (likely(get_kfree_skb_cb(skb)->reason == SKB_REASON_CONSUMED)) trace_consume_skb(skb); else - trace_kfree_skb(skb, net_tx_action); + trace_kfree_skb(skb, net_tx_action, + SKB_DROP_REASON_NOT_SPECIFIED); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 3d0ab2eec916..7b288a121a41 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -110,7 +110,8 @@ static u32 net_dm_queue_len = 1000; struct net_dm_alert_ops { void (*kfree_skb_probe)(void *ignore, struct sk_buff *skb, - void *location); + void *location, + enum skb_drop_reason reason); void (*napi_poll_probe)(void *ignore, struct napi_struct *napi, int work, int budget); void (*work_item_func)(struct work_struct *work); @@ -262,7 +263,9 @@ out: spin_unlock_irqrestore(&data->lock, flags); } -static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) +static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, + void *location, + enum skb_drop_reason reason) { trace_drop_common(skb, location); } @@ -490,7 +493,8 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = { static void net_dm_packet_trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, - void *location) + void *location, + enum skb_drop_reason reason) { ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *data; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index e514a36bcffc..0118f0afaa4f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -759,21 +759,23 @@ void __kfree_skb(struct sk_buff *skb) EXPORT_SYMBOL(__kfree_skb); /** - * kfree_skb - free an sk_buff + * kfree_skb_reason - free an sk_buff with special reason * @skb: buffer to free + * @reason: reason why this skb is dropped * * Drop a reference to the buffer and free it if the usage count has - * hit zero. + * hit zero. Meanwhile, pass the drop reason to 'kfree_skb' + * tracepoint. */ -void kfree_skb(struct sk_buff *skb) +void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (!skb_unref(skb)) return; - trace_kfree_skb(skb, __builtin_return_address(0)); + trace_kfree_skb(skb, __builtin_return_address(0), reason); __kfree_skb(skb); } -EXPORT_SYMBOL(kfree_skb); +EXPORT_SYMBOL(kfree_skb_reason); void kfree_skb_list(struct sk_buff *segs) { -- cgit v1.2.3 From 85125597419aec3aa7b8f3b8713e415f997796f2 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 9 Jan 2022 14:36:27 +0800 Subject: net: skb: use kfree_skb_reason() in tcp_v4_rcv() Replace kfree_skb() with kfree_skb_reason() in tcp_v4_rcv(). Following drop reasons are added: SKB_DROP_REASON_NO_SOCKET SKB_DROP_REASON_PKT_TOO_SMALL SKB_DROP_REASON_TCP_CSUM SKB_DROP_REASON_TCP_FILTER After this patch, 'kfree_skb' event will print message like this: $ TASK-PID CPU# ||||| TIMESTAMP FUNCTION $ | | | ||||| | | -0 [000] ..s1. 36.113438: kfree_skb: skbaddr=(____ptrval____) protocol=2048 location=(____ptrval____) reason: NO_SOCKET The reason of skb drop is printed too. Signed-off-by: Menglong Dong Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 4 ++++ include/trace/events/skb.h | 4 ++++ net/ipv4/tcp_ipv4.c | 14 +++++++++++--- 3 files changed, 19 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ef0870abc791..c9c97b0d0fe9 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -313,6 +313,10 @@ struct sk_buff; */ enum skb_drop_reason { SKB_DROP_REASON_NOT_SPECIFIED, + SKB_DROP_REASON_NO_SOCKET, + SKB_DROP_REASON_PKT_TOO_SMALL, + SKB_DROP_REASON_TCP_CSUM, + SKB_DROP_REASON_TCP_FILTER, SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 294c61bbe44b..faa7d068a7bc 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -11,6 +11,10 @@ #define TRACE_SKB_DROP_REASON \ EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED) \ + EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ + EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ + EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ + EM(SKB_DROP_REASON_TCP_FILTER, TCP_FILTER) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9861786b8336..b3f34e366b27 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1971,8 +1971,10 @@ int tcp_v4_rcv(struct sk_buff *skb) const struct tcphdr *th; bool refcounted; struct sock *sk; + int drop_reason; int ret; + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -1984,8 +1986,10 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; - if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) + if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; + } if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; @@ -2090,8 +2094,10 @@ process: nf_reset_ct(skb); - if (tcp_filter(sk, skb)) + if (tcp_filter(sk, skb)) { + drop_reason = SKB_DROP_REASON_TCP_FILTER; goto discard_and_relse; + } th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); @@ -2124,6 +2130,7 @@ put_and_return: return ret; no_tcp_socket: + drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; @@ -2131,6 +2138,7 @@ no_tcp_socket: if (tcp_checksum_complete(skb)) { csum_error: + drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: @@ -2141,7 +2149,7 @@ bad_packet: discard_it: /* Discard frame. */ - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; discard_and_relse: -- cgit v1.2.3 From 1c7fab70df085d866a3765955f397ca2b4025b15 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 9 Jan 2022 14:36:28 +0800 Subject: net: skb: use kfree_skb_reason() in __udp4_lib_rcv() Replace kfree_skb() with kfree_skb_reason() in __udp4_lib_rcv. New drop reason 'SKB_DROP_REASON_UDP_CSUM' is added for udp csum error. Signed-off-by: Menglong Dong Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + net/ipv4/udp.c | 10 ++++++++-- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c9c97b0d0fe9..af64c7de9b53 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -317,6 +317,7 @@ enum skb_drop_reason { SKB_DROP_REASON_PKT_TOO_SMALL, SKB_DROP_REASON_TCP_CSUM, SKB_DROP_REASON_TCP_FILTER, + SKB_DROP_REASON_UDP_CSUM, SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index faa7d068a7bc..3e042ca2cedb 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -15,6 +15,7 @@ EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ EM(SKB_DROP_REASON_TCP_FILTER, TCP_FILTER) \ + EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c2a4411d2b04..464590ea922e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2411,6 +2411,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, __be32 saddr, daddr; struct net *net = dev_net(skb->dev); bool refcounted; + int drop_reason; + + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; /* * Validate the packet. @@ -2466,6 +2469,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp_lib_checksum_complete(skb)) goto csum_error; + drop_reason = SKB_DROP_REASON_NO_SOCKET; __UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -2473,10 +2477,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; short_packet: + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; net_dbg_ratelimited("UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), @@ -2489,6 +2494,7 @@ csum_error: * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ + drop_reason = SKB_DROP_REASON_UDP_CSUM; net_dbg_ratelimited("UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", proto == IPPROTO_UDPLITE ? "Lite" : "", &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), @@ -2496,7 +2502,7 @@ csum_error: __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; } -- cgit v1.2.3 From a6b5a28eb56c3f4988f7ff5290b954ba296e309a Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Sat, 14 Nov 2020 13:43:54 -0500 Subject: nfs: Convert to new fscache volume/cookie API Change the nfs filesystem to support fscache's indexing rewrite and reenable caching in nfs. The following changes have been made: (1) The fscache_netfs struct is no more, and there's no need to register the filesystem as a whole. (2) The session cookie is now an fscache_volume cookie, allocated with fscache_acquire_volume(). That takes three parameters: a string representing the "volume" in the index, a string naming the cache to use (or NULL) and a u64 that conveys coherency metadata for the volume. For nfs, I've made it render the volume name string as: "nfs,,,
,,,*<,param>[,]" (3) The fscache_cookie_def is no more and needed information is passed directly to fscache_acquire_cookie(). The cache no longer calls back into the filesystem, but rather metadata changes are indicated at other times. fscache_acquire_cookie() is passed the same keying and coherency information as before. (4) fscache_enable/disable_cookie() have been removed. Call fscache_use_cookie() and fscache_unuse_cookie() when a file is opened or closed to prevent a cache file from being culled and to keep resources to hand that are needed to do I/O. If a file is opened for writing, we invalidate it with FSCACHE_INVAL_DIO_WRITE in lieu of doing writeback to the cache, thereby making it cease caching until all currently open files are closed. This should give the same behaviour as the uptream code. Making the cache store local modifications isn't straightforward for NFS, so that's left for future patches. (5) fscache_invalidate() now needs to be given uptodate auxiliary data and a file size. It also takes a flag to indicate if this was due to a DIO write. (6) Call nfs_fscache_invalidate() with FSCACHE_INVAL_DIO_WRITE on a file to which a DIO write is made. (7) Call fscache_note_page_release() from nfs_release_page(). (8) Use a killable wait in nfs_vm_page_mkwrite() when waiting for PG_fscache to be cleared. (9) The functions to read and write data to/from the cache are stubbed out pending a conversion to use netfslib. Changes ======= ver #3: - Added missing =n fallback for nfs_fscache_release_file()[1][2]. ver #2: - Use gfpflags_allow_blocking() rather than using flag directly. - fscache_acquire_volume() now returns errors. - Remove NFS_INO_FSCACHE as it's no longer used. - Need to unuse a cookie on file-release, not inode-clear. Signed-off-by: Dave Wysochanski Co-developed-by: David Howells Signed-off-by: David Howells Tested-by: Dave Wysochanski Acked-by: Jeff Layton cc: Trond Myklebust cc: Anna Schumaker cc: linux-nfs@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/202112100804.nksO8K4u-lkp@intel.com/ [1] Link: https://lore.kernel.org/r/202112100957.2oEDT20W-lkp@intel.com/ [2] Link: https://lore.kernel.org/r/163819668938.215744.14448852181937731615.stgit@warthog.procyon.org.uk/ # v1 Link: https://lore.kernel.org/r/163906979003.143852.2601189243864854724.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967182112.1823006.7791504655391213379.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021575950.640689.12069642327533368467.stgit@warthog.procyon.org.uk/ # v4 --- fs/nfs/Kconfig | 2 +- fs/nfs/Makefile | 2 +- fs/nfs/client.c | 4 - fs/nfs/direct.c | 2 + fs/nfs/file.c | 13 +- fs/nfs/fscache-index.c | 140 --------------- fs/nfs/fscache.c | 434 +++++++++++----------------------------------- fs/nfs/fscache.h | 127 ++++---------- fs/nfs/inode.c | 11 +- fs/nfs/nfstrace.h | 1 - fs/nfs/super.c | 28 +-- fs/nfs/write.c | 1 + include/linux/nfs_fs.h | 1 - include/linux/nfs_fs_sb.h | 9 +- 14 files changed, 172 insertions(+), 603 deletions(-) delete mode 100644 fs/nfs/fscache-index.c (limited to 'include/linux') diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index bdc11b89eac5..14a72224b657 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -170,7 +170,7 @@ config ROOT_NFS config NFS_FSCACHE bool "Provide NFS client caching support" - depends on NFS_FS=m && FSCACHE_OLD_API || NFS_FS=y && FSCACHE_OLD_API=y + depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y help Say Y here if you want NFS data to be cached locally on disc through the general filesystem cache manager diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 22d11fdc6deb..5f6db37f461e 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,7 +12,7 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ export.o sysfs.o fs_context.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o -nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +nfs-$(CONFIG_NFS_FSCACHE) += fscache.o obj-$(CONFIG_NFS_V2) += nfsv2.o nfsv2-y := nfs2super.o proc.o nfs2xdr.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 1e4dc1ab9312..8d8b85b5a641 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -183,8 +183,6 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) clp->cl_net = get_net(cl_init->net); clp->cl_principal = "*"; - nfs_fscache_get_client_cookie(clp); - return clp; error_cleanup: @@ -238,8 +236,6 @@ static void pnfs_init_server(struct nfs_server *server) */ void nfs_free_client(struct nfs_client *clp) { - nfs_fscache_release_client_cookie(clp); - /* -EIO all pending I/O */ if (!IS_ERR(clp->cl_rpcclient)) rpc_shutdown_client(clp->cl_rpcclient); diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 9cff8709c80a..eabfdab543c8 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -59,6 +59,7 @@ #include "internal.h" #include "iostat.h" #include "pnfs.h" +#include "fscache.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -959,6 +960,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter) } else { result = requested; } + nfs_fscache_invalidate(inode, FSCACHE_INVAL_DIO_WRITE); out_release: nfs_direct_req_release(dreq); out: diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 24e7dccce355..76d76acbc594 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -84,6 +84,7 @@ nfs_file_release(struct inode *inode, struct file *filp) nfs_inc_stats(inode, NFSIOS_VFSRELEASE); nfs_file_clear_open_context(filp); + nfs_fscache_release_file(inode, filp); return 0; } EXPORT_SYMBOL_GPL(nfs_file_release); @@ -415,8 +416,7 @@ static void nfs_invalidate_page(struct page *page, unsigned int offset, return; /* Cancel any unstarted writes on this page */ nfs_wb_page_cancel(page_file_mapping(page)->host, page); - - nfs_fscache_invalidate_page(page, page->mapping->host); + wait_on_page_fscache(page); } /* @@ -475,12 +475,11 @@ static void nfs_check_dirty_writeback(struct page *page, static int nfs_launder_page(struct page *page) { struct inode *inode = page_file_mapping(page)->host; - struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n", inode->i_ino, (long long)page_offset(page)); - nfs_fscache_wait_on_page_write(nfsi, page); + wait_on_page_fscache(page); return nfs_wb_page(inode, page); } @@ -555,7 +554,11 @@ static vm_fault_t nfs_vm_page_mkwrite(struct vm_fault *vmf) sb_start_pagefault(inode->i_sb); /* make sure the cache has finished storing the page */ - nfs_fscache_wait_on_page_write(NFS_I(inode), page); + if (PageFsCache(page) && + wait_on_page_fscache_killable(vmf->page) < 0) { + ret = VM_FAULT_RETRY; + goto out; + } wait_on_bit_action(&NFS_I(inode)->flags, NFS_INO_INVALIDATING, nfs_wait_bit_killable, TASK_KILLABLE); diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c deleted file mode 100644 index 573b1da9342c..000000000000 --- a/fs/nfs/fscache-index.c +++ /dev/null @@ -1,140 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* NFS FS-Cache index structure definition - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - */ - -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" -#include "fscache.h" - -#define NFSDBG_FACILITY NFSDBG_FSCACHE - -/* - * Define the NFS filesystem for FS-Cache. Upon registration FS-Cache sticks - * the cookie for the top-level index object for NFS into here. The top-level - * index can than have other cache objects inserted into it. - */ -struct fscache_netfs nfs_fscache_netfs = { - .name = "nfs", - .version = 0, -}; - -/* - * Register NFS for caching - */ -int nfs_fscache_register(void) -{ - return fscache_register_netfs(&nfs_fscache_netfs); -} - -/* - * Unregister NFS for caching - */ -void nfs_fscache_unregister(void) -{ - fscache_unregister_netfs(&nfs_fscache_netfs); -} - -/* - * Define the server object for FS-Cache. This is used to describe a server - * object to fscache_acquire_cookie(). It is keyed by the NFS protocol and - * server address parameters. - */ -const struct fscache_cookie_def nfs_fscache_server_index_def = { - .name = "NFS.server", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Define the superblock object for FS-Cache. This is used to describe a - * superblock object to fscache_acquire_cookie(). It is keyed by all the NFS - * parameters that might cause a separate superblock. - */ -const struct fscache_cookie_def nfs_fscache_super_index_def = { - .name = "NFS.super", - .type = FSCACHE_COOKIE_TYPE_INDEX, -}; - -/* - * Consult the netfs about the state of an object - * - This function can be absent if the index carries no state data - * - The netfs data from the cookie being used as the target is - * presented, as is the auxiliary data - */ -static -enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, - const void *data, - uint16_t datalen, - loff_t object_size) -{ - struct nfs_fscache_inode_auxdata auxdata; - struct nfs_inode *nfsi = cookie_netfs_data; - - if (datalen != sizeof(auxdata)) - return FSCACHE_CHECKAUX_OBSOLETE; - - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); - - if (memcmp(data, &auxdata, datalen) != 0) - return FSCACHE_CHECKAUX_OBSOLETE; - - return FSCACHE_CHECKAUX_OKAY; -} - -/* - * Get an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - * - The read context is passed back to NFS in the event that a data read on the - * cache fails with EIO - in which case the server must be contacted to - * retrieve the data, which requires the read context for security. - */ -static void nfs_fh_get_context(void *cookie_netfs_data, void *context) -{ - get_nfs_open_context(context); -} - -/* - * Release an extra reference on a read context. - * - This function can be absent if the completion function doesn't require a - * context. - */ -static void nfs_fh_put_context(void *cookie_netfs_data, void *context) -{ - if (context) - put_nfs_open_context(context); -} - -/* - * Define the inode object for FS-Cache. This is used to describe an inode - * object to fscache_acquire_cookie(). It is keyed by the NFS file handle for - * an inode. - * - * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime - * held in the cache auxiliary data for the data storage object with those in - * the inode struct in memory. - */ -const struct fscache_cookie_def nfs_fscache_inode_object_def = { - .name = "NFS.fh", - .type = FSCACHE_COOKIE_TYPE_DATAFILE, - .check_aux = nfs_fscache_inode_check_aux, - .get_context = nfs_fh_get_context, - .put_context = nfs_fh_put_context, -}; diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index d743629e05e1..fac6438477a0 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -22,24 +22,18 @@ #define NFSDBG_FACILITY NFSDBG_FSCACHE -static struct rb_root nfs_fscache_keys = RB_ROOT; -static DEFINE_SPINLOCK(nfs_fscache_keys_lock); +#define NFS_MAX_KEY_LEN 1000 -/* - * Layout of the key for an NFS server cache object. - */ -struct nfs_server_key { - struct { - uint16_t nfsversion; /* NFS protocol version */ - uint32_t minorversion; /* NFSv4 minor version */ - uint16_t family; /* address family */ - __be16 port; /* IP port */ - } hdr; - union { - struct in_addr ipv4_addr; /* IPv4 address */ - struct in6_addr ipv6_addr; /* IPv6 address */ - }; -} __packed; +static bool nfs_append_int(char *key, int *_len, unsigned long long x) +{ + if (*_len > NFS_MAX_KEY_LEN) + return false; + if (x == 0) + key[(*_len)++] = ','; + else + *_len += sprintf(key + *_len, ",%llx", x); + return true; +} /* * Get the per-client index cookie for an NFS client if the appropriate mount @@ -47,160 +41,108 @@ struct nfs_server_key { * - We always try and get an index cookie for the client, but get filehandle * cookies on a per-superblock basis, depending on the mount flags */ -void nfs_fscache_get_client_cookie(struct nfs_client *clp) +static bool nfs_fscache_get_client_key(struct nfs_client *clp, + char *key, int *_len) { const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr; const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr; - struct nfs_server_key key; - uint16_t len = sizeof(key.hdr); - memset(&key, 0, sizeof(key)); - key.hdr.nfsversion = clp->rpc_ops->version; - key.hdr.minorversion = clp->cl_minorversion; - key.hdr.family = clp->cl_addr.ss_family; + *_len += snprintf(key + *_len, NFS_MAX_KEY_LEN - *_len, + ",%u.%u,%x", + clp->rpc_ops->version, + clp->cl_minorversion, + clp->cl_addr.ss_family); switch (clp->cl_addr.ss_family) { case AF_INET: - key.hdr.port = sin->sin_port; - key.ipv4_addr = sin->sin_addr; - len += sizeof(key.ipv4_addr); - break; + if (!nfs_append_int(key, _len, sin->sin_port) || + !nfs_append_int(key, _len, sin->sin_addr.s_addr)) + return false; + return true; case AF_INET6: - key.hdr.port = sin6->sin6_port; - key.ipv6_addr = sin6->sin6_addr; - len += sizeof(key.ipv6_addr); - break; + if (!nfs_append_int(key, _len, sin6->sin6_port) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[0]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[1]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[2]) || + !nfs_append_int(key, _len, sin6->sin6_addr.s6_addr32[3])) + return false; + return true; default: printk(KERN_WARNING "NFS: Unknown network family '%d'\n", clp->cl_addr.ss_family); - clp->fscache = NULL; - return; + return false; } - - /* create a cache index for looking up filehandles */ - clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index, - &nfs_fscache_server_index_def, - &key, len, - NULL, 0, - clp, 0, true); - dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n", - clp, clp->fscache); -} - -/* - * Dispose of a per-client cookie - */ -void nfs_fscache_release_client_cookie(struct nfs_client *clp) -{ - dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n", - clp, clp->fscache); - - fscache_relinquish_cookie(clp->fscache, NULL, false); - clp->fscache = NULL; } /* - * Get the cache cookie for an NFS superblock. We have to handle - * uniquification here because the cache doesn't do it for us. + * Get the cache cookie for an NFS superblock. * * The default uniquifier is just an empty string, but it may be overridden * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent * superblock across an automount point of some nature. */ -void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) +int nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen) { - struct nfs_fscache_key *key, *xkey; + struct fscache_volume *vcookie; struct nfs_server *nfss = NFS_SB(sb); - struct rb_node **p, *parent; - int diff; + unsigned int len = 3; + char *key; - nfss->fscache_key = NULL; - nfss->fscache = NULL; - if (!uniq) { - uniq = ""; - ulen = 1; + if (uniq) { + nfss->fscache_uniq = kmemdup_nul(uniq, ulen, GFP_KERNEL); + if (!nfss->fscache_uniq) + return -ENOMEM; } - key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL); + key = kmalloc(NFS_MAX_KEY_LEN + 24, GFP_KERNEL); if (!key) - return; - - key->nfs_client = nfss->nfs_client; - key->key.super.s_flags = sb->s_flags & NFS_SB_MASK; - key->key.nfs_server.flags = nfss->flags; - key->key.nfs_server.rsize = nfss->rsize; - key->key.nfs_server.wsize = nfss->wsize; - key->key.nfs_server.acregmin = nfss->acregmin; - key->key.nfs_server.acregmax = nfss->acregmax; - key->key.nfs_server.acdirmin = nfss->acdirmin; - key->key.nfs_server.acdirmax = nfss->acdirmax; - key->key.nfs_server.fsid = nfss->fsid; - key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor; - - key->key.uniq_len = ulen; - memcpy(key->key.uniquifier, uniq, ulen); - - spin_lock(&nfs_fscache_keys_lock); - p = &nfs_fscache_keys.rb_node; - parent = NULL; - while (*p) { - parent = *p; - xkey = rb_entry(parent, struct nfs_fscache_key, node); - - if (key->nfs_client < xkey->nfs_client) - goto go_left; - if (key->nfs_client > xkey->nfs_client) - goto go_right; - - diff = memcmp(&key->key, &xkey->key, sizeof(key->key)); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - - if (key->key.uniq_len == 0) - goto non_unique; - diff = memcmp(key->key.uniquifier, - xkey->key.uniquifier, - key->key.uniq_len); - if (diff < 0) - goto go_left; - if (diff > 0) - goto go_right; - goto non_unique; - - go_left: - p = &(*p)->rb_left; - continue; - go_right: - p = &(*p)->rb_right; + return -ENOMEM; + + memcpy(key, "nfs", 3); + if (!nfs_fscache_get_client_key(nfss->nfs_client, key, &len) || + !nfs_append_int(key, &len, nfss->fsid.major) || + !nfs_append_int(key, &len, nfss->fsid.minor) || + !nfs_append_int(key, &len, sb->s_flags & NFS_SB_MASK) || + !nfs_append_int(key, &len, nfss->flags) || + !nfs_append_int(key, &len, nfss->rsize) || + !nfs_append_int(key, &len, nfss->wsize) || + !nfs_append_int(key, &len, nfss->acregmin) || + !nfs_append_int(key, &len, nfss->acregmax) || + !nfs_append_int(key, &len, nfss->acdirmin) || + !nfs_append_int(key, &len, nfss->acdirmax) || + !nfs_append_int(key, &len, nfss->client->cl_auth->au_flavor)) + goto out; + + if (ulen > 0) { + if (ulen > NFS_MAX_KEY_LEN - len) + goto out; + key[len++] = ','; + memcpy(key + len, uniq, ulen); + len += ulen; } - - rb_link_node(&key->node, parent, p); - rb_insert_color(&key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - nfss->fscache_key = key; + key[len] = 0; /* create a cache index for looking up filehandles */ - nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache, - &nfs_fscache_super_index_def, - &key->key, - sizeof(key->key) + ulen, - NULL, 0, - nfss, 0, true); + vcookie = fscache_acquire_volume(key, + NULL, /* preferred_cache */ + NULL, 0 /* coherency_data */); dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", - nfss, nfss->fscache); - return; + nfss, vcookie); + if (IS_ERR(vcookie)) { + if (vcookie != ERR_PTR(-EBUSY)) { + kfree(key); + return PTR_ERR(vcookie); + } + pr_err("NFS: Cache volume key already in use (%s)\n", key); + vcookie = NULL; + } + nfss->fscache = vcookie; -non_unique: - spin_unlock(&nfs_fscache_keys_lock); +out: kfree(key); - nfss->fscache_key = NULL; - nfss->fscache = NULL; - printk(KERN_WARNING "NFS:" - " Cache request denied due to non-unique superblock keys\n"); + return 0; } /* @@ -213,29 +155,9 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n", nfss, nfss->fscache); - fscache_relinquish_cookie(nfss->fscache, NULL, false); + fscache_relinquish_volume(nfss->fscache, NULL, false); nfss->fscache = NULL; - - if (nfss->fscache_key) { - spin_lock(&nfs_fscache_keys_lock); - rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys); - spin_unlock(&nfs_fscache_keys_lock); - kfree(nfss->fscache_key); - nfss->fscache_key = NULL; - } -} - -static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, - struct nfs_inode *nfsi) -{ - memset(auxdata, 0, sizeof(*auxdata)); - auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); + kfree(nfss->fscache_uniq); } /* @@ -254,10 +176,12 @@ void nfs_fscache_init_inode(struct inode *inode) nfs_fscache_update_auxdata(&auxdata, nfsi); nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, - &nfs_fscache_inode_object_def, - nfsi->fh.data, nfsi->fh.size, - &auxdata, sizeof(auxdata), - nfsi, nfsi->vfs_inode.i_size, false); + 0, + nfsi->fh.data, /* index_key */ + nfsi->fh.size, + &auxdata, /* aux_data */ + sizeof(auxdata), + i_size_read(&nfsi->vfs_inode)); } /* @@ -265,24 +189,15 @@ void nfs_fscache_init_inode(struct inode *inode) */ void nfs_fscache_clear_inode(struct inode *inode) { - struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); - nfs_fscache_update_auxdata(&auxdata, nfsi); - fscache_relinquish_cookie(cookie, &auxdata, false); + fscache_relinquish_cookie(cookie, false); nfsi->fscache = NULL; } -static bool nfs_fscache_can_enable(void *data) -{ - struct inode *inode = data; - - return !inode_is_open_for_write(inode); -} - /* * Enable or disable caching for a file that is being opened as appropriate. * The cookie is allocated when the inode is initialised, but is not enabled at @@ -307,93 +222,31 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp) struct nfs_fscache_inode_auxdata auxdata; struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); + bool open_for_write = inode_is_open_for_write(inode); if (!fscache_cookie_valid(cookie)) return; - nfs_fscache_update_auxdata(&auxdata, nfsi); - - if (inode_is_open_for_write(inode)) { + fscache_use_cookie(cookie, open_for_write); + if (open_for_write) { dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); - clear_bit(NFS_INO_FSCACHE, &nfsi->flags); - fscache_disable_cookie(cookie, &auxdata, true); - fscache_uncache_all_inode_pages(cookie, inode); - } else { - dfprintk(FSCACHE, "NFS: nfsi 0x%p enabling cache\n", nfsi); - fscache_enable_cookie(cookie, &auxdata, nfsi->vfs_inode.i_size, - nfs_fscache_can_enable, inode); - if (fscache_cookie_enabled(cookie)) - set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags); + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_invalidate(cookie, &auxdata, i_size_read(inode), + FSCACHE_INVAL_DIO_WRITE); } } EXPORT_SYMBOL_GPL(nfs_fscache_open_file); -/* - * Release the caching state associated with a page, if the page isn't busy - * interacting with the cache. - * - Returns true (can release page) or false (page busy). - */ -int nfs_fscache_release_page(struct page *page, gfp_t gfp) -{ - if (PageFsCache(page)) { - struct fscache_cookie *cookie = nfs_i_fscache(page->mapping->host); - - BUG_ON(!cookie); - dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(page->mapping->host)); - - if (!fscache_maybe_release_page(cookie, page, gfp)) - return 0; - - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); - } - - return 1; -} - -/* - * Release the caching state associated with a page if undergoing complete page - * invalidation. - */ -void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode) +void nfs_fscache_release_file(struct inode *inode, struct file *filp) { + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); struct fscache_cookie *cookie = nfs_i_fscache(inode); - BUG_ON(!cookie); - - dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n", - cookie, page, NFS_I(inode)); - - fscache_wait_on_page_write(cookie, page); - - BUG_ON(!PageLocked(page)); - fscache_uncache_page(cookie, page); - nfs_inc_fscache_stats(page->mapping->host, - NFSIOS_FSCACHE_PAGES_UNCACHED); -} - -/* - * Handle completion of a page being read from the cache. - * - Called in process (keventd) context. - */ -static void nfs_readpage_from_fscache_complete(struct page *page, - void *context, - int error) -{ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n", - page, context, error); - - /* - * If the read completes with an error, mark the page with PG_checked, - * unlock the page, and let the VM reissue the readpage. - */ - if (!error) - SetPageUptodate(page); - else - SetPageChecked(page); - unlock_page(page); + if (fscache_cookie_valid(cookie)) { + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_unuse_cookie(cookie, &auxdata, NULL); + } } /* @@ -402,8 +255,6 @@ static void nfs_readpage_from_fscache_complete(struct page *page, int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, struct inode *inode, struct page *page) { - int ret; - dfprintk(FSCACHE, "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", nfs_i_fscache(inode), page, page->index, page->flags, inode); @@ -413,31 +264,7 @@ int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, return 1; } - ret = fscache_read_or_alloc_page(nfs_i_fscache(inode), - page, - nfs_readpage_from_fscache_complete, - ctx, - GFP_KERNEL); - - switch (ret) { - case 0: /* read BIO submitted (page in fscache) */ - dfprintk(FSCACHE, - "NFS: readpage_from_fscache: BIO submitted\n"); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); - return ret; - - case -ENOBUFS: /* inode not in cache */ - case -ENODATA: /* page not in cache */ - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - dfprintk(FSCACHE, - "NFS: readpage_from_fscache %d\n", ret); - return 1; - - default: - dfprintk(FSCACHE, "NFS: readpage_from_fscache %d\n", ret); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); - } - return ret; + return -ENOBUFS; // TODO: Use netfslib } /* @@ -449,45 +276,10 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, struct list_head *pages, unsigned *nr_pages) { - unsigned npages = *nr_pages; - int ret; - dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", - nfs_i_fscache(inode), npages, inode); - - ret = fscache_read_or_alloc_pages(nfs_i_fscache(inode), - mapping, pages, nr_pages, - nfs_readpage_from_fscache_complete, - ctx, - mapping_gfp_mask(mapping)); - if (*nr_pages < npages) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, - npages); - if (*nr_pages > 0) - nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, - *nr_pages); - - switch (ret) { - case 0: /* read submitted to the cache for all pages */ - BUG_ON(!list_empty(pages)); - BUG_ON(*nr_pages != 0); - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: submitted\n"); - - return ret; - - case -ENOBUFS: /* some pages aren't cached and can't be */ - case -ENODATA: /* some pages aren't cached */ - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: no page: %d\n", ret); - return 1; + nfs_i_fscache(inode), *nr_pages, inode); - default: - dfprintk(FSCACHE, - "NFS: nfs_getpages_from_fscache: ret %d\n", ret); - } - - return ret; + return -ENOBUFS; // TODO: Use netfslib } /* @@ -496,25 +288,9 @@ int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, */ void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) { - int ret; - dfprintk(FSCACHE, "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", nfs_i_fscache(inode), page, page->index, page->flags, sync); - ret = fscache_write_page(nfs_i_fscache(inode), page, - inode->i_size, GFP_KERNEL); - dfprintk(FSCACHE, - "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", - page, page->index, page->flags, ret); - - if (ret != 0) { - fscache_uncache_page(nfs_i_fscache(inode), page); - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); - nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); - } else { - nfs_inc_fscache_stats(inode, - NFSIOS_FSCACHE_PAGES_WRITTEN_OK); - } + return; // TODO: Use netfslib } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 6754c8607230..0fa267243d26 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -12,46 +12,10 @@ #include #include #include +#include #ifdef CONFIG_NFS_FSCACHE -/* - * set of NFS FS-Cache objects that form a superblock key - */ -struct nfs_fscache_key { - struct rb_node node; - struct nfs_client *nfs_client; /* the server */ - - /* the elements of the unique key - as used by nfs_compare_super() and - * nfs_compare_mount_options() to distinguish superblocks */ - struct { - struct { - unsigned long s_flags; /* various flags - * (& NFS_MS_MASK) */ - } super; - - struct { - struct nfs_fsid fsid; - int flags; - unsigned int rsize; /* read size */ - unsigned int wsize; /* write size */ - unsigned int acregmin; /* attr cache timeouts */ - unsigned int acregmax; - unsigned int acdirmin; - unsigned int acdirmax; - } nfs_server; - - struct { - rpc_authflavor_t au_flavor; - } rpc_auth; - - /* uniquifier - can be used if nfs_server.flags includes - * NFS_MOUNT_UNSHARED */ - u8 uniq_len; - char uniquifier[0]; - } key; -}; - /* * Definition of the auxiliary data attached to NFS inode storage objects * within the cache. @@ -69,32 +33,18 @@ struct nfs_fscache_inode_auxdata { u64 change_attr; }; -/* - * fscache-index.c - */ -extern struct fscache_netfs nfs_fscache_netfs; -extern const struct fscache_cookie_def nfs_fscache_server_index_def; -extern const struct fscache_cookie_def nfs_fscache_super_index_def; -extern const struct fscache_cookie_def nfs_fscache_inode_object_def; - -extern int nfs_fscache_register(void); -extern void nfs_fscache_unregister(void); - /* * fscache.c */ -extern void nfs_fscache_get_client_cookie(struct nfs_client *); -extern void nfs_fscache_release_client_cookie(struct nfs_client *); - -extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int); +extern int nfs_fscache_get_super_cookie(struct super_block *, const char *, int); extern void nfs_fscache_release_super_cookie(struct super_block *); extern void nfs_fscache_init_inode(struct inode *); extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); +extern void nfs_fscache_release_file(struct inode *, struct file *); extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); -extern int nfs_fscache_release_page(struct page *, gfp_t); extern int __nfs_readpage_from_fscache(struct nfs_open_context *, struct inode *, struct page *); @@ -103,25 +53,17 @@ extern int __nfs_readpages_from_fscache(struct nfs_open_context *, struct list_head *, unsigned *); extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); -/* - * wait for a page to complete writing to the cache - */ -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) -{ - if (PageFsCache(page)) - fscache_wait_on_page_write(nfsi->fscache, page); -} - -/* - * release the caching state associated with a page if undergoing complete page - * invalidation - */ -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) +static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { - if (PageFsCache(page)) - __nfs_fscache_invalidate_page(page, inode); + if (PageFsCache(page)) { + if (!gfpflags_allow_blocking(gfp) || !(gfp & __GFP_FS)) + return false; + wait_on_page_fscache(page); + fscache_note_page_release(nfs_i_fscache(page->mapping->host)); + nfs_inc_fscache_stats(page->mapping->host, + NFSIOS_FSCACHE_PAGES_UNCACHED); + } + return true; } /* @@ -163,20 +105,32 @@ static inline void nfs_readpage_to_fscache(struct inode *inode, __nfs_readpage_to_fscache(inode, page, sync); } -/* - * Invalidate the contents of fscache for this inode. This will not sleep. - */ -static inline void nfs_fscache_invalidate(struct inode *inode) +static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, + struct nfs_inode *nfsi) { - fscache_invalidate(NFS_I(inode)->fscache); + memset(auxdata, 0, sizeof(*auxdata)); + auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; + auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; + auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; + auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + + if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) + auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); } /* - * Wait for an object to finish being invalidated. + * Invalidate the contents of fscache for this inode. This will not sleep. */ -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) { - fscache_wait_on_invalidate(NFS_I(inode)->fscache); + struct nfs_fscache_inode_auxdata auxdata; + struct nfs_inode *nfsi = NFS_I(inode); + + if (nfsi->fscache) { + nfs_fscache_update_auxdata(&auxdata, nfsi); + fscache_invalidate(nfsi->fscache, &auxdata, + i_size_read(&nfsi->vfs_inode), flags); + } } /* @@ -190,28 +144,18 @@ static inline const char *nfs_server_fscache_state(struct nfs_server *server) } #else /* CONFIG_NFS_FSCACHE */ -static inline int nfs_fscache_register(void) { return 0; } -static inline void nfs_fscache_unregister(void) {} - -static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {} -static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {} - static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {} static inline void nfs_fscache_init_inode(struct inode *inode) {} static inline void nfs_fscache_clear_inode(struct inode *inode) {} static inline void nfs_fscache_open_file(struct inode *inode, struct file *filp) {} +static inline void nfs_fscache_release_file(struct inode *inode, struct file *file) {} static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { return 1; /* True: may release page */ } -static inline void nfs_fscache_invalidate_page(struct page *page, - struct inode *inode) {} -static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi, - struct page *page) {} - static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, struct inode *inode, struct page *page) @@ -230,8 +174,7 @@ static inline void nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) {} -static inline void nfs_fscache_invalidate(struct inode *inode) {} -static inline void nfs_fscache_wait_on_invalidate(struct inode *inode) {} +static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} static inline const char *nfs_server_fscache_state(struct nfs_server *server) { diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index fda530d5e764..a918c3a834b6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -209,7 +209,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags) if (!nfs_has_xattr_cache(nfsi)) flags &= ~NFS_INO_INVALID_XATTR; if (flags & NFS_INO_INVALID_DATA) - nfs_fscache_invalidate(inode); + nfs_fscache_invalidate(inode, 0); flags &= ~(NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED); nfsi->cache_validity |= flags; @@ -1289,6 +1289,7 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map { int ret; + nfs_fscache_invalidate(inode, 0); if (mapping->nrpages != 0) { if (S_ISREG(inode->i_mode)) { ret = nfs_sync_mapping(mapping); @@ -1300,7 +1301,6 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map return ret; } nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); - nfs_fscache_wait_on_invalidate(inode); dfprintk(PAGECACHE, "NFS: (%s/%Lu) data cache invalidated\n", inode->i_sb->s_id, @@ -2374,10 +2374,6 @@ static int __init init_nfs_fs(void) if (err < 0) goto out9; - err = nfs_fscache_register(); - if (err < 0) - goto out8; - err = nfsiod_start(); if (err) goto out7; @@ -2429,8 +2425,6 @@ out5: out6: nfsiod_stop(); out7: - nfs_fscache_unregister(); -out8: unregister_pernet_subsys(&nfs_net_ops); out9: nfs_sysfs_exit(); @@ -2445,7 +2439,6 @@ static void __exit exit_nfs_fs(void) nfs_destroy_readpagecache(); nfs_destroy_inodecache(); nfs_destroy_nfspagecache(); - nfs_fscache_unregister(); unregister_pernet_subsys(&nfs_net_ops); rpc_proc_unregister(&init_net, "nfs"); unregister_nfs_fs(); diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index b3aee261801e..317ce27bdc4b 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -42,7 +42,6 @@ { BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \ { BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \ { BIT(NFS_INO_FSCACHE), "FSCACHE" }, \ - { BIT(NFS_INO_FSCACHE_LOCK), "FSCACHE_LOCK" }, \ { BIT(NFS_INO_LAYOUTCOMMIT), "NEED_LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTCOMMITTING), "LAYOUTCOMMIT" }, \ { BIT(NFS_INO_LAYOUTSTATS), "LAYOUTSTATS" }, \ diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3aced401735c..6ab5eeb000dc 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1204,42 +1204,42 @@ static int nfs_compare_super(struct super_block *sb, struct fs_context *fc) } #ifdef CONFIG_NFS_FSCACHE -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { struct nfs_server *nfss = NFS_SB(sb); char *uniq = NULL; int ulen = 0; - nfss->fscache_key = NULL; nfss->fscache = NULL; if (!ctx) - return; + return 0; if (ctx->clone_data.sb) { struct nfs_server *mnt_s = NFS_SB(ctx->clone_data.sb); if (!(mnt_s->options & NFS_OPTION_FSCACHE)) - return; - if (mnt_s->fscache_key) { - uniq = mnt_s->fscache_key->key.uniquifier; - ulen = mnt_s->fscache_key->key.uniq_len; + return 0; + if (mnt_s->fscache_uniq) { + uniq = mnt_s->fscache_uniq; + ulen = strlen(uniq); } } else { if (!(ctx->options & NFS_OPTION_FSCACHE)) - return; + return 0; if (ctx->fscache_uniq) { uniq = ctx->fscache_uniq; ulen = strlen(ctx->fscache_uniq); } } - nfs_fscache_get_super_cookie(sb, uniq, ulen); + return nfs_fscache_get_super_cookie(sb, uniq, ulen); } #else -static void nfs_get_cache_cookie(struct super_block *sb, - struct nfs_fs_context *ctx) +static int nfs_get_cache_cookie(struct super_block *sb, + struct nfs_fs_context *ctx) { + return 0; } #endif @@ -1299,7 +1299,9 @@ int nfs_get_tree_common(struct fs_context *fc) s->s_blocksize_bits = bsize; s->s_blocksize = 1U << bsize; } - nfs_get_cache_cookie(s, ctx); + error = nfs_get_cache_cookie(s, ctx); + if (error < 0) + goto error_splat_super; } error = nfs_get_root(s, fc); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 9b7619ce17a7..2b322170372a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -294,6 +294,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); out: spin_unlock(&inode->i_lock); + nfs_fscache_invalidate(inode, 0); } /* A writeback failed: mark the page as bad, and invalidate the page cache */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 05f249f20f55..00835bacd236 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -275,7 +275,6 @@ struct nfs4_copy_state { #define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */ #define NFS_INO_INVALIDATING (3) /* inode is being invalidated */ #define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */ -#define NFS_INO_FSCACHE_LOCK (6) /* FS-Cache cookie management lock */ #define NFS_INO_FORCE_READDIR (7) /* force readdirplus */ #define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */ #define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */ diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 2a9acbfe00f0..77b2dba27bbb 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -120,11 +120,6 @@ struct nfs_client { * This is used to generate the mv0 callback address. */ char cl_ipaddr[48]; - -#ifdef CONFIG_NFS_FSCACHE - struct fscache_cookie *fscache; /* client index cache cookie */ -#endif - struct net *cl_net; struct list_head pending_cb_stateids; }; @@ -194,8 +189,8 @@ struct nfs_server { struct nfs_auth_info auth_info; /* parsed auth flavors */ #ifdef CONFIG_NFS_FSCACHE - struct nfs_fscache_key *fscache_key; /* unique key for superblock */ - struct fscache_cookie *fscache; /* superblock cookie */ + struct fscache_volume *fscache; /* superblock cookie */ + char *fscache_uniq; /* Uniquifier (or NULL) */ #endif u32 pnfs_blksize; /* layout_blksize attr */ -- cgit v1.2.3 From 16f2f4e679cfdaa9552574484f104014908a76c6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 27 Aug 2021 15:19:34 +0100 Subject: nfs: Implement cache I/O by accessing the cache directly Move NFS to using fscache DIO API instead of the old upstream I/O API as that has been removed. This is a stopgap solution as the intention is that at sometime in the future, the cache will move to using larger blocks and won't be able to store individual pages in order to deal with the potential for data corruption due to the backing filesystem being able insert/remove bridging blocks of zeros into its extent list[1]. NFS then reads and writes cache pages synchronously and one page at a time. The preferred change would be to use the netfs lib, but the new I/O API can be used directly. It's just that as the cache now needs to track data for itself, caching blocks may exceed page size... This code is somewhat borrowed from my "fallback I/O" patchset[2]. Changes ======= ver #3: - Restore lost =n fallback for nfs_fscache_release_page()[2]. Signed-off-by: David Howells Tested-by: Dave Wysochanski Acked-by: Jeff Layton cc: Trond Myklebust cc: Anna Schumaker cc: linux-nfs@vger.kernel.org cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/YO17ZNOcq+9PajfQ@mit.edu [1] Link: https://lore.kernel.org/r/202112100957.2oEDT20W-lkp@intel.com/ [2] Link: https://lore.kernel.org/r/163189108292.2509237.12615909591150927232.stgit@warthog.procyon.org.uk/ [2] Link: https://lore.kernel.org/r/163906981318.143852.17220018647843475985.stgit@warthog.procyon.org.uk/ # v2 Link: https://lore.kernel.org/r/163967184451.1823006.6450645559828329590.stgit@warthog.procyon.org.uk/ # v3 Link: https://lore.kernel.org/r/164021577632.640689.11069627070150063812.stgit@warthog.procyon.org.uk/ # v4 --- fs/fscache/io.c | 8 +++ fs/nfs/fscache.c | 126 +++++++++++++++++++++++++++++++++++++++--------- fs/nfs/fscache.h | 52 +++++--------------- fs/nfs/read.c | 25 +++------- fs/nfs/write.c | 7 ++- include/linux/fscache.h | 28 +++++++++++ 6 files changed, 163 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/fs/fscache/io.c b/fs/fscache/io.c index bed7628a5a9d..7a769ea57720 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -150,6 +150,14 @@ int __fscache_begin_read_operation(struct netfs_cache_resources *cres, } EXPORT_SYMBOL(__fscache_begin_read_operation); +int __fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + return fscache_begin_operation(cres, cookie, FSCACHE_WANT_PARAMS, + fscache_access_io_write); +} +EXPORT_SYMBOL(__fscache_begin_write_operation); + /** * fscache_set_page_dirty - Mark page dirty and pin a cache object for writeback * @page: The page being dirtied diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index fac6438477a0..cfe901650ab0 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -249,48 +249,128 @@ void nfs_fscache_release_file(struct inode *inode, struct file *filp) } } +static inline void fscache_end_operation(struct netfs_cache_resources *cres) +{ + const struct netfs_cache_ops *ops = fscache_operation_valid(cres); + + if (ops) + ops->end_operation(cres); +} + +/* + * Fallback page reading interface. + */ +static int fscache_fallback_read_page(struct inode *inode, struct page *page) +{ + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, READ, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_read_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = fscache_read(&cres, page_offset(page), &iter, NETFS_READ_HOLE_FAIL, + NULL, NULL); + fscache_end_operation(&cres); + return ret; +} + +/* + * Fallback page writing interface. + */ +static int fscache_fallback_write_page(struct inode *inode, struct page *page, + bool no_space_allocated_yet) +{ + struct netfs_cache_resources cres; + struct fscache_cookie *cookie = nfs_i_fscache(inode); + struct iov_iter iter; + struct bio_vec bvec[1]; + loff_t start = page_offset(page); + size_t len = PAGE_SIZE; + int ret; + + memset(&cres, 0, sizeof(cres)); + bvec[0].bv_page = page; + bvec[0].bv_offset = 0; + bvec[0].bv_len = PAGE_SIZE; + iov_iter_bvec(&iter, WRITE, bvec, ARRAY_SIZE(bvec), PAGE_SIZE); + + ret = fscache_begin_write_operation(&cres, cookie); + if (ret < 0) + return ret; + + ret = cres.ops->prepare_write(&cres, &start, &len, i_size_read(inode), + no_space_allocated_yet); + if (ret == 0) + ret = fscache_write(&cres, page_offset(page), &iter, NULL, NULL); + fscache_end_operation(&cres); + return ret; +} + /* * Retrieve a page from fscache */ -int __nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, struct page *page) +int __nfs_readpage_from_fscache(struct inode *inode, struct page *page) { + int ret; + dfprintk(FSCACHE, "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n", nfs_i_fscache(inode), page, page->index, page->flags, inode); if (PageChecked(page)) { + dfprintk(FSCACHE, "NFS: readpage_from_fscache: PageChecked\n"); ClearPageChecked(page); return 1; } - return -ENOBUFS; // TODO: Use netfslib -} - -/* - * Retrieve a set of pages from fscache - */ -int __nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n", - nfs_i_fscache(inode), *nr_pages, inode); + ret = fscache_fallback_read_page(inode, page); + if (ret < 0) { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL); + dfprintk(FSCACHE, + "NFS: readpage_from_fscache failed %d\n", ret); + SetPageChecked(page); + return ret; + } - return -ENOBUFS; // TODO: Use netfslib + /* Read completed synchronously */ + dfprintk(FSCACHE, "NFS: readpage_from_fscache: read successful\n"); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK); + SetPageUptodate(page); + return 0; } /* - * Store a newly fetched page in fscache - * - PG_fscache must be set on the page + * Store a newly fetched page in fscache. We can be certain there's no page + * stored in the cache as yet otherwise we would've read it from there. */ -void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync) +void __nfs_readpage_to_fscache(struct inode *inode, struct page *page) { + int ret; + dfprintk(FSCACHE, - "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n", - nfs_i_fscache(inode), page, page->index, page->flags, sync); + "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx))\n", + nfs_i_fscache(inode), page, page->index, page->flags); - return; // TODO: Use netfslib + ret = fscache_fallback_write_page(inode, page, true); + + dfprintk(FSCACHE, + "NFS: readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n", + page, page->index, page->flags, ret); + + if (ret != 0) { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL); + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED); + } else { + nfs_inc_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_WRITTEN_OK); + } } diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h index 0fa267243d26..e0220fc40366 100644 --- a/fs/nfs/fscache.h +++ b/fs/nfs/fscache.h @@ -44,14 +44,10 @@ extern void nfs_fscache_clear_inode(struct inode *); extern void nfs_fscache_open_file(struct inode *, struct file *); extern void nfs_fscache_release_file(struct inode *, struct file *); -extern void __nfs_fscache_invalidate_page(struct page *, struct inode *); - -extern int __nfs_readpage_from_fscache(struct nfs_open_context *, - struct inode *, struct page *); -extern int __nfs_readpages_from_fscache(struct nfs_open_context *, - struct inode *, struct address_space *, - struct list_head *, unsigned *); -extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int); +extern int __nfs_readpage_from_fscache(struct inode *, struct page *); +extern void __nfs_read_completion_to_fscache(struct nfs_pgio_header *hdr, + unsigned long bytes); +extern void __nfs_readpage_to_fscache(struct inode *, struct page *); static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { @@ -69,27 +65,11 @@ static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) /* * Retrieve a page from an inode data storage object. */ -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, +static inline int nfs_readpage_from_fscache(struct inode *inode, struct page *page) { if (NFS_I(inode)->fscache) - return __nfs_readpage_from_fscache(ctx, inode, page); - return -ENOBUFS; -} - -/* - * Retrieve a set of pages from an inode data storage object. - */ -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - if (NFS_I(inode)->fscache) - return __nfs_readpages_from_fscache(ctx, inode, mapping, pages, - nr_pages); + return __nfs_readpage_from_fscache(inode, page); return -ENOBUFS; } @@ -98,11 +78,10 @@ static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, * in the cache. */ static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, - int sync) + struct page *page) { - if (PageFsCache(page)) - __nfs_readpage_to_fscache(inode, page, sync); + if (NFS_I(inode)->fscache) + __nfs_readpage_to_fscache(inode, page); } static inline void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, @@ -156,22 +135,13 @@ static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp) { return 1; /* True: may release page */ } -static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, +static inline int nfs_readpage_from_fscache(struct inode *inode, struct page *page) { return -ENOBUFS; } -static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx, - struct inode *inode, - struct address_space *mapping, - struct list_head *pages, - unsigned *nr_pages) -{ - return -ENOBUFS; -} static inline void nfs_readpage_to_fscache(struct inode *inode, - struct page *page, int sync) {} + struct page *page) {} static inline void nfs_fscache_invalidate(struct inode *inode, int flags) {} diff --git a/fs/nfs/read.c b/fs/nfs/read.c index d11af2a9299c..eb00229c1a50 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -123,7 +123,7 @@ static void nfs_readpage_release(struct nfs_page *req, int error) struct address_space *mapping = page_file_mapping(page); if (PageUptodate(page)) - nfs_readpage_to_fscache(inode, page, 0); + nfs_readpage_to_fscache(inode, page); else if (!PageError(page) && !PagePrivate(page)) generic_error_remove_page(mapping, page); unlock_page(page); @@ -305,6 +305,12 @@ readpage_async_filler(void *data, struct page *page) aligned_len = min_t(unsigned int, ALIGN(len, rsize), PAGE_SIZE); + if (!IS_SYNC(page->mapping->host)) { + error = nfs_readpage_from_fscache(page->mapping->host, page); + if (error == 0) + goto out_unlock; + } + new = nfs_create_request(desc->ctx, page, 0, aligned_len); if (IS_ERR(new)) goto out_error; @@ -320,6 +326,7 @@ readpage_async_filler(void *data, struct page *page) return 0; out_error: error = PTR_ERR(new); +out_unlock: unlock_page(page); out: return error; @@ -366,12 +373,6 @@ int nfs_readpage(struct file *file, struct page *page) desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); xchg(&desc.ctx->error, 0); - if (!IS_SYNC(inode)) { - ret = nfs_readpage_from_fscache(desc.ctx, inode, page); - if (ret == 0) - goto out_wait; - } - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -381,7 +382,6 @@ int nfs_readpage(struct file *file, struct page *page) nfs_pageio_complete_read(&desc.pgio); ret = desc.pgio.pg_error < 0 ? desc.pgio.pg_error : 0; -out_wait: if (!ret) { ret = wait_on_page_locked_killable(page); if (!PageUptodate(page) && !ret) @@ -419,14 +419,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping, } else desc.ctx = get_nfs_open_context(nfs_file_open_context(file)); - /* attempt to read as many of the pages as possible from the cache - * - this returns -ENOBUFS immediately if the cookie is negative - */ - ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping, - pages, &nr_pages); - if (ret == 0) - goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&desc.pgio, inode, false, &nfs_async_read_completion_ops); @@ -434,7 +426,6 @@ int nfs_readpages(struct file *file, struct address_space *mapping, nfs_pageio_complete_read(&desc.pgio); -read_complete: put_nfs_open_context(desc.ctx); out: trace_nfs_aop_readahead_done(inode, nr_pages, ret); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 2b322170372a..987a187bd39a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2126,8 +2126,11 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage, if (PagePrivate(page)) return -EBUSY; - if (!nfs_fscache_release_page(page, GFP_KERNEL)) - return -EBUSY; + if (PageFsCache(page)) { + if (mode == MIGRATE_ASYNC) + return -EBUSY; + wait_on_page_fscache(page); + } return migrate_page(mapping, newpage, page, mode); } diff --git a/include/linux/fscache.h b/include/linux/fscache.h index 7bd35f60d19a..ede50406bcb0 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -168,6 +168,7 @@ extern void __fscache_relinquish_cookie(struct fscache_cookie *, bool); extern void __fscache_resize_cookie(struct fscache_cookie *, loff_t); extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t, unsigned int); extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *); +extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *); extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *, loff_t, size_t, loff_t, netfs_io_terminated_t, void *, @@ -499,6 +500,33 @@ int fscache_read(struct netfs_cache_resources *cres, term_func, term_func_priv); } +/** + * fscache_begin_write_operation - Begin a write operation for the netfs lib + * @cres: The cache resources for the write being performed + * @cookie: The cookie representing the cache object + * + * Begin a write operation on behalf of the netfs helper library. @cres + * indicates the cache resources to which the operation state should be + * attached; @cookie indicates the cache object that will be accessed. + * + * @cres->inval_counter is set from @cookie->inval_counter for comparison at + * the end of the operation. This allows invalidation during the operation to + * be detected by the caller. + * + * Returns: + * * 0 - Success + * * -ENOBUFS - No caching available + * * Other error code from the cache, such as -ENOMEM. + */ +static inline +int fscache_begin_write_operation(struct netfs_cache_resources *cres, + struct fscache_cookie *cookie) +{ + if (fscache_cookie_enabled(cookie)) + return __fscache_begin_write_operation(cres, cookie); + return -ENOBUFS; +} + /** * fscache_write - Start a write to the cache. * @cres: The cache resources to use -- cgit v1.2.3 From a59466ee91aaa9d43889a4c51e01de087d188448 Mon Sep 17 00:00:00 2001 From: Karolina Drobnik Date: Tue, 11 Jan 2022 10:28:47 +0000 Subject: memblock: Remove #ifdef __KERNEL__ from memblock.h memblock.h is not a uAPI header, so __KERNEL__ guard can be deleted Signed-off-by: Karolina Drobnik Signed-off-by: Mike Rapoport Link: https://lore.kernel.org/r/20220111102847.673746-1-karolinadrobnik@gmail.com --- include/linux/memblock.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9dc7cb239d21..50ad19662a32 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef _LINUX_MEMBLOCK_H #define _LINUX_MEMBLOCK_H -#ifdef __KERNEL__ /* * Logical memory blocks. @@ -605,6 +604,5 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) } #endif -#endif /* __KERNEL__ */ #endif /* _LINUX_MEMBLOCK_H */ -- cgit v1.2.3 From 500b55b05d0a21c4adddf4c3b29ee6f32b502046 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 21 Dec 2021 10:45:07 -0600 Subject: PCI: Work around Intel I210 ROM BAR overlap defect Per PCIe r5, sec 7.5.1.2.4, a device must not claim accesses to its Expansion ROM unless both the Memory Space Enable and the Expansion ROM Enable bit are set. But apparently some Intel I210 NICs don't work correctly if the ROM BAR overlaps another BAR, even if the Expansion ROM is disabled. Michael reported that on a Kontron SMARC-sAL28 ARM64 system with U-Boot v2021.01-rc3, the ROM BAR overlaps BAR 3, and networking doesn't work at all: BAR 0: 0x40000000 (32-bit, non-prefetchable) [size=1M] BAR 3: 0x40200000 (32-bit, non-prefetchable) [size=16K] ROM: 0x40200000 (disabled) [size=1M] NETDEV WATCHDOG: enP2p1s0 (igb): transmit queue 0 timed out Hardware name: Kontron SMARC-sAL28 (Single PHY) on SMARC Eval 2.0 carrier (DT) igb 0002:01:00.0 enP2p1s0: Reset adapter Previously, pci_std_update_resource() wrote the assigned ROM address to the BAR only when the ROM was enabled. This meant that the I210 ROM BAR could be left with an address assigned by firmware, which might overlap with other BARs. Quirk these I210 devices so pci_std_update_resource() always writes the assigned address to the ROM BAR, whether or not the ROM is enabled. Link: https://lore.kernel.org/r/20211223163754.GA1267351@bhelgaas Link: https://lore.kernel.org/r/20201230185317.30915-1-michael@walle.cc Link: https://bugzilla.kernel.org/show_bug.cgi?id=211105 Reported-by: Michael Walle Tested-by: Michael Walle Signed-off-by: Bjorn Helgaas --- drivers/pci/quirks.c | 10 ++++++++++ drivers/pci/setup-res.c | 8 ++++++-- include/linux/pci.h | 1 + 3 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 003950c738d2..46ff04091fa3 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5857,3 +5857,13 @@ static void nvidia_ion_ahci_fixup(struct pci_dev *pdev) pdev->dev_flags |= PCI_DEV_FLAGS_HAS_MSI_MASKING; } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0ab8, nvidia_ion_ahci_fixup); + +static void rom_bar_overlap_defect(struct pci_dev *dev) +{ + pci_info(dev, "working around ROM BAR overlap defect\n"); + dev->rom_bar_overlap = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1533, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1536, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1537, rom_bar_overlap_defect); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x1538, rom_bar_overlap_defect); diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 7f1acb3918d0..439ac5f5907a 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -75,12 +75,16 @@ static void pci_std_update_resource(struct pci_dev *dev, int resno) * as zero when disabled, so don't update ROM BARs unless * they're enabled. See * https://lore.kernel.org/r/43147B3D.1030309@vc.cvut.cz/ + * But we must update ROM BAR for buggy devices where even a + * disabled ROM can conflict with other BARs. */ - if (!(res->flags & IORESOURCE_ROM_ENABLE)) + if (!(res->flags & IORESOURCE_ROM_ENABLE) && + !dev->rom_bar_overlap) return; reg = dev->rom_base_reg; - new |= PCI_ROM_ADDRESS_ENABLE; + if (res->flags & IORESOURCE_ROM_ENABLE) + new |= PCI_ROM_ADDRESS_ENABLE; } else return; diff --git a/include/linux/pci.h b/include/linux/pci.h index 18a75c8e615c..51c4a063f489 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -455,6 +455,7 @@ struct pci_dev { unsigned int link_active_reporting:1;/* Device capable of reporting link active */ unsigned int no_vf_scan:1; /* Don't scan for VFs after IOV enablement */ unsigned int no_command_memory:1; /* No PCI_COMMAND_MEMORY */ + unsigned int rom_bar_overlap:1; /* ROM BAR disable broken */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */ -- cgit v1.2.3 From 1d3cfc2835c1754d19a743dc346a9e58cf0c07c0 Mon Sep 17 00:00:00 2001 From: Kelvin Cao Date: Thu, 23 Dec 2021 17:23:33 -0800 Subject: ntb_hw_switchtec: Remove code for disabling ID protection ID protection is a firmware setting for NT window access control. With it enabled, only the posted requests with requester IDs in the requester ID table will be allowed to access the NT windows. Otherwise all posted requests are allowed. Normally user will configure it statically via the Switchtec config file, and it will take effect when the firmware boots up. The driver can also toggle the ID protection setting dynamically, which will overwrite the static setting in the Switchtec config file as a side effect. Currently, the driver disables the ID protection. However, it's not necessary to disable the ID protection at the driver level as the driver has already configured the proper requester IDs in the requester ID table to allow the corresponding posted requests to hit the NT windows. Remove the code that disables the ID protection to make the static setting prevail. Note: ID protection is not applicable to non-posted requests. Signed-off-by: Kelvin Cao Signed-off-by: Jon Mason --- drivers/ntb/hw/mscc/ntb_hw_switchtec.c | 3 --- include/linux/switchtec.h | 2 -- 2 files changed, 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index ba6a9670c681..e79a355bafbf 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -967,9 +967,6 @@ static int config_req_id_table(struct switchtec_ntb *sndev, if (rc) return rc; - iowrite32(NTB_PART_CTRL_ID_PROT_DIS, - &mmio_ctrl->partition_ctrl); - for (i = 0; i < count; i++) { iowrite32(req_ids[i] << 16 | NTB_CTRL_REQ_ID_EN, &mmio_ctrl->req_id_table[i]); diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h index be24056ac00f..48fabe36509e 100644 --- a/include/linux/switchtec.h +++ b/include/linux/switchtec.h @@ -337,8 +337,6 @@ enum { NTB_CTRL_REQ_ID_EN = 1 << 0, NTB_CTRL_LUT_EN = 1 << 0, - - NTB_PART_CTRL_ID_PROT_DIS = 1 << 0, }; struct ntb_ctrl_regs { -- cgit v1.2.3 From ca321ec74322e3c49552fc1ffc80b42d0dbf1a84 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 8 Jan 2022 15:06:57 +0100 Subject: module.h: allow #define strings to work with MODULE_IMPORT_NS The MODULE_IMPORT_NS() macro does not allow defined strings to work properly with it, so add a layer of indirection to allow this to happen. Cc: Luis Chamberlain Cc: Jessica Yu Cc: Matthias Maennich Signed-off-by: Greg Kroah-Hartman Reviewed-by: Matthias Maennich Signed-off-by: Luis Chamberlain --- include/linux/module.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/module.h b/include/linux/module.h index c9f1200b2312..f4338235ed2c 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -290,7 +290,8 @@ extern typeof(name) __mod_##type##__##name##_device_table \ * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) -#define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) +#define _MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, #ns) +#define MODULE_IMPORT_NS(ns) _MODULE_IMPORT_NS(ns) struct notifier_block; -- cgit v1.2.3 From 3f4b32511a77bc5a05cfbf26fec94c4e1b1cf46a Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 7 Jan 2022 18:17:18 +0000 Subject: PM: core: Remove DEFINE_UNIVERSAL_DEV_PM_OPS() macro The deprecated UNIVERSAL_DEV_PM_OPS() macro uses the provided callbacks for both runtime PM and system sleep, which is very likely to be a mistake, as a system sleep can be triggered while a given device is already PM-suspended, which would cause the suspend callback to be called twice. The amount of users of UNIVERSAL_DEV_PM_OPS() is also tiny (16 occurences) compared to the number of places where SET_SYSTEM_SLEEP_PM_OPS() is used with pm_runtime_force_suspend() and pm_runtime_force_resume(), which makes me think that none of these cases are actually valid. As the new macro DEFINE_UNIVERSAL_DEV_PM_OPS() which was introduced to replace UNIVERSAL_DEV_PM_OPS() is currently unused, remove it before someone starts to use it in yet another invalid case. Signed-off-by: Paul Cercueil Acked-by: Jonathan Cameron Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index e1e9402180b9..02f059d814bb 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -366,6 +366,12 @@ static const struct dev_pm_ops name = { \ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } +/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ +#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ +const struct dev_pm_ops __maybe_unused name = { \ + SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ +} + /* * Use this for defining a set of PM operations to be used in all situations * (system suspend, hibernation or runtime PM). @@ -378,20 +384,9 @@ static const struct dev_pm_ops name = { \ * suspend and "early" resume callback pointers, .suspend_late() and * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). + * + * Deprecated. You most likely don't want this macro. */ -#define DEFINE_UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ -static const struct dev_pm_ops name = { \ - SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ - RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) \ -} - -/* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ -#define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops __maybe_unused name = { \ - SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ -} - -/* Deprecated. Use DEFINE_UNIVERSAL_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ SET_SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ -- cgit v1.2.3 From 52cc1d7f9786d2be44a3ab9b5b48416a7618e713 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 7 Jan 2022 18:17:19 +0000 Subject: PM: core: Remove static qualifier in DEFINE_SIMPLE_DEV_PM_OPS macro Keep this macro in line with the other ones. This makes it possible to use them in the cases where the underlying dev_pm_ops structure is exported. Restore the "static" qualifier in the two drivers where the DEFINE_SIMPLE_DEV_PM_OPS macro was used. Signed-off-by: Paul Cercueil Acked-by: Jonathan Cameron Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- drivers/mmc/host/jz4740_mmc.c | 4 ++-- drivers/mmc/host/mxcmmc.c | 2 +- include/linux/pm.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/jz4740_mmc.c b/drivers/mmc/host/jz4740_mmc.c index bb612fce7ead..4ac87b0797bb 100644 --- a/drivers/mmc/host/jz4740_mmc.c +++ b/drivers/mmc/host/jz4740_mmc.c @@ -1113,8 +1113,8 @@ static int jz4740_mmc_resume(struct device *dev) return pinctrl_select_default_state(dev); } -DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend, - jz4740_mmc_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(jz4740_mmc_pm_ops, jz4740_mmc_suspend, + jz4740_mmc_resume); static struct platform_driver jz4740_mmc_driver = { .probe = jz4740_mmc_probe, diff --git a/drivers/mmc/host/mxcmmc.c b/drivers/mmc/host/mxcmmc.c index 98c218bd6669..40b6878bea6c 100644 --- a/drivers/mmc/host/mxcmmc.c +++ b/drivers/mmc/host/mxcmmc.c @@ -1210,7 +1210,7 @@ static int mxcmci_resume(struct device *dev) return ret; } -DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(mxcmci_pm_ops, mxcmci_suspend, mxcmci_resume); static struct platform_driver mxcmci_driver = { .probe = mxcmci_probe, diff --git a/include/linux/pm.h b/include/linux/pm.h index 02f059d814bb..8e13387e70ec 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -362,7 +362,7 @@ struct dev_pm_ops { * to RAM and hibernation. */ #define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -static const struct dev_pm_ops name = { \ +const struct dev_pm_ops name = { \ SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ } -- cgit v1.2.3 From 0ae101fdd3297b7165755340e05386f1e1379709 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 7 Jan 2022 18:17:20 +0000 Subject: PM: core: Add EXPORT[_GPL]_SIMPLE_DEV_PM_OPS macros These macros are defined conditionally, according to CONFIG_PM: - if CONFIG_PM is enabled, these macros resolve to DEFINE_SIMPLE_DEV_PM_OPS(), and the dev_pm_ops symbol will be exported. - if CONFIG_PM is disabled, these macros will result in a dummy static dev_pm_ops to be created with the __maybe_unused flag. The dev_pm_ops will then be discarded by the compiler, along with the provided callback functions if they are not used anywhere else. In the second case, the symbol is not exported, which should be perfectly fine - users of the symbol should all use the pm_ptr() or pm_sleep_ptr() macro, so the dev_pm_ops marked as "extern" in the client's code will never be accessed. Signed-off-by: Paul Cercueil Acked-by: Jonathan Cameron Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 35 ++++++++++++++++++++++++++++++++--- 1 file changed, 32 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 8e13387e70ec..8279af2c538a 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -8,6 +8,7 @@ #ifndef _LINUX_PM_H #define _LINUX_PM_H +#include #include #include #include @@ -357,14 +358,42 @@ struct dev_pm_ops { #define SET_RUNTIME_PM_OPS(suspend_fn, resume_fn, idle_fn) #endif +#define _DEFINE_DEV_PM_OPS(name, \ + suspend_fn, resume_fn, \ + runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +const struct dev_pm_ops name = { \ + SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ + RUNTIME_PM_OPS(runtime_suspend_fn, runtime_resume_fn, idle_fn) \ +} + +#ifdef CONFIG_PM +#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn, sec) \ + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn); \ + _EXPORT_SYMBOL(name, sec) +#else +#define _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn, sec) \ +static __maybe_unused _DEFINE_DEV_PM_OPS(__static_##name, suspend_fn, \ + resume_fn, runtime_suspend_fn, \ + runtime_resume_fn, idle_fn) +#endif + /* * Use this if you want to use the same suspend and resume callbacks for suspend * to RAM and hibernation. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_SIMPLE_DEV_PM_OPS() or EXPORT_GPL_SIMPLE_DEV_PM_OPS() instead. */ #define DEFINE_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -const struct dev_pm_ops name = { \ - SYSTEM_SLEEP_PM_OPS(suspend_fn, resume_fn) \ -} + _DEFINE_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL) + +#define EXPORT_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "") +#define EXPORT_GPL_SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ + _EXPORT_DEV_PM_OPS(name, suspend_fn, resume_fn, NULL, NULL, NULL, "_gpl") /* Deprecated. Use DEFINE_SIMPLE_DEV_PM_OPS() instead. */ #define SIMPLE_DEV_PM_OPS(name, suspend_fn, resume_fn) \ -- cgit v1.2.3 From 9d8619190031af0a314bee865262d8975473e4dd Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 7 Jan 2022 18:17:21 +0000 Subject: PM: runtime: Add DEFINE_RUNTIME_DEV_PM_OPS() macro A lot of drivers create a dev_pm_ops struct with the system sleep suspend/resume callbacks set to pm_runtime_force_suspend() and pm_runtime_force_resume(). These drivers can now use the DEFINE_RUNTIME_DEV_PM_OPS() macro, which will use pm_runtime_force_{suspend,resume}() as the system sleep callbacks, while having the same dead code removal characteristic that is already provided by DEFINE_SIMPLE_DEV_PM_OPS(). Signed-off-by: Paul Cercueil Acked-by: Jonathan Cameron Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm.h | 3 ++- include/linux/pm_runtime.h | 14 ++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/pm.h b/include/linux/pm.h index 8279af2c538a..f7d2be686359 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -414,7 +414,8 @@ const struct dev_pm_ops __maybe_unused name = { \ * .resume_early(), to the same routines as .runtime_suspend() and * .runtime_resume(), respectively (and analogously for hibernation). * - * Deprecated. You most likely don't want this macro. + * Deprecated. You most likely don't want this macro. Use + * DEFINE_RUNTIME_DEV_PM_OPS() instead. */ #define UNIVERSAL_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ const struct dev_pm_ops __maybe_unused name = { \ diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 016de5776b6d..4af454d29281 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -22,6 +22,20 @@ usage_count */ #define RPM_AUTO 0x08 /* Use autosuspend_delay */ +/* + * Use this for defining a set of PM operations to be used in all situations + * (system suspend, hibernation or runtime PM). + * + * Note that the behaviour differs from the deprecated UNIVERSAL_DEV_PM_OPS() + * macro, which uses the provided callbacks for both runtime PM and system + * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() + * and pm_runtime_force_resume() for its system sleep callbacks. + */ +#define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ + pm_runtime_force_resume, suspend_fn, \ + resume_fn, idle_fn) + #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; -- cgit v1.2.3 From d59ff7d9d84b03d22c5107f794e28fc8e1fce3a6 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Fri, 7 Jan 2022 18:17:22 +0000 Subject: PM: runtime: Add EXPORT[_GPL]_RUNTIME_DEV_PM_OPS macros Similar to EXPORT[_GPL]_SIMPLE_DEV_PM_OPS, but for users with runtime-PM suspend/resume callbacks. Signed-off-by: Paul Cercueil Acked-by: Jonathan Cameron Reviewed-by: Ulf Hansson Signed-off-by: Rafael J. Wysocki --- include/linux/pm_runtime.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 4af454d29281..9f09601c465a 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -30,12 +30,22 @@ * macro, which uses the provided callbacks for both runtime PM and system * sleep, while DEFINE_RUNTIME_DEV_PM_OPS() uses pm_runtime_force_suspend() * and pm_runtime_force_resume() for its system sleep callbacks. + * + * If the underlying dev_pm_ops struct symbol has to be exported, use + * EXPORT_RUNTIME_DEV_PM_OPS() or EXPORT_GPL_RUNTIME_DEV_PM_OPS() instead. */ #define DEFINE_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ _DEFINE_DEV_PM_OPS(name, pm_runtime_force_suspend, \ pm_runtime_force_resume, suspend_fn, \ resume_fn, idle_fn) +#define EXPORT_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "") +#define EXPORT_GPL_RUNTIME_DEV_PM_OPS(name, suspend_fn, resume_fn, idle_fn) \ + _EXPORT_DEV_PM_OPS(name, pm_runtime_force_suspend, pm_runtime_force_resume, \ + suspend_fn, resume_fn, idle_fn, "_gpl") + #ifdef CONFIG_PM extern struct workqueue_struct *pm_wq; -- cgit v1.2.3 From 8a59bb93b7e3cca389af44781a429ac12ac49be6 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Thu, 9 Dec 2021 14:53:30 -0500 Subject: NFSv4 store server support for fs_location attribute Define and store if server returns it supports fs_locations attribute as a capability. Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/nfs4proc.c | 2 ++ include/linux/nfs_fs_sb.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 44ab27f20f04..7d4c63282793 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3875,6 +3875,8 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f if (res.attr_bitmask[2] & FATTR4_WORD2_SECURITY_LABEL) server->caps |= NFS_CAP_SECURITY_LABEL; #endif + if (res.attr_bitmask[0] & FATTR4_WORD0_FS_LOCATIONS) + server->caps |= NFS_CAP_FS_LOCATIONS; if (!(res.attr_bitmask[0] & FATTR4_WORD0_FILEID)) server->fattr_valid &= ~NFS_ATTR_FATTR_FILEID; if (!(res.attr_bitmask[1] & FATTR4_WORD1_MODE)) diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index f24fc67af42d..8c08b356c8ca 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -289,5 +289,5 @@ struct nfs_server { #define NFS_CAP_COPY_NOTIFY (1U << 27) #define NFS_CAP_XATTR (1U << 28) #define NFS_CAP_READ_PLUS (1U << 29) - +#define NFS_CAP_FS_LOCATIONS (1U << 30) #endif -- cgit v1.2.3 From 2d7c86a8f9cdce1408c4f3c69d94d007eff2f179 Mon Sep 17 00:00:00 2001 From: Venky Shankar Date: Wed, 14 Jul 2021 15:35:50 +0530 Subject: libceph: generalize addr/ip parsing based on delimiter ... and remove hardcoded function name in ceph_parse_ips(). [ idryomov: delim parameter, drop CEPH_ADDR_PARSE_DEFAULT_DELIM ] Signed-off-by: Venky Shankar Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- drivers/block/rbd.c | 3 ++- fs/ceph/super.c | 2 +- include/linux/ceph/libceph.h | 2 +- include/linux/ceph/messenger.h | 2 +- net/ceph/ceph_common.c | 9 ++++----- net/ceph/messenger.c | 15 ++++++++------- 6 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 953fa134cd3d..909dbe6111bf 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -6497,7 +6497,8 @@ static int rbd_add_parse_args(const char *buf, pctx.opts->exclusive = RBD_EXCLUSIVE_DEFAULT; pctx.opts->trim = RBD_TRIM_DEFAULT; - ret = ceph_parse_mon_ips(mon_addrs, mon_addrs_size, pctx.copts, NULL); + ret = ceph_parse_mon_ips(mon_addrs, mon_addrs_size, pctx.copts, NULL, + ','); if (ret) goto out_err; diff --git a/fs/ceph/super.c b/fs/ceph/super.c index bab61232dc5a..c444371ebc38 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -272,7 +272,7 @@ static int ceph_parse_source(struct fs_parameter *param, struct fs_context *fc) dout("server path '%s'\n", fsopt->server_path); ret = ceph_parse_mon_ips(param->string, dev_name_end - dev_name, - pctx->copts, fc->log.log); + pctx->copts, fc->log.log, ','); if (ret) return ret; diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 409d8c29bc4f..c72285d8594e 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -301,7 +301,7 @@ struct fs_parameter; struct fc_log; struct ceph_options *ceph_alloc_options(void); int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, - struct fc_log *l); + struct fc_log *l, char delim); int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, struct fc_log *l); int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 0e6e9ad3c3bf..ff99ce094cfa 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -532,7 +532,7 @@ extern const char *ceph_pr_addr(const struct ceph_entity_addr *addr); extern int ceph_parse_ips(const char *c, const char *end, struct ceph_entity_addr *addr, - int max_count, int *count); + int max_count, int *count, char delim); extern int ceph_msgr_init(void); extern void ceph_msgr_exit(void); diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 97d6ea763e32..851b0c4c5730 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -422,14 +422,14 @@ out: } int ceph_parse_mon_ips(const char *buf, size_t len, struct ceph_options *opt, - struct fc_log *l) + struct fc_log *l, char delim) { struct p_log log = {.prefix = "libceph", .log = l}; int ret; - /* ip1[:port1][,ip2[:port2]...] */ + /* ip1[:port1][ip2[:port2]...] */ ret = ceph_parse_ips(buf, buf + len, opt->mon_addr, CEPH_MAX_MON, - &opt->num_mon); + &opt->num_mon, delim); if (ret) { error_plog(&log, "Failed to parse monitor IPs: %d", ret); return ret; @@ -455,8 +455,7 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, case Opt_ip: err = ceph_parse_ips(param->string, param->string + param->size, - &opt->my_addr, - 1, NULL); + &opt->my_addr, 1, NULL, ','); if (err) { error_plog(&log, "Failed to parse ip: %d", err); return err; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 57d043b382ed..929ed91f2ec3 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1267,30 +1267,31 @@ static int ceph_parse_server_name(const char *name, size_t namelen, */ int ceph_parse_ips(const char *c, const char *end, struct ceph_entity_addr *addr, - int max_count, int *count) + int max_count, int *count, char delim) { int i, ret = -EINVAL; const char *p = c; dout("parse_ips on '%.*s'\n", (int)(end-c), c); for (i = 0; i < max_count; i++) { + char cur_delim = delim; const char *ipend; int port; - char delim = ','; if (*p == '[') { - delim = ']'; + cur_delim = ']'; p++; } - ret = ceph_parse_server_name(p, end - p, &addr[i], delim, &ipend); + ret = ceph_parse_server_name(p, end - p, &addr[i], cur_delim, + &ipend); if (ret) goto bad; ret = -EINVAL; p = ipend; - if (delim == ']') { + if (cur_delim == ']') { if (*p != ']') { dout("missing matching ']'\n"); goto bad; @@ -1326,11 +1327,11 @@ int ceph_parse_ips(const char *c, const char *end, addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY; addr[i].nonce = 0; - dout("parse_ips got %s\n", ceph_pr_addr(&addr[i])); + dout("%s got %s\n", __func__, ceph_pr_addr(&addr[i])); if (p == end) break; - if (*p != ',') + if (*p != delim) goto bad; p++; } -- cgit v1.2.3 From 4153c7fc937a2afa077dbdb9fe3189b9981f423c Mon Sep 17 00:00:00 2001 From: Venky Shankar Date: Wed, 14 Jul 2021 15:35:51 +0530 Subject: libceph: rename parse_fsid() to ceph_parse_fsid() and export ... as it is too generic. also, use __func__ when logging rather than hardcoding the function name. Signed-off-by: Venky Shankar Reviewed-by: Jeff Layton Signed-off-by: Ilya Dryomov --- include/linux/ceph/libceph.h | 1 + net/ceph/ceph_common.c | 9 +++++---- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index c72285d8594e..644f224eccf7 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -296,6 +296,7 @@ extern bool libceph_compatible(void *data); extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); extern void *ceph_kvmalloc(size_t size, gfp_t flags); +extern int ceph_parse_fsid(const char *str, struct ceph_fsid *fsid); struct fs_parameter; struct fc_log; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 851b0c4c5730..decae43b4262 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -217,14 +217,14 @@ void *ceph_kvmalloc(size_t size, gfp_t flags) return p; } -static int parse_fsid(const char *str, struct ceph_fsid *fsid) +int ceph_parse_fsid(const char *str, struct ceph_fsid *fsid) { int i = 0; char tmp[3]; int err = -EINVAL; int d; - dout("parse_fsid '%s'\n", str); + dout("%s '%s'\n", __func__, str); tmp[2] = 0; while (*str && i < 16) { if (ispunct(*str)) { @@ -244,9 +244,10 @@ static int parse_fsid(const char *str, struct ceph_fsid *fsid) if (i == 16) err = 0; - dout("parse_fsid ret %d got fsid %pU\n", err, fsid); + dout("%s ret %d got fsid %pU\n", __func__, err, fsid); return err; } +EXPORT_SYMBOL(ceph_parse_fsid); /* * ceph options @@ -464,7 +465,7 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, break; case Opt_fsid: - err = parse_fsid(param->string, &opt->fsid); + err = ceph_parse_fsid(param->string, &opt->fsid); if (err) { error_plog(&log, "Failed to parse fsid: %d", err); return err; -- cgit v1.2.3 From 1976b2b31462151403c9fc110204fcc2a77bdfd1 Mon Sep 17 00:00:00 2001 From: Olga Kornievskaia Date: Wed, 12 Jan 2022 10:27:38 -0500 Subject: NFSv4.1 query for fs_location attr on a new file system Query the server for other possible trunkable locations for a given file system on a 4.1+ mount. v2: -- added missing static to nfs4_discover_trunking, reported by the kernel test robot Signed-off-by: Olga Kornievskaia Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 7 +++++ fs/nfs/nfs4_fs.h | 9 +++--- fs/nfs/nfs4proc.c | 76 ++++++++++++++++++++++++++++++++++++++++++------- fs/nfs/nfs4state.c | 3 +- include/linux/nfs_xdr.h | 1 + 5 files changed, 81 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 1e4dc1ab9312..f7e39cc4472b 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -860,6 +860,13 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str server->namelen = pathinfo.max_namelen; } + if (clp->rpc_ops->discover_trunking != NULL && + (server->caps & NFS_CAP_FS_LOCATIONS)) { + error = clp->rpc_ops->discover_trunking(server, mntfh); + if (error < 0) + return error; + } + return 0; } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 89076dd32334..166ea6112e61 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -260,8 +260,8 @@ struct nfs4_state_maintenance_ops { }; struct nfs4_mig_recovery_ops { - int (*get_locations)(struct inode *, struct nfs4_fs_locations *, - struct page *, const struct cred *); + int (*get_locations)(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, struct page *, const struct cred *); int (*fsid_present)(struct inode *, const struct cred *); }; @@ -302,8 +302,9 @@ extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait); extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); extern int nfs4_proc_fs_locations(struct rpc_clnt *, struct inode *, const struct qstr *, struct nfs4_fs_locations *, struct page *); -extern int nfs4_proc_get_locations(struct inode *, struct nfs4_fs_locations *, - struct page *page, const struct cred *); +extern int nfs4_proc_get_locations(struct nfs_server *, struct nfs_fh *, + struct nfs4_fs_locations *, + struct page *page, const struct cred *); extern int nfs4_proc_fsid_present(struct inode *, const struct cred *); extern struct rpc_clnt *nfs4_proc_lookup_mountpoint(struct inode *, struct dentry *, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7d4c63282793..fc4629d2d2ab 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3935,6 +3935,60 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) return err; } +static int _nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_fs_locations *locations = NULL; + struct page *page; + const struct cred *cred; + struct nfs_client *clp = server->nfs_client; + const struct nfs4_state_maintenance_ops *ops = + clp->cl_mvops->state_renewal_ops; + int status = -ENOMEM; + + cred = ops->get_state_renewal_cred(clp); + if (cred == NULL) { + cred = nfs4_get_clid_cred(clp); + if (cred == NULL) + return -ENOKEY; + } + + page = alloc_page(GFP_KERNEL); + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (page == NULL || locations == NULL) + goto out; + + status = nfs4_proc_get_locations(server, fhandle, locations, page, + cred); + if (status) + goto out; +out: + if (page) + __free_page(page); + kfree(locations); + return status; +} + +static int nfs4_discover_trunking(struct nfs_server *server, + struct nfs_fh *fhandle) +{ + struct nfs4_exception exception = { + .interruptible = true, + }; + struct nfs_client *clp = server->nfs_client; + int err = 0; + + if (!nfs4_has_session(clp)) + goto out; + do { + err = nfs4_handle_exception(server, + _nfs4_discover_trunking(server, fhandle), + &exception); + } while (exception.retry); +out: + return err; +} + static int _nfs4_lookup_root(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *info) { @@ -7823,18 +7877,18 @@ int nfs4_proc_fs_locations(struct rpc_clnt *client, struct inode *dir, * appended to this compound to identify the client ID which is * performing recovery. */ -static int _nfs40_proc_get_locations(struct inode *inode, +static int _nfs40_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { .clientid = server->nfs_client->cl_clientid, - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7880,17 +7934,17 @@ static int _nfs40_proc_get_locations(struct inode *inode, * When the client supports GETATTR(fs_locations_info), it can * be plumbed in here. */ -static int _nfs41_proc_get_locations(struct inode *inode, +static int _nfs41_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct rpc_clnt *clnt = server->client; u32 bitmask[2] = { [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, }; struct nfs4_fs_locations_arg args = { - .fh = NFS_FH(inode), + .fh = fhandle, .page = page, .bitmask = bitmask, .migration = 1, /* skip LOOKUP */ @@ -7939,11 +7993,11 @@ static int _nfs41_proc_get_locations(struct inode *inode, * -NFS4ERR_LEASE_MOVED is returned if the server still has leases * from this client that require migration recovery. */ -int nfs4_proc_get_locations(struct inode *inode, +int nfs4_proc_get_locations(struct nfs_server *server, + struct nfs_fh *fhandle, struct nfs4_fs_locations *locations, struct page *page, const struct cred *cred) { - struct nfs_server *server = NFS_SERVER(inode); struct nfs_client *clp = server->nfs_client; const struct nfs4_mig_recovery_ops *ops = clp->cl_mvops->mig_recovery_ops; @@ -7956,10 +8010,11 @@ int nfs4_proc_get_locations(struct inode *inode, (unsigned long long)server->fsid.major, (unsigned long long)server->fsid.minor, clp->cl_hostname); - nfs_display_fhandle(NFS_FH(inode), __func__); + nfs_display_fhandle(fhandle, __func__); do { - status = ops->get_locations(inode, locations, page, cred); + status = ops->get_locations(server, fhandle, locations, page, + cred); if (status != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, status, &exception); @@ -10428,6 +10483,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .free_client = nfs4_free_client, .create_server = nfs4_create_server, .clone_server = nfs_clone_server, + .discover_trunking = nfs4_discover_trunking, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index f3265575c28d..499bef9fe118 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -2098,7 +2098,8 @@ static int nfs4_try_migration(struct nfs_server *server, const struct cred *cred } inode = d_inode(server->super->s_root); - result = nfs4_proc_get_locations(inode, locations, page, cred); + result = nfs4_proc_get_locations(server, NFS_FH(inode), locations, + page, cred); if (result) { dprintk("<-- %s: failed to retrieve fs_locations: %d\n", __func__, result); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index ddff92396a3f..728cb0c1f0b6 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1797,6 +1797,7 @@ struct nfs_rpc_ops { struct nfs_server *(*create_server)(struct fs_context *); struct nfs_server *(*clone_server)(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *, rpc_authflavor_t); + int (*discover_trunking)(struct nfs_server *, struct nfs_fh *); }; /* -- cgit v1.2.3 From 180dccb0dba4f5e84a4a70c1be1d34cbb6528b32 Mon Sep 17 00:00:00 2001 From: Laibin Qiu Date: Thu, 13 Jan 2022 10:55:36 +0800 Subject: blk-mq: fix tag_get wait task can't be awakened In case of shared tags, there might be more than one hctx which allocates from the same tags, and each hctx is limited to allocate at most: hctx_max_depth = max((bt->sb.depth + users - 1) / users, 4U); tag idle detection is lazy, and may be delayed for 30sec, so there could be just one real active hctx(queue) but all others are actually idle and still accounted as active because of the lazy idle detection. Then if wake_batch is > hctx_max_depth, driver tag allocation may wait forever on this real active hctx. Fix this by recalculating wake_batch when inc or dec active_queues. Fixes: 0d2602ca30e41 ("blk-mq: improve support for shared tags maps") Suggested-by: Ming Lei Suggested-by: John Garry Signed-off-by: Laibin Qiu Reviewed-by: Andy Shevchenko Link: https://lore.kernel.org/r/20220113025536.1479653-1-qiulaibin@huawei.com Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 40 +++++++++++++++++++++++++++++++++------- include/linux/sbitmap.h | 11 +++++++++++ lib/sbitmap.c | 25 ++++++++++++++++++++++--- 3 files changed, 66 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index e55a6834c9a6..845f74e8dd7b 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -16,6 +16,21 @@ #include "blk-mq-sched.h" #include "blk-mq-tag.h" +/* + * Recalculate wakeup batch when tag is shared by hctx. + */ +static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, + unsigned int users) +{ + if (!users) + return; + + sbitmap_queue_recalculate_wake_batch(&tags->bitmap_tags, + users); + sbitmap_queue_recalculate_wake_batch(&tags->breserved_tags, + users); +} + /* * If a previously inactive queue goes active, bump the active user count. * We need to do this before try to allocate driver tag, then even if fail @@ -24,18 +39,26 @@ */ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { + unsigned int users; + if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; - if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && - !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) - atomic_inc(&hctx->tags->active_queues); + if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || + test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) { + return true; + } } else { - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && - !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - atomic_inc(&hctx->tags->active_queues); + if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || + test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) { + return true; + } } + users = atomic_inc_return(&hctx->tags->active_queues); + + blk_mq_update_wake_batch(hctx->tags, users); + return true; } @@ -56,6 +79,7 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; + unsigned int users; if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; @@ -68,7 +92,9 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) return; } - atomic_dec(&tags->active_queues); + users = atomic_dec_return(&tags->active_queues); + + blk_mq_update_wake_batch(tags, users); blk_mq_tag_wakeup_all(tags, false); } diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index fc0357a6e19b..95df357ec009 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -415,6 +415,17 @@ static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) sbitmap_free(&sbq->sb); } +/** + * sbitmap_queue_recalculate_wake_batch() - Recalculate wake batch + * @sbq: Bitmap queue to recalculate wake batch. + * @users: Number of shares. + * + * Like sbitmap_queue_update_wake_batch(), this will calculate wake batch + * by depth. This interface is for HCTX shared tags or queue shared tags. + */ +void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, + unsigned int users); + /** * sbitmap_queue_resize() - Resize a &struct sbitmap_queue. * @sbq: Bitmap queue to resize. diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 2709ab825499..6220fa67fb7e 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -457,10 +457,9 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, } EXPORT_SYMBOL_GPL(sbitmap_queue_init_node); -static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq, - unsigned int depth) +static inline void __sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq, + unsigned int wake_batch) { - unsigned int wake_batch = sbq_calc_wake_batch(sbq, depth); int i; if (sbq->wake_batch != wake_batch) { @@ -476,6 +475,26 @@ static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq, } } +static void sbitmap_queue_update_wake_batch(struct sbitmap_queue *sbq, + unsigned int depth) +{ + unsigned int wake_batch; + + wake_batch = sbq_calc_wake_batch(sbq, depth); + __sbitmap_queue_update_wake_batch(sbq, wake_batch); +} + +void sbitmap_queue_recalculate_wake_batch(struct sbitmap_queue *sbq, + unsigned int users) +{ + unsigned int wake_batch; + + wake_batch = clamp_val((sbq->sb.depth + users - 1) / + users, 4, SBQ_WAKE_BATCH); + __sbitmap_queue_update_wake_batch(sbq, wake_batch); +} +EXPORT_SYMBOL_GPL(sbitmap_queue_recalculate_wake_batch); + void sbitmap_queue_resize(struct sbitmap_queue *sbq, unsigned int depth) { sbitmap_queue_update_wake_batch(sbq, depth); -- cgit v1.2.3 From 289e7b0f7eb47b87a0441e6c81336316f301eb39 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 13 Dec 2021 11:08:53 +0100 Subject: tracing: Account bottom half disabled sections. Disabling only bottom halves via local_bh_disable() disables also preemption but this remains invisible to tracing. On a CONFIG_PREEMPT kernel one might wonder why there is no scheduling happening despite the N flag in the trace. The reason might be the a rcu_read_lock_bh() section. Add a 'b' to the tracing output if in task context with disabled bottom halves. Link: https://lkml.kernel.org/r/YbcbtdtC/bjCKo57@linutronix.de Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Steven Rostedt --- include/linux/trace_events.h | 1 + kernel/trace/trace.c | 6 ++++-- kernel/trace/trace_output.c | 4 ++++ 3 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 3900404aa063..70c069aef02c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -172,6 +172,7 @@ enum trace_flag_type { TRACE_FLAG_SOFTIRQ = 0x10, TRACE_FLAG_PREEMPT_RESCHED = 0x20, TRACE_FLAG_NMI = 0x40, + TRACE_FLAG_BH_OFF = 0x80, }; #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 547d82628c2e..a73d78dcda2c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2603,6 +2603,8 @@ unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) trace_flags |= TRACE_FLAG_HARDIRQ; if (in_serving_softirq()) trace_flags |= TRACE_FLAG_SOFTIRQ; + if (softirq_count() >> (SOFTIRQ_SHIFT + 1)) + trace_flags |= TRACE_FLAG_BH_OFF; if (tif_need_resched()) trace_flags |= TRACE_FLAG_NEED_RESCHED; @@ -4190,7 +4192,7 @@ unsigned long trace_total_entries(struct trace_array *tr) static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" + "# / _-----=> irqs-off/BH-disabled\n" "# | / _----=> need-resched \n" "# || / _---=> hardirq/softirq \n" "# ||| / _--=> preempt-depth \n" @@ -4231,7 +4233,7 @@ static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file print_event_info(buf, m); - seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); + seq_printf(m, "# %.*s _-----=> irqs-off/BH-disabled\n", prec, space); seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 3547e7176ff7..8aa493d25c73 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -445,14 +445,18 @@ int trace_print_lat_fmt(struct trace_seq *s, struct trace_entry *entry) char irqs_off; int hardirq; int softirq; + int bh_off; int nmi; nmi = entry->flags & TRACE_FLAG_NMI; hardirq = entry->flags & TRACE_FLAG_HARDIRQ; softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + bh_off = entry->flags & TRACE_FLAG_BH_OFF; irqs_off = + (entry->flags & TRACE_FLAG_IRQS_OFF && bh_off) ? 'D' : (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : + bh_off ? 'b' : (entry->flags & TRACE_FLAG_IRQS_NOSUPPORT) ? 'X' : '.'; -- cgit v1.2.3 From 6840f9094f2bd788a316d8cb0a4e42538d3e47dd Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 13 Jan 2022 16:44:19 -0500 Subject: pagevec: Initialise folio_batch->percpu_pvec_drained When UBSAN is enabled, it reports an invalid value in __pagevec_release() when accessing pvec->percpu_pvec_drained, which is simply whatever garbage was on the stack. Initialise it when initialising the rest of the folio_batch. Fixes: 10331795fb79 ("pagevec: Add folio_batch") Reported-by: Randy Dunlap Tested-by: Randy Dunlap Signed-off-by: Matthew Wilcox (Oracle) --- include/linux/pagevec.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index dda8d5868c81..67b1246f136b 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -111,6 +111,7 @@ static_assert(offsetof(struct pagevec, pages) == static inline void folio_batch_init(struct folio_batch *fbatch) { fbatch->nr = 0; + fbatch->percpu_pvec_drained = false; } static inline unsigned int folio_batch_count(struct folio_batch *fbatch) -- cgit v1.2.3 From e5b48ee30aec1fe6dff05e36b22e886c665b4736 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 4 Jan 2022 16:14:46 +0900 Subject: ata: sata_fsl: fix scsi host initialization When compiling with W=1, the sata_fsl driver compilation throws the warning: drivers/ata/sata_fsl.c:1385:22: error: initialized field overwritten [-Werror=override-init] 1385 | .can_queue = SATA_FSL_QUEUE_DEPTH, This is due to the driver scsi host template initialization overwriting the can_queue field that is already set using the ATA_NCQ_SHT() initializer macro, resulting in the same field being initialized twice in the host template declaration. To remove this warning, introduce the ATA_SUBBASE_SHT_QD() and ATA_NCQ_SHT_QD() initialization macros to allow specifying a queue depth different from the default ATA_DEF_QUEUE using an additional argument to the macro. Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke --- drivers/ata/sata_fsl.c | 3 +-- include/linux/libata.h | 11 +++++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c index 142e65d5efc7..101d4dd79f62 100644 --- a/drivers/ata/sata_fsl.c +++ b/drivers/ata/sata_fsl.c @@ -1380,8 +1380,7 @@ static void sata_fsl_host_stop(struct ata_host *host) * scsi mid-layer and libata interface structures */ static struct scsi_host_template sata_fsl_sht = { - ATA_NCQ_SHT("sata_fsl"), - .can_queue = SATA_FSL_QUEUE_DEPTH, + ATA_NCQ_SHT_QD("sata_fsl", SATA_FSL_QUEUE_DEPTH), .sg_tablesize = SATA_FSL_MAX_PRD_USABLE, .dma_boundary = ATA_DMA_BOUNDARY, }; diff --git a/include/linux/libata.h b/include/linux/libata.h index c258f69106f4..2e5e7c40c991 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1385,6 +1385,12 @@ extern const struct attribute_group *ata_common_sdev_groups[]; .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ .slave_configure = ata_scsi_slave_config +#define ATA_SUBBASE_SHT_QD(drv_name, drv_qd) \ + __ATA_BASE_SHT(drv_name), \ + .can_queue = drv_qd, \ + .tag_alloc_policy = BLK_TAG_ALLOC_RR, \ + .slave_configure = ata_scsi_slave_config + #define ATA_BASE_SHT(drv_name) \ ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_common_sdev_groups @@ -1396,6 +1402,11 @@ extern const struct attribute_group *ata_ncq_sdev_groups[]; ATA_SUBBASE_SHT(drv_name), \ .sdev_groups = ata_ncq_sdev_groups, \ .change_queue_depth = ata_scsi_change_queue_depth + +#define ATA_NCQ_SHT_QD(drv_name, drv_qd) \ + ATA_SUBBASE_SHT_QD(drv_name, drv_qd), \ + .sdev_groups = ata_ncq_sdev_groups, \ + .change_queue_depth = ata_scsi_change_queue_depth #endif /* -- cgit v1.2.3 From 0561e514c944da874ccdfbe2922f71b4c333c7e1 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Tue, 4 Jan 2022 17:54:18 +0900 Subject: ata: fix read_id() ata port operation interface Drivers that need to tweak a device IDENTIFY data implement the read_id() port operation. The IDENTIFY data buffer is passed as an argument to the read_id() operation for drivers to use. However, when this operation is called, the IDENTIFY data is not yet converted to CPU endian and contains le16 words. Change the interface of the read_id operation to pass a __le16 * pointer to the IDENTIFY data buffer to clarify the buffer endianness. Fix the pata_netcell, pata_it821x, ahci_xgene, ahci_ceva and ahci_brcm drivers implementation of this operation and modify the code to corretly deal with identify data words manipulation to avoid sparse warnings such as: drivers/ata/ahci_xgene.c:262:33: warning: invalid assignment: &= drivers/ata/ahci_xgene.c:262:33: left side has type unsigned short drivers/ata/ahci_xgene.c:262:33: right side has type restricted __le16 Signed-off-by: Damien Le Moal Reviewed-by: Hannes Reinecke --- drivers/ata/ahci_brcm.c | 2 +- drivers/ata/ahci_ceva.c | 5 ++--- drivers/ata/ahci_xgene.c | 2 +- drivers/ata/libata-core.c | 6 +++--- drivers/ata/pata_it821x.c | 23 +++++++++++------------ drivers/ata/pata_netcell.c | 5 +++-- include/linux/libata.h | 5 +++-- 7 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index 6e9c5ade4c2e..ba695338927a 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -246,7 +246,7 @@ static void brcm_sata_init(struct brcm_ahci_priv *priv) } static unsigned int brcm_ahci_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { struct ata_port *ap = dev->link->ap; struct ata_host *host = ap->host; diff --git a/drivers/ata/ahci_ceva.c b/drivers/ata/ahci_ceva.c index e9c7c07fd84c..acf59f51b356 100644 --- a/drivers/ata/ahci_ceva.c +++ b/drivers/ata/ahci_ceva.c @@ -92,9 +92,8 @@ struct ceva_ahci_priv { }; static unsigned int ceva_ahci_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { - __le16 *__id = (__le16 *)id; u32 err_mask; err_mask = ata_do_dev_read_id(dev, tf, id); @@ -104,7 +103,7 @@ static unsigned int ceva_ahci_read_id(struct ata_device *dev, * Since CEVA controller does not support device sleep feature, we * need to clear DEVSLP (bit 8) in word78 of the IDENTIFY DEVICE data. */ - __id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8)); + id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8)); return 0; } diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c index 68ec7e9430b2..8e206379d699 100644 --- a/drivers/ata/ahci_xgene.c +++ b/drivers/ata/ahci_xgene.c @@ -237,7 +237,7 @@ static bool xgene_ahci_is_memram_inited(struct xgene_ahci_context *ctx) * does not support DEVSLP. */ static unsigned int xgene_ahci_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { u32 err_mask; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 9c2947905d1e..67f88027680a 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -1722,7 +1722,7 @@ static u32 ata_pio_mask_no_iordy(const struct ata_device *adev) * this function is wrapped or replaced by the driver */ unsigned int ata_do_dev_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { return ata_exec_internal(dev, tf, NULL, DMA_FROM_DEVICE, id, sizeof(id[0]) * ATA_ID_WORDS, 0); @@ -1795,9 +1795,9 @@ retry: tf.flags |= ATA_TFLAG_POLLING; if (ap->ops->read_id) - err_mask = ap->ops->read_id(dev, &tf, id); + err_mask = ap->ops->read_id(dev, &tf, (__le16 *)id); else - err_mask = ata_do_dev_read_id(dev, &tf, id); + err_mask = ata_do_dev_read_id(dev, &tf, (__le16 *)id); if (err_mask) { if (err_mask & AC_ERR_NODEV_HINT) { diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c index b77ef0046dbe..8a5b4e0079ab 100644 --- a/drivers/ata/pata_it821x.c +++ b/drivers/ata/pata_it821x.c @@ -537,7 +537,7 @@ static void it821x_dev_config(struct ata_device *adev) */ static unsigned int it821x_read_id(struct ata_device *adev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { unsigned int err_mask; unsigned char model_num[ATA_ID_PROD_LEN + 1]; @@ -545,21 +545,20 @@ static unsigned int it821x_read_id(struct ata_device *adev, err_mask = ata_do_dev_read_id(adev, tf, id); if (err_mask) return err_mask; - ata_id_c_string(id, model_num, ATA_ID_PROD, sizeof(model_num)); + ata_id_c_string((u16 *)id, model_num, ATA_ID_PROD, sizeof(model_num)); - id[83] &= ~(1 << 12); /* Cache flush is firmware handled */ - id[83] &= ~(1 << 13); /* Ditto for LBA48 flushes */ - id[84] &= ~(1 << 6); /* No FUA */ - id[85] &= ~(1 << 10); /* No HPA */ - id[76] = 0; /* No NCQ/AN etc */ + id[83] &= cpu_to_le16(~(1 << 12)); /* Cache flush is firmware handled */ + id[84] &= cpu_to_le16(~(1 << 6)); /* No FUA */ + id[85] &= cpu_to_le16(~(1 << 10)); /* No HPA */ + id[76] = 0; /* No NCQ/AN etc */ if (strstr(model_num, "Integrated Technology Express")) { /* Set feature bits the firmware neglects */ - id[49] |= 0x0300; /* LBA, DMA */ - id[83] &= 0x7FFF; - id[83] |= 0x4400; /* Word 83 is valid and LBA48 */ - id[86] |= 0x0400; /* LBA48 on */ - id[ATA_ID_MAJOR_VER] |= 0x1F; + id[49] |= cpu_to_le16(0x0300); /* LBA, DMA */ + id[83] &= cpu_to_le16(0x7FFF); + id[83] |= cpu_to_le16(0x4400); /* Word 83 is valid and LBA48 */ + id[86] |= cpu_to_le16(0x0400); /* LBA48 on */ + id[ATA_ID_MAJOR_VER] |= cpu_to_le16(0x1F); /* Clear the serial number because it's different each boot which breaks validation on resume */ memset(&id[ATA_ID_SERNO], 0x20, ATA_ID_SERNO_LEN); diff --git a/drivers/ata/pata_netcell.c b/drivers/ata/pata_netcell.c index a7ecc1a204b5..06929e77c491 100644 --- a/drivers/ata/pata_netcell.c +++ b/drivers/ata/pata_netcell.c @@ -21,12 +21,13 @@ /* No PIO or DMA methods needed for this device */ static unsigned int netcell_read_id(struct ata_device *adev, - struct ata_taskfile *tf, u16 *id) + struct ata_taskfile *tf, __le16 *id) { unsigned int err_mask = ata_do_dev_read_id(adev, tf, id); + /* Firmware forgets to mark words 85-87 valid */ if (err_mask == 0) - id[ATA_ID_CSF_DEFAULT] |= 0x4000; + id[ATA_ID_CSF_DEFAULT] |= cpu_to_le16(0x4000); return err_mask; } diff --git a/include/linux/libata.h b/include/linux/libata.h index 2e5e7c40c991..bf706cd45674 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -884,7 +884,8 @@ struct ata_port_operations { void (*set_piomode)(struct ata_port *ap, struct ata_device *dev); void (*set_dmamode)(struct ata_port *ap, struct ata_device *dev); int (*set_mode)(struct ata_link *link, struct ata_device **r_failed_dev); - unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, u16 *id); + unsigned int (*read_id)(struct ata_device *dev, struct ata_taskfile *tf, + __le16 *id); void (*dev_config)(struct ata_device *dev); @@ -1119,7 +1120,7 @@ extern void ata_id_string(const u16 *id, unsigned char *s, extern void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len); extern unsigned int ata_do_dev_read_id(struct ata_device *dev, - struct ata_taskfile *tf, u16 *id); + struct ata_taskfile *tf, __le16 *id); extern void ata_qc_complete(struct ata_queued_cmd *qc); extern u64 ata_qc_get_active(struct ata_port *ap); extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd); -- cgit v1.2.3 From b9ba367c513dbc165dd6c01266a59db4be2a3564 Mon Sep 17 00:00:00 2001 From: Paul Menzel Date: Wed, 5 Jan 2022 16:36:16 +0100 Subject: ata: libata: Rename link flag ATA_LFLAG_NO_DB_DELAY Rename the link flag ATA_LFLAG_NO_DB_DELAY to ATA_LFLAG_NO_DEBOUNCE_DELAY. The new name is longer, but clearer. Signed-off-by: Paul Menzel Signed-off-by: Damien Le Moal --- drivers/ata/ahci_brcm.c | 2 +- drivers/ata/libata-sata.c | 2 +- include/linux/libata.h | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/ahci_brcm.c b/drivers/ata/ahci_brcm.c index ba695338927a..64dd8aa397d5 100644 --- a/drivers/ata/ahci_brcm.c +++ b/drivers/ata/ahci_brcm.c @@ -333,7 +333,7 @@ static struct ata_port_operations ahci_brcm_platform_ops = { static const struct ata_port_info ahci_brcm_port_info = { .flags = AHCI_FLAG_COMMON | ATA_FLAG_NO_DIPM, - .link_flags = ATA_LFLAG_NO_DB_DELAY, + .link_flags = ATA_LFLAG_NO_DEBOUNCE_DELAY, .pio_mask = ATA_PIO4, .udma_mask = ATA_UDMA6, .port_ops = &ahci_brcm_platform_ops, diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c index bfe9595d4f33..071158c0c44c 100644 --- a/drivers/ata/libata-sata.c +++ b/drivers/ata/libata-sata.c @@ -317,7 +317,7 @@ int sata_link_resume(struct ata_link *link, const unsigned long *params, * immediately after resuming. Delay 200ms before * debouncing. */ - if (!(link->flags & ATA_LFLAG_NO_DB_DELAY)) + if (!(link->flags & ATA_LFLAG_NO_DEBOUNCE_DELAY)) ata_msleep(link->ap, 200); /* is SControl restored correctly? */ diff --git a/include/linux/libata.h b/include/linux/libata.h index bf706cd45674..605756f645be 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -143,7 +143,7 @@ enum { ATA_LFLAG_NO_LPM = (1 << 8), /* disable LPM on this link */ ATA_LFLAG_RST_ONCE = (1 << 9), /* limit recovery to one reset */ ATA_LFLAG_CHANGED = (1 << 10), /* LPM state changed on this link */ - ATA_LFLAG_NO_DB_DELAY = (1 << 11), /* no debounce delay on link resume */ + ATA_LFLAG_NO_DEBOUNCE_DELAY = (1 << 11), /* no debounce delay on link resume */ /* struct ata_port flags */ ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ -- cgit v1.2.3 From d9679d0013a66849f23057978f92e76b255c50aa Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Wed, 13 Oct 2021 06:55:44 -0400 Subject: virtio: wrap config->reset calls This will enable cleanups down the road. The idea is to disable cbs, then add "flush_queued_cbs" callback as a parameter, this way drivers can flush any work queued after callbacks have been disabled. Signed-off-by: Michael S. Tsirkin Link: https://lore.kernel.org/r/20211013105226.20225-1-mst@redhat.com Signed-off-by: Michael S. Tsirkin --- arch/um/drivers/virt-pci.c | 2 +- drivers/block/virtio_blk.c | 4 ++-- drivers/bluetooth/virtio_bt.c | 2 +- drivers/char/hw_random/virtio-rng.c | 2 +- drivers/char/virtio_console.c | 4 ++-- drivers/crypto/virtio/virtio_crypto_core.c | 8 ++++---- drivers/firmware/arm_scmi/virtio.c | 2 +- drivers/gpio/gpio-virtio.c | 2 +- drivers/gpu/drm/virtio/virtgpu_kms.c | 2 +- drivers/i2c/busses/i2c-virtio.c | 2 +- drivers/iommu/virtio-iommu.c | 2 +- drivers/net/caif/caif_virtio.c | 2 +- drivers/net/virtio_net.c | 4 ++-- drivers/net/wireless/mac80211_hwsim.c | 2 +- drivers/nvdimm/virtio_pmem.c | 2 +- drivers/rpmsg/virtio_rpmsg_bus.c | 2 +- drivers/scsi/virtio_scsi.c | 2 +- drivers/virtio/virtio.c | 6 ++++++ drivers/virtio/virtio_balloon.c | 2 +- drivers/virtio/virtio_input.c | 2 +- drivers/virtio/virtio_mem.c | 2 +- fs/fuse/virtio_fs.c | 4 ++-- include/linux/virtio.h | 1 + net/9p/trans_virtio.c | 2 +- net/vmw_vsock/virtio_transport.c | 4 ++-- sound/virtio/virtio_card.c | 4 ++-- 26 files changed, 40 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/arch/um/drivers/virt-pci.c b/arch/um/drivers/virt-pci.c index c08066633023..22c4d87c9c15 100644 --- a/arch/um/drivers/virt-pci.c +++ b/arch/um/drivers/virt-pci.c @@ -616,7 +616,7 @@ static void um_pci_virtio_remove(struct virtio_device *vdev) int i; /* Stop all virtqueues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); device_set_wakeup_enable(&vdev->dev, false); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 6ae38776e30e..644c6cddad6d 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -977,7 +977,7 @@ static void virtblk_remove(struct virtio_device *vdev) mutex_lock(&vblk->vdev_mutex); /* Stop all the virtqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ vblk->vdev = NULL; @@ -996,7 +996,7 @@ static int virtblk_freeze(struct virtio_device *vdev) struct virtio_blk *vblk = vdev->priv; /* Ensure we don't receive any more interrupts */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 57908ce4fae8..24a9258962fa 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -364,7 +364,7 @@ static void virtbt_remove(struct virtio_device *vdev) struct hci_dev *hdev = vbt->hdev; hci_unregister_dev(hdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); hci_free_dev(hdev); vbt->hdev = NULL; diff --git a/drivers/char/hw_random/virtio-rng.c b/drivers/char/hw_random/virtio-rng.c index 0a7dde135db1..b2bf78b25630 100644 --- a/drivers/char/hw_random/virtio-rng.c +++ b/drivers/char/hw_random/virtio-rng.c @@ -179,7 +179,7 @@ static void remove_common(struct virtio_device *vdev) vi->data_avail = 0; vi->data_idx = 0; complete(&vi->have_data); - vdev->config->reset(vdev); + virtio_reset_device(vdev); if (vi->hwrng_register_done) hwrng_unregister(&vi->hwrng); vdev->config->del_vqs(vdev); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 660c5c388c29..2359889a35a0 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1958,7 +1958,7 @@ static void virtcons_remove(struct virtio_device *vdev) spin_unlock_irq(&pdrvdata_lock); /* Disable interrupts for vqs */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); /* Finish up work that's lined up */ if (use_multiport(portdev)) cancel_work_sync(&portdev->control_work); @@ -2148,7 +2148,7 @@ static int virtcons_freeze(struct virtio_device *vdev) portdev = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); if (use_multiport(portdev)) virtqueue_disable_cb(portdev->c_ivq); diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index e2375d992308..8e977b7627cb 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -404,7 +404,7 @@ static int virtcrypto_probe(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); free_dev: virtcrypto_devmgr_rm_dev(vcrypto); @@ -436,7 +436,7 @@ static void virtcrypto_remove(struct virtio_device *vdev) if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); virtcrypto_clear_crypto_engines(vcrypto); virtcrypto_del_vqs(vcrypto); @@ -456,7 +456,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); @@ -492,7 +492,7 @@ static int virtcrypto_restore(struct virtio_device *vdev) free_engines: virtcrypto_clear_crypto_engines(vcrypto); free_vqs: - vcrypto->vdev->config->reset(vdev); + virtio_reset_device(vdev); virtcrypto_del_vqs(vcrypto); return err; } diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 87039c5c03fd..eefcc4146749 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -452,7 +452,7 @@ static void scmi_vio_remove(struct virtio_device *vdev) * outstanding message on any vqueue to be ignored by complete_cb: now * we can just stop processing buffers and destroy the vqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); /* Ensure scmi_vdev is visible as NULL */ smp_store_mb(scmi_vdev, NULL); diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c index 9f4941bc5760..fcc5e8c08973 100644 --- a/drivers/gpio/gpio-virtio.c +++ b/drivers/gpio/gpio-virtio.c @@ -450,7 +450,7 @@ static void virtio_gpio_request_vq(struct virtqueue *vq) static void virtio_gpio_free_vqs(struct virtio_device *vdev) { - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 21f410901694..3313b92db531 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -279,7 +279,7 @@ void virtio_gpu_deinit(struct drm_device *dev) flush_work(&vgdev->ctrlq.dequeue_work); flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); - vgdev->vdev->config->reset(vgdev->vdev); + virtio_reset_device(vgdev->vdev); vgdev->vdev->config->del_vqs(vgdev->vdev); } diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index 41eb0dcc3204..4b9536f50800 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -165,7 +165,7 @@ err_free: static void virtio_i2c_del_vqs(struct virtio_device *vdev) { - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index 80930ce04a16..1d4e1e7cf175 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -1115,7 +1115,7 @@ static void viommu_remove(struct virtio_device *vdev) iommu_device_unregister(&viommu->iommu); /* Stop all virtqueues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); dev_info(&vdev->dev, "device removed\n"); diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c index 91230894692d..444ef6a342f6 100644 --- a/drivers/net/caif/caif_virtio.c +++ b/drivers/net/caif/caif_virtio.c @@ -754,7 +754,7 @@ static void cfv_remove(struct virtio_device *vdev) debugfs_remove_recursive(cfv->debugfs); vringh_kiov_cleanup(&cfv->ctx.riov); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->vringh_config->del_vrhs(cfv->vdev); cfv->vr_rx = NULL; vdev->config->del_vqs(cfv->vdev); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b107835242ad..eeed458c794e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -3310,7 +3310,7 @@ static int virtnet_probe(struct virtio_device *vdev) return 0; free_unregister_netdev: - vi->vdev->config->reset(vdev); + virtio_reset_device(vdev); unregister_netdev(dev); free_failover: @@ -3326,7 +3326,7 @@ free: static void remove_vq_common(struct virtnet_info *vi) { - vi->vdev->config->reset(vi->vdev); + virtio_reset_device(vi->vdev); /* Free unused buffers in both send and recv, if any. */ free_unused_bufs(vi); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 23219f3747f8..02d374360bcc 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -4498,7 +4498,7 @@ static void remove_vqs(struct virtio_device *vdev) { int i; - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; i < ARRAY_SIZE(hwsim_vqs); i++) { struct virtqueue *vq = hwsim_vqs[i]; diff --git a/drivers/nvdimm/virtio_pmem.c b/drivers/nvdimm/virtio_pmem.c index 726c7354d465..995b6cdc67ed 100644 --- a/drivers/nvdimm/virtio_pmem.c +++ b/drivers/nvdimm/virtio_pmem.c @@ -105,7 +105,7 @@ static void virtio_pmem_remove(struct virtio_device *vdev) nvdimm_bus_unregister(nvdimm_bus); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); } static struct virtio_driver virtio_pmem_driver = { diff --git a/drivers/rpmsg/virtio_rpmsg_bus.c b/drivers/rpmsg/virtio_rpmsg_bus.c index 9c112aa65040..4bda40568dc9 100644 --- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -1024,7 +1024,7 @@ static void rpmsg_remove(struct virtio_device *vdev) size_t total_buf_space = vrp->num_bufs * vrp->buf_size; int ret; - vdev->config->reset(vdev); + virtio_reset_device(vdev); ret = device_for_each_child(&vdev->dev, NULL, rpmsg_remove_device); if (ret) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 28e1d98ae102..c616c7171cc4 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -778,7 +778,7 @@ static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq, static void virtscsi_remove_vqs(struct virtio_device *vdev) { /* Stop all the virtqueues. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); } diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 236081afe9a2..00ac9db792a4 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -204,6 +204,12 @@ int virtio_finalize_features(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_finalize_features); +void virtio_reset_device(struct virtio_device *dev) +{ + dev->config->reset(dev); +} +EXPORT_SYMBOL_GPL(virtio_reset_device); + static int virtio_dev_probe(struct device *_d) { int err, i; diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index c22ff0117b46..f4c34a2a6b8e 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -1056,7 +1056,7 @@ static void remove_common(struct virtio_balloon *vb) return_free_pages_to_mm(vb, ULONG_MAX); /* Now we reset the device so we can clean up the queues. */ - vb->vdev->config->reset(vb->vdev); + virtio_reset_device(vb->vdev); vb->vdev->config->del_vqs(vb->vdev); } diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c index ce51ae165943..3aa46703872d 100644 --- a/drivers/virtio/virtio_input.c +++ b/drivers/virtio/virtio_input.c @@ -347,7 +347,7 @@ static void virtinput_remove(struct virtio_device *vdev) spin_unlock_irqrestore(&vi->lock, flags); input_unregister_device(vi->idev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL) kfree(buf); vdev->config->del_vqs(vdev); diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 96e5a8782769..033fb93ed528 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -2850,7 +2850,7 @@ static void virtio_mem_remove(struct virtio_device *vdev) virtio_mem_deinit_hotplug(vm); /* reset the device and cleanup the queues */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); kfree(vm); diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index 4cfa4bc1f579..ca2cac196d73 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -895,7 +895,7 @@ static int virtio_fs_probe(struct virtio_device *vdev) return 0; out_vqs: - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev, fs); kfree(fs->vqs); @@ -927,7 +927,7 @@ static void virtio_fs_remove(struct virtio_device *vdev) list_del_init(&fs->list); virtio_fs_stop_all_queues(fs); virtio_fs_drain_all_queues_locked(fs); - vdev->config->reset(vdev); + virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev, fs); vdev->priv = NULL; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 41edbc01ffa4..72292a62cd90 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -138,6 +138,7 @@ int virtio_finalize_features(struct virtio_device *dev); int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); #endif +void virtio_reset_device(struct virtio_device *dev); size_t virtio_max_dma_size(struct virtio_device *vdev); diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index bd5a89c4960d..8ff6d7160677 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -721,7 +721,7 @@ static void p9_virtio_remove(struct virtio_device *vdev) mutex_unlock(&virtio_9p_lock); - vdev->config->reset(vdev); + virtio_reset_device(vdev); vdev->config->del_vqs(vdev); sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr); diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 4f7c99dfd16c..fb3302fff627 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -665,7 +665,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) vsock_for_each_connected_socket(virtio_vsock_reset_sock); /* Stop all work handlers to make sure no one is accessing the device, - * so we can safely call vdev->config->reset(). + * so we can safely call virtio_reset_device(). */ mutex_lock(&vsock->rx_lock); vsock->rx_run = false; @@ -682,7 +682,7 @@ static void virtio_vsock_remove(struct virtio_device *vdev) /* Flush all device writes and interrupts, device will not use any * more buffers. */ - vdev->config->reset(vdev); + virtio_reset_device(vdev); mutex_lock(&vsock->rx_lock); while ((pkt = virtqueue_detach_unused_buf(vsock->vqs[VSOCK_VQ_RX]))) diff --git a/sound/virtio/virtio_card.c b/sound/virtio/virtio_card.c index 150ab3e37013..e2847c040f75 100644 --- a/sound/virtio/virtio_card.c +++ b/sound/virtio/virtio_card.c @@ -350,7 +350,7 @@ static void virtsnd_remove(struct virtio_device *vdev) snd_card_free(snd->card); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; snd->substreams && i < snd->nsubstreams; ++i) { struct virtio_pcm_substream *vss = &snd->substreams[i]; @@ -379,7 +379,7 @@ static int virtsnd_freeze(struct virtio_device *vdev) virtsnd_ctl_msg_cancel_all(snd); vdev->config->del_vqs(vdev); - vdev->config->reset(vdev); + virtio_reset_device(vdev); for (i = 0; i < snd->nsubstreams; ++i) cancel_work_sync(&snd->substreams[i].elapsed_period); -- cgit v1.2.3 From 539fec78edb4e084e7c532affc56cc42d4ceea4b Mon Sep 17 00:00:00 2001 From: Stefano Garzarella Date: Fri, 26 Nov 2021 17:47:53 +0100 Subject: vdpa: add driver_override support `driver_override` allows to control which of the vDPA bus drivers binds to a vDPA device. If `driver_override` is not set, the previous behaviour is followed: devices use the first vDPA bus driver loaded (unless auto binding is disabled). Tested on Fedora 34 with driverctl(8): $ modprobe virtio-vdpa $ modprobe vhost-vdpa $ modprobe vdpa-sim-net $ vdpa dev add mgmtdev vdpasim_net name dev1 # dev1 is attached to the first vDPA bus driver loaded $ driverctl -b vdpa list-devices dev1 virtio_vdpa $ driverctl -b vdpa set-override dev1 vhost_vdpa $ driverctl -b vdpa list-devices dev1 vhost_vdpa [*] Note: driverctl(8) integrates with udev so the binding is preserved. Suggested-by: Jason Wang Acked-by: Jason Wang Signed-off-by: Stefano Garzarella Link: https://lore.kernel.org/r/20211126164753.181829-3-sgarzare@redhat.com Signed-off-by: Michael S. Tsirkin --- Documentation/ABI/testing/sysfs-bus-vdpa | 20 +++++++++ drivers/vdpa/vdpa.c | 74 ++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 2 + 3 files changed, 96 insertions(+) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-vdpa b/Documentation/ABI/testing/sysfs-bus-vdpa index 4e55761a39df..28a6111202ba 100644 --- a/Documentation/ABI/testing/sysfs-bus-vdpa +++ b/Documentation/ABI/testing/sysfs-bus-vdpa @@ -35,3 +35,23 @@ Description: Writing a device name to this file will cause the driver to attempt to unbind from the device. This may be useful when overriding default bindings. + +What: /sys/bus/vdpa/devices/.../driver_override +Date: November 2021 +Contact: virtualization@lists.linux-foundation.org +Description: + This file allows the driver for a device to be specified. + When specified, only a driver with a name matching the value + written to driver_override will have an opportunity to bind to + the device. The override is specified by writing a string to the + driver_override file (echo vhost-vdpa > driver_override) and may + be cleared with an empty string (echo > driver_override). + This returns the device to standard matching rules binding. + Writing to driver_override does not automatically unbind the + device from its current driver or make any attempt to + automatically load the specified driver. If no driver with a + matching name is currently loaded in the kernel, the device will + not bind to any driver. This also allows devices to opt-out of + driver binding using a driver_override name such as "none". + Only a single driver may be specified in the override, there is + no support for parsing delimiters. diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 09bbe53c3ac4..59d0b8bbb79c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -52,8 +52,81 @@ static void vdpa_dev_remove(struct device *d) drv->remove(vdev); } +static int vdpa_dev_match(struct device *dev, struct device_driver *drv) +{ + struct vdpa_device *vdev = dev_to_vdpa(dev); + + /* Check override first, and if set, only use the named driver */ + if (vdev->driver_override) + return strcmp(vdev->driver_override, drv->name) == 0; + + /* Currently devices must be supported by all vDPA bus drivers */ + return 1; +} + +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct vdpa_device *vdev = dev_to_vdpa(dev); + const char *driver_override, *old; + char *cp; + + /* We need to keep extra room for a newline */ + if (count >= (PAGE_SIZE - 1)) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + device_lock(dev); + old = vdev->driver_override; + if (strlen(driver_override)) { + vdev->driver_override = driver_override; + } else { + kfree(driver_override); + vdev->driver_override = NULL; + } + device_unlock(dev); + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct vdpa_device *vdev = dev_to_vdpa(dev); + ssize_t len; + + device_lock(dev); + len = snprintf(buf, PAGE_SIZE, "%s\n", vdev->driver_override); + device_unlock(dev); + + return len; +} +static DEVICE_ATTR_RW(driver_override); + +static struct attribute *vdpa_dev_attrs[] = { + &dev_attr_driver_override.attr, + NULL, +}; + +static const struct attribute_group vdpa_dev_group = { + .attrs = vdpa_dev_attrs, +}; +__ATTRIBUTE_GROUPS(vdpa_dev); + static struct bus_type vdpa_bus = { .name = "vdpa", + .dev_groups = vdpa_dev_groups, + .match = vdpa_dev_match, .probe = vdpa_dev_probe, .remove = vdpa_dev_remove, }; @@ -68,6 +141,7 @@ static void vdpa_release_dev(struct device *d) ida_simple_remove(&vdpa_index_ida, vdev->index); mutex_destroy(&vdev->cf_mutex); + kfree(vdev->driver_override); kfree(vdev); } diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index c3011ccda430..ae34015b37b7 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -64,6 +64,7 @@ struct vdpa_mgmt_dev; * struct vdpa_device - representation of a vDPA device * @dev: underlying device * @dma_dev: the actual device that is performing DMA + * @driver_override: driver name to force a match * @config: the configuration ops for this device. * @cf_mutex: Protects get and set access to configuration layout. * @index: device index @@ -76,6 +77,7 @@ struct vdpa_mgmt_dev; struct vdpa_device { struct device dev; struct device *dma_dev; + const char *driver_override; const struct vdpa_config_ops *config; struct mutex cf_mutex; /* Protects get/set config */ unsigned int index; -- cgit v1.2.3 From 28cc408be72cebb0f3fcc37bc74ab3196d4de726 Mon Sep 17 00:00:00 2001 From: Eugenio Pérez Date: Thu, 4 Nov 2021 20:52:48 +0100 Subject: vdpa: Mark vdpa_config_ops.get_vq_notification as optional MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since vhost_vdpa_mmap checks for its existence before calling it. Signed-off-by: Eugenio Pérez Link: https://lore.kernel.org/r/20211104195248.2088904-1-eperezma@redhat.com Signed-off-by: Michael S. Tsirkin Acked-by: Jason Wang Reviewed-by: Stefano Garzarella --- include/linux/vdpa.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index ae34015b37b7..2b7db96bb7d3 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -157,7 +157,7 @@ struct vdpa_map_file { * @vdev: vdpa device * @idx: virtqueue index * @state: pointer to returned state (last_avail_idx) - * @get_vq_notification: Get the notification area for a virtqueue + * @get_vq_notification: Get the notification area for a virtqueue (optional) * @vdev: vdpa device * @idx: virtqueue index * Returns the notifcation area -- cgit v1.2.3 From a64917bc2e9b1e0aa716b783c4ec879fdd280300 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 5 Jan 2022 13:46:33 +0200 Subject: vdpa: Provide interface to read driver features Provide an interface to read the negotiated features. This is needed when building the netlink message in vdpa_dev_net_config_fill(). Also fix the implementation of vdpa_dev_net_config_fill() to use the negotiated features instead of the device features. To make APIs clearer, make the following name changes to struct vdpa_config_ops so they better describe their operations: get_features -> get_device_features set_features -> set_driver_features Finally, add get_driver_features to return the negotiated features and add implementation to all the upstream drivers. Acked-by: Jason Wang Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220105114646.577224-2-elic@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/alibaba/eni_vdpa.c | 16 ++++++++++++---- drivers/vdpa/ifcvf/ifcvf_main.c | 16 ++++++++++++---- drivers/vdpa/mlx5/net/mlx5_vnet.c | 16 ++++++++++++---- drivers/vdpa/vdpa.c | 2 +- drivers/vdpa/vdpa_sim/vdpa_sim.c | 21 +++++++++++++++------ drivers/vdpa/vdpa_user/vduse_dev.c | 16 ++++++++++++---- drivers/vdpa/virtio_pci/vp_vdpa.c | 16 ++++++++++++---- drivers/vhost/vdpa.c | 2 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 14 +++++++++----- 10 files changed, 87 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/alibaba/eni_vdpa.c b/drivers/vdpa/alibaba/eni_vdpa.c index fe1b83b5f80d..f480d54f308c 100644 --- a/drivers/vdpa/alibaba/eni_vdpa.c +++ b/drivers/vdpa/alibaba/eni_vdpa.c @@ -58,7 +58,7 @@ static struct virtio_pci_legacy_device *vdpa_to_ldev(struct vdpa_device *vdpa) return &eni_vdpa->ldev; } -static u64 eni_vdpa_get_features(struct vdpa_device *vdpa) +static u64 eni_vdpa_get_device_features(struct vdpa_device *vdpa) { struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); u64 features = vp_legacy_get_features(ldev); @@ -69,7 +69,7 @@ static u64 eni_vdpa_get_features(struct vdpa_device *vdpa) return features; } -static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int eni_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); @@ -84,6 +84,13 @@ static int eni_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 eni_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); + + return vp_legacy_get_driver_features(ldev); +} + static u8 eni_vdpa_get_status(struct vdpa_device *vdpa) { struct virtio_pci_legacy_device *ldev = vdpa_to_ldev(vdpa); @@ -401,8 +408,9 @@ static void eni_vdpa_set_config_cb(struct vdpa_device *vdpa, } static const struct vdpa_config_ops eni_vdpa_ops = { - .get_features = eni_vdpa_get_features, - .set_features = eni_vdpa_set_features, + .get_device_features = eni_vdpa_get_device_features, + .set_driver_features = eni_vdpa_set_driver_features, + .get_driver_features = eni_vdpa_get_driver_features, .get_status = eni_vdpa_get_status, .set_status = eni_vdpa_set_status, .reset = eni_vdpa_reset, diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index 92ba7126e5d6..d1a6b5ab543c 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -169,7 +169,7 @@ static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev) return &adapter->vf; } -static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) +static u64 ifcvf_vdpa_get_device_features(struct vdpa_device *vdpa_dev) { struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev); struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); @@ -187,7 +187,7 @@ static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev) return features; } -static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) +static int ifcvf_vdpa_set_driver_features(struct vdpa_device *vdpa_dev, u64 features) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); int ret; @@ -201,6 +201,13 @@ static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features) return 0; } +static u64 ifcvf_vdpa_get_driver_features(struct vdpa_device *vdpa_dev) +{ + struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); + + return vf->req_features; +} + static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev) { struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev); @@ -426,8 +433,9 @@ static struct vdpa_notification_area ifcvf_get_vq_notification(struct vdpa_devic * implemented set_map()/dma_map()/dma_unmap() */ static const struct vdpa_config_ops ifc_vdpa_ops = { - .get_features = ifcvf_vdpa_get_features, - .set_features = ifcvf_vdpa_set_features, + .get_device_features = ifcvf_vdpa_get_device_features, + .set_driver_features = ifcvf_vdpa_set_driver_features, + .get_driver_features = ifcvf_vdpa_get_driver_features, .get_status = ifcvf_vdpa_get_status, .set_status = ifcvf_vdpa_set_status, .reset = ifcvf_vdpa_reset, diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index c104d7699c16..3206e355230c 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1878,7 +1878,7 @@ static u64 mlx_to_vritio_features(u16 dev_features) return result; } -static u64 mlx5_vdpa_get_features(struct vdpa_device *vdev) +static u64 mlx5_vdpa_get_device_features(struct vdpa_device *vdev) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); @@ -1971,7 +1971,7 @@ static void update_cvq_info(struct mlx5_vdpa_dev *mvdev) } } -static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features) +static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) { struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); @@ -2338,6 +2338,13 @@ static int mlx5_get_vq_irq(struct vdpa_device *vdv, u16 idx) return -EOPNOTSUPP; } +static u64 mlx5_vdpa_get_driver_features(struct vdpa_device *vdev) +{ + struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev); + + return mvdev->actual_features; +} + static const struct vdpa_config_ops mlx5_vdpa_ops = { .set_vq_address = mlx5_vdpa_set_vq_address, .set_vq_num = mlx5_vdpa_set_vq_num, @@ -2350,8 +2357,9 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .get_vq_notification = mlx5_get_vq_notification, .get_vq_irq = mlx5_get_vq_irq, .get_vq_align = mlx5_vdpa_get_vq_align, - .get_features = mlx5_vdpa_get_features, - .set_features = mlx5_vdpa_set_features, + .get_device_features = mlx5_vdpa_get_device_features, + .set_driver_features = mlx5_vdpa_set_driver_features, + .get_driver_features = mlx5_vdpa_get_driver_features, .set_config_cb = mlx5_vdpa_set_config_cb, .get_vq_num_max = mlx5_vdpa_get_vq_num_max, .get_device_id = mlx5_vdpa_get_device_id, diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 59d0b8bbb79c..42d71d60d5dc 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -808,7 +808,7 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16)) return -EMSGSIZE; - features = vdev->config->get_features(vdev); + features = vdev->config->get_driver_features(vdev); return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); } diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c index 41b0cd17fcba..ddbe142af09a 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c @@ -399,14 +399,14 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa) return VDPASIM_QUEUE_ALIGN; } -static u64 vdpasim_get_features(struct vdpa_device *vdpa) +static u64 vdpasim_get_device_features(struct vdpa_device *vdpa) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); return vdpasim->dev_attr.supported_features; } -static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) +static int vdpasim_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct vdpasim *vdpasim = vdpa_to_sim(vdpa); @@ -419,6 +419,13 @@ static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vdpasim_get_driver_features(struct vdpa_device *vdpa) +{ + struct vdpasim *vdpasim = vdpa_to_sim(vdpa); + + return vdpasim->features; +} + static void vdpasim_set_config_cb(struct vdpa_device *vdpa, struct vdpa_callback *cb) { @@ -613,8 +620,9 @@ static const struct vdpa_config_ops vdpasim_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, - .get_features = vdpasim_get_features, - .set_features = vdpasim_set_features, + .get_device_features = vdpasim_get_device_features, + .set_driver_features = vdpasim_set_driver_features, + .get_driver_features = vdpasim_get_driver_features, .set_config_cb = vdpasim_set_config_cb, .get_vq_num_max = vdpasim_get_vq_num_max, .get_device_id = vdpasim_get_device_id, @@ -642,8 +650,9 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = { .set_vq_state = vdpasim_set_vq_state, .get_vq_state = vdpasim_get_vq_state, .get_vq_align = vdpasim_get_vq_align, - .get_features = vdpasim_get_features, - .set_features = vdpasim_set_features, + .get_device_features = vdpasim_get_device_features, + .set_driver_features = vdpasim_set_driver_features, + .get_driver_features = vdpasim_get_driver_features, .set_config_cb = vdpasim_set_config_cb, .get_vq_num_max = vdpasim_get_vq_num_max, .get_device_id = vdpasim_get_device_id, diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c index f3cc7dde39af..f85d1a08ed87 100644 --- a/drivers/vdpa/vdpa_user/vduse_dev.c +++ b/drivers/vdpa/vdpa_user/vduse_dev.c @@ -573,14 +573,14 @@ static u32 vduse_vdpa_get_vq_align(struct vdpa_device *vdpa) return dev->vq_align; } -static u64 vduse_vdpa_get_features(struct vdpa_device *vdpa) +static u64 vduse_vdpa_get_device_features(struct vdpa_device *vdpa) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); return dev->device_features; } -static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int vduse_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct vduse_dev *dev = vdpa_to_vduse(vdpa); @@ -588,6 +588,13 @@ static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vduse_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct vduse_dev *dev = vdpa_to_vduse(vdpa); + + return dev->driver_features; +} + static void vduse_vdpa_set_config_cb(struct vdpa_device *vdpa, struct vdpa_callback *cb) { @@ -721,8 +728,9 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = { .set_vq_state = vduse_vdpa_set_vq_state, .get_vq_state = vduse_vdpa_get_vq_state, .get_vq_align = vduse_vdpa_get_vq_align, - .get_features = vduse_vdpa_get_features, - .set_features = vduse_vdpa_set_features, + .get_device_features = vduse_vdpa_get_device_features, + .set_driver_features = vduse_vdpa_set_driver_features, + .get_driver_features = vduse_vdpa_get_driver_features, .set_config_cb = vduse_vdpa_set_config_cb, .get_vq_num_max = vduse_vdpa_get_vq_num_max, .get_device_id = vduse_vdpa_get_device_id, diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index e3ff7875e123..a57e381e830b 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -53,14 +53,14 @@ static struct virtio_pci_modern_device *vdpa_to_mdev(struct vdpa_device *vdpa) return &vp_vdpa->mdev; } -static u64 vp_vdpa_get_features(struct vdpa_device *vdpa) +static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); return vp_modern_get_features(mdev); } -static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features) +static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -69,6 +69,13 @@ static int vp_vdpa_set_features(struct vdpa_device *vdpa, u64 features) return 0; } +static u64 vp_vdpa_get_driver_features(struct vdpa_device *vdpa) +{ + struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); + + return vp_modern_get_driver_features(mdev); +} + static u8 vp_vdpa_get_status(struct vdpa_device *vdpa) { struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa); @@ -415,8 +422,9 @@ vp_vdpa_get_vq_notification(struct vdpa_device *vdpa, u16 qid) } static const struct vdpa_config_ops vp_vdpa_ops = { - .get_features = vp_vdpa_get_features, - .set_features = vp_vdpa_set_features, + .get_device_features = vp_vdpa_get_device_features, + .set_driver_features = vp_vdpa_set_driver_features, + .get_driver_features = vp_vdpa_get_driver_features, .get_status = vp_vdpa_get_status, .set_status = vp_vdpa_set_status, .reset = vp_vdpa_reset, diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index ecfccd687ea0..a8fa7fc6db1e 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -262,7 +262,7 @@ static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep) const struct vdpa_config_ops *ops = vdpa->config; u64 features; - features = ops->get_features(vdpa); + features = ops->get_device_features(vdpa); if (copy_to_user(featurep, &features, sizeof(features))) return -EFAULT; diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index f85f860bc10b..a84b04ba3195 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -308,7 +308,7 @@ static u64 virtio_vdpa_get_features(struct virtio_device *vdev) struct vdpa_device *vdpa = vd_get_vdpa(vdev); const struct vdpa_config_ops *ops = vdpa->config; - return ops->get_features(vdpa); + return ops->get_device_features(vdpa); } static int virtio_vdpa_finalize_features(struct virtio_device *vdev) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2b7db96bb7d3..9cc4291a79b3 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -171,14 +171,17 @@ struct vdpa_map_file { * for the device * @vdev: vdpa device * Returns virtqueue algin requirement - * @get_features: Get virtio features supported by the device + * @get_device_features: Get virtio features supported by the device * @vdev: vdpa device * Returns the virtio features support by the * device - * @set_features: Set virtio features supported by the driver + * @set_driver_features: Set virtio features supported by the driver * @vdev: vdpa device * @features: feature support by the driver * Returns integer: success (0) or error (< 0) + * @get_driver_features: Get the virtio driver features in action + * @vdev: vdpa device + * Returns the virtio features accepted * @set_config_cb: Set the config interrupt callback * @vdev: vdpa device * @cb: virtio-vdev interrupt callback structure @@ -278,8 +281,9 @@ struct vdpa_config_ops { /* Device ops */ u32 (*get_vq_align)(struct vdpa_device *vdev); - u64 (*get_features)(struct vdpa_device *vdev); - int (*set_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_device_features)(struct vdpa_device *vdev); + int (*set_driver_features)(struct vdpa_device *vdev, u64 features); + u64 (*get_driver_features)(struct vdpa_device *vdev); void (*set_config_cb)(struct vdpa_device *vdev, struct vdpa_callback *cb); u16 (*get_vq_num_max)(struct vdpa_device *vdev); @@ -397,7 +401,7 @@ static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) const struct vdpa_config_ops *ops = vdev->config; vdev->features_valid = true; - return ops->set_features(vdev, features); + return ops->set_driver_features(vdev, features); } void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, -- cgit v1.2.3 From 73bc0dbb591baea322a7319c735e5f6c7dba9cfb Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 5 Jan 2022 13:46:35 +0200 Subject: vdpa: Sync calls set/get config/status with cf_mutex Add wrappers to get/set status and protect these operations with cf_mutex to serialize these operations with respect to get/set config operations. Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220105114646.577224-4-elic@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 19 +++++++++++++++++++ drivers/vhost/vdpa.c | 7 +++---- drivers/virtio/virtio_vdpa.c | 3 +-- include/linux/vdpa.h | 3 +++ 4 files changed, 26 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 42d71d60d5dc..5134c83c4a22 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -21,6 +21,25 @@ static LIST_HEAD(mdev_head); static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); +u8 vdpa_get_status(struct vdpa_device *vdev) +{ + u8 status; + + mutex_lock(&vdev->cf_mutex); + status = vdev->config->get_status(vdev); + mutex_unlock(&vdev->cf_mutex); + return status; +} +EXPORT_SYMBOL(vdpa_get_status); + +void vdpa_set_status(struct vdpa_device *vdev, u8 status) +{ + mutex_lock(&vdev->cf_mutex); + vdev->config->set_status(vdev, status); + mutex_unlock(&vdev->cf_mutex); +} +EXPORT_SYMBOL(vdpa_set_status); + static struct genl_family vdpa_nl_family; static int vdpa_dev_probe(struct device *d) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index a8fa7fc6db1e..293c51fdf9ab 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -142,10 +142,9 @@ static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) static long vhost_vdpa_get_status(struct vhost_vdpa *v, u8 __user *statusp) { struct vdpa_device *vdpa = v->vdpa; - const struct vdpa_config_ops *ops = vdpa->config; u8 status; - status = ops->get_status(vdpa); + status = vdpa_get_status(vdpa); if (copy_to_user(statusp, &status, sizeof(status))) return -EFAULT; @@ -164,7 +163,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) if (copy_from_user(&status, statusp, sizeof(status))) return -EFAULT; - status_old = ops->get_status(vdpa); + status_old = vdpa_get_status(vdpa); /* * Userspace shouldn't remove status bits unless reset the @@ -182,7 +181,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) if (ret) return ret; } else - ops->set_status(vdpa, status); + vdpa_set_status(vdpa, status); if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) for (i = 0; i < nvqs; i++) diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index a84b04ba3195..76504559bc25 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -91,9 +91,8 @@ static u8 virtio_vdpa_get_status(struct virtio_device *vdev) static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status) { struct vdpa_device *vdpa = vd_get_vdpa(vdev); - const struct vdpa_config_ops *ops = vdpa->config; - return ops->set_status(vdpa, status); + return vdpa_set_status(vdpa, status); } static void virtio_vdpa_reset(struct virtio_device *vdev) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 9cc4291a79b3..ae047fae2603 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -408,6 +408,9 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, const void *buf, unsigned int length); +u8 vdpa_get_status(struct vdpa_device *vdev); +void vdpa_set_status(struct vdpa_device *vdev, u8 status); + /** * struct vdpa_mgmtdev_ops - vdpa device ops * @dev_add: Add a vdpa device using alloc and register -- cgit v1.2.3 From aba21aff772b8622e08f07219069be793429a48f Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 5 Jan 2022 13:46:37 +0200 Subject: vdpa: Allow to configure max data virtqueues Add netlink support to configure the max virtqueue pairs for a device. At least one pair is required. The maximum is dictated by the device. Example: $ vdpa dev add name vdpa-a mgmtdev auxiliary/mlx5_core.sf.1 max_vqp 4 Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220105114646.577224-6-elic@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 15 +++++++++++++-- drivers/vhost/vdpa.c | 2 +- drivers/virtio/virtio_vdpa.c | 2 +- include/linux/vdpa.h | 19 ++++++++++++++++--- 4 files changed, 31 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 4494325cae91..96d31b80fdce 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -404,7 +404,7 @@ static void vdpa_get_config_unlocked(struct vdpa_device *vdev, * If it does happen we assume a legacy guest. */ if (!vdev->features_valid) - vdpa_set_features(vdev, 0); + vdpa_set_features(vdev, 0, true); ops->get_config(vdev, offset, buf, len); } @@ -581,7 +581,8 @@ out: } #define VDPA_DEV_NET_ATTRS_MASK ((1 << VDPA_ATTR_DEV_NET_CFG_MACADDR) | \ - (1 << VDPA_ATTR_DEV_NET_CFG_MTU)) + (1 << VDPA_ATTR_DEV_NET_CFG_MTU) | \ + (1 << VDPA_ATTR_DEV_NET_CFG_MAX_VQP)) static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *info) { @@ -607,6 +608,16 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MTU]); config.mask |= (1 << VDPA_ATTR_DEV_NET_CFG_MTU); } + if (nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]) { + config.net.max_vq_pairs = + nla_get_u16(nl_attrs[VDPA_ATTR_DEV_NET_CFG_MAX_VQP]); + if (!config.net.max_vq_pairs) { + NL_SET_ERR_MSG_MOD(info->extack, + "At least one pair of VQs is required"); + return -EINVAL; + } + config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP); + } /* Skip checking capability if user didn't prefer to configure any * device networking attributes. It is likely that user might have used diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 293c51fdf9ab..6e7edaf2472b 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -285,7 +285,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; - if (vdpa_set_features(vdpa, features)) + if (vdpa_set_features(vdpa, features, false)) return -EINVAL; return 0; diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index 76504559bc25..7767a7f0119b 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -317,7 +317,7 @@ static int virtio_vdpa_finalize_features(struct virtio_device *vdev) /* Give virtio_ring a chance to accept features. */ vring_transport_features(vdev); - return vdpa_set_features(vdpa, vdev->features); + return vdpa_set_features(vdpa, vdev->features, false); } static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index ae047fae2603..6d4d7e4fe208 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -101,6 +101,7 @@ struct vdpa_dev_set_config { struct { u8 mac[ETH_ALEN]; u16 mtu; + u16 max_vq_pairs; } net; u64 mask; }; @@ -391,17 +392,29 @@ static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev) static inline int vdpa_reset(struct vdpa_device *vdev) { const struct vdpa_config_ops *ops = vdev->config; + int ret; + mutex_lock(&vdev->cf_mutex); vdev->features_valid = false; - return ops->reset(vdev); + ret = ops->reset(vdev); + mutex_unlock(&vdev->cf_mutex); + return ret; } -static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features, bool locked) { const struct vdpa_config_ops *ops = vdev->config; + int ret; + + if (!locked) + mutex_lock(&vdev->cf_mutex); vdev->features_valid = true; - return ops->set_driver_features(vdev, features); + ret = ops->set_driver_features(vdev, features); + if (!locked) + mutex_unlock(&vdev->cf_mutex); + + return ret; } void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, -- cgit v1.2.3 From cd2629f6df1cab5b3df34705ae7f3bde6147fce3 Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Wed, 5 Jan 2022 13:46:42 +0200 Subject: vdpa: Support reporting max device capabilities Add max_supported_vqs and supported_features fields to struct vdpa_mgmt_dev. Upstream drivers need to feel these values according to the device capabilities. These values are reported back in a netlink message when showing management devices. Examples: $ auxiliary/mlx5_core.sf.1: supported_classes net max_supported_vqs 257 dev_features CSUM GUEST_CSUM MTU HOST_TSO4 HOST_TSO6 STATUS CTRL_VQ MQ \ CTRL_MAC_ADDR VERSION_1 ACCESS_PLATFORM $ vdpa -j mgmtdev show {"mgmtdev":{"auxiliary/mlx5_core.sf.1":{"supported_classes":["net"], \ "max_supported_vqs":257,"dev_features":["CSUM","GUEST_CSUM","MTU", \ "HOST_TSO4","HOST_TSO6","STATUS","CTRL_VQ","MQ","CTRL_MAC_ADDR", \ "VERSION_1","ACCESS_PLATFORM"]}}} $ vdpa -jp mgmtdev show { "mgmtdev": { "auxiliary/mlx5_core.sf.1": { "supported_classes": [ "net" ], "max_supported_vqs": 257, "dev_features": ["CSUM","GUEST_CSUM","MTU","HOST_TSO4", \ "HOST_TSO6","STATUS","CTRL_VQ","MQ", \ "CTRL_MAC_ADDR","VERSION_1","ACCESS_PLATFORM"] } } } Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220105114646.577224-11-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu --- drivers/vdpa/vdpa.c | 10 ++++++++++ include/linux/vdpa.h | 2 ++ include/uapi/linux/vdpa.h | 2 ++ 3 files changed, 14 insertions(+) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 60cf821175fa..34fa251db8cc 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -514,6 +514,16 @@ static int vdpa_mgmtdev_fill(const struct vdpa_mgmt_dev *mdev, struct sk_buff *m err = -EMSGSIZE; goto msg_err; } + if (nla_put_u32(msg, VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, + mdev->max_supported_vqs)) { + err = -EMSGSIZE; + goto msg_err; + } + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_SUPPORTED_FEATURES, + mdev->supported_features, VDPA_ATTR_PAD)) { + err = -EMSGSIZE; + goto msg_err; + } genlmsg_end(msg, hdr); return 0; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 6d4d7e4fe208..a6047fd6cf12 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -460,6 +460,8 @@ struct vdpa_mgmt_dev { const struct virtio_device_id *id_table; u64 config_attr_mask; struct list_head list; + u64 supported_features; + u32 max_supported_vqs; }; int vdpa_mgmtdev_register(struct vdpa_mgmt_dev *mdev); diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index db3738ef3beb..1061d8d2d09d 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -44,6 +44,8 @@ enum vdpa_attr { VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ VDPA_ATTR_DEV_NEGOTIATED_FEATURES, /* u64 */ + VDPA_ATTR_DEV_MGMTDEV_MAX_VQS, /* u32 */ + VDPA_ATTR_DEV_SUPPORTED_FEATURES, /* u64 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From f6d955d80830b6e6f6a170be68cc3628f36365dd Mon Sep 17 00:00:00 2001 From: Eli Cohen Date: Tue, 11 Jan 2022 20:33:57 +0200 Subject: vdpa: Avoid taking cf_mutex lock on get status Avoid the wrapper holding cf_mutex since it is not protecting anything. To avoid confusion and unnecessary overhead incurred by it, remove. Fixes: f489f27bc0ab ("vdpa: Sync calls set/get config/status with cf_mutex") Signed-off-by: Eli Cohen Link: https://lore.kernel.org/r/20220111183400.38418-2-elic@nvidia.com Signed-off-by: Michael S. Tsirkin Reviewed-by: Si-Wei Liu Acked-by: Jason Wang --- drivers/vdpa/vdpa.c | 11 ----------- drivers/vhost/vdpa.c | 5 +++-- include/linux/vdpa.h | 1 - 3 files changed, 3 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 4380367d00b5..9846c9de4bfa 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -21,17 +21,6 @@ static LIST_HEAD(mdev_head); static DEFINE_MUTEX(vdpa_dev_mutex); static DEFINE_IDA(vdpa_index_ida); -u8 vdpa_get_status(struct vdpa_device *vdev) -{ - u8 status; - - mutex_lock(&vdev->cf_mutex); - status = vdev->config->get_status(vdev); - mutex_unlock(&vdev->cf_mutex); - return status; -} -EXPORT_SYMBOL(vdpa_get_status); - void vdpa_set_status(struct vdpa_device *vdev, u8 status) { mutex_lock(&vdev->cf_mutex); diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 6e7edaf2472b..0ed6cbadb52d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -142,9 +142,10 @@ static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp) static long vhost_vdpa_get_status(struct vhost_vdpa *v, u8 __user *statusp) { struct vdpa_device *vdpa = v->vdpa; + const struct vdpa_config_ops *ops = vdpa->config; u8 status; - status = vdpa_get_status(vdpa); + status = ops->get_status(vdpa); if (copy_to_user(statusp, &status, sizeof(status))) return -EFAULT; @@ -163,7 +164,7 @@ static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp) if (copy_from_user(&status, statusp, sizeof(status))) return -EFAULT; - status_old = vdpa_get_status(vdpa); + status_old = ops->get_status(vdpa); /* * Userspace shouldn't remove status bits unless reset the diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index a6047fd6cf12..2de442ececae 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -421,7 +421,6 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, void *buf, unsigned int len); void vdpa_set_config(struct vdpa_device *dev, unsigned int offset, const void *buf, unsigned int length); -u8 vdpa_get_status(struct vdpa_device *vdev); void vdpa_set_status(struct vdpa_device *vdev, u8 status); /** -- cgit v1.2.3 From 800977f6f32e452cba6b04ef21d2f5383ca29209 Mon Sep 17 00:00:00 2001 From: Cai Huoqing Date: Fri, 14 Jan 2022 14:02:52 -0800 Subject: kthread: add the helper function kthread_run_on_cpu() Add a new helper function kthread_run_on_cpu(), which includes kthread_create_on_cpu/wake_up_process(). In some cases, use kthread_run_on_cpu() directly instead of kthread_create_on_node/kthread_bind/wake_up_process() or kthread_create_on_cpu/wake_up_process() or kthreadd_create/kthread_bind/wake_up_process() to simplify the code. [akpm@linux-foundation.org: export kthread_create_on_cpu to modules] Link: https://lkml.kernel.org/r/20211022025711.3673-2-caihuoqing@baidu.com Signed-off-by: Cai Huoqing Cc: Bernard Metzler Cc: Cai Huoqing Cc: Daniel Bristot de Oliveira Cc: Davidlohr Bueso Cc: Doug Ledford Cc: Ingo Molnar Cc: Jason Gunthorpe Cc: Joel Fernandes (Google) Cc: Josh Triplett Cc: Lai Jiangshan Cc: Mathieu Desnoyers Cc: "Paul E . McKenney" Cc: Steven Rostedt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kthread.h | 25 +++++++++++++++++++++++++ kernel/kthread.c | 1 + 2 files changed, 26 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 346b0f269161..db47aae7c481 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -56,6 +56,31 @@ bool kthread_is_per_cpu(struct task_struct *k); __k; \ }) +/** + * kthread_run_on_cpu - create and wake a cpu bound thread. + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: Convenient wrapper for kthread_create_on_cpu() + * followed by wake_up_process(). Returns the kthread or + * ERR_PTR(-ENOMEM). + */ +static inline struct task_struct * +kthread_run_on_cpu(int (*threadfn)(void *data), void *data, + unsigned int cpu, const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_cpu(threadfn, data, cpu, namefmt); + if (!IS_ERR(p)) + wake_up_process(p); + + return p; +} + void free_kthread_struct(struct task_struct *k); void kthread_bind(struct task_struct *k, unsigned int cpu); void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask); diff --git a/kernel/kthread.c b/kernel/kthread.c index 7113003fab63..4ed9e7bce9e8 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -523,6 +523,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), to_kthread(p)->cpu = cpu; return p; } +EXPORT_SYMBOL(kthread_create_on_cpu); void kthread_set_per_cpu(struct task_struct *k, int cpu) { -- cgit v1.2.3 From 60115fa54ad7b913b7cb5844e6b7ffeb842d55f2 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Fri, 14 Jan 2022 14:04:11 -0800 Subject: mm: defer kmemleak object creation of module_alloc() Yongqiang reports a kmemleak panic when module insmod/rmmod with KASAN enabled(without KASAN_VMALLOC) on x86[1]. When the module area allocates memory, it's kmemleak_object is created successfully, but the KASAN shadow memory of module allocation is not ready, so when kmemleak scan the module's pointer, it will panic due to no shadow memory with KASAN check. module_alloc __vmalloc_node_range kmemleak_vmalloc kmemleak_scan update_checksum kasan_module_alloc kmemleak_ignore Note, there is no problem if KASAN_VMALLOC enabled, the modules area entire shadow memory is preallocated. Thus, the bug only exits on ARCH which supports dynamic allocation of module area per module load, for now, only x86/arm64/s390 are involved. Add a VM_DEFER_KMEMLEAK flags, defer vmalloc'ed object register of kmemleak in module_alloc() to fix this issue. [1] https://lore.kernel.org/all/6d41e2b9-4692-5ec4-b1cd-cbe29ae89739@huawei.com/ [wangkefeng.wang@huawei.com: fix build] Link: https://lkml.kernel.org/r/20211125080307.27225-1-wangkefeng.wang@huawei.com [akpm@linux-foundation.org: simplify ifdefs, per Andrey] Link: https://lkml.kernel.org/r/CA+fCnZcnwJHUQq34VuRxpdoY6_XbJCDJ-jopksS5Eia4PijPzw@mail.gmail.com Link: https://lkml.kernel.org/r/20211124142034.192078-1-wangkefeng.wang@huawei.com Fixes: 793213a82de4 ("s390/kasan: dynamic shadow mem allocation for modules") Fixes: 39d114ddc682 ("arm64: add KASAN support") Fixes: bebf56a1b176 ("kasan: enable instrumentation of global variables") Signed-off-by: Kefeng Wang Reported-by: Yongqiang Liu Cc: Andrey Konovalov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Catalin Marinas Cc: Will Deacon Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Alexander Gordeev Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: Alexander Potapenko Cc: Kefeng Wang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm64/kernel/module.c | 4 ++-- arch/s390/kernel/module.c | 5 +++-- arch/x86/kernel/module.c | 7 ++++--- include/linux/kasan.h | 4 ++-- include/linux/vmalloc.h | 7 +++++++ mm/kasan/shadow.c | 9 +++++++-- mm/vmalloc.c | 3 ++- 7 files changed, 27 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index b5ec010c481f..309a27553c87 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -36,7 +36,7 @@ void *module_alloc(unsigned long size) module_alloc_end = MODULES_END; p = __vmalloc_node_range(size, MODULE_ALIGN, module_alloc_base, - module_alloc_end, gfp_mask, PAGE_KERNEL, 0, + module_alloc_end, gfp_mask, PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && @@ -58,7 +58,7 @@ void *module_alloc(unsigned long size) PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index b01ba460b7ca..d52d85367bf7 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -37,14 +37,15 @@ void *module_alloc(unsigned long size) { + gfp_t gfp_mask = GFP_KERNEL; void *p; if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR, MODULES_END, - GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + gfp_mask, PAGE_KERNEL_EXEC, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 169fb6f4cd2e..95fa745e310a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -67,6 +67,7 @@ static unsigned long int get_module_load_offset(void) void *module_alloc(unsigned long size) { + gfp_t gfp_mask = GFP_KERNEL; void *p; if (PAGE_ALIGN(size) > MODULES_LEN) @@ -74,10 +75,10 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), - MODULES_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, + MODULES_END, gfp_mask, + PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index d8783b682669..89c99e5e67de 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -474,12 +474,12 @@ static inline void kasan_populate_early_vm_area_shadow(void *start, * allocations with real shadow memory. With KASAN vmalloc, the special * case is unnecessary, as the work is handled in the generic case. */ -int kasan_module_alloc(void *addr, size_t size); +int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask); void kasan_free_shadow(const struct vm_struct *vm); #else /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -static inline int kasan_module_alloc(void *addr, size_t size) { return 0; } +static inline int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask) { return 0; } static inline void kasan_free_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 6e022cc712e6..880227b9f044 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -28,6 +28,13 @@ struct notifier_block; /* in notifier.h */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_NO_HUGE_VMAP 0x00000400 /* force PAGE_SIZE pte mapping */ +#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ + !defined(CONFIG_KASAN_VMALLOC) +#define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ +#else +#define VM_DEFER_KMEMLEAK 0 +#endif + /* * VM_KASAN is used slightly differently depending on CONFIG_KASAN_VMALLOC. * diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 4a4929b29a23..94136f84b449 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -498,7 +498,7 @@ void kasan_release_vmalloc(unsigned long start, unsigned long end, #else /* CONFIG_KASAN_VMALLOC */ -int kasan_module_alloc(void *addr, size_t size) +int kasan_module_alloc(void *addr, size_t size, gfp_t gfp_mask) { void *ret; size_t scaled_size; @@ -520,9 +520,14 @@ int kasan_module_alloc(void *addr, size_t size) __builtin_return_address(0)); if (ret) { + struct vm_struct *vm = find_vm_area(addr); __memset(ret, KASAN_SHADOW_INIT, shadow_size); - find_vm_area(addr)->flags |= VM_KASAN; + vm->flags |= VM_KASAN; kmemleak_ignore(ret); + + if (vm->flags & VM_DEFER_KMEMLEAK) + kmemleak_vmalloc(vm, size, gfp_mask); + return 0; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d2a00ad4e1dd..bf3c2fe8f528 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3074,7 +3074,8 @@ again: clear_vm_uninitialized_flag(area); size = PAGE_ALIGN(size); - kmemleak_vmalloc(area, size, gfp_mask); + if (!(vm_flags & VM_DEFER_KMEMLEAK)) + kmemleak_vmalloc(area, size, gfp_mask); return addr; -- cgit v1.2.3 From c4386bd8ee3a921c3c799b7197dc898ade76a453 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Fri, 14 Jan 2022 14:04:22 -0800 Subject: mm/memremap: add ZONE_DEVICE support for compound pages Add a new @vmemmap_shift property for struct dev_pagemap which specifies that a devmap is composed of a set of compound pages of order @vmemmap_shift, instead of base pages. When a compound page devmap is requested, all but the first page are initialised as tail pages instead of order-0 pages. For certain ZONE_DEVICE users like device-dax which have a fixed page size, this creates an opportunity to optimize GUP and GUP-fast walkers, treating it the same way as THP or hugetlb pages. Additionally, commit 7118fc2906e2 ("hugetlb: address ref count racing in prep_compound_gigantic_page") removed set_page_count() because the setting of page ref count to zero was redundant. devmap pages don't come from page allocator though and only head page refcount is used for compound pages, hence initialize tail page count to zero. Link: https://lkml.kernel.org/r/20211202204422.26777-5-joao.m.martins@oracle.com Signed-off-by: Joao Martins Reviewed-by: Dan Williams Cc: Christoph Hellwig Cc: Dave Jiang Cc: Jane Chu Cc: Jason Gunthorpe Cc: Jason Gunthorpe Cc: John Hubbard Cc: Jonathan Corbet Cc: Matthew Wilcox (Oracle) Cc: Mike Kravetz Cc: Muchun Song Cc: Naoya Horiguchi Cc: Vishal Verma Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memremap.h | 11 +++++++++++ mm/memremap.c | 18 ++++++++++++------ mm/page_alloc.c | 38 +++++++++++++++++++++++++++++++++++++- 3 files changed, 60 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memremap.h b/include/linux/memremap.h index c0e9d35889e8..61a6a0e27359 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -99,6 +99,11 @@ struct dev_pagemap_ops { * @done: completion for @internal_ref * @type: memory type: see MEMORY_* in memory_hotplug.h * @flags: PGMAP_* flags to specify defailed behavior + * @vmemmap_shift: structural definition of how the vmemmap page metadata + * is populated, specifically the metadata page order. + * A zero value (default) uses base pages as the vmemmap metadata + * representation. A bigger value will set up compound struct pages + * of the requested order value. * @ops: method table * @owner: an opaque pointer identifying the entity that manages this * instance. Used by various helpers to make sure that no @@ -114,6 +119,7 @@ struct dev_pagemap { struct completion done; enum memory_type type; unsigned int flags; + unsigned long vmemmap_shift; const struct dev_pagemap_ops *ops; void *owner; int nr_range; @@ -130,6 +136,11 @@ static inline struct vmem_altmap *pgmap_altmap(struct dev_pagemap *pgmap) return NULL; } +static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap) +{ + return 1 << pgmap->vmemmap_shift; +} + #ifdef CONFIG_ZONE_DEVICE void *memremap_pages(struct dev_pagemap *pgmap, int nid); void memunmap_pages(struct dev_pagemap *pgmap); diff --git a/mm/memremap.c b/mm/memremap.c index 5a66a71ab591..a2869d8519a2 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -102,15 +102,22 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id) return (range->start + range_len(range)) >> PAGE_SHIFT; } -static unsigned long pfn_next(unsigned long pfn) +static unsigned long pfn_next(struct dev_pagemap *pgmap, unsigned long pfn) { - if (pfn % 1024 == 0) + if (pfn % (1024 << pgmap->vmemmap_shift)) cond_resched(); - return pfn + 1; + return pfn + pgmap_vmemmap_nr(pgmap); +} + +static unsigned long pfn_len(struct dev_pagemap *pgmap, unsigned long range_id) +{ + return (pfn_end(pgmap, range_id) - + pfn_first(pgmap, range_id)) >> pgmap->vmemmap_shift; } #define for_each_device_pfn(pfn, map, i) \ - for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn)) + for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); \ + pfn = pfn_next(map, pfn)) static void dev_pagemap_kill(struct dev_pagemap *pgmap) { @@ -295,8 +302,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params, memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], PHYS_PFN(range->start), PHYS_PFN(range_len(range)), pgmap); - percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id) - - pfn_first(pgmap, range_id)); + percpu_ref_get_many(pgmap->ref, pfn_len(pgmap, range_id)); return 0; err_add_memory: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 23045a2a1339..d59023a676ed 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6612,6 +6612,35 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn, } } +static void __ref memmap_init_compound(struct page *head, + unsigned long head_pfn, + unsigned long zone_idx, int nid, + struct dev_pagemap *pgmap, + unsigned long nr_pages) +{ + unsigned long pfn, end_pfn = head_pfn + nr_pages; + unsigned int order = pgmap->vmemmap_shift; + + __SetPageHead(head); + for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + prep_compound_tail(head, pfn - head_pfn); + set_page_count(page, 0); + + /* + * The first tail page stores compound_mapcount_ptr() and + * compound_order() and the second tail page stores + * compound_pincount_ptr(). Call prep_compound_head() after + * the first and second tail pages have been initialized to + * not have the data overwritten. + */ + if (pfn == head_pfn + 2) + prep_compound_head(head, order); + } +} + void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, @@ -6620,6 +6649,7 @@ void __ref memmap_init_zone_device(struct zone *zone, unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); + unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap); unsigned long zone_idx = zone_idx(zone); unsigned long start = jiffies; int nid = pgdat->node_id; @@ -6637,10 +6667,16 @@ void __ref memmap_init_zone_device(struct zone *zone, nr_pages = end_pfn - start_pfn; } - for (pfn = start_pfn; pfn < end_pfn; pfn++) { + for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) { struct page *page = pfn_to_page(pfn); __init_zone_device_page(page, pfn, zone_idx, nid, pgmap); + + if (pfns_per_compound == 1) + continue; + + memmap_init_compound(page, pfn, zone_idx, nid, pgmap, + pfns_per_compound); } pr_info("%s initialised %lu pages in %ums\n", __func__, -- cgit v1.2.3 From 3e9d80a891df3b1a5d77db47fa7fdf33ba71e5cb Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Jan 2022 14:05:04 -0800 Subject: mm,fs: split dump_mapping() out from dump_page() dump_mapping() is a big chunk of dump_page(), and it'd be handy to be able to call it when we don't have a struct page. Split it out and move it to fs/inode.c. Take the opportunity to simplify some of the debug messages a little. Link: https://lkml.kernel.org/r/20211121121056.2870061-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski Acked-by: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/fs.h | 1 + mm/debug.c | 52 ++-------------------------------------------------- 3 files changed, 52 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 6b80a51129d5..980e7b7a5460 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -526,6 +526,55 @@ void __remove_inode_hash(struct inode *inode) } EXPORT_SYMBOL(__remove_inode_hash); +void dump_mapping(const struct address_space *mapping) +{ + struct inode *host; + const struct address_space_operations *a_ops; + struct hlist_node *dentry_first; + struct dentry *dentry_ptr; + struct dentry dentry; + unsigned long ino; + + /* + * If mapping is an invalid pointer, we don't want to crash + * accessing it, so probe everything depending on it carefully. + */ + if (get_kernel_nofault(host, &mapping->host) || + get_kernel_nofault(a_ops, &mapping->a_ops)) { + pr_warn("invalid mapping:%px\n", mapping); + return; + } + + if (!host) { + pr_warn("aops:%ps\n", a_ops); + return; + } + + if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || + get_kernel_nofault(ino, &host->i_ino)) { + pr_warn("aops:%ps invalid inode:%px\n", a_ops, host); + return; + } + + if (!dentry_first) { + pr_warn("aops:%ps ino:%lx\n", a_ops, ino); + return; + } + + dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); + if (get_kernel_nofault(dentry, dentry_ptr)) { + pr_warn("aops:%ps ino:%lx invalid dentry:%px\n", + a_ops, ino, dentry_ptr); + return; + } + + /* + * if dentry is corrupted, the %pd handler may still crash, + * but it's unlikely that we reach here with a corrupt mapping + */ + pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", a_ops, ino, &dentry); +} + void clear_inode(struct inode *inode) { /* diff --git a/include/linux/fs.h b/include/linux/fs.h index bbf812ce89a8..5315fa68f751 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3152,6 +3152,7 @@ extern void unlock_new_inode(struct inode *); extern void discard_new_inode(struct inode *); extern unsigned int get_next_ino(void); extern void evict_inodes(struct super_block *sb); +void dump_mapping(const struct address_space *); /* * Userspace may rely on the the inode number being non-zero. For example, glibc diff --git a/mm/debug.c b/mm/debug.c index a05a39ff8fe4..bc9ac87f0e08 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -112,56 +112,8 @@ static void __dump_page(struct page *page) type = "ksm "; else if (PageAnon(page)) type = "anon "; - else if (mapping) { - struct inode *host; - const struct address_space_operations *a_ops; - struct hlist_node *dentry_first; - struct dentry *dentry_ptr; - struct dentry dentry; - unsigned long ino; - - /* - * mapping can be invalid pointer and we don't want to crash - * accessing it, so probe everything depending on it carefully - */ - if (get_kernel_nofault(host, &mapping->host) || - get_kernel_nofault(a_ops, &mapping->a_ops)) { - pr_warn("failed to read mapping contents, not a valid kernel address?\n"); - goto out_mapping; - } - - if (!host) { - pr_warn("aops:%ps\n", a_ops); - goto out_mapping; - } - - if (get_kernel_nofault(dentry_first, &host->i_dentry.first) || - get_kernel_nofault(ino, &host->i_ino)) { - pr_warn("aops:%ps with invalid host inode %px\n", - a_ops, host); - goto out_mapping; - } - - if (!dentry_first) { - pr_warn("aops:%ps ino:%lx\n", a_ops, ino); - goto out_mapping; - } - - dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias); - if (get_kernel_nofault(dentry, dentry_ptr)) { - pr_warn("aops:%ps ino:%lx with invalid dentry %px\n", - a_ops, ino, dentry_ptr); - } else { - /* - * if dentry is corrupted, the %pd handler may still - * crash, but it's unlikely that we reach here with a - * corrupted struct page - */ - pr_warn("aops:%ps ino:%lx dentry name:\"%pd\"\n", - a_ops, ino, &dentry); - } - } -out_mapping: + else if (mapping) + dump_mapping(mapping); BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); pr_warn("%sflags: %pGp%s\n", type, &head->flags, -- cgit v1.2.3 From b6bf9abb0aa44e53ffe9c1e6e1d32568f5b25e4a Mon Sep 17 00:00:00 2001 From: Dan Schatzberg Date: Fri, 14 Jan 2022 14:05:35 -0800 Subject: mm/memcg: add oom_group_kill memory event Our container agent wants to know when a container exits if it was OOM killed or not to report to the user. We use memory.oom.group = 1 to ensure that OOM kills within the container's cgroup kill everything. Existing memory.events are insufficient for knowing if this triggered: 1) Our current approach reads memory.events oom_kill and reports the container was killed if the value is non-zero. This is erroneous in some cases where containers create their children cgroups with memory.oom.group=1 as such OOM kills will get counted against the container cgroup's oom_kill counter despite not actually OOM killing the entire container. 2) Reading memory.events.local will fail to identify OOM kills in leaf cgroups (that don't set memory.oom.group) within the container cgroup. This patch adds a new oom_group_kill event when memory.oom.group triggers to allow userspace to cleanly identify when an entire cgroup is oom killed. [schatzberg.dan@gmail.com: changes from Johannes and Chris] Link: https://lkml.kernel.org/r/20211213162511.2492267-1-schatzberg.dan@gmail.com Link: https://lkml.kernel.org/r/20211203162426.3375036-1-schatzberg.dan@gmail.com Signed-off-by: Dan Schatzberg Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: Chris Down Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Tejun Heo Cc: Zefan Li Cc: Jonathan Corbet Cc: Vladimir Davydov Cc: Matthew Wilcox (Oracle) Cc: Muchun Song Cc: Alex Shi Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 3 +++ include/linux/memcontrol.h | 1 + mm/memcontrol.c | 2 ++ mm/oom_kill.c | 1 + 4 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 2aeb7ae8b393..8269bfa240f4 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1268,6 +1268,9 @@ PAGE_SIZE multiple when read back. The number of processes belonging to this cgroup killed by any kind of OOM killer. + oom_group_kill + The number of times a group OOM has occurred. + memory.events.local Similar to memory.events but the fields in the file are local to the cgroup i.e. not hierarchical. The file modified event diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0c5c403f4be6..951f24f42147 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -42,6 +42,7 @@ enum memcg_memory_event { MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, + MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bfe9bdec192b..2d39d58baccf 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -6318,6 +6318,8 @@ static void __memory_events_show(struct seq_file *m, atomic_long_t *events) seq_printf(m, "oom %lu\n", atomic_long_read(&events[MEMCG_OOM])); seq_printf(m, "oom_kill %lu\n", atomic_long_read(&events[MEMCG_OOM_KILL])); + seq_printf(m, "oom_group_kill %lu\n", + atomic_long_read(&events[MEMCG_OOM_GROUP_KILL])); } static int memory_events_show(struct seq_file *m, void *v) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 1ddabefcfb5a..e52ce0b1465d 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -994,6 +994,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * If necessary, kill all tasks in the selected memory cgroup. */ if (oom_group) { + memcg_memory_event(oom_group, MEMCG_OOM_GROUP_KILL); mem_cgroup_print_oom_group(oom_group); mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, (void *)message); -- cgit v1.2.3 From 4e5aa1f4c2b489bc6f3ab5ca54747b18a847289d Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 14 Jan 2022 14:05:45 -0800 Subject: memcg: add per-memcg vmalloc stat The kvmalloc* allocation functions can fallback to vmalloc allocations and more often on long running machines. In addition the kernel does have __GFP_ACCOUNT kvmalloc* calls. So, often on long running machines, the memory.stat does not tell the complete picture which type of memory is charged to the memcg. So add a per-memcg vmalloc stat. [shakeelb@google.com: page_memcg() within rcu lock, per Muchun] Link: https://lkml.kernel.org/r/20211222052457.1960701-1-shakeelb@google.com [akpm@linux-foundation.org: remove cast, per Muchun] [shakeelb@google.com: remove area->page[0] checks and move to page by page accounting per Michal] Link: https://lkml.kernel.org/r/20220104222341.3972772-1-shakeelb@google.com Link: https://lkml.kernel.org/r/20211221215336.1922823-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Roman Gushchin Reviewed-by: Muchun Song Acked-by: Michal Hocko Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 3 +++ include/linux/memcontrol.h | 21 +++++++++++++++++++++ mm/memcontrol.c | 1 + mm/vmalloc.c | 13 +++++++++++-- 4 files changed, 36 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 8269bfa240f4..4f400b03dddf 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1314,6 +1314,9 @@ PAGE_SIZE multiple when read back. sock (npn) Amount of memory used in network transmission buffers + vmalloc (npn) + Amount of memory used for vmap backed memory. + shmem Amount of cached filesystem data that is swap-backed, such as tmpfs, shm segments, shared anonymous mmap()s diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 951f24f42147..0131e5574c88 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -33,6 +33,7 @@ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, + MEMCG_VMALLOC, MEMCG_NR_STAT, }; @@ -992,6 +993,21 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, local_irq_restore(flags); } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return; + + rcu_read_lock(); + memcg = page_memcg(page); + if (memcg) + mod_memcg_state(memcg, idx, val); + rcu_read_unlock(); +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return READ_ONCE(memcg->vmstats.state[idx]); @@ -1447,6 +1463,11 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, { } +static inline void mod_memcg_page_state(struct page *page, + int idx, int val) +{ +} + static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 88e1be912aa7..c9ddd02dc5de 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1375,6 +1375,7 @@ static const struct memory_stat memory_stats[] = { { "pagetables", NR_PAGETABLE }, { "percpu", MEMCG_PERCPU_B }, { "sock", MEMCG_SOCK }, + { "vmalloc", MEMCG_VMALLOC }, { "shmem", NR_SHMEM }, { "file_mapped", NR_FILE_MAPPED }, { "file_dirty", NR_FILE_DIRTY }, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index bf3c2fe8f528..80c6de4c425f 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -2623,12 +2624,13 @@ static void __vunmap(const void *addr, int deallocate_pages) if (deallocate_pages) { unsigned int page_order = vm_area_page_order(area); - int i; + int i, step = 1U << page_order; - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < area->nr_pages; i += step) { struct page *page = area->pages[i]; BUG_ON(!page); + mod_memcg_page_state(page, MEMCG_VMALLOC, -step); __free_pages(page, page_order); cond_resched(); } @@ -2955,6 +2957,13 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, page_order, nr_small_pages, area->pages); atomic_long_add(area->nr_pages, &nr_vmalloc_pages); + if (gfp_mask & __GFP_ACCOUNT) { + int i, step = 1U << page_order; + + for (i = 0; i < area->nr_pages; i += step) + mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, + step); + } /* * If not enough pages were obtained to accomplish an -- cgit v1.2.3 From 9a10064f5625d5572c3626c1516e0bebc6c9fe9b Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Fri, 14 Jan 2022 14:05:59 -0800 Subject: mm: add a field to store names for private anonymous memory In many userspace applications, and especially in VM based applications like Android uses heavily, there are multiple different allocators in use. At a minimum there is libc malloc and the stack, and in many cases there are libc malloc, the stack, direct syscalls to mmap anonymous memory, and multiple VM heaps (one for small objects, one for big objects, etc.). Each of these layers usually has its own tools to inspect its usage; malloc by compiling a debug version, the VM through heap inspection tools, and for direct syscalls there is usually no way to track them. On Android we heavily use a set of tools that use an extended version of the logic covered in Documentation/vm/pagemap.txt to walk all pages mapped in userspace and slice their usage by process, shared (COW) vs. unique mappings, backing, etc. This can account for real physical memory usage even in cases like fork without exec (which Android uses heavily to share as many private COW pages as possible between processes), Kernel SamePage Merging, and clean zero pages. It produces a measurement of the pages that only exist in that process (USS, for unique), and a measurement of the physical memory usage of that process with the cost of shared pages being evenly split between processes that share them (PSS). If all anonymous memory is indistinguishable then figuring out the real physical memory usage (PSS) of each heap requires either a pagemap walking tool that can understand the heap debugging of every layer, or for every layer's heap debugging tools to implement the pagemap walking logic, in which case it is hard to get a consistent view of memory across the whole system. Tracking the information in userspace leads to all sorts of problems. It either needs to be stored inside the process, which means every process has to have an API to export its current heap information upon request, or it has to be stored externally in a filesystem that somebody needs to clean up on crashes. It needs to be readable while the process is still running, so it has to have some sort of synchronization with every layer of userspace. Efficiently tracking the ranges requires reimplementing something like the kernel vma trees, and linking to it from every layer of userspace. It requires more memory, more syscalls, more runtime cost, and more complexity to separately track regions that the kernel is already tracking. This patch adds a field to /proc/pid/maps and /proc/pid/smaps to show a userspace-provided name for anonymous vmas. The names of named anonymous vmas are shown in /proc/pid/maps and /proc/pid/smaps as [anon:]. Userspace can set the name for a region of memory by calling prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name) Setting the name to NULL clears it. The name length limit is 80 bytes including NUL-terminator and is checked to contain only printable ascii characters (including space), except '[',']','\','$' and '`'. Ascii strings are being used to have a descriptive identifiers for vmas, which can be understood by the users reading /proc/pid/maps or /proc/pid/smaps. Names can be standardized for a given system and they can include some variable parts such as the name of the allocator or a library, tid of the thread using it, etc. The name is stored in a pointer in the shared union in vm_area_struct that points to a null terminated string. Anonymous vmas with the same name (equivalent strings) and are otherwise mergeable will be merged. The name pointers are not shared between vmas even if they contain the same name. The name pointer is stored in a union with fields that are only used on file-backed mappings, so it does not increase memory usage. CONFIG_ANON_VMA_NAME kernel configuration is introduced to enable this feature. It keeps the feature disabled by default to prevent any additional memory overhead and to avoid confusing procfs parsers on systems which are not ready to support named anonymous vmas. The patch is based on the original patch developed by Colin Cross, more specifically on its latest version [1] posted upstream by Sumit Semwal. It used a userspace pointer to store vma names. In that design, name pointers could be shared between vmas. However during the last upstreaming attempt, Kees Cook raised concerns [2] about this approach and suggested to copy the name into kernel memory space, perform validity checks [3] and store as a string referenced from vm_area_struct. One big concern is about fork() performance which would need to strdup anonymous vma names. Dave Hansen suggested experimenting with worst-case scenario of forking a process with 64k vmas having longest possible names [4]. I ran this experiment on an ARM64 Android device and recorded a worst-case regression of almost 40% when forking such a process. This regression is addressed in the followup patch which replaces the pointer to a name with a refcounted structure that allows sharing the name pointer between vmas of the same name. Instead of duplicating the string during fork() or when splitting a vma it increments the refcount. [1] https://lore.kernel.org/linux-mm/20200901161459.11772-4-sumit.semwal@linaro.org/ [2] https://lore.kernel.org/linux-mm/202009031031.D32EF57ED@keescook/ [3] https://lore.kernel.org/linux-mm/202009031022.3834F692@keescook/ [4] https://lore.kernel.org/linux-mm/5d0358ab-8c47-2f5f-8e43-23b89d6a8e95@intel.com/ Changes for prctl(2) manual page (in the options section): PR_SET_VMA Sets an attribute specified in arg2 for virtual memory areas starting from the address specified in arg3 and spanning the size specified in arg4. arg5 specifies the value of the attribute to be set. Note that assigning an attribute to a virtual memory area might prevent it from being merged with adjacent virtual memory areas due to the difference in that attribute's value. Currently, arg2 must be one of: PR_SET_VMA_ANON_NAME Set a name for anonymous virtual memory areas. arg5 should be a pointer to a null-terminated string containing the name. The name length including null byte cannot exceed 80 bytes. If arg5 is NULL, the name of the appropriate anonymous virtual memory areas will be reset. The name can contain only printable ascii characters (including space), except '[',']','\','$' and '`'. This feature is available only if the kernel is built with the CONFIG_ANON_VMA_NAME option enabled. [surenb@google.com: docs: proc.rst: /proc/PID/maps: fix malformed table] Link: https://lkml.kernel.org/r/20211123185928.2513763-1-surenb@google.com [surenb: rebased over v5.15-rc6, replaced userpointer with a kernel copy, added input sanitization and CONFIG_ANON_VMA_NAME config. The bulk of the work here was done by Colin Cross, therefore, with his permission, keeping him as the author] Link: https://lkml.kernel.org/r/20211019215511.3771969-2-surenb@google.com Signed-off-by: Colin Cross Signed-off-by: Suren Baghdasaryan Reviewed-by: Kees Cook Cc: Stephen Rothwell Cc: Al Viro Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: David Rientjes Cc: "Eric W. Biederman" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jan Glauber Cc: Johannes Weiner Cc: John Stultz Cc: Mel Gorman Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Rob Landley Cc: "Serge E. Hallyn" Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/filesystems/proc.rst | 6 +- fs/proc/task_mmu.c | 12 +++- fs/userfaultfd.c | 7 +- include/linux/mm.h | 13 +++- include/linux/mm_types.h | 64 ++++++++++++++++-- include/uapi/linux/prctl.h | 3 + kernel/fork.c | 2 + kernel/sys.c | 63 ++++++++++++++++++ mm/Kconfig | 14 ++++ mm/madvise.c | 129 +++++++++++++++++++++++++++++++++++-- mm/mempolicy.c | 3 +- mm/mlock.c | 2 +- mm/mmap.c | 38 ++++++----- mm/mprotect.c | 2 +- 14 files changed, 324 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 8d7f141c6fc7..061744c436d9 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -426,12 +426,14 @@ with the memory region, as the case would be with BSS (uninitialized data). The "pathname" shows the name associated file for this mapping. If the mapping is not associated with a file: - ======= ==================================== + ============= ==================================== [heap] the heap of the program [stack] the stack of the main process [vdso] the "virtual dynamic shared object", the kernel system call handler - ======= ==================================== + [anon:] an anonymous mapping that has been + named by userspace + ============= ==================================== or if empty, the mapping is anonymous. diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ad667dbc96f5..e6998652fd67 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -308,6 +308,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) name = arch_vma_name(vma); if (!name) { + const char *anon_name; + if (!mm) { name = "[vdso]"; goto done; @@ -319,8 +321,16 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) goto done; } - if (is_stack(vma)) + if (is_stack(vma)) { name = "[stack]"; + goto done; + } + + anon_name = vma_anon_name(vma); + if (anon_name) { + seq_pad(m, ' '); + seq_printf(m, "[anon:%s]", anon_name); + } } done: diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 22bf14ab2d16..5b2af7b82776 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -877,7 +877,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, vma_anon_name(vma)); if (prev) vma = prev; else @@ -1436,7 +1436,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx })); + ((struct vm_userfaultfd_ctx){ ctx }), + vma_anon_name(vma)); if (prev) { vma = prev; goto next; @@ -1613,7 +1614,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, vma_anon_name(vma)); if (prev) { vma = prev; goto next; diff --git a/include/linux/mm.h b/include/linux/mm.h index a7e4a9e7d807..7000442984b9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2658,7 +2658,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, const char *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); @@ -3391,5 +3391,16 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) return 0; } +#ifdef CONFIG_ANON_VMA_NAME +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name); +#else +static inline int +madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name) { + return 0; +} +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index c3a6e6209600..799e2ee626b2 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -426,11 +426,19 @@ struct vm_area_struct { /* * For areas with an address space and backing store, * linkage into the address_space->i_mmap interval tree. + * + * For private anonymous mappings, a pointer to a null terminated string + * containing the name given to the vma, or NULL if unnamed. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + + union { + struct { + struct rb_node rb; + unsigned long rb_subtree_last; + } shared; + /* Serialized by mmap_sem. */ + char *anon_name; + }; /* * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma @@ -875,4 +883,52 @@ typedef struct { unsigned long val; } swp_entry_t; +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling vma_anon_name() and while using + * the returned pointer. + */ +extern const char *vma_anon_name(struct vm_area_struct *vma); + +/* + * mmap_lock should be read-locked for orig_vma->vm_mm. + * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be + * isolated. + */ +extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma); + +/* + * mmap_lock should be write-locked or vma should have been isolated under + * write-locked mmap_lock protection. + */ +extern void free_vma_anon_name(struct vm_area_struct *vma); + +/* mmap_lock should be read-locked */ +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + const char *vma_name = vma_anon_name(vma); + + /* either both NULL, or pointers to same string */ + if (vma_name == name) + return true; + + return name && vma_name && !strcmp(name, vma_name); +} +#else /* CONFIG_ANON_VMA_NAME */ +static inline const char *vma_anon_name(struct vm_area_struct *vma) +{ + return NULL; +} +static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_vma_anon_name(struct vm_area_struct *vma) {} +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + return true; +} +#endif /* CONFIG_ANON_VMA_NAME */ + #endif /* _LINUX_MM_TYPES_H */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index bb73e9a0b24f..e998764f0262 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -272,4 +272,7 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 # define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 +#define PR_SET_VMA 0x53564d41 +# define PR_SET_VMA_ANON_NAME 0 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 3244cc56b697..4cf20b5f2da3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -365,12 +365,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; + dup_vma_anon_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { + free_vma_anon_name(vma); kmem_cache_free(vm_area_cachep, vma); } diff --git a/kernel/sys.c b/kernel/sys.c index 8fdac0d90504..2450a9f33cb0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2261,6 +2261,66 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) +#ifdef CONFIG_ANON_VMA_NAME + +#define ANON_VMA_NAME_MAX_LEN 80 +#define ANON_VMA_NAME_INVALID_CHARS "\\`$[]" + +static inline bool is_valid_name_char(char ch) +{ + /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */ + return ch > 0x1f && ch < 0x7f && + !strchr(ANON_VMA_NAME_INVALID_CHARS, ch); +} + +static int prctl_set_vma(unsigned long opt, unsigned long addr, + unsigned long size, unsigned long arg) +{ + struct mm_struct *mm = current->mm; + const char __user *uname; + char *name, *pch; + int error; + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + uname = (const char __user *)arg; + if (uname) { + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + + if (IS_ERR(name)) + return PTR_ERR(name); + + for (pch = name; *pch != '\0'; pch++) { + if (!is_valid_name_char(*pch)) { + kfree(name); + return -EINVAL; + } + } + } else { + /* Reset the name */ + name = NULL; + } + + mmap_write_lock(mm); + error = madvise_set_anon_name(mm, addr, size, name); + mmap_write_unlock(mm); + kfree(name); + break; + default: + error = -EINVAL; + } + + return error; +} + +#else /* CONFIG_ANON_VMA_NAME */ +static int prctl_set_vma(unsigned long opt, unsigned long start, + unsigned long size, unsigned long arg) +{ + return -EINVAL; +} +#endif /* CONFIG_ANON_VMA_NAME */ + SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) { @@ -2530,6 +2590,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, error = sched_core_share_pid(arg2, arg3, arg4, arg5); break; #endif + case PR_SET_VMA: + error = prctl_set_vma(arg2, arg3, arg4, arg5); + break; default: error = -EINVAL; break; diff --git a/mm/Kconfig b/mm/Kconfig index 356f4f2c779e..53d7485fc38f 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -900,6 +900,20 @@ config IO_MAPPING config SECRETMEM def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED +config ANON_VMA_NAME + bool "Anonymous VMA name support" + depends on PROC_FS && ADVISE_SYSCALLS && MMU + + help + Allow naming anonymous virtual memory areas. + + This feature allows assigning names to virtual memory areas. Assigned + names can be later retrieved from /proc/pid/maps and /proc/pid/smaps + and help identifying individual anonymous memory areas. + Assigning a name to anonymous virtual memory area might prevent that + area from being merged with adjacent virtual memory areas due to the + difference in their name. + source "mm/damon/Kconfig" endmenu diff --git a/mm/madvise.c b/mm/madvise.c index 4b9c5509990c..413bbc6e40a0 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -62,19 +63,84 @@ static int madvise_need_mmap_write(int behavior) } } +#ifdef CONFIG_ANON_VMA_NAME +static inline bool has_vma_anon_name(struct vm_area_struct *vma) +{ + return !vma->vm_file && vma->anon_name; +} + +const char *vma_anon_name(struct vm_area_struct *vma) +{ + if (!has_vma_anon_name(vma)) + return NULL; + + mmap_assert_locked(vma->vm_mm); + + return vma->anon_name; +} + +void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + if (!has_vma_anon_name(orig_vma)) + return; + + new_vma->anon_name = kstrdup(orig_vma->anon_name, GFP_KERNEL); +} + +void free_vma_anon_name(struct vm_area_struct *vma) +{ + if (!has_vma_anon_name(vma)) + return; + + kfree(vma->anon_name); + vma->anon_name = NULL; +} + +/* mmap_lock should be write-locked */ +static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +{ + if (!name) { + free_vma_anon_name(vma); + return 0; + } + + if (vma->anon_name) { + /* Same name, nothing to do here */ + if (!strcmp(name, vma->anon_name)) + return 0; + + free_vma_anon_name(vma); + } + vma->anon_name = kstrdup(name, GFP_KERNEL); + if (!vma->anon_name) + return -ENOMEM; + + return 0; +} +#else /* CONFIG_ANON_VMA_NAME */ +static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +{ + if (name) + return -EINVAL; + + return 0; +} +#endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_sem held for writing; */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, - unsigned long end, unsigned long new_flags) + unsigned long end, unsigned long new_flags, + const char *name) { struct mm_struct *mm = vma->vm_mm; int error; pgoff_t pgoff; - if (new_flags == vma->vm_flags) { + if (new_flags == vma->vm_flags && is_same_vma_anon_name(vma, name)) { *prev = vma; return 0; } @@ -82,7 +148,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, name); if (*prev) { vma = *prev; goto success; @@ -111,6 +177,11 @@ success: * vm_flags is protected by the mmap_lock held in write mode. */ vma->vm_flags = new_flags; + if (!vma->vm_file) { + error = replace_vma_anon_name(vma, name); + if (error) + return error; + } return 0; } @@ -938,7 +1009,8 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, break; } - error = madvise_update_vma(vma, prev, start, end, new_flags); + error = madvise_update_vma(vma, prev, start, end, new_flags, + vma_anon_name(vma)); out: /* @@ -1118,6 +1190,55 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, return unmapped_error; } +#ifdef CONFIG_ANON_VMA_NAME +static int madvise_vma_anon_name(struct vm_area_struct *vma, + struct vm_area_struct **prev, + unsigned long start, unsigned long end, + unsigned long name) +{ + int error; + + /* Only anonymous mappings can be named */ + if (vma->vm_file) + return -EBADF; + + error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, + (const char *)name); + + /* + * madvise() returns EAGAIN if kernel resources, such as + * slab, are temporarily unavailable. + */ + if (error == -ENOMEM) + error = -EAGAIN; + return error; +} + +int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, + unsigned long len_in, const char *name) +{ + unsigned long end; + unsigned long len; + + if (start & ~PAGE_MASK) + return -EINVAL; + len = (len_in + ~PAGE_MASK) & PAGE_MASK; + + /* Check to see whether len was rounded up from small -ve to zero */ + if (len_in && !len) + return -EINVAL; + + end = start + len; + if (end < start) + return -EINVAL; + + if (end == start) + return 0; + + return madvise_walk_vmas(mm, start, end, (unsigned long)name, + madvise_vma_anon_name); +} +#endif /* CONFIG_ANON_VMA_NAME */ /* * The madvise(2) system call. * diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f6248affaf38..679f47b3a079 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -810,7 +810,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx); + new_pol, vma->vm_userfaultfd_ctx, + vma_anon_name(vma)); if (prev) { vma = prev; next = vma->vm_next; diff --git a/mm/mlock.c b/mm/mlock.c index e263d62ae2d0..8f584eddd305 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -512,7 +512,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index bfb0ea164a90..85edb0011453 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1029,7 +1029,8 @@ again: */ static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -1047,6 +1048,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; + if (!is_same_vma_anon_name(vma, anon_name)) + return 0; return 1; } @@ -1079,9 +1082,10 @@ static int can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { if (vma->vm_pgoff == vm_pgoff) return 1; @@ -1100,9 +1104,10 @@ static int can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { - if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) && + if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { pgoff_t vm_pglen; vm_pglen = vma_pages(vma); @@ -1113,9 +1118,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, } /* - * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out - * whether that can be merged with its predecessor or its successor. - * Or both (it neatly fills a hole). + * Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name), + * figure out whether that can be merged with its predecessor or its + * successor. Or both (it neatly fills a hole). * * In most cases - when called for mmap, brk or mremap - [addr,end) is * certain not to be mapped by the time vma_merge is called; but when @@ -1160,7 +1165,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + const char *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -1190,7 +1196,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(vma_policy(prev), policy) && can_vma_merge_after(prev, vm_flags, anon_vma, file, pgoff, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, anon_name)) { /* * OK, it can. Can we now merge in the successor as well? */ @@ -1199,7 +1205,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx) && + vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(prev->anon_vma, next->anon_vma, NULL)) { /* cases 1, 6 */ @@ -1222,7 +1228,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, mpol_equal(policy, vma_policy(next)) && can_vma_merge_before(next, vm_flags, anon_vma, file, pgoff+pglen, - vm_userfaultfd_ctx)) { + vm_userfaultfd_ctx, anon_name)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, addr, prev->vm_pgoff, NULL, next); @@ -1754,7 +1760,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -1803,7 +1809,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, - NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (merge) { /* ->mmap() can change vma->vm_file and fput the original file. So * fput the vma->vm_file here or we would add an extra fput for file @@ -3056,7 +3062,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL); if (vma) goto out; @@ -3249,7 +3255,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index e552f5e0ccbd..0138dfcdb1d8 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -464,7 +464,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, vma_anon_name(vma)); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); -- cgit v1.2.3 From 78db3412833dc9c479cd17412035f216cfd01a29 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jan 2022 14:06:03 -0800 Subject: mm: add anonymous vma name refcounting While forking a process with high number (64K) of named anonymous vmas the overhead caused by strdup() is noticeable. Experiments with ARM64 Android device show up to 40% performance regression when forking a process with 64k unpopulated anonymous vmas using the max name lengths vs the same process with the same number of anonymous vmas having no name. Introduce anon_vma_name refcounted structure to avoid the overhead of copying vma names during fork() and when splitting named anonymous vmas. When a vma is duplicated, instead of copying the name we increment the refcount of this structure. Multiple vmas can point to the same anon_vma_name as long as they increment the refcount. The name member of anon_vma_name structure is assigned at structure allocation time and is never changed. If vma name changes then the refcount of the original structure is dropped, a new anon_vma_name structure is allocated to hold the new name and the vma pointer is updated to point to the new structure. With this approach the fork() performance regressions is reduced 3-4x times and with usecases using more reasonable number of VMAs (a few thousand) the regressions is not measurable. Link: https://lkml.kernel.org/r/20211019215511.3771969-3-surenb@google.com Signed-off-by: Suren Baghdasaryan Reviewed-by: Kees Cook Cc: Al Viro Cc: Colin Cross Cc: Cyrill Gorcunov Cc: Dave Hansen Cc: David Rientjes Cc: "Eric W. Biederman" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jan Glauber Cc: Johannes Weiner Cc: John Stultz Cc: Mel Gorman Cc: Minchan Kim Cc: Oleg Nesterov Cc: Pekka Enberg Cc: Peter Zijlstra Cc: Rob Landley Cc: "Serge E. Hallyn" Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 9 ++++++++- mm/madvise.c | 42 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 44 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 799e2ee626b2..449b6eafc695 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -5,6 +5,7 @@ #include #include +#include #include #include #include @@ -386,6 +387,12 @@ struct vm_userfaultfd_ctx { struct vm_userfaultfd_ctx {}; #endif /* CONFIG_USERFAULTFD */ +struct anon_vma_name { + struct kref kref; + /* The name needs to be at the end because it is dynamically sized. */ + char name[]; +}; + /* * This struct describes a virtual memory area. There is one of these * per VM-area/task. A VM area is any part of the process virtual memory @@ -437,7 +444,7 @@ struct vm_area_struct { unsigned long rb_subtree_last; } shared; /* Serialized by mmap_sem. */ - char *anon_name; + struct anon_vma_name *anon_name; }; /* diff --git a/mm/madvise.c b/mm/madvise.c index 413bbc6e40a0..c63aacbbfa78 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -64,6 +64,29 @@ static int madvise_need_mmap_write(int behavior) } #ifdef CONFIG_ANON_VMA_NAME +static struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + struct anon_vma_name *anon_name; + size_t count; + + /* Add 1 for NUL terminator at the end of the anon_name->name */ + count = strlen(name) + 1; + anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL); + if (anon_name) { + kref_init(&anon_name->kref); + memcpy(anon_name->name, name, count); + } + + return anon_name; +} + +static void vma_anon_name_free(struct kref *kref) +{ + struct anon_vma_name *anon_name = + container_of(kref, struct anon_vma_name, kref); + kfree(anon_name); +} + static inline bool has_vma_anon_name(struct vm_area_struct *vma) { return !vma->vm_file && vma->anon_name; @@ -76,7 +99,7 @@ const char *vma_anon_name(struct vm_area_struct *vma) mmap_assert_locked(vma->vm_mm); - return vma->anon_name; + return vma->anon_name->name; } void dup_vma_anon_name(struct vm_area_struct *orig_vma, @@ -85,34 +108,41 @@ void dup_vma_anon_name(struct vm_area_struct *orig_vma, if (!has_vma_anon_name(orig_vma)) return; - new_vma->anon_name = kstrdup(orig_vma->anon_name, GFP_KERNEL); + kref_get(&orig_vma->anon_name->kref); + new_vma->anon_name = orig_vma->anon_name; } void free_vma_anon_name(struct vm_area_struct *vma) { + struct anon_vma_name *anon_name; + if (!has_vma_anon_name(vma)) return; - kfree(vma->anon_name); + anon_name = vma->anon_name; vma->anon_name = NULL; + kref_put(&anon_name->kref, vma_anon_name_free); } /* mmap_lock should be write-locked */ static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) { + const char *anon_name; + if (!name) { free_vma_anon_name(vma); return 0; } - if (vma->anon_name) { + anon_name = vma_anon_name(vma); + if (anon_name) { /* Same name, nothing to do here */ - if (!strcmp(name, vma->anon_name)) + if (!strcmp(name, anon_name)) return 0; free_vma_anon_name(vma); } - vma->anon_name = kstrdup(name, GFP_KERNEL); + vma->anon_name = anon_vma_name_alloc(name); if (!vma->anon_name) return -ENOMEM; -- cgit v1.2.3 From 17fca131cee21724ee953a17c185c14e9533af5b Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jan 2022 14:06:07 -0800 Subject: mm: move anon_vma declarations to linux/mm_inline.h The patch to add anonymous vma names causes a build failure in some configurations: include/linux/mm_types.h: In function 'is_same_vma_anon_name': include/linux/mm_types.h:924:37: error: implicit declaration of function 'strcmp' [-Werror=implicit-function-declaration] 924 | return name && vma_name && !strcmp(name, vma_name); | ^~~~~~ include/linux/mm_types.h:22:1: note: 'strcmp' is defined in header ''; did you forget to '#include '? This should not really be part of linux/mm_types.h in the first place, as that header is meant to only contain structure defintions and need a minimum set of indirect includes itself. While the header clearly includes more than it should at this point, let's not make it worse by including string.h as well, which would pull in the expensive (compile-speed wise) fortify-string logic. Move the new functions into a separate header that only needs to be included in a couple of locations. Link: https://lkml.kernel.org/r/20211207125710.2503446-1-arnd@kernel.org Fixes: "mm: add a field to store names for private anonymous memory" Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Colin Cross Cc: Eric Biederman Cc: Kees Cook Cc: Matthew Wilcox (Oracle) Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Stephen Rothwell Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Yu Zhao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 1 + fs/userfaultfd.c | 1 + include/linux/mm_inline.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++ include/linux/mm_types.h | 48 --------------------------------------------- kernel/fork.c | 1 + mm/madvise.c | 1 + mm/mmap.c | 1 + 7 files changed, 55 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e6998652fd67..18f8c3acbb85 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include +#include #include #include #include diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 5b2af7b82776..e26b10132d47 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e2ec68b0515c..47d96d2647ca 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -4,6 +4,7 @@ #include #include +#include /** * folio_is_file_lru - Should the folio be on a file LRU or anon LRU? @@ -135,4 +136,53 @@ static __always_inline void del_page_from_lru_list(struct page *page, { lruvec_del_folio(lruvec, page_folio(page)); } + +#ifdef CONFIG_ANON_VMA_NAME +/* + * mmap_lock should be read-locked when calling vma_anon_name() and while using + * the returned pointer. + */ +extern const char *vma_anon_name(struct vm_area_struct *vma); + +/* + * mmap_lock should be read-locked for orig_vma->vm_mm. + * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be + * isolated. + */ +extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma); + +/* + * mmap_lock should be write-locked or vma should have been isolated under + * write-locked mmap_lock protection. + */ +extern void free_vma_anon_name(struct vm_area_struct *vma); + +/* mmap_lock should be read-locked */ +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + const char *vma_name = vma_anon_name(vma); + + /* either both NULL, or pointers to same string */ + if (vma_name == name) + return true; + + return name && vma_name && !strcmp(name, vma_name); +} +#else /* CONFIG_ANON_VMA_NAME */ +static inline const char *vma_anon_name(struct vm_area_struct *vma) +{ + return NULL; +} +static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_vma_anon_name(struct vm_area_struct *vma) {} +static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, + const char *name) +{ + return true; +} +#endif /* CONFIG_ANON_VMA_NAME */ + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 449b6eafc695..4d5fb84eed5e 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -890,52 +890,4 @@ typedef struct { unsigned long val; } swp_entry_t; -#ifdef CONFIG_ANON_VMA_NAME -/* - * mmap_lock should be read-locked when calling vma_anon_name() and while using - * the returned pointer. - */ -extern const char *vma_anon_name(struct vm_area_struct *vma); - -/* - * mmap_lock should be read-locked for orig_vma->vm_mm. - * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be - * isolated. - */ -extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma); - -/* - * mmap_lock should be write-locked or vma should have been isolated under - * write-locked mmap_lock protection. - */ -extern void free_vma_anon_name(struct vm_area_struct *vma); - -/* mmap_lock should be read-locked */ -static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, - const char *name) -{ - const char *vma_name = vma_anon_name(vma); - - /* either both NULL, or pointers to same string */ - if (vma_name == name) - return true; - - return name && vma_name && !strcmp(name, vma_name); -} -#else /* CONFIG_ANON_VMA_NAME */ -static inline const char *vma_anon_name(struct vm_area_struct *vma) -{ - return NULL; -} -static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma) {} -static inline void free_vma_anon_name(struct vm_area_struct *vma) {} -static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, - const char *name) -{ - return true; -} -#endif /* CONFIG_ANON_VMA_NAME */ - #endif /* _LINUX_MM_TYPES_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 4cf20b5f2da3..75737e566441 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/madvise.c b/mm/madvise.c index c63aacbbfa78..5604064df464 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/mmap.c b/mm/mmap.c index 85edb0011453..77733b113c40 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.3 From 36090def7bad06a6346f86a7cfdbfda2d138cb64 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 14 Jan 2022 14:06:10 -0800 Subject: mm: move tlb_flush_pending inline helpers to mm_inline.h linux/mm_types.h should only define structure definitions, to make it cheap to include elsewhere. The atomic_t helper function definitions are particularly large, so it's better to move the helpers using those into the existing linux/mm_inline.h and only include that where needed. As a follow-up, we may want to go through all the indirect includes in mm_types.h and reduce them as much as possible. Link: https://lkml.kernel.org/r/20211207125710.2503446-2-arnd@kernel.org Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Stephen Rothwell Cc: Suren Baghdasaryan Cc: Colin Cross Cc: Kees Cook Cc: Peter Xu Cc: Peter Zijlstra (Intel) Cc: Yu Zhao Cc: Vlastimil Babka Cc: Matthew Wilcox (Oracle) Cc: Eric Biederman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/include/asm/pgtable.h | 2 +- include/linux/mm.h | 45 -------------- include/linux/mm_inline.h | 86 +++++++++++++++++++++++++++ include/linux/mm_types.h | 129 ++++++++++++++--------------------------- mm/ksm.c | 1 + mm/mapping_dirty_helpers.c | 1 + mm/memory.c | 1 + mm/mmu_gather.c | 1 + mm/pgtable-generic.c | 1 + 9 files changed, 137 insertions(+), 130 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 448cd01eb3ec..5196958aa6ac 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -752,7 +752,7 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && - mm_tlb_flush_pending(mm)) + atomic_read(&mm->tlb_flush_pending)) return true; return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7000442984b9..c17e5cfc1e47 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -424,51 +424,6 @@ extern unsigned int kobjsize(const void *objp); */ extern pgprot_t protection_map[16]; -/** - * enum fault_flag - Fault flag definitions. - * @FAULT_FLAG_WRITE: Fault was a write fault. - * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. - * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. - * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. - * @FAULT_FLAG_TRIED: The fault has been tried once. - * @FAULT_FLAG_USER: The fault originated in userspace. - * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. - * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. - * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. - * - * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify - * whether we would allow page faults to retry by specifying these two - * fault flags correctly. Currently there can be three legal combinations: - * - * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and - * this is the first try - * - * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and - * we've already tried at least once - * - * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry - * - * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never - * be used. Note that page faults can be allowed to retry for multiple times, - * in which case we'll have an initial fault with flags (a) then later on - * continuous faults with flags (b). We should always try to detect pending - * signals before a retry to make sure the continuous page faults can still be - * interrupted if necessary. - */ -enum fault_flag { - FAULT_FLAG_WRITE = 1 << 0, - FAULT_FLAG_MKWRITE = 1 << 1, - FAULT_FLAG_ALLOW_RETRY = 1 << 2, - FAULT_FLAG_RETRY_NOWAIT = 1 << 3, - FAULT_FLAG_KILLABLE = 1 << 4, - FAULT_FLAG_TRIED = 1 << 5, - FAULT_FLAG_USER = 1 << 6, - FAULT_FLAG_REMOTE = 1 << 7, - FAULT_FLAG_INSTRUCTION = 1 << 8, - FAULT_FLAG_INTERRUPTIBLE = 1 << 9, -}; - /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 47d96d2647ca..b725839dfe71 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,6 +2,7 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include #include #include #include @@ -185,4 +186,89 @@ static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); + /* + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. + */ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4d5fb84eed5e..6a89f128c990 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -692,90 +692,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); -static inline void init_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_set(&mm->tlb_flush_pending, 0); -} - -static inline void inc_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_inc(&mm->tlb_flush_pending); - /* - * The only time this value is relevant is when there are indeed pages - * to flush. And we'll only flush pages after changing them, which - * requires the PTL. - * - * So the ordering here is: - * - * atomic_inc(&mm->tlb_flush_pending); - * spin_lock(&ptl); - * ... - * set_pte_at(); - * spin_unlock(&ptl); - * - * spin_lock(&ptl) - * mm_tlb_flush_pending(); - * .... - * spin_unlock(&ptl); - * - * flush_tlb_range(); - * atomic_dec(&mm->tlb_flush_pending); - * - * Where the increment if constrained by the PTL unlock, it thus - * ensures that the increment is visible if the PTE modification is - * visible. After all, if there is no PTE modification, nobody cares - * about TLB flushes either. - * - * This very much relies on users (mm_tlb_flush_pending() and - * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and - * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc - * locks (PPC) the unlock of one doesn't order against the lock of - * another PTL. - * - * The decrement is ordered by the flush_tlb_range(), such that - * mm_tlb_flush_pending() will not return false unless all flushes have - * completed. - */ -} - -static inline void dec_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * See inc_tlb_flush_pending(). - * - * This cannot be smp_mb__before_atomic() because smp_mb() simply does - * not order against TLB invalidate completion, which is what we need. - * - * Therefore we must rely on tlb_flush_*() to guarantee order. - */ - atomic_dec(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * Must be called after having acquired the PTL; orders against that - * PTLs release and therefore ensures that if we observe the modified - * PTE we must also observe the increment from inc_tlb_flush_pending(). - * - * That is, it only guarantees to return true if there is a flush - * pending for _this_ PTL. - */ - return atomic_read(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) -{ - /* - * Similar to mm_tlb_flush_pending(), we must have acquired the PTL - * for which there is a TLB flush pending in order to guarantee - * we've seen both that PTE modification and the increment. - * - * (no requirement on actually still holding the PTL, that is irrelevant) - */ - return atomic_read(&mm->tlb_flush_pending) > 1; -} - struct vm_fault; /** @@ -890,4 +806,49 @@ typedef struct { unsigned long val; } swp_entry_t; +/** + * enum fault_flag - Fault flag definitions. + * @FAULT_FLAG_WRITE: Fault was a write fault. + * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. + * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. + * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. + * @FAULT_FLAG_TRIED: The fault has been tried once. + * @FAULT_FLAG_USER: The fault originated in userspace. + * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. + * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. + * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * + * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify + * whether we would allow page faults to retry by specifying these two + * fault flags correctly. Currently there can be three legal combinations: + * + * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and + * this is the first try + * + * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and + * we've already tried at least once + * + * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry + * + * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never + * be used. Note that page faults can be allowed to retry for multiple times, + * in which case we'll have an initial fault with flags (a) then later on + * continuous faults with flags (b). We should always try to detect pending + * signals before a retry to make sure the continuous page faults can still be + * interrupted if necessary. + */ +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/mm/ksm.c b/mm/ksm.c index 0662093237e4..f34476ac0a41 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -15,6 +15,7 @@ #include #include +#include #include #include #include diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index ea734f248fce..1b0ab8fcfd8b 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include diff --git a/mm/memory.c b/mm/memory.c index 8f1de811a1dc..bc80d4effac9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -41,6 +41,7 @@ #include #include +#include #include #include #include diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 1b9837419bf9..afb7185ffdc4 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4e640baf9794..6523fda274e5 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -10,6 +10,7 @@ #include #include #include +#include #include /* -- cgit v1.2.3 From cc6dcfee72509868271d42919a3c1081b6b0dc7e Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Fri, 14 Jan 2022 14:06:18 -0800 Subject: mm: document locking restrictions for vm_operations_struct::close Add comments for vm_operations_struct::close documenting locking requirements for this callback and its callers. Link: https://lkml.kernel.org/r/20211209191325.3069345-2-surenb@google.com Signed-off-by: Suren Baghdasaryan Acked-by: Michal Hocko Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Christian Brauner Cc: Christian Brauner Cc: Christoph Hellwig Cc: David Hildenbrand Cc: David Rientjes Cc: Florian Weimer Cc: Jan Engelhardt Cc: Jann Horn Cc: Johannes Weiner Cc: Kirill A. Shutemov Cc: Matthew Wilcox Cc: Minchan Kim Cc: Oleg Nesterov Cc: Rik van Riel Cc: Roman Gushchin Cc: Shakeel Butt Cc: Tim Murray Cc: Jason Gunthorpe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c17e5cfc1e47..4d7245e6802a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -532,6 +532,10 @@ enum page_entry_size { */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); + /** + * @close: Called when the VMA is being removed from the MM. + * Context: User context. May sleep. Caller holds mmap_lock. + */ void (*close)(struct vm_area_struct * area); /* Called any time before splitting to check if it's allowed */ int (*may_split)(struct vm_area_struct *area, unsigned long addr); -- cgit v1.2.3 From 08d5b29eac7dd5e6c79b66d390ecbb9219e05931 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Fri, 14 Jan 2022 14:06:33 -0800 Subject: mm: ptep_clear() page table helper We have ptep_get_and_clear() and ptep_get_and_clear_full() helpers to clear PTE from user page tables, but there is no variant for simple clear of a present PTE from user page tables without using a low level pte_clear() which can be either native or para-virtualised. Add a new ptep_clear() that can be used in common code to clear PTEs from page table. We will need this call later in order to add a hook for page table check. Link: https://lkml.kernel.org/r/20211221154650.1047963-3-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Cc: Aneesh Kumar K.V Cc: Dave Hansen Cc: David Rientjes Cc: Frederic Weisbecker Cc: Greg Thelen Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jiri Slaby Cc: Jonathan Corbet Cc: Kees Cook Cc: Masahiro Yamada Cc: Mike Rapoport Cc: Muchun Song Cc: Paul Turner Cc: Peter Zijlstra Cc: Sami Tolvanen Cc: Thomas Gleixner Cc: Wei Xu Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/arch_pgtable_helpers.rst | 6 ++++-- include/linux/pgtable.h | 8 ++++++++ mm/debug_vm_pgtable.c | 2 +- mm/khugepaged.c | 12 ++---------- 4 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/arch_pgtable_helpers.rst b/Documentation/vm/arch_pgtable_helpers.rst index b3166c33db39..f8b225fc9190 100644 --- a/Documentation/vm/arch_pgtable_helpers.rst +++ b/Documentation/vm/arch_pgtable_helpers.rst @@ -66,9 +66,11 @@ PTE Page Table Helpers +---------------------------+--------------------------------------------------+ | pte_mknotpresent | Invalidates a mapped PTE | +---------------------------+--------------------------------------------------+ -| ptep_get_and_clear | Clears a PTE | +| ptep_clear | Clears a PTE | +---------------------------+--------------------------------------------------+ -| ptep_get_and_clear_full | Clears a PTE | +| ptep_get_and_clear | Clears and returns PTE | ++---------------------------+--------------------------------------------------+ +| ptep_get_and_clear_full | Clears and returns PTE (batched PTE unmap) | +---------------------------+--------------------------------------------------+ | ptep_test_and_clear_young | Clears young from a PTE | +---------------------------+--------------------------------------------------+ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e24d2c992b11..bc8713a76e03 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -258,6 +258,14 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif +#ifndef __HAVE_ARCH_PTEP_CLEAR +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + pte_clear(mm, addr, ptep); +} +#endif + #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long address, diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c index 2a2b24e87877..a7ac97c76762 100644 --- a/mm/debug_vm_pgtable.c +++ b/mm/debug_vm_pgtable.c @@ -652,7 +652,7 @@ static void __init pte_clear_tests(struct pgtable_debug_args *args) set_pte_at(args->mm, args->vaddr, args->ptep, pte); flush_dcache_page(page); barrier(); - pte_clear(args->mm, args->vaddr, args->ptep); + ptep_clear(args->mm, args->vaddr, args->ptep); pte = ptep_get(args->ptep); WARN_ON(!pte_none(pte)); } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index e99101162f1a..9d40dd8890e5 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -756,11 +756,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, * ptl mostly unnecessary. */ spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); + ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); } } else { @@ -774,11 +770,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page, * inside page_remove_rmap(). */ spin_lock(ptl); - /* - * paravirt calls inside pte_clear here are - * superfluous. - */ - pte_clear(vma->vm_mm, address, _pte); + ptep_clear(vma->vm_mm, address, _pte); page_remove_rmap(src_page, false); spin_unlock(ptl); free_page_and_swap_cache(src_page); -- cgit v1.2.3 From df4e817b710809425d899340dbfa8504a3ca4ba5 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Fri, 14 Jan 2022 14:06:37 -0800 Subject: mm: page table check Check user page table entries at the time they are added and removed. Allows to synchronously catch memory corruption issues related to double mapping. When a pte for an anonymous page is added into page table, we verify that this pte does not already point to a file backed page, and vice versa if this is a file backed page that is being added we verify that this page does not have an anonymous mapping We also enforce that read-only sharing for anonymous pages is allowed (i.e. cow after fork). All other sharing must be for file pages. Page table check allows to protect and debug cases where "struct page" metadata became corrupted for some reason. For example, when refcnt or mapcount become invalid. Link: https://lkml.kernel.org/r/20211221154650.1047963-4-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin Cc: Aneesh Kumar K.V Cc: Dave Hansen Cc: David Rientjes Cc: Frederic Weisbecker Cc: Greg Thelen Cc: "H. Peter Anvin" Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jiri Slaby Cc: Jonathan Corbet Cc: Kees Cook Cc: Masahiro Yamada Cc: Mike Rapoport Cc: Muchun Song Cc: Paul Turner Cc: Peter Zijlstra Cc: Sami Tolvanen Cc: Thomas Gleixner Cc: Wei Xu Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/index.rst | 1 + Documentation/vm/page_table_check.rst | 56 +++++++ MAINTAINERS | 9 ++ arch/Kconfig | 3 + include/linux/page_table_check.h | 147 ++++++++++++++++++ mm/Kconfig.debug | 24 +++ mm/Makefile | 1 + mm/page_alloc.c | 4 + mm/page_ext.c | 4 + mm/page_table_check.c | 270 ++++++++++++++++++++++++++++++++++ 10 files changed, 519 insertions(+) create mode 100644 Documentation/vm/page_table_check.rst create mode 100644 include/linux/page_table_check.h create mode 100644 mm/page_table_check.c (limited to 'include/linux') diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index b1826ca2c576..932440805453 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -31,6 +31,7 @@ algorithms. If you are looking for advice on simply allocating memory, see the page_migration page_frags page_owner + page_table_check remap_file_pages slub split_page_table_lock diff --git a/Documentation/vm/page_table_check.rst b/Documentation/vm/page_table_check.rst new file mode 100644 index 000000000000..81f521ff7ea7 --- /dev/null +++ b/Documentation/vm/page_table_check.rst @@ -0,0 +1,56 @@ +.. SPDX-License-Identifier: GPL-2.0 + +.. _page_table_check: + +================ +Page Table Check +================ + +Introduction +============ + +Page table check allows to hardern the kernel by ensuring that some types of +the memory corruptions are prevented. + +Page table check performs extra verifications at the time when new pages become +accessible from the userspace by getting their page table entries (PTEs PMDs +etc.) added into the table. + +In case of detected corruption, the kernel is crashed. There is a small +performance and memory overhead associated with the page table check. Therefore, +it is disabled by default, but can be optionally enabled on systems where the +extra hardening outweighs the performance costs. Also, because page table check +is synchronous, it can help with debugging double map memory corruption issues, +by crashing kernel at the time wrong mapping occurs instead of later which is +often the case with memory corruptions bugs. + +Double mapping detection logic +============================== + ++-------------------+-------------------+-------------------+------------------+ +| Current Mapping | New mapping | Permissions | Rule | ++===================+===================+===================+==================+ +| Anonymous | Anonymous | Read | Allow | ++-------------------+-------------------+-------------------+------------------+ +| Anonymous | Anonymous | Read / Write | Prohibit | ++-------------------+-------------------+-------------------+------------------+ +| Anonymous | Named | Any | Prohibit | ++-------------------+-------------------+-------------------+------------------+ +| Named | Anonymous | Any | Prohibit | ++-------------------+-------------------+-------------------+------------------+ +| Named | Named | Any | Allow | ++-------------------+-------------------+-------------------+------------------+ + +Enabling Page Table Check +========================= + +Build kernel with: + +- PAGE_TABLE_CHECK=y + Note, it can only be enabled on platforms where ARCH_SUPPORTS_PAGE_TABLE_CHECK + is available. + +- Boot with 'page_table_check=on' kernel parameter. + +Optionally, build kernel with PAGE_TABLE_CHECK_ENFORCED in order to have page +table support without extra kernel parameter. diff --git a/MAINTAINERS b/MAINTAINERS index dd36acc87ce6..fbdb860c0b8b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14387,6 +14387,15 @@ F: include/net/page_pool.h F: include/trace/events/page_pool.h F: net/core/page_pool.c +PAGE TABLE CHECK +M: Pasha Tatashin +M: Andrew Morton +L: linux-mm@kvack.org +S: Maintained +F: Documentation/vm/page_table_check.rst +F: include/linux/page_table_check.h +F: mm/page_table_check.c + PANASONIC LAPTOP ACPI EXTRAS DRIVER M: Kenneth Chan L: platform-driver-x86@vger.kernel.org diff --git a/arch/Kconfig b/arch/Kconfig index d3c4ab249e9c..4568b6b70b5d 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1297,6 +1297,9 @@ config HAVE_ARCH_PFN_VALID config ARCH_SUPPORTS_DEBUG_PAGEALLOC bool +config ARCH_SUPPORTS_PAGE_TABLE_CHECK + bool + config ARCH_SPLIT_ARG64 bool help diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h new file mode 100644 index 000000000000..38cace1da7b6 --- /dev/null +++ b/include/linux/page_table_check.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2021, Google LLC. + * Pasha Tatashin + */ +#ifndef __LINUX_PAGE_TABLE_CHECK_H +#define __LINUX_PAGE_TABLE_CHECK_H + +#ifdef CONFIG_PAGE_TABLE_CHECK +#include + +extern struct static_key_true page_table_check_disabled; +extern struct page_ext_operations page_table_check_ops; + +void __page_table_check_zero(struct page *page, unsigned int order); +void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t pte); +void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, + pmd_t pmd); +void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, + pud_t pud); +void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd); +void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud); + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_zero(page, order); +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear(mm, addr, pte); +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_clear(mm, addr, pmd); +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_clear(mm, addr, pud); +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_set(mm, addr, ptep, pte); +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pmd_set(mm, addr, pmdp, pmd); +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pud_set(mm, addr, pudp, pud); +} + +#else + +static inline void page_table_check_alloc(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_free(struct page *page, unsigned int order) +{ +} + +static inline void page_table_check_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t pte) +{ +} + +static inline void page_table_check_pmd_clear(struct mm_struct *mm, + unsigned long addr, pmd_t pmd) +{ +} + +static inline void page_table_check_pud_clear(struct mm_struct *mm, + unsigned long addr, pud_t pud) +{ +} + +static inline void page_table_check_pte_set(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + pte_t pte) +{ +} + +static inline void page_table_check_pmd_set(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp, + pmd_t pmd) +{ +} + +static inline void page_table_check_pud_set(struct mm_struct *mm, + unsigned long addr, pud_t *pudp, + pud_t pud) +{ +} + +#endif /* CONFIG_PAGE_TABLE_CHECK */ +#endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 1e73717802f8..5bd5bb097252 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -62,6 +62,30 @@ config PAGE_OWNER If unsure, say N. +config PAGE_TABLE_CHECK + bool "Check for invalid mappings in user page tables" + depends on ARCH_SUPPORTS_PAGE_TABLE_CHECK + select PAGE_EXTENSION + help + Check that anonymous page is not being mapped twice with read write + permissions. Check that anonymous and file pages are not being + erroneously shared. Since the checking is performed at the time + entries are added and removed to user page tables, leaking, corruption + and double mapping problems are detected synchronously. + + If unsure say "n". + +config PAGE_TABLE_CHECK_ENFORCED + bool "Enforce the page table checking by default" + depends on PAGE_TABLE_CHECK + help + Always enable page table checking. By default the page table checking + is disabled, and can be optionally enabled via page_table_check=on + kernel parameter. This config enforces that page table check is always + enabled. + + If unsure say "n". + config PAGE_POISONING bool "Poison pages after freeing" help diff --git a/mm/Makefile b/mm/Makefile index d6c0042e3aa0..5c5a3a480fa6 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -112,6 +112,7 @@ obj-$(CONFIG_GENERIC_EARLY_IOREMAP) += early_ioremap.o obj-$(CONFIG_CMA) += cma.o obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o +obj-$(CONFIG_PAGE_TABLE_CHECK) += page_table_check.o obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o obj-$(CONFIG_SECRETMEM) += secretmem.o obj-$(CONFIG_CMA_SYSFS) += cma_sysfs.o diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d59023a676ed..806f317c2e7e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -63,6 +63,7 @@ #include #include #include +#include #include #include #include @@ -1307,6 +1308,7 @@ static __always_inline bool free_pages_prepare(struct page *page, if (memcg_kmem_enabled() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); reset_page_owner(page, order); + page_table_check_free(page, order); return false; } @@ -1346,6 +1348,7 @@ static __always_inline bool free_pages_prepare(struct page *page, page_cpupid_reset_last(page); page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; reset_page_owner(page, order); + page_table_check_free(page, order); if (!PageHighMem(page)) { debug_check_no_locks_freed(page_address(page), @@ -2420,6 +2423,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, } set_page_owner(page, order, gfp_flags); + page_table_check_alloc(page, order); } static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, diff --git a/mm/page_ext.c b/mm/page_ext.c index 6242afb24d84..bee3240604dc 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -8,6 +8,7 @@ #include #include #include +#include /* * struct page extension @@ -75,6 +76,9 @@ static struct page_ext_operations *page_ext_ops[] = { #if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT) &page_idle_ops, #endif +#ifdef CONFIG_PAGE_TABLE_CHECK + &page_table_check_ops, +#endif }; unsigned long page_ext_size = sizeof(struct page_ext); diff --git a/mm/page_table_check.c b/mm/page_table_check.c new file mode 100644 index 000000000000..7504e7caa2a1 --- /dev/null +++ b/mm/page_table_check.c @@ -0,0 +1,270 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2021, Google LLC. + * Pasha Tatashin + */ +#include +#include + +#undef pr_fmt +#define pr_fmt(fmt) "page_table_check: " fmt + +struct page_table_check { + atomic_t anon_map_count; + atomic_t file_map_count; +}; + +static bool __page_table_check_enabled __initdata = + IS_ENABLED(CONFIG_PAGE_TABLE_CHECK_ENFORCED); + +DEFINE_STATIC_KEY_TRUE(page_table_check_disabled); +EXPORT_SYMBOL(page_table_check_disabled); + +static int __init early_page_table_check_param(char *buf) +{ + if (!buf) + return -EINVAL; + + if (strcmp(buf, "on") == 0) + __page_table_check_enabled = true; + else if (strcmp(buf, "off") == 0) + __page_table_check_enabled = false; + + return 0; +} + +early_param("page_table_check", early_page_table_check_param); + +static bool __init need_page_table_check(void) +{ + return __page_table_check_enabled; +} + +static void __init init_page_table_check(void) +{ + if (!__page_table_check_enabled) + return; + static_branch_disable(&page_table_check_disabled); +} + +struct page_ext_operations page_table_check_ops = { + .size = sizeof(struct page_table_check), + .need = need_page_table_check, + .init = init_page_table_check, +}; + +static struct page_table_check *get_page_table_check(struct page_ext *page_ext) +{ + BUG_ON(!page_ext); + return (void *)(page_ext) + page_table_check_ops.offset; +} + +static inline bool pte_user_accessible_page(pte_t pte) +{ + return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); +} + +static inline bool pmd_user_accessible_page(pmd_t pmd) +{ + return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && + (pmd_val(pmd) & _PAGE_USER); +} + +static inline bool pud_user_accessible_page(pud_t pud) +{ + return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && + (pud_val(pud) & _PAGE_USER); +} + +/* + * An enty is removed from the page table, decrement the counters for that page + * verify that it is of correct type and counters do not become negative. + */ +static void page_table_check_clear(struct mm_struct *mm, unsigned long addr, + unsigned long pfn, unsigned long pgcnt) +{ + struct page_ext *page_ext; + struct page *page; + bool anon; + int i; + + if (!pfn_valid(pfn)) + return; + + page = pfn_to_page(pfn); + page_ext = lookup_page_ext(page); + anon = PageAnon(page); + + for (i = 0; i < pgcnt; i++) { + struct page_table_check *ptc = get_page_table_check(page_ext); + + if (anon) { + BUG_ON(atomic_read(&ptc->file_map_count)); + BUG_ON(atomic_dec_return(&ptc->anon_map_count) < 0); + } else { + BUG_ON(atomic_read(&ptc->anon_map_count)); + BUG_ON(atomic_dec_return(&ptc->file_map_count) < 0); + } + page_ext = page_ext_next(page_ext); + } +} + +/* + * A new enty is added to the page table, increment the counters for that page + * verify that it is of correct type and is not being mapped with a different + * type to a different process. + */ +static void page_table_check_set(struct mm_struct *mm, unsigned long addr, + unsigned long pfn, unsigned long pgcnt, + bool rw) +{ + struct page_ext *page_ext; + struct page *page; + bool anon; + int i; + + if (!pfn_valid(pfn)) + return; + + page = pfn_to_page(pfn); + page_ext = lookup_page_ext(page); + anon = PageAnon(page); + + for (i = 0; i < pgcnt; i++) { + struct page_table_check *ptc = get_page_table_check(page_ext); + + if (anon) { + BUG_ON(atomic_read(&ptc->file_map_count)); + BUG_ON(atomic_inc_return(&ptc->anon_map_count) > 1 && rw); + } else { + BUG_ON(atomic_read(&ptc->anon_map_count)); + BUG_ON(atomic_inc_return(&ptc->file_map_count) < 0); + } + page_ext = page_ext_next(page_ext); + } +} + +/* + * page is on free list, or is being allocated, verify that counters are zeroes + * crash if they are not. + */ +void __page_table_check_zero(struct page *page, unsigned int order) +{ + struct page_ext *page_ext = lookup_page_ext(page); + int i; + + BUG_ON(!page_ext); + for (i = 0; i < (1 << order); i++) { + struct page_table_check *ptc = get_page_table_check(page_ext); + + BUG_ON(atomic_read(&ptc->anon_map_count)); + BUG_ON(atomic_read(&ptc->file_map_count)); + page_ext = page_ext_next(page_ext); + } +} + +void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t pte) +{ + if (&init_mm == mm) + return; + + if (pte_user_accessible_page(pte)) { + page_table_check_clear(mm, addr, pte_pfn(pte), + PAGE_SIZE >> PAGE_SHIFT); + } +} +EXPORT_SYMBOL(__page_table_check_pte_clear); + +void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr, + pmd_t pmd) +{ + if (&init_mm == mm) + return; + + if (pmd_user_accessible_page(pmd)) { + page_table_check_clear(mm, addr, pmd_pfn(pmd), + PMD_PAGE_SIZE >> PAGE_SHIFT); + } +} +EXPORT_SYMBOL(__page_table_check_pmd_clear); + +void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr, + pud_t pud) +{ + if (&init_mm == mm) + return; + + if (pud_user_accessible_page(pud)) { + page_table_check_clear(mm, addr, pud_pfn(pud), + PUD_PAGE_SIZE >> PAGE_SHIFT); + } +} +EXPORT_SYMBOL(__page_table_check_pud_clear); + +void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + pte_t old_pte; + + if (&init_mm == mm) + return; + + old_pte = *ptep; + if (pte_user_accessible_page(old_pte)) { + page_table_check_clear(mm, addr, pte_pfn(old_pte), + PAGE_SIZE >> PAGE_SHIFT); + } + + if (pte_user_accessible_page(pte)) { + page_table_check_set(mm, addr, pte_pfn(pte), + PAGE_SIZE >> PAGE_SHIFT, + pte_write(pte)); + } +} +EXPORT_SYMBOL(__page_table_check_pte_set); + +void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + pmd_t old_pmd; + + if (&init_mm == mm) + return; + + old_pmd = *pmdp; + if (pmd_user_accessible_page(old_pmd)) { + page_table_check_clear(mm, addr, pmd_pfn(old_pmd), + PMD_PAGE_SIZE >> PAGE_SHIFT); + } + + if (pmd_user_accessible_page(pmd)) { + page_table_check_set(mm, addr, pmd_pfn(pmd), + PMD_PAGE_SIZE >> PAGE_SHIFT, + pmd_write(pmd)); + } +} +EXPORT_SYMBOL(__page_table_check_pmd_set); + +void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + pud_t old_pud; + + if (&init_mm == mm) + return; + + old_pud = *pudp; + if (pud_user_accessible_page(old_pud)) { + page_table_check_clear(mm, addr, pud_pfn(old_pud), + PUD_PAGE_SIZE >> PAGE_SHIFT); + } + + if (pud_user_accessible_page(pud)) { + page_table_check_set(mm, addr, pud_pfn(pud), + PUD_PAGE_SIZE >> PAGE_SHIFT, + pud_write(pud)); + } +} +EXPORT_SYMBOL(__page_table_check_pud_set); -- cgit v1.2.3 From 020e87650af9f43683546729f959fdc78422a4b7 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Jan 2022 14:06:44 -0800 Subject: mm: remove last argument of reuse_swap_page() None of the callers care about the total_map_swapcount() any more. Link: https://lkml.kernel.org/r/20211220205943.456187-1-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Acked-by: Linus Torvalds Reviewed-by: William Kucharski Reviewed-by: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 +++--- mm/huge_memory.c | 2 +- mm/khugepaged.c | 2 +- mm/memory.c | 2 +- mm/swapfile.c | 8 +------- 5 files changed, 7 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index d1ea44b31f19..bdccbf1efa61 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -514,7 +514,7 @@ extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern struct swap_info_struct *swp_swap_info(swp_entry_t entry); -extern bool reuse_swap_page(struct page *, int *); +extern bool reuse_swap_page(struct page *); extern int try_to_free_swap(struct page *); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); @@ -680,8 +680,8 @@ static inline int swp_swapcount(swp_entry_t entry) return 0; } -#define reuse_swap_page(page, total_map_swapcount) \ - (page_trans_huge_mapcount(page, total_map_swapcount) == 1) +#define reuse_swap_page(page) \ + (page_trans_huge_mapcount(page, NULL) == 1) static inline int try_to_free_swap(struct page *page) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e5483347291c..b61fbe95c856 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1322,7 +1322,7 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) * We can only reuse the page if nobody else maps the huge page or it's * part. */ - if (reuse_swap_page(page, NULL)) { + if (reuse_swap_page(page)) { pmd_t entry; entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 9d40dd8890e5..698ea19775ac 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -681,7 +681,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, goto out; } if (!pte_write(pteval) && PageSwapCache(page) && - !reuse_swap_page(page, NULL)) { + !reuse_swap_page(page)) { /* * Page is in the swap cache and cannot be re-used. * It cannot be collapsed into a THP. diff --git a/mm/memory.c b/mm/memory.c index 5fea331b1560..571d02f419ba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3627,7 +3627,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); dec_mm_counter_fast(vma->vm_mm, MM_SWAPENTS); pte = mk_pte(page, vma->vm_page_prot); - if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page, NULL)) { + if ((vmf->flags & FAULT_FLAG_WRITE) && reuse_swap_page(page)) { pte = maybe_mkwrite(pte_mkdirty(pte), vma); vmf->flags &= ~FAULT_FLAG_WRITE; ret |= VM_FAULT_WRITE; diff --git a/mm/swapfile.c b/mm/swapfile.c index e64207e2ef1d..31d13a393cf0 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1668,12 +1668,8 @@ static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. - * - * NOTE: total_map_swapcount should not be relied upon by the caller if - * reuse_swap_page() returns false, but it may be always overwritten - * (see the other implementation for CONFIG_SWAP=n). */ -bool reuse_swap_page(struct page *page, int *total_map_swapcount) +bool reuse_swap_page(struct page *page) { int count, total_mapcount, total_swapcount; @@ -1682,8 +1678,6 @@ bool reuse_swap_page(struct page *page, int *total_map_swapcount) return false; count = page_trans_huge_map_swapcount(page, &total_mapcount, &total_swapcount); - if (total_map_swapcount) - *total_map_swapcount = total_mapcount + total_swapcount; if (count == 1 && PageSwapCache(page) && (likely(!PageTransCompound(page)) || /* The remaining swap count will be freed soon */ -- cgit v1.2.3 From d08d2b62510e2407cf939e693aefd179dc114913 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 14 Jan 2022 14:06:51 -0800 Subject: mm: remove the total_mapcount argument from page_trans_huge_mapcount() All callers pass NULL, so we can stop calculating the value we would store in it. Link: https://lkml.kernel.org/r/20211220205943.456187-3-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: William Kucharski Acked-by: Linus Torvalds Cc: David Hildenbrand Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 10 +++------- include/linux/swap.h | 2 +- mm/huge_memory.c | 30 ++++++++++-------------------- mm/swapfile.c | 2 +- 4 files changed, 15 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 4d7245e6802a..cef65f9cbdf2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -799,19 +799,15 @@ static inline int page_mapcount(struct page *page) #ifdef CONFIG_TRANSPARENT_HUGEPAGE int total_mapcount(struct page *page); -int page_trans_huge_mapcount(struct page *page, int *total_mapcount); +int page_trans_huge_mapcount(struct page *page); #else static inline int total_mapcount(struct page *page) { return page_mapcount(page); } -static inline int page_trans_huge_mapcount(struct page *page, - int *total_mapcount) +static inline int page_trans_huge_mapcount(struct page *page) { - int mapcount = page_mapcount(page); - if (total_mapcount) - *total_mapcount = mapcount; - return mapcount; + return page_mapcount(page); } #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index bdccbf1efa61..1d38d9475c4d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -681,7 +681,7 @@ static inline int swp_swapcount(swp_entry_t entry) } #define reuse_swap_page(page) \ - (page_trans_huge_mapcount(page, NULL) == 1) + (page_trans_huge_mapcount(page) == 1) static inline int try_to_free_swap(struct page *page) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b61fbe95c856..6ed86a8f6a5b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2542,38 +2542,28 @@ int total_mapcount(struct page *page) * need full accuracy to avoid breaking page pinning, because * page_trans_huge_mapcount() is slower than page_mapcount(). */ -int page_trans_huge_mapcount(struct page *page, int *total_mapcount) +int page_trans_huge_mapcount(struct page *page) { - int i, ret, _total_mapcount, mapcount; + int i, ret; /* hugetlbfs shouldn't call it */ VM_BUG_ON_PAGE(PageHuge(page), page); - if (likely(!PageTransCompound(page))) { - mapcount = atomic_read(&page->_mapcount) + 1; - if (total_mapcount) - *total_mapcount = mapcount; - return mapcount; - } + if (likely(!PageTransCompound(page))) + return atomic_read(&page->_mapcount) + 1; page = compound_head(page); - _total_mapcount = ret = 0; + ret = 0; for (i = 0; i < thp_nr_pages(page); i++) { - mapcount = atomic_read(&page[i]._mapcount) + 1; + int mapcount = atomic_read(&page[i]._mapcount) + 1; ret = max(ret, mapcount); - _total_mapcount += mapcount; } - if (PageDoubleMap(page)) { + + if (PageDoubleMap(page)) ret -= 1; - _total_mapcount -= thp_nr_pages(page); - } - mapcount = compound_mapcount(page); - ret += mapcount; - _total_mapcount += mapcount; - if (total_mapcount) - *total_mapcount = _total_mapcount; - return ret; + + return ret + compound_mapcount(page); } /* Racy check whether the huge page can be split */ diff --git a/mm/swapfile.c b/mm/swapfile.c index a93f5b5fc8b6..caa9f81a0d15 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1619,7 +1619,7 @@ static int page_trans_huge_map_swapcount(struct page *page, swapcount = page_swapcount(page); if (total_swapcount) *total_swapcount = swapcount; - return swapcount + page_trans_huge_mapcount(page, NULL); + return swapcount + page_trans_huge_mapcount(page); } page = compound_head(page); -- cgit v1.2.3 From a421ef303008b0ceee2cfc625c3246fa7654b0ca Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 14 Jan 2022 14:07:07 -0800 Subject: mm: allow !GFP_KERNEL allocations for kvmalloc Support for GFP_NO{FS,IO} and __GFP_NOFAIL has been implemented by previous patches so we can allow the support for kvmalloc. This will allow some external users to simplify or completely remove their helpers. GFP_NOWAIT semantic hasn't been supported so far but it hasn't been explicitly documented so let's add a note about that. ceph_kvmalloc is the first helper to be dropped and changed to kvmalloc. Link: https://lkml.kernel.org/r/20211122153233.9924-5-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Uladzislau Rezki (Sony) Acked-by: Vlastimil Babka Cc: Christoph Hellwig Cc: Dave Chinner Cc: Ilya Dryomov Cc: Jeff Layton Cc: Neil Brown Cc: Sebastian Andrzej Siewior Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ceph/libceph.h | 1 - mm/util.c | 15 ++++----------- net/ceph/buffer.c | 4 ++-- net/ceph/ceph_common.c | 27 --------------------------- net/ceph/crypto.c | 2 +- net/ceph/messenger.c | 2 +- net/ceph/messenger_v2.c | 2 +- net/ceph/osdmap.c | 12 ++++++------ 8 files changed, 15 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 409d8c29bc4f..309acbcb5a8a 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -295,7 +295,6 @@ extern bool libceph_compatible(void *data); extern const char *ceph_msg_type_name(int type); extern int ceph_check_fsid(struct ceph_client *client, struct ceph_fsid *fsid); -extern void *ceph_kvmalloc(size_t size, gfp_t flags); struct fs_parameter; struct fc_log; diff --git a/mm/util.c b/mm/util.c index 741ba32a43ac..7e43369064c8 100644 --- a/mm/util.c +++ b/mm/util.c @@ -549,13 +549,10 @@ EXPORT_SYMBOL(vm_mmap); * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * - * Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. + * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * - * Please note that any use of gfp flags outside of GFP_KERNEL is careful to not - * fall back to vmalloc. - * * Return: pointer to the allocated memory of %NULL in case of failure */ void *kvmalloc_node(size_t size, gfp_t flags, int node) @@ -563,13 +560,6 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) gfp_t kmalloc_flags = flags; void *ret; - /* - * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) - * so the given set of flags has to be compatible. - */ - if ((flags & GFP_KERNEL) != GFP_KERNEL) - return kmalloc_node(size, flags, node); - /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore @@ -582,6 +572,9 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; + + /* nofail semantic is implemented by the vmalloc fallback */ + kmalloc_flags &= ~__GFP_NOFAIL; } ret = kmalloc_node(size, kmalloc_flags, node); diff --git a/net/ceph/buffer.c b/net/ceph/buffer.c index 5622763ad402..7e51f128045d 100644 --- a/net/ceph/buffer.c +++ b/net/ceph/buffer.c @@ -7,7 +7,7 @@ #include #include -#include /* for ceph_kvmalloc */ +#include /* for kvmalloc */ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) { @@ -17,7 +17,7 @@ struct ceph_buffer *ceph_buffer_new(size_t len, gfp_t gfp) if (!b) return NULL; - b->vec.iov_base = ceph_kvmalloc(len, gfp); + b->vec.iov_base = kvmalloc(len, gfp); if (!b->vec.iov_base) { kfree(b); return NULL; diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index 97d6ea763e32..9441b4a4912b 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -190,33 +190,6 @@ int ceph_compare_options(struct ceph_options *new_opt, } EXPORT_SYMBOL(ceph_compare_options); -/* - * kvmalloc() doesn't fall back to the vmalloc allocator unless flags are - * compatible with (a superset of) GFP_KERNEL. This is because while the - * actual pages are allocated with the specified flags, the page table pages - * are always allocated with GFP_KERNEL. - * - * ceph_kvmalloc() may be called with GFP_KERNEL, GFP_NOFS or GFP_NOIO. - */ -void *ceph_kvmalloc(size_t size, gfp_t flags) -{ - void *p; - - if ((flags & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS)) { - p = kvmalloc(size, flags); - } else if ((flags & (__GFP_IO | __GFP_FS)) == __GFP_IO) { - unsigned int nofs_flag = memalloc_nofs_save(); - p = kvmalloc(size, GFP_KERNEL); - memalloc_nofs_restore(nofs_flag); - } else { - unsigned int noio_flag = memalloc_noio_save(); - p = kvmalloc(size, GFP_KERNEL); - memalloc_noio_restore(noio_flag); - } - - return p; -} - static int parse_fsid(const char *str, struct ceph_fsid *fsid) { int i = 0; diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 92d89b331645..051d22c0e4ad 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -147,7 +147,7 @@ void ceph_crypto_key_destroy(struct ceph_crypto_key *key) static const u8 *aes_iv = (u8 *)CEPH_AES_IV; /* - * Should be used for buffers allocated with ceph_kvmalloc(). + * Should be used for buffers allocated with kvmalloc(). * Currently these are encrypt out-buffer (ceph_buffer) and decrypt * in-buffer (msg front). * diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 57d043b382ed..7b891be799d2 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1920,7 +1920,7 @@ struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items, /* front */ if (front_len) { - m->front.iov_base = ceph_kvmalloc(front_len, flags); + m->front.iov_base = kvmalloc(front_len, flags); if (m->front.iov_base == NULL) { dout("ceph_msg_new can't allocate %d bytes\n", front_len); diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index cc40ce4e02fb..c4099b641b38 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -308,7 +308,7 @@ static void *alloc_conn_buf(struct ceph_connection *con, int len) if (WARN_ON(con->v2.conn_buf_cnt >= ARRAY_SIZE(con->v2.conn_bufs))) return NULL; - buf = ceph_kvmalloc(len, GFP_NOIO); + buf = kvmalloc(len, GFP_NOIO); if (!buf) return NULL; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 75b738083523..2823bb3cff55 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -980,7 +980,7 @@ static struct crush_work *alloc_workspace(const struct crush_map *c) work_size = crush_work_size(c, CEPH_PG_MAX_SIZE); dout("%s work_size %zu bytes\n", __func__, work_size); - work = ceph_kvmalloc(work_size, GFP_NOIO); + work = kvmalloc(work_size, GFP_NOIO); if (!work) return NULL; @@ -1190,9 +1190,9 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max) if (max == map->max_osd) return 0; - state = ceph_kvmalloc(array_size(max, sizeof(*state)), GFP_NOFS); - weight = ceph_kvmalloc(array_size(max, sizeof(*weight)), GFP_NOFS); - addr = ceph_kvmalloc(array_size(max, sizeof(*addr)), GFP_NOFS); + state = kvmalloc(array_size(max, sizeof(*state)), GFP_NOFS); + weight = kvmalloc(array_size(max, sizeof(*weight)), GFP_NOFS); + addr = kvmalloc(array_size(max, sizeof(*addr)), GFP_NOFS); if (!state || !weight || !addr) { kvfree(state); kvfree(weight); @@ -1222,7 +1222,7 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max) if (map->osd_primary_affinity) { u32 *affinity; - affinity = ceph_kvmalloc(array_size(max, sizeof(*affinity)), + affinity = kvmalloc(array_size(max, sizeof(*affinity)), GFP_NOFS); if (!affinity) return -ENOMEM; @@ -1503,7 +1503,7 @@ static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff) if (!map->osd_primary_affinity) { int i; - map->osd_primary_affinity = ceph_kvmalloc( + map->osd_primary_affinity = kvmalloc( array_size(map->max_osd, sizeof(*map->osd_primary_affinity)), GFP_NOFS); if (!map->osd_primary_affinity) -- cgit v1.2.3 From 4034247a0d6ab281ba3293798ce67af494d86129 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 14 Jan 2022 14:07:14 -0800 Subject: mm: introduce memalloc_retry_wait() Various places in the kernel - largely in filesystems - respond to a memory allocation failure by looping around and re-trying. Some of these cannot conveniently use __GFP_NOFAIL, for reasons such as: - a GFP_ATOMIC allocation, which __GFP_NOFAIL doesn't work on - a need to check for the process being signalled between failures - the possibility that other recovery actions could be performed - the allocation is quite deep in support code, and passing down an extra flag to say if __GFP_NOFAIL is wanted would be clumsy. Many of these currently use congestion_wait() which (in almost all cases) simply waits the given timeout - congestion isn't tracked for most devices. It isn't clear what the best delay is for loops, but it is clear that the various filesystems shouldn't be responsible for choosing a timeout. This patch introduces memalloc_retry_wait() with takes on that responsibility. Code that wants to retry a memory allocation can call this function passing the GFP flags that were used. It will wait however is appropriate. For now, it only considers __GFP_NORETRY and whatever gfpflags_allow_blocking() tests. If blocking is allowed without __GFP_NORETRY, then alloc_page either made some reclaim progress, or waited for a while, before failing. So there is no need for much further waiting. memalloc_retry_wait() will wait until the current jiffie ends. If this condition is not met, then alloc_page() won't have waited much if at all. In that case memalloc_retry_wait() waits about 200ms. This is the delay that most current loops uses. linux/sched/mm.h needs to be included in some files now, but linux/backing-dev.h does not. Link: https://lkml.kernel.org/r/163754371968.13692.1277530886009912421@noble.neil.brown.name Signed-off-by: NeilBrown Cc: Dave Chinner Cc: Michal Hocko Cc: "Theodore Ts'o" Cc: Jaegeuk Kim Cc: Chao Yu Cc: Darrick J. Wong Cc: Chuck Lever Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/extents.c | 8 +++----- fs/ext4/inline.c | 5 ++--- fs/ext4/page-io.c | 9 +++++---- fs/f2fs/data.c | 4 ++-- fs/f2fs/gc.c | 5 ++--- fs/f2fs/inode.c | 4 ++-- fs/f2fs/node.c | 4 ++-- fs/f2fs/recovery.c | 6 +++--- fs/f2fs/segment.c | 9 +++------ fs/f2fs/super.c | 5 ++--- fs/xfs/kmem.c | 3 +-- fs/xfs/xfs_buf.c | 2 +- include/linux/sched/mm.h | 26 ++++++++++++++++++++++++++ net/sunrpc/svc_xprt.c | 3 ++- 14 files changed, 56 insertions(+), 37 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0ecf819bf189..5582fba36b44 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -27,8 +27,8 @@ #include #include #include -#include #include +#include #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" @@ -4407,8 +4407,7 @@ retry: err = ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry; } if (err) @@ -4416,8 +4415,7 @@ retry: retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry_remove_space; } return err; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 39a1ab129fdc..635bcf68a67e 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include "ext4_jbd2.h" #include "ext4.h" @@ -1929,8 +1929,7 @@ int ext4_inline_data_truncate(struct inode *inode, int *has_inline) retry: err = ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); if (err == -ENOMEM) { - cond_resched(); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(GFP_ATOMIC); goto retry; } if (err) diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 9cb261714991..1d370364230e 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include "ext4_jbd2.h" #include "xattr.h" @@ -523,12 +523,13 @@ int ext4_bio_write_page(struct ext4_io_submit *io, ret = PTR_ERR(bounce_page); if (ret == -ENOMEM && (io->io_bio || wbc->sync_mode == WB_SYNC_ALL)) { - gfp_flags = GFP_NOFS; + gfp_t new_gfp_flags = GFP_NOFS; if (io->io_bio) ext4_io_submit(io); else - gfp_flags |= __GFP_NOFAIL; - congestion_wait(BLK_RW_ASYNC, HZ/50); + new_gfp_flags |= __GFP_NOFAIL; + memalloc_retry_wait(gfp_flags); + gfp_flags = new_gfp_flags; goto retry_encrypt; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9f754aaef558..aacf5e4dcc57 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -8,9 +8,9 @@ #include #include #include +#include #include #include -#include #include #include #include @@ -2542,7 +2542,7 @@ retry_encrypt: /* flush pending IOs and wait for a while in the ENOMEM case */ if (PTR_ERR(fio->encrypted_page) == -ENOMEM) { f2fs_flush_merged_writes(fio->sbi); - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); gfp_flags |= __GFP_NOFAIL; goto retry_encrypt; } diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index a946ce0ead34..374bbb5294d9 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -7,7 +7,6 @@ */ #include #include -#include #include #include #include @@ -15,6 +14,7 @@ #include #include #include +#include #include "f2fs.h" #include "node.h" @@ -1375,8 +1375,7 @@ retry: if (err) { clear_page_private_gcing(page); if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry; } if (is_dirty) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index 0f8b2df3e1e0..4c11254a07d4 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -8,8 +8,8 @@ #include #include #include -#include #include +#include #include "f2fs.h" #include "node.h" @@ -562,7 +562,7 @@ retry: inode = f2fs_iget(sb, ino); if (IS_ERR(inode)) { if (PTR_ERR(inode) == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry; } } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 556fcd8457f3..219506ca9a97 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include @@ -2750,7 +2750,7 @@ int f2fs_recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) retry: ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false); if (!ipage) { - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry; } diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index 6a1b4668d933..d1664a0567ef 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "f2fs.h" #include "node.h" #include "segment.h" @@ -587,7 +588,7 @@ retry_dn: err = f2fs_get_dnode_of_data(&dn, start, ALLOC_NODE); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry_dn; } goto out; @@ -670,8 +671,7 @@ retry_prev: err = check_index_in_prev_nodes(sbi, dest, &dn); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto retry_prev; } goto err; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index df9ed75f0b7a..40fdb4a8daeb 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -245,9 +246,7 @@ retry: LOOKUP_NODE); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); - cond_resched(); + memalloc_retry_wait(GFP_NOFS); goto retry; } err = -EAGAIN; @@ -424,9 +423,7 @@ retry: err = f2fs_do_write_data_page(&fio); if (err) { if (err == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); - cond_resched(); + memalloc_retry_wait(GFP_NOFS); goto retry; } unlock_page(page); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 040b6d02e1d8..3bace24f8800 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -8,9 +8,9 @@ #include #include #include +#include #include #include -#include #include #include #include @@ -2415,8 +2415,7 @@ repeat: page = read_cache_page_gfp(mapping, blkidx, GFP_NOFS); if (IS_ERR(page)) { if (PTR_ERR(page) == -ENOMEM) { - congestion_wait(BLK_RW_ASYNC, - DEFAULT_IO_TIMEOUT); + memalloc_retry_wait(GFP_NOFS); goto repeat; } set_sbi_flag(F2FS_SB(sb), SBI_QUOTA_NEED_REPAIR); diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c index 6f49bf39183c..c557a030acfe 100644 --- a/fs/xfs/kmem.c +++ b/fs/xfs/kmem.c @@ -4,7 +4,6 @@ * All Rights Reserved. */ #include "xfs.h" -#include #include "xfs_message.h" #include "xfs_trace.h" @@ -26,6 +25,6 @@ kmem_alloc(size_t size, xfs_km_flags_t flags) "%s(%u) possible memory allocation deadlock size %u in %s (mode:0x%x)", current->comm, current->pid, (unsigned int)size, __func__, lflags); - congestion_wait(BLK_RW_ASYNC, HZ/50); + memalloc_retry_wait(lflags); } while (1); } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 631c5a61d89b..6c45e3fa56f4 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -394,7 +394,7 @@ xfs_buf_alloc_pages( } XFS_STATS_INC(bp->b_mount, xb_page_retries); - congestion_wait(BLK_RW_ASYNC, HZ / 50); + memalloc_retry_wait(gfp_mask); } return 0; } diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index aca874d33fe6..aa5f09ca5bcf 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -214,6 +214,32 @@ static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif +/* Any memory-allocation retry loop should use + * memalloc_retry_wait(), and pass the flags for the most + * constrained allocation attempt that might have failed. + * This provides useful documentation of where loops are, + * and a central place to fine tune the waiting as the MM + * implementation changes. + */ +static inline void memalloc_retry_wait(gfp_t gfp_flags) +{ + /* We use io_schedule_timeout because waiting for memory + * typically included waiting for dirty pages to be + * written out, which requires IO. + */ + __set_current_state(TASK_UNINTERRUPTIBLE); + gfp_flags = current_gfp_context(gfp_flags); + if (gfpflags_allow_blocking(gfp_flags) && + !(gfp_flags & __GFP_NORETRY)) + /* Probably waited already, no need for much more */ + io_schedule_timeout(1); + else + /* Probably didn't wait, and has now released a lock, + * so now is a good time to wait + */ + io_schedule_timeout(HZ/50); +} + /** * might_alloc - Mark possible allocation sites * @gfp_mask: gfp_t flags that would be used to allocate diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 1e99ba1b9d72..9cb18b822ab2 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -6,6 +6,7 @@ */ #include +#include #include #include #include @@ -688,7 +689,7 @@ static int svc_alloc_arg(struct svc_rqst *rqstp) return -EINTR; } trace_svc_alloc_arg_err(pages); - schedule_timeout(msecs_to_jiffies(500)); + memalloc_retry_wait(GFP_KERNEL); } rqstp->rq_page_end = &rqstp->rq_pages[pages]; rqstp->rq_pages[pages] = NULL; /* this might be seen in nfsd_splice_actor() */ -- cgit v1.2.3 From 1611f74a94ba2e0f2d25b75008ed8e76e122097a Mon Sep 17 00:00:00 2001 From: Changcheng Deng Date: Fri, 14 Jan 2022 14:07:21 -0800 Subject: mm: fix boolreturn.cocci warning Return statements in functions returning bool should use true/false instead of 1/0. Link: https://lkml.kernel.org/r/20211126073327.74815-1-deng.changcheng@zte.com.cn Signed-off-by: Changcheng Deng Reported-by: Zeal Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index b5f14d581113..18423c2157e8 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -383,7 +383,7 @@ static __always_inline int TestClearPage##uname(struct page *page) \ TESTCLEARFLAG(uname, lname, policy) #define TESTPAGEFLAG_FALSE(uname, lname) \ -static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \ +static inline bool folio_test_##lname(const struct folio *folio) { return false; } \ static inline int Page##uname(const struct page *page) { return 0; } #define SETPAGEFLAG_NOOP(uname, lname) \ -- cgit v1.2.3 From be1a13eb51077b2ec5f7f4306f93dfece503a3f1 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 14 Jan 2022 14:07:27 -0800 Subject: mm: drop node from alloc_pages_vma alloc_pages_vma is meant to allocate a page with a vma specific memory policy. The initial node parameter is always a local node so it is pointless to waste a function argument for this. Drop the parameter. Link: https://lkml.kernel.org/r/YaSnlv4QpryEpesG@dhcp22.suse.cz Signed-off-by: Michal Hocko Cc: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: "Huang, Ying" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 8 ++++---- mm/mempolicy.c | 3 ++- mm/shmem.c | 3 +-- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 8fcc38467af6..78b58448f796 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -598,9 +598,9 @@ struct page *alloc_pages(gfp_t gfp, unsigned int order); struct folio *folio_alloc(gfp_t gfp, unsigned order); extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); + bool hugepage); #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + alloc_pages_vma(gfp_mask, order, vma, addr, true) #else static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) { @@ -610,14 +610,14 @@ static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order) { return __folio_alloc_node(gfp, order, numa_node_id()); } -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ +#define alloc_pages_vma(gfp_mask, order, vma, addr, false)\ alloc_pages(gfp_mask, order) #define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, false) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 679f47b3a079..ed7d15acb6a2 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2084,9 +2084,10 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, bool hugepage) { struct mempolicy *pol; + int node = numa_node_id(); struct page *page; int preferred_nid; nodemask_t *nmask; diff --git a/mm/shmem.c b/mm/shmem.c index 8f940552c182..0700e9acf53b 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1564,8 +1564,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, return NULL; shmem_pseudo_vma_init(&pvma, info, hindex); - page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), - true); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, &pvma, 0, true); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); -- cgit v1.2.3 From 04a536bfbd0f885338eecc2a4503dfca50ac94dd Mon Sep 17 00:00:00 2001 From: Miles Chen Date: Fri, 14 Jan 2022 14:07:30 -0800 Subject: include/linux/gfp.h: further document GFP_DMA32 kmalloc(..., GFP_DMA32) does not return DMA32 memory because the DMA32 kmalloc cache array is not implemented. (Reason: there is no such user in kernel). Put a short comment about this so people can understand this by reading the comment. [1] https://lists.linuxfoundation.org/pipermail/iommu/2018-December/031696.html Link: https://lkml.kernel.org/r/20211207093610.6406-1-miles.chen@mediatek.com Signed-off-by: Miles Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 78b58448f796..80f63c862be5 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -302,7 +302,9 @@ struct vm_area_struct; * lowest zone as a type of emergency reserve. * * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit - * address. + * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory + * because the DMA32 kmalloc cache array is not implemented. + * (Reason: there is no such user in kernel). * * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, * do not need to be directly accessible by the kernel but that cannot -- cgit v1.2.3 From 62b3107073646e0946bd97ff926832bafb846d17 Mon Sep 17 00:00:00 2001 From: Baoquan He Date: Fri, 14 Jan 2022 14:07:37 -0800 Subject: mm_zone: add function to check if managed dma zone exists Patch series "Handle warning of allocation failure on DMA zone w/o managed pages", v4. **Problem observed: On x86_64, when crash is triggered and entering into kdump kernel, page allocation failure can always be seen. --------------------------------- DMA: preallocated 128 KiB GFP_KERNEL pool for atomic allocations swapper/0: page allocation failure: order:5, mode:0xcc1(GFP_KERNEL|GFP_DMA), nodemask=(null),cpuset=/,mems_allowed=0 CPU: 0 PID: 1 Comm: swapper/0 Call Trace: dump_stack+0x7f/0xa1 warn_alloc.cold+0x72/0xd6 ...... __alloc_pages+0x24d/0x2c0 ...... dma_atomic_pool_init+0xdb/0x176 do_one_initcall+0x67/0x320 ? rcu_read_lock_sched_held+0x3f/0x80 kernel_init_freeable+0x290/0x2dc ? rest_init+0x24f/0x24f kernel_init+0xa/0x111 ret_from_fork+0x22/0x30 Mem-Info: ------------------------------------ ***Root cause: In the current kernel, it assumes that DMA zone must have managed pages and try to request pages if CONFIG_ZONE_DMA is enabled. While this is not always true. E.g in kdump kernel of x86_64, only low 1M is presented and locked down at very early stage of boot, so that this low 1M won't be added into buddy allocator to become managed pages of DMA zone. This exception will always cause page allocation failure if page is requested from DMA zone. ***Investigation: This failure happens since below commit merged into linus's tree. 1a6a9044b967 x86/setup: Remove CONFIG_X86_RESERVE_LOW and reservelow= options 23721c8e92f7 x86/crash: Remove crash_reserve_low_1M() f1d4d47c5851 x86/setup: Always reserve the first 1M of RAM 7c321eb2b843 x86/kdump: Remove the backup region handling 6f599d84231f x86/kdump: Always reserve the low 1M when the crashkernel option is specified Before them, on x86_64, the low 640K area will be reused by kdump kernel. So in kdump kernel, the content of low 640K area is copied into a backup region for dumping before jumping into kdump. Then except of those firmware reserved region in [0, 640K], the left area will be added into buddy allocator to become available managed pages of DMA zone. However, after above commits applied, in kdump kernel of x86_64, the low 1M is reserved by memblock, but not released to buddy allocator. So any later page allocation requested from DMA zone will fail. At the beginning, if crashkernel is reserved, the low 1M need be locked down because AMD SME encrypts memory making the old backup region mechanims impossible when switching into kdump kernel. Later, it was also observed that there are BIOSes corrupting memory under 1M. To solve this, in commit f1d4d47c5851, the entire region of low 1M is always reserved after the real mode trampoline is allocated. Besides, recently, Intel engineer mentioned their TDX (Trusted domain extensions) which is under development in kernel also needs to lock down the low 1M. So we can't simply revert above commits to fix the page allocation failure from DMA zone as someone suggested. ***Solution: Currently, only DMA atomic pool and dma-kmalloc will initialize and request page allocation with GFP_DMA during bootup. So only initializ DMA atomic pool when DMA zone has available managed pages, otherwise just skip the initialization. For dma-kmalloc(), for the time being, let's mute the warning of allocation failure if requesting pages from DMA zone while no manged pages. Meanwhile, change code to use dma_alloc_xx/dma_map_xx API to replace kmalloc(GFP_DMA), or do not use GFP_DMA when calling kmalloc() if not necessary. Christoph is posting patches to fix those under drivers/scsi/. Finally, we can remove the need of dma-kmalloc() as people suggested. This patch (of 3): In some places of the current kernel, it assumes that dma zone must have managed pages if CONFIG_ZONE_DMA is enabled. While this is not always true. E.g in kdump kernel of x86_64, only low 1M is presented and locked down at very early stage of boot, so that there's no managed pages at all in DMA zone. This exception will always cause page allocation failure if page is requested from DMA zone. Here add function has_managed_dma() and the relevant helper functions to check if there's DMA zone with managed pages. It will be used in later patches. Link: https://lkml.kernel.org/r/20211223094435.248523-1-bhe@redhat.com Link: https://lkml.kernel.org/r/20211223094435.248523-2-bhe@redhat.com Fixes: 6f599d84231f ("x86/kdump: Always reserve the low 1M when the crashkernel option is specified") Signed-off-by: Baoquan He Reviewed-by: David Hildenbrand Acked-by: John Donnelly Cc: Christoph Hellwig Cc: Christoph Lameter Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com> Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: David Laight Cc: Borislav Petkov Cc: Marek Szyprowski Cc: Robin Murphy Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 9 +++++++++ mm/page_alloc.c | 15 +++++++++++++++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 936dc0b6c226..aed44e9b5d89 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1047,6 +1047,15 @@ static inline int is_highmem_idx(enum zone_type idx) #endif } +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void); +#else +static inline bool has_managed_dma(void) +{ + return false; +} +#endif + /** * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 3eace0065ecc..e2ad2303f634 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -9518,3 +9518,18 @@ bool take_page_off_buddy(struct page *page) return ret; } #endif + +#ifdef CONFIG_ZONE_DMA +bool has_managed_dma(void) +{ + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) { + struct zone *zone = &pgdat->node_zones[ZONE_DMA]; + + if (managed_zone(zone)) + return true; + } + return false; +} +#endif /* CONFIG_ZONE_DMA */ -- cgit v1.2.3 From f47761999052b1cc987dd3e3d3adf47997358fc0 Mon Sep 17 00:00:00 2001 From: Mina Almasry Date: Fri, 14 Jan 2022 14:07:48 -0800 Subject: hugetlb: add hugetlb.*.numa_stat file For hugetlb backed jobs/VMs it's critical to understand the numa information for the memory backing these jobs to deliver optimal performance. Currently this technically can be queried from /proc/self/numa_maps, but there are significant issues with that. Namely: 1. Memory can be mapped or unmapped. 2. numa_maps are per process and need to be aggregated across all processes in the cgroup. For shared memory this is more involved as the userspace needs to make sure it doesn't double count shared mappings. 3. I believe querying numa_maps needs to hold the mmap_lock which adds to the contention on this lock. For these reasons I propose simply adding hugetlb.*.numa_stat file, which shows the numa information of the cgroup similarly to memory.numa_stat. On cgroup-v2: cat /sys/fs/cgroup/unified/test/hugetlb.2MB.numa_stat total=2097152 N0=2097152 N1=0 On cgroup-v1: cat /sys/fs/cgroup/hugetlb/test/hugetlb.2MB.numa_stat total=2097152 N0=2097152 N1=0 hierarichal_total=2097152 N0=2097152 N1=0 This patch was tested manually by allocating hugetlb memory and querying the hugetlb.*.numa_stat file of the cgroup and its parents. [colin.i.king@googlemail.com: fix spelling mistake "hierarichal" -> "hierarchical"] Link: https://lkml.kernel.org/r/20211125090635.23508-1-colin.i.king@gmail.com [keescook@chromium.org: fix copy/paste array assignment] Link: https://lkml.kernel.org/r/20211203065647.2819707-1-keescook@chromium.org Link: https://lkml.kernel.org/r/20211123001020.4083653-1-almasrymina@google.com Signed-off-by: Mina Almasry Signed-off-by: Colin Ian King Signed-off-by: Kees Cook Reviewed-by: Shakeel Butt Reviewed-by: Muchun Song Reviewed-by: Mike Kravetz Cc: Shuah Khan Cc: Miaohe Lin Cc: Oscar Salvador Cc: Michal Hocko Cc: David Rientjes Cc: Jue Wang Cc: Yang Yao Cc: Joanna Li Cc: Cannon Matthews Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v1/hugetlb.rst | 4 + Documentation/admin-guide/cgroup-v2.rst | 5 + include/linux/hugetlb.h | 4 +- include/linux/hugetlb_cgroup.h | 7 ++ mm/hugetlb_cgroup.c | 133 ++++++++++++++++++++++-- 5 files changed, 141 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/cgroup-v1/hugetlb.rst b/Documentation/admin-guide/cgroup-v1/hugetlb.rst index 338f2c7d7a1c..0fa724d82abb 100644 --- a/Documentation/admin-guide/cgroup-v1/hugetlb.rst +++ b/Documentation/admin-guide/cgroup-v1/hugetlb.rst @@ -29,12 +29,14 @@ Brief summary of control files:: hugetlb..max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded hugetlb..usage_in_bytes # show current usage for "hugepagesize" hugetlb hugetlb..failcnt # show the number of allocation failure due to HugeTLB usage limit + hugetlb..numa_stat # show the numa information of the hugetlb memory charged to this cgroup For a system supporting three hugepage sizes (64k, 32M and 1G), the control files include:: hugetlb.1GB.limit_in_bytes hugetlb.1GB.max_usage_in_bytes + hugetlb.1GB.numa_stat hugetlb.1GB.usage_in_bytes hugetlb.1GB.failcnt hugetlb.1GB.rsvd.limit_in_bytes @@ -43,6 +45,7 @@ files include:: hugetlb.1GB.rsvd.failcnt hugetlb.64KB.limit_in_bytes hugetlb.64KB.max_usage_in_bytes + hugetlb.64KB.numa_stat hugetlb.64KB.usage_in_bytes hugetlb.64KB.failcnt hugetlb.64KB.rsvd.limit_in_bytes @@ -51,6 +54,7 @@ files include:: hugetlb.64KB.rsvd.failcnt hugetlb.32MB.limit_in_bytes hugetlb.32MB.max_usage_in_bytes + hugetlb.32MB.numa_stat hugetlb.32MB.usage_in_bytes hugetlb.32MB.failcnt hugetlb.32MB.rsvd.limit_in_bytes diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 4f400b03dddf..5aa368d165da 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -2266,6 +2266,11 @@ HugeTLB Interface Files are local to the cgroup i.e. not hierarchical. The file modified event generated on this file reflects only the local events. + hugetlb..numa_stat + Similar to memory.numa_stat, it shows the numa information of the + hugetlb pages of in this cgroup. Only active in + use hugetlb pages are included. The per-node values are in bytes. + Misc ---- diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 00351ccb49a3..d1897a69c540 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -622,8 +622,8 @@ struct hstate { #endif #ifdef CONFIG_CGROUP_HUGETLB /* cgroup control files */ - struct cftype cgroup_files_dfl[7]; - struct cftype cgroup_files_legacy[9]; + struct cftype cgroup_files_dfl[8]; + struct cftype cgroup_files_legacy[10]; #endif char name[HSTATE_NAME_LEN]; }; diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index ba025ae27882..379344828e78 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -36,6 +36,11 @@ enum hugetlb_memory_event { HUGETLB_NR_MEMORY_EVENTS, }; +struct hugetlb_cgroup_per_node { + /* hugetlb usage in pages over all hstates. */ + unsigned long usage[HUGE_MAX_HSTATE]; +}; + struct hugetlb_cgroup { struct cgroup_subsys_state css; @@ -57,6 +62,8 @@ struct hugetlb_cgroup { /* Handle for "hugetlb.events.local" */ struct cgroup_file events_local_file[HUGE_MAX_HSTATE]; + + struct hugetlb_cgroup_per_node *nodeinfo[]; }; static inline struct hugetlb_cgroup * diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 79d93534ef1e..f9942841df18 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -123,29 +123,58 @@ static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, } } +static void hugetlb_cgroup_free(struct hugetlb_cgroup *h_cgroup) +{ + int node; + + for_each_node(node) + kfree(h_cgroup->nodeinfo[node]); + kfree(h_cgroup); +} + static struct cgroup_subsys_state * hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); struct hugetlb_cgroup *h_cgroup; + int node; + + h_cgroup = kzalloc(struct_size(h_cgroup, nodeinfo, nr_node_ids), + GFP_KERNEL); - h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); if (!parent_h_cgroup) root_h_cgroup = h_cgroup; + /* + * TODO: this routine can waste much memory for nodes which will + * never be onlined. It's better to use memory hotplug callback + * function. + */ + for_each_node(node) { + /* Set node_to_alloc to -1 for offline nodes. */ + int node_to_alloc = + node_state(node, N_NORMAL_MEMORY) ? node : -1; + h_cgroup->nodeinfo[node] = + kzalloc_node(sizeof(struct hugetlb_cgroup_per_node), + GFP_KERNEL, node_to_alloc); + if (!h_cgroup->nodeinfo[node]) + goto fail_alloc_nodeinfo; + } + hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); return &h_cgroup->css; + +fail_alloc_nodeinfo: + hugetlb_cgroup_free(h_cgroup); + return ERR_PTR(-ENOMEM); } static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { - struct hugetlb_cgroup *h_cgroup; - - h_cgroup = hugetlb_cgroup_from_css(css); - kfree(h_cgroup); + hugetlb_cgroup_free(hugetlb_cgroup_from_css(css)); } /* @@ -289,7 +318,17 @@ static void __hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, return; __set_hugetlb_cgroup(page, h_cg, rsvd); - return; + if (!rsvd) { + unsigned long usage = + h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; + /* + * This write is not atomic due to fetching usage and writing + * to it, but that's fine because we call this with + * hugetlb_lock held anyway. + */ + WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx], + usage + nr_pages); + } } void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, @@ -328,8 +367,17 @@ static void __hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, if (rsvd) css_put(&h_cg->css); - - return; + else { + unsigned long usage = + h_cg->nodeinfo[page_to_nid(page)]->usage[idx]; + /* + * This write is not atomic due to fetching usage and writing + * to it, but that's fine because we call this with + * hugetlb_lock held anyway. + */ + WRITE_ONCE(h_cg->nodeinfo[page_to_nid(page)]->usage[idx], + usage - nr_pages); + } } void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages, @@ -418,6 +466,59 @@ enum { RES_RSVD_FAILCNT, }; +static int hugetlb_cgroup_read_numa_stat(struct seq_file *seq, void *dummy) +{ + int nid; + struct cftype *cft = seq_cft(seq); + int idx = MEMFILE_IDX(cft->private); + bool legacy = MEMFILE_ATTR(cft->private); + struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(seq_css(seq)); + struct cgroup_subsys_state *css; + unsigned long usage; + + if (legacy) { + /* Add up usage across all nodes for the non-hierarchical total. */ + usage = 0; + for_each_node_state(nid, N_MEMORY) + usage += READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]); + seq_printf(seq, "total=%lu", usage * PAGE_SIZE); + + /* Simply print the per-node usage for the non-hierarchical total. */ + for_each_node_state(nid, N_MEMORY) + seq_printf(seq, " N%d=%lu", nid, + READ_ONCE(h_cg->nodeinfo[nid]->usage[idx]) * + PAGE_SIZE); + seq_putc(seq, '\n'); + } + + /* + * The hierarchical total is pretty much the value recorded by the + * counter, so use that. + */ + seq_printf(seq, "%stotal=%lu", legacy ? "hierarchical_" : "", + page_counter_read(&h_cg->hugepage[idx]) * PAGE_SIZE); + + /* + * For each node, transverse the css tree to obtain the hierarchical + * node usage. + */ + for_each_node_state(nid, N_MEMORY) { + usage = 0; + rcu_read_lock(); + css_for_each_descendant_pre(css, &h_cg->css) { + usage += READ_ONCE(hugetlb_cgroup_from_css(css) + ->nodeinfo[nid] + ->usage[idx]); + } + rcu_read_unlock(); + seq_printf(seq, " N%d=%lu", nid, usage * PAGE_SIZE); + } + + seq_putc(seq, '\n'); + + return 0; +} + static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -668,8 +769,14 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) events_local_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; - /* NULL terminate the last cft */ + /* Add the numa stat file */ cft = &h->cgroup_files_dfl[6]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf); + cft->seq_show = hugetlb_cgroup_read_numa_stat; + cft->flags = CFTYPE_NOT_ON_ROOT; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files_dfl[7]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_dfl_cftypes(&hugetlb_cgrp_subsys, @@ -739,8 +846,14 @@ static void __init __hugetlb_cgroup_file_legacy_init(int idx) cft->write = hugetlb_cgroup_reset; cft->read_u64 = hugetlb_cgroup_read_u64; - /* NULL terminate the last cft */ + /* Add the numa stat file */ cft = &h->cgroup_files_legacy[8]; + snprintf(cft->name, MAX_CFTYPE_NAME, "%s.numa_stat", buf); + cft->private = MEMFILE_PRIVATE(idx, 1); + cft->seq_show = hugetlb_cgroup_read_numa_stat; + + /* NULL terminate the last cft */ + cft = &h->cgroup_files_legacy[9]; memset(cft, 0, sizeof(*cft)); WARN_ON(cgroup_add_legacy_cftypes(&hugetlb_cgrp_subsys, -- cgit v1.2.3 From e9ea874a8ffb0f8ebed4f4981531a32c5b663d79 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Fri, 14 Jan 2022 14:07:55 -0800 Subject: mm/vmstat: add events for THP max_ptes_* exceeds There are interfaces to adjust max_ptes_none, max_ptes_swap, max_ptes_shared values, see /sys/kernel/mm/transparent_hugepage/khugepaged/. But system administrator may not know which value is the best. So Add those events to support adjusting max_ptes_* to suitable values. For example, if default max_ptes_swap value causes too much failures, and system uses zram whose IO is fast, administrator could increase max_ptes_swap until THP_SCAN_EXCEED_SWAP_PTE not increase anymore. Link: https://lkml.kernel.org/r/20211225094036.574157-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Cc: "Huang, Ying" Cc: Dave Hansen Cc: Minchan Kim Cc: Saravanan D Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vm_event_item.h | 3 +++ mm/khugepaged.c | 7 +++++++ mm/vmstat.c | 3 +++ 3 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index a185cc75ff52..7b2363388bfa 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -98,6 +98,9 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, THP_SPLIT_PAGE_FAILED, THP_DEFERRED_SPLIT_PAGE, THP_SPLIT_PMD, + THP_SCAN_EXCEED_NONE_PTE, + THP_SCAN_EXCEED_SWAP_PTE, + THP_SCAN_EXCEED_SHARED_PTE, #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD THP_SPLIT_PUD, #endif diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 698ea19775ac..02071f213c58 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -618,6 +618,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, continue; } else { result = SCAN_EXCEED_NONE_PTE; + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } @@ -636,6 +637,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; + count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } @@ -1253,6 +1255,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, continue; } else { result = SCAN_EXCEED_SWAP_PTE; + count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } @@ -1262,6 +1265,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, continue; } else { result = SCAN_EXCEED_NONE_PTE; + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } @@ -1290,6 +1294,7 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, if (page_mapcount(page) > 1 && ++shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; + count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } @@ -2000,6 +2005,7 @@ static void khugepaged_scan_file(struct mm_struct *mm, if (xa_is_value(page)) { if (++swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; + count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; @@ -2046,6 +2052,7 @@ static void khugepaged_scan_file(struct mm_struct *mm, if (result == SCAN_SUCCEED) { if (present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; + count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { node = khugepaged_find_target_node(); collapse_file(mm, file, start, hpage, node); diff --git a/mm/vmstat.c b/mm/vmstat.c index d701c335628c..4057372745d0 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1353,6 +1353,9 @@ const char * const vmstat_text[] = { "thp_split_page_failed", "thp_deferred_split_page", "thp_split_pmd", + "thp_scan_exceed_none_pte", + "thp_scan_exceed_swap_pte", + "thp_scan_exceed_share_pte", #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD "thp_split_pud", #endif -- cgit v1.2.3 From e4b424b7ec8791087375bb1f2480a3ba05d21e0b Mon Sep 17 00:00:00 2001 From: Gang Li Date: Fri, 14 Jan 2022 14:08:07 -0800 Subject: vmscan: make drop_slab_node static drop_slab_node is only used in drop_slab. So remove it's declaration from header file and add keyword static for it's definition. Link: https://lkml.kernel.org/r/20211111062445.5236-1-ligang.bdlg@bytedance.com Signed-off-by: Gang Li Reviewed-by: David Hildenbrand Reviewed-by: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 - mm/vmscan.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index cef65f9cbdf2..eb67eb699b78 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3122,7 +3122,6 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *, #endif void drop_slab(void); -void drop_slab_node(int nid); #ifndef CONFIG_MMU #define randomize_va_space 0 diff --git a/mm/vmscan.c b/mm/vmscan.c index 700434db5735..090bfb605ecf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -951,7 +951,7 @@ out: return freed; } -void drop_slab_node(int nid) +static void drop_slab_node(int nid) { unsigned long freed; int shift = 0; -- cgit v1.2.3 From c6018b4b254971863bd0ad36bb5e7d0fa0f0ddb0 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 14 Jan 2022 14:08:17 -0800 Subject: mm/mempolicy: add set_mempolicy_home_node syscall This syscall can be used to set a home node for the MPOL_BIND and MPOL_PREFERRED_MANY memory policy. Users should use this syscall after setting up a memory policy for the specified range as shown below. mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp, new_nodes->size + 1, 0); sys_set_mempolicy_home_node((unsigned long)p, nr_pages * page_size, home_node, 0); The syscall allows specifying a home node/preferred node from which kernel will fulfill memory allocation requests first. For address range with MPOL_BIND memory policy, if nodemask specifies more than one node, page allocations will come from the node in the nodemask with sufficient free memory that is closest to the home node/preferred node. For MPOL_PREFERRED_MANY if the nodemask specifies more than one node, page allocation will come from the node in the nodemask with sufficient free memory that is closest to the home node/preferred node. If there is not enough memory in all the nodes specified in the nodemask, the allocation will be attempted from the closest numa node to the home node in the system. This helps applications to hint at a memory allocation preference node and fallback to _only_ a set of nodes if the memory is not available on the preferred node. Fallback allocation is attempted from the node which is nearest to the preferred node. This helps applications to have control on memory allocation numa nodes and avoids default fallback to slow memory NUMA nodes. For example a system with NUMA nodes 1,2 and 3 with DRAM memory and 10, 11 and 12 of slow memory new_nodes = numa_bitmask_alloc(nr_nodes); numa_bitmask_setbit(new_nodes, 1); numa_bitmask_setbit(new_nodes, 2); numa_bitmask_setbit(new_nodes, 3); p = mmap(NULL, nr_pages * page_size, protflag, mapflag, -1, 0); mbind(p, nr_pages * page_size, MPOL_BIND, new_nodes->maskp, new_nodes->size + 1, 0); sys_set_mempolicy_home_node(p, nr_pages * page_size, 2, 0); This will allocate from nodes closer to node 2 and will make sure the kernel will only allocate from nodes 1, 2, and 3. Memory will not be allocated from slow memory nodes 10, 11, and 12. This differs from default MPOL_BIND behavior in that with default MPOL_BIND the allocation will be attempted from node closer to the local node. One of the reasons to specify a home node is to allow allocations from cpu less NUMA node and its nearby NUMA nodes. With MPOL_PREFERRED_MANY on the other hand will first try to allocate from the closest node to node 2 from the node list 1, 2 and 3. If those nodes don't have enough memory, kernel will allocate from slow memory node 10, 11 and 12 which ever is closer to node 2. Link: https://lkml.kernel.org/r/20211202123810.267175-3-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- .../admin-guide/mm/numa_memory_policy.rst | 16 ++++- include/linux/mempolicy.h | 1 + mm/mempolicy.c | 79 ++++++++++++++++++++++ 3 files changed, 95 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst index 64fd0ba0d057..5a6afecbb0d0 100644 --- a/Documentation/admin-guide/mm/numa_memory_policy.rst +++ b/Documentation/admin-guide/mm/numa_memory_policy.rst @@ -408,7 +408,7 @@ follows: Memory Policy APIs ================== -Linux supports 3 system calls for controlling memory policy. These APIS +Linux supports 4 system calls for controlling memory policy. These APIS always affect only the calling task, the calling task's address space, or some shared object mapped into the calling task's address space. @@ -460,6 +460,20 @@ requested via the 'flags' argument. See the mbind(2) man page for more details. +Set home node for a Range of Task's Address Spacec:: + + long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); + +sys_set_mempolicy_home_node set the home node for a VMA policy present in the +task's address range. The system call updates the home node only for the existing +mempolicy range. Other address ranges are ignored. A home node is the NUMA node +closest to which page allocation will come from. Specifying the home node override +the default allocation policy to allocate memory close to the local node for an +executing CPU. + + Memory Policy Command Line Interface ==================================== diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 3c7595e81150..668389b4b53d 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -46,6 +46,7 @@ struct mempolicy { unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ + int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ diff --git a/mm/mempolicy.c b/mm/mempolicy.c index de70f119984a..fc6cae7926f3 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -296,6 +296,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; + policy->home_node = NUMA_NO_NODE; return policy; } @@ -1478,6 +1479,77 @@ static long kernel_mbind(unsigned long start, unsigned long len, return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } +SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, + unsigned long, home_node, unsigned long, flags) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + struct mempolicy *new; + unsigned long vmstart; + unsigned long vmend; + unsigned long end; + int err = -ENOENT; + + start = untagged_addr(start); + if (start & ~PAGE_MASK) + return -EINVAL; + /* + * flags is used for future extension if any. + */ + if (flags != 0) + return -EINVAL; + + /* + * Check home_node is online to avoid accessing uninitialized + * NODE_DATA. + */ + if (home_node >= MAX_NUMNODES || !node_online(home_node)) + return -EINVAL; + + len = (len + PAGE_SIZE - 1) & PAGE_MASK; + end = start + len; + + if (end < start) + return -EINVAL; + if (end == start) + return 0; + mmap_write_lock(mm); + vma = find_vma(mm, start); + for (; vma && vma->vm_start < end; vma = vma->vm_next) { + + vmstart = max(start, vma->vm_start); + vmend = min(end, vma->vm_end); + new = mpol_dup(vma_policy(vma)); + if (IS_ERR(new)) { + err = PTR_ERR(new); + break; + } + /* + * Only update home node if there is an existing vma policy + */ + if (!new) + continue; + + /* + * If any vma in the range got policy other than MPOL_BIND + * or MPOL_PREFERRED_MANY we return error. We don't reset + * the home node for vmas we already updated before. + */ + if (new->mode != MPOL_BIND && new->mode != MPOL_PREFERRED_MANY) { + err = -EOPNOTSUPP; + break; + } + + new->home_node = home_node; + err = mbind_range(mm, vmstart, vmend, new); + mpol_put(new); + if (err) + break; + } + mmap_write_unlock(mm); + return err; +} + SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) @@ -1802,6 +1874,11 @@ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd) WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE)); } + if ((policy->mode == MPOL_BIND || + policy->mode == MPOL_PREFERRED_MANY) && + policy->home_node != NUMA_NO_NODE) + return policy->home_node; + return nd; } @@ -2344,6 +2421,8 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) return false; if (a->flags != b->flags) return false; + if (a->home_node != b->home_node) + return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; -- cgit v1.2.3 From 21b084fdf2a49ca1634e8e360e9ab6f9ff0dee11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 14 Jan 2022 14:08:21 -0800 Subject: mm/mempolicy: wire up syscall set_mempolicy_home_node Link: https://lkml.kernel.org/r/20211202123810.267175-4-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Cc: Ben Widawsky Cc: Dave Hansen Cc: Feng Tang Cc: Michal Hocko Cc: Andrea Arcangeli Cc: Mel Gorman Cc: Mike Kravetz Cc: Randy Dunlap Cc: Vlastimil Babka Cc: Andi Kleen Cc: Dan Williams Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/syscalls.h | 3 +++ include/uapi/asm-generic/unistd.h | 5 ++++- kernel/sys_ni.c | 1 + 21 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index ca5a32228cd6..3515bc4f16a4 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -489,3 +489,4 @@ # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease 559 common futex_waitv sys_futex_waitv +560 common set_mempolicy_home_node sys_ni_syscall diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 543100151f2b..ac964612d8b0 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -463,3 +463,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 6bdb5f5db438..4e65da3445c7 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 450 +#define __NR_compat_syscalls 451 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 41ea1195e44b..604a2053d006 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -905,6 +905,8 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 707ae121f6d3..78b1d03e86e1 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -370,3 +370,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 45bc32a41b90..b1f3940bc298 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -449,3 +449,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 2204bde3ce4a..820145e47350 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -455,3 +455,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 72d02d363f36..253ff994ed2e 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -388,3 +388,4 @@ # 447 reserved for memfd_secret 448 n32 process_mrelease sys_process_mrelease 449 n32 futex_waitv sys_futex_waitv +450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index e2c481fcede6..3f1886ad9d80 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -364,3 +364,4 @@ # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3714c97b2643..8f243e35a7b2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -437,3 +437,4 @@ # 447 reserved for memfd_secret 448 o32 process_mrelease sys_process_mrelease 449 o32 futex_waitv sys_futex_waitv +450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 358c00000755..68b46fe2f17c 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -447,3 +447,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 15109af9d075..2600b4237292 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -529,3 +529,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index ed9c5c2eafad..799147658dee 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index d9539d28bdaa..2de85c977f54 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 46adabcb1720..4398cc6fb68d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -495,3 +495,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7e25543693de..320480a8db4f 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -454,3 +454,4 @@ 447 i386 memfd_secret sys_memfd_secret 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv +450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index fe8f8dd157b4..c84d12608cd2 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -371,6 +371,7 @@ 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 3e3e1a506bed..52c94ab5c205 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -420,3 +420,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 528a478dbda8..819c0cb00b6d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1057,6 +1057,9 @@ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type ru const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); asmlinkage long sys_memfd_secret(unsigned int flags); +asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 4557a8b6086f..1c48b0ae3ba3 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -883,8 +883,11 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) + #undef __NR_syscalls -#define __NR_syscalls 450 +#define __NR_syscalls 451 /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index d1944258cfc0..a492f159624f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -297,6 +297,7 @@ COND_SYSCALL(get_mempolicy); COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); +COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); -- cgit v1.2.3 From c9fdc4d5487a16bd1f003fc8b66e91f88efb50e6 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 14 Jan 2022 14:09:06 -0800 Subject: mm/hwpoison: remove MF_MSG_BUDDY_2ND and MF_MSG_POISONED_HUGE These action_page_types are no longer used, so remove them. Link: https://lkml.kernel.org/r/20211115084006.3728254-3-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Acked-by: Yang Shi Cc: "Aneesh Kumar K.V" Cc: David Hildenbrand Cc: Ding Hui Cc: Miaohe Lin Cc: Michal Hocko Cc: Oscar Salvador Cc: Peter Xu Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- include/ras/ras_event.h | 2 -- mm/memory-failure.c | 2 -- 3 files changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index eb67eb699b78..7f594da84aca 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3201,7 +3201,6 @@ enum mf_action_page_type { MF_MSG_KERNEL_HIGH_ORDER, MF_MSG_SLAB, MF_MSG_DIFFERENT_COMPOUND, - MF_MSG_POISONED_HUGE, MF_MSG_HUGE, MF_MSG_FREE_HUGE, MF_MSG_NON_PMD_HUGE, @@ -3216,7 +3215,6 @@ enum mf_action_page_type { MF_MSG_CLEAN_LRU, MF_MSG_TRUNCATED_LRU, MF_MSG_BUDDY, - MF_MSG_BUDDY_2ND, MF_MSG_DAX, MF_MSG_UNSPLIT_THP, MF_MSG_UNKNOWN, diff --git a/include/ras/ras_event.h b/include/ras/ras_event.h index 0bdbc0d17d2f..d0337a41141c 100644 --- a/include/ras/ras_event.h +++ b/include/ras/ras_event.h @@ -358,7 +358,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_KERNEL_HIGH_ORDER, "high-order kernel page" ) \ EM ( MF_MSG_SLAB, "kernel slab page" ) \ EM ( MF_MSG_DIFFERENT_COMPOUND, "different compound page after locking" ) \ - EM ( MF_MSG_POISONED_HUGE, "huge page already hardware poisoned" ) \ EM ( MF_MSG_HUGE, "huge page" ) \ EM ( MF_MSG_FREE_HUGE, "free huge page" ) \ EM ( MF_MSG_NON_PMD_HUGE, "non-pmd-sized huge page" ) \ @@ -373,7 +372,6 @@ TRACE_EVENT(aer_event, EM ( MF_MSG_CLEAN_LRU, "clean LRU page" ) \ EM ( MF_MSG_TRUNCATED_LRU, "already truncated LRU page" ) \ EM ( MF_MSG_BUDDY, "free buddy page" ) \ - EM ( MF_MSG_BUDDY_2ND, "free buddy page (2nd try)" ) \ EM ( MF_MSG_DAX, "dax page" ) \ EM ( MF_MSG_UNSPLIT_THP, "unsplit thp" ) \ EMe ( MF_MSG_UNKNOWN, "unknown page" ) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 607785491a52..810328fe8adb 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -723,7 +723,6 @@ static const char * const action_page_types[] = { [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", [MF_MSG_SLAB] = "kernel slab page", [MF_MSG_DIFFERENT_COMPOUND] = "different compound page after locking", - [MF_MSG_POISONED_HUGE] = "huge page already hardware poisoned", [MF_MSG_HUGE] = "huge page", [MF_MSG_FREE_HUGE] = "free huge page", [MF_MSG_NON_PMD_HUGE] = "non-pmd-sized huge page", @@ -738,7 +737,6 @@ static const char * const action_page_types[] = { [MF_MSG_CLEAN_LRU] = "clean LRU page", [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", [MF_MSG_BUDDY] = "free buddy page", - [MF_MSG_BUDDY_2ND] = "free buddy page (2nd try)", [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", [MF_MSG_UNKNOWN] = "unknown page", -- cgit v1.2.3 From bf181c582588f8f7406d52f2ee228539b465f173 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 14 Jan 2022 14:09:09 -0800 Subject: mm/hwpoison: fix unpoison_memory() After recent soft-offline rework, error pages can be taken off from buddy allocator, but the existing unpoison_memory() does not properly undo the operation. Moreover, due to the recent change on __get_hwpoison_page(), get_page_unless_zero() is hardly called for hwpoisoned pages. So __get_hwpoison_page() highly likely returns -EBUSY (meaning to fail to grab page refcount) and unpoison just clears PG_hwpoison without releasing a refcount. That does not lead to a critical issue like kernel panic, but unpoisoned pages never get back to buddy (leaked permanently), which is not good. To (partially) fix this, we need to identify "taken off" pages from other types of hwpoisoned pages. We can't use refcount or page flags for this purpose, so a pseudo flag is defined by hacking ->private field. Someone might think that put_page() is enough to cancel taken-off pages, but the normal free path contains some operations not suitable for the current purpose, and can fire VM_BUG_ON(). Note that unpoison_memory() is now supposed to be cancel hwpoison events injected only by madvise() or /sys/devices/system/memory/{hard,soft}_offline_page, not by MCE injection, so please don't try to use unpoison when testing with MCE injection. [lkp@intel.com: report build failure for ARCH=i386] Link: https://lkml.kernel.org/r/20211115084006.3728254-4-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Reviewed-by: Yang Shi Cc: David Hildenbrand Cc: Oscar Salvador Cc: Michal Hocko Cc: Ding Hui Cc: Tony Luck Cc: "Aneesh Kumar K.V" Cc: Miaohe Lin Cc: Peter Xu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 1 + include/linux/page-flags.h | 4 ++ mm/memory-failure.c | 109 +++++++++++++++++++++++++++++++++++++-------- mm/page_alloc.c | 27 +++++++++++ 4 files changed, 122 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 7f594da84aca..d4fb49a5d60d 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3174,6 +3174,7 @@ enum mf_flags { MF_ACTION_REQUIRED = 1 << 1, MF_MUST_KILL = 1 << 2, MF_SOFT_OFFLINE = 1 << 3, + MF_UNPOISON = 1 << 4, }; extern int memory_failure(unsigned long pfn, int flags); extern void memory_failure_queue(unsigned long pfn, int flags); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 18423c2157e8..7e2b90dc7d3f 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -522,7 +522,11 @@ PAGEFLAG_FALSE(Uncached, uncached) PAGEFLAG(HWPoison, hwpoison, PF_ANY) TESTSCFLAG(HWPoison, hwpoison, PF_ANY) #define __PG_HWPOISON (1UL << PG_hwpoison) +#define MAGIC_HWPOISON 0x48575053U /* HWPS */ +extern void SetPageHWPoisonTakenOff(struct page *page); +extern void ClearPageHWPoisonTakenOff(struct page *page); extern bool take_page_off_buddy(struct page *page); +extern bool put_page_back_buddy(struct page *page); #else PAGEFLAG_FALSE(HWPoison, hwpoison) #define __PG_HWPOISON 0 diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 810328fe8adb..6a2b4b86b679 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1160,6 +1160,22 @@ static int page_action(struct page_state *ps, struct page *p, return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY; } +static inline bool PageHWPoisonTakenOff(struct page *page) +{ + return PageHWPoison(page) && page_private(page) == MAGIC_HWPOISON; +} + +void SetPageHWPoisonTakenOff(struct page *page) +{ + set_page_private(page, MAGIC_HWPOISON); +} + +void ClearPageHWPoisonTakenOff(struct page *page) +{ + if (PageHWPoison(page)) + set_page_private(page, 0); +} + /* * Return true if a page type of a given page is supported by hwpoison * mechanism (while handling could fail), otherwise false. This function @@ -1262,6 +1278,27 @@ out: return ret; } +static int __get_unpoison_page(struct page *page) +{ + struct page *head = compound_head(page); + int ret = 0; + bool hugetlb = false; + + ret = get_hwpoison_huge_page(head, &hugetlb); + if (hugetlb) + return ret; + + /* + * PageHWPoisonTakenOff pages are not only marked as PG_hwpoison, + * but also isolated from buddy freelist, so need to identify the + * state and have to cancel both operations to unpoison. + */ + if (PageHWPoisonTakenOff(page)) + return -EHWPOISON; + + return get_page_unless_zero(page) ? 1 : 0; +} + /** * get_hwpoison_page() - Get refcount for memory error handling * @p: Raw error page (hit by memory error) @@ -1278,18 +1315,26 @@ out: * extra care for the error page's state (as done in __get_hwpoison_page()), * and has some retry logic in get_any_page(). * + * When called from unpoison_memory(), the caller should already ensure that + * the given page has PG_hwpoison. So it's never reused for other page + * allocations, and __get_unpoison_page() never races with them. + * * Return: 0 on failure, * 1 on success for in-use pages in a well-defined state, * -EIO for pages on which we can not handle memory errors, * -EBUSY when get_hwpoison_page() has raced with page lifecycle - * operations like allocation and free. + * operations like allocation and free, + * -EHWPOISON when the page is hwpoisoned and taken off from buddy. */ static int get_hwpoison_page(struct page *p, unsigned long flags) { int ret; zone_pcp_disable(page_zone(p)); - ret = get_any_page(p, flags); + if (flags & MF_UNPOISON) + ret = __get_unpoison_page(p); + else + ret = get_any_page(p, flags); zone_pcp_enable(page_zone(p)); return ret; @@ -1937,6 +1982,28 @@ core_initcall(memory_failure_init); pr_info(fmt, pfn); \ }) +static inline int clear_page_hwpoison(struct ratelimit_state *rs, struct page *p) +{ + if (TestClearPageHWPoison(p)) { + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + page_to_pfn(p), rs); + num_poisoned_pages_dec(); + return 1; + } + return 0; +} + +static inline int unpoison_taken_off_page(struct ratelimit_state *rs, + struct page *p) +{ + if (put_page_back_buddy(p)) { + unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", + page_to_pfn(p), rs); + return 0; + } + return -EBUSY; +} + /** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page @@ -1953,9 +2020,7 @@ int unpoison_memory(unsigned long pfn) { struct page *page; struct page *p; - int freeit = 0; - int ret = 0; - unsigned long flags = 0; + int ret = -EBUSY; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -1991,24 +2056,30 @@ int unpoison_memory(unsigned long pfn) goto unlock_mutex; } - if (!get_hwpoison_page(p, flags)) { - if (TestClearPageHWPoison(p)) - num_poisoned_pages_dec(); - unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n", - pfn, &unpoison_rs); + if (PageSlab(page) || PageTable(page)) goto unlock_mutex; - } - if (TestClearPageHWPoison(page)) { - unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", - pfn, &unpoison_rs); - num_poisoned_pages_dec(); - freeit = 1; - } + ret = get_hwpoison_page(p, MF_UNPOISON); + if (!ret) { + if (clear_page_hwpoison(&unpoison_rs, page)) + ret = 0; + else + ret = -EBUSY; + } else if (ret < 0) { + if (ret == -EHWPOISON) { + ret = unpoison_taken_off_page(&unpoison_rs, p); + } else + unpoison_pr_info("Unpoison: failed to grab page %#lx\n", + pfn, &unpoison_rs); + } else { + int freeit = clear_page_hwpoison(&unpoison_rs, p); - put_page(page); - if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) put_page(page); + if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) { + put_page(page); + ret = 0; + } + } unlock_mutex: mutex_unlock(&mf_mutex); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 99fc65c532f0..d4205e5e41d1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -19,6 +19,7 @@ #include #include #include +#include #include #include #include @@ -9508,6 +9509,7 @@ bool take_page_off_buddy(struct page *page) del_page_from_free_list(page_head, zone, page_order); break_down_buddy_pages(zone, page_head, page, 0, page_order, migratetype); + SetPageHWPoisonTakenOff(page); if (!is_migrate_isolate(migratetype)) __mod_zone_freepage_state(zone, -1, migratetype); ret = true; @@ -9519,6 +9521,31 @@ bool take_page_off_buddy(struct page *page) spin_unlock_irqrestore(&zone->lock, flags); return ret; } + +/* + * Cancel takeoff done by take_page_off_buddy(). + */ +bool put_page_back_buddy(struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long pfn = page_to_pfn(page); + unsigned long flags; + int migratetype = get_pfnblock_migratetype(page, pfn); + bool ret = false; + + spin_lock_irqsave(&zone->lock, flags); + if (put_page_testzero(page)) { + ClearPageHWPoisonTakenOff(page); + __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE); + if (TestClearPageHWPoison(page)) { + num_poisoned_pages_dec(); + ret = true; + } + } + spin_unlock_irqrestore(&zone->lock, flags); + + return ret; +} #endif #ifdef CONFIG_ZONE_DMA -- cgit v1.2.3 From 5ee2fa2f063649570c702164f47a558a3432dd9e Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 14 Jan 2022 14:09:16 -0800 Subject: mm/rmap: fix potential batched TLB flush race In theory, the following race is possible for batched TLB flushing. CPU0 CPU1 ---- ---- shrink_page_list() unmap zap_pte_range() flush_tlb_batched_pending() flush_tlb_mm() try_to_unmap() set_tlb_ubc_flush_pending() mm->tlb_flush_batched = true mm->tlb_flush_batched = false After the TLB is flushed on CPU1 via flush_tlb_mm() and before mm->tlb_flush_batched is set to false, some PTE is unmapped on CPU0 and the TLB flushing is pended. Then the pended TLB flushing will be lost. Although both set_tlb_ubc_flush_pending() and flush_tlb_batched_pending() are called with PTL locked, different PTL instances may be used. Because the race window is really small, and the lost TLB flushing will cause problem only if a TLB entry is inserted before the unmapping in the race window, the race is only theoretical. But the fix is simple and cheap too. Syzbot has reported this too as follows: ================================================================== BUG: KCSAN: data-race in flush_tlb_batched_pending / try_to_unmap_one write to 0xffff8881072cfbbc of 1 bytes by task 17406 on cpu 1: flush_tlb_batched_pending+0x5f/0x80 mm/rmap.c:691 madvise_free_pte_range+0xee/0x7d0 mm/madvise.c:594 walk_pmd_range mm/pagewalk.c:128 [inline] walk_pud_range mm/pagewalk.c:205 [inline] walk_p4d_range mm/pagewalk.c:240 [inline] walk_pgd_range mm/pagewalk.c:277 [inline] __walk_page_range+0x981/0x1160 mm/pagewalk.c:379 walk_page_range+0x131/0x300 mm/pagewalk.c:475 madvise_free_single_vma mm/madvise.c:734 [inline] madvise_dontneed_free mm/madvise.c:822 [inline] madvise_vma mm/madvise.c:996 [inline] do_madvise+0xe4a/0x1140 mm/madvise.c:1202 __do_sys_madvise mm/madvise.c:1228 [inline] __se_sys_madvise mm/madvise.c:1226 [inline] __x64_sys_madvise+0x5d/0x70 mm/madvise.c:1226 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae write to 0xffff8881072cfbbc of 1 bytes by task 71 on cpu 0: set_tlb_ubc_flush_pending mm/rmap.c:636 [inline] try_to_unmap_one+0x60e/0x1220 mm/rmap.c:1515 rmap_walk_anon+0x2fb/0x470 mm/rmap.c:2301 try_to_unmap+0xec/0x110 shrink_page_list+0xe91/0x2620 mm/vmscan.c:1719 shrink_inactive_list+0x3fb/0x730 mm/vmscan.c:2394 shrink_list mm/vmscan.c:2621 [inline] shrink_lruvec+0x3c9/0x710 mm/vmscan.c:2940 shrink_node_memcgs+0x23e/0x410 mm/vmscan.c:3129 shrink_node+0x8f6/0x1190 mm/vmscan.c:3252 kswapd_shrink_node mm/vmscan.c:4022 [inline] balance_pgdat+0x702/0xd30 mm/vmscan.c:4213 kswapd+0x200/0x340 mm/vmscan.c:4473 kthread+0x2c7/0x2e0 kernel/kthread.c:327 ret_from_fork+0x1f/0x30 value changed: 0x01 -> 0x00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 71 Comm: kswapd0 Not tainted 5.16.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ================================================================== [akpm@linux-foundation.org: tweak comments] Link: https://lkml.kernel.org/r/20211201021104.126469-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reported-by: syzbot+aa5bebed695edaccf0df@syzkaller.appspotmail.com Cc: Nadav Amit Cc: Mel Gorman Cc: Andrea Arcangeli Cc: Andy Lutomirski Cc: Dave Hansen Cc: Will Deacon Cc: Yu Zhao Cc: Marco Elver Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- mm/rmap.c | 43 ++++++++++++++++++++++++++++++++++++------- 2 files changed, 37 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6a89f128c990..e3b0476a4fda 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -647,7 +647,7 @@ struct mm_struct { atomic_t tlb_flush_pending; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* See flush_tlb_batched_pending() */ - bool tlb_flush_batched; + atomic_t tlb_flush_batched; #endif struct uprobes_state uprobes_state; #ifdef CONFIG_PREEMPT_RT diff --git a/mm/rmap.c b/mm/rmap.c index 163ac4e6bcee..6a1e8c7f6213 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -621,9 +621,20 @@ void try_to_unmap_flush_dirty(void) try_to_unmap_flush(); } +/* + * Bits 0-14 of mm->tlb_flush_batched record pending generations. + * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. + */ +#define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 +#define TLB_FLUSH_BATCH_PENDING_MASK \ + ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) +#define TLB_FLUSH_BATCH_PENDING_LARGE \ + (TLB_FLUSH_BATCH_PENDING_MASK / 2) + static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; + int batch, nbatch; arch_tlbbatch_add_mm(&tlb_ubc->arch, mm); tlb_ubc->flush_required = true; @@ -633,7 +644,22 @@ static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable) * before the PTE is cleared. */ barrier(); - mm->tlb_flush_batched = true; + batch = atomic_read(&mm->tlb_flush_batched); +retry: + if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { + /* + * Prevent `pending' from catching up with `flushed' because of + * overflow. Reset `pending' and `flushed' to be 1 and 0 if + * `pending' becomes large. + */ + nbatch = atomic_cmpxchg(&mm->tlb_flush_batched, batch, 1); + if (nbatch != batch) { + batch = nbatch; + goto retry; + } + } else { + atomic_inc(&mm->tlb_flush_batched); + } /* * If the PTE was dirty then it's best to assume it's writable. The @@ -680,15 +706,18 @@ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) */ void flush_tlb_batched_pending(struct mm_struct *mm) { - if (data_race(mm->tlb_flush_batched)) { - flush_tlb_mm(mm); + int batch = atomic_read(&mm->tlb_flush_batched); + int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; + int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; + if (pending != flushed) { + flush_tlb_mm(mm); /* - * Do not allow the compiler to re-order the clearing of - * tlb_flush_batched before the tlb is flushed. + * If the new TLB flushing is pending during flushing, leave + * mm->tlb_flush_batched as is, to avoid losing flushing. */ - barrier(); - mm->tlb_flush_batched = false; + atomic_cmpxchg(&mm->tlb_flush_batched, batch, + pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else -- cgit v1.2.3 From cab0a7c115546a4865fb7439558af9077a569574 Mon Sep 17 00:00:00 2001 From: Ting Liu Date: Fri, 14 Jan 2022 14:09:28 -0800 Subject: mm: make some vars and functions static or __init "page_idle_ops" as a global var, but its scope of use within this document. So it should be static. "page_ext_ops" is a var used in the kernel initial phase. And other functions are aslo used in the kernel initial phase. So they should be __init or __initdata to reclaim memory. Link: https://lkml.kernel.org/r/20211217095023.67293-1-liuting.0x7c00@bytedance.com Signed-off-by: Ting Liu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_idle.h | 1 - mm/page_ext.c | 4 ++-- mm/page_owner.c | 4 ++-- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index 83abf95e9fa7..4663dfed1293 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -13,7 +13,6 @@ * If there is not enough space to store Idle and Young bits in page flags, use * page ext flags instead. */ -extern struct page_ext_operations page_idle_ops; static inline bool folio_test_young(struct folio *folio) { diff --git a/mm/page_ext.c b/mm/page_ext.c index bee3240604dc..2e66d934d63f 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -64,12 +64,12 @@ static bool need_page_idle(void) { return true; } -struct page_ext_operations page_idle_ops = { +static struct page_ext_operations page_idle_ops __initdata = { .need = need_page_idle, }; #endif -static struct page_ext_operations *page_ext_ops[] = { +static struct page_ext_operations *page_ext_ops[] __initdata = { #ifdef CONFIG_PAGE_OWNER &page_owner_ops, #endif diff --git a/mm/page_owner.c b/mm/page_owner.c index 4f924957ce7a..5eea061bb1e5 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -46,7 +46,7 @@ static int __init early_page_owner_param(char *buf) } early_param("page_owner", early_page_owner_param); -static bool need_page_owner(void) +static __init bool need_page_owner(void) { return page_owner_enabled; } @@ -75,7 +75,7 @@ static noinline void register_early_stack(void) early_handle = create_dummy_stack(); } -static void init_page_owner(void) +static __init void init_page_owner(void) { if (!page_owner_enabled) return; -- cgit v1.2.3 From cdeed009f3bceee41f73f0137db785fd29a05cb8 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 14 Jan 2022 14:09:44 -0800 Subject: mm/damon: remove some unneeded function definitions in damon.h In damon.h some func definitions about VA & PA can only be used in its own file, so there no need to define in the header file, and the header file will look cleaner. If other files later need these functions, the prototypes can be added to damon.h at that time. [sj@kernel.org: remove unnecessary function prototype position changes] Link: https://lkml.kernel.org/r/20211118114827.20052-1-sj@kernel.org Link: https://lkml.kernel.org/r/45fd5b3ef6cce8e28dbc1c92f9dc845ccfc949d7.1636989871.git.xhao@linux.alibaba.com Signed-off-by: Xin Hao Signed-off-by: SeongJae Park Reviewed-by: SeongJae Park Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 21 --------------------- mm/damon/paddr.c | 11 ++++++----- mm/damon/vaddr.c | 18 ++++++++++-------- 3 files changed, 16 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index b4d4be3cc987..1d1be348f506 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -461,34 +461,13 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs); #endif /* CONFIG_DAMON */ #ifdef CONFIG_DAMON_VADDR - -/* Monitoring primitives for virtual memory address spaces */ -void damon_va_init(struct damon_ctx *ctx); -void damon_va_update(struct damon_ctx *ctx); -void damon_va_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_va_check_accesses(struct damon_ctx *ctx); bool damon_va_target_valid(void *t); -void damon_va_cleanup(struct damon_ctx *ctx); -int damon_va_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); void damon_va_set_primitives(struct damon_ctx *ctx); - #endif /* CONFIG_DAMON_VADDR */ #ifdef CONFIG_DAMON_PADDR - -/* Monitoring primitives for the physical memory address space */ -void damon_pa_prepare_access_checks(struct damon_ctx *ctx); -unsigned int damon_pa_check_accesses(struct damon_ctx *ctx); bool damon_pa_target_valid(void *t); -int damon_pa_apply_scheme(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); -int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); void damon_pa_set_primitives(struct damon_ctx *ctx); - #endif /* CONFIG_DAMON_PADDR */ #endif /* _DAMON_H */ diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index a496d6f203d6..4318134cbc4c 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -73,7 +73,7 @@ static void __damon_pa_prepare_access_check(struct damon_ctx *ctx, damon_pa_mkold(r->sampling_addr); } -void damon_pa_prepare_access_checks(struct damon_ctx *ctx) +static void damon_pa_prepare_access_checks(struct damon_ctx *ctx) { struct damon_target *t; struct damon_region *r; @@ -192,7 +192,7 @@ static void __damon_pa_check_access(struct damon_ctx *ctx, last_addr = r->sampling_addr; } -unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) +static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx) { struct damon_target *t; struct damon_region *r; @@ -213,7 +213,7 @@ bool damon_pa_target_valid(void *t) return true; } -int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, +static int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, struct damos *scheme) { unsigned long addr; @@ -246,8 +246,9 @@ int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, return 0; } -int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static int damon_pa_scheme_score(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { switch (scheme->action) { case DAMOS_PAGEOUT: diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 73c5d1aafda6..a9d3b4d96e29 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -272,7 +272,7 @@ static void __damon_va_init_regions(struct damon_ctx *ctx, } /* Initialize '->regions_list' of every target (task) */ -void damon_va_init(struct damon_ctx *ctx) +static void damon_va_init(struct damon_ctx *ctx) { struct damon_target *t; @@ -292,7 +292,8 @@ void damon_va_init(struct damon_ctx *ctx) * * Returns true if it is. */ -static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re) +static bool damon_intersect(struct damon_region *r, + struct damon_addr_range *re) { return !(r->ar.end <= re->start || re->end <= r->ar.start); } @@ -356,7 +357,7 @@ static void damon_va_apply_three_regions(struct damon_target *t, /* * Update regions for current memory mappings */ -void damon_va_update(struct damon_ctx *ctx) +static void damon_va_update(struct damon_ctx *ctx) { struct damon_addr_range three_regions[3]; struct damon_target *t; @@ -418,7 +419,7 @@ static void __damon_va_prepare_access_check(struct damon_ctx *ctx, damon_va_mkold(mm, r->sampling_addr); } -void damon_va_prepare_access_checks(struct damon_ctx *ctx) +static void damon_va_prepare_access_checks(struct damon_ctx *ctx) { struct damon_target *t; struct mm_struct *mm; @@ -539,7 +540,7 @@ static void __damon_va_check_access(struct damon_ctx *ctx, last_addr = r->sampling_addr; } -unsigned int damon_va_check_accesses(struct damon_ctx *ctx) +static unsigned int damon_va_check_accesses(struct damon_ctx *ctx) { struct damon_target *t; struct mm_struct *mm; @@ -603,7 +604,7 @@ out: } #endif /* CONFIG_ADVISE_SYSCALLS */ -int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, +static int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, struct damon_region *r, struct damos *scheme) { int madv_action; @@ -633,8 +634,9 @@ int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, return damos_madvise(t, r, madv_action); } -int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static int damon_va_scheme_score(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { switch (scheme->action) { -- cgit v1.2.3 From 9b2a38d6ef25c1748e3964b0ff30a89e4ed26583 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 14 Jan 2022 14:09:53 -0800 Subject: mm/damon: move damon_rand() definition into damon.h damon_rand() is called in three files:damon/core.c, damon/ paddr.c, damon/vaddr.c, i think there is no need to redefine this twice, So move it to damon.h will be a good choice. Link: https://lkml.kernel.org/r/20211202075859.51341-1-xhao@linux.alibaba.com Signed-off-by: Xin Hao Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 4 ++++ mm/damon/core.c | 4 ---- mm/damon/prmtv-common.h | 4 ---- 3 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 1d1be348f506..3e91a597a1aa 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -11,12 +11,16 @@ #include #include #include +#include /* Minimal region size. Every damon_region is aligned by this. */ #define DAMON_MIN_REGION PAGE_SIZE /* Max priority score for DAMON-based operation schemes */ #define DAMOS_MAX_SCORE (99) +/* Get a random number in [l, r) */ +#define damon_rand(l, r) (l + prandom_u32_max(r - l)) + /** * struct damon_addr_range - Represents an address region of [@start, @end). * @start: Start address of the region (inclusive). diff --git a/mm/damon/core.c b/mm/damon/core.c index 04b8df7fd9e9..61e844d15b13 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include @@ -23,9 +22,6 @@ #define DAMON_MIN_REGION 1 #endif -/* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) - static DEFINE_MUTEX(damon_lock); static int nr_running_ctxs; diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h index 61f27037603e..e790cb5f8fe0 100644 --- a/mm/damon/prmtv-common.h +++ b/mm/damon/prmtv-common.h @@ -6,10 +6,6 @@ */ #include -#include - -/* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) struct page *damon_get_page(unsigned long pfn); -- cgit v1.2.3 From 234d68732b6c135087bdebfa0630a43ae8c27758 Mon Sep 17 00:00:00 2001 From: Xin Hao Date: Fri, 14 Jan 2022 14:09:56 -0800 Subject: mm/damon: modify damon_rand() macro to static inline function damon_rand() cannot be implemented as a macro. Example: damon_rand(a++, b); The value of 'a' will be incremented twice, This is obviously unreasonable, So there fix it. Link: https://lkml.kernel.org/r/110ffcd4e420c86c42b41ce2bc9f0fe6a4f32cd3.1638795127.git.xhao@linux.alibaba.com Fixes: b9a6ac4e4ede ("mm/damon: adaptively adjust regions") Signed-off-by: Xin Hao Reported-by: Andrew Morton Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 3e91a597a1aa..e2c8152985b7 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -19,7 +19,10 @@ #define DAMOS_MAX_SCORE (99) /* Get a random number in [l, r) */ -#define damon_rand(l, r) (l + prandom_u32_max(r - l)) +static inline unsigned long damon_rand(unsigned long l, unsigned long r) +{ + return l + prandom_u32_max(r - l); +} /** * struct damon_addr_range - Represents an address region of [@start, @end). -- cgit v1.2.3 From 88f86dcfa454784f7de550966c60fc78a3e95d6d Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:09:59 -0800 Subject: mm/damon: convert macro functions to static inline functions Patch series "mm/damon: Misc cleanups". This patchset contains miscellaneous cleanups for DAMON's macro functions and documentation. This patch (of 6): This commit converts macro functions in DAMON to static inline functions, for better type checking, code documentation, etc[1]. [1] https://lore.kernel.org/linux-mm/20211202151213.6ec830863342220da4141bc5@linux-foundation.org/ Link: https://lkml.kernel.org/r/20211209131806.19317-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211209131806.19317-2-sj@kernel.org Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 18 ++++++++++++------ mm/damon/core.c | 5 ++++- mm/damon/vaddr.c | 6 ++++-- 3 files changed, 20 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index e2c8152985b7..2dbc1f545da2 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -399,14 +399,20 @@ struct damon_ctx { struct list_head schemes; }; -#define damon_next_region(r) \ - (container_of(r->list.next, struct damon_region, list)) +static inline struct damon_region *damon_next_region(struct damon_region *r) +{ + return container_of(r->list.next, struct damon_region, list); +} -#define damon_prev_region(r) \ - (container_of(r->list.prev, struct damon_region, list)) +static inline struct damon_region *damon_prev_region(struct damon_region *r) +{ + return container_of(r->list.prev, struct damon_region, list); +} -#define damon_last_region(t) \ - (list_last_entry(&t->regions_list, struct damon_region, list)) +static inline struct damon_region *damon_last_region(struct damon_target *t) +{ + return list_last_entry(&t->regions_list, struct damon_region, list); +} #define damon_for_each_region(r, t) \ list_for_each_entry(r, &t->regions_list, list) diff --git a/mm/damon/core.c b/mm/damon/core.c index 61e844d15b13..4515cf82c433 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -729,7 +729,10 @@ static void kdamond_apply_schemes(struct damon_ctx *c) } } -#define sz_damon_region(r) (r->ar.end - r->ar.start) +static inline unsigned long sz_damon_region(struct damon_region *r) +{ + return r->ar.end - r->ar.start; +} /* * Merge two adjacent regions into one region diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 78ff2bcb66eb..68d9e4134816 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -26,8 +26,10 @@ * 't->id' should be the pointer to the relevant 'struct pid' having reference * count. Caller must put the returned task, unless it is NULL. */ -#define damon_get_task_struct(t) \ - (get_pid_task((struct pid *)t->id, PIDTYPE_PID)) +static inline struct task_struct *damon_get_task_struct(struct damon_target *t) +{ + return get_pid_task((struct pid *)t->id, PIDTYPE_PID); +} /* * Get the mm_struct of the given target -- cgit v1.2.3 From f4c6d22c6cf282ef7d24a724b9bd978ee2b74fc6 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:10:14 -0800 Subject: mm/damon: remove a mistakenly added comment for a future feature Due to a mistake in patches reordering, a comment for a future feature called 'arbitrary monitoring target support'[1], which is still under development, has added. Because it only introduces confusion and we don't have a plan to post the patches soon, this commit removes the mistakenly added part. [1] https://lore.kernel.org/linux-mm/20201215115448.25633-3-sjpark@amazon.com/ Link: https://lkml.kernel.org/r/20211209131806.19317-7-sj@kernel.org Fixes: 1f366e421c8f ("mm/damon/core: implement DAMON-based Operation Schemes (DAMOS)") Signed-off-by: SeongJae Park Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 2dbc1f545da2..97f4a224e950 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -281,7 +281,7 @@ struct damon_ctx; * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action - * to the region. This is not used for &DAMON_ARBITRARY_TARGET case. + * to the region. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. -- cgit v1.2.3 From 0e92c2ee9f459542c5384d9cfab24873c3dd6398 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:10:17 -0800 Subject: mm/damon/schemes: account scheme actions that successfully applied Patch series "mm/damon/schemes: Extend stats for better online analysis and tuning". To help online access pattern analysis and tuning of DAMON-based Operation Schemes (DAMOS), DAMOS provides simple statistics for each scheme. Introduction of DAMOS time/space quota further made the tuning easier by making the risk management easier. However, that also made understanding of the working schemes a little bit more difficult. For an example, progress of a given scheme can now be throttled by not only the aggressiveness of the target access pattern, but also the time/space quotas. So, when a scheme is showing unexpectedly slow progress, it's difficult to know by what the progress of the scheme is throttled, with currently provided statistics. This patchset extends the statistics to contain some metrics that can be helpful for such online schemes analysis and tuning (patches 1-2), exports those to users (patches 3 and 5), and add documents (patches 4 and 6). This patch (of 6): DAMON-based operation schemes (DAMOS) stats provide only the number and the amount of regions that the action of the scheme has tried to be applied. Because the action could be failed for some reasons, the currently provided information is sometimes not useful or convenient enough for schemes profiling and tuning. To improve this situation, this commit extends the DAMOS stats to provide the number and the amount of regions that the action has successfully applied. Link: https://lkml.kernel.org/r/20211210150016.35349-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211210150016.35349-2-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 28 +++++++++++++++++++++------- mm/damon/core.c | 13 ++++++++----- mm/damon/dbgfs.c | 2 +- mm/damon/paddr.c | 13 +++++++------ mm/damon/vaddr.c | 30 ++++++++++++++++-------------- 5 files changed, 53 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index 97f4a224e950..e0ad3d9aaeed 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -192,6 +192,20 @@ struct damos_watermarks { bool activated; }; +/** + * struct damos_stat - Statistics on a given scheme. + * @nr_tried: Total number of regions that the scheme is tried to be applied. + * @sz_tried: Total size of regions that the scheme is tried to be applied. + * @nr_applied: Total number of regions that the scheme is applied. + * @sz_applied: Total size of regions that the scheme is applied. + */ +struct damos_stat { + unsigned long nr_tried; + unsigned long sz_tried; + unsigned long nr_applied; + unsigned long sz_applied; +}; + /** * struct damos - Represents a Data Access Monitoring-based Operation Scheme. * @min_sz_region: Minimum size of target regions. @@ -203,8 +217,7 @@ struct damos_watermarks { * @action: &damo_action to be applied to the target regions. * @quota: Control the aggressiveness of this scheme. * @wmarks: Watermarks for automated (in)activation of this scheme. - * @stat_count: Total number of regions that this scheme is applied. - * @stat_sz: Total size of regions that this scheme is applied. + * @stat: Statistics of this scheme. * @list: List head for siblings. * * For each aggregation interval, DAMON finds regions which fit in the @@ -235,8 +248,7 @@ struct damos { enum damos_action action; struct damos_quota quota; struct damos_watermarks wmarks; - unsigned long stat_count; - unsigned long stat_sz; + struct damos_stat stat; struct list_head list; }; @@ -281,7 +293,8 @@ struct damon_ctx; * as an integer in [0, &DAMOS_MAX_SCORE]. * @apply_scheme is called from @kdamond when a region for user provided * DAMON-based operation scheme is found. It should apply the scheme's action - * to the region. + * to the region and return bytes of the region that the action is successfully + * applied. * @target_valid should check whether the target is still valid for the * monitoring. * @cleanup is called from @kdamond just before its termination. @@ -295,8 +308,9 @@ struct damon_primitive { int (*get_scheme_score)(struct damon_ctx *context, struct damon_target *t, struct damon_region *r, struct damos *scheme); - int (*apply_scheme)(struct damon_ctx *context, struct damon_target *t, - struct damon_region *r, struct damos *scheme); + unsigned long (*apply_scheme)(struct damon_ctx *context, + struct damon_target *t, struct damon_region *r, + struct damos *scheme); bool (*target_valid)(void *target); void (*cleanup)(struct damon_ctx *context); }; diff --git a/mm/damon/core.c b/mm/damon/core.c index 4515cf82c433..d745bf28509f 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -102,8 +102,7 @@ struct damos *damon_new_scheme( scheme->min_age_region = min_age_region; scheme->max_age_region = max_age_region; scheme->action = action; - scheme->stat_count = 0; - scheme->stat_sz = 0; + scheme->stat = (struct damos_stat){}; INIT_LIST_HEAD(&scheme->list); scheme->quota.ms = quota->ms; @@ -574,6 +573,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, struct damos_quota *quota = &s->quota; unsigned long sz = r->ar.end - r->ar.start; struct timespec64 begin, end; + unsigned long sz_applied = 0; if (!s->wmarks.activated) continue; @@ -627,7 +627,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, damon_split_region_at(c, t, r, sz); } ktime_get_coarse_ts64(&begin); - c->primitive.apply_scheme(c, t, r, s); + sz_applied = c->primitive.apply_scheme(c, t, r, s); ktime_get_coarse_ts64(&end); quota->total_charged_ns += timespec64_to_ns(&end) - timespec64_to_ns(&begin); @@ -641,8 +641,11 @@ static void damon_do_apply_schemes(struct damon_ctx *c, r->age = 0; update_stat: - s->stat_count++; - s->stat_sz += sz; + s->stat.nr_tried++; + s->stat.sz_tried += sz; + if (sz_applied) + s->stat.nr_applied++; + s->stat.sz_applied += sz_applied; } } diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c index bf36a2756cfb..9318b52d0b46 100644 --- a/mm/damon/dbgfs.c +++ b/mm/damon/dbgfs.c @@ -117,7 +117,7 @@ static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len) s->quota.weight_age, s->wmarks.metric, s->wmarks.interval, s->wmarks.high, s->wmarks.mid, s->wmarks.low, - s->stat_count, s->stat_sz); + s->stat.nr_tried, s->stat.sz_tried); if (!rc) return -ENOMEM; diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c index 4318134cbc4c..5e8244f65a1a 100644 --- a/mm/damon/paddr.c +++ b/mm/damon/paddr.c @@ -213,14 +213,15 @@ bool damon_pa_target_valid(void *t) return true; } -static int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { - unsigned long addr; + unsigned long addr, applied; LIST_HEAD(page_list); if (scheme->action != DAMOS_PAGEOUT) - return -EINVAL; + return 0; for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) { struct page *page = damon_get_page(PHYS_PFN(addr)); @@ -241,9 +242,9 @@ static int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, put_page(page); } } - reclaim_pages(&page_list); + applied = reclaim_pages(&page_list); cond_resched(); - return 0; + return applied * PAGE_SIZE; } static int damon_pa_scheme_score(struct damon_ctx *context, diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c index 68d9e4134816..a10df3fd3d02 100644 --- a/mm/damon/vaddr.c +++ b/mm/damon/vaddr.c @@ -572,32 +572,34 @@ bool damon_va_target_valid(void *target) } #ifndef CONFIG_ADVISE_SYSCALLS -static int damos_madvise(struct damon_target *target, struct damon_region *r, - int behavior) +static unsigned long damos_madvise(struct damon_target *target, + struct damon_region *r, int behavior) { - return -EINVAL; + return 0; } #else -static int damos_madvise(struct damon_target *target, struct damon_region *r, - int behavior) +static unsigned long damos_madvise(struct damon_target *target, + struct damon_region *r, int behavior) { struct mm_struct *mm; - int ret = -ENOMEM; + unsigned long start = PAGE_ALIGN(r->ar.start); + unsigned long len = PAGE_ALIGN(r->ar.end - r->ar.start); + unsigned long applied; mm = damon_get_mm(target); if (!mm) - goto out; + return 0; - ret = do_madvise(mm, PAGE_ALIGN(r->ar.start), - PAGE_ALIGN(r->ar.end - r->ar.start), behavior); + applied = do_madvise(mm, start, len, behavior) ? 0 : len; mmput(mm); -out: - return ret; + + return applied; } #endif /* CONFIG_ADVISE_SYSCALLS */ -static int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, - struct damon_region *r, struct damos *scheme) +static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx, + struct damon_target *t, struct damon_region *r, + struct damos *scheme) { int madv_action; @@ -620,7 +622,7 @@ static int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t, case DAMOS_STAT: return 0; default: - return -EINVAL; + return 0; } return damos_madvise(t, r, madv_action); -- cgit v1.2.3 From 6268eac34ca30af7f6313504d556ec7fcd295621 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 14 Jan 2022 14:10:20 -0800 Subject: mm/damon/schemes: account how many times quota limit has exceeded If the time/space quotas of a given DAMON-based operation scheme is too small, the scheme could show unexpectedly slow progress. However, there is no good way to notice the case in runtime. This commit extends the DAMOS stat to provide how many times the quota limits exceeded so that the users can easily notice the case and tune the scheme. Link: https://lkml.kernel.org/r/20211210150016.35349-3-sj@kernel.org Signed-off-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 2 ++ mm/damon/core.c | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index e0ad3d9aaeed..af648388e759 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -198,12 +198,14 @@ struct damos_watermarks { * @sz_tried: Total size of regions that the scheme is tried to be applied. * @nr_applied: Total number of regions that the scheme is applied. * @sz_applied: Total size of regions that the scheme is applied. + * @qt_exceeds: Total number of times the quota of the scheme has exceeded. */ struct damos_stat { unsigned long nr_tried; unsigned long sz_tried; unsigned long nr_applied; unsigned long sz_applied; + unsigned long qt_exceeds; }; /** diff --git a/mm/damon/core.c b/mm/damon/core.c index d745bf28509f..d5120b326e1b 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -693,6 +693,8 @@ static void kdamond_apply_schemes(struct damon_ctx *c) if (time_after_eq(jiffies, quota->charged_from + msecs_to_jiffies( quota->reset_interval))) { + if (quota->esz && quota->charged_sz >= quota->esz) + s->stat.qt_exceeds++; quota->total_charged_sz += quota->charged_sz; quota->charged_from = jiffies; quota->charged_sz = 0; -- cgit v1.2.3 From 2cd4b8e10cc31eadb5b10b1d73b3f28156f3776c Mon Sep 17 00:00:00 2001 From: Guoqing Jiang Date: Fri, 14 Jan 2022 14:10:38 -0800 Subject: mm/damon: move the implementation of damon_insert_region to damon.h Usually, inline function is declared static since it should sit between storage and type. And implement it in a header file if used by multiple files. And this change also fixes compile issue when backport damon to 5.10. mm/damon/vaddr.c: In function `damon_va_evenly_split_region': ./include/linux/damon.h:425:13: error: inlining failed in call to `always_inline' `damon_insert_region': function body not available 425 | inline void damon_insert_region(struct damon_region *r, | ^~~~~~~~~~~~~~~~~~~ mm/damon/vaddr.c:86:3: note: called from here 86 | damon_insert_region(n, r, next, t); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Link: https://lkml.kernel.org/r/20211223085703.6142-1-guoqing.jiang@linux.dev Signed-off-by: Guoqing Jiang Reviewed-by: SeongJae Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/damon.h | 13 +++++++++++-- mm/damon/core.c | 11 ----------- 2 files changed, 11 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/damon.h b/include/linux/damon.h index af648388e759..5e1e3a128b77 100644 --- a/include/linux/damon.h +++ b/include/linux/damon.h @@ -451,9 +451,18 @@ static inline struct damon_region *damon_last_region(struct damon_target *t) #ifdef CONFIG_DAMON struct damon_region *damon_new_region(unsigned long start, unsigned long end); -inline void damon_insert_region(struct damon_region *r, + +/* + * Add a region between two other regions + */ +static inline void damon_insert_region(struct damon_region *r, struct damon_region *prev, struct damon_region *next, - struct damon_target *t); + struct damon_target *t) +{ + __list_add(&r->list, &prev->list, &next->list); + t->nr_regions++; +} + void damon_add_region(struct damon_region *r, struct damon_target *t); void damon_destroy_region(struct damon_region *r, struct damon_target *t); diff --git a/mm/damon/core.c b/mm/damon/core.c index d5120b326e1b..6482d510dcbe 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -49,17 +49,6 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end) return region; } -/* - * Add a region between two other regions - */ -inline void damon_insert_region(struct damon_region *r, - struct damon_region *prev, struct damon_region *next, - struct damon_target *t) -{ - __list_add(&r->list, &prev->list, &next->list); - t->nr_regions++; -} - void damon_add_region(struct damon_region *r, struct damon_target *t) { list_add_tail(&r->list, &t->regions_list); -- cgit v1.2.3 From 47d8c15615c0a2046d2d90b04cb80b81ddf31fb1 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:16:59 -0700 Subject: include: move find.h from asm_generic to linux find_bit API and bitmap API are closely related, but inclusion paths are different - include/asm-generic and include/linux, correspondingly. In the past it made a lot of troubles due to circular dependencies and/or undefined symbols. Fix this by moving find.h under include/linux. Signed-off-by: Yury Norov Tested-by: Wolfram Sang Acked-by: Geert Uytterhoeven --- MAINTAINERS | 2 +- arch/alpha/include/asm/bitops.h | 2 - arch/arc/include/asm/bitops.h | 1 - arch/arm/include/asm/bitops.h | 1 - arch/arm64/include/asm/bitops.h | 1 - arch/csky/include/asm/bitops.h | 1 - arch/h8300/include/asm/bitops.h | 1 - arch/hexagon/include/asm/bitops.h | 1 - arch/ia64/include/asm/bitops.h | 2 - arch/m68k/include/asm/bitops.h | 2 - arch/mips/include/asm/bitops.h | 1 - arch/openrisc/include/asm/bitops.h | 1 - arch/parisc/include/asm/bitops.h | 1 - arch/powerpc/include/asm/bitops.h | 2 - arch/riscv/include/asm/bitops.h | 1 - arch/s390/include/asm/bitops.h | 1 - arch/sh/include/asm/bitops.h | 1 - arch/sparc/include/asm/bitops_32.h | 1 - arch/sparc/include/asm/bitops_64.h | 2 - arch/x86/include/asm/bitops.h | 2 - arch/xtensa/include/asm/bitops.h | 1 - include/asm-generic/bitops.h | 1 - include/asm-generic/bitops/find.h | 262 ------------------------------------ include/linux/bitmap.h | 1 + include/linux/find.h | 268 +++++++++++++++++++++++++++++++++++++ 25 files changed, 270 insertions(+), 290 deletions(-) delete mode 100644 include/asm-generic/bitops/find.h create mode 100644 include/linux/find.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index dd36acc87ce6..4646786f5302 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3359,8 +3359,8 @@ M: Yury Norov R: Andy Shevchenko R: Rasmus Villemoes S: Maintained -F: include/asm-generic/bitops/find.h F: include/linux/bitmap.h +F: include/linux/find.h F: lib/bitmap.c F: lib/find_bit.c F: lib/find_bit_benchmark.c diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h index 5adca78830b5..e1d8483a45f2 100644 --- a/arch/alpha/include/asm/bitops.h +++ b/arch/alpha/include/asm/bitops.h @@ -430,8 +430,6 @@ static inline unsigned int __arch_hweight8(unsigned int w) #endif /* __KERNEL__ */ -#include - #ifdef __KERNEL__ /* diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h index a7daaf64ae34..bdb7e190a294 100644 --- a/arch/arc/include/asm/bitops.h +++ b/arch/arc/include/asm/bitops.h @@ -189,7 +189,6 @@ static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x) #include #include -#include #include #include diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index c92e42a5c8f7..8e94fe7ab5eb 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -264,7 +264,6 @@ static inline int find_next_bit_le(const void *p, int size, int offset) #endif -#include #include /* diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h index 81a3e519b07d..9b3c787132d2 100644 --- a/arch/arm64/include/asm/bitops.h +++ b/arch/arm64/include/asm/bitops.h @@ -18,7 +18,6 @@ #include #include -#include #include #include diff --git a/arch/csky/include/asm/bitops.h b/arch/csky/include/asm/bitops.h index 02b72a000767..72e1b2aa29a0 100644 --- a/arch/csky/include/asm/bitops.h +++ b/arch/csky/include/asm/bitops.h @@ -59,7 +59,6 @@ static __always_inline unsigned long __fls(unsigned long x) #include #include -#include #ifndef _LINUX_BITOPS_H #error only can be included directly diff --git a/arch/h8300/include/asm/bitops.h b/arch/h8300/include/asm/bitops.h index c867a80cab5b..4489e3d6edd3 100644 --- a/arch/h8300/include/asm/bitops.h +++ b/arch/h8300/include/asm/bitops.h @@ -168,7 +168,6 @@ static inline unsigned long __ffs(unsigned long word) return result; } -#include #include #include #include diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 71429f756af0..75d6ba3643b8 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -271,7 +271,6 @@ static inline unsigned long __fls(unsigned long word) } #include -#include #include #include diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h index 2f24ee6459d2..577be93c0818 100644 --- a/arch/ia64/include/asm/bitops.h +++ b/arch/ia64/include/asm/bitops.h @@ -441,8 +441,6 @@ static __inline__ unsigned long __arch_hweight64(unsigned long x) #endif /* __KERNEL__ */ -#include - #ifdef __KERNEL__ #include diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 7b93e1fd8ffa..51283db53667 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -529,6 +529,4 @@ static inline int __fls(int x) #include #endif /* __KERNEL__ */ -#include - #endif /* _M68K_BITOPS_H */ diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index dc2a6234dd3c..c09d57f907f7 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -446,7 +446,6 @@ static inline int ffs(int word) } #include -#include #ifdef __KERNEL__ diff --git a/arch/openrisc/include/asm/bitops.h b/arch/openrisc/include/asm/bitops.h index 7f1ca35213d8..d773ed938acb 100644 --- a/arch/openrisc/include/asm/bitops.h +++ b/arch/openrisc/include/asm/bitops.h @@ -30,7 +30,6 @@ #include #include #include -#include #ifndef _LINUX_BITOPS_H #error only can be included directly diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h index daa2afd974fb..0ec9cfc5131f 100644 --- a/arch/parisc/include/asm/bitops.h +++ b/arch/parisc/include/asm/bitops.h @@ -203,7 +203,6 @@ static __inline__ int fls(unsigned int x) #include #include #include -#include #include #include diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h index 11847b6a244e..abc8f2c7c570 100644 --- a/arch/powerpc/include/asm/bitops.h +++ b/arch/powerpc/include/asm/bitops.h @@ -255,8 +255,6 @@ unsigned long __arch_hweight64(__u64 w); #include #endif -#include - /* wrappers that deal with KASAN instrumentation */ #include #include diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h index 396a3303c537..3540b690944b 100644 --- a/arch/riscv/include/asm/bitops.h +++ b/arch/riscv/include/asm/bitops.h @@ -20,7 +20,6 @@ #include #include #include -#include #include #include diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 5a530c552c23..1d40630128a5 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -387,7 +387,6 @@ static inline int fls(unsigned int word) #endif /* CONFIG_HAVE_MARCH_Z9_109_FEATURES */ #include -#include #include #include #include diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h index 3b6c7b5b7ec9..10ceb0d6b5a9 100644 --- a/arch/sh/include/asm/bitops.h +++ b/arch/sh/include/asm/bitops.h @@ -68,6 +68,5 @@ static inline unsigned long __ffs(unsigned long word) #include #include -#include #endif /* __ASM_SH_BITOPS_H */ diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h index 0ceff3b915a8..889afa9f990f 100644 --- a/arch/sparc/include/asm/bitops_32.h +++ b/arch/sparc/include/asm/bitops_32.h @@ -100,7 +100,6 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) #include #include #include -#include #include #include diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h index ca7ea5913494..005a8ae858f1 100644 --- a/arch/sparc/include/asm/bitops_64.h +++ b/arch/sparc/include/asm/bitops_64.h @@ -52,8 +52,6 @@ unsigned int __arch_hweight8(unsigned int w); #include #endif /* __KERNEL__ */ -#include - #ifdef __KERNEL__ #include diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 0367efdc5b7a..a288ecd230ab 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -380,8 +380,6 @@ static __always_inline int fls64(__u64 x) #include #endif -#include - #include #include diff --git a/arch/xtensa/include/asm/bitops.h b/arch/xtensa/include/asm/bitops.h index 3f71d364ba90..cd225896c40f 100644 --- a/arch/xtensa/include/asm/bitops.h +++ b/arch/xtensa/include/asm/bitops.h @@ -205,7 +205,6 @@ BIT_OPS(change, "xor", ) #undef BIT_OP #undef TEST_AND_BIT_OP -#include #include #include diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h index df9b5bc3d282..a47b8a71d6fe 100644 --- a/include/asm-generic/bitops.h +++ b/include/asm-generic/bitops.h @@ -20,7 +20,6 @@ #include #include #include -#include #ifndef _LINUX_BITOPS_H #error only can be included directly diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h deleted file mode 100644 index 91b1b23f2b0c..000000000000 --- a/include/asm-generic/bitops/find.h +++ /dev/null @@ -1,262 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_GENERIC_BITOPS_FIND_H_ -#define _ASM_GENERIC_BITOPS_FIND_H_ - -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); -extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); -extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); -extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); - -#ifndef find_next_bit -/** - * find_next_bit - find the next set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The bitmap size in bits - * - * Returns the bit number for the next set bit - * If no bits are set, returns @size. - */ -static inline -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val; - - if (unlikely(offset >= size)) - return size; - - val = *addr & GENMASK(size - 1, offset); - return val ? __ffs(val) : size; - } - - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); -} -#endif - -#ifndef find_next_and_bit -/** - * find_next_and_bit - find the next set bit in both memory regions - * @addr1: The first address to base the search on - * @addr2: The second address to base the search on - * @offset: The bitnumber to start searching at - * @size: The bitmap size in bits - * - * Returns the bit number for the next set bit - * If no bits are set, returns @size. - */ -static inline -unsigned long find_next_and_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long size, - unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val; - - if (unlikely(offset >= size)) - return size; - - val = *addr1 & *addr2 & GENMASK(size - 1, offset); - return val ? __ffs(val) : size; - } - - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); -} -#endif - -#ifndef find_next_zero_bit -/** - * find_next_zero_bit - find the next cleared bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The bitmap size in bits - * - * Returns the bit number of the next zero bit - * If no bits are zero, returns @size. - */ -static inline -unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val; - - if (unlikely(offset >= size)) - return size; - - val = *addr | ~GENMASK(size - 1, offset); - return val == ~0UL ? size : ffz(val); - } - - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); -} -#endif - -#ifdef CONFIG_GENERIC_FIND_FIRST_BIT - -#ifndef find_first_bit -/** - * find_first_bit - find the first set bit in a memory region - * @addr: The address to start the search at - * @size: The maximum number of bits to search - * - * Returns the bit number of the first set bit. - * If no bits are set, returns @size. - */ -static inline -unsigned long find_first_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr & GENMASK(size - 1, 0); - - return val ? __ffs(val) : size; - } - - return _find_first_bit(addr, size); -} -#endif - -#ifndef find_first_zero_bit -/** - * find_first_zero_bit - find the first cleared bit in a memory region - * @addr: The address to start the search at - * @size: The maximum number of bits to search - * - * Returns the bit number of the first cleared bit. - * If no bits are zero, returns @size. - */ -static inline -unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr | ~GENMASK(size - 1, 0); - - return val == ~0UL ? size : ffz(val); - } - - return _find_first_zero_bit(addr, size); -} -#endif - -#else /* CONFIG_GENERIC_FIND_FIRST_BIT */ - -#ifndef find_first_bit -#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) -#endif -#ifndef find_first_zero_bit -#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) -#endif - -#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ - -#ifndef find_last_bit -/** - * find_last_bit - find the last set bit in a memory region - * @addr: The address to start the search at - * @size: The number of bits to search - * - * Returns the bit number of the last set bit, or size. - */ -static inline -unsigned long find_last_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr & GENMASK(size - 1, 0); - - return val ? __fls(val) : size; - } - - return _find_last_bit(addr, size); -} -#endif - -/** - * find_next_clump8 - find next 8-bit clump with set bits in a memory region - * @clump: location to store copy of found clump - * @addr: address to base the search on - * @size: bitmap size in number of bits - * @offset: bit offset at which to start searching - * - * Returns the bit offset for the next set clump; the found clump value is - * copied to the location pointed by @clump. If no bits are set, returns @size. - */ -extern unsigned long find_next_clump8(unsigned long *clump, - const unsigned long *addr, - unsigned long size, unsigned long offset); - -#define find_first_clump8(clump, bits, size) \ - find_next_clump8((clump), (bits), (size), 0) - -#if defined(__LITTLE_ENDIAN) - -static inline unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset) -{ - return find_next_zero_bit(addr, size, offset); -} - -static inline unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset) -{ - return find_next_bit(addr, size, offset); -} - -static inline unsigned long find_first_zero_bit_le(const void *addr, - unsigned long size) -{ - return find_first_zero_bit(addr, size); -} - -#elif defined(__BIG_ENDIAN) - -#ifndef find_next_zero_bit_le -static inline -unsigned long find_next_zero_bit_le(const void *addr, unsigned - long size, unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val = *(const unsigned long *)addr; - - if (unlikely(offset >= size)) - return size; - - val = swab(val) | ~GENMASK(size - 1, offset); - return val == ~0UL ? size : ffz(val); - } - - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); -} -#endif - -#ifndef find_next_bit_le -static inline -unsigned long find_next_bit_le(const void *addr, unsigned - long size, unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val = *(const unsigned long *)addr; - - if (unlikely(offset >= size)) - return size; - - val = swab(val) & GENMASK(size - 1, offset); - return val ? __ffs(val) : size; - } - - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); -} -#endif - -#ifndef find_first_zero_bit_le -#define find_first_zero_bit_le(addr, size) \ - find_next_zero_bit_le((addr), (size), 0) -#endif - -#else -#error "Please fix " -#endif - -#endif /*_ASM_GENERIC_BITOPS_FIND_H_ */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index a241dcf50f39..ead4a150bd7f 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -6,6 +6,7 @@ #include #include +#include #include #include #include diff --git a/include/linux/find.h b/include/linux/find.h new file mode 100644 index 000000000000..c5410c243e04 --- /dev/null +++ b/include/linux/find.h @@ -0,0 +1,268 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_FIND_H_ +#define __LINUX_FIND_H_ + +#ifndef __LINUX_BITMAP_H +#error only can be included directly +#endif + +#include + +extern unsigned long _find_next_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long nbits, + unsigned long start, unsigned long invert, unsigned long le); +extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); + +#ifndef find_next_bit +/** + * find_next_bit - find the next set bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); +} +#endif + +#ifndef find_next_and_bit +/** + * find_next_and_bit - find the next set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & *addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); +} +#endif + +#ifndef find_next_zero_bit +/** + * find_next_zero_bit - find the next cleared bit in a memory region + * @addr: The address to base the search on + * @offset: The bitnumber to start searching at + * @size: The bitmap size in bits + * + * Returns the bit number of the next zero bit + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); +} +#endif + +#ifdef CONFIG_GENERIC_FIND_FIRST_BIT + +#ifndef find_first_bit +/** + * find_first_bit - find the first set bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first set bit. + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_bit(addr, size); +} +#endif + +#ifndef find_first_zero_bit +/** + * find_first_zero_bit - find the first cleared bit in a memory region + * @addr: The address to start the search at + * @size: The maximum number of bits to search + * + * Returns the bit number of the first cleared bit. + * If no bits are zero, returns @size. + */ +static inline +unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr | ~GENMASK(size - 1, 0); + + return val == ~0UL ? size : ffz(val); + } + + return _find_first_zero_bit(addr, size); +} +#endif + +#else /* CONFIG_GENERIC_FIND_FIRST_BIT */ + +#ifndef find_first_bit +#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) +#endif +#ifndef find_first_zero_bit +#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) +#endif + +#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ + +#ifndef find_last_bit +/** + * find_last_bit - find the last set bit in a memory region + * @addr: The address to start the search at + * @size: The number of bits to search + * + * Returns the bit number of the last set bit, or size. + */ +static inline +unsigned long find_last_bit(const unsigned long *addr, unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr & GENMASK(size - 1, 0); + + return val ? __fls(val) : size; + } + + return _find_last_bit(addr, size); +} +#endif + +/** + * find_next_clump8 - find next 8-bit clump with set bits in a memory region + * @clump: location to store copy of found clump + * @addr: address to base the search on + * @size: bitmap size in number of bits + * @offset: bit offset at which to start searching + * + * Returns the bit offset for the next set clump; the found clump value is + * copied to the location pointed by @clump. If no bits are set, returns @size. + */ +extern unsigned long find_next_clump8(unsigned long *clump, + const unsigned long *addr, + unsigned long size, unsigned long offset); + +#define find_first_clump8(clump, bits, size) \ + find_next_clump8((clump), (bits), (size), 0) + +#if defined(__LITTLE_ENDIAN) + +static inline unsigned long find_next_zero_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_zero_bit(addr, size, offset); +} + +static inline unsigned long find_next_bit_le(const void *addr, + unsigned long size, unsigned long offset) +{ + return find_next_bit(addr, size, offset); +} + +static inline unsigned long find_first_zero_bit_le(const void *addr, + unsigned long size) +{ + return find_first_zero_bit(addr, size); +} + +#elif defined(__BIG_ENDIAN) + +#ifndef find_next_zero_bit_le +static inline +unsigned long find_next_zero_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + + return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); +} +#endif + +#ifndef find_next_bit_le +static inline +unsigned long find_next_bit_le(const void *addr, unsigned + long size, unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_bit(addr, NULL, size, offset, 0UL, 1); +} +#endif + +#ifndef find_first_zero_bit_le +#define find_first_zero_bit_le(addr, size) \ + find_next_zero_bit_le((addr), (size), 0) +#endif + +#else +#error "Please fix " +#endif + +#endif /*__LINUX_FIND_H_ */ -- cgit v1.2.3 From c126a53c276048125b4a950072bab37ad0fea120 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:00 -0700 Subject: arch: remove GENERIC_FIND_FIRST_BIT entirely In 5.12 cycle we enabled GENERIC_FIND_FIRST_BIT config option for ARM64 and MIPS. It increased performance and shrunk .text size; and so far I didn't receive any negative feedback on the change. https://lore.kernel.org/linux-arch/20210225135700.1381396-1-yury.norov@gmail.com/ Now I think it's a good time to switch all architectures to use find_{first,last}_bit() unconditionally, and so remove corresponding config option. The patch does't introduce functioal changes for arc, arm, arm64, mips, m68k, s390 and x86, for other architectures I expect improvement both in performance and .text size. Signed-off-by: Yury Norov Tested-by: Alexander Lobakin (mips) Reviewed-by: Alexander Lobakin (mips) Reviewed-by: Andy Shevchenko Acked-by: Will Deacon Tested-by: Wolfram Sang --- arch/arc/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/x86/um/Kconfig | 1 - include/linux/find.h | 13 ------------- lib/Kconfig | 3 --- 8 files changed, 22 deletions(-) (limited to 'include/linux') diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index b4ae6058902a..4bec4b0b6ce1 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -20,7 +20,6 @@ config ARC select COMMON_CLK select DMA_DIRECT_REMAP select GENERIC_ATOMIC64 if !ISA_ARCV2 || !(ARC_HAS_LL64 && ARC_HAS_LLSC) - select GENERIC_FIND_FIRST_BIT # for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index c4207cf9bb17..517d26c8002d 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -120,7 +120,6 @@ config ARM64 select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP - select GENERIC_FIND_FIRST_BIT select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_IPI select GENERIC_IRQ_PROBE diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0215dc1529e9..00951bfdbab0 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -32,7 +32,6 @@ config MIPS select GENERIC_ATOMIC64 if !64BIT select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE - select GENERIC_FIND_FIRST_BIT select GENERIC_GETTIMEOFDAY select GENERIC_IOMAP select GENERIC_IRQ_PROBE diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2a5bb4f29cfe..4f80f1c95468 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -127,7 +127,6 @@ config S390 select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_VULNERABILITIES select GENERIC_ENTRY - select GENERIC_FIND_FIRST_BIT select GENERIC_GETTIMEOFDAY select GENERIC_PTDUMP select GENERIC_SMP_IDLE_THREAD diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5c2ccb85f2ef..60484b39257c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -136,7 +136,6 @@ config X86 select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_ENTRY - select GENERIC_FIND_FIRST_BIT select GENERIC_IOMAP select GENERIC_IRQ_EFFECTIVE_AFF_MASK if SMP select GENERIC_IRQ_MATRIX_ALLOCATOR if X86_LOCAL_APIC diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index 95d26a69088b..40d6a06e41c8 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -8,7 +8,6 @@ endmenu config UML_X86 def_bool y - select GENERIC_FIND_FIRST_BIT config 64BIT bool "64-bit kernel" if "$(SUBARCH)" = "x86" diff --git a/include/linux/find.h b/include/linux/find.h index c5410c243e04..ea57f7f38c49 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -101,8 +101,6 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, } #endif -#ifdef CONFIG_GENERIC_FIND_FIRST_BIT - #ifndef find_first_bit /** * find_first_bit - find the first set bit in a memory region @@ -147,17 +145,6 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) } #endif -#else /* CONFIG_GENERIC_FIND_FIRST_BIT */ - -#ifndef find_first_bit -#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) -#endif -#ifndef find_first_zero_bit -#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) -#endif - -#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ - #ifndef find_last_bit /** * find_last_bit - find the last set bit in a memory region diff --git a/lib/Kconfig b/lib/Kconfig index 5e7165e6a346..6a6ae5312fa0 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -65,9 +65,6 @@ config GENERIC_STRNLEN_USER config GENERIC_NET_UTILS bool -config GENERIC_FIND_FIRST_BIT - bool - source "lib/math/Kconfig" config NO_GENERIC_PCI_IOPORT_MAP -- cgit v1.2.3 From f68edc9297bf3f7c94abb54b9b0b053607f7587b Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:01 -0700 Subject: lib: add find_first_and_bit() Currently find_first_and_bit() is an alias to find_next_and_bit(). However, it is widely used in cpumask, so it worth to optimize it. This patch adds its own implementation for find_first_and_bit(). On x86_64 find_bit_benchmark says: Before (#define find_first_and_bit(...) find_next_and_bit(..., 0): Start testing find_bit() with random-filled bitmap [ 140.291468] find_first_and_bit: 46890919 ns, 32671 iterations Start testing find_bit() with sparse bitmap [ 140.295028] find_first_and_bit: 7103 ns, 1 iterations After: Start testing find_bit() with random-filled bitmap [ 162.574907] find_first_and_bit: 25045813 ns, 32846 iterations Start testing find_bit() with sparse bitmap [ 162.578458] find_first_and_bit: 4900 ns, 1 iterations (Thanks to Alexey Klimov for thorough testing.) Signed-off-by: Yury Norov Tested-by: Wolfram Sang Tested-by: Alexey Klimov --- include/linux/find.h | 27 +++++++++++++++++++++++++++ lib/find_bit.c | 21 +++++++++++++++++++++ lib/find_bit_benchmark.c | 21 +++++++++++++++++++++ 3 files changed, 69 insertions(+) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index ea57f7f38c49..6048f8c97418 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -12,6 +12,8 @@ extern unsigned long _find_next_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -123,6 +125,31 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) } #endif +#ifndef find_first_and_bit +/** + * find_first_and_bit - find the first set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_bit(addr1, addr2, size); +} +#endif + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region diff --git a/lib/find_bit.c b/lib/find_bit.c index 0f8e2e369b1d..1b8e4b2a9cba 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -89,6 +89,27 @@ unsigned long _find_first_bit(const unsigned long *addr, unsigned long size) EXPORT_SYMBOL(_find_first_bit); #endif +#ifndef find_first_and_bit +/* + * Find the first set bit in two memory regions. + */ +unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + unsigned long idx, val; + + for (idx = 0; idx * BITS_PER_LONG < size; idx++) { + val = addr1[idx] & addr2[idx]; + if (val) + return min(idx * BITS_PER_LONG + __ffs(val), size); + } + + return size; +} +EXPORT_SYMBOL(_find_first_and_bit); +#endif + #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c index 5637c5711db9..db904b57d4b8 100644 --- a/lib/find_bit_benchmark.c +++ b/lib/find_bit_benchmark.c @@ -49,6 +49,25 @@ static int __init test_find_first_bit(void *bitmap, unsigned long len) return 0; } +static int __init test_find_first_and_bit(void *bitmap, const void *bitmap2, unsigned long len) +{ + static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata; + unsigned long i, cnt; + ktime_t time; + + bitmap_copy(cp, bitmap, BITMAP_LEN); + + time = ktime_get(); + for (cnt = i = 0; i < len; cnt++) { + i = find_first_and_bit(cp, bitmap2, len); + __clear_bit(i, cp); + } + time = ktime_get() - time; + pr_err("find_first_and_bit: %18llu ns, %6ld iterations\n", time, cnt); + + return 0; +} + static int __init test_find_next_bit(const void *bitmap, unsigned long len) { unsigned long i, cnt; @@ -129,6 +148,7 @@ static int __init find_bit_test(void) * traverse only part of bitmap to avoid soft lockup. */ test_find_first_bit(bitmap, BITMAP_LEN / 10); + test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN / 2); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); @@ -145,6 +165,7 @@ static int __init find_bit_test(void) test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); /* -- cgit v1.2.3 From 93ba139ba8190c33009c5353ca43c8519443f467 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:02 -0700 Subject: cpumask: use find_first_and_bit() Now we have an efficient implementation for find_first_and_bit(), so switch cpumask to use it where appropriate. Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- include/linux/cpumask.h | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 1e7399fc69c0..c4e1b9ea0ba4 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -123,6 +123,12 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return 0; } +static inline unsigned int cpumask_first_and(const struct cpumask *srcp1, + const struct cpumask *srcp2) +{ + return 0; +} + static inline unsigned int cpumask_last(const struct cpumask *srcp) { return 0; @@ -167,7 +173,7 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) static inline int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { - return cpumask_next_and(-1, src1p, src2p); + return cpumask_first_and(src1p, src2p); } static inline int cpumask_any_distribute(const struct cpumask *srcp) @@ -195,6 +201,19 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 + * @src1p: the first input + * @src2p: the second input + * + * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). + */ +static inline +unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) +{ + return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), nr_cpumask_bits); +} + /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer @@ -585,15 +604,6 @@ static inline void cpumask_copy(struct cpumask *dstp, */ #define cpumask_any(srcp) cpumask_first(srcp) -/** - * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 - * @src1p: the first input - * @src2p: the second input - * - * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). - */ -#define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) - /** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask -- cgit v1.2.3 From 9b51d9d866482a703646fd4c07e433c3d9d88efd Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:05 -0700 Subject: cpumask: replace cpumask_next_* with cpumask_first_* where appropriate cpumask_first() is a more effective analogue of 'next' version if n == -1 (which means start == 0). This patch replaces 'next' with 'first' where things look trivial. There's no cpumask_first_zero() function, so create it. Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- block/blk-mq.c | 2 +- drivers/net/virtio_net.c | 2 +- drivers/soc/fsl/qbman/bman_portal.c | 2 +- drivers/soc/fsl/qbman/qman_portal.c | 2 +- include/linux/cpumask.h | 16 ++++++++++++++++ kernel/time/clocksource.c | 4 ++-- 6 files changed, 22 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index 8874a63ae952..ef56e753ab38 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2967,7 +2967,7 @@ static bool blk_mq_hctx_has_requests(struct blk_mq_hw_ctx *hctx) static inline bool blk_mq_last_cpu_in_hctx(unsigned int cpu, struct blk_mq_hw_ctx *hctx) { - if (cpumask_next_and(-1, hctx->cpumask, cpu_online_mask) != cpu) + if (cpumask_first_and(hctx->cpumask, cpu_online_mask) != cpu) return false; if (cpumask_next_and(cpu, hctx->cpumask, cpu_online_mask) < nr_cpu_ids) return false; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b107835242ad..8c70ab3c436a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2101,7 +2101,7 @@ static void virtnet_set_affinity(struct virtnet_info *vi) stragglers = num_cpu >= vi->curr_queue_pairs ? num_cpu % vi->curr_queue_pairs : 0; - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); for (i = 0; i < vi->curr_queue_pairs; i++) { group_size = stride + (i < stragglers ? 1 : 0); diff --git a/drivers/soc/fsl/qbman/bman_portal.c b/drivers/soc/fsl/qbman/bman_portal.c index acda8a5637c5..4d7b9caee1c4 100644 --- a/drivers/soc/fsl/qbman/bman_portal.c +++ b/drivers/soc/fsl/qbman/bman_portal.c @@ -155,7 +155,7 @@ static int bman_portal_probe(struct platform_device *pdev) } spin_lock(&bman_lock); - cpu = cpumask_next_zero(-1, &portal_cpus); + cpu = cpumask_first_zero(&portal_cpus); if (cpu >= nr_cpu_ids) { __bman_portals_probed = 1; /* unassigned portal, skip init */ diff --git a/drivers/soc/fsl/qbman/qman_portal.c b/drivers/soc/fsl/qbman/qman_portal.c index 96f74a1dc603..e23b60618c1a 100644 --- a/drivers/soc/fsl/qbman/qman_portal.c +++ b/drivers/soc/fsl/qbman/qman_portal.c @@ -248,7 +248,7 @@ static int qman_portal_probe(struct platform_device *pdev) pcfg->pools = qm_get_pools_sdqcr(); spin_lock(&qman_lock); - cpu = cpumask_next_zero(-1, &portal_cpus); + cpu = cpumask_first_zero(&portal_cpus); if (cpu >= nr_cpu_ids) { __qman_portals_probed = 1; /* unassigned portal, skip init */ diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index c4e1b9ea0ba4..64dae70d31f5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -123,6 +123,11 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return 0; } +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +{ + return 0; +} + static inline unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2) { @@ -201,6 +206,17 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp) return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } +/** + * cpumask_first_zero - get the first unset cpu in a cpumask + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if all cpus are set. + */ +static inline unsigned int cpumask_first_zero(const struct cpumask *srcp) +{ + return find_first_zero_bit(cpumask_bits(srcp), nr_cpumask_bits); +} + /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @src1p: the first input diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index b8a14d2fb5ba..f29d1a524fa5 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -257,7 +257,7 @@ static void clocksource_verify_choose_cpus(void) return; /* Make sure to select at least one CPU other than the current CPU. */ - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); if (cpu == smp_processor_id()) cpu = cpumask_next(cpu, cpu_online_mask); if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) @@ -279,7 +279,7 @@ static void clocksource_verify_choose_cpus(void) cpu = prandom_u32() % nr_cpu_ids; cpu = cpumask_next(cpu - 1, cpu_online_mask); if (cpu >= nr_cpu_ids) - cpu = cpumask_next(-1, cpu_online_mask); + cpu = cpumask_first(cpu_online_mask); if (!WARN_ON_ONCE(cpu >= nr_cpu_ids)) cpumask_set_cpu(cpu, &cpus_chosen); } -- cgit v1.2.3 From bc9d6635c293a2ac30c6319f7cfd08860ab7948a Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:06 -0700 Subject: include/linux: move for_each_bit() macros from bitops.h to find.h for_each_bit() macros depend on find_bit() machinery, and so the proper place for them is the find.h header. Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- include/linux/bitops.h | 34 ---------------------------------- include/linux/find.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 5e62e2383b7f..7aaed501f768 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -32,40 +32,6 @@ extern unsigned long __sw_hweight64(__u64 w); */ #include -#define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -/* same as for_each_set_bit() but use bit as value to start with */ -#define for_each_set_bit_from(bit, addr, size) \ - for ((bit) = find_next_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_bit((addr), (size), (bit) + 1)) - -#define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_first_zero_bit((addr), (size)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) - -/* same as for_each_clear_bit() but use bit as value to start with */ -#define for_each_clear_bit_from(bit, addr, size) \ - for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ - (bit) < (size); \ - (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) - -/** - * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits - * @start: bit offset to start search and to store the current iteration offset - * @clump: location to store copy of current 8-bit clump - * @bits: bitmap address to base the search on - * @size: bitmap size in number of bits - */ -#define for_each_set_clump8(start, clump, bits, size) \ - for ((start) = find_first_clump8(&(clump), (bits), (size)); \ - (start) < (size); \ - (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) - static inline int get_bitmask_order(unsigned int count) { int order; diff --git a/include/linux/find.h b/include/linux/find.h index 6048f8c97418..4500e8ab93e2 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -279,4 +279,38 @@ unsigned long find_next_bit_le(const void *addr, unsigned #error "Please fix " #endif +#define for_each_set_bit(bit, addr, size) \ + for ((bit) = find_first_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +/* same as for_each_set_bit() but use bit as value to start with */ +#define for_each_set_bit_from(bit, addr, size) \ + for ((bit) = find_next_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_bit((addr), (size), (bit) + 1)) + +#define for_each_clear_bit(bit, addr, size) \ + for ((bit) = find_first_zero_bit((addr), (size)); \ + (bit) < (size); \ + (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + +/* same as for_each_clear_bit() but use bit as value to start with */ +#define for_each_clear_bit_from(bit, addr, size) \ + for ((bit) = find_next_zero_bit((addr), (size), (bit)); \ + (bit) < (size); \ + (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) + +/** + * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits + * @start: bit offset to start search and to store the current iteration offset + * @clump: location to store copy of current 8-bit clump + * @bits: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_clump8(start, clump, bits, size) \ + for ((start) = find_first_clump8(&(clump), (bits), (size)); \ + (start) < (size); \ + (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8)) + #endif /*__LINUX_FIND_H_ */ -- cgit v1.2.3 From 7516be9931b8bc8bcaac8531f490b42ab11ded1e Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:07 -0700 Subject: find: micro-optimize for_each_{set,clear}_bit() The macros iterate thru all set/clear bits in a bitmap. They search a first bit using find_first_bit(), and the rest bits using find_next_bit(). Since find_next_bit() is called shortly after find_first_bit(), we can save few lines of I-cache by not using find_first_bit(). Signed-off-by: Yury Norov Tested-by: Wolfram Sang --- include/linux/find.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/find.h b/include/linux/find.h index 4500e8ab93e2..ae9ed52b52b8 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -280,7 +280,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned #endif #define for_each_set_bit(bit, addr, size) \ - for ((bit) = find_first_bit((addr), (size)); \ + for ((bit) = find_next_bit((addr), (size), 0); \ (bit) < (size); \ (bit) = find_next_bit((addr), (size), (bit) + 1)) @@ -291,7 +291,7 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) = find_next_bit((addr), (size), (bit) + 1)) #define for_each_clear_bit(bit, addr, size) \ - for ((bit) = find_first_zero_bit((addr), (size)); \ + for ((bit) = find_next_zero_bit((addr), (size), 0); \ (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) -- cgit v1.2.3 From ec288a2cf7ca40a939316b6df206ab845bb112d1 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 14 Aug 2021 14:17:11 -0700 Subject: bitmap: unify find_bit operations bitmap_for_each_{set,clear}_region() are similar to for_each_bit() macros in include/linux/find.h, but interface and implementation of them are different. This patch adds for_each_bitrange() macros and drops unused bitmap_*_region() API in sake of unification. Signed-off-by: Yury Norov Tested-by: Wolfram Sang Acked-by: Dennis Zhou Acked-by: Ulf Hansson # For MMC --- drivers/mmc/host/renesas_sdhi_core.c | 2 +- include/linux/bitmap.h | 33 --------------------- include/linux/find.h | 56 ++++++++++++++++++++++++++++++++++++ mm/percpu.c | 20 ++++++------- 4 files changed, 65 insertions(+), 46 deletions(-) (limited to 'include/linux') diff --git a/drivers/mmc/host/renesas_sdhi_core.c b/drivers/mmc/host/renesas_sdhi_core.c index f5b2684ad805..6de30a2719a3 100644 --- a/drivers/mmc/host/renesas_sdhi_core.c +++ b/drivers/mmc/host/renesas_sdhi_core.c @@ -628,7 +628,7 @@ static int renesas_sdhi_select_tuning(struct tmio_mmc_host *host) * is at least SH_MOBILE_SDHI_MIN_TAP_ROW probes long then use the * center index as the tap, otherwise bail out. */ - bitmap_for_each_set_region(bitmap, rs, re, 0, taps_size) { + for_each_set_bitrange(rs, re, bitmap, taps_size) { if (re - rs > tap_cnt) { tap_end = re; tap_start = rs; diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index ead4a150bd7f..7dba0847510c 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -55,12 +55,6 @@ struct device; * bitmap_clear(dst, pos, nbits) Clear specified bit area * bitmap_find_next_zero_area(buf, len, pos, n, mask) Find bit free area * bitmap_find_next_zero_area_off(buf, len, pos, n, mask, mask_off) as above - * bitmap_next_clear_region(map, &start, &end, nbits) Find next clear region - * bitmap_next_set_region(map, &start, &end, nbits) Find next set region - * bitmap_for_each_clear_region(map, rs, re, start, end) - * Iterate over all clear regions - * bitmap_for_each_set_region(map, rs, re, start, end) - * Iterate over all set regions * bitmap_shift_right(dst, src, n, nbits) *dst = *src >> n * bitmap_shift_left(dst, src, n, nbits) *dst = *src << n * bitmap_cut(dst, src, first, n, nbits) Cut n bits from first, copy rest @@ -467,14 +461,6 @@ static inline void bitmap_replace(unsigned long *dst, __bitmap_replace(dst, old, new, mask, nbits); } -static inline void bitmap_next_clear_region(unsigned long *bitmap, - unsigned int *rs, unsigned int *re, - unsigned int end) -{ - *rs = find_next_zero_bit(bitmap, end, *rs); - *re = find_next_bit(bitmap, end, *rs + 1); -} - static inline void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs, unsigned int *re, unsigned int end) @@ -483,25 +469,6 @@ static inline void bitmap_next_set_region(unsigned long *bitmap, *re = find_next_zero_bit(bitmap, end, *rs + 1); } -/* - * Bitmap region iterators. Iterates over the bitmap between [@start, @end). - * @rs and @re should be integer variables and will be set to start and end - * index of the current clear or set region. - */ -#define bitmap_for_each_clear_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_clear_region((bitmap), &(rs), &(re), (end))) - -#define bitmap_for_each_set_region(bitmap, rs, re, start, end) \ - for ((rs) = (start), \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end)); \ - (rs) < (re); \ - (rs) = (re) + 1, \ - bitmap_next_set_region((bitmap), &(rs), &(re), (end))) - /** * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap. * @n: u64 value diff --git a/include/linux/find.h b/include/linux/find.h index ae9ed52b52b8..5bb6db213bcb 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -301,6 +301,62 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) < (size); \ (bit) = find_next_zero_bit((addr), (size), (bit) + 1)) +/** + * for_each_set_bitrange - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit) + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange(b, e, addr, size) \ + for ((b) = find_next_bit((addr), (size), 0), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_bit((addr), (size), (e) + 1), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1)) + +/** + * for_each_set_bitrange_from - iterate over all set bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_set_bitrange_from(b, e, addr, size) \ + for ((b) = find_next_bit((addr), (size), (b)), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_bit((addr), (size), (e) + 1), \ + (e) = find_next_zero_bit((addr), (size), (b) + 1)) + +/** + * for_each_clear_bitrange - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first unset bit) + * @e: bit offset of end of current bitrange (first set bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange(b, e, addr, size) \ + for ((b) = find_next_zero_bit((addr), (size), 0), \ + (e) = find_next_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_zero_bit((addr), (size), (e) + 1), \ + (e) = find_next_bit((addr), (size), (b) + 1)) + +/** + * for_each_clear_bitrange_from - iterate over all unset bit ranges [b; e) + * @b: bit offset of start of current bitrange (first set bit); must be initialized + * @e: bit offset of end of current bitrange (first unset bit) + * @addr: bitmap address to base the search on + * @size: bitmap size in number of bits + */ +#define for_each_clear_bitrange_from(b, e, addr, size) \ + for ((b) = find_next_zero_bit((addr), (size), (b)), \ + (e) = find_next_bit((addr), (size), (b) + 1); \ + (b) < (size); \ + (b) = find_next_zero_bit((addr), (size), (e) + 1), \ + (e) = find_next_bit((addr), (size), (b) + 1)) + /** * for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits * @start: bit offset to start search and to store the current iteration offset diff --git a/mm/percpu.c b/mm/percpu.c index 0c6f85c5514f..293009cc03ef 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -779,7 +779,7 @@ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) { struct pcpu_block_md *block = chunk->md_blocks + index; unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index); - unsigned int rs, re, start; /* region start, region end */ + unsigned int start, end; /* region start, region end */ /* promote scan_hint to contig_hint */ if (block->scan_hint) { @@ -795,9 +795,8 @@ static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index) block->right_free = 0; /* iterate over free areas and update the contig hints */ - bitmap_for_each_clear_region(alloc_map, rs, re, start, - PCPU_BITMAP_BLOCK_BITS) - pcpu_block_update(block, rs, re); + for_each_clear_bitrange_from(start, end, alloc_map, PCPU_BITMAP_BLOCK_BITS) + pcpu_block_update(block, start, end); } /** @@ -1852,13 +1851,12 @@ area_found: /* populate if not all pages are already there */ if (!is_atomic) { - unsigned int page_start, page_end, rs, re; + unsigned int page_end, rs, re; - page_start = PFN_DOWN(off); + rs = PFN_DOWN(off); page_end = PFN_UP(off + size); - bitmap_for_each_clear_region(chunk->populated, rs, re, - page_start, page_end) { + for_each_clear_bitrange_from(rs, re, chunk->populated, page_end) { WARN_ON(chunk->immutable); ret = pcpu_populate_chunk(chunk, rs, re, pcpu_gfp); @@ -2014,8 +2012,7 @@ static void pcpu_balance_free(bool empty_only) list_for_each_entry_safe(chunk, next, &to_free, list) { unsigned int rs, re; - bitmap_for_each_set_region(chunk->populated, rs, re, 0, - chunk->nr_pages) { + for_each_set_bitrange(rs, re, chunk->populated, chunk->nr_pages) { pcpu_depopulate_chunk(chunk, rs, re); spin_lock_irq(&pcpu_lock); pcpu_chunk_depopulated(chunk, rs, re); @@ -2085,8 +2082,7 @@ retry_pop: continue; /* @chunk can't go away while pcpu_alloc_mutex is held */ - bitmap_for_each_clear_region(chunk->populated, rs, re, 0, - chunk->nr_pages) { + for_each_clear_bitrange(rs, re, chunk->populated, chunk->nr_pages) { int nr = min_t(int, re - rs, nr_to_pop); spin_unlock_irq(&pcpu_lock); -- cgit v1.2.3 From 7372971c1be5b7d4fdd8ad237798bdc1d1d54162 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 11 Jan 2022 10:19:22 +0300 Subject: rtc: mc146818-lib: fix signedness bug in mc146818_get_time() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The mc146818_get_time() function returns zero on success or negative a error code on failure. It needs to be type int. Fixes: d35786b3a28d ("rtc: mc146818-lib: change return values of mc146818_get_time()") Signed-off-by: Dan Carpenter Reviewed-by: Mateusz Jończyk Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20220111071922.GE11243@kili --- drivers/rtc/rtc-mc146818-lib.c | 2 +- include/linux/mc146818rtc.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/rtc/rtc-mc146818-lib.c b/drivers/rtc/rtc-mc146818-lib.c index f62e658cbe23..7f689f1bafc5 100644 --- a/drivers/rtc/rtc-mc146818-lib.c +++ b/drivers/rtc/rtc-mc146818-lib.c @@ -130,7 +130,7 @@ static void mc146818_get_time_callback(unsigned char seconds, void *param_in) p->ctrl = CMOS_READ(RTC_CONTROL); } -unsigned int mc146818_get_time(struct rtc_time *time) +int mc146818_get_time(struct rtc_time *time) { struct mc146818_get_time_callback_param p = { .time = time diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h index 67fb0a12becc..808bb4cee230 100644 --- a/include/linux/mc146818rtc.h +++ b/include/linux/mc146818rtc.h @@ -124,7 +124,7 @@ struct cmos_rtc_board_info { #endif /* ARCH_RTC_LOCATION */ bool mc146818_does_rtc_work(void); -unsigned int mc146818_get_time(struct rtc_time *time); +int mc146818_get_time(struct rtc_time *time); int mc146818_set_time(struct rtc_time *time); bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param), -- cgit v1.2.3 From 3fe7fa5843d204e235d92902190fecb972a3f9cc Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 10 Dec 2021 15:09:21 -0500 Subject: mm: Add folio_put_refs() This is like folio_put(), but puts N references at once instead of just one. It's like put_page_refs(), but does one atomic operation instead of two, and is available to more than just gup.c. Signed-off-by: Matthew Wilcox (Oracle) Reviewed-by: Christoph Hellwig Reviewed-by: John Hubbard Reviewed-by: Jason Gunthorpe Reviewed-by: William Kucharski --- include/linux/mm.h | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index c768a7c81b0b..cb98f75b245e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1244,6 +1244,26 @@ static inline void folio_put(struct folio *folio) __put_page(&folio->page); } +/** + * folio_put_refs - Reduce the reference count on a folio. + * @folio: The folio. + * @refs: The amount to subtract from the folio's reference count. + * + * If the folio's reference count reaches zero, the memory will be + * released back to the page allocator and may be used by another + * allocation immediately. Do not access the memory or the struct folio + * after calling folio_put_refs() unless you can be sure that these weren't + * the last references. + * + * Context: May be called in process or interrupt context, but not in NMI + * context. May be called while holding a spinlock. + */ +static inline void folio_put_refs(struct folio *folio, int refs) +{ + if (folio_ref_sub_and_test(folio, refs)) + __put_page(&folio->page); +} + static inline void put_page(struct page *page) { struct folio *folio = page_folio(page); -- cgit v1.2.3 From a6097180d884ddab769fb25588ea8598589c218c Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 17 Jan 2022 09:07:26 +1100 Subject: devtmpfs regression fix: reconfigure on each mount Prior to Linux v5.4 devtmpfs used mount_single() which treats the given mount options as "remount" options, so it updates the configuration of the single super_block on each mount. Since that was changed, the mount options used for devtmpfs are ignored. This is a regression which affect systemd - which mounts devtmpfs with "-o mode=755,size=4m,nr_inodes=1m". This patch restores the "remount" effect by calling reconfigure_single() Fixes: d401727ea0d7 ("devtmpfs: don't mix {ramfs,shmem}_fill_super() with mount_single()") Acked-by: Christian Brauner Cc: Al Viro Signed-off-by: NeilBrown Signed-off-by: Linus Torvalds --- drivers/base/devtmpfs.c | 7 +++++++ fs/super.c | 4 ++-- include/linux/fs_context.h | 2 ++ 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/devtmpfs.c b/drivers/base/devtmpfs.c index 1e2c2d3882e2..f41063ac1aee 100644 --- a/drivers/base/devtmpfs.c +++ b/drivers/base/devtmpfs.c @@ -65,8 +65,15 @@ static struct dentry *public_dev_mount(struct file_system_type *fs_type, int fla const char *dev_name, void *data) { struct super_block *s = mnt->mnt_sb; + int err; + atomic_inc(&s->s_active); down_write(&s->s_umount); + err = reconfigure_single(s, flags, data); + if (err < 0) { + deactivate_locked_super(s); + return ERR_PTR(err); + } return dget(s->s_root); } diff --git a/fs/super.c b/fs/super.c index 3bfc0f8fbd5b..a6405d44d4ca 100644 --- a/fs/super.c +++ b/fs/super.c @@ -1423,8 +1423,8 @@ struct dentry *mount_nodev(struct file_system_type *fs_type, } EXPORT_SYMBOL(mount_nodev); -static int reconfigure_single(struct super_block *s, - int flags, void *data) +int reconfigure_single(struct super_block *s, + int flags, void *data) { struct fs_context *fc; int ret; diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 6b54982fc5f3..13fa6f3df8e4 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -142,6 +142,8 @@ extern void put_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param); extern void fc_drop_locked(struct fs_context *fc); +int reconfigure_single(struct super_block *s, + int flags, void *data); /* * sget() wrappers to be called from the ->get_tree() op. -- cgit v1.2.3 From 09f5e7dc7ad705289e1b1ec065439aa3c42951c4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 20 Dec 2021 13:19:52 +0100 Subject: perf: Fix perf_event_read_local() time Time readers that cannot take locks (due to NMI etc..) currently make use of perf_event::shadow_ctx_time, which, for that event gives: time' = now + (time - timestamp) or, alternatively arranged: time' = time + (now - timestamp) IOW, the progression of time since the last time the shadow_ctx_time was updated. There's problems with this: A) the shadow_ctx_time is per-event, even though the ctx_time it reflects is obviously per context. The direct concequence of this is that the context needs to iterate all events all the time to keep the shadow_ctx_time in sync. B) even with the prior point, the context itself might not be active meaning its time should not advance to begin with. C) shadow_ctx_time isn't consistently updated when ctx_time is There are 3 users of this stuff, that suffer differently from this: - calc_timer_values() - perf_output_read() - perf_event_update_userpage() /* A */ - perf_event_read_local() /* A,B */ In particular, perf_output_read() doesn't suffer at all, because it's sample driven and hence only relevant when the event is actually running. This same was supposed to be true for perf_event_update_userpage(), after all self-monitoring implies the context is active *HOWEVER*, as per commit f79256532682 ("perf/core: fix userpage->time_enabled of inactive events") this goes wrong when combined with counter overcommit, in that case those events that do not get scheduled when the context becomes active (task events typically) miss out on the EVENT_TIME update and ENABLED time is inflated (for a little while) with the time the context was inactive. Once the event gets rotated in, this gets corrected, leading to a non-monotonic timeflow. perf_event_read_local() made things even worse, it can request time at any point, suffering all the problems perf_event_update_userpage() does and more. Because while perf_event_update_userpage() is limited by the context being active, perf_event_read_local() users have no such constraint. Therefore, completely overhaul things and do away with perf_event::shadow_ctx_time. Instead have regular context time updates keep track of this offset directly and provide perf_event_time_now() to complement perf_event_time(). perf_event_time_now() will, in adition to being context wide, also take into account if the context is active. For inactive context, it will not advance time. This latter property means the cgroup perf_cgroup_info context needs to grow addition state to track this. Additionally, since all this is strictly per-cpu, we can use barrier() to order context activity vs context time. Fixes: 7d9285e82db5 ("perf/bpf: Extend the perf_event_read_local() interface, a.k.a. "bpf: perf event change needed for subsequent bpf helpers"") Signed-off-by: Peter Zijlstra (Intel) Tested-by: Song Liu Tested-by: Namhyung Kim Link: https://lkml.kernel.org/r/YcB06DasOBtU0b00@hirez.programming.kicks-ass.net --- include/linux/perf_event.h | 15 +-- kernel/events/core.c | 246 +++++++++++++++++++++++++++------------------ 2 files changed, 149 insertions(+), 112 deletions(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 117f230bcdfd..733649184b27 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -693,18 +693,6 @@ struct perf_event { u64 total_time_running; u64 tstamp; - /* - * timestamp shadows the actual context timing but it can - * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in, - * or when ctx_sched_in failed to schedule the event because we - * run out of PMC. - * - * ctx_time already accounts for ctx->timestamp. Therefore to - * compute ctx_time for a sample, simply add perf_clock(). - */ - u64 shadow_ctx_time; - struct perf_event_attr attr; u16 header_size; u16 id_header_size; @@ -852,6 +840,7 @@ struct perf_event_context { */ u64 time; u64 timestamp; + u64 timeoffset; /* * These fields let us detect when two contexts have both @@ -934,6 +923,8 @@ struct bpf_perf_event_data_kern { struct perf_cgroup_info { u64 time; u64 timestamp; + u64 timeoffset; + int active; }; struct perf_cgroup { diff --git a/kernel/events/core.c b/kernel/events/core.c index fc18664f49b0..479c9e672ec4 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -674,6 +674,23 @@ perf_event_set_state(struct perf_event *event, enum perf_event_state state) WRITE_ONCE(event->state, state); } +/* + * UP store-release, load-acquire + */ + +#define __store_release(ptr, val) \ +do { \ + barrier(); \ + WRITE_ONCE(*(ptr), (val)); \ +} while (0) + +#define __load_acquire(ptr) \ +({ \ + __unqual_scalar_typeof(*(ptr)) ___p = READ_ONCE(*(ptr)); \ + barrier(); \ + ___p; \ +}) + #ifdef CONFIG_CGROUP_PERF static inline bool @@ -719,34 +736,51 @@ static inline u64 perf_cgroup_event_time(struct perf_event *event) return t->time; } -static inline void __update_cgrp_time(struct perf_cgroup *cgrp) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { - struct perf_cgroup_info *info; - u64 now; - - now = perf_clock(); + struct perf_cgroup_info *t; - info = this_cpu_ptr(cgrp->info); + t = per_cpu_ptr(event->cgrp->info, event->cpu); + if (!__load_acquire(&t->active)) + return t->time; + now += READ_ONCE(t->timeoffset); + return now; +} - info->time += now - info->timestamp; +static inline void __update_cgrp_time(struct perf_cgroup_info *info, u64 now, bool adv) +{ + if (adv) + info->time += now - info->timestamp; info->timestamp = now; + /* + * see update_context_time() + */ + WRITE_ONCE(info->timeoffset, info->time - info->timestamp); } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, bool final) { struct perf_cgroup *cgrp = cpuctx->cgrp; struct cgroup_subsys_state *css; + struct perf_cgroup_info *info; if (cgrp) { + u64 now = perf_clock(); + for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); - __update_cgrp_time(cgrp); + info = this_cpu_ptr(cgrp->info); + + __update_cgrp_time(info, now, true); + if (final) + __store_release(&info->active, 0); } } } static inline void update_cgrp_time_from_event(struct perf_event *event) { + struct perf_cgroup_info *info; struct perf_cgroup *cgrp; /* @@ -760,8 +794,10 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) /* * Do not update time when cgroup is not active */ - if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) - __update_cgrp_time(event->cgrp); + if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) { + info = this_cpu_ptr(event->cgrp->info); + __update_cgrp_time(info, perf_clock(), true); + } } static inline void @@ -785,7 +821,8 @@ perf_cgroup_set_timestamp(struct task_struct *task, for (css = &cgrp->css; css; css = css->parent) { cgrp = container_of(css, struct perf_cgroup, css); info = this_cpu_ptr(cgrp->info); - info->timestamp = ctx->timestamp; + __update_cgrp_time(info, ctx->timestamp, false); + __store_release(&info->active, 1); } } @@ -981,14 +1018,6 @@ out: return ret; } -static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) -{ - struct perf_cgroup_info *t; - t = per_cpu_ptr(event->cgrp->info, event->cpu); - event->shadow_ctx_time = now - t->timestamp; -} - static inline void perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ctx) { @@ -1066,7 +1095,8 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) { } -static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx) +static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx, + bool final) { } @@ -1098,12 +1128,12 @@ perf_cgroup_switch(struct task_struct *task, struct task_struct *next) { } -static inline void -perf_cgroup_set_shadow_time(struct perf_event *event, u64 now) +static inline u64 perf_cgroup_event_time(struct perf_event *event) { + return 0; } -static inline u64 perf_cgroup_event_time(struct perf_event *event) +static inline u64 perf_cgroup_event_time_now(struct perf_event *event, u64 now) { return 0; } @@ -1525,22 +1555,59 @@ static void perf_unpin_context(struct perf_event_context *ctx) /* * Update the record of the current time in a context. */ -static void update_context_time(struct perf_event_context *ctx) +static void __update_context_time(struct perf_event_context *ctx, bool adv) { u64 now = perf_clock(); - ctx->time += now - ctx->timestamp; + if (adv) + ctx->time += now - ctx->timestamp; ctx->timestamp = now; + + /* + * The above: time' = time + (now - timestamp), can be re-arranged + * into: time` = now + (time - timestamp), which gives a single value + * offset to compute future time without locks on. + * + * See perf_event_time_now(), which can be used from NMI context where + * it's (obviously) not possible to acquire ctx->lock in order to read + * both the above values in a consistent manner. + */ + WRITE_ONCE(ctx->timeoffset, ctx->time - ctx->timestamp); +} + +static void update_context_time(struct perf_event_context *ctx) +{ + __update_context_time(ctx, true); } static u64 perf_event_time(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; + if (unlikely(!ctx)) + return 0; + if (is_cgroup_event(event)) return perf_cgroup_event_time(event); - return ctx ? ctx->time : 0; + return ctx->time; +} + +static u64 perf_event_time_now(struct perf_event *event, u64 now) +{ + struct perf_event_context *ctx = event->ctx; + + if (unlikely(!ctx)) + return 0; + + if (is_cgroup_event(event)) + return perf_cgroup_event_time_now(event, now); + + if (!(__load_acquire(&ctx->is_active) & EVENT_TIME)) + return ctx->time; + + now += READ_ONCE(ctx->timeoffset); + return now; } static enum event_type_t get_event_type(struct perf_event *event) @@ -2350,7 +2417,7 @@ __perf_remove_from_context(struct perf_event *event, if (ctx->is_active & EVENT_TIME) { update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, false); } event_sched_out(event, cpuctx, ctx); @@ -2361,6 +2428,9 @@ __perf_remove_from_context(struct perf_event *event, list_del_event(event, ctx); if (!ctx->nr_events && ctx->is_active) { + if (ctx == &cpuctx->ctx) + update_cgrp_time_from_cpuctx(cpuctx, true); + ctx->is_active = 0; ctx->rotate_necessary = 0; if (ctx->task) { @@ -2482,40 +2552,6 @@ void perf_event_disable_inatomic(struct perf_event *event) irq_work_queue(&event->pending); } -static void perf_set_shadow_time(struct perf_event *event, - struct perf_event_context *ctx) -{ - /* - * use the correct time source for the time snapshot - * - * We could get by without this by leveraging the - * fact that to get to this function, the caller - * has most likely already called update_context_time() - * and update_cgrp_time_xx() and thus both timestamp - * are identical (or very close). Given that tstamp is, - * already adjusted for cgroup, we could say that: - * tstamp - ctx->timestamp - * is equivalent to - * tstamp - cgrp->timestamp. - * - * Then, in perf_output_read(), the calculation would - * work with no changes because: - * - event is guaranteed scheduled in - * - no scheduled out in between - * - thus the timestamp would be the same - * - * But this is a bit hairy. - * - * So instead, we have an explicit cgroup call to remain - * within the time source all along. We believe it - * is cleaner and simpler to understand. - */ - if (is_cgroup_event(event)) - perf_cgroup_set_shadow_time(event, event->tstamp); - else - event->shadow_ctx_time = event->tstamp - ctx->timestamp; -} - #define MAX_INTERRUPTS (~0ULL) static void perf_log_throttle(struct perf_event *event, int enable); @@ -2556,8 +2592,6 @@ event_sched_in(struct perf_event *event, perf_pmu_disable(event->pmu); - perf_set_shadow_time(event, ctx); - perf_log_itrace_start(event); if (event->pmu->add(event, PERF_EF_START)) { @@ -3251,16 +3285,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, return; } - ctx->is_active &= ~event_type; - if (!(ctx->is_active & EVENT_ALL)) - ctx->is_active = 0; - - if (ctx->task) { - WARN_ON_ONCE(cpuctx->task_ctx != ctx); - if (!ctx->is_active) - cpuctx->task_ctx = NULL; - } - /* * Always update time if it was set; not only when it changes. * Otherwise we can 'forget' to update time for any but the last @@ -3274,7 +3298,22 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_TIME) { /* update (and stop) ctx time */ update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); + update_cgrp_time_from_cpuctx(cpuctx, ctx == &cpuctx->ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + + ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; } is_active ^= ctx->is_active; /* changed bits */ @@ -3711,13 +3750,19 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +/* + * Because the userpage is strictly per-event (there is no concept of context, + * so there cannot be a context indirection), every userpage must be updated + * when context time starts :-( + * + * IOW, we must not miss EVENT_TIME edges. + */ static inline bool event_update_userpage(struct perf_event *event) { if (likely(!atomic_read(&event->mmap_count))) return false; perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_update_userpage(event); return true; @@ -3801,13 +3846,23 @@ ctx_sched_in(struct perf_event_context *ctx, struct task_struct *task) { int is_active = ctx->is_active; - u64 now; lockdep_assert_held(&ctx->lock); if (likely(!ctx->nr_events)) return; + if (is_active ^ EVENT_TIME) { + /* start ctx time */ + __update_context_time(ctx, false); + perf_cgroup_set_timestamp(task, ctx); + /* + * CPU-release for the below ->is_active store, + * see __load_acquire() in perf_event_time_now() + */ + barrier(); + } + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) @@ -3818,13 +3873,6 @@ ctx_sched_in(struct perf_event_context *ctx, is_active ^= ctx->is_active; /* changed bits */ - if (is_active & EVENT_TIME) { - /* start ctx time */ - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); - } - /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. @@ -4418,6 +4466,18 @@ static inline u64 perf_event_count(struct perf_event *event) return local64_read(&event->count) + atomic64_read(&event->child_count); } +static void calc_timer_values(struct perf_event *event, + u64 *now, + u64 *enabled, + u64 *running) +{ + u64 ctx_time; + + *now = perf_clock(); + ctx_time = perf_event_time_now(event, *now); + __perf_update_times(event, ctx_time, enabled, running); +} + /* * NMI-safe method to read a local event, that is an event that * is: @@ -4477,10 +4537,9 @@ int perf_event_read_local(struct perf_event *event, u64 *value, *value = local64_read(&event->count); if (enabled || running) { - u64 now = event->shadow_ctx_time + perf_clock(); - u64 __enabled, __running; + u64 __enabled, __running, __now;; - __perf_update_times(event, now, &__enabled, &__running); + calc_timer_values(event, &__now, &__enabled, &__running); if (enabled) *enabled = __enabled; if (running) @@ -5802,18 +5861,6 @@ static int perf_event_index(struct perf_event *event) return event->pmu->event_idx(event); } -static void calc_timer_values(struct perf_event *event, - u64 *now, - u64 *enabled, - u64 *running) -{ - u64 ctx_time; - - *now = perf_clock(); - ctx_time = event->shadow_ctx_time + *now; - __perf_update_times(event, ctx_time, enabled, running); -} - static void perf_event_init_userpage(struct perf_event *event) { struct perf_event_mmap_page *userpg; @@ -6353,7 +6400,6 @@ accounting: ring_buffer_attach(event, rb); perf_event_update_time(event); - perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { -- cgit v1.2.3 From a06247c6804f1a7c86a2e5398a4c1f1db1471848 Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Tue, 11 Jan 2022 15:23:09 -0800 Subject: psi: Fix uaf issue when psi trigger is destroyed while being polled With write operation on psi files replacing old trigger with a new one, the lifetime of its waitqueue is totally arbitrary. Overwriting an existing trigger causes its waitqueue to be freed and pending poll() will stumble on trigger->event_wait which was destroyed. Fix this by disallowing to redefine an existing psi trigger. If a write operation is used on a file descriptor with an already existing psi trigger, the operation will fail with EBUSY error. Also bypass a check for psi_disabled in the psi_trigger_destroy as the flag can be flipped after the trigger is created, leading to a memory leak. Fixes: 0e94682b73bf ("psi: introduce psi monitor") Reported-by: syzbot+cdb5dd11c97cc532efad@syzkaller.appspotmail.com Suggested-by: Linus Torvalds Analyzed-by: Eric Biggers Signed-off-by: Suren Baghdasaryan Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Eric Biggers Acked-by: Johannes Weiner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220111232309.1786347-1-surenb@google.com --- Documentation/accounting/psi.rst | 3 +- include/linux/psi.h | 2 +- include/linux/psi_types.h | 3 -- kernel/cgroup/cgroup.c | 11 +++++-- kernel/sched/psi.c | 66 ++++++++++++++++++---------------------- 5 files changed, 40 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/Documentation/accounting/psi.rst b/Documentation/accounting/psi.rst index f2b3439edcc2..860fe651d645 100644 --- a/Documentation/accounting/psi.rst +++ b/Documentation/accounting/psi.rst @@ -92,7 +92,8 @@ Triggers can be set on more than one psi metric and more than one trigger for the same psi metric can be specified. However for each trigger a separate file descriptor is required to be able to poll it separately from others, therefore for each trigger a separate open() syscall should be made even -when opening the same psi interface file. +when opening the same psi interface file. Write operations to a file descriptor +with an already existing psi trigger will fail with EBUSY. Monitors activate only when system enters stall state for the monitored psi metric and deactivates upon exit from the stall state. While system is diff --git a/include/linux/psi.h b/include/linux/psi.h index a70ca833c6d7..f8ce53bfdb2a 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -33,7 +33,7 @@ void cgroup_move_task(struct task_struct *p, struct css_set *to); struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *t); +void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 516c0fe836fd..1a3cef26d129 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -141,9 +141,6 @@ struct psi_trigger { * events to one per window */ u64 last_event_time; - - /* Refcounting to prevent premature destruction */ - struct kref refcount; }; struct psi_group { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index b31e1465868a..9d05c3ca2d5e 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3643,6 +3643,12 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, cgroup_get(cgrp); cgroup_kn_unlock(of->kn); + /* Allow only one trigger per file descriptor */ + if (ctx->psi.trigger) { + cgroup_put(cgrp); + return -EBUSY; + } + psi = cgroup_ino(cgrp) == 1 ? &psi_system : &cgrp->psi; new = psi_trigger_create(psi, buf, nbytes, res); if (IS_ERR(new)) { @@ -3650,8 +3656,7 @@ static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, return PTR_ERR(new); } - psi_trigger_replace(&ctx->psi.trigger, new); - + smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; @@ -3690,7 +3695,7 @@ static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; - psi_trigger_replace(&ctx->psi.trigger, NULL); + psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index a679613a7cb7..c137c4d6983e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1162,7 +1162,6 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; init_waitqueue_head(&t->event_wait); - kref_init(&t->refcount); mutex_lock(&group->trigger_lock); @@ -1191,15 +1190,19 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, return t; } -static void psi_trigger_destroy(struct kref *ref) +void psi_trigger_destroy(struct psi_trigger *t) { - struct psi_trigger *t = container_of(ref, struct psi_trigger, refcount); - struct psi_group *group = t->group; + struct psi_group *group; struct task_struct *task_to_destroy = NULL; - if (static_branch_likely(&psi_disabled)) + /* + * We do not check psi_disabled since it might have been disabled after + * the trigger got created. + */ + if (!t) return; + group = t->group; /* * Wakeup waiters to stop polling. Can happen if cgroup is deleted * from under a polling process. @@ -1235,9 +1238,9 @@ static void psi_trigger_destroy(struct kref *ref) mutex_unlock(&group->trigger_lock); /* - * Wait for both *trigger_ptr from psi_trigger_replace and - * poll_task RCUs to complete their read-side critical sections - * before destroying the trigger and optionally the poll_task + * Wait for psi_schedule_poll_work RCU to complete its read-side + * critical section before destroying the trigger and optionally the + * poll_task. */ synchronize_rcu(); /* @@ -1254,18 +1257,6 @@ static void psi_trigger_destroy(struct kref *ref) kfree(t); } -void psi_trigger_replace(void **trigger_ptr, struct psi_trigger *new) -{ - struct psi_trigger *old = *trigger_ptr; - - if (static_branch_likely(&psi_disabled)) - return; - - rcu_assign_pointer(*trigger_ptr, new); - if (old) - kref_put(&old->refcount, psi_trigger_destroy); -} - __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait) { @@ -1275,24 +1266,15 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (static_branch_likely(&psi_disabled)) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - rcu_read_lock(); - - t = rcu_dereference(*(void __rcu __force **)trigger_ptr); - if (!t) { - rcu_read_unlock(); + t = smp_load_acquire(trigger_ptr); + if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - } - kref_get(&t->refcount); - - rcu_read_unlock(); poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; - kref_put(&t->refcount, psi_trigger_destroy); - return ret; } @@ -1316,14 +1298,24 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, buf[buf_size - 1] = '\0'; - new = psi_trigger_create(&psi_system, buf, nbytes, res); - if (IS_ERR(new)) - return PTR_ERR(new); - seq = file->private_data; + /* Take seq->lock to protect seq->private from concurrent writes */ mutex_lock(&seq->lock); - psi_trigger_replace(&seq->private, new); + + /* Allow only one trigger per file descriptor */ + if (seq->private) { + mutex_unlock(&seq->lock); + return -EBUSY; + } + + new = psi_trigger_create(&psi_system, buf, nbytes, res); + if (IS_ERR(new)) { + mutex_unlock(&seq->lock); + return PTR_ERR(new); + } + + smp_store_release(&seq->private, new); mutex_unlock(&seq->lock); return nbytes; @@ -1358,7 +1350,7 @@ static int psi_fop_release(struct inode *inode, struct file *file) { struct seq_file *seq = file->private_data; - psi_trigger_replace(&seq->private, NULL); + psi_trigger_destroy(seq->private); return single_release(inode, file); } -- cgit v1.2.3 From 0e3872499de1a1230cef5221607d71aa09264bd5 Mon Sep 17 00:00:00 2001 From: Hui Su Date: Fri, 7 Jan 2022 17:52:54 +0800 Subject: kernel/sched: Remove dl_boosted flag comment since commit 2279f540ea7d ("sched/deadline: Fix priority inheritance with multiple scheduling classes"), we should not keep it here. Signed-off-by: Hui Su Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Daniel Bristot de Oliveira Link: https://lore.kernel.org/r/20220107095254.GA49258@localhost.localdomain --- include/linux/sched.h | 4 ---- 1 file changed, 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 7a1f16df66e3..7f8b4495e243 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -614,10 +614,6 @@ struct sched_dl_entity { * task has to wait for a replenishment to be performed at the * next firing of dl_timer. * - * @dl_boosted tells if we are boosted due to DI. If so we are - * outside bandwidth enforcement mechanism (but only until we - * exit the critical section); - * * @dl_yielded tells if task gave up the CPU before consuming * all its available runtime during the last job. * -- cgit v1.2.3 From be80a1d3f9dbe5aee79a325964f7037fe2d92f30 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 10 Jan 2022 14:05:49 +0000 Subject: bpf: Generalize check_ctx_reg for reuse with other types Generalize the check_ctx_reg() helper function into a more generic named one so that it can be reused for other register types as well to check whether their offset is non-zero. No functional change. Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 4 ++-- kernel/bpf/btf.c | 2 +- kernel/bpf/verifier.c | 21 +++++++++++---------- 3 files changed, 14 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 143401d4c9d9..e9993172f892 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -519,8 +519,8 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off, void bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt); -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno); +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno); int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size); diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 33bb8ae4a804..e16dafeb2450 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5686,7 +5686,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, i, btf_type_str(t)); return -EINVAL; } - if (check_ctx_reg(env, reg, regno)) + if (check_ptr_off_reg(env, reg, regno)) return -EINVAL; } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) { const struct btf_type *reg_ref_t; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a8587210907d..9b8334068e71 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -3969,16 +3969,16 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, } #endif -int check_ctx_reg(struct bpf_verifier_env *env, - const struct bpf_reg_state *reg, int regno) +int check_ptr_off_reg(struct bpf_verifier_env *env, + const struct bpf_reg_state *reg, int regno) { - /* Access to ctx or passing it to a helper is only allowed in - * its original, unmodified form. + /* Access to this pointer-typed register or passing it to a helper + * is only allowed in its original, unmodified form. */ if (reg->off) { - verbose(env, "dereference of modified ctx ptr R%d off=%d disallowed\n", - regno, reg->off); + verbose(env, "dereference of modified %s ptr R%d off=%d disallowed\n", + reg_type_str(env, reg->type), regno, reg->off); return -EACCES; } @@ -3986,7 +3986,8 @@ int check_ctx_reg(struct bpf_verifier_env *env, char tn_buf[48]; tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off); - verbose(env, "variable ctx access var_off=%s disallowed\n", tn_buf); + verbose(env, "variable %s access var_off=%s disallowed\n", + reg_type_str(env, reg->type), tn_buf); return -EACCES; } @@ -4437,7 +4438,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn return -EACCES; } - err = check_ctx_reg(env, reg, regno); + err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; @@ -5305,7 +5306,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, return err; if (type == PTR_TO_CTX) { - err = check_ctx_reg(env, reg, regno); + err = check_ptr_off_reg(env, reg, regno); if (err < 0) return err; } @@ -9651,7 +9652,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } - err = check_ctx_reg(env, ®s[ctx_reg], ctx_reg); + err = check_ptr_off_reg(env, ®s[ctx_reg], ctx_reg); if (err < 0) return err; -- cgit v1.2.3 From a672b2e36a648afb04ad3bda93b6bda947a479a5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 13 Jan 2022 11:11:30 +0000 Subject: bpf: Fix ringbuf memory type confusion when passing to helpers The bpf_ringbuf_submit() and bpf_ringbuf_discard() have ARG_PTR_TO_ALLOC_MEM in their bpf_func_proto definition as their first argument, and thus both expect the result from a prior bpf_ringbuf_reserve() call which has a return type of RET_PTR_TO_ALLOC_MEM_OR_NULL. While the non-NULL memory from bpf_ringbuf_reserve() can be passed to other helpers, the two sinks (bpf_ringbuf_submit(), bpf_ringbuf_discard()) right now only enforce a register type of PTR_TO_MEM. This can lead to potential type confusion since it would allow other PTR_TO_MEM memory to be passed into the two sinks which did not come from bpf_ringbuf_reserve(). Add a new MEM_ALLOC composable type attribute for PTR_TO_MEM, and enforce that: - bpf_ringbuf_reserve() returns NULL or PTR_TO_MEM | MEM_ALLOC - bpf_ringbuf_submit() and bpf_ringbuf_discard() only take PTR_TO_MEM | MEM_ALLOC but not plain PTR_TO_MEM arguments via ARG_PTR_TO_ALLOC_MEM - however, other helpers might treat PTR_TO_MEM | MEM_ALLOC as plain PTR_TO_MEM to populate the memory area when they use ARG_PTR_TO_{UNINIT_,}MEM in their func proto description Fixes: 457f44363a88 ("bpf: Implement BPF ring buffer and verifier support for it") Reported-by: Alexei Starovoitov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Alexei Starovoitov --- include/linux/bpf.h | 9 +++++++-- kernel/bpf/verifier.c | 6 +++++- 2 files changed, 12 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 6e947cd91152..fa517ae604ad 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -316,7 +316,12 @@ enum bpf_type_flag { */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), - __BPF_TYPE_LAST_FLAG = MEM_RDONLY, + /* MEM was "allocated" from a different helper, and cannot be mixed + * with regular non-MEM_ALLOC'ed MEM types. + */ + MEM_ALLOC = BIT(2 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_ALLOC, }; /* Max number of base types. */ @@ -400,7 +405,7 @@ enum bpf_return_type { RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, - RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c72c57a6684f..a39eedecc93a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -570,6 +570,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env, if (type & MEM_RDONLY) strncpy(prefix, "rdonly_", 16); + if (type & MEM_ALLOC) + strncpy(prefix, "alloc_", 16); snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s", prefix, str[base_type(type)], postfix); @@ -5135,6 +5137,7 @@ static const struct bpf_reg_types mem_types = { PTR_TO_MAP_KEY, PTR_TO_MAP_VALUE, PTR_TO_MEM, + PTR_TO_MEM | MEM_ALLOC, PTR_TO_BUF, }, }; @@ -5152,7 +5155,7 @@ static const struct bpf_reg_types int_ptr_types = { static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } }; static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } }; static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } }; -static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } }; +static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM | MEM_ALLOC } }; static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } }; static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } }; static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } }; @@ -5315,6 +5318,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg, case PTR_TO_MAP_VALUE: case PTR_TO_MEM: case PTR_TO_MEM | MEM_RDONLY: + case PTR_TO_MEM | MEM_ALLOC: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: case PTR_TO_STACK: -- cgit v1.2.3 From e6eec09b7bc7869a49ac0ff376415bad40030ade Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 8 Dec 2021 01:52:15 +0000 Subject: KVM: Drop unused kvm_vcpu.pre_pcpu field Remove kvm_vcpu.pre_pcpu as it no longer has any users. No functional change intended. Signed-off-by: Sean Christopherson Reviewed-by: Maxim Levitsky Message-Id: <20211208015236.1616697-6-seanjc@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - virt/kvm/kvm_main.c | 1 - 2 files changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3c47b146851a..5c3c67b6318f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -309,7 +309,6 @@ struct kvm_vcpu { u64 requests; unsigned long guest_debug; - int pre_pcpu; struct list_head blocked_vcpu_list; struct mutex mutex; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index dc6d1823a9d9..c301cd8d583e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -427,7 +427,6 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) #endif kvm_async_pf_vcpu_init(vcpu); - vcpu->pre_pcpu = -1; INIT_LIST_HEAD(&vcpu->blocked_vcpu_list); kvm_vcpu_set_in_spin_loop(vcpu, false); -- cgit v1.2.3 From 12a8eee5686ef3ea7d8db90cd664f11e4a39e349 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 8 Dec 2021 01:52:16 +0000 Subject: KVM: Move x86 VMX's posted interrupt list_head to vcpu_vmx Move the seemingly generic block_vcpu_list from kvm_vcpu to vcpu_vmx, and rename the list and all associated variables to clarify that it tracks the set of vCPU that need to be poked on a posted interrupt to the wakeup vector. The list is not used to track _all_ vCPUs that are blocking, and the term "blocked" can be misleading as it may refer to a blocking condition in the host or the guest, where as the PI wakeup case is specifically for the vCPUs that are actively blocking from within the guest. No functional change intended. Signed-off-by: Sean Christopherson Reviewed-by: Maxim Levitsky Message-Id: <20211208015236.1616697-7-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/vmx/posted_intr.c | 39 ++++++++++++++++++++------------------- arch/x86/kvm/vmx/vmx.c | 2 ++ arch/x86/kvm/vmx/vmx.h | 3 +++ include/linux/kvm_host.h | 2 -- virt/kvm/kvm_main.c | 2 -- 5 files changed, 25 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 63e2399f353a..901eea44cf24 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -19,7 +19,7 @@ * wake the target vCPUs. vCPUs are removed from the list and the notification * vector is reset when the vCPU is scheduled in. */ -static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); +static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu); /* * Protect the per-CPU list with a per-CPU spinlock to handle task migration. * When a blocking vCPU is awakened _and_ migrated to a different pCPU, the @@ -27,7 +27,7 @@ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); * CPU. IRQs must be disabled when taking this lock, otherwise deadlock will * occur if a wakeup IRQ arrives and attempts to acquire the lock. */ -static DEFINE_PER_CPU(raw_spinlock_t, blocked_vcpu_on_cpu_lock); +static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock); static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) { @@ -51,6 +51,7 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new) void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); struct pi_desc old, new; unsigned long flags; unsigned int dest; @@ -86,9 +87,9 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) * current pCPU if the task was migrated. */ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) { - raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); - list_del(&vcpu->blocked_vcpu_list); - raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); + raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); + list_del(&vmx->pi_wakeup_list); + raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); } dest = cpu_physical_id(cpu); @@ -142,15 +143,16 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm) static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) { struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); struct pi_desc old, new; unsigned long flags; local_irq_save(flags); - raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); - list_add_tail(&vcpu->blocked_vcpu_list, - &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu)); - raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu)); + raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); + list_add_tail(&vmx->pi_wakeup_list, + &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu)); + raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); WARN(pi_desc->sn, "PI descriptor SN field set before blocking"); @@ -199,24 +201,23 @@ void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu) */ void pi_wakeup_handler(void) { - struct kvm_vcpu *vcpu; int cpu = smp_processor_id(); + struct vcpu_vmx *vmx; - raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); - list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu), - blocked_vcpu_list) { - struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); + raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu)); + list_for_each_entry(vmx, &per_cpu(wakeup_vcpus_on_cpu, cpu), + pi_wakeup_list) { - if (pi_test_on(pi_desc)) - kvm_vcpu_kick(vcpu); + if (pi_test_on(&vmx->pi_desc)) + kvm_vcpu_kick(&vmx->vcpu); } - raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu)); } void __init pi_init_cpu(int cpu) { - INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu)); - raw_spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu)); + INIT_LIST_HEAD(&per_cpu(wakeup_vcpus_on_cpu, cpu)); + raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu)); } bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3a9a49a87b9d..1840898bb184 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6943,6 +6943,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0); vmx = to_vmx(vcpu); + INIT_LIST_HEAD(&vmx->pi_wakeup_list); + err = -ENOMEM; vmx->vpid = allocate_vpid(); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index f8fc7441baea..7f2c82e7f38f 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -317,6 +317,9 @@ struct vcpu_vmx { /* Posted interrupt descriptor */ struct pi_desc pi_desc; + /* Used if this vCPU is waiting for PI notification wakeup. */ + struct list_head pi_wakeup_list; + /* Support for a guest hypervisor (nested VMX) */ struct nested_vmx nested; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 5c3c67b6318f..f079820f52b5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -309,8 +309,6 @@ struct kvm_vcpu { u64 requests; unsigned long guest_debug; - struct list_head blocked_vcpu_list; - struct mutex mutex; struct kvm_run *run; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index c301cd8d583e..5a1164483e6c 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -427,8 +427,6 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) #endif kvm_async_pf_vcpu_init(vcpu); - INIT_LIST_HEAD(&vcpu->blocked_vcpu_list); - kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; -- cgit v1.2.3 From 1ca3fb3abd2b615c4b61728de545760a6e2c2d8b Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 19 Jan 2022 18:07:45 -0800 Subject: mm: percpu: add pcpu_fc_cpu_to_node_fn_t typedef Add pcpu_fc_cpu_to_node_fn_t and pass it into pcpu_fc_alloc_fn_t, pcpu first chunk allocation will call it to alloc memblock on the corresponding node by it, this is prepare for the next patch. Link: https://lkml.kernel.org/r/20211216112359.103822-3-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: Thomas Bogendoerfer Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Albert Ou Cc: Catalin Marinas Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/init.c | 12 +++++++++--- arch/powerpc/kernel/setup_64.c | 15 +++++++++++---- arch/sparc/kernel/smp_64.c | 13 ++++++++++--- arch/x86/kernel/setup_percpu.c | 18 +++++++++++++----- drivers/base/arch_numa.c | 8 +++++--- include/linux/percpu.h | 7 +++++-- mm/percpu.c | 14 +++++++++----- 7 files changed, 62 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 325e1552cbea..1d8f2844704c 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -519,12 +519,17 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return node_distance(cpu_to_node(from), cpu_to_node(to)); } -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, - size_t align) +static int __init pcpu_cpu_to_node(int cpu) +{ + return cpu_to_node(cpu); +} + +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, - cpu_to_node(cpu)); + cpu_to_nd_fn(cpu)); } static void __init pcpu_fc_free(void *ptr, size_t size) @@ -545,6 +550,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, pcpu_cpu_distance, + pcpu_cpu_to_node, pcpu_fc_alloc, pcpu_fc_free); if (rc < 0) panic("Failed to initialize percpu areas."); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 6052f5d5ded3..b79b10ae466f 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -784,12 +784,12 @@ void __init emergency_stack_init(void) * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, - size_t align) +static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA - int node = early_cpu_to_node(cpu); + int node = cpu_to_nd_fun(cpu); void *ptr; if (!node_online(node) || !NODE_DATA(node)) { @@ -823,6 +823,11 @@ static int pcpu_cpu_distance(unsigned int from, unsigned int to) return REMOTE_DISTANCE; } +static __init int pcpu_cpu_to_node(int cpu) +{ + return early_cpu_to_node(cpu); +} + unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); @@ -891,6 +896,7 @@ void __init setup_per_cpu_areas(void) if (pcpu_chosen_fc != PCPU_FC_PAGE) { rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, + pcpu_cpu_to_node, pcpu_alloc_bootmem, pcpu_free_bootmem); if (rc) pr_warn("PERCPU: %s allocator failed (%d), " @@ -899,7 +905,8 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) - rc = pcpu_page_first_chunk(0, pcpu_alloc_bootmem, pcpu_free_bootmem, + rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node, + pcpu_alloc_bootmem, pcpu_free_bootmem, pcpu_populate_pte); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index b98a7bbe6728..14d719aa318d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1539,12 +1539,12 @@ void smp_send_stop(void) * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, - size_t align) +static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA - int node = cpu_to_node(cpu); + int node = cpu_to_nd_fn(cpu); void *ptr; if (!node_online(node) || !NODE_DATA(node)) { @@ -1578,6 +1578,11 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return REMOTE_DISTANCE; } +static int __init pcpu_cpu_to_node(int cpu) +{ + return cpu_to_node(cpu); +} + static void __init pcpu_populate_pte(unsigned long addr) { pgd_t *pgd = pgd_offset_k(addr); @@ -1641,6 +1646,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, 4 << 20, pcpu_cpu_distance, + pcpu_cpu_to_node, pcpu_alloc_bootmem, pcpu_free_bootmem); if (rc) @@ -1650,6 +1656,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, + pcpu_cpu_to_node, pcpu_alloc_bootmem, pcpu_free_bootmem, pcpu_populate_pte); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 7b65275544b2..1d41f4844149 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -97,12 +97,12 @@ static bool __init pcpu_need_numa(void) * RETURNS: * Pointer to the allocated area on success, NULL on failure. */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, - unsigned long align) +static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, unsigned long align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { const unsigned long goal = __pa(MAX_DMA_ADDRESS); #ifdef CONFIG_NUMA - int node = early_cpu_to_node(cpu); + int node = cpu_to_nd_fn(cpu); void *ptr; if (!node_online(node) || !NODE_DATA(node)) { @@ -128,9 +128,10 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, /* * Helpers for first chunk memory allocation */ -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { - return pcpu_alloc_bootmem(cpu, size, align); + return pcpu_alloc_bootmem(cpu, size, align, cpu_to_nd_fn); } static void __init pcpu_fc_free(void *ptr, size_t size) @@ -150,6 +151,11 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) #endif } +static int __init pcpu_cpu_to_node(int cpu) +{ + return early_cpu_to_node(cpu); +} + static void __init pcpup_populate_pte(unsigned long addr) { populate_extra_pte(addr); @@ -205,6 +211,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, dyn_size, atom_size, pcpu_cpu_distance, + pcpu_cpu_to_node, pcpu_fc_alloc, pcpu_fc_free); if (rc < 0) pr_warn("%s allocator failed (%d), falling back to page size\n", @@ -212,6 +219,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, + pcpu_cpu_to_node, pcpu_fc_alloc, pcpu_fc_free, pcpup_populate_pte); if (rc < 0) diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index bc1876915457..dae861838535 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -155,10 +155,10 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); } -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, - size_t align) +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { - int nid = early_cpu_to_node(cpu); + int nid = cpu_to_nd_fn(cpu); return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); @@ -229,6 +229,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, pcpu_cpu_distance, + early_cpu_to_node, pcpu_fc_alloc, pcpu_fc_free); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) @@ -240,6 +241,7 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, + early_cpu_to_node, pcpu_fc_alloc, pcpu_fc_free, pcpu_populate_pte); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index ae4004e7957e..e4078bf45fd5 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -94,8 +94,9 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; -typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, - size_t align); +typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu); +typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); @@ -111,12 +112,14 @@ extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK extern int __init pcpu_page_first_chunk(size_t reserved_size, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn); diff --git a/mm/percpu.c b/mm/percpu.c index f5b2c2ea5a54..267a4d295fcf 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3001,6 +3001,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( * @dyn_size: minimum free size for dynamic allocation in bytes * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional + * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * @alloc_fn: function to allocate percpu page * @free_fn: function to free percpu page * @@ -3030,6 +3031,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn) { @@ -3066,7 +3068,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ - ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size); + ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; @@ -3143,6 +3145,7 @@ out_free: /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes + * @cpu_to_nd_fn: callback to convert cpu to it's node, optional * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE * @free_fn: function to free percpu page, always called with PAGE_SIZE * @populate_pte_fn: function to populate pte @@ -3157,6 +3160,7 @@ out_free: * 0 on success, -errno on failure. */ int __init pcpu_page_first_chunk(size_t reserved_size, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, pcpu_fc_alloc_fn_t alloc_fn, pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn) @@ -3201,7 +3205,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, for (i = 0; i < unit_pages; i++) { void *ptr; - ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE); + ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); @@ -3278,8 +3282,8 @@ out_free_ar: unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); -static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, - size_t align) +static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS)); } @@ -3300,7 +3304,7 @@ void __init setup_per_cpu_areas(void) * what the legacy allocator did. */ rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, + PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL, pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); if (rc < 0) panic("Failed to initialize percpu areas."); -- cgit v1.2.3 From 23f917169ef157aa7a6bf80d8c4aad6f1282852c Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 19 Jan 2022 18:07:49 -0800 Subject: mm: percpu: add generic pcpu_fc_alloc/free funciton With the previous patch, we could add a generic pcpu first chunk allocate and free function to cleanup the duplicated definations on each architecture. Link: https://lkml.kernel.org/r/20211216112359.103822-4-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: Thomas Bogendoerfer Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Greg Kroah-Hartman Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Albert Ou Cc: Catalin Marinas Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: "Rafael J. Wysocki" Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/mips/mm/init.c | 16 +-------- arch/powerpc/kernel/setup_64.c | 51 ++------------------------- arch/sparc/kernel/smp_64.c | 50 +-------------------------- arch/x86/kernel/setup_percpu.c | 59 +------------------------------- drivers/base/arch_numa.c | 19 +--------- include/linux/percpu.h | 9 +---- mm/percpu.c | 78 +++++++++++++++++++++++++----------------- 7 files changed, 54 insertions(+), 228 deletions(-) (limited to 'include/linux') diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 1d8f2844704c..5a8002839550 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -524,19 +524,6 @@ static int __init pcpu_cpu_to_node(int cpu) return cpu_to_node(cpu); } -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), - MEMBLOCK_ALLOC_ACCESSIBLE, - cpu_to_nd_fn(cpu)); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - void __init setup_per_cpu_areas(void) { unsigned long delta; @@ -550,8 +537,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, pcpu_cpu_distance, - pcpu_cpu_to_node, - pcpu_fc_alloc, pcpu_fc_free); + pcpu_cpu_to_node); if (rc < 0) panic("Failed to initialize percpu areas."); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index b79b10ae466f..a0c55c6e3023 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -771,50 +771,6 @@ void __init emergency_stack_init(void) } #ifdef CONFIG_SMP -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = cpu_to_nd_fun(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, node); - pr_debug("per cpu data for cpu%d %lu bytes on node%d at " - "%016lx\n", cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -static void __init pcpu_free_bootmem(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int pcpu_cpu_distance(unsigned int from, unsigned int to) { if (early_cpu_to_node(from) == early_cpu_to_node(to)) @@ -896,8 +852,7 @@ void __init setup_per_cpu_areas(void) if (pcpu_chosen_fc != PCPU_FC_PAGE) { rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_cpu_to_node, - pcpu_alloc_bootmem, pcpu_free_bootmem); + pcpu_cpu_to_node); if (rc) pr_warn("PERCPU: %s allocator failed (%d), " "falling back to page size\n", @@ -905,9 +860,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) - rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node, - pcpu_alloc_bootmem, pcpu_free_bootmem, - pcpu_populate_pte); + rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node, pcpu_populate_pte); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 14d719aa318d..ef815b3f0592 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1526,50 +1526,6 @@ void smp_send_stop(void) smp_call_function(stop_this_cpu, NULL, 0); } -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = cpu_to_nd_fn(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, node); - pr_debug("per cpu data for cpu%d %lu bytes on node%d at " - "%016lx\n", cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -static void __init pcpu_free_bootmem(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) { if (cpu_to_node(from) == cpu_to_node(to)) @@ -1646,9 +1602,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, 4 << 20, pcpu_cpu_distance, - pcpu_cpu_to_node, - pcpu_alloc_bootmem, - pcpu_free_bootmem); + pcpu_cpu_to_node); if (rc) pr_warn("PERCPU: %s allocator failed (%d), " "falling back to page size\n", @@ -1657,8 +1611,6 @@ void __init setup_per_cpu_areas(void) if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, pcpu_cpu_to_node, - pcpu_alloc_bootmem, - pcpu_free_bootmem, pcpu_populate_pte); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 1d41f4844149..15c5bf3cbe5f 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -84,61 +84,6 @@ static bool __init pcpu_need_numa(void) } #endif -/** - * pcpu_alloc_bootmem - NUMA friendly alloc_bootmem wrapper for percpu - * @cpu: cpu to allocate for - * @size: size allocation in bytes - * @align: alignment - * - * Allocate @size bytes aligned at @align for cpu @cpu. This wrapper - * does the right thing for NUMA regardless of the current - * configuration. - * - * RETURNS: - * Pointer to the allocated area on success, NULL on failure. - */ -static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, unsigned long align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - const unsigned long goal = __pa(MAX_DMA_ADDRESS); -#ifdef CONFIG_NUMA - int node = cpu_to_nd_fn(cpu); - void *ptr; - - if (!node_online(node) || !NODE_DATA(node)) { - ptr = memblock_alloc_from(size, align, goal); - pr_info("cpu %d has no node %d or node-local memory\n", - cpu, node); - pr_debug("per cpu data for cpu%d %lu bytes at %016lx\n", - cpu, size, __pa(ptr)); - } else { - ptr = memblock_alloc_try_nid(size, align, goal, - MEMBLOCK_ALLOC_ACCESSIBLE, - node); - - pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", - cpu, size, node, __pa(ptr)); - } - return ptr; -#else - return memblock_alloc_from(size, align, goal); -#endif -} - -/* - * Helpers for first chunk memory allocation - */ -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - return pcpu_alloc_bootmem(cpu, size, align, cpu_to_nd_fn); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) { #ifdef CONFIG_NUMA @@ -211,8 +156,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, dyn_size, atom_size, pcpu_cpu_distance, - pcpu_cpu_to_node, - pcpu_fc_alloc, pcpu_fc_free); + pcpu_cpu_to_node); if (rc < 0) pr_warn("%s allocator failed (%d), falling back to page size\n", pcpu_fc_names[pcpu_chosen_fc], rc); @@ -220,7 +164,6 @@ void __init setup_per_cpu_areas(void) if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, pcpu_cpu_to_node, - pcpu_fc_alloc, pcpu_fc_free, pcpup_populate_pte); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index dae861838535..23a10cc36165 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -155,20 +155,6 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); } -static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - int nid = cpu_to_nd_fn(cpu); - - return memblock_alloc_try_nid(size, align, - __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); -} - -static void __init pcpu_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK static void __init pcpu_populate_pte(unsigned long addr) { @@ -229,8 +215,7 @@ void __init setup_per_cpu_areas(void) rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, pcpu_cpu_distance, - early_cpu_to_node, - pcpu_fc_alloc, pcpu_fc_free); + early_cpu_to_node); #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) pr_warn("PERCPU: %s allocator failed (%d), falling back to page size\n", @@ -242,8 +227,6 @@ void __init setup_per_cpu_areas(void) if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, early_cpu_to_node, - pcpu_fc_alloc, - pcpu_fc_free, pcpu_populate_pte); #endif if (rc < 0) diff --git a/include/linux/percpu.h b/include/linux/percpu.h index e4078bf45fd5..d73c97ef4ff4 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -95,9 +95,6 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu); -typedef void * (*pcpu_fc_alloc_fn_t)(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); -typedef void (*pcpu_fc_free_fn_t)(void *ptr, size_t size); typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); @@ -112,16 +109,12 @@ extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK extern int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn); #endif diff --git a/mm/percpu.c b/mm/percpu.c index 267a4d295fcf..0f79b6d9a6d6 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2992,6 +2992,42 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( return ai; } + +static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align, + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) +{ + const unsigned long goal = __pa(MAX_DMA_ADDRESS); +#ifdef CONFIG_NUMA + int node = NUMA_NO_NODE; + void *ptr; + + if (cpu_to_nd_fn) + node = cpu_to_nd_fn(cpu); + + if (node == NUMA_NO_NODE || !node_online(node) || !NODE_DATA(node)) { + ptr = memblock_alloc_from(size, align, goal); + pr_info("cpu %d has no node %d or node-local memory\n", + cpu, node); + pr_debug("per cpu data for cpu%d %zu bytes at 0x%llx\n", + cpu, size, (u64)__pa(ptr)); + } else { + ptr = memblock_alloc_try_nid(size, align, goal, + MEMBLOCK_ALLOC_ACCESSIBLE, + node); + + pr_debug("per cpu data for cpu%d %zu bytes on node%d at 0x%llx\n", + cpu, size, node, (u64)__pa(ptr)); + } + return ptr; +#else + return memblock_alloc_from(size, align, goal); +#endif +} + +static void __init pcpu_fc_free(void *ptr, size_t size) +{ + memblock_free(ptr, size); +} #endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */ #if defined(BUILD_EMBED_FIRST_CHUNK) @@ -3002,14 +3038,12 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( * @atom_size: allocation atom size * @cpu_distance_fn: callback to determine distance between cpus, optional * @cpu_to_nd_fn: callback to convert cpu to it's node, optional - * @alloc_fn: function to allocate percpu page - * @free_fn: function to free percpu page * * This is a helper to ease setting up embedded first percpu chunk and * can be called where pcpu_setup_first_chunk() is expected. * * If this function is used to setup the first chunk, it is allocated - * by calling @alloc_fn and used as-is without being mapped into + * by calling pcpu_fc_alloc and used as-is without being mapped into * vmalloc area. Allocations are always whole multiples of @atom_size * aligned to @atom_size. * @@ -3023,7 +3057,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( * @dyn_size specifies the minimum dynamic area size. * * If the needed size is smaller than the minimum or specified unit - * size, the leftover is returned using @free_fn. + * size, the leftover is returned using pcpu_fc_free. * * RETURNS: * 0 on success, -errno on failure. @@ -3031,9 +3065,7 @@ static struct pcpu_alloc_info * __init __flatten pcpu_build_alloc_info( int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_t atom_size, pcpu_fc_cpu_distance_fn_t cpu_distance_fn, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn) + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { void *base = (void *)ULONG_MAX; void **areas = NULL; @@ -3068,7 +3100,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, BUG_ON(cpu == NR_CPUS); /* allocate space for the whole group */ - ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); + ptr = pcpu_fc_alloc(cpu, gi->nr_units * ai->unit_size, atom_size, cpu_to_nd_fn); if (!ptr) { rc = -ENOMEM; goto out_free_areas; @@ -3107,12 +3139,12 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) { if (gi->cpu_map[i] == NR_CPUS) { /* unused unit, free whole */ - free_fn(ptr, ai->unit_size); + pcpu_fc_free(ptr, ai->unit_size); continue; } /* copy and return the unused part */ memcpy(ptr, __per_cpu_load, ai->static_size); - free_fn(ptr + size_sum, ai->unit_size - size_sum); + pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum); } } @@ -3131,7 +3163,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, out_free_areas: for (group = 0; group < ai->nr_groups; group++) if (areas[group]) - free_fn(areas[group], + pcpu_fc_free(areas[group], ai->groups[group].nr_units * ai->unit_size); out_free: pcpu_free_alloc_info(ai); @@ -3146,8 +3178,6 @@ out_free: * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional - * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE - * @free_fn: function to free percpu page, always called with PAGE_SIZE * @populate_pte_fn: function to populate pte * * This is a helper to ease setting up page-remapped first percpu @@ -3161,8 +3191,6 @@ out_free: */ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, - pcpu_fc_alloc_fn_t alloc_fn, - pcpu_fc_free_fn_t free_fn, pcpu_fc_populate_pte_fn_t populate_pte_fn) { static struct vm_struct vm; @@ -3205,7 +3233,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, for (i = 0; i < unit_pages; i++) { void *ptr; - ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); + ptr = pcpu_fc_alloc(cpu, PAGE_SIZE, PAGE_SIZE, cpu_to_nd_fn); if (!ptr) { pr_warn("failed to allocate %s page for cpu%u\n", psize_str, cpu); @@ -3257,7 +3285,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, enomem: while (--j >= 0) - free_fn(page_address(pages[j]), PAGE_SIZE); + pcpu_fc_free(page_address(pages[j]), PAGE_SIZE); rc = -ENOMEM; out_free_ar: memblock_free(pages, pages_size); @@ -3282,17 +3310,6 @@ out_free_ar: unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); -static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) -{ - return memblock_alloc_from(size, align, __pa(MAX_DMA_ADDRESS)); -} - -static void __init pcpu_dfl_fc_free(void *ptr, size_t size) -{ - memblock_free(ptr, size); -} - void __init setup_per_cpu_areas(void) { unsigned long delta; @@ -3303,9 +3320,8 @@ void __init setup_per_cpu_areas(void) * Always reserve area for module percpu variables. That's * what the legacy allocator did. */ - rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, - PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL, NULL, - pcpu_dfl_fc_alloc, pcpu_dfl_fc_free); + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE, PERCPU_DYNAMIC_RESERVE, + PAGE_SIZE, NULL, NULL); if (rc < 0) panic("Failed to initialize percpu areas."); -- cgit v1.2.3 From 20c035764626c56c4f6514936b9ee4be0f4cd962 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Wed, 19 Jan 2022 18:07:53 -0800 Subject: mm: percpu: add generic pcpu_populate_pte() function With NEED_PER_CPU_PAGE_FIRST_CHUNK enabled, we need a function to populate pte, this patch adds a generic pcpu populate pte function, pcpu_populate_pte(), which is marked __weak and used on most architectures, but it is overridden on x86, which has its own implementation. Link: https://lkml.kernel.org/r/20211216112359.103822-5-wangkefeng.wang@huawei.com Signed-off-by: Kefeng Wang Cc: Michael Ellerman Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: "David S. Miller" Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: Dennis Zhou Cc: Tejun Heo Cc: Christoph Lameter Cc: Albert Ou Cc: Catalin Marinas Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Thomas Bogendoerfer Cc: Will Deacon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/setup_64.c | 47 +------------------------- arch/sparc/kernel/smp_64.c | 56 +------------------------------ arch/x86/kernel/setup_percpu.c | 5 ++- drivers/base/arch_numa.c | 51 +--------------------------- include/linux/percpu.h | 5 ++- mm/percpu.c | 76 +++++++++++++++++++++++++++++++++++++++--- 6 files changed, 78 insertions(+), 162 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index a0c55c6e3023..f7cf408217c5 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -787,51 +787,6 @@ static __init int pcpu_cpu_to_node(int cpu) unsigned long __per_cpu_offset[NR_CPUS] __read_mostly; EXPORT_SYMBOL(__per_cpu_offset); -static void __init pcpu_populate_pte(unsigned long addr) -{ - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); -} - - void __init setup_per_cpu_areas(void) { const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE; @@ -860,7 +815,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) - rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node, pcpu_populate_pte); + rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index ef815b3f0592..a1f78e9ddaf3 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1539,59 +1539,6 @@ static int __init pcpu_cpu_to_node(int cpu) return cpu_to_node(cpu); } -static void __init pcpu_populate_pte(unsigned long addr) -{ - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - if (pgd_none(*pgd)) { - pud_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pgd_populate(&init_mm, pgd, new); - } - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc_from(PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); -} - void __init setup_per_cpu_areas(void) { unsigned long delta; @@ -1610,8 +1557,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, - pcpu_cpu_to_node, - pcpu_populate_pte); + pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 15c5bf3cbe5f..49325caa7307 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -101,7 +101,7 @@ static int __init pcpu_cpu_to_node(int cpu) return early_cpu_to_node(cpu); } -static void __init pcpup_populate_pte(unsigned long addr) +void __init pcpu_populate_pte(unsigned long addr) { populate_extra_pte(addr); } @@ -163,8 +163,7 @@ void __init setup_per_cpu_areas(void) } if (rc < 0) rc = pcpu_page_first_chunk(PERCPU_FIRST_CHUNK_RESERVE, - pcpu_cpu_to_node, - pcpup_populate_pte); + pcpu_cpu_to_node); if (rc < 0) panic("cannot initialize percpu area (err=%d)", rc); diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c index 23a10cc36165..eaa31e567d1e 100644 --- a/drivers/base/arch_numa.c +++ b/drivers/base/arch_numa.c @@ -14,7 +14,6 @@ #include #include -#include struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); @@ -155,52 +154,6 @@ static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) return node_distance(early_cpu_to_node(from), early_cpu_to_node(to)); } -#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK -static void __init pcpu_populate_pte(unsigned long addr) -{ - pgd_t *pgd = pgd_offset_k(addr); - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - p4d = p4d_offset(pgd, addr); - if (p4d_none(*p4d)) { - pud_t *new; - - new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - p4d_populate(&init_mm, p4d, new); - } - - pud = pud_offset(p4d, addr); - if (pud_none(*pud)) { - pmd_t *new; - - new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pud_populate(&init_mm, pud, new); - } - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) { - pte_t *new; - - new = memblock_alloc(PAGE_SIZE, PAGE_SIZE); - if (!new) - goto err_alloc; - pmd_populate_kernel(&init_mm, pmd, new); - } - - return; - -err_alloc: - panic("%s: Failed to allocate %lu bytes align=%lx from=%lx\n", - __func__, PAGE_SIZE, PAGE_SIZE, PAGE_SIZE); -} -#endif - void __init setup_per_cpu_areas(void) { unsigned long delta; @@ -225,9 +178,7 @@ void __init setup_per_cpu_areas(void) #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK if (rc < 0) - rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, - early_cpu_to_node, - pcpu_populate_pte); + rc = pcpu_page_first_chunk(PERCPU_MODULE_RESERVE, early_cpu_to_node); #endif if (rc < 0) panic("Failed to initialize percpu areas (err=%d).", rc); diff --git a/include/linux/percpu.h b/include/linux/percpu.h index d73c97ef4ff4..f1ec5ad1351c 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -95,7 +95,6 @@ extern const char * const pcpu_fc_names[PCPU_FC_NR]; extern enum pcpu_fc pcpu_chosen_fc; typedef int (pcpu_fc_cpu_to_node_fn_t)(int cpu); -typedef void (*pcpu_fc_populate_pte_fn_t)(unsigned long addr); typedef int (pcpu_fc_cpu_distance_fn_t)(unsigned int from, unsigned int to); extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, @@ -113,9 +112,9 @@ extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, #endif #ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK +void __init pcpu_populate_pte(unsigned long addr); extern int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn); + pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn); #endif extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __alloc_size(1); diff --git a/mm/percpu.c b/mm/percpu.c index 0f79b6d9a6d6..fc6f591cb54f 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3174,11 +3174,79 @@ out_free: #endif /* BUILD_EMBED_FIRST_CHUNK */ #ifdef BUILD_PAGE_FIRST_CHUNK +#include + +#ifndef P4D_TABLE_SIZE +#define P4D_TABLE_SIZE PAGE_SIZE +#endif + +#ifndef PUD_TABLE_SIZE +#define PUD_TABLE_SIZE PAGE_SIZE +#endif + +#ifndef PMD_TABLE_SIZE +#define PMD_TABLE_SIZE PAGE_SIZE +#endif + +#ifndef PTE_TABLE_SIZE +#define PTE_TABLE_SIZE PAGE_SIZE +#endif +void __init __weak pcpu_populate_pte(unsigned long addr) +{ + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + if (pgd_none(*pgd)) { + p4d_t *new; + + new = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); + if (!new) + goto err_alloc; + pgd_populate(&init_mm, pgd, new); + } + + p4d = p4d_offset(pgd, addr); + if (p4d_none(*p4d)) { + pud_t *new; + + new = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); + if (!new) + goto err_alloc; + p4d_populate(&init_mm, p4d, new); + } + + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) { + pmd_t *new; + + new = memblock_alloc(PMD_TABLE_SIZE, PMD_TABLE_SIZE); + if (!new) + goto err_alloc; + pud_populate(&init_mm, pud, new); + } + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + pte_t *new; + + new = memblock_alloc(PTE_TABLE_SIZE, PTE_TABLE_SIZE); + if (!new) + goto err_alloc; + pmd_populate_kernel(&init_mm, pmd, new); + } + + return; + +err_alloc: + panic("%s: Failed to allocate memory\n", __func__); +} + /** * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages * @reserved_size: the size of reserved percpu area in bytes * @cpu_to_nd_fn: callback to convert cpu to it's node, optional - * @populate_pte_fn: function to populate pte * * This is a helper to ease setting up page-remapped first percpu * chunk and can be called where pcpu_setup_first_chunk() is expected. @@ -3189,9 +3257,7 @@ out_free: * RETURNS: * 0 on success, -errno on failure. */ -int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn, - pcpu_fc_populate_pte_fn_t populate_pte_fn) +int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t cpu_to_nd_fn) { static struct vm_struct vm; struct pcpu_alloc_info *ai; @@ -3255,7 +3321,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, (unsigned long)vm.addr + unit * ai->unit_size; for (i = 0; i < unit_pages; i++) - populate_pte_fn(unit_addr + (i << PAGE_SHIFT)); + pcpu_populate_pte(unit_addr + (i << PAGE_SHIFT)); /* pte already populated, the following shouldn't fail */ rc = __pcpu_map_pages(unit_addr, &pages[unit * unit_pages], -- cgit v1.2.3 From ae62fbe299629d3b2fa61d4cf5146258c4d99fdf Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 19 Jan 2022 18:08:00 -0800 Subject: proc: make the proc_create[_data]() stubs static inlines Change the proc_create[_data]() stubs which are used when CONFIG_PROC_FS is not set from #defines to a static inline stubs. This should fix clang -Werror builds failing due to errors like this: drivers/platform/x86/thinkpad_acpi.c:918:30: error: unused variable 'dispatch_proc_ops' [-Werror,-Wunused-const-variable] Fixing this in include/linux/proc_fs.h should ensure that the same issue is also fixed in any other drivers hitting the same -Werror issue. [akpm@linux-foundation.org: fix CONFIG_PROC_FS=n] [akpm@linux-foundation.org: fix arch/sparc/kernel/led.c] [akpm@linux-foundation.org: fix build] Link: https://lkml.kernel.org/r/20211116131112.508304-1-hdegoede@redhat.com Signed-off-by: Hans de Goede Reported-by: kernel test robot Acked-by: Christian Brauner Cc: Alexander Viro Cc: Hans de Goede Cc: David Howells Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/led.c | 8 +++----- include/linux/proc_fs.h | 12 ++++++++++-- 2 files changed, 13 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/arch/sparc/kernel/led.c b/arch/sparc/kernel/led.c index 3a66e62eb2a0..ab657b359789 100644 --- a/arch/sparc/kernel/led.c +++ b/arch/sparc/kernel/led.c @@ -114,18 +114,16 @@ static const struct proc_ops led_proc_ops = { }; #endif -static struct proc_dir_entry *led; - #define LED_VERSION "0.1" static int __init led_init(void) { timer_setup(&led_blink_timer, led_blink, 0); - led = proc_create("led", 0, NULL, &led_proc_ops); - if (!led) +#ifdef CONFIG_PROC_FS + if (!proc_create("led", 0, NULL, &led_proc_ops)) return -ENOMEM; - +#endif printk(KERN_INFO "led: version %s, Lars Kotthoff \n", LED_VERSION); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 069c7fd95396..01b9268451a8 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -178,8 +178,16 @@ static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, #define proc_create_seq(name, mode, parent, ops) ({NULL;}) #define proc_create_single(name, mode, parent, show) ({NULL;}) #define proc_create_single_data(name, mode, parent, show, data) ({NULL;}) -#define proc_create(name, mode, parent, proc_ops) ({NULL;}) -#define proc_create_data(name, mode, parent, proc_ops, data) ({NULL;}) + +static inline struct proc_dir_entry * +proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops) +{ return NULL; } + +static inline struct proc_dir_entry * +proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, + const struct proc_ops *proc_ops, void *data) +{ return NULL; } static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -- cgit v1.2.3 From 22c033989c3eb9731ad0c497dfab4231b8e367d6 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jan 2022 18:08:12 -0800 Subject: include/linux/unaligned: replace kernel.h with the necessary inclusions When kernel.h is used in the headers it adds a lot into dependency hell, especially when there are circular dependencies are involved. Replace kernel.h inclusion with the list of what is really being used. The rest of the changes are induced by the above and may not be split. Link: https://lkml.kernel.org/r/20211209123823.20425-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Arend van Spriel [brcmfmac] Acked-by: Kalle Valo Cc: Arend van Spriel Cc: Franky Lin Cc: Hante Meuleman Cc: Chi-hsien Lin Cc: Wright Feng Cc: Chung-hsien Hsu Cc: Kalle Valo Cc: David S. Miller Cc: Jakub Kicinski Cc: Heikki Krogerus Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c | 2 ++ include/linux/unaligned/packed_struct.h | 2 +- lib/lz4/lz4defs.h | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c index 2f3c451148db..2f8908074303 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/xtlv.c @@ -4,6 +4,8 @@ */ #include + +#include #include #include diff --git a/include/linux/unaligned/packed_struct.h b/include/linux/unaligned/packed_struct.h index c0d817de4df2..f4c8eaf4d012 100644 --- a/include/linux/unaligned/packed_struct.h +++ b/include/linux/unaligned/packed_struct.h @@ -1,7 +1,7 @@ #ifndef _LINUX_UNALIGNED_PACKED_STRUCT_H #define _LINUX_UNALIGNED_PACKED_STRUCT_H -#include +#include struct __una_u16 { u16 x; } __packed; struct __una_u32 { u32 x; } __packed; diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index 673bd206aa98..330aa539b46e 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -36,6 +36,8 @@ */ #include + +#include #include /* memset, memcpy */ #define FORCE_INLINE __always_inline -- cgit v1.2.3 From 40cbf09f060c8febef64541c463d4dd526abe445 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jan 2022 18:08:16 -0800 Subject: kernel.h: include a note to discourage people from including it in headers Include a note at the top to discourage people from including it in headers. Link: https://lkml.kernel.org/r/20211209150803.4473-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 77755ac3e189..36a612d82956 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -1,4 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * NOTE: + * + * This header has combined a lot of unrelated to each other stuff. + * The process of splitting its content is in progress while keeping + * backward compatibility. That's why it's highly recommended NOT to + * include this header inside another header file, especially under + * generic or architectural include/ directory. + */ #ifndef _LINUX_KERNEL_H #define _LINUX_KERNEL_H -- cgit v1.2.3 From 95af469c4f609de011debc08e7a35b45201623a8 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 19 Jan 2022 18:08:29 -0800 Subject: fs/binfmt_elf: replace open-coded string copy with get_task_comm It is better to use get_task_comm() instead of the open coded string copy as we do in other places. struct elf_prpsinfo is used to dump the task information in userspace coredump or kernel vmcore. Below is the verification of vmcore, crash> ps PID PPID CPU TASK ST %MEM VSZ RSS COMM 0 0 0 ffffffff9d21a940 RU 0.0 0 0 [swapper/0] > 0 0 1 ffffa09e40f85e80 RU 0.0 0 0 [swapper/1] > 0 0 2 ffffa09e40f81f80 RU 0.0 0 0 [swapper/2] > 0 0 3 ffffa09e40f83f00 RU 0.0 0 0 [swapper/3] > 0 0 4 ffffa09e40f80000 RU 0.0 0 0 [swapper/4] > 0 0 5 ffffa09e40f89f80 RU 0.0 0 0 [swapper/5] 0 0 6 ffffa09e40f8bf00 RU 0.0 0 0 [swapper/6] > 0 0 7 ffffa09e40f88000 RU 0.0 0 0 [swapper/7] > 0 0 8 ffffa09e40f8de80 RU 0.0 0 0 [swapper/8] > 0 0 9 ffffa09e40f95e80 RU 0.0 0 0 [swapper/9] > 0 0 10 ffffa09e40f91f80 RU 0.0 0 0 [swapper/10] > 0 0 11 ffffa09e40f93f00 RU 0.0 0 0 [swapper/11] > 0 0 12 ffffa09e40f90000 RU 0.0 0 0 [swapper/12] > 0 0 13 ffffa09e40f9bf00 RU 0.0 0 0 [swapper/13] > 0 0 14 ffffa09e40f98000 RU 0.0 0 0 [swapper/14] > 0 0 15 ffffa09e40f9de80 RU 0.0 0 0 [swapper/15] It works well as expected. Some comments are added to explain why we use the hard-coded 16. Link: https://lkml.kernel.org/r/20211120112738.45980-5-laoar.shao@gmail.com Suggested-by: Kees Cook Signed-off-by: Yafang Shao Reviewed-by: David Hildenbrand Cc: Mathieu Desnoyers Cc: Arnaldo Carvalho de Melo Cc: Andrii Nakryiko Cc: Michal Miroslaw Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Matthew Wilcox Cc: David Hildenbrand Cc: Al Viro Cc: Kees Cook Cc: Petr Mladek Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Dennis Dalessandro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/binfmt_elf.c | 2 +- include/linux/elfcore-compat.h | 5 +++++ include/linux/elfcore.h | 5 +++++ 3 files changed, 11 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index f8c7f26f1fbb..b9a33cc34d6b 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1585,7 +1585,7 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, SET_UID(psinfo->pr_uid, from_kuid_munged(cred->user_ns, cred->uid)); SET_GID(psinfo->pr_gid, from_kgid_munged(cred->user_ns, cred->gid)); rcu_read_unlock(); - strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); + get_task_comm(psinfo->pr_fname, p); return 0; } diff --git a/include/linux/elfcore-compat.h b/include/linux/elfcore-compat.h index e272c3d452ce..54feb64e9b5d 100644 --- a/include/linux/elfcore-compat.h +++ b/include/linux/elfcore-compat.h @@ -43,6 +43,11 @@ struct compat_elf_prpsinfo __compat_uid_t pr_uid; __compat_gid_t pr_gid; compat_pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; char pr_psargs[ELF_PRARGSZ]; }; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 957ebec35aad..746e081879a5 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -65,6 +65,11 @@ struct elf_prpsinfo __kernel_gid_t pr_gid; pid_t pr_pid, pr_ppid, pr_pgrp, pr_sid; /* Lots missing */ + /* + * The hard-coded 16 is derived from TASK_COMM_LEN, but it can't be + * changed as it is exposed to userspace. We'd better make it hard-coded + * here. + */ char pr_fname[16]; /* filename of executable */ char pr_psargs[ELF_PRARGSZ]; /* initial part of arg list */ }; -- cgit v1.2.3 From 3087c61ed2c48548b74dd343a5209b87082c682d Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 19 Jan 2022 18:08:40 -0800 Subject: tools/testing/selftests/bpf: replace open-coded 16 with TASK_COMM_LEN As the sched:sched_switch tracepoint args are derived from the kernel, we'd better make it same with the kernel. So the macro TASK_COMM_LEN is converted to type enum, then all the BPF programs can get it through BTF. The BPF program which wants to use TASK_COMM_LEN should include the header vmlinux.h. Regarding the test_stacktrace_map and test_tracepoint, as the type defined in linux/bpf.h are also defined in vmlinux.h, so we don't need to include linux/bpf.h again. Link: https://lkml.kernel.org/r/20211120112738.45980-8-laoar.shao@gmail.com Signed-off-by: Yafang Shao Acked-by: Andrii Nakryiko Acked-by: David Hildenbrand Cc: Mathieu Desnoyers Cc: Arnaldo Carvalho de Melo Cc: Andrii Nakryiko Cc: Michal Miroslaw Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Matthew Wilcox Cc: David Hildenbrand Cc: Al Viro Cc: Kees Cook Cc: Petr Mladek Cc: Alexei Starovoitov Cc: Dennis Dalessandro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 9 +++++++-- tools/testing/selftests/bpf/progs/test_stacktrace_map.c | 6 +++--- tools/testing/selftests/bpf/progs/test_tracepoint.c | 6 +++--- 3 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 78c351e35fec..cecd4806edc6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -274,8 +274,13 @@ struct task_group; #define get_current_state() READ_ONCE(current->__state) -/* Task command name length: */ -#define TASK_COMM_LEN 16 +/* + * Define the task command name length as enum, then it can be visible to + * BPF programs. + */ +enum { + TASK_COMM_LEN = 16, +}; extern void scheduler_tick(void); diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index a8233e7f173b..728dbd39eff0 100644 --- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2018 Facebook -#include +#include #include #ifndef PERF_MAX_STACK_DEPTH @@ -41,11 +41,11 @@ struct { /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index ce6974016f53..43bd7a20cc50 100644 --- a/tools/testing/selftests/bpf/progs/test_tracepoint.c +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c @@ -1,17 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2017 Facebook -#include +#include #include /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ struct sched_switch_args { unsigned long long pad; - char prev_comm[16]; + char prev_comm[TASK_COMM_LEN]; int prev_pid; int prev_prio; long long prev_state; - char next_comm[16]; + char next_comm[TASK_COMM_LEN]; int next_pid; int next_prio; }; -- cgit v1.2.3 From d6986ce24fc00b0638bd29efe8fb7ba7619ed2aa Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Wed, 19 Jan 2022 18:08:43 -0800 Subject: kthread: dynamically allocate memory to store kthread's full name When I was implementing a new per-cpu kthread cfs_migration, I found the comm of it "cfs_migration/%u" is truncated due to the limitation of TASK_COMM_LEN. For example, the comm of the percpu thread on CPU10~19 all have the same name "cfs_migration/1", which will confuse the user. This issue is not critical, because we can get the corresponding CPU from the task's Cpus_allowed. But for kthreads corresponding to other hardware devices, it is not easy to get the detailed device info from task comm, for example, jbd2/nvme0n1p2- xfs-reclaim/sdf Currently there are so many truncated kthreads: rcu_tasks_kthre rcu_tasks_rude_ rcu_tasks_trace poll_mpt3sas0_s ext4-rsv-conver xfs-reclaim/sd{a, b, c, ...} xfs-blockgc/sd{a, b, c, ...} xfs-inodegc/sd{a, b, c, ...} audit_send_repl ecryptfs-kthrea vfio-irqfd-clea jbd2/nvme0n1p2- ... We can shorten these names to work around this problem, but it may be not applied to all of the truncated kthreads. Take 'jbd2/nvme0n1p2-' for example, it is a nice name, and it is not a good idea to shorten it. One possible way to fix this issue is extending the task comm size, but as task->comm is used in lots of places, that may cause some potential buffer overflows. Another more conservative approach is introducing a new pointer to store kthread's full name if it is truncated, which won't introduce too much overhead as it is in the non-critical path. Finally we make a dicision to use the second approach. See also the discussions in this thread: https://lore.kernel.org/lkml/20211101060419.4682-1-laoar.shao@gmail.com/ After this change, the full name of these truncated kthreads will be displayed via /proc/[pid]/comm: rcu_tasks_kthread rcu_tasks_rude_kthread rcu_tasks_trace_kthread poll_mpt3sas0_statu ext4-rsv-conversion xfs-reclaim/sdf1 xfs-blockgc/sdf1 xfs-inodegc/sdf1 audit_send_reply ecryptfs-kthread vfio-irqfd-cleanup jbd2/nvme0n1p2-8 Link: https://lkml.kernel.org/r/20211120112850.46047-1-laoar.shao@gmail.com Signed-off-by: Yafang Shao Reviewed-by: David Hildenbrand Reviewed-by: Petr Mladek Suggested-by: Petr Mladek Suggested-by: Steven Rostedt Cc: Mathieu Desnoyers Cc: Arnaldo Carvalho de Melo Cc: Alexei Starovoitov Cc: Andrii Nakryiko Cc: Michal Miroslaw Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Matthew Wilcox Cc: Al Viro Cc: Kees Cook Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/array.c | 3 +++ include/linux/kthread.h | 1 + kernel/kthread.c | 32 ++++++++++++++++++++++++++++++-- 3 files changed, 34 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/array.c b/fs/proc/array.c index ff869a66b34e..4321aa63835d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -92,6 +92,7 @@ #include #include #include +#include #include #include "internal.h" @@ -102,6 +103,8 @@ void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape) if (p->flags & PF_WQ_WORKER) wq_worker_comm(tcomm, sizeof(tcomm), p); + else if (p->flags & PF_KTHREAD) + get_kthread_comm(tcomm, sizeof(tcomm), p); else __get_task_comm(tcomm, sizeof(tcomm), p); diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 346b0f269161..2a5c04494663 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -33,6 +33,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), unsigned int cpu, const char *namefmt); +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk); void set_kthread_struct(struct task_struct *p); void kthread_set_per_cpu(struct task_struct *k, int cpu); diff --git a/kernel/kthread.c b/kernel/kthread.c index 7113003fab63..a70cd5dc94e3 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -60,6 +60,8 @@ struct kthread { #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif + /* To store the full name if task comm is truncated. */ + char *full_name; }; enum KTHREAD_BITS { @@ -93,6 +95,18 @@ static inline struct kthread *__to_kthread(struct task_struct *p) return kthread; } +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) +{ + struct kthread *kthread = to_kthread(tsk); + + if (!kthread || !kthread->full_name) { + __get_task_comm(buf, buf_size, tsk); + return; + } + + strscpy_pad(buf, kthread->full_name, buf_size); +} + void set_kthread_struct(struct task_struct *p) { struct kthread *kthread; @@ -118,9 +132,13 @@ void free_kthread_struct(struct task_struct *k) * or if kmalloc() in kthread() failed. */ kthread = to_kthread(k); + if (!kthread) + return; + #ifdef CONFIG_BLK_CGROUP - WARN_ON_ONCE(kthread && kthread->blkcg_css); + WARN_ON_ONCE(kthread->blkcg_css); #endif + kfree(kthread->full_name); kfree(kthread); } @@ -406,12 +424,22 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), task = create->result; if (!IS_ERR(task)) { char name[TASK_COMM_LEN]; + va_list aq; + int len; /* * task is already visible to other tasks, so updating * COMM must be protected. */ - vsnprintf(name, sizeof(name), namefmt, args); + va_copy(aq, args); + len = vsnprintf(name, sizeof(name), namefmt, aq); + va_end(aq); + if (len >= TASK_COMM_LEN) { + struct kthread *kthread = to_kthread(task); + + /* leave it truncated when out of memory. */ + kthread->full_name = kvasprintf(GFP_KERNEL, namefmt, args); + } set_task_comm(task, name); } kfree(create); -- cgit v1.2.3 From 0425473037db40d9e322631f2d4dc6ef51f97e88 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 19 Jan 2022 18:08:56 -0800 Subject: list: introduce list_is_head() helper and re-use it in list.h Introduce list_is_head() in the similar (*) way as it's done for list_entry_is_head(). Make use of it in the list.h. *) it's done as inliner and not a macro to be aligned with other list_is_*() APIs; while at it, make all three to have the same style. Link: https://lkml.kernel.org/r/20211201141824.81400-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Cc: Heikki Krogerus Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list.h | 36 ++++++++++++++++++++++-------------- 1 file changed, 22 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/list.h b/include/linux/list.h index 6636fc07f918..dd6c2041d09c 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -258,8 +258,7 @@ static inline void list_bulk_move_tail(struct list_head *head, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_first(const struct list_head *list, - const struct list_head *head) +static inline int list_is_first(const struct list_head *list, const struct list_head *head) { return list->prev == head; } @@ -269,12 +268,21 @@ static inline int list_is_first(const struct list_head *list, * @list: the entry to test * @head: the head of the list */ -static inline int list_is_last(const struct list_head *list, - const struct list_head *head) +static inline int list_is_last(const struct list_head *list, const struct list_head *head) { return list->next == head; } +/** + * list_is_head - tests whether @list is the list @head + * @list: the entry to test + * @head: the head of the list + */ +static inline int list_is_head(const struct list_head *list, const struct list_head *head) +{ + return list == head; +} + /** * list_empty - tests whether a list is empty * @head: the list to test. @@ -318,7 +326,7 @@ static inline void list_del_init_careful(struct list_head *entry) static inline int list_empty_careful(const struct list_head *head) { struct list_head *next = smp_load_acquire(&head->next); - return (next == head) && (next == head->prev); + return list_is_head(next, head) && (next == head->prev); } /** @@ -393,10 +401,9 @@ static inline void list_cut_position(struct list_head *list, { if (list_empty(head)) return; - if (list_is_singular(head) && - (head->next != entry && head != entry)) + if (list_is_singular(head) && !list_is_head(entry, head) && (entry != head->next)) return; - if (entry == head) + if (list_is_head(entry, head)) INIT_LIST_HEAD(list); else __list_cut_position(list, head, entry); @@ -570,7 +577,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each(pos, head) \ - for (pos = (head)->next; pos != (head); pos = pos->next) + for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_continue - continue iteration over a list @@ -580,7 +587,7 @@ static inline void list_splice_tail_init(struct list_head *list, * Continue to iterate over a list, continuing after the current position. */ #define list_for_each_continue(pos, head) \ - for (pos = pos->next; pos != (head); pos = pos->next) + for (pos = pos->next; !list_is_head(pos, (head)); pos = pos->next) /** * list_for_each_prev - iterate over a list backwards @@ -588,7 +595,7 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_prev(pos, head) \ - for (pos = (head)->prev; pos != (head); pos = pos->prev) + for (pos = (head)->prev; !list_is_head(pos, (head)); pos = pos->prev) /** * list_for_each_safe - iterate over a list safe against removal of list entry @@ -597,8 +604,9 @@ static inline void list_splice_tail_init(struct list_head *list, * @head: the head for your list. */ #define list_for_each_safe(pos, n, head) \ - for (pos = (head)->next, n = pos->next; pos != (head); \ - pos = n, n = pos->next) + for (pos = (head)->next, n = pos->next; \ + !list_is_head(pos, (head)); \ + pos = n, n = pos->next) /** * list_for_each_prev_safe - iterate over a list backwards safe against removal of list entry @@ -608,7 +616,7 @@ static inline void list_splice_tail_init(struct list_head *list, */ #define list_for_each_prev_safe(pos, n, head) \ for (pos = (head)->prev, n = pos->prev; \ - pos != (head); \ + !list_is_head(pos, (head)); \ pos = n, n = pos->prev) /** -- cgit v1.2.3 From fd0a1462405b087377e59b84e119fe7e2d08499a Mon Sep 17 00:00:00 2001 From: Isabella Basso Date: Wed, 19 Jan 2022 18:09:02 -0800 Subject: hash.h: remove unused define directive MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "test_hash.c: refactor into KUnit", v3. We refactored the lib/test_hash.c file into KUnit as part of the student group LKCAMP [1] introductory hackathon for kernel development. This test was pointed to our group by Daniel Latypov [2], so its full conversion into a pure KUnit test was our goal in this patch series, but we ran into many problems relating to it not being split as unit tests, which complicated matters a bit, as the reasoning behind the original tests is quite cryptic for those unfamiliar with hash implementations. Some interesting developments we'd like to highlight are: - In patch 1/5 we noticed that there was an unused define directive that could be removed. - In patch 4/5 we noticed how stringhash and hash tests are all under the lib/test_hash.c file, which might cause some confusion, and we also broke those kernel config entries up. Overall KUnit developments have been made in the other patches in this series: In patches 2/5, 3/5 and 5/5 we refactored the lib/test_hash.c file so as to make it more compatible with the KUnit style, whilst preserving the original idea of the maintainer who designed it (i.e. George Spelvin), which might be undesirable for unit tests, but we assume it is enough for a first patch. This patch (of 5): Currently, there exist hash_32() and __hash_32() functions, which were introduced in a patch [1] targeting architecture specific optimizations. These functions can be overridden on a per-architecture basis to achieve such optimizations. They must set their corresponding define directive (HAVE_ARCH_HASH_32 and HAVE_ARCH__HASH_32, respectively) so that header files can deal with these overrides properly. As the supported 32-bit architectures that have their own hash function implementation (i.e. m68k, Microblaze, H8/300, pa-risc) have only been making use of the (more general) __hash_32() function (which only lacks a right shift operation when compared to the hash_32() function), remove the define directive corresponding to the arch-specific hash_32() implementation. [1] https://lore.kernel.org/lkml/20160525073311.5600.qmail@ns.sciencehorizons.net/ [akpm@linux-foundation.org: hash_32_generic() becomes hash_32()] Link: https://lkml.kernel.org/r/20211208183711.390454-1-isabbasso@riseup.net Link: https://lkml.kernel.org/r/20211208183711.390454-2-isabbasso@riseup.net Reviewed-by: David Gow Tested-by: David Gow Co-developed-by: Augusto Durães Camargo Signed-off-by: Augusto Durães Camargo Co-developed-by: Enzo Ferreira Signed-off-by: Enzo Ferreira Signed-off-by: Isabella Basso Cc: Geert Uytterhoeven Cc: Brendan Higgins Cc: Daniel Latypov Cc: Shuah Khan Cc: Rodrigo Siqueira Cc: kernel test robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/sw/rxe/rxe_qp.c | 3 +-- include/linux/hash.h | 5 +---- lib/test_hash.c | 24 +----------------------- tools/include/linux/hash.h | 5 +---- 4 files changed, 4 insertions(+), 33 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 54b8711321c1..44c9ea601bff 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -217,8 +217,7 @@ static int rxe_qp_init_req(struct rxe_dev *rxe, struct rxe_qp *qp, * the port number must be in the Dynamic Ports range * (0xc000 - 0xffff). */ - qp->src_port = RXE_ROCE_V2_SPORT + - (hash_32_generic(qp_num(qp), 14) & 0x3fff); + qp->src_port = RXE_ROCE_V2_SPORT + (hash_32(qp_num(qp), 14) & 0x3fff); qp->sq.max_wr = init->cap.max_send_wr; /* These caps are limited by rxe_qp_chk_cap() done by the caller */ diff --git a/include/linux/hash.h b/include/linux/hash.h index ad6fa21d977b..38edaa08f862 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val) return val * GOLDEN_RATIO_32; } -#ifndef HAVE_ARCH_HASH_32 -#define hash_32 hash_32_generic -#endif -static inline u32 hash_32_generic(u32 val, unsigned int bits) +static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); diff --git a/lib/test_hash.c b/lib/test_hash.c index 0ee40b4a56dd..d4b0cfdb0377 100644 --- a/lib/test_hash.c +++ b/lib/test_hash.c @@ -94,22 +94,7 @@ test_int_hash(unsigned long long h64, u32 hash_or[2][33]) pr_err("hash_32(%#x, %d) = %#x > %#x", h0, k, h1, m); return false; } -#ifdef HAVE_ARCH_HASH_32 - h2 = hash_32_generic(h0, k); -#if HAVE_ARCH_HASH_32 == 1 - if (h1 != h2) { - pr_err("hash_32(%#x, %d) = %#x != hash_32_generic() " - " = %#x", h0, k, h1, h2); - return false; - } -#else - if (h2 > m) { - pr_err("hash_32_generic(%#x, %d) = %#x > %#x", - h0, k, h1, m); - return false; - } -#endif -#endif + /* Test hash_64 */ hash_or[1][k] |= h1 = hash_64(h64, k); if (h1 > m) { @@ -227,13 +212,6 @@ test_hash_init(void) #else pr_info("__hash_32() has no arch implementation to test."); #endif -#ifdef HAVE_ARCH_HASH_32 -#if HAVE_ARCH_HASH_32 != 1 - pr_info("hash_32() is arch-specific; not compared to generic."); -#endif -#else - pr_info("hash_32() has no arch implementation to test."); -#endif #ifdef HAVE_ARCH_HASH_64 #if HAVE_ARCH_HASH_64 != 1 pr_info("hash_64() is arch-specific; not compared to generic."); diff --git a/tools/include/linux/hash.h b/tools/include/linux/hash.h index ad6fa21d977b..38edaa08f862 100644 --- a/tools/include/linux/hash.h +++ b/tools/include/linux/hash.h @@ -62,10 +62,7 @@ static inline u32 __hash_32_generic(u32 val) return val * GOLDEN_RATIO_32; } -#ifndef HAVE_ARCH_HASH_32 -#define hash_32 hash_32_generic -#endif -static inline u32 hash_32_generic(u32 val, unsigned int bits) +static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); -- cgit v1.2.3 From a3d5dc908a5f572ce3e31fe83fd2459a1c3c5422 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 19 Jan 2022 18:10:02 -0800 Subject: delayacct: support swapin delay accounting for swapping without blkio Currently delayacct accounts swapin delay only for swapping that cause blkio. If we use zram for swapping, tools/accounting/getdelays can't get any SWAP delay. It's useful to get zram swapin delay information, for example to adjust compress algorithm or /proc/sys/vm/swappiness. Reference to PSI, it accounts any kind of swapping by doing its work in swap_readpage(), no matter whether swapping causes blkio. Let delayacct do the similar work. Link: https://lkml.kernel.org/r/20211112083813.8559-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Reported-by: Zeal Robot Cc: Balbir Singh Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 44 ++++++++++++++++++++++---------------------- kernel/delayacct.c | 33 ++++++++++++++++++--------------- mm/memory.c | 4 ---- mm/page_io.c | 3 +++ 4 files changed, 43 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index af7e6eb50283..b96d68f310a2 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -9,14 +9,6 @@ #include -/* - * Per-task flags relevant to delay accounting - * maintained privately to avoid exhausting similar flags in sched.h:PF_* - * Used to set current->delays->flags - */ -#define DELAYACCT_PF_SWAPIN 0x00000001 /* I am doing a swapin */ -#define DELAYACCT_PF_BLKIO 0x00000002 /* I am waiting on IO */ - #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; @@ -37,13 +29,13 @@ struct task_delay_info { * associated with the operation is added to XXX_delay. * XXX_delay contains the accumulated delay time in nanoseconds. */ - u64 blkio_start; /* Shared by blkio, swapin */ + u64 blkio_start; u64 blkio_delay; /* wait for sync block io completion */ - u64 swapin_delay; /* wait for swapin block io completion */ + u64 swapin_start; + u64 swapin_delay; /* wait for swapin */ u32 blkio_count; /* total count of the number of sync block */ /* io operations performed */ - u32 swapin_count; /* total count of the number of swapin block */ - /* io operations performed */ + u32 swapin_count; /* total count of swapin */ u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ @@ -79,14 +71,8 @@ extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); - -static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) -{ - if (p->delays) - return (p->delays->flags & DELAYACCT_PF_BLKIO); - else - return 0; -} +extern void __delayacct_swapin_start(void); +extern void __delayacct_swapin_end(void); static inline void delayacct_set_flag(struct task_struct *p, int flag) { @@ -123,7 +109,6 @@ static inline void delayacct_blkio_start(void) if (!static_branch_unlikely(&delayacct_key)) return; - delayacct_set_flag(current, DELAYACCT_PF_BLKIO); if (current->delays) __delayacct_blkio_start(); } @@ -135,7 +120,6 @@ static inline void delayacct_blkio_end(struct task_struct *p) if (p->delays) __delayacct_blkio_end(p); - delayacct_clear_flag(p, DELAYACCT_PF_BLKIO); } static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) @@ -169,6 +153,18 @@ static inline void delayacct_thrashing_end(void) __delayacct_thrashing_end(); } +static inline void delayacct_swapin_start(void) +{ + if (current->delays) + __delayacct_swapin_start(); +} + +static inline void delayacct_swapin_end(void) +{ + if (current->delays) + __delayacct_swapin_end(); +} + #else static inline void delayacct_set_flag(struct task_struct *p, int flag) {} @@ -199,6 +195,10 @@ static inline void delayacct_thrashing_start(void) {} static inline void delayacct_thrashing_end(void) {} +static inline void delayacct_swapin_start(void) +{} +static inline void delayacct_swapin_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 51530d5b15a8..97699848c1f0 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -100,19 +100,10 @@ void __delayacct_blkio_start(void) */ void __delayacct_blkio_end(struct task_struct *p) { - struct task_delay_info *delays = p->delays; - u64 *total; - u32 *count; - - if (p->delays->flags & DELAYACCT_PF_SWAPIN) { - total = &delays->swapin_delay; - count = &delays->swapin_count; - } else { - total = &delays->blkio_delay; - count = &delays->blkio_count; - } - - delayacct_end(&delays->lock, &delays->blkio_start, total, count); + delayacct_end(&p->delays->lock, + &p->delays->blkio_start, + &p->delays->blkio_delay, + &p->delays->blkio_count); } int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) @@ -179,8 +170,7 @@ __u64 __delayacct_blkio_ticks(struct task_struct *tsk) unsigned long flags; raw_spin_lock_irqsave(&tsk->delays->lock, flags); - ret = nsec_to_clock_t(tsk->delays->blkio_delay + - tsk->delays->swapin_delay); + ret = nsec_to_clock_t(tsk->delays->blkio_delay); raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return ret; } @@ -210,3 +200,16 @@ void __delayacct_thrashing_end(void) ¤t->delays->thrashing_delay, ¤t->delays->thrashing_count); } + +void __delayacct_swapin_start(void) +{ + current->delays->swapin_start = local_clock(); +} + +void __delayacct_swapin_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->swapin_start, + ¤t->delays->swapin_delay, + ¤t->delays->swapin_count); +} diff --git a/mm/memory.c b/mm/memory.c index 8f1de811a1dc..ced3274c3deb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3507,7 +3507,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) if (unlikely(!si)) goto out; - delayacct_set_flag(current, DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry, vma, vmf->address); swapcache = page; @@ -3555,7 +3554,6 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) vmf->address, &vmf->ptl); if (likely(pte_same(*vmf->pte, vmf->orig_pte))) ret = VM_FAULT_OOM; - delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto unlock; } @@ -3569,13 +3567,11 @@ vm_fault_t do_swap_page(struct vm_fault *vmf) * owner processes (which may be unknown at hwpoison time) */ ret = VM_FAULT_HWPOISON; - delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); goto out_release; } locked = lock_page_or_retry(page, vma->vm_mm, vmf->flags); - delayacct_clear_flag(current, DELAYACCT_PF_SWAPIN); if (!locked) { ret |= VM_FAULT_RETRY; goto out_release; diff --git a/mm/page_io.c b/mm/page_io.c index 9725c7e1eeea..0bf8e40f4e57 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -25,6 +25,7 @@ #include #include #include +#include void end_swap_bio_write(struct bio *bio) { @@ -370,6 +371,7 @@ int swap_readpage(struct page *page, bool synchronous) * significant part of overall IO time. */ psi_memstall_enter(&pflags); + delayacct_swapin_start(); if (frontswap_load(page) == 0) { SetPageUptodate(page); @@ -432,6 +434,7 @@ int swap_readpage(struct page *page, bool synchronous) out: psi_memstall_leave(&pflags); + delayacct_swapin_end(); return ret; } -- cgit v1.2.3 From 82065b7266899fbdce4c7394d7dd02688161f0cf Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 19 Jan 2022 18:10:06 -0800 Subject: delayacct: fix incomplete disable operation when switch enable to disable When a task is created after delayacct is enabled, kernel will do all the delay accountings for that task. The problems is if user disables delayacct by set /proc/sys/kernel/task_delayacct to zero, only blkio delay accounting is disabled. Now disable all the kinds of delay accountings when /proc/sys/kernel/task_delayacct sets to zero. Link: https://lkml.kernel.org/r/20211123140342.32962-1-ran.xiaokai@zte.com.cn Signed-off-by: Yang Yang Reported-by: Zeal Robot Cc: Balbir Singh Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index b96d68f310a2..c675cfb6437e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -131,36 +131,54 @@ static inline __u64 delayacct_blkio_ticks(struct task_struct *tsk) static inline void delayacct_freepages_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_start(); } static inline void delayacct_freepages_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_freepages_end(); } static inline void delayacct_thrashing_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_thrashing_start(); } static inline void delayacct_thrashing_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_thrashing_end(); } static inline void delayacct_swapin_start(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_swapin_start(); } static inline void delayacct_swapin_end(void) { + if (!static_branch_unlikely(&delayacct_key)) + return; + if (current->delays) __delayacct_swapin_end(); } -- cgit v1.2.3 From 1193829da1a6728249cd02577a020bd64fd9c160 Mon Sep 17 00:00:00 2001 From: Yang Yang Date: Wed, 19 Jan 2022 18:10:09 -0800 Subject: delayacct: cleanup flags in struct task_delay_info and functions use it Flags in struct task_delay_info is used to distinguish the difference between swapin and blkio delay acountings. But after patch "delayacct: support swapin delay accounting for swapping without blkio", there is no need to do that since swapin and blkio delay accounting use their own functions. Link: https://lkml.kernel.org/r/20211124065958.36703-1-yang.yang29@zte.com.cn Signed-off-by: Yang Yang Cc: Balbir Singh Cc: Ingo Molnar Cc: Johannes Weiner Cc: Peter Zijlstra Cc: Zeal Robot Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 17 ----------------- 1 file changed, 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index c675cfb6437e..435c3654a0ff 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -12,7 +12,6 @@ #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info { raw_spinlock_t lock; - unsigned int flags; /* Private per-task flags */ /* For each stat XXX, add following, aligned appropriately * @@ -74,18 +73,6 @@ extern void __delayacct_thrashing_end(void); extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags |= flag; -} - -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{ - if (p->delays) - p->delays->flags &= ~flag; -} - static inline void delayacct_tsk_init(struct task_struct *tsk) { /* reinitialize in case parent's non-null pointer was dup'ed*/ @@ -184,10 +171,6 @@ static inline void delayacct_swapin_end(void) } #else -static inline void delayacct_set_flag(struct task_struct *p, int flag) -{} -static inline void delayacct_clear_flag(struct task_struct *p, int flag) -{} static inline void delayacct_init(void) {} static inline void delayacct_tsk_init(struct task_struct *tsk) -- cgit v1.2.3 From 5bf18281534451bf1ad56a45a3085cd7ad46860d Mon Sep 17 00:00:00 2001 From: wangyong Date: Wed, 19 Jan 2022 18:10:15 -0800 Subject: delayacct: track delays from memory compact Delay accounting does not track the delay of memory compact. When there is not enough free memory, tasks can spend a amount of their time waiting for compact. To get the impact of tasks in direct memory compact, measure the delay when allocating memory through memory compact. Also update tools/accounting/getdelays.c: / # ./getdelays_next -di -p 304 print delayacct stats ON printing IO accounting PID 304 CPU count real total virtual total delay total delay average 277 780000000 849039485 18877296 0.068ms IO count delay total delay average 0 0 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 5 11088812685 2217ms THRASHING count delay total delay average 0 0 0ms COMPACT count delay total delay average 3 72758 0ms watch: read=0, write=0, cancelled_write=0 Link: https://lkml.kernel.org/r/1638619795-71451-1-git-send-email-wang.yong12@zte.com.cn Signed-off-by: wangyong Reviewed-by: Jiang Xuexin Reviewed-by: Zhang Wenya Reviewed-by: Yang Yang Reviewed-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 28 ++++++++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 16 ++++++++++++++++ mm/page_alloc.c | 3 +++ tools/accounting/getdelays.c | 8 +++++++- 5 files changed, 59 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 435c3654a0ff..3e03d010bd2e 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -42,8 +42,12 @@ struct task_delay_info { u64 thrashing_start; u64 thrashing_delay; /* wait for thrashing page */ + u64 compact_start; + u64 compact_delay; /* wait for memory compact */ + u32 freepages_count; /* total count of memory reclaim */ u32 thrashing_count; /* total count of thrash waits */ + u32 compact_count; /* total count of memory compact */ }; #endif @@ -72,6 +76,8 @@ extern void __delayacct_thrashing_start(void); extern void __delayacct_thrashing_end(void); extern void __delayacct_swapin_start(void); extern void __delayacct_swapin_end(void); +extern void __delayacct_compact_start(void); +extern void __delayacct_compact_end(void); static inline void delayacct_tsk_init(struct task_struct *tsk) { @@ -170,6 +176,24 @@ static inline void delayacct_swapin_end(void) __delayacct_swapin_end(); } +static inline void delayacct_compact_start(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_start(); +} + +static inline void delayacct_compact_end(void) +{ + if (!static_branch_unlikely(&delayacct_key)) + return; + + if (current->delays) + __delayacct_compact_end(); +} + #else static inline void delayacct_init(void) {} @@ -200,6 +224,10 @@ static inline void delayacct_swapin_start(void) {} static inline void delayacct_swapin_end(void) {} +static inline void delayacct_compact_start(void) +{} +static inline void delayacct_compact_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index ccbd08709321..12327d32378f 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 10 +#define TASKSTATS_VERSION 11 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -172,6 +172,10 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ + + /* Delay waiting for memory compact */ + __u64 compact_count; + __u64 compact_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index 97699848c1f0..c5e8cea9e05f 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -155,10 +155,13 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; + tmp = d->compact_delay_total + tsk->delays->compact_delay; + d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; d->thrashing_count += tsk->delays->thrashing_count; + d->compact_count += tsk->delays->compact_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -213,3 +216,16 @@ void __delayacct_swapin_end(void) ¤t->delays->swapin_delay, ¤t->delays->swapin_count); } + +void __delayacct_compact_start(void) +{ + current->delays->compact_start = local_clock(); +} + +void __delayacct_compact_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->compact_start, + ¤t->delays->compact_delay, + ¤t->delays->compact_count); +} diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c5952749ad40..635063f49671 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -72,6 +72,7 @@ #include #include #include +#include #include #include #include @@ -4348,6 +4349,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; psi_memstall_enter(&pflags); + delayacct_compact_start(); noreclaim_flag = memalloc_noreclaim_save(); *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, @@ -4355,6 +4357,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, memalloc_noreclaim_restore(noreclaim_flag); psi_memstall_leave(&pflags); + delayacct_compact_end(); if (*compact_result == COMPACT_SKIPPED) return NULL; diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 5ef1c15e88ad..11e86739456d 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -205,6 +205,8 @@ static void print_delayacct(struct taskstats *t) "RECLAIM %12s%15s%15s\n" " %15llu%15llu%15llums\n" "THRASHING%12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "COMPACT %12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -228,7 +230,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->thrashing_count, (unsigned long long)t->thrashing_delay_total, - average_ms(t->thrashing_delay_total, t->thrashing_count)); + average_ms(t->thrashing_delay_total, t->thrashing_count), + "count", "delay total", "delay average", + (unsigned long long)t->compact_count, + (unsigned long long)t->compact_delay_total, + average_ms(t->compact_delay_total, t->compact_count)); } static void task_context_switch_counts(struct taskstats *t) -- cgit v1.2.3 From 47934e06b65637c88a762d9c98329ae6e3238888 Mon Sep 17 00:00:00 2001 From: Congyu Liu Date: Tue, 18 Jan 2022 14:20:13 -0500 Subject: net: fix information leakage in /proc/net/ptype In one net namespace, after creating a packet socket without binding it to a device, users in other net namespaces can observe the new `packet_type` added by this packet socket by reading `/proc/net/ptype` file. This is minor information leakage as packet socket is namespace aware. Add a net pointer in `packet_type` to keep the net namespace of of corresponding packet socket. In `ptype_seq_show`, this net pointer must be checked when it is not NULL. Fixes: 2feb27dbe00c ("[NETNS]: Minor information leak via /proc/net/ptype file.") Signed-off-by: Congyu Liu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + net/core/net-procfs.c | 3 ++- net/packet/af_packet.c | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 3213c7227b59..e490b84732d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2548,6 +2548,7 @@ struct packet_type { struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); + struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index d8b9dbabd4a4..5b8016335aca 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -260,7 +260,8 @@ static int ptype_seq_show(struct seq_file *seq, void *v) if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); - else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { + else if ((!pt->af_packet_net || net_eq(pt->af_packet_net, seq_file_net(seq))) && + (!pt->dev || net_eq(dev_net(pt->dev), seq_file_net(seq)))) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5bd409ab4cc2..85ea7ddb48db 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1774,6 +1774,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; + match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; list_add(&match->list, &fanout_list); @@ -3353,6 +3354,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; + po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; -- cgit v1.2.3 From e2f08207c558bc0bc8abaa557cdb29bad776ac7b Mon Sep 17 00:00:00 2001 From: Moshe Tal Date: Thu, 20 Jan 2022 11:55:50 +0200 Subject: ethtool: Fix link extended state for big endian The link extended sub-states are assigned as enum that is an integer size but read from a union as u8, this is working for small values on little endian systems but for big endian this always give 0. Fix the variable in the union to match the enum size. Fixes: ecc31c60240b ("ethtool: Add link extended state") Signed-off-by: Moshe Tal Reviewed-by: Ido Schimmel Tested-by: Ido Schimmel Reviewed-by: Gal Pressman Reviewed-by: Amit Cohen Signed-off-by: David S. Miller --- include/linux/ethtool.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index a26f37a27167..11efc45de66a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -111,7 +111,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; enum ethtool_link_ext_substate_module module; - u8 __link_ext_substate; + u32 __link_ext_substate; }; }; -- cgit v1.2.3 From 66a8f7f04979f4ad739085f01d99c8caf620b4f5 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 18 Jan 2022 18:35:02 +0100 Subject: of: base: make small of_parse_phandle() variants static inline Make all the smaller variants of the of_parse_phandle() static inline. This also let us remove the empty function stubs if CONFIG_OF is not defined. Suggested-by: Rob Herring Signed-off-by: Michael Walle [robh: move index < 0 check into __of_parse_phandle_with_args] Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220118173504.2867523-2-michael@walle.cc --- drivers/of/base.c | 131 ++++------------------------------------------- include/linux/of.h | 148 +++++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 129 insertions(+), 150 deletions(-) (limited to 'include/linux') diff --git a/drivers/of/base.c b/drivers/of/base.c index 8a24d37153b4..e7d92b67cb8a 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1420,15 +1420,18 @@ int of_phandle_iterator_args(struct of_phandle_iterator *it, return count; } -static int __of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, - const char *cells_name, - int cell_count, int index, - struct of_phandle_args *out_args) +int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int cell_count, int index, + struct of_phandle_args *out_args) { struct of_phandle_iterator it; int rc, cur_index = 0; + if (index < 0) + return -EINVAL; + /* Loop over the phandles until all the requested entry is found */ of_for_each_phandle(&it, rc, np, list_name, cells_name, cell_count) { /* @@ -1471,82 +1474,7 @@ static int __of_parse_phandle_with_args(const struct device_node *np, of_node_put(it.node); return rc; } - -/** - * of_parse_phandle - Resolve a phandle property to a device_node pointer - * @np: Pointer to device node holding phandle property - * @phandle_name: Name of property holding a phandle value - * @index: For properties holding a table of phandles, this is the index into - * the table - * - * Return: The device_node pointer with refcount incremented. Use - * of_node_put() on it when done. - */ -struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, int index) -{ - struct of_phandle_args args; - - if (index < 0) - return NULL; - - if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0, - index, &args)) - return NULL; - - return args.np; -} -EXPORT_SYMBOL(of_parse_phandle); - -/** - * of_parse_phandle_with_args() - Find a node pointed by phandle in a list - * @np: pointer to a device tree node containing a list - * @list_name: property name that contains a list - * @cells_name: property name that specifies phandles' arguments count - * @index: index of a phandle to parse out - * @out_args: optional pointer to output arguments structure (will be filled) - * - * This function is useful to parse lists of phandles and their arguments. - * Returns 0 on success and fills out_args, on error returns appropriate - * errno value. - * - * Caller is responsible to call of_node_put() on the returned out_args->np - * pointer. - * - * Example:: - * - * phandle1: node1 { - * #list-cells = <2>; - * }; - * - * phandle2: node2 { - * #list-cells = <1>; - * }; - * - * node3 { - * list = <&phandle1 1 2 &phandle2 3>; - * }; - * - * To get a device_node of the ``node2`` node you may call this: - * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args); - */ -int of_parse_phandle_with_args(const struct device_node *np, const char *list_name, - const char *cells_name, int index, - struct of_phandle_args *out_args) -{ - int cell_count = -1; - - if (index < 0) - return -EINVAL; - - /* If cells_name is NULL we assume a cell count of 0 */ - if (!cells_name) - cell_count = 0; - - return __of_parse_phandle_with_args(np, list_name, cells_name, - cell_count, index, out_args); -} -EXPORT_SYMBOL(of_parse_phandle_with_args); +EXPORT_SYMBOL(__of_parse_phandle_with_args); /** * of_parse_phandle_with_args_map() - Find a node pointed by phandle in a list and remap it @@ -1732,47 +1660,6 @@ free: } EXPORT_SYMBOL(of_parse_phandle_with_args_map); -/** - * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list - * @np: pointer to a device tree node containing a list - * @list_name: property name that contains a list - * @cell_count: number of argument cells following the phandle - * @index: index of a phandle to parse out - * @out_args: optional pointer to output arguments structure (will be filled) - * - * This function is useful to parse lists of phandles and their arguments. - * Returns 0 on success and fills out_args, on error returns appropriate - * errno value. - * - * Caller is responsible to call of_node_put() on the returned out_args->np - * pointer. - * - * Example:: - * - * phandle1: node1 { - * }; - * - * phandle2: node2 { - * }; - * - * node3 { - * list = <&phandle1 0 2 &phandle2 2 3>; - * }; - * - * To get a device_node of the ``node2`` node you may call this: - * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args); - */ -int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cell_count, - int index, struct of_phandle_args *out_args) -{ - if (index < 0) - return -EINVAL; - return __of_parse_phandle_with_args(np, list_name, NULL, cell_count, - index, out_args); -} -EXPORT_SYMBOL(of_parse_phandle_with_fixed_args); - /** * of_count_phandle_with_args() - Find the number of phandles references in a property * @np: pointer to a device tree node containing a list diff --git a/include/linux/of.h b/include/linux/of.h index ff143a027abc..16d76c92fbe0 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -364,18 +364,12 @@ extern const struct of_device_id *of_match_node( const struct of_device_id *matches, const struct device_node *node); extern int of_modalias_node(struct device_node *node, char *modalias, int len); extern void of_print_phandle_args(const char *msg, const struct of_phandle_args *args); -extern struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, - int index); -extern int of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, const char *cells_name, int index, - struct of_phandle_args *out_args); +extern int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, const char *cells_name, int cell_count, + int index, struct of_phandle_args *out_args); extern int of_parse_phandle_with_args_map(const struct device_node *np, const char *list_name, const char *stem_name, int index, struct of_phandle_args *out_args); -extern int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cells_count, int index, - struct of_phandle_args *out_args); extern int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name); @@ -865,18 +859,12 @@ static inline int of_property_read_string_helper(const struct device_node *np, return -ENOSYS; } -static inline struct device_node *of_parse_phandle(const struct device_node *np, - const char *phandle_name, - int index) -{ - return NULL; -} - -static inline int of_parse_phandle_with_args(const struct device_node *np, - const char *list_name, - const char *cells_name, - int index, - struct of_phandle_args *out_args) +static inline int __of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int cell_count, + int index, + struct of_phandle_args *out_args) { return -ENOSYS; } @@ -890,13 +878,6 @@ static inline int of_parse_phandle_with_args_map(const struct device_node *np, return -ENOSYS; } -static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, - const char *list_name, int cells_count, int index, - struct of_phandle_args *out_args) -{ - return -ENOSYS; -} - static inline int of_count_phandle_with_args(const struct device_node *np, const char *list_name, const char *cells_name) @@ -1077,6 +1058,117 @@ static inline bool of_node_is_type(const struct device_node *np, const char *typ return np && match && type && !strcmp(match, type); } +/** + * of_parse_phandle - Resolve a phandle property to a device_node pointer + * @np: Pointer to device node holding phandle property + * @phandle_name: Name of property holding a phandle value + * @index: For properties holding a table of phandles, this is the index into + * the table + * + * Return: The device_node pointer with refcount incremented. Use + * of_node_put() on it when done. + */ +static inline struct device_node *of_parse_phandle(const struct device_node *np, + const char *phandle_name, + int index) +{ + struct of_phandle_args args; + + if (__of_parse_phandle_with_args(np, phandle_name, NULL, 0, + index, &args)) + return NULL; + + return args.np; +} + +/** + * of_parse_phandle_with_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cells_name: property name that specifies phandles' arguments count + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * This function is useful to parse lists of phandles and their arguments. + * Returns 0 on success and fills out_args, on error returns appropriate + * errno value. + * + * Caller is responsible to call of_node_put() on the returned out_args->np + * pointer. + * + * Example:: + * + * phandle1: node1 { + * #list-cells = <2>; + * }; + * + * phandle2: node2 { + * #list-cells = <1>; + * }; + * + * node3 { + * list = <&phandle1 1 2 &phandle2 3>; + * }; + * + * To get a device_node of the ``node2`` node you may call this: + * of_parse_phandle_with_args(node3, "list", "#list-cells", 1, &args); + */ +static inline int of_parse_phandle_with_args(const struct device_node *np, + const char *list_name, + const char *cells_name, + int index, + struct of_phandle_args *out_args) +{ + int cell_count = -1; + + /* If cells_name is NULL we assume a cell count of 0 */ + if (!cells_name) + cell_count = 0; + + return __of_parse_phandle_with_args(np, list_name, cells_name, + cell_count, index, out_args); +} + +/** + * of_parse_phandle_with_fixed_args() - Find a node pointed by phandle in a list + * @np: pointer to a device tree node containing a list + * @list_name: property name that contains a list + * @cell_count: number of argument cells following the phandle + * @index: index of a phandle to parse out + * @out_args: optional pointer to output arguments structure (will be filled) + * + * This function is useful to parse lists of phandles and their arguments. + * Returns 0 on success and fills out_args, on error returns appropriate + * errno value. + * + * Caller is responsible to call of_node_put() on the returned out_args->np + * pointer. + * + * Example:: + * + * phandle1: node1 { + * }; + * + * phandle2: node2 { + * }; + * + * node3 { + * list = <&phandle1 0 2 &phandle2 2 3>; + * }; + * + * To get a device_node of the ``node2`` node you may call this: + * of_parse_phandle_with_fixed_args(node3, "list", 2, 1, &args); + */ +static inline int of_parse_phandle_with_fixed_args(const struct device_node *np, + const char *list_name, + int cell_count, + int index, + struct of_phandle_args *out_args) +{ + return __of_parse_phandle_with_args(np, list_name, NULL, cell_count, + index, out_args); +} + /** * of_property_count_u8_elems - Count the number of u8 elements in a property * -- cgit v1.2.3 From 2ca42c3ad9ed875b136065b010753a4caaaa1d38 Mon Sep 17 00:00:00 2001 From: Michael Walle Date: Tue, 18 Jan 2022 18:35:03 +0100 Subject: of: property: define of_property_read_u{8,16,32,64}_array() unconditionally We can get rid of all the empty stubs because all these functions call of_property_read_variable_u{8,16,32,64}_array() which already have an empty stub if CONFIG_OF is not defined. Signed-off-by: Michael Walle Signed-off-by: Rob Herring Link: https://lore.kernel.org/r/20220118173504.2867523-3-michael@walle.cc --- include/linux/of.h | 274 ++++++++++++++++++++++++----------------------------- 1 file changed, 124 insertions(+), 150 deletions(-) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index 16d76c92fbe0..2dc77430a91a 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -410,130 +410,6 @@ extern int of_detach_node(struct device_node *); #define of_match_ptr(_ptr) (_ptr) -/** - * of_property_read_u8_array - Find and read an array of u8 from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 8-bit value(s) from - * it. - * - * dts entry of array should be like: - * ``property = /bits/ 8 <0x50 0x60 0x70>;`` - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u8 value can be decoded. - */ -static inline int of_property_read_u8_array(const struct device_node *np, - const char *propname, - u8 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u8_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u16_array - Find and read an array of u16 from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 16-bit value(s) from - * it. - * - * dts entry of array should be like: - * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;`` - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u16 value can be decoded. - */ -static inline int of_property_read_u16_array(const struct device_node *np, - const char *propname, - u16 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u16_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u32_array - Find and read an array of 32 bit integers - * from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 32-bit value(s) from - * it. - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u32 value can be decoded. - */ -static inline int of_property_read_u32_array(const struct device_node *np, - const char *propname, - u32 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u32_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - -/** - * of_property_read_u64_array - Find and read an array of 64 bit integers - * from a property. - * - * @np: device node from which the property value is to be read. - * @propname: name of the property to be searched. - * @out_values: pointer to return value, modified only if return value is 0. - * @sz: number of array elements to read - * - * Search for a property in a device node and read 64-bit value(s) from - * it. - * - * Return: 0 on success, -EINVAL if the property does not exist, - * -ENODATA if property does not have a value, and -EOVERFLOW if the - * property data isn't large enough. - * - * The out_values is modified only if a valid u64 value can be decoded. - */ -static inline int of_property_read_u64_array(const struct device_node *np, - const char *propname, - u64 *out_values, size_t sz) -{ - int ret = of_property_read_variable_u64_array(np, propname, out_values, - sz, 0); - if (ret >= 0) - return 0; - else - return ret; -} - /* * struct property *prop; * const __be32 *p; @@ -728,32 +604,6 @@ static inline int of_property_count_elems_of_size(const struct device_node *np, return -ENOSYS; } -static inline int of_property_read_u8_array(const struct device_node *np, - const char *propname, u8 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u16_array(const struct device_node *np, - const char *propname, u16 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u32_array(const struct device_node *np, - const char *propname, - u32 *out_values, size_t sz) -{ - return -ENOSYS; -} - -static inline int of_property_read_u64_array(const struct device_node *np, - const char *propname, - u64 *out_values, size_t sz) -{ - return -ENOSYS; -} - static inline int of_property_read_u32_index(const struct device_node *np, const char *propname, u32 index, u32 *out_value) { @@ -1328,6 +1178,130 @@ static inline bool of_property_read_bool(const struct device_node *np, return prop ? true : false; } +/** + * of_property_read_u8_array - Find and read an array of u8 from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 8-bit value(s) from + * it. + * + * dts entry of array should be like: + * ``property = /bits/ 8 <0x50 0x60 0x70>;`` + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u8 value can be decoded. + */ +static inline int of_property_read_u8_array(const struct device_node *np, + const char *propname, + u8 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u8_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u16_array - Find and read an array of u16 from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 16-bit value(s) from + * it. + * + * dts entry of array should be like: + * ``property = /bits/ 16 <0x5000 0x6000 0x7000>;`` + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u16 value can be decoded. + */ +static inline int of_property_read_u16_array(const struct device_node *np, + const char *propname, + u16 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u16_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u32_array - Find and read an array of 32 bit integers + * from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 32-bit value(s) from + * it. + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u32 value can be decoded. + */ +static inline int of_property_read_u32_array(const struct device_node *np, + const char *propname, + u32 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u32_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + +/** + * of_property_read_u64_array - Find and read an array of 64 bit integers + * from a property. + * + * @np: device node from which the property value is to be read. + * @propname: name of the property to be searched. + * @out_values: pointer to return value, modified only if return value is 0. + * @sz: number of array elements to read + * + * Search for a property in a device node and read 64-bit value(s) from + * it. + * + * Return: 0 on success, -EINVAL if the property does not exist, + * -ENODATA if property does not have a value, and -EOVERFLOW if the + * property data isn't large enough. + * + * The out_values is modified only if a valid u64 value can be decoded. + */ +static inline int of_property_read_u64_array(const struct device_node *np, + const char *propname, + u64 *out_values, size_t sz) +{ + int ret = of_property_read_variable_u64_array(np, propname, out_values, + sz, 0); + if (ret >= 0) + return 0; + else + return ret; +} + static inline int of_property_read_u8(const struct device_node *np, const char *propname, u8 *out_value) -- cgit v1.2.3 From 5298d4bfe80f6ae6ae2777bcd1357b0022d98573 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 18 Jan 2022 07:56:14 +0100 Subject: unicode: clean up the Kconfig symbol confusion Turn the CONFIG_UNICODE symbol into a tristate that generates some always built in code and remove the confusing CONFIG_UNICODE_UTF8_DATA symbol. Note that a lot of the IS_ENABLED() checks could be turned from cpp statements into normal ifs, but this change is intended to be fairly mechanic, so that should be cleaned up later. Fixes: 2b3d04787012 ("unicode: Add utf8-data module") Reported-by: Linus Torvalds Reviewed-by: Eric Biggers Signed-off-by: Christoph Hellwig Signed-off-by: Gabriel Krisman Bertazi --- fs/Makefile | 2 +- fs/ext4/ext4.h | 14 +++++++------- fs/ext4/hash.c | 2 +- fs/ext4/namei.c | 12 ++++++------ fs/ext4/super.c | 10 +++++----- fs/ext4/sysfs.c | 8 ++++---- fs/f2fs/dir.c | 10 +++++----- fs/f2fs/f2fs.h | 2 +- fs/f2fs/hash.c | 2 +- fs/f2fs/namei.c | 4 ++-- fs/f2fs/recovery.c | 4 ++-- fs/f2fs/super.c | 10 +++++----- fs/f2fs/sysfs.c | 10 +++++----- fs/libfs.c | 10 +++++----- fs/unicode/Kconfig | 18 +++++------------- fs/unicode/Makefile | 6 ++++-- include/linux/fs.h | 2 +- 17 files changed, 60 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/fs/Makefile b/fs/Makefile index 84c5e4cdfee5..c71ee0127866 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -94,7 +94,7 @@ obj-$(CONFIG_EXPORTFS) += exportfs/ obj-$(CONFIG_NFSD) += nfsd/ obj-$(CONFIG_LOCKD) += lockd/ obj-$(CONFIG_NLS) += nls/ -obj-$(CONFIG_UNICODE) += unicode/ +obj-y += unicode/ obj-$(CONFIG_SYSV_FS) += sysv/ obj-$(CONFIG_SMBFS_COMMON) += smbfs_common/ obj-$(CONFIG_CIFS) += cifs/ diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 71a3cdceaa03..242e74cfb060 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2485,7 +2485,7 @@ struct ext4_filename { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct fscrypt_str cf_name; #endif }; @@ -2721,7 +2721,7 @@ extern unsigned ext4_free_clusters_after_init(struct super_block *sb, struct ext4_group_desc *gdp); ext4_fsblk_t ext4_inode_to_goal_block(struct inode *); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname, struct ext4_filename *fname); @@ -2754,7 +2754,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif return err; @@ -2773,7 +2773,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, ext4_fname_from_fscrypt_name(fname, &name); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname); #endif return err; @@ -2790,7 +2790,7 @@ static inline void ext4_fname_free_filename(struct ext4_filename *fname) fname->usr_fname = NULL; fname->disk_name.name = NULL; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif @@ -2806,7 +2806,7 @@ static inline int ext4_fname_setup_filename(struct inode *dir, fname->disk_name.name = (unsigned char *) iname->name; fname->disk_name.len = iname->len; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) err = ext4_fname_setup_ci_filename(dir, iname, fname); #endif @@ -2822,7 +2822,7 @@ static inline int ext4_fname_prepare_lookup(struct inode *dir, static inline void ext4_fname_free_filename(struct ext4_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) kfree(fname->cf_name.name); fname->cf_name.name = NULL; #endif diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index f34f4176c1e7..147b5241dd94 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -290,7 +290,7 @@ static int __ext4fs_dirhash(const struct inode *dir, const char *name, int len, int ext4fs_dirhash(const struct inode *dir, const char *name, int len, struct dx_hash_info *hinfo) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) const struct unicode_map *um = dir->i_sb->s_encoding; int r, dlen; unsigned char *buff; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 52c9bd154122..269d2d051ede 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1317,7 +1317,7 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block) dx_set_count(entries, count + 1); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. If quick is set, assume the name being looked up @@ -1428,7 +1428,7 @@ static bool ext4_match(struct inode *parent, f.crypto_buf = fname->crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) && (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) { if (fname->cf_name.name) { @@ -1800,7 +1800,7 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi } } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -2308,7 +2308,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) && sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name)) return -EINVAL; @@ -3126,7 +3126,7 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry) ext4_fc_track_unlink(handle, dentry); retval = ext4_mark_inode_dirty(handle, dir); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the @@ -3231,7 +3231,7 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = __ext4_unlink(handle, dir, &dentry->d_name, d_inode(dentry)); if (!retval) ext4_fc_track_unlink(handle, dentry); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the diff --git a/fs/ext4/super.c b/fs/ext4/super.c index db9fe4843529..52be1ca38eef 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1302,7 +1302,7 @@ static void ext4_put_super(struct super_block *sb) kfree(sbi->s_blockgroup_lock); fs_put_dax(sbi->s_daxdev); fscrypt_free_dummy_policy(&sbi->s_dummy_enc_policy); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -1962,7 +1962,7 @@ static const struct mount_opts { {Opt_err, 0, 0} }; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct ext4_sb_encodings { __u16 magic; char *name; @@ -3609,7 +3609,7 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) return 0; } -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb)) { ext4_msg(sb, KERN_ERR, "Filesystem with casefold feature cannot be " @@ -4613,7 +4613,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) if (err < 0) goto failed_mount; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (ext4_has_feature_casefold(sb) && !sb->s_encoding) { const struct ext4_sb_encodings *encoding_info; struct unicode_map *encoding; @@ -5517,7 +5517,7 @@ failed_mount: if (sbi->s_chksum_driver) crypto_free_shash(sbi->s_chksum_driver); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index f61e65ae27d8..d233c24ea342 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -309,7 +309,7 @@ EXT4_ATTR_FEATURE(meta_bg_resize); EXT4_ATTR_FEATURE(encryption); EXT4_ATTR_FEATURE(test_dummy_encryption_v2); #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) EXT4_ATTR_FEATURE(casefold); #endif #ifdef CONFIG_FS_VERITY @@ -317,7 +317,7 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) EXT4_ATTR_FEATURE(encrypted_casefold); #endif @@ -329,7 +329,7 @@ static struct attribute *ext4_feat_attrs[] = { ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif #ifdef CONFIG_FS_VERITY @@ -337,7 +337,7 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), -#if defined(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) +#if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) ATTR_LIST(encrypted_casefold), #endif NULL, diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c index 1820e9c106f7..166f08623362 100644 --- a/fs/f2fs/dir.c +++ b/fs/f2fs/dir.c @@ -16,7 +16,7 @@ #include "xattr.h" #include -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern struct kmem_cache *f2fs_cf_name_slab; #endif @@ -79,7 +79,7 @@ unsigned char f2fs_get_de_type(struct f2fs_dir_entry *de) int f2fs_init_casefolded_name(const struct inode *dir, struct f2fs_filename *fname) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = dir->i_sb; if (IS_CASEFOLDED(dir)) { @@ -174,7 +174,7 @@ void f2fs_free_filename(struct f2fs_filename *fname) kfree(fname->crypto_buf.name); fname->crypto_buf.name = NULL; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (fname->cf_name.name) { kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name); fname->cf_name.name = NULL; @@ -208,7 +208,7 @@ static struct f2fs_dir_entry *find_in_block(struct inode *dir, return f2fs_find_target_dentry(&d, fname, max_slots); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Test whether a case-insensitive directory entry matches the filename * being searched for. @@ -266,7 +266,7 @@ static inline int f2fs_match_name(const struct inode *dir, { struct fscrypt_name f; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (fname->cf_name.name) { struct qstr cf = FSTR_TO_QSTR(&fname->cf_name); diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index d0d603187171..4da88928ffb5 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -487,7 +487,7 @@ struct f2fs_filename { */ struct fscrypt_str crypto_buf; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * For casefolded directories: the casefolded name, but it's left NULL * if the original name is not valid Unicode, if the directory is both diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c index e3beac546c63..3cb1e7a24740 100644 --- a/fs/f2fs/hash.c +++ b/fs/f2fs/hash.c @@ -105,7 +105,7 @@ void f2fs_hash_filename(const struct inode *dir, struct f2fs_filename *fname) return; } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (IS_CASEFOLDED(dir)) { /* * If the casefolded name is provided, hash it instead of the diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index a728a0af9ce0..5f213f05556d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -561,7 +561,7 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry, goto out_iput; } out_splice: -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (!inode && IS_CASEFOLDED(dir)) { /* Eventually we want to call d_add_ci(dentry, NULL) * for negative dentries in the encoding case as @@ -622,7 +622,7 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry) goto fail; } f2fs_delete_entry(de, page, dir, inode); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* VFS negative dentries are incompatible with Encoding and * Case-insensitiveness. Eventually we'll want avoid * invalidating the dentries here, alongside with returning the diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c index d1664a0567ef..2fbbc820c00a 100644 --- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -46,7 +46,7 @@ static struct kmem_cache *fsync_entry_slab; -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) extern struct kmem_cache *f2fs_cf_name_slab; #endif @@ -149,7 +149,7 @@ static int init_recovered_filename(const struct inode *dir, if (err) return err; f2fs_hash_filename(dir, fname); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* Case-sensitive match is fine for recovery */ kmem_cache_free(f2fs_cf_name_slab, fname->cf_name.name); fname->cf_name.name = NULL; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 15f12ece0ac6..b870c6459fa1 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -256,7 +256,7 @@ void f2fs_printk(struct f2fs_sb_info *sbi, const char *fmt, ...) va_end(args); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) static const struct f2fs_sb_encodings { __u16 magic; char *name; @@ -1218,7 +1218,7 @@ default_check: return -EINVAL; } #endif -#ifndef CONFIG_UNICODE +#if !IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi)) { f2fs_err(sbi, "Filesystem with casefold feature cannot be mounted without CONFIG_UNICODE"); @@ -1578,7 +1578,7 @@ static void f2fs_put_super(struct super_block *sb) f2fs_destroy_iostat(sbi); for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); #endif kfree(sbi); @@ -3861,7 +3861,7 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi) static int f2fs_setup_casefold(struct f2fs_sb_info *sbi) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (f2fs_sb_has_casefold(sbi) && !sbi->sb->s_encoding) { const struct f2fs_sb_encodings *encoding_info; struct unicode_map *encoding; @@ -4412,7 +4412,7 @@ free_bio_info: for (i = 0; i < NR_PAGE_TYPE; i++) kvfree(sbi->write_io[i]); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) utf8_unload(sb->s_encoding); sb->s_encoding = NULL; #endif diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c index 8408f77764e8..fa3d9cb2d69b 100644 --- a/fs/f2fs/sysfs.c +++ b/fs/f2fs/sysfs.c @@ -192,7 +192,7 @@ static ssize_t unusable_show(struct f2fs_attr *a, static ssize_t encoding_show(struct f2fs_attr *a, struct f2fs_sb_info *sbi, char *buf) { -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct super_block *sb = sbi->sb; if (f2fs_sb_has_casefold(sbi)) @@ -756,7 +756,7 @@ F2FS_GENERAL_RO_ATTR(avg_vblocks); #ifdef CONFIG_FS_ENCRYPTION F2FS_FEATURE_RO_ATTR(encryption); F2FS_FEATURE_RO_ATTR(test_dummy_encryption_v2); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(encrypted_casefold); #endif #endif /* CONFIG_FS_ENCRYPTION */ @@ -775,7 +775,7 @@ F2FS_FEATURE_RO_ATTR(lost_found); F2FS_FEATURE_RO_ATTR(verity); #endif F2FS_FEATURE_RO_ATTR(sb_checksum); -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) F2FS_FEATURE_RO_ATTR(casefold); #endif F2FS_FEATURE_RO_ATTR(readonly); @@ -886,7 +886,7 @@ static struct attribute *f2fs_feat_attrs[] = { #ifdef CONFIG_FS_ENCRYPTION ATTR_LIST(encryption), ATTR_LIST(test_dummy_encryption_v2), -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(encrypted_casefold), #endif #endif /* CONFIG_FS_ENCRYPTION */ @@ -905,7 +905,7 @@ static struct attribute *f2fs_feat_attrs[] = { ATTR_LIST(verity), #endif ATTR_LIST(sb_checksum), -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) ATTR_LIST(casefold), #endif ATTR_LIST(readonly), diff --git a/fs/libfs.c b/fs/libfs.c index ba7438ab9371..974125270a42 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -1379,7 +1379,7 @@ bool is_empty_dir_inode(struct inode *inode) (inode->i_op == &empty_dir_inode_operations); } -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) /* * Determine if the name of a dentry should be casefolded. * @@ -1473,7 +1473,7 @@ static const struct dentry_operations generic_encrypted_dentry_ops = { }; #endif -#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE) +#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) static const struct dentry_operations generic_encrypted_ci_dentry_ops = { .d_hash = generic_ci_d_hash, .d_compare = generic_ci_d_compare, @@ -1508,10 +1508,10 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) #ifdef CONFIG_FS_ENCRYPTION bool needs_encrypt_ops = dentry->d_flags & DCACHE_NOKEY_NAME; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) bool needs_ci_ops = dentry->d_sb->s_encoding; #endif -#if defined(CONFIG_FS_ENCRYPTION) && defined(CONFIG_UNICODE) +#if defined(CONFIG_FS_ENCRYPTION) && IS_ENABLED(CONFIG_UNICODE) if (needs_encrypt_ops && needs_ci_ops) { d_set_d_op(dentry, &generic_encrypted_ci_dentry_ops); return; @@ -1523,7 +1523,7 @@ void generic_set_encrypted_ci_d_ops(struct dentry *dentry) return; } #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) if (needs_ci_ops) { d_set_d_op(dentry, &generic_ci_dentry_ops); return; diff --git a/fs/unicode/Kconfig b/fs/unicode/Kconfig index 610d7bc05d6e..da786a687fdc 100644 --- a/fs/unicode/Kconfig +++ b/fs/unicode/Kconfig @@ -3,21 +3,13 @@ # UTF-8 normalization # config UNICODE - bool "UTF-8 normalization and casefolding support" + tristate "UTF-8 normalization and casefolding support" help Say Y here to enable UTF-8 NFD normalization and NFD+CF casefolding - support. - -config UNICODE_UTF8_DATA - tristate "UTF-8 normalization and casefolding tables" - depends on UNICODE - default UNICODE - help - This contains a large table of case foldings, which can be loaded as - a separate module if you say M here. To be on the safe side stick - to the default of Y. Saying N here makes no sense, if you do not want - utf8 casefolding support, disable CONFIG_UNICODE instead. + support. If you say M here the large table of case foldings will + be a separate loadable module that gets requested only when a file + system actually use it. config UNICODE_NORMALIZATION_SELFTEST tristate "Test UTF-8 normalization support" - depends on UNICODE_UTF8_DATA + depends on UNICODE diff --git a/fs/unicode/Makefile b/fs/unicode/Makefile index 2f9d9188852b..0cc87423de82 100644 --- a/fs/unicode/Makefile +++ b/fs/unicode/Makefile @@ -1,8 +1,10 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_UNICODE) += unicode.o +ifneq ($(CONFIG_UNICODE),) +obj-y += unicode.o +endif +obj-$(CONFIG_UNICODE) += utf8data.o obj-$(CONFIG_UNICODE_NORMALIZATION_SELFTEST) += utf8-selftest.o -obj-$(CONFIG_UNICODE_UTF8_DATA) += utf8data.o unicode-y := utf8-norm.o utf8-core.o diff --git a/include/linux/fs.h b/include/linux/fs.h index c8510da6cc6d..fdac22d16c2b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1490,7 +1490,7 @@ struct super_block { #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; #endif -#ifdef CONFIG_UNICODE +#if IS_ENABLED(CONFIG_UNICODE) struct unicode_map *s_encoding; __u16 s_encoding_flags; #endif -- cgit v1.2.3 From c522e3ad296b7b692ed3960dfde467f2a34b434f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Jan 2022 09:28:41 +0000 Subject: fscache: Add a comment explaining how page-release optimisation works Add a comment into fscache_note_page_release() to explain how the page-release optimisation logic works[1]. It's not entirely obvious as it has nothing to do with whether or not the netfs file contains data. FSCACHE_COOKIE_NO_DATA_TO_READ is set if we have no data in the cache yet (ie. the backing file lookup was negative, the file is 0 length or the cookie got invalidated). It means that we have no data in the cache, not that the file is necessarily empty on the server. FSCACHE_COOKIE_HAVE_DATA is set once we've stored data in the backing file. From that point on, we have data we *could* read - however, it's covered by pages in the netfs pagecache until at such time one of those covering pages is released. So if we've written data to the cache (HAVE_DATA) and there wasn't any data in the cache when we started (NO_DATA_TO_READ), it may no longer be true that we can skip reading from the cache. Read skipping is done by cachefiles_prepare_read(). Note that tracking is not done on a per-page basis, but only on a per-file basis. Signed-off-by: David Howells Reviewed-by: Jeff Layton cc: linux-cachefs@redhat.com Link: https://lore.kernel.org/r/043a206f03929c2667a465314144e518070a9b2d.camel@kernel.org/ [1] Link: https://lore.kernel.org/r/164251408479.3435901.9540165422908194636.stgit@warthog.procyon.org.uk/ # v1 --- include/linux/fscache.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fscache.h b/include/linux/fscache.h index ede50406bcb0..296c5f1d9f35 100644 --- a/include/linux/fscache.h +++ b/include/linux/fscache.h @@ -665,6 +665,11 @@ static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie, static inline void fscache_note_page_release(struct fscache_cookie *cookie) { + /* If we've written data to the cache (HAVE_DATA) and there wasn't any + * data in the cache when we started (NO_DATA_TO_READ), it may no + * longer be true that we can skip reading from the cache - so clear + * the flag that causes reads to be skipped. + */ if (cookie && test_bit(FSCACHE_COOKIE_HAVE_DATA, &cookie->flags) && test_bit(FSCACHE_COOKIE_NO_DATA_TO_READ, &cookie->flags)) -- cgit v1.2.3 From ffa65753c43142f3b803486442813744da71cff2 Mon Sep 17 00:00:00 2001 From: Alistair Popple Date: Fri, 21 Jan 2022 22:10:46 -0800 Subject: mm/migrate.c: rework migration_entry_wait() to not take a pageref This fixes the FIXME in migrate_vma_check_page(). Before migrating a page migration code will take a reference and check there are no unexpected page references, failing the migration if there are. When a thread faults on a migration entry it will take a temporary reference to the page to wait for the page to become unlocked signifying the migration entry has been removed. This reference is dropped just prior to waiting on the page lock, however the extra reference can cause migration failures so it is desirable to avoid taking it. As migration code already has a reference to the migrating page an extra reference to wait on PG_locked is unnecessary so long as the reference can't be dropped whilst setting up the wait. When faulting on a migration entry the ptl is taken to check the migration entry. Removing a migration entry also requires the ptl, and migration code won't drop its page reference until after the migration entry has been removed. Therefore retaining the ptl of a migration entry is sufficient to ensure the page has a reference. Reworking migration_entry_wait() to hold the ptl until the wait setup is complete means the extra page reference is no longer needed. [apopple@nvidia.com: v5] Link: https://lkml.kernel.org/r/20211213033848.1973946-1-apopple@nvidia.com Link: https://lkml.kernel.org/r/20211118020754.954425-1-apopple@nvidia.com Signed-off-by: Alistair Popple Acked-by: David Hildenbrand Cc: David Howells Cc: Hugh Dickins Cc: Jason Gunthorpe Cc: Jerome Glisse Cc: John Hubbard Cc: Matthew Wilcox (Oracle) Cc: Ralph Campbell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 ++ mm/filemap.c | 91 +++++++++++++++++++++++++++++++++++++++++++++++++ mm/migrate.c | 38 +++------------------ 3 files changed, 97 insertions(+), 34 deletions(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 4850cc5bf813..db96e10eb8da 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -40,6 +40,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, int extra_count); +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl); void folio_migrate_flags(struct folio *newfolio, struct folio *folio); void folio_migrate_copy(struct folio *newfolio, struct folio *folio); int folio_migrate_mapping(struct address_space *mapping, diff --git a/mm/filemap.c b/mm/filemap.c index 2fd9b2f24025..60866ae711e2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -41,6 +42,7 @@ #include #include #include +#include #include #include #include "internal.h" @@ -1388,6 +1390,95 @@ repeat: return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } +#ifdef CONFIG_MIGRATION +/** + * migration_entry_wait_on_locked - Wait for a migration entry to be removed + * @entry: migration swap entry. + * @ptep: mapped pte pointer. Will return with the ptep unmapped. Only required + * for pte entries, pass NULL for pmd entries. + * @ptl: already locked ptl. This function will drop the lock. + * + * Wait for a migration entry referencing the given page to be removed. This is + * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except + * this can be called without taking a reference on the page. Instead this + * should be called while holding the ptl for the migration entry referencing + * the page. + * + * Returns after unmapping and unlocking the pte/ptl with pte_unmap_unlock(). + * + * This follows the same logic as folio_wait_bit_common() so see the comments + * there. + */ +void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep, + spinlock_t *ptl) +{ + struct wait_page_queue wait_page; + wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; + bool delayacct = false; + unsigned long pflags; + wait_queue_head_t *q; + struct folio *folio = page_folio(pfn_swap_entry_to_page(entry)); + + q = folio_waitqueue(folio); + if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { + if (!folio_test_swapbacked(folio)) { + delayacct_thrashing_start(); + delayacct = true; + } + psi_memstall_enter(&pflags); + thrashing = true; + } + + init_wait(wait); + wait->func = wake_page_function; + wait_page.folio = folio; + wait_page.bit_nr = PG_locked; + wait->flags = 0; + + spin_lock_irq(&q->lock); + folio_set_waiters(folio); + if (!folio_trylock_flag(folio, PG_locked, wait)) + __add_wait_queue_entry_tail(q, wait); + spin_unlock_irq(&q->lock); + + /* + * If a migration entry exists for the page the migration path must hold + * a valid reference to the page, and it must take the ptl to remove the + * migration entry. So the page is valid until the ptl is dropped. + */ + if (ptep) + pte_unmap_unlock(ptep, ptl); + else + spin_unlock(ptl); + + for (;;) { + unsigned int flags; + + set_current_state(TASK_UNINTERRUPTIBLE); + + /* Loop until we've been woken or interrupted */ + flags = smp_load_acquire(&wait->flags); + if (!(flags & WQ_FLAG_WOKEN)) { + if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) + break; + + io_schedule(); + continue; + } + break; + } + + finish_wait(q, wait); + + if (thrashing) { + if (delayacct) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } +} +#endif + void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); diff --git a/mm/migrate.c b/mm/migrate.c index 18ce840914f0..c7da064b4781 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -291,7 +291,6 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, { pte_t pte; swp_entry_t entry; - struct folio *folio; spin_lock(ptl); pte = *ptep; @@ -302,17 +301,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, if (!is_migration_entry(entry)) goto out; - folio = page_folio(pfn_swap_entry_to_page(entry)); - - /* - * Once page cache replacement of page migration started, page_count - * is zero; but we must not call folio_put_wait_locked() without - * a ref. Use folio_try_get(), and just fault again if it fails. - */ - if (!folio_try_get(folio)) - goto out; - pte_unmap_unlock(ptep, ptl); - folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); + migration_entry_wait_on_locked(entry, ptep, ptl); return; out: pte_unmap_unlock(ptep, ptl); @@ -337,16 +326,11 @@ void migration_entry_wait_huge(struct vm_area_struct *vma, void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd) { spinlock_t *ptl; - struct folio *folio; ptl = pmd_lock(mm, pmd); if (!is_pmd_migration_entry(*pmd)) goto unlock; - folio = page_folio(pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd))); - if (!folio_try_get(folio)) - goto unlock; - spin_unlock(ptl); - folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); + migration_entry_wait_on_locked(pmd_to_swp_entry(*pmd), NULL, ptl); return; unlock: spin_unlock(ptl); @@ -2431,22 +2415,8 @@ static bool migrate_vma_check_page(struct page *page) return false; /* Page from ZONE_DEVICE have one extra reference */ - if (is_zone_device_page(page)) { - /* - * Private page can never be pin as they have no valid pte and - * GUP will fail for those. Yet if there is a pending migration - * a thread might try to wait on the pte migration entry and - * will bump the page reference count. Sadly there is no way to - * differentiate a regular pin from migration wait. Hence to - * avoid 2 racing thread trying to migrate back to CPU to enter - * infinite loop (one stopping migration because the other is - * waiting on pte migration entry). We always return true here. - * - * FIXME proper solution is to rework migration_entry_wait() so - * it does not need to take a reference on page. - */ - return is_device_private_page(page); - } + if (is_zone_device_page(page)) + extra++; /* For file back page */ if (page_mapping(page)) -- cgit v1.2.3 From 3ddd9a808cee7284931312f2f3e854c9617f44b2 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:10:50 -0800 Subject: sysctl: add a new register_sysctl_init() interface Patch series "sysctl: first set of kernel/sysctl cleanups", v2. Finally had time to respin the series of the work we had started last year on cleaning up the kernel/sysct.c kitchen sink. People keeps stuffing their sysctls in that file and this creates a maintenance burden. So this effort is aimed at placing sysctls where they actually belong. I'm going to split patches up into series as there is quite a bit of work. This first set adds register_sysctl_init() for uses of registerting a sysctl on the init path, adds const where missing to a few places, generalizes common values so to be more easy to share, and starts the move of a few kernel/sysctl.c out where they belong. The majority of rework on v2 in this first patch set is 0-day fixes. Eric Biederman's feedback is later addressed in subsequent patch sets. I'll only post the first two patch sets for now. We can address the rest once the first two patch sets get completely reviewed / Acked. This patch (of 9): The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. Today though folks heavily rely on tables on kernel/sysctl.c so they can easily just extend this table with their needed sysctls. In order to help users move their sysctls out we need to provide a helper which can be used during code initialization. We special-case the initialization use of register_sysctl() since it *is* safe to fail, given all that sysctls do is provide a dynamic interface to query or modify at runtime an existing variable. So the use case of register_sysctl() on init should *not* stop if the sysctls don't end up getting registered. It would be counter productive to stop boot if a simple sysctl registration failed. Provide a helper for init then, and document the recommended init levels to use for callers of this routine. We will later use this in subsequent patches to start slimming down kernel/sysctl.c tables and moving sysctl registration to the code which actually needs these sysctls. [mcgrof@kernel.org: major commit log and documentation rephrasing also moved to fs/proc/proc_sysctl.c ] Link: https://lkml.kernel.org/r/20211123202347.818157-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20211123202347.818157-2-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Reviewed-by: Kees Cook Cc: Iurii Zaikin Cc: "Eric W. Biederman" Cc: Peter Zijlstra Cc: Greg Kroah-Hartman Cc: Paul Turner Cc: Andy Shevchenko Cc: Sebastian Reichel Cc: Tetsuo Handa Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Qing Wang Cc: Benjamin LaHaise Cc: Al Viro Cc: Jan Kara Cc: Amir Goldstein Cc: Stephen Kitt Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 33 +++++++++++++++++++++++++++++++++ include/linux/sysctl.h | 3 +++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 389e1e42e7d9..55a54973f061 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "internal.h" static const struct dentry_operations proc_sys_dentry_operations; @@ -1383,6 +1384,38 @@ struct ctl_table_header *register_sysctl(const char *path, struct ctl_table *tab } EXPORT_SYMBOL(register_sysctl); +/** + * __register_sysctl_init() - register sysctl table to path + * @path: path name for sysctl base + * @table: This is the sysctl table that needs to be registered to the path + * @table_name: The name of sysctl table, only used for log printing when + * registration fails + * + * The sysctl interface is used by userspace to query or modify at runtime + * a predefined value set on a variable. These variables however have default + * values pre-set. Code which depends on these variables will always work even + * if register_sysctl() fails. If register_sysctl() fails you'd just loose the + * ability to query or modify the sysctls dynamically at run time. Chances of + * register_sysctl() failing on init are extremely low, and so for both reasons + * this function does not return any error as it is used by initialization code. + * + * Context: Can only be called after your respective sysctl base path has been + * registered. So for instance, most base directories are registered early on + * init before init levels are processed through proc_sys_init() and + * sysctl_init(). + */ +void __init __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name) +{ + struct ctl_table_header *hdr = register_sysctl(path, table); + + if (unlikely(!hdr)) { + pr_err("failed when register_sysctl %s to %s\n", table_name, path); + return; + } + kmemleak_not_leak(hdr); +} + static char *append_path(const char *path, char *pos, const char *name) { int namelen; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 1fa2b69c6fc3..d3ab7969b6b5 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -199,6 +199,9 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); extern int sysctl_init(void); +extern void __register_sysctl_init(const char *path, struct ctl_table *table, + const char *table_name); +#define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) void do_sysctl_args(void); extern int pwrsw_enabled; -- cgit v1.2.3 From 78e36f3b0dae586f623c4a37ec5eb5496f5abbe1 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:10:55 -0800 Subject: sysctl: move some boundary constants from sysctl.c to sysctl_vals sysctl has helpers which let us specify boundary values for a min or max int value. Since these are used for a boundary check only they don't change, so move these variables to sysctl_vals to avoid adding duplicate variables. This will help with our cleanup of kernel/sysctl.c. [akpm@linux-foundation.org: update it for "mm/pagealloc: sysctl: change watermark_scale_factor max limit to 30%"] [mcgrof@kernel.org: major rebase] Link: https://lkml.kernel.org/r/20211123202347.818157-3-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Reviewed-by: Kees Cook Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Benjamin LaHaise Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Jan Kara Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Qing Wang Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 2 +- include/linux/sysctl.h | 13 ++++++++++--- kernel/sysctl.c | 45 +++++++++++++++++++-------------------------- 3 files changed, 30 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 55a54973f061..cd8bbf13d0f0 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -26,7 +26,7 @@ static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; /* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { 0, 1, INT_MAX }; +const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX }; EXPORT_SYMBOL(sysctl_vals); /* Support for permanently empty directories */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index d3ab7969b6b5..47cf70c8eb93 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -38,9 +38,16 @@ struct ctl_table_header; struct ctl_dir; /* Keep the same order as in fs/proc/proc_sysctl.c */ -#define SYSCTL_ZERO ((void *)&sysctl_vals[0]) -#define SYSCTL_ONE ((void *)&sysctl_vals[1]) -#define SYSCTL_INT_MAX ((void *)&sysctl_vals[2]) +#define SYSCTL_NEG_ONE ((void *)&sysctl_vals[0]) +#define SYSCTL_ZERO ((void *)&sysctl_vals[1]) +#define SYSCTL_ONE ((void *)&sysctl_vals[2]) +#define SYSCTL_TWO ((void *)&sysctl_vals[3]) +#define SYSCTL_FOUR ((void *)&sysctl_vals[4]) +#define SYSCTL_ONE_HUNDRED ((void *)&sysctl_vals[5]) +#define SYSCTL_TWO_HUNDRED ((void *)&sysctl_vals[6]) +#define SYSCTL_ONE_THOUSAND ((void *)&sysctl_vals[7]) +#define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) +#define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) extern const int sysctl_vals[]; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ef77be575d87..901a9dfe4d62 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -114,16 +114,9 @@ static int sixty = 60; #endif -static int __maybe_unused neg_one = -1; -static int __maybe_unused two = 2; -static int __maybe_unused four = 4; static unsigned long zero_ul; static unsigned long one_ul = 1; static unsigned long long_max = LONG_MAX; -static int one_hundred = 100; -static int two_hundred = 200; -static int one_thousand = 1000; -static int three_thousand = 3000; #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -1964,7 +1957,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, + .extra1 = SYSCTL_NEG_ONE, .extra2 = SYSCTL_ONE, }, #endif @@ -2306,7 +2299,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax_sysadmin, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, #endif { @@ -2566,7 +2559,7 @@ static struct ctl_table kern_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &neg_one, + .extra1 = SYSCTL_NEG_ONE, }, #endif #ifdef CONFIG_RT_MUTEXES @@ -2628,7 +2621,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_cpu_time_max_percent_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "perf_event_max_stack", @@ -2646,7 +2639,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = perf_event_max_stack_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_thousand, + .extra2 = SYSCTL_ONE_THOUSAND, }, #endif { @@ -2677,7 +2670,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", @@ -2731,7 +2724,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = overcommit_policy_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "panic_on_oom", @@ -2740,7 +2733,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "oom_kill_allocating_task", @@ -2785,7 +2778,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_background_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_background_bytes", @@ -2802,7 +2795,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = dirty_ratio_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "dirty_bytes", @@ -2842,7 +2835,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two_hundred, + .extra2 = SYSCTL_TWO_HUNDRED, }, #ifdef CONFIG_HUGETLB_PAGE { @@ -2899,7 +2892,7 @@ static struct ctl_table vm_table[] = { .mode = 0200, .proc_handler = drop_caches_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &four, + .extra2 = SYSCTL_FOUR, }, #ifdef CONFIG_COMPACTION { @@ -2916,7 +2909,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "extfrag_threshold", @@ -2961,7 +2954,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = watermark_scale_factor_sysctl_handler, .extra1 = SYSCTL_ONE, - .extra2 = &three_thousand, + .extra2 = SYSCTL_THREE_THOUSAND, }, { .procname = "percpu_pagelist_high_fraction", @@ -3040,7 +3033,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_unmapped_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, { .procname = "min_slab_ratio", @@ -3049,7 +3042,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = sysctl_min_slab_ratio_sysctl_handler, .extra1 = SYSCTL_ZERO, - .extra2 = &one_hundred, + .extra2 = SYSCTL_ONE_HUNDRED, }, #endif #ifdef CONFIG_SMP @@ -3339,7 +3332,7 @@ static struct ctl_table fs_table[] = { .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "protected_regular", @@ -3348,7 +3341,7 @@ static struct ctl_table fs_table[] = { .mode = 0600, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, { .procname = "suid_dumpable", @@ -3357,7 +3350,7 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, .extra1 = SYSCTL_ZERO, - .extra2 = &two, + .extra2 = SYSCTL_TWO, }, #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE) { -- cgit v1.2.3 From bbe7a10ed83a5fa0b0ff6161ecdc4e65a0e9c993 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:11:00 -0800 Subject: hung_task: move hung_task sysctl interface to hung_task.c The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move hung_task sysctl interface to hung_task.c and use register_sysctl() to register the sysctl interface. [mcgrof@kernel.org: commit log refresh and fixed 2-3 0day reported compile issues] Link: https://lkml.kernel.org/r/20211123202347.818157-4-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Reviewed-by: Kees Cook Reviewed-by: Petr Mladek Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Benjamin LaHaise Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Jan Kara Cc: Paul Turner Cc: Peter Zijlstra Cc: Qing Wang Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched/sysctl.h | 14 +------- kernel/hung_task.c | 81 ++++++++++++++++++++++++++++++++++++++++++-- kernel/sysctl.c | 61 --------------------------------- 3 files changed, 79 insertions(+), 77 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 304f431178fd..c19dd5a2c05c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -7,20 +7,8 @@ struct ctl_table; #ifdef CONFIG_DETECT_HUNG_TASK - -#ifdef CONFIG_SMP -extern unsigned int sysctl_hung_task_all_cpu_backtrace; -#else -#define sysctl_hung_task_all_cpu_backtrace 0 -#endif /* CONFIG_SMP */ - -extern int sysctl_hung_task_check_count; -extern unsigned int sysctl_hung_task_panic; +/* used for hung_task and block/ */ extern unsigned long sysctl_hung_task_timeout_secs; -extern unsigned long sysctl_hung_task_check_interval_secs; -extern int sysctl_hung_task_warnings; -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); #else /* Avoid need for ifdefs elsewhere in the code */ enum { sysctl_hung_task_timeout_secs = 0 }; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 9888e2bc8c76..52501e5f7655 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -63,7 +63,9 @@ static struct task_struct *watchdog_task; * Should we dump all CPUs backtraces in a hung task event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +#else +#define sysctl_hung_task_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ /* @@ -222,11 +224,13 @@ static long hung_timeout_jiffies(unsigned long last_checked, MAX_SCHEDULE_TIMEOUT; } +#ifdef CONFIG_SYSCTL /* * Process updating of timeout sysctl */ -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) { int ret; @@ -241,6 +245,76 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, return ret; } +/* + * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs + * and hung_task_check_interval_secs + */ +static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); +static struct ctl_table hung_task_sysctls[] = { +#ifdef CONFIG_SMP + { + .procname = "hung_task_all_cpu_backtrace", + .data = &sysctl_hung_task_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ + { + .procname = "hung_task_panic", + .data = &sysctl_hung_task_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "hung_task_check_count", + .data = &sysctl_hung_task_check_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "hung_task_timeout_secs", + .data = &sysctl_hung_task_timeout_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_check_interval_secs", + .data = &sysctl_hung_task_check_interval_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_warnings", + .data = &sysctl_hung_task_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_NEG_ONE, + }, + {} +}; + +static void __init hung_task_sysctl_init(void) +{ + register_sysctl_init("kernel", hung_task_sysctls); +} +#else +#define hung_task_sysctl_init() do { } while (0) +#endif /* CONFIG_SYSCTL */ + + static atomic_t reset_hung_task = ATOMIC_INIT(0); void reset_hung_task_detector(void) @@ -310,6 +384,7 @@ static int __init hung_task_init(void) pm_notifier(hungtask_pm_notify, 0); watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); + hung_task_sysctl_init(); return 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 901a9dfe4d62..a4e00abe6f78 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -134,13 +134,6 @@ static int minolduid; static int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; -/* - * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs - * and hung_task_check_interval_secs - */ -#ifdef CONFIG_DETECT_HUNG_TASK -static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); -#endif #ifdef CONFIG_INOTIFY_USER #include @@ -2508,60 +2501,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_DETECT_HUNG_TASK -#ifdef CONFIG_SMP - { - .procname = "hung_task_all_cpu_backtrace", - .data = &sysctl_hung_task_all_cpu_backtrace, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, -#endif /* CONFIG_SMP */ - { - .procname = "hung_task_panic", - .data = &sysctl_hung_task_panic, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "hung_task_check_count", - .data = &sysctl_hung_task_check_count, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - }, - { - .procname = "hung_task_timeout_secs", - .data = &sysctl_hung_task_timeout_secs, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_dohung_task_timeout_secs, - .extra2 = &hung_task_timeout_max, - }, - { - .procname = "hung_task_check_interval_secs", - .data = &sysctl_hung_task_check_interval_secs, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_dohung_task_timeout_secs, - .extra2 = &hung_task_timeout_max, - }, - { - .procname = "hung_task_warnings", - .data = &sysctl_hung_task_warnings, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_NEG_ONE, - }, -#endif #ifdef CONFIG_RT_MUTEXES { .procname = "max_lock_depth", -- cgit v1.2.3 From 86b12b6c5d6b46e64bf2e8080528781032e4bd90 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:11:24 -0800 Subject: aio: move aio sysctl to aio.c The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. Move aio sysctl to aio.c and use the new register_sysctl_init() to register the sysctl interface for aio. [mcgrof@kernel.org: adjust commit log to justify the move] Link: https://lkml.kernel.org/r/20211123202347.818157-9-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Reviewed-by: Jan Kara Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Benjamin LaHaise Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Kees Cook Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Qing Wang Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/aio.c | 31 +++++++++++++++++++++++++++++-- include/linux/aio.h | 4 ---- kernel/sysctl.c | 17 ----------------- 3 files changed, 29 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/aio.c b/fs/aio.c index f6f1cbffef9e..4ceba13a7db0 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -220,9 +220,35 @@ struct aio_kiocb { /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); -unsigned long aio_nr; /* current system wide number of aio requests */ -unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ +static unsigned long aio_nr; /* current system wide number of aio requests */ +static unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ +#ifdef CONFIG_SYSCTL +static struct ctl_table aio_sysctls[] = { + { + .procname = "aio-nr", + .data = &aio_nr, + .maxlen = sizeof(aio_nr), + .mode = 0444, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "aio-max-nr", + .data = &aio_max_nr, + .maxlen = sizeof(aio_max_nr), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + {} +}; + +static void __init aio_sysctl_init(void) +{ + register_sysctl_init("fs", aio_sysctls); +} +#else +#define aio_sysctl_init() do { } while (0) +#endif static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; @@ -275,6 +301,7 @@ static int __init aio_setup(void) kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); + aio_sysctl_init(); return 0; } __initcall(aio_setup); diff --git a/include/linux/aio.h b/include/linux/aio.h index b83e68dd006f..86892a4fe7c8 100644 --- a/include/linux/aio.h +++ b/include/linux/aio.h @@ -20,8 +20,4 @@ static inline void kiocb_set_cancel_fn(struct kiocb *req, kiocb_cancel_fn *cancel) { } #endif /* CONFIG_AIO */ -/* for sysctl: */ -extern unsigned long aio_nr; -extern unsigned long aio_max_nr; - #endif /* __LINUX__AIO_H */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a2175a305f10..822555a0ec76 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -20,7 +20,6 @@ */ #include -#include #include #include #include @@ -3111,22 +3110,6 @@ static struct ctl_table fs_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_AIO - { - .procname = "aio-nr", - .data = &aio_nr, - .maxlen = sizeof(aio_nr), - .mode = 0444, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "aio-max-nr", - .data = &aio_max_nr, - .maxlen = sizeof(aio_max_nr), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, -#endif /* CONFIG_AIO */ #ifdef CONFIG_INOTIFY_USER { .procname = "inotify", -- cgit v1.2.3 From 49a4de75719b6c0f1f375df9908a95cef1e34945 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:11:29 -0800 Subject: dnotify: move dnotify sysctl to dnotify.c The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move dnotify sysctls to dnotify.c and use the new register_sysctl_init() to register the sysctl interface. [mcgrof@kernel.org: adjust the commit log to justify the move] Link: https://lkml.kernel.org/r/20211123202347.818157-10-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Acked-by: Jan Kara Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Benjamin LaHaise Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Kees Cook Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Qing Wang Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Phillip Potter Cc: Rodrigo Vivi Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/dnotify/dnotify.c | 21 ++++++++++++++++++++- include/linux/dnotify.h | 1 - kernel/sysctl.c | 10 ---------- 3 files changed, 20 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c index d5ebebb034ff..829dd4a61b66 100644 --- a/fs/notify/dnotify/dnotify.c +++ b/fs/notify/dnotify/dnotify.c @@ -19,7 +19,25 @@ #include #include -int dir_notify_enable __read_mostly = 1; +static int dir_notify_enable __read_mostly = 1; +#ifdef CONFIG_SYSCTL +static struct ctl_table dnotify_sysctls[] = { + { + .procname = "dir-notify-enable", + .data = &dir_notify_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; +static void __init dnotify_sysctl_init(void) +{ + register_sysctl_init("fs", dnotify_sysctls); +} +#else +#define dnotify_sysctl_init() do { } while (0) +#endif static struct kmem_cache *dnotify_struct_cache __read_mostly; static struct kmem_cache *dnotify_mark_cache __read_mostly; @@ -386,6 +404,7 @@ static int __init dnotify_init(void) dnotify_group = fsnotify_alloc_group(&dnotify_fsnotify_ops); if (IS_ERR(dnotify_group)) panic("unable to allocate fsnotify group for dnotify\n"); + dnotify_sysctl_init(); return 0; } diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h index b87c3b85a166..b1d26f9f1c9f 100644 --- a/include/linux/dnotify.h +++ b/include/linux/dnotify.h @@ -29,7 +29,6 @@ struct dnotify_struct { FS_CREATE | FS_RENAME |\ FS_MOVED_FROM | FS_MOVED_TO) -extern int dir_notify_enable; extern void dnotify_flush(struct file *, fl_owner_t); extern int fcntl_dirnotify(int, struct file *, unsigned long); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 822555a0ec76..fb37825cd3cd 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -49,7 +49,6 @@ #include #include #include -#include #include #include #include @@ -3091,15 +3090,6 @@ static struct ctl_table fs_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_DNOTIFY - { - .procname = "dir-notify-enable", - .data = &dir_notify_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif #ifdef CONFIG_MMU #ifdef CONFIG_FILE_LOCKING { -- cgit v1.2.3 From 7b9ad122b52c9839e1f68f16c907990a6ad6f793 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:11:59 -0800 Subject: inotify: simplify subdirectory registration with register_sysctl() There is no need to user boiler plate code to specify a set of base directories we're going to stuff sysctls under. Simplify this by using register_sysctl() and specifying the directory path directly. Move inotify_user sysctl to inotify_user.c while at it to remove clutter from kernel/sysctl.c. [mcgrof@kernel.org: remember to register fanotify_table] Link: https://lkml.kernel.org/r/YZ5A6iWLb0h3N3RC@bombadil.infradead.org [mcgrof@kernel.org: update commit log to reflect new path we decided to take] Link: https://lkml.kernel.org/r/20211123202422.819032-7-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Kees Cook Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Phillip Potter Cc: Qing Wang Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/fanotify/fanotify_user.c | 10 +++++++++- fs/notify/inotify/inotify_user.c | 11 ++++++++++- include/linux/fanotify.h | 2 -- include/linux/inotify.h | 3 --- kernel/sysctl.c | 21 --------------------- 5 files changed, 19 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 73a3e939c921..73b1615f9d96 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -59,7 +59,7 @@ static int fanotify_max_queued_events __read_mostly; static long ft_zero = 0; static long ft_int_max = INT_MAX; -struct ctl_table fanotify_table[] = { +static struct ctl_table fanotify_table[] = { { .procname = "max_user_groups", .data = &init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS], @@ -88,6 +88,13 @@ struct ctl_table fanotify_table[] = { }, { } }; + +static void __init fanotify_sysctls_init(void) +{ + register_sysctl("fs/fanotify", fanotify_table); +} +#else +#define fanotify_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ /* @@ -1743,6 +1750,7 @@ static int __init fanotify_user_setup(void) init_user_ns.ucount_max[UCOUNT_FANOTIFY_GROUPS] = FANOTIFY_DEFAULT_MAX_GROUPS; init_user_ns.ucount_max[UCOUNT_FANOTIFY_MARKS] = max_marks; + fanotify_sysctls_init(); return 0; } diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c index 29fca3284bb5..54583f62dc44 100644 --- a/fs/notify/inotify/inotify_user.c +++ b/fs/notify/inotify/inotify_user.c @@ -58,7 +58,7 @@ struct kmem_cache *inotify_inode_mark_cachep __read_mostly; static long it_zero = 0; static long it_int_max = INT_MAX; -struct ctl_table inotify_table[] = { +static struct ctl_table inotify_table[] = { { .procname = "max_user_instances", .data = &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES], @@ -87,6 +87,14 @@ struct ctl_table inotify_table[] = { }, { } }; + +static void __init inotify_sysctls_init(void) +{ + register_sysctl("fs/inotify", inotify_table); +} + +#else +#define inotify_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static inline __u32 inotify_arg_to_mask(struct inode *inode, u32 arg) @@ -849,6 +857,7 @@ static int __init inotify_user_setup(void) inotify_max_queued_events = 16384; init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128; init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = watches_max; + inotify_sysctls_init(); return 0; } diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h index 3afdf339d53c..419cadcd7ff5 100644 --- a/include/linux/fanotify.h +++ b/include/linux/fanotify.h @@ -5,8 +5,6 @@ #include #include -extern struct ctl_table fanotify_table[]; /* for sysctl */ - #define FAN_GROUP_FLAG(group, flag) \ ((group)->fanotify_data.flags & (flag)) diff --git a/include/linux/inotify.h b/include/linux/inotify.h index 6a24905f6e1e..8d20caa1b268 100644 --- a/include/linux/inotify.h +++ b/include/linux/inotify.h @@ -7,11 +7,8 @@ #ifndef _LINUX_INOTIFY_H #define _LINUX_INOTIFY_H -#include #include -extern struct ctl_table inotify_table[]; /* for sysctl */ - #define ALL_INOTIFY_BITS (IN_ACCESS | IN_MODIFY | IN_ATTRIB | IN_CLOSE_WRITE | \ IN_CLOSE_NOWRITE | IN_OPEN | IN_MOVED_FROM | \ IN_MOVED_TO | IN_CREATE | IN_DELETE | \ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index fb37825cd3cd..2ee0e76888d8 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -126,13 +126,6 @@ static const int maxolduid = 65535; static const int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; -#ifdef CONFIG_INOTIFY_USER -#include -#endif -#ifdef CONFIG_FANOTIFY -#include -#endif - #ifdef CONFIG_PROC_SYSCTL /** @@ -3100,20 +3093,6 @@ static struct ctl_table fs_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_INOTIFY_USER - { - .procname = "inotify", - .mode = 0555, - .child = inotify_table, - }, -#endif -#ifdef CONFIG_FANOTIFY - { - .procname = "fanotify", - .mode = 0555, - .child = fanotify_table, - }, -#endif #ifdef CONFIG_EPOLL { .procname = "epoll", -- cgit v1.2.3 From a8f5de894f76f1c73f4a068d04897a5e2f873825 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:12:09 -0800 Subject: eventpoll: simplify sysctl declaration with register_sysctl() The kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the epoll_table sysctl to fs/eventpoll.c and use register_sysctl(). Link: https://lkml.kernel.org/r/20211123202422.819032-9-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: "Eric W. Biederman" Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Kees Cook Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Phillip Potter Cc: Qing Wang Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Tetsuo Handa Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Jani Nikula Cc: John Ogness Cc: Martin K. Petersen Cc: "Rafael J. Wysocki" Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/eventpoll.c | 10 +++++++++- include/linux/poll.h | 2 -- include/linux/sysctl.h | 1 - kernel/sysctl.c | 7 ------- 4 files changed, 9 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 06f4c5ae1451..e2daa940ebce 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -307,7 +307,7 @@ static void unlist_file(struct epitems_head *head) static long long_zero; static long long_max = LONG_MAX; -struct ctl_table epoll_table[] = { +static struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, @@ -319,6 +319,13 @@ struct ctl_table epoll_table[] = { }, { } }; + +static void __init epoll_sysctls_init(void) +{ + register_sysctl("fs/epoll", epoll_table); +} +#else +#define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; @@ -2378,6 +2385,7 @@ static int __init eventpoll_init(void) /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); + epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); diff --git a/include/linux/poll.h b/include/linux/poll.h index 1cdc32b1f1b0..a9e0e1c2d1f2 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -8,12 +8,10 @@ #include #include #include -#include #include #include #include -extern struct ctl_table epoll_table[]; /* for sysctl */ /* ~832 bytes of stack space used max in sys_select/sys_poll before allocating additional memory. */ #ifdef __clang__ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 47cf70c8eb93..6dd0f277f844 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -219,7 +219,6 @@ extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; extern struct ctl_table random_table[]; extern struct ctl_table firmware_config_table[]; -extern struct ctl_table epoll_table[]; #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2ee0e76888d8..09fa72299f18 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -3093,13 +3093,6 @@ static struct ctl_table fs_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_EPOLL - { - .procname = "epoll", - .mode = 0555, - .child = epoll_table, - }, -#endif #endif { .procname = "protected_symlinks", -- cgit v1.2.3 From 6aad36d421d8bfe156508fa4edfe67827234cf0f Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:12:13 -0800 Subject: firmware_loader: move firmware sysctl to its own files Patch series "sysctl: 3rd set of kernel/sysctl cleanups", v2. This is the third set of patches to help address cleaning the kitchen seink in kernel/sysctl.c and to move sysctls away to where they are actually implemented / used. This patch (of 8): kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the firmware configuration sysctl table to the only place where it is used, and make it clear that if sysctls are disabled this is not used. [akpm@linux-foundation.org: export register_firmware_config_sysctl and unregister_firmware_config_sysctl to modules] [akpm@linux-foundation.org: use EXPORT_SYMBOL_NS_GPL instead] [sfr@canb.auug.org.au: fix that so it compiles] Link: https://lkml.kernel.org/r/20211201160626.401d828d@canb.auug.org.au [mcgrof@kernel.org: major commit log update to justify the move] Link: https://lkml.kernel.org/r/20211124231435.1445213-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20211124231435.1445213-2-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Signed-off-by: Stephen Rothwell Cc: Kees Cook Cc: Iurii Zaikin Cc: Eric Biederman Cc: Stephen Kitt Cc: Greg Kroah-Hartman Cc: "Rafael J. Wysocki" Cc: "Theodore Ts'o" Cc: Al Viro Cc: Petr Mladek Cc: Sergey Senozhatsky Cc: Steven Rostedt (VMware) Cc: John Ogness Cc: Douglas Gilbert Cc: James E.J. Bottomley Cc: Martin K. Petersen Cc: Lukas Middendorf Cc: Antti Palosaari Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: Jani Nikula Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Mark Fasheh Cc: Paul Turner Cc: Peter Zijlstra Cc: Phillip Potter Cc: Qing Wang Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Suren Baghdasaryan Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/firmware_loader/fallback.c | 7 ++++++- drivers/base/firmware_loader/fallback.h | 11 +++++++++++ drivers/base/firmware_loader/fallback_table.c | 25 +++++++++++++++++++++++-- include/linux/sysctl.h | 1 - kernel/sysctl.c | 7 ------- 5 files changed, 40 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c index d7d63c1aa993..4afb0e9312c0 100644 --- a/drivers/base/firmware_loader/fallback.c +++ b/drivers/base/firmware_loader/fallback.c @@ -199,11 +199,16 @@ static struct class firmware_class = { int register_sysfs_loader(void) { - return class_register(&firmware_class); + int ret = class_register(&firmware_class); + + if (ret != 0) + return ret; + return register_firmware_config_sysctl(); } void unregister_sysfs_loader(void) { + unregister_firmware_config_sysctl(); class_unregister(&firmware_class); } diff --git a/drivers/base/firmware_loader/fallback.h b/drivers/base/firmware_loader/fallback.h index 3af7205b302f..9f3055d3b4ca 100644 --- a/drivers/base/firmware_loader/fallback.h +++ b/drivers/base/firmware_loader/fallback.h @@ -42,6 +42,17 @@ void fw_fallback_set_default_timeout(void); int register_sysfs_loader(void); void unregister_sysfs_loader(void); +#ifdef CONFIG_SYSCTL +extern int register_firmware_config_sysctl(void); +extern void unregister_firmware_config_sysctl(void); +#else +static inline int register_firmware_config_sysctl(void) +{ + return 0; +} +static inline void unregister_firmware_config_sysctl(void) { } +#endif /* CONFIG_SYSCTL */ + #else /* CONFIG_FW_LOADER_USER_HELPER */ static inline int firmware_fallback_sysfs(struct firmware *fw, const char *name, struct device *device, diff --git a/drivers/base/firmware_loader/fallback_table.c b/drivers/base/firmware_loader/fallback_table.c index 46a731dede6f..e5ac098d0742 100644 --- a/drivers/base/firmware_loader/fallback_table.c +++ b/drivers/base/firmware_loader/fallback_table.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -24,7 +25,7 @@ struct firmware_fallback_config fw_fallback_config = { EXPORT_SYMBOL_NS_GPL(fw_fallback_config, FIRMWARE_LOADER_PRIVATE); #ifdef CONFIG_SYSCTL -struct ctl_table firmware_config_table[] = { +static struct ctl_table firmware_config_table[] = { { .procname = "force_sysfs_fallback", .data = &fw_fallback_config.force_sysfs_fallback, @@ -45,4 +46,24 @@ struct ctl_table firmware_config_table[] = { }, { } }; -#endif + +static struct ctl_table_header *firmware_config_sysct_table_header; +int register_firmware_config_sysctl(void) +{ + firmware_config_sysct_table_header = + register_sysctl("kernel/firmware_config", + firmware_config_table); + if (!firmware_config_sysct_table_header) + return -ENOMEM; + return 0; +} +EXPORT_SYMBOL_NS_GPL(register_firmware_config_sysctl, FIRMWARE_LOADER_PRIVATE); + +void unregister_firmware_config_sysctl(void) +{ + unregister_sysctl_table(firmware_config_sysct_table_header); + firmware_config_sysct_table_header = NULL; +} +EXPORT_SYMBOL_NS_GPL(unregister_firmware_config_sysctl, FIRMWARE_LOADER_PRIVATE); + +#endif /* CONFIG_SYSCTL */ diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 6dd0f277f844..3985e9c80155 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -218,7 +218,6 @@ extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; extern struct ctl_table random_table[]; -extern struct ctl_table firmware_config_table[]; #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09fa72299f18..5fc3ae16e995 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2154,13 +2154,6 @@ static struct ctl_table kern_table[] = { .mode = 0555, .child = usermodehelper_table, }, -#ifdef CONFIG_FW_LOADER_USER_HELPER - { - .procname = "firmware_config", - .mode = 0555, - .child = firmware_config_table, - }, -#endif { .procname = "overflowuid", .data = &overflowuid, -- cgit v1.2.3 From 5475e8f03c80bbce7b43a57d861f5acc44a60b22 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:12:18 -0800 Subject: random: move the random sysctl declarations to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the random sysctls to their own file and use register_sysctl_init(). [mcgrof@kernel.org: commit log update to justify the move] Link: https://lkml.kernel.org/r/20211124231435.1445213-3-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: Douglas Gilbert Cc: Eric Biederman Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: James E.J. Bottomley Cc: Jani Nikula Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: John Ogness Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Kees Cook Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Martin K. Petersen Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Phillip Potter Cc: Qing Wang Cc: "Rafael J. Wysocki" Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: Tetsuo Handa Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/random.c | 14 ++++++++++++-- include/linux/sysctl.h | 1 - kernel/sysctl.c | 5 ----- 3 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/drivers/char/random.c b/drivers/char/random.c index b411182df6f6..68613f0b6887 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1992,8 +1992,7 @@ static int proc_do_entropy(struct ctl_table *table, int write, void *buffer, } static int sysctl_poolsize = POOL_BITS; -extern struct ctl_table random_table[]; -struct ctl_table random_table[] = { +static struct ctl_table random_table[] = { { .procname = "poolsize", .data = &sysctl_poolsize, @@ -2055,6 +2054,17 @@ struct ctl_table random_table[] = { #endif { } }; + +/* + * rand_initialize() is called before sysctl_init(), + * so we cannot call register_sysctl_init() in rand_initialize() + */ +static int __init random_sysctls_init(void) +{ + register_sysctl_init("kernel/random", random_table); + return 0; +} +device_initcall(random_sysctls_init); #endif /* CONFIG_SYSCTL */ struct batched_entropy { diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 3985e9c80155..fce05a060bc5 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -217,7 +217,6 @@ extern int unaligned_dump_stack; extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; -extern struct ctl_table random_table[]; #else /* CONFIG_SYSCTL */ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5fc3ae16e995..67a5b04f2f84 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2144,11 +2144,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = sysctl_max_threads, }, - { - .procname = "random", - .mode = 0555, - .child = random_table, - }, { .procname = "usermodehelper", .mode = 0555, -- cgit v1.2.3 From ee9efac48a082904d17a20131aa73d82f058cdd6 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:12:23 -0800 Subject: sysctl: add helper to register a sysctl mount point The way to create a subdirectory on top of sysctl_mount_point is a bit obscure, and *why* we do that even so more. Provide a helper which makes it clear why we do this. [akpm@linux-foundation.org: export register_sysctl_mount_point() to modules] Link: https://lkml.kernel.org/r/20211124231435.1445213-4-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Suggested-by: "Eric W. Biederman" Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: Douglas Gilbert Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: James E.J. Bottomley Cc: Jani Nikula Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: John Ogness Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Kees Cook Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Martin K. Petersen Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Phillip Potter Cc: Qing Wang Cc: "Rafael J. Wysocki" Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: Tetsuo Handa Cc: "Theodore Ts'o" Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 14 ++++++++++++++ include/linux/sysctl.h | 7 +++++++ 2 files changed, 21 insertions(+) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index cd8bbf13d0f0..6bb2d9a3513d 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -35,6 +35,20 @@ struct ctl_table sysctl_mount_point[] = { { } }; +/** + * register_sysctl_mount_point() - registers a sysctl mount point + * @path: path for the mount point + * + * Used to create a permanently empty directory to serve as mount point. + * There are some subtle but important permission checks this allows in the + * case of unprivileged mounts. + */ +struct ctl_table_header *register_sysctl_mount_point(const char *path) +{ + return register_sysctl(path, sysctl_mount_point); +} +EXPORT_SYMBOL(register_sysctl_mount_point); + static bool is_empty_dir(struct ctl_table_header *head) { return head->ctl_table[0].child == sysctl_mount_point; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index fce05a060bc5..746c098a6ff5 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -209,6 +209,8 @@ extern int sysctl_init(void); extern void __register_sysctl_init(const char *path, struct ctl_table *table, const char *table_name); #define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) +extern struct ctl_table_header *register_sysctl_mount_point(const char *path); + void do_sysctl_args(void); extern int pwrsw_enabled; @@ -224,6 +226,11 @@ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * return NULL; } +static inline struct sysctl_header *register_sysctl_mount_point(const char *path) +{ + return NULL; +} + static inline struct ctl_table_header *register_sysctl_paths( const struct ctl_path *path, struct ctl_table *table) { -- cgit v1.2.3 From 0df8bdd5e3b3e557ce2c2575fce0c64c5dd1045a Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:12:43 -0800 Subject: stackleak: move stack_erasing sysctl to stackleak.c kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the stack_erasing sysctl from kernel/sysctl.c to kernel/stackleak.c and use register_sysctl() to register the sysctl interface. [mcgrof@kernel.org: commit log update] Link: https://lkml.kernel.org/r/20211124231435.1445213-8-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: Douglas Gilbert Cc: Eric Biederman Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: James E.J. Bottomley Cc: Jani Nikula Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: John Ogness Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Kees Cook Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Martin K. Petersen Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Phillip Potter Cc: Qing Wang Cc: "Rafael J. Wysocki" Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: Tetsuo Handa Cc: "Theodore Ts'o" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stackleak.h | 5 ----- kernel/stackleak.c | 26 ++++++++++++++++++++++++-- kernel/sysctl.c | 14 -------------- 3 files changed, 24 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index a59db2f08e76..ccaab2043fcd 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -23,11 +23,6 @@ static inline void stackleak_task_init(struct task_struct *t) # endif } -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); -#endif - #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif diff --git a/kernel/stackleak.c b/kernel/stackleak.c index ce161a8e8d97..66b8af394e58 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -16,11 +16,13 @@ #ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE #include #include +#include static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); -int stack_erasing_sysctl(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +#ifdef CONFIG_SYSCTL +static int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret = 0; int state = !static_branch_unlikely(&stack_erasing_bypass); @@ -42,6 +44,26 @@ int stack_erasing_sysctl(struct ctl_table *table, int write, state ? "enabled" : "disabled"); return ret; } +static struct ctl_table stackleak_sysctls[] = { + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init stackleak_sysctls_init(void) +{ + register_sysctl_init("kernel", stackleak_sysctls); + return 0; +} +late_initcall(stackleak_sysctls_init); +#endif /* CONFIG_SYSCTL */ #define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) #else diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b0cced3808d4..3e06dafdd2c3 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -95,9 +95,6 @@ #if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_LOCK_STAT) #include #endif -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE -#include -#endif #if defined(CONFIG_SYSCTL) @@ -2442,17 +2439,6 @@ static struct ctl_table kern_table[] = { .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, -#endif -#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE - { - .procname = "stack_erasing", - .data = NULL, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = stack_erasing_sysctl, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { } }; -- cgit v1.2.3 From b1f2aff888af54a057c2c3c0d88a13ef5d37b52a Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:12:48 -0800 Subject: sysctl: share unsigned long const values Provide a way to share unsigned long values. This will allow others to not have to re-invent these values. Link: https://lkml.kernel.org/r/20211124231435.1445213-9-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Amir Goldstein Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Benjamin LaHaise Cc: Clemens Ladisch Cc: David Airlie Cc: Douglas Gilbert Cc: Eric Biederman Cc: Greg Kroah-Hartman Cc: Iurii Zaikin Cc: James E.J. Bottomley Cc: Jani Nikula Cc: Jani Nikula Cc: Jan Kara Cc: Joel Becker Cc: John Ogness Cc: Joonas Lahtinen Cc: Joseph Qi Cc: Julia Lawall Cc: Kees Cook Cc: Lukas Middendorf Cc: Mark Fasheh Cc: Martin K. Petersen Cc: Paul Turner Cc: Peter Zijlstra Cc: Petr Mladek Cc: Phillip Potter Cc: Qing Wang Cc: "Rafael J. Wysocki" Cc: Rodrigo Vivi Cc: Sebastian Reichel Cc: Sergey Senozhatsky Cc: Stephen Kitt Cc: Steven Rostedt (VMware) Cc: Suren Baghdasaryan Cc: Tetsuo Handa Cc: "Theodore Ts'o" Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 3 +++ include/linux/sysctl.h | 6 ++++++ kernel/sysctl.c | 9 +++------ 3 files changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 6bb2d9a3513d..2eb5987091ea 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -29,6 +29,9 @@ static const struct inode_operations proc_sys_dir_operations; const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX }; EXPORT_SYMBOL(sysctl_vals); +const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX }; +EXPORT_SYMBOL_GPL(sysctl_long_vals); + /* Support for permanently empty directories */ struct ctl_table sysctl_mount_point[] = { diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 746c098a6ff5..2de6d20d191b 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -51,6 +51,12 @@ struct ctl_dir; extern const int sysctl_vals[]; +#define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0]) +#define SYSCTL_LONG_ONE ((void *)&sysctl_long_vals[1]) +#define SYSCTL_LONG_MAX ((void *)&sysctl_long_vals[2]) + +extern const unsigned long sysctl_long_vals[]; + typedef int proc_handler(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3e06dafdd2c3..1b8a1cb8aac9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -100,9 +100,6 @@ /* Constants used for minimum and maximum */ -static const unsigned long zero_ul; -static const unsigned long one_ul = 1; -static const unsigned long long_max = LONG_MAX; #ifdef CONFIG_PRINTK static const int ten_thousand = 10000; #endif @@ -2513,7 +2510,7 @@ static struct ctl_table vm_table[] = { .maxlen = sizeof(dirty_background_bytes), .mode = 0644, .proc_handler = dirty_background_bytes_handler, - .extra1 = (void *)&one_ul, + .extra1 = SYSCTL_LONG_ONE, }, { .procname = "dirty_ratio", @@ -2931,8 +2928,8 @@ static struct ctl_table fs_table[] = { .maxlen = sizeof(files_stat.max_files), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = (void *)&zero_ul, - .extra2 = (void *)&long_max, + .extra1 = SYSCTL_LONG_ZERO, + .extra2 = SYSCTL_LONG_MAX, }, { .procname = "nr_open", -- cgit v1.2.3 From 1d67fe585049d3e2448b997af78c68cbf90ada09 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:12:52 -0800 Subject: fs: move inode sysctls to its own file Patch series "sysctl: 4th set of kernel/sysctl cleanups". This is slimming down the fs uses of kernel/sysctl.c to the point that the next step is to just get rid of the fs base directory for it and move that elsehwere, so that next patch series starts dealing with that to demo how we can end up cleaning up a full base directory from kernel/sysctl.c, one at a time. This patch (of 9): kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the inode sysctls to its own file. Since we are no longer using this outside of fs/ remove the extern declaration of its respective proc helper. We use early_initcall() as it is the earliest we can use. [arnd@arndb.de: avoid unused-variable warning] Link: https://lkml.kernel.org/r/20211203190123.874239-1-arnd@kernel.org Link: https://lkml.kernel.org/r/20211129205548.605569-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20211129205548.605569-2-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Kees Cook Cc: Iurii Zaikin Cc: Xiaoming Ni Cc: Eric Biederman Cc: Stephen Kitt Cc: Lukas Middendorf Cc: Antti Palosaari Cc: Andy Shevchenko Cc: Jeff Layton Cc: "J. Bruce Fields" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/inode.c | 39 ++++++++++++++++++++++++++++++++------- include/linux/fs.h | 3 --- kernel/sysctl.c | 14 -------------- 3 files changed, 32 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/fs/inode.c b/fs/inode.c index 980e7b7a5460..63324df6fa27 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -67,11 +67,6 @@ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); -/* - * Statistics gathering.. - */ -struct inodes_stat_t inodes_stat; - static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); @@ -106,13 +101,43 @@ long get_nr_dirty_inodes(void) * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL -int proc_nr_inodes(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +/* + * Statistics gathering.. + */ +static struct inodes_stat_t inodes_stat; + +static int proc_nr_inodes(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } + +static struct ctl_table inodes_sysctls[] = { + { + .procname = "inode-nr", + .data = &inodes_stat, + .maxlen = 2*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_inodes, + }, + { + .procname = "inode-state", + .data = &inodes_stat, + .maxlen = 7*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_inodes, + }, + { } +}; + +static int __init init_fs_inode_sysctls(void) +{ + register_sysctl_init("fs", inodes_sysctls); + return 0; +} +early_initcall(init_fs_inode_sysctls); #endif static int no_open(struct inode *inode, struct file *file) diff --git a/include/linux/fs.h b/include/linux/fs.h index c8510da6cc6d..044de67c8167 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -82,7 +82,6 @@ extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; -extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; @@ -3537,8 +3536,6 @@ int proc_nr_files(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); -int proc_nr_inodes(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 1b8a1cb8aac9..402c9d3246bf 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2901,20 +2901,6 @@ static struct ctl_table vm_table[] = { }; static struct ctl_table fs_table[] = { - { - .procname = "inode-nr", - .data = &inodes_stat, - .maxlen = 2*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_inodes, - }, - { - .procname = "inode-state", - .data = &inodes_stat, - .maxlen = 7*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_inodes, - }, { .procname = "file-nr", .data = &files_stat, -- cgit v1.2.3 From 204d5a24e15562b2816825c0f9b49d26814b77be Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:12:56 -0800 Subject: fs: move fs stat sysctls to file_table.c kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. We can create the sysctl dynamically on early init for fs stat to help with this clutter. This dusts off the fs stat syctls knobs and puts them into where they are declared. Link: https://lkml.kernel.org/r/20211129205548.605569-3-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Eric Biederman Cc: Iurii Zaikin Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Kees Cook Cc: Lukas Middendorf Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/file_table.c | 47 +++++++++++++++++++++++++++++++++++++++-------- include/linux/fs.h | 3 --- kernel/sysctl.c | 25 ------------------------- 3 files changed, 39 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/fs/file_table.c b/fs/file_table.c index 45437f8e1003..57edef16dce4 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -33,7 +33,7 @@ #include "internal.h" /* sysctl tunables... */ -struct files_stat_struct files_stat = { +static struct files_stat_struct files_stat = { .max_files = NR_FILE }; @@ -75,22 +75,53 @@ unsigned long get_max_files(void) } EXPORT_SYMBOL_GPL(get_max_files); +#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) + /* * Handle nr_files sysctl */ -#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_nr_files(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { files_stat.nr_files = get_nr_files(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } -#else -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) + +static struct ctl_table fs_stat_sysctls[] = { + { + .procname = "file-nr", + .data = &files_stat, + .maxlen = sizeof(files_stat), + .mode = 0444, + .proc_handler = proc_nr_files, + }, + { + .procname = "file-max", + .data = &files_stat.max_files, + .maxlen = sizeof(files_stat.max_files), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + .extra1 = SYSCTL_LONG_ZERO, + .extra2 = SYSCTL_LONG_MAX, + }, + { + .procname = "nr_open", + .data = &sysctl_nr_open, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &sysctl_nr_open_min, + .extra2 = &sysctl_nr_open_max, + }, + { } +}; + +static int __init init_fs_stat_sysctls(void) { - return -ENOSYS; + register_sysctl_init("fs", fs_stat_sysctls); + return 0; } +fs_initcall(init_fs_stat_sysctls); #endif static struct file *__alloc_file(int flags, const struct cred *cred) diff --git a/include/linux/fs.h b/include/linux/fs.h index 044de67c8167..1e6761966120 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -79,7 +79,6 @@ extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); -extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; extern int leases_enable, lease_break_time; @@ -3532,8 +3531,6 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_files(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 402c9d3246bf..d2c411b15854 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2901,31 +2901,6 @@ static struct ctl_table vm_table[] = { }; static struct ctl_table fs_table[] = { - { - .procname = "file-nr", - .data = &files_stat, - .maxlen = sizeof(files_stat), - .mode = 0444, - .proc_handler = proc_nr_files, - }, - { - .procname = "file-max", - .data = &files_stat.max_files, - .maxlen = sizeof(files_stat.max_files), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - .extra1 = SYSCTL_LONG_ZERO, - .extra2 = SYSCTL_LONG_MAX, - }, - { - .procname = "nr_open", - .data = &sysctl_nr_open, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &sysctl_nr_open_min, - .extra2 = &sysctl_nr_open_max, - }, { .procname = "dentry-state", .data = &dentry_stat, -- cgit v1.2.3 From c8c0c239d5ab1e3e8d2bb0453ce642fe2c6357ec Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:12:59 -0800 Subject: fs: move dcache sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the dcache sysctl clutter out of kernel/sysctl.c. This is a small one-off entry, perhaps later we can simplify this representation, but for now we use the helpers we have. We won't know how we can simplify this further untl we're fully done with the cleanup. [arnd@arndb.de: avoid unused-function warning] Link: https://lkml.kernel.org/r/20211203190123.874239-2-arnd@kernel.org Link: https://lkml.kernel.org/r/20211129205548.605569-4-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Signed-off-by: Arnd Bergmann Cc: Al Viro Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Eric Biederman Cc: Iurii Zaikin Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Kees Cook Cc: Lukas Middendorf Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dcache.c | 37 +++++++++++++++++++++++++++++++------ include/linux/dcache.h | 10 ---------- include/linux/fs.h | 2 -- kernel/sysctl.c | 7 ------- 4 files changed, 31 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/fs/dcache.c b/fs/dcache.c index cf871a81f4fd..c84269c6e8bf 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -115,10 +115,13 @@ static inline struct hlist_bl_head *in_lookup_hash(const struct dentry *parent, return in_lookup_hashtable + hash_32(hash, IN_LOOKUP_SHIFT); } - -/* Statistics gathering. */ -struct dentry_stat_t dentry_stat = { - .age_limit = 45, +struct dentry_stat_t { + long nr_dentry; + long nr_unused; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; static DEFINE_PER_CPU(long, nr_dentry); @@ -126,6 +129,10 @@ static DEFINE_PER_CPU(long, nr_dentry_unused); static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) +/* Statistics gathering. */ +static struct dentry_stat_t dentry_stat = { + .age_limit = 45, +}; /* * Here we resort to our own counters instead of using generic per-cpu counters @@ -167,14 +174,32 @@ static long get_nr_dentry_negative(void) return sum < 0 ? 0 : sum; } -int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos) +static int proc_nr_dentry(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } + +static struct ctl_table fs_dcache_sysctls[] = { + { + .procname = "dentry-state", + .data = &dentry_stat, + .maxlen = 6*sizeof(long), + .mode = 0444, + .proc_handler = proc_nr_dentry, + }, + { } +}; + +static int __init init_fs_dcache_sysctls(void) +{ + register_sysctl_init("fs", fs_dcache_sysctls); + return 0; +} +fs_initcall(init_fs_dcache_sysctls); #endif /* diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 9e23d33bb6f1..f5bba51480b2 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -61,16 +61,6 @@ extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; -struct dentry_stat_t { - long nr_dentry; - long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long nr_negative; /* # of unused negative dentries */ - long dummy; /* Reserved for future use */ -}; -extern struct dentry_stat_t dentry_stat; - /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the diff --git a/include/linux/fs.h b/include/linux/fs.h index 1e6761966120..9b856d5da9e2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3531,8 +3531,6 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos); struct ctl_table; -int proc_nr_dentry(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos); int __init list_bdev_fs_names(char *buf, size_t size); #define __FMODE_EXEC ((__force int) FMODE_EXEC) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d2c411b15854..4d182fb5c22e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2901,13 +2901,6 @@ static struct ctl_table vm_table[] = { }; static struct ctl_table fs_table[] = { - { - .procname = "dentry-state", - .data = &dentry_stat, - .maxlen = 6*sizeof(long), - .mode = 0444, - .proc_handler = proc_nr_dentry, - }, { .procname = "overflowuid", .data = &fs_overflowuid, -- cgit v1.2.3 From 54771613e8a7dbbba2a205ddf1b33e25a290b3fd Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:03 -0800 Subject: sysctl: move maxolduid as a sysctl specific const MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The maxolduid value is only shared for sysctl purposes for use on a max range. Just stuff this into our shared const array. [akpm@linux-foundation.org: fix sysctl_vals[], per Mickaël] Link: https://lkml.kernel.org/r/20211129205548.605569-5-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Signed-off-by: Mickaël Salaün Cc: Al Viro Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Eric Biederman Cc: Iurii Zaikin Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Kees Cook Cc: Lukas Middendorf Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 2 +- include/linux/sysctl.h | 3 +++ kernel/sysctl.c | 12 ++++-------- 3 files changed, 8 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 2eb5987091ea..b9d53b53d769 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -26,7 +26,7 @@ static const struct file_operations proc_sys_dir_file_operations; static const struct inode_operations proc_sys_dir_operations; /* shared constants to be used in various sysctls */ -const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX }; +const int sysctl_vals[] = { -1, 0, 1, 2, 4, 100, 200, 1000, 3000, INT_MAX, 65535 }; EXPORT_SYMBOL(sysctl_vals); const unsigned long sysctl_long_vals[] = { 0, 1, LONG_MAX }; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 2de6d20d191b..bb921eb8a02d 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -49,6 +49,9 @@ struct ctl_dir; #define SYSCTL_THREE_THOUSAND ((void *)&sysctl_vals[8]) #define SYSCTL_INT_MAX ((void *)&sysctl_vals[9]) +/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ +#define SYSCTL_MAXOLDUID ((void *)&sysctl_vals[10]) + extern const int sysctl_vals[]; #define SYSCTL_LONG_ZERO ((void *)&sysctl_long_vals[0]) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 4d182fb5c22e..5bbb4c59dd1a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -110,10 +110,6 @@ static const int six_hundred_forty_kb = 640 * 1024; /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ static const unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ -static const int maxolduid = 65535; -/* minolduid is SYSCTL_ZERO */ - static const int ngroups_max = NGROUPS_MAX; static const int cap_last_cap = CAP_LAST_CAP; @@ -2127,7 +2123,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = (void *)&maxolduid, + .extra2 = SYSCTL_MAXOLDUID, }, { .procname = "overflowgid", @@ -2136,7 +2132,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = (void *)&maxolduid, + .extra2 = SYSCTL_MAXOLDUID, }, #ifdef CONFIG_S390 { @@ -2908,7 +2904,7 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = (void *)&maxolduid, + .extra2 = SYSCTL_MAXOLDUID, }, { .procname = "overflowgid", @@ -2917,7 +2913,7 @@ static struct ctl_table fs_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = (void *)&maxolduid, + .extra2 = SYSCTL_MAXOLDUID, }, #ifdef CONFIG_FILE_LOCKING { -- cgit v1.2.3 From dd81faa88340a1fe8cd81c8ecbadd8e95c58549c Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:10 -0800 Subject: fs: move locking sysctls where they are used kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. The locking fs sysctls are only used on fs/locks.c, so move them there. Link: https://lkml.kernel.org/r/20211129205548.605569-7-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Eric Biederman Cc: Iurii Zaikin Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Kees Cook Cc: Lukas Middendorf Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/locks.c | 34 ++++++++++++++++++++++++++++++++-- include/linux/fs.h | 4 ---- kernel/sysctl.c | 20 -------------------- 3 files changed, 32 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/fs/locks.c b/fs/locks.c index 0fca9d680978..8c6df10cd9ed 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -62,6 +62,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -88,8 +89,37 @@ static int target_leasetype(struct file_lock *fl) return fl->fl_type; } -int leases_enable = 1; -int lease_break_time = 45; +static int leases_enable = 1; +static int lease_break_time = 45; + +#ifdef CONFIG_SYSCTL +static struct ctl_table locks_sysctls[] = { + { + .procname = "leases-enable", + .data = &leases_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_MMU + { + .procname = "lease-break-time", + .data = &lease_break_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_MMU */ + {} +}; + +static int __init init_fs_locks_sysctls(void) +{ + register_sysctl_init("fs", locks_sysctls); + return 0; +} +early_initcall(init_fs_locks_sysctls); +#endif /* CONFIG_SYSCTL */ /* * The global file_lock_list is only used for displaying /proc/locks, so we diff --git a/include/linux/fs.h b/include/linux/fs.h index 9b856d5da9e2..0e08c3dd8f75 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -82,10 +82,6 @@ extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; extern int leases_enable, lease_break_time; -extern int sysctl_protected_symlinks; -extern int sysctl_protected_hardlinks; -extern int sysctl_protected_fifos; -extern int sysctl_protected_regular; typedef __kernel_rwf_t rwf_t; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 6d9d2001b790..073948e9d165 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2897,26 +2897,6 @@ static struct ctl_table vm_table[] = { }; static struct ctl_table fs_table[] = { -#ifdef CONFIG_FILE_LOCKING - { - .procname = "leases-enable", - .data = &leases_enable, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#ifdef CONFIG_MMU -#ifdef CONFIG_FILE_LOCKING - { - .procname = "lease-break-time", - .data = &lease_break_time, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#endif -#endif { .procname = "protected_symlinks", .data = &sysctl_protected_symlinks, -- cgit v1.2.3 From 9c011be132972ff94bde2ae99064e29f94e85c68 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:13 -0800 Subject: fs: move namei sysctls to its own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move namei's own sysctl knobs to its own file. Other than the move we also avoid initializing two static variables to 0 as this is not needed: * sysctl_protected_symlinks * sysctl_protected_hardlinks Link: https://lkml.kernel.org/r/20211129205548.605569-8-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Eric Biederman Cc: Iurii Zaikin Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Kees Cook Cc: Lukas Middendorf Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/namei.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++---- include/linux/fs.h | 1 - kernel/sysctl.c | 36 --------------------------------- 3 files changed, 54 insertions(+), 41 deletions(-) (limited to 'include/linux') diff --git a/fs/namei.c b/fs/namei.c index d81f04f8d818..b867a92c078e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1020,10 +1020,60 @@ static inline void put_link(struct nameidata *nd) path_put(&last->link); } -int sysctl_protected_symlinks __read_mostly = 0; -int sysctl_protected_hardlinks __read_mostly = 0; -int sysctl_protected_fifos __read_mostly; -int sysctl_protected_regular __read_mostly; +static int sysctl_protected_symlinks __read_mostly; +static int sysctl_protected_hardlinks __read_mostly; +static int sysctl_protected_fifos __read_mostly; +static int sysctl_protected_regular __read_mostly; + +#ifdef CONFIG_SYSCTL +static struct ctl_table namei_sysctls[] = { + { + .procname = "protected_symlinks", + .data = &sysctl_protected_symlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "protected_hardlinks", + .data = &sysctl_protected_hardlinks, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "protected_fifos", + .data = &sysctl_protected_fifos, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { + .procname = "protected_regular", + .data = &sysctl_protected_regular, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, + }, + { } +}; + +static int __init init_fs_namei_sysctls(void) +{ + register_sysctl_init("fs", namei_sysctls); + return 0; +} +fs_initcall(init_fs_namei_sysctls); + +#endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations diff --git a/include/linux/fs.h b/include/linux/fs.h index 0e08c3dd8f75..9617dea24978 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -81,7 +81,6 @@ extern void __init files_maxfiles_init(void); extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; -extern int leases_enable, lease_break_time; typedef __kernel_rwf_t rwf_t; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 073948e9d165..53fb4692facc 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2897,42 +2897,6 @@ static struct ctl_table vm_table[] = { }; static struct ctl_table fs_table[] = { - { - .procname = "protected_symlinks", - .data = &sysctl_protected_symlinks, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "protected_hardlinks", - .data = &sysctl_protected_hardlinks, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, - { - .procname = "protected_fifos", - .data = &sysctl_protected_fifos, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, - }, - { - .procname = "protected_regular", - .data = &sysctl_protected_regular, - .maxlen = sizeof(int), - .mode = 0600, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, - }, { .procname = "suid_dumpable", .data = &suid_dumpable, -- cgit v1.2.3 From 1998f19324d24df7de4e74d81503b4299eb99e7d Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:20 -0800 Subject: fs: move pipe sysctls to is own file kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. So move the pipe sysctls to its own file. Link: https://lkml.kernel.org/r/20211129205548.605569-10-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Andy Shevchenko Cc: Antti Palosaari Cc: Eric Biederman Cc: Iurii Zaikin Cc: "J. Bruce Fields" Cc: Jeff Layton Cc: Kees Cook Cc: Lukas Middendorf Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/pipe.c | 64 ++++++++++++++++++++++++++++++++++++++++++++--- include/linux/pipe_fs_i.h | 4 --- include/linux/sysctl.h | 6 +++++ kernel/sysctl.c | 61 +++++--------------------------------------- 4 files changed, 73 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/fs/pipe.c b/fs/pipe.c index 6d4342bad9f1..cc28623a67b6 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include @@ -50,13 +51,13 @@ * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ -unsigned int pipe_max_size = 1048576; +static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ -unsigned long pipe_user_pages_hard; -unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; +static unsigned long pipe_user_pages_hard; +static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of @@ -1428,6 +1429,60 @@ static struct file_system_type pipe_fs_type = { .kill_sb = kill_anon_super, }; +#ifdef CONFIG_SYSCTL +static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, + unsigned int *valp, + int write, void *data) +{ + if (write) { + unsigned int val; + + val = round_pipe_size(*lvalp); + if (val == 0) + return -EINVAL; + + *valp = val; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long) val; + } + + return 0; +} + +static int proc_dopipe_max_size(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_douintvec(table, write, buffer, lenp, ppos, + do_proc_dopipe_max_size_conv, NULL); +} + +static struct ctl_table fs_pipe_sysctls[] = { + { + .procname = "pipe-max-size", + .data = &pipe_max_size, + .maxlen = sizeof(pipe_max_size), + .mode = 0644, + .proc_handler = proc_dopipe_max_size, + }, + { + .procname = "pipe-user-pages-hard", + .data = &pipe_user_pages_hard, + .maxlen = sizeof(pipe_user_pages_hard), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { + .procname = "pipe-user-pages-soft", + .data = &pipe_user_pages_soft, + .maxlen = sizeof(pipe_user_pages_soft), + .mode = 0644, + .proc_handler = proc_doulongvec_minmax, + }, + { } +}; +#endif + static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); @@ -1439,6 +1494,9 @@ static int __init init_pipe_fs(void) unregister_filesystem(&pipe_fs_type); } } +#ifdef CONFIG_SYSCTL + register_sysctl_init("fs", fs_pipe_sysctls); +#endif return err; } diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index fc5642431b92..c00c618ef290 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -238,10 +238,6 @@ void pipe_lock(struct pipe_inode_info *); void pipe_unlock(struct pipe_inode_info *); void pipe_double_lock(struct pipe_inode_info *, struct pipe_inode_info *); -extern unsigned int pipe_max_size; -extern unsigned long pipe_user_pages_hard; -extern unsigned long pipe_user_pages_soft; - /* Wait for a pipe to be readable/writable while dropping the pipe lock */ void pipe_wait_readable(struct pipe_inode_info *); void pipe_wait_writable(struct pipe_inode_info *); diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index bb921eb8a02d..4294e9668bd5 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -221,6 +221,12 @@ extern void __register_sysctl_init(const char *path, struct ctl_table *table, extern struct ctl_table_header *register_sysctl_mount_point(const char *path); void do_sysctl_args(void); +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data); extern int pwrsw_enabled; extern int unaligned_enabled; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 8bab82aa0192..f79ec2cf8721 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -57,7 +57,6 @@ #include #include #include -#include #include #include #include @@ -761,12 +760,12 @@ static int __do_proc_douintvec(void *tbl_data, struct ctl_table *table, return do_proc_douintvec_r(i, buffer, lenp, ppos, conv, data); } -static int do_proc_douintvec(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos, - int (*conv)(unsigned long *lvalp, - unsigned int *valp, - int write, void *data), - void *data) +int do_proc_douintvec(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos, + int (*conv)(unsigned long *lvalp, + unsigned int *valp, + int write, void *data), + void *data) { return __do_proc_douintvec(table->data, table, write, buffer, lenp, ppos, conv, data); @@ -1090,33 +1089,6 @@ int proc_dou8vec_minmax(struct ctl_table *table, int write, } EXPORT_SYMBOL_GPL(proc_dou8vec_minmax); -static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, - unsigned int *valp, - int write, void *data) -{ - if (write) { - unsigned int val; - - val = round_pipe_size(*lvalp); - if (val == 0) - return -EINVAL; - - *valp = val; - } else { - unsigned int val = *valp; - *lvalp = (unsigned long) val; - } - - return 0; -} - -static int proc_dopipe_max_size(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - return do_proc_douintvec(table, write, buffer, lenp, ppos, - do_proc_dopipe_max_size_conv, NULL); -} - #ifdef CONFIG_MAGIC_SYSRQ static int sysrq_sysctl_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -2840,27 +2812,6 @@ static struct ctl_table vm_table[] = { }; static struct ctl_table fs_table[] = { - { - .procname = "pipe-max-size", - .data = &pipe_max_size, - .maxlen = sizeof(pipe_max_size), - .mode = 0644, - .proc_handler = proc_dopipe_max_size, - }, - { - .procname = "pipe-user-pages-hard", - .data = &pipe_user_pages_hard, - .maxlen = sizeof(pipe_user_pages_hard), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, - { - .procname = "pipe-user-pages-soft", - .data = &pipe_user_pages_soft, - .maxlen = sizeof(pipe_user_pages_soft), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax, - }, { .procname = "mount-max", .data = &sysctl_mount_max, -- cgit v1.2.3 From 51cb8dfc5a5c39e6c70376b9dc9a14d624a9d271 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:24 -0800 Subject: sysctl: add and use base directory declarer and registration helper Patch series "sysctl: add and use base directory declarer and registration helper". In this patch series we start addressing base directories, and so we start with the "fs" sysctls. The end goal is we end up completely moving all "fs" sysctl knobs out from kernel/sysctl. This patch (of 6): Add a set of helpers which can be used to declare and register base directory sysctls on their own. We do this so we can later move each of the base sysctl directories like "fs", "kernel", etc, to their own respective files instead of shoving the declarations and registrations all on kernel/sysctl.c. The lazy approach has caught up and with this, we just end up extending the list of base directories / sysctls on one file and this makes maintenance difficult due to merge conflicts from many developers. The declarations are used first by kernel/sysctl.c for registration its own base which over time we'll try to clean up. It will be used in the next patch to demonstrate how to cleanly deal with base sysctl directories. [mcgrof@kernel.org: null-terminate the ctl_table arrays] Link: https://lkml.kernel.org/r/YafJY3rXDYnjK/gs@bombadil.infradead.org Link: https://lkml.kernel.org/r/20211129211943.640266-1-mcgrof@kernel.org Link: https://lkml.kernel.org/r/20211129211943.640266-2-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Kees Cook Cc: Iurii Zaikin Cc: Xiaoming Ni Cc: Eric Biederman Cc: Stephen Kitt Cc: Lukas Middendorf Cc: Antti Palosaari Cc: Christian Brauner Cc: Eric Biggers Cc: "Naveen N. Rao" Cc: "David S. Miller" Cc: Masami Hiramatsu Cc: Anil S Keshavamurthy Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/proc_sysctl.c | 9 +++++++++ include/linux/sysctl.h | 24 ++++++++++++++++++++++++ kernel/sysctl.c | 41 ++++++++++------------------------------- 3 files changed, 43 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index b9d53b53d769..95dfd195e04e 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1646,6 +1646,15 @@ struct ctl_table_header *register_sysctl_table(struct ctl_table *table) } EXPORT_SYMBOL(register_sysctl_table); +int __register_sysctl_base(struct ctl_table *base_table) +{ + struct ctl_table_header *hdr; + + hdr = register_sysctl_table(base_table); + kmemleak_not_leak(hdr); + return 0; +} + static void put_links(struct ctl_table_header *header) { struct ctl_table_set *root_set = &sysctl_table_root.default_set; diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 4294e9668bd5..02134a8abad7 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -194,6 +194,20 @@ struct ctl_path { #ifdef CONFIG_SYSCTL +#define DECLARE_SYSCTL_BASE(_name, _table) \ +static struct ctl_table _name##_base_table[] = { \ + { \ + .procname = #_name, \ + .mode = 0555, \ + .child = _table, \ + }, \ + { }, \ +} + +extern int __register_sysctl_base(struct ctl_table *base_table); + +#define register_sysctl_base(_name) __register_sysctl_base(_name##_base_table) + void proc_sys_poll_notify(struct ctl_table_poll *poll); extern void setup_sysctl_set(struct ctl_table_set *p, @@ -236,6 +250,16 @@ extern int no_unaligned_warning; extern struct ctl_table sysctl_mount_point[]; #else /* CONFIG_SYSCTL */ + +#define DECLARE_SYSCTL_BASE(_name, _table) + +static inline int __register_sysctl_base(struct ctl_table *base_table) +{ + return 0; +} + +#define register_sysctl_base(table) __register_sysctl_base(table) + static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * table) { return NULL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index f79ec2cf8721..12456a535059 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2851,41 +2851,20 @@ static struct ctl_table dev_table[] = { { } }; -static struct ctl_table sysctl_base_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = kern_table, - }, - { - .procname = "vm", - .mode = 0555, - .child = vm_table, - }, - { - .procname = "fs", - .mode = 0555, - .child = fs_table, - }, - { - .procname = "debug", - .mode = 0555, - .child = debug_table, - }, - { - .procname = "dev", - .mode = 0555, - .child = dev_table, - }, - { } -}; +DECLARE_SYSCTL_BASE(kernel, kern_table); +DECLARE_SYSCTL_BASE(vm, vm_table); +DECLARE_SYSCTL_BASE(fs, fs_table); +DECLARE_SYSCTL_BASE(debug, debug_table); +DECLARE_SYSCTL_BASE(dev, dev_table); int __init sysctl_init(void) { - struct ctl_table_header *hdr; + register_sysctl_base(kernel); + register_sysctl_base(vm); + register_sysctl_base(fs); + register_sysctl_base(debug); + register_sysctl_base(dev); - hdr = register_sysctl_table(sysctl_base_table); - kmemleak_not_leak(hdr); return 0; } #endif /* CONFIG_SYSCTL */ -- cgit v1.2.3 From ab171b952c6e065779687b44041038efdadb3915 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:27 -0800 Subject: fs: move namespace sysctls and declare fs base directory This moves the namespace sysctls to its own file as part of the kernel/sysctl.c spring cleaning Since we have now removed all sysctls for "fs", we now have to declare it on the filesystem code, we do that using the new helper, which reduces boiler plate code. We rename init_fs_shared_sysctls() to init_fs_sysctls() to reflect that now fs/sysctls.c is taking on the burden of being the first to register the base directory as well. Lastly, since init code will load in the order in which we link it we have to move the sysctl code to be linked in early, so that its early init routine runs prior to other fs code. This way, other filesystem code can register their own sysctls using the helpers after this: * register_sysctl_init() * register_sysctl() Link: https://lkml.kernel.org/r/20211129211943.640266-3-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Anil S Keshavamurthy Cc: Antti Palosaari Cc: Christian Brauner Cc: "David S. Miller" Cc: Eric Biederman Cc: Eric Biggers Cc: Iurii Zaikin Cc: Kees Cook Cc: Lukas Middendorf Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/Makefile | 3 ++- fs/namespace.c | 24 +++++++++++++++++++++++- fs/sysctls.c | 9 +++++---- include/linux/mount.h | 3 --- kernel/sysctl.c | 14 -------------- 5 files changed, 30 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/Makefile b/fs/Makefile index ea8770d124da..dab324aea08f 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -6,6 +6,8 @@ # Rewritten to use lists instead of if-statements. # +obj-$(CONFIG_SYSCTL) += sysctls.o + obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ ioctl.o readdir.o select.o dcache.o inode.o \ @@ -28,7 +30,6 @@ obj-y += notify/ obj-$(CONFIG_EPOLL) += eventpoll.o obj-y += anon_inodes.o obj-$(CONFIG_SIGNALFD) += signalfd.o -obj-$(CONFIG_SYSCTL) += sysctls.o obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o obj-$(CONFIG_USERFAULTFD) += userfaultfd.o diff --git a/fs/namespace.c b/fs/namespace.c index dc31ad6b370f..40b994a29e90 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -37,7 +37,7 @@ #include "internal.h" /* Maximum number of mounts in a mount namespace */ -unsigned int sysctl_mount_max __read_mostly = 100000; +static unsigned int sysctl_mount_max __read_mostly = 100000; static unsigned int m_hash_mask __read_mostly; static unsigned int m_hash_shift __read_mostly; @@ -4620,3 +4620,25 @@ const struct proc_ns_operations mntns_operations = { .install = mntns_install, .owner = mntns_owner, }; + +#ifdef CONFIG_SYSCTL +static struct ctl_table fs_namespace_sysctls[] = { + { + .procname = "mount-max", + .data = &sysctl_mount_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, + { } +}; + +static int __init init_fs_namespace_sysctls(void) +{ + register_sysctl_init("fs", fs_namespace_sysctls); + return 0; +} +fs_initcall(init_fs_namespace_sysctls); + +#endif /* CONFIG_SYSCTL */ diff --git a/fs/sysctls.c b/fs/sysctls.c index 54216cd1ecd7..c701273c9432 100644 --- a/fs/sysctls.c +++ b/fs/sysctls.c @@ -29,10 +29,11 @@ static struct ctl_table fs_shared_sysctls[] = { { } }; -static int __init init_fs_shared_sysctls(void) +DECLARE_SYSCTL_BASE(fs, fs_shared_sysctls); + +static int __init init_fs_sysctls(void) { - register_sysctl_init("fs", fs_shared_sysctls); - return 0; + return register_sysctl_base(fs); } -early_initcall(init_fs_shared_sysctls); +early_initcall(init_fs_sysctls); diff --git a/include/linux/mount.h b/include/linux/mount.h index 5d92a7e1a742..7f18a7555dff 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -113,9 +113,6 @@ extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern dev_t name_to_dev_t(const char *name); - -extern unsigned int sysctl_mount_max; - extern bool path_is_mountpoint(const struct path *path); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 12456a535059..cdc3dc5f0005 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2811,18 +2811,6 @@ static struct ctl_table vm_table[] = { { } }; -static struct ctl_table fs_table[] = { - { - .procname = "mount-max", - .data = &sysctl_mount_max, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ONE, - }, - { } -}; - static struct ctl_table debug_table[] = { #ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { @@ -2853,7 +2841,6 @@ static struct ctl_table dev_table[] = { DECLARE_SYSCTL_BASE(kernel, kern_table); DECLARE_SYSCTL_BASE(vm, vm_table); -DECLARE_SYSCTL_BASE(fs, fs_table); DECLARE_SYSCTL_BASE(debug, debug_table); DECLARE_SYSCTL_BASE(dev, dev_table); @@ -2861,7 +2848,6 @@ int __init sysctl_init(void) { register_sysctl_base(kernel); register_sysctl_base(vm); - register_sysctl_base(fs); register_sysctl_base(debug); register_sysctl_base(dev); -- cgit v1.2.3 From d8c0418aac78e661b5283c9d6a1dfc61d44f26fd Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 21 Jan 2022 22:13:31 -0800 Subject: kernel/sysctl.c: rename sysctl_init() to sysctl_init_bases() Rename sysctl_init() to sysctl_init_bases() so to reflect exactly what this is doing. Link: https://lkml.kernel.org/r/20211129211943.640266-4-mcgrof@kernel.org Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Anil S Keshavamurthy Cc: Antti Palosaari Cc: Christian Brauner Cc: "David S. Miller" Cc: Eric Biederman Cc: Eric Biggers Cc: Iurii Zaikin Cc: Kees Cook Cc: Lukas Middendorf Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Stephen Kitt Cc: Xiaoming Ni Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/alignment.c | 2 +- arch/sh/mm/alignment.c | 2 +- fs/proc/proc_sysctl.c | 4 ++-- include/linux/sysctl.h | 2 +- kernel/sysctl.c | 2 +- 5 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c index adbb3817d0be..6f499559d193 100644 --- a/arch/arm/mm/alignment.c +++ b/arch/arm/mm/alignment.c @@ -1005,7 +1005,7 @@ static int __init noalign_setup(char *__unused) __setup("noalign", noalign_setup); /* - * This needs to be done after sysctl_init, otherwise sys/ will be + * This needs to be done after sysctl_init_bases(), otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since * it isn't a sysctl, and it doesn't contain sysctl information. * We now locate it in /proc/cpu/alignment instead. diff --git a/arch/sh/mm/alignment.c b/arch/sh/mm/alignment.c index fb517b82a87b..d802801ceb93 100644 --- a/arch/sh/mm/alignment.c +++ b/arch/sh/mm/alignment.c @@ -161,7 +161,7 @@ static const struct proc_ops alignment_proc_ops = { }; /* - * This needs to be done after sysctl_init, otherwise sys/ will be + * This needs to be done after sysctl_init_bases(), otherwise sys/ will be * overwritten. Actually, this shouldn't be in sys/ at all since * it isn't a sysctl, and it doesn't contain sysctl information. * We now locate it in /proc/cpu/alignment instead. diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c index 95dfd195e04e..7d9cfc730bd4 100644 --- a/fs/proc/proc_sysctl.c +++ b/fs/proc/proc_sysctl.c @@ -1419,7 +1419,7 @@ EXPORT_SYMBOL(register_sysctl); * Context: Can only be called after your respective sysctl base path has been * registered. So for instance, most base directories are registered early on * init before init levels are processed through proc_sys_init() and - * sysctl_init(). + * sysctl_init_bases(). */ void __init __register_sysctl_init(const char *path, struct ctl_table *table, const char *table_name) @@ -1768,7 +1768,7 @@ int __init proc_sys_init(void) proc_sys_root->proc_dir_ops = &proc_sys_dir_file_operations; proc_sys_root->nlink = 0; - return sysctl_init(); + return sysctl_init_bases(); } struct sysctl_alias { diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 02134a8abad7..180adf7da785 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -228,7 +228,7 @@ struct ctl_table_header *register_sysctl_paths(const struct ctl_path *path, void unregister_sysctl_table(struct ctl_table_header * table); -extern int sysctl_init(void); +extern int sysctl_init_bases(void); extern void __register_sysctl_init(const char *path, struct ctl_table *table, const char *table_name); #define register_sysctl_init(path, table) __register_sysctl_init(path, table, #table) diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cdc3dc5f0005..bb07183cd305 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2844,7 +2844,7 @@ DECLARE_SYSCTL_BASE(vm, vm_table); DECLARE_SYSCTL_BASE(debug, debug_table); DECLARE_SYSCTL_BASE(dev, dev_table); -int __init sysctl_init(void) +int __init sysctl_init_bases(void) { register_sysctl_base(kernel); register_sysctl_base(vm); -- cgit v1.2.3 From fdcd4073fccc6f989308be3f1d61d8a68cd990ce Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:13:34 -0800 Subject: printk: fix build warning when CONFIG_PRINTK=n build warning when CONFIG_PRINTK=n kernel/printk/printk.c:175:5: warning: no previous prototype for 'devkmsg_sysctl_set_loglvl' [-Wmissing-prototypes] devkmsg_sysctl_set_loglvl() is only used in sysctl.c when CONFIG_PRINTK=y, but it participates in the build when CONFIG_PRINTK=n. So add compile dependency CONFIG_PRINTK=y && CONFIG_SYSCTL=y to fix the build warning. Link: https://lkml.kernel.org/r/20211129211943.640266-5-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Anil S Keshavamurthy Cc: Antti Palosaari Cc: Christian Brauner Cc: "David S. Miller" Cc: Eric Biederman Cc: Eric Biggers Cc: Iurii Zaikin Cc: Kees Cook Cc: Lukas Middendorf Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Stephen Kitt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/printk.h | 4 ---- kernel/printk/internal.h | 2 ++ kernel/printk/printk.c | 3 ++- 3 files changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/printk.h b/include/linux/printk.h index 9497f6b98339..1522df223c0f 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -183,10 +183,6 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies, extern int printk_delay_msec; extern int dmesg_restrict; -extern int -devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buf, - size_t *lenp, loff_t *ppos); - extern void wake_up_klogd(void); char *log_buf_addr_get(void); diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 6b1c4b399845..d947ca6c84f9 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -6,6 +6,8 @@ #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) void __init printk_sysctl_init(void); +int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos); #else #define printk_sysctl_init() do { } while (0) #endif diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 363a493bded8..82abfaf3c2aa 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -171,7 +171,7 @@ static int __init control_devkmsg(char *str) __setup("printk.devkmsg=", control_devkmsg); char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit"; - +#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -210,6 +210,7 @@ int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write, return 0; } +#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */ /* Number of registered extended console drivers. */ static int nr_ext_console_drivers; -- cgit v1.2.3 From f0bc21b268c1464603192a00851cdbbf7c2cdc36 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:13:38 -0800 Subject: fs/coredump: move coredump sysctls into its own file This moves the fs/coredump.c respective sysctls to its own file. Link: https://lkml.kernel.org/r/20211129211943.640266-6-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Anil S Keshavamurthy Cc: Antti Palosaari Cc: Christian Brauner Cc: "David S. Miller" Cc: Eric Biederman Cc: Eric Biggers Cc: Iurii Zaikin Cc: Kees Cook Cc: Lukas Middendorf Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Stephen Kitt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/coredump.c | 66 ++++++++++++++++++++++++++++++++++++++++++++---- fs/exec.c | 55 ---------------------------------------- include/linux/coredump.h | 10 +++++--- kernel/sysctl.c | 2 -- 4 files changed, 67 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/fs/coredump.c b/fs/coredump.c index 7dece20b162b..1c060c0a2d72 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -41,6 +41,7 @@ #include #include #include +#include #include #include @@ -52,9 +53,9 @@ #include -int core_uses_pid; -unsigned int core_pipe_limit; -char core_pattern[CORENAME_MAX_SIZE] = "core"; +static int core_uses_pid; +static unsigned int core_pipe_limit; +static char core_pattern[CORENAME_MAX_SIZE] = "core"; static int core_name_size = CORENAME_MAX_SIZE; struct core_name { @@ -62,8 +63,6 @@ struct core_name { int used, size; }; -/* The maximal length of core_pattern is also specified in sysctl.c */ - static int expand_corename(struct core_name *cn, int size) { char *corename = krealloc(cn->corename, size, GFP_KERNEL); @@ -893,6 +892,63 @@ int dump_align(struct coredump_params *cprm, int align) } EXPORT_SYMBOL(dump_align); +#ifdef CONFIG_SYSCTL + +void validate_coredump_safety(void) +{ + if (suid_dumpable == SUID_DUMP_ROOT && + core_pattern[0] != '/' && core_pattern[0] != '|') { + pr_warn( +"Unsafe core_pattern used with fs.suid_dumpable=2.\n" +"Pipe handler or fully qualified core dump path required.\n" +"Set kernel.core_pattern before fs.suid_dumpable.\n" + ); + } +} + +static int proc_dostring_coredump(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + int error = proc_dostring(table, write, buffer, lenp, ppos); + + if (!error) + validate_coredump_safety(); + return error; +} + +static struct ctl_table coredump_sysctls[] = { + { + .procname = "core_uses_pid", + .data = &core_uses_pid, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "core_pattern", + .data = core_pattern, + .maxlen = CORENAME_MAX_SIZE, + .mode = 0644, + .proc_handler = proc_dostring_coredump, + }, + { + .procname = "core_pipe_limit", + .data = &core_pipe_limit, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { } +}; + +static int __init init_fs_coredump_sysctls(void) +{ + register_sysctl_init("kernel", coredump_sysctls); + return 0; +} +fs_initcall(init_fs_coredump_sysctls); +#endif /* CONFIG_SYSCTL */ + /* * The purpose of always_dump_vma() is to make sure that special kernel mappings * that are useful for post-mortem analysis are included in every core dump. diff --git a/fs/exec.c b/fs/exec.c index 310750340e4a..79f2c9483302 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2103,20 +2103,6 @@ COMPAT_SYSCALL_DEFINE5(execveat, int, fd, #ifdef CONFIG_SYSCTL -static void validate_coredump_safety(void) -{ -#ifdef CONFIG_COREDUMP - if (suid_dumpable == SUID_DUMP_ROOT && - core_pattern[0] != '/' && core_pattern[0] != '|') { - pr_warn( -"Unsafe core_pattern used with fs.suid_dumpable=2.\n" -"Pipe handler or fully qualified core dump path required.\n" -"Set kernel.core_pattern before fs.suid_dumpable.\n" - ); - } -#endif -} - static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -2140,50 +2126,9 @@ static struct ctl_table fs_exec_sysctls[] = { { } }; -#ifdef CONFIG_COREDUMP - -static int proc_dostring_coredump(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int error = proc_dostring(table, write, buffer, lenp, ppos); - - if (!error) - validate_coredump_safety(); - return error; -} - -static struct ctl_table kernel_exec_sysctls[] = { - { - .procname = "core_uses_pid", - .data = &core_uses_pid, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "core_pattern", - .data = core_pattern, - .maxlen = CORENAME_MAX_SIZE, - .mode = 0644, - .proc_handler = proc_dostring_coredump, - }, - { - .procname = "core_pipe_limit", - .data = &core_pipe_limit, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { } -}; -#endif - static int __init init_fs_exec_sysctls(void) { register_sysctl_init("fs", fs_exec_sysctls); -#ifdef CONFIG_COREDUMP - register_sysctl_init("kernel", kernel_exec_sysctls); -#endif return 0; } diff --git a/include/linux/coredump.h b/include/linux/coredump.h index 78fcd776b185..248a68c668b4 100644 --- a/include/linux/coredump.h +++ b/include/linux/coredump.h @@ -14,10 +14,6 @@ struct core_vma_metadata { unsigned long dump_size; }; -extern int core_uses_pid; -extern char core_pattern[]; -extern unsigned int core_pipe_limit; - /* * These are the only things you should do on a core-file: use only these * functions to write out all the necessary info. @@ -37,4 +33,10 @@ extern void do_coredump(const kernel_siginfo_t *siginfo); static inline void do_coredump(const kernel_siginfo_t *siginfo) {} #endif +#if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL) +extern void validate_coredump_safety(void); +#else +static inline void validate_coredump_safety(void) {} +#endif + #endif /* _LINUX_COREDUMP_H */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index bb07183cd305..c78585292005 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -62,12 +62,10 @@ #include #include #include -#include #include #include #include #include -#include #include #include #include -- cgit v1.2.3 From a737a3c6744bc822d1e6a837fef550e665ddf877 Mon Sep 17 00:00:00 2001 From: Xiaoming Ni Date: Fri, 21 Jan 2022 22:13:41 -0800 Subject: kprobe: move sysctl_kprobes_optimization to kprobes.c kernel/sysctl.c is a kitchen sink where everyone leaves their dirty dishes, this makes it very difficult to maintain. To help with this maintenance let's start by moving sysctls to places where they actually belong. The proc sysctl maintainers do not want to know what sysctl knobs you wish to add for your own piece of code, we just care about the core logic. Move sysctl_kprobes_optimization from kernel/sysctl.c to kernel/kprobes.c. Use register_sysctl() to register the sysctl interface. [mcgrof@kernel.org: fix compile issue when CONFIG_OPTPROBES is disabled] Link: https://lkml.kernel.org/r/20211129211943.640266-7-mcgrof@kernel.org Signed-off-by: Xiaoming Ni Signed-off-by: Luis Chamberlain Cc: Al Viro Cc: Anil S Keshavamurthy Cc: Antti Palosaari Cc: Christian Brauner Cc: "David S. Miller" Cc: Eric Biederman Cc: Eric Biggers Cc: Iurii Zaikin Cc: Kees Cook Cc: Lukas Middendorf Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Stephen Kitt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kprobes.h | 6 ------ kernel/kprobes.c | 30 ++++++++++++++++++++++++++---- kernel/sysctl.c | 12 ------------ 3 files changed, 26 insertions(+), 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 8c8f7a4d93af..19b884353b15 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -348,12 +348,6 @@ extern void opt_pre_handler(struct kprobe *p, struct pt_regs *regs); DEFINE_INSN_CACHE_OPS(optinsn); -#ifdef CONFIG_SYSCTL -extern int sysctl_kprobes_optimization; -extern int proc_kprobes_optimization_handler(struct ctl_table *table, - int write, void *buffer, - size_t *length, loff_t *ppos); -#endif /* CONFIG_SYSCTL */ extern void wait_for_kprobe_optimizer(void); #else /* !CONFIG_OPTPROBES */ static inline void wait_for_kprobe_optimizer(void) { } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 21eccc961bba..94cab8c9ce56 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -48,6 +48,9 @@ #define KPROBE_HASH_BITS 6 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS) +#if !defined(CONFIG_OPTPROBES) || !defined(CONFIG_SYSCTL) +#define kprobe_sysctls_init() do { } while (0) +#endif static int kprobes_initialized; /* kprobe_table can be accessed by @@ -938,10 +941,10 @@ static void unoptimize_all_kprobes(void) } static DEFINE_MUTEX(kprobe_sysctl_mutex); -int sysctl_kprobes_optimization; -int proc_kprobes_optimization_handler(struct ctl_table *table, int write, - void *buffer, size_t *length, - loff_t *ppos) +static int sysctl_kprobes_optimization; +static int proc_kprobes_optimization_handler(struct ctl_table *table, + int write, void *buffer, + size_t *length, loff_t *ppos) { int ret; @@ -957,6 +960,24 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write, return ret; } + +static struct ctl_table kprobe_sysctls[] = { + { + .procname = "kprobes-optimization", + .data = &sysctl_kprobes_optimization, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_kprobes_optimization_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static void __init kprobe_sysctls_init(void) +{ + register_sysctl_init("debug", kprobe_sysctls); +} #endif /* CONFIG_SYSCTL */ /* Put a breakpoint for a probe. */ @@ -2584,6 +2605,7 @@ static int __init init_kprobes(void) err = register_module_notifier(&kprobe_module_nb); kprobes_initialized = (err == 0); + kprobe_sysctls_init(); return err; } early_initcall(init_kprobes); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index c78585292005..c322bb629d10 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -56,7 +56,6 @@ #include #include #include -#include #include #include #include @@ -2818,17 +2817,6 @@ static struct ctl_table debug_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, -#endif -#if defined(CONFIG_OPTPROBES) - { - .procname = "kprobes-optimization", - .data = &sysctl_kprobes_optimization, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_kprobes_optimization_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, #endif { } }; -- cgit v1.2.3 From 4a57d6bbaecd28c8175dc5da013009e4158018c2 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Fri, 21 Jan 2022 22:14:10 -0800 Subject: locking/rwlocks: introduce write_lock_nested In preparation for converting bit_spin_lock to rwlock in zsmalloc so that multiple writers of zspages can run at the same time but those zspages are supposed to be different zspage instance. Thus, it's not deadlock. This patch adds write_lock_nested to support the case for LOCKDEP. [minchan@kernel.org: fix write_lock_nested for RT] Link: https://lkml.kernel.org/r/YZfrMTAXV56HFWJY@google.com [bigeasy@linutronix.de: fixup write_lock_nested() implementation] Link: https://lkml.kernel.org/r/20211123170134.y6xb7pmpgdn4m3bn@linutronix.de Link: https://lkml.kernel.org/r/20211115185909.3949505-8-minchan@kernel.org Signed-off-by: Minchan Kim Signed-off-by: Sebastian Andrzej Siewior Acked-by: Peter Zijlstra (Intel) Acked-by: Sebastian Andrzej Siewior Tested-by: Sebastian Andrzej Siewior Cc: Mike Galbraith Cc: Sergey Senozhatsky Cc: Thomas Gleixner Cc: Naresh Kamboju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/rwlock.h | 6 ++++++ include/linux/rwlock_api_smp.h | 8 ++++++++ include/linux/rwlock_rt.h | 10 ++++++++++ include/linux/spinlock_api_up.h | 1 + kernel/locking/spinlock.c | 10 ++++++++++ kernel/locking/spinlock_rt.c | 12 ++++++++++++ 6 files changed, 47 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h index 2c0ad417ce3c..8f416c5e929e 100644 --- a/include/linux/rwlock.h +++ b/include/linux/rwlock.h @@ -55,6 +55,12 @@ do { \ #define write_lock(lock) _raw_write_lock(lock) #define read_lock(lock) _raw_read_lock(lock) +#ifdef CONFIG_DEBUG_LOCK_ALLOC +#define write_lock_nested(lock, subclass) _raw_write_lock_nested(lock, subclass) +#else +#define write_lock_nested(lock, subclass) _raw_write_lock(lock) +#endif + #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define read_lock_irqsave(lock, flags) \ diff --git a/include/linux/rwlock_api_smp.h b/include/linux/rwlock_api_smp.h index f1db6f17c4fb..dceb0a59b692 100644 --- a/include/linux/rwlock_api_smp.h +++ b/include/linux/rwlock_api_smp.h @@ -17,6 +17,7 @@ void __lockfunc _raw_read_lock(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock(rwlock_t *lock) __acquires(lock); +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) __acquires(lock); void __lockfunc _raw_read_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_write_lock_bh(rwlock_t *lock) __acquires(lock); void __lockfunc _raw_read_lock_irq(rwlock_t *lock) __acquires(lock); @@ -209,6 +210,13 @@ static inline void __raw_write_lock(rwlock_t *lock) LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); } +static inline void __raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + preempt_disable(); + rwlock_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + LOCK_CONTENDED(lock, do_raw_write_trylock, do_raw_write_lock); +} + #endif /* !CONFIG_GENERIC_LOCKBREAK || CONFIG_DEBUG_LOCK_ALLOC */ static inline void __raw_write_unlock(rwlock_t *lock) diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h index 49c1f3842ed5..8544ff05e594 100644 --- a/include/linux/rwlock_rt.h +++ b/include/linux/rwlock_rt.h @@ -28,6 +28,7 @@ extern void rt_read_lock(rwlock_t *rwlock); extern int rt_read_trylock(rwlock_t *rwlock); extern void rt_read_unlock(rwlock_t *rwlock); extern void rt_write_lock(rwlock_t *rwlock); +extern void rt_write_lock_nested(rwlock_t *rwlock, int subclass); extern int rt_write_trylock(rwlock_t *rwlock); extern void rt_write_unlock(rwlock_t *rwlock); @@ -83,6 +84,15 @@ static __always_inline void write_lock(rwlock_t *rwlock) rt_write_lock(rwlock); } +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static __always_inline void write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rt_write_lock_nested(rwlock, subclass); +} +#else +#define write_lock_nested(lock, subclass) rt_write_lock(((void)(subclass), (lock))) +#endif + static __always_inline void write_lock_bh(rwlock_t *rwlock) { local_bh_disable(); diff --git a/include/linux/spinlock_api_up.h b/include/linux/spinlock_api_up.h index d0d188861ad6..b8ba00ccccde 100644 --- a/include/linux/spinlock_api_up.h +++ b/include/linux/spinlock_api_up.h @@ -59,6 +59,7 @@ #define _raw_spin_lock_nested(lock, subclass) __LOCK(lock) #define _raw_read_lock(lock) __LOCK(lock) #define _raw_write_lock(lock) __LOCK(lock) +#define _raw_write_lock_nested(lock, subclass) __LOCK(lock) #define _raw_spin_lock_bh(lock) __LOCK_BH(lock) #define _raw_read_lock_bh(lock) __LOCK_BH(lock) #define _raw_write_lock_bh(lock) __LOCK_BH(lock) diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c index b562f9289372..7f49baaa4979 100644 --- a/kernel/locking/spinlock.c +++ b/kernel/locking/spinlock.c @@ -300,6 +300,16 @@ void __lockfunc _raw_write_lock(rwlock_t *lock) __raw_write_lock(lock); } EXPORT_SYMBOL(_raw_write_lock); + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +#define __raw_write_lock_nested(lock, subclass) __raw_write_lock(((void)(subclass), (lock))) +#endif + +void __lockfunc _raw_write_lock_nested(rwlock_t *lock, int subclass) +{ + __raw_write_lock_nested(lock, subclass); +} +EXPORT_SYMBOL(_raw_write_lock_nested); #endif #ifndef CONFIG_INLINE_WRITE_LOCK_IRQSAVE diff --git a/kernel/locking/spinlock_rt.c b/kernel/locking/spinlock_rt.c index 9e396a09fe0f..48a19ed8486d 100644 --- a/kernel/locking/spinlock_rt.c +++ b/kernel/locking/spinlock_rt.c @@ -239,6 +239,18 @@ void __sched rt_write_lock(rwlock_t *rwlock) } EXPORT_SYMBOL(rt_write_lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void __sched rt_write_lock_nested(rwlock_t *rwlock, int subclass) +{ + rtlock_might_resched(); + rwlock_acquire(&rwlock->dep_map, subclass, 0, _RET_IP_); + rwbase_write_lock(&rwlock->rwbase, TASK_RTLOCK_WAIT); + rcu_read_lock(); + migrate_disable(); +} +EXPORT_SYMBOL(rt_write_lock_nested); +#endif + void __sched rt_read_unlock(rwlock_t *rwlock) { rwlock_release(&rwlock->dep_map, _RET_IP_); -- cgit v1.2.3 From 6dfbbae14a7b961f41d80a106e1ab60e86d061c5 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 21 Jan 2022 22:14:20 -0800 Subject: fs: proc: store PDE()->data into inode->i_private PDE_DATA(inode) is introduced to get user private data and hide the layout of struct proc_dir_entry. The inode->i_private is used to do the same thing as well. Save a copy of user private data to inode-> i_private when proc inode is allocated. This means the user also can get their private data by inode->i_private. Introduce pde_data() to wrap inode->i_private so that we can remove PDE_DATA() from fs/proc/generic.c and make PTE_DATE() as a wrapper of pde_data(). It will be easier if we decide to remove PDE_DATE() in the future. Link: https://lkml.kernel.org/r/20211124081956.87711-1-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Christian Brauner Cc: Alexey Dobriyan Cc: Alexey Gladkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/generic.c | 6 ------ fs/proc/inode.c | 1 + fs/proc/internal.h | 5 ----- include/linux/proc_fs.h | 13 ++++++++++++- 4 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 5b78739e60e4..f2132407e133 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -791,12 +791,6 @@ void proc_remove(struct proc_dir_entry *de) } EXPORT_SYMBOL(proc_remove); -void *PDE_DATA(const struct inode *inode) -{ - return __PDE_DATA(inode); -} -EXPORT_SYMBOL(PDE_DATA); - /* * Pull a user buffer into memory and pass it to the file's write handler if * one is supplied. The ->write() method is permitted to modify the diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 599eb724ff2d..f84355c5a36d 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -650,6 +650,7 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) return NULL; } + inode->i_private = de->data; inode->i_ino = de->low_ino; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); PROC_I(inode)->pde = de; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 03415f3fb3a8..06a80f78433d 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -115,11 +115,6 @@ static inline struct proc_dir_entry *PDE(const struct inode *inode) return PROC_I(inode)->pde; } -static inline void *__PDE_DATA(const struct inode *inode) -{ - return PDE(inode)->data; -} - static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 01b9268451a8..b6e7005cc1b2 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -110,7 +110,18 @@ extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *proc_create(const char *name, umode_t mode, struct proc_dir_entry *parent, const struct proc_ops *proc_ops); extern void proc_set_size(struct proc_dir_entry *, loff_t); extern void proc_set_user(struct proc_dir_entry *, kuid_t, kgid_t); -extern void *PDE_DATA(const struct inode *); + +/* + * Obtain the private data passed by user through proc_create_data() or + * related. + */ +static inline void *pde_data(const struct inode *inode) +{ + return inode->i_private; +} + +#define PDE_DATA(i) pde_data(i) + extern void *proc_get_parent_data(const struct inode *); extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); -- cgit v1.2.3 From 359745d78351c6f5442435f81549f0207ece28aa Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Fri, 21 Jan 2022 22:14:23 -0800 Subject: proc: remove PDE_DATA() completely Remove PDE_DATA() completely and replace it with pde_data(). [akpm@linux-foundation.org: fix naming clash in drivers/nubus/proc.c] [akpm@linux-foundation.org: now fix it properly] Link: https://lkml.kernel.org/r/20211124081956.87711-2-songmuchun@bytedance.com Signed-off-by: Muchun Song Acked-by: Christian Brauner Cc: Alexey Dobriyan Cc: Alexey Gladkov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/srm_env.c | 4 +-- arch/arm/kernel/atags_proc.c | 2 +- arch/ia64/kernel/salinfo.c | 10 +++--- arch/powerpc/kernel/proc_powerpc.c | 4 +-- arch/sh/mm/alignment.c | 2 +- arch/xtensa/platforms/iss/simdisk.c | 4 +-- drivers/acpi/proc.c | 2 +- drivers/hwmon/dell-smm-hwmon.c | 4 +-- drivers/net/bonding/bond_procfs.c | 8 ++--- drivers/net/wireless/cisco/airo.c | 22 ++++++------- drivers/net/wireless/intersil/hostap/hostap_ap.c | 16 +++++----- .../net/wireless/intersil/hostap/hostap_download.c | 2 +- drivers/net/wireless/intersil/hostap/hostap_proc.c | 24 +++++++-------- drivers/net/wireless/ray_cs.c | 2 +- drivers/nubus/proc.c | 36 +++++++++++----------- drivers/parisc/led.c | 4 +-- drivers/pci/proc.c | 10 +++--- drivers/platform/x86/thinkpad_acpi.c | 4 +-- drivers/platform/x86/toshiba_acpi.c | 16 +++++----- drivers/pnp/isapnp/proc.c | 2 +- drivers/pnp/pnpbios/proc.c | 4 +-- drivers/scsi/scsi_proc.c | 4 +-- drivers/usb/gadget/function/rndis.c | 4 +-- drivers/zorro/proc.c | 2 +- fs/afs/proc.c | 6 ++-- fs/ext4/mballoc.c | 14 ++++----- fs/jbd2/journal.c | 2 +- fs/proc/proc_net.c | 8 ++--- include/linux/proc_fs.h | 4 +-- include/linux/seq_file.h | 2 +- ipc/util.c | 2 +- kernel/irq/proc.c | 8 ++--- kernel/resource.c | 4 +-- net/atm/proc.c | 4 +-- net/bluetooth/af_bluetooth.c | 8 ++--- net/can/bcm.c | 2 +- net/can/proc.c | 2 +- net/core/neighbour.c | 6 ++-- net/core/pktgen.c | 6 ++-- net/ipv4/netfilter/ipt_CLUSTERIP.c | 6 ++-- net/ipv4/raw.c | 8 ++--- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 6 ++-- net/netfilter/x_tables.c | 10 +++--- net/netfilter/xt_hashlimit.c | 18 +++++------ net/netfilter/xt_recent.c | 4 +-- net/sunrpc/auth_gss/svcauth_gss.c | 4 +-- net/sunrpc/cache.c | 24 +++++++-------- net/sunrpc/stats.c | 2 +- sound/core/info.c | 4 +-- 50 files changed, 178 insertions(+), 180 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/kernel/srm_env.c b/arch/alpha/kernel/srm_env.c index 528d2be58182..217b4dca51dd 100644 --- a/arch/alpha/kernel/srm_env.c +++ b/arch/alpha/kernel/srm_env.c @@ -83,14 +83,14 @@ static int srm_env_proc_show(struct seq_file *m, void *v) static int srm_env_proc_open(struct inode *inode, struct file *file) { - return single_open(file, srm_env_proc_show, PDE_DATA(inode)); + return single_open(file, srm_env_proc_show, pde_data(inode)); } static ssize_t srm_env_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { int res; - unsigned long id = (unsigned long)PDE_DATA(file_inode(file)); + unsigned long id = (unsigned long)pde_data(file_inode(file)); char *buf = (char *) __get_free_page(GFP_USER); unsigned long ret1, ret2; diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c index 3c2faf2bd124..3ec2afe78423 100644 --- a/arch/arm/kernel/atags_proc.c +++ b/arch/arm/kernel/atags_proc.c @@ -13,7 +13,7 @@ struct buffer { static ssize_t atags_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct buffer *b = PDE_DATA(file_inode(file)); + struct buffer *b = pde_data(file_inode(file)); return simple_read_from_buffer(buf, count, ppos, b->data, b->size); } diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c index a25ab9b37953..bd3ba276e69c 100644 --- a/arch/ia64/kernel/salinfo.c +++ b/arch/ia64/kernel/salinfo.c @@ -282,7 +282,7 @@ salinfo_event_open(struct inode *inode, struct file *file) static ssize_t salinfo_event_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { - struct salinfo_data *data = PDE_DATA(file_inode(file)); + struct salinfo_data *data = pde_data(file_inode(file)); char cmd[32]; size_t size; int i, n, cpu = -1; @@ -340,7 +340,7 @@ static const struct proc_ops salinfo_event_proc_ops = { static int salinfo_log_open(struct inode *inode, struct file *file) { - struct salinfo_data *data = PDE_DATA(inode); + struct salinfo_data *data = pde_data(inode); if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -365,7 +365,7 @@ salinfo_log_open(struct inode *inode, struct file *file) static int salinfo_log_release(struct inode *inode, struct file *file) { - struct salinfo_data *data = PDE_DATA(inode); + struct salinfo_data *data = pde_data(inode); if (data->state == STATE_NO_DATA) { vfree(data->log_buffer); @@ -433,7 +433,7 @@ retry: static ssize_t salinfo_log_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { - struct salinfo_data *data = PDE_DATA(file_inode(file)); + struct salinfo_data *data = pde_data(file_inode(file)); u8 *buf; u64 bufsize; @@ -494,7 +494,7 @@ salinfo_log_clear(struct salinfo_data *data, int cpu) static ssize_t salinfo_log_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - struct salinfo_data *data = PDE_DATA(file_inode(file)); + struct salinfo_data *data = pde_data(file_inode(file)); char cmd[32]; size_t size; u32 offset; diff --git a/arch/powerpc/kernel/proc_powerpc.c b/arch/powerpc/kernel/proc_powerpc.c index 877817471e3c..6a029f2378e1 100644 --- a/arch/powerpc/kernel/proc_powerpc.c +++ b/arch/powerpc/kernel/proc_powerpc.c @@ -25,7 +25,7 @@ static ssize_t page_map_read( struct file *file, char __user *buf, size_t nbytes loff_t *ppos) { return simple_read_from_buffer(buf, nbytes, ppos, - PDE_DATA(file_inode(file)), PAGE_SIZE); + pde_data(file_inode(file)), PAGE_SIZE); } static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) @@ -34,7 +34,7 @@ static int page_map_mmap( struct file *file, struct vm_area_struct *vma ) return -EINVAL; remap_pfn_range(vma, vma->vm_start, - __pa(PDE_DATA(file_inode(file))) >> PAGE_SHIFT, + __pa(pde_data(file_inode(file))) >> PAGE_SHIFT, PAGE_SIZE, vma->vm_page_prot); return 0; } diff --git a/arch/sh/mm/alignment.c b/arch/sh/mm/alignment.c index d802801ceb93..3a76a766f423 100644 --- a/arch/sh/mm/alignment.c +++ b/arch/sh/mm/alignment.c @@ -140,7 +140,7 @@ static int alignment_proc_open(struct inode *inode, struct file *file) static ssize_t alignment_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { - int *data = PDE_DATA(file_inode(file)); + int *data = pde_data(file_inode(file)); char mode; if (count > 0) { diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 07b642c1916a..8eb6ad1a3a1d 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -208,7 +208,7 @@ static int simdisk_detach(struct simdisk *dev) static ssize_t proc_read_simdisk(struct file *file, char __user *buf, size_t size, loff_t *ppos) { - struct simdisk *dev = PDE_DATA(file_inode(file)); + struct simdisk *dev = pde_data(file_inode(file)); const char *s = dev->filename; if (s) { ssize_t n = simple_read_from_buffer(buf, size, ppos, @@ -225,7 +225,7 @@ static ssize_t proc_write_simdisk(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char *tmp = memdup_user_nul(buf, count); - struct simdisk *dev = PDE_DATA(file_inode(file)); + struct simdisk *dev = pde_data(file_inode(file)); int err; if (IS_ERR(tmp)) diff --git a/drivers/acpi/proc.c b/drivers/acpi/proc.c index 0cca7991f186..4322f2da6d10 100644 --- a/drivers/acpi/proc.c +++ b/drivers/acpi/proc.c @@ -127,7 +127,7 @@ static int acpi_system_wakeup_device_open_fs(struct inode *inode, struct file *file) { return single_open(file, acpi_system_wakeup_device_seq_show, - PDE_DATA(inode)); + pde_data(inode)); } static const struct proc_ops acpi_system_wakeup_device_proc_ops = { diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c index d401f9acf450..9949eeb79378 100644 --- a/drivers/hwmon/dell-smm-hwmon.c +++ b/drivers/hwmon/dell-smm-hwmon.c @@ -451,7 +451,7 @@ static int i8k_get_power_status(void) static long i8k_ioctl(struct file *fp, unsigned int cmd, unsigned long arg) { - struct dell_smm_data *data = PDE_DATA(file_inode(fp)); + struct dell_smm_data *data = pde_data(file_inode(fp)); int __user *argp = (int __user *)arg; int speed, err; int val = 0; @@ -585,7 +585,7 @@ static int i8k_proc_show(struct seq_file *seq, void *offset) static int i8k_open_fs(struct inode *inode, struct file *file) { - return single_open(file, i8k_proc_show, PDE_DATA(inode)); + return single_open(file, i8k_proc_show, pde_data(inode)); } static const struct proc_ops i8k_proc_ops = { diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 2ec11af5f0cc..46b150e6289e 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -11,7 +11,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); struct list_head *iter; struct slave *slave; loff_t off = 0; @@ -30,7 +30,7 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); struct list_head *iter; struct slave *slave; bool found = false; @@ -57,7 +57,7 @@ static void bond_info_seq_stop(struct seq_file *seq, void *v) static void bond_info_show_master(struct seq_file *seq) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); const struct bond_opt_value *optval; struct slave *curr, *primary; int i; @@ -175,7 +175,7 @@ static void bond_info_show_master(struct seq_file *seq) static void bond_info_show_slave(struct seq_file *seq, const struct slave *slave) { - struct bonding *bond = PDE_DATA(file_inode(seq->file)); + struct bonding *bond = pde_data(file_inode(seq->file)); seq_printf(seq, "\nSlave Interface: %s\n", slave->dev->name); seq_printf(seq, "MII Status: %s\n", bond_slave_link_status(slave->link)); diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c index 45594f003ef7..452d08545d31 100644 --- a/drivers/net/wireless/cisco/airo.c +++ b/drivers/net/wireless/cisco/airo.c @@ -4672,7 +4672,7 @@ static ssize_t proc_write(struct file *file, static int proc_status_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *apriv = dev->ml_priv; CapabilityRid cap_rid; StatusRid status_rid; @@ -4756,7 +4756,7 @@ static int proc_stats_rid_open(struct inode *inode, u16 rid) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *apriv = dev->ml_priv; StatsRid stats; int i, j; @@ -4819,7 +4819,7 @@ static inline int sniffing_mode(struct airo_info *ai) static void proc_config_on_close(struct inode *inode, struct file *file) { struct proc_data *data = file->private_data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; char *line; @@ -5030,7 +5030,7 @@ static const char *get_rmode(__le16 mode) static int proc_config_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i; __le16 mode; @@ -5120,7 +5120,7 @@ static int proc_config_open(struct inode *inode, struct file *file) static void proc_SSID_on_close(struct inode *inode, struct file *file) { struct proc_data *data = file->private_data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; SsidRid SSID_rid; int i; @@ -5156,7 +5156,7 @@ static void proc_SSID_on_close(struct inode *inode, struct file *file) static void proc_APList_on_close(struct inode *inode, struct file *file) { struct proc_data *data = file->private_data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; APListRid *APList_rid = &ai->APList; int i; @@ -5280,7 +5280,7 @@ static int set_wep_tx_idx(struct airo_info *ai, u16 index, int perm, int lock) static void proc_wepkey_on_close(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i, rc; char key[16]; @@ -5331,7 +5331,7 @@ static void proc_wepkey_on_close(struct inode *inode, struct file *file) static int proc_wepkey_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; char *ptr; WepKeyRid wkr; @@ -5379,7 +5379,7 @@ static int proc_wepkey_open(struct inode *inode, struct file *file) static int proc_SSID_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i; char *ptr; @@ -5423,7 +5423,7 @@ static int proc_SSID_open(struct inode *inode, struct file *file) static int proc_APList_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; int i; char *ptr; @@ -5462,7 +5462,7 @@ static int proc_APList_open(struct inode *inode, struct file *file) static int proc_BSSList_open(struct inode *inode, struct file *file) { struct proc_data *data; - struct net_device *dev = PDE_DATA(inode); + struct net_device *dev = pde_data(inode); struct airo_info *ai = dev->ml_priv; char *ptr; BSSListRid BSSList_rid; diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c index 8bcc1cdcb75b..462ccc7d7d1a 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_ap.c +++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c @@ -69,7 +69,7 @@ static void prism2_send_mgmt(struct net_device *dev, #if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS) static int ap_debug_proc_show(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); seq_printf(m, "BridgedUnicastFrames=%u\n", ap->bridged_unicast); seq_printf(m, "BridgedMulticastFrames=%u\n", ap->bridged_multicast); @@ -320,7 +320,7 @@ void hostap_deauth_all_stas(struct net_device *dev, struct ap_data *ap, static int ap_control_proc_show(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); char *policy_txt; struct mac_entry *entry; @@ -352,20 +352,20 @@ static int ap_control_proc_show(struct seq_file *m, void *v) static void *ap_control_proc_start(struct seq_file *m, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_lock_bh(&ap->mac_restrictions.lock); return seq_list_start_head(&ap->mac_restrictions.mac_list, *_pos); } static void *ap_control_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); return seq_list_next(v, &ap->mac_restrictions.mac_list, _pos); } static void ap_control_proc_stop(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_unlock_bh(&ap->mac_restrictions.lock); } @@ -554,20 +554,20 @@ static int prism2_ap_proc_show(struct seq_file *m, void *v) static void *prism2_ap_proc_start(struct seq_file *m, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_lock_bh(&ap->sta_table_lock); return seq_list_start_head(&ap->sta_list, *_pos); } static void *prism2_ap_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); return seq_list_next(v, &ap->sta_list, _pos); } static void prism2_ap_proc_stop(struct seq_file *m, void *v) { - struct ap_data *ap = PDE_DATA(file_inode(m->file)); + struct ap_data *ap = pde_data(file_inode(m->file)); spin_unlock_bh(&ap->sta_table_lock); } diff --git a/drivers/net/wireless/intersil/hostap/hostap_download.c b/drivers/net/wireless/intersil/hostap/hostap_download.c index 7c6a5a6d1d45..3672291ced5c 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_download.c +++ b/drivers/net/wireless/intersil/hostap/hostap_download.c @@ -227,7 +227,7 @@ static int prism2_download_aux_dump_proc_open(struct inode *inode, struct file * sizeof(struct prism2_download_aux_dump)); if (ret == 0) { struct seq_file *m = file->private_data; - m->private = PDE_DATA(inode); + m->private = pde_data(inode); } return ret; } diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c index 51c847d98755..61f68786056f 100644 --- a/drivers/net/wireless/intersil/hostap/hostap_proc.c +++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c @@ -97,20 +97,20 @@ static int prism2_wds_proc_show(struct seq_file *m, void *v) static void *prism2_wds_proc_start(struct seq_file *m, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); read_lock_bh(&local->iface_lock); return seq_list_start(&local->hostap_interfaces, *_pos); } static void *prism2_wds_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); return seq_list_next(v, &local->hostap_interfaces, _pos); } static void prism2_wds_proc_stop(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); read_unlock_bh(&local->iface_lock); } @@ -123,7 +123,7 @@ static const struct seq_operations prism2_wds_proc_seqops = { static int prism2_bss_list_proc_show(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); struct list_head *ptr = v; struct hostap_bss_info *bss; @@ -151,21 +151,21 @@ static int prism2_bss_list_proc_show(struct seq_file *m, void *v) static void *prism2_bss_list_proc_start(struct seq_file *m, loff_t *_pos) __acquires(&local->lock) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_lock_bh(&local->lock); return seq_list_start_head(&local->bss_list, *_pos); } static void *prism2_bss_list_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); return seq_list_next(v, &local->bss_list, _pos); } static void prism2_bss_list_proc_stop(struct seq_file *m, void *v) __releases(&local->lock) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_unlock_bh(&local->lock); } @@ -198,7 +198,7 @@ static int prism2_crypt_proc_show(struct seq_file *m, void *v) static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf, size_t count, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(file)); + local_info_t *local = pde_data(file_inode(file)); size_t off; if (local->pda == NULL || *_pos >= PRISM2_PDA_SIZE) @@ -272,7 +272,7 @@ static int prism2_io_debug_proc_read(char *page, char **start, off_t off, #ifndef PRISM2_NO_STATION_MODES static int prism2_scan_results_proc_show(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); unsigned long entry; int i, len; struct hfa384x_hostscan_result *scanres; @@ -322,7 +322,7 @@ static int prism2_scan_results_proc_show(struct seq_file *m, void *v) static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_lock_bh(&local->lock); /* We have a header (pos 0) + N results to show (pos 1...N) */ @@ -333,7 +333,7 @@ static void *prism2_scan_results_proc_start(struct seq_file *m, loff_t *_pos) static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t *_pos) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); ++*_pos; if (*_pos > local->last_scan_results_count) @@ -343,7 +343,7 @@ static void *prism2_scan_results_proc_next(struct seq_file *m, void *v, loff_t * static void prism2_scan_results_proc_stop(struct seq_file *m, void *v) { - local_info_t *local = PDE_DATA(file_inode(m->file)); + local_info_t *local = pde_data(file_inode(m->file)); spin_unlock_bh(&local->lock); } diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index e3a3dc3e45b4..2987ad9271f6 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -2746,7 +2746,7 @@ static ssize_t int_proc_write(struct file *file, const char __user *buffer, nr = nr * 10 + c; p++; } while (--len); - *(int *)PDE_DATA(file_inode(file)) = nr; + *(int *)pde_data(file_inode(file)) = nr; return count; } diff --git a/drivers/nubus/proc.c b/drivers/nubus/proc.c index 88e1f9a0faaf..1fd667852271 100644 --- a/drivers/nubus/proc.c +++ b/drivers/nubus/proc.c @@ -93,30 +93,30 @@ struct nubus_proc_pde_data { static struct nubus_proc_pde_data * nubus_proc_alloc_pde_data(unsigned char *ptr, unsigned int size) { - struct nubus_proc_pde_data *pde_data; + struct nubus_proc_pde_data *pded; - pde_data = kmalloc(sizeof(*pde_data), GFP_KERNEL); - if (!pde_data) + pded = kmalloc(sizeof(*pded), GFP_KERNEL); + if (!pded) return NULL; - pde_data->res_ptr = ptr; - pde_data->res_size = size; - return pde_data; + pded->res_ptr = ptr; + pded->res_size = size; + return pded; } static int nubus_proc_rsrc_show(struct seq_file *m, void *v) { struct inode *inode = m->private; - struct nubus_proc_pde_data *pde_data; + struct nubus_proc_pde_data *pded; - pde_data = PDE_DATA(inode); - if (!pde_data) + pded = pde_data(inode); + if (!pded) return 0; - if (pde_data->res_size > m->size) + if (pded->res_size > m->size) return -EFBIG; - if (pde_data->res_size) { + if (pded->res_size) { int lanes = (int)proc_get_parent_data(inode); struct nubus_dirent ent; @@ -124,11 +124,11 @@ static int nubus_proc_rsrc_show(struct seq_file *m, void *v) return 0; ent.mask = lanes; - ent.base = pde_data->res_ptr; + ent.base = pded->res_ptr; ent.data = 0; - nubus_seq_write_rsrc_mem(m, &ent, pde_data->res_size); + nubus_seq_write_rsrc_mem(m, &ent, pded->res_size); } else { - unsigned int data = (unsigned int)pde_data->res_ptr; + unsigned int data = (unsigned int)pded->res_ptr; seq_putc(m, data >> 16); seq_putc(m, data >> 8); @@ -142,18 +142,18 @@ void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir, unsigned int size) { char name[9]; - struct nubus_proc_pde_data *pde_data; + struct nubus_proc_pde_data *pded; if (!procdir) return; snprintf(name, sizeof(name), "%x", ent->type); if (size) - pde_data = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size); + pded = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size); else - pde_data = NULL; + pded = NULL; proc_create_single_data(name, S_IFREG | 0444, procdir, - nubus_proc_rsrc_show, pde_data); + nubus_proc_rsrc_show, pded); } void nubus_proc_add_rsrc(struct proc_dir_entry *procdir, diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c index cf91cb024be3..1e4a5663d011 100644 --- a/drivers/parisc/led.c +++ b/drivers/parisc/led.c @@ -168,14 +168,14 @@ static int led_proc_show(struct seq_file *m, void *v) static int led_proc_open(struct inode *inode, struct file *file) { - return single_open(file, led_proc_show, PDE_DATA(inode)); + return single_open(file, led_proc_show, pde_data(inode)); } static ssize_t led_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - void *data = PDE_DATA(file_inode(file)); + void *data = pde_data(file_inode(file)); char *cur, lbuf[32]; int d; diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index cb18f8a13ab6..9c7edec64f7e 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -21,14 +21,14 @@ static int proc_initialized; /* = 0 */ static loff_t proc_bus_pci_lseek(struct file *file, loff_t off, int whence) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); return fixed_size_llseek(file, off, whence, dev->cfg_size); } static ssize_t proc_bus_pci_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); unsigned int pos = *ppos; unsigned int cnt, size; @@ -114,7 +114,7 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos) { struct inode *ino = file_inode(file); - struct pci_dev *dev = PDE_DATA(ino); + struct pci_dev *dev = pde_data(ino); int pos = *ppos; int size = dev->cfg_size; int cnt, ret; @@ -196,7 +196,7 @@ struct pci_filp_private { static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); #ifdef HAVE_PCI_MMAP struct pci_filp_private *fpriv = file->private_data; #endif /* HAVE_PCI_MMAP */ @@ -244,7 +244,7 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, #ifdef HAVE_PCI_MMAP static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma) { - struct pci_dev *dev = PDE_DATA(file_inode(file)); + struct pci_dev *dev = pde_data(file_inode(file)); struct pci_filp_private *fpriv = file->private_data; int i, ret, write_combine = 0, res_bit = IORESOURCE_MEM; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 82fa6148216c..098180fb1cfc 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -880,14 +880,14 @@ static int dispatch_proc_show(struct seq_file *m, void *v) static int dispatch_proc_open(struct inode *inode, struct file *file) { - return single_open(file, dispatch_proc_show, PDE_DATA(inode)); + return single_open(file, dispatch_proc_show, pde_data(inode)); } static ssize_t dispatch_proc_write(struct file *file, const char __user *userbuf, size_t count, loff_t *pos) { - struct ibm_struct *ibm = PDE_DATA(file_inode(file)); + struct ibm_struct *ibm = pde_data(file_inode(file)); char *kernbuf; int ret; diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c index 352508d30467..f113dec98e21 100644 --- a/drivers/platform/x86/toshiba_acpi.c +++ b/drivers/platform/x86/toshiba_acpi.c @@ -1368,7 +1368,7 @@ static int lcd_proc_show(struct seq_file *m, void *v) static int lcd_proc_open(struct inode *inode, struct file *file) { - return single_open(file, lcd_proc_show, PDE_DATA(inode)); + return single_open(file, lcd_proc_show, pde_data(inode)); } static int set_lcd_brightness(struct toshiba_acpi_dev *dev, int value) @@ -1404,7 +1404,7 @@ static int set_lcd_status(struct backlight_device *bd) static ssize_t lcd_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char cmd[42]; size_t len; int levels; @@ -1469,13 +1469,13 @@ static int video_proc_show(struct seq_file *m, void *v) static int video_proc_open(struct inode *inode, struct file *file) { - return single_open(file, video_proc_show, PDE_DATA(inode)); + return single_open(file, video_proc_show, pde_data(inode)); } static ssize_t video_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char *buffer; char *cmd; int lcd_out = -1, crt_out = -1, tv_out = -1; @@ -1580,13 +1580,13 @@ static int fan_proc_show(struct seq_file *m, void *v) static int fan_proc_open(struct inode *inode, struct file *file) { - return single_open(file, fan_proc_show, PDE_DATA(inode)); + return single_open(file, fan_proc_show, pde_data(inode)); } static ssize_t fan_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char cmd[42]; size_t len; int value; @@ -1628,13 +1628,13 @@ static int keys_proc_show(struct seq_file *m, void *v) static int keys_proc_open(struct inode *inode, struct file *file) { - return single_open(file, keys_proc_show, PDE_DATA(inode)); + return single_open(file, keys_proc_show, pde_data(inode)); } static ssize_t keys_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - struct toshiba_acpi_dev *dev = PDE_DATA(file_inode(file)); + struct toshiba_acpi_dev *dev = pde_data(file_inode(file)); char cmd[42]; size_t len; int value; diff --git a/drivers/pnp/isapnp/proc.c b/drivers/pnp/isapnp/proc.c index 1ae458c02656..55ae72a2818b 100644 --- a/drivers/pnp/isapnp/proc.c +++ b/drivers/pnp/isapnp/proc.c @@ -22,7 +22,7 @@ static loff_t isapnp_proc_bus_lseek(struct file *file, loff_t off, int whence) static ssize_t isapnp_proc_bus_read(struct file *file, char __user * buf, size_t nbytes, loff_t * ppos) { - struct pnp_dev *dev = PDE_DATA(file_inode(file)); + struct pnp_dev *dev = pde_data(file_inode(file)); int pos = *ppos; int cnt, size = 256; diff --git a/drivers/pnp/pnpbios/proc.c b/drivers/pnp/pnpbios/proc.c index a806830e3a40..0f0d819b157f 100644 --- a/drivers/pnp/pnpbios/proc.c +++ b/drivers/pnp/pnpbios/proc.c @@ -173,13 +173,13 @@ static int pnpbios_proc_show(struct seq_file *m, void *v) static int pnpbios_proc_open(struct inode *inode, struct file *file) { - return single_open(file, pnpbios_proc_show, PDE_DATA(inode)); + return single_open(file, pnpbios_proc_show, pde_data(inode)); } static ssize_t pnpbios_proc_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { - void *data = PDE_DATA(file_inode(file)); + void *data = pde_data(file_inode(file)); struct pnp_bios_node *node; int boot = (long)data >> 8; u8 nodenum = (long)data; diff --git a/drivers/scsi/scsi_proc.c b/drivers/scsi/scsi_proc.c index d6982d355739..95aee1ad1383 100644 --- a/drivers/scsi/scsi_proc.c +++ b/drivers/scsi/scsi_proc.c @@ -49,7 +49,7 @@ static DEFINE_MUTEX(global_host_template_mutex); static ssize_t proc_scsi_host_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct Scsi_Host *shost = PDE_DATA(file_inode(file)); + struct Scsi_Host *shost = pde_data(file_inode(file)); ssize_t ret = -ENOMEM; char *page; @@ -79,7 +79,7 @@ static int proc_scsi_show(struct seq_file *m, void *v) static int proc_scsi_host_open(struct inode *inode, struct file *file) { - return single_open_size(file, proc_scsi_show, PDE_DATA(inode), + return single_open_size(file, proc_scsi_show, pde_data(inode), 4 * PAGE_SIZE); } diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 64de9f1b874c..431d5a7d737e 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -1117,7 +1117,7 @@ static int rndis_proc_show(struct seq_file *m, void *v) static ssize_t rndis_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - rndis_params *p = PDE_DATA(file_inode(file)); + rndis_params *p = pde_data(file_inode(file)); u32 speed = 0; int i, fl_speed = 0; @@ -1161,7 +1161,7 @@ static ssize_t rndis_proc_write(struct file *file, const char __user *buffer, static int rndis_proc_open(struct inode *inode, struct file *file) { - return single_open(file, rndis_proc_show, PDE_DATA(inode)); + return single_open(file, rndis_proc_show, pde_data(inode)); } static const struct proc_ops rndis_proc_ops = { diff --git a/drivers/zorro/proc.c b/drivers/zorro/proc.c index 1c9ae08225d8..f916bf60b312 100644 --- a/drivers/zorro/proc.c +++ b/drivers/zorro/proc.c @@ -30,7 +30,7 @@ proc_bus_zorro_lseek(struct file *file, loff_t off, int whence) static ssize_t proc_bus_zorro_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) { - struct zorro_dev *z = PDE_DATA(file_inode(file)); + struct zorro_dev *z = pde_data(file_inode(file)); struct ConfigDev cd; loff_t pos = *ppos; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 065a28bfa3f1..e1b863449296 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -227,7 +227,7 @@ static int afs_proc_cell_volumes_show(struct seq_file *m, void *v) static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos) __acquires(cell->proc_lock) { - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_cell *cell = pde_data(file_inode(m->file)); rcu_read_lock(); return seq_hlist_start_head_rcu(&cell->proc_volumes, *_pos); @@ -236,7 +236,7 @@ static void *afs_proc_cell_volumes_start(struct seq_file *m, loff_t *_pos) static void *afs_proc_cell_volumes_next(struct seq_file *m, void *v, loff_t *_pos) { - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_cell *cell = pde_data(file_inode(m->file)); return seq_hlist_next_rcu(v, &cell->proc_volumes, _pos); } @@ -322,7 +322,7 @@ static void *afs_proc_cell_vlservers_start(struct seq_file *m, loff_t *_pos) { struct afs_vl_seq_net_private *priv = m->private; struct afs_vlserver_list *vllist; - struct afs_cell *cell = PDE_DATA(file_inode(m->file)); + struct afs_cell *cell = pde_data(file_inode(m->file)); loff_t pos = *_pos; rcu_read_lock(); diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index cf2fd9fc7d98..9f86dd947032 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2834,7 +2834,7 @@ out: static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; if (*pos < 0 || *pos >= ext4_get_groups_count(sb)) @@ -2845,7 +2845,7 @@ static void *ext4_mb_seq_groups_start(struct seq_file *seq, loff_t *pos) static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group; ++*pos; @@ -2857,7 +2857,7 @@ static void *ext4_mb_seq_groups_next(struct seq_file *seq, void *v, loff_t *pos) static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); ext4_group_t group = (ext4_group_t) ((unsigned long) v); int i; int err, buddy_loaded = 0; @@ -2985,7 +2985,7 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset) static void *ext4_mb_seq_structs_summary_start(struct seq_file *seq, loff_t *pos) __acquires(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; read_lock(&EXT4_SB(sb)->s_mb_rb_lock); @@ -2998,7 +2998,7 @@ __acquires(&EXT4_SB(sb)->s_mb_rb_lock) static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, loff_t *pos) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); unsigned long position; ++*pos; @@ -3010,7 +3010,7 @@ static void *ext4_mb_seq_structs_summary_next(struct seq_file *seq, void *v, lof static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); struct ext4_sb_info *sbi = EXT4_SB(sb); unsigned long position = ((unsigned long) v); struct ext4_group_info *grp; @@ -3058,7 +3058,7 @@ static int ext4_mb_seq_structs_summary_show(struct seq_file *seq, void *v) static void ext4_mb_seq_structs_summary_stop(struct seq_file *seq, void *v) __releases(&EXT4_SB(sb)->s_mb_rb_lock) { - struct super_block *sb = PDE_DATA(file_inode(seq->file)); + struct super_block *sb = pde_data(file_inode(seq->file)); read_unlock(&EXT4_SB(sb)->s_mb_rb_lock); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0b86a4365b66..f13d548e4a7f 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1212,7 +1212,7 @@ static const struct seq_operations jbd2_seq_info_ops = { static int jbd2_seq_info_open(struct inode *inode, struct file *file) { - journal_t *journal = PDE_DATA(inode); + journal_t *journal = pde_data(inode); struct jbd2_stats_proc_session *s; int rc, size; diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index 39b823ab2564..e1cfeda397f3 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -138,7 +138,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * @parent: The parent directory in which to create. * @ops: The seq_file ops with which to read the file. * @write: The write method with which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @data: Data for retrieval by pde_data(). * * Create a network namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -153,7 +153,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_data); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode, @@ -230,7 +230,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * @parent: The parent directory in which to create. * @show: The seqfile show method with which to read the file. * @write: The write method with which to 'modify' the file. - * @data: Data for retrieval by PDE_DATA(). + * @data: Data for retrieval by pde_data(). * * Create a network-namespaced proc file in the @parent directory with the * specified @name and @mode that allows reading of a file that displays a @@ -245,7 +245,7 @@ EXPORT_SYMBOL_GPL(proc_create_net_single); * modified by the @write function. @write should return 0 on success. * * The @data value is accessible from the @show and @write functions by calling - * PDE_DATA() on the file inode. The network namespace must be accessed by + * pde_data() on the file inode. The network namespace must be accessed by * calling seq_file_single_net() on the seq_file struct. */ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mode, diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b6e7005cc1b2..81d6e4ec2294 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -120,8 +120,6 @@ static inline void *pde_data(const struct inode *inode) return inode->i_private; } -#define PDE_DATA(i) pde_data(i) - extern void *proc_get_parent_data(const struct inode *); extern void proc_remove(struct proc_dir_entry *); extern void remove_proc_entry(const char *, struct proc_dir_entry *); @@ -202,7 +200,7 @@ proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, static inline void proc_set_size(struct proc_dir_entry *de, loff_t size) {} static inline void proc_set_user(struct proc_dir_entry *de, kuid_t uid, kgid_t gid) {} -static inline void *PDE_DATA(const struct inode *inode) {BUG(); return NULL;} +static inline void *pde_data(const struct inode *inode) {BUG(); return NULL;} static inline void *proc_get_parent_data(const struct inode *inode) { BUG(); return NULL; } static inline void proc_remove(struct proc_dir_entry *de) {} diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index 72dbb44a4573..88cc16444b43 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -209,7 +209,7 @@ static const struct file_operations __name ## _fops = { \ #define DEFINE_PROC_SHOW_ATTRIBUTE(__name) \ static int __name ## _open(struct inode *inode, struct file *file) \ { \ - return single_open(file, __name ## _show, PDE_DATA(inode)); \ + return single_open(file, __name ## _show, pde_data(inode)); \ } \ \ static const struct proc_ops __name ## _proc_ops = { \ diff --git a/ipc/util.c b/ipc/util.c index fa2d86ef3fb8..a2208d0f26b2 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -894,7 +894,7 @@ static int sysvipc_proc_open(struct inode *inode, struct file *file) if (!iter) return -ENOMEM; - iter->iface = PDE_DATA(inode); + iter->iface = pde_data(inode); iter->ns = get_ipc_ns(current->nsproxy->ipc_ns); iter->pid_ns = get_pid_ns(task_active_pid_ns(current)); diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index ee595ec09778..623b8136e9af 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -137,7 +137,7 @@ static inline int irq_select_affinity_usr(unsigned int irq) static ssize_t write_irq_affinity(int type, struct file *file, const char __user *buffer, size_t count, loff_t *pos) { - unsigned int irq = (int)(long)PDE_DATA(file_inode(file)); + unsigned int irq = (int)(long)pde_data(file_inode(file)); cpumask_var_t new_value; int err; @@ -190,12 +190,12 @@ static ssize_t irq_affinity_list_proc_write(struct file *file, static int irq_affinity_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_proc_show, pde_data(inode)); } static int irq_affinity_list_proc_open(struct inode *inode, struct file *file) { - return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode)); + return single_open(file, irq_affinity_list_proc_show, pde_data(inode)); } static const struct proc_ops irq_affinity_proc_ops = { @@ -265,7 +265,7 @@ out: static int default_affinity_open(struct inode *inode, struct file *file) { - return single_open(file, default_affinity_show, PDE_DATA(inode)); + return single_open(file, default_affinity_show, pde_data(inode)); } static const struct proc_ops default_affinity_proc_ops = { diff --git a/kernel/resource.c b/kernel/resource.c index 5ad3eba619ba..9c08d6e9eef2 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -99,7 +99,7 @@ enum { MAX_IORES_LEVEL = 5 }; static void *r_start(struct seq_file *m, loff_t *pos) __acquires(resource_lock) { - struct resource *p = PDE_DATA(file_inode(m->file)); + struct resource *p = pde_data(file_inode(m->file)); loff_t l = 0; read_lock(&resource_lock); for (p = p->child; p && l < *pos; p = r_next(m, p, &l)) @@ -115,7 +115,7 @@ static void r_stop(struct seq_file *m, void *v) static int r_show(struct seq_file *m, void *v) { - struct resource *root = PDE_DATA(file_inode(m->file)); + struct resource *root = pde_data(file_inode(m->file)); struct resource *r = v, *p; unsigned long long start, end; int width = root->end < 0x10000 ? 4 : 8; diff --git a/net/atm/proc.c b/net/atm/proc.c index 4369ffa3302a..9bf736290e48 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -108,7 +108,7 @@ out: static inline void *vcc_walk(struct seq_file *seq, loff_t l) { struct vcc_state *state = seq->private; - int family = (uintptr_t)(PDE_DATA(file_inode(seq->file))); + int family = (uintptr_t)(pde_data(file_inode(seq->file))); return __vcc_walk(&state->sk, family, &state->bucket, l) ? state : NULL; @@ -324,7 +324,7 @@ static ssize_t proc_dev_atm_read(struct file *file, char __user *buf, page = get_zeroed_page(GFP_KERNEL); if (!page) return -ENOMEM; - dev = PDE_DATA(file_inode(file)); + dev = pde_data(file_inode(file)); if (!dev->ops->proc_read) length = -EINVAL; else { diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 1661979b6a6e..ee319779781e 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -611,7 +611,7 @@ EXPORT_SYMBOL(bt_sock_wait_ready); static void *bt_seq_start(struct seq_file *seq, loff_t *pos) __acquires(seq->private->l->lock) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); read_lock(&l->lock); return seq_hlist_start_head(&l->head, *pos); @@ -619,7 +619,7 @@ static void *bt_seq_start(struct seq_file *seq, loff_t *pos) static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); return seq_hlist_next(v, &l->head, pos); } @@ -627,14 +627,14 @@ static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void bt_seq_stop(struct seq_file *seq, void *v) __releases(seq->private->l->lock) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); read_unlock(&l->lock); } static int bt_seq_show(struct seq_file *seq, void *v) { - struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); + struct bt_sock_list *l = pde_data(file_inode(seq->file)); if (v == SEQ_START_TOKEN) { seq_puts(seq, "sk RefCnt Rmem Wmem User Inode Parent"); diff --git a/net/can/bcm.c b/net/can/bcm.c index bc88d901a1c0..95d209b52e6a 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -193,7 +193,7 @@ static int bcm_proc_show(struct seq_file *m, void *v) { char ifname[IFNAMSIZ]; struct net *net = m->private; - struct sock *sk = (struct sock *)PDE_DATA(m->file->f_inode); + struct sock *sk = (struct sock *)pde_data(m->file->f_inode); struct bcm_sock *bo = bcm_sk(sk); struct bcm_op *op; diff --git a/net/can/proc.c b/net/can/proc.c index b3099f0a3cb8..bbce97825f13 100644 --- a/net/can/proc.c +++ b/net/can/proc.c @@ -305,7 +305,7 @@ static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ - int idx = (int)(long)PDE_DATA(m->file->f_inode); + int idx = (int)(long)pde_data(m->file->f_inode); struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 213cb7b26b7a..6c2016f7f3d1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -3364,7 +3364,7 @@ EXPORT_SYMBOL(neigh_seq_stop); static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) { - struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); + struct neigh_table *tbl = pde_data(file_inode(seq->file)); int cpu; if (*pos == 0) @@ -3381,7 +3381,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); + struct neigh_table *tbl = pde_data(file_inode(seq->file)); int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { @@ -3401,7 +3401,7 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v) static int neigh_stat_seq_show(struct seq_file *seq, void *v) { - struct neigh_table *tbl = PDE_DATA(file_inode(seq->file)); + struct neigh_table *tbl = pde_data(file_inode(seq->file)); struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 560a5e712dc3..84b62cd7bc57 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -546,7 +546,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, static int pgctrl_open(struct inode *inode, struct file *file) { - return single_open(file, pgctrl_show, PDE_DATA(inode)); + return single_open(file, pgctrl_show, pde_data(inode)); } static const struct proc_ops pktgen_proc_ops = { @@ -1811,7 +1811,7 @@ static ssize_t pktgen_if_write(struct file *file, static int pktgen_if_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_if_show, PDE_DATA(inode)); + return single_open(file, pktgen_if_show, pde_data(inode)); } static const struct proc_ops pktgen_if_proc_ops = { @@ -1948,7 +1948,7 @@ out: static int pktgen_thread_open(struct inode *inode, struct file *file) { - return single_open(file, pktgen_thread_show, PDE_DATA(inode)); + return single_open(file, pktgen_thread_show, pde_data(inode)); } static const struct proc_ops pktgen_thread_proc_ops = { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index b518f20c9a24..f8e176c77d1c 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -776,7 +776,7 @@ static int clusterip_proc_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - struct clusterip_config *c = PDE_DATA(inode); + struct clusterip_config *c = pde_data(inode); sf->private = c; @@ -788,7 +788,7 @@ static int clusterip_proc_open(struct inode *inode, struct file *file) static int clusterip_proc_release(struct inode *inode, struct file *file) { - struct clusterip_config *c = PDE_DATA(inode); + struct clusterip_config *c = pde_data(inode); int ret; ret = seq_release(inode, file); @@ -802,7 +802,7 @@ static int clusterip_proc_release(struct inode *inode, struct file *file) static ssize_t clusterip_proc_write(struct file *file, const char __user *input, size_t size, loff_t *ofs) { - struct clusterip_config *c = PDE_DATA(file_inode(file)); + struct clusterip_config *c = pde_data(file_inode(file)); #define PROC_WRITELEN 10 char buffer[PROC_WRITELEN+1]; unsigned long nodenum; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a53f256bf9d3..9eb5fc247868 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -971,7 +971,7 @@ struct proto raw_prot = { static struct sock *raw_get_first(struct seq_file *seq) { struct sock *sk; - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; @@ -987,7 +987,7 @@ found: static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) { - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); struct raw_iter_state *state = raw_seq_private(seq); do { @@ -1016,7 +1016,7 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos) void *raw_seq_start(struct seq_file *seq, loff_t *pos) __acquires(&h->lock) { - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); read_lock(&h->lock); return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; @@ -1039,7 +1039,7 @@ EXPORT_SYMBOL_GPL(raw_seq_next); void raw_seq_stop(struct seq_file *seq, void *v) __releases(&h->lock) { - struct raw_hashinfo *h = PDE_DATA(file_inode(seq->file)); + struct raw_hashinfo *h = pde_data(file_inode(seq->file)); read_unlock(&h->lock); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b3f34e366b27..b53476e78c84 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3002,7 +3002,7 @@ static unsigned short seq_file_family(const struct seq_file *seq) #endif /* Iterated from proc fs */ - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); return afinfo->family; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 464590ea922e..090360939401 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2960,7 +2960,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { @@ -2993,7 +2993,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); do { sk = sk_next(sk); @@ -3050,7 +3050,7 @@ void udp_seq_stop(struct seq_file *seq, void *v) if (state->bpf_seq_afinfo) afinfo = state->bpf_seq_afinfo; else - afinfo = PDE_DATA(file_inode(seq->file)); + afinfo = pde_data(file_inode(seq->file)); if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index 25524e393349..54a489f16b17 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1517,7 +1517,7 @@ EXPORT_SYMBOL_GPL(xt_unregister_table); #ifdef CONFIG_PROC_FS static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) { - u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); + u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; @@ -1529,7 +1529,7 @@ static void *xt_table_seq_start(struct seq_file *seq, loff_t *pos) static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - u8 af = (unsigned long)PDE_DATA(file_inode(seq->file)); + u8 af = (unsigned long)pde_data(file_inode(seq->file)); struct net *net = seq_file_net(seq); struct xt_pernet *xt_net; @@ -1540,7 +1540,7 @@ static void *xt_table_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void xt_table_seq_stop(struct seq_file *seq, void *v) { - u_int8_t af = (unsigned long)PDE_DATA(file_inode(seq->file)); + u_int8_t af = (unsigned long)pde_data(file_inode(seq->file)); mutex_unlock(&xt[af].mutex); } @@ -1584,7 +1584,7 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, [MTTG_TRAV_NFP_UNSPEC] = MTTG_TRAV_NFP_SPEC, [MTTG_TRAV_NFP_SPEC] = MTTG_TRAV_DONE, }; - uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); + uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; if (ppos != NULL) @@ -1633,7 +1633,7 @@ static void *xt_mttg_seq_start(struct seq_file *seq, loff_t *pos, static void xt_mttg_seq_stop(struct seq_file *seq, void *v) { - uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); + uint8_t nfproto = (unsigned long)pde_data(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; switch (trav->class) { diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9c5cfd74a0ee..0859b8f76764 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1052,7 +1052,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -1069,7 +1069,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); @@ -1083,7 +1083,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) @@ -1125,7 +1125,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1140,7 +1140,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1155,7 +1155,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *ht = pde_data(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1169,7 +1169,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show_v2(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; @@ -1183,7 +1183,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v) static int dl_seq_show_v1(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; @@ -1197,7 +1197,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) static int dl_seq_show(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); + struct xt_hashlimit_htable *htable = pde_data(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 0446307516cd..7ddb9a78e3fc 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -551,7 +551,7 @@ static int recent_seq_open(struct inode *inode, struct file *file) if (st == NULL) return -ENOMEM; - st->table = PDE_DATA(inode); + st->table = pde_data(inode); return 0; } @@ -559,7 +559,7 @@ static ssize_t recent_mt_proc_write(struct file *file, const char __user *input, size_t size, loff_t *loff) { - struct recent_table *t = PDE_DATA(file_inode(file)); + struct recent_table *t = pde_data(file_inode(file)); struct recent_entry *e; char buf[sizeof("+b335:1d35:1e55:dead:c0de:1715:5afe:c0de")]; const char *c = buf; diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index b87565b64928..c2ba9d4cd2c7 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1433,7 +1433,7 @@ static bool use_gss_proxy(struct net *net) static ssize_t write_gssp(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct net *net = PDE_DATA(file_inode(file)); + struct net *net = pde_data(file_inode(file)); char tbuf[20]; unsigned long i; int res; @@ -1461,7 +1461,7 @@ static ssize_t write_gssp(struct file *file, const char __user *buf, static ssize_t read_gssp(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - struct net *net = PDE_DATA(file_inode(file)); + struct net *net = pde_data(file_inode(file)); struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); unsigned long p = *ppos; char tbuf[10]; diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 59641803472c..bb1177395b99 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1536,7 +1536,7 @@ static ssize_t write_flush(struct file *file, const char __user *buf, static ssize_t cache_read_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return cache_read(filp, buf, count, ppos, cd); } @@ -1544,14 +1544,14 @@ static ssize_t cache_read_procfs(struct file *filp, char __user *buf, static ssize_t cache_write_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return cache_write(filp, buf, count, ppos, cd); } static __poll_t cache_poll_procfs(struct file *filp, poll_table *wait) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return cache_poll(filp, wait, cd); } @@ -1560,21 +1560,21 @@ static long cache_ioctl_procfs(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return cache_ioctl(inode, filp, cmd, arg, cd); } static int cache_open_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return cache_open(inode, filp, cd); } static int cache_release_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return cache_release(inode, filp, cd); } @@ -1591,14 +1591,14 @@ static const struct proc_ops cache_channel_proc_ops = { static int content_open_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return content_open(inode, filp, cd); } static int content_release_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return content_release(inode, filp, cd); } @@ -1612,14 +1612,14 @@ static const struct proc_ops content_proc_ops = { static int open_flush_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return open_flush(inode, filp, cd); } static int release_flush_procfs(struct inode *inode, struct file *filp) { - struct cache_detail *cd = PDE_DATA(inode); + struct cache_detail *cd = pde_data(inode); return release_flush(inode, filp, cd); } @@ -1627,7 +1627,7 @@ static int release_flush_procfs(struct inode *inode, struct file *filp) static ssize_t read_flush_procfs(struct file *filp, char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return read_flush(filp, buf, count, ppos, cd); } @@ -1636,7 +1636,7 @@ static ssize_t write_flush_procfs(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { - struct cache_detail *cd = PDE_DATA(file_inode(filp)); + struct cache_detail *cd = pde_data(file_inode(filp)); return write_flush(filp, buf, count, ppos, cd); } diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c index c964b48eaaba..52908f9e6eab 100644 --- a/net/sunrpc/stats.c +++ b/net/sunrpc/stats.c @@ -66,7 +66,7 @@ static int rpc_proc_show(struct seq_file *seq, void *v) { static int rpc_proc_open(struct inode *inode, struct file *file) { - return single_open(file, rpc_proc_show, PDE_DATA(inode)); + return single_open(file, rpc_proc_show, pde_data(inode)); } static const struct proc_ops rpc_proc_ops = { diff --git a/sound/core/info.c b/sound/core/info.c index a451b24199c3..782fba87cc04 100644 --- a/sound/core/info.c +++ b/sound/core/info.c @@ -234,7 +234,7 @@ static int snd_info_entry_mmap(struct file *file, struct vm_area_struct *vma) static int snd_info_entry_open(struct inode *inode, struct file *file) { - struct snd_info_entry *entry = PDE_DATA(inode); + struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int mode, err; @@ -365,7 +365,7 @@ static int snd_info_seq_show(struct seq_file *seq, void *p) static int snd_info_text_entry_open(struct inode *inode, struct file *file) { - struct snd_info_entry *entry = PDE_DATA(inode); + struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int err; -- cgit v1.2.3 From 2dba5eb1c73b6ba2988ced07250edeac0f8cbf5a Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 21 Jan 2022 22:14:27 -0800 Subject: lib/stackdepot: allow optional init and stack_table allocation by kvmalloc() Currently, enabling CONFIG_STACKDEPOT means its stack_table will be allocated from memblock, even if stack depot ends up not actually used. The default size of stack_table is 4MB on 32-bit, 8MB on 64-bit. This is fine for use-cases such as KASAN which is also a config option and has overhead on its own. But it's an issue for functionality that has to be actually enabled on boot (page_owner) or depends on hardware (GPU drivers) and thus the memory might be wasted. This was raised as an issue [1] when attempting to add stackdepot support for SLUB's debug object tracking functionality. It's common to build kernels with CONFIG_SLUB_DEBUG and enable slub_debug on boot only when needed, or create only specific kmem caches with debugging for testing purposes. It would thus be more efficient if stackdepot's table was allocated only when actually going to be used. This patch thus makes the allocation (and whole stack_depot_init() call) optional: - Add a CONFIG_STACKDEPOT_ALWAYS_INIT flag to keep using the current well-defined point of allocation as part of mem_init(). Make CONFIG_KASAN select this flag. - Other users have to call stack_depot_init() as part of their own init when it's determined that stack depot will actually be used. This may depend on both config and runtime conditions. Convert current users which are page_owner and several in the DRM subsystem. Same will be done for SLUB later. - Because the init might now be called after the boot-time memblock allocation has given all memory to the buddy allocator, change stack_depot_init() to allocate stack_table with kvmalloc() when memblock is no longer available. Also handle allocation failure by disabling stackdepot (could have theoretically happened even with memblock allocation previously), and don't unnecessarily align the memblock allocation to its own size anymore. [1] https://lore.kernel.org/all/CAMuHMdW=eoVzM1Re5FVoEN87nKfiLmM2+Ah7eNu2KXEhCvbZyA@mail.gmail.com/ Link: https://lkml.kernel.org/r/20211013073005.11351-1-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Dmitry Vyukov Reviewed-by: Marco Elver # stackdepot Cc: Marco Elver Cc: Vijayanand Jitta Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Geert Uytterhoeven Cc: Oliver Glitta Cc: Imran Khan From: Colin Ian King Subject: lib/stackdepot: fix spelling mistake and grammar in pr_err message There is a spelling mistake of the work allocation so fix this and re-phrase the message to make it easier to read. Link: https://lkml.kernel.org/r/20211015104159.11282-1-colin.king@canonical.com Signed-off-by: Colin Ian King Cc: Vlastimil Babka From: Vlastimil Babka Subject: lib/stackdepot: allow optional init and stack_table allocation by kvmalloc() - fixup On FLATMEM, we call page_ext_init_flatmem_late() just before kmem_cache_init() which means stack_depot_init() (called by page owner init) will not recognize properly it should use kvmalloc() and not memblock_alloc(). memblock_alloc() will also not issue a warning and return a block memory that can be invalid and cause kernel page fault when saving stacks, as reported by the kernel test robot [1]. Fix this by moving page_ext_init_flatmem_late() below kmem_cache_init() so that slab_is_available() is true during stack_depot_init(). SPARSEMEM doesn't have this issue, as it doesn't do page_ext_init_flatmem_late(), but a different page_ext_init() even later in the boot process. Thanks to Mike Rapoport for pointing out the FLATMEM init ordering issue. While at it, also actually resolve a checkpatch warning in stack_depot_init() from DRM CI, which was supposed to be in the original patch already. [1] https://lore.kernel.org/all/20211014085450.GC18719@xsang-OptiPlex-9020/ Link: https://lkml.kernel.org/r/6abd9213-19a9-6d58-cedc-2414386d2d81@suse.cz Signed-off-by: Vlastimil Babka Reported-by: kernel test robot Cc: Mike Rapoport Cc: Stephen Rothwell From: Vlastimil Babka Subject: lib/stackdepot: allow optional init and stack_table allocation by kvmalloc() - fixup3 Due to cd06ab2fd48f ("drm/locking: add backtrace for locking contended locks without backoff") landing recently to -next adding a new stack depot user in drivers/gpu/drm/drm_modeset_lock.c we need to add an appropriate call to stack_depot_init() there as well. Link: https://lkml.kernel.org/r/2a692365-cfa1-64f2-34e0-8aa5674dce5e@suse.cz Signed-off-by: Vlastimil Babka Cc: Jani Nikula Cc: Naresh Kamboju Cc: Marco Elver Cc: Vijayanand Jitta Cc: Maarten Lankhorst Cc: Maxime Ripard Cc: Thomas Zimmermann Cc: David Airlie Cc: Daniel Vetter Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Geert Uytterhoeven Cc: Oliver Glitta Cc: Imran Khan Cc: Stephen Rothwell From: Vlastimil Babka Subject: lib/stackdepot: allow optional init and stack_table allocation by kvmalloc() - fixup4 Due to 4e66934eaadc ("lib: add reference counting tracking infrastructure") landing recently to net-next adding a new stack depot user in lib/ref_tracker.c we need to add an appropriate call to stack_depot_init() there as well. Link: https://lkml.kernel.org/r/45c1b738-1a2f-5b5f-2f6d-86fab206d01c@suse.cz Signed-off-by: Vlastimil Babka Reviewed-by: Eric Dumazet Cc: Jiri Slab Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/gpu/drm/drm_dp_mst_topology.c | 1 + drivers/gpu/drm/drm_mm.c | 4 ++++ drivers/gpu/drm/drm_modeset_lock.c | 9 +++++++++ drivers/gpu/drm/i915/intel_runtime_pm.c | 3 +++ include/linux/ref_tracker.h | 2 ++ include/linux/stackdepot.h | 25 ++++++++++++++++--------- init/main.c | 9 ++++++--- lib/Kconfig | 4 ++++ lib/Kconfig.kasan | 2 +- lib/stackdepot.c | 33 ++++++++++++++++++++++++++++----- mm/page_owner.c | 2 ++ 11 files changed, 76 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index f3d79eda94bb..8b3822142fed 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -5511,6 +5511,7 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr, mutex_init(&mgr->probe_lock); #if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) mutex_init(&mgr->topology_ref_history_lock); + stack_depot_init(); #endif INIT_LIST_HEAD(&mgr->tx_msg_downq); INIT_LIST_HEAD(&mgr->destroy_port_list); diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c index 7d1c578388d3..8257f9d4f619 100644 --- a/drivers/gpu/drm/drm_mm.c +++ b/drivers/gpu/drm/drm_mm.c @@ -980,6 +980,10 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size) add_hole(&mm->head_node); mm->scan_active = 0; + +#ifdef CONFIG_DRM_DEBUG_MM + stack_depot_init(); +#endif } EXPORT_SYMBOL(drm_mm_init); diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index c97323365675..918065982db4 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -107,6 +107,11 @@ static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) kfree(buf); } + +static void __drm_stack_depot_init(void) +{ + stack_depot_init(); +} #else /* CONFIG_DRM_DEBUG_MODESET_LOCK */ static depot_stack_handle_t __drm_stack_depot_save(void) { @@ -115,6 +120,9 @@ static depot_stack_handle_t __drm_stack_depot_save(void) static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) { } +static void __drm_stack_depot_init(void) +{ +} #endif /* CONFIG_DRM_DEBUG_MODESET_LOCK */ /** @@ -359,6 +367,7 @@ void drm_modeset_lock_init(struct drm_modeset_lock *lock) { ww_mutex_init(&lock->mutex, &crtc_ww_class); INIT_LIST_HEAD(&lock->head); + __drm_stack_depot_init(); } EXPORT_SYMBOL(drm_modeset_lock_init); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 22dab36afcb6..53f1ccb78849 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -68,6 +68,9 @@ static noinline depot_stack_handle_t __save_depot_stack(void) static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm) { spin_lock_init(&rpm->debug.lock); + + if (rpm->available) + stack_depot_init(); } static noinline depot_stack_handle_t diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h index c11c9db5825c..60f3453be23e 100644 --- a/include/linux/ref_tracker.h +++ b/include/linux/ref_tracker.h @@ -4,6 +4,7 @@ #include #include #include +#include struct ref_tracker; @@ -26,6 +27,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, spin_lock_init(&dir->lock); dir->quarantine_avail = quarantine_count; refcount_set(&dir->untracked, 1); + stack_depot_init(); } void ref_tracker_dir_exit(struct ref_tracker_dir *dir); diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index c34b55a6e554..17f992fe6355 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -19,6 +19,22 @@ depot_stack_handle_t __stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags, bool can_alloc); +/* + * Every user of stack depot has to call this during its own init when it's + * decided that it will be calling stack_depot_save() later. + * + * The alternative is to select STACKDEPOT_ALWAYS_INIT to have stack depot + * enabled as part of mm_init(), for subsystems where it's known at compile time + * that stack depot will be used. + */ +int stack_depot_init(void); + +#ifdef CONFIG_STACKDEPOT_ALWAYS_INIT +static inline int stack_depot_early_init(void) { return stack_depot_init(); } +#else +static inline int stack_depot_early_init(void) { return 0; } +#endif + depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); @@ -30,13 +46,4 @@ int stack_depot_snprint(depot_stack_handle_t handle, char *buf, size_t size, void stack_depot_print(depot_stack_handle_t stack); -#ifdef CONFIG_STACKDEPOT -int stack_depot_init(void); -#else -static inline int stack_depot_init(void) -{ - return 0; -} -#endif /* CONFIG_STACKDEPOT */ - #endif diff --git a/init/main.c b/init/main.c index bb984ed79de0..65fa2e41a9c0 100644 --- a/init/main.c +++ b/init/main.c @@ -834,12 +834,15 @@ static void __init mm_init(void) init_mem_debugging_and_hardening(); kfence_alloc_pool(); report_meminit(); - stack_depot_init(); + stack_depot_early_init(); mem_init(); mem_init_print_info(); - /* page_owner must be initialized after buddy is ready */ - page_ext_init_flatmem_late(); kmem_cache_init(); + /* + * page_owner must be initialized after buddy is ready, and also after + * slab is ready so that stack_depot_init() works properly + */ + page_ext_init_flatmem_late(); kmemleak_init(); pgtable_init(); debug_objects_mem_init(); diff --git a/lib/Kconfig b/lib/Kconfig index c20b68ad2bc3..51c368a50b16 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -673,6 +673,10 @@ config STACKDEPOT bool select STACKTRACE +config STACKDEPOT_ALWAYS_INIT + bool + select STACKDEPOT + config STACK_HASH_ORDER int "stack depot hash size (12 => 4KB, 20 => 1024KB)" range 12 20 diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index cdc842d090db..879757b6dd14 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -38,7 +38,7 @@ menuconfig KASAN CC_HAS_WORKING_NOSANITIZE_ADDRESS) || \ HAVE_ARCH_KASAN_HW_TAGS depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB) - select STACKDEPOT + select STACKDEPOT_ALWAYS_INIT help Enables KASAN (KernelAddressSANitizer) - runtime memory debugger, designed to find out-of-bounds accesses and use-after-free bugs. diff --git a/lib/stackdepot.c b/lib/stackdepot.c index b437ae79aca1..00ccb106f1a8 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include @@ -161,18 +162,40 @@ static int __init is_stack_depot_disabled(char *str) } early_param("stack_depot_disable", is_stack_depot_disabled); -int __init stack_depot_init(void) +/* + * __ref because of memblock_alloc(), which will not be actually called after + * the __init code is gone, because at that point slab_is_available() is true + */ +__ref int stack_depot_init(void) { - if (!stack_depot_disable) { + static DEFINE_MUTEX(stack_depot_init_mutex); + + mutex_lock(&stack_depot_init_mutex); + if (!stack_depot_disable && !stack_table) { size_t size = (STACK_HASH_SIZE * sizeof(struct stack_record *)); int i; - stack_table = memblock_alloc(size, size); - for (i = 0; i < STACK_HASH_SIZE; i++) - stack_table[i] = NULL; + if (slab_is_available()) { + pr_info("Stack Depot allocating hash table with kvmalloc\n"); + stack_table = kvmalloc(size, GFP_KERNEL); + } else { + pr_info("Stack Depot allocating hash table with memblock_alloc\n"); + stack_table = memblock_alloc(size, SMP_CACHE_BYTES); + } + if (stack_table) { + for (i = 0; i < STACK_HASH_SIZE; i++) + stack_table[i] = NULL; + } else { + pr_err("Stack Depot hash table allocation failed, disabling\n"); + stack_depot_disable = true; + mutex_unlock(&stack_depot_init_mutex); + return -ENOMEM; + } } + mutex_unlock(&stack_depot_init_mutex); return 0; } +EXPORT_SYMBOL_GPL(stack_depot_init); /* Calculate hash for a stack */ static inline u32 hash_stack(unsigned long *entries, unsigned int size) diff --git a/mm/page_owner.c b/mm/page_owner.c index 5eea061bb1e5..99e360df9465 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -80,6 +80,8 @@ static __init void init_page_owner(void) if (!page_owner_enabled) return; + stack_depot_init(); + register_dummy_stack(); register_failure_stack(); register_early_stack(); -- cgit v1.2.3 From 0a4ee518185e902758191d968600399f3bc2be31 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:34 -0800 Subject: mm: remove cleancache Patch series "remove Xen tmem leftovers". Since the removal of the Xen tmem driver in 2019, the cleancache hooks are entirely unused, as are large parts of frontswap. This series against linux-next (with the folio changes included) removes cleancaches, and cuts down frontswap to the bits actually used by zswap. This patch (of 13): The cleancache subsystem is unused since the removal of Xen tmem driver in commit 814bbf49dcd0 ("xen: remove tmem driver"). [akpm@linux-foundation.org: remove now-unreachable code] Link: https://lkml.kernel.org/r/20211224062246.1258487-1-hch@lst.de Link: https://lkml.kernel.org/r/20211224062246.1258487-2-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Acked-by: Geert Uytterhoeven Cc: Konrad Rzeszutek Wilk Cc: Hugh Dickins Cc: Seth Jennings Cc: Dan Streetman Cc: Vitaly Wool Cc: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/cleancache.rst | 296 -------------------------------- Documentation/vm/frontswap.rst | 12 +- Documentation/vm/index.rst | 1 - MAINTAINERS | 7 - arch/arm/configs/bcm2835_defconfig | 1 - arch/arm/configs/qcom_defconfig | 1 - arch/m68k/configs/amiga_defconfig | 1 - arch/m68k/configs/apollo_defconfig | 1 - arch/m68k/configs/atari_defconfig | 1 - arch/m68k/configs/bvme6000_defconfig | 1 - arch/m68k/configs/hp300_defconfig | 1 - arch/m68k/configs/mac_defconfig | 1 - arch/m68k/configs/multi_defconfig | 1 - arch/m68k/configs/mvme147_defconfig | 1 - arch/m68k/configs/mvme16x_defconfig | 1 - arch/m68k/configs/q40_defconfig | 1 - arch/m68k/configs/sun3_defconfig | 1 - arch/m68k/configs/sun3x_defconfig | 1 - arch/s390/configs/debug_defconfig | 1 - arch/s390/configs/defconfig | 1 - block/bdev.c | 5 - fs/btrfs/extent_io.c | 10 -- fs/btrfs/super.c | 2 - fs/ext4/readpage.c | 6 - fs/ext4/super.c | 3 - fs/f2fs/data.c | 13 -- fs/mpage.c | 7 - fs/ntfs3/ntfs_fs.h | 1 - fs/ocfs2/super.c | 2 - fs/super.c | 3 - include/linux/cleancache.h | 124 -------------- include/linux/fs.h | 5 - mm/Kconfig | 22 --- mm/Makefile | 1 - mm/cleancache.c | 315 ----------------------------------- mm/filemap.c | 11 -- mm/truncate.c | 15 +- 37 files changed, 4 insertions(+), 873 deletions(-) delete mode 100644 Documentation/vm/cleancache.rst delete mode 100644 include/linux/cleancache.h delete mode 100644 mm/cleancache.c (limited to 'include/linux') diff --git a/Documentation/vm/cleancache.rst b/Documentation/vm/cleancache.rst deleted file mode 100644 index 68cba9131c31..000000000000 --- a/Documentation/vm/cleancache.rst +++ /dev/null @@ -1,296 +0,0 @@ -.. _cleancache: - -========== -Cleancache -========== - -Motivation -========== - -Cleancache is a new optional feature provided by the VFS layer that -potentially dramatically increases page cache effectiveness for -many workloads in many environments at a negligible cost. - -Cleancache can be thought of as a page-granularity victim cache for clean -pages that the kernel's pageframe replacement algorithm (PFRA) would like -to keep around, but can't since there isn't enough memory. So when the -PFRA "evicts" a page, it first attempts to use cleancache code to -put the data contained in that page into "transcendent memory", memory -that is not directly accessible or addressable by the kernel and is -of unknown and possibly time-varying size. - -Later, when a cleancache-enabled filesystem wishes to access a page -in a file on disk, it first checks cleancache to see if it already -contains it; if it does, the page of data is copied into the kernel -and a disk access is avoided. - -Transcendent memory "drivers" for cleancache are currently implemented -in Xen (using hypervisor memory) and zcache (using in-kernel compressed -memory) and other implementations are in development. - -:ref:`FAQs ` are included below. - -Implementation Overview -======================= - -A cleancache "backend" that provides transcendent memory registers itself -to the kernel's cleancache "frontend" by calling cleancache_register_ops, -passing a pointer to a cleancache_ops structure with funcs set appropriately. -The functions provided must conform to certain semantics as follows: - -Most important, cleancache is "ephemeral". Pages which are copied into -cleancache have an indefinite lifetime which is completely unknowable -by the kernel and so may or may not still be in cleancache at any later time. -Thus, as its name implies, cleancache is not suitable for dirty pages. -Cleancache has complete discretion over what pages to preserve and what -pages to discard and when. - -Mounting a cleancache-enabled filesystem should call "init_fs" to obtain a -pool id which, if positive, must be saved in the filesystem's superblock; -a negative return value indicates failure. A "put_page" will copy a -(presumably about-to-be-evicted) page into cleancache and associate it with -the pool id, a file key, and a page index into the file. (The combination -of a pool id, a file key, and an index is sometimes called a "handle".) -A "get_page" will copy the page, if found, from cleancache into kernel memory. -An "invalidate_page" will ensure the page no longer is present in cleancache; -an "invalidate_inode" will invalidate all pages associated with the specified -file; and, when a filesystem is unmounted, an "invalidate_fs" will invalidate -all pages in all files specified by the given pool id and also surrender -the pool id. - -An "init_shared_fs", like init_fs, obtains a pool id but tells cleancache -to treat the pool as shared using a 128-bit UUID as a key. On systems -that may run multiple kernels (such as hard partitioned or virtualized -systems) that may share a clustered filesystem, and where cleancache -may be shared among those kernels, calls to init_shared_fs that specify the -same UUID will receive the same pool id, thus allowing the pages to -be shared. Note that any security requirements must be imposed outside -of the kernel (e.g. by "tools" that control cleancache). Or a -cleancache implementation can simply disable shared_init by always -returning a negative value. - -If a get_page is successful on a non-shared pool, the page is invalidated -(thus making cleancache an "exclusive" cache). On a shared pool, the page -is NOT invalidated on a successful get_page so that it remains accessible to -other sharers. The kernel is responsible for ensuring coherency between -cleancache (shared or not), the page cache, and the filesystem, using -cleancache invalidate operations as required. - -Note that cleancache must enforce put-put-get coherency and get-get -coherency. For the former, if two puts are made to the same handle but -with different data, say AAA by the first put and BBB by the second, a -subsequent get can never return the stale data (AAA). For get-get coherency, -if a get for a given handle fails, subsequent gets for that handle will -never succeed unless preceded by a successful put with that handle. - -Last, cleancache provides no SMP serialization guarantees; if two -different Linux threads are simultaneously putting and invalidating a page -with the same handle, the results are indeterminate. Callers must -lock the page to ensure serial behavior. - -Cleancache Performance Metrics -============================== - -If properly configured, monitoring of cleancache is done via debugfs in -the `/sys/kernel/debug/cleancache` directory. The effectiveness of cleancache -can be measured (across all filesystems) with: - -``succ_gets`` - number of gets that were successful - -``failed_gets`` - number of gets that failed - -``puts`` - number of puts attempted (all "succeed") - -``invalidates`` - number of invalidates attempted - -A backend implementation may provide additional metrics. - -.. _faq: - -FAQ -=== - -* Where's the value? (Andrew Morton) - -Cleancache provides a significant performance benefit to many workloads -in many environments with negligible overhead by improving the -effectiveness of the pagecache. Clean pagecache pages are -saved in transcendent memory (RAM that is otherwise not directly -addressable to the kernel); fetching those pages later avoids "refaults" -and thus disk reads. - -Cleancache (and its sister code "frontswap") provide interfaces for -this transcendent memory (aka "tmem"), which conceptually lies between -fast kernel-directly-addressable RAM and slower DMA/asynchronous devices. -Disallowing direct kernel or userland reads/writes to tmem -is ideal when data is transformed to a different form and size (such -as with compression) or secretly moved (as might be useful for write- -balancing for some RAM-like devices). Evicted page-cache pages (and -swap pages) are a great use for this kind of slower-than-RAM-but-much- -faster-than-disk transcendent memory, and the cleancache (and frontswap) -"page-object-oriented" specification provides a nice way to read and -write -- and indirectly "name" -- the pages. - -In the virtual case, the whole point of virtualization is to statistically -multiplex physical resources across the varying demands of multiple -virtual machines. This is really hard to do with RAM and efforts to -do it well with no kernel change have essentially failed (except in some -well-publicized special-case workloads). Cleancache -- and frontswap -- -with a fairly small impact on the kernel, provide a huge amount -of flexibility for more dynamic, flexible RAM multiplexing. -Specifically, the Xen Transcendent Memory backend allows otherwise -"fallow" hypervisor-owned RAM to not only be "time-shared" between multiple -virtual machines, but the pages can be compressed and deduplicated to -optimize RAM utilization. And when guest OS's are induced to surrender -underutilized RAM (e.g. with "self-ballooning"), page cache pages -are the first to go, and cleancache allows those pages to be -saved and reclaimed if overall host system memory conditions allow. - -And the identical interface used for cleancache can be used in -physical systems as well. The zcache driver acts as a memory-hungry -device that stores pages of data in a compressed state. And -the proposed "RAMster" driver shares RAM across multiple physical -systems. - -* Why does cleancache have its sticky fingers so deep inside the - filesystems and VFS? (Andrew Morton and Christoph Hellwig) - -The core hooks for cleancache in VFS are in most cases a single line -and the minimum set are placed precisely where needed to maintain -coherency (via cleancache_invalidate operations) between cleancache, -the page cache, and disk. All hooks compile into nothingness if -cleancache is config'ed off and turn into a function-pointer- -compare-to-NULL if config'ed on but no backend claims the ops -functions, or to a compare-struct-element-to-negative if a -backend claims the ops functions but a filesystem doesn't enable -cleancache. - -Some filesystems are built entirely on top of VFS and the hooks -in VFS are sufficient, so don't require an "init_fs" hook; the -initial implementation of cleancache didn't provide this hook. -But for some filesystems (such as btrfs), the VFS hooks are -incomplete and one or more hooks in fs-specific code are required. -And for some other filesystems, such as tmpfs, cleancache may -be counterproductive. So it seemed prudent to require a filesystem -to "opt in" to use cleancache, which requires adding a hook in -each filesystem. Not all filesystems are supported by cleancache -only because they haven't been tested. The existing set should -be sufficient to validate the concept, the opt-in approach means -that untested filesystems are not affected, and the hooks in the -existing filesystems should make it very easy to add more -filesystems in the future. - -The total impact of the hooks to existing fs and mm files is only -about 40 lines added (not counting comments and blank lines). - -* Why not make cleancache asynchronous and batched so it can more - easily interface with real devices with DMA instead of copying each - individual page? (Minchan Kim) - -The one-page-at-a-time copy semantics simplifies the implementation -on both the frontend and backend and also allows the backend to -do fancy things on-the-fly like page compression and -page deduplication. And since the data is "gone" (copied into/out -of the pageframe) before the cleancache get/put call returns, -a great deal of race conditions and potential coherency issues -are avoided. While the interface seems odd for a "real device" -or for real kernel-addressable RAM, it makes perfect sense for -transcendent memory. - -* Why is non-shared cleancache "exclusive"? And where is the - page "invalidated" after a "get"? (Minchan Kim) - -The main reason is to free up space in transcendent memory and -to avoid unnecessary cleancache_invalidate calls. If you want inclusive, -the page can be "put" immediately following the "get". If -put-after-get for inclusive becomes common, the interface could -be easily extended to add a "get_no_invalidate" call. - -The invalidate is done by the cleancache backend implementation. - -* What's the performance impact? - -Performance analysis has been presented at OLS'09 and LCA'10. -Briefly, performance gains can be significant on most workloads, -especially when memory pressure is high (e.g. when RAM is -overcommitted in a virtual workload); and because the hooks are -invoked primarily in place of or in addition to a disk read/write, -overhead is negligible even in worst case workloads. Basically -cleancache replaces I/O with memory-copy-CPU-overhead; on older -single-core systems with slow memory-copy speeds, cleancache -has little value, but in newer multicore machines, especially -consolidated/virtualized machines, it has great value. - -* How do I add cleancache support for filesystem X? (Boaz Harrash) - -Filesystems that are well-behaved and conform to certain -restrictions can utilize cleancache simply by making a call to -cleancache_init_fs at mount time. Unusual, misbehaving, or -poorly layered filesystems must either add additional hooks -and/or undergo extensive additional testing... or should just -not enable the optional cleancache. - -Some points for a filesystem to consider: - - - The FS should be block-device-based (e.g. a ram-based FS such - as tmpfs should not enable cleancache) - - To ensure coherency/correctness, the FS must ensure that all - file removal or truncation operations either go through VFS or - add hooks to do the equivalent cleancache "invalidate" operations - - To ensure coherency/correctness, either inode numbers must - be unique across the lifetime of the on-disk file OR the - FS must provide an "encode_fh" function. - - The FS must call the VFS superblock alloc and deactivate routines - or add hooks to do the equivalent cleancache calls done there. - - To maximize performance, all pages fetched from the FS should - go through the do_mpag_readpage routine or the FS should add - hooks to do the equivalent (cf. btrfs) - - Currently, the FS blocksize must be the same as PAGESIZE. This - is not an architectural restriction, but no backends currently - support anything different. - - A clustered FS should invoke the "shared_init_fs" cleancache - hook to get best performance for some backends. - -* Why not use the KVA of the inode as the key? (Christoph Hellwig) - -If cleancache would use the inode virtual address instead of -inode/filehandle, the pool id could be eliminated. But, this -won't work because cleancache retains pagecache data pages -persistently even when the inode has been pruned from the -inode unused list, and only invalidates the data page if the file -gets removed/truncated. So if cleancache used the inode kva, -there would be potential coherency issues if/when the inode -kva is reused for a different file. Alternately, if cleancache -invalidated the pages when the inode kva was freed, much of the value -of cleancache would be lost because the cache of pages in cleanache -is potentially much larger than the kernel pagecache and is most -useful if the pages survive inode cache removal. - -* Why is a global variable required? - -The cleancache_enabled flag is checked in all of the frequently-used -cleancache hooks. The alternative is a function call to check a static -variable. Since cleancache is enabled dynamically at runtime, systems -that don't enable cleancache would suffer thousands (possibly -tens-of-thousands) of unnecessary function calls per second. So the -global variable allows cleancache to be enabled by default at compile -time, but have insignificant performance impact when cleancache remains -disabled at runtime. - -* Does cleanache work with KVM? - -The memory model of KVM is sufficiently different that a cleancache -backend may have less value for KVM. This remains to be tested, -especially in an overcommitted system. - -* Does cleancache work in userspace? It sounds useful for - memory hungry caches like web browsers. (Jamie Lokier) - -No plans yet, though we agree it sounds useful, at least for -apps that bypass the page cache (e.g. O_DIRECT). - -Last updated: Dan Magenheimer, April 13 2011 diff --git a/Documentation/vm/frontswap.rst b/Documentation/vm/frontswap.rst index 1979f430c1c5..e2e5ab3e375e 100644 --- a/Documentation/vm/frontswap.rst +++ b/Documentation/vm/frontswap.rst @@ -8,12 +8,6 @@ Frontswap provides a "transcendent memory" interface for swap pages. In some environments, dramatic performance savings may be obtained because swapped pages are saved in RAM (or a RAM-like device) instead of a swap disk. -(Note, frontswap -- and :ref:`cleancache` (merged at 3.0) -- are the "frontends" -and the only necessary changes to the core kernel for transcendent memory; -all other supporting code -- the "backends" -- is implemented as drivers. -See the LWN.net article `Transcendent memory in a nutshell`_ -for a detailed overview of frontswap and related kernel parts) - .. _Transcendent memory in a nutshell: https://lwn.net/Articles/454795/ Frontswap is so named because it can be thought of as the opposite of @@ -87,11 +81,9 @@ This interface is ideal when data is transformed to a different form and size (such as with compression) or secretly moved (as might be useful for write-balancing for some RAM-like devices). Swap pages (and evicted page-cache pages) are a great use for this kind of slower-than-RAM- -but-much-faster-than-disk "pseudo-RAM device" and the frontswap (and -cleancache) interface to transcendent memory provides a nice way to read -and write -- and indirectly "name" -- the pages. +but-much-faster-than-disk "pseudo-RAM device". -Frontswap -- and cleancache -- with a fairly small impact on the kernel, +Frontswap with a fairly small impact on the kernel, provides a huge amount of flexibility for more dynamic, flexible RAM utilization in various system configurations: diff --git a/Documentation/vm/index.rst b/Documentation/vm/index.rst index 932440805453..44365c4574a3 100644 --- a/Documentation/vm/index.rst +++ b/Documentation/vm/index.rst @@ -15,7 +15,6 @@ algorithms. If you are looking for advice on simply allocating memory, see the active_mm arch_pgtable_helpers balance - cleancache damon/index free_page_reporting frontswap diff --git a/MAINTAINERS b/MAINTAINERS index 6c08cbe953fe..45f8750f6e30 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4705,13 +4705,6 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/cla F: include/linux/cfi.h F: kernel/cfi.c -CLEANCACHE API -M: Konrad Rzeszutek Wilk -L: linux-kernel@vger.kernel.org -S: Maintained -F: include/linux/cleancache.h -F: mm/cleancache.c - CLK API M: Russell King L: linux-clk@vger.kernel.org diff --git a/arch/arm/configs/bcm2835_defconfig b/arch/arm/configs/bcm2835_defconfig index 383c632eba7b..a9ed79b7f871 100644 --- a/arch/arm/configs/bcm2835_defconfig +++ b/arch/arm/configs/bcm2835_defconfig @@ -31,7 +31,6 @@ CONFIG_ARCH_BCM2835=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_AEABI=y CONFIG_KSM=y -CONFIG_CLEANCACHE=y CONFIG_CMA=y CONFIG_SECCOMP=y CONFIG_KEXEC=y diff --git a/arch/arm/configs/qcom_defconfig b/arch/arm/configs/qcom_defconfig index 0daa9c0d298e..9981566f2096 100644 --- a/arch/arm/configs/qcom_defconfig +++ b/arch/arm/configs/qcom_defconfig @@ -27,7 +27,6 @@ CONFIG_PCIE_QCOM=y CONFIG_SMP=y CONFIG_PREEMPT=y CONFIG_HIGHMEM=y -CONFIG_CLEANCACHE=y CONFIG_ARM_APPENDED_DTB=y CONFIG_ARM_ATAG_DTB_COMPAT=y CONFIG_CPU_IDLE=y diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index a4b6c7108465..bc9952f8be66 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -45,7 +45,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 2db721965520..a77269c6e5ba 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -41,7 +41,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index c266a704eecd..7a74efa6b9a1 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -48,7 +48,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index f644f08dd6ed..a5323bf2eb33 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -38,7 +38,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index e4924650b687..5e80aa0869d5 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -40,7 +40,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 24113871ea76..e84326a3f62d 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -39,7 +39,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 6a7e4be70eea..337552f43339 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -59,7 +59,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 1d223247aff0..7b688f7d272a 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -37,7 +37,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index 961f789f96c9..7c2cb31d63dd 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -38,7 +38,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index ff4b5e469390..ca43897af26d 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -39,7 +39,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 5f228621d0cc..e3d515f37144 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -35,7 +35,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index a600cb9e68c2..d601606c969b 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -35,7 +35,6 @@ CONFIG_IOSCHED_BFQ=m CONFIG_BINFMT_AOUT=m CONFIG_BINFMT_MISC=m # CONFIG_COMPACTION is not set -CONFIG_CLEANCACHE=y CONFIG_ZPOOL=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 354e51dcb3e2..7fe8975b49ec 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -96,7 +96,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_DEBUG=y CONFIG_CMA_DEBUGFS=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8dee6c3782f3..466780c465f5 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -91,7 +91,6 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y -CONFIG_CLEANCACHE=y CONFIG_FRONTSWAP=y CONFIG_CMA_SYSFS=y CONFIG_CMA_AREAS=7 diff --git a/block/bdev.c b/block/bdev.c index 8bf93a19041b..102837a37051 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -24,7 +24,6 @@ #include #include #include -#include #include #include #include "../fs/internal.h" @@ -88,10 +87,6 @@ void invalidate_bdev(struct block_device *bdev) lru_add_drain_all(); /* make sure all lru add caches are flushed */ invalidate_mapping_pages(mapping, 0, -1); } - /* 99% of the time, we don't need to flush the cleancache on the bdev. - * But, for the strange corners, lets be cautious - */ - cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(invalidate_bdev); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d6d48ecf823c..409bad3928db 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include "misc.h" #include "extent_io.h" @@ -3578,15 +3577,6 @@ int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, goto out; } - if (!PageUptodate(page)) { - if (cleancache_get_page(page) == 0) { - BUG_ON(blocksize != PAGE_SIZE); - unlock_extent(tree, start, end); - unlock_page(page); - goto out; - } - } - if (page->index == last_byte >> PAGE_SHIFT) { size_t zero_offset = offset_in_page(last_byte); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 0ec09fe01be6..4d947ba32da9 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include @@ -1374,7 +1373,6 @@ static int btrfs_fill_super(struct super_block *sb, goto fail_close; } - cleancache_init_fs(sb); sb->s_flags |= SB_ACTIVE; return 0; diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index 3db923403505..4cd62f1d848c 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -43,7 +43,6 @@ #include #include #include -#include #include "ext4.h" @@ -350,11 +349,6 @@ int ext4_mpage_readpages(struct inode *inode, } else if (fully_mapped) { SetPageMappedToDisk(page); } - if (fully_mapped && blocks_per_page == 1 && - !PageUptodate(page) && cleancache_get_page(page) == 0) { - SetPageUptodate(page); - goto confused; - } /* * This page will go to BIO. Do we need to send this diff --git a/fs/ext4/super.c b/fs/ext4/super.c index db9fe4843529..eee0d9ebfa6c 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -39,7 +39,6 @@ #include #include #include -#include #include #include #include @@ -3149,8 +3148,6 @@ done: EXT4_BLOCKS_PER_GROUP(sb), EXT4_INODES_PER_GROUP(sb), sbi->s_mount_opt, sbi->s_mount_opt2); - - cleancache_init_fs(sb); return err; } diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 0a1d236212f8..8c417864c66a 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include @@ -2035,12 +2034,6 @@ got_it: block_nr = map->m_pblk + block_in_file - map->m_lblk; SetPageMappedToDisk(page); - if (!PageUptodate(page) && (!PageSwapCache(page) && - !cleancache_get_page(page))) { - SetPageUptodate(page); - goto confused; - } - if (!f2fs_is_valid_blkaddr(F2FS_I_SB(inode), block_nr, DATA_GENERIC_ENHANCE_READ)) { ret = -EFSCORRUPTED; @@ -2096,12 +2089,6 @@ submit_and_realloc: ClearPageError(page); *last_block_in_bio = block_nr; goto out; -confused: - if (bio) { - __submit_bio(F2FS_I_SB(inode), bio, DATA); - bio = NULL; - } - unlock_page(page); out: *bio_ret = bio; return ret; diff --git a/fs/mpage.c b/fs/mpage.c index 334e7d09aa65..87f5cfef6caa 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -29,7 +29,6 @@ #include #include #include -#include #include "internal.h" /* @@ -284,12 +283,6 @@ static struct bio *do_mpage_readpage(struct mpage_readpage_args *args) SetPageMappedToDisk(page); } - if (fully_mapped && blocks_per_page == 1 && !PageUptodate(page) && - cleancache_get_page(page) == 0) { - SetPageUptodate(page); - goto confused; - } - /* * This page will go to BIO. Do we need to send this BIO off first? */ diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 8aaec7e0804e..fb825059d488 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -11,7 +11,6 @@ #include #include -#include #include #include #include diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 1286b88b6fa1..2772dec9dcea 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -25,7 +25,6 @@ #include #include #include -#include #include #define CREATE_TRACE_POINTS @@ -2283,7 +2282,6 @@ static int ocfs2_initialize_super(struct super_block *sb, mlog_errno(status); goto bail; } - cleancache_init_shared_fs(sb); osb->ocfs2_wq = alloc_ordered_workqueue("ocfs2_wq", WQ_MEM_RECLAIM); if (!osb->ocfs2_wq) { diff --git a/fs/super.c b/fs/super.c index a6405d44d4ca..7af820ba5ad5 100644 --- a/fs/super.c +++ b/fs/super.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include #include @@ -260,7 +259,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags, s->s_time_gran = 1000000000; s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; - s->cleancache_poolid = CLEANCACHE_NO_POOL; s->s_shrink.seeks = DEFAULT_SEEKS; s->s_shrink.scan_objects = super_cache_scan; @@ -330,7 +328,6 @@ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { - cleancache_invalidate_fs(s); unregister_shrinker(&s->s_shrink); fs->kill_sb(s); diff --git a/include/linux/cleancache.h b/include/linux/cleancache.h deleted file mode 100644 index 5f5730c1d324..000000000000 --- a/include/linux/cleancache.h +++ /dev/null @@ -1,124 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_CLEANCACHE_H -#define _LINUX_CLEANCACHE_H - -#include -#include -#include - -#define CLEANCACHE_NO_POOL -1 -#define CLEANCACHE_NO_BACKEND -2 -#define CLEANCACHE_NO_BACKEND_SHARED -3 - -#define CLEANCACHE_KEY_MAX 6 - -/* - * cleancache requires every file with a page in cleancache to have a - * unique key unless/until the file is removed/truncated. For some - * filesystems, the inode number is unique, but for "modern" filesystems - * an exportable filehandle is required (see exportfs.h) - */ -struct cleancache_filekey { - union { - ino_t ino; - __u32 fh[CLEANCACHE_KEY_MAX]; - u32 key[CLEANCACHE_KEY_MAX]; - } u; -}; - -struct cleancache_ops { - int (*init_fs)(size_t); - int (*init_shared_fs)(uuid_t *uuid, size_t); - int (*get_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*put_page)(int, struct cleancache_filekey, - pgoff_t, struct page *); - void (*invalidate_page)(int, struct cleancache_filekey, pgoff_t); - void (*invalidate_inode)(int, struct cleancache_filekey); - void (*invalidate_fs)(int); -}; - -extern int cleancache_register_ops(const struct cleancache_ops *ops); -extern void __cleancache_init_fs(struct super_block *); -extern void __cleancache_init_shared_fs(struct super_block *); -extern int __cleancache_get_page(struct page *); -extern void __cleancache_put_page(struct page *); -extern void __cleancache_invalidate_page(struct address_space *, struct page *); -extern void __cleancache_invalidate_inode(struct address_space *); -extern void __cleancache_invalidate_fs(struct super_block *); - -#ifdef CONFIG_CLEANCACHE -#define cleancache_enabled (1) -static inline bool cleancache_fs_enabled_mapping(struct address_space *mapping) -{ - return mapping->host->i_sb->cleancache_poolid >= 0; -} -static inline bool cleancache_fs_enabled(struct page *page) -{ - return cleancache_fs_enabled_mapping(page->mapping); -} -#else -#define cleancache_enabled (0) -#define cleancache_fs_enabled(_page) (0) -#define cleancache_fs_enabled_mapping(_page) (0) -#endif - -/* - * The shim layer provided by these inline functions allows the compiler - * to reduce all cleancache hooks to nothingness if CONFIG_CLEANCACHE - * is disabled, to a single global variable check if CONFIG_CLEANCACHE - * is enabled but no cleancache "backend" has dynamically enabled it, - * and, for the most frequent cleancache ops, to a single global variable - * check plus a superblock element comparison if CONFIG_CLEANCACHE is enabled - * and a cleancache backend has dynamically enabled cleancache, but the - * filesystem referenced by that cleancache op has not enabled cleancache. - * As a result, CONFIG_CLEANCACHE can be enabled by default with essentially - * no measurable performance impact. - */ - -static inline void cleancache_init_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_fs(sb); -} - -static inline void cleancache_init_shared_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_init_shared_fs(sb); -} - -static inline int cleancache_get_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - return __cleancache_get_page(page); - return -1; -} - -static inline void cleancache_put_page(struct page *page) -{ - if (cleancache_enabled && cleancache_fs_enabled(page)) - __cleancache_put_page(page); -} - -static inline void cleancache_invalidate_page(struct address_space *mapping, - struct page *page) -{ - /* careful... page->mapping is NULL sometimes when this is called */ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_page(mapping, page); -} - -static inline void cleancache_invalidate_inode(struct address_space *mapping) -{ - if (cleancache_enabled && cleancache_fs_enabled_mapping(mapping)) - __cleancache_invalidate_inode(mapping); -} - -static inline void cleancache_invalidate_fs(struct super_block *sb) -{ - if (cleancache_enabled) - __cleancache_invalidate_fs(sb); -} - -#endif /* _LINUX_CLEANCACHE_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 9617dea24978..f3daaea16554 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1535,11 +1535,6 @@ struct super_block { const struct dentry_operations *s_d_op; /* default d_op for dentries */ - /* - * Saved pool identifier for cleancache (-1 means none) - */ - int cleancache_poolid; - struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ diff --git a/mm/Kconfig b/mm/Kconfig index a99bd499ef51..430240289b02 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -444,28 +444,6 @@ config USE_PERCPU_NUMA_NODE_ID config HAVE_SETUP_PER_CPU_AREA bool -config CLEANCACHE - bool "Enable cleancache driver to cache clean pages if tmem is present" - help - Cleancache can be thought of as a page-granularity victim cache - for clean pages that the kernel's pageframe replacement algorithm - (PFRA) would like to keep around, but can't since there isn't enough - memory. So when the PFRA "evicts" a page, it first attempts to use - cleancache code to put the data contained in that page into - "transcendent memory", memory that is not directly accessible or - addressable by the kernel and is of unknown and possibly - time-varying size. And when a cleancache-enabled - filesystem wishes to access a page in a file on disk, it first - checks cleancache to see if it already contains it; if it does, - the page is copied into the kernel and a disk access is avoided. - When a transcendent memory driver is available (such as zcache or - Xen transcendent memory), a significant I/O reduction - may be achieved. When none is available, all cleancache calls - are reduced to a single pointer-compare-against-NULL resulting - in a negligible performance hit. - - If unsure, say Y to enable cleancache - config FRONTSWAP bool "Enable frontswap to cache swap pages if tmem is present" depends on SWAP diff --git a/mm/Makefile b/mm/Makefile index 588d3113f3b0..70d4309c9ce3 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -104,7 +104,6 @@ obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o obj-$(CONFIG_DEBUG_VM_PGTABLE) += debug_vm_pgtable.o obj-$(CONFIG_PAGE_OWNER) += page_owner.o -obj-$(CONFIG_CLEANCACHE) += cleancache.o obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o obj-$(CONFIG_ZPOOL) += zpool.o obj-$(CONFIG_ZBUD) += zbud.o diff --git a/mm/cleancache.c b/mm/cleancache.c deleted file mode 100644 index db7eee9c0886..000000000000 --- a/mm/cleancache.c +++ /dev/null @@ -1,315 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Cleancache frontend - * - * This code provides the generic "frontend" layer to call a matching - * "backend" driver implementation of cleancache. See - * Documentation/vm/cleancache.rst for more information. - * - * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. - * Author: Dan Magenheimer - */ - -#include -#include -#include -#include -#include -#include - -/* - * cleancache_ops is set by cleancache_register_ops to contain the pointers - * to the cleancache "backend" implementation functions. - */ -static const struct cleancache_ops *cleancache_ops __read_mostly; - -/* - * Counters available via /sys/kernel/debug/cleancache (if debugfs is - * properly configured. These are for information only so are not protected - * against increment races. - */ -static u64 cleancache_succ_gets; -static u64 cleancache_failed_gets; -static u64 cleancache_puts; -static u64 cleancache_invalidates; - -static void cleancache_register_ops_sb(struct super_block *sb, void *unused) -{ - switch (sb->cleancache_poolid) { - case CLEANCACHE_NO_BACKEND: - __cleancache_init_fs(sb); - break; - case CLEANCACHE_NO_BACKEND_SHARED: - __cleancache_init_shared_fs(sb); - break; - } -} - -/* - * Register operations for cleancache. Returns 0 on success. - */ -int cleancache_register_ops(const struct cleancache_ops *ops) -{ - if (cmpxchg(&cleancache_ops, NULL, ops)) - return -EBUSY; - - /* - * A cleancache backend can be built as a module and hence loaded after - * a cleancache enabled filesystem has called cleancache_init_fs. To - * handle such a scenario, here we call ->init_fs or ->init_shared_fs - * for each active super block. To differentiate between local and - * shared filesystems, we temporarily initialize sb->cleancache_poolid - * to CLEANCACHE_NO_BACKEND or CLEANCACHE_NO_BACKEND_SHARED - * respectively in case there is no backend registered at the time - * cleancache_init_fs or cleancache_init_shared_fs is called. - * - * Since filesystems can be mounted concurrently with cleancache - * backend registration, we have to be careful to guarantee that all - * cleancache enabled filesystems that has been mounted by the time - * cleancache_register_ops is called has got and all mounted later will - * get cleancache_poolid. This is assured by the following statements - * tied together: - * - * a) iterate_supers skips only those super blocks that has started - * ->kill_sb - * - * b) if iterate_supers encounters a super block that has not finished - * ->mount yet, it waits until it is finished - * - * c) cleancache_init_fs is called from ->mount and - * cleancache_invalidate_fs is called from ->kill_sb - * - * d) we call iterate_supers after cleancache_ops has been set - * - * From a) it follows that if iterate_supers skips a super block, then - * either the super block is already dead, in which case we do not need - * to bother initializing cleancache for it, or it was mounted after we - * initiated iterate_supers. In the latter case, it must have seen - * cleancache_ops set according to d) and initialized cleancache from - * ->mount by itself according to c). This proves that we call - * ->init_fs at least once for each active super block. - * - * From b) and c) it follows that if iterate_supers encounters a super - * block that has already started ->init_fs, it will wait until ->mount - * and hence ->init_fs has finished, then check cleancache_poolid, see - * that it has already been set and therefore do nothing. This proves - * that we call ->init_fs no more than once for each super block. - * - * Combined together, the last two paragraphs prove the function - * correctness. - * - * Note that various cleancache callbacks may proceed before this - * function is called or even concurrently with it, but since - * CLEANCACHE_NO_BACKEND is negative, they will all result in a noop - * until the corresponding ->init_fs has been actually called and - * cleancache_ops has been set. - */ - iterate_supers(cleancache_register_ops_sb, NULL); - return 0; -} -EXPORT_SYMBOL(cleancache_register_ops); - -/* Called by a cleancache-enabled filesystem at time of mount */ -void __cleancache_init_fs(struct super_block *sb) -{ - int pool_id = CLEANCACHE_NO_BACKEND; - - if (cleancache_ops) { - pool_id = cleancache_ops->init_fs(PAGE_SIZE); - if (pool_id < 0) - pool_id = CLEANCACHE_NO_POOL; - } - sb->cleancache_poolid = pool_id; -} -EXPORT_SYMBOL(__cleancache_init_fs); - -/* Called by a cleancache-enabled clustered filesystem at time of mount */ -void __cleancache_init_shared_fs(struct super_block *sb) -{ - int pool_id = CLEANCACHE_NO_BACKEND_SHARED; - - if (cleancache_ops) { - pool_id = cleancache_ops->init_shared_fs(&sb->s_uuid, PAGE_SIZE); - if (pool_id < 0) - pool_id = CLEANCACHE_NO_POOL; - } - sb->cleancache_poolid = pool_id; -} -EXPORT_SYMBOL(__cleancache_init_shared_fs); - -/* - * If the filesystem uses exportable filehandles, use the filehandle as - * the key, else use the inode number. - */ -static int cleancache_get_key(struct inode *inode, - struct cleancache_filekey *key) -{ - int (*fhfn)(struct inode *, __u32 *fh, int *, struct inode *); - int len = 0, maxlen = CLEANCACHE_KEY_MAX; - struct super_block *sb = inode->i_sb; - - key->u.ino = inode->i_ino; - if (sb->s_export_op != NULL) { - fhfn = sb->s_export_op->encode_fh; - if (fhfn) { - len = (*fhfn)(inode, &key->u.fh[0], &maxlen, NULL); - if (len <= FILEID_ROOT || len == FILEID_INVALID) - return -1; - if (maxlen > CLEANCACHE_KEY_MAX) - return -1; - } - } - return 0; -} - -/* - * "Get" data from cleancache associated with the poolid/inode/index - * that were specified when the data was put to cleanache and, if - * successful, use it to fill the specified page with data and return 0. - * The pageframe is unchanged and returns -1 if the get fails. - * Page must be locked by caller. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -int __cleancache_get_page(struct page *page) -{ - int ret = -1; - int pool_id; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) { - cleancache_failed_gets++; - goto out; - } - - VM_BUG_ON_PAGE(!PageLocked(page), page); - pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (pool_id < 0) - goto out; - - if (cleancache_get_key(page->mapping->host, &key) < 0) - goto out; - - ret = cleancache_ops->get_page(pool_id, key, page->index, page); - if (ret == 0) - cleancache_succ_gets++; - else - cleancache_failed_gets++; -out: - return ret; -} -EXPORT_SYMBOL(__cleancache_get_page); - -/* - * "Put" data from a page to cleancache and associate it with the - * (previously-obtained per-filesystem) poolid and the page's, - * inode and page index. Page must be locked. Note that a put_page - * always "succeeds", though a subsequent get_page may succeed or fail. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -void __cleancache_put_page(struct page *page) -{ - int pool_id; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) { - cleancache_puts++; - return; - } - - VM_BUG_ON_PAGE(!PageLocked(page), page); - pool_id = page->mapping->host->i_sb->cleancache_poolid; - if (pool_id >= 0 && - cleancache_get_key(page->mapping->host, &key) >= 0) { - cleancache_ops->put_page(pool_id, key, page->index, page); - cleancache_puts++; - } -} -EXPORT_SYMBOL(__cleancache_put_page); - -/* - * Invalidate any data from cleancache associated with the poolid and the - * page's inode and page index so that a subsequent "get" will fail. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -void __cleancache_invalidate_page(struct address_space *mapping, - struct page *page) -{ - /* careful... page->mapping is NULL sometimes when this is called */ - int pool_id = mapping->host->i_sb->cleancache_poolid; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) - return; - - if (pool_id >= 0) { - VM_BUG_ON_PAGE(!PageLocked(page), page); - if (cleancache_get_key(mapping->host, &key) >= 0) { - cleancache_ops->invalidate_page(pool_id, - key, page->index); - cleancache_invalidates++; - } - } -} -EXPORT_SYMBOL(__cleancache_invalidate_page); - -/* - * Invalidate all data from cleancache associated with the poolid and the - * mappings's inode so that all subsequent gets to this poolid/inode - * will fail. - * - * The function has two checks before any action is taken - whether - * a backend is registered and whether the sb->cleancache_poolid - * is correct. - */ -void __cleancache_invalidate_inode(struct address_space *mapping) -{ - int pool_id = mapping->host->i_sb->cleancache_poolid; - struct cleancache_filekey key = { .u.key = { 0 } }; - - if (!cleancache_ops) - return; - - if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) - cleancache_ops->invalidate_inode(pool_id, key); -} -EXPORT_SYMBOL(__cleancache_invalidate_inode); - -/* - * Called by any cleancache-enabled filesystem at time of unmount; - * note that pool_id is surrendered and may be returned by a subsequent - * cleancache_init_fs or cleancache_init_shared_fs. - */ -void __cleancache_invalidate_fs(struct super_block *sb) -{ - int pool_id; - - pool_id = sb->cleancache_poolid; - sb->cleancache_poolid = CLEANCACHE_NO_POOL; - - if (cleancache_ops && pool_id >= 0) - cleancache_ops->invalidate_fs(pool_id); -} -EXPORT_SYMBOL(__cleancache_invalidate_fs); - -static int __init init_cleancache(void) -{ -#ifdef CONFIG_DEBUG_FS - struct dentry *root = debugfs_create_dir("cleancache", NULL); - - debugfs_create_u64("succ_gets", 0444, root, &cleancache_succ_gets); - debugfs_create_u64("failed_gets", 0444, root, &cleancache_failed_gets); - debugfs_create_u64("puts", 0444, root, &cleancache_puts); - debugfs_create_u64("invalidates", 0444, root, &cleancache_invalidates); -#endif - return 0; -} -module_init(init_cleancache) diff --git a/mm/filemap.c b/mm/filemap.c index 60866ae711e2..b50910ac2c88 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include @@ -151,16 +150,6 @@ static void filemap_unaccount_folio(struct address_space *mapping, { long nr; - /* - * if we're uptodate, flush out into the cleancache, otherwise - * invalidate any existing cleancache entries. We can't leave - * stale data around in the cleancache once our page is gone - */ - if (folio_test_uptodate(folio) && folio_test_mappedtodisk(folio)) - cleancache_put_page(&folio->page); - else - cleancache_invalidate_page(mapping, &folio->page); - VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { int mapcount; diff --git a/mm/truncate.c b/mm/truncate.c index 5e243d7269c0..9dbf0b75da5d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -22,7 +22,6 @@ #include /* grr. try_to_release_page, do_invalidatepage */ #include -#include #include #include "internal.h" @@ -264,7 +263,6 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) */ folio_zero_range(folio, offset, length); - cleancache_invalidate_page(folio->mapping, &folio->page); if (folio_has_private(folio)) do_invalidatepage(&folio->page, offset, length); if (!folio_test_large(folio)) @@ -351,7 +349,7 @@ void truncate_inode_pages_range(struct address_space *mapping, bool same_folio; if (mapping_empty(mapping)) - goto out; + return; /* * 'start' and 'end' always covers the range of pages to be fully @@ -442,9 +440,6 @@ void truncate_inode_pages_range(struct address_space *mapping, folio_batch_release(&fbatch); index++; } - -out: - cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); @@ -498,10 +493,6 @@ void truncate_inode_pages_final(struct address_space *mapping) xa_unlock_irq(&mapping->i_pages); } - /* - * Cleancache needs notification even if there are no pages or shadow - * entries. - */ truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); @@ -661,7 +652,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, int did_range_unmap = 0; if (mapping_empty(mapping)) - goto out; + return 0; folio_batch_init(&fbatch); index = start; @@ -725,8 +716,6 @@ int invalidate_inode_pages2_range(struct address_space *mapping, if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } -out: - cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); -- cgit v1.2.3 From 3d6035f136009f9cae380022754cba31f32570c5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:38 -0800 Subject: frontswap: remove frontswap_writethrough frontswap_writethrough is never called, so remove it. Link: https://lkml.kernel.org/r/20211224062246.1258487-3-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/frontswap.rst | 6 ------ include/linux/frontswap.h | 1 - mm/frontswap.c | 23 +---------------------- 3 files changed, 1 insertion(+), 29 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/frontswap.rst b/Documentation/vm/frontswap.rst index e2e5ab3e375e..2ab660651d04 100644 --- a/Documentation/vm/frontswap.rst +++ b/Documentation/vm/frontswap.rst @@ -39,12 +39,6 @@ a disk write and, if the data is later read back, a disk read are avoided. If a store returns failure, transcendent memory has rejected the data, and the page can be written to swap as usual. -If a backend chooses, frontswap can be configured as a "writethrough -cache" by calling frontswap_writethrough(). In this mode, the reduction -in swap device writes is lost (and also a non-trivial performance advantage) -in order to allow the backend to arbitrarily "reclaim" space used to -store frontswap pages to more completely manage its memory usage. - Note that if a page is stored and the page already exists in transcendent memory (a "duplicate" store), either the store succeeds and the data is overwritten, or the store fails AND the page is invalidated. This ensures stale data may diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index b07d88c92bb2..4a03fda41572 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -26,7 +26,6 @@ struct frontswap_ops { extern void frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); -extern void frontswap_writethrough(bool); #define FRONTSWAP_HAS_EXCLUSIVE_GETS extern void frontswap_tmem_exclusive_gets(bool); diff --git a/mm/frontswap.c b/mm/frontswap.c index 6bed12260dea..51a662a83955 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -32,16 +32,6 @@ static struct frontswap_ops *frontswap_ops __read_mostly; #define for_each_frontswap_ops(ops) \ for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next) -/* - * If enabled, frontswap_store will return failure even on success. As - * a result, the swap subsystem will always write the page to swap, in - * effect converting frontswap into a writethrough cache. In this mode, - * there is no direct reduction in swap writes, but a frontswap backend - * can unilaterally "reclaim" any pages in use with no data loss, thus - * providing increases control over maximum memory usage due to frontswap. - */ -static bool frontswap_writethrough_enabled __read_mostly; - /* * If enabled, the underlying tmem implementation is capable of doing * exclusive gets, so frontswap_load, on a successful tmem_get must @@ -170,15 +160,6 @@ void frontswap_register_ops(struct frontswap_ops *ops) } EXPORT_SYMBOL(frontswap_register_ops); -/* - * Enable/disable frontswap writethrough (see above). - */ -void frontswap_writethrough(bool enable) -{ - frontswap_writethrough_enabled = enable; -} -EXPORT_SYMBOL(frontswap_writethrough); - /* * Enable/disable frontswap exclusive gets (see above). */ @@ -283,9 +264,7 @@ int __frontswap_store(struct page *page) } else { inc_frontswap_failed_stores(); } - if (frontswap_writethrough_enabled) - /* report failure so swap also writes to swap device */ - ret = -1; + return ret; } EXPORT_SYMBOL(__frontswap_store); -- cgit v1.2.3 From 71024cb4a0bfe7767aec7a128d0a1a13a37b7fcd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:41 -0800 Subject: frontswap: remove frontswap_tmem_exclusive_gets frontswap_tmem_exclusive_gets is never called, so remove it. Link: https://lkml.kernel.org/r/20211224062246.1258487-4-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 2 -- mm/frontswap.c | 23 +---------------------- 2 files changed, 1 insertion(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 4a03fda41572..83a56392cc7f 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -26,8 +26,6 @@ struct frontswap_ops { extern void frontswap_register_ops(struct frontswap_ops *ops); extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); -#define FRONTSWAP_HAS_EXCLUSIVE_GETS -extern void frontswap_tmem_exclusive_gets(bool); extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); extern void __frontswap_init(unsigned type, unsigned long *map); diff --git a/mm/frontswap.c b/mm/frontswap.c index 51a662a83955..dba7f087ee86 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -32,13 +32,6 @@ static struct frontswap_ops *frontswap_ops __read_mostly; #define for_each_frontswap_ops(ops) \ for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next) -/* - * If enabled, the underlying tmem implementation is capable of doing - * exclusive gets, so frontswap_load, on a successful tmem_get must - * mark the page as no longer in frontswap AND mark it dirty. - */ -static bool frontswap_tmem_exclusive_gets_enabled __read_mostly; - #ifdef CONFIG_DEBUG_FS /* * Counters available via /sys/kernel/debug/frontswap (if debugfs is @@ -160,15 +153,6 @@ void frontswap_register_ops(struct frontswap_ops *ops) } EXPORT_SYMBOL(frontswap_register_ops); -/* - * Enable/disable frontswap exclusive gets (see above). - */ -void frontswap_tmem_exclusive_gets(bool enable) -{ - frontswap_tmem_exclusive_gets_enabled = enable; -} -EXPORT_SYMBOL(frontswap_tmem_exclusive_gets); - /* * Called when a swap device is swapon'd. */ @@ -296,13 +280,8 @@ int __frontswap_load(struct page *page) if (!ret) /* successful load */ break; } - if (ret == 0) { + if (ret == 0) inc_frontswap_loads(); - if (frontswap_tmem_exclusive_gets_enabled) { - SetPageDirty(page); - __frontswap_clear(sis, offset); - } - } return ret; } EXPORT_SYMBOL(__frontswap_load); -- cgit v1.2.3 From 0b364446d734da76e421dbfb09e5268270cefaf0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:44 -0800 Subject: frontswap: remove frontswap_shrink frontswap_shrink is never called, so remove it. Link: https://lkml.kernel.org/r/20211224062246.1258487-5-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/frontswap.rst | 13 ------- include/linux/frontswap.h | 1 - mm/frontswap.c | 83 ------------------------------------------ 3 files changed, 97 deletions(-) (limited to 'include/linux') diff --git a/Documentation/vm/frontswap.rst b/Documentation/vm/frontswap.rst index 2ab660651d04..feecc5e24477 100644 --- a/Documentation/vm/frontswap.rst +++ b/Documentation/vm/frontswap.rst @@ -255,19 +255,6 @@ the old data and ensure that it is no longer accessible. Since the swap subsystem then writes the new data to the read swap device, this is the correct course of action to ensure coherency. -* What is frontswap_shrink for? - -When the (non-frontswap) swap subsystem swaps out a page to a real -swap device, that page is only taking up low-value pre-allocated disk -space. But if frontswap has placed a page in transcendent memory, that -page may be taking up valuable real estate. The frontswap_shrink -routine allows code outside of the swap subsystem to force pages out -of the memory managed by frontswap and back into kernel-addressable memory. -For example, in RAMster, a "suction driver" thread will attempt -to "repatriate" pages sent to a remote machine back to the local machine; -this is driven using the frontswap_shrink mechanism when memory pressure -subsides. - * Why does the frontswap patch create the new include file swapfile.h? The frontswap code depends on some swap-subsystem-internal data diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 83a56392cc7f..d268d7bb6513 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -24,7 +24,6 @@ struct frontswap_ops { }; extern void frontswap_register_ops(struct frontswap_ops *ops); -extern void frontswap_shrink(unsigned long); extern unsigned long frontswap_curr_pages(void); extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); diff --git a/mm/frontswap.c b/mm/frontswap.c index dba7f087ee86..a77ebba6101b 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -341,89 +341,6 @@ static unsigned long __frontswap_curr_pages(void) return totalpages; } -static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused, - int *swapid) -{ - int ret = -EINVAL; - struct swap_info_struct *si = NULL; - int si_frontswap_pages; - unsigned long total_pages_to_unuse = total; - unsigned long pages = 0, pages_to_unuse = 0; - - assert_spin_locked(&swap_lock); - plist_for_each_entry(si, &swap_active_head, list) { - si_frontswap_pages = atomic_read(&si->frontswap_pages); - if (total_pages_to_unuse < si_frontswap_pages) { - pages = pages_to_unuse = total_pages_to_unuse; - } else { - pages = si_frontswap_pages; - pages_to_unuse = 0; /* unuse all */ - } - /* ensure there is enough RAM to fetch pages from frontswap */ - if (security_vm_enough_memory_mm(current->mm, pages)) { - ret = -ENOMEM; - continue; - } - vm_unacct_memory(pages); - *unused = pages_to_unuse; - *swapid = si->type; - ret = 0; - break; - } - - return ret; -} - -/* - * Used to check if it's necessary and feasible to unuse pages. - * Return 1 when nothing to do, 0 when need to shrink pages, - * error code when there is an error. - */ -static int __frontswap_shrink(unsigned long target_pages, - unsigned long *pages_to_unuse, - int *type) -{ - unsigned long total_pages = 0, total_pages_to_unuse; - - assert_spin_locked(&swap_lock); - - total_pages = __frontswap_curr_pages(); - if (total_pages <= target_pages) { - /* Nothing to do */ - *pages_to_unuse = 0; - return 1; - } - total_pages_to_unuse = total_pages - target_pages; - return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type); -} - -/* - * Frontswap, like a true swap device, may unnecessarily retain pages - * under certain circumstances; "shrink" frontswap is essentially a - * "partial swapoff" and works by calling try_to_unuse to attempt to - * unuse enough frontswap pages to attempt to -- subject to memory - * constraints -- reduce the number of pages in frontswap to the - * number given in the parameter target_pages. - */ -void frontswap_shrink(unsigned long target_pages) -{ - unsigned long pages_to_unuse = 0; - int type, ret; - - /* - * we don't want to hold swap_lock while doing a very - * lengthy try_to_unuse, but swap_list may change - * so restart scan from swap_active_head each time - */ - spin_lock(&swap_lock); - ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type); - spin_unlock(&swap_lock); - if (ret == 0) - try_to_unuse(type, true, pages_to_unuse); - return; -} -EXPORT_SYMBOL(frontswap_shrink); - /* * Count and return the number of frontswap pages across all * swap devices. This is exported so that backend drivers can -- cgit v1.2.3 From 3e8e1af63d7a831f576477c25d9b89049bd2d53d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:47 -0800 Subject: frontswap: remove frontswap_curr_pages frontswap_curr_pages is never called, so remove it. Link: https://lkml.kernel.org/r/20211224062246.1258487-6-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 1 - mm/frontswap.c | 28 ---------------------------- 2 files changed, 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index d268d7bb6513..5205c2977b20 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -24,7 +24,6 @@ struct frontswap_ops { }; extern void frontswap_register_ops(struct frontswap_ops *ops); -extern unsigned long frontswap_curr_pages(void); extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); extern void __frontswap_init(unsigned type, unsigned long *map); diff --git a/mm/frontswap.c b/mm/frontswap.c index a77ebba6101b..af8f68d0e5cc 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -330,34 +330,6 @@ void __frontswap_invalidate_area(unsigned type) } EXPORT_SYMBOL(__frontswap_invalidate_area); -static unsigned long __frontswap_curr_pages(void) -{ - unsigned long totalpages = 0; - struct swap_info_struct *si = NULL; - - assert_spin_locked(&swap_lock); - plist_for_each_entry(si, &swap_active_head, list) - totalpages += atomic_read(&si->frontswap_pages); - return totalpages; -} - -/* - * Count and return the number of frontswap pages across all - * swap devices. This is exported so that backend drivers can - * determine current usage without reading debugfs. - */ -unsigned long frontswap_curr_pages(void) -{ - unsigned long totalpages = 0; - - spin_lock(&swap_lock); - totalpages = __frontswap_curr_pages(); - spin_unlock(&swap_lock); - - return totalpages; -} -EXPORT_SYMBOL(frontswap_curr_pages); - static int __init init_frontswap(void) { #ifdef CONFIG_DEBUG_FS -- cgit v1.2.3 From 1cf53c894d15dd4b73397a56fa055d76d3db66b4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:51 -0800 Subject: frontswap: simplify frontswap_init Just use IS_ENABLED() and remove the __frontswap_init indirection. Also remove the unused export. Link: https://lkml.kernel.org/r/20211224062246.1258487-7-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 9 +-------- mm/frontswap.c | 3 +-- mm/swapfile.c | 3 ++- 3 files changed, 4 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 5205c2977b20..73d7beb44f2b 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -26,7 +26,7 @@ struct frontswap_ops { extern void frontswap_register_ops(struct frontswap_ops *ops); extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); -extern void __frontswap_init(unsigned type, unsigned long *map); +extern void frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); extern void __frontswap_invalidate_page(unsigned, pgoff_t); @@ -107,11 +107,4 @@ static inline void frontswap_invalidate_area(unsigned type) __frontswap_invalidate_area(type); } -static inline void frontswap_init(unsigned type, unsigned long *map) -{ -#ifdef CONFIG_FRONTSWAP - __frontswap_init(type, map); -#endif -} - #endif /* _LINUX_FRONTSWAP_H */ diff --git a/mm/frontswap.c b/mm/frontswap.c index af8f68d0e5cc..132d6ad6d70b 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -156,7 +156,7 @@ EXPORT_SYMBOL(frontswap_register_ops); /* * Called when a swap device is swapon'd. */ -void __frontswap_init(unsigned type, unsigned long *map) +void frontswap_init(unsigned type, unsigned long *map) { struct swap_info_struct *sis = swap_info[type]; struct frontswap_ops *ops; @@ -179,7 +179,6 @@ void __frontswap_init(unsigned type, unsigned long *map) for_each_frontswap_ops(ops) ops->init(type); } -EXPORT_SYMBOL(__frontswap_init); bool __frontswap_test(struct swap_info_struct *sis, pgoff_t offset) diff --git a/mm/swapfile.c b/mm/swapfile.c index caa9f81a0d15..df5930ccd93d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2463,7 +2463,8 @@ static void enable_swap_info(struct swap_info_struct *p, int prio, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { - frontswap_init(p->type, frontswap_map); + if (IS_ENABLED(CONFIG_FRONTSWAP)) + frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); -- cgit v1.2.3 From 10a9c496789fe2098bfc018650fc77b23ba08a54 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:14:57 -0800 Subject: mm: simplify try_to_unuse Remove the unused frontswap and pages_to_unuse arguments, and mark the function static now that the caller in frontswap is gone. [akpm@linux-foundation.org: fix shmem_unuse() stub, per Matthew] Link: https://lkml.kernel.org/r/20211224062246.1258487-9-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Cc: Naresh Kamboju Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 7 ---- include/linux/shmem_fs.h | 3 +- include/linux/swapfile.h | 1 - mm/shmem.c | 33 ++++--------------- mm/swapfile.c | 83 +++++++++++++---------------------------------- 5 files changed, 30 insertions(+), 97 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index 73d7beb44f2b..a9817d4fa74c 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -7,13 +7,6 @@ #include #include -/* - * Return code to denote that requested number of - * frontswap pages are unused(moved to page cache). - * Used in shmem_unuse and try_to_unuse. - */ -#define FRONTSWAP_PAGES_UNUSED 2 - struct frontswap_ops { void (*init)(unsigned); /* this swap type was just swapon'ed */ int (*store)(unsigned, pgoff_t, struct page *); /* store a page */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 166158b6e917..e65b80ed09e7 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -83,8 +83,7 @@ extern void shmem_unlock_mapping(struct address_space *mapping); extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); -extern int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse); +int shmem_unuse(unsigned int type); extern bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, pgoff_t index); diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index e06febf62978..809cd01ef2c5 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -9,7 +9,6 @@ extern spinlock_t swap_lock; extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; -extern int try_to_unuse(unsigned int, bool, unsigned long); extern unsigned long generic_max_swapfile_size(void); extern unsigned long max_swapfile_size(void); diff --git a/mm/shmem.c b/mm/shmem.c index 66909efd0a1b..a09b29ec2b45 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -36,7 +36,6 @@ #include #include #include -#include #include #include @@ -1152,7 +1151,7 @@ static void shmem_evict_inode(struct inode *inode) static int shmem_find_swap_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices, - unsigned int type, bool frontswap) + unsigned int type) { XA_STATE(xas, &mapping->i_pages, start); struct page *page; @@ -1173,9 +1172,6 @@ static int shmem_find_swap_entries(struct address_space *mapping, entry = radix_to_swp_entry(page); if (swp_type(entry) != type) continue; - if (frontswap && - !frontswap_test(swap_info[type], swp_offset(entry))) - continue; indices[ret] = xas.xa_index; entries[ret] = page; @@ -1228,26 +1224,20 @@ static int shmem_unuse_swap_entries(struct inode *inode, struct pagevec pvec, /* * If swap found in inode, free it and move page from swapcache to filecache. */ -static int shmem_unuse_inode(struct inode *inode, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int shmem_unuse_inode(struct inode *inode, unsigned int type) { struct address_space *mapping = inode->i_mapping; pgoff_t start = 0; struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; - bool frontswap_partial = (frontswap && *fs_pages_to_unuse > 0); int ret = 0; pagevec_init(&pvec); do { unsigned int nr_entries = PAGEVEC_SIZE; - if (frontswap_partial && *fs_pages_to_unuse < PAGEVEC_SIZE) - nr_entries = *fs_pages_to_unuse; - pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries, - pvec.pages, indices, - type, frontswap); + pvec.pages, indices, type); if (pvec.nr == 0) { ret = 0; break; @@ -1257,14 +1247,6 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, if (ret < 0) break; - if (frontswap_partial) { - *fs_pages_to_unuse -= ret; - if (*fs_pages_to_unuse == 0) { - ret = FRONTSWAP_PAGES_UNUSED; - break; - } - } - start = indices[pvec.nr - 1]; } while (true); @@ -1276,8 +1258,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type, * device 'type' back into memory, so the swap device can be * unused. */ -int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) +int shmem_unuse(unsigned int type) { struct shmem_inode_info *info, *next; int error = 0; @@ -1300,8 +1281,7 @@ int shmem_unuse(unsigned int type, bool frontswap, atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); - error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, - fs_pages_to_unuse); + error = shmem_unuse_inode(&info->vfs_inode, type); cond_resched(); mutex_lock(&shmem_swaplist_mutex); @@ -4015,8 +3995,7 @@ int __init shmem_init(void) return 0; } -int shmem_unuse(unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) +int shmem_unuse(unsigned int type) { return 0; } diff --git a/mm/swapfile.c b/mm/swapfile.c index df5930ccd93d..82342c77791b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1923,8 +1923,7 @@ out: static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { struct page *page; swp_entry_t entry; @@ -1945,9 +1944,6 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, continue; offset = swp_offset(entry); - if (frontswap && !frontswap_test(si, offset)) - continue; - pte_unmap(pte); swap_map = &si->swap_map[offset]; page = lookup_swap_cache(entry, vma, addr); @@ -1979,11 +1975,6 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, try_to_free_swap(page); unlock_page(page); put_page(page); - - if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { - ret = FRONTSWAP_PAGES_UNUSED; - goto out; - } try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1996,8 +1987,7 @@ out: static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { pmd_t *pmd; unsigned long next; @@ -2009,8 +1999,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; - ret = unuse_pte_range(vma, pmd, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pte_range(vma, pmd, addr, next, type); if (ret) return ret; } while (pmd++, addr = next, addr != end); @@ -2019,8 +2008,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { pud_t *pud; unsigned long next; @@ -2031,8 +2019,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; - ret = unuse_pmd_range(vma, pud, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pmd_range(vma, pud, addr, next, type); if (ret) return ret; } while (pud++, addr = next, addr != end); @@ -2041,8 +2028,7 @@ static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, - unsigned int type, bool frontswap, - unsigned long *fs_pages_to_unuse) + unsigned int type) { p4d_t *p4d; unsigned long next; @@ -2053,16 +2039,14 @@ static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; - ret = unuse_pud_range(vma, p4d, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_pud_range(vma, p4d, addr, next, type); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } -static int unuse_vma(struct vm_area_struct *vma, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int unuse_vma(struct vm_area_struct *vma, unsigned int type) { pgd_t *pgd; unsigned long addr, end, next; @@ -2076,16 +2060,14 @@ static int unuse_vma(struct vm_area_struct *vma, unsigned int type, next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; - ret = unuse_p4d_range(vma, pgd, addr, next, type, - frontswap, fs_pages_to_unuse); + ret = unuse_p4d_range(vma, pgd, addr, next, type); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } -static int unuse_mm(struct mm_struct *mm, unsigned int type, - bool frontswap, unsigned long *fs_pages_to_unuse) +static int unuse_mm(struct mm_struct *mm, unsigned int type) { struct vm_area_struct *vma; int ret = 0; @@ -2093,8 +2075,7 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type, mmap_read_lock(mm); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma) { - ret = unuse_vma(vma, type, frontswap, - fs_pages_to_unuse); + ret = unuse_vma(vma, type); if (ret) break; } @@ -2110,7 +2091,7 @@ static int unuse_mm(struct mm_struct *mm, unsigned int type, * if there are no inuse entries after prev till end of the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, - unsigned int prev, bool frontswap) + unsigned int prev) { unsigned int i; unsigned char count; @@ -2124,8 +2105,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) - if (!frontswap || frontswap_test(si, i)) - break; + break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } @@ -2136,12 +2116,7 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si, return i; } -/* - * If the boolean frontswap is true, only unuse pages_to_unuse pages; - * pages_to_unuse==0 means all pages; ignored if frontswap is false - */ -int try_to_unuse(unsigned int type, bool frontswap, - unsigned long pages_to_unuse) +static int try_to_unuse(unsigned int type) { struct mm_struct *prev_mm; struct mm_struct *mm; @@ -2155,13 +2130,10 @@ int try_to_unuse(unsigned int type, bool frontswap, if (!READ_ONCE(si->inuse_pages)) return 0; - if (!frontswap) - pages_to_unuse = 0; - retry: - retval = shmem_unuse(type, frontswap, &pages_to_unuse); + retval = shmem_unuse(type); if (retval) - goto out; + return retval; prev_mm = &init_mm; mmget(prev_mm); @@ -2178,11 +2150,10 @@ retry: spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; - retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); - + retval = unuse_mm(mm, type); if (retval) { mmput(prev_mm); - goto out; + return retval; } /* @@ -2199,7 +2170,7 @@ retry: i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && - (i = find_next_to_unuse(si, i, frontswap)) != 0) { + (i = find_next_to_unuse(si, i)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); @@ -2217,14 +2188,6 @@ retry: try_to_free_swap(page); unlock_page(page); put_page(page); - - /* - * For frontswap, we just need to unuse pages_to_unuse, if - * it was specified. Need not check frontswap again here as - * we already zeroed out pages_to_unuse if not frontswap. - */ - if (pages_to_unuse && --pages_to_unuse == 0) - goto out; } /* @@ -2242,10 +2205,10 @@ retry: if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; - retval = -EINTR; + return -EINTR; } -out: - return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; + + return 0; } /* @@ -2577,7 +2540,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) disable_swap_slots_cache_lock(); set_current_oom_origin(); - err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ + err = try_to_unuse(p->type); clear_current_oom_origin(); if (err) { -- cgit v1.2.3 From bd9cd521496ba8d537d8f46f4167bf4221aba9a3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:15:01 -0800 Subject: frontswap: remove frontswap_test frontswap_test is unused now, remove it. Link: https://lkml.kernel.org/r/20211224062246.1258487-10-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 11 ----------- mm/frontswap.c | 2 +- 2 files changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index a9817d4fa74c..c5b2848d2240 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -18,7 +18,6 @@ struct frontswap_ops { extern void frontswap_register_ops(struct frontswap_ops *ops); -extern bool __frontswap_test(struct swap_info_struct *, pgoff_t); extern void frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); extern int __frontswap_load(struct page *page); @@ -33,11 +32,6 @@ static inline bool frontswap_enabled(void) return static_branch_unlikely(&frontswap_enabled_key); } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return __frontswap_test(sis, offset); -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { @@ -56,11 +50,6 @@ static inline bool frontswap_enabled(void) return false; } -static inline bool frontswap_test(struct swap_info_struct *sis, pgoff_t offset) -{ - return false; -} - static inline void frontswap_map_set(struct swap_info_struct *p, unsigned long *map) { diff --git a/mm/frontswap.c b/mm/frontswap.c index 42d554da53bb..f51159f0d75d 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -179,7 +179,7 @@ void frontswap_init(unsigned type, unsigned long *map) ops->init(type); } -bool __frontswap_test(struct swap_info_struct *sis, +static bool __frontswap_test(struct swap_info_struct *sis, pgoff_t offset) { if (sis->frontswap_map) -- cgit v1.2.3 From 633423a09cb5cfe61438283e1ce49c23cf4a0611 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:15:07 -0800 Subject: mm: mark swap_lock and swap_active_head static swap_lock and swap_active_head are only used in swapfile.c, so mark them static. Link: https://lkml.kernel.org/r/20211224062246.1258487-12-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swapfile.h | 2 -- mm/swapfile.c | 4 ++-- 2 files changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 809cd01ef2c5..54078542134c 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -6,8 +6,6 @@ * these were static in swapfile.c but frontswap.c needs them and we don't * want to expose them to the dozens of source files that include swap.h */ -extern spinlock_t swap_lock; -extern struct plist_head swap_active_head; extern struct swap_info_struct *swap_info[]; extern unsigned long generic_max_swapfile_size(void); extern unsigned long max_swapfile_size(void); diff --git a/mm/swapfile.c b/mm/swapfile.c index 82342c77791b..bf0df7aa7158 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -49,7 +49,7 @@ static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); -DEFINE_SPINLOCK(swap_lock); +static DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* @@ -71,7 +71,7 @@ static const char Unused_offset[] = "Unused swap offset entry "; * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ -PLIST_HEAD(swap_active_head); +static PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs -- cgit v1.2.3 From 1da0d94a3ec8c5f3793b7be8538b55e60ebeefe3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 21 Jan 2022 22:15:10 -0800 Subject: frontswap: remove support for multiple ops There is only a single instance of frontswap ops in the kernel, so simplify the frontswap code by removing support for multiple operations. Link: https://lkml.kernel.org/r/20211224062246.1258487-13-hch@lst.de Signed-off-by: Christoph Hellwig Reviewed-by: Juergen Gross Cc: Dan Streetman Cc: Geert Uytterhoeven Cc: Hugh Dickins Cc: Konrad Rzeszutek Wilk Cc: Matthew Wilcox (Oracle) Cc: Seth Jennings Cc: Vitaly Wool Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/frontswap.h | 3 +-- mm/frontswap.c | 50 ++++++++++++----------------------------------- mm/zswap.c | 8 ++++++-- 3 files changed, 19 insertions(+), 42 deletions(-) (limited to 'include/linux') diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h index c5b2848d2240..a631bac12220 100644 --- a/include/linux/frontswap.h +++ b/include/linux/frontswap.h @@ -13,10 +13,9 @@ struct frontswap_ops { int (*load)(unsigned, pgoff_t, struct page *); /* load a page */ void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */ void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */ - struct frontswap_ops *next; /* private pointer to next ops */ }; -extern void frontswap_register_ops(struct frontswap_ops *ops); +int frontswap_register_ops(const struct frontswap_ops *ops); extern void frontswap_init(unsigned type, unsigned long *map); extern int __frontswap_store(struct page *page); diff --git a/mm/frontswap.c b/mm/frontswap.c index 35040fa4eba8..6f69b044a8cc 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -27,10 +27,7 @@ DEFINE_STATIC_KEY_FALSE(frontswap_enabled_key); * may be registered, but implementations can never deregister. This * is a simple singly-linked list of all registered implementations. */ -static struct frontswap_ops *frontswap_ops __read_mostly; - -#define for_each_frontswap_ops(ops) \ - for ((ops) = frontswap_ops; (ops); (ops) = (ops)->next) +static const struct frontswap_ops *frontswap_ops __read_mostly; #ifdef CONFIG_DEBUG_FS /* @@ -97,18 +94,14 @@ static inline void inc_frontswap_invalidates(void) { } /* * Register operations for frontswap */ -void frontswap_register_ops(struct frontswap_ops *ops) +int frontswap_register_ops(const struct frontswap_ops *ops) { - /* - * Setting frontswap_ops must happen after the ops->init() calls - * above; cmpxchg implies smp_mb() which will ensure the init is - * complete at this point. - */ - do { - ops->next = frontswap_ops; - } while (cmpxchg(&frontswap_ops, ops->next, ops) != ops->next); + if (frontswap_ops) + return -EINVAL; + frontswap_ops = ops; static_branch_inc(&frontswap_enabled_key); + return 0; } /* @@ -117,7 +110,6 @@ void frontswap_register_ops(struct frontswap_ops *ops) void frontswap_init(unsigned type, unsigned long *map) { struct swap_info_struct *sis = swap_info[type]; - struct frontswap_ops *ops; VM_BUG_ON(sis == NULL); @@ -133,9 +125,7 @@ void frontswap_init(unsigned type, unsigned long *map) * p->frontswap set to something valid to work properly. */ frontswap_map_set(sis, map); - - for_each_frontswap_ops(ops) - ops->init(type); + frontswap_ops->init(type); } static bool __frontswap_test(struct swap_info_struct *sis, @@ -174,7 +164,6 @@ int __frontswap_store(struct page *page) int type = swp_type(entry); struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(!PageLocked(page)); @@ -188,16 +177,10 @@ int __frontswap_store(struct page *page) */ if (__frontswap_test(sis, offset)) { __frontswap_clear(sis, offset); - for_each_frontswap_ops(ops) - ops->invalidate_page(type, offset); + frontswap_ops->invalidate_page(type, offset); } - /* Try to store in each implementation, until one succeeds. */ - for_each_frontswap_ops(ops) { - ret = ops->store(type, offset, page); - if (!ret) /* successful store */ - break; - } + ret = frontswap_ops->store(type, offset, page); if (ret == 0) { __frontswap_set(sis, offset); inc_frontswap_succ_stores(); @@ -220,7 +203,6 @@ int __frontswap_load(struct page *page) int type = swp_type(entry); struct swap_info_struct *sis = swap_info[type]; pgoff_t offset = swp_offset(entry); - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(!PageLocked(page)); @@ -230,11 +212,7 @@ int __frontswap_load(struct page *page) return -1; /* Try loading from each implementation, until one succeeds. */ - for_each_frontswap_ops(ops) { - ret = ops->load(type, offset, page); - if (!ret) /* successful load */ - break; - } + ret = frontswap_ops->load(type, offset, page); if (ret == 0) inc_frontswap_loads(); return ret; @@ -247,7 +225,6 @@ int __frontswap_load(struct page *page) void __frontswap_invalidate_page(unsigned type, pgoff_t offset) { struct swap_info_struct *sis = swap_info[type]; - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(sis == NULL); @@ -255,8 +232,7 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset) if (!__frontswap_test(sis, offset)) return; - for_each_frontswap_ops(ops) - ops->invalidate_page(type, offset); + frontswap_ops->invalidate_page(type, offset); __frontswap_clear(sis, offset); inc_frontswap_invalidates(); } @@ -268,7 +244,6 @@ void __frontswap_invalidate_page(unsigned type, pgoff_t offset) void __frontswap_invalidate_area(unsigned type) { struct swap_info_struct *sis = swap_info[type]; - struct frontswap_ops *ops; VM_BUG_ON(!frontswap_ops); VM_BUG_ON(sis == NULL); @@ -276,8 +251,7 @@ void __frontswap_invalidate_area(unsigned type) if (sis->frontswap_map == NULL) return; - for_each_frontswap_ops(ops) - ops->invalidate_area(type); + frontswap_ops->invalidate_area(type); atomic_set(&sis->frontswap_pages, 0); bitmap_zero(sis->frontswap_map, sis->max); } diff --git a/mm/zswap.c b/mm/zswap.c index 7944e3e57e78..cdf6950fcb2e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1378,7 +1378,7 @@ static void zswap_frontswap_init(unsigned type) zswap_trees[type] = tree; } -static struct frontswap_ops zswap_frontswap_ops = { +static const struct frontswap_ops zswap_frontswap_ops = { .store = zswap_frontswap_store, .load = zswap_frontswap_load, .invalidate_page = zswap_frontswap_invalidate_page, @@ -1475,11 +1475,15 @@ static int __init init_zswap(void) if (!shrink_wq) goto fallback_fail; - frontswap_register_ops(&zswap_frontswap_ops); + ret = frontswap_register_ops(&zswap_frontswap_ops); + if (ret) + goto destroy_wq; if (zswap_debugfs_init()) pr_warn("debugfs initialization failed\n"); return 0; +destroy_wq: + destroy_workqueue(shrink_wq); fallback_fail: if (pool) zswap_pool_destroy(pool); -- cgit v1.2.3 From a37d9a17f099072fe4d3a9048b0321978707a918 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Thu, 20 Jan 2022 23:53:04 +0200 Subject: fsnotify: invalidate dcache before IN_DELETE event Apparently, there are some applications that use IN_DELETE event as an invalidation mechanism and expect that if they try to open a file with the name reported with the delete event, that it should not contain the content of the deleted file. Commit 49246466a989 ("fsnotify: move fsnotify_nameremove() hook out of d_delete()") moved the fsnotify delete hook before d_delete() so fsnotify will have access to a positive dentry. This allowed a race where opening the deleted file via cached dentry is now possible after receiving the IN_DELETE event. To fix the regression, create a new hook fsnotify_delete() that takes the unlinked inode as an argument and use a helper d_delete_notify() to pin the inode, so we can pass it to fsnotify_delete() after d_delete(). Backporting hint: this regression is from v5.3. Although patch will apply with only trivial conflicts to v5.4 and v5.10, it won't build, because fsnotify_delete() implementation is different in each of those versions (see fsnotify_link()). A follow up patch will fix the fsnotify_unlink/rmdir() calls in pseudo filesystem that do not need to call d_delete(). Link: https://lore.kernel.org/r/20220120215305.282577-1-amir73il@gmail.com Reported-by: Ivan Delalande Link: https://lore.kernel.org/linux-fsdevel/YeNyzoDM5hP5LtGW@visor/ Fixes: 49246466a989 ("fsnotify: move fsnotify_nameremove() hook out of d_delete()") Cc: stable@vger.kernel.org # v5.3+ Signed-off-by: Amir Goldstein Signed-off-by: Jan Kara --- fs/btrfs/ioctl.c | 6 ++---- fs/namei.c | 10 +++++----- include/linux/fsnotify.h | 49 ++++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 50 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a5bd6926f7ff..7807b28b7892 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3086,10 +3086,8 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, btrfs_inode_lock(inode, 0); err = btrfs_delete_subvolume(dir, dentry); btrfs_inode_unlock(inode, 0); - if (!err) { - fsnotify_rmdir(dir, dentry); - d_delete(dentry); - } + if (!err) + d_delete_notify(dir, dentry); out_dput: dput(dentry); diff --git a/fs/namei.c b/fs/namei.c index d81f04f8d818..4ed0e41feab7 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3974,13 +3974,12 @@ int vfs_rmdir(struct user_namespace *mnt_userns, struct inode *dir, dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); detach_mounts(dentry); - fsnotify_rmdir(dir, dentry); out: inode_unlock(dentry->d_inode); dput(dentry); if (!error) - d_delete(dentry); + d_delete_notify(dir, dentry); return error; } EXPORT_SYMBOL(vfs_rmdir); @@ -4102,7 +4101,6 @@ int vfs_unlink(struct user_namespace *mnt_userns, struct inode *dir, if (!error) { dont_mount(dentry); detach_mounts(dentry); - fsnotify_unlink(dir, dentry); } } } @@ -4110,9 +4108,11 @@ out: inode_unlock(target); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ - if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + if (!error && dentry->d_flags & DCACHE_NFSFS_RENAMED) { + fsnotify_unlink(dir, dentry); + } else if (!error) { fsnotify_link_count(target); - d_delete(dentry); + d_delete_notify(dir, dentry); } return error; diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h index 3a2d7dc3c607..bb8467cd11ae 100644 --- a/include/linux/fsnotify.h +++ b/include/linux/fsnotify.h @@ -224,6 +224,43 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, dir, &new_dentry->d_name, 0); } +/* + * fsnotify_delete - @dentry was unlinked and unhashed + * + * Caller must make sure that dentry->d_name is stable. + * + * Note: unlike fsnotify_unlink(), we have to pass also the unlinked inode + * as this may be called after d_delete() and old_dentry may be negative. + */ +static inline void fsnotify_delete(struct inode *dir, struct inode *inode, + struct dentry *dentry) +{ + __u32 mask = FS_DELETE; + + if (S_ISDIR(inode->i_mode)) + mask |= FS_ISDIR; + + fsnotify_name(mask, inode, FSNOTIFY_EVENT_INODE, dir, &dentry->d_name, + 0); +} + +/** + * d_delete_notify - delete a dentry and call fsnotify_delete() + * @dentry: The dentry to delete + * + * This helper is used to guaranty that the unlinked inode cannot be found + * by lookup of this name after fsnotify_delete() event has been delivered. + */ +static inline void d_delete_notify(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + + ihold(inode); + d_delete(dentry); + fsnotify_delete(dir, inode, dentry); + iput(inode); +} + /* * fsnotify_unlink - 'name' was unlinked * @@ -231,10 +268,10 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, */ static inline void fsnotify_unlink(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* @@ -258,10 +295,10 @@ static inline void fsnotify_mkdir(struct inode *dir, struct dentry *dentry) */ static inline void fsnotify_rmdir(struct inode *dir, struct dentry *dentry) { - /* Expected to be called before d_delete() */ - WARN_ON_ONCE(d_is_negative(dentry)); + if (WARN_ON_ONCE(d_is_negative(dentry))) + return; - fsnotify_dirent(dir, dentry, FS_DELETE | FS_ISDIR); + fsnotify_delete(dir, d_inode(dentry), dentry); } /* -- cgit v1.2.3 From 9daf0a4d32d60a57f2a2533bdf4c178be7fdff7f Mon Sep 17 00:00:00 2001 From: Tom Rix Date: Sun, 16 Jan 2022 04:59:36 -0800 Subject: quota: cleanup double word in comment Remove the second 'handle'. Link: https://lore.kernel.org/r/20220116125936.389767-1-trix@redhat.com Signed-off-by: Tom Rix Signed-off-by: Jan Kara --- include/linux/quota.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/quota.h b/include/linux/quota.h index 18ebd39c9487..fd692b4a41d5 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -91,7 +91,7 @@ extern bool qid_valid(struct kqid qid); * * When there is no mapping defined for the user-namespace, type, * qid tuple an invalid kqid is returned. Callers are expected to - * test for and handle handle invalid kqids being returned. + * test for and handle invalid kqids being returned. * Invalid kqids may be tested for using qid_valid(). */ static inline struct kqid make_kqid(struct user_namespace *from, -- cgit v1.2.3 From 945c37ed564770c78dfe6b9f08bed57a1b4e60ef Mon Sep 17 00:00:00 2001 From: Linyu Yuan Date: Mon, 10 Jan 2022 20:43:28 +0800 Subject: usb: roles: fix include/linux/usb/role.h compile issue when CONFIG_USB_ROLE_SWITCH is not defined, add usb_role_switch_find_by_fwnode() definition which return NULL. Fixes: c6919d5e0cd1 ("usb: roles: Add usb_role_switch_find_by_fwnode()") Signed-off-by: Linyu Yuan Link: https://lore.kernel.org/r/1641818608-25039-1-git-send-email-quic_linyyuan@quicinc.com Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/role.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/role.h b/include/linux/usb/role.h index 031f148ab373..b5deafd91f67 100644 --- a/include/linux/usb/role.h +++ b/include/linux/usb/role.h @@ -91,6 +91,12 @@ fwnode_usb_role_switch_get(struct fwnode_handle *node) static inline void usb_role_switch_put(struct usb_role_switch *sw) { } +static inline struct usb_role_switch * +usb_role_switch_find_by_fwnode(const struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct usb_role_switch * usb_role_switch_register(struct device *parent, const struct usb_role_switch_desc *desc) -- cgit v1.2.3 From 33569ef3c754a82010f266b7b938a66a3ccf90a4 Mon Sep 17 00:00:00 2001 From: Amadeusz Sławiński Date: Wed, 19 Jan 2022 11:47:51 +0100 Subject: PM: hibernate: Remove register_nosave_region_late() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is an unused wrapper forcing kmalloc allocation for registering nosave regions. Also, rename __register_nosave_region() to register_nosave_region() now that there is no need for disambiguation. Signed-off-by: Amadeusz Sławiński Reviewed-by: Cezary Rojewski Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 11 +---------- kernel/power/snapshot.c | 21 +++++++-------------- 2 files changed, 8 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 5785d909c321..3e8ecdebe601 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -430,15 +430,7 @@ struct platform_hibernation_ops { #ifdef CONFIG_HIBERNATION /* kernel/power/snapshot.c */ -extern void __register_nosave_region(unsigned long b, unsigned long e, int km); -static inline void __init register_nosave_region(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 0); -} -static inline void __init register_nosave_region_late(unsigned long b, unsigned long e) -{ - __register_nosave_region(b, e, 1); -} +extern void register_nosave_region(unsigned long b, unsigned long e); extern int swsusp_page_is_forbidden(struct page *); extern void swsusp_set_page_free(struct page *); extern void swsusp_unset_page_free(struct page *); @@ -458,7 +450,6 @@ int pfn_is_nosave(unsigned long pfn); int hibernate_quiet_exec(int (*func)(void *data), void *data); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} -static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} static inline int swsusp_page_is_forbidden(struct page *p) { return 0; } static inline void swsusp_set_page_free(struct page *p) {} static inline void swsusp_unset_page_free(struct page *p) {} diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f7a986078213..330d49937692 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -978,8 +978,7 @@ static void memory_bm_recycle(struct memory_bitmap *bm) * Register a range of page frames the contents of which should not be saved * during hibernation (to be used in the early initialization code). */ -void __init __register_nosave_region(unsigned long start_pfn, - unsigned long end_pfn, int use_kmalloc) +void __init register_nosave_region(unsigned long start_pfn, unsigned long end_pfn) { struct nosave_region *region; @@ -995,18 +994,12 @@ void __init __register_nosave_region(unsigned long start_pfn, goto Report; } } - if (use_kmalloc) { - /* During init, this shouldn't fail */ - region = kmalloc(sizeof(struct nosave_region), GFP_KERNEL); - BUG_ON(!region); - } else { - /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), - SMP_CACHE_BYTES); - if (!region) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct nosave_region)); - } + /* This allocation cannot fail */ + region = memblock_alloc(sizeof(struct nosave_region), + SMP_CACHE_BYTES); + if (!region) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(struct nosave_region)); region->start_pfn = start_pfn; region->end_pfn = end_pfn; list_add_tail(®ion->list, &nosave_regions); -- cgit v1.2.3 From ebb7fb1557b1d03b906b668aa2164b51e6b7d19a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 26 Jan 2022 09:19:20 -0800 Subject: xfs, iomap: limit individual ioend chain lengths in writeback Trond Myklebust reported soft lockups in XFS IO completion such as this: watchdog: BUG: soft lockup - CPU#12 stuck for 23s! [kworker/12:1:3106] CPU: 12 PID: 3106 Comm: kworker/12:1 Not tainted 4.18.0-305.10.2.el8_4.x86_64 #1 Workqueue: xfs-conv/md127 xfs_end_io [xfs] RIP: 0010:_raw_spin_unlock_irqrestore+0x11/0x20 Call Trace: wake_up_page_bit+0x8a/0x110 iomap_finish_ioend+0xd7/0x1c0 iomap_finish_ioends+0x7f/0xb0 xfs_end_ioend+0x6b/0x100 [xfs] xfs_end_io+0xb9/0xe0 [xfs] process_one_work+0x1a7/0x360 worker_thread+0x1fa/0x390 kthread+0x116/0x130 ret_from_fork+0x35/0x40 Ioends are processed as an atomic completion unit when all the chained bios in the ioend have completed their IO. Logically contiguous ioends can also be merged and completed as a single, larger unit. Both of these things can be problematic as both the bio chains per ioend and the size of the merged ioends processed as a single completion are both unbound. If we have a large sequential dirty region in the page cache, write_cache_pages() will keep feeding us sequential pages and we will keep mapping them into ioends and bios until we get a dirty page at a non-sequential file offset. These large sequential runs can will result in bio and ioend chaining to optimise the io patterns. The pages iunder writeback are pinned within these chains until the submission chaining is broken, allowing the entire chain to be completed. This can result in huge chains being processed in IO completion context. We get deep bio chaining if we have large contiguous physical extents. We will keep adding pages to the current bio until it is full, then we'll chain a new bio to keep adding pages for writeback. Hence we can build bio chains that map millions of pages and tens of gigabytes of RAM if the page cache contains big enough contiguous dirty file regions. This long bio chain pins those pages until the final bio in the chain completes and the ioend can iterate all the chained bios and complete them. OTOH, if we have a physically fragmented file, we end up submitting one ioend per physical fragment that each have a small bio or bio chain attached to them. We do not chain these at IO submission time, but instead we chain them at completion time based on file offset via iomap_ioend_try_merge(). Hence we can end up with unbound ioend chains being built via completion merging. XFS can then do COW remapping or unwritten extent conversion on that merged chain, which involves walking an extent fragment at a time and running a transaction to modify the physical extent information. IOWs, we merge all the discontiguous ioends together into a contiguous file range, only to then process them individually as discontiguous extents. This extent manipulation is computationally expensive and can run in a tight loop, so merging logically contiguous but physically discontigous ioends gains us nothing except for hiding the fact the fact we broke the ioends up into individual physical extents at submission and then need to loop over those individual physical extents at completion. Hence we need to have mechanisms to limit ioend sizes and to break up completion processing of large merged ioend chains: 1. bio chains per ioend need to be bound in length. Pure overwrites go straight to iomap_finish_ioend() in softirq context with the exact bio chain attached to the ioend by submission. Hence the only way to prevent long holdoffs here is to bound ioend submission sizes because we can't reschedule in softirq context. 2. iomap_finish_ioends() has to handle unbound merged ioend chains correctly. This relies on any one call to iomap_finish_ioend() being bound in runtime so that cond_resched() can be issued regularly as the long ioend chain is processed. i.e. this relies on mechanism #1 to limit individual ioend sizes to work correctly. 3. filesystems have to loop over the merged ioends to process physical extent manipulations. This means they can loop internally, and so we break merging at physical extent boundaries so the filesystem can easily insert reschedule points between individual extent manipulations. Signed-off-by: Dave Chinner Reported-and-tested-by: Trond Myklebust Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/iomap/buffered-io.c | 52 ++++++++++++++++++++++++++++++++++++++++++++++---- fs/xfs/xfs_aops.c | 16 +++++++++++++++- include/linux/iomap.h | 2 ++ 3 files changed, 65 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index c938bbad075e..6c51a75d0be6 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -21,6 +21,8 @@ #include "../internal.h" +#define IOEND_BATCH_SIZE 4096 + /* * Structure allocated for each folio when block size < folio size * to track sub-folio uptodate status and I/O completions. @@ -1039,7 +1041,7 @@ static void iomap_finish_folio_write(struct inode *inode, struct folio *folio, * state, release holds on bios, and finally free up memory. Do not use the * ioend after this. */ -static void +static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error) { struct inode *inode = ioend->io_inode; @@ -1048,6 +1050,7 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) u64 start = bio->bi_iter.bi_sector; loff_t offset = ioend->io_offset; bool quiet = bio_flagged(bio, BIO_QUIET); + u32 folio_count = 0; for (bio = &ioend->io_inline_bio; bio; bio = next) { struct folio_iter fi; @@ -1062,9 +1065,11 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) next = bio->bi_private; /* walk all folios in bio, ending page IO on them */ - bio_for_each_folio_all(fi, bio) + bio_for_each_folio_all(fi, bio) { iomap_finish_folio_write(inode, fi.folio, fi.length, error); + folio_count++; + } bio_put(bio); } /* The ioend has been freed by bio_put() */ @@ -1074,20 +1079,36 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error) "%s: writeback error on inode %lu, offset %lld, sector %llu", inode->i_sb->s_id, inode->i_ino, offset, start); } + return folio_count; } +/* + * Ioend completion routine for merged bios. This can only be called from task + * contexts as merged ioends can be of unbound length. Hence we have to break up + * the writeback completions into manageable chunks to avoid long scheduler + * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get + * good batch processing throughput without creating adverse scheduler latency + * conditions. + */ void iomap_finish_ioends(struct iomap_ioend *ioend, int error) { struct list_head tmp; + u32 completions; + + might_sleep(); list_replace_init(&ioend->io_list, &tmp); - iomap_finish_ioend(ioend, error); + completions = iomap_finish_ioend(ioend, error); while (!list_empty(&tmp)) { + if (completions > IOEND_BATCH_SIZE * 8) { + cond_resched(); + completions = 0; + } ioend = list_first_entry(&tmp, struct iomap_ioend, io_list); list_del_init(&ioend->io_list); - iomap_finish_ioend(ioend, error); + completions += iomap_finish_ioend(ioend, error); } } EXPORT_SYMBOL_GPL(iomap_finish_ioends); @@ -1108,6 +1129,18 @@ iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next) return false; if (ioend->io_offset + ioend->io_size != next->io_offset) return false; + /* + * Do not merge physically discontiguous ioends. The filesystem + * completion functions will have to iterate the physical + * discontiguities even if we merge the ioends at a logical level, so + * we don't gain anything by merging physical discontiguities here. + * + * We cannot use bio->bi_iter.bi_sector here as it is modified during + * submission so does not point to the start sector of the bio at + * completion. + */ + if (ioend->io_sector + (ioend->io_size >> 9) != next->io_sector) + return false; return true; } @@ -1209,8 +1242,10 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, ioend->io_flags = wpc->iomap.flags; ioend->io_inode = inode; ioend->io_size = 0; + ioend->io_folios = 0; ioend->io_offset = offset; ioend->io_bio = bio; + ioend->io_sector = sector; return ioend; } @@ -1251,6 +1286,13 @@ iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t offset, return false; if (sector != bio_end_sector(wpc->ioend->io_bio)) return false; + /* + * Limit ioend bio chain lengths to minimise IO completion latency. This + * also prevents long tight loops ending page writeback on all the + * folios in the ioend. + */ + if (wpc->ioend->io_folios >= IOEND_BATCH_SIZE) + return false; return true; } @@ -1335,6 +1377,8 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc, &submit_list); count++; } + if (count) + wpc->ioend->io_folios++; WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list)); WARN_ON_ONCE(!folio_test_locked(folio)); diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 2705f91bdd0d..9d6a67c7d227 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -136,7 +136,20 @@ done: memalloc_nofs_restore(nofs_flag); } -/* Finish all pending io completions. */ +/* + * Finish all pending IO completions that require transactional modifications. + * + * We try to merge physical and logically contiguous ioends before completion to + * minimise the number of transactions we need to perform during IO completion. + * Both unwritten extent conversion and COW remapping need to iterate and modify + * one physical extent at a time, so we gain nothing by merging physically + * discontiguous extents here. + * + * The ioend chain length that we can be processing here is largely unbound in + * length and we may have to perform significant amounts of work on each ioend + * to complete it. Hence we have to be careful about holding the CPU for too + * long in this loop. + */ void xfs_end_io( struct work_struct *work) @@ -157,6 +170,7 @@ xfs_end_io( list_del_init(&ioend->io_list); iomap_ioend_try_merge(ioend, &tmp); xfs_end_ioend(ioend); + cond_resched(); } } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index b55bd49e55f5..97a3a2edb585 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -263,9 +263,11 @@ struct iomap_ioend { struct list_head io_list; /* next ioend in chain */ u16 io_type; u16 io_flags; /* IOMAP_F_* */ + u32 io_folios; /* folios added to ioend */ struct inode *io_inode; /* file being written to */ size_t io_size; /* size of the extent */ loff_t io_offset; /* offset in the file */ + sector_t io_sector; /* start sector of ioend */ struct bio *io_bio; /* bio being built */ struct bio io_inline_bio; /* MUST BE LAST! */ }; -- cgit v1.2.3 From d7e4f8545b497b3f5687e592f1c355cbaee64c8c Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Wed, 26 Jan 2022 13:04:26 +0800 Subject: pid: Introduce helper task_is_in_init_pid_ns() Currently the kernel uses open code in multiple places to check if a task is in the root PID namespace with the kind of format: if (task_active_pid_ns(current) == &init_pid_ns) do_something(); This patch creates a new helper function, task_is_in_init_pid_ns(), it returns true if a passed task is in the root PID namespace, otherwise returns false. So it will be used to replace open codes. Suggested-by: Suzuki K Poulose Signed-off-by: Leo Yan Reviewed-by: Leon Romanovsky Acked-by: Suzuki K Poulose Acked-by: Balbir Singh Signed-off-by: Jakub Kicinski --- include/linux/pid_namespace.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 7c7e627503d2..07481bb87d4e 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -86,4 +86,9 @@ extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pid_idr_init(void); +static inline bool task_is_in_init_pid_ns(struct task_struct *tsk) +{ + return task_active_pid_ns(tsk) == &init_pid_ns; +} + #endif /* _LINUX_PID_NS_H */ -- cgit v1.2.3 From 364df53c081d93fcfd6b91085ff2650c7f17b3c7 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Thu, 27 Jan 2022 17:13:01 +0800 Subject: net: socket: rename SKB_DROP_REASON_SOCKET_FILTER Rename SKB_DROP_REASON_SOCKET_FILTER, which is used as the reason of skb drop out of socket filter before it's part of a released kernel. It will be used for more protocols than just TCP in future series. Signed-off-by: Menglong Dong Reviewed-by: David Ahern Link: https://lore.kernel.org/all/20220127091308.91401-2-imagedong@tencent.com/ Signed-off-by: Jakub Kicinski --- include/linux/skbuff.h | 2 +- include/trace/events/skb.h | 2 +- net/ipv4/tcp_ipv4.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf11e1fbd69b..8a636e678902 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -318,7 +318,7 @@ enum skb_drop_reason { SKB_DROP_REASON_NO_SOCKET, SKB_DROP_REASON_PKT_TOO_SMALL, SKB_DROP_REASON_TCP_CSUM, - SKB_DROP_REASON_TCP_FILTER, + SKB_DROP_REASON_SOCKET_FILTER, SKB_DROP_REASON_UDP_CSUM, SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 3e042ca2cedb..a8a64b97504d 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -14,7 +14,7 @@ EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ - EM(SKB_DROP_REASON_TCP_FILTER, TCP_FILTER) \ + EM(SKB_DROP_REASON_SOCKET_FILTER, SOCKET_FILTER) \ EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ EMe(SKB_DROP_REASON_MAX, MAX) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b3f34e366b27..938b59636578 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2095,7 +2095,7 @@ process: nf_reset_ct(skb); if (tcp_filter(sk, skb)) { - drop_reason = SKB_DROP_REASON_TCP_FILTER; + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; } th = (const struct tcphdr *)skb->data; -- cgit v1.2.3 From 7f5056b9e7b71149bf11073f00a57fa1ac2921a9 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 26 Jan 2022 15:35:14 -0500 Subject: security, lsm: dentry_init_security() Handle multi LSM registration A ceph user has reported that ceph is crashing with kernel NULL pointer dereference. Following is the backtrace. /proc/version: Linux version 5.16.2-arch1-1 (linux@archlinux) (gcc (GCC) 11.1.0, GNU ld (GNU Binutils) 2.36.1) #1 SMP PREEMPT Thu, 20 Jan 2022 16:18:29 +0000 distro / arch: Arch Linux / x86_64 SELinux is not enabled ceph cluster version: 16.2.7 (dd0603118f56ab514f133c8d2e3adfc983942503) relevant dmesg output: [ 30.947129] BUG: kernel NULL pointer dereference, address: 0000000000000000 [ 30.947206] #PF: supervisor read access in kernel mode [ 30.947258] #PF: error_code(0x0000) - not-present page [ 30.947310] PGD 0 P4D 0 [ 30.947342] Oops: 0000 [#1] PREEMPT SMP PTI [ 30.947388] CPU: 5 PID: 778 Comm: touch Not tainted 5.16.2-arch1-1 #1 86fbf2c313cc37a553d65deb81d98e9dcc2a3659 [ 30.947486] Hardware name: Gigabyte Technology Co., Ltd. B365M DS3H/B365M DS3H, BIOS F5 08/13/2019 [ 30.947569] RIP: 0010:strlen+0x0/0x20 [ 30.947616] Code: b6 07 38 d0 74 16 48 83 c7 01 84 c0 74 05 48 39 f7 75 ec 31 c0 31 d2 89 d6 89 d7 c3 48 89 f8 31 d2 89 d6 89 d7 c3 0 f 1f 40 00 <80> 3f 00 74 12 48 89 f8 48 83 c0 01 80 38 00 75 f7 48 29 f8 31 ff [ 30.947782] RSP: 0018:ffffa4ed80ffbbb8 EFLAGS: 00010246 [ 30.947836] RAX: 0000000000000000 RBX: ffffa4ed80ffbc60 RCX: 0000000000000000 [ 30.947904] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 [ 30.947971] RBP: ffff94b0d15c0ae0 R08: 0000000000000000 R09: 0000000000000000 [ 30.948040] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 [ 30.948106] R13: 0000000000000001 R14: ffffa4ed80ffbc60 R15: 0000000000000000 [ 30.948174] FS: 00007fc7520f0740(0000) GS:ffff94b7ced40000(0000) knlGS:0000000000000000 [ 30.948252] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 30.948308] CR2: 0000000000000000 CR3: 0000000104a40001 CR4: 00000000003706e0 [ 30.948376] Call Trace: [ 30.948404] [ 30.948431] ceph_security_init_secctx+0x7b/0x240 [ceph 49f9c4b9bf5be8760f19f1747e26da33920bce4b] [ 30.948582] ceph_atomic_open+0x51e/0x8a0 [ceph 49f9c4b9bf5be8760f19f1747e26da33920bce4b] [ 30.948708] ? get_cached_acl+0x4d/0xa0 [ 30.948759] path_openat+0x60d/0x1030 [ 30.948809] do_filp_open+0xa5/0x150 [ 30.948859] do_sys_openat2+0xc4/0x190 [ 30.948904] __x64_sys_openat+0x53/0xa0 [ 30.948948] do_syscall_64+0x5c/0x90 [ 30.948989] ? exc_page_fault+0x72/0x180 [ 30.949034] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 30.949091] RIP: 0033:0x7fc7521e25bb [ 30.950849] Code: 25 00 00 41 00 3d 00 00 41 00 74 4b 64 8b 04 25 18 00 00 00 85 c0 75 67 44 89 e2 48 89 ee bf 9c ff ff ff b8 01 01 0 0 00 0f 05 <48> 3d 00 f0 ff ff 0f 87 91 00 00 00 48 8b 54 24 28 64 48 2b 14 25 Core of the problem is that ceph checks for return code from security_dentry_init_security() and if return code is 0, it assumes everything is fine and continues to call strlen(name), which crashes. Typically SELinux LSM returns 0 and sets name to "security.selinux" and it is not a problem. Or if selinux is not compiled in or disabled, it returns -EOPNOTSUP and ceph deals with it. But somehow in this configuration, 0 is being returned and "name" is not being initialized and that's creating the problem. Our suspicion is that BPF LSM is registering a hook for dentry_init_security() and returns hook default of 0. LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry,...) I have not been able to reproduce it just by doing CONFIG_BPF_LSM=y. Stephen has tested the patch though and confirms it solves the problem for him. dentry_init_security() is written in such a way that it expects only one LSM to register the hook. Atleast that's the expectation with current code. If another LSM returns a hook and returns default, it will simply return 0 as of now and that will break ceph. Hence, suggestion is that change semantics of this hook a bit. If there are no LSMs or no LSM is taking ownership and initializing security context, then return -EOPNOTSUP. Also allow at max one LSM to initialize security context. This hook can't deal with multiple LSMs trying to init security context. This patch implements this new behavior. Reported-by: Stephen Muth Tested-by: Stephen Muth Suggested-by: Casey Schaufler Acked-by: Casey Schaufler Reviewed-by: Serge Hallyn Cc: Jeff Layton Cc: Christian Brauner Cc: Paul Moore Cc: # 5.16.0 Signed-off-by: Vivek Goyal Reviewed-by: Jeff Layton Acked-by: Paul Moore Acked-by: Christian Brauner Signed-off-by: James Morris --- include/linux/lsm_hook_defs.h | 2 +- security/security.c | 15 +++++++++++++-- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index df8de62f4710..f0c7b352340a 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -82,7 +82,7 @@ LSM_HOOK(int, 0, sb_add_mnt_opt, const char *option, const char *val, int len, void **mnt_opts) LSM_HOOK(int, 0, move_mount, const struct path *from_path, const struct path *to_path) -LSM_HOOK(int, 0, dentry_init_security, struct dentry *dentry, +LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry, int mode, const struct qstr *name, const char **xattr_name, void **ctx, u32 *ctxlen) LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode, diff --git a/security/security.c b/security/security.c index c88167a414b4..64abdfb20bc2 100644 --- a/security/security.c +++ b/security/security.c @@ -1056,8 +1056,19 @@ int security_dentry_init_security(struct dentry *dentry, int mode, const char **xattr_name, void **ctx, u32 *ctxlen) { - return call_int_hook(dentry_init_security, -EOPNOTSUPP, dentry, mode, - name, xattr_name, ctx, ctxlen); + struct security_hook_list *hp; + int rc; + + /* + * Only one module will provide a security context. + */ + hlist_for_each_entry(hp, &security_hook_heads.dentry_init_security, list) { + rc = hp->hook.dentry_init_security(dentry, mode, name, + xattr_name, ctx, ctxlen); + if (rc != LSM_RET_DEFAULT(dentry_init_security)) + return rc; + } + return LSM_RET_DEFAULT(dentry_init_security); } EXPORT_SYMBOL(security_dentry_init_security); -- cgit v1.2.3 From e45c47d1f94e0cc7b6b079fdb4bcce2995e2adc4 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Fri, 28 Jan 2022 10:58:39 -0500 Subject: block: add bio_start_io_acct_time() to control start_time bio_start_io_acct_time() interface is like bio_start_io_acct() that allows start_time to be passed in. This gives drivers the ability to defer starting accounting until after IO is issued (but possibily not entirely due to bio splitting). Reviewed-by: Christoph Hellwig Signed-off-by: Mike Snitzer Link: https://lore.kernel.org/r/20220128155841.39644-2-snitzer@redhat.com Signed-off-by: Jens Axboe --- block/blk-core.c | 25 +++++++++++++++++++------ include/linux/blkdev.h | 1 + 2 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 97f8bc8d3a79..d93e3bb9a769 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1061,20 +1061,32 @@ again: } static unsigned long __part_start_io_acct(struct block_device *part, - unsigned int sectors, unsigned int op) + unsigned int sectors, unsigned int op, + unsigned long start_time) { const int sgrp = op_stat_group(op); - unsigned long now = READ_ONCE(jiffies); part_stat_lock(); - update_io_ticks(part, now, false); + update_io_ticks(part, start_time, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); - return now; + return start_time; +} + +/** + * bio_start_io_acct_time - start I/O accounting for bio based drivers + * @bio: bio to start account for + * @start_time: start time that should be passed back to bio_end_io_acct(). + */ +void bio_start_io_acct_time(struct bio *bio, unsigned long start_time) +{ + __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), start_time); } +EXPORT_SYMBOL_GPL(bio_start_io_acct_time); /** * bio_start_io_acct - start I/O accounting for bio based drivers @@ -1084,14 +1096,15 @@ static unsigned long __part_start_io_acct(struct block_device *part, */ unsigned long bio_start_io_acct(struct bio *bio) { - return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), bio_op(bio)); + return __part_start_io_acct(bio->bi_bdev, bio_sectors(bio), + bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { - return __part_start_io_acct(disk->part0, sectors, op); + return __part_start_io_acct(disk->part0, sectors, op, jiffies); } EXPORT_SYMBOL(disk_start_io_acct); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9c95df26fc26..f35aea98bc35 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1258,6 +1258,7 @@ unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time); +void bio_start_io_acct_time(struct bio *bio, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev); -- cgit v1.2.3 From 6cb917411e028dcb66ce8f5db1b47361b78d7d3f Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Sat, 29 Jan 2022 13:40:52 -0800 Subject: include/linux/sysctl.h: fix register_sysctl_mount_point() return type The CONFIG_SYSCTL=n stub returns the wrong type. Fixes: ee9efac48a082 ("sysctl: add helper to register a sysctl mount point") Reported-by: kernel test robot Acked-by: Luis Chamberlain Cc: Tong Zhang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 180adf7da785..6353d6db69b2 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -265,7 +265,7 @@ static inline struct ctl_table_header *register_sysctl_table(struct ctl_table * return NULL; } -static inline struct sysctl_header *register_sysctl_mount_point(const char *path) +static inline struct ctl_table_header *register_sysctl_mount_point(const char *path) { return NULL; } -- cgit v1.2.3 From 536f4217ced62b671bd759f6b549621a5654a70f Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Sat, 29 Jan 2022 13:41:04 -0800 Subject: mm: page->mapping folio->mapping should have the same offset As with the other members of folio, the offset of page->mapping and folio->mapping must be the same. The compile-time check was inadvertently removed during development. Add it back. [willy@infradead.org: changelog redo] Link: https://lkml.kernel.org/r/20220104011734.21714-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Reviewed-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 9db36dc5d4cf..5140e5feb486 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -261,6 +261,7 @@ static_assert(sizeof(struct page) == sizeof(struct folio)); static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl)) FOLIO_MATCH(flags, flags); FOLIO_MATCH(lru, lru); +FOLIO_MATCH(mapping, mapping); FOLIO_MATCH(compound_head, lru); FOLIO_MATCH(index, index); FOLIO_MATCH(private, private); -- cgit v1.2.3 From 27fe73394a1c6d0b07fa4d95f1bca116d1cc66e9 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Sat, 29 Jan 2022 13:41:14 -0800 Subject: mm, kasan: use compare-exchange operation to set KASAN page tag It has been reported that the tag setting operation on newly-allocated pages can cause the page flags to be corrupted when performed concurrently with other flag updates as a result of the use of non-atomic operations. Fix the problem by using a compare-exchange loop to update the tag. Link: https://lkml.kernel.org/r/20220120020148.1632253-1-pcc@google.com Link: https://linux-review.googlesource.com/id/I456b24a2b9067d93968d43b4bb3351c0cec63101 Fixes: 2813b9c02962 ("kasan, mm, arm64: tag non slab memory allocated via pagealloc") Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Cc: Peter Zijlstra Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index e1a84b1e6787..213cc569b192 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1506,11 +1506,18 @@ static inline u8 page_kasan_tag(const struct page *page) static inline void page_kasan_tag_set(struct page *page, u8 tag) { - if (kasan_enabled()) { - tag ^= 0xff; - page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); - page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; - } + unsigned long old_flags, flags; + + if (!kasan_enabled()) + return; + + tag ^= 0xff; + old_flags = READ_ONCE(page->flags); + do { + flags = old_flags; + flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); + flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; + } while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags))); } static inline void page_kasan_tag_reset(struct page *page) -- cgit v1.2.3 From 51e50fbd3efc6064c30ed73a5e009018b36e290a Mon Sep 17 00:00:00 2001 From: Suren Baghdasaryan Date: Sat, 29 Jan 2022 13:41:17 -0800 Subject: psi: fix "no previous prototype" warnings when CONFIG_CGROUPS=n When CONFIG_CGROUPS is disabled psi code generates the following warnings: kernel/sched/psi.c:1112:21: warning: no previous prototype for 'psi_trigger_create' [-Wmissing-prototypes] 1112 | struct psi_trigger *psi_trigger_create(struct psi_group *group, | ^~~~~~~~~~~~~~~~~~ kernel/sched/psi.c:1182:6: warning: no previous prototype for 'psi_trigger_destroy' [-Wmissing-prototypes] 1182 | void psi_trigger_destroy(struct psi_trigger *t) | ^~~~~~~~~~~~~~~~~~~ kernel/sched/psi.c:1249:10: warning: no previous prototype for 'psi_trigger_poll' [-Wmissing-prototypes] 1249 | __poll_t psi_trigger_poll(void **trigger_ptr, | ^~~~~~~~~~~~~~~~ Change the declarations of these functions in the header to provide the prototypes even when they are unused. Link: https://lkml.kernel.org/r/20220119223940.787748-2-surenb@google.com Fixes: 0e94682b73bf ("psi: introduce psi monitor") Signed-off-by: Suren Baghdasaryan Reported-by: kernel test robot Acked-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/psi.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/psi.h b/include/linux/psi.h index f8ce53bfdb2a..7f7d1d88c3bb 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -25,18 +25,17 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); - -#ifdef CONFIG_CGROUPS -int psi_cgroup_alloc(struct cgroup *cgrp); -void psi_cgroup_free(struct cgroup *cgrp); -void cgroup_move_task(struct task_struct *p, struct css_set *to); - struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, size_t nbytes, enum psi_res res); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, poll_table *wait); + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgrp); +void psi_cgroup_free(struct cgroup *cgrp); +void cgroup_move_task(struct task_struct *p, struct css_set *to); #endif #else /* CONFIG_PSI */ -- cgit v1.2.3 From ef9989afda73332df566852d6e9ca695c05f10ce Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 1 Feb 2022 13:29:22 +0000 Subject: kvm: add guest_state_{enter,exit}_irqoff() When transitioning to/from guest mode, it is necessary to inform lockdep, tracing, and RCU in a specific order, similar to the requirements for transitions to/from user mode. Additionally, it is necessary to perform vtime accounting for a window around running the guest, with RCU enabled, such that timer interrupts taken from the guest can be accounted as guest time. Most architectures don't handle all the necessary pieces, and a have a number of common bugs, including unsafe usage of RCU during the window between guest_enter() and guest_exit(). On x86, this was dealt with across commits: 87fa7f3e98a1310e ("x86/kvm: Move context tracking where it belongs") 0642391e2139a2c1 ("x86/kvm/vmx: Add hardirq tracing to guest enter/exit") 9fc975e9efd03e57 ("x86/kvm/svm: Add hardirq tracing on guest enter/exit") 3ebccdf373c21d86 ("x86/kvm/vmx: Move guest enter/exit into .noinstr.text") 135961e0a7d555fc ("x86/kvm/svm: Move guest enter/exit into .noinstr.text") 160457140187c5fb ("KVM: x86: Defer vtime accounting 'til after IRQ handling") bc908e091b326467 ("KVM: x86: Consolidate guest enter/exit logic to common helpers") ... but those fixes are specific to x86, and as the resulting logic (while correct) is split across generic helper functions and x86-specific helper functions, it is difficult to see that the entry/exit accounting is balanced. This patch adds generic helpers which architectures can use to handle guest entry/exit consistently and correctly. The guest_{enter,exit}() helpers are split into guest_timing_{enter,exit}() to perform vtime accounting, and guest_context_{enter,exit}() to perform the necessary context tracking and RCU management. The existing guest_{enter,exit}() heleprs are left as wrappers of these. Atop this, new guest_state_enter_irqoff() and guest_state_exit_irqoff() helpers are added to handle the ordering of lockdep, tracing, and RCU manageent. These are inteneded to mirror exit_to_user_mode() and enter_from_user_mode(). Subsequent patches will migrate architectures over to the new helpers, following a sequence: guest_timing_enter_irqoff(); guest_state_enter_irqoff(); < run the vcpu > guest_state_exit_irqoff(); < take any pending IRQs > guest_timing_exit_irqoff(); This sequences handles all of the above correctly, and more clearly balances the entry and exit portions, making it easier to understand. The existing helpers are marked as deprecated, and will be removed once all architectures have been converted. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Marc Zyngier Reviewed-by: Paolo Bonzini Reviewed-by: Nicolas Saenz Julienne Message-Id: <20220201132926.3301912-2-mark.rutland@arm.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 112 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 109 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index f079820f52b5..b3810976a27f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -29,7 +29,9 @@ #include #include #include +#include #include +#include #include #include #include @@ -368,8 +370,11 @@ struct kvm_vcpu { u64 last_used_slot_gen; }; -/* must be called with irqs disabled */ -static __always_inline void guest_enter_irqoff(void) +/* + * Start accounting time towards a guest. + * Must be called before entering guest context. + */ +static __always_inline void guest_timing_enter_irqoff(void) { /* * This is running in ioctl context so its safe to assume that it's the @@ -378,7 +383,18 @@ static __always_inline void guest_enter_irqoff(void) instrumentation_begin(); vtime_account_guest_enter(); instrumentation_end(); +} +/* + * Enter guest context and enter an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_enter_irqoff(void) +{ /* * KVM does not hold any references to rcu protected data when it * switches CPU into a guest mode. In fact switching to a guest mode @@ -394,16 +410,79 @@ static __always_inline void guest_enter_irqoff(void) } } -static __always_inline void guest_exit_irqoff(void) +/* + * Deprecated. Architectures should move to guest_timing_enter_irqoff() and + * guest_state_enter_irqoff(). + */ +static __always_inline void guest_enter_irqoff(void) +{ + guest_timing_enter_irqoff(); + guest_context_enter_irqoff(); +} + +/** + * guest_state_enter_irqoff - Fixup state when entering a guest + * + * Entry to a guest will enable interrupts, but the kernel state is interrupts + * disabled when this is invoked. Also tell RCU about it. + * + * 1) Trace interrupts on state + * 2) Invoke context tracking if enabled to adjust RCU state + * 3) Tell lockdep that interrupts are enabled + * + * Invoked from architecture specific code before entering a guest. + * Must be called with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_enter_irqoff() before this. + * + * Note: this is analogous to exit_to_user_mode(). + */ +static __always_inline void guest_state_enter_irqoff(void) +{ + instrumentation_begin(); + trace_hardirqs_on_prepare(); + lockdep_hardirqs_on_prepare(CALLER_ADDR0); + instrumentation_end(); + + guest_context_enter_irqoff(); + lockdep_hardirqs_on(CALLER_ADDR0); +} + +/* + * Exit guest context and exit an RCU extended quiescent state. + * + * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is + * unsafe to use any code which may directly or indirectly use RCU, tracing + * (including IRQ flag tracing), or lockdep. All code in this period must be + * non-instrumentable. + */ +static __always_inline void guest_context_exit_irqoff(void) { context_tracking_guest_exit(); +} +/* + * Stop accounting time towards a guest. + * Must be called after exiting guest context. + */ +static __always_inline void guest_timing_exit_irqoff(void) +{ instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ vtime_account_guest_exit(); instrumentation_end(); } +/* + * Deprecated. Architectures should move to guest_state_exit_irqoff() and + * guest_timing_exit_irqoff(). + */ +static __always_inline void guest_exit_irqoff(void) +{ + guest_context_exit_irqoff(); + guest_timing_exit_irqoff(); +} + static inline void guest_exit(void) { unsigned long flags; @@ -413,6 +492,33 @@ static inline void guest_exit(void) local_irq_restore(flags); } +/** + * guest_state_exit_irqoff - Establish state when returning from guest mode + * + * Entry from a guest disables interrupts, but guest mode is traced as + * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. + * + * 1) Tell lockdep that interrupts are disabled + * 2) Invoke context tracking if enabled to reactivate RCU + * 3) Trace interrupts off state + * + * Invoked from architecture specific code after exiting a guest. + * Must be invoked with interrupts disabled and the caller must be + * non-instrumentable. + * The caller has to invoke guest_timing_exit_irqoff() after this. + * + * Note: this is analogous to enter_from_user_mode(). + */ +static __always_inline void guest_state_exit_irqoff(void) +{ + lockdep_hardirqs_off(CALLER_ADDR0); + guest_context_exit_irqoff(); + + instrumentation_begin(); + trace_hardirqs_off_finish(); + instrumentation_end(); +} + static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu) { /* -- cgit v1.2.3 From bee9f65523218e3baeeecde9295c8fbe9bc08e0a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 27 Jan 2022 16:02:50 +0000 Subject: netfs, cachefiles: Add a method to query presence of data in the cache Add a netfs_cache_ops method by which a network filesystem can ask the cache about what data it has available and where so that it can make a multipage read more efficient. Signed-off-by: David Howells cc: linux-cachefs@redhat.com Acked-by: Jeff Layton Reviewed-by: Rohith Surabattula Signed-off-by: Steve French --- Documentation/filesystems/netfs_library.rst | 16 ++++++++ fs/cachefiles/io.c | 59 +++++++++++++++++++++++++++++ include/linux/netfs.h | 7 ++++ 3 files changed, 82 insertions(+) (limited to 'include/linux') diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst index 136f8da3d0e2..4f373a8ec47b 100644 --- a/Documentation/filesystems/netfs_library.rst +++ b/Documentation/filesystems/netfs_library.rst @@ -462,6 +462,10 @@ operation table looks like the following:: struct iov_iter *iter, netfs_io_terminated_t term_func, void *term_func_priv); + + int (*query_occupancy)(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len); }; With a termination handler function pointer:: @@ -536,6 +540,18 @@ The methods defined in the table are: indicating whether the termination is definitely happening in the caller's context. + * ``query_occupancy()`` + + [Required] Called to find out where the next piece of data is within a + particular region of the cache. The start and length of the region to be + queried are passed in, along with the granularity to which the answer needs + to be aligned. The function passes back the start and length of the data, + if any, available within that region. Note that there may be a hole at the + front. + + It returns 0 if some data was found, -ENODATA if there was no usable data + within the region or -ENOBUFS if there is no caching on this file. + Note that these methods are passed a pointer to the cache resource structure, not the read request structure as they could be used in other situations where there isn't a read request structure as well, such as writing dirty data to the diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c index 04eb52736990..753986ea1583 100644 --- a/fs/cachefiles/io.c +++ b/fs/cachefiles/io.c @@ -191,6 +191,64 @@ presubmission_error: return ret; } +/* + * Query the occupancy of the cache in a region, returning where the next chunk + * of data starts and how long it is. + */ +static int cachefiles_query_occupancy(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len) +{ + struct cachefiles_object *object; + struct file *file; + loff_t off, off2; + + *_data_start = -1; + *_data_len = 0; + + if (!fscache_wait_for_operation(cres, FSCACHE_WANT_READ)) + return -ENOBUFS; + + object = cachefiles_cres_object(cres); + file = cachefiles_cres_file(cres); + granularity = max_t(size_t, object->volume->cache->bsize, granularity); + + _enter("%pD,%li,%llx,%zx/%llx", + file, file_inode(file)->i_ino, start, len, + i_size_read(file_inode(file))); + + off = cachefiles_inject_read_error(); + if (off == 0) + off = vfs_llseek(file, start, SEEK_DATA); + if (off == -ENXIO) + return -ENODATA; /* Beyond EOF */ + if (off < 0 && off >= (loff_t)-MAX_ERRNO) + return -ENOBUFS; /* Error. */ + if (round_up(off, granularity) >= start + len) + return -ENODATA; /* No data in range */ + + off2 = cachefiles_inject_read_error(); + if (off2 == 0) + off2 = vfs_llseek(file, off, SEEK_HOLE); + if (off2 == -ENXIO) + return -ENODATA; /* Beyond EOF */ + if (off2 < 0 && off2 >= (loff_t)-MAX_ERRNO) + return -ENOBUFS; /* Error. */ + + /* Round away partial blocks */ + off = round_up(off, granularity); + off2 = round_down(off2, granularity); + if (off2 <= off) + return -ENODATA; + + *_data_start = off; + if (off2 > start + len) + *_data_len = len; + else + *_data_len = off2 - off; + return 0; +} + /* * Handle completion of a write to the cache. */ @@ -545,6 +603,7 @@ static const struct netfs_cache_ops cachefiles_netfs_cache_ops = { .write = cachefiles_write, .prepare_read = cachefiles_prepare_read, .prepare_write = cachefiles_prepare_write, + .query_occupancy = cachefiles_query_occupancy, }; /* diff --git a/include/linux/netfs.h b/include/linux/netfs.h index b46c39d98bbd..614f22213e21 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -244,6 +244,13 @@ struct netfs_cache_ops { int (*prepare_write)(struct netfs_cache_resources *cres, loff_t *_start, size_t *_len, loff_t i_size, bool no_space_allocated_yet); + + /* Query the occupancy of the cache in a region, returning where the + * next chunk of data starts and how long it is. + */ + int (*query_occupancy)(struct netfs_cache_resources *cres, + loff_t start, size_t len, size_t granularity, + loff_t *_data_start, size_t *_data_len); }; struct readahead_control; -- cgit v1.2.3 From 6d5c900eb64107001e91e1f46bddc254dded8a59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 24 Jan 2022 09:22:41 -0800 Subject: net/mlx5e: Use struct_group() for memcpy() region In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally writing across neighboring fields. Use struct_group() in struct vlan_ethhdr around members h_dest and h_source, so they can be referenced together. This will allow memcpy() and sizeof() to more easily reason about sizes, improve readability, and avoid future warnings about writing beyond the end of h_dest. "pahole" shows no size nor member offset changes to struct vlan_ethhdr. "objdump -d" shows no object code changes. Fixes: 34802a42b352 ("net/mlx5e: Do not modify the TX SKB") Signed-off-by: Kees Cook Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 2 +- include/linux/if_vlan.h | 6 ++++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 7fd33b356cc8..ee7ecb88adc1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -208,7 +208,7 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs) int cpy1_sz = 2 * ETH_ALEN; int cpy2_sz = ihs - cpy1_sz; - memcpy(vhdr, skb->data, cpy1_sz); + memcpy(&vhdr->addrs, skb->data, cpy1_sz); vhdr->h_vlan_proto = skb->vlan_proto; vhdr->h_vlan_TCI = cpu_to_be16(skb_vlan_tag_get(skb)); memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz); diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 8420fe504927..2be4dd7e90a9 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -46,8 +46,10 @@ struct vlan_hdr { * @h_vlan_encapsulated_proto: packet type ID or len */ struct vlan_ethhdr { - unsigned char h_dest[ETH_ALEN]; - unsigned char h_source[ETH_ALEN]; + struct_group(addrs, + unsigned char h_dest[ETH_ALEN]; + unsigned char h_source[ETH_ALEN]; + ); __be16 h_vlan_proto; __be16 h_vlan_TCI; __be16 h_vlan_encapsulated_proto; -- cgit v1.2.3 From 1148836fd3226c20de841084aba24184d4fbbe77 Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Wed, 2 Feb 2022 14:55:29 +0100 Subject: Revert "fbdev: Garbage collect fbdev scrolling acceleration, part 1 (from TODO list)" This reverts commit b3ec8cdf457e5e63d396fe1346cc788cf7c1b578. Revert the second (of 2) commits which disabled scrolling acceleration in fbcon/fbdev. It introduced a regression for fbdev-supported graphic cards because of the performance penalty by doing screen scrolling by software instead of using the existing graphic card 2D hardware acceleration. Console scrolling acceleration was disabled by dropping code which checked at runtime the driver hardware capabilities for the BINFO_HWACCEL_COPYAREA or FBINFO_HWACCEL_FILLRECT flags and if set, it enabled scrollmode SCROLL_MOVE which uses hardware acceleration to move screen contents. After dropping those checks scrollmode was hard-wired to SCROLL_REDRAW instead, which forces all graphic cards to redraw every character at the new screen position when scrolling. This change effectively disabled all hardware-based scrolling acceleration for ALL drivers, because now all kind of 2D hardware acceleration (bitblt, fillrect) in the drivers isn't used any longer. The original commit message mentions that only 3 DRM drivers (nouveau, omapdrm and gma500) used hardware acceleration in the past and thus code for checking and using scrolling acceleration is obsolete. This statement is NOT TRUE, because beside the DRM drivers there are around 35 other fbdev drivers which depend on fbdev/fbcon and still provide hardware acceleration for fbdev/fbcon. The original commit message also states that syzbot found lots of bugs in fbcon and thus it's "often the solution to just delete code and remove features". This is true, and the bugs - which actually affected all users of fbcon, including DRM - were fixed, or code was dropped like e.g. the support for software scrollback in vgacon (commit 973c096f6a85). So to further analyze which bugs were found by syzbot, I've looked through all patches in drivers/video which were tagged with syzbot or syzkaller back to year 2005. The vast majority fixed the reported issues on a higher level, e.g. when screen is to be resized, or when font size is to be changed. The few ones which touched driver code fixed a real driver bug, e.g. by adding a check. But NONE of those patches touched code of either the SCROLL_MOVE or the SCROLL_REDRAW case. That means, there was no real reason why SCROLL_MOVE had to be ripped-out and just SCROLL_REDRAW had to be used instead. The only reason I can imagine so far was that SCROLL_MOVE wasn't used by DRM and as such it was assumed that it could go away. That argument completely missed the fact that SCROLL_MOVE is still heavily used by fbdev (non-DRM) drivers. Some people mention that using memcpy() instead of the hardware acceleration is pretty much the same speed. But that's not true, at least not for older graphic cards and machines where we see speed decreases by factor 10 and more and thus this change leads to console responsiveness way worse than before. That's why the original commit is to be reverted. By reverting we reintroduce hardware-based scrolling acceleration and fix the performance regression for fbdev drivers. There isn't any impact on DRM when reverting those patches. Signed-off-by: Helge Deller Acked-by: Geert Uytterhoeven Acked-by: Sven Schnelle Cc: stable@vger.kernel.org # v5.16+ Signed-off-by: Helge Deller Signed-off-by: Daniel Vetter Link: https://patchwork.freedesktop.org/patch/msgid/20220202135531.92183-2-deller@gmx.de --- Documentation/gpu/todo.rst | 13 +- drivers/video/fbdev/core/bitblit.c | 16 + drivers/video/fbdev/core/fbcon.c | 509 ++++++++++++++++++++++++++++++-- drivers/video/fbdev/core/fbcon.h | 59 ++++ drivers/video/fbdev/core/fbcon_ccw.c | 28 +- drivers/video/fbdev/core/fbcon_cw.c | 28 +- drivers/video/fbdev/core/fbcon_rotate.h | 9 + drivers/video/fbdev/core/fbcon_ud.c | 37 ++- drivers/video/fbdev/core/tileblit.c | 16 + drivers/video/fbdev/skeletonfb.c | 12 +- include/linux/fb.h | 2 +- 11 files changed, 678 insertions(+), 51 deletions(-) (limited to 'include/linux') diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst index da138dd39883..29506815d24a 100644 --- a/Documentation/gpu/todo.rst +++ b/Documentation/gpu/todo.rst @@ -303,19 +303,16 @@ Level: Advanced Garbage collect fbdev scrolling acceleration -------------------------------------------- -Scroll acceleration has been disabled in fbcon. Now it works as the old -SCROLL_REDRAW mode. A ton of code was removed in fbcon.c and the hook bmove was -removed from fbcon_ops. -Remaining tasks: +Scroll acceleration is disabled in fbcon by hard-wiring p->scrollmode = +SCROLL_REDRAW. There's a ton of code this will allow us to remove: -- a bunch of the hooks in fbcon_ops could be removed or simplified by calling +- lots of code in fbcon.c + +- a bunch of the hooks in fbcon_ops, maybe the remaining hooks could be called directly instead of the function table (with a switch on p->rotate) - fb_copyarea is unused after this, and can be deleted from all drivers -- after that, fb_copyarea can be deleted from fb_ops in include/linux/fb.h as - well as cfb_copyarea - Note that not all acceleration code can be deleted, since clearing and cursor support is still accelerated, which might be good candidates for further deletion projects. diff --git a/drivers/video/fbdev/core/bitblit.c b/drivers/video/fbdev/core/bitblit.c index 01fae2c96965..f98e8f298bc1 100644 --- a/drivers/video/fbdev/core/bitblit.c +++ b/drivers/video/fbdev/core/bitblit.c @@ -43,6 +43,21 @@ static void update_attr(u8 *dst, u8 *src, int attribute, } } +static void bit_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fb_copyarea area; + + area.sx = sx * vc->vc_font.width; + area.sy = sy * vc->vc_font.height; + area.dx = dx * vc->vc_font.width; + area.dy = dy * vc->vc_font.height; + area.height = height * vc->vc_font.height; + area.width = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void bit_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -378,6 +393,7 @@ static int bit_update_start(struct fb_info *info) void fbcon_set_bitops(struct fbcon_ops *ops) { + ops->bmove = bit_bmove; ops->clear = bit_clear; ops->putcs = bit_putcs; ops->clear_margins = bit_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 99ecd9a6d844..fc34caddf9cf 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -173,6 +173,8 @@ static void fbcon_putcs(struct vc_data *vc, const unsigned short *s, int count, int ypos, int xpos); static void fbcon_clear_margins(struct vc_data *vc, int bottom_only); static void fbcon_cursor(struct vc_data *vc, int mode); +static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, + int height, int width); static int fbcon_switch(struct vc_data *vc); static int fbcon_blank(struct vc_data *vc, int blank, int mode_switch); static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); @@ -180,8 +182,16 @@ static void fbcon_set_palette(struct vc_data *vc, const unsigned char *table); /* * Internal routines */ +static __inline__ void ywrap_up(struct vc_data *vc, int count); +static __inline__ void ywrap_down(struct vc_data *vc, int count); +static __inline__ void ypan_up(struct vc_data *vc, int count); +static __inline__ void ypan_down(struct vc_data *vc, int count); +static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, + int dy, int dx, int height, int width, u_int y_break); static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, int unit); +static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, + int line, int count, int dy); static void fbcon_modechanged(struct fb_info *info); static void fbcon_set_all_vcs(struct fb_info *info); static void fbcon_start(void); @@ -1125,6 +1135,14 @@ static void fbcon_init(struct vc_data *vc, int init) ops->graphics = 0; + /* + * No more hw acceleration for fbcon. + * + * FIXME: Garbage collect all the now dead code after sufficient time + * has passed. + */ + p->scrollmode = SCROLL_REDRAW; + /* * ++guenther: console.c:vc_allocate() relies on initializing * vc_{cols,rows}, but we must not set those if we are only @@ -1211,13 +1229,14 @@ finished: * This system is now divided into two levels because of complications * caused by hardware scrolling. Top level functions: * - * fbcon_clear(), fbcon_putc(), fbcon_clear_margins() + * fbcon_bmove(), fbcon_clear(), fbcon_putc(), fbcon_clear_margins() * * handles y values in range [0, scr_height-1] that correspond to real * screen positions. y_wrap shift means that first line of bitmap may be * anywhere on this display. These functions convert lineoffsets to * bitmap offsets and deal with the wrap-around case by splitting blits. * + * fbcon_bmove_physical_8() -- These functions fast implementations * fbcon_clear_physical_8() -- of original fbcon_XXX fns. * fbcon_putc_physical_8() -- (font width != 8) may be added later * @@ -1390,6 +1409,224 @@ static void fbcon_set_disp(struct fb_info *info, struct fb_var_screeninfo *var, } } +static __inline__ void ywrap_up(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll += count; + if (p->yscroll >= p->vrows) /* Deal with wrap */ + p->yscroll -= p->vrows; + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode |= FB_VMODE_YWRAP; + ops->update_start(info); + scrollback_max += count; + if (scrollback_max > scrollback_phys_max) + scrollback_max = scrollback_phys_max; + scrollback_current = 0; +} + +static __inline__ void ywrap_down(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll -= count; + if (p->yscroll < 0) /* Deal with wrap */ + p->yscroll += p->vrows; + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode |= FB_VMODE_YWRAP; + ops->update_start(info); + scrollback_max -= count; + if (scrollback_max < 0) + scrollback_max = 0; + scrollback_current = 0; +} + +static __inline__ void ypan_up(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_display *p = &fb_display[vc->vc_num]; + struct fbcon_ops *ops = info->fbcon_par; + + p->yscroll += count; + if (p->yscroll > p->vrows - vc->vc_rows) { + ops->bmove(vc, info, p->vrows - vc->vc_rows, + 0, 0, 0, vc->vc_rows, vc->vc_cols); + p->yscroll -= p->vrows - vc->vc_rows; + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max += count; + if (scrollback_max > scrollback_phys_max) + scrollback_max = scrollback_phys_max; + scrollback_current = 0; +} + +static __inline__ void ypan_up_redraw(struct vc_data *vc, int t, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll += count; + + if (p->yscroll > p->vrows - vc->vc_rows) { + p->yscroll -= p->vrows - vc->vc_rows; + fbcon_redraw_move(vc, p, t + count, vc->vc_rows - count, t); + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max += count; + if (scrollback_max > scrollback_phys_max) + scrollback_max = scrollback_phys_max; + scrollback_current = 0; +} + +static __inline__ void ypan_down(struct vc_data *vc, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_display *p = &fb_display[vc->vc_num]; + struct fbcon_ops *ops = info->fbcon_par; + + p->yscroll -= count; + if (p->yscroll < 0) { + ops->bmove(vc, info, 0, 0, p->vrows - vc->vc_rows, + 0, vc->vc_rows, vc->vc_cols); + p->yscroll += p->vrows - vc->vc_rows; + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max -= count; + if (scrollback_max < 0) + scrollback_max = 0; + scrollback_current = 0; +} + +static __inline__ void ypan_down_redraw(struct vc_data *vc, int t, int count) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + p->yscroll -= count; + + if (p->yscroll < 0) { + p->yscroll += p->vrows - vc->vc_rows; + fbcon_redraw_move(vc, p, t, vc->vc_rows - count, t + count); + } + + ops->var.xoffset = 0; + ops->var.yoffset = p->yscroll * vc->vc_font.height; + ops->var.vmode &= ~FB_VMODE_YWRAP; + ops->update_start(info); + fbcon_clear_margins(vc, 1); + scrollback_max -= count; + if (scrollback_max < 0) + scrollback_max = 0; + scrollback_current = 0; +} + +static void fbcon_redraw_move(struct vc_data *vc, struct fbcon_display *p, + int line, int count, int dy) +{ + unsigned short *s = (unsigned short *) + (vc->vc_origin + vc->vc_size_row * line); + + while (count--) { + unsigned short *start = s; + unsigned short *le = advance_row(s, 1); + unsigned short c; + int x = 0; + unsigned short attr = 1; + + do { + c = scr_readw(s); + if (attr != (c & 0xff00)) { + attr = c & 0xff00; + if (s > start) { + fbcon_putcs(vc, start, s - start, + dy, x); + x += s - start; + start = s; + } + } + console_conditional_schedule(); + s++; + } while (s < le); + if (s > start) + fbcon_putcs(vc, start, s - start, dy, x); + console_conditional_schedule(); + dy++; + } +} + +static void fbcon_redraw_blit(struct vc_data *vc, struct fb_info *info, + struct fbcon_display *p, int line, int count, int ycount) +{ + int offset = ycount * vc->vc_cols; + unsigned short *d = (unsigned short *) + (vc->vc_origin + vc->vc_size_row * line); + unsigned short *s = d + offset; + struct fbcon_ops *ops = info->fbcon_par; + + while (count--) { + unsigned short *start = s; + unsigned short *le = advance_row(s, 1); + unsigned short c; + int x = 0; + + do { + c = scr_readw(s); + + if (c == scr_readw(d)) { + if (s > start) { + ops->bmove(vc, info, line + ycount, x, + line, x, 1, s-start); + x += s - start + 1; + start = s + 1; + } else { + x++; + start++; + } + } + + scr_writew(c, d); + console_conditional_schedule(); + s++; + d++; + } while (s < le); + if (s > start) + ops->bmove(vc, info, line + ycount, x, line, x, 1, + s-start); + console_conditional_schedule(); + if (ycount > 0) + line++; + else { + line--; + /* NOTE: We subtract two lines from these pointers */ + s -= vc->vc_size_row; + d -= vc->vc_size_row; + } + } +} + static void fbcon_redraw(struct vc_data *vc, struct fbcon_display *p, int line, int count, int offset) { @@ -1450,6 +1687,7 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, { struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; struct fbcon_display *p = &fb_display[vc->vc_num]; + int scroll_partial = info->flags & FBINFO_PARTIAL_PAN_OK; if (fbcon_is_inactive(vc, info)) return true; @@ -1466,32 +1704,249 @@ static bool fbcon_scroll(struct vc_data *vc, unsigned int t, unsigned int b, case SM_UP: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - fbcon_redraw(vc, p, t, b - t - count, - count * vc->vc_cols); - fbcon_clear(vc, b - count, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - (b - count)), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; + if (logo_shown >= 0) + goto redraw_up; + switch (p->scrollmode) { + case SCROLL_MOVE: + fbcon_redraw_blit(vc, info, p, t, b - t - count, + count); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + (b - count)), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + + case SCROLL_WRAP_MOVE: + if (b - t - count > 3 * vc->vc_rows >> 2) { + if (t > 0) + fbcon_bmove(vc, 0, 0, count, 0, t, + vc->vc_cols); + ywrap_up(vc, count); + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b - count, 0, b, 0, + vc->vc_rows - b, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t + count, 0, t, 0, + b - t - count, vc->vc_cols); + else + goto redraw_up; + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_REDRAW: + if ((p->yscroll + count <= + 2 * (p->vrows - vc->vc_rows)) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (t > 0) + fbcon_redraw_move(vc, p, 0, t, count); + ypan_up_redraw(vc, t, count); + if (vc->vc_rows - b > 0) + fbcon_redraw_move(vc, p, b, + vc->vc_rows - b, b); + } else + fbcon_redraw_move(vc, p, t + count, b - t - count, t); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_MOVE: + if ((p->yscroll + count <= + 2 * (p->vrows - vc->vc_rows)) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (t > 0) + fbcon_bmove(vc, 0, 0, count, 0, t, + vc->vc_cols); + ypan_up(vc, count); + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b - count, 0, b, 0, + vc->vc_rows - b, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t + count, 0, t, 0, + b - t - count, vc->vc_cols); + else + goto redraw_up; + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + break; + + case SCROLL_REDRAW: + redraw_up: + fbcon_redraw(vc, p, t, b - t - count, + count * vc->vc_cols); + fbcon_clear(vc, b - count, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + (b - count)), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + } + break; case SM_DOWN: if (count > vc->vc_rows) /* Maximum realistic size */ count = vc->vc_rows; - fbcon_redraw(vc, p, b - 1, b - t - count, - -count * vc->vc_cols); - fbcon_clear(vc, t, 0, count, vc->vc_cols); - scr_memsetw((unsigned short *) (vc->vc_origin + - vc->vc_size_row * - t), - vc->vc_video_erase_char, - vc->vc_size_row * count); - return true; + if (logo_shown >= 0) + goto redraw_down; + switch (p->scrollmode) { + case SCROLL_MOVE: + fbcon_redraw_blit(vc, info, p, b - 1, b - t - count, + -count); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + t), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + + case SCROLL_WRAP_MOVE: + if (b - t - count > 3 * vc->vc_rows >> 2) { + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b, 0, b - count, 0, + vc->vc_rows - b, + vc->vc_cols); + ywrap_down(vc, count); + if (t > 0) + fbcon_bmove(vc, count, 0, 0, 0, t, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t, 0, t + count, 0, + b - t - count, vc->vc_cols); + else + goto redraw_down; + fbcon_clear(vc, t, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_MOVE: + if ((count - p->yscroll <= p->vrows - vc->vc_rows) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (vc->vc_rows - b > 0) + fbcon_bmove(vc, b, 0, b - count, 0, + vc->vc_rows - b, + vc->vc_cols); + ypan_down(vc, count); + if (t > 0) + fbcon_bmove(vc, count, 0, 0, 0, t, + vc->vc_cols); + } else if (info->flags & FBINFO_READS_FAST) + fbcon_bmove(vc, t, 0, t + count, 0, + b - t - count, vc->vc_cols); + else + goto redraw_down; + fbcon_clear(vc, t, 0, count, vc->vc_cols); + break; + + case SCROLL_PAN_REDRAW: + if ((count - p->yscroll <= p->vrows - vc->vc_rows) + && ((!scroll_partial && (b - t == vc->vc_rows)) + || (scroll_partial + && (b - t - count > + 3 * vc->vc_rows >> 2)))) { + if (vc->vc_rows - b > 0) + fbcon_redraw_move(vc, p, b, vc->vc_rows - b, + b - count); + ypan_down_redraw(vc, t, count); + if (t > 0) + fbcon_redraw_move(vc, p, count, t, 0); + } else + fbcon_redraw_move(vc, p, t, b - t - count, t + count); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + break; + + case SCROLL_REDRAW: + redraw_down: + fbcon_redraw(vc, p, b - 1, b - t - count, + -count * vc->vc_cols); + fbcon_clear(vc, t, 0, count, vc->vc_cols); + scr_memsetw((unsigned short *) (vc->vc_origin + + vc->vc_size_row * + t), + vc->vc_video_erase_char, + vc->vc_size_row * count); + return true; + } } return false; } + +static void fbcon_bmove(struct vc_data *vc, int sy, int sx, int dy, int dx, + int height, int width) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_display *p = &fb_display[vc->vc_num]; + + if (fbcon_is_inactive(vc, info)) + return; + + if (!width || !height) + return; + + /* Split blits that cross physical y_wrap case. + * Pathological case involves 4 blits, better to use recursive + * code rather than unrolled case + * + * Recursive invocations don't need to erase the cursor over and + * over again, so we use fbcon_bmove_rec() + */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, height, width, + p->vrows - p->yscroll); +} + +static void fbcon_bmove_rec(struct vc_data *vc, struct fbcon_display *p, int sy, int sx, + int dy, int dx, int height, int width, u_int y_break) +{ + struct fb_info *info = registered_fb[con2fb_map[vc->vc_num]]; + struct fbcon_ops *ops = info->fbcon_par; + u_int b; + + if (sy < y_break && sy + height > y_break) { + b = y_break - sy; + if (dy < sy) { /* Avoid trashing self */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + } else { + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + } + return; + } + + if (dy < y_break && dy + height > y_break) { + b = y_break - dy; + if (dy < sy) { /* Avoid trashing self */ + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + } else { + fbcon_bmove_rec(vc, p, sy + b, sx, dy + b, dx, + height - b, width, y_break); + fbcon_bmove_rec(vc, p, sy, sx, dy, dx, b, width, + y_break); + } + return; + } + ops->bmove(vc, info, real_y(p, sy), sx, real_y(p, dy), dx, + height, width); +} + static void updatescrollmode(struct fbcon_display *p, struct fb_info *info, struct vc_data *vc) @@ -1664,7 +2119,21 @@ static int fbcon_switch(struct vc_data *vc) updatescrollmode(p, info, vc); - scrollback_phys_max = 0; + switch (p->scrollmode) { + case SCROLL_WRAP_MOVE: + scrollback_phys_max = p->vrows - vc->vc_rows; + break; + case SCROLL_PAN_MOVE: + case SCROLL_PAN_REDRAW: + scrollback_phys_max = p->vrows - 2 * vc->vc_rows; + if (scrollback_phys_max < 0) + scrollback_phys_max = 0; + break; + default: + scrollback_phys_max = 0; + break; + } + scrollback_max = 0; scrollback_current = 0; diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index a00603b4451a..5246d0f2574b 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -29,6 +29,7 @@ struct fbcon_display { /* Filled in by the low-level console driver */ const u_char *fontdata; int userfont; /* != 0 if fontdata kmalloc()ed */ + u_short scrollmode; /* Scroll Method */ u_short inverse; /* != 0 text black on white as default */ short yscroll; /* Hardware scrolling */ int vrows; /* number of virtual rows */ @@ -51,6 +52,8 @@ struct fbcon_display { }; struct fbcon_ops { + void (*bmove)(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width); void (*clear)(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width); void (*putcs)(struct vc_data *vc, struct fb_info *info, @@ -149,6 +152,62 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) + /* + * Scroll Method + */ + +/* There are several methods fbcon can use to move text around the screen: + * + * Operation Pan Wrap + *--------------------------------------------- + * SCROLL_MOVE copyarea No No + * SCROLL_PAN_MOVE copyarea Yes No + * SCROLL_WRAP_MOVE copyarea No Yes + * SCROLL_REDRAW imageblit No No + * SCROLL_PAN_REDRAW imageblit Yes No + * SCROLL_WRAP_REDRAW imageblit No Yes + * + * (SCROLL_WRAP_REDRAW is not implemented yet) + * + * In general, fbcon will choose the best scrolling + * method based on the rule below: + * + * Pan/Wrap > accel imageblit > accel copyarea > + * soft imageblit > (soft copyarea) + * + * Exception to the rule: Pan + accel copyarea is + * preferred over Pan + accel imageblit. + * + * The above is typical for PCI/AGP cards. Unless + * overridden, fbcon will never use soft copyarea. + * + * If you need to override the above rule, set the + * appropriate flags in fb_info->flags. For example, + * to prefer copyarea over imageblit, set + * FBINFO_READS_FAST. + * + * Other notes: + * + use the hardware engine to move the text + * (hw-accelerated copyarea() and fillrect()) + * + use hardware-supported panning on a large virtual screen + * + amifb can not only pan, but also wrap the display by N lines + * (i.e. visible line i = physical line (i+N) % yres). + * + read what's already rendered on the screen and + * write it in a different place (this is cfb_copyarea()) + * + re-render the text to the screen + * + * Whether to use wrapping or panning can only be figured out at + * runtime (when we know whether our font height is a multiple + * of the pan/wrap step) + * + */ + +#define SCROLL_MOVE 0x001 +#define SCROLL_PAN_MOVE 0x002 +#define SCROLL_WRAP_MOVE 0x003 +#define SCROLL_REDRAW 0x004 +#define SCROLL_PAN_REDRAW 0x005 + #ifdef CONFIG_FB_TILEBLITTING extern void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info); #endif diff --git a/drivers/video/fbdev/core/fbcon_ccw.c b/drivers/video/fbdev/core/fbcon_ccw.c index ffa78936eaab..9cd2c4b05c32 100644 --- a/drivers/video/fbdev/core/fbcon_ccw.c +++ b/drivers/video/fbdev/core/fbcon_ccw.c @@ -59,12 +59,31 @@ static void ccw_update_attr(u8 *dst, u8 *src, int attribute, } } + +static void ccw_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct fb_copyarea area; + u32 vyres = GETVYRES(ops->p->scrollmode, info); + + area.sx = sy * vc->vc_font.height; + area.sy = vyres - ((sx + width) * vc->vc_font.width); + area.dx = dy * vc->vc_font.height; + area.dy = vyres - ((dx + width) * vc->vc_font.width); + area.width = height * vc->vc_font.height; + area.height = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void ccw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { + struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = sy * vc->vc_font.height; @@ -121,7 +140,7 @@ static void ccw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); if (!ops->fontbuffer) return; @@ -210,7 +229,7 @@ static void ccw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); if (!ops->fontbuffer) return; @@ -368,7 +387,7 @@ static int ccw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; u32 yoffset; - u32 vyres = info->var.yres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); int err; yoffset = (vyres - info->var.yres) - ops->var.xoffset; @@ -383,6 +402,7 @@ static int ccw_update_start(struct fb_info *info) void fbcon_rotate_ccw(struct fbcon_ops *ops) { + ops->bmove = ccw_bmove; ops->clear = ccw_clear; ops->putcs = ccw_putcs; ops->clear_margins = ccw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_cw.c b/drivers/video/fbdev/core/fbcon_cw.c index 92e5b7fb51ee..88d89fad3f05 100644 --- a/drivers/video/fbdev/core/fbcon_cw.c +++ b/drivers/video/fbdev/core/fbcon_cw.c @@ -44,12 +44,31 @@ static void cw_update_attr(u8 *dst, u8 *src, int attribute, } } + +static void cw_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct fb_copyarea area; + u32 vxres = GETVXRES(ops->p->scrollmode, info); + + area.sx = vxres - ((sy + height) * vc->vc_font.height); + area.sy = sx * vc->vc_font.width; + area.dx = vxres - ((dy + height) * vc->vc_font.height); + area.dy = dx * vc->vc_font.width; + area.width = height * vc->vc_font.height; + area.height = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void cw_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { + struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p->scrollmode, info); region.color = attr_bgcol_ec(bgshift,vc,info); region.dx = vxres - ((sy + height) * vc->vc_font.height); @@ -106,7 +125,7 @@ static void cw_putcs(struct vc_data *vc, struct fb_info *info, u32 cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p->scrollmode, info); if (!ops->fontbuffer) return; @@ -193,7 +212,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p->scrollmode, info); if (!ops->fontbuffer) return; @@ -350,7 +369,7 @@ static void cw_cursor(struct vc_data *vc, struct fb_info *info, int mode, static int cw_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; - u32 vxres = info->var.xres; + u32 vxres = GETVXRES(ops->p->scrollmode, info); u32 xoffset; int err; @@ -366,6 +385,7 @@ static int cw_update_start(struct fb_info *info) void fbcon_rotate_cw(struct fbcon_ops *ops) { + ops->bmove = cw_bmove; ops->clear = cw_clear; ops->putcs = cw_putcs; ops->clear_margins = cw_clear_margins; diff --git a/drivers/video/fbdev/core/fbcon_rotate.h b/drivers/video/fbdev/core/fbcon_rotate.h index b528b2e54283..e233444cda66 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.h +++ b/drivers/video/fbdev/core/fbcon_rotate.h @@ -11,6 +11,15 @@ #ifndef _FBCON_ROTATE_H #define _FBCON_ROTATE_H +#define GETVYRES(s,i) ({ \ + (s == SCROLL_REDRAW || s == SCROLL_MOVE) ? \ + (i)->var.yres : (i)->var.yres_virtual; }) + +#define GETVXRES(s,i) ({ \ + (s == SCROLL_REDRAW || s == SCROLL_MOVE || !(i)->fix.xpanstep) ? \ + (i)->var.xres : (i)->var.xres_virtual; }) + + static inline int pattern_test_bit(u32 x, u32 y, u32 pitch, const char *pat) { u32 tmp = (y * pitch) + x, index = tmp / 8, bit = tmp % 8; diff --git a/drivers/video/fbdev/core/fbcon_ud.c b/drivers/video/fbdev/core/fbcon_ud.c index 09619bd8e021..8d5e66b1bdfb 100644 --- a/drivers/video/fbdev/core/fbcon_ud.c +++ b/drivers/video/fbdev/core/fbcon_ud.c @@ -44,13 +44,33 @@ static void ud_update_attr(u8 *dst, u8 *src, int attribute, } } + +static void ud_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fbcon_ops *ops = info->fbcon_par; + struct fb_copyarea area; + u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vxres = GETVXRES(ops->p->scrollmode, info); + + area.sy = vyres - ((sy + height) * vc->vc_font.height); + area.sx = vxres - ((sx + width) * vc->vc_font.width); + area.dy = vyres - ((dy + height) * vc->vc_font.height); + area.dx = vxres - ((dx + width) * vc->vc_font.width); + area.height = height * vc->vc_font.height; + area.width = width * vc->vc_font.width; + + info->fbops->fb_copyarea(info, &area); +} + static void ud_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { + struct fbcon_ops *ops = info->fbcon_par; struct fb_fillrect region; int bgshift = (vc->vc_hi_font_mask) ? 13 : 12; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vxres = GETVXRES(ops->p->scrollmode, info); region.color = attr_bgcol_ec(bgshift,vc,info); region.dy = vyres - ((sy + height) * vc->vc_font.height); @@ -142,8 +162,8 @@ static void ud_putcs(struct vc_data *vc, struct fb_info *info, u32 mod = vc->vc_font.width % 8, cnt, pitch, size; u32 attribute = get_attribute(info, scr_readw(s)); u8 *dst, *buf = NULL; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vxres = GETVXRES(ops->p->scrollmode, info); if (!ops->fontbuffer) return; @@ -239,8 +259,8 @@ static void ud_cursor(struct vc_data *vc, struct fb_info *info, int mode, int attribute, use_sw = vc->vc_cursor_type & CUR_SW; int err = 1, dx, dy; char *src; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vxres = GETVXRES(ops->p->scrollmode, info); if (!ops->fontbuffer) return; @@ -390,8 +410,8 @@ static int ud_update_start(struct fb_info *info) { struct fbcon_ops *ops = info->fbcon_par; int xoffset, yoffset; - u32 vyres = info->var.yres; - u32 vxres = info->var.xres; + u32 vyres = GETVYRES(ops->p->scrollmode, info); + u32 vxres = GETVXRES(ops->p->scrollmode, info); int err; xoffset = vxres - info->var.xres - ops->var.xoffset; @@ -409,6 +429,7 @@ static int ud_update_start(struct fb_info *info) void fbcon_rotate_ud(struct fbcon_ops *ops) { + ops->bmove = ud_bmove; ops->clear = ud_clear; ops->putcs = ud_putcs; ops->clear_margins = ud_clear_margins; diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 72af95053bcb..2768eff247ba 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -16,6 +16,21 @@ #include #include "fbcon.h" +static void tile_bmove(struct vc_data *vc, struct fb_info *info, int sy, + int sx, int dy, int dx, int height, int width) +{ + struct fb_tilearea area; + + area.sx = sx; + area.sy = sy; + area.dx = dx; + area.dy = dy; + area.height = height; + area.width = width; + + info->tileops->fb_tilecopy(info, &area); +} + static void tile_clear(struct vc_data *vc, struct fb_info *info, int sy, int sx, int height, int width) { @@ -118,6 +133,7 @@ void fbcon_set_tileops(struct vc_data *vc, struct fb_info *info) struct fb_tilemap map; struct fbcon_ops *ops = info->fbcon_par; + ops->bmove = tile_bmove; ops->clear = tile_clear; ops->putcs = tile_putcs; ops->clear_margins = tile_clear_margins; diff --git a/drivers/video/fbdev/skeletonfb.c b/drivers/video/fbdev/skeletonfb.c index 0fe922f726e9..bcacfb6934fa 100644 --- a/drivers/video/fbdev/skeletonfb.c +++ b/drivers/video/fbdev/skeletonfb.c @@ -505,15 +505,15 @@ void xxxfb_fillrect(struct fb_info *p, const struct fb_fillrect *region) } /** - * xxxfb_copyarea - OBSOLETE function. + * xxxfb_copyarea - REQUIRED function. Can use generic routines if + * non acclerated hardware and packed pixel based. * Copies one area of the screen to another area. - * Will be deleted in a future version * * @info: frame buffer structure that represents a single frame buffer * @area: Structure providing the data to copy the framebuffer contents * from one region to another. * - * This drawing operation copied a rectangular area from one area of the + * This drawing operation copies a rectangular area from one area of the * screen to another area. */ void xxxfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) @@ -645,9 +645,9 @@ static const struct fb_ops xxxfb_ops = { .fb_setcolreg = xxxfb_setcolreg, .fb_blank = xxxfb_blank, .fb_pan_display = xxxfb_pan_display, - .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ - .fb_copyarea = xxxfb_copyarea, /* Obsolete */ - .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ + .fb_fillrect = xxxfb_fillrect, /* Needed !!! */ + .fb_copyarea = xxxfb_copyarea, /* Needed !!! */ + .fb_imageblit = xxxfb_imageblit, /* Needed !!! */ .fb_cursor = xxxfb_cursor, /* Optional !!! */ .fb_sync = xxxfb_sync, .fb_ioctl = xxxfb_ioctl, diff --git a/include/linux/fb.h b/include/linux/fb.h index 3da95842b207..02f362c661c8 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -262,7 +262,7 @@ struct fb_ops { /* Draws a rectangle */ void (*fb_fillrect) (struct fb_info *info, const struct fb_fillrect *rect); - /* Copy data from area to another. Obsolete. */ + /* Copy data from area to another */ void (*fb_copyarea) (struct fb_info *info, const struct fb_copyarea *region); /* Draws a image to the display */ void (*fb_imageblit) (struct fb_info *info, const struct fb_image *image); -- cgit v1.2.3 From e1d2699b96793d19388e302fa095e0da2c145701 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Tue, 18 Jan 2022 22:10:52 -0500 Subject: NFS: Avoid duplicate uncached readdir calls on eof If we've reached the end of the directory, then cache that information in the context so that we don't need to do an uncached readdir in order to rediscover that fact. Fixes: 794092c57f89 ("NFS: Do uncached readdir when we're seeking a cookie in an empty page cache") Signed-off-by: Trond Myklebust Signed-off-by: Anna Schumaker --- fs/nfs/dir.c | 20 +++++++++++++++----- include/linux/nfs_fs.h | 1 + 2 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a3de586d21e2..7bc7cf6b26f0 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -80,6 +80,7 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir ctx->dir_cookie = 0; ctx->dup_cookie = 0; ctx->page_index = 0; + ctx->eof = false; spin_lock(&dir->i_lock); if (list_empty(&nfsi->open_files) && (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER)) @@ -168,6 +169,7 @@ struct nfs_readdir_descriptor { unsigned int cache_entry_index; signed char duped; bool plus; + bool eob; bool eof; }; @@ -989,7 +991,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, ent = &array->array[i]; if (!dir_emit(desc->ctx, ent->name, ent->name_len, nfs_compat_user_ino64(ent->ino), ent->d_type)) { - desc->eof = true; + desc->eob = true; break; } memcpy(desc->verf, verf, sizeof(desc->verf)); @@ -1005,7 +1007,7 @@ static void nfs_do_filldir(struct nfs_readdir_descriptor *desc, desc->duped = 1; } if (array->page_is_eof) - desc->eof = true; + desc->eof = !desc->eob; kunmap(desc->page); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n", @@ -1048,7 +1050,7 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc) status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz); - for (i = 0; !desc->eof && i < sz && arrays[i]; i++) { + for (i = 0; !desc->eob && i < sz && arrays[i]; i++) { desc->page = arrays[i]; nfs_do_filldir(desc, verf); } @@ -1107,9 +1109,15 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) desc->duped = dir_ctx->duped; page_index = dir_ctx->page_index; desc->attr_gencount = dir_ctx->attr_gencount; + desc->eof = dir_ctx->eof; memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf)); spin_unlock(&file->f_lock); + if (desc->eof) { + res = 0; + goto out_free; + } + if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) && list_is_singular(&nfsi->open_files)) invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1); @@ -1143,7 +1151,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) nfs_do_filldir(desc, nfsi->cookieverf); nfs_readdir_page_unlock_and_put_cached(desc); - } while (!desc->eof); + } while (!desc->eob && !desc->eof); spin_lock(&file->f_lock); dir_ctx->dir_cookie = desc->dir_cookie; @@ -1151,9 +1159,10 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) dir_ctx->duped = desc->duped; dir_ctx->attr_gencount = desc->attr_gencount; dir_ctx->page_index = desc->page_index; + dir_ctx->eof = desc->eof; memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf)); spin_unlock(&file->f_lock); - +out_free: kfree(desc); out: @@ -1195,6 +1204,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence) if (offset == 0) memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf)); dir_ctx->duped = 0; + dir_ctx->eof = false; } spin_unlock(&filp->f_lock); return offset; diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 02aa49323d1d..68f81d8d36de 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -107,6 +107,7 @@ struct nfs_open_dir_context { __u64 dup_cookie; pgoff_t page_index; signed char duped; + bool eof; }; /* -- cgit v1.2.3 From 2ea88716369ac9a7486a8cb309d6bf1239ea156c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 23 Jan 2022 17:27:47 +0100 Subject: libceph: make recv path in secure mode work the same as send path The recv path of secure mode is intertwined with that of crc mode. While it's slightly more efficient that way (the ciphertext is read into the destination buffer and decrypted in place, thus avoiding two potentially heavy memory allocations for the bounce buffer and the corresponding sg array), it isn't really amenable to changes. Sacrifice that edge and align with the send path which always uses a full-sized bounce buffer (currently there is no other way -- if the kernel crypto API ever grows support for streaming (piecewise) en/decryption for GCM [1], we would be able to easily take advantage of that on both sides). [1] https://lore.kernel.org/all/20141225202830.GA18794@gondor.apana.org.au/ Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/messenger.h | 4 + net/ceph/messenger_v2.c | 216 +++++++++++++++++++++++++++++------------ 2 files changed, 158 insertions(+), 62 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index ff99ce094cfa..6c6b6ea52bb8 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -383,6 +383,10 @@ struct ceph_connection_v2_info { struct ceph_gcm_nonce in_gcm_nonce; struct ceph_gcm_nonce out_gcm_nonce; + struct page **in_enc_pages; + int in_enc_page_cnt; + int in_enc_resid; + int in_enc_i; struct page **out_enc_pages; int out_enc_page_cnt; int out_enc_resid; diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index c4099b641b38..2ea00489e691 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -57,8 +57,9 @@ #define IN_S_HANDLE_CONTROL_REMAINDER 3 #define IN_S_PREPARE_READ_DATA 4 #define IN_S_PREPARE_READ_DATA_CONT 5 -#define IN_S_HANDLE_EPILOGUE 6 -#define IN_S_FINISH_SKIP 7 +#define IN_S_PREPARE_READ_ENC_PAGE 6 +#define IN_S_HANDLE_EPILOGUE 7 +#define IN_S_FINISH_SKIP 8 #define OUT_S_QUEUE_DATA 1 #define OUT_S_QUEUE_DATA_CONT 2 @@ -1032,22 +1033,41 @@ static int decrypt_control_remainder(struct ceph_connection *con) padded_len(rem_len) + CEPH_GCM_TAG_LEN); } -static int decrypt_message(struct ceph_connection *con) +static int decrypt_tail(struct ceph_connection *con) { + struct sg_table enc_sgt = {}; struct sg_table sgt = {}; + int tail_len; int ret; + tail_len = tail_onwire_len(con->in_msg, true); + ret = sg_alloc_table_from_pages(&enc_sgt, con->v2.in_enc_pages, + con->v2.in_enc_page_cnt, 0, tail_len, + GFP_NOIO); + if (ret) + goto out; + ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf), MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf), con->v2.in_buf, true); if (ret) goto out; - ret = gcm_crypt(con, false, sgt.sgl, sgt.sgl, - tail_onwire_len(con->in_msg, true)); + dout("%s con %p msg %p enc_page_cnt %d sg_cnt %d\n", __func__, con, + con->in_msg, con->v2.in_enc_page_cnt, sgt.orig_nents); + ret = gcm_crypt(con, false, enc_sgt.sgl, sgt.sgl, tail_len); + if (ret) + goto out; + + WARN_ON(!con->v2.in_enc_page_cnt); + ceph_release_page_vector(con->v2.in_enc_pages, + con->v2.in_enc_page_cnt); + con->v2.in_enc_pages = NULL; + con->v2.in_enc_page_cnt = 0; out: sg_free_table(&sgt); + sg_free_table(&enc_sgt); return ret; } @@ -1737,8 +1757,7 @@ static void prepare_read_data(struct ceph_connection *con) { struct bio_vec bv; - if (!con_secure(con)) - con->in_data_crc = -1; + con->in_data_crc = -1; ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg, data_len(con->in_msg)); @@ -1751,11 +1770,10 @@ static void prepare_read_data_cont(struct ceph_connection *con) { struct bio_vec bv; - if (!con_secure(con)) - con->in_data_crc = ceph_crc32c_page(con->in_data_crc, - con->v2.in_bvec.bv_page, - con->v2.in_bvec.bv_offset, - con->v2.in_bvec.bv_len); + con->in_data_crc = ceph_crc32c_page(con->in_data_crc, + con->v2.in_bvec.bv_page, + con->v2.in_bvec.bv_offset, + con->v2.in_bvec.bv_len); ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len); if (con->v2.in_cursor.total_resid) { @@ -1766,21 +1784,94 @@ static void prepare_read_data_cont(struct ceph_connection *con) } /* - * We've read all data. Prepare to read data padding (if any) - * and epilogue. + * We've read all data. Prepare to read epilogue. */ reset_in_kvecs(con); - if (con_secure(con)) { - if (need_padding(data_len(con->in_msg))) - add_in_kvec(con, DATA_PAD(con->v2.in_buf), - padding_len(data_len(con->in_msg))); - add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_SECURE_LEN); + add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN); + con->v2.in_state = IN_S_HANDLE_EPILOGUE; +} + +static void prepare_read_tail_plain(struct ceph_connection *con) +{ + struct ceph_msg *msg = con->in_msg; + + if (!front_len(msg) && !middle_len(msg)) { + WARN_ON(!data_len(msg)); + prepare_read_data(con); + return; + } + + reset_in_kvecs(con); + if (front_len(msg)) { + add_in_kvec(con, msg->front.iov_base, front_len(msg)); + WARN_ON(msg->front.iov_len != front_len(msg)); + } + if (middle_len(msg)) { + add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg)); + WARN_ON(msg->middle->vec.iov_len != middle_len(msg)); + } + + if (data_len(msg)) { + con->v2.in_state = IN_S_PREPARE_READ_DATA; } else { add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN); + con->v2.in_state = IN_S_HANDLE_EPILOGUE; + } +} + +static void prepare_read_enc_page(struct ceph_connection *con) +{ + struct bio_vec bv; + + dout("%s con %p i %d resid %d\n", __func__, con, con->v2.in_enc_i, + con->v2.in_enc_resid); + WARN_ON(!con->v2.in_enc_resid); + + bv.bv_page = con->v2.in_enc_pages[con->v2.in_enc_i]; + bv.bv_offset = 0; + bv.bv_len = min(con->v2.in_enc_resid, (int)PAGE_SIZE); + + set_in_bvec(con, &bv); + con->v2.in_enc_i++; + con->v2.in_enc_resid -= bv.bv_len; + + if (con->v2.in_enc_resid) { + con->v2.in_state = IN_S_PREPARE_READ_ENC_PAGE; + return; } + + /* + * We are set to read the last piece of ciphertext (ending + * with epilogue) + auth tag. + */ + WARN_ON(con->v2.in_enc_i != con->v2.in_enc_page_cnt); con->v2.in_state = IN_S_HANDLE_EPILOGUE; } +static int prepare_read_tail_secure(struct ceph_connection *con) +{ + struct page **enc_pages; + int enc_page_cnt; + int tail_len; + + tail_len = tail_onwire_len(con->in_msg, true); + WARN_ON(!tail_len); + + enc_page_cnt = calc_pages_for(0, tail_len); + enc_pages = ceph_alloc_page_vector(enc_page_cnt, GFP_NOIO); + if (IS_ERR(enc_pages)) + return PTR_ERR(enc_pages); + + WARN_ON(con->v2.in_enc_pages || con->v2.in_enc_page_cnt); + con->v2.in_enc_pages = enc_pages; + con->v2.in_enc_page_cnt = enc_page_cnt; + con->v2.in_enc_resid = tail_len; + con->v2.in_enc_i = 0; + + prepare_read_enc_page(con); + return 0; +} + static void __finish_skip(struct ceph_connection *con) { con->in_seq++; @@ -2589,46 +2680,26 @@ static int __handle_control(struct ceph_connection *con, void *p) } msg = con->in_msg; /* set in process_message_header() */ - if (!front_len(msg) && !middle_len(msg)) { - if (!data_len(msg)) - return process_message(con); - - prepare_read_data(con); - return 0; - } - - reset_in_kvecs(con); if (front_len(msg)) { WARN_ON(front_len(msg) > msg->front_alloc_len); - add_in_kvec(con, msg->front.iov_base, front_len(msg)); msg->front.iov_len = front_len(msg); - - if (con_secure(con) && need_padding(front_len(msg))) - add_in_kvec(con, FRONT_PAD(con->v2.in_buf), - padding_len(front_len(msg))); } else { msg->front.iov_len = 0; } if (middle_len(msg)) { WARN_ON(middle_len(msg) > msg->middle->alloc_len); - add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg)); msg->middle->vec.iov_len = middle_len(msg); - - if (con_secure(con) && need_padding(middle_len(msg))) - add_in_kvec(con, MIDDLE_PAD(con->v2.in_buf), - padding_len(middle_len(msg))); } else if (msg->middle) { msg->middle->vec.iov_len = 0; } - if (data_len(msg)) { - con->v2.in_state = IN_S_PREPARE_READ_DATA; - } else { - add_in_kvec(con, con->v2.in_buf, - con_secure(con) ? CEPH_EPILOGUE_SECURE_LEN : - CEPH_EPILOGUE_PLAIN_LEN); - con->v2.in_state = IN_S_HANDLE_EPILOGUE; - } + if (!front_len(msg) && !middle_len(msg) && !data_len(msg)) + return process_message(con); + + if (con_secure(con)) + return prepare_read_tail_secure(con); + + prepare_read_tail_plain(con); return 0; } @@ -2717,7 +2788,7 @@ static int handle_epilogue(struct ceph_connection *con) int ret; if (con_secure(con)) { - ret = decrypt_message(con); + ret = decrypt_tail(con); if (ret) { if (ret == -EBADMSG) con->error_msg = "integrity error, bad epilogue auth tag"; @@ -2792,6 +2863,10 @@ static int populate_in_iter(struct ceph_connection *con) prepare_read_data_cont(con); ret = 0; break; + case IN_S_PREPARE_READ_ENC_PAGE: + prepare_read_enc_page(con); + ret = 0; + break; case IN_S_HANDLE_EPILOGUE: ret = handle_epilogue(con); break; @@ -3326,20 +3401,16 @@ void ceph_con_v2_revoke(struct ceph_connection *con) static void revoke_at_prepare_read_data(struct ceph_connection *con) { - int remaining; /* data + [data padding] + epilogue */ + int remaining; int resid; + WARN_ON(con_secure(con)); WARN_ON(!data_len(con->in_msg)); WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter)); resid = iov_iter_count(&con->v2.in_iter); WARN_ON(!resid); - if (con_secure(con)) - remaining = padded_len(data_len(con->in_msg)) + - CEPH_EPILOGUE_SECURE_LEN; - else - remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN; - + remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN; dout("%s con %p resid %d remaining %d\n", __func__, con, resid, remaining); con->v2.in_iter.count -= resid; @@ -3350,8 +3421,9 @@ static void revoke_at_prepare_read_data(struct ceph_connection *con) static void revoke_at_prepare_read_data_cont(struct ceph_connection *con) { int recved, resid; /* current piece of data */ - int remaining; /* [data padding] + epilogue */ + int remaining; + WARN_ON(con_secure(con)); WARN_ON(!data_len(con->in_msg)); WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter)); resid = iov_iter_count(&con->v2.in_iter); @@ -3363,12 +3435,7 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con) ceph_msg_data_advance(&con->v2.in_cursor, recved); WARN_ON(resid > con->v2.in_cursor.total_resid); - if (con_secure(con)) - remaining = padding_len(data_len(con->in_msg)) + - CEPH_EPILOGUE_SECURE_LEN; - else - remaining = CEPH_EPILOGUE_PLAIN_LEN; - + remaining = CEPH_EPILOGUE_PLAIN_LEN; dout("%s con %p total_resid %zu remaining %d\n", __func__, con, con->v2.in_cursor.total_resid, remaining); con->v2.in_iter.count -= resid; @@ -3376,11 +3443,26 @@ static void revoke_at_prepare_read_data_cont(struct ceph_connection *con) con->v2.in_state = IN_S_FINISH_SKIP; } +static void revoke_at_prepare_read_enc_page(struct ceph_connection *con) +{ + int resid; /* current enc page (not necessarily data) */ + + WARN_ON(!con_secure(con)); + WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter)); + resid = iov_iter_count(&con->v2.in_iter); + WARN_ON(!resid || resid > con->v2.in_bvec.bv_len); + + dout("%s con %p resid %d enc_resid %d\n", __func__, con, resid, + con->v2.in_enc_resid); + con->v2.in_iter.count -= resid; + set_in_skip(con, resid + con->v2.in_enc_resid); + con->v2.in_state = IN_S_FINISH_SKIP; +} + static void revoke_at_handle_epilogue(struct ceph_connection *con) { int resid; - WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter)); resid = iov_iter_count(&con->v2.in_iter); WARN_ON(!resid); @@ -3399,6 +3481,9 @@ void ceph_con_v2_revoke_incoming(struct ceph_connection *con) case IN_S_PREPARE_READ_DATA_CONT: revoke_at_prepare_read_data_cont(con); break; + case IN_S_PREPARE_READ_ENC_PAGE: + revoke_at_prepare_read_enc_page(con); + break; case IN_S_HANDLE_EPILOGUE: revoke_at_handle_epilogue(con); break; @@ -3432,6 +3517,13 @@ void ceph_con_v2_reset_protocol(struct ceph_connection *con) clear_out_sign_kvecs(con); free_conn_bufs(con); + if (con->v2.in_enc_pages) { + WARN_ON(!con->v2.in_enc_page_cnt); + ceph_release_page_vector(con->v2.in_enc_pages, + con->v2.in_enc_page_cnt); + con->v2.in_enc_pages = NULL; + con->v2.in_enc_page_cnt = 0; + } if (con->v2.out_enc_pages) { WARN_ON(!con->v2.out_enc_page_cnt); ceph_release_page_vector(con->v2.out_enc_pages, -- cgit v1.2.3 From 038b8d1d1ab1cce11a158d30bf080ff41a2cfd15 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 30 Dec 2021 15:13:32 +0100 Subject: libceph: optionally use bounce buffer on recv path in crc mode Both msgr1 and msgr2 in crc mode are zero copy in the sense that message data is read from the socket directly into the destination buffer. We assume that the destination buffer is stable (i.e. remains unchanged while it is being read to) though. Otherwise, CRC errors ensue: libceph: read_partial_message 0000000048edf8ad data crc 1063286393 != exp. 228122706 libceph: osd1 (1)192.168.122.1:6843 bad crc/signature libceph: bad data crc, calculated 57958023, expected 1805382778 libceph: osd2 (2)192.168.122.1:6876 integrity error, bad crc Introduce rxbounce option to enable use of a bounce buffer when receiving message data. In particular this is needed if a mapped image is a Windows VM disk, passed to QEMU. Windows has a system-wide "dummy" page that may be mapped into the destination buffer (potentially more than once into the same buffer) by the Windows Memory Manager in an effort to generate a single large I/O [1][2]. QEMU makes a point of preserving overlap relationships when cloning I/O vectors, so krbd gets exposed to this behaviour. [1] "What Is Really in That MDL?" https://docs.microsoft.com/en-us/previous-versions/windows/hardware/design/dn614012(v=vs.85) [2] https://blogs.msmvps.com/kernelmustard/2005/05/04/dummy-pages/ URL: https://bugzilla.redhat.com/show_bug.cgi?id=1973317 Signed-off-by: Ilya Dryomov Reviewed-by: Jeff Layton --- include/linux/ceph/libceph.h | 1 + include/linux/ceph/messenger.h | 1 + net/ceph/ceph_common.c | 7 +++++ net/ceph/messenger.c | 4 +++ net/ceph/messenger_v1.c | 54 ++++++++++++++++++++++++++++++++++----- net/ceph/messenger_v2.c | 58 ++++++++++++++++++++++++++++++++---------- 6 files changed, 105 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 6a89ea410e43..edf62eaa6285 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -35,6 +35,7 @@ #define CEPH_OPT_TCP_NODELAY (1<<4) /* TCP_NODELAY on TCP sockets */ #define CEPH_OPT_NOMSGSIGN (1<<5) /* don't sign msgs (msgr1) */ #define CEPH_OPT_ABORT_ON_FULL (1<<6) /* abort w/ ENOSPC when full */ +#define CEPH_OPT_RXBOUNCE (1<<7) /* double-buffer read data */ #define CEPH_OPT_DEFAULT (CEPH_OPT_TCP_NODELAY) diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h index 6c6b6ea52bb8..e7f2fb2fc207 100644 --- a/include/linux/ceph/messenger.h +++ b/include/linux/ceph/messenger.h @@ -461,6 +461,7 @@ struct ceph_connection { struct ceph_msg *out_msg; /* sending message (== tail of out_sent) */ + struct page *bounce_page; u32 in_front_crc, in_middle_crc, in_data_crc; /* calculated crc */ struct timespec64 last_keepalive_ack; /* keepalive2 ack stamp */ diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c index ecc400a0b7bb..4c6441536d55 100644 --- a/net/ceph/ceph_common.c +++ b/net/ceph/ceph_common.c @@ -246,6 +246,7 @@ enum { Opt_cephx_sign_messages, Opt_tcp_nodelay, Opt_abort_on_full, + Opt_rxbounce, }; enum { @@ -295,6 +296,7 @@ static const struct fs_parameter_spec ceph_parameters[] = { fsparam_u32 ("osdkeepalive", Opt_osdkeepalivetimeout), fsparam_enum ("read_from_replica", Opt_read_from_replica, ceph_param_read_from_replica), + fsparam_flag ("rxbounce", Opt_rxbounce), fsparam_enum ("ms_mode", Opt_ms_mode, ceph_param_ms_mode), fsparam_string ("secret", Opt_secret), @@ -584,6 +586,9 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt, case Opt_abort_on_full: opt->flags |= CEPH_OPT_ABORT_ON_FULL; break; + case Opt_rxbounce: + opt->flags |= CEPH_OPT_RXBOUNCE; + break; default: BUG(); @@ -660,6 +665,8 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client, seq_puts(m, "notcp_nodelay,"); if (show_all && (opt->flags & CEPH_OPT_ABORT_ON_FULL)) seq_puts(m, "abort_on_full,"); + if (opt->flags & CEPH_OPT_RXBOUNCE) + seq_puts(m, "rxbounce,"); if (opt->mount_timeout != CEPH_MOUNT_TIMEOUT_DEFAULT) seq_printf(m, "mount_timeout=%d,", diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 45eba2dcb67a..d3bb656308b4 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -515,6 +515,10 @@ static void ceph_con_reset_protocol(struct ceph_connection *con) ceph_msg_put(con->out_msg); con->out_msg = NULL; } + if (con->bounce_page) { + __free_page(con->bounce_page); + con->bounce_page = NULL; + } if (ceph_msgr2(from_msgr(con->msgr))) ceph_con_v2_reset_protocol(con); diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index 2cb5ffdf071a..6b014eca3a13 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -992,8 +992,7 @@ static int read_partial_message_section(struct ceph_connection *con, static int read_partial_msg_data(struct ceph_connection *con) { - struct ceph_msg *msg = con->in_msg; - struct ceph_msg_data_cursor *cursor = &msg->cursor; + struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC); struct page *page; size_t page_offset; @@ -1001,9 +1000,6 @@ static int read_partial_msg_data(struct ceph_connection *con) u32 crc = 0; int ret; - if (!msg->num_data_items) - return -EIO; - if (do_datacrc) crc = con->in_data_crc; while (cursor->total_resid) { @@ -1031,6 +1027,46 @@ static int read_partial_msg_data(struct ceph_connection *con) return 1; /* must return > 0 to indicate success */ } +static int read_partial_msg_data_bounce(struct ceph_connection *con) +{ + struct ceph_msg_data_cursor *cursor = &con->in_msg->cursor; + struct page *page; + size_t off, len; + u32 crc; + int ret; + + if (unlikely(!con->bounce_page)) { + con->bounce_page = alloc_page(GFP_NOIO); + if (!con->bounce_page) { + pr_err("failed to allocate bounce page\n"); + return -ENOMEM; + } + } + + crc = con->in_data_crc; + while (cursor->total_resid) { + if (!cursor->resid) { + ceph_msg_data_advance(cursor, 0); + continue; + } + + page = ceph_msg_data_next(cursor, &off, &len, NULL); + ret = ceph_tcp_recvpage(con->sock, con->bounce_page, 0, len); + if (ret <= 0) { + con->in_data_crc = crc; + return ret; + } + + crc = crc32c(crc, page_address(con->bounce_page), ret); + memcpy_to_page(page, off, page_address(con->bounce_page), ret); + + ceph_msg_data_advance(cursor, ret); + } + con->in_data_crc = crc; + + return 1; /* must return > 0 to indicate success */ +} + /* * read (part of) a message. */ @@ -1141,7 +1177,13 @@ static int read_partial_message(struct ceph_connection *con) /* (page) data */ if (data_len) { - ret = read_partial_msg_data(con); + if (!m->num_data_items) + return -EIO; + + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) + ret = read_partial_msg_data_bounce(con); + else + ret = read_partial_msg_data(con); if (ret <= 0) return ret; } diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 2ea00489e691..c81379f93ad5 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -1753,7 +1753,7 @@ static int prepare_read_control_remainder(struct ceph_connection *con) return 0; } -static void prepare_read_data(struct ceph_connection *con) +static int prepare_read_data(struct ceph_connection *con) { struct bio_vec bv; @@ -1762,23 +1762,55 @@ static void prepare_read_data(struct ceph_connection *con) data_len(con->in_msg)); get_bvec_at(&con->v2.in_cursor, &bv); - set_in_bvec(con, &bv); + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) { + if (unlikely(!con->bounce_page)) { + con->bounce_page = alloc_page(GFP_NOIO); + if (!con->bounce_page) { + pr_err("failed to allocate bounce page\n"); + return -ENOMEM; + } + } + + bv.bv_page = con->bounce_page; + bv.bv_offset = 0; + set_in_bvec(con, &bv); + } else { + set_in_bvec(con, &bv); + } con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT; + return 0; } static void prepare_read_data_cont(struct ceph_connection *con) { struct bio_vec bv; - con->in_data_crc = ceph_crc32c_page(con->in_data_crc, - con->v2.in_bvec.bv_page, - con->v2.in_bvec.bv_offset, - con->v2.in_bvec.bv_len); + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) { + con->in_data_crc = crc32c(con->in_data_crc, + page_address(con->bounce_page), + con->v2.in_bvec.bv_len); + + get_bvec_at(&con->v2.in_cursor, &bv); + memcpy_to_page(bv.bv_page, bv.bv_offset, + page_address(con->bounce_page), + con->v2.in_bvec.bv_len); + } else { + con->in_data_crc = ceph_crc32c_page(con->in_data_crc, + con->v2.in_bvec.bv_page, + con->v2.in_bvec.bv_offset, + con->v2.in_bvec.bv_len); + } ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len); if (con->v2.in_cursor.total_resid) { get_bvec_at(&con->v2.in_cursor, &bv); - set_in_bvec(con, &bv); + if (ceph_test_opt(from_msgr(con->msgr), RXBOUNCE)) { + bv.bv_page = con->bounce_page; + bv.bv_offset = 0; + set_in_bvec(con, &bv); + } else { + set_in_bvec(con, &bv); + } WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT); return; } @@ -1791,14 +1823,13 @@ static void prepare_read_data_cont(struct ceph_connection *con) con->v2.in_state = IN_S_HANDLE_EPILOGUE; } -static void prepare_read_tail_plain(struct ceph_connection *con) +static int prepare_read_tail_plain(struct ceph_connection *con) { struct ceph_msg *msg = con->in_msg; if (!front_len(msg) && !middle_len(msg)) { WARN_ON(!data_len(msg)); - prepare_read_data(con); - return; + return prepare_read_data(con); } reset_in_kvecs(con); @@ -1817,6 +1848,7 @@ static void prepare_read_tail_plain(struct ceph_connection *con) add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN); con->v2.in_state = IN_S_HANDLE_EPILOGUE; } + return 0; } static void prepare_read_enc_page(struct ceph_connection *con) @@ -2699,8 +2731,7 @@ static int __handle_control(struct ceph_connection *con, void *p) if (con_secure(con)) return prepare_read_tail_secure(con); - prepare_read_tail_plain(con); - return 0; + return prepare_read_tail_plain(con); } static int handle_preamble(struct ceph_connection *con) @@ -2856,8 +2887,7 @@ static int populate_in_iter(struct ceph_connection *con) ret = handle_control_remainder(con); break; case IN_S_PREPARE_READ_DATA: - prepare_read_data(con); - ret = 0; + ret = prepare_read_data(con); break; case IN_S_PREPARE_READ_DATA_CONT: prepare_read_data_cont(con); -- cgit v1.2.3 From bfb1a7c91fb7758273b4a8d735313d9cc388b502 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Wed, 2 Feb 2022 12:55:53 -0800 Subject: x86/bug: Merge annotate_reachable() into _BUG_FLAGS() asm In __WARN_FLAGS(), we had two asm statements (abbreviated): asm volatile("ud2"); asm volatile(".pushsection .discard.reachable"); These pair of statements are used to trigger an exception, but then help objtool understand that for warnings, control flow will be restored immediately afterwards. The problem is that volatile is not a compiler barrier. GCC explicitly documents this: > Note that the compiler can move even volatile asm instructions > relative to other code, including across jump instructions. Also, no clobbers are specified to prevent instructions from subsequent statements from being scheduled by compiler before the second asm statement. This can lead to instructions from subsequent statements being emitted by the compiler before the second asm statement. Providing a scheduling model such as via -march= options enables the compiler to better schedule instructions with known latencies to hide latencies from data hazards compared to inline asm statements in which latencies are not estimated. If an instruction gets scheduled by the compiler between the two asm statements, then objtool will think that it is not reachable, producing a warning. To prevent instructions from being scheduled in between the two asm statements, merge them. Also remove an unnecessary unreachable() asm annotation from BUG() in favor of __builtin_unreachable(). objtool is able to track that the ud2 from BUG() terminates control flow within the function. Link: https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html#Volatile Link: https://github.com/ClangBuiltLinux/linux/issues/1483 Signed-off-by: Nick Desaulniers Signed-off-by: Josh Poimboeuf Link: https://lore.kernel.org/r/20220202205557.2260694-1-ndesaulniers@google.com --- arch/x86/include/asm/bug.h | 20 +++++++++++--------- include/linux/compiler.h | 21 +++++---------------- 2 files changed, 16 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 84b87538a15d..bab883c0b6fe 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -22,7 +22,7 @@ #ifdef CONFIG_DEBUG_BUGVERBOSE -#define _BUG_FLAGS(ins, flags) \ +#define _BUG_FLAGS(ins, flags, extra) \ do { \ asm_inline volatile("1:\t" ins "\n" \ ".pushsection __bug_table,\"aw\"\n" \ @@ -31,7 +31,8 @@ do { \ "\t.word %c1" "\t# bug_entry::line\n" \ "\t.word %c2" "\t# bug_entry::flags\n" \ "\t.org 2b+%c3\n" \ - ".popsection" \ + ".popsection\n" \ + extra \ : : "i" (__FILE__), "i" (__LINE__), \ "i" (flags), \ "i" (sizeof(struct bug_entry))); \ @@ -39,14 +40,15 @@ do { \ #else /* !CONFIG_DEBUG_BUGVERBOSE */ -#define _BUG_FLAGS(ins, flags) \ +#define _BUG_FLAGS(ins, flags, extra) \ do { \ asm_inline volatile("1:\t" ins "\n" \ ".pushsection __bug_table,\"aw\"\n" \ "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \ "\t.word %c0" "\t# bug_entry::flags\n" \ "\t.org 2b+%c1\n" \ - ".popsection" \ + ".popsection\n" \ + extra \ : : "i" (flags), \ "i" (sizeof(struct bug_entry))); \ } while (0) @@ -55,7 +57,7 @@ do { \ #else -#define _BUG_FLAGS(ins, flags) asm volatile(ins) +#define _BUG_FLAGS(ins, flags, extra) asm volatile(ins) #endif /* CONFIG_GENERIC_BUG */ @@ -63,8 +65,8 @@ do { \ #define BUG() \ do { \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, 0); \ - unreachable(); \ + _BUG_FLAGS(ASM_UD2, 0, ""); \ + __builtin_unreachable(); \ } while (0) /* @@ -75,9 +77,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ + __auto_type f = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, BUGFLAG_WARNING|(flags)); \ - annotate_reachable(); \ + _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 429dcebe2b99..0f7fd205ab7e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -117,14 +117,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, */ #define __stringify_label(n) #n -#define __annotate_reachable(c) ({ \ - asm volatile(__stringify_label(c) ":\n\t" \ - ".pushsection .discard.reachable\n\t" \ - ".long " __stringify_label(c) "b - .\n\t" \ - ".popsection\n\t" : : "i" (c)); \ -}) -#define annotate_reachable() __annotate_reachable(__COUNTER__) - #define __annotate_unreachable(c) ({ \ asm volatile(__stringify_label(c) ":\n\t" \ ".pushsection .discard.unreachable\n\t" \ @@ -133,24 +125,21 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, }) #define annotate_unreachable() __annotate_unreachable(__COUNTER__) -#define ASM_UNREACHABLE \ - "999:\n\t" \ - ".pushsection .discard.unreachable\n\t" \ - ".long 999b - .\n\t" \ +#define ASM_REACHABLE \ + "998:\n\t" \ + ".pushsection .discard.reachable\n\t" \ + ".long 998b - .\n\t" \ ".popsection\n\t" /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(".rodata..c_jump_table") #else -#define annotate_reachable() #define annotate_unreachable() +# define ASM_REACHABLE #define __annotate_jump_table #endif -#ifndef ASM_UNREACHABLE -# define ASM_UNREACHABLE -#endif #ifndef unreachable # define unreachable() do { \ annotate_unreachable(); \ -- cgit v1.2.3 From e85c81ba8859a4c839bcd69c5d83b32954133a5b Mon Sep 17 00:00:00 2001 From: Xin Yin Date: Mon, 17 Jan 2022 17:36:54 +0800 Subject: ext4: fast commit may not fallback for ineligible commit For the follow scenario: 1. jbd start commit transaction n 2. task A get new handle for transaction n+1 3. task A do some ineligible actions and mark FC_INELIGIBLE 4. jbd complete transaction n and clean FC_INELIGIBLE 5. task A call fsync In this case fast commit will not fallback to full commit and transaction n+1 also not handled by jbd. Make ext4_fc_mark_ineligible() also record transaction tid for latest ineligible case, when call ext4_fc_cleanup() check current transaction tid, if small than latest ineligible tid do not clear the EXT4_MF_FC_INELIGIBLE. Reported-by: kernel test robot Reported-by: Dan Carpenter Reported-by: Ritesh Harjani Suggested-by: Harshad Shirwadkar Signed-off-by: Xin Yin Link: https://lore.kernel.org/r/20220117093655.35160-2-yinxin.x@bytedance.com Signed-off-by: Theodore Ts'o Cc: stable@kernel.org --- fs/ext4/ext4.h | 3 ++- fs/ext4/extents.c | 4 ++-- fs/ext4/fast_commit.c | 33 +++++++++++++++++++++++++-------- fs/ext4/inode.c | 4 ++-- fs/ext4/ioctl.c | 4 ++-- fs/ext4/namei.c | 4 ++-- fs/ext4/super.c | 1 + fs/ext4/xattr.c | 6 +++--- fs/jbd2/commit.c | 2 +- fs/jbd2/journal.c | 2 +- include/linux/jbd2.h | 2 +- 11 files changed, 42 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 598ecf07652a..d52295becda3 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1749,6 +1749,7 @@ struct ext4_sb_info { spinlock_t s_fc_lock; struct buffer_head *s_fc_bh; struct ext4_fc_stats s_fc_stats; + tid_t s_fc_ineligible_tid; #ifdef CONFIG_EXT4_DEBUG int s_fc_debug_max_replay; #endif @@ -2925,7 +2926,7 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); -void ext4_fc_mark_ineligible(struct super_block *sb, int reason); +void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle); void ext4_fc_start_update(struct inode *inode); void ext4_fc_stop_update(struct inode *inode); void ext4_fc_del(struct inode *inode); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 5dd13108d4b7..3ce4fc250b0d 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -5336,7 +5336,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) ret = PTR_ERR(handle); goto out_mmap; } - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode, 0); @@ -5476,7 +5476,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) ret = PTR_ERR(handle); goto out_mmap; } - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 1abe78b8d84f..e031afee42de 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -300,18 +300,32 @@ restart: } /* - * Mark file system as fast commit ineligible. This means that next commit - * operation would result in a full jbd2 commit. + * Mark file system as fast commit ineligible, and record latest + * ineligible transaction tid. This means until the recorded + * transaction, commit operation would result in a full jbd2 commit. */ -void ext4_fc_mark_ineligible(struct super_block *sb, int reason) +void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle) { struct ext4_sb_info *sbi = EXT4_SB(sb); + tid_t tid; if (!test_opt2(sb, JOURNAL_FAST_COMMIT) || (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)) return; ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + if (handle && !IS_ERR(handle)) + tid = handle->h_transaction->t_tid; + else { + read_lock(&sbi->s_journal->j_state_lock); + tid = sbi->s_journal->j_running_transaction ? + sbi->s_journal->j_running_transaction->t_tid : 0; + read_unlock(&sbi->s_journal->j_state_lock); + } + spin_lock(&sbi->s_fc_lock); + if (sbi->s_fc_ineligible_tid < tid) + sbi->s_fc_ineligible_tid = tid; + spin_unlock(&sbi->s_fc_lock); WARN_ON(reason >= EXT4_FC_REASON_MAX); sbi->s_fc_stats.fc_ineligible_reason_count[reason]++; } @@ -387,7 +401,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) mutex_unlock(&ei->i_fc_lock); node = kmem_cache_alloc(ext4_fc_dentry_cachep, GFP_NOFS); if (!node) { - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -400,7 +414,7 @@ static int __track_dentry_update(struct inode *inode, void *arg, bool update) if (!node->fcd_name.name) { kmem_cache_free(ext4_fc_dentry_cachep, node); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_NOMEM); + EXT4_FC_REASON_NOMEM, NULL); mutex_lock(&ei->i_fc_lock); return -ENOMEM; } @@ -502,7 +516,7 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode) if (ext4_should_journal_data(inode)) { ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_INODE_JOURNAL_DATA); + EXT4_FC_REASON_INODE_JOURNAL_DATA, handle); return; } @@ -1179,7 +1193,7 @@ fallback: * Fast commit cleanup routine. This is called after every fast commit and * full commit. full is true if we are called after a full commit. */ -static void ext4_fc_cleanup(journal_t *journal, int full) +static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid) { struct super_block *sb = journal->j_private; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1227,7 +1241,10 @@ static void ext4_fc_cleanup(journal_t *journal, int full) &sbi->s_fc_q[FC_Q_MAIN]); ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); - ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + if (tid >= sbi->s_fc_ineligible_tid) { + sbi->s_fc_ineligible_tid = 0; + ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); + } if (full) sbi->s_fc_bytes = 0; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9dbeb772de60..f368dd5fd8d5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -337,7 +337,7 @@ stop_handle: return; no_delete: if (!list_empty(&EXT4_I(inode)->i_fc_list)) - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } @@ -5976,7 +5976,7 @@ int ext4_change_inode_journal_flag(struct inode *inode, int val) return PTR_ERR(handle); ext4_fc_mark_ineligible(inode->i_sb, - EXT4_FC_REASON_JOURNAL_FLAG_CHANGE); + EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle); err = ext4_mark_inode_dirty(handle, inode); ext4_handle_sync(handle); ext4_journal_stop(handle); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index bbbedf27b71c..a8022c2c6a58 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -411,7 +411,7 @@ static long swap_inode_boot_loader(struct super_block *sb, err = -EINVAL; goto err_out; } - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); @@ -1373,7 +1373,7 @@ mext_out: err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { - ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE); + ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 52c9bd154122..47b9f87dbc6f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3889,7 +3889,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, * dirents in directories. */ ext4_fc_mark_ineligible(old.inode->i_sb, - EXT4_FC_REASON_RENAME_DIR); + EXT4_FC_REASON_RENAME_DIR, handle); } else { if (new.inode) ext4_fc_track_unlink(handle, new.dentry); @@ -4049,7 +4049,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, if (unlikely(retval)) goto end_rename; ext4_fc_mark_ineligible(new.inode->i_sb, - EXT4_FC_REASON_CROSS_RENAME); + EXT4_FC_REASON_CROSS_RENAME, handle); if (old.dir_bh) { retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino); if (retval) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9a936ecbaa3b..6930b7737ce4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5084,6 +5084,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb) sbi->s_fc_bytes = 0; ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE); ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING); + sbi->s_fc_ineligible_tid = 0; spin_lock_init(&sbi->s_fc_lock); memset(&sbi->s_fc_stats, 0, sizeof(sbi->s_fc_stats)); sbi->s_fc_replay_state.fc_regions = NULL; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 1e0fc1ed845b..042325349098 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -2408,7 +2408,7 @@ retry_inode: if (IS_SYNC(inode)) ext4_handle_sync(handle); } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); cleanup: brelse(is.iloc.bh); @@ -2486,7 +2486,7 @@ retry: if (error == 0) error = error2; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, NULL); return error; } @@ -2920,7 +2920,7 @@ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, error); goto cleanup; } - ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR); + ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); } error = 0; cleanup: diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 3cc4ab2ba7f4..d188fa913a07 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -1170,7 +1170,7 @@ restart_loop: if (journal->j_commit_callback) journal->j_commit_callback(journal, commit_transaction); if (journal->j_fc_cleanup_callback) - journal->j_fc_cleanup_callback(journal, 1); + journal->j_fc_cleanup_callback(journal, 1, commit_transaction->t_tid); trace_jbd2_end_commit(journal, commit_transaction); jbd_debug(1, "JBD2: commit %d complete, head %d\n", diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 0b86a4365b66..a8e64ad11ae3 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -771,7 +771,7 @@ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) { jbd2_journal_unlock_updates(journal); if (journal->j_fc_cleanup_callback) - journal->j_fc_cleanup_callback(journal, 0); + journal->j_fc_cleanup_callback(journal, 0, tid); write_lock(&journal->j_state_lock); journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; if (fallback) diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index fd933c45281a..d63b8106796e 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1295,7 +1295,7 @@ struct journal_s * Clean-up after fast commit or full commit. JBD2 calls this function * after every commit operation. */ - void (*j_fc_cleanup_callback)(struct journal_s *journal, int); + void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); /** * @j_fc_replay_callback: -- cgit v1.2.3 From 3ca40c0d329113a9f76f6aa01abe73d9f16ace9d Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Mon, 17 Jan 2022 17:41:50 +0530 Subject: jbd2: cleanup unused functions declarations from jbd2.h During code review found no references of few of these below function declarations. This patch cleans those up from jbd2.h Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/30d1fc327becda197a4136cf9cdc73d9baa3b7b9.1642416995.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- include/linux/jbd2.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d63b8106796e..afc5572e7b8a 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1419,9 +1419,7 @@ extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); @@ -1486,9 +1484,6 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct buffer_head **bh_out, sector_t blocknr); -/* Transaction locking */ -extern void __wait_on_journal (journal_t *); - /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); extern int __init jbd2_journal_init_transaction_cache(void); @@ -1774,8 +1769,6 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -extern int jbd_blocks_per_page(struct inode *inode); - /* JBD uses a CRC32 checksum */ #define JBD_MAX_CHECKSUM_SIZE 4 -- cgit v1.2.3 From 4f98186848707f530669238d90e0562d92a78aab Mon Sep 17 00:00:00 2001 From: Ritesh Harjani Date: Mon, 17 Jan 2022 17:41:51 +0530 Subject: jbd2: refactor wait logic for transaction updates into a common function No functionality change as such in this patch. This only refactors the common piece of code which waits for t_updates to finish into a common function named as jbd2_journal_wait_updates(journal_t *) Signed-off-by: Ritesh Harjani Reviewed-by: Jan Kara Link: https://lore.kernel.org/r/8c564f70f4b2591171677a2a74fccb22a7b6c3a4.1642416995.git.riteshh@linux.ibm.com Signed-off-by: Theodore Ts'o --- fs/jbd2/commit.c | 19 +++--------------- fs/jbd2/transaction.c | 53 +++++++++++++++++++++++++++++++-------------------- include/linux/jbd2.h | 4 +++- 3 files changed, 38 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index d188fa913a07..5b9408e3b370 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -484,22 +484,9 @@ void jbd2_journal_commit_transaction(journal_t *journal) stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, stats.run.rs_locked); - spin_lock(&commit_transaction->t_handle_lock); - while (atomic_read(&commit_transaction->t_updates)) { - DEFINE_WAIT(wait); + // waits for any t_updates to finish + jbd2_journal_wait_updates(journal); - prepare_to_wait(&journal->j_wait_updates, &wait, - TASK_UNINTERRUPTIBLE); - if (atomic_read(&commit_transaction->t_updates)) { - spin_unlock(&commit_transaction->t_handle_lock); - write_unlock(&journal->j_state_lock); - schedule(); - write_lock(&journal->j_state_lock); - spin_lock(&commit_transaction->t_handle_lock); - } - finish_wait(&journal->j_wait_updates, &wait); - } - spin_unlock(&commit_transaction->t_handle_lock); commit_transaction->t_state = T_SWITCH; write_unlock(&journal->j_state_lock); @@ -817,7 +804,7 @@ start_journal_io: commit_transaction->t_state = T_COMMIT_DFLUSH; write_unlock(&journal->j_state_lock); - /* + /* * If the journal is not located on the file system device, * then we must flush the file system device before we issue * the commit record diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 6a3caedd2285..8e2f8275a253 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -449,7 +449,7 @@ repeat: } /* OK, account for the buffers that this operation expects to - * use and add the handle to the running transaction. + * use and add the handle to the running transaction. */ update_t_max_wait(transaction, ts); handle->h_transaction = transaction; @@ -836,6 +836,35 @@ int jbd2_journal_restart(handle_t *handle, int nblocks) } EXPORT_SYMBOL(jbd2_journal_restart); +/* + * Waits for any outstanding t_updates to finish. + * This is called with write j_state_lock held. + */ +void jbd2_journal_wait_updates(journal_t *journal) +{ + transaction_t *commit_transaction = journal->j_running_transaction; + + if (!commit_transaction) + return; + + spin_lock(&commit_transaction->t_handle_lock); + while (atomic_read(&commit_transaction->t_updates)) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_wait_updates, &wait, + TASK_UNINTERRUPTIBLE); + if (atomic_read(&commit_transaction->t_updates)) { + spin_unlock(&commit_transaction->t_handle_lock); + write_unlock(&journal->j_state_lock); + schedule(); + write_lock(&journal->j_state_lock); + spin_lock(&commit_transaction->t_handle_lock); + } + finish_wait(&journal->j_wait_updates, &wait); + } + spin_unlock(&commit_transaction->t_handle_lock); +} + /** * jbd2_journal_lock_updates () - establish a transaction barrier. * @journal: Journal to establish a barrier on. @@ -863,27 +892,9 @@ void jbd2_journal_lock_updates(journal_t *journal) write_lock(&journal->j_state_lock); } - /* Wait until there are no running updates */ - while (1) { - transaction_t *transaction = journal->j_running_transaction; - - if (!transaction) - break; + /* Wait until there are no running t_updates */ + jbd2_journal_wait_updates(journal); - spin_lock(&transaction->t_handle_lock); - prepare_to_wait(&journal->j_wait_updates, &wait, - TASK_UNINTERRUPTIBLE); - if (!atomic_read(&transaction->t_updates)) { - spin_unlock(&transaction->t_handle_lock); - finish_wait(&journal->j_wait_updates, &wait); - break; - } - spin_unlock(&transaction->t_handle_lock); - write_unlock(&journal->j_state_lock); - schedule(); - finish_wait(&journal->j_wait_updates, &wait); - write_lock(&journal->j_state_lock); - } write_unlock(&journal->j_state_lock); /* diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index afc5572e7b8a..9c3ada74ffb1 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -594,7 +594,7 @@ struct transaction_s */ unsigned long t_log_start; - /* + /* * Number of buffers on the t_buffers list [j_list_lock, no locks * needed for jbd2 thread] */ @@ -1538,6 +1538,8 @@ extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); +void jbd2_journal_wait_updates(journal_t *); + extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); -- cgit v1.2.3 From 67d6212afda218d564890d1674bab28e8612170f Mon Sep 17 00:00:00 2001 From: Igor Pylypiv Date: Thu, 27 Jan 2022 15:39:53 -0800 Subject: Revert "module, async: async_synchronize_full() on module init iff async is used" This reverts commit 774a1221e862b343388347bac9b318767336b20b. We need to finish all async code before the module init sequence is done. In the reverted commit the PF_USED_ASYNC flag was added to mark a thread that called async_schedule(). Then the PF_USED_ASYNC flag was used to determine whether or not async_synchronize_full() needs to be invoked. This works when modprobe thread is calling async_schedule(), but it does not work if module dispatches init code to a worker thread which then calls async_schedule(). For example, PCI driver probing is invoked from a worker thread based on a node where device is attached: if (cpu < nr_cpu_ids) error = work_on_cpu(cpu, local_pci_probe, &ddi); else error = local_pci_probe(&ddi); We end up in a situation where a worker thread gets the PF_USED_ASYNC flag set instead of the modprobe thread. As a result, async_synchronize_full() is not invoked and modprobe completes without waiting for the async code to finish. The issue was discovered while loading the pm80xx driver: (scsi_mod.scan=async) modprobe pm80xx worker ... do_init_module() ... pci_call_probe() work_on_cpu(local_pci_probe) local_pci_probe() pm8001_pci_probe() scsi_scan_host() async_schedule() worker->flags |= PF_USED_ASYNC; ... < return from worker > ... if (current->flags & PF_USED_ASYNC) <--- false async_synchronize_full(); Commit 21c3c5d28007 ("block: don't request module during elevator init") fixed the deadlock issue which the reverted commit 774a1221e862 ("module, async: async_synchronize_full() on module init iff async is used") tried to fix. Since commit 0fdff3ec6d87 ("async, kmod: warn on synchronous request_module() from async workers") synchronous module loading from async is not allowed. Given that the original deadlock issue is fixed and it is no longer allowed to call synchronous request_module() from async we can remove PF_USED_ASYNC flag to make module init consistently invoke async_synchronize_full() unless async module probe is requested. Signed-off-by: Igor Pylypiv Reviewed-by: Changyuan Lyu Reviewed-by: Luis Chamberlain Acked-by: Tejun Heo Signed-off-by: Linus Torvalds --- include/linux/sched.h | 1 - kernel/async.c | 3 --- kernel/module.c | 25 +++++-------------------- 3 files changed, 5 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index f5b2be39a78c..75ba8aa60248 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1680,7 +1680,6 @@ extern struct pid *cad_pid; #define PF_MEMALLOC 0x00000800 /* Allocating memory */ #define PF_NPROC_EXCEEDED 0x00001000 /* set_user() noticed that RLIMIT_NPROC was exceeded */ #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ -#define PF_USED_ASYNC 0x00004000 /* Used async_schedule*(), used by module init */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ #define PF_FROZEN 0x00010000 /* Frozen for system suspend */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ diff --git a/kernel/async.c b/kernel/async.c index b8d7a663497f..b2c4ba5686ee 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -205,9 +205,6 @@ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); - /* mark that this task has queued an async job, used by module init */ - current->flags |= PF_USED_ASYNC; - /* schedule for execution */ queue_work_node(node, system_unbound_wq, &entry->work); diff --git a/kernel/module.c b/kernel/module.c index 24dab046e16c..46a5c2ed1928 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3725,12 +3725,6 @@ static noinline int do_init_module(struct module *mod) } freeinit->module_init = mod->init_layout.base; - /* - * We want to find out whether @mod uses async during init. Clear - * PF_USED_ASYNC. async_schedule*() will set it. - */ - current->flags &= ~PF_USED_ASYNC; - do_mod_ctors(mod); /* Start the module */ if (mod->init != NULL) @@ -3756,22 +3750,13 @@ static noinline int do_init_module(struct module *mod) /* * We need to finish all async code before the module init sequence - * is done. This has potential to deadlock. For example, a newly - * detected block device can trigger request_module() of the - * default iosched from async probing task. Once userland helper - * reaches here, async_synchronize_full() will wait on the async - * task waiting on request_module() and deadlock. - * - * This deadlock is avoided by perfomring async_synchronize_full() - * iff module init queued any async jobs. This isn't a full - * solution as it will deadlock the same if module loading from - * async jobs nests more than once; however, due to the various - * constraints, this hack seems to be the best option for now. - * Please refer to the following thread for details. + * is done. This has potential to deadlock if synchronous module + * loading is requested from async (which is not allowed!). * - * http://thread.gmane.org/gmane.linux.kernel/1420814 + * See commit 0fdff3ec6d87 ("async, kmod: warn on synchronous + * request_module() from async workers") for more details. */ - if (!mod->async_probe_requested && (current->flags & PF_USED_ASYNC)) + if (!mod->async_probe_requested) async_synchronize_full(); ftrace_free_mem(mod, mod->init_layout.base, mod->init_layout.base + -- cgit v1.2.3 From ac9f0c810684a1b161c18eb4b91ce84cbc13c91d Mon Sep 17 00:00:00 2001 From: Anton Lundin Date: Thu, 3 Feb 2022 10:41:35 +0100 Subject: ata: libata-core: Introduce ATA_HORKAGE_NO_LOG_DIR horkage 06f6c4c6c3e8 ("ata: libata: add missing ata_identify_page_supported() calls") introduced additional calls to ata_identify_page_supported(), thus also adding indirectly accesses to the device log directory log page through ata_log_supported(). Reading this log page causes SATADOM-ML 3ME devices to lock up. Introduce the horkage flag ATA_HORKAGE_NO_LOG_DIR to prevent accesses to the log directory in ata_log_supported() and add a blacklist entry with this flag for "SATADOM-ML 3ME" devices. Fixes: 636f6e2af4fb ("libata: add horkage for missing Identify Device log") Cc: stable@vger.kernel.org # v5.10+ Signed-off-by: Anton Lundin Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 10 ++++++++++ include/linux/libata.h | 1 + 2 files changed, 11 insertions(+) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 67f88027680a..e1b1dd215267 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2007,6 +2007,9 @@ static bool ata_log_supported(struct ata_device *dev, u8 log) { struct ata_port *ap = dev->link->ap; + if (dev->horkage & ATA_HORKAGE_NO_LOG_DIR) + return false; + if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) return false; return get_unaligned_le16(&ap->sector_buf[log * 2]) ? true : false; @@ -4073,6 +4076,13 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "WDC WD3000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD3200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, + /* + * This sata dom device goes on a walkabout when the ATA_LOG_DIRECTORY + * log page is accessed. Ensure we never ask for this log page with + * these devices. + */ + { "SATADOM-ML 3ME", NULL, ATA_HORKAGE_NO_LOG_DIR }, + /* End Marker */ { } }; diff --git a/include/linux/libata.h b/include/linux/libata.h index 605756f645be..7f99b4d78822 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -380,6 +380,7 @@ enum { ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27), /* Disable NCQ on ATI chipset */ ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28), /* Identify device log missing */ + ATA_HORKAGE_NO_LOG_DIR = (1 << 29), /* Do not read log directory */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.3 From 80110bbfbba6f0078d5a1cbc8df004506db8ffe5 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin Date: Thu, 3 Feb 2022 20:49:24 -0800 Subject: mm/page_table_check: check entries at pmd levels syzbot detected a case where the page table counters were not properly updated. syzkaller login: ------------[ cut here ]------------ kernel BUG at mm/page_table_check.c:162! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 3099 Comm: pasha Not tainted 5.16.0+ #48 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIO4 RIP: 0010:__page_table_check_zero+0x159/0x1a0 Call Trace: free_pcp_prepare+0x3be/0xaa0 free_unref_page+0x1c/0x650 free_compound_page+0xec/0x130 free_transhuge_page+0x1be/0x260 __put_compound_page+0x90/0xd0 release_pages+0x54c/0x1060 __pagevec_release+0x7c/0x110 shmem_undo_range+0x85e/0x1250 ... The repro involved having a huge page that is split due to uprobe event temporarily replacing one of the pages in the huge page. Later the huge page was combined again, but the counters were off, as the PTE level was not properly updated. Make sure that when PMD is cleared and prior to freeing the level the PTEs are updated. Link: https://lkml.kernel.org/r/20220131203249.2832273-5-pasha.tatashin@soleen.com Fixes: df4e817b7108 ("mm: page table check") Signed-off-by: Pasha Tatashin Acked-by: David Rientjes Cc: Aneesh Kumar K.V Cc: Anshuman Khandual Cc: Dave Hansen Cc: Greg Thelen Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: Jiri Slaby Cc: Mike Rapoport Cc: Muchun Song Cc: Paul Turner Cc: Wei Xu Cc: Will Deacon Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_table_check.h | 19 +++++++++++++++++++ mm/khugepaged.c | 3 +++ mm/page_table_check.c | 20 ++++++++++++++++++++ 3 files changed, 42 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h index 38cace1da7b6..01e16c7696ec 100644 --- a/include/linux/page_table_check.h +++ b/include/linux/page_table_check.h @@ -26,6 +26,9 @@ void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd); void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud); +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd); static inline void page_table_check_alloc(struct page *page, unsigned int order) { @@ -100,6 +103,16 @@ static inline void page_table_check_pud_set(struct mm_struct *mm, __page_table_check_pud_set(mm, addr, pudp, pud); } +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (static_branch_likely(&page_table_check_disabled)) + return; + + __page_table_check_pte_clear_range(mm, addr, pmd); +} + #else static inline void page_table_check_alloc(struct page *page, unsigned int order) @@ -143,5 +156,11 @@ static inline void page_table_check_pud_set(struct mm_struct *mm, { } +static inline void page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ +} + #endif /* CONFIG_PAGE_TABLE_CHECK */ #endif /* __LINUX_PAGE_TABLE_CHECK_H */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 30e59e4af272..131492fd1148 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include @@ -1422,10 +1423,12 @@ static void collapse_and_free_pmd(struct mm_struct *mm, struct vm_area_struct *v spinlock_t *ptl; pmd_t pmd; + mmap_assert_write_locked(mm); ptl = pmd_lock(vma->vm_mm, pmdp); pmd = pmdp_collapse_flush(vma, addr, pmdp); spin_unlock(ptl); mm_dec_nr_ptes(mm); + page_table_check_pte_clear_range(mm, addr, pmd); pte_free(mm, pmd_pgtable(pmd)); } diff --git a/mm/page_table_check.c b/mm/page_table_check.c index c61d7ebe13b1..3763bd077861 100644 --- a/mm/page_table_check.c +++ b/mm/page_table_check.c @@ -247,3 +247,23 @@ void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr, } } EXPORT_SYMBOL(__page_table_check_pud_set); + +void __page_table_check_pte_clear_range(struct mm_struct *mm, + unsigned long addr, + pmd_t pmd) +{ + if (&init_mm == mm) + return; + + if (!pmd_bad(pmd) && !pmd_leaf(pmd)) { + pte_t *ptep = pte_offset_map(&pmd, addr); + unsigned long i; + + pte_unmap(ptep); + for (i = 0; i < PTRS_PER_PTE; i++) { + __page_table_check_pte_clear(mm, addr, *ptep); + addr += PAGE_SIZE; + ptep++; + } + } +} -- cgit v1.2.3 From 314c459a6fe0957b5885fbc65c53d51444092880 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Thu, 3 Feb 2022 20:49:29 -0800 Subject: mm/pgtable: define pte_index so that preprocessor could recognize it Since commit 974b9b2c68f3 ("mm: consolidate pte_index() and pte_offset_*() definitions") pte_index is a static inline and there is no define for it that can be recognized by the preprocessor. As a result, vm_insert_pages() uses slower loop over vm_insert_page() instead of insert_pages() that amortizes the cost of spinlock operations when inserting multiple pages. Link: https://lkml.kernel.org/r/20220111145457.20748-1-rppt@kernel.org Fixes: 974b9b2c68f3 ("mm: consolidate pte_index() and pte_offset_*() definitions") Signed-off-by: Mike Rapoport Reported-by: Christian Dietrich Reviewed-by: Khalid Aziz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/pgtable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index bc8713a76e03..f4f4077b97aa 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -62,6 +62,7 @@ static inline unsigned long pte_index(unsigned long address) { return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1); } +#define pte_index pte_index #ifndef pmd_index static inline unsigned long pmd_index(unsigned long address) -- cgit v1.2.3 From fda17afc6166e975bec1197bd94cd2a3317bce3f Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Mon, 7 Feb 2022 11:27:53 +0900 Subject: ata: libata-core: Fix ata_dev_config_cpr() The concurrent positioning ranges log page 47h is a general purpose log page and not a subpage of the indentify device log. Using ata_identify_page_supported() to test for concurrent positioning ranges support is thus wrong. ata_log_supported() must be used. Furthermore, unlike other advanced ATA features (e.g. NCQ priority), accesses to the concurrent positioning ranges log page are not gated by a feature bit from the device IDENTIFY data. Since many older drives react badly to the READ LOG EXT and/or READ LOG DMA EXT commands isued to read device log pages, avoid problems with older drives by limiting the concurrent positioning ranges support detection to drives implementing at least the ACS-4 ATA standard (major version 11). This additional condition effectively turns ata_dev_config_cpr() into a nop for older drives, avoiding problems in the field. Fixes: fe22e1c2f705 ("libata: support concurrent positioning ranges log") BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=215519 Cc: stable@vger.kernel.org Reviewed-by: Hannes Reinecke Tested-by: Abderraouf Adjal Signed-off-by: Damien Le Moal --- drivers/ata/libata-core.c | 14 ++++++-------- include/linux/ata.h | 2 +- 2 files changed, 7 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e1b1dd215267..ba9273f80069 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2448,23 +2448,21 @@ static void ata_dev_config_cpr(struct ata_device *dev) struct ata_cpr_log *cpr_log = NULL; u8 *desc, *buf = NULL; - if (!ata_identify_page_supported(dev, - ATA_LOG_CONCURRENT_POSITIONING_RANGES)) + if (ata_id_major_version(dev->id) < 11 || + !ata_log_supported(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES)) goto out; /* - * Read IDENTIFY DEVICE data log, page 0x47 - * (concurrent positioning ranges). We can have at most 255 32B range - * descriptors plus a 64B header. + * Read the concurrent positioning ranges log (0x47). We can have at + * most 255 32B range descriptors plus a 64B header. */ buf_len = (64 + 255 * 32 + 511) & ~511; buf = kzalloc(buf_len, GFP_KERNEL); if (!buf) goto out; - err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, - ATA_LOG_CONCURRENT_POSITIONING_RANGES, - buf, buf_len >> 9); + err_mask = ata_read_log_page(dev, ATA_LOG_CONCURRENT_POSITIONING_RANGES, + 0, buf, buf_len >> 9); if (err_mask) goto out; diff --git a/include/linux/ata.h b/include/linux/ata.h index 199e47e97d64..21292b5bbb55 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -324,12 +324,12 @@ enum { ATA_LOG_NCQ_NON_DATA = 0x12, ATA_LOG_NCQ_SEND_RECV = 0x13, ATA_LOG_IDENTIFY_DEVICE = 0x30, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device log pages: */ ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, - ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, -- cgit v1.2.3 From cb1f65c1e1424a4b5e4a86da8aa3b8fd8459c8ec Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 4 Feb 2022 18:35:22 +0100 Subject: PM: s2idle: ACPI: Fix wakeup interrupts handling After commit e3728b50cd9b ("ACPI: PM: s2idle: Avoid possible race related to the EC GPE") wakeup interrupts occurring immediately after the one discarded by acpi_s2idle_wake() may be missed. Moreover, if the SCI triggers again immediately after the rearming in acpi_s2idle_wake(), that wakeup may be missed too. The problem is that pm_system_irq_wakeup() only calls pm_system_wakeup() when pm_wakeup_irq is 0, but that's not the case any more after the interrupt causing acpi_s2idle_wake() to run until pm_wakeup_irq is cleared by the pm_wakeup_clear() call in s2idle_loop(). However, there may be wakeup interrupts occurring in that time frame and if that happens, they will be missed. To address that issue first move the clearing of pm_wakeup_irq to the point at which it is known that the interrupt causing acpi_s2idle_wake() to tun will be discarded, before rearming the SCI for wakeup. Moreover, because that only reduces the size of the time window in which the issue may manifest itself, allow pm_system_irq_wakeup() to register two second wakeup interrupts in a row and, when discarding the first one, replace it with the second one. [Of course, this assumes that only one wakeup interrupt can be discarded in one go, but currently that is the case and I am not aware of any plans to change that.] Fixes: e3728b50cd9b ("ACPI: PM: s2idle: Avoid possible race related to the EC GPE") Cc: 5.4+ # 5.4+ Signed-off-by: Rafael J. Wysocki --- drivers/acpi/sleep.c | 1 + drivers/base/power/wakeup.c | 41 ++++++++++++++++++++++++++++++++++------- include/linux/suspend.h | 4 ++-- kernel/power/main.c | 5 ++++- kernel/power/process.c | 2 +- kernel/power/suspend.c | 2 -- 6 files changed, 42 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index fac7c9d4c9a1..d4fbea91ab6b 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -758,6 +758,7 @@ bool acpi_s2idle_wake(void) return true; } + pm_wakeup_clear(acpi_sci_irq); rearm_wake_irq(acpi_sci_irq); } diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 99bda0da23a8..8666590201c9 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -34,7 +34,8 @@ suspend_state_t pm_suspend_target_state; bool events_check_enabled __read_mostly; /* First wakeup IRQ seen by the kernel in the last cycle. */ -unsigned int pm_wakeup_irq __read_mostly; +static unsigned int wakeup_irq[2] __read_mostly; +static DEFINE_RAW_SPINLOCK(wakeup_irq_lock); /* If greater than 0 and the system is suspending, terminate the suspend. */ static atomic_t pm_abort_suspend __read_mostly; @@ -942,19 +943,45 @@ void pm_system_cancel_wakeup(void) atomic_dec_if_positive(&pm_abort_suspend); } -void pm_wakeup_clear(bool reset) +void pm_wakeup_clear(unsigned int irq_number) { - pm_wakeup_irq = 0; - if (reset) + raw_spin_lock_irq(&wakeup_irq_lock); + + if (irq_number && wakeup_irq[0] == irq_number) + wakeup_irq[0] = wakeup_irq[1]; + else + wakeup_irq[0] = 0; + + wakeup_irq[1] = 0; + + raw_spin_unlock_irq(&wakeup_irq_lock); + + if (!irq_number) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { - if (pm_wakeup_irq == 0) { - pm_wakeup_irq = irq_number; + unsigned long flags; + + raw_spin_lock_irqsave(&wakeup_irq_lock, flags); + + if (wakeup_irq[0] == 0) + wakeup_irq[0] = irq_number; + else if (wakeup_irq[1] == 0) + wakeup_irq[1] = irq_number; + else + irq_number = 0; + + raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags); + + if (irq_number) pm_system_wakeup(); - } +} + +unsigned int pm_wakeup_irq(void) +{ + return wakeup_irq[0]; } /** diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 3e8ecdebe601..300273ff40cc 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -497,14 +497,14 @@ extern void ksys_sync_helper(void); /* drivers/base/power/wakeup.c */ extern bool events_check_enabled; -extern unsigned int pm_wakeup_irq; extern suspend_state_t pm_suspend_target_state; extern bool pm_wakeup_pending(void); extern void pm_system_wakeup(void); extern void pm_system_cancel_wakeup(void); -extern void pm_wakeup_clear(bool reset); +extern void pm_wakeup_clear(unsigned int irq_number); extern void pm_system_irq_wakeup(unsigned int irq_number); +extern unsigned int pm_wakeup_irq(void); extern bool pm_get_wakeup_count(unsigned int *count, bool block); extern bool pm_save_wakeup_count(unsigned int count); extern void pm_wakep_autosleep_enabled(bool set); diff --git a/kernel/power/main.c b/kernel/power/main.c index 44169f3081fd..7e646079fbeb 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -504,7 +504,10 @@ static ssize_t pm_wakeup_irq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - return pm_wakeup_irq ? sprintf(buf, "%u\n", pm_wakeup_irq) : -ENODATA; + if (!pm_wakeup_irq()) + return -ENODATA; + + return sprintf(buf, "%u\n", pm_wakeup_irq()); } power_attr_ro(pm_wakeup_irq); diff --git a/kernel/power/process.c b/kernel/power/process.c index b7e7798637b8..11b570fcf049 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -134,7 +134,7 @@ int freeze_processes(void) if (!pm_freezing) atomic_inc(&system_freezing_cnt); - pm_wakeup_clear(true); + pm_wakeup_clear(0); pr_info("Freezing user space processes ... "); pm_freezing = true; error = try_to_freeze_tasks(true); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 80cc1f0f502b..6fcdee7e87a5 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -136,8 +136,6 @@ static void s2idle_loop(void) break; } - pm_wakeup_clear(false); - s2idle_enter(); } -- cgit v1.2.3 From c306d737691ef84305d4ed0d302c63db2932f0bb Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Tue, 25 Jan 2022 15:57:45 -0500 Subject: NFSD: Deprecate NFS_OFFSET_MAX NFS_OFFSET_MAX was introduced way back in Linux v2.3.y before there was a kernel-wide OFFSET_MAX value. As a clean up, replace the last few uses of it with its generic equivalent, and get rid of it. Signed-off-by: Chuck Lever --- fs/nfsd/nfs3xdr.c | 2 +- fs/nfsd/nfs4xdr.c | 2 +- include/linux/nfs.h | 8 -------- 3 files changed, 2 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 2e47a07029f1..0293b8d65f10 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -1060,7 +1060,7 @@ svcxdr_encode_entry3_common(struct nfsd3_readdirres *resp, const char *name, return false; /* cookie */ resp->cookie_offset = dirlist->len; - if (xdr_stream_encode_u64(xdr, NFS_OFFSET_MAX) < 0) + if (xdr_stream_encode_u64(xdr, OFFSET_MAX) < 0) return false; return true; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index f5e3430bb6ff..714a3a3bd50c 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3495,7 +3495,7 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, p = xdr_reserve_space(xdr, 3*4 + namlen); if (!p) goto fail; - p = xdr_encode_hyper(p, NFS_OFFSET_MAX); /* offset of next entry */ + p = xdr_encode_hyper(p, OFFSET_MAX); /* offset of next entry */ p = xdr_encode_array(p, name, namlen); /* name length & name */ nfserr = nfsd4_encode_dirent_fattr(xdr, cd, name, namlen); diff --git a/include/linux/nfs.h b/include/linux/nfs.h index 0dc7ad38a0da..b06375e88e58 100644 --- a/include/linux/nfs.h +++ b/include/linux/nfs.h @@ -36,14 +36,6 @@ static inline void nfs_copy_fh(struct nfs_fh *target, const struct nfs_fh *sourc memcpy(target->data, source->data, source->size); } - -/* - * This is really a general kernel constant, but since nothing like - * this is defined in the kernel headers, I have to do it here. - */ -#define NFS_OFFSET_MAX ((__s64)((~(__u64)0) >> 1)) - - enum nfs3_stable_how { NFS_UNSTABLE = 0, NFS_DATA_SYNC = 1, -- cgit v1.2.3 From 0764db9b49c932b89ee4d9e3236dff4bb07b4a66 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 11 Feb 2022 16:32:32 -0800 Subject: mm: memcg: synchronize objcg lists with a dedicated spinlock Alexander reported a circular lock dependency revealed by the mmap1 ltp test: LOCKDEP_CIRCULAR (suite: ltp, case: mtest06 (mmap1)) WARNING: possible circular locking dependency detected 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Not tainted ------------------------------------------------------ mmap1/202299 is trying to acquire lock: 00000001892c0188 (css_set_lock){..-.}-{2:2}, at: obj_cgroup_release+0x4a/0xe0 but task is already holding lock: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sighand->siglock){-.-.}-{2:2}: __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 __lock_task_sighand+0x90/0x190 cgroup_freeze_task+0x2e/0x90 cgroup_migrate_execute+0x11c/0x608 cgroup_update_dfl_csses+0x246/0x270 cgroup_subtree_control_write+0x238/0x518 kernfs_fop_write_iter+0x13e/0x1e0 new_sync_write+0x100/0x190 vfs_write+0x22c/0x2d8 ksys_write+0x6c/0xf8 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #0 (css_set_lock){..-.}-{2:2}: check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sighand->siglock); lock(css_set_lock); lock(&sighand->siglock); lock(css_set_lock); *** DEADLOCK *** 2 locks held by mmap1/202299: #0: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 #1: 00000001892ad560 (rcu_read_lock){....}-{1:2}, at: percpu_ref_put_many.constprop.0+0x0/0x168 stack backtrace: CPU: 15 PID: 202299 Comm: mmap1 Not tainted 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Hardware name: IBM 3906 M04 704 (LPAR) Call Trace: dump_stack_lvl+0x76/0x98 check_noncircular+0x136/0x158 check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 INFO: lockdep is turned off. In this example a slab allocation from __send_signal() caused a refilling and draining of a percpu objcg stock, resulted in a releasing of another non-related objcg. Objcg release path requires taking the css_set_lock, which is used to synchronize objcg lists. This can create a circular dependency with the sighandler lock, which is taken with the locked css_set_lock by the freezer code (to freeze a task). In general it seems that using css_set_lock to synchronize objcg lists makes any slab allocations and deallocation with the locked css_set_lock and any intervened locks risky. To fix the problem and make the code more robust let's stop using css_set_lock to synchronize objcg lists and use a new dedicated spinlock instead. Link: https://lkml.kernel.org/r/Yfm1IHmoGdyUR81T@carbon.dhcp.thefacebook.com Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API") Signed-off-by: Roman Gushchin Reported-by: Alexander Egorenkov Tested-by: Alexander Egorenkov Reviewed-by: Waiman Long Acked-by: Tejun Heo Reviewed-by: Shakeel Butt Reviewed-by: Jeremy Linton Tested-by: Jeremy Linton Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- mm/memcontrol.c | 10 +++++----- 2 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b72d75141e12..0abbd685703b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -219,7 +219,7 @@ struct obj_cgroup { struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { - struct list_head list; + struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; @@ -315,7 +315,8 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; struct obj_cgroup __rcu *objcg; - struct list_head objcg_list; /* list of inherited objcgs */ + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif MEMCG_PADDING(_pad2_); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 09d342c7cbd0..36e9f38c919d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -254,7 +254,7 @@ struct mem_cgroup *vmpressure_to_memcg(struct vmpressure *vmpr) } #ifdef CONFIG_MEMCG_KMEM -extern spinlock_t css_set_lock; +static DEFINE_SPINLOCK(objcg_lock); bool mem_cgroup_kmem_disabled(void) { @@ -298,9 +298,9 @@ static void obj_cgroup_release(struct percpu_ref *ref) if (nr_pages) obj_cgroup_uncharge_pages(objcg, nr_pages); - spin_lock_irqsave(&css_set_lock, flags); + spin_lock_irqsave(&objcg_lock, flags); list_del(&objcg->list); - spin_unlock_irqrestore(&css_set_lock, flags); + spin_unlock_irqrestore(&objcg_lock, flags); percpu_ref_exit(ref); kfree_rcu(objcg, rcu); @@ -332,7 +332,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, objcg = rcu_replace_pointer(memcg->objcg, NULL, true); - spin_lock_irq(&css_set_lock); + spin_lock_irq(&objcg_lock); /* 1) Ready to reparent active objcg. */ list_add(&objcg->list, &memcg->objcg_list); @@ -342,7 +342,7 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, /* 3) Move already reparented objcgs to the parent's list */ list_splice(&memcg->objcg_list, &parent->objcg_list); - spin_unlock_irq(&css_set_lock); + spin_unlock_irq(&objcg_lock); percpu_ref_kill(&objcg->refcnt); } -- cgit v1.2.3 From 8913c61001482378d4ed8cc577b17c1ba3e847e4 Mon Sep 17 00:00:00 2001 From: Peng Liu Date: Fri, 11 Feb 2022 16:32:35 -0800 Subject: kfence: make test case compatible with run time set sample interval The parameter kfence_sample_interval can be set via boot parameter and late shell command, which is convenient for automated tests and KFENCE parameter optimization. However, KFENCE test case just uses compile-time CONFIG_KFENCE_SAMPLE_INTERVAL, which will make KFENCE test case not run as users desired. Export kfence_sample_interval, so that KFENCE test case can use run-time-set sample interval. Link: https://lkml.kernel.org/r/20220207034432.185532-1-liupeng256@huawei.com Signed-off-by: Peng Liu Reviewed-by: Marco Elver Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: Jonathan Corbet Cc: Sumit Semwal Cc: Christian Knig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kfence.h | 2 ++ mm/kfence/core.c | 3 ++- mm/kfence/kfence_test.c | 8 ++++---- 3 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kfence.h b/include/linux/kfence.h index 4b5e3679a72c..f49e64222628 100644 --- a/include/linux/kfence.h +++ b/include/linux/kfence.h @@ -17,6 +17,8 @@ #include #include +extern unsigned long kfence_sample_interval; + /* * We allocate an even number of pages, as it simplifies calculations to map * address to metadata indices; effectively, the very first page serves as an diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 5ad40e3add45..13128fa13062 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -47,7 +47,8 @@ static bool kfence_enabled __read_mostly; -static unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; +unsigned long kfence_sample_interval __read_mostly = CONFIG_KFENCE_SAMPLE_INTERVAL; +EXPORT_SYMBOL_GPL(kfence_sample_interval); /* Export for test modules. */ #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c index a22b1af85577..50dbb815a2a8 100644 --- a/mm/kfence/kfence_test.c +++ b/mm/kfence/kfence_test.c @@ -268,13 +268,13 @@ static void *test_alloc(struct kunit *test, size_t size, gfp_t gfp, enum allocat * 100x the sample interval should be more than enough to ensure we get * a KFENCE allocation eventually. */ - timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval); /* * Especially for non-preemption kernels, ensure the allocation-gate * timer can catch up: after @resched_after, every failed allocation * attempt yields, to ensure the allocation-gate timer is scheduled. */ - resched_after = jiffies + msecs_to_jiffies(CONFIG_KFENCE_SAMPLE_INTERVAL); + resched_after = jiffies + msecs_to_jiffies(kfence_sample_interval); do { if (test_cache) alloc = kmem_cache_alloc(test_cache, gfp); @@ -608,7 +608,7 @@ static void test_gfpzero(struct kunit *test) int i; /* Skip if we think it'd take too long. */ - KFENCE_TEST_REQUIRES(test, CONFIG_KFENCE_SAMPLE_INTERVAL <= 100); + KFENCE_TEST_REQUIRES(test, kfence_sample_interval <= 100); setup_test_cache(test, size, 0, NULL); buf1 = test_alloc(test, size, GFP_KERNEL, ALLOCATE_ANY); @@ -739,7 +739,7 @@ static void test_memcache_alloc_bulk(struct kunit *test) * 100x the sample interval should be more than enough to ensure we get * a KFENCE allocation eventually. */ - timeout = jiffies + msecs_to_jiffies(100 * CONFIG_KFENCE_SAMPLE_INTERVAL); + timeout = jiffies + msecs_to_jiffies(100 * kfence_sample_interval); do { void *objects[100]; int i, num = kmem_cache_alloc_bulk(test_cache, GFP_ATOMIC, ARRAY_SIZE(objects), -- cgit v1.2.3